From b238290b965f23ac5f8aeb64cd731aef18aa796c Mon Sep 17 00:00:00 2001
From: Neil Spring <ntspring@fb.com>
Date: Mon, 30 Aug 2021 20:33:56 -0700
Subject: bpf: Permit ingress_ifindex in bpf_prog_test_run_xattr

bpf_prog_test_run_xattr takes a struct __sk_buff, but did not permit
that __skbuff to include an nonzero ingress_ifindex.

This patch updates to allow ingress_ifindex, convert the __sk_buff field to
sk_buff (skb_iif) and back, and tests that the value is present from on BPF
program side. The test sets an unlikely distinct value for ingress_ifindex
(11) from ifindex (1), which is in line with the rest of the synthetic field
tests.

Adding this support allows testing BPF that operates differently on
incoming and outgoing skbs by discriminating on this field.

Signed-off-by: Neil Spring <ntspring@fb.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Acked-by: John Fastabend <john.fastabend@gmail.com>
Link: https://lore.kernel.org/bpf/20210831033356.1459316-1-ntspring@fb.com
---
 tools/testing/selftests/bpf/prog_tests/skb_ctx.c | 5 +++++
 tools/testing/selftests/bpf/progs/test_skb_ctx.c | 4 ++++
 2 files changed, 9 insertions(+)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/prog_tests/skb_ctx.c b/tools/testing/selftests/bpf/prog_tests/skb_ctx.c
index fafeddaad6a9..2bf8c687348b 100644
--- a/tools/testing/selftests/bpf/prog_tests/skb_ctx.c
+++ b/tools/testing/selftests/bpf/prog_tests/skb_ctx.c
@@ -11,6 +11,7 @@ void test_skb_ctx(void)
 		.cb[3] = 4,
 		.cb[4] = 5,
 		.priority = 6,
+		.ingress_ifindex = 11,
 		.ifindex = 1,
 		.tstamp = 7,
 		.wire_len = 100,
@@ -97,6 +98,10 @@ void test_skb_ctx(void)
 		   "ctx_out_ifindex",
 		   "skb->ifindex == %d, expected %d\n",
 		   skb.ifindex, 1);
+	CHECK_ATTR(skb.ingress_ifindex != 11,
+		   "ctx_out_ingress_ifindex",
+		   "skb->ingress_ifindex == %d, expected %d\n",
+		   skb.ingress_ifindex, 11);
 	CHECK_ATTR(skb.tstamp != 8,
 		   "ctx_out_tstamp",
 		   "skb->tstamp == %lld, expected %d\n",
diff --git a/tools/testing/selftests/bpf/progs/test_skb_ctx.c b/tools/testing/selftests/bpf/progs/test_skb_ctx.c
index b02ea589ce7e..bbd5a9c1c4df 100644
--- a/tools/testing/selftests/bpf/progs/test_skb_ctx.c
+++ b/tools/testing/selftests/bpf/progs/test_skb_ctx.c
@@ -25,6 +25,10 @@ int process(struct __sk_buff *skb)
 		return 1;
 	if (skb->gso_size != 10)
 		return 1;
+	if (skb->ingress_ifindex != 11)
+		return 1;
+	if (skb->ifindex != 1)
+		return 1;
 
 	return 0;
 }
-- 
cgit v1.2.3


From 03e601f48b2da6fb44d0f7b86957a8f6bacfb347 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Toke=20H=C3=B8iland-J=C3=B8rgensen?= <toke@redhat.com>
Date: Wed, 1 Sep 2021 13:48:12 +0200
Subject: libbpf: Don't crash on object files with no symbol tables
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

If libbpf encounters an ELF file that has been stripped of its symbol
table, it will crash in bpf_object__add_programs() when trying to
dereference the obj->efile.symbols pointer.

Fix this by erroring out of bpf_object__elf_collect() if it is not able
able to find the symbol table.

v2:
  - Move check into bpf_object__elf_collect() and add nice error message

Fixes: 6245947c1b3c ("libbpf: Allow gaps in BPF program sections to support overriden weak functions")
Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20210901114812.204720-1-toke@redhat.com
---
 tools/lib/bpf/libbpf.c | 6 ++++++
 1 file changed, 6 insertions(+)

(limited to 'tools')

diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 88d8825fc6f6..8f579c6666b2 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -2993,6 +2993,12 @@ static int bpf_object__elf_collect(struct bpf_object *obj)
 		}
 	}
 
+	if (!obj->efile.symbols) {
+		pr_warn("elf: couldn't find symbol table in %s, stripped object file?\n",
+			obj->path);
+		return -ENOENT;
+	}
+
 	scn = NULL;
 	while ((scn = elf_nextscn(elf, scn)) != NULL) {
 		idx++;
-- 
cgit v1.2.3


From 08a6f22ef6f843d0ea7252087787b5ab04610bec Mon Sep 17 00:00:00 2001
From: Matt Smith <alastorze@fb.com>
Date: Wed, 1 Sep 2021 12:44:37 -0700
Subject: libbpf: Change bpf_object_skeleton data field to const pointer

This change was necessary to enforce the implied contract
that bpf_object_skeleton->data should not be mutated.  The data
will be cast to `void *` during assignment to handle the case
where a user is compiling with older libbpf headers to avoid
a compiler warning of `const void *` data being cast to `void *`

Signed-off-by: Matt Smith <alastorze@fb.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20210901194439.3853238-2-alastorze@fb.com
---
 tools/lib/bpf/libbpf.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'tools')

diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h
index f177d897c5f7..2f6f0e15d1e7 100644
--- a/tools/lib/bpf/libbpf.h
+++ b/tools/lib/bpf/libbpf.h
@@ -854,7 +854,7 @@ struct bpf_object_skeleton {
 	size_t sz; /* size of this struct, for forward/backward compatibility */
 
 	const char *name;
-	void *data;
+	const void *data;
 	size_t data_sz;
 
 	struct bpf_object **obj;
-- 
cgit v1.2.3


From a6cc6b34b93e3660149a7cb947be98a9b239ffce Mon Sep 17 00:00:00 2001
From: Matt Smith <alastorze@fb.com>
Date: Wed, 1 Sep 2021 12:44:38 -0700
Subject: bpftool: Provide a helper method for accessing skeleton's embedded
 ELF data

This adds a skeleton method X__elf_bytes() which returns the binary data of
the compiled and embedded BPF object file. It additionally sets the size of
the return data to the provided size_t pointer argument.

The assignment to s->data is cast to void * to ensure no warning is issued if
compiled with a previous version of libbpf where the bpf_object_skeleton field
is void * instead of const void *

Signed-off-by: Matt Smith <alastorze@fb.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20210901194439.3853238-3-alastorze@fb.com
---
 tools/bpf/bpftool/gen.c | 31 +++++++++++++++++++------------
 1 file changed, 19 insertions(+), 12 deletions(-)

(limited to 'tools')

diff --git a/tools/bpf/bpftool/gen.c b/tools/bpf/bpftool/gen.c
index d40d92bbf0e4..e3ec47a6a612 100644
--- a/tools/bpf/bpftool/gen.c
+++ b/tools/bpf/bpftool/gen.c
@@ -238,8 +238,8 @@ static void codegen(const char *template, ...)
 		} else if (c == '\n') {
 			break;
 		} else {
-			p_err("unrecognized character at pos %td in template '%s'",
-			      src - template - 1, template);
+			p_err("unrecognized character at pos %td in template '%s': '%c'",
+			      src - template - 1, template, c);
 			free(s);
 			exit(-1);
 		}
@@ -406,7 +406,7 @@ static void codegen_destroy(struct bpf_object *obj, const char *obj_name)
 	}
 
 	bpf_object__for_each_map(map, obj) {
-		const char * ident;
+		const char *ident;
 
 		ident = get_map_ident(map);
 		if (!ident)
@@ -862,6 +862,8 @@ static int do_skeleton(int argc, char **argv)
 	codegen("\
 		\n\
 									    \n\
+		static inline const void *%1$s__elf_bytes(size_t *sz);	    \n\
+									    \n\
 		static inline int					    \n\
 		%1$s__create_skeleton(struct %1$s *obj)			    \n\
 		{							    \n\
@@ -943,10 +945,20 @@ static int do_skeleton(int argc, char **argv)
 	codegen("\
 		\n\
 									    \n\
-			s->data_sz = %d;				    \n\
-			s->data = (void *)\"\\				    \n\
-		",
-		file_sz);
+			s->data = (void *)%2$s__elf_bytes(&s->data_sz);	    \n\
+									    \n\
+			return 0;					    \n\
+		err:							    \n\
+			bpf_object__destroy_skeleton(s);		    \n\
+			return -ENOMEM;					    \n\
+		}							    \n\
+									    \n\
+		static inline const void *%2$s__elf_bytes(size_t *sz)	    \n\
+		{							    \n\
+			*sz = %1$d;					    \n\
+			return (const void *)\"\\			    \n\
+		"
+		, file_sz, obj_name);
 
 	/* embed contents of BPF object file */
 	print_hex(obj_data, file_sz);
@@ -954,11 +966,6 @@ static int do_skeleton(int argc, char **argv)
 	codegen("\
 		\n\
 		\";							    \n\
-									    \n\
-			return 0;					    \n\
-		err:							    \n\
-			bpf_object__destroy_skeleton(s);		    \n\
-			return -ENOMEM;					    \n\
 		}							    \n\
 									    \n\
 		#endif /* %s */						    \n\
-- 
cgit v1.2.3


From 980a1a4c342f353a62d64174d0a6a9466a741273 Mon Sep 17 00:00:00 2001
From: Matt Smith <alastorze@fb.com>
Date: Wed, 1 Sep 2021 12:44:39 -0700
Subject: selftests/bpf: Add checks for X__elf_bytes() skeleton helper

This patch adds two checks for the X__elf_bytes BPF skeleton helper
method. The first asserts that the pointer returned from the helper
method is valid, the second asserts that the provided size pointer is
set.

Signed-off-by: Matt Smith <alastorze@fb.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20210901194439.3853238-4-alastorze@fb.com
---
 tools/testing/selftests/bpf/prog_tests/skeleton.c | 6 ++++++
 1 file changed, 6 insertions(+)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/prog_tests/skeleton.c b/tools/testing/selftests/bpf/prog_tests/skeleton.c
index f6f130c99b8c..fe1e204a65c6 100644
--- a/tools/testing/selftests/bpf/prog_tests/skeleton.c
+++ b/tools/testing/selftests/bpf/prog_tests/skeleton.c
@@ -18,6 +18,8 @@ void test_skeleton(void)
 	struct test_skeleton__data *data;
 	struct test_skeleton__rodata *rodata;
 	struct test_skeleton__kconfig *kcfg;
+	const void *elf_bytes;
+	size_t elf_bytes_sz = 0;
 
 	skel = test_skeleton__open();
 	if (CHECK(!skel, "skel_open", "failed to open skeleton\n"))
@@ -91,6 +93,10 @@ void test_skeleton(void)
 	CHECK(bss->kern_ver != kcfg->LINUX_KERNEL_VERSION, "ext2",
 	      "got %d != exp %d\n", bss->kern_ver, kcfg->LINUX_KERNEL_VERSION);
 
+	elf_bytes = test_skeleton__elf_bytes(&elf_bytes_sz);
+	ASSERT_OK_PTR(elf_bytes, "elf_bytes");
+	ASSERT_GE(elf_bytes_sz, 0, "elf_bytes_sz");
+
 cleanup:
 	test_skeleton__destroy(skel);
 }
-- 
cgit v1.2.3


From 006a5099fc18a43792b01d002e1e45c5541ea666 Mon Sep 17 00:00:00 2001
From: Andrii Nakryiko <andrii@kernel.org>
Date: Tue, 7 Sep 2021 15:10:23 -0700
Subject: libbpf: Fix build with latest gcc/binutils with LTO

After updating to binutils 2.35, the build began to fail with an
assembler error. A bug was opened on the Red Hat Bugzilla a few days
later for the same issue.

Work around the problem by using the new `symver` attribute (introduced
in GCC 10) as needed instead of assembler directives.

This addresses Red Hat ([0]) and OpenSUSE ([1]) bug reports, as well as libbpf
issue ([2]).

  [0]: https://bugzilla.redhat.com/show_bug.cgi?id=1863059
  [1]: https://bugzilla.opensuse.org/show_bug.cgi?id=1188749
  [2]: Closes: https://github.com/libbpf/libbpf/issues/338

Co-developed-by: Patrick McCarty <patrick.mccarty@intel.com>
Co-developed-by: Michal Suchanek <msuchanek@suse.de>
Signed-off-by: Patrick McCarty <patrick.mccarty@intel.com>
Signed-off-by: Michal Suchanek <msuchanek@suse.de>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20210907221023.2660953-1-andrii@kernel.org
---
 tools/lib/bpf/libbpf_internal.h | 25 +++++++++++++++++++------
 tools/lib/bpf/xsk.c             |  4 ++--
 2 files changed, 21 insertions(+), 8 deletions(-)

(limited to 'tools')

diff --git a/tools/lib/bpf/libbpf_internal.h b/tools/lib/bpf/libbpf_internal.h
index 533b0211f40a..4f6ff5c23695 100644
--- a/tools/lib/bpf/libbpf_internal.h
+++ b/tools/lib/bpf/libbpf_internal.h
@@ -90,17 +90,30 @@
 /* Symbol versioning is different between static and shared library.
  * Properly versioned symbols are needed for shared library, but
  * only the symbol of the new version is needed for static library.
+ * Starting with GNU C 10, use symver attribute instead of .symver assembler
+ * directive, which works better with GCC LTO builds.
  */
-#ifdef SHARED
-# define COMPAT_VERSION(internal_name, api_name, version) \
+#if defined(SHARED) && defined(__GNUC__) && __GNUC__ >= 10
+
+#define DEFAULT_VERSION(internal_name, api_name, version) \
+	__attribute__((symver(#api_name "@@" #version)))
+#define COMPAT_VERSION(internal_name, api_name, version) \
+	__attribute__((symver(#api_name "@" #version)))
+
+#elif defined(SHARED)
+
+#define COMPAT_VERSION(internal_name, api_name, version) \
 	asm(".symver " #internal_name "," #api_name "@" #version);
-# define DEFAULT_VERSION(internal_name, api_name, version) \
+#define DEFAULT_VERSION(internal_name, api_name, version) \
 	asm(".symver " #internal_name "," #api_name "@@" #version);
-#else
-# define COMPAT_VERSION(internal_name, api_name, version)
-# define DEFAULT_VERSION(internal_name, api_name, version) \
+
+#else /* !SHARED */
+
+#define COMPAT_VERSION(internal_name, api_name, version)
+#define DEFAULT_VERSION(internal_name, api_name, version) \
 	extern typeof(internal_name) api_name \
 	__attribute__((alias(#internal_name)));
+
 #endif
 
 extern void libbpf_print(enum libbpf_print_level level,
diff --git a/tools/lib/bpf/xsk.c b/tools/lib/bpf/xsk.c
index e9b619aa0cdf..a2111696ba91 100644
--- a/tools/lib/bpf/xsk.c
+++ b/tools/lib/bpf/xsk.c
@@ -281,6 +281,7 @@ out_mmap:
 	return err;
 }
 
+DEFAULT_VERSION(xsk_umem__create_v0_0_4, xsk_umem__create, LIBBPF_0.0.4)
 int xsk_umem__create_v0_0_4(struct xsk_umem **umem_ptr, void *umem_area,
 			    __u64 size, struct xsk_ring_prod *fill,
 			    struct xsk_ring_cons *comp,
@@ -345,6 +346,7 @@ struct xsk_umem_config_v1 {
 	__u32 frame_headroom;
 };
 
+COMPAT_VERSION(xsk_umem__create_v0_0_2, xsk_umem__create, LIBBPF_0.0.2)
 int xsk_umem__create_v0_0_2(struct xsk_umem **umem_ptr, void *umem_area,
 			    __u64 size, struct xsk_ring_prod *fill,
 			    struct xsk_ring_cons *comp,
@@ -358,8 +360,6 @@ int xsk_umem__create_v0_0_2(struct xsk_umem **umem_ptr, void *umem_area,
 	return xsk_umem__create_v0_0_4(umem_ptr, umem_area, size, fill, comp,
 					&config);
 }
-COMPAT_VERSION(xsk_umem__create_v0_0_2, xsk_umem__create, LIBBPF_0.0.2)
-DEFAULT_VERSION(xsk_umem__create_v0_0_4, xsk_umem__create, LIBBPF_0.0.4)
 
 static enum xsk_prog get_xsk_prog(void)
 {
-- 
cgit v1.2.3


From 0b46b755056043dccfe078b96b256502b88f2464 Mon Sep 17 00:00:00 2001
From: Quentin Monnet <quentin@isovalent.com>
Date: Wed, 8 Sep 2021 14:32:26 -0700
Subject: libbpf: Add LIBBPF_DEPRECATED_SINCE macro for scheduling API
 deprecations

Introduce a macro LIBBPF_DEPRECATED_SINCE(major, minor, message) to prepare
the deprecation of two API functions. This macro marks functions as deprecated
when libbpf's version reaches the values passed as an argument.

As part of this change libbpf_version.h header is added with recorded major
(LIBBPF_MAJOR_VERSION) and minor (LIBBPF_MINOR_VERSION) libbpf version macros.
They are now part of libbpf public API and can be relied upon by user code.
libbpf_version.h is installed system-wide along other libbpf public headers.

Due to this new build-time auto-generated header, in-kernel applications
relying on libbpf (resolve_btfids, bpftool, bpf_preload) are updated to
include libbpf's output directory as part of a list of include search paths.
Better fix would be to use libbpf's make_install target to install public API
headers, but that clean up is left out as a future improvement. The build
changes were tested by building kernel (with KBUILD_OUTPUT and O= specified
explicitly), bpftool, libbpf, selftests/bpf, and resolve_btfids builds. No
problems were detected.

Note that because of the constraints of the C preprocessor we have to write
a few lines of macro magic for each version used to prepare deprecation (0.6
for now).

Also, use LIBBPF_DEPRECATED_SINCE() to schedule deprecation of
btf__get_from_id() and btf__load(), which are replaced by
btf__load_from_kernel_by_id() and btf__load_into_kernel(), respectively,
starting from future libbpf v0.6. This is part of libbpf 1.0 effort ([0]).

  [0] Closes: https://github.com/libbpf/libbpf/issues/278

Co-developed-by: Quentin Monnet <quentin@isovalent.com>
Co-developed-by: Andrii Nakryiko <andrii@kernel.org>
Signed-off-by: Quentin Monnet <quentin@isovalent.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/bpf/20210908213226.1871016-1-andrii@kernel.org
---
 tools/bpf/bpftool/Makefile           |  4 ++++
 tools/bpf/resolve_btfids/Makefile    |  6 ++++--
 tools/lib/bpf/Makefile               | 24 +++++++++++++++++-------
 tools/lib/bpf/btf.h                  |  2 ++
 tools/lib/bpf/libbpf_common.h        | 19 +++++++++++++++++++
 tools/testing/selftests/bpf/Makefile |  4 ++--
 6 files changed, 48 insertions(+), 11 deletions(-)

(limited to 'tools')

diff --git a/tools/bpf/bpftool/Makefile b/tools/bpf/bpftool/Makefile
index d73232be1e99..06aa1616dabe 100644
--- a/tools/bpf/bpftool/Makefile
+++ b/tools/bpf/bpftool/Makefile
@@ -60,6 +60,7 @@ CFLAGS += -W -Wall -Wextra -Wno-unused-parameter -Wno-missing-field-initializers
 CFLAGS += $(filter-out -Wswitch-enum -Wnested-externs,$(EXTRA_WARNINGS))
 CFLAGS += -DPACKAGE='"bpftool"' -D__EXPORTED_HEADERS__ \
 	-I$(if $(OUTPUT),$(OUTPUT),.) \
+	$(if $(LIBBPF_OUTPUT),-I$(LIBBPF_OUTPUT)) \
 	-I$(srctree)/kernel/bpf/ \
 	-I$(srctree)/tools/include \
 	-I$(srctree)/tools/include/uapi \
@@ -137,7 +138,10 @@ endif
 BPFTOOL_BOOTSTRAP := $(BOOTSTRAP_OUTPUT)bpftool
 
 BOOTSTRAP_OBJS = $(addprefix $(BOOTSTRAP_OUTPUT),main.o common.o json_writer.o gen.o btf.o xlated_dumper.o btf_dumper.o disasm.o)
+$(BOOTSTRAP_OBJS): $(LIBBPF_BOOTSTRAP)
+
 OBJS = $(patsubst %.c,$(OUTPUT)%.o,$(SRCS)) $(OUTPUT)disasm.o
+$(OBJS): $(LIBBPF)
 
 VMLINUX_BTF_PATHS ?= $(if $(O),$(O)/vmlinux)				\
 		     $(if $(KBUILD_OUTPUT),$(KBUILD_OUTPUT)/vmlinux)	\
diff --git a/tools/bpf/resolve_btfids/Makefile b/tools/bpf/resolve_btfids/Makefile
index bb9fa8de7e62..edc0c329cf74 100644
--- a/tools/bpf/resolve_btfids/Makefile
+++ b/tools/bpf/resolve_btfids/Makefile
@@ -26,6 +26,7 @@ LIBBPF_SRC := $(srctree)/tools/lib/bpf/
 SUBCMD_SRC := $(srctree)/tools/lib/subcmd/
 
 BPFOBJ     := $(OUTPUT)/libbpf/libbpf.a
+LIBBPF_OUT := $(abspath $(dir $(BPFOBJ)))/
 SUBCMDOBJ  := $(OUTPUT)/libsubcmd/libsubcmd.a
 
 BINARY     := $(OUTPUT)/resolve_btfids
@@ -41,11 +42,12 @@ $(SUBCMDOBJ): fixdep FORCE | $(OUTPUT)/libsubcmd
 	$(Q)$(MAKE) -C $(SUBCMD_SRC) OUTPUT=$(abspath $(dir $@))/ $(abspath $@)
 
 $(BPFOBJ): $(wildcard $(LIBBPF_SRC)/*.[ch] $(LIBBPF_SRC)/Makefile) | $(OUTPUT)/libbpf
-	$(Q)$(MAKE) $(submake_extras) -C $(LIBBPF_SRC)  OUTPUT=$(abspath $(dir $@))/ $(abspath $@)
+	$(Q)$(MAKE) $(submake_extras) -C $(LIBBPF_SRC)  OUTPUT=$(LIBBPF_OUT) $(abspath $@)
 
 CFLAGS := -g \
           -I$(srctree)/tools/include \
           -I$(srctree)/tools/include/uapi \
+          -I$(LIBBPF_OUT) \
           -I$(LIBBPF_SRC) \
           -I$(SUBCMD_SRC)
 
@@ -54,7 +56,7 @@ LIBS = -lelf -lz
 export srctree OUTPUT CFLAGS Q
 include $(srctree)/tools/build/Makefile.include
 
-$(BINARY_IN): fixdep FORCE | $(OUTPUT)
+$(BINARY_IN): $(BPFOBJ) fixdep FORCE | $(OUTPUT)
 	$(Q)$(MAKE) $(build)=resolve_btfids
 
 $(BINARY): $(BPFOBJ) $(SUBCMDOBJ) $(BINARY_IN)
diff --git a/tools/lib/bpf/Makefile b/tools/lib/bpf/Makefile
index 74c3b73a5fbe..dab21e0c7cc2 100644
--- a/tools/lib/bpf/Makefile
+++ b/tools/lib/bpf/Makefile
@@ -8,7 +8,8 @@ VERSION_SCRIPT := libbpf.map
 LIBBPF_VERSION := $(shell \
 	grep -oE '^LIBBPF_([0-9.]+)' $(VERSION_SCRIPT) | \
 	sort -rV | head -n1 | cut -d'_' -f2)
-LIBBPF_MAJOR_VERSION := $(firstword $(subst ., ,$(LIBBPF_VERSION)))
+LIBBPF_MAJOR_VERSION := $(word 1,$(subst ., ,$(LIBBPF_VERSION)))
+LIBBPF_MINOR_VERSION := $(word 2,$(subst ., ,$(LIBBPF_VERSION)))
 
 MAKEFLAGS += --no-print-directory
 
@@ -59,7 +60,8 @@ ifndef VERBOSE
   VERBOSE = 0
 endif
 
-INCLUDES = -I. -I$(srctree)/tools/include -I$(srctree)/tools/include/uapi
+INCLUDES = -I$(if $(OUTPUT),$(OUTPUT),.)				\
+	   -I$(srctree)/tools/include -I$(srctree)/tools/include/uapi
 
 export prefix libdir src obj
 
@@ -111,7 +113,9 @@ SHARED_OBJDIR	:= $(OUTPUT)sharedobjs/
 STATIC_OBJDIR	:= $(OUTPUT)staticobjs/
 BPF_IN_SHARED	:= $(SHARED_OBJDIR)libbpf-in.o
 BPF_IN_STATIC	:= $(STATIC_OBJDIR)libbpf-in.o
+VERSION_HDR	:= $(OUTPUT)libbpf_version.h
 BPF_HELPER_DEFS	:= $(OUTPUT)bpf_helper_defs.h
+BPF_GENERATED	:= $(BPF_HELPER_DEFS) $(VERSION_HDR)
 
 LIB_TARGET	:= $(addprefix $(OUTPUT),$(LIB_TARGET))
 LIB_FILE	:= $(addprefix $(OUTPUT),$(LIB_FILE))
@@ -136,7 +140,7 @@ all: fixdep
 
 all_cmd: $(CMD_TARGETS) check
 
-$(BPF_IN_SHARED): force $(BPF_HELPER_DEFS)
+$(BPF_IN_SHARED): force $(BPF_GENERATED)
 	@(test -f ../../include/uapi/linux/bpf.h -a -f ../../../include/uapi/linux/bpf.h && ( \
 	(diff -B ../../include/uapi/linux/bpf.h ../../../include/uapi/linux/bpf.h >/dev/null) || \
 	echo "Warning: Kernel ABI header at 'tools/include/uapi/linux/bpf.h' differs from latest version at 'include/uapi/linux/bpf.h'" >&2 )) || true
@@ -154,13 +158,19 @@ $(BPF_IN_SHARED): force $(BPF_HELPER_DEFS)
 	echo "Warning: Kernel ABI header at 'tools/include/uapi/linux/if_xdp.h' differs from latest version at 'include/uapi/linux/if_xdp.h'" >&2 )) || true
 	$(Q)$(MAKE) $(build)=libbpf OUTPUT=$(SHARED_OBJDIR) CFLAGS="$(CFLAGS) $(SHLIB_FLAGS)"
 
-$(BPF_IN_STATIC): force $(BPF_HELPER_DEFS)
+$(BPF_IN_STATIC): force $(BPF_GENERATED)
 	$(Q)$(MAKE) $(build)=libbpf OUTPUT=$(STATIC_OBJDIR)
 
 $(BPF_HELPER_DEFS): $(srctree)/tools/include/uapi/linux/bpf.h
 	$(QUIET_GEN)$(srctree)/scripts/bpf_doc.py --header \
 		--file $(srctree)/tools/include/uapi/linux/bpf.h > $(BPF_HELPER_DEFS)
 
+$(VERSION_HDR): force
+	$(QUIET_GEN)echo "/* This file was auto-generated. */" > $@
+	@echo "" >> $@
+	@echo "#define LIBBPF_MAJOR_VERSION $(LIBBPF_MAJOR_VERSION)" >> $@
+	@echo "#define LIBBPF_MINOR_VERSION $(LIBBPF_MINOR_VERSION)" >> $@
+
 $(OUTPUT)libbpf.so: $(OUTPUT)libbpf.so.$(LIBBPF_VERSION)
 
 $(OUTPUT)libbpf.so.$(LIBBPF_VERSION): $(BPF_IN_SHARED) $(VERSION_SCRIPT)
@@ -224,10 +234,10 @@ install_lib: all_cmd
 		cp -fpR $(LIB_FILE) $(DESTDIR)$(libdir_SQ)
 
 INSTALL_HEADERS = bpf.h libbpf.h btf.h libbpf_common.h libbpf_legacy.h xsk.h \
-		  bpf_helpers.h $(BPF_HELPER_DEFS) bpf_tracing.h	     \
+		  bpf_helpers.h $(BPF_GENERATED) bpf_tracing.h	     \
 		  bpf_endian.h bpf_core_read.h skel_internal.h
 
-install_headers: $(BPF_HELPER_DEFS)
+install_headers: $(BPF_GENERATED)
 	$(call QUIET_INSTALL, headers)					     \
 		$(foreach hdr,$(INSTALL_HEADERS),			     \
 			$(call do_install,$(hdr),$(prefix)/include/bpf,644);)
@@ -240,7 +250,7 @@ install: install_lib install_pkgconfig install_headers
 
 clean:
 	$(call QUIET_CLEAN, libbpf) $(RM) -rf $(CMD_TARGETS)		     \
-		*~ .*.d .*.cmd LIBBPF-CFLAGS $(BPF_HELPER_DEFS)		     \
+		*~ .*.d .*.cmd LIBBPF-CFLAGS $(BPF_GENERATED)		     \
 		$(SHARED_OBJDIR) $(STATIC_OBJDIR)			     \
 		$(addprefix $(OUTPUT),					     \
 			    *.o *.a *.so *.so.$(LIBBPF_MAJOR_VERSION) *.pc)
diff --git a/tools/lib/bpf/btf.h b/tools/lib/bpf/btf.h
index 4a711f990904..f2e2fab950b7 100644
--- a/tools/lib/bpf/btf.h
+++ b/tools/lib/bpf/btf.h
@@ -50,9 +50,11 @@ LIBBPF_API struct btf *libbpf_find_kernel_btf(void);
 
 LIBBPF_API struct btf *btf__load_from_kernel_by_id(__u32 id);
 LIBBPF_API struct btf *btf__load_from_kernel_by_id_split(__u32 id, struct btf *base_btf);
+LIBBPF_DEPRECATED_SINCE(0, 6, "use btf__load_from_kernel_by_id instead")
 LIBBPF_API int btf__get_from_id(__u32 id, struct btf **btf);
 
 LIBBPF_API int btf__finalize_data(struct bpf_object *obj, struct btf *btf);
+LIBBPF_DEPRECATED_SINCE(0, 6, "use btf__load_into_kernel instead")
 LIBBPF_API int btf__load(struct btf *btf);
 LIBBPF_API int btf__load_into_kernel(struct btf *btf);
 LIBBPF_API __s32 btf__find_by_name(const struct btf *btf,
diff --git a/tools/lib/bpf/libbpf_common.h b/tools/lib/bpf/libbpf_common.h
index 947d8bd8a7bb..36ac77f2bea2 100644
--- a/tools/lib/bpf/libbpf_common.h
+++ b/tools/lib/bpf/libbpf_common.h
@@ -10,6 +10,7 @@
 #define __LIBBPF_LIBBPF_COMMON_H
 
 #include <string.h>
+#include "libbpf_version.h"
 
 #ifndef LIBBPF_API
 #define LIBBPF_API __attribute__((visibility("default")))
@@ -17,6 +18,24 @@
 
 #define LIBBPF_DEPRECATED(msg) __attribute__((deprecated(msg)))
 
+/* Mark a symbol as deprecated when libbpf version is >= {major}.{minor} */
+#define LIBBPF_DEPRECATED_SINCE(major, minor, msg)			    \
+	__LIBBPF_MARK_DEPRECATED_ ## major ## _ ## minor		    \
+		(LIBBPF_DEPRECATED("libbpf v" # major "." # minor "+: " msg))
+
+#define __LIBBPF_CURRENT_VERSION_GEQ(major, minor)			    \
+	(LIBBPF_MAJOR_VERSION > (major) ||				    \
+	 (LIBBPF_MAJOR_VERSION == (major) && LIBBPF_MINOR_VERSION >= (minor)))
+
+/* Add checks for other versions below when planning deprecation of API symbols
+ * with the LIBBPF_DEPRECATED_SINCE macro.
+ */
+#if __LIBBPF_CURRENT_VERSION_GEQ(0, 6)
+#define __LIBBPF_MARK_DEPRECATED_0_6(X) X
+#else
+#define __LIBBPF_MARK_DEPRECATED_0_6(X)
+#endif
+
 /* Helper macro to declare and initialize libbpf options struct
  *
  * This dance with uninitialized declaration, followed by memset to zero,
diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index 866531c08e4f..1a4d30ff3275 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -512,14 +512,14 @@ $(OUTPUT)/test_cpp: test_cpp.cpp $(OUTPUT)/test_core_extern.skel.h $(BPFOBJ)
 	$(Q)$(CXX) $(CFLAGS) $(filter %.a %.o %.cpp,$^) $(LDLIBS) -o $@
 
 # Benchmark runner
-$(OUTPUT)/bench_%.o: benchs/bench_%.c bench.h
+$(OUTPUT)/bench_%.o: benchs/bench_%.c bench.h $(BPFOBJ)
 	$(call msg,CC,,$@)
 	$(Q)$(CC) $(CFLAGS) -c $(filter %.c,$^) $(LDLIBS) -o $@
 $(OUTPUT)/bench_rename.o: $(OUTPUT)/test_overhead.skel.h
 $(OUTPUT)/bench_trigger.o: $(OUTPUT)/trigger_bench.skel.h
 $(OUTPUT)/bench_ringbufs.o: $(OUTPUT)/ringbuf_bench.skel.h \
 			    $(OUTPUT)/perfbuf_bench.skel.h
-$(OUTPUT)/bench.o: bench.h testing_helpers.h
+$(OUTPUT)/bench.o: bench.h testing_helpers.h $(BPFOBJ)
 $(OUTPUT)/bench: LDLIBS += -lm
 $(OUTPUT)/bench: $(OUTPUT)/bench.o $(OUTPUT)/testing_helpers.o \
 		 $(OUTPUT)/bench_count.o \
-- 
cgit v1.2.3


From ed7b74dc777777254a97de3e18e5dcbcebf3f015 Mon Sep 17 00:00:00 2001
From: Magnus Karlsson <magnus.karlsson@intel.com>
Date: Tue, 7 Sep 2021 09:19:09 +0200
Subject: selftests: xsk: Simplify xsk and umem arrays

Simplify the xsk_info and umem_info allocation by allocating them
upfront in an array, instead of allocating an array of pointers to
future creations of these. Allocating them upfront also has the
advantage that configuration information can be stored in these
structures instead of relying on global variables. With the previous
structure, xsk_info and umem_info were created too late to be able to
store most configuration information. This will be used to eliminate
most global variables in later patches in this series.

Signed-off-by: Magnus Karlsson <magnus.karlsson@intel.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Link: https://lore.kernel.org/bpf/20210907071928.9750-2-magnus.karlsson@gmail.com
---
 tools/testing/selftests/bpf/xdpxceiver.c | 78 +++++++++++++-------------------
 tools/testing/selftests/bpf/xdpxceiver.h |  5 +-
 2 files changed, 34 insertions(+), 49 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/xdpxceiver.c b/tools/testing/selftests/bpf/xdpxceiver.c
index f53ce2683f8d..9639d8da516d 100644
--- a/tools/testing/selftests/bpf/xdpxceiver.c
+++ b/tools/testing/selftests/bpf/xdpxceiver.c
@@ -235,7 +235,7 @@ static void gen_udp_csum(struct udphdr *udp_hdr, struct iphdr *ip_hdr)
 	    udp_csum(ip_hdr->saddr, ip_hdr->daddr, UDP_PKT_SIZE, IPPROTO_UDP, (u16 *)udp_hdr);
 }
 
-static void xsk_configure_umem(struct ifobject *data, void *buffer, u64 size, int idx)
+static int xsk_configure_umem(struct xsk_umem_info *umem, void *buffer, u64 size, int idx)
 {
 	struct xsk_umem_config cfg = {
 		.fill_size = XSK_RING_PROD__DEFAULT_NUM_DESCS,
@@ -244,21 +244,15 @@ static void xsk_configure_umem(struct ifobject *data, void *buffer, u64 size, in
 		.frame_headroom = frame_headroom,
 		.flags = XSK_UMEM__DEFAULT_FLAGS
 	};
-	struct xsk_umem_info *umem;
 	int ret;
 
-	umem = calloc(1, sizeof(struct xsk_umem_info));
-	if (!umem)
-		exit_with_error(errno);
-
 	ret = xsk_umem__create(&umem->umem, buffer, size,
 			       &umem->fq, &umem->cq, &cfg);
 	if (ret)
-		exit_with_error(-ret);
+		return ret;
 
 	umem->buffer = buffer;
-
-	data->umem_arr[idx] = umem;
+	return 0;
 }
 
 static void xsk_populate_fill_ring(struct xsk_umem_info *umem)
@@ -274,19 +268,14 @@ static void xsk_populate_fill_ring(struct xsk_umem_info *umem)
 	xsk_ring_prod__submit(&umem->fq, XSK_RING_PROD__DEFAULT_NUM_DESCS);
 }
 
-static int xsk_configure_socket(struct ifobject *ifobject, int idx)
+static int xsk_configure_socket(struct xsk_socket_info *xsk, struct xsk_umem_info *umem,
+				struct ifobject *ifobject, u32 qid)
 {
 	struct xsk_socket_config cfg;
-	struct xsk_socket_info *xsk;
 	struct xsk_ring_cons *rxr;
 	struct xsk_ring_prod *txr;
-	int ret;
 
-	xsk = calloc(1, sizeof(struct xsk_socket_info));
-	if (!xsk)
-		exit_with_error(errno);
-
-	xsk->umem = ifobject->umem;
+	xsk->umem = umem;
 	cfg.rx_size = rxqsize;
 	cfg.tx_size = XSK_RING_PROD__DEFAULT_NUM_DESCS;
 	cfg.libbpf_flags = 0;
@@ -301,14 +290,7 @@ static int xsk_configure_socket(struct ifobject *ifobject, int idx)
 		txr = &xsk->tx;
 	}
 
-	ret = xsk_socket__create(&xsk->xsk, ifobject->ifname, idx,
-				 ifobject->umem->umem, rxr, txr, &cfg);
-	if (ret)
-		return 1;
-
-	ifobject->xsk_arr[idx] = xsk;
-
-	return 0;
+	return xsk_socket__create(&xsk->xsk, ifobject->ifname, qid, umem->umem, rxr, txr, &cfg);
 }
 
 static struct option long_options[] = {
@@ -756,8 +738,7 @@ static void thread_common_ops(struct ifobject *ifobject, void *bufs)
 	u64 umem_sz = num_frames * XSK_UMEM__DEFAULT_FRAME_SIZE;
 	int mmap_flags = MAP_PRIVATE | MAP_ANONYMOUS | MAP_NORESERVE;
 	size_t mmap_sz = umem_sz;
-	int ctr = 0;
-	int ret;
+	int ctr = 0, ret;
 
 	ifobject->ns_fd = switch_namespace(ifobject->nsname);
 
@@ -769,31 +750,34 @@ static void thread_common_ops(struct ifobject *ifobject, void *bufs)
 		exit_with_error(errno);
 
 	while (ctr++ < SOCK_RECONF_CTR) {
-		xsk_configure_umem(ifobject, bufs, umem_sz, 0);
-		ifobject->umem = ifobject->umem_arr[0];
-		ret = xsk_configure_socket(ifobject, 0);
+		ret = xsk_configure_umem(&ifobject->umem_arr[0], bufs, umem_sz, 0);
+		if (ret)
+			exit_with_error(-ret);
+
+		ret = xsk_configure_socket(&ifobject->xsk_arr[0], &ifobject->umem_arr[0],
+					   ifobject, 0);
 		if (!ret)
 			break;
 
 		/* Retry Create Socket if it fails as xsk_socket__create() is asynchronous */
-		usleep(USLEEP_MAX);
 		if (ctr >= SOCK_RECONF_CTR)
 			exit_with_error(-ret);
+		usleep(USLEEP_MAX);
 	}
 
-	ifobject->umem = ifobject->umem_arr[0];
-	ifobject->xsk = ifobject->xsk_arr[0];
-
 	if (test_type == TEST_TYPE_BPF_RES) {
-		xsk_configure_umem(ifobject, (u8 *)bufs + umem_sz, umem_sz, 1);
-		ifobject->umem = ifobject->umem_arr[1];
-		ret = xsk_configure_socket(ifobject, 1);
+		ret = xsk_configure_umem(&ifobject->umem_arr[1], (u8 *)bufs + umem_sz, umem_sz, 1);
+		if (ret)
+			exit_with_error(-ret);
+
+		ret = xsk_configure_socket(&ifobject->xsk_arr[1], &ifobject->umem_arr[1],
+					   ifobject, 1);
+		if (ret)
+			exit_with_error(-ret);
 	}
 
-	ifobject->umem = ifobject->umem_arr[0];
-	ifobject->xsk = ifobject->xsk_arr[0];
-	print_verbose("Interface [%s] vector [%s]\n",
-		      ifobject->ifname, ifobject->fv.vector == tx ? "Tx" : "Rx");
+	ifobject->umem = &ifobject->umem_arr[0];
+	ifobject->xsk = &ifobject->xsk_arr[0];
 }
 
 static bool testapp_is_test_two_stepped(void)
@@ -941,10 +925,10 @@ static void swap_xsk_res(void)
 	xsk_umem__delete(ifdict_tx->umem->umem);
 	xsk_socket__delete(ifdict_rx->xsk->xsk);
 	xsk_umem__delete(ifdict_rx->umem->umem);
-	ifdict_tx->umem = ifdict_tx->umem_arr[1];
-	ifdict_tx->xsk = ifdict_tx->xsk_arr[1];
-	ifdict_rx->umem = ifdict_rx->umem_arr[1];
-	ifdict_rx->xsk = ifdict_rx->xsk_arr[1];
+	ifdict_tx->umem = &ifdict_tx->umem_arr[1];
+	ifdict_tx->xsk = &ifdict_tx->xsk_arr[1];
+	ifdict_rx->umem = &ifdict_rx->umem_arr[1];
+	ifdict_rx->xsk = &ifdict_rx->xsk_arr[1];
 }
 
 static void testapp_bpf_res(void)
@@ -1071,11 +1055,11 @@ static struct ifobject *ifobject_create(void)
 	if (!ifobj)
 		return NULL;
 
-	ifobj->xsk_arr = calloc(2, sizeof(struct xsk_socket_info *));
+	ifobj->xsk_arr = calloc(MAX_SOCKETS, sizeof(*ifobj->xsk_arr));
 	if (!ifobj->xsk_arr)
 		goto out_xsk_arr;
 
-	ifobj->umem_arr = calloc(2, sizeof(struct xsk_umem_info *));
+	ifobj->umem_arr = calloc(MAX_SOCKETS, sizeof(*ifobj->umem_arr));
 	if (!ifobj->umem_arr)
 		goto out_umem_arr;
 
diff --git a/tools/testing/selftests/bpf/xdpxceiver.h b/tools/testing/selftests/bpf/xdpxceiver.h
index 7e49b9fbe25e..de80516ac6c2 100644
--- a/tools/testing/selftests/bpf/xdpxceiver.h
+++ b/tools/testing/selftests/bpf/xdpxceiver.h
@@ -21,6 +21,7 @@
 #define MAX_INTERFACE_NAME_CHARS 7
 #define MAX_INTERFACES_NAMESPACE_CHARS 10
 #define MAX_SOCKS 1
+#define MAX_SOCKETS 2
 #define MAX_TEARDOWN_ITER 10
 #define MAX_BIDI_ITER 2
 #define MAX_BPF_ITER 2
@@ -119,9 +120,9 @@ struct ifobject {
 	char ifname[MAX_INTERFACE_NAME_CHARS];
 	char nsname[MAX_INTERFACES_NAMESPACE_CHARS];
 	struct xsk_socket_info *xsk;
-	struct xsk_socket_info **xsk_arr;
-	struct xsk_umem_info **umem_arr;
+	struct xsk_socket_info *xsk_arr;
 	struct xsk_umem_info *umem;
+	struct xsk_umem_info *umem_arr;
 	void *(*func_ptr)(void *arg);
 	struct flow_vector fv;
 	struct pkt_stream *pkt_stream;
-- 
cgit v1.2.3


From 744eb5c882e8133d97f656cb6f9c49817889fa64 Mon Sep 17 00:00:00 2001
From: Magnus Karlsson <magnus.karlsson@intel.com>
Date: Tue, 7 Sep 2021 09:19:10 +0200
Subject: selftests: xsk: Introduce type for thread function

Introduce a typedef of the thread function so this can be passed to
init_iface() in order to simplify that function.

Signed-off-by: Magnus Karlsson <magnus.karlsson@intel.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Link: https://lore.kernel.org/bpf/20210907071928.9750-3-magnus.karlsson@gmail.com
---
 tools/testing/selftests/bpf/xdpxceiver.c | 25 ++++++++++++-------------
 tools/testing/selftests/bpf/xdpxceiver.h |  4 +++-
 2 files changed, 15 insertions(+), 14 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/xdpxceiver.c b/tools/testing/selftests/bpf/xdpxceiver.c
index 9639d8da516d..edf5b6cc6998 100644
--- a/tools/testing/selftests/bpf/xdpxceiver.c
+++ b/tools/testing/selftests/bpf/xdpxceiver.c
@@ -974,10 +974,9 @@ static void testapp_stats(void)
 	print_ksft_result();
 }
 
-static void init_iface(struct ifobject *ifobj, const char *dst_mac,
-		       const char *src_mac, const char *dst_ip,
-		       const char *src_ip, const u16 dst_port,
-		       const u16 src_port, enum fvector vector)
+static void init_iface(struct ifobject *ifobj, const char *dst_mac, const char *src_mac,
+		       const char *dst_ip, const char *src_ip, const u16 dst_port,
+		       const u16 src_port, enum fvector vector, thread_func_t func_ptr)
 {
 	struct in_addr ip;
 
@@ -993,15 +992,13 @@ static void init_iface(struct ifobject *ifobj, const char *dst_mac,
 	ifobj->dst_port = dst_port;
 	ifobj->src_port = src_port;
 
-	if (vector == tx) {
-		ifobj->fv.vector = tx;
-		ifobj->func_ptr = worker_testapp_validate_tx;
+	if (vector == tx)
 		ifdict_tx = ifobj;
-	} else {
-		ifobj->fv.vector = rx;
-		ifobj->func_ptr = worker_testapp_validate_rx;
+	else
 		ifdict_rx = ifobj;
-	}
+
+	ifobj->fv.vector = vector;
+	ifobj->func_ptr = func_ptr;
 }
 
 static void run_pkt_test(int mode, int type)
@@ -1097,8 +1094,10 @@ int main(int argc, char **argv)
 
 	parse_command_line(argc, argv);
 
-	init_iface(ifdict[tx], MAC1, MAC2, IP1, IP2, UDP_PORT1, UDP_PORT2, tx);
-	init_iface(ifdict[rx], MAC2, MAC1, IP2, IP1, UDP_PORT2, UDP_PORT1, rx);
+	init_iface(ifdict[tx], MAC1, MAC2, IP1, IP2, UDP_PORT1, UDP_PORT2, tx,
+		   worker_testapp_validate_tx);
+	init_iface(ifdict[rx], MAC2, MAC1, IP2, IP1, UDP_PORT2, UDP_PORT1, rx,
+		   worker_testapp_validate_rx);
 
 	ksft_set_plan(TEST_MODE_MAX * TEST_TYPE_MAX);
 
diff --git a/tools/testing/selftests/bpf/xdpxceiver.h b/tools/testing/selftests/bpf/xdpxceiver.h
index de80516ac6c2..799d524eb425 100644
--- a/tools/testing/selftests/bpf/xdpxceiver.h
+++ b/tools/testing/selftests/bpf/xdpxceiver.h
@@ -116,6 +116,8 @@ struct pkt_stream {
 	struct pkt *pkts;
 };
 
+typedef void *(*thread_func_t)(void *arg);
+
 struct ifobject {
 	char ifname[MAX_INTERFACE_NAME_CHARS];
 	char nsname[MAX_INTERFACES_NAMESPACE_CHARS];
@@ -123,8 +125,8 @@ struct ifobject {
 	struct xsk_socket_info *xsk_arr;
 	struct xsk_umem_info *umem;
 	struct xsk_umem_info *umem_arr;
-	void *(*func_ptr)(void *arg);
 	struct flow_vector fv;
+	thread_func_t func_ptr;
 	struct pkt_stream *pkt_stream;
 	int ns_fd;
 	u32 dst_ip;
-- 
cgit v1.2.3


From ce74acaf015c5ac9365abc017af051560950e46b Mon Sep 17 00:00:00 2001
From: Magnus Karlsson <magnus.karlsson@intel.com>
Date: Tue, 7 Sep 2021 09:19:11 +0200
Subject: selftests: xsk: Introduce test specifications

Introduce a test specification to be able to concisely describe a
test. Currently, a test is implemented by sprinkling test specific if
statements here and there, which is not scalable or easy to
understand. The end goal with this patch set is to come to the point
in which a test is completely specified by a test specification that
can easily be constructed in a single function so that new tests can
be added without too much trouble. This test specification will be run
by a test runner that has no idea about tests. It just executes the
what test specification states.

This patch introduces the test specification and, as a start, puts the
two interface objects in there, one containing the packet stream to be
sent and the other one the packet stream that is supposed to be
received for a test to pass. The global variables containing these can
then be eliminated. The following patches will convert each existing
test into a test specification and add the needed fields into it and
the functionality in the test runner that act on the test
specification. At the end, the test runner should contain no test
specific code and each test should be described in a single simple
function.

Signed-off-by: Magnus Karlsson <magnus.karlsson@intel.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Link: https://lore.kernel.org/bpf/20210907071928.9750-4-magnus.karlsson@gmail.com
---
 tools/testing/selftests/bpf/xdpxceiver.c | 203 +++++++++++++++++++------------
 tools/testing/selftests/bpf/xdpxceiver.h |   7 +-
 2 files changed, 126 insertions(+), 84 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/xdpxceiver.c b/tools/testing/selftests/bpf/xdpxceiver.c
index edf5b6cc6998..a6bcc7453860 100644
--- a/tools/testing/selftests/bpf/xdpxceiver.c
+++ b/tools/testing/selftests/bpf/xdpxceiver.c
@@ -336,45 +336,43 @@ static int switch_namespace(const char *nsname)
 	return nsfd;
 }
 
-static int validate_interfaces(void)
+static bool validate_interface(struct ifobject *ifobj)
 {
-	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>.");
-		}
-	}
-	return ret;
+	if (!strcmp(ifobj->ifname, ""))
+		return false;
+	return true;
 }
 
-static void parse_command_line(int argc, char **argv)
+static void parse_command_line(struct test_spec *test, int argc, char **argv)
 {
-	int option_index, interface_index = 0, c;
+	struct ifobject *ifobj;
+	u32 interface_nb = 0;
+	int option_index, c;
 
 	opterr = 0;
 
 	for (;;) {
-		c = getopt_long(argc, argv, "i:Dv", long_options, &option_index);
+		char *sptr, *token;
 
+		c = getopt_long(argc, argv, "i:Dv", long_options, &option_index);
 		if (c == -1)
 			break;
 
 		switch (c) {
 		case 'i':
-			if (interface_index == MAX_INTERFACES)
+			if (interface_nb == 0)
+				ifobj = test->ifobj_tx;
+			else if (interface_nb == 1)
+				ifobj = test->ifobj_rx;
+			else
 				break;
-			char *sptr, *token;
 
 			sptr = strndupa(optarg, strlen(optarg));
-			memcpy(ifdict[interface_index]->ifname,
-			       strsep(&sptr, ","), MAX_INTERFACE_NAME_CHARS);
+			memcpy(ifobj->ifname, strsep(&sptr, ","), MAX_INTERFACE_NAME_CHARS);
 			token = strsep(&sptr, ",");
 			if (token)
-				memcpy(ifdict[interface_index]->nsname, token,
-				       MAX_INTERFACES_NAMESPACE_CHARS);
-			interface_index++;
+				memcpy(ifobj->nsname, token, MAX_INTERFACES_NAMESPACE_CHARS);
+			interface_nb++;
 			break;
 		case 'D':
 			opt_pkt_dump = true;
@@ -387,11 +385,44 @@ static void parse_command_line(int argc, char **argv)
 			ksft_exit_xfail();
 		}
 	}
+}
 
-	if (!validate_interfaces()) {
-		usage(basename(argv[0]));
-		ksft_exit_xfail();
+static void __test_spec_init(struct test_spec *test, struct ifobject *ifobj_tx,
+			     struct ifobject *ifobj_rx)
+{
+	u32 i, j;
+
+	for (i = 0; i < MAX_INTERFACES; i++) {
+		struct ifobject *ifobj = i ? ifobj_rx : ifobj_tx;
+
+		ifobj->umem = &ifobj->umem_arr[0];
+		ifobj->xsk = &ifobj->xsk_arr[0];
+
+		if (i == tx)
+			ifobj->fv.vector = tx;
+		else
+			ifobj->fv.vector = rx;
+
+		for (j = 0; j < MAX_SOCKETS; j++) {
+			memset(&ifobj->umem_arr[j], 0, sizeof(ifobj->umem_arr[j]));
+			memset(&ifobj->xsk_arr[j], 0, sizeof(ifobj->xsk_arr[j]));
+		}
 	}
+
+	test->ifobj_tx = ifobj_tx;
+	test->ifobj_rx = ifobj_rx;
+}
+
+static void test_spec_init(struct test_spec *test, struct ifobject *ifobj_tx,
+			   struct ifobject *ifobj_rx)
+{
+	memset(test, 0, sizeof(*test));
+	__test_spec_init(test, ifobj_tx, ifobj_rx);
+}
+
+static void test_spec_reset(struct test_spec *test)
+{
+	__test_spec_init(test, test->ifobj_tx, test->ifobj_rx);
 }
 
 static struct pkt *pkt_stream_get_pkt(struct pkt_stream *pkt_stream, u32 pkt_nb)
@@ -842,8 +873,10 @@ static void *worker_testapp_validate_rx(void *arg)
 	pthread_exit(NULL);
 }
 
-static void testapp_validate(void)
+static void testapp_validate_traffic(struct test_spec *test)
 {
+	struct ifobject *ifobj_tx = test->ifobj_tx;
+	struct ifobject *ifobj_rx = test->ifobj_rx;
 	bool bidi = test_type == TEST_TYPE_BIDI;
 	bool bpf = test_type == TEST_TYPE_BPF_RES;
 	struct pkt_stream *pkt_stream;
@@ -855,18 +888,18 @@ static void testapp_validate(void)
 		pkt_stream = pkt_stream_generate(DEFAULT_PKT_CNT, XSK_UMEM__INVALID_FRAME_SIZE);
 	else
 		pkt_stream = pkt_stream_generate(DEFAULT_PKT_CNT, PKT_SIZE);
-	ifdict_tx->pkt_stream = pkt_stream;
-	ifdict_rx->pkt_stream = pkt_stream;
+	ifobj_tx->pkt_stream = pkt_stream;
+	ifobj_rx->pkt_stream = pkt_stream;
 
 	/*Spawn RX thread */
-	pthread_create(&t0, NULL, ifdict_rx->func_ptr, ifdict_rx);
+	pthread_create(&t0, NULL, ifobj_rx->func_ptr, ifobj_rx);
 
 	pthread_barrier_wait(&barr);
 	if (pthread_barrier_destroy(&barr))
 		exit_with_error(errno);
 
 	/*Spawn TX thread */
-	pthread_create(&t1, NULL, ifdict_tx->func_ptr, ifdict_tx);
+	pthread_create(&t1, NULL, ifobj_tx->func_ptr, ifobj_tx);
 
 	pthread_join(t1, NULL);
 	pthread_join(t0, NULL);
@@ -875,80 +908,82 @@ static void testapp_validate(void)
 		print_ksft_result();
 }
 
-static void testapp_teardown(void)
+static void testapp_teardown(struct test_spec *test)
 {
 	int i;
 
 	for (i = 0; i < MAX_TEARDOWN_ITER; i++) {
-		print_verbose("Creating socket\n");
-		testapp_validate();
+		testapp_validate_traffic(test);
+		test_spec_reset(test);
 	}
 
 	print_ksft_result();
 }
 
-static void swap_vectors(struct ifobject *ifobj1, struct ifobject *ifobj2)
+static void swap_directions(struct ifobject **ifobj1, struct ifobject **ifobj2)
 {
-	void *(*tmp_func_ptr)(void *) = ifobj1->func_ptr;
-	enum fvector tmp_vector = ifobj1->fv.vector;
+	thread_func_t tmp_func_ptr = (*ifobj1)->func_ptr;
+	enum fvector tmp_vector = (*ifobj1)->fv.vector;
+	struct ifobject *tmp_ifobj = (*ifobj1);
 
-	ifobj1->func_ptr = ifobj2->func_ptr;
-	ifobj1->fv.vector = ifobj2->fv.vector;
+	(*ifobj1)->func_ptr = (*ifobj2)->func_ptr;
+	(*ifobj1)->fv.vector = (*ifobj2)->fv.vector;
 
-	ifobj2->func_ptr = tmp_func_ptr;
-	ifobj2->fv.vector = tmp_vector;
+	(*ifobj2)->func_ptr = tmp_func_ptr;
+	(*ifobj2)->fv.vector = tmp_vector;
 
-	ifdict_tx = ifobj1;
-	ifdict_rx = ifobj2;
+	*ifobj1 = *ifobj2;
+	*ifobj2 = tmp_ifobj;
 }
 
-static void testapp_bidi(void)
+static void testapp_bidi(struct test_spec *test)
 {
 	for (int i = 0; i < MAX_BIDI_ITER; i++) {
 		print_verbose("Creating socket\n");
-		testapp_validate();
+		testapp_validate_traffic(test);
 		if (!second_step) {
 			print_verbose("Switching Tx/Rx vectors\n");
-			swap_vectors(ifdict[1], ifdict[0]);
+			swap_directions(&test->ifobj_rx, &test->ifobj_tx);
 		}
 		second_step = true;
 	}
 
-	swap_vectors(ifdict[0], ifdict[1]);
+	swap_directions(&test->ifobj_rx, &test->ifobj_tx);
 
 	print_ksft_result();
 }
 
-static void swap_xsk_res(void)
+static void swap_xsk_resources(struct ifobject *ifobj_tx, struct ifobject *ifobj_rx)
 {
-	xsk_socket__delete(ifdict_tx->xsk->xsk);
-	xsk_umem__delete(ifdict_tx->umem->umem);
-	xsk_socket__delete(ifdict_rx->xsk->xsk);
-	xsk_umem__delete(ifdict_rx->umem->umem);
-	ifdict_tx->umem = &ifdict_tx->umem_arr[1];
-	ifdict_tx->xsk = &ifdict_tx->xsk_arr[1];
-	ifdict_rx->umem = &ifdict_rx->umem_arr[1];
-	ifdict_rx->xsk = &ifdict_rx->xsk_arr[1];
+	xsk_socket__delete(ifobj_tx->xsk->xsk);
+	xsk_umem__delete(ifobj_tx->umem->umem);
+	xsk_socket__delete(ifobj_rx->xsk->xsk);
+	xsk_umem__delete(ifobj_rx->umem->umem);
+	ifobj_tx->umem = &ifobj_tx->umem_arr[1];
+	ifobj_tx->xsk = &ifobj_tx->xsk_arr[1];
+	ifobj_rx->umem = &ifobj_rx->umem_arr[1];
+	ifobj_rx->xsk = &ifobj_rx->xsk_arr[1];
 }
 
-static void testapp_bpf_res(void)
+static void testapp_bpf_res(struct test_spec *test)
 {
 	int i;
 
 	for (i = 0; i < MAX_BPF_ITER; i++) {
 		print_verbose("Creating socket\n");
-		testapp_validate();
+		testapp_validate_traffic(test);
 		if (!second_step)
-			swap_xsk_res();
+			swap_xsk_resources(test->ifobj_tx, test->ifobj_rx);
 		second_step = true;
 	}
 
 	print_ksft_result();
 }
 
-static void testapp_stats(void)
+static void testapp_stats(struct test_spec *test)
 {
 	for (int i = 0; i < STAT_TEST_TYPE_MAX; i++) {
+		test_spec_reset(test);
 		stat_test_type = i;
 
 		/* reset defaults */
@@ -968,7 +1003,7 @@ static void testapp_stats(void)
 		default:
 			break;
 		}
-		testapp_validate();
+		testapp_validate_traffic(test);
 	}
 
 	print_ksft_result();
@@ -992,16 +1027,11 @@ static void init_iface(struct ifobject *ifobj, const char *dst_mac, const char *
 	ifobj->dst_port = dst_port;
 	ifobj->src_port = src_port;
 
-	if (vector == tx)
-		ifdict_tx = ifobj;
-	else
-		ifdict_rx = ifobj;
-
 	ifobj->fv.vector = vector;
 	ifobj->func_ptr = func_ptr;
 }
 
-static void run_pkt_test(int mode, int type)
+static void run_pkt_test(struct test_spec *test, int mode, int type)
 {
 	test_type = type;
 
@@ -1027,19 +1057,19 @@ static void run_pkt_test(int mode, int type)
 
 	switch (test_type) {
 	case TEST_TYPE_STATS:
-		testapp_stats();
+		testapp_stats(test);
 		break;
 	case TEST_TYPE_TEARDOWN:
-		testapp_teardown();
+		testapp_teardown(test);
 		break;
 	case TEST_TYPE_BIDI:
-		testapp_bidi();
+		testapp_bidi(test);
 		break;
 	case TEST_TYPE_BPF_RES:
-		testapp_bpf_res();
+		testapp_bpf_res(test);
 		break;
 	default:
-		testapp_validate();
+		testapp_validate_traffic(test);
 		break;
 	}
 }
@@ -1079,36 +1109,47 @@ static void ifobject_delete(struct ifobject *ifobj)
 int main(int argc, char **argv)
 {
 	struct rlimit _rlim = { RLIM_INFINITY, RLIM_INFINITY };
-	int i, j;
+	struct ifobject *ifobj_tx, *ifobj_rx;
+	struct test_spec test;
+	u32 i, j;
 
 	if (setrlimit(RLIMIT_MEMLOCK, &_rlim))
 		exit_with_error(errno);
 
-	for (i = 0; i < MAX_INTERFACES; i++) {
-		ifdict[i] = ifobject_create();
-		if (!ifdict[i])
-			exit_with_error(ENOMEM);
-	}
+	ifobj_tx = ifobject_create();
+	if (!ifobj_tx)
+		exit_with_error(ENOMEM);
+	ifobj_rx = ifobject_create();
+	if (!ifobj_rx)
+		exit_with_error(ENOMEM);
+
+	test_spec_init(&test, ifobj_tx, ifobj_rx);
 
 	setlocale(LC_ALL, "");
 
-	parse_command_line(argc, argv);
+	parse_command_line(&test, argc, argv);
+
+	if (!validate_interface(ifobj_tx) || !validate_interface(ifobj_rx)) {
+		usage(basename(argv[0]));
+		ksft_exit_xfail();
+	}
 
-	init_iface(ifdict[tx], MAC1, MAC2, IP1, IP2, UDP_PORT1, UDP_PORT2, tx,
+	init_iface(ifobj_tx, MAC1, MAC2, IP1, IP2, UDP_PORT1, UDP_PORT2, tx,
 		   worker_testapp_validate_tx);
-	init_iface(ifdict[rx], MAC2, MAC1, IP2, IP1, UDP_PORT2, UDP_PORT1, rx,
+	init_iface(ifobj_rx, MAC2, MAC1, IP2, IP1, UDP_PORT2, UDP_PORT1, rx,
 		   worker_testapp_validate_rx);
 
 	ksft_set_plan(TEST_MODE_MAX * TEST_TYPE_MAX);
 
 	for (i = 0; i < TEST_MODE_MAX; i++)
 		for (j = 0; j < TEST_TYPE_MAX; j++) {
-			run_pkt_test(i, j);
+			test_spec_init(&test, ifobj_tx, ifobj_rx);
+			run_pkt_test(&test, i, j);
 			usleep(USLEEP_MAX);
 		}
 
-	for (i = 0; i < MAX_INTERFACES; i++)
-		ifobject_delete(ifdict[i]);
+	ifobject_delete(ifobj_tx);
+	ifobject_delete(ifobj_rx);
 
 	ksft_exit_pass();
 	return 0;
diff --git a/tools/testing/selftests/bpf/xdpxceiver.h b/tools/testing/selftests/bpf/xdpxceiver.h
index 799d524eb425..e279aa893438 100644
--- a/tools/testing/selftests/bpf/xdpxceiver.h
+++ b/tools/testing/selftests/bpf/xdpxceiver.h
@@ -137,9 +137,10 @@ struct ifobject {
 	u8 src_mac[ETH_ALEN];
 };
 
-static struct ifobject *ifdict[MAX_INTERFACES];
-static struct ifobject *ifdict_rx;
-static struct ifobject *ifdict_tx;
+struct test_spec {
+	struct ifobject *ifobj_tx;
+	struct ifobject *ifobj_rx;
+};
 
 /*threads*/
 pthread_barrier_t barr;
-- 
cgit v1.2.3


From 83f4ae2f26bd67c58d528c3967c5ad3e58098be3 Mon Sep 17 00:00:00 2001
From: Magnus Karlsson <magnus.karlsson@intel.com>
Date: Tue, 7 Sep 2021 09:19:12 +0200
Subject: selftests: xsk: Move num_frames and frame_headroom to xsk_umem_info

Move the global variables num_frames and frame_headroom to struct
xsk_umem_info. They describe properties of the umem so no reason for
them to be global.

Signed-off-by: Magnus Karlsson <magnus.karlsson@intel.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Link: https://lore.kernel.org/bpf/20210907071928.9750-5-magnus.karlsson@gmail.com
---
 tools/testing/selftests/bpf/xdpxceiver.c | 20 ++++++++++----------
 tools/testing/selftests/bpf/xdpxceiver.h |  4 ++--
 2 files changed, 12 insertions(+), 12 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/xdpxceiver.c b/tools/testing/selftests/bpf/xdpxceiver.c
index a6bcc7453860..56ee03fda2b3 100644
--- a/tools/testing/selftests/bpf/xdpxceiver.c
+++ b/tools/testing/selftests/bpf/xdpxceiver.c
@@ -241,7 +241,7 @@ static int xsk_configure_umem(struct xsk_umem_info *umem, void *buffer, u64 size
 		.fill_size = XSK_RING_PROD__DEFAULT_NUM_DESCS,
 		.comp_size = XSK_RING_CONS__DEFAULT_NUM_DESCS,
 		.frame_size = XSK_UMEM__DEFAULT_FRAME_SIZE,
-		.frame_headroom = frame_headroom,
+		.frame_headroom = umem->frame_headroom,
 		.flags = XSK_UMEM__DEFAULT_FLAGS
 	};
 	int ret;
@@ -406,6 +406,7 @@ static void __test_spec_init(struct test_spec *test, struct ifobject *ifobj_tx,
 		for (j = 0; j < MAX_SOCKETS; j++) {
 			memset(&ifobj->umem_arr[j], 0, sizeof(ifobj->umem_arr[j]));
 			memset(&ifobj->xsk_arr[j], 0, sizeof(ifobj->xsk_arr[j]));
+			ifobj->umem_arr[j].num_frames = DEFAULT_PKT_CNT / 4;
 		}
 	}
 
@@ -433,7 +434,7 @@ static struct pkt *pkt_stream_get_pkt(struct pkt_stream *pkt_stream, u32 pkt_nb)
 	return &pkt_stream->pkts[pkt_nb];
 }
 
-static struct pkt_stream *pkt_stream_generate(u32 nb_pkts, u32 pkt_len)
+static struct pkt_stream *pkt_stream_generate(struct xsk_umem_info *umem, u32 nb_pkts, u32 pkt_len)
 {
 	struct pkt_stream *pkt_stream;
 	u32 i;
@@ -448,7 +449,7 @@ static struct pkt_stream *pkt_stream_generate(u32 nb_pkts, u32 pkt_len)
 
 	pkt_stream->nb_pkts = nb_pkts;
 	for (i = 0; i < nb_pkts; i++) {
-		pkt_stream->pkts[i].addr = (i % num_frames) * XSK_UMEM__DEFAULT_FRAME_SIZE;
+		pkt_stream->pkts[i].addr = (i % umem->num_frames) * XSK_UMEM__DEFAULT_FRAME_SIZE;
 		pkt_stream->pkts[i].len = pkt_len;
 		pkt_stream->pkts[i].payload = i;
 	}
@@ -766,7 +767,7 @@ static void tx_stats_validate(struct ifobject *ifobject)
 
 static void thread_common_ops(struct ifobject *ifobject, void *bufs)
 {
-	u64 umem_sz = num_frames * XSK_UMEM__DEFAULT_FRAME_SIZE;
+	u64 umem_sz = ifobject->umem->num_frames * XSK_UMEM__DEFAULT_FRAME_SIZE;
 	int mmap_flags = MAP_PRIVATE | MAP_ANONYMOUS | MAP_NORESERVE;
 	size_t mmap_sz = umem_sz;
 	int ctr = 0, ret;
@@ -885,9 +886,10 @@ static void testapp_validate_traffic(struct test_spec *test)
 		exit_with_error(errno);
 
 	if (stat_test_type == STAT_TEST_TX_INVALID)
-		pkt_stream = pkt_stream_generate(DEFAULT_PKT_CNT, XSK_UMEM__INVALID_FRAME_SIZE);
+		pkt_stream = pkt_stream_generate(test->ifobj_tx->umem, DEFAULT_PKT_CNT,
+						 XSK_UMEM__INVALID_FRAME_SIZE);
 	else
-		pkt_stream = pkt_stream_generate(DEFAULT_PKT_CNT, PKT_SIZE);
+		pkt_stream = pkt_stream_generate(test->ifobj_tx->umem, DEFAULT_PKT_CNT, PKT_SIZE);
 	ifobj_tx->pkt_stream = pkt_stream;
 	ifobj_rx->pkt_stream = pkt_stream;
 
@@ -988,12 +990,11 @@ static void testapp_stats(struct test_spec *test)
 
 		/* reset defaults */
 		rxqsize = XSK_RING_CONS__DEFAULT_NUM_DESCS;
-		frame_headroom = XSK_UMEM__DEFAULT_FRAME_HEADROOM;
 
 		switch (stat_test_type) {
 		case STAT_TEST_RX_DROPPED:
-			frame_headroom = XSK_UMEM__DEFAULT_FRAME_SIZE -
-						XDP_PACKET_HEADROOM - 1;
+			test->ifobj_rx->umem->frame_headroom = XSK_UMEM__DEFAULT_FRAME_SIZE -
+				XDP_PACKET_HEADROOM - 1;
 			break;
 		case STAT_TEST_RX_FULL:
 			rxqsize = RX_FULL_RXQSIZE;
@@ -1040,7 +1041,6 @@ static void run_pkt_test(struct test_spec *test, int mode, int type)
 	second_step = 0;
 	stat_test_type = -1;
 	rxqsize = XSK_RING_CONS__DEFAULT_NUM_DESCS;
-	frame_headroom = XSK_UMEM__DEFAULT_FRAME_HEADROOM;
 
 	configured_mode = mode;
 
diff --git a/tools/testing/selftests/bpf/xdpxceiver.h b/tools/testing/selftests/bpf/xdpxceiver.h
index e279aa893438..0d93a9e6c4f3 100644
--- a/tools/testing/selftests/bpf/xdpxceiver.h
+++ b/tools/testing/selftests/bpf/xdpxceiver.h
@@ -71,7 +71,6 @@ enum stat_test_type {
 
 static int configured_mode;
 static bool opt_pkt_dump;
-static u32 num_frames = DEFAULT_PKT_CNT / 4;
 static bool second_step;
 static int test_type;
 
@@ -81,12 +80,13 @@ static u32 xdp_flags = XDP_FLAGS_UPDATE_IF_NOEXIST;
 static u32 xdp_bind_flags = XDP_USE_NEED_WAKEUP | XDP_COPY;
 static int stat_test_type;
 static u32 rxqsize;
-static u32 frame_headroom;
 
 struct xsk_umem_info {
 	struct xsk_ring_prod fq;
 	struct xsk_ring_cons cq;
 	struct xsk_umem *umem;
+	u32 num_frames;
+	u32 frame_headroom;
 	void *buffer;
 };
 
-- 
cgit v1.2.3


From 4bf8ee65ba4ebf6b0d732cca8ecde2d5e1898d8a Mon Sep 17 00:00:00 2001
From: Magnus Karlsson <magnus.karlsson@intel.com>
Date: Tue, 7 Sep 2021 09:19:13 +0200
Subject: selftests: xsk: Move rxqsize into xsk_socket_info

Move the global variable rxqsize to struct xsk_socket_info as it
describes the size of a ring in that struct. By default, it is set to
the size dictated by libbpf.

Signed-off-by: Magnus Karlsson <magnus.karlsson@intel.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Link: https://lore.kernel.org/bpf/20210907071928.9750-6-magnus.karlsson@gmail.com
---
 tools/testing/selftests/bpf/xdpxceiver.c | 9 +++------
 tools/testing/selftests/bpf/xdpxceiver.h | 2 +-
 2 files changed, 4 insertions(+), 7 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/xdpxceiver.c b/tools/testing/selftests/bpf/xdpxceiver.c
index 56ee03fda2b3..28bf62c56190 100644
--- a/tools/testing/selftests/bpf/xdpxceiver.c
+++ b/tools/testing/selftests/bpf/xdpxceiver.c
@@ -276,7 +276,7 @@ static int xsk_configure_socket(struct xsk_socket_info *xsk, struct xsk_umem_inf
 	struct xsk_ring_prod *txr;
 
 	xsk->umem = umem;
-	cfg.rx_size = rxqsize;
+	cfg.rx_size = xsk->rxqsize;
 	cfg.tx_size = XSK_RING_PROD__DEFAULT_NUM_DESCS;
 	cfg.libbpf_flags = 0;
 	cfg.xdp_flags = xdp_flags;
@@ -407,6 +407,7 @@ static void __test_spec_init(struct test_spec *test, struct ifobject *ifobj_tx,
 			memset(&ifobj->umem_arr[j], 0, sizeof(ifobj->umem_arr[j]));
 			memset(&ifobj->xsk_arr[j], 0, sizeof(ifobj->xsk_arr[j]));
 			ifobj->umem_arr[j].num_frames = DEFAULT_PKT_CNT / 4;
+			ifobj->xsk_arr[j].rxqsize = XSK_RING_CONS__DEFAULT_NUM_DESCS;
 		}
 	}
 
@@ -988,16 +989,13 @@ static void testapp_stats(struct test_spec *test)
 		test_spec_reset(test);
 		stat_test_type = i;
 
-		/* reset defaults */
-		rxqsize = XSK_RING_CONS__DEFAULT_NUM_DESCS;
-
 		switch (stat_test_type) {
 		case STAT_TEST_RX_DROPPED:
 			test->ifobj_rx->umem->frame_headroom = XSK_UMEM__DEFAULT_FRAME_SIZE -
 				XDP_PACKET_HEADROOM - 1;
 			break;
 		case STAT_TEST_RX_FULL:
-			rxqsize = RX_FULL_RXQSIZE;
+			test->ifobj_rx->xsk->rxqsize = RX_FULL_RXQSIZE;
 			break;
 		case STAT_TEST_TX_INVALID:
 			continue;
@@ -1040,7 +1038,6 @@ static void run_pkt_test(struct test_spec *test, int mode, int type)
 	xdp_flags = XDP_FLAGS_UPDATE_IF_NOEXIST;
 	second_step = 0;
 	stat_test_type = -1;
-	rxqsize = XSK_RING_CONS__DEFAULT_NUM_DESCS;
 
 	configured_mode = mode;
 
diff --git a/tools/testing/selftests/bpf/xdpxceiver.h b/tools/testing/selftests/bpf/xdpxceiver.h
index 0d93a9e6c4f3..09e4e015b1bf 100644
--- a/tools/testing/selftests/bpf/xdpxceiver.h
+++ b/tools/testing/selftests/bpf/xdpxceiver.h
@@ -79,7 +79,6 @@ static bool opt_verbose;
 static u32 xdp_flags = XDP_FLAGS_UPDATE_IF_NOEXIST;
 static u32 xdp_bind_flags = XDP_USE_NEED_WAKEUP | XDP_COPY;
 static int stat_test_type;
-static u32 rxqsize;
 
 struct xsk_umem_info {
 	struct xsk_ring_prod fq;
@@ -96,6 +95,7 @@ struct xsk_socket_info {
 	struct xsk_umem_info *umem;
 	struct xsk_socket *xsk;
 	u32 outstanding_tx;
+	u32 rxqsize;
 };
 
 struct flow_vector {
-- 
cgit v1.2.3


From c160d7afba8f52c16b16111f8cbedd87f8d16d75 Mon Sep 17 00:00:00 2001
From: Magnus Karlsson <magnus.karlsson@intel.com>
Date: Tue, 7 Sep 2021 09:19:14 +0200
Subject: selftests: xsk: Make frame_size configurable

Make the frame size configurable instead of it being hard coded to a
default. This is a property of the umem and will make it possible to
implement tests for different umem frame sizes in a later patch.

Signed-off-by: Magnus Karlsson <magnus.karlsson@intel.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Link: https://lore.kernel.org/bpf/20210907071928.9750-7-magnus.karlsson@gmail.com
---
 tools/testing/selftests/bpf/xdpxceiver.c | 11 ++++++-----
 tools/testing/selftests/bpf/xdpxceiver.h |  1 +
 2 files changed, 7 insertions(+), 5 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/xdpxceiver.c b/tools/testing/selftests/bpf/xdpxceiver.c
index 28bf62c56190..79cf082a7581 100644
--- a/tools/testing/selftests/bpf/xdpxceiver.c
+++ b/tools/testing/selftests/bpf/xdpxceiver.c
@@ -240,7 +240,7 @@ static int xsk_configure_umem(struct xsk_umem_info *umem, void *buffer, u64 size
 	struct xsk_umem_config cfg = {
 		.fill_size = XSK_RING_PROD__DEFAULT_NUM_DESCS,
 		.comp_size = XSK_RING_CONS__DEFAULT_NUM_DESCS,
-		.frame_size = XSK_UMEM__DEFAULT_FRAME_SIZE,
+		.frame_size = umem->frame_size,
 		.frame_headroom = umem->frame_headroom,
 		.flags = XSK_UMEM__DEFAULT_FLAGS
 	};
@@ -264,7 +264,7 @@ static void xsk_populate_fill_ring(struct xsk_umem_info *umem)
 	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__fill_addr(&umem->fq, idx++) = i * umem->frame_size;
 	xsk_ring_prod__submit(&umem->fq, XSK_RING_PROD__DEFAULT_NUM_DESCS);
 }
 
@@ -407,6 +407,7 @@ static void __test_spec_init(struct test_spec *test, struct ifobject *ifobj_tx,
 			memset(&ifobj->umem_arr[j], 0, sizeof(ifobj->umem_arr[j]));
 			memset(&ifobj->xsk_arr[j], 0, sizeof(ifobj->xsk_arr[j]));
 			ifobj->umem_arr[j].num_frames = DEFAULT_PKT_CNT / 4;
+			ifobj->umem_arr[j].frame_size = XSK_UMEM__DEFAULT_FRAME_SIZE;
 			ifobj->xsk_arr[j].rxqsize = XSK_RING_CONS__DEFAULT_NUM_DESCS;
 		}
 	}
@@ -450,7 +451,7 @@ static struct pkt_stream *pkt_stream_generate(struct xsk_umem_info *umem, u32 nb
 
 	pkt_stream->nb_pkts = nb_pkts;
 	for (i = 0; i < nb_pkts; i++) {
-		pkt_stream->pkts[i].addr = (i % umem->num_frames) * XSK_UMEM__DEFAULT_FRAME_SIZE;
+		pkt_stream->pkts[i].addr = (i % umem->num_frames) * umem->frame_size;
 		pkt_stream->pkts[i].len = pkt_len;
 		pkt_stream->pkts[i].payload = i;
 	}
@@ -768,7 +769,7 @@ static void tx_stats_validate(struct ifobject *ifobject)
 
 static void thread_common_ops(struct ifobject *ifobject, void *bufs)
 {
-	u64 umem_sz = ifobject->umem->num_frames * XSK_UMEM__DEFAULT_FRAME_SIZE;
+	u64 umem_sz = ifobject->umem->num_frames * ifobject->umem->frame_size;
 	int mmap_flags = MAP_PRIVATE | MAP_ANONYMOUS | MAP_NORESERVE;
 	size_t mmap_sz = umem_sz;
 	int ctr = 0, ret;
@@ -991,7 +992,7 @@ static void testapp_stats(struct test_spec *test)
 
 		switch (stat_test_type) {
 		case STAT_TEST_RX_DROPPED:
-			test->ifobj_rx->umem->frame_headroom = XSK_UMEM__DEFAULT_FRAME_SIZE -
+			test->ifobj_rx->umem->frame_headroom = test->ifobj_rx->umem->frame_size -
 				XDP_PACKET_HEADROOM - 1;
 			break;
 		case STAT_TEST_RX_FULL:
diff --git a/tools/testing/selftests/bpf/xdpxceiver.h b/tools/testing/selftests/bpf/xdpxceiver.h
index 09e4e015b1bf..bfd14190abfc 100644
--- a/tools/testing/selftests/bpf/xdpxceiver.h
+++ b/tools/testing/selftests/bpf/xdpxceiver.h
@@ -87,6 +87,7 @@ struct xsk_umem_info {
 	u32 num_frames;
 	u32 frame_headroom;
 	void *buffer;
+	u32 frame_size;
 };
 
 struct xsk_socket_info {
-- 
cgit v1.2.3


From 53cb3cec2f1e2c2c0c3624f20675d01e84a8bbac Mon Sep 17 00:00:00 2001
From: Magnus Karlsson <magnus.karlsson@intel.com>
Date: Tue, 7 Sep 2021 09:19:15 +0200
Subject: selftests: xsx: Introduce test name in test spec

Introduce the test name in the test specification. This so we can set
the name locally in the test function and simplify the logic for
printing out test results.

Signed-off-by: Magnus Karlsson <magnus.karlsson@intel.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Link: https://lore.kernel.org/bpf/20210907071928.9750-8-magnus.karlsson@gmail.com
---
 tools/testing/selftests/bpf/xdpxceiver.c | 49 +++++++++++++++++++-------------
 tools/testing/selftests/bpf/xdpxceiver.h |  2 ++
 2 files changed, 31 insertions(+), 20 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/xdpxceiver.c b/tools/testing/selftests/bpf/xdpxceiver.c
index 79cf082a7581..8ef58081d4d2 100644
--- a/tools/testing/selftests/bpf/xdpxceiver.c
+++ b/tools/testing/selftests/bpf/xdpxceiver.c
@@ -112,13 +112,9 @@ static void __exit_with_error(int error, const char *file, const char *func, int
 
 #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%s%s\n", configured_mode ? "DRV" : "SKB",\
-			       test_type == TEST_TYPE_POLL ? "POLL" : "NOPOLL",\
-			       test_type == TEST_TYPE_TEARDOWN ? "Socket Teardown" : "",\
-			       test_type == TEST_TYPE_BIDI ? "Bi-directional Sockets" : "",\
-			       test_type == TEST_TYPE_STATS ? "Stats" : "",\
-			       test_type == TEST_TYPE_BPF_RES ? "BPF RES" : ""))
+#define print_ksft_result(test)\
+	(ksft_test_result_pass("PASS: %s %s\n", configured_mode ? "DRV" : "SKB", \
+			       (test)->name))
 
 static void memset32_htonl(void *dest, u32 val, u32 size)
 {
@@ -428,6 +424,11 @@ static void test_spec_reset(struct test_spec *test)
 	__test_spec_init(test, test->ifobj_tx, test->ifobj_rx);
 }
 
+static void test_spec_set_name(struct test_spec *test, const char *name)
+{
+	strncpy(test->name, name, MAX_TEST_NAME_SIZE);
+}
+
 static struct pkt *pkt_stream_get_pkt(struct pkt_stream *pkt_stream, u32 pkt_nb)
 {
 	if (pkt_nb >= pkt_stream->nb_pkts)
@@ -880,8 +881,6 @@ static void testapp_validate_traffic(struct test_spec *test)
 {
 	struct ifobject *ifobj_tx = test->ifobj_tx;
 	struct ifobject *ifobj_rx = test->ifobj_rx;
-	bool bidi = test_type == TEST_TYPE_BIDI;
-	bool bpf = test_type == TEST_TYPE_BPF_RES;
 	struct pkt_stream *pkt_stream;
 
 	if (pthread_barrier_init(&barr, NULL, 2))
@@ -907,21 +906,17 @@ static void testapp_validate_traffic(struct test_spec *test)
 
 	pthread_join(t1, NULL);
 	pthread_join(t0, NULL);
-
-	if (!(test_type == TEST_TYPE_TEARDOWN) && !bidi && !bpf && !(test_type == TEST_TYPE_STATS))
-		print_ksft_result();
 }
 
 static void testapp_teardown(struct test_spec *test)
 {
 	int i;
 
+	test_spec_set_name(test, "TEARDOWN");
 	for (i = 0; i < MAX_TEARDOWN_ITER; i++) {
 		testapp_validate_traffic(test);
 		test_spec_reset(test);
 	}
-
-	print_ksft_result();
 }
 
 static void swap_directions(struct ifobject **ifobj1, struct ifobject **ifobj2)
@@ -942,6 +937,7 @@ static void swap_directions(struct ifobject **ifobj1, struct ifobject **ifobj2)
 
 static void testapp_bidi(struct test_spec *test)
 {
+	test_spec_set_name(test, "BIDIRECTIONAL");
 	for (int i = 0; i < MAX_BIDI_ITER; i++) {
 		print_verbose("Creating socket\n");
 		testapp_validate_traffic(test);
@@ -953,8 +949,6 @@ static void testapp_bidi(struct test_spec *test)
 	}
 
 	swap_directions(&test->ifobj_rx, &test->ifobj_tx);
-
-	print_ksft_result();
 }
 
 static void swap_xsk_resources(struct ifobject *ifobj_tx, struct ifobject *ifobj_rx)
@@ -973,6 +967,7 @@ static void testapp_bpf_res(struct test_spec *test)
 {
 	int i;
 
+	test_spec_set_name(test, "BPF_RES");
 	for (i = 0; i < MAX_BPF_ITER; i++) {
 		print_verbose("Creating socket\n");
 		testapp_validate_traffic(test);
@@ -980,8 +975,6 @@ static void testapp_bpf_res(struct test_spec *test)
 			swap_xsk_resources(test->ifobj_tx, test->ifobj_rx);
 		second_step = true;
 	}
-
-	print_ksft_result();
 }
 
 static void testapp_stats(struct test_spec *test)
@@ -992,21 +985,28 @@ static void testapp_stats(struct test_spec *test)
 
 		switch (stat_test_type) {
 		case STAT_TEST_RX_DROPPED:
+			test_spec_set_name(test, "STAT_RX_DROPPED");
 			test->ifobj_rx->umem->frame_headroom = test->ifobj_rx->umem->frame_size -
 				XDP_PACKET_HEADROOM - 1;
 			break;
 		case STAT_TEST_RX_FULL:
+			test_spec_set_name(test, "STAT_RX_FULL");
 			test->ifobj_rx->xsk->rxqsize = RX_FULL_RXQSIZE;
 			break;
 		case STAT_TEST_TX_INVALID:
+			test_spec_set_name(test, "STAT_TX_INVALID");
 			continue;
+		case STAT_TEST_RX_FILL_EMPTY:
+			test_spec_set_name(test, "STAT_RX_FILL_EMPTY");
+			break;
 		default:
 			break;
 		}
 		testapp_validate_traffic(test);
 	}
 
-	print_ksft_result();
+	/* To only see the whole stat set being completed unless an individual test fails. */
+	test_spec_set_name(test, "STATS");
 }
 
 static void init_iface(struct ifobject *ifobj, const char *dst_mac, const char *src_mac,
@@ -1066,10 +1066,19 @@ static void run_pkt_test(struct test_spec *test, int mode, int type)
 	case TEST_TYPE_BPF_RES:
 		testapp_bpf_res(test);
 		break;
-	default:
+	case TEST_TYPE_NOPOLL:
+		test_spec_set_name(test, "RUN_TO_COMPLETION");
+		testapp_validate_traffic(test);
+		break;
+	case TEST_TYPE_POLL:
+		test_spec_set_name(test, "POLL");
 		testapp_validate_traffic(test);
 		break;
+	default:
+		break;
 	}
+
+	print_ksft_result(test);
 }
 
 static struct ifobject *ifobject_create(void)
diff --git a/tools/testing/selftests/bpf/xdpxceiver.h b/tools/testing/selftests/bpf/xdpxceiver.h
index bfd14190abfc..15eab31b3b32 100644
--- a/tools/testing/selftests/bpf/xdpxceiver.h
+++ b/tools/testing/selftests/bpf/xdpxceiver.h
@@ -22,6 +22,7 @@
 #define MAX_INTERFACES_NAMESPACE_CHARS 10
 #define MAX_SOCKS 1
 #define MAX_SOCKETS 2
+#define MAX_TEST_NAME_SIZE 32
 #define MAX_TEARDOWN_ITER 10
 #define MAX_BIDI_ITER 2
 #define MAX_BPF_ITER 2
@@ -141,6 +142,7 @@ struct ifobject {
 struct test_spec {
 	struct ifobject *ifobj_tx;
 	struct ifobject *ifobj_rx;
+	char name[MAX_TEST_NAME_SIZE];
 };
 
 /*threads*/
-- 
cgit v1.2.3


From 119d4b02feb5c3c5045f0b42a6c48d853ab40917 Mon Sep 17 00:00:00 2001
From: Magnus Karlsson <magnus.karlsson@intel.com>
Date: Tue, 7 Sep 2021 09:19:16 +0200
Subject: selftests: xsk: Add use_poll to ifobject

Add a use_poll option to the ifobject so that we do not need to use a
test specific if-statement in the test runner.

Signed-off-by: Magnus Karlsson <magnus.karlsson@intel.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Link: https://lore.kernel.org/bpf/20210907071928.9750-9-magnus.karlsson@gmail.com
---
 tools/testing/selftests/bpf/xdpxceiver.c | 5 ++++-
 tools/testing/selftests/bpf/xdpxceiver.h | 1 +
 2 files changed, 5 insertions(+), 1 deletion(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/xdpxceiver.c b/tools/testing/selftests/bpf/xdpxceiver.c
index 8ef58081d4d2..9a98c45933c5 100644
--- a/tools/testing/selftests/bpf/xdpxceiver.c
+++ b/tools/testing/selftests/bpf/xdpxceiver.c
@@ -393,6 +393,7 @@ static void __test_spec_init(struct test_spec *test, struct ifobject *ifobj_tx,
 
 		ifobj->umem = &ifobj->umem_arr[0];
 		ifobj->xsk = &ifobj->xsk_arr[0];
+		ifobj->use_poll = false;
 
 		if (i == tx)
 			ifobj->fv.vector = tx;
@@ -684,7 +685,7 @@ static void send_pkts(struct ifobject *ifobject)
 	while (pkt_cnt < ifobject->pkt_stream->nb_pkts) {
 		u32 sent;
 
-		if (test_type == TEST_TYPE_POLL) {
+		if (ifobject->use_poll) {
 			int ret;
 
 			ret = poll(fds, 1, POLL_TMOUT);
@@ -1071,6 +1072,8 @@ static void run_pkt_test(struct test_spec *test, int mode, int type)
 		testapp_validate_traffic(test);
 		break;
 	case TEST_TYPE_POLL:
+		test->ifobj_tx->use_poll = true;
+		test->ifobj_rx->use_poll = true;
 		test_spec_set_name(test, "POLL");
 		testapp_validate_traffic(test);
 		break;
diff --git a/tools/testing/selftests/bpf/xdpxceiver.h b/tools/testing/selftests/bpf/xdpxceiver.h
index 15eab31b3b32..e02a4dd71bfb 100644
--- a/tools/testing/selftests/bpf/xdpxceiver.h
+++ b/tools/testing/selftests/bpf/xdpxceiver.h
@@ -135,6 +135,7 @@ struct ifobject {
 	u32 src_ip;
 	u16 src_port;
 	u16 dst_port;
+	bool use_poll;
 	u8 dst_mac[ETH_ALEN];
 	u8 src_mac[ETH_ALEN];
 };
-- 
cgit v1.2.3


From 1856c24db0a8c51122b7b87909a98f379309ff69 Mon Sep 17 00:00:00 2001
From: Magnus Karlsson <magnus.karlsson@intel.com>
Date: Tue, 7 Sep 2021 09:19:17 +0200
Subject: selftests: xsk: Introduce rx_on and tx_on in ifobject

Introduce rx_on and tx_on in the ifobject so that we can describe if
the thread should create a socket with only tx, rx, or both. This
eliminates some test specific if statements from the code. We can also
eliminate the flow vector structure now as this is fully specified
by the tx_on and rx_on variables.

Signed-off-by: Magnus Karlsson <magnus.karlsson@intel.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Link: https://lore.kernel.org/bpf/20210907071928.9750-10-magnus.karlsson@gmail.com
---
 tools/testing/selftests/bpf/xdpxceiver.c | 34 +++++++++++++-------------------
 tools/testing/selftests/bpf/xdpxceiver.h | 10 ++--------
 2 files changed, 16 insertions(+), 28 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/xdpxceiver.c b/tools/testing/selftests/bpf/xdpxceiver.c
index 9a98c45933c5..a896d5845c0e 100644
--- a/tools/testing/selftests/bpf/xdpxceiver.c
+++ b/tools/testing/selftests/bpf/xdpxceiver.c
@@ -278,14 +278,8 @@ static int xsk_configure_socket(struct xsk_socket_info *xsk, struct xsk_umem_inf
 	cfg.xdp_flags = xdp_flags;
 	cfg.bind_flags = xdp_bind_flags;
 
-	if (test_type != TEST_TYPE_BIDI) {
-		rxr = (ifobject->fv.vector == rx) ? &xsk->rx : NULL;
-		txr = (ifobject->fv.vector == tx) ? &xsk->tx : NULL;
-	} else {
-		rxr = &xsk->rx;
-		txr = &xsk->tx;
-	}
-
+	txr = ifobject->tx_on ? &xsk->tx : NULL;
+	rxr = ifobject->rx_on ? &xsk->rx : NULL;
 	return xsk_socket__create(&xsk->xsk, ifobject->ifname, qid, umem->umem, rxr, txr, &cfg);
 }
 
@@ -395,10 +389,13 @@ static void __test_spec_init(struct test_spec *test, struct ifobject *ifobj_tx,
 		ifobj->xsk = &ifobj->xsk_arr[0];
 		ifobj->use_poll = false;
 
-		if (i == tx)
-			ifobj->fv.vector = tx;
-		else
-			ifobj->fv.vector = rx;
+		if (i == 0) {
+			ifobj->rx_on = false;
+			ifobj->tx_on = true;
+		} else {
+			ifobj->rx_on = true;
+			ifobj->tx_on = false;
+		}
 
 		for (j = 0; j < MAX_SOCKETS; j++) {
 			memset(&ifobj->umem_arr[j], 0, sizeof(ifobj->umem_arr[j]));
@@ -923,14 +920,10 @@ static void testapp_teardown(struct test_spec *test)
 static void swap_directions(struct ifobject **ifobj1, struct ifobject **ifobj2)
 {
 	thread_func_t tmp_func_ptr = (*ifobj1)->func_ptr;
-	enum fvector tmp_vector = (*ifobj1)->fv.vector;
 	struct ifobject *tmp_ifobj = (*ifobj1);
 
 	(*ifobj1)->func_ptr = (*ifobj2)->func_ptr;
-	(*ifobj1)->fv.vector = (*ifobj2)->fv.vector;
-
 	(*ifobj2)->func_ptr = tmp_func_ptr;
-	(*ifobj2)->fv.vector = tmp_vector;
 
 	*ifobj1 = *ifobj2;
 	*ifobj2 = tmp_ifobj;
@@ -939,6 +932,8 @@ static void swap_directions(struct ifobject **ifobj1, struct ifobject **ifobj2)
 static void testapp_bidi(struct test_spec *test)
 {
 	test_spec_set_name(test, "BIDIRECTIONAL");
+	test->ifobj_tx->rx_on = true;
+	test->ifobj_rx->tx_on = true;
 	for (int i = 0; i < MAX_BIDI_ITER; i++) {
 		print_verbose("Creating socket\n");
 		testapp_validate_traffic(test);
@@ -1012,7 +1007,7 @@ static void testapp_stats(struct test_spec *test)
 
 static void init_iface(struct ifobject *ifobj, const char *dst_mac, const char *src_mac,
 		       const char *dst_ip, const char *src_ip, const u16 dst_port,
-		       const u16 src_port, enum fvector vector, thread_func_t func_ptr)
+		       const u16 src_port, thread_func_t func_ptr)
 {
 	struct in_addr ip;
 
@@ -1028,7 +1023,6 @@ static void init_iface(struct ifobject *ifobj, const char *dst_mac, const char *
 	ifobj->dst_port = dst_port;
 	ifobj->src_port = src_port;
 
-	ifobj->fv.vector = vector;
 	ifobj->func_ptr = func_ptr;
 }
 
@@ -1144,9 +1138,9 @@ int main(int argc, char **argv)
 		ksft_exit_xfail();
 	}
 
-	init_iface(ifobj_tx, MAC1, MAC2, IP1, IP2, UDP_PORT1, UDP_PORT2, tx,
+	init_iface(ifobj_tx, MAC1, MAC2, IP1, IP2, UDP_PORT1, UDP_PORT2,
 		   worker_testapp_validate_tx);
-	init_iface(ifobj_rx, MAC2, MAC1, IP2, IP1, UDP_PORT2, UDP_PORT1, rx,
+	init_iface(ifobj_rx, MAC2, MAC1, IP2, IP1, UDP_PORT2, UDP_PORT1,
 		   worker_testapp_validate_rx);
 
 	ksft_set_plan(TEST_MODE_MAX * TEST_TYPE_MAX);
diff --git a/tools/testing/selftests/bpf/xdpxceiver.h b/tools/testing/selftests/bpf/xdpxceiver.h
index e02a4dd71bfb..03ff52897d7b 100644
--- a/tools/testing/selftests/bpf/xdpxceiver.h
+++ b/tools/testing/selftests/bpf/xdpxceiver.h
@@ -100,13 +100,6 @@ struct xsk_socket_info {
 	u32 rxqsize;
 };
 
-struct flow_vector {
-	enum fvector {
-		tx,
-		rx,
-	} vector;
-};
-
 struct pkt {
 	u64 addr;
 	u32 len;
@@ -127,7 +120,6 @@ struct ifobject {
 	struct xsk_socket_info *xsk_arr;
 	struct xsk_umem_info *umem;
 	struct xsk_umem_info *umem_arr;
-	struct flow_vector fv;
 	thread_func_t func_ptr;
 	struct pkt_stream *pkt_stream;
 	int ns_fd;
@@ -135,6 +127,8 @@ struct ifobject {
 	u32 src_ip;
 	u16 src_port;
 	u16 dst_port;
+	bool tx_on;
+	bool rx_on;
 	bool use_poll;
 	u8 dst_mac[ETH_ALEN];
 	u8 src_mac[ETH_ALEN];
-- 
cgit v1.2.3


From 55be575dc13ccfc9bf27ebb5af938b70206a9eb5 Mon Sep 17 00:00:00 2001
From: Magnus Karlsson <magnus.karlsson@intel.com>
Date: Tue, 7 Sep 2021 09:19:18 +0200
Subject: selftests: xsk: Replace second_step global variable

Replace the second_step global variable with a test specification
variable called total_steps that a test can be set to indicate how
many times the packet stream should be sent without reinitializing any
sockets. This eliminates test specific code in the test runner around
the bidirectional test.

The total_steps variable is 1 by default as most tests only need a
single round of packets.

Signed-off-by: Magnus Karlsson <magnus.karlsson@intel.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Link: https://lore.kernel.org/bpf/20210907071928.9750-11-magnus.karlsson@gmail.com
---
 tools/testing/selftests/bpf/xdpxceiver.c | 77 ++++++++++++++------------------
 tools/testing/selftests/bpf/xdpxceiver.h |  4 +-
 2 files changed, 36 insertions(+), 45 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/xdpxceiver.c b/tools/testing/selftests/bpf/xdpxceiver.c
index a896d5845c0e..0a3e28c9e2a9 100644
--- a/tools/testing/selftests/bpf/xdpxceiver.c
+++ b/tools/testing/selftests/bpf/xdpxceiver.c
@@ -408,6 +408,8 @@ static void __test_spec_init(struct test_spec *test, struct ifobject *ifobj_tx,
 
 	test->ifobj_tx = ifobj_tx;
 	test->ifobj_rx = ifobj_rx;
+	test->current_step = 0;
+	test->total_steps = 1;
 }
 
 static void test_spec_init(struct test_spec *test, struct ifobject *ifobj_tx,
@@ -713,7 +715,7 @@ static bool rx_stats_are_valid(struct ifobject *ifobject)
 	optlen = sizeof(stats);
 	err = getsockopt(fd, SOL_XDP, XDP_STATISTICS, &stats, &optlen);
 	if (err) {
-		ksft_test_result_fail("ERROR: [%s] getsockopt(XDP_STATISTICS) error %u %s\n",
+		ksft_test_result_fail("ERROR Rx: [%s] getsockopt(XDP_STATISTICS) error %u %s\n",
 				      __func__, -err, strerror(-err));
 		return true;
 	}
@@ -754,7 +756,7 @@ static void tx_stats_validate(struct ifobject *ifobject)
 	optlen = sizeof(stats);
 	err = getsockopt(fd, SOL_XDP, XDP_STATISTICS, &stats, &optlen);
 	if (err) {
-		ksft_test_result_fail("ERROR: [%s] getsockopt(XDP_STATISTICS) error %u %s\n",
+		ksft_test_result_fail("ERROR Tx: [%s] getsockopt(XDP_STATISTICS) error %u %s\n",
 				      __func__, -err, strerror(-err));
 		return;
 	}
@@ -766,12 +768,13 @@ static void tx_stats_validate(struct ifobject *ifobject)
 			      __func__, stats.tx_invalid_descs, ifobject->pkt_stream->nb_pkts);
 }
 
-static void thread_common_ops(struct ifobject *ifobject, void *bufs)
+static void thread_common_ops(struct test_spec *test, struct ifobject *ifobject)
 {
 	u64 umem_sz = ifobject->umem->num_frames * ifobject->umem->frame_size;
 	int mmap_flags = MAP_PRIVATE | MAP_ANONYMOUS | MAP_NORESERVE;
 	size_t mmap_sz = umem_sz;
 	int ctr = 0, ret;
+	void *bufs;
 
 	ifobject->ns_fd = switch_namespace(ifobject->nsname);
 
@@ -813,26 +816,19 @@ static void thread_common_ops(struct ifobject *ifobject, void *bufs)
 	ifobject->xsk = &ifobject->xsk_arr[0];
 }
 
-static bool testapp_is_test_two_stepped(void)
-{
-	return (test_type != TEST_TYPE_BIDI && test_type != TEST_TYPE_BPF_RES) || second_step;
-}
-
 static void testapp_cleanup_xsk_res(struct ifobject *ifobj)
 {
-	if (testapp_is_test_two_stepped()) {
-		xsk_socket__delete(ifobj->xsk->xsk);
-		(void)xsk_umem__delete(ifobj->umem->umem);
-	}
+	xsk_socket__delete(ifobj->xsk->xsk);
+	xsk_umem__delete(ifobj->umem->umem);
 }
 
 static void *worker_testapp_validate_tx(void *arg)
 {
-	struct ifobject *ifobject = (struct ifobject *)arg;
-	void *bufs = NULL;
+	struct test_spec *test = (struct test_spec *)arg;
+	struct ifobject *ifobject = test->ifobj_tx;
 
-	if (!second_step)
-		thread_common_ops(ifobject, bufs);
+	if (test->current_step == 1)
+		thread_common_ops(test, ifobject);
 
 	print_verbose("Sending %d packets on interface %s\n", ifobject->pkt_stream->nb_pkts,
 		      ifobject->ifname);
@@ -841,18 +837,19 @@ static void *worker_testapp_validate_tx(void *arg)
 	if (stat_test_type == STAT_TEST_TX_INVALID)
 		tx_stats_validate(ifobject);
 
-	testapp_cleanup_xsk_res(ifobject);
+	if (test->total_steps == test->current_step)
+		testapp_cleanup_xsk_res(ifobject);
 	pthread_exit(NULL);
 }
 
 static void *worker_testapp_validate_rx(void *arg)
 {
-	struct ifobject *ifobject = (struct ifobject *)arg;
+	struct test_spec *test = (struct test_spec *)arg;
+	struct ifobject *ifobject = test->ifobj_rx;
 	struct pollfd fds[MAX_SOCKS] = { };
-	void *bufs = NULL;
 
-	if (!second_step)
-		thread_common_ops(ifobject, bufs);
+	if (test->current_step == 1)
+		thread_common_ops(test, ifobject);
 
 	if (stat_test_type != STAT_TEST_RX_FILL_EMPTY)
 		xsk_populate_fill_ring(ifobject->umem);
@@ -871,7 +868,8 @@ static void *worker_testapp_validate_rx(void *arg)
 	if (test_type == TEST_TYPE_TEARDOWN)
 		print_verbose("Destroying socket\n");
 
-	testapp_cleanup_xsk_res(ifobject);
+	if (test->total_steps == test->current_step)
+		testapp_cleanup_xsk_res(ifobject);
 	pthread_exit(NULL);
 }
 
@@ -891,16 +889,17 @@ static void testapp_validate_traffic(struct test_spec *test)
 		pkt_stream = pkt_stream_generate(test->ifobj_tx->umem, DEFAULT_PKT_CNT, PKT_SIZE);
 	ifobj_tx->pkt_stream = pkt_stream;
 	ifobj_rx->pkt_stream = pkt_stream;
+	test->current_step++;
 
 	/*Spawn RX thread */
-	pthread_create(&t0, NULL, ifobj_rx->func_ptr, ifobj_rx);
+	pthread_create(&t0, NULL, ifobj_rx->func_ptr, test);
 
 	pthread_barrier_wait(&barr);
 	if (pthread_barrier_destroy(&barr))
 		exit_with_error(errno);
 
 	/*Spawn TX thread */
-	pthread_create(&t1, NULL, ifobj_tx->func_ptr, ifobj_tx);
+	pthread_create(&t1, NULL, ifobj_tx->func_ptr, test);
 
 	pthread_join(t1, NULL);
 	pthread_join(t0, NULL);
@@ -934,15 +933,12 @@ static void testapp_bidi(struct test_spec *test)
 	test_spec_set_name(test, "BIDIRECTIONAL");
 	test->ifobj_tx->rx_on = true;
 	test->ifobj_rx->tx_on = true;
-	for (int i = 0; i < MAX_BIDI_ITER; i++) {
-		print_verbose("Creating socket\n");
-		testapp_validate_traffic(test);
-		if (!second_step) {
-			print_verbose("Switching Tx/Rx vectors\n");
-			swap_directions(&test->ifobj_rx, &test->ifobj_tx);
-		}
-		second_step = true;
-	}
+	test->total_steps = 2;
+	testapp_validate_traffic(test);
+
+	print_verbose("Switching Tx/Rx vectors\n");
+	swap_directions(&test->ifobj_rx, &test->ifobj_tx);
+	testapp_validate_traffic(test);
 
 	swap_directions(&test->ifobj_rx, &test->ifobj_tx);
 }
@@ -961,16 +957,12 @@ static void swap_xsk_resources(struct ifobject *ifobj_tx, struct ifobject *ifobj
 
 static void testapp_bpf_res(struct test_spec *test)
 {
-	int i;
-
 	test_spec_set_name(test, "BPF_RES");
-	for (i = 0; i < MAX_BPF_ITER; i++) {
-		print_verbose("Creating socket\n");
-		testapp_validate_traffic(test);
-		if (!second_step)
-			swap_xsk_resources(test->ifobj_tx, test->ifobj_rx);
-		second_step = true;
-	}
+	test->total_steps = 2;
+	testapp_validate_traffic(test);
+
+	swap_xsk_resources(test->ifobj_tx, test->ifobj_rx);
+	testapp_validate_traffic(test);
 }
 
 static void testapp_stats(struct test_spec *test)
@@ -1032,7 +1024,6 @@ static void run_pkt_test(struct test_spec *test, int mode, int type)
 
 	/* reset defaults after potential previous test */
 	xdp_flags = XDP_FLAGS_UPDATE_IF_NOEXIST;
-	second_step = 0;
 	stat_test_type = -1;
 
 	configured_mode = mode;
diff --git a/tools/testing/selftests/bpf/xdpxceiver.h b/tools/testing/selftests/bpf/xdpxceiver.h
index 03ff52897d7b..ea505a4cb8c0 100644
--- a/tools/testing/selftests/bpf/xdpxceiver.h
+++ b/tools/testing/selftests/bpf/xdpxceiver.h
@@ -24,7 +24,6 @@
 #define MAX_SOCKETS 2
 #define MAX_TEST_NAME_SIZE 32
 #define MAX_TEARDOWN_ITER 10
-#define MAX_BIDI_ITER 2
 #define MAX_BPF_ITER 2
 #define PKT_HDR_SIZE (sizeof(struct ethhdr) + sizeof(struct iphdr) + \
 			sizeof(struct udphdr))
@@ -72,7 +71,6 @@ enum stat_test_type {
 
 static int configured_mode;
 static bool opt_pkt_dump;
-static bool second_step;
 static int test_type;
 
 static bool opt_verbose;
@@ -137,6 +135,8 @@ struct ifobject {
 struct test_spec {
 	struct ifobject *ifobj_tx;
 	struct ifobject *ifobj_rx;
+	u16 total_steps;
+	u16 current_step;
 	char name[MAX_TEST_NAME_SIZE];
 };
 
-- 
cgit v1.2.3


From 85c6c95739703620abb75e5fcc46ad3068c50f48 Mon Sep 17 00:00:00 2001
From: Magnus Karlsson <magnus.karlsson@intel.com>
Date: Tue, 7 Sep 2021 09:19:19 +0200
Subject: selftests: xsk: Specify number of sockets to create

Add the ability in the test specification to specify numbers of
sockets to create. The default is one socket. This is then used to
remove test specific if-statements around the bpf_res tests.

Signed-off-by: Magnus Karlsson <magnus.karlsson@intel.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Link: https://lore.kernel.org/bpf/20210907071928.9750-12-magnus.karlsson@gmail.com
---
 tools/testing/selftests/bpf/xdpxceiver.c | 59 ++++++++++++++------------------
 tools/testing/selftests/bpf/xdpxceiver.h |  2 +-
 2 files changed, 27 insertions(+), 34 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/xdpxceiver.c b/tools/testing/selftests/bpf/xdpxceiver.c
index 0a3e28c9e2a9..06fa767191af 100644
--- a/tools/testing/selftests/bpf/xdpxceiver.c
+++ b/tools/testing/selftests/bpf/xdpxceiver.c
@@ -231,7 +231,7 @@ static void gen_udp_csum(struct udphdr *udp_hdr, struct iphdr *ip_hdr)
 	    udp_csum(ip_hdr->saddr, ip_hdr->daddr, UDP_PKT_SIZE, IPPROTO_UDP, (u16 *)udp_hdr);
 }
 
-static int xsk_configure_umem(struct xsk_umem_info *umem, void *buffer, u64 size, int idx)
+static int xsk_configure_umem(struct xsk_umem_info *umem, void *buffer, u64 size)
 {
 	struct xsk_umem_config cfg = {
 		.fill_size = XSK_RING_PROD__DEFAULT_NUM_DESCS,
@@ -410,6 +410,7 @@ static void __test_spec_init(struct test_spec *test, struct ifobject *ifobj_tx,
 	test->ifobj_rx = ifobj_rx;
 	test->current_step = 0;
 	test->total_steps = 1;
+	test->nb_sockets = 1;
 }
 
 static void test_spec_init(struct test_spec *test, struct ifobject *ifobj_tx,
@@ -770,46 +771,37 @@ static void tx_stats_validate(struct ifobject *ifobject)
 
 static void thread_common_ops(struct test_spec *test, struct ifobject *ifobject)
 {
-	u64 umem_sz = ifobject->umem->num_frames * ifobject->umem->frame_size;
-	int mmap_flags = MAP_PRIVATE | MAP_ANONYMOUS | MAP_NORESERVE;
-	size_t mmap_sz = umem_sz;
-	int ctr = 0, ret;
-	void *bufs;
+	u32 i;
 
 	ifobject->ns_fd = switch_namespace(ifobject->nsname);
 
-	if (test_type == TEST_TYPE_BPF_RES)
-		mmap_sz *= 2;
-
-	bufs = mmap(NULL, mmap_sz, PROT_READ | PROT_WRITE, mmap_flags, -1, 0);
-	if (bufs == MAP_FAILED)
-		exit_with_error(errno);
+	for (i = 0; i < test->nb_sockets; i++) {
+		u64 umem_sz = ifobject->umem->num_frames * ifobject->umem->frame_size;
+		int mmap_flags = MAP_PRIVATE | MAP_ANONYMOUS | MAP_NORESERVE;
+		u32 ctr = 0;
+		void *bufs;
 
-	while (ctr++ < SOCK_RECONF_CTR) {
-		ret = xsk_configure_umem(&ifobject->umem_arr[0], bufs, umem_sz, 0);
-		if (ret)
-			exit_with_error(-ret);
+		bufs = mmap(NULL, umem_sz, PROT_READ | PROT_WRITE, mmap_flags, -1, 0);
+		if (bufs == MAP_FAILED)
+			exit_with_error(errno);
 
-		ret = xsk_configure_socket(&ifobject->xsk_arr[0], &ifobject->umem_arr[0],
-					   ifobject, 0);
-		if (!ret)
-			break;
+		while (ctr++ < SOCK_RECONF_CTR) {
+			int ret;
 
-		/* Retry Create Socket if it fails as xsk_socket__create() is asynchronous */
-		if (ctr >= SOCK_RECONF_CTR)
-			exit_with_error(-ret);
-		usleep(USLEEP_MAX);
-	}
+			ret = xsk_configure_umem(&ifobject->umem_arr[i], bufs, umem_sz);
+			if (ret)
+				exit_with_error(-ret);
 
-	if (test_type == TEST_TYPE_BPF_RES) {
-		ret = xsk_configure_umem(&ifobject->umem_arr[1], (u8 *)bufs + umem_sz, umem_sz, 1);
-		if (ret)
-			exit_with_error(-ret);
+			ret = xsk_configure_socket(&ifobject->xsk_arr[i], &ifobject->umem_arr[i],
+						   ifobject, i);
+			if (!ret)
+				break;
 
-		ret = xsk_configure_socket(&ifobject->xsk_arr[1], &ifobject->umem_arr[1],
-					   ifobject, 1);
-		if (ret)
-			exit_with_error(-ret);
+			/* Retry if it fails as xsk_socket__create() is asynchronous */
+			if (ctr >= SOCK_RECONF_CTR)
+				exit_with_error(-ret);
+			usleep(USLEEP_MAX);
+		}
 	}
 
 	ifobject->umem = &ifobject->umem_arr[0];
@@ -959,6 +951,7 @@ static void testapp_bpf_res(struct test_spec *test)
 {
 	test_spec_set_name(test, "BPF_RES");
 	test->total_steps = 2;
+	test->nb_sockets = 2;
 	testapp_validate_traffic(test);
 
 	swap_xsk_resources(test->ifobj_tx, test->ifobj_rx);
diff --git a/tools/testing/selftests/bpf/xdpxceiver.h b/tools/testing/selftests/bpf/xdpxceiver.h
index ea505a4cb8c0..c09b73fd9878 100644
--- a/tools/testing/selftests/bpf/xdpxceiver.h
+++ b/tools/testing/selftests/bpf/xdpxceiver.h
@@ -24,7 +24,6 @@
 #define MAX_SOCKETS 2
 #define MAX_TEST_NAME_SIZE 32
 #define MAX_TEARDOWN_ITER 10
-#define MAX_BPF_ITER 2
 #define PKT_HDR_SIZE (sizeof(struct ethhdr) + sizeof(struct iphdr) + \
 			sizeof(struct udphdr))
 #define MIN_PKT_SIZE 64
@@ -137,6 +136,7 @@ struct test_spec {
 	struct ifobject *ifobj_rx;
 	u16 total_steps;
 	u16 current_step;
+	u16 nb_sockets;
 	char name[MAX_TEST_NAME_SIZE];
 };
 
-- 
cgit v1.2.3


From af6731d1e1c69b4ee32063acd51ec86ece0a1ced Mon Sep 17 00:00:00 2001
From: Magnus Karlsson <magnus.karlsson@intel.com>
Date: Tue, 7 Sep 2021 09:19:20 +0200
Subject: selftests: xsk: Make xdp_flags and bind_flags local

Make xdp_flags and bind_flags local instead of global by moving them
into the interface object. These flags decide if the socket should be
created in SKB mode or in DRV mode and therefore they are sticky and
will survive a test_spec_reset. Since every test is first run in SKB
mode then in DRV mode, this change only happens once. With this
change, the configured_mode global variable can also be
erradicated. The first test_spec_init() also becomes superfluous and
can be eliminated.

Signed-off-by: Magnus Karlsson <magnus.karlsson@intel.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Link: https://lore.kernel.org/bpf/20210907071928.9750-13-magnus.karlsson@gmail.com
---
 tools/testing/selftests/bpf/xdpxceiver.c | 57 ++++++++++++++++----------------
 tools/testing/selftests/bpf/xdpxceiver.h |  6 ++--
 2 files changed, 31 insertions(+), 32 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/xdpxceiver.c b/tools/testing/selftests/bpf/xdpxceiver.c
index 06fa767191af..3a1afece7c2c 100644
--- a/tools/testing/selftests/bpf/xdpxceiver.c
+++ b/tools/testing/selftests/bpf/xdpxceiver.c
@@ -112,9 +112,10 @@ static void __exit_with_error(int error, const char *file, const char *func, int
 
 #define exit_with_error(error) __exit_with_error(error, __FILE__, __func__, __LINE__)
 
-#define print_ksft_result(test)\
-	(ksft_test_result_pass("PASS: %s %s\n", configured_mode ? "DRV" : "SKB", \
-			       (test)->name))
+#define mode_string(test) (test)->ifobj_tx->xdp_flags & XDP_FLAGS_SKB_MODE ? "SKB" : "DRV"
+
+#define print_ksft_result(test)						\
+	(ksft_test_result_pass("PASS: %s %s\n", mode_string(test), (test)->name))
 
 static void memset32_htonl(void *dest, u32 val, u32 size)
 {
@@ -275,8 +276,8 @@ static int xsk_configure_socket(struct xsk_socket_info *xsk, struct xsk_umem_inf
 	cfg.rx_size = xsk->rxqsize;
 	cfg.tx_size = XSK_RING_PROD__DEFAULT_NUM_DESCS;
 	cfg.libbpf_flags = 0;
-	cfg.xdp_flags = xdp_flags;
-	cfg.bind_flags = xdp_bind_flags;
+	cfg.xdp_flags = ifobject->xdp_flags;
+	cfg.bind_flags = ifobject->bind_flags;
 
 	txr = ifobject->tx_on ? &xsk->tx : NULL;
 	rxr = ifobject->rx_on ? &xsk->rx : NULL;
@@ -333,7 +334,8 @@ static bool validate_interface(struct ifobject *ifobj)
 	return true;
 }
 
-static void parse_command_line(struct test_spec *test, int argc, char **argv)
+static void parse_command_line(struct ifobject *ifobj_tx, struct ifobject *ifobj_rx, int argc,
+			       char **argv)
 {
 	struct ifobject *ifobj;
 	u32 interface_nb = 0;
@@ -351,9 +353,9 @@ static void parse_command_line(struct test_spec *test, int argc, char **argv)
 		switch (c) {
 		case 'i':
 			if (interface_nb == 0)
-				ifobj = test->ifobj_tx;
+				ifobj = ifobj_tx;
 			else if (interface_nb == 1)
-				ifobj = test->ifobj_rx;
+				ifobj = ifobj_rx;
 			else
 				break;
 
@@ -414,9 +416,24 @@ static void __test_spec_init(struct test_spec *test, struct ifobject *ifobj_tx,
 }
 
 static void test_spec_init(struct test_spec *test, struct ifobject *ifobj_tx,
-			   struct ifobject *ifobj_rx)
+			   struct ifobject *ifobj_rx, enum test_mode mode)
 {
+	u32 i;
+
 	memset(test, 0, sizeof(*test));
+
+	for (i = 0; i < MAX_INTERFACES; i++) {
+		struct ifobject *ifobj = i ? ifobj_rx : ifobj_tx;
+
+		ifobj->xdp_flags = XDP_FLAGS_UPDATE_IF_NOEXIST;
+		if (mode == TEST_MODE_SKB)
+			ifobj->xdp_flags |= XDP_FLAGS_SKB_MODE;
+		else
+			ifobj->xdp_flags |= XDP_FLAGS_DRV_MODE;
+
+		ifobj->bind_flags = XDP_USE_NEED_WAKEUP | XDP_COPY;
+	}
+
 	__test_spec_init(test, ifobj_tx, ifobj_rx);
 }
 
@@ -1011,27 +1028,13 @@ static void init_iface(struct ifobject *ifobj, const char *dst_mac, const char *
 	ifobj->func_ptr = func_ptr;
 }
 
-static void run_pkt_test(struct test_spec *test, int mode, int type)
+static void run_pkt_test(struct test_spec *test, enum test_mode mode, enum test_type type)
 {
 	test_type = type;
 
 	/* reset defaults after potential previous test */
-	xdp_flags = XDP_FLAGS_UPDATE_IF_NOEXIST;
 	stat_test_type = -1;
 
-	configured_mode = mode;
-
-	switch (mode) {
-	case (TEST_MODE_SKB):
-		xdp_flags |= XDP_FLAGS_SKB_MODE;
-		break;
-	case (TEST_MODE_DRV):
-		xdp_flags |= XDP_FLAGS_DRV_MODE;
-		break;
-	default:
-		break;
-	}
-
 	switch (test_type) {
 	case TEST_TYPE_STATS:
 		testapp_stats(test);
@@ -1111,11 +1114,9 @@ int main(int argc, char **argv)
 	if (!ifobj_rx)
 		exit_with_error(ENOMEM);
 
-	test_spec_init(&test, ifobj_tx, ifobj_rx);
-
 	setlocale(LC_ALL, "");
 
-	parse_command_line(&test, argc, argv);
+	parse_command_line(ifobj_tx, ifobj_rx, argc, argv);
 
 	if (!validate_interface(ifobj_tx) || !validate_interface(ifobj_rx)) {
 		usage(basename(argv[0]));
@@ -1131,7 +1132,7 @@ int main(int argc, char **argv)
 
 	for (i = 0; i < TEST_MODE_MAX; i++)
 		for (j = 0; j < TEST_TYPE_MAX; j++) {
-			test_spec_init(&test, ifobj_tx, ifobj_rx);
+			test_spec_init(&test, ifobj_tx, ifobj_rx, i);
 			run_pkt_test(&test, i, j);
 			usleep(USLEEP_MAX);
 		}
diff --git a/tools/testing/selftests/bpf/xdpxceiver.h b/tools/testing/selftests/bpf/xdpxceiver.h
index c09b73fd9878..7ed16128f2ad 100644
--- a/tools/testing/selftests/bpf/xdpxceiver.h
+++ b/tools/testing/selftests/bpf/xdpxceiver.h
@@ -68,14 +68,10 @@ enum stat_test_type {
 	STAT_TEST_TYPE_MAX
 };
 
-static int configured_mode;
 static bool opt_pkt_dump;
 static int test_type;
 
 static bool opt_verbose;
-
-static u32 xdp_flags = XDP_FLAGS_UPDATE_IF_NOEXIST;
-static u32 xdp_bind_flags = XDP_USE_NEED_WAKEUP | XDP_COPY;
 static int stat_test_type;
 
 struct xsk_umem_info {
@@ -122,6 +118,8 @@ struct ifobject {
 	int ns_fd;
 	u32 dst_ip;
 	u32 src_ip;
+	u32 xdp_flags;
+	u32 bind_flags;
 	u16 src_port;
 	u16 dst_port;
 	bool tx_on;
-- 
cgit v1.2.3


From e2d850d5346c3cd751b032a7dccdd472013b8a84 Mon Sep 17 00:00:00 2001
From: Magnus Karlsson <magnus.karlsson@intel.com>
Date: Tue, 7 Sep 2021 09:19:21 +0200
Subject: selftests: xsx: Make pthreads local scope

Make the pthread_t variables local scope instead of global. No reason
for them to be global.

Signed-off-by: Magnus Karlsson <magnus.karlsson@intel.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Link: https://lore.kernel.org/bpf/20210907071928.9750-14-magnus.karlsson@gmail.com
---
 tools/testing/selftests/bpf/xdpxceiver.c | 1 +
 tools/testing/selftests/bpf/xdpxceiver.h | 2 --
 2 files changed, 1 insertion(+), 2 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/xdpxceiver.c b/tools/testing/selftests/bpf/xdpxceiver.c
index 3a1afece7c2c..5ea78c503741 100644
--- a/tools/testing/selftests/bpf/xdpxceiver.c
+++ b/tools/testing/selftests/bpf/xdpxceiver.c
@@ -887,6 +887,7 @@ static void testapp_validate_traffic(struct test_spec *test)
 	struct ifobject *ifobj_tx = test->ifobj_tx;
 	struct ifobject *ifobj_rx = test->ifobj_rx;
 	struct pkt_stream *pkt_stream;
+	pthread_t t0, t1;
 
 	if (pthread_barrier_init(&barr, NULL, 2))
 		exit_with_error(errno);
diff --git a/tools/testing/selftests/bpf/xdpxceiver.h b/tools/testing/selftests/bpf/xdpxceiver.h
index 7ed16128f2ad..34ae4e4ea4ac 100644
--- a/tools/testing/selftests/bpf/xdpxceiver.h
+++ b/tools/testing/selftests/bpf/xdpxceiver.h
@@ -138,8 +138,6 @@ struct test_spec {
 	char name[MAX_TEST_NAME_SIZE];
 };
 
-/*threads*/
 pthread_barrier_t barr;
-pthread_t t0, t1;
 
 #endif				/* XDPXCEIVER_H */
-- 
cgit v1.2.3


From 8ce7192b508df2c54932e245bbc6ce04cfe174a7 Mon Sep 17 00:00:00 2001
From: Magnus Karlsson <magnus.karlsson@intel.com>
Date: Tue, 7 Sep 2021 09:19:22 +0200
Subject: selftests: xsk: Eliminate MAX_SOCKS define

Remove the MAX_SOCKS define as it always will be one for the forseable
future and the code does not work for any other case anyway.

Signed-off-by: Magnus Karlsson <magnus.karlsson@intel.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Link: https://lore.kernel.org/bpf/20210907071928.9750-15-magnus.karlsson@gmail.com
---
 tools/testing/selftests/bpf/xdpxceiver.c | 18 +++++++++---------
 tools/testing/selftests/bpf/xdpxceiver.h |  1 -
 2 files changed, 9 insertions(+), 10 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/xdpxceiver.c b/tools/testing/selftests/bpf/xdpxceiver.c
index 5ea78c503741..0fb5cae974de 100644
--- a/tools/testing/selftests/bpf/xdpxceiver.c
+++ b/tools/testing/selftests/bpf/xdpxceiver.c
@@ -693,11 +693,11 @@ static void wait_for_tx_completion(struct xsk_socket_info *xsk)
 
 static void send_pkts(struct ifobject *ifobject)
 {
-	struct pollfd fds[MAX_SOCKS] = { };
+	struct pollfd fds = { };
 	u32 pkt_cnt = 0;
 
-	fds[0].fd = xsk_socket__fd(ifobject->xsk->xsk);
-	fds[0].events = POLLOUT;
+	fds.fd = xsk_socket__fd(ifobject->xsk->xsk);
+	fds.events = POLLOUT;
 
 	while (pkt_cnt < ifobject->pkt_stream->nb_pkts) {
 		u32 sent;
@@ -705,11 +705,11 @@ static void send_pkts(struct ifobject *ifobject)
 		if (ifobject->use_poll) {
 			int ret;
 
-			ret = poll(fds, 1, POLL_TMOUT);
+			ret = poll(&fds, 1, POLL_TMOUT);
 			if (ret <= 0)
 				continue;
 
-			if (!(fds[0].revents & POLLOUT))
+			if (!(fds.revents & POLLOUT))
 				continue;
 		}
 
@@ -855,7 +855,7 @@ static void *worker_testapp_validate_rx(void *arg)
 {
 	struct test_spec *test = (struct test_spec *)arg;
 	struct ifobject *ifobject = test->ifobj_rx;
-	struct pollfd fds[MAX_SOCKS] = { };
+	struct pollfd fds = { };
 
 	if (test->current_step == 1)
 		thread_common_ops(test, ifobject);
@@ -863,8 +863,8 @@ static void *worker_testapp_validate_rx(void *arg)
 	if (stat_test_type != STAT_TEST_RX_FILL_EMPTY)
 		xsk_populate_fill_ring(ifobject->umem);
 
-	fds[0].fd = xsk_socket__fd(ifobject->xsk->xsk);
-	fds[0].events = POLLIN;
+	fds.fd = xsk_socket__fd(ifobject->xsk->xsk);
+	fds.events = POLLIN;
 
 	pthread_barrier_wait(&barr);
 
@@ -872,7 +872,7 @@ static void *worker_testapp_validate_rx(void *arg)
 		while (!rx_stats_are_valid(ifobject))
 			continue;
 	else
-		receive_pkts(ifobject->pkt_stream, ifobject->xsk, fds);
+		receive_pkts(ifobject->pkt_stream, ifobject->xsk, &fds);
 
 	if (test_type == TEST_TYPE_TEARDOWN)
 		print_verbose("Destroying socket\n");
diff --git a/tools/testing/selftests/bpf/xdpxceiver.h b/tools/testing/selftests/bpf/xdpxceiver.h
index 34ae4e4ea4ac..1e9a563380c8 100644
--- a/tools/testing/selftests/bpf/xdpxceiver.h
+++ b/tools/testing/selftests/bpf/xdpxceiver.h
@@ -20,7 +20,6 @@
 #define MAX_INTERFACES 2
 #define MAX_INTERFACE_NAME_CHARS 7
 #define MAX_INTERFACES_NAMESPACE_CHARS 10
-#define MAX_SOCKS 1
 #define MAX_SOCKETS 2
 #define MAX_TEST_NAME_SIZE 32
 #define MAX_TEARDOWN_ITER 10
-- 
cgit v1.2.3


From 8abf6f725a9e50cf8e8bd44edb2a577d98f0d775 Mon Sep 17 00:00:00 2001
From: Magnus Karlsson <magnus.karlsson@intel.com>
Date: Tue, 7 Sep 2021 09:19:23 +0200
Subject: selftests: xsk: Allow for invalid packets

Allow for invalid packets to be sent. These are verified by the Rx
thread not to be received. Or put in another way, if they are
received, the test will fail. This feature will be used to eliminate
an if statement for a stats test and will also be used by other tests
in later patches. The previous code could only deal with valid
packets.

Signed-off-by: Magnus Karlsson <magnus.karlsson@intel.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Link: https://lore.kernel.org/bpf/20210907071928.9750-16-magnus.karlsson@gmail.com
---
 tools/testing/selftests/bpf/xdpxceiver.c | 16 ++++++++++------
 tools/testing/selftests/bpf/xdpxceiver.h |  1 +
 2 files changed, 11 insertions(+), 6 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/xdpxceiver.c b/tools/testing/selftests/bpf/xdpxceiver.c
index 0fb5cae974de..09d2854c10e6 100644
--- a/tools/testing/selftests/bpf/xdpxceiver.c
+++ b/tools/testing/selftests/bpf/xdpxceiver.c
@@ -473,6 +473,11 @@ static struct pkt_stream *pkt_stream_generate(struct xsk_umem_info *umem, u32 nb
 		pkt_stream->pkts[i].addr = (i % umem->num_frames) * umem->frame_size;
 		pkt_stream->pkts[i].len = pkt_len;
 		pkt_stream->pkts[i].payload = i;
+
+		if (pkt_len > umem->frame_size)
+			pkt_stream->pkts[i].valid = false;
+		else
+			pkt_stream->pkts[i].valid = true;
 	}
 
 	return pkt_stream;
@@ -658,7 +663,7 @@ static void receive_pkts(struct pkt_stream *pkt_stream, struct xsk_socket_info *
 static u32 __send_pkts(struct ifobject *ifobject, u32 pkt_nb)
 {
 	struct xsk_socket_info *xsk = ifobject->xsk;
-	u32 i, idx;
+	u32 i, idx, valid_pkts = 0;
 
 	while (xsk_ring_prod__reserve(&xsk->tx, BATCH_SIZE, &idx) < BATCH_SIZE)
 		complete_pkts(xsk, BATCH_SIZE);
@@ -673,14 +678,13 @@ static u32 __send_pkts(struct ifobject *ifobject, u32 pkt_nb)
 		tx_desc->addr = pkt->addr;
 		tx_desc->len = pkt->len;
 		pkt_nb++;
+		if (pkt->valid)
+			valid_pkts++;
 	}
 
 	xsk_ring_prod__submit(&xsk->tx, i);
-	if (stat_test_type != STAT_TEST_TX_INVALID)
-		xsk->outstanding_tx += i;
-	else if (xsk_ring_prod__needs_wakeup(&xsk->tx))
-		kick_tx(xsk);
-	complete_pkts(xsk, i);
+	xsk->outstanding_tx += valid_pkts;
+	complete_pkts(xsk, BATCH_SIZE);
 
 	return i;
 }
diff --git a/tools/testing/selftests/bpf/xdpxceiver.h b/tools/testing/selftests/bpf/xdpxceiver.h
index 1e9a563380c8..c5baa7c5f560 100644
--- a/tools/testing/selftests/bpf/xdpxceiver.h
+++ b/tools/testing/selftests/bpf/xdpxceiver.h
@@ -96,6 +96,7 @@ struct pkt {
 	u64 addr;
 	u32 len;
 	u32 payload;
+	bool valid;
 };
 
 struct pkt_stream {
-- 
cgit v1.2.3


From 605091c5100ddc1ae0d67a74b688d8755658d3c9 Mon Sep 17 00:00:00 2001
From: Magnus Karlsson <magnus.karlsson@intel.com>
Date: Tue, 7 Sep 2021 09:19:24 +0200
Subject: selftests: xsk: Introduce replacing the default packet stream

Introduce the concept of a default packet stream that is the set of
packets sent by most tests. Then add the ability to replace it for a
test that would like to send or receive something else through the use
of the function pkt_stream_replace() and then restored with
pkt_stream_restore_default(). These are then used to convert the
STAT_TEST_TX_INVALID to use these new APIs.

Signed-off-by: Magnus Karlsson <magnus.karlsson@intel.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Link: https://lore.kernel.org/bpf/20210907071928.9750-17-magnus.karlsson@gmail.com
---
 tools/testing/selftests/bpf/xdpxceiver.c | 65 +++++++++++++++++++++++---------
 tools/testing/selftests/bpf/xdpxceiver.h |  1 +
 2 files changed, 48 insertions(+), 18 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/xdpxceiver.c b/tools/testing/selftests/bpf/xdpxceiver.c
index 09d2854c10e6..70a8435e3d5e 100644
--- a/tools/testing/selftests/bpf/xdpxceiver.c
+++ b/tools/testing/selftests/bpf/xdpxceiver.c
@@ -390,6 +390,7 @@ static void __test_spec_init(struct test_spec *test, struct ifobject *ifobj_tx,
 		ifobj->umem = &ifobj->umem_arr[0];
 		ifobj->xsk = &ifobj->xsk_arr[0];
 		ifobj->use_poll = false;
+		ifobj->pkt_stream = test->pkt_stream_default;
 
 		if (i == 0) {
 			ifobj->rx_on = false;
@@ -418,9 +419,12 @@ static void __test_spec_init(struct test_spec *test, struct ifobject *ifobj_tx,
 static void test_spec_init(struct test_spec *test, struct ifobject *ifobj_tx,
 			   struct ifobject *ifobj_rx, enum test_mode mode)
 {
+	struct pkt_stream *pkt_stream;
 	u32 i;
 
+	pkt_stream = test->pkt_stream_default;
 	memset(test, 0, sizeof(*test));
+	test->pkt_stream_default = pkt_stream;
 
 	for (i = 0; i < MAX_INTERFACES; i++) {
 		struct ifobject *ifobj = i ? ifobj_rx : ifobj_tx;
@@ -455,6 +459,19 @@ static struct pkt *pkt_stream_get_pkt(struct pkt_stream *pkt_stream, u32 pkt_nb)
 	return &pkt_stream->pkts[pkt_nb];
 }
 
+static void pkt_stream_delete(struct pkt_stream *pkt_stream)
+{
+	free(pkt_stream->pkts);
+	free(pkt_stream);
+}
+
+static void pkt_stream_restore_default(struct test_spec *test)
+{
+	pkt_stream_delete(test->ifobj_tx->pkt_stream);
+	test->ifobj_tx->pkt_stream = test->pkt_stream_default;
+	test->ifobj_rx->pkt_stream = test->pkt_stream_default;
+}
+
 static struct pkt_stream *pkt_stream_generate(struct xsk_umem_info *umem, u32 nb_pkts, u32 pkt_len)
 {
 	struct pkt_stream *pkt_stream;
@@ -483,6 +500,15 @@ static struct pkt_stream *pkt_stream_generate(struct xsk_umem_info *umem, u32 nb
 	return pkt_stream;
 }
 
+static void pkt_stream_replace(struct test_spec *test, u32 nb_pkts, u32 pkt_len)
+{
+	struct pkt_stream *pkt_stream;
+
+	pkt_stream = pkt_stream_generate(test->ifobj_tx->umem, nb_pkts, pkt_len);
+	test->ifobj_tx->pkt_stream = pkt_stream;
+	test->ifobj_rx->pkt_stream = pkt_stream;
+}
+
 static struct pkt *pkt_generate(struct ifobject *ifobject, u32 pkt_nb)
 {
 	struct pkt *pkt = pkt_stream_get_pkt(ifobject->pkt_stream, pkt_nb);
@@ -557,7 +583,7 @@ static bool is_pkt_valid(struct pkt *pkt, void *buffer, const struct xdp_desc *d
 	if (iphdr->version == IP_PKT_VER && iphdr->tos == IP_PKT_TOS) {
 		u32 seqnum = ntohl(*((u32 *)(data + PKT_HDR_SIZE)));
 
-		if (opt_pkt_dump && test_type != TEST_TYPE_STATS)
+		if (opt_pkt_dump)
 			pkt_dump(data, PKT_SIZE);
 
 		if (pkt->len != desc->len) {
@@ -598,9 +624,6 @@ static void complete_pkts(struct xsk_socket_info *xsk, int batch_size)
 	unsigned int rcvd;
 	u32 idx;
 
-	if (!xsk->outstanding_tx)
-		return;
-
 	if (xsk_ring_prod__needs_wakeup(&xsk->tx))
 		kick_tx(xsk);
 
@@ -831,6 +854,7 @@ static void thread_common_ops(struct test_spec *test, struct ifobject *ifobject)
 
 static void testapp_cleanup_xsk_res(struct ifobject *ifobj)
 {
+	print_verbose("Destroying socket\n");
 	xsk_socket__delete(ifobj->xsk->xsk);
 	xsk_umem__delete(ifobj->umem->umem);
 }
@@ -878,9 +902,6 @@ static void *worker_testapp_validate_rx(void *arg)
 	else
 		receive_pkts(ifobject->pkt_stream, ifobject->xsk, &fds);
 
-	if (test_type == TEST_TYPE_TEARDOWN)
-		print_verbose("Destroying socket\n");
-
 	if (test->total_steps == test->current_step)
 		testapp_cleanup_xsk_res(ifobject);
 	pthread_exit(NULL);
@@ -890,19 +911,11 @@ static void testapp_validate_traffic(struct test_spec *test)
 {
 	struct ifobject *ifobj_tx = test->ifobj_tx;
 	struct ifobject *ifobj_rx = test->ifobj_rx;
-	struct pkt_stream *pkt_stream;
 	pthread_t t0, t1;
 
 	if (pthread_barrier_init(&barr, NULL, 2))
 		exit_with_error(errno);
 
-	if (stat_test_type == STAT_TEST_TX_INVALID)
-		pkt_stream = pkt_stream_generate(test->ifobj_tx->umem, DEFAULT_PKT_CNT,
-						 XSK_UMEM__INVALID_FRAME_SIZE);
-	else
-		pkt_stream = pkt_stream_generate(test->ifobj_tx->umem, DEFAULT_PKT_CNT, PKT_SIZE);
-	ifobj_tx->pkt_stream = pkt_stream;
-	ifobj_rx->pkt_stream = pkt_stream;
 	test->current_step++;
 
 	/*Spawn RX thread */
@@ -982,7 +995,9 @@ static void testapp_bpf_res(struct test_spec *test)
 
 static void testapp_stats(struct test_spec *test)
 {
-	for (int i = 0; i < STAT_TEST_TYPE_MAX; i++) {
+	int i;
+
+	for (i = 0; i < STAT_TEST_TYPE_MAX; i++) {
 		test_spec_reset(test);
 		stat_test_type = i;
 
@@ -991,21 +1006,27 @@ static void testapp_stats(struct test_spec *test)
 			test_spec_set_name(test, "STAT_RX_DROPPED");
 			test->ifobj_rx->umem->frame_headroom = test->ifobj_rx->umem->frame_size -
 				XDP_PACKET_HEADROOM - 1;
+			testapp_validate_traffic(test);
 			break;
 		case STAT_TEST_RX_FULL:
 			test_spec_set_name(test, "STAT_RX_FULL");
 			test->ifobj_rx->xsk->rxqsize = RX_FULL_RXQSIZE;
+			testapp_validate_traffic(test);
 			break;
 		case STAT_TEST_TX_INVALID:
 			test_spec_set_name(test, "STAT_TX_INVALID");
-			continue;
+			pkt_stream_replace(test, DEFAULT_PKT_CNT, XSK_UMEM__INVALID_FRAME_SIZE);
+			testapp_validate_traffic(test);
+
+			pkt_stream_restore_default(test);
+			break;
 		case STAT_TEST_RX_FILL_EMPTY:
 			test_spec_set_name(test, "STAT_RX_FILL_EMPTY");
+			testapp_validate_traffic(test);
 			break;
 		default:
 			break;
 		}
-		testapp_validate_traffic(test);
 	}
 
 	/* To only see the whole stat set being completed unless an individual test fails. */
@@ -1105,6 +1126,7 @@ static void ifobject_delete(struct ifobject *ifobj)
 int main(int argc, char **argv)
 {
 	struct rlimit _rlim = { RLIM_INFINITY, RLIM_INFINITY };
+	struct pkt_stream *pkt_stream_default;
 	struct ifobject *ifobj_tx, *ifobj_rx;
 	struct test_spec test;
 	u32 i, j;
@@ -1133,6 +1155,12 @@ int main(int argc, char **argv)
 	init_iface(ifobj_rx, MAC2, MAC1, IP2, IP1, UDP_PORT2, UDP_PORT1,
 		   worker_testapp_validate_rx);
 
+	test_spec_init(&test, ifobj_tx, ifobj_rx, 0);
+	pkt_stream_default = pkt_stream_generate(ifobj_tx->umem, DEFAULT_PKT_CNT, PKT_SIZE);
+	if (!pkt_stream_default)
+		exit_with_error(ENOMEM);
+	test.pkt_stream_default = pkt_stream_default;
+
 	ksft_set_plan(TEST_MODE_MAX * TEST_TYPE_MAX);
 
 	for (i = 0; i < TEST_MODE_MAX; i++)
@@ -1142,6 +1170,7 @@ int main(int argc, char **argv)
 			usleep(USLEEP_MAX);
 		}
 
+	pkt_stream_delete(pkt_stream_default);
 	ifobject_delete(ifobj_tx);
 	ifobject_delete(ifobj_rx);
 
diff --git a/tools/testing/selftests/bpf/xdpxceiver.h b/tools/testing/selftests/bpf/xdpxceiver.h
index c5baa7c5f560..e27fe348ae50 100644
--- a/tools/testing/selftests/bpf/xdpxceiver.h
+++ b/tools/testing/selftests/bpf/xdpxceiver.h
@@ -132,6 +132,7 @@ struct ifobject {
 struct test_spec {
 	struct ifobject *ifobj_tx;
 	struct ifobject *ifobj_rx;
+	struct pkt_stream *pkt_stream_default;
 	u16 total_steps;
 	u16 current_step;
 	u16 nb_sockets;
-- 
cgit v1.2.3


From a4ba98dd0c693e4f0f4aa93ef210a77a72d32025 Mon Sep 17 00:00:00 2001
From: Magnus Karlsson <magnus.karlsson@intel.com>
Date: Tue, 7 Sep 2021 09:19:25 +0200
Subject: selftests: xsk: Add test for unaligned mode

Add a test for unaligned mode in which packet buffers can be placed
anywhere within the umem. Some packets are made to straddle page
boundaries in order to check for correctness. On the Tx side, buffers
are now allocated according to the addresses found in the packet
stream. Thus, the placement of buffers can be controlled with the
boolean use_addr_for_fill in the packet stream.

One new pkt_stream interface is introduced: pkt_stream_replace_half()
that replaces every other packet in the default packet stream with the
specified new packet. The constant DEFAULT_OFFSET is also
introduced. It specifies at what offset from the start of a chunk a Tx
packet is placed by the sending thread. This is just to be able to
test that it is possible to send packets at an offset not equal to
zero.

Signed-off-by: Magnus Karlsson <magnus.karlsson@intel.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Link: https://lore.kernel.org/bpf/20210907071928.9750-18-magnus.karlsson@gmail.com
---
 tools/testing/selftests/bpf/xdpxceiver.c | 127 +++++++++++++++++++++++++------
 tools/testing/selftests/bpf/xdpxceiver.h |   4 +
 2 files changed, 108 insertions(+), 23 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/xdpxceiver.c b/tools/testing/selftests/bpf/xdpxceiver.c
index 70a8435e3d5e..7cc75d1481e2 100644
--- a/tools/testing/selftests/bpf/xdpxceiver.c
+++ b/tools/testing/selftests/bpf/xdpxceiver.c
@@ -19,7 +19,7 @@
  * Virtual Ethernet interfaces.
  *
  * For each mode, the following tests are run:
- *    a. nopoll - soft-irq processing
+ *    a. nopoll - soft-irq processing in run-to-completion mode
  *    b. poll - using poll() syscall
  *    c. Socket Teardown
  *       Create a Tx and a Rx socket, Tx from one socket, Rx on another. Destroy
@@ -45,6 +45,7 @@
  *       Configure sockets at indexes 0 and 1, run a traffic on queue ids 0,
  *       then remove xsk sockets from queue 0 on both veth interfaces and
  *       finally run a traffic on queues ids 1
+ *    g. unaligned mode
  *
  * Total tests: 12
  *
@@ -243,6 +244,9 @@ static int xsk_configure_umem(struct xsk_umem_info *umem, void *buffer, u64 size
 	};
 	int ret;
 
+	if (umem->unaligned_mode)
+		cfg.flags |= XDP_UMEM_UNALIGNED_CHUNK_FLAG;
+
 	ret = xsk_umem__create(&umem->umem, buffer, size,
 			       &umem->fq, &umem->cq, &cfg);
 	if (ret)
@@ -252,19 +256,6 @@ static int xsk_configure_umem(struct xsk_umem_info *umem, void *buffer, u64 size
 	return 0;
 }
 
-static void xsk_populate_fill_ring(struct xsk_umem_info *umem)
-{
-	int ret, i;
-	u32 idx = 0;
-
-	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 * umem->frame_size;
-	xsk_ring_prod__submit(&umem->fq, XSK_RING_PROD__DEFAULT_NUM_DESCS);
-}
-
 static int xsk_configure_socket(struct xsk_socket_info *xsk, struct xsk_umem_info *umem,
 				struct ifobject *ifobject, u32 qid)
 {
@@ -477,7 +468,7 @@ static struct pkt_stream *pkt_stream_generate(struct xsk_umem_info *umem, u32 nb
 	struct pkt_stream *pkt_stream;
 	u32 i;
 
-	pkt_stream = malloc(sizeof(*pkt_stream));
+	pkt_stream = calloc(1, sizeof(*pkt_stream));
 	if (!pkt_stream)
 		exit_with_error(ENOMEM);
 
@@ -487,7 +478,8 @@ static struct pkt_stream *pkt_stream_generate(struct xsk_umem_info *umem, u32 nb
 
 	pkt_stream->nb_pkts = nb_pkts;
 	for (i = 0; i < nb_pkts; i++) {
-		pkt_stream->pkts[i].addr = (i % umem->num_frames) * umem->frame_size;
+		pkt_stream->pkts[i].addr = (i % umem->num_frames) * umem->frame_size +
+			DEFAULT_OFFSET;
 		pkt_stream->pkts[i].len = pkt_len;
 		pkt_stream->pkts[i].payload = i;
 
@@ -500,6 +492,12 @@ static struct pkt_stream *pkt_stream_generate(struct xsk_umem_info *umem, u32 nb
 	return pkt_stream;
 }
 
+static struct pkt_stream *pkt_stream_clone(struct xsk_umem_info *umem,
+					   struct pkt_stream *pkt_stream)
+{
+	return pkt_stream_generate(umem, pkt_stream->nb_pkts, pkt_stream->pkts[0].len);
+}
+
 static void pkt_stream_replace(struct test_spec *test, u32 nb_pkts, u32 pkt_len)
 {
 	struct pkt_stream *pkt_stream;
@@ -509,6 +507,22 @@ static void pkt_stream_replace(struct test_spec *test, u32 nb_pkts, u32 pkt_len)
 	test->ifobj_rx->pkt_stream = pkt_stream;
 }
 
+static void pkt_stream_replace_half(struct test_spec *test, u32 pkt_len, u32 offset)
+{
+	struct xsk_umem_info *umem = test->ifobj_tx->umem;
+	struct pkt_stream *pkt_stream;
+	u32 i;
+
+	pkt_stream = pkt_stream_clone(umem, test->pkt_stream_default);
+	for (i = 0; i < test->pkt_stream_default->nb_pkts; i += 2) {
+		pkt_stream->pkts[i].addr = (i % umem->num_frames) * umem->frame_size + offset;
+		pkt_stream->pkts[i].len = pkt_len;
+	}
+
+	test->ifobj_tx->pkt_stream = pkt_stream;
+	test->ifobj_rx->pkt_stream = pkt_stream;
+}
+
 static struct pkt *pkt_generate(struct ifobject *ifobject, u32 pkt_nb)
 {
 	struct pkt *pkt = pkt_stream_get_pkt(ifobject->pkt_stream, pkt_nb);
@@ -570,9 +584,9 @@ static void pkt_dump(void *pkt, u32 len)
 	fprintf(stdout, "---------------------------------------\n");
 }
 
-static bool is_pkt_valid(struct pkt *pkt, void *buffer, const struct xdp_desc *desc)
+static bool is_pkt_valid(struct pkt *pkt, void *buffer, u64 addr, u32 len)
 {
-	void *data = xsk_umem__get_data(buffer, desc->addr);
+	void *data = xsk_umem__get_data(buffer, addr);
 	struct iphdr *iphdr = (struct iphdr *)(data + sizeof(struct ethhdr));
 
 	if (!pkt) {
@@ -586,10 +600,10 @@ static bool is_pkt_valid(struct pkt *pkt, void *buffer, const struct xdp_desc *d
 		if (opt_pkt_dump)
 			pkt_dump(data, PKT_SIZE);
 
-		if (pkt->len != desc->len) {
+		if (pkt->len != len) {
 			ksft_test_result_fail
 				("ERROR: [%s] expected length [%d], got length [%d]\n",
-					__func__, pkt->len, desc->len);
+					__func__, pkt->len, len);
 			return false;
 		}
 
@@ -671,7 +685,7 @@ static void receive_pkts(struct pkt_stream *pkt_stream, struct xsk_socket_info *
 
 			orig = xsk_umem__extract_addr(addr);
 			addr = xsk_umem__add_offset_to_addr(addr);
-			if (!is_pkt_valid(pkt, xsk->umem->buffer, desc))
+			if (!is_pkt_valid(pkt, xsk->umem->buffer, addr, desc->len))
 				return;
 
 			*xsk_ring_prod__fill_addr(&xsk->umem->fq, idx_fq++) = orig;
@@ -815,13 +829,16 @@ static void tx_stats_validate(struct ifobject *ifobject)
 
 static void thread_common_ops(struct test_spec *test, struct ifobject *ifobject)
 {
+	int mmap_flags = MAP_PRIVATE | MAP_ANONYMOUS | MAP_NORESERVE;
 	u32 i;
 
 	ifobject->ns_fd = switch_namespace(ifobject->nsname);
 
+	if (ifobject->umem->unaligned_mode)
+		mmap_flags |= MAP_HUGETLB;
+
 	for (i = 0; i < test->nb_sockets; i++) {
 		u64 umem_sz = ifobject->umem->num_frames * ifobject->umem->frame_size;
-		int mmap_flags = MAP_PRIVATE | MAP_ANONYMOUS | MAP_NORESERVE;
 		u32 ctr = 0;
 		void *bufs;
 
@@ -879,6 +896,32 @@ static void *worker_testapp_validate_tx(void *arg)
 	pthread_exit(NULL);
 }
 
+static void xsk_populate_fill_ring(struct xsk_umem_info *umem, struct pkt_stream *pkt_stream)
+{
+	u32 idx = 0, i;
+	int ret;
+
+	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(ENOSPC);
+	for (i = 0; i < XSK_RING_PROD__DEFAULT_NUM_DESCS; i++) {
+		u64 addr;
+
+		if (pkt_stream->use_addr_for_fill) {
+			struct pkt *pkt = pkt_stream_get_pkt(pkt_stream, i);
+
+			if (!pkt)
+				break;
+			addr = pkt->addr;
+		} else {
+			addr = (i % umem->num_frames) * umem->frame_size + DEFAULT_OFFSET;
+		}
+
+		*xsk_ring_prod__fill_addr(&umem->fq, idx++) = addr;
+	}
+	xsk_ring_prod__submit(&umem->fq, XSK_RING_PROD__DEFAULT_NUM_DESCS);
+}
+
 static void *worker_testapp_validate_rx(void *arg)
 {
 	struct test_spec *test = (struct test_spec *)arg;
@@ -889,7 +932,7 @@ static void *worker_testapp_validate_rx(void *arg)
 		thread_common_ops(test, ifobject);
 
 	if (stat_test_type != STAT_TEST_RX_FILL_EMPTY)
-		xsk_populate_fill_ring(ifobject->umem);
+		xsk_populate_fill_ring(ifobject->umem, ifobject->pkt_stream);
 
 	fds.fd = xsk_socket__fd(ifobject->xsk->xsk);
 	fds.events = POLLIN;
@@ -1033,6 +1076,40 @@ static void testapp_stats(struct test_spec *test)
 	test_spec_set_name(test, "STATS");
 }
 
+/* Simple test */
+static bool hugepages_present(struct ifobject *ifobject)
+{
+	const size_t mmap_sz = 2 * ifobject->umem->num_frames * ifobject->umem->frame_size;
+	void *bufs;
+
+	bufs = mmap(NULL, mmap_sz, PROT_READ | PROT_WRITE,
+		    MAP_PRIVATE | MAP_ANONYMOUS | MAP_NORESERVE | MAP_HUGETLB, -1, 0);
+	if (bufs == MAP_FAILED)
+		return false;
+
+	munmap(bufs, mmap_sz);
+	return true;
+}
+
+static bool testapp_unaligned(struct test_spec *test)
+{
+	if (!hugepages_present(test->ifobj_tx)) {
+		ksft_test_result_skip("No 2M huge pages present.\n");
+		return false;
+	}
+
+	test_spec_set_name(test, "UNALIGNED_MODE");
+	test->ifobj_tx->umem->unaligned_mode = true;
+	test->ifobj_rx->umem->unaligned_mode = true;
+	/* Let half of the packets straddle a buffer boundrary */
+	pkt_stream_replace_half(test, PKT_SIZE, test->ifobj_tx->umem->frame_size - 32);
+	test->ifobj_rx->pkt_stream->use_addr_for_fill = true;
+	testapp_validate_traffic(test);
+
+	pkt_stream_restore_default(test);
+	return true;
+}
+
 static void init_iface(struct ifobject *ifobj, const char *dst_mac, const char *src_mac,
 		       const char *dst_ip, const char *src_ip, const u16 dst_port,
 		       const u16 src_port, thread_func_t func_ptr)
@@ -1084,6 +1161,10 @@ static void run_pkt_test(struct test_spec *test, enum test_mode mode, enum test_
 		test_spec_set_name(test, "POLL");
 		testapp_validate_traffic(test);
 		break;
+	case TEST_TYPE_UNALIGNED:
+		if (!testapp_unaligned(test))
+			return;
+		break;
 	default:
 		break;
 	}
diff --git a/tools/testing/selftests/bpf/xdpxceiver.h b/tools/testing/selftests/bpf/xdpxceiver.h
index e27fe348ae50..129801eb013c 100644
--- a/tools/testing/selftests/bpf/xdpxceiver.h
+++ b/tools/testing/selftests/bpf/xdpxceiver.h
@@ -39,6 +39,7 @@
 #define POLL_TMOUT 1000
 #define DEFAULT_PKT_CNT (4 * 1024)
 #define RX_FULL_RXQSIZE 32
+#define DEFAULT_OFFSET 256
 #define XSK_UMEM__INVALID_FRAME_SIZE (XSK_UMEM__DEFAULT_FRAME_SIZE + 1)
 
 #define print_verbose(x...) do { if (opt_verbose) ksft_print_msg(x); } while (0)
@@ -52,6 +53,7 @@ enum test_mode {
 enum test_type {
 	TEST_TYPE_NOPOLL,
 	TEST_TYPE_POLL,
+	TEST_TYPE_UNALIGNED,
 	TEST_TYPE_TEARDOWN,
 	TEST_TYPE_BIDI,
 	TEST_TYPE_STATS,
@@ -81,6 +83,7 @@ struct xsk_umem_info {
 	u32 frame_headroom;
 	void *buffer;
 	u32 frame_size;
+	bool unaligned_mode;
 };
 
 struct xsk_socket_info {
@@ -102,6 +105,7 @@ struct pkt {
 struct pkt_stream {
 	u32 nb_pkts;
 	struct pkt *pkts;
+	bool use_addr_for_fill;
 };
 
 typedef void *(*thread_func_t)(void *arg);
-- 
cgit v1.2.3


From 6ce67b5165e630a4f874e9e45bd9cca86aa4f4a6 Mon Sep 17 00:00:00 2001
From: Magnus Karlsson <magnus.karlsson@intel.com>
Date: Tue, 7 Sep 2021 09:19:26 +0200
Subject: selftests: xsk: Eliminate test specific if-statement in test runner

Eliminate a test specific if-statement for the RX_FILL_EMTPY stats
test that is present in the test runner. We can do this as we now have
the use_addr_for_fill option. Just create and empty Rx packet stream
and indicated that the test runner should use the addresses in that to
populate the fill ring. As there are no packets in the stream, the
fill ring will be empty and we will get the error stats that we want
to test.

Signed-off-by: Magnus Karlsson <magnus.karlsson@intel.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Link: https://lore.kernel.org/bpf/20210907071928.9750-19-magnus.karlsson@gmail.com
---
 tools/testing/selftests/bpf/xdpxceiver.c | 16 ++++++++++++----
 1 file changed, 12 insertions(+), 4 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/xdpxceiver.c b/tools/testing/selftests/bpf/xdpxceiver.c
index 7cc75d1481e2..4d86c4b62aa9 100644
--- a/tools/testing/selftests/bpf/xdpxceiver.c
+++ b/tools/testing/selftests/bpf/xdpxceiver.c
@@ -458,8 +458,10 @@ static void pkt_stream_delete(struct pkt_stream *pkt_stream)
 
 static void pkt_stream_restore_default(struct test_spec *test)
 {
-	pkt_stream_delete(test->ifobj_tx->pkt_stream);
-	test->ifobj_tx->pkt_stream = test->pkt_stream_default;
+	if (test->ifobj_tx->pkt_stream != test->pkt_stream_default) {
+		pkt_stream_delete(test->ifobj_tx->pkt_stream);
+		test->ifobj_tx->pkt_stream = test->pkt_stream_default;
+	}
 	test->ifobj_rx->pkt_stream = test->pkt_stream_default;
 }
 
@@ -931,8 +933,7 @@ static void *worker_testapp_validate_rx(void *arg)
 	if (test->current_step == 1)
 		thread_common_ops(test, ifobject);
 
-	if (stat_test_type != STAT_TEST_RX_FILL_EMPTY)
-		xsk_populate_fill_ring(ifobject->umem, ifobject->pkt_stream);
+	xsk_populate_fill_ring(ifobject->umem, ifobject->pkt_stream);
 
 	fds.fd = xsk_socket__fd(ifobject->xsk->xsk);
 	fds.events = POLLIN;
@@ -1065,7 +1066,14 @@ static void testapp_stats(struct test_spec *test)
 			break;
 		case STAT_TEST_RX_FILL_EMPTY:
 			test_spec_set_name(test, "STAT_RX_FILL_EMPTY");
+			test->ifobj_rx->pkt_stream = pkt_stream_generate(test->ifobj_rx->umem, 0,
+									 MIN_PKT_SIZE);
+			if (!test->ifobj_rx->pkt_stream)
+				exit_with_error(ENOMEM);
+			test->ifobj_rx->pkt_stream->use_addr_for_fill = true;
 			testapp_validate_traffic(test);
+
+			pkt_stream_restore_default(test);
 			break;
 		default:
 			break;
-- 
cgit v1.2.3


From 0d1b7f3a00cf530c2cad643812f08220b7729b9b Mon Sep 17 00:00:00 2001
From: Magnus Karlsson <magnus.karlsson@intel.com>
Date: Tue, 7 Sep 2021 09:19:27 +0200
Subject: selftests: xsk: Add tests for invalid xsk descriptors

Add tests for invalid xsk descriptors in the Tx ring. A number of
handcrafted nasty invalid descriptors are created and submitted to the
tx ring to check that they are validated correctly. Corner case valid
ones are also sent. The tests are run for both aligned and unaligned
mode.

pkt_stream_set() is introduced to be able to create a hand-crafted
packet stream where every single packet is specified in detail.

Signed-off-by: Magnus Karlsson <magnus.karlsson@intel.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Link: https://lore.kernel.org/bpf/20210907071928.9750-20-magnus.karlsson@gmail.com
---
 tools/testing/selftests/bpf/xdpxceiver.c | 143 +++++++++++++++++++++++++++----
 tools/testing/selftests/bpf/xdpxceiver.h |   7 +-
 2 files changed, 132 insertions(+), 18 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/xdpxceiver.c b/tools/testing/selftests/bpf/xdpxceiver.c
index 4d86c4b62aa9..1a03f7941bb8 100644
--- a/tools/testing/selftests/bpf/xdpxceiver.c
+++ b/tools/testing/selftests/bpf/xdpxceiver.c
@@ -46,6 +46,8 @@
  *       then remove xsk sockets from queue 0 on both veth interfaces and
  *       finally run a traffic on queues ids 1
  *    g. unaligned mode
+ *    h. tests for invalid and corner case Tx descriptors so that the correct ones
+ *       are discarded and let through, respectively.
  *
  * Total tests: 12
  *
@@ -394,7 +396,7 @@ static void __test_spec_init(struct test_spec *test, struct ifobject *ifobj_tx,
 		for (j = 0; j < MAX_SOCKETS; j++) {
 			memset(&ifobj->umem_arr[j], 0, sizeof(ifobj->umem_arr[j]));
 			memset(&ifobj->xsk_arr[j], 0, sizeof(ifobj->xsk_arr[j]));
-			ifobj->umem_arr[j].num_frames = DEFAULT_PKT_CNT / 4;
+			ifobj->umem_arr[j].num_frames = DEFAULT_UMEM_BUFFERS;
 			ifobj->umem_arr[j].frame_size = XSK_UMEM__DEFAULT_FRAME_SIZE;
 			ifobj->xsk_arr[j].rxqsize = XSK_RING_CONS__DEFAULT_NUM_DESCS;
 		}
@@ -450,6 +452,16 @@ static struct pkt *pkt_stream_get_pkt(struct pkt_stream *pkt_stream, u32 pkt_nb)
 	return &pkt_stream->pkts[pkt_nb];
 }
 
+static struct pkt *pkt_stream_get_next_rx_pkt(struct pkt_stream *pkt_stream)
+{
+	while (pkt_stream->rx_pkt_nb < pkt_stream->nb_pkts) {
+		if (pkt_stream->pkts[pkt_stream->rx_pkt_nb].valid)
+			return &pkt_stream->pkts[pkt_stream->rx_pkt_nb++];
+		pkt_stream->rx_pkt_nb++;
+	}
+	return NULL;
+}
+
 static void pkt_stream_delete(struct pkt_stream *pkt_stream)
 {
 	free(pkt_stream->pkts);
@@ -465,17 +477,31 @@ static void pkt_stream_restore_default(struct test_spec *test)
 	test->ifobj_rx->pkt_stream = test->pkt_stream_default;
 }
 
-static struct pkt_stream *pkt_stream_generate(struct xsk_umem_info *umem, u32 nb_pkts, u32 pkt_len)
+static struct pkt_stream *__pkt_stream_alloc(u32 nb_pkts)
 {
 	struct pkt_stream *pkt_stream;
-	u32 i;
 
 	pkt_stream = calloc(1, sizeof(*pkt_stream));
 	if (!pkt_stream)
-		exit_with_error(ENOMEM);
+		return NULL;
 
 	pkt_stream->pkts = calloc(nb_pkts, sizeof(*pkt_stream->pkts));
-	if (!pkt_stream->pkts)
+	if (!pkt_stream->pkts) {
+		free(pkt_stream);
+		return NULL;
+	}
+
+	pkt_stream->nb_pkts = nb_pkts;
+	return pkt_stream;
+}
+
+static struct pkt_stream *pkt_stream_generate(struct xsk_umem_info *umem, u32 nb_pkts, u32 pkt_len)
+{
+	struct pkt_stream *pkt_stream;
+	u32 i;
+
+	pkt_stream = __pkt_stream_alloc(nb_pkts);
+	if (!pkt_stream)
 		exit_with_error(ENOMEM);
 
 	pkt_stream->nb_pkts = nb_pkts;
@@ -535,6 +561,8 @@ static struct pkt *pkt_generate(struct ifobject *ifobject, u32 pkt_nb)
 
 	if (!pkt)
 		return NULL;
+	if (!pkt->valid || pkt->len < PKT_SIZE)
+		return pkt;
 
 	data = xsk_umem__get_data(ifobject->umem->buffer, pkt->addr);
 	udp_hdr = (struct udphdr *)(data + sizeof(struct ethhdr) + sizeof(struct iphdr));
@@ -549,6 +577,26 @@ static struct pkt *pkt_generate(struct ifobject *ifobject, u32 pkt_nb)
 	return pkt;
 }
 
+static void pkt_stream_generate_custom(struct test_spec *test, struct pkt *pkts, u32 nb_pkts)
+{
+	struct pkt_stream *pkt_stream;
+	u32 i;
+
+	pkt_stream = __pkt_stream_alloc(nb_pkts);
+	if (!pkt_stream)
+		exit_with_error(ENOMEM);
+
+	test->ifobj_tx->pkt_stream = pkt_stream;
+	test->ifobj_rx->pkt_stream = pkt_stream;
+
+	for (i = 0; i < nb_pkts; i++) {
+		pkt_stream->pkts[i].addr = pkts[i].addr;
+		pkt_stream->pkts[i].len = pkts[i].len;
+		pkt_stream->pkts[i].payload = i;
+		pkt_stream->pkts[i].valid = pkts[i].valid;
+	}
+}
+
 static void pkt_dump(void *pkt, u32 len)
 {
 	char s[INET_ADDRSTRLEN];
@@ -596,19 +644,24 @@ static bool is_pkt_valid(struct pkt *pkt, void *buffer, u64 addr, u32 len)
 		return false;
 	}
 
+	if (len < PKT_SIZE) {
+		/*Do not try to verify packets that are smaller than minimum size. */
+		return true;
+	}
+
+	if (pkt->len != len) {
+		ksft_test_result_fail
+			("ERROR: [%s] expected length [%d], got length [%d]\n",
+			 __func__, pkt->len, len);
+		return false;
+	}
+
 	if (iphdr->version == IP_PKT_VER && iphdr->tos == IP_PKT_TOS) {
 		u32 seqnum = ntohl(*((u32 *)(data + PKT_HDR_SIZE)));
 
 		if (opt_pkt_dump)
 			pkt_dump(data, PKT_SIZE);
 
-		if (pkt->len != len) {
-			ksft_test_result_fail
-				("ERROR: [%s] expected length [%d], got length [%d]\n",
-					__func__, pkt->len, len);
-			return false;
-		}
-
 		if (pkt->payload != seqnum) {
 			ksft_test_result_fail
 				("ERROR: [%s] expected seqnum [%d], got seqnum [%d]\n",
@@ -645,6 +698,15 @@ static void complete_pkts(struct xsk_socket_info *xsk, int batch_size)
 
 	rcvd = xsk_ring_cons__peek(&xsk->umem->cq, batch_size, &idx);
 	if (rcvd) {
+		if (rcvd > xsk->outstanding_tx) {
+			u64 addr = *xsk_ring_cons__comp_addr(&xsk->umem->cq, idx + rcvd - 1);
+
+			ksft_test_result_fail("ERROR: [%s] Too many packets completed\n",
+					      __func__);
+			ksft_print_msg("Last completion address: %llx\n", addr);
+			return;
+		}
+
 		xsk_ring_cons__release(&xsk->umem->cq, rcvd);
 		xsk->outstanding_tx -= rcvd;
 	}
@@ -653,11 +715,10 @@ static void complete_pkts(struct xsk_socket_info *xsk, int batch_size)
 static void receive_pkts(struct pkt_stream *pkt_stream, struct xsk_socket_info *xsk,
 			 struct pollfd *fds)
 {
-	u32 idx_rx = 0, idx_fq = 0, rcvd, i, pkt_count = 0;
-	struct pkt *pkt;
+	struct pkt *pkt = pkt_stream_get_next_rx_pkt(pkt_stream);
+	u32 idx_rx = 0, idx_fq = 0, rcvd, i;
 	int ret;
 
-	pkt = pkt_stream_get_pkt(pkt_stream, pkt_count++);
 	while (pkt) {
 		rcvd = xsk_ring_cons__peek(&xsk->rx, BATCH_SIZE, &idx_rx);
 		if (!rcvd) {
@@ -685,13 +746,21 @@ static void receive_pkts(struct pkt_stream *pkt_stream, struct xsk_socket_info *
 			const struct xdp_desc *desc = xsk_ring_cons__rx_desc(&xsk->rx, idx_rx++);
 			u64 addr = desc->addr, orig;
 
+			if (!pkt) {
+				ksft_test_result_fail("ERROR: [%s] Received too many packets.\n",
+						      __func__);
+				ksft_print_msg("Last packet has addr: %llx len: %u\n",
+					       addr, desc->len);
+				return;
+			}
+
 			orig = xsk_umem__extract_addr(addr);
 			addr = xsk_umem__add_offset_to_addr(addr);
 			if (!is_pkt_valid(pkt, xsk->umem->buffer, addr, desc->len))
 				return;
 
 			*xsk_ring_prod__fill_addr(&xsk->umem->fq, idx_fq++) = orig;
-			pkt = pkt_stream_get_pkt(pkt_stream, pkt_count++);
+			pkt = pkt_stream_get_next_rx_pkt(pkt_stream);
 		}
 
 		xsk_ring_prod__submit(&xsk->umem->fq, rcvd);
@@ -875,6 +944,7 @@ static void testapp_cleanup_xsk_res(struct ifobject *ifobj)
 {
 	print_verbose("Destroying socket\n");
 	xsk_socket__delete(ifobj->xsk->xsk);
+	munmap(ifobj->umem->buffer, ifobj->umem->num_frames * ifobj->umem->frame_size);
 	xsk_umem__delete(ifobj->umem->umem);
 }
 
@@ -1118,6 +1188,35 @@ static bool testapp_unaligned(struct test_spec *test)
 	return true;
 }
 
+static void testapp_invalid_desc(struct test_spec *test)
+{
+	struct pkt pkts[] = {
+		/* Zero packet length at address zero allowed */
+		{0, 0, 0, true},
+		/* Zero packet length allowed */
+		{0x1000, 0, 0, true},
+		/* Straddling the start of umem */
+		{-2, PKT_SIZE, 0, false},
+		/* Packet too large */
+		{0x2000, XSK_UMEM__INVALID_FRAME_SIZE, 0, false},
+		/* After umem ends */
+		{UMEM_SIZE, PKT_SIZE, 0, false},
+		/* Straddle the end of umem */
+		{UMEM_SIZE - PKT_SIZE / 2, PKT_SIZE, 0, false},
+		/* Straddle a page boundrary */
+		{0x3000 - PKT_SIZE / 2, PKT_SIZE, 0, false},
+		/* Valid packet for synch so that something is received */
+		{0x4000, PKT_SIZE, 0, true}};
+
+	if (test->ifobj_tx->umem->unaligned_mode) {
+		/* Crossing a page boundrary allowed */
+		pkts[6].valid = true;
+	}
+	pkt_stream_generate_custom(test, pkts, ARRAY_SIZE(pkts));
+	testapp_validate_traffic(test);
+	pkt_stream_restore_default(test);
+}
+
 static void init_iface(struct ifobject *ifobj, const char *dst_mac, const char *src_mac,
 		       const char *dst_ip, const char *src_ip, const u16 dst_port,
 		       const u16 src_port, thread_func_t func_ptr)
@@ -1159,7 +1258,7 @@ static void run_pkt_test(struct test_spec *test, enum test_mode mode, enum test_
 	case TEST_TYPE_BPF_RES:
 		testapp_bpf_res(test);
 		break;
-	case TEST_TYPE_NOPOLL:
+	case TEST_TYPE_RUN_TO_COMPLETION:
 		test_spec_set_name(test, "RUN_TO_COMPLETION");
 		testapp_validate_traffic(test);
 		break;
@@ -1169,6 +1268,16 @@ static void run_pkt_test(struct test_spec *test, enum test_mode mode, enum test_
 		test_spec_set_name(test, "POLL");
 		testapp_validate_traffic(test);
 		break;
+	case TEST_TYPE_ALIGNED_INV_DESC:
+		test_spec_set_name(test, "ALIGNED_INV_DESC");
+		testapp_invalid_desc(test);
+		break;
+	case TEST_TYPE_UNALIGNED_INV_DESC:
+		test_spec_set_name(test, "UNALIGNED_INV_DESC");
+		test->ifobj_tx->umem->unaligned_mode = true;
+		test->ifobj_rx->umem->unaligned_mode = true;
+		testapp_invalid_desc(test);
+		break;
 	case TEST_TYPE_UNALIGNED:
 		if (!testapp_unaligned(test))
 			return;
diff --git a/tools/testing/selftests/bpf/xdpxceiver.h b/tools/testing/selftests/bpf/xdpxceiver.h
index 129801eb013c..2d9efb89ea28 100644
--- a/tools/testing/selftests/bpf/xdpxceiver.h
+++ b/tools/testing/selftests/bpf/xdpxceiver.h
@@ -38,6 +38,8 @@
 #define BATCH_SIZE 8
 #define POLL_TMOUT 1000
 #define DEFAULT_PKT_CNT (4 * 1024)
+#define DEFAULT_UMEM_BUFFERS (DEFAULT_PKT_CNT / 4)
+#define UMEM_SIZE (DEFAULT_UMEM_BUFFERS * XSK_UMEM__DEFAULT_FRAME_SIZE)
 #define RX_FULL_RXQSIZE 32
 #define DEFAULT_OFFSET 256
 #define XSK_UMEM__INVALID_FRAME_SIZE (XSK_UMEM__DEFAULT_FRAME_SIZE + 1)
@@ -51,9 +53,11 @@ enum test_mode {
 };
 
 enum test_type {
-	TEST_TYPE_NOPOLL,
+	TEST_TYPE_RUN_TO_COMPLETION,
 	TEST_TYPE_POLL,
 	TEST_TYPE_UNALIGNED,
+	TEST_TYPE_ALIGNED_INV_DESC,
+	TEST_TYPE_UNALIGNED_INV_DESC,
 	TEST_TYPE_TEARDOWN,
 	TEST_TYPE_BIDI,
 	TEST_TYPE_STATS,
@@ -104,6 +108,7 @@ struct pkt {
 
 struct pkt_stream {
 	u32 nb_pkts;
+	u32 rx_pkt_nb;
 	struct pkt *pkts;
 	bool use_addr_for_fill;
 };
-- 
cgit v1.2.3


From 909f0e28207ced098612653ebaafcbb2e13be834 Mon Sep 17 00:00:00 2001
From: Magnus Karlsson <magnus.karlsson@intel.com>
Date: Tue, 7 Sep 2021 09:19:28 +0200
Subject: selftests: xsk: Add tests for 2K frame size

Add tests for 2K frame size. Both a standard send and receive test and
one testing for invalid descriptors when the frame size is 2K.

Signed-off-by: Magnus Karlsson <magnus.karlsson@intel.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Link: https://lore.kernel.org/bpf/20210907071928.9750-21-magnus.karlsson@gmail.com
---
 tools/testing/selftests/bpf/xdpxceiver.c | 23 +++++++++++++++++++++++
 tools/testing/selftests/bpf/xdpxceiver.h |  2 ++
 2 files changed, 25 insertions(+)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/xdpxceiver.c b/tools/testing/selftests/bpf/xdpxceiver.c
index 1a03f7941bb8..127bcde06c86 100644
--- a/tools/testing/selftests/bpf/xdpxceiver.c
+++ b/tools/testing/selftests/bpf/xdpxceiver.c
@@ -48,6 +48,7 @@
  *    g. unaligned mode
  *    h. tests for invalid and corner case Tx descriptors so that the correct ones
  *       are discarded and let through, respectively.
+ *    i. 2K frame size tests
  *
  * Total tests: 12
  *
@@ -1205,6 +1206,8 @@ static void testapp_invalid_desc(struct test_spec *test)
 		{UMEM_SIZE - PKT_SIZE / 2, PKT_SIZE, 0, false},
 		/* Straddle a page boundrary */
 		{0x3000 - PKT_SIZE / 2, PKT_SIZE, 0, false},
+		/* Straddle a 2K boundrary */
+		{0x3800 - PKT_SIZE / 2, PKT_SIZE, 0, true},
 		/* Valid packet for synch so that something is received */
 		{0x4000, PKT_SIZE, 0, true}};
 
@@ -1212,6 +1215,11 @@ static void testapp_invalid_desc(struct test_spec *test)
 		/* Crossing a page boundrary allowed */
 		pkts[6].valid = true;
 	}
+	if (test->ifobj_tx->umem->frame_size == XSK_UMEM__DEFAULT_FRAME_SIZE / 2) {
+		/* Crossing a 2K frame size boundrary not allowed */
+		pkts[7].valid = false;
+	}
+
 	pkt_stream_generate_custom(test, pkts, ARRAY_SIZE(pkts));
 	testapp_validate_traffic(test);
 	pkt_stream_restore_default(test);
@@ -1262,6 +1270,15 @@ static void run_pkt_test(struct test_spec *test, enum test_mode mode, enum test_
 		test_spec_set_name(test, "RUN_TO_COMPLETION");
 		testapp_validate_traffic(test);
 		break;
+	case TEST_TYPE_RUN_TO_COMPLETION_2K_FRAME:
+		test_spec_set_name(test, "RUN_TO_COMPLETION_2K_FRAME_SIZE");
+		test->ifobj_tx->umem->frame_size = 2048;
+		test->ifobj_rx->umem->frame_size = 2048;
+		pkt_stream_replace(test, DEFAULT_PKT_CNT, MIN_PKT_SIZE);
+		testapp_validate_traffic(test);
+
+		pkt_stream_restore_default(test);
+		break;
 	case TEST_TYPE_POLL:
 		test->ifobj_tx->use_poll = true;
 		test->ifobj_rx->use_poll = true;
@@ -1272,6 +1289,12 @@ static void run_pkt_test(struct test_spec *test, enum test_mode mode, enum test_
 		test_spec_set_name(test, "ALIGNED_INV_DESC");
 		testapp_invalid_desc(test);
 		break;
+	case TEST_TYPE_ALIGNED_INV_DESC_2K_FRAME:
+		test_spec_set_name(test, "ALIGNED_INV_DESC_2K_FRAME_SIZE");
+		test->ifobj_tx->umem->frame_size = 2048;
+		test->ifobj_rx->umem->frame_size = 2048;
+		testapp_invalid_desc(test);
+		break;
 	case TEST_TYPE_UNALIGNED_INV_DESC:
 		test_spec_set_name(test, "UNALIGNED_INV_DESC");
 		test->ifobj_tx->umem->unaligned_mode = true;
diff --git a/tools/testing/selftests/bpf/xdpxceiver.h b/tools/testing/selftests/bpf/xdpxceiver.h
index 2d9efb89ea28..5ac4a5e64744 100644
--- a/tools/testing/selftests/bpf/xdpxceiver.h
+++ b/tools/testing/selftests/bpf/xdpxceiver.h
@@ -54,9 +54,11 @@ enum test_mode {
 
 enum test_type {
 	TEST_TYPE_RUN_TO_COMPLETION,
+	TEST_TYPE_RUN_TO_COMPLETION_2K_FRAME,
 	TEST_TYPE_POLL,
 	TEST_TYPE_UNALIGNED,
 	TEST_TYPE_ALIGNED_INV_DESC,
+	TEST_TYPE_ALIGNED_INV_DESC_2K_FRAME,
 	TEST_TYPE_UNALIGNED_INV_DESC,
 	TEST_TYPE_TEARDOWN,
 	TEST_TYPE_BIDI,
-- 
cgit v1.2.3


From f64c4acea51fbe2c08c0b0f48b7f5d1657d7a5e4 Mon Sep 17 00:00:00 2001
From: Vadim Fedorenko <vfedorenko@novek.ru>
Date: Fri, 10 Sep 2021 01:04:08 +0300
Subject: bpf: Add hardware timestamp field to __sk_buff

BPF programs may want to know hardware timestamps if NIC supports
such timestamping.

Expose this data as hwtstamp field of __sk_buff the same way as
gso_segs/gso_size. This field could be accessed from the same
programs as tstamp field, but it's read-only field. Explicit test
to deny access to padding data is added to bpf_skb_is_valid_access.

Also update BPF_PROG_TEST_RUN tests of the feature.

Signed-off-by: Vadim Fedorenko <vfedorenko@novek.ru>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Link: https://lore.kernel.org/bpf/20210909220409.8804-2-vfedorenko@novek.ru
---
 tools/include/uapi/linux/bpf.h | 2 ++
 1 file changed, 2 insertions(+)

(limited to 'tools')

diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 791f31dd0abe..51cfd91cc387 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -5284,6 +5284,8 @@ struct __sk_buff {
 	__u32 gso_segs;
 	__bpf_md_ptr(struct bpf_sock *, sk);
 	__u32 gso_size;
+	__u32 :32;		/* Padding, future use. */
+	__u64 hwtstamp;
 };
 
 struct bpf_tunnel_key {
-- 
cgit v1.2.3


From 3384c7c7641b44987e35eadbc9df6c16a0520159 Mon Sep 17 00:00:00 2001
From: Vadim Fedorenko <vfedorenko@novek.ru>
Date: Fri, 10 Sep 2021 01:04:09 +0300
Subject: selftests/bpf: Test new __sk_buff field hwtstamp

Analogous to the gso_segs selftests introduced in commit d9ff286a0f59
("bpf: allow BPF programs access skb_shared_info->gso_segs field").

Signed-off-by: Vadim Fedorenko <vfedorenko@novek.ru>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Link: https://lore.kernel.org/bpf/20210909220409.8804-3-vfedorenko@novek.ru
---
 tools/testing/selftests/bpf/prog_tests/skb_ctx.c |  1 +
 tools/testing/selftests/bpf/progs/test_skb_ctx.c |  2 +
 tools/testing/selftests/bpf/verifier/ctx_skb.c   | 60 ++++++++++++++++++++++++
 3 files changed, 63 insertions(+)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/prog_tests/skb_ctx.c b/tools/testing/selftests/bpf/prog_tests/skb_ctx.c
index 2bf8c687348b..c437e6ba8fe2 100644
--- a/tools/testing/selftests/bpf/prog_tests/skb_ctx.c
+++ b/tools/testing/selftests/bpf/prog_tests/skb_ctx.c
@@ -18,6 +18,7 @@ void test_skb_ctx(void)
 		.gso_segs = 8,
 		.mark = 9,
 		.gso_size = 10,
+		.hwtstamp = 11,
 	};
 	struct bpf_prog_test_run_attr tattr = {
 		.data_in = &pkt_v4,
diff --git a/tools/testing/selftests/bpf/progs/test_skb_ctx.c b/tools/testing/selftests/bpf/progs/test_skb_ctx.c
index bbd5a9c1c4df..ba4dab09d19c 100644
--- a/tools/testing/selftests/bpf/progs/test_skb_ctx.c
+++ b/tools/testing/selftests/bpf/progs/test_skb_ctx.c
@@ -29,6 +29,8 @@ int process(struct __sk_buff *skb)
 		return 1;
 	if (skb->ifindex != 1)
 		return 1;
+	if (skb->hwtstamp != 11)
+		return 1;
 
 	return 0;
 }
diff --git a/tools/testing/selftests/bpf/verifier/ctx_skb.c b/tools/testing/selftests/bpf/verifier/ctx_skb.c
index 2022c0f2cd75..9e1a30b94197 100644
--- a/tools/testing/selftests/bpf/verifier/ctx_skb.c
+++ b/tools/testing/selftests/bpf/verifier/ctx_skb.c
@@ -1057,6 +1057,66 @@
 	.result = ACCEPT,
 	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
 },
+{
+	"padding after gso_size is not accessible",
+	.insns = {
+	BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
+		    offsetofend(struct __sk_buff, gso_size)),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	},
+	.result = REJECT,
+	.result_unpriv = REJECT,
+	.errstr = "invalid bpf_context access off=180 size=4",
+	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+},
+{
+	"read hwtstamp from CGROUP_SKB",
+	.insns = {
+	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1,
+		    offsetof(struct __sk_buff, hwtstamp)),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	},
+	.result = ACCEPT,
+	.prog_type = BPF_PROG_TYPE_CGROUP_SKB,
+},
+{
+	"read hwtstamp from CGROUP_SKB",
+	.insns = {
+	BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_1,
+		    offsetof(struct __sk_buff, hwtstamp)),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	},
+	.result = ACCEPT,
+	.prog_type = BPF_PROG_TYPE_CGROUP_SKB,
+},
+{
+	"write hwtstamp from CGROUP_SKB",
+	.insns = {
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_0,
+		    offsetof(struct __sk_buff, hwtstamp)),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	},
+	.result = REJECT,
+	.result_unpriv = REJECT,
+	.errstr = "invalid bpf_context access off=184 size=8",
+	.prog_type = BPF_PROG_TYPE_CGROUP_SKB,
+},
+{
+	"read hwtstamp from CLS",
+	.insns = {
+	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1,
+		    offsetof(struct __sk_buff, hwtstamp)),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	},
+	.result = ACCEPT,
+	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+},
 {
 	"check wire_len is not readable by sockets",
 	.insns = {
-- 
cgit v1.2.3


From 856c02dbce4f8d6a5644083db22c11750aa11481 Mon Sep 17 00:00:00 2001
From: Song Liu <songliubraving@fb.com>
Date: Fri, 10 Sep 2021 11:33:51 -0700
Subject: bpf: Introduce helper bpf_get_branch_snapshot

Introduce bpf_get_branch_snapshot(), which allows tracing pogram to get
branch trace from hardware (e.g. Intel LBR). To use the feature, the
user need to create perf_event with proper branch_record filtering
on each cpu, and then calls bpf_get_branch_snapshot in the bpf function.
On Intel CPUs, VLBR event (raw event 0x1b00) can be use for this.

Signed-off-by: Song Liu <songliubraving@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: John Fastabend <john.fastabend@gmail.com>
Acked-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20210910183352.3151445-3-songliubraving@fb.com
---
 tools/include/uapi/linux/bpf.h | 22 ++++++++++++++++++++++
 1 file changed, 22 insertions(+)

(limited to 'tools')

diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 51cfd91cc387..d21326558d42 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -4877,6 +4877,27 @@ union bpf_attr {
  *		Get the struct pt_regs associated with **task**.
  *	Return
  *		A pointer to struct pt_regs.
+ *
+ * long bpf_get_branch_snapshot(void *entries, u32 size, u64 flags)
+ *	Description
+ *		Get branch trace from hardware engines like Intel LBR. The
+ *		hardware engine is stopped shortly after the helper is
+ *		called. Therefore, the user need to filter branch entries
+ *		based on the actual use case. To capture branch trace
+ *		before the trigger point of the BPF program, the helper
+ *		should be called at the beginning of the BPF program.
+ *
+ *		The data is stored as struct perf_branch_entry into output
+ *		buffer *entries*. *size* is the size of *entries* in bytes.
+ *		*flags* is reserved for now and must be zero.
+ *
+ *	Return
+ *		On success, number of bytes written to *buf*. On error, a
+ *		negative value.
+ *
+ *		**-EINVAL** if *flags* is not zero.
+ *
+ *		**-ENOENT** if architecture does not support branch records.
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -5055,6 +5076,7 @@ union bpf_attr {
 	FN(get_func_ip),		\
 	FN(get_attach_cookie),		\
 	FN(task_pt_regs),		\
+	FN(get_branch_snapshot),	\
 	/* */
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
-- 
cgit v1.2.3


From 025bd7c753aab18cd594924a46ab46ac47209df9 Mon Sep 17 00:00:00 2001
From: Song Liu <songliubraving@fb.com>
Date: Fri, 10 Sep 2021 11:33:52 -0700
Subject: selftests/bpf: Add test for bpf_get_branch_snapshot

This test uses bpf_get_branch_snapshot from a fexit program. The test uses
a target function (bpf_testmod_loop_test) and compares the record against
kallsyms. If there isn't enough record matching kallsyms, the test fails.

Signed-off-by: Song Liu <songliubraving@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Andrii Nakryiko <andrii@kernel.org>
Acked-by: John Fastabend <john.fastabend@gmail.com>
Link: https://lore.kernel.org/bpf/20210910183352.3151445-4-songliubraving@fb.com
---
 .../selftests/bpf/bpf_testmod/bpf_testmod.c        |  19 +++-
 .../testing/selftests/bpf/prog_tests/core_reloc.c  |  14 +--
 .../selftests/bpf/prog_tests/get_branch_snapshot.c | 100 +++++++++++++++++++++
 .../selftests/bpf/prog_tests/module_attach.c       |  39 --------
 .../selftests/bpf/progs/get_branch_snapshot.c      |  40 +++++++++
 tools/testing/selftests/bpf/test_progs.c           |  39 ++++++++
 tools/testing/selftests/bpf/test_progs.h           |   2 +
 tools/testing/selftests/bpf/trace_helpers.c        |  37 ++++++++
 tools/testing/selftests/bpf/trace_helpers.h        |   5 ++
 9 files changed, 243 insertions(+), 52 deletions(-)
 create mode 100644 tools/testing/selftests/bpf/prog_tests/get_branch_snapshot.c
 create mode 100644 tools/testing/selftests/bpf/progs/get_branch_snapshot.c

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c b/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c
index 141d8da687d2..50fc5561110a 100644
--- a/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c
+++ b/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c
@@ -13,6 +13,18 @@
 
 DEFINE_PER_CPU(int, bpf_testmod_ksym_percpu) = 123;
 
+noinline int bpf_testmod_loop_test(int n)
+{
+	int i, sum = 0;
+
+	/* the primary goal of this test is to test LBR. Create a lot of
+	 * branches in the function, so we can catch it easily.
+	 */
+	for (i = 0; i < n; i++)
+		sum += i;
+	return sum;
+}
+
 noinline ssize_t
 bpf_testmod_test_read(struct file *file, struct kobject *kobj,
 		      struct bin_attribute *bin_attr,
@@ -24,7 +36,11 @@ bpf_testmod_test_read(struct file *file, struct kobject *kobj,
 		.len = len,
 	};
 
-	trace_bpf_testmod_test_read(current, &ctx);
+	/* This is always true. Use the check to make sure the compiler
+	 * doesn't remove bpf_testmod_loop_test.
+	 */
+	if (bpf_testmod_loop_test(101) > 100)
+		trace_bpf_testmod_test_read(current, &ctx);
 
 	return -EIO; /* always fail */
 }
@@ -71,4 +87,3 @@ 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/prog_tests/core_reloc.c b/tools/testing/selftests/bpf/prog_tests/core_reloc.c
index 4739b15b2a97..15d355af8d1d 100644
--- a/tools/testing/selftests/bpf/prog_tests/core_reloc.c
+++ b/tools/testing/selftests/bpf/prog_tests/core_reloc.c
@@ -30,7 +30,7 @@ static int duration = 0;
 	.output_len = sizeof(struct core_reloc_module_output),		\
 	.prog_sec_name = sec_name,					\
 	.raw_tp_name = tp_name,						\
-	.trigger = trigger_module_test_read,				\
+	.trigger = __trigger_module_test_read,				\
 	.needs_testmod = true,						\
 }
 
@@ -475,19 +475,11 @@ 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)
+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);
 
+	trigger_module_test_read(exp->len);
 	return 0;
 }
 
diff --git a/tools/testing/selftests/bpf/prog_tests/get_branch_snapshot.c b/tools/testing/selftests/bpf/prog_tests/get_branch_snapshot.c
new file mode 100644
index 000000000000..f81db9135ae4
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/get_branch_snapshot.c
@@ -0,0 +1,100 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2021 Facebook */
+#include <test_progs.h>
+#include "get_branch_snapshot.skel.h"
+
+static int *pfd_array;
+static int cpu_cnt;
+
+static int create_perf_events(void)
+{
+	struct perf_event_attr attr = {0};
+	int cpu;
+
+	/* create perf event */
+	attr.size = sizeof(attr);
+	attr.type = PERF_TYPE_RAW;
+	attr.config = 0x1b00;
+	attr.sample_type = PERF_SAMPLE_BRANCH_STACK;
+	attr.branch_sample_type = PERF_SAMPLE_BRANCH_KERNEL |
+		PERF_SAMPLE_BRANCH_USER | PERF_SAMPLE_BRANCH_ANY;
+
+	cpu_cnt = libbpf_num_possible_cpus();
+	pfd_array = malloc(sizeof(int) * cpu_cnt);
+	if (!pfd_array) {
+		cpu_cnt = 0;
+		return 1;
+	}
+
+	for (cpu = 0; cpu < cpu_cnt; cpu++) {
+		pfd_array[cpu] = syscall(__NR_perf_event_open, &attr,
+					 -1, cpu, -1, PERF_FLAG_FD_CLOEXEC);
+		if (pfd_array[cpu] < 0)
+			break;
+	}
+
+	return cpu == 0;
+}
+
+static void close_perf_events(void)
+{
+	int cpu = 0;
+	int fd;
+
+	while (cpu++ < cpu_cnt) {
+		fd = pfd_array[cpu];
+		if (fd < 0)
+			break;
+		close(fd);
+	}
+	free(pfd_array);
+}
+
+void test_get_branch_snapshot(void)
+{
+	struct get_branch_snapshot *skel = NULL;
+	int err;
+
+	if (create_perf_events()) {
+		test__skip();  /* system doesn't support LBR */
+		goto cleanup;
+	}
+
+	skel = get_branch_snapshot__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "get_branch_snapshot__open_and_load"))
+		goto cleanup;
+
+	err = kallsyms_find("bpf_testmod_loop_test", &skel->bss->address_low);
+	if (!ASSERT_OK(err, "kallsyms_find"))
+		goto cleanup;
+
+	err = kallsyms_find_next("bpf_testmod_loop_test", &skel->bss->address_high);
+	if (!ASSERT_OK(err, "kallsyms_find_next"))
+		goto cleanup;
+
+	err = get_branch_snapshot__attach(skel);
+	if (!ASSERT_OK(err, "get_branch_snapshot__attach"))
+		goto cleanup;
+
+	trigger_module_test_read(100);
+
+	if (skel->bss->total_entries < 16) {
+		/* too few entries for the hit/waste test */
+		test__skip();
+		goto cleanup;
+	}
+
+	ASSERT_GT(skel->bss->test1_hits, 6, "find_looptest_in_lbr");
+
+	/* Given we stop LBR in software, we will waste a few entries.
+	 * But we should try to waste as few as possible entries. We are at
+	 * about 7 on x86_64 systems.
+	 * Add a check for < 10 so that we get heads-up when something
+	 * changes and wastes too many entries.
+	 */
+	ASSERT_LT(skel->bss->wasted_entries, 10, "check_wasted_entries");
+
+cleanup:
+	get_branch_snapshot__destroy(skel);
+	close_perf_events();
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/module_attach.c b/tools/testing/selftests/bpf/prog_tests/module_attach.c
index d85a69b7ce44..1797a6e4d6d8 100644
--- a/tools/testing/selftests/bpf/prog_tests/module_attach.c
+++ b/tools/testing/selftests/bpf/prog_tests/module_attach.c
@@ -6,45 +6,6 @@
 
 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;
-}
-
-static int trigger_module_test_write(int write_sz)
-{
-	int fd, err;
-	char *buf = malloc(write_sz);
-
-	if (!buf)
-		return -ENOMEM;
-
-	memset(buf, 'a', write_sz);
-	buf[write_sz-1] = '\0';
-
-	fd = open("/sys/kernel/bpf_testmod", O_WRONLY);
-	err = -errno;
-	if (CHECK(fd < 0, "testmod_file_open", "failed: %d\n", err)) {
-		free(buf);
-		return err;
-	}
-
-	write(fd, buf, write_sz);
-	close(fd);
-	free(buf);
-	return 0;
-}
-
 static int delete_module(const char *name, int flags)
 {
 	return syscall(__NR_delete_module, name, flags);
diff --git a/tools/testing/selftests/bpf/progs/get_branch_snapshot.c b/tools/testing/selftests/bpf/progs/get_branch_snapshot.c
new file mode 100644
index 000000000000..a1b139888048
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/get_branch_snapshot.c
@@ -0,0 +1,40 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2021 Facebook */
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+
+char _license[] SEC("license") = "GPL";
+
+__u64 test1_hits = 0;
+__u64 address_low = 0;
+__u64 address_high = 0;
+int wasted_entries = 0;
+long total_entries = 0;
+
+#define ENTRY_CNT 32
+struct perf_branch_entry entries[ENTRY_CNT] = {};
+
+static inline bool in_range(__u64 val)
+{
+	return (val >= address_low) && (val < address_high);
+}
+
+SEC("fexit/bpf_testmod_loop_test")
+int BPF_PROG(test1, int n, int ret)
+{
+	long i;
+
+	total_entries = bpf_get_branch_snapshot(entries, sizeof(entries), 0);
+	total_entries /= sizeof(struct perf_branch_entry);
+
+	for (i = 0; i < ENTRY_CNT; i++) {
+		if (i >= total_entries)
+			break;
+		if (in_range(entries[i].from) && in_range(entries[i].to))
+			test1_hits++;
+		else if (!test1_hits)
+			wasted_entries++;
+	}
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/test_progs.c b/tools/testing/selftests/bpf/test_progs.c
index cc1cd240445d..2ed01f615d20 100644
--- a/tools/testing/selftests/bpf/test_progs.c
+++ b/tools/testing/selftests/bpf/test_progs.c
@@ -743,6 +743,45 @@ int cd_flavor_subdir(const char *exec_name)
 	return chdir(flavor);
 }
 
+int trigger_module_test_read(int read_sz)
+{
+	int fd, err;
+
+	fd = open("/sys/kernel/bpf_testmod", O_RDONLY);
+	err = -errno;
+	if (!ASSERT_GE(fd, 0, "testmod_file_open"))
+		return err;
+
+	read(fd, NULL, read_sz);
+	close(fd);
+
+	return 0;
+}
+
+int trigger_module_test_write(int write_sz)
+{
+	int fd, err;
+	char *buf = malloc(write_sz);
+
+	if (!buf)
+		return -ENOMEM;
+
+	memset(buf, 'a', write_sz);
+	buf[write_sz-1] = '\0';
+
+	fd = open("/sys/kernel/bpf_testmod", O_WRONLY);
+	err = -errno;
+	if (!ASSERT_GE(fd, 0, "testmod_file_open")) {
+		free(buf);
+		return err;
+	}
+
+	write(fd, buf, write_sz);
+	close(fd);
+	free(buf);
+	return 0;
+}
+
 #define MAX_BACKTRACE_SZ 128
 void crash_handler(int signum)
 {
diff --git a/tools/testing/selftests/bpf/test_progs.h b/tools/testing/selftests/bpf/test_progs.h
index c8c2bf878f67..94bef0aa74cf 100644
--- a/tools/testing/selftests/bpf/test_progs.h
+++ b/tools/testing/selftests/bpf/test_progs.h
@@ -291,6 +291,8 @@ int compare_map_keys(int map1_fd, int map2_fd);
 int compare_stack_ips(int smap_fd, int amap_fd, int stack_trace_len);
 int extract_build_id(char *build_id, size_t size);
 int kern_sync_rcu(void);
+int trigger_module_test_read(int read_sz);
+int trigger_module_test_write(int write_sz);
 
 #ifdef __x86_64__
 #define SYS_NANOSLEEP_KPROBE_NAME "__x64_sys_nanosleep"
diff --git a/tools/testing/selftests/bpf/trace_helpers.c b/tools/testing/selftests/bpf/trace_helpers.c
index e7a19b04d4ea..5100a169b72b 100644
--- a/tools/testing/selftests/bpf/trace_helpers.c
+++ b/tools/testing/selftests/bpf/trace_helpers.c
@@ -1,4 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0
+#include <ctype.h>
 #include <stdio.h>
 #include <stdlib.h>
 #include <string.h>
@@ -117,6 +118,42 @@ out:
 	return err;
 }
 
+/* find the address of the next symbol of the same type, this can be used
+ * to determine the end of a function.
+ */
+int kallsyms_find_next(const char *sym, unsigned long long *addr)
+{
+	char type, found_type, name[500];
+	unsigned long long value;
+	bool found = false;
+	int err = 0;
+	FILE *f;
+
+	f = fopen("/proc/kallsyms", "r");
+	if (!f)
+		return -EINVAL;
+
+	while (fscanf(f, "%llx %c %499s%*[^\n]\n", &value, &type, name) > 0) {
+		/* Different types of symbols in kernel modules are mixed
+		 * in /proc/kallsyms. Only return the next matching type.
+		 * Use tolower() for type so that 'T' matches 't'.
+		 */
+		if (found && found_type == tolower(type)) {
+			*addr = value;
+			goto out;
+		}
+		if (strcmp(name, sym) == 0) {
+			found = true;
+			found_type = tolower(type);
+		}
+	}
+	err = -ENOENT;
+
+out:
+	fclose(f);
+	return err;
+}
+
 void read_trace_pipe(void)
 {
 	int trace_fd;
diff --git a/tools/testing/selftests/bpf/trace_helpers.h b/tools/testing/selftests/bpf/trace_helpers.h
index d907b445524d..bc8ed86105d9 100644
--- a/tools/testing/selftests/bpf/trace_helpers.h
+++ b/tools/testing/selftests/bpf/trace_helpers.h
@@ -16,6 +16,11 @@ long ksym_get_addr(const char *name);
 /* open kallsyms and find addresses on the fly, faster than load + search. */
 int kallsyms_find(const char *sym, unsigned long long *addr);
 
+/* find the address of the next symbol, this can be used to determine the
+ * end of a function
+ */
+int kallsyms_find_next(const char *sym, unsigned long long *addr);
+
 void read_trace_pipe(void);
 
 ssize_t get_uprobe_offset(const void *addr, ssize_t base);
-- 
cgit v1.2.3


From dbd7eb14e0607afa1dd3aee7175f37022ecc5f03 Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Fri, 10 Sep 2021 11:19:00 +0200
Subject: bpf, selftests: Replicate tailcall limit test for indirect call case

The tailcall_3 test program uses bpf_tail_call_static() where the JIT
would patch a direct jump. Add a new tailcall_6 test program replicating
exactly the same test just ensuring that bpf_tail_call() uses a map
index where the verifier cannot make assumptions this time.

In other words, this will now cover both on x86-64 JIT, meaning, JIT
images with emit_bpf_tail_call_direct() emission as well as JIT images
with emit_bpf_tail_call_indirect() emission.

  # echo 1 > /proc/sys/net/core/bpf_jit_enable
  # ./test_progs -t tailcalls
  #136/1 tailcalls/tailcall_1:OK
  #136/2 tailcalls/tailcall_2:OK
  #136/3 tailcalls/tailcall_3:OK
  #136/4 tailcalls/tailcall_4:OK
  #136/5 tailcalls/tailcall_5:OK
  #136/6 tailcalls/tailcall_6:OK
  #136/7 tailcalls/tailcall_bpf2bpf_1:OK
  #136/8 tailcalls/tailcall_bpf2bpf_2:OK
  #136/9 tailcalls/tailcall_bpf2bpf_3:OK
  #136/10 tailcalls/tailcall_bpf2bpf_4:OK
  #136/11 tailcalls/tailcall_bpf2bpf_5:OK
  #136 tailcalls:OK
  Summary: 1/11 PASSED, 0 SKIPPED, 0 FAILED

  # echo 0 > /proc/sys/net/core/bpf_jit_enable
  # ./test_progs -t tailcalls
  #136/1 tailcalls/tailcall_1:OK
  #136/2 tailcalls/tailcall_2:OK
  #136/3 tailcalls/tailcall_3:OK
  #136/4 tailcalls/tailcall_4:OK
  #136/5 tailcalls/tailcall_5:OK
  #136/6 tailcalls/tailcall_6:OK
  [...]

For interpreter, the tailcall_1-6 tests are passing as well. The later
tailcall_bpf2bpf_* are failing due lack of bpf2bpf + tailcall support
in interpreter, so this is expected.

Also, manual inspection shows that both loaded programs from tailcall_3
and tailcall_6 test case emit the expected opcodes:

* tailcall_3 disasm, emit_bpf_tail_call_direct():

  [...]
   b:   push   %rax
   c:   push   %rbx
   d:   push   %r13
   f:   mov    %rdi,%rbx
  12:   movabs $0xffff8d3f5afb0200,%r13
  1c:   mov    %rbx,%rdi
  1f:   mov    %r13,%rsi
  22:   xor    %edx,%edx                 _
  24:   mov    -0x4(%rbp),%eax          |  limit check
  2a:   cmp    $0x20,%eax               |
  2d:   ja     0x0000000000000046       |
  2f:   add    $0x1,%eax                |
  32:   mov    %eax,-0x4(%rbp)          |_
  38:   nopl   0x0(%rax,%rax,1)
  3d:   pop    %r13
  3f:   pop    %rbx
  40:   pop    %rax
  41:   jmpq   0xffffffffffffe377
  [...]

* tailcall_6 disasm, emit_bpf_tail_call_indirect():

  [...]
  47:   movabs $0xffff8d3f59143a00,%rsi
  51:   mov    %edx,%edx
  53:   cmp    %edx,0x24(%rsi)
  56:   jbe    0x0000000000000093        _
  58:   mov    -0x4(%rbp),%eax          |  limit check
  5e:   cmp    $0x20,%eax               |
  61:   ja     0x0000000000000093       |
  63:   add    $0x1,%eax                |
  66:   mov    %eax,-0x4(%rbp)          |_
  6c:   mov    0x110(%rsi,%rdx,8),%rcx
  74:   test   %rcx,%rcx
  77:   je     0x0000000000000093
  79:   pop    %rax
  7a:   mov    0x30(%rcx),%rcx
  7e:   add    $0xb,%rcx
  82:   callq  0x000000000000008e
  87:   pause
  89:   lfence
  8c:   jmp    0x0000000000000087
  8e:   mov    %rcx,(%rsp)
  92:   retq
  [...]

Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Tested-by: Tiezhu Yang <yangtiezhu@loongson.cn>
Acked-by: Yonghong Song <yhs@fb.com>
Acked-by: Johan Almbladh <johan.almbladh@anyfinetworks.com>
Acked-by: Paul Chaignon <paul@cilium.io>
Link: https://lore.kernel.org/bpf/CAM1=_QRyRVCODcXo_Y6qOm1iT163HoiSj8U2pZ8Rj3hzMTT=HQ@mail.gmail.com
Link: https://lore.kernel.org/bpf/20210910091900.16119-1-daniel@iogearbox.net
---
 tools/testing/selftests/bpf/prog_tests/tailcalls.c | 25 ++++++++++++----
 tools/testing/selftests/bpf/progs/tailcall6.c      | 34 ++++++++++++++++++++++
 2 files changed, 54 insertions(+), 5 deletions(-)
 create mode 100644 tools/testing/selftests/bpf/progs/tailcall6.c

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/prog_tests/tailcalls.c b/tools/testing/selftests/bpf/prog_tests/tailcalls.c
index b5940e6ca67c..7bf3a7a97d7b 100644
--- a/tools/testing/selftests/bpf/prog_tests/tailcalls.c
+++ b/tools/testing/selftests/bpf/prog_tests/tailcalls.c
@@ -219,10 +219,7 @@ out:
 	bpf_object__close(obj);
 }
 
-/* test_tailcall_3 checks that the count value of the tail call limit
- * enforcement matches with expectations.
- */
-static void test_tailcall_3(void)
+static void test_tailcall_count(const char *which)
 {
 	int err, map_fd, prog_fd, main_fd, data_fd, i, val;
 	struct bpf_map *prog_array, *data_map;
@@ -231,7 +228,7 @@ static void test_tailcall_3(void)
 	__u32 retval, duration;
 	char buff[128] = {};
 
-	err = bpf_prog_load("tailcall3.o", BPF_PROG_TYPE_SCHED_CLS, &obj,
+	err = bpf_prog_load(which, BPF_PROG_TYPE_SCHED_CLS, &obj,
 			    &prog_fd);
 	if (CHECK_FAIL(err))
 		return;
@@ -296,6 +293,22 @@ out:
 	bpf_object__close(obj);
 }
 
+/* test_tailcall_3 checks that the count value of the tail call limit
+ * enforcement matches with expectations. JIT uses direct jump.
+ */
+static void test_tailcall_3(void)
+{
+	test_tailcall_count("tailcall3.o");
+}
+
+/* test_tailcall_6 checks that the count value of the tail call limit
+ * enforcement matches with expectations. JIT uses indirect jump.
+ */
+static void test_tailcall_6(void)
+{
+	test_tailcall_count("tailcall6.o");
+}
+
 /* test_tailcall_4 checks that the kernel properly selects indirect jump
  * for the case where the key is not known. Latter is passed via global
  * data to select different targets we can compare return value of.
@@ -822,6 +835,8 @@ void test_tailcalls(void)
 		test_tailcall_4();
 	if (test__start_subtest("tailcall_5"))
 		test_tailcall_5();
+	if (test__start_subtest("tailcall_6"))
+		test_tailcall_6();
 	if (test__start_subtest("tailcall_bpf2bpf_1"))
 		test_tailcall_bpf2bpf_1();
 	if (test__start_subtest("tailcall_bpf2bpf_2"))
diff --git a/tools/testing/selftests/bpf/progs/tailcall6.c b/tools/testing/selftests/bpf/progs/tailcall6.c
new file mode 100644
index 000000000000..0f4a811cc028
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/tailcall6.c
@@ -0,0 +1,34 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/bpf.h>
+
+#include <bpf/bpf_helpers.h>
+
+struct {
+	__uint(type, BPF_MAP_TYPE_PROG_ARRAY);
+	__uint(max_entries, 1);
+	__uint(key_size, sizeof(__u32));
+	__uint(value_size, sizeof(__u32));
+} jmp_table SEC(".maps");
+
+int count, which;
+
+SEC("classifier/0")
+int bpf_func_0(struct __sk_buff *skb)
+{
+	count++;
+	if (__builtin_constant_p(which))
+		__bpf_unreachable();
+	bpf_tail_call(skb, &jmp_table, which);
+	return 1;
+}
+
+SEC("classifier")
+int entry(struct __sk_buff *skb)
+{
+	if (__builtin_constant_p(which))
+		__bpf_unreachable();
+	bpf_tail_call(skb, &jmp_table, which);
+	return 0;
+}
+
+char __license[] SEC("license") = "GPL";
-- 
cgit v1.2.3


From 2f383041278672332ab57c78570c30c47d6f35fd Mon Sep 17 00:00:00 2001
From: Andrii Nakryiko <andrii@kernel.org>
Date: Mon, 13 Sep 2021 15:23:09 -0700
Subject: libbpf: Make libbpf_version.h non-auto-generated

Turn previously auto-generated libbpf_version.h header into a normal
header file. This prevents various tricky Makefile integration issues,
simplifies the overall build process, but also allows to further extend
it with some more versioning-related APIs in the future.

To prevent accidental out-of-sync versions as defined by libbpf.map and
libbpf_version.h, Makefile checks their consistency at build time.

Simultaneously with this change bump libbpf.map to v0.6.

Also undo adding libbpf's output directory into include path for
kernel/bpf/preload, bpftool, and resolve_btfids, which is not necessary
because libbpf_version.h is just a normal header like any other.

Fixes: 0b46b7550560 ("libbpf: Add LIBBPF_DEPRECATED_SINCE macro for scheduling API deprecations")
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20210913222309.3220849-1-andrii@kernel.org
---
 tools/bpf/bpftool/Makefile        |  1 -
 tools/bpf/resolve_btfids/Makefile |  1 -
 tools/lib/bpf/.gitignore          |  1 -
 tools/lib/bpf/Makefile            | 33 +++++++++++++++++++++------------
 tools/lib/bpf/libbpf.map          |  3 +++
 tools/lib/bpf/libbpf_version.h    |  9 +++++++++
 6 files changed, 33 insertions(+), 15 deletions(-)
 create mode 100644 tools/lib/bpf/libbpf_version.h

(limited to 'tools')

diff --git a/tools/bpf/bpftool/Makefile b/tools/bpf/bpftool/Makefile
index 06aa1616dabe..1fcf5b01a193 100644
--- a/tools/bpf/bpftool/Makefile
+++ b/tools/bpf/bpftool/Makefile
@@ -60,7 +60,6 @@ CFLAGS += -W -Wall -Wextra -Wno-unused-parameter -Wno-missing-field-initializers
 CFLAGS += $(filter-out -Wswitch-enum -Wnested-externs,$(EXTRA_WARNINGS))
 CFLAGS += -DPACKAGE='"bpftool"' -D__EXPORTED_HEADERS__ \
 	-I$(if $(OUTPUT),$(OUTPUT),.) \
-	$(if $(LIBBPF_OUTPUT),-I$(LIBBPF_OUTPUT)) \
 	-I$(srctree)/kernel/bpf/ \
 	-I$(srctree)/tools/include \
 	-I$(srctree)/tools/include/uapi \
diff --git a/tools/bpf/resolve_btfids/Makefile b/tools/bpf/resolve_btfids/Makefile
index edc0c329cf74..08b75e314ae7 100644
--- a/tools/bpf/resolve_btfids/Makefile
+++ b/tools/bpf/resolve_btfids/Makefile
@@ -47,7 +47,6 @@ $(BPFOBJ): $(wildcard $(LIBBPF_SRC)/*.[ch] $(LIBBPF_SRC)/Makefile) | $(OUTPUT)/l
 CFLAGS := -g \
           -I$(srctree)/tools/include \
           -I$(srctree)/tools/include/uapi \
-          -I$(LIBBPF_OUT) \
           -I$(LIBBPF_SRC) \
           -I$(SUBCMD_SRC)
 
diff --git a/tools/lib/bpf/.gitignore b/tools/lib/bpf/.gitignore
index 5d4cfac671d5..0da84cb9e66d 100644
--- a/tools/lib/bpf/.gitignore
+++ b/tools/lib/bpf/.gitignore
@@ -1,5 +1,4 @@
 # SPDX-License-Identifier: GPL-2.0-only
-libbpf_version.h
 libbpf.pc
 libbpf.so.*
 TAGS
diff --git a/tools/lib/bpf/Makefile b/tools/lib/bpf/Makefile
index dab21e0c7cc2..0f766345506f 100644
--- a/tools/lib/bpf/Makefile
+++ b/tools/lib/bpf/Makefile
@@ -113,9 +113,8 @@ SHARED_OBJDIR	:= $(OUTPUT)sharedobjs/
 STATIC_OBJDIR	:= $(OUTPUT)staticobjs/
 BPF_IN_SHARED	:= $(SHARED_OBJDIR)libbpf-in.o
 BPF_IN_STATIC	:= $(STATIC_OBJDIR)libbpf-in.o
-VERSION_HDR	:= $(OUTPUT)libbpf_version.h
 BPF_HELPER_DEFS	:= $(OUTPUT)bpf_helper_defs.h
-BPF_GENERATED	:= $(BPF_HELPER_DEFS) $(VERSION_HDR)
+BPF_GENERATED	:= $(BPF_HELPER_DEFS)
 
 LIB_TARGET	:= $(addprefix $(OUTPUT),$(LIB_TARGET))
 LIB_FILE	:= $(addprefix $(OUTPUT),$(LIB_FILE))
@@ -165,12 +164,6 @@ $(BPF_HELPER_DEFS): $(srctree)/tools/include/uapi/linux/bpf.h
 	$(QUIET_GEN)$(srctree)/scripts/bpf_doc.py --header \
 		--file $(srctree)/tools/include/uapi/linux/bpf.h > $(BPF_HELPER_DEFS)
 
-$(VERSION_HDR): force
-	$(QUIET_GEN)echo "/* This file was auto-generated. */" > $@
-	@echo "" >> $@
-	@echo "#define LIBBPF_MAJOR_VERSION $(LIBBPF_MAJOR_VERSION)" >> $@
-	@echo "#define LIBBPF_MINOR_VERSION $(LIBBPF_MINOR_VERSION)" >> $@
-
 $(OUTPUT)libbpf.so: $(OUTPUT)libbpf.so.$(LIBBPF_VERSION)
 
 $(OUTPUT)libbpf.so.$(LIBBPF_VERSION): $(BPF_IN_SHARED) $(VERSION_SCRIPT)
@@ -189,7 +182,7 @@ $(OUTPUT)libbpf.pc:
 		-e "s|@VERSION@|$(LIBBPF_VERSION)|" \
 		< libbpf.pc.template > $@
 
-check: check_abi
+check: check_abi check_version
 
 check_abi: $(OUTPUT)libbpf.so $(VERSION_SCRIPT)
 	@if [ "$(GLOBAL_SYM_COUNT)" != "$(VERSIONED_SYM_COUNT)" ]; then	 \
@@ -215,6 +208,21 @@ check_abi: $(OUTPUT)libbpf.so $(VERSION_SCRIPT)
 		exit 1;							 \
 	fi
 
+HDR_MAJ_VERSION := $(shell grep -oE '^\#define LIBBPF_MAJOR_VERSION ([0-9]+)$$' libbpf_version.h | cut -d' ' -f3)
+HDR_MIN_VERSION := $(shell grep -oE '^\#define LIBBPF_MINOR_VERSION ([0-9]+)$$' libbpf_version.h | cut -d' ' -f3)
+
+check_version: $(VERSION_SCRIPT) libbpf_version.h
+	@if [ "$(HDR_MAJ_VERSION)" != "$(LIBBPF_MAJOR_VERSION)" ]; then        \
+		echo "Error: libbpf major version mismatch detected: "	       \
+		     "'$(HDR_MAJ_VERSION)' != '$(LIBBPF_MAJOR_VERSION)'" >&2;  \
+		exit 1;							       \
+	fi
+	@if [ "$(HDR_MIN_VERSION)" != "$(LIBBPF_MINOR_VERSION)" ]; then	       \
+		echo "Error: libbpf minor version mismatch detected: "	       \
+		     "'$(HDR_MIN_VERSION)' != '$(LIBBPF_MINOR_VERSION)'" >&2;  \
+		exit 1;							       \
+	fi
+
 define do_install_mkdir
 	if [ ! -d '$(DESTDIR_SQ)$1' ]; then		\
 		$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$1';	\
@@ -234,8 +242,9 @@ install_lib: all_cmd
 		cp -fpR $(LIB_FILE) $(DESTDIR)$(libdir_SQ)
 
 INSTALL_HEADERS = bpf.h libbpf.h btf.h libbpf_common.h libbpf_legacy.h xsk.h \
-		  bpf_helpers.h $(BPF_GENERATED) bpf_tracing.h	     \
-		  bpf_endian.h bpf_core_read.h skel_internal.h
+		  bpf_helpers.h $(BPF_GENERATED) bpf_tracing.h		     \
+		  bpf_endian.h bpf_core_read.h skel_internal.h		     \
+		  libbpf_version.h
 
 install_headers: $(BPF_GENERATED)
 	$(call QUIET_INSTALL, headers)					     \
@@ -255,7 +264,7 @@ clean:
 		$(addprefix $(OUTPUT),					     \
 			    *.o *.a *.so *.so.$(LIBBPF_MAJOR_VERSION) *.pc)
 
-PHONY += force cscope tags
+PHONY += force cscope tags check check_abi check_version
 force:
 
 cscope:
diff --git a/tools/lib/bpf/libbpf.map b/tools/lib/bpf/libbpf.map
index bbc53bb25f68..78ea62c9346f 100644
--- a/tools/lib/bpf/libbpf.map
+++ b/tools/lib/bpf/libbpf.map
@@ -386,3 +386,6 @@ LIBBPF_0.5.0 {
 		btf_dump__dump_type_data;
 		libbpf_set_strict_mode;
 } LIBBPF_0.4.0;
+
+LIBBPF_0.6.0 {
+} LIBBPF_0.5.0;
diff --git a/tools/lib/bpf/libbpf_version.h b/tools/lib/bpf/libbpf_version.h
new file mode 100644
index 000000000000..dd56d76f291c
--- /dev/null
+++ b/tools/lib/bpf/libbpf_version.h
@@ -0,0 +1,9 @@
+/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */
+/* Copyright (C) 2021 Facebook */
+#ifndef __LIBBPF_VERSION_H
+#define __LIBBPF_VERSION_H
+
+#define LIBBPF_MAJOR_VERSION 0
+#define LIBBPF_MINOR_VERSION 6
+
+#endif /* __LIBBPF_VERSION_H */
-- 
cgit v1.2.3


From ca304b40c20d5750f08200f0ad3445384646620c Mon Sep 17 00:00:00 2001
From: Rafael David Tinoco <rafaeldtinoco@gmail.com>
Date: Sun, 12 Sep 2021 03:48:44 -0300
Subject: libbpf: Introduce legacy kprobe events support

Allow kprobe tracepoint events creation through legacy interface, as the
kprobe dynamic PMUs support, used by default, was only created in v4.17.

Store legacy kprobe name in struct bpf_perf_link, instead of creating
a new "subclass" off of bpf_perf_link. This is ok as it's just two new
fields, which are also going to be reused for legacy uprobe support in
follow up patches.

Signed-off-by: Rafael David Tinoco <rafaeldtinoco@gmail.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20210912064844.3181742-1-rafaeldtinoco@gmail.com
---
 tools/lib/bpf/libbpf.c | 128 +++++++++++++++++++++++++++++++++++++++++++++++--
 1 file changed, 124 insertions(+), 4 deletions(-)

(limited to 'tools')

diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 8f579c6666b2..9d99183bffba 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -8993,9 +8993,57 @@ int bpf_link__unpin(struct bpf_link *link)
 	return 0;
 }
 
+static int poke_kprobe_events(bool add, const char *name, bool retprobe, uint64_t offset)
+{
+	int fd, ret = 0;
+	pid_t p = getpid();
+	char cmd[260], probename[128], probefunc[128];
+	const char *file = "/sys/kernel/debug/tracing/kprobe_events";
+
+	if (retprobe)
+		snprintf(probename, sizeof(probename), "kretprobes/%s_libbpf_%u", name, p);
+	else
+		snprintf(probename, sizeof(probename), "kprobes/%s_libbpf_%u", name, p);
+
+	if (offset)
+		snprintf(probefunc, sizeof(probefunc), "%s+%zu", name, (size_t)offset);
+
+	if (add) {
+		snprintf(cmd, sizeof(cmd), "%c:%s %s",
+			 retprobe ? 'r' : 'p',
+			 probename,
+			 offset ? probefunc : name);
+	} else {
+		snprintf(cmd, sizeof(cmd), "-:%s", probename);
+	}
+
+	fd = open(file, O_WRONLY | O_APPEND, 0);
+	if (!fd)
+		return -errno;
+	ret = write(fd, cmd, strlen(cmd));
+	if (ret < 0)
+		ret = -errno;
+	close(fd);
+
+	return ret;
+}
+
+static inline int add_kprobe_event_legacy(const char *name, bool retprobe, uint64_t offset)
+{
+	return poke_kprobe_events(true, name, retprobe, offset);
+}
+
+static inline int remove_kprobe_event_legacy(const char *name, bool retprobe)
+{
+	return poke_kprobe_events(false, name, retprobe, 0);
+}
+
 struct bpf_link_perf {
 	struct bpf_link link;
 	int perf_event_fd;
+	/* legacy kprobe support: keep track of probe identifier and type */
+	char *legacy_probe_name;
+	bool legacy_is_retprobe;
 };
 
 static int bpf_link_perf_detach(struct bpf_link *link)
@@ -9010,13 +9058,19 @@ static int bpf_link_perf_detach(struct bpf_link *link)
 		close(perf_link->perf_event_fd);
 	close(link->fd);
 
-	return libbpf_err(err);
+	/* legacy kprobe needs to be removed after perf event fd closure */
+	if (perf_link->legacy_probe_name)
+		err = remove_kprobe_event_legacy(perf_link->legacy_probe_name,
+						 perf_link->legacy_is_retprobe);
+
+	return err;
 }
 
 static void bpf_link_perf_dealloc(struct bpf_link *link)
 {
 	struct bpf_link_perf *perf_link = container_of(link, struct bpf_link_perf, link);
 
+	free(perf_link->legacy_probe_name);
 	free(perf_link);
 }
 
@@ -9130,6 +9184,18 @@ static int parse_uint_from_file(const char *file, const char *fmt)
 	return ret;
 }
 
+static int determine_kprobe_perf_type_legacy(const char *func_name, bool is_retprobe)
+{
+	char file[192];
+
+	snprintf(file, sizeof(file),
+		 "/sys/kernel/debug/tracing/events/%s/%s_libbpf_%d/id",
+		 is_retprobe ? "kretprobes" : "kprobes",
+		 func_name, getpid());
+
+	return parse_uint_from_file(file, "%d\n");
+}
+
 static int determine_kprobe_perf_type(void)
 {
 	const char *file = "/sys/bus/event_source/devices/kprobe/type";
@@ -9212,6 +9278,41 @@ static int perf_event_open_probe(bool uprobe, bool retprobe, const char *name,
 	return pfd;
 }
 
+static int perf_event_kprobe_open_legacy(bool retprobe, const char *name, uint64_t offset, int pid)
+{
+	struct perf_event_attr attr = {};
+	char errmsg[STRERR_BUFSIZE];
+	int type, pfd, err;
+
+	err = add_kprobe_event_legacy(name, retprobe, offset);
+	if (err < 0) {
+		pr_warn("failed to add legacy kprobe event: %s\n",
+			libbpf_strerror_r(err, errmsg, sizeof(errmsg)));
+		return err;
+	}
+	type = determine_kprobe_perf_type_legacy(name, retprobe);
+	if (type < 0) {
+		pr_warn("failed to determine legacy kprobe event id: %s\n",
+			libbpf_strerror_r(type, errmsg, sizeof(errmsg)));
+		return type;
+	}
+	attr.size = sizeof(attr);
+	attr.config = type;
+	attr.type = PERF_TYPE_TRACEPOINT;
+
+	pfd = syscall(__NR_perf_event_open, &attr,
+		      pid < 0 ? -1 : pid, /* pid */
+		      pid == -1 ? 0 : -1, /* cpu */
+		      -1 /* group_fd */,  PERF_FLAG_FD_CLOEXEC);
+	if (pfd < 0) {
+		err = -errno;
+		pr_warn("legacy kprobe perf_event_open() failed: %s\n",
+			libbpf_strerror_r(err, errmsg, sizeof(errmsg)));
+		return err;
+	}
+	return pfd;
+}
+
 struct bpf_link *
 bpf_program__attach_kprobe_opts(struct bpf_program *prog,
 				const char *func_name,
@@ -9219,9 +9320,10 @@ bpf_program__attach_kprobe_opts(struct bpf_program *prog,
 {
 	DECLARE_LIBBPF_OPTS(bpf_perf_event_opts, pe_opts);
 	char errmsg[STRERR_BUFSIZE];
+	char *legacy_probe = NULL;
 	struct bpf_link *link;
 	unsigned long offset;
-	bool retprobe;
+	bool retprobe, legacy;
 	int pfd, err;
 
 	if (!OPTS_VALID(opts, bpf_kprobe_opts))
@@ -9231,8 +9333,19 @@ bpf_program__attach_kprobe_opts(struct bpf_program *prog,
 	offset = OPTS_GET(opts, offset, 0);
 	pe_opts.bpf_cookie = OPTS_GET(opts, bpf_cookie, 0);
 
-	pfd = perf_event_open_probe(false /* uprobe */, retprobe, func_name,
-				    offset, -1 /* pid */, 0 /* ref_ctr_off */);
+	legacy = determine_kprobe_perf_type() < 0;
+	if (!legacy) {
+		pfd = perf_event_open_probe(false /* uprobe */, retprobe,
+					    func_name, offset,
+					    -1 /* pid */, 0 /* ref_ctr_off */);
+	} else {
+		legacy_probe = strdup(func_name);
+		if (!legacy_probe)
+			return libbpf_err_ptr(-ENOMEM);
+
+		pfd = perf_event_kprobe_open_legacy(retprobe, func_name,
+						    offset, -1 /* pid */);
+	}
 	if (pfd < 0) {
 		pr_warn("prog '%s': failed to create %s '%s' perf event: %s\n",
 			prog->name, retprobe ? "kretprobe" : "kprobe", func_name,
@@ -9248,6 +9361,13 @@ bpf_program__attach_kprobe_opts(struct bpf_program *prog,
 			libbpf_strerror_r(err, errmsg, sizeof(errmsg)));
 		return libbpf_err_ptr(err);
 	}
+	if (legacy) {
+		struct bpf_link_perf *perf_link = container_of(link, struct bpf_link_perf, link);
+
+		perf_link->legacy_probe_name = legacy_probe;
+		perf_link->legacy_is_retprobe = retprobe;
+	}
+
 	return link;
 }
 
-- 
cgit v1.2.3


From 53df63ccdc0258118e53089197d0428c5330cc9c Mon Sep 17 00:00:00 2001
From: Andrii Nakryiko <andrii@kernel.org>
Date: Mon, 13 Sep 2021 18:47:30 -0700
Subject: selftests/bpf: Update selftests to always provide "struct_ops" SEC

Update struct_ops selftests to always specify "struct_ops" section
prefix. Libbpf will require a proper BPF program type set in the next
patch, so this prevents tests breaking.

Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Link: https://lore.kernel.org/bpf/20210914014733.2768-2-andrii@kernel.org
---
 tools/testing/selftests/bpf/progs/bpf_cubic.c | 12 +++---------
 1 file changed, 3 insertions(+), 9 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/progs/bpf_cubic.c b/tools/testing/selftests/bpf/progs/bpf_cubic.c
index f62df4d023f9..d9660e7200e2 100644
--- a/tools/testing/selftests/bpf/progs/bpf_cubic.c
+++ b/tools/testing/selftests/bpf/progs/bpf_cubic.c
@@ -169,11 +169,7 @@ static __always_inline void bictcp_hystart_reset(struct sock *sk)
 	ca->sample_cnt = 0;
 }
 
-/* "struct_ops/" prefix is not a requirement
- * It will be recognized as BPF_PROG_TYPE_STRUCT_OPS
- * as long as it is used in one of the func ptr
- * under SEC(".struct_ops").
- */
+/* "struct_ops/" prefix is a requirement */
 SEC("struct_ops/bpf_cubic_init")
 void BPF_PROG(bpf_cubic_init, struct sock *sk)
 {
@@ -188,10 +184,8 @@ void BPF_PROG(bpf_cubic_init, struct sock *sk)
 		tcp_sk(sk)->snd_ssthresh = initial_ssthresh;
 }
 
-/* No prefix in SEC will also work.
- * The remaining tcp-cubic functions have an easier way.
- */
-SEC("no-sec-prefix-bictcp_cwnd_event")
+/* "struct_ops" prefix is a requirement */
+SEC("struct_ops/bpf_cubic_cwnd_event")
 void BPF_PROG(bpf_cubic_cwnd_event, struct sock *sk, enum tcp_ca_event event)
 {
 	if (event == CA_EVENT_TX_START) {
-- 
cgit v1.2.3


From 91b4d1d1d54431c72f3a7ff034f30a635f787426 Mon Sep 17 00:00:00 2001
From: Andrii Nakryiko <andrii@kernel.org>
Date: Mon, 13 Sep 2021 18:47:31 -0700
Subject: libbpf: Ensure BPF prog types are set before relocations

Refactor bpf_object__open() sequencing to perform BPF program type
detection based on SEC() definitions before we get to relocations
collection. This allows to have more information about BPF program by
the time we get to, say, struct_ops relocation gathering. This,
subsequently, simplifies struct_ops logic and removes the need to
perform extra find_sec_def() resolution.

With this patch libbpf will require all struct_ops BPF programs to be
marked with SEC("struct_ops") or SEC("struct_ops/xxx") annotations.
Real-world applications are already doing that through something like
selftests's BPF_STRUCT_OPS() macro. This change streamlines libbpf's
internal handling of SEC() definitions and is in the sprit of
upcoming libbpf-1.0 section strictness changes ([0]).

  [0] https://github.com/libbpf/libbpf/wiki/Libbpf:-the-road-to-v1.0#stricter-and-more-uniform-bpf-program-section-name-sec-handling

Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Link: https://lore.kernel.org/bpf/20210914014733.2768-3-andrii@kernel.org
---
 tools/lib/bpf/libbpf.c | 93 +++++++++++++++++++++++++++-----------------------
 1 file changed, 51 insertions(+), 42 deletions(-)

(limited to 'tools')

diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 9d99183bffba..6abfbf283092 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -6373,12 +6373,37 @@ bpf_object__load_progs(struct bpf_object *obj, int log_level)
 
 static const struct bpf_sec_def *find_sec_def(const char *sec_name);
 
+static int bpf_object_init_progs(struct bpf_object *obj, const struct bpf_object_open_opts *opts)
+{
+	struct bpf_program *prog;
+
+	bpf_object__for_each_program(prog, obj) {
+		prog->sec_def = find_sec_def(prog->sec_name);
+		if (!prog->sec_def) {
+			/* couldn't guess, but user might manually specify */
+			pr_debug("prog '%s': unrecognized ELF section name '%s'\n",
+				prog->name, prog->sec_name);
+			continue;
+		}
+
+		if (prog->sec_def->is_sleepable)
+			prog->prog_flags |= BPF_F_SLEEPABLE;
+		bpf_program__set_type(prog, prog->sec_def->prog_type);
+		bpf_program__set_expected_attach_type(prog, prog->sec_def->expected_attach_type);
+
+		if (prog->sec_def->prog_type == BPF_PROG_TYPE_TRACING ||
+		    prog->sec_def->prog_type == BPF_PROG_TYPE_EXT)
+			prog->attach_prog_fd = OPTS_GET(opts, attach_prog_fd, 0);
+	}
+
+	return 0;
+}
+
 static struct bpf_object *
 __bpf_object__open(const char *path, const void *obj_buf, size_t obj_buf_sz,
 		   const struct bpf_object_open_opts *opts)
 {
 	const char *obj_name, *kconfig, *btf_tmp_path;
-	struct bpf_program *prog;
 	struct bpf_object *obj;
 	char tmp_name[64];
 	int err;
@@ -6436,30 +6461,12 @@ __bpf_object__open(const char *path, const void *obj_buf, size_t obj_buf_sz,
 	err = err ? : bpf_object__collect_externs(obj);
 	err = err ? : bpf_object__finalize_btf(obj);
 	err = err ? : bpf_object__init_maps(obj, opts);
+	err = err ? : bpf_object_init_progs(obj, opts);
 	err = err ? : bpf_object__collect_relos(obj);
 	if (err)
 		goto out;
-	bpf_object__elf_finish(obj);
 
-	bpf_object__for_each_program(prog, obj) {
-		prog->sec_def = find_sec_def(prog->sec_name);
-		if (!prog->sec_def) {
-			/* couldn't guess, but user might manually specify */
-			pr_debug("prog '%s': unrecognized ELF section name '%s'\n",
-				prog->name, prog->sec_name);
-			continue;
-		}
-
-		if (prog->sec_def->is_sleepable)
-			prog->prog_flags |= BPF_F_SLEEPABLE;
-		bpf_program__set_type(prog, prog->sec_def->prog_type);
-		bpf_program__set_expected_attach_type(prog,
-				prog->sec_def->expected_attach_type);
-
-		if (prog->sec_def->prog_type == BPF_PROG_TYPE_TRACING ||
-		    prog->sec_def->prog_type == BPF_PROG_TYPE_EXT)
-			prog->attach_prog_fd = OPTS_GET(opts, attach_prog_fd, 0);
-	}
+	bpf_object__elf_finish(obj);
 
 	return obj;
 out:
@@ -8250,35 +8257,37 @@ static int bpf_object__collect_st_ops_relos(struct bpf_object *obj,
 			return -EINVAL;
 		}
 
-		if (prog->type == BPF_PROG_TYPE_UNSPEC) {
-			const struct bpf_sec_def *sec_def;
-
-			sec_def = find_sec_def(prog->sec_name);
-			if (sec_def &&
-			    sec_def->prog_type != BPF_PROG_TYPE_STRUCT_OPS) {
-				/* for pr_warn */
-				prog->type = sec_def->prog_type;
-				goto invalid_prog;
-			}
+		/* prevent the use of BPF prog with invalid type */
+		if (prog->type != BPF_PROG_TYPE_STRUCT_OPS) {
+			pr_warn("struct_ops reloc %s: prog %s is not struct_ops BPF program\n",
+				map->name, prog->name);
+			return -EINVAL;
+		}
 
-			prog->type = BPF_PROG_TYPE_STRUCT_OPS;
+		/* if we haven't yet processed this BPF program, record proper
+		 * attach_btf_id and member_idx
+		 */
+		if (!prog->attach_btf_id) {
 			prog->attach_btf_id = st_ops->type_id;
 			prog->expected_attach_type = member_idx;
-		} else if (prog->type != BPF_PROG_TYPE_STRUCT_OPS ||
-			   prog->attach_btf_id != st_ops->type_id ||
-			   prog->expected_attach_type != member_idx) {
-			goto invalid_prog;
 		}
+
+		/* struct_ops BPF prog can be re-used between multiple
+		 * .struct_ops as long as it's the same struct_ops struct
+		 * definition and the same function pointer field
+		 */
+		if (prog->attach_btf_id != st_ops->type_id ||
+		    prog->expected_attach_type != member_idx) {
+			pr_warn("struct_ops reloc %s: cannot use prog %s in sec %s with type %u attach_btf_id %u expected_attach_type %u for func ptr %s\n",
+				map->name, prog->name, prog->sec_name, prog->type,
+				prog->attach_btf_id, prog->expected_attach_type, name);
+			return -EINVAL;
+		}
+
 		st_ops->progs[member_idx] = prog;
 	}
 
 	return 0;
-
-invalid_prog:
-	pr_warn("struct_ops reloc %s: cannot use prog %s in sec %s with type %u attach_btf_id %u expected_attach_type %u for func ptr %s\n",
-		map->name, prog->name, prog->sec_name, prog->type,
-		prog->attach_btf_id, prog->expected_attach_type, name);
-	return -EINVAL;
 }
 
 #define BTF_TRACE_PREFIX "btf_trace_"
-- 
cgit v1.2.3


From 5532dfd42e4846e84d346a6dfe01e477e35baa65 Mon Sep 17 00:00:00 2001
From: Andrii Nakryiko <andrii@kernel.org>
Date: Mon, 13 Sep 2021 18:47:32 -0700
Subject: libbpf: Simplify BPF program auto-attach code

Remove the need to explicitly pass bpf_sec_def for auto-attachable BPF
programs, as it is already recorded at bpf_object__open() time for all
recognized type of BPF programs. This further reduces number of explicit
calls to find_sec_def(), simplifying further refactorings.

No functional changes are done by this patch.

Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Link: https://lore.kernel.org/bpf/20210914014733.2768-4-andrii@kernel.org
---
 tools/lib/bpf/libbpf.c | 61 ++++++++++++++++++--------------------------------
 1 file changed, 22 insertions(+), 39 deletions(-)

(limited to 'tools')

diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 6abfbf283092..e473fbd2b361 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -218,8 +218,7 @@ struct reloc_desc {
 
 struct bpf_sec_def;
 
-typedef struct bpf_link *(*attach_fn_t)(const struct bpf_sec_def *sec,
-					struct bpf_program *prog);
+typedef struct bpf_link *(*attach_fn_t)(struct bpf_program *prog);
 
 struct bpf_sec_def {
 	const char *sec;
@@ -7920,18 +7919,12 @@ void bpf_program__set_expected_attach_type(struct bpf_program *prog,
 	__VA_ARGS__							    \
 }
 
-static struct bpf_link *attach_kprobe(const struct bpf_sec_def *sec,
-				      struct bpf_program *prog);
-static struct bpf_link *attach_tp(const struct bpf_sec_def *sec,
-				  struct bpf_program *prog);
-static struct bpf_link *attach_raw_tp(const struct bpf_sec_def *sec,
-				      struct bpf_program *prog);
-static struct bpf_link *attach_trace(const struct bpf_sec_def *sec,
-				     struct bpf_program *prog);
-static struct bpf_link *attach_lsm(const struct bpf_sec_def *sec,
-				   struct bpf_program *prog);
-static struct bpf_link *attach_iter(const struct bpf_sec_def *sec,
-				    struct bpf_program *prog);
+static struct bpf_link *attach_kprobe(struct bpf_program *prog);
+static struct bpf_link *attach_tp(struct bpf_program *prog);
+static struct bpf_link *attach_raw_tp(struct bpf_program *prog);
+static struct bpf_link *attach_trace(struct bpf_program *prog);
+static struct bpf_link *attach_lsm(struct bpf_program *prog);
+static struct bpf_link *attach_iter(struct bpf_program *prog);
 
 static const struct bpf_sec_def section_defs[] = {
 	BPF_PROG_SEC("socket",			BPF_PROG_TYPE_SOCKET_FILTER),
@@ -9391,8 +9384,7 @@ struct bpf_link *bpf_program__attach_kprobe(struct bpf_program *prog,
 	return bpf_program__attach_kprobe_opts(prog, func_name, &opts);
 }
 
-static struct bpf_link *attach_kprobe(const struct bpf_sec_def *sec,
-				      struct bpf_program *prog)
+static struct bpf_link *attach_kprobe(struct bpf_program *prog)
 {
 	DECLARE_LIBBPF_OPTS(bpf_kprobe_opts, opts);
 	unsigned long offset = 0;
@@ -9401,8 +9393,8 @@ static struct bpf_link *attach_kprobe(const struct bpf_sec_def *sec,
 	char *func;
 	int n, err;
 
-	func_name = prog->sec_name + sec->len;
-	opts.retprobe = strcmp(sec->sec, "kretprobe/") == 0;
+	func_name = prog->sec_name + prog->sec_def->len;
+	opts.retprobe = strcmp(prog->sec_def->sec, "kretprobe/") == 0;
 
 	n = sscanf(func_name, "%m[a-zA-Z0-9_.]+%li", &func, &offset);
 	if (n < 1) {
@@ -9565,8 +9557,7 @@ struct bpf_link *bpf_program__attach_tracepoint(struct bpf_program *prog,
 	return bpf_program__attach_tracepoint_opts(prog, tp_category, tp_name, NULL);
 }
 
-static struct bpf_link *attach_tp(const struct bpf_sec_def *sec,
-				  struct bpf_program *prog)
+static struct bpf_link *attach_tp(struct bpf_program *prog)
 {
 	char *sec_name, *tp_cat, *tp_name;
 	struct bpf_link *link;
@@ -9576,7 +9567,7 @@ static struct bpf_link *attach_tp(const struct bpf_sec_def *sec,
 		return libbpf_err_ptr(-ENOMEM);
 
 	/* extract "tp/<category>/<name>" */
-	tp_cat = sec_name + sec->len;
+	tp_cat = sec_name + prog->sec_def->len;
 	tp_name = strchr(tp_cat, '/');
 	if (!tp_name) {
 		free(sec_name);
@@ -9620,10 +9611,9 @@ struct bpf_link *bpf_program__attach_raw_tracepoint(struct bpf_program *prog,
 	return link;
 }
 
-static struct bpf_link *attach_raw_tp(const struct bpf_sec_def *sec,
-				      struct bpf_program *prog)
+static struct bpf_link *attach_raw_tp(struct bpf_program *prog)
 {
-	const char *tp_name = prog->sec_name + sec->len;
+	const char *tp_name = prog->sec_name + prog->sec_def->len;
 
 	return bpf_program__attach_raw_tracepoint(prog, tp_name);
 }
@@ -9668,14 +9658,12 @@ struct bpf_link *bpf_program__attach_lsm(struct bpf_program *prog)
 	return bpf_program__attach_btf_id(prog);
 }
 
-static struct bpf_link *attach_trace(const struct bpf_sec_def *sec,
-				     struct bpf_program *prog)
+static struct bpf_link *attach_trace(struct bpf_program *prog)
 {
 	return bpf_program__attach_trace(prog);
 }
 
-static struct bpf_link *attach_lsm(const struct bpf_sec_def *sec,
-				   struct bpf_program *prog)
+static struct bpf_link *attach_lsm(struct bpf_program *prog)
 {
 	return bpf_program__attach_lsm(prog);
 }
@@ -9806,21 +9794,17 @@ bpf_program__attach_iter(struct bpf_program *prog,
 	return link;
 }
 
-static struct bpf_link *attach_iter(const struct bpf_sec_def *sec,
-				    struct bpf_program *prog)
+static struct bpf_link *attach_iter(struct bpf_program *prog)
 {
 	return bpf_program__attach_iter(prog, NULL);
 }
 
 struct bpf_link *bpf_program__attach(struct bpf_program *prog)
 {
-	const struct bpf_sec_def *sec_def;
-
-	sec_def = find_sec_def(prog->sec_name);
-	if (!sec_def || !sec_def->attach_fn)
+	if (!prog->sec_def || !prog->sec_def->attach_fn)
 		return libbpf_err_ptr(-ESRCH);
 
-	return sec_def->attach_fn(sec_def, prog);
+	return prog->sec_def->attach_fn(prog);
 }
 
 static int bpf_link__detach_struct_ops(struct bpf_link *link)
@@ -10899,16 +10883,15 @@ int bpf_object__attach_skeleton(struct bpf_object_skeleton *s)
 	for (i = 0; i < s->prog_cnt; i++) {
 		struct bpf_program *prog = *s->progs[i].prog;
 		struct bpf_link **link = s->progs[i].link;
-		const struct bpf_sec_def *sec_def;
 
 		if (!prog->load)
 			continue;
 
-		sec_def = find_sec_def(prog->sec_name);
-		if (!sec_def || !sec_def->attach_fn)
+		/* auto-attaching not supported for this program */
+		if (!prog->sec_def || !prog->sec_def->attach_fn)
 			continue;
 
-		*link = sec_def->attach_fn(sec_def, prog);
+		*link = prog->sec_def->attach_fn(prog);
 		err = libbpf_get_error(*link);
 		if (err) {
 			pr_warn("failed to auto-attach program '%s': %d\n",
-- 
cgit v1.2.3


From b6291a6f30d35bd4459dc35aac2f30669a4356ac Mon Sep 17 00:00:00 2001
From: Andrii Nakryiko <andrii@kernel.org>
Date: Mon, 13 Sep 2021 18:47:33 -0700
Subject: libbpf: Minimize explicit iterator of section definition array

Remove almost all the code that explicitly iterated BPF program section
definitions in favor of using find_sec_def(). The only remaining user of
section_defs is libbpf_get_type_names that has to iterate all of them to
construct its result.

Having one internal API entry point for section definitions will
simplify further refactorings around libbpf's program section
definitions parsing.

Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Link: https://lore.kernel.org/bpf/20210914014733.2768-5-andrii@kernel.org
---
 tools/lib/bpf/libbpf.c | 46 +++++++++++++++++++---------------------------
 1 file changed, 19 insertions(+), 27 deletions(-)

(limited to 'tools')

diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index e473fbd2b361..62ed073ea944 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -8438,22 +8438,13 @@ static int libbpf_find_attach_btf_id(struct bpf_program *prog, int *btf_obj_fd,
 	__u32 attach_prog_fd = prog->attach_prog_fd;
 	const char *name = prog->sec_name, *attach_name;
 	const struct bpf_sec_def *sec = NULL;
-	int i, err = 0;
+	int err = 0;
 
 	if (!name)
 		return -EINVAL;
 
-	for (i = 0; i < ARRAY_SIZE(section_defs); i++) {
-		if (!section_defs[i].is_attach_btf)
-			continue;
-		if (strncmp(name, section_defs[i].sec, section_defs[i].len))
-			continue;
-
-		sec = &section_defs[i];
-		break;
-	}
-
-	if (!sec) {
+	sec = find_sec_def(name);
+	if (!sec || !sec->is_attach_btf) {
 		pr_warn("failed to identify BTF ID based on ELF section name '%s'\n", name);
 		return -ESRCH;
 	}
@@ -8491,27 +8482,28 @@ int libbpf_attach_type_by_name(const char *name,
 			       enum bpf_attach_type *attach_type)
 {
 	char *type_names;
-	int i;
+	const struct bpf_sec_def *sec_def;
 
 	if (!name)
 		return libbpf_err(-EINVAL);
 
-	for (i = 0; i < ARRAY_SIZE(section_defs); i++) {
-		if (strncmp(name, section_defs[i].sec, section_defs[i].len))
-			continue;
-		if (!section_defs[i].is_attachable)
-			return libbpf_err(-EINVAL);
-		*attach_type = section_defs[i].expected_attach_type;
-		return 0;
-	}
-	pr_debug("failed to guess attach type based on ELF section name '%s'\n", name);
-	type_names = libbpf_get_type_names(true);
-	if (type_names != NULL) {
-		pr_debug("attachable section(type) names are:%s\n", type_names);
-		free(type_names);
+	sec_def = find_sec_def(name);
+	if (!sec_def) {
+		pr_debug("failed to guess attach type based on ELF section name '%s'\n", name);
+		type_names = libbpf_get_type_names(true);
+		if (type_names != NULL) {
+			pr_debug("attachable section(type) names are:%s\n", type_names);
+			free(type_names);
+		}
+
+		return libbpf_err(-EINVAL);
 	}
 
-	return libbpf_err(-EINVAL);
+	if (!sec_def->is_attachable)
+		return libbpf_err(-EINVAL);
+
+	*attach_type = sec_def->expected_attach_type;
+	return 0;
 }
 
 int bpf_map__fd(const struct bpf_map *map)
-- 
cgit v1.2.3


From c0354077439bc9adcc9f2c96d6bbaf8b13748317 Mon Sep 17 00:00:00 2001
From: Jie Meng <jmeng@fb.com>
Date: Mon, 13 Sep 2021 14:13:37 -0700
Subject: bpf,x64 Emit IMUL instead of MUL for x86-64

IMUL allows for multiple operands and saving and storing rax/rdx is no
longer needed. Signedness of the operands doesn't matter here because
the we only keep the lower 32/64 bit of the product for 32/64 bit
multiplications.

Signed-off-by: Jie Meng <jmeng@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20210913211337.1564014-1-jmeng@fb.com
---
 tools/testing/selftests/bpf/verifier/jit.c | 22 +++++++++++++++++++---
 1 file changed, 19 insertions(+), 3 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/verifier/jit.c b/tools/testing/selftests/bpf/verifier/jit.c
index df215e004566..eedcb752bf70 100644
--- a/tools/testing/selftests/bpf/verifier/jit.c
+++ b/tools/testing/selftests/bpf/verifier/jit.c
@@ -62,6 +62,11 @@
 	BPF_JMP_REG(BPF_JEQ, BPF_REG_3, BPF_REG_2, 2),
 	BPF_MOV64_IMM(BPF_REG_0, 1),
 	BPF_EXIT_INSN(),
+	BPF_LD_IMM64(BPF_REG_3, 0xfefefeULL),
+	BPF_ALU64_IMM(BPF_MUL, BPF_REG_3, 0xefefef),
+	BPF_JMP_REG(BPF_JEQ, BPF_REG_3, BPF_REG_2, 2),
+	BPF_MOV64_IMM(BPF_REG_0, 1),
+	BPF_EXIT_INSN(),
 	BPF_MOV32_REG(BPF_REG_2, BPF_REG_2),
 	BPF_LD_IMM64(BPF_REG_0, 0xfefefeULL),
 	BPF_ALU32_REG(BPF_MUL, BPF_REG_0, BPF_REG_1),
@@ -73,11 +78,22 @@
 	BPF_JMP_REG(BPF_JEQ, BPF_REG_3, BPF_REG_2, 2),
 	BPF_MOV64_IMM(BPF_REG_0, 1),
 	BPF_EXIT_INSN(),
+	BPF_LD_IMM64(BPF_REG_3, 0xfefefeULL),
+	BPF_ALU32_IMM(BPF_MUL, BPF_REG_3, 0xefefef),
+	BPF_JMP_REG(BPF_JEQ, BPF_REG_3, BPF_REG_2, 2),
+	BPF_MOV64_IMM(BPF_REG_0, 1),
+	BPF_EXIT_INSN(),
+	BPF_LD_IMM64(BPF_REG_0, 0xfefefeULL),
+	BPF_LD_IMM64(BPF_REG_2, 0x2ad4d4aaULL),
+	BPF_ALU32_IMM(BPF_MUL, BPF_REG_0, 0x2b),
+	BPF_JMP_REG(BPF_JEQ, BPF_REG_0, BPF_REG_2, 2),
+	BPF_MOV64_IMM(BPF_REG_0, 1),
+	BPF_EXIT_INSN(),
 	BPF_LD_IMM64(BPF_REG_0, 0x952a7bbcULL),
 	BPF_LD_IMM64(BPF_REG_1, 0xfefefeULL),
-	BPF_LD_IMM64(BPF_REG_2, 0xeeff0d413122ULL),
-	BPF_ALU32_REG(BPF_MUL, BPF_REG_2, BPF_REG_1),
-	BPF_JMP_REG(BPF_JEQ, BPF_REG_2, BPF_REG_0, 2),
+	BPF_LD_IMM64(BPF_REG_5, 0xeeff0d413122ULL),
+	BPF_ALU32_REG(BPF_MUL, BPF_REG_5, BPF_REG_1),
+	BPF_JMP_REG(BPF_JEQ, BPF_REG_5, BPF_REG_0, 2),
 	BPF_MOV64_IMM(BPF_REG_0, 1),
 	BPF_EXIT_INSN(),
 	BPF_MOV64_IMM(BPF_REG_0, 2),
-- 
cgit v1.2.3


From 8987ede3ed276f669eb88d952184e1d2bf42ea6b Mon Sep 17 00:00:00 2001
From: Andrii Nakryiko <andrii@kernel.org>
Date: Tue, 14 Sep 2021 09:22:28 -0700
Subject: selftests/bpf: Fix .gitignore to not ignore test_progs.c

List all possible test_progs flavors explicitly to avoid accidentally
ignoring valid source code files. In this case, test_progs.c was still
ignored after recent 809ed84de8b3 ("selftests/bpf: Whitelist test_progs.h
from .gitignore") fix that added exception only for test_progs.h.

Fixes: 74b5a5968fe8 ("selftests/bpf: Replace test_progs and test_maps w/ general rule")
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Yonghong Song <yhs@fb.com>
Link: https://lore.kernel.org/bpf/20210914162228.3995740-1-andrii@kernel.org
---
 tools/testing/selftests/bpf/.gitignore | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/.gitignore b/tools/testing/selftests/bpf/.gitignore
index 433f8bef261e..1dad8d617da8 100644
--- a/tools/testing/selftests/bpf/.gitignore
+++ b/tools/testing/selftests/bpf/.gitignore
@@ -9,8 +9,9 @@ test_tag
 FEATURE-DUMP.libbpf
 fixdep
 test_dev_cgroup
-/test_progs*
-!test_progs.h
+/test_progs
+/test_progs-no_alu32
+/test_progs-bpf_gcc
 test_verifier_log
 feature
 test_sock
-- 
cgit v1.2.3


From 41ced4cd88020c9d4b71ff7c50d020f081efa4a0 Mon Sep 17 00:00:00 2001
From: Yonghong Song <yhs@fb.com>
Date: Tue, 14 Sep 2021 15:30:09 -0700
Subject: btf: Change BTF_KIND_* macros to enums

Change BTF_KIND_* macros to enums so they are encoded in dwarf and
appear in vmlinux.h. This will make it easier for bpf programs
to use these constants without macro definitions.

Signed-off-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20210914223009.245307-1-yhs@fb.com
---
 tools/include/uapi/linux/btf.h | 41 ++++++++++++++++++++++-------------------
 1 file changed, 22 insertions(+), 19 deletions(-)

(limited to 'tools')

diff --git a/tools/include/uapi/linux/btf.h b/tools/include/uapi/linux/btf.h
index d27b1708efe9..10e401073dd1 100644
--- a/tools/include/uapi/linux/btf.h
+++ b/tools/include/uapi/linux/btf.h
@@ -56,25 +56,28 @@ struct btf_type {
 #define BTF_INFO_VLEN(info)	((info) & 0xffff)
 #define BTF_INFO_KFLAG(info)	((info) >> 31)
 
-#define BTF_KIND_UNKN		0	/* Unknown	*/
-#define BTF_KIND_INT		1	/* Integer	*/
-#define BTF_KIND_PTR		2	/* Pointer	*/
-#define BTF_KIND_ARRAY		3	/* Array	*/
-#define BTF_KIND_STRUCT		4	/* Struct	*/
-#define BTF_KIND_UNION		5	/* Union	*/
-#define BTF_KIND_ENUM		6	/* Enumeration	*/
-#define BTF_KIND_FWD		7	/* Forward	*/
-#define BTF_KIND_TYPEDEF	8	/* Typedef	*/
-#define BTF_KIND_VOLATILE	9	/* Volatile	*/
-#define BTF_KIND_CONST		10	/* Const	*/
-#define BTF_KIND_RESTRICT	11	/* Restrict	*/
-#define BTF_KIND_FUNC		12	/* Function	*/
-#define BTF_KIND_FUNC_PROTO	13	/* Function Proto	*/
-#define BTF_KIND_VAR		14	/* Variable	*/
-#define BTF_KIND_DATASEC	15	/* Section	*/
-#define BTF_KIND_FLOAT		16	/* Floating point	*/
-#define BTF_KIND_MAX		BTF_KIND_FLOAT
-#define NR_BTF_KINDS		(BTF_KIND_MAX + 1)
+enum {
+	BTF_KIND_UNKN		= 0,	/* Unknown	*/
+	BTF_KIND_INT		= 1,	/* Integer	*/
+	BTF_KIND_PTR		= 2,	/* Pointer	*/
+	BTF_KIND_ARRAY		= 3,	/* Array	*/
+	BTF_KIND_STRUCT		= 4,	/* Struct	*/
+	BTF_KIND_UNION		= 5,	/* Union	*/
+	BTF_KIND_ENUM		= 6,	/* Enumeration	*/
+	BTF_KIND_FWD		= 7,	/* Forward	*/
+	BTF_KIND_TYPEDEF	= 8,	/* Typedef	*/
+	BTF_KIND_VOLATILE	= 9,	/* Volatile	*/
+	BTF_KIND_CONST		= 10,	/* Const	*/
+	BTF_KIND_RESTRICT	= 11,	/* Restrict	*/
+	BTF_KIND_FUNC		= 12,	/* Function	*/
+	BTF_KIND_FUNC_PROTO	= 13,	/* Function Proto	*/
+	BTF_KIND_VAR		= 14,	/* Variable	*/
+	BTF_KIND_DATASEC	= 15,	/* Section	*/
+	BTF_KIND_FLOAT		= 16,	/* Floating point	*/
+
+	NR_BTF_KINDS,
+	BTF_KIND_MAX		= NR_BTF_KINDS - 1,
+};
 
 /* For some specific BTF_KIND, "struct btf_type" is immediately
  * followed by extra data.
-- 
cgit v1.2.3


From b5ea834dde6b6e7f75e51d5f66dac8cd7c97b5ef Mon Sep 17 00:00:00 2001
From: Yonghong Song <yhs@fb.com>
Date: Tue, 14 Sep 2021 15:30:15 -0700
Subject: bpf: Support for new btf kind BTF_KIND_TAG

LLVM14 added support for a new C attribute ([1])
  __attribute__((btf_tag("arbitrary_str")))
This attribute will be emitted to dwarf ([2]) and pahole
will convert it to BTF. Or for bpf target, this
attribute will be emitted to BTF directly ([3], [4]).
The attribute is intended to provide additional
information for
  - struct/union type or struct/union member
  - static/global variables
  - static/global function or function parameter.

For linux kernel, the btf_tag can be applied
in various places to specify user pointer,
function pre- or post- condition, function
allow/deny in certain context, etc. Such information
will be encoded in vmlinux BTF and can be used
by verifier.

The btf_tag can also be applied to bpf programs
to help global verifiable functions, e.g.,
specifying preconditions, etc.

This patch added basic parsing and checking support
in kernel for new BTF_KIND_TAG kind.

 [1] https://reviews.llvm.org/D106614
 [2] https://reviews.llvm.org/D106621
 [3] https://reviews.llvm.org/D106622
 [4] https://reviews.llvm.org/D109560

Signed-off-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20210914223015.245546-1-yhs@fb.com
---
 tools/include/uapi/linux/btf.h | 14 +++++++++++++-
 1 file changed, 13 insertions(+), 1 deletion(-)

(limited to 'tools')

diff --git a/tools/include/uapi/linux/btf.h b/tools/include/uapi/linux/btf.h
index 10e401073dd1..642b6ecb37d7 100644
--- a/tools/include/uapi/linux/btf.h
+++ b/tools/include/uapi/linux/btf.h
@@ -43,7 +43,7 @@ struct btf_type {
 	 * "size" tells the size of the type it is describing.
 	 *
 	 * "type" is used by PTR, TYPEDEF, VOLATILE, CONST, RESTRICT,
-	 * FUNC, FUNC_PROTO and VAR.
+	 * FUNC, FUNC_PROTO, VAR and TAG.
 	 * "type" is a type_id referring to another type.
 	 */
 	union {
@@ -74,6 +74,7 @@ enum {
 	BTF_KIND_VAR		= 14,	/* Variable	*/
 	BTF_KIND_DATASEC	= 15,	/* Section	*/
 	BTF_KIND_FLOAT		= 16,	/* Floating point	*/
+	BTF_KIND_TAG		= 17,	/* Tag */
 
 	NR_BTF_KINDS,
 	BTF_KIND_MAX		= NR_BTF_KINDS - 1,
@@ -173,4 +174,15 @@ struct btf_var_secinfo {
 	__u32	size;
 };
 
+/* BTF_KIND_TAG is followed by a single "struct btf_tag" to describe
+ * additional information related to the tag applied location.
+ * If component_idx == -1, the tag is applied to a struct, union,
+ * variable or function. Otherwise, it is applied to a struct/union
+ * member or a func argument, and component_idx indicates which member
+ * or argument (0 ... vlen-1).
+ */
+struct btf_tag {
+       __s32   component_idx;
+};
+
 #endif /* _UAPI__LINUX_BTF_H__ */
-- 
cgit v1.2.3


From 30025e8bd80fdc5a4159ec7f9511121ea561f456 Mon Sep 17 00:00:00 2001
From: Yonghong Song <yhs@fb.com>
Date: Tue, 14 Sep 2021 15:30:20 -0700
Subject: libbpf: Rename btf_{hash,equal}_int to btf_{hash,equal}_int_tag

This patch renames functions btf_{hash,equal}_int() to
btf_{hash,equal}_int_tag() so they can be reused for
BTF_KIND_TAG support. There is no functionality change for
this patch.

Signed-off-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20210914223020.245829-1-yhs@fb.com
---
 tools/lib/bpf/btf.c | 16 ++++++++--------
 1 file changed, 8 insertions(+), 8 deletions(-)

(limited to 'tools')

diff --git a/tools/lib/bpf/btf.c b/tools/lib/bpf/btf.c
index 77dc24d58302..7cb6ebf1be37 100644
--- a/tools/lib/bpf/btf.c
+++ b/tools/lib/bpf/btf.c
@@ -3256,8 +3256,8 @@ static bool btf_equal_common(struct btf_type *t1, struct btf_type *t2)
 	       t1->size == t2->size;
 }
 
-/* Calculate type signature hash of INT. */
-static long btf_hash_int(struct btf_type *t)
+/* Calculate type signature hash of INT or TAG. */
+static long btf_hash_int_tag(struct btf_type *t)
 {
 	__u32 info = *(__u32 *)(t + 1);
 	long h;
@@ -3267,8 +3267,8 @@ static long btf_hash_int(struct btf_type *t)
 	return h;
 }
 
-/* Check structural equality of two INTs. */
-static bool btf_equal_int(struct btf_type *t1, struct btf_type *t2)
+/* Check structural equality of two INTs or TAGs. */
+static bool btf_equal_int_tag(struct btf_type *t1, struct btf_type *t2)
 {
 	__u32 info1, info2;
 
@@ -3535,7 +3535,7 @@ static int btf_dedup_prep(struct btf_dedup *d)
 			h = btf_hash_common(t);
 			break;
 		case BTF_KIND_INT:
-			h = btf_hash_int(t);
+			h = btf_hash_int_tag(t);
 			break;
 		case BTF_KIND_ENUM:
 			h = btf_hash_enum(t);
@@ -3593,11 +3593,11 @@ static int btf_dedup_prim_type(struct btf_dedup *d, __u32 type_id)
 		return 0;
 
 	case BTF_KIND_INT:
-		h = btf_hash_int(t);
+		h = btf_hash_int_tag(t);
 		for_each_dedup_cand(d, hash_entry, h) {
 			cand_id = (__u32)(long)hash_entry->value;
 			cand = btf_type_by_id(d->btf, cand_id);
-			if (btf_equal_int(t, cand)) {
+			if (btf_equal_int_tag(t, cand)) {
 				new_id = cand_id;
 				break;
 			}
@@ -3881,7 +3881,7 @@ static int btf_dedup_is_equiv(struct btf_dedup *d, __u32 cand_id,
 
 	switch (cand_kind) {
 	case BTF_KIND_INT:
-		return btf_equal_int(cand_type, canon_type);
+		return btf_equal_int_tag(cand_type, canon_type);
 
 	case BTF_KIND_ENUM:
 		if (d->opts.dont_resolve_fwds)
-- 
cgit v1.2.3


From 5b84bd10363e36ceb7c4c1ae749a3fc8adf8df45 Mon Sep 17 00:00:00 2001
From: Yonghong Song <yhs@fb.com>
Date: Tue, 14 Sep 2021 15:30:25 -0700
Subject: libbpf: Add support for BTF_KIND_TAG

Add BTF_KIND_TAG support for parsing and dedup.
Also added sanitization for BTF_KIND_TAG. If BTF_KIND_TAG is not
supported in the kernel, sanitize it to INTs.

Signed-off-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20210914223025.246687-1-yhs@fb.com
---
 tools/lib/bpf/btf.c             | 68 +++++++++++++++++++++++++++++++++++++++++
 tools/lib/bpf/btf.h             | 15 +++++++++
 tools/lib/bpf/btf_dump.c        |  3 ++
 tools/lib/bpf/libbpf.c          | 31 +++++++++++++++++--
 tools/lib/bpf/libbpf.map        |  2 ++
 tools/lib/bpf/libbpf_internal.h |  2 ++
 6 files changed, 118 insertions(+), 3 deletions(-)

(limited to 'tools')

diff --git a/tools/lib/bpf/btf.c b/tools/lib/bpf/btf.c
index 7cb6ebf1be37..6ad63e4d418a 100644
--- a/tools/lib/bpf/btf.c
+++ b/tools/lib/bpf/btf.c
@@ -304,6 +304,8 @@ static int btf_type_size(const struct btf_type *t)
 		return base_size + sizeof(struct btf_var);
 	case BTF_KIND_DATASEC:
 		return base_size + vlen * sizeof(struct btf_var_secinfo);
+	case BTF_KIND_TAG:
+		return base_size + sizeof(struct btf_tag);
 	default:
 		pr_debug("Unsupported BTF_KIND:%u\n", btf_kind(t));
 		return -EINVAL;
@@ -376,6 +378,9 @@ static int btf_bswap_type_rest(struct btf_type *t)
 			v->size = bswap_32(v->size);
 		}
 		return 0;
+	case BTF_KIND_TAG:
+		btf_tag(t)->component_idx = bswap_32(btf_tag(t)->component_idx);
+		return 0;
 	default:
 		pr_debug("Unsupported BTF_KIND:%u\n", btf_kind(t));
 		return -EINVAL;
@@ -586,6 +591,7 @@ __s64 btf__resolve_size(const struct btf *btf, __u32 type_id)
 		case BTF_KIND_CONST:
 		case BTF_KIND_RESTRICT:
 		case BTF_KIND_VAR:
+		case BTF_KIND_TAG:
 			type_id = t->type;
 			break;
 		case BTF_KIND_ARRAY:
@@ -2440,6 +2446,48 @@ int btf__add_datasec_var_info(struct btf *btf, int var_type_id, __u32 offset, __
 	return 0;
 }
 
+/*
+ * Append new BTF_KIND_TAG type with:
+ *   - *value* - non-empty/non-NULL string;
+ *   - *ref_type_id* - referenced type ID, it might not exist yet;
+ *   - *component_idx* - -1 for tagging reference type, otherwise struct/union
+ *     member or function argument index;
+ * Returns:
+ *   - >0, type ID of newly added BTF type;
+ *   - <0, on error.
+ */
+int btf__add_tag(struct btf *btf, const char *value, int ref_type_id,
+		 int component_idx)
+{
+	struct btf_type *t;
+	int sz, value_off;
+
+	if (!value || !value[0] || component_idx < -1)
+		return libbpf_err(-EINVAL);
+
+	if (validate_type_id(ref_type_id))
+		return libbpf_err(-EINVAL);
+
+	if (btf_ensure_modifiable(btf))
+		return libbpf_err(-ENOMEM);
+
+	sz = sizeof(struct btf_type) + sizeof(struct btf_tag);
+	t = btf_add_type_mem(btf, sz);
+	if (!t)
+		return libbpf_err(-ENOMEM);
+
+	value_off = btf__add_str(btf, value);
+	if (value_off < 0)
+		return value_off;
+
+	t->name_off = value_off;
+	t->info = btf_type_info(BTF_KIND_TAG, 0, false);
+	t->type = ref_type_id;
+	btf_tag(t)->component_idx = component_idx;
+
+	return btf_commit_type(btf, sz);
+}
+
 struct btf_ext_sec_setup_param {
 	__u32 off;
 	__u32 len;
@@ -3535,6 +3583,7 @@ static int btf_dedup_prep(struct btf_dedup *d)
 			h = btf_hash_common(t);
 			break;
 		case BTF_KIND_INT:
+		case BTF_KIND_TAG:
 			h = btf_hash_int_tag(t);
 			break;
 		case BTF_KIND_ENUM:
@@ -3590,6 +3639,7 @@ static int btf_dedup_prim_type(struct btf_dedup *d, __u32 type_id)
 	case BTF_KIND_FUNC_PROTO:
 	case BTF_KIND_VAR:
 	case BTF_KIND_DATASEC:
+	case BTF_KIND_TAG:
 		return 0;
 
 	case BTF_KIND_INT:
@@ -4210,6 +4260,23 @@ static int btf_dedup_ref_type(struct btf_dedup *d, __u32 type_id)
 		}
 		break;
 
+	case BTF_KIND_TAG:
+		ref_type_id = btf_dedup_ref_type(d, t->type);
+		if (ref_type_id < 0)
+			return ref_type_id;
+		t->type = ref_type_id;
+
+		h = btf_hash_int_tag(t);
+		for_each_dedup_cand(d, hash_entry, h) {
+			cand_id = (__u32)(long)hash_entry->value;
+			cand = btf_type_by_id(d->btf, cand_id);
+			if (btf_equal_int_tag(t, cand)) {
+				new_id = cand_id;
+				break;
+			}
+		}
+		break;
+
 	case BTF_KIND_ARRAY: {
 		struct btf_array *info = btf_array(t);
 
@@ -4482,6 +4549,7 @@ int btf_type_visit_type_ids(struct btf_type *t, type_id_visit_fn visit, void *ct
 	case BTF_KIND_TYPEDEF:
 	case BTF_KIND_FUNC:
 	case BTF_KIND_VAR:
+	case BTF_KIND_TAG:
 		return visit(&t->type, ctx);
 
 	case BTF_KIND_ARRAY: {
diff --git a/tools/lib/bpf/btf.h b/tools/lib/bpf/btf.h
index f2e2fab950b7..659ea8a2769b 100644
--- a/tools/lib/bpf/btf.h
+++ b/tools/lib/bpf/btf.h
@@ -143,6 +143,10 @@ LIBBPF_API int btf__add_datasec(struct btf *btf, const char *name, __u32 byte_sz
 LIBBPF_API int btf__add_datasec_var_info(struct btf *btf, int var_type_id,
 					 __u32 offset, __u32 byte_sz);
 
+/* tag construction API */
+LIBBPF_API int btf__add_tag(struct btf *btf, const char *value, int ref_type_id,
+			    int component_idx);
+
 struct btf_dedup_opts {
 	unsigned int dedup_table_size;
 	bool dont_resolve_fwds;
@@ -330,6 +334,11 @@ static inline bool btf_is_float(const struct btf_type *t)
 	return btf_kind(t) == BTF_KIND_FLOAT;
 }
 
+static inline bool btf_is_tag(const struct btf_type *t)
+{
+	return btf_kind(t) == BTF_KIND_TAG;
+}
+
 static inline __u8 btf_int_encoding(const struct btf_type *t)
 {
 	return BTF_INT_ENCODING(*(__u32 *)(t + 1));
@@ -398,6 +407,12 @@ btf_var_secinfos(const struct btf_type *t)
 	return (struct btf_var_secinfo *)(t + 1);
 }
 
+struct btf_tag;
+static inline struct btf_tag *btf_tag(const struct btf_type *t)
+{
+	return (struct btf_tag *)(t + 1);
+}
+
 #ifdef __cplusplus
 } /* extern "C" */
 #endif
diff --git a/tools/lib/bpf/btf_dump.c b/tools/lib/bpf/btf_dump.c
index e4b483f15fb9..ad6df97295ae 100644
--- a/tools/lib/bpf/btf_dump.c
+++ b/tools/lib/bpf/btf_dump.c
@@ -316,6 +316,7 @@ static int btf_dump_mark_referenced(struct btf_dump *d)
 		case BTF_KIND_TYPEDEF:
 		case BTF_KIND_FUNC:
 		case BTF_KIND_VAR:
+		case BTF_KIND_TAG:
 			d->type_states[t->type].referenced = 1;
 			break;
 
@@ -583,6 +584,7 @@ static int btf_dump_order_type(struct btf_dump *d, __u32 id, bool through_ptr)
 	case BTF_KIND_FUNC:
 	case BTF_KIND_VAR:
 	case BTF_KIND_DATASEC:
+	case BTF_KIND_TAG:
 		d->type_states[id].order_state = ORDERED;
 		return 0;
 
@@ -2215,6 +2217,7 @@ static int btf_dump_dump_type_data(struct btf_dump *d,
 	case BTF_KIND_FWD:
 	case BTF_KIND_FUNC:
 	case BTF_KIND_FUNC_PROTO:
+	case BTF_KIND_TAG:
 		err = btf_dump_unsupported_data(d, t, id);
 		break;
 	case BTF_KIND_INT:
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 62ed073ea944..62a43c408d73 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -195,6 +195,8 @@ enum kern_feature_id {
 	FEAT_BTF_FLOAT,
 	/* BPF perf link support */
 	FEAT_PERF_LINK,
+	/* BTF_KIND_TAG support */
+	FEAT_BTF_TAG,
 	__FEAT_CNT,
 };
 
@@ -1986,6 +1988,7 @@ static const char *__btf_kind_str(__u16 kind)
 	case BTF_KIND_VAR: return "var";
 	case BTF_KIND_DATASEC: return "datasec";
 	case BTF_KIND_FLOAT: return "float";
+	case BTF_KIND_TAG: return "tag";
 	default: return "unknown";
 	}
 }
@@ -2485,8 +2488,9 @@ static bool btf_needs_sanitization(struct bpf_object *obj)
 	bool has_datasec = kernel_supports(obj, FEAT_BTF_DATASEC);
 	bool has_float = kernel_supports(obj, FEAT_BTF_FLOAT);
 	bool has_func = kernel_supports(obj, FEAT_BTF_FUNC);
+	bool has_tag = kernel_supports(obj, FEAT_BTF_TAG);
 
-	return !has_func || !has_datasec || !has_func_global || !has_float;
+	return !has_func || !has_datasec || !has_func_global || !has_float || !has_tag;
 }
 
 static void bpf_object__sanitize_btf(struct bpf_object *obj, struct btf *btf)
@@ -2495,14 +2499,15 @@ static void bpf_object__sanitize_btf(struct bpf_object *obj, struct btf *btf)
 	bool has_datasec = kernel_supports(obj, FEAT_BTF_DATASEC);
 	bool has_float = kernel_supports(obj, FEAT_BTF_FLOAT);
 	bool has_func = kernel_supports(obj, FEAT_BTF_FUNC);
+	bool has_tag = kernel_supports(obj, FEAT_BTF_TAG);
 	struct btf_type *t;
 	int i, j, vlen;
 
 	for (i = 1; i <= btf__get_nr_types(btf); i++) {
 		t = (struct btf_type *)btf__type_by_id(btf, i);
 
-		if (!has_datasec && btf_is_var(t)) {
-			/* replace VAR with INT */
+		if ((!has_datasec && btf_is_var(t)) || (!has_tag && btf_is_tag(t))) {
+			/* replace VAR/TAG with INT */
 			t->info = BTF_INFO_ENC(BTF_KIND_INT, 0, 0);
 			/*
 			 * using size = 1 is the safest choice, 4 will be too
@@ -4212,6 +4217,23 @@ static int probe_kern_btf_float(void)
 					     strs, sizeof(strs)));
 }
 
+static int probe_kern_btf_tag(void)
+{
+	static const char strs[] = "\0tag";
+	__u32 types[] = {
+		/* int */
+		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),  /* [1] */
+		/* VAR x */                                     /* [2] */
+		BTF_TYPE_ENC(1, BTF_INFO_ENC(BTF_KIND_VAR, 0, 0), 1),
+		BTF_VAR_STATIC,
+		/* attr */
+		BTF_TYPE_TAG_ENC(1, 2, -1),
+	};
+
+	return probe_fd(libbpf__load_raw_btf((char *)types, sizeof(types),
+					     strs, sizeof(strs)));
+}
+
 static int probe_kern_array_mmap(void)
 {
 	struct bpf_create_map_attr attr = {
@@ -4428,6 +4450,9 @@ static struct kern_feature_desc {
 	[FEAT_PERF_LINK] = {
 		"BPF perf link support", probe_perf_link,
 	},
+	[FEAT_BTF_TAG] = {
+		"BTF_KIND_TAG support", probe_kern_btf_tag,
+	},
 };
 
 static bool kernel_supports(const struct bpf_object *obj, enum kern_feature_id feat_id)
diff --git a/tools/lib/bpf/libbpf.map b/tools/lib/bpf/libbpf.map
index 78ea62c9346f..9e649cf9e771 100644
--- a/tools/lib/bpf/libbpf.map
+++ b/tools/lib/bpf/libbpf.map
@@ -388,4 +388,6 @@ LIBBPF_0.5.0 {
 } LIBBPF_0.4.0;
 
 LIBBPF_0.6.0 {
+	global:
+		btf__add_tag;
 } LIBBPF_0.5.0;
diff --git a/tools/lib/bpf/libbpf_internal.h b/tools/lib/bpf/libbpf_internal.h
index 4f6ff5c23695..ceb0c98979bc 100644
--- a/tools/lib/bpf/libbpf_internal.h
+++ b/tools/lib/bpf/libbpf_internal.h
@@ -69,6 +69,8 @@
 #define BTF_VAR_SECINFO_ENC(type, offset, size) (type), (offset), (size)
 #define BTF_TYPE_FLOAT_ENC(name, sz) \
 	BTF_TYPE_ENC(name, BTF_INFO_ENC(BTF_KIND_FLOAT, 0, 0), sz)
+#define BTF_TYPE_TAG_ENC(value, type, component_idx) \
+	BTF_TYPE_ENC(value, BTF_INFO_ENC(BTF_KIND_TAG, 0, 0), type), (component_idx)
 
 #ifndef likely
 #define likely(x) __builtin_expect(!!(x), 1)
-- 
cgit v1.2.3


From 5c07f2fec00361fb5e8cff8ba7fdede7b29f38bd Mon Sep 17 00:00:00 2001
From: Yonghong Song <yhs@fb.com>
Date: Tue, 14 Sep 2021 15:30:31 -0700
Subject: bpftool: Add support for BTF_KIND_TAG

Added bpftool support to dump BTF_KIND_TAG information.
The new bpftool will be used in later patches to dump
btf in the test bpf program object file.

Currently, the tags are not emitted with
  bpftool btf dump file <path> format c
and they are silently ignored.  The tag information is
mostly used in the kernel for verification purpose and the kernel
uses its own btf to check. With adding these tags
to vmlinux.h, tags will be encoded in program's btf but
they will not be used by the kernel, at least for now.
So let us delay adding these tags to format C header files
until there is a real need.

Signed-off-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20210914223031.246951-1-yhs@fb.com
---
 tools/bpf/bpftool/btf.c | 12 ++++++++++++
 1 file changed, 12 insertions(+)

(limited to 'tools')

diff --git a/tools/bpf/bpftool/btf.c b/tools/bpf/bpftool/btf.c
index f7e5ff3586c9..49743ad96851 100644
--- a/tools/bpf/bpftool/btf.c
+++ b/tools/bpf/bpftool/btf.c
@@ -37,6 +37,7 @@ static const char * const btf_kind_str[NR_BTF_KINDS] = {
 	[BTF_KIND_VAR]		= "VAR",
 	[BTF_KIND_DATASEC]	= "DATASEC",
 	[BTF_KIND_FLOAT]	= "FLOAT",
+	[BTF_KIND_TAG]		= "TAG",
 };
 
 struct btf_attach_table {
@@ -347,6 +348,17 @@ static int dump_btf_type(const struct btf *btf, __u32 id,
 			printf(" size=%u", t->size);
 		break;
 	}
+	case BTF_KIND_TAG: {
+		const struct btf_tag *tag = (const void *)(t + 1);
+
+		if (json_output) {
+			jsonw_uint_field(w, "type_id", t->type);
+			jsonw_int_field(w, "component_idx", tag->component_idx);
+		} else {
+			printf(" type_id=%u component_idx=%d", t->type, tag->component_idx);
+		}
+		break;
+	}
 	default:
 		break;
 	}
-- 
cgit v1.2.3


From 71d29c2d47d112404fe23e31cf33f7cccde75a8c Mon Sep 17 00:00:00 2001
From: Yonghong Song <yhs@fb.com>
Date: Tue, 14 Sep 2021 15:30:36 -0700
Subject: selftests/bpf: Test libbpf API function btf__add_tag()

Add btf_write tests with btf__add_tag() function.

Signed-off-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20210914223036.247560-1-yhs@fb.com
---
 tools/testing/selftests/bpf/btf_helpers.c          |  7 ++++++-
 tools/testing/selftests/bpf/prog_tests/btf_write.c | 21 +++++++++++++++++++++
 2 files changed, 27 insertions(+), 1 deletion(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/btf_helpers.c b/tools/testing/selftests/bpf/btf_helpers.c
index b692e6ead9b5..ce103fb0ad1b 100644
--- a/tools/testing/selftests/bpf/btf_helpers.c
+++ b/tools/testing/selftests/bpf/btf_helpers.c
@@ -24,11 +24,12 @@ static const char * const btf_kind_str_mapping[] = {
 	[BTF_KIND_VAR]		= "VAR",
 	[BTF_KIND_DATASEC]	= "DATASEC",
 	[BTF_KIND_FLOAT]	= "FLOAT",
+	[BTF_KIND_TAG]		= "TAG",
 };
 
 static const char *btf_kind_str(__u16 kind)
 {
-	if (kind > BTF_KIND_DATASEC)
+	if (kind > BTF_KIND_TAG)
 		return "UNKNOWN";
 	return btf_kind_str_mapping[kind];
 }
@@ -177,6 +178,10 @@ int fprintf_btf_type_raw(FILE *out, const struct btf *btf, __u32 id)
 	case BTF_KIND_FLOAT:
 		fprintf(out, " size=%u", t->size);
 		break;
+	case BTF_KIND_TAG:
+		fprintf(out, " type_id=%u component_idx=%d",
+			t->type, btf_tag(t)->component_idx);
+		break;
 	default:
 		break;
 	}
diff --git a/tools/testing/selftests/bpf/prog_tests/btf_write.c b/tools/testing/selftests/bpf/prog_tests/btf_write.c
index 022c7d89d6f4..76548eecce2c 100644
--- a/tools/testing/selftests/bpf/prog_tests/btf_write.c
+++ b/tools/testing/selftests/bpf/prog_tests/btf_write.c
@@ -281,5 +281,26 @@ void test_btf_write() {
 		     "[17] DATASEC 'datasec1' size=12 vlen=1\n"
 		     "\ttype_id=1 offset=4 size=8", "raw_dump");
 
+	/* TAG */
+	id = btf__add_tag(btf, "tag1", 16, -1);
+	ASSERT_EQ(id, 18, "tag_id");
+	t = btf__type_by_id(btf, 18);
+	ASSERT_STREQ(btf__str_by_offset(btf, t->name_off), "tag1", "tag_value");
+	ASSERT_EQ(btf_kind(t), BTF_KIND_TAG, "tag_kind");
+	ASSERT_EQ(t->type, 16, "tag_type");
+	ASSERT_EQ(btf_tag(t)->component_idx, -1, "tag_component_idx");
+	ASSERT_STREQ(btf_type_raw_dump(btf, 18),
+		     "[18] TAG 'tag1' type_id=16 component_idx=-1", "raw_dump");
+
+	id = btf__add_tag(btf, "tag2", 14, 1);
+	ASSERT_EQ(id, 19, "tag_id");
+	t = btf__type_by_id(btf, 19);
+	ASSERT_STREQ(btf__str_by_offset(btf, t->name_off), "tag2", "tag_value");
+	ASSERT_EQ(btf_kind(t), BTF_KIND_TAG, "tag_kind");
+	ASSERT_EQ(t->type, 14, "tag_type");
+	ASSERT_EQ(btf_tag(t)->component_idx, 1, "tag_component_idx");
+	ASSERT_STREQ(btf_type_raw_dump(btf, 19),
+		     "[19] TAG 'tag2' type_id=14 component_idx=1", "raw_dump");
+
 	btf__free(btf);
 }
-- 
cgit v1.2.3


From 3df3bd68d4811bccc74adc04d4d84512957a1a07 Mon Sep 17 00:00:00 2001
From: Yonghong Song <yhs@fb.com>
Date: Tue, 14 Sep 2021 15:30:41 -0700
Subject: selftests/bpf: Change NAME_NTH/IS_NAME_NTH for BTF_KIND_TAG format

BTF_KIND_TAG ELF format has a component_idx which might have value -1.
test_btf may confuse it with common_type.name as NAME_NTH checkes
high 16bit to be 0xffff. Change NAME_NTH high 16bit check to be
0xfffe so it won't confuse with component_idx.

Signed-off-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20210914223041.248009-1-yhs@fb.com
---
 tools/testing/selftests/bpf/prog_tests/btf.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/prog_tests/btf.c b/tools/testing/selftests/bpf/prog_tests/btf.c
index 649f87382c8d..ad39f4d588d0 100644
--- a/tools/testing/selftests/bpf/prog_tests/btf.c
+++ b/tools/testing/selftests/bpf/prog_tests/btf.c
@@ -39,8 +39,8 @@ static bool always_log;
 #define BTF_END_RAW 0xdeadbeef
 #define NAME_TBD 0xdeadb33f
 
-#define NAME_NTH(N) (0xffff0000 | N)
-#define IS_NAME_NTH(X) ((X & 0xffff0000) == 0xffff0000)
+#define NAME_NTH(N) (0xfffe0000 | N)
+#define IS_NAME_NTH(X) ((X & 0xffff0000) == 0xfffe0000)
 #define GET_NAME_NTH_IDX(X) (X & 0x0000ffff)
 
 #define MAX_NR_RAW_U32 1024
-- 
cgit v1.2.3


From 35baba7a832fa466b4aa2e0d00473d795cec8f20 Mon Sep 17 00:00:00 2001
From: Yonghong Song <yhs@fb.com>
Date: Tue, 14 Sep 2021 15:30:47 -0700
Subject: selftests/bpf: Add BTF_KIND_TAG unit tests

Test good and bad variants of BTF_KIND_TAG encoding.

Signed-off-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20210914223047.248223-1-yhs@fb.com
---
 tools/testing/selftests/bpf/prog_tests/btf.c | 245 +++++++++++++++++++++++++++
 tools/testing/selftests/bpf/test_btf.h       |   3 +
 2 files changed, 248 insertions(+)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/prog_tests/btf.c b/tools/testing/selftests/bpf/prog_tests/btf.c
index ad39f4d588d0..b4e86a8423cb 100644
--- a/tools/testing/selftests/bpf/prog_tests/btf.c
+++ b/tools/testing/selftests/bpf/prog_tests/btf.c
@@ -3661,6 +3661,249 @@ static struct btf_raw_test raw_tests[] = {
 	.err_str = "Invalid type_size",
 },
 
+{
+	.descr = "tag test #1, struct/member, well-formed",
+	.raw_types = {
+		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),	/* [1] */
+		BTF_STRUCT_ENC(0, 2, 8),			/* [2] */
+		BTF_MEMBER_ENC(NAME_TBD, 1, 0),
+		BTF_MEMBER_ENC(NAME_TBD, 1, 32),
+		BTF_TAG_ENC(NAME_TBD, 2, -1),
+		BTF_TAG_ENC(NAME_TBD, 2, 0),
+		BTF_TAG_ENC(NAME_TBD, 2, 1),
+		BTF_END_RAW,
+	},
+	BTF_STR_SEC("\0m1\0m2\0tag1\0tag2\0tag3"),
+	.map_type = BPF_MAP_TYPE_ARRAY,
+	.map_name = "tag_type_check_btf",
+	.key_size = sizeof(int),
+	.value_size = 8,
+	.key_type_id = 1,
+	.value_type_id = 2,
+	.max_entries = 1,
+},
+{
+	.descr = "tag test #2, union/member, well-formed",
+	.raw_types = {
+		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),	/* [1] */
+		BTF_UNION_ENC(NAME_TBD, 2, 4),			/* [2] */
+		BTF_MEMBER_ENC(NAME_TBD, 1, 0),
+		BTF_MEMBER_ENC(NAME_TBD, 1, 0),
+		BTF_TAG_ENC(NAME_TBD, 2, -1),
+		BTF_TAG_ENC(NAME_TBD, 2, 0),
+		BTF_TAG_ENC(NAME_TBD, 2, 1),
+		BTF_END_RAW,
+	},
+	BTF_STR_SEC("\0t\0m1\0m2\0tag1\0tag2\0tag3"),
+	.map_type = BPF_MAP_TYPE_ARRAY,
+	.map_name = "tag_type_check_btf",
+	.key_size = sizeof(int),
+	.value_size = 4,
+	.key_type_id = 1,
+	.value_type_id = 2,
+	.max_entries = 1,
+},
+{
+	.descr = "tag test #3, variable, well-formed",
+	.raw_types = {
+		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),	/* [1] */
+		BTF_VAR_ENC(NAME_TBD, 1, 0),			/* [2] */
+		BTF_VAR_ENC(NAME_TBD, 1, 1),			/* [3] */
+		BTF_TAG_ENC(NAME_TBD, 2, -1),
+		BTF_TAG_ENC(NAME_TBD, 3, -1),
+		BTF_END_RAW,
+	},
+	BTF_STR_SEC("\0local\0global\0tag1\0tag2"),
+	.map_type = BPF_MAP_TYPE_ARRAY,
+	.map_name = "tag_type_check_btf",
+	.key_size = sizeof(int),
+	.value_size = 4,
+	.key_type_id = 1,
+	.value_type_id = 1,
+	.max_entries = 1,
+},
+{
+	.descr = "tag test #4, func/parameter, well-formed",
+	.raw_types = {
+		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),	/* [1] */
+		BTF_FUNC_PROTO_ENC(0, 2),			/* [2] */
+			BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 1),
+			BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 1),
+		BTF_FUNC_ENC(NAME_TBD, 2),			/* [3] */
+		BTF_TAG_ENC(NAME_TBD, 3, -1),
+		BTF_TAG_ENC(NAME_TBD, 3, 0),
+		BTF_TAG_ENC(NAME_TBD, 3, 1),
+		BTF_END_RAW,
+	},
+	BTF_STR_SEC("\0arg1\0arg2\0f\0tag1\0tag2\0tag3"),
+	.map_type = BPF_MAP_TYPE_ARRAY,
+	.map_name = "tag_type_check_btf",
+	.key_size = sizeof(int),
+	.value_size = 4,
+	.key_type_id = 1,
+	.value_type_id = 1,
+	.max_entries = 1,
+},
+{
+	.descr = "tag test #5, invalid value",
+	.raw_types = {
+		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),	/* [1] */
+		BTF_VAR_ENC(NAME_TBD, 1, 0),			/* [2] */
+		BTF_TAG_ENC(0, 2, -1),
+		BTF_END_RAW,
+	},
+	BTF_STR_SEC("\0local\0tag"),
+	.map_type = BPF_MAP_TYPE_ARRAY,
+	.map_name = "tag_type_check_btf",
+	.key_size = sizeof(int),
+	.value_size = 4,
+	.key_type_id = 1,
+	.value_type_id = 1,
+	.max_entries = 1,
+	.btf_load_err = true,
+	.err_str = "Invalid value",
+},
+{
+	.descr = "tag test #6, invalid target type",
+	.raw_types = {
+		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),	/* [1] */
+		BTF_TAG_ENC(NAME_TBD, 1, -1),
+		BTF_END_RAW,
+	},
+	BTF_STR_SEC("\0tag1"),
+	.map_type = BPF_MAP_TYPE_ARRAY,
+	.map_name = "tag_type_check_btf",
+	.key_size = sizeof(int),
+	.value_size = 4,
+	.key_type_id = 1,
+	.value_type_id = 1,
+	.max_entries = 1,
+	.btf_load_err = true,
+	.err_str = "Invalid type",
+},
+{
+	.descr = "tag test #7, invalid vlen",
+	.raw_types = {
+		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),	/* [1] */
+		BTF_VAR_ENC(NAME_TBD, 1, 0),			/* [2] */
+		BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_TAG, 0, 1), 2), (0),
+		BTF_END_RAW,
+	},
+	BTF_STR_SEC("\0local\0tag1"),
+	.map_type = BPF_MAP_TYPE_ARRAY,
+	.map_name = "tag_type_check_btf",
+	.key_size = sizeof(int),
+	.value_size = 4,
+	.key_type_id = 1,
+	.value_type_id = 1,
+	.max_entries = 1,
+	.btf_load_err = true,
+	.err_str = "vlen != 0",
+},
+{
+	.descr = "tag test #8, invalid kflag",
+	.raw_types = {
+		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),	/* [1] */
+		BTF_VAR_ENC(NAME_TBD, 1, 0),			/* [2] */
+		BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_TAG, 1, 0), 2), (-1),
+		BTF_END_RAW,
+	},
+	BTF_STR_SEC("\0local\0tag1"),
+	.map_type = BPF_MAP_TYPE_ARRAY,
+	.map_name = "tag_type_check_btf",
+	.key_size = sizeof(int),
+	.value_size = 4,
+	.key_type_id = 1,
+	.value_type_id = 1,
+	.max_entries = 1,
+	.btf_load_err = true,
+	.err_str = "Invalid btf_info kind_flag",
+},
+{
+	.descr = "tag test #9, var, invalid component_idx",
+	.raw_types = {
+		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),	/* [1] */
+		BTF_VAR_ENC(NAME_TBD, 1, 0),			/* [2] */
+		BTF_TAG_ENC(NAME_TBD, 2, 0),
+		BTF_END_RAW,
+	},
+	BTF_STR_SEC("\0local\0tag"),
+	.map_type = BPF_MAP_TYPE_ARRAY,
+	.map_name = "tag_type_check_btf",
+	.key_size = sizeof(int),
+	.value_size = 4,
+	.key_type_id = 1,
+	.value_type_id = 1,
+	.max_entries = 1,
+	.btf_load_err = true,
+	.err_str = "Invalid component_idx",
+},
+{
+	.descr = "tag test #10, struct member, invalid component_idx",
+	.raw_types = {
+		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),	/* [1] */
+		BTF_STRUCT_ENC(0, 2, 8),			/* [2] */
+		BTF_MEMBER_ENC(NAME_TBD, 1, 0),
+		BTF_MEMBER_ENC(NAME_TBD, 1, 32),
+		BTF_TAG_ENC(NAME_TBD, 2, 2),
+		BTF_END_RAW,
+	},
+	BTF_STR_SEC("\0m1\0m2\0tag"),
+	.map_type = BPF_MAP_TYPE_ARRAY,
+	.map_name = "tag_type_check_btf",
+	.key_size = sizeof(int),
+	.value_size = 8,
+	.key_type_id = 1,
+	.value_type_id = 2,
+	.max_entries = 1,
+	.btf_load_err = true,
+	.err_str = "Invalid component_idx",
+},
+{
+	.descr = "tag test #11, func parameter, invalid component_idx",
+	.raw_types = {
+		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),	/* [1] */
+		BTF_FUNC_PROTO_ENC(0, 2),			/* [2] */
+			BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 1),
+			BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 1),
+		BTF_FUNC_ENC(NAME_TBD, 2),			/* [3] */
+		BTF_TAG_ENC(NAME_TBD, 3, 2),
+		BTF_END_RAW,
+	},
+	BTF_STR_SEC("\0arg1\0arg2\0f\0tag"),
+	.map_type = BPF_MAP_TYPE_ARRAY,
+	.map_name = "tag_type_check_btf",
+	.key_size = sizeof(int),
+	.value_size = 4,
+	.key_type_id = 1,
+	.value_type_id = 1,
+	.max_entries = 1,
+	.btf_load_err = true,
+	.err_str = "Invalid component_idx",
+},
+{
+	.descr = "tag test #12, < -1 component_idx",
+	.raw_types = {
+		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),	/* [1] */
+		BTF_FUNC_PROTO_ENC(0, 2),			/* [2] */
+			BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 1),
+			BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 1),
+		BTF_FUNC_ENC(NAME_TBD, 2),			/* [3] */
+		BTF_TAG_ENC(NAME_TBD, 3, -2),
+		BTF_END_RAW,
+	},
+	BTF_STR_SEC("\0arg1\0arg2\0f\0tag"),
+	.map_type = BPF_MAP_TYPE_ARRAY,
+	.map_name = "tag_type_check_btf",
+	.key_size = sizeof(int),
+	.value_size = 4,
+	.key_type_id = 1,
+	.value_type_id = 1,
+	.max_entries = 1,
+	.btf_load_err = true,
+	.err_str = "Invalid component_idx",
+},
+
 }; /* struct btf_raw_test raw_tests[] */
 
 static const char *get_next_str(const char *start, const char *end)
@@ -6801,6 +7044,8 @@ static int btf_type_size(const struct btf_type *t)
 		return base_size + sizeof(struct btf_var);
 	case BTF_KIND_DATASEC:
 		return base_size + vlen * sizeof(struct btf_var_secinfo);
+	case BTF_KIND_TAG:
+		return base_size + sizeof(struct btf_tag);
 	default:
 		fprintf(stderr, "Unsupported BTF_KIND:%u\n", kind);
 		return -EINVAL;
diff --git a/tools/testing/selftests/bpf/test_btf.h b/tools/testing/selftests/bpf/test_btf.h
index e2394eea4b7f..0619e06d745e 100644
--- a/tools/testing/selftests/bpf/test_btf.h
+++ b/tools/testing/selftests/bpf/test_btf.h
@@ -69,4 +69,7 @@
 #define BTF_TYPE_FLOAT_ENC(name, sz) \
 	BTF_TYPE_ENC(name, BTF_INFO_ENC(BTF_KIND_FLOAT, 0, 0), sz)
 
+#define BTF_TAG_ENC(value, type, component_idx)	\
+	BTF_TYPE_ENC(value, BTF_INFO_ENC(BTF_KIND_TAG, 0, 0), type), (component_idx)
+
 #endif /* _TEST_BTF_H */
-- 
cgit v1.2.3


From ad526474aec1d9abb9838e3fb1330bb991715c22 Mon Sep 17 00:00:00 2001
From: Yonghong Song <yhs@fb.com>
Date: Tue, 14 Sep 2021 15:30:52 -0700
Subject: selftests/bpf: Test BTF_KIND_TAG for deduplication

Add unit tests for BTF_KIND_TAG deduplication for
  - struct and struct member
  - variable
  - func and func argument

Signed-off-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20210914223052.248535-1-yhs@fb.com
---
 tools/testing/selftests/bpf/prog_tests/btf.c | 192 ++++++++++++++++++++++++---
 1 file changed, 175 insertions(+), 17 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/prog_tests/btf.c b/tools/testing/selftests/bpf/prog_tests/btf.c
index b4e86a8423cb..9c85d7d27409 100644
--- a/tools/testing/selftests/bpf/prog_tests/btf.c
+++ b/tools/testing/selftests/bpf/prog_tests/btf.c
@@ -6664,27 +6664,33 @@ const struct btf_dedup_test dedup_tests[] = {
 				BTF_MEMBER_ENC(NAME_NTH(4), 5, 64),	/* const int *a;	*/
 				BTF_MEMBER_ENC(NAME_NTH(5), 2, 128),	/* int b[16];		*/
 				BTF_MEMBER_ENC(NAME_NTH(6), 1, 640),	/* int c;		*/
-				BTF_MEMBER_ENC(NAME_NTH(8), 13, 672),	/* float d;		*/
+				BTF_MEMBER_ENC(NAME_NTH(8), 15, 672),	/* float d;		*/
 			/* ptr -> [3] struct s */
 			BTF_PTR_ENC(3),							/* [4] */
 			/* ptr -> [6] const int */
 			BTF_PTR_ENC(6),							/* [5] */
 			/* const -> [1] int */
 			BTF_CONST_ENC(1),						/* [6] */
+			/* tag -> [3] struct s */
+			BTF_TAG_ENC(NAME_NTH(2), 3, -1),				/* [7] */
+			/* tag -> [3] struct s, member 1 */
+			BTF_TAG_ENC(NAME_NTH(2), 3, 1),					/* [8] */
 
 			/* full copy of the above */
-			BTF_TYPE_INT_ENC(NAME_NTH(1), BTF_INT_SIGNED, 0, 32, 4),	/* [7] */
-			BTF_TYPE_ARRAY_ENC(7, 7, 16),					/* [8] */
-			BTF_STRUCT_ENC(NAME_NTH(2), 5, 88),				/* [9] */
-				BTF_MEMBER_ENC(NAME_NTH(3), 10, 0),
-				BTF_MEMBER_ENC(NAME_NTH(4), 11, 64),
-				BTF_MEMBER_ENC(NAME_NTH(5), 8, 128),
-				BTF_MEMBER_ENC(NAME_NTH(6), 7, 640),
-				BTF_MEMBER_ENC(NAME_NTH(8), 13, 672),
-			BTF_PTR_ENC(9),							/* [10] */
-			BTF_PTR_ENC(12),						/* [11] */
-			BTF_CONST_ENC(7),						/* [12] */
-			BTF_TYPE_FLOAT_ENC(NAME_NTH(7), 4),				/* [13] */
+			BTF_TYPE_INT_ENC(NAME_NTH(1), BTF_INT_SIGNED, 0, 32, 4),	/* [9] */
+			BTF_TYPE_ARRAY_ENC(9, 9, 16),					/* [10] */
+			BTF_STRUCT_ENC(NAME_NTH(2), 5, 88),				/* [11] */
+				BTF_MEMBER_ENC(NAME_NTH(3), 12, 0),
+				BTF_MEMBER_ENC(NAME_NTH(4), 13, 64),
+				BTF_MEMBER_ENC(NAME_NTH(5), 10, 128),
+				BTF_MEMBER_ENC(NAME_NTH(6), 9, 640),
+				BTF_MEMBER_ENC(NAME_NTH(8), 15, 672),
+			BTF_PTR_ENC(11),						/* [12] */
+			BTF_PTR_ENC(14),						/* [13] */
+			BTF_CONST_ENC(9),						/* [14] */
+			BTF_TYPE_FLOAT_ENC(NAME_NTH(7), 4),				/* [15] */
+			BTF_TAG_ENC(NAME_NTH(2), 11, -1),				/* [16] */
+			BTF_TAG_ENC(NAME_NTH(2), 11, 1),				/* [17] */
 			BTF_END_RAW,
 		},
 		BTF_STR_SEC("\0int\0s\0next\0a\0b\0c\0float\0d"),
@@ -6701,14 +6707,16 @@ const struct btf_dedup_test dedup_tests[] = {
 				BTF_MEMBER_ENC(NAME_NTH(1), 5, 64),	/* const int *a;	*/
 				BTF_MEMBER_ENC(NAME_NTH(2), 2, 128),	/* int b[16];		*/
 				BTF_MEMBER_ENC(NAME_NTH(3), 1, 640),	/* int c;		*/
-				BTF_MEMBER_ENC(NAME_NTH(4), 7, 672),	/* float d;		*/
+				BTF_MEMBER_ENC(NAME_NTH(4), 9, 672),	/* float d;		*/
 			/* ptr -> [3] struct s */
 			BTF_PTR_ENC(3),							/* [4] */
 			/* ptr -> [6] const int */
 			BTF_PTR_ENC(6),							/* [5] */
 			/* const -> [1] int */
 			BTF_CONST_ENC(1),						/* [6] */
-			BTF_TYPE_FLOAT_ENC(NAME_NTH(7), 4),				/* [7] */
+			BTF_TAG_ENC(NAME_NTH(2), 3, -1),				/* [7] */
+			BTF_TAG_ENC(NAME_NTH(2), 3, 1),					/* [8] */
+			BTF_TYPE_FLOAT_ENC(NAME_NTH(7), 4),				/* [9] */
 			BTF_END_RAW,
 		},
 		BTF_STR_SEC("\0a\0b\0c\0d\0int\0float\0next\0s"),
@@ -6833,9 +6841,11 @@ const struct btf_dedup_test dedup_tests[] = {
 				BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 8),
 			BTF_FUNC_ENC(NAME_TBD, 12),					/* [13] func */
 			BTF_TYPE_FLOAT_ENC(NAME_TBD, 2),				/* [14] float */
+			BTF_TAG_ENC(NAME_TBD, 13, -1),					/* [15] tag */
+			BTF_TAG_ENC(NAME_TBD, 13, 1),					/* [16] tag */
 			BTF_END_RAW,
 		},
-		BTF_STR_SEC("\0A\0B\0C\0D\0E\0F\0G\0H\0I\0J\0K\0L\0M\0N"),
+		BTF_STR_SEC("\0A\0B\0C\0D\0E\0F\0G\0H\0I\0J\0K\0L\0M\0N\0O\0P"),
 	},
 	.expect = {
 		.raw_types = {
@@ -6859,9 +6869,11 @@ const struct btf_dedup_test dedup_tests[] = {
 				BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 8),
 			BTF_FUNC_ENC(NAME_TBD, 12),					/* [13] func */
 			BTF_TYPE_FLOAT_ENC(NAME_TBD, 2),				/* [14] float */
+			BTF_TAG_ENC(NAME_TBD, 13, -1),					/* [15] tag */
+			BTF_TAG_ENC(NAME_TBD, 13, 1),					/* [16] tag */
 			BTF_END_RAW,
 		},
-		BTF_STR_SEC("\0A\0B\0C\0D\0E\0F\0G\0H\0I\0J\0K\0L\0M\0N"),
+		BTF_STR_SEC("\0A\0B\0C\0D\0E\0F\0G\0H\0I\0J\0K\0L\0M\0N\0O\0P"),
 	},
 	.opts = {
 		.dont_resolve_fwds = false,
@@ -7010,6 +7022,152 @@ const struct btf_dedup_test dedup_tests[] = {
 		.dedup_table_size = 1
 	},
 },
+{
+	.descr = "dedup: func/func_arg/var tags",
+	.input = {
+		.raw_types = {
+			/* int */
+			BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),	/* [1] */
+			/* static int t */
+			BTF_VAR_ENC(NAME_NTH(1), 1, 0),			/* [2] */
+			/* void f(int a1, int a2) */
+			BTF_FUNC_PROTO_ENC(0, 2),			/* [3] */
+				BTF_FUNC_PROTO_ARG_ENC(NAME_NTH(2), 1),
+				BTF_FUNC_PROTO_ARG_ENC(NAME_NTH(3), 1),
+			BTF_FUNC_ENC(NAME_NTH(4), 2),			/* [4] */
+			/* tag -> t */
+			BTF_TAG_ENC(NAME_NTH(5), 2, -1),		/* [5] */
+			BTF_TAG_ENC(NAME_NTH(5), 2, -1),		/* [6] */
+			/* tag -> func */
+			BTF_TAG_ENC(NAME_NTH(5), 4, -1),		/* [7] */
+			BTF_TAG_ENC(NAME_NTH(5), 4, -1),		/* [8] */
+			/* tag -> func arg a1 */
+			BTF_TAG_ENC(NAME_NTH(5), 4, 1),			/* [9] */
+			BTF_TAG_ENC(NAME_NTH(5), 4, 1),			/* [10] */
+			BTF_END_RAW,
+		},
+		BTF_STR_SEC("\0t\0a1\0a2\0f\0tag"),
+	},
+	.expect = {
+		.raw_types = {
+			BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),	/* [1] */
+			BTF_VAR_ENC(NAME_NTH(1), 1, 0),			/* [2] */
+			BTF_FUNC_PROTO_ENC(0, 2),			/* [3] */
+				BTF_FUNC_PROTO_ARG_ENC(NAME_NTH(2), 1),
+				BTF_FUNC_PROTO_ARG_ENC(NAME_NTH(3), 1),
+			BTF_FUNC_ENC(NAME_NTH(4), 2),			/* [4] */
+			BTF_TAG_ENC(NAME_NTH(5), 2, -1),		/* [5] */
+			BTF_TAG_ENC(NAME_NTH(5), 4, -1),		/* [6] */
+			BTF_TAG_ENC(NAME_NTH(5), 4, 1),			/* [7] */
+			BTF_END_RAW,
+		},
+		BTF_STR_SEC("\0t\0a1\0a2\0f\0tag"),
+	},
+	.opts = {
+		.dont_resolve_fwds = false,
+	},
+},
+{
+	.descr = "dedup: func/func_param tags",
+	.input = {
+		.raw_types = {
+			/* int */
+			BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),	/* [1] */
+			/* void f(int a1, int a2) */
+			BTF_FUNC_PROTO_ENC(0, 2),			/* [2] */
+				BTF_FUNC_PROTO_ARG_ENC(NAME_NTH(1), 1),
+				BTF_FUNC_PROTO_ARG_ENC(NAME_NTH(2), 1),
+			BTF_FUNC_ENC(NAME_NTH(3), 2),			/* [3] */
+			/* void f(int a1, int a2) */
+			BTF_FUNC_PROTO_ENC(0, 2),			/* [4] */
+				BTF_FUNC_PROTO_ARG_ENC(NAME_NTH(1), 1),
+				BTF_FUNC_PROTO_ARG_ENC(NAME_NTH(2), 1),
+			BTF_FUNC_ENC(NAME_NTH(3), 4),			/* [5] */
+			/* tag -> f: tag1, tag2 */
+			BTF_TAG_ENC(NAME_NTH(4), 3, -1),		/* [6] */
+			BTF_TAG_ENC(NAME_NTH(5), 3, -1),		/* [7] */
+			/* tag -> f/a2: tag1, tag2 */
+			BTF_TAG_ENC(NAME_NTH(4), 3, 1),			/* [8] */
+			BTF_TAG_ENC(NAME_NTH(5), 3, 1),			/* [9] */
+			/* tag -> f: tag1, tag3 */
+			BTF_TAG_ENC(NAME_NTH(4), 5, -1),		/* [10] */
+			BTF_TAG_ENC(NAME_NTH(6), 5, -1),		/* [11] */
+			/* tag -> f/a2: tag1, tag3 */
+			BTF_TAG_ENC(NAME_NTH(4), 5, 1),			/* [12] */
+			BTF_TAG_ENC(NAME_NTH(6), 5, 1),			/* [13] */
+			BTF_END_RAW,
+		},
+		BTF_STR_SEC("\0a1\0a2\0f\0tag1\0tag2\0tag3"),
+	},
+	.expect = {
+		.raw_types = {
+			BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),	/* [1] */
+			BTF_FUNC_PROTO_ENC(0, 2),			/* [2] */
+				BTF_FUNC_PROTO_ARG_ENC(NAME_NTH(1), 1),
+				BTF_FUNC_PROTO_ARG_ENC(NAME_NTH(2), 1),
+			BTF_FUNC_ENC(NAME_NTH(3), 2),			/* [3] */
+			BTF_TAG_ENC(NAME_NTH(4), 3, -1),		/* [4] */
+			BTF_TAG_ENC(NAME_NTH(5), 3, -1),		/* [5] */
+			BTF_TAG_ENC(NAME_NTH(6), 3, -1),		/* [6] */
+			BTF_TAG_ENC(NAME_NTH(4), 3, 1),			/* [7] */
+			BTF_TAG_ENC(NAME_NTH(5), 3, 1),			/* [8] */
+			BTF_TAG_ENC(NAME_NTH(6), 3, 1),			/* [9] */
+			BTF_END_RAW,
+		},
+		BTF_STR_SEC("\0a1\0a2\0f\0tag1\0tag2\0tag3"),
+	},
+	.opts = {
+		.dont_resolve_fwds = false,
+	},
+},
+{
+	.descr = "dedup: struct/struct_member tags",
+	.input = {
+		.raw_types = {
+			/* int */
+			BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),	/* [1] */
+			BTF_STRUCT_ENC(NAME_NTH(1), 2, 8),		/* [2] */
+				BTF_MEMBER_ENC(NAME_NTH(2), 1, 0),
+				BTF_MEMBER_ENC(NAME_NTH(3), 1, 32),
+			BTF_STRUCT_ENC(NAME_NTH(1), 2, 8),		/* [3] */
+				BTF_MEMBER_ENC(NAME_NTH(2), 1, 0),
+				BTF_MEMBER_ENC(NAME_NTH(3), 1, 32),
+			/* tag -> t: tag1, tag2 */
+			BTF_TAG_ENC(NAME_NTH(4), 2, -1),		/* [4] */
+			BTF_TAG_ENC(NAME_NTH(5), 2, -1),		/* [5] */
+			/* tag -> t/m2: tag1, tag2 */
+			BTF_TAG_ENC(NAME_NTH(4), 2, 1),			/* [6] */
+			BTF_TAG_ENC(NAME_NTH(5), 2, 1),			/* [7] */
+			/* tag -> t: tag1, tag3 */
+			BTF_TAG_ENC(NAME_NTH(4), 3, -1),		/* [8] */
+			BTF_TAG_ENC(NAME_NTH(6), 3, -1),		/* [9] */
+			/* tag -> t/m2: tag1, tag3 */
+			BTF_TAG_ENC(NAME_NTH(4), 3, 1),			/* [10] */
+			BTF_TAG_ENC(NAME_NTH(6), 3, 1),			/* [11] */
+			BTF_END_RAW,
+		},
+		BTF_STR_SEC("\0t\0m1\0m2\0tag1\0tag2\0tag3"),
+	},
+	.expect = {
+		.raw_types = {
+			BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),	/* [1] */
+			BTF_STRUCT_ENC(NAME_NTH(1), 2, 8),		/* [2] */
+				BTF_MEMBER_ENC(NAME_NTH(2), 1, 0),
+				BTF_MEMBER_ENC(NAME_NTH(3), 1, 32),
+			BTF_TAG_ENC(NAME_NTH(4), 2, -1),		/* [3] */
+			BTF_TAG_ENC(NAME_NTH(5), 2, -1),		/* [4] */
+			BTF_TAG_ENC(NAME_NTH(6), 2, -1),		/* [5] */
+			BTF_TAG_ENC(NAME_NTH(4), 2, 1),			/* [6] */
+			BTF_TAG_ENC(NAME_NTH(5), 2, 1),			/* [7] */
+			BTF_TAG_ENC(NAME_NTH(6), 2, 1),			/* [8] */
+			BTF_END_RAW,
+		},
+		BTF_STR_SEC("\0t\0m1\0m2\0tag1\0tag2\0tag3"),
+	},
+	.opts = {
+		.dont_resolve_fwds = false,
+	},
+},
 
 };
 
-- 
cgit v1.2.3


From c240ba28789063690077d282f8f89e03f31037d0 Mon Sep 17 00:00:00 2001
From: Yonghong Song <yhs@fb.com>
Date: Tue, 14 Sep 2021 15:30:58 -0700
Subject: selftests/bpf: Add a test with a bpf program with btf_tag attributes

Add a bpf program with btf_tag attributes. The program is
loaded successfully with the kernel. With the command
  bpftool btf dump file ./tag.o
the following dump shows that tags are properly encoded:
  [8] STRUCT 'key_t' size=12 vlen=3
          'a' type_id=2 bits_offset=0
          'b' type_id=2 bits_offset=32
          'c' type_id=2 bits_offset=64
  [9] TAG 'tag1' type_id=8 component_id=-1
  [10] TAG 'tag2' type_id=8 component_id=-1
  [11] TAG 'tag1' type_id=8 component_id=1
  [12] TAG 'tag2' type_id=8 component_id=1
  ...
  [21] FUNC_PROTO '(anon)' ret_type_id=2 vlen=1
          'x' type_id=2
  [22] FUNC 'foo' type_id=21 linkage=static
  [23] TAG 'tag1' type_id=22 component_id=0
  [24] TAG 'tag2' type_id=22 component_id=0
  [25] TAG 'tag1' type_id=22 component_id=-1
  [26] TAG 'tag2' type_id=22 component_id=-1
  ...
  [29] VAR 'total' type_id=27, linkage=global
  [30] TAG 'tag1' type_id=29 component_id=-1
  [31] TAG 'tag2' type_id=29 component_id=-1

If an old clang compiler, which does not support btf_tag attribute,
is used, these btf_tag attributes will be silently ignored.

Signed-off-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20210914223058.248949-1-yhs@fb.com
---
 tools/testing/selftests/bpf/prog_tests/btf_tag.c | 14 +++++++++
 tools/testing/selftests/bpf/progs/tag.c          | 39 ++++++++++++++++++++++++
 2 files changed, 53 insertions(+)
 create mode 100644 tools/testing/selftests/bpf/prog_tests/btf_tag.c
 create mode 100644 tools/testing/selftests/bpf/progs/tag.c

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/prog_tests/btf_tag.c b/tools/testing/selftests/bpf/prog_tests/btf_tag.c
new file mode 100644
index 000000000000..f939527ede77
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/btf_tag.c
@@ -0,0 +1,14 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2021 Facebook */
+#include <test_progs.h>
+#include "tag.skel.h"
+
+void test_btf_tag(void)
+{
+	struct tag *skel;
+
+	skel = tag__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "btf_tag"))
+		return;
+	tag__destroy(skel);
+}
diff --git a/tools/testing/selftests/bpf/progs/tag.c b/tools/testing/selftests/bpf/progs/tag.c
new file mode 100644
index 000000000000..17f88c58a6c5
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/tag.c
@@ -0,0 +1,39 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2021 Facebook */
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+
+#define __tag1 __attribute__((btf_tag("tag1")))
+#define __tag2 __attribute__((btf_tag("tag2")))
+
+struct key_t {
+	int a;
+	int b __tag1 __tag2;
+	int c;
+} __tag1 __tag2;
+
+struct {
+	__uint(type, BPF_MAP_TYPE_HASH);
+	__uint(max_entries, 3);
+	__type(key, struct key_t);
+	__type(value, __u64);
+} hashmap1 SEC(".maps");
+
+__u32 total __tag1 __tag2 = 0;
+
+static __noinline int foo(int x __tag1 __tag2) __tag1 __tag2
+{
+	struct key_t key;
+	__u64 val = 1;
+
+	key.a = key.b = key.c = x;
+	bpf_map_update_elem(&hashmap1, &key, &val, 0);
+	return 0;
+}
+
+SEC("fentry/bpf_fentry_test1")
+int BPF_PROG(sub, int x)
+{
+	return foo(x);
+}
-- 
cgit v1.2.3


From 2d6a58996ee23f85745a8e42edaad7a2b86d1a83 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Mon, 13 Sep 2021 15:53:32 -0700
Subject: selftests: net: test ethtool -L vs mq

Add a selftest for checking mq children are visible after ethtool -L.

Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../drivers/net/netdevsim/ethtool-common.sh        |  2 +-
 .../drivers/net/netdevsim/tc-mq-visibility.sh      | 77 ++++++++++++++++++++++
 2 files changed, 78 insertions(+), 1 deletion(-)
 create mode 100755 tools/testing/selftests/drivers/net/netdevsim/tc-mq-visibility.sh

(limited to 'tools')

diff --git a/tools/testing/selftests/drivers/net/netdevsim/ethtool-common.sh b/tools/testing/selftests/drivers/net/netdevsim/ethtool-common.sh
index 7ca1f030d209..922744059aaa 100644
--- a/tools/testing/selftests/drivers/net/netdevsim/ethtool-common.sh
+++ b/tools/testing/selftests/drivers/net/netdevsim/ethtool-common.sh
@@ -50,7 +50,7 @@ function make_netdev {
 	modprobe netdevsim
     fi
 
-    echo $NSIM_ID > /sys/bus/netdevsim/new_device
+    echo $NSIM_ID $@ > /sys/bus/netdevsim/new_device
     # get new device name
     ls /sys/bus/netdevsim/devices/netdevsim${NSIM_ID}/net/
 }
diff --git a/tools/testing/selftests/drivers/net/netdevsim/tc-mq-visibility.sh b/tools/testing/selftests/drivers/net/netdevsim/tc-mq-visibility.sh
new file mode 100755
index 000000000000..fd13c8cfb7a8
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/netdevsim/tc-mq-visibility.sh
@@ -0,0 +1,77 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0-only
+
+source ethtool-common.sh
+
+set -o pipefail
+
+n_children() {
+    n=$(tc qdisc show dev $NDEV | grep '^qdisc' | wc -l)
+    echo $((n - 1))
+}
+
+tcq() {
+    tc qdisc $1 dev $NDEV ${@:2}
+}
+
+n_child_assert() {
+    n=$(n_children)
+    if [ $n -ne $1 ]; then
+	echo "ERROR ($root): ${@:2}, expected $1 have $n"
+	((num_errors++))
+    else
+	((num_passes++))
+    fi
+}
+
+
+for root in mq mqprio; do
+    NDEV=$(make_netdev 1 4)
+
+    opts=
+    [ $root == "mqprio" ] && opts='hw 0 num_tc 1 map 0 0 0 0  queues 1@0'
+
+    tcq add root handle 100: $root $opts
+    n_child_assert 4 'Init'
+
+    # All defaults
+
+    for n in 3 2 1 2 3 4 1 4; do
+	ethtool -L $NDEV combined $n
+	n_child_assert $n "Change queues to $n while down"
+    done
+
+    ip link set dev $NDEV up
+
+    for n in 3 2 1 2 3 4 1 4; do
+	ethtool -L $NDEV combined $n
+	n_child_assert $n "Change queues to $n while up"
+    done
+
+    # One real one
+    tcq replace parent 100:4 handle 204: pfifo_fast
+    n_child_assert 4 "One real queue"
+
+    ethtool -L $NDEV combined 1
+    n_child_assert 2 "One real queue, one default"
+
+    ethtool -L $NDEV combined 4
+    n_child_assert 4 "One real queue, rest default"
+
+    # Graft some
+    tcq replace parent 100:1 handle 204:
+    n_child_assert 3 "Grafted"
+
+    ethtool -L $NDEV combined 1
+    n_child_assert 1 "Grafted, one"
+
+    cleanup_nsim
+done
+
+if [ $num_errors -eq 0 ]; then
+    echo "PASSED all $((num_passes)) checks"
+    exit 0
+else
+    echo "FAILED $num_errors/$((num_errors+num_passes)) checks"
+    exit 1
+fi
-- 
cgit v1.2.3


From 2220ecf55c1b7aa36e99b00a6b964f4e5333f9bf Mon Sep 17 00:00:00 2001
From: Yonghong Song <yhs@fb.com>
Date: Tue, 14 Sep 2021 23:10:36 -0700
Subject: selftests/bpf: Skip btf_tag test if btf_tag attribute not supported

Commit c240ba287890 ("selftests/bpf: Add a test with a bpf
program with btf_tag attributes") added btf_tag selftest
to test BTF_KIND_TAG generation from C source code, and to
test kernel validation of generated BTF types.
But if an old clang (clang 13 or earlier) is used, the
following compiler warning may be seen:
  progs/tag.c:23:20: warning: unknown attribute 'btf_tag' ignored
and the test itself is marked OK. The compiler warning is bad
and the test itself shouldn't be marked OK.

This patch added the check for btf_tag attribute support.
If btf_tag is not supported by the clang, the attribute will
not be used in the code and the test will be marked as skipped.
For example, with clang 13:
  ./test_progs -t btf_tag
  #21 btf_tag:SKIP
  Summary: 1/0 PASSED, 1 SKIPPED, 0 FAILED

The selftests/README.rst is updated to clarify when the btf_tag
test may be skipped.

Signed-off-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20210915061036.2577971-1-yhs@fb.com
---
 tools/testing/selftests/bpf/README.rst           | 14 ++++++++++++++
 tools/testing/selftests/bpf/prog_tests/btf_tag.c |  6 ++++++
 tools/testing/selftests/bpf/progs/tag.c          | 12 +++++++++++-
 3 files changed, 31 insertions(+), 1 deletion(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/README.rst b/tools/testing/selftests/bpf/README.rst
index 9b17f2867488..8200c0da2769 100644
--- a/tools/testing/selftests/bpf/README.rst
+++ b/tools/testing/selftests/bpf/README.rst
@@ -201,6 +201,20 @@ Without it, the error from compiling bpf selftests looks like:
 
 __ https://reviews.llvm.org/D93563
 
+btf_tag test and Clang version
+==============================
+
+The btf_tag selftest require LLVM support to recognize the btf_tag attribute.
+It was introduced in `Clang 14`__.
+
+Without it, the btf_tag selftest will be skipped and you will observe:
+
+.. code-block:: console
+
+  #<test_num> btf_tag:SKIP
+
+__ https://reviews.llvm.org/D106614
+
 Clang dependencies for static linking tests
 ===========================================
 
diff --git a/tools/testing/selftests/bpf/prog_tests/btf_tag.c b/tools/testing/selftests/bpf/prog_tests/btf_tag.c
index f939527ede77..91821f42714d 100644
--- a/tools/testing/selftests/bpf/prog_tests/btf_tag.c
+++ b/tools/testing/selftests/bpf/prog_tests/btf_tag.c
@@ -10,5 +10,11 @@ void test_btf_tag(void)
 	skel = tag__open_and_load();
 	if (!ASSERT_OK_PTR(skel, "btf_tag"))
 		return;
+
+	if (skel->rodata->skip_tests) {
+		printf("%s:SKIP: btf_tag attribute not supported", __func__);
+		test__skip();
+	}
+
 	tag__destroy(skel);
 }
diff --git a/tools/testing/selftests/bpf/progs/tag.c b/tools/testing/selftests/bpf/progs/tag.c
index 17f88c58a6c5..b46b1bfac7da 100644
--- a/tools/testing/selftests/bpf/progs/tag.c
+++ b/tools/testing/selftests/bpf/progs/tag.c
@@ -4,8 +4,19 @@
 #include <bpf/bpf_helpers.h>
 #include <bpf/bpf_tracing.h>
 
+#ifndef __has_attribute
+#define __has_attribute(x) 0
+#endif
+
+#if __has_attribute(btf_tag)
 #define __tag1 __attribute__((btf_tag("tag1")))
 #define __tag2 __attribute__((btf_tag("tag2")))
+volatile const bool skip_tests __tag1 __tag2 = false;
+#else
+#define __tag1
+#define __tag2
+volatile const bool skip_tests = true;
+#endif
 
 struct key_t {
 	int a;
@@ -20,7 +31,6 @@ struct {
 	__type(value, __u64);
 } hashmap1 SEC(".maps");
 
-__u32 total __tag1 __tag2 = 0;
 
 static __noinline int foo(int x __tag1 __tag2) __tag1 __tag2
 {
-- 
cgit v1.2.3


From 69cd823956ba8ce266a901170b1060db8073bddd Mon Sep 17 00:00:00 2001
From: Grant Seltzer <grantseltzer@gmail.com>
Date: Tue, 14 Sep 2021 22:19:52 -0400
Subject: libbpf: Add sphinx code documentation comments

This adds comments above five functions in btf.h which document
their uses. These comments are of a format that doxygen and sphinx
can pick up and render. These are rendered by libbpf.readthedocs.org

Signed-off-by: Grant Seltzer <grantseltzer@gmail.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20210915021951.117186-1-grantseltzer@gmail.com
---
 tools/lib/bpf/btf.h | 70 +++++++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 70 insertions(+)

(limited to 'tools')

diff --git a/tools/lib/bpf/btf.h b/tools/lib/bpf/btf.h
index 659ea8a2769b..2cfe31327920 100644
--- a/tools/lib/bpf/btf.h
+++ b/tools/lib/bpf/btf.h
@@ -1,5 +1,6 @@
 /* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */
 /* Copyright (c) 2018 Facebook */
+/*! \file */
 
 #ifndef __LIBBPF_BTF_H
 #define __LIBBPF_BTF_H
@@ -30,11 +31,80 @@ enum btf_endianness {
 	BTF_BIG_ENDIAN = 1,
 };
 
+/**
+ * @brief **btf__free()** frees all data of a BTF object
+ * @param btf BTF object to free
+ */
 LIBBPF_API void btf__free(struct btf *btf);
 
+/**
+ * @brief **btf__new()** creates a new instance of a BTF object from the raw
+ * bytes of an ELF's BTF section
+ * @param data raw bytes
+ * @param size number of bytes passed in `data`
+ * @return new BTF object instance which has to be eventually freed with
+ * **btf__free()**
+ *
+ * On error, error-code-encoded-as-pointer is returned, not a NULL. To extract
+ * error code from such a pointer `libbpf_get_error()` should be used. If
+ * `libbpf_set_strict_mode(LIBBPF_STRICT_CLEAN_PTRS)` is enabled, NULL is
+ * returned on error instead. In both cases thread-local `errno` variable is
+ * always set to error code as well.
+ */
 LIBBPF_API struct btf *btf__new(const void *data, __u32 size);
+
+/**
+ * @brief **btf__new_split()** create a new instance of a BTF object from the
+ * provided raw data bytes. It takes another BTF instance, **base_btf**, which
+ * serves as a base BTF, which is extended by types in a newly created BTF
+ * instance
+ * @param data raw bytes
+ * @param size length of raw bytes
+ * @param base_btf the base BTF object
+ * @return new BTF object instance which has to be eventually freed with
+ * **btf__free()**
+ *
+ * If *base_btf* is NULL, `btf__new_split()` is equivalent to `btf__new()` and
+ * creates non-split BTF.
+ *
+ * On error, error-code-encoded-as-pointer is returned, not a NULL. To extract
+ * error code from such a pointer `libbpf_get_error()` should be used. If
+ * `libbpf_set_strict_mode(LIBBPF_STRICT_CLEAN_PTRS)` is enabled, NULL is
+ * returned on error instead. In both cases thread-local `errno` variable is
+ * always set to error code as well.
+ */
 LIBBPF_API struct btf *btf__new_split(const void *data, __u32 size, struct btf *base_btf);
+
+/**
+ * @brief **btf__new_empty()** creates an empty BTF object.  Use
+ * `btf__add_*()` to populate such BTF object.
+ * @return new BTF object instance which has to be eventually freed with
+ * **btf__free()**
+ *
+ * On error, error-code-encoded-as-pointer is returned, not a NULL. To extract
+ * error code from such a pointer `libbpf_get_error()` should be used. If
+ * `libbpf_set_strict_mode(LIBBPF_STRICT_CLEAN_PTRS)` is enabled, NULL is
+ * returned on error instead. In both cases thread-local `errno` variable is
+ * always set to error code as well.
+ */
 LIBBPF_API struct btf *btf__new_empty(void);
+
+/**
+ * @brief **btf__new_empty_split()** creates an unpopulated BTF object from an
+ * ELF BTF section except with a base BTF on top of which split BTF should be
+ * based
+ * @return new BTF object instance which has to be eventually freed with
+ * **btf__free()**
+ *
+ * If *base_btf* is NULL, `btf__new_empty_split()` is equivalent to
+ * `btf__new_empty()` and creates non-split BTF.
+ *
+ * On error, error-code-encoded-as-pointer is returned, not a NULL. To extract
+ * error code from such a pointer `libbpf_get_error()` should be used. If
+ * `libbpf_set_strict_mode(LIBBPF_STRICT_CLEAN_PTRS)` is enabled, NULL is
+ * returned on error instead. In both cases thread-local `errno` variable is
+ * always set to error code as well.
+ */
 LIBBPF_API struct btf *btf__new_empty_split(struct btf *base_btf);
 
 LIBBPF_API struct btf *btf__parse(const char *path, struct btf_ext **btf_ext);
-- 
cgit v1.2.3


From 336562752acc1a723f9a24b5b8129ae22e0478c6 Mon Sep 17 00:00:00 2001
From: Matteo Croce <mcroce@microsoft.com>
Date: Wed, 15 Sep 2021 01:54:00 +0200
Subject: bpf: Update bpf_get_smp_processor_id() documentation

BPF programs run with migration disabled regardless of preemption, as
they are protected by migrate_disable(). Update the uapi documentation
accordingly.

Signed-off-by: Matteo Croce <mcroce@microsoft.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Yonghong Song <yhs@fb.com>
Link: https://lore.kernel.org/bpf/20210914235400.59427-1-mcroce@linux.microsoft.com
---
 tools/include/uapi/linux/bpf.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'tools')

diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index d21326558d42..3e9785f1064a 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -1629,7 +1629,7 @@ union bpf_attr {
  * u32 bpf_get_smp_processor_id(void)
  * 	Description
  * 		Get the SMP (symmetric multiprocessing) processor id. Note that
- * 		all programs run with preemption disabled, which means that the
+ * 		all programs run with migration disabled, which means that the
  * 		SMP processor id is stable during all the execution of the
  * 		program.
  * 	Return
-- 
cgit v1.2.3


From f11f86a3931b5d533aed1be1720fbd55bd63174d Mon Sep 17 00:00:00 2001
From: Andrii Nakryiko <andrii@kernel.org>
Date: Wed, 15 Sep 2021 18:58:30 -0700
Subject: libbpf: Use pre-setup sec_def in libbpf_find_attach_btf_id()

Don't perform another search for sec_def inside
libbpf_find_attach_btf_id(), as each recognized bpf_program already has
prog->sec_def set.

Also remove unnecessary NULL check for prog->sec_name, as it can never
be NULL.

Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Yonghong Song <yhs@fb.com>
Link: https://lore.kernel.org/bpf/20210916015836.1248906-2-andrii@kernel.org
---
 tools/lib/bpf/libbpf.c | 14 +++++---------
 1 file changed, 5 insertions(+), 9 deletions(-)

(limited to 'tools')

diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 62a43c408d73..5ba11b249e9b 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -8461,19 +8461,15 @@ static int libbpf_find_attach_btf_id(struct bpf_program *prog, int *btf_obj_fd,
 {
 	enum bpf_attach_type attach_type = prog->expected_attach_type;
 	__u32 attach_prog_fd = prog->attach_prog_fd;
-	const char *name = prog->sec_name, *attach_name;
-	const struct bpf_sec_def *sec = NULL;
+	const char *attach_name;
 	int err = 0;
 
-	if (!name)
-		return -EINVAL;
-
-	sec = find_sec_def(name);
-	if (!sec || !sec->is_attach_btf) {
-		pr_warn("failed to identify BTF ID based on ELF section name '%s'\n", name);
+	if (!prog->sec_def || !prog->sec_def->is_attach_btf) {
+		pr_warn("failed to identify BTF ID based on ELF section name '%s'\n",
+			prog->sec_name);
 		return -ESRCH;
 	}
-	attach_name = name + sec->len;
+	attach_name = prog->sec_name + prog->sec_def->len;
 
 	/* BPF program's BTF ID */
 	if (attach_prog_fd) {
-- 
cgit v1.2.3


From 23a7baaa93882c241ad3464cdeeb8ef0d1d40a12 Mon Sep 17 00:00:00 2001
From: Andrii Nakryiko <andrii@kernel.org>
Date: Wed, 15 Sep 2021 18:58:31 -0700
Subject: selftests/bpf: Stop using relaxed_core_relocs which has no effect

relaxed_core_relocs option hasn't had any effect for a while now, stop
specifying it. Next patch marks it as deprecated.

Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Yonghong Song <yhs@fb.com>
Link: https://lore.kernel.org/bpf/20210916015836.1248906-3-andrii@kernel.org
---
 tools/testing/selftests/bpf/prog_tests/core_reloc.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/prog_tests/core_reloc.c b/tools/testing/selftests/bpf/prog_tests/core_reloc.c
index 15d355af8d1d..763302e63a29 100644
--- a/tools/testing/selftests/bpf/prog_tests/core_reloc.c
+++ b/tools/testing/selftests/bpf/prog_tests/core_reloc.c
@@ -249,8 +249,7 @@ static int duration = 0;
 #define SIZE_CASE_COMMON(name)						\
 	.case_name = #name,						\
 	.bpf_obj_file = "test_core_reloc_size.o",			\
-	.btf_src_file = "btf__core_reloc_" #name ".o",			\
-	.relaxed_core_relocs = true
+	.btf_src_file = "btf__core_reloc_" #name ".o"
 
 #define SIZE_OUTPUT_DATA(type)						\
 	STRUCT_TO_CHAR_PTR(core_reloc_size_output) {			\
-- 
cgit v1.2.3


From 277641859e833549722eb82c97cbc2d55421df7c Mon Sep 17 00:00:00 2001
From: Andrii Nakryiko <andrii@kernel.org>
Date: Wed, 15 Sep 2021 18:58:32 -0700
Subject: libbpf: Deprecated bpf_object_open_opts.relaxed_core_relocs

It's relevant and hasn't been doing anything for a long while now.
Deprecated it.

Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Yonghong Song <yhs@fb.com>
Link: https://lore.kernel.org/bpf/20210916015836.1248906-4-andrii@kernel.org
---
 tools/lib/bpf/libbpf.h | 1 +
 1 file changed, 1 insertion(+)

(limited to 'tools')

diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h
index 2f6f0e15d1e7..7111e8d651de 100644
--- a/tools/lib/bpf/libbpf.h
+++ b/tools/lib/bpf/libbpf.h
@@ -83,6 +83,7 @@ struct bpf_object_open_opts {
 	 * Non-relocatable instructions are replaced with invalid ones to
 	 * prevent accidental errors.
 	 * */
+	LIBBPF_DEPRECATED_SINCE(0, 6, "field has no effect")
 	bool relaxed_core_relocs;
 	/* maps that set the 'pinning' attribute in their definition will have
 	 * their pin_path attribute set to a file in this directory, and be
-- 
cgit v1.2.3


From 2d5ec1c66e25f0b4dd895a211e651a12dec2ef4f Mon Sep 17 00:00:00 2001
From: Andrii Nakryiko <andrii@kernel.org>
Date: Wed, 15 Sep 2021 18:58:33 -0700
Subject: libbpf: Allow skipping attach_func_name in
 bpf_program__set_attach_target()

Allow to use bpf_program__set_attach_target to only set target attach
program FD, while letting libbpf to use target attach function name from
SEC() definition. This might be useful for some scenarios where
bpf_object contains multiple related freplace BPF programs intended to
replace different sub-programs in target BPF program. In such case all
programs will have the same attach_prog_fd, but different
attach_func_name. It's convenient to specify such target function names
declaratively in SEC() definitions, but attach_prog_fd is a dynamic
runtime setting.

To simplify such scenario, allow bpf_program__set_attach_target() to
delay BTF ID resolution till the BPF program load time by providing NULL
attach_func_name. In that case the behavior will be similar to using
bpf_object_open_opts.attach_prog_fd (which is marked deprecated since
v0.7), but has the benefit of allowing more control by user in what is
attached to what. Such setup allows having BPF programs attached to
different target attach_prog_fd with target functions still declaratively
recorded in BPF source code in SEC() definitions.

Selftests changes in the next patch should make this more obvious.

Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Yonghong Song <yhs@fb.com>
Link: https://lore.kernel.org/bpf/20210916015836.1248906-5-andrii@kernel.org
---
 tools/lib/bpf/libbpf.c | 13 ++++++++++++-
 1 file changed, 12 insertions(+), 1 deletion(-)

(limited to 'tools')

diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 5ba11b249e9b..552d05a85cbb 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -10643,18 +10643,29 @@ int bpf_program__set_attach_target(struct bpf_program *prog,
 {
 	int btf_obj_fd = 0, btf_id = 0, err;
 
-	if (!prog || attach_prog_fd < 0 || !attach_func_name)
+	if (!prog || attach_prog_fd < 0)
 		return libbpf_err(-EINVAL);
 
 	if (prog->obj->loaded)
 		return libbpf_err(-EINVAL);
 
+	if (attach_prog_fd && !attach_func_name) {
+		/* remember attach_prog_fd and let bpf_program__load() find
+		 * BTF ID during the program load
+		 */
+		prog->attach_prog_fd = attach_prog_fd;
+		return 0;
+	}
+
 	if (attach_prog_fd) {
 		btf_id = libbpf_find_prog_btf_id(attach_func_name,
 						 attach_prog_fd);
 		if (btf_id < 0)
 			return libbpf_err(btf_id);
 	} else {
+		if (!attach_func_name)
+			return libbpf_err(-EINVAL);
+
 		/* load btf_vmlinux, if not yet */
 		err = bpf_object__load_vmlinux_btf(prog->obj, true);
 		if (err)
-- 
cgit v1.2.3


From 60aed22076b0d0ec2b7c7f9dba3ccd642520e1f3 Mon Sep 17 00:00:00 2001
From: Andrii Nakryiko <andrii@kernel.org>
Date: Wed, 15 Sep 2021 18:58:34 -0700
Subject: selftests/bpf: Switch fexit_bpf2bpf selftest to set_attach_target()
 API

Switch fexit_bpf2bpf selftest to bpf_program__set_attach_target()
instead of using bpf_object_open_opts.attach_prog_fd, which is going to
be deprecated. These changes also demonstrate the new mode of
set_attach_target() in which it allows NULL when the target is BPF
program (attach_prog_fd != 0).

Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Yonghong Song <yhs@fb.com>
Link: https://lore.kernel.org/bpf/20210916015836.1248906-6-andrii@kernel.org
---
 .../selftests/bpf/prog_tests/fexit_bpf2bpf.c       | 43 +++++++++++++---------
 1 file changed, 26 insertions(+), 17 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/prog_tests/fexit_bpf2bpf.c b/tools/testing/selftests/bpf/prog_tests/fexit_bpf2bpf.c
index 73b4c76e6b86..c7c1816899bf 100644
--- a/tools/testing/selftests/bpf/prog_tests/fexit_bpf2bpf.c
+++ b/tools/testing/selftests/bpf/prog_tests/fexit_bpf2bpf.c
@@ -60,7 +60,7 @@ static void test_fexit_bpf2bpf_common(const char *obj_file,
 	struct bpf_object *obj = NULL, *tgt_obj;
 	__u32 retval, tgt_prog_id, info_len;
 	struct bpf_prog_info prog_info = {};
-	struct bpf_program **prog = NULL;
+	struct bpf_program **prog = NULL, *p;
 	struct bpf_link **link = NULL;
 	int err, tgt_fd, i;
 	struct btf *btf;
@@ -69,9 +69,6 @@ static void test_fexit_bpf2bpf_common(const char *obj_file,
 			    &tgt_obj, &tgt_fd);
 	if (!ASSERT_OK(err, "tgt_prog_load"))
 		return;
-	DECLARE_LIBBPF_OPTS(bpf_object_open_opts, opts,
-			    .attach_prog_fd = tgt_fd,
-			   );
 
 	info_len = sizeof(prog_info);
 	err = bpf_obj_get_info_by_fd(tgt_fd, &prog_info, &info_len);
@@ -89,10 +86,15 @@ static void test_fexit_bpf2bpf_common(const char *obj_file,
 	if (!ASSERT_OK_PTR(prog, "prog_ptr"))
 		goto close_prog;
 
-	obj = bpf_object__open_file(obj_file, &opts);
+	obj = bpf_object__open_file(obj_file, NULL);
 	if (!ASSERT_OK_PTR(obj, "obj_open"))
 		goto close_prog;
 
+	bpf_object__for_each_program(p, obj) {
+		err = bpf_program__set_attach_target(p, tgt_fd, NULL);
+		ASSERT_OK(err, "set_attach_target");
+	}
+
 	err = bpf_object__load(obj);
 	if (!ASSERT_OK(err, "obj_load"))
 		goto close_prog;
@@ -270,7 +272,7 @@ static void test_fmod_ret_freplace(void)
 	struct bpf_link *freplace_link = NULL;
 	struct bpf_program *prog;
 	__u32 duration = 0;
-	int err, pkt_fd;
+	int err, pkt_fd, attach_prog_fd;
 
 	err = bpf_prog_load(tgt_name, BPF_PROG_TYPE_UNSPEC,
 			    &pkt_obj, &pkt_fd);
@@ -278,26 +280,32 @@ static void test_fmod_ret_freplace(void)
 	if (CHECK(err, "tgt_prog_load", "file %s err %d errno %d\n",
 		  tgt_name, err, errno))
 		return;
-	opts.attach_prog_fd = pkt_fd;
 
-	freplace_obj = bpf_object__open_file(freplace_name, &opts);
+	freplace_obj = bpf_object__open_file(freplace_name, NULL);
 	if (!ASSERT_OK_PTR(freplace_obj, "freplace_obj_open"))
 		goto out;
 
+	prog = bpf_program__next(NULL, freplace_obj);
+	err = bpf_program__set_attach_target(prog, pkt_fd, NULL);
+	ASSERT_OK(err, "freplace__set_attach_target");
+
 	err = bpf_object__load(freplace_obj);
 	if (CHECK(err, "freplace_obj_load", "err %d\n", err))
 		goto out;
 
-	prog = bpf_program__next(NULL, freplace_obj);
 	freplace_link = bpf_program__attach_trace(prog);
 	if (!ASSERT_OK_PTR(freplace_link, "freplace_attach_trace"))
 		goto out;
 
-	opts.attach_prog_fd = bpf_program__fd(prog);
-	fmod_obj = bpf_object__open_file(fmod_ret_name, &opts);
+	fmod_obj = bpf_object__open_file(fmod_ret_name, NULL);
 	if (!ASSERT_OK_PTR(fmod_obj, "fmod_obj_open"))
 		goto out;
 
+	attach_prog_fd = bpf_program__fd(prog);
+	prog = bpf_program__next(NULL, fmod_obj);
+	err = bpf_program__set_attach_target(prog, attach_prog_fd, NULL);
+	ASSERT_OK(err, "fmod_ret_set_attach_target");
+
 	err = bpf_object__load(fmod_obj);
 	if (CHECK(!err, "fmod_obj_load", "loading fmod_ret should fail\n"))
 		goto out;
@@ -322,14 +330,14 @@ static void test_func_sockmap_update(void)
 }
 
 static void test_obj_load_failure_common(const char *obj_file,
-					  const char *target_obj_file)
-
+					 const char *target_obj_file)
 {
 	/*
 	 * standalone test that asserts failure to load freplace prog
 	 * because of invalid return code.
 	 */
 	struct bpf_object *obj = NULL, *pkt_obj;
+	struct bpf_program *prog;
 	int err, pkt_fd;
 	__u32 duration = 0;
 
@@ -339,14 +347,15 @@ static void test_obj_load_failure_common(const char *obj_file,
 	if (CHECK(err, "tgt_prog_load", "file %s err %d errno %d\n",
 		  target_obj_file, err, errno))
 		return;
-	DECLARE_LIBBPF_OPTS(bpf_object_open_opts, opts,
-			    .attach_prog_fd = pkt_fd,
-			   );
 
-	obj = bpf_object__open_file(obj_file, &opts);
+	obj = bpf_object__open_file(obj_file, NULL);
 	if (!ASSERT_OK_PTR(obj, "obj_open"))
 		goto close_prog;
 
+	prog = bpf_program__next(NULL, obj);
+	err = bpf_program__set_attach_target(prog, pkt_fd, NULL);
+	ASSERT_OK(err, "set_attach_target");
+
 	/* It should fail to load the program */
 	err = bpf_object__load(obj);
 	if (CHECK(!err, "bpf_obj_load should fail", "err %d\n", err))
-- 
cgit v1.2.3


From 91b555d73e53879fc6d4cf82c8c0e14c00ce212d Mon Sep 17 00:00:00 2001
From: Andrii Nakryiko <andrii@kernel.org>
Date: Wed, 15 Sep 2021 18:58:35 -0700
Subject: libbpf: Schedule open_opts.attach_prog_fd deprecation since v0.7

bpf_object_open_opts.attach_prog_fd makes a pretty strong assumption
that bpf_object contains either only single freplace BPF program or all
of BPF programs in BPF object are freplaces intended to replace
different subprograms of the same target BPF program. This seems both
a bit confusing, too assuming, and limiting.

We've had bpf_program__set_attach_target() API which allows more
fine-grained control over this, on a per-program level. As such, mark
open_opts.attach_prog_fd as deprecated starting from v0.7, so that we
have one more universal way of setting freplace targets. With previous
change to allow NULL attach_func_name argument, and especially combined
with BPF skeleton, arguable bpf_program__set_attach_target() is a more
convenient and explicit API as well.

Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Yonghong Song <yhs@fb.com>
Link: https://lore.kernel.org/bpf/20210916015836.1248906-7-andrii@kernel.org
---
 tools/lib/bpf/libbpf.c        | 3 +++
 tools/lib/bpf/libbpf.h        | 2 ++
 tools/lib/bpf/libbpf_common.h | 5 +++++
 3 files changed, 10 insertions(+)

(limited to 'tools')

diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 552d05a85cbb..6aeeb0e82acc 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -6415,9 +6415,12 @@ static int bpf_object_init_progs(struct bpf_object *obj, const struct bpf_object
 		bpf_program__set_type(prog, prog->sec_def->prog_type);
 		bpf_program__set_expected_attach_type(prog, prog->sec_def->expected_attach_type);
 
+#pragma GCC diagnostic push
+#pragma GCC diagnostic ignored "-Wdeprecated-declarations"
 		if (prog->sec_def->prog_type == BPF_PROG_TYPE_TRACING ||
 		    prog->sec_def->prog_type == BPF_PROG_TYPE_EXT)
 			prog->attach_prog_fd = OPTS_GET(opts, attach_prog_fd, 0);
+#pragma GCC diagnostic pop
 	}
 
 	return 0;
diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h
index 7111e8d651de..52b7ee090037 100644
--- a/tools/lib/bpf/libbpf.h
+++ b/tools/lib/bpf/libbpf.h
@@ -90,6 +90,8 @@ struct bpf_object_open_opts {
 	 * auto-pinned to that path on load; defaults to "/sys/fs/bpf".
 	 */
 	const char *pin_root_path;
+
+	LIBBPF_DEPRECATED_SINCE(0, 7, "use bpf_program__set_attach_target() on each individual bpf_program")
 	__u32 attach_prog_fd;
 	/* Additional kernel config content that augments and overrides
 	 * system Kconfig for CONFIG_xxx externs.
diff --git a/tools/lib/bpf/libbpf_common.h b/tools/lib/bpf/libbpf_common.h
index 36ac77f2bea2..aaa1efbf6f51 100644
--- a/tools/lib/bpf/libbpf_common.h
+++ b/tools/lib/bpf/libbpf_common.h
@@ -35,6 +35,11 @@
 #else
 #define __LIBBPF_MARK_DEPRECATED_0_6(X)
 #endif
+#if __LIBBPF_CURRENT_VERSION_GEQ(0, 7)
+#define __LIBBPF_MARK_DEPRECATED_0_7(X) X
+#else
+#define __LIBBPF_MARK_DEPRECATED_0_7(X)
+#endif
 
 /* Helper macro to declare and initialize libbpf options struct
  *
-- 
cgit v1.2.3


From 942025c9f37ee45e69eb5f39a2877afab66d9555 Mon Sep 17 00:00:00 2001
From: Andrii Nakryiko <andrii@kernel.org>
Date: Wed, 15 Sep 2021 18:58:36 -0700
Subject: libbpf: Constify all high-level program attach APIs

Attach APIs shouldn't need to modify bpf_program/bpf_map structs, so
change all struct bpf_program and struct bpf_map pointers to const
pointers. This is completely backwards compatible with no functional
change.

Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Yonghong Song <yhs@fb.com>
Link: https://lore.kernel.org/bpf/20210916015836.1248906-8-andrii@kernel.org
---
 tools/lib/bpf/libbpf.c | 68 +++++++++++++++++++++++++-------------------------
 tools/lib/bpf/libbpf.h | 36 +++++++++++++-------------
 2 files changed, 52 insertions(+), 52 deletions(-)

(limited to 'tools')

diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 6aeeb0e82acc..da65a1666a5e 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -220,7 +220,7 @@ struct reloc_desc {
 
 struct bpf_sec_def;
 
-typedef struct bpf_link *(*attach_fn_t)(struct bpf_program *prog);
+typedef struct bpf_link *(*attach_fn_t)(const struct bpf_program *prog);
 
 struct bpf_sec_def {
 	const char *sec;
@@ -7947,12 +7947,12 @@ void bpf_program__set_expected_attach_type(struct bpf_program *prog,
 	__VA_ARGS__							    \
 }
 
-static struct bpf_link *attach_kprobe(struct bpf_program *prog);
-static struct bpf_link *attach_tp(struct bpf_program *prog);
-static struct bpf_link *attach_raw_tp(struct bpf_program *prog);
-static struct bpf_link *attach_trace(struct bpf_program *prog);
-static struct bpf_link *attach_lsm(struct bpf_program *prog);
-static struct bpf_link *attach_iter(struct bpf_program *prog);
+static struct bpf_link *attach_kprobe(const struct bpf_program *prog);
+static struct bpf_link *attach_tp(const struct bpf_program *prog);
+static struct bpf_link *attach_raw_tp(const struct bpf_program *prog);
+static struct bpf_link *attach_trace(const struct bpf_program *prog);
+static struct bpf_link *attach_lsm(const struct bpf_program *prog);
+static struct bpf_link *attach_iter(const struct bpf_program *prog);
 
 static const struct bpf_sec_def section_defs[] = {
 	BPF_PROG_SEC("socket",			BPF_PROG_TYPE_SOCKET_FILTER),
@@ -9092,7 +9092,7 @@ static void bpf_link_perf_dealloc(struct bpf_link *link)
 	free(perf_link);
 }
 
-struct bpf_link *bpf_program__attach_perf_event_opts(struct bpf_program *prog, int pfd,
+struct bpf_link *bpf_program__attach_perf_event_opts(const struct bpf_program *prog, int pfd,
 						     const struct bpf_perf_event_opts *opts)
 {
 	char errmsg[STRERR_BUFSIZE];
@@ -9167,7 +9167,7 @@ err_out:
 	return libbpf_err_ptr(err);
 }
 
-struct bpf_link *bpf_program__attach_perf_event(struct bpf_program *prog, int pfd)
+struct bpf_link *bpf_program__attach_perf_event(const struct bpf_program *prog, int pfd)
 {
 	return bpf_program__attach_perf_event_opts(prog, pfd, NULL);
 }
@@ -9332,7 +9332,7 @@ static int perf_event_kprobe_open_legacy(bool retprobe, const char *name, uint64
 }
 
 struct bpf_link *
-bpf_program__attach_kprobe_opts(struct bpf_program *prog,
+bpf_program__attach_kprobe_opts(const struct bpf_program *prog,
 				const char *func_name,
 				const struct bpf_kprobe_opts *opts)
 {
@@ -9389,7 +9389,7 @@ bpf_program__attach_kprobe_opts(struct bpf_program *prog,
 	return link;
 }
 
-struct bpf_link *bpf_program__attach_kprobe(struct bpf_program *prog,
+struct bpf_link *bpf_program__attach_kprobe(const struct bpf_program *prog,
 					    bool retprobe,
 					    const char *func_name)
 {
@@ -9400,7 +9400,7 @@ struct bpf_link *bpf_program__attach_kprobe(struct bpf_program *prog,
 	return bpf_program__attach_kprobe_opts(prog, func_name, &opts);
 }
 
-static struct bpf_link *attach_kprobe(struct bpf_program *prog)
+static struct bpf_link *attach_kprobe(const struct bpf_program *prog)
 {
 	DECLARE_LIBBPF_OPTS(bpf_kprobe_opts, opts);
 	unsigned long offset = 0;
@@ -9432,7 +9432,7 @@ static struct bpf_link *attach_kprobe(struct bpf_program *prog)
 }
 
 LIBBPF_API struct bpf_link *
-bpf_program__attach_uprobe_opts(struct bpf_program *prog, pid_t pid,
+bpf_program__attach_uprobe_opts(const struct bpf_program *prog, pid_t pid,
 				const char *binary_path, size_t func_offset,
 				const struct bpf_uprobe_opts *opts)
 {
@@ -9472,7 +9472,7 @@ bpf_program__attach_uprobe_opts(struct bpf_program *prog, pid_t pid,
 	return link;
 }
 
-struct bpf_link *bpf_program__attach_uprobe(struct bpf_program *prog,
+struct bpf_link *bpf_program__attach_uprobe(const struct bpf_program *prog,
 					    bool retprobe, pid_t pid,
 					    const char *binary_path,
 					    size_t func_offset)
@@ -9532,7 +9532,7 @@ static int perf_event_open_tracepoint(const char *tp_category,
 	return pfd;
 }
 
-struct bpf_link *bpf_program__attach_tracepoint_opts(struct bpf_program *prog,
+struct bpf_link *bpf_program__attach_tracepoint_opts(const struct bpf_program *prog,
 						     const char *tp_category,
 						     const char *tp_name,
 						     const struct bpf_tracepoint_opts *opts)
@@ -9566,14 +9566,14 @@ struct bpf_link *bpf_program__attach_tracepoint_opts(struct bpf_program *prog,
 	return link;
 }
 
-struct bpf_link *bpf_program__attach_tracepoint(struct bpf_program *prog,
+struct bpf_link *bpf_program__attach_tracepoint(const struct bpf_program *prog,
 						const char *tp_category,
 						const char *tp_name)
 {
 	return bpf_program__attach_tracepoint_opts(prog, tp_category, tp_name, NULL);
 }
 
-static struct bpf_link *attach_tp(struct bpf_program *prog)
+static struct bpf_link *attach_tp(const struct bpf_program *prog)
 {
 	char *sec_name, *tp_cat, *tp_name;
 	struct bpf_link *link;
@@ -9597,7 +9597,7 @@ static struct bpf_link *attach_tp(struct bpf_program *prog)
 	return link;
 }
 
-struct bpf_link *bpf_program__attach_raw_tracepoint(struct bpf_program *prog,
+struct bpf_link *bpf_program__attach_raw_tracepoint(const struct bpf_program *prog,
 						    const char *tp_name)
 {
 	char errmsg[STRERR_BUFSIZE];
@@ -9627,7 +9627,7 @@ struct bpf_link *bpf_program__attach_raw_tracepoint(struct bpf_program *prog,
 	return link;
 }
 
-static struct bpf_link *attach_raw_tp(struct bpf_program *prog)
+static struct bpf_link *attach_raw_tp(const struct bpf_program *prog)
 {
 	const char *tp_name = prog->sec_name + prog->sec_def->len;
 
@@ -9635,7 +9635,7 @@ static struct bpf_link *attach_raw_tp(struct bpf_program *prog)
 }
 
 /* Common logic for all BPF program types that attach to a btf_id */
-static struct bpf_link *bpf_program__attach_btf_id(struct bpf_program *prog)
+static struct bpf_link *bpf_program__attach_btf_id(const struct bpf_program *prog)
 {
 	char errmsg[STRERR_BUFSIZE];
 	struct bpf_link *link;
@@ -9664,28 +9664,28 @@ static struct bpf_link *bpf_program__attach_btf_id(struct bpf_program *prog)
 	return (struct bpf_link *)link;
 }
 
-struct bpf_link *bpf_program__attach_trace(struct bpf_program *prog)
+struct bpf_link *bpf_program__attach_trace(const struct bpf_program *prog)
 {
 	return bpf_program__attach_btf_id(prog);
 }
 
-struct bpf_link *bpf_program__attach_lsm(struct bpf_program *prog)
+struct bpf_link *bpf_program__attach_lsm(const struct bpf_program *prog)
 {
 	return bpf_program__attach_btf_id(prog);
 }
 
-static struct bpf_link *attach_trace(struct bpf_program *prog)
+static struct bpf_link *attach_trace(const struct bpf_program *prog)
 {
 	return bpf_program__attach_trace(prog);
 }
 
-static struct bpf_link *attach_lsm(struct bpf_program *prog)
+static struct bpf_link *attach_lsm(const struct bpf_program *prog)
 {
 	return bpf_program__attach_lsm(prog);
 }
 
 static struct bpf_link *
-bpf_program__attach_fd(struct bpf_program *prog, int target_fd, int btf_id,
+bpf_program__attach_fd(const struct bpf_program *prog, int target_fd, int btf_id,
 		       const char *target_name)
 {
 	DECLARE_LIBBPF_OPTS(bpf_link_create_opts, opts,
@@ -9721,24 +9721,24 @@ bpf_program__attach_fd(struct bpf_program *prog, int target_fd, int btf_id,
 }
 
 struct bpf_link *
-bpf_program__attach_cgroup(struct bpf_program *prog, int cgroup_fd)
+bpf_program__attach_cgroup(const struct bpf_program *prog, int cgroup_fd)
 {
 	return bpf_program__attach_fd(prog, cgroup_fd, 0, "cgroup");
 }
 
 struct bpf_link *
-bpf_program__attach_netns(struct bpf_program *prog, int netns_fd)
+bpf_program__attach_netns(const struct bpf_program *prog, int netns_fd)
 {
 	return bpf_program__attach_fd(prog, netns_fd, 0, "netns");
 }
 
-struct bpf_link *bpf_program__attach_xdp(struct bpf_program *prog, int ifindex)
+struct bpf_link *bpf_program__attach_xdp(const struct bpf_program *prog, int ifindex)
 {
 	/* target_fd/target_ifindex use the same field in LINK_CREATE */
 	return bpf_program__attach_fd(prog, ifindex, 0, "xdp");
 }
 
-struct bpf_link *bpf_program__attach_freplace(struct bpf_program *prog,
+struct bpf_link *bpf_program__attach_freplace(const struct bpf_program *prog,
 					      int target_fd,
 					      const char *attach_func_name)
 {
@@ -9771,7 +9771,7 @@ struct bpf_link *bpf_program__attach_freplace(struct bpf_program *prog,
 }
 
 struct bpf_link *
-bpf_program__attach_iter(struct bpf_program *prog,
+bpf_program__attach_iter(const struct bpf_program *prog,
 			 const struct bpf_iter_attach_opts *opts)
 {
 	DECLARE_LIBBPF_OPTS(bpf_link_create_opts, link_create_opts);
@@ -9810,12 +9810,12 @@ bpf_program__attach_iter(struct bpf_program *prog,
 	return link;
 }
 
-static struct bpf_link *attach_iter(struct bpf_program *prog)
+static struct bpf_link *attach_iter(const struct bpf_program *prog)
 {
 	return bpf_program__attach_iter(prog, NULL);
 }
 
-struct bpf_link *bpf_program__attach(struct bpf_program *prog)
+struct bpf_link *bpf_program__attach(const struct bpf_program *prog)
 {
 	if (!prog->sec_def || !prog->sec_def->attach_fn)
 		return libbpf_err_ptr(-ESRCH);
@@ -9833,7 +9833,7 @@ static int bpf_link__detach_struct_ops(struct bpf_link *link)
 	return 0;
 }
 
-struct bpf_link *bpf_map__attach_struct_ops(struct bpf_map *map)
+struct bpf_link *bpf_map__attach_struct_ops(const struct bpf_map *map)
 {
 	struct bpf_struct_ops *st_ops;
 	struct bpf_link *link;
@@ -10918,7 +10918,7 @@ int bpf_object__attach_skeleton(struct bpf_object_skeleton *s)
 		if (!prog->sec_def || !prog->sec_def->attach_fn)
 			continue;
 
-		*link = prog->sec_def->attach_fn(prog);
+		*link = bpf_program__attach(prog);
 		err = libbpf_get_error(*link);
 		if (err) {
 			pr_warn("failed to auto-attach program '%s': %d\n",
diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h
index 52b7ee090037..c90e3d79e72c 100644
--- a/tools/lib/bpf/libbpf.h
+++ b/tools/lib/bpf/libbpf.h
@@ -246,7 +246,7 @@ LIBBPF_API int bpf_link__detach(struct bpf_link *link);
 LIBBPF_API int bpf_link__destroy(struct bpf_link *link);
 
 LIBBPF_API struct bpf_link *
-bpf_program__attach(struct bpf_program *prog);
+bpf_program__attach(const struct bpf_program *prog);
 
 struct bpf_perf_event_opts {
 	/* size of this struct, for forward/backward compatiblity */
@@ -257,10 +257,10 @@ struct bpf_perf_event_opts {
 #define bpf_perf_event_opts__last_field bpf_cookie
 
 LIBBPF_API struct bpf_link *
-bpf_program__attach_perf_event(struct bpf_program *prog, int pfd);
+bpf_program__attach_perf_event(const struct bpf_program *prog, int pfd);
 
 LIBBPF_API struct bpf_link *
-bpf_program__attach_perf_event_opts(struct bpf_program *prog, int pfd,
+bpf_program__attach_perf_event_opts(const struct bpf_program *prog, int pfd,
 				    const struct bpf_perf_event_opts *opts);
 
 struct bpf_kprobe_opts {
@@ -277,10 +277,10 @@ struct bpf_kprobe_opts {
 #define bpf_kprobe_opts__last_field retprobe
 
 LIBBPF_API struct bpf_link *
-bpf_program__attach_kprobe(struct bpf_program *prog, bool retprobe,
+bpf_program__attach_kprobe(const struct bpf_program *prog, bool retprobe,
 			   const char *func_name);
 LIBBPF_API struct bpf_link *
-bpf_program__attach_kprobe_opts(struct bpf_program *prog,
+bpf_program__attach_kprobe_opts(const struct bpf_program *prog,
                                 const char *func_name,
                                 const struct bpf_kprobe_opts *opts);
 
@@ -300,11 +300,11 @@ struct bpf_uprobe_opts {
 #define bpf_uprobe_opts__last_field retprobe
 
 LIBBPF_API struct bpf_link *
-bpf_program__attach_uprobe(struct bpf_program *prog, bool retprobe,
+bpf_program__attach_uprobe(const struct bpf_program *prog, bool retprobe,
 			   pid_t pid, const char *binary_path,
 			   size_t func_offset);
 LIBBPF_API struct bpf_link *
-bpf_program__attach_uprobe_opts(struct bpf_program *prog, pid_t pid,
+bpf_program__attach_uprobe_opts(const struct bpf_program *prog, pid_t pid,
 				const char *binary_path, size_t func_offset,
 				const struct bpf_uprobe_opts *opts);
 
@@ -317,35 +317,35 @@ struct bpf_tracepoint_opts {
 #define bpf_tracepoint_opts__last_field bpf_cookie
 
 LIBBPF_API struct bpf_link *
-bpf_program__attach_tracepoint(struct bpf_program *prog,
+bpf_program__attach_tracepoint(const struct bpf_program *prog,
 			       const char *tp_category,
 			       const char *tp_name);
 LIBBPF_API struct bpf_link *
-bpf_program__attach_tracepoint_opts(struct bpf_program *prog,
+bpf_program__attach_tracepoint_opts(const struct bpf_program *prog,
 				    const char *tp_category,
 				    const char *tp_name,
 				    const struct bpf_tracepoint_opts *opts);
 
 LIBBPF_API struct bpf_link *
-bpf_program__attach_raw_tracepoint(struct bpf_program *prog,
+bpf_program__attach_raw_tracepoint(const struct bpf_program *prog,
 				   const char *tp_name);
 LIBBPF_API struct bpf_link *
-bpf_program__attach_trace(struct bpf_program *prog);
+bpf_program__attach_trace(const struct bpf_program *prog);
 LIBBPF_API struct bpf_link *
-bpf_program__attach_lsm(struct bpf_program *prog);
+bpf_program__attach_lsm(const struct bpf_program *prog);
 LIBBPF_API struct bpf_link *
-bpf_program__attach_cgroup(struct bpf_program *prog, int cgroup_fd);
+bpf_program__attach_cgroup(const struct bpf_program *prog, int cgroup_fd);
 LIBBPF_API struct bpf_link *
-bpf_program__attach_netns(struct bpf_program *prog, int netns_fd);
+bpf_program__attach_netns(const struct bpf_program *prog, int netns_fd);
 LIBBPF_API struct bpf_link *
-bpf_program__attach_xdp(struct bpf_program *prog, int ifindex);
+bpf_program__attach_xdp(const struct bpf_program *prog, int ifindex);
 LIBBPF_API struct bpf_link *
-bpf_program__attach_freplace(struct bpf_program *prog,
+bpf_program__attach_freplace(const struct bpf_program *prog,
 			     int target_fd, const char *attach_func_name);
 
 struct bpf_map;
 
-LIBBPF_API struct bpf_link *bpf_map__attach_struct_ops(struct bpf_map *map);
+LIBBPF_API struct bpf_link *bpf_map__attach_struct_ops(const struct bpf_map *map);
 
 struct bpf_iter_attach_opts {
 	size_t sz; /* size of this struct for forward/backward compatibility */
@@ -355,7 +355,7 @@ struct bpf_iter_attach_opts {
 #define bpf_iter_attach_opts__last_field link_info_len
 
 LIBBPF_API struct bpf_link *
-bpf_program__attach_iter(struct bpf_program *prog,
+bpf_program__attach_iter(const struct bpf_program *prog,
 			 const struct bpf_iter_attach_opts *opts);
 
 struct bpf_insn;
-- 
cgit v1.2.3


From ca21a3e5edfd47c90141724557f9d6f5000e46f3 Mon Sep 17 00:00:00 2001
From: Yonghong Song <yhs@fb.com>
Date: Thu, 16 Sep 2021 21:33:43 -0700
Subject: selftests/bpf: Fix a few compiler warnings

With clang building selftests/bpf, I hit a few warnings like below:

  .../bpf_iter.c:592:48: warning: variable 'expected_key_c' set but not used [-Wunused-but-set-variable]
  __u32 expected_key_a = 0, expected_key_b = 0, expected_key_c = 0;
                                                ^

  .../bpf_iter.c:688:48: warning: variable 'expected_key_c' set but not used [-Wunused-but-set-variable]
  __u32 expected_key_a = 0, expected_key_b = 0, expected_key_c = 0;
                                                ^

  .../tc_redirect.c:657:6: warning: variable 'target_fd' is used uninitialized whenever 'if' condition is true [-Wsometimes-uninitialized]
  if (!ASSERT_OK_PTR(nstoken, "setns " NS_FWD))
      ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
  .../tc_redirect.c:743:6: note: uninitialized use occurs here
  if (target_fd >= 0)
      ^~~~~~~~~

Removing unused variables and initializing the previously-uninitialized variable
to ensure these warnings are gone.

Signed-off-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20210917043343.3711917-1-yhs@fb.com
---
 tools/testing/selftests/bpf/prog_tests/bpf_iter.c    | 6 ++----
 tools/testing/selftests/bpf/prog_tests/tc_redirect.c | 2 +-
 2 files changed, 3 insertions(+), 5 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_iter.c b/tools/testing/selftests/bpf/prog_tests/bpf_iter.c
index 77ac24b191d4..9454331aaf85 100644
--- a/tools/testing/selftests/bpf/prog_tests/bpf_iter.c
+++ b/tools/testing/selftests/bpf/prog_tests/bpf_iter.c
@@ -589,7 +589,7 @@ out:
 
 static void test_bpf_hash_map(void)
 {
-	__u32 expected_key_a = 0, expected_key_b = 0, expected_key_c = 0;
+	__u32 expected_key_a = 0, expected_key_b = 0;
 	DECLARE_LIBBPF_OPTS(bpf_iter_attach_opts, opts);
 	struct bpf_iter_bpf_hash_map *skel;
 	int err, i, len, map_fd, iter_fd;
@@ -638,7 +638,6 @@ static void test_bpf_hash_map(void)
 		val = i + 4;
 		expected_key_a += key.a;
 		expected_key_b += key.b;
-		expected_key_c += key.c;
 		expected_val += val;
 
 		err = bpf_map_update_elem(map_fd, &key, &val, BPF_ANY);
@@ -685,7 +684,7 @@ out:
 
 static void test_bpf_percpu_hash_map(void)
 {
-	__u32 expected_key_a = 0, expected_key_b = 0, expected_key_c = 0;
+	__u32 expected_key_a = 0, expected_key_b = 0;
 	DECLARE_LIBBPF_OPTS(bpf_iter_attach_opts, opts);
 	struct bpf_iter_bpf_percpu_hash_map *skel;
 	int err, i, j, len, map_fd, iter_fd;
@@ -722,7 +721,6 @@ static void test_bpf_percpu_hash_map(void)
 		key.c = i + 3;
 		expected_key_a += key.a;
 		expected_key_b += key.b;
-		expected_key_c += key.c;
 
 		for (j = 0; j < bpf_num_possible_cpus(); j++) {
 			*(__u32 *)(val + j * 8) = i + j;
diff --git a/tools/testing/selftests/bpf/prog_tests/tc_redirect.c b/tools/testing/selftests/bpf/prog_tests/tc_redirect.c
index e7201ba29ccd..e87bc4466d9a 100644
--- a/tools/testing/selftests/bpf/prog_tests/tc_redirect.c
+++ b/tools/testing/selftests/bpf/prog_tests/tc_redirect.c
@@ -633,7 +633,7 @@ static void test_tc_redirect_peer_l3(struct netns_setup_result *setup_result)
 	struct nstoken *nstoken = NULL;
 	int err;
 	int tunnel_pid = -1;
-	int src_fd, target_fd;
+	int src_fd, target_fd = -1;
 	int ifindex;
 
 	/* Start a L3 TUN/TAP tunnel between the src and dst namespaces.
-- 
cgit v1.2.3


From 84b4c52960bdccd86d6c3c42a730fd8d0ab75427 Mon Sep 17 00:00:00 2001
From: Dave Marchevsky <davemarchevsky@fb.com>
Date: Fri, 17 Sep 2021 11:29:04 -0700
Subject: selftests/bpf: Stop using bpf_program__load

bpf_program__load is not supposed to be used directly. Replace it with
bpf_object__ APIs for the reference_tracking prog_test, which is the
last offender in bpf selftests.

Some additional complexity is added for this test, namely the use of one
bpf_object to iterate through progs, while a second bpf_object is
created and opened/closed to test actual loading of progs. This is
because the test was doing bpf_program__load then __unload to test
loading of individual progs and same semantics with
bpf_object__load/__unload result in failure to load an __unload-ed obj.

Signed-off-by: Dave Marchevsky <davemarchevsky@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20210917182911.2426606-3-davemarchevsky@fb.com
---
 .../selftests/bpf/prog_tests/reference_tracking.c  | 39 +++++++++++++++++-----
 1 file changed, 31 insertions(+), 8 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/prog_tests/reference_tracking.c b/tools/testing/selftests/bpf/prog_tests/reference_tracking.c
index 4e91f4d6466c..ded2dc8ddd79 100644
--- a/tools/testing/selftests/bpf/prog_tests/reference_tracking.c
+++ b/tools/testing/selftests/bpf/prog_tests/reference_tracking.c
@@ -1,6 +1,21 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <test_progs.h>
 
+static void toggle_object_autoload_progs(const struct bpf_object *obj,
+					 const char *title_load)
+{
+	struct bpf_program *prog;
+
+	bpf_object__for_each_program(prog, obj) {
+		const char *title = bpf_program__section_name(prog);
+
+		if (!strcmp(title_load, title))
+			bpf_program__set_autoload(prog, true);
+		else
+			bpf_program__set_autoload(prog, false);
+	}
+}
+
 void test_reference_tracking(void)
 {
 	const char *file = "test_sk_lookup_kern.o";
@@ -9,21 +24,21 @@ void test_reference_tracking(void)
 		.object_name = obj_name,
 		.relaxed_maps = true,
 	);
-	struct bpf_object *obj;
+	struct bpf_object *obj_iter, *obj = NULL;
 	struct bpf_program *prog;
 	__u32 duration = 0;
 	int err = 0;
 
-	obj = bpf_object__open_file(file, &open_opts);
-	if (!ASSERT_OK_PTR(obj, "obj_open_file"))
+	obj_iter = bpf_object__open_file(file, &open_opts);
+	if (!ASSERT_OK_PTR(obj_iter, "obj_iter_open_file"))
 		return;
 
-	if (CHECK(strcmp(bpf_object__name(obj), obj_name), "obj_name",
+	if (CHECK(strcmp(bpf_object__name(obj_iter), obj_name), "obj_name",
 		  "wrong obj name '%s', expected '%s'\n",
-		  bpf_object__name(obj), obj_name))
+		  bpf_object__name(obj_iter), obj_name))
 		goto cleanup;
 
-	bpf_object__for_each_program(prog, obj) {
+	bpf_object__for_each_program(prog, obj_iter) {
 		const char *title;
 
 		/* Ignore .text sections */
@@ -34,19 +49,27 @@ void test_reference_tracking(void)
 		if (!test__start_subtest(title))
 			continue;
 
+		obj = bpf_object__open_file(file, &open_opts);
+		if (!ASSERT_OK_PTR(obj, "obj_open_file"))
+			goto cleanup;
+
+		toggle_object_autoload_progs(obj, title);
 		/* Expect verifier failure if test name has 'err' */
 		if (strstr(title, "err_") != NULL) {
 			libbpf_print_fn_t old_print_fn;
 
 			old_print_fn = libbpf_set_print(NULL);
-			err = !bpf_program__load(prog, "GPL", 0);
+			err = !bpf_object__load(obj);
 			libbpf_set_print(old_print_fn);
 		} else {
-			err = bpf_program__load(prog, "GPL", 0);
+			err = bpf_object__load(obj);
 		}
 		CHECK(err, title, "\n");
+		bpf_object__close(obj);
+		obj = NULL;
 	}
 
 cleanup:
 	bpf_object__close(obj);
+	bpf_object__close(obj_iter);
 }
-- 
cgit v1.2.3


From 10aceb629e198429c849d5e995c3bb1ba7a9aaa3 Mon Sep 17 00:00:00 2001
From: Dave Marchevsky <davemarchevsky@fb.com>
Date: Fri, 17 Sep 2021 11:29:05 -0700
Subject: bpf: Add bpf_trace_vprintk helper

This helper is meant to be "bpf_trace_printk, but with proper vararg
support". Follow bpf_snprintf's example and take a u64 pseudo-vararg
array. Write to /sys/kernel/debug/tracing/trace_pipe using the same
mechanism as bpf_trace_printk. The functionality of this helper was
requested in the libbpf issue tracker [0].

[0] Closes: https://github.com/libbpf/libbpf/issues/315

Signed-off-by: Dave Marchevsky <davemarchevsky@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20210917182911.2426606-4-davemarchevsky@fb.com
---
 tools/include/uapi/linux/bpf.h | 11 +++++++++++
 1 file changed, 11 insertions(+)

(limited to 'tools')

diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 3e9785f1064a..98ca79a67937 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -4898,6 +4898,16 @@ union bpf_attr {
  *		**-EINVAL** if *flags* is not zero.
  *
  *		**-ENOENT** if architecture does not support branch records.
+ *
+ * long bpf_trace_vprintk(const char *fmt, u32 fmt_size, const void *data, u32 data_len)
+ *	Description
+ *		Behaves like **bpf_trace_printk**\ () helper, but takes an array of u64
+ *		to format and can handle more format args as a result.
+ *
+ *		Arguments are to be used as in **bpf_seq_printf**\ () helper.
+ *	Return
+ *		The number of bytes written to the buffer, or a negative error
+ *		in case of failure.
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -5077,6 +5087,7 @@ union bpf_attr {
 	FN(get_attach_cookie),		\
 	FN(task_pt_regs),		\
 	FN(get_branch_snapshot),	\
+	FN(trace_vprintk),		\
 	/* */
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
-- 
cgit v1.2.3


From c2758baa9798bf75d79a9aad8792edb8b694373e Mon Sep 17 00:00:00 2001
From: Dave Marchevsky <davemarchevsky@fb.com>
Date: Fri, 17 Sep 2021 11:29:06 -0700
Subject: libbpf: Modify bpf_printk to choose helper based on arg count

Instead of being a thin wrapper which calls into bpf_trace_printk,
libbpf's bpf_printk convenience macro now chooses between
bpf_trace_printk and bpf_trace_vprintk. If the arg count (excluding
format string) is >3, use bpf_trace_vprintk, otherwise use the older
helper.

The motivation behind this added complexity - instead of migrating
entirely to bpf_trace_vprintk - is to maintain good developer experience
for users compiling against new libbpf but running on older kernels.
Users who are passing <=3 args to bpf_printk will see no change in their
bytecode.

__bpf_vprintk functions similarly to BPF_SEQ_PRINTF and BPF_SNPRINTF
macros elsewhere in the file - it allows use of bpf_trace_vprintk
without manual conversion of varargs to u64 array. Previous
implementation of bpf_printk macro is moved to __bpf_printk for use by
the new implementation.

This does change behavior of bpf_printk calls with >3 args in the "new
libbpf, old kernels" scenario. Before this patch, attempting to use 4
args to bpf_printk results in a compile-time error. After this patch,
using bpf_printk with 4 args results in a trace_vprintk helper call
being emitted and a load-time failure on older kernels.

Signed-off-by: Dave Marchevsky <davemarchevsky@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20210917182911.2426606-5-davemarchevsky@fb.com
---
 tools/lib/bpf/bpf_helpers.h | 45 +++++++++++++++++++++++++++++++++++++--------
 1 file changed, 37 insertions(+), 8 deletions(-)

(limited to 'tools')

diff --git a/tools/lib/bpf/bpf_helpers.h b/tools/lib/bpf/bpf_helpers.h
index b9987c3efa3c..55a308796625 100644
--- a/tools/lib/bpf/bpf_helpers.h
+++ b/tools/lib/bpf/bpf_helpers.h
@@ -14,14 +14,6 @@
 #define __type(name, val) typeof(val) *name
 #define __array(name, val) typeof(val) *name[]
 
-/* Helper macro to print out debug messages */
-#define bpf_printk(fmt, ...)				\
-({							\
-	char ____fmt[] = fmt;				\
-	bpf_trace_printk(____fmt, sizeof(____fmt),	\
-			 ##__VA_ARGS__);		\
-})
-
 /*
  * Helper macro to place programs, maps, license in
  * different sections in elf_bpf file. Section names
@@ -224,4 +216,41 @@ enum libbpf_tristate {
 		     ___param, sizeof(___param));		\
 })
 
+#define __bpf_printk(fmt, ...)				\
+({							\
+	char ____fmt[] = fmt;				\
+	bpf_trace_printk(____fmt, sizeof(____fmt),	\
+			 ##__VA_ARGS__);		\
+})
+
+/*
+ * __bpf_vprintk wraps the bpf_trace_vprintk helper with variadic arguments
+ * instead of an array of u64.
+ */
+#define __bpf_vprintk(fmt, args...)				\
+({								\
+	static const char ___fmt[] = fmt;			\
+	unsigned long long ___param[___bpf_narg(args)];		\
+								\
+	_Pragma("GCC diagnostic push")				\
+	_Pragma("GCC diagnostic ignored \"-Wint-conversion\"")	\
+	___bpf_fill(___param, args);				\
+	_Pragma("GCC diagnostic pop")				\
+								\
+	bpf_trace_vprintk(___fmt, sizeof(___fmt),		\
+			  ___param, sizeof(___param));		\
+})
+
+/* Use __bpf_printk when bpf_printk call has 3 or fewer fmt args
+ * Otherwise use __bpf_vprintk
+ */
+#define ___bpf_pick_printk(...) \
+	___bpf_nth(_, ##__VA_ARGS__, __bpf_vprintk, __bpf_vprintk, __bpf_vprintk,	\
+		   __bpf_vprintk, __bpf_vprintk, __bpf_vprintk, __bpf_vprintk,		\
+		   __bpf_vprintk, __bpf_vprintk, __bpf_printk /*3*/, __bpf_printk /*2*/,\
+		   __bpf_printk /*1*/, __bpf_printk /*0*/)
+
+/* Helper macro to print out debug messages */
+#define bpf_printk(fmt, args...) ___bpf_pick_printk(args)(fmt, ##args)
+
 #endif
-- 
cgit v1.2.3


From 6c66b0e7c91a1320c1b85ad8150bdd534eb4ddae Mon Sep 17 00:00:00 2001
From: Dave Marchevsky <davemarchevsky@fb.com>
Date: Fri, 17 Sep 2021 11:29:07 -0700
Subject: libbpf: Use static const fmt string in __bpf_printk

The __bpf_printk convenience macro was using a 'char' fmt string holder
as it predates support for globals in libbpf. Move to more efficient
'static const char', but provide a fallback to the old way via
BPF_NO_GLOBAL_DATA so users on old kernels can still use the macro.

Signed-off-by: Dave Marchevsky <davemarchevsky@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20210917182911.2426606-6-davemarchevsky@fb.com
---
 tools/lib/bpf/bpf_helpers.h | 8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)

(limited to 'tools')

diff --git a/tools/lib/bpf/bpf_helpers.h b/tools/lib/bpf/bpf_helpers.h
index 55a308796625..963b1060d944 100644
--- a/tools/lib/bpf/bpf_helpers.h
+++ b/tools/lib/bpf/bpf_helpers.h
@@ -216,9 +216,15 @@ enum libbpf_tristate {
 		     ___param, sizeof(___param));		\
 })
 
+#ifdef BPF_NO_GLOBAL_DATA
+#define BPF_PRINTK_FMT_MOD
+#else
+#define BPF_PRINTK_FMT_MOD static const
+#endif
+
 #define __bpf_printk(fmt, ...)				\
 ({							\
-	char ____fmt[] = fmt;				\
+	BPF_PRINTK_FMT_MOD char ____fmt[] = fmt;	\
 	bpf_trace_printk(____fmt, sizeof(____fmt),	\
 			 ##__VA_ARGS__);		\
 })
-- 
cgit v1.2.3


From 4190c299a49f323232221e73fe1846c53e3fc3f1 Mon Sep 17 00:00:00 2001
From: Dave Marchevsky <davemarchevsky@fb.com>
Date: Fri, 17 Sep 2021 11:29:08 -0700
Subject: bpftool: Only probe trace_vprintk feature in 'full' mode

Since commit 368cb0e7cdb5e ("bpftool: Make probes which emit dmesg
warnings optional"), some helpers aren't probed by bpftool unless
`full` arg is added to `bpftool feature probe`.

bpf_trace_vprintk can emit dmesg warnings when probed, so include it.

Signed-off-by: Dave Marchevsky <davemarchevsky@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20210917182911.2426606-7-davemarchevsky@fb.com
---
 tools/bpf/bpftool/feature.c                 |  1 +
 tools/testing/selftests/bpf/test_bpftool.py | 22 +++++++++-------------
 2 files changed, 10 insertions(+), 13 deletions(-)

(limited to 'tools')

diff --git a/tools/bpf/bpftool/feature.c b/tools/bpf/bpftool/feature.c
index 7f36385aa9e2..ade44577688e 100644
--- a/tools/bpf/bpftool/feature.c
+++ b/tools/bpf/bpftool/feature.c
@@ -624,6 +624,7 @@ probe_helpers_for_progtype(enum bpf_prog_type prog_type, bool supported_type,
 		 */
 		switch (id) {
 		case BPF_FUNC_trace_printk:
+		case BPF_FUNC_trace_vprintk:
 		case BPF_FUNC_probe_write_user:
 			if (!full_mode)
 				continue;
diff --git a/tools/testing/selftests/bpf/test_bpftool.py b/tools/testing/selftests/bpf/test_bpftool.py
index 4fed2dc25c0a..1c2408ee1f5d 100644
--- a/tools/testing/selftests/bpf/test_bpftool.py
+++ b/tools/testing/selftests/bpf/test_bpftool.py
@@ -57,6 +57,11 @@ def default_iface(f):
         return f(*args, iface, **kwargs)
     return wrapper
 
+DMESG_EMITTING_HELPERS = [
+        "bpf_probe_write_user",
+        "bpf_trace_printk",
+        "bpf_trace_vprintk",
+    ]
 
 class TestBpftool(unittest.TestCase):
     @classmethod
@@ -67,10 +72,7 @@ class TestBpftool(unittest.TestCase):
 
     @default_iface
     def test_feature_dev_json(self, iface):
-        unexpected_helpers = [
-            "bpf_probe_write_user",
-            "bpf_trace_printk",
-        ]
+        unexpected_helpers = DMESG_EMITTING_HELPERS
         expected_keys = [
             "syscall_config",
             "program_types",
@@ -94,10 +96,7 @@ class TestBpftool(unittest.TestCase):
             bpftool_json(["feature", "probe"]),
             bpftool_json(["feature"]),
         ]
-        unexpected_helpers = [
-            "bpf_probe_write_user",
-            "bpf_trace_printk",
-        ]
+        unexpected_helpers = DMESG_EMITTING_HELPERS
         expected_keys = [
             "syscall_config",
             "system_config",
@@ -121,10 +120,7 @@ class TestBpftool(unittest.TestCase):
             bpftool_json(["feature", "probe", "kernel", "full"]),
             bpftool_json(["feature", "probe", "full"]),
         ]
-        expected_helpers = [
-            "bpf_probe_write_user",
-            "bpf_trace_printk",
-        ]
+        expected_helpers = DMESG_EMITTING_HELPERS
 
         for tc in test_cases:
             # Check if expected helpers are included at least once in any
@@ -157,7 +153,7 @@ class TestBpftool(unittest.TestCase):
                 not_full_set.add(helper)
 
         self.assertCountEqual(full_set - not_full_set,
-                                {"bpf_probe_write_user", "bpf_trace_printk"})
+                              set(DMESG_EMITTING_HELPERS))
         self.assertCountEqual(not_full_set - full_set, set())
 
     def test_feature_macros(self):
-- 
cgit v1.2.3


From d313d45a226fdc59739c3da05bbd065f71bae5a6 Mon Sep 17 00:00:00 2001
From: Dave Marchevsky <davemarchevsky@fb.com>
Date: Fri, 17 Sep 2021 11:29:09 -0700
Subject: selftests/bpf: Migrate prog_tests/trace_printk CHECKs to ASSERTs

Guidance for new tests is to use ASSERT macros instead of CHECK. Since
trace_vprintk test will borrow heavily from trace_printk's, migrate its
CHECKs so it remains obvious that the two are closely related.

Signed-off-by: Dave Marchevsky <davemarchevsky@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20210917182911.2426606-8-davemarchevsky@fb.com
---
 .../selftests/bpf/prog_tests/trace_printk.c        | 24 ++++++++--------------
 1 file changed, 9 insertions(+), 15 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/prog_tests/trace_printk.c b/tools/testing/selftests/bpf/prog_tests/trace_printk.c
index d39bc00feb45..e47835f0a674 100644
--- a/tools/testing/selftests/bpf/prog_tests/trace_printk.c
+++ b/tools/testing/selftests/bpf/prog_tests/trace_printk.c
@@ -10,7 +10,7 @@
 
 void test_trace_printk(void)
 {
-	int err, iter = 0, duration = 0, found = 0;
+	int err = 0, iter = 0, found = 0;
 	struct trace_printk__bss *bss;
 	struct trace_printk *skel;
 	char *buf = NULL;
@@ -18,25 +18,24 @@ void test_trace_printk(void)
 	size_t buflen;
 
 	skel = trace_printk__open();
-	if (CHECK(!skel, "skel_open", "failed to open skeleton\n"))
+	if (!ASSERT_OK_PTR(skel, "trace_printk__open"))
 		return;
 
-	ASSERT_EQ(skel->rodata->fmt[0], 'T', "invalid printk fmt string");
+	ASSERT_EQ(skel->rodata->fmt[0], 'T', "skel->rodata->fmt[0]");
 	skel->rodata->fmt[0] = 't';
 
 	err = trace_printk__load(skel);
-	if (CHECK(err, "skel_load", "failed to load skeleton: %d\n", err))
+	if (!ASSERT_OK(err, "trace_printk__load"))
 		goto cleanup;
 
 	bss = skel->bss;
 
 	err = trace_printk__attach(skel);
-	if (CHECK(err, "skel_attach", "skeleton attach failed: %d\n", err))
+	if (!ASSERT_OK(err, "trace_printk__attach"))
 		goto cleanup;
 
 	fp = fopen(TRACEBUF, "r");
-	if (CHECK(fp == NULL, "could not open trace buffer",
-		  "error %d opening %s", errno, TRACEBUF))
+	if (!ASSERT_OK_PTR(fp, "fopen(TRACEBUF)"))
 		goto cleanup;
 
 	/* We do not want to wait forever if this test fails... */
@@ -46,14 +45,10 @@ void test_trace_printk(void)
 	usleep(1);
 	trace_printk__detach(skel);
 
-	if (CHECK(bss->trace_printk_ran == 0,
-		  "bpf_trace_printk never ran",
-		  "ran == %d", bss->trace_printk_ran))
+	if (!ASSERT_GT(bss->trace_printk_ran, 0, "bss->trace_printk_ran"))
 		goto cleanup;
 
-	if (CHECK(bss->trace_printk_ret <= 0,
-		  "bpf_trace_printk returned <= 0 value",
-		  "got %d", bss->trace_printk_ret))
+	if (!ASSERT_GT(bss->trace_printk_ret, 0, "bss->trace_printk_ret"))
 		goto cleanup;
 
 	/* verify our search string is in the trace buffer */
@@ -66,8 +61,7 @@ void test_trace_printk(void)
 			break;
 	}
 
-	if (CHECK(!found, "message from bpf_trace_printk not found",
-		  "no instance of %s in %s", SEARCHMSG, TRACEBUF))
+	if (!ASSERT_EQ(found, bss->trace_printk_ran, "found"))
 		goto cleanup;
 
 cleanup:
-- 
cgit v1.2.3


From 7606729fe24e163923430a5df9d50a246b22d287 Mon Sep 17 00:00:00 2001
From: Dave Marchevsky <davemarchevsky@fb.com>
Date: Fri, 17 Sep 2021 11:29:10 -0700
Subject: selftests/bpf: Add trace_vprintk test prog

This commit adds a test prog for vprintk which confirms that:
  * bpf_trace_vprintk is writing to /sys/kernel/debug/tracing/trace_pipe
  * __bpf_vprintk macro works as expected
  * >3 args are printed
  * bpf_printk w/ 0 format args compiles
  * bpf_trace_vprintk call w/ a fmt specifier but NULL fmt data fails

Approach and code are borrowed from trace_printk test.

Signed-off-by: Dave Marchevsky <davemarchevsky@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20210917182911.2426606-9-davemarchevsky@fb.com
---
 tools/testing/selftests/bpf/Makefile               |  3 +-
 .../selftests/bpf/prog_tests/trace_vprintk.c       | 68 ++++++++++++++++++++++
 tools/testing/selftests/bpf/progs/trace_vprintk.c  | 33 +++++++++++
 3 files changed, 103 insertions(+), 1 deletion(-)
 create mode 100644 tools/testing/selftests/bpf/prog_tests/trace_vprintk.c
 create mode 100644 tools/testing/selftests/bpf/progs/trace_vprintk.c

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index 1a4d30ff3275..326ea75ce99e 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -315,7 +315,8 @@ LINKED_SKELS := test_static_linked.skel.h linked_funcs.skel.h		\
 		linked_vars.skel.h linked_maps.skel.h
 
 LSKELS := kfunc_call_test.c fentry_test.c fexit_test.c fexit_sleep.c \
-	test_ksyms_module.c test_ringbuf.c atomics.c trace_printk.c
+	test_ksyms_module.c test_ringbuf.c atomics.c trace_printk.c \
+	trace_vprintk.c
 SKEL_BLACKLIST += $$(LSKELS)
 
 test_static_linked.skel.h-deps := test_static_linked1.o test_static_linked2.o
diff --git a/tools/testing/selftests/bpf/prog_tests/trace_vprintk.c b/tools/testing/selftests/bpf/prog_tests/trace_vprintk.c
new file mode 100644
index 000000000000..61a24e62e1a0
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/trace_vprintk.c
@@ -0,0 +1,68 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2021 Facebook */
+
+#include <test_progs.h>
+
+#include "trace_vprintk.lskel.h"
+
+#define TRACEBUF	"/sys/kernel/debug/tracing/trace_pipe"
+#define SEARCHMSG	"1,2,3,4,5,6,7,8,9,10"
+
+void test_trace_vprintk(void)
+{
+	int err = 0, iter = 0, found = 0;
+	struct trace_vprintk__bss *bss;
+	struct trace_vprintk *skel;
+	char *buf = NULL;
+	FILE *fp = NULL;
+	size_t buflen;
+
+	skel = trace_vprintk__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "trace_vprintk__open_and_load"))
+		goto cleanup;
+
+	bss = skel->bss;
+
+	err = trace_vprintk__attach(skel);
+	if (!ASSERT_OK(err, "trace_vprintk__attach"))
+		goto cleanup;
+
+	fp = fopen(TRACEBUF, "r");
+	if (!ASSERT_OK_PTR(fp, "fopen(TRACEBUF)"))
+		goto cleanup;
+
+	/* We do not want to wait forever if this test fails... */
+	fcntl(fileno(fp), F_SETFL, O_NONBLOCK);
+
+	/* wait for tracepoint to trigger */
+	usleep(1);
+	trace_vprintk__detach(skel);
+
+	if (!ASSERT_GT(bss->trace_vprintk_ran, 0, "bss->trace_vprintk_ran"))
+		goto cleanup;
+
+	if (!ASSERT_GT(bss->trace_vprintk_ret, 0, "bss->trace_vprintk_ret"))
+		goto cleanup;
+
+	/* verify our search string is in the trace buffer */
+	while (getline(&buf, &buflen, fp) >= 0 || errno == EAGAIN) {
+		if (strstr(buf, SEARCHMSG) != NULL)
+			found++;
+		if (found == bss->trace_vprintk_ran)
+			break;
+		if (++iter > 1000)
+			break;
+	}
+
+	if (!ASSERT_EQ(found, bss->trace_vprintk_ran, "found"))
+		goto cleanup;
+
+	if (!ASSERT_LT(bss->null_data_vprintk_ret, 0, "bss->null_data_vprintk_ret"))
+		goto cleanup;
+
+cleanup:
+	trace_vprintk__destroy(skel);
+	free(buf);
+	if (fp)
+		fclose(fp);
+}
diff --git a/tools/testing/selftests/bpf/progs/trace_vprintk.c b/tools/testing/selftests/bpf/progs/trace_vprintk.c
new file mode 100644
index 000000000000..d327241ba047
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/trace_vprintk.c
@@ -0,0 +1,33 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2021 Facebook */
+
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+
+char _license[] SEC("license") = "GPL";
+
+int null_data_vprintk_ret = 0;
+int trace_vprintk_ret = 0;
+int trace_vprintk_ran = 0;
+
+SEC("fentry/__x64_sys_nanosleep")
+int sys_enter(void *ctx)
+{
+	static const char one[] = "1";
+	static const char three[] = "3";
+	static const char five[] = "5";
+	static const char seven[] = "7";
+	static const char nine[] = "9";
+	static const char f[] = "%pS\n";
+
+	/* runner doesn't search for \t, just ensure it compiles */
+	bpf_printk("\t");
+
+	trace_vprintk_ret = __bpf_vprintk("%s,%d,%s,%d,%s,%d,%s,%d,%s,%d %d\n",
+		one, 2, three, 4, five, 6, seven, 8, nine, 10, ++trace_vprintk_ran);
+
+	/* non-NULL fmt w/ NULL data should result in error */
+	null_data_vprintk_ret = bpf_trace_vprintk(f, sizeof(f), NULL, 0);
+	return 0;
+}
-- 
cgit v1.2.3


From a42effb0b24fcaf49513c2d7d77ef6daa9e32a6f Mon Sep 17 00:00:00 2001
From: Dave Marchevsky <davemarchevsky@fb.com>
Date: Fri, 17 Sep 2021 11:29:11 -0700
Subject: bpf: Clarify data_len param in bpf_snprintf and bpf_seq_printf
 comments

Since the data_len in these two functions is a byte len of the preceding
u64 *data array, it must always be a multiple of 8. If this isn't the
case both helpers error out, so let's make the requirement explicit so
users don't need to infer it.

Signed-off-by: Dave Marchevsky <davemarchevsky@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20210917182911.2426606-10-davemarchevsky@fb.com
---
 tools/include/uapi/linux/bpf.h | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

(limited to 'tools')

diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 98ca79a67937..6fc59d61937a 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -4046,7 +4046,7 @@ union bpf_attr {
  * 		arguments. The *data* are a **u64** array and corresponding format string
  * 		values are stored in the array. For strings and pointers where pointees
  * 		are accessed, only the pointer values are stored in the *data* array.
- * 		The *data_len* is the size of *data* in bytes.
+ * 		The *data_len* is the size of *data* in bytes - must be a multiple of 8.
  *
  *		Formats **%s**, **%p{i,I}{4,6}** requires to read kernel memory.
  *		Reading kernel memory may fail due to either invalid address or
@@ -4751,7 +4751,8 @@ union bpf_attr {
  *		Each format specifier in **fmt** corresponds to one u64 element
  *		in the **data** array. For strings and pointers where pointees
  *		are accessed, only the pointer values are stored in the *data*
- *		array. The *data_len* is the size of *data* in bytes.
+ *		array. The *data_len* is the size of *data* in bytes - must be
+ *		a multiple of 8.
  *
  *		Formats **%s** and **%p{i,I}{4,6}** require to read kernel
  *		memory. Reading kernel memory may fail due to either invalid
-- 
cgit v1.2.3


From ce9979129a0ba700112151a83a6d4cf09c7a1158 Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Fri, 17 Sep 2021 16:33:22 -0700
Subject: selftests: mptcp: add mptcp getsockopt test cases

Add a test program that retrieves the three info types:
1. mptcp meta information
2. tcp info for subflow
3. subflow endpoint addresses

For all three rudimentary checks are added.

1. Meta information checks that the logical mptcp
   sequence numbers advance as expected, based on the bytes read
   (init seq + bytes_received/sent) and the connection state
   (after close, we should exect 1 extra byte due to FIN).

2. TCP info checks the number of bytes sent/received vs.
   sums of read/write syscall return values.

3. Subflow endpoint addresses are checked vs. getsockname/getpeername
   result.

Tests for forward compatibility (0-initialisation of output-only
fields in mptcp_subflow_data structure) are added as well.

Co-developed-by: Matthieu Baerts <matthieu.baerts@tessares.net>
Signed-off-by: Matthieu Baerts <matthieu.baerts@tessares.net>
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Mat Martineau <mathew.j.martineau@linux.intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/mptcp/.gitignore       |   1 +
 tools/testing/selftests/net/mptcp/Makefile         |   2 +-
 tools/testing/selftests/net/mptcp/mptcp_sockopt.c  | 683 +++++++++++++++++++++
 tools/testing/selftests/net/mptcp/mptcp_sockopt.sh |  31 +-
 4 files changed, 714 insertions(+), 3 deletions(-)
 create mode 100644 tools/testing/selftests/net/mptcp/mptcp_sockopt.c

(limited to 'tools')

diff --git a/tools/testing/selftests/net/mptcp/.gitignore b/tools/testing/selftests/net/mptcp/.gitignore
index 260336d5f0b1..7569d892967a 100644
--- a/tools/testing/selftests/net/mptcp/.gitignore
+++ b/tools/testing/selftests/net/mptcp/.gitignore
@@ -1,4 +1,5 @@
 # SPDX-License-Identifier: GPL-2.0-only
 mptcp_connect
+mptcp_sockopt
 pm_nl_ctl
 *.pcap
diff --git a/tools/testing/selftests/net/mptcp/Makefile b/tools/testing/selftests/net/mptcp/Makefile
index f1464f09b080..bbf4e448bad9 100644
--- a/tools/testing/selftests/net/mptcp/Makefile
+++ b/tools/testing/selftests/net/mptcp/Makefile
@@ -8,7 +8,7 @@ CFLAGS =  -Wall -Wl,--no-as-needed -O2 -g  -I$(top_srcdir)/usr/include
 TEST_PROGS := mptcp_connect.sh pm_netlink.sh mptcp_join.sh diag.sh \
 	      simult_flows.sh mptcp_sockopt.sh
 
-TEST_GEN_FILES = mptcp_connect pm_nl_ctl
+TEST_GEN_FILES = mptcp_connect pm_nl_ctl mptcp_sockopt
 
 TEST_FILES := settings
 
diff --git a/tools/testing/selftests/net/mptcp/mptcp_sockopt.c b/tools/testing/selftests/net/mptcp/mptcp_sockopt.c
new file mode 100644
index 000000000000..417b11cafafe
--- /dev/null
+++ b/tools/testing/selftests/net/mptcp/mptcp_sockopt.c
@@ -0,0 +1,683 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#define _GNU_SOURCE
+
+#include <assert.h>
+#include <errno.h>
+#include <limits.h>
+#include <string.h>
+#include <stdarg.h>
+#include <stdbool.h>
+#include <stdint.h>
+#include <inttypes.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <strings.h>
+#include <unistd.h>
+
+#include <sys/socket.h>
+#include <sys/types.h>
+#include <sys/wait.h>
+
+#include <netdb.h>
+#include <netinet/in.h>
+
+#include <linux/tcp.h>
+
+static int pf = AF_INET;
+
+#ifndef IPPROTO_MPTCP
+#define IPPROTO_MPTCP 262
+#endif
+#ifndef SOL_MPTCP
+#define SOL_MPTCP 284
+#endif
+
+#ifndef MPTCP_INFO
+struct mptcp_info {
+	__u8	mptcpi_subflows;
+	__u8	mptcpi_add_addr_signal;
+	__u8	mptcpi_add_addr_accepted;
+	__u8	mptcpi_subflows_max;
+	__u8	mptcpi_add_addr_signal_max;
+	__u8	mptcpi_add_addr_accepted_max;
+	__u32	mptcpi_flags;
+	__u32	mptcpi_token;
+	__u64	mptcpi_write_seq;
+	__u64	mptcpi_snd_una;
+	__u64	mptcpi_rcv_nxt;
+	__u8	mptcpi_local_addr_used;
+	__u8	mptcpi_local_addr_max;
+	__u8	mptcpi_csum_enabled;
+};
+
+struct mptcp_subflow_data {
+	__u32		size_subflow_data;		/* size of this structure in userspace */
+	__u32		num_subflows;			/* must be 0, set by kernel */
+	__u32		size_kernel;			/* must be 0, set by kernel */
+	__u32		size_user;			/* size of one element in data[] */
+} __attribute__((aligned(8)));
+
+struct mptcp_subflow_addrs {
+	union {
+		__kernel_sa_family_t sa_family;
+		struct sockaddr sa_local;
+		struct sockaddr_in sin_local;
+		struct sockaddr_in6 sin6_local;
+		struct __kernel_sockaddr_storage ss_local;
+	};
+	union {
+		struct sockaddr sa_remote;
+		struct sockaddr_in sin_remote;
+		struct sockaddr_in6 sin6_remote;
+		struct __kernel_sockaddr_storage ss_remote;
+	};
+};
+
+#define MPTCP_INFO		1
+#define MPTCP_TCPINFO		2
+#define MPTCP_SUBFLOW_ADDRS	3
+#endif
+
+struct so_state {
+	struct mptcp_info mi;
+	uint64_t mptcpi_rcv_delta;
+	uint64_t tcpi_rcv_delta;
+};
+
+static void die_perror(const char *msg)
+{
+	perror(msg);
+	exit(1);
+}
+
+static void die_usage(int r)
+{
+	fprintf(stderr, "Usage: mptcp_sockopt [-6]\n");
+	exit(r);
+}
+
+static void xerror(const char *fmt, ...)
+{
+	va_list ap;
+
+	va_start(ap, fmt);
+	vfprintf(stderr, fmt, ap);
+	va_end(ap);
+	fputc('\n', stderr);
+	exit(1);
+}
+
+static const char *getxinfo_strerr(int err)
+{
+	if (err == EAI_SYSTEM)
+		return strerror(errno);
+
+	return gai_strerror(err);
+}
+
+static void xgetaddrinfo(const char *node, const char *service,
+			 const struct addrinfo *hints,
+			 struct addrinfo **res)
+{
+	int err = getaddrinfo(node, service, hints, res);
+
+	if (err) {
+		const char *errstr = getxinfo_strerr(err);
+
+		fprintf(stderr, "Fatal: getaddrinfo(%s:%s): %s\n",
+			node ? node : "", service ? service : "", errstr);
+		exit(1);
+	}
+}
+
+static int sock_listen_mptcp(const char * const listenaddr,
+			     const char * const port)
+{
+	int sock;
+	struct addrinfo hints = {
+		.ai_protocol = IPPROTO_TCP,
+		.ai_socktype = SOCK_STREAM,
+		.ai_flags = AI_PASSIVE | AI_NUMERICHOST
+	};
+
+	hints.ai_family = pf;
+
+	struct addrinfo *a, *addr;
+	int one = 1;
+
+	xgetaddrinfo(listenaddr, port, &hints, &addr);
+	hints.ai_family = pf;
+
+	for (a = addr; a; a = a->ai_next) {
+		sock = socket(a->ai_family, a->ai_socktype, IPPROTO_MPTCP);
+		if (sock < 0)
+			continue;
+
+		if (-1 == setsockopt(sock, SOL_SOCKET, SO_REUSEADDR, &one,
+				     sizeof(one)))
+			perror("setsockopt");
+
+		if (bind(sock, a->ai_addr, a->ai_addrlen) == 0)
+			break; /* success */
+
+		perror("bind");
+		close(sock);
+		sock = -1;
+	}
+
+	freeaddrinfo(addr);
+
+	if (sock < 0)
+		xerror("could not create listen socket");
+
+	if (listen(sock, 20))
+		die_perror("listen");
+
+	return sock;
+}
+
+static int sock_connect_mptcp(const char * const remoteaddr,
+			      const char * const port, int proto)
+{
+	struct addrinfo hints = {
+		.ai_protocol = IPPROTO_TCP,
+		.ai_socktype = SOCK_STREAM,
+	};
+	struct addrinfo *a, *addr;
+	int sock = -1;
+
+	hints.ai_family = pf;
+
+	xgetaddrinfo(remoteaddr, port, &hints, &addr);
+	for (a = addr; a; a = a->ai_next) {
+		sock = socket(a->ai_family, a->ai_socktype, proto);
+		if (sock < 0)
+			continue;
+
+		if (connect(sock, a->ai_addr, a->ai_addrlen) == 0)
+			break; /* success */
+
+		die_perror("connect");
+	}
+
+	if (sock < 0)
+		xerror("could not create connect socket");
+
+	freeaddrinfo(addr);
+	return sock;
+}
+
+static void parse_opts(int argc, char **argv)
+{
+	int c;
+
+	while ((c = getopt(argc, argv, "h6")) != -1) {
+		switch (c) {
+		case 'h':
+			die_usage(0);
+			break;
+		case '6':
+			pf = AF_INET6;
+			break;
+		default:
+			die_usage(1);
+			break;
+		}
+	}
+}
+
+static void do_getsockopt_bogus_sf_data(int fd, int optname)
+{
+	struct mptcp_subflow_data good_data;
+	struct bogus_data {
+		struct mptcp_subflow_data d;
+		char buf[2];
+	} bd;
+	socklen_t olen, _olen;
+	int ret;
+
+	memset(&bd, 0, sizeof(bd));
+	memset(&good_data, 0, sizeof(good_data));
+
+	olen = sizeof(good_data);
+	good_data.size_subflow_data = olen;
+
+	ret = getsockopt(fd, SOL_MPTCP, optname, &bd, &olen);
+	assert(ret < 0); /* 0 size_subflow_data */
+	assert(olen == sizeof(good_data));
+
+	bd.d = good_data;
+
+	ret = getsockopt(fd, SOL_MPTCP, optname, &bd, &olen);
+	assert(ret == 0);
+	assert(olen == sizeof(good_data));
+	assert(bd.d.num_subflows == 1);
+	assert(bd.d.size_kernel > 0);
+	assert(bd.d.size_user == 0);
+
+	bd.d = good_data;
+	_olen = rand() % olen;
+	olen = _olen;
+	ret = getsockopt(fd, SOL_MPTCP, optname, &bd, &olen);
+	assert(ret < 0);	/* bogus olen */
+	assert(olen == _olen);	/* must be unchanged */
+
+	bd.d = good_data;
+	olen = sizeof(good_data);
+	bd.d.size_kernel = 1;
+	ret = getsockopt(fd, SOL_MPTCP, optname, &bd, &olen);
+	assert(ret < 0); /* size_kernel not 0 */
+
+	bd.d = good_data;
+	olen = sizeof(good_data);
+	bd.d.num_subflows = 1;
+	ret = getsockopt(fd, SOL_MPTCP, optname, &bd, &olen);
+	assert(ret < 0); /* num_subflows not 0 */
+
+	/* forward compat check: larger struct mptcp_subflow_data on 'old' kernel */
+	bd.d = good_data;
+	olen = sizeof(bd);
+	bd.d.size_subflow_data = sizeof(bd);
+
+	ret = getsockopt(fd, SOL_MPTCP, optname, &bd, &olen);
+	assert(ret == 0);
+
+	/* olen must be truncated to real data size filled by kernel: */
+	assert(olen == sizeof(good_data));
+
+	assert(bd.d.size_subflow_data == sizeof(bd));
+
+	bd.d = good_data;
+	bd.d.size_subflow_data += 1;
+	bd.d.size_user = 1;
+	olen = bd.d.size_subflow_data + 1;
+	_olen = olen;
+
+	ret = getsockopt(fd, SOL_MPTCP, optname, &bd, &_olen);
+	assert(ret == 0);
+
+	/* no truncation, kernel should have filled 1 byte of optname payload in buf[1]: */
+	assert(olen == _olen);
+
+	assert(bd.d.size_subflow_data == sizeof(good_data) + 1);
+	assert(bd.buf[0] == 0);
+}
+
+static void do_getsockopt_mptcp_info(struct so_state *s, int fd, size_t w)
+{
+	struct mptcp_info i;
+	socklen_t olen;
+	int ret;
+
+	olen = sizeof(i);
+	ret = getsockopt(fd, SOL_MPTCP, MPTCP_INFO, &i, &olen);
+
+	if (ret < 0)
+		die_perror("getsockopt MPTCP_INFO");
+
+	assert(olen == sizeof(i));
+
+	if (s->mi.mptcpi_write_seq == 0)
+		s->mi = i;
+
+	assert(s->mi.mptcpi_write_seq + w == i.mptcpi_write_seq);
+
+	s->mptcpi_rcv_delta = i.mptcpi_rcv_nxt - s->mi.mptcpi_rcv_nxt;
+}
+
+static void do_getsockopt_tcp_info(struct so_state *s, int fd, size_t r, size_t w)
+{
+	struct my_tcp_info {
+		struct mptcp_subflow_data d;
+		struct tcp_info ti[2];
+	} ti;
+	int ret, tries = 5;
+	socklen_t olen;
+
+	do {
+		memset(&ti, 0, sizeof(ti));
+
+		ti.d.size_subflow_data = sizeof(struct mptcp_subflow_data);
+		ti.d.size_user = sizeof(struct tcp_info);
+		olen = sizeof(ti);
+
+		ret = getsockopt(fd, SOL_MPTCP, MPTCP_TCPINFO, &ti, &olen);
+		if (ret < 0)
+			xerror("getsockopt MPTCP_TCPINFO (tries %d, %m)");
+
+		assert(olen <= sizeof(ti));
+		assert(ti.d.size_user == ti.d.size_kernel);
+		assert(ti.d.size_user == sizeof(struct tcp_info));
+		assert(ti.d.num_subflows == 1);
+
+		assert(olen > (socklen_t)sizeof(struct mptcp_subflow_data));
+		olen -= sizeof(struct mptcp_subflow_data);
+		assert(olen == sizeof(struct tcp_info));
+
+		if (ti.ti[0].tcpi_bytes_sent == w &&
+		    ti.ti[0].tcpi_bytes_received == r)
+			goto done;
+
+		if (r == 0 && ti.ti[0].tcpi_bytes_sent == w &&
+		    ti.ti[0].tcpi_bytes_received) {
+			s->tcpi_rcv_delta = ti.ti[0].tcpi_bytes_received;
+			goto done;
+		}
+
+		/* wait and repeat, might be that tx is still ongoing */
+		sleep(1);
+	} while (tries-- > 0);
+
+	xerror("tcpi_bytes_sent %" PRIu64 ", want %zu. tcpi_bytes_received %" PRIu64 ", want %zu",
+		ti.ti[0].tcpi_bytes_sent, w, ti.ti[0].tcpi_bytes_received, r);
+
+done:
+	do_getsockopt_bogus_sf_data(fd, MPTCP_TCPINFO);
+}
+
+static void do_getsockopt_subflow_addrs(int fd)
+{
+	struct sockaddr_storage remote, local;
+	socklen_t olen, rlen, llen;
+	int ret;
+	struct my_addrs {
+		struct mptcp_subflow_data d;
+		struct mptcp_subflow_addrs addr[2];
+	} addrs;
+
+	memset(&addrs, 0, sizeof(addrs));
+	memset(&local, 0, sizeof(local));
+	memset(&remote, 0, sizeof(remote));
+
+	addrs.d.size_subflow_data = sizeof(struct mptcp_subflow_data);
+	addrs.d.size_user = sizeof(struct mptcp_subflow_addrs);
+	olen = sizeof(addrs);
+
+	ret = getsockopt(fd, SOL_MPTCP, MPTCP_SUBFLOW_ADDRS, &addrs, &olen);
+	if (ret < 0)
+		die_perror("getsockopt MPTCP_SUBFLOW_ADDRS");
+
+	assert(olen <= sizeof(addrs));
+	assert(addrs.d.size_user == addrs.d.size_kernel);
+	assert(addrs.d.size_user == sizeof(struct mptcp_subflow_addrs));
+	assert(addrs.d.num_subflows == 1);
+
+	assert(olen > (socklen_t)sizeof(struct mptcp_subflow_data));
+	olen -= sizeof(struct mptcp_subflow_data);
+	assert(olen == sizeof(struct mptcp_subflow_addrs));
+
+	llen = sizeof(local);
+	ret = getsockname(fd, (struct sockaddr *)&local, &llen);
+	if (ret < 0)
+		die_perror("getsockname");
+	rlen = sizeof(remote);
+	ret = getpeername(fd, (struct sockaddr *)&remote, &rlen);
+	if (ret < 0)
+		die_perror("getpeername");
+
+	assert(rlen > 0);
+	assert(rlen == llen);
+
+	assert(remote.ss_family == local.ss_family);
+
+	assert(memcmp(&local, &addrs.addr[0].ss_local, sizeof(local)) == 0);
+	assert(memcmp(&remote, &addrs.addr[0].ss_remote, sizeof(remote)) == 0);
+
+	memset(&addrs, 0, sizeof(addrs));
+
+	addrs.d.size_subflow_data = sizeof(struct mptcp_subflow_data);
+	addrs.d.size_user = sizeof(sa_family_t);
+	olen = sizeof(addrs.d) + sizeof(sa_family_t);
+
+	ret = getsockopt(fd, SOL_MPTCP, MPTCP_SUBFLOW_ADDRS, &addrs, &olen);
+	assert(ret == 0);
+	assert(olen == sizeof(addrs.d) + sizeof(sa_family_t));
+
+	assert(addrs.addr[0].sa_family == pf);
+	assert(addrs.addr[0].sa_family == local.ss_family);
+
+	assert(memcmp(&local, &addrs.addr[0].ss_local, sizeof(local)) != 0);
+	assert(memcmp(&remote, &addrs.addr[0].ss_remote, sizeof(remote)) != 0);
+
+	do_getsockopt_bogus_sf_data(fd, MPTCP_SUBFLOW_ADDRS);
+}
+
+static void do_getsockopts(struct so_state *s, int fd, size_t r, size_t w)
+{
+	do_getsockopt_mptcp_info(s, fd, w);
+
+	do_getsockopt_tcp_info(s, fd, r, w);
+
+	do_getsockopt_subflow_addrs(fd);
+}
+
+static void connect_one_server(int fd, int pipefd)
+{
+	char buf[4096], buf2[4096];
+	size_t len, i, total;
+	struct so_state s;
+	bool eof = false;
+	ssize_t ret;
+
+	memset(&s, 0, sizeof(s));
+
+	len = rand() % (sizeof(buf) - 1);
+
+	if (len < 128)
+		len = 128;
+
+	for (i = 0; i < len ; i++) {
+		buf[i] = rand() % 26;
+		buf[i] += 'A';
+	}
+
+	buf[i] = '\n';
+
+	do_getsockopts(&s, fd, 0, 0);
+
+	/* un-block server */
+	ret = read(pipefd, buf2, 4);
+	assert(ret == 4);
+	close(pipefd);
+
+	assert(strncmp(buf2, "xmit", 4) == 0);
+
+	ret = write(fd, buf, len);
+	if (ret < 0)
+		die_perror("write");
+
+	if (ret != (ssize_t)len)
+		xerror("short write");
+
+	total = 0;
+	do {
+		ret = read(fd, buf2 + total, sizeof(buf2) - total);
+		if (ret < 0)
+			die_perror("read");
+		if (ret == 0) {
+			eof = true;
+			break;
+		}
+
+		total += ret;
+	} while (total < len);
+
+	if (total != len)
+		xerror("total %lu, len %lu eof %d\n", total, len, eof);
+
+	if (memcmp(buf, buf2, len))
+		xerror("data corruption");
+
+	if (s.tcpi_rcv_delta)
+		assert(s.tcpi_rcv_delta <= total);
+
+	do_getsockopts(&s, fd, ret, ret);
+
+	if (eof)
+		total += 1; /* sequence advances due to FIN */
+
+	assert(s.mptcpi_rcv_delta == (uint64_t)total);
+	close(fd);
+}
+
+static void process_one_client(int fd, int pipefd)
+{
+	ssize_t ret, ret2, ret3;
+	struct so_state s;
+	char buf[4096];
+
+	memset(&s, 0, sizeof(s));
+	do_getsockopts(&s, fd, 0, 0);
+
+	ret = write(pipefd, "xmit", 4);
+	assert(ret == 4);
+
+	ret = read(fd, buf, sizeof(buf));
+	if (ret < 0)
+		die_perror("read");
+
+	assert(s.mptcpi_rcv_delta <= (uint64_t)ret);
+
+	if (s.tcpi_rcv_delta)
+		assert(s.tcpi_rcv_delta == (uint64_t)ret);
+
+	ret2 = write(fd, buf, ret);
+	if (ret2 < 0)
+		die_perror("write");
+
+	/* wait for hangup */
+	ret3 = read(fd, buf, 1);
+	if (ret3 != 0)
+		xerror("expected EOF, got %lu", ret3);
+
+	do_getsockopts(&s, fd, ret, ret2);
+	if (s.mptcpi_rcv_delta != (uint64_t)ret + 1)
+		xerror("mptcpi_rcv_delta %" PRIu64 ", expect %" PRIu64, s.mptcpi_rcv_delta, ret + 1, s.mptcpi_rcv_delta - ret);
+	close(fd);
+}
+
+static int xaccept(int s)
+{
+	int fd = accept(s, NULL, 0);
+
+	if (fd < 0)
+		die_perror("accept");
+
+	return fd;
+}
+
+static int server(int pipefd)
+{
+	int fd = -1, r;
+
+	switch (pf) {
+	case AF_INET:
+		fd = sock_listen_mptcp("127.0.0.1", "15432");
+		break;
+	case AF_INET6:
+		fd = sock_listen_mptcp("::1", "15432");
+		break;
+	default:
+		xerror("Unknown pf %d\n", pf);
+		break;
+	}
+
+	r = write(pipefd, "conn", 4);
+	assert(r == 4);
+
+	alarm(15);
+	r = xaccept(fd);
+
+	process_one_client(r, pipefd);
+
+	return 0;
+}
+
+static int client(int pipefd)
+{
+	int fd = -1;
+
+	alarm(15);
+
+	switch (pf) {
+	case AF_INET:
+		fd = sock_connect_mptcp("127.0.0.1", "15432", IPPROTO_MPTCP);
+		break;
+	case AF_INET6:
+		fd = sock_connect_mptcp("::1", "15432", IPPROTO_MPTCP);
+		break;
+	default:
+		xerror("Unknown pf %d\n", pf);
+	}
+
+	connect_one_server(fd, pipefd);
+
+	return 0;
+}
+
+static pid_t xfork(void)
+{
+	pid_t p = fork();
+
+	if (p < 0)
+		die_perror("fork");
+
+	return p;
+}
+
+static int rcheck(int wstatus, const char *what)
+{
+	if (WIFEXITED(wstatus)) {
+		if (WEXITSTATUS(wstatus) == 0)
+			return 0;
+		fprintf(stderr, "%s exited, status=%d\n", what, WEXITSTATUS(wstatus));
+		return WEXITSTATUS(wstatus);
+	} else if (WIFSIGNALED(wstatus)) {
+		xerror("%s killed by signal %d\n", what, WTERMSIG(wstatus));
+	} else if (WIFSTOPPED(wstatus)) {
+		xerror("%s stopped by signal %d\n", what, WSTOPSIG(wstatus));
+	}
+
+	return 111;
+}
+
+int main(int argc, char *argv[])
+{
+	int e1, e2, wstatus;
+	pid_t s, c, ret;
+	int pipefds[2];
+
+	parse_opts(argc, argv);
+
+	e1 = pipe(pipefds);
+	if (e1 < 0)
+		die_perror("pipe");
+
+	s = xfork();
+	if (s == 0)
+		return server(pipefds[1]);
+
+	close(pipefds[1]);
+
+	/* wait until server bound a socket */
+	e1 = read(pipefds[0], &e1, 4);
+	assert(e1 == 4);
+
+	c = xfork();
+	if (c == 0)
+		return client(pipefds[0]);
+
+	close(pipefds[0]);
+
+	ret = waitpid(s, &wstatus, 0);
+	if (ret == -1)
+		die_perror("waitpid");
+	e1 = rcheck(wstatus, "server");
+	ret = waitpid(c, &wstatus, 0);
+	if (ret == -1)
+		die_perror("waitpid");
+	e2 = rcheck(wstatus, "client");
+
+	return e1 ? e1 : e2;
+}
diff --git a/tools/testing/selftests/net/mptcp/mptcp_sockopt.sh b/tools/testing/selftests/net/mptcp/mptcp_sockopt.sh
index 1579e471a5e7..41de643788b8 100755
--- a/tools/testing/selftests/net/mptcp/mptcp_sockopt.sh
+++ b/tools/testing/selftests/net/mptcp/mptcp_sockopt.sh
@@ -239,12 +239,35 @@ make_file()
 	echo "Created $name (size $size KB) containing data sent by $who"
 }
 
+do_mptcp_sockopt_tests()
+{
+	local lret=0
+
+	./mptcp_sockopt
+	lret=$?
+
+	if [ $lret -ne 0 ]; then
+		echo "FAIL: SOL_MPTCP getsockopt" 1>&2
+		ret=$lret
+		return
+	fi
+
+	./mptcp_sockopt -6
+	lret=$?
+
+	if [ $lret -ne 0 ]; then
+		echo "FAIL: SOL_MPTCP getsockopt (ipv6)" 1>&2
+		ret=$lret
+		return
+	fi
+}
+
 run_tests()
 {
 	listener_ns="$1"
 	connector_ns="$2"
 	connect_addr="$3"
-	lret=0
+	local lret=0
 
 	do_transfer ${listener_ns} ${connector_ns} MPTCP MPTCP ${connect_addr}
 
@@ -268,9 +291,13 @@ trap cleanup EXIT
 run_tests $ns1 $ns2 10.0.1.1
 run_tests $ns1 $ns2 dead:beef:1::1
 
-
 if [ $ret -eq 0 ];then
 	echo "PASS: all packets had packet mark set"
 fi
 
+do_mptcp_sockopt_tests
+if [ $ret -eq 0 ];then
+	echo "PASS: SOL_MPTCP getsockopt has expected information"
+fi
+
 exit $ret
-- 
cgit v1.2.3


From 97c140d94e2e5f050d5f418317cc34f83da3d0f5 Mon Sep 17 00:00:00 2001
From: Grant Seltzer <grantseltzer@gmail.com>
Date: Fri, 17 Sep 2021 23:14:58 -0400
Subject: libbpf: Add doc comments in libbpf.h

This adds comments above functions in libbpf.h which document
their uses. These comments are of a format that doxygen and sphinx
can pick up and render. These are rendered by libbpf.readthedocs.org

These doc comments are for:
- bpf_object__find_map_by_name()
- bpf_map__fd()
- bpf_map__is_internal()
- libbpf_get_error()
- libbpf_num_possible_cpus()

Signed-off-by: Grant Seltzer <grantseltzer@gmail.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20210918031457.36204-1-grantseltzer@gmail.com
---
 tools/lib/bpf/libbpf.h | 65 +++++++++++++++++++++++++++++++++++++++++++-------
 1 file changed, 57 insertions(+), 8 deletions(-)

(limited to 'tools')

diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h
index c90e3d79e72c..d0bedd673273 100644
--- a/tools/lib/bpf/libbpf.h
+++ b/tools/lib/bpf/libbpf.h
@@ -481,9 +481,13 @@ struct bpf_map_def {
 	unsigned int map_flags;
 };
 
-/*
- * The 'struct bpf_map' in include/linux/bpf.h is internal to the kernel,
- * so no need to worry about a name clash.
+/**
+ * @brief **bpf_object__find_map_by_name()** returns BPF map of
+ * the given name, if it exists within the passed BPF object
+ * @param obj BPF object
+ * @param name name of the BPF map
+ * @return BPF map instance, if such map exists within the BPF object;
+ * or NULL otherwise.
  */
 LIBBPF_API struct bpf_map *
 bpf_object__find_map_by_name(const struct bpf_object *obj, const char *name);
@@ -509,7 +513,12 @@ bpf_map__next(const struct bpf_map *map, const struct bpf_object *obj);
 LIBBPF_API struct bpf_map *
 bpf_map__prev(const struct bpf_map *map, const struct bpf_object *obj);
 
-/* get/set map FD */
+/**
+ * @brief **bpf_map__fd()** gets the file descriptor of the passed
+ * BPF map
+ * @param map the BPF map instance
+ * @return the file descriptor; or -EINVAL in case of an error
+ */
 LIBBPF_API int bpf_map__fd(const struct bpf_map *map);
 LIBBPF_API int bpf_map__reuse_fd(struct bpf_map *map, int fd);
 /* get map definition */
@@ -550,6 +559,14 @@ LIBBPF_API int bpf_map__set_initial_value(struct bpf_map *map,
 					  const void *data, size_t size);
 LIBBPF_API const void *bpf_map__initial_value(struct bpf_map *map, size_t *psize);
 LIBBPF_API bool bpf_map__is_offload_neutral(const struct bpf_map *map);
+
+/**
+ * @brief **bpf_map__is_internal()** tells the caller whether or not the
+ * passed map is a special map created by libbpf automatically for things like
+ * global variables, __ksym externs, Kconfig values, etc
+ * @param map the bpf_map
+ * @return true, if the map is an internal map; false, otherwise
+ */
 LIBBPF_API bool bpf_map__is_internal(const struct bpf_map *map);
 LIBBPF_API int bpf_map__set_pin_path(struct bpf_map *map, const char *path);
 LIBBPF_API const char *bpf_map__get_pin_path(const struct bpf_map *map);
@@ -561,6 +578,38 @@ LIBBPF_API int bpf_map__unpin(struct bpf_map *map, const char *path);
 LIBBPF_API int bpf_map__set_inner_map_fd(struct bpf_map *map, int fd);
 LIBBPF_API struct bpf_map *bpf_map__inner_map(struct bpf_map *map);
 
+/**
+ * @brief **libbpf_get_error()** extracts the error code from the passed
+ * pointer
+ * @param ptr pointer returned from libbpf API function
+ * @return error code; or 0 if no error occured
+ *
+ * Many libbpf API functions which return pointers have logic to encode error
+ * codes as pointers, and do not return NULL. Meaning **libbpf_get_error()**
+ * should be used on the return value from these functions immediately after
+ * calling the API function, with no intervening calls that could clobber the
+ * `errno` variable. Consult the individual functions documentation to verify
+ * if this logic applies should be used.
+ *
+ * For these API functions, if `libbpf_set_strict_mode(LIBBPF_STRICT_CLEAN_PTRS)`
+ * is enabled, NULL is returned on error instead.
+ *
+ * If ptr is NULL, then errno should be already set by the failing
+ * API, because libbpf never returns NULL on success and it now always
+ * sets errno on error.
+ *
+ * Example usage:
+ *
+ *   struct perf_buffer *pb;
+ *
+ *   pb = perf_buffer__new(bpf_map__fd(obj->maps.events), PERF_BUFFER_PAGES, &opts);
+ *   err = libbpf_get_error(pb);
+ *   if (err) {
+ *	  pb = NULL;
+ *	  fprintf(stderr, "failed to open perf buffer: %d\n", err);
+ *	  goto cleanup;
+ *   }
+ */
 LIBBPF_API long libbpf_get_error(const void *ptr);
 
 struct bpf_prog_load_attr {
@@ -825,9 +874,10 @@ bpf_program__bpil_addr_to_offs(struct bpf_prog_info_linear *info_linear);
 LIBBPF_API void
 bpf_program__bpil_offs_to_addr(struct bpf_prog_info_linear *info_linear);
 
-/*
- * A helper function to get the number of possible CPUs before looking up
- * per-CPU maps. Negative errno is returned on failure.
+/**
+ * @brief **libbpf_num_possible_cpus()** is a helper function to get the
+ * number of possible CPUs that the host kernel supports and expects.
+ * @return number of possible CPUs; or error code on failure
  *
  * Example usage:
  *
@@ -837,7 +887,6 @@ bpf_program__bpil_offs_to_addr(struct bpf_prog_info_linear *info_linear);
  *     }
  *     long values[ncpus];
  *     bpf_map_lookup_elem(per_cpu_map_fd, key, values);
- *
  */
 LIBBPF_API int libbpf_num_possible_cpus(void);
 
-- 
cgit v1.2.3


From 303a257223a3bbd7cc6ccc2b7777179c8d9f3989 Mon Sep 17 00:00:00 2001
From: Andrii Nakryiko <andrii@kernel.org>
Date: Tue, 21 Sep 2021 14:00:33 -0700
Subject: libbpf: Fix memory leak in legacy kprobe attach logic

In some error scenarios legacy_probe string won't be free()'d. Fix this.
This was reported by Coverity static analysis.

Fixes: ca304b40c20d ("libbpf: Introduce legacy kprobe events support")
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20210921210036.1545557-2-andrii@kernel.org
---
 tools/lib/bpf/libbpf.c | 10 +++++++---
 1 file changed, 7 insertions(+), 3 deletions(-)

(limited to 'tools')

diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index da65a1666a5e..6d2f12db6034 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -9365,10 +9365,11 @@ bpf_program__attach_kprobe_opts(const struct bpf_program *prog,
 						    offset, -1 /* pid */);
 	}
 	if (pfd < 0) {
+		err = pfd;
 		pr_warn("prog '%s': failed to create %s '%s' perf event: %s\n",
 			prog->name, retprobe ? "kretprobe" : "kprobe", func_name,
-			libbpf_strerror_r(pfd, errmsg, sizeof(errmsg)));
-		return libbpf_err_ptr(pfd);
+			libbpf_strerror_r(err, errmsg, sizeof(errmsg)));
+		goto err_out;
 	}
 	link = bpf_program__attach_perf_event_opts(prog, pfd, &pe_opts);
 	err = libbpf_get_error(link);
@@ -9377,7 +9378,7 @@ bpf_program__attach_kprobe_opts(const struct bpf_program *prog,
 		pr_warn("prog '%s': failed to attach to %s '%s': %s\n",
 			prog->name, retprobe ? "kretprobe" : "kprobe", func_name,
 			libbpf_strerror_r(err, errmsg, sizeof(errmsg)));
-		return libbpf_err_ptr(err);
+		goto err_out;
 	}
 	if (legacy) {
 		struct bpf_link_perf *perf_link = container_of(link, struct bpf_link_perf, link);
@@ -9387,6 +9388,9 @@ bpf_program__attach_kprobe_opts(const struct bpf_program *prog,
 	}
 
 	return link;
+err_out:
+	free(legacy_probe);
+	return libbpf_err_ptr(err);
 }
 
 struct bpf_link *bpf_program__attach_kprobe(const struct bpf_program *prog,
-- 
cgit v1.2.3


From d3b0e3b03cf75896de7b03ad1fca2bff98c59f15 Mon Sep 17 00:00:00 2001
From: Andrii Nakryiko <andrii@kernel.org>
Date: Tue, 21 Sep 2021 14:00:34 -0700
Subject: selftests/bpf: Adopt attach_probe selftest to work on old kernels

Make sure to not use ref_ctr_off feature when running on old kernels
that don't support this feature. This allows to test libbpf's legacy
kprobe and uprobe logic on old kernels.

Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20210921210036.1545557-3-andrii@kernel.org
---
 .../selftests/bpf/prog_tests/attach_probe.c        | 24 ++++++++++++++++++----
 1 file changed, 20 insertions(+), 4 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/prog_tests/attach_probe.c b/tools/testing/selftests/bpf/prog_tests/attach_probe.c
index bf307bb9e446..6c511dcd1465 100644
--- a/tools/testing/selftests/bpf/prog_tests/attach_probe.c
+++ b/tools/testing/selftests/bpf/prog_tests/attach_probe.c
@@ -14,6 +14,20 @@ void test_attach_probe(void)
 	struct test_attach_probe* skel;
 	size_t uprobe_offset;
 	ssize_t base_addr, ref_ctr_offset;
+	bool legacy;
+
+	/* Check if new-style kprobe/uprobe API is supported.
+	 * Kernels that support new FD-based kprobe and uprobe BPF attachment
+	 * through perf_event_open() syscall expose
+	 * /sys/bus/event_source/devices/kprobe/type and
+	 * /sys/bus/event_source/devices/uprobe/type files, respectively. They
+	 * contain magic numbers that are passed as "type" field of
+	 * perf_event_attr. Lack of such file in the system indicates legacy
+	 * kernel with old-style kprobe/uprobe attach interface through
+	 * creating per-probe event through tracefs. For such cases
+	 * ref_ctr_offset feature is not supported, so we don't test it.
+	 */
+	legacy = access("/sys/bus/event_source/devices/kprobe/type", F_OK) != 0;
 
 	base_addr = get_base_addr();
 	if (CHECK(base_addr < 0, "get_base_addr",
@@ -45,10 +59,11 @@ void test_attach_probe(void)
 		goto cleanup;
 	skel->links.handle_kretprobe = kretprobe_link;
 
-	ASSERT_EQ(uprobe_ref_ctr, 0, "uprobe_ref_ctr_before");
+	if (!legacy)
+		ASSERT_EQ(uprobe_ref_ctr, 0, "uprobe_ref_ctr_before");
 
 	uprobe_opts.retprobe = false;
-	uprobe_opts.ref_ctr_offset = ref_ctr_offset;
+	uprobe_opts.ref_ctr_offset = legacy ? 0 : ref_ctr_offset;
 	uprobe_link = bpf_program__attach_uprobe_opts(skel->progs.handle_uprobe,
 						      0 /* self pid */,
 						      "/proc/self/exe",
@@ -58,11 +73,12 @@ void test_attach_probe(void)
 		goto cleanup;
 	skel->links.handle_uprobe = uprobe_link;
 
-	ASSERT_GT(uprobe_ref_ctr, 0, "uprobe_ref_ctr_after");
+	if (!legacy)
+		ASSERT_GT(uprobe_ref_ctr, 0, "uprobe_ref_ctr_after");
 
 	/* if uprobe uses ref_ctr, uretprobe has to use ref_ctr as well */
 	uprobe_opts.retprobe = true;
-	uprobe_opts.ref_ctr_offset = ref_ctr_offset;
+	uprobe_opts.ref_ctr_offset = legacy ? 0 : ref_ctr_offset;
 	uretprobe_link = bpf_program__attach_uprobe_opts(skel->progs.handle_uretprobe,
 							 -1 /* any pid */,
 							 "/proc/self/exe",
-- 
cgit v1.2.3


From 46ed5fc33db966aa1a46e8ae9d96b08b756a2546 Mon Sep 17 00:00:00 2001
From: Andrii Nakryiko <andrii@kernel.org>
Date: Tue, 21 Sep 2021 14:00:35 -0700
Subject: libbpf: Refactor and simplify legacy kprobe code

Refactor legacy kprobe handling code to follow the same logic as uprobe
legacy logic added in the next patchs:
  - add append_to_file() helper that makes it simpler to work with
    tracefs file-based interface for creating and deleting probes;
  - move out probe/event name generation outside of the code that
    adds/removes it, which simplifies bookkeeping significantly;
  - change the probe name format to start with "libbpf_" prefix and
    include offset within kernel function;
  - switch 'unsigned long' to 'size_t' for specifying kprobe offsets,
    which is consistent with how uprobes define that, simplifies
    printf()-ing internally, and also avoids unnecessary complications on
    architectures where sizeof(long) != sizeof(void *).

This patch also implicitly fixes the problem with invalid open() error
handling present in poke_kprobe_events(), which (the function) this
patch removes.

Fixes: ca304b40c20d ("libbpf: Introduce legacy kprobe events support")
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20210921210036.1545557-4-andrii@kernel.org
---
 tools/lib/bpf/libbpf.c | 159 +++++++++++++++++++++++++++----------------------
 tools/lib/bpf/libbpf.h |   2 +-
 2 files changed, 88 insertions(+), 73 deletions(-)

(limited to 'tools')

diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 6d2f12db6034..aa842f0721cb 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -9011,59 +9011,17 @@ int bpf_link__unpin(struct bpf_link *link)
 	return 0;
 }
 
-static int poke_kprobe_events(bool add, const char *name, bool retprobe, uint64_t offset)
-{
-	int fd, ret = 0;
-	pid_t p = getpid();
-	char cmd[260], probename[128], probefunc[128];
-	const char *file = "/sys/kernel/debug/tracing/kprobe_events";
-
-	if (retprobe)
-		snprintf(probename, sizeof(probename), "kretprobes/%s_libbpf_%u", name, p);
-	else
-		snprintf(probename, sizeof(probename), "kprobes/%s_libbpf_%u", name, p);
-
-	if (offset)
-		snprintf(probefunc, sizeof(probefunc), "%s+%zu", name, (size_t)offset);
-
-	if (add) {
-		snprintf(cmd, sizeof(cmd), "%c:%s %s",
-			 retprobe ? 'r' : 'p',
-			 probename,
-			 offset ? probefunc : name);
-	} else {
-		snprintf(cmd, sizeof(cmd), "-:%s", probename);
-	}
-
-	fd = open(file, O_WRONLY | O_APPEND, 0);
-	if (!fd)
-		return -errno;
-	ret = write(fd, cmd, strlen(cmd));
-	if (ret < 0)
-		ret = -errno;
-	close(fd);
-
-	return ret;
-}
-
-static inline int add_kprobe_event_legacy(const char *name, bool retprobe, uint64_t offset)
-{
-	return poke_kprobe_events(true, name, retprobe, offset);
-}
-
-static inline int remove_kprobe_event_legacy(const char *name, bool retprobe)
-{
-	return poke_kprobe_events(false, name, retprobe, 0);
-}
-
 struct bpf_link_perf {
 	struct bpf_link link;
 	int perf_event_fd;
 	/* legacy kprobe support: keep track of probe identifier and type */
 	char *legacy_probe_name;
+	bool legacy_is_kprobe;
 	bool legacy_is_retprobe;
 };
 
+static int remove_kprobe_event_legacy(const char *probe_name, bool retprobe);
+
 static int bpf_link_perf_detach(struct bpf_link *link)
 {
 	struct bpf_link_perf *perf_link = container_of(link, struct bpf_link_perf, link);
@@ -9077,9 +9035,12 @@ static int bpf_link_perf_detach(struct bpf_link *link)
 	close(link->fd);
 
 	/* legacy kprobe needs to be removed after perf event fd closure */
-	if (perf_link->legacy_probe_name)
-		err = remove_kprobe_event_legacy(perf_link->legacy_probe_name,
-						 perf_link->legacy_is_retprobe);
+	if (perf_link->legacy_probe_name) {
+		if (perf_link->legacy_is_kprobe) {
+			err = remove_kprobe_event_legacy(perf_link->legacy_probe_name,
+							 perf_link->legacy_is_retprobe);
+		}
+	}
 
 	return err;
 }
@@ -9202,18 +9163,6 @@ static int parse_uint_from_file(const char *file, const char *fmt)
 	return ret;
 }
 
-static int determine_kprobe_perf_type_legacy(const char *func_name, bool is_retprobe)
-{
-	char file[192];
-
-	snprintf(file, sizeof(file),
-		 "/sys/kernel/debug/tracing/events/%s/%s_libbpf_%d/id",
-		 is_retprobe ? "kretprobes" : "kprobes",
-		 func_name, getpid());
-
-	return parse_uint_from_file(file, "%d\n");
-}
-
 static int determine_kprobe_perf_type(void)
 {
 	const char *file = "/sys/bus/event_source/devices/kprobe/type";
@@ -9296,21 +9245,79 @@ static int perf_event_open_probe(bool uprobe, bool retprobe, const char *name,
 	return pfd;
 }
 
-static int perf_event_kprobe_open_legacy(bool retprobe, const char *name, uint64_t offset, int pid)
+static int append_to_file(const char *file, const char *fmt, ...)
+{
+	int fd, n, err = 0;
+	va_list ap;
+
+	fd = open(file, O_WRONLY | O_APPEND, 0);
+	if (fd < 0)
+		return -errno;
+
+	va_start(ap, fmt);
+	n = vdprintf(fd, fmt, ap);
+	va_end(ap);
+
+	if (n < 0)
+		err = -errno;
+
+	close(fd);
+	return err;
+}
+
+static void gen_kprobe_legacy_event_name(char *buf, size_t buf_sz,
+					 const char *kfunc_name, size_t offset)
+{
+	snprintf(buf, buf_sz, "libbpf_%u_%s_0x%zx", getpid(), kfunc_name, offset);
+}
+
+static int add_kprobe_event_legacy(const char *probe_name, bool retprobe,
+				   const char *kfunc_name, size_t offset)
+{
+	const char *file = "/sys/kernel/debug/tracing/kprobe_events";
+
+	return append_to_file(file, "%c:%s/%s %s+0x%zx",
+			      retprobe ? 'r' : 'p',
+			      retprobe ? "kretprobes" : "kprobes",
+			      probe_name, kfunc_name, offset);
+}
+
+static int remove_kprobe_event_legacy(const char *probe_name, bool retprobe)
+{
+	const char *file = "/sys/kernel/debug/tracing/kprobe_events";
+
+	return append_to_file(file, "-:%s/%s", retprobe ? "kretprobes" : "kprobes", probe_name);
+}
+
+static int determine_kprobe_perf_type_legacy(const char *probe_name, bool retprobe)
+{
+	char file[256];
+
+	snprintf(file, sizeof(file),
+		 "/sys/kernel/debug/tracing/events/%s/%s/id",
+		 retprobe ? "kretprobes" : "kprobes", probe_name);
+
+	return parse_uint_from_file(file, "%d\n");
+}
+
+static int perf_event_kprobe_open_legacy(const char *probe_name, bool retprobe,
+					 const char *kfunc_name, size_t offset, int pid)
 {
 	struct perf_event_attr attr = {};
 	char errmsg[STRERR_BUFSIZE];
 	int type, pfd, err;
 
-	err = add_kprobe_event_legacy(name, retprobe, offset);
+	err = add_kprobe_event_legacy(probe_name, retprobe, kfunc_name, offset);
 	if (err < 0) {
-		pr_warn("failed to add legacy kprobe event: %s\n",
+		pr_warn("failed to add legacy kprobe event for '%s+0x%zx': %s\n",
+			kfunc_name, offset,
 			libbpf_strerror_r(err, errmsg, sizeof(errmsg)));
 		return err;
 	}
-	type = determine_kprobe_perf_type_legacy(name, retprobe);
+	type = determine_kprobe_perf_type_legacy(probe_name, retprobe);
 	if (type < 0) {
-		pr_warn("failed to determine legacy kprobe event id: %s\n",
+		pr_warn("failed to determine legacy kprobe event id for '%s+0x%zx': %s\n",
+			kfunc_name, offset,
 			libbpf_strerror_r(type, errmsg, sizeof(errmsg)));
 		return type;
 	}
@@ -9340,7 +9347,7 @@ bpf_program__attach_kprobe_opts(const struct bpf_program *prog,
 	char errmsg[STRERR_BUFSIZE];
 	char *legacy_probe = NULL;
 	struct bpf_link *link;
-	unsigned long offset;
+	size_t offset;
 	bool retprobe, legacy;
 	int pfd, err;
 
@@ -9357,17 +9364,23 @@ bpf_program__attach_kprobe_opts(const struct bpf_program *prog,
 					    func_name, offset,
 					    -1 /* pid */, 0 /* ref_ctr_off */);
 	} else {
+		char probe_name[256];
+
+		gen_kprobe_legacy_event_name(probe_name, sizeof(probe_name),
+					     func_name, offset);
+
 		legacy_probe = strdup(func_name);
 		if (!legacy_probe)
 			return libbpf_err_ptr(-ENOMEM);
 
-		pfd = perf_event_kprobe_open_legacy(retprobe, func_name,
+		pfd = perf_event_kprobe_open_legacy(legacy_probe, retprobe, func_name,
 						    offset, -1 /* pid */);
 	}
 	if (pfd < 0) {
-		err = pfd;
-		pr_warn("prog '%s': failed to create %s '%s' perf event: %s\n",
-			prog->name, retprobe ? "kretprobe" : "kprobe", func_name,
+		err = -errno;
+		pr_warn("prog '%s': failed to create %s '%s+0x%zx' perf event: %s\n",
+			prog->name, retprobe ? "kretprobe" : "kprobe",
+			func_name, offset,
 			libbpf_strerror_r(err, errmsg, sizeof(errmsg)));
 		goto err_out;
 	}
@@ -9375,8 +9388,9 @@ bpf_program__attach_kprobe_opts(const struct bpf_program *prog,
 	err = libbpf_get_error(link);
 	if (err) {
 		close(pfd);
-		pr_warn("prog '%s': failed to attach to %s '%s': %s\n",
-			prog->name, retprobe ? "kretprobe" : "kprobe", func_name,
+		pr_warn("prog '%s': failed to attach to %s '%s+0x%zx': %s\n",
+			prog->name, retprobe ? "kretprobe" : "kprobe",
+			func_name, offset,
 			libbpf_strerror_r(err, errmsg, sizeof(errmsg)));
 		goto err_out;
 	}
@@ -9384,6 +9398,7 @@ bpf_program__attach_kprobe_opts(const struct bpf_program *prog,
 		struct bpf_link_perf *perf_link = container_of(link, struct bpf_link_perf, link);
 
 		perf_link->legacy_probe_name = legacy_probe;
+		perf_link->legacy_is_kprobe = true;
 		perf_link->legacy_is_retprobe = retprobe;
 	}
 
diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h
index d0bedd673273..e35490c54eb3 100644
--- a/tools/lib/bpf/libbpf.h
+++ b/tools/lib/bpf/libbpf.h
@@ -269,7 +269,7 @@ struct bpf_kprobe_opts {
 	/* custom user-provided value fetchable through bpf_get_attach_cookie() */
 	__u64 bpf_cookie;
 	/* function's offset to install kprobe to */
-	unsigned long offset;
+	size_t offset;
 	/* kprobe is return probe */
 	bool retprobe;
 	size_t :0;
-- 
cgit v1.2.3


From cc10623c681019c608c0cb30e2b38994e2c90b2a Mon Sep 17 00:00:00 2001
From: Andrii Nakryiko <andrii@kernel.org>
Date: Tue, 21 Sep 2021 14:00:36 -0700
Subject: libbpf: Add legacy uprobe attaching support

Similarly to recently added legacy kprobe attach interface support
through tracefs, support attaching uprobes using the legacy interface if
host kernel doesn't support newer FD-based interface.

For uprobes event name consists of "libbpf_" prefix, PID, sanitized
binary path and offset within that binary. Structuraly the code is
aligned with kprobe logic refactoring in previous patch. struct
bpf_link_perf is re-used and all the same legacy_probe_name and
legacy_is_retprobe fields are used to ensure proper cleanup on
bpf_link__destroy().

Users should be aware, though, that on old kernels which don't support
FD-based interface for kprobe/uprobe attachment, if the application
crashes before bpf_link__destroy() is called, uprobe legacy
events will be left in tracefs. This is the same limitation as with
legacy kprobe interfaces.

Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20210921210036.1545557-5-andrii@kernel.org
---
 tools/lib/bpf/libbpf.c | 130 ++++++++++++++++++++++++++++++++++++++++++++++---
 1 file changed, 122 insertions(+), 8 deletions(-)

(limited to 'tools')

diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index aa842f0721cb..ef5db34bf913 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -9021,6 +9021,7 @@ struct bpf_link_perf {
 };
 
 static int remove_kprobe_event_legacy(const char *probe_name, bool retprobe);
+static int remove_uprobe_event_legacy(const char *probe_name, bool retprobe);
 
 static int bpf_link_perf_detach(struct bpf_link *link)
 {
@@ -9034,11 +9035,14 @@ static int bpf_link_perf_detach(struct bpf_link *link)
 		close(perf_link->perf_event_fd);
 	close(link->fd);
 
-	/* legacy kprobe needs to be removed after perf event fd closure */
+	/* legacy uprobe/kprobe needs to be removed after perf event fd closure */
 	if (perf_link->legacy_probe_name) {
 		if (perf_link->legacy_is_kprobe) {
 			err = remove_kprobe_event_legacy(perf_link->legacy_probe_name,
 							 perf_link->legacy_is_retprobe);
+		} else {
+			err = remove_uprobe_event_legacy(perf_link->legacy_probe_name,
+							 perf_link->legacy_is_retprobe);
 		}
 	}
 
@@ -9450,17 +9454,96 @@ static struct bpf_link *attach_kprobe(const struct bpf_program *prog)
 	return link;
 }
 
+static void gen_uprobe_legacy_event_name(char *buf, size_t buf_sz,
+					 const char *binary_path, uint64_t offset)
+{
+	int i;
+
+	snprintf(buf, buf_sz, "libbpf_%u_%s_0x%zx", getpid(), binary_path, (size_t)offset);
+
+	/* sanitize binary_path in the probe name */
+	for (i = 0; buf[i]; i++) {
+		if (!isalnum(buf[i]))
+			buf[i] = '_';
+	}
+}
+
+static inline int add_uprobe_event_legacy(const char *probe_name, bool retprobe,
+					  const char *binary_path, size_t offset)
+{
+	const char *file = "/sys/kernel/debug/tracing/uprobe_events";
+
+	return append_to_file(file, "%c:%s/%s %s:0x%zx",
+			      retprobe ? 'r' : 'p',
+			      retprobe ? "uretprobes" : "uprobes",
+			      probe_name, binary_path, offset);
+}
+
+static inline int remove_uprobe_event_legacy(const char *probe_name, bool retprobe)
+{
+	const char *file = "/sys/kernel/debug/tracing/uprobe_events";
+
+	return append_to_file(file, "-:%s/%s", retprobe ? "uretprobes" : "uprobes", probe_name);
+}
+
+static int determine_uprobe_perf_type_legacy(const char *probe_name, bool retprobe)
+{
+	char file[512];
+
+	snprintf(file, sizeof(file),
+		 "/sys/kernel/debug/tracing/events/%s/%s/id",
+		 retprobe ? "uretprobes" : "uprobes", probe_name);
+
+	return parse_uint_from_file(file, "%d\n");
+}
+
+static int perf_event_uprobe_open_legacy(const char *probe_name, bool retprobe,
+					 const char *binary_path, size_t offset, int pid)
+{
+	struct perf_event_attr attr;
+	int type, pfd, err;
+
+	err = add_uprobe_event_legacy(probe_name, retprobe, binary_path, offset);
+	if (err < 0) {
+		pr_warn("failed to add legacy uprobe event for %s:0x%zx: %d\n",
+			binary_path, (size_t)offset, err);
+		return err;
+	}
+	type = determine_uprobe_perf_type_legacy(probe_name, retprobe);
+	if (type < 0) {
+		pr_warn("failed to determine legacy uprobe event id for %s:0x%zx: %d\n",
+			binary_path, offset, err);
+		return type;
+	}
+
+	memset(&attr, 0, sizeof(attr));
+	attr.size = sizeof(attr);
+	attr.config = type;
+	attr.type = PERF_TYPE_TRACEPOINT;
+
+	pfd = syscall(__NR_perf_event_open, &attr,
+		      pid < 0 ? -1 : pid, /* pid */
+		      pid == -1 ? 0 : -1, /* cpu */
+		      -1 /* group_fd */,  PERF_FLAG_FD_CLOEXEC);
+	if (pfd < 0) {
+		err = -errno;
+		pr_warn("legacy uprobe perf_event_open() failed: %d\n", err);
+		return err;
+	}
+	return pfd;
+}
+
 LIBBPF_API struct bpf_link *
 bpf_program__attach_uprobe_opts(const struct bpf_program *prog, pid_t pid,
 				const char *binary_path, size_t func_offset,
 				const struct bpf_uprobe_opts *opts)
 {
 	DECLARE_LIBBPF_OPTS(bpf_perf_event_opts, pe_opts);
-	char errmsg[STRERR_BUFSIZE];
+	char errmsg[STRERR_BUFSIZE], *legacy_probe = NULL;
 	struct bpf_link *link;
 	size_t ref_ctr_off;
 	int pfd, err;
-	bool retprobe;
+	bool retprobe, legacy;
 
 	if (!OPTS_VALID(opts, bpf_uprobe_opts))
 		return libbpf_err_ptr(-EINVAL);
@@ -9469,15 +9552,35 @@ bpf_program__attach_uprobe_opts(const struct bpf_program *prog, pid_t pid,
 	ref_ctr_off = OPTS_GET(opts, ref_ctr_offset, 0);
 	pe_opts.bpf_cookie = OPTS_GET(opts, bpf_cookie, 0);
 
-	pfd = perf_event_open_probe(true /* uprobe */, retprobe, binary_path,
-				    func_offset, pid, ref_ctr_off);
+	legacy = determine_uprobe_perf_type() < 0;
+	if (!legacy) {
+		pfd = perf_event_open_probe(true /* uprobe */, retprobe, binary_path,
+					    func_offset, pid, ref_ctr_off);
+	} else {
+		char probe_name[512];
+
+		if (ref_ctr_off)
+			return libbpf_err_ptr(-EINVAL);
+
+		gen_uprobe_legacy_event_name(probe_name, sizeof(probe_name),
+					     binary_path, func_offset);
+
+		legacy_probe = strdup(probe_name);
+		if (!legacy_probe)
+			return libbpf_err_ptr(-ENOMEM);
+
+		pfd = perf_event_uprobe_open_legacy(legacy_probe, retprobe,
+						    binary_path, func_offset, pid);
+	}
 	if (pfd < 0) {
+		err = -errno;
 		pr_warn("prog '%s': failed to create %s '%s:0x%zx' perf event: %s\n",
 			prog->name, retprobe ? "uretprobe" : "uprobe",
 			binary_path, func_offset,
-			libbpf_strerror_r(pfd, errmsg, sizeof(errmsg)));
-		return libbpf_err_ptr(pfd);
+			libbpf_strerror_r(err, errmsg, sizeof(errmsg)));
+		goto err_out;
 	}
+
 	link = bpf_program__attach_perf_event_opts(prog, pfd, &pe_opts);
 	err = libbpf_get_error(link);
 	if (err) {
@@ -9486,9 +9589,20 @@ bpf_program__attach_uprobe_opts(const struct bpf_program *prog, pid_t pid,
 			prog->name, retprobe ? "uretprobe" : "uprobe",
 			binary_path, func_offset,
 			libbpf_strerror_r(err, errmsg, sizeof(errmsg)));
-		return libbpf_err_ptr(err);
+		goto err_out;
+	}
+	if (legacy) {
+		struct bpf_link_perf *perf_link = container_of(link, struct bpf_link_perf, link);
+
+		perf_link->legacy_probe_name = legacy_probe;
+		perf_link->legacy_is_kprobe = false;
+		perf_link->legacy_is_retprobe = retprobe;
 	}
 	return link;
+err_out:
+	free(legacy_probe);
+	return libbpf_err_ptr(err);
+
 }
 
 struct bpf_link *bpf_program__attach_uprobe(const struct bpf_program *prog,
-- 
cgit v1.2.3


From 17b52c226a9a170f1611f69d12a71be05748aefd Mon Sep 17 00:00:00 2001
From: Jiri Benc <jbenc@redhat.com>
Date: Tue, 21 Sep 2021 16:59:11 +0200
Subject: seltests: bpf: test_tunnel: Use ip neigh

The 'arp' command is deprecated and is another dependency of the selftest.
Just use 'ip neigh', the test depends on iproute2 already.

Signed-off-by: Jiri Benc <jbenc@redhat.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/40f24b9d3f0f53b5c44471b452f9a11f4d13b7af.1632236133.git.jbenc@redhat.com
---
 tools/testing/selftests/bpf/test_tunnel.sh | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/test_tunnel.sh b/tools/testing/selftests/bpf/test_tunnel.sh
index 1ccbe804e8e1..ca1372924023 100755
--- a/tools/testing/selftests/bpf/test_tunnel.sh
+++ b/tools/testing/selftests/bpf/test_tunnel.sh
@@ -168,14 +168,15 @@ add_vxlan_tunnel()
 	ip netns exec at_ns0 \
 		ip link set dev $DEV_NS address 52:54:00:d9:01:00 up
 	ip netns exec at_ns0 ip addr add dev $DEV_NS 10.1.1.100/24
-	ip netns exec at_ns0 arp -s 10.1.1.200 52:54:00:d9:02:00
+	ip netns exec at_ns0 \
+		ip neigh add 10.1.1.200 lladdr 52:54:00:d9:02:00 dev $DEV_NS
 	ip netns exec at_ns0 iptables -A OUTPUT -j MARK --set-mark 0x800FF
 
 	# root namespace
 	ip link add dev $DEV type $TYPE external gbp dstport 4789
 	ip link set dev $DEV address 52:54:00:d9:02:00 up
 	ip addr add dev $DEV 10.1.1.200/24
-	arp -s 10.1.1.100 52:54:00:d9:01:00
+	ip neigh add 10.1.1.100 lladdr 52:54:00:d9:01:00 dev $DEV
 }
 
 add_ip6vxlan_tunnel()
-- 
cgit v1.2.3


From 091037fb770e1771a52246f9b68dc76082178a3c Mon Sep 17 00:00:00 2001
From: Yonghong Song <yhs@fb.com>
Date: Thu, 23 Sep 2021 19:58:56 -0700
Subject: selftests/bpf: Fix btf_dump __int128 test failure with clang build
 kernel

With clang build kernel (adding LLVM=1 to kernel and selftests/bpf build
command line), I hit the following test failure:

  $ ./test_progs -t btf_dump
  ...
  btf_dump_data:PASS:ensure expected/actual match 0 nsec
  btf_dump_data:FAIL:find type id unexpected find type id: actual -2 < expected 0
  btf_dump_data:FAIL:find type id unexpected find type id: actual -2 < expected 0
  test_btf_dump_int_data:FAIL:dump __int128 unexpected error: -2 (errno 2)
  #15/9 btf_dump/btf_dump: int_data:FAIL

Further analysis showed gcc build kernel has type "__int128" in dwarf/BTF
and it doesn't exist in clang build kernel. Code searching for kernel code
found the following:
  arch/s390/include/asm/types.h:  unsigned __int128 pair;
  crypto/ecc.c:   unsigned __int128 m = (unsigned __int128)left * right;
  include/linux/math64.h: return (u64)(((unsigned __int128)a * mul) >> shift);
  include/linux/math64.h: return (u64)(((unsigned __int128)a * mul) >> shift);
  lib/ubsan.h:typedef __int128 s_max;
  lib/ubsan.h:typedef unsigned __int128 u_max;

In my case, CONFIG_UBSAN is not enabled. Even if we only have "unsigned __int128"
in the code, somehow gcc still put "__int128" in dwarf while clang didn't.
Hence current test works fine for gcc but not for clang.

Enabling CONFIG_UBSAN is an option to provide __int128 type into dwarf
reliably for both gcc and clang, but not everybody enables CONFIG_UBSAN
in their kernel build. So the best choice is to use "unsigned __int128" type
which is available in both clang and gcc build kernels. But clang and gcc
dwarf encoded names for "unsigned __int128" are different:

  [$ ~] cat t.c
  unsigned __int128 a;
  [$ ~] gcc -g -c t.c && llvm-dwarfdump t.o | grep __int128
                  DW_AT_type      (0x00000031 "__int128 unsigned")
                  DW_AT_name      ("__int128 unsigned")
  [$ ~] clang -g -c t.c && llvm-dwarfdump t.o | grep __int128
                  DW_AT_type      (0x00000033 "unsigned __int128")
                  DW_AT_name      ("unsigned __int128")

The test change in this patch tries to test type name before
doing actual test.

Signed-off-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Reviewed-by: Alan Maguire <alan.maguire@oracle.com>
Link: https://lore.kernel.org/bpf/20210924025856.2192476-1-yhs@fb.com
---
 tools/testing/selftests/bpf/prog_tests/btf_dump.c | 27 ++++++++++++++++++-----
 1 file changed, 21 insertions(+), 6 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/prog_tests/btf_dump.c b/tools/testing/selftests/bpf/prog_tests/btf_dump.c
index 52ccf0cf35e1..87f9df653e4e 100644
--- a/tools/testing/selftests/bpf/prog_tests/btf_dump.c
+++ b/tools/testing/selftests/bpf/prog_tests/btf_dump.c
@@ -358,12 +358,27 @@ static void test_btf_dump_int_data(struct btf *btf, struct btf_dump *d,
 	TEST_BTF_DUMP_DATA_OVER(btf, d, NULL, str, int, sizeof(int)-1, "", 1);
 
 #ifdef __SIZEOF_INT128__
-	TEST_BTF_DUMP_DATA(btf, d, NULL, str, __int128, BTF_F_COMPACT,
-			   "(__int128)0xffffffffffffffff",
-			   0xffffffffffffffff);
-	ASSERT_OK(btf_dump_data(btf, d, "__int128", NULL, 0, &i, 16, str,
-				"(__int128)0xfffffffffffffffffffffffffffffffe"),
-		  "dump __int128");
+	/* gcc encode unsigned __int128 type with name "__int128 unsigned" in dwarf,
+	 * and clang encode it with name "unsigned __int128" in dwarf.
+	 * Do an availability test for either variant before doing actual test.
+	 */
+	if (btf__find_by_name(btf, "unsigned __int128") > 0) {
+		TEST_BTF_DUMP_DATA(btf, d, NULL, str, unsigned __int128, BTF_F_COMPACT,
+				   "(unsigned __int128)0xffffffffffffffff",
+				   0xffffffffffffffff);
+		ASSERT_OK(btf_dump_data(btf, d, "unsigned __int128", NULL, 0, &i, 16, str,
+					"(unsigned __int128)0xfffffffffffffffffffffffffffffffe"),
+			  "dump unsigned __int128");
+	} else if (btf__find_by_name(btf, "__int128 unsigned") > 0) {
+		TEST_BTF_DUMP_DATA(btf, d, NULL, str, __int128 unsigned, BTF_F_COMPACT,
+				   "(__int128 unsigned)0xffffffffffffffff",
+				   0xffffffffffffffff);
+		ASSERT_OK(btf_dump_data(btf, d, "__int128 unsigned", NULL, 0, &i, 16, str,
+					"(__int128 unsigned)0xfffffffffffffffffffffffffffffffe"),
+			  "dump unsigned __int128");
+	} else {
+		ASSERT_TRUE(false, "unsigned_int128_not_found");
+	}
 #endif
 }
 
-- 
cgit v1.2.3


From 54ea6079b7d5fd5c6d2b98322a892188d6a1db78 Mon Sep 17 00:00:00 2001
From: Martin KaFai Lau <kafai@fb.com>
Date: Tue, 21 Sep 2021 17:49:47 -0700
Subject: bpf: selftest: A bpf prog that has a 32bit scalar spill

It is a simplified example that can trigger a 32bit scalar spill.
The const scalar is refilled and added to a skb->data later.
Since the reg state of the 32bit scalar spill is not saved now,
adding the refilled reg to skb->data and then comparing it with
skb->data_end cannot verify the skb->data access.

With the earlier verifier patch and the llvm patch [1].  The verifier
can correctly verify the bpf prog.

Here is the snippet of the verifier log that leads to verifier conclusion
that the packet data is unsafe to read.  The log is from the kerne
without the previous verifier patch to save the <8-byte scalar spill.
67: R0=inv1 R1=inv17 R2=invP2 R3=inv1 R4=pkt(id=0,off=68,r=102,imm=0) R5=inv102 R6=pkt(id=0,off=62,r=102,imm=0) R7=pkt(id=0,off=0,r=102,imm=0) R8=pkt_end(id=0,off=0,imm=0) R9=inv17 R10=fp0
67: (63) *(u32 *)(r10 -12) = r5
68: R0=inv1 R1=inv17 R2=invP2 R3=inv1 R4=pkt(id=0,off=68,r=102,imm=0) R5=inv102 R6=pkt(id=0,off=62,r=102,imm=0) R7=pkt(id=0,off=0,r=102,imm=0) R8=pkt_end(id=0,off=0,imm=0) R9=inv17 R10=fp0 fp-16=mmmm????
...
101: R0_w=map_value_or_null(id=2,off=0,ks=16,vs=1,imm=0) R6_w=pkt(id=0,off=70,r=102,imm=0) R7=pkt(id=0,off=0,r=102,imm=0) R8=pkt_end(id=0,off=0,imm=0) R9=inv17 R10=fp0 fp-16=mmmmmmmm
101: (61) r1 = *(u32 *)(r10 -12)
102: R0_w=map_value_or_null(id=2,off=0,ks=16,vs=1,imm=0) R1_w=inv(id=0,umax_value=4294967295,var_off=(0x0; 0xffffffff)) R6_w=pkt(id=0,off=70,r=102,imm=0) R7=pkt(id=0,off=0,r=102,imm=0) R8=pkt_end(id=0,off=0,imm=0) R9=inv17 R10=fp0 fp-16=mmmmmmmm
102: (bc) w1 = w1
103: R0_w=map_value_or_null(id=2,off=0,ks=16,vs=1,imm=0) R1_w=inv(id=0,umax_value=4294967295,var_off=(0x0; 0xffffffff)) R6_w=pkt(id=0,off=70,r=102,imm=0) R7=pkt(id=0,off=0,r=102,imm=0) R8=pkt_end(id=0,off=0,imm=0) R9=inv17 R10=fp0 fp-16=mmmmmmmm
103: (0f) r7 += r1
last_idx 103 first_idx 67
regs=2 stack=0 before 102: (bc) w1 = w1
regs=2 stack=0 before 101: (61) r1 = *(u32 *)(r10 -12)
104: R0_w=map_value_or_null(id=2,off=0,ks=16,vs=1,imm=0) R1_w=invP(id=0,umax_value=4294967295,var_off=(0x0; 0xffffffff)) R6_w=pkt(id=0,off=70,r=102,imm=0) R7_w=pkt(id=3,off=0,r=0,umax_value=4294967295,var_off=(0x0; 0xffffffff)) R8=pkt_end(id=0,off=0,imm=0) R9=inv17 R10=fp0 fp-16=mmmmmmmm
...
127: R0_w=inv1 R1=invP(id=0,umax_value=4294967295,var_off=(0x0; 0xffffffff)) R6=pkt(id=0,off=70,r=102,imm=0) R7=pkt(id=3,off=0,r=0,umax_value=4294967295,var_off=(0x0; 0xffffffff)) R8=pkt_end(id=0,off=0,imm=0) R9_w=invP17 R10=fp0 fp-16=mmmmmmmm
127: (bf) r1 = r7
128: R0_w=inv1 R1_w=pkt(id=3,off=0,r=0,umax_value=4294967295,var_off=(0x0; 0xffffffff)) R6=pkt(id=0,off=70,r=102,imm=0) R7=pkt(id=3,off=0,r=0,umax_value=4294967295,var_off=(0x0; 0xffffffff)) R8=pkt_end(id=0,off=0,imm=0) R9_w=invP17 R10=fp0 fp-16=mmmmmmmm
128: (07) r1 += 8
129: R0_w=inv1 R1_w=pkt(id=3,off=8,r=0,umax_value=4294967295,var_off=(0x0; 0xffffffff)) R6=pkt(id=0,off=70,r=102,imm=0) R7=pkt(id=3,off=0,r=0,umax_value=4294967295,var_off=(0x0; 0xffffffff)) R8=pkt_end(id=0,off=0,imm=0) R9_w=invP17 R10=fp0 fp-16=mmmmmmmm
129: (b4) w0 = 1
130: R0=inv1 R1=pkt(id=3,off=8,r=0,umax_value=4294967295,var_off=(0x0; 0xffffffff)) R6=pkt(id=0,off=70,r=102,imm=0) R7=pkt(id=3,off=0,r=0,umax_value=4294967295,var_off=(0x0; 0xffffffff)) R8=pkt_end(id=0,off=0,imm=0) R9=invP17 R10=fp0 fp-16=mmmmmmmm
130: (2d) if r1 > r8 goto pc-66
 R0=inv1 R1=pkt(id=3,off=8,r=0,umax_value=4294967295,var_off=(0x0; 0xffffffff)) R6=pkt(id=0,off=70,r=102,imm=0) R7=pkt(id=3,off=0,r=0,umax_value=4294967295,var_off=(0x0; 0xffffffff)) R8=pkt_end(id=0,off=0,imm=0) R9=invP17 R10=fp0 fp-16=mmmmmmmm
131: R0=inv1 R1=pkt(id=3,off=8,r=0,umax_value=4294967295,var_off=(0x0; 0xffffffff)) R6=pkt(id=0,off=70,r=102,imm=0) R7=pkt(id=3,off=0,r=0,umax_value=4294967295,var_off=(0x0; 0xffffffff)) R8=pkt_end(id=0,off=0,imm=0) R9=invP17 R10=fp0 fp-16=mmmmmmmm
131: (69) r6 = *(u16 *)(r7 +0)
invalid access to packet, off=0 size=2, R7(id=3,off=0,r=0)
R7 offset is outside of the packet

[1]: https://reviews.llvm.org/D109073

Signed-off-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20210922004947.626286-1-kafai@fb.com
---
 tools/testing/selftests/bpf/README.rst           |  13 +
 tools/testing/selftests/bpf/prog_tests/xdpwall.c |  15 +
 tools/testing/selftests/bpf/progs/xdpwall.c      | 365 +++++++++++++++++++++++
 3 files changed, 393 insertions(+)
 create mode 100644 tools/testing/selftests/bpf/prog_tests/xdpwall.c
 create mode 100644 tools/testing/selftests/bpf/progs/xdpwall.c

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/README.rst b/tools/testing/selftests/bpf/README.rst
index 8200c0da2769..554553acc6d9 100644
--- a/tools/testing/selftests/bpf/README.rst
+++ b/tools/testing/selftests/bpf/README.rst
@@ -242,3 +242,16 @@ To fix this issue, user newer libbpf.
 .. Links
 .. _clang reloc patch: https://reviews.llvm.org/D102712
 .. _kernel llvm reloc: /Documentation/bpf/llvm_reloc.rst
+
+Clang dependencies for the u32 spill test (xdpwall)
+===================================================
+The xdpwall selftest requires a change in `Clang 14`__.
+
+Without it, the xdpwall selftest will fail and the error message
+from running test_progs will look like:
+
+.. code-block:: console
+
+  test_xdpwall:FAIL:Does LLVM have https://reviews.llvm.org/D109073? unexpected error: -4007
+
+__ https://reviews.llvm.org/D109073
diff --git a/tools/testing/selftests/bpf/prog_tests/xdpwall.c b/tools/testing/selftests/bpf/prog_tests/xdpwall.c
new file mode 100644
index 000000000000..f3927829a55a
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/xdpwall.c
@@ -0,0 +1,15 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2021 Facebook */
+
+#include "test_progs.h"
+#include "xdpwall.skel.h"
+
+void test_xdpwall(void)
+{
+	struct xdpwall *skel;
+
+	skel = xdpwall__open_and_load();
+	ASSERT_OK_PTR(skel, "Does LLMV have https://reviews.llvm.org/D109073?");
+
+	xdpwall__destroy(skel);
+}
diff --git a/tools/testing/selftests/bpf/progs/xdpwall.c b/tools/testing/selftests/bpf/progs/xdpwall.c
new file mode 100644
index 000000000000..7a891a0c3a39
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/xdpwall.c
@@ -0,0 +1,365 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2021 Facebook */
+#include <stdbool.h>
+#include <stdint.h>
+#include <linux/stddef.h>
+#include <linux/if_ether.h>
+#include <linux/in.h>
+#include <linux/in6.h>
+#include <linux/ip.h>
+#include <linux/ipv6.h>
+#include <linux/tcp.h>
+#include <linux/udp.h>
+#include <linux/bpf.h>
+#include <linux/types.h>
+#include <bpf/bpf_endian.h>
+#include <bpf/bpf_helpers.h>
+
+enum pkt_parse_err {
+	NO_ERR,
+	BAD_IP6_HDR,
+	BAD_IP4GUE_HDR,
+	BAD_IP6GUE_HDR,
+};
+
+enum pkt_flag {
+	TUNNEL = 0x1,
+	TCP_SYN = 0x2,
+	QUIC_INITIAL_FLAG = 0x4,
+	TCP_ACK = 0x8,
+	TCP_RST = 0x10
+};
+
+struct v4_lpm_key {
+	__u32 prefixlen;
+	__u32 src;
+};
+
+struct v4_lpm_val {
+	struct v4_lpm_key key;
+	__u8 val;
+};
+
+struct {
+	__uint(type, BPF_MAP_TYPE_HASH);
+	__uint(max_entries, 16);
+	__type(key, struct in6_addr);
+	__type(value, bool);
+} v6_addr_map SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_HASH);
+	__uint(max_entries, 16);
+	__type(key, __u32);
+	__type(value, bool);
+} v4_addr_map SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_LPM_TRIE);
+	__uint(max_entries, 16);
+	__uint(key_size, sizeof(struct v4_lpm_key));
+	__uint(value_size, sizeof(struct v4_lpm_val));
+	__uint(map_flags, BPF_F_NO_PREALLOC);
+} v4_lpm_val_map SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__uint(max_entries, 16);
+	__type(key, int);
+	__type(value, __u8);
+} tcp_port_map SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__uint(max_entries, 16);
+	__type(key, int);
+	__type(value, __u16);
+} udp_port_map SEC(".maps");
+
+enum ip_type { V4 = 1, V6 = 2 };
+
+struct fw_match_info {
+	__u8 v4_src_ip_match;
+	__u8 v6_src_ip_match;
+	__u8 v4_src_prefix_match;
+	__u8 v4_dst_prefix_match;
+	__u8 tcp_dp_match;
+	__u16 udp_sp_match;
+	__u16 udp_dp_match;
+	bool is_tcp;
+	bool is_tcp_syn;
+};
+
+struct pkt_info {
+	enum ip_type type;
+	union {
+		struct iphdr *ipv4;
+		struct ipv6hdr *ipv6;
+	} ip;
+	int sport;
+	int dport;
+	__u16 trans_hdr_offset;
+	__u8 proto;
+	__u8 flags;
+};
+
+static __always_inline struct ethhdr *parse_ethhdr(void *data, void *data_end)
+{
+	struct ethhdr *eth = data;
+
+	if (eth + 1 > data_end)
+		return NULL;
+
+	return eth;
+}
+
+static __always_inline __u8 filter_ipv6_addr(const struct in6_addr *ipv6addr)
+{
+	__u8 *leaf;
+
+	leaf = bpf_map_lookup_elem(&v6_addr_map, ipv6addr);
+
+	return leaf ? *leaf : 0;
+}
+
+static __always_inline __u8 filter_ipv4_addr(const __u32 ipaddr)
+{
+	__u8 *leaf;
+
+	leaf = bpf_map_lookup_elem(&v4_addr_map, &ipaddr);
+
+	return leaf ? *leaf : 0;
+}
+
+static __always_inline __u8 filter_ipv4_lpm(const __u32 ipaddr)
+{
+	struct v4_lpm_key v4_key = {};
+	struct v4_lpm_val *lpm_val;
+
+	v4_key.src = ipaddr;
+	v4_key.prefixlen = 32;
+
+	lpm_val = bpf_map_lookup_elem(&v4_lpm_val_map, &v4_key);
+
+	return lpm_val ? lpm_val->val : 0;
+}
+
+
+static __always_inline void
+filter_src_dst_ip(struct pkt_info* info, struct fw_match_info* match_info)
+{
+	if (info->type == V6) {
+		match_info->v6_src_ip_match =
+			filter_ipv6_addr(&info->ip.ipv6->saddr);
+	} else if (info->type == V4) {
+		match_info->v4_src_ip_match =
+			filter_ipv4_addr(info->ip.ipv4->saddr);
+		match_info->v4_src_prefix_match =
+			filter_ipv4_lpm(info->ip.ipv4->saddr);
+		match_info->v4_dst_prefix_match =
+			filter_ipv4_lpm(info->ip.ipv4->daddr);
+	}
+}
+
+static __always_inline void *
+get_transport_hdr(__u16 offset, void *data, void *data_end)
+{
+	if (offset > 255 || data + offset > data_end)
+		return NULL;
+
+	return data + offset;
+}
+
+static __always_inline bool tcphdr_only_contains_flag(struct tcphdr *tcp,
+						      __u32 FLAG)
+{
+	return (tcp_flag_word(tcp) &
+		(TCP_FLAG_ACK | TCP_FLAG_RST | TCP_FLAG_SYN | TCP_FLAG_FIN)) == FLAG;
+}
+
+static __always_inline void set_tcp_flags(struct pkt_info *info,
+					  struct tcphdr *tcp) {
+	if (tcphdr_only_contains_flag(tcp, TCP_FLAG_SYN))
+		info->flags |= TCP_SYN;
+	else if (tcphdr_only_contains_flag(tcp, TCP_FLAG_ACK))
+		info->flags |= TCP_ACK;
+	else if (tcphdr_only_contains_flag(tcp, TCP_FLAG_RST))
+		info->flags |= TCP_RST;
+}
+
+static __always_inline bool
+parse_tcp(struct pkt_info *info, void *transport_hdr, void *data_end)
+{
+	struct tcphdr *tcp = transport_hdr;
+
+	if (tcp + 1 > data_end)
+		return false;
+
+	info->sport = bpf_ntohs(tcp->source);
+	info->dport = bpf_ntohs(tcp->dest);
+	set_tcp_flags(info, tcp);
+
+	return true;
+}
+
+static __always_inline bool
+parse_udp(struct pkt_info *info, void *transport_hdr, void *data_end)
+{
+	struct udphdr *udp = transport_hdr;
+
+	if (udp + 1 > data_end)
+		return false;
+
+	info->sport = bpf_ntohs(udp->source);
+	info->dport = bpf_ntohs(udp->dest);
+
+	return true;
+}
+
+static __always_inline __u8 filter_tcp_port(int port)
+{
+	__u8 *leaf = bpf_map_lookup_elem(&tcp_port_map, &port);
+
+	return leaf ? *leaf : 0;
+}
+
+static __always_inline __u16 filter_udp_port(int port)
+{
+	__u16 *leaf = bpf_map_lookup_elem(&udp_port_map, &port);
+
+	return leaf ? *leaf : 0;
+}
+
+static __always_inline bool
+filter_transport_hdr(void *transport_hdr, void *data_end,
+		     struct pkt_info *info, struct fw_match_info *match_info)
+{
+	if (info->proto == IPPROTO_TCP) {
+		if (!parse_tcp(info, transport_hdr, data_end))
+			return false;
+
+		match_info->is_tcp = true;
+		match_info->is_tcp_syn = (info->flags & TCP_SYN) > 0;
+
+		match_info->tcp_dp_match = filter_tcp_port(info->dport);
+	} else if (info->proto == IPPROTO_UDP) {
+		if (!parse_udp(info, transport_hdr, data_end))
+			return false;
+
+		match_info->udp_dp_match = filter_udp_port(info->dport);
+		match_info->udp_sp_match = filter_udp_port(info->sport);
+	}
+
+	return true;
+}
+
+static __always_inline __u8
+parse_gue_v6(struct pkt_info *info, struct ipv6hdr *ip6h, void *data_end)
+{
+	struct udphdr *udp = (struct udphdr *)(ip6h + 1);
+	void *encap_data = udp + 1;
+
+	if (udp + 1 > data_end)
+		return BAD_IP6_HDR;
+
+	if (udp->dest != bpf_htons(6666))
+		return NO_ERR;
+
+	info->flags |= TUNNEL;
+
+	if (encap_data + 1 > data_end)
+		return BAD_IP6GUE_HDR;
+
+	if (*(__u8 *)encap_data & 0x30) {
+		struct ipv6hdr *inner_ip6h = encap_data;
+
+		if (inner_ip6h + 1 > data_end)
+			return BAD_IP6GUE_HDR;
+
+		info->type = V6;
+		info->proto = inner_ip6h->nexthdr;
+		info->ip.ipv6 = inner_ip6h;
+		info->trans_hdr_offset += sizeof(struct ipv6hdr) + sizeof(struct udphdr);
+	} else {
+		struct iphdr *inner_ip4h = encap_data;
+
+		if (inner_ip4h + 1 > data_end)
+			return BAD_IP6GUE_HDR;
+
+		info->type = V4;
+		info->proto = inner_ip4h->protocol;
+		info->ip.ipv4 = inner_ip4h;
+		info->trans_hdr_offset += sizeof(struct iphdr) + sizeof(struct udphdr);
+	}
+
+	return NO_ERR;
+}
+
+static __always_inline __u8 parse_ipv6_gue(struct pkt_info *info,
+					   void *data, void *data_end)
+{
+	struct ipv6hdr *ip6h = data + sizeof(struct ethhdr);
+
+	if (ip6h + 1 > data_end)
+		return BAD_IP6_HDR;
+
+	info->proto = ip6h->nexthdr;
+	info->ip.ipv6 = ip6h;
+	info->type = V6;
+	info->trans_hdr_offset = sizeof(struct ethhdr) + sizeof(struct ipv6hdr);
+
+	if (info->proto == IPPROTO_UDP)
+		return parse_gue_v6(info, ip6h, data_end);
+
+	return NO_ERR;
+}
+
+SEC("xdp")
+int edgewall(struct xdp_md *ctx)
+{
+	void *data_end = (void *)(long)(ctx->data_end);
+	void *data = (void *)(long)(ctx->data);
+	struct fw_match_info match_info = {};
+	struct pkt_info info = {};
+	__u8 parse_err = NO_ERR;
+	void *transport_hdr;
+	struct ethhdr *eth;
+	bool filter_res;
+	__u32 proto;
+
+	eth = parse_ethhdr(data, data_end);
+	if (!eth)
+		return XDP_DROP;
+
+	proto = eth->h_proto;
+	if (proto != bpf_htons(ETH_P_IPV6))
+		return XDP_DROP;
+
+	if (parse_ipv6_gue(&info, data, data_end))
+		return XDP_DROP;
+
+	if (info.proto == IPPROTO_ICMPV6)
+		return XDP_PASS;
+
+	if (info.proto != IPPROTO_TCP && info.proto != IPPROTO_UDP)
+		return XDP_DROP;
+
+	filter_src_dst_ip(&info, &match_info);
+
+	transport_hdr = get_transport_hdr(info.trans_hdr_offset, data,
+					  data_end);
+	if (!transport_hdr)
+		return XDP_DROP;
+
+	filter_res = filter_transport_hdr(transport_hdr, data_end,
+					  &info, &match_info);
+	if (!filter_res)
+		return XDP_DROP;
+
+	if (match_info.is_tcp && !match_info.is_tcp_syn)
+		return XDP_PASS;
+
+	return XDP_DROP;
+}
+
+char LICENSE[] SEC("license") = "GPL";
-- 
cgit v1.2.3


From ef979017b837031cbe3f2f7a4d78b00c48dc770b Mon Sep 17 00:00:00 2001
From: Martin KaFai Lau <kafai@fb.com>
Date: Tue, 21 Sep 2021 17:49:53 -0700
Subject: bpf: selftest: Add verifier tests for <8-byte scalar spill and refill

This patch adds a few verifier tests for <8-byte spill and refill.

Signed-off-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20210922004953.627183-1-kafai@fb.com
---
 tools/testing/selftests/bpf/verifier/spill_fill.c | 161 ++++++++++++++++++++++
 1 file changed, 161 insertions(+)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/verifier/spill_fill.c b/tools/testing/selftests/bpf/verifier/spill_fill.c
index 0b943897aaf6..c9991c3f3bd2 100644
--- a/tools/testing/selftests/bpf/verifier/spill_fill.c
+++ b/tools/testing/selftests/bpf/verifier/spill_fill.c
@@ -104,3 +104,164 @@
 	.result = ACCEPT,
 	.retval = POINTER_VALUE,
 },
+{
+	"Spill and refill a u32 const scalar.  Offset to skb->data",
+	.insns = {
+	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+		    offsetof(struct __sk_buff, data)),
+	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+		    offsetof(struct __sk_buff, data_end)),
+	/* r4 = 20 */
+	BPF_MOV32_IMM(BPF_REG_4, 20),
+	/* *(u32 *)(r10 -8) = r4 */
+	BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_4, -8),
+	/* r4 = *(u32 *)(r10 -8) */
+	BPF_LDX_MEM(BPF_W, BPF_REG_4, BPF_REG_10, -8),
+	/* r0 = r2 */
+	BPF_MOV64_REG(BPF_REG_0, BPF_REG_2),
+	/* r0 += r4 R0=pkt R2=pkt R3=pkt_end R4=inv20 */
+	BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_4),
+	/* if (r0 > r3) R0=pkt,off=20 R2=pkt R3=pkt_end R4=inv20 */
+	BPF_JMP_REG(BPF_JGT, BPF_REG_0, BPF_REG_3, 1),
+	/* r0 = *(u32 *)r2 R0=pkt,off=20,r=20 R2=pkt,r=20 R3=pkt_end R4=inv20 */
+	BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_2, 0),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	},
+	.result = ACCEPT,
+	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+},
+{
+	"Spill a u32 const, refill from another half of the uninit u32 from the stack",
+	.insns = {
+	/* r4 = 20 */
+	BPF_MOV32_IMM(BPF_REG_4, 20),
+	/* *(u32 *)(r10 -8) = r4 */
+	BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_4, -8),
+	/* r4 = *(u32 *)(r10 -4) fp-8=????rrrr*/
+	BPF_LDX_MEM(BPF_W, BPF_REG_4, BPF_REG_10, -4),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	},
+	.result = REJECT,
+	.errstr = "invalid read from stack off -4+0 size 4",
+	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+},
+{
+	"Spill a u32 const scalar.  Refill as u16.  Offset to skb->data",
+	.insns = {
+	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+		    offsetof(struct __sk_buff, data)),
+	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+		    offsetof(struct __sk_buff, data_end)),
+	/* r4 = 20 */
+	BPF_MOV32_IMM(BPF_REG_4, 20),
+	/* *(u32 *)(r10 -8) = r4 */
+	BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_4, -8),
+	/* r4 = *(u16 *)(r10 -8) */
+	BPF_LDX_MEM(BPF_H, BPF_REG_4, BPF_REG_10, -8),
+	/* r0 = r2 */
+	BPF_MOV64_REG(BPF_REG_0, BPF_REG_2),
+	/* r0 += r4 R0=pkt R2=pkt R3=pkt_end R4=inv,umax=65535 */
+	BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_4),
+	/* if (r0 > r3) R0=pkt,umax=65535 R2=pkt R3=pkt_end R4=inv,umax=65535 */
+	BPF_JMP_REG(BPF_JGT, BPF_REG_0, BPF_REG_3, 1),
+	/* r0 = *(u32 *)r2 R0=pkt,umax=65535 R2=pkt R3=pkt_end R4=inv20 */
+	BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_2, 0),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	},
+	.result = REJECT,
+	.errstr = "invalid access to packet",
+	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+},
+{
+	"Spill a u32 const scalar.  Refill as u16 from fp-6.  Offset to skb->data",
+	.insns = {
+	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+		    offsetof(struct __sk_buff, data)),
+	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+		    offsetof(struct __sk_buff, data_end)),
+	/* r4 = 20 */
+	BPF_MOV32_IMM(BPF_REG_4, 20),
+	/* *(u32 *)(r10 -8) = r4 */
+	BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_4, -8),
+	/* r4 = *(u16 *)(r10 -6) */
+	BPF_LDX_MEM(BPF_H, BPF_REG_4, BPF_REG_10, -6),
+	/* r0 = r2 */
+	BPF_MOV64_REG(BPF_REG_0, BPF_REG_2),
+	/* r0 += r4 R0=pkt R2=pkt R3=pkt_end R4=inv,umax=65535 */
+	BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_4),
+	/* if (r0 > r3) R0=pkt,umax=65535 R2=pkt R3=pkt_end R4=inv,umax=65535 */
+	BPF_JMP_REG(BPF_JGT, BPF_REG_0, BPF_REG_3, 1),
+	/* r0 = *(u32 *)r2 R0=pkt,umax=65535 R2=pkt R3=pkt_end R4=inv20 */
+	BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_2, 0),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	},
+	.result = REJECT,
+	.errstr = "invalid access to packet",
+	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+},
+{
+	"Spill and refill a u32 const scalar at non 8byte aligned stack addr.  Offset to skb->data",
+	.insns = {
+	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+		    offsetof(struct __sk_buff, data)),
+	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+		    offsetof(struct __sk_buff, data_end)),
+	/* r4 = 20 */
+	BPF_MOV32_IMM(BPF_REG_4, 20),
+	/* *(u32 *)(r10 -8) = r4 */
+	BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_4, -8),
+	/* *(u32 *)(r10 -4) = r4 */
+	BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_4, -4),
+	/* r4 = *(u32 *)(r10 -4),  */
+	BPF_LDX_MEM(BPF_W, BPF_REG_4, BPF_REG_10, -4),
+	/* r0 = r2 */
+	BPF_MOV64_REG(BPF_REG_0, BPF_REG_2),
+	/* r0 += r4 R0=pkt R2=pkt R3=pkt_end R4=inv,umax=U32_MAX */
+	BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_4),
+	/* if (r0 > r3) R0=pkt,umax=U32_MAX R2=pkt R3=pkt_end R4=inv */
+	BPF_JMP_REG(BPF_JGT, BPF_REG_0, BPF_REG_3, 1),
+	/* r0 = *(u32 *)r2 R0=pkt,umax=U32_MAX R2=pkt R3=pkt_end R4=inv */
+	BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_2, 0),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	},
+	.result = REJECT,
+	.errstr = "invalid access to packet",
+	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+},
+{
+	"Spill and refill a umax=40 bounded scalar.  Offset to skb->data",
+	.insns = {
+	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+		    offsetof(struct __sk_buff, data)),
+	BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+		    offsetof(struct __sk_buff, data_end)),
+	BPF_LDX_MEM(BPF_DW, BPF_REG_4, BPF_REG_1,
+		    offsetof(struct __sk_buff, tstamp)),
+	BPF_JMP_IMM(BPF_JLE, BPF_REG_4, 40, 2),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	/* *(u32 *)(r10 -8) = r4 R4=inv,umax=40 */
+	BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_4, -8),
+	/* r4 = (*u32 *)(r10 - 8) */
+	BPF_LDX_MEM(BPF_W, BPF_REG_4, BPF_REG_10, -8),
+	/* r2 += r4 R2=pkt R4=inv,umax=40 */
+	BPF_ALU64_REG(BPF_ADD, BPF_REG_2, BPF_REG_4),
+	/* r0 = r2 R2=pkt,umax=40 R4=inv,umax=40 */
+	BPF_MOV64_REG(BPF_REG_0, BPF_REG_2),
+	/* r2 += 20 R0=pkt,umax=40 R2=pkt,umax=40 */
+	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, 20),
+	/* if (r2 > r3) R0=pkt,umax=40 R2=pkt,off=20,umax=40 */
+	BPF_JMP_REG(BPF_JGT, BPF_REG_2, BPF_REG_3, 1),
+	/* r0 = *(u32 *)r0 R0=pkt,r=20,umax=40 R2=pkt,off=20,r=20,umax=40 */
+	BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_0, 0),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	},
+	.result = ACCEPT,
+	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+},
-- 
cgit v1.2.3


From b69c99463d414cc263411462d52f25205657e9af Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@nvidia.com>
Date: Fri, 24 Sep 2021 12:04:27 +0200
Subject: selftests: net: fib_nexthops: Wait before checking reported idle time

The purpose of this test is to verify that after a short activity passes,
the reported time is reasonable: not zero (which could be reported by
mistake), and not something outrageous (which would be indicative of an
issue in used units).

However, the idle time is reported in units of clock_t, or hundredths of
second. If the initial sequence of commands is very quick, it is possible
that the idle time is reported as just flat-out zero. When this test was
recently enabled in our nightly regression, we started seeing spurious
failures for exactly this reason.

Therefore buffer the delay leading up to the test with a sleep, to make
sure there is no legitimate way of reporting 0.

Signed-off-by: Petr Machata <petrm@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/fib_nexthops.sh | 1 +
 1 file changed, 1 insertion(+)

(limited to 'tools')

diff --git a/tools/testing/selftests/net/fib_nexthops.sh b/tools/testing/selftests/net/fib_nexthops.sh
index 0d293391e9a4..b5a69ad191b0 100755
--- a/tools/testing/selftests/net/fib_nexthops.sh
+++ b/tools/testing/selftests/net/fib_nexthops.sh
@@ -2078,6 +2078,7 @@ basic_res()
 		"id 101 index 0 nhid 2 id 101 index 1 nhid 2 id 101 index 2 nhid 1 id 101 index 3 nhid 1"
 	log_test $? 0 "Dump all nexthop buckets in a group"
 
+	sleep 0.1
 	(( $($IP -j nexthop bucket list id 101 |
 	     jq '[.[] | select(.bucket.idle_time > 0 and
 	                       .bucket.idle_time < 2)] | length') == 4 ))
-- 
cgit v1.2.3


From 5b132056123dfe25b0a8c96d1420e9c31cb8edf8 Mon Sep 17 00:00:00 2001
From: Magnus Karlsson <magnus.karlsson@intel.com>
Date: Wed, 22 Sep 2021 09:56:07 +0200
Subject: selftests: xsk: Fix missing initialization

Fix missing initialization of the member rx_pkt_nb in the packet
stream. This leads to some tests declaring success too early as the
test thought all packets had already been received.

Signed-off-by: Magnus Karlsson <magnus.karlsson@intel.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/bpf/20210922075613.12186-8-magnus.karlsson@gmail.com
---
 tools/testing/selftests/bpf/xdpxceiver.c | 7 +++++++
 1 file changed, 7 insertions(+)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/xdpxceiver.c b/tools/testing/selftests/bpf/xdpxceiver.c
index 127bcde06c86..97591e2a69f7 100644
--- a/tools/testing/selftests/bpf/xdpxceiver.c
+++ b/tools/testing/selftests/bpf/xdpxceiver.c
@@ -445,6 +445,12 @@ static void test_spec_set_name(struct test_spec *test, const char *name)
 	strncpy(test->name, name, MAX_TEST_NAME_SIZE);
 }
 
+static void pkt_stream_reset(struct pkt_stream *pkt_stream)
+{
+	if (pkt_stream)
+		pkt_stream->rx_pkt_nb = 0;
+}
+
 static struct pkt *pkt_stream_get_pkt(struct pkt_stream *pkt_stream, u32 pkt_nb)
 {
 	if (pkt_nb >= pkt_stream->nb_pkts)
@@ -1032,6 +1038,7 @@ static void testapp_validate_traffic(struct test_spec *test)
 		exit_with_error(errno);
 
 	test->current_step++;
+	pkt_stream_reset(ifobj_rx->pkt_stream);
 
 	/*Spawn RX thread */
 	pthread_create(&t0, NULL, ifobj_rx->func_ptr, test);
-- 
cgit v1.2.3


From 872a1184dbf2b6ed9f435d6a37ad8007126da982 Mon Sep 17 00:00:00 2001
From: Magnus Karlsson <magnus.karlsson@intel.com>
Date: Wed, 22 Sep 2021 09:56:08 +0200
Subject: selftests: xsk: Put the same buffer only once in the fill ring

Fix a problem where the fill ring was populated with too many
entries. If number of buffers in the umem was smaller than the fill
ring size, the code used to loop over from the beginning of the umem
and start putting the same buffers in again. This is racy indeed as a
later packet can be received overwriting an earlier one before the Rx
thread manages to validate it.

Signed-off-by: Magnus Karlsson <magnus.karlsson@intel.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/bpf/20210922075613.12186-9-magnus.karlsson@gmail.com
---
 tools/testing/selftests/bpf/xdpxceiver.c | 17 +++++++++++------
 1 file changed, 11 insertions(+), 6 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/xdpxceiver.c b/tools/testing/selftests/bpf/xdpxceiver.c
index 97591e2a69f7..c5c68b860ae0 100644
--- a/tools/testing/selftests/bpf/xdpxceiver.c
+++ b/tools/testing/selftests/bpf/xdpxceiver.c
@@ -977,13 +977,18 @@ static void *worker_testapp_validate_tx(void *arg)
 
 static void xsk_populate_fill_ring(struct xsk_umem_info *umem, struct pkt_stream *pkt_stream)
 {
-	u32 idx = 0, i;
+	u32 idx = 0, i, buffers_to_fill;
 	int ret;
 
-	ret = xsk_ring_prod__reserve(&umem->fq, XSK_RING_PROD__DEFAULT_NUM_DESCS, &idx);
-	if (ret != XSK_RING_PROD__DEFAULT_NUM_DESCS)
+	if (umem->num_frames < XSK_RING_PROD__DEFAULT_NUM_DESCS)
+		buffers_to_fill = umem->num_frames;
+	else
+		buffers_to_fill = XSK_RING_PROD__DEFAULT_NUM_DESCS;
+
+	ret = xsk_ring_prod__reserve(&umem->fq, buffers_to_fill, &idx);
+	if (ret != buffers_to_fill)
 		exit_with_error(ENOSPC);
-	for (i = 0; i < XSK_RING_PROD__DEFAULT_NUM_DESCS; i++) {
+	for (i = 0; i < buffers_to_fill; i++) {
 		u64 addr;
 
 		if (pkt_stream->use_addr_for_fill) {
@@ -993,12 +998,12 @@ static void xsk_populate_fill_ring(struct xsk_umem_info *umem, struct pkt_stream
 				break;
 			addr = pkt->addr;
 		} else {
-			addr = (i % umem->num_frames) * umem->frame_size + DEFAULT_OFFSET;
+			addr = i * umem->frame_size + DEFAULT_OFFSET;
 		}
 
 		*xsk_ring_prod__fill_addr(&umem->fq, idx++) = addr;
 	}
-	xsk_ring_prod__submit(&umem->fq, XSK_RING_PROD__DEFAULT_NUM_DESCS);
+	xsk_ring_prod__submit(&umem->fq, buffers_to_fill);
 }
 
 static void *worker_testapp_validate_rx(void *arg)
-- 
cgit v1.2.3


From 89013b8a29281fa42e39406b8b25672cb6ce2341 Mon Sep 17 00:00:00 2001
From: Magnus Karlsson <magnus.karlsson@intel.com>
Date: Wed, 22 Sep 2021 09:56:09 +0200
Subject: selftests: xsk: Fix socket creation retry

The socket creation retry unnecessarily registered the umem once for
every retry. No reason to do this. It wastes memory and it might lead
to too many pages being locked at some point and the failure of a
test.

Signed-off-by: Magnus Karlsson <magnus.karlsson@intel.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/bpf/20210922075613.12186-10-magnus.karlsson@gmail.com
---
 tools/testing/selftests/bpf/xdpxceiver.c | 11 +++++------
 1 file changed, 5 insertions(+), 6 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/xdpxceiver.c b/tools/testing/selftests/bpf/xdpxceiver.c
index c5c68b860ae0..aa5660dc0699 100644
--- a/tools/testing/selftests/bpf/xdpxceiver.c
+++ b/tools/testing/selftests/bpf/xdpxceiver.c
@@ -919,18 +919,17 @@ static void thread_common_ops(struct test_spec *test, struct ifobject *ifobject)
 		u64 umem_sz = ifobject->umem->num_frames * ifobject->umem->frame_size;
 		u32 ctr = 0;
 		void *bufs;
+		int ret;
 
 		bufs = mmap(NULL, umem_sz, PROT_READ | PROT_WRITE, mmap_flags, -1, 0);
 		if (bufs == MAP_FAILED)
 			exit_with_error(errno);
 
-		while (ctr++ < SOCK_RECONF_CTR) {
-			int ret;
-
-			ret = xsk_configure_umem(&ifobject->umem_arr[i], bufs, umem_sz);
-			if (ret)
-				exit_with_error(-ret);
+		ret = xsk_configure_umem(&ifobject->umem_arr[i], bufs, umem_sz);
+		if (ret)
+			exit_with_error(-ret);
 
+		while (ctr++ < SOCK_RECONF_CTR) {
 			ret = xsk_configure_socket(&ifobject->xsk_arr[i], &ifobject->umem_arr[i],
 						   ifobject, i);
 			if (!ret)
-- 
cgit v1.2.3


From 1bf3649688c103f80690a7088a105924f9d5a6e4 Mon Sep 17 00:00:00 2001
From: Magnus Karlsson <magnus.karlsson@intel.com>
Date: Wed, 22 Sep 2021 09:56:10 +0200
Subject: selftests: xsk: Introduce pacing of traffic

Introduce pacing of traffic so that the Tx thread can never send more
packets than the receiver has processed plus the number of packets it
can have in its umem. So at any point in time, the number of in flight
packets (not processed by the Rx thread) are less than or equal to the
number of packets that can be held in the Rx thread's umem.

The batch size is also increased to improve running time.

Signed-off-by: Magnus Karlsson <magnus.karlsson@intel.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/bpf/20210922075613.12186-11-magnus.karlsson@gmail.com
---
 tools/testing/selftests/bpf/xdpxceiver.c | 29 +++++++++++++++++++++++------
 tools/testing/selftests/bpf/xdpxceiver.h |  7 ++++++-
 2 files changed, 29 insertions(+), 7 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/xdpxceiver.c b/tools/testing/selftests/bpf/xdpxceiver.c
index aa5660dc0699..597fbe206026 100644
--- a/tools/testing/selftests/bpf/xdpxceiver.c
+++ b/tools/testing/selftests/bpf/xdpxceiver.c
@@ -384,6 +384,7 @@ static void __test_spec_init(struct test_spec *test, struct ifobject *ifobj_tx,
 		ifobj->umem = &ifobj->umem_arr[0];
 		ifobj->xsk = &ifobj->xsk_arr[0];
 		ifobj->use_poll = false;
+		ifobj->pacing_on = true;
 		ifobj->pkt_stream = test->pkt_stream_default;
 
 		if (i == 0) {
@@ -724,6 +725,7 @@ static void receive_pkts(struct pkt_stream *pkt_stream, struct xsk_socket_info *
 {
 	struct pkt *pkt = pkt_stream_get_next_rx_pkt(pkt_stream);
 	u32 idx_rx = 0, idx_fq = 0, rcvd, i;
+	u32 total = 0;
 	int ret;
 
 	while (pkt) {
@@ -772,6 +774,13 @@ static void receive_pkts(struct pkt_stream *pkt_stream, struct xsk_socket_info *
 
 		xsk_ring_prod__submit(&xsk->umem->fq, rcvd);
 		xsk_ring_cons__release(&xsk->rx, rcvd);
+
+		pthread_mutex_lock(&pacing_mutex);
+		pkts_in_flight -= rcvd;
+		total += rcvd;
+		if (pkts_in_flight < umem->num_frames)
+			pthread_cond_signal(&pacing_cond);
+		pthread_mutex_unlock(&pacing_mutex);
 	}
 }
 
@@ -797,10 +806,19 @@ static u32 __send_pkts(struct ifobject *ifobject, u32 pkt_nb)
 			valid_pkts++;
 	}
 
+	pthread_mutex_lock(&pacing_mutex);
+	pkts_in_flight += valid_pkts;
+	if (ifobject->pacing_on && pkts_in_flight >= ifobject->umem->num_frames - BATCH_SIZE) {
+		kick_tx(xsk);
+		pthread_cond_wait(&pacing_cond, &pacing_mutex);
+	}
+	pthread_mutex_unlock(&pacing_mutex);
+
 	xsk_ring_prod__submit(&xsk->tx, i);
 	xsk->outstanding_tx += valid_pkts;
-	complete_pkts(xsk, BATCH_SIZE);
+	complete_pkts(xsk, i);
 
+	usleep(10);
 	return i;
 }
 
@@ -819,8 +837,6 @@ static void send_pkts(struct ifobject *ifobject)
 	fds.events = POLLOUT;
 
 	while (pkt_cnt < ifobject->pkt_stream->nb_pkts) {
-		u32 sent;
-
 		if (ifobject->use_poll) {
 			int ret;
 
@@ -832,9 +848,7 @@ static void send_pkts(struct ifobject *ifobject)
 				continue;
 		}
 
-		sent = __send_pkts(ifobject, pkt_cnt);
-		pkt_cnt += sent;
-		usleep(10);
+		pkt_cnt += __send_pkts(ifobject, pkt_cnt);
 	}
 
 	wait_for_tx_completion(ifobject->xsk);
@@ -1043,6 +1057,7 @@ static void testapp_validate_traffic(struct test_spec *test)
 
 	test->current_step++;
 	pkt_stream_reset(ifobj_rx->pkt_stream);
+	pkts_in_flight = 0;
 
 	/*Spawn RX thread */
 	pthread_create(&t0, NULL, ifobj_rx->func_ptr, test);
@@ -1126,6 +1141,8 @@ static void testapp_stats(struct test_spec *test)
 	for (i = 0; i < STAT_TEST_TYPE_MAX; i++) {
 		test_spec_reset(test);
 		stat_test_type = i;
+		/* No or few packets will be received so cannot pace packets */
+		test->ifobj_tx->pacing_on = false;
 
 		switch (stat_test_type) {
 		case STAT_TEST_RX_DROPPED:
diff --git a/tools/testing/selftests/bpf/xdpxceiver.h b/tools/testing/selftests/bpf/xdpxceiver.h
index 5ac4a5e64744..00790c976f4f 100644
--- a/tools/testing/selftests/bpf/xdpxceiver.h
+++ b/tools/testing/selftests/bpf/xdpxceiver.h
@@ -35,7 +35,7 @@
 #define UDP_PKT_DATA_SIZE (UDP_PKT_SIZE - sizeof(struct udphdr))
 #define USLEEP_MAX 10000
 #define SOCK_RECONF_CTR 10
-#define BATCH_SIZE 8
+#define BATCH_SIZE 64
 #define POLL_TMOUT 1000
 #define DEFAULT_PKT_CNT (4 * 1024)
 #define DEFAULT_UMEM_BUFFERS (DEFAULT_PKT_CNT / 4)
@@ -136,6 +136,7 @@ struct ifobject {
 	bool tx_on;
 	bool rx_on;
 	bool use_poll;
+	bool pacing_on;
 	u8 dst_mac[ETH_ALEN];
 	u8 src_mac[ETH_ALEN];
 };
@@ -151,5 +152,9 @@ struct test_spec {
 };
 
 pthread_barrier_t barr;
+pthread_mutex_t pacing_mutex = PTHREAD_MUTEX_INITIALIZER;
+pthread_cond_t pacing_cond = PTHREAD_COND_INITIALIZER;
+
+u32 pkts_in_flight;
 
 #endif				/* XDPXCEIVER_H */
-- 
cgit v1.2.3


From 96a40678ce5390cd8515ff32e55ad932fd1fa328 Mon Sep 17 00:00:00 2001
From: Magnus Karlsson <magnus.karlsson@intel.com>
Date: Wed, 22 Sep 2021 09:56:11 +0200
Subject: selftests: xsk: Add single packet test

Add a test where a single packet is sent and received. This might
sound like a silly test, but since many of the interfaces in xsk are
batched, it is important to be able to validate that we did not break
something as fundamental as just receiving single packets, instead of
batches of packets at high speed.

Signed-off-by: Magnus Karlsson <magnus.karlsson@intel.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/bpf/20210922075613.12186-12-magnus.karlsson@gmail.com
---
 tools/testing/selftests/bpf/xdpxceiver.c | 13 +++++++++++++
 tools/testing/selftests/bpf/xdpxceiver.h |  1 +
 2 files changed, 14 insertions(+)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/xdpxceiver.c b/tools/testing/selftests/bpf/xdpxceiver.c
index 597fbe206026..3beea7531c8e 100644
--- a/tools/testing/selftests/bpf/xdpxceiver.c
+++ b/tools/testing/selftests/bpf/xdpxceiver.c
@@ -1217,6 +1217,15 @@ static bool testapp_unaligned(struct test_spec *test)
 	return true;
 }
 
+static void testapp_single_pkt(struct test_spec *test)
+{
+	struct pkt pkts[] = {{0x1000, PKT_SIZE, 0, true}};
+
+	pkt_stream_generate_custom(test, pkts, ARRAY_SIZE(pkts));
+	testapp_validate_traffic(test);
+	pkt_stream_restore_default(test);
+}
+
 static void testapp_invalid_desc(struct test_spec *test)
 {
 	struct pkt pkts[] = {
@@ -1298,6 +1307,10 @@ static void run_pkt_test(struct test_spec *test, enum test_mode mode, enum test_
 		test_spec_set_name(test, "RUN_TO_COMPLETION");
 		testapp_validate_traffic(test);
 		break;
+	case TEST_TYPE_RUN_TO_COMPLETION_SINGLE_PKT:
+		test_spec_set_name(test, "RUN_TO_COMPLETION_SINGLE_PKT");
+		testapp_single_pkt(test);
+		break;
 	case TEST_TYPE_RUN_TO_COMPLETION_2K_FRAME:
 		test_spec_set_name(test, "RUN_TO_COMPLETION_2K_FRAME_SIZE");
 		test->ifobj_tx->umem->frame_size = 2048;
diff --git a/tools/testing/selftests/bpf/xdpxceiver.h b/tools/testing/selftests/bpf/xdpxceiver.h
index 00790c976f4f..d075192c95f8 100644
--- a/tools/testing/selftests/bpf/xdpxceiver.h
+++ b/tools/testing/selftests/bpf/xdpxceiver.h
@@ -55,6 +55,7 @@ enum test_mode {
 enum test_type {
 	TEST_TYPE_RUN_TO_COMPLETION,
 	TEST_TYPE_RUN_TO_COMPLETION_2K_FRAME,
+	TEST_TYPE_RUN_TO_COMPLETION_SINGLE_PKT,
 	TEST_TYPE_POLL,
 	TEST_TYPE_UNALIGNED,
 	TEST_TYPE_ALIGNED_INV_DESC,
-- 
cgit v1.2.3


From e4e9baf06a6ea6cfbf69db4c3766a0879329dda2 Mon Sep 17 00:00:00 2001
From: Magnus Karlsson <magnus.karlsson@intel.com>
Date: Wed, 22 Sep 2021 09:56:12 +0200
Subject: selftests: xsk: Change interleaving of packets in unaligned mode

Change the interleaving of packets in unaligned mode. With the current
buffer addresses in the packet stream, the last buffer in the umem
could not be used as a large packet could potentially write over the
end of the umem. The kernel correctly threw this buffer address away
and refused to use it. This is perfectly fine for all regular packet
streams, but the ones used for unaligned mode have every other packet
being at some different offset. As we will add checks for correct
offsets in the next patch, this needs to be fixed. Just start these
page-boundary straddling buffers one page earlier so that the last
one is not on the last page of the umem, making all buffers valid.

Signed-off-by: Magnus Karlsson <magnus.karlsson@intel.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/bpf/20210922075613.12186-13-magnus.karlsson@gmail.com
---
 tools/testing/selftests/bpf/xdpxceiver.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/xdpxceiver.c b/tools/testing/selftests/bpf/xdpxceiver.c
index 3beea7531c8e..fd620f8accfd 100644
--- a/tools/testing/selftests/bpf/xdpxceiver.c
+++ b/tools/testing/selftests/bpf/xdpxceiver.c
@@ -543,14 +543,14 @@ static void pkt_stream_replace(struct test_spec *test, u32 nb_pkts, u32 pkt_len)
 	test->ifobj_rx->pkt_stream = pkt_stream;
 }
 
-static void pkt_stream_replace_half(struct test_spec *test, u32 pkt_len, u32 offset)
+static void pkt_stream_replace_half(struct test_spec *test, u32 pkt_len, int offset)
 {
 	struct xsk_umem_info *umem = test->ifobj_tx->umem;
 	struct pkt_stream *pkt_stream;
 	u32 i;
 
 	pkt_stream = pkt_stream_clone(umem, test->pkt_stream_default);
-	for (i = 0; i < test->pkt_stream_default->nb_pkts; i += 2) {
+	for (i = 1; i < test->pkt_stream_default->nb_pkts; i += 2) {
 		pkt_stream->pkts[i].addr = (i % umem->num_frames) * umem->frame_size + offset;
 		pkt_stream->pkts[i].len = pkt_len;
 	}
@@ -1209,7 +1209,7 @@ static bool testapp_unaligned(struct test_spec *test)
 	test->ifobj_tx->umem->unaligned_mode = true;
 	test->ifobj_rx->umem->unaligned_mode = true;
 	/* Let half of the packets straddle a buffer boundrary */
-	pkt_stream_replace_half(test, PKT_SIZE, test->ifobj_tx->umem->frame_size - 32);
+	pkt_stream_replace_half(test, PKT_SIZE, -PKT_SIZE / 2);
 	test->ifobj_rx->pkt_stream->use_addr_for_fill = true;
 	testapp_validate_traffic(test);
 
-- 
cgit v1.2.3


From e34087fc00f4f853886952711195984abdece7a3 Mon Sep 17 00:00:00 2001
From: Magnus Karlsson <magnus.karlsson@intel.com>
Date: Wed, 22 Sep 2021 09:56:13 +0200
Subject: selftests: xsk: Add frame_headroom test

Add a test for the frame_headroom feature that can be set on the
umem. The logic added validates that all offsets in all tests and
packets are valid, not just the ones that have a specifically
configured frame_headroom.

Signed-off-by: Magnus Karlsson <magnus.karlsson@intel.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/bpf/20210922075613.12186-14-magnus.karlsson@gmail.com
---
 tools/testing/selftests/bpf/xdpxceiver.c | 52 ++++++++++++++++++++++++++------
 tools/testing/selftests/bpf/xdpxceiver.h |  3 +-
 2 files changed, 44 insertions(+), 11 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/xdpxceiver.c b/tools/testing/selftests/bpf/xdpxceiver.c
index fd620f8accfd..6c7cf8aadc79 100644
--- a/tools/testing/selftests/bpf/xdpxceiver.c
+++ b/tools/testing/selftests/bpf/xdpxceiver.c
@@ -514,8 +514,7 @@ static struct pkt_stream *pkt_stream_generate(struct xsk_umem_info *umem, u32 nb
 
 	pkt_stream->nb_pkts = nb_pkts;
 	for (i = 0; i < nb_pkts; i++) {
-		pkt_stream->pkts[i].addr = (i % umem->num_frames) * umem->frame_size +
-			DEFAULT_OFFSET;
+		pkt_stream->pkts[i].addr = (i % umem->num_frames) * umem->frame_size;
 		pkt_stream->pkts[i].len = pkt_len;
 		pkt_stream->pkts[i].payload = i;
 
@@ -642,6 +641,25 @@ static void pkt_dump(void *pkt, u32 len)
 	fprintf(stdout, "---------------------------------------\n");
 }
 
+static bool is_offset_correct(struct xsk_umem_info *umem, struct pkt_stream *pkt_stream, u64 addr,
+			      u64 pkt_stream_addr)
+{
+	u32 headroom = umem->unaligned_mode ? 0 : umem->frame_headroom;
+	u32 offset = addr % umem->frame_size, expected_offset = 0;
+
+	if (!pkt_stream->use_addr_for_fill)
+		pkt_stream_addr = 0;
+
+	expected_offset += (pkt_stream_addr + headroom + XDP_PACKET_HEADROOM) % umem->frame_size;
+
+	if (offset == expected_offset)
+		return true;
+
+	ksft_test_result_fail("ERROR: [%s] expected [%u], got [%u]\n", __func__, expected_offset,
+			      offset);
+	return false;
+}
+
 static bool is_pkt_valid(struct pkt *pkt, void *buffer, u64 addr, u32 len)
 {
 	void *data = xsk_umem__get_data(buffer, addr);
@@ -724,6 +742,7 @@ static void receive_pkts(struct pkt_stream *pkt_stream, struct xsk_socket_info *
 			 struct pollfd *fds)
 {
 	struct pkt *pkt = pkt_stream_get_next_rx_pkt(pkt_stream);
+	struct xsk_umem_info *umem = xsk->umem;
 	u32 idx_rx = 0, idx_fq = 0, rcvd, i;
 	u32 total = 0;
 	int ret;
@@ -731,7 +750,7 @@ static void receive_pkts(struct pkt_stream *pkt_stream, struct xsk_socket_info *
 	while (pkt) {
 		rcvd = xsk_ring_cons__peek(&xsk->rx, BATCH_SIZE, &idx_rx);
 		if (!rcvd) {
-			if (xsk_ring_prod__needs_wakeup(&xsk->umem->fq)) {
+			if (xsk_ring_prod__needs_wakeup(&umem->fq)) {
 				ret = poll(fds, 1, POLL_TMOUT);
 				if (ret < 0)
 					exit_with_error(-ret);
@@ -739,16 +758,16 @@ static void receive_pkts(struct pkt_stream *pkt_stream, struct xsk_socket_info *
 			continue;
 		}
 
-		ret = xsk_ring_prod__reserve(&xsk->umem->fq, rcvd, &idx_fq);
+		ret = xsk_ring_prod__reserve(&umem->fq, rcvd, &idx_fq);
 		while (ret != rcvd) {
 			if (ret < 0)
 				exit_with_error(-ret);
-			if (xsk_ring_prod__needs_wakeup(&xsk->umem->fq)) {
+			if (xsk_ring_prod__needs_wakeup(&umem->fq)) {
 				ret = poll(fds, 1, POLL_TMOUT);
 				if (ret < 0)
 					exit_with_error(-ret);
 			}
-			ret = xsk_ring_prod__reserve(&xsk->umem->fq, rcvd, &idx_fq);
+			ret = xsk_ring_prod__reserve(&umem->fq, rcvd, &idx_fq);
 		}
 
 		for (i = 0; i < rcvd; i++) {
@@ -765,14 +784,17 @@ static void receive_pkts(struct pkt_stream *pkt_stream, struct xsk_socket_info *
 
 			orig = xsk_umem__extract_addr(addr);
 			addr = xsk_umem__add_offset_to_addr(addr);
-			if (!is_pkt_valid(pkt, xsk->umem->buffer, addr, desc->len))
+
+			if (!is_pkt_valid(pkt, umem->buffer, addr, desc->len))
+				return;
+			if (!is_offset_correct(umem, pkt_stream, addr, pkt->addr))
 				return;
 
-			*xsk_ring_prod__fill_addr(&xsk->umem->fq, idx_fq++) = orig;
+			*xsk_ring_prod__fill_addr(&umem->fq, idx_fq++) = orig;
 			pkt = pkt_stream_get_next_rx_pkt(pkt_stream);
 		}
 
-		xsk_ring_prod__submit(&xsk->umem->fq, rcvd);
+		xsk_ring_prod__submit(&umem->fq, rcvd);
 		xsk_ring_cons__release(&xsk->rx, rcvd);
 
 		pthread_mutex_lock(&pacing_mutex);
@@ -1011,7 +1033,7 @@ static void xsk_populate_fill_ring(struct xsk_umem_info *umem, struct pkt_stream
 				break;
 			addr = pkt->addr;
 		} else {
-			addr = i * umem->frame_size + DEFAULT_OFFSET;
+			addr = i * umem->frame_size;
 		}
 
 		*xsk_ring_prod__fill_addr(&umem->fq, idx++) = addr;
@@ -1134,6 +1156,13 @@ static void testapp_bpf_res(struct test_spec *test)
 	testapp_validate_traffic(test);
 }
 
+static void testapp_headroom(struct test_spec *test)
+{
+	test_spec_set_name(test, "UMEM_HEADROOM");
+	test->ifobj_rx->umem->frame_headroom = UMEM_HEADROOM_TEST_SIZE;
+	testapp_validate_traffic(test);
+}
+
 static void testapp_stats(struct test_spec *test)
 {
 	int i;
@@ -1346,6 +1375,9 @@ static void run_pkt_test(struct test_spec *test, enum test_mode mode, enum test_
 		if (!testapp_unaligned(test))
 			return;
 		break;
+	case TEST_TYPE_HEADROOM:
+		testapp_headroom(test);
+		break;
 	default:
 		break;
 	}
diff --git a/tools/testing/selftests/bpf/xdpxceiver.h b/tools/testing/selftests/bpf/xdpxceiver.h
index d075192c95f8..2f705f44b748 100644
--- a/tools/testing/selftests/bpf/xdpxceiver.h
+++ b/tools/testing/selftests/bpf/xdpxceiver.h
@@ -41,7 +41,7 @@
 #define DEFAULT_UMEM_BUFFERS (DEFAULT_PKT_CNT / 4)
 #define UMEM_SIZE (DEFAULT_UMEM_BUFFERS * XSK_UMEM__DEFAULT_FRAME_SIZE)
 #define RX_FULL_RXQSIZE 32
-#define DEFAULT_OFFSET 256
+#define UMEM_HEADROOM_TEST_SIZE 128
 #define XSK_UMEM__INVALID_FRAME_SIZE (XSK_UMEM__DEFAULT_FRAME_SIZE + 1)
 
 #define print_verbose(x...) do { if (opt_verbose) ksft_print_msg(x); } while (0)
@@ -61,6 +61,7 @@ enum test_type {
 	TEST_TYPE_ALIGNED_INV_DESC,
 	TEST_TYPE_ALIGNED_INV_DESC_2K_FRAME,
 	TEST_TYPE_UNALIGNED_INV_DESC,
+	TEST_TYPE_HEADROOM,
 	TEST_TYPE_TEARDOWN,
 	TEST_TYPE_BIDI,
 	TEST_TYPE_STATS,
-- 
cgit v1.2.3


From c3e8c44a90631d2479fec6ecc6ba37e3188f487d Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Toke=20H=C3=B8iland-J=C3=B8rgensen?= <toke@redhat.com>
Date: Mon, 27 Sep 2021 22:58:10 +0200
Subject: libbpf: Ignore STT_SECTION symbols in 'maps' section
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

When parsing legacy map definitions, libbpf would error out when
encountering an STT_SECTION symbol. This becomes a problem because some
versions of binutils will produce SECTION symbols for every section when
processing an ELF file, so BPF files run through 'strip' will end up with
such symbols, making libbpf refuse to load them.

There's not really any reason why erroring out is strictly necessary, so
change libbpf to just ignore SECTION symbols when parsing the ELF.

Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20210927205810.715656-1-toke@redhat.com
---
 tools/lib/bpf/libbpf.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

(limited to 'tools')

diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index ef5db34bf913..453148fe8b4b 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -1869,6 +1869,8 @@ static int bpf_object__init_user_maps(struct bpf_object *obj, bool strict)
 			continue;
 		if (sym.st_shndx != obj->efile.maps_shndx)
 			continue;
+		if (GELF_ST_TYPE(sym.st_info) == STT_SECTION)
+			continue;
 
 		map = bpf_object__add_map(obj);
 		if (IS_ERR(map))
@@ -1881,8 +1883,7 @@ static int bpf_object__init_user_maps(struct bpf_object *obj, bool strict)
 			return -LIBBPF_ERRNO__FORMAT;
 		}
 
-		if (GELF_ST_TYPE(sym.st_info) == STT_SECTION
-		    || GELF_ST_BIND(sym.st_info) == STB_LOCAL) {
+		if (GELF_ST_BIND(sym.st_info) == STB_LOCAL) {
 			pr_warn("map '%s' (legacy): static maps are not supported\n", map_name);
 			return -ENOTSUP;
 		}
-- 
cgit v1.2.3


From 9673268f03ba72efcc00fa95f3fe3744fcae0dd0 Mon Sep 17 00:00:00 2001
From: Andrii Nakryiko <andrii@kernel.org>
Date: Tue, 28 Sep 2021 09:19:37 -0700
Subject: libbpf: Add "tc" SEC_DEF which is a better name for "classifier"

As argued in [0], add "tc" ELF section definition for SCHED_CLS BPF
program type. "classifier" is a misleading terminology and should be
migrated away from.

  [0] https://lore.kernel.org/bpf/270e27b1-e5be-5b1c-b343-51bd644d0747@iogearbox.net/

Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20210928161946.2512801-2-andrii@kernel.org
---
 tools/lib/bpf/libbpf.c | 1 +
 1 file changed, 1 insertion(+)

(limited to 'tools')

diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 453148fe8b4b..0bcd0a4c867a 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -7968,6 +7968,7 @@ static const struct bpf_sec_def section_defs[] = {
 		.attach_fn = attach_kprobe),
 	BPF_PROG_SEC("uretprobe/",		BPF_PROG_TYPE_KPROBE),
 	BPF_PROG_SEC("classifier",		BPF_PROG_TYPE_SCHED_CLS),
+	BPF_PROG_SEC("tc",			BPF_PROG_TYPE_SCHED_CLS),
 	BPF_PROG_SEC("action",			BPF_PROG_TYPE_SCHED_ACT),
 	SEC_DEF("tracepoint/", TRACEPOINT,
 		.attach_fn = attach_tp),
-- 
cgit v1.2.3


From 8fffa0e3451abdd84e4b4e427f7e66040eb24f43 Mon Sep 17 00:00:00 2001
From: Andrii Nakryiko <andrii@kernel.org>
Date: Tue, 28 Sep 2021 09:19:38 -0700
Subject: selftests/bpf: Normalize XDP section names in selftests

Convert almost all SEC("xdp_blah") uses to strict SEC("xdp") to comply
with strict libbpf 1.0 logic of exact section name match for XDP program
types. There is only one exception, which is only tested through
iproute2 and defines multiple XDP programs within the same BPF object.
Given iproute2 still works in non-strict libbpf mode and it doesn't have
means to specify XDP programs by its name (not section name/title),
leave that single file alone for now until iproute2 gains lookup by
function/program name.

Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Dave Marchevsky <davemarchevsky@fb.com>
Link: https://lore.kernel.org/bpf/20210928161946.2512801-3-andrii@kernel.org
---
 tools/testing/selftests/bpf/progs/test_map_in_map.c               | 2 +-
 tools/testing/selftests/bpf/progs/test_tcp_check_syncookie_kern.c | 2 +-
 tools/testing/selftests/bpf/progs/test_xdp.c                      | 2 +-
 tools/testing/selftests/bpf/progs/test_xdp_adjust_tail_grow.c     | 2 +-
 tools/testing/selftests/bpf/progs/test_xdp_adjust_tail_shrink.c   | 4 +---
 tools/testing/selftests/bpf/progs/test_xdp_devmap_helpers.c       | 2 +-
 tools/testing/selftests/bpf/progs/test_xdp_link.c                 | 2 +-
 tools/testing/selftests/bpf/progs/test_xdp_loop.c                 | 2 +-
 tools/testing/selftests/bpf/progs/test_xdp_noinline.c             | 4 ++--
 tools/testing/selftests/bpf/progs/test_xdp_with_cpumap_helpers.c  | 4 ++--
 tools/testing/selftests/bpf/progs/test_xdp_with_devmap_helpers.c  | 4 ++--
 tools/testing/selftests/bpf/progs/xdp_dummy.c                     | 2 +-
 tools/testing/selftests/bpf/progs/xdp_redirect_multi_kern.c       | 4 ++--
 tools/testing/selftests/bpf/progs/xdping_kern.c                   | 4 ++--
 tools/testing/selftests/bpf/test_tcp_check_syncookie.sh           | 2 +-
 tools/testing/selftests/bpf/test_xdp_redirect.sh                  | 4 ++--
 tools/testing/selftests/bpf/test_xdp_redirect_multi.sh            | 2 +-
 tools/testing/selftests/bpf/test_xdp_veth.sh                      | 4 ++--
 tools/testing/selftests/bpf/xdping.c                              | 5 ++---
 19 files changed, 27 insertions(+), 30 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/progs/test_map_in_map.c b/tools/testing/selftests/bpf/progs/test_map_in_map.c
index 1cfeb940cf9f..5f0e0bfc151e 100644
--- a/tools/testing/selftests/bpf/progs/test_map_in_map.c
+++ b/tools/testing/selftests/bpf/progs/test_map_in_map.c
@@ -23,7 +23,7 @@ struct {
 	__uint(value_size, sizeof(__u32));
 } mim_hash SEC(".maps");
 
-SEC("xdp_mimtest")
+SEC("xdp")
 int xdp_mimtest0(struct xdp_md *ctx)
 {
 	int value = 123;
diff --git a/tools/testing/selftests/bpf/progs/test_tcp_check_syncookie_kern.c b/tools/testing/selftests/bpf/progs/test_tcp_check_syncookie_kern.c
index 47cbe2eeae43..fac7ef99f9a6 100644
--- a/tools/testing/selftests/bpf/progs/test_tcp_check_syncookie_kern.c
+++ b/tools/testing/selftests/bpf/progs/test_tcp_check_syncookie_kern.c
@@ -156,7 +156,7 @@ int check_syncookie_clsact(struct __sk_buff *skb)
 	return TC_ACT_OK;
 }
 
-SEC("xdp/check_syncookie")
+SEC("xdp")
 int check_syncookie_xdp(struct xdp_md *ctx)
 {
 	check_syncookie(ctx, (void *)(long)ctx->data,
diff --git a/tools/testing/selftests/bpf/progs/test_xdp.c b/tools/testing/selftests/bpf/progs/test_xdp.c
index 31f9bce37491..e6aa2fc6ce6b 100644
--- a/tools/testing/selftests/bpf/progs/test_xdp.c
+++ b/tools/testing/selftests/bpf/progs/test_xdp.c
@@ -210,7 +210,7 @@ static __always_inline int handle_ipv6(struct xdp_md *xdp)
 	return XDP_TX;
 }
 
-SEC("xdp_tx_iptunnel")
+SEC("xdp")
 int _xdp_tx_iptunnel(struct xdp_md *xdp)
 {
 	void *data_end = (void *)(long)xdp->data_end;
diff --git a/tools/testing/selftests/bpf/progs/test_xdp_adjust_tail_grow.c b/tools/testing/selftests/bpf/progs/test_xdp_adjust_tail_grow.c
index 3d66599eee2e..199c61b7d062 100644
--- a/tools/testing/selftests/bpf/progs/test_xdp_adjust_tail_grow.c
+++ b/tools/testing/selftests/bpf/progs/test_xdp_adjust_tail_grow.c
@@ -2,7 +2,7 @@
 #include <linux/bpf.h>
 #include <bpf/bpf_helpers.h>
 
-SEC("xdp_adjust_tail_grow")
+SEC("xdp")
 int _xdp_adjust_tail_grow(struct xdp_md *xdp)
 {
 	void *data_end = (void *)(long)xdp->data_end;
diff --git a/tools/testing/selftests/bpf/progs/test_xdp_adjust_tail_shrink.c b/tools/testing/selftests/bpf/progs/test_xdp_adjust_tail_shrink.c
index 22065a9cfb25..b7448253d135 100644
--- a/tools/testing/selftests/bpf/progs/test_xdp_adjust_tail_shrink.c
+++ b/tools/testing/selftests/bpf/progs/test_xdp_adjust_tail_shrink.c
@@ -9,9 +9,7 @@
 #include <linux/if_ether.h>
 #include <bpf/bpf_helpers.h>
 
-int _version SEC("version") = 1;
-
-SEC("xdp_adjust_tail_shrink")
+SEC("xdp")
 int _xdp_adjust_tail_shrink(struct xdp_md *xdp)
 {
 	void *data_end = (void *)(long)xdp->data_end;
diff --git a/tools/testing/selftests/bpf/progs/test_xdp_devmap_helpers.c b/tools/testing/selftests/bpf/progs/test_xdp_devmap_helpers.c
index b360ba2bd441..807bf895f42c 100644
--- a/tools/testing/selftests/bpf/progs/test_xdp_devmap_helpers.c
+++ b/tools/testing/selftests/bpf/progs/test_xdp_devmap_helpers.c
@@ -5,7 +5,7 @@
 #include <linux/bpf.h>
 #include <bpf/bpf_helpers.h>
 
-SEC("xdp_dm_log")
+SEC("xdp")
 int xdpdm_devlog(struct xdp_md *ctx)
 {
 	char fmt[] = "devmap redirect: dev %u -> dev %u len %u\n";
diff --git a/tools/testing/selftests/bpf/progs/test_xdp_link.c b/tools/testing/selftests/bpf/progs/test_xdp_link.c
index eb93ea95d1d8..ee7d6ac0f615 100644
--- a/tools/testing/selftests/bpf/progs/test_xdp_link.c
+++ b/tools/testing/selftests/bpf/progs/test_xdp_link.c
@@ -5,7 +5,7 @@
 
 char LICENSE[] SEC("license") = "GPL";
 
-SEC("xdp/handler")
+SEC("xdp")
 int xdp_handler(struct xdp_md *xdp)
 {
 	return 0;
diff --git a/tools/testing/selftests/bpf/progs/test_xdp_loop.c b/tools/testing/selftests/bpf/progs/test_xdp_loop.c
index fcabcda30ba3..27eb52dda92c 100644
--- a/tools/testing/selftests/bpf/progs/test_xdp_loop.c
+++ b/tools/testing/selftests/bpf/progs/test_xdp_loop.c
@@ -206,7 +206,7 @@ static __always_inline int handle_ipv6(struct xdp_md *xdp)
 	return XDP_TX;
 }
 
-SEC("xdp_tx_iptunnel")
+SEC("xdp")
 int _xdp_tx_iptunnel(struct xdp_md *xdp)
 {
 	void *data_end = (void *)(long)xdp->data_end;
diff --git a/tools/testing/selftests/bpf/progs/test_xdp_noinline.c b/tools/testing/selftests/bpf/progs/test_xdp_noinline.c
index 3a67921f62b5..596c4e71bf3a 100644
--- a/tools/testing/selftests/bpf/progs/test_xdp_noinline.c
+++ b/tools/testing/selftests/bpf/progs/test_xdp_noinline.c
@@ -797,7 +797,7 @@ out:
 	return XDP_DROP;
 }
 
-SEC("xdp-test-v4")
+SEC("xdp")
 int balancer_ingress_v4(struct xdp_md *ctx)
 {
 	void *data = (void *)(long)ctx->data;
@@ -816,7 +816,7 @@ int balancer_ingress_v4(struct xdp_md *ctx)
 		return XDP_DROP;
 }
 
-SEC("xdp-test-v6")
+SEC("xdp")
 int balancer_ingress_v6(struct xdp_md *ctx)
 {
 	void *data = (void *)(long)ctx->data;
diff --git a/tools/testing/selftests/bpf/progs/test_xdp_with_cpumap_helpers.c b/tools/testing/selftests/bpf/progs/test_xdp_with_cpumap_helpers.c
index 59ee4f182ff8..532025057711 100644
--- a/tools/testing/selftests/bpf/progs/test_xdp_with_cpumap_helpers.c
+++ b/tools/testing/selftests/bpf/progs/test_xdp_with_cpumap_helpers.c
@@ -12,13 +12,13 @@ struct {
 	__uint(max_entries, 4);
 } cpu_map SEC(".maps");
 
-SEC("xdp_redir")
+SEC("xdp")
 int xdp_redir_prog(struct xdp_md *ctx)
 {
 	return bpf_redirect_map(&cpu_map, 1, 0);
 }
 
-SEC("xdp_dummy")
+SEC("xdp")
 int xdp_dummy_prog(struct xdp_md *ctx)
 {
 	return XDP_PASS;
diff --git a/tools/testing/selftests/bpf/progs/test_xdp_with_devmap_helpers.c b/tools/testing/selftests/bpf/progs/test_xdp_with_devmap_helpers.c
index 0ac086497722..1e6b9c38ea6d 100644
--- a/tools/testing/selftests/bpf/progs/test_xdp_with_devmap_helpers.c
+++ b/tools/testing/selftests/bpf/progs/test_xdp_with_devmap_helpers.c
@@ -9,7 +9,7 @@ struct {
 	__uint(max_entries, 4);
 } dm_ports SEC(".maps");
 
-SEC("xdp_redir")
+SEC("xdp")
 int xdp_redir_prog(struct xdp_md *ctx)
 {
 	return bpf_redirect_map(&dm_ports, 1, 0);
@@ -18,7 +18,7 @@ int xdp_redir_prog(struct xdp_md *ctx)
 /* invalid program on DEVMAP entry;
  * SEC name means expected attach type not set
  */
-SEC("xdp_dummy")
+SEC("xdp")
 int xdp_dummy_prog(struct xdp_md *ctx)
 {
 	return XDP_PASS;
diff --git a/tools/testing/selftests/bpf/progs/xdp_dummy.c b/tools/testing/selftests/bpf/progs/xdp_dummy.c
index ea25e8881992..d988b2e0cee8 100644
--- a/tools/testing/selftests/bpf/progs/xdp_dummy.c
+++ b/tools/testing/selftests/bpf/progs/xdp_dummy.c
@@ -4,7 +4,7 @@
 #include <linux/bpf.h>
 #include <bpf/bpf_helpers.h>
 
-SEC("xdp_dummy")
+SEC("xdp")
 int xdp_dummy_prog(struct xdp_md *ctx)
 {
 	return XDP_PASS;
diff --git a/tools/testing/selftests/bpf/progs/xdp_redirect_multi_kern.c b/tools/testing/selftests/bpf/progs/xdp_redirect_multi_kern.c
index 880debcbcd65..8395782b6e0a 100644
--- a/tools/testing/selftests/bpf/progs/xdp_redirect_multi_kern.c
+++ b/tools/testing/selftests/bpf/progs/xdp_redirect_multi_kern.c
@@ -34,7 +34,7 @@ struct {
 	__uint(max_entries, 128);
 } mac_map SEC(".maps");
 
-SEC("xdp_redirect_map_multi")
+SEC("xdp")
 int xdp_redirect_map_multi_prog(struct xdp_md *ctx)
 {
 	void *data_end = (void *)(long)ctx->data_end;
@@ -63,7 +63,7 @@ int xdp_redirect_map_multi_prog(struct xdp_md *ctx)
 }
 
 /* The following 2 progs are for 2nd devmap prog testing */
-SEC("xdp_redirect_map_ingress")
+SEC("xdp")
 int xdp_redirect_map_all_prog(struct xdp_md *ctx)
 {
 	return bpf_redirect_map(&map_egress, 0,
diff --git a/tools/testing/selftests/bpf/progs/xdping_kern.c b/tools/testing/selftests/bpf/progs/xdping_kern.c
index 6b9ca40bd1f4..4ad73847b8a5 100644
--- a/tools/testing/selftests/bpf/progs/xdping_kern.c
+++ b/tools/testing/selftests/bpf/progs/xdping_kern.c
@@ -86,7 +86,7 @@ static __always_inline int icmp_check(struct xdp_md *ctx, int type)
 	return XDP_TX;
 }
 
-SEC("xdpclient")
+SEC("xdp")
 int xdping_client(struct xdp_md *ctx)
 {
 	void *data_end = (void *)(long)ctx->data_end;
@@ -150,7 +150,7 @@ int xdping_client(struct xdp_md *ctx)
 	return XDP_TX;
 }
 
-SEC("xdpserver")
+SEC("xdp")
 int xdping_server(struct xdp_md *ctx)
 {
 	void *data_end = (void *)(long)ctx->data_end;
diff --git a/tools/testing/selftests/bpf/test_tcp_check_syncookie.sh b/tools/testing/selftests/bpf/test_tcp_check_syncookie.sh
index 9b3617d770a5..fed765157c53 100755
--- a/tools/testing/selftests/bpf/test_tcp_check_syncookie.sh
+++ b/tools/testing/selftests/bpf/test_tcp_check_syncookie.sh
@@ -77,7 +77,7 @@ TEST_IF=lo
 MAX_PING_TRIES=5
 BPF_PROG_OBJ="${DIR}/test_tcp_check_syncookie_kern.o"
 CLSACT_SECTION="clsact/check_syncookie"
-XDP_SECTION="xdp/check_syncookie"
+XDP_SECTION="xdp"
 BPF_PROG_ID=0
 PROG="${DIR}/test_tcp_check_syncookie_user"
 
diff --git a/tools/testing/selftests/bpf/test_xdp_redirect.sh b/tools/testing/selftests/bpf/test_xdp_redirect.sh
index c033850886f4..57c8db9972a6 100755
--- a/tools/testing/selftests/bpf/test_xdp_redirect.sh
+++ b/tools/testing/selftests/bpf/test_xdp_redirect.sh
@@ -52,8 +52,8 @@ test_xdp_redirect()
 		return 0
 	fi
 
-	ip -n ns1 link set veth11 $xdpmode obj xdp_dummy.o sec xdp_dummy &> /dev/null
-	ip -n ns2 link set veth22 $xdpmode obj xdp_dummy.o sec xdp_dummy &> /dev/null
+	ip -n ns1 link set veth11 $xdpmode obj xdp_dummy.o sec xdp &> /dev/null
+	ip -n ns2 link set veth22 $xdpmode obj xdp_dummy.o sec xdp &> /dev/null
 	ip link set dev veth1 $xdpmode obj test_xdp_redirect.o sec redirect_to_222 &> /dev/null
 	ip link set dev veth2 $xdpmode obj test_xdp_redirect.o sec redirect_to_111 &> /dev/null
 
diff --git a/tools/testing/selftests/bpf/test_xdp_redirect_multi.sh b/tools/testing/selftests/bpf/test_xdp_redirect_multi.sh
index 1538373157e3..351955c2bdfd 100755
--- a/tools/testing/selftests/bpf/test_xdp_redirect_multi.sh
+++ b/tools/testing/selftests/bpf/test_xdp_redirect_multi.sh
@@ -88,7 +88,7 @@ setup_ns()
 		# Add a neigh entry for IPv4 ping test
 		ip -n ns$i neigh add 192.0.2.253 lladdr 00:00:00:00:00:01 dev veth0
 		ip -n ns$i link set veth0 $mode obj \
-			xdp_dummy.o sec xdp_dummy &> /dev/null || \
+			xdp_dummy.o sec xdp &> /dev/null || \
 			{ test_fail "Unable to load dummy xdp" && exit 1; }
 		IFACES="$IFACES veth$i"
 		veth_mac[$i]=$(ip link show veth$i | awk '/link\/ether/ {print $2}')
diff --git a/tools/testing/selftests/bpf/test_xdp_veth.sh b/tools/testing/selftests/bpf/test_xdp_veth.sh
index 995278e684b6..a3a1eaee26ea 100755
--- a/tools/testing/selftests/bpf/test_xdp_veth.sh
+++ b/tools/testing/selftests/bpf/test_xdp_veth.sh
@@ -107,9 +107,9 @@ ip link set dev veth1 xdp pinned $BPF_DIR/progs/redirect_map_0
 ip link set dev veth2 xdp pinned $BPF_DIR/progs/redirect_map_1
 ip link set dev veth3 xdp pinned $BPF_DIR/progs/redirect_map_2
 
-ip -n ns1 link set dev veth11 xdp obj xdp_dummy.o sec xdp_dummy
+ip -n ns1 link set dev veth11 xdp obj xdp_dummy.o sec xdp
 ip -n ns2 link set dev veth22 xdp obj xdp_tx.o sec xdp
-ip -n ns3 link set dev veth33 xdp obj xdp_dummy.o sec xdp_dummy
+ip -n ns3 link set dev veth33 xdp obj xdp_dummy.o sec xdp
 
 trap cleanup EXIT
 
diff --git a/tools/testing/selftests/bpf/xdping.c b/tools/testing/selftests/bpf/xdping.c
index 842d9155d36c..79a3453dab25 100644
--- a/tools/testing/selftests/bpf/xdping.c
+++ b/tools/testing/selftests/bpf/xdping.c
@@ -178,9 +178,8 @@ int main(int argc, char **argv)
 		return 1;
 	}
 
-	main_prog = bpf_object__find_program_by_title(obj,
-						      server ? "xdpserver" :
-							       "xdpclient");
+	main_prog = bpf_object__find_program_by_name(obj,
+						     server ? "xdping_server" : "xdping_client");
 	if (main_prog)
 		prog_fd = bpf_program__fd(main_prog);
 	if (!main_prog || prog_fd < 0) {
-- 
cgit v1.2.3


From c22bdd28257f3532092746b31856932d84ca2e2b Mon Sep 17 00:00:00 2001
From: Andrii Nakryiko <andrii@kernel.org>
Date: Tue, 28 Sep 2021 09:19:39 -0700
Subject: selftests/bpf: Switch SEC("classifier*") usage to a strict SEC("tc")

Convert all SEC("classifier*") uses to a new and strict SEC("tc")
section name. In reference_tracking selftests switch from ambiguous
searching by program title (section name) to non-ambiguous searching by
name in some selftests, getting closer to completely removing
bpf_object__find_program_by_title().

Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20210928161946.2512801-4-andrii@kernel.org
---
 .../selftests/bpf/prog_tests/reference_tracking.c  | 23 ++++-----
 tools/testing/selftests/bpf/prog_tests/sk_assign.c |  2 +-
 tools/testing/selftests/bpf/prog_tests/tailcalls.c | 58 +++++++++++-----------
 .../selftests/bpf/progs/for_each_array_map_elem.c  |  2 +-
 .../selftests/bpf/progs/for_each_hash_map_elem.c   |  2 +-
 .../testing/selftests/bpf/progs/kfunc_call_test.c  |  4 +-
 .../selftests/bpf/progs/kfunc_call_test_subprog.c  |  2 +-
 tools/testing/selftests/bpf/progs/skb_pkt_end.c    |  2 +-
 tools/testing/selftests/bpf/progs/tailcall1.c      |  7 ++-
 tools/testing/selftests/bpf/progs/tailcall2.c      | 23 ++++-----
 tools/testing/selftests/bpf/progs/tailcall3.c      |  7 ++-
 tools/testing/selftests/bpf/progs/tailcall4.c      |  7 ++-
 tools/testing/selftests/bpf/progs/tailcall5.c      |  7 ++-
 tools/testing/selftests/bpf/progs/tailcall6.c      |  6 +--
 .../selftests/bpf/progs/tailcall_bpf2bpf1.c        |  7 ++-
 .../selftests/bpf/progs/tailcall_bpf2bpf2.c        |  7 ++-
 .../selftests/bpf/progs/tailcall_bpf2bpf3.c        | 11 ++--
 .../selftests/bpf/progs/tailcall_bpf2bpf4.c        | 15 +++---
 .../selftests/bpf/progs/test_btf_skc_cls_ingress.c |  2 +-
 tools/testing/selftests/bpf/progs/test_check_mtu.c | 12 ++---
 .../selftests/bpf/progs/test_cls_redirect.c        |  2 +-
 .../testing/selftests/bpf/progs/test_global_data.c |  2 +-
 .../selftests/bpf/progs/test_global_func1.c        |  2 +-
 .../selftests/bpf/progs/test_global_func3.c        |  2 +-
 .../selftests/bpf/progs/test_global_func5.c        |  2 +-
 .../selftests/bpf/progs/test_global_func6.c        |  2 +-
 .../selftests/bpf/progs/test_global_func7.c        |  2 +-
 .../testing/selftests/bpf/progs/test_pkt_access.c  |  2 +-
 .../selftests/bpf/progs/test_pkt_md_access.c       |  4 +-
 tools/testing/selftests/bpf/progs/test_sk_assign.c |  3 +-
 .../selftests/bpf/progs/test_sk_lookup_kern.c      | 37 +++++++-------
 .../testing/selftests/bpf/progs/test_skb_helpers.c |  2 +-
 .../selftests/bpf/progs/test_sockmap_update.c      |  2 +-
 tools/testing/selftests/bpf/progs/test_tc_bpf.c    |  2 +-
 tools/testing/selftests/bpf/progs/test_tc_neigh.c  |  6 +--
 .../selftests/bpf/progs/test_tc_neigh_fib.c        |  6 +--
 tools/testing/selftests/bpf/progs/test_tc_peer.c   | 10 ++--
 .../bpf/progs/test_tcp_check_syncookie_kern.c      |  2 +-
 .../selftests/bpf/test_tcp_check_syncookie.sh      |  2 +-
 39 files changed, 141 insertions(+), 157 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/prog_tests/reference_tracking.c b/tools/testing/selftests/bpf/prog_tests/reference_tracking.c
index ded2dc8ddd79..873323fb18ba 100644
--- a/tools/testing/selftests/bpf/prog_tests/reference_tracking.c
+++ b/tools/testing/selftests/bpf/prog_tests/reference_tracking.c
@@ -2,14 +2,14 @@
 #include <test_progs.h>
 
 static void toggle_object_autoload_progs(const struct bpf_object *obj,
-					 const char *title_load)
+					 const char *name_load)
 {
 	struct bpf_program *prog;
 
 	bpf_object__for_each_program(prog, obj) {
-		const char *title = bpf_program__section_name(prog);
+		const char *name = bpf_program__name(prog);
 
-		if (!strcmp(title_load, title))
+		if (!strcmp(name_load, name))
 			bpf_program__set_autoload(prog, true);
 		else
 			bpf_program__set_autoload(prog, false);
@@ -39,23 +39,19 @@ void test_reference_tracking(void)
 		goto cleanup;
 
 	bpf_object__for_each_program(prog, obj_iter) {
-		const char *title;
+		const char *name;
 
-		/* Ignore .text sections */
-		title = bpf_program__section_name(prog);
-		if (strstr(title, ".text") != NULL)
-			continue;
-
-		if (!test__start_subtest(title))
+		name = bpf_program__name(prog);
+		if (!test__start_subtest(name))
 			continue;
 
 		obj = bpf_object__open_file(file, &open_opts);
 		if (!ASSERT_OK_PTR(obj, "obj_open_file"))
 			goto cleanup;
 
-		toggle_object_autoload_progs(obj, title);
+		toggle_object_autoload_progs(obj, name);
 		/* Expect verifier failure if test name has 'err' */
-		if (strstr(title, "err_") != NULL) {
+		if (strncmp(name, "err_", sizeof("err_") - 1) == 0) {
 			libbpf_print_fn_t old_print_fn;
 
 			old_print_fn = libbpf_set_print(NULL);
@@ -64,7 +60,8 @@ void test_reference_tracking(void)
 		} else {
 			err = bpf_object__load(obj);
 		}
-		CHECK(err, title, "\n");
+		ASSERT_OK(err, name);
+
 		bpf_object__close(obj);
 		obj = NULL;
 	}
diff --git a/tools/testing/selftests/bpf/prog_tests/sk_assign.c b/tools/testing/selftests/bpf/prog_tests/sk_assign.c
index 3a469099f30d..1d272e05188e 100644
--- a/tools/testing/selftests/bpf/prog_tests/sk_assign.c
+++ b/tools/testing/selftests/bpf/prog_tests/sk_assign.c
@@ -48,7 +48,7 @@ configure_stack(void)
 		return false;
 	sprintf(tc_cmd, "%s %s %s %s", "tc filter add dev lo ingress bpf",
 		       "direct-action object-file ./test_sk_assign.o",
-		       "section classifier/sk_assign_test",
+		       "section tc",
 		       (env.verbosity < VERBOSE_VERY) ? " 2>/dev/null" : "verbose");
 	if (CHECK(system(tc_cmd), "BPF load failed;",
 		  "run with -vv for more info\n"))
diff --git a/tools/testing/selftests/bpf/prog_tests/tailcalls.c b/tools/testing/selftests/bpf/prog_tests/tailcalls.c
index 7bf3a7a97d7b..9825f1f7bfcc 100644
--- a/tools/testing/selftests/bpf/prog_tests/tailcalls.c
+++ b/tools/testing/selftests/bpf/prog_tests/tailcalls.c
@@ -21,7 +21,7 @@ static void test_tailcall_1(void)
 	if (CHECK_FAIL(err))
 		return;
 
-	prog = bpf_object__find_program_by_title(obj, "classifier");
+	prog = bpf_object__find_program_by_name(obj, "entry");
 	if (CHECK_FAIL(!prog))
 		goto out;
 
@@ -38,9 +38,9 @@ static void test_tailcall_1(void)
 		goto out;
 
 	for (i = 0; i < bpf_map__def(prog_array)->max_entries; i++) {
-		snprintf(prog_name, sizeof(prog_name), "classifier/%i", i);
+		snprintf(prog_name, sizeof(prog_name), "classifier_%d", i);
 
-		prog = bpf_object__find_program_by_title(obj, prog_name);
+		prog = bpf_object__find_program_by_name(obj, prog_name);
 		if (CHECK_FAIL(!prog))
 			goto out;
 
@@ -70,9 +70,9 @@ static void test_tailcall_1(void)
 	      err, errno, retval);
 
 	for (i = 0; i < bpf_map__def(prog_array)->max_entries; i++) {
-		snprintf(prog_name, sizeof(prog_name), "classifier/%i", i);
+		snprintf(prog_name, sizeof(prog_name), "classifier_%d", i);
 
-		prog = bpf_object__find_program_by_title(obj, prog_name);
+		prog = bpf_object__find_program_by_name(obj, prog_name);
 		if (CHECK_FAIL(!prog))
 			goto out;
 
@@ -92,9 +92,9 @@ static void test_tailcall_1(void)
 
 	for (i = 0; i < bpf_map__def(prog_array)->max_entries; i++) {
 		j = bpf_map__def(prog_array)->max_entries - 1 - i;
-		snprintf(prog_name, sizeof(prog_name), "classifier/%i", j);
+		snprintf(prog_name, sizeof(prog_name), "classifier_%d", j);
 
-		prog = bpf_object__find_program_by_title(obj, prog_name);
+		prog = bpf_object__find_program_by_name(obj, prog_name);
 		if (CHECK_FAIL(!prog))
 			goto out;
 
@@ -159,7 +159,7 @@ static void test_tailcall_2(void)
 	if (CHECK_FAIL(err))
 		return;
 
-	prog = bpf_object__find_program_by_title(obj, "classifier");
+	prog = bpf_object__find_program_by_name(obj, "entry");
 	if (CHECK_FAIL(!prog))
 		goto out;
 
@@ -176,9 +176,9 @@ static void test_tailcall_2(void)
 		goto out;
 
 	for (i = 0; i < bpf_map__def(prog_array)->max_entries; i++) {
-		snprintf(prog_name, sizeof(prog_name), "classifier/%i", i);
+		snprintf(prog_name, sizeof(prog_name), "classifier_%d", i);
 
-		prog = bpf_object__find_program_by_title(obj, prog_name);
+		prog = bpf_object__find_program_by_name(obj, prog_name);
 		if (CHECK_FAIL(!prog))
 			goto out;
 
@@ -233,7 +233,7 @@ static void test_tailcall_count(const char *which)
 	if (CHECK_FAIL(err))
 		return;
 
-	prog = bpf_object__find_program_by_title(obj, "classifier");
+	prog = bpf_object__find_program_by_name(obj, "entry");
 	if (CHECK_FAIL(!prog))
 		goto out;
 
@@ -249,7 +249,7 @@ static void test_tailcall_count(const char *which)
 	if (CHECK_FAIL(map_fd < 0))
 		goto out;
 
-	prog = bpf_object__find_program_by_title(obj, "classifier/0");
+	prog = bpf_object__find_program_by_name(obj, "classifier_0");
 	if (CHECK_FAIL(!prog))
 		goto out;
 
@@ -329,7 +329,7 @@ static void test_tailcall_4(void)
 	if (CHECK_FAIL(err))
 		return;
 
-	prog = bpf_object__find_program_by_title(obj, "classifier");
+	prog = bpf_object__find_program_by_name(obj, "entry");
 	if (CHECK_FAIL(!prog))
 		goto out;
 
@@ -354,9 +354,9 @@ static void test_tailcall_4(void)
 		return;
 
 	for (i = 0; i < bpf_map__def(prog_array)->max_entries; i++) {
-		snprintf(prog_name, sizeof(prog_name), "classifier/%i", i);
+		snprintf(prog_name, sizeof(prog_name), "classifier_%d", i);
 
-		prog = bpf_object__find_program_by_title(obj, prog_name);
+		prog = bpf_object__find_program_by_name(obj, prog_name);
 		if (CHECK_FAIL(!prog))
 			goto out;
 
@@ -417,7 +417,7 @@ static void test_tailcall_5(void)
 	if (CHECK_FAIL(err))
 		return;
 
-	prog = bpf_object__find_program_by_title(obj, "classifier");
+	prog = bpf_object__find_program_by_name(obj, "entry");
 	if (CHECK_FAIL(!prog))
 		goto out;
 
@@ -442,9 +442,9 @@ static void test_tailcall_5(void)
 		return;
 
 	for (i = 0; i < bpf_map__def(prog_array)->max_entries; i++) {
-		snprintf(prog_name, sizeof(prog_name), "classifier/%i", i);
+		snprintf(prog_name, sizeof(prog_name), "classifier_%d", i);
 
-		prog = bpf_object__find_program_by_title(obj, prog_name);
+		prog = bpf_object__find_program_by_name(obj, prog_name);
 		if (CHECK_FAIL(!prog))
 			goto out;
 
@@ -503,7 +503,7 @@ static void test_tailcall_bpf2bpf_1(void)
 	if (CHECK_FAIL(err))
 		return;
 
-	prog = bpf_object__find_program_by_title(obj, "classifier");
+	prog = bpf_object__find_program_by_name(obj, "entry");
 	if (CHECK_FAIL(!prog))
 		goto out;
 
@@ -521,9 +521,9 @@ static void test_tailcall_bpf2bpf_1(void)
 
 	/* nop -> jmp */
 	for (i = 0; i < bpf_map__def(prog_array)->max_entries; i++) {
-		snprintf(prog_name, sizeof(prog_name), "classifier/%i", i);
+		snprintf(prog_name, sizeof(prog_name), "classifier_%d", i);
 
-		prog = bpf_object__find_program_by_title(obj, prog_name);
+		prog = bpf_object__find_program_by_name(obj, prog_name);
 		if (CHECK_FAIL(!prog))
 			goto out;
 
@@ -587,7 +587,7 @@ static void test_tailcall_bpf2bpf_2(void)
 	if (CHECK_FAIL(err))
 		return;
 
-	prog = bpf_object__find_program_by_title(obj, "classifier");
+	prog = bpf_object__find_program_by_name(obj, "entry");
 	if (CHECK_FAIL(!prog))
 		goto out;
 
@@ -603,7 +603,7 @@ static void test_tailcall_bpf2bpf_2(void)
 	if (CHECK_FAIL(map_fd < 0))
 		goto out;
 
-	prog = bpf_object__find_program_by_title(obj, "classifier/0");
+	prog = bpf_object__find_program_by_name(obj, "classifier_0");
 	if (CHECK_FAIL(!prog))
 		goto out;
 
@@ -665,7 +665,7 @@ static void test_tailcall_bpf2bpf_3(void)
 	if (CHECK_FAIL(err))
 		return;
 
-	prog = bpf_object__find_program_by_title(obj, "classifier");
+	prog = bpf_object__find_program_by_name(obj, "entry");
 	if (CHECK_FAIL(!prog))
 		goto out;
 
@@ -682,9 +682,9 @@ static void test_tailcall_bpf2bpf_3(void)
 		goto out;
 
 	for (i = 0; i < bpf_map__def(prog_array)->max_entries; i++) {
-		snprintf(prog_name, sizeof(prog_name), "classifier/%i", i);
+		snprintf(prog_name, sizeof(prog_name), "classifier_%d", i);
 
-		prog = bpf_object__find_program_by_title(obj, prog_name);
+		prog = bpf_object__find_program_by_name(obj, prog_name);
 		if (CHECK_FAIL(!prog))
 			goto out;
 
@@ -762,7 +762,7 @@ static void test_tailcall_bpf2bpf_4(bool noise)
 	if (CHECK_FAIL(err))
 		return;
 
-	prog = bpf_object__find_program_by_title(obj, "classifier");
+	prog = bpf_object__find_program_by_name(obj, "entry");
 	if (CHECK_FAIL(!prog))
 		goto out;
 
@@ -779,9 +779,9 @@ static void test_tailcall_bpf2bpf_4(bool noise)
 		goto out;
 
 	for (i = 0; i < bpf_map__def(prog_array)->max_entries; i++) {
-		snprintf(prog_name, sizeof(prog_name), "classifier/%i", i);
+		snprintf(prog_name, sizeof(prog_name), "classifier_%d", i);
 
-		prog = bpf_object__find_program_by_title(obj, prog_name);
+		prog = bpf_object__find_program_by_name(obj, prog_name);
 		if (CHECK_FAIL(!prog))
 			goto out;
 
diff --git a/tools/testing/selftests/bpf/progs/for_each_array_map_elem.c b/tools/testing/selftests/bpf/progs/for_each_array_map_elem.c
index 75e8e1069fe7..df918b2469da 100644
--- a/tools/testing/selftests/bpf/progs/for_each_array_map_elem.c
+++ b/tools/testing/selftests/bpf/progs/for_each_array_map_elem.c
@@ -47,7 +47,7 @@ check_percpu_elem(struct bpf_map *map, __u32 *key, __u64 *val,
 
 u32 arraymap_output = 0;
 
-SEC("classifier")
+SEC("tc")
 int test_pkt_access(struct __sk_buff *skb)
 {
 	struct callback_ctx data;
diff --git a/tools/testing/selftests/bpf/progs/for_each_hash_map_elem.c b/tools/testing/selftests/bpf/progs/for_each_hash_map_elem.c
index 913dd91aafff..276994d5c0c7 100644
--- a/tools/testing/selftests/bpf/progs/for_each_hash_map_elem.c
+++ b/tools/testing/selftests/bpf/progs/for_each_hash_map_elem.c
@@ -78,7 +78,7 @@ int hashmap_output = 0;
 int hashmap_elems = 0;
 int percpu_map_elems = 0;
 
-SEC("classifier")
+SEC("tc")
 int test_pkt_access(struct __sk_buff *skb)
 {
 	struct callback_ctx data;
diff --git a/tools/testing/selftests/bpf/progs/kfunc_call_test.c b/tools/testing/selftests/bpf/progs/kfunc_call_test.c
index 470f8723e463..8a8cf59017aa 100644
--- a/tools/testing/selftests/bpf/progs/kfunc_call_test.c
+++ b/tools/testing/selftests/bpf/progs/kfunc_call_test.c
@@ -8,7 +8,7 @@ extern int bpf_kfunc_call_test2(struct sock *sk, __u32 a, __u32 b) __ksym;
 extern __u64 bpf_kfunc_call_test1(struct sock *sk, __u32 a, __u64 b,
 				  __u32 c, __u64 d) __ksym;
 
-SEC("classifier")
+SEC("tc")
 int kfunc_call_test2(struct __sk_buff *skb)
 {
 	struct bpf_sock *sk = skb->sk;
@@ -23,7 +23,7 @@ int kfunc_call_test2(struct __sk_buff *skb)
 	return bpf_kfunc_call_test2((struct sock *)sk, 1, 2);
 }
 
-SEC("classifier")
+SEC("tc")
 int kfunc_call_test1(struct __sk_buff *skb)
 {
 	struct bpf_sock *sk = skb->sk;
diff --git a/tools/testing/selftests/bpf/progs/kfunc_call_test_subprog.c b/tools/testing/selftests/bpf/progs/kfunc_call_test_subprog.c
index 5fbd9e232d44..c1fdecabeabf 100644
--- a/tools/testing/selftests/bpf/progs/kfunc_call_test_subprog.c
+++ b/tools/testing/selftests/bpf/progs/kfunc_call_test_subprog.c
@@ -33,7 +33,7 @@ int __noinline f1(struct __sk_buff *skb)
 	return (__u32)bpf_kfunc_call_test1((struct sock *)sk, 1, 2, 3, 4);
 }
 
-SEC("classifier")
+SEC("tc")
 int kfunc_call_test1(struct __sk_buff *skb)
 {
 	return f1(skb);
diff --git a/tools/testing/selftests/bpf/progs/skb_pkt_end.c b/tools/testing/selftests/bpf/progs/skb_pkt_end.c
index 7f2eaa2f89f8..992b7861003a 100644
--- a/tools/testing/selftests/bpf/progs/skb_pkt_end.c
+++ b/tools/testing/selftests/bpf/progs/skb_pkt_end.c
@@ -25,7 +25,7 @@ out:
 	return ip;
 }
 
-SEC("classifier/cls")
+SEC("tc")
 int main_prog(struct __sk_buff *skb)
 {
 	struct iphdr *ip = NULL;
diff --git a/tools/testing/selftests/bpf/progs/tailcall1.c b/tools/testing/selftests/bpf/progs/tailcall1.c
index 7115bcefbe8a..8159a0b4a69a 100644
--- a/tools/testing/selftests/bpf/progs/tailcall1.c
+++ b/tools/testing/selftests/bpf/progs/tailcall1.c
@@ -11,8 +11,8 @@ struct {
 } jmp_table SEC(".maps");
 
 #define TAIL_FUNC(x) 				\
-	SEC("classifier/" #x)			\
-	int bpf_func_##x(struct __sk_buff *skb)	\
+	SEC("tc")				\
+	int classifier_##x(struct __sk_buff *skb)	\
 	{					\
 		return x;			\
 	}
@@ -20,7 +20,7 @@ TAIL_FUNC(0)
 TAIL_FUNC(1)
 TAIL_FUNC(2)
 
-SEC("classifier")
+SEC("tc")
 int entry(struct __sk_buff *skb)
 {
 	/* Multiple locations to make sure we patch
@@ -45,4 +45,3 @@ int entry(struct __sk_buff *skb)
 }
 
 char __license[] SEC("license") = "GPL";
-int _version SEC("version") = 1;
diff --git a/tools/testing/selftests/bpf/progs/tailcall2.c b/tools/testing/selftests/bpf/progs/tailcall2.c
index 0431e4fe7efd..a5ff53e61702 100644
--- a/tools/testing/selftests/bpf/progs/tailcall2.c
+++ b/tools/testing/selftests/bpf/progs/tailcall2.c
@@ -10,41 +10,41 @@ struct {
 	__uint(value_size, sizeof(__u32));
 } jmp_table SEC(".maps");
 
-SEC("classifier/0")
-int bpf_func_0(struct __sk_buff *skb)
+SEC("tc")
+int classifier_0(struct __sk_buff *skb)
 {
 	bpf_tail_call_static(skb, &jmp_table, 1);
 	return 0;
 }
 
-SEC("classifier/1")
-int bpf_func_1(struct __sk_buff *skb)
+SEC("tc")
+int classifier_1(struct __sk_buff *skb)
 {
 	bpf_tail_call_static(skb, &jmp_table, 2);
 	return 1;
 }
 
-SEC("classifier/2")
-int bpf_func_2(struct __sk_buff *skb)
+SEC("tc")
+int classifier_2(struct __sk_buff *skb)
 {
 	return 2;
 }
 
-SEC("classifier/3")
-int bpf_func_3(struct __sk_buff *skb)
+SEC("tc")
+int classifier_3(struct __sk_buff *skb)
 {
 	bpf_tail_call_static(skb, &jmp_table, 4);
 	return 3;
 }
 
-SEC("classifier/4")
-int bpf_func_4(struct __sk_buff *skb)
+SEC("tc")
+int classifier_4(struct __sk_buff *skb)
 {
 	bpf_tail_call_static(skb, &jmp_table, 3);
 	return 4;
 }
 
-SEC("classifier")
+SEC("tc")
 int entry(struct __sk_buff *skb)
 {
 	bpf_tail_call_static(skb, &jmp_table, 0);
@@ -56,4 +56,3 @@ int entry(struct __sk_buff *skb)
 }
 
 char __license[] SEC("license") = "GPL";
-int _version SEC("version") = 1;
diff --git a/tools/testing/selftests/bpf/progs/tailcall3.c b/tools/testing/selftests/bpf/progs/tailcall3.c
index 910858fe078a..f60bcd7b8d4b 100644
--- a/tools/testing/selftests/bpf/progs/tailcall3.c
+++ b/tools/testing/selftests/bpf/progs/tailcall3.c
@@ -12,15 +12,15 @@ struct {
 
 int count = 0;
 
-SEC("classifier/0")
-int bpf_func_0(struct __sk_buff *skb)
+SEC("tc")
+int classifier_0(struct __sk_buff *skb)
 {
 	count++;
 	bpf_tail_call_static(skb, &jmp_table, 0);
 	return 1;
 }
 
-SEC("classifier")
+SEC("tc")
 int entry(struct __sk_buff *skb)
 {
 	bpf_tail_call_static(skb, &jmp_table, 0);
@@ -28,4 +28,3 @@ int entry(struct __sk_buff *skb)
 }
 
 char __license[] SEC("license") = "GPL";
-int _version SEC("version") = 1;
diff --git a/tools/testing/selftests/bpf/progs/tailcall4.c b/tools/testing/selftests/bpf/progs/tailcall4.c
index bd4be135c39d..a56bbc2313ca 100644
--- a/tools/testing/selftests/bpf/progs/tailcall4.c
+++ b/tools/testing/selftests/bpf/progs/tailcall4.c
@@ -13,8 +13,8 @@ struct {
 int selector = 0;
 
 #define TAIL_FUNC(x)				\
-	SEC("classifier/" #x)			\
-	int bpf_func_##x(struct __sk_buff *skb)	\
+	SEC("tc")				\
+	int classifier_##x(struct __sk_buff *skb)	\
 	{					\
 		return x;			\
 	}
@@ -22,7 +22,7 @@ TAIL_FUNC(0)
 TAIL_FUNC(1)
 TAIL_FUNC(2)
 
-SEC("classifier")
+SEC("tc")
 int entry(struct __sk_buff *skb)
 {
 	bpf_tail_call(skb, &jmp_table, selector);
@@ -30,4 +30,3 @@ int entry(struct __sk_buff *skb)
 }
 
 char __license[] SEC("license") = "GPL";
-int _version SEC("version") = 1;
diff --git a/tools/testing/selftests/bpf/progs/tailcall5.c b/tools/testing/selftests/bpf/progs/tailcall5.c
index adf30a33064e..8d03496eb6ca 100644
--- a/tools/testing/selftests/bpf/progs/tailcall5.c
+++ b/tools/testing/selftests/bpf/progs/tailcall5.c
@@ -13,8 +13,8 @@ struct {
 int selector = 0;
 
 #define TAIL_FUNC(x)				\
-	SEC("classifier/" #x)			\
-	int bpf_func_##x(struct __sk_buff *skb)	\
+	SEC("tc")				\
+	int classifier_##x(struct __sk_buff *skb)	\
 	{					\
 		return x;			\
 	}
@@ -22,7 +22,7 @@ TAIL_FUNC(0)
 TAIL_FUNC(1)
 TAIL_FUNC(2)
 
-SEC("classifier")
+SEC("tc")
 int entry(struct __sk_buff *skb)
 {
 	int idx = 0;
@@ -37,4 +37,3 @@ int entry(struct __sk_buff *skb)
 }
 
 char __license[] SEC("license") = "GPL";
-int _version SEC("version") = 1;
diff --git a/tools/testing/selftests/bpf/progs/tailcall6.c b/tools/testing/selftests/bpf/progs/tailcall6.c
index 0f4a811cc028..d77b8abd62f3 100644
--- a/tools/testing/selftests/bpf/progs/tailcall6.c
+++ b/tools/testing/selftests/bpf/progs/tailcall6.c
@@ -12,8 +12,8 @@ struct {
 
 int count, which;
 
-SEC("classifier/0")
-int bpf_func_0(struct __sk_buff *skb)
+SEC("tc")
+int classifier_0(struct __sk_buff *skb)
 {
 	count++;
 	if (__builtin_constant_p(which))
@@ -22,7 +22,7 @@ int bpf_func_0(struct __sk_buff *skb)
 	return 1;
 }
 
-SEC("classifier")
+SEC("tc")
 int entry(struct __sk_buff *skb)
 {
 	if (__builtin_constant_p(which))
diff --git a/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf1.c b/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf1.c
index 0103f3dd9f02..8c91428deb90 100644
--- a/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf1.c
+++ b/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf1.c
@@ -10,8 +10,8 @@ struct {
 } jmp_table SEC(".maps");
 
 #define TAIL_FUNC(x) 				\
-	SEC("classifier/" #x)			\
-	int bpf_func_##x(struct __sk_buff *skb)	\
+	SEC("tc")				\
+	int classifier_##x(struct __sk_buff *skb)	\
 	{					\
 		return x;			\
 	}
@@ -26,7 +26,7 @@ int subprog_tail(struct __sk_buff *skb)
 	return skb->len * 2;
 }
 
-SEC("classifier")
+SEC("tc")
 int entry(struct __sk_buff *skb)
 {
 	bpf_tail_call_static(skb, &jmp_table, 1);
@@ -35,4 +35,3 @@ int entry(struct __sk_buff *skb)
 }
 
 char __license[] SEC("license") = "GPL";
-int _version SEC("version") = 1;
diff --git a/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf2.c b/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf2.c
index 3cc4c12817b5..ce97d141daee 100644
--- a/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf2.c
+++ b/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf2.c
@@ -22,14 +22,14 @@ int subprog_tail(struct __sk_buff *skb)
 
 int count = 0;
 
-SEC("classifier/0")
-int bpf_func_0(struct __sk_buff *skb)
+SEC("tc")
+int classifier_0(struct __sk_buff *skb)
 {
 	count++;
 	return subprog_tail(skb);
 }
 
-SEC("classifier")
+SEC("tc")
 int entry(struct __sk_buff *skb)
 {
 	bpf_tail_call_static(skb, &jmp_table, 0);
@@ -38,4 +38,3 @@ int entry(struct __sk_buff *skb)
 }
 
 char __license[] SEC("license") = "GPL";
-int _version SEC("version") = 1;
diff --git a/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf3.c b/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf3.c
index 0d5482bea6c9..7fab39a3bb12 100644
--- a/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf3.c
+++ b/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf3.c
@@ -33,23 +33,23 @@ int subprog_tail(struct __sk_buff *skb)
 	return skb->len * 2;
 }
 
-SEC("classifier/0")
-int bpf_func_0(struct __sk_buff *skb)
+SEC("tc")
+int classifier_0(struct __sk_buff *skb)
 {
 	volatile char arr[128] = {};
 
 	return subprog_tail2(skb);
 }
 
-SEC("classifier/1")
-int bpf_func_1(struct __sk_buff *skb)
+SEC("tc")
+int classifier_1(struct __sk_buff *skb)
 {
 	volatile char arr[128] = {};
 
 	return skb->len * 3;
 }
 
-SEC("classifier")
+SEC("tc")
 int entry(struct __sk_buff *skb)
 {
 	volatile char arr[128] = {};
@@ -58,4 +58,3 @@ int entry(struct __sk_buff *skb)
 }
 
 char __license[] SEC("license") = "GPL";
-int _version SEC("version") = 1;
diff --git a/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf4.c b/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf4.c
index e89368a50b97..b67e8022d500 100644
--- a/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf4.c
+++ b/tools/testing/selftests/bpf/progs/tailcall_bpf2bpf4.c
@@ -50,30 +50,29 @@ int subprog_tail(struct __sk_buff *skb)
 	return skb->len;
 }
 
-SEC("classifier/1")
-int bpf_func_1(struct __sk_buff *skb)
+SEC("tc")
+int classifier_1(struct __sk_buff *skb)
 {
 	return subprog_tail_2(skb);
 }
 
-SEC("classifier/2")
-int bpf_func_2(struct __sk_buff *skb)
+SEC("tc")
+int classifier_2(struct __sk_buff *skb)
 {
 	count++;
 	return subprog_tail_2(skb);
 }
 
-SEC("classifier/0")
-int bpf_func_0(struct __sk_buff *skb)
+SEC("tc")
+int classifier_0(struct __sk_buff *skb)
 {
 	return subprog_tail_1(skb);
 }
 
-SEC("classifier")
+SEC("tc")
 int entry(struct __sk_buff *skb)
 {
 	return subprog_tail(skb);
 }
 
 char __license[] SEC("license") = "GPL";
-int _version SEC("version") = 1;
diff --git a/tools/testing/selftests/bpf/progs/test_btf_skc_cls_ingress.c b/tools/testing/selftests/bpf/progs/test_btf_skc_cls_ingress.c
index 9a6b85dd52d2..e2bea4da194b 100644
--- a/tools/testing/selftests/bpf/progs/test_btf_skc_cls_ingress.c
+++ b/tools/testing/selftests/bpf/progs/test_btf_skc_cls_ingress.c
@@ -145,7 +145,7 @@ release:
 	return TC_ACT_OK;
 }
 
-SEC("classifier/ingress")
+SEC("tc")
 int cls_ingress(struct __sk_buff *skb)
 {
 	struct ipv6hdr *ip6h;
diff --git a/tools/testing/selftests/bpf/progs/test_check_mtu.c b/tools/testing/selftests/bpf/progs/test_check_mtu.c
index 71184af57749..2ec1de11a3ae 100644
--- a/tools/testing/selftests/bpf/progs/test_check_mtu.c
+++ b/tools/testing/selftests/bpf/progs/test_check_mtu.c
@@ -153,7 +153,7 @@ int xdp_input_len_exceed(struct xdp_md *ctx)
 	return retval;
 }
 
-SEC("classifier")
+SEC("tc")
 int tc_use_helper(struct __sk_buff *ctx)
 {
 	int retval = BPF_OK; /* Expected retval on successful test */
@@ -172,7 +172,7 @@ out:
 	return retval;
 }
 
-SEC("classifier")
+SEC("tc")
 int tc_exceed_mtu(struct __sk_buff *ctx)
 {
 	__u32 ifindex = GLOBAL_USER_IFINDEX;
@@ -196,7 +196,7 @@ int tc_exceed_mtu(struct __sk_buff *ctx)
 	return retval;
 }
 
-SEC("classifier")
+SEC("tc")
 int tc_exceed_mtu_da(struct __sk_buff *ctx)
 {
 	/* SKB Direct-Access variant */
@@ -223,7 +223,7 @@ int tc_exceed_mtu_da(struct __sk_buff *ctx)
 	return retval;
 }
 
-SEC("classifier")
+SEC("tc")
 int tc_minus_delta(struct __sk_buff *ctx)
 {
 	int retval = BPF_OK; /* Expected retval on successful test */
@@ -245,7 +245,7 @@ int tc_minus_delta(struct __sk_buff *ctx)
 	return retval;
 }
 
-SEC("classifier")
+SEC("tc")
 int tc_input_len(struct __sk_buff *ctx)
 {
 	int retval = BPF_OK; /* Expected retval on successful test */
@@ -265,7 +265,7 @@ int tc_input_len(struct __sk_buff *ctx)
 	return retval;
 }
 
-SEC("classifier")
+SEC("tc")
 int tc_input_len_exceed(struct __sk_buff *ctx)
 {
 	int retval = BPF_DROP; /* Fail */
diff --git a/tools/testing/selftests/bpf/progs/test_cls_redirect.c b/tools/testing/selftests/bpf/progs/test_cls_redirect.c
index e2a5acc4785c..2833ad722cb7 100644
--- a/tools/testing/selftests/bpf/progs/test_cls_redirect.c
+++ b/tools/testing/selftests/bpf/progs/test_cls_redirect.c
@@ -928,7 +928,7 @@ static INLINING verdict_t process_ipv6(buf_t *pkt, metrics_t *metrics)
 	}
 }
 
-SEC("classifier/cls_redirect")
+SEC("tc")
 int cls_redirect(struct __sk_buff *skb)
 {
 	metrics_t *metrics = get_global_metrics();
diff --git a/tools/testing/selftests/bpf/progs/test_global_data.c b/tools/testing/selftests/bpf/progs/test_global_data.c
index 1319be1c54ba..719e314ef3e4 100644
--- a/tools/testing/selftests/bpf/progs/test_global_data.c
+++ b/tools/testing/selftests/bpf/progs/test_global_data.c
@@ -68,7 +68,7 @@ static struct foo struct3 = {
 		bpf_map_update_elem(&result_##map, &key, var, 0);	\
 	} while (0)
 
-SEC("classifier/static_data_load")
+SEC("tc")
 int load_static_data(struct __sk_buff *skb)
 {
 	static const __u64 bar = ~0;
diff --git a/tools/testing/selftests/bpf/progs/test_global_func1.c b/tools/testing/selftests/bpf/progs/test_global_func1.c
index 880260f6d536..7b42dad187b8 100644
--- a/tools/testing/selftests/bpf/progs/test_global_func1.c
+++ b/tools/testing/selftests/bpf/progs/test_global_func1.c
@@ -38,7 +38,7 @@ int f3(int val, struct __sk_buff *skb, int var)
 	return skb->ifindex * val * var;
 }
 
-SEC("classifier/test")
+SEC("tc")
 int test_cls(struct __sk_buff *skb)
 {
 	return f0(1, skb) + f1(skb) + f2(2, skb) + f3(3, skb, 4);
diff --git a/tools/testing/selftests/bpf/progs/test_global_func3.c b/tools/testing/selftests/bpf/progs/test_global_func3.c
index 86f0ecb304fc..01bf8275dfd6 100644
--- a/tools/testing/selftests/bpf/progs/test_global_func3.c
+++ b/tools/testing/selftests/bpf/progs/test_global_func3.c
@@ -54,7 +54,7 @@ int f8(struct __sk_buff *skb)
 }
 #endif
 
-SEC("classifier/test")
+SEC("tc")
 int test_cls(struct __sk_buff *skb)
 {
 #ifndef NO_FN8
diff --git a/tools/testing/selftests/bpf/progs/test_global_func5.c b/tools/testing/selftests/bpf/progs/test_global_func5.c
index 260c25b827ef..9248d03e0d06 100644
--- a/tools/testing/selftests/bpf/progs/test_global_func5.c
+++ b/tools/testing/selftests/bpf/progs/test_global_func5.c
@@ -24,7 +24,7 @@ int f3(int val, struct __sk_buff *skb)
 	return skb->ifindex * val;
 }
 
-SEC("classifier/test")
+SEC("tc")
 int test_cls(struct __sk_buff *skb)
 {
 	return f1(skb) + f2(2, skb) + f3(3, skb);
diff --git a/tools/testing/selftests/bpf/progs/test_global_func6.c b/tools/testing/selftests/bpf/progs/test_global_func6.c
index 69e19c64e10b..af8c78bdfb25 100644
--- a/tools/testing/selftests/bpf/progs/test_global_func6.c
+++ b/tools/testing/selftests/bpf/progs/test_global_func6.c
@@ -24,7 +24,7 @@ int f3(int val, struct __sk_buff *skb)
 	return skb->ifindex * val;
 }
 
-SEC("classifier/test")
+SEC("tc")
 int test_cls(struct __sk_buff *skb)
 {
 	return f1(skb) + f2(2, skb) + f3(3, skb);
diff --git a/tools/testing/selftests/bpf/progs/test_global_func7.c b/tools/testing/selftests/bpf/progs/test_global_func7.c
index 309b3f6136bd..6cb8e2f5254c 100644
--- a/tools/testing/selftests/bpf/progs/test_global_func7.c
+++ b/tools/testing/selftests/bpf/progs/test_global_func7.c
@@ -10,7 +10,7 @@ void foo(struct __sk_buff *skb)
 	skb->tc_index = 0;
 }
 
-SEC("classifier/test")
+SEC("tc")
 int test_cls(struct __sk_buff *skb)
 {
 	foo(skb);
diff --git a/tools/testing/selftests/bpf/progs/test_pkt_access.c b/tools/testing/selftests/bpf/progs/test_pkt_access.c
index 852051064507..3cfd88141ddc 100644
--- a/tools/testing/selftests/bpf/progs/test_pkt_access.c
+++ b/tools/testing/selftests/bpf/progs/test_pkt_access.c
@@ -97,7 +97,7 @@ int test_pkt_write_access_subprog(struct __sk_buff *skb, __u32 off)
 	return 0;
 }
 
-SEC("classifier/test_pkt_access")
+SEC("tc")
 int test_pkt_access(struct __sk_buff *skb)
 {
 	void *data_end = (void *)(long)skb->data_end;
diff --git a/tools/testing/selftests/bpf/progs/test_pkt_md_access.c b/tools/testing/selftests/bpf/progs/test_pkt_md_access.c
index 610c74ea9f64..d1839366f3e1 100644
--- a/tools/testing/selftests/bpf/progs/test_pkt_md_access.c
+++ b/tools/testing/selftests/bpf/progs/test_pkt_md_access.c
@@ -7,8 +7,6 @@
 #include <linux/pkt_cls.h>
 #include <bpf/bpf_helpers.h>
 
-int _version SEC("version") = 1;
-
 #if  __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__
 #define TEST_FIELD(TYPE, FIELD, MASK)					\
 	{								\
@@ -27,7 +25,7 @@ int _version SEC("version") = 1;
 	}
 #endif
 
-SEC("classifier/test_pkt_md_access")
+SEC("tc")
 int test_pkt_md_access(struct __sk_buff *skb)
 {
 	TEST_FIELD(__u8,  len, 0xFF);
diff --git a/tools/testing/selftests/bpf/progs/test_sk_assign.c b/tools/testing/selftests/bpf/progs/test_sk_assign.c
index 1ecd987005d2..02f79356d5eb 100644
--- a/tools/testing/selftests/bpf/progs/test_sk_assign.c
+++ b/tools/testing/selftests/bpf/progs/test_sk_assign.c
@@ -36,7 +36,6 @@ struct {
 	.pinning = PIN_GLOBAL_NS,
 };
 
-int _version SEC("version") = 1;
 char _license[] SEC("license") = "GPL";
 
 /* Fill 'tuple' with L3 info, and attempt to find L4. On fail, return NULL. */
@@ -159,7 +158,7 @@ assign:
 	return ret;
 }
 
-SEC("classifier/sk_assign_test")
+SEC("tc")
 int bpf_sk_assign_test(struct __sk_buff *skb)
 {
 	struct bpf_sock_tuple *tuple, ln = {0};
diff --git a/tools/testing/selftests/bpf/progs/test_sk_lookup_kern.c b/tools/testing/selftests/bpf/progs/test_sk_lookup_kern.c
index 8249075f088f..40f161480a2f 100644
--- a/tools/testing/selftests/bpf/progs/test_sk_lookup_kern.c
+++ b/tools/testing/selftests/bpf/progs/test_sk_lookup_kern.c
@@ -15,7 +15,6 @@
 #include <bpf/bpf_helpers.h>
 #include <bpf/bpf_endian.h>
 
-int _version SEC("version") = 1;
 char _license[] SEC("license") = "GPL";
 
 /* Fill 'tuple' with L3 info, and attempt to find L4. On fail, return NULL. */
@@ -53,8 +52,8 @@ static struct bpf_sock_tuple *get_tuple(void *data, __u64 nh_off,
 	return result;
 }
 
-SEC("classifier/sk_lookup_success")
-int bpf_sk_lookup_test0(struct __sk_buff *skb)
+SEC("tc")
+int sk_lookup_success(struct __sk_buff *skb)
 {
 	void *data_end = (void *)(long)skb->data_end;
 	void *data = (void *)(long)skb->data;
@@ -79,8 +78,8 @@ int bpf_sk_lookup_test0(struct __sk_buff *skb)
 	return sk ? TC_ACT_OK : TC_ACT_UNSPEC;
 }
 
-SEC("classifier/sk_lookup_success_simple")
-int bpf_sk_lookup_test1(struct __sk_buff *skb)
+SEC("tc")
+int sk_lookup_success_simple(struct __sk_buff *skb)
 {
 	struct bpf_sock_tuple tuple = {};
 	struct bpf_sock *sk;
@@ -91,8 +90,8 @@ int bpf_sk_lookup_test1(struct __sk_buff *skb)
 	return 0;
 }
 
-SEC("classifier/err_use_after_free")
-int bpf_sk_lookup_uaf(struct __sk_buff *skb)
+SEC("tc")
+int err_use_after_free(struct __sk_buff *skb)
 {
 	struct bpf_sock_tuple tuple = {};
 	struct bpf_sock *sk;
@@ -106,8 +105,8 @@ int bpf_sk_lookup_uaf(struct __sk_buff *skb)
 	return family;
 }
 
-SEC("classifier/err_modify_sk_pointer")
-int bpf_sk_lookup_modptr(struct __sk_buff *skb)
+SEC("tc")
+int err_modify_sk_pointer(struct __sk_buff *skb)
 {
 	struct bpf_sock_tuple tuple = {};
 	struct bpf_sock *sk;
@@ -121,8 +120,8 @@ int bpf_sk_lookup_modptr(struct __sk_buff *skb)
 	return 0;
 }
 
-SEC("classifier/err_modify_sk_or_null_pointer")
-int bpf_sk_lookup_modptr_or_null(struct __sk_buff *skb)
+SEC("tc")
+int err_modify_sk_or_null_pointer(struct __sk_buff *skb)
 {
 	struct bpf_sock_tuple tuple = {};
 	struct bpf_sock *sk;
@@ -135,8 +134,8 @@ int bpf_sk_lookup_modptr_or_null(struct __sk_buff *skb)
 	return 0;
 }
 
-SEC("classifier/err_no_release")
-int bpf_sk_lookup_test2(struct __sk_buff *skb)
+SEC("tc")
+int err_no_release(struct __sk_buff *skb)
 {
 	struct bpf_sock_tuple tuple = {};
 
@@ -144,8 +143,8 @@ int bpf_sk_lookup_test2(struct __sk_buff *skb)
 	return 0;
 }
 
-SEC("classifier/err_release_twice")
-int bpf_sk_lookup_test3(struct __sk_buff *skb)
+SEC("tc")
+int err_release_twice(struct __sk_buff *skb)
 {
 	struct bpf_sock_tuple tuple = {};
 	struct bpf_sock *sk;
@@ -156,8 +155,8 @@ int bpf_sk_lookup_test3(struct __sk_buff *skb)
 	return 0;
 }
 
-SEC("classifier/err_release_unchecked")
-int bpf_sk_lookup_test4(struct __sk_buff *skb)
+SEC("tc")
+int err_release_unchecked(struct __sk_buff *skb)
 {
 	struct bpf_sock_tuple tuple = {};
 	struct bpf_sock *sk;
@@ -173,8 +172,8 @@ void lookup_no_release(struct __sk_buff *skb)
 	bpf_sk_lookup_tcp(skb, &tuple, sizeof(tuple), BPF_F_CURRENT_NETNS, 0);
 }
 
-SEC("classifier/err_no_release_subcall")
-int bpf_sk_lookup_test5(struct __sk_buff *skb)
+SEC("tc")
+int err_no_release_subcall(struct __sk_buff *skb)
 {
 	lookup_no_release(skb);
 	return 0;
diff --git a/tools/testing/selftests/bpf/progs/test_skb_helpers.c b/tools/testing/selftests/bpf/progs/test_skb_helpers.c
index bb3fbf1a29e3..507215791c5b 100644
--- a/tools/testing/selftests/bpf/progs/test_skb_helpers.c
+++ b/tools/testing/selftests/bpf/progs/test_skb_helpers.c
@@ -14,7 +14,7 @@ struct {
 
 char _license[] SEC("license") = "GPL";
 
-SEC("classifier/test_skb_helpers")
+SEC("tc")
 int test_skb_helpers(struct __sk_buff *skb)
 {
 	struct task_struct *task;
diff --git a/tools/testing/selftests/bpf/progs/test_sockmap_update.c b/tools/testing/selftests/bpf/progs/test_sockmap_update.c
index 9d0c9f28cab2..6d64ea536e3d 100644
--- a/tools/testing/selftests/bpf/progs/test_sockmap_update.c
+++ b/tools/testing/selftests/bpf/progs/test_sockmap_update.c
@@ -24,7 +24,7 @@ struct {
 	__type(value, __u64);
 } dst_sock_hash SEC(".maps");
 
-SEC("classifier/copy_sock_map")
+SEC("tc")
 int copy_sock_map(void *ctx)
 {
 	struct bpf_sock *sk;
diff --git a/tools/testing/selftests/bpf/progs/test_tc_bpf.c b/tools/testing/selftests/bpf/progs/test_tc_bpf.c
index 18a3a7ed924a..d28ca8d1f3d0 100644
--- a/tools/testing/selftests/bpf/progs/test_tc_bpf.c
+++ b/tools/testing/selftests/bpf/progs/test_tc_bpf.c
@@ -5,7 +5,7 @@
 
 /* Dummy prog to test TC-BPF API */
 
-SEC("classifier")
+SEC("tc")
 int cls(struct __sk_buff *skb)
 {
 	return 0;
diff --git a/tools/testing/selftests/bpf/progs/test_tc_neigh.c b/tools/testing/selftests/bpf/progs/test_tc_neigh.c
index 0c93d326a663..3e32ea375ab4 100644
--- a/tools/testing/selftests/bpf/progs/test_tc_neigh.c
+++ b/tools/testing/selftests/bpf/progs/test_tc_neigh.c
@@ -70,7 +70,7 @@ static __always_inline bool is_remote_ep_v6(struct __sk_buff *skb,
 	return v6_equal(ip6h->daddr, addr);
 }
 
-SEC("classifier/chk_egress")
+SEC("tc")
 int tc_chk(struct __sk_buff *skb)
 {
 	void *data_end = ctx_ptr(skb->data_end);
@@ -83,7 +83,7 @@ int tc_chk(struct __sk_buff *skb)
 	return !raw[0] && !raw[1] && !raw[2] ? TC_ACT_SHOT : TC_ACT_OK;
 }
 
-SEC("classifier/dst_ingress")
+SEC("tc")
 int tc_dst(struct __sk_buff *skb)
 {
 	__u8 zero[ETH_ALEN * 2];
@@ -108,7 +108,7 @@ int tc_dst(struct __sk_buff *skb)
 	return bpf_redirect_neigh(IFINDEX_SRC, NULL, 0, 0);
 }
 
-SEC("classifier/src_ingress")
+SEC("tc")
 int tc_src(struct __sk_buff *skb)
 {
 	__u8 zero[ETH_ALEN * 2];
diff --git a/tools/testing/selftests/bpf/progs/test_tc_neigh_fib.c b/tools/testing/selftests/bpf/progs/test_tc_neigh_fib.c
index f7ab69cf018e..ec4cce19362d 100644
--- a/tools/testing/selftests/bpf/progs/test_tc_neigh_fib.c
+++ b/tools/testing/selftests/bpf/progs/test_tc_neigh_fib.c
@@ -75,7 +75,7 @@ static __always_inline int fill_fib_params_v6(struct __sk_buff *skb,
 	return 0;
 }
 
-SEC("classifier/chk_egress")
+SEC("tc")
 int tc_chk(struct __sk_buff *skb)
 {
 	void *data_end = ctx_ptr(skb->data_end);
@@ -143,13 +143,13 @@ static __always_inline int tc_redir(struct __sk_buff *skb)
 /* these are identical, but keep them separate for compatibility with the
  * section names expected by test_tc_redirect.sh
  */
-SEC("classifier/dst_ingress")
+SEC("tc")
 int tc_dst(struct __sk_buff *skb)
 {
 	return tc_redir(skb);
 }
 
-SEC("classifier/src_ingress")
+SEC("tc")
 int tc_src(struct __sk_buff *skb)
 {
 	return tc_redir(skb);
diff --git a/tools/testing/selftests/bpf/progs/test_tc_peer.c b/tools/testing/selftests/bpf/progs/test_tc_peer.c
index fe818cd5f010..365eacb5dc34 100644
--- a/tools/testing/selftests/bpf/progs/test_tc_peer.c
+++ b/tools/testing/selftests/bpf/progs/test_tc_peer.c
@@ -16,31 +16,31 @@ volatile const __u32 IFINDEX_DST;
 static const __u8 src_mac[] = {0x00, 0x11, 0x22, 0x33, 0x44, 0x55};
 static const __u8 dst_mac[] = {0x00, 0x22, 0x33, 0x44, 0x55, 0x66};
 
-SEC("classifier/chk_egress")
+SEC("tc")
 int tc_chk(struct __sk_buff *skb)
 {
 	return TC_ACT_SHOT;
 }
 
-SEC("classifier/dst_ingress")
+SEC("tc")
 int tc_dst(struct __sk_buff *skb)
 {
 	return bpf_redirect_peer(IFINDEX_SRC, 0);
 }
 
-SEC("classifier/src_ingress")
+SEC("tc")
 int tc_src(struct __sk_buff *skb)
 {
 	return bpf_redirect_peer(IFINDEX_DST, 0);
 }
 
-SEC("classifier/dst_ingress_l3")
+SEC("tc")
 int tc_dst_l3(struct __sk_buff *skb)
 {
 	return bpf_redirect(IFINDEX_SRC, 0);
 }
 
-SEC("classifier/src_ingress_l3")
+SEC("tc")
 int tc_src_l3(struct __sk_buff *skb)
 {
 	__u16 proto = skb->protocol;
diff --git a/tools/testing/selftests/bpf/progs/test_tcp_check_syncookie_kern.c b/tools/testing/selftests/bpf/progs/test_tcp_check_syncookie_kern.c
index fac7ef99f9a6..cd747cd93dbe 100644
--- a/tools/testing/selftests/bpf/progs/test_tcp_check_syncookie_kern.c
+++ b/tools/testing/selftests/bpf/progs/test_tcp_check_syncookie_kern.c
@@ -148,7 +148,7 @@ release:
 	bpf_sk_release(sk);
 }
 
-SEC("clsact/check_syncookie")
+SEC("tc")
 int check_syncookie_clsact(struct __sk_buff *skb)
 {
 	check_syncookie(skb, (void *)(long)skb->data,
diff --git a/tools/testing/selftests/bpf/test_tcp_check_syncookie.sh b/tools/testing/selftests/bpf/test_tcp_check_syncookie.sh
index fed765157c53..6413c1472554 100755
--- a/tools/testing/selftests/bpf/test_tcp_check_syncookie.sh
+++ b/tools/testing/selftests/bpf/test_tcp_check_syncookie.sh
@@ -76,7 +76,7 @@ DIR=$(dirname $0)
 TEST_IF=lo
 MAX_PING_TRIES=5
 BPF_PROG_OBJ="${DIR}/test_tcp_check_syncookie_kern.o"
-CLSACT_SECTION="clsact/check_syncookie"
+CLSACT_SECTION="tc"
 XDP_SECTION="xdp"
 BPF_PROG_ID=0
 PROG="${DIR}/test_tcp_check_syncookie_user"
-- 
cgit v1.2.3


From 15669e1dcd75fe6d51e495f8479222b5884665b6 Mon Sep 17 00:00:00 2001
From: Andrii Nakryiko <andrii@kernel.org>
Date: Tue, 28 Sep 2021 09:19:40 -0700
Subject: selftests/bpf: Normalize all the rest SEC() uses

Normalize all the other non-conforming SEC() usages across all
selftests. This is in preparation for libbpf to start to enforce
stricter SEC() rules in libbpf 1.0 mode.

Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Dave Marchevsky <davemarchevsky@fb.com>
Link: https://lore.kernel.org/bpf/20210928161946.2512801-5-andrii@kernel.org
---
 .../selftests/bpf/prog_tests/flow_dissector.c      |  4 +--
 .../selftests/bpf/prog_tests/sockopt_multi.c       | 30 +++++++++++-----------
 tools/testing/selftests/bpf/progs/bpf_flow.c       |  3 +--
 .../bpf/progs/cg_storage_multi_isolated.c          |  4 +--
 .../selftests/bpf/progs/cg_storage_multi_shared.c  |  4 +--
 tools/testing/selftests/bpf/progs/sockopt_multi.c  |  5 ++--
 .../testing/selftests/bpf/progs/test_cgroup_link.c |  4 +--
 .../bpf/progs/test_misc_tcp_hdr_options.c          |  2 +-
 tools/testing/selftests/bpf/progs/test_sk_lookup.c |  6 ++---
 .../selftests/bpf/progs/test_sockmap_listen.c      |  2 +-
 .../bpf/progs/test_sockmap_skb_verdict_attach.c    |  2 +-
 .../selftests/bpf/progs/test_tcp_hdr_options.c     |  2 +-
 12 files changed, 33 insertions(+), 35 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/prog_tests/flow_dissector.c b/tools/testing/selftests/bpf/prog_tests/flow_dissector.c
index 225714f71ac6..ac54e3f91d42 100644
--- a/tools/testing/selftests/bpf/prog_tests/flow_dissector.c
+++ b/tools/testing/selftests/bpf/prog_tests/flow_dissector.c
@@ -458,9 +458,9 @@ static int init_prog_array(struct bpf_object *obj, struct bpf_map *prog_array)
 		return -1;
 
 	for (i = 0; i < bpf_map__def(prog_array)->max_entries; i++) {
-		snprintf(prog_name, sizeof(prog_name), "flow_dissector/%i", i);
+		snprintf(prog_name, sizeof(prog_name), "flow_dissector_%d", i);
 
-		prog = bpf_object__find_program_by_title(obj, prog_name);
+		prog = bpf_object__find_program_by_name(obj, prog_name);
 		if (!prog)
 			return -1;
 
diff --git a/tools/testing/selftests/bpf/prog_tests/sockopt_multi.c b/tools/testing/selftests/bpf/prog_tests/sockopt_multi.c
index 51fac975b316..bc34f7773444 100644
--- a/tools/testing/selftests/bpf/prog_tests/sockopt_multi.c
+++ b/tools/testing/selftests/bpf/prog_tests/sockopt_multi.c
@@ -2,7 +2,7 @@
 #include <test_progs.h>
 #include "cgroup_helpers.h"
 
-static int prog_attach(struct bpf_object *obj, int cgroup_fd, const char *title)
+static int prog_attach(struct bpf_object *obj, int cgroup_fd, const char *title, const char *name)
 {
 	enum bpf_attach_type attach_type;
 	enum bpf_prog_type prog_type;
@@ -15,23 +15,23 @@ static int prog_attach(struct bpf_object *obj, int cgroup_fd, const char *title)
 		return -1;
 	}
 
-	prog = bpf_object__find_program_by_title(obj, title);
+	prog = bpf_object__find_program_by_name(obj, name);
 	if (!prog) {
-		log_err("Failed to find %s BPF program", title);
+		log_err("Failed to find %s BPF program", name);
 		return -1;
 	}
 
 	err = bpf_prog_attach(bpf_program__fd(prog), cgroup_fd,
 			      attach_type, BPF_F_ALLOW_MULTI);
 	if (err) {
-		log_err("Failed to attach %s BPF program", title);
+		log_err("Failed to attach %s BPF program", name);
 		return -1;
 	}
 
 	return 0;
 }
 
-static int prog_detach(struct bpf_object *obj, int cgroup_fd, const char *title)
+static int prog_detach(struct bpf_object *obj, int cgroup_fd, const char *title, const char *name)
 {
 	enum bpf_attach_type attach_type;
 	enum bpf_prog_type prog_type;
@@ -42,7 +42,7 @@ static int prog_detach(struct bpf_object *obj, int cgroup_fd, const char *title)
 	if (err)
 		return -1;
 
-	prog = bpf_object__find_program_by_title(obj, title);
+	prog = bpf_object__find_program_by_name(obj, name);
 	if (!prog)
 		return -1;
 
@@ -89,7 +89,7 @@ static int run_getsockopt_test(struct bpf_object *obj, int cg_parent,
 	 * - child:  0x80 -> 0x90
 	 */
 
-	err = prog_attach(obj, cg_child, "cgroup/getsockopt/child");
+	err = prog_attach(obj, cg_child, "cgroup/getsockopt", "_getsockopt_child");
 	if (err)
 		goto detach;
 
@@ -113,7 +113,7 @@ static int run_getsockopt_test(struct bpf_object *obj, int cg_parent,
 	 * - parent: 0x90 -> 0xA0
 	 */
 
-	err = prog_attach(obj, cg_parent, "cgroup/getsockopt/parent");
+	err = prog_attach(obj, cg_parent, "cgroup/getsockopt", "_getsockopt_parent");
 	if (err)
 		goto detach;
 
@@ -157,7 +157,7 @@ static int run_getsockopt_test(struct bpf_object *obj, int cg_parent,
 	 * - parent: unexpected 0x40, EPERM
 	 */
 
-	err = prog_detach(obj, cg_child, "cgroup/getsockopt/child");
+	err = prog_detach(obj, cg_child, "cgroup/getsockopt", "_getsockopt_child");
 	if (err) {
 		log_err("Failed to detach child program");
 		goto detach;
@@ -198,8 +198,8 @@ static int run_getsockopt_test(struct bpf_object *obj, int cg_parent,
 	}
 
 detach:
-	prog_detach(obj, cg_child, "cgroup/getsockopt/child");
-	prog_detach(obj, cg_parent, "cgroup/getsockopt/parent");
+	prog_detach(obj, cg_child, "cgroup/getsockopt", "_getsockopt_child");
+	prog_detach(obj, cg_parent, "cgroup/getsockopt", "_getsockopt_parent");
 
 	return err;
 }
@@ -236,7 +236,7 @@ static int run_setsockopt_test(struct bpf_object *obj, int cg_parent,
 
 	/* Attach child program and make sure it adds 0x10. */
 
-	err = prog_attach(obj, cg_child, "cgroup/setsockopt");
+	err = prog_attach(obj, cg_child, "cgroup/setsockopt", "_setsockopt");
 	if (err)
 		goto detach;
 
@@ -263,7 +263,7 @@ static int run_setsockopt_test(struct bpf_object *obj, int cg_parent,
 
 	/* Attach parent program and make sure it adds another 0x10. */
 
-	err = prog_attach(obj, cg_parent, "cgroup/setsockopt");
+	err = prog_attach(obj, cg_parent, "cgroup/setsockopt", "_setsockopt");
 	if (err)
 		goto detach;
 
@@ -289,8 +289,8 @@ static int run_setsockopt_test(struct bpf_object *obj, int cg_parent,
 	}
 
 detach:
-	prog_detach(obj, cg_child, "cgroup/setsockopt");
-	prog_detach(obj, cg_parent, "cgroup/setsockopt");
+	prog_detach(obj, cg_child, "cgroup/setsockopt", "_setsockopt");
+	prog_detach(obj, cg_parent, "cgroup/setsockopt", "_setsockopt");
 
 	return err;
 }
diff --git a/tools/testing/selftests/bpf/progs/bpf_flow.c b/tools/testing/selftests/bpf/progs/bpf_flow.c
index 95a5a0778ed7..f266c757b3df 100644
--- a/tools/testing/selftests/bpf/progs/bpf_flow.c
+++ b/tools/testing/selftests/bpf/progs/bpf_flow.c
@@ -19,9 +19,8 @@
 #include <bpf/bpf_helpers.h>
 #include <bpf/bpf_endian.h>
 
-int _version SEC("version") = 1;
 #define PROG(F) PROG_(F, _##F)
-#define PROG_(NUM, NAME) SEC("flow_dissector/"#NUM) int bpf_func##NAME
+#define PROG_(NUM, NAME) SEC("flow_dissector") int flow_dissector_##NUM
 
 /* These are the identifiers of the BPF programs that will be used in tail
  * calls. Name is limited to 16 characters, with the terminating character and
diff --git a/tools/testing/selftests/bpf/progs/cg_storage_multi_isolated.c b/tools/testing/selftests/bpf/progs/cg_storage_multi_isolated.c
index a25373002055..3f81ff92184c 100644
--- a/tools/testing/selftests/bpf/progs/cg_storage_multi_isolated.c
+++ b/tools/testing/selftests/bpf/progs/cg_storage_multi_isolated.c
@@ -20,7 +20,7 @@ struct {
 
 __u32 invocations = 0;
 
-SEC("cgroup_skb/egress/1")
+SEC("cgroup_skb/egress")
 int egress1(struct __sk_buff *skb)
 {
 	struct cgroup_value *ptr_cg_storage =
@@ -32,7 +32,7 @@ int egress1(struct __sk_buff *skb)
 	return 1;
 }
 
-SEC("cgroup_skb/egress/2")
+SEC("cgroup_skb/egress")
 int egress2(struct __sk_buff *skb)
 {
 	struct cgroup_value *ptr_cg_storage =
diff --git a/tools/testing/selftests/bpf/progs/cg_storage_multi_shared.c b/tools/testing/selftests/bpf/progs/cg_storage_multi_shared.c
index a149f33bc533..d662db27fe4a 100644
--- a/tools/testing/selftests/bpf/progs/cg_storage_multi_shared.c
+++ b/tools/testing/selftests/bpf/progs/cg_storage_multi_shared.c
@@ -20,7 +20,7 @@ struct {
 
 __u32 invocations = 0;
 
-SEC("cgroup_skb/egress/1")
+SEC("cgroup_skb/egress")
 int egress1(struct __sk_buff *skb)
 {
 	struct cgroup_value *ptr_cg_storage =
@@ -32,7 +32,7 @@ int egress1(struct __sk_buff *skb)
 	return 1;
 }
 
-SEC("cgroup_skb/egress/2")
+SEC("cgroup_skb/egress")
 int egress2(struct __sk_buff *skb)
 {
 	struct cgroup_value *ptr_cg_storage =
diff --git a/tools/testing/selftests/bpf/progs/sockopt_multi.c b/tools/testing/selftests/bpf/progs/sockopt_multi.c
index 9d8c212dde9f..177a59069dae 100644
--- a/tools/testing/selftests/bpf/progs/sockopt_multi.c
+++ b/tools/testing/selftests/bpf/progs/sockopt_multi.c
@@ -4,9 +4,8 @@
 #include <bpf/bpf_helpers.h>
 
 char _license[] SEC("license") = "GPL";
-__u32 _version SEC("version") = 1;
 
-SEC("cgroup/getsockopt/child")
+SEC("cgroup/getsockopt")
 int _getsockopt_child(struct bpf_sockopt *ctx)
 {
 	__u8 *optval_end = ctx->optval_end;
@@ -29,7 +28,7 @@ int _getsockopt_child(struct bpf_sockopt *ctx)
 	return 1;
 }
 
-SEC("cgroup/getsockopt/parent")
+SEC("cgroup/getsockopt")
 int _getsockopt_parent(struct bpf_sockopt *ctx)
 {
 	__u8 *optval_end = ctx->optval_end;
diff --git a/tools/testing/selftests/bpf/progs/test_cgroup_link.c b/tools/testing/selftests/bpf/progs/test_cgroup_link.c
index 77e47b9e4446..4faba88e45a5 100644
--- a/tools/testing/selftests/bpf/progs/test_cgroup_link.c
+++ b/tools/testing/selftests/bpf/progs/test_cgroup_link.c
@@ -6,14 +6,14 @@
 int calls = 0;
 int alt_calls = 0;
 
-SEC("cgroup_skb/egress1")
+SEC("cgroup_skb/egress")
 int egress(struct __sk_buff *skb)
 {
 	__sync_fetch_and_add(&calls, 1);
 	return 1;
 }
 
-SEC("cgroup_skb/egress2")
+SEC("cgroup_skb/egress")
 int egress_alt(struct __sk_buff *skb)
 {
 	__sync_fetch_and_add(&alt_calls, 1);
diff --git a/tools/testing/selftests/bpf/progs/test_misc_tcp_hdr_options.c b/tools/testing/selftests/bpf/progs/test_misc_tcp_hdr_options.c
index 6077a025092c..2c121c5d66a7 100644
--- a/tools/testing/selftests/bpf/progs/test_misc_tcp_hdr_options.c
+++ b/tools/testing/selftests/bpf/progs/test_misc_tcp_hdr_options.c
@@ -293,7 +293,7 @@ static int handle_passive_estab(struct bpf_sock_ops *skops)
 	return check_active_hdr_in(skops);
 }
 
-SEC("sockops/misc_estab")
+SEC("sockops")
 int misc_estab(struct bpf_sock_ops *skops)
 {
 	int true_val = 1;
diff --git a/tools/testing/selftests/bpf/progs/test_sk_lookup.c b/tools/testing/selftests/bpf/progs/test_sk_lookup.c
index ac6f7f205e25..6c4d32c56765 100644
--- a/tools/testing/selftests/bpf/progs/test_sk_lookup.c
+++ b/tools/testing/selftests/bpf/progs/test_sk_lookup.c
@@ -84,13 +84,13 @@ int lookup_drop(struct bpf_sk_lookup *ctx)
 	return SK_DROP;
 }
 
-SEC("sk_reuseport/reuse_pass")
+SEC("sk_reuseport")
 int reuseport_pass(struct sk_reuseport_md *ctx)
 {
 	return SK_PASS;
 }
 
-SEC("sk_reuseport/reuse_drop")
+SEC("sk_reuseport")
 int reuseport_drop(struct sk_reuseport_md *ctx)
 {
 	return SK_DROP;
@@ -194,7 +194,7 @@ int select_sock_a_no_reuseport(struct bpf_sk_lookup *ctx)
 	return err ? SK_DROP : SK_PASS;
 }
 
-SEC("sk_reuseport/select_sock_b")
+SEC("sk_reuseport")
 int select_sock_b(struct sk_reuseport_md *ctx)
 {
 	__u32 key = KEY_SERVER_B;
diff --git a/tools/testing/selftests/bpf/progs/test_sockmap_listen.c b/tools/testing/selftests/bpf/progs/test_sockmap_listen.c
index a1cc58b10c7c..00f1456aaeda 100644
--- a/tools/testing/selftests/bpf/progs/test_sockmap_listen.c
+++ b/tools/testing/selftests/bpf/progs/test_sockmap_listen.c
@@ -56,7 +56,7 @@ int prog_stream_verdict(struct __sk_buff *skb)
 	return verdict;
 }
 
-SEC("sk_skb/skb_verdict")
+SEC("sk_skb")
 int prog_skb_verdict(struct __sk_buff *skb)
 {
 	unsigned int *count;
diff --git a/tools/testing/selftests/bpf/progs/test_sockmap_skb_verdict_attach.c b/tools/testing/selftests/bpf/progs/test_sockmap_skb_verdict_attach.c
index 2d31f66e4f23..3c69aa971738 100644
--- a/tools/testing/selftests/bpf/progs/test_sockmap_skb_verdict_attach.c
+++ b/tools/testing/selftests/bpf/progs/test_sockmap_skb_verdict_attach.c
@@ -9,7 +9,7 @@ struct {
 	__type(value, __u64);
 } sock_map SEC(".maps");
 
-SEC("sk_skb/skb_verdict")
+SEC("sk_skb")
 int prog_skb_verdict(struct __sk_buff *skb)
 {
 	return SK_DROP;
diff --git a/tools/testing/selftests/bpf/progs/test_tcp_hdr_options.c b/tools/testing/selftests/bpf/progs/test_tcp_hdr_options.c
index 678bd0fad29e..5f4e87ee949a 100644
--- a/tools/testing/selftests/bpf/progs/test_tcp_hdr_options.c
+++ b/tools/testing/selftests/bpf/progs/test_tcp_hdr_options.c
@@ -594,7 +594,7 @@ static int handle_parse_hdr(struct bpf_sock_ops *skops)
 	return CG_OK;
 }
 
-SEC("sockops/estab")
+SEC("sockops")
 int estab(struct bpf_sock_ops *skops)
 {
 	int true_val = 1;
-- 
cgit v1.2.3


From 12d9466d8bf3d1d4b4fd0f5733b6fa0cc5ee1013 Mon Sep 17 00:00:00 2001
From: Andrii Nakryiko <andrii@kernel.org>
Date: Tue, 28 Sep 2021 09:19:41 -0700
Subject: libbpf: Refactor internal sec_def handling to enable pluggability

Refactor internals of libbpf to allow adding custom SEC() handling logic
easily from outside of libbpf. To that effect, each SEC()-handling
registration sets mandatory program type/expected attach type for
a given prefix and can provide three callbacks called at different
points of BPF program lifetime:

  - init callback for right after bpf_program is initialized and
  prog_type/expected_attach_type is set. This happens during
  bpf_object__open() step, close to the very end of constructing
  bpf_object, so all the libbpf APIs for querying and updating
  bpf_program properties should be available;

  - pre-load callback is called right before BPF_PROG_LOAD command is
  called in the kernel. This callbacks has ability to set both
  bpf_program properties, as well as program load attributes, overriding
  and augmenting the standard libbpf handling of them;

  - optional auto-attach callback, which makes a given SEC() handler
  support auto-attachment of a BPF program through bpf_program__attach()
  API and/or BPF skeletons <skel>__attach() method.

Each callbacks gets a `long cookie` parameter passed in, which is
specified during SEC() handling. This can be used by callbacks to lookup
whatever additional information is necessary.

This is not yet completely ready to be exposed to the outside world,
mainly due to non-public nature of struct bpf_prog_load_params. Instead
of making it part of public API, we'll wait until the planned low-level
libbpf API improvements for BPF_PROG_LOAD and other typical bpf()
syscall APIs, at which point we'll have a public, probably OPTS-based,
way to fully specify BPF program load parameters, which will be used as
an interface for custom pre-load callbacks.

But this change itself is already a good first step to unify the BPF
program hanling logic even within the libbpf itself. As one example, all
the extra per-program type handling (sleepable bit, attach_btf_id
resolution, unsetting optional expected attach type) is now more obvious
and is gathered in one place.

Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Dave Marchevsky <davemarchevsky@fb.com>
Link: https://lore.kernel.org/bpf/20210928161946.2512801-6-andrii@kernel.org
---
 tools/lib/bpf/libbpf.c | 129 +++++++++++++++++++++++++++++++++----------------
 1 file changed, 87 insertions(+), 42 deletions(-)

(limited to 'tools')

diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 0bcd0a4c867a..d4d56536dc4b 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -220,7 +220,9 @@ struct reloc_desc {
 
 struct bpf_sec_def;
 
-typedef struct bpf_link *(*attach_fn_t)(const struct bpf_program *prog);
+typedef int (*init_fn_t)(struct bpf_program *prog, long cookie);
+typedef int (*preload_fn_t)(struct bpf_program *prog, struct bpf_prog_load_params *attr, long cookie);
+typedef struct bpf_link *(*attach_fn_t)(const struct bpf_program *prog, long cookie);
 
 struct bpf_sec_def {
 	const char *sec;
@@ -231,7 +233,11 @@ struct bpf_sec_def {
 	bool is_attachable;
 	bool is_attach_btf;
 	bool is_sleepable;
+
+	init_fn_t init_fn;
+	preload_fn_t preload_fn;
 	attach_fn_t attach_fn;
+	long cookie;
 };
 
 /*
@@ -6095,6 +6101,44 @@ static int bpf_object__sanitize_prog(struct bpf_object *obj, struct bpf_program
 	return 0;
 }
 
+static int libbpf_find_attach_btf_id(struct bpf_program *prog, int *btf_obj_fd, int *btf_type_id);
+
+/* this is called as prog->sec_def->preload_fn for libbpf-supported sec_defs */
+static int libbpf_preload_prog(struct bpf_program *prog,
+			       struct bpf_prog_load_params *attr, long cookie)
+{
+	/* old kernels might not support specifying expected_attach_type */
+	if (prog->sec_def->is_exp_attach_type_optional &&
+	    !kernel_supports(prog->obj, FEAT_EXP_ATTACH_TYPE))
+		attr->expected_attach_type = 0;
+
+	if (prog->sec_def->is_sleepable)
+		attr->prog_flags |= BPF_F_SLEEPABLE;
+
+	if ((prog->type == BPF_PROG_TYPE_TRACING ||
+	     prog->type == BPF_PROG_TYPE_LSM ||
+	     prog->type == BPF_PROG_TYPE_EXT) && !prog->attach_btf_id) {
+		int btf_obj_fd = 0, btf_type_id = 0, err;
+
+		err = libbpf_find_attach_btf_id(prog, &btf_obj_fd, &btf_type_id);
+		if (err)
+			return err;
+
+		/* cache resolved BTF FD and BTF type ID in the prog */
+		prog->attach_btf_obj_fd = btf_obj_fd;
+		prog->attach_btf_id = btf_type_id;
+
+		/* but by now libbpf common logic is not utilizing
+		 * prog->atach_btf_obj_fd/prog->attach_btf_id anymore because
+		 * this callback is called after attrs were populated by
+		 * libbpf, so this callback has to update attr explicitly here
+		 */
+		attr->attach_btf_obj_fd = btf_obj_fd;
+		attr->attach_btf_id = btf_type_id;
+	}
+	return 0;
+}
+
 static int
 load_program(struct bpf_program *prog, struct bpf_insn *insns, int insns_cnt,
 	     char *license, __u32 kern_version, int *pfd)
@@ -6103,7 +6147,7 @@ load_program(struct bpf_program *prog, struct bpf_insn *insns, int insns_cnt,
 	char *cp, errmsg[STRERR_BUFSIZE];
 	size_t log_buf_size = 0;
 	char *log_buf = NULL;
-	int btf_fd, ret;
+	int btf_fd, ret, err;
 
 	if (prog->type == BPF_PROG_TYPE_UNSPEC) {
 		/*
@@ -6119,22 +6163,15 @@ load_program(struct bpf_program *prog, struct bpf_insn *insns, int insns_cnt,
 		return -EINVAL;
 
 	load_attr.prog_type = prog->type;
-	/* old kernels might not support specifying expected_attach_type */
-	if (!kernel_supports(prog->obj, FEAT_EXP_ATTACH_TYPE) && prog->sec_def &&
-	    prog->sec_def->is_exp_attach_type_optional)
-		load_attr.expected_attach_type = 0;
-	else
-		load_attr.expected_attach_type = prog->expected_attach_type;
+	load_attr.expected_attach_type = prog->expected_attach_type;
 	if (kernel_supports(prog->obj, FEAT_PROG_NAME))
 		load_attr.name = prog->name;
 	load_attr.insns = insns;
 	load_attr.insn_cnt = insns_cnt;
 	load_attr.license = license;
 	load_attr.attach_btf_id = prog->attach_btf_id;
-	if (prog->attach_prog_fd)
-		load_attr.attach_prog_fd = prog->attach_prog_fd;
-	else
-		load_attr.attach_btf_obj_fd = prog->attach_btf_obj_fd;
+	load_attr.attach_prog_fd = prog->attach_prog_fd;
+	load_attr.attach_btf_obj_fd = prog->attach_btf_obj_fd;
 	load_attr.attach_btf_id = prog->attach_btf_id;
 	load_attr.kern_version = kern_version;
 	load_attr.prog_ifindex = prog->prog_ifindex;
@@ -6153,6 +6190,16 @@ load_program(struct bpf_program *prog, struct bpf_insn *insns, int insns_cnt,
 	load_attr.log_level = prog->log_level;
 	load_attr.prog_flags = prog->prog_flags;
 
+	/* adjust load_attr if sec_def provides custom preload callback */
+	if (prog->sec_def && prog->sec_def->preload_fn) {
+		err = prog->sec_def->preload_fn(prog, &load_attr, prog->sec_def->cookie);
+		if (err < 0) {
+			pr_warn("prog '%s': failed to prepare load attributes: %d\n",
+				prog->name, err);
+			return err;
+		}
+	}
+
 	if (prog->obj->gen_loader) {
 		bpf_gen__prog_load(prog->obj->gen_loader, &load_attr,
 				   prog - prog->obj->programs);
@@ -6268,8 +6315,6 @@ static int bpf_program__record_externs(struct bpf_program *prog)
 	return 0;
 }
 
-static int libbpf_find_attach_btf_id(struct bpf_program *prog, int *btf_obj_fd, int *btf_type_id);
-
 int bpf_program__load(struct bpf_program *prog, char *license, __u32 kern_ver)
 {
 	int err = 0, fd, i;
@@ -6279,19 +6324,6 @@ int bpf_program__load(struct bpf_program *prog, char *license, __u32 kern_ver)
 		return libbpf_err(-EINVAL);
 	}
 
-	if ((prog->type == BPF_PROG_TYPE_TRACING ||
-	     prog->type == BPF_PROG_TYPE_LSM ||
-	     prog->type == BPF_PROG_TYPE_EXT) && !prog->attach_btf_id) {
-		int btf_obj_fd = 0, btf_type_id = 0;
-
-		err = libbpf_find_attach_btf_id(prog, &btf_obj_fd, &btf_type_id);
-		if (err)
-			return libbpf_err(err);
-
-		prog->attach_btf_obj_fd = btf_obj_fd;
-		prog->attach_btf_id = btf_type_id;
-	}
-
 	if (prog->instances.nr < 0 || !prog->instances.fds) {
 		if (prog->preprocessor) {
 			pr_warn("Internal error: can't load program '%s'\n",
@@ -6401,6 +6433,7 @@ static const struct bpf_sec_def *find_sec_def(const char *sec_name);
 static int bpf_object_init_progs(struct bpf_object *obj, const struct bpf_object_open_opts *opts)
 {
 	struct bpf_program *prog;
+	int err;
 
 	bpf_object__for_each_program(prog, obj) {
 		prog->sec_def = find_sec_def(prog->sec_name);
@@ -6411,8 +6444,6 @@ static int bpf_object_init_progs(struct bpf_object *obj, const struct bpf_object
 			continue;
 		}
 
-		if (prog->sec_def->is_sleepable)
-			prog->prog_flags |= BPF_F_SLEEPABLE;
 		bpf_program__set_type(prog, prog->sec_def->prog_type);
 		bpf_program__set_expected_attach_type(prog, prog->sec_def->expected_attach_type);
 
@@ -6422,6 +6453,18 @@ static int bpf_object_init_progs(struct bpf_object *obj, const struct bpf_object
 		    prog->sec_def->prog_type == BPF_PROG_TYPE_EXT)
 			prog->attach_prog_fd = OPTS_GET(opts, attach_prog_fd, 0);
 #pragma GCC diagnostic pop
+
+		/* sec_def can have custom callback which should be called
+		 * after bpf_program is initialized to adjust its properties
+		 */
+		if (prog->sec_def->init_fn) {
+			err = prog->sec_def->init_fn(prog, prog->sec_def->cookie);
+			if (err < 0) {
+				pr_warn("prog '%s': failed to initialize: %d\n",
+					prog->name, err);
+				return err;
+			}
+		}
 	}
 
 	return 0;
@@ -7919,6 +7962,7 @@ void bpf_program__set_expected_attach_type(struct bpf_program *prog,
 		.is_exp_attach_type_optional = eatype_optional,		    \
 		.is_attachable = attachable,				    \
 		.is_attach_btf = attach_btf,				    \
+		.preload_fn = libbpf_preload_prog,			    \
 	}
 
 /* Programs that can NOT be attached. */
@@ -7945,15 +7989,16 @@ void bpf_program__set_expected_attach_type(struct bpf_program *prog,
 	.sec = sec_pfx,							    \
 	.len = sizeof(sec_pfx) - 1,					    \
 	.prog_type = BPF_PROG_TYPE_##ptype,				    \
+	.preload_fn = libbpf_preload_prog,				    \
 	__VA_ARGS__							    \
 }
 
-static struct bpf_link *attach_kprobe(const struct bpf_program *prog);
-static struct bpf_link *attach_tp(const struct bpf_program *prog);
-static struct bpf_link *attach_raw_tp(const struct bpf_program *prog);
-static struct bpf_link *attach_trace(const struct bpf_program *prog);
-static struct bpf_link *attach_lsm(const struct bpf_program *prog);
-static struct bpf_link *attach_iter(const struct bpf_program *prog);
+static struct bpf_link *attach_kprobe(const struct bpf_program *prog, long cookie);
+static struct bpf_link *attach_tp(const struct bpf_program *prog, long cookie);
+static struct bpf_link *attach_raw_tp(const struct bpf_program *prog, long cookie);
+static struct bpf_link *attach_trace(const struct bpf_program *prog, long cookie);
+static struct bpf_link *attach_lsm(const struct bpf_program *prog, long cookie);
+static struct bpf_link *attach_iter(const struct bpf_program *prog, long cookie);
 
 static const struct bpf_sec_def section_defs[] = {
 	BPF_PROG_SEC("socket",			BPF_PROG_TYPE_SOCKET_FILTER),
@@ -9425,7 +9470,7 @@ struct bpf_link *bpf_program__attach_kprobe(const struct bpf_program *prog,
 	return bpf_program__attach_kprobe_opts(prog, func_name, &opts);
 }
 
-static struct bpf_link *attach_kprobe(const struct bpf_program *prog)
+static struct bpf_link *attach_kprobe(const struct bpf_program *prog, long cookie)
 {
 	DECLARE_LIBBPF_OPTS(bpf_kprobe_opts, opts);
 	unsigned long offset = 0;
@@ -9708,7 +9753,7 @@ struct bpf_link *bpf_program__attach_tracepoint(const struct bpf_program *prog,
 	return bpf_program__attach_tracepoint_opts(prog, tp_category, tp_name, NULL);
 }
 
-static struct bpf_link *attach_tp(const struct bpf_program *prog)
+static struct bpf_link *attach_tp(const struct bpf_program *prog, long cookie)
 {
 	char *sec_name, *tp_cat, *tp_name;
 	struct bpf_link *link;
@@ -9762,7 +9807,7 @@ struct bpf_link *bpf_program__attach_raw_tracepoint(const struct bpf_program *pr
 	return link;
 }
 
-static struct bpf_link *attach_raw_tp(const struct bpf_program *prog)
+static struct bpf_link *attach_raw_tp(const struct bpf_program *prog, long cookie)
 {
 	const char *tp_name = prog->sec_name + prog->sec_def->len;
 
@@ -9809,12 +9854,12 @@ struct bpf_link *bpf_program__attach_lsm(const struct bpf_program *prog)
 	return bpf_program__attach_btf_id(prog);
 }
 
-static struct bpf_link *attach_trace(const struct bpf_program *prog)
+static struct bpf_link *attach_trace(const struct bpf_program *prog, long cookie)
 {
 	return bpf_program__attach_trace(prog);
 }
 
-static struct bpf_link *attach_lsm(const struct bpf_program *prog)
+static struct bpf_link *attach_lsm(const struct bpf_program *prog, long cookie)
 {
 	return bpf_program__attach_lsm(prog);
 }
@@ -9945,7 +9990,7 @@ bpf_program__attach_iter(const struct bpf_program *prog,
 	return link;
 }
 
-static struct bpf_link *attach_iter(const struct bpf_program *prog)
+static struct bpf_link *attach_iter(const struct bpf_program *prog, long cookie)
 {
 	return bpf_program__attach_iter(prog, NULL);
 }
@@ -9955,7 +10000,7 @@ struct bpf_link *bpf_program__attach(const struct bpf_program *prog)
 	if (!prog->sec_def || !prog->sec_def->attach_fn)
 		return libbpf_err_ptr(-ESRCH);
 
-	return prog->sec_def->attach_fn(prog);
+	return prog->sec_def->attach_fn(prog, prog->sec_def->cookie);
 }
 
 static int bpf_link__detach_struct_ops(struct bpf_link *link)
-- 
cgit v1.2.3


From 13d35a0cf1741431333ba4aa9bce9c5bbc88f63b Mon Sep 17 00:00:00 2001
From: Andrii Nakryiko <andrii@kernel.org>
Date: Tue, 28 Sep 2021 09:19:42 -0700
Subject: libbpf: Reduce reliance of attach_fns on sec_def internals

Move closer to not relying on bpf_sec_def internals that won't be part
of public API, when pluggable SEC() handlers will be allowed. Drop
pre-calculated prefix length, and in various helpers don't rely on this
prefix length availability. Also minimize reliance on knowing
bpf_sec_def's prefix for few places where section prefix shortcuts are
supported (e.g., tp vs tracepoint, raw_tp vs raw_tracepoint).

Given checking some string for having a given string-constant prefix is
such a common operation and so annoying to be done with pure C code, add
a small macro helper, str_has_pfx(), and reuse it throughout libbpf.c
where prefix comparison is performed. With __builtin_constant_p() it's
possible to have a convenient helper that checks some string for having
a given prefix, where prefix is either string literal (or compile-time
known string due to compiler optimization) or just a runtime string
pointer, which is quite convenient and saves a lot of typing and string
literal duplication.

Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Dave Marchevsky <davemarchevsky@fb.com>
Link: https://lore.kernel.org/bpf/20210928161946.2512801-7-andrii@kernel.org
---
 tools/lib/bpf/libbpf.c          | 41 +++++++++++++++++++++++------------------
 tools/lib/bpf/libbpf_internal.h |  7 +++++++
 2 files changed, 30 insertions(+), 18 deletions(-)

(limited to 'tools')

diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index d4d56536dc4b..f87ffd4d7eab 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -226,7 +226,6 @@ typedef struct bpf_link *(*attach_fn_t)(const struct bpf_program *prog, long coo
 
 struct bpf_sec_def {
 	const char *sec;
-	size_t len;
 	enum bpf_prog_type prog_type;
 	enum bpf_attach_type expected_attach_type;
 	bool is_exp_attach_type_optional;
@@ -1671,7 +1670,7 @@ static int bpf_object__process_kconfig_line(struct bpf_object *obj,
 	void *ext_val;
 	__u64 num;
 
-	if (strncmp(buf, "CONFIG_", 7))
+	if (!str_has_pfx(buf, "CONFIG_"))
 		return 0;
 
 	sep = strchr(buf, '=');
@@ -2920,7 +2919,7 @@ static Elf_Data *elf_sec_data(const struct bpf_object *obj, Elf_Scn *scn)
 static bool is_sec_name_dwarf(const char *name)
 {
 	/* approximation, but the actual list is too long */
-	return strncmp(name, ".debug_", sizeof(".debug_") - 1) == 0;
+	return str_has_pfx(name, ".debug_");
 }
 
 static bool ignore_elf_section(GElf_Shdr *hdr, const char *name)
@@ -2942,7 +2941,7 @@ static bool ignore_elf_section(GElf_Shdr *hdr, const char *name)
 	if (is_sec_name_dwarf(name))
 		return true;
 
-	if (strncmp(name, ".rel", sizeof(".rel") - 1) == 0) {
+	if (str_has_pfx(name, ".rel")) {
 		name += sizeof(".rel") - 1;
 		/* DWARF section relocations */
 		if (is_sec_name_dwarf(name))
@@ -6891,8 +6890,7 @@ static int bpf_object__resolve_externs(struct bpf_object *obj,
 			if (err)
 				return err;
 			pr_debug("extern (kcfg) %s=0x%x\n", ext->name, kver);
-		} else if (ext->type == EXT_KCFG &&
-			   strncmp(ext->name, "CONFIG_", 7) == 0) {
+		} else if (ext->type == EXT_KCFG && str_has_pfx(ext->name, "CONFIG_")) {
 			need_config = true;
 		} else if (ext->type == EXT_KSYM) {
 			if (ext->ksym.type_id)
@@ -7956,7 +7954,6 @@ void bpf_program__set_expected_attach_type(struct bpf_program *prog,
 			  attachable, attach_btf)			    \
 	{								    \
 		.sec = string,						    \
-		.len = sizeof(string) - 1,				    \
 		.prog_type = ptype,					    \
 		.expected_attach_type = eatype,				    \
 		.is_exp_attach_type_optional = eatype_optional,		    \
@@ -7987,7 +7984,6 @@ void bpf_program__set_expected_attach_type(struct bpf_program *prog,
 
 #define SEC_DEF(sec_pfx, ptype, ...) {					    \
 	.sec = sec_pfx,							    \
-	.len = sizeof(sec_pfx) - 1,					    \
 	.prog_type = BPF_PROG_TYPE_##ptype,				    \
 	.preload_fn = libbpf_preload_prog,				    \
 	__VA_ARGS__							    \
@@ -8162,10 +8158,8 @@ static const struct bpf_sec_def *find_sec_def(const char *sec_name)
 	int i, n = ARRAY_SIZE(section_defs);
 
 	for (i = 0; i < n; i++) {
-		if (strncmp(sec_name,
-			    section_defs[i].sec, section_defs[i].len))
-			continue;
-		return &section_defs[i];
+		if (str_has_pfx(sec_name, section_defs[i].sec))
+			return &section_defs[i];
 	}
 	return NULL;
 }
@@ -8519,7 +8513,7 @@ static int libbpf_find_attach_btf_id(struct bpf_program *prog, int *btf_obj_fd,
 			prog->sec_name);
 		return -ESRCH;
 	}
-	attach_name = prog->sec_name + prog->sec_def->len;
+	attach_name = prog->sec_name + strlen(prog->sec_def->sec);
 
 	/* BPF program's BTF ID */
 	if (attach_prog_fd) {
@@ -9479,8 +9473,11 @@ static struct bpf_link *attach_kprobe(const struct bpf_program *prog, long cooki
 	char *func;
 	int n, err;
 
-	func_name = prog->sec_name + prog->sec_def->len;
-	opts.retprobe = strcmp(prog->sec_def->sec, "kretprobe/") == 0;
+	opts.retprobe = str_has_pfx(prog->sec_name, "kretprobe/");
+	if (opts.retprobe)
+		func_name = prog->sec_name + sizeof("kretprobe/") - 1;
+	else
+		func_name = prog->sec_name + sizeof("kprobe/") - 1;
 
 	n = sscanf(func_name, "%m[a-zA-Z0-9_.]+%li", &func, &offset);
 	if (n < 1) {
@@ -9762,8 +9759,11 @@ static struct bpf_link *attach_tp(const struct bpf_program *prog, long cookie)
 	if (!sec_name)
 		return libbpf_err_ptr(-ENOMEM);
 
-	/* extract "tp/<category>/<name>" */
-	tp_cat = sec_name + prog->sec_def->len;
+	/* extract "tp/<category>/<name>" or "tracepoint/<category>/<name>" */
+	if (str_has_pfx(prog->sec_name, "tp/"))
+		tp_cat = sec_name + sizeof("tp/") - 1;
+	else
+		tp_cat = sec_name + sizeof("tracepoint/") - 1;
 	tp_name = strchr(tp_cat, '/');
 	if (!tp_name) {
 		free(sec_name);
@@ -9809,7 +9809,12 @@ struct bpf_link *bpf_program__attach_raw_tracepoint(const struct bpf_program *pr
 
 static struct bpf_link *attach_raw_tp(const struct bpf_program *prog, long cookie)
 {
-	const char *tp_name = prog->sec_name + prog->sec_def->len;
+	const char *tp_name;
+
+	if (str_has_pfx(prog->sec_name, "raw_tp/"))
+		tp_name = prog->sec_name + sizeof("raw_tp/") - 1;
+	else
+		tp_name = prog->sec_name + sizeof("raw_tracepoint/") - 1;
 
 	return bpf_program__attach_raw_tracepoint(prog, tp_name);
 }
diff --git a/tools/lib/bpf/libbpf_internal.h b/tools/lib/bpf/libbpf_internal.h
index ceb0c98979bc..ec79400517d4 100644
--- a/tools/lib/bpf/libbpf_internal.h
+++ b/tools/lib/bpf/libbpf_internal.h
@@ -89,6 +89,13 @@
 	(offsetof(TYPE, FIELD) + sizeof(((TYPE *)0)->FIELD))
 #endif
 
+/* Check whether a string `str` has prefix `pfx`, regardless if `pfx` is
+ * a string literal known at compilation time or char * pointer known only at
+ * runtime.
+ */
+#define str_has_pfx(str, pfx) \
+	(strncmp(str, pfx, __builtin_constant_p(pfx) ? sizeof(pfx) - 1 : strlen(pfx)) == 0)
+
 /* Symbol versioning is different between static and shared library.
  * Properly versioned symbols are needed for shared library, but
  * only the symbol of the new version is needed for static library.
-- 
cgit v1.2.3


From 15ea31fadd7f5b1076b4f91f75562bc319799c24 Mon Sep 17 00:00:00 2001
From: Andrii Nakryiko <andrii@kernel.org>
Date: Tue, 28 Sep 2021 09:19:43 -0700
Subject: libbpf: Refactor ELF section handler definitions

Refactor ELF section handler definitions table to use a set of flags and
unified SEC_DEF() macro. This allows for more succinct and table-like
set of definitions, and allows to more easily extend the logic without
adding more verbosity (this is utilized in later patches in the series).

This approach is also making libbpf-internal program pre-load callback
not rely on bpf_sec_def definition, which demonstrates that future
pluggable ELF section handlers will be able to achieve similar level of
integration without libbpf having to expose extra types and APIs.

For starters, update SEC_DEF() definitions and make them more succinct.
Also convert BPF_PROG_SEC() and BPF_APROG_COMPAT() definitions to
a common SEC_DEF() use.

Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Dave Marchevsky <davemarchevsky@fb.com>
Link: https://lore.kernel.org/bpf/20210928161946.2512801-8-andrii@kernel.org
---
 tools/lib/bpf/libbpf.c | 195 +++++++++++++++++++++----------------------------
 1 file changed, 84 insertions(+), 111 deletions(-)

(limited to 'tools')

diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index f87ffd4d7eab..954c135a8adf 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -224,19 +224,35 @@ typedef int (*init_fn_t)(struct bpf_program *prog, long cookie);
 typedef int (*preload_fn_t)(struct bpf_program *prog, struct bpf_prog_load_params *attr, long cookie);
 typedef struct bpf_link *(*attach_fn_t)(const struct bpf_program *prog, long cookie);
 
+/* stored as sec_def->cookie for all libbpf-supported SEC()s */
+enum sec_def_flags {
+	SEC_NONE = 0,
+	/* expected_attach_type is optional, if kernel doesn't support that */
+	SEC_EXP_ATTACH_OPT = 1,
+	/* legacy, only used by libbpf_get_type_names() and
+	 * libbpf_attach_type_by_name(), not used by libbpf itself at all.
+	 * This used to be associated with cgroup (and few other) BPF programs
+	 * that were attachable through BPF_PROG_ATTACH command. Pretty
+	 * meaningless nowadays, though.
+	 */
+	SEC_ATTACHABLE = 2,
+	SEC_ATTACHABLE_OPT = SEC_ATTACHABLE | SEC_EXP_ATTACH_OPT,
+	/* attachment target is specified through BTF ID in either kernel or
+	 * other BPF program's BTF object */
+	SEC_ATTACH_BTF = 4,
+	/* BPF program type allows sleeping/blocking in kernel */
+	SEC_SLEEPABLE = 8,
+};
+
 struct bpf_sec_def {
 	const char *sec;
 	enum bpf_prog_type prog_type;
 	enum bpf_attach_type expected_attach_type;
-	bool is_exp_attach_type_optional;
-	bool is_attachable;
-	bool is_attach_btf;
-	bool is_sleepable;
+	long cookie;
 
 	init_fn_t init_fn;
 	preload_fn_t preload_fn;
 	attach_fn_t attach_fn;
-	long cookie;
 };
 
 /*
@@ -6100,26 +6116,30 @@ static int bpf_object__sanitize_prog(struct bpf_object *obj, struct bpf_program
 	return 0;
 }
 
-static int libbpf_find_attach_btf_id(struct bpf_program *prog, int *btf_obj_fd, int *btf_type_id);
+static int libbpf_find_attach_btf_id(struct bpf_program *prog, const char *attach_name,
+				     int *btf_obj_fd, int *btf_type_id);
 
 /* this is called as prog->sec_def->preload_fn for libbpf-supported sec_defs */
 static int libbpf_preload_prog(struct bpf_program *prog,
 			       struct bpf_prog_load_params *attr, long cookie)
 {
+	enum sec_def_flags def = cookie;
+
 	/* old kernels might not support specifying expected_attach_type */
-	if (prog->sec_def->is_exp_attach_type_optional &&
-	    !kernel_supports(prog->obj, FEAT_EXP_ATTACH_TYPE))
+	if ((def & SEC_EXP_ATTACH_OPT) && !kernel_supports(prog->obj, FEAT_EXP_ATTACH_TYPE))
 		attr->expected_attach_type = 0;
 
-	if (prog->sec_def->is_sleepable)
+	if (def & SEC_SLEEPABLE)
 		attr->prog_flags |= BPF_F_SLEEPABLE;
 
 	if ((prog->type == BPF_PROG_TYPE_TRACING ||
 	     prog->type == BPF_PROG_TYPE_LSM ||
 	     prog->type == BPF_PROG_TYPE_EXT) && !prog->attach_btf_id) {
 		int btf_obj_fd = 0, btf_type_id = 0, err;
+		const char *attach_name;
 
-		err = libbpf_find_attach_btf_id(prog, &btf_obj_fd, &btf_type_id);
+		attach_name = strchr(prog->sec_name, '/') + 1;
+		err = libbpf_find_attach_btf_id(prog, attach_name, &btf_obj_fd, &btf_type_id);
 		if (err)
 			return err;
 
@@ -7956,15 +7976,14 @@ void bpf_program__set_expected_attach_type(struct bpf_program *prog,
 		.sec = string,						    \
 		.prog_type = ptype,					    \
 		.expected_attach_type = eatype,				    \
-		.is_exp_attach_type_optional = eatype_optional,		    \
-		.is_attachable = attachable,				    \
-		.is_attach_btf = attach_btf,				    \
+		.cookie = (long) (					    \
+			(eatype_optional ? SEC_EXP_ATTACH_OPT : 0) |   \
+			(attachable ? SEC_ATTACHABLE : 0) |		    \
+			(attach_btf ? SEC_ATTACH_BTF : 0)		    \
+		),							    \
 		.preload_fn = libbpf_preload_prog,			    \
 	}
 
-/* Programs that can NOT be attached. */
-#define BPF_PROG_SEC(string, ptype) BPF_PROG_SEC_IMPL(string, ptype, 0, 0, 0, 0)
-
 /* Programs that can be attached. */
 #define BPF_APROG_SEC(string, ptype, atype) \
 	BPF_PROG_SEC_IMPL(string, ptype, atype, true, 1, 0)
@@ -7977,14 +7996,11 @@ void bpf_program__set_expected_attach_type(struct bpf_program *prog,
 #define BPF_PROG_BTF(string, ptype, eatype) \
 	BPF_PROG_SEC_IMPL(string, ptype, eatype, false, 0, 1)
 
-/* Programs that can be attached but attach type can't be identified by section
- * name. Kept for backward compatibility.
- */
-#define BPF_APROG_COMPAT(string, ptype) BPF_PROG_SEC(string, ptype)
-
-#define SEC_DEF(sec_pfx, ptype, ...) {					    \
+#define SEC_DEF(sec_pfx, ptype, atype, flags, ...) {			    \
 	.sec = sec_pfx,							    \
 	.prog_type = BPF_PROG_TYPE_##ptype,				    \
+	.expected_attach_type = atype,					    \
+	.cookie = (long)(flags),					    \
 	.preload_fn = libbpf_preload_prog,				    \
 	__VA_ARGS__							    \
 }
@@ -7997,93 +8013,50 @@ static struct bpf_link *attach_lsm(const struct bpf_program *prog, long cookie);
 static struct bpf_link *attach_iter(const struct bpf_program *prog, long cookie);
 
 static const struct bpf_sec_def section_defs[] = {
-	BPF_PROG_SEC("socket",			BPF_PROG_TYPE_SOCKET_FILTER),
+	SEC_DEF("socket",		SOCKET_FILTER, 0, SEC_NONE),
 	BPF_EAPROG_SEC("sk_reuseport/migrate",	BPF_PROG_TYPE_SK_REUSEPORT,
 						BPF_SK_REUSEPORT_SELECT_OR_MIGRATE),
 	BPF_EAPROG_SEC("sk_reuseport",		BPF_PROG_TYPE_SK_REUSEPORT,
 						BPF_SK_REUSEPORT_SELECT),
-	SEC_DEF("kprobe/", KPROBE,
-		.attach_fn = attach_kprobe),
-	BPF_PROG_SEC("uprobe/",			BPF_PROG_TYPE_KPROBE),
-	SEC_DEF("kretprobe/", KPROBE,
-		.attach_fn = attach_kprobe),
-	BPF_PROG_SEC("uretprobe/",		BPF_PROG_TYPE_KPROBE),
-	BPF_PROG_SEC("classifier",		BPF_PROG_TYPE_SCHED_CLS),
-	BPF_PROG_SEC("tc",			BPF_PROG_TYPE_SCHED_CLS),
-	BPF_PROG_SEC("action",			BPF_PROG_TYPE_SCHED_ACT),
-	SEC_DEF("tracepoint/", TRACEPOINT,
-		.attach_fn = attach_tp),
-	SEC_DEF("tp/", TRACEPOINT,
-		.attach_fn = attach_tp),
-	SEC_DEF("raw_tracepoint/", RAW_TRACEPOINT,
-		.attach_fn = attach_raw_tp),
-	SEC_DEF("raw_tp/", RAW_TRACEPOINT,
-		.attach_fn = attach_raw_tp),
-	SEC_DEF("tp_btf/", TRACING,
-		.expected_attach_type = BPF_TRACE_RAW_TP,
-		.is_attach_btf = true,
-		.attach_fn = attach_trace),
-	SEC_DEF("fentry/", TRACING,
-		.expected_attach_type = BPF_TRACE_FENTRY,
-		.is_attach_btf = true,
-		.attach_fn = attach_trace),
-	SEC_DEF("fmod_ret/", TRACING,
-		.expected_attach_type = BPF_MODIFY_RETURN,
-		.is_attach_btf = true,
-		.attach_fn = attach_trace),
-	SEC_DEF("fexit/", TRACING,
-		.expected_attach_type = BPF_TRACE_FEXIT,
-		.is_attach_btf = true,
-		.attach_fn = attach_trace),
-	SEC_DEF("fentry.s/", TRACING,
-		.expected_attach_type = BPF_TRACE_FENTRY,
-		.is_attach_btf = true,
-		.is_sleepable = true,
-		.attach_fn = attach_trace),
-	SEC_DEF("fmod_ret.s/", TRACING,
-		.expected_attach_type = BPF_MODIFY_RETURN,
-		.is_attach_btf = true,
-		.is_sleepable = true,
-		.attach_fn = attach_trace),
-	SEC_DEF("fexit.s/", TRACING,
-		.expected_attach_type = BPF_TRACE_FEXIT,
-		.is_attach_btf = true,
-		.is_sleepable = true,
-		.attach_fn = attach_trace),
-	SEC_DEF("freplace/", EXT,
-		.is_attach_btf = true,
-		.attach_fn = attach_trace),
-	SEC_DEF("lsm/", LSM,
-		.is_attach_btf = true,
-		.expected_attach_type = BPF_LSM_MAC,
-		.attach_fn = attach_lsm),
-	SEC_DEF("lsm.s/", LSM,
-		.is_attach_btf = true,
-		.is_sleepable = true,
-		.expected_attach_type = BPF_LSM_MAC,
-		.attach_fn = attach_lsm),
-	SEC_DEF("iter/", TRACING,
-		.expected_attach_type = BPF_TRACE_ITER,
-		.is_attach_btf = true,
-		.attach_fn = attach_iter),
-	SEC_DEF("syscall", SYSCALL,
-		.is_sleepable = true),
+	SEC_DEF("kprobe/",		KPROBE,	0, SEC_NONE, attach_kprobe),
+	SEC_DEF("uprobe/",		KPROBE,	0, SEC_NONE),
+	SEC_DEF("kretprobe/",		KPROBE, 0, SEC_NONE, attach_kprobe),
+	SEC_DEF("uretprobe/",		KPROBE, 0, SEC_NONE),
+	SEC_DEF("classifier",		SCHED_CLS, 0, SEC_NONE),
+	SEC_DEF("tc",			SCHED_CLS, 0, SEC_NONE),
+	SEC_DEF("action",		SCHED_ACT, 0, SEC_NONE),
+	SEC_DEF("tracepoint/",		TRACEPOINT, 0, SEC_NONE, attach_tp),
+	SEC_DEF("tp/",			TRACEPOINT, 0, SEC_NONE, attach_tp),
+	SEC_DEF("raw_tracepoint/",	RAW_TRACEPOINT, 0, SEC_NONE, attach_raw_tp),
+	SEC_DEF("raw_tp/",		RAW_TRACEPOINT, 0, SEC_NONE, attach_raw_tp),
+	SEC_DEF("tp_btf/",		TRACING, BPF_TRACE_RAW_TP, SEC_ATTACH_BTF, attach_trace),
+	SEC_DEF("fentry/",		TRACING, BPF_TRACE_FENTRY, SEC_ATTACH_BTF, attach_trace),
+	SEC_DEF("fmod_ret/",		TRACING, BPF_MODIFY_RETURN, SEC_ATTACH_BTF, attach_trace),
+	SEC_DEF("fexit/",		TRACING, BPF_TRACE_FEXIT, SEC_ATTACH_BTF, attach_trace),
+	SEC_DEF("fentry.s/",		TRACING, BPF_TRACE_FENTRY, SEC_ATTACH_BTF | SEC_SLEEPABLE, attach_trace),
+	SEC_DEF("fmod_ret.s/",		TRACING, BPF_MODIFY_RETURN, SEC_ATTACH_BTF | SEC_SLEEPABLE, attach_trace),
+	SEC_DEF("fexit.s/",		TRACING, BPF_TRACE_FEXIT, SEC_ATTACH_BTF | SEC_SLEEPABLE, attach_trace),
+	SEC_DEF("freplace/",		EXT, 0, SEC_ATTACH_BTF, attach_trace),
+	SEC_DEF("lsm/",			LSM, BPF_LSM_MAC, SEC_ATTACH_BTF, attach_lsm),
+	SEC_DEF("lsm.s/",		LSM, BPF_LSM_MAC, SEC_ATTACH_BTF | SEC_SLEEPABLE, attach_lsm),
+	SEC_DEF("iter/",		TRACING, BPF_TRACE_ITER, SEC_ATTACH_BTF, attach_iter),
+	SEC_DEF("syscall",		SYSCALL, 0, SEC_SLEEPABLE),
 	BPF_EAPROG_SEC("xdp_devmap/",		BPF_PROG_TYPE_XDP,
 						BPF_XDP_DEVMAP),
 	BPF_EAPROG_SEC("xdp_cpumap/",		BPF_PROG_TYPE_XDP,
 						BPF_XDP_CPUMAP),
 	BPF_APROG_SEC("xdp",			BPF_PROG_TYPE_XDP,
 						BPF_XDP),
-	BPF_PROG_SEC("perf_event",		BPF_PROG_TYPE_PERF_EVENT),
-	BPF_PROG_SEC("lwt_in",			BPF_PROG_TYPE_LWT_IN),
-	BPF_PROG_SEC("lwt_out",			BPF_PROG_TYPE_LWT_OUT),
-	BPF_PROG_SEC("lwt_xmit",		BPF_PROG_TYPE_LWT_XMIT),
-	BPF_PROG_SEC("lwt_seg6local",		BPF_PROG_TYPE_LWT_SEG6LOCAL),
+	SEC_DEF("perf_event",		PERF_EVENT, 0, SEC_NONE),
+	SEC_DEF("lwt_in",		LWT_IN, 0, SEC_NONE),
+	SEC_DEF("lwt_out",		LWT_OUT, 0, SEC_NONE),
+	SEC_DEF("lwt_xmit",		LWT_XMIT, 0, SEC_NONE),
+	SEC_DEF("lwt_seg6local",	LWT_SEG6LOCAL, 0, SEC_NONE),
 	BPF_APROG_SEC("cgroup_skb/ingress",	BPF_PROG_TYPE_CGROUP_SKB,
 						BPF_CGROUP_INET_INGRESS),
 	BPF_APROG_SEC("cgroup_skb/egress",	BPF_PROG_TYPE_CGROUP_SKB,
 						BPF_CGROUP_INET_EGRESS),
-	BPF_APROG_COMPAT("cgroup/skb",		BPF_PROG_TYPE_CGROUP_SKB),
+	SEC_DEF("cgroup/skb",		CGROUP_SKB, 0, SEC_NONE),
 	BPF_EAPROG_SEC("cgroup/sock_create",	BPF_PROG_TYPE_CGROUP_SOCK,
 						BPF_CGROUP_INET_SOCK_CREATE),
 	BPF_EAPROG_SEC("cgroup/sock_release",	BPF_PROG_TYPE_CGROUP_SOCK,
@@ -8102,7 +8075,7 @@ static const struct bpf_sec_def section_defs[] = {
 						BPF_SK_SKB_STREAM_PARSER),
 	BPF_APROG_SEC("sk_skb/stream_verdict",	BPF_PROG_TYPE_SK_SKB,
 						BPF_SK_SKB_STREAM_VERDICT),
-	BPF_APROG_COMPAT("sk_skb",		BPF_PROG_TYPE_SK_SKB),
+	SEC_DEF("sk_skb",		SK_SKB, 0, SEC_NONE),
 	BPF_APROG_SEC("sk_msg",			BPF_PROG_TYPE_SK_MSG,
 						BPF_SK_MSG_VERDICT),
 	BPF_APROG_SEC("lirc_mode2",		BPF_PROG_TYPE_LIRC_MODE2,
@@ -8139,16 +8112,14 @@ static const struct bpf_sec_def section_defs[] = {
 						BPF_CGROUP_GETSOCKOPT),
 	BPF_EAPROG_SEC("cgroup/setsockopt",	BPF_PROG_TYPE_CGROUP_SOCKOPT,
 						BPF_CGROUP_SETSOCKOPT),
-	BPF_PROG_SEC("struct_ops",		BPF_PROG_TYPE_STRUCT_OPS),
+	SEC_DEF("struct_ops",		STRUCT_OPS, 0, SEC_NONE),
 	BPF_EAPROG_SEC("sk_lookup/",		BPF_PROG_TYPE_SK_LOOKUP,
 						BPF_SK_LOOKUP),
 };
 
 #undef BPF_PROG_SEC_IMPL
-#undef BPF_PROG_SEC
 #undef BPF_APROG_SEC
 #undef BPF_EAPROG_SEC
-#undef BPF_APROG_COMPAT
 #undef SEC_DEF
 
 #define MAX_TYPE_NAME_SIZE 32
@@ -8176,8 +8147,15 @@ static char *libbpf_get_type_names(bool attach_type)
 	buf[0] = '\0';
 	/* Forge string buf with all available names */
 	for (i = 0; i < ARRAY_SIZE(section_defs); i++) {
-		if (attach_type && !section_defs[i].is_attachable)
-			continue;
+		const struct bpf_sec_def *sec_def = &section_defs[i];
+
+		if (attach_type) {
+			if (sec_def->preload_fn != libbpf_preload_prog)
+				continue;
+
+			if (!(sec_def->cookie & SEC_ATTACHABLE))
+				continue;
+		}
 
 		if (strlen(buf) + strlen(section_defs[i].sec) + 2 > len) {
 			free(buf);
@@ -8501,20 +8479,13 @@ static int find_kernel_btf_id(struct bpf_object *obj, const char *attach_name,
 	return -ESRCH;
 }
 
-static int libbpf_find_attach_btf_id(struct bpf_program *prog, int *btf_obj_fd, int *btf_type_id)
+static int libbpf_find_attach_btf_id(struct bpf_program *prog, const char *attach_name,
+				     int *btf_obj_fd, int *btf_type_id)
 {
 	enum bpf_attach_type attach_type = prog->expected_attach_type;
 	__u32 attach_prog_fd = prog->attach_prog_fd;
-	const char *attach_name;
 	int err = 0;
 
-	if (!prog->sec_def || !prog->sec_def->is_attach_btf) {
-		pr_warn("failed to identify BTF ID based on ELF section name '%s'\n",
-			prog->sec_name);
-		return -ESRCH;
-	}
-	attach_name = prog->sec_name + strlen(prog->sec_def->sec);
-
 	/* BPF program's BTF ID */
 	if (attach_prog_fd) {
 		err = libbpf_find_prog_btf_id(attach_name, attach_prog_fd);
@@ -8564,7 +8535,9 @@ int libbpf_attach_type_by_name(const char *name,
 		return libbpf_err(-EINVAL);
 	}
 
-	if (!sec_def->is_attachable)
+	if (sec_def->preload_fn != libbpf_preload_prog)
+		return libbpf_err(-EINVAL);
+	if (!(sec_def->cookie & SEC_ATTACHABLE))
 		return libbpf_err(-EINVAL);
 
 	*attach_type = sec_def->expected_attach_type;
-- 
cgit v1.2.3


From d41ea045a6e461673d1b2fad106b8cd04c3ba863 Mon Sep 17 00:00:00 2001
From: Andrii Nakryiko <andrii@kernel.org>
Date: Tue, 28 Sep 2021 09:19:44 -0700
Subject: libbpf: Complete SEC() table unification for
 BPF_APROG_SEC/BPF_EAPROG_SEC

Complete SEC() table refactoring towards unified form by rewriting
BPF_APROG_SEC and BPF_EAPROG_SEC definitions with
SEC_DEF(SEC_ATTACHABLE_OPT) (for optional expected_attach_type) and
SEC_DEF(SEC_ATTACHABLE) (mandatory expected_attach_type), respectively.
Drop BPF_APROG_SEC, BPF_EAPROG_SEC, and BPF_PROG_SEC_IMPL macros after
that, leaving SEC_DEF() macro as the only one used.

Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Dave Marchevsky <davemarchevsky@fb.com>
Link: https://lore.kernel.org/bpf/20210928161946.2512801-9-andrii@kernel.org
---
 tools/lib/bpf/libbpf.c | 136 +++++++++++++------------------------------------
 1 file changed, 35 insertions(+), 101 deletions(-)

(limited to 'tools')

diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 954c135a8adf..4ba67dff6b0d 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -7970,32 +7970,6 @@ void bpf_program__set_expected_attach_type(struct bpf_program *prog,
 	prog->expected_attach_type = type;
 }
 
-#define BPF_PROG_SEC_IMPL(string, ptype, eatype, eatype_optional,	    \
-			  attachable, attach_btf)			    \
-	{								    \
-		.sec = string,						    \
-		.prog_type = ptype,					    \
-		.expected_attach_type = eatype,				    \
-		.cookie = (long) (					    \
-			(eatype_optional ? SEC_EXP_ATTACH_OPT : 0) |   \
-			(attachable ? SEC_ATTACHABLE : 0) |		    \
-			(attach_btf ? SEC_ATTACH_BTF : 0)		    \
-		),							    \
-		.preload_fn = libbpf_preload_prog,			    \
-	}
-
-/* Programs that can be attached. */
-#define BPF_APROG_SEC(string, ptype, atype) \
-	BPF_PROG_SEC_IMPL(string, ptype, atype, true, 1, 0)
-
-/* Programs that must specify expected attach type at load time. */
-#define BPF_EAPROG_SEC(string, ptype, eatype) \
-	BPF_PROG_SEC_IMPL(string, ptype, eatype, false, 1, 0)
-
-/* Programs that use BTF to identify attach point */
-#define BPF_PROG_BTF(string, ptype, eatype) \
-	BPF_PROG_SEC_IMPL(string, ptype, eatype, false, 0, 1)
-
 #define SEC_DEF(sec_pfx, ptype, atype, flags, ...) {			    \
 	.sec = sec_pfx,							    \
 	.prog_type = BPF_PROG_TYPE_##ptype,				    \
@@ -8014,10 +7988,8 @@ static struct bpf_link *attach_iter(const struct bpf_program *prog, long cookie)
 
 static const struct bpf_sec_def section_defs[] = {
 	SEC_DEF("socket",		SOCKET_FILTER, 0, SEC_NONE),
-	BPF_EAPROG_SEC("sk_reuseport/migrate",	BPF_PROG_TYPE_SK_REUSEPORT,
-						BPF_SK_REUSEPORT_SELECT_OR_MIGRATE),
-	BPF_EAPROG_SEC("sk_reuseport",		BPF_PROG_TYPE_SK_REUSEPORT,
-						BPF_SK_REUSEPORT_SELECT),
+	SEC_DEF("sk_reuseport/migrate",	SK_REUSEPORT, BPF_SK_REUSEPORT_SELECT_OR_MIGRATE, SEC_ATTACHABLE),
+	SEC_DEF("sk_reuseport",		SK_REUSEPORT, BPF_SK_REUSEPORT_SELECT, SEC_ATTACHABLE),
 	SEC_DEF("kprobe/",		KPROBE,	0, SEC_NONE, attach_kprobe),
 	SEC_DEF("uprobe/",		KPROBE,	0, SEC_NONE),
 	SEC_DEF("kretprobe/",		KPROBE, 0, SEC_NONE, attach_kprobe),
@@ -8041,87 +8013,49 @@ static const struct bpf_sec_def section_defs[] = {
 	SEC_DEF("lsm.s/",		LSM, BPF_LSM_MAC, SEC_ATTACH_BTF | SEC_SLEEPABLE, attach_lsm),
 	SEC_DEF("iter/",		TRACING, BPF_TRACE_ITER, SEC_ATTACH_BTF, attach_iter),
 	SEC_DEF("syscall",		SYSCALL, 0, SEC_SLEEPABLE),
-	BPF_EAPROG_SEC("xdp_devmap/",		BPF_PROG_TYPE_XDP,
-						BPF_XDP_DEVMAP),
-	BPF_EAPROG_SEC("xdp_cpumap/",		BPF_PROG_TYPE_XDP,
-						BPF_XDP_CPUMAP),
-	BPF_APROG_SEC("xdp",			BPF_PROG_TYPE_XDP,
-						BPF_XDP),
+	SEC_DEF("xdp_devmap/",		XDP, BPF_XDP_DEVMAP, SEC_ATTACHABLE),
+	SEC_DEF("xdp_cpumap/",		XDP, BPF_XDP_CPUMAP, SEC_ATTACHABLE),
+	SEC_DEF("xdp",			XDP, BPF_XDP, SEC_ATTACHABLE_OPT),
 	SEC_DEF("perf_event",		PERF_EVENT, 0, SEC_NONE),
 	SEC_DEF("lwt_in",		LWT_IN, 0, SEC_NONE),
 	SEC_DEF("lwt_out",		LWT_OUT, 0, SEC_NONE),
 	SEC_DEF("lwt_xmit",		LWT_XMIT, 0, SEC_NONE),
 	SEC_DEF("lwt_seg6local",	LWT_SEG6LOCAL, 0, SEC_NONE),
-	BPF_APROG_SEC("cgroup_skb/ingress",	BPF_PROG_TYPE_CGROUP_SKB,
-						BPF_CGROUP_INET_INGRESS),
-	BPF_APROG_SEC("cgroup_skb/egress",	BPF_PROG_TYPE_CGROUP_SKB,
-						BPF_CGROUP_INET_EGRESS),
+	SEC_DEF("cgroup_skb/ingress",	CGROUP_SKB, BPF_CGROUP_INET_INGRESS, SEC_ATTACHABLE_OPT),
+	SEC_DEF("cgroup_skb/egress",	CGROUP_SKB, BPF_CGROUP_INET_EGRESS, SEC_ATTACHABLE_OPT),
 	SEC_DEF("cgroup/skb",		CGROUP_SKB, 0, SEC_NONE),
-	BPF_EAPROG_SEC("cgroup/sock_create",	BPF_PROG_TYPE_CGROUP_SOCK,
-						BPF_CGROUP_INET_SOCK_CREATE),
-	BPF_EAPROG_SEC("cgroup/sock_release",	BPF_PROG_TYPE_CGROUP_SOCK,
-						BPF_CGROUP_INET_SOCK_RELEASE),
-	BPF_APROG_SEC("cgroup/sock",		BPF_PROG_TYPE_CGROUP_SOCK,
-						BPF_CGROUP_INET_SOCK_CREATE),
-	BPF_EAPROG_SEC("cgroup/post_bind4",	BPF_PROG_TYPE_CGROUP_SOCK,
-						BPF_CGROUP_INET4_POST_BIND),
-	BPF_EAPROG_SEC("cgroup/post_bind6",	BPF_PROG_TYPE_CGROUP_SOCK,
-						BPF_CGROUP_INET6_POST_BIND),
-	BPF_APROG_SEC("cgroup/dev",		BPF_PROG_TYPE_CGROUP_DEVICE,
-						BPF_CGROUP_DEVICE),
-	BPF_APROG_SEC("sockops",		BPF_PROG_TYPE_SOCK_OPS,
-						BPF_CGROUP_SOCK_OPS),
-	BPF_APROG_SEC("sk_skb/stream_parser",	BPF_PROG_TYPE_SK_SKB,
-						BPF_SK_SKB_STREAM_PARSER),
-	BPF_APROG_SEC("sk_skb/stream_verdict",	BPF_PROG_TYPE_SK_SKB,
-						BPF_SK_SKB_STREAM_VERDICT),
+	SEC_DEF("cgroup/sock_create",	CGROUP_SOCK, BPF_CGROUP_INET_SOCK_CREATE, SEC_ATTACHABLE),
+	SEC_DEF("cgroup/sock_release",	CGROUP_SOCK, BPF_CGROUP_INET_SOCK_RELEASE, SEC_ATTACHABLE),
+	SEC_DEF("cgroup/sock",		CGROUP_SOCK, BPF_CGROUP_INET_SOCK_CREATE, SEC_ATTACHABLE_OPT),
+	SEC_DEF("cgroup/post_bind4",	CGROUP_SOCK, BPF_CGROUP_INET4_POST_BIND, SEC_ATTACHABLE),
+	SEC_DEF("cgroup/post_bind6",	CGROUP_SOCK, BPF_CGROUP_INET6_POST_BIND, SEC_ATTACHABLE),
+	SEC_DEF("cgroup/dev",		CGROUP_DEVICE, BPF_CGROUP_DEVICE, SEC_ATTACHABLE_OPT),
+	SEC_DEF("sockops",		SOCK_OPS, BPF_CGROUP_SOCK_OPS, SEC_ATTACHABLE_OPT),
+	SEC_DEF("sk_skb/stream_parser",	SK_SKB, BPF_SK_SKB_STREAM_PARSER, SEC_ATTACHABLE_OPT),
+	SEC_DEF("sk_skb/stream_verdict",SK_SKB, BPF_SK_SKB_STREAM_VERDICT, SEC_ATTACHABLE_OPT),
 	SEC_DEF("sk_skb",		SK_SKB, 0, SEC_NONE),
-	BPF_APROG_SEC("sk_msg",			BPF_PROG_TYPE_SK_MSG,
-						BPF_SK_MSG_VERDICT),
-	BPF_APROG_SEC("lirc_mode2",		BPF_PROG_TYPE_LIRC_MODE2,
-						BPF_LIRC_MODE2),
-	BPF_APROG_SEC("flow_dissector",		BPF_PROG_TYPE_FLOW_DISSECTOR,
-						BPF_FLOW_DISSECTOR),
-	BPF_EAPROG_SEC("cgroup/bind4",		BPF_PROG_TYPE_CGROUP_SOCK_ADDR,
-						BPF_CGROUP_INET4_BIND),
-	BPF_EAPROG_SEC("cgroup/bind6",		BPF_PROG_TYPE_CGROUP_SOCK_ADDR,
-						BPF_CGROUP_INET6_BIND),
-	BPF_EAPROG_SEC("cgroup/connect4",	BPF_PROG_TYPE_CGROUP_SOCK_ADDR,
-						BPF_CGROUP_INET4_CONNECT),
-	BPF_EAPROG_SEC("cgroup/connect6",	BPF_PROG_TYPE_CGROUP_SOCK_ADDR,
-						BPF_CGROUP_INET6_CONNECT),
-	BPF_EAPROG_SEC("cgroup/sendmsg4",	BPF_PROG_TYPE_CGROUP_SOCK_ADDR,
-						BPF_CGROUP_UDP4_SENDMSG),
-	BPF_EAPROG_SEC("cgroup/sendmsg6",	BPF_PROG_TYPE_CGROUP_SOCK_ADDR,
-						BPF_CGROUP_UDP6_SENDMSG),
-	BPF_EAPROG_SEC("cgroup/recvmsg4",	BPF_PROG_TYPE_CGROUP_SOCK_ADDR,
-						BPF_CGROUP_UDP4_RECVMSG),
-	BPF_EAPROG_SEC("cgroup/recvmsg6",	BPF_PROG_TYPE_CGROUP_SOCK_ADDR,
-						BPF_CGROUP_UDP6_RECVMSG),
-	BPF_EAPROG_SEC("cgroup/getpeername4",	BPF_PROG_TYPE_CGROUP_SOCK_ADDR,
-						BPF_CGROUP_INET4_GETPEERNAME),
-	BPF_EAPROG_SEC("cgroup/getpeername6",	BPF_PROG_TYPE_CGROUP_SOCK_ADDR,
-						BPF_CGROUP_INET6_GETPEERNAME),
-	BPF_EAPROG_SEC("cgroup/getsockname4",	BPF_PROG_TYPE_CGROUP_SOCK_ADDR,
-						BPF_CGROUP_INET4_GETSOCKNAME),
-	BPF_EAPROG_SEC("cgroup/getsockname6",	BPF_PROG_TYPE_CGROUP_SOCK_ADDR,
-						BPF_CGROUP_INET6_GETSOCKNAME),
-	BPF_EAPROG_SEC("cgroup/sysctl",		BPF_PROG_TYPE_CGROUP_SYSCTL,
-						BPF_CGROUP_SYSCTL),
-	BPF_EAPROG_SEC("cgroup/getsockopt",	BPF_PROG_TYPE_CGROUP_SOCKOPT,
-						BPF_CGROUP_GETSOCKOPT),
-	BPF_EAPROG_SEC("cgroup/setsockopt",	BPF_PROG_TYPE_CGROUP_SOCKOPT,
-						BPF_CGROUP_SETSOCKOPT),
+	SEC_DEF("sk_msg",		SK_MSG, BPF_SK_MSG_VERDICT, SEC_ATTACHABLE_OPT),
+	SEC_DEF("lirc_mode2",		LIRC_MODE2, BPF_LIRC_MODE2, SEC_ATTACHABLE_OPT),
+	SEC_DEF("flow_dissector",	FLOW_DISSECTOR, BPF_FLOW_DISSECTOR, SEC_ATTACHABLE_OPT),
+	SEC_DEF("cgroup/bind4",		CGROUP_SOCK_ADDR, BPF_CGROUP_INET4_BIND, SEC_ATTACHABLE),
+	SEC_DEF("cgroup/bind6",		CGROUP_SOCK_ADDR, BPF_CGROUP_INET6_BIND, SEC_ATTACHABLE),
+	SEC_DEF("cgroup/connect4",	CGROUP_SOCK_ADDR, BPF_CGROUP_INET4_CONNECT, SEC_ATTACHABLE),
+	SEC_DEF("cgroup/connect6",	CGROUP_SOCK_ADDR, BPF_CGROUP_INET6_CONNECT, SEC_ATTACHABLE),
+	SEC_DEF("cgroup/sendmsg4",	CGROUP_SOCK_ADDR, BPF_CGROUP_UDP4_SENDMSG, SEC_ATTACHABLE),
+	SEC_DEF("cgroup/sendmsg6",	CGROUP_SOCK_ADDR, BPF_CGROUP_UDP6_SENDMSG, SEC_ATTACHABLE),
+	SEC_DEF("cgroup/recvmsg4",	CGROUP_SOCK_ADDR, BPF_CGROUP_UDP4_RECVMSG, SEC_ATTACHABLE),
+	SEC_DEF("cgroup/recvmsg6",	CGROUP_SOCK_ADDR, BPF_CGROUP_UDP6_RECVMSG, SEC_ATTACHABLE),
+	SEC_DEF("cgroup/getpeername4",	CGROUP_SOCK_ADDR, BPF_CGROUP_INET4_GETPEERNAME, SEC_ATTACHABLE),
+	SEC_DEF("cgroup/getpeername6",	CGROUP_SOCK_ADDR, BPF_CGROUP_INET6_GETPEERNAME, SEC_ATTACHABLE),
+	SEC_DEF("cgroup/getsockname4",	CGROUP_SOCK_ADDR, BPF_CGROUP_INET4_GETSOCKNAME, SEC_ATTACHABLE),
+	SEC_DEF("cgroup/getsockname6",	CGROUP_SOCK_ADDR, BPF_CGROUP_INET6_GETSOCKNAME, SEC_ATTACHABLE),
+	SEC_DEF("cgroup/sysctl",	CGROUP_SYSCTL, BPF_CGROUP_SYSCTL, SEC_ATTACHABLE),
+	SEC_DEF("cgroup/getsockopt",	CGROUP_SOCKOPT, BPF_CGROUP_GETSOCKOPT, SEC_ATTACHABLE),
+	SEC_DEF("cgroup/setsockopt",	CGROUP_SOCKOPT, BPF_CGROUP_SETSOCKOPT, SEC_ATTACHABLE),
 	SEC_DEF("struct_ops",		STRUCT_OPS, 0, SEC_NONE),
-	BPF_EAPROG_SEC("sk_lookup/",		BPF_PROG_TYPE_SK_LOOKUP,
-						BPF_SK_LOOKUP),
+	SEC_DEF("sk_lookup/",		SK_LOOKUP, BPF_SK_LOOKUP, SEC_ATTACHABLE),
 };
 
-#undef BPF_PROG_SEC_IMPL
-#undef BPF_APROG_SEC
-#undef BPF_EAPROG_SEC
-#undef SEC_DEF
-
 #define MAX_TYPE_NAME_SIZE 32
 
 static const struct bpf_sec_def *find_sec_def(const char *sec_name)
-- 
cgit v1.2.3


From dd94d45cf0acb1d82748b17e1106b2c8b487b28b Mon Sep 17 00:00:00 2001
From: Andrii Nakryiko <andrii@kernel.org>
Date: Tue, 28 Sep 2021 09:19:45 -0700
Subject: libbpf: Add opt-in strict BPF program section name handling logic

Implement strict ELF section name handling for BPF programs. It utilizes
`libbpf_set_strict_mode()` framework and adds new flag: LIBBPF_STRICT_SEC_NAME.

If this flag is set, libbpf will enforce exact section name matching for
a lot of program types that previously allowed just partial prefix
match. E.g., if previously SEC("xdp_whatever_i_want") was allowed, now
in strict mode only SEC("xdp") will be accepted, which makes SEC("")
definitions cleaner and more structured. SEC() now won't be used as yet
another way to uniquely encode BPF program identifier (for that
C function name is better and is guaranteed to be unique within
bpf_object). Now SEC() is strictly BPF program type and, depending on
program type, extra load/attach parameter specification.

Libbpf completely supports multiple BPF programs in the same ELF
section, so multiple BPF programs of the same type/specification easily
co-exist together within the same bpf_object scope.

Additionally, a new (for now internal) convention is introduced: section
name that can be a stand-alone exact BPF program type specificator, but
also could have extra parameters after '/' delimiter. An example of such
section is "struct_ops", which can be specified by itself, but also
allows to specify the intended operation to be attached to, e.g.,
"struct_ops/dctcp_init". Note, that "struct_ops_some_op" is not allowed.
Such section definition is specified as "struct_ops+".

This change is part of libbpf 1.0 effort ([0], [1]).

  [0] Closes: https://github.com/libbpf/libbpf/issues/271
  [1] https://github.com/libbpf/libbpf/wiki/Libbpf:-the-road-to-v1.0#stricter-and-more-uniform-bpf-program-section-name-sec-handling

Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Dave Marchevsky <davemarchevsky@fb.com>
Link: https://lore.kernel.org/bpf/20210928161946.2512801-10-andrii@kernel.org
---
 tools/lib/bpf/libbpf.c        | 136 ++++++++++++++++++++++++++++--------------
 tools/lib/bpf/libbpf_legacy.h |   9 +++
 2 files changed, 99 insertions(+), 46 deletions(-)

(limited to 'tools')

diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 4ba67dff6b0d..3e1f6211b9b9 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -242,6 +242,8 @@ enum sec_def_flags {
 	SEC_ATTACH_BTF = 4,
 	/* BPF program type allows sleeping/blocking in kernel */
 	SEC_SLEEPABLE = 8,
+	/* allow non-strict prefix matching */
+	SEC_SLOPPY_PFX = 16,
 };
 
 struct bpf_sec_def {
@@ -7987,16 +7989,16 @@ static struct bpf_link *attach_lsm(const struct bpf_program *prog, long cookie);
 static struct bpf_link *attach_iter(const struct bpf_program *prog, long cookie);
 
 static const struct bpf_sec_def section_defs[] = {
-	SEC_DEF("socket",		SOCKET_FILTER, 0, SEC_NONE),
-	SEC_DEF("sk_reuseport/migrate",	SK_REUSEPORT, BPF_SK_REUSEPORT_SELECT_OR_MIGRATE, SEC_ATTACHABLE),
-	SEC_DEF("sk_reuseport",		SK_REUSEPORT, BPF_SK_REUSEPORT_SELECT, SEC_ATTACHABLE),
+	SEC_DEF("socket",		SOCKET_FILTER, 0, SEC_NONE | SEC_SLOPPY_PFX),
+	SEC_DEF("sk_reuseport/migrate",	SK_REUSEPORT, BPF_SK_REUSEPORT_SELECT_OR_MIGRATE, SEC_ATTACHABLE | SEC_SLOPPY_PFX),
+	SEC_DEF("sk_reuseport",		SK_REUSEPORT, BPF_SK_REUSEPORT_SELECT, SEC_ATTACHABLE | SEC_SLOPPY_PFX),
 	SEC_DEF("kprobe/",		KPROBE,	0, SEC_NONE, attach_kprobe),
 	SEC_DEF("uprobe/",		KPROBE,	0, SEC_NONE),
 	SEC_DEF("kretprobe/",		KPROBE, 0, SEC_NONE, attach_kprobe),
 	SEC_DEF("uretprobe/",		KPROBE, 0, SEC_NONE),
-	SEC_DEF("classifier",		SCHED_CLS, 0, SEC_NONE),
 	SEC_DEF("tc",			SCHED_CLS, 0, SEC_NONE),
-	SEC_DEF("action",		SCHED_ACT, 0, SEC_NONE),
+	SEC_DEF("classifier",		SCHED_CLS, 0, SEC_NONE | SEC_SLOPPY_PFX),
+	SEC_DEF("action",		SCHED_ACT, 0, SEC_NONE | SEC_SLOPPY_PFX),
 	SEC_DEF("tracepoint/",		TRACEPOINT, 0, SEC_NONE, attach_tp),
 	SEC_DEF("tp/",			TRACEPOINT, 0, SEC_NONE, attach_tp),
 	SEC_DEF("raw_tracepoint/",	RAW_TRACEPOINT, 0, SEC_NONE, attach_raw_tp),
@@ -8015,44 +8017,44 @@ static const struct bpf_sec_def section_defs[] = {
 	SEC_DEF("syscall",		SYSCALL, 0, SEC_SLEEPABLE),
 	SEC_DEF("xdp_devmap/",		XDP, BPF_XDP_DEVMAP, SEC_ATTACHABLE),
 	SEC_DEF("xdp_cpumap/",		XDP, BPF_XDP_CPUMAP, SEC_ATTACHABLE),
-	SEC_DEF("xdp",			XDP, BPF_XDP, SEC_ATTACHABLE_OPT),
-	SEC_DEF("perf_event",		PERF_EVENT, 0, SEC_NONE),
-	SEC_DEF("lwt_in",		LWT_IN, 0, SEC_NONE),
-	SEC_DEF("lwt_out",		LWT_OUT, 0, SEC_NONE),
-	SEC_DEF("lwt_xmit",		LWT_XMIT, 0, SEC_NONE),
-	SEC_DEF("lwt_seg6local",	LWT_SEG6LOCAL, 0, SEC_NONE),
-	SEC_DEF("cgroup_skb/ingress",	CGROUP_SKB, BPF_CGROUP_INET_INGRESS, SEC_ATTACHABLE_OPT),
-	SEC_DEF("cgroup_skb/egress",	CGROUP_SKB, BPF_CGROUP_INET_EGRESS, SEC_ATTACHABLE_OPT),
-	SEC_DEF("cgroup/skb",		CGROUP_SKB, 0, SEC_NONE),
-	SEC_DEF("cgroup/sock_create",	CGROUP_SOCK, BPF_CGROUP_INET_SOCK_CREATE, SEC_ATTACHABLE),
-	SEC_DEF("cgroup/sock_release",	CGROUP_SOCK, BPF_CGROUP_INET_SOCK_RELEASE, SEC_ATTACHABLE),
-	SEC_DEF("cgroup/sock",		CGROUP_SOCK, BPF_CGROUP_INET_SOCK_CREATE, SEC_ATTACHABLE_OPT),
-	SEC_DEF("cgroup/post_bind4",	CGROUP_SOCK, BPF_CGROUP_INET4_POST_BIND, SEC_ATTACHABLE),
-	SEC_DEF("cgroup/post_bind6",	CGROUP_SOCK, BPF_CGROUP_INET6_POST_BIND, SEC_ATTACHABLE),
-	SEC_DEF("cgroup/dev",		CGROUP_DEVICE, BPF_CGROUP_DEVICE, SEC_ATTACHABLE_OPT),
-	SEC_DEF("sockops",		SOCK_OPS, BPF_CGROUP_SOCK_OPS, SEC_ATTACHABLE_OPT),
-	SEC_DEF("sk_skb/stream_parser",	SK_SKB, BPF_SK_SKB_STREAM_PARSER, SEC_ATTACHABLE_OPT),
-	SEC_DEF("sk_skb/stream_verdict",SK_SKB, BPF_SK_SKB_STREAM_VERDICT, SEC_ATTACHABLE_OPT),
-	SEC_DEF("sk_skb",		SK_SKB, 0, SEC_NONE),
-	SEC_DEF("sk_msg",		SK_MSG, BPF_SK_MSG_VERDICT, SEC_ATTACHABLE_OPT),
-	SEC_DEF("lirc_mode2",		LIRC_MODE2, BPF_LIRC_MODE2, SEC_ATTACHABLE_OPT),
-	SEC_DEF("flow_dissector",	FLOW_DISSECTOR, BPF_FLOW_DISSECTOR, SEC_ATTACHABLE_OPT),
-	SEC_DEF("cgroup/bind4",		CGROUP_SOCK_ADDR, BPF_CGROUP_INET4_BIND, SEC_ATTACHABLE),
-	SEC_DEF("cgroup/bind6",		CGROUP_SOCK_ADDR, BPF_CGROUP_INET6_BIND, SEC_ATTACHABLE),
-	SEC_DEF("cgroup/connect4",	CGROUP_SOCK_ADDR, BPF_CGROUP_INET4_CONNECT, SEC_ATTACHABLE),
-	SEC_DEF("cgroup/connect6",	CGROUP_SOCK_ADDR, BPF_CGROUP_INET6_CONNECT, SEC_ATTACHABLE),
-	SEC_DEF("cgroup/sendmsg4",	CGROUP_SOCK_ADDR, BPF_CGROUP_UDP4_SENDMSG, SEC_ATTACHABLE),
-	SEC_DEF("cgroup/sendmsg6",	CGROUP_SOCK_ADDR, BPF_CGROUP_UDP6_SENDMSG, SEC_ATTACHABLE),
-	SEC_DEF("cgroup/recvmsg4",	CGROUP_SOCK_ADDR, BPF_CGROUP_UDP4_RECVMSG, SEC_ATTACHABLE),
-	SEC_DEF("cgroup/recvmsg6",	CGROUP_SOCK_ADDR, BPF_CGROUP_UDP6_RECVMSG, SEC_ATTACHABLE),
-	SEC_DEF("cgroup/getpeername4",	CGROUP_SOCK_ADDR, BPF_CGROUP_INET4_GETPEERNAME, SEC_ATTACHABLE),
-	SEC_DEF("cgroup/getpeername6",	CGROUP_SOCK_ADDR, BPF_CGROUP_INET6_GETPEERNAME, SEC_ATTACHABLE),
-	SEC_DEF("cgroup/getsockname4",	CGROUP_SOCK_ADDR, BPF_CGROUP_INET4_GETSOCKNAME, SEC_ATTACHABLE),
-	SEC_DEF("cgroup/getsockname6",	CGROUP_SOCK_ADDR, BPF_CGROUP_INET6_GETSOCKNAME, SEC_ATTACHABLE),
-	SEC_DEF("cgroup/sysctl",	CGROUP_SYSCTL, BPF_CGROUP_SYSCTL, SEC_ATTACHABLE),
-	SEC_DEF("cgroup/getsockopt",	CGROUP_SOCKOPT, BPF_CGROUP_GETSOCKOPT, SEC_ATTACHABLE),
-	SEC_DEF("cgroup/setsockopt",	CGROUP_SOCKOPT, BPF_CGROUP_SETSOCKOPT, SEC_ATTACHABLE),
-	SEC_DEF("struct_ops",		STRUCT_OPS, 0, SEC_NONE),
+	SEC_DEF("xdp",			XDP, BPF_XDP, SEC_ATTACHABLE_OPT | SEC_SLOPPY_PFX),
+	SEC_DEF("perf_event",		PERF_EVENT, 0, SEC_NONE | SEC_SLOPPY_PFX),
+	SEC_DEF("lwt_in",		LWT_IN, 0, SEC_NONE | SEC_SLOPPY_PFX),
+	SEC_DEF("lwt_out",		LWT_OUT, 0, SEC_NONE | SEC_SLOPPY_PFX),
+	SEC_DEF("lwt_xmit",		LWT_XMIT, 0, SEC_NONE | SEC_SLOPPY_PFX),
+	SEC_DEF("lwt_seg6local",	LWT_SEG6LOCAL, 0, SEC_NONE | SEC_SLOPPY_PFX),
+	SEC_DEF("cgroup_skb/ingress",	CGROUP_SKB, BPF_CGROUP_INET_INGRESS, SEC_ATTACHABLE_OPT | SEC_SLOPPY_PFX),
+	SEC_DEF("cgroup_skb/egress",	CGROUP_SKB, BPF_CGROUP_INET_EGRESS, SEC_ATTACHABLE_OPT | SEC_SLOPPY_PFX),
+	SEC_DEF("cgroup/skb",		CGROUP_SKB, 0, SEC_NONE | SEC_SLOPPY_PFX),
+	SEC_DEF("cgroup/sock_create",	CGROUP_SOCK, BPF_CGROUP_INET_SOCK_CREATE, SEC_ATTACHABLE | SEC_SLOPPY_PFX),
+	SEC_DEF("cgroup/sock_release",	CGROUP_SOCK, BPF_CGROUP_INET_SOCK_RELEASE, SEC_ATTACHABLE | SEC_SLOPPY_PFX),
+	SEC_DEF("cgroup/sock",		CGROUP_SOCK, BPF_CGROUP_INET_SOCK_CREATE, SEC_ATTACHABLE_OPT | SEC_SLOPPY_PFX),
+	SEC_DEF("cgroup/post_bind4",	CGROUP_SOCK, BPF_CGROUP_INET4_POST_BIND, SEC_ATTACHABLE | SEC_SLOPPY_PFX),
+	SEC_DEF("cgroup/post_bind6",	CGROUP_SOCK, BPF_CGROUP_INET6_POST_BIND, SEC_ATTACHABLE | SEC_SLOPPY_PFX),
+	SEC_DEF("cgroup/dev",		CGROUP_DEVICE, BPF_CGROUP_DEVICE, SEC_ATTACHABLE_OPT | SEC_SLOPPY_PFX),
+	SEC_DEF("sockops",		SOCK_OPS, BPF_CGROUP_SOCK_OPS, SEC_ATTACHABLE_OPT | SEC_SLOPPY_PFX),
+	SEC_DEF("sk_skb/stream_parser",	SK_SKB, BPF_SK_SKB_STREAM_PARSER, SEC_ATTACHABLE_OPT | SEC_SLOPPY_PFX),
+	SEC_DEF("sk_skb/stream_verdict",SK_SKB, BPF_SK_SKB_STREAM_VERDICT, SEC_ATTACHABLE_OPT | SEC_SLOPPY_PFX),
+	SEC_DEF("sk_skb",		SK_SKB, 0, SEC_NONE | SEC_SLOPPY_PFX),
+	SEC_DEF("sk_msg",		SK_MSG, BPF_SK_MSG_VERDICT, SEC_ATTACHABLE_OPT | SEC_SLOPPY_PFX),
+	SEC_DEF("lirc_mode2",		LIRC_MODE2, BPF_LIRC_MODE2, SEC_ATTACHABLE_OPT | SEC_SLOPPY_PFX),
+	SEC_DEF("flow_dissector",	FLOW_DISSECTOR, BPF_FLOW_DISSECTOR, SEC_ATTACHABLE_OPT | SEC_SLOPPY_PFX),
+	SEC_DEF("cgroup/bind4",		CGROUP_SOCK_ADDR, BPF_CGROUP_INET4_BIND, SEC_ATTACHABLE | SEC_SLOPPY_PFX),
+	SEC_DEF("cgroup/bind6",		CGROUP_SOCK_ADDR, BPF_CGROUP_INET6_BIND, SEC_ATTACHABLE | SEC_SLOPPY_PFX),
+	SEC_DEF("cgroup/connect4",	CGROUP_SOCK_ADDR, BPF_CGROUP_INET4_CONNECT, SEC_ATTACHABLE | SEC_SLOPPY_PFX),
+	SEC_DEF("cgroup/connect6",	CGROUP_SOCK_ADDR, BPF_CGROUP_INET6_CONNECT, SEC_ATTACHABLE | SEC_SLOPPY_PFX),
+	SEC_DEF("cgroup/sendmsg4",	CGROUP_SOCK_ADDR, BPF_CGROUP_UDP4_SENDMSG, SEC_ATTACHABLE | SEC_SLOPPY_PFX),
+	SEC_DEF("cgroup/sendmsg6",	CGROUP_SOCK_ADDR, BPF_CGROUP_UDP6_SENDMSG, SEC_ATTACHABLE | SEC_SLOPPY_PFX),
+	SEC_DEF("cgroup/recvmsg4",	CGROUP_SOCK_ADDR, BPF_CGROUP_UDP4_RECVMSG, SEC_ATTACHABLE | SEC_SLOPPY_PFX),
+	SEC_DEF("cgroup/recvmsg6",	CGROUP_SOCK_ADDR, BPF_CGROUP_UDP6_RECVMSG, SEC_ATTACHABLE | SEC_SLOPPY_PFX),
+	SEC_DEF("cgroup/getpeername4",	CGROUP_SOCK_ADDR, BPF_CGROUP_INET4_GETPEERNAME, SEC_ATTACHABLE | SEC_SLOPPY_PFX),
+	SEC_DEF("cgroup/getpeername6",	CGROUP_SOCK_ADDR, BPF_CGROUP_INET6_GETPEERNAME, SEC_ATTACHABLE | SEC_SLOPPY_PFX),
+	SEC_DEF("cgroup/getsockname4",	CGROUP_SOCK_ADDR, BPF_CGROUP_INET4_GETSOCKNAME, SEC_ATTACHABLE | SEC_SLOPPY_PFX),
+	SEC_DEF("cgroup/getsockname6",	CGROUP_SOCK_ADDR, BPF_CGROUP_INET6_GETSOCKNAME, SEC_ATTACHABLE | SEC_SLOPPY_PFX),
+	SEC_DEF("cgroup/sysctl",	CGROUP_SYSCTL, BPF_CGROUP_SYSCTL, SEC_ATTACHABLE | SEC_SLOPPY_PFX),
+	SEC_DEF("cgroup/getsockopt",	CGROUP_SOCKOPT, BPF_CGROUP_GETSOCKOPT, SEC_ATTACHABLE | SEC_SLOPPY_PFX),
+	SEC_DEF("cgroup/setsockopt",	CGROUP_SOCKOPT, BPF_CGROUP_SETSOCKOPT, SEC_ATTACHABLE | SEC_SLOPPY_PFX),
+	SEC_DEF("struct_ops+",		STRUCT_OPS, 0, SEC_NONE),
 	SEC_DEF("sk_lookup/",		SK_LOOKUP, BPF_SK_LOOKUP, SEC_ATTACHABLE),
 };
 
@@ -8060,11 +8062,53 @@ static const struct bpf_sec_def section_defs[] = {
 
 static const struct bpf_sec_def *find_sec_def(const char *sec_name)
 {
-	int i, n = ARRAY_SIZE(section_defs);
+	const struct bpf_sec_def *sec_def;
+	enum sec_def_flags sec_flags;
+	int i, n = ARRAY_SIZE(section_defs), len;
+	bool strict = libbpf_mode & LIBBPF_STRICT_SEC_NAME;
 
 	for (i = 0; i < n; i++) {
-		if (str_has_pfx(sec_name, section_defs[i].sec))
-			return &section_defs[i];
+		sec_def = &section_defs[i];
+		sec_flags = sec_def->cookie;
+		len = strlen(sec_def->sec);
+
+		/* "type/" always has to have proper SEC("type/extras") form */
+		if (sec_def->sec[len - 1] == '/') {
+			if (str_has_pfx(sec_name, sec_def->sec))
+				return sec_def;
+			continue;
+		}
+
+		/* "type+" means it can be either exact SEC("type") or
+		 * well-formed SEC("type/extras") with proper '/' separator
+		 */
+		if (sec_def->sec[len - 1] == '+') {
+			len--;
+			/* not even a prefix */
+			if (strncmp(sec_name, sec_def->sec, len) != 0)
+				continue;
+			/* exact match or has '/' separator */
+			if (sec_name[len] == '\0' || sec_name[len] == '/')
+				return sec_def;
+			continue;
+		}
+
+		/* SEC_SLOPPY_PFX definitions are allowed to be just prefix
+		 * matches, unless strict section name mode
+		 * (LIBBPF_STRICT_SEC_NAME) is enabled, in which case the
+		 * match has to be exact.
+		 */
+		if ((sec_flags & SEC_SLOPPY_PFX) && !strict)  {
+			if (str_has_pfx(sec_name, sec_def->sec))
+				return sec_def;
+			continue;
+		}
+
+		/* Definitions not marked SEC_SLOPPY_PFX (e.g.,
+		 * SEC("syscall")) are exact matches in both modes.
+		 */
+		if (strcmp(sec_name, sec_def->sec) == 0)
+			return sec_def;
 	}
 	return NULL;
 }
diff --git a/tools/lib/bpf/libbpf_legacy.h b/tools/lib/bpf/libbpf_legacy.h
index df0d03dcffab..74e6f860f703 100644
--- a/tools/lib/bpf/libbpf_legacy.h
+++ b/tools/lib/bpf/libbpf_legacy.h
@@ -46,6 +46,15 @@ enum libbpf_strict_mode {
 	 */
 	LIBBPF_STRICT_DIRECT_ERRS = 0x02,
 
+	/*
+	 * Enforce strict BPF program section (SEC()) names.
+	 * E.g., while prefiously SEC("xdp_whatever") or SEC("perf_event_blah") were
+	 * allowed, with LIBBPF_STRICT_SEC_PREFIX this will become
+	 * unrecognized by libbpf and would have to be just SEC("xdp") and
+	 * SEC("xdp") and SEC("perf_event").
+	 */
+	LIBBPF_STRICT_SEC_NAME = 0x04,
+
 	__LIBBPF_STRICT_LAST,
 };
 
-- 
cgit v1.2.3


From 7c80c87ad56a05ec56069c3f5d7e60b5b1eb19b4 Mon Sep 17 00:00:00 2001
From: Andrii Nakryiko <andrii@kernel.org>
Date: Tue, 28 Sep 2021 09:19:46 -0700
Subject: selftests/bpf: Switch sk_lookup selftests to strict SEC("sk_lookup")
 use

Update "sk_lookup/" definition to be a stand-alone type specifier,
with backwards-compatible prefix match logic in non-libbpf-1.0 mode.

Currently in selftests all the "sk_lookup/<whatever>" uses just use
<whatever> for duplicated unique name encoding, which is redundant as
BPF program's name (C function name) uniquely and descriptively
identifies the intended use for such BPF programs.

With libbpf's SEC_DEF("sk_lookup") definition updated, switch existing
sk_lookup programs to use "unqualified" SEC("sk_lookup") section names,
with no random text after it.

Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Dave Marchevsky <davemarchevsky@fb.com>
Link: https://lore.kernel.org/bpf/20210928161946.2512801-11-andrii@kernel.org
---
 tools/lib/bpf/libbpf.c                             |  2 +-
 tools/testing/selftests/bpf/progs/test_sk_lookup.c | 38 +++++++++++-----------
 2 files changed, 20 insertions(+), 20 deletions(-)

(limited to 'tools')

diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 3e1f6211b9b9..1c859b32968d 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -8055,7 +8055,7 @@ static const struct bpf_sec_def section_defs[] = {
 	SEC_DEF("cgroup/getsockopt",	CGROUP_SOCKOPT, BPF_CGROUP_GETSOCKOPT, SEC_ATTACHABLE | SEC_SLOPPY_PFX),
 	SEC_DEF("cgroup/setsockopt",	CGROUP_SOCKOPT, BPF_CGROUP_SETSOCKOPT, SEC_ATTACHABLE | SEC_SLOPPY_PFX),
 	SEC_DEF("struct_ops+",		STRUCT_OPS, 0, SEC_NONE),
-	SEC_DEF("sk_lookup/",		SK_LOOKUP, BPF_SK_LOOKUP, SEC_ATTACHABLE),
+	SEC_DEF("sk_lookup",		SK_LOOKUP, BPF_SK_LOOKUP, SEC_ATTACHABLE | SEC_SLOPPY_PFX),
 };
 
 #define MAX_TYPE_NAME_SIZE 32
diff --git a/tools/testing/selftests/bpf/progs/test_sk_lookup.c b/tools/testing/selftests/bpf/progs/test_sk_lookup.c
index 6c4d32c56765..48534d810391 100644
--- a/tools/testing/selftests/bpf/progs/test_sk_lookup.c
+++ b/tools/testing/selftests/bpf/progs/test_sk_lookup.c
@@ -72,13 +72,13 @@ static const __u16 DST_PORT = 7007; /* Host byte order */
 static const __u32 DST_IP4 = IP4(127, 0, 0, 1);
 static const __u32 DST_IP6[] = IP6(0xfd000000, 0x0, 0x0, 0x00000001);
 
-SEC("sk_lookup/lookup_pass")
+SEC("sk_lookup")
 int lookup_pass(struct bpf_sk_lookup *ctx)
 {
 	return SK_PASS;
 }
 
-SEC("sk_lookup/lookup_drop")
+SEC("sk_lookup")
 int lookup_drop(struct bpf_sk_lookup *ctx)
 {
 	return SK_DROP;
@@ -97,7 +97,7 @@ int reuseport_drop(struct sk_reuseport_md *ctx)
 }
 
 /* Redirect packets destined for port DST_PORT to socket at redir_map[0]. */
-SEC("sk_lookup/redir_port")
+SEC("sk_lookup")
 int redir_port(struct bpf_sk_lookup *ctx)
 {
 	struct bpf_sock *sk;
@@ -116,7 +116,7 @@ int redir_port(struct bpf_sk_lookup *ctx)
 }
 
 /* Redirect packets destined for DST_IP4 address to socket at redir_map[0]. */
-SEC("sk_lookup/redir_ip4")
+SEC("sk_lookup")
 int redir_ip4(struct bpf_sk_lookup *ctx)
 {
 	struct bpf_sock *sk;
@@ -139,7 +139,7 @@ int redir_ip4(struct bpf_sk_lookup *ctx)
 }
 
 /* Redirect packets destined for DST_IP6 address to socket at redir_map[0]. */
-SEC("sk_lookup/redir_ip6")
+SEC("sk_lookup")
 int redir_ip6(struct bpf_sk_lookup *ctx)
 {
 	struct bpf_sock *sk;
@@ -164,7 +164,7 @@ int redir_ip6(struct bpf_sk_lookup *ctx)
 	return err ? SK_DROP : SK_PASS;
 }
 
-SEC("sk_lookup/select_sock_a")
+SEC("sk_lookup")
 int select_sock_a(struct bpf_sk_lookup *ctx)
 {
 	struct bpf_sock *sk;
@@ -179,7 +179,7 @@ int select_sock_a(struct bpf_sk_lookup *ctx)
 	return err ? SK_DROP : SK_PASS;
 }
 
-SEC("sk_lookup/select_sock_a_no_reuseport")
+SEC("sk_lookup")
 int select_sock_a_no_reuseport(struct bpf_sk_lookup *ctx)
 {
 	struct bpf_sock *sk;
@@ -205,7 +205,7 @@ int select_sock_b(struct sk_reuseport_md *ctx)
 }
 
 /* Check that bpf_sk_assign() returns -EEXIST if socket already selected. */
-SEC("sk_lookup/sk_assign_eexist")
+SEC("sk_lookup")
 int sk_assign_eexist(struct bpf_sk_lookup *ctx)
 {
 	struct bpf_sock *sk;
@@ -238,7 +238,7 @@ out:
 }
 
 /* Check that bpf_sk_assign(BPF_SK_LOOKUP_F_REPLACE) can override selection. */
-SEC("sk_lookup/sk_assign_replace_flag")
+SEC("sk_lookup")
 int sk_assign_replace_flag(struct bpf_sk_lookup *ctx)
 {
 	struct bpf_sock *sk;
@@ -270,7 +270,7 @@ out:
 }
 
 /* Check that bpf_sk_assign(sk=NULL) is accepted. */
-SEC("sk_lookup/sk_assign_null")
+SEC("sk_lookup")
 int sk_assign_null(struct bpf_sk_lookup *ctx)
 {
 	struct bpf_sock *sk = NULL;
@@ -313,7 +313,7 @@ out:
 }
 
 /* Check that selected sk is accessible through context. */
-SEC("sk_lookup/access_ctx_sk")
+SEC("sk_lookup")
 int access_ctx_sk(struct bpf_sk_lookup *ctx)
 {
 	struct bpf_sock *sk1 = NULL, *sk2 = NULL;
@@ -379,7 +379,7 @@ out:
  * are not covered because they give bogus results, that is the
  * verifier ignores the offset.
  */
-SEC("sk_lookup/ctx_narrow_access")
+SEC("sk_lookup")
 int ctx_narrow_access(struct bpf_sk_lookup *ctx)
 {
 	struct bpf_sock *sk;
@@ -553,7 +553,7 @@ int ctx_narrow_access(struct bpf_sk_lookup *ctx)
 }
 
 /* Check that sk_assign rejects SERVER_A socket with -ESOCKNOSUPPORT */
-SEC("sk_lookup/sk_assign_esocknosupport")
+SEC("sk_lookup")
 int sk_assign_esocknosupport(struct bpf_sk_lookup *ctx)
 {
 	struct bpf_sock *sk;
@@ -578,28 +578,28 @@ out:
 	return ret;
 }
 
-SEC("sk_lookup/multi_prog_pass1")
+SEC("sk_lookup")
 int multi_prog_pass1(struct bpf_sk_lookup *ctx)
 {
 	bpf_map_update_elem(&run_map, &KEY_PROG1, &PROG_DONE, BPF_ANY);
 	return SK_PASS;
 }
 
-SEC("sk_lookup/multi_prog_pass2")
+SEC("sk_lookup")
 int multi_prog_pass2(struct bpf_sk_lookup *ctx)
 {
 	bpf_map_update_elem(&run_map, &KEY_PROG2, &PROG_DONE, BPF_ANY);
 	return SK_PASS;
 }
 
-SEC("sk_lookup/multi_prog_drop1")
+SEC("sk_lookup")
 int multi_prog_drop1(struct bpf_sk_lookup *ctx)
 {
 	bpf_map_update_elem(&run_map, &KEY_PROG1, &PROG_DONE, BPF_ANY);
 	return SK_DROP;
 }
 
-SEC("sk_lookup/multi_prog_drop2")
+SEC("sk_lookup")
 int multi_prog_drop2(struct bpf_sk_lookup *ctx)
 {
 	bpf_map_update_elem(&run_map, &KEY_PROG2, &PROG_DONE, BPF_ANY);
@@ -623,7 +623,7 @@ static __always_inline int select_server_a(struct bpf_sk_lookup *ctx)
 	return SK_PASS;
 }
 
-SEC("sk_lookup/multi_prog_redir1")
+SEC("sk_lookup")
 int multi_prog_redir1(struct bpf_sk_lookup *ctx)
 {
 	int ret;
@@ -633,7 +633,7 @@ int multi_prog_redir1(struct bpf_sk_lookup *ctx)
 	return SK_PASS;
 }
 
-SEC("sk_lookup/multi_prog_redir2")
+SEC("sk_lookup")
 int multi_prog_redir2(struct bpf_sk_lookup *ctx)
 {
 	int ret;
-- 
cgit v1.2.3


From 09710d82c0a3469eadc32781721ac2336fdf915d Mon Sep 17 00:00:00 2001
From: Yucong Sun <fallentree@fb.com>
Date: Tue, 28 Sep 2021 11:42:21 -0700
Subject: bpftool: Avoid using "?: " in generated code

"?:" is a GNU C extension, some environment has warning flags for its
use, or even prohibit it directly.  This patch avoid triggering these
problems by simply expand it to its full form, no functionality change.

Signed-off-by: Yucong Sun <fallentree@fb.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20210928184221.1545079-1-fallentree@fb.com
---
 tools/bpf/bpftool/gen.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

(limited to 'tools')

diff --git a/tools/bpf/bpftool/gen.c b/tools/bpf/bpftool/gen.c
index e3ec47a6a612..cc835859465b 100644
--- a/tools/bpf/bpftool/gen.c
+++ b/tools/bpf/bpftool/gen.c
@@ -803,7 +803,10 @@ static int do_skeleton(int argc, char **argv)
 			}						    \n\
 									    \n\
 			err = %1$s__create_skeleton(obj);		    \n\
-			err = err ?: bpf_object__open_skeleton(obj->skeleton, opts);\n\
+			if (err)					    \n\
+				goto err_out;				    \n\
+									    \n\
+			err = bpf_object__open_skeleton(obj->skeleton, opts);\n\
 			if (err)					    \n\
 				goto err_out;				    \n\
 									    \n\
-- 
cgit v1.2.3


From 38261f369fb905552ebdd3feb9699c0788fd3371 Mon Sep 17 00:00:00 2001
From: Yonghong Song <yhs@fb.com>
Date: Tue, 28 Sep 2021 20:30:00 -0700
Subject: selftests/bpf: Fix probe_user test failure with clang build kernel

clang build kernel failed the selftest probe_user.
  $ ./test_progs -t probe_user
  $ ...
  $ test_probe_user:PASS:get_kprobe_res 0 nsec
  $ test_probe_user:FAIL:check_kprobe_res wrong kprobe res from probe read: 0.0.0.0:0
  $ #94 probe_user:FAIL

The test attached to kernel function __sys_connect(). In net/socket.c, we have
  int __sys_connect(int fd, struct sockaddr __user *uservaddr, int addrlen)
  {
        ......
  }
  ...
  SYSCALL_DEFINE3(connect, int, fd, struct sockaddr __user *, uservaddr,
                  int, addrlen)
  {
        return __sys_connect(fd, uservaddr, addrlen);
  }

The gcc compiler (8.5.0) does not inline __sys_connect() in syscall entry
function. But latest clang trunk did the inlining. So the bpf program
is not triggered.

To make the test more reliable, let us kprobe the syscall entry function
instead. Note that x86_64, arm64 and s390 have syscall wrappers and they have
to be handled specially.

Signed-off-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20210929033000.3711921-1-yhs@fb.com
---
 .../testing/selftests/bpf/prog_tests/probe_user.c  |  4 ++--
 .../testing/selftests/bpf/progs/test_probe_user.c  | 28 ++++++++++++++++++++--
 2 files changed, 28 insertions(+), 4 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/prog_tests/probe_user.c b/tools/testing/selftests/bpf/prog_tests/probe_user.c
index 95bd12097358..52fe157e2a90 100644
--- a/tools/testing/selftests/bpf/prog_tests/probe_user.c
+++ b/tools/testing/selftests/bpf/prog_tests/probe_user.c
@@ -3,7 +3,7 @@
 
 void test_probe_user(void)
 {
-	const char *prog_name = "kprobe/__sys_connect";
+	const char *prog_name = "handle_sys_connect";
 	const char *obj_file = "./test_probe_user.o";
 	DECLARE_LIBBPF_OPTS(bpf_object_open_opts, opts, );
 	int err, results_map_fd, sock_fd, duration = 0;
@@ -18,7 +18,7 @@ void test_probe_user(void)
 	if (!ASSERT_OK_PTR(obj, "obj_open_file"))
 		return;
 
-	kprobe_prog = bpf_object__find_program_by_title(obj, prog_name);
+	kprobe_prog = bpf_object__find_program_by_name(obj, prog_name);
 	if (CHECK(!kprobe_prog, "find_probe",
 		  "prog '%s' not found\n", prog_name))
 		goto cleanup;
diff --git a/tools/testing/selftests/bpf/progs/test_probe_user.c b/tools/testing/selftests/bpf/progs/test_probe_user.c
index 89b3532ccc75..8812a90da4eb 100644
--- a/tools/testing/selftests/bpf/progs/test_probe_user.c
+++ b/tools/testing/selftests/bpf/progs/test_probe_user.c
@@ -8,13 +8,37 @@
 #include <bpf/bpf_helpers.h>
 #include <bpf/bpf_tracing.h>
 
+#if defined(__TARGET_ARCH_x86)
+#define SYSCALL_WRAPPER 1
+#define SYS_PREFIX "__x64_"
+#elif defined(__TARGET_ARCH_s390)
+#define SYSCALL_WRAPPER 1
+#define SYS_PREFIX "__s390x_"
+#elif defined(__TARGET_ARCH_arm64)
+#define SYSCALL_WRAPPER 1
+#define SYS_PREFIX "__arm64_"
+#else
+#define SYSCALL_WRAPPER 0
+#define SYS_PREFIX ""
+#endif
+
 static struct sockaddr_in old;
 
-SEC("kprobe/__sys_connect")
+SEC("kprobe/" SYS_PREFIX "sys_connect")
 int BPF_KPROBE(handle_sys_connect)
 {
-	void *ptr = (void *)PT_REGS_PARM2(ctx);
+#if SYSCALL_WRAPPER == 1
+	struct pt_regs *real_regs;
+#endif
 	struct sockaddr_in new;
+	void *ptr;
+
+#if SYSCALL_WRAPPER == 0
+	ptr = (void *)PT_REGS_PARM2(ctx);
+#else
+	real_regs = (struct pt_regs *)PT_REGS_PARM1(ctx);
+	bpf_probe_read_kernel(&ptr, sizeof(ptr), &PT_REGS_PARM2(real_regs));
+#endif
 
 	bpf_probe_read_user(&old, sizeof(old), ptr);
 	__builtin_memset(&new, 0xab, sizeof(new));
-- 
cgit v1.2.3


From e31eec77e4ab90dcec7d2da93415f839098dc287 Mon Sep 17 00:00:00 2001
From: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Date: Mon, 27 Sep 2021 20:29:40 +0530
Subject: bpf: selftests: Fix fd cleanup in get_branch_snapshot

Cleanup code uses while (cpu++ < cpu_cnt) for closing fds, which means
it starts iterating from 1 for closing fds. If the first fd is -1, it
skips over it and closes garbage fds (typically zero) in the remaining
array. This leads to test failures for future tests when they end up
storing fd 0 (as the slot becomes free due to close(0)) in ldimm64's BTF
fd, ending up trying to match module BTF id with vmlinux.

This was observed as spurious CI failure for the ksym_module_libbpf and
module_attach tests. The test ends up closing fd 0 and breaking libbpf's
assumption that module BTF fd will always be > 0, which leads to the
kernel thinking that we are pointing to a BTF ID in vmlinux BTF.

Fixes: 025bd7c753aa (selftests/bpf: Add test for bpf_get_branch_snapshot)
Signed-off-by: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Song Liu <songliubraving@fb.com>
Link: https://lore.kernel.org/bpf/20210927145941.1383001-12-memxor@gmail.com
---
 tools/testing/selftests/bpf/prog_tests/get_branch_snapshot.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/prog_tests/get_branch_snapshot.c b/tools/testing/selftests/bpf/prog_tests/get_branch_snapshot.c
index f81db9135ae4..67e86f8d8677 100644
--- a/tools/testing/selftests/bpf/prog_tests/get_branch_snapshot.c
+++ b/tools/testing/selftests/bpf/prog_tests/get_branch_snapshot.c
@@ -38,10 +38,9 @@ static int create_perf_events(void)
 
 static void close_perf_events(void)
 {
-	int cpu = 0;
-	int fd;
+	int cpu, fd;
 
-	while (cpu++ < cpu_cnt) {
+	for (cpu = 0; cpu < cpu_cnt; cpu++) {
 		fd = pfd_array[cpu];
 		if (fd < 0)
 			break;
-- 
cgit v1.2.3


From 66fe33241726d1f872e55d95a35c063d58602ae1 Mon Sep 17 00:00:00 2001
From: Alexei Starovoitov <ast@kernel.org>
Date: Mon, 27 Sep 2021 20:29:37 +0530
Subject: libbpf: Make gen_loader data aligned.

Align gen_loader data to 8 byte boundary to make sure union bpf_attr,
bpf_insns and other structs are aligned.

Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20210927145941.1383001-9-memxor@gmail.com
---
 tools/lib/bpf/gen_loader.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

(limited to 'tools')

diff --git a/tools/lib/bpf/gen_loader.c b/tools/lib/bpf/gen_loader.c
index 8df718a6b142..80087b13877f 100644
--- a/tools/lib/bpf/gen_loader.c
+++ b/tools/lib/bpf/gen_loader.c
@@ -5,6 +5,7 @@
 #include <string.h>
 #include <errno.h>
 #include <linux/filter.h>
+#include <sys/param.h>
 #include "btf.h"
 #include "bpf.h"
 #include "libbpf.h"
@@ -135,13 +136,17 @@ void bpf_gen__init(struct bpf_gen *gen, int log_level)
 
 static int add_data(struct bpf_gen *gen, const void *data, __u32 size)
 {
+	__u32 size8 = roundup(size, 8);
+	__u64 zero = 0;
 	void *prev;
 
-	if (realloc_data_buf(gen, size))
+	if (realloc_data_buf(gen, size8))
 		return 0;
 	prev = gen->data_cur;
 	memcpy(gen->data_cur, data, size);
 	gen->data_cur += size;
+	memcpy(gen->data_cur, &zero, size8 - size);
+	gen->data_cur += size8 - size;
 	return prev - gen->data_start;
 }
 
-- 
cgit v1.2.3


From 161ecd537948a7003129889b04a3a0858687bc70 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Toke=20H=C3=B8iland-J=C3=B8rgensen?= <toke@redhat.com>
Date: Wed, 29 Sep 2021 23:38:37 +0200
Subject: libbpf: Properly ignore STT_SECTION symbols in legacy map definitions
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The previous patch to ignore STT_SECTION symbols only added the ignore
condition in one of them. This fails if there's more than one map
definition in the 'maps' section, because the subsequent modulus check will
fail, resulting in error messages like:

libbpf: elf: unable to determine legacy map definition size in ./xdpdump_xdp.o

Fix this by also ignoring STT_SECTION in the first loop.

Fixes: c3e8c44a9063 ("libbpf: Ignore STT_SECTION symbols in 'maps' section")
Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20210929213837.832449-1-toke@redhat.com
---
 tools/lib/bpf/libbpf.c | 2 ++
 1 file changed, 2 insertions(+)

(limited to 'tools')

diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 1c859b32968d..7544d7d09160 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -1868,6 +1868,8 @@ static int bpf_object__init_user_maps(struct bpf_object *obj, bool strict)
 			continue;
 		if (sym.st_shndx != obj->efile.maps_shndx)
 			continue;
+		if (GELF_ST_TYPE(sym.st_info) == STT_SECTION)
+			continue;
 		nr_maps++;
 	}
 	/* Assume equally sized map definitions */
-- 
cgit v1.2.3


From e68ac0082787f4e8ee6ae5b19076ec7709ce715b Mon Sep 17 00:00:00 2001
From: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Date: Mon, 27 Sep 2021 20:29:39 +0530
Subject: libbpf: Fix skel_internal.h to set errno on loader retval < 0

When the loader indicates an internal error (result of a checked bpf
system call), it returns the result in attr.test.retval. However, tests
that rely on ASSERT_OK_PTR on NULL (returned from light skeleton) may
miss that NULL denotes an error if errno is set to 0. This would result
in skel pointer being NULL, while ASSERT_OK_PTR returning 1, leading to
a SEGV on dereference of skel, because libbpf_get_error relies on the
assumption that errno is always set in case of error for ptr == NULL.

In particular, this was observed for the ksyms_module test. When
executed using `./test_progs -t ksyms`, prior tests manipulated errno
and the test didn't crash when it failed at ksyms_module load, while
using `./test_progs -t ksyms_module` crashed due to errno being
untouched.

Fixes: 67234743736a (libbpf: Generate loader program out of BPF ELF file.)
Signed-off-by: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20210927145941.1383001-11-memxor@gmail.com
---
 tools/lib/bpf/skel_internal.h | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

(limited to 'tools')

diff --git a/tools/lib/bpf/skel_internal.h b/tools/lib/bpf/skel_internal.h
index b22b50c1b173..9cf66702fa8d 100644
--- a/tools/lib/bpf/skel_internal.h
+++ b/tools/lib/bpf/skel_internal.h
@@ -105,10 +105,12 @@ static inline int bpf_load_and_run(struct bpf_load_and_run_opts *opts)
 	err = skel_sys_bpf(BPF_PROG_RUN, &attr, sizeof(attr));
 	if (err < 0 || (int)attr.test.retval < 0) {
 		opts->errstr = "failed to execute loader prog";
-		if (err < 0)
+		if (err < 0) {
 			err = -errno;
-		else
+		} else {
 			err = (int)attr.test.retval;
+			errno = -err;
+		}
 		goto out;
 	}
 	err = 0;
-- 
cgit v1.2.3


From d4b6f87e8d3929d3d1594fca0256299113301fd7 Mon Sep 17 00:00:00 2001
From: Po-Hsu Lin <po-hsu.lin@canonical.com>
Date: Wed, 29 Sep 2021 13:12:50 +0800
Subject: selftests/bpf: Use kselftest skip code for skipped tests

There are several test cases in the bpf directory are still using
exit 0 when they need to be skipped. Use kselftest framework skip
code instead so it can help us to distinguish the return status.

Criterion to filter out what should be fixed in bpf directory:
  grep -r "exit 0" -B1 | grep -i skip

This change might cause some false-positives if people are running
these test scripts directly and only checking their return codes,
which will change from 0 to 4. However I think the impact should be
small as most of our scripts here are already using this skip code.
And there will be no such issue if running them with the kselftest
framework.

Signed-off-by: Po-Hsu Lin <po-hsu.lin@canonical.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/bpf/20210929051250.13831-1-po-hsu.lin@canonical.com
---
 tools/testing/selftests/bpf/test_xdp_meta.sh | 5 ++++-
 tools/testing/selftests/bpf/test_xdp_vlan.sh | 7 +++++--
 2 files changed, 9 insertions(+), 3 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/test_xdp_meta.sh b/tools/testing/selftests/bpf/test_xdp_meta.sh
index 637fcf4fe4e3..d10cefd6eb09 100755
--- a/tools/testing/selftests/bpf/test_xdp_meta.sh
+++ b/tools/testing/selftests/bpf/test_xdp_meta.sh
@@ -1,5 +1,8 @@
 #!/bin/sh
 
+# Kselftest framework requirement - SKIP code is 4.
+readonly KSFT_SKIP=4
+
 cleanup()
 {
 	if [ "$?" = "0" ]; then
@@ -17,7 +20,7 @@ cleanup()
 ip link set dev lo xdp off 2>/dev/null > /dev/null
 if [ $? -ne 0 ];then
 	echo "selftests: [SKIP] Could not run test without the ip xdp support"
-	exit 0
+	exit $KSFT_SKIP
 fi
 set -e
 
diff --git a/tools/testing/selftests/bpf/test_xdp_vlan.sh b/tools/testing/selftests/bpf/test_xdp_vlan.sh
index bb8b0da91686..0cbc7604a2f8 100755
--- a/tools/testing/selftests/bpf/test_xdp_vlan.sh
+++ b/tools/testing/selftests/bpf/test_xdp_vlan.sh
@@ -2,6 +2,9 @@
 # SPDX-License-Identifier: GPL-2.0
 # Author: Jesper Dangaard Brouer <hawk@kernel.org>
 
+# Kselftest framework requirement - SKIP code is 4.
+readonly KSFT_SKIP=4
+
 # Allow wrapper scripts to name test
 if [ -z "$TESTNAME" ]; then
     TESTNAME=xdp_vlan
@@ -94,7 +97,7 @@ while true; do
 	    -h | --help )
 		usage;
 		echo "selftests: $TESTNAME [SKIP] usage help info requested"
-		exit 0
+		exit $KSFT_SKIP
 		;;
 	    * )
 		shift
@@ -117,7 +120,7 @@ fi
 ip link set dev lo xdpgeneric off 2>/dev/null > /dev/null
 if [ $? -ne 0 ]; then
 	echo "selftests: $TESTNAME [SKIP] need ip xdp support"
-	exit 0
+	exit $KSFT_SKIP
 fi
 
 # Interactive mode likely require us to cleanup netns
-- 
cgit v1.2.3


From f731052325efc3726577feb743c7495f880ae07d Mon Sep 17 00:00:00 2001
From: Hengqi Chen <hengqi.chen@gmail.com>
Date: Fri, 1 Oct 2021 00:14:55 +0800
Subject: libbpf: Support uniform BTF-defined key/value specification across
 all BPF maps

A bunch of BPF maps do not support specifying BTF types for key and value.
This is non-uniform and inconvenient[0]. Currently, libbpf uses a retry
logic which removes BTF type IDs when BPF map creation failed. Instead
of retrying, this commit recognizes those specialized maps and removes
BTF type IDs when creating BPF map.

  [0] Closes: https://github.com/libbpf/libbpf/issues/355

Signed-off-by: Hengqi Chen <hengqi.chen@gmail.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20210930161456.3444544-2-hengqi.chen@gmail.com
---
 tools/lib/bpf/libbpf.c | 24 ++++++++++++++++++++++++
 1 file changed, 24 insertions(+)

(limited to 'tools')

diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 7544d7d09160..e23f1b6b9402 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -4669,6 +4669,30 @@ static int bpf_object__create_map(struct bpf_object *obj, struct bpf_map *map, b
 			create_attr.inner_map_fd = map->inner_map_fd;
 	}
 
+	switch (def->type) {
+	case BPF_MAP_TYPE_PERF_EVENT_ARRAY:
+	case BPF_MAP_TYPE_CGROUP_ARRAY:
+	case BPF_MAP_TYPE_STACK_TRACE:
+	case BPF_MAP_TYPE_ARRAY_OF_MAPS:
+	case BPF_MAP_TYPE_HASH_OF_MAPS:
+	case BPF_MAP_TYPE_DEVMAP:
+	case BPF_MAP_TYPE_DEVMAP_HASH:
+	case BPF_MAP_TYPE_CPUMAP:
+	case BPF_MAP_TYPE_XSKMAP:
+	case BPF_MAP_TYPE_SOCKMAP:
+	case BPF_MAP_TYPE_SOCKHASH:
+	case BPF_MAP_TYPE_QUEUE:
+	case BPF_MAP_TYPE_STACK:
+	case BPF_MAP_TYPE_RINGBUF:
+		create_attr.btf_fd = 0;
+		create_attr.btf_key_type_id = 0;
+		create_attr.btf_value_type_id = 0;
+		map->btf_key_type_id = 0;
+		map->btf_value_type_id = 0;
+	default:
+		break;
+	}
+
 	if (obj->gen_loader) {
 		bpf_gen__map_create(obj->gen_loader, &create_attr, is_inner ? -1 : map - obj->maps);
 		/* Pretend to have valid FD to pass various fd >= 0 checks.
-- 
cgit v1.2.3


From bd368cb554d685c60e65ab799bf238663c682105 Mon Sep 17 00:00:00 2001
From: Hengqi Chen <hengqi.chen@gmail.com>
Date: Fri, 1 Oct 2021 00:14:56 +0800
Subject: selftests/bpf: Use BTF-defined key/value for map definitions

Change map definitions in BPF selftests to use BTF-defined
key/value types. This unifies the map definitions and ensures
libbpf won't emit warning about retrying map creation.

Signed-off-by: Hengqi Chen <hengqi.chen@gmail.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20210930161456.3444544-3-hengqi.chen@gmail.com
---
 tools/testing/selftests/bpf/progs/kfree_skb.c              |  4 ++--
 tools/testing/selftests/bpf/progs/perf_event_stackmap.c    |  4 ++--
 tools/testing/selftests/bpf/progs/sockmap_verdict_prog.c   | 12 ++++++------
 tools/testing/selftests/bpf/progs/test_btf_map_in_map.c    | 14 +++++++-------
 tools/testing/selftests/bpf/progs/test_map_in_map.c        | 10 ++++------
 .../testing/selftests/bpf/progs/test_map_in_map_invalid.c  |  2 +-
 tools/testing/selftests/bpf/progs/test_pe_preserve_elems.c |  8 ++++----
 tools/testing/selftests/bpf/progs/test_perf_buffer.c       |  4 ++--
 .../selftests/bpf/progs/test_select_reuseport_kern.c       |  4 ++--
 .../testing/selftests/bpf/progs/test_stacktrace_build_id.c |  4 ++--
 tools/testing/selftests/bpf/progs/test_stacktrace_map.c    |  4 ++--
 tools/testing/selftests/bpf/progs/test_tcpnotify_kern.c    |  4 ++--
 tools/testing/selftests/bpf/progs/test_xdp_bpf2bpf.c       |  4 ++--
 13 files changed, 38 insertions(+), 40 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/progs/kfree_skb.c b/tools/testing/selftests/bpf/progs/kfree_skb.c
index 55e283050cab..7236da72ce80 100644
--- a/tools/testing/selftests/bpf/progs/kfree_skb.c
+++ b/tools/testing/selftests/bpf/progs/kfree_skb.c
@@ -9,8 +9,8 @@
 char _license[] SEC("license") = "GPL";
 struct {
 	__uint(type, BPF_MAP_TYPE_PERF_EVENT_ARRAY);
-	__uint(key_size, sizeof(int));
-	__uint(value_size, sizeof(int));
+	__type(key, int);
+	__type(value, int);
 } perf_buf_map SEC(".maps");
 
 #define _(P) (__builtin_preserve_access_index(P))
diff --git a/tools/testing/selftests/bpf/progs/perf_event_stackmap.c b/tools/testing/selftests/bpf/progs/perf_event_stackmap.c
index 25467d13c356..b3fcb5274ee0 100644
--- a/tools/testing/selftests/bpf/progs/perf_event_stackmap.c
+++ b/tools/testing/selftests/bpf/progs/perf_event_stackmap.c
@@ -11,8 +11,8 @@ typedef __u64 stack_trace_t[PERF_MAX_STACK_DEPTH];
 struct {
 	__uint(type, BPF_MAP_TYPE_STACK_TRACE);
 	__uint(max_entries, 16384);
-	__uint(key_size, sizeof(__u32));
-	__uint(value_size, sizeof(stack_trace_t));
+	__type(key, __u32);
+	__type(value, stack_trace_t);
 } stackmap SEC(".maps");
 
 struct {
diff --git a/tools/testing/selftests/bpf/progs/sockmap_verdict_prog.c b/tools/testing/selftests/bpf/progs/sockmap_verdict_prog.c
index 4797dc985064..73872c535cbb 100644
--- a/tools/testing/selftests/bpf/progs/sockmap_verdict_prog.c
+++ b/tools/testing/selftests/bpf/progs/sockmap_verdict_prog.c
@@ -7,22 +7,22 @@ int _version SEC("version") = 1;
 struct {
 	__uint(type, BPF_MAP_TYPE_SOCKMAP);
 	__uint(max_entries, 20);
-	__uint(key_size, sizeof(int));
-	__uint(value_size, sizeof(int));
+	__type(key, int);
+	__type(value, int);
 } sock_map_rx SEC(".maps");
 
 struct {
 	__uint(type, BPF_MAP_TYPE_SOCKMAP);
 	__uint(max_entries, 20);
-	__uint(key_size, sizeof(int));
-	__uint(value_size, sizeof(int));
+	__type(key, int);
+	__type(value, int);
 } sock_map_tx SEC(".maps");
 
 struct {
 	__uint(type, BPF_MAP_TYPE_SOCKMAP);
 	__uint(max_entries, 20);
-	__uint(key_size, sizeof(int));
-	__uint(value_size, sizeof(int));
+	__type(key, int);
+	__type(value, int);
 } sock_map_msg SEC(".maps");
 
 struct {
diff --git a/tools/testing/selftests/bpf/progs/test_btf_map_in_map.c b/tools/testing/selftests/bpf/progs/test_btf_map_in_map.c
index c1e0c8c7c55f..c218cf8989a9 100644
--- a/tools/testing/selftests/bpf/progs/test_btf_map_in_map.c
+++ b/tools/testing/selftests/bpf/progs/test_btf_map_in_map.c
@@ -21,8 +21,8 @@ struct inner_map_sz2 {
 struct outer_arr {
 	__uint(type, BPF_MAP_TYPE_ARRAY_OF_MAPS);
 	__uint(max_entries, 3);
-	__uint(key_size, sizeof(int));
-	__uint(value_size, sizeof(int));
+	__type(key, int);
+	__type(value, int);
 	/* it's possible to use anonymous struct as inner map definition here */
 	__array(values, struct {
 		__uint(type, BPF_MAP_TYPE_ARRAY);
@@ -61,8 +61,8 @@ struct inner_map_sz4 {
 struct outer_arr_dyn {
 	__uint(type, BPF_MAP_TYPE_ARRAY_OF_MAPS);
 	__uint(max_entries, 3);
-	__uint(key_size, sizeof(int));
-	__uint(value_size, sizeof(int));
+	__type(key, int);
+	__type(value, int);
 	__array(values, struct {
 		__uint(type, BPF_MAP_TYPE_ARRAY);
 		__uint(map_flags, BPF_F_INNER_MAP);
@@ -81,7 +81,7 @@ struct outer_arr_dyn {
 struct outer_hash {
 	__uint(type, BPF_MAP_TYPE_HASH_OF_MAPS);
 	__uint(max_entries, 5);
-	__uint(key_size, sizeof(int));
+	__type(key, int);
 	/* Here everything works flawlessly due to reuse of struct inner_map
 	 * and compiler will complain at the attempt to use non-inner_map
 	 * references below. This is great experience.
@@ -111,8 +111,8 @@ struct sockarr_sz2 {
 struct outer_sockarr_sz1 {
 	__uint(type, BPF_MAP_TYPE_ARRAY_OF_MAPS);
 	__uint(max_entries, 1);
-	__uint(key_size, sizeof(int));
-	__uint(value_size, sizeof(int));
+	__type(key, int);
+	__type(value, int);
 	__array(values, struct sockarr_sz1);
 } outer_sockarr SEC(".maps") = {
 	.values = { (void *)&sockarr_sz1 },
diff --git a/tools/testing/selftests/bpf/progs/test_map_in_map.c b/tools/testing/selftests/bpf/progs/test_map_in_map.c
index 5f0e0bfc151e..a6d91932dcd5 100644
--- a/tools/testing/selftests/bpf/progs/test_map_in_map.c
+++ b/tools/testing/selftests/bpf/progs/test_map_in_map.c
@@ -9,18 +9,16 @@ struct {
 	__uint(type, BPF_MAP_TYPE_ARRAY_OF_MAPS);
 	__uint(max_entries, 1);
 	__uint(map_flags, 0);
-	__uint(key_size, sizeof(__u32));
-	/* must be sizeof(__u32) for map in map */
-	__uint(value_size, sizeof(__u32));
+	__type(key, __u32);
+	__type(value, __u32);
 } mim_array SEC(".maps");
 
 struct {
 	__uint(type, BPF_MAP_TYPE_HASH_OF_MAPS);
 	__uint(max_entries, 1);
 	__uint(map_flags, 0);
-	__uint(key_size, sizeof(int));
-	/* must be sizeof(__u32) for map in map */
-	__uint(value_size, sizeof(__u32));
+	__type(key, int);
+	__type(value, __u32);
 } mim_hash SEC(".maps");
 
 SEC("xdp")
diff --git a/tools/testing/selftests/bpf/progs/test_map_in_map_invalid.c b/tools/testing/selftests/bpf/progs/test_map_in_map_invalid.c
index 703c08e06442..9c7d75cf0bd6 100644
--- a/tools/testing/selftests/bpf/progs/test_map_in_map_invalid.c
+++ b/tools/testing/selftests/bpf/progs/test_map_in_map_invalid.c
@@ -13,7 +13,7 @@ struct inner {
 struct {
 	__uint(type, BPF_MAP_TYPE_ARRAY_OF_MAPS);
 	__uint(max_entries, 0); /* This will make map creation to fail */
-	__uint(key_size, sizeof(__u32));
+	__type(key, __u32);
 	__array(values, struct inner);
 } mim SEC(".maps");
 
diff --git a/tools/testing/selftests/bpf/progs/test_pe_preserve_elems.c b/tools/testing/selftests/bpf/progs/test_pe_preserve_elems.c
index fb22de7c365d..1249a945699f 100644
--- a/tools/testing/selftests/bpf/progs/test_pe_preserve_elems.c
+++ b/tools/testing/selftests/bpf/progs/test_pe_preserve_elems.c
@@ -7,15 +7,15 @@
 struct {
 	__uint(type, BPF_MAP_TYPE_PERF_EVENT_ARRAY);
 	__uint(max_entries, 1);
-	__uint(key_size, sizeof(int));
-	__uint(value_size, sizeof(int));
+	__type(key, int);
+	__type(value, int);
 } array_1 SEC(".maps");
 
 struct {
 	__uint(type, BPF_MAP_TYPE_PERF_EVENT_ARRAY);
 	__uint(max_entries, 1);
-	__uint(key_size, sizeof(int));
-	__uint(value_size, sizeof(int));
+	__type(key, int);
+	__type(value, int);
 	__uint(map_flags, BPF_F_PRESERVE_ELEMS);
 } array_2 SEC(".maps");
 
diff --git a/tools/testing/selftests/bpf/progs/test_perf_buffer.c b/tools/testing/selftests/bpf/progs/test_perf_buffer.c
index 8207a2dc2f9d..d37ce29fd393 100644
--- a/tools/testing/selftests/bpf/progs/test_perf_buffer.c
+++ b/tools/testing/selftests/bpf/progs/test_perf_buffer.c
@@ -8,8 +8,8 @@
 
 struct {
 	__uint(type, BPF_MAP_TYPE_PERF_EVENT_ARRAY);
-	__uint(key_size, sizeof(int));
-	__uint(value_size, sizeof(int));
+	__type(key, int);
+	__type(value, int);
 } perf_buf_map SEC(".maps");
 
 SEC("tp/raw_syscalls/sys_enter")
diff --git a/tools/testing/selftests/bpf/progs/test_select_reuseport_kern.c b/tools/testing/selftests/bpf/progs/test_select_reuseport_kern.c
index 26e77dcc7e91..0f9bc258225e 100644
--- a/tools/testing/selftests/bpf/progs/test_select_reuseport_kern.c
+++ b/tools/testing/selftests/bpf/progs/test_select_reuseport_kern.c
@@ -24,8 +24,8 @@ int _version SEC("version") = 1;
 struct {
 	__uint(type, BPF_MAP_TYPE_ARRAY_OF_MAPS);
 	__uint(max_entries, 1);
-	__uint(key_size, sizeof(__u32));
-	__uint(value_size, sizeof(__u32));
+	__type(key, __u32);
+	__type(value, __u32);
 } outer_map SEC(".maps");
 
 struct {
diff --git a/tools/testing/selftests/bpf/progs/test_stacktrace_build_id.c b/tools/testing/selftests/bpf/progs/test_stacktrace_build_id.c
index 0cf0134631b4..7449fdb1763b 100644
--- a/tools/testing/selftests/bpf/progs/test_stacktrace_build_id.c
+++ b/tools/testing/selftests/bpf/progs/test_stacktrace_build_id.c
@@ -28,8 +28,8 @@ struct {
 	__uint(type, BPF_MAP_TYPE_STACK_TRACE);
 	__uint(max_entries, 128);
 	__uint(map_flags, BPF_F_STACK_BUILD_ID);
-	__uint(key_size, sizeof(__u32));
-	__uint(value_size, sizeof(stack_trace_t));
+	__type(key, __u32);
+	__type(value, stack_trace_t);
 } stackmap SEC(".maps");
 
 struct {
diff --git a/tools/testing/selftests/bpf/progs/test_stacktrace_map.c b/tools/testing/selftests/bpf/progs/test_stacktrace_map.c
index 00ed48672620..a8233e7f173b 100644
--- a/tools/testing/selftests/bpf/progs/test_stacktrace_map.c
+++ b/tools/testing/selftests/bpf/progs/test_stacktrace_map.c
@@ -27,8 +27,8 @@ typedef __u64 stack_trace_t[PERF_MAX_STACK_DEPTH];
 struct {
 	__uint(type, BPF_MAP_TYPE_STACK_TRACE);
 	__uint(max_entries, 16384);
-	__uint(key_size, sizeof(__u32));
-	__uint(value_size, sizeof(stack_trace_t));
+	__type(key, __u32);
+	__type(value, stack_trace_t);
 } stackmap SEC(".maps");
 
 struct {
diff --git a/tools/testing/selftests/bpf/progs/test_tcpnotify_kern.c b/tools/testing/selftests/bpf/progs/test_tcpnotify_kern.c
index ac63410bb541..24e9344994ef 100644
--- a/tools/testing/selftests/bpf/progs/test_tcpnotify_kern.c
+++ b/tools/testing/selftests/bpf/progs/test_tcpnotify_kern.c
@@ -24,8 +24,8 @@ struct {
 struct {
 	__uint(type, BPF_MAP_TYPE_PERF_EVENT_ARRAY);
 	__uint(max_entries, 2);
-	__uint(key_size, sizeof(int));
-	__uint(value_size, sizeof(__u32));
+	__type(key, int);
+	__type(value, __u32);
 } perf_event_map SEC(".maps");
 
 int _version SEC("version") = 1;
diff --git a/tools/testing/selftests/bpf/progs/test_xdp_bpf2bpf.c b/tools/testing/selftests/bpf/progs/test_xdp_bpf2bpf.c
index a038e827f850..58cf4345f5cc 100644
--- a/tools/testing/selftests/bpf/progs/test_xdp_bpf2bpf.c
+++ b/tools/testing/selftests/bpf/progs/test_xdp_bpf2bpf.c
@@ -36,8 +36,8 @@ struct meta {
 
 struct {
 	__uint(type, BPF_MAP_TYPE_PERF_EVENT_ARRAY);
-	__uint(key_size, sizeof(int));
-	__uint(value_size, sizeof(int));
+	__type(key, int);
+	__type(value, int);
 } perf_buf_map SEC(".maps");
 
 __u64 test_result_fentry = 0;
-- 
cgit v1.2.3


From 239f163ceabb8ee176396476de7d2b6b5261af39 Mon Sep 17 00:00:00 2001
From: Vladimir Oltean <vladimir.oltean@nxp.com>
Date: Fri, 1 Oct 2021 18:15:29 +0300
Subject: selftests: net: mscc: ocelot: bring up the ports automatically

Looks like when I wrote the selftests I was using a network manager that
brought up the ports automatically. In order to not rely on that, let
the script open them up.

Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/drivers/net/ocelot/tc_flower_chains.sh | 5 +++++
 1 file changed, 5 insertions(+)

(limited to 'tools')

diff --git a/tools/testing/selftests/drivers/net/ocelot/tc_flower_chains.sh b/tools/testing/selftests/drivers/net/ocelot/tc_flower_chains.sh
index f7d84549cc3e..0e19b56effe6 100755
--- a/tools/testing/selftests/drivers/net/ocelot/tc_flower_chains.sh
+++ b/tools/testing/selftests/drivers/net/ocelot/tc_flower_chains.sh
@@ -156,6 +156,11 @@ create_tcam_skeleton()
 
 setup_prepare()
 {
+	ip link set $eth0 up
+	ip link set $eth1 up
+	ip link set $eth2 up
+	ip link set $eth3 up
+
 	create_tcam_skeleton $eth0
 
 	ip link add br0 type bridge
-- 
cgit v1.2.3


From 4a907f659461908cd546bca083b373f6de20aa24 Mon Sep 17 00:00:00 2001
From: Vladimir Oltean <vladimir.oltean@nxp.com>
Date: Fri, 1 Oct 2021 18:15:30 +0300
Subject: selftests: net: mscc: ocelot: rename the VLAN modification test to
 ingress

There will be one more VLAN modification selftest added, this time for
egress. Rename the one that exists right now to be more specific.

Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/drivers/net/ocelot/tc_flower_chains.sh | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/drivers/net/ocelot/tc_flower_chains.sh b/tools/testing/selftests/drivers/net/ocelot/tc_flower_chains.sh
index 0e19b56effe6..4711313a92a3 100755
--- a/tools/testing/selftests/drivers/net/ocelot/tc_flower_chains.sh
+++ b/tools/testing/selftests/drivers/net/ocelot/tc_flower_chains.sh
@@ -247,9 +247,9 @@ test_vlan_push()
 	tcpdump_cleanup
 }
 
-test_vlan_modify()
+test_vlan_ingress_modify()
 {
-	printf "Testing VLAN modification..		"
+	printf "Testing ingress VLAN modification..		"
 
 	ip link set br0 type bridge vlan_filtering 1
 	bridge vlan add dev $eth0 vid 200
@@ -309,7 +309,7 @@ trap cleanup EXIT
 ALL_TESTS="
 	test_vlan_pop
 	test_vlan_push
-	test_vlan_modify
+	test_vlan_ingress_modify
 	test_skbedit_priority
 "
 
-- 
cgit v1.2.3


From 434ef35095d6d9da013d4d8f3777ffd99cce699a Mon Sep 17 00:00:00 2001
From: Vladimir Oltean <vladimir.oltean@nxp.com>
Date: Fri, 1 Oct 2021 18:15:31 +0300
Subject: selftests: net: mscc: ocelot: add a test for egress VLAN modification

For this test we are exercising the VCAP ES0 block's ability to match on
a packet with a given VLAN ID, and push an ES0 TAG A with a VID derived
from VID_A_VAL plus the classified VLAN.

$eth3.200 is the generator port
$eth0 is the bridged DUT port that receives
$eth1 is the bridged DUT port that forwards and rewrites VID 200 to 300
      on egress via VCAP ES0
$eth2 is the port that receives from the DUT port $eth1

Since the egress rewriting happens outside the bridging service, VID 300
does not need to be in the bridge VLAN table of $eth1.

Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../drivers/net/ocelot/tc_flower_chains.sh         | 39 ++++++++++++++++++++++
 1 file changed, 39 insertions(+)

(limited to 'tools')

diff --git a/tools/testing/selftests/drivers/net/ocelot/tc_flower_chains.sh b/tools/testing/selftests/drivers/net/ocelot/tc_flower_chains.sh
index 4711313a92a3..eaf8a04a7ca5 100755
--- a/tools/testing/selftests/drivers/net/ocelot/tc_flower_chains.sh
+++ b/tools/testing/selftests/drivers/net/ocelot/tc_flower_chains.sh
@@ -285,6 +285,44 @@ test_vlan_ingress_modify()
 	ip link set br0 type bridge vlan_filtering 0
 }
 
+test_vlan_egress_modify()
+{
+	printf "Testing egress VLAN modification..		"
+
+	tc qdisc add dev $eth1 clsact
+
+	ip link set br0 type bridge vlan_filtering 1
+	bridge vlan add dev $eth0 vid 200
+	bridge vlan add dev $eth1 vid 200
+
+	tc filter add dev $eth1 egress chain $(ES0) pref 3 \
+		protocol 802.1Q flower skip_sw vlan_id 200 vlan_prio 0 \
+		action vlan modify id 300 priority 7
+
+	tcpdump_start $eth2
+
+	$MZ $eth3.200 -q -c 1 -p 64 -a $eth3_mac -b $eth2_mac -t ip
+
+	sleep 1
+
+	tcpdump_stop
+
+	if tcpdump_show | grep -q "$eth3_mac > $eth2_mac, .* vlan 300"; then
+		echo "OK"
+	else
+		echo "FAIL"
+	fi
+
+	tcpdump_cleanup
+
+	tc filter del dev $eth1 egress chain $(ES0) pref 3
+	tc qdisc del dev $eth1 clsact
+
+	bridge vlan del dev $eth0 vid 200
+	bridge vlan del dev $eth1 vid 200
+	ip link set br0 type bridge vlan_filtering 0
+}
+
 test_skbedit_priority()
 {
 	local num_pkts=100
@@ -310,6 +348,7 @@ ALL_TESTS="
 	test_vlan_pop
 	test_vlan_push
 	test_vlan_ingress_modify
+	test_vlan_egress_modify
 	test_skbedit_priority
 "
 
-- 
cgit v1.2.3


From bf77b1400a56332819f9358cac52b326d6d49dfd Mon Sep 17 00:00:00 2001
From: Justin Iurman <justin.iurman@uliege.be>
Date: Sun, 3 Oct 2021 20:45:39 +0200
Subject: selftests: net: Test for the IOAM encapsulation with IPv6

This patch adds support for testing the encap (ip6ip6) mode of IOAM.

Signed-off-by: Justin Iurman <justin.iurman@uliege.be>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/ioam6.sh | 209 ++++++++++++++++++++++++++---------
 1 file changed, 159 insertions(+), 50 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/net/ioam6.sh b/tools/testing/selftests/net/ioam6.sh
index 3caf72bb9c6a..90700303d8a9 100755
--- a/tools/testing/selftests/net/ioam6.sh
+++ b/tools/testing/selftests/net/ioam6.sh
@@ -6,7 +6,7 @@
 # This script evaluates the IOAM insertion for IPv6 by checking the IOAM data
 # consistency directly inside packets on the receiver side. Tests are divided
 # into three categories: OUTPUT (evaluates the IOAM processing by the sender),
-# INPUT (evaluates the IOAM processing by the receiver) and GLOBAL (evaluates
+# INPUT (evaluates the IOAM processing by a receiver) and GLOBAL (evaluates
 # wider use cases that do not fall into the other two categories). Both OUTPUT
 # and INPUT tests only use a two-node topology (alpha and beta), while GLOBAL
 # tests use the entire three-node topology (alpha, beta, gamma). Each test is
@@ -200,7 +200,7 @@ check_kernel_compatibility()
   ip -netns ioam-tmp-node link set veth0 up
   ip -netns ioam-tmp-node link set veth1 up
 
-  ip -netns ioam-tmp-node ioam namespace add 0 &>/dev/null
+  ip -netns ioam-tmp-node ioam namespace add 0
   ns_ad=$?
 
   ip -netns ioam-tmp-node ioam namespace show | grep -q "namespace 0"
@@ -214,11 +214,11 @@ check_kernel_compatibility()
     exit 1
   fi
 
-  ip -netns ioam-tmp-node route add db02::/64 encap ioam6 trace prealloc \
-         type 0x800000 ns 0 size 4 dev veth0 &>/dev/null
+  ip -netns ioam-tmp-node route add db02::/64 encap ioam6 mode inline \
+         trace prealloc type 0x800000 ns 0 size 4 dev veth0
   tr_ad=$?
 
-  ip -netns ioam-tmp-node -6 route | grep -q "encap ioam6 trace"
+  ip -netns ioam-tmp-node -6 route | grep -q "encap ioam6"
   tr_sh=$?
 
   if [[ $tr_ad != 0 || $tr_sh != 0 ]]
@@ -232,6 +232,30 @@ check_kernel_compatibility()
 
   ip link del veth0 2>/dev/null || true
   ip netns del ioam-tmp-node || true
+
+  lsmod | grep -q "ip6_tunnel"
+  ip6tnl_loaded=$?
+
+  if [ $ip6tnl_loaded = 0 ]
+  then
+    encap_tests=0
+  else
+    modprobe ip6_tunnel &>/dev/null
+    lsmod | grep -q "ip6_tunnel"
+    encap_tests=$?
+
+    if [ $encap_tests != 0 ]
+    then
+      ip a | grep -q "ip6tnl0"
+      encap_tests=$?
+
+      if [ $encap_tests != 0 ]
+      then
+        echo "Note: ip6_tunnel not found neither as a module nor inside the" \
+             "kernel, tests that require it (encap mode) will be omitted"
+      fi
+    fi
+  fi
 }
 
 cleanup()
@@ -242,6 +266,11 @@ cleanup()
   ip netns del ioam-node-alpha || true
   ip netns del ioam-node-beta || true
   ip netns del ioam-node-gamma || true
+
+  if [ $ip6tnl_loaded != 0 ]
+  then
+    modprobe -r ip6_tunnel 2>/dev/null || true
+  fi
 }
 
 setup()
@@ -329,6 +358,12 @@ log_test_failed()
   printf "TEST: %-60s  [FAIL]\n" "${desc}"
 }
 
+log_results()
+{
+  echo "- Tests passed: ${npassed}"
+  echo "- Tests failed: ${nfailed}"
+}
+
 run_test()
 {
   local name=$1
@@ -349,16 +384,26 @@ run_test()
   ip netns exec $node_src ping6 -t 64 -c 1 -W 1 $ip6_dst &>/dev/null
   if [ $? != 0 ]
   then
+    nfailed=$((nfailed+1))
     log_test_failed "${desc}"
     kill -2 $spid &>/dev/null
   else
     wait $spid
-    [ $? = 0 ] && log_test_passed "${desc}" || log_test_failed "${desc}"
+    if [ $? = 0 ]
+    then
+      npassed=$((npassed+1))
+      log_test_passed "${desc}"
+    else
+      nfailed=$((nfailed+1))
+      log_test_failed "${desc}"
+    fi
   fi
 }
 
 run()
 {
+  echo
+  printf "%0.s-" {1..74}
   echo
   echo "OUTPUT tests"
   printf "%0.s-" {1..74}
@@ -369,7 +414,8 @@ run()
 
   for t in $TESTS_OUTPUT
   do
-    $t
+    $t "inline"
+    [ $encap_tests = 0 ] && $t "encap"
   done
 
   # clean OUTPUT settings
@@ -377,6 +423,8 @@ run()
   ip -netns ioam-node-alpha route change db01::/64 dev veth0
 
 
+  echo
+  printf "%0.s-" {1..74}
   echo
   echo "INPUT tests"
   printf "%0.s-" {1..74}
@@ -387,7 +435,8 @@ run()
 
   for t in $TESTS_INPUT
   do
-    $t
+    $t "inline"
+    [ $encap_tests = 0 ] && $t "encap"
   done
 
   # clean INPUT settings
@@ -396,7 +445,8 @@ run()
   ip -netns ioam-node-alpha ioam namespace set 123 schema ${ALPHA[8]}
   ip -netns ioam-node-alpha route change db01::/64 dev veth0
 
-
+  echo
+  printf "%0.s-" {1..74}
   echo
   echo "GLOBAL tests"
   printf "%0.s-" {1..74}
@@ -404,8 +454,12 @@ run()
 
   for t in $TESTS_GLOBAL
   do
-    $t
+    $t "inline"
+    [ $encap_tests = 0 ] && $t "encap"
   done
+
+  echo
+  log_results
 }
 
 bit2type=(
@@ -431,11 +485,16 @@ out_undef_ns()
   ##############################################################################
   local desc="Unknown IOAM namespace"
 
-  ip -netns ioam-node-alpha route change db01::/64 encap ioam6 trace prealloc \
-         type 0x800000 ns 0 size 4 dev veth0
+  [ "$1" = "encap" ] && mode="$1 tundst db01::1" || mode="$1"
+  [ "$1" = "encap" ] && ip -netns ioam-node-beta link set ip6tnl0 up
+
+  ip -netns ioam-node-alpha route change db01::/64 encap ioam6 mode $mode \
+         trace prealloc type 0x800000 ns 0 size 4 dev veth0
 
-  run_test ${FUNCNAME[0]} "${desc}" ioam-node-alpha ioam-node-beta db01::2 \
-         db01::1 veth0 0x800000 0
+  run_test ${FUNCNAME[0]} "${desc} ($1 mode)" ioam-node-alpha ioam-node-beta \
+         db01::2 db01::1 veth0 0x800000 0
+
+  [ "$1" = "encap" ] && ip -netns ioam-node-beta link set ip6tnl0 down
 }
 
 out_no_room()
@@ -446,11 +505,16 @@ out_no_room()
   ##############################################################################
   local desc="Missing trace room"
 
-  ip -netns ioam-node-alpha route change db01::/64 encap ioam6 trace prealloc \
-         type 0xc00000 ns 123 size 4 dev veth0
+  [ "$1" = "encap" ] && mode="$1 tundst db01::1" || mode="$1"
+  [ "$1" = "encap" ] && ip -netns ioam-node-beta link set ip6tnl0 up
+
+  ip -netns ioam-node-alpha route change db01::/64 encap ioam6 mode $mode \
+         trace prealloc type 0xc00000 ns 123 size 4 dev veth0
+
+  run_test ${FUNCNAME[0]} "${desc} ($1 mode)" ioam-node-alpha ioam-node-beta \
+         db01::2 db01::1 veth0 0xc00000 123
 
-  run_test ${FUNCNAME[0]} "${desc}" ioam-node-alpha ioam-node-beta db01::2 \
-         db01::1 veth0 0xc00000 123
+  [ "$1" = "encap" ] && ip -netns ioam-node-beta link set ip6tnl0 down
 }
 
 out_bits()
@@ -465,15 +529,21 @@ out_bits()
   local tmp=${bit2size[22]}
   bit2size[22]=$(( $tmp + ${#ALPHA[9]} + ((4 - (${#ALPHA[9]} % 4)) % 4) ))
 
+  [ "$1" = "encap" ] && mode="$1 tundst db01::1" || mode="$1"
+  [ "$1" = "encap" ] && ip -netns ioam-node-beta link set ip6tnl0 up
+
   for i in {0..22}
   do
-    ip -netns ioam-node-alpha route change db01::/64 encap ioam6 trace \
-           prealloc type ${bit2type[$i]} ns 123 size ${bit2size[$i]} dev veth0
+    ip -netns ioam-node-alpha route change db01::/64 encap ioam6 mode $mode \
+           trace prealloc type ${bit2type[$i]} ns 123 size ${bit2size[$i]} \
+           dev veth0
 
-    run_test "out_bit$i" "${desc/<n>/$i}" ioam-node-alpha ioam-node-beta \
-           db01::2 db01::1 veth0 ${bit2type[$i]} 123
+    run_test "out_bit$i" "${desc/<n>/$i} ($1 mode)" ioam-node-alpha \
+           ioam-node-beta db01::2 db01::1 veth0 ${bit2type[$i]} 123
   done
 
+  [ "$1" = "encap" ] && ip -netns ioam-node-beta link set ip6tnl0 down
+
   bit2size[22]=$tmp
 }
 
@@ -485,11 +555,16 @@ out_full_supp_trace()
   ##############################################################################
   local desc="Full supported trace"
 
-  ip -netns ioam-node-alpha route change db01::/64 encap ioam6 trace prealloc \
-         type 0xfff002 ns 123 size 100 dev veth0
+  [ "$1" = "encap" ] && mode="$1 tundst db01::1" || mode="$1"
+  [ "$1" = "encap" ] && ip -netns ioam-node-beta link set ip6tnl0 up
 
-  run_test ${FUNCNAME[0]} "${desc}" ioam-node-alpha ioam-node-beta db01::2 \
-         db01::1 veth0 0xfff002 123
+  ip -netns ioam-node-alpha route change db01::/64 encap ioam6 mode $mode \
+         trace prealloc type 0xfff002 ns 123 size 100 dev veth0
+
+  run_test ${FUNCNAME[0]} "${desc} ($1 mode)" ioam-node-alpha ioam-node-beta \
+         db01::2 db01::1 veth0 0xfff002 123
+
+  [ "$1" = "encap" ] && ip -netns ioam-node-beta link set ip6tnl0 down
 }
 
 
@@ -510,11 +585,16 @@ in_undef_ns()
   ##############################################################################
   local desc="Unknown IOAM namespace"
 
-  ip -netns ioam-node-alpha route change db01::/64 encap ioam6 trace prealloc \
-         type 0x800000 ns 0 size 4 dev veth0
+  [ "$1" = "encap" ] && mode="$1 tundst db01::1" || mode="$1"
+  [ "$1" = "encap" ] && ip -netns ioam-node-beta link set ip6tnl0 up
+
+  ip -netns ioam-node-alpha route change db01::/64 encap ioam6 mode $mode \
+         trace prealloc type 0x800000 ns 0 size 4 dev veth0
 
-  run_test ${FUNCNAME[0]} "${desc}" ioam-node-alpha ioam-node-beta db01::2 \
-         db01::1 veth0 0x800000 0
+  run_test ${FUNCNAME[0]} "${desc} ($1 mode)" ioam-node-alpha ioam-node-beta \
+         db01::2 db01::1 veth0 0x800000 0
+
+  [ "$1" = "encap" ] && ip -netns ioam-node-beta link set ip6tnl0 down
 }
 
 in_no_room()
@@ -525,11 +605,16 @@ in_no_room()
   ##############################################################################
   local desc="Missing trace room"
 
-  ip -netns ioam-node-alpha route change db01::/64 encap ioam6 trace prealloc \
-         type 0xc00000 ns 123 size 4 dev veth0
+  [ "$1" = "encap" ] && mode="$1 tundst db01::1" || mode="$1"
+  [ "$1" = "encap" ] && ip -netns ioam-node-beta link set ip6tnl0 up
+
+  ip -netns ioam-node-alpha route change db01::/64 encap ioam6 mode $mode \
+         trace prealloc type 0xc00000 ns 123 size 4 dev veth0
 
-  run_test ${FUNCNAME[0]} "${desc}" ioam-node-alpha ioam-node-beta db01::2 \
-         db01::1 veth0 0xc00000 123
+  run_test ${FUNCNAME[0]} "${desc} ($1 mode)" ioam-node-alpha ioam-node-beta \
+         db01::2 db01::1 veth0 0xc00000 123
+
+  [ "$1" = "encap" ] && ip -netns ioam-node-beta link set ip6tnl0 down
 }
 
 in_bits()
@@ -544,15 +629,21 @@ in_bits()
   local tmp=${bit2size[22]}
   bit2size[22]=$(( $tmp + ${#BETA[9]} + ((4 - (${#BETA[9]} % 4)) % 4) ))
 
+  [ "$1" = "encap" ] && mode="$1 tundst db01::1" || mode="$1"
+  [ "$1" = "encap" ] && ip -netns ioam-node-beta link set ip6tnl0 up
+
   for i in {0..22}
   do
-    ip -netns ioam-node-alpha route change db01::/64 encap ioam6 trace \
-           prealloc type ${bit2type[$i]} ns 123 size ${bit2size[$i]} dev veth0
+    ip -netns ioam-node-alpha route change db01::/64 encap ioam6 mode $mode \
+           trace prealloc type ${bit2type[$i]} ns 123 size ${bit2size[$i]} \
+           dev veth0
 
-    run_test "in_bit$i" "${desc/<n>/$i}" ioam-node-alpha ioam-node-beta \
-           db01::2 db01::1 veth0 ${bit2type[$i]} 123
+    run_test "in_bit$i" "${desc/<n>/$i} ($1 mode)" ioam-node-alpha \
+           ioam-node-beta db01::2 db01::1 veth0 ${bit2type[$i]} 123
   done
 
+  [ "$1" = "encap" ] && ip -netns ioam-node-beta link set ip6tnl0 down
+
   bit2size[22]=$tmp
 }
 
@@ -569,11 +660,16 @@ in_oflag()
   #   back the IOAM namespace that was previously configured on the sender.
   ip -netns ioam-node-alpha ioam namespace add 123
 
-  ip -netns ioam-node-alpha route change db01::/64 encap ioam6 trace prealloc \
-         type 0xc00000 ns 123 size 4 dev veth0
+  [ "$1" = "encap" ] && mode="$1 tundst db01::1" || mode="$1"
+  [ "$1" = "encap" ] && ip -netns ioam-node-beta link set ip6tnl0 up
+
+  ip -netns ioam-node-alpha route change db01::/64 encap ioam6 mode $mode \
+         trace prealloc type 0xc00000 ns 123 size 4 dev veth0
+
+  run_test ${FUNCNAME[0]} "${desc} ($1 mode)" ioam-node-alpha ioam-node-beta \
+         db01::2 db01::1 veth0 0xc00000 123
 
-  run_test ${FUNCNAME[0]} "${desc}" ioam-node-alpha ioam-node-beta db01::2 \
-         db01::1 veth0 0xc00000 123
+  [ "$1" = "encap" ] && ip -netns ioam-node-beta link set ip6tnl0 down
 
   # And we clean the exception for this test to get things back to normal for
   # other INPUT tests
@@ -588,11 +684,16 @@ in_full_supp_trace()
   ##############################################################################
   local desc="Full supported trace"
 
-  ip -netns ioam-node-alpha route change db01::/64 encap ioam6 trace prealloc \
-         type 0xfff002 ns 123 size 80 dev veth0
+  [ "$1" = "encap" ] && mode="$1 tundst db01::1" || mode="$1"
+  [ "$1" = "encap" ] && ip -netns ioam-node-beta link set ip6tnl0 up
 
-  run_test ${FUNCNAME[0]} "${desc}" ioam-node-alpha ioam-node-beta db01::2 \
-         db01::1 veth0 0xfff002 123
+  ip -netns ioam-node-alpha route change db01::/64 encap ioam6 mode $mode \
+         trace prealloc type 0xfff002 ns 123 size 80 dev veth0
+
+  run_test ${FUNCNAME[0]} "${desc} ($1 mode)" ioam-node-alpha ioam-node-beta \
+         db01::2 db01::1 veth0 0xfff002 123
+
+  [ "$1" = "encap" ] && ip -netns ioam-node-beta link set ip6tnl0 down
 }
 
 
@@ -611,11 +712,16 @@ fwd_full_supp_trace()
   ##############################################################################
   local desc="Forward - Full supported trace"
 
-  ip -netns ioam-node-alpha route change db02::/64 encap ioam6 trace prealloc \
-         type 0xfff002 ns 123 size 244 via db01::1 dev veth0
+  [ "$1" = "encap" ] && mode="$1 tundst db02::2" || mode="$1"
+  [ "$1" = "encap" ] && ip -netns ioam-node-gamma link set ip6tnl0 up
+
+  ip -netns ioam-node-alpha route change db02::/64 encap ioam6 mode $mode \
+         trace prealloc type 0xfff002 ns 123 size 244 via db01::1 dev veth0
 
-  run_test ${FUNCNAME[0]} "${desc}" ioam-node-alpha ioam-node-gamma db01::2 \
-         db02::2 veth0 0xfff002 123
+  run_test ${FUNCNAME[0]} "${desc} ($1 mode)" ioam-node-alpha ioam-node-gamma \
+         db01::2 db02::2 veth0 0xfff002 123
+
+  [ "$1" = "encap" ] && ip -netns ioam-node-gamma link set ip6tnl0 down
 }
 
 
@@ -625,6 +731,9 @@ fwd_full_supp_trace()
 #                                                                              #
 ################################################################################
 
+npassed=0
+nfailed=0
+
 if [ "$(id -u)" -ne 0 ]
 then
   echo "SKIP: Need root privileges"
-- 
cgit v1.2.3


From f614f2c755b6125c646d680d1c990b3b262bd0a9 Mon Sep 17 00:00:00 2001
From: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Date: Sat, 2 Oct 2021 06:47:52 +0530
Subject: tools: Allow specifying base BTF file in resolve_btfids

This commit allows specifying the base BTF for resolving btf id
lists/sets during link time in the resolve_btfids tool. The base BTF is
set to NULL if no path is passed. This allows resolving BTF ids for
module kernel objects.

Also, drop the --no-fail option, as it is only used in case .BTF_ids
section is not present, instead make no-fail the default mode. The long
option name is same as that of pahole.

Signed-off-by: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20211002011757.311265-5-memxor@gmail.com
---
 tools/bpf/resolve_btfids/main.c      | 28 +++++++++++++++++++---------
 tools/testing/selftests/bpf/Makefile |  2 +-
 2 files changed, 20 insertions(+), 10 deletions(-)

(limited to 'tools')

diff --git a/tools/bpf/resolve_btfids/main.c b/tools/bpf/resolve_btfids/main.c
index de6365b53c9c..c6c3e613858a 100644
--- a/tools/bpf/resolve_btfids/main.c
+++ b/tools/bpf/resolve_btfids/main.c
@@ -89,6 +89,7 @@ struct btf_id {
 struct object {
 	const char *path;
 	const char *btf;
+	const char *base_btf_path;
 
 	struct {
 		int		 fd;
@@ -477,16 +478,27 @@ static int symbols_resolve(struct object *obj)
 	int nr_structs  = obj->nr_structs;
 	int nr_unions   = obj->nr_unions;
 	int nr_funcs    = obj->nr_funcs;
+	struct btf *base_btf = NULL;
 	int err, type_id;
 	struct btf *btf;
 	__u32 nr_types;
 
-	btf = btf__parse(obj->btf ?: obj->path, NULL);
+	if (obj->base_btf_path) {
+		base_btf = btf__parse(obj->base_btf_path, NULL);
+		err = libbpf_get_error(base_btf);
+		if (err) {
+			pr_err("FAILED: load base BTF from %s: %s\n",
+			       obj->base_btf_path, strerror(-err));
+			return -1;
+		}
+	}
+
+	btf = btf__parse_split(obj->btf ?: obj->path, base_btf);
 	err = libbpf_get_error(btf);
 	if (err) {
 		pr_err("FAILED: load BTF from %s: %s\n",
 			obj->btf ?: obj->path, strerror(-err));
-		return -1;
+		goto out;
 	}
 
 	err = -1;
@@ -545,6 +557,7 @@ static int symbols_resolve(struct object *obj)
 
 	err = 0;
 out:
+	btf__free(base_btf);
 	btf__free(btf);
 	return err;
 }
@@ -678,7 +691,6 @@ static const char * const resolve_btfids_usage[] = {
 
 int main(int argc, const char **argv)
 {
-	bool no_fail = false;
 	struct object obj = {
 		.efile = {
 			.idlist_shndx  = -1,
@@ -695,8 +707,8 @@ int main(int argc, const char **argv)
 			 "be more verbose (show errors, etc)"),
 		OPT_STRING(0, "btf", &obj.btf, "BTF data",
 			   "BTF data"),
-		OPT_BOOLEAN(0, "no-fail", &no_fail,
-			   "do not fail if " BTF_IDS_SECTION " section is not found"),
+		OPT_STRING('b', "btf_base", &obj.base_btf_path, "file",
+			   "path of file providing base BTF"),
 		OPT_END()
 	};
 	int err = -1;
@@ -717,10 +729,8 @@ int main(int argc, const char **argv)
 	 */
 	if (obj.efile.idlist_shndx == -1 ||
 	    obj.efile.symbols_shndx == -1) {
-		if (no_fail)
-			return 0;
-		pr_err("FAILED to find needed sections\n");
-		return -1;
+		pr_debug("Cannot find .BTF_ids or symbols sections, nothing to do\n");
+		return 0;
 	}
 
 	if (symbols_collect(&obj))
diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index aa94739a1835..5a94d0900d1b 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -454,7 +454,7 @@ $(OUTPUT)/$(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 $(TRUNNER_OUTPUT)/btf_data.o $$@
+	$(Q)$(RESOLVE_BTFIDS) --btf $(TRUNNER_OUTPUT)/btf_data.o $$@
 
 endef
 
-- 
cgit v1.2.3


From 9dbe6015636c19f929a7f7b742f27f303ff6069d Mon Sep 17 00:00:00 2001
From: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Date: Sat, 2 Oct 2021 06:47:54 +0530
Subject: libbpf: Support kernel module function calls

This patch adds libbpf support for kernel module function call support.
The fd_array parameter is used during BPF program load to pass module
BTFs referenced by the program. insn->off is set to index into this
array, but starts from 1, because insn->off as 0 is reserved for
btf_vmlinux.

We try to use existing insn->off for a module, since the kernel limits
the maximum distinct module BTFs for kfuncs to 256, and also because
index must never exceed the maximum allowed value that can fit in
insn->off (INT16_MAX). In the future, if kernel interprets signed offset
as unsigned for kfunc calls, this limit can be increased to UINT16_MAX.

Also introduce a btf__find_by_name_kind_own helper to start searching
from module BTF's start id when we know that the BTF ID is not present
in vmlinux BTF (in find_ksym_btf_id).

Signed-off-by: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20211002011757.311265-7-memxor@gmail.com
---
 tools/lib/bpf/bpf.c             |  1 +
 tools/lib/bpf/btf.c             | 18 ++++++++--
 tools/lib/bpf/libbpf.c          | 74 +++++++++++++++++++++++++++++------------
 tools/lib/bpf/libbpf_internal.h |  3 ++
 4 files changed, 72 insertions(+), 24 deletions(-)

(limited to 'tools')

diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c
index 2401fad090c5..7d1741ceaa32 100644
--- a/tools/lib/bpf/bpf.c
+++ b/tools/lib/bpf/bpf.c
@@ -264,6 +264,7 @@ int libbpf__bpf_prog_load(const struct bpf_prog_load_params *load_attr)
 	attr.line_info_rec_size = load_attr->line_info_rec_size;
 	attr.line_info_cnt = load_attr->line_info_cnt;
 	attr.line_info = ptr_to_u64(load_attr->line_info);
+	attr.fd_array = ptr_to_u64(load_attr->fd_array);
 
 	if (load_attr->name)
 		memcpy(attr.prog_name, load_attr->name,
diff --git a/tools/lib/bpf/btf.c b/tools/lib/bpf/btf.c
index 6ad63e4d418a..7774f99afa6e 100644
--- a/tools/lib/bpf/btf.c
+++ b/tools/lib/bpf/btf.c
@@ -695,15 +695,15 @@ __s32 btf__find_by_name(const struct btf *btf, const char *type_name)
 	return libbpf_err(-ENOENT);
 }
 
-__s32 btf__find_by_name_kind(const struct btf *btf, const char *type_name,
-			     __u32 kind)
+static __s32 btf_find_by_name_kind(const struct btf *btf, int start_id,
+				   const char *type_name, __u32 kind)
 {
 	__u32 i, nr_types = btf__get_nr_types(btf);
 
 	if (kind == BTF_KIND_UNKN || !strcmp(type_name, "void"))
 		return 0;
 
-	for (i = 1; i <= nr_types; i++) {
+	for (i = start_id; i <= nr_types; i++) {
 		const struct btf_type *t = btf__type_by_id(btf, i);
 		const char *name;
 
@@ -717,6 +717,18 @@ __s32 btf__find_by_name_kind(const struct btf *btf, const char *type_name,
 	return libbpf_err(-ENOENT);
 }
 
+__s32 btf__find_by_name_kind_own(const struct btf *btf, const char *type_name,
+				 __u32 kind)
+{
+	return btf_find_by_name_kind(btf, btf->start_id, type_name, kind);
+}
+
+__s32 btf__find_by_name_kind(const struct btf *btf, const char *type_name,
+			     __u32 kind)
+{
+	return btf_find_by_name_kind(btf, 1, type_name, kind);
+}
+
 static bool btf_is_modifiable(const struct btf *btf)
 {
 	return (void *)btf->hdr != btf->raw_data;
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index e23f1b6b9402..ea1c51dbc0f3 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -443,6 +443,11 @@ struct extern_desc {
 
 			/* local btf_id of the ksym extern's type. */
 			__u32 type_id;
+			/* BTF fd index to be patched in for insn->off, this is
+			 * 0 for vmlinux BTF, index in obj->fd_array for module
+			 * BTF
+			 */
+			__s16 btf_fd_idx;
 		} ksym;
 	};
 };
@@ -454,6 +459,7 @@ struct module_btf {
 	char *name;
 	__u32 id;
 	int fd;
+	int fd_array_idx;
 };
 
 struct bpf_object {
@@ -539,6 +545,10 @@ struct bpf_object {
 	void *priv;
 	bpf_object_clear_priv_t clear_priv;
 
+	int *fd_array;
+	size_t fd_array_cap;
+	size_t fd_array_cnt;
+
 	char path[];
 };
 #define obj_elf_valid(o)	((o)->efile.elf)
@@ -5407,6 +5417,7 @@ bpf_object__relocate_data(struct bpf_object *obj, struct bpf_program *prog)
 			ext = &obj->externs[relo->sym_off];
 			insn[0].src_reg = BPF_PSEUDO_KFUNC_CALL;
 			insn[0].imm = ext->ksym.kernel_btf_id;
+			insn[0].off = ext->ksym.btf_fd_idx;
 			break;
 		case RELO_SUBPROG_ADDR:
 			if (insn[0].src_reg != BPF_PSEUDO_FUNC) {
@@ -6236,6 +6247,7 @@ load_program(struct bpf_program *prog, struct bpf_insn *insns, int insns_cnt,
 	}
 	load_attr.log_level = prog->log_level;
 	load_attr.prog_flags = prog->prog_flags;
+	load_attr.fd_array = prog->obj->fd_array;
 
 	/* adjust load_attr if sec_def provides custom preload callback */
 	if (prog->sec_def && prog->sec_def->preload_fn) {
@@ -6752,13 +6764,14 @@ out:
 
 static int find_ksym_btf_id(struct bpf_object *obj, const char *ksym_name,
 			    __u16 kind, struct btf **res_btf,
-			    int *res_btf_fd)
+			    struct module_btf **res_mod_btf)
 {
-	int i, id, btf_fd, err;
+	struct module_btf *mod_btf;
 	struct btf *btf;
+	int i, id, err;
 
 	btf = obj->btf_vmlinux;
-	btf_fd = 0;
+	mod_btf = NULL;
 	id = btf__find_by_name_kind(btf, ksym_name, kind);
 
 	if (id == -ENOENT) {
@@ -6767,10 +6780,10 @@ static int find_ksym_btf_id(struct bpf_object *obj, const char *ksym_name,
 			return err;
 
 		for (i = 0; i < obj->btf_module_cnt; i++) {
-			btf = obj->btf_modules[i].btf;
-			/* we assume module BTF FD is always >0 */
-			btf_fd = obj->btf_modules[i].fd;
-			id = btf__find_by_name_kind(btf, ksym_name, kind);
+			/* we assume module_btf's BTF FD is always >0 */
+			mod_btf = &obj->btf_modules[i];
+			btf = mod_btf->btf;
+			id = btf__find_by_name_kind_own(btf, ksym_name, kind);
 			if (id != -ENOENT)
 				break;
 		}
@@ -6779,7 +6792,7 @@ static int find_ksym_btf_id(struct bpf_object *obj, const char *ksym_name,
 		return -ESRCH;
 
 	*res_btf = btf;
-	*res_btf_fd = btf_fd;
+	*res_mod_btf = mod_btf;
 	return id;
 }
 
@@ -6788,11 +6801,12 @@ static int bpf_object__resolve_ksym_var_btf_id(struct bpf_object *obj,
 {
 	const struct btf_type *targ_var, *targ_type;
 	__u32 targ_type_id, local_type_id;
+	struct module_btf *mod_btf = NULL;
 	const char *targ_var_name;
-	int id, btf_fd = 0, err;
 	struct btf *btf = NULL;
+	int id, err;
 
-	id = find_ksym_btf_id(obj, ext->name, BTF_KIND_VAR, &btf, &btf_fd);
+	id = find_ksym_btf_id(obj, ext->name, BTF_KIND_VAR, &btf, &mod_btf);
 	if (id == -ESRCH && ext->is_weak) {
 		return 0;
 	} else if (id < 0) {
@@ -6827,7 +6841,7 @@ static int bpf_object__resolve_ksym_var_btf_id(struct bpf_object *obj,
 	}
 
 	ext->is_set = true;
-	ext->ksym.kernel_btf_obj_fd = btf_fd;
+	ext->ksym.kernel_btf_obj_fd = mod_btf ? mod_btf->fd : 0;
 	ext->ksym.kernel_btf_id = id;
 	pr_debug("extern (var ksym) '%s': resolved to [%d] %s %s\n",
 		 ext->name, id, btf_kind_str(targ_var), targ_var_name);
@@ -6839,26 +6853,20 @@ static int bpf_object__resolve_ksym_func_btf_id(struct bpf_object *obj,
 						struct extern_desc *ext)
 {
 	int local_func_proto_id, kfunc_proto_id, kfunc_id;
+	struct module_btf *mod_btf = NULL;
 	const struct btf_type *kern_func;
 	struct btf *kern_btf = NULL;
-	int ret, kern_btf_fd = 0;
+	int ret;
 
 	local_func_proto_id = ext->ksym.type_id;
 
-	kfunc_id = find_ksym_btf_id(obj, ext->name, BTF_KIND_FUNC,
-				    &kern_btf, &kern_btf_fd);
+	kfunc_id = find_ksym_btf_id(obj, ext->name, BTF_KIND_FUNC, &kern_btf, &mod_btf);
 	if (kfunc_id < 0) {
 		pr_warn("extern (func ksym) '%s': not found in kernel BTF\n",
 			ext->name);
 		return kfunc_id;
 	}
 
-	if (kern_btf != obj->btf_vmlinux) {
-		pr_warn("extern (func ksym) '%s': function in kernel module is not supported\n",
-			ext->name);
-		return -ENOTSUP;
-	}
-
 	kern_func = btf__type_by_id(kern_btf, kfunc_id);
 	kfunc_proto_id = kern_func->type;
 
@@ -6870,9 +6878,30 @@ static int bpf_object__resolve_ksym_func_btf_id(struct bpf_object *obj,
 		return -EINVAL;
 	}
 
+	/* set index for module BTF fd in fd_array, if unset */
+	if (mod_btf && !mod_btf->fd_array_idx) {
+		/* insn->off is s16 */
+		if (obj->fd_array_cnt == INT16_MAX) {
+			pr_warn("extern (func ksym) '%s': module BTF fd index %d too big to fit in bpf_insn offset\n",
+				ext->name, mod_btf->fd_array_idx);
+			return -E2BIG;
+		}
+		/* Cannot use index 0 for module BTF fd */
+		if (!obj->fd_array_cnt)
+			obj->fd_array_cnt = 1;
+
+		ret = libbpf_ensure_mem((void **)&obj->fd_array, &obj->fd_array_cap, sizeof(int),
+					obj->fd_array_cnt + 1);
+		if (ret)
+			return ret;
+		mod_btf->fd_array_idx = obj->fd_array_cnt;
+		/* we assume module BTF FD is always >0 */
+		obj->fd_array[obj->fd_array_cnt++] = mod_btf->fd;
+	}
+
 	ext->is_set = true;
-	ext->ksym.kernel_btf_obj_fd = kern_btf_fd;
 	ext->ksym.kernel_btf_id = kfunc_id;
+	ext->ksym.btf_fd_idx = mod_btf ? mod_btf->fd_array_idx : 0;
 	pr_debug("extern (func ksym) '%s': resolved to kernel [%d]\n",
 		 ext->name, kfunc_id);
 
@@ -7031,6 +7060,9 @@ int bpf_object__load_xattr(struct bpf_object_load_attr *attr)
 			err = bpf_gen__finish(obj->gen_loader);
 	}
 
+	/* clean up fd_array */
+	zfree(&obj->fd_array);
+
 	/* clean up module BTFs */
 	for (i = 0; i < obj->btf_module_cnt; i++) {
 		close(obj->btf_modules[i].fd);
diff --git a/tools/lib/bpf/libbpf_internal.h b/tools/lib/bpf/libbpf_internal.h
index ec79400517d4..f7fd3944d46d 100644
--- a/tools/lib/bpf/libbpf_internal.h
+++ b/tools/lib/bpf/libbpf_internal.h
@@ -298,6 +298,7 @@ struct bpf_prog_load_params {
 	__u32 log_level;
 	char *log_buf;
 	size_t log_buf_sz;
+	int *fd_array;
 };
 
 int libbpf__bpf_prog_load(const struct bpf_prog_load_params *load_attr);
@@ -408,6 +409,8 @@ int btf_type_visit_type_ids(struct btf_type *t, type_id_visit_fn visit, void *ct
 int btf_type_visit_str_offs(struct btf_type *t, str_off_visit_fn visit, void *ctx);
 int btf_ext_visit_type_ids(struct btf_ext *btf_ext, type_id_visit_fn visit, void *ctx);
 int btf_ext_visit_str_offs(struct btf_ext *btf_ext, str_off_visit_fn visit, void *ctx);
+__s32 btf__find_by_name_kind_own(const struct btf *btf, const char *type_name,
+				 __u32 kind);
 
 extern enum libbpf_strict_mode libbpf_mode;
 
-- 
cgit v1.2.3


From 466b2e13971ef65cd7b621ca3044be14028b002b Mon Sep 17 00:00:00 2001
From: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Date: Sat, 2 Oct 2021 06:47:55 +0530
Subject: libbpf: Resolve invalid weak kfunc calls with imm = 0, off = 0

Preserve these calls as it allows verifier to succeed in loading the
program if they are determined to be unreachable after dead code
elimination during program load. If not, the verifier will fail at
runtime. This is done for ext->is_weak symbols similar to the case for
variable ksyms.

Signed-off-by: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20211002011757.311265-8-memxor@gmail.com
---
 tools/lib/bpf/libbpf.c | 24 +++++++++++++-----------
 1 file changed, 13 insertions(+), 11 deletions(-)

(limited to 'tools')

diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index ea1c51dbc0f3..092cf4bd1879 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -3439,11 +3439,6 @@ static int bpf_object__collect_externs(struct bpf_object *obj)
 				return -ENOTSUP;
 			}
 		} else if (strcmp(sec_name, KSYMS_SEC) == 0) {
-			if (btf_is_func(t) && ext->is_weak) {
-				pr_warn("extern weak function %s is unsupported\n",
-					ext->name);
-				return -ENOTSUP;
-			}
 			ksym_sec = sec;
 			ext->type = EXT_KSYM;
 			skip_mods_and_typedefs(obj->btf, t->type,
@@ -5416,8 +5411,13 @@ bpf_object__relocate_data(struct bpf_object *obj, struct bpf_program *prog)
 		case RELO_EXTERN_FUNC:
 			ext = &obj->externs[relo->sym_off];
 			insn[0].src_reg = BPF_PSEUDO_KFUNC_CALL;
-			insn[0].imm = ext->ksym.kernel_btf_id;
-			insn[0].off = ext->ksym.btf_fd_idx;
+			if (ext->is_set) {
+				insn[0].imm = ext->ksym.kernel_btf_id;
+				insn[0].off = ext->ksym.btf_fd_idx;
+			} else { /* unresolved weak kfunc */
+				insn[0].imm = 0;
+				insn[0].off = 0;
+			}
 			break;
 		case RELO_SUBPROG_ADDR:
 			if (insn[0].src_reg != BPF_PSEUDO_FUNC) {
@@ -6807,9 +6807,9 @@ static int bpf_object__resolve_ksym_var_btf_id(struct bpf_object *obj,
 	int id, err;
 
 	id = find_ksym_btf_id(obj, ext->name, BTF_KIND_VAR, &btf, &mod_btf);
-	if (id == -ESRCH && ext->is_weak) {
-		return 0;
-	} else if (id < 0) {
+	if (id < 0) {
+		if (id == -ESRCH && ext->is_weak)
+			return 0;
 		pr_warn("extern (var ksym) '%s': not found in kernel BTF\n",
 			ext->name);
 		return id;
@@ -6862,7 +6862,9 @@ static int bpf_object__resolve_ksym_func_btf_id(struct bpf_object *obj,
 
 	kfunc_id = find_ksym_btf_id(obj, ext->name, BTF_KIND_FUNC, &kern_btf, &mod_btf);
 	if (kfunc_id < 0) {
-		pr_warn("extern (func ksym) '%s': not found in kernel BTF\n",
+		if (kfunc_id == -ESRCH && ext->is_weak)
+			return 0;
+		pr_warn("extern (func ksym) '%s': not found in kernel or module BTFs\n",
 			ext->name);
 		return kfunc_id;
 	}
-- 
cgit v1.2.3


From 18f4fccbf314fdb07d276f4cd3eaf53f1825550d Mon Sep 17 00:00:00 2001
From: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Date: Sat, 2 Oct 2021 06:47:56 +0530
Subject: libbpf: Update gen_loader to emit BTF_KIND_FUNC relocations

This change updates the BPF syscall loader to relocate BTF_KIND_FUNC
relocations, with support for weak kfunc relocations. The general idea
is to move map_fds to loader map, and also use the data for storing
kfunc BTF fds. Since both reuse the fd_array parameter, they need to be
kept together.

For map_fds, we reserve MAX_USED_MAPS slots in a region, and for kfunc,
we reserve MAX_KFUNC_DESCS. This is done so that insn->off has more
chances of being <= INT16_MAX than treating data map as a sparse array
and adding fd as needed.

When the MAX_KFUNC_DESCS limit is reached, we fall back to the sparse
array model, so that as long as it does remain <= INT16_MAX, we pass an
index relative to the start of fd_array.

We store all ksyms in an array where we try to avoid calling the
bpf_btf_find_by_name_kind helper, and also reuse the BTF fd that was
already stored. This also speeds up the loading process compared to
emitting calls in all cases, in later tests.

Signed-off-by: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20211002011757.311265-9-memxor@gmail.com
---
 tools/lib/bpf/bpf_gen_internal.h |  16 +-
 tools/lib/bpf/gen_loader.c       | 314 ++++++++++++++++++++++++++++++++-------
 tools/lib/bpf/libbpf.c           |   8 +-
 3 files changed, 280 insertions(+), 58 deletions(-)

(limited to 'tools')

diff --git a/tools/lib/bpf/bpf_gen_internal.h b/tools/lib/bpf/bpf_gen_internal.h
index 615400391e57..70eccbffefb1 100644
--- a/tools/lib/bpf/bpf_gen_internal.h
+++ b/tools/lib/bpf/bpf_gen_internal.h
@@ -7,6 +7,15 @@ struct ksym_relo_desc {
 	const char *name;
 	int kind;
 	int insn_idx;
+	bool is_weak;
+};
+
+struct ksym_desc {
+	const char *name;
+	int ref;
+	int kind;
+	int off;
+	int insn;
 };
 
 struct bpf_gen {
@@ -24,6 +33,10 @@ struct bpf_gen {
 	int relo_cnt;
 	char attach_target[128];
 	int attach_kind;
+	struct ksym_desc *ksyms;
+	__u32 nr_ksyms;
+	int fd_array;
+	int nr_fd_array;
 };
 
 void bpf_gen__init(struct bpf_gen *gen, int log_level);
@@ -36,6 +49,7 @@ void bpf_gen__prog_load(struct bpf_gen *gen, struct bpf_prog_load_params *load_a
 void bpf_gen__map_update_elem(struct bpf_gen *gen, int map_idx, void *value, __u32 value_size);
 void bpf_gen__map_freeze(struct bpf_gen *gen, int map_idx);
 void bpf_gen__record_attach_target(struct bpf_gen *gen, const char *name, enum bpf_attach_type type);
-void bpf_gen__record_extern(struct bpf_gen *gen, const char *name, int kind, int insn_idx);
+void bpf_gen__record_extern(struct bpf_gen *gen, const char *name, bool is_weak, int kind,
+			    int insn_idx);
 
 #endif
diff --git a/tools/lib/bpf/gen_loader.c b/tools/lib/bpf/gen_loader.c
index 80087b13877f..937bfc7db41e 100644
--- a/tools/lib/bpf/gen_loader.c
+++ b/tools/lib/bpf/gen_loader.c
@@ -14,8 +14,10 @@
 #include "bpf_gen_internal.h"
 #include "skel_internal.h"
 
-#define MAX_USED_MAPS 64
-#define MAX_USED_PROGS 32
+#define MAX_USED_MAPS	64
+#define MAX_USED_PROGS	32
+#define MAX_KFUNC_DESCS 256
+#define MAX_FD_ARRAY_SZ (MAX_USED_PROGS + MAX_KFUNC_DESCS)
 
 /* The following structure describes the stack layout of the loader program.
  * In addition R6 contains the pointer to context.
@@ -30,7 +32,6 @@
  */
 struct loader_stack {
 	__u32 btf_fd;
-	__u32 map_fd[MAX_USED_MAPS];
 	__u32 prog_fd[MAX_USED_PROGS];
 	__u32 inner_map_fd;
 };
@@ -143,13 +144,49 @@ static int add_data(struct bpf_gen *gen, const void *data, __u32 size)
 	if (realloc_data_buf(gen, size8))
 		return 0;
 	prev = gen->data_cur;
-	memcpy(gen->data_cur, data, size);
-	gen->data_cur += size;
-	memcpy(gen->data_cur, &zero, size8 - size);
-	gen->data_cur += size8 - size;
+	if (data) {
+		memcpy(gen->data_cur, data, size);
+		memcpy(gen->data_cur + size, &zero, size8 - size);
+	} else {
+		memset(gen->data_cur, 0, size8);
+	}
+	gen->data_cur += size8;
 	return prev - gen->data_start;
 }
 
+/* Get index for map_fd/btf_fd slot in reserved fd_array, or in data relative
+ * to start of fd_array. Caller can decide if it is usable or not.
+ */
+static int add_map_fd(struct bpf_gen *gen)
+{
+	if (!gen->fd_array)
+		gen->fd_array = add_data(gen, NULL, MAX_FD_ARRAY_SZ * sizeof(int));
+	if (gen->nr_maps == MAX_USED_MAPS) {
+		pr_warn("Total maps exceeds %d\n", MAX_USED_MAPS);
+		gen->error = -E2BIG;
+		return 0;
+	}
+	return gen->nr_maps++;
+}
+
+static int add_kfunc_btf_fd(struct bpf_gen *gen)
+{
+	int cur;
+
+	if (!gen->fd_array)
+		gen->fd_array = add_data(gen, NULL, MAX_FD_ARRAY_SZ * sizeof(int));
+	if (gen->nr_fd_array == MAX_KFUNC_DESCS) {
+		cur = add_data(gen, NULL, sizeof(int));
+		return (cur - gen->fd_array) / sizeof(int);
+	}
+	return MAX_USED_MAPS + gen->nr_fd_array++;
+}
+
+static int blob_fd_array_off(struct bpf_gen *gen, int index)
+{
+	return gen->fd_array + index * sizeof(int);
+}
+
 static int insn_bytes_to_bpf_size(__u32 sz)
 {
 	switch (sz) {
@@ -171,14 +208,22 @@ static void emit_rel_store(struct bpf_gen *gen, int off, int data)
 	emit(gen, BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_0, 0));
 }
 
-/* *(u64 *)(blob + off) = (u64)(void *)(%sp + stack_off) */
-static void emit_rel_store_sp(struct bpf_gen *gen, int off, int stack_off)
+static void move_blob2blob(struct bpf_gen *gen, int off, int size, int blob_off)
 {
-	emit(gen, BPF_MOV64_REG(BPF_REG_0, BPF_REG_10));
-	emit(gen, BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, stack_off));
+	emit2(gen, BPF_LD_IMM64_RAW_FULL(BPF_REG_2, BPF_PSEUDO_MAP_IDX_VALUE,
+					 0, 0, 0, blob_off));
+	emit(gen, BPF_LDX_MEM(insn_bytes_to_bpf_size(size), BPF_REG_0, BPF_REG_2, 0));
 	emit2(gen, BPF_LD_IMM64_RAW_FULL(BPF_REG_1, BPF_PSEUDO_MAP_IDX_VALUE,
 					 0, 0, 0, off));
-	emit(gen, BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_0, 0));
+	emit(gen, BPF_STX_MEM(insn_bytes_to_bpf_size(size), BPF_REG_1, BPF_REG_0, 0));
+}
+
+static void move_blob2ctx(struct bpf_gen *gen, int ctx_off, int size, int blob_off)
+{
+	emit2(gen, BPF_LD_IMM64_RAW_FULL(BPF_REG_1, BPF_PSEUDO_MAP_IDX_VALUE,
+					 0, 0, 0, blob_off));
+	emit(gen, BPF_LDX_MEM(insn_bytes_to_bpf_size(size), BPF_REG_0, BPF_REG_1, 0));
+	emit(gen, BPF_STX_MEM(insn_bytes_to_bpf_size(size), BPF_REG_6, BPF_REG_0, ctx_off));
 }
 
 static void move_ctx2blob(struct bpf_gen *gen, int off, int size, int ctx_off,
@@ -326,11 +371,11 @@ int bpf_gen__finish(struct bpf_gen *gen)
 			       offsetof(struct bpf_prog_desc, prog_fd), 4,
 			       stack_off(prog_fd[i]));
 	for (i = 0; i < gen->nr_maps; i++)
-		move_stack2ctx(gen,
-			       sizeof(struct bpf_loader_ctx) +
-			       sizeof(struct bpf_map_desc) * i +
-			       offsetof(struct bpf_map_desc, map_fd), 4,
-			       stack_off(map_fd[i]));
+		move_blob2ctx(gen,
+			      sizeof(struct bpf_loader_ctx) +
+			      sizeof(struct bpf_map_desc) * i +
+			      offsetof(struct bpf_map_desc, map_fd), 4,
+			      blob_fd_array_off(gen, i));
 	emit(gen, BPF_MOV64_IMM(BPF_REG_0, 0));
 	emit(gen, BPF_EXIT_INSN());
 	pr_debug("gen: finish %d\n", gen->error);
@@ -390,7 +435,7 @@ void bpf_gen__map_create(struct bpf_gen *gen,
 {
 	int attr_size = offsetofend(union bpf_attr, btf_vmlinux_value_type_id);
 	bool close_inner_map_fd = false;
-	int map_create_attr;
+	int map_create_attr, idx;
 	union bpf_attr attr;
 
 	memset(&attr, 0, attr_size);
@@ -467,9 +512,11 @@ void bpf_gen__map_create(struct bpf_gen *gen,
 		gen->error = -EDOM; /* internal bug */
 		return;
 	} else {
-		emit(gen, BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_7,
-				      stack_off(map_fd[map_idx])));
-		gen->nr_maps++;
+		/* add_map_fd does gen->nr_maps++ */
+		idx = add_map_fd(gen);
+		emit2(gen, BPF_LD_IMM64_RAW_FULL(BPF_REG_1, BPF_PSEUDO_MAP_IDX_VALUE,
+						 0, 0, 0, blob_fd_array_off(gen, idx)));
+		emit(gen, BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_7, 0));
 	}
 	if (close_inner_map_fd)
 		emit_sys_close_stack(gen, stack_off(inner_map_fd));
@@ -511,8 +558,8 @@ static void emit_find_attach_target(struct bpf_gen *gen)
 	 */
 }
 
-void bpf_gen__record_extern(struct bpf_gen *gen, const char *name, int kind,
-			    int insn_idx)
+void bpf_gen__record_extern(struct bpf_gen *gen, const char *name, bool is_weak,
+			    int kind, int insn_idx)
 {
 	struct ksym_relo_desc *relo;
 
@@ -524,38 +571,192 @@ void bpf_gen__record_extern(struct bpf_gen *gen, const char *name, int kind,
 	gen->relos = relo;
 	relo += gen->relo_cnt;
 	relo->name = name;
+	relo->is_weak = is_weak;
 	relo->kind = kind;
 	relo->insn_idx = insn_idx;
 	gen->relo_cnt++;
 }
 
-static void emit_relo(struct bpf_gen *gen, struct ksym_relo_desc *relo, int insns)
+/* returns existing ksym_desc with ref incremented, or inserts a new one */
+static struct ksym_desc *get_ksym_desc(struct bpf_gen *gen, struct ksym_relo_desc *relo)
 {
-	int name, insn, len = strlen(relo->name) + 1;
+	struct ksym_desc *kdesc;
 
-	pr_debug("gen: emit_relo: %s at %d\n", relo->name, relo->insn_idx);
-	name = add_data(gen, relo->name, len);
+	for (int i = 0; i < gen->nr_ksyms; i++) {
+		if (!strcmp(gen->ksyms[i].name, relo->name)) {
+			gen->ksyms[i].ref++;
+			return &gen->ksyms[i];
+		}
+	}
+	kdesc = libbpf_reallocarray(gen->ksyms, gen->nr_ksyms + 1, sizeof(*kdesc));
+	if (!kdesc) {
+		gen->error = -ENOMEM;
+		return NULL;
+	}
+	gen->ksyms = kdesc;
+	kdesc = &gen->ksyms[gen->nr_ksyms++];
+	kdesc->name = relo->name;
+	kdesc->kind = relo->kind;
+	kdesc->ref = 1;
+	kdesc->off = 0;
+	kdesc->insn = 0;
+	return kdesc;
+}
+
+/* Overwrites BPF_REG_{0, 1, 2, 3, 4, 7}
+ * Returns result in BPF_REG_7
+ */
+static void emit_bpf_find_by_name_kind(struct bpf_gen *gen, struct ksym_relo_desc *relo)
+{
+	int name_off, len = strlen(relo->name) + 1;
 
+	name_off = add_data(gen, relo->name, len);
 	emit2(gen, BPF_LD_IMM64_RAW_FULL(BPF_REG_1, BPF_PSEUDO_MAP_IDX_VALUE,
-					 0, 0, 0, name));
+					 0, 0, 0, name_off));
 	emit(gen, BPF_MOV64_IMM(BPF_REG_2, len));
 	emit(gen, BPF_MOV64_IMM(BPF_REG_3, relo->kind));
 	emit(gen, BPF_MOV64_IMM(BPF_REG_4, 0));
 	emit(gen, BPF_EMIT_CALL(BPF_FUNC_btf_find_by_name_kind));
 	emit(gen, BPF_MOV64_REG(BPF_REG_7, BPF_REG_0));
 	debug_ret(gen, "find_by_name_kind(%s,%d)", relo->name, relo->kind);
-	emit_check_err(gen);
+}
+
+/* Expects:
+ * BPF_REG_8 - pointer to instruction
+ *
+ * We need to reuse BTF fd for same symbol otherwise each relocation takes a new
+ * index, while kernel limits total kfunc BTFs to 256. For duplicate symbols,
+ * this would mean a new BTF fd index for each entry. By pairing symbol name
+ * with index, we get the insn->imm, insn->off pairing that kernel uses for
+ * kfunc_tab, which becomes the effective limit even though all of them may
+ * share same index in fd_array (such that kfunc_btf_tab has 1 element).
+ */
+static void emit_relo_kfunc_btf(struct bpf_gen *gen, struct ksym_relo_desc *relo, int insn)
+{
+	struct ksym_desc *kdesc;
+	int btf_fd_idx;
+
+	kdesc = get_ksym_desc(gen, relo);
+	if (!kdesc)
+		return;
+	/* try to copy from existing bpf_insn */
+	if (kdesc->ref > 1) {
+		move_blob2blob(gen, insn + offsetof(struct bpf_insn, imm), 4,
+			       kdesc->insn + offsetof(struct bpf_insn, imm));
+		move_blob2blob(gen, insn + offsetof(struct bpf_insn, off), 2,
+			       kdesc->insn + offsetof(struct bpf_insn, off));
+		goto log;
+	}
+	/* remember insn offset, so we can copy BTF ID and FD later */
+	kdesc->insn = insn;
+	emit_bpf_find_by_name_kind(gen, relo);
+	if (!relo->is_weak)
+		emit_check_err(gen);
+	/* get index in fd_array to store BTF FD at */
+	btf_fd_idx = add_kfunc_btf_fd(gen);
+	if (btf_fd_idx > INT16_MAX) {
+		pr_warn("BTF fd off %d for kfunc %s exceeds INT16_MAX, cannot process relocation\n",
+			btf_fd_idx, relo->name);
+		gen->error = -E2BIG;
+		return;
+	}
+	kdesc->off = btf_fd_idx;
+	/* set a default value for imm */
+	emit(gen, BPF_ST_MEM(BPF_W, BPF_REG_8, offsetof(struct bpf_insn, imm), 0));
+	/* skip success case store if ret < 0 */
+	emit(gen, BPF_JMP_IMM(BPF_JSLT, BPF_REG_7, 0, 1));
 	/* store btf_id into insn[insn_idx].imm */
-	insn = insns + sizeof(struct bpf_insn) * relo->insn_idx +
-		offsetof(struct bpf_insn, imm);
+	emit(gen, BPF_STX_MEM(BPF_W, BPF_REG_8, BPF_REG_7, offsetof(struct bpf_insn, imm)));
+	/* load fd_array slot pointer */
 	emit2(gen, BPF_LD_IMM64_RAW_FULL(BPF_REG_0, BPF_PSEUDO_MAP_IDX_VALUE,
-					 0, 0, 0, insn));
-	emit(gen, BPF_STX_MEM(BPF_W, BPF_REG_0, BPF_REG_7, 0));
-	if (relo->kind == BTF_KIND_VAR) {
-		/* store btf_obj_fd into insn[insn_idx + 1].imm */
-		emit(gen, BPF_ALU64_IMM(BPF_RSH, BPF_REG_7, 32));
-		emit(gen, BPF_STX_MEM(BPF_W, BPF_REG_0, BPF_REG_7,
-				      sizeof(struct bpf_insn)));
+					 0, 0, 0, blob_fd_array_off(gen, btf_fd_idx)));
+	/* skip store of BTF fd if ret < 0 */
+	emit(gen, BPF_JMP_IMM(BPF_JSLT, BPF_REG_7, 0, 3));
+	/* store BTF fd in slot */
+	emit(gen, BPF_MOV64_REG(BPF_REG_9, BPF_REG_7));
+	emit(gen, BPF_ALU64_IMM(BPF_RSH, BPF_REG_9, 32));
+	emit(gen, BPF_STX_MEM(BPF_W, BPF_REG_0, BPF_REG_9, 0));
+	/* set a default value for off */
+	emit(gen, BPF_ST_MEM(BPF_H, BPF_REG_8, offsetof(struct bpf_insn, off), 0));
+	/* skip insn->off store if ret < 0 */
+	emit(gen, BPF_JMP_IMM(BPF_JSLT, BPF_REG_7, 0, 2));
+	/* skip if vmlinux BTF */
+	emit(gen, BPF_JMP_IMM(BPF_JEQ, BPF_REG_9, 0, 1));
+	/* store index into insn[insn_idx].off */
+	emit(gen, BPF_ST_MEM(BPF_H, BPF_REG_8, offsetof(struct bpf_insn, off), btf_fd_idx));
+log:
+	if (!gen->log_level)
+		return;
+	emit(gen, BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_8,
+			      offsetof(struct bpf_insn, imm)));
+	emit(gen, BPF_LDX_MEM(BPF_H, BPF_REG_9, BPF_REG_8,
+			      offsetof(struct bpf_insn, off)));
+	debug_regs(gen, BPF_REG_7, BPF_REG_9, " func (%s:count=%d): imm: %%d, off: %%d",
+		   relo->name, kdesc->ref);
+	emit2(gen, BPF_LD_IMM64_RAW_FULL(BPF_REG_0, BPF_PSEUDO_MAP_IDX_VALUE,
+					 0, 0, 0, blob_fd_array_off(gen, kdesc->off)));
+	emit(gen, BPF_LDX_MEM(BPF_W, BPF_REG_9, BPF_REG_0, 0));
+	debug_regs(gen, BPF_REG_9, -1, " func (%s:count=%d): btf_fd",
+		   relo->name, kdesc->ref);
+}
+
+/* Expects:
+ * BPF_REG_8 - pointer to instruction
+ */
+static void emit_relo_ksym_btf(struct bpf_gen *gen, struct ksym_relo_desc *relo, int insn)
+{
+	struct ksym_desc *kdesc;
+
+	kdesc = get_ksym_desc(gen, relo);
+	if (!kdesc)
+		return;
+	/* try to copy from existing ldimm64 insn */
+	if (kdesc->ref > 1) {
+		move_blob2blob(gen, insn + offsetof(struct bpf_insn, imm), 4,
+			       kdesc->insn + offsetof(struct bpf_insn, imm));
+		move_blob2blob(gen, insn + sizeof(struct bpf_insn) + offsetof(struct bpf_insn, imm), 4,
+			       kdesc->insn + sizeof(struct bpf_insn) + offsetof(struct bpf_insn, imm));
+		goto log;
+	}
+	/* remember insn offset, so we can copy BTF ID and FD later */
+	kdesc->insn = insn;
+	emit_bpf_find_by_name_kind(gen, relo);
+	emit_check_err(gen);
+	/* store btf_id into insn[insn_idx].imm */
+	emit(gen, BPF_STX_MEM(BPF_W, BPF_REG_8, BPF_REG_7, offsetof(struct bpf_insn, imm)));
+	/* store btf_obj_fd into insn[insn_idx + 1].imm */
+	emit(gen, BPF_ALU64_IMM(BPF_RSH, BPF_REG_7, 32));
+	emit(gen, BPF_STX_MEM(BPF_W, BPF_REG_8, BPF_REG_7,
+			      sizeof(struct bpf_insn) + offsetof(struct bpf_insn, imm)));
+log:
+	if (!gen->log_level)
+		return;
+	emit(gen, BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_8,
+			      offsetof(struct bpf_insn, imm)));
+	emit(gen, BPF_LDX_MEM(BPF_H, BPF_REG_9, BPF_REG_8, sizeof(struct bpf_insn) +
+			      offsetof(struct bpf_insn, imm)));
+	debug_regs(gen, BPF_REG_7, BPF_REG_9, " var (%s:count=%d): imm: %%d, fd: %%d",
+		   relo->name, kdesc->ref);
+}
+
+static void emit_relo(struct bpf_gen *gen, struct ksym_relo_desc *relo, int insns)
+{
+	int insn;
+
+	pr_debug("gen: emit_relo (%d): %s at %d\n", relo->kind, relo->name, relo->insn_idx);
+	insn = insns + sizeof(struct bpf_insn) * relo->insn_idx;
+	emit2(gen, BPF_LD_IMM64_RAW_FULL(BPF_REG_8, BPF_PSEUDO_MAP_IDX_VALUE, 0, 0, 0, insn));
+	switch (relo->kind) {
+	case BTF_KIND_VAR:
+		emit_relo_ksym_btf(gen, relo, insn);
+		break;
+	case BTF_KIND_FUNC:
+		emit_relo_kfunc_btf(gen, relo, insn);
+		break;
+	default:
+		pr_warn("Unknown relocation kind '%d'\n", relo->kind);
+		gen->error = -EDOM;
+		return;
 	}
 }
 
@@ -571,14 +772,22 @@ static void cleanup_relos(struct bpf_gen *gen, int insns)
 {
 	int i, insn;
 
-	for (i = 0; i < gen->relo_cnt; i++) {
-		if (gen->relos[i].kind != BTF_KIND_VAR)
-			continue;
-		/* close fd recorded in insn[insn_idx + 1].imm */
-		insn = insns +
-			sizeof(struct bpf_insn) * (gen->relos[i].insn_idx + 1) +
-			offsetof(struct bpf_insn, imm);
-		emit_sys_close_blob(gen, insn);
+	for (i = 0; i < gen->nr_ksyms; i++) {
+		if (gen->ksyms[i].kind == BTF_KIND_VAR) {
+			/* close fd recorded in insn[insn_idx + 1].imm */
+			insn = gen->ksyms[i].insn;
+			insn += sizeof(struct bpf_insn) + offsetof(struct bpf_insn, imm);
+			emit_sys_close_blob(gen, insn);
+		} else { /* BTF_KIND_FUNC */
+			emit_sys_close_blob(gen, blob_fd_array_off(gen, gen->ksyms[i].off));
+			if (gen->ksyms[i].off < MAX_FD_ARRAY_SZ)
+				gen->nr_fd_array--;
+		}
+	}
+	if (gen->nr_ksyms) {
+		free(gen->ksyms);
+		gen->nr_ksyms = 0;
+		gen->ksyms = NULL;
 	}
 	if (gen->relo_cnt) {
 		free(gen->relos);
@@ -637,9 +846,8 @@ void bpf_gen__prog_load(struct bpf_gen *gen,
 	/* populate union bpf_attr with a pointer to line_info */
 	emit_rel_store(gen, attr_field(prog_load_attr, line_info), line_info);
 
-	/* populate union bpf_attr fd_array with a pointer to stack where map_fds are saved */
-	emit_rel_store_sp(gen, attr_field(prog_load_attr, fd_array),
-			  stack_off(map_fd[0]));
+	/* populate union bpf_attr fd_array with a pointer to data where map_fds are saved */
+	emit_rel_store(gen, attr_field(prog_load_attr, fd_array), gen->fd_array);
 
 	/* populate union bpf_attr with user provided log details */
 	move_ctx2blob(gen, attr_field(prog_load_attr, log_level), 4,
@@ -706,8 +914,8 @@ void bpf_gen__map_update_elem(struct bpf_gen *gen, int map_idx, void *pvalue,
 	emit(gen, BPF_EMIT_CALL(BPF_FUNC_copy_from_user));
 
 	map_update_attr = add_data(gen, &attr, attr_size);
-	move_stack2blob(gen, attr_field(map_update_attr, map_fd), 4,
-			stack_off(map_fd[map_idx]));
+	move_blob2blob(gen, attr_field(map_update_attr, map_fd), 4,
+		       blob_fd_array_off(gen, map_idx));
 	emit_rel_store(gen, attr_field(map_update_attr, key), key);
 	emit_rel_store(gen, attr_field(map_update_attr, value), value);
 	/* emit MAP_UPDATE_ELEM command */
@@ -725,8 +933,8 @@ void bpf_gen__map_freeze(struct bpf_gen *gen, int map_idx)
 	memset(&attr, 0, attr_size);
 	pr_debug("gen: map_freeze: idx %d\n", map_idx);
 	map_freeze_attr = add_data(gen, &attr, attr_size);
-	move_stack2blob(gen, attr_field(map_freeze_attr, map_fd), 4,
-			stack_off(map_fd[map_idx]));
+	move_blob2blob(gen, attr_field(map_freeze_attr, map_fd), 4,
+		       blob_fd_array_off(gen, map_idx));
 	/* emit MAP_FREEZE command */
 	emit_sys_bpf(gen, BPF_MAP_FREEZE, map_freeze_attr, attr_size);
 	debug_ret(gen, "map_freeze");
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 092cf4bd1879..f32fa51b1e63 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -6360,12 +6360,12 @@ static int bpf_program__record_externs(struct bpf_program *prog)
 					ext->name);
 				return -ENOTSUP;
 			}
-			bpf_gen__record_extern(obj->gen_loader, ext->name, BTF_KIND_VAR,
-					       relo->insn_idx);
+			bpf_gen__record_extern(obj->gen_loader, ext->name, ext->is_weak,
+					       BTF_KIND_VAR, relo->insn_idx);
 			break;
 		case RELO_EXTERN_FUNC:
-			bpf_gen__record_extern(obj->gen_loader, ext->name, BTF_KIND_FUNC,
-					       relo->insn_idx);
+			bpf_gen__record_extern(obj->gen_loader, ext->name, ext->is_weak,
+					       BTF_KIND_FUNC, relo->insn_idx);
 			break;
 		default:
 			continue;
-- 
cgit v1.2.3


From c48e51c8b07aba8a18125221cb67a40cb1256bf2 Mon Sep 17 00:00:00 2001
From: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Date: Sat, 2 Oct 2021 06:47:57 +0530
Subject: bpf: selftests: Add selftests for module kfunc support

This adds selftests that tests the success and failure path for modules
kfuncs (in presence of invalid kfunc calls) for both libbpf and
gen_loader. It also adds a prog_test kfunc_btf_id_list so that we can
add module BTF ID set from bpf_testmod.

This also introduces  a couple of test cases to verifier selftests for
validating whether we get an error or not depending on if invalid kfunc
call remains after elimination of unreachable instructions.

Signed-off-by: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20211002011757.311265-10-memxor@gmail.com
---
 tools/testing/selftests/bpf/Makefile               |  7 ++--
 .../selftests/bpf/bpf_testmod/bpf_testmod.c        | 23 ++++++++++-
 .../selftests/bpf/prog_tests/ksyms_module.c        | 29 +++++++-------
 .../selftests/bpf/prog_tests/ksyms_module_libbpf.c | 28 +++++++++++++
 .../selftests/bpf/progs/test_ksyms_module.c        | 46 ++++++++++++++++------
 tools/testing/selftests/bpf/verifier/calls.c       | 23 +++++++++++
 6 files changed, 126 insertions(+), 30 deletions(-)
 create mode 100644 tools/testing/selftests/bpf/prog_tests/ksyms_module_libbpf.c

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index 5a94d0900d1b..c5c9a9f50d8d 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -315,8 +315,9 @@ LINKED_SKELS := test_static_linked.skel.h linked_funcs.skel.h		\
 		linked_vars.skel.h linked_maps.skel.h
 
 LSKELS := kfunc_call_test.c fentry_test.c fexit_test.c fexit_sleep.c \
-	test_ksyms_module.c test_ringbuf.c atomics.c trace_printk.c \
-	trace_vprintk.c
+	test_ringbuf.c atomics.c trace_printk.c trace_vprintk.c
+# Generate both light skeleton and libbpf skeleton for these
+LSKELS_EXTRA := test_ksyms_module.c
 SKEL_BLACKLIST += $$(LSKELS)
 
 test_static_linked.skel.h-deps := test_static_linked1.o test_static_linked2.o
@@ -346,7 +347,7 @@ TRUNNER_BPF_OBJS := $$(patsubst %.c,$$(TRUNNER_OUTPUT)/%.o, $$(TRUNNER_BPF_SRCS)
 TRUNNER_BPF_SKELS := $$(patsubst %.c,$$(TRUNNER_OUTPUT)/%.skel.h,	\
 				 $$(filter-out $(SKEL_BLACKLIST) $(LINKED_BPF_SRCS),\
 					       $$(TRUNNER_BPF_SRCS)))
-TRUNNER_BPF_LSKELS := $$(patsubst %.c,$$(TRUNNER_OUTPUT)/%.lskel.h, $$(LSKELS))
+TRUNNER_BPF_LSKELS := $$(patsubst %.c,$$(TRUNNER_OUTPUT)/%.lskel.h, $$(LSKELS) $$(LSKELS_EXTRA))
 TRUNNER_BPF_SKELS_LINKED := $$(addprefix $$(TRUNNER_OUTPUT)/,$(LINKED_SKELS))
 TEST_GEN_FILES += $$(TRUNNER_BPF_OBJS)
 
diff --git a/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c b/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c
index 50fc5561110a..b892948dc134 100644
--- a/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c
+++ b/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c
@@ -1,5 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 /* Copyright (c) 2020 Facebook */
+#include <linux/btf.h>
+#include <linux/btf_ids.h>
 #include <linux/error-injection.h>
 #include <linux/init.h>
 #include <linux/module.h>
@@ -13,6 +15,12 @@
 
 DEFINE_PER_CPU(int, bpf_testmod_ksym_percpu) = 123;
 
+noinline void
+bpf_testmod_test_mod_kfunc(int i)
+{
+	*(int *)this_cpu_ptr(&bpf_testmod_ksym_percpu) = i;
+}
+
 noinline int bpf_testmod_loop_test(int n)
 {
 	int i, sum = 0;
@@ -71,13 +79,26 @@ static struct bin_attribute bin_attr_bpf_testmod_file __ro_after_init = {
 	.write = bpf_testmod_test_write,
 };
 
+BTF_SET_START(bpf_testmod_kfunc_ids)
+BTF_ID(func, bpf_testmod_test_mod_kfunc)
+BTF_SET_END(bpf_testmod_kfunc_ids)
+
+static DEFINE_KFUNC_BTF_ID_SET(&bpf_testmod_kfunc_ids, bpf_testmod_kfunc_btf_set);
+
 static int bpf_testmod_init(void)
 {
-	return sysfs_create_bin_file(kernel_kobj, &bin_attr_bpf_testmod_file);
+	int ret;
+
+	ret = sysfs_create_bin_file(kernel_kobj, &bin_attr_bpf_testmod_file);
+	if (ret)
+		return ret;
+	register_kfunc_btf_id_set(&prog_test_kfunc_list, &bpf_testmod_kfunc_btf_set);
+	return 0;
 }
 
 static void bpf_testmod_exit(void)
 {
+	unregister_kfunc_btf_id_set(&prog_test_kfunc_list, &bpf_testmod_kfunc_btf_set);
 	return sysfs_remove_bin_file(kernel_kobj, &bin_attr_bpf_testmod_file);
 }
 
diff --git a/tools/testing/selftests/bpf/prog_tests/ksyms_module.c b/tools/testing/selftests/bpf/prog_tests/ksyms_module.c
index 2cd5cded543f..831447878d7b 100644
--- a/tools/testing/selftests/bpf/prog_tests/ksyms_module.c
+++ b/tools/testing/selftests/bpf/prog_tests/ksyms_module.c
@@ -2,30 +2,29 @@
 /* Copyright (c) 2021 Facebook */
 
 #include <test_progs.h>
-#include <bpf/libbpf.h>
-#include <bpf/btf.h>
+#include <network_helpers.h>
 #include "test_ksyms_module.lskel.h"
 
-static int duration;
-
 void test_ksyms_module(void)
 {
-	struct test_ksyms_module* skel;
+	struct test_ksyms_module *skel;
+	int retval;
 	int err;
 
-	skel = test_ksyms_module__open_and_load();
-	if (CHECK(!skel, "skel_open", "failed to open skeleton\n"))
+	if (!env.has_testmod) {
+		test__skip();
 		return;
+	}
 
-	err = test_ksyms_module__attach(skel);
-	if (CHECK(err, "skel_attach", "skeleton attach failed: %d\n", err))
+	skel = test_ksyms_module__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "test_ksyms_module__open_and_load"))
+		return;
+	err = bpf_prog_test_run(skel->progs.load.prog_fd, 1, &pkt_v4, sizeof(pkt_v4),
+				NULL, NULL, (__u32 *)&retval, NULL);
+	if (!ASSERT_OK(err, "bpf_prog_test_run"))
 		goto cleanup;
-
-	usleep(1);
-
-	ASSERT_EQ(skel->bss->triggered, true, "triggered");
-	ASSERT_EQ(skel->bss->out_mod_ksym_global, 123, "global_ksym_val");
-
+	ASSERT_EQ(retval, 0, "retval");
+	ASSERT_EQ(skel->bss->out_bpf_testmod_ksym, 42, "bpf_testmod_ksym");
 cleanup:
 	test_ksyms_module__destroy(skel);
 }
diff --git a/tools/testing/selftests/bpf/prog_tests/ksyms_module_libbpf.c b/tools/testing/selftests/bpf/prog_tests/ksyms_module_libbpf.c
new file mode 100644
index 000000000000..e6343ef63af9
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/ksyms_module_libbpf.c
@@ -0,0 +1,28 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <test_progs.h>
+#include <network_helpers.h>
+#include "test_ksyms_module.skel.h"
+
+void test_ksyms_module_libbpf(void)
+{
+	struct test_ksyms_module *skel;
+	int retval, err;
+
+	if (!env.has_testmod) {
+		test__skip();
+		return;
+	}
+
+	skel = test_ksyms_module__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "test_ksyms_module__open"))
+		return;
+	err = bpf_prog_test_run(bpf_program__fd(skel->progs.load), 1, &pkt_v4,
+				sizeof(pkt_v4), NULL, NULL, (__u32 *)&retval, NULL);
+	if (!ASSERT_OK(err, "bpf_prog_test_run"))
+		goto cleanup;
+	ASSERT_EQ(retval, 0, "retval");
+	ASSERT_EQ(skel->bss->out_bpf_testmod_ksym, 42, "bpf_testmod_ksym");
+cleanup:
+	test_ksyms_module__destroy(skel);
+}
diff --git a/tools/testing/selftests/bpf/progs/test_ksyms_module.c b/tools/testing/selftests/bpf/progs/test_ksyms_module.c
index d6a0b3086b90..0650d918c096 100644
--- a/tools/testing/selftests/bpf/progs/test_ksyms_module.c
+++ b/tools/testing/selftests/bpf/progs/test_ksyms_module.c
@@ -2,24 +2,48 @@
 /* Copyright (c) 2021 Facebook */
 
 #include "vmlinux.h"
-
 #include <bpf/bpf_helpers.h>
 
+#define X_0(x)
+#define X_1(x) x X_0(x)
+#define X_2(x) x X_1(x)
+#define X_3(x) x X_2(x)
+#define X_4(x) x X_3(x)
+#define X_5(x) x X_4(x)
+#define X_6(x) x X_5(x)
+#define X_7(x) x X_6(x)
+#define X_8(x) x X_7(x)
+#define X_9(x) x X_8(x)
+#define X_10(x) x X_9(x)
+#define REPEAT_256(Y) X_2(X_10(X_10(Y))) X_5(X_10(Y)) X_6(Y)
+
 extern const int bpf_testmod_ksym_percpu __ksym;
+extern void bpf_testmod_test_mod_kfunc(int i) __ksym;
+extern void bpf_testmod_invalid_mod_kfunc(void) __ksym __weak;
 
-int out_mod_ksym_global = 0;
-bool triggered = false;
+int out_bpf_testmod_ksym = 0;
+const volatile int x = 0;
 
-SEC("raw_tp/sys_enter")
-int handler(const void *ctx)
+SEC("tc")
+int load(struct __sk_buff *skb)
 {
-	int *val;
-	__u32 cpu;
-
-	val = (int *)bpf_this_cpu_ptr(&bpf_testmod_ksym_percpu);
-	out_mod_ksym_global = *val;
-	triggered = true;
+	/* This will be kept by clang, but removed by verifier. Since it is
+	 * marked as __weak, libbpf and gen_loader don't error out if BTF ID
+	 * is not found for it, instead imm and off is set to 0 for it.
+	 */
+	if (x)
+		bpf_testmod_invalid_mod_kfunc();
+	bpf_testmod_test_mod_kfunc(42);
+	out_bpf_testmod_ksym = *(int *)bpf_this_cpu_ptr(&bpf_testmod_ksym_percpu);
+	return 0;
+}
 
+SEC("tc")
+int load_256(struct __sk_buff *skb)
+{
+	/* this will fail if kfunc doesn't reuse its own btf fd index */
+	REPEAT_256(bpf_testmod_test_mod_kfunc(42););
+	bpf_testmod_test_mod_kfunc(42);
 	return 0;
 }
 
diff --git a/tools/testing/selftests/bpf/verifier/calls.c b/tools/testing/selftests/bpf/verifier/calls.c
index 336a749673d1..d7b74eb28333 100644
--- a/tools/testing/selftests/bpf/verifier/calls.c
+++ b/tools/testing/selftests/bpf/verifier/calls.c
@@ -1,3 +1,26 @@
+{
+	"calls: invalid kfunc call not eliminated",
+	.insns = {
+	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, BPF_PSEUDO_KFUNC_CALL, 0, 0),
+	BPF_MOV64_IMM(BPF_REG_0, 1),
+	BPF_EXIT_INSN(),
+	},
+	.prog_type = BPF_PROG_TYPE_TRACEPOINT,
+	.result  = REJECT,
+	.errstr = "invalid kernel function call not eliminated in verifier pass",
+},
+{
+	"calls: invalid kfunc call unreachable",
+	.insns = {
+	BPF_MOV64_IMM(BPF_REG_0, 1),
+	BPF_JMP_IMM(BPF_JGT, BPF_REG_0, 0, 2),
+	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, BPF_PSEUDO_KFUNC_CALL, 0, 0),
+	BPF_MOV64_IMM(BPF_REG_0, 1),
+	BPF_EXIT_INSN(),
+	},
+	.prog_type = BPF_PROG_TYPE_TRACEPOINT,
+	.result  = ACCEPT,
+},
 {
 	"calls: basic sanity",
 	.insns = {
-- 
cgit v1.2.3


From 57a610f1c58fa493315e1c24eef6d992cdf4c4a9 Mon Sep 17 00:00:00 2001
From: Jie Meng <jmeng@fb.com>
Date: Fri, 1 Oct 2021 20:56:26 -0700
Subject: bpf, x64: Save bytes for DIV by reducing reg copies

Instead of unconditionally performing push/pop on %rax/%rdx in case of
division/modulo, we can save a few bytes in case of destination register
being either BPF r0 (%rax) or r3 (%rdx) since the result is written in
there anyway.

Also, we do not need to copy the source to %r11 unless the source is either
%rax, %rdx or an immediate.

For example, before the patch:

  22:   push   %rax
  23:   push   %rdx
  24:   mov    %rsi,%r11
  27:   xor    %edx,%edx
  29:   div    %r11
  2c:   mov    %rax,%r11
  2f:   pop    %rdx
  30:   pop    %rax
  31:   mov    %r11,%rax

After:

  22:   push   %rdx
  23:   xor    %edx,%edx
  25:   div    %rsi
  28:   pop    %rdx

Signed-off-by: Jie Meng <jmeng@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Tested-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/bpf/20211002035626.2041910-1-jmeng@fb.com
---
 tools/testing/selftests/bpf/verifier/jit.c | 47 ++++++++++++++++++++++++++++++
 1 file changed, 47 insertions(+)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/verifier/jit.c b/tools/testing/selftests/bpf/verifier/jit.c
index eedcb752bf70..79021c30e51e 100644
--- a/tools/testing/selftests/bpf/verifier/jit.c
+++ b/tools/testing/selftests/bpf/verifier/jit.c
@@ -102,6 +102,53 @@
 	.result = ACCEPT,
 	.retval = 2,
 },
+{
+	"jit: various div tests",
+	.insns = {
+	BPF_LD_IMM64(BPF_REG_2, 0xefeffeULL),
+	BPF_LD_IMM64(BPF_REG_0, 0xeeff0d413122ULL),
+	BPF_LD_IMM64(BPF_REG_1, 0xfefeeeULL),
+	BPF_ALU64_REG(BPF_DIV, BPF_REG_0, BPF_REG_1),
+	BPF_JMP_REG(BPF_JEQ, BPF_REG_0, BPF_REG_2, 2),
+	BPF_MOV64_IMM(BPF_REG_0, 1),
+	BPF_EXIT_INSN(),
+	BPF_LD_IMM64(BPF_REG_3, 0xeeff0d413122ULL),
+	BPF_ALU64_IMM(BPF_DIV, BPF_REG_3, 0xfefeeeULL),
+	BPF_JMP_REG(BPF_JEQ, BPF_REG_3, BPF_REG_2, 2),
+	BPF_MOV64_IMM(BPF_REG_0, 1),
+	BPF_EXIT_INSN(),
+	BPF_LD_IMM64(BPF_REG_2, 0xaa93ULL),
+	BPF_ALU64_IMM(BPF_MOD, BPF_REG_1, 0xbeefULL),
+	BPF_JMP_REG(BPF_JEQ, BPF_REG_1, BPF_REG_2, 2),
+	BPF_MOV64_IMM(BPF_REG_0, 1),
+	BPF_EXIT_INSN(),
+	BPF_LD_IMM64(BPF_REG_1, 0xfefeeeULL),
+	BPF_LD_IMM64(BPF_REG_3, 0xbeefULL),
+	BPF_ALU64_REG(BPF_MOD, BPF_REG_1, BPF_REG_3),
+	BPF_JMP_REG(BPF_JEQ, BPF_REG_1, BPF_REG_2, 2),
+	BPF_MOV64_IMM(BPF_REG_0, 1),
+	BPF_EXIT_INSN(),
+	BPF_LD_IMM64(BPF_REG_2, 0x5ee1dULL),
+	BPF_LD_IMM64(BPF_REG_1, 0xfefeeeULL),
+	BPF_LD_IMM64(BPF_REG_3, 0x2bULL),
+	BPF_ALU32_REG(BPF_DIV, BPF_REG_1, BPF_REG_3),
+	BPF_JMP_REG(BPF_JEQ, BPF_REG_1, BPF_REG_2, 2),
+	BPF_MOV64_IMM(BPF_REG_0, 1),
+	BPF_EXIT_INSN(),
+	BPF_ALU32_REG(BPF_DIV, BPF_REG_1, BPF_REG_1),
+	BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, 1, 2),
+	BPF_MOV64_IMM(BPF_REG_0, 1),
+	BPF_EXIT_INSN(),
+	BPF_ALU64_REG(BPF_MOD, BPF_REG_2, BPF_REG_2),
+	BPF_JMP_IMM(BPF_JEQ, BPF_REG_2, 0, 2),
+	BPF_MOV64_IMM(BPF_REG_0, 1),
+	BPF_EXIT_INSN(),
+	BPF_MOV64_IMM(BPF_REG_0, 2),
+	BPF_EXIT_INSN(),
+	},
+	.result = ACCEPT,
+	.retval = 2,
+},
 {
 	"jit: jsgt, jslt",
 	.insns = {
-- 
cgit v1.2.3


From 7ca61121598338ab713a5c705a843f3b8fed9f90 Mon Sep 17 00:00:00 2001
From: Andrii Nakryiko <andrii@kernel.org>
Date: Tue, 5 Oct 2021 22:11:05 -0700
Subject: libbpf: Add API that copies all BTF types from one BTF object to
 another

Add a bulk copying api, btf__add_btf(), that speeds up and simplifies
appending entire contents of one BTF object to another one, taking care
of copying BTF type data, adjusting resulting BTF type IDs according to
their new locations in the destination BTF object, as well as copying
and deduplicating all the referenced strings and updating all the string
offsets in new BTF types as appropriate.

This API is intended to be used from tools that are generating and
otherwise manipulating BTFs generically, such as pahole. In pahole's
case, this API is useful for speeding up parallelized BTF encoding, as
it allows pahole to offload all the intricacies of BTF type copying to
libbpf and handle the parallelization aspects of the process.

Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Song Liu <songliubraving@fb.com>
Cc: Arnaldo Carvalho de Melo <acme@kernel.org>
Link: https://lore.kernel.org/bpf/20211006051107.17921-2-andrii@kernel.org
---
 tools/lib/bpf/btf.c      | 114 ++++++++++++++++++++++++++++++++++++++++++++++-
 tools/lib/bpf/btf.h      |  22 +++++++++
 tools/lib/bpf/libbpf.map |   1 +
 3 files changed, 135 insertions(+), 2 deletions(-)

(limited to 'tools')

diff --git a/tools/lib/bpf/btf.c b/tools/lib/bpf/btf.c
index 7774f99afa6e..60fbd1c6d466 100644
--- a/tools/lib/bpf/btf.c
+++ b/tools/lib/bpf/btf.c
@@ -189,12 +189,17 @@ int libbpf_ensure_mem(void **data, size_t *cap_cnt, size_t elem_sz, size_t need_
 	return 0;
 }
 
+static void *btf_add_type_offs_mem(struct btf *btf, size_t add_cnt)
+{
+	return libbpf_add_mem((void **)&btf->type_offs, &btf->type_offs_cap, sizeof(__u32),
+			      btf->nr_types, BTF_MAX_NR_TYPES, add_cnt);
+}
+
 static int btf_add_type_idx_entry(struct btf *btf, __u32 type_off)
 {
 	__u32 *p;
 
-	p = libbpf_add_mem((void **)&btf->type_offs, &btf->type_offs_cap, sizeof(__u32),
-			   btf->nr_types, BTF_MAX_NR_TYPES, 1);
+	p = btf_add_type_offs_mem(btf, 1);
 	if (!p)
 		return -ENOMEM;
 
@@ -1703,6 +1708,111 @@ int btf__add_type(struct btf *btf, const struct btf *src_btf, const struct btf_t
 	return btf_commit_type(btf, sz);
 }
 
+static int btf_rewrite_type_ids(__u32 *type_id, void *ctx)
+{
+	struct btf *btf = ctx;
+
+	if (!*type_id) /* nothing to do for VOID references */
+		return 0;
+
+	/* we haven't updated btf's type count yet, so
+	 * btf->start_id + btf->nr_types - 1 is the type ID offset we should
+	 * add to all newly added BTF types
+	 */
+	*type_id += btf->start_id + btf->nr_types - 1;
+	return 0;
+}
+
+int btf__add_btf(struct btf *btf, const struct btf *src_btf)
+{
+	struct btf_pipe p = { .src = src_btf, .dst = btf };
+	int data_sz, sz, cnt, i, err, old_strs_len;
+	__u32 *off;
+	void *t;
+
+	/* appending split BTF isn't supported yet */
+	if (src_btf->base_btf)
+		return libbpf_err(-ENOTSUP);
+
+	/* deconstruct BTF, if necessary, and invalidate raw_data */
+	if (btf_ensure_modifiable(btf))
+		return libbpf_err(-ENOMEM);
+
+	/* remember original strings section size if we have to roll back
+	 * partial strings section changes
+	 */
+	old_strs_len = btf->hdr->str_len;
+
+	data_sz = src_btf->hdr->type_len;
+	cnt = btf__get_nr_types(src_btf);
+
+	/* pre-allocate enough memory for new types */
+	t = btf_add_type_mem(btf, data_sz);
+	if (!t)
+		return libbpf_err(-ENOMEM);
+
+	/* pre-allocate enough memory for type offset index for new types */
+	off = btf_add_type_offs_mem(btf, cnt);
+	if (!off)
+		return libbpf_err(-ENOMEM);
+
+	/* bulk copy types data for all types from src_btf */
+	memcpy(t, src_btf->types_data, data_sz);
+
+	for (i = 0; i < cnt; i++) {
+		sz = btf_type_size(t);
+		if (sz < 0) {
+			/* unlikely, has to be corrupted src_btf */
+			err = sz;
+			goto err_out;
+		}
+
+		/* fill out type ID to type offset mapping for lookups by type ID */
+		*off = t - btf->types_data;
+
+		/* add, dedup, and remap strings referenced by this BTF type */
+		err = btf_type_visit_str_offs(t, btf_rewrite_str, &p);
+		if (err)
+			goto err_out;
+
+		/* remap all type IDs referenced from this BTF type */
+		err = btf_type_visit_type_ids(t, btf_rewrite_type_ids, btf);
+		if (err)
+			goto err_out;
+
+		/* go to next type data and type offset index entry */
+		t += sz;
+		off++;
+	}
+
+	/* Up until now any of the copied type data was effectively invisible,
+	 * so if we exited early before this point due to error, BTF would be
+	 * effectively unmodified. There would be extra internal memory
+	 * pre-allocated, but it would not be available for querying.  But now
+	 * that we've copied and rewritten all the data successfully, we can
+	 * update type count and various internal offsets and sizes to
+	 * "commit" the changes and made them visible to the outside world.
+	 */
+	btf->hdr->type_len += data_sz;
+	btf->hdr->str_off += data_sz;
+	btf->nr_types += cnt;
+
+	/* return type ID of the first added BTF type */
+	return btf->start_id + btf->nr_types - cnt;
+err_out:
+	/* zero out preallocated memory as if it was just allocated with
+	 * libbpf_add_mem()
+	 */
+	memset(btf->types_data + btf->hdr->type_len, 0, data_sz);
+	memset(btf->strs_data + old_strs_len, 0, btf->hdr->str_len - old_strs_len);
+
+	/* and now restore original strings section size; types data size
+	 * wasn't modified, so doesn't need restoring, see big comment above */
+	btf->hdr->str_len = old_strs_len;
+
+	return libbpf_err(err);
+}
+
 /*
  * Append new BTF_KIND_INT type with:
  *   - *name* - non-empty, non-NULL type name;
diff --git a/tools/lib/bpf/btf.h b/tools/lib/bpf/btf.h
index 2cfe31327920..864eb51753a1 100644
--- a/tools/lib/bpf/btf.h
+++ b/tools/lib/bpf/btf.h
@@ -173,6 +173,28 @@ LIBBPF_API int btf__find_str(struct btf *btf, const char *s);
 LIBBPF_API int btf__add_str(struct btf *btf, const char *s);
 LIBBPF_API int btf__add_type(struct btf *btf, const struct btf *src_btf,
 			     const struct btf_type *src_type);
+/**
+ * @brief **btf__add_btf()** appends all the BTF types from *src_btf* into *btf*
+ * @param btf BTF object which all the BTF types and strings are added to
+ * @param src_btf BTF object which all BTF types and referenced strings are copied from
+ * @return BTF type ID of the first appended BTF type, or negative error code
+ *
+ * **btf__add_btf()** can be used to simply and efficiently append the entire
+ * contents of one BTF object to another one. All the BTF type data is copied
+ * over, all referenced type IDs are adjusted by adding a necessary ID offset.
+ * Only strings referenced from BTF types are copied over and deduplicated, so
+ * if there were some unused strings in *src_btf*, those won't be copied over,
+ * which is consistent with the general string deduplication semantics of BTF
+ * writing APIs.
+ *
+ * If any error is encountered during this process, the contents of *btf* is
+ * left intact, which means that **btf__add_btf()** follows the transactional
+ * semantics and the operation as a whole is all-or-nothing.
+ *
+ * *src_btf* has to be non-split BTF, as of now copying types from split BTF
+ * is not supported and will result in -ENOTSUP error code returned.
+ */
+LIBBPF_API int btf__add_btf(struct btf *btf, const struct btf *src_btf);
 
 LIBBPF_API int btf__add_int(struct btf *btf, const char *name, size_t byte_sz, int encoding);
 LIBBPF_API int btf__add_float(struct btf *btf, const char *name, size_t byte_sz);
diff --git a/tools/lib/bpf/libbpf.map b/tools/lib/bpf/libbpf.map
index 9e649cf9e771..f6b0db1e8c8b 100644
--- a/tools/lib/bpf/libbpf.map
+++ b/tools/lib/bpf/libbpf.map
@@ -389,5 +389,6 @@ LIBBPF_0.5.0 {
 
 LIBBPF_0.6.0 {
 	global:
+		btf__add_btf;
 		btf__add_tag;
 } LIBBPF_0.5.0;
-- 
cgit v1.2.3


From c65eb8082d4cb02ef87bdecedce8969d5ccbea54 Mon Sep 17 00:00:00 2001
From: Andrii Nakryiko <andrii@kernel.org>
Date: Tue, 5 Oct 2021 22:11:06 -0700
Subject: selftests/bpf: Refactor btf_write selftest to reuse BTF generation
 logic

Next patch will need to reuse BTF generation logic, which tests every
supported BTF kind, for testing btf__add_btf() APIs. So restructure
existing selftests and make it as a single subtest that uses bulk
VALIDATE_RAW_BTF() macro for raw BTF dump checking.

Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Song Liu <songliubraving@fb.com>
Link: https://lore.kernel.org/bpf/20211006051107.17921-3-andrii@kernel.org
---
 tools/testing/selftests/bpf/prog_tests/btf_write.c | 55 +++++++++++++++++++---
 1 file changed, 49 insertions(+), 6 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/prog_tests/btf_write.c b/tools/testing/selftests/bpf/prog_tests/btf_write.c
index 76548eecce2c..aa4505618252 100644
--- a/tools/testing/selftests/bpf/prog_tests/btf_write.c
+++ b/tools/testing/selftests/bpf/prog_tests/btf_write.c
@@ -4,19 +4,15 @@
 #include <bpf/btf.h>
 #include "btf_helpers.h"
 
-void test_btf_write() {
+static void gen_btf(struct btf *btf)
+{
 	const struct btf_var_secinfo *vi;
 	const struct btf_type *t;
 	const struct btf_member *m;
 	const struct btf_enum *v;
 	const struct btf_param *p;
-	struct btf *btf;
 	int id, err, str_off;
 
-	btf = btf__new_empty();
-	if (!ASSERT_OK_PTR(btf, "new_empty"))
-		return;
-
 	str_off = btf__find_str(btf, "int");
 	ASSERT_EQ(str_off, -ENOENT, "int_str_missing_off");
 
@@ -301,6 +297,53 @@ void test_btf_write() {
 	ASSERT_EQ(btf_tag(t)->component_idx, 1, "tag_component_idx");
 	ASSERT_STREQ(btf_type_raw_dump(btf, 19),
 		     "[19] TAG 'tag2' type_id=14 component_idx=1", "raw_dump");
+}
+
+static void test_btf_add()
+{
+	struct btf *btf;
+
+	btf = btf__new_empty();
+	if (!ASSERT_OK_PTR(btf, "new_empty"))
+		return;
+
+	gen_btf(btf);
+
+	VALIDATE_RAW_BTF(
+		btf,
+		"[1] INT 'int' size=4 bits_offset=0 nr_bits=32 encoding=SIGNED",
+		"[2] PTR '(anon)' type_id=1",
+		"[3] CONST '(anon)' type_id=5",
+		"[4] VOLATILE '(anon)' type_id=3",
+		"[5] RESTRICT '(anon)' type_id=4",
+		"[6] ARRAY '(anon)' type_id=2 index_type_id=1 nr_elems=10",
+		"[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",
+		"[8] UNION 'u1' size=8 vlen=1\n"
+		"\t'f1' type_id=1 bits_offset=0 bitfield_size=16",
+		"[9] ENUM 'e1' size=4 vlen=2\n"
+		"\t'v1' val=1\n"
+		"\t'v2' val=2",
+		"[10] FWD 'struct_fwd' fwd_kind=struct",
+		"[11] FWD 'union_fwd' fwd_kind=union",
+		"[12] ENUM 'enum_fwd' size=4 vlen=0",
+		"[13] TYPEDEF 'typedef1' type_id=1",
+		"[14] FUNC 'func1' type_id=15 linkage=global",
+		"[15] FUNC_PROTO '(anon)' ret_type_id=1 vlen=2\n"
+		"\t'p1' type_id=1\n"
+		"\t'p2' type_id=2",
+		"[16] VAR 'var1' type_id=1, linkage=global-alloc",
+		"[17] DATASEC 'datasec1' size=12 vlen=1\n"
+		"\ttype_id=1 offset=4 size=8",
+		"[18] TAG 'tag1' type_id=16 component_idx=-1",
+		"[19] TAG 'tag2' type_id=14 component_idx=1");
 
 	btf__free(btf);
 }
+
+void test_btf_write()
+{
+	if (test__start_subtest("btf_add"))
+		test_btf_add();
+}
-- 
cgit v1.2.3


From 9d05787223913171fce20a737ba54e3b6e7da13c Mon Sep 17 00:00:00 2001
From: Andrii Nakryiko <andrii@kernel.org>
Date: Tue, 5 Oct 2021 22:11:07 -0700
Subject: selftests/bpf: Test new btf__add_btf() API

Add a test that validates that btf__add_btf() API is correctly copying
all the types from the source BTF into destination BTF object and
adjusts type IDs and string offsets properly.

Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/bpf/20211006051107.17921-4-andrii@kernel.org
---
 tools/testing/selftests/bpf/prog_tests/btf_write.c | 86 ++++++++++++++++++++++
 1 file changed, 86 insertions(+)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/prog_tests/btf_write.c b/tools/testing/selftests/bpf/prog_tests/btf_write.c
index aa4505618252..886e0fc1efb1 100644
--- a/tools/testing/selftests/bpf/prog_tests/btf_write.c
+++ b/tools/testing/selftests/bpf/prog_tests/btf_write.c
@@ -342,8 +342,94 @@ static void test_btf_add()
 	btf__free(btf);
 }
 
+static void test_btf_add_btf()
+{
+	struct btf *btf1 = NULL, *btf2 = NULL;
+	int id;
+
+	btf1 = btf__new_empty();
+	if (!ASSERT_OK_PTR(btf1, "btf1"))
+		return;
+
+	btf2 = btf__new_empty();
+	if (!ASSERT_OK_PTR(btf2, "btf2"))
+		goto cleanup;
+
+	gen_btf(btf1);
+	gen_btf(btf2);
+
+	id = btf__add_btf(btf1, btf2);
+	if (!ASSERT_EQ(id, 20, "id"))
+		goto cleanup;
+
+	VALIDATE_RAW_BTF(
+		btf1,
+		"[1] INT 'int' size=4 bits_offset=0 nr_bits=32 encoding=SIGNED",
+		"[2] PTR '(anon)' type_id=1",
+		"[3] CONST '(anon)' type_id=5",
+		"[4] VOLATILE '(anon)' type_id=3",
+		"[5] RESTRICT '(anon)' type_id=4",
+		"[6] ARRAY '(anon)' type_id=2 index_type_id=1 nr_elems=10",
+		"[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",
+		"[8] UNION 'u1' size=8 vlen=1\n"
+		"\t'f1' type_id=1 bits_offset=0 bitfield_size=16",
+		"[9] ENUM 'e1' size=4 vlen=2\n"
+		"\t'v1' val=1\n"
+		"\t'v2' val=2",
+		"[10] FWD 'struct_fwd' fwd_kind=struct",
+		"[11] FWD 'union_fwd' fwd_kind=union",
+		"[12] ENUM 'enum_fwd' size=4 vlen=0",
+		"[13] TYPEDEF 'typedef1' type_id=1",
+		"[14] FUNC 'func1' type_id=15 linkage=global",
+		"[15] FUNC_PROTO '(anon)' ret_type_id=1 vlen=2\n"
+		"\t'p1' type_id=1\n"
+		"\t'p2' type_id=2",
+		"[16] VAR 'var1' type_id=1, linkage=global-alloc",
+		"[17] DATASEC 'datasec1' size=12 vlen=1\n"
+		"\ttype_id=1 offset=4 size=8",
+		"[18] TAG 'tag1' type_id=16 component_idx=-1",
+		"[19] TAG 'tag2' type_id=14 component_idx=1",
+
+		/* types appended from the second BTF */
+		"[20] INT 'int' size=4 bits_offset=0 nr_bits=32 encoding=SIGNED",
+		"[21] PTR '(anon)' type_id=20",
+		"[22] CONST '(anon)' type_id=24",
+		"[23] VOLATILE '(anon)' type_id=22",
+		"[24] RESTRICT '(anon)' type_id=23",
+		"[25] ARRAY '(anon)' type_id=21 index_type_id=20 nr_elems=10",
+		"[26] STRUCT 's1' size=8 vlen=2\n"
+		"\t'f1' type_id=20 bits_offset=0\n"
+		"\t'f2' type_id=20 bits_offset=32 bitfield_size=16",
+		"[27] UNION 'u1' size=8 vlen=1\n"
+		"\t'f1' type_id=20 bits_offset=0 bitfield_size=16",
+		"[28] ENUM 'e1' size=4 vlen=2\n"
+		"\t'v1' val=1\n"
+		"\t'v2' val=2",
+		"[29] FWD 'struct_fwd' fwd_kind=struct",
+		"[30] FWD 'union_fwd' fwd_kind=union",
+		"[31] ENUM 'enum_fwd' size=4 vlen=0",
+		"[32] TYPEDEF 'typedef1' type_id=20",
+		"[33] FUNC 'func1' type_id=34 linkage=global",
+		"[34] FUNC_PROTO '(anon)' ret_type_id=20 vlen=2\n"
+		"\t'p1' type_id=20\n"
+		"\t'p2' type_id=21",
+		"[35] VAR 'var1' type_id=20, linkage=global-alloc",
+		"[36] DATASEC 'datasec1' size=12 vlen=1\n"
+		"\ttype_id=20 offset=4 size=8",
+		"[37] TAG 'tag1' type_id=35 component_idx=-1",
+		"[38] TAG 'tag2' type_id=33 component_idx=1");
+
+cleanup:
+	btf__free(btf1);
+	btf__free(btf2);
+}
+
 void test_btf_write()
 {
 	if (test__start_subtest("btf_add"))
 		test_btf_add();
+	if (test__start_subtest("btf_add_btf"))
+		test_btf_add_btf();
 }
-- 
cgit v1.2.3


From 929bef467771d4d5a22b9edb51a2025dc0e49113 Mon Sep 17 00:00:00 2001
From: Quentin Monnet <quentin@isovalent.com>
Date: Wed, 6 Oct 2021 12:10:49 +0100
Subject: bpf: Use $(pound) instead of \# in Makefiles

Recent-ish versions of make do no longer consider number signs ("#") as
comment symbols when they are inserted inside of a macro reference or in
a function invocation. In such cases, the symbols should not be escaped.

There are a few occurrences of "\#" in libbpf's and samples' Makefiles.
In the former, the backslash is harmless, because grep associates no
particular meaning to the escaped symbol and reads it as a regular "#".
In samples' Makefile, recent versions of make will pass the backslash
down to the compiler, making the probe fail all the time and resulting
in the display of a warning about "make headers_install" being required,
even after headers have been installed.

A similar issue has been addressed at some other locations by commit
9564a8cf422d ("Kbuild: fix # escaping in .cmd files for future Make").
Let's address it for libbpf's and samples' Makefiles in the same
fashion, by using a "$(pound)" variable (pulled from
tools/scripts/Makefile.include for libbpf, or re-defined for the
samples).

Reference for the change in make:
https://git.savannah.gnu.org/cgit/make.git/commit/?id=c6966b323811c37acedff05b57

Fixes: 2f3830412786 ("libbpf: Make libbpf_version.h non-auto-generated")
Fixes: 07c3bbdb1a9b ("samples: bpf: print a warning about headers_install")
Signed-off-by: Quentin Monnet <quentin@isovalent.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20211006111049.20708-1-quentin@isovalent.com
---
 tools/lib/bpf/Makefile | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'tools')

diff --git a/tools/lib/bpf/Makefile b/tools/lib/bpf/Makefile
index 0f766345506f..41e4f78dbad5 100644
--- a/tools/lib/bpf/Makefile
+++ b/tools/lib/bpf/Makefile
@@ -208,8 +208,8 @@ check_abi: $(OUTPUT)libbpf.so $(VERSION_SCRIPT)
 		exit 1;							 \
 	fi
 
-HDR_MAJ_VERSION := $(shell grep -oE '^\#define LIBBPF_MAJOR_VERSION ([0-9]+)$$' libbpf_version.h | cut -d' ' -f3)
-HDR_MIN_VERSION := $(shell grep -oE '^\#define LIBBPF_MINOR_VERSION ([0-9]+)$$' libbpf_version.h | cut -d' ' -f3)
+HDR_MAJ_VERSION := $(shell grep -oE '^$(pound)define LIBBPF_MAJOR_VERSION ([0-9]+)$$' libbpf_version.h | cut -d' ' -f3)
+HDR_MIN_VERSION := $(shell grep -oE '^$(pound)define LIBBPF_MINOR_VERSION ([0-9]+)$$' libbpf_version.h | cut -d' ' -f3)
 
 check_version: $(VERSION_SCRIPT) libbpf_version.h
 	@if [ "$(HDR_MAJ_VERSION)" != "$(LIBBPF_MAJOR_VERSION)" ]; then        \
-- 
cgit v1.2.3


From 189c83bdde850e1fc8bb347f813cdd8776ce7abf Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@redhat.com>
Date: Sun, 3 Oct 2021 18:49:25 +0200
Subject: selftest/bpf: Switch recursion test to use htab_map_delete_elem

Currently the recursion test is hooking __htab_map_lookup_elem
function, which is invoked both from bpf_prog and bpf syscall.

But in our kernel build, the __htab_map_lookup_elem gets inlined
within the htab_map_lookup_elem, so it's not trigered and the
test fails.

Fixing this by using htab_map_delete_elem, which is not inlined
for bpf_prog calls (like htab_map_lookup_elem is) and is used
directly as pointer for map_delete_elem, so it won't disappear
by inlining.

Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Acked-by: Song Liu <songliubraving@fb.com>
Link: https://lore.kernel.org/bpf/YVnfFTL/3T6jOwHI@krava
---
 tools/testing/selftests/bpf/prog_tests/recursion.c | 10 +++++-----
 tools/testing/selftests/bpf/progs/recursion.c      |  9 +++------
 2 files changed, 8 insertions(+), 11 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/prog_tests/recursion.c b/tools/testing/selftests/bpf/prog_tests/recursion.c
index 0e378d63fe18..f3af2627b599 100644
--- a/tools/testing/selftests/bpf/prog_tests/recursion.c
+++ b/tools/testing/selftests/bpf/prog_tests/recursion.c
@@ -20,18 +20,18 @@ void test_recursion(void)
 		goto out;
 
 	ASSERT_EQ(skel->bss->pass1, 0, "pass1 == 0");
-	bpf_map_lookup_elem(bpf_map__fd(skel->maps.hash1), &key, 0);
+	bpf_map_delete_elem(bpf_map__fd(skel->maps.hash1), &key);
 	ASSERT_EQ(skel->bss->pass1, 1, "pass1 == 1");
-	bpf_map_lookup_elem(bpf_map__fd(skel->maps.hash1), &key, 0);
+	bpf_map_delete_elem(bpf_map__fd(skel->maps.hash1), &key);
 	ASSERT_EQ(skel->bss->pass1, 2, "pass1 == 2");
 
 	ASSERT_EQ(skel->bss->pass2, 0, "pass2 == 0");
-	bpf_map_lookup_elem(bpf_map__fd(skel->maps.hash2), &key, 0);
+	bpf_map_delete_elem(bpf_map__fd(skel->maps.hash2), &key);
 	ASSERT_EQ(skel->bss->pass2, 1, "pass2 == 1");
-	bpf_map_lookup_elem(bpf_map__fd(skel->maps.hash2), &key, 0);
+	bpf_map_delete_elem(bpf_map__fd(skel->maps.hash2), &key);
 	ASSERT_EQ(skel->bss->pass2, 2, "pass2 == 2");
 
-	err = bpf_obj_get_info_by_fd(bpf_program__fd(skel->progs.on_lookup),
+	err = bpf_obj_get_info_by_fd(bpf_program__fd(skel->progs.on_delete),
 				     &prog_info, &prog_info_len);
 	if (!ASSERT_OK(err, "get_prog_info"))
 		goto out;
diff --git a/tools/testing/selftests/bpf/progs/recursion.c b/tools/testing/selftests/bpf/progs/recursion.c
index 49f679375b9d..3c2423bb19e2 100644
--- a/tools/testing/selftests/bpf/progs/recursion.c
+++ b/tools/testing/selftests/bpf/progs/recursion.c
@@ -24,8 +24,8 @@ struct {
 int pass1 = 0;
 int pass2 = 0;
 
-SEC("fentry/__htab_map_lookup_elem")
-int BPF_PROG(on_lookup, struct bpf_map *map)
+SEC("fentry/htab_map_delete_elem")
+int BPF_PROG(on_delete, struct bpf_map *map)
 {
 	int key = 0;
 
@@ -35,10 +35,7 @@ int BPF_PROG(on_lookup, struct bpf_map *map)
 	}
 	if (map == (void *)&hash2) {
 		pass2++;
-		/* htab_map_gen_lookup() will inline below call
-		 * into direct call to __htab_map_lookup_elem()
-		 */
-		bpf_map_lookup_elem(&hash2, &key);
+		bpf_map_delete_elem(&hash2, &key);
 		return 0;
 	}
 
-- 
cgit v1.2.3


From 4a404a7e8a3902fc560527241a611186605efb4e Mon Sep 17 00:00:00 2001
From: Hengqi Chen <hengqi.chen@gmail.com>
Date: Sun, 3 Oct 2021 00:10:00 +0800
Subject: libbpf: Deprecate bpf_object__unload() API since v0.6

BPF objects are not reloadable after unload. Users are expected to use
bpf_object__close() to unload and free up resources in one operation.
No need to expose bpf_object__unload() as a public API, deprecate it
([0]).  Add bpf_object__unload() as an alias to internal
bpf_object_unload() and replace all bpf_object__unload() uses to avoid
compilation errors.

  [0] Closes: https://github.com/libbpf/libbpf/issues/290

Signed-off-by: Hengqi Chen <hengqi.chen@gmail.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Acked-by: Song Liu <songliubraving@fb.com>
Link: https://lore.kernel.org/bpf/20211002161000.3854559-1-hengqi.chen@gmail.com
---
 tools/lib/bpf/libbpf.c | 8 +++++---
 tools/lib/bpf/libbpf.h | 1 +
 2 files changed, 6 insertions(+), 3 deletions(-)

(limited to 'tools')

diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index f32fa51b1e63..4b90878a315f 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -6672,7 +6672,7 @@ bpf_object__open_buffer(const void *obj_buf, size_t obj_buf_sz,
 	return libbpf_ptr(__bpf_object__open(NULL, obj_buf, obj_buf_sz, &opts));
 }
 
-int bpf_object__unload(struct bpf_object *obj)
+static int bpf_object_unload(struct bpf_object *obj)
 {
 	size_t i;
 
@@ -6691,6 +6691,8 @@ int bpf_object__unload(struct bpf_object *obj)
 	return 0;
 }
 
+int bpf_object__unload(struct bpf_object *obj) __attribute__((alias("bpf_object_unload")));
+
 static int bpf_object__sanitize_maps(struct bpf_object *obj)
 {
 	struct bpf_map *m;
@@ -7089,7 +7091,7 @@ out:
 		if (obj->maps[i].pinned && !obj->maps[i].reused)
 			bpf_map__unpin(&obj->maps[i], NULL);
 
-	bpf_object__unload(obj);
+	bpf_object_unload(obj);
 	pr_warn("failed to load object '%s'\n", obj->path);
 	return libbpf_err(err);
 }
@@ -7698,7 +7700,7 @@ void bpf_object__close(struct bpf_object *obj)
 
 	bpf_gen__free(obj->gen_loader);
 	bpf_object__elf_finish(obj);
-	bpf_object__unload(obj);
+	bpf_object_unload(obj);
 	btf__free(obj->btf);
 	btf_ext__free(obj->btf_ext);
 
diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h
index e35490c54eb3..df10d14dbbb8 100644
--- a/tools/lib/bpf/libbpf.h
+++ b/tools/lib/bpf/libbpf.h
@@ -150,6 +150,7 @@ struct bpf_object_load_attr {
 /* Load/unload object into/from kernel */
 LIBBPF_API int bpf_object__load(struct bpf_object *obj);
 LIBBPF_API int bpf_object__load_xattr(struct bpf_object_load_attr *attr);
+LIBBPF_DEPRECATED_SINCE(0, 6, "bpf_object__unload() is deprecated, use bpf_object__close() instead")
 LIBBPF_API int bpf_object__unload(struct bpf_object *obj);
 
 LIBBPF_API const char *bpf_object__name(const struct bpf_object *obj);
-- 
cgit v1.2.3


From 2088a3a71d870115fdfb799c0f7de76d7383ba03 Mon Sep 17 00:00:00 2001
From: Hengqi Chen <hengqi.chen@gmail.com>
Date: Mon, 4 Oct 2021 00:58:43 +0800
Subject: libbpf: Deprecate bpf_{map,program}__{prev,next} APIs since v0.7

Deprecate bpf_{map,program}__{prev,next} APIs. Replace them with
a new set of APIs named bpf_object__{prev,next}_{program,map} which
follow the libbpf API naming convention ([0]). No functionality changes.

  [0] Closes: https://github.com/libbpf/libbpf/issues/296

Signed-off-by: Hengqi Chen <hengqi.chen@gmail.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Acked-by: Song Liu <songliubraving@fb.com>
Link: https://lore.kernel.org/bpf/20211003165844.4054931-2-hengqi.chen@gmail.com
---
 tools/lib/bpf/libbpf.c   | 24 ++++++++++++++++++++++++
 tools/lib/bpf/libbpf.h   | 35 +++++++++++++++++++++++------------
 tools/lib/bpf/libbpf.map |  4 ++++
 3 files changed, 51 insertions(+), 12 deletions(-)

(limited to 'tools')

diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 4b90878a315f..ed313fd491bd 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -7834,6 +7834,12 @@ __bpf_program__iter(const struct bpf_program *p, const struct bpf_object *obj,
 
 struct bpf_program *
 bpf_program__next(struct bpf_program *prev, const struct bpf_object *obj)
+{
+	return bpf_object__next_program(obj, prev);
+}
+
+struct bpf_program *
+bpf_object__next_program(const struct bpf_object *obj, struct bpf_program *prev)
 {
 	struct bpf_program *prog = prev;
 
@@ -7846,6 +7852,12 @@ bpf_program__next(struct bpf_program *prev, const struct bpf_object *obj)
 
 struct bpf_program *
 bpf_program__prev(struct bpf_program *next, const struct bpf_object *obj)
+{
+	return bpf_object__prev_program(obj, next);
+}
+
+struct bpf_program *
+bpf_object__prev_program(const struct bpf_object *obj, struct bpf_program *next)
 {
 	struct bpf_program *prog = next;
 
@@ -8778,6 +8790,12 @@ __bpf_map__iter(const struct bpf_map *m, const struct bpf_object *obj, int i)
 
 struct bpf_map *
 bpf_map__next(const struct bpf_map *prev, const struct bpf_object *obj)
+{
+	return bpf_object__next_map(obj, prev);
+}
+
+struct bpf_map *
+bpf_object__next_map(const struct bpf_object *obj, const struct bpf_map *prev)
 {
 	if (prev == NULL)
 		return obj->maps;
@@ -8787,6 +8805,12 @@ bpf_map__next(const struct bpf_map *prev, const struct bpf_object *obj)
 
 struct bpf_map *
 bpf_map__prev(const struct bpf_map *next, const struct bpf_object *obj)
+{
+	return bpf_object__prev_map(obj, next);
+}
+
+struct bpf_map *
+bpf_object__prev_map(const struct bpf_object *obj, const struct bpf_map *next)
 {
 	if (next == NULL) {
 		if (!obj->nr_maps)
diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h
index df10d14dbbb8..89ca9c83ed4e 100644
--- a/tools/lib/bpf/libbpf.h
+++ b/tools/lib/bpf/libbpf.h
@@ -190,16 +190,22 @@ LIBBPF_API int libbpf_find_vmlinux_btf_id(const char *name,
 
 /* Accessors of bpf_program */
 struct bpf_program;
-LIBBPF_API struct bpf_program *bpf_program__next(struct bpf_program *prog,
-						 const struct bpf_object *obj);
+LIBBPF_API LIBBPF_DEPRECATED_SINCE(0, 7, "use bpf_object__next_program() instead")
+struct bpf_program *bpf_program__next(struct bpf_program *prog,
+				      const struct bpf_object *obj);
+LIBBPF_API struct bpf_program *
+bpf_object__next_program(const struct bpf_object *obj, struct bpf_program *prog);
 
-#define bpf_object__for_each_program(pos, obj)		\
-	for ((pos) = bpf_program__next(NULL, (obj));	\
-	     (pos) != NULL;				\
-	     (pos) = bpf_program__next((pos), (obj)))
+#define bpf_object__for_each_program(pos, obj)			\
+	for ((pos) = bpf_object__next_program((obj), NULL);	\
+	     (pos) != NULL;					\
+	     (pos) = bpf_object__next_program((obj), (pos)))
 
-LIBBPF_API struct bpf_program *bpf_program__prev(struct bpf_program *prog,
-						 const struct bpf_object *obj);
+LIBBPF_API LIBBPF_DEPRECATED_SINCE(0, 7, "use bpf_object__prev_program() instead")
+struct bpf_program *bpf_program__prev(struct bpf_program *prog,
+				      const struct bpf_object *obj);
+LIBBPF_API struct bpf_program *
+bpf_object__prev_program(const struct bpf_object *obj, struct bpf_program *prog);
 
 typedef void (*bpf_program_clear_priv_t)(struct bpf_program *, void *);
 
@@ -503,16 +509,21 @@ bpf_object__find_map_fd_by_name(const struct bpf_object *obj, const char *name);
 LIBBPF_API struct bpf_map *
 bpf_object__find_map_by_offset(struct bpf_object *obj, size_t offset);
 
+LIBBPF_API LIBBPF_DEPRECATED_SINCE(0, 7, "use bpf_object__next_map() instead")
+struct bpf_map *bpf_map__next(const struct bpf_map *map, const struct bpf_object *obj);
 LIBBPF_API struct bpf_map *
-bpf_map__next(const struct bpf_map *map, const struct bpf_object *obj);
+bpf_object__next_map(const struct bpf_object *obj, const struct bpf_map *map);
+
 #define bpf_object__for_each_map(pos, obj)		\
-	for ((pos) = bpf_map__next(NULL, (obj));	\
+	for ((pos) = bpf_object__next_map((obj), NULL);	\
 	     (pos) != NULL;				\
-	     (pos) = bpf_map__next((pos), (obj)))
+	     (pos) = bpf_object__next_map((obj), (pos)))
 #define bpf_map__for_each bpf_object__for_each_map
 
+LIBBPF_API LIBBPF_DEPRECATED_SINCE(0, 7, "use bpf_object__prev_map() instead")
+struct bpf_map *bpf_map__prev(const struct bpf_map *map, const struct bpf_object *obj);
 LIBBPF_API struct bpf_map *
-bpf_map__prev(const struct bpf_map *map, const struct bpf_object *obj);
+bpf_object__prev_map(const struct bpf_object *obj, const struct bpf_map *map);
 
 /**
  * @brief **bpf_map__fd()** gets the file descriptor of the passed
diff --git a/tools/lib/bpf/libbpf.map b/tools/lib/bpf/libbpf.map
index f6b0db1e8c8b..f270d25e4af3 100644
--- a/tools/lib/bpf/libbpf.map
+++ b/tools/lib/bpf/libbpf.map
@@ -389,6 +389,10 @@ LIBBPF_0.5.0 {
 
 LIBBPF_0.6.0 {
 	global:
+		bpf_object__next_map;
+		bpf_object__next_program;
+		bpf_object__prev_map;
+		bpf_object__prev_program;
 		btf__add_btf;
 		btf__add_tag;
 } LIBBPF_0.5.0;
-- 
cgit v1.2.3


From 6f2b219b62a4376ca2da15c503de79d0650c8155 Mon Sep 17 00:00:00 2001
From: Hengqi Chen <hengqi.chen@gmail.com>
Date: Mon, 4 Oct 2021 00:58:44 +0800
Subject: selftests/bpf: Switch to new bpf_object__next_{map,program} APIs

Replace deprecated bpf_{map,program}__next APIs with newly added
bpf_object__next_{map,program} APIs, so that no compilation warnings
emit.

Signed-off-by: Hengqi Chen <hengqi.chen@gmail.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Acked-by: Song Liu <songliubraving@fb.com>
Link: https://lore.kernel.org/bpf/20211003165844.4054931-3-hengqi.chen@gmail.com
---
 tools/bpf/bpftool/iter.c                                  | 2 +-
 tools/bpf/bpftool/prog.c                                  | 2 +-
 tools/testing/selftests/bpf/prog_tests/btf.c              | 2 +-
 tools/testing/selftests/bpf/prog_tests/fexit_bpf2bpf.c    | 6 +++---
 tools/testing/selftests/bpf/prog_tests/select_reuseport.c | 2 +-
 tools/testing/selftests/bpf/prog_tests/tcp_rtt.c          | 2 +-
 tools/testing/selftests/bpf/xdping.c                      | 2 +-
 7 files changed, 9 insertions(+), 9 deletions(-)

(limited to 'tools')

diff --git a/tools/bpf/bpftool/iter.c b/tools/bpf/bpftool/iter.c
index 84a9b01d956d..6c0de647b8ad 100644
--- a/tools/bpf/bpftool/iter.c
+++ b/tools/bpf/bpftool/iter.c
@@ -57,7 +57,7 @@ static int do_pin(int argc, char **argv)
 		goto close_obj;
 	}
 
-	prog = bpf_program__next(NULL, obj);
+	prog = bpf_object__next_program(obj, NULL);
 	if (!prog) {
 		p_err("can't find bpf program in objfile %s", objfile);
 		goto close_obj;
diff --git a/tools/bpf/bpftool/prog.c b/tools/bpf/bpftool/prog.c
index 9c3e343b7d87..a24ea7e26aa4 100644
--- a/tools/bpf/bpftool/prog.c
+++ b/tools/bpf/bpftool/prog.c
@@ -1601,7 +1601,7 @@ static int load_with_options(int argc, char **argv, bool first_prog_only)
 		goto err_close_obj;
 
 	if (first_prog_only) {
-		prog = bpf_program__next(NULL, obj);
+		prog = bpf_object__next_program(obj, NULL);
 		if (!prog) {
 			p_err("object file doesn't contain any bpf program");
 			goto err_close_obj;
diff --git a/tools/testing/selftests/bpf/prog_tests/btf.c b/tools/testing/selftests/bpf/prog_tests/btf.c
index 9c85d7d27409..acd33d0cd5d9 100644
--- a/tools/testing/selftests/bpf/prog_tests/btf.c
+++ b/tools/testing/selftests/bpf/prog_tests/btf.c
@@ -4511,7 +4511,7 @@ static void do_test_file(unsigned int test_num)
 	if (CHECK(err, "obj: %d", err))
 		return;
 
-	prog = bpf_program__next(NULL, obj);
+	prog = bpf_object__next_program(obj, NULL);
 	if (CHECK(!prog, "Cannot find bpf_prog")) {
 		err = -1;
 		goto done;
diff --git a/tools/testing/selftests/bpf/prog_tests/fexit_bpf2bpf.c b/tools/testing/selftests/bpf/prog_tests/fexit_bpf2bpf.c
index c7c1816899bf..2839f4270a26 100644
--- a/tools/testing/selftests/bpf/prog_tests/fexit_bpf2bpf.c
+++ b/tools/testing/selftests/bpf/prog_tests/fexit_bpf2bpf.c
@@ -285,7 +285,7 @@ static void test_fmod_ret_freplace(void)
 	if (!ASSERT_OK_PTR(freplace_obj, "freplace_obj_open"))
 		goto out;
 
-	prog = bpf_program__next(NULL, freplace_obj);
+	prog = bpf_object__next_program(freplace_obj, NULL);
 	err = bpf_program__set_attach_target(prog, pkt_fd, NULL);
 	ASSERT_OK(err, "freplace__set_attach_target");
 
@@ -302,7 +302,7 @@ static void test_fmod_ret_freplace(void)
 		goto out;
 
 	attach_prog_fd = bpf_program__fd(prog);
-	prog = bpf_program__next(NULL, fmod_obj);
+	prog = bpf_object__next_program(fmod_obj, NULL);
 	err = bpf_program__set_attach_target(prog, attach_prog_fd, NULL);
 	ASSERT_OK(err, "fmod_ret_set_attach_target");
 
@@ -352,7 +352,7 @@ static void test_obj_load_failure_common(const char *obj_file,
 	if (!ASSERT_OK_PTR(obj, "obj_open"))
 		goto close_prog;
 
-	prog = bpf_program__next(NULL, obj);
+	prog = bpf_object__next_program(obj, NULL);
 	err = bpf_program__set_attach_target(prog, pkt_fd, NULL);
 	ASSERT_OK(err, "set_attach_target");
 
diff --git a/tools/testing/selftests/bpf/prog_tests/select_reuseport.c b/tools/testing/selftests/bpf/prog_tests/select_reuseport.c
index 4efd337d6a3c..d40e9156c48d 100644
--- a/tools/testing/selftests/bpf/prog_tests/select_reuseport.c
+++ b/tools/testing/selftests/bpf/prog_tests/select_reuseport.c
@@ -114,7 +114,7 @@ static int prepare_bpf_obj(void)
 	err = bpf_object__load(obj);
 	RET_ERR(err, "load bpf_object", "err:%d\n", err);
 
-	prog = bpf_program__next(NULL, obj);
+	prog = bpf_object__next_program(obj, NULL);
 	RET_ERR(!prog, "get first bpf_program", "!prog\n");
 	select_by_skb_data_prog = bpf_program__fd(prog);
 	RET_ERR(select_by_skb_data_prog < 0, "get prog fd",
diff --git a/tools/testing/selftests/bpf/prog_tests/tcp_rtt.c b/tools/testing/selftests/bpf/prog_tests/tcp_rtt.c
index d207e968e6b1..265b4fe33ec3 100644
--- a/tools/testing/selftests/bpf/prog_tests/tcp_rtt.c
+++ b/tools/testing/selftests/bpf/prog_tests/tcp_rtt.c
@@ -109,7 +109,7 @@ static int run_test(int cgroup_fd, int server_fd)
 		return -1;
 	}
 
-	map = bpf_map__next(NULL, obj);
+	map = bpf_object__next_map(obj, NULL);
 	map_fd = bpf_map__fd(map);
 
 	err = bpf_prog_attach(prog_fd, cgroup_fd, BPF_CGROUP_SOCK_OPS, 0);
diff --git a/tools/testing/selftests/bpf/xdping.c b/tools/testing/selftests/bpf/xdping.c
index 79a3453dab25..30f12637f4e4 100644
--- a/tools/testing/selftests/bpf/xdping.c
+++ b/tools/testing/selftests/bpf/xdping.c
@@ -187,7 +187,7 @@ int main(int argc, char **argv)
 		return 1;
 	}
 
-	map = bpf_map__next(NULL, obj);
+	map = bpf_object__next_map(obj, NULL);
 	if (map)
 		map_fd = bpf_map__fd(map);
 	if (!map || map_fd < 0) {
-- 
cgit v1.2.3


From aa67fdb4643616f04cb59b6d090010c371ab1a80 Mon Sep 17 00:00:00 2001
From: Song Liu <songliubraving@fb.com>
Date: Wed, 6 Oct 2021 22:02:31 -0700
Subject: selftests/bpf: Skip the second half of get_branch_snapshot in vm

VMs running on upstream 5.12+ kernel support LBR. However,
bpf_get_branch_snapshot couldn't stop the LBR before too many entries
are flushed. Skip the hit/waste test for VMs before we find a proper fix
for LBR in VM.

Fixes: 025bd7c753aa ("selftests/bpf: Add test for bpf_get_branch_snapshot")
Signed-off-by: Song Liu <songliubraving@fb.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20211007050231.728496-1-songliubraving@fb.com
---
 .../selftests/bpf/prog_tests/get_branch_snapshot.c | 34 ++++++++++++++++++++++
 1 file changed, 34 insertions(+)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/prog_tests/get_branch_snapshot.c b/tools/testing/selftests/bpf/prog_tests/get_branch_snapshot.c
index 67e86f8d8677..e4f92feb7b32 100644
--- a/tools/testing/selftests/bpf/prog_tests/get_branch_snapshot.c
+++ b/tools/testing/selftests/bpf/prog_tests/get_branch_snapshot.c
@@ -6,6 +6,30 @@
 static int *pfd_array;
 static int cpu_cnt;
 
+static bool is_hypervisor(void)
+{
+	char *line = NULL;
+	bool ret = false;
+	size_t len;
+	FILE *fp;
+
+	fp = fopen("/proc/cpuinfo", "r");
+	if (!fp)
+		return false;
+
+	while (getline(&line, &len, fp) != -1) {
+		if (!strncmp(line, "flags", 5)) {
+			if (strstr(line, "hypervisor") != NULL)
+				ret = true;
+			break;
+		}
+	}
+
+	free(line);
+	fclose(fp);
+	return ret;
+}
+
 static int create_perf_events(void)
 {
 	struct perf_event_attr attr = {0};
@@ -83,6 +107,16 @@ void test_get_branch_snapshot(void)
 		goto cleanup;
 	}
 
+	if (is_hypervisor()) {
+		/* As of today, LBR in hypervisor cannot be stopped before
+		 * too many entries are flushed. Skip the hit/waste test
+		 * for now in hypervisor until we optimize the LBR in
+		 * hypervisor.
+		 */
+		test__skip();
+		goto cleanup;
+	}
+
 	ASSERT_GT(skel->bss->test1_hits, 6, "find_looptest_in_lbr");
 
 	/* Given we stop LBR in software, we will waste a few entries.
-- 
cgit v1.2.3


From dd65acf72d0e073970459d5da80573a04304aaa9 Mon Sep 17 00:00:00 2001
From: Dave Marchevsky <davemarchevsky@fb.com>
Date: Thu, 7 Oct 2021 16:12:34 -0700
Subject: selftests/bpf: Remove SEC("version") from test progs

Since commit 6c4fc209fcf9d ("bpf: remove useless version check for prog
load") these "version" sections, which result in bpf_attr.kern_version
being set, have been unnecessary.

Remove them so that it's obvious to folks using selftests as a guide that
"modern" BPF progs don't need this section.

Signed-off-by: Dave Marchevsky <davemarchevsky@fb.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20211007231234.2223081-1-davemarchevsky@fb.com
---
 tools/testing/selftests/bpf/progs/cgroup_skb_sk_lookup_kern.c  | 1 -
 tools/testing/selftests/bpf/progs/connect4_prog.c              | 2 --
 tools/testing/selftests/bpf/progs/connect6_prog.c              | 2 --
 tools/testing/selftests/bpf/progs/connect_force_port4.c        | 1 -
 tools/testing/selftests/bpf/progs/connect_force_port6.c        | 1 -
 tools/testing/selftests/bpf/progs/dev_cgroup.c                 | 1 -
 tools/testing/selftests/bpf/progs/get_cgroup_id_kern.c         | 1 -
 tools/testing/selftests/bpf/progs/map_ptr_kern.c               | 1 -
 tools/testing/selftests/bpf/progs/netcnt_prog.c                | 1 -
 tools/testing/selftests/bpf/progs/sendmsg4_prog.c              | 2 --
 tools/testing/selftests/bpf/progs/sendmsg6_prog.c              | 2 --
 tools/testing/selftests/bpf/progs/sockmap_parse_prog.c         | 2 --
 tools/testing/selftests/bpf/progs/sockmap_tcp_msg_prog.c       | 2 --
 tools/testing/selftests/bpf/progs/sockmap_verdict_prog.c       | 2 --
 tools/testing/selftests/bpf/progs/sockopt_inherit.c            | 1 -
 tools/testing/selftests/bpf/progs/tcp_rtt.c                    | 1 -
 tools/testing/selftests/bpf/progs/test_btf_haskv.c             | 2 --
 tools/testing/selftests/bpf/progs/test_btf_newkv.c             | 2 --
 tools/testing/selftests/bpf/progs/test_btf_nokv.c              | 2 --
 tools/testing/selftests/bpf/progs/test_l4lb.c                  | 2 --
 tools/testing/selftests/bpf/progs/test_map_in_map.c            | 1 -
 tools/testing/selftests/bpf/progs/test_pinning.c               | 2 --
 tools/testing/selftests/bpf/progs/test_pinning_invalid.c       | 2 --
 tools/testing/selftests/bpf/progs/test_pkt_access.c            | 1 -
 tools/testing/selftests/bpf/progs/test_queue_stack_map.h       | 2 --
 tools/testing/selftests/bpf/progs/test_select_reuseport_kern.c | 2 --
 tools/testing/selftests/bpf/progs/test_sk_lookup.c             | 1 -
 tools/testing/selftests/bpf/progs/test_skb_cgroup_id_kern.c    | 2 --
 tools/testing/selftests/bpf/progs/test_skb_ctx.c               | 1 -
 tools/testing/selftests/bpf/progs/test_sockmap_kern.h          | 1 -
 tools/testing/selftests/bpf/progs/test_sockmap_listen.c        | 1 -
 tools/testing/selftests/bpf/progs/test_stacktrace_build_id.c   | 1 -
 tools/testing/selftests/bpf/progs/test_tcp_estats.c            | 1 -
 tools/testing/selftests/bpf/progs/test_tcpbpf_kern.c           | 1 -
 tools/testing/selftests/bpf/progs/test_tcpnotify_kern.c        | 2 --
 tools/testing/selftests/bpf/progs/test_tracepoint.c            | 1 -
 tools/testing/selftests/bpf/progs/test_tunnel_kern.c           | 2 --
 tools/testing/selftests/bpf/progs/test_xdp.c                   | 2 --
 tools/testing/selftests/bpf/progs/test_xdp_loop.c              | 2 --
 tools/testing/selftests/bpf/progs/test_xdp_redirect.c          | 2 --
 40 files changed, 61 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/progs/cgroup_skb_sk_lookup_kern.c b/tools/testing/selftests/bpf/progs/cgroup_skb_sk_lookup_kern.c
index 3f757e30d7a0..88638315c582 100644
--- a/tools/testing/selftests/bpf/progs/cgroup_skb_sk_lookup_kern.c
+++ b/tools/testing/selftests/bpf/progs/cgroup_skb_sk_lookup_kern.c
@@ -14,7 +14,6 @@
 #include <sys/types.h>
 #include <sys/socket.h>
 
-int _version SEC("version") = 1;
 char _license[] SEC("license") = "GPL";
 
 __u16 g_serv_port = 0;
diff --git a/tools/testing/selftests/bpf/progs/connect4_prog.c b/tools/testing/selftests/bpf/progs/connect4_prog.c
index a943d394fd3a..b241932911db 100644
--- a/tools/testing/selftests/bpf/progs/connect4_prog.c
+++ b/tools/testing/selftests/bpf/progs/connect4_prog.c
@@ -31,8 +31,6 @@
 #define IFNAMSIZ 16
 #endif
 
-int _version SEC("version") = 1;
-
 __attribute__ ((noinline))
 int do_bind(struct bpf_sock_addr *ctx)
 {
diff --git a/tools/testing/selftests/bpf/progs/connect6_prog.c b/tools/testing/selftests/bpf/progs/connect6_prog.c
index 506d0f81a375..40266d2c737c 100644
--- a/tools/testing/selftests/bpf/progs/connect6_prog.c
+++ b/tools/testing/selftests/bpf/progs/connect6_prog.c
@@ -24,8 +24,6 @@
 
 #define DST_REWRITE_PORT6	6666
 
-int _version SEC("version") = 1;
-
 SEC("cgroup/connect6")
 int connect_v6_prog(struct bpf_sock_addr *ctx)
 {
diff --git a/tools/testing/selftests/bpf/progs/connect_force_port4.c b/tools/testing/selftests/bpf/progs/connect_force_port4.c
index a979aaef2a76..27a632dd382e 100644
--- a/tools/testing/selftests/bpf/progs/connect_force_port4.c
+++ b/tools/testing/selftests/bpf/progs/connect_force_port4.c
@@ -13,7 +13,6 @@
 #include <bpf_sockopt_helpers.h>
 
 char _license[] SEC("license") = "GPL";
-int _version SEC("version") = 1;
 
 struct svc_addr {
 	__be32 addr;
diff --git a/tools/testing/selftests/bpf/progs/connect_force_port6.c b/tools/testing/selftests/bpf/progs/connect_force_port6.c
index afc8f1c5a9d6..19cad93e612f 100644
--- a/tools/testing/selftests/bpf/progs/connect_force_port6.c
+++ b/tools/testing/selftests/bpf/progs/connect_force_port6.c
@@ -12,7 +12,6 @@
 #include <bpf_sockopt_helpers.h>
 
 char _license[] SEC("license") = "GPL";
-int _version SEC("version") = 1;
 
 struct svc_addr {
 	__be32 addr[4];
diff --git a/tools/testing/selftests/bpf/progs/dev_cgroup.c b/tools/testing/selftests/bpf/progs/dev_cgroup.c
index 8924e06bdef0..79b54a4fa244 100644
--- a/tools/testing/selftests/bpf/progs/dev_cgroup.c
+++ b/tools/testing/selftests/bpf/progs/dev_cgroup.c
@@ -57,4 +57,3 @@ int bpf_prog1(struct bpf_cgroup_dev_ctx *ctx)
 }
 
 char _license[] SEC("license") = "GPL";
-__u32 _version SEC("version") = LINUX_VERSION_CODE;
diff --git a/tools/testing/selftests/bpf/progs/get_cgroup_id_kern.c b/tools/testing/selftests/bpf/progs/get_cgroup_id_kern.c
index 6b42db2fe391..68587b1de34e 100644
--- a/tools/testing/selftests/bpf/progs/get_cgroup_id_kern.c
+++ b/tools/testing/selftests/bpf/progs/get_cgroup_id_kern.c
@@ -37,4 +37,3 @@ int trace(void *ctx)
 }
 
 char _license[] SEC("license") = "GPL";
-__u32 _version SEC("version") = 1; /* ignored by tracepoints, required by libbpf.a */
diff --git a/tools/testing/selftests/bpf/progs/map_ptr_kern.c b/tools/testing/selftests/bpf/progs/map_ptr_kern.c
index d1d304c980f0..b1b711d9b214 100644
--- a/tools/testing/selftests/bpf/progs/map_ptr_kern.c
+++ b/tools/testing/selftests/bpf/progs/map_ptr_kern.c
@@ -683,5 +683,4 @@ int cg_skb(void *ctx)
 	return 1;
 }
 
-__u32 _version SEC("version") = 1;
 char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/netcnt_prog.c b/tools/testing/selftests/bpf/progs/netcnt_prog.c
index 43649bce4c54..f718b2c212dc 100644
--- a/tools/testing/selftests/bpf/progs/netcnt_prog.c
+++ b/tools/testing/selftests/bpf/progs/netcnt_prog.c
@@ -68,4 +68,3 @@ int bpf_nextcnt(struct __sk_buff *skb)
 }
 
 char _license[] SEC("license") = "GPL";
-__u32 _version SEC("version") = LINUX_VERSION_CODE;
diff --git a/tools/testing/selftests/bpf/progs/sendmsg4_prog.c b/tools/testing/selftests/bpf/progs/sendmsg4_prog.c
index ac5abc34cde8..ea75a44cb7fc 100644
--- a/tools/testing/selftests/bpf/progs/sendmsg4_prog.c
+++ b/tools/testing/selftests/bpf/progs/sendmsg4_prog.c
@@ -18,8 +18,6 @@
 #define DST_PORT		4040
 #define DST_REWRITE_PORT4	4444
 
-int _version SEC("version") = 1;
-
 SEC("cgroup/sendmsg4")
 int sendmsg_v4_prog(struct bpf_sock_addr *ctx)
 {
diff --git a/tools/testing/selftests/bpf/progs/sendmsg6_prog.c b/tools/testing/selftests/bpf/progs/sendmsg6_prog.c
index 24694b1a8d82..bf9b46b806f6 100644
--- a/tools/testing/selftests/bpf/progs/sendmsg6_prog.c
+++ b/tools/testing/selftests/bpf/progs/sendmsg6_prog.c
@@ -22,8 +22,6 @@
 
 #define DST_REWRITE_PORT6	6666
 
-int _version SEC("version") = 1;
-
 SEC("cgroup/sendmsg6")
 int sendmsg_v6_prog(struct bpf_sock_addr *ctx)
 {
diff --git a/tools/testing/selftests/bpf/progs/sockmap_parse_prog.c b/tools/testing/selftests/bpf/progs/sockmap_parse_prog.c
index ca283af80d4e..95d5b941bc1f 100644
--- a/tools/testing/selftests/bpf/progs/sockmap_parse_prog.c
+++ b/tools/testing/selftests/bpf/progs/sockmap_parse_prog.c
@@ -2,8 +2,6 @@
 #include <bpf/bpf_helpers.h>
 #include <bpf/bpf_endian.h>
 
-int _version SEC("version") = 1;
-
 SEC("sk_skb1")
 int bpf_prog1(struct __sk_buff *skb)
 {
diff --git a/tools/testing/selftests/bpf/progs/sockmap_tcp_msg_prog.c b/tools/testing/selftests/bpf/progs/sockmap_tcp_msg_prog.c
index eeaf6e75c9a2..80632954c5a1 100644
--- a/tools/testing/selftests/bpf/progs/sockmap_tcp_msg_prog.c
+++ b/tools/testing/selftests/bpf/progs/sockmap_tcp_msg_prog.c
@@ -3,8 +3,6 @@
 #include <bpf/bpf_helpers.h>
 #include <bpf/bpf_endian.h>
 
-int _version SEC("version") = 1;
-
 SEC("sk_msg1")
 int bpf_prog1(struct sk_msg_md *msg)
 {
diff --git a/tools/testing/selftests/bpf/progs/sockmap_verdict_prog.c b/tools/testing/selftests/bpf/progs/sockmap_verdict_prog.c
index 73872c535cbb..e2468a6d01a5 100644
--- a/tools/testing/selftests/bpf/progs/sockmap_verdict_prog.c
+++ b/tools/testing/selftests/bpf/progs/sockmap_verdict_prog.c
@@ -2,8 +2,6 @@
 #include <bpf/bpf_helpers.h>
 #include <bpf/bpf_endian.h>
 
-int _version SEC("version") = 1;
-
 struct {
 	__uint(type, BPF_MAP_TYPE_SOCKMAP);
 	__uint(max_entries, 20);
diff --git a/tools/testing/selftests/bpf/progs/sockopt_inherit.c b/tools/testing/selftests/bpf/progs/sockopt_inherit.c
index c6d428a8d785..9fb241b97291 100644
--- a/tools/testing/selftests/bpf/progs/sockopt_inherit.c
+++ b/tools/testing/selftests/bpf/progs/sockopt_inherit.c
@@ -3,7 +3,6 @@
 #include <bpf/bpf_helpers.h>
 
 char _license[] SEC("license") = "GPL";
-__u32 _version SEC("version") = 1;
 
 #define SOL_CUSTOM			0xdeadbeef
 #define CUSTOM_INHERIT1			0
diff --git a/tools/testing/selftests/bpf/progs/tcp_rtt.c b/tools/testing/selftests/bpf/progs/tcp_rtt.c
index 0cb3204ddb18..0988d79f1587 100644
--- a/tools/testing/selftests/bpf/progs/tcp_rtt.c
+++ b/tools/testing/selftests/bpf/progs/tcp_rtt.c
@@ -3,7 +3,6 @@
 #include <bpf/bpf_helpers.h>
 
 char _license[] SEC("license") = "GPL";
-__u32 _version SEC("version") = 1;
 
 struct tcp_rtt_storage {
 	__u32 invoked;
diff --git a/tools/testing/selftests/bpf/progs/test_btf_haskv.c b/tools/testing/selftests/bpf/progs/test_btf_haskv.c
index 31538c9ed193..160ead6c67b2 100644
--- a/tools/testing/selftests/bpf/progs/test_btf_haskv.c
+++ b/tools/testing/selftests/bpf/progs/test_btf_haskv.c
@@ -4,8 +4,6 @@
 #include <bpf/bpf_helpers.h>
 #include "bpf_legacy.h"
 
-int _version SEC("version") = 1;
-
 struct ipv_counts {
 	unsigned int v4;
 	unsigned int v6;
diff --git a/tools/testing/selftests/bpf/progs/test_btf_newkv.c b/tools/testing/selftests/bpf/progs/test_btf_newkv.c
index 6c5560162746..1884a5bd10f5 100644
--- a/tools/testing/selftests/bpf/progs/test_btf_newkv.c
+++ b/tools/testing/selftests/bpf/progs/test_btf_newkv.c
@@ -4,8 +4,6 @@
 #include <bpf/bpf_helpers.h>
 #include "bpf_legacy.h"
 
-int _version SEC("version") = 1;
-
 struct ipv_counts {
 	unsigned int v4;
 	unsigned int v6;
diff --git a/tools/testing/selftests/bpf/progs/test_btf_nokv.c b/tools/testing/selftests/bpf/progs/test_btf_nokv.c
index 506da7fd2da2..15e0f9945fe4 100644
--- a/tools/testing/selftests/bpf/progs/test_btf_nokv.c
+++ b/tools/testing/selftests/bpf/progs/test_btf_nokv.c
@@ -3,8 +3,6 @@
 #include <linux/bpf.h>
 #include <bpf/bpf_helpers.h>
 
-int _version SEC("version") = 1;
-
 struct ipv_counts {
 	unsigned int v4;
 	unsigned int v6;
diff --git a/tools/testing/selftests/bpf/progs/test_l4lb.c b/tools/testing/selftests/bpf/progs/test_l4lb.c
index 33493911d87a..04fee08863cb 100644
--- a/tools/testing/selftests/bpf/progs/test_l4lb.c
+++ b/tools/testing/selftests/bpf/progs/test_l4lb.c
@@ -21,8 +21,6 @@
 #include "test_iptunnel_common.h"
 #include <bpf/bpf_endian.h>
 
-int _version SEC("version") = 1;
-
 static inline __u32 rol32(__u32 word, unsigned int shift)
 {
 	return (word << shift) | (word >> ((-shift) & 31));
diff --git a/tools/testing/selftests/bpf/progs/test_map_in_map.c b/tools/testing/selftests/bpf/progs/test_map_in_map.c
index a6d91932dcd5..f416032ba858 100644
--- a/tools/testing/selftests/bpf/progs/test_map_in_map.c
+++ b/tools/testing/selftests/bpf/progs/test_map_in_map.c
@@ -47,5 +47,4 @@ int xdp_mimtest0(struct xdp_md *ctx)
 	return XDP_PASS;
 }
 
-int _version SEC("version") = 1;
 char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/test_pinning.c b/tools/testing/selftests/bpf/progs/test_pinning.c
index 4ef2630292b2..0facea6cbbae 100644
--- a/tools/testing/selftests/bpf/progs/test_pinning.c
+++ b/tools/testing/selftests/bpf/progs/test_pinning.c
@@ -3,8 +3,6 @@
 #include <linux/bpf.h>
 #include <bpf/bpf_helpers.h>
 
-int _version SEC("version") = 1;
-
 struct {
 	__uint(type, BPF_MAP_TYPE_ARRAY);
 	__uint(max_entries, 1);
diff --git a/tools/testing/selftests/bpf/progs/test_pinning_invalid.c b/tools/testing/selftests/bpf/progs/test_pinning_invalid.c
index 5412e0c732c7..2a56db1094b8 100644
--- a/tools/testing/selftests/bpf/progs/test_pinning_invalid.c
+++ b/tools/testing/selftests/bpf/progs/test_pinning_invalid.c
@@ -3,8 +3,6 @@
 #include <linux/bpf.h>
 #include <bpf/bpf_helpers.h>
 
-int _version SEC("version") = 1;
-
 struct {
 	__uint(type, BPF_MAP_TYPE_ARRAY);
 	__uint(max_entries, 1);
diff --git a/tools/testing/selftests/bpf/progs/test_pkt_access.c b/tools/testing/selftests/bpf/progs/test_pkt_access.c
index 3cfd88141ddc..0558544e1ff0 100644
--- a/tools/testing/selftests/bpf/progs/test_pkt_access.c
+++ b/tools/testing/selftests/bpf/progs/test_pkt_access.c
@@ -15,7 +15,6 @@
 #include <bpf/bpf_endian.h>
 
 #define barrier() __asm__ __volatile__("": : :"memory")
-int _version SEC("version") = 1;
 
 /* llvm will optimize both subprograms into exactly the same BPF assembly
  *
diff --git a/tools/testing/selftests/bpf/progs/test_queue_stack_map.h b/tools/testing/selftests/bpf/progs/test_queue_stack_map.h
index 4dd9806ad73b..0fcd3ff0e38a 100644
--- a/tools/testing/selftests/bpf/progs/test_queue_stack_map.h
+++ b/tools/testing/selftests/bpf/progs/test_queue_stack_map.h
@@ -8,8 +8,6 @@
 #include <linux/pkt_cls.h>
 #include <bpf/bpf_helpers.h>
 
-int _version SEC("version") = 1;
-
 struct {
 	__uint(type, MAP_TYPE);
 	__uint(max_entries, 32);
diff --git a/tools/testing/selftests/bpf/progs/test_select_reuseport_kern.c b/tools/testing/selftests/bpf/progs/test_select_reuseport_kern.c
index 0f9bc258225e..7d56ed47cd4d 100644
--- a/tools/testing/selftests/bpf/progs/test_select_reuseport_kern.c
+++ b/tools/testing/selftests/bpf/progs/test_select_reuseport_kern.c
@@ -15,8 +15,6 @@
 #include <bpf/bpf_helpers.h>
 #include "test_select_reuseport_common.h"
 
-int _version SEC("version") = 1;
-
 #ifndef offsetof
 #define offsetof(TYPE, MEMBER) ((size_t) &((TYPE *)0)->MEMBER)
 #endif
diff --git a/tools/testing/selftests/bpf/progs/test_sk_lookup.c b/tools/testing/selftests/bpf/progs/test_sk_lookup.c
index 48534d810391..19d2465d9442 100644
--- a/tools/testing/selftests/bpf/progs/test_sk_lookup.c
+++ b/tools/testing/selftests/bpf/progs/test_sk_lookup.c
@@ -644,4 +644,3 @@ int multi_prog_redir2(struct bpf_sk_lookup *ctx)
 }
 
 char _license[] SEC("license") = "Dual BSD/GPL";
-__u32 _version SEC("version") = 1;
diff --git a/tools/testing/selftests/bpf/progs/test_skb_cgroup_id_kern.c b/tools/testing/selftests/bpf/progs/test_skb_cgroup_id_kern.c
index 552f2090665c..c304cd5b8cad 100644
--- a/tools/testing/selftests/bpf/progs/test_skb_cgroup_id_kern.c
+++ b/tools/testing/selftests/bpf/progs/test_skb_cgroup_id_kern.c
@@ -42,6 +42,4 @@ int log_cgroup_id(struct __sk_buff *skb)
 	return TC_ACT_OK;
 }
 
-int _version SEC("version") = 1;
-
 char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/test_skb_ctx.c b/tools/testing/selftests/bpf/progs/test_skb_ctx.c
index ba4dab09d19c..1d61b36e6067 100644
--- a/tools/testing/selftests/bpf/progs/test_skb_ctx.c
+++ b/tools/testing/selftests/bpf/progs/test_skb_ctx.c
@@ -3,7 +3,6 @@
 #include <linux/bpf.h>
 #include <bpf/bpf_helpers.h>
 
-int _version SEC("version") = 1;
 char _license[] SEC("license") = "GPL";
 
 SEC("skb_ctx")
diff --git a/tools/testing/selftests/bpf/progs/test_sockmap_kern.h b/tools/testing/selftests/bpf/progs/test_sockmap_kern.h
index 1858435de7aa..2966564b8497 100644
--- a/tools/testing/selftests/bpf/progs/test_sockmap_kern.h
+++ b/tools/testing/selftests/bpf/progs/test_sockmap_kern.h
@@ -361,5 +361,4 @@ int bpf_prog10(struct sk_msg_md *msg)
 	return SK_DROP;
 }
 
-int _version SEC("version") = 1;
 char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/test_sockmap_listen.c b/tools/testing/selftests/bpf/progs/test_sockmap_listen.c
index 00f1456aaeda..325c9f193432 100644
--- a/tools/testing/selftests/bpf/progs/test_sockmap_listen.c
+++ b/tools/testing/selftests/bpf/progs/test_sockmap_listen.c
@@ -116,5 +116,4 @@ int prog_reuseport(struct sk_reuseport_md *reuse)
 	return verdict;
 }
 
-int _version SEC("version") = 1;
 char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/test_stacktrace_build_id.c b/tools/testing/selftests/bpf/progs/test_stacktrace_build_id.c
index 7449fdb1763b..36a707e7c7a7 100644
--- a/tools/testing/selftests/bpf/progs/test_stacktrace_build_id.c
+++ b/tools/testing/selftests/bpf/progs/test_stacktrace_build_id.c
@@ -73,4 +73,3 @@ int oncpu(struct random_urandom_args *args)
 }
 
 char _license[] SEC("license") = "GPL";
-__u32 _version SEC("version") = 1; /* ignored by tracepoints, required by libbpf.a */
diff --git a/tools/testing/selftests/bpf/progs/test_tcp_estats.c b/tools/testing/selftests/bpf/progs/test_tcp_estats.c
index adc83a54c352..2c5c602c6011 100644
--- a/tools/testing/selftests/bpf/progs/test_tcp_estats.c
+++ b/tools/testing/selftests/bpf/progs/test_tcp_estats.c
@@ -255,4 +255,3 @@ int _dummy_tracepoint(struct dummy_tracepoint_args *arg)
 }
 
 char _license[] SEC("license") = "GPL";
-__u32 _version SEC("version") = 1; /* ignored by tracepoints, required by libbpf.a */
diff --git a/tools/testing/selftests/bpf/progs/test_tcpbpf_kern.c b/tools/testing/selftests/bpf/progs/test_tcpbpf_kern.c
index 94f50f7e94d6..3ded05280757 100644
--- a/tools/testing/selftests/bpf/progs/test_tcpbpf_kern.c
+++ b/tools/testing/selftests/bpf/progs/test_tcpbpf_kern.c
@@ -16,7 +16,6 @@
 #include "test_tcpbpf.h"
 
 struct tcpbpf_globals global = {};
-int _version SEC("version") = 1;
 
 /**
  * SOL_TCP is defined in <netinet/tcp.h> while
diff --git a/tools/testing/selftests/bpf/progs/test_tcpnotify_kern.c b/tools/testing/selftests/bpf/progs/test_tcpnotify_kern.c
index 24e9344994ef..540181c115a8 100644
--- a/tools/testing/selftests/bpf/progs/test_tcpnotify_kern.c
+++ b/tools/testing/selftests/bpf/progs/test_tcpnotify_kern.c
@@ -28,8 +28,6 @@ struct {
 	__type(value, __u32);
 } perf_event_map SEC(".maps");
 
-int _version SEC("version") = 1;
-
 SEC("sockops")
 int bpf_testcb(struct bpf_sock_ops *skops)
 {
diff --git a/tools/testing/selftests/bpf/progs/test_tracepoint.c b/tools/testing/selftests/bpf/progs/test_tracepoint.c
index 4b825ee122cf..ce6974016f53 100644
--- a/tools/testing/selftests/bpf/progs/test_tracepoint.c
+++ b/tools/testing/selftests/bpf/progs/test_tracepoint.c
@@ -23,4 +23,3 @@ int oncpu(struct sched_switch_args *ctx)
 }
 
 char _license[] SEC("license") = "GPL";
-__u32 _version SEC("version") = 1; /* ignored by tracepoints, required by libbpf.a */
diff --git a/tools/testing/selftests/bpf/progs/test_tunnel_kern.c b/tools/testing/selftests/bpf/progs/test_tunnel_kern.c
index e7b673117436..ef0dde83b85a 100644
--- a/tools/testing/selftests/bpf/progs/test_tunnel_kern.c
+++ b/tools/testing/selftests/bpf/progs/test_tunnel_kern.c
@@ -26,8 +26,6 @@
 		bpf_trace_printk(fmt, sizeof(fmt), __LINE__, ret); \
 	} while (0)
 
-int _version SEC("version") = 1;
-
 struct geneve_opt {
 	__be16	opt_class;
 	__u8	type;
diff --git a/tools/testing/selftests/bpf/progs/test_xdp.c b/tools/testing/selftests/bpf/progs/test_xdp.c
index e6aa2fc6ce6b..d7a9a74b7245 100644
--- a/tools/testing/selftests/bpf/progs/test_xdp.c
+++ b/tools/testing/selftests/bpf/progs/test_xdp.c
@@ -20,8 +20,6 @@
 #include <bpf/bpf_endian.h>
 #include "test_iptunnel_common.h"
 
-int _version SEC("version") = 1;
-
 struct {
 	__uint(type, BPF_MAP_TYPE_PERCPU_ARRAY);
 	__uint(max_entries, 256);
diff --git a/tools/testing/selftests/bpf/progs/test_xdp_loop.c b/tools/testing/selftests/bpf/progs/test_xdp_loop.c
index 27eb52dda92c..c98fb44156f0 100644
--- a/tools/testing/selftests/bpf/progs/test_xdp_loop.c
+++ b/tools/testing/selftests/bpf/progs/test_xdp_loop.c
@@ -16,8 +16,6 @@
 #include <bpf/bpf_endian.h>
 #include "test_iptunnel_common.h"
 
-int _version SEC("version") = 1;
-
 struct {
 	__uint(type, BPF_MAP_TYPE_PERCPU_ARRAY);
 	__uint(max_entries, 256);
diff --git a/tools/testing/selftests/bpf/progs/test_xdp_redirect.c b/tools/testing/selftests/bpf/progs/test_xdp_redirect.c
index a5337cd9400b..b778cad45485 100644
--- a/tools/testing/selftests/bpf/progs/test_xdp_redirect.c
+++ b/tools/testing/selftests/bpf/progs/test_xdp_redirect.c
@@ -12,8 +12,6 @@
 #include <linux/bpf.h>
 #include <bpf/bpf_helpers.h>
 
-int _version SEC("version") = 1;
-
 SEC("redirect_to_111")
 int xdp_redirect_to_111(struct xdp_md *xdp)
 {
-- 
cgit v1.2.3


From 45d45e5323a9dab88ab1b50264d1e19242935176 Mon Sep 17 00:00:00 2001
From: Amit Cohen <amcohen@nvidia.com>
Date: Fri, 8 Oct 2021 16:12:34 +0300
Subject: testing: selftests: forwarding.config.sample: Add tc flag

Add TC_FLAG value to tests topology.
This flag supposed to be skip_sw/skip_hw which means do not filter by
software/hardware.

This can be useful for adding tests to forwarding directory, and be able
to verify that packets go through the hardware.

When the flag is not set or set to 'skip_hw', tests can still be executed
with veth pairs.

Signed-off-by: Amit Cohen <amcohen@nvidia.com>
Reviewed-by: Petr Machata <petrm@nvidia.com>
Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/forwarding/forwarding.config.sample | 3 +++
 1 file changed, 3 insertions(+)

(limited to 'tools')

diff --git a/tools/testing/selftests/net/forwarding/forwarding.config.sample b/tools/testing/selftests/net/forwarding/forwarding.config.sample
index b802c14d2950..10ce3720aa6f 100644
--- a/tools/testing/selftests/net/forwarding/forwarding.config.sample
+++ b/tools/testing/selftests/net/forwarding/forwarding.config.sample
@@ -39,3 +39,6 @@ NETIF_CREATE=yes
 # Timeout (in seconds) before ping exits regardless of how many packets have
 # been sent or received
 PING_TIMEOUT=5
+# Flag for tc match, supposed to be skip_sw/skip_hw which means do not process
+# filter by software/hardware
+TC_FLAG=skip_hw
-- 
cgit v1.2.3


From c08d227290f618ada4028f0303743263cc026dd9 Mon Sep 17 00:00:00 2001
From: Amit Cohen <amcohen@nvidia.com>
Date: Fri, 8 Oct 2021 16:12:35 +0300
Subject: testing: selftests: tc_common: Add tc_check_at_least_x_packets()

Add function that checks that at least X packets hit the tc rule.
There are cases that it is not possible to catch only the interesting
packets, so then, it is possible to send many packets and verify that at
least this amount of packets hit the rule.

This function will be used in the next patch for general tc rule that
can be used to test both software and hardware.

Signed-off-by: Amit Cohen <amcohen@nvidia.com>
Reviewed-by: Petr Machata <petrm@nvidia.com>
Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/forwarding/tc_common.sh | 10 ++++++++++
 1 file changed, 10 insertions(+)

(limited to 'tools')

diff --git a/tools/testing/selftests/net/forwarding/tc_common.sh b/tools/testing/selftests/net/forwarding/tc_common.sh
index 0e18e8be6e2a..bce8bb8d2b6f 100644
--- a/tools/testing/selftests/net/forwarding/tc_common.sh
+++ b/tools/testing/selftests/net/forwarding/tc_common.sh
@@ -16,6 +16,16 @@ tc_check_packets()
 		 tc_rule_handle_stats_get "$id" "$handle" > /dev/null
 }
 
+tc_check_at_least_x_packets()
+{
+	local id=$1
+	local handle=$2
+	local count=$3
+
+	busywait "$TC_HIT_TIMEOUT" until_counter_is ">= $count" \
+		 tc_rule_handle_stats_get "$id" "$handle" > /dev/null
+}
+
 tc_check_packets_hitting()
 {
 	local id=$1
-- 
cgit v1.2.3


From 7df29960fa65bb11a5571468056155ca04d8f6df Mon Sep 17 00:00:00 2001
From: Amit Cohen <amcohen@nvidia.com>
Date: Fri, 8 Oct 2021 16:12:36 +0300
Subject: selftests: forwarding: Add IPv6 GRE flat tests

Add tests that check IPv6-in-IPv6, IPv4-in-IPv6 and MTU change of GRE
tunnel. The tests use flat model - overlay and underlay share the same VRF.

These tests can be run with TC_FLAG=skip_sw, so then they will verify
that packets go through hardware as part of enacp and decap phases.

Signed-off-by: Amit Cohen <amcohen@nvidia.com>
Reviewed-by: Petr Machata <petrm@nvidia.com>
Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../selftests/net/forwarding/ip6gre_flat.sh        |  65 +++++
 .../selftests/net/forwarding/ip6gre_flat_key.sh    |  65 +++++
 .../selftests/net/forwarding/ip6gre_flat_keys.sh   |  65 +++++
 .../testing/selftests/net/forwarding/ip6gre_lib.sh | 270 +++++++++++++++++++++
 4 files changed, 465 insertions(+)
 create mode 100755 tools/testing/selftests/net/forwarding/ip6gre_flat.sh
 create mode 100755 tools/testing/selftests/net/forwarding/ip6gre_flat_key.sh
 create mode 100755 tools/testing/selftests/net/forwarding/ip6gre_flat_keys.sh
 create mode 100644 tools/testing/selftests/net/forwarding/ip6gre_lib.sh

(limited to 'tools')

diff --git a/tools/testing/selftests/net/forwarding/ip6gre_flat.sh b/tools/testing/selftests/net/forwarding/ip6gre_flat.sh
new file mode 100755
index 000000000000..96c97064f2d3
--- /dev/null
+++ b/tools/testing/selftests/net/forwarding/ip6gre_flat.sh
@@ -0,0 +1,65 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+# Test IP-in-IP GRE tunnel without key.
+# This test uses flat topology for IP tunneling tests. See ip6gre_lib.sh for
+# more details.
+
+ALL_TESTS="
+	gre_flat
+	gre_mtu_change
+"
+
+NUM_NETIFS=6
+source lib.sh
+source ip6gre_lib.sh
+
+setup_prepare()
+{
+	h1=${NETIFS[p1]}
+	ol1=${NETIFS[p2]}
+
+	ul1=${NETIFS[p3]}
+	ul2=${NETIFS[p4]}
+
+	ol2=${NETIFS[p5]}
+	h2=${NETIFS[p6]}
+
+	forwarding_enable
+	vrf_prepare
+	h1_create
+	h2_create
+	sw1_flat_create $ol1 $ul1
+	sw2_flat_create $ol2 $ul2
+}
+
+gre_flat()
+{
+	test_traffic_ip4ip6 "GRE flat IPv4-in-IPv6"
+	test_traffic_ip6ip6 "GRE flat IPv6-in-IPv6"
+}
+
+gre_mtu_change()
+{
+	test_mtu_change
+}
+
+cleanup()
+{
+	pre_cleanup
+
+	sw2_flat_destroy $ol2 $ul2
+	sw1_flat_destroy $ol1 $ul1
+	h2_destroy
+	h1_destroy
+	vrf_cleanup
+	forwarding_restore
+}
+
+trap cleanup EXIT
+
+setup_prepare
+setup_wait
+tests_run
+
+exit $EXIT_STATUS
diff --git a/tools/testing/selftests/net/forwarding/ip6gre_flat_key.sh b/tools/testing/selftests/net/forwarding/ip6gre_flat_key.sh
new file mode 100755
index 000000000000..ff9fb0db9bd1
--- /dev/null
+++ b/tools/testing/selftests/net/forwarding/ip6gre_flat_key.sh
@@ -0,0 +1,65 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+# Test IP-in-IP GRE tunnel with key.
+# This test uses flat topology for IP tunneling tests. See ip6gre_lib.sh for
+# more details.
+
+ALL_TESTS="
+	gre_flat
+	gre_mtu_change
+"
+
+NUM_NETIFS=6
+source lib.sh
+source ip6gre_lib.sh
+
+setup_prepare()
+{
+	h1=${NETIFS[p1]}
+	ol1=${NETIFS[p2]}
+
+	ul1=${NETIFS[p3]}
+	ul2=${NETIFS[p4]}
+
+	ol2=${NETIFS[p5]}
+	h2=${NETIFS[p6]}
+
+	forwarding_enable
+	vrf_prepare
+	h1_create
+	h2_create
+	sw1_flat_create $ol1 $ul1 key 233
+	sw2_flat_create $ol2 $ul2 key 233
+}
+
+gre_flat()
+{
+	test_traffic_ip4ip6 "GRE flat IPv4-in-IPv6 with key"
+	test_traffic_ip6ip6 "GRE flat IPv6-in-IPv6 with key"
+}
+
+gre_mtu_change()
+{
+	test_mtu_change
+}
+
+cleanup()
+{
+	pre_cleanup
+
+	sw2_flat_destroy $ol2 $ul2
+	sw1_flat_destroy $ol1 $ul1
+	h2_destroy
+	h1_destroy
+	vrf_cleanup
+	forwarding_restore
+}
+
+trap cleanup EXIT
+
+setup_prepare
+setup_wait
+tests_run
+
+exit $EXIT_STATUS
diff --git a/tools/testing/selftests/net/forwarding/ip6gre_flat_keys.sh b/tools/testing/selftests/net/forwarding/ip6gre_flat_keys.sh
new file mode 100755
index 000000000000..12c138785242
--- /dev/null
+++ b/tools/testing/selftests/net/forwarding/ip6gre_flat_keys.sh
@@ -0,0 +1,65 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+# Test IP-in-IP GRE tunnel with keys.
+# This test uses flat topology for IP tunneling tests. See ip6gre_lib.sh for
+# more details.
+
+ALL_TESTS="
+	gre_flat
+	gre_mtu_change
+"
+
+NUM_NETIFS=6
+source lib.sh
+source ip6gre_lib.sh
+
+setup_prepare()
+{
+	h1=${NETIFS[p1]}
+	ol1=${NETIFS[p2]}
+
+	ul1=${NETIFS[p3]}
+	ul2=${NETIFS[p4]}
+
+	ol2=${NETIFS[p5]}
+	h2=${NETIFS[p6]}
+
+	forwarding_enable
+	vrf_prepare
+	h1_create
+	h2_create
+	sw1_flat_create $ol1 $ul1 ikey 111 okey 222
+	sw2_flat_create $ol2 $ul2 ikey 222 okey 111
+}
+
+gre_flat()
+{
+	test_traffic_ip4ip6 "GRE flat IPv4-in-IPv6 with ikey/okey"
+	test_traffic_ip6ip6 "GRE flat IPv6-in-IPv6 with ikey/okey"
+}
+
+gre_mtu_change()
+{
+	test_mtu_change	gre
+}
+
+cleanup()
+{
+	pre_cleanup
+
+	sw2_flat_destroy $ol2 $ul2
+	sw1_flat_destroy $ol1 $ul1
+	h2_destroy
+	h1_destroy
+	vrf_cleanup
+	forwarding_restore
+}
+
+trap cleanup EXIT
+
+setup_prepare
+setup_wait
+tests_run
+
+exit $EXIT_STATUS
diff --git a/tools/testing/selftests/net/forwarding/ip6gre_lib.sh b/tools/testing/selftests/net/forwarding/ip6gre_lib.sh
new file mode 100644
index 000000000000..2a5b2126b674
--- /dev/null
+++ b/tools/testing/selftests/net/forwarding/ip6gre_lib.sh
@@ -0,0 +1,270 @@
+# SPDX-License-Identifier: GPL-2.0
+#!/bin/bash
+
+# Handles creation and destruction of IP-in-IP or GRE tunnels over the given
+# topology.
+#
+# Flat Model:
+# Overlay and underlay share the same VRF.
+# SW1 uses default VRF so tunnel has no bound dev.
+# SW2 uses non-default VRF tunnel has a bound dev.
+# +--------------------------------+
+# | H1                             |
+# |                     $h1 +      |
+# |        198.51.100.1/24  |      |
+# |        2001:db8:1::1/64 |      |
+# +-------------------------|------+
+#                           |
+# +-------------------------|-------------------+
+# | SW1                     |                   |
+# |                    $ol1 +                   |
+# |        198.51.100.2/24                      |
+# |        2001:db8:1::2/64                     |
+# |                                             |
+# |      + g1a (ip6gre)                         |
+# |        loc=2001:db8:3::1                    |
+# |        rem=2001:db8:3::2 --.                |
+# |        tos=inherit         |                |
+# |                            .                |
+# |      .---------------------                 |
+# |      |                                      |
+# |      v                                      |
+# |      + $ul1.111 (vlan)                      |
+# |      | 2001:db8:10::1/64                    |
+# |       \                                     |
+# |        \____________                        |
+# |                     |                       |
+# | VRF default         + $ul1                  |
+# +---------------------|-----------------------+
+#                       |
+# +---------------------|-----------------------+
+# | SW2                 |                       |
+# |                $ul2 +                       |
+# |          ___________|                       |
+# |         /                                   |
+# |        /                                    |
+# |       + $ul2.111 (vlan)                     |
+# |       ^ 2001:db8:10::2/64                   |
+# |       |                                     |
+# |       |                                     |
+# |       '----------------------.              |
+# |       + g2a (ip6gre)         |              |
+# |         loc=2001:db8:3::2    |              |
+# |         rem=2001:db8:3::1  --'              |
+# |         tos=inherit                         |
+# |                                             |
+# |                     + $ol2                  |
+# |                     | 203.0.113.2/24        |
+# | VRF v$ol2           | 2001:db8:2::2/64      |
+# +---------------------|-----------------------+
+# +---------------------|----------+
+# | H2                  |          |
+# |                 $h2 +          |
+# |    203.0.113.1/24              |
+# |    2001:db8:2::1/64            |
+# +--------------------------------+
+
+source lib.sh
+source tc_common.sh
+
+h1_create()
+{
+	simple_if_init $h1 198.51.100.1/24 2001:db8:1::1/64
+	ip route add vrf v$h1 203.0.113.0/24 via 198.51.100.2
+	ip -6 route add vrf v$h1 2001:db8:2::/64 via 2001:db8:1::2
+}
+
+h1_destroy()
+{
+	ip -6 route del vrf v$h1 2001:db8:2::/64 via 2001:db8:1::2
+	ip route del vrf v$h1 203.0.113.0/24 via 198.51.100.2
+	simple_if_fini $h1 198.51.100.1/24 2001:db8:1::1/64
+}
+
+h2_create()
+{
+	simple_if_init $h2 203.0.113.1/24 2001:db8:2::1/64
+	ip route add vrf v$h2 198.51.100.0/24 via 203.0.113.2
+	ip -6 route add vrf v$h2 2001:db8:1::/64 via 2001:db8:2::2
+}
+
+h2_destroy()
+{
+	ip -6 route del vrf v$h2 2001:db8:1::/64 via 2001:db8:2::2
+	ip route del vrf v$h2 198.51.100.0/24 via 203.0.113.2
+	simple_if_fini $h2 203.0.113.1/24 2001:db8:2::1/64
+}
+
+sw1_flat_create()
+{
+	local ol1=$1; shift
+	local ul1=$1; shift
+
+	ip link set dev $ol1 up
+        __addr_add_del $ol1 add 198.51.100.2/24 2001:db8:1::2/64
+
+	ip link set dev $ul1 up
+	vlan_create $ul1 111 "" 2001:db8:10::1/64
+
+	tunnel_create g1a ip6gre 2001:db8:3::1 2001:db8:3::2 tos inherit \
+		ttl inherit "$@"
+	ip link set dev g1a up
+        __addr_add_del g1a add "2001:db8:3::1/128"
+
+	ip -6 route add 2001:db8:3::2/128 via 2001:db8:10::2
+	ip route add 203.0.113.0/24 dev g1a
+	ip -6 route add 2001:db8:2::/64 dev g1a
+}
+
+sw1_flat_destroy()
+{
+	local ol1=$1; shift
+	local ul1=$1; shift
+
+	ip -6 route del 2001:db8:2::/64
+	ip route del 203.0.113.0/24
+	ip -6 route del 2001:db8:3::2/128 via 2001:db8:10::2
+
+	__simple_if_fini g1a 2001:db8:3::1/128
+	tunnel_destroy g1a
+
+	vlan_destroy $ul1 111
+	__simple_if_fini $ul1
+	__simple_if_fini $ol1 198.51.100.2/24 2001:db8:1::2/64
+}
+
+sw2_flat_create()
+{
+	local ol2=$1; shift
+	local ul2=$1; shift
+
+	simple_if_init $ol2 203.0.113.2/24 2001:db8:2::2/64
+	__simple_if_init $ul2 v$ol2
+	vlan_create $ul2 111 v$ol2 2001:db8:10::2/64
+
+	tunnel_create g2a ip6gre 2001:db8:3::2 2001:db8:3::1 tos inherit \
+		ttl inherit dev v$ol2 "$@"
+	__simple_if_init g2a v$ol2 2001:db8:3::2/128
+
+	# Replace neighbor to avoid 1 dropped packet due to "unresolved neigh"
+	ip neigh replace dev $ol2 203.0.113.1 lladdr $(mac_get $h2)
+	ip -6 neigh replace dev $ol2 2001:db8:2::1 lladdr $(mac_get $h2)
+
+	ip -6 route add vrf v$ol2 2001:db8:3::1/128 via 2001:db8:10::1
+	ip route add vrf v$ol2 198.51.100.0/24 dev g2a
+	ip -6 route add vrf v$ol2 2001:db8:1::/64 dev g2a
+}
+
+sw2_flat_destroy()
+{
+	local ol2=$1; shift
+	local ul2=$1; shift
+
+	ip -6 route del vrf v$ol2 2001:db8:2::/64
+	ip route del vrf v$ol2 198.51.100.0/24
+	ip -6 route del vrf v$ol2 2001:db8:3::1/128 via 2001:db8:10::1
+
+	__simple_if_fini g2a 2001:db8:3::2/128
+	tunnel_destroy g2a
+
+	vlan_destroy $ul2 111
+	__simple_if_fini $ul2
+	simple_if_fini $ol2 203.0.113.2/24 2001:db8:2::2/64
+}
+
+test_traffic_ip4ip6()
+{
+	RET=0
+
+	h1mac=$(mac_get $h1)
+	ol1mac=$(mac_get $ol1)
+
+	tc qdisc add dev $ul1 clsact
+	tc filter add dev $ul1 egress proto all pref 1 handle 101 \
+		flower $TC_FLAG action pass
+
+	tc qdisc add dev $ol2 clsact
+	tc filter add dev $ol2 egress protocol ipv4 pref 1 handle 101 \
+		flower $TC_FLAG dst_ip 203.0.113.1 action pass
+
+	$MZ $h1 -c 1000 -p 64 -a $h1mac -b $ol1mac -A 198.51.100.1 \
+		-B 203.0.113.1 -t ip -q -d 1msec
+
+	# Check ports after encap and after decap.
+	tc_check_at_least_x_packets "dev $ul1 egress" 101 1000
+	check_err $? "Packets did not go through $ul1, tc_flag = $TC_FLAG"
+
+	tc_check_at_least_x_packets "dev $ol2 egress" 101 1000
+	check_err $? "Packets did not go through $ol2, tc_flag = $TC_FLAG"
+
+	log_test "$@"
+
+	tc filter del dev $ol2 egress protocol ipv4 pref 1 handle 101 flower
+	tc qdisc del dev $ol2 clsact
+	tc filter del dev $ul1 egress proto all pref 1 handle 101 flower
+	tc qdisc del dev $ul1 clsact
+}
+
+test_traffic_ip6ip6()
+{
+	RET=0
+
+	h1mac=$(mac_get $h1)
+	ol1mac=$(mac_get $ol1)
+
+	tc qdisc add dev $ul1 clsact
+	tc filter add dev $ul1 egress proto all pref 1 handle 101 \
+		flower $TC_FLAG action pass
+
+	tc qdisc add dev $ol2 clsact
+	tc filter add dev $ol2 egress protocol ipv6 pref 1 handle 101 \
+		flower $TC_FLAG dst_ip 2001:db8:2::1 action pass
+
+	$MZ -6 $h1 -c 1000 -p 64 -a $h1mac -b $ol1mac -A 2001:db8:1::1 \
+		-B 2001:db8:2::1 -t ip -q -d 1msec
+
+	# Check ports after encap and after decap.
+	tc_check_at_least_x_packets "dev $ul1 egress" 101 1000
+	check_err $? "Packets did not go through $ul1, tc_flag = $TC_FLAG"
+
+	tc_check_at_least_x_packets "dev $ol2 egress" 101 1000
+	check_err $? "Packets did not go through $ol2, tc_flag = $TC_FLAG"
+
+	log_test "$@"
+
+	tc filter del dev $ol2 egress protocol ipv6 pref 1 handle 101 flower
+	tc qdisc del dev $ol2 clsact
+	tc filter del dev $ul1 egress proto all pref 1 handle 101 flower
+	tc qdisc del dev $ul1 clsact
+}
+
+topo_mtu_change()
+{
+	local mtu=$1
+
+	ip link set mtu $mtu dev $h1
+	ip link set mtu $mtu dev $ol1
+	ip link set mtu $mtu dev g1a
+	ip link set mtu $mtu dev $ul1
+	ip link set mtu $mtu dev $ul1.111
+	ip link set mtu $mtu dev $h2
+	ip link set mtu $mtu dev $ol2
+	ip link set mtu $mtu dev g2a
+	ip link set mtu $mtu dev $ul2
+	ip link set mtu $mtu dev $ul2.111
+}
+
+test_mtu_change()
+{
+	RET=0
+
+	ping6_do $h1 2001:db8:2::1 "-s 1800 -w 3"
+	check_fail $? "ping GRE IPv6 should not pass with packet size 1800"
+
+	RET=0
+
+	topo_mtu_change	2000
+	ping6_do $h1 2001:db8:2::1 "-s 1800 -w 3"
+	check_err $?
+	log_test "ping GRE IPv6, packet size 1800 after MTU change"
+}
-- 
cgit v1.2.3


From 4b3d967b5cb99a445a2d55478035308f000cd568 Mon Sep 17 00:00:00 2001
From: Amit Cohen <amcohen@nvidia.com>
Date: Fri, 8 Oct 2021 16:12:37 +0300
Subject: selftests: forwarding: Add IPv6 GRE hierarchical tests

Add tests that check IPv6-in-IPv6, IPv4-in-IPv6 and MTU change of GRE
tunnel. The tests use hierarchical model - the tunnel is bound to a device
in a different VRF.

These tests can be run with TC_FLAG=skip_sw, so then they will verify
that packets go through hardware as part of enacp and decap phases.

Signed-off-by: Amit Cohen <amcohen@nvidia.com>
Reviewed-by: Petr Machata <petrm@nvidia.com>
Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../selftests/net/forwarding/ip6gre_hier.sh        |  65 ++++++++
 .../selftests/net/forwarding/ip6gre_hier_key.sh    |  65 ++++++++
 .../selftests/net/forwarding/ip6gre_hier_keys.sh   |  65 ++++++++
 .../testing/selftests/net/forwarding/ip6gre_lib.sh | 170 ++++++++++++++++++++-
 4 files changed, 364 insertions(+), 1 deletion(-)
 create mode 100755 tools/testing/selftests/net/forwarding/ip6gre_hier.sh
 create mode 100755 tools/testing/selftests/net/forwarding/ip6gre_hier_key.sh
 create mode 100755 tools/testing/selftests/net/forwarding/ip6gre_hier_keys.sh

(limited to 'tools')

diff --git a/tools/testing/selftests/net/forwarding/ip6gre_hier.sh b/tools/testing/selftests/net/forwarding/ip6gre_hier.sh
new file mode 100755
index 000000000000..83b55c30a5c3
--- /dev/null
+++ b/tools/testing/selftests/net/forwarding/ip6gre_hier.sh
@@ -0,0 +1,65 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+# Test IP-in-IP GRE tunnels without key.
+# This test uses hierarchical topology for IP tunneling tests. See
+# ip6gre_lib.sh for more details.
+
+ALL_TESTS="
+	gre_hier
+	gre_mtu_change
+"
+
+NUM_NETIFS=6
+source lib.sh
+source ip6gre_lib.sh
+
+setup_prepare()
+{
+	h1=${NETIFS[p1]}
+	ol1=${NETIFS[p2]}
+
+	ul1=${NETIFS[p3]}
+	ul2=${NETIFS[p4]}
+
+	ol2=${NETIFS[p5]}
+	h2=${NETIFS[p6]}
+
+	forwarding_enable
+	vrf_prepare
+	h1_create
+	h2_create
+	sw1_hierarchical_create $ol1 $ul1
+	sw2_hierarchical_create $ol2 $ul2
+}
+
+gre_hier()
+{
+	test_traffic_ip4ip6 "GRE hierarchical IPv4-in-IPv6"
+	test_traffic_ip6ip6 "GRE hierarchical IPv6-in-IPv6"
+}
+
+gre_mtu_change()
+{
+	test_mtu_change gre
+}
+
+cleanup()
+{
+	pre_cleanup
+
+	sw2_hierarchical_destroy $ol2 $ul2
+	sw1_hierarchical_destroy $ol1 $ul1
+	h2_destroy
+	h1_destroy
+	vrf_cleanup
+	forwarding_restore
+}
+
+trap cleanup EXIT
+
+setup_prepare
+setup_wait
+tests_run
+
+exit $EXIT_STATUS
diff --git a/tools/testing/selftests/net/forwarding/ip6gre_hier_key.sh b/tools/testing/selftests/net/forwarding/ip6gre_hier_key.sh
new file mode 100755
index 000000000000..256607916d92
--- /dev/null
+++ b/tools/testing/selftests/net/forwarding/ip6gre_hier_key.sh
@@ -0,0 +1,65 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+# Test IP-in-IP GRE tunnels without key.
+# This test uses hierarchical topology for IP tunneling tests. See
+# ip6gre_lib.sh for more details.
+
+ALL_TESTS="
+	gre_hier
+	gre_mtu_change
+"
+
+NUM_NETIFS=6
+source lib.sh
+source ip6gre_lib.sh
+
+setup_prepare()
+{
+	h1=${NETIFS[p1]}
+	ol1=${NETIFS[p2]}
+
+	ul1=${NETIFS[p3]}
+	ul2=${NETIFS[p4]}
+
+	ol2=${NETIFS[p5]}
+	h2=${NETIFS[p6]}
+
+	forwarding_enable
+	vrf_prepare
+	h1_create
+	h2_create
+	sw1_hierarchical_create $ol1 $ul1 key 22
+	sw2_hierarchical_create $ol2 $ul2 key 22
+}
+
+gre_hier()
+{
+	test_traffic_ip4ip6 "GRE hierarchical IPv4-in-IPv6 with key"
+	test_traffic_ip6ip6 "GRE hierarchical IPv6-in-IPv6 with key"
+}
+
+gre_mtu_change()
+{
+	test_mtu_change gre
+}
+
+cleanup()
+{
+	pre_cleanup
+
+	sw2_hierarchical_destroy $ol2 $ul2
+	sw1_hierarchical_destroy $ol1 $ul1
+	h2_destroy
+	h1_destroy
+	vrf_cleanup
+	forwarding_restore
+}
+
+trap cleanup EXIT
+
+setup_prepare
+setup_wait
+tests_run
+
+exit $EXIT_STATUS
diff --git a/tools/testing/selftests/net/forwarding/ip6gre_hier_keys.sh b/tools/testing/selftests/net/forwarding/ip6gre_hier_keys.sh
new file mode 100755
index 000000000000..ad1bcd6334a8
--- /dev/null
+++ b/tools/testing/selftests/net/forwarding/ip6gre_hier_keys.sh
@@ -0,0 +1,65 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+# Test IP-in-IP GRE tunnels without key.
+# This test uses hierarchical topology for IP tunneling tests. See
+# ip6gre_lib.sh for more details.
+
+ALL_TESTS="
+	gre_hier
+	gre_mtu_change
+"
+
+NUM_NETIFS=6
+source lib.sh
+source ip6gre_lib.sh
+
+setup_prepare()
+{
+	h1=${NETIFS[p1]}
+	ol1=${NETIFS[p2]}
+
+	ul1=${NETIFS[p3]}
+	ul2=${NETIFS[p4]}
+
+	ol2=${NETIFS[p5]}
+	h2=${NETIFS[p6]}
+
+	forwarding_enable
+	vrf_prepare
+	h1_create
+	h2_create
+	sw1_hierarchical_create $ol1 $ul1 ikey 111 okey 222
+	sw2_hierarchical_create $ol2 $ul2 ikey 222 okey 111
+}
+
+gre_hier()
+{
+	test_traffic_ip4ip6 "GRE hierarchical IPv4-in-IPv6 with ikey/okey"
+	test_traffic_ip6ip6 "GRE hierarchical IPv6-in-IPv6 with ikey/okey"
+}
+
+gre_mtu_change()
+{
+	test_mtu_change gre
+}
+
+cleanup()
+{
+	pre_cleanup
+
+	sw2_hierarchical_destroy $ol2 $ul2
+	sw1_hierarchical_destroy $ol1 $ul1
+	h2_destroy
+	h1_destroy
+	vrf_cleanup
+	forwarding_restore
+}
+
+trap cleanup EXIT
+
+setup_prepare
+setup_wait
+tests_run
+
+exit $EXIT_STATUS
diff --git a/tools/testing/selftests/net/forwarding/ip6gre_lib.sh b/tools/testing/selftests/net/forwarding/ip6gre_lib.sh
index 2a5b2126b674..58a3597037b1 100644
--- a/tools/testing/selftests/net/forwarding/ip6gre_lib.sh
+++ b/tools/testing/selftests/net/forwarding/ip6gre_lib.sh
@@ -2,7 +2,7 @@
 #!/bin/bash
 
 # Handles creation and destruction of IP-in-IP or GRE tunnels over the given
-# topology.
+# topology. Supports both flat and hierarchical models.
 #
 # Flat Model:
 # Overlay and underlay share the same VRF.
@@ -63,6 +63,91 @@
 # |    203.0.113.1/24              |
 # |    2001:db8:2::1/64            |
 # +--------------------------------+
+#
+# Hierarchical model:
+# The tunnel is bound to a device in a different VRF
+#
+# +--------------------------------+
+# | H1                             |
+# |                     $h1 +      |
+# |        198.51.100.1/24  |      |
+# |        2001:db8:1::1/64 |      |
+# +-------------------------|------+
+#                           |
+# +-------------------------|-------------------+
+# | SW1                     |                   |
+# | +-----------------------|-----------------+ |
+# | |                  $ol1 +                 | |
+# | |      198.51.100.2/24                    | |
+# | |      2001:db8:1::2/64                   | |
+# | |                                         | |
+# | |              + g1a (ip6gre)             | |
+# | |                loc=2001:db8:3::1        | |
+# | |                rem=2001:db8:3::2        | |
+# | |                tos=inherit              | |
+# | |                    ^                    | |
+# | |   VRF v$ol1        |                    | |
+# | +--------------------|--------------------+ |
+# |                      |                      |
+# | +--------------------|--------------------+ |
+# | |   VRF v$ul1        |                    | |
+# | |                    |                    | |
+# | |                    v                    | |
+# | |             dummy1 +                    | |
+# | |       2001:db8:3::1/64                  | |
+# | |         .-----------'                   | |
+# | |         |                               | |
+# | |         v                               | |
+# | |         + $ul1.111 (vlan)               | |
+# | |         | 2001:db8:10::1/64             | |
+# | |         \                               | |
+# | |          \__________                    | |
+# | |                     |                   | |
+# | |                     + $ul1              | |
+# | +---------------------|-------------------+ |
+# +-----------------------|---------------------+
+#                         |
+# +-----------------------|---------------------+
+# | SW2                   |                     |
+# | +---------------------|-------------------+ |
+# | |                     + $ul2              | |
+# | |                _____|                   | |
+# | |               /                         | |
+# | |              /                          | |
+# | |              | $ul2.111 (vlan)          | |
+# | |              + 2001:db8:10::2/64        | |
+# | |              ^                          | |
+# | |              |                          | |
+# | |              '------.                   | |
+# | |              dummy2 +                   | |
+# | |              2001:db8:3::2/64           | |
+# | |                     ^                   | |
+# | |                     |                   | |
+# | |                     |                   | |
+# | | VRF v$ul2           |                   | |
+# | +---------------------|-------------------+ |
+# |                       |                     |
+# | +---------------------|-------------------+ |
+# | | VRF v$ol2           |                   | |
+# | |                     |                   | |
+# | |                     v                   | |
+# | |        g2a (ip6gre) +                   | |
+# | |        loc=2001:db8:3::2                | |
+# | |        rem=2001:db8:3::1                | |
+# | |        tos=inherit                      | |
+# | |                                         | |
+# | |                $ol2 +                   | |
+# | |    203.0.113.2/24   |                   | |
+# | |    2001:db8:2::2/64 |                   | |
+# | +---------------------|-------------------+ |
+# +-----------------------|---------------------+
+#                         |
+# +-----------------------|--------+
+# | H2                    |        |
+# |                   $h2 +        |
+# |      203.0.113.1/24            |
+# |      2001:db8:2::1/64          |
+# +--------------------------------+
 
 source lib.sh
 source tc_common.sh
@@ -172,6 +257,89 @@ sw2_flat_destroy()
 	simple_if_fini $ol2 203.0.113.2/24 2001:db8:2::2/64
 }
 
+sw1_hierarchical_create()
+{
+	local ol1=$1; shift
+	local ul1=$1; shift
+
+	simple_if_init $ol1 198.51.100.2/24 2001:db8:1::2/64
+	simple_if_init $ul1
+	ip link add name dummy1 type dummy
+	__simple_if_init dummy1 v$ul1 2001:db8:3::1/64
+
+	vlan_create $ul1 111 v$ul1 2001:db8:10::1/64
+	tunnel_create g1a ip6gre 2001:db8:3::1 2001:db8:3::2 tos inherit \
+		ttl inherit dev dummy1 "$@"
+	ip link set dev g1a master v$ol1
+
+	ip -6 route add vrf v$ul1 2001:db8:3::2/128 via 2001:db8:10::2
+	ip route add vrf v$ol1 203.0.113.0/24 dev g1a
+	ip -6 route add vrf v$ol1 2001:db8:2::/64 dev g1a
+}
+
+sw1_hierarchical_destroy()
+{
+	local ol1=$1; shift
+	local ul1=$1; shift
+
+	ip -6 route del vrf v$ol1 2001:db8:2::/64
+	ip route del vrf v$ol1 203.0.113.0/24
+	ip -6 route del vrf v$ul1 2001:db8:3::2/128
+
+	tunnel_destroy g1a
+	vlan_destroy $ul1 111
+
+	__simple_if_fini dummy1 2001:db8:3::1/64
+	ip link del dev dummy1
+
+	simple_if_fini $ul1
+	simple_if_fini $ol1 198.51.100.2/24 2001:db8:1::2/64
+}
+
+sw2_hierarchical_create()
+{
+	local ol2=$1; shift
+	local ul2=$1; shift
+
+	simple_if_init $ol2 203.0.113.2/24 2001:db8:2::2/64
+	simple_if_init $ul2
+
+	ip link add name dummy2 type dummy
+	__simple_if_init dummy2 v$ul2 2001:db8:3::2/64
+
+	vlan_create $ul2 111 v$ul2 2001:db8:10::2/64
+	tunnel_create g2a ip6gre 2001:db8:3::2 2001:db8:3::1 tos inherit \
+		ttl inherit dev dummy2 "$@"
+	ip link set dev g2a master v$ol2
+
+	# Replace neighbor to avoid 1 dropped packet due to "unresolved neigh"
+	ip neigh replace dev $ol2 203.0.113.1 lladdr $(mac_get $h2)
+	ip -6 neigh replace dev $ol2 2001:db8:2::1 lladdr $(mac_get $h2)
+
+	ip -6 route add vrf v$ul2 2001:db8:3::1/128 via 2001:db8:10::1
+	ip route add vrf v$ol2 198.51.100.0/24 dev g2a
+	ip -6 route add vrf v$ol2 2001:db8:1::/64 dev g2a
+}
+
+sw2_hierarchical_destroy()
+{
+	local ol2=$1; shift
+	local ul2=$1; shift
+
+	ip -6 route del vrf v$ol2 2001:db8:2::/64
+	ip route del vrf v$ol2 198.51.100.0/24
+	ip -6 route del vrf v$ul2 2001:db8:3::1/128
+
+	tunnel_destroy g2a
+	vlan_destroy $ul2 111
+
+	__simple_if_fini dummy2 2001:db8:3::2/64
+	ip link del dev dummy2
+
+	simple_if_fini $ul2
+	simple_if_fini $ol2 203.0.113.2/24 2001:db8:2::2/64
+}
+
 test_traffic_ip4ip6()
 {
 	RET=0
-- 
cgit v1.2.3


From 4bb6cce00a2bef813a2457cd998f90ec9c30b6d0 Mon Sep 17 00:00:00 2001
From: Amit Cohen <amcohen@nvidia.com>
Date: Fri, 8 Oct 2021 16:12:38 +0300
Subject: selftests: mlxsw: devlink_trap_tunnel_ipip6: Add test case for IPv6
 decap_error

IPv6 underlay support was added, add test to check that "decap_error" trap
is triggered under the right conditions and that devlink counters increase.

Signed-off-by: Amit Cohen <amcohen@nvidia.com>
Reviewed-by: Petr Machata <petrm@nvidia.com>
Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../mlxsw/spectrum-2/devlink_trap_tunnel_ipip6.sh  | 250 +++++++++++++++++++++
 1 file changed, 250 insertions(+)
 create mode 100755 tools/testing/selftests/drivers/net/mlxsw/spectrum-2/devlink_trap_tunnel_ipip6.sh

(limited to 'tools')

diff --git a/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/devlink_trap_tunnel_ipip6.sh b/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/devlink_trap_tunnel_ipip6.sh
new file mode 100755
index 000000000000..f62ce479c266
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/devlink_trap_tunnel_ipip6.sh
@@ -0,0 +1,250 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+#
+# Test devlink-trap tunnel exceptions functionality over mlxsw.
+# Check all exception traps to make sure they are triggered under the right
+# conditions.
+
+# +-------------------------+
+# | H1                      |
+# |               $h1 +     |
+# |  2001:db8:1::1/64 |     |
+# +-------------------|-----+
+#                     |
+# +-------------------|-----+
+# | SW1               |     |
+# |             $swp1 +     |
+# |  2001:db8:1::2/64       |
+# |                         |
+# |  + g1 (ip6gre)          |
+# |    loc=2001:db8:3::1    |
+# |    rem=2001:db8:3::2    |
+# |    tos=inherit          |
+# |                         |
+# |  + $rp1                 |
+# |  | 2001:db8:10::1/64    |
+# +--|----------------------+
+#    |
+# +--|----------------------+
+# |  |                 VRF2 |
+# |  + $rp2                 |
+# |    2001:db8:10::2/64    |
+# +-------------------------+
+
+lib_dir=$(dirname $0)/../../../../net/forwarding
+
+ALL_TESTS="
+	decap_error_test
+"
+
+NUM_NETIFS=4
+source $lib_dir/lib.sh
+source $lib_dir/tc_common.sh
+source $lib_dir/devlink_lib.sh
+
+h1_create()
+{
+	simple_if_init $h1 2001:db8:1::1/64
+}
+
+h1_destroy()
+{
+	simple_if_fini $h1 2001:db8:1::1/64
+}
+
+vrf2_create()
+{
+	simple_if_init $rp2 2001:db8:10::2/64
+}
+
+vrf2_destroy()
+{
+	simple_if_fini $rp2 2001:db8:10::2/64
+}
+
+switch_create()
+{
+	ip link set dev $swp1 up
+	__addr_add_del $swp1 add 2001:db8:1::2/64
+	tc qdisc add dev $swp1 clsact
+
+	tunnel_create g1 ip6gre 2001:db8:3::1 2001:db8:3::2 tos inherit \
+		ttl inherit
+	ip link set dev g1 up
+	__addr_add_del g1 add 2001:db8:3::1/128
+
+	ip link set dev $rp1 up
+	__addr_add_del $rp1 add 2001:db8:10::1/64
+}
+
+switch_destroy()
+{
+	__addr_add_del $rp1 del 2001:db8:10::1/64
+	ip link set dev $rp1 down
+
+	__addr_add_del g1 del 2001:db8:3::1/128
+	ip link set dev g1 down
+	tunnel_destroy g1
+
+	tc qdisc del dev $swp1 clsact
+	__addr_add_del $swp1 del 2001:db8:1::2/64
+	ip link set dev $swp1 down
+}
+
+setup_prepare()
+{
+	h1=${NETIFS[p1]}
+	swp1=${NETIFS[p2]}
+
+	rp1=${NETIFS[p3]}
+	rp2=${NETIFS[p4]}
+
+	forwarding_enable
+	vrf_prepare
+	h1_create
+	switch_create
+	vrf2_create
+}
+
+cleanup()
+{
+	pre_cleanup
+
+	vrf2_destroy
+	switch_destroy
+	h1_destroy
+	vrf_cleanup
+	forwarding_restore
+}
+
+ipip_payload_get()
+{
+	local saddr="20:01:0d:b8:00:02:00:00:00:00:00:00:00:00:00:01"
+	local daddr="20:01:0d:b8:00:01:00:00:00:00:00:00:00:00:00:01"
+	local flags=$1; shift
+	local key=$1; shift
+
+	p=$(:
+		)"$flags"$(		      : GRE flags
+	        )"0:00:"$(                    : Reserved + version
+		)"86:dd:"$(		      : ETH protocol type
+		)"$key"$( 		      : Key
+		)"6"$(	                      : IP version
+		)"0:0"$(		      : Traffic class
+		)"0:00:00:"$(		      : Flow label
+		)"00:00:"$(                   : Payload length
+		)"3a:"$(                      : Next header
+		)"04:"$(                      : Hop limit
+		)"$saddr:"$(                  : IP saddr
+		)"$daddr:"$(                  : IP daddr
+		)
+	echo $p
+}
+
+ecn_payload_get()
+{
+	echo $(ipip_payload_get "0")
+}
+
+ecn_decap_test()
+{
+	local trap_name="decap_error"
+	local desc=$1; shift
+	local ecn_desc=$1; shift
+	local outer_tos=$1; shift
+	local mz_pid
+
+	RET=0
+
+	tc filter add dev $swp1 egress protocol ipv6 pref 1 handle 101 \
+		flower src_ip 2001:db8:2::1 dst_ip 2001:db8:1::1 skip_sw \
+		action pass
+
+	rp1_mac=$(mac_get $rp1)
+	rp2_mac=$(mac_get $rp2)
+	payload=$(ecn_payload_get)
+
+	ip vrf exec v$rp2 $MZ -6 $rp2 -c 0 -d 1msec -a $rp2_mac -b $rp1_mac \
+		-A 2001:db8:3::2 -B 2001:db8:3::1 -t ip \
+			tos=$outer_tos,next=47,p=$payload -q &
+	mz_pid=$!
+
+	devlink_trap_exception_test $trap_name
+
+	tc_check_packets "dev $swp1 egress" 101 0
+	check_err $? "Packets were not dropped"
+
+	log_test "$desc: Inner ECN is not ECT and outer is $ecn_desc"
+
+	kill $mz_pid && wait $mz_pid &> /dev/null
+	tc filter del dev $swp1 egress protocol ipv6 pref 1 handle 101 flower
+}
+
+no_matching_tunnel_test()
+{
+	local trap_name="decap_error"
+	local desc=$1; shift
+	local sip=$1; shift
+	local mz_pid
+
+	RET=0
+
+	tc filter add dev $swp1 egress protocol ipv6 pref 1 handle 101 \
+		flower src_ip 2001:db8:2::1 dst_ip 2001:db8:1::1 action pass
+
+	rp1_mac=$(mac_get $rp1)
+	rp2_mac=$(mac_get $rp2)
+	payload=$(ipip_payload_get "$@")
+
+	ip vrf exec v$rp2 $MZ -6 $rp2 -c 0 -d 1msec -a $rp2_mac -b $rp1_mac \
+		-A $sip -B 2001:db8:3::1 -t ip next=47,p=$payload -q &
+	mz_pid=$!
+
+	devlink_trap_exception_test $trap_name
+
+	tc_check_packets "dev $swp1 egress" 101 0
+	check_err $? "Packets were not dropped"
+
+	log_test "$desc"
+
+	kill $mz_pid && wait $mz_pid &> /dev/null
+	tc filter del dev $swp1 egress protocol ipv6 pref 1 handle 101 flower
+}
+
+decap_error_test()
+{
+	# Correct source IP - the remote address
+	local sip=2001:db8:3::2
+
+	ecn_decap_test "Decap error" "ECT(1)" 01
+	ecn_decap_test "Decap error" "ECT(0)" 02
+	ecn_decap_test "Decap error" "CE" 03
+
+	no_matching_tunnel_test "Decap error: Source IP check failed" \
+		2001:db8:4::2 "0"
+	no_matching_tunnel_test \
+		"Decap error: Key exists but was not expected" $sip "2" \
+		"00:00:00:E9:"
+
+	# Destroy the tunnel and create new one with key
+	__addr_add_del g1 del 2001:db8:3::1/128
+	tunnel_destroy g1
+
+	tunnel_create g1 ip6gre 2001:db8:3::1 2001:db8:3::2 tos inherit \
+		ttl inherit key 233
+	__addr_add_del g1 add 2001:db8:3::1/128
+
+	no_matching_tunnel_test \
+		"Decap error: Key does not exist but was expected" $sip "0"
+	no_matching_tunnel_test \
+		"Decap error: Packet has a wrong key field" $sip "2" \
+		"00:00:00:E8:"
+}
+
+trap cleanup EXIT
+
+setup_prepare
+setup_wait
+tests_run
+
+exit $EXIT_STATUS
-- 
cgit v1.2.3


From c473f723f97a0b3a2d0b3ae75bfcf090882afa85 Mon Sep 17 00:00:00 2001
From: Amit Cohen <amcohen@nvidia.com>
Date: Fri, 8 Oct 2021 16:12:39 +0300
Subject: selftests: mlxsw: devlink_trap_tunnel_ipip: Align topology drawing
 correctly

As part of adding same test for GRE tunnel with IPv6 underlay, wrong
alignments were found, fix them.

Signed-off-by: Amit Cohen <amcohen@nvidia.com>
Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../testing/selftests/drivers/net/mlxsw/devlink_trap_tunnel_ipip.sh | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_tunnel_ipip.sh b/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_tunnel_ipip.sh
index 8817851da7a9..e2ab26b790a0 100755
--- a/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_tunnel_ipip.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_tunnel_ipip.sh
@@ -13,7 +13,7 @@
 #                     |
 # +-------------------|-----+
 # | SW1               |     |
-# |              $swp1 +    |
+# |             $swp1 +     |
 # |      192.0.2.2/28       |
 # |                         |
 # |  + g1a (gre)            |
@@ -27,8 +27,8 @@
 #    |
 # +--|----------------------+
 # |  |                 VRF2 |
-# | + $rp2                  |
-# |   198.51.100.2/28       |
+# |  + $rp2                 |
+# |    198.51.100.2/28      |
 # +-------------------------+
 
 lib_dir=$(dirname $0)/../../../net/forwarding
-- 
cgit v1.2.3


From 8bb0ebd52238972fd4c60280669103560838ab0d Mon Sep 17 00:00:00 2001
From: Amit Cohen <amcohen@nvidia.com>
Date: Fri, 8 Oct 2021 16:12:40 +0300
Subject: selftests: mlxsw: devlink_trap_tunnel_ipip: Remove code duplication

As part of adding same test for GRE tunnel with IPv6 underlay, an
optional improvement was found - call ipip_payload_get from
ecn_payload_get, so do not duplicate the code which creates the payload.

Signed-off-by: Amit Cohen <amcohen@nvidia.com>
Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../drivers/net/mlxsw/devlink_trap_tunnel_ipip.sh  | 38 +++++++---------------
 1 file changed, 11 insertions(+), 27 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_tunnel_ipip.sh b/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_tunnel_ipip.sh
index e2ab26b790a0..c072c1633f1d 100755
--- a/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_tunnel_ipip.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_tunnel_ipip.sh
@@ -116,12 +116,16 @@ cleanup()
 	forwarding_restore
 }
 
-ecn_payload_get()
+ipip_payload_get()
 {
+	local flags=$1; shift
+	local key=$1; shift
+
 	p=$(:
-		)"0"$(		              : GRE flags
+		)"$flags"$(		      : GRE flags
 	        )"0:00:"$(                    : Reserved + version
 		)"08:00:"$(		      : ETH protocol type
+		)"$key"$( 		      : Key
 		)"4"$(	                      : IP version
 		)"5:"$(                       : IHL
 		)"00:"$(                      : IP TOS
@@ -137,6 +141,11 @@ ecn_payload_get()
 	echo $p
 }
 
+ecn_payload_get()
+{
+	echo $(ipip_payload_get "0")
+}
+
 ecn_decap_test()
 {
 	local trap_name="decap_error"
@@ -171,31 +180,6 @@ ecn_decap_test()
 	tc filter del dev $swp1 egress protocol ip pref 1 handle 101 flower
 }
 
-ipip_payload_get()
-{
-	local flags=$1; shift
-	local key=$1; shift
-
-	p=$(:
-		)"$flags"$(		      : GRE flags
-	        )"0:00:"$(                    : Reserved + version
-		)"08:00:"$(		      : ETH protocol type
-		)"$key"$( 		      : Key
-		)"4"$(	                      : IP version
-		)"5:"$(                       : IHL
-		)"00:"$(                      : IP TOS
-		)"00:14:"$(                   : IP total length
-		)"00:00:"$(                   : IP identification
-		)"20:00:"$(                   : IP flags + frag off
-		)"30:"$(                      : IP TTL
-		)"01:"$(                      : IP proto
-		)"E7:E6:"$(    	              : IP header csum
-		)"C0:00:01:01:"$(             : IP saddr : 192.0.1.1
-		)"C0:00:02:01:"$(             : IP daddr : 192.0.2.1
-		)
-	echo $p
-}
-
 no_matching_tunnel_test()
 {
 	local trap_name="decap_error"
-- 
cgit v1.2.3


From 7f63cdde50302bcdf48c35afbb057a8d3d3e0d85 Mon Sep 17 00:00:00 2001
From: Amit Cohen <amcohen@nvidia.com>
Date: Fri, 8 Oct 2021 16:12:41 +0300
Subject: selftests: mlxsw: devlink_trap_tunnel_ipip: Send a full-length key

As part of adding same test for GRE tunnel with IPv6 underlay, missing
bytes for key were found.

mausezahn does not fill zeros between two colons, so send them
explicitly. For example, use "00:00:00:E9:" instead of ":E9:"

Signed-off-by: Amit Cohen <amcohen@nvidia.com>
Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../testing/selftests/drivers/net/mlxsw/devlink_trap_tunnel_ipip.sh | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_tunnel_ipip.sh b/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_tunnel_ipip.sh
index c072c1633f1d..e9a82cae8c9a 100755
--- a/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_tunnel_ipip.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_tunnel_ipip.sh
@@ -223,7 +223,8 @@ decap_error_test()
 	no_matching_tunnel_test "Decap error: Source IP check failed" \
 		192.0.2.68 "0"
 	no_matching_tunnel_test \
-		"Decap error: Key exists but was not expected" $sip "2" ":E9:"
+		"Decap error: Key exists but was not expected" $sip "2" \
+		"00:00:00:E9:"
 
 	# Destroy the tunnel and create new one with key
 	__addr_add_del g1 del 192.0.2.65/32
@@ -235,7 +236,8 @@ decap_error_test()
 	no_matching_tunnel_test \
 		"Decap error: Key does not exist but was expected" $sip "0"
 	no_matching_tunnel_test \
-		"Decap error: Packet has a wrong key field" $sip "2" "E8:"
+		"Decap error: Packet has a wrong key field" $sip "2" \
+		"00:00:00:E8:"
 }
 
 trap cleanup EXIT
-- 
cgit v1.2.3


From 7e3cbd3405cb7b6c036b8984baa694bc55c08e46 Mon Sep 17 00:00:00 2001
From: Yucong Sun <sunyucong@gmail.com>
Date: Fri, 8 Oct 2021 10:31:39 -0700
Subject: selftests/bpf: Fix btf_dump test under new clang

New clang version changed ([0]) type name in dwarf from "long int" to "long",
this is causing btf_dump tests to fail.

  [0] https://github.com/llvm/llvm-project/commit/f6a561c4d6754b13165a49990e8365d819f64c86

Signed-off-by: Yucong Sun <sunyucong@gmail.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20211008173139.1457407-1-fallentree@fb.com
---
 .../testing/selftests/bpf/progs/btf_dump_test_case_bitfields.c | 10 +++++-----
 tools/testing/selftests/bpf/progs/btf_dump_test_case_packing.c |  4 ++--
 tools/testing/selftests/bpf/progs/btf_dump_test_case_padding.c |  2 +-
 tools/testing/selftests/bpf/progs/btf_dump_test_case_syntax.c  |  2 +-
 4 files changed, 9 insertions(+), 9 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/progs/btf_dump_test_case_bitfields.c b/tools/testing/selftests/bpf/progs/btf_dump_test_case_bitfields.c
index 8f44767a75fa..e5560a656030 100644
--- a/tools/testing/selftests/bpf/progs/btf_dump_test_case_bitfields.c
+++ b/tools/testing/selftests/bpf/progs/btf_dump_test_case_bitfields.c
@@ -11,7 +11,7 @@
 /*
  *struct bitfields_only_mixed_types {
  *	int a: 3;
- *	long int b: 2;
+ *	long b: 2;
  *	_Bool c: 1;
  *	enum {
  *		A = 0,
@@ -27,7 +27,7 @@
 
 struct bitfields_only_mixed_types {
 	int a: 3;
-	long int b: 2;
+	long b: 2;
 	bool c: 1; /* it's really a _Bool type */
 	enum {
 		A, /* A = 0, dumper is very explicit */
@@ -44,8 +44,8 @@ struct bitfields_only_mixed_types {
  *	char: 4;
  *	int a: 4;
  *	short b;
- *	long int c;
- *	long int d: 8;
+ *	long c;
+ *	long d: 8;
  *	int e;
  *	int f;
  *};
@@ -71,7 +71,7 @@ struct bitfield_mixed_with_others {
  *struct bitfield_flushed {
  *	int a: 4;
  *	long: 60;
- *	long int b: 16;
+ *	long b: 16;
  *};
  *
  */
diff --git a/tools/testing/selftests/bpf/progs/btf_dump_test_case_packing.c b/tools/testing/selftests/bpf/progs/btf_dump_test_case_packing.c
index 1cef3bec1dc7..e304b6204bd9 100644
--- a/tools/testing/selftests/bpf/progs/btf_dump_test_case_packing.c
+++ b/tools/testing/selftests/bpf/progs/btf_dump_test_case_packing.c
@@ -29,7 +29,7 @@ struct non_packed_fields {
 struct nested_packed {
 	char: 4;
 	int a: 4;
-	long int b;
+	long b;
 	struct {
 		char c;
 		int d;
@@ -44,7 +44,7 @@ union union_is_never_packed {
 
 union union_does_not_need_packing {
 	struct {
-		long int a;
+		long a;
 		int b;
 	} __attribute__((packed));
 	int c;
diff --git a/tools/testing/selftests/bpf/progs/btf_dump_test_case_padding.c b/tools/testing/selftests/bpf/progs/btf_dump_test_case_padding.c
index 35c512818a56..f2661c8d2d90 100644
--- a/tools/testing/selftests/bpf/progs/btf_dump_test_case_padding.c
+++ b/tools/testing/selftests/bpf/progs/btf_dump_test_case_padding.c
@@ -9,7 +9,7 @@
 /* ----- START-EXPECTED-OUTPUT ----- */
 struct padded_implicitly {
 	int a;
-	long int b;
+	long b;
 	char c;
 };
 
diff --git a/tools/testing/selftests/bpf/progs/btf_dump_test_case_syntax.c b/tools/testing/selftests/bpf/progs/btf_dump_test_case_syntax.c
index 8aaa24a00322..1c7105fcae3c 100644
--- a/tools/testing/selftests/bpf/progs/btf_dump_test_case_syntax.c
+++ b/tools/testing/selftests/bpf/progs/btf_dump_test_case_syntax.c
@@ -189,7 +189,7 @@ struct struct_with_embedded_stuff {
 			const char *d;
 		} e;
 		union {
-			volatile long int f;
+			volatile long f;
 			void * restrict g;
 		};
 	};
-- 
cgit v1.2.3


From b79c2ce3baa99beea7f8410ce3154cc23e26dbd8 Mon Sep 17 00:00:00 2001
From: Quentin Monnet <quentin@isovalent.com>
Date: Thu, 7 Oct 2021 20:44:27 +0100
Subject: libbpf: Skip re-installing headers file if source is older than
 target

The "install_headers" target in libbpf's Makefile would unconditionally
export all API headers to the target directory. When those headers are
installed to compile another application, this means that make always
finds newer dependencies for the source files relying on those headers,
and deduces that the targets should be rebuilt.

Avoid that by making "install_headers" depend on the source header
files, and (re-)install them only when necessary.

Signed-off-by: Quentin Monnet <quentin@isovalent.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20211007194438.34443-2-quentin@isovalent.com
---
 tools/lib/bpf/Makefile | 27 ++++++++++++++++++---------
 1 file changed, 18 insertions(+), 9 deletions(-)

(limited to 'tools')

diff --git a/tools/lib/bpf/Makefile b/tools/lib/bpf/Makefile
index 41e4f78dbad5..9c6804ca5b45 100644
--- a/tools/lib/bpf/Makefile
+++ b/tools/lib/bpf/Makefile
@@ -241,15 +241,24 @@ install_lib: all_cmd
 		$(call do_install_mkdir,$(libdir_SQ)); \
 		cp -fpR $(LIB_FILE) $(DESTDIR)$(libdir_SQ)
 
-INSTALL_HEADERS = bpf.h libbpf.h btf.h libbpf_common.h libbpf_legacy.h xsk.h \
-		  bpf_helpers.h $(BPF_GENERATED) bpf_tracing.h		     \
-		  bpf_endian.h bpf_core_read.h skel_internal.h		     \
-		  libbpf_version.h
-
-install_headers: $(BPF_GENERATED)
-	$(call QUIET_INSTALL, headers)					     \
-		$(foreach hdr,$(INSTALL_HEADERS),			     \
-			$(call do_install,$(hdr),$(prefix)/include/bpf,644);)
+SRC_HDRS := bpf.h libbpf.h btf.h libbpf_common.h libbpf_legacy.h xsk.h	     \
+	    bpf_helpers.h bpf_tracing.h bpf_endian.h bpf_core_read.h	     \
+	    skel_internal.h libbpf_version.h
+GEN_HDRS := $(BPF_GENERATED)
+
+INSTALL_PFX := $(DESTDIR)$(prefix)/include/bpf
+INSTALL_SRC_HDRS := $(addprefix $(INSTALL_PFX)/, $(SRC_HDRS))
+INSTALL_GEN_HDRS := $(addprefix $(INSTALL_PFX)/, $(notdir $(GEN_HDRS)))
+
+$(INSTALL_SRC_HDRS): $(INSTALL_PFX)/%.h: %.h
+	$(call QUIET_INSTALL, $@) \
+		$(call do_install,$<,$(prefix)/include/bpf,644)
+
+$(INSTALL_GEN_HDRS): $(INSTALL_PFX)/%.h: $(OUTPUT)%.h
+	$(call QUIET_INSTALL, $@) \
+		$(call do_install,$<,$(prefix)/include/bpf,644)
+
+install_headers: $(BPF_GENERATED) $(INSTALL_SRC_HDRS) $(INSTALL_GEN_HDRS)
 
 install_pkgconfig: $(PC_FILE)
 	$(call QUIET_INSTALL, $(PC_FILE)) \
-- 
cgit v1.2.3


From c66a248f1950d41502fb67624147281d9de0e868 Mon Sep 17 00:00:00 2001
From: Quentin Monnet <quentin@isovalent.com>
Date: Thu, 7 Oct 2021 20:44:28 +0100
Subject: bpftool: Remove unused includes to <bpf/bpf_gen_internal.h>

It seems that the header file was never necessary to compile bpftool,
and it is not part of the headers exported from libbpf. Let's remove the
includes from prog.c and gen.c.

Fixes: d510296d331a ("bpftool: Use syscall/loader program in "prog load" and "gen skeleton" command.")
Signed-off-by: Quentin Monnet <quentin@isovalent.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20211007194438.34443-3-quentin@isovalent.com
---
 tools/bpf/bpftool/gen.c  | 1 -
 tools/bpf/bpftool/prog.c | 1 -
 2 files changed, 2 deletions(-)

(limited to 'tools')

diff --git a/tools/bpf/bpftool/gen.c b/tools/bpf/bpftool/gen.c
index cc835859465b..b2ffc18eafc1 100644
--- a/tools/bpf/bpftool/gen.c
+++ b/tools/bpf/bpftool/gen.c
@@ -18,7 +18,6 @@
 #include <sys/stat.h>
 #include <sys/mman.h>
 #include <bpf/btf.h>
-#include <bpf/bpf_gen_internal.h>
 
 #include "json_writer.h"
 #include "main.h"
diff --git a/tools/bpf/bpftool/prog.c b/tools/bpf/bpftool/prog.c
index a24ea7e26aa4..277d51c4c5d9 100644
--- a/tools/bpf/bpftool/prog.c
+++ b/tools/bpf/bpftool/prog.c
@@ -25,7 +25,6 @@
 #include <bpf/bpf.h>
 #include <bpf/btf.h>
 #include <bpf/libbpf.h>
-#include <bpf/bpf_gen_internal.h>
 #include <bpf/skel_internal.h>
 
 #include "cfg.h"
-- 
cgit v1.2.3


From f012ade10b34c461663bc3dd957636be06804b0d Mon Sep 17 00:00:00 2001
From: Quentin Monnet <quentin@isovalent.com>
Date: Thu, 7 Oct 2021 20:44:29 +0100
Subject: bpftool: Install libbpf headers instead of including the dir

Bpftool relies on libbpf, therefore it relies on a number of headers
from the library and must be linked against the library. The Makefile
for bpftool exposes these objects by adding tools/lib as an include
directory ("-I$(srctree)/tools/lib"). This is a working solution, but
this is not the cleanest one. The risk is to involuntarily include
objects that are not intended to be exposed by the libbpf.

The headers needed to compile bpftool should in fact be "installed" from
libbpf, with its "install_headers" Makefile target. In addition, there
is one header which is internal to the library and not supposed to be
used by external applications, but that bpftool uses anyway.

Adjust the Makefile in order to install the header files properly before
compiling bpftool. Also copy the additional internal header file
(nlattr.h), but call it out explicitly. Build (and install headers) in a
subdirectory under bpftool/ instead of tools/lib/bpf/. When descending
from a parent Makefile, this is configurable by setting the OUTPUT,
LIBBPF_OUTPUT and LIBBPF_DESTDIR variables.

Also adjust the Makefile for BPF selftests, so as to reuse the (host)
libbpf compiled earlier and to avoid compiling a separate version of the
library just for bpftool.

Signed-off-by: Quentin Monnet <quentin@isovalent.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Acked-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20211007194438.34443-4-quentin@isovalent.com
---
 tools/bpf/bpftool/Makefile           | 33 +++++++++++++++++++++------------
 tools/testing/selftests/bpf/Makefile |  2 ++
 2 files changed, 23 insertions(+), 12 deletions(-)

(limited to 'tools')

diff --git a/tools/bpf/bpftool/Makefile b/tools/bpf/bpftool/Makefile
index 1fcf5b01a193..ba02d71c39ef 100644
--- a/tools/bpf/bpftool/Makefile
+++ b/tools/bpf/bpftool/Makefile
@@ -17,19 +17,23 @@ endif
 BPF_DIR = $(srctree)/tools/lib/bpf/
 
 ifneq ($(OUTPUT),)
-  LIBBPF_OUTPUT = $(OUTPUT)/libbpf/
-  LIBBPF_PATH = $(LIBBPF_OUTPUT)
-  BOOTSTRAP_OUTPUT = $(OUTPUT)/bootstrap/
+  _OUTPUT := $(OUTPUT)
 else
-  LIBBPF_OUTPUT =
-  LIBBPF_PATH = $(BPF_DIR)
-  BOOTSTRAP_OUTPUT = $(CURDIR)/bootstrap/
+  _OUTPUT := $(CURDIR)
 endif
+BOOTSTRAP_OUTPUT := $(_OUTPUT)/bootstrap/
+LIBBPF_OUTPUT := $(_OUTPUT)/libbpf/
+LIBBPF_DESTDIR := $(LIBBPF_OUTPUT)
+LIBBPF_INCLUDE := $(LIBBPF_DESTDIR)/include
 
-LIBBPF = $(LIBBPF_PATH)libbpf.a
+LIBBPF = $(LIBBPF_OUTPUT)libbpf.a
 LIBBPF_BOOTSTRAP_OUTPUT = $(BOOTSTRAP_OUTPUT)libbpf/
 LIBBPF_BOOTSTRAP = $(LIBBPF_BOOTSTRAP_OUTPUT)libbpf.a
 
+# We need to copy nlattr.h which is not otherwise exported by libbpf, but still
+# required by bpftool.
+LIBBPF_INTERNAL_HDRS := nlattr.h
+
 ifeq ($(BPFTOOL_VERSION),)
 BPFTOOL_VERSION := $(shell make -rR --no-print-directory -sC ../../.. kernelversion)
 endif
@@ -38,7 +42,13 @@ $(LIBBPF_OUTPUT) $(BOOTSTRAP_OUTPUT) $(LIBBPF_BOOTSTRAP_OUTPUT):
 	$(QUIET_MKDIR)mkdir -p $@
 
 $(LIBBPF): FORCE | $(LIBBPF_OUTPUT)
-	$(Q)$(MAKE) -C $(BPF_DIR) OUTPUT=$(LIBBPF_OUTPUT) $(LIBBPF_OUTPUT)libbpf.a
+	$(Q)$(MAKE) -C $(BPF_DIR) OUTPUT=$(LIBBPF_OUTPUT) \
+		DESTDIR=$(LIBBPF_DESTDIR) prefix= $(LIBBPF) install_headers
+
+$(LIBBPF_INCLUDE)/bpf/$(LIBBPF_INTERNAL_HDRS): \
+		$(addprefix $(BPF_DIR),$(LIBBPF_INTERNAL_HDRS)) $(LIBBPF)
+	$(call QUIET_INSTALL, bpf/$(notdir $@))
+	$(Q)install -m 644 -t $(LIBBPF_INCLUDE)/bpf/ $(BPF_DIR)$(notdir $@)
 
 $(LIBBPF_BOOTSTRAP): FORCE | $(LIBBPF_BOOTSTRAP_OUTPUT)
 	$(Q)$(MAKE) -C $(BPF_DIR) OUTPUT=$(LIBBPF_BOOTSTRAP_OUTPUT) \
@@ -60,10 +70,10 @@ CFLAGS += -W -Wall -Wextra -Wno-unused-parameter -Wno-missing-field-initializers
 CFLAGS += $(filter-out -Wswitch-enum -Wnested-externs,$(EXTRA_WARNINGS))
 CFLAGS += -DPACKAGE='"bpftool"' -D__EXPORTED_HEADERS__ \
 	-I$(if $(OUTPUT),$(OUTPUT),.) \
+	-I$(LIBBPF_INCLUDE) \
 	-I$(srctree)/kernel/bpf/ \
 	-I$(srctree)/tools/include \
 	-I$(srctree)/tools/include/uapi \
-	-I$(srctree)/tools/lib \
 	-I$(srctree)/tools/perf
 CFLAGS += -DBPFTOOL_VERSION='"$(BPFTOOL_VERSION)"'
 ifneq ($(EXTRA_CFLAGS),)
@@ -140,7 +150,7 @@ BOOTSTRAP_OBJS = $(addprefix $(BOOTSTRAP_OUTPUT),main.o common.o json_writer.o g
 $(BOOTSTRAP_OBJS): $(LIBBPF_BOOTSTRAP)
 
 OBJS = $(patsubst %.c,$(OUTPUT)%.o,$(SRCS)) $(OUTPUT)disasm.o
-$(OBJS): $(LIBBPF)
+$(OBJS): $(LIBBPF) $(LIBBPF_INCLUDE)/bpf/$(LIBBPF_INTERNAL_HDRS)
 
 VMLINUX_BTF_PATHS ?= $(if $(O),$(O)/vmlinux)				\
 		     $(if $(KBUILD_OUTPUT),$(KBUILD_OUTPUT)/vmlinux)	\
@@ -167,8 +177,7 @@ $(OUTPUT)%.bpf.o: skeleton/%.bpf.c $(OUTPUT)vmlinux.h $(LIBBPF)
 	$(QUIET_CLANG)$(CLANG) \
 		-I$(if $(OUTPUT),$(OUTPUT),.) \
 		-I$(srctree)/tools/include/uapi/ \
-		-I$(LIBBPF_PATH) \
-		-I$(srctree)/tools/lib \
+		-I$(LIBBPF_INCLUDE) \
 		-g -O2 -Wall -target bpf -c $< -o $@ && $(LLVM_STRIP) -g $@
 
 $(OUTPUT)%.skel.h: $(OUTPUT)%.bpf.o $(BPFTOOL_BOOTSTRAP)
diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index c5c9a9f50d8d..849a4637f59d 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -209,6 +209,8 @@ $(DEFAULT_BPFTOOL): $(wildcard $(BPFTOOLDIR)/*.[ch] $(BPFTOOLDIR)/Makefile)    \
 		    CC=$(HOSTCC) LD=$(HOSTLD)				       \
 		    EXTRA_CFLAGS='-g -O0'				       \
 		    OUTPUT=$(HOST_BUILD_DIR)/bpftool/			       \
+		    LIBBPF_OUTPUT=$(HOST_BUILD_DIR)/libbpf/		       \
+		    LIBBPF_DESTDIR=$(HOST_SCRATCH_DIR)/			       \
 		    prefix= DESTDIR=$(HOST_SCRATCH_DIR)/ install
 
 all: docs
-- 
cgit v1.2.3


From 1478994aad82810d833bf9c816fb4e9845553e9b Mon Sep 17 00:00:00 2001
From: Quentin Monnet <quentin@isovalent.com>
Date: Thu, 7 Oct 2021 20:44:30 +0100
Subject: tools/resolve_btfids: Install libbpf headers when building

API headers from libbpf should not be accessed directly from the
library's source directory. Instead, they should be exported with "make
install_headers". Let's make sure that resolve_btfids installs the
headers properly when building.

When descending from a parent Makefile, the specific output directories
for building the library and exporting the headers are configurable with
LIBBPF_OUT and LIBBPF_DESTDIR, respectively. This is in addition to
OUTPUT, on top of which those variables are constructed by default.

Also adjust the Makefile for the BPF selftests in order to point to the
(target) libbpf shared with other tools, instead of building a version
specific to resolve_btfids. Remove libbpf's order-only dependencies on
the include directories (they are created by libbpf and don't need to
exist beforehand).

Signed-off-by: Quentin Monnet <quentin@isovalent.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Acked-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20211007194438.34443-5-quentin@isovalent.com
---
 tools/bpf/resolve_btfids/Makefile    | 16 +++++++++++-----
 tools/bpf/resolve_btfids/main.c      |  4 ++--
 tools/testing/selftests/bpf/Makefile |  7 +++++--
 3 files changed, 18 insertions(+), 9 deletions(-)

(limited to 'tools')

diff --git a/tools/bpf/resolve_btfids/Makefile b/tools/bpf/resolve_btfids/Makefile
index 08b75e314ae7..751643f860b2 100644
--- a/tools/bpf/resolve_btfids/Makefile
+++ b/tools/bpf/resolve_btfids/Makefile
@@ -29,25 +29,30 @@ BPFOBJ     := $(OUTPUT)/libbpf/libbpf.a
 LIBBPF_OUT := $(abspath $(dir $(BPFOBJ)))/
 SUBCMDOBJ  := $(OUTPUT)/libsubcmd/libsubcmd.a
 
+LIBBPF_DESTDIR := $(LIBBPF_OUT)
+LIBBPF_INCLUDE := $(LIBBPF_DESTDIR)include
+
 BINARY     := $(OUTPUT)/resolve_btfids
 BINARY_IN  := $(BINARY)-in.o
 
 all: $(BINARY)
 
-$(OUTPUT) $(OUTPUT)/libbpf $(OUTPUT)/libsubcmd:
+$(OUTPUT) $(OUTPUT)/libsubcmd $(LIBBPF_OUT):
 	$(call msg,MKDIR,,$@)
 	$(Q)mkdir -p $(@)
 
 $(SUBCMDOBJ): fixdep FORCE | $(OUTPUT)/libsubcmd
 	$(Q)$(MAKE) -C $(SUBCMD_SRC) OUTPUT=$(abspath $(dir $@))/ $(abspath $@)
 
-$(BPFOBJ): $(wildcard $(LIBBPF_SRC)/*.[ch] $(LIBBPF_SRC)/Makefile) | $(OUTPUT)/libbpf
-	$(Q)$(MAKE) $(submake_extras) -C $(LIBBPF_SRC)  OUTPUT=$(LIBBPF_OUT) $(abspath $@)
+$(BPFOBJ): $(wildcard $(LIBBPF_SRC)/*.[ch] $(LIBBPF_SRC)/Makefile) | $(LIBBPF_OUT)
+	$(Q)$(MAKE) $(submake_extras) -C $(LIBBPF_SRC) OUTPUT=$(LIBBPF_OUT)    \
+		    DESTDIR=$(LIBBPF_DESTDIR) prefix=			       \
+		    $(abspath $@) install_headers
 
 CFLAGS := -g \
           -I$(srctree)/tools/include \
           -I$(srctree)/tools/include/uapi \
-          -I$(LIBBPF_SRC) \
+          -I$(LIBBPF_INCLUDE) \
           -I$(SUBCMD_SRC)
 
 LIBS = -lelf -lz
@@ -65,7 +70,8 @@ $(BINARY): $(BPFOBJ) $(SUBCMDOBJ) $(BINARY_IN)
 clean_objects := $(wildcard $(OUTPUT)/*.o                \
                             $(OUTPUT)/.*.o.cmd           \
                             $(OUTPUT)/.*.o.d             \
-                            $(OUTPUT)/libbpf             \
+                            $(LIBBPF_OUT)                \
+                            $(LIBBPF_DESTDIR)            \
                             $(OUTPUT)/libsubcmd          \
                             $(OUTPUT)/resolve_btfids)
 
diff --git a/tools/bpf/resolve_btfids/main.c b/tools/bpf/resolve_btfids/main.c
index c6c3e613858a..716e6ad1864b 100644
--- a/tools/bpf/resolve_btfids/main.c
+++ b/tools/bpf/resolve_btfids/main.c
@@ -60,8 +60,8 @@
 #include <linux/rbtree.h>
 #include <linux/zalloc.h>
 #include <linux/err.h>
-#include <btf.h>
-#include <libbpf.h>
+#include <bpf/btf.h>
+#include <bpf/libbpf.h>
 #include <parse-options.h>
 
 #define BTF_IDS_SECTION	".BTF_ids"
diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index 849a4637f59d..090f424ac5e1 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -122,9 +122,11 @@ BPFOBJ := $(BUILD_DIR)/libbpf/libbpf.a
 ifneq ($(CROSS_COMPILE),)
 HOST_BUILD_DIR		:= $(BUILD_DIR)/host
 HOST_SCRATCH_DIR	:= $(OUTPUT)/host-tools
+HOST_INCLUDE_DIR	:= $(HOST_SCRATCH_DIR)/include
 else
 HOST_BUILD_DIR		:= $(BUILD_DIR)
 HOST_SCRATCH_DIR	:= $(SCRATCH_DIR)
+HOST_INCLUDE_DIR	:= $(INCLUDE_DIR)
 endif
 HOST_BPFOBJ := $(HOST_BUILD_DIR)/libbpf/libbpf.a
 RESOLVE_BTFIDS := $(HOST_BUILD_DIR)/resolve_btfids/resolve_btfids
@@ -227,7 +229,7 @@ docs-clean:
 
 $(BPFOBJ): $(wildcard $(BPFDIR)/*.[ch] $(BPFDIR)/Makefile)		       \
 	   ../../../include/uapi/linux/bpf.h                                   \
-	   | $(INCLUDE_DIR) $(BUILD_DIR)/libbpf
+	   | $(BUILD_DIR)/libbpf
 	$(Q)$(MAKE) $(submake_extras) -C $(BPFDIR) OUTPUT=$(BUILD_DIR)/libbpf/ \
 		    EXTRA_CFLAGS='-g -O0'				       \
 		    DESTDIR=$(SCRATCH_DIR) prefix= all install_headers
@@ -235,7 +237,7 @@ $(BPFOBJ): $(wildcard $(BPFDIR)/*.[ch] $(BPFDIR)/Makefile)		       \
 ifneq ($(BPFOBJ),$(HOST_BPFOBJ))
 $(HOST_BPFOBJ): $(wildcard $(BPFDIR)/*.[ch] $(BPFDIR)/Makefile)                \
 	   ../../../include/uapi/linux/bpf.h                                   \
-	   | $(INCLUDE_DIR) $(HOST_BUILD_DIR)/libbpf
+	   | $(HOST_BUILD_DIR)/libbpf
 	$(Q)$(MAKE) $(submake_extras) -C $(BPFDIR)                             \
 		    EXTRA_CFLAGS='-g -O0'				       \
 		    OUTPUT=$(HOST_BUILD_DIR)/libbpf/ CC=$(HOSTCC) LD=$(HOSTLD) \
@@ -260,6 +262,7 @@ $(RESOLVE_BTFIDS): $(HOST_BPFOBJ) | $(HOST_BUILD_DIR)/resolve_btfids	\
 		       $(TOOLSDIR)/lib/str_error_r.c
 	$(Q)$(MAKE) $(submake_extras) -C $(TOOLSDIR)/bpf/resolve_btfids	\
 		CC=$(HOSTCC) LD=$(HOSTLD) AR=$(HOSTAR) \
+		LIBBPF_INCLUDE=$(HOST_INCLUDE_DIR) \
 		OUTPUT=$(HOST_BUILD_DIR)/resolve_btfids/ BPFOBJ=$(HOST_BPFOBJ)
 
 # Get Clang's default includes on this system, as opposed to those seen by
-- 
cgit v1.2.3


From be79505caf3f99a2f9cca5946261085b333f7034 Mon Sep 17 00:00:00 2001
From: Quentin Monnet <quentin@isovalent.com>
Date: Thu, 7 Oct 2021 20:44:31 +0100
Subject: tools/runqslower: Install libbpf headers when building

API headers from libbpf should not be accessed directly from the
library's source directory. Instead, they should be exported with "make
install_headers". Let's make sure that runqslower installs the
headers properly when building.

We use a libbpf_hdrs target to mark the logical dependency on libbpf's
headers export for a number of object files, even though the headers
should have been exported at this time (since bpftool needs them, and is
required to generate the skeleton or the vmlinux.h).

When descending from a parent Makefile, the specific output directories
for building the library and exporting the headers are configurable with
BPFOBJ_OUTPUT and BPF_DESTDIR, respectively. This is in addition to
OUTPUT, on top of which those variables are constructed by default.

Also adjust the Makefile for the BPF selftests. We pass a number of
variables to the "make" invocation, because we want to point runqslower
to the (target) libbpf shared with other tools, instead of building its
own version. In addition, runqslower relies on (target) bpftool, and we
also want to pass the proper variables to its Makefile so that bpftool
itself reuses the same libbpf.

Signed-off-by: Quentin Monnet <quentin@isovalent.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20211007194438.34443-6-quentin@isovalent.com
---
 tools/bpf/runqslower/Makefile        | 22 +++++++++++++---------
 tools/testing/selftests/bpf/Makefile | 15 +++++++++------
 2 files changed, 22 insertions(+), 15 deletions(-)

(limited to 'tools')

diff --git a/tools/bpf/runqslower/Makefile b/tools/bpf/runqslower/Makefile
index 3818ec511fd2..bbd1150578f7 100644
--- a/tools/bpf/runqslower/Makefile
+++ b/tools/bpf/runqslower/Makefile
@@ -9,9 +9,9 @@ BPFTOOL ?= $(DEFAULT_BPFTOOL)
 LIBBPF_SRC := $(abspath ../../lib/bpf)
 BPFOBJ_OUTPUT := $(OUTPUT)libbpf/
 BPFOBJ := $(BPFOBJ_OUTPUT)libbpf.a
-BPF_INCLUDE := $(BPFOBJ_OUTPUT)
-INCLUDES := -I$(OUTPUT) -I$(BPF_INCLUDE) -I$(abspath ../../lib)        \
-       -I$(abspath ../../include/uapi)
+BPF_DESTDIR := $(BPFOBJ_OUTPUT)
+BPF_INCLUDE := $(BPF_DESTDIR)/include
+INCLUDES := -I$(OUTPUT) -I$(BPF_INCLUDE) -I$(abspath ../../include/uapi)
 CFLAGS := -g -Wall
 
 # Try to detect best kernel BTF source
@@ -33,7 +33,7 @@ endif
 
 .DELETE_ON_ERROR:
 
-.PHONY: all clean runqslower
+.PHONY: all clean runqslower libbpf_hdrs
 all: runqslower
 
 runqslower: $(OUTPUT)/runqslower
@@ -46,13 +46,15 @@ clean:
 	$(Q)$(RM) $(OUTPUT)runqslower
 	$(Q)$(RM) -r .output
 
+libbpf_hdrs: $(BPFOBJ)
+
 $(OUTPUT)/runqslower: $(OUTPUT)/runqslower.o $(BPFOBJ)
 	$(QUIET_LINK)$(CC) $(CFLAGS) $^ -lelf -lz -o $@
 
 $(OUTPUT)/runqslower.o: runqslower.h $(OUTPUT)/runqslower.skel.h	      \
-			$(OUTPUT)/runqslower.bpf.o
+			$(OUTPUT)/runqslower.bpf.o | libbpf_hdrs
 
-$(OUTPUT)/runqslower.bpf.o: $(OUTPUT)/vmlinux.h runqslower.h
+$(OUTPUT)/runqslower.bpf.o: $(OUTPUT)/vmlinux.h runqslower.h | libbpf_hdrs
 
 $(OUTPUT)/%.skel.h: $(OUTPUT)/%.bpf.o | $(BPFTOOL)
 	$(QUIET_GEN)$(BPFTOOL) gen skeleton $< > $@
@@ -81,8 +83,10 @@ else
 endif
 
 $(BPFOBJ): $(wildcard $(LIBBPF_SRC)/*.[ch] $(LIBBPF_SRC)/Makefile) | $(BPFOBJ_OUTPUT)
-	$(Q)$(MAKE) $(submake_extras) -C $(LIBBPF_SRC) OUTPUT=$(BPFOBJ_OUTPUT) $@
+	$(Q)$(MAKE) $(submake_extras) -C $(LIBBPF_SRC) OUTPUT=$(BPFOBJ_OUTPUT) \
+		    DESTDIR=$(BPFOBJ_OUTPUT) prefix= $(abspath $@) install_headers
 
-$(DEFAULT_BPFTOOL): | $(BPFTOOL_OUTPUT)
+$(DEFAULT_BPFTOOL): $(BPFOBJ) | $(BPFTOOL_OUTPUT)
 	$(Q)$(MAKE) $(submake_extras) -C ../bpftool OUTPUT=$(BPFTOOL_OUTPUT)   \
-		    CC=$(HOSTCC) LD=$(HOSTLD)
+		    LIBBPF_OUTPUT=$(BPFOBJ_OUTPUT)			       \
+		    LIBBPF_DESTDIR=$(BPF_DESTDIR) CC=$(HOSTCC) LD=$(HOSTLD)
diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index 090f424ac5e1..e023d734f7b0 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -130,6 +130,7 @@ HOST_INCLUDE_DIR	:= $(INCLUDE_DIR)
 endif
 HOST_BPFOBJ := $(HOST_BUILD_DIR)/libbpf/libbpf.a
 RESOLVE_BTFIDS := $(HOST_BUILD_DIR)/resolve_btfids/resolve_btfids
+RUNQSLOWER_OUTPUT := $(BUILD_DIR)/runqslower/
 
 VMLINUX_BTF_PATHS ?= $(if $(O),$(O)/vmlinux)				\
 		     $(if $(KBUILD_OUTPUT),$(KBUILD_OUTPUT)/vmlinux)	\
@@ -154,7 +155,7 @@ $(notdir $(TEST_GEN_PROGS)						\
 # sort removes libbpf duplicates when not cross-building
 MAKE_DIRS := $(sort $(BUILD_DIR)/libbpf $(HOST_BUILD_DIR)/libbpf	       \
 	       $(HOST_BUILD_DIR)/bpftool $(HOST_BUILD_DIR)/resolve_btfids      \
-	       $(INCLUDE_DIR))
+	       $(RUNQSLOWER_OUTPUT) $(INCLUDE_DIR))
 $(MAKE_DIRS):
 	$(call msg,MKDIR,,$@)
 	$(Q)mkdir -p $@
@@ -183,11 +184,13 @@ $(OUTPUT)/test_stub.o: test_stub.c $(BPFOBJ)
 
 DEFAULT_BPFTOOL := $(HOST_SCRATCH_DIR)/sbin/bpftool
 
-$(OUTPUT)/runqslower: $(BPFOBJ) | $(DEFAULT_BPFTOOL)
-	$(Q)$(MAKE) $(submake_extras) -C $(TOOLSDIR)/bpf/runqslower	\
-		    OUTPUT=$(SCRATCH_DIR)/ VMLINUX_BTF=$(VMLINUX_BTF)   \
-		    BPFOBJ=$(BPFOBJ) BPF_INCLUDE=$(INCLUDE_DIR) &&	\
-		    cp $(SCRATCH_DIR)/runqslower $@
+$(OUTPUT)/runqslower: $(BPFOBJ) | $(DEFAULT_BPFTOOL) $(RUNQSLOWER_OUTPUT)
+	$(Q)$(MAKE) $(submake_extras) -C $(TOOLSDIR)/bpf/runqslower	       \
+		    OUTPUT=$(RUNQSLOWER_OUTPUT) VMLINUX_BTF=$(VMLINUX_BTF)     \
+		    BPFTOOL_OUTPUT=$(BUILD_DIR)/bpftool/		       \
+		    BPFOBJ_OUTPUT=$(BUILD_DIR)/libbpf			       \
+		    BPFOBJ=$(BPFOBJ) BPF_INCLUDE=$(INCLUDE_DIR) &&	       \
+		    cp $(RUNQSLOWER_OUTPUT)runqslower $@
 
 TEST_GEN_PROGS_EXTENDED += $(DEFAULT_BPFTOOL)
 
-- 
cgit v1.2.3


From 87ee33bfdd4f74edc1548c7f0140800cfcc33039 Mon Sep 17 00:00:00 2001
From: Quentin Monnet <quentin@isovalent.com>
Date: Thu, 7 Oct 2021 20:44:37 +0100
Subject: selftests/bpf: Better clean up for runqslower in
 test_bpftool_build.sh

The script test_bpftool_build.sh attempts to build bpftool in the
various supported ways, to make sure nothing breaks.

One of those ways is to run "make tools/bpf" from the root of the kernel
repository. This command builds bpftool, along with the other tools
under tools/bpf, and runqslower in particular. After running the
command and upon a successful bpftool build, the script attempts to
cleanup the generated objects. However, after building with this target
and in the case of runqslower, the files are not cleaned up as expected.

This is because the "tools/bpf" target sets $(OUTPUT) to
.../tools/bpf/runqslower/ when building the tool, causing the object
files to be placed directly under the runqslower directory. But when
running "cd tools/bpf; make clean", the value for $(OUTPUT) is set to
".output" (relative to the runqslower directory) by runqslower's
Makefile, and this is where the Makefile looks for files to clean up.

We cannot easily fix in the root Makefile (where "tools/bpf" is defined)
or in tools/scripts/Makefile.include (setting $(OUTPUT)), where changing
the way the output variables are passed would likely have consequences
elsewhere. We could change runqslower's Makefile to build in the
repository instead of in a dedicated ".output/", but doing so just to
accommodate a test script doesn't sound great. Instead, let's just make
sure that we clean up runqslower properly by adding the correct command
to the script.

This will attempt to clean runqslower twice: the first try with command
"cd tools/bpf; make clean" will search for tools/bpf/runqslower/.output
and fail to clean it (but will still clean the other tools, in
particular bpftool), the second one (added in this commit) sets the
$(OUTPUT) variable like for building with the "tool/bpf" target and
should succeed.

Signed-off-by: Quentin Monnet <quentin@isovalent.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20211007194438.34443-12-quentin@isovalent.com
---
 tools/testing/selftests/bpf/test_bpftool_build.sh | 4 ++++
 1 file changed, 4 insertions(+)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/test_bpftool_build.sh b/tools/testing/selftests/bpf/test_bpftool_build.sh
index b03a87571592..1453a53ed547 100755
--- a/tools/testing/selftests/bpf/test_bpftool_build.sh
+++ b/tools/testing/selftests/bpf/test_bpftool_build.sh
@@ -90,6 +90,10 @@ echo -e "... through kbuild\n"
 
 if [ -f ".config" ] ; then
 	make_and_clean tools/bpf
+	## "make tools/bpf" sets $(OUTPUT) to ...tools/bpf/runqslower for
+	## runqslower, but the default (used for the "clean" target) is .output.
+	## Let's make sure we clean runqslower's directory properly.
+	make -C tools/bpf/runqslower OUTPUT=${KDIR_ROOT_DIR}/tools/bpf/runqslower/ clean
 
 	## $OUTPUT is overwritten in kbuild Makefile, and thus cannot be passed
 	## down from toplevel Makefile to bpftool's Makefile.
-- 
cgit v1.2.3


From d7db0a4e8d95101ebb545444578ba7085c270e5f Mon Sep 17 00:00:00 2001
From: Quentin Monnet <quentin@isovalent.com>
Date: Thu, 7 Oct 2021 20:44:38 +0100
Subject: bpftool: Add install-bin target to install binary only

With "make install", bpftool installs its binary and its bash completion
file. Usually, this is what we want. But a few components in the kernel
repository (namely, BPF iterators and selftests) also install bpftool
locally before using it. In such a case, bash completion is not
necessary and is just a useless build artifact.

Let's add an "install-bin" target to bpftool, to offer a way to install
the binary only.

Signed-off-by: Quentin Monnet <quentin@isovalent.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20211007194438.34443-13-quentin@isovalent.com
---
 tools/bpf/bpftool/Makefile           | 6 ++++--
 tools/testing/selftests/bpf/Makefile | 2 +-
 2 files changed, 5 insertions(+), 3 deletions(-)

(limited to 'tools')

diff --git a/tools/bpf/bpftool/Makefile b/tools/bpf/bpftool/Makefile
index ba02d71c39ef..9c2d13c513f0 100644
--- a/tools/bpf/bpftool/Makefile
+++ b/tools/bpf/bpftool/Makefile
@@ -226,10 +226,12 @@ clean: $(LIBBPF)-clean $(LIBBPF_BOOTSTRAP)-clean feature-detect-clean
 	$(Q)$(RM) -- $(OUTPUT)FEATURE-DUMP.bpftool
 	$(Q)$(RM) -r -- $(OUTPUT)feature/
 
-install: $(OUTPUT)bpftool
+install-bin: $(OUTPUT)bpftool
 	$(call QUIET_INSTALL, bpftool)
 	$(Q)$(INSTALL) -m 0755 -d $(DESTDIR)$(prefix)/sbin
 	$(Q)$(INSTALL) $(OUTPUT)bpftool $(DESTDIR)$(prefix)/sbin/bpftool
+
+install: install-bin
 	$(Q)$(INSTALL) -m 0755 -d $(DESTDIR)$(bash_compdir)
 	$(Q)$(INSTALL) -m 0644 bash-completion/bpftool $(DESTDIR)$(bash_compdir)
 
@@ -256,6 +258,6 @@ zdep:
 	@if [ "$(feature-zlib)" != "1" ]; then echo "No zlib found"; exit 1 ; fi
 
 .SECONDARY:
-.PHONY: all FORCE clean install uninstall zdep
+.PHONY: all FORCE clean install-bin install uninstall zdep
 .PHONY: doc doc-clean doc-install doc-uninstall
 .DEFAULT_GOAL := all
diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index e023d734f7b0..498222543c37 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -216,7 +216,7 @@ $(DEFAULT_BPFTOOL): $(wildcard $(BPFTOOLDIR)/*.[ch] $(BPFTOOLDIR)/Makefile)    \
 		    OUTPUT=$(HOST_BUILD_DIR)/bpftool/			       \
 		    LIBBPF_OUTPUT=$(HOST_BUILD_DIR)/libbpf/		       \
 		    LIBBPF_DESTDIR=$(HOST_SCRATCH_DIR)/			       \
-		    prefix= DESTDIR=$(HOST_SCRATCH_DIR)/ install
+		    prefix= DESTDIR=$(HOST_SCRATCH_DIR)/ install-bin
 
 all: docs
 
-- 
cgit v1.2.3


From ccaf12d6215a56836472db220520cda8024d6c4f Mon Sep 17 00:00:00 2001
From: Hou Tao <houtao1@huawei.com>
Date: Mon, 4 Oct 2021 17:48:56 +0800
Subject: libbpf: Support detecting and attaching of writable tracepoint
 program

Program on writable tracepoint is BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE,
but its attachment is the same as BPF_PROG_TYPE_RAW_TRACEPOINT.

Signed-off-by: Hou Tao <houtao1@huawei.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20211004094857.30868-3-hotforest@gmail.com
---
 tools/lib/bpf/libbpf.c | 26 +++++++++++++++++++++-----
 1 file changed, 21 insertions(+), 5 deletions(-)

(limited to 'tools')

diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index ed313fd491bd..ae0889bebe32 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -8077,6 +8077,8 @@ static const struct bpf_sec_def section_defs[] = {
 	SEC_DEF("tp/",			TRACEPOINT, 0, SEC_NONE, attach_tp),
 	SEC_DEF("raw_tracepoint/",	RAW_TRACEPOINT, 0, SEC_NONE, attach_raw_tp),
 	SEC_DEF("raw_tp/",		RAW_TRACEPOINT, 0, SEC_NONE, attach_raw_tp),
+	SEC_DEF("raw_tracepoint.w/",	RAW_TRACEPOINT_WRITABLE, 0, SEC_NONE, attach_raw_tp),
+	SEC_DEF("raw_tp.w/",		RAW_TRACEPOINT_WRITABLE, 0, SEC_NONE, attach_raw_tp),
 	SEC_DEF("tp_btf/",		TRACING, BPF_TRACE_RAW_TP, SEC_ATTACH_BTF, attach_trace),
 	SEC_DEF("fentry/",		TRACING, BPF_TRACE_FENTRY, SEC_ATTACH_BTF, attach_trace),
 	SEC_DEF("fmod_ret/",		TRACING, BPF_MODIFY_RETURN, SEC_ATTACH_BTF, attach_trace),
@@ -9846,12 +9848,26 @@ struct bpf_link *bpf_program__attach_raw_tracepoint(const struct bpf_program *pr
 
 static struct bpf_link *attach_raw_tp(const struct bpf_program *prog, long cookie)
 {
-	const char *tp_name;
+	static const char *const prefixes[] = {
+		"raw_tp/",
+		"raw_tracepoint/",
+		"raw_tp.w/",
+		"raw_tracepoint.w/",
+	};
+	size_t i;
+	const char *tp_name = NULL;
 
-	if (str_has_pfx(prog->sec_name, "raw_tp/"))
-		tp_name = prog->sec_name + sizeof("raw_tp/") - 1;
-	else
-		tp_name = prog->sec_name + sizeof("raw_tracepoint/") - 1;
+	for (i = 0; i < ARRAY_SIZE(prefixes); i++) {
+		if (str_has_pfx(prog->sec_name, prefixes[i])) {
+			tp_name = prog->sec_name + strlen(prefixes[i]);
+			break;
+		}
+	}
+	if (!tp_name) {
+		pr_warn("prog '%s': invalid section name '%s'\n",
+			prog->name, prog->sec_name);
+		return libbpf_err_ptr(-EINVAL);
+	}
 
 	return bpf_program__attach_raw_tracepoint(prog, tp_name);
 }
-- 
cgit v1.2.3


From fa7f17d066bd0996b930b664aa0ed1f213fc1828 Mon Sep 17 00:00:00 2001
From: Hou Tao <houtao1@huawei.com>
Date: Mon, 4 Oct 2021 17:48:57 +0800
Subject: bpf/selftests: Add test for writable bare tracepoint

Add a writable bare tracepoint in bpf_testmod module, and
trigger its calling when reading /sys/kernel/bpf_testmod
with a specific buffer length. The reading will return
the value in writable context if the early return flag
is enabled in writable context.

Signed-off-by: Hou Tao <houtao1@huawei.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Acked-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20211004094857.30868-4-hotforest@gmail.com
---
 .../selftests/bpf/bpf_testmod/bpf_testmod-events.h | 15 ++++++++++
 .../selftests/bpf/bpf_testmod/bpf_testmod.c        | 10 +++++++
 .../selftests/bpf/bpf_testmod/bpf_testmod.h        |  5 ++++
 .../selftests/bpf/prog_tests/module_attach.c       | 35 ++++++++++++++++++++++
 .../selftests/bpf/progs/test_module_attach.c       | 14 +++++++++
 tools/testing/selftests/bpf/test_progs.c           |  4 +--
 tools/testing/selftests/bpf/test_progs.h           |  2 ++
 7 files changed, 83 insertions(+), 2 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod-events.h b/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod-events.h
index 89c6d58e5dd6..11ee801e75e7 100644
--- a/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod-events.h
+++ b/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod-events.h
@@ -34,6 +34,21 @@ DECLARE_TRACE(bpf_testmod_test_write_bare,
 	TP_ARGS(task, ctx)
 );
 
+#undef BPF_TESTMOD_DECLARE_TRACE
+#ifdef DECLARE_TRACE_WRITABLE
+#define BPF_TESTMOD_DECLARE_TRACE(call, proto, args, size) \
+	DECLARE_TRACE_WRITABLE(call, PARAMS(proto), PARAMS(args), size)
+#else
+#define BPF_TESTMOD_DECLARE_TRACE(call, proto, args, size) \
+	DECLARE_TRACE(call, PARAMS(proto), PARAMS(args))
+#endif
+
+BPF_TESTMOD_DECLARE_TRACE(bpf_testmod_test_writable_bare,
+	TP_PROTO(struct bpf_testmod_test_writable_ctx *ctx),
+	TP_ARGS(ctx),
+	sizeof(struct bpf_testmod_test_writable_ctx)
+);
+
 #endif /* _BPF_TESTMOD_EVENTS_H */
 
 #undef TRACE_INCLUDE_PATH
diff --git a/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c b/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c
index b892948dc134..5d52ea2768df 100644
--- a/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c
+++ b/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c
@@ -50,6 +50,16 @@ bpf_testmod_test_read(struct file *file, struct kobject *kobj,
 	if (bpf_testmod_loop_test(101) > 100)
 		trace_bpf_testmod_test_read(current, &ctx);
 
+	/* Magic number to enable writable tp */
+	if (len == 64) {
+		struct bpf_testmod_test_writable_ctx writable = {
+			.val = 1024,
+		};
+		trace_bpf_testmod_test_writable_bare(&writable);
+		if (writable.early_ret)
+			return snprintf(buf, len, "%d\n", writable.val);
+	}
+
 	return -EIO; /* always fail */
 }
 EXPORT_SYMBOL(bpf_testmod_test_read);
diff --git a/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.h b/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.h
index b3892dc40111..0d71e2607832 100644
--- a/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.h
+++ b/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.h
@@ -17,4 +17,9 @@ struct bpf_testmod_test_write_ctx {
 	size_t len;
 };
 
+struct bpf_testmod_test_writable_ctx {
+	bool early_ret;
+	int val;
+};
+
 #endif /* _BPF_TESTMOD_H */
diff --git a/tools/testing/selftests/bpf/prog_tests/module_attach.c b/tools/testing/selftests/bpf/prog_tests/module_attach.c
index 1797a6e4d6d8..6d0e50dcf47c 100644
--- a/tools/testing/selftests/bpf/prog_tests/module_attach.c
+++ b/tools/testing/selftests/bpf/prog_tests/module_attach.c
@@ -2,10 +2,36 @@
 /* Copyright (c) 2020 Facebook */
 
 #include <test_progs.h>
+#include <stdbool.h>
 #include "test_module_attach.skel.h"
 
 static int duration;
 
+static int trigger_module_test_writable(int *val)
+{
+	int fd, err;
+	char buf[65];
+	ssize_t rd;
+
+	fd = open(BPF_TESTMOD_TEST_FILE, O_RDONLY);
+	err = -errno;
+	if (!ASSERT_GE(fd, 0, "testmode_file_open"))
+		return err;
+
+	rd = read(fd, buf, sizeof(buf) - 1);
+	err = -errno;
+	if (!ASSERT_GT(rd, 0, "testmod_file_rd_val")) {
+		close(fd);
+		return err;
+	}
+
+	buf[rd] = '\0';
+	*val = strtol(buf, NULL, 0);
+	close(fd);
+
+	return 0;
+}
+
 static int delete_module(const char *name, int flags)
 {
 	return syscall(__NR_delete_module, name, flags);
@@ -19,6 +45,7 @@ void test_module_attach(void)
 	struct test_module_attach__bss *bss;
 	struct bpf_link *link;
 	int err;
+	int writable_val = 0;
 
 	skel = test_module_attach__open();
 	if (CHECK(!skel, "skel_open", "failed to open skeleton\n"))
@@ -51,6 +78,14 @@ void test_module_attach(void)
 	ASSERT_EQ(bss->fexit_ret, -EIO, "fexit_tet");
 	ASSERT_EQ(bss->fmod_ret_read_sz, READ_SZ, "fmod_ret");
 
+	bss->raw_tp_writable_bare_early_ret = true;
+	bss->raw_tp_writable_bare_out_val = 0xf1f2f3f4;
+	ASSERT_OK(trigger_module_test_writable(&writable_val),
+		  "trigger_writable");
+	ASSERT_EQ(bss->raw_tp_writable_bare_in_val, 1024, "writable_test_in");
+	ASSERT_EQ(bss->raw_tp_writable_bare_out_val, writable_val,
+		  "writable_test_out");
+
 	test_module_attach__detach(skel);
 
 	/* attach fentry/fexit and make sure it get's module reference */
diff --git a/tools/testing/selftests/bpf/progs/test_module_attach.c b/tools/testing/selftests/bpf/progs/test_module_attach.c
index bd37ceec5587..b36857093f71 100644
--- a/tools/testing/selftests/bpf/progs/test_module_attach.c
+++ b/tools/testing/selftests/bpf/progs/test_module_attach.c
@@ -27,6 +27,20 @@ int BPF_PROG(handle_raw_tp_bare,
 	return 0;
 }
 
+int raw_tp_writable_bare_in_val = 0;
+int raw_tp_writable_bare_early_ret = 0;
+int raw_tp_writable_bare_out_val = 0;
+
+SEC("raw_tp.w/bpf_testmod_test_writable_bare")
+int BPF_PROG(handle_raw_tp_writable_bare,
+	     struct bpf_testmod_test_writable_ctx *writable)
+{
+	raw_tp_writable_bare_in_val = writable->val;
+	writable->early_ret = raw_tp_writable_bare_early_ret;
+	writable->val = raw_tp_writable_bare_out_val;
+	return 0;
+}
+
 __u32 tp_btf_read_sz = 0;
 
 SEC("tp_btf/bpf_testmod_test_read")
diff --git a/tools/testing/selftests/bpf/test_progs.c b/tools/testing/selftests/bpf/test_progs.c
index 2ed01f615d20..007b4ff85fea 100644
--- a/tools/testing/selftests/bpf/test_progs.c
+++ b/tools/testing/selftests/bpf/test_progs.c
@@ -747,7 +747,7 @@ int trigger_module_test_read(int read_sz)
 {
 	int fd, err;
 
-	fd = open("/sys/kernel/bpf_testmod", O_RDONLY);
+	fd = open(BPF_TESTMOD_TEST_FILE, O_RDONLY);
 	err = -errno;
 	if (!ASSERT_GE(fd, 0, "testmod_file_open"))
 		return err;
@@ -769,7 +769,7 @@ int trigger_module_test_write(int write_sz)
 	memset(buf, 'a', write_sz);
 	buf[write_sz-1] = '\0';
 
-	fd = open("/sys/kernel/bpf_testmod", O_WRONLY);
+	fd = open(BPF_TESTMOD_TEST_FILE, O_WRONLY);
 	err = -errno;
 	if (!ASSERT_GE(fd, 0, "testmod_file_open")) {
 		free(buf);
diff --git a/tools/testing/selftests/bpf/test_progs.h b/tools/testing/selftests/bpf/test_progs.h
index 94bef0aa74cf..9b8a1810b700 100644
--- a/tools/testing/selftests/bpf/test_progs.h
+++ b/tools/testing/selftests/bpf/test_progs.h
@@ -301,3 +301,5 @@ int trigger_module_test_write(int write_sz);
 #else
 #define SYS_NANOSLEEP_KPROBE_NAME "sys_nanosleep"
 #endif
+
+#define BPF_TESTMOD_TEST_FILE "/sys/kernel/bpf_testmod"
-- 
cgit v1.2.3


From 91b2c0afd00cb01d715d6e9503624ab33580d5b6 Mon Sep 17 00:00:00 2001
From: Yucong Sun <sunyucong@gmail.com>
Date: Wed, 6 Oct 2021 11:56:06 -0700
Subject: selftests/bpf: Add parallelism to test_progs

This patch adds "-j" mode to test_progs, executing tests in multiple
process.  "-j" mode is optional, and works with all existing test
selection mechanism, as well as "-v", "-l" etc.

In "-j" mode, main process use UDS/SEQPACKET to communicate to each forked
worker, commanding it to run tests and collect logs. After all tests are
finished, a summary is printed. main process use multiple competing
threads to dispatch work to worker, trying to keep them all busy.

The test status will be printed as soon as it is finished, if there are
error logs, it will be printed after the final summary line.

By specifying "--debug", additional debug information on server/worker
communication will be printed.

Example output:
  > ./test_progs -n 15-20 -j
  [   12.801730] bpf_testmod: loading out-of-tree module taints kernel.
  Launching 8 workers.
  #20 btf_split:OK
  #16 btf_endian:OK
  #18 btf_module:OK
  #17 btf_map_in_map:OK
  #19 btf_skc_cls_ingress:OK
  #15 btf_dump:OK
  Summary: 6/20 PASSED, 0 SKIPPED, 0 FAILED

Signed-off-by: Yucong Sun <sunyucong@gmail.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20211006185619.364369-2-fallentree@fb.com
---
 tools/testing/selftests/bpf/test_progs.c | 611 +++++++++++++++++++++++++++++--
 tools/testing/selftests/bpf/test_progs.h |  36 +-
 2 files changed, 610 insertions(+), 37 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/test_progs.c b/tools/testing/selftests/bpf/test_progs.c
index 007b4ff85fea..20dd1e2f8d06 100644
--- a/tools/testing/selftests/bpf/test_progs.c
+++ b/tools/testing/selftests/bpf/test_progs.c
@@ -12,6 +12,11 @@
 #include <string.h>
 #include <execinfo.h> /* backtrace */
 #include <linux/membarrier.h>
+#include <sys/sysinfo.h> /* get_nprocs */
+#include <netinet/in.h>
+#include <sys/select.h>
+#include <sys/socket.h>
+#include <sys/un.h>
 
 /* Adapted from perf/util/string.c */
 static bool glob_match(const char *str, const char *pat)
@@ -48,6 +53,8 @@ struct prog_test_def {
 	bool force_log;
 	int error_cnt;
 	int skip_cnt;
+	int sub_succ_cnt;
+	bool should_run;
 	bool tested;
 	bool need_cgroup_cleanup;
 
@@ -97,6 +104,10 @@ static void dump_test_log(const struct prog_test_def *test, bool failed)
 	if (stdout == env.stdout)
 		return;
 
+	/* worker always holds log */
+	if (env.worker_id != -1)
+		return;
+
 	fflush(stdout); /* exports env.log_buf & env.log_cnt */
 
 	if (env.verbosity > VERBOSE_NONE || test->force_log || failed) {
@@ -107,8 +118,6 @@ static void dump_test_log(const struct prog_test_def *test, bool failed)
 				fprintf(env.stdout, "\n");
 		}
 	}
-
-	fseeko(stdout, 0, SEEK_SET); /* rewind */
 }
 
 static void skip_account(void)
@@ -124,7 +133,8 @@ static void stdio_restore(void);
 /* A bunch of tests set custom affinity per-thread and/or per-process. Reset
  * it after each test/sub-test.
  */
-static void reset_affinity() {
+static void reset_affinity(void)
+{
 
 	cpu_set_t cpuset;
 	int i, err;
@@ -165,21 +175,21 @@ static void restore_netns(void)
 	}
 }
 
-void test__end_subtest()
+void test__end_subtest(void)
 {
 	struct prog_test_def *test = env.test;
 	int sub_error_cnt = test->error_cnt - test->old_error_cnt;
 
 	dump_test_log(test, sub_error_cnt);
 
-	fprintf(env.stdout, "#%d/%d %s/%s:%s\n",
+	fprintf(stdout, "#%d/%d %s/%s:%s\n",
 	       test->test_num, test->subtest_num, test->test_name, test->subtest_name,
 	       sub_error_cnt ? "FAIL" : (test->skip_cnt ? "SKIP" : "OK"));
 
 	if (sub_error_cnt)
-		env.fail_cnt++;
+		test->error_cnt++;
 	else if (test->skip_cnt == 0)
-		env.sub_succ_cnt++;
+		test->sub_succ_cnt++;
 	skip_account();
 
 	free(test->subtest_name);
@@ -217,7 +227,8 @@ bool test__start_subtest(const char *name)
 	return true;
 }
 
-void test__force_log() {
+void test__force_log(void)
+{
 	env.test->force_log = true;
 }
 
@@ -474,6 +485,8 @@ enum ARG_KEYS {
 	ARG_LIST_TEST_NAMES = 'l',
 	ARG_TEST_NAME_GLOB_ALLOWLIST = 'a',
 	ARG_TEST_NAME_GLOB_DENYLIST = 'd',
+	ARG_NUM_WORKERS = 'j',
+	ARG_DEBUG = -1,
 };
 
 static const struct argp_option opts[] = {
@@ -495,6 +508,10 @@ static const struct argp_option opts[] = {
 	  "Run tests with name matching the pattern (supports '*' wildcard)." },
 	{ "deny", ARG_TEST_NAME_GLOB_DENYLIST, "NAMES", 0,
 	  "Don't run tests with name matching the pattern (supports '*' wildcard)." },
+	{ "workers", ARG_NUM_WORKERS, "WORKERS", OPTION_ARG_OPTIONAL,
+	  "Number of workers to run in parallel, default to number of cpus." },
+	{ "debug", ARG_DEBUG, NULL, 0,
+	  "print extra debug information for test_progs." },
 	{},
 };
 
@@ -650,7 +667,7 @@ static error_t parse_arg(int key, char *arg, struct argp_state *state)
 				fprintf(stderr,
 					"Unable to setenv SELFTESTS_VERBOSE=1 (errno=%d)",
 					errno);
-				return -1;
+				return -EINVAL;
 			}
 		}
 
@@ -661,6 +678,20 @@ static error_t parse_arg(int key, char *arg, struct argp_state *state)
 	case ARG_LIST_TEST_NAMES:
 		env->list_test_names = true;
 		break;
+	case ARG_NUM_WORKERS:
+		if (arg) {
+			env->workers = atoi(arg);
+			if (!env->workers) {
+				fprintf(stderr, "Invalid number of worker: %s.", arg);
+				return -EINVAL;
+			}
+		} else {
+			env->workers = get_nprocs();
+		}
+		break;
+	case ARG_DEBUG:
+		env->debug = true;
+		break;
 	case ARGP_KEY_ARG:
 		argp_usage(state);
 		break;
@@ -678,7 +709,7 @@ static void stdio_hijack(void)
 	env.stdout = stdout;
 	env.stderr = stderr;
 
-	if (env.verbosity > VERBOSE_NONE) {
+	if (env.verbosity > VERBOSE_NONE && env.worker_id == -1) {
 		/* nothing to do, output to stdout by default */
 		return;
 	}
@@ -704,10 +735,6 @@ static void stdio_restore(void)
 		return;
 
 	fclose(stdout);
-	free(env.log_buf);
-
-	env.log_buf = NULL;
-	env.log_cnt = 0;
 
 	stdout = env.stdout;
 	stderr = env.stderr;
@@ -794,11 +821,461 @@ void crash_handler(int signum)
 		dump_test_log(env.test, true);
 	if (env.stdout)
 		stdio_restore();
-
+	if (env.worker_id != -1)
+		fprintf(stderr, "[%d]: ", env.worker_id);
 	fprintf(stderr, "Caught signal #%d!\nStack trace:\n", signum);
 	backtrace_symbols_fd(bt, sz, STDERR_FILENO);
 }
 
+static void sigint_handler(int signum)
+{
+	int i;
+
+	for (i = 0; i < env.workers; i++)
+		if (env.worker_socks[i] > 0)
+			close(env.worker_socks[i]);
+}
+
+static int current_test_idx;
+static pthread_mutex_t current_test_lock;
+static pthread_mutex_t stdout_output_lock;
+
+struct test_result {
+	int error_cnt;
+	int skip_cnt;
+	int sub_succ_cnt;
+
+	size_t log_cnt;
+	char *log_buf;
+};
+
+static struct test_result test_results[ARRAY_SIZE(prog_test_defs)];
+
+static inline const char *str_msg(const struct msg *msg, char *buf)
+{
+	switch (msg->type) {
+	case MSG_DO_TEST:
+		sprintf(buf, "MSG_DO_TEST %d", msg->do_test.test_num);
+		break;
+	case MSG_TEST_DONE:
+		sprintf(buf, "MSG_TEST_DONE %d (log: %d)",
+			msg->test_done.test_num,
+			msg->test_done.have_log);
+		break;
+	case MSG_TEST_LOG:
+		sprintf(buf, "MSG_TEST_LOG (cnt: %ld, last: %d)",
+			strlen(msg->test_log.log_buf),
+			msg->test_log.is_last);
+		break;
+	case MSG_EXIT:
+		sprintf(buf, "MSG_EXIT");
+		break;
+	default:
+		sprintf(buf, "UNKNOWN");
+		break;
+	}
+
+	return buf;
+}
+
+static int send_message(int sock, const struct msg *msg)
+{
+	char buf[256];
+
+	if (env.debug)
+		fprintf(stderr, "Sending msg: %s\n", str_msg(msg, buf));
+	return send(sock, msg, sizeof(*msg), 0);
+}
+
+static int recv_message(int sock, struct msg *msg)
+{
+	int ret;
+	char buf[256];
+
+	memset(msg, 0, sizeof(*msg));
+	ret = recv(sock, msg, sizeof(*msg), 0);
+	if (ret >= 0) {
+		if (env.debug)
+			fprintf(stderr, "Received msg: %s\n", str_msg(msg, buf));
+	}
+	return ret;
+}
+
+static void run_one_test(int test_num)
+{
+	struct prog_test_def *test = &prog_test_defs[test_num];
+
+	env.test = test;
+
+	test->run_test();
+
+	/* ensure last sub-test is finalized properly */
+	if (test->subtest_name)
+		test__end_subtest();
+
+	test->tested = true;
+
+	dump_test_log(test, test->error_cnt);
+
+	reset_affinity();
+	restore_netns();
+	if (test->need_cgroup_cleanup)
+		cleanup_cgroup_environment();
+}
+
+struct dispatch_data {
+	int worker_id;
+	int sock_fd;
+};
+
+static void *dispatch_thread(void *ctx)
+{
+	struct dispatch_data *data = ctx;
+	int sock_fd;
+	FILE *log_fd = NULL;
+
+	sock_fd = data->sock_fd;
+
+	while (true) {
+		int test_to_run = -1;
+		struct prog_test_def *test;
+		struct test_result *result;
+
+		/* grab a test */
+		{
+			pthread_mutex_lock(&current_test_lock);
+
+			if (current_test_idx >= prog_test_cnt) {
+				pthread_mutex_unlock(&current_test_lock);
+				goto done;
+			}
+
+			test = &prog_test_defs[current_test_idx];
+			test_to_run = current_test_idx;
+			current_test_idx++;
+
+			pthread_mutex_unlock(&current_test_lock);
+		}
+
+		if (!test->should_run)
+			continue;
+
+		/* run test through worker */
+		{
+			struct msg msg_do_test;
+
+			msg_do_test.type = MSG_DO_TEST;
+			msg_do_test.do_test.test_num = test_to_run;
+			if (send_message(sock_fd, &msg_do_test) < 0) {
+				perror("Fail to send command");
+				goto done;
+			}
+			env.worker_current_test[data->worker_id] = test_to_run;
+		}
+
+		/* wait for test done */
+		{
+			int err;
+			struct msg msg_test_done;
+
+			err = recv_message(sock_fd, &msg_test_done);
+			if (err < 0)
+				goto error;
+			if (msg_test_done.type != MSG_TEST_DONE)
+				goto error;
+			if (test_to_run != msg_test_done.test_done.test_num)
+				goto error;
+
+			test->tested = true;
+			result = &test_results[test_to_run];
+
+			result->error_cnt = msg_test_done.test_done.error_cnt;
+			result->skip_cnt = msg_test_done.test_done.skip_cnt;
+			result->sub_succ_cnt = msg_test_done.test_done.sub_succ_cnt;
+
+			/* collect all logs */
+			if (msg_test_done.test_done.have_log) {
+				log_fd = open_memstream(&result->log_buf, &result->log_cnt);
+				if (!log_fd)
+					goto error;
+
+				while (true) {
+					struct msg msg_log;
+
+					if (recv_message(sock_fd, &msg_log) < 0)
+						goto error;
+					if (msg_log.type != MSG_TEST_LOG)
+						goto error;
+
+					fprintf(log_fd, "%s", msg_log.test_log.log_buf);
+					if (msg_log.test_log.is_last)
+						break;
+				}
+				fclose(log_fd);
+				log_fd = NULL;
+			}
+			/* output log */
+			{
+				pthread_mutex_lock(&stdout_output_lock);
+
+				if (result->log_cnt) {
+					result->log_buf[result->log_cnt] = '\0';
+					fprintf(stdout, "%s", result->log_buf);
+					if (result->log_buf[result->log_cnt - 1] != '\n')
+						fprintf(stdout, "\n");
+				}
+
+				fprintf(stdout, "#%d %s:%s\n",
+					test->test_num, test->test_name,
+					result->error_cnt ? "FAIL" : (result->skip_cnt ? "SKIP" : "OK"));
+
+				pthread_mutex_unlock(&stdout_output_lock);
+			}
+
+		} /* wait for test done */
+	} /* while (true) */
+error:
+	if (env.debug)
+		fprintf(stderr, "[%d]: Protocol/IO error: %s.\n", data->worker_id, strerror(errno));
+
+	if (log_fd)
+		fclose(log_fd);
+done:
+	{
+		struct msg msg_exit;
+
+		msg_exit.type = MSG_EXIT;
+		if (send_message(sock_fd, &msg_exit) < 0) {
+			if (env.debug)
+				fprintf(stderr, "[%d]: send_message msg_exit: %s.\n",
+					data->worker_id, strerror(errno));
+		}
+	}
+	return NULL;
+}
+
+static void print_all_error_logs(void)
+{
+	int i;
+
+	if (env.fail_cnt)
+		fprintf(stdout, "\nAll error logs:\n");
+
+	/* print error logs again */
+	for (i = 0; i < prog_test_cnt; i++) {
+		struct prog_test_def *test;
+		struct test_result *result;
+
+		test = &prog_test_defs[i];
+		result = &test_results[i];
+
+		if (!test->tested || !result->error_cnt)
+			continue;
+
+		fprintf(stdout, "\n#%d %s:%s\n",
+			test->test_num, test->test_name,
+			result->error_cnt ? "FAIL" : (result->skip_cnt ? "SKIP" : "OK"));
+
+		if (result->log_cnt) {
+			result->log_buf[result->log_cnt] = '\0';
+			fprintf(stdout, "%s", result->log_buf);
+			if (result->log_buf[result->log_cnt - 1] != '\n')
+				fprintf(stdout, "\n");
+		}
+	}
+}
+
+static int server_main(void)
+{
+	pthread_t *dispatcher_threads;
+	struct dispatch_data *data;
+	struct sigaction sigact_int = {
+		.sa_handler = sigint_handler,
+		.sa_flags = SA_RESETHAND,
+	};
+	int i;
+
+	sigaction(SIGINT, &sigact_int, NULL);
+
+	dispatcher_threads = calloc(sizeof(pthread_t), env.workers);
+	data = calloc(sizeof(struct dispatch_data), env.workers);
+
+	env.worker_current_test = calloc(sizeof(int), env.workers);
+	for (i = 0; i < env.workers; i++) {
+		int rc;
+
+		data[i].worker_id = i;
+		data[i].sock_fd = env.worker_socks[i];
+		rc = pthread_create(&dispatcher_threads[i], NULL, dispatch_thread, &data[i]);
+		if (rc < 0) {
+			perror("Failed to launch dispatcher thread");
+			exit(EXIT_ERR_SETUP_INFRA);
+		}
+	}
+
+	/* wait for all dispatcher to finish */
+	for (i = 0; i < env.workers; i++) {
+		while (true) {
+			int ret = pthread_tryjoin_np(dispatcher_threads[i], NULL);
+
+			if (!ret) {
+				break;
+			} else if (ret == EBUSY) {
+				if (env.debug)
+					fprintf(stderr, "Still waiting for thread %d (test %d).\n",
+						i,  env.worker_current_test[i] + 1);
+				usleep(1000 * 1000);
+				continue;
+			} else {
+				fprintf(stderr, "Unexpected error joining dispatcher thread: %d", ret);
+				break;
+			}
+		}
+	}
+	free(dispatcher_threads);
+	free(env.worker_current_test);
+	free(data);
+
+	/* generate summary */
+	fflush(stderr);
+	fflush(stdout);
+
+	for (i = 0; i < prog_test_cnt; i++) {
+		struct prog_test_def *current_test;
+		struct test_result *result;
+
+		current_test = &prog_test_defs[i];
+		result = &test_results[i];
+
+		if (!current_test->tested)
+			continue;
+
+		env.succ_cnt += result->error_cnt ? 0 : 1;
+		env.skip_cnt += result->skip_cnt;
+		if (result->error_cnt)
+			env.fail_cnt++;
+		env.sub_succ_cnt += result->sub_succ_cnt;
+	}
+
+	fprintf(stdout, "Summary: %d/%d PASSED, %d SKIPPED, %d FAILED\n",
+		env.succ_cnt, env.sub_succ_cnt, env.skip_cnt, env.fail_cnt);
+
+	print_all_error_logs();
+
+	/* reap all workers */
+	for (i = 0; i < env.workers; i++) {
+		int wstatus, pid;
+
+		pid = waitpid(env.worker_pids[i], &wstatus, 0);
+		if (pid != env.worker_pids[i])
+			perror("Unable to reap worker");
+	}
+
+	return 0;
+}
+
+static int worker_main(int sock)
+{
+	save_netns();
+
+	while (true) {
+		/* receive command */
+		struct msg msg;
+
+		if (recv_message(sock, &msg) < 0)
+			goto out;
+
+		switch (msg.type) {
+		case MSG_EXIT:
+			if (env.debug)
+				fprintf(stderr, "[%d]: worker exit.\n",
+					env.worker_id);
+			goto out;
+		case MSG_DO_TEST: {
+			int test_to_run;
+			struct prog_test_def *test;
+			struct msg msg_done;
+
+			test_to_run = msg.do_test.test_num;
+			test = &prog_test_defs[test_to_run];
+
+			if (env.debug)
+				fprintf(stderr, "[%d]: #%d:%s running.\n",
+					env.worker_id,
+					test_to_run + 1,
+					test->test_name);
+
+			stdio_hijack();
+
+			run_one_test(test_to_run);
+
+			stdio_restore();
+
+			memset(&msg_done, 0, sizeof(msg_done));
+			msg_done.type = MSG_TEST_DONE;
+			msg_done.test_done.test_num = test_to_run;
+			msg_done.test_done.error_cnt = test->error_cnt;
+			msg_done.test_done.skip_cnt = test->skip_cnt;
+			msg_done.test_done.sub_succ_cnt = test->sub_succ_cnt;
+			msg_done.test_done.have_log = false;
+
+			if (env.verbosity > VERBOSE_NONE || test->force_log || test->error_cnt) {
+				if (env.log_cnt)
+					msg_done.test_done.have_log = true;
+			}
+			if (send_message(sock, &msg_done) < 0) {
+				perror("Fail to send message done");
+				goto out;
+			}
+
+			/* send logs */
+			if (msg_done.test_done.have_log) {
+				char *src;
+				size_t slen;
+
+				src = env.log_buf;
+				slen = env.log_cnt;
+				while (slen) {
+					struct msg msg_log;
+					char *dest;
+					size_t len;
+
+					memset(&msg_log, 0, sizeof(msg_log));
+					msg_log.type = MSG_TEST_LOG;
+					dest = msg_log.test_log.log_buf;
+					len = slen >= MAX_LOG_TRUNK_SIZE ? MAX_LOG_TRUNK_SIZE : slen;
+					memcpy(dest, src, len);
+
+					src += len;
+					slen -= len;
+					if (!slen)
+						msg_log.test_log.is_last = true;
+
+					assert(send_message(sock, &msg_log) >= 0);
+				}
+			}
+			if (env.log_buf) {
+				free(env.log_buf);
+				env.log_buf = NULL;
+				env.log_cnt = 0;
+			}
+			if (env.debug)
+				fprintf(stderr, "[%d]: #%d:%s done.\n",
+					env.worker_id,
+					test_to_run + 1,
+					test->test_name);
+			break;
+		} /* case MSG_DO_TEST */
+		default:
+			if (env.debug)
+				fprintf(stderr, "[%d]: unknown message.\n",  env.worker_id);
+			return -1;
+		}
+	}
+out:
+	return 0;
+}
+
 int main(int argc, char **argv)
 {
 	static const struct argp argp = {
@@ -809,7 +1286,7 @@ int main(int argc, char **argv)
 	struct sigaction sigact = {
 		.sa_handler = crash_handler,
 		.sa_flags = SA_RESETHAND,
-	};
+		};
 	int err, i;
 
 	sigaction(SIGSEGV, &sigact, NULL);
@@ -837,21 +1314,77 @@ int main(int argc, char **argv)
 		return -1;
 	}
 
-	save_netns();
-	stdio_hijack();
+	env.stdout = stdout;
+	env.stderr = stderr;
+
 	env.has_testmod = true;
 	if (!env.list_test_names && load_bpf_testmod()) {
 		fprintf(env.stderr, "WARNING! Selftests relying on bpf_testmod.ko will be skipped.\n");
 		env.has_testmod = false;
 	}
+
+	/* initializing tests */
 	for (i = 0; i < prog_test_cnt; i++) {
 		struct prog_test_def *test = &prog_test_defs[i];
 
-		env.test = test;
 		test->test_num = i + 1;
-
-		if (!should_run(&env.test_selector,
+		if (should_run(&env.test_selector,
 				test->test_num, test->test_name))
+			test->should_run = true;
+		else
+			test->should_run = false;
+	}
+
+	/* ignore workers if we are just listing */
+	if (env.get_test_cnt || env.list_test_names)
+		env.workers = 0;
+
+	/* launch workers if requested */
+	env.worker_id = -1; /* main process */
+	if (env.workers) {
+		env.worker_pids = calloc(sizeof(__pid_t), env.workers);
+		env.worker_socks = calloc(sizeof(int), env.workers);
+		if (env.debug)
+			fprintf(stdout, "Launching %d workers.\n", env.workers);
+		for (i = 0; i < env.workers; i++) {
+			int sv[2];
+			pid_t pid;
+
+			if (socketpair(AF_UNIX, SOCK_SEQPACKET | SOCK_CLOEXEC, 0, sv) < 0) {
+				perror("Fail to create worker socket");
+				return -1;
+			}
+			pid = fork();
+			if (pid < 0) {
+				perror("Failed to fork worker");
+				return -1;
+			} else if (pid != 0) { /* main process */
+				close(sv[1]);
+				env.worker_pids[i] = pid;
+				env.worker_socks[i] = sv[0];
+			} else { /* inside each worker process */
+				close(sv[0]);
+				env.worker_id = i;
+				return worker_main(sv[1]);
+			}
+		}
+
+		if (env.worker_id == -1) {
+			server_main();
+			goto out;
+		}
+	}
+
+	/* The rest of the main process */
+
+	/* on single mode */
+	save_netns();
+
+	for (i = 0; i < prog_test_cnt; i++) {
+		struct prog_test_def *test = &prog_test_defs[i];
+		struct test_result *result;
+
+		if (!test->should_run)
 			continue;
 
 		if (env.get_test_cnt) {
@@ -865,33 +1398,35 @@ int main(int argc, char **argv)
 			continue;
 		}
 
-		test->run_test();
-		/* ensure last sub-test is finalized properly */
-		if (test->subtest_name)
-			test__end_subtest();
+		stdio_hijack();
 
-		test->tested = true;
+		run_one_test(i);
 
-		dump_test_log(test, test->error_cnt);
+		stdio_restore();
 
 		fprintf(env.stdout, "#%d %s:%s\n",
 			test->test_num, test->test_name,
 			test->error_cnt ? "FAIL" : (test->skip_cnt ? "SKIP" : "OK"));
 
+		result = &test_results[i];
+		result->error_cnt = test->error_cnt;
+		if (env.log_buf) {
+			result->log_buf = strdup(env.log_buf);
+			result->log_cnt = env.log_cnt;
+
+			free(env.log_buf);
+			env.log_buf = NULL;
+			env.log_cnt = 0;
+		}
+
 		if (test->error_cnt)
 			env.fail_cnt++;
 		else
 			env.succ_cnt++;
-		skip_account();
 
-		reset_affinity();
-		restore_netns();
-		if (test->need_cgroup_cleanup)
-			cleanup_cgroup_environment();
+		skip_account();
+		env.sub_succ_cnt += test->sub_succ_cnt;
 	}
-	if (!env.list_test_names && env.has_testmod)
-		unload_bpf_testmod();
-	stdio_restore();
 
 	if (env.get_test_cnt) {
 		printf("%d\n", env.succ_cnt);
@@ -904,14 +1439,18 @@ int main(int argc, char **argv)
 	fprintf(stdout, "Summary: %d/%d PASSED, %d SKIPPED, %d FAILED\n",
 		env.succ_cnt, env.sub_succ_cnt, env.skip_cnt, env.fail_cnt);
 
+	print_all_error_logs();
+
+	close(env.saved_netns_fd);
 out:
+	if (!env.list_test_names && env.has_testmod)
+		unload_bpf_testmod();
 	free_str_set(&env.test_selector.blacklist);
 	free_str_set(&env.test_selector.whitelist);
 	free(env.test_selector.num_set);
 	free_str_set(&env.subtest_selector.blacklist);
 	free_str_set(&env.subtest_selector.whitelist);
 	free(env.subtest_selector.num_set);
-	close(env.saved_netns_fd);
 
 	if (env.succ_cnt + env.fail_cnt + env.skip_cnt == 0)
 		return EXIT_NO_TEST;
diff --git a/tools/testing/selftests/bpf/test_progs.h b/tools/testing/selftests/bpf/test_progs.h
index 9b8a1810b700..93c1ff705533 100644
--- a/tools/testing/selftests/bpf/test_progs.h
+++ b/tools/testing/selftests/bpf/test_progs.h
@@ -62,6 +62,7 @@ struct test_env {
 	struct test_selector test_selector;
 	struct test_selector subtest_selector;
 	bool verifier_stats;
+	bool debug;
 	enum verbosity verbosity;
 
 	bool jit_enabled;
@@ -69,7 +70,8 @@ struct test_env {
 	bool get_test_cnt;
 	bool list_test_names;
 
-	struct prog_test_def *test;
+	struct prog_test_def *test; /* current running tests */
+
 	FILE *stdout;
 	FILE *stderr;
 	char *log_buf;
@@ -82,6 +84,38 @@ struct test_env {
 	int skip_cnt; /* skipped tests */
 
 	int saved_netns_fd;
+	int workers; /* number of worker process */
+	int worker_id; /* id number of current worker, main process is -1 */
+	pid_t *worker_pids; /* array of worker pids */
+	int *worker_socks; /* array of worker socks */
+	int *worker_current_test; /* array of current running test for each worker */
+};
+
+#define MAX_LOG_TRUNK_SIZE 8192
+enum msg_type {
+	MSG_DO_TEST = 0,
+	MSG_TEST_DONE = 1,
+	MSG_TEST_LOG = 2,
+	MSG_EXIT = 255,
+};
+struct msg {
+	enum msg_type type;
+	union {
+		struct {
+			int test_num;
+		} do_test;
+		struct {
+			int test_num;
+			int sub_succ_cnt;
+			int error_cnt;
+			int skip_cnt;
+			bool have_log;
+		} test_done;
+		struct {
+			char log_buf[MAX_LOG_TRUNK_SIZE + 1];
+			bool is_last;
+		} test_log;
+	};
 };
 
 extern struct test_env env;
-- 
cgit v1.2.3


From 6587ff58cea4a7f252b8bbc4031a1bf4ec3781d8 Mon Sep 17 00:00:00 2001
From: Yucong Sun <sunyucong@gmail.com>
Date: Wed, 6 Oct 2021 11:56:07 -0700
Subject: selftests/bpf: Allow some tests to be executed in sequence

This patch allows tests to define serial_test_name() instead of
test_name(), and this will make test_progs execute those in sequence
after all other tests finished executing concurrently.

Signed-off-by: Yucong Sun <sunyucong@gmail.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20211006185619.364369-3-fallentree@fb.com
---
 tools/testing/selftests/bpf/test_progs.c | 60 ++++++++++++++++++++++++++++----
 1 file changed, 54 insertions(+), 6 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/test_progs.c b/tools/testing/selftests/bpf/test_progs.c
index 20dd1e2f8d06..1f4a48566991 100644
--- a/tools/testing/selftests/bpf/test_progs.c
+++ b/tools/testing/selftests/bpf/test_progs.c
@@ -50,6 +50,7 @@ struct prog_test_def {
 	const char *test_name;
 	int test_num;
 	void (*run_test)(void);
+	void (*run_serial_test)(void);
 	bool force_log;
 	int error_cnt;
 	int skip_cnt;
@@ -457,14 +458,17 @@ static int load_bpf_testmod(void)
 }
 
 /* extern declarations for test funcs */
-#define DEFINE_TEST(name) extern void test_##name(void);
+#define DEFINE_TEST(name)				\
+	extern void test_##name(void) __weak;		\
+	extern void serial_test_##name(void) __weak;
 #include <prog_tests/tests.h>
 #undef DEFINE_TEST
 
 static struct prog_test_def prog_test_defs[] = {
-#define DEFINE_TEST(name) {		\
-	.test_name = #name,		\
-	.run_test = &test_##name,	\
+#define DEFINE_TEST(name) {			\
+	.test_name = #name,			\
+	.run_test = &test_##name,		\
+	.run_serial_test = &serial_test_##name,	\
 },
 #include <prog_tests/tests.h>
 #undef DEFINE_TEST
@@ -907,7 +911,10 @@ static void run_one_test(int test_num)
 
 	env.test = test;
 
-	test->run_test();
+	if (test->run_test)
+		test->run_test();
+	else if (test->run_serial_test)
+		test->run_serial_test();
 
 	/* ensure last sub-test is finalized properly */
 	if (test->subtest_name)
@@ -957,7 +964,7 @@ static void *dispatch_thread(void *ctx)
 			pthread_mutex_unlock(&current_test_lock);
 		}
 
-		if (!test->should_run)
+		if (!test->should_run || test->run_serial_test)
 			continue;
 
 		/* run test through worker */
@@ -1136,6 +1143,40 @@ static int server_main(void)
 	free(env.worker_current_test);
 	free(data);
 
+	/* run serial tests */
+	save_netns();
+
+	for (int i = 0; i < prog_test_cnt; i++) {
+		struct prog_test_def *test = &prog_test_defs[i];
+		struct test_result *result = &test_results[i];
+
+		if (!test->should_run || !test->run_serial_test)
+			continue;
+
+		stdio_hijack();
+
+		run_one_test(i);
+
+		stdio_restore();
+		if (env.log_buf) {
+			result->log_cnt = env.log_cnt;
+			result->log_buf = strdup(env.log_buf);
+
+			free(env.log_buf);
+			env.log_buf = NULL;
+			env.log_cnt = 0;
+		}
+		restore_netns();
+
+		fprintf(stdout, "#%d %s:%s\n",
+			test->test_num, test->test_name,
+			test->error_cnt ? "FAIL" : (test->skip_cnt ? "SKIP" : "OK"));
+
+		result->error_cnt = test->error_cnt;
+		result->skip_cnt = test->skip_cnt;
+		result->sub_succ_cnt = test->sub_succ_cnt;
+	}
+
 	/* generate summary */
 	fflush(stderr);
 	fflush(stdout);
@@ -1333,6 +1374,13 @@ int main(int argc, char **argv)
 			test->should_run = true;
 		else
 			test->should_run = false;
+
+		if ((test->run_test == NULL && test->run_serial_test == NULL) ||
+		    (test->run_test != NULL && test->run_serial_test != NULL)) {
+			fprintf(stderr, "Test %d:%s must have either test_%s() or serial_test_%sl() defined.\n",
+				test->test_num, test->test_name, test->test_name, test->test_name);
+			exit(EXIT_ERR_SETUP_INFRA);
+		}
 	}
 
 	/* ignore workers if we are just listing */
-- 
cgit v1.2.3


From e87c3434f81ae566693cfdc22370dc938b2989dd Mon Sep 17 00:00:00 2001
From: Yucong Sun <sunyucong@gmail.com>
Date: Wed, 6 Oct 2021 11:56:09 -0700
Subject: selftests/bpf: Add per worker cgroup suffix

This patch make each worker use a unique cgroup base directory, thus
allowing tests that uses cgroups to run concurrently.

Signed-off-by: Yucong Sun <sunyucong@gmail.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20211006185619.364369-5-fallentree@fb.com
---
 tools/testing/selftests/bpf/cgroup_helpers.c | 6 +++---
 tools/testing/selftests/bpf/cgroup_helpers.h | 2 +-
 2 files changed, 4 insertions(+), 4 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/cgroup_helpers.c b/tools/testing/selftests/bpf/cgroup_helpers.c
index f3daa44a8266..8fcd44841bb2 100644
--- a/tools/testing/selftests/bpf/cgroup_helpers.c
+++ b/tools/testing/selftests/bpf/cgroup_helpers.c
@@ -11,6 +11,7 @@
 #include <fcntl.h>
 #include <unistd.h>
 #include <ftw.h>
+#include <unistd.h>
 
 #include "cgroup_helpers.h"
 
@@ -33,10 +34,9 @@
 #define CGROUP_MOUNT_DFLT		"/sys/fs/cgroup"
 #define NETCLS_MOUNT_PATH		CGROUP_MOUNT_DFLT "/net_cls"
 #define CGROUP_WORK_DIR			"/cgroup-test-work-dir"
-
 #define format_cgroup_path(buf, path) \
-	snprintf(buf, sizeof(buf), "%s%s%s", CGROUP_MOUNT_PATH, \
-		 CGROUP_WORK_DIR, path)
+	snprintf(buf, sizeof(buf), "%s%s%d%s", CGROUP_MOUNT_PATH, \
+	CGROUP_WORK_DIR, getpid(), path)
 
 #define format_classid_path(buf)				\
 	snprintf(buf, sizeof(buf), "%s%s", NETCLS_MOUNT_PATH,	\
diff --git a/tools/testing/selftests/bpf/cgroup_helpers.h b/tools/testing/selftests/bpf/cgroup_helpers.h
index 629da3854b3e..fcc9cb91b211 100644
--- a/tools/testing/selftests/bpf/cgroup_helpers.h
+++ b/tools/testing/selftests/bpf/cgroup_helpers.h
@@ -26,4 +26,4 @@ int join_classid(void);
 int setup_classid_environment(void);
 void cleanup_classid_environment(void);
 
-#endif /* __CGROUP_HELPERS_H */
+#endif /* __CGROUP_HELPERS_H */
\ No newline at end of file
-- 
cgit v1.2.3


From d719de0d2f3cbdb5890a147b90a51c5eaaef103e Mon Sep 17 00:00:00 2001
From: Yucong Sun <sunyucong@gmail.com>
Date: Wed, 6 Oct 2021 11:56:11 -0700
Subject: selftests/bpf: Fix race condition in enable_stats

In parallel execution mode, this test now need to use atomic operation
to avoid race condition.

Signed-off-by: Yucong Sun <sunyucong@gmail.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20211006185619.364369-7-fallentree@fb.com
---
 tools/testing/selftests/bpf/progs/test_enable_stats.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/progs/test_enable_stats.c b/tools/testing/selftests/bpf/progs/test_enable_stats.c
index 01a002ade529..1705097d01d7 100644
--- a/tools/testing/selftests/bpf/progs/test_enable_stats.c
+++ b/tools/testing/selftests/bpf/progs/test_enable_stats.c
@@ -13,6 +13,6 @@ __u64 count = 0;
 SEC("raw_tracepoint/sys_enter")
 int test_enable_stats(void *ctx)
 {
-	count += 1;
+	__sync_fetch_and_add(&count, 1);
 	return 0;
 }
-- 
cgit v1.2.3


From 445e72c782a1f770440e229afeb0c4e386da943c Mon Sep 17 00:00:00 2001
From: Yucong Sun <sunyucong@gmail.com>
Date: Wed, 6 Oct 2021 11:56:12 -0700
Subject: selftests/bpf: Make cgroup_v1v2 use its own port

This patch change cgroup_v1v2 use a different port, avoid conflict with
other tests.

Signed-off-by: Yucong Sun <sunyucong@gmail.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20211006185619.364369-8-fallentree@fb.com
---
 tools/testing/selftests/bpf/prog_tests/cgroup_v1v2.c | 2 +-
 tools/testing/selftests/bpf/progs/connect4_dropper.c | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/prog_tests/cgroup_v1v2.c b/tools/testing/selftests/bpf/prog_tests/cgroup_v1v2.c
index ab3b9bc5e6d1..9026b42914d3 100644
--- a/tools/testing/selftests/bpf/prog_tests/cgroup_v1v2.c
+++ b/tools/testing/selftests/bpf/prog_tests/cgroup_v1v2.c
@@ -46,7 +46,7 @@ void test_cgroup_v1v2(void)
 {
 	struct network_helper_opts opts = {};
 	int server_fd, client_fd, cgroup_fd;
-	static const int port = 60123;
+	static const int port = 60120;
 
 	/* Step 1: Check base connectivity works without any BPF. */
 	server_fd = start_server(AF_INET, SOCK_STREAM, NULL, port, 0);
diff --git a/tools/testing/selftests/bpf/progs/connect4_dropper.c b/tools/testing/selftests/bpf/progs/connect4_dropper.c
index b565d997810a..d3f4c5e4fb69 100644
--- a/tools/testing/selftests/bpf/progs/connect4_dropper.c
+++ b/tools/testing/selftests/bpf/progs/connect4_dropper.c
@@ -18,7 +18,7 @@ int connect_v4_dropper(struct bpf_sock_addr *ctx)
 {
 	if (ctx->type != SOCK_STREAM)
 		return VERDICT_PROCEED;
-	if (ctx->user_port == bpf_htons(60123))
+	if (ctx->user_port == bpf_htons(60120))
 		return VERDICT_REJECT;
 	return VERDICT_PROCEED;
 }
-- 
cgit v1.2.3


From 0f4feacc9155776fd2c7f1c7bcb41001d94990a0 Mon Sep 17 00:00:00 2001
From: Yucong Sun <sunyucong@gmail.com>
Date: Wed, 6 Oct 2021 11:56:15 -0700
Subject: selftests/bpf: Adding pid filtering for atomics test

This make atomics test able to run in parallel with other tests.

Signed-off-by: Yucong Sun <sunyucong@gmail.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20211006185619.364369-11-fallentree@fb.com
---
 tools/testing/selftests/bpf/prog_tests/atomics.c |  1 +
 tools/testing/selftests/bpf/progs/atomics.c      | 16 ++++++++++++++++
 2 files changed, 17 insertions(+)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/prog_tests/atomics.c b/tools/testing/selftests/bpf/prog_tests/atomics.c
index ba0e1efe5a45..1486be5d3209 100644
--- a/tools/testing/selftests/bpf/prog_tests/atomics.c
+++ b/tools/testing/selftests/bpf/prog_tests/atomics.c
@@ -225,6 +225,7 @@ void test_atomics(void)
 		test__skip();
 		goto cleanup;
 	}
+	skel->bss->pid = getpid();
 
 	if (test__start_subtest("add"))
 		test_add(skel);
diff --git a/tools/testing/selftests/bpf/progs/atomics.c b/tools/testing/selftests/bpf/progs/atomics.c
index c245345e41ca..16e57313204a 100644
--- a/tools/testing/selftests/bpf/progs/atomics.c
+++ b/tools/testing/selftests/bpf/progs/atomics.c
@@ -10,6 +10,8 @@ bool skip_tests __attribute((__section__(".data"))) = false;
 bool skip_tests = true;
 #endif
 
+__u32 pid = 0;
+
 __u64 add64_value = 1;
 __u64 add64_result = 0;
 __u32 add32_value = 1;
@@ -21,6 +23,8 @@ __u64 add_noreturn_value = 1;
 SEC("fentry/bpf_fentry_test1")
 int BPF_PROG(add, int a)
 {
+	if (pid != (bpf_get_current_pid_tgid() >> 32))
+		return 0;
 #ifdef ENABLE_ATOMICS_TESTS
 	__u64 add_stack_value = 1;
 
@@ -45,6 +49,8 @@ __s64 sub_noreturn_value = 1;
 SEC("fentry/bpf_fentry_test1")
 int BPF_PROG(sub, int a)
 {
+	if (pid != (bpf_get_current_pid_tgid() >> 32))
+		return 0;
 #ifdef ENABLE_ATOMICS_TESTS
 	__u64 sub_stack_value = 1;
 
@@ -67,6 +73,8 @@ __u64 and_noreturn_value = (0x110ull << 32);
 SEC("fentry/bpf_fentry_test1")
 int BPF_PROG(and, int a)
 {
+	if (pid != (bpf_get_current_pid_tgid() >> 32))
+		return 0;
 #ifdef ENABLE_ATOMICS_TESTS
 
 	and64_result = __sync_fetch_and_and(&and64_value, 0x011ull << 32);
@@ -86,6 +94,8 @@ __u64 or_noreturn_value = (0x110ull << 32);
 SEC("fentry/bpf_fentry_test1")
 int BPF_PROG(or, int a)
 {
+	if (pid != (bpf_get_current_pid_tgid() >> 32))
+		return 0;
 #ifdef ENABLE_ATOMICS_TESTS
 	or64_result = __sync_fetch_and_or(&or64_value, 0x011ull << 32);
 	or32_result = __sync_fetch_and_or(&or32_value, 0x011);
@@ -104,6 +114,8 @@ __u64 xor_noreturn_value = (0x110ull << 32);
 SEC("fentry/bpf_fentry_test1")
 int BPF_PROG(xor, int a)
 {
+	if (pid != (bpf_get_current_pid_tgid() >> 32))
+		return 0;
 #ifdef ENABLE_ATOMICS_TESTS
 	xor64_result = __sync_fetch_and_xor(&xor64_value, 0x011ull << 32);
 	xor32_result = __sync_fetch_and_xor(&xor32_value, 0x011);
@@ -123,6 +135,8 @@ __u32 cmpxchg32_result_succeed = 0;
 SEC("fentry/bpf_fentry_test1")
 int BPF_PROG(cmpxchg, int a)
 {
+	if (pid != (bpf_get_current_pid_tgid() >> 32))
+		return 0;
 #ifdef ENABLE_ATOMICS_TESTS
 	cmpxchg64_result_fail = __sync_val_compare_and_swap(&cmpxchg64_value, 0, 3);
 	cmpxchg64_result_succeed = __sync_val_compare_and_swap(&cmpxchg64_value, 1, 2);
@@ -142,6 +156,8 @@ __u32 xchg32_result = 0;
 SEC("fentry/bpf_fentry_test1")
 int BPF_PROG(xchg, int a)
 {
+	if (pid != (bpf_get_current_pid_tgid() >> 32))
+		return 0;
 #ifdef ENABLE_ATOMICS_TESTS
 	__u64 val64 = 2;
 	__u32 val32 = 2;
-- 
cgit v1.2.3


From 5db02dd7f09fdc32fa3866386784d383aca191d8 Mon Sep 17 00:00:00 2001
From: Yucong Sun <sunyucong@gmail.com>
Date: Wed, 6 Oct 2021 11:56:17 -0700
Subject: selftests/bpf: Fix pid check in fexit_sleep test

bpf_get_current_pid_tgid() returns u64, whose upper 32 bits are the same
as userspace getpid() return value.

Signed-off-by: Yucong Sun <sunyucong@gmail.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20211006185619.364369-13-fallentree@fb.com
---
 tools/testing/selftests/bpf/progs/fexit_sleep.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/progs/fexit_sleep.c b/tools/testing/selftests/bpf/progs/fexit_sleep.c
index 03a672d76353..bca92c9bd29a 100644
--- a/tools/testing/selftests/bpf/progs/fexit_sleep.c
+++ b/tools/testing/selftests/bpf/progs/fexit_sleep.c
@@ -13,7 +13,7 @@ int fexit_cnt = 0;
 SEC("fentry/__x64_sys_nanosleep")
 int BPF_PROG(nanosleep_fentry, const struct pt_regs *regs)
 {
-	if ((int)bpf_get_current_pid_tgid() != pid)
+	if (bpf_get_current_pid_tgid() >> 32 != pid)
 		return 0;
 
 	fentry_cnt++;
@@ -23,7 +23,7 @@ int BPF_PROG(nanosleep_fentry, const struct pt_regs *regs)
 SEC("fexit/__x64_sys_nanosleep")
 int BPF_PROG(nanosleep_fexit, const struct pt_regs *regs, int ret)
 {
-	if ((int)bpf_get_current_pid_tgid() != pid)
+	if (bpf_get_current_pid_tgid() >> 32 != pid)
 		return 0;
 
 	fexit_cnt++;
-- 
cgit v1.2.3


From d3f7b1664d3ebd69751327f45f5cd4adfb29f620 Mon Sep 17 00:00:00 2001
From: Yucong Sun <sunyucong@gmail.com>
Date: Wed, 6 Oct 2021 11:56:19 -0700
Subject: selfetest/bpf: Make some tests serial

Change tests that often fails in parallel execution mode to serial.

Signed-off-by: Yucong Sun <sunyucong@gmail.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20211006185619.364369-15-fallentree@fb.com
---
 tools/testing/selftests/bpf/prog_tests/bpf_iter_setsockopt.c       | 2 +-
 tools/testing/selftests/bpf/prog_tests/bpf_obj_id.c                | 2 +-
 tools/testing/selftests/bpf/prog_tests/cg_storage_multi.c          | 2 +-
 tools/testing/selftests/bpf/prog_tests/cgroup_attach_autodetach.c  | 2 +-
 tools/testing/selftests/bpf/prog_tests/cgroup_attach_multi.c       | 2 +-
 tools/testing/selftests/bpf/prog_tests/cgroup_attach_override.c    | 2 +-
 tools/testing/selftests/bpf/prog_tests/cgroup_link.c               | 2 +-
 tools/testing/selftests/bpf/prog_tests/check_mtu.c                 | 2 +-
 tools/testing/selftests/bpf/prog_tests/fexit_bpf2bpf.c             | 3 ++-
 tools/testing/selftests/bpf/prog_tests/flow_dissector_load_bytes.c | 2 +-
 tools/testing/selftests/bpf/prog_tests/flow_dissector_reattach.c   | 2 +-
 tools/testing/selftests/bpf/prog_tests/get_branch_snapshot.c       | 2 +-
 tools/testing/selftests/bpf/prog_tests/kfree_skb.c                 | 3 ++-
 tools/testing/selftests/bpf/prog_tests/migrate_reuseport.c         | 2 +-
 tools/testing/selftests/bpf/prog_tests/modify_return.c             | 3 ++-
 tools/testing/selftests/bpf/prog_tests/ns_current_pid_tgid.c       | 3 ++-
 tools/testing/selftests/bpf/prog_tests/perf_buffer.c               | 2 +-
 tools/testing/selftests/bpf/prog_tests/perf_link.c                 | 3 ++-
 tools/testing/selftests/bpf/prog_tests/probe_user.c                | 3 ++-
 tools/testing/selftests/bpf/prog_tests/raw_tp_writable_test_run.c  | 3 ++-
 tools/testing/selftests/bpf/prog_tests/select_reuseport.c          | 2 +-
 tools/testing/selftests/bpf/prog_tests/send_signal_sched_switch.c  | 3 ++-
 tools/testing/selftests/bpf/prog_tests/sk_storage_tracing.c        | 2 +-
 tools/testing/selftests/bpf/prog_tests/snprintf_btf.c              | 2 +-
 tools/testing/selftests/bpf/prog_tests/sock_fields.c               | 2 +-
 tools/testing/selftests/bpf/prog_tests/sockmap_listen.c            | 2 +-
 tools/testing/selftests/bpf/prog_tests/timer.c                     | 3 ++-
 tools/testing/selftests/bpf/prog_tests/timer_mim.c                 | 2 +-
 tools/testing/selftests/bpf/prog_tests/tp_attach_query.c           | 2 +-
 tools/testing/selftests/bpf/prog_tests/trace_printk.c              | 2 +-
 tools/testing/selftests/bpf/prog_tests/trace_vprintk.c             | 2 +-
 tools/testing/selftests/bpf/prog_tests/trampoline_count.c          | 3 ++-
 tools/testing/selftests/bpf/prog_tests/xdp_attach.c                | 2 +-
 tools/testing/selftests/bpf/prog_tests/xdp_bonding.c               | 2 +-
 tools/testing/selftests/bpf/prog_tests/xdp_cpumap_attach.c         | 2 +-
 tools/testing/selftests/bpf/prog_tests/xdp_devmap_attach.c         | 2 +-
 tools/testing/selftests/bpf/prog_tests/xdp_info.c                  | 2 +-
 tools/testing/selftests/bpf/prog_tests/xdp_link.c                  | 2 +-
 38 files changed, 48 insertions(+), 38 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_iter_setsockopt.c b/tools/testing/selftests/bpf/prog_tests/bpf_iter_setsockopt.c
index 85babb0487b3..b52ff8ce34db 100644
--- a/tools/testing/selftests/bpf/prog_tests/bpf_iter_setsockopt.c
+++ b/tools/testing/selftests/bpf/prog_tests/bpf_iter_setsockopt.c
@@ -179,7 +179,7 @@ done:
 	free_fds(est_fds, nr_est);
 }
 
-void test_bpf_iter_setsockopt(void)
+void serial_test_bpf_iter_setsockopt(void)
 {
 	struct bpf_iter_setsockopt *iter_skel = NULL;
 	struct bpf_cubic *cubic_skel = NULL;
diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_obj_id.c b/tools/testing/selftests/bpf/prog_tests/bpf_obj_id.c
index 284d5921c345..eb8eeebe6935 100644
--- a/tools/testing/selftests/bpf/prog_tests/bpf_obj_id.c
+++ b/tools/testing/selftests/bpf/prog_tests/bpf_obj_id.c
@@ -3,7 +3,7 @@
 
 #define nr_iters 2
 
-void test_bpf_obj_id(void)
+void serial_test_bpf_obj_id(void)
 {
 	const __u64 array_magic_value = 0xfaceb00c;
 	const __u32 array_key = 0;
diff --git a/tools/testing/selftests/bpf/prog_tests/cg_storage_multi.c b/tools/testing/selftests/bpf/prog_tests/cg_storage_multi.c
index 876be0ecb654..621c57222191 100644
--- a/tools/testing/selftests/bpf/prog_tests/cg_storage_multi.c
+++ b/tools/testing/selftests/bpf/prog_tests/cg_storage_multi.c
@@ -363,7 +363,7 @@ close_bpf_object:
 	cg_storage_multi_shared__destroy(obj);
 }
 
-void test_cg_storage_multi(void)
+void serial_test_cg_storage_multi(void)
 {
 	int parent_cgroup_fd = -1, child_cgroup_fd = -1;
 
diff --git a/tools/testing/selftests/bpf/prog_tests/cgroup_attach_autodetach.c b/tools/testing/selftests/bpf/prog_tests/cgroup_attach_autodetach.c
index 70e94e783070..5de485c7370f 100644
--- a/tools/testing/selftests/bpf/prog_tests/cgroup_attach_autodetach.c
+++ b/tools/testing/selftests/bpf/prog_tests/cgroup_attach_autodetach.c
@@ -21,7 +21,7 @@ static int prog_load(void)
 			       bpf_log_buf, BPF_LOG_BUF_SIZE);
 }
 
-void test_cgroup_attach_autodetach(void)
+void serial_test_cgroup_attach_autodetach(void)
 {
 	__u32 duration = 0, prog_cnt = 4, attach_flags;
 	int allow_prog[2] = {-1};
diff --git a/tools/testing/selftests/bpf/prog_tests/cgroup_attach_multi.c b/tools/testing/selftests/bpf/prog_tests/cgroup_attach_multi.c
index 20bb8831dda6..731bea84d8ed 100644
--- a/tools/testing/selftests/bpf/prog_tests/cgroup_attach_multi.c
+++ b/tools/testing/selftests/bpf/prog_tests/cgroup_attach_multi.c
@@ -74,7 +74,7 @@ static int prog_load_cnt(int verdict, int val)
 	return ret;
 }
 
-void test_cgroup_attach_multi(void)
+void serial_test_cgroup_attach_multi(void)
 {
 	__u32 prog_ids[4], prog_cnt = 0, attach_flags, saved_prog_id;
 	int cg1 = 0, cg2 = 0, cg3 = 0, cg4 = 0, cg5 = 0, key = 0;
diff --git a/tools/testing/selftests/bpf/prog_tests/cgroup_attach_override.c b/tools/testing/selftests/bpf/prog_tests/cgroup_attach_override.c
index 9e96f8d87fea..10d3c33821a7 100644
--- a/tools/testing/selftests/bpf/prog_tests/cgroup_attach_override.c
+++ b/tools/testing/selftests/bpf/prog_tests/cgroup_attach_override.c
@@ -23,7 +23,7 @@ static int prog_load(int verdict)
 			       bpf_log_buf, BPF_LOG_BUF_SIZE);
 }
 
-void test_cgroup_attach_override(void)
+void serial_test_cgroup_attach_override(void)
 {
 	int drop_prog = -1, allow_prog = -1, foo = -1, bar = -1;
 	__u32 duration = 0;
diff --git a/tools/testing/selftests/bpf/prog_tests/cgroup_link.c b/tools/testing/selftests/bpf/prog_tests/cgroup_link.c
index 9091524131d6..9e6e6aad347c 100644
--- a/tools/testing/selftests/bpf/prog_tests/cgroup_link.c
+++ b/tools/testing/selftests/bpf/prog_tests/cgroup_link.c
@@ -24,7 +24,7 @@ int ping_and_check(int exp_calls, int exp_alt_calls)
 	return 0;
 }
 
-void test_cgroup_link(void)
+void serial_test_cgroup_link(void)
 {
 	struct {
 		const char *path;
diff --git a/tools/testing/selftests/bpf/prog_tests/check_mtu.c b/tools/testing/selftests/bpf/prog_tests/check_mtu.c
index 012068f33a0a..f73e6e36b74d 100644
--- a/tools/testing/selftests/bpf/prog_tests/check_mtu.c
+++ b/tools/testing/selftests/bpf/prog_tests/check_mtu.c
@@ -195,7 +195,7 @@ cleanup:
 	test_check_mtu__destroy(skel);
 }
 
-void test_check_mtu(void)
+void serial_test_check_mtu(void)
 {
 	__u32 mtu_lo;
 
diff --git a/tools/testing/selftests/bpf/prog_tests/fexit_bpf2bpf.c b/tools/testing/selftests/bpf/prog_tests/fexit_bpf2bpf.c
index 2839f4270a26..9cff14a23bb7 100644
--- a/tools/testing/selftests/bpf/prog_tests/fexit_bpf2bpf.c
+++ b/tools/testing/selftests/bpf/prog_tests/fexit_bpf2bpf.c
@@ -380,7 +380,8 @@ static void test_func_map_prog_compatibility(void)
 				     "./test_attach_probe.o");
 }
 
-void test_fexit_bpf2bpf(void)
+/* NOTE: affect other tests, must run in serial mode */
+void serial_test_fexit_bpf2bpf(void)
 {
 	if (test__start_subtest("target_no_callees"))
 		test_target_no_callees();
diff --git a/tools/testing/selftests/bpf/prog_tests/flow_dissector_load_bytes.c b/tools/testing/selftests/bpf/prog_tests/flow_dissector_load_bytes.c
index 0e8a4d2f023d..6093728497c7 100644
--- a/tools/testing/selftests/bpf/prog_tests/flow_dissector_load_bytes.c
+++ b/tools/testing/selftests/bpf/prog_tests/flow_dissector_load_bytes.c
@@ -2,7 +2,7 @@
 #include <test_progs.h>
 #include <network_helpers.h>
 
-void test_flow_dissector_load_bytes(void)
+void serial_test_flow_dissector_load_bytes(void)
 {
 	struct bpf_flow_keys flow_keys;
 	__u32 duration = 0, retval, size;
diff --git a/tools/testing/selftests/bpf/prog_tests/flow_dissector_reattach.c b/tools/testing/selftests/bpf/prog_tests/flow_dissector_reattach.c
index 3931ede5c534..f0c6c226aba8 100644
--- a/tools/testing/selftests/bpf/prog_tests/flow_dissector_reattach.c
+++ b/tools/testing/selftests/bpf/prog_tests/flow_dissector_reattach.c
@@ -628,7 +628,7 @@ out_close:
 	}
 }
 
-void test_flow_dissector_reattach(void)
+void serial_test_flow_dissector_reattach(void)
 {
 	int err, new_net, saved_net;
 
diff --git a/tools/testing/selftests/bpf/prog_tests/get_branch_snapshot.c b/tools/testing/selftests/bpf/prog_tests/get_branch_snapshot.c
index e4f92feb7b32..d6d70a359aeb 100644
--- a/tools/testing/selftests/bpf/prog_tests/get_branch_snapshot.c
+++ b/tools/testing/selftests/bpf/prog_tests/get_branch_snapshot.c
@@ -73,7 +73,7 @@ static void close_perf_events(void)
 	free(pfd_array);
 }
 
-void test_get_branch_snapshot(void)
+void serial_test_get_branch_snapshot(void)
 {
 	struct get_branch_snapshot *skel = NULL;
 	int err;
diff --git a/tools/testing/selftests/bpf/prog_tests/kfree_skb.c b/tools/testing/selftests/bpf/prog_tests/kfree_skb.c
index ddfb6bf97152..032a322d51f2 100644
--- a/tools/testing/selftests/bpf/prog_tests/kfree_skb.c
+++ b/tools/testing/selftests/bpf/prog_tests/kfree_skb.c
@@ -48,7 +48,8 @@ static void on_sample(void *ctx, int cpu, void *data, __u32 size)
 	*(bool *)ctx = true;
 }
 
-void test_kfree_skb(void)
+/* TODO: fix kernel panic caused by this test in parallel mode */
+void serial_test_kfree_skb(void)
 {
 	struct __sk_buff skb = {};
 	struct bpf_prog_test_run_attr tattr = {
diff --git a/tools/testing/selftests/bpf/prog_tests/migrate_reuseport.c b/tools/testing/selftests/bpf/prog_tests/migrate_reuseport.c
index 59adb4715394..7589c03fd26b 100644
--- a/tools/testing/selftests/bpf/prog_tests/migrate_reuseport.c
+++ b/tools/testing/selftests/bpf/prog_tests/migrate_reuseport.c
@@ -541,7 +541,7 @@ close_servers:
 	}
 }
 
-void test_migrate_reuseport(void)
+void serial_test_migrate_reuseport(void)
 {
 	struct test_migrate_reuseport *skel;
 	int i;
diff --git a/tools/testing/selftests/bpf/prog_tests/modify_return.c b/tools/testing/selftests/bpf/prog_tests/modify_return.c
index 97fec70c600b..b772fe30ce9b 100644
--- a/tools/testing/selftests/bpf/prog_tests/modify_return.c
+++ b/tools/testing/selftests/bpf/prog_tests/modify_return.c
@@ -53,7 +53,8 @@ cleanup:
 	modify_return__destroy(skel);
 }
 
-void test_modify_return(void)
+/* TODO: conflict with get_func_ip_test */
+void serial_test_modify_return(void)
 {
 	run_test(0 /* input_retval */,
 		 1 /* want_side_effect */,
diff --git a/tools/testing/selftests/bpf/prog_tests/ns_current_pid_tgid.c b/tools/testing/selftests/bpf/prog_tests/ns_current_pid_tgid.c
index 2535788e135f..24d493482ffc 100644
--- a/tools/testing/selftests/bpf/prog_tests/ns_current_pid_tgid.c
+++ b/tools/testing/selftests/bpf/prog_tests/ns_current_pid_tgid.c
@@ -78,7 +78,8 @@ static void test_ns_current_pid_tgid_new_ns(void)
 		return;
 }
 
-void test_ns_current_pid_tgid(void)
+/* TODO: use a different tracepoint */
+void serial_test_ns_current_pid_tgid(void)
 {
 	if (test__start_subtest("ns_current_pid_tgid_root_ns"))
 		test_current_pid_tgid(NULL);
diff --git a/tools/testing/selftests/bpf/prog_tests/perf_buffer.c b/tools/testing/selftests/bpf/prog_tests/perf_buffer.c
index 6490e9673002..6979aff4aab2 100644
--- a/tools/testing/selftests/bpf/prog_tests/perf_buffer.c
+++ b/tools/testing/selftests/bpf/prog_tests/perf_buffer.c
@@ -43,7 +43,7 @@ int trigger_on_cpu(int cpu)
 	return 0;
 }
 
-void test_perf_buffer(void)
+void serial_test_perf_buffer(void)
 {
 	int err, on_len, nr_on_cpus = 0, nr_cpus, i;
 	struct perf_buffer_opts pb_opts = {};
diff --git a/tools/testing/selftests/bpf/prog_tests/perf_link.c b/tools/testing/selftests/bpf/prog_tests/perf_link.c
index b1abd0c46607..ede07344f264 100644
--- a/tools/testing/selftests/bpf/prog_tests/perf_link.c
+++ b/tools/testing/selftests/bpf/prog_tests/perf_link.c
@@ -23,7 +23,8 @@ static void burn_cpu(void)
 		++j;
 }
 
-void test_perf_link(void)
+/* TODO: often fails in concurrent mode */
+void serial_test_perf_link(void)
 {
 	struct test_perf_link *skel = NULL;
 	struct perf_event_attr attr;
diff --git a/tools/testing/selftests/bpf/prog_tests/probe_user.c b/tools/testing/selftests/bpf/prog_tests/probe_user.c
index 52fe157e2a90..abf890d066eb 100644
--- a/tools/testing/selftests/bpf/prog_tests/probe_user.c
+++ b/tools/testing/selftests/bpf/prog_tests/probe_user.c
@@ -1,7 +1,8 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <test_progs.h>
 
-void test_probe_user(void)
+/* TODO: corrupts other tests uses connect() */
+void serial_test_probe_user(void)
 {
 	const char *prog_name = "handle_sys_connect";
 	const char *obj_file = "./test_probe_user.o";
diff --git a/tools/testing/selftests/bpf/prog_tests/raw_tp_writable_test_run.c b/tools/testing/selftests/bpf/prog_tests/raw_tp_writable_test_run.c
index 5c45424cac5f..ddefa1192e5d 100644
--- a/tools/testing/selftests/bpf/prog_tests/raw_tp_writable_test_run.c
+++ b/tools/testing/selftests/bpf/prog_tests/raw_tp_writable_test_run.c
@@ -3,7 +3,8 @@
 #include <test_progs.h>
 #include <linux/nbd.h>
 
-void test_raw_tp_writable_test_run(void)
+/* NOTE: conflict with other tests. */
+void serial_test_raw_tp_writable_test_run(void)
 {
 	__u32 duration = 0;
 	char error[4096];
diff --git a/tools/testing/selftests/bpf/prog_tests/select_reuseport.c b/tools/testing/selftests/bpf/prog_tests/select_reuseport.c
index d40e9156c48d..3cfc910ab3c1 100644
--- a/tools/testing/selftests/bpf/prog_tests/select_reuseport.c
+++ b/tools/testing/selftests/bpf/prog_tests/select_reuseport.c
@@ -858,7 +858,7 @@ out:
 	cleanup();
 }
 
-void test_select_reuseport(void)
+void serial_test_select_reuseport(void)
 {
 	saved_tcp_fo = read_int_sysctl(TCP_FO_SYSCTL);
 	if (saved_tcp_fo < 0)
diff --git a/tools/testing/selftests/bpf/prog_tests/send_signal_sched_switch.c b/tools/testing/selftests/bpf/prog_tests/send_signal_sched_switch.c
index 189a34a7addb..15dacfcfaa6d 100644
--- a/tools/testing/selftests/bpf/prog_tests/send_signal_sched_switch.c
+++ b/tools/testing/selftests/bpf/prog_tests/send_signal_sched_switch.c
@@ -25,7 +25,8 @@ static void *worker(void *p)
 	return NULL;
 }
 
-void test_send_signal_sched_switch(void)
+/* NOTE: cause events loss */
+void serial_test_send_signal_sched_switch(void)
 {
 	struct test_send_signal_kern *skel;
 	pthread_t threads[THREAD_COUNT];
diff --git a/tools/testing/selftests/bpf/prog_tests/sk_storage_tracing.c b/tools/testing/selftests/bpf/prog_tests/sk_storage_tracing.c
index 2b392590e8ca..547ae53cde74 100644
--- a/tools/testing/selftests/bpf/prog_tests/sk_storage_tracing.c
+++ b/tools/testing/selftests/bpf/prog_tests/sk_storage_tracing.c
@@ -105,7 +105,7 @@ out:
 		close(listen_fd);
 }
 
-void test_sk_storage_tracing(void)
+void serial_test_sk_storage_tracing(void)
 {
 	struct test_sk_storage_trace_itself *skel_itself;
 	int err;
diff --git a/tools/testing/selftests/bpf/prog_tests/snprintf_btf.c b/tools/testing/selftests/bpf/prog_tests/snprintf_btf.c
index 76e1f5fe18fa..dd41b826be30 100644
--- a/tools/testing/selftests/bpf/prog_tests/snprintf_btf.c
+++ b/tools/testing/selftests/bpf/prog_tests/snprintf_btf.c
@@ -6,7 +6,7 @@
 /* Demonstrate that bpf_snprintf_btf succeeds and that various data types
  * are formatted correctly.
  */
-void test_snprintf_btf(void)
+void serial_test_snprintf_btf(void)
 {
 	struct netif_receive_skb *skel;
 	struct netif_receive_skb__bss *bss;
diff --git a/tools/testing/selftests/bpf/prog_tests/sock_fields.c b/tools/testing/selftests/bpf/prog_tests/sock_fields.c
index 577d619fb07e..fae40db4d81f 100644
--- a/tools/testing/selftests/bpf/prog_tests/sock_fields.c
+++ b/tools/testing/selftests/bpf/prog_tests/sock_fields.c
@@ -329,7 +329,7 @@ done:
 		close(listen_fd);
 }
 
-void test_sock_fields(void)
+void serial_test_sock_fields(void)
 {
 	struct bpf_link *egress_link = NULL, *ingress_link = NULL;
 	int parent_cg_fd = -1, child_cg_fd = -1;
diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c b/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c
index 5c5979046523..102c73a00402 100644
--- a/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c
+++ b/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c
@@ -2037,7 +2037,7 @@ static void run_tests(struct test_sockmap_listen *skel, struct bpf_map *map,
 	test_udp_unix_redir(skel, map, family);
 }
 
-void test_sockmap_listen(void)
+void serial_test_sockmap_listen(void)
 {
 	struct test_sockmap_listen *skel;
 
diff --git a/tools/testing/selftests/bpf/prog_tests/timer.c b/tools/testing/selftests/bpf/prog_tests/timer.c
index 25f40e1b9967..0f4e49e622cd 100644
--- a/tools/testing/selftests/bpf/prog_tests/timer.c
+++ b/tools/testing/selftests/bpf/prog_tests/timer.c
@@ -39,7 +39,8 @@ static int timer(struct timer *timer_skel)
 	return 0;
 }
 
-void test_timer(void)
+/* TODO: use pid filtering */
+void serial_test_timer(void)
 {
 	struct timer *timer_skel = NULL;
 	int err;
diff --git a/tools/testing/selftests/bpf/prog_tests/timer_mim.c b/tools/testing/selftests/bpf/prog_tests/timer_mim.c
index ced8f6cf347c..949a0617869d 100644
--- a/tools/testing/selftests/bpf/prog_tests/timer_mim.c
+++ b/tools/testing/selftests/bpf/prog_tests/timer_mim.c
@@ -52,7 +52,7 @@ static int timer_mim(struct timer_mim *timer_skel)
 	return 0;
 }
 
-void test_timer_mim(void)
+void serial_test_timer_mim(void)
 {
 	struct timer_mim_reject *timer_reject_skel = NULL;
 	libbpf_print_fn_t old_print_fn = NULL;
diff --git a/tools/testing/selftests/bpf/prog_tests/tp_attach_query.c b/tools/testing/selftests/bpf/prog_tests/tp_attach_query.c
index fb095e5cd9af..8652d0a46c87 100644
--- a/tools/testing/selftests/bpf/prog_tests/tp_attach_query.c
+++ b/tools/testing/selftests/bpf/prog_tests/tp_attach_query.c
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <test_progs.h>
 
-void test_tp_attach_query(void)
+void serial_test_tp_attach_query(void)
 {
 	const int num_progs = 3;
 	int i, j, bytes, efd, err, prog_fd[num_progs], pmu_fd[num_progs];
diff --git a/tools/testing/selftests/bpf/prog_tests/trace_printk.c b/tools/testing/selftests/bpf/prog_tests/trace_printk.c
index e47835f0a674..3f7a7141265e 100644
--- a/tools/testing/selftests/bpf/prog_tests/trace_printk.c
+++ b/tools/testing/selftests/bpf/prog_tests/trace_printk.c
@@ -8,7 +8,7 @@
 #define TRACEBUF	"/sys/kernel/debug/tracing/trace_pipe"
 #define SEARCHMSG	"testing,testing"
 
-void test_trace_printk(void)
+void serial_test_trace_printk(void)
 {
 	int err = 0, iter = 0, found = 0;
 	struct trace_printk__bss *bss;
diff --git a/tools/testing/selftests/bpf/prog_tests/trace_vprintk.c b/tools/testing/selftests/bpf/prog_tests/trace_vprintk.c
index 61a24e62e1a0..46101270cb1a 100644
--- a/tools/testing/selftests/bpf/prog_tests/trace_vprintk.c
+++ b/tools/testing/selftests/bpf/prog_tests/trace_vprintk.c
@@ -8,7 +8,7 @@
 #define TRACEBUF	"/sys/kernel/debug/tracing/trace_pipe"
 #define SEARCHMSG	"1,2,3,4,5,6,7,8,9,10"
 
-void test_trace_vprintk(void)
+void serial_test_trace_vprintk(void)
 {
 	int err = 0, iter = 0, found = 0;
 	struct trace_vprintk__bss *bss;
diff --git a/tools/testing/selftests/bpf/prog_tests/trampoline_count.c b/tools/testing/selftests/bpf/prog_tests/trampoline_count.c
index d7f5a931d7f3..fc146671b20a 100644
--- a/tools/testing/selftests/bpf/prog_tests/trampoline_count.c
+++ b/tools/testing/selftests/bpf/prog_tests/trampoline_count.c
@@ -41,7 +41,8 @@ static struct bpf_link *load(struct bpf_object *obj, const char *name)
 	return bpf_program__attach_trace(prog);
 }
 
-void test_trampoline_count(void)
+/* TODO: use different target function to run in concurrent mode */
+void serial_test_trampoline_count(void)
 {
 	const char *fentry_name = "fentry/__set_task_comm";
 	const char *fexit_name = "fexit/__set_task_comm";
diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_attach.c b/tools/testing/selftests/bpf/prog_tests/xdp_attach.c
index 15ef3531483e..4c4057262cd8 100644
--- a/tools/testing/selftests/bpf/prog_tests/xdp_attach.c
+++ b/tools/testing/selftests/bpf/prog_tests/xdp_attach.c
@@ -4,7 +4,7 @@
 #define IFINDEX_LO 1
 #define XDP_FLAGS_REPLACE		(1U << 4)
 
-void test_xdp_attach(void)
+void serial_test_xdp_attach(void)
 {
 	__u32 duration = 0, id1, id2, id0 = 0, len;
 	struct bpf_object *obj1, *obj2, *obj3;
diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_bonding.c b/tools/testing/selftests/bpf/prog_tests/xdp_bonding.c
index ad3ba81b4048..faa22b84f2ee 100644
--- a/tools/testing/selftests/bpf/prog_tests/xdp_bonding.c
+++ b/tools/testing/selftests/bpf/prog_tests/xdp_bonding.c
@@ -519,7 +519,7 @@ static struct bond_test_case bond_test_cases[] = {
 	{ "xdp_bonding_xor_layer34", BOND_MODE_XOR, BOND_XMIT_POLICY_LAYER34, },
 };
 
-void test_xdp_bonding(void)
+void serial_test_xdp_bonding(void)
 {
 	libbpf_print_fn_t old_print_fn;
 	struct skeletons skeletons = {};
diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_cpumap_attach.c b/tools/testing/selftests/bpf/prog_tests/xdp_cpumap_attach.c
index 8755effd80b0..fd812bd43600 100644
--- a/tools/testing/selftests/bpf/prog_tests/xdp_cpumap_attach.c
+++ b/tools/testing/selftests/bpf/prog_tests/xdp_cpumap_attach.c
@@ -7,7 +7,7 @@
 
 #define IFINDEX_LO	1
 
-void test_xdp_cpumap_attach(void)
+void serial_test_xdp_cpumap_attach(void)
 {
 	struct test_xdp_with_cpumap_helpers *skel;
 	struct bpf_prog_info info = {};
diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_devmap_attach.c b/tools/testing/selftests/bpf/prog_tests/xdp_devmap_attach.c
index c72af030ff10..d4e9a9972a67 100644
--- a/tools/testing/selftests/bpf/prog_tests/xdp_devmap_attach.c
+++ b/tools/testing/selftests/bpf/prog_tests/xdp_devmap_attach.c
@@ -72,7 +72,7 @@ void test_neg_xdp_devmap_helpers(void)
 }
 
 
-void test_xdp_devmap_attach(void)
+void serial_test_xdp_devmap_attach(void)
 {
 	if (test__start_subtest("DEVMAP with programs in entries"))
 		test_xdp_with_devmap_helpers();
diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_info.c b/tools/testing/selftests/bpf/prog_tests/xdp_info.c
index d2d7a283d72f..4e2a4fd56f67 100644
--- a/tools/testing/selftests/bpf/prog_tests/xdp_info.c
+++ b/tools/testing/selftests/bpf/prog_tests/xdp_info.c
@@ -4,7 +4,7 @@
 
 #define IFINDEX_LO 1
 
-void test_xdp_info(void)
+void serial_test_xdp_info(void)
 {
 	__u32 len = sizeof(struct bpf_prog_info), duration = 0, prog_id;
 	const char *file = "./xdp_dummy.o";
diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_link.c b/tools/testing/selftests/bpf/prog_tests/xdp_link.c
index 46eed0a33c23..983ab0b47d30 100644
--- a/tools/testing/selftests/bpf/prog_tests/xdp_link.c
+++ b/tools/testing/selftests/bpf/prog_tests/xdp_link.c
@@ -6,7 +6,7 @@
 
 #define IFINDEX_LO 1
 
-void test_xdp_link(void)
+void serial_test_xdp_link(void)
 {
 	__u32 duration = 0, id1, id2, id0 = 0, prog_fd1, prog_fd2, err;
 	DECLARE_LIBBPF_OPTS(bpf_xdp_set_link_opts, opts, .old_fd = -1);
-- 
cgit v1.2.3


From e506342a03c777a8d56389ff2764617648562bcf Mon Sep 17 00:00:00 2001
From: Tianjia Zhang <tianjia.zhang@linux.alibaba.com>
Date: Fri, 8 Oct 2021 17:17:45 +0800
Subject: selftests/tls: add SM4 GCM/CCM to tls selftests

Add new cipher as a variant of standard tls selftests.

Signed-off-by: Tianjia Zhang <tianjia.zhang@linux.alibaba.com>
Link: https://lore.kernel.org/r/20211008091745.42917-1-tianjia.zhang@linux.alibaba.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/tls.c | 28 ++++++++++++++++++++++++++--
 1 file changed, 26 insertions(+), 2 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/net/tls.c b/tools/testing/selftests/net/tls.c
index 97fceb9be9ed..d3047e251fe9 100644
--- a/tools/testing/selftests/net/tls.c
+++ b/tools/testing/selftests/net/tls.c
@@ -29,6 +29,8 @@ struct tls_crypto_info_keys {
 	union {
 		struct tls12_crypto_info_aes_gcm_128 aes128;
 		struct tls12_crypto_info_chacha20_poly1305 chacha20;
+		struct tls12_crypto_info_sm4_gcm sm4gcm;
+		struct tls12_crypto_info_sm4_ccm sm4ccm;
 	};
 	size_t len;
 };
@@ -49,6 +51,16 @@ static void tls_crypto_info_init(uint16_t tls_version, uint16_t cipher_type,
 		tls12->aes128.info.version = tls_version;
 		tls12->aes128.info.cipher_type = cipher_type;
 		break;
+	case TLS_CIPHER_SM4_GCM:
+		tls12->len = sizeof(struct tls12_crypto_info_sm4_gcm);
+		tls12->sm4gcm.info.version = tls_version;
+		tls12->sm4gcm.info.cipher_type = cipher_type;
+		break;
+	case TLS_CIPHER_SM4_CCM:
+		tls12->len = sizeof(struct tls12_crypto_info_sm4_ccm);
+		tls12->sm4ccm.info.version = tls_version;
+		tls12->sm4ccm.info.cipher_type = cipher_type;
+		break;
 	default:
 		break;
 	}
@@ -148,13 +160,13 @@ FIXTURE_VARIANT(tls)
 	uint16_t cipher_type;
 };
 
-FIXTURE_VARIANT_ADD(tls, 12_gcm)
+FIXTURE_VARIANT_ADD(tls, 12_aes_gcm)
 {
 	.tls_version = TLS_1_2_VERSION,
 	.cipher_type = TLS_CIPHER_AES_GCM_128,
 };
 
-FIXTURE_VARIANT_ADD(tls, 13_gcm)
+FIXTURE_VARIANT_ADD(tls, 13_aes_gcm)
 {
 	.tls_version = TLS_1_3_VERSION,
 	.cipher_type = TLS_CIPHER_AES_GCM_128,
@@ -172,6 +184,18 @@ FIXTURE_VARIANT_ADD(tls, 13_chacha)
 	.cipher_type = TLS_CIPHER_CHACHA20_POLY1305,
 };
 
+FIXTURE_VARIANT_ADD(tls, 13_sm4_gcm)
+{
+	.tls_version = TLS_1_3_VERSION,
+	.cipher_type = TLS_CIPHER_SM4_GCM,
+};
+
+FIXTURE_VARIANT_ADD(tls, 13_sm4_ccm)
+{
+	.tls_version = TLS_1_3_VERSION,
+	.cipher_type = TLS_CIPHER_SM4_CCM,
+};
+
 FIXTURE_SETUP(tls)
 {
 	struct tls_crypto_info_keys tls12;
-- 
cgit v1.2.3


From 5319255b8df9271474bc9027cabf82253934f28d Mon Sep 17 00:00:00 2001
From: Ilya Leoshkevich <iii@linux.ibm.com>
Date: Thu, 7 Oct 2021 19:33:28 +0200
Subject: selftests/bpf: Skip verifier tests that fail to load with ENOTSUPP

The verifier tests added in commit c48e51c8b07a ("bpf: selftests: Add
selftests for module kfunc support") fail on s390, since the JIT does
not support calling kernel functions. This is most likely an issue for
all the other non-Intel arches, as well as on Intel with
!CONFIG_DEBUG_INFO_BTF or !CONFIG_BPF_JIT.

Trying to check for messages from all the possible add_kfunc_call()
failure cases in test_verifier looks pointless, so do a much simpler
thing instead: just like it's already done in do_prog_test_run(), skip
the tests that fail to load with ENOTSUPP.

Signed-off-by: Ilya Leoshkevich <iii@linux.ibm.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Acked-by: Song Liu <songliubraving@fb.com>
Link: https://lore.kernel.org/bpf/20211007173329.381754-1-iii@linux.ibm.com
---
 tools/testing/selftests/bpf/test_verifier.c | 12 +++++++++++-
 1 file changed, 11 insertions(+), 1 deletion(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c
index 3a9e332c5e36..25afe423b3f0 100644
--- a/tools/testing/selftests/bpf/test_verifier.c
+++ b/tools/testing/selftests/bpf/test_verifier.c
@@ -47,6 +47,10 @@
 #include "test_btf.h"
 #include "../../../include/linux/filter.h"
 
+#ifndef ENOTSUPP
+#define ENOTSUPP 524
+#endif
+
 #define MAX_INSNS	BPF_MAXINSNS
 #define MAX_TEST_INSNS	1000000
 #define MAX_FIXUPS	8
@@ -974,7 +978,7 @@ static int do_prog_test_run(int fd_prog, bool unpriv, uint32_t expected_val,
 
 	if (err) {
 		switch (saved_errno) {
-		case 524/*ENOTSUPP*/:
+		case ENOTSUPP:
 			printf("Did not run the program (not supported) ");
 			return 0;
 		case EPERM:
@@ -1119,6 +1123,12 @@ static void do_test_single(struct bpf_test *test, bool unpriv,
 		goto close_fds;
 	}
 
+	if (fd_prog < 0 && saved_errno == ENOTSUPP) {
+		printf("SKIP (program uses an unsupported feature)\n");
+		skips++;
+		goto close_fds;
+	}
+
 	alignment_prevented_execution = 0;
 
 	if (expected_ret == ACCEPT || expected_ret == VERBOSE_ACCEPT) {
-- 
cgit v1.2.3


From a703b5179b5c0740c69358b2cfb22c12545d13a4 Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@nvidia.com>
Date: Sun, 10 Oct 2021 14:40:17 +0300
Subject: selftests: mlxsw: sch_red_core: Drop two unused variables

These variables are cut'n'pasted from other functions in the file and not
actually used.

Signed-off-by: Petr Machata <petrm@nvidia.com>
Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/drivers/net/mlxsw/sch_red_core.sh | 2 --
 1 file changed, 2 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/drivers/net/mlxsw/sch_red_core.sh b/tools/testing/selftests/drivers/net/mlxsw/sch_red_core.sh
index 33ddd01689be..88053f8dfd12 100644
--- a/tools/testing/selftests/drivers/net/mlxsw/sch_red_core.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/sch_red_core.sh
@@ -551,10 +551,8 @@ do_drop_test()
 	local trigger=$1; shift
 	local subtest=$1; shift
 	local fetch_counter=$1; shift
-	local backlog
 	local base
 	local now
-	local pct
 
 	RET=0
 
-- 
cgit v1.2.3


From 0cd6fa99a076b79744d26bb2f4d089e1c4eae2e4 Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@nvidia.com>
Date: Sun, 10 Oct 2021 14:40:18 +0300
Subject: selftests: mlxsw: RED: Add selftests for the mark qevent

Add do_mark_test(), which is to do_ecn_test() like do_drop_test() is to
do_red_test(): meant to test that actions on the RED mark qevent block are
offloaded, and executed on ECN-marked packets.

The test splits install_qdisc() into its constituents, install_root_qdisc()
and install_qdisc_tcX(). This is in order to test that when mirroring is
enabled on one TC, the other TC does not mirror.

Signed-off-by: Petr Machata <petrm@nvidia.com>
Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../selftests/drivers/net/mlxsw/sch_red_core.sh    | 74 ++++++++++++++++++++++
 .../selftests/drivers/net/mlxsw/sch_red_ets.sh     | 53 ++++++++++++++--
 2 files changed, 122 insertions(+), 5 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/drivers/net/mlxsw/sch_red_core.sh b/tools/testing/selftests/drivers/net/mlxsw/sch_red_core.sh
index 88053f8dfd12..eea3e5ad3f38 100644
--- a/tools/testing/selftests/drivers/net/mlxsw/sch_red_core.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/sch_red_core.sh
@@ -544,6 +544,53 @@ do_mc_backlog_test()
 	log_test "TC $((vlan - 10)): Qdisc reports MC backlog"
 }
 
+do_mark_test()
+{
+	local vlan=$1; shift
+	local limit=$1; shift
+	local subtest=$1; shift
+	local fetch_counter=$1; shift
+	local should_fail=$1; shift
+	local base
+
+	RET=0
+
+	start_tcp_traffic $h1.$vlan $(ipaddr 1 $vlan) $(ipaddr 3 $vlan) \
+			  $h3_mac tos=0x01
+
+	# Create a bit of a backlog and observe no mirroring due to marks.
+	qevent_rule_install_$subtest
+
+	build_backlog $vlan $((2 * limit / 3)) tcp tos=0x01 >/dev/null
+
+	base=$($fetch_counter)
+	count=$(busywait 1100 until_counter_is ">= $((base + 1))" \
+		$fetch_counter)
+	check_fail $? "Spurious packets ($base -> $count) observed without buffer pressure"
+
+	# Above limit, everything should be mirrored, we should see lots of
+	# packets.
+	build_backlog $vlan $((3 * limit / 2)) tcp tos=0x01 >/dev/null
+	busywait_for_counter 1100 +10000 \
+		 $fetch_counter > /dev/null
+	check_err_fail "$should_fail" $? "ECN-marked packets $subtest'd"
+
+	# When the rule is uninstalled, there should be no mirroring.
+	qevent_rule_uninstall_$subtest
+	busywait_for_counter 1100 +10 \
+		 $fetch_counter > /dev/null
+	check_fail $? "Spurious packets observed after uninstall"
+
+	if ((should_fail)); then
+		log_test "TC $((vlan - 10)): marked packets not $subtest'd"
+	else
+		log_test "TC $((vlan - 10)): marked packets $subtest'd"
+	fi
+
+	stop_traffic
+	sleep 1
+}
+
 do_drop_test()
 {
 	local vlan=$1; shift
@@ -626,6 +673,22 @@ do_drop_mirror_test()
 	tc filter del dev $h2 ingress pref 1 handle 101 flower
 }
 
+do_mark_mirror_test()
+{
+	local vlan=$1; shift
+	local limit=$1; shift
+
+	tc filter add dev $h2 ingress pref 1 handle 101 prot ip \
+	   flower skip_sw ip_proto tcp \
+	   action drop
+
+	do_mark_test "$vlan" "$limit" mirror \
+		     qevent_counter_fetch_mirror \
+		     $(: should_fail=)0
+
+	tc filter del dev $h2 ingress pref 1 handle 101 flower
+}
+
 qevent_rule_install_trap()
 {
 	tc filter add block 10 pref 1234 handle 102 matchall skip_sw \
@@ -653,3 +716,14 @@ do_drop_trap_test()
 	do_drop_test "$vlan" "$limit" "$trap_name" trap \
 		     "qevent_counter_fetch_trap $trap_name"
 }
+
+qevent_rule_install_trap_fwd()
+{
+	tc filter add block 10 pref 1234 handle 102 matchall skip_sw \
+	   action trap_fwd hw_stats disabled
+}
+
+qevent_rule_uninstall_trap_fwd()
+{
+	tc filter del block 10 pref 1234 handle 102 matchall
+}
diff --git a/tools/testing/selftests/drivers/net/mlxsw/sch_red_ets.sh b/tools/testing/selftests/drivers/net/mlxsw/sch_red_ets.sh
index f3ef3274f9b3..b58b4cf9dc13 100755
--- a/tools/testing/selftests/drivers/net/mlxsw/sch_red_ets.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/sch_red_ets.sh
@@ -9,6 +9,7 @@ ALL_TESTS="
 	mc_backlog_test
 	red_mirror_test
 	red_trap_test
+	ecn_mirror_test
 "
 : ${QDISC:=ets}
 source sch_red_core.sh
@@ -21,28 +22,60 @@ source sch_red_core.sh
 BACKLOG1=200000
 BACKLOG2=500000
 
-install_qdisc()
+install_root_qdisc()
 {
-	local -a args=("$@")
-
 	tc qdisc add dev $swp3 root handle 10: $QDISC \
 	   bands 8 priomap 7 6 5 4 3 2 1 0
+}
+
+install_qdisc_tc0()
+{
+	local -a args=("$@")
+
 	tc qdisc add dev $swp3 parent 10:8 handle 108: red \
 	   limit 1000000 min $BACKLOG1 max $((BACKLOG1 + 1)) \
 	   probability 1.0 avpkt 8000 burst 38 "${args[@]}"
+}
+
+install_qdisc_tc1()
+{
+	local -a args=("$@")
+
 	tc qdisc add dev $swp3 parent 10:7 handle 107: red \
 	   limit 1000000 min $BACKLOG2 max $((BACKLOG2 + 1)) \
 	   probability 1.0 avpkt 8000 burst 63 "${args[@]}"
+}
+
+install_qdisc()
+{
+	install_root_qdisc
+	install_qdisc_tc0 "$@"
+	install_qdisc_tc1 "$@"
 	sleep 1
 }
 
-uninstall_qdisc()
+uninstall_qdisc_tc0()
 {
-	tc qdisc del dev $swp3 parent 10:7
 	tc qdisc del dev $swp3 parent 10:8
+}
+
+uninstall_qdisc_tc1()
+{
+	tc qdisc del dev $swp3 parent 10:7
+}
+
+uninstall_root_qdisc()
+{
 	tc qdisc del dev $swp3 root
 }
 
+uninstall_qdisc()
+{
+	uninstall_qdisc_tc0
+	uninstall_qdisc_tc1
+	uninstall_root_qdisc
+}
+
 ecn_test()
 {
 	install_qdisc ecn
@@ -112,6 +145,16 @@ red_trap_test()
 	uninstall_qdisc
 }
 
+ecn_mirror_test()
+{
+	install_qdisc ecn qevent mark block 10
+
+	do_mark_mirror_test 10 $BACKLOG1
+	do_mark_mirror_test 11 $BACKLOG2
+
+	uninstall_qdisc
+}
+
 trap cleanup EXIT
 
 setup_prepare
-- 
cgit v1.2.3


From bf862732945cbfebc8616ef6ca60a879f1445fe1 Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@nvidia.com>
Date: Wed, 13 Oct 2021 13:37:48 +0300
Subject: selftests: mlxsw: RED: Test per-TC ECN counters

Add a variant of ECN test that uses qdisc marked counter (supported on
Spectrum-3 and above) instead of the aggregate ethtool ecn_marked counter.

Signed-off-by: Petr Machata <petrm@nvidia.com>
Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../selftests/drivers/net/mlxsw/sch_red_core.sh    | 51 +++++++++++++++++-----
 .../selftests/drivers/net/mlxsw/sch_red_ets.sh     | 11 +++++
 .../selftests/drivers/net/mlxsw/sch_red_root.sh    |  8 ++++
 3 files changed, 60 insertions(+), 10 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/drivers/net/mlxsw/sch_red_core.sh b/tools/testing/selftests/drivers/net/mlxsw/sch_red_core.sh
index eea3e5ad3f38..dd90cd87d4f9 100644
--- a/tools/testing/selftests/drivers/net/mlxsw/sch_red_core.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/sch_red_core.sh
@@ -331,6 +331,14 @@ get_nmarked()
 	ethtool_stats_get $swp3 ecn_marked
 }
 
+get_qdisc_nmarked()
+{
+	local vlan=$1; shift
+
+	busywait_for_counter 1100 +1 \
+		qdisc_stats_get $swp3 $(get_qdisc_handle $vlan) .marked
+}
+
 get_qdisc_npackets()
 {
 	local vlan=$1; shift
@@ -384,14 +392,15 @@ build_backlog()
 
 check_marking()
 {
+	local get_nmarked=$1; shift
 	local vlan=$1; shift
 	local cond=$1; shift
 
 	local npackets_0=$(get_qdisc_npackets $vlan)
-	local nmarked_0=$(get_nmarked $vlan)
+	local nmarked_0=$($get_nmarked $vlan)
 	sleep 5
 	local npackets_1=$(get_qdisc_npackets $vlan)
-	local nmarked_1=$(get_nmarked $vlan)
+	local nmarked_1=$($get_nmarked $vlan)
 
 	local nmarked_d=$((nmarked_1 - nmarked_0))
 	local npackets_d=$((npackets_1 - npackets_0))
@@ -404,6 +413,7 @@ check_marking()
 ecn_test_common()
 {
 	local name=$1; shift
+	local get_nmarked=$1; shift
 	local vlan=$1; shift
 	local limit=$1; shift
 	local backlog
@@ -416,7 +426,7 @@ ecn_test_common()
 	RET=0
 	backlog=$(build_backlog $vlan $((2 * limit / 3)) udp)
 	check_err $? "Could not build the requested backlog"
-	pct=$(check_marking $vlan "== 0")
+	pct=$(check_marking "$get_nmarked" $vlan "== 0")
 	check_err $? "backlog $backlog / $limit Got $pct% marked packets, expected == 0."
 	log_test "TC $((vlan - 10)): $name backlog < limit"
 
@@ -426,22 +436,23 @@ ecn_test_common()
 	RET=0
 	backlog=$(build_backlog $vlan $((3 * limit / 2)) tcp tos=0x01)
 	check_err $? "Could not build the requested backlog"
-	pct=$(check_marking $vlan ">= 95")
+	pct=$(check_marking "$get_nmarked" $vlan ">= 95")
 	check_err $? "backlog $backlog / $limit Got $pct% marked packets, expected >= 95."
 	log_test "TC $((vlan - 10)): $name backlog > limit"
 }
 
-do_ecn_test()
+__do_ecn_test()
 {
+	local get_nmarked=$1; shift
 	local vlan=$1; shift
 	local limit=$1; shift
-	local name=ECN
+	local name=${1-ECN}; shift
 
 	start_tcp_traffic $h1.$vlan $(ipaddr 1 $vlan) $(ipaddr 3 $vlan) \
 			  $h3_mac tos=0x01
 	sleep 1
 
-	ecn_test_common "$name" $vlan $limit
+	ecn_test_common "$name" "$get_nmarked" $vlan $limit
 
 	# Up there we saw that UDP gets accepted when backlog is below the
 	# limit. Now that it is above, it should all get dropped, and backlog
@@ -455,6 +466,26 @@ do_ecn_test()
 	sleep 1
 }
 
+do_ecn_test()
+{
+	local vlan=$1; shift
+	local limit=$1; shift
+
+	__do_ecn_test get_nmarked "$vlan" "$limit"
+}
+
+do_ecn_test_perband()
+{
+	local vlan=$1; shift
+	local limit=$1; shift
+
+	# Per-band ECN counters are not supported on Spectrum-1 and Spectrum-2.
+	[[ "$DEVLINK_VIDDID" == "15b3:cb84" ||
+	   "$DEVLINK_VIDDID" == "15b3:cf6c" ]] && return
+
+	__do_ecn_test get_qdisc_nmarked "$vlan" "$limit" "per-band ECN"
+}
+
 do_ecn_nodrop_test()
 {
 	local vlan=$1; shift
@@ -465,7 +496,7 @@ do_ecn_nodrop_test()
 			  $h3_mac tos=0x01
 	sleep 1
 
-	ecn_test_common "$name" $vlan $limit
+	ecn_test_common "$name" get_nmarked $vlan $limit
 
 	# Up there we saw that UDP gets accepted when backlog is below the
 	# limit. Now that it is above, in nodrop mode, make sure it goes to
@@ -495,7 +526,7 @@ do_red_test()
 	RET=0
 	backlog=$(build_backlog $vlan $((2 * limit / 3)) tcp tos=0x01)
 	check_err $? "Could not build the requested backlog"
-	pct=$(check_marking $vlan "== 0")
+	pct=$(check_marking get_nmarked $vlan "== 0")
 	check_err $? "backlog $backlog / $limit Got $pct% marked packets, expected == 0."
 	log_test "TC $((vlan - 10)): RED backlog < limit"
 
@@ -503,7 +534,7 @@ do_red_test()
 	RET=0
 	backlog=$(build_backlog $vlan $((3 * limit / 2)) tcp tos=0x01)
 	check_fail $? "Traffic went into backlog instead of being early-dropped"
-	pct=$(check_marking $vlan "== 0")
+	pct=$(check_marking get_nmarked $vlan "== 0")
 	check_err $? "backlog $backlog / $limit Got $pct% marked packets, expected == 0."
 	local diff=$((limit - backlog))
 	pct=$((100 * diff / limit))
diff --git a/tools/testing/selftests/drivers/net/mlxsw/sch_red_ets.sh b/tools/testing/selftests/drivers/net/mlxsw/sch_red_ets.sh
index b58b4cf9dc13..1e5ad3209436 100755
--- a/tools/testing/selftests/drivers/net/mlxsw/sch_red_ets.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/sch_red_ets.sh
@@ -4,6 +4,7 @@
 ALL_TESTS="
 	ping_ipv4
 	ecn_test
+	ecn_test_perband
 	ecn_nodrop_test
 	red_test
 	mc_backlog_test
@@ -86,6 +87,16 @@ ecn_test()
 	uninstall_qdisc
 }
 
+ecn_test_perband()
+{
+	install_qdisc ecn
+
+	do_ecn_test_perband 10 $BACKLOG1
+	do_ecn_test_perband 11 $BACKLOG2
+
+	uninstall_qdisc
+}
+
 ecn_nodrop_test()
 {
 	install_qdisc ecn nodrop
diff --git a/tools/testing/selftests/drivers/net/mlxsw/sch_red_root.sh b/tools/testing/selftests/drivers/net/mlxsw/sch_red_root.sh
index ede9c38d3eff..d79a82f317d2 100755
--- a/tools/testing/selftests/drivers/net/mlxsw/sch_red_root.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/sch_red_root.sh
@@ -4,6 +4,7 @@
 ALL_TESTS="
 	ping_ipv4
 	ecn_test
+	ecn_test_perband
 	ecn_nodrop_test
 	red_test
 	mc_backlog_test
@@ -35,6 +36,13 @@ ecn_test()
 	uninstall_qdisc
 }
 
+ecn_test_perband()
+{
+	install_qdisc ecn
+	do_ecn_test_perband 10 $BACKLOG
+	uninstall_qdisc
+}
+
 ecn_nodrop_test()
 {
 	install_qdisc ecn nodrop
-- 
cgit v1.2.3


From 72bcbc46a5c385961b9c167db79ad1f38f04e6a7 Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Fri, 15 Oct 2021 16:05:51 -0700
Subject: mptcp: increase default max additional subflows to 2

The current default does not allowing additional subflows, mostly
as a safety restriction to avoid uncontrolled resource consumption
on busy servers.

Still the system admin and/or the application have to opt-in to
MPTCP explicitly. After that, they need to change (increase) the
default maximum number of additional subflows.

Let set that to reasonable default, and make end-users life easier.

Additionally we need to update some self-tests accordingly.

Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: Mat Martineau <mathew.j.martineau@linux.intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/mptcp/mptcp_join.sh | 5 ++++-
 tools/testing/selftests/net/mptcp/pm_netlink.sh | 6 +++---
 2 files changed, 7 insertions(+), 4 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh
index 255793c5ac4f..293d349e21fe 100755
--- a/tools/testing/selftests/net/mptcp/mptcp_join.sh
+++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh
@@ -945,12 +945,15 @@ subflows_tests()
 
 	# subflow limited by client
 	reset
+	ip netns exec $ns1 ./pm_nl_ctl limits 0 0
+	ip netns exec $ns2 ./pm_nl_ctl limits 0 0
 	ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow
 	run_tests $ns1 $ns2 10.0.1.1
 	chk_join_nr "single subflow, limited by client" 0 0 0
 
 	# subflow limited by server
 	reset
+	ip netns exec $ns1 ./pm_nl_ctl limits 0 0
 	ip netns exec $ns2 ./pm_nl_ctl limits 0 1
 	ip netns exec $ns2 ./pm_nl_ctl add 10.0.3.2 flags subflow
 	run_tests $ns1 $ns2 10.0.1.1
@@ -973,7 +976,7 @@ subflows_tests()
 	run_tests $ns1 $ns2 10.0.1.1
 	chk_join_nr "multiple subflows" 2 2 2
 
-	# multiple subflows limited by serverf
+	# multiple subflows limited by server
 	reset
 	ip netns exec $ns1 ./pm_nl_ctl limits 0 1
 	ip netns exec $ns2 ./pm_nl_ctl limits 0 2
diff --git a/tools/testing/selftests/net/mptcp/pm_netlink.sh b/tools/testing/selftests/net/mptcp/pm_netlink.sh
index 3c741abe034e..cbacf9f6538b 100755
--- a/tools/testing/selftests/net/mptcp/pm_netlink.sh
+++ b/tools/testing/selftests/net/mptcp/pm_netlink.sh
@@ -70,7 +70,7 @@ check()
 
 check "ip netns exec $ns1 ./pm_nl_ctl dump" "" "defaults addr list"
 check "ip netns exec $ns1 ./pm_nl_ctl limits" "accept 0
-subflows 0" "defaults limits"
+subflows 2" "defaults limits"
 
 ip netns exec $ns1 ./pm_nl_ctl add 10.0.1.1
 ip netns exec $ns1 ./pm_nl_ctl add 10.0.1.2 flags subflow dev lo
@@ -118,11 +118,11 @@ check "ip netns exec $ns1 ./pm_nl_ctl dump" "" "flush addrs"
 
 ip netns exec $ns1 ./pm_nl_ctl limits 9 1
 check "ip netns exec $ns1 ./pm_nl_ctl limits" "accept 0
-subflows 0" "rcv addrs above hard limit"
+subflows 2" "rcv addrs above hard limit"
 
 ip netns exec $ns1 ./pm_nl_ctl limits 1 9
 check "ip netns exec $ns1 ./pm_nl_ctl limits" "accept 0
-subflows 0" "subflows above hard limit"
+subflows 2" "subflows above hard limit"
 
 ip netns exec $ns1 ./pm_nl_ctl limits 8 8
 check "ip netns exec $ns1 ./pm_nl_ctl limits" "accept 8
-- 
cgit v1.2.3


From 223f903e9c832699f4e5f422281a60756c1c6cfe Mon Sep 17 00:00:00 2001
From: Yonghong Song <yhs@fb.com>
Date: Tue, 12 Oct 2021 09:48:38 -0700
Subject: bpf: Rename BTF_KIND_TAG to BTF_KIND_DECL_TAG

Patch set [1] introduced BTF_KIND_TAG to allow tagging
declarations for struct/union, struct/union field, var, func
and func arguments and these tags will be encoded into
dwarf. They are also encoded to btf by llvm for the bpf target.

After BTF_KIND_TAG is introduced, we intended to use it
for kernel __user attributes. But kernel __user is actually
a type attribute. Upstream and internal discussion showed
it is not a good idea to mix declaration attribute and
type attribute. So we proposed to introduce btf_type_tag
as a type attribute and existing btf_tag renamed to
btf_decl_tag ([2]).

This patch renamed BTF_KIND_TAG to BTF_KIND_DECL_TAG and some
other declarations with *_tag to *_decl_tag to make it clear
the tag is for declaration. In the future, BTF_KIND_TYPE_TAG
might be introduced per [3].

 [1] https://lore.kernel.org/bpf/20210914223004.244411-1-yhs@fb.com/
 [2] https://reviews.llvm.org/D111588
 [3] https://reviews.llvm.org/D111199

Fixes: b5ea834dde6b ("bpf: Support for new btf kind BTF_KIND_TAG")
Fixes: 5b84bd10363e ("libbpf: Add support for BTF_KIND_TAG")
Fixes: 5c07f2fec003 ("bpftool: Add support for BTF_KIND_TAG")
Signed-off-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20211012164838.3345699-1-yhs@fb.com
---
 tools/bpf/bpftool/btf.c                            |   6 +-
 tools/include/uapi/linux/btf.h                     |   8 +-
 tools/lib/bpf/btf.c                                |  36 ++---
 tools/lib/bpf/btf.h                                |  12 +-
 tools/lib/bpf/btf_dump.c                           |   6 +-
 tools/lib/bpf/libbpf.c                             |  24 ++--
 tools/lib/bpf/libbpf.map                           |   2 +-
 tools/lib/bpf/libbpf_internal.h                    |   4 +-
 tools/testing/selftests/bpf/README.rst             |   4 +-
 tools/testing/selftests/bpf/btf_helpers.c          |   8 +-
 tools/testing/selftests/bpf/prog_tests/btf.c       | 160 ++++++++++-----------
 tools/testing/selftests/bpf/prog_tests/btf_write.c |  30 ++--
 tools/testing/selftests/bpf/progs/tag.c            |   6 +-
 tools/testing/selftests/bpf/test_btf.h             |   4 +-
 14 files changed, 155 insertions(+), 155 deletions(-)

(limited to 'tools')

diff --git a/tools/bpf/bpftool/btf.c b/tools/bpf/bpftool/btf.c
index 49743ad96851..7b68d4f65fe6 100644
--- a/tools/bpf/bpftool/btf.c
+++ b/tools/bpf/bpftool/btf.c
@@ -37,7 +37,7 @@ static const char * const btf_kind_str[NR_BTF_KINDS] = {
 	[BTF_KIND_VAR]		= "VAR",
 	[BTF_KIND_DATASEC]	= "DATASEC",
 	[BTF_KIND_FLOAT]	= "FLOAT",
-	[BTF_KIND_TAG]		= "TAG",
+	[BTF_KIND_DECL_TAG]	= "DECL_TAG",
 };
 
 struct btf_attach_table {
@@ -348,8 +348,8 @@ static int dump_btf_type(const struct btf *btf, __u32 id,
 			printf(" size=%u", t->size);
 		break;
 	}
-	case BTF_KIND_TAG: {
-		const struct btf_tag *tag = (const void *)(t + 1);
+	case BTF_KIND_DECL_TAG: {
+		const struct btf_decl_tag *tag = (const void *)(t + 1);
 
 		if (json_output) {
 			jsonw_uint_field(w, "type_id", t->type);
diff --git a/tools/include/uapi/linux/btf.h b/tools/include/uapi/linux/btf.h
index 642b6ecb37d7..deb12f755f0f 100644
--- a/tools/include/uapi/linux/btf.h
+++ b/tools/include/uapi/linux/btf.h
@@ -43,7 +43,7 @@ struct btf_type {
 	 * "size" tells the size of the type it is describing.
 	 *
 	 * "type" is used by PTR, TYPEDEF, VOLATILE, CONST, RESTRICT,
-	 * FUNC, FUNC_PROTO, VAR and TAG.
+	 * FUNC, FUNC_PROTO, VAR and DECL_TAG.
 	 * "type" is a type_id referring to another type.
 	 */
 	union {
@@ -74,7 +74,7 @@ enum {
 	BTF_KIND_VAR		= 14,	/* Variable	*/
 	BTF_KIND_DATASEC	= 15,	/* Section	*/
 	BTF_KIND_FLOAT		= 16,	/* Floating point	*/
-	BTF_KIND_TAG		= 17,	/* Tag */
+	BTF_KIND_DECL_TAG	= 17,	/* Decl Tag */
 
 	NR_BTF_KINDS,
 	BTF_KIND_MAX		= NR_BTF_KINDS - 1,
@@ -174,14 +174,14 @@ struct btf_var_secinfo {
 	__u32	size;
 };
 
-/* BTF_KIND_TAG is followed by a single "struct btf_tag" to describe
+/* BTF_KIND_DECL_TAG is followed by a single "struct btf_decl_tag" to describe
  * additional information related to the tag applied location.
  * If component_idx == -1, the tag is applied to a struct, union,
  * variable or function. Otherwise, it is applied to a struct/union
  * member or a func argument, and component_idx indicates which member
  * or argument (0 ... vlen-1).
  */
-struct btf_tag {
+struct btf_decl_tag {
        __s32   component_idx;
 };
 
diff --git a/tools/lib/bpf/btf.c b/tools/lib/bpf/btf.c
index 60fbd1c6d466..1f6dea11f600 100644
--- a/tools/lib/bpf/btf.c
+++ b/tools/lib/bpf/btf.c
@@ -309,8 +309,8 @@ static int btf_type_size(const struct btf_type *t)
 		return base_size + sizeof(struct btf_var);
 	case BTF_KIND_DATASEC:
 		return base_size + vlen * sizeof(struct btf_var_secinfo);
-	case BTF_KIND_TAG:
-		return base_size + sizeof(struct btf_tag);
+	case BTF_KIND_DECL_TAG:
+		return base_size + sizeof(struct btf_decl_tag);
 	default:
 		pr_debug("Unsupported BTF_KIND:%u\n", btf_kind(t));
 		return -EINVAL;
@@ -383,8 +383,8 @@ static int btf_bswap_type_rest(struct btf_type *t)
 			v->size = bswap_32(v->size);
 		}
 		return 0;
-	case BTF_KIND_TAG:
-		btf_tag(t)->component_idx = bswap_32(btf_tag(t)->component_idx);
+	case BTF_KIND_DECL_TAG:
+		btf_decl_tag(t)->component_idx = bswap_32(btf_decl_tag(t)->component_idx);
 		return 0;
 	default:
 		pr_debug("Unsupported BTF_KIND:%u\n", btf_kind(t));
@@ -596,7 +596,7 @@ __s64 btf__resolve_size(const struct btf *btf, __u32 type_id)
 		case BTF_KIND_CONST:
 		case BTF_KIND_RESTRICT:
 		case BTF_KIND_VAR:
-		case BTF_KIND_TAG:
+		case BTF_KIND_DECL_TAG:
 			type_id = t->type;
 			break;
 		case BTF_KIND_ARRAY:
@@ -2569,7 +2569,7 @@ int btf__add_datasec_var_info(struct btf *btf, int var_type_id, __u32 offset, __
 }
 
 /*
- * Append new BTF_KIND_TAG type with:
+ * Append new BTF_KIND_DECL_TAG type with:
  *   - *value* - non-empty/non-NULL string;
  *   - *ref_type_id* - referenced type ID, it might not exist yet;
  *   - *component_idx* - -1 for tagging reference type, otherwise struct/union
@@ -2578,7 +2578,7 @@ int btf__add_datasec_var_info(struct btf *btf, int var_type_id, __u32 offset, __
  *   - >0, type ID of newly added BTF type;
  *   - <0, on error.
  */
-int btf__add_tag(struct btf *btf, const char *value, int ref_type_id,
+int btf__add_decl_tag(struct btf *btf, const char *value, int ref_type_id,
 		 int component_idx)
 {
 	struct btf_type *t;
@@ -2593,7 +2593,7 @@ int btf__add_tag(struct btf *btf, const char *value, int ref_type_id,
 	if (btf_ensure_modifiable(btf))
 		return libbpf_err(-ENOMEM);
 
-	sz = sizeof(struct btf_type) + sizeof(struct btf_tag);
+	sz = sizeof(struct btf_type) + sizeof(struct btf_decl_tag);
 	t = btf_add_type_mem(btf, sz);
 	if (!t)
 		return libbpf_err(-ENOMEM);
@@ -2603,9 +2603,9 @@ int btf__add_tag(struct btf *btf, const char *value, int ref_type_id,
 		return value_off;
 
 	t->name_off = value_off;
-	t->info = btf_type_info(BTF_KIND_TAG, 0, false);
+	t->info = btf_type_info(BTF_KIND_DECL_TAG, 0, false);
 	t->type = ref_type_id;
-	btf_tag(t)->component_idx = component_idx;
+	btf_decl_tag(t)->component_idx = component_idx;
 
 	return btf_commit_type(btf, sz);
 }
@@ -3427,7 +3427,7 @@ static bool btf_equal_common(struct btf_type *t1, struct btf_type *t2)
 }
 
 /* Calculate type signature hash of INT or TAG. */
-static long btf_hash_int_tag(struct btf_type *t)
+static long btf_hash_int_decl_tag(struct btf_type *t)
 {
 	__u32 info = *(__u32 *)(t + 1);
 	long h;
@@ -3705,8 +3705,8 @@ static int btf_dedup_prep(struct btf_dedup *d)
 			h = btf_hash_common(t);
 			break;
 		case BTF_KIND_INT:
-		case BTF_KIND_TAG:
-			h = btf_hash_int_tag(t);
+		case BTF_KIND_DECL_TAG:
+			h = btf_hash_int_decl_tag(t);
 			break;
 		case BTF_KIND_ENUM:
 			h = btf_hash_enum(t);
@@ -3761,11 +3761,11 @@ static int btf_dedup_prim_type(struct btf_dedup *d, __u32 type_id)
 	case BTF_KIND_FUNC_PROTO:
 	case BTF_KIND_VAR:
 	case BTF_KIND_DATASEC:
-	case BTF_KIND_TAG:
+	case BTF_KIND_DECL_TAG:
 		return 0;
 
 	case BTF_KIND_INT:
-		h = btf_hash_int_tag(t);
+		h = btf_hash_int_decl_tag(t);
 		for_each_dedup_cand(d, hash_entry, h) {
 			cand_id = (__u32)(long)hash_entry->value;
 			cand = btf_type_by_id(d->btf, cand_id);
@@ -4382,13 +4382,13 @@ static int btf_dedup_ref_type(struct btf_dedup *d, __u32 type_id)
 		}
 		break;
 
-	case BTF_KIND_TAG:
+	case BTF_KIND_DECL_TAG:
 		ref_type_id = btf_dedup_ref_type(d, t->type);
 		if (ref_type_id < 0)
 			return ref_type_id;
 		t->type = ref_type_id;
 
-		h = btf_hash_int_tag(t);
+		h = btf_hash_int_decl_tag(t);
 		for_each_dedup_cand(d, hash_entry, h) {
 			cand_id = (__u32)(long)hash_entry->value;
 			cand = btf_type_by_id(d->btf, cand_id);
@@ -4671,7 +4671,7 @@ int btf_type_visit_type_ids(struct btf_type *t, type_id_visit_fn visit, void *ct
 	case BTF_KIND_TYPEDEF:
 	case BTF_KIND_FUNC:
 	case BTF_KIND_VAR:
-	case BTF_KIND_TAG:
+	case BTF_KIND_DECL_TAG:
 		return visit(&t->type, ctx);
 
 	case BTF_KIND_ARRAY: {
diff --git a/tools/lib/bpf/btf.h b/tools/lib/bpf/btf.h
index 864eb51753a1..4011e206e6f7 100644
--- a/tools/lib/bpf/btf.h
+++ b/tools/lib/bpf/btf.h
@@ -236,7 +236,7 @@ LIBBPF_API int btf__add_datasec_var_info(struct btf *btf, int var_type_id,
 					 __u32 offset, __u32 byte_sz);
 
 /* tag construction API */
-LIBBPF_API int btf__add_tag(struct btf *btf, const char *value, int ref_type_id,
+LIBBPF_API int btf__add_decl_tag(struct btf *btf, const char *value, int ref_type_id,
 			    int component_idx);
 
 struct btf_dedup_opts {
@@ -426,9 +426,9 @@ static inline bool btf_is_float(const struct btf_type *t)
 	return btf_kind(t) == BTF_KIND_FLOAT;
 }
 
-static inline bool btf_is_tag(const struct btf_type *t)
+static inline bool btf_is_decl_tag(const struct btf_type *t)
 {
-	return btf_kind(t) == BTF_KIND_TAG;
+	return btf_kind(t) == BTF_KIND_DECL_TAG;
 }
 
 static inline __u8 btf_int_encoding(const struct btf_type *t)
@@ -499,10 +499,10 @@ btf_var_secinfos(const struct btf_type *t)
 	return (struct btf_var_secinfo *)(t + 1);
 }
 
-struct btf_tag;
-static inline struct btf_tag *btf_tag(const struct btf_type *t)
+struct btf_decl_tag;
+static inline struct btf_decl_tag *btf_decl_tag(const struct btf_type *t)
 {
-	return (struct btf_tag *)(t + 1);
+	return (struct btf_decl_tag *)(t + 1);
 }
 
 #ifdef __cplusplus
diff --git a/tools/lib/bpf/btf_dump.c b/tools/lib/bpf/btf_dump.c
index ad6df97295ae..5ef42f0abed1 100644
--- a/tools/lib/bpf/btf_dump.c
+++ b/tools/lib/bpf/btf_dump.c
@@ -316,7 +316,7 @@ static int btf_dump_mark_referenced(struct btf_dump *d)
 		case BTF_KIND_TYPEDEF:
 		case BTF_KIND_FUNC:
 		case BTF_KIND_VAR:
-		case BTF_KIND_TAG:
+		case BTF_KIND_DECL_TAG:
 			d->type_states[t->type].referenced = 1;
 			break;
 
@@ -584,7 +584,7 @@ static int btf_dump_order_type(struct btf_dump *d, __u32 id, bool through_ptr)
 	case BTF_KIND_FUNC:
 	case BTF_KIND_VAR:
 	case BTF_KIND_DATASEC:
-	case BTF_KIND_TAG:
+	case BTF_KIND_DECL_TAG:
 		d->type_states[id].order_state = ORDERED;
 		return 0;
 
@@ -2217,7 +2217,7 @@ static int btf_dump_dump_type_data(struct btf_dump *d,
 	case BTF_KIND_FWD:
 	case BTF_KIND_FUNC:
 	case BTF_KIND_FUNC_PROTO:
-	case BTF_KIND_TAG:
+	case BTF_KIND_DECL_TAG:
 		err = btf_dump_unsupported_data(d, t, id);
 		break;
 	case BTF_KIND_INT:
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index ae0889bebe32..63d738654ff6 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -195,8 +195,8 @@ enum kern_feature_id {
 	FEAT_BTF_FLOAT,
 	/* BPF perf link support */
 	FEAT_PERF_LINK,
-	/* BTF_KIND_TAG support */
-	FEAT_BTF_TAG,
+	/* BTF_KIND_DECL_TAG support */
+	FEAT_BTF_DECL_TAG,
 	__FEAT_CNT,
 };
 
@@ -2024,7 +2024,7 @@ static const char *__btf_kind_str(__u16 kind)
 	case BTF_KIND_VAR: return "var";
 	case BTF_KIND_DATASEC: return "datasec";
 	case BTF_KIND_FLOAT: return "float";
-	case BTF_KIND_TAG: return "tag";
+	case BTF_KIND_DECL_TAG: return "decl_tag";
 	default: return "unknown";
 	}
 }
@@ -2524,9 +2524,9 @@ static bool btf_needs_sanitization(struct bpf_object *obj)
 	bool has_datasec = kernel_supports(obj, FEAT_BTF_DATASEC);
 	bool has_float = kernel_supports(obj, FEAT_BTF_FLOAT);
 	bool has_func = kernel_supports(obj, FEAT_BTF_FUNC);
-	bool has_tag = kernel_supports(obj, FEAT_BTF_TAG);
+	bool has_decl_tag = kernel_supports(obj, FEAT_BTF_DECL_TAG);
 
-	return !has_func || !has_datasec || !has_func_global || !has_float || !has_tag;
+	return !has_func || !has_datasec || !has_func_global || !has_float || !has_decl_tag;
 }
 
 static void bpf_object__sanitize_btf(struct bpf_object *obj, struct btf *btf)
@@ -2535,15 +2535,15 @@ static void bpf_object__sanitize_btf(struct bpf_object *obj, struct btf *btf)
 	bool has_datasec = kernel_supports(obj, FEAT_BTF_DATASEC);
 	bool has_float = kernel_supports(obj, FEAT_BTF_FLOAT);
 	bool has_func = kernel_supports(obj, FEAT_BTF_FUNC);
-	bool has_tag = kernel_supports(obj, FEAT_BTF_TAG);
+	bool has_decl_tag = kernel_supports(obj, FEAT_BTF_DECL_TAG);
 	struct btf_type *t;
 	int i, j, vlen;
 
 	for (i = 1; i <= btf__get_nr_types(btf); i++) {
 		t = (struct btf_type *)btf__type_by_id(btf, i);
 
-		if ((!has_datasec && btf_is_var(t)) || (!has_tag && btf_is_tag(t))) {
-			/* replace VAR/TAG with INT */
+		if ((!has_datasec && btf_is_var(t)) || (!has_decl_tag && btf_is_decl_tag(t))) {
+			/* replace VAR/DECL_TAG with INT */
 			t->info = BTF_INFO_ENC(BTF_KIND_INT, 0, 0);
 			/*
 			 * using size = 1 is the safest choice, 4 will be too
@@ -4248,7 +4248,7 @@ static int probe_kern_btf_float(void)
 					     strs, sizeof(strs)));
 }
 
-static int probe_kern_btf_tag(void)
+static int probe_kern_btf_decl_tag(void)
 {
 	static const char strs[] = "\0tag";
 	__u32 types[] = {
@@ -4258,7 +4258,7 @@ static int probe_kern_btf_tag(void)
 		BTF_TYPE_ENC(1, BTF_INFO_ENC(BTF_KIND_VAR, 0, 0), 1),
 		BTF_VAR_STATIC,
 		/* attr */
-		BTF_TYPE_TAG_ENC(1, 2, -1),
+		BTF_TYPE_DECL_TAG_ENC(1, 2, -1),
 	};
 
 	return probe_fd(libbpf__load_raw_btf((char *)types, sizeof(types),
@@ -4481,8 +4481,8 @@ static struct kern_feature_desc {
 	[FEAT_PERF_LINK] = {
 		"BPF perf link support", probe_perf_link,
 	},
-	[FEAT_BTF_TAG] = {
-		"BTF_KIND_TAG support", probe_kern_btf_tag,
+	[FEAT_BTF_DECL_TAG] = {
+		"BTF_KIND_DECL_TAG support", probe_kern_btf_decl_tag,
 	},
 };
 
diff --git a/tools/lib/bpf/libbpf.map b/tools/lib/bpf/libbpf.map
index f270d25e4af3..e6fb1ba49369 100644
--- a/tools/lib/bpf/libbpf.map
+++ b/tools/lib/bpf/libbpf.map
@@ -394,5 +394,5 @@ LIBBPF_0.6.0 {
 		bpf_object__prev_map;
 		bpf_object__prev_program;
 		btf__add_btf;
-		btf__add_tag;
+		btf__add_decl_tag;
 } LIBBPF_0.5.0;
diff --git a/tools/lib/bpf/libbpf_internal.h b/tools/lib/bpf/libbpf_internal.h
index f7fd3944d46d..f6a5748dd318 100644
--- a/tools/lib/bpf/libbpf_internal.h
+++ b/tools/lib/bpf/libbpf_internal.h
@@ -69,8 +69,8 @@
 #define BTF_VAR_SECINFO_ENC(type, offset, size) (type), (offset), (size)
 #define BTF_TYPE_FLOAT_ENC(name, sz) \
 	BTF_TYPE_ENC(name, BTF_INFO_ENC(BTF_KIND_FLOAT, 0, 0), sz)
-#define BTF_TYPE_TAG_ENC(value, type, component_idx) \
-	BTF_TYPE_ENC(value, BTF_INFO_ENC(BTF_KIND_TAG, 0, 0), type), (component_idx)
+#define BTF_TYPE_DECL_TAG_ENC(value, type, component_idx) \
+	BTF_TYPE_ENC(value, BTF_INFO_ENC(BTF_KIND_DECL_TAG, 0, 0), type), (component_idx)
 
 #ifndef likely
 #define likely(x) __builtin_expect(!!(x), 1)
diff --git a/tools/testing/selftests/bpf/README.rst b/tools/testing/selftests/bpf/README.rst
index 554553acc6d9..5e287e445f75 100644
--- a/tools/testing/selftests/bpf/README.rst
+++ b/tools/testing/selftests/bpf/README.rst
@@ -204,7 +204,7 @@ __ https://reviews.llvm.org/D93563
 btf_tag test and Clang version
 ==============================
 
-The btf_tag selftest require LLVM support to recognize the btf_tag attribute.
+The btf_tag selftest require LLVM support to recognize the btf_decl_tag attribute.
 It was introduced in `Clang 14`__.
 
 Without it, the btf_tag selftest will be skipped and you will observe:
@@ -213,7 +213,7 @@ Without it, the btf_tag selftest will be skipped and you will observe:
 
   #<test_num> btf_tag:SKIP
 
-__ https://reviews.llvm.org/D106614
+__ https://reviews.llvm.org/D111588
 
 Clang dependencies for static linking tests
 ===========================================
diff --git a/tools/testing/selftests/bpf/btf_helpers.c b/tools/testing/selftests/bpf/btf_helpers.c
index ce103fb0ad1b..668cfa20bb1b 100644
--- a/tools/testing/selftests/bpf/btf_helpers.c
+++ b/tools/testing/selftests/bpf/btf_helpers.c
@@ -24,12 +24,12 @@ static const char * const btf_kind_str_mapping[] = {
 	[BTF_KIND_VAR]		= "VAR",
 	[BTF_KIND_DATASEC]	= "DATASEC",
 	[BTF_KIND_FLOAT]	= "FLOAT",
-	[BTF_KIND_TAG]		= "TAG",
+	[BTF_KIND_DECL_TAG]	= "DECL_TAG",
 };
 
 static const char *btf_kind_str(__u16 kind)
 {
-	if (kind > BTF_KIND_TAG)
+	if (kind > BTF_KIND_DECL_TAG)
 		return "UNKNOWN";
 	return btf_kind_str_mapping[kind];
 }
@@ -178,9 +178,9 @@ int fprintf_btf_type_raw(FILE *out, const struct btf *btf, __u32 id)
 	case BTF_KIND_FLOAT:
 		fprintf(out, " size=%u", t->size);
 		break;
-	case BTF_KIND_TAG:
+	case BTF_KIND_DECL_TAG:
 		fprintf(out, " type_id=%u component_idx=%d",
-			t->type, btf_tag(t)->component_idx);
+			t->type, btf_decl_tag(t)->component_idx);
 		break;
 	default:
 		break;
diff --git a/tools/testing/selftests/bpf/prog_tests/btf.c b/tools/testing/selftests/bpf/prog_tests/btf.c
index acd33d0cd5d9..fa67f25bbef5 100644
--- a/tools/testing/selftests/bpf/prog_tests/btf.c
+++ b/tools/testing/selftests/bpf/prog_tests/btf.c
@@ -3662,15 +3662,15 @@ static struct btf_raw_test raw_tests[] = {
 },
 
 {
-	.descr = "tag test #1, struct/member, well-formed",
+	.descr = "decl_tag test #1, struct/member, well-formed",
 	.raw_types = {
 		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),	/* [1] */
 		BTF_STRUCT_ENC(0, 2, 8),			/* [2] */
 		BTF_MEMBER_ENC(NAME_TBD, 1, 0),
 		BTF_MEMBER_ENC(NAME_TBD, 1, 32),
-		BTF_TAG_ENC(NAME_TBD, 2, -1),
-		BTF_TAG_ENC(NAME_TBD, 2, 0),
-		BTF_TAG_ENC(NAME_TBD, 2, 1),
+		BTF_DECL_TAG_ENC(NAME_TBD, 2, -1),
+		BTF_DECL_TAG_ENC(NAME_TBD, 2, 0),
+		BTF_DECL_TAG_ENC(NAME_TBD, 2, 1),
 		BTF_END_RAW,
 	},
 	BTF_STR_SEC("\0m1\0m2\0tag1\0tag2\0tag3"),
@@ -3683,15 +3683,15 @@ static struct btf_raw_test raw_tests[] = {
 	.max_entries = 1,
 },
 {
-	.descr = "tag test #2, union/member, well-formed",
+	.descr = "decl_tag test #2, union/member, well-formed",
 	.raw_types = {
 		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),	/* [1] */
 		BTF_UNION_ENC(NAME_TBD, 2, 4),			/* [2] */
 		BTF_MEMBER_ENC(NAME_TBD, 1, 0),
 		BTF_MEMBER_ENC(NAME_TBD, 1, 0),
-		BTF_TAG_ENC(NAME_TBD, 2, -1),
-		BTF_TAG_ENC(NAME_TBD, 2, 0),
-		BTF_TAG_ENC(NAME_TBD, 2, 1),
+		BTF_DECL_TAG_ENC(NAME_TBD, 2, -1),
+		BTF_DECL_TAG_ENC(NAME_TBD, 2, 0),
+		BTF_DECL_TAG_ENC(NAME_TBD, 2, 1),
 		BTF_END_RAW,
 	},
 	BTF_STR_SEC("\0t\0m1\0m2\0tag1\0tag2\0tag3"),
@@ -3704,13 +3704,13 @@ static struct btf_raw_test raw_tests[] = {
 	.max_entries = 1,
 },
 {
-	.descr = "tag test #3, variable, well-formed",
+	.descr = "decl_tag test #3, variable, well-formed",
 	.raw_types = {
 		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),	/* [1] */
 		BTF_VAR_ENC(NAME_TBD, 1, 0),			/* [2] */
 		BTF_VAR_ENC(NAME_TBD, 1, 1),			/* [3] */
-		BTF_TAG_ENC(NAME_TBD, 2, -1),
-		BTF_TAG_ENC(NAME_TBD, 3, -1),
+		BTF_DECL_TAG_ENC(NAME_TBD, 2, -1),
+		BTF_DECL_TAG_ENC(NAME_TBD, 3, -1),
 		BTF_END_RAW,
 	},
 	BTF_STR_SEC("\0local\0global\0tag1\0tag2"),
@@ -3723,16 +3723,16 @@ static struct btf_raw_test raw_tests[] = {
 	.max_entries = 1,
 },
 {
-	.descr = "tag test #4, func/parameter, well-formed",
+	.descr = "decl_tag test #4, func/parameter, well-formed",
 	.raw_types = {
 		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),	/* [1] */
 		BTF_FUNC_PROTO_ENC(0, 2),			/* [2] */
 			BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 1),
 			BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 1),
 		BTF_FUNC_ENC(NAME_TBD, 2),			/* [3] */
-		BTF_TAG_ENC(NAME_TBD, 3, -1),
-		BTF_TAG_ENC(NAME_TBD, 3, 0),
-		BTF_TAG_ENC(NAME_TBD, 3, 1),
+		BTF_DECL_TAG_ENC(NAME_TBD, 3, -1),
+		BTF_DECL_TAG_ENC(NAME_TBD, 3, 0),
+		BTF_DECL_TAG_ENC(NAME_TBD, 3, 1),
 		BTF_END_RAW,
 	},
 	BTF_STR_SEC("\0arg1\0arg2\0f\0tag1\0tag2\0tag3"),
@@ -3745,11 +3745,11 @@ static struct btf_raw_test raw_tests[] = {
 	.max_entries = 1,
 },
 {
-	.descr = "tag test #5, invalid value",
+	.descr = "decl_tag test #5, invalid value",
 	.raw_types = {
 		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),	/* [1] */
 		BTF_VAR_ENC(NAME_TBD, 1, 0),			/* [2] */
-		BTF_TAG_ENC(0, 2, -1),
+		BTF_DECL_TAG_ENC(0, 2, -1),
 		BTF_END_RAW,
 	},
 	BTF_STR_SEC("\0local\0tag"),
@@ -3764,10 +3764,10 @@ static struct btf_raw_test raw_tests[] = {
 	.err_str = "Invalid value",
 },
 {
-	.descr = "tag test #6, invalid target type",
+	.descr = "decl_tag test #6, invalid target type",
 	.raw_types = {
 		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),	/* [1] */
-		BTF_TAG_ENC(NAME_TBD, 1, -1),
+		BTF_DECL_TAG_ENC(NAME_TBD, 1, -1),
 		BTF_END_RAW,
 	},
 	BTF_STR_SEC("\0tag1"),
@@ -3782,11 +3782,11 @@ static struct btf_raw_test raw_tests[] = {
 	.err_str = "Invalid type",
 },
 {
-	.descr = "tag test #7, invalid vlen",
+	.descr = "decl_tag test #7, invalid vlen",
 	.raw_types = {
 		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),	/* [1] */
 		BTF_VAR_ENC(NAME_TBD, 1, 0),			/* [2] */
-		BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_TAG, 0, 1), 2), (0),
+		BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_DECL_TAG, 0, 1), 2), (0),
 		BTF_END_RAW,
 	},
 	BTF_STR_SEC("\0local\0tag1"),
@@ -3801,11 +3801,11 @@ static struct btf_raw_test raw_tests[] = {
 	.err_str = "vlen != 0",
 },
 {
-	.descr = "tag test #8, invalid kflag",
+	.descr = "decl_tag test #8, invalid kflag",
 	.raw_types = {
 		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),	/* [1] */
 		BTF_VAR_ENC(NAME_TBD, 1, 0),			/* [2] */
-		BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_TAG, 1, 0), 2), (-1),
+		BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_DECL_TAG, 1, 0), 2), (-1),
 		BTF_END_RAW,
 	},
 	BTF_STR_SEC("\0local\0tag1"),
@@ -3820,11 +3820,11 @@ static struct btf_raw_test raw_tests[] = {
 	.err_str = "Invalid btf_info kind_flag",
 },
 {
-	.descr = "tag test #9, var, invalid component_idx",
+	.descr = "decl_tag test #9, var, invalid component_idx",
 	.raw_types = {
 		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),	/* [1] */
 		BTF_VAR_ENC(NAME_TBD, 1, 0),			/* [2] */
-		BTF_TAG_ENC(NAME_TBD, 2, 0),
+		BTF_DECL_TAG_ENC(NAME_TBD, 2, 0),
 		BTF_END_RAW,
 	},
 	BTF_STR_SEC("\0local\0tag"),
@@ -3839,13 +3839,13 @@ static struct btf_raw_test raw_tests[] = {
 	.err_str = "Invalid component_idx",
 },
 {
-	.descr = "tag test #10, struct member, invalid component_idx",
+	.descr = "decl_tag test #10, struct member, invalid component_idx",
 	.raw_types = {
 		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),	/* [1] */
 		BTF_STRUCT_ENC(0, 2, 8),			/* [2] */
 		BTF_MEMBER_ENC(NAME_TBD, 1, 0),
 		BTF_MEMBER_ENC(NAME_TBD, 1, 32),
-		BTF_TAG_ENC(NAME_TBD, 2, 2),
+		BTF_DECL_TAG_ENC(NAME_TBD, 2, 2),
 		BTF_END_RAW,
 	},
 	BTF_STR_SEC("\0m1\0m2\0tag"),
@@ -3860,14 +3860,14 @@ static struct btf_raw_test raw_tests[] = {
 	.err_str = "Invalid component_idx",
 },
 {
-	.descr = "tag test #11, func parameter, invalid component_idx",
+	.descr = "decl_tag test #11, func parameter, invalid component_idx",
 	.raw_types = {
 		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),	/* [1] */
 		BTF_FUNC_PROTO_ENC(0, 2),			/* [2] */
 			BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 1),
 			BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 1),
 		BTF_FUNC_ENC(NAME_TBD, 2),			/* [3] */
-		BTF_TAG_ENC(NAME_TBD, 3, 2),
+		BTF_DECL_TAG_ENC(NAME_TBD, 3, 2),
 		BTF_END_RAW,
 	},
 	BTF_STR_SEC("\0arg1\0arg2\0f\0tag"),
@@ -3882,14 +3882,14 @@ static struct btf_raw_test raw_tests[] = {
 	.err_str = "Invalid component_idx",
 },
 {
-	.descr = "tag test #12, < -1 component_idx",
+	.descr = "decl_tag test #12, < -1 component_idx",
 	.raw_types = {
 		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),	/* [1] */
 		BTF_FUNC_PROTO_ENC(0, 2),			/* [2] */
 			BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 1),
 			BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 1),
 		BTF_FUNC_ENC(NAME_TBD, 2),			/* [3] */
-		BTF_TAG_ENC(NAME_TBD, 3, -2),
+		BTF_DECL_TAG_ENC(NAME_TBD, 3, -2),
 		BTF_END_RAW,
 	},
 	BTF_STR_SEC("\0arg1\0arg2\0f\0tag"),
@@ -6672,9 +6672,9 @@ const struct btf_dedup_test dedup_tests[] = {
 			/* const -> [1] int */
 			BTF_CONST_ENC(1),						/* [6] */
 			/* tag -> [3] struct s */
-			BTF_TAG_ENC(NAME_NTH(2), 3, -1),				/* [7] */
+			BTF_DECL_TAG_ENC(NAME_NTH(2), 3, -1),				/* [7] */
 			/* tag -> [3] struct s, member 1 */
-			BTF_TAG_ENC(NAME_NTH(2), 3, 1),					/* [8] */
+			BTF_DECL_TAG_ENC(NAME_NTH(2), 3, 1),				/* [8] */
 
 			/* full copy of the above */
 			BTF_TYPE_INT_ENC(NAME_NTH(1), BTF_INT_SIGNED, 0, 32, 4),	/* [9] */
@@ -6689,8 +6689,8 @@ const struct btf_dedup_test dedup_tests[] = {
 			BTF_PTR_ENC(14),						/* [13] */
 			BTF_CONST_ENC(9),						/* [14] */
 			BTF_TYPE_FLOAT_ENC(NAME_NTH(7), 4),				/* [15] */
-			BTF_TAG_ENC(NAME_NTH(2), 11, -1),				/* [16] */
-			BTF_TAG_ENC(NAME_NTH(2), 11, 1),				/* [17] */
+			BTF_DECL_TAG_ENC(NAME_NTH(2), 11, -1),				/* [16] */
+			BTF_DECL_TAG_ENC(NAME_NTH(2), 11, 1),				/* [17] */
 			BTF_END_RAW,
 		},
 		BTF_STR_SEC("\0int\0s\0next\0a\0b\0c\0float\0d"),
@@ -6714,8 +6714,8 @@ const struct btf_dedup_test dedup_tests[] = {
 			BTF_PTR_ENC(6),							/* [5] */
 			/* const -> [1] int */
 			BTF_CONST_ENC(1),						/* [6] */
-			BTF_TAG_ENC(NAME_NTH(2), 3, -1),				/* [7] */
-			BTF_TAG_ENC(NAME_NTH(2), 3, 1),					/* [8] */
+			BTF_DECL_TAG_ENC(NAME_NTH(2), 3, -1),				/* [7] */
+			BTF_DECL_TAG_ENC(NAME_NTH(2), 3, 1),				/* [8] */
 			BTF_TYPE_FLOAT_ENC(NAME_NTH(7), 4),				/* [9] */
 			BTF_END_RAW,
 		},
@@ -6841,8 +6841,8 @@ const struct btf_dedup_test dedup_tests[] = {
 				BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 8),
 			BTF_FUNC_ENC(NAME_TBD, 12),					/* [13] func */
 			BTF_TYPE_FLOAT_ENC(NAME_TBD, 2),				/* [14] float */
-			BTF_TAG_ENC(NAME_TBD, 13, -1),					/* [15] tag */
-			BTF_TAG_ENC(NAME_TBD, 13, 1),					/* [16] tag */
+			BTF_DECL_TAG_ENC(NAME_TBD, 13, -1),				/* [15] tag */
+			BTF_DECL_TAG_ENC(NAME_TBD, 13, 1),				/* [16] tag */
 			BTF_END_RAW,
 		},
 		BTF_STR_SEC("\0A\0B\0C\0D\0E\0F\0G\0H\0I\0J\0K\0L\0M\0N\0O\0P"),
@@ -6869,8 +6869,8 @@ const struct btf_dedup_test dedup_tests[] = {
 				BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 8),
 			BTF_FUNC_ENC(NAME_TBD, 12),					/* [13] func */
 			BTF_TYPE_FLOAT_ENC(NAME_TBD, 2),				/* [14] float */
-			BTF_TAG_ENC(NAME_TBD, 13, -1),					/* [15] tag */
-			BTF_TAG_ENC(NAME_TBD, 13, 1),					/* [16] tag */
+			BTF_DECL_TAG_ENC(NAME_TBD, 13, -1),				/* [15] tag */
+			BTF_DECL_TAG_ENC(NAME_TBD, 13, 1),				/* [16] tag */
 			BTF_END_RAW,
 		},
 		BTF_STR_SEC("\0A\0B\0C\0D\0E\0F\0G\0H\0I\0J\0K\0L\0M\0N\0O\0P"),
@@ -7036,14 +7036,14 @@ const struct btf_dedup_test dedup_tests[] = {
 				BTF_FUNC_PROTO_ARG_ENC(NAME_NTH(3), 1),
 			BTF_FUNC_ENC(NAME_NTH(4), 2),			/* [4] */
 			/* tag -> t */
-			BTF_TAG_ENC(NAME_NTH(5), 2, -1),		/* [5] */
-			BTF_TAG_ENC(NAME_NTH(5), 2, -1),		/* [6] */
+			BTF_DECL_TAG_ENC(NAME_NTH(5), 2, -1),		/* [5] */
+			BTF_DECL_TAG_ENC(NAME_NTH(5), 2, -1),		/* [6] */
 			/* tag -> func */
-			BTF_TAG_ENC(NAME_NTH(5), 4, -1),		/* [7] */
-			BTF_TAG_ENC(NAME_NTH(5), 4, -1),		/* [8] */
+			BTF_DECL_TAG_ENC(NAME_NTH(5), 4, -1),		/* [7] */
+			BTF_DECL_TAG_ENC(NAME_NTH(5), 4, -1),		/* [8] */
 			/* tag -> func arg a1 */
-			BTF_TAG_ENC(NAME_NTH(5), 4, 1),			/* [9] */
-			BTF_TAG_ENC(NAME_NTH(5), 4, 1),			/* [10] */
+			BTF_DECL_TAG_ENC(NAME_NTH(5), 4, 1),		/* [9] */
+			BTF_DECL_TAG_ENC(NAME_NTH(5), 4, 1),		/* [10] */
 			BTF_END_RAW,
 		},
 		BTF_STR_SEC("\0t\0a1\0a2\0f\0tag"),
@@ -7056,9 +7056,9 @@ const struct btf_dedup_test dedup_tests[] = {
 				BTF_FUNC_PROTO_ARG_ENC(NAME_NTH(2), 1),
 				BTF_FUNC_PROTO_ARG_ENC(NAME_NTH(3), 1),
 			BTF_FUNC_ENC(NAME_NTH(4), 2),			/* [4] */
-			BTF_TAG_ENC(NAME_NTH(5), 2, -1),		/* [5] */
-			BTF_TAG_ENC(NAME_NTH(5), 4, -1),		/* [6] */
-			BTF_TAG_ENC(NAME_NTH(5), 4, 1),			/* [7] */
+			BTF_DECL_TAG_ENC(NAME_NTH(5), 2, -1),		/* [5] */
+			BTF_DECL_TAG_ENC(NAME_NTH(5), 4, -1),		/* [6] */
+			BTF_DECL_TAG_ENC(NAME_NTH(5), 4, 1),		/* [7] */
 			BTF_END_RAW,
 		},
 		BTF_STR_SEC("\0t\0a1\0a2\0f\0tag"),
@@ -7084,17 +7084,17 @@ const struct btf_dedup_test dedup_tests[] = {
 				BTF_FUNC_PROTO_ARG_ENC(NAME_NTH(2), 1),
 			BTF_FUNC_ENC(NAME_NTH(3), 4),			/* [5] */
 			/* tag -> f: tag1, tag2 */
-			BTF_TAG_ENC(NAME_NTH(4), 3, -1),		/* [6] */
-			BTF_TAG_ENC(NAME_NTH(5), 3, -1),		/* [7] */
+			BTF_DECL_TAG_ENC(NAME_NTH(4), 3, -1),		/* [6] */
+			BTF_DECL_TAG_ENC(NAME_NTH(5), 3, -1),		/* [7] */
 			/* tag -> f/a2: tag1, tag2 */
-			BTF_TAG_ENC(NAME_NTH(4), 3, 1),			/* [8] */
-			BTF_TAG_ENC(NAME_NTH(5), 3, 1),			/* [9] */
+			BTF_DECL_TAG_ENC(NAME_NTH(4), 3, 1),		/* [8] */
+			BTF_DECL_TAG_ENC(NAME_NTH(5), 3, 1),		/* [9] */
 			/* tag -> f: tag1, tag3 */
-			BTF_TAG_ENC(NAME_NTH(4), 5, -1),		/* [10] */
-			BTF_TAG_ENC(NAME_NTH(6), 5, -1),		/* [11] */
+			BTF_DECL_TAG_ENC(NAME_NTH(4), 5, -1),		/* [10] */
+			BTF_DECL_TAG_ENC(NAME_NTH(6), 5, -1),		/* [11] */
 			/* tag -> f/a2: tag1, tag3 */
-			BTF_TAG_ENC(NAME_NTH(4), 5, 1),			/* [12] */
-			BTF_TAG_ENC(NAME_NTH(6), 5, 1),			/* [13] */
+			BTF_DECL_TAG_ENC(NAME_NTH(4), 5, 1),		/* [12] */
+			BTF_DECL_TAG_ENC(NAME_NTH(6), 5, 1),		/* [13] */
 			BTF_END_RAW,
 		},
 		BTF_STR_SEC("\0a1\0a2\0f\0tag1\0tag2\0tag3"),
@@ -7106,12 +7106,12 @@ const struct btf_dedup_test dedup_tests[] = {
 				BTF_FUNC_PROTO_ARG_ENC(NAME_NTH(1), 1),
 				BTF_FUNC_PROTO_ARG_ENC(NAME_NTH(2), 1),
 			BTF_FUNC_ENC(NAME_NTH(3), 2),			/* [3] */
-			BTF_TAG_ENC(NAME_NTH(4), 3, -1),		/* [4] */
-			BTF_TAG_ENC(NAME_NTH(5), 3, -1),		/* [5] */
-			BTF_TAG_ENC(NAME_NTH(6), 3, -1),		/* [6] */
-			BTF_TAG_ENC(NAME_NTH(4), 3, 1),			/* [7] */
-			BTF_TAG_ENC(NAME_NTH(5), 3, 1),			/* [8] */
-			BTF_TAG_ENC(NAME_NTH(6), 3, 1),			/* [9] */
+			BTF_DECL_TAG_ENC(NAME_NTH(4), 3, -1),		/* [4] */
+			BTF_DECL_TAG_ENC(NAME_NTH(5), 3, -1),		/* [5] */
+			BTF_DECL_TAG_ENC(NAME_NTH(6), 3, -1),		/* [6] */
+			BTF_DECL_TAG_ENC(NAME_NTH(4), 3, 1),		/* [7] */
+			BTF_DECL_TAG_ENC(NAME_NTH(5), 3, 1),		/* [8] */
+			BTF_DECL_TAG_ENC(NAME_NTH(6), 3, 1),		/* [9] */
 			BTF_END_RAW,
 		},
 		BTF_STR_SEC("\0a1\0a2\0f\0tag1\0tag2\0tag3"),
@@ -7133,17 +7133,17 @@ const struct btf_dedup_test dedup_tests[] = {
 				BTF_MEMBER_ENC(NAME_NTH(2), 1, 0),
 				BTF_MEMBER_ENC(NAME_NTH(3), 1, 32),
 			/* tag -> t: tag1, tag2 */
-			BTF_TAG_ENC(NAME_NTH(4), 2, -1),		/* [4] */
-			BTF_TAG_ENC(NAME_NTH(5), 2, -1),		/* [5] */
+			BTF_DECL_TAG_ENC(NAME_NTH(4), 2, -1),		/* [4] */
+			BTF_DECL_TAG_ENC(NAME_NTH(5), 2, -1),		/* [5] */
 			/* tag -> t/m2: tag1, tag2 */
-			BTF_TAG_ENC(NAME_NTH(4), 2, 1),			/* [6] */
-			BTF_TAG_ENC(NAME_NTH(5), 2, 1),			/* [7] */
+			BTF_DECL_TAG_ENC(NAME_NTH(4), 2, 1),		/* [6] */
+			BTF_DECL_TAG_ENC(NAME_NTH(5), 2, 1),		/* [7] */
 			/* tag -> t: tag1, tag3 */
-			BTF_TAG_ENC(NAME_NTH(4), 3, -1),		/* [8] */
-			BTF_TAG_ENC(NAME_NTH(6), 3, -1),		/* [9] */
+			BTF_DECL_TAG_ENC(NAME_NTH(4), 3, -1),		/* [8] */
+			BTF_DECL_TAG_ENC(NAME_NTH(6), 3, -1),		/* [9] */
 			/* tag -> t/m2: tag1, tag3 */
-			BTF_TAG_ENC(NAME_NTH(4), 3, 1),			/* [10] */
-			BTF_TAG_ENC(NAME_NTH(6), 3, 1),			/* [11] */
+			BTF_DECL_TAG_ENC(NAME_NTH(4), 3, 1),		/* [10] */
+			BTF_DECL_TAG_ENC(NAME_NTH(6), 3, 1),		/* [11] */
 			BTF_END_RAW,
 		},
 		BTF_STR_SEC("\0t\0m1\0m2\0tag1\0tag2\0tag3"),
@@ -7154,12 +7154,12 @@ const struct btf_dedup_test dedup_tests[] = {
 			BTF_STRUCT_ENC(NAME_NTH(1), 2, 8),		/* [2] */
 				BTF_MEMBER_ENC(NAME_NTH(2), 1, 0),
 				BTF_MEMBER_ENC(NAME_NTH(3), 1, 32),
-			BTF_TAG_ENC(NAME_NTH(4), 2, -1),		/* [3] */
-			BTF_TAG_ENC(NAME_NTH(5), 2, -1),		/* [4] */
-			BTF_TAG_ENC(NAME_NTH(6), 2, -1),		/* [5] */
-			BTF_TAG_ENC(NAME_NTH(4), 2, 1),			/* [6] */
-			BTF_TAG_ENC(NAME_NTH(5), 2, 1),			/* [7] */
-			BTF_TAG_ENC(NAME_NTH(6), 2, 1),			/* [8] */
+			BTF_DECL_TAG_ENC(NAME_NTH(4), 2, -1),		/* [3] */
+			BTF_DECL_TAG_ENC(NAME_NTH(5), 2, -1),		/* [4] */
+			BTF_DECL_TAG_ENC(NAME_NTH(6), 2, -1),		/* [5] */
+			BTF_DECL_TAG_ENC(NAME_NTH(4), 2, 1),		/* [6] */
+			BTF_DECL_TAG_ENC(NAME_NTH(5), 2, 1),		/* [7] */
+			BTF_DECL_TAG_ENC(NAME_NTH(6), 2, 1),		/* [8] */
 			BTF_END_RAW,
 		},
 		BTF_STR_SEC("\0t\0m1\0m2\0tag1\0tag2\0tag3"),
@@ -7202,8 +7202,8 @@ static int btf_type_size(const struct btf_type *t)
 		return base_size + sizeof(struct btf_var);
 	case BTF_KIND_DATASEC:
 		return base_size + vlen * sizeof(struct btf_var_secinfo);
-	case BTF_KIND_TAG:
-		return base_size + sizeof(struct btf_tag);
+	case BTF_KIND_DECL_TAG:
+		return base_size + sizeof(struct btf_decl_tag);
 	default:
 		fprintf(stderr, "Unsupported BTF_KIND:%u\n", kind);
 		return -EINVAL;
diff --git a/tools/testing/selftests/bpf/prog_tests/btf_write.c b/tools/testing/selftests/bpf/prog_tests/btf_write.c
index 886e0fc1efb1..b912eeb0b6b4 100644
--- a/tools/testing/selftests/bpf/prog_tests/btf_write.c
+++ b/tools/testing/selftests/bpf/prog_tests/btf_write.c
@@ -277,26 +277,26 @@ static void gen_btf(struct btf *btf)
 		     "[17] DATASEC 'datasec1' size=12 vlen=1\n"
 		     "\ttype_id=1 offset=4 size=8", "raw_dump");
 
-	/* TAG */
-	id = btf__add_tag(btf, "tag1", 16, -1);
+	/* DECL_TAG */
+	id = btf__add_decl_tag(btf, "tag1", 16, -1);
 	ASSERT_EQ(id, 18, "tag_id");
 	t = btf__type_by_id(btf, 18);
 	ASSERT_STREQ(btf__str_by_offset(btf, t->name_off), "tag1", "tag_value");
-	ASSERT_EQ(btf_kind(t), BTF_KIND_TAG, "tag_kind");
+	ASSERT_EQ(btf_kind(t), BTF_KIND_DECL_TAG, "tag_kind");
 	ASSERT_EQ(t->type, 16, "tag_type");
-	ASSERT_EQ(btf_tag(t)->component_idx, -1, "tag_component_idx");
+	ASSERT_EQ(btf_decl_tag(t)->component_idx, -1, "tag_component_idx");
 	ASSERT_STREQ(btf_type_raw_dump(btf, 18),
-		     "[18] TAG 'tag1' type_id=16 component_idx=-1", "raw_dump");
+		     "[18] DECL_TAG 'tag1' type_id=16 component_idx=-1", "raw_dump");
 
-	id = btf__add_tag(btf, "tag2", 14, 1);
+	id = btf__add_decl_tag(btf, "tag2", 14, 1);
 	ASSERT_EQ(id, 19, "tag_id");
 	t = btf__type_by_id(btf, 19);
 	ASSERT_STREQ(btf__str_by_offset(btf, t->name_off), "tag2", "tag_value");
-	ASSERT_EQ(btf_kind(t), BTF_KIND_TAG, "tag_kind");
+	ASSERT_EQ(btf_kind(t), BTF_KIND_DECL_TAG, "tag_kind");
 	ASSERT_EQ(t->type, 14, "tag_type");
-	ASSERT_EQ(btf_tag(t)->component_idx, 1, "tag_component_idx");
+	ASSERT_EQ(btf_decl_tag(t)->component_idx, 1, "tag_component_idx");
 	ASSERT_STREQ(btf_type_raw_dump(btf, 19),
-		     "[19] TAG 'tag2' type_id=14 component_idx=1", "raw_dump");
+		     "[19] DECL_TAG 'tag2' type_id=14 component_idx=1", "raw_dump");
 }
 
 static void test_btf_add()
@@ -336,8 +336,8 @@ static void test_btf_add()
 		"[16] VAR 'var1' type_id=1, linkage=global-alloc",
 		"[17] DATASEC 'datasec1' size=12 vlen=1\n"
 		"\ttype_id=1 offset=4 size=8",
-		"[18] TAG 'tag1' type_id=16 component_idx=-1",
-		"[19] TAG 'tag2' type_id=14 component_idx=1");
+		"[18] DECL_TAG 'tag1' type_id=16 component_idx=-1",
+		"[19] DECL_TAG 'tag2' type_id=14 component_idx=1");
 
 	btf__free(btf);
 }
@@ -389,8 +389,8 @@ static void test_btf_add_btf()
 		"[16] VAR 'var1' type_id=1, linkage=global-alloc",
 		"[17] DATASEC 'datasec1' size=12 vlen=1\n"
 		"\ttype_id=1 offset=4 size=8",
-		"[18] TAG 'tag1' type_id=16 component_idx=-1",
-		"[19] TAG 'tag2' type_id=14 component_idx=1",
+		"[18] DECL_TAG 'tag1' type_id=16 component_idx=-1",
+		"[19] DECL_TAG 'tag2' type_id=14 component_idx=1",
 
 		/* types appended from the second BTF */
 		"[20] INT 'int' size=4 bits_offset=0 nr_bits=32 encoding=SIGNED",
@@ -418,8 +418,8 @@ static void test_btf_add_btf()
 		"[35] VAR 'var1' type_id=20, linkage=global-alloc",
 		"[36] DATASEC 'datasec1' size=12 vlen=1\n"
 		"\ttype_id=20 offset=4 size=8",
-		"[37] TAG 'tag1' type_id=35 component_idx=-1",
-		"[38] TAG 'tag2' type_id=33 component_idx=1");
+		"[37] DECL_TAG 'tag1' type_id=35 component_idx=-1",
+		"[38] DECL_TAG 'tag2' type_id=33 component_idx=1");
 
 cleanup:
 	btf__free(btf1);
diff --git a/tools/testing/selftests/bpf/progs/tag.c b/tools/testing/selftests/bpf/progs/tag.c
index b46b1bfac7da..672d19e7b120 100644
--- a/tools/testing/selftests/bpf/progs/tag.c
+++ b/tools/testing/selftests/bpf/progs/tag.c
@@ -8,9 +8,9 @@
 #define __has_attribute(x) 0
 #endif
 
-#if __has_attribute(btf_tag)
-#define __tag1 __attribute__((btf_tag("tag1")))
-#define __tag2 __attribute__((btf_tag("tag2")))
+#if __has_attribute(btf_decl_tag)
+#define __tag1 __attribute__((btf_decl_tag("tag1")))
+#define __tag2 __attribute__((btf_decl_tag("tag2")))
 volatile const bool skip_tests __tag1 __tag2 = false;
 #else
 #define __tag1
diff --git a/tools/testing/selftests/bpf/test_btf.h b/tools/testing/selftests/bpf/test_btf.h
index 0619e06d745e..32c7a57867da 100644
--- a/tools/testing/selftests/bpf/test_btf.h
+++ b/tools/testing/selftests/bpf/test_btf.h
@@ -69,7 +69,7 @@
 #define BTF_TYPE_FLOAT_ENC(name, sz) \
 	BTF_TYPE_ENC(name, BTF_INFO_ENC(BTF_KIND_FLOAT, 0, 0), sz)
 
-#define BTF_TAG_ENC(value, type, component_idx)	\
-	BTF_TYPE_ENC(value, BTF_INFO_ENC(BTF_KIND_TAG, 0, 0), type), (component_idx)
+#define BTF_DECL_TAG_ENC(value, type, component_idx)	\
+	BTF_TYPE_ENC(value, BTF_INFO_ENC(BTF_KIND_DECL_TAG, 0, 0), type), (component_idx)
 
 #endif /* _TEST_BTF_H */
-- 
cgit v1.2.3


From 29c1eac2e64eda847d6ea51a00c2021198447ed9 Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@nvidia.com>
Date: Tue, 19 Oct 2021 11:07:12 +0300
Subject: selftests: mlxsw: Add a test for un/offloadable qdisc trees

This checks that various qdisc configurations either are or are not
offloaded.

Signed-off-by: Petr Machata <petrm@nvidia.com>
Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../selftests/drivers/net/mlxsw/sch_offload.sh     | 276 +++++++++++++++++++++
 1 file changed, 276 insertions(+)
 create mode 100755 tools/testing/selftests/drivers/net/mlxsw/sch_offload.sh

(limited to 'tools')

diff --git a/tools/testing/selftests/drivers/net/mlxsw/sch_offload.sh b/tools/testing/selftests/drivers/net/mlxsw/sch_offload.sh
new file mode 100755
index 000000000000..ade79ef08de3
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/mlxsw/sch_offload.sh
@@ -0,0 +1,276 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+#
+# Test qdisc offload indication
+
+
+ALL_TESTS="
+	test_root
+	test_etsprio
+"
+NUM_NETIFS=1
+lib_dir=$(dirname $0)/../../../net/forwarding
+source $lib_dir/lib.sh
+
+check_not_offloaded()
+{
+	local handle=$1; shift
+	local h
+	local offloaded
+
+	h=$(qdisc_stats_get $h1 "$handle" .handle)
+	[[ $h == '"'$handle'"' ]]
+	check_err $? "Qdisc with handle $handle does not exist"
+
+	offloaded=$(qdisc_stats_get $h1 "$handle" .offloaded)
+	[[ $offloaded == true ]]
+	check_fail $? "Qdisc with handle $handle offloaded, but should not be"
+}
+
+check_all_offloaded()
+{
+	local handle=$1; shift
+
+	if [[ ! -z $handle ]]; then
+		local offloaded=$(qdisc_stats_get $h1 "$handle" .offloaded)
+		[[ $offloaded == true ]]
+		check_err $? "Qdisc with handle $handle not offloaded"
+	fi
+
+	local unoffloaded=$(tc q sh dev $h1 invisible |
+				grep -v offloaded |
+				sed s/root/parent\ root/ |
+				cut -d' ' -f 5)
+	[[ -z $unoffloaded ]]
+	check_err $? "Qdiscs with following parents not offloaded: $unoffloaded"
+
+	pre_cleanup
+}
+
+with_ets()
+{
+	local handle=$1; shift
+	local locus=$1; shift
+
+	tc qdisc add dev $h1 $locus handle $handle \
+	   ets bands 8 priomap 7 6 5 4 3 2 1 0
+	"$@"
+	tc qdisc del dev $h1 $locus
+}
+
+with_prio()
+{
+	local handle=$1; shift
+	local locus=$1; shift
+
+	tc qdisc add dev $h1 $locus handle $handle \
+	   prio bands 8 priomap 7 6 5 4 3 2 1 0
+	"$@"
+	tc qdisc del dev $h1 $locus
+}
+
+with_red()
+{
+	local handle=$1; shift
+	local locus=$1; shift
+
+	tc qdisc add dev $h1 $locus handle $handle \
+	   red limit 1000000 min 200000 max 300000 probability 0.5 avpkt 1500
+	"$@"
+	tc qdisc del dev $h1 $locus
+}
+
+with_tbf()
+{
+	local handle=$1; shift
+	local locus=$1; shift
+
+	tc qdisc add dev $h1 $locus handle $handle \
+	   tbf rate 400Mbit burst 128K limit 1M
+	"$@"
+	tc qdisc del dev $h1 $locus
+}
+
+with_pfifo()
+{
+	local handle=$1; shift
+	local locus=$1; shift
+
+	tc qdisc add dev $h1 $locus handle $handle pfifo limit 100K
+	"$@"
+	tc qdisc del dev $h1 $locus
+}
+
+with_bfifo()
+{
+	local handle=$1; shift
+	local locus=$1; shift
+
+	tc qdisc add dev $h1 $locus handle $handle bfifo limit 100K
+	"$@"
+	tc qdisc del dev $h1 $locus
+}
+
+with_drr()
+{
+	local handle=$1; shift
+	local locus=$1; shift
+
+	tc qdisc add dev $h1 $locus handle $handle drr
+	"$@"
+	tc qdisc del dev $h1 $locus
+}
+
+with_qdiscs()
+{
+	local handle=$1; shift
+	local parent=$1; shift
+	local kind=$1; shift
+	local next_handle=$((handle * 2))
+	local locus;
+
+	if [[ $kind == "--" ]]; then
+		local cmd=$1; shift
+		$cmd $(printf %x: $parent) "$@"
+	else
+		if ((parent == 0)); then
+			locus=root
+		else
+			locus=$(printf "parent %x:1" $parent)
+		fi
+
+		with_$kind $(printf %x: $handle) "$locus" \
+			with_qdiscs $next_handle $handle "$@"
+	fi
+}
+
+get_name()
+{
+	local parent=$1; shift
+	local name=$(echo "" "${@^^}" | tr ' ' -)
+
+	if ((parent != 0)); then
+		kind=$(qdisc_stats_get $h1 $parent: .kind)
+		kind=${kind%\"}
+		kind=${kind#\"}
+		name="-${kind^^}$name"
+	fi
+
+	echo root$name
+}
+
+do_test_offloaded()
+{
+	local handle=$1; shift
+	local parent=$1; shift
+
+	RET=0
+	with_qdiscs $handle $parent "$@" -- check_all_offloaded
+	log_test $(get_name $parent "$@")" offloaded"
+}
+
+do_test_nooffload()
+{
+	local handle=$1; shift
+	local parent=$1; shift
+
+	local name=$(echo "${@^^}" | tr ' ' -)
+	local kind
+
+	RET=0
+	with_qdiscs $handle $parent "$@" -- check_not_offloaded
+	log_test $(get_name $parent "$@")" not offloaded"
+}
+
+do_test_combinations()
+{
+	local handle=$1; shift
+	local parent=$1; shift
+
+	local cont
+	local leaf
+	local fifo
+
+	for cont in "" ets prio; do
+		for leaf in "" red tbf "red tbf" "tbf red"; do
+			for fifo in "" pfifo bfifo; do
+				if [[ -z "$cont$leaf$fifo" ]]; then
+					continue
+				fi
+				do_test_offloaded $handle $parent \
+						  $cont $leaf $fifo
+			done
+		done
+	done
+
+	for cont in ets prio; do
+		for leaf in red tbf; do
+			do_test_nooffload $handle $parent $cont red tbf $leaf
+			do_test_nooffload $handle $parent $cont tbf red $leaf
+		done
+		for leaf in "red red" "tbf tbf"; do
+			do_test_nooffload $handle $parent $cont $leaf
+		done
+	done
+
+	do_test_nooffload $handle $parent drr
+}
+
+test_root()
+{
+	do_test_combinations 1 0
+}
+
+do_test_etsprio()
+{
+	local parent=$1; shift
+	local tbfpfx=$1; shift
+	local cont
+
+	for cont in ets prio; do
+		RET=0
+		with_$cont 8: "$parent" \
+			with_red 11: "parent 8:1" \
+			with_red 12: "parent 8:2" \
+			with_tbf 13: "parent 8:3" \
+			with_tbf 14: "parent 8:4" \
+			check_all_offloaded
+		log_test "root$tbfpfx-ETS-{RED,TBF} offloaded"
+
+		RET=0
+		with_$cont 8: "$parent" \
+			with_red 81: "parent 8:1" \
+				with_tbf 811: "parent 81:1" \
+			with_tbf 84: "parent 8:4" \
+				with_red 841: "parent 84:1" \
+			check_all_offloaded
+		log_test "root$tbfpfx-ETS-{RED-TBF,TBF-RED} offloaded"
+
+		RET=0
+		with_$cont 8: "$parent" \
+			with_red 81: "parent 8:1" \
+				with_tbf 811: "parent 81:1" \
+					with_bfifo 8111: "parent 811:1" \
+			with_tbf 82: "parent 8:2" \
+				with_red 821: "parent 82:1" \
+					with_bfifo 8211: "parent 821:1" \
+			check_all_offloaded
+		log_test "root$tbfpfx-ETS-{RED-TBF-bFIFO,TBF-RED-bFIFO} offloaded"
+	done
+}
+
+test_etsprio()
+{
+	do_test_etsprio root ""
+}
+
+cleanup()
+{
+	tc qdisc del dev $h1 root &>/dev/null
+}
+
+trap cleanup EXIT
+h1=${NETIFS[p1]}
+tests_run
+
+exit $EXIT_STATUS
-- 
cgit v1.2.3


From d51b6b2287ae0c5432f03457a1dbc844e1968d12 Mon Sep 17 00:00:00 2001
From: Quentin Monnet <quentin@isovalent.com>
Date: Sun, 10 Oct 2021 01:25:28 +0100
Subject: libbpf: Remove Makefile warnings on out-of-sync netlink.h/if_link.h

Although relying on some definitions from the netlink.h and if_link.h
headers copied into tools/include/uapi/linux/, libbpf does not need
those headers to stay entirely up-to-date with their original versions,
and the warnings emitted by the Makefile when it detects a difference
are usually just noise. Let's remove those warnings.

Suggested-by: Andrii Nakryiko <andrii@kernel.org>
Signed-off-by: Quentin Monnet <quentin@isovalent.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20211010002528.9772-1-quentin@isovalent.com
---
 tools/lib/bpf/Makefile | 6 ------
 1 file changed, 6 deletions(-)

(limited to 'tools')

diff --git a/tools/lib/bpf/Makefile b/tools/lib/bpf/Makefile
index 9c6804ca5b45..b393b5e82380 100644
--- a/tools/lib/bpf/Makefile
+++ b/tools/lib/bpf/Makefile
@@ -146,12 +146,6 @@ $(BPF_IN_SHARED): force $(BPF_GENERATED)
 	@(test -f ../../include/uapi/linux/bpf_common.h -a -f ../../../include/uapi/linux/bpf_common.h && ( \
 	(diff -B ../../include/uapi/linux/bpf_common.h ../../../include/uapi/linux/bpf_common.h >/dev/null) || \
 	echo "Warning: Kernel ABI header at 'tools/include/uapi/linux/bpf_common.h' differs from latest version at 'include/uapi/linux/bpf_common.h'" >&2 )) || true
-	@(test -f ../../include/uapi/linux/netlink.h -a -f ../../../include/uapi/linux/netlink.h && ( \
-	(diff -B ../../include/uapi/linux/netlink.h ../../../include/uapi/linux/netlink.h >/dev/null) || \
-	echo "Warning: Kernel ABI header at 'tools/include/uapi/linux/netlink.h' differs from latest version at 'include/uapi/linux/netlink.h'" >&2 )) || true
-	@(test -f ../../include/uapi/linux/if_link.h -a -f ../../../include/uapi/linux/if_link.h && ( \
-	(diff -B ../../include/uapi/linux/if_link.h ../../../include/uapi/linux/if_link.h >/dev/null) || \
-	echo "Warning: Kernel ABI header at 'tools/include/uapi/linux/if_link.h' differs from latest version at 'include/uapi/linux/if_link.h'" >&2 )) || true
 	@(test -f ../../include/uapi/linux/if_xdp.h -a -f ../../../include/uapi/linux/if_xdp.h && ( \
 	(diff -B ../../include/uapi/linux/if_xdp.h ../../../include/uapi/linux/if_xdp.h >/dev/null) || \
 	echo "Warning: Kernel ABI header at 'tools/include/uapi/linux/if_xdp.h' differs from latest version at 'include/uapi/linux/if_xdp.h'" >&2 )) || true
-- 
cgit v1.2.3


From 34e3ab1447db13daad066bb9fcf76cb88a827da6 Mon Sep 17 00:00:00 2001
From: Quentin Monnet <quentin@isovalent.com>
Date: Sat, 9 Oct 2021 22:03:39 +0100
Subject: bpftool: Fix install for libbpf's internal header(s)

We recently updated bpftool's Makefile to make it install the headers
from libbpf, instead of pulling them directly from libbpf's directory.
There is also an additional header, internal to libbpf, that needs be
installed. The way that bpftool's Makefile installs that particular
header is currently correct, but would break if we were to modify
$(LIBBPF_INTERNAL_HDRS) to make it point to more than one header.

Use a static pattern rule instead, so that the Makefile can withstand
the addition of other headers to install.

The objective is simply to make the Makefile more robust. It should
_not_ be read as an invitation to import more internal headers from
libbpf into bpftool.

Fixes: f012ade10b34 ("bpftool: Install libbpf headers instead of including the dir")
Reported-by: Andrii Nakryiko <andrii@kernel.org>
Signed-off-by: Quentin Monnet <quentin@isovalent.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Acked-by: John Fastabend <john.fastabend@gmail.com>
Link: https://lore.kernel.org/bpf/20211009210341.6291-2-quentin@isovalent.com
---
 tools/bpf/bpftool/Makefile | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

(limited to 'tools')

diff --git a/tools/bpf/bpftool/Makefile b/tools/bpf/bpftool/Makefile
index 9c2d13c513f0..646fd40b3253 100644
--- a/tools/bpf/bpftool/Makefile
+++ b/tools/bpf/bpftool/Makefile
@@ -14,7 +14,7 @@ else
   Q = @
 endif
 
-BPF_DIR = $(srctree)/tools/lib/bpf/
+BPF_DIR = $(srctree)/tools/lib/bpf
 
 ifneq ($(OUTPUT),)
   _OUTPUT := $(OUTPUT)
@@ -25,6 +25,7 @@ BOOTSTRAP_OUTPUT := $(_OUTPUT)/bootstrap/
 LIBBPF_OUTPUT := $(_OUTPUT)/libbpf/
 LIBBPF_DESTDIR := $(LIBBPF_OUTPUT)
 LIBBPF_INCLUDE := $(LIBBPF_DESTDIR)/include
+LIBBPF_HDRS_DIR := $(LIBBPF_INCLUDE)/bpf
 
 LIBBPF = $(LIBBPF_OUTPUT)libbpf.a
 LIBBPF_BOOTSTRAP_OUTPUT = $(BOOTSTRAP_OUTPUT)libbpf/
@@ -32,7 +33,7 @@ LIBBPF_BOOTSTRAP = $(LIBBPF_BOOTSTRAP_OUTPUT)libbpf.a
 
 # We need to copy nlattr.h which is not otherwise exported by libbpf, but still
 # required by bpftool.
-LIBBPF_INTERNAL_HDRS := nlattr.h
+LIBBPF_INTERNAL_HDRS := $(addprefix $(LIBBPF_HDRS_DIR)/,nlattr.h)
 
 ifeq ($(BPFTOOL_VERSION),)
 BPFTOOL_VERSION := $(shell make -rR --no-print-directory -sC ../../.. kernelversion)
@@ -45,10 +46,9 @@ $(LIBBPF): FORCE | $(LIBBPF_OUTPUT)
 	$(Q)$(MAKE) -C $(BPF_DIR) OUTPUT=$(LIBBPF_OUTPUT) \
 		DESTDIR=$(LIBBPF_DESTDIR) prefix= $(LIBBPF) install_headers
 
-$(LIBBPF_INCLUDE)/bpf/$(LIBBPF_INTERNAL_HDRS): \
-		$(addprefix $(BPF_DIR),$(LIBBPF_INTERNAL_HDRS)) $(LIBBPF)
-	$(call QUIET_INSTALL, bpf/$(notdir $@))
-	$(Q)install -m 644 -t $(LIBBPF_INCLUDE)/bpf/ $(BPF_DIR)$(notdir $@)
+$(LIBBPF_INTERNAL_HDRS): $(LIBBPF_HDRS_DIR)/%.h: $(BPF_DIR)/%.h $(LIBBPF)
+	$(call QUIET_INSTALL, $@)
+	$(Q)install -m 644 -t $(LIBBPF_HDRS_DIR) $<
 
 $(LIBBPF_BOOTSTRAP): FORCE | $(LIBBPF_BOOTSTRAP_OUTPUT)
 	$(Q)$(MAKE) -C $(BPF_DIR) OUTPUT=$(LIBBPF_BOOTSTRAP_OUTPUT) \
@@ -150,7 +150,7 @@ BOOTSTRAP_OBJS = $(addprefix $(BOOTSTRAP_OUTPUT),main.o common.o json_writer.o g
 $(BOOTSTRAP_OBJS): $(LIBBPF_BOOTSTRAP)
 
 OBJS = $(patsubst %.c,$(OUTPUT)%.o,$(SRCS)) $(OUTPUT)disasm.o
-$(OBJS): $(LIBBPF) $(LIBBPF_INCLUDE)/bpf/$(LIBBPF_INTERNAL_HDRS)
+$(OBJS): $(LIBBPF) $(LIBBPF_INTERNAL_HDRS)
 
 VMLINUX_BTF_PATHS ?= $(if $(O),$(O)/vmlinux)				\
 		     $(if $(KBUILD_OUTPUT),$(KBUILD_OUTPUT)/vmlinux)	\
-- 
cgit v1.2.3


From ced846c65e8ffdaac7138936cdbbc9337a939fb9 Mon Sep 17 00:00:00 2001
From: Quentin Monnet <quentin@isovalent.com>
Date: Sat, 9 Oct 2021 22:03:40 +0100
Subject: bpftool: Do not FORCE-build libbpf

In bpftool's Makefile, libbpf has a FORCE dependency, to make sure we
rebuild it in case its source files changed. Let's instead make the
rebuild depend on the source files directly, through a call to the
"$(wildcard ...)" function. This avoids descending into libbpf's
directory if there is nothing to update.

Do the same for the bootstrap libbpf version.

This results in a slightly faster operation and less verbose output when
running make a second time in bpftool's directory.

Before:

    Auto-detecting system features:
    ...                        libbfd: [ on  ]
    ...        disassembler-four-args: [ on  ]
    ...                          zlib: [ on  ]
    ...                        libcap: [ on  ]
    ...               clang-bpf-co-re: [ on  ]

    make[1]: Entering directory '/root/dev/linux/tools/lib/bpf'
    make[1]: Entering directory '/root/dev/linux/tools/lib/bpf'
    make[1]: Nothing to be done for 'install_headers'.
    make[1]: Leaving directory '/root/dev/linux/tools/lib/bpf'
    make[1]: Leaving directory '/root/dev/linux/tools/lib/bpf'

After:

    Auto-detecting system features:
    ...                        libbfd: [ on  ]
    ...        disassembler-four-args: [ on  ]
    ...                          zlib: [ on  ]
    ...                        libcap: [ on  ]
    ...               clang-bpf-co-re: [ on  ]

Other ways to clean up the output could be to pass the "-s" option, or
to redirect the output to >/dev/null, when calling make recursively to
descend into libbpf's directory. However, this would suppress some
useful output if something goes wrong during the build. A better
alternative would be to pass "--no-print-directory" to the recursive
make, but that would still leave us with some noise for
"install_headers". Skipping the descent into libbpf's directory if no
source file has changed works best, and seems the most logical option
overall.

Reported-by: Andrii Nakryiko <andrii@kernel.org>
Signed-off-by: Quentin Monnet <quentin@isovalent.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Acked-by: John Fastabend <john.fastabend@gmail.com>
Link: https://lore.kernel.org/bpf/20211009210341.6291-3-quentin@isovalent.com
---
 tools/bpf/bpftool/Makefile | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'tools')

diff --git a/tools/bpf/bpftool/Makefile b/tools/bpf/bpftool/Makefile
index 646fd40b3253..331019f6d5b1 100644
--- a/tools/bpf/bpftool/Makefile
+++ b/tools/bpf/bpftool/Makefile
@@ -42,7 +42,7 @@ endif
 $(LIBBPF_OUTPUT) $(BOOTSTRAP_OUTPUT) $(LIBBPF_BOOTSTRAP_OUTPUT):
 	$(QUIET_MKDIR)mkdir -p $@
 
-$(LIBBPF): FORCE | $(LIBBPF_OUTPUT)
+$(LIBBPF): $(wildcard $(BPF_DIR)/*.[ch] $(BPF_DIR)/Makefile) | $(LIBBPF_OUTPUT)
 	$(Q)$(MAKE) -C $(BPF_DIR) OUTPUT=$(LIBBPF_OUTPUT) \
 		DESTDIR=$(LIBBPF_DESTDIR) prefix= $(LIBBPF) install_headers
 
@@ -50,7 +50,7 @@ $(LIBBPF_INTERNAL_HDRS): $(LIBBPF_HDRS_DIR)/%.h: $(BPF_DIR)/%.h $(LIBBPF)
 	$(call QUIET_INSTALL, $@)
 	$(Q)install -m 644 -t $(LIBBPF_HDRS_DIR) $<
 
-$(LIBBPF_BOOTSTRAP): FORCE | $(LIBBPF_BOOTSTRAP_OUTPUT)
+$(LIBBPF_BOOTSTRAP): $(wildcard $(BPF_DIR)/*.[ch] $(BPF_DIR)/Makefile) | $(LIBBPF_BOOTSTRAP_OUTPUT)
 	$(Q)$(MAKE) -C $(BPF_DIR) OUTPUT=$(LIBBPF_BOOTSTRAP_OUTPUT) \
 		ARCH= CC=$(HOSTCC) LD=$(HOSTLD) $@
 
-- 
cgit v1.2.3


From 062e1fc008ded14a637ed9c8631fa31f57534dfc Mon Sep 17 00:00:00 2001
From: Quentin Monnet <quentin@isovalent.com>
Date: Sat, 9 Oct 2021 22:03:41 +0100
Subject: bpftool: Turn check on zlib from a phony target into a conditional
 error

One of bpftool's object files depends on zlib. To make sure we do not
attempt to build that object when the library is not available, commit
d66fa3c70e59 ("tools: bpftool: add feature check for zlib") introduced a
feature check to detect whether zlib is present.

This check comes as a rule for which the target ("zdep") is a
nonexistent file (phony target), which means that the Makefile always
attempts to rebuild it. It is mostly harmless. However, one side effect
is that, on running again once bpftool is already built, make considers
that "something" (the recipe for zdep) was executed, and does not print
the usual message "make: Nothing to be done for 'all'", which is a
user-friendly indicator that the build went fine.

Before, with some level of debugging information:

    $ make --debug=m
    [...]
    Reading makefiles...

    Auto-detecting system features:
    ...                        libbfd: [ on  ]
    ...        disassembler-four-args: [ on  ]
    ...                          zlib: [ on  ]
    ...                        libcap: [ on  ]
    ...               clang-bpf-co-re: [ on  ]

    Updating makefiles....
    Updating goal targets....
     File 'all' does not exist.
           File 'zdep' does not exist.
          Must remake target 'zdep'.
     File 'all' does not exist.
    Must remake target 'all'.
    Successfully remade target file 'all'.

After the patch:

    $ make --debug=m
    [...]

    Auto-detecting system features:
    ...                        libbfd: [ on  ]
    ...        disassembler-four-args: [ on  ]
    ...                          zlib: [ on  ]
    ...                        libcap: [ on  ]
    ...               clang-bpf-co-re: [ on  ]

    Updating makefiles....
    Updating goal targets....
     File 'all' does not exist.
    Must remake target 'all'.
    Successfully remade target file 'all'.
    make: Nothing to be done for 'all'.

(Note the last line, which is not part of make's debug information.)

Signed-off-by: Quentin Monnet <quentin@isovalent.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Acked-by: John Fastabend <john.fastabend@gmail.com>
Link: https://lore.kernel.org/bpf/20211009210341.6291-4-quentin@isovalent.com
---
 tools/bpf/bpftool/Makefile | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

(limited to 'tools')

diff --git a/tools/bpf/bpftool/Makefile b/tools/bpf/bpftool/Makefile
index 331019f6d5b1..abcef1f72d65 100644
--- a/tools/bpf/bpftool/Makefile
+++ b/tools/bpf/bpftool/Makefile
@@ -198,7 +198,10 @@ $(BOOTSTRAP_OUTPUT)disasm.o: $(srctree)/kernel/bpf/disasm.c
 $(OUTPUT)disasm.o: $(srctree)/kernel/bpf/disasm.c
 	$(QUIET_CC)$(CC) $(CFLAGS) -c -MMD -o $@ $<
 
-$(OUTPUT)feature.o: | zdep
+$(OUTPUT)feature.o:
+ifneq ($(feature-zlib), 1)
+	$(error "No zlib found")
+endif
 
 $(BPFTOOL_BOOTSTRAP): $(BOOTSTRAP_OBJS) $(LIBBPF_BOOTSTRAP)
 	$(QUIET_LINK)$(HOSTCC) $(CFLAGS) $(LDFLAGS) -o $@ $(BOOTSTRAP_OBJS) \
@@ -254,10 +257,7 @@ doc-uninstall:
 
 FORCE:
 
-zdep:
-	@if [ "$(feature-zlib)" != "1" ]; then echo "No zlib found"; exit 1 ; fi
-
 .SECONDARY:
-.PHONY: all FORCE clean install-bin install uninstall zdep
+.PHONY: all FORCE clean install-bin install uninstall
 .PHONY: doc doc-clean doc-install doc-uninstall
 .DEFAULT_GOAL := all
-- 
cgit v1.2.3


From ebc7b50a3849d73665013573cf3c09f27fb14fde Mon Sep 17 00:00:00 2001
From: Dave Marchevsky <davemarchevsky@fb.com>
Date: Mon, 11 Oct 2021 01:20:28 -0700
Subject: libbpf: Migrate internal use of bpf_program__get_prog_info_linear

In preparation for bpf_program__get_prog_info_linear deprecation, move
the single use in libbpf to call bpf_obj_get_info_by_fd directly.

Signed-off-by: Dave Marchevsky <davemarchevsky@fb.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20211011082031.4148337-2-davemarchevsky@fb.com
---
 tools/lib/bpf/libbpf.c | 22 ++++++++++------------
 1 file changed, 10 insertions(+), 12 deletions(-)

(limited to 'tools')

diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 63d738654ff6..760c7e346603 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -8461,28 +8461,27 @@ int libbpf_find_vmlinux_btf_id(const char *name,
 
 static int libbpf_find_prog_btf_id(const char *name, __u32 attach_prog_fd)
 {
-	struct bpf_prog_info_linear *info_linear;
-	struct bpf_prog_info *info;
+	struct bpf_prog_info info = {};
+	__u32 info_len = sizeof(info);
 	struct btf *btf;
 	int err;
 
-	info_linear = bpf_program__get_prog_info_linear(attach_prog_fd, 0);
-	err = libbpf_get_error(info_linear);
+	err = bpf_obj_get_info_by_fd(attach_prog_fd, &info, &info_len);
 	if (err) {
-		pr_warn("failed get_prog_info_linear for FD %d\n",
-			attach_prog_fd);
+		pr_warn("failed bpf_obj_get_info_by_fd for FD %d: %d\n",
+			attach_prog_fd, err);
 		return err;
 	}
 
 	err = -EINVAL;
-	info = &info_linear->info;
-	if (!info->btf_id) {
+	if (!info.btf_id) {
 		pr_warn("The target program doesn't have BTF\n");
 		goto out;
 	}
-	btf = btf__load_from_kernel_by_id(info->btf_id);
-	if (libbpf_get_error(btf)) {
-		pr_warn("Failed to get BTF of the program\n");
+	btf = btf__load_from_kernel_by_id(info.btf_id);
+	err = libbpf_get_error(btf);
+	if (err) {
+		pr_warn("Failed to get BTF %d of the program: %d\n", info.btf_id, err);
 		goto out;
 	}
 	err = btf__find_by_name_kind(btf, name, BTF_KIND_FUNC);
@@ -8492,7 +8491,6 @@ static int libbpf_find_prog_btf_id(const char *name, __u32 attach_prog_fd)
 		goto out;
 	}
 out:
-	free(info_linear);
 	return err;
 }
 
-- 
cgit v1.2.3


From b8f49dce799f0c177ee6a56b3fd67e7fdc6e68c2 Mon Sep 17 00:00:00 2001
From: Wan Jiabing <wanjiabing@vivo.com>
Date: Tue, 12 Oct 2021 10:32:30 +0800
Subject: selftests/bpf: Remove duplicated include in cgroup_helpers

Fix following checkincludes.pl warning:
./scripts/checkincludes.pl tools/testing/selftests/bpf/cgroup_helpers.c
tools/testing/selftests/bpf/cgroup_helpers.c: unistd.h is included more
than once.

Signed-off-by: Wan Jiabing <wanjiabing@vivo.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Acked-by: John Fastabend <john.fastabend@gmail.com>
Link: https://lore.kernel.org/bpf/20211012023231.19911-1-wanjiabing@vivo.com
---
 tools/testing/selftests/bpf/cgroup_helpers.c | 1 -
 1 file changed, 1 deletion(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/cgroup_helpers.c b/tools/testing/selftests/bpf/cgroup_helpers.c
index 8fcd44841bb2..9d59c3990ca8 100644
--- a/tools/testing/selftests/bpf/cgroup_helpers.c
+++ b/tools/testing/selftests/bpf/cgroup_helpers.c
@@ -11,7 +11,6 @@
 #include <fcntl.h>
 #include <unistd.h>
 #include <ftw.h>
-#include <unistd.h>
 
 #include "cgroup_helpers.h"
 
-- 
cgit v1.2.3


From efc36d6c642a753c2880d97b8e8c3c7cfaf64ad1 Mon Sep 17 00:00:00 2001
From: Quentin Monnet <quentin@isovalent.com>
Date: Wed, 20 Oct 2021 10:48:26 +0100
Subject: bpftool: Remove useless #include to <perf-sys.h> from map_perf_ring.c

The header is no longer needed since the event_pipe implementation
was updated to rely on libbpf's perf_buffer. This makes bpftool free of
dependencies to perf files, and we can update the Makefile accordingly.

Fixes: 9b190f185d2f ("tools/bpftool: switch map event_pipe to libbpf's perf_buffer")
Signed-off-by: Quentin Monnet <quentin@isovalent.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20211020094826.16046-1-quentin@isovalent.com
---
 tools/bpf/bpftool/Makefile        | 3 +--
 tools/bpf/bpftool/map_perf_ring.c | 1 -
 2 files changed, 1 insertion(+), 3 deletions(-)

(limited to 'tools')

diff --git a/tools/bpf/bpftool/Makefile b/tools/bpf/bpftool/Makefile
index abcef1f72d65..098d762e111a 100644
--- a/tools/bpf/bpftool/Makefile
+++ b/tools/bpf/bpftool/Makefile
@@ -73,8 +73,7 @@ CFLAGS += -DPACKAGE='"bpftool"' -D__EXPORTED_HEADERS__ \
 	-I$(LIBBPF_INCLUDE) \
 	-I$(srctree)/kernel/bpf/ \
 	-I$(srctree)/tools/include \
-	-I$(srctree)/tools/include/uapi \
-	-I$(srctree)/tools/perf
+	-I$(srctree)/tools/include/uapi
 CFLAGS += -DBPFTOOL_VERSION='"$(BPFTOOL_VERSION)"'
 ifneq ($(EXTRA_CFLAGS),)
 CFLAGS += $(EXTRA_CFLAGS)
diff --git a/tools/bpf/bpftool/map_perf_ring.c b/tools/bpf/bpftool/map_perf_ring.c
index 825f29f93a57..b98ea702d284 100644
--- a/tools/bpf/bpftool/map_perf_ring.c
+++ b/tools/bpf/bpftool/map_perf_ring.c
@@ -22,7 +22,6 @@
 #include <sys/syscall.h>
 
 #include <bpf/bpf.h>
-#include <perf-sys.h>
 
 #include "main.h"
 
-- 
cgit v1.2.3


From b16d12f3900283e00aded9131ba1e9b2880513c3 Mon Sep 17 00:00:00 2001
From: Ilya Leoshkevich <iii@linux.ibm.com>
Date: Wed, 13 Oct 2021 18:08:59 +0200
Subject: selftests/bpf: Use cpu_number only on arches that have it

cpu_number exists only on Intel and aarch64, so skip the test involing
it on other arches. An alternative would be to replace it with an
exported non-ifdefed primitive-typed percpu variable from the common
code, but there appears to be none.

Signed-off-by: Ilya Leoshkevich <iii@linux.ibm.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20211013160902.428340-2-iii@linux.ibm.com
---
 tools/testing/selftests/bpf/prog_tests/btf_dump.c | 2 ++
 1 file changed, 2 insertions(+)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/prog_tests/btf_dump.c b/tools/testing/selftests/bpf/prog_tests/btf_dump.c
index 87f9df653e4e..12f457b6786d 100644
--- a/tools/testing/selftests/bpf/prog_tests/btf_dump.c
+++ b/tools/testing/selftests/bpf/prog_tests/btf_dump.c
@@ -778,8 +778,10 @@ static void test_btf_dump_struct_data(struct btf *btf, struct btf_dump *d,
 static void test_btf_dump_var_data(struct btf *btf, struct btf_dump *d,
 				   char *str)
 {
+#if defined(__i386__) || defined(__x86_64__) || defined(__aarch64__)
 	TEST_BTF_DUMP_VAR(btf, d, NULL, str, "cpu_number", int, BTF_F_COMPACT,
 			  "int cpu_number = (int)100", 100);
+#endif
 	TEST_BTF_DUMP_VAR(btf, d, NULL, str, "cpu_profile_flip", int, BTF_F_COMPACT,
 			  "static int cpu_profile_flip = (int)2", 2);
 }
-- 
cgit v1.2.3


From c9e982b879465ca74e3593ce82808aa259265a71 Mon Sep 17 00:00:00 2001
From: Ilya Leoshkevich <iii@linux.ibm.com>
Date: Wed, 13 Oct 2021 18:09:00 +0200
Subject: libbpf: Fix dumping big-endian bitfields

On big-endian arches not only bytes, but also bits are numbered in
reverse order (see e.g. S/390 ELF ABI Supplement, but this is also true
for other big-endian arches as well).

Signed-off-by: Ilya Leoshkevich <iii@linux.ibm.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20211013160902.428340-3-iii@linux.ibm.com
---
 tools/lib/bpf/btf_dump.c | 15 +++++++--------
 1 file changed, 7 insertions(+), 8 deletions(-)

(limited to 'tools')

diff --git a/tools/lib/bpf/btf_dump.c b/tools/lib/bpf/btf_dump.c
index 5ef42f0abed1..679bf34e3f47 100644
--- a/tools/lib/bpf/btf_dump.c
+++ b/tools/lib/bpf/btf_dump.c
@@ -1562,29 +1562,28 @@ static int btf_dump_get_bitfield_value(struct btf_dump *d,
 				       __u64 *value)
 {
 	__u16 left_shift_bits, right_shift_bits;
-	__u8 nr_copy_bits, nr_copy_bytes;
 	const __u8 *bytes = data;
-	int sz = t->size;
+	__u8 nr_copy_bits;
 	__u64 num = 0;
 	int i;
 
 	/* Maximum supported bitfield size is 64 bits */
-	if (sz > 8) {
-		pr_warn("unexpected bitfield size %d\n", sz);
+	if (t->size > 8) {
+		pr_warn("unexpected bitfield size %d\n", t->size);
 		return -EINVAL;
 	}
 
 	/* Bitfield value retrieval is done in two steps; first relevant bytes are
 	 * stored in num, then we left/right shift num to eliminate irrelevant bits.
 	 */
-	nr_copy_bits = bit_sz + bits_offset;
-	nr_copy_bytes = t->size;
 #if __BYTE_ORDER == __LITTLE_ENDIAN
-	for (i = nr_copy_bytes - 1; i >= 0; i--)
+	for (i = t->size - 1; i >= 0; i--)
 		num = num * 256 + bytes[i];
+	nr_copy_bits = bit_sz + bits_offset;
 #elif __BYTE_ORDER == __BIG_ENDIAN
-	for (i = 0; i < nr_copy_bytes; i++)
+	for (i = 0; i < t->size; i++)
 		num = num * 256 + bytes[i];
+	nr_copy_bits = t->size * 8 - bits_offset;
 #else
 # error "Unrecognized __BYTE_ORDER__"
 #endif
-- 
cgit v1.2.3


From 961632d5416389a6f2e7478b674ac645c7e3ff01 Mon Sep 17 00:00:00 2001
From: Ilya Leoshkevich <iii@linux.ibm.com>
Date: Wed, 13 Oct 2021 18:09:01 +0200
Subject: libbpf: Fix dumping non-aligned __int128

Non-aligned integers are dumped as bitfields, which is supported for at
most 64-bit integers. Fix by using the same trick as
btf_dump_float_data(): copy non-aligned values to the local buffer.

Signed-off-by: Ilya Leoshkevich <iii@linux.ibm.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20211013160902.428340-4-iii@linux.ibm.com
---
 tools/lib/bpf/btf_dump.c | 9 ++++++---
 1 file changed, 6 insertions(+), 3 deletions(-)

(limited to 'tools')

diff --git a/tools/lib/bpf/btf_dump.c b/tools/lib/bpf/btf_dump.c
index 679bf34e3f47..e98c201f29b5 100644
--- a/tools/lib/bpf/btf_dump.c
+++ b/tools/lib/bpf/btf_dump.c
@@ -1670,9 +1670,10 @@ static int btf_dump_int_data(struct btf_dump *d,
 {
 	__u8 encoding = btf_int_encoding(t);
 	bool sign = encoding & BTF_INT_SIGNED;
+	char buf[16] __aligned(16);
 	int sz = t->size;
 
-	if (sz == 0) {
+	if (sz == 0 || sz > sizeof(buf)) {
 		pr_warn("unexpected size %d for id [%u]\n", sz, type_id);
 		return -EINVAL;
 	}
@@ -1680,8 +1681,10 @@ static int btf_dump_int_data(struct btf_dump *d,
 	/* handle packed int data - accesses of integers not aligned on
 	 * int boundaries can cause problems on some platforms.
 	 */
-	if (!ptr_is_aligned(data, sz))
-		return btf_dump_bitfield_data(d, t, data, 0, 0);
+	if (!ptr_is_aligned(data, sz)) {
+		memcpy(buf, data, sz);
+		data = buf;
+	}
 
 	switch (sz) {
 	case 16: {
-- 
cgit v1.2.3


From 7960d02dddccc0676d4a1b58e9964718b47388e1 Mon Sep 17 00:00:00 2001
From: Brendan Jackman <jackmanb@google.com>
Date: Fri, 15 Oct 2021 09:33:18 +0000
Subject: selftests/bpf: Some more atomic tests

Some new verifier tests that hit some important gaps in the parameter
space for atomic ops.

There are already exhaustive tests for the JIT part in
lib/test_bpf.c, but these exercise the verifier too.

Signed-off-by: Brendan Jackman <jackmanb@google.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20211015093318.1273686-1-jackmanb@google.com
---
 .../selftests/bpf/verifier/atomic_cmpxchg.c        | 38 +++++++++++++++
 .../testing/selftests/bpf/verifier/atomic_fetch.c  | 57 ++++++++++++++++++++++
 .../selftests/bpf/verifier/atomic_invalid.c        | 25 ++++++++++
 3 files changed, 120 insertions(+)
 create mode 100644 tools/testing/selftests/bpf/verifier/atomic_fetch.c
 create mode 100644 tools/testing/selftests/bpf/verifier/atomic_invalid.c

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/verifier/atomic_cmpxchg.c b/tools/testing/selftests/bpf/verifier/atomic_cmpxchg.c
index 6e52dfc64415..c22dc83a41fd 100644
--- a/tools/testing/selftests/bpf/verifier/atomic_cmpxchg.c
+++ b/tools/testing/selftests/bpf/verifier/atomic_cmpxchg.c
@@ -119,3 +119,41 @@
 	},
 	.result = ACCEPT,
 },
+{
+	"Dest pointer in r0 - fail",
+	.insns = {
+		/* val = 0; */
+		BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
+		/* r0 = &val */
+		BPF_MOV64_REG(BPF_REG_0, BPF_REG_10),
+		/* r0 = atomic_cmpxchg(&val, r0, 1); */
+		BPF_MOV64_IMM(BPF_REG_1, 1),
+		BPF_ATOMIC_OP(BPF_DW, BPF_CMPXCHG, BPF_REG_10, BPF_REG_1, -8),
+		/* if (r0 != 0) exit(1); */
+		BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 2),
+		BPF_MOV64_IMM(BPF_REG_0, 1),
+		BPF_EXIT_INSN(),
+		/* exit(0); */
+		BPF_MOV64_IMM(BPF_REG_0, 0),
+		BPF_EXIT_INSN(),
+	},
+	.result = ACCEPT,
+},
+{
+	"Dest pointer in r0 - succeed",
+	.insns = {
+		/* r0 = &val */
+		BPF_MOV64_REG(BPF_REG_0, BPF_REG_10),
+		/* val = r0; */
+		BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -8),
+		/* r0 = atomic_cmpxchg(&val, r0, 0); */
+		BPF_MOV64_IMM(BPF_REG_1, 0),
+		BPF_ATOMIC_OP(BPF_DW, BPF_CMPXCHG, BPF_REG_10, BPF_REG_1, -8),
+		/* r1 = *r0 */
+		BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_0, -8),
+		/* exit(0); */
+		BPF_MOV64_IMM(BPF_REG_0, 0),
+		BPF_EXIT_INSN(),
+	},
+	.result = ACCEPT,
+},
diff --git a/tools/testing/selftests/bpf/verifier/atomic_fetch.c b/tools/testing/selftests/bpf/verifier/atomic_fetch.c
new file mode 100644
index 000000000000..3bc9ff7a860b
--- /dev/null
+++ b/tools/testing/selftests/bpf/verifier/atomic_fetch.c
@@ -0,0 +1,57 @@
+#define __ATOMIC_FETCH_OP_TEST(src_reg, dst_reg, operand1, op, operand2, expect) \
+	{								\
+		"atomic fetch " #op ", src=" #dst_reg " dst=" #dst_reg,	\
+		.insns = {						\
+			/* u64 val = operan1; */			\
+			BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, operand1),	\
+			/* u64 old = atomic_fetch_add(&val, operand2); */ \
+			BPF_MOV64_REG(dst_reg, BPF_REG_10),		\
+			BPF_MOV64_IMM(src_reg, operand2),		\
+			BPF_ATOMIC_OP(BPF_DW, op,			\
+				      dst_reg, src_reg, -8),		\
+			/* if (old != operand1) exit(1); */		\
+			BPF_JMP_IMM(BPF_JEQ, src_reg, operand1, 2),	\
+			BPF_MOV64_IMM(BPF_REG_0, 1),			\
+			BPF_EXIT_INSN(),				\
+			/* if (val != result) exit (2); */		\
+			BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_10, -8),	\
+			BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, expect, 2),	\
+			BPF_MOV64_IMM(BPF_REG_0, 2),			\
+			BPF_EXIT_INSN(),				\
+			/* exit(0); */					\
+			BPF_MOV64_IMM(BPF_REG_0, 0),			\
+			BPF_EXIT_INSN(),				\
+		},							\
+		.result = ACCEPT,					\
+	}
+__ATOMIC_FETCH_OP_TEST(BPF_REG_1, BPF_REG_2, 1, BPF_ADD | BPF_FETCH, 2, 3),
+__ATOMIC_FETCH_OP_TEST(BPF_REG_0, BPF_REG_1, 1, BPF_ADD | BPF_FETCH, 2, 3),
+__ATOMIC_FETCH_OP_TEST(BPF_REG_1, BPF_REG_0, 1, BPF_ADD | BPF_FETCH, 2, 3),
+__ATOMIC_FETCH_OP_TEST(BPF_REG_2, BPF_REG_3, 1, BPF_ADD | BPF_FETCH, 2, 3),
+__ATOMIC_FETCH_OP_TEST(BPF_REG_4, BPF_REG_5, 1, BPF_ADD | BPF_FETCH, 2, 3),
+__ATOMIC_FETCH_OP_TEST(BPF_REG_9, BPF_REG_8, 1, BPF_ADD | BPF_FETCH, 2, 3),
+__ATOMIC_FETCH_OP_TEST(BPF_REG_1, BPF_REG_2, 0x010, BPF_AND | BPF_FETCH, 0x011, 0x010),
+__ATOMIC_FETCH_OP_TEST(BPF_REG_0, BPF_REG_1, 0x010, BPF_AND | BPF_FETCH, 0x011, 0x010),
+__ATOMIC_FETCH_OP_TEST(BPF_REG_1, BPF_REG_0, 0x010, BPF_AND | BPF_FETCH, 0x011, 0x010),
+__ATOMIC_FETCH_OP_TEST(BPF_REG_2, BPF_REG_3, 0x010, BPF_AND | BPF_FETCH, 0x011, 0x010),
+__ATOMIC_FETCH_OP_TEST(BPF_REG_4, BPF_REG_5, 0x010, BPF_AND | BPF_FETCH, 0x011, 0x010),
+__ATOMIC_FETCH_OP_TEST(BPF_REG_9, BPF_REG_8, 0x010, BPF_AND | BPF_FETCH, 0x011, 0x010),
+__ATOMIC_FETCH_OP_TEST(BPF_REG_1, BPF_REG_2, 0x010, BPF_OR | BPF_FETCH, 0x011, 0x011),
+__ATOMIC_FETCH_OP_TEST(BPF_REG_0, BPF_REG_1, 0x010, BPF_OR | BPF_FETCH, 0x011, 0x011),
+__ATOMIC_FETCH_OP_TEST(BPF_REG_1, BPF_REG_0, 0x010, BPF_OR | BPF_FETCH, 0x011, 0x011),
+__ATOMIC_FETCH_OP_TEST(BPF_REG_2, BPF_REG_3, 0x010, BPF_OR | BPF_FETCH, 0x011, 0x011),
+__ATOMIC_FETCH_OP_TEST(BPF_REG_4, BPF_REG_5, 0x010, BPF_OR | BPF_FETCH, 0x011, 0x011),
+__ATOMIC_FETCH_OP_TEST(BPF_REG_9, BPF_REG_8, 0x010, BPF_OR | BPF_FETCH, 0x011, 0x011),
+__ATOMIC_FETCH_OP_TEST(BPF_REG_1, BPF_REG_2, 0x010, BPF_XOR | BPF_FETCH, 0x011, 0x001),
+__ATOMIC_FETCH_OP_TEST(BPF_REG_0, BPF_REG_1, 0x010, BPF_XOR | BPF_FETCH, 0x011, 0x001),
+__ATOMIC_FETCH_OP_TEST(BPF_REG_1, BPF_REG_0, 0x010, BPF_XOR | BPF_FETCH, 0x011, 0x001),
+__ATOMIC_FETCH_OP_TEST(BPF_REG_2, BPF_REG_3, 0x010, BPF_XOR | BPF_FETCH, 0x011, 0x001),
+__ATOMIC_FETCH_OP_TEST(BPF_REG_4, BPF_REG_5, 0x010, BPF_XOR | BPF_FETCH, 0x011, 0x001),
+__ATOMIC_FETCH_OP_TEST(BPF_REG_9, BPF_REG_8, 0x010, BPF_XOR | BPF_FETCH, 0x011, 0x001),
+__ATOMIC_FETCH_OP_TEST(BPF_REG_1, BPF_REG_2, 0x010, BPF_XCHG, 0x011, 0x011),
+__ATOMIC_FETCH_OP_TEST(BPF_REG_0, BPF_REG_1, 0x010, BPF_XCHG, 0x011, 0x011),
+__ATOMIC_FETCH_OP_TEST(BPF_REG_1, BPF_REG_0, 0x010, BPF_XCHG, 0x011, 0x011),
+__ATOMIC_FETCH_OP_TEST(BPF_REG_2, BPF_REG_3, 0x010, BPF_XCHG, 0x011, 0x011),
+__ATOMIC_FETCH_OP_TEST(BPF_REG_4, BPF_REG_5, 0x010, BPF_XCHG, 0x011, 0x011),
+__ATOMIC_FETCH_OP_TEST(BPF_REG_9, BPF_REG_8, 0x010, BPF_XCHG, 0x011, 0x011),
+#undef __ATOMIC_FETCH_OP_TEST
diff --git a/tools/testing/selftests/bpf/verifier/atomic_invalid.c b/tools/testing/selftests/bpf/verifier/atomic_invalid.c
new file mode 100644
index 000000000000..39272720b2f6
--- /dev/null
+++ b/tools/testing/selftests/bpf/verifier/atomic_invalid.c
@@ -0,0 +1,25 @@
+#define __INVALID_ATOMIC_ACCESS_TEST(op)					\
+	{								\
+		"atomic " #op " access through non-pointer ",			\
+		.insns = {						\
+			BPF_MOV64_IMM(BPF_REG_0, 1),			\
+			BPF_MOV64_IMM(BPF_REG_1, 0),			\
+			BPF_ATOMIC_OP(BPF_DW, op, BPF_REG_1, BPF_REG_0, -8), \
+			BPF_MOV64_IMM(BPF_REG_0, 0),			\
+			BPF_EXIT_INSN(),				\
+		},							\
+		.result = REJECT,					\
+		.errstr = "R1 invalid mem access 'inv'"			\
+	}
+__INVALID_ATOMIC_ACCESS_TEST(BPF_ADD),
+__INVALID_ATOMIC_ACCESS_TEST(BPF_ADD | BPF_FETCH),
+__INVALID_ATOMIC_ACCESS_TEST(BPF_ADD),
+__INVALID_ATOMIC_ACCESS_TEST(BPF_ADD | BPF_FETCH),
+__INVALID_ATOMIC_ACCESS_TEST(BPF_AND),
+__INVALID_ATOMIC_ACCESS_TEST(BPF_AND | BPF_FETCH),
+__INVALID_ATOMIC_ACCESS_TEST(BPF_OR),
+__INVALID_ATOMIC_ACCESS_TEST(BPF_OR | BPF_FETCH),
+__INVALID_ATOMIC_ACCESS_TEST(BPF_XOR),
+__INVALID_ATOMIC_ACCESS_TEST(BPF_XOR | BPF_FETCH),
+__INVALID_ATOMIC_ACCESS_TEST(BPF_XCHG),
+__INVALID_ATOMIC_ACCESS_TEST(BPF_CMPXCHG),
-- 
cgit v1.2.3


From 9eeb3aa33ae005526f672b394c1791578463513f Mon Sep 17 00:00:00 2001
From: Hengqi Chen <hengqi.chen@gmail.com>
Date: Thu, 21 Oct 2021 21:47:51 +0800
Subject: bpf: Add bpf_skc_to_unix_sock() helper

The helper is used in tracing programs to cast a socket
pointer to a unix_sock pointer.
The return value could be NULL if the casting is illegal.

Suggested-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Hengqi Chen <hengqi.chen@gmail.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Song Liu <songliubraving@fb.com>
Link: https://lore.kernel.org/bpf/20211021134752.1223426-2-hengqi.chen@gmail.com
---
 tools/include/uapi/linux/bpf.h | 7 +++++++
 1 file changed, 7 insertions(+)

(limited to 'tools')

diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 6fc59d61937a..22e7a3f38b9f 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -4909,6 +4909,12 @@ union bpf_attr {
  *	Return
  *		The number of bytes written to the buffer, or a negative error
  *		in case of failure.
+ *
+ * struct unix_sock *bpf_skc_to_unix_sock(void *sk)
+ * 	Description
+ *		Dynamically cast a *sk* pointer to a *unix_sock* pointer.
+ *	Return
+ *		*sk* if casting is valid, or **NULL** otherwise.
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -5089,6 +5095,7 @@ union bpf_attr {
 	FN(task_pt_regs),		\
 	FN(get_branch_snapshot),	\
 	FN(trace_vprintk),		\
+	FN(skc_to_unix_sock),		\
 	/* */
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
-- 
cgit v1.2.3


From b6c4e71516099be676ebd897ea440ce2dddca6d1 Mon Sep 17 00:00:00 2001
From: Hengqi Chen <hengqi.chen@gmail.com>
Date: Thu, 21 Oct 2021 21:47:52 +0800
Subject: selftests/bpf: Test bpf_skc_to_unix_sock() helper

Add a new test which triggers unix_listen kernel function
to test bpf_skc_to_unix_sock helper.

Signed-off-by: Hengqi Chen <hengqi.chen@gmail.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20211021134752.1223426-3-hengqi.chen@gmail.com
---
 .../selftests/bpf/prog_tests/skc_to_unix_sock.c    | 54 ++++++++++++++++++++++
 .../selftests/bpf/progs/test_skc_to_unix_sock.c    | 40 ++++++++++++++++
 2 files changed, 94 insertions(+)
 create mode 100644 tools/testing/selftests/bpf/prog_tests/skc_to_unix_sock.c
 create mode 100644 tools/testing/selftests/bpf/progs/test_skc_to_unix_sock.c

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/prog_tests/skc_to_unix_sock.c b/tools/testing/selftests/bpf/prog_tests/skc_to_unix_sock.c
new file mode 100644
index 000000000000..3eefdfed1db9
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/skc_to_unix_sock.c
@@ -0,0 +1,54 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) 2021 Hengqi Chen */
+
+#include <test_progs.h>
+#include <sys/un.h>
+#include "test_skc_to_unix_sock.skel.h"
+
+static const char *sock_path = "@skc_to_unix_sock";
+
+void test_skc_to_unix_sock(void)
+{
+	struct test_skc_to_unix_sock *skel;
+	struct sockaddr_un sockaddr;
+	int err, sockfd = 0;
+
+	skel = test_skc_to_unix_sock__open();
+	if (!ASSERT_OK_PTR(skel, "could not open BPF object"))
+		return;
+
+	skel->rodata->my_pid = getpid();
+
+	err = test_skc_to_unix_sock__load(skel);
+	if (!ASSERT_OK(err, "could not load BPF object"))
+		goto cleanup;
+
+	err = test_skc_to_unix_sock__attach(skel);
+	if (!ASSERT_OK(err, "could not attach BPF object"))
+		goto cleanup;
+
+	/* trigger unix_listen */
+	sockfd = socket(AF_UNIX, SOCK_STREAM, 0);
+	if (!ASSERT_GT(sockfd, 0, "socket failed"))
+		goto cleanup;
+
+	memset(&sockaddr, 0, sizeof(sockaddr));
+	sockaddr.sun_family = AF_UNIX;
+	strncpy(sockaddr.sun_path, sock_path, strlen(sock_path));
+	sockaddr.sun_path[0] = '\0';
+
+	err = bind(sockfd, (struct sockaddr *)&sockaddr, sizeof(sockaddr));
+	if (!ASSERT_OK(err, "bind failed"))
+		goto cleanup;
+
+	err = listen(sockfd, 1);
+	if (!ASSERT_OK(err, "listen failed"))
+		goto cleanup;
+
+	ASSERT_EQ(strcmp(skel->bss->path, sock_path), 0, "bpf_skc_to_unix_sock failed");
+
+cleanup:
+	if (sockfd)
+		close(sockfd);
+	test_skc_to_unix_sock__destroy(skel);
+}
diff --git a/tools/testing/selftests/bpf/progs/test_skc_to_unix_sock.c b/tools/testing/selftests/bpf/progs/test_skc_to_unix_sock.c
new file mode 100644
index 000000000000..a408ec95cba4
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_skc_to_unix_sock.c
@@ -0,0 +1,40 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) 2021 Hengqi Chen */
+
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+#include "bpf_tracing_net.h"
+
+const volatile pid_t my_pid = 0;
+char path[256] = {};
+
+SEC("fentry/unix_listen")
+int BPF_PROG(unix_listen, struct socket *sock, int backlog)
+{
+	pid_t pid = bpf_get_current_pid_tgid() >> 32;
+	struct unix_sock *unix_sk;
+	int i, len;
+
+	if (pid != my_pid)
+		return 0;
+
+	unix_sk = (struct unix_sock *)bpf_skc_to_unix_sock(sock->sk);
+	if (!unix_sk)
+		return 0;
+
+	if (!UNIX_ABSTRACT(unix_sk))
+		return 0;
+
+	len = unix_sk->addr->len - sizeof(short);
+	path[0] = '@';
+	for (i = 1; i < len; i++) {
+		if (i >= sizeof(struct sockaddr_un))
+			break;
+
+		path[i] = unix_sk->addr->name->sun_path[i];
+	}
+	return 0;
+}
+
+char _license[] SEC("license") = "GPL";
-- 
cgit v1.2.3


From 632f96d2652e0d4188de837f88a977eedb55aee1 Mon Sep 17 00:00:00 2001
From: Ilya Leoshkevich <iii@linux.ibm.com>
Date: Thu, 21 Oct 2021 12:46:58 +0200
Subject: libbpf: Fix ptr_is_aligned() usages

Currently ptr_is_aligned() takes size, and not alignment, as a
parameter, which may be overly pessimistic e.g. for __i128 on s390,
which must be only 8-byte aligned. Fix by using btf__align_of().

Signed-off-by: Ilya Leoshkevich <iii@linux.ibm.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20211021104658.624944-2-iii@linux.ibm.com
---
 tools/lib/bpf/btf_dump.c | 20 ++++++++++++--------
 1 file changed, 12 insertions(+), 8 deletions(-)

(limited to 'tools')

diff --git a/tools/lib/bpf/btf_dump.c b/tools/lib/bpf/btf_dump.c
index e98c201f29b5..e9e5801ece4c 100644
--- a/tools/lib/bpf/btf_dump.c
+++ b/tools/lib/bpf/btf_dump.c
@@ -1657,9 +1657,15 @@ static int btf_dump_base_type_check_zero(struct btf_dump *d,
 	return 0;
 }
 
-static bool ptr_is_aligned(const void *data, int data_sz)
+static bool ptr_is_aligned(const struct btf *btf, __u32 type_id,
+			   const void *data)
 {
-	return ((uintptr_t)data) % data_sz == 0;
+	int alignment = btf__align_of(btf, type_id);
+
+	if (alignment == 0)
+		return false;
+
+	return ((uintptr_t)data) % alignment == 0;
 }
 
 static int btf_dump_int_data(struct btf_dump *d,
@@ -1681,7 +1687,7 @@ static int btf_dump_int_data(struct btf_dump *d,
 	/* handle packed int data - accesses of integers not aligned on
 	 * int boundaries can cause problems on some platforms.
 	 */
-	if (!ptr_is_aligned(data, sz)) {
+	if (!ptr_is_aligned(d->btf, type_id, data)) {
 		memcpy(buf, data, sz);
 		data = buf;
 	}
@@ -1770,7 +1776,7 @@ static int btf_dump_float_data(struct btf_dump *d,
 	int sz = t->size;
 
 	/* handle unaligned data; copy to local union */
-	if (!ptr_is_aligned(data, sz)) {
+	if (!ptr_is_aligned(d->btf, type_id, data)) {
 		memcpy(&fl, data, sz);
 		flp = &fl;
 	}
@@ -1933,7 +1939,7 @@ static int btf_dump_ptr_data(struct btf_dump *d,
 			      __u32 id,
 			      const void *data)
 {
-	if (ptr_is_aligned(data, d->ptr_sz) && d->ptr_sz == sizeof(void *)) {
+	if (ptr_is_aligned(d->btf, id, data) && d->ptr_sz == sizeof(void *)) {
 		btf_dump_type_values(d, "%p", *(void **)data);
 	} else {
 		union ptr_data pt;
@@ -1953,10 +1959,8 @@ static int btf_dump_get_enum_value(struct btf_dump *d,
 				   __u32 id,
 				   __s64 *value)
 {
-	int sz = t->size;
-
 	/* handle unaligned enum value */
-	if (!ptr_is_aligned(data, sz)) {
+	if (!ptr_is_aligned(d->btf, id, data)) {
 		__u64 val;
 		int err;
 
-- 
cgit v1.2.3


From aba64c7da98330141dcdadd5612f088043a83696 Mon Sep 17 00:00:00 2001
From: Dave Marchevsky <davemarchevsky@fb.com>
Date: Wed, 20 Oct 2021 00:48:17 -0700
Subject: bpf: Add verified_insns to bpf_prog_info and fdinfo

This stat is currently printed in the verifier log and not stored
anywhere. To ease consumption of this data, add a field to bpf_prog_aux
so it can be exposed via BPF_OBJ_GET_INFO_BY_FD and fdinfo.

Signed-off-by: Dave Marchevsky <davemarchevsky@fb.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Acked-by: John Fastabend <john.fastabend@gmail.com>
Link: https://lore.kernel.org/bpf/20211020074818.1017682-2-davemarchevsky@fb.com
---
 tools/include/uapi/linux/bpf.h | 1 +
 1 file changed, 1 insertion(+)

(limited to 'tools')

diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 22e7a3f38b9f..c10820037883 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -5620,6 +5620,7 @@ struct bpf_prog_info {
 	__u64 run_time_ns;
 	__u64 run_cnt;
 	__u64 recursion_misses;
+	__u32 verified_insns;
 } __attribute__((aligned(8)));
 
 struct bpf_map_info {
-- 
cgit v1.2.3


From e1b9023fc7ab0dcfeefe9f0a14772ad7a1c37b5b Mon Sep 17 00:00:00 2001
From: Dave Marchevsky <davemarchevsky@fb.com>
Date: Wed, 20 Oct 2021 00:48:18 -0700
Subject: selftests/bpf: Add verif_stats test

verified_insns field was added to response of bpf_obj_get_info_by_fd
call on a prog. Confirm that it's being populated by loading a simple
program and asking for its info.

Signed-off-by: Dave Marchevsky <davemarchevsky@fb.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Acked-by: John Fastabend <john.fastabend@gmail.com>
Acked-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20211020074818.1017682-3-davemarchevsky@fb.com
---
 .../testing/selftests/bpf/prog_tests/verif_stats.c | 28 ++++++++++++++++++++++
 1 file changed, 28 insertions(+)
 create mode 100644 tools/testing/selftests/bpf/prog_tests/verif_stats.c

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/prog_tests/verif_stats.c b/tools/testing/selftests/bpf/prog_tests/verif_stats.c
new file mode 100644
index 000000000000..b4bae1340cf1
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/verif_stats.c
@@ -0,0 +1,28 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2021 Facebook */
+
+#include <test_progs.h>
+
+#include "trace_vprintk.lskel.h"
+
+void test_verif_stats(void)
+{
+	__u32 len = sizeof(struct bpf_prog_info);
+	struct bpf_prog_info info = {};
+	struct trace_vprintk *skel;
+	int err;
+
+	skel = trace_vprintk__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "trace_vprintk__open_and_load"))
+		goto cleanup;
+
+	err = bpf_obj_get_info_by_fd(skel->progs.sys_enter.prog_fd, &info, &len);
+	if (!ASSERT_OK(err, "bpf_obj_get_info_by_fd"))
+		goto cleanup;
+
+	if (!ASSERT_GT(info.verified_insns, 0, "verified_insns"))
+		goto cleanup;
+
+cleanup:
+	trace_vprintk__destroy(skel);
+}
-- 
cgit v1.2.3


From d4121376ac7a9c81a696d7558789b2f29ef3574e Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@redhat.com>
Date: Thu, 21 Oct 2021 13:41:30 +0200
Subject: selftests/bpf: Fix perf_buffer test on system with offline cpus

The perf_buffer fails on system with offline cpus:

  # test_progs -t perf_buffer
  test_perf_buffer:PASS:nr_cpus 0 nsec
  test_perf_buffer:PASS:nr_on_cpus 0 nsec
  test_perf_buffer:PASS:skel_load 0 nsec
  test_perf_buffer:PASS:attach_kprobe 0 nsec
  test_perf_buffer:PASS:perf_buf__new 0 nsec
  test_perf_buffer:PASS:epoll_fd 0 nsec
  skipping offline CPU #24
  skipping offline CPU #25
  skipping offline CPU #26
  skipping offline CPU #27
  skipping offline CPU #28
  skipping offline CPU #29
  skipping offline CPU #30
  skipping offline CPU #31
  test_perf_buffer:PASS:perf_buffer__poll 0 nsec
  test_perf_buffer:PASS:seen_cpu_cnt 0 nsec
  test_perf_buffer:FAIL:buf_cnt got 24, expected 32
  Summary: 0/0 PASSED, 0 SKIPPED, 1 FAILED

Changing the test to check online cpus instead of possible.

Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Acked-by: John Fastabend <john.fastabend@gmail.com>
Link: https://lore.kernel.org/bpf/20211021114132.8196-2-jolsa@kernel.org
---
 tools/testing/selftests/bpf/prog_tests/perf_buffer.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/prog_tests/perf_buffer.c b/tools/testing/selftests/bpf/prog_tests/perf_buffer.c
index 6979aff4aab2..877600392851 100644
--- a/tools/testing/selftests/bpf/prog_tests/perf_buffer.c
+++ b/tools/testing/selftests/bpf/prog_tests/perf_buffer.c
@@ -107,8 +107,8 @@ void serial_test_perf_buffer(void)
 		  "expect %d, seen %d\n", nr_on_cpus, CPU_COUNT(&cpu_seen)))
 		goto out_free_pb;
 
-	if (CHECK(perf_buffer__buffer_cnt(pb) != nr_cpus, "buf_cnt",
-		  "got %zu, expected %d\n", perf_buffer__buffer_cnt(pb), nr_cpus))
+	if (CHECK(perf_buffer__buffer_cnt(pb) != nr_on_cpus, "buf_cnt",
+		  "got %zu, expected %d\n", perf_buffer__buffer_cnt(pb), nr_on_cpus))
 		goto out_close;
 
 	for (i = 0; i < nr_cpus; i++) {
-- 
cgit v1.2.3


From aa274f98b269b2babf37b6308f8a1a009ca4fc41 Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@redhat.com>
Date: Thu, 21 Oct 2021 13:41:31 +0200
Subject: selftests/bpf: Fix possible/online index mismatch in perf_buffer test

The perf_buffer fails on system with offline cpus:

  # test_progs -t perf_buffer
  serial_test_perf_buffer:PASS:nr_cpus 0 nsec
  serial_test_perf_buffer:PASS:nr_on_cpus 0 nsec
  serial_test_perf_buffer:PASS:skel_load 0 nsec
  serial_test_perf_buffer:PASS:attach_kprobe 0 nsec
  serial_test_perf_buffer:PASS:perf_buf__new 0 nsec
  serial_test_perf_buffer:PASS:epoll_fd 0 nsec
  skipping offline CPU #4
  serial_test_perf_buffer:PASS:perf_buffer__poll 0 nsec
  serial_test_perf_buffer:PASS:seen_cpu_cnt 0 nsec
  serial_test_perf_buffer:PASS:buf_cnt 0 nsec
  ...
  serial_test_perf_buffer:PASS:fd_check 0 nsec
  serial_test_perf_buffer:PASS:drain_buf 0 nsec
  serial_test_perf_buffer:PASS:consume_buf 0 nsec
  serial_test_perf_buffer:FAIL:cpu_seen cpu 5 not seen
  #88 perf_buffer:FAIL
  Summary: 0/0 PASSED, 0 SKIPPED, 1 FAILED

If the offline cpu is from the middle of the possible set,
we get mismatch with possible and online cpu buffers.

The perf buffer test calls perf_buffer__consume_buffer for
all 'possible' cpus, but the library holds only 'online'
cpu buffers and perf_buffer__consume_buffer returns them
based on index.

Adding extra (online) index to keep track of online buffers,
we need the original (possible) index to trigger trace on
proper cpu.

Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Acked-by: John Fastabend <john.fastabend@gmail.com>
Link: https://lore.kernel.org/bpf/20211021114132.8196-3-jolsa@kernel.org
---
 tools/testing/selftests/bpf/prog_tests/perf_buffer.c | 13 +++++++------
 1 file changed, 7 insertions(+), 6 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/prog_tests/perf_buffer.c b/tools/testing/selftests/bpf/prog_tests/perf_buffer.c
index 877600392851..0b0cd045979b 100644
--- a/tools/testing/selftests/bpf/prog_tests/perf_buffer.c
+++ b/tools/testing/selftests/bpf/prog_tests/perf_buffer.c
@@ -45,7 +45,7 @@ int trigger_on_cpu(int cpu)
 
 void serial_test_perf_buffer(void)
 {
-	int err, on_len, nr_on_cpus = 0, nr_cpus, i;
+	int err, on_len, nr_on_cpus = 0, nr_cpus, i, j;
 	struct perf_buffer_opts pb_opts = {};
 	struct test_perf_buffer *skel;
 	cpu_set_t cpu_seen;
@@ -111,15 +111,15 @@ void serial_test_perf_buffer(void)
 		  "got %zu, expected %d\n", perf_buffer__buffer_cnt(pb), nr_on_cpus))
 		goto out_close;
 
-	for (i = 0; i < nr_cpus; i++) {
+	for (i = 0, j = 0; i < nr_cpus; i++) {
 		if (i >= on_len || !online[i])
 			continue;
 
-		fd = perf_buffer__buffer_fd(pb, i);
+		fd = perf_buffer__buffer_fd(pb, j);
 		CHECK(fd < 0 || last_fd == fd, "fd_check", "last fd %d == fd %d\n", last_fd, fd);
 		last_fd = fd;
 
-		err = perf_buffer__consume_buffer(pb, i);
+		err = perf_buffer__consume_buffer(pb, j);
 		if (CHECK(err, "drain_buf", "cpu %d, err %d\n", i, err))
 			goto out_close;
 
@@ -127,12 +127,13 @@ void serial_test_perf_buffer(void)
 		if (trigger_on_cpu(i))
 			goto out_close;
 
-		err = perf_buffer__consume_buffer(pb, i);
-		if (CHECK(err, "consume_buf", "cpu %d, err %d\n", i, err))
+		err = perf_buffer__consume_buffer(pb, j);
+		if (CHECK(err, "consume_buf", "cpu %d, err %d\n", j, err))
 			goto out_close;
 
 		if (CHECK(!CPU_ISSET(i, &cpu_seen), "cpu_seen", "cpu %d not seen\n", i))
 			goto out_close;
+		j++;
 	}
 
 out_free_pb:
-- 
cgit v1.2.3


From 99d099757ab487e0d317c69541b47aaae0b6c431 Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@redhat.com>
Date: Thu, 21 Oct 2021 13:41:32 +0200
Subject: selftests/bpf: Use nanosleep tracepoint in perf buffer test

The perf buffer tests triggers trace with nanosleep syscall,
but monitors all syscalls, which results in lot of data in the
buffer and makes it harder to debug. Let's lower the trace
traffic and monitor just nanosleep syscall.

Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Acked-by: John Fastabend <john.fastabend@gmail.com>
Link: https://lore.kernel.org/bpf/20211021114132.8196-4-jolsa@kernel.org
---
 tools/testing/selftests/bpf/progs/test_perf_buffer.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/progs/test_perf_buffer.c b/tools/testing/selftests/bpf/progs/test_perf_buffer.c
index d37ce29fd393..a08874c5bdf2 100644
--- a/tools/testing/selftests/bpf/progs/test_perf_buffer.c
+++ b/tools/testing/selftests/bpf/progs/test_perf_buffer.c
@@ -12,7 +12,7 @@ struct {
 	__type(value, int);
 } perf_buf_map SEC(".maps");
 
-SEC("tp/raw_syscalls/sys_enter")
+SEC("tp/syscalls/sys_enter_nanosleep")
 int handle_sys_enter(void *ctx)
 {
 	int cpu = bpf_get_smp_processor_id();
-- 
cgit v1.2.3


From b96c07f3b5ae6944eb52fd96a322340aa80aef5d Mon Sep 17 00:00:00 2001
From: Andrii Nakryiko <andrii@kernel.org>
Date: Wed, 20 Oct 2021 18:43:55 -0700
Subject: libbpf: Deprecate btf__finalize_data() and move it into libbpf.c

There isn't a good use case where anyone but libbpf itself needs to call
btf__finalize_data(). It was implemented for internal use and it's not
clear why it was made into public API in the first place. To function, it
requires active ELF data, which is stored inside bpf_object for the
duration of opening phase only. But the only BTF that needs bpf_object's
ELF is that bpf_object's BTF itself, which libbpf fixes up automatically
during bpf_object__open() operation anyways. There is no need for any
additional fix up and no reasonable scenario where it's useful and
appropriate.

Thus, btf__finalize_data() is just an API atavism and is better removed.
So this patch marks it as deprecated immediately (v0.6+) and moves the
code from btf.c into libbpf.c where it's used in the context of
bpf_object opening phase. Such code co-location allows to make code
structure more straightforward and remove bpf_object__section_size() and
bpf_object__variable_offset() internal helpers from libbpf_internal.h,
making them static. Their naming is also adjusted to not create
a wrong illusion that they are some sort of method of bpf_object. They
are internal helpers and are called appropriately.

This is part of libbpf 1.0 effort ([0]).

  [0] Closes: https://github.com/libbpf/libbpf/issues/276

Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Song Liu <songliubraving@fb.com>
Link: https://lore.kernel.org/bpf/20211021014404.2635234-2-andrii@kernel.org
---
 tools/lib/bpf/btf.c             |  93 -----------------------------------
 tools/lib/bpf/btf.h             |   1 +
 tools/lib/bpf/libbpf.c          | 106 ++++++++++++++++++++++++++++++++++++++--
 tools/lib/bpf/libbpf_internal.h |   4 --
 4 files changed, 102 insertions(+), 102 deletions(-)

(limited to 'tools')

diff --git a/tools/lib/bpf/btf.c b/tools/lib/bpf/btf.c
index 1f6dea11f600..3a01c4b7f36a 100644
--- a/tools/lib/bpf/btf.c
+++ b/tools/lib/bpf/btf.c
@@ -1107,99 +1107,6 @@ struct btf *btf__parse_split(const char *path, struct btf *base_btf)
 	return libbpf_ptr(btf_parse(path, base_btf, NULL));
 }
 
-static int compare_vsi_off(const void *_a, const void *_b)
-{
-	const struct btf_var_secinfo *a = _a;
-	const struct btf_var_secinfo *b = _b;
-
-	return a->offset - b->offset;
-}
-
-static int btf_fixup_datasec(struct bpf_object *obj, struct btf *btf,
-			     struct btf_type *t)
-{
-	__u32 size = 0, off = 0, i, vars = btf_vlen(t);
-	const char *name = btf__name_by_offset(btf, t->name_off);
-	const struct btf_type *t_var;
-	struct btf_var_secinfo *vsi;
-	const struct btf_var *var;
-	int ret;
-
-	if (!name) {
-		pr_debug("No name found in string section for DATASEC kind.\n");
-		return -ENOENT;
-	}
-
-	/* .extern datasec size and var offsets were set correctly during
-	 * extern collection step, so just skip straight to sorting variables
-	 */
-	if (t->size)
-		goto sort_vars;
-
-	ret = bpf_object__section_size(obj, name, &size);
-	if (ret || !size || (t->size && t->size != size)) {
-		pr_debug("Invalid size for section %s: %u bytes\n", name, size);
-		return -ENOENT;
-	}
-
-	t->size = size;
-
-	for (i = 0, vsi = btf_var_secinfos(t); i < vars; i++, vsi++) {
-		t_var = btf__type_by_id(btf, vsi->type);
-		var = btf_var(t_var);
-
-		if (!btf_is_var(t_var)) {
-			pr_debug("Non-VAR type seen in section %s\n", name);
-			return -EINVAL;
-		}
-
-		if (var->linkage == BTF_VAR_STATIC)
-			continue;
-
-		name = btf__name_by_offset(btf, t_var->name_off);
-		if (!name) {
-			pr_debug("No name found in string section for VAR kind\n");
-			return -ENOENT;
-		}
-
-		ret = bpf_object__variable_offset(obj, name, &off);
-		if (ret) {
-			pr_debug("No offset found in symbol table for VAR %s\n",
-				 name);
-			return -ENOENT;
-		}
-
-		vsi->offset = off;
-	}
-
-sort_vars:
-	qsort(btf_var_secinfos(t), vars, sizeof(*vsi), compare_vsi_off);
-	return 0;
-}
-
-int btf__finalize_data(struct bpf_object *obj, struct btf *btf)
-{
-	int err = 0;
-	__u32 i;
-
-	for (i = 1; i <= btf->nr_types; i++) {
-		struct btf_type *t = btf_type_by_id(btf, i);
-
-		/* Loader needs to fix up some of the things compiler
-		 * couldn't get its hands on while emitting BTF. This
-		 * is section size and global variable offset. We use
-		 * the info from the ELF itself for this purpose.
-		 */
-		if (btf_is_datasec(t)) {
-			err = btf_fixup_datasec(obj, btf, t);
-			if (err)
-				break;
-		}
-	}
-
-	return libbpf_err(err);
-}
-
 static void *btf_get_raw_data(const struct btf *btf, __u32 *size, bool swap_endian);
 
 int btf__load_into_kernel(struct btf *btf)
diff --git a/tools/lib/bpf/btf.h b/tools/lib/bpf/btf.h
index 4011e206e6f7..c9364be42035 100644
--- a/tools/lib/bpf/btf.h
+++ b/tools/lib/bpf/btf.h
@@ -123,6 +123,7 @@ LIBBPF_API struct btf *btf__load_from_kernel_by_id_split(__u32 id, struct btf *b
 LIBBPF_DEPRECATED_SINCE(0, 6, "use btf__load_from_kernel_by_id instead")
 LIBBPF_API int btf__get_from_id(__u32 id, struct btf **btf);
 
+LIBBPF_DEPRECATED_SINCE(0, 6, "intended for internal libbpf use only")
 LIBBPF_API int btf__finalize_data(struct bpf_object *obj, struct btf *btf);
 LIBBPF_DEPRECATED_SINCE(0, 6, "use btf__load_into_kernel instead")
 LIBBPF_API int btf__load(struct btf *btf);
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 760c7e346603..fdc25a112150 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -1324,8 +1324,7 @@ static bool bpf_map_type__is_map_in_map(enum bpf_map_type type)
 	return false;
 }
 
-int bpf_object__section_size(const struct bpf_object *obj, const char *name,
-			     __u32 *size)
+static int find_elf_sec_sz(const struct bpf_object *obj, const char *name, __u32 *size)
 {
 	int ret = -ENOENT;
 
@@ -1357,8 +1356,7 @@ int bpf_object__section_size(const struct bpf_object *obj, const char *name,
 	return *size ? 0 : ret;
 }
 
-int bpf_object__variable_offset(const struct bpf_object *obj, const char *name,
-				__u32 *off)
+static int find_elf_var_offset(const struct bpf_object *obj, const char *name, __u32 *off)
 {
 	Elf_Data *symbols = obj->efile.symbols;
 	const char *sname;
@@ -2650,6 +2648,104 @@ out:
 	return 0;
 }
 
+static int compare_vsi_off(const void *_a, const void *_b)
+{
+	const struct btf_var_secinfo *a = _a;
+	const struct btf_var_secinfo *b = _b;
+
+	return a->offset - b->offset;
+}
+
+static int btf_fixup_datasec(struct bpf_object *obj, struct btf *btf,
+			     struct btf_type *t)
+{
+	__u32 size = 0, off = 0, i, vars = btf_vlen(t);
+	const char *name = btf__name_by_offset(btf, t->name_off);
+	const struct btf_type *t_var;
+	struct btf_var_secinfo *vsi;
+	const struct btf_var *var;
+	int ret;
+
+	if (!name) {
+		pr_debug("No name found in string section for DATASEC kind.\n");
+		return -ENOENT;
+	}
+
+	/* .extern datasec size and var offsets were set correctly during
+	 * extern collection step, so just skip straight to sorting variables
+	 */
+	if (t->size)
+		goto sort_vars;
+
+	ret = find_elf_sec_sz(obj, name, &size);
+	if (ret || !size || (t->size && t->size != size)) {
+		pr_debug("Invalid size for section %s: %u bytes\n", name, size);
+		return -ENOENT;
+	}
+
+	t->size = size;
+
+	for (i = 0, vsi = btf_var_secinfos(t); i < vars; i++, vsi++) {
+		t_var = btf__type_by_id(btf, vsi->type);
+		var = btf_var(t_var);
+
+		if (!btf_is_var(t_var)) {
+			pr_debug("Non-VAR type seen in section %s\n", name);
+			return -EINVAL;
+		}
+
+		if (var->linkage == BTF_VAR_STATIC)
+			continue;
+
+		name = btf__name_by_offset(btf, t_var->name_off);
+		if (!name) {
+			pr_debug("No name found in string section for VAR kind\n");
+			return -ENOENT;
+		}
+
+		ret = find_elf_var_offset(obj, name, &off);
+		if (ret) {
+			pr_debug("No offset found in symbol table for VAR %s\n",
+				 name);
+			return -ENOENT;
+		}
+
+		vsi->offset = off;
+	}
+
+sort_vars:
+	qsort(btf_var_secinfos(t), vars, sizeof(*vsi), compare_vsi_off);
+	return 0;
+}
+
+static int btf_finalize_data(struct bpf_object *obj, struct btf *btf)
+{
+	int err = 0;
+	__u32 i, n = btf__get_nr_types(btf);
+
+	for (i = 1; i <= n; i++) {
+		struct btf_type *t = btf_type_by_id(btf, i);
+
+		/* Loader needs to fix up some of the things compiler
+		 * couldn't get its hands on while emitting BTF. This
+		 * is section size and global variable offset. We use
+		 * the info from the ELF itself for this purpose.
+		 */
+		if (btf_is_datasec(t)) {
+			err = btf_fixup_datasec(obj, btf, t);
+			if (err)
+				break;
+		}
+	}
+
+	return libbpf_err(err);
+}
+
+int btf__finalize_data(struct bpf_object *obj, struct btf *btf)
+{
+	return btf_finalize_data(obj, btf);
+}
+
 static int bpf_object__finalize_btf(struct bpf_object *obj)
 {
 	int err;
@@ -2657,7 +2753,7 @@ static int bpf_object__finalize_btf(struct bpf_object *obj)
 	if (!obj->btf)
 		return 0;
 
-	err = btf__finalize_data(obj, obj->btf);
+	err = btf_finalize_data(obj, obj->btf);
 	if (err) {
 		pr_warn("Error finalizing %s: %d.\n", BTF_ELF_SEC, err);
 		return err;
diff --git a/tools/lib/bpf/libbpf_internal.h b/tools/lib/bpf/libbpf_internal.h
index f6a5748dd318..4bbd327a4ce9 100644
--- a/tools/lib/bpf/libbpf_internal.h
+++ b/tools/lib/bpf/libbpf_internal.h
@@ -303,10 +303,6 @@ struct bpf_prog_load_params {
 
 int libbpf__bpf_prog_load(const struct bpf_prog_load_params *load_attr);
 
-int bpf_object__section_size(const struct bpf_object *obj, const char *name,
-			     __u32 *size);
-int bpf_object__variable_offset(const struct bpf_object *obj, const char *name,
-				__u32 *off);
 struct btf *btf_get_from_fd(int btf_fd, struct btf *base_btf);
 void btf_get_kernel_prefix_kind(enum bpf_attach_type attach_type,
 				const char **prefix, int *kind);
-- 
cgit v1.2.3


From 29a30ff501518a49282754909543cef1ef49e4bc Mon Sep 17 00:00:00 2001
From: Andrii Nakryiko <andrii@kernel.org>
Date: Wed, 20 Oct 2021 18:43:56 -0700
Subject: libbpf: Extract ELF processing state into separate struct

Name currently anonymous internal struct that keeps ELF-related state
for bpf_object. Just a bit of clean up, no functional changes.

Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Song Liu <songliubraving@fb.com>
Link: https://lore.kernel.org/bpf/20211021014404.2635234-3-andrii@kernel.org
---
 tools/lib/bpf/libbpf.c | 70 ++++++++++++++++++++++++--------------------------
 1 file changed, 34 insertions(+), 36 deletions(-)

(limited to 'tools')

diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index fdc25a112150..84a0683d214b 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -462,6 +462,35 @@ struct module_btf {
 	int fd_array_idx;
 };
 
+struct elf_state {
+	int fd;
+	const void *obj_buf;
+	size_t obj_buf_sz;
+	Elf *elf;
+	GElf_Ehdr ehdr;
+	Elf_Data *symbols;
+	Elf_Data *data;
+	Elf_Data *rodata;
+	Elf_Data *bss;
+	Elf_Data *st_ops_data;
+	size_t shstrndx; /* section index for section name strings */
+	size_t strtabidx;
+	struct {
+		GElf_Shdr shdr;
+		Elf_Data *data;
+	} *reloc_sects;
+	int nr_reloc_sects;
+	int maps_shndx;
+	int btf_maps_shndx;
+	__u32 btf_maps_sec_btf_id;
+	int text_shndx;
+	int symbols_shndx;
+	int data_shndx;
+	int rodata_shndx;
+	int bss_shndx;
+	int st_ops_shndx;
+};
+
 struct bpf_object {
 	char name[BPF_OBJ_NAME_LEN];
 	char license[64];
@@ -484,40 +513,10 @@ struct bpf_object {
 
 	struct bpf_gen *gen_loader;
 
+	/* Information when doing ELF related work. Only valid if efile.elf is not NULL */
+	struct elf_state efile;
 	/*
-	 * Information when doing elf related work. Only valid if fd
-	 * is valid.
-	 */
-	struct {
-		int fd;
-		const void *obj_buf;
-		size_t obj_buf_sz;
-		Elf *elf;
-		GElf_Ehdr ehdr;
-		Elf_Data *symbols;
-		Elf_Data *data;
-		Elf_Data *rodata;
-		Elf_Data *bss;
-		Elf_Data *st_ops_data;
-		size_t shstrndx; /* section index for section name strings */
-		size_t strtabidx;
-		struct {
-			GElf_Shdr shdr;
-			Elf_Data *data;
-		} *reloc_sects;
-		int nr_reloc_sects;
-		int maps_shndx;
-		int btf_maps_shndx;
-		__u32 btf_maps_sec_btf_id;
-		int text_shndx;
-		int symbols_shndx;
-		int data_shndx;
-		int rodata_shndx;
-		int bss_shndx;
-		int st_ops_shndx;
-	} efile;
-	/*
-	 * All loaded bpf_object is linked in a list, which is
+	 * All loaded bpf_object are linked in a list, which is
 	 * hidden to caller. bpf_objects__<func> handlers deal with
 	 * all objects.
 	 */
@@ -551,7 +550,6 @@ struct bpf_object {
 
 	char path[];
 };
-#define obj_elf_valid(o)	((o)->efile.elf)
 
 static const char *elf_sym_str(const struct bpf_object *obj, size_t off);
 static const char *elf_sec_str(const struct bpf_object *obj, size_t off);
@@ -1185,7 +1183,7 @@ static struct bpf_object *bpf_object__new(const char *path,
 
 static void bpf_object__elf_finish(struct bpf_object *obj)
 {
-	if (!obj_elf_valid(obj))
+	if (!obj->efile.elf)
 		return;
 
 	if (obj->efile.elf) {
@@ -1210,7 +1208,7 @@ static int bpf_object__elf_init(struct bpf_object *obj)
 	int err = 0;
 	GElf_Ehdr *ep;
 
-	if (obj_elf_valid(obj)) {
+	if (obj->efile.elf) {
 		pr_warn("elf: init internal error\n");
 		return -LIBBPF_ERRNO__LIBELF;
 	}
-- 
cgit v1.2.3


From ad23b7238474c6319bf692ae6ce037d9696df1d1 Mon Sep 17 00:00:00 2001
From: Andrii Nakryiko <andrii@kernel.org>
Date: Wed, 20 Oct 2021 18:43:57 -0700
Subject: libbpf: Use Elf64-specific types explicitly for dealing with ELF

Minimize the usage of class-agnostic gelf_xxx() APIs from libelf. These
APIs require copying ELF data structures into local GElf_xxx structs and
have a more cumbersome API. BPF ELF file is defined to be always 64-bit
ELF object, even when intended to be run on 32-bit host architectures,
so there is no need to do class-agnostic conversions everywhere. BPF
static linker implementation within libbpf has been using Elf64-specific
types since initial implementation.

Add two simple helpers, elf_sym_by_idx() and elf_rel_by_idx(), for more
succinct direct access to ELF symbol and relocation records within ELF
data itself and switch all the GElf_xxx usage into Elf64_xxx
equivalents. The only remaining place within libbpf.c that's still using
gelf API is gelf_getclass(), as there doesn't seem to be a direct way to
get underlying ELF bitness.

No functional changes intended.

Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Song Liu <songliubraving@fb.com>
Link: https://lore.kernel.org/bpf/20211021014404.2635234-4-andrii@kernel.org
---
 tools/lib/bpf/libbpf.c          | 353 ++++++++++++++++++++++------------------
 tools/lib/bpf/libbpf_internal.h |   4 +-
 tools/lib/bpf/linker.c          |   1 -
 3 files changed, 196 insertions(+), 162 deletions(-)

(limited to 'tools')

diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 84a0683d214b..74f7d9252d13 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -467,7 +467,7 @@ struct elf_state {
 	const void *obj_buf;
 	size_t obj_buf_sz;
 	Elf *elf;
-	GElf_Ehdr ehdr;
+	Elf64_Ehdr *ehdr;
 	Elf_Data *symbols;
 	Elf_Data *data;
 	Elf_Data *rodata;
@@ -476,7 +476,7 @@ struct elf_state {
 	size_t shstrndx; /* section index for section name strings */
 	size_t strtabidx;
 	struct {
-		GElf_Shdr shdr;
+		Elf64_Shdr *shdr;
 		Elf_Data *data;
 	} *reloc_sects;
 	int nr_reloc_sects;
@@ -555,9 +555,11 @@ static const char *elf_sym_str(const struct bpf_object *obj, size_t off);
 static const char *elf_sec_str(const struct bpf_object *obj, size_t off);
 static Elf_Scn *elf_sec_by_idx(const struct bpf_object *obj, size_t idx);
 static Elf_Scn *elf_sec_by_name(const struct bpf_object *obj, const char *name);
-static int elf_sec_hdr(const struct bpf_object *obj, Elf_Scn *scn, GElf_Shdr *hdr);
+static Elf64_Shdr *elf_sec_hdr(const struct bpf_object *obj, Elf_Scn *scn);
 static const char *elf_sec_name(const struct bpf_object *obj, Elf_Scn *scn);
 static Elf_Data *elf_sec_data(const struct bpf_object *obj, Elf_Scn *scn);
+static Elf64_Sym *elf_sym_by_idx(const struct bpf_object *obj, size_t idx);
+static Elf64_Rel *elf_rel_by_idx(Elf_Data *data, size_t idx);
 
 void bpf_program__unload(struct bpf_program *prog)
 {
@@ -699,25 +701,25 @@ bpf_object__add_programs(struct bpf_object *obj, Elf_Data *sec_data,
 	size_t sec_sz = sec_data->d_size, sec_off, prog_sz, nr_syms;
 	int nr_progs, err, i;
 	const char *name;
-	GElf_Sym sym;
+	Elf64_Sym *sym;
 
 	progs = obj->programs;
 	nr_progs = obj->nr_programs;
-	nr_syms = symbols->d_size / sizeof(GElf_Sym);
+	nr_syms = symbols->d_size / sizeof(Elf64_Sym);
 	sec_off = 0;
 
 	for (i = 0; i < nr_syms; i++) {
-		if (!gelf_getsym(symbols, i, &sym))
-			continue;
-		if (sym.st_shndx != sec_idx)
+		sym = elf_sym_by_idx(obj, i);
+
+		if (sym->st_shndx != sec_idx)
 			continue;
-		if (GELF_ST_TYPE(sym.st_info) != STT_FUNC)
+		if (ELF64_ST_TYPE(sym->st_info) != STT_FUNC)
 			continue;
 
-		prog_sz = sym.st_size;
-		sec_off = sym.st_value;
+		prog_sz = sym->st_size;
+		sec_off = sym->st_value;
 
-		name = elf_sym_str(obj, sym.st_name);
+		name = elf_sym_str(obj, sym->st_name);
 		if (!name) {
 			pr_warn("sec '%s': failed to get symbol name for offset %zu\n",
 				sec_name, sec_off);
@@ -730,7 +732,7 @@ bpf_object__add_programs(struct bpf_object *obj, Elf_Data *sec_data,
 			return -LIBBPF_ERRNO__FORMAT;
 		}
 
-		if (sec_idx != obj->efile.text_shndx && GELF_ST_BIND(sym.st_info) == STB_LOCAL) {
+		if (sec_idx != obj->efile.text_shndx && ELF64_ST_BIND(sym->st_info) == STB_LOCAL) {
 			pr_warn("sec '%s': program '%s' is static and not supported\n", sec_name, name);
 			return -ENOTSUP;
 		}
@@ -763,9 +765,9 @@ bpf_object__add_programs(struct bpf_object *obj, Elf_Data *sec_data,
 		 * as static to enable more permissive BPF verification mode
 		 * with more outside context available to BPF verifier
 		 */
-		if (GELF_ST_BIND(sym.st_info) != STB_LOCAL
-		    && (GELF_ST_VISIBILITY(sym.st_other) == STV_HIDDEN
-			|| GELF_ST_VISIBILITY(sym.st_other) == STV_INTERNAL))
+		if (ELF64_ST_BIND(sym->st_info) != STB_LOCAL
+		    && (ELF64_ST_VISIBILITY(sym->st_other) == STV_HIDDEN
+			|| ELF64_ST_VISIBILITY(sym->st_other) == STV_INTERNAL))
 			prog->mark_btf_static = true;
 
 		nr_progs++;
@@ -1205,8 +1207,9 @@ static void bpf_object__elf_finish(struct bpf_object *obj)
 
 static int bpf_object__elf_init(struct bpf_object *obj)
 {
+	Elf64_Ehdr *ehdr;
 	int err = 0;
-	GElf_Ehdr *ep;
+	Elf *elf;
 
 	if (obj->efile.elf) {
 		pr_warn("elf: init internal error\n");
@@ -1218,8 +1221,7 @@ static int bpf_object__elf_init(struct bpf_object *obj)
 		 * obj_buf should have been validated by
 		 * bpf_object__open_buffer().
 		 */
-		obj->efile.elf = elf_memory((char *)obj->efile.obj_buf,
-					    obj->efile.obj_buf_sz);
+		elf = elf_memory((char *)obj->efile.obj_buf, obj->efile.obj_buf_sz);
 	} else {
 		obj->efile.fd = open(obj->path, O_RDONLY);
 		if (obj->efile.fd < 0) {
@@ -1231,23 +1233,37 @@ static int bpf_object__elf_init(struct bpf_object *obj)
 			return err;
 		}
 
-		obj->efile.elf = elf_begin(obj->efile.fd, ELF_C_READ_MMAP, NULL);
+		elf = elf_begin(obj->efile.fd, ELF_C_READ_MMAP, NULL);
 	}
 
-	if (!obj->efile.elf) {
+	if (!elf) {
 		pr_warn("elf: failed to open %s as ELF file: %s\n", obj->path, elf_errmsg(-1));
 		err = -LIBBPF_ERRNO__LIBELF;
 		goto errout;
 	}
 
-	if (!gelf_getehdr(obj->efile.elf, &obj->efile.ehdr)) {
+	obj->efile.elf = elf;
+
+	if (elf_kind(elf) != ELF_K_ELF) {
+		err = -LIBBPF_ERRNO__FORMAT;
+		pr_warn("elf: '%s' is not a proper ELF object\n", obj->path);
+		goto errout;
+	}
+
+	if (gelf_getclass(elf) != ELFCLASS64) {
+		err = -LIBBPF_ERRNO__FORMAT;
+		pr_warn("elf: '%s' is not a 64-bit ELF object\n", obj->path);
+		goto errout;
+	}
+
+	obj->efile.ehdr = ehdr = elf64_getehdr(elf);
+	if (!obj->efile.ehdr) {
 		pr_warn("elf: failed to get ELF header from %s: %s\n", obj->path, elf_errmsg(-1));
 		err = -LIBBPF_ERRNO__FORMAT;
 		goto errout;
 	}
-	ep = &obj->efile.ehdr;
 
-	if (elf_getshdrstrndx(obj->efile.elf, &obj->efile.shstrndx)) {
+	if (elf_getshdrstrndx(elf, &obj->efile.shstrndx)) {
 		pr_warn("elf: failed to get section names section index for %s: %s\n",
 			obj->path, elf_errmsg(-1));
 		err = -LIBBPF_ERRNO__FORMAT;
@@ -1255,7 +1271,7 @@ static int bpf_object__elf_init(struct bpf_object *obj)
 	}
 
 	/* Elf is corrupted/truncated, avoid calling elf_strptr. */
-	if (!elf_rawdata(elf_getscn(obj->efile.elf, obj->efile.shstrndx), NULL)) {
+	if (!elf_rawdata(elf_getscn(elf, obj->efile.shstrndx), NULL)) {
 		pr_warn("elf: failed to get section names strings from %s: %s\n",
 			obj->path, elf_errmsg(-1));
 		err = -LIBBPF_ERRNO__FORMAT;
@@ -1263,8 +1279,7 @@ static int bpf_object__elf_init(struct bpf_object *obj)
 	}
 
 	/* Old LLVM set e_machine to EM_NONE */
-	if (ep->e_type != ET_REL ||
-	    (ep->e_machine && ep->e_machine != EM_BPF)) {
+	if (ehdr->e_type != ET_REL || (ehdr->e_machine && ehdr->e_machine != EM_BPF)) {
 		pr_warn("elf: %s is not a valid eBPF object file\n", obj->path);
 		err = -LIBBPF_ERRNO__FORMAT;
 		goto errout;
@@ -1279,10 +1294,10 @@ errout:
 static int bpf_object__check_endianness(struct bpf_object *obj)
 {
 #if __BYTE_ORDER == __LITTLE_ENDIAN
-	if (obj->efile.ehdr.e_ident[EI_DATA] == ELFDATA2LSB)
+	if (obj->efile.ehdr->e_ident[EI_DATA] == ELFDATA2LSB)
 		return 0;
 #elif __BYTE_ORDER == __BIG_ENDIAN
-	if (obj->efile.ehdr.e_ident[EI_DATA] == ELFDATA2MSB)
+	if (obj->efile.ehdr->e_ident[EI_DATA] == ELFDATA2MSB)
 		return 0;
 #else
 # error "Unrecognized __BYTE_ORDER__"
@@ -1363,23 +1378,20 @@ static int find_elf_var_offset(const struct bpf_object *obj, const char *name, _
 	if (!name || !off)
 		return -EINVAL;
 
-	for (si = 0; si < symbols->d_size / sizeof(GElf_Sym); si++) {
-		GElf_Sym sym;
+	for (si = 0; si < symbols->d_size / sizeof(Elf64_Sym); si++) {
+		Elf64_Sym *sym = elf_sym_by_idx(obj, si);
 
-		if (!gelf_getsym(symbols, si, &sym))
-			continue;
-		if (GELF_ST_BIND(sym.st_info) != STB_GLOBAL ||
-		    GELF_ST_TYPE(sym.st_info) != STT_OBJECT)
+		if (ELF64_ST_BIND(sym->st_info) != STB_GLOBAL ||
+		    ELF64_ST_TYPE(sym->st_info) != STT_OBJECT)
 			continue;
 
-		sname = elf_sym_str(obj, sym.st_name);
+		sname = elf_sym_str(obj, sym->st_name);
 		if (!sname) {
-			pr_warn("failed to get sym name string for var %s\n",
-				name);
+			pr_warn("failed to get sym name string for var %s\n", name);
 			return -EIO;
 		}
 		if (strcmp(name, sname) == 0) {
-			*off = sym.st_value;
+			*off = sym->st_value;
 			return 0;
 		}
 	}
@@ -1866,15 +1878,13 @@ static int bpf_object__init_user_maps(struct bpf_object *obj, bool strict)
 	 *
 	 * TODO: Detect array of map and report error.
 	 */
-	nr_syms = symbols->d_size / sizeof(GElf_Sym);
+	nr_syms = symbols->d_size / sizeof(Elf64_Sym);
 	for (i = 0; i < nr_syms; i++) {
-		GElf_Sym sym;
+		Elf64_Sym *sym = elf_sym_by_idx(obj, i);
 
-		if (!gelf_getsym(symbols, i, &sym))
+		if (sym->st_shndx != obj->efile.maps_shndx)
 			continue;
-		if (sym.st_shndx != obj->efile.maps_shndx)
-			continue;
-		if (GELF_ST_TYPE(sym.st_info) == STT_SECTION)
+		if (ELF64_ST_TYPE(sym->st_info) == STT_SECTION)
 			continue;
 		nr_maps++;
 	}
@@ -1891,40 +1901,38 @@ static int bpf_object__init_user_maps(struct bpf_object *obj, bool strict)
 
 	/* Fill obj->maps using data in "maps" section.  */
 	for (i = 0; i < nr_syms; i++) {
-		GElf_Sym sym;
+		Elf64_Sym *sym = elf_sym_by_idx(obj, i);
 		const char *map_name;
 		struct bpf_map_def *def;
 		struct bpf_map *map;
 
-		if (!gelf_getsym(symbols, i, &sym))
-			continue;
-		if (sym.st_shndx != obj->efile.maps_shndx)
+		if (sym->st_shndx != obj->efile.maps_shndx)
 			continue;
-		if (GELF_ST_TYPE(sym.st_info) == STT_SECTION)
+		if (ELF64_ST_TYPE(sym->st_info) == STT_SECTION)
 			continue;
 
 		map = bpf_object__add_map(obj);
 		if (IS_ERR(map))
 			return PTR_ERR(map);
 
-		map_name = elf_sym_str(obj, sym.st_name);
+		map_name = elf_sym_str(obj, sym->st_name);
 		if (!map_name) {
 			pr_warn("failed to get map #%d name sym string for obj %s\n",
 				i, obj->path);
 			return -LIBBPF_ERRNO__FORMAT;
 		}
 
-		if (GELF_ST_BIND(sym.st_info) == STB_LOCAL) {
+		if (ELF64_ST_BIND(sym->st_info) == STB_LOCAL) {
 			pr_warn("map '%s' (legacy): static maps are not supported\n", map_name);
 			return -ENOTSUP;
 		}
 
 		map->libbpf_type = LIBBPF_MAP_UNSPEC;
-		map->sec_idx = sym.st_shndx;
-		map->sec_offset = sym.st_value;
+		map->sec_idx = sym->st_shndx;
+		map->sec_offset = sym->st_value;
 		pr_debug("map '%s' (legacy): at sec_idx %d, offset %zu.\n",
 			 map_name, map->sec_idx, map->sec_offset);
-		if (sym.st_value + map_def_sz > data->d_size) {
+		if (sym->st_value + map_def_sz > data->d_size) {
 			pr_warn("corrupted maps section in %s: last map \"%s\" too small\n",
 				obj->path, map_name);
 			return -EINVAL;
@@ -1936,7 +1944,7 @@ static int bpf_object__init_user_maps(struct bpf_object *obj, bool strict)
 			return -ENOMEM;
 		}
 		pr_debug("map %d is \"%s\"\n", i, map->name);
-		def = (struct bpf_map_def *)(data->d_buf + sym.st_value);
+		def = (struct bpf_map_def *)(data->d_buf + sym->st_value);
 		/*
 		 * If the definition of the map in the object file fits in
 		 * bpf_map_def, copy it.  Any extra fields in our version
@@ -2506,12 +2514,13 @@ static int bpf_object__init_maps(struct bpf_object *obj,
 
 static bool section_have_execinstr(struct bpf_object *obj, int idx)
 {
-	GElf_Shdr sh;
+	Elf64_Shdr *sh;
 
-	if (elf_sec_hdr(obj, elf_sec_by_idx(obj, idx), &sh))
+	sh = elf_sec_hdr(obj, elf_sec_by_idx(obj, idx));
+	if (!sh)
 		return false;
 
-	return sh.sh_flags & SHF_EXECINSTR;
+	return sh->sh_flags & SHF_EXECINSTR;
 }
 
 static bool btf_needs_sanitization(struct bpf_object *obj)
@@ -2987,32 +2996,36 @@ static Elf_Scn *elf_sec_by_name(const struct bpf_object *obj, const char *name)
 	return NULL;
 }
 
-static int elf_sec_hdr(const struct bpf_object *obj, Elf_Scn *scn, GElf_Shdr *hdr)
+static Elf64_Shdr *elf_sec_hdr(const struct bpf_object *obj, Elf_Scn *scn)
 {
+	Elf64_Shdr *shdr;
+
 	if (!scn)
-		return -EINVAL;
+		return NULL;
 
-	if (gelf_getshdr(scn, hdr) != hdr) {
+	shdr = elf64_getshdr(scn);
+	if (!shdr) {
 		pr_warn("elf: failed to get section(%zu) header from %s: %s\n",
 			elf_ndxscn(scn), obj->path, elf_errmsg(-1));
-		return -EINVAL;
+		return NULL;
 	}
 
-	return 0;
+	return shdr;
 }
 
 static const char *elf_sec_name(const struct bpf_object *obj, Elf_Scn *scn)
 {
 	const char *name;
-	GElf_Shdr sh;
+	Elf64_Shdr *sh;
 
 	if (!scn)
 		return NULL;
 
-	if (elf_sec_hdr(obj, scn, &sh))
+	sh = elf_sec_hdr(obj, scn);
+	if (!sh)
 		return NULL;
 
-	name = elf_sec_str(obj, sh.sh_name);
+	name = elf_sec_str(obj, sh->sh_name);
 	if (!name) {
 		pr_warn("elf: failed to get section(%zu) name from %s: %s\n",
 			elf_ndxscn(scn), obj->path, elf_errmsg(-1));
@@ -3040,13 +3053,29 @@ static Elf_Data *elf_sec_data(const struct bpf_object *obj, Elf_Scn *scn)
 	return data;
 }
 
+static Elf64_Sym *elf_sym_by_idx(const struct bpf_object *obj, size_t idx)
+{
+	if (idx >= obj->efile.symbols->d_size / sizeof(Elf64_Sym))
+		return NULL;
+
+	return (Elf64_Sym *)obj->efile.symbols->d_buf + idx;
+}
+
+static Elf64_Rel *elf_rel_by_idx(Elf_Data *data, size_t idx)
+{
+	if (idx >= data->d_size / sizeof(Elf64_Rel))
+		return NULL;
+
+	return (Elf64_Rel *)data->d_buf + idx;
+}
+
 static bool is_sec_name_dwarf(const char *name)
 {
 	/* approximation, but the actual list is too long */
 	return str_has_pfx(name, ".debug_");
 }
 
-static bool ignore_elf_section(GElf_Shdr *hdr, const char *name)
+static bool ignore_elf_section(Elf64_Shdr *hdr, const char *name)
 {
 	/* no special handling of .strtab */
 	if (hdr->sh_type == SHT_STRTAB)
@@ -3101,17 +3130,18 @@ static int bpf_object__elf_collect(struct bpf_object *obj)
 	const char *name;
 	Elf_Data *data;
 	Elf_Scn *scn;
-	GElf_Shdr sh;
+	Elf64_Shdr *sh;
 
 	/* a bunch of ELF parsing functionality depends on processing symbols,
 	 * so do the first pass and find the symbol table
 	 */
 	scn = NULL;
 	while ((scn = elf_nextscn(elf, scn)) != NULL) {
-		if (elf_sec_hdr(obj, scn, &sh))
+		sh = elf_sec_hdr(obj, scn);
+		if (!sh)
 			return -LIBBPF_ERRNO__FORMAT;
 
-		if (sh.sh_type == SHT_SYMTAB) {
+		if (sh->sh_type == SHT_SYMTAB) {
 			if (obj->efile.symbols) {
 				pr_warn("elf: multiple symbol tables in %s\n", obj->path);
 				return -LIBBPF_ERRNO__FORMAT;
@@ -3123,7 +3153,7 @@ static int bpf_object__elf_collect(struct bpf_object *obj)
 
 			obj->efile.symbols = data;
 			obj->efile.symbols_shndx = elf_ndxscn(scn);
-			obj->efile.strtabidx = sh.sh_link;
+			obj->efile.strtabidx = sh->sh_link;
 		}
 	}
 
@@ -3137,14 +3167,15 @@ static int bpf_object__elf_collect(struct bpf_object *obj)
 	while ((scn = elf_nextscn(elf, scn)) != NULL) {
 		idx++;
 
-		if (elf_sec_hdr(obj, scn, &sh))
+		sh = elf_sec_hdr(obj, scn);
+		if (!sh)
 			return -LIBBPF_ERRNO__FORMAT;
 
-		name = elf_sec_str(obj, sh.sh_name);
+		name = elf_sec_str(obj, sh->sh_name);
 		if (!name)
 			return -LIBBPF_ERRNO__FORMAT;
 
-		if (ignore_elf_section(&sh, name))
+		if (ignore_elf_section(sh, name))
 			continue;
 
 		data = elf_sec_data(obj, scn);
@@ -3153,8 +3184,8 @@ static int bpf_object__elf_collect(struct bpf_object *obj)
 
 		pr_debug("elf: section(%d) %s, size %ld, link %d, flags %lx, type=%d\n",
 			 idx, name, (unsigned long)data->d_size,
-			 (int)sh.sh_link, (unsigned long)sh.sh_flags,
-			 (int)sh.sh_type);
+			 (int)sh->sh_link, (unsigned long)sh->sh_flags,
+			 (int)sh->sh_type);
 
 		if (strcmp(name, "license") == 0) {
 			err = bpf_object__init_license(obj, data->d_buf, data->d_size);
@@ -3172,10 +3203,10 @@ static int bpf_object__elf_collect(struct bpf_object *obj)
 			btf_data = data;
 		} else if (strcmp(name, BTF_EXT_ELF_SEC) == 0) {
 			btf_ext_data = data;
-		} else if (sh.sh_type == SHT_SYMTAB) {
+		} else if (sh->sh_type == SHT_SYMTAB) {
 			/* already processed during the first pass above */
-		} else if (sh.sh_type == SHT_PROGBITS && data->d_size > 0) {
-			if (sh.sh_flags & SHF_EXECINSTR) {
+		} else if (sh->sh_type == SHT_PROGBITS && data->d_size > 0) {
+			if (sh->sh_flags & SHF_EXECINSTR) {
 				if (strcmp(name, ".text") == 0)
 					obj->efile.text_shndx = idx;
 				err = bpf_object__add_programs(obj, data, name, idx);
@@ -3194,10 +3225,10 @@ static int bpf_object__elf_collect(struct bpf_object *obj)
 				pr_info("elf: skipping unrecognized data section(%d) %s\n",
 					idx, name);
 			}
-		} else if (sh.sh_type == SHT_REL) {
+		} else if (sh->sh_type == SHT_REL) {
 			int nr_sects = obj->efile.nr_reloc_sects;
 			void *sects = obj->efile.reloc_sects;
-			int sec = sh.sh_info; /* points to other section */
+			int sec = sh->sh_info; /* points to other section */
 
 			/* Only do relo for section with exec instructions */
 			if (!section_have_execinstr(obj, sec) &&
@@ -3219,12 +3250,12 @@ static int bpf_object__elf_collect(struct bpf_object *obj)
 
 			obj->efile.reloc_sects[nr_sects].shdr = sh;
 			obj->efile.reloc_sects[nr_sects].data = data;
-		} else if (sh.sh_type == SHT_NOBITS && strcmp(name, BSS_SEC) == 0) {
+		} else if (sh->sh_type == SHT_NOBITS && strcmp(name, BSS_SEC) == 0) {
 			obj->efile.bss = data;
 			obj->efile.bss_shndx = idx;
 		} else {
 			pr_info("elf: skipping section(%d) %s (size %zu)\n", idx, name,
-				(size_t)sh.sh_size);
+				(size_t)sh->sh_size);
 		}
 	}
 
@@ -3240,19 +3271,19 @@ static int bpf_object__elf_collect(struct bpf_object *obj)
 	return bpf_object__init_btf(obj, btf_data, btf_ext_data);
 }
 
-static bool sym_is_extern(const GElf_Sym *sym)
+static bool sym_is_extern(const Elf64_Sym *sym)
 {
-	int bind = GELF_ST_BIND(sym->st_info);
+	int bind = ELF64_ST_BIND(sym->st_info);
 	/* externs are symbols w/ type=NOTYPE, bind=GLOBAL|WEAK, section=UND */
 	return sym->st_shndx == SHN_UNDEF &&
 	       (bind == STB_GLOBAL || bind == STB_WEAK) &&
-	       GELF_ST_TYPE(sym->st_info) == STT_NOTYPE;
+	       ELF64_ST_TYPE(sym->st_info) == STT_NOTYPE;
 }
 
-static bool sym_is_subprog(const GElf_Sym *sym, int text_shndx)
+static bool sym_is_subprog(const Elf64_Sym *sym, int text_shndx)
 {
-	int bind = GELF_ST_BIND(sym->st_info);
-	int type = GELF_ST_TYPE(sym->st_info);
+	int bind = ELF64_ST_BIND(sym->st_info);
+	int type = ELF64_ST_TYPE(sym->st_info);
 
 	/* in .text section */
 	if (sym->st_shndx != text_shndx)
@@ -3450,30 +3481,31 @@ static int bpf_object__collect_externs(struct bpf_object *obj)
 	int i, n, off, dummy_var_btf_id;
 	const char *ext_name, *sec_name;
 	Elf_Scn *scn;
-	GElf_Shdr sh;
+	Elf64_Shdr *sh;
 
 	if (!obj->efile.symbols)
 		return 0;
 
 	scn = elf_sec_by_idx(obj, obj->efile.symbols_shndx);
-	if (elf_sec_hdr(obj, scn, &sh))
+	sh = elf_sec_hdr(obj, scn);
+	if (!sh)
 		return -LIBBPF_ERRNO__FORMAT;
 
 	dummy_var_btf_id = add_dummy_ksym_var(obj->btf);
 	if (dummy_var_btf_id < 0)
 		return dummy_var_btf_id;
 
-	n = sh.sh_size / sh.sh_entsize;
+	n = sh->sh_size / sh->sh_entsize;
 	pr_debug("looking for externs among %d symbols...\n", n);
 
 	for (i = 0; i < n; i++) {
-		GElf_Sym sym;
+		Elf64_Sym *sym = elf_sym_by_idx(obj, i);
 
-		if (!gelf_getsym(obj->efile.symbols, i, &sym))
+		if (!sym)
 			return -LIBBPF_ERRNO__FORMAT;
-		if (!sym_is_extern(&sym))
+		if (!sym_is_extern(sym))
 			continue;
-		ext_name = elf_sym_str(obj, sym.st_name);
+		ext_name = elf_sym_str(obj, sym->st_name);
 		if (!ext_name || !ext_name[0])
 			continue;
 
@@ -3495,7 +3527,7 @@ static int bpf_object__collect_externs(struct bpf_object *obj)
 		t = btf__type_by_id(obj->btf, ext->btf_id);
 		ext->name = btf__name_by_offset(obj->btf, t->name_off);
 		ext->sym_idx = i;
-		ext->is_weak = GELF_ST_BIND(sym.st_info) == STB_WEAK;
+		ext->is_weak = ELF64_ST_BIND(sym->st_info) == STB_WEAK;
 
 		ext->sec_btf_id = find_extern_sec_btf_id(obj->btf, ext->btf_id);
 		if (ext->sec_btf_id <= 0) {
@@ -3730,7 +3762,7 @@ bpf_object__section_to_libbpf_map_type(const struct bpf_object *obj, int shndx)
 static int bpf_program__record_reloc(struct bpf_program *prog,
 				     struct reloc_desc *reloc_desc,
 				     __u32 insn_idx, const char *sym_name,
-				     const GElf_Sym *sym, const GElf_Rel *rel)
+				     const Elf64_Sym *sym, const Elf64_Rel *rel)
 {
 	struct bpf_insn *insn = &prog->insns[insn_idx];
 	size_t map_idx, nr_maps = prog->obj->nr_maps;
@@ -3747,7 +3779,7 @@ static int bpf_program__record_reloc(struct bpf_program *prog,
 	}
 
 	if (sym_is_extern(sym)) {
-		int sym_idx = GELF_R_SYM(rel->r_info);
+		int sym_idx = ELF64_R_SYM(rel->r_info);
 		int i, n = obj->nr_extern;
 		struct extern_desc *ext;
 
@@ -3912,9 +3944,8 @@ static struct bpf_program *find_prog_by_sec_insn(const struct bpf_object *obj,
 }
 
 static int
-bpf_object__collect_prog_relos(struct bpf_object *obj, GElf_Shdr *shdr, Elf_Data *data)
+bpf_object__collect_prog_relos(struct bpf_object *obj, Elf64_Shdr *shdr, Elf_Data *data)
 {
-	Elf_Data *symbols = obj->efile.symbols;
 	const char *relo_sec_name, *sec_name;
 	size_t sec_idx = shdr->sh_info;
 	struct bpf_program *prog;
@@ -3924,8 +3955,8 @@ bpf_object__collect_prog_relos(struct bpf_object *obj, GElf_Shdr *shdr, Elf_Data
 	__u32 insn_idx;
 	Elf_Scn *scn;
 	Elf_Data *scn_data;
-	GElf_Sym sym;
-	GElf_Rel rel;
+	Elf64_Sym *sym;
+	Elf64_Rel *rel;
 
 	scn = elf_sec_by_idx(obj, sec_idx);
 	scn_data = elf_sec_data(obj, scn);
@@ -3940,33 +3971,36 @@ bpf_object__collect_prog_relos(struct bpf_object *obj, GElf_Shdr *shdr, Elf_Data
 	nrels = shdr->sh_size / shdr->sh_entsize;
 
 	for (i = 0; i < nrels; i++) {
-		if (!gelf_getrel(data, i, &rel)) {
+		rel = elf_rel_by_idx(data, i);
+		if (!rel) {
 			pr_warn("sec '%s': failed to get relo #%d\n", relo_sec_name, i);
 			return -LIBBPF_ERRNO__FORMAT;
 		}
-		if (!gelf_getsym(symbols, GELF_R_SYM(rel.r_info), &sym)) {
+
+		sym = elf_sym_by_idx(obj, ELF64_R_SYM(rel->r_info));
+		if (!sym) {
 			pr_warn("sec '%s': symbol 0x%zx not found for relo #%d\n",
-				relo_sec_name, (size_t)GELF_R_SYM(rel.r_info), i);
+				relo_sec_name, (size_t)ELF64_R_SYM(rel->r_info), i);
 			return -LIBBPF_ERRNO__FORMAT;
 		}
 
-		if (rel.r_offset % BPF_INSN_SZ || rel.r_offset >= scn_data->d_size) {
+		if (rel->r_offset % BPF_INSN_SZ || rel->r_offset >= scn_data->d_size) {
 			pr_warn("sec '%s': invalid offset 0x%zx for relo #%d\n",
-				relo_sec_name, (size_t)GELF_R_SYM(rel.r_info), i);
+				relo_sec_name, (size_t)ELF64_R_SYM(rel->r_info), i);
 			return -LIBBPF_ERRNO__FORMAT;
 		}
 
-		insn_idx = rel.r_offset / BPF_INSN_SZ;
+		insn_idx = rel->r_offset / BPF_INSN_SZ;
 		/* relocations against static functions are recorded as
 		 * relocations against the section that contains a function;
 		 * in such case, symbol will be STT_SECTION and sym.st_name
 		 * will point to empty string (0), so fetch section name
 		 * instead
 		 */
-		if (GELF_ST_TYPE(sym.st_info) == STT_SECTION && sym.st_name == 0)
-			sym_name = elf_sec_name(obj, elf_sec_by_idx(obj, sym.st_shndx));
+		if (ELF64_ST_TYPE(sym->st_info) == STT_SECTION && sym->st_name == 0)
+			sym_name = elf_sec_name(obj, elf_sec_by_idx(obj, sym->st_shndx));
 		else
-			sym_name = elf_sym_str(obj, sym.st_name);
+			sym_name = elf_sym_str(obj, sym->st_name);
 		sym_name = sym_name ?: "<?";
 
 		pr_debug("sec '%s': relo #%d: insn #%u against '%s'\n",
@@ -3988,7 +4022,7 @@ bpf_object__collect_prog_relos(struct bpf_object *obj, GElf_Shdr *shdr, Elf_Data
 		/* adjust insn_idx to local BPF program frame of reference */
 		insn_idx -= prog->sec_insn_off;
 		err = bpf_program__record_reloc(prog, &relos[prog->nr_reloc],
-						insn_idx, sym_name, &sym, &rel);
+						insn_idx, sym_name, sym, rel);
 		if (err)
 			return err;
 
@@ -6036,10 +6070,10 @@ bpf_object__relocate(struct bpf_object *obj, const char *targ_btf_path)
 }
 
 static int bpf_object__collect_st_ops_relos(struct bpf_object *obj,
-					    GElf_Shdr *shdr, Elf_Data *data);
+					    Elf64_Shdr *shdr, Elf_Data *data);
 
 static int bpf_object__collect_map_relos(struct bpf_object *obj,
-					 GElf_Shdr *shdr, Elf_Data *data)
+					 Elf64_Shdr *shdr, Elf_Data *data)
 {
 	const int bpf_ptr_sz = 8, host_ptr_sz = sizeof(void *);
 	int i, j, nrels, new_sz;
@@ -6048,10 +6082,9 @@ static int bpf_object__collect_map_relos(struct bpf_object *obj,
 	struct bpf_map *map = NULL, *targ_map;
 	const struct btf_member *member;
 	const char *name, *mname;
-	Elf_Data *symbols;
 	unsigned int moff;
-	GElf_Sym sym;
-	GElf_Rel rel;
+	Elf64_Sym *sym;
+	Elf64_Rel *rel;
 	void *tmp;
 
 	if (!obj->efile.btf_maps_sec_btf_id || !obj->btf)
@@ -6060,28 +6093,30 @@ static int bpf_object__collect_map_relos(struct bpf_object *obj,
 	if (!sec)
 		return -EINVAL;
 
-	symbols = obj->efile.symbols;
 	nrels = shdr->sh_size / shdr->sh_entsize;
 	for (i = 0; i < nrels; i++) {
-		if (!gelf_getrel(data, i, &rel)) {
+		rel = elf_rel_by_idx(data, i);
+		if (!rel) {
 			pr_warn(".maps relo #%d: failed to get ELF relo\n", i);
 			return -LIBBPF_ERRNO__FORMAT;
 		}
-		if (!gelf_getsym(symbols, GELF_R_SYM(rel.r_info), &sym)) {
+
+		sym = elf_sym_by_idx(obj, ELF64_R_SYM(rel->r_info));
+		if (!sym) {
 			pr_warn(".maps relo #%d: symbol %zx not found\n",
-				i, (size_t)GELF_R_SYM(rel.r_info));
+				i, (size_t)ELF64_R_SYM(rel->r_info));
 			return -LIBBPF_ERRNO__FORMAT;
 		}
-		name = elf_sym_str(obj, sym.st_name) ?: "<?>";
-		if (sym.st_shndx != obj->efile.btf_maps_shndx) {
+		name = elf_sym_str(obj, sym->st_name) ?: "<?>";
+		if (sym->st_shndx != obj->efile.btf_maps_shndx) {
 			pr_warn(".maps relo #%d: '%s' isn't a BTF-defined map\n",
 				i, name);
 			return -LIBBPF_ERRNO__RELOC;
 		}
 
-		pr_debug(".maps relo #%d: for %zd value %zd rel.r_offset %zu name %d ('%s')\n",
-			 i, (ssize_t)(rel.r_info >> 32), (size_t)sym.st_value,
-			 (size_t)rel.r_offset, sym.st_name, name);
+		pr_debug(".maps relo #%d: for %zd value %zd rel->r_offset %zu name %d ('%s')\n",
+			 i, (ssize_t)(rel->r_info >> 32), (size_t)sym->st_value,
+			 (size_t)rel->r_offset, sym->st_name, name);
 
 		for (j = 0; j < obj->nr_maps; j++) {
 			map = &obj->maps[j];
@@ -6089,13 +6124,13 @@ static int bpf_object__collect_map_relos(struct bpf_object *obj,
 				continue;
 
 			vi = btf_var_secinfos(sec) + map->btf_var_idx;
-			if (vi->offset <= rel.r_offset &&
-			    rel.r_offset + bpf_ptr_sz <= vi->offset + vi->size)
+			if (vi->offset <= rel->r_offset &&
+			    rel->r_offset + bpf_ptr_sz <= vi->offset + vi->size)
 				break;
 		}
 		if (j == obj->nr_maps) {
-			pr_warn(".maps relo #%d: cannot find map '%s' at rel.r_offset %zu\n",
-				i, name, (size_t)rel.r_offset);
+			pr_warn(".maps relo #%d: cannot find map '%s' at rel->r_offset %zu\n",
+				i, name, (size_t)rel->r_offset);
 			return -EINVAL;
 		}
 
@@ -6122,10 +6157,10 @@ static int bpf_object__collect_map_relos(struct bpf_object *obj,
 			return -EINVAL;
 
 		moff = btf_member_bit_offset(def, btf_vlen(def) - 1) / 8;
-		if (rel.r_offset - vi->offset < moff)
+		if (rel->r_offset - vi->offset < moff)
 			return -EINVAL;
 
-		moff = rel.r_offset - vi->offset - moff;
+		moff = rel->r_offset - vi->offset - moff;
 		/* here we use BPF pointer size, which is always 64 bit, as we
 		 * are parsing ELF that was built for BPF target
 		 */
@@ -6171,7 +6206,7 @@ static int bpf_object__collect_relos(struct bpf_object *obj)
 	int i, err;
 
 	for (i = 0; i < obj->efile.nr_reloc_sects; i++) {
-		GElf_Shdr *shdr = &obj->efile.reloc_sects[i].shdr;
+		Elf64_Shdr *shdr = obj->efile.reloc_sects[i].shdr;
 		Elf_Data *data = obj->efile.reloc_sects[i].data;
 		int idx = shdr->sh_info;
 
@@ -8362,7 +8397,7 @@ static struct bpf_map *find_struct_ops_map_by_offset(struct bpf_object *obj,
 
 /* Collect the reloc from ELF and populate the st_ops->progs[] */
 static int bpf_object__collect_st_ops_relos(struct bpf_object *obj,
-					    GElf_Shdr *shdr, Elf_Data *data)
+					    Elf64_Shdr *shdr, Elf_Data *data)
 {
 	const struct btf_member *member;
 	struct bpf_struct_ops *st_ops;
@@ -8370,58 +8405,58 @@ static int bpf_object__collect_st_ops_relos(struct bpf_object *obj,
 	unsigned int shdr_idx;
 	const struct btf *btf;
 	struct bpf_map *map;
-	Elf_Data *symbols;
 	unsigned int moff, insn_idx;
 	const char *name;
 	__u32 member_idx;
-	GElf_Sym sym;
-	GElf_Rel rel;
+	Elf64_Sym *sym;
+	Elf64_Rel *rel;
 	int i, nrels;
 
-	symbols = obj->efile.symbols;
 	btf = obj->btf;
 	nrels = shdr->sh_size / shdr->sh_entsize;
 	for (i = 0; i < nrels; i++) {
-		if (!gelf_getrel(data, i, &rel)) {
+		rel = elf_rel_by_idx(data, i);
+		if (!rel) {
 			pr_warn("struct_ops reloc: failed to get %d reloc\n", i);
 			return -LIBBPF_ERRNO__FORMAT;
 		}
 
-		if (!gelf_getsym(symbols, GELF_R_SYM(rel.r_info), &sym)) {
+		sym = elf_sym_by_idx(obj, ELF64_R_SYM(rel->r_info));
+		if (!sym) {
 			pr_warn("struct_ops reloc: symbol %zx not found\n",
-				(size_t)GELF_R_SYM(rel.r_info));
+				(size_t)ELF64_R_SYM(rel->r_info));
 			return -LIBBPF_ERRNO__FORMAT;
 		}
 
-		name = elf_sym_str(obj, sym.st_name) ?: "<?>";
-		map = find_struct_ops_map_by_offset(obj, rel.r_offset);
+		name = elf_sym_str(obj, sym->st_name) ?: "<?>";
+		map = find_struct_ops_map_by_offset(obj, rel->r_offset);
 		if (!map) {
-			pr_warn("struct_ops reloc: cannot find map at rel.r_offset %zu\n",
-				(size_t)rel.r_offset);
+			pr_warn("struct_ops reloc: cannot find map at rel->r_offset %zu\n",
+				(size_t)rel->r_offset);
 			return -EINVAL;
 		}
 
-		moff = rel.r_offset - map->sec_offset;
-		shdr_idx = sym.st_shndx;
+		moff = rel->r_offset - map->sec_offset;
+		shdr_idx = sym->st_shndx;
 		st_ops = map->st_ops;
-		pr_debug("struct_ops reloc %s: for %lld value %lld shdr_idx %u rel.r_offset %zu map->sec_offset %zu name %d (\'%s\')\n",
+		pr_debug("struct_ops reloc %s: for %lld value %lld shdr_idx %u rel->r_offset %zu map->sec_offset %zu name %d (\'%s\')\n",
 			 map->name,
-			 (long long)(rel.r_info >> 32),
-			 (long long)sym.st_value,
-			 shdr_idx, (size_t)rel.r_offset,
-			 map->sec_offset, sym.st_name, name);
+			 (long long)(rel->r_info >> 32),
+			 (long long)sym->st_value,
+			 shdr_idx, (size_t)rel->r_offset,
+			 map->sec_offset, sym->st_name, name);
 
 		if (shdr_idx >= SHN_LORESERVE) {
-			pr_warn("struct_ops reloc %s: rel.r_offset %zu shdr_idx %u unsupported non-static function\n",
-				map->name, (size_t)rel.r_offset, shdr_idx);
+			pr_warn("struct_ops reloc %s: rel->r_offset %zu shdr_idx %u unsupported non-static function\n",
+				map->name, (size_t)rel->r_offset, shdr_idx);
 			return -LIBBPF_ERRNO__RELOC;
 		}
-		if (sym.st_value % BPF_INSN_SZ) {
+		if (sym->st_value % BPF_INSN_SZ) {
 			pr_warn("struct_ops reloc %s: invalid target program offset %llu\n",
-				map->name, (unsigned long long)sym.st_value);
+				map->name, (unsigned long long)sym->st_value);
 			return -LIBBPF_ERRNO__FORMAT;
 		}
-		insn_idx = sym.st_value / BPF_INSN_SZ;
+		insn_idx = sym->st_value / BPF_INSN_SZ;
 
 		member = find_member_by_offset(st_ops->type, moff * 8);
 		if (!member) {
diff --git a/tools/lib/bpf/libbpf_internal.h b/tools/lib/bpf/libbpf_internal.h
index 4bbd327a4ce9..13bc7950e304 100644
--- a/tools/lib/bpf/libbpf_internal.h
+++ b/tools/lib/bpf/libbpf_internal.h
@@ -52,8 +52,8 @@
 #endif
 
 /* Older libelf all end up in this expression, for both 32 and 64 bit */
-#ifndef GELF_ST_VISIBILITY
-#define GELF_ST_VISIBILITY(o) ((o) & 0x03)
+#ifndef ELF64_ST_VISIBILITY
+#define ELF64_ST_VISIBILITY(o) ((o) & 0x03)
 #endif
 
 #define BTF_INFO_ENC(kind, kind_flag, vlen) \
diff --git a/tools/lib/bpf/linker.c b/tools/lib/bpf/linker.c
index 2df880cefdae..13e6fdc7d8cb 100644
--- a/tools/lib/bpf/linker.c
+++ b/tools/lib/bpf/linker.c
@@ -15,7 +15,6 @@
 #include <linux/btf.h>
 #include <elf.h>
 #include <libelf.h>
-#include <gelf.h>
 #include <fcntl.h>
 #include "libbpf.h"
 #include "btf.h"
-- 
cgit v1.2.3


From 25bbbd7a444b1624000389830d46ffdc5b809ee8 Mon Sep 17 00:00:00 2001
From: Andrii Nakryiko <andrii@kernel.org>
Date: Wed, 20 Oct 2021 18:43:58 -0700
Subject: libbpf: Remove assumptions about uniqueness of .rodata/.data/.bss
 maps

Remove internal libbpf assumption that there can be only one .rodata,
.data, and .bss map per BPF object. To achieve that, extend and
generalize the scheme that was used for keeping track of relocation ELF
sections. Now each ELF section has a temporary extra index that keeps
track of logical type of ELF section (relocations, data, read-only data,
BSS). Switch relocation to this scheme, as well as .rodata/.data/.bss
handling.

We don't yet allow multiple .rodata, .data, and .bss sections, but no
libbpf internal code makes an assumption that there can be only one of
each and thus they can be explicitly referenced by a single index. Next
patches will actually allow multiple .rodata and .data sections.

Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Song Liu <songliubraving@fb.com>
Link: https://lore.kernel.org/bpf/20211021014404.2635234-5-andrii@kernel.org
---
 tools/lib/bpf/libbpf.c | 260 ++++++++++++++++++++++++++-----------------------
 1 file changed, 140 insertions(+), 120 deletions(-)

(limited to 'tools')

diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 74f7d9252d13..a7320d272b34 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -462,6 +462,20 @@ struct module_btf {
 	int fd_array_idx;
 };
 
+enum sec_type {
+	SEC_UNUSED = 0,
+	SEC_RELO,
+	SEC_BSS,
+	SEC_DATA,
+	SEC_RODATA,
+};
+
+struct elf_sec_desc {
+	enum sec_type sec_type;
+	Elf64_Shdr *shdr;
+	Elf_Data *data;
+};
+
 struct elf_state {
 	int fd;
 	const void *obj_buf;
@@ -469,25 +483,16 @@ struct elf_state {
 	Elf *elf;
 	Elf64_Ehdr *ehdr;
 	Elf_Data *symbols;
-	Elf_Data *data;
-	Elf_Data *rodata;
-	Elf_Data *bss;
 	Elf_Data *st_ops_data;
 	size_t shstrndx; /* section index for section name strings */
 	size_t strtabidx;
-	struct {
-		Elf64_Shdr *shdr;
-		Elf_Data *data;
-	} *reloc_sects;
-	int nr_reloc_sects;
+	struct elf_sec_desc *secs;
+	int sec_cnt;
 	int maps_shndx;
 	int btf_maps_shndx;
 	__u32 btf_maps_sec_btf_id;
 	int text_shndx;
 	int symbols_shndx;
-	int data_shndx;
-	int rodata_shndx;
-	int bss_shndx;
 	int st_ops_shndx;
 };
 
@@ -506,10 +511,10 @@ struct bpf_object {
 	struct extern_desc *externs;
 	int nr_extern;
 	int kconfig_map_idx;
-	int rodata_map_idx;
 
 	bool loaded;
 	bool has_subcalls;
+	bool has_rodata;
 
 	struct bpf_gen *gen_loader;
 
@@ -1168,12 +1173,8 @@ static struct bpf_object *bpf_object__new(const char *path,
 	obj->efile.obj_buf_sz = obj_buf_sz;
 	obj->efile.maps_shndx = -1;
 	obj->efile.btf_maps_shndx = -1;
-	obj->efile.data_shndx = -1;
-	obj->efile.rodata_shndx = -1;
-	obj->efile.bss_shndx = -1;
 	obj->efile.st_ops_shndx = -1;
 	obj->kconfig_map_idx = -1;
-	obj->rodata_map_idx = -1;
 
 	obj->kern_version = get_kernel_version();
 	obj->loaded = false;
@@ -1193,13 +1194,10 @@ static void bpf_object__elf_finish(struct bpf_object *obj)
 		obj->efile.elf = NULL;
 	}
 	obj->efile.symbols = NULL;
-	obj->efile.data = NULL;
-	obj->efile.rodata = NULL;
-	obj->efile.bss = NULL;
 	obj->efile.st_ops_data = NULL;
 
-	zfree(&obj->efile.reloc_sects);
-	obj->efile.nr_reloc_sects = 0;
+	zfree(&obj->efile.secs);
+	obj->efile.sec_cnt = 0;
 	zclose(obj->efile.fd);
 	obj->efile.obj_buf = NULL;
 	obj->efile.obj_buf_sz = 0;
@@ -1340,30 +1338,18 @@ static bool bpf_map_type__is_map_in_map(enum bpf_map_type type)
 static int find_elf_sec_sz(const struct bpf_object *obj, const char *name, __u32 *size)
 {
 	int ret = -ENOENT;
+	Elf_Data *data;
+	Elf_Scn *scn;
 
 	*size = 0;
-	if (!name) {
+	if (!name)
 		return -EINVAL;
-	} else if (!strcmp(name, DATA_SEC)) {
-		if (obj->efile.data)
-			*size = obj->efile.data->d_size;
-	} else if (!strcmp(name, BSS_SEC)) {
-		if (obj->efile.bss)
-			*size = obj->efile.bss->d_size;
-	} else if (!strcmp(name, RODATA_SEC)) {
-		if (obj->efile.rodata)
-			*size = obj->efile.rodata->d_size;
-	} else if (!strcmp(name, STRUCT_OPS_SEC)) {
-		if (obj->efile.st_ops_data)
-			*size = obj->efile.st_ops_data->d_size;
-	} else {
-		Elf_Scn *scn = elf_sec_by_name(obj, name);
-		Elf_Data *data = elf_sec_data(obj, scn);
 
-		if (data) {
-			ret = 0; /* found it */
-			*size = data->d_size;
-		}
+	scn = elf_sec_by_name(obj, name);
+	data = elf_sec_data(obj, scn);
+	if (data) {
+		ret = 0; /* found it */
+		*size = data->d_size;
 	}
 
 	return *size ? 0 : ret;
@@ -1516,34 +1502,39 @@ bpf_object__init_internal_map(struct bpf_object *obj, enum libbpf_map_type type,
 
 static int bpf_object__init_global_data_maps(struct bpf_object *obj)
 {
-	int err;
+	struct elf_sec_desc *sec_desc;
+	int err = 0, sec_idx;
 
 	/*
 	 * Populate obj->maps with libbpf internal maps.
 	 */
-	if (obj->efile.data_shndx >= 0) {
-		err = bpf_object__init_internal_map(obj, LIBBPF_MAP_DATA,
-						    obj->efile.data_shndx,
-						    obj->efile.data->d_buf,
-						    obj->efile.data->d_size);
-		if (err)
-			return err;
-	}
-	if (obj->efile.rodata_shndx >= 0) {
-		err = bpf_object__init_internal_map(obj, LIBBPF_MAP_RODATA,
-						    obj->efile.rodata_shndx,
-						    obj->efile.rodata->d_buf,
-						    obj->efile.rodata->d_size);
-		if (err)
-			return err;
-
-		obj->rodata_map_idx = obj->nr_maps - 1;
-	}
-	if (obj->efile.bss_shndx >= 0) {
-		err = bpf_object__init_internal_map(obj, LIBBPF_MAP_BSS,
-						    obj->efile.bss_shndx,
-						    NULL,
-						    obj->efile.bss->d_size);
+	for (sec_idx = 1; sec_idx < obj->efile.sec_cnt; sec_idx++) {
+		sec_desc = &obj->efile.secs[sec_idx];
+
+		switch (sec_desc->sec_type) {
+		case SEC_DATA:
+			err = bpf_object__init_internal_map(obj, LIBBPF_MAP_DATA,
+							    sec_idx,
+							    sec_desc->data->d_buf,
+							    sec_desc->data->d_size);
+			break;
+		case SEC_RODATA:
+			obj->has_rodata = true;
+			err = bpf_object__init_internal_map(obj, LIBBPF_MAP_RODATA,
+							    sec_idx,
+							    sec_desc->data->d_buf,
+							    sec_desc->data->d_size);
+			break;
+		case SEC_BSS:
+			err = bpf_object__init_internal_map(obj, LIBBPF_MAP_BSS,
+							    sec_idx,
+							    NULL,
+							    sec_desc->data->d_size);
+			break;
+		default:
+			/* skip */
+			break;
+		}
 		if (err)
 			return err;
 	}
@@ -3123,6 +3114,7 @@ static int cmp_progs(const void *_a, const void *_b)
 
 static int bpf_object__elf_collect(struct bpf_object *obj)
 {
+	struct elf_sec_desc *sec_desc;
 	Elf *elf = obj->efile.elf;
 	Elf_Data *btf_ext_data = NULL;
 	Elf_Data *btf_data = NULL;
@@ -3132,6 +3124,15 @@ static int bpf_object__elf_collect(struct bpf_object *obj)
 	Elf_Scn *scn;
 	Elf64_Shdr *sh;
 
+	/* ELF section indices are 1-based, so allocate +1 element to keep
+	 * indexing simple. Also include 0th invalid section into sec_cnt for
+	 * simpler and more traditional iteration logic.
+	 */
+	obj->efile.sec_cnt = 1 + obj->efile.ehdr->e_shnum;
+	obj->efile.secs = calloc(obj->efile.sec_cnt, sizeof(*obj->efile.secs));
+	if (!obj->efile.secs)
+		return -ENOMEM;
+
 	/* a bunch of ELF parsing functionality depends on processing symbols,
 	 * so do the first pass and find the symbol table
 	 */
@@ -3151,8 +3152,10 @@ static int bpf_object__elf_collect(struct bpf_object *obj)
 			if (!data)
 				return -LIBBPF_ERRNO__FORMAT;
 
+			idx = elf_ndxscn(scn);
+
 			obj->efile.symbols = data;
-			obj->efile.symbols_shndx = elf_ndxscn(scn);
+			obj->efile.symbols_shndx = idx;
 			obj->efile.strtabidx = sh->sh_link;
 		}
 	}
@@ -3165,7 +3168,8 @@ static int bpf_object__elf_collect(struct bpf_object *obj)
 
 	scn = NULL;
 	while ((scn = elf_nextscn(elf, scn)) != NULL) {
-		idx++;
+		idx = elf_ndxscn(scn);
+		sec_desc = &obj->efile.secs[idx];
 
 		sh = elf_sec_hdr(obj, scn);
 		if (!sh)
@@ -3213,11 +3217,13 @@ static int bpf_object__elf_collect(struct bpf_object *obj)
 				if (err)
 					return err;
 			} else if (strcmp(name, DATA_SEC) == 0) {
-				obj->efile.data = data;
-				obj->efile.data_shndx = idx;
+				sec_desc->sec_type = SEC_DATA;
+				sec_desc->shdr = sh;
+				sec_desc->data = data;
 			} else if (strcmp(name, RODATA_SEC) == 0) {
-				obj->efile.rodata = data;
-				obj->efile.rodata_shndx = idx;
+				sec_desc->sec_type = SEC_RODATA;
+				sec_desc->shdr = sh;
+				sec_desc->data = data;
 			} else if (strcmp(name, STRUCT_OPS_SEC) == 0) {
 				obj->efile.st_ops_data = data;
 				obj->efile.st_ops_shndx = idx;
@@ -3226,33 +3232,25 @@ static int bpf_object__elf_collect(struct bpf_object *obj)
 					idx, name);
 			}
 		} else if (sh->sh_type == SHT_REL) {
-			int nr_sects = obj->efile.nr_reloc_sects;
-			void *sects = obj->efile.reloc_sects;
-			int sec = sh->sh_info; /* points to other section */
+			int targ_sec_idx = sh->sh_info; /* points to other section */
 
 			/* Only do relo for section with exec instructions */
-			if (!section_have_execinstr(obj, sec) &&
+			if (!section_have_execinstr(obj, targ_sec_idx) &&
 			    strcmp(name, ".rel" STRUCT_OPS_SEC) &&
 			    strcmp(name, ".rel" MAPS_ELF_SEC)) {
 				pr_info("elf: skipping relo section(%d) %s for section(%d) %s\n",
-					idx, name, sec,
-					elf_sec_name(obj, elf_sec_by_idx(obj, sec)) ?: "<?>");
+					idx, name, targ_sec_idx,
+					elf_sec_name(obj, elf_sec_by_idx(obj, targ_sec_idx)) ?: "<?>");
 				continue;
 			}
 
-			sects = libbpf_reallocarray(sects, nr_sects + 1,
-						    sizeof(*obj->efile.reloc_sects));
-			if (!sects)
-				return -ENOMEM;
-
-			obj->efile.reloc_sects = sects;
-			obj->efile.nr_reloc_sects++;
-
-			obj->efile.reloc_sects[nr_sects].shdr = sh;
-			obj->efile.reloc_sects[nr_sects].data = data;
+			sec_desc->sec_type = SEC_RELO;
+			sec_desc->shdr = sh;
+			sec_desc->data = data;
 		} else if (sh->sh_type == SHT_NOBITS && strcmp(name, BSS_SEC) == 0) {
-			obj->efile.bss = data;
-			obj->efile.bss_shndx = idx;
+			sec_desc->sec_type = SEC_BSS;
+			sec_desc->shdr = sh;
+			sec_desc->data = data;
 		} else {
 			pr_info("elf: skipping section(%d) %s (size %zu)\n", idx, name,
 				(size_t)sh->sh_size);
@@ -3732,9 +3730,14 @@ bpf_object__find_program_by_name(const struct bpf_object *obj,
 static bool bpf_object__shndx_is_data(const struct bpf_object *obj,
 				      int shndx)
 {
-	return shndx == obj->efile.data_shndx ||
-	       shndx == obj->efile.bss_shndx ||
-	       shndx == obj->efile.rodata_shndx;
+	switch (obj->efile.secs[shndx].sec_type) {
+	case SEC_BSS:
+	case SEC_DATA:
+	case SEC_RODATA:
+		return true;
+	default:
+		return false;
+	}
 }
 
 static bool bpf_object__shndx_is_maps(const struct bpf_object *obj,
@@ -3747,16 +3750,19 @@ static bool bpf_object__shndx_is_maps(const struct bpf_object *obj,
 static enum libbpf_map_type
 bpf_object__section_to_libbpf_map_type(const struct bpf_object *obj, int shndx)
 {
-	if (shndx == obj->efile.data_shndx)
-		return LIBBPF_MAP_DATA;
-	else if (shndx == obj->efile.bss_shndx)
+	if (shndx == obj->efile.symbols_shndx)
+		return LIBBPF_MAP_KCONFIG;
+
+	switch (obj->efile.secs[shndx].sec_type) {
+	case SEC_BSS:
 		return LIBBPF_MAP_BSS;
-	else if (shndx == obj->efile.rodata_shndx)
+	case SEC_DATA:
+		return LIBBPF_MAP_DATA;
+	case SEC_RODATA:
 		return LIBBPF_MAP_RODATA;
-	else if (shndx == obj->efile.symbols_shndx)
-		return LIBBPF_MAP_KCONFIG;
-	else
+	default:
 		return LIBBPF_MAP_UNSPEC;
+	}
 }
 
 static int bpf_program__record_reloc(struct bpf_program *prog,
@@ -3892,7 +3898,7 @@ static int bpf_program__record_reloc(struct bpf_program *prog,
 	}
 	for (map_idx = 0; map_idx < nr_maps; map_idx++) {
 		map = &obj->maps[map_idx];
-		if (map->libbpf_type != type)
+		if (map->libbpf_type != type || map->sec_idx != sym->st_shndx)
 			continue;
 		pr_debug("prog '%s': found data map %zd (%s, sec %d, off %zu) for insn %u\n",
 			 prog->name, map_idx, map->name, map->sec_idx,
@@ -6205,10 +6211,18 @@ static int bpf_object__collect_relos(struct bpf_object *obj)
 {
 	int i, err;
 
-	for (i = 0; i < obj->efile.nr_reloc_sects; i++) {
-		Elf64_Shdr *shdr = obj->efile.reloc_sects[i].shdr;
-		Elf_Data *data = obj->efile.reloc_sects[i].data;
-		int idx = shdr->sh_info;
+	for (i = 0; i < obj->efile.sec_cnt; i++) {
+		struct elf_sec_desc *sec_desc = &obj->efile.secs[i];
+		Elf64_Shdr *shdr;
+		Elf_Data *data;
+		int idx;
+
+		if (sec_desc->sec_type != SEC_RELO)
+			continue;
+
+		shdr = sec_desc->shdr;
+		data = sec_desc->data;
+		idx = shdr->sh_info;
 
 		if (shdr->sh_type != SHT_REL) {
 			pr_warn("internal error at %d\n", __LINE__);
@@ -6331,6 +6345,7 @@ load_program(struct bpf_program *prog, struct bpf_insn *insns, int insns_cnt,
 	     char *license, __u32 kern_version, int *pfd)
 {
 	struct bpf_prog_load_params load_attr = {};
+	struct bpf_object *obj = prog->obj;
 	char *cp, errmsg[STRERR_BUFSIZE];
 	size_t log_buf_size = 0;
 	char *log_buf = NULL;
@@ -6351,7 +6366,7 @@ load_program(struct bpf_program *prog, struct bpf_insn *insns, int insns_cnt,
 
 	load_attr.prog_type = prog->type;
 	load_attr.expected_attach_type = prog->expected_attach_type;
-	if (kernel_supports(prog->obj, FEAT_PROG_NAME))
+	if (kernel_supports(obj, FEAT_PROG_NAME))
 		load_attr.name = prog->name;
 	load_attr.insns = insns;
 	load_attr.insn_cnt = insns_cnt;
@@ -6364,8 +6379,8 @@ load_program(struct bpf_program *prog, struct bpf_insn *insns, int insns_cnt,
 	load_attr.prog_ifindex = prog->prog_ifindex;
 
 	/* specify func_info/line_info only if kernel supports them */
-	btf_fd = bpf_object__btf_fd(prog->obj);
-	if (btf_fd >= 0 && kernel_supports(prog->obj, FEAT_BTF_FUNC)) {
+	btf_fd = bpf_object__btf_fd(obj);
+	if (btf_fd >= 0 && kernel_supports(obj, FEAT_BTF_FUNC)) {
 		load_attr.prog_btf_fd = btf_fd;
 		load_attr.func_info = prog->func_info;
 		load_attr.func_info_rec_size = prog->func_info_rec_size;
@@ -6376,7 +6391,7 @@ load_program(struct bpf_program *prog, struct bpf_insn *insns, int insns_cnt,
 	}
 	load_attr.log_level = prog->log_level;
 	load_attr.prog_flags = prog->prog_flags;
-	load_attr.fd_array = prog->obj->fd_array;
+	load_attr.fd_array = obj->fd_array;
 
 	/* adjust load_attr if sec_def provides custom preload callback */
 	if (prog->sec_def && prog->sec_def->preload_fn) {
@@ -6388,9 +6403,9 @@ load_program(struct bpf_program *prog, struct bpf_insn *insns, int insns_cnt,
 		}
 	}
 
-	if (prog->obj->gen_loader) {
-		bpf_gen__prog_load(prog->obj->gen_loader, &load_attr,
-				   prog - prog->obj->programs);
+	if (obj->gen_loader) {
+		bpf_gen__prog_load(obj->gen_loader, &load_attr,
+				   prog - obj->programs);
 		*pfd = -1;
 		return 0;
 	}
@@ -6411,16 +6426,21 @@ retry_load:
 		if (log_buf && load_attr.log_level)
 			pr_debug("verifier log:\n%s", log_buf);
 
-		if (prog->obj->rodata_map_idx >= 0 &&
-		    kernel_supports(prog->obj, FEAT_PROG_BIND_MAP)) {
-			struct bpf_map *rodata_map =
-				&prog->obj->maps[prog->obj->rodata_map_idx];
+		if (obj->has_rodata && kernel_supports(obj, FEAT_PROG_BIND_MAP)) {
+			struct bpf_map *map;
+			int i;
+
+			for (i = 0; i < obj->nr_maps; i++) {
+				map = &prog->obj->maps[i];
+				if (map->libbpf_type != LIBBPF_MAP_RODATA)
+					continue;
 
-			if (bpf_prog_bind_map(ret, bpf_map__fd(rodata_map), NULL)) {
-				cp = libbpf_strerror_r(errno, errmsg, sizeof(errmsg));
-				pr_warn("prog '%s': failed to bind .rodata map: %s\n",
-					prog->name, cp);
-				/* Don't fail hard if can't bind rodata. */
+				if (bpf_prog_bind_map(ret, bpf_map__fd(map), NULL)) {
+					cp = libbpf_strerror_r(errno, errmsg, sizeof(errmsg));
+					pr_warn("prog '%s': failed to bind .rodata map: %s\n",
+						prog->name, cp);
+					/* Don't fail hard if can't bind rodata. */
+				}
 			}
 		}
 
-- 
cgit v1.2.3


From 8654b4d35e6c915ef456c14320ec8720383e81a7 Mon Sep 17 00:00:00 2001
From: Andrii Nakryiko <andrii@kernel.org>
Date: Wed, 20 Oct 2021 18:43:59 -0700
Subject: bpftool: Support multiple .rodata/.data internal maps in skeleton

Remove the assumption about only single instance of each of .rodata and
.data internal maps. Nothing changes for '.rodata' and '.data' maps, but new
'.rodata.something' map will get 'rodata_something' section in BPF
skeleton for them (as well as having struct bpf_map * field in maps
section with the same field name).

Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Song Liu <songliubraving@fb.com>
Link: https://lore.kernel.org/bpf/20211021014404.2635234-6-andrii@kernel.org
---
 tools/bpf/bpftool/gen.c | 107 +++++++++++++++++++++++++++---------------------
 1 file changed, 60 insertions(+), 47 deletions(-)

(limited to 'tools')

diff --git a/tools/bpf/bpftool/gen.c b/tools/bpf/bpftool/gen.c
index b2ffc18eafc1..59afe9a2ca3c 100644
--- a/tools/bpf/bpftool/gen.c
+++ b/tools/bpf/bpftool/gen.c
@@ -33,6 +33,11 @@ static void sanitize_identifier(char *name)
 			name[i] = '_';
 }
 
+static bool str_has_prefix(const char *str, const char *prefix)
+{
+	return strncmp(str, prefix, strlen(prefix)) == 0;
+}
+
 static bool str_has_suffix(const char *str, const char *suffix)
 {
 	size_t i, n1 = strlen(str), n2 = strlen(suffix);
@@ -67,23 +72,47 @@ static void get_header_guard(char *guard, const char *obj_name)
 		guard[i] = toupper(guard[i]);
 }
 
-static const char *get_map_ident(const struct bpf_map *map)
+static bool get_map_ident(const struct bpf_map *map, char *buf, size_t buf_sz)
 {
+	static const char *sfxs[] = { ".data", ".rodata", ".bss", ".kconfig" };
 	const char *name = bpf_map__name(map);
+	int i, n;
+
+	if (!bpf_map__is_internal(map)) {
+		snprintf(buf, buf_sz, "%s", name);
+		return true;
+	}
+
+	for  (i = 0, n = ARRAY_SIZE(sfxs); i < n; i++) {
+		const char *sfx = sfxs[i], *p;
+
+		p = strstr(name, sfx);
+		if (p) {
+			snprintf(buf, buf_sz, "%s", p + 1);
+			sanitize_identifier(buf);
+			return true;
+		}
+	}
 
-	if (!bpf_map__is_internal(map))
-		return name;
-
-	if (str_has_suffix(name, ".data"))
-		return "data";
-	else if (str_has_suffix(name, ".rodata"))
-		return "rodata";
-	else if (str_has_suffix(name, ".bss"))
-		return "bss";
-	else if (str_has_suffix(name, ".kconfig"))
-		return "kconfig";
-	else
-		return NULL;
+	return false;
+}
+
+static bool get_datasec_ident(const char *sec_name, char *buf, size_t buf_sz)
+{
+	static const char *pfxs[] = { ".data", ".rodata", ".bss", ".kconfig" };
+	int i, n;
+
+	for  (i = 0, n = ARRAY_SIZE(pfxs); i < n; i++) {
+		const char *pfx = pfxs[i];
+
+		if (str_has_prefix(sec_name, pfx)) {
+			snprintf(buf, buf_sz, "%s", sec_name + 1);
+			sanitize_identifier(buf);
+			return true;
+		}
+	}
+
+	return false;
 }
 
 static void codegen_btf_dump_printf(void *ctx, const char *fmt, va_list args)
@@ -100,24 +129,14 @@ static int codegen_datasec_def(struct bpf_object *obj,
 	const char *sec_name = btf__name_by_offset(btf, sec->name_off);
 	const struct btf_var_secinfo *sec_var = btf_var_secinfos(sec);
 	int i, err, off = 0, pad_cnt = 0, vlen = btf_vlen(sec);
-	const char *sec_ident;
-	char var_ident[256];
+	char var_ident[256], sec_ident[256];
 	bool strip_mods = false;
 
-	if (strcmp(sec_name, ".data") == 0) {
-		sec_ident = "data";
-		strip_mods = true;
-	} else if (strcmp(sec_name, ".bss") == 0) {
-		sec_ident = "bss";
-		strip_mods = true;
-	} else if (strcmp(sec_name, ".rodata") == 0) {
-		sec_ident = "rodata";
-		strip_mods = true;
-	} else if (strcmp(sec_name, ".kconfig") == 0) {
-		sec_ident = "kconfig";
-	} else {
+	if (!get_datasec_ident(sec_name, sec_ident, sizeof(sec_ident)))
 		return 0;
-	}
+
+	if (strcmp(sec_name, ".kconfig") != 0)
+		strip_mods = true;
 
 	printf("	struct %s__%s {\n", obj_name, sec_ident);
 	for (i = 0; i < vlen; i++, sec_var++) {
@@ -385,6 +404,7 @@ static void codegen_destroy(struct bpf_object *obj, const char *obj_name)
 {
 	struct bpf_program *prog;
 	struct bpf_map *map;
+	char ident[256];
 
 	codegen("\
 		\n\
@@ -405,10 +425,7 @@ static void codegen_destroy(struct bpf_object *obj, const char *obj_name)
 	}
 
 	bpf_object__for_each_map(map, obj) {
-		const char *ident;
-
-		ident = get_map_ident(map);
-		if (!ident)
+		if (!get_map_ident(map, ident, sizeof(ident)))
 			continue;
 		if (bpf_map__is_internal(map) &&
 		    (bpf_map__def(map)->map_flags & BPF_F_MMAPABLE))
@@ -432,6 +449,7 @@ static int gen_trace(struct bpf_object *obj, const char *obj_name, const char *h
 	struct bpf_object_load_attr load_attr = {};
 	DECLARE_LIBBPF_OPTS(gen_loader_opts, opts);
 	struct bpf_map *map;
+	char ident[256];
 	int err = 0;
 
 	err = bpf_object__gen_loader(obj, &opts);
@@ -477,12 +495,10 @@ static int gen_trace(struct bpf_object *obj, const char *obj_name, const char *h
 		",
 		obj_name, opts.data_sz);
 	bpf_object__for_each_map(map, obj) {
-		const char *ident;
 		const void *mmap_data = NULL;
 		size_t mmap_size = 0;
 
-		ident = get_map_ident(map);
-		if (!ident)
+		if (!get_map_ident(map, ident, sizeof(ident)))
 			continue;
 
 		if (!bpf_map__is_internal(map) ||
@@ -544,15 +560,15 @@ static int gen_trace(struct bpf_object *obj, const char *obj_name, const char *h
 				return err;				    \n\
 		", obj_name);
 	bpf_object__for_each_map(map, obj) {
-		const char *ident, *mmap_flags;
+		const char *mmap_flags;
 
-		ident = get_map_ident(map);
-		if (!ident)
+		if (!get_map_ident(map, ident, sizeof(ident)))
 			continue;
 
 		if (!bpf_map__is_internal(map) ||
 		    !(bpf_map__def(map)->map_flags & BPF_F_MMAPABLE))
 			continue;
+
 		if (bpf_map__def(map)->map_flags & BPF_F_RDONLY_PROG)
 			mmap_flags = "PROT_READ";
 		else
@@ -602,7 +618,8 @@ static int do_skeleton(int argc, char **argv)
 	DECLARE_LIBBPF_OPTS(bpf_object_open_opts, opts);
 	char obj_name[MAX_OBJ_NAME_LEN] = "", *obj_data;
 	struct bpf_object *obj = NULL;
-	const char *file, *ident;
+	const char *file;
+	char ident[256];
 	struct bpf_program *prog;
 	int fd, err = -1;
 	struct bpf_map *map;
@@ -673,8 +690,7 @@ static int do_skeleton(int argc, char **argv)
 	}
 
 	bpf_object__for_each_map(map, obj) {
-		ident = get_map_ident(map);
-		if (!ident) {
+		if (!get_map_ident(map, ident, sizeof(ident))) {
 			p_err("ignoring unrecognized internal map '%s'...",
 			      bpf_map__name(map));
 			continue;
@@ -727,8 +743,7 @@ static int do_skeleton(int argc, char **argv)
 	if (map_cnt) {
 		printf("\tstruct {\n");
 		bpf_object__for_each_map(map, obj) {
-			ident = get_map_ident(map);
-			if (!ident)
+			if (!get_map_ident(map, ident, sizeof(ident)))
 				continue;
 			if (use_loader)
 				printf("\t\tstruct bpf_map_desc %s;\n", ident);
@@ -897,9 +912,7 @@ static int do_skeleton(int argc, char **argv)
 		);
 		i = 0;
 		bpf_object__for_each_map(map, obj) {
-			ident = get_map_ident(map);
-
-			if (!ident)
+			if (!get_map_ident(map, ident, sizeof(ident)))
 				continue;
 
 			codegen("\
-- 
cgit v1.2.3


From ef9356d392f980b3b192668fa05b2eaaad127da1 Mon Sep 17 00:00:00 2001
From: Andrii Nakryiko <andrii@kernel.org>
Date: Wed, 20 Oct 2021 18:44:00 -0700
Subject: bpftool: Improve skeleton generation for data maps without DATASEC
 type

It can happen that some data sections (e.g., .rodata.cst16, containing
compiler populated string constants) won't have a corresponding BTF
DATASEC type. Now that libbpf supports .rodata.* and .data.* sections,
situation like that will cause invalid BPF skeleton to be generated that
won't compile successfully, as some parts of skeleton would assume
memory-mapped struct definitions for each special data section.

Fix this by generating empty struct definitions for such data sections.

Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Song Liu <songliubraving@fb.com>
Link: https://lore.kernel.org/bpf/20211021014404.2635234-7-andrii@kernel.org
---
 tools/bpf/bpftool/gen.c | 51 +++++++++++++++++++++++++++++++++++++++++++------
 1 file changed, 45 insertions(+), 6 deletions(-)

(limited to 'tools')

diff --git a/tools/bpf/bpftool/gen.c b/tools/bpf/bpftool/gen.c
index 59afe9a2ca3c..c446405ab73f 100644
--- a/tools/bpf/bpftool/gen.c
+++ b/tools/bpf/bpftool/gen.c
@@ -213,22 +213,61 @@ static int codegen_datasecs(struct bpf_object *obj, const char *obj_name)
 	struct btf *btf = bpf_object__btf(obj);
 	int n = btf__get_nr_types(btf);
 	struct btf_dump *d;
+	struct bpf_map *map;
+	const struct btf_type *sec;
+	char sec_ident[256], map_ident[256];
 	int i, err = 0;
 
 	d = btf_dump__new(btf, NULL, NULL, codegen_btf_dump_printf);
 	if (IS_ERR(d))
 		return PTR_ERR(d);
 
-	for (i = 1; i <= n; i++) {
-		const struct btf_type *t = btf__type_by_id(btf, i);
+	bpf_object__for_each_map(map, obj) {
+		/* only generate definitions for memory-mapped internal maps */
+		if (!bpf_map__is_internal(map))
+			continue;
+		if (!(bpf_map__def(map)->map_flags & BPF_F_MMAPABLE))
+			continue;
 
-		if (!btf_is_datasec(t))
+		if (!get_map_ident(map, map_ident, sizeof(map_ident)))
 			continue;
 
-		err = codegen_datasec_def(obj, btf, d, t, obj_name);
-		if (err)
-			goto out;
+		sec = NULL;
+		for (i = 1; i <= n; i++) {
+			const struct btf_type *t = btf__type_by_id(btf, i);
+			const char *name;
+
+			if (!btf_is_datasec(t))
+				continue;
+
+			name = btf__str_by_offset(btf, t->name_off);
+			if (!get_datasec_ident(name, sec_ident, sizeof(sec_ident)))
+				continue;
+
+			if (strcmp(sec_ident, map_ident) == 0) {
+				sec = t;
+				break;
+			}
+		}
+
+		/* In some cases (e.g., sections like .rodata.cst16 containing
+		 * compiler allocated string constants only) there will be
+		 * special internal maps with no corresponding DATASEC BTF
+		 * type. In such case, generate empty structs for each such
+		 * map. It will still be memory-mapped and its contents
+		 * accessible from user-space through BPF skeleton.
+		 */
+		if (!sec) {
+			printf("	struct %s__%s {\n", obj_name, map_ident);
+			printf("	} *%s;\n", map_ident);
+		} else {
+			err = codegen_datasec_def(obj, btf, d, sec, obj_name);
+			if (err)
+				goto out;
+		}
 	}
+
+
 out:
 	btf_dump__free(d);
 	return err;
-- 
cgit v1.2.3


From aed659170a3171e425913ae259d46396fb9c10ef Mon Sep 17 00:00:00 2001
From: Andrii Nakryiko <andrii@kernel.org>
Date: Wed, 20 Oct 2021 18:44:01 -0700
Subject: libbpf: Support multiple .rodata.* and .data.* BPF maps

Add support for having multiple .rodata and .data data sections ([0]).
.rodata/.data are supported like the usual, but now also
.rodata.<whatever> and .data.<whatever> are also supported. Each such
section will get its own backing BPF_MAP_TYPE_ARRAY, just like
.rodata and .data.

Multiple .bss maps are not supported, as the whole '.bss' name is
confusing and might be deprecated soon, as well as user would need to
specify custom ELF section with SEC() attribute anyway, so might as well
stick to just .data.* and .rodata.* convention.

User-visible map name for such new maps is going to be just their ELF
section names.

  [0] https://github.com/libbpf/libbpf/issues/274

Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Song Liu <songliubraving@fb.com>
Link: https://lore.kernel.org/bpf/20211021014404.2635234-8-andrii@kernel.org
---
 tools/lib/bpf/libbpf.c | 130 ++++++++++++++++++++++++++++++++++++++-----------
 1 file changed, 101 insertions(+), 29 deletions(-)

(limited to 'tools')

diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index a7320d272b34..031f4611e0ff 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -370,15 +370,14 @@ enum libbpf_map_type {
 	LIBBPF_MAP_KCONFIG,
 };
 
-static const char * const libbpf_type_to_btf_name[] = {
-	[LIBBPF_MAP_DATA]	= DATA_SEC,
-	[LIBBPF_MAP_BSS]	= BSS_SEC,
-	[LIBBPF_MAP_RODATA]	= RODATA_SEC,
-	[LIBBPF_MAP_KCONFIG]	= KCONFIG_SEC,
-};
-
 struct bpf_map {
 	char *name;
+	/* real_name is defined for special internal maps (.rodata*,
+	 * .data*, .bss, .kconfig) and preserves their original ELF section
+	 * name. This is important to be be able to find corresponding BTF
+	 * DATASEC information.
+	 */
+	char *real_name;
 	int fd;
 	int sec_idx;
 	size_t sec_offset;
@@ -1429,17 +1428,55 @@ static size_t bpf_map_mmap_sz(const struct bpf_map *map)
 	return map_sz;
 }
 
-static char *internal_map_name(struct bpf_object *obj,
-			       enum libbpf_map_type type)
+static char *internal_map_name(struct bpf_object *obj, const char *real_name)
 {
 	char map_name[BPF_OBJ_NAME_LEN], *p;
-	const char *sfx = libbpf_type_to_btf_name[type];
-	int sfx_len = max((size_t)7, strlen(sfx));
-	int pfx_len = min((size_t)BPF_OBJ_NAME_LEN - sfx_len - 1,
-			  strlen(obj->name));
+	int pfx_len, sfx_len = max((size_t)7, strlen(real_name));
+
+	/* This is one of the more confusing parts of libbpf for various
+	 * reasons, some of which are historical. The original idea for naming
+	 * internal names was to include as much of BPF object name prefix as
+	 * possible, so that it can be distinguished from similar internal
+	 * maps of a different BPF object.
+	 * As an example, let's say we have bpf_object named 'my_object_name'
+	 * and internal map corresponding to '.rodata' ELF section. The final
+	 * map name advertised to user and to the kernel will be
+	 * 'my_objec.rodata', taking first 8 characters of object name and
+	 * entire 7 characters of '.rodata'.
+	 * Somewhat confusingly, if internal map ELF section name is shorter
+	 * than 7 characters, e.g., '.bss', we still reserve 7 characters
+	 * for the suffix, even though we only have 4 actual characters, and
+	 * resulting map will be called 'my_objec.bss', not even using all 15
+	 * characters allowed by the kernel. Oh well, at least the truncated
+	 * object name is somewhat consistent in this case. But if the map
+	 * name is '.kconfig', we'll still have entirety of '.kconfig' added
+	 * (8 chars) and thus will be left with only first 7 characters of the
+	 * object name ('my_obje'). Happy guessing, user, that the final map
+	 * name will be "my_obje.kconfig".
+	 * Now, with libbpf starting to support arbitrarily named .rodata.*
+	 * and .data.* data sections, it's possible that ELF section name is
+	 * longer than allowed 15 chars, so we now need to be careful to take
+	 * only up to 15 first characters of ELF name, taking no BPF object
+	 * name characters at all. So '.rodata.abracadabra' will result in
+	 * '.rodata.abracad' kernel and user-visible name.
+	 * We need to keep this convoluted logic intact for .data, .bss and
+	 * .rodata maps, but for new custom .data.custom and .rodata.custom
+	 * maps we use their ELF names as is, not prepending bpf_object name
+	 * in front. We still need to truncate them to 15 characters for the
+	 * kernel. Full name can be recovered for such maps by using DATASEC
+	 * BTF type associated with such map's value type, though.
+	 */
+	if (sfx_len >= BPF_OBJ_NAME_LEN)
+		sfx_len = BPF_OBJ_NAME_LEN - 1;
+
+	/* if there are two or more dots in map name, it's a custom dot map */
+	if (strchr(real_name + 1, '.') != NULL)
+		pfx_len = 0;
+	else
+		pfx_len = min((size_t)BPF_OBJ_NAME_LEN - sfx_len - 1, strlen(obj->name));
 
 	snprintf(map_name, sizeof(map_name), "%.*s%.*s", pfx_len, obj->name,
-		 sfx_len, libbpf_type_to_btf_name[type]);
+		 sfx_len, real_name);
 
 	/* sanitise map name to characters allowed by kernel */
 	for (p = map_name; *p && p < map_name + sizeof(map_name); p++)
@@ -1451,7 +1488,7 @@ static char *internal_map_name(struct bpf_object *obj,
 
 static int
 bpf_object__init_internal_map(struct bpf_object *obj, enum libbpf_map_type type,
-			      int sec_idx, void *data, size_t data_sz)
+			      const char *real_name, int sec_idx, void *data, size_t data_sz)
 {
 	struct bpf_map_def *def;
 	struct bpf_map *map;
@@ -1464,9 +1501,11 @@ bpf_object__init_internal_map(struct bpf_object *obj, enum libbpf_map_type type,
 	map->libbpf_type = type;
 	map->sec_idx = sec_idx;
 	map->sec_offset = 0;
-	map->name = internal_map_name(obj, type);
-	if (!map->name) {
-		pr_warn("failed to alloc map name\n");
+	map->real_name = strdup(real_name);
+	map->name = internal_map_name(obj, real_name);
+	if (!map->real_name || !map->name) {
+		zfree(&map->real_name);
+		zfree(&map->name);
 		return -ENOMEM;
 	}
 
@@ -1489,6 +1528,7 @@ bpf_object__init_internal_map(struct bpf_object *obj, enum libbpf_map_type type,
 		map->mmaped = NULL;
 		pr_warn("failed to alloc map '%s' content buffer: %d\n",
 			map->name, err);
+		zfree(&map->real_name);
 		zfree(&map->name);
 		return err;
 	}
@@ -1503,6 +1543,7 @@ bpf_object__init_internal_map(struct bpf_object *obj, enum libbpf_map_type type,
 static int bpf_object__init_global_data_maps(struct bpf_object *obj)
 {
 	struct elf_sec_desc *sec_desc;
+	const char *sec_name;
 	int err = 0, sec_idx;
 
 	/*
@@ -1513,21 +1554,24 @@ static int bpf_object__init_global_data_maps(struct bpf_object *obj)
 
 		switch (sec_desc->sec_type) {
 		case SEC_DATA:
+			sec_name = elf_sec_name(obj, elf_sec_by_idx(obj, sec_idx));
 			err = bpf_object__init_internal_map(obj, LIBBPF_MAP_DATA,
-							    sec_idx,
+							    sec_name, sec_idx,
 							    sec_desc->data->d_buf,
 							    sec_desc->data->d_size);
 			break;
 		case SEC_RODATA:
 			obj->has_rodata = true;
+			sec_name = elf_sec_name(obj, elf_sec_by_idx(obj, sec_idx));
 			err = bpf_object__init_internal_map(obj, LIBBPF_MAP_RODATA,
-							    sec_idx,
+							    sec_name, sec_idx,
 							    sec_desc->data->d_buf,
 							    sec_desc->data->d_size);
 			break;
 		case SEC_BSS:
+			sec_name = elf_sec_name(obj, elf_sec_by_idx(obj, sec_idx));
 			err = bpf_object__init_internal_map(obj, LIBBPF_MAP_BSS,
-							    sec_idx,
+							    sec_name, sec_idx,
 							    NULL,
 							    sec_desc->data->d_size);
 			break;
@@ -1831,7 +1875,7 @@ static int bpf_object__init_kconfig_map(struct bpf_object *obj)
 
 	map_sz = last_ext->kcfg.data_off + last_ext->kcfg.sz;
 	err = bpf_object__init_internal_map(obj, LIBBPF_MAP_KCONFIG,
-					    obj->efile.symbols_shndx,
+					    ".kconfig", obj->efile.symbols_shndx,
 					    NULL, map_sz);
 	if (err)
 		return err;
@@ -1931,7 +1975,7 @@ static int bpf_object__init_user_maps(struct bpf_object *obj, bool strict)
 
 		map->name = strdup(map_name);
 		if (!map->name) {
-			pr_warn("failed to alloc map name\n");
+			pr_warn("map '%s': failed to alloc map name\n", map_name);
 			return -ENOMEM;
 		}
 		pr_debug("map %d is \"%s\"\n", i, map->name);
@@ -3216,11 +3260,13 @@ static int bpf_object__elf_collect(struct bpf_object *obj)
 				err = bpf_object__add_programs(obj, data, name, idx);
 				if (err)
 					return err;
-			} else if (strcmp(name, DATA_SEC) == 0) {
+			} else if (strcmp(name, DATA_SEC) == 0 ||
+				   str_has_pfx(name, DATA_SEC ".")) {
 				sec_desc->sec_type = SEC_DATA;
 				sec_desc->shdr = sh;
 				sec_desc->data = data;
-			} else if (strcmp(name, RODATA_SEC) == 0) {
+			} else if (strcmp(name, RODATA_SEC) == 0 ||
+				   str_has_pfx(name, RODATA_SEC ".")) {
 				sec_desc->sec_type = SEC_RODATA;
 				sec_desc->shdr = sh;
 				sec_desc->data = data;
@@ -4060,8 +4106,7 @@ static int bpf_map_find_btf_info(struct bpf_object *obj, struct bpf_map *map)
 		 * LLVM annotates global data differently in BTF, that is,
 		 * only as '.data', '.bss' or '.rodata'.
 		 */
-		ret = btf__find_by_name(obj->btf,
-				libbpf_type_to_btf_name[map->libbpf_type]);
+		ret = btf__find_by_name(obj->btf, map->real_name);
 	}
 	if (ret < 0)
 		return ret;
@@ -7831,6 +7876,7 @@ static void bpf_map__destroy(struct bpf_map *map)
 	}
 
 	zfree(&map->name);
+	zfree(&map->real_name);
 	zfree(&map->pin_path);
 
 	if (map->fd >= 0)
@@ -8755,9 +8801,30 @@ const struct bpf_map_def *bpf_map__def(const struct bpf_map *map)
 	return map ? &map->def : libbpf_err_ptr(-EINVAL);
 }
 
+static bool map_uses_real_name(const struct bpf_map *map)
+{
+	/* Since libbpf started to support custom .data.* and .rodata.* maps,
+	 * their user-visible name differs from kernel-visible name. Users see
+	 * such map's corresponding ELF section name as a map name.
+	 * This check distinguishes .data/.rodata from .data.* and .rodata.*
+	 * maps to know which name has to be returned to the user.
+	 */
+	if (map->libbpf_type == LIBBPF_MAP_DATA && strcmp(map->real_name, DATA_SEC) != 0)
+		return true;
+	if (map->libbpf_type == LIBBPF_MAP_RODATA && strcmp(map->real_name, RODATA_SEC) != 0)
+		return true;
+	return false;
+}
+
 const char *bpf_map__name(const struct bpf_map *map)
 {
-	return map ? map->name : NULL;
+	if (!map)
+		return NULL;
+
+	if (map_uses_real_name(map))
+		return map->real_name;
+
+	return map->name;
 }
 
 enum bpf_map_type bpf_map__type(const struct bpf_map *map)
@@ -8976,7 +9043,12 @@ bpf_object__find_map_by_name(const struct bpf_object *obj, const char *name)
 	struct bpf_map *pos;
 
 	bpf_object__for_each_map(pos, obj) {
-		if (pos->name && !strcmp(pos->name, name))
+		if (map_uses_real_name(pos)) {
+			if (strcmp(pos->real_name, name) == 0)
+				return pos;
+			continue;
+		}
+		if (strcmp(pos->name, name) == 0)
 			return pos;
 	}
 	return errno = ENOENT, NULL;
-- 
cgit v1.2.3


From 30c5bd96476ced0d3e08372be5186ff7f421d10c Mon Sep 17 00:00:00 2001
From: Andrii Nakryiko <andrii@kernel.org>
Date: Wed, 20 Oct 2021 18:44:02 -0700
Subject: selftests/bpf: Demonstrate use of custom .rodata/.data sections

Enhance existing selftests to demonstrate the use of custom
.data/.rodata sections.

Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Song Liu <songliubraving@fb.com>
Link: https://lore.kernel.org/bpf/20211021014404.2635234-9-andrii@kernel.org
---
 tools/testing/selftests/bpf/prog_tests/skeleton.c | 29 +++++++++++++++++++++++
 tools/testing/selftests/bpf/progs/test_skeleton.c | 18 ++++++++++++++
 2 files changed, 47 insertions(+)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/prog_tests/skeleton.c b/tools/testing/selftests/bpf/prog_tests/skeleton.c
index fe1e204a65c6..180afd632f4c 100644
--- a/tools/testing/selftests/bpf/prog_tests/skeleton.c
+++ b/tools/testing/selftests/bpf/prog_tests/skeleton.c
@@ -16,10 +16,13 @@ void test_skeleton(void)
 	struct test_skeleton* skel;
 	struct test_skeleton__bss *bss;
 	struct test_skeleton__data *data;
+	struct test_skeleton__data_dyn *data_dyn;
 	struct test_skeleton__rodata *rodata;
+	struct test_skeleton__rodata_dyn *rodata_dyn;
 	struct test_skeleton__kconfig *kcfg;
 	const void *elf_bytes;
 	size_t elf_bytes_sz = 0;
+	int i;
 
 	skel = test_skeleton__open();
 	if (CHECK(!skel, "skel_open", "failed to open skeleton\n"))
@@ -30,7 +33,12 @@ void test_skeleton(void)
 
 	bss = skel->bss;
 	data = skel->data;
+	data_dyn = skel->data_dyn;
 	rodata = skel->rodata;
+	rodata_dyn = skel->rodata_dyn;
+
+	ASSERT_STREQ(bpf_map__name(skel->maps.rodata_dyn), ".rodata.dyn", "rodata_dyn_name");
+	ASSERT_STREQ(bpf_map__name(skel->maps.data_dyn), ".data.dyn", "data_dyn_name");
 
 	/* validate values are pre-initialized correctly */
 	CHECK(data->in1 != -1, "in1", "got %d != exp %d\n", data->in1, -1);
@@ -46,6 +54,12 @@ void test_skeleton(void)
 	CHECK(rodata->in.in6 != 0, "in6", "got %d != exp %d\n", rodata->in.in6, 0);
 	CHECK(bss->out6 != 0, "out6", "got %d != exp %d\n", bss->out6, 0);
 
+	ASSERT_EQ(rodata_dyn->in_dynarr_sz, 0, "in_dynarr_sz");
+	for (i = 0; i < 4; i++)
+		ASSERT_EQ(rodata_dyn->in_dynarr[i], -(i + 1), "in_dynarr");
+	for (i = 0; i < 4; i++)
+		ASSERT_EQ(data_dyn->out_dynarr[i], i + 1, "out_dynarr");
+
 	/* validate we can pre-setup global variables, even in .bss */
 	data->in1 = 10;
 	data->in2 = 11;
@@ -53,6 +67,10 @@ void test_skeleton(void)
 	bss->in4 = 13;
 	rodata->in.in6 = 14;
 
+	rodata_dyn->in_dynarr_sz = 4;
+	for (i = 0; i < 4; i++)
+		rodata_dyn->in_dynarr[i] = i + 10;
+
 	err = test_skeleton__load(skel);
 	if (CHECK(err, "skel_load", "failed to load skeleton: %d\n", err))
 		goto cleanup;
@@ -64,6 +82,10 @@ void test_skeleton(void)
 	CHECK(bss->in4 != 13, "in4", "got %lld != exp %lld\n", bss->in4, 13LL);
 	CHECK(rodata->in.in6 != 14, "in6", "got %d != exp %d\n", rodata->in.in6, 14);
 
+	ASSERT_EQ(rodata_dyn->in_dynarr_sz, 4, "in_dynarr_sz");
+	for (i = 0; i < 4; i++)
+		ASSERT_EQ(rodata_dyn->in_dynarr[i], i + 10, "in_dynarr");
+
 	/* now set new values and attach to get them into outX variables */
 	data->in1 = 1;
 	data->in2 = 2;
@@ -73,6 +95,8 @@ void test_skeleton(void)
 	bss->in5.b = 6;
 	kcfg = skel->kconfig;
 
+	skel->data_read_mostly->read_mostly_var = 123;
+
 	err = test_skeleton__attach(skel);
 	if (CHECK(err, "skel_attach", "skeleton attach failed: %d\n", err))
 		goto cleanup;
@@ -93,6 +117,11 @@ void test_skeleton(void)
 	CHECK(bss->kern_ver != kcfg->LINUX_KERNEL_VERSION, "ext2",
 	      "got %d != exp %d\n", bss->kern_ver, kcfg->LINUX_KERNEL_VERSION);
 
+	for (i = 0; i < 4; i++)
+		ASSERT_EQ(data_dyn->out_dynarr[i], i + 10, "out_dynarr");
+
+	ASSERT_EQ(skel->bss->out_mostly_var, 123, "out_mostly_var");
+
 	elf_bytes = test_skeleton__elf_bytes(&elf_bytes_sz);
 	ASSERT_OK_PTR(elf_bytes, "elf_bytes");
 	ASSERT_GE(elf_bytes_sz, 0, "elf_bytes_sz");
diff --git a/tools/testing/selftests/bpf/progs/test_skeleton.c b/tools/testing/selftests/bpf/progs/test_skeleton.c
index 441fa1c552c8..1b1187d2967b 100644
--- a/tools/testing/selftests/bpf/progs/test_skeleton.c
+++ b/tools/testing/selftests/bpf/progs/test_skeleton.c
@@ -5,6 +5,8 @@
 #include <linux/bpf.h>
 #include <bpf/bpf_helpers.h>
 
+#define __read_mostly SEC(".data.read_mostly")
+
 struct s {
 	int a;
 	long long b;
@@ -40,9 +42,20 @@ int kern_ver = 0;
 
 struct s out5 = {};
 
+
+const volatile int in_dynarr_sz SEC(".rodata.dyn");
+const volatile int in_dynarr[4] SEC(".rodata.dyn") = { -1, -2, -3, -4 };
+
+int out_dynarr[4] SEC(".data.dyn") = { 1, 2, 3, 4 };
+
+int read_mostly_var __read_mostly;
+int out_mostly_var;
+
 SEC("raw_tp/sys_enter")
 int handler(const void *ctx)
 {
+	int i;
+
 	out1 = in1;
 	out2 = in2;
 	out3 = in3;
@@ -53,6 +66,11 @@ int handler(const void *ctx)
 	bpf_syscall = CONFIG_BPF_SYSCALL;
 	kern_ver = LINUX_KERNEL_VERSION;
 
+	for (i = 0; i < in_dynarr_sz; i++)
+		out_dynarr[i] = in_dynarr[i];
+
+	out_mostly_var = read_mostly_var;
+
 	return 0;
 }
 
-- 
cgit v1.2.3


From 26071635ac5ecd8276bf3bdfc3ea1128c93ac722 Mon Sep 17 00:00:00 2001
From: Andrii Nakryiko <andrii@kernel.org>
Date: Wed, 20 Oct 2021 18:44:03 -0700
Subject: libbpf: Simplify look up by name of internal maps

Map name that's assigned to internal maps (.rodata, .data, .bss, etc)
consist of a small prefix of bpf_object's name and ELF section name as
a suffix. This makes it hard for users to "guess" the name to use for
looking up by name with bpf_object__find_map_by_name() API.

One proposal was to drop object name prefix from the map name and just
use ".rodata", ".data", etc, names. One downside called out was that
when multiple BPF applications are active on the host, it will be hard
to distinguish between multiple instances of .rodata and know which BPF
object (app) they belong to. Having few first characters, while quite
limiting, still can give a bit of a clue, in general.

Note, though, that btf_value_type_id for such global data maps (ARRAY)
points to DATASEC type, which encodes full ELF name, so tools like
bpftool can take advantage of this fact to "recover" full original name
of the map. This is also the reason why for custom .data.* and .rodata.*
maps libbpf uses only their ELF names and doesn't prepend object name at
all.

Another downside of such approach is that it is not backwards compatible
and, among direct use of bpf_object__find_map_by_name() API, will break
any BPF skeleton generated using bpftool that was compiled with older
libbpf version.

Instead of causing all this pain, libbpf will still generate map name
using a combination of object name and ELF section name, but it will
allow looking such maps up by their natural names, which correspond to
their respective ELF section names. This means non-truncated ELF section
names longer than 15 characters are going to be expected and supported.

With such set up, we get the best of both worlds: leave small bits of
a clue about BPF application that instantiated such maps, as well as
making it easy for user apps to lookup such maps at runtime. In this
sense it closes corresponding libbpf 1.0 issue ([0]).

BPF skeletons will continue using full names for lookups.

  [0] Closes: https://github.com/libbpf/libbpf/issues/275

Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Song Liu <songliubraving@fb.com>
Link: https://lore.kernel.org/bpf/20211021014404.2635234-10-andrii@kernel.org
---
 tools/lib/bpf/libbpf.c | 10 ++++++++++
 1 file changed, 10 insertions(+)

(limited to 'tools')

diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 031f4611e0ff..db6e48014839 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -9043,6 +9043,16 @@ bpf_object__find_map_by_name(const struct bpf_object *obj, const char *name)
 	struct bpf_map *pos;
 
 	bpf_object__for_each_map(pos, obj) {
+		/* if it's a special internal map name (which always starts
+		 * with dot) then check if that special name matches the
+		 * real map name (ELF section name)
+		 */
+		if (name[0] == '.') {
+			if (pos->real_name && strcmp(pos->real_name, name) == 0)
+				return pos;
+			continue;
+		}
+		/* otherwise map name has to be an exact match */
 		if (map_uses_real_name(pos)) {
 			if (strcmp(pos->real_name, name) == 0)
 				return pos;
-- 
cgit v1.2.3


From 4f2511e1990985103929ab799fb3ebca81969b77 Mon Sep 17 00:00:00 2001
From: Andrii Nakryiko <andrii@kernel.org>
Date: Wed, 20 Oct 2021 18:44:04 -0700
Subject: selftests/bpf: Switch to ".bss"/".rodata"/".data" lookups for
 internal maps

Utilize libbpf's feature of allowing to lookup internal maps by their
ELF section names. No need to guess or calculate the exact truncated
prefix taken from the object name.

Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Song Liu <songliubraving@fb.com>
Link: https://lore.kernel.org/bpf/20211021014404.2635234-11-andrii@kernel.org
---
 tools/testing/selftests/bpf/prog_tests/core_autosize.c    |  2 +-
 tools/testing/selftests/bpf/prog_tests/core_reloc.c       |  2 +-
 tools/testing/selftests/bpf/prog_tests/global_data.c      | 11 +++++++++--
 tools/testing/selftests/bpf/prog_tests/global_data_init.c |  2 +-
 tools/testing/selftests/bpf/prog_tests/kfree_skb.c        |  2 +-
 tools/testing/selftests/bpf/prog_tests/rdonly_maps.c      |  2 +-
 6 files changed, 14 insertions(+), 7 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/prog_tests/core_autosize.c b/tools/testing/selftests/bpf/prog_tests/core_autosize.c
index 3d4b2a358d47..2a0dac6394ef 100644
--- a/tools/testing/selftests/bpf/prog_tests/core_autosize.c
+++ b/tools/testing/selftests/bpf/prog_tests/core_autosize.c
@@ -163,7 +163,7 @@ void test_core_autosize(void)
 
 	usleep(1);
 
-	bss_map = bpf_object__find_map_by_name(skel->obj, "test_cor.bss");
+	bss_map = bpf_object__find_map_by_name(skel->obj, ".bss");
 	if (!ASSERT_OK_PTR(bss_map, "bss_map_find"))
 		goto cleanup;
 
diff --git a/tools/testing/selftests/bpf/prog_tests/core_reloc.c b/tools/testing/selftests/bpf/prog_tests/core_reloc.c
index 763302e63a29..cc50f8feeca3 100644
--- a/tools/testing/selftests/bpf/prog_tests/core_reloc.c
+++ b/tools/testing/selftests/bpf/prog_tests/core_reloc.c
@@ -867,7 +867,7 @@ void test_core_reloc(void)
 			goto cleanup;
 		}
 
-		data_map = bpf_object__find_map_by_name(obj, "test_cor.bss");
+		data_map = bpf_object__find_map_by_name(obj, ".bss");
 		if (CHECK(!data_map, "find_data_map", "data map not found\n"))
 			goto cleanup;
 
diff --git a/tools/testing/selftests/bpf/prog_tests/global_data.c b/tools/testing/selftests/bpf/prog_tests/global_data.c
index 9efa7e50eab2..afd8639f9a94 100644
--- a/tools/testing/selftests/bpf/prog_tests/global_data.c
+++ b/tools/testing/selftests/bpf/prog_tests/global_data.c
@@ -103,11 +103,18 @@ static void test_global_data_struct(struct bpf_object *obj, __u32 duration)
 static void test_global_data_rdonly(struct bpf_object *obj, __u32 duration)
 {
 	int err = -ENOMEM, map_fd, zero = 0;
-	struct bpf_map *map;
+	struct bpf_map *map, *map2;
 	__u8 *buff;
 
 	map = bpf_object__find_map_by_name(obj, "test_glo.rodata");
-	if (CHECK_FAIL(!map || !bpf_map__is_internal(map)))
+	if (!ASSERT_OK_PTR(map, "map"))
+		return;
+	if (!ASSERT_TRUE(bpf_map__is_internal(map), "is_internal"))
+		return;
+
+	/* ensure we can lookup internal maps by their ELF names */
+	map2 = bpf_object__find_map_by_name(obj, ".rodata");
+	if (!ASSERT_EQ(map, map2, "same_maps"))
 		return;
 
 	map_fd = bpf_map__fd(map);
diff --git a/tools/testing/selftests/bpf/prog_tests/global_data_init.c b/tools/testing/selftests/bpf/prog_tests/global_data_init.c
index ee46b11f1f9a..1db86eab101b 100644
--- a/tools/testing/selftests/bpf/prog_tests/global_data_init.c
+++ b/tools/testing/selftests/bpf/prog_tests/global_data_init.c
@@ -16,7 +16,7 @@ void test_global_data_init(void)
 	if (CHECK_FAIL(err))
 		return;
 
-	map = bpf_object__find_map_by_name(obj, "test_glo.rodata");
+	map = bpf_object__find_map_by_name(obj, ".rodata");
 	if (CHECK_FAIL(!map || !bpf_map__is_internal(map)))
 		goto out;
 
diff --git a/tools/testing/selftests/bpf/prog_tests/kfree_skb.c b/tools/testing/selftests/bpf/prog_tests/kfree_skb.c
index 032a322d51f2..01e51d16c8b8 100644
--- a/tools/testing/selftests/bpf/prog_tests/kfree_skb.c
+++ b/tools/testing/selftests/bpf/prog_tests/kfree_skb.c
@@ -93,7 +93,7 @@ void serial_test_kfree_skb(void)
 	if (CHECK(!fexit, "find_prog", "prog eth_type_trans not found\n"))
 		goto close_prog;
 
-	global_data = bpf_object__find_map_by_name(obj2, "kfree_sk.bss");
+	global_data = bpf_object__find_map_by_name(obj2, ".bss");
 	if (CHECK(!global_data, "find global data", "not found\n"))
 		goto close_prog;
 
diff --git a/tools/testing/selftests/bpf/prog_tests/rdonly_maps.c b/tools/testing/selftests/bpf/prog_tests/rdonly_maps.c
index 5f9eaa3ab584..fd5d2ddfb062 100644
--- a/tools/testing/selftests/bpf/prog_tests/rdonly_maps.c
+++ b/tools/testing/selftests/bpf/prog_tests/rdonly_maps.c
@@ -37,7 +37,7 @@ void test_rdonly_maps(void)
 	if (CHECK(err, "obj_load", "err %d errno %d\n", err, errno))
 		goto cleanup;
 
-	bss_map = bpf_object__find_map_by_name(obj, "test_rdo.bss");
+	bss_map = bpf_object__find_map_by_name(obj, ".bss");
 	if (CHECK(!bss_map, "find_bss_map", "failed\n"))
 		goto cleanup;
 
-- 
cgit v1.2.3


From fae1b05e6f0acf116f6450535b0e1c13051102d3 Mon Sep 17 00:00:00 2001
From: Andrii Nakryiko <andrii@kernel.org>
Date: Fri, 22 Oct 2021 12:25:02 -0700
Subject: libbpf: Fix the use of aligned attribute

Building libbpf sources out of kernel tree (in Github repo) we run into
compilation error due to unknown __aligned attribute. It must be coming
from some kernel header, which is not available to Github sources. Use
explicit __attribute__((aligned(16))) instead.

Fixes: 961632d54163 ("libbpf: Fix dumping non-aligned __int128")
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20211022192502.2975553-1-andrii@kernel.org
---
 tools/lib/bpf/btf_dump.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'tools')

diff --git a/tools/lib/bpf/btf_dump.c b/tools/lib/bpf/btf_dump.c
index e9e5801ece4c..3c19644b5fad 100644
--- a/tools/lib/bpf/btf_dump.c
+++ b/tools/lib/bpf/btf_dump.c
@@ -1676,7 +1676,7 @@ static int btf_dump_int_data(struct btf_dump *d,
 {
 	__u8 encoding = btf_int_encoding(t);
 	bool sign = encoding & BTF_INT_SIGNED;
-	char buf[16] __aligned(16);
+	char buf[16] __attribute__((aligned(16)));
 	int sz = t->size;
 
 	if (sz == 0 || sz > sizeof(buf)) {
-- 
cgit v1.2.3


From 57385ae31ff0ffa6e9c9ae39206740efdc7f5972 Mon Sep 17 00:00:00 2001
From: Andrii Nakryiko <andrii@kernel.org>
Date: Fri, 22 Oct 2021 13:13:42 -0700
Subject: selftests/bpf: Make perf_buffer selftests work on 4.9 kernel again

Recent change to use tp/syscalls/sys_enter_nanosleep for perf_buffer
selftests causes this selftest to fail on 4.9 kernel in libbpf CI ([0]):

  libbpf: prog 'handle_sys_enter': failed to attach to perf_event FD 6: Invalid argument
  libbpf: prog 'handle_sys_enter': failed to attach to tracepoint 'syscalls/sys_enter_nanosleep': Invalid argument

It's not exactly clear why, because perf_event itself is created for
this tracepoint, but I can't even compile 4.9 kernel locally, so it's
hard to figure this out. If anyone has better luck and would like to
help investigating this, I'd really appreciate this.

For now, unblock CI by switching back to raw_syscalls/sys_enter, but reduce
amount of unnecessary samples emitted by filter by process ID. Use
explicit ARRAY map for that to make it work on 4.9 as well, because
global data isn't yet supported there.

Fixes: aa274f98b269 ("selftests/bpf: Fix possible/online index mismatch in perf_buffer test")
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20211022201342.3490692-1-andrii@kernel.org
---
 tools/testing/selftests/bpf/prog_tests/perf_buffer.c |  5 +++++
 tools/testing/selftests/bpf/progs/test_perf_buffer.c | 20 ++++++++++++++++++--
 2 files changed, 23 insertions(+), 2 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/prog_tests/perf_buffer.c b/tools/testing/selftests/bpf/prog_tests/perf_buffer.c
index 0b0cd045979b..4e32f3586a75 100644
--- a/tools/testing/selftests/bpf/prog_tests/perf_buffer.c
+++ b/tools/testing/selftests/bpf/prog_tests/perf_buffer.c
@@ -46,6 +46,7 @@ int trigger_on_cpu(int cpu)
 void serial_test_perf_buffer(void)
 {
 	int err, on_len, nr_on_cpus = 0, nr_cpus, i, j;
+	int zero = 0, my_pid = getpid();
 	struct perf_buffer_opts pb_opts = {};
 	struct test_perf_buffer *skel;
 	cpu_set_t cpu_seen;
@@ -71,6 +72,10 @@ void serial_test_perf_buffer(void)
 	if (CHECK(!skel, "skel_load", "skeleton open/load failed\n"))
 		goto out_close;
 
+	err = bpf_map_update_elem(bpf_map__fd(skel->maps.my_pid_map), &zero, &my_pid, 0);
+	if (!ASSERT_OK(err, "my_pid_update"))
+		goto out_close;
+
 	/* attach probe */
 	err = test_perf_buffer__attach(skel);
 	if (CHECK(err, "attach_kprobe", "err %d\n", err))
diff --git a/tools/testing/selftests/bpf/progs/test_perf_buffer.c b/tools/testing/selftests/bpf/progs/test_perf_buffer.c
index a08874c5bdf2..17d5b67744d5 100644
--- a/tools/testing/selftests/bpf/progs/test_perf_buffer.c
+++ b/tools/testing/selftests/bpf/progs/test_perf_buffer.c
@@ -6,20 +6,36 @@
 #include <bpf/bpf_helpers.h>
 #include <bpf/bpf_tracing.h>
 
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__type(key, int);
+	__type(value, int);
+	__uint(max_entries, 1);
+} my_pid_map SEC(".maps");
+
 struct {
 	__uint(type, BPF_MAP_TYPE_PERF_EVENT_ARRAY);
 	__type(key, int);
 	__type(value, int);
 } perf_buf_map SEC(".maps");
 
-SEC("tp/syscalls/sys_enter_nanosleep")
+SEC("tp/raw_syscalls/sys_enter")
 int handle_sys_enter(void *ctx)
 {
+	int zero = 0, *my_pid, cur_pid;
 	int cpu = bpf_get_smp_processor_id();
 
+	my_pid = bpf_map_lookup_elem(&my_pid_map, &zero);
+	if (!my_pid)
+		return 1;
+
+	cur_pid = bpf_get_current_pid_tgid() >> 32;
+	if (cur_pid != *my_pid)
+		return 1;
+
 	bpf_perf_event_output(ctx, &perf_buf_map, BPF_F_CURRENT_CPU,
 			      &cpu, sizeof(cpu));
-	return 0;
+	return 1;
 }
 
 char _license[] SEC("license") = "GPL";
-- 
cgit v1.2.3


From 1000298c76830bc291358e98e8fa5baa3baa9b3a Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Mauricio=20V=C3=A1squez?= <mauricio@kinvolk.io>
Date: Fri, 22 Oct 2021 15:20:35 -0500
Subject: libbpf: Fix memory leak in btf__dedup()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Free btf_dedup if btf_ensure_modifiable() returns error.

Fixes: 919d2b1dbb07 ("libbpf: Allow modification of BTF and add btf__add_str API")
Signed-off-by: Mauricio Vásquez <mauricio@kinvolk.io>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20211022202035.48868-1-mauricio@kinvolk.io
---
 tools/lib/bpf/btf.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

(limited to 'tools')

diff --git a/tools/lib/bpf/btf.c b/tools/lib/bpf/btf.c
index 3a01c4b7f36a..85705c10f7b2 100644
--- a/tools/lib/bpf/btf.c
+++ b/tools/lib/bpf/btf.c
@@ -2991,8 +2991,10 @@ int btf__dedup(struct btf *btf, struct btf_ext *btf_ext,
 		return libbpf_err(-EINVAL);
 	}
 
-	if (btf_ensure_modifiable(btf))
-		return libbpf_err(-ENOMEM);
+	if (btf_ensure_modifiable(btf)) {
+		err = -ENOMEM;
+		goto done;
+	}
 
 	err = btf_dedup_prep(d);
 	if (err) {
-- 
cgit v1.2.3


From 6a886de070fad850d6cb74a787c9ed017303d9ac Mon Sep 17 00:00:00 2001
From: Hengqi Chen <hengqi.chen@gmail.com>
Date: Fri, 22 Oct 2021 21:06:19 +0800
Subject: libbpf: Add btf__type_cnt() and btf__raw_data() APIs

Add btf__type_cnt() and btf__raw_data() APIs and deprecate
btf__get_nr_type() and btf__get_raw_data() since the old APIs
don't follow the libbpf naming convention for getters which
omit 'get' in the name (see [0]). btf__raw_data() is just an
alias to the existing btf__get_raw_data(). btf__type_cnt()
now returns the number of all types of the BTF object
including 'void'.

  [0] Closes: https://github.com/libbpf/libbpf/issues/279

Signed-off-by: Hengqi Chen <hengqi.chen@gmail.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20211022130623.1548429-2-hengqi.chen@gmail.com
---
 tools/lib/bpf/btf.c      | 36 ++++++++++++++++++++++--------------
 tools/lib/bpf/btf.h      |  4 ++++
 tools/lib/bpf/btf_dump.c |  8 ++++----
 tools/lib/bpf/libbpf.c   | 36 ++++++++++++++++++------------------
 tools/lib/bpf/libbpf.map |  2 ++
 tools/lib/bpf/linker.c   | 28 ++++++++++++++--------------
 6 files changed, 64 insertions(+), 50 deletions(-)

(limited to 'tools')

diff --git a/tools/lib/bpf/btf.c b/tools/lib/bpf/btf.c
index 85705c10f7b2..66997d985ff8 100644
--- a/tools/lib/bpf/btf.c
+++ b/tools/lib/bpf/btf.c
@@ -57,7 +57,7 @@ struct btf {
 	 * representation is broken up into three independently allocated
 	 * memory regions to be able to modify them independently.
 	 * raw_data is nulled out at that point, but can be later allocated
-	 * and cached again if user calls btf__get_raw_data(), at which point
+	 * and cached again if user calls btf__raw_data(), at which point
 	 * raw_data will contain a contiguous copy of header, types, and
 	 * strings:
 	 *
@@ -435,6 +435,11 @@ __u32 btf__get_nr_types(const struct btf *btf)
 	return btf->start_id + btf->nr_types - 1;
 }
 
+__u32 btf__type_cnt(const struct btf *btf)
+{
+	return btf->start_id + btf->nr_types;
+}
+
 const struct btf *btf__base_btf(const struct btf *btf)
 {
 	return btf->base_btf;
@@ -466,8 +471,8 @@ static int determine_ptr_size(const struct btf *btf)
 	if (btf->base_btf && btf->base_btf->ptr_sz > 0)
 		return btf->base_btf->ptr_sz;
 
-	n = btf__get_nr_types(btf);
-	for (i = 1; i <= n; i++) {
+	n = btf__type_cnt(btf);
+	for (i = 1; i < n; i++) {
 		t = btf__type_by_id(btf, i);
 		if (!btf_is_int(t))
 			continue;
@@ -684,12 +689,12 @@ int btf__resolve_type(const struct btf *btf, __u32 type_id)
 
 __s32 btf__find_by_name(const struct btf *btf, const char *type_name)
 {
-	__u32 i, nr_types = btf__get_nr_types(btf);
+	__u32 i, nr_types = btf__type_cnt(btf);
 
 	if (!strcmp(type_name, "void"))
 		return 0;
 
-	for (i = 1; i <= nr_types; i++) {
+	for (i = 1; i < nr_types; i++) {
 		const struct btf_type *t = btf__type_by_id(btf, i);
 		const char *name = btf__name_by_offset(btf, t->name_off);
 
@@ -703,12 +708,12 @@ __s32 btf__find_by_name(const struct btf *btf, const char *type_name)
 static __s32 btf_find_by_name_kind(const struct btf *btf, int start_id,
 				   const char *type_name, __u32 kind)
 {
-	__u32 i, nr_types = btf__get_nr_types(btf);
+	__u32 i, nr_types = btf__type_cnt(btf);
 
 	if (kind == BTF_KIND_UNKN || !strcmp(type_name, "void"))
 		return 0;
 
-	for (i = start_id; i <= nr_types; i++) {
+	for (i = start_id; i < nr_types; i++) {
 		const struct btf_type *t = btf__type_by_id(btf, i);
 		const char *name;
 
@@ -781,7 +786,7 @@ static struct btf *btf_new_empty(struct btf *base_btf)
 
 	if (base_btf) {
 		btf->base_btf = base_btf;
-		btf->start_id = btf__get_nr_types(base_btf) + 1;
+		btf->start_id = btf__type_cnt(base_btf);
 		btf->start_str_off = base_btf->hdr->str_len;
 	}
 
@@ -831,7 +836,7 @@ static struct btf *btf_new(const void *data, __u32 size, struct btf *base_btf)
 
 	if (base_btf) {
 		btf->base_btf = base_btf;
-		btf->start_id = btf__get_nr_types(base_btf) + 1;
+		btf->start_id = btf__type_cnt(base_btf);
 		btf->start_str_off = base_btf->hdr->str_len;
 	}
 
@@ -1224,7 +1229,7 @@ err_out:
 	return NULL;
 }
 
-const void *btf__get_raw_data(const struct btf *btf_ro, __u32 *size)
+const void *btf__raw_data(const struct btf *btf_ro, __u32 *size)
 {
 	struct btf *btf = (struct btf *)btf_ro;
 	__u32 data_sz;
@@ -1232,7 +1237,7 @@ const void *btf__get_raw_data(const struct btf *btf_ro, __u32 *size)
 
 	data = btf_get_raw_data(btf, &data_sz, btf->swapped_endian);
 	if (!data)
-		return errno = -ENOMEM, NULL;
+		return errno = ENOMEM, NULL;
 
 	btf->raw_size = data_sz;
 	if (btf->swapped_endian)
@@ -1243,6 +1248,9 @@ const void *btf__get_raw_data(const struct btf *btf_ro, __u32 *size)
 	return data;
 }
 
+__attribute__((alias("btf__raw_data")))
+const void *btf__get_raw_data(const struct btf *btf, __u32 *size);
+
 const char *btf__str_by_offset(const struct btf *btf, __u32 offset)
 {
 	if (offset < btf->start_str_off)
@@ -1651,7 +1659,7 @@ int btf__add_btf(struct btf *btf, const struct btf *src_btf)
 	old_strs_len = btf->hdr->str_len;
 
 	data_sz = src_btf->hdr->type_len;
-	cnt = btf__get_nr_types(src_btf);
+	cnt = btf__type_cnt(src_btf) - 1;
 
 	/* pre-allocate enough memory for new types */
 	t = btf_add_type_mem(btf, data_sz);
@@ -1968,7 +1976,7 @@ int btf__add_union(struct btf *btf, const char *name, __u32 byte_sz)
 
 static struct btf_type *btf_last_type(struct btf *btf)
 {
-	return btf_type_by_id(btf, btf__get_nr_types(btf));
+	return btf_type_by_id(btf, btf__type_cnt(btf) - 1);
 }
 
 /*
@@ -3174,7 +3182,7 @@ static struct btf_dedup *btf_dedup_new(struct btf *btf, struct btf_ext *btf_ext,
 		goto done;
 	}
 
-	type_cnt = btf__get_nr_types(btf) + 1;
+	type_cnt = btf__type_cnt(btf);
 	d->map = malloc(sizeof(__u32) * type_cnt);
 	if (!d->map) {
 		err = -ENOMEM;
diff --git a/tools/lib/bpf/btf.h b/tools/lib/bpf/btf.h
index c9364be42035..bc005ba3ceec 100644
--- a/tools/lib/bpf/btf.h
+++ b/tools/lib/bpf/btf.h
@@ -132,7 +132,9 @@ LIBBPF_API __s32 btf__find_by_name(const struct btf *btf,
 				   const char *type_name);
 LIBBPF_API __s32 btf__find_by_name_kind(const struct btf *btf,
 					const char *type_name, __u32 kind);
+LIBBPF_DEPRECATED_SINCE(0, 7, "use btf__type_cnt() instead; note that btf__get_nr_types() == btf__type_cnt() - 1")
 LIBBPF_API __u32 btf__get_nr_types(const struct btf *btf);
+LIBBPF_API __u32 btf__type_cnt(const struct btf *btf);
 LIBBPF_API const struct btf *btf__base_btf(const struct btf *btf);
 LIBBPF_API const struct btf_type *btf__type_by_id(const struct btf *btf,
 						  __u32 id);
@@ -145,7 +147,9 @@ LIBBPF_API int btf__resolve_type(const struct btf *btf, __u32 type_id);
 LIBBPF_API int btf__align_of(const struct btf *btf, __u32 id);
 LIBBPF_API int btf__fd(const struct btf *btf);
 LIBBPF_API void btf__set_fd(struct btf *btf, int fd);
+LIBBPF_DEPRECATED_SINCE(0, 7, "use btf__raw_data() instead")
 LIBBPF_API const void *btf__get_raw_data(const struct btf *btf, __u32 *size);
+LIBBPF_API const void *btf__raw_data(const struct btf *btf, __u32 *size);
 LIBBPF_API const char *btf__name_by_offset(const struct btf *btf, __u32 offset);
 LIBBPF_API const char *btf__str_by_offset(const struct btf *btf, __u32 offset);
 LIBBPF_API int btf__get_map_kv_tids(const struct btf *btf, const char *map_name,
diff --git a/tools/lib/bpf/btf_dump.c b/tools/lib/bpf/btf_dump.c
index 3c19644b5fad..8e05ab44c22a 100644
--- a/tools/lib/bpf/btf_dump.c
+++ b/tools/lib/bpf/btf_dump.c
@@ -188,7 +188,7 @@ err:
 
 static int btf_dump_resize(struct btf_dump *d)
 {
-	int err, last_id = btf__get_nr_types(d->btf);
+	int err, last_id = btf__type_cnt(d->btf) - 1;
 
 	if (last_id <= d->last_id)
 		return 0;
@@ -262,7 +262,7 @@ int btf_dump__dump_type(struct btf_dump *d, __u32 id)
 {
 	int err, i;
 
-	if (id > btf__get_nr_types(d->btf))
+	if (id >= btf__type_cnt(d->btf))
 		return libbpf_err(-EINVAL);
 
 	err = btf_dump_resize(d);
@@ -294,11 +294,11 @@ int btf_dump__dump_type(struct btf_dump *d, __u32 id)
  */
 static int btf_dump_mark_referenced(struct btf_dump *d)
 {
-	int i, j, n = btf__get_nr_types(d->btf);
+	int i, j, n = btf__type_cnt(d->btf);
 	const struct btf_type *t;
 	__u16 vlen;
 
-	for (i = d->last_id + 1; i <= n; i++) {
+	for (i = d->last_id + 1; i < n; i++) {
 		t = btf__type_by_id(d->btf, i);
 		vlen = btf_vlen(t);
 
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index db6e48014839..eb102440a28a 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -2497,8 +2497,8 @@ static int bpf_object__init_user_btf_maps(struct bpf_object *obj, bool strict,
 		return -EINVAL;
 	}
 
-	nr_types = btf__get_nr_types(obj->btf);
-	for (i = 1; i <= nr_types; i++) {
+	nr_types = btf__type_cnt(obj->btf);
+	for (i = 1; i < nr_types; i++) {
 		t = btf__type_by_id(obj->btf, i);
 		if (!btf_is_datasec(t))
 			continue;
@@ -2579,7 +2579,7 @@ static void bpf_object__sanitize_btf(struct bpf_object *obj, struct btf *btf)
 	struct btf_type *t;
 	int i, j, vlen;
 
-	for (i = 1; i <= btf__get_nr_types(btf); i++) {
+	for (i = 1; i < btf__type_cnt(btf); i++) {
 		t = (struct btf_type *)btf__type_by_id(btf, i);
 
 		if ((!has_datasec && btf_is_var(t)) || (!has_decl_tag && btf_is_decl_tag(t))) {
@@ -2763,9 +2763,9 @@ sort_vars:
 static int btf_finalize_data(struct bpf_object *obj, struct btf *btf)
 {
 	int err = 0;
-	__u32 i, n = btf__get_nr_types(btf);
+	__u32 i, n = btf__type_cnt(btf);
 
-	for (i = 1; i <= n; i++) {
+	for (i = 1; i < n; i++) {
 		struct btf_type *t = btf_type_by_id(btf, i);
 
 		/* Loader needs to fix up some of the things compiler
@@ -2905,8 +2905,8 @@ static int bpf_object__sanitize_and_load_btf(struct bpf_object *obj)
 		if (!prog->mark_btf_static || !prog_is_subprog(obj, prog))
 			continue;
 
-		n = btf__get_nr_types(obj->btf);
-		for (j = 1; j <= n; j++) {
+		n = btf__type_cnt(obj->btf);
+		for (j = 1; j < n; j++) {
 			t = btf_type_by_id(obj->btf, j);
 			if (!btf_is_func(t) || btf_func_linkage(t) != BTF_FUNC_GLOBAL)
 				continue;
@@ -2926,7 +2926,7 @@ static int bpf_object__sanitize_and_load_btf(struct bpf_object *obj)
 		__u32 sz;
 
 		/* clone BTF to sanitize a copy and leave the original intact */
-		raw_data = btf__get_raw_data(obj->btf, &sz);
+		raw_data = btf__raw_data(obj->btf, &sz);
 		kern_btf = btf__new(raw_data, sz);
 		err = libbpf_get_error(kern_btf);
 		if (err)
@@ -2939,7 +2939,7 @@ static int bpf_object__sanitize_and_load_btf(struct bpf_object *obj)
 
 	if (obj->gen_loader) {
 		__u32 raw_size = 0;
-		const void *raw_data = btf__get_raw_data(kern_btf, &raw_size);
+		const void *raw_data = btf__raw_data(kern_btf, &raw_size);
 
 		if (!raw_data)
 			return -ENOMEM;
@@ -3350,8 +3350,8 @@ static int find_extern_btf_id(const struct btf *btf, const char *ext_name)
 	if (!btf)
 		return -ESRCH;
 
-	n = btf__get_nr_types(btf);
-	for (i = 1; i <= n; i++) {
+	n = btf__type_cnt(btf);
+	for (i = 1; i < n; i++) {
 		t = btf__type_by_id(btf, i);
 
 		if (!btf_is_var(t) && !btf_is_func(t))
@@ -3382,8 +3382,8 @@ static int find_extern_sec_btf_id(struct btf *btf, int ext_btf_id) {
 	if (!btf)
 		return -ESRCH;
 
-	n = btf__get_nr_types(btf);
-	for (i = 1; i <= n; i++) {
+	n = btf__type_cnt(btf);
+	for (i = 1; i < n; i++) {
 		t = btf__type_by_id(btf, i);
 
 		if (!btf_is_datasec(t))
@@ -3467,8 +3467,8 @@ static int find_int_btf_id(const struct btf *btf)
 	const struct btf_type *t;
 	int i, n;
 
-	n = btf__get_nr_types(btf);
-	for (i = 1; i <= n; i++) {
+	n = btf__type_cnt(btf);
+	for (i = 1; i < n; i++) {
 		t = btf__type_by_id(btf, i);
 
 		if (btf_is_int(t) && btf_int_bits(t) == 32)
@@ -5076,8 +5076,8 @@ static int bpf_core_add_cands(struct bpf_core_cand *local_cand,
 	size_t targ_essent_len;
 	int n, i;
 
-	n = btf__get_nr_types(targ_btf);
-	for (i = targ_start_id; i <= n; i++) {
+	n = btf__type_cnt(targ_btf);
+	for (i = targ_start_id; i < n; i++) {
 		t = btf__type_by_id(targ_btf, i);
 		if (btf_kind(t) != btf_kind(local_cand->t))
 			continue;
@@ -5252,7 +5252,7 @@ bpf_core_find_cands(struct bpf_object *obj, const struct btf *local_btf, __u32 l
 		err = bpf_core_add_cands(&local_cand, local_essent_len,
 					 obj->btf_modules[i].btf,
 					 obj->btf_modules[i].name,
-					 btf__get_nr_types(obj->btf_vmlinux) + 1,
+					 btf__type_cnt(obj->btf_vmlinux),
 					 cands);
 		if (err)
 			goto err_out;
diff --git a/tools/lib/bpf/libbpf.map b/tools/lib/bpf/libbpf.map
index e6fb1ba49369..116964a29e44 100644
--- a/tools/lib/bpf/libbpf.map
+++ b/tools/lib/bpf/libbpf.map
@@ -395,4 +395,6 @@ LIBBPF_0.6.0 {
 		bpf_object__prev_program;
 		btf__add_btf;
 		btf__add_decl_tag;
+		btf__raw_data;
+		btf__type_cnt;
 } LIBBPF_0.5.0;
diff --git a/tools/lib/bpf/linker.c b/tools/lib/bpf/linker.c
index 13e6fdc7d8cb..7bf658fbda80 100644
--- a/tools/lib/bpf/linker.c
+++ b/tools/lib/bpf/linker.c
@@ -920,7 +920,7 @@ static int check_btf_type_id(__u32 *type_id, void *ctx)
 {
 	struct btf *btf = ctx;
 
-	if (*type_id > btf__get_nr_types(btf))
+	if (*type_id >= btf__type_cnt(btf))
 		return -EINVAL;
 
 	return 0;
@@ -947,8 +947,8 @@ static int linker_sanity_check_btf(struct src_obj *obj)
 	if (!obj->btf)
 		return 0;
 
-	n = btf__get_nr_types(obj->btf);
-	for (i = 1; i <= n; i++) {
+	n = btf__type_cnt(obj->btf);
+	for (i = 1; i < n; i++) {
 		t = btf_type_by_id(obj->btf, i);
 
 		err = err ?: btf_type_visit_type_ids(t, check_btf_type_id, obj->btf);
@@ -1658,8 +1658,8 @@ static int find_glob_sym_btf(struct src_obj *obj, Elf64_Sym *sym, const char *sy
 		return -EINVAL;
 	}
 
-	n = btf__get_nr_types(obj->btf);
-	for (i = 1; i <= n; i++) {
+	n = btf__type_cnt(obj->btf);
+	for (i = 1; i < n; i++) {
 		t = btf__type_by_id(obj->btf, i);
 
 		/* some global and extern FUNCs and VARs might not be associated with any
@@ -2130,8 +2130,8 @@ static int linker_fixup_btf(struct src_obj *obj)
 	if (!obj->btf)
 		return 0;
 
-	n = btf__get_nr_types(obj->btf);
-	for (i = 1; i <= n; i++) {
+	n = btf__type_cnt(obj->btf);
+	for (i = 1; i < n; i++) {
 		struct btf_var_secinfo *vi;
 		struct btf_type *t;
 
@@ -2234,14 +2234,14 @@ static int linker_append_btf(struct bpf_linker *linker, struct src_obj *obj)
 	if (!obj->btf)
 		return 0;
 
-	start_id = btf__get_nr_types(linker->btf) + 1;
-	n = btf__get_nr_types(obj->btf);
+	start_id = btf__type_cnt(linker->btf);
+	n = btf__type_cnt(obj->btf);
 
 	obj->btf_type_map = calloc(n + 1, sizeof(int));
 	if (!obj->btf_type_map)
 		return -ENOMEM;
 
-	for (i = 1; i <= n; i++) {
+	for (i = 1; i < n; i++) {
 		struct glob_sym *glob_sym = NULL;
 
 		t = btf__type_by_id(obj->btf, i);
@@ -2296,8 +2296,8 @@ static int linker_append_btf(struct bpf_linker *linker, struct src_obj *obj)
 	}
 
 	/* remap all the types except DATASECs */
-	n = btf__get_nr_types(linker->btf);
-	for (i = start_id; i <= n; i++) {
+	n = btf__type_cnt(linker->btf);
+	for (i = start_id; i < n; i++) {
 		struct btf_type *dst_t = btf_type_by_id(linker->btf, i);
 
 		if (btf_type_visit_type_ids(dst_t, remap_type_id, obj->btf_type_map))
@@ -2656,7 +2656,7 @@ static int finalize_btf(struct bpf_linker *linker)
 	__u32 raw_sz;
 
 	/* bail out if no BTF data was produced */
-	if (btf__get_nr_types(linker->btf) == 0)
+	if (btf__type_cnt(linker->btf) == 1)
 		return 0;
 
 	for (i = 1; i < linker->sec_cnt; i++) {
@@ -2693,7 +2693,7 @@ static int finalize_btf(struct bpf_linker *linker)
 	}
 
 	/* Emit .BTF section */
-	raw_data = btf__get_raw_data(linker->btf, &raw_sz);
+	raw_data = btf__raw_data(linker->btf, &raw_sz);
 	if (!raw_data)
 		return -ENOMEM;
 
-- 
cgit v1.2.3


From 2502e74bb5f9a49c5cd50dd365fc699a7d50daed Mon Sep 17 00:00:00 2001
From: Hengqi Chen <hengqi.chen@gmail.com>
Date: Fri, 22 Oct 2021 21:06:20 +0800
Subject: perf bpf: Switch to new btf__raw_data API

Replace the call to btf__get_raw_data with new API btf__raw_data.
The old APIs will be deprecated in libbpf v0.7+. No functionality
change.

Signed-off-by: Hengqi Chen <hengqi.chen@gmail.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20211022130623.1548429-3-hengqi.chen@gmail.com
---
 tools/perf/util/bpf-event.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'tools')

diff --git a/tools/perf/util/bpf-event.c b/tools/perf/util/bpf-event.c
index 1a7112a87736..388847bab6d9 100644
--- a/tools/perf/util/bpf-event.c
+++ b/tools/perf/util/bpf-event.c
@@ -110,7 +110,7 @@ static int perf_env__fetch_btf(struct perf_env *env,
 	u32 data_size;
 	const void *data;
 
-	data = btf__get_raw_data(btf, &data_size);
+	data = btf__raw_data(btf, &data_size);
 
 	node = malloc(data_size + sizeof(struct btf_node));
 	if (!node)
-- 
cgit v1.2.3


From 2d8f09fafc6351d77f724c208c8168d2512d5478 Mon Sep 17 00:00:00 2001
From: Hengqi Chen <hengqi.chen@gmail.com>
Date: Fri, 22 Oct 2021 21:06:21 +0800
Subject: tools/resolve_btfids: Switch to new btf__type_cnt API

Replace the call to btf__get_nr_types with new API btf__type_cnt.
The old API will be deprecated in libbpf v0.7+. No functionality
change.

Signed-off-by: Hengqi Chen <hengqi.chen@gmail.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20211022130623.1548429-4-hengqi.chen@gmail.com
---
 tools/bpf/resolve_btfids/main.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'tools')

diff --git a/tools/bpf/resolve_btfids/main.c b/tools/bpf/resolve_btfids/main.c
index 716e6ad1864b..a59cb0ee609c 100644
--- a/tools/bpf/resolve_btfids/main.c
+++ b/tools/bpf/resolve_btfids/main.c
@@ -502,12 +502,12 @@ static int symbols_resolve(struct object *obj)
 	}
 
 	err = -1;
-	nr_types = btf__get_nr_types(btf);
+	nr_types = btf__type_cnt(btf);
 
 	/*
 	 * Iterate all the BTF types and search for collected symbol IDs.
 	 */
-	for (type_id = 1; type_id <= nr_types; type_id++) {
+	for (type_id = 1; type_id < nr_types; type_id++) {
 		const struct btf_type *type;
 		struct rb_root *root;
 		struct btf_id *id;
-- 
cgit v1.2.3


From 58fc155b0e4bbd69584b7a241ab01d55ee7cfde6 Mon Sep 17 00:00:00 2001
From: Hengqi Chen <hengqi.chen@gmail.com>
Date: Fri, 22 Oct 2021 21:06:22 +0800
Subject: bpftool: Switch to new btf__type_cnt API

Replace the call to btf__get_nr_types with new API btf__type_cnt.
The old API will be deprecated in libbpf v0.7+. No functionality
change.

Signed-off-by: Hengqi Chen <hengqi.chen@gmail.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20211022130623.1548429-5-hengqi.chen@gmail.com
---
 tools/bpf/bpftool/btf.c | 12 ++++++------
 tools/bpf/bpftool/gen.c |  4 ++--
 2 files changed, 8 insertions(+), 8 deletions(-)

(limited to 'tools')

diff --git a/tools/bpf/bpftool/btf.c b/tools/bpf/bpftool/btf.c
index 7b68d4f65fe6..0cd769adac66 100644
--- a/tools/bpf/bpftool/btf.c
+++ b/tools/bpf/bpftool/btf.c
@@ -329,7 +329,7 @@ static int dump_btf_type(const struct btf *btf, __u32 id,
 				printf("\n\ttype_id=%u offset=%u size=%u",
 				       v->type, v->offset, v->size);
 
-				if (v->type <= btf__get_nr_types(btf)) {
+				if (v->type < btf__type_cnt(btf)) {
 					vt = btf__type_by_id(btf, v->type);
 					printf(" (%s '%s')",
 					       btf_kind_str[btf_kind_safe(btf_kind(vt))],
@@ -390,14 +390,14 @@ static int dump_btf_raw(const struct btf *btf,
 		}
 	} else {
 		const struct btf *base;
-		int cnt = btf__get_nr_types(btf);
+		int cnt = btf__type_cnt(btf);
 		int start_id = 1;
 
 		base = btf__base_btf(btf);
 		if (base)
-			start_id = btf__get_nr_types(base) + 1;
+			start_id = btf__type_cnt(base);
 
-		for (i = start_id; i <= cnt; i++) {
+		for (i = start_id; i < cnt; i++) {
 			t = btf__type_by_id(btf, i);
 			dump_btf_type(btf, i, t);
 		}
@@ -440,9 +440,9 @@ static int dump_btf_c(const struct btf *btf,
 				goto done;
 		}
 	} else {
-		int cnt = btf__get_nr_types(btf);
+		int cnt = btf__type_cnt(btf);
 
-		for (i = 1; i <= cnt; i++) {
+		for (i = 1; i < cnt; i++) {
 			err = btf_dump__dump_type(d, i);
 			if (err)
 				goto done;
diff --git a/tools/bpf/bpftool/gen.c b/tools/bpf/bpftool/gen.c
index c446405ab73f..5c18351290f0 100644
--- a/tools/bpf/bpftool/gen.c
+++ b/tools/bpf/bpftool/gen.c
@@ -211,7 +211,7 @@ static int codegen_datasec_def(struct bpf_object *obj,
 static int codegen_datasecs(struct bpf_object *obj, const char *obj_name)
 {
 	struct btf *btf = bpf_object__btf(obj);
-	int n = btf__get_nr_types(btf);
+	int n = btf__type_cnt(btf);
 	struct btf_dump *d;
 	struct bpf_map *map;
 	const struct btf_type *sec;
@@ -233,7 +233,7 @@ static int codegen_datasecs(struct bpf_object *obj, const char *obj_name)
 			continue;
 
 		sec = NULL;
-		for (i = 1; i <= n; i++) {
+		for (i = 1; i < n; i++) {
 			const struct btf_type *t = btf__type_by_id(btf, i);
 			const char *name;
 
-- 
cgit v1.2.3


From 487ef148cf17730442444c07a4c56f16578ec73e Mon Sep 17 00:00:00 2001
From: Hengqi Chen <hengqi.chen@gmail.com>
Date: Fri, 22 Oct 2021 21:06:23 +0800
Subject: selftests/bpf: Switch to new btf__type_cnt/btf__raw_data APIs

Replace the calls to btf__get_nr_types/btf__get_raw_data in
selftests with new APIs btf__type_cnt/btf__raw_data. The old
APIs will be deprecated in libbpf v0.7+.

Signed-off-by: Hengqi Chen <hengqi.chen@gmail.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20211022130623.1548429-6-hengqi.chen@gmail.com
---
 tools/testing/selftests/bpf/btf_helpers.c               |  4 ++--
 tools/testing/selftests/bpf/prog_tests/btf.c            | 10 +++++-----
 tools/testing/selftests/bpf/prog_tests/btf_dump.c       |  8 ++++----
 tools/testing/selftests/bpf/prog_tests/btf_endian.c     | 12 ++++++------
 tools/testing/selftests/bpf/prog_tests/btf_split.c      |  2 +-
 tools/testing/selftests/bpf/prog_tests/core_autosize.c  |  2 +-
 tools/testing/selftests/bpf/prog_tests/core_reloc.c     |  2 +-
 tools/testing/selftests/bpf/prog_tests/resolve_btfids.c |  4 ++--
 8 files changed, 22 insertions(+), 22 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/btf_helpers.c b/tools/testing/selftests/bpf/btf_helpers.c
index 668cfa20bb1b..b5b6b013a245 100644
--- a/tools/testing/selftests/bpf/btf_helpers.c
+++ b/tools/testing/selftests/bpf/btf_helpers.c
@@ -215,7 +215,7 @@ 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");
+	ASSERT_EQ(btf__type_cnt(btf) - 1, 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"))
@@ -254,7 +254,7 @@ const char *btf_type_c_dump(const struct btf *btf)
 		return NULL;
 	}
 
-	for (i = 1; i <= btf__get_nr_types(btf); i++) {
+	for (i = 1; i < btf__type_cnt(btf); i++) {
 		err = btf_dump__dump_type(d, i);
 		if (err) {
 			fprintf(stderr, "Failed to dump type [%d]: %d\n", i, err);
diff --git a/tools/testing/selftests/bpf/prog_tests/btf.c b/tools/testing/selftests/bpf/prog_tests/btf.c
index fa67f25bbef5..557f948f9964 100644
--- a/tools/testing/selftests/bpf/prog_tests/btf.c
+++ b/tools/testing/selftests/bpf/prog_tests/btf.c
@@ -7274,8 +7274,8 @@ static void do_test_dedup(unsigned int test_num)
 		goto done;
 	}
 
-	test_btf_data = btf__get_raw_data(test_btf, &test_btf_size);
-	expect_btf_data = btf__get_raw_data(expect_btf, &expect_btf_size);
+	test_btf_data = btf__raw_data(test_btf, &test_btf_size);
+	expect_btf_data = btf__raw_data(expect_btf, &expect_btf_size);
 	if (CHECK(test_btf_size != expect_btf_size,
 		  "test_btf_size:%u != expect_btf_size:%u",
 		  test_btf_size, expect_btf_size)) {
@@ -7329,8 +7329,8 @@ static void do_test_dedup(unsigned int test_num)
 		expect_str_cur += expect_len + 1;
 	}
 
-	test_nr_types = btf__get_nr_types(test_btf);
-	expect_nr_types = btf__get_nr_types(expect_btf);
+	test_nr_types = btf__type_cnt(test_btf);
+	expect_nr_types = btf__type_cnt(expect_btf);
 	if (CHECK(test_nr_types != expect_nr_types,
 		  "test_nr_types:%u != expect_nr_types:%u",
 		  test_nr_types, expect_nr_types)) {
@@ -7338,7 +7338,7 @@ static void do_test_dedup(unsigned int test_num)
 		goto done;
 	}
 
-	for (i = 1; i <= test_nr_types; i++) {
+	for (i = 1; i < test_nr_types; i++) {
 		const struct btf_type *test_type, *expect_type;
 		int test_size, expect_size;
 
diff --git a/tools/testing/selftests/bpf/prog_tests/btf_dump.c b/tools/testing/selftests/bpf/prog_tests/btf_dump.c
index 12f457b6786d..3d837a7019fd 100644
--- a/tools/testing/selftests/bpf/prog_tests/btf_dump.c
+++ b/tools/testing/selftests/bpf/prog_tests/btf_dump.c
@@ -27,7 +27,7 @@ static struct btf_dump_test_case {
 static int btf_dump_all_types(const struct btf *btf,
 			      const struct btf_dump_opts *opts)
 {
-	size_t type_cnt = btf__get_nr_types(btf);
+	size_t type_cnt = btf__type_cnt(btf);
 	struct btf_dump *d;
 	int err = 0, id;
 
@@ -36,7 +36,7 @@ static int btf_dump_all_types(const struct btf *btf,
 	if (err)
 		return err;
 
-	for (id = 1; id <= type_cnt; id++) {
+	for (id = 1; id < type_cnt; id++) {
 		err = btf_dump__dump_type(d, id);
 		if (err)
 			goto done;
@@ -171,7 +171,7 @@ void test_btf_dump_incremental(void)
 	err = btf__add_field(btf, "x", 2, 0, 0);
 	ASSERT_OK(err, "field_ok");
 
-	for (i = 1; i <= btf__get_nr_types(btf); i++) {
+	for (i = 1; i < btf__type_cnt(btf); i++) {
 		err = btf_dump__dump_type(d, i);
 		ASSERT_OK(err, "dump_type_ok");
 	}
@@ -210,7 +210,7 @@ void test_btf_dump_incremental(void)
 	err = btf__add_field(btf, "s", 3, 32, 0);
 	ASSERT_OK(err, "field_ok");
 
-	for (i = 1; i <= btf__get_nr_types(btf); i++) {
+	for (i = 1; i < btf__type_cnt(btf); i++) {
 		err = btf_dump__dump_type(d, i);
 		ASSERT_OK(err, "dump_type_ok");
 	}
diff --git a/tools/testing/selftests/bpf/prog_tests/btf_endian.c b/tools/testing/selftests/bpf/prog_tests/btf_endian.c
index 8ab5d3e358dd..2653cc482df4 100644
--- a/tools/testing/selftests/bpf/prog_tests/btf_endian.c
+++ b/tools/testing/selftests/bpf/prog_tests/btf_endian.c
@@ -32,7 +32,7 @@ void test_btf_endian() {
 	ASSERT_EQ(btf__endianness(btf), swap_endian, "endian");
 
 	/* Get raw BTF data in non-native endianness... */
-	raw_data = btf__get_raw_data(btf, &raw_sz);
+	raw_data = btf__raw_data(btf, &raw_sz);
 	if (!ASSERT_OK_PTR(raw_data, "raw_data_inverted"))
 		goto err_out;
 
@@ -42,9 +42,9 @@ void test_btf_endian() {
 		goto err_out;
 
 	ASSERT_EQ(btf__endianness(swap_btf), swap_endian, "endian");
-	ASSERT_EQ(btf__get_nr_types(swap_btf), btf__get_nr_types(btf), "nr_types");
+	ASSERT_EQ(btf__type_cnt(swap_btf), btf__type_cnt(btf), "nr_types");
 
-	swap_raw_data = btf__get_raw_data(swap_btf, &swap_raw_sz);
+	swap_raw_data = btf__raw_data(swap_btf, &swap_raw_sz);
 	if (!ASSERT_OK_PTR(swap_raw_data, "swap_raw_data"))
 		goto err_out;
 
@@ -58,7 +58,7 @@ void test_btf_endian() {
 
 	/* swap it back to native endianness */
 	btf__set_endianness(swap_btf, endian);
-	swap_raw_data = btf__get_raw_data(swap_btf, &swap_raw_sz);
+	swap_raw_data = btf__raw_data(swap_btf, &swap_raw_sz);
 	if (!ASSERT_OK_PTR(swap_raw_data, "swap_raw_data"))
 		goto err_out;
 
@@ -75,7 +75,7 @@ void test_btf_endian() {
 	swap_btf = NULL;
 
 	btf__set_endianness(btf, swap_endian);
-	raw_data = btf__get_raw_data(btf, &raw_sz);
+	raw_data = btf__raw_data(btf, &raw_sz);
 	if (!ASSERT_OK_PTR(raw_data, "raw_data_inverted"))
 		goto err_out;
 
@@ -85,7 +85,7 @@ void test_btf_endian() {
 		goto err_out;
 
 	ASSERT_EQ(btf__endianness(swap_btf), swap_endian, "endian");
-	ASSERT_EQ(btf__get_nr_types(swap_btf), btf__get_nr_types(btf), "nr_types");
+	ASSERT_EQ(btf__type_cnt(swap_btf), btf__type_cnt(btf), "nr_types");
 
 	/* the type should appear as if it was stored in native endianness */
 	t = btf__type_by_id(swap_btf, var_id);
diff --git a/tools/testing/selftests/bpf/prog_tests/btf_split.c b/tools/testing/selftests/bpf/prog_tests/btf_split.c
index ca7c2a91610a..b1ffe61f2aa9 100644
--- a/tools/testing/selftests/bpf/prog_tests/btf_split.c
+++ b/tools/testing/selftests/bpf/prog_tests/btf_split.c
@@ -72,7 +72,7 @@ void test_btf_split() {
 	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++) {
+	for (i = 1; i < btf__type_cnt(btf2); i++) {
 		err = btf_dump__dump_type(d, i);
 		ASSERT_OK(err, "dump_type_ok");
 	}
diff --git a/tools/testing/selftests/bpf/prog_tests/core_autosize.c b/tools/testing/selftests/bpf/prog_tests/core_autosize.c
index 2a0dac6394ef..1dfe14ff6aa4 100644
--- a/tools/testing/selftests/bpf/prog_tests/core_autosize.c
+++ b/tools/testing/selftests/bpf/prog_tests/core_autosize.c
@@ -112,7 +112,7 @@ void test_core_autosize(void)
 	if (!ASSERT_OK_PTR(f, "btf_fdopen"))
 		goto cleanup;
 
-	raw_data = btf__get_raw_data(btf, &raw_sz);
+	raw_data = btf__raw_data(btf, &raw_sz);
 	if (!ASSERT_OK_PTR(raw_data, "raw_data"))
 		goto cleanup;
 	written = fwrite(raw_data, 1, raw_sz, f);
diff --git a/tools/testing/selftests/bpf/prog_tests/core_reloc.c b/tools/testing/selftests/bpf/prog_tests/core_reloc.c
index cc50f8feeca3..55ec85ba7375 100644
--- a/tools/testing/selftests/bpf/prog_tests/core_reloc.c
+++ b/tools/testing/selftests/bpf/prog_tests/core_reloc.c
@@ -381,7 +381,7 @@ static int setup_type_id_case_local(struct core_reloc_test_case *test)
 	exp->local_anon_void_ptr = -1;
 	exp->local_anon_arr = -1;
 
-	for (i = 1; i <= btf__get_nr_types(local_btf); i++)
+	for (i = 1; i < btf__type_cnt(local_btf); i++)
 	{
 		t = btf__type_by_id(local_btf, i);
 		/* we are interested only in anonymous types */
diff --git a/tools/testing/selftests/bpf/prog_tests/resolve_btfids.c b/tools/testing/selftests/bpf/prog_tests/resolve_btfids.c
index f62361306f6d..badda6309fd9 100644
--- a/tools/testing/selftests/bpf/prog_tests/resolve_btfids.c
+++ b/tools/testing/selftests/bpf/prog_tests/resolve_btfids.c
@@ -106,9 +106,9 @@ static int resolve_symbols(void)
 		  "Failed to load BTF from btf_data.o\n"))
 		return -1;
 
-	nr = btf__get_nr_types(btf);
+	nr = btf__type_cnt(btf);
 
-	for (type_id = 1; type_id <= nr; type_id++) {
+	for (type_id = 1; type_id < nr; type_id++) {
 		if (__resolve_symbol(btf, type_id))
 			break;
 	}
-- 
cgit v1.2.3


From e89ef634f81c9d90e1824ab183721f3b361472e6 Mon Sep 17 00:00:00 2001
From: Quentin Monnet <quentin@isovalent.com>
Date: Fri, 22 Oct 2021 10:47:43 +0100
Subject: bpftool: Avoid leaking the JSON writer prepared for program metadata

Bpftool creates a new JSON object for writing program metadata in plain
text mode, regardless of metadata being present or not. Then this writer
is freed if any metadata has been found and printed, but it leaks
otherwise. We cannot destroy the object unconditionally, because the
destructor prints an undesirable line break. Instead, make sure the
writer is created only after we have found program metadata to print.

Found with valgrind.

Fixes: aff52e685eb3 ("bpftool: Support dumping metadata")
Signed-off-by: Quentin Monnet <quentin@isovalent.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20211022094743.11052-1-quentin@isovalent.com
---
 tools/bpf/bpftool/prog.c | 16 +++++++++-------
 1 file changed, 9 insertions(+), 7 deletions(-)

(limited to 'tools')

diff --git a/tools/bpf/bpftool/prog.c b/tools/bpf/bpftool/prog.c
index 277d51c4c5d9..f633299b1261 100644
--- a/tools/bpf/bpftool/prog.c
+++ b/tools/bpf/bpftool/prog.c
@@ -307,18 +307,12 @@ static void show_prog_metadata(int fd, __u32 num_maps)
 		if (printed_header)
 			jsonw_end_object(json_wtr);
 	} else {
-		json_writer_t *btf_wtr = jsonw_new(stdout);
+		json_writer_t *btf_wtr;
 		struct btf_dumper d = {
 			.btf = btf,
-			.jw = btf_wtr,
 			.is_plain_text = true,
 		};
 
-		if (!btf_wtr) {
-			p_err("jsonw alloc failed");
-			goto out_free;
-		}
-
 		for (i = 0; i < vlen; i++, vsi++) {
 			t_var = btf__type_by_id(btf, vsi->type);
 			name = btf__name_by_offset(btf, t_var->name_off);
@@ -328,6 +322,14 @@ static void show_prog_metadata(int fd, __u32 num_maps)
 
 			if (!printed_header) {
 				printf("\tmetadata:");
+
+				btf_wtr = jsonw_new(stdout);
+				if (!btf_wtr) {
+					p_err("jsonw alloc failed");
+					goto out_free;
+				}
+				d.jw = btf_wtr,
+
 				printed_header = true;
 			}
 
-- 
cgit v1.2.3


From a77f879ba1178437e5df87090165e5a45a91ba7f Mon Sep 17 00:00:00 2001
From: Stanislav Fomichev <sdf@google.com>
Date: Thu, 21 Oct 2021 14:48:12 -0700
Subject: libbpf: Use func name when pinning programs with
 LIBBPF_STRICT_SEC_NAME

We can't use section name anymore because they are not unique
and pinning objects with multiple programs with the same
progtype/secname will fail.

  [0] Closes: https://github.com/libbpf/libbpf/issues/273

Fixes: 33a2c75c55e2 ("libbpf: add internal pin_name")
Signed-off-by: Stanislav Fomichev <sdf@google.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Reviewed-by: Quentin Monnet <quentin@isovalent.com>
Link: https://lore.kernel.org/bpf/20211021214814.1236114-2-sdf@google.com
---
 tools/lib/bpf/libbpf.c        | 13 +++++++++++--
 tools/lib/bpf/libbpf_legacy.h |  3 +++
 2 files changed, 14 insertions(+), 2 deletions(-)

(limited to 'tools')

diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index eb102440a28a..604abe00785f 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -285,7 +285,7 @@ struct bpf_program {
 	size_t sub_insn_off;
 
 	char *name;
-	/* sec_name with / replaced by _; makes recursive pinning
+	/* name with / replaced by _; makes recursive pinning
 	 * in bpf_object__pin_programs easier
 	 */
 	char *pin_name;
@@ -618,7 +618,16 @@ static char *__bpf_program__pin_name(struct bpf_program *prog)
 {
 	char *name, *p;
 
-	name = p = strdup(prog->sec_name);
+	if (libbpf_mode & LIBBPF_STRICT_SEC_NAME)
+		name = strdup(prog->name);
+	else
+		name = strdup(prog->sec_name);
+
+	if (!name)
+		return NULL;
+
+	p = name;
+
 	while ((p = strchr(p, '/')))
 		*p = '_';
 
diff --git a/tools/lib/bpf/libbpf_legacy.h b/tools/lib/bpf/libbpf_legacy.h
index 74e6f860f703..29ccafab11a8 100644
--- a/tools/lib/bpf/libbpf_legacy.h
+++ b/tools/lib/bpf/libbpf_legacy.h
@@ -52,6 +52,9 @@ enum libbpf_strict_mode {
 	 * allowed, with LIBBPF_STRICT_SEC_PREFIX this will become
 	 * unrecognized by libbpf and would have to be just SEC("xdp") and
 	 * SEC("xdp") and SEC("perf_event").
+	 *
+	 * Note, in this mode the program pin path will be based on the
+	 * function name instead of section name.
 	 */
 	LIBBPF_STRICT_SEC_NAME = 0x04,
 
-- 
cgit v1.2.3


From d1321207b176b0a5a8004b371ade5a0d8dec7732 Mon Sep 17 00:00:00 2001
From: Stanislav Fomichev <sdf@google.com>
Date: Thu, 21 Oct 2021 14:48:14 -0700
Subject: selftests/bpf: Fix flow dissector tests

- update custom loader to search by name, not section name
- update bpftool commands to use proper pin path

Signed-off-by: Stanislav Fomichev <sdf@google.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20211021214814.1236114-4-sdf@google.com
---
 tools/testing/selftests/bpf/flow_dissector_load.c  | 18 +++++++++++-------
 tools/testing/selftests/bpf/flow_dissector_load.h  | 10 ++--------
 tools/testing/selftests/bpf/test_flow_dissector.sh | 10 +++++-----
 3 files changed, 18 insertions(+), 20 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/flow_dissector_load.c b/tools/testing/selftests/bpf/flow_dissector_load.c
index 3fd83b9dc1bf..87fd1aa323a9 100644
--- a/tools/testing/selftests/bpf/flow_dissector_load.c
+++ b/tools/testing/selftests/bpf/flow_dissector_load.c
@@ -17,7 +17,7 @@
 const char *cfg_pin_path = "/sys/fs/bpf/flow_dissector";
 const char *cfg_map_name = "jmp_table";
 bool cfg_attach = true;
-char *cfg_section_name;
+char *cfg_prog_name;
 char *cfg_path_name;
 
 static void load_and_attach_program(void)
@@ -25,7 +25,11 @@ static void load_and_attach_program(void)
 	int prog_fd, ret;
 	struct bpf_object *obj;
 
-	ret = bpf_flow_load(&obj, cfg_path_name, cfg_section_name,
+	ret = libbpf_set_strict_mode(LIBBPF_STRICT_ALL);
+	if (ret)
+		error(1, 0, "failed to enable libbpf strict mode: %d", ret);
+
+	ret = bpf_flow_load(&obj, cfg_path_name, cfg_prog_name,
 			    cfg_map_name, NULL, &prog_fd, NULL);
 	if (ret)
 		error(1, 0, "bpf_flow_load %s", cfg_path_name);
@@ -75,15 +79,15 @@ static void parse_opts(int argc, char **argv)
 			break;
 		case 'p':
 			if (cfg_path_name)
-				error(1, 0, "only one prog name can be given");
+				error(1, 0, "only one path can be given");
 
 			cfg_path_name = optarg;
 			break;
 		case 's':
-			if (cfg_section_name)
-				error(1, 0, "only one section can be given");
+			if (cfg_prog_name)
+				error(1, 0, "only one prog can be given");
 
-			cfg_section_name = optarg;
+			cfg_prog_name = optarg;
 			break;
 		}
 	}
@@ -94,7 +98,7 @@ static void parse_opts(int argc, char **argv)
 	if (cfg_attach && !cfg_path_name)
 		error(1, 0, "must provide a path to the BPF program");
 
-	if (cfg_attach && !cfg_section_name)
+	if (cfg_attach && !cfg_prog_name)
 		error(1, 0, "must provide a section name");
 }
 
diff --git a/tools/testing/selftests/bpf/flow_dissector_load.h b/tools/testing/selftests/bpf/flow_dissector_load.h
index 7290401ec172..9d0acc2fc6cc 100644
--- a/tools/testing/selftests/bpf/flow_dissector_load.h
+++ b/tools/testing/selftests/bpf/flow_dissector_load.h
@@ -7,7 +7,7 @@
 
 static inline int bpf_flow_load(struct bpf_object **obj,
 				const char *path,
-				const char *section_name,
+				const char *prog_name,
 				const char *map_name,
 				const char *keys_map_name,
 				int *prog_fd,
@@ -23,13 +23,7 @@ static inline int bpf_flow_load(struct bpf_object **obj,
 	if (ret)
 		return ret;
 
-	main_prog = NULL;
-	bpf_object__for_each_program(prog, *obj) {
-		if (strcmp(section_name, bpf_program__section_name(prog)) == 0) {
-			main_prog = prog;
-			break;
-		}
-	}
+	main_prog = bpf_object__find_program_by_name(*obj, prog_name);
 	if (!main_prog)
 		return -1;
 
diff --git a/tools/testing/selftests/bpf/test_flow_dissector.sh b/tools/testing/selftests/bpf/test_flow_dissector.sh
index 174b72a64a4c..dbd91221727d 100755
--- a/tools/testing/selftests/bpf/test_flow_dissector.sh
+++ b/tools/testing/selftests/bpf/test_flow_dissector.sh
@@ -26,22 +26,22 @@ if [[ -z $(ip netns identify $$) ]]; then
 			type flow_dissector
 
 		if ! unshare --net $bpftool prog attach pinned \
-			/sys/fs/bpf/flow/flow_dissector flow_dissector; then
+			/sys/fs/bpf/flow/_dissect flow_dissector; then
 			echo "Unexpected unsuccessful attach in namespace" >&2
 			err=1
 		fi
 
-		$bpftool prog attach pinned /sys/fs/bpf/flow/flow_dissector \
+		$bpftool prog attach pinned /sys/fs/bpf/flow/_dissect \
 			flow_dissector
 
 		if unshare --net $bpftool prog attach pinned \
-			/sys/fs/bpf/flow/flow_dissector flow_dissector; then
+			/sys/fs/bpf/flow/_dissect flow_dissector; then
 			echo "Unexpected successful attach in namespace" >&2
 			err=1
 		fi
 
 		if ! $bpftool prog detach pinned \
-			/sys/fs/bpf/flow/flow_dissector flow_dissector; then
+			/sys/fs/bpf/flow/_dissect flow_dissector; then
 			echo "Failed to detach flow dissector" >&2
 			err=1
 		fi
@@ -95,7 +95,7 @@ else
 fi
 
 # Attach BPF program
-./flow_dissector_load -p bpf_flow.o -s flow_dissector
+./flow_dissector_load -p bpf_flow.o -s _dissect
 
 # Setup
 tc qdisc add dev lo ingress
-- 
cgit v1.2.3


From 9d19a12b02bf009fefc3620234b4297e4bd7c5d5 Mon Sep 17 00:00:00 2001
From: Yonghong Song <yhs@fb.com>
Date: Thu, 21 Oct 2021 12:56:33 -0700
Subject: selftests/bpf: Add BTF_KIND_DECL_TAG typedef unit tests

Test good and bad variants of typedef BTF_KIND_DECL_TAG encoding.

Signed-off-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20211021195633.4019472-1-yhs@fb.com
---
 tools/testing/selftests/bpf/prog_tests/btf.c | 36 ++++++++++++++++++++++++++++
 1 file changed, 36 insertions(+)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/prog_tests/btf.c b/tools/testing/selftests/bpf/prog_tests/btf.c
index 557f948f9964..8257ee0af14d 100644
--- a/tools/testing/selftests/bpf/prog_tests/btf.c
+++ b/tools/testing/selftests/bpf/prog_tests/btf.c
@@ -3903,6 +3903,42 @@ static struct btf_raw_test raw_tests[] = {
 	.btf_load_err = true,
 	.err_str = "Invalid component_idx",
 },
+{
+	.descr = "decl_tag test #13, typedef, well-formed",
+	.raw_types = {
+		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),	/* [1] */
+		BTF_TYPEDEF_ENC(NAME_TBD, 1),			/* [2] */
+		BTF_DECL_TAG_ENC(NAME_TBD, 2, -1),
+		BTF_END_RAW,
+	},
+	BTF_STR_SEC("\0t\0tag"),
+	.map_type = BPF_MAP_TYPE_ARRAY,
+	.map_name = "tag_type_check_btf",
+	.key_size = sizeof(int),
+	.value_size = 4,
+	.key_type_id = 1,
+	.value_type_id = 1,
+	.max_entries = 1,
+},
+{
+	.descr = "decl_tag test #14, typedef, invalid component_idx",
+	.raw_types = {
+		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),	/* [1] */
+		BTF_TYPEDEF_ENC(NAME_TBD, 1),			/* [2] */
+		BTF_DECL_TAG_ENC(NAME_TBD, 2, 0),
+		BTF_END_RAW,
+	},
+	BTF_STR_SEC("\0local\0tag"),
+	.map_type = BPF_MAP_TYPE_ARRAY,
+	.map_name = "tag_type_check_btf",
+	.key_size = sizeof(int),
+	.value_size = 4,
+	.key_type_id = 1,
+	.value_type_id = 1,
+	.max_entries = 1,
+	.btf_load_err = true,
+	.err_str = "Invalid component_idx",
+},
 
 }; /* struct btf_raw_test raw_tests[] */
 
-- 
cgit v1.2.3


From 557c8c480401457d885bf7a82221dcc877692aa7 Mon Sep 17 00:00:00 2001
From: Yonghong Song <yhs@fb.com>
Date: Thu, 21 Oct 2021 12:56:38 -0700
Subject: selftests/bpf: Test deduplication for BTF_KIND_DECL_TAG typedef

Add unit tests for deduplication of BTF_KIND_DECL_TAG to typedef types.
Also changed a few comments from "tag" to "decl_tag" to match
BTF_KIND_DECL_TAG enum value name.

Signed-off-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20211021195638.4019770-1-yhs@fb.com
---
 tools/testing/selftests/bpf/prog_tests/btf.c | 47 ++++++++++++++++++++++++----
 1 file changed, 41 insertions(+), 6 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/prog_tests/btf.c b/tools/testing/selftests/bpf/prog_tests/btf.c
index 8257ee0af14d..ac596cb06e40 100644
--- a/tools/testing/selftests/bpf/prog_tests/btf.c
+++ b/tools/testing/selftests/bpf/prog_tests/btf.c
@@ -6877,11 +6877,12 @@ const struct btf_dedup_test dedup_tests[] = {
 				BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 8),
 			BTF_FUNC_ENC(NAME_TBD, 12),					/* [13] func */
 			BTF_TYPE_FLOAT_ENC(NAME_TBD, 2),				/* [14] float */
-			BTF_DECL_TAG_ENC(NAME_TBD, 13, -1),				/* [15] tag */
-			BTF_DECL_TAG_ENC(NAME_TBD, 13, 1),				/* [16] tag */
+			BTF_DECL_TAG_ENC(NAME_TBD, 13, -1),				/* [15] decl_tag */
+			BTF_DECL_TAG_ENC(NAME_TBD, 13, 1),				/* [16] decl_tag */
+			BTF_DECL_TAG_ENC(NAME_TBD, 7, -1),				/* [17] decl_tag */
 			BTF_END_RAW,
 		},
-		BTF_STR_SEC("\0A\0B\0C\0D\0E\0F\0G\0H\0I\0J\0K\0L\0M\0N\0O\0P"),
+		BTF_STR_SEC("\0A\0B\0C\0D\0E\0F\0G\0H\0I\0J\0K\0L\0M\0N\0O\0P\0Q"),
 	},
 	.expect = {
 		.raw_types = {
@@ -6905,11 +6906,12 @@ const struct btf_dedup_test dedup_tests[] = {
 				BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 8),
 			BTF_FUNC_ENC(NAME_TBD, 12),					/* [13] func */
 			BTF_TYPE_FLOAT_ENC(NAME_TBD, 2),				/* [14] float */
-			BTF_DECL_TAG_ENC(NAME_TBD, 13, -1),				/* [15] tag */
-			BTF_DECL_TAG_ENC(NAME_TBD, 13, 1),				/* [16] tag */
+			BTF_DECL_TAG_ENC(NAME_TBD, 13, -1),				/* [15] decl_tag */
+			BTF_DECL_TAG_ENC(NAME_TBD, 13, 1),				/* [16] decl_tag */
+			BTF_DECL_TAG_ENC(NAME_TBD, 7, -1),				/* [17] decl_tag */
 			BTF_END_RAW,
 		},
-		BTF_STR_SEC("\0A\0B\0C\0D\0E\0F\0G\0H\0I\0J\0K\0L\0M\0N\0O\0P"),
+		BTF_STR_SEC("\0A\0B\0C\0D\0E\0F\0G\0H\0I\0J\0K\0L\0M\0N\0O\0P\0Q"),
 	},
 	.opts = {
 		.dont_resolve_fwds = false,
@@ -7204,6 +7206,39 @@ const struct btf_dedup_test dedup_tests[] = {
 		.dont_resolve_fwds = false,
 	},
 },
+{
+	.descr = "dedup: typedef tags",
+	.input = {
+		.raw_types = {
+			/* int */
+			BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),	/* [1] */
+			BTF_TYPEDEF_ENC(NAME_NTH(1), 1),		/* [2] */
+			BTF_TYPEDEF_ENC(NAME_NTH(1), 1),		/* [3] */
+			/* tag -> t: tag1, tag2 */
+			BTF_DECL_TAG_ENC(NAME_NTH(2), 2, -1),		/* [4] */
+			BTF_DECL_TAG_ENC(NAME_NTH(3), 2, -1),		/* [5] */
+			/* tag -> t: tag1, tag3 */
+			BTF_DECL_TAG_ENC(NAME_NTH(2), 3, -1),		/* [6] */
+			BTF_DECL_TAG_ENC(NAME_NTH(4), 3, -1),		/* [7] */
+			BTF_END_RAW,
+		},
+		BTF_STR_SEC("\0t\0tag1\0tag2\0tag3"),
+	},
+	.expect = {
+		.raw_types = {
+			BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),	/* [1] */
+			BTF_TYPEDEF_ENC(NAME_NTH(1), 1),		/* [2] */
+			BTF_DECL_TAG_ENC(NAME_NTH(2), 2, -1),		/* [3] */
+			BTF_DECL_TAG_ENC(NAME_NTH(3), 2, -1),		/* [4] */
+			BTF_DECL_TAG_ENC(NAME_NTH(4), 2, -1),		/* [5] */
+			BTF_END_RAW,
+		},
+		BTF_STR_SEC("\0t\0tag1\0tag2\0tag3"),
+	},
+	.opts = {
+		.dont_resolve_fwds = false,
+	},
+},
 
 };
 
-- 
cgit v1.2.3


From 8c18ea2d2c2913c80d8700c8bc8fe8568b8650a1 Mon Sep 17 00:00:00 2001
From: Yonghong Song <yhs@fb.com>
Date: Thu, 21 Oct 2021 12:56:43 -0700
Subject: selftests/bpf: Add BTF_KIND_DECL_TAG typedef example in tag.c

Change value type in progs/tag.c to a typedef with a btf_decl_tag.
With `bpftool btf dump file tag.o`, we have
  ...
  [14] TYPEDEF 'value_t' type_id=17
  [15] DECL_TAG 'tag1' type_id=14 component_idx=-1
  [16] DECL_TAG 'tag2' type_id=14 component_idx=-1
  [17] STRUCT '(anon)' size=8 vlen=2
        'a' type_id=2 bits_offset=0
        'b' type_id=2 bits_offset=32
  ...

The btf_tag selftest also succeeded:
  $ ./test_progs -t tag
    #21 btf_tag:OK
    Summary: 1/0 PASSED, 0 SKIPPED, 0 FAILED

Signed-off-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20211021195643.4020315-1-yhs@fb.com
---
 tools/testing/selftests/bpf/progs/tag.c | 9 +++++++--
 1 file changed, 7 insertions(+), 2 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/progs/tag.c b/tools/testing/selftests/bpf/progs/tag.c
index 672d19e7b120..1792f4eda095 100644
--- a/tools/testing/selftests/bpf/progs/tag.c
+++ b/tools/testing/selftests/bpf/progs/tag.c
@@ -24,18 +24,23 @@ struct key_t {
 	int c;
 } __tag1 __tag2;
 
+typedef struct {
+	int a;
+	int b;
+} value_t __tag1 __tag2;
+
 struct {
 	__uint(type, BPF_MAP_TYPE_HASH);
 	__uint(max_entries, 3);
 	__type(key, struct key_t);
-	__type(value, __u64);
+	__type(value, value_t);
 } hashmap1 SEC(".maps");
 
 
 static __noinline int foo(int x __tag1 __tag2) __tag1 __tag2
 {
 	struct key_t key;
-	__u64 val = 1;
+	value_t val = {};
 
 	key.a = key.b = key.c = x;
 	bpf_map_update_elem(&hashmap1, &key, &val, 0);
-- 
cgit v1.2.3


From 5245dafe3d49efba4d3285cf27ee1cc1eeafafc6 Mon Sep 17 00:00:00 2001
From: Andrii Nakryiko <andrii@kernel.org>
Date: Fri, 22 Oct 2021 17:31:56 -0700
Subject: libbpf: Fix overflow in BTF sanity checks

btf_header's str_off+str_len or type_off+type_len can overflow as they
are u32s. This will lead to bypassing the sanity checks during BTF
parsing, resulting in crashes afterwards. Fix by using 64-bit signed
integers for comparison.

Fixes: d8123624506c ("libbpf: Fix BTF data layout checks and allow empty BTF")
Reported-by: Evgeny Vereshchagin <evvers@ya.ru>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20211023003157.726961-1-andrii@kernel.org
---
 tools/lib/bpf/btf.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'tools')

diff --git a/tools/lib/bpf/btf.c b/tools/lib/bpf/btf.c
index 66997d985ff8..05b945208815 100644
--- a/tools/lib/bpf/btf.c
+++ b/tools/lib/bpf/btf.c
@@ -241,12 +241,12 @@ static int btf_parse_hdr(struct btf *btf)
 	}
 
 	meta_left = btf->raw_size - sizeof(*hdr);
-	if (meta_left < hdr->str_off + hdr->str_len) {
+	if (meta_left < (long long)hdr->str_off + hdr->str_len) {
 		pr_debug("Invalid BTF total size:%u\n", btf->raw_size);
 		return -EINVAL;
 	}
 
-	if (hdr->type_off + hdr->type_len > hdr->str_off) {
+	if ((long long)hdr->type_off + hdr->type_len > hdr->str_off) {
 		pr_debug("Invalid BTF data sections layout: type data at %u + %u, strings data at %u + %u\n",
 			 hdr->type_off, hdr->type_len, hdr->str_off, hdr->str_len);
 		return -EINVAL;
-- 
cgit v1.2.3


From c825f5fee19caf301d9821cd79abaa734322de26 Mon Sep 17 00:00:00 2001
From: Andrii Nakryiko <andrii@kernel.org>
Date: Fri, 22 Oct 2021 17:31:57 -0700
Subject: libbpf: Fix BTF header parsing checks

Original code assumed fixed and correct BTF header length. That's not
always the case, though, so fix this bug with a proper additional check.
And use actual header length instead of sizeof(struct btf_header) in
sanity checks.

Fixes: 8a138aed4a80 ("bpf: btf: Add BTF support to libbpf")
Reported-by: Evgeny Vereshchagin <evvers@ya.ru>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20211023003157.726961-2-andrii@kernel.org
---
 tools/lib/bpf/btf.c | 12 +++++++++---
 1 file changed, 9 insertions(+), 3 deletions(-)

(limited to 'tools')

diff --git a/tools/lib/bpf/btf.c b/tools/lib/bpf/btf.c
index 05b945208815..ef924fc2c911 100644
--- a/tools/lib/bpf/btf.c
+++ b/tools/lib/bpf/btf.c
@@ -236,13 +236,19 @@ static int btf_parse_hdr(struct btf *btf)
 		}
 		btf_bswap_hdr(hdr);
 	} else if (hdr->magic != BTF_MAGIC) {
-		pr_debug("Invalid BTF magic:%x\n", hdr->magic);
+		pr_debug("Invalid BTF magic: %x\n", hdr->magic);
 		return -EINVAL;
 	}
 
-	meta_left = btf->raw_size - sizeof(*hdr);
+	if (btf->raw_size < hdr->hdr_len) {
+		pr_debug("BTF header len %u larger than data size %u\n",
+			 hdr->hdr_len, btf->raw_size);
+		return -EINVAL;
+	}
+
+	meta_left = btf->raw_size - hdr->hdr_len;
 	if (meta_left < (long long)hdr->str_off + hdr->str_len) {
-		pr_debug("Invalid BTF total size:%u\n", btf->raw_size);
+		pr_debug("Invalid BTF total size: %u\n", btf->raw_size);
 		return -EINVAL;
 	}
 
-- 
cgit v1.2.3


From 016748961ba52d2d952297b0ba8c430c1584adcc Mon Sep 17 00:00:00 2001
From: Vladimir Oltean <vladimir.oltean@nxp.com>
Date: Fri, 22 Oct 2021 21:43:11 +0300
Subject: selftests: lib: forwarding: allow tests to not require mz and jq

These programs are useful, but not all selftests require them.

Additionally, on embedded boards without package management (things like
buildroot), installing mausezahn or jq is not always as trivial as
downloading a package from the web.

So it is actually a bit annoying to require programs that are not used.
Introduce options that can be set by scripts to not enforce these
dependencies. For compatibility, default to "yes".

Cc: Nikolay Aleksandrov <nikolay@nvidia.com>
Cc: Ido Schimmel <idosch@nvidia.com>
Cc: Guillaume Nault <gnault@redhat.com>
Cc: Po-Hsu Lin <po-hsu.lin@canonical.com>
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/forwarding/lib.sh | 10 ++++++++--
 1 file changed, 8 insertions(+), 2 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/net/forwarding/lib.sh b/tools/testing/selftests/net/forwarding/lib.sh
index 92087d423bcf..520d8b53464b 100644
--- a/tools/testing/selftests/net/forwarding/lib.sh
+++ b/tools/testing/selftests/net/forwarding/lib.sh
@@ -23,6 +23,8 @@ MC_CLI=${MC_CLI:=smcroutectl}
 PING_TIMEOUT=${PING_TIMEOUT:=5}
 WAIT_TIMEOUT=${WAIT_TIMEOUT:=20}
 INTERFACE_TIMEOUT=${INTERFACE_TIMEOUT:=600}
+REQUIRE_JQ=${REQUIRE_JQ:=yes}
+REQUIRE_MZ=${REQUIRE_MZ:=yes}
 
 relative_path="${BASH_SOURCE%/*}"
 if [[ "$relative_path" == "${BASH_SOURCE}" ]]; then
@@ -141,8 +143,12 @@ require_command()
 	fi
 }
 
-require_command jq
-require_command $MZ
+if [[ "$REQUIRE_JQ" = "yes" ]]; then
+	require_command jq
+fi
+if [[ "$REQUIRE_MZ" = "yes" ]]; then
+	require_command $MZ
+fi
 
 if [[ ! -v NUM_NETIFS ]]; then
 	echo "SKIP: importer does not define \"NUM_NETIFS\""
-- 
cgit v1.2.3


From edc90d15850c4812a6c72b004c9b81c37755b997 Mon Sep 17 00:00:00 2001
From: Vladimir Oltean <vladimir.oltean@nxp.com>
Date: Fri, 22 Oct 2021 21:43:12 +0300
Subject: selftests: net: dsa: add a stress test for unlocked FDB operations

This test is a bit strange in that it is perhaps more manual than
others: it does not transmit a clear OK/FAIL verdict, because user space
does not have synchronous feedback from the kernel. If a hardware access
fails, it is in deferred context.

Nonetheless, on sja1105 I have used it successfully to find and solve a
concurrency issue, so it can be used as a starting point for other
driver maintainers too.

Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../drivers/net/dsa/test_bridge_fdb_stress.sh      | 47 ++++++++++++++++++++++
 1 file changed, 47 insertions(+)
 create mode 100755 tools/testing/selftests/drivers/net/dsa/test_bridge_fdb_stress.sh

(limited to 'tools')

diff --git a/tools/testing/selftests/drivers/net/dsa/test_bridge_fdb_stress.sh b/tools/testing/selftests/drivers/net/dsa/test_bridge_fdb_stress.sh
new file mode 100755
index 000000000000..dca8be6092b9
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/dsa/test_bridge_fdb_stress.sh
@@ -0,0 +1,47 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+# Bridge FDB entries can be offloaded to DSA switches without holding the
+# rtnl_mutex. Traditionally this mutex has conferred drivers implicit
+# serialization, which means their code paths are not well tested in the
+# presence of concurrency.
+# This test creates a background task that stresses the FDB by adding and
+# deleting an entry many times in a row without the rtnl_mutex held.
+# It then tests the driver resistance to concurrency by calling .ndo_fdb_dump
+# (with rtnl_mutex held) from a foreground task.
+# Since either the FDB dump or the additions/removals can fail, but the
+# additions and removals are performed in deferred as opposed to process
+# context, we cannot simply check for user space error codes.
+
+WAIT_TIME=1
+NUM_NETIFS=1
+REQUIRE_JQ="no"
+REQUIRE_MZ="no"
+NETIF_CREATE="no"
+lib_dir=$(dirname $0)/../../../net/forwarding
+source $lib_dir/lib.sh
+
+cleanup() {
+	echo "Cleaning up"
+	kill $pid && wait $pid &> /dev/null
+	ip link del br0
+	echo "Please check kernel log for errors"
+}
+trap 'cleanup' EXIT
+
+eth=${NETIFS[p1]}
+
+ip link del br0 2&>1 >/dev/null || :
+ip link add br0 type bridge && ip link set $eth master br0
+
+(while :; do
+	bridge fdb add 00:01:02:03:04:05 dev $eth master static
+	bridge fdb del 00:01:02:03:04:05 dev $eth master static
+done) &
+pid=$!
+
+for i in $(seq 1 50); do
+	bridge fdb show > /dev/null
+	sleep 3
+	echo "$((${i} * 2))% complete..."
+done
-- 
cgit v1.2.3


From 2d7e73f09fc2f5d968ca375f047718cf25ae2b92 Mon Sep 17 00:00:00 2001
From: "David S. Miller" <davem@davemloft.net>
Date: Mon, 25 Oct 2021 12:59:25 +0100
Subject: Revert "Merge branch 'dsa-rtnl'"

This reverts commit 965e6b262f48257dbdb51b565ecfd84877a0ab5f, reversing
changes made to 4d98bb0d7ec2d0b417df6207b0bafe1868bad9f8.
---
 .../drivers/net/dsa/test_bridge_fdb_stress.sh      | 47 ----------------------
 tools/testing/selftests/net/forwarding/lib.sh      | 10 +----
 2 files changed, 2 insertions(+), 55 deletions(-)
 delete mode 100755 tools/testing/selftests/drivers/net/dsa/test_bridge_fdb_stress.sh

(limited to 'tools')

diff --git a/tools/testing/selftests/drivers/net/dsa/test_bridge_fdb_stress.sh b/tools/testing/selftests/drivers/net/dsa/test_bridge_fdb_stress.sh
deleted file mode 100755
index dca8be6092b9..000000000000
--- a/tools/testing/selftests/drivers/net/dsa/test_bridge_fdb_stress.sh
+++ /dev/null
@@ -1,47 +0,0 @@
-#!/bin/bash
-# SPDX-License-Identifier: GPL-2.0
-
-# Bridge FDB entries can be offloaded to DSA switches without holding the
-# rtnl_mutex. Traditionally this mutex has conferred drivers implicit
-# serialization, which means their code paths are not well tested in the
-# presence of concurrency.
-# This test creates a background task that stresses the FDB by adding and
-# deleting an entry many times in a row without the rtnl_mutex held.
-# It then tests the driver resistance to concurrency by calling .ndo_fdb_dump
-# (with rtnl_mutex held) from a foreground task.
-# Since either the FDB dump or the additions/removals can fail, but the
-# additions and removals are performed in deferred as opposed to process
-# context, we cannot simply check for user space error codes.
-
-WAIT_TIME=1
-NUM_NETIFS=1
-REQUIRE_JQ="no"
-REQUIRE_MZ="no"
-NETIF_CREATE="no"
-lib_dir=$(dirname $0)/../../../net/forwarding
-source $lib_dir/lib.sh
-
-cleanup() {
-	echo "Cleaning up"
-	kill $pid && wait $pid &> /dev/null
-	ip link del br0
-	echo "Please check kernel log for errors"
-}
-trap 'cleanup' EXIT
-
-eth=${NETIFS[p1]}
-
-ip link del br0 2&>1 >/dev/null || :
-ip link add br0 type bridge && ip link set $eth master br0
-
-(while :; do
-	bridge fdb add 00:01:02:03:04:05 dev $eth master static
-	bridge fdb del 00:01:02:03:04:05 dev $eth master static
-done) &
-pid=$!
-
-for i in $(seq 1 50); do
-	bridge fdb show > /dev/null
-	sleep 3
-	echo "$((${i} * 2))% complete..."
-done
diff --git a/tools/testing/selftests/net/forwarding/lib.sh b/tools/testing/selftests/net/forwarding/lib.sh
index 520d8b53464b..92087d423bcf 100644
--- a/tools/testing/selftests/net/forwarding/lib.sh
+++ b/tools/testing/selftests/net/forwarding/lib.sh
@@ -23,8 +23,6 @@ MC_CLI=${MC_CLI:=smcroutectl}
 PING_TIMEOUT=${PING_TIMEOUT:=5}
 WAIT_TIMEOUT=${WAIT_TIMEOUT:=20}
 INTERFACE_TIMEOUT=${INTERFACE_TIMEOUT:=600}
-REQUIRE_JQ=${REQUIRE_JQ:=yes}
-REQUIRE_MZ=${REQUIRE_MZ:=yes}
 
 relative_path="${BASH_SOURCE%/*}"
 if [[ "$relative_path" == "${BASH_SOURCE}" ]]; then
@@ -143,12 +141,8 @@ require_command()
 	fi
 }
 
-if [[ "$REQUIRE_JQ" = "yes" ]]; then
-	require_command jq
-fi
-if [[ "$REQUIRE_MZ" = "yes" ]]; then
-	require_command $MZ
-fi
+require_command jq
+require_command $MZ
 
 if [[ ! -v NUM_NETIFS ]]; then
 	echo "SKIP: importer does not define \"NUM_NETIFS\""
-- 
cgit v1.2.3


From d70b51f2845d4a0352361fd4f9741913a2cf2145 Mon Sep 17 00:00:00 2001
From: Vladimir Oltean <vladimir.oltean@nxp.com>
Date: Sun, 24 Oct 2021 20:17:56 +0300
Subject: selftests: lib: forwarding: allow tests to not require mz and jq

These programs are useful, but not all selftests require them.

Additionally, on embedded boards without package management (things like
buildroot), installing mausezahn or jq is not always as trivial as
downloading a package from the web.

So it is actually a bit annoying to require programs that are not used.
Introduce options that can be set by scripts to not enforce these
dependencies. For compatibility, default to "yes".

Cc: Nikolay Aleksandrov <nikolay@nvidia.com>
Cc: Ido Schimmel <idosch@nvidia.com>
Cc: Guillaume Nault <gnault@redhat.com>
Cc: Po-Hsu Lin <po-hsu.lin@canonical.com>
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Reviewed-by: Ido Schimmel <idosch@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/forwarding/lib.sh | 10 ++++++++--
 1 file changed, 8 insertions(+), 2 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/net/forwarding/lib.sh b/tools/testing/selftests/net/forwarding/lib.sh
index 92087d423bcf..520d8b53464b 100644
--- a/tools/testing/selftests/net/forwarding/lib.sh
+++ b/tools/testing/selftests/net/forwarding/lib.sh
@@ -23,6 +23,8 @@ MC_CLI=${MC_CLI:=smcroutectl}
 PING_TIMEOUT=${PING_TIMEOUT:=5}
 WAIT_TIMEOUT=${WAIT_TIMEOUT:=20}
 INTERFACE_TIMEOUT=${INTERFACE_TIMEOUT:=600}
+REQUIRE_JQ=${REQUIRE_JQ:=yes}
+REQUIRE_MZ=${REQUIRE_MZ:=yes}
 
 relative_path="${BASH_SOURCE%/*}"
 if [[ "$relative_path" == "${BASH_SOURCE}" ]]; then
@@ -141,8 +143,12 @@ require_command()
 	fi
 }
 
-require_command jq
-require_command $MZ
+if [[ "$REQUIRE_JQ" = "yes" ]]; then
+	require_command jq
+fi
+if [[ "$REQUIRE_MZ" = "yes" ]]; then
+	require_command $MZ
+fi
 
 if [[ ! -v NUM_NETIFS ]]; then
 	echo "SKIP: importer does not define \"NUM_NETIFS\""
-- 
cgit v1.2.3


From eccd0a80dc7f4be65430236db475546b0ab9ec37 Mon Sep 17 00:00:00 2001
From: Vladimir Oltean <vladimir.oltean@nxp.com>
Date: Sun, 24 Oct 2021 20:17:57 +0300
Subject: selftests: net: dsa: add a stress test for unlocked FDB operations

This test is a bit strange in that it is perhaps more manual than
others: it does not transmit a clear OK/FAIL verdict, because user space
does not have synchronous feedback from the kernel. If a hardware access
fails, it is in deferred context.

Nonetheless, on sja1105 I have used it successfully to find and solve a
concurrency issue, so it can be used as a starting point for other
driver maintainers too.

Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../drivers/net/dsa/test_bridge_fdb_stress.sh      | 47 ++++++++++++++++++++++
 1 file changed, 47 insertions(+)
 create mode 100755 tools/testing/selftests/drivers/net/dsa/test_bridge_fdb_stress.sh

(limited to 'tools')

diff --git a/tools/testing/selftests/drivers/net/dsa/test_bridge_fdb_stress.sh b/tools/testing/selftests/drivers/net/dsa/test_bridge_fdb_stress.sh
new file mode 100755
index 000000000000..dca8be6092b9
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/dsa/test_bridge_fdb_stress.sh
@@ -0,0 +1,47 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+# Bridge FDB entries can be offloaded to DSA switches without holding the
+# rtnl_mutex. Traditionally this mutex has conferred drivers implicit
+# serialization, which means their code paths are not well tested in the
+# presence of concurrency.
+# This test creates a background task that stresses the FDB by adding and
+# deleting an entry many times in a row without the rtnl_mutex held.
+# It then tests the driver resistance to concurrency by calling .ndo_fdb_dump
+# (with rtnl_mutex held) from a foreground task.
+# Since either the FDB dump or the additions/removals can fail, but the
+# additions and removals are performed in deferred as opposed to process
+# context, we cannot simply check for user space error codes.
+
+WAIT_TIME=1
+NUM_NETIFS=1
+REQUIRE_JQ="no"
+REQUIRE_MZ="no"
+NETIF_CREATE="no"
+lib_dir=$(dirname $0)/../../../net/forwarding
+source $lib_dir/lib.sh
+
+cleanup() {
+	echo "Cleaning up"
+	kill $pid && wait $pid &> /dev/null
+	ip link del br0
+	echo "Please check kernel log for errors"
+}
+trap 'cleanup' EXIT
+
+eth=${NETIFS[p1]}
+
+ip link del br0 2&>1 >/dev/null || :
+ip link add br0 type bridge && ip link set $eth master br0
+
+(while :; do
+	bridge fdb add 00:01:02:03:04:05 dev $eth master static
+	bridge fdb del 00:01:02:03:04:05 dev $eth master static
+done) &
+pid=$!
+
+for i in $(seq 1 50); do
+	bridge fdb show > /dev/null
+	sleep 3
+	echo "$((${i} * 2))% complete..."
+done
-- 
cgit v1.2.3


From b8bfafe43481e0b053694227bb013150f10db3ae Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@nvidia.com>
Date: Sun, 24 Oct 2021 10:19:09 +0300
Subject: selftests: mlxsw: Add helpers for skipping selftests

A number of mlxsw-specific selftests currently detect whether they are run
on a compatible machine, and bail out silently when not. These tests are
however done in a somewhat impenetrable manner by directly comparing PCI
IDs against a blacklist or a whitelist, and bailing out silently if the
machine is not compatible.

Instead, add a helper, mlxsw_only_on_spectrum(), which allows specifying
the supported machines in a human-readable manner. If the current machine
is incompatible, the helper emits a SKIP message and returns an error code,
based on which the caller can gracefully bail out in a suitable way. This
allows a more readable conditions such as:

	mlxsw_only_on_spectrum 2+ || return

Convert all existing open-coded guards to the new helper. Also add two new
guards to do_mark_test() and do_drop_test(), which are supported only on
Spectrum-2+, but the corresponding check was not there.

Signed-off-by: Petr Machata <petrm@nvidia.com>
Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../drivers/net/mlxsw/devlink_trap_control.sh      |  7 ++-
 .../selftests/drivers/net/mlxsw/mlxsw_lib.sh       | 50 ++++++++++++++++++++++
 .../selftests/drivers/net/mlxsw/sch_red_core.sh    | 10 +++--
 .../drivers/net/mlxsw/spectrum-2/resource_scale.sh |  7 +--
 .../net/mlxsw/spectrum/devlink_lib_spectrum.sh     |  6 +--
 .../selftests/drivers/net/mlxsw/tc_restrictions.sh |  3 +-
 .../selftests/drivers/net/mlxsw/tc_sample.sh       | 13 +++---
 tools/testing/selftests/net/forwarding/lib.sh      |  9 ++++
 8 files changed, 81 insertions(+), 24 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_control.sh b/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_control.sh
index a37273473c1b..d3a891d421ab 100755
--- a/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_control.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_control.sh
@@ -87,6 +87,7 @@ ALL_TESTS="
 NUM_NETIFS=4
 source $lib_dir/lib.sh
 source $lib_dir/devlink_lib.sh
+source mlxsw_lib.sh
 
 h1_create()
 {
@@ -626,8 +627,7 @@ ipv6_redirect_test()
 
 ptp_event_test()
 {
-	# PTP is only supported on Spectrum-1, for now.
-	[[ "$DEVLINK_VIDDID" != "15b3:cb84" ]] && return
+	mlxsw_only_on_spectrum 1 || return
 
 	# PTP Sync (0)
 	devlink_trap_stats_test "PTP Time-Critical Event Message" "ptp_event" \
@@ -638,8 +638,7 @@ ptp_event_test()
 
 ptp_general_test()
 {
-	# PTP is only supported on Spectrum-1, for now.
-	[[ "$DEVLINK_VIDDID" != "15b3:cb84" ]] && return
+	mlxsw_only_on_spectrum 1 || return
 
 	# PTP Announce (b)
 	devlink_trap_stats_test "PTP General Message" "ptp_general" \
diff --git a/tools/testing/selftests/drivers/net/mlxsw/mlxsw_lib.sh b/tools/testing/selftests/drivers/net/mlxsw/mlxsw_lib.sh
index cbe50f260a40..a95856aafd2a 100644
--- a/tools/testing/selftests/drivers/net/mlxsw/mlxsw_lib.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/mlxsw_lib.sh
@@ -11,3 +11,53 @@ if [[ ! -v MLXSW_CHIP ]]; then
 		exit 1
 	fi
 fi
+
+MLXSW_SPECTRUM_REV=$(case $MLXSW_CHIP in
+			     mlxsw_spectrum)
+				     echo 1 ;;
+			     mlxsw_spectrum*)
+				     echo ${MLXSW_CHIP#mlxsw_spectrum} ;;
+			     *)
+				     echo "Couldn't determine Spectrum chip revision." \
+					  > /dev/stderr ;;
+		     esac)
+
+mlxsw_on_spectrum()
+{
+	local rev=$1; shift
+	local op="=="
+	local rev2=${rev%+}
+
+	if [[ $rev2 != $rev ]]; then
+		op=">="
+	fi
+
+	((MLXSW_SPECTRUM_REV $op rev2))
+}
+
+__mlxsw_only_on_spectrum()
+{
+	local rev=$1; shift
+	local caller=$1; shift
+	local src=$1; shift
+
+	if ! mlxsw_on_spectrum "$rev"; then
+		log_test_skip $src:$caller "(Spectrum-$rev only)"
+		return 1
+	fi
+}
+
+mlxsw_only_on_spectrum()
+{
+	local caller=${FUNCNAME[1]}
+	local src=${BASH_SOURCE[1]}
+	local rev
+
+	for rev in "$@"; do
+		if __mlxsw_only_on_spectrum "$rev" "$caller" "$src"; then
+			return 0
+		fi
+	done
+
+	return 1
+}
diff --git a/tools/testing/selftests/drivers/net/mlxsw/sch_red_core.sh b/tools/testing/selftests/drivers/net/mlxsw/sch_red_core.sh
index dd90cd87d4f9..f260f01db0e8 100644
--- a/tools/testing/selftests/drivers/net/mlxsw/sch_red_core.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/sch_red_core.sh
@@ -73,6 +73,7 @@ CHECK_TC="yes"
 lib_dir=$(dirname $0)/../../../net/forwarding
 source $lib_dir/lib.sh
 source $lib_dir/devlink_lib.sh
+source mlxsw_lib.sh
 source qos_lib.sh
 
 ipaddr()
@@ -479,10 +480,7 @@ do_ecn_test_perband()
 	local vlan=$1; shift
 	local limit=$1; shift
 
-	# Per-band ECN counters are not supported on Spectrum-1 and Spectrum-2.
-	[[ "$DEVLINK_VIDDID" == "15b3:cb84" ||
-	   "$DEVLINK_VIDDID" == "15b3:cf6c" ]] && return
-
+	mlxsw_only_on_spectrum 3+ || return
 	__do_ecn_test get_qdisc_nmarked "$vlan" "$limit" "per-band ECN"
 }
 
@@ -584,6 +582,8 @@ do_mark_test()
 	local should_fail=$1; shift
 	local base
 
+	mlxsw_only_on_spectrum 2+ || return
+
 	RET=0
 
 	start_tcp_traffic $h1.$vlan $(ipaddr 1 $vlan) $(ipaddr 3 $vlan) \
@@ -632,6 +632,8 @@ do_drop_test()
 	local base
 	local now
 
+	mlxsw_only_on_spectrum 2+ || return
+
 	RET=0
 
 	start_traffic $h1.$vlan $(ipaddr 1 $vlan) $(ipaddr 3 $vlan) $h3_mac
diff --git a/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/resource_scale.sh b/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/resource_scale.sh
index 50654f8a8c37..02b7eea19743 100755
--- a/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/resource_scale.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/resource_scale.sh
@@ -7,12 +7,9 @@ NUM_NETIFS=6
 source $lib_dir/lib.sh
 source $lib_dir/tc_common.sh
 source $lib_dir/devlink_lib.sh
+source ../mlxsw_lib.sh
 
-if [[ "$DEVLINK_VIDDID" != "15b3:cf6c" && \
-	"$DEVLINK_VIDDID" != "15b3:cf70" ]]; then
-	echo "SKIP: test is tailored for Mellanox Spectrum-2 and Spectrum-3"
-	exit 1
-fi
+mlxsw_only_on_spectrum 2+ || exit 1
 
 current_test=""
 
diff --git a/tools/testing/selftests/drivers/net/mlxsw/spectrum/devlink_lib_spectrum.sh b/tools/testing/selftests/drivers/net/mlxsw/spectrum/devlink_lib_spectrum.sh
index 73035e25085d..06a80f40daa4 100644
--- a/tools/testing/selftests/drivers/net/mlxsw/spectrum/devlink_lib_spectrum.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/spectrum/devlink_lib_spectrum.sh
@@ -2,11 +2,9 @@
 # SPDX-License-Identifier: GPL-2.0
 
 source "../../../../net/forwarding/devlink_lib.sh"
+source ../mlxsw_lib.sh
 
-if [ "$DEVLINK_VIDDID" != "15b3:cb84" ]; then
-	echo "SKIP: test is tailored for Mellanox Spectrum"
-	exit 1
-fi
+mlxsw_only_on_spectrum 1 || exit 1
 
 # Needed for returning to default
 declare -A KVD_DEFAULTS
diff --git a/tools/testing/selftests/drivers/net/mlxsw/tc_restrictions.sh b/tools/testing/selftests/drivers/net/mlxsw/tc_restrictions.sh
index 5ec3beb637c8..0441a18f098b 100755
--- a/tools/testing/selftests/drivers/net/mlxsw/tc_restrictions.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/tc_restrictions.sh
@@ -20,6 +20,7 @@ NUM_NETIFS=2
 source $lib_dir/tc_common.sh
 source $lib_dir/lib.sh
 source $lib_dir/devlink_lib.sh
+source mlxsw_lib.sh
 
 switch_create()
 {
@@ -169,7 +170,7 @@ matchall_sample_egress_test()
 
 	# It is forbidden in mlxsw driver to have matchall with sample action
 	# bound on egress. Spectrum-1 specific restriction
-	[[ "$DEVLINK_VIDDID" != "15b3:cb84" ]] && return
+	mlxsw_only_on_spectrum 1 || return
 
 	tc qdisc add dev $swp1 clsact
 
diff --git a/tools/testing/selftests/drivers/net/mlxsw/tc_sample.sh b/tools/testing/selftests/drivers/net/mlxsw/tc_sample.sh
index 373d5f2a846e..83a0210e7544 100755
--- a/tools/testing/selftests/drivers/net/mlxsw/tc_sample.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/tc_sample.sh
@@ -51,6 +51,7 @@ NUM_NETIFS=8
 CAPTURE_FILE=$(mktemp)
 source $lib_dir/lib.sh
 source $lib_dir/devlink_lib.sh
+source mlxsw_lib.sh
 
 # Available at https://github.com/Mellanox/libpsample
 require_command psample
@@ -431,7 +432,7 @@ tc_sample_md_out_tc_test()
 	RET=0
 
 	# Output traffic class is not supported on Spectrum-1.
-	[[ "$DEVLINK_VIDDID" == "15b3:cb84" ]] && return
+	mlxsw_only_on_spectrum 2+ || return
 
 	tc filter add dev $rp1 ingress protocol all pref 1 handle 101 matchall \
 		skip_sw action sample rate 5 group 1
@@ -477,7 +478,7 @@ tc_sample_md_out_tc_occ_test()
 	RET=0
 
 	# Output traffic class occupancy is not supported on Spectrum-1.
-	[[ "$DEVLINK_VIDDID" == "15b3:cb84" ]] && return
+	mlxsw_only_on_spectrum 2+ || return
 
 	tc filter add dev $rp1 ingress protocol all pref 1 handle 101 matchall \
 		skip_sw action sample rate 1024 group 1
@@ -521,7 +522,7 @@ tc_sample_md_latency_test()
 	RET=0
 
 	# Egress sampling not supported on Spectrum-1.
-	[[ "$DEVLINK_VIDDID" == "15b3:cb84" ]] && return
+	mlxsw_only_on_spectrum 2+ || return
 
 	tc filter add dev $rp2 egress protocol all pref 1 handle 101 matchall \
 		skip_sw action sample rate 5 group 1
@@ -550,7 +551,7 @@ tc_sample_acl_group_conflict_test()
 	# port with different groups.
 
 	# Policy-based sampling is not supported on Spectrum-1.
-	[[ "$DEVLINK_VIDDID" == "15b3:cb84" ]] && return
+	mlxsw_only_on_spectrum 2+ || return
 
 	tc filter add dev $rp1 ingress protocol ip pref 1 handle 101 flower \
 		skip_sw action sample rate 1024 group 1
@@ -579,7 +580,7 @@ __tc_sample_acl_rate_test()
 	RET=0
 
 	# Policy-based sampling is not supported on Spectrum-1.
-	[[ "$DEVLINK_VIDDID" == "15b3:cb84" ]] && return
+	mlxsw_only_on_spectrum 2+ || return
 
 	tc filter add dev $port $bind protocol ip pref 1 handle 101 flower \
 		skip_sw dst_ip 198.51.100.1 action sample rate 32 group 1
@@ -631,7 +632,7 @@ tc_sample_acl_max_rate_test()
 	RET=0
 
 	# Policy-based sampling is not supported on Spectrum-1.
-	[[ "$DEVLINK_VIDDID" == "15b3:cb84" ]] && return
+	mlxsw_only_on_spectrum 2+ || return
 
 	tc filter add dev $rp1 ingress protocol ip pref 1 handle 101 flower \
 		skip_sw action sample rate $((2 ** 24 - 1)) group 1
diff --git a/tools/testing/selftests/net/forwarding/lib.sh b/tools/testing/selftests/net/forwarding/lib.sh
index 520d8b53464b..dfd827b7a9f9 100644
--- a/tools/testing/selftests/net/forwarding/lib.sh
+++ b/tools/testing/selftests/net/forwarding/lib.sh
@@ -286,6 +286,15 @@ log_test()
 	return 0
 }
 
+log_test_skip()
+{
+	local test_name=$1
+	local opt_str=$2
+
+	printf "TEST: %-60s  [SKIP]\n" "$test_name $opt_str"
+	return 0
+}
+
 log_info()
 {
 	local msg=$1
-- 
cgit v1.2.3


From 535ac9a5fba51acce1cbde2257a0ef8f35d4ac70 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@nvidia.com>
Date: Sun, 24 Oct 2021 10:19:10 +0300
Subject: selftests: mlxsw: Use permanent neighbours instead of reachable ones

The nexthop objects tests configure dummy reachable neighbours so that
the nexthops will have a MAC address and be programmed to the device.

Since these are dummy reachable neighbours, they can be transitioned by
the kernel to a failed state if they are around for too long. This can
happen, for example, if the "TIMEOUT" variable is configured with a too
high value.

Make the tests more robust by configuring the neighbours as permanent,
so that the tests do not depend on the configured timeout value.

Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Petr Machata <petrm@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../selftests/drivers/net/mlxsw/rtnetlink.sh       | 22 +++++++++++-----------
 1 file changed, 11 insertions(+), 11 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/drivers/net/mlxsw/rtnetlink.sh b/tools/testing/selftests/drivers/net/mlxsw/rtnetlink.sh
index a217f9f6775b..1075d70e8f25 100755
--- a/tools/testing/selftests/drivers/net/mlxsw/rtnetlink.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/rtnetlink.sh
@@ -779,7 +779,7 @@ nexthop_obj_offload_test()
 	setup_wait
 
 	ip nexthop add id 1 via 192.0.2.2 dev $swp1
-	ip neigh replace 192.0.2.2 lladdr 00:11:22:33:44:55 nud reachable \
+	ip neigh replace 192.0.2.2 lladdr 00:11:22:33:44:55 nud perm \
 		dev $swp1
 
 	busywait "$TIMEOUT" wait_for_offload \
@@ -791,7 +791,7 @@ nexthop_obj_offload_test()
 		ip nexthop show id 1
 	check_err $? "nexthop marked as offloaded after setting neigh to failed state"
 
-	ip neigh replace 192.0.2.2 lladdr 00:11:22:33:44:55 nud reachable \
+	ip neigh replace 192.0.2.2 lladdr 00:11:22:33:44:55 nud perm \
 		dev $swp1
 	busywait "$TIMEOUT" wait_for_offload \
 		ip nexthop show id 1
@@ -828,11 +828,11 @@ nexthop_obj_group_offload_test()
 	ip nexthop add id 1 via 192.0.2.2 dev $swp1
 	ip nexthop add id 2 via 2001:db8:1::2 dev $swp1
 	ip nexthop add id 10 group 1/2
-	ip neigh replace 192.0.2.2 lladdr 00:11:22:33:44:55 nud reachable \
+	ip neigh replace 192.0.2.2 lladdr 00:11:22:33:44:55 nud perm \
 		dev $swp1
-	ip neigh replace 192.0.2.3 lladdr 00:11:22:33:44:55 nud reachable \
+	ip neigh replace 192.0.2.3 lladdr 00:11:22:33:44:55 nud perm \
 		dev $swp1
-	ip neigh replace 2001:db8:1::2 lladdr 00:11:22:33:44:55 nud reachable \
+	ip neigh replace 2001:db8:1::2 lladdr 00:11:22:33:44:55 nud perm \
 		dev $swp1
 
 	busywait "$TIMEOUT" wait_for_offload \
@@ -888,11 +888,11 @@ nexthop_obj_bucket_offload_test()
 	ip nexthop add id 1 via 192.0.2.2 dev $swp1
 	ip nexthop add id 2 via 2001:db8:1::2 dev $swp1
 	ip nexthop add id 10 group 1/2 type resilient buckets 32 idle_timer 0
-	ip neigh replace 192.0.2.2 lladdr 00:11:22:33:44:55 nud reachable \
+	ip neigh replace 192.0.2.2 lladdr 00:11:22:33:44:55 nud perm \
 		dev $swp1
-	ip neigh replace 192.0.2.3 lladdr 00:11:22:33:44:55 nud reachable \
+	ip neigh replace 192.0.2.3 lladdr 00:11:22:33:44:55 nud perm \
 		dev $swp1
-	ip neigh replace 2001:db8:1::2 lladdr 00:11:22:33:44:55 nud reachable \
+	ip neigh replace 2001:db8:1::2 lladdr 00:11:22:33:44:55 nud perm \
 		dev $swp1
 
 	busywait "$TIMEOUT" wait_for_offload \
@@ -921,7 +921,7 @@ nexthop_obj_bucket_offload_test()
 	check_err $? "nexthop bucket not marked as offloaded after revalidating nexthop"
 
 	# Revalidate nexthop id 2 by changing its neighbour
-	ip neigh replace 2001:db8:1::2 lladdr 00:11:22:33:44:55 nud reachable \
+	ip neigh replace 2001:db8:1::2 lladdr 00:11:22:33:44:55 nud perm \
 		dev $swp1
 	busywait "$TIMEOUT" wait_for_offload \
 		ip nexthop bucket show nhid 2
@@ -971,9 +971,9 @@ nexthop_obj_route_offload_test()
 	setup_wait
 
 	ip nexthop add id 1 via 192.0.2.2 dev $swp1
-	ip neigh replace 192.0.2.2 lladdr 00:11:22:33:44:55 nud reachable \
+	ip neigh replace 192.0.2.2 lladdr 00:11:22:33:44:55 nud perm \
 		dev $swp1
-	ip neigh replace 192.0.2.3 lladdr 00:11:22:33:44:55 nud reachable \
+	ip neigh replace 192.0.2.3 lladdr 00:11:22:33:44:55 nud perm \
 		dev $swp1
 
 	ip route replace 198.51.100.0/24 nhid 1
-- 
cgit v1.2.3


From e860419684b547dd4daa8143ad70a97955571482 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@nvidia.com>
Date: Sun, 24 Oct 2021 10:19:11 +0300
Subject: selftests: mlxsw: Reduce test run time

Instead of iterating over all the available trap policers, only perform
the tests with three policers: The first, the last and the one in the
middle of the range. On a Spectrum-3 system, this reduces the run time
from almost an hour to a few minutes.

Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Petr Machata <petrm@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../drivers/net/mlxsw/devlink_trap_policer.sh      | 32 ++++++++++++++--------
 .../selftests/net/forwarding/devlink_lib.sh        |  6 ----
 2 files changed, 20 insertions(+), 18 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_policer.sh b/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_policer.sh
index 508a702f0021..0bd5ffc218ac 100755
--- a/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_policer.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/devlink_trap_policer.sh
@@ -272,13 +272,17 @@ __rate_test()
 
 rate_test()
 {
-	local id
+	local last_policer=$(devlink -j -p trap policer show |
+			     jq '[.[]["'$DEVLINK_DEV'"][].policer] | max')
 
-	for id in $(devlink_trap_policer_ids_get); do
-		echo
-		log_info "Running rate test for policer $id"
-		__rate_test $id
-	done
+	log_info "Running rate test for policer 1"
+	__rate_test 1
+
+	log_info "Running rate test for policer $((last_policer / 2))"
+	__rate_test $((last_policer / 2))
+
+	log_info "Running rate test for policer $last_policer"
+	__rate_test $last_policer
 }
 
 __burst_test()
@@ -342,13 +346,17 @@ __burst_test()
 
 burst_test()
 {
-	local id
+	local last_policer=$(devlink -j -p trap policer show |
+			     jq '[.[]["'$DEVLINK_DEV'"][].policer] | max')
+
+	log_info "Running burst test for policer 1"
+	__burst_test 1
+
+	log_info "Running burst test for policer $((last_policer / 2))"
+	__burst_test $((last_policer / 2))
 
-	for id in $(devlink_trap_policer_ids_get); do
-		echo
-		log_info "Running burst size test for policer $id"
-		__burst_test $id
-	done
+	log_info "Running burst test for policer $last_policer"
+	__burst_test $last_policer
 }
 
 trap cleanup EXIT
diff --git a/tools/testing/selftests/net/forwarding/devlink_lib.sh b/tools/testing/selftests/net/forwarding/devlink_lib.sh
index 2c14a86adaaa..de9944d42027 100644
--- a/tools/testing/selftests/net/forwarding/devlink_lib.sh
+++ b/tools/testing/selftests/net/forwarding/devlink_lib.sh
@@ -563,12 +563,6 @@ devlink_trap_group_policer_get()
 		| jq '.[][][]["policer"]'
 }
 
-devlink_trap_policer_ids_get()
-{
-	devlink -j -p trap policer show \
-		| jq '.[]["'$DEVLINK_DEV'"][]["policer"]'
-}
-
 devlink_port_by_netdev()
 {
 	local if_name=$1
-- 
cgit v1.2.3


From 6972dc3b8778ce0d9ce819c6f1e3d32ce2bc3dd9 Mon Sep 17 00:00:00 2001
From: Andrii Nakryiko <andrii@kernel.org>
Date: Fri, 22 Oct 2021 15:32:25 -0700
Subject: selftests/bpf: Normalize selftest entry points

Ensure that all test entry points are global void functions with no
input arguments. Mark few subtest entry points as static.

Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20211022223228.99920-2-andrii@kernel.org
---
 tools/testing/selftests/bpf/prog_tests/btf_dump.c          |  2 +-
 tools/testing/selftests/bpf/prog_tests/resolve_btfids.c    | 10 ++++------
 tools/testing/selftests/bpf/prog_tests/signal_pending.c    |  2 +-
 tools/testing/selftests/bpf/prog_tests/snprintf.c          |  4 ++--
 tools/testing/selftests/bpf/prog_tests/xdp_adjust_tail.c   |  6 +++---
 tools/testing/selftests/bpf/prog_tests/xdp_devmap_attach.c |  4 ++--
 6 files changed, 13 insertions(+), 15 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/prog_tests/btf_dump.c b/tools/testing/selftests/bpf/prog_tests/btf_dump.c
index 3d837a7019fd..aa76360d8f49 100644
--- a/tools/testing/selftests/bpf/prog_tests/btf_dump.c
+++ b/tools/testing/selftests/bpf/prog_tests/btf_dump.c
@@ -133,7 +133,7 @@ static char *dump_buf;
 static size_t dump_buf_sz;
 static FILE *dump_buf_file;
 
-void test_btf_dump_incremental(void)
+static void test_btf_dump_incremental(void)
 {
 	struct btf *btf = NULL;
 	struct btf_dump *d = NULL;
diff --git a/tools/testing/selftests/bpf/prog_tests/resolve_btfids.c b/tools/testing/selftests/bpf/prog_tests/resolve_btfids.c
index badda6309fd9..f4a13d9dd5c8 100644
--- a/tools/testing/selftests/bpf/prog_tests/resolve_btfids.c
+++ b/tools/testing/selftests/bpf/prog_tests/resolve_btfids.c
@@ -117,14 +117,14 @@ static int resolve_symbols(void)
 	return 0;
 }
 
-int test_resolve_btfids(void)
+void test_resolve_btfids(void)
 {
 	__u32 *test_list, *test_lists[] = { test_list_local, test_list_global };
 	unsigned int i, j;
 	int ret = 0;
 
 	if (resolve_symbols())
-		return -1;
+		return;
 
 	/* Check BTF_ID_LIST(test_list_local) and
 	 * BTF_ID_LIST_GLOBAL(test_list_global) IDs
@@ -138,7 +138,7 @@ int test_resolve_btfids(void)
 				    test_symbols[i].name,
 				    test_list[i], test_symbols[i].id);
 			if (ret)
-				return ret;
+				return;
 		}
 	}
 
@@ -161,9 +161,7 @@ int test_resolve_btfids(void)
 
 		if (i > 0) {
 			if (!ASSERT_LE(test_set.ids[i - 1], test_set.ids[i], "sort_check"))
-				return -1;
+				return;
 		}
 	}
-
-	return ret;
 }
diff --git a/tools/testing/selftests/bpf/prog_tests/signal_pending.c b/tools/testing/selftests/bpf/prog_tests/signal_pending.c
index dfcbddcbe4d3..fdfdcff6cbef 100644
--- a/tools/testing/selftests/bpf/prog_tests/signal_pending.c
+++ b/tools/testing/selftests/bpf/prog_tests/signal_pending.c
@@ -42,7 +42,7 @@ static void test_signal_pending_by_type(enum bpf_prog_type prog_type)
 	signal(SIGALRM, SIG_DFL);
 }
 
-void test_signal_pending(enum bpf_prog_type prog_type)
+void test_signal_pending(void)
 {
 	test_signal_pending_by_type(BPF_PROG_TYPE_SOCKET_FILTER);
 	test_signal_pending_by_type(BPF_PROG_TYPE_FLOW_DISSECTOR);
diff --git a/tools/testing/selftests/bpf/prog_tests/snprintf.c b/tools/testing/selftests/bpf/prog_tests/snprintf.c
index 8fd1b4b29a0e..394ebfc3bbf3 100644
--- a/tools/testing/selftests/bpf/prog_tests/snprintf.c
+++ b/tools/testing/selftests/bpf/prog_tests/snprintf.c
@@ -33,7 +33,7 @@
 
 #define EXP_NO_BUF_RET 29
 
-void test_snprintf_positive(void)
+static void test_snprintf_positive(void)
 {
 	char exp_addr_out[] = EXP_ADDR_OUT;
 	char exp_sym_out[]  = EXP_SYM_OUT;
@@ -103,7 +103,7 @@ static int load_single_snprintf(char *fmt)
 	return ret;
 }
 
-void test_snprintf_negative(void)
+static void test_snprintf_negative(void)
 {
 	ASSERT_OK(load_single_snprintf("valid %d"), "valid usage");
 
diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_adjust_tail.c b/tools/testing/selftests/bpf/prog_tests/xdp_adjust_tail.c
index d5c98f2cb12f..f529e3c923ae 100644
--- a/tools/testing/selftests/bpf/prog_tests/xdp_adjust_tail.c
+++ b/tools/testing/selftests/bpf/prog_tests/xdp_adjust_tail.c
@@ -2,7 +2,7 @@
 #include <test_progs.h>
 #include <network_helpers.h>
 
-void test_xdp_adjust_tail_shrink(void)
+static void test_xdp_adjust_tail_shrink(void)
 {
 	const char *file = "./test_xdp_adjust_tail_shrink.o";
 	__u32 duration, retval, size, expect_sz;
@@ -30,7 +30,7 @@ void test_xdp_adjust_tail_shrink(void)
 	bpf_object__close(obj);
 }
 
-void test_xdp_adjust_tail_grow(void)
+static void test_xdp_adjust_tail_grow(void)
 {
 	const char *file = "./test_xdp_adjust_tail_grow.o";
 	struct bpf_object *obj;
@@ -58,7 +58,7 @@ void test_xdp_adjust_tail_grow(void)
 	bpf_object__close(obj);
 }
 
-void test_xdp_adjust_tail_grow2(void)
+static void test_xdp_adjust_tail_grow2(void)
 {
 	const char *file = "./test_xdp_adjust_tail_grow.o";
 	char buf[4096]; /* avoid segfault: large buf to hold grow results */
diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_devmap_attach.c b/tools/testing/selftests/bpf/prog_tests/xdp_devmap_attach.c
index d4e9a9972a67..3079d5568f8f 100644
--- a/tools/testing/selftests/bpf/prog_tests/xdp_devmap_attach.c
+++ b/tools/testing/selftests/bpf/prog_tests/xdp_devmap_attach.c
@@ -8,7 +8,7 @@
 
 #define IFINDEX_LO 1
 
-void test_xdp_with_devmap_helpers(void)
+static void test_xdp_with_devmap_helpers(void)
 {
 	struct test_xdp_with_devmap_helpers *skel;
 	struct bpf_prog_info info = {};
@@ -60,7 +60,7 @@ out_close:
 	test_xdp_with_devmap_helpers__destroy(skel);
 }
 
-void test_neg_xdp_devmap_helpers(void)
+static void test_neg_xdp_devmap_helpers(void)
 {
 	struct test_xdp_devmap_helpers *skel;
 
-- 
cgit v1.2.3


From 8ea688e7f444f1830aa4b283e1364ab9d9bf42b5 Mon Sep 17 00:00:00 2001
From: Andrii Nakryiko <andrii@kernel.org>
Date: Fri, 22 Oct 2021 15:32:26 -0700
Subject: selftests/bpf: Support multiple tests per file

Revamp how test discovery works for test_progs and allow multiple test
entries per file. Any global void function with no arguments and
serial_test_ or test_ prefix is considered a test.

Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20211022223228.99920-3-andrii@kernel.org
---
 tools/testing/selftests/bpf/Makefile | 7 +++----
 1 file changed, 3 insertions(+), 4 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index 498222543c37..ac47cf9760fc 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -421,10 +421,9 @@ 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 |					\
-			sed -e 's@\([^\.]*\)\.c@DEFINE_TEST(\1)@';	\
+	$$(shell (echo '/* Generated header, do not edit */';					\
+		  sed -n -E 's/^void (serial_)?test_([a-zA-Z0-9_]+)\((void)?\).*/DEFINE_TEST(\2)/p'	\
+			$(TRUNNER_TESTS_DIR)/*.c | sort ;	\
 		 ) > $$@)
 endif
 
-- 
cgit v1.2.3


From 2c0f51ac320649402a80a6228744eb54f42a5c21 Mon Sep 17 00:00:00 2001
From: Andrii Nakryiko <andrii@kernel.org>
Date: Fri, 22 Oct 2021 15:32:27 -0700
Subject: selftests/bpf: Mark tc_redirect selftest as serial

It seems to cause a lot of harm to kprobe/tracepoint selftests. Yucong
mentioned before that it does manipulate sysfs, which might be the
reason. So let's mark it as serial, though ideally it would be less
intrusive on the system at test.

Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20211022223228.99920-4-andrii@kernel.org
---
 tools/testing/selftests/bpf/prog_tests/tc_redirect.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/prog_tests/tc_redirect.c b/tools/testing/selftests/bpf/prog_tests/tc_redirect.c
index e87bc4466d9a..53672634bc52 100644
--- a/tools/testing/selftests/bpf/prog_tests/tc_redirect.c
+++ b/tools/testing/selftests/bpf/prog_tests/tc_redirect.c
@@ -769,7 +769,7 @@ static void *test_tc_redirect_run_tests(void *arg)
 	return NULL;
 }
 
-void test_tc_redirect(void)
+void serial_test_tc_redirect(void)
 {
 	pthread_t test_thread;
 	int err;
-- 
cgit v1.2.3


From 3762a39ce85feb07996f3f0390963da71874c651 Mon Sep 17 00:00:00 2001
From: Andrii Nakryiko <andrii@kernel.org>
Date: Fri, 22 Oct 2021 15:32:28 -0700
Subject: selftests/bpf: Split out bpf_verif_scale selftests into multiple
 tests

Instead of using subtests in bpf_verif_scale selftest, turn each scale
sub-test into its own test. Each subtest is compltely independent and
just reuses a bit of common test running logic, so the conversion is
trivial. For convenience, keep all of BPF verifier scale tests in one
file.

This conversion shaves off a significant amount of time when running
test_progs in parallel mode. E.g., just running scale tests (-t verif_scale):

BEFORE
======
Summary: 24/0 PASSED, 0 SKIPPED, 0 FAILED

real    0m22.894s
user    0m0.012s
sys     0m22.797s

AFTER
=====
Summary: 24/0 PASSED, 0 SKIPPED, 0 FAILED

real    0m12.044s
user    0m0.024s
sys     0m27.869s

Ten second saving right there. test_progs -j is not yet ready to be
turned on by default, unfortunately, and some tests fail almost every
time, but this is a good improvement nevertheless. Ignoring few
failures, here is sequential vs parallel run times when running all
tests now:

SEQUENTIAL
==========
Summary: 206/953 PASSED, 4 SKIPPED, 0 FAILED

real    1m5.625s
user    0m4.211s
sys     0m31.650s

PARALLEL
========
Summary: 204/952 PASSED, 4 SKIPPED, 2 FAILED

real    0m35.550s
user    0m4.998s
sys     0m39.890s

Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20211022223228.99920-5-andrii@kernel.org
---
 .../selftests/bpf/prog_tests/bpf_verif_scale.c     | 220 ++++++++++++++-------
 1 file changed, 152 insertions(+), 68 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_verif_scale.c b/tools/testing/selftests/bpf/prog_tests/bpf_verif_scale.c
index 3d002c245d2b..867349e4ed9e 100644
--- a/tools/testing/selftests/bpf/prog_tests/bpf_verif_scale.c
+++ b/tools/testing/selftests/bpf/prog_tests/bpf_verif_scale.c
@@ -39,82 +39,166 @@ struct scale_test_def {
 	bool fails;
 };
 
-void test_bpf_verif_scale(void)
-{
-	struct scale_test_def tests[] = {
-		{ "loop3.o", BPF_PROG_TYPE_RAW_TRACEPOINT, true /* fails */ },
-
-		{ "test_verif_scale1.o", BPF_PROG_TYPE_SCHED_CLS },
-		{ "test_verif_scale2.o", BPF_PROG_TYPE_SCHED_CLS },
-		{ "test_verif_scale3.o", BPF_PROG_TYPE_SCHED_CLS },
-
-		{ "pyperf_global.o", BPF_PROG_TYPE_RAW_TRACEPOINT },
-		{ "pyperf_subprogs.o", BPF_PROG_TYPE_RAW_TRACEPOINT },
-
-		/* full unroll by llvm */
-		{ "pyperf50.o", BPF_PROG_TYPE_RAW_TRACEPOINT },
-		{ "pyperf100.o", BPF_PROG_TYPE_RAW_TRACEPOINT },
-		{ "pyperf180.o", BPF_PROG_TYPE_RAW_TRACEPOINT },
-
-		/* partial unroll. llvm will unroll loop ~150 times.
-		 * C loop count -> 600.
-		 * Asm loop count -> 4.
-		 * 16k insns in loop body.
-		 * Total of 5 such loops. Total program size ~82k insns.
-		 */
-		{ "pyperf600.o", BPF_PROG_TYPE_RAW_TRACEPOINT },
-
-		/* no unroll at all.
-		 * C loop count -> 600.
-		 * ASM loop count -> 600.
-		 * ~110 insns in loop body.
-		 * Total of 5 such loops. Total program size ~1500 insns.
-		 */
-		{ "pyperf600_nounroll.o", BPF_PROG_TYPE_RAW_TRACEPOINT },
-
-		{ "loop1.o", BPF_PROG_TYPE_RAW_TRACEPOINT },
-		{ "loop2.o", BPF_PROG_TYPE_RAW_TRACEPOINT },
-		{ "loop4.o", BPF_PROG_TYPE_SCHED_CLS },
-		{ "loop5.o", BPF_PROG_TYPE_SCHED_CLS },
-		{ "loop6.o", BPF_PROG_TYPE_KPROBE },
-
-		/* partial unroll. 19k insn in a loop.
-		 * Total program size 20.8k insn.
-		 * ~350k processed_insns
-		 */
-		{ "strobemeta.o", BPF_PROG_TYPE_RAW_TRACEPOINT },
-
-		/* no unroll, tiny loops */
-		{ "strobemeta_nounroll1.o", BPF_PROG_TYPE_RAW_TRACEPOINT },
-		{ "strobemeta_nounroll2.o", BPF_PROG_TYPE_RAW_TRACEPOINT },
-
-		/* non-inlined subprogs */
-		{ "strobemeta_subprogs.o", BPF_PROG_TYPE_RAW_TRACEPOINT },
-
-		{ "test_sysctl_loop1.o", BPF_PROG_TYPE_CGROUP_SYSCTL },
-		{ "test_sysctl_loop2.o", BPF_PROG_TYPE_CGROUP_SYSCTL },
-
-		{ "test_xdp_loop.o", BPF_PROG_TYPE_XDP },
-		{ "test_seg6_loop.o", BPF_PROG_TYPE_LWT_SEG6LOCAL },
-	};
+static void scale_test(const char *file,
+		       enum bpf_prog_type attach_type,
+		       bool should_fail)
+{
 	libbpf_print_fn_t old_print_fn = NULL;
-	int err, i;
+	int err;
 
 	if (env.verifier_stats) {
 		test__force_log();
 		old_print_fn = libbpf_set_print(libbpf_debug_print);
 	}
 
-	for (i = 0; i < ARRAY_SIZE(tests); i++) {
-		const struct scale_test_def *test = &tests[i];
-
-		if (!test__start_subtest(test->file))
-			continue;
-
-		err = check_load(test->file, test->attach_type);
-		CHECK_FAIL(err && !test->fails);
-	}
+	err = check_load(file, attach_type);
+	if (should_fail)
+		ASSERT_ERR(err, "expect_error");
+	else
+		ASSERT_OK(err, "expect_success");
 
 	if (env.verifier_stats)
 		libbpf_set_print(old_print_fn);
 }
+
+void test_verif_scale1()
+{
+	scale_test("test_verif_scale1.o", BPF_PROG_TYPE_SCHED_CLS, false);
+}
+
+void test_verif_scale2()
+{
+	scale_test("test_verif_scale2.o", BPF_PROG_TYPE_SCHED_CLS, false);
+}
+
+void test_verif_scale3()
+{
+	scale_test("test_verif_scale3.o", BPF_PROG_TYPE_SCHED_CLS, false);
+}
+
+void test_verif_scale_pyperf_global()
+{
+	scale_test("pyperf_global.o", BPF_PROG_TYPE_RAW_TRACEPOINT, false);
+}
+
+void test_verif_scale_pyperf_subprogs()
+{
+	scale_test("pyperf_subprogs.o", BPF_PROG_TYPE_RAW_TRACEPOINT, false);
+}
+
+void test_verif_scale_pyperf50()
+{
+	/* full unroll by llvm */
+	scale_test("pyperf50.o", BPF_PROG_TYPE_RAW_TRACEPOINT, false);
+}
+
+void test_verif_scale_pyperf100()
+{
+	/* full unroll by llvm */
+	scale_test("pyperf100.o", BPF_PROG_TYPE_RAW_TRACEPOINT, false);
+}
+
+void test_verif_scale_pyperf180()
+{
+	/* full unroll by llvm */
+	scale_test("pyperf180.o", BPF_PROG_TYPE_RAW_TRACEPOINT, false);
+}
+
+void test_verif_scale_pyperf600()
+{
+	/* partial unroll. llvm will unroll loop ~150 times.
+	 * C loop count -> 600.
+	 * Asm loop count -> 4.
+	 * 16k insns in loop body.
+	 * Total of 5 such loops. Total program size ~82k insns.
+	 */
+	scale_test("pyperf600.o", BPF_PROG_TYPE_RAW_TRACEPOINT, false);
+}
+
+void test_verif_scale_pyperf600_nounroll()
+{
+	/* no unroll at all.
+	 * C loop count -> 600.
+	 * ASM loop count -> 600.
+	 * ~110 insns in loop body.
+	 * Total of 5 such loops. Total program size ~1500 insns.
+	 */
+	scale_test("pyperf600_nounroll.o", BPF_PROG_TYPE_RAW_TRACEPOINT, false);
+}
+
+void test_verif_scale_loop1()
+{
+	scale_test("loop1.o", BPF_PROG_TYPE_RAW_TRACEPOINT, false);
+}
+
+void test_verif_scale_loop2()
+{
+	scale_test("loop2.o", BPF_PROG_TYPE_RAW_TRACEPOINT, false);
+}
+
+void test_verif_scale_loop3_fail()
+{
+	scale_test("loop3.o", BPF_PROG_TYPE_RAW_TRACEPOINT, true /* fails */);
+}
+
+void test_verif_scale_loop4()
+{
+	scale_test("loop4.o", BPF_PROG_TYPE_SCHED_CLS, false);
+}
+
+void test_verif_scale_loop5()
+{
+	scale_test("loop5.o", BPF_PROG_TYPE_SCHED_CLS, false);
+}
+
+void test_verif_scale_loop6()
+{
+	scale_test("loop6.o", BPF_PROG_TYPE_KPROBE, false);
+}
+
+void test_verif_scale_strobemeta()
+{
+	/* partial unroll. 19k insn in a loop.
+	 * Total program size 20.8k insn.
+	 * ~350k processed_insns
+	 */
+	scale_test("strobemeta.o", BPF_PROG_TYPE_RAW_TRACEPOINT, false);
+}
+
+void test_verif_scale_strobemeta_nounroll1()
+{
+	/* no unroll, tiny loops */
+	scale_test("strobemeta_nounroll1.o", BPF_PROG_TYPE_RAW_TRACEPOINT, false);
+}
+
+void test_verif_scale_strobemeta_nounroll2()
+{
+	/* no unroll, tiny loops */
+	scale_test("strobemeta_nounroll2.o", BPF_PROG_TYPE_RAW_TRACEPOINT, false);
+}
+
+void test_verif_scale_strobemeta_subprogs()
+{
+	/* non-inlined subprogs */
+	scale_test("strobemeta_subprogs.o", BPF_PROG_TYPE_RAW_TRACEPOINT, false);
+}
+
+void test_verif_scale_sysctl_loop1()
+{
+	scale_test("test_sysctl_loop1.o", BPF_PROG_TYPE_CGROUP_SYSCTL, false);
+}
+
+void test_verif_scale_sysctl_loop2()
+{
+	scale_test("test_sysctl_loop2.o", BPF_PROG_TYPE_CGROUP_SYSCTL, false);
+}
+
+void test_verif_scale_xdp_loop()
+{
+	scale_test("test_xdp_loop.o", BPF_PROG_TYPE_XDP, false);
+}
+
+void test_verif_scale_seg6_loop()
+{
+	scale_test("test_seg6_loop.o", BPF_PROG_TYPE_LWT_SEG6LOCAL, false);
+}
-- 
cgit v1.2.3


From 8b6c46241c774c83998092a4eafe40f054568881 Mon Sep 17 00:00:00 2001
From: Quentin Monnet <quentin@isovalent.com>
Date: Sat, 23 Oct 2021 21:51:50 +0100
Subject: bpftool: Remove Makefile dep. on $(LIBBPF) for
 $(LIBBPF_INTERNAL_HDRS)

The dependency is only useful to make sure that the $(LIBBPF_HDRS_DIR)
directory is created before we try to install locally the required
libbpf internal header. Let's create this directory properly instead.

This is in preparation of making $(LIBBPF_INTERNAL_HDRS) a dependency to
the bootstrap bpftool version, in which case we want no dependency on
$(LIBBPF).

Signed-off-by: Quentin Monnet <quentin@isovalent.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20211023205154.6710-2-quentin@isovalent.com
---
 tools/bpf/bpftool/Makefile | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'tools')

diff --git a/tools/bpf/bpftool/Makefile b/tools/bpf/bpftool/Makefile
index 098d762e111a..939b0fca5fb9 100644
--- a/tools/bpf/bpftool/Makefile
+++ b/tools/bpf/bpftool/Makefile
@@ -39,14 +39,14 @@ ifeq ($(BPFTOOL_VERSION),)
 BPFTOOL_VERSION := $(shell make -rR --no-print-directory -sC ../../.. kernelversion)
 endif
 
-$(LIBBPF_OUTPUT) $(BOOTSTRAP_OUTPUT) $(LIBBPF_BOOTSTRAP_OUTPUT):
+$(LIBBPF_OUTPUT) $(BOOTSTRAP_OUTPUT) $(LIBBPF_BOOTSTRAP_OUTPUT) $(LIBBPF_HDRS_DIR):
 	$(QUIET_MKDIR)mkdir -p $@
 
 $(LIBBPF): $(wildcard $(BPF_DIR)/*.[ch] $(BPF_DIR)/Makefile) | $(LIBBPF_OUTPUT)
 	$(Q)$(MAKE) -C $(BPF_DIR) OUTPUT=$(LIBBPF_OUTPUT) \
 		DESTDIR=$(LIBBPF_DESTDIR) prefix= $(LIBBPF) install_headers
 
-$(LIBBPF_INTERNAL_HDRS): $(LIBBPF_HDRS_DIR)/%.h: $(BPF_DIR)/%.h $(LIBBPF)
+$(LIBBPF_INTERNAL_HDRS): $(LIBBPF_HDRS_DIR)/%.h: $(BPF_DIR)/%.h | $(LIBBPF_HDRS_DIR)
 	$(call QUIET_INSTALL, $@)
 	$(Q)install -m 644 -t $(LIBBPF_HDRS_DIR) $<
 
-- 
cgit v1.2.3


From 46241271d18f3ae095b7ec3d9d136d8f4e28e025 Mon Sep 17 00:00:00 2001
From: Quentin Monnet <quentin@isovalent.com>
Date: Sat, 23 Oct 2021 21:51:51 +0100
Subject: bpftool: Do not expose and init hash maps for pinned path in main.c

BPF programs, maps, and links, can all be listed with their pinned paths
by bpftool, when the "-f" option is provided. To do so, bpftool builds
hash maps containing all pinned paths for each kind of objects.

These three hash maps are always initialised in main.c, and exposed
through main.h. There appear to be no particular reason to do so: we can
just as well make them static to the files that need them (prog.c,
map.c, and link.c respectively), and initialise them only when we want
to show objects and the "-f" switch is provided.

This may prevent unnecessary memory allocations if the implementation of
the hash maps was to change in the future.

Signed-off-by: Quentin Monnet <quentin@isovalent.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20211023205154.6710-3-quentin@isovalent.com
---
 tools/bpf/bpftool/link.c |  9 ++++++++-
 tools/bpf/bpftool/main.c | 12 ------------
 tools/bpf/bpftool/main.h |  3 ---
 tools/bpf/bpftool/map.c  |  9 ++++++++-
 tools/bpf/bpftool/prog.c |  9 ++++++++-
 5 files changed, 24 insertions(+), 18 deletions(-)

(limited to 'tools')

diff --git a/tools/bpf/bpftool/link.c b/tools/bpf/bpftool/link.c
index 8cc3e36f8cc6..a5effb1816b7 100644
--- a/tools/bpf/bpftool/link.c
+++ b/tools/bpf/bpftool/link.c
@@ -20,6 +20,8 @@ static const char * const link_type_name[] = {
 	[BPF_LINK_TYPE_NETNS]			= "netns",
 };
 
+static struct pinned_obj_table link_table;
+
 static int link_parse_fd(int *argc, char ***argv)
 {
 	int fd;
@@ -302,8 +304,10 @@ static int do_show(int argc, char **argv)
 	__u32 id = 0;
 	int err, fd;
 
-	if (show_pinned)
+	if (show_pinned) {
+		hash_init(link_table.table);
 		build_pinned_obj_table(&link_table, BPF_OBJ_LINK);
+	}
 	build_obj_refs_table(&refs_table, BPF_OBJ_LINK);
 
 	if (argc == 2) {
@@ -346,6 +350,9 @@ static int do_show(int argc, char **argv)
 
 	delete_obj_refs_table(&refs_table);
 
+	if (show_pinned)
+		delete_pinned_obj_table(&link_table);
+
 	return errno == ENOENT ? 0 : -1;
 }
 
diff --git a/tools/bpf/bpftool/main.c b/tools/bpf/bpftool/main.c
index 02eaaf065f65..7a33f0e6da28 100644
--- a/tools/bpf/bpftool/main.c
+++ b/tools/bpf/bpftool/main.c
@@ -31,9 +31,6 @@ bool verifier_logs;
 bool relaxed_maps;
 bool use_loader;
 struct btf *base_btf;
-struct pinned_obj_table prog_table;
-struct pinned_obj_table map_table;
-struct pinned_obj_table link_table;
 struct obj_refs_table refs_table;
 
 static void __noreturn clean_and_exit(int i)
@@ -409,10 +406,6 @@ int main(int argc, char **argv)
 	block_mount = false;
 	bin_name = argv[0];
 
-	hash_init(prog_table.table);
-	hash_init(map_table.table);
-	hash_init(link_table.table);
-
 	opterr = 0;
 	while ((opt = getopt_long(argc, argv, "VhpjfLmndB:",
 				  options, NULL)) >= 0) {
@@ -479,11 +472,6 @@ int main(int argc, char **argv)
 	if (json_output)
 		jsonw_destroy(&json_wtr);
 
-	if (show_pinned) {
-		delete_pinned_obj_table(&prog_table);
-		delete_pinned_obj_table(&map_table);
-		delete_pinned_obj_table(&link_table);
-	}
 	btf__free(base_btf);
 
 	return ret;
diff --git a/tools/bpf/bpftool/main.h b/tools/bpf/bpftool/main.h
index 90caa42aac4c..baf607cd5924 100644
--- a/tools/bpf/bpftool/main.h
+++ b/tools/bpf/bpftool/main.h
@@ -91,9 +91,6 @@ extern bool verifier_logs;
 extern bool relaxed_maps;
 extern bool use_loader;
 extern struct btf *base_btf;
-extern struct pinned_obj_table prog_table;
-extern struct pinned_obj_table map_table;
-extern struct pinned_obj_table link_table;
 extern struct obj_refs_table refs_table;
 
 void __printf(1, 2) p_err(const char *fmt, ...);
diff --git a/tools/bpf/bpftool/map.c b/tools/bpf/bpftool/map.c
index 407071d54ab1..0085039d9610 100644
--- a/tools/bpf/bpftool/map.c
+++ b/tools/bpf/bpftool/map.c
@@ -56,6 +56,8 @@ const char * const map_type_name[] = {
 
 const size_t map_type_name_size = ARRAY_SIZE(map_type_name);
 
+static struct pinned_obj_table map_table;
+
 static bool map_is_per_cpu(__u32 type)
 {
 	return type == BPF_MAP_TYPE_PERCPU_HASH ||
@@ -694,8 +696,10 @@ static int do_show(int argc, char **argv)
 	int err;
 	int fd;
 
-	if (show_pinned)
+	if (show_pinned) {
+		hash_init(map_table.table);
 		build_pinned_obj_table(&map_table, BPF_OBJ_MAP);
+	}
 	build_obj_refs_table(&refs_table, BPF_OBJ_MAP);
 
 	if (argc == 2)
@@ -742,6 +746,9 @@ static int do_show(int argc, char **argv)
 
 	delete_obj_refs_table(&refs_table);
 
+	if (show_pinned)
+		delete_pinned_obj_table(&map_table);
+
 	return errno == ENOENT ? 0 : -1;
 }
 
diff --git a/tools/bpf/bpftool/prog.c b/tools/bpf/bpftool/prog.c
index f633299b1261..48c2fa4d068e 100644
--- a/tools/bpf/bpftool/prog.c
+++ b/tools/bpf/bpftool/prog.c
@@ -84,6 +84,8 @@ static const char * const attach_type_strings[] = {
 	[__MAX_BPF_ATTACH_TYPE] = NULL,
 };
 
+static struct pinned_obj_table prog_table;
+
 static enum bpf_attach_type parse_attach_type(const char *str)
 {
 	enum bpf_attach_type type;
@@ -567,8 +569,10 @@ static int do_show(int argc, char **argv)
 	int err;
 	int fd;
 
-	if (show_pinned)
+	if (show_pinned) {
+		hash_init(prog_table.table);
 		build_pinned_obj_table(&prog_table, BPF_OBJ_PROG);
+	}
 	build_obj_refs_table(&refs_table, BPF_OBJ_PROG);
 
 	if (argc == 2)
@@ -613,6 +617,9 @@ static int do_show(int argc, char **argv)
 
 	delete_obj_refs_table(&refs_table);
 
+	if (show_pinned)
+		delete_pinned_obj_table(&prog_table);
+
 	return err;
 }
 
-- 
cgit v1.2.3


From 8f184732b60b74a8f8ba0d9a5c248bf611b1ebba Mon Sep 17 00:00:00 2001
From: Quentin Monnet <quentin@isovalent.com>
Date: Sat, 23 Oct 2021 21:51:52 +0100
Subject: bpftool: Switch to libbpf's hashmap for pinned paths of BPF objects

In order to show pinned paths for BPF programs, maps, or links when
listing them with the "-f" option, bpftool creates hash maps to store
all relevant paths under the bpffs. So far, it would rely on the
kernel implementation (from tools/include/linux/hashtable.h).

We can make bpftool rely on libbpf's implementation instead. The
motivation is to make bpftool less dependent of kernel headers, to ease
the path to a potential out-of-tree mirror, like libbpf has.

This commit is the first step of the conversion: the hash maps for
pinned paths for programs, maps, and links are converted to libbpf's
hashmap.{c,h}. Other hash maps used for the PIDs of process holding
references to BPF objects are left unchanged for now. On the build side,
this requires adding a dependency to a second header internal to libbpf,
and making it a dependency for the bootstrap bpftool version as well.
The rest of the changes are a rather straightforward conversion.

Signed-off-by: Quentin Monnet <quentin@isovalent.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20211023205154.6710-4-quentin@isovalent.com
---
 tools/bpf/bpftool/Makefile |  8 ++++----
 tools/bpf/bpftool/common.c | 50 +++++++++++++++++++++++++++-------------------
 tools/bpf/bpftool/link.c   | 36 ++++++++++++++++++---------------
 tools/bpf/bpftool/main.h   | 29 ++++++++++++++++-----------
 tools/bpf/bpftool/map.c    | 36 ++++++++++++++++++---------------
 tools/bpf/bpftool/prog.c   | 36 ++++++++++++++++++---------------
 6 files changed, 111 insertions(+), 84 deletions(-)

(limited to 'tools')

diff --git a/tools/bpf/bpftool/Makefile b/tools/bpf/bpftool/Makefile
index 939b0fca5fb9..c0c30e56988f 100644
--- a/tools/bpf/bpftool/Makefile
+++ b/tools/bpf/bpftool/Makefile
@@ -31,9 +31,9 @@ LIBBPF = $(LIBBPF_OUTPUT)libbpf.a
 LIBBPF_BOOTSTRAP_OUTPUT = $(BOOTSTRAP_OUTPUT)libbpf/
 LIBBPF_BOOTSTRAP = $(LIBBPF_BOOTSTRAP_OUTPUT)libbpf.a
 
-# We need to copy nlattr.h which is not otherwise exported by libbpf, but still
-# required by bpftool.
-LIBBPF_INTERNAL_HDRS := $(addprefix $(LIBBPF_HDRS_DIR)/,nlattr.h)
+# We need to copy hashmap.h and nlattr.h which is not otherwise exported by
+# libbpf, but still required by bpftool.
+LIBBPF_INTERNAL_HDRS := $(addprefix $(LIBBPF_HDRS_DIR)/,hashmap.h nlattr.h)
 
 ifeq ($(BPFTOOL_VERSION),)
 BPFTOOL_VERSION := $(shell make -rR --no-print-directory -sC ../../.. kernelversion)
@@ -209,7 +209,7 @@ $(BPFTOOL_BOOTSTRAP): $(BOOTSTRAP_OBJS) $(LIBBPF_BOOTSTRAP)
 $(OUTPUT)bpftool: $(OBJS) $(LIBBPF)
 	$(QUIET_LINK)$(CC) $(CFLAGS) $(LDFLAGS) -o $@ $(OBJS) $(LIBS)
 
-$(BOOTSTRAP_OUTPUT)%.o: %.c | $(BOOTSTRAP_OUTPUT)
+$(BOOTSTRAP_OUTPUT)%.o: %.c $(LIBBPF_INTERNAL_HDRS) | $(BOOTSTRAP_OUTPUT)
 	$(QUIET_CC)$(HOSTCC) $(CFLAGS) -c -MMD -o $@ $<
 
 $(OUTPUT)%.o: %.c
diff --git a/tools/bpf/bpftool/common.c b/tools/bpf/bpftool/common.c
index d42d930a3ec4..511eccdbdfe6 100644
--- a/tools/bpf/bpftool/common.c
+++ b/tools/bpf/bpftool/common.c
@@ -22,6 +22,7 @@
 #include <sys/vfs.h>
 
 #include <bpf/bpf.h>
+#include <bpf/hashmap.h>
 #include <bpf/libbpf.h> /* libbpf_num_possible_cpus */
 
 #include "main.h"
@@ -393,7 +394,7 @@ void print_hex_data_json(uint8_t *data, size_t len)
 }
 
 /* extra params for nftw cb */
-static struct pinned_obj_table *build_fn_table;
+static struct hashmap *build_fn_table;
 static enum bpf_obj_type build_fn_type;
 
 static int do_build_table_cb(const char *fpath, const struct stat *sb,
@@ -401,9 +402,9 @@ static int do_build_table_cb(const char *fpath, const struct stat *sb,
 {
 	struct bpf_prog_info pinned_info;
 	__u32 len = sizeof(pinned_info);
-	struct pinned_obj *obj_node;
 	enum bpf_obj_type objtype;
 	int fd, err = 0;
+	char *path;
 
 	if (typeflag != FTW_F)
 		goto out_ret;
@@ -420,28 +421,26 @@ static int do_build_table_cb(const char *fpath, const struct stat *sb,
 	if (bpf_obj_get_info_by_fd(fd, &pinned_info, &len))
 		goto out_close;
 
-	obj_node = calloc(1, sizeof(*obj_node));
-	if (!obj_node) {
+	path = strdup(fpath);
+	if (!path) {
 		err = -1;
 		goto out_close;
 	}
 
-	obj_node->id = pinned_info.id;
-	obj_node->path = strdup(fpath);
-	if (!obj_node->path) {
-		err = -1;
-		free(obj_node);
+	err = hashmap__append(build_fn_table, u32_as_hash_field(pinned_info.id), path);
+	if (err) {
+		p_err("failed to append entry to hashmap for ID %u, path '%s': %s",
+		      pinned_info.id, path, strerror(errno));
 		goto out_close;
 	}
 
-	hash_add(build_fn_table->table, &obj_node->hash, obj_node->id);
 out_close:
 	close(fd);
 out_ret:
 	return err;
 }
 
-int build_pinned_obj_table(struct pinned_obj_table *tab,
+int build_pinned_obj_table(struct hashmap *tab,
 			   enum bpf_obj_type type)
 {
 	struct mntent *mntent = NULL;
@@ -470,17 +469,18 @@ int build_pinned_obj_table(struct pinned_obj_table *tab,
 	return err;
 }
 
-void delete_pinned_obj_table(struct pinned_obj_table *tab)
+void delete_pinned_obj_table(struct hashmap *map)
 {
-	struct pinned_obj *obj;
-	struct hlist_node *tmp;
-	unsigned int bkt;
+	struct hashmap_entry *entry;
+	size_t bkt;
 
-	hash_for_each_safe(tab->table, bkt, tmp, obj, hash) {
-		hash_del(&obj->hash);
-		free(obj->path);
-		free(obj);
-	}
+	if (!map)
+		return;
+
+	hashmap__for_each_entry(map, entry, bkt)
+		free(entry->value);
+
+	hashmap__free(map);
 }
 
 unsigned int get_page_size(void)
@@ -962,3 +962,13 @@ int map_parse_fd_and_info(int *argc, char ***argv, void *info, __u32 *info_len)
 
 	return fd;
 }
+
+size_t hash_fn_for_key_as_id(const void *key, void *ctx)
+{
+	return (size_t)key;
+}
+
+bool equal_fn_for_key_as_id(const void *k1, const void *k2, void *ctx)
+{
+	return k1 == k2;
+}
diff --git a/tools/bpf/bpftool/link.c b/tools/bpf/bpftool/link.c
index a5effb1816b7..404cc5459c6b 100644
--- a/tools/bpf/bpftool/link.c
+++ b/tools/bpf/bpftool/link.c
@@ -7,6 +7,7 @@
 #include <unistd.h>
 
 #include <bpf/bpf.h>
+#include <bpf/hashmap.h>
 
 #include "json_writer.h"
 #include "main.h"
@@ -20,7 +21,7 @@ static const char * const link_type_name[] = {
 	[BPF_LINK_TYPE_NETNS]			= "netns",
 };
 
-static struct pinned_obj_table link_table;
+static struct hashmap *link_table;
 
 static int link_parse_fd(int *argc, char ***argv)
 {
@@ -158,15 +159,14 @@ static int show_link_close_json(int fd, struct bpf_link_info *info)
 		break;
 	}
 
-	if (!hash_empty(link_table.table)) {
-		struct pinned_obj *obj;
+	if (!hashmap__empty(link_table)) {
+		struct hashmap_entry *entry;
 
 		jsonw_name(json_wtr, "pinned");
 		jsonw_start_array(json_wtr);
-		hash_for_each_possible(link_table.table, obj, hash, info->id) {
-			if (obj->id == info->id)
-				jsonw_string(json_wtr, obj->path);
-		}
+		hashmap__for_each_key_entry(link_table, entry,
+					    u32_as_hash_field(info->id))
+			jsonw_string(json_wtr, entry->value);
 		jsonw_end_array(json_wtr);
 	}
 
@@ -246,13 +246,12 @@ static int show_link_close_plain(int fd, struct bpf_link_info *info)
 		break;
 	}
 
-	if (!hash_empty(link_table.table)) {
-		struct pinned_obj *obj;
+	if (!hashmap__empty(link_table)) {
+		struct hashmap_entry *entry;
 
-		hash_for_each_possible(link_table.table, obj, hash, info->id) {
-			if (obj->id == info->id)
-				printf("\n\tpinned %s", obj->path);
-		}
+		hashmap__for_each_key_entry(link_table, entry,
+					    u32_as_hash_field(info->id))
+			printf("\n\tpinned %s", (char *)entry->value);
 	}
 	emit_obj_refs_plain(&refs_table, info->id, "\n\tpids ");
 
@@ -305,8 +304,13 @@ static int do_show(int argc, char **argv)
 	int err, fd;
 
 	if (show_pinned) {
-		hash_init(link_table.table);
-		build_pinned_obj_table(&link_table, BPF_OBJ_LINK);
+		link_table = hashmap__new(hash_fn_for_key_as_id,
+					  equal_fn_for_key_as_id, NULL);
+		if (!link_table) {
+			p_err("failed to create hashmap for pinned paths");
+			return -1;
+		}
+		build_pinned_obj_table(link_table, BPF_OBJ_LINK);
 	}
 	build_obj_refs_table(&refs_table, BPF_OBJ_LINK);
 
@@ -351,7 +355,7 @@ static int do_show(int argc, char **argv)
 	delete_obj_refs_table(&refs_table);
 
 	if (show_pinned)
-		delete_pinned_obj_table(&link_table);
+		delete_pinned_obj_table(link_table);
 
 	return errno == ENOENT ? 0 : -1;
 }
diff --git a/tools/bpf/bpftool/main.h b/tools/bpf/bpftool/main.h
index baf607cd5924..0d64e39573f2 100644
--- a/tools/bpf/bpftool/main.h
+++ b/tools/bpf/bpftool/main.h
@@ -14,6 +14,7 @@
 #include <linux/hashtable.h>
 #include <tools/libc_compat.h>
 
+#include <bpf/hashmap.h>
 #include <bpf/libbpf.h>
 
 #include "json_writer.h"
@@ -105,16 +106,6 @@ void set_max_rlimit(void);
 
 int mount_tracefs(const char *target);
 
-struct pinned_obj_table {
-	DECLARE_HASHTABLE(table, 16);
-};
-
-struct pinned_obj {
-	__u32 id;
-	char *path;
-	struct hlist_node hash;
-};
-
 struct obj_refs_table {
 	DECLARE_HASHTABLE(table, 16);
 };
@@ -134,9 +125,9 @@ struct obj_refs {
 struct btf;
 struct bpf_line_info;
 
-int build_pinned_obj_table(struct pinned_obj_table *table,
+int build_pinned_obj_table(struct hashmap *table,
 			   enum bpf_obj_type type);
-void delete_pinned_obj_table(struct pinned_obj_table *tab);
+void delete_pinned_obj_table(struct hashmap *table);
 __weak int build_obj_refs_table(struct obj_refs_table *table,
 				enum bpf_obj_type type);
 __weak void delete_obj_refs_table(struct obj_refs_table *table);
@@ -256,4 +247,18 @@ int do_filter_dump(struct tcmsg *ifinfo, struct nlattr **tb, const char *kind,
 
 int print_all_levels(__maybe_unused enum libbpf_print_level level,
 		     const char *format, va_list args);
+
+size_t hash_fn_for_key_as_id(const void *key, void *ctx);
+bool equal_fn_for_key_as_id(const void *k1, const void *k2, void *ctx);
+
+static inline void *u32_as_hash_field(__u32 x)
+{
+	return (void *)(uintptr_t)x;
+}
+
+static inline bool hashmap__empty(struct hashmap *map)
+{
+	return map ? hashmap__size(map) == 0 : true;
+}
+
 #endif
diff --git a/tools/bpf/bpftool/map.c b/tools/bpf/bpftool/map.c
index 0085039d9610..2647603c5e5d 100644
--- a/tools/bpf/bpftool/map.c
+++ b/tools/bpf/bpftool/map.c
@@ -17,6 +17,7 @@
 
 #include <bpf/bpf.h>
 #include <bpf/btf.h>
+#include <bpf/hashmap.h>
 
 #include "json_writer.h"
 #include "main.h"
@@ -56,7 +57,7 @@ const char * const map_type_name[] = {
 
 const size_t map_type_name_size = ARRAY_SIZE(map_type_name);
 
-static struct pinned_obj_table map_table;
+static struct hashmap *map_table;
 
 static bool map_is_per_cpu(__u32 type)
 {
@@ -537,15 +538,14 @@ static int show_map_close_json(int fd, struct bpf_map_info *info)
 	if (info->btf_id)
 		jsonw_int_field(json_wtr, "btf_id", info->btf_id);
 
-	if (!hash_empty(map_table.table)) {
-		struct pinned_obj *obj;
+	if (!hashmap__empty(map_table)) {
+		struct hashmap_entry *entry;
 
 		jsonw_name(json_wtr, "pinned");
 		jsonw_start_array(json_wtr);
-		hash_for_each_possible(map_table.table, obj, hash, info->id) {
-			if (obj->id == info->id)
-				jsonw_string(json_wtr, obj->path);
-		}
+		hashmap__for_each_key_entry(map_table, entry,
+					    u32_as_hash_field(info->id))
+			jsonw_string(json_wtr, entry->value);
 		jsonw_end_array(json_wtr);
 	}
 
@@ -612,13 +612,12 @@ static int show_map_close_plain(int fd, struct bpf_map_info *info)
 	}
 	close(fd);
 
-	if (!hash_empty(map_table.table)) {
-		struct pinned_obj *obj;
+	if (!hashmap__empty(map_table)) {
+		struct hashmap_entry *entry;
 
-		hash_for_each_possible(map_table.table, obj, hash, info->id) {
-			if (obj->id == info->id)
-				printf("\n\tpinned %s", obj->path);
-		}
+		hashmap__for_each_key_entry(map_table, entry,
+					    u32_as_hash_field(info->id))
+			printf("\n\tpinned %s", (char *)entry->value);
 	}
 	printf("\n");
 
@@ -697,8 +696,13 @@ static int do_show(int argc, char **argv)
 	int fd;
 
 	if (show_pinned) {
-		hash_init(map_table.table);
-		build_pinned_obj_table(&map_table, BPF_OBJ_MAP);
+		map_table = hashmap__new(hash_fn_for_key_as_id,
+					 equal_fn_for_key_as_id, NULL);
+		if (!map_table) {
+			p_err("failed to create hashmap for pinned paths");
+			return -1;
+		}
+		build_pinned_obj_table(map_table, BPF_OBJ_MAP);
 	}
 	build_obj_refs_table(&refs_table, BPF_OBJ_MAP);
 
@@ -747,7 +751,7 @@ static int do_show(int argc, char **argv)
 	delete_obj_refs_table(&refs_table);
 
 	if (show_pinned)
-		delete_pinned_obj_table(&map_table);
+		delete_pinned_obj_table(map_table);
 
 	return errno == ENOENT ? 0 : -1;
 }
diff --git a/tools/bpf/bpftool/prog.c b/tools/bpf/bpftool/prog.c
index 48c2fa4d068e..8fce78ce6f8b 100644
--- a/tools/bpf/bpftool/prog.c
+++ b/tools/bpf/bpftool/prog.c
@@ -24,6 +24,7 @@
 
 #include <bpf/bpf.h>
 #include <bpf/btf.h>
+#include <bpf/hashmap.h>
 #include <bpf/libbpf.h>
 #include <bpf/skel_internal.h>
 
@@ -84,7 +85,7 @@ static const char * const attach_type_strings[] = {
 	[__MAX_BPF_ATTACH_TYPE] = NULL,
 };
 
-static struct pinned_obj_table prog_table;
+static struct hashmap *prog_table;
 
 static enum bpf_attach_type parse_attach_type(const char *str)
 {
@@ -418,15 +419,14 @@ static void print_prog_json(struct bpf_prog_info *info, int fd)
 	if (info->btf_id)
 		jsonw_int_field(json_wtr, "btf_id", info->btf_id);
 
-	if (!hash_empty(prog_table.table)) {
-		struct pinned_obj *obj;
+	if (!hashmap__empty(prog_table)) {
+		struct hashmap_entry *entry;
 
 		jsonw_name(json_wtr, "pinned");
 		jsonw_start_array(json_wtr);
-		hash_for_each_possible(prog_table.table, obj, hash, info->id) {
-			if (obj->id == info->id)
-				jsonw_string(json_wtr, obj->path);
-		}
+		hashmap__for_each_key_entry(prog_table, entry,
+					    u32_as_hash_field(info->id))
+			jsonw_string(json_wtr, entry->value);
 		jsonw_end_array(json_wtr);
 	}
 
@@ -490,13 +490,12 @@ static void print_prog_plain(struct bpf_prog_info *info, int fd)
 	if (info->nr_map_ids)
 		show_prog_maps(fd, info->nr_map_ids);
 
-	if (!hash_empty(prog_table.table)) {
-		struct pinned_obj *obj;
+	if (!hashmap__empty(prog_table)) {
+		struct hashmap_entry *entry;
 
-		hash_for_each_possible(prog_table.table, obj, hash, info->id) {
-			if (obj->id == info->id)
-				printf("\n\tpinned %s", obj->path);
-		}
+		hashmap__for_each_key_entry(prog_table, entry,
+					    u32_as_hash_field(info->id))
+			printf("\n\tpinned %s", (char *)entry->value);
 	}
 
 	if (info->btf_id)
@@ -570,8 +569,13 @@ static int do_show(int argc, char **argv)
 	int fd;
 
 	if (show_pinned) {
-		hash_init(prog_table.table);
-		build_pinned_obj_table(&prog_table, BPF_OBJ_PROG);
+		prog_table = hashmap__new(hash_fn_for_key_as_id,
+					  equal_fn_for_key_as_id, NULL);
+		if (!prog_table) {
+			p_err("failed to create hashmap for pinned paths");
+			return -1;
+		}
+		build_pinned_obj_table(prog_table, BPF_OBJ_PROG);
 	}
 	build_obj_refs_table(&refs_table, BPF_OBJ_PROG);
 
@@ -618,7 +622,7 @@ static int do_show(int argc, char **argv)
 	delete_obj_refs_table(&refs_table);
 
 	if (show_pinned)
-		delete_pinned_obj_table(&prog_table);
+		delete_pinned_obj_table(prog_table);
 
 	return err;
 }
-- 
cgit v1.2.3


From 2828d0d75b738c9cd98080c530b7b7ea90b279dd Mon Sep 17 00:00:00 2001
From: Quentin Monnet <quentin@isovalent.com>
Date: Sat, 23 Oct 2021 21:51:53 +0100
Subject: bpftool: Switch to libbpf's hashmap for programs/maps in BTF listing

In order to show BPF programs and maps using BTF objects when the latter
are being listed, bpftool creates hash maps to store all relevant items.
This commit is part of a set that transitions from the kernel's hash map
implementation to the one coming with libbpf.

The motivation is to make bpftool less dependent of kernel headers, to
ease the path to a potential out-of-tree mirror, like libbpf has.

This commit focuses on the two hash maps used by bpftool when listing
BTF objects to store references to programs and maps, and convert them
to the libbpf's implementation.

Signed-off-by: Quentin Monnet <quentin@isovalent.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20211023205154.6710-5-quentin@isovalent.com
---
 tools/bpf/bpftool/btf.c  | 125 +++++++++++++++++++++--------------------------
 tools/bpf/bpftool/main.h |   5 ++
 2 files changed, 62 insertions(+), 68 deletions(-)

(limited to 'tools')

diff --git a/tools/bpf/bpftool/btf.c b/tools/bpf/bpftool/btf.c
index 0cd769adac66..11dd31b6e730 100644
--- a/tools/bpf/bpftool/btf.c
+++ b/tools/bpf/bpftool/btf.c
@@ -8,14 +8,16 @@
 #include <stdio.h>
 #include <string.h>
 #include <unistd.h>
-#include <bpf/bpf.h>
-#include <bpf/btf.h>
-#include <bpf/libbpf.h>
 #include <linux/btf.h>
 #include <linux/hashtable.h>
 #include <sys/types.h>
 #include <sys/stat.h>
 
+#include <bpf/bpf.h>
+#include <bpf/btf.h>
+#include <bpf/hashmap.h>
+#include <bpf/libbpf.h>
+
 #include "json_writer.h"
 #include "main.h"
 
@@ -40,14 +42,9 @@ static const char * const btf_kind_str[NR_BTF_KINDS] = {
 	[BTF_KIND_DECL_TAG]	= "DECL_TAG",
 };
 
-struct btf_attach_table {
-	DECLARE_HASHTABLE(table, 16);
-};
-
 struct btf_attach_point {
 	__u32 obj_id;
 	__u32 btf_id;
-	struct hlist_node hash;
 };
 
 static const char *btf_int_enc_str(__u8 encoding)
@@ -645,21 +642,8 @@ static int btf_parse_fd(int *argc, char ***argv)
 	return fd;
 }
 
-static void delete_btf_table(struct btf_attach_table *tab)
-{
-	struct btf_attach_point *obj;
-	struct hlist_node *tmp;
-
-	unsigned int bkt;
-
-	hash_for_each_safe(tab->table, bkt, tmp, obj, hash) {
-		hash_del(&obj->hash);
-		free(obj);
-	}
-}
-
 static int
-build_btf_type_table(struct btf_attach_table *tab, enum bpf_obj_type type,
+build_btf_type_table(struct hashmap *tab, enum bpf_obj_type type,
 		     void *info, __u32 *len)
 {
 	static const char * const names[] = {
@@ -667,7 +651,6 @@ build_btf_type_table(struct btf_attach_table *tab, enum bpf_obj_type type,
 		[BPF_OBJ_PROG]		= "prog",
 		[BPF_OBJ_MAP]		= "map",
 	};
-	struct btf_attach_point *obj_node;
 	__u32 btf_id, id = 0;
 	int err;
 	int fd;
@@ -741,28 +724,25 @@ build_btf_type_table(struct btf_attach_table *tab, enum bpf_obj_type type,
 		if (!btf_id)
 			continue;
 
-		obj_node = calloc(1, sizeof(*obj_node));
-		if (!obj_node) {
-			p_err("failed to allocate memory: %s", strerror(errno));
-			err = -ENOMEM;
+		err = hashmap__append(tab, u32_as_hash_field(btf_id),
+				      u32_as_hash_field(id));
+		if (err) {
+			p_err("failed to append entry to hashmap for BTF ID %u, object ID %u: %s",
+			      btf_id, id, strerror(errno));
 			goto err_free;
 		}
-
-		obj_node->obj_id = id;
-		obj_node->btf_id = btf_id;
-		hash_add(tab->table, &obj_node->hash, obj_node->btf_id);
 	}
 
 	return 0;
 
 err_free:
-	delete_btf_table(tab);
+	hashmap__free(tab);
 	return err;
 }
 
 static int
-build_btf_tables(struct btf_attach_table *btf_prog_table,
-		 struct btf_attach_table *btf_map_table)
+build_btf_tables(struct hashmap *btf_prog_table,
+		 struct hashmap *btf_map_table)
 {
 	struct bpf_prog_info prog_info;
 	__u32 prog_len = sizeof(prog_info);
@@ -778,7 +758,7 @@ build_btf_tables(struct btf_attach_table *btf_prog_table,
 	err = build_btf_type_table(btf_map_table, BPF_OBJ_MAP, &map_info,
 				   &map_len);
 	if (err) {
-		delete_btf_table(btf_prog_table);
+		hashmap__free(btf_prog_table);
 		return err;
 	}
 
@@ -787,10 +767,10 @@ build_btf_tables(struct btf_attach_table *btf_prog_table,
 
 static void
 show_btf_plain(struct bpf_btf_info *info, int fd,
-	       struct btf_attach_table *btf_prog_table,
-	       struct btf_attach_table *btf_map_table)
+	       struct hashmap *btf_prog_table,
+	       struct hashmap *btf_map_table)
 {
-	struct btf_attach_point *obj;
+	struct hashmap_entry *entry;
 	const char *name = u64_to_ptr(info->name);
 	int n;
 
@@ -804,18 +784,19 @@ show_btf_plain(struct bpf_btf_info *info, int fd,
 	printf("size %uB", info->btf_size);
 
 	n = 0;
-	hash_for_each_possible(btf_prog_table->table, obj, hash, info->id) {
-		if (obj->btf_id == info->id)
-			printf("%s%u", n++ == 0 ? "  prog_ids " : ",",
-			       obj->obj_id);
+	hashmap__for_each_key_entry(btf_prog_table, entry,
+				    u32_as_hash_field(info->id)) {
+		printf("%s%u", n++ == 0 ? "  prog_ids " : ",",
+		       hash_field_as_u32(entry->value));
 	}
 
 	n = 0;
-	hash_for_each_possible(btf_map_table->table, obj, hash, info->id) {
-		if (obj->btf_id == info->id)
-			printf("%s%u", n++ == 0 ? "  map_ids " : ",",
-			       obj->obj_id);
+	hashmap__for_each_key_entry(btf_map_table, entry,
+				    u32_as_hash_field(info->id)) {
+		printf("%s%u", n++ == 0 ? "  map_ids " : ",",
+		       hash_field_as_u32(entry->value));
 	}
+
 	emit_obj_refs_plain(&refs_table, info->id, "\n\tpids ");
 
 	printf("\n");
@@ -823,10 +804,10 @@ show_btf_plain(struct bpf_btf_info *info, int fd,
 
 static void
 show_btf_json(struct bpf_btf_info *info, int fd,
-	      struct btf_attach_table *btf_prog_table,
-	      struct btf_attach_table *btf_map_table)
+	      struct hashmap *btf_prog_table,
+	      struct hashmap *btf_map_table)
 {
-	struct btf_attach_point *obj;
+	struct hashmap_entry *entry;
 	const char *name = u64_to_ptr(info->name);
 
 	jsonw_start_object(json_wtr);	/* btf object */
@@ -835,19 +816,17 @@ show_btf_json(struct bpf_btf_info *info, int fd,
 
 	jsonw_name(json_wtr, "prog_ids");
 	jsonw_start_array(json_wtr);	/* prog_ids */
-	hash_for_each_possible(btf_prog_table->table, obj, hash,
-			       info->id) {
-		if (obj->btf_id == info->id)
-			jsonw_uint(json_wtr, obj->obj_id);
+	hashmap__for_each_key_entry(btf_prog_table, entry,
+				    u32_as_hash_field(info->id)) {
+		jsonw_uint(json_wtr, hash_field_as_u32(entry->value));
 	}
 	jsonw_end_array(json_wtr);	/* prog_ids */
 
 	jsonw_name(json_wtr, "map_ids");
 	jsonw_start_array(json_wtr);	/* map_ids */
-	hash_for_each_possible(btf_map_table->table, obj, hash,
-			       info->id) {
-		if (obj->btf_id == info->id)
-			jsonw_uint(json_wtr, obj->obj_id);
+	hashmap__for_each_key_entry(btf_map_table, entry,
+				    u32_as_hash_field(info->id)) {
+		jsonw_uint(json_wtr, hash_field_as_u32(entry->value));
 	}
 	jsonw_end_array(json_wtr);	/* map_ids */
 
@@ -862,8 +841,8 @@ show_btf_json(struct bpf_btf_info *info, int fd,
 }
 
 static int
-show_btf(int fd, struct btf_attach_table *btf_prog_table,
-	 struct btf_attach_table *btf_map_table)
+show_btf(int fd, struct hashmap *btf_prog_table,
+	 struct hashmap *btf_map_table)
 {
 	struct bpf_btf_info info;
 	__u32 len = sizeof(info);
@@ -900,8 +879,8 @@ show_btf(int fd, struct btf_attach_table *btf_prog_table,
 
 static int do_show(int argc, char **argv)
 {
-	struct btf_attach_table btf_prog_table;
-	struct btf_attach_table btf_map_table;
+	struct hashmap *btf_prog_table;
+	struct hashmap *btf_map_table;
 	int err, fd = -1;
 	__u32 id = 0;
 
@@ -917,9 +896,19 @@ static int do_show(int argc, char **argv)
 		return BAD_ARG();
 	}
 
-	hash_init(btf_prog_table.table);
-	hash_init(btf_map_table.table);
-	err = build_btf_tables(&btf_prog_table, &btf_map_table);
+	btf_prog_table = hashmap__new(hash_fn_for_key_as_id,
+				      equal_fn_for_key_as_id, NULL);
+	btf_map_table = hashmap__new(hash_fn_for_key_as_id,
+				     equal_fn_for_key_as_id, NULL);
+	if (!btf_prog_table || !btf_map_table) {
+		hashmap__free(btf_prog_table);
+		hashmap__free(btf_map_table);
+		if (fd >= 0)
+			close(fd);
+		p_err("failed to create hashmap for object references");
+		return -1;
+	}
+	err = build_btf_tables(btf_prog_table, btf_map_table);
 	if (err) {
 		if (fd >= 0)
 			close(fd);
@@ -928,7 +917,7 @@ static int do_show(int argc, char **argv)
 	build_obj_refs_table(&refs_table, BPF_OBJ_BTF);
 
 	if (fd >= 0) {
-		err = show_btf(fd, &btf_prog_table, &btf_map_table);
+		err = show_btf(fd, btf_prog_table, btf_map_table);
 		close(fd);
 		goto exit_free;
 	}
@@ -960,7 +949,7 @@ static int do_show(int argc, char **argv)
 			break;
 		}
 
-		err = show_btf(fd, &btf_prog_table, &btf_map_table);
+		err = show_btf(fd, btf_prog_table, btf_map_table);
 		close(fd);
 		if (err)
 			break;
@@ -970,8 +959,8 @@ static int do_show(int argc, char **argv)
 		jsonw_end_array(json_wtr);	/* root array */
 
 exit_free:
-	delete_btf_table(&btf_prog_table);
-	delete_btf_table(&btf_map_table);
+	hashmap__free(btf_prog_table);
+	hashmap__free(btf_map_table);
 	delete_obj_refs_table(&refs_table);
 
 	return err;
diff --git a/tools/bpf/bpftool/main.h b/tools/bpf/bpftool/main.h
index 0d64e39573f2..f6f2f951b193 100644
--- a/tools/bpf/bpftool/main.h
+++ b/tools/bpf/bpftool/main.h
@@ -256,6 +256,11 @@ static inline void *u32_as_hash_field(__u32 x)
 	return (void *)(uintptr_t)x;
 }
 
+static inline __u32 hash_field_as_u32(const void *x)
+{
+	return (__u32)(uintptr_t)x;
+}
+
 static inline bool hashmap__empty(struct hashmap *map)
 {
 	return map ? hashmap__size(map) == 0 : true;
-- 
cgit v1.2.3


From d6699f8e0f834b40db35466f704705ae757be11a Mon Sep 17 00:00:00 2001
From: Quentin Monnet <quentin@isovalent.com>
Date: Sat, 23 Oct 2021 21:51:54 +0100
Subject: bpftool: Switch to libbpf's hashmap for PIDs/names references

In order to show PIDs and names for processes holding references to BPF
programs, maps, links, or BTF objects, bpftool creates hash maps to
store all relevant information. This commit is part of a set that
transitions from the kernel's hash map implementation to the one coming
with libbpf.

The motivation is to make bpftool less dependent of kernel headers, to
ease the path to a potential out-of-tree mirror, like libbpf has.

This is the third and final step of the transition, in which we convert
the hash maps used for storing the information about the processes
holding references to BPF objects (programs, maps, links, BTF), and at
last we drop the inclusion of tools/include/linux/hashtable.h.

Note: Checkpatch complains about the use of __weak declarations, and the
missing empty lines after the bunch of empty function declarations when
compiling without the BPF skeletons (none of these were introduced in
this patch). We want to keep things as they are, and the reports should
be safe to ignore.

Signed-off-by: Quentin Monnet <quentin@isovalent.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20211023205154.6710-6-quentin@isovalent.com
---
 tools/bpf/bpftool/btf.c  |  7 ++--
 tools/bpf/bpftool/link.c |  6 ++--
 tools/bpf/bpftool/main.c |  5 +--
 tools/bpf/bpftool/main.h | 17 +++------
 tools/bpf/bpftool/map.c  |  6 ++--
 tools/bpf/bpftool/pids.c | 90 ++++++++++++++++++++++++++++--------------------
 tools/bpf/bpftool/prog.c |  6 ++--
 7 files changed, 72 insertions(+), 65 deletions(-)

(limited to 'tools')

diff --git a/tools/bpf/bpftool/btf.c b/tools/bpf/bpftool/btf.c
index 11dd31b6e730..015d2758f826 100644
--- a/tools/bpf/bpftool/btf.c
+++ b/tools/bpf/bpftool/btf.c
@@ -9,7 +9,6 @@
 #include <string.h>
 #include <unistd.h>
 #include <linux/btf.h>
-#include <linux/hashtable.h>
 #include <sys/types.h>
 #include <sys/stat.h>
 
@@ -797,7 +796,7 @@ show_btf_plain(struct bpf_btf_info *info, int fd,
 		       hash_field_as_u32(entry->value));
 	}
 
-	emit_obj_refs_plain(&refs_table, info->id, "\n\tpids ");
+	emit_obj_refs_plain(refs_table, info->id, "\n\tpids ");
 
 	printf("\n");
 }
@@ -830,7 +829,7 @@ show_btf_json(struct bpf_btf_info *info, int fd,
 	}
 	jsonw_end_array(json_wtr);	/* map_ids */
 
-	emit_obj_refs_json(&refs_table, info->id, json_wtr); /* pids */
+	emit_obj_refs_json(refs_table, info->id, json_wtr); /* pids */
 
 	jsonw_bool_field(json_wtr, "kernel", info->kernel_btf);
 
@@ -961,7 +960,7 @@ static int do_show(int argc, char **argv)
 exit_free:
 	hashmap__free(btf_prog_table);
 	hashmap__free(btf_map_table);
-	delete_obj_refs_table(&refs_table);
+	delete_obj_refs_table(refs_table);
 
 	return err;
 }
diff --git a/tools/bpf/bpftool/link.c b/tools/bpf/bpftool/link.c
index 404cc5459c6b..2c258db0d352 100644
--- a/tools/bpf/bpftool/link.c
+++ b/tools/bpf/bpftool/link.c
@@ -170,7 +170,7 @@ static int show_link_close_json(int fd, struct bpf_link_info *info)
 		jsonw_end_array(json_wtr);
 	}
 
-	emit_obj_refs_json(&refs_table, info->id, json_wtr);
+	emit_obj_refs_json(refs_table, info->id, json_wtr);
 
 	jsonw_end_object(json_wtr);
 
@@ -253,7 +253,7 @@ static int show_link_close_plain(int fd, struct bpf_link_info *info)
 					    u32_as_hash_field(info->id))
 			printf("\n\tpinned %s", (char *)entry->value);
 	}
-	emit_obj_refs_plain(&refs_table, info->id, "\n\tpids ");
+	emit_obj_refs_plain(refs_table, info->id, "\n\tpids ");
 
 	printf("\n");
 
@@ -352,7 +352,7 @@ static int do_show(int argc, char **argv)
 	if (json_output)
 		jsonw_end_array(json_wtr);
 
-	delete_obj_refs_table(&refs_table);
+	delete_obj_refs_table(refs_table);
 
 	if (show_pinned)
 		delete_pinned_obj_table(link_table);
diff --git a/tools/bpf/bpftool/main.c b/tools/bpf/bpftool/main.c
index 7a33f0e6da28..28237d7cef67 100644
--- a/tools/bpf/bpftool/main.c
+++ b/tools/bpf/bpftool/main.c
@@ -10,8 +10,9 @@
 #include <string.h>
 
 #include <bpf/bpf.h>
-#include <bpf/libbpf.h>
 #include <bpf/btf.h>
+#include <bpf/hashmap.h>
+#include <bpf/libbpf.h>
 
 #include "main.h"
 
@@ -31,7 +32,7 @@ bool verifier_logs;
 bool relaxed_maps;
 bool use_loader;
 struct btf *base_btf;
-struct obj_refs_table refs_table;
+struct hashmap *refs_table;
 
 static void __noreturn clean_and_exit(int i)
 {
diff --git a/tools/bpf/bpftool/main.h b/tools/bpf/bpftool/main.h
index f6f2f951b193..383835c2604d 100644
--- a/tools/bpf/bpftool/main.h
+++ b/tools/bpf/bpftool/main.h
@@ -11,7 +11,6 @@
 #include <linux/bpf.h>
 #include <linux/compiler.h>
 #include <linux/kernel.h>
-#include <linux/hashtable.h>
 #include <tools/libc_compat.h>
 
 #include <bpf/hashmap.h>
@@ -92,7 +91,7 @@ extern bool verifier_logs;
 extern bool relaxed_maps;
 extern bool use_loader;
 extern struct btf *base_btf;
-extern struct obj_refs_table refs_table;
+extern struct hashmap *refs_table;
 
 void __printf(1, 2) p_err(const char *fmt, ...);
 void __printf(1, 2) p_info(const char *fmt, ...);
@@ -106,18 +105,12 @@ void set_max_rlimit(void);
 
 int mount_tracefs(const char *target);
 
-struct obj_refs_table {
-	DECLARE_HASHTABLE(table, 16);
-};
-
 struct obj_ref {
 	int pid;
 	char comm[16];
 };
 
 struct obj_refs {
-	struct hlist_node node;
-	__u32 id;
 	int ref_cnt;
 	struct obj_ref *refs;
 };
@@ -128,12 +121,12 @@ struct bpf_line_info;
 int build_pinned_obj_table(struct hashmap *table,
 			   enum bpf_obj_type type);
 void delete_pinned_obj_table(struct hashmap *table);
-__weak int build_obj_refs_table(struct obj_refs_table *table,
+__weak int build_obj_refs_table(struct hashmap **table,
 				enum bpf_obj_type type);
-__weak void delete_obj_refs_table(struct obj_refs_table *table);
-__weak void emit_obj_refs_json(struct obj_refs_table *table, __u32 id,
+__weak void delete_obj_refs_table(struct hashmap *table);
+__weak void emit_obj_refs_json(struct hashmap *table, __u32 id,
 			       json_writer_t *json_wtr);
-__weak void emit_obj_refs_plain(struct obj_refs_table *table, __u32 id,
+__weak void emit_obj_refs_plain(struct hashmap *table, __u32 id,
 				const char *prefix);
 void print_dev_plain(__u32 ifindex, __u64 ns_dev, __u64 ns_inode);
 void print_dev_json(__u32 ifindex, __u64 ns_dev, __u64 ns_inode);
diff --git a/tools/bpf/bpftool/map.c b/tools/bpf/bpftool/map.c
index 2647603c5e5d..cae1f1119296 100644
--- a/tools/bpf/bpftool/map.c
+++ b/tools/bpf/bpftool/map.c
@@ -549,7 +549,7 @@ static int show_map_close_json(int fd, struct bpf_map_info *info)
 		jsonw_end_array(json_wtr);
 	}
 
-	emit_obj_refs_json(&refs_table, info->id, json_wtr);
+	emit_obj_refs_json(refs_table, info->id, json_wtr);
 
 	jsonw_end_object(json_wtr);
 
@@ -637,7 +637,7 @@ static int show_map_close_plain(int fd, struct bpf_map_info *info)
 	if (frozen)
 		printf("%sfrozen", info->btf_id ? "  " : "");
 
-	emit_obj_refs_plain(&refs_table, info->id, "\n\tpids ");
+	emit_obj_refs_plain(refs_table, info->id, "\n\tpids ");
 
 	printf("\n");
 	return 0;
@@ -748,7 +748,7 @@ static int do_show(int argc, char **argv)
 	if (json_output)
 		jsonw_end_array(json_wtr);
 
-	delete_obj_refs_table(&refs_table);
+	delete_obj_refs_table(refs_table);
 
 	if (show_pinned)
 		delete_pinned_obj_table(map_table);
diff --git a/tools/bpf/bpftool/pids.c b/tools/bpf/bpftool/pids.c
index 477e55d59c34..56b598eee043 100644
--- a/tools/bpf/bpftool/pids.c
+++ b/tools/bpf/bpftool/pids.c
@@ -6,35 +6,37 @@
 #include <stdlib.h>
 #include <string.h>
 #include <unistd.h>
+
 #include <bpf/bpf.h>
+#include <bpf/hashmap.h>
 
 #include "main.h"
 #include "skeleton/pid_iter.h"
 
 #ifdef BPFTOOL_WITHOUT_SKELETONS
 
-int build_obj_refs_table(struct obj_refs_table *table, enum bpf_obj_type type)
+int build_obj_refs_table(struct hashmap **map, enum bpf_obj_type type)
 {
 	return -ENOTSUP;
 }
-void delete_obj_refs_table(struct obj_refs_table *table) {}
-void emit_obj_refs_plain(struct obj_refs_table *table, __u32 id, const char *prefix) {}
-void emit_obj_refs_json(struct obj_refs_table *table, __u32 id, json_writer_t *json_writer) {}
+void delete_obj_refs_table(struct hashmap *map) {}
+void emit_obj_refs_plain(struct hashmap *map, __u32 id, const char *prefix) {}
+void emit_obj_refs_json(struct hashmap *map, __u32 id, json_writer_t *json_writer) {}
 
 #else /* BPFTOOL_WITHOUT_SKELETONS */
 
 #include "pid_iter.skel.h"
 
-static void add_ref(struct obj_refs_table *table, struct pid_iter_entry *e)
+static void add_ref(struct hashmap *map, struct pid_iter_entry *e)
 {
+	struct hashmap_entry *entry;
 	struct obj_refs *refs;
 	struct obj_ref *ref;
+	int err, i;
 	void *tmp;
-	int i;
 
-	hash_for_each_possible(table->table, refs, node, e->id) {
-		if (refs->id != e->id)
-			continue;
+	hashmap__for_each_key_entry(map, entry, u32_as_hash_field(e->id)) {
+		refs = entry->value;
 
 		for (i = 0; i < refs->ref_cnt; i++) {
 			if (refs->refs[i].pid == e->pid)
@@ -64,7 +66,6 @@ static void add_ref(struct obj_refs_table *table, struct pid_iter_entry *e)
 		return;
 	}
 
-	refs->id = e->id;
 	refs->refs = malloc(sizeof(*refs->refs));
 	if (!refs->refs) {
 		free(refs);
@@ -76,7 +77,11 @@ static void add_ref(struct obj_refs_table *table, struct pid_iter_entry *e)
 	ref->pid = e->pid;
 	memcpy(ref->comm, e->comm, sizeof(ref->comm));
 	refs->ref_cnt = 1;
-	hash_add(table->table, &refs->node, e->id);
+
+	err = hashmap__append(map, u32_as_hash_field(e->id), refs);
+	if (err)
+		p_err("failed to append entry to hashmap for ID %u: %s",
+		      e->id, strerror(errno));
 }
 
 static int __printf(2, 0)
@@ -87,7 +92,7 @@ libbpf_print_none(__maybe_unused enum libbpf_print_level level,
 	return 0;
 }
 
-int build_obj_refs_table(struct obj_refs_table *table, enum bpf_obj_type type)
+int build_obj_refs_table(struct hashmap **map, enum bpf_obj_type type)
 {
 	struct pid_iter_entry *e;
 	char buf[4096 / sizeof(*e) * sizeof(*e)];
@@ -95,7 +100,11 @@ int build_obj_refs_table(struct obj_refs_table *table, enum bpf_obj_type type)
 	int err, ret, fd = -1, i;
 	libbpf_print_fn_t default_print;
 
-	hash_init(table->table);
+	*map = hashmap__new(hash_fn_for_key_as_id, equal_fn_for_key_as_id, NULL);
+	if (!*map) {
+		p_err("failed to create hashmap for PID references");
+		return -1;
+	}
 	set_max_rlimit();
 
 	skel = pid_iter_bpf__open();
@@ -151,7 +160,7 @@ int build_obj_refs_table(struct obj_refs_table *table, enum bpf_obj_type type)
 
 		e = (void *)buf;
 		for (i = 0; i < ret; i++, e++) {
-			add_ref(table, e);
+			add_ref(*map, e);
 		}
 	}
 	err = 0;
@@ -162,39 +171,44 @@ out:
 	return err;
 }
 
-void delete_obj_refs_table(struct obj_refs_table *table)
+void delete_obj_refs_table(struct hashmap *map)
 {
-	struct obj_refs *refs;
-	struct hlist_node *tmp;
-	unsigned int bkt;
+	struct hashmap_entry *entry;
+	size_t bkt;
+
+	if (!map)
+		return;
+
+	hashmap__for_each_entry(map, entry, bkt) {
+		struct obj_refs *refs = entry->value;
 
-	hash_for_each_safe(table->table, bkt, tmp, refs, node) {
-		hash_del(&refs->node);
 		free(refs->refs);
 		free(refs);
 	}
+
+	hashmap__free(map);
 }
 
-void emit_obj_refs_json(struct obj_refs_table *table, __u32 id,
+void emit_obj_refs_json(struct hashmap *map, __u32 id,
 			json_writer_t *json_writer)
 {
-	struct obj_refs *refs;
-	struct obj_ref *ref;
-	int i;
+	struct hashmap_entry *entry;
 
-	if (hash_empty(table->table))
+	if (hashmap__empty(map))
 		return;
 
-	hash_for_each_possible(table->table, refs, node, id) {
-		if (refs->id != id)
-			continue;
+	hashmap__for_each_key_entry(map, entry, u32_as_hash_field(id)) {
+		struct obj_refs *refs = entry->value;
+		int i;
+
 		if (refs->ref_cnt == 0)
 			break;
 
 		jsonw_name(json_writer, "pids");
 		jsonw_start_array(json_writer);
 		for (i = 0; i < refs->ref_cnt; i++) {
-			ref = &refs->refs[i];
+			struct obj_ref *ref = &refs->refs[i];
+
 			jsonw_start_object(json_writer);
 			jsonw_int_field(json_writer, "pid", ref->pid);
 			jsonw_string_field(json_writer, "comm", ref->comm);
@@ -205,24 +219,24 @@ void emit_obj_refs_json(struct obj_refs_table *table, __u32 id,
 	}
 }
 
-void emit_obj_refs_plain(struct obj_refs_table *table, __u32 id, const char *prefix)
+void emit_obj_refs_plain(struct hashmap *map, __u32 id, const char *prefix)
 {
-	struct obj_refs *refs;
-	struct obj_ref *ref;
-	int i;
+	struct hashmap_entry *entry;
 
-	if (hash_empty(table->table))
+	if (hashmap__empty(map))
 		return;
 
-	hash_for_each_possible(table->table, refs, node, id) {
-		if (refs->id != id)
-			continue;
+	hashmap__for_each_key_entry(map, entry, u32_as_hash_field(id)) {
+		struct obj_refs *refs = entry->value;
+		int i;
+
 		if (refs->ref_cnt == 0)
 			break;
 
 		printf("%s", prefix);
 		for (i = 0; i < refs->ref_cnt; i++) {
-			ref = &refs->refs[i];
+			struct obj_ref *ref = &refs->refs[i];
+
 			printf("%s%s(%d)", i == 0 ? "" : ", ", ref->comm, ref->pid);
 		}
 		break;
diff --git a/tools/bpf/bpftool/prog.c b/tools/bpf/bpftool/prog.c
index 8fce78ce6f8b..515d22952602 100644
--- a/tools/bpf/bpftool/prog.c
+++ b/tools/bpf/bpftool/prog.c
@@ -430,7 +430,7 @@ static void print_prog_json(struct bpf_prog_info *info, int fd)
 		jsonw_end_array(json_wtr);
 	}
 
-	emit_obj_refs_json(&refs_table, info->id, json_wtr);
+	emit_obj_refs_json(refs_table, info->id, json_wtr);
 
 	show_prog_metadata(fd, info->nr_map_ids);
 
@@ -501,7 +501,7 @@ static void print_prog_plain(struct bpf_prog_info *info, int fd)
 	if (info->btf_id)
 		printf("\n\tbtf_id %d", info->btf_id);
 
-	emit_obj_refs_plain(&refs_table, info->id, "\n\tpids ");
+	emit_obj_refs_plain(refs_table, info->id, "\n\tpids ");
 
 	printf("\n");
 
@@ -619,7 +619,7 @@ static int do_show(int argc, char **argv)
 	if (json_output)
 		jsonw_end_array(json_wtr);
 
-	delete_obj_refs_table(&refs_table);
+	delete_obj_refs_table(refs_table);
 
 	if (show_pinned)
 		delete_pinned_obj_table(prog_table);
-- 
cgit v1.2.3


From de5d0dcef602de39070c31c7e56c58249c56ba37 Mon Sep 17 00:00:00 2001
From: Andrii Nakryiko <andrii@kernel.org>
Date: Mon, 25 Oct 2021 15:45:28 -0700
Subject: libbpf: Fix off-by-one bug in bpf_core_apply_relo()

Fix instruction index validity check which has off-by-one error.

Fixes: 3ee4f5335511 ("libbpf: Split bpf_core_apply_relo() into bpf_program independent helper.")
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20211025224531.1088894-2-andrii@kernel.org
---
 tools/lib/bpf/libbpf.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'tools')

diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 604abe00785f..e27a249d46fb 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -5405,7 +5405,7 @@ static int bpf_core_apply_relo(struct bpf_program *prog,
 	 * relocated, so it's enough to just subtract in-section offset
 	 */
 	insn_idx = insn_idx - prog->sec_insn_off;
-	if (insn_idx > prog->insns_cnt)
+	if (insn_idx >= prog->insns_cnt)
 		return -EINVAL;
 	insn = &prog->insns[insn_idx];
 
-- 
cgit v1.2.3


From 65a7fa2e4e5381d205d3b0098da0fc8471fbbfb6 Mon Sep 17 00:00:00 2001
From: Andrii Nakryiko <andrii@kernel.org>
Date: Mon, 25 Oct 2021 15:45:29 -0700
Subject: libbpf: Add ability to fetch bpf_program's underlying instructions

Add APIs providing read-only access to bpf_program BPF instructions ([0]).
This is useful for diagnostics purposes, but it also allows a cleaner
support for cloning BPF programs after libbpf did all the FD resolution
and CO-RE relocations, subprog instructions appending, etc. Currently,
cloning BPF program is possible only through hijacking a half-broken
bpf_program__set_prep() API, which doesn't really work well for anything
but most primitive programs. For instance, set_prep() API doesn't allow
adjusting BPF program load parameters which are necessary for loading
fentry/fexit BPF programs (the case where BPF program cloning is
a necessity if doing some sort of mass-attachment functionality).

Given bpf_program__set_prep() API is set to be deprecated, having
a cleaner alternative is a must. libbpf internally already keeps track
of linear array of struct bpf_insn, so it's not hard to expose it. The
only gotcha is that libbpf previously freed instructions array during
bpf_object load time, which would make this API much less useful overall,
because in between bpf_object__open() and bpf_object__load() a lot of
changes to instructions are done by libbpf.

So this patch makes libbpf hold onto prog->insns array even after BPF
program loading. I think this is a small price for added functionality
and improved introspection of BPF program code.

See retsnoop PR ([1]) for how it can be used in practice and code
savings compared to relying on bpf_program__set_prep().

  [0] Closes: https://github.com/libbpf/libbpf/issues/298
  [1] https://github.com/anakryiko/retsnoop/pull/1

Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20211025224531.1088894-3-andrii@kernel.org
---
 tools/lib/bpf/libbpf.c   | 12 ++++++++++--
 tools/lib/bpf/libbpf.h   | 36 ++++++++++++++++++++++++++++++++++--
 tools/lib/bpf/libbpf.map |  2 ++
 3 files changed, 46 insertions(+), 4 deletions(-)

(limited to 'tools')

diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index e27a249d46fb..dc86ad24dfcb 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -6653,8 +6653,6 @@ int bpf_program__load(struct bpf_program *prog, char *license, __u32 kern_ver)
 out:
 	if (err)
 		pr_warn("failed to load program '%s'\n", prog->name);
-	zfree(&prog->insns);
-	prog->insns_cnt = 0;
 	return libbpf_err(err);
 }
 
@@ -8143,6 +8141,16 @@ size_t bpf_program__size(const struct bpf_program *prog)
 	return prog->insns_cnt * BPF_INSN_SZ;
 }
 
+const struct bpf_insn *bpf_program__insns(const struct bpf_program *prog)
+{
+	return prog->insns;
+}
+
+size_t bpf_program__insn_cnt(const struct bpf_program *prog)
+{
+	return prog->insns_cnt;
+}
+
 int bpf_program__set_prep(struct bpf_program *prog, int nr_instances,
 			  bpf_program_prep_t prep)
 {
diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h
index 89ca9c83ed4e..c6bcc5b98906 100644
--- a/tools/lib/bpf/libbpf.h
+++ b/tools/lib/bpf/libbpf.h
@@ -226,6 +226,40 @@ LIBBPF_API int bpf_program__set_autoload(struct bpf_program *prog, bool autoload
 /* returns program size in bytes */
 LIBBPF_API size_t bpf_program__size(const struct bpf_program *prog);
 
+struct bpf_insn;
+
+/**
+ * @brief **bpf_program__insns()** gives read-only access to BPF program's
+ * underlying BPF instructions.
+ * @param prog BPF program for which to return instructions
+ * @return a pointer to an array of BPF instructions that belong to the
+ * specified BPF program
+ *
+ * Returned pointer is always valid and not NULL. Number of `struct bpf_insn`
+ * pointed to can be fetched using **bpf_program__insn_cnt()** API.
+ *
+ * Keep in mind, libbpf can modify and append/delete BPF program's
+ * instructions as it processes BPF object file and prepares everything for
+ * uploading into the kernel. So depending on the point in BPF object
+ * lifetime, **bpf_program__insns()** can return different sets of
+ * instructions. As an example, during BPF object load phase BPF program
+ * instructions will be CO-RE-relocated, BPF subprograms instructions will be
+ * appended, ldimm64 instructions will have FDs embedded, etc. So instructions
+ * returned before **bpf_object__load()** and after it might be quite
+ * different.
+ */
+LIBBPF_API const struct bpf_insn *bpf_program__insns(const struct bpf_program *prog);
+/**
+ * @brief **bpf_program__insn_cnt()** returns number of `struct bpf_insn`'s
+ * that form specified BPF program.
+ * @param prog BPF program for which to return number of BPF instructions
+ *
+ * See **bpf_program__insns()** documentation for notes on how libbpf can
+ * change instructions and their count during different phases of
+ * **bpf_object** lifetime.
+ */
+LIBBPF_API size_t bpf_program__insn_cnt(const struct bpf_program *prog);
+
 LIBBPF_API int bpf_program__load(struct bpf_program *prog, char *license,
 				 __u32 kern_version);
 LIBBPF_API int bpf_program__fd(const struct bpf_program *prog);
@@ -365,8 +399,6 @@ LIBBPF_API struct bpf_link *
 bpf_program__attach_iter(const struct bpf_program *prog,
 			 const struct bpf_iter_attach_opts *opts);
 
-struct bpf_insn;
-
 /*
  * Libbpf allows callers to adjust BPF programs before being loaded
  * into kernel. One program in an object file can be transformed into
diff --git a/tools/lib/bpf/libbpf.map b/tools/lib/bpf/libbpf.map
index 116964a29e44..15239c05659c 100644
--- a/tools/lib/bpf/libbpf.map
+++ b/tools/lib/bpf/libbpf.map
@@ -393,6 +393,8 @@ LIBBPF_0.6.0 {
 		bpf_object__next_program;
 		bpf_object__prev_map;
 		bpf_object__prev_program;
+		bpf_program__insn_cnt;
+		bpf_program__insns;
 		btf__add_btf;
 		btf__add_decl_tag;
 		btf__raw_data;
-- 
cgit v1.2.3


From e21d585cb3db65a207cd338c74b9886090ef1ceb Mon Sep 17 00:00:00 2001
From: Andrii Nakryiko <andrii@kernel.org>
Date: Mon, 25 Oct 2021 15:45:30 -0700
Subject: libbpf: Deprecate multi-instance bpf_program APIs

Schedule deprecation of a set of APIs that are related to multi-instance
bpf_programs:
  - bpf_program__set_prep() ([0]);
  - bpf_program__{set,unset}_instance() ([1]);
  - bpf_program__nth_fd().

These APIs are obscure, very niche, and don't seem to be used much in
practice. bpf_program__set_prep() is pretty useless for anything but the
simplest BPF programs, as it doesn't allow to adjust BPF program load
attributes, among other things. In short, it already bitrotted and will
bitrot some more if not removed.

With bpf_program__insns() API, which gives access to post-processed BPF
program instructions of any given entry-point BPF program, it's now
possible to do whatever necessary adjustments were possible with
set_prep() API before, but also more. Given any such use case is
automatically an advanced use case, requiring users to stick to
low-level bpf_prog_load() APIs and managing their own prog FDs is
reasonable.

  [0] Closes: https://github.com/libbpf/libbpf/issues/299
  [1] Closes: https://github.com/libbpf/libbpf/issues/300

Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20211025224531.1088894-4-andrii@kernel.org
---
 tools/lib/bpf/libbpf.c | 22 +++++++++++++---------
 tools/lib/bpf/libbpf.h |  6 +++++-
 2 files changed, 18 insertions(+), 10 deletions(-)

(limited to 'tools')

diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index dc86ad24dfcb..4b2158657507 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -7358,8 +7358,7 @@ static int check_path(const char *path)
 	return err;
 }
 
-int bpf_program__pin_instance(struct bpf_program *prog, const char *path,
-			      int instance)
+static int bpf_program_pin_instance(struct bpf_program *prog, const char *path, int instance)
 {
 	char *cp, errmsg[STRERR_BUFSIZE];
 	int err;
@@ -7394,8 +7393,7 @@ int bpf_program__pin_instance(struct bpf_program *prog, const char *path,
 	return 0;
 }
 
-int bpf_program__unpin_instance(struct bpf_program *prog, const char *path,
-				int instance)
+static int bpf_program_unpin_instance(struct bpf_program *prog, const char *path, int instance)
 {
 	int err;
 
@@ -7423,6 +7421,12 @@ int bpf_program__unpin_instance(struct bpf_program *prog, const char *path,
 	return 0;
 }
 
+__attribute__((alias("bpf_program_pin_instance")))
+int bpf_object__pin_instance(struct bpf_program *prog, const char *path, int instance);
+
+__attribute__((alias("bpf_program_unpin_instance")))
+int bpf_program__unpin_instance(struct bpf_program *prog, const char *path, int instance);
+
 int bpf_program__pin(struct bpf_program *prog, const char *path)
 {
 	int i, err;
@@ -7447,7 +7451,7 @@ int bpf_program__pin(struct bpf_program *prog, const char *path)
 
 	if (prog->instances.nr == 1) {
 		/* don't create subdirs when pinning single instance */
-		return bpf_program__pin_instance(prog, path, 0);
+		return bpf_program_pin_instance(prog, path, 0);
 	}
 
 	for (i = 0; i < prog->instances.nr; i++) {
@@ -7463,7 +7467,7 @@ int bpf_program__pin(struct bpf_program *prog, const char *path)
 			goto err_unpin;
 		}
 
-		err = bpf_program__pin_instance(prog, buf, i);
+		err = bpf_program_pin_instance(prog, buf, i);
 		if (err)
 			goto err_unpin;
 	}
@@ -7481,7 +7485,7 @@ err_unpin:
 		else if (len >= PATH_MAX)
 			continue;
 
-		bpf_program__unpin_instance(prog, buf, i);
+		bpf_program_unpin_instance(prog, buf, i);
 	}
 
 	rmdir(path);
@@ -7509,7 +7513,7 @@ int bpf_program__unpin(struct bpf_program *prog, const char *path)
 
 	if (prog->instances.nr == 1) {
 		/* don't create subdirs when pinning single instance */
-		return bpf_program__unpin_instance(prog, path, 0);
+		return bpf_program_unpin_instance(prog, path, 0);
 	}
 
 	for (i = 0; i < prog->instances.nr; i++) {
@@ -7522,7 +7526,7 @@ int bpf_program__unpin(struct bpf_program *prog, const char *path)
 		else if (len >= PATH_MAX)
 			return libbpf_err(-ENAMETOOLONG);
 
-		err = bpf_program__unpin_instance(prog, buf, i);
+		err = bpf_program_unpin_instance(prog, buf, i);
 		if (err)
 			return err;
 	}
diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h
index c6bcc5b98906..449eeed80be6 100644
--- a/tools/lib/bpf/libbpf.h
+++ b/tools/lib/bpf/libbpf.h
@@ -263,9 +263,11 @@ LIBBPF_API size_t bpf_program__insn_cnt(const struct bpf_program *prog);
 LIBBPF_API int bpf_program__load(struct bpf_program *prog, char *license,
 				 __u32 kern_version);
 LIBBPF_API int bpf_program__fd(const struct bpf_program *prog);
+LIBBPF_DEPRECATED_SINCE(0, 7, "multi-instance bpf_program support is deprecated")
 LIBBPF_API int bpf_program__pin_instance(struct bpf_program *prog,
 					 const char *path,
 					 int instance);
+LIBBPF_DEPRECATED_SINCE(0, 7, "multi-instance bpf_program support is deprecated")
 LIBBPF_API int bpf_program__unpin_instance(struct bpf_program *prog,
 					   const char *path,
 					   int instance);
@@ -427,7 +429,7 @@ bpf_program__attach_iter(const struct bpf_program *prog,
  * one instance. In this case bpf_program__fd(prog) is equal to
  * bpf_program__nth_fd(prog, 0).
  */
-
+LIBBPF_DEPRECATED_SINCE(0, 7, "use bpf_program__insns() for getting bpf_program instructions")
 struct bpf_prog_prep_result {
 	/*
 	 * If not NULL, load new instruction array.
@@ -456,9 +458,11 @@ typedef int (*bpf_program_prep_t)(struct bpf_program *prog, int n,
 				  struct bpf_insn *insns, int insns_cnt,
 				  struct bpf_prog_prep_result *res);
 
+LIBBPF_DEPRECATED_SINCE(0, 7, "use bpf_program__insns() for getting bpf_program instructions")
 LIBBPF_API int bpf_program__set_prep(struct bpf_program *prog, int nr_instance,
 				     bpf_program_prep_t prep);
 
+LIBBPF_DEPRECATED_SINCE(0, 7, "multi-instance bpf_program support is deprecated")
 LIBBPF_API int bpf_program__nth_fd(const struct bpf_program *prog, int n);
 
 /*
-- 
cgit v1.2.3


From c4813e969ac471af730902377a2656b6b1b92c4d Mon Sep 17 00:00:00 2001
From: Andrii Nakryiko <andrii@kernel.org>
Date: Mon, 25 Oct 2021 15:45:31 -0700
Subject: libbpf: Deprecate ambiguously-named bpf_program__size() API

The name of the API doesn't convey clearly that this size is in number
of bytes (there needed to be a separate comment to make this clear in
libbpf.h). Further, measuring the size of BPF program in bytes is not
exactly the best fit, because BPF programs always consist of 8-byte
instructions. As such, bpf_program__insn_cnt() is a better alternative
in pretty much any imaginable case.

So schedule bpf_program__size() deprecation starting from v0.7 and it
will be removed in libbpf 1.0.

Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20211025224531.1088894-5-andrii@kernel.org
---
 tools/lib/bpf/libbpf.h | 1 +
 1 file changed, 1 insertion(+)

(limited to 'tools')

diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h
index 449eeed80be6..e1900819bfab 100644
--- a/tools/lib/bpf/libbpf.h
+++ b/tools/lib/bpf/libbpf.h
@@ -224,6 +224,7 @@ LIBBPF_API bool bpf_program__autoload(const struct bpf_program *prog);
 LIBBPF_API int bpf_program__set_autoload(struct bpf_program *prog, bool autoload);
 
 /* returns program size in bytes */
+LIBBPF_DEPRECATED_SINCE(0, 7, "use bpf_program__insn_cnt() instead")
 LIBBPF_API size_t bpf_program__size(const struct bpf_program *prog);
 
 struct bpf_insn;
-- 
cgit v1.2.3


From 45f2bebc8079788f62f22d9e8b2819afb1789d7b Mon Sep 17 00:00:00 2001
From: Ilya Leoshkevich <iii@linux.ibm.com>
Date: Tue, 26 Oct 2021 03:08:26 +0200
Subject: libbpf: Fix endianness detection in BPF_CORE_READ_BITFIELD_PROBED()

__BYTE_ORDER is supposed to be defined by a libc, and __BYTE_ORDER__ -
by a compiler. bpf_core_read.h checks __BYTE_ORDER == __LITTLE_ENDIAN,
which is true if neither are defined, leading to incorrect behavior on
big-endian hosts if libc headers are not included, which is often the
case.

Fixes: ee26dade0e3b ("libbpf: Add support for relocatable bitfields")
Signed-off-by: Ilya Leoshkevich <iii@linux.ibm.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20211026010831.748682-2-iii@linux.ibm.com
---
 tools/lib/bpf/bpf_core_read.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'tools')

diff --git a/tools/lib/bpf/bpf_core_read.h b/tools/lib/bpf/bpf_core_read.h
index 09ebe3db5f2f..e4aa9996a550 100644
--- a/tools/lib/bpf/bpf_core_read.h
+++ b/tools/lib/bpf/bpf_core_read.h
@@ -40,7 +40,7 @@ enum bpf_enum_value_kind {
 #define __CORE_RELO(src, field, info)					      \
 	__builtin_preserve_field_info((src)->field, BPF_FIELD_##info)
 
-#if __BYTE_ORDER == __LITTLE_ENDIAN
+#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__
 #define __CORE_BITFIELD_PROBE_READ(dst, src, fld)			      \
 	bpf_probe_read_kernel(						      \
 			(void *)dst,				      \
-- 
cgit v1.2.3


From 3930198dc9a0720a2b6561c67e55859ec51b73f9 Mon Sep 17 00:00:00 2001
From: Ilya Leoshkevich <iii@linux.ibm.com>
Date: Tue, 26 Oct 2021 03:08:27 +0200
Subject: libbpf: Use __BYTE_ORDER__

Use the compiler-defined __BYTE_ORDER__ instead of the libc-defined
__BYTE_ORDER for consistency.

Signed-off-by: Ilya Leoshkevich <iii@linux.ibm.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20211026010831.748682-3-iii@linux.ibm.com
---
 tools/lib/bpf/btf.c       |  4 ++--
 tools/lib/bpf/btf_dump.c  |  8 ++++----
 tools/lib/bpf/libbpf.c    |  4 ++--
 tools/lib/bpf/linker.c    | 12 ++++++------
 tools/lib/bpf/relo_core.c |  2 +-
 5 files changed, 15 insertions(+), 15 deletions(-)

(limited to 'tools')

diff --git a/tools/lib/bpf/btf.c b/tools/lib/bpf/btf.c
index ef924fc2c911..0c628c33e23b 100644
--- a/tools/lib/bpf/btf.c
+++ b/tools/lib/bpf/btf.c
@@ -538,9 +538,9 @@ int btf__set_pointer_size(struct btf *btf, size_t ptr_sz)
 
 static bool is_host_big_endian(void)
 {
-#if __BYTE_ORDER == __LITTLE_ENDIAN
+#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__
 	return false;
-#elif __BYTE_ORDER == __BIG_ENDIAN
+#elif __BYTE_ORDER__ == __ORDER_BIG_ENDIAN__
 	return true;
 #else
 # error "Unrecognized __BYTE_ORDER__"
diff --git a/tools/lib/bpf/btf_dump.c b/tools/lib/bpf/btf_dump.c
index 8e05ab44c22a..17db62b5002e 100644
--- a/tools/lib/bpf/btf_dump.c
+++ b/tools/lib/bpf/btf_dump.c
@@ -1576,11 +1576,11 @@ static int btf_dump_get_bitfield_value(struct btf_dump *d,
 	/* Bitfield value retrieval is done in two steps; first relevant bytes are
 	 * stored in num, then we left/right shift num to eliminate irrelevant bits.
 	 */
-#if __BYTE_ORDER == __LITTLE_ENDIAN
+#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__
 	for (i = t->size - 1; i >= 0; i--)
 		num = num * 256 + bytes[i];
 	nr_copy_bits = bit_sz + bits_offset;
-#elif __BYTE_ORDER == __BIG_ENDIAN
+#elif __BYTE_ORDER__ == __ORDER_BIG_ENDIAN__
 	for (i = 0; i < t->size; i++)
 		num = num * 256 + bytes[i];
 	nr_copy_bits = t->size * 8 - bits_offset;
@@ -1700,10 +1700,10 @@ static int btf_dump_int_data(struct btf_dump *d,
 		/* avoid use of __int128 as some 32-bit platforms do not
 		 * support it.
 		 */
-#if __BYTE_ORDER == __LITTLE_ENDIAN
+#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__
 		lsi = ints[0];
 		msi = ints[1];
-#elif __BYTE_ORDER == __BIG_ENDIAN
+#elif __BYTE_ORDER__ == __ORDER_BIG_ENDIAN__
 		lsi = ints[1];
 		msi = ints[0];
 #else
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 4b2158657507..2fbed2d4a645 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -1299,10 +1299,10 @@ errout:
 
 static int bpf_object__check_endianness(struct bpf_object *obj)
 {
-#if __BYTE_ORDER == __LITTLE_ENDIAN
+#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__
 	if (obj->efile.ehdr->e_ident[EI_DATA] == ELFDATA2LSB)
 		return 0;
-#elif __BYTE_ORDER == __BIG_ENDIAN
+#elif __BYTE_ORDER__ == __ORDER_BIG_ENDIAN__
 	if (obj->efile.ehdr->e_ident[EI_DATA] == ELFDATA2MSB)
 		return 0;
 #else
diff --git a/tools/lib/bpf/linker.c b/tools/lib/bpf/linker.c
index 7bf658fbda80..ce0800e61dc7 100644
--- a/tools/lib/bpf/linker.c
+++ b/tools/lib/bpf/linker.c
@@ -323,12 +323,12 @@ static int init_output_elf(struct bpf_linker *linker, const char *file)
 
 	linker->elf_hdr->e_machine = EM_BPF;
 	linker->elf_hdr->e_type = ET_REL;
-#if __BYTE_ORDER == __LITTLE_ENDIAN
+#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__
 	linker->elf_hdr->e_ident[EI_DATA] = ELFDATA2LSB;
-#elif __BYTE_ORDER == __BIG_ENDIAN
+#elif __BYTE_ORDER__ == __ORDER_BIG_ENDIAN__
 	linker->elf_hdr->e_ident[EI_DATA] = ELFDATA2MSB;
 #else
-#error "Unknown __BYTE_ORDER"
+#error "Unknown __BYTE_ORDER__"
 #endif
 
 	/* STRTAB */
@@ -538,12 +538,12 @@ static int linker_load_obj_file(struct bpf_linker *linker, const char *filename,
 				const struct bpf_linker_file_opts *opts,
 				struct src_obj *obj)
 {
-#if __BYTE_ORDER == __LITTLE_ENDIAN
+#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__
 	const int host_endianness = ELFDATA2LSB;
-#elif __BYTE_ORDER == __BIG_ENDIAN
+#elif __BYTE_ORDER__ == __ORDER_BIG_ENDIAN__
 	const int host_endianness = ELFDATA2MSB;
 #else
-#error "Unknown __BYTE_ORDER"
+#error "Unknown __BYTE_ORDER__"
 #endif
 	int err = 0;
 	Elf_Scn *scn;
diff --git a/tools/lib/bpf/relo_core.c b/tools/lib/bpf/relo_core.c
index 4016ed492d0c..b5b8956a1be8 100644
--- a/tools/lib/bpf/relo_core.c
+++ b/tools/lib/bpf/relo_core.c
@@ -662,7 +662,7 @@ static int bpf_core_calc_field_relo(const char *prog_name,
 			*validate = true; /* signedness is never ambiguous */
 		break;
 	case BPF_FIELD_LSHIFT_U64:
-#if __BYTE_ORDER == __LITTLE_ENDIAN
+#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__
 		*val = 64 - (bit_off + bit_sz - byte_off  * 8);
 #else
 		*val = (8 - byte_sz) * 8 + (bit_off - byte_off * 8);
-- 
cgit v1.2.3


From 06fca841fb64c9ed499a3575a530014268d0251a Mon Sep 17 00:00:00 2001
From: Ilya Leoshkevich <iii@linux.ibm.com>
Date: Tue, 26 Oct 2021 03:08:28 +0200
Subject: selftests/bpf: Use __BYTE_ORDER__

Use the compiler-defined __BYTE_ORDER__ instead of the libc-defined
__BYTE_ORDER for consistency.

Signed-off-by: Ilya Leoshkevich <iii@linux.ibm.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20211026010831.748682-4-iii@linux.ibm.com
---
 tools/testing/selftests/bpf/prog_tests/btf_endian.c        |  6 +++---
 tools/testing/selftests/bpf/test_sysctl.c                  |  4 ++--
 tools/testing/selftests/bpf/verifier/ctx_skb.c             | 14 +++++++-------
 tools/testing/selftests/bpf/verifier/lwt.c                 |  2 +-
 .../selftests/bpf/verifier/perf_event_sample_period.c      |  6 +++---
 5 files changed, 16 insertions(+), 16 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/prog_tests/btf_endian.c b/tools/testing/selftests/bpf/prog_tests/btf_endian.c
index 2653cc482df4..8afbf3d0b89a 100644
--- a/tools/testing/selftests/bpf/prog_tests/btf_endian.c
+++ b/tools/testing/selftests/bpf/prog_tests/btf_endian.c
@@ -7,12 +7,12 @@
 #include <bpf/btf.h>
 
 void test_btf_endian() {
-#if __BYTE_ORDER == __LITTLE_ENDIAN
+#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__
 	enum btf_endianness endian = BTF_LITTLE_ENDIAN;
-#elif __BYTE_ORDER == __BIG_ENDIAN
+#elif __BYTE_ORDER__ == __ORDER_BIG_ENDIAN__
 	enum btf_endianness endian = BTF_BIG_ENDIAN;
 #else
-#error "Unrecognized __BYTE_ORDER"
+#error "Unrecognized __BYTE_ORDER__"
 #endif
 	enum btf_endianness swap_endian = 1 - endian;
 	struct btf *btf = NULL, *swap_btf = NULL;
diff --git a/tools/testing/selftests/bpf/test_sysctl.c b/tools/testing/selftests/bpf/test_sysctl.c
index a20a919244c0..a3bb6d399daa 100644
--- a/tools/testing/selftests/bpf/test_sysctl.c
+++ b/tools/testing/selftests/bpf/test_sysctl.c
@@ -124,7 +124,7 @@ static struct sysctl_test tests[] = {
 		.descr = "ctx:write sysctl:write read ok narrow",
 		.insns = {
 			/* u64 w = (u16)write & 1; */
-#if __BYTE_ORDER == __LITTLE_ENDIAN
+#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__
 			BPF_LDX_MEM(BPF_H, BPF_REG_7, BPF_REG_1,
 				    offsetof(struct bpf_sysctl, write)),
 #else
@@ -184,7 +184,7 @@ static struct sysctl_test tests[] = {
 		.descr = "ctx:file_pos sysctl:read read ok narrow",
 		.insns = {
 			/* If (file_pos == X) */
-#if __BYTE_ORDER == __LITTLE_ENDIAN
+#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__
 			BPF_LDX_MEM(BPF_B, BPF_REG_7, BPF_REG_1,
 				    offsetof(struct bpf_sysctl, file_pos)),
 #else
diff --git a/tools/testing/selftests/bpf/verifier/ctx_skb.c b/tools/testing/selftests/bpf/verifier/ctx_skb.c
index 9e1a30b94197..83cecfbd6739 100644
--- a/tools/testing/selftests/bpf/verifier/ctx_skb.c
+++ b/tools/testing/selftests/bpf/verifier/ctx_skb.c
@@ -502,7 +502,7 @@
 	"check skb->hash byte load permitted",
 	.insns = {
 	BPF_MOV64_IMM(BPF_REG_0, 0),
-#if __BYTE_ORDER == __LITTLE_ENDIAN
+#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__
 	BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1,
 		    offsetof(struct __sk_buff, hash)),
 #else
@@ -537,7 +537,7 @@
 	"check skb->hash byte load permitted 3",
 	.insns = {
 	BPF_MOV64_IMM(BPF_REG_0, 0),
-#if __BYTE_ORDER == __LITTLE_ENDIAN
+#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__
 	BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1,
 		    offsetof(struct __sk_buff, hash) + 3),
 #else
@@ -646,7 +646,7 @@
 	"check skb->hash half load permitted",
 	.insns = {
 	BPF_MOV64_IMM(BPF_REG_0, 0),
-#if __BYTE_ORDER == __LITTLE_ENDIAN
+#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__
 	BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_1,
 		    offsetof(struct __sk_buff, hash)),
 #else
@@ -661,7 +661,7 @@
 	"check skb->hash half load permitted 2",
 	.insns = {
 	BPF_MOV64_IMM(BPF_REG_0, 0),
-#if __BYTE_ORDER == __LITTLE_ENDIAN
+#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__
 	BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_1,
 		    offsetof(struct __sk_buff, hash) + 2),
 #else
@@ -676,7 +676,7 @@
 	"check skb->hash half load not permitted, unaligned 1",
 	.insns = {
 	BPF_MOV64_IMM(BPF_REG_0, 0),
-#if __BYTE_ORDER == __LITTLE_ENDIAN
+#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__
 	BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_1,
 		    offsetof(struct __sk_buff, hash) + 1),
 #else
@@ -693,7 +693,7 @@
 	"check skb->hash half load not permitted, unaligned 3",
 	.insns = {
 	BPF_MOV64_IMM(BPF_REG_0, 0),
-#if __BYTE_ORDER == __LITTLE_ENDIAN
+#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__
 	BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_1,
 		    offsetof(struct __sk_buff, hash) + 3),
 #else
@@ -951,7 +951,7 @@
 	"check skb->data half load not permitted",
 	.insns = {
 	BPF_MOV64_IMM(BPF_REG_0, 0),
-#if __BYTE_ORDER == __LITTLE_ENDIAN
+#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__
 	BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_1,
 		    offsetof(struct __sk_buff, data)),
 #else
diff --git a/tools/testing/selftests/bpf/verifier/lwt.c b/tools/testing/selftests/bpf/verifier/lwt.c
index 2cab6a3966bb..5c8944d0b091 100644
--- a/tools/testing/selftests/bpf/verifier/lwt.c
+++ b/tools/testing/selftests/bpf/verifier/lwt.c
@@ -174,7 +174,7 @@
 	"check skb->tc_classid half load not permitted for lwt prog",
 	.insns = {
 	BPF_MOV64_IMM(BPF_REG_0, 0),
-#if __BYTE_ORDER == __LITTLE_ENDIAN
+#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__
 	BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_1,
 		    offsetof(struct __sk_buff, tc_classid)),
 #else
diff --git a/tools/testing/selftests/bpf/verifier/perf_event_sample_period.c b/tools/testing/selftests/bpf/verifier/perf_event_sample_period.c
index 471c1a5950d8..d8a9b1a1f9a2 100644
--- a/tools/testing/selftests/bpf/verifier/perf_event_sample_period.c
+++ b/tools/testing/selftests/bpf/verifier/perf_event_sample_period.c
@@ -2,7 +2,7 @@
 	"check bpf_perf_event_data->sample_period byte load permitted",
 	.insns = {
 	BPF_MOV64_IMM(BPF_REG_0, 0),
-#if __BYTE_ORDER == __LITTLE_ENDIAN
+#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__
 	BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1,
 		    offsetof(struct bpf_perf_event_data, sample_period)),
 #else
@@ -18,7 +18,7 @@
 	"check bpf_perf_event_data->sample_period half load permitted",
 	.insns = {
 	BPF_MOV64_IMM(BPF_REG_0, 0),
-#if __BYTE_ORDER == __LITTLE_ENDIAN
+#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__
 	BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_1,
 		    offsetof(struct bpf_perf_event_data, sample_period)),
 #else
@@ -34,7 +34,7 @@
 	"check bpf_perf_event_data->sample_period word load permitted",
 	.insns = {
 	BPF_MOV64_IMM(BPF_REG_0, 0),
-#if __BYTE_ORDER == __LITTLE_ENDIAN
+#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__
 	BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
 		    offsetof(struct bpf_perf_event_data, sample_period)),
 #else
-- 
cgit v1.2.3


From 3e7ed9cebb551ce9bfbf2985da9cdadd8186e1eb Mon Sep 17 00:00:00 2001
From: Ilya Leoshkevich <iii@linux.ibm.com>
Date: Tue, 26 Oct 2021 03:08:30 +0200
Subject: selftests/seccomp: Use __BYTE_ORDER__

Use the compiler-defined __BYTE_ORDER__ instead of the libc-defined
__BYTE_ORDER for consistency.

Signed-off-by: Ilya Leoshkevich <iii@linux.ibm.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20211026010831.748682-6-iii@linux.ibm.com
---
 tools/testing/selftests/seccomp/seccomp_bpf.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/seccomp/seccomp_bpf.c b/tools/testing/selftests/seccomp/seccomp_bpf.c
index 1d64891e6492..d425688cf59c 100644
--- a/tools/testing/selftests/seccomp/seccomp_bpf.c
+++ b/tools/testing/selftests/seccomp/seccomp_bpf.c
@@ -276,12 +276,12 @@ int seccomp(unsigned int op, unsigned int flags, void *args)
 }
 #endif
 
-#if __BYTE_ORDER == __LITTLE_ENDIAN
+#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__
 #define syscall_arg(_n) (offsetof(struct seccomp_data, args[_n]))
-#elif __BYTE_ORDER == __BIG_ENDIAN
+#elif __BYTE_ORDER__ == __ORDER_BIG_ENDIAN__
 #define syscall_arg(_n) (offsetof(struct seccomp_data, args[_n]) + sizeof(__u32))
 #else
-#error "wut? Unknown __BYTE_ORDER?!"
+#error "wut? Unknown __BYTE_ORDER__?!"
 #endif
 
 #define SIBLING_EXIT_UNKILLED	0xbadbeef
-- 
cgit v1.2.3


From 2e2c6d3fb38344df92b63162a28ec09491cc0700 Mon Sep 17 00:00:00 2001
From: Ilya Leoshkevich <iii@linux.ibm.com>
Date: Tue, 26 Oct 2021 03:08:31 +0200
Subject: selftests/bpf: Fix test_core_reloc_mods on big-endian machines

This is the same as commit d164dd9a5c08 ("selftests/bpf: Fix
test_core_autosize on big-endian machines"), but for
test_core_reloc_mods.

Signed-off-by: Ilya Leoshkevich <iii@linux.ibm.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20211026010831.748682-7-iii@linux.ibm.com
---
 tools/testing/selftests/bpf/progs/test_core_reloc_mods.c | 9 +++++++++
 1 file changed, 9 insertions(+)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/progs/test_core_reloc_mods.c b/tools/testing/selftests/bpf/progs/test_core_reloc_mods.c
index 8b533db4a7a5..b2ded497572a 100644
--- a/tools/testing/selftests/bpf/progs/test_core_reloc_mods.c
+++ b/tools/testing/selftests/bpf/progs/test_core_reloc_mods.c
@@ -42,7 +42,16 @@ struct core_reloc_mods {
 	core_reloc_mods_substruct_t h;
 };
 
+#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__
 #define CORE_READ(dst, src) bpf_core_read(dst, sizeof(*(dst)), src)
+#else
+#define CORE_READ(dst, src) ({ \
+	int __sz = sizeof(*(dst)) < sizeof(*(src)) ? sizeof(*(dst)) : \
+						     sizeof(*(src)); \
+	bpf_core_read((char *)(dst) + sizeof(*(dst)) - __sz, __sz, \
+		      (const char *)(src) + sizeof(*(src)) - __sz); \
+})
+#endif
 
 SEC("raw_tracepoint/sys_enter")
 int test_core_mods(void *ctx)
-- 
cgit v1.2.3


From b4e87072762d063f9c20ba0ab2120e1910fa379f Mon Sep 17 00:00:00 2001
From: Song Liu <songliubraving@fb.com>
Date: Mon, 25 Oct 2021 17:07:33 -0700
Subject: selftests/bpf: Skip all serial_test_get_branch_snapshot in vm

Skipping the second half of the test is not enough to silent the warning
in dmesg. Skip the whole test before we can either properly silent the
warning in kernel, or fix LBR snapshot for VM.

Fixes: 025bd7c753aa ("selftests/bpf: Add test for bpf_get_branch_snapshot")
Fixes: aa67fdb46436 ("selftests/bpf: Skip the second half of get_branch_snapshot in vm")
Signed-off-by: Song Liu <songliubraving@fb.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20211026000733.477714-1-songliubraving@fb.com
---
 .../selftests/bpf/prog_tests/get_branch_snapshot.c       | 16 ++++++----------
 1 file changed, 6 insertions(+), 10 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/prog_tests/get_branch_snapshot.c b/tools/testing/selftests/bpf/prog_tests/get_branch_snapshot.c
index d6d70a359aeb..81402e443984 100644
--- a/tools/testing/selftests/bpf/prog_tests/get_branch_snapshot.c
+++ b/tools/testing/selftests/bpf/prog_tests/get_branch_snapshot.c
@@ -78,6 +78,12 @@ void serial_test_get_branch_snapshot(void)
 	struct get_branch_snapshot *skel = NULL;
 	int err;
 
+	/* Skip the test before we fix LBR snapshot for hypervisor. */
+	if (is_hypervisor()) {
+		test__skip();
+		return;
+	}
+
 	if (create_perf_events()) {
 		test__skip();  /* system doesn't support LBR */
 		goto cleanup;
@@ -107,16 +113,6 @@ void serial_test_get_branch_snapshot(void)
 		goto cleanup;
 	}
 
-	if (is_hypervisor()) {
-		/* As of today, LBR in hypervisor cannot be stopped before
-		 * too many entries are flushed. Skip the hit/waste test
-		 * for now in hypervisor until we optimize the LBR in
-		 * hypervisor.
-		 */
-		test__skip();
-		goto cleanup;
-	}
-
 	ASSERT_GT(skel->bss->test1_hits, 6, "find_looptest_in_lbr");
 
 	/* Given we stop LBR in software, we will waste a few entries.
-- 
cgit v1.2.3


From 20d1b54a52bd9a1d5d23a45dab75993ce2f1d617 Mon Sep 17 00:00:00 2001
From: Song Liu <songliubraving@fb.com>
Date: Fri, 22 Oct 2021 16:48:14 -0700
Subject: selftests/bpf: Guess function end for test_get_branch_snapshot

Function in modules could appear in /proc/kallsyms in random order.

ffffffffa02608a0 t bpf_testmod_loop_test
ffffffffa02600c0 t __traceiter_bpf_testmod_test_writable_bare
ffffffffa0263b60 d __tracepoint_bpf_testmod_test_write_bare
ffffffffa02608c0 T bpf_testmod_test_read
ffffffffa0260d08 t __SCT__tp_func_bpf_testmod_test_writable_bare
ffffffffa0263300 d __SCK__tp_func_bpf_testmod_test_read
ffffffffa0260680 T bpf_testmod_test_write
ffffffffa0260860 t bpf_testmod_test_mod_kfunc

Therefore, we cannot reliably use kallsyms_find_next() to find the end of
a function. Replace it with a simple guess (start + 128). This is good
enough for this test.

Signed-off-by: Song Liu <songliubraving@fb.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20211022234814.318457-1-songliubraving@fb.com
---
 .../selftests/bpf/prog_tests/get_branch_snapshot.c |  7 +++--
 tools/testing/selftests/bpf/trace_helpers.c        | 36 ----------------------
 tools/testing/selftests/bpf/trace_helpers.h        |  5 ---
 3 files changed, 4 insertions(+), 44 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/prog_tests/get_branch_snapshot.c b/tools/testing/selftests/bpf/prog_tests/get_branch_snapshot.c
index 81402e443984..3948da12a528 100644
--- a/tools/testing/selftests/bpf/prog_tests/get_branch_snapshot.c
+++ b/tools/testing/selftests/bpf/prog_tests/get_branch_snapshot.c
@@ -97,9 +97,10 @@ void serial_test_get_branch_snapshot(void)
 	if (!ASSERT_OK(err, "kallsyms_find"))
 		goto cleanup;
 
-	err = kallsyms_find_next("bpf_testmod_loop_test", &skel->bss->address_high);
-	if (!ASSERT_OK(err, "kallsyms_find_next"))
-		goto cleanup;
+	/* Just a guess for the end of this function, as module functions
+	 * in /proc/kallsyms could come in any order.
+	 */
+	skel->bss->address_high = skel->bss->address_low + 128;
 
 	err = get_branch_snapshot__attach(skel);
 	if (!ASSERT_OK(err, "get_branch_snapshot__attach"))
diff --git a/tools/testing/selftests/bpf/trace_helpers.c b/tools/testing/selftests/bpf/trace_helpers.c
index 5100a169b72b..7b7f918eda77 100644
--- a/tools/testing/selftests/bpf/trace_helpers.c
+++ b/tools/testing/selftests/bpf/trace_helpers.c
@@ -118,42 +118,6 @@ out:
 	return err;
 }
 
-/* find the address of the next symbol of the same type, this can be used
- * to determine the end of a function.
- */
-int kallsyms_find_next(const char *sym, unsigned long long *addr)
-{
-	char type, found_type, name[500];
-	unsigned long long value;
-	bool found = false;
-	int err = 0;
-	FILE *f;
-
-	f = fopen("/proc/kallsyms", "r");
-	if (!f)
-		return -EINVAL;
-
-	while (fscanf(f, "%llx %c %499s%*[^\n]\n", &value, &type, name) > 0) {
-		/* Different types of symbols in kernel modules are mixed
-		 * in /proc/kallsyms. Only return the next matching type.
-		 * Use tolower() for type so that 'T' matches 't'.
-		 */
-		if (found && found_type == tolower(type)) {
-			*addr = value;
-			goto out;
-		}
-		if (strcmp(name, sym) == 0) {
-			found = true;
-			found_type = tolower(type);
-		}
-	}
-	err = -ENOENT;
-
-out:
-	fclose(f);
-	return err;
-}
-
 void read_trace_pipe(void)
 {
 	int trace_fd;
diff --git a/tools/testing/selftests/bpf/trace_helpers.h b/tools/testing/selftests/bpf/trace_helpers.h
index bc8ed86105d9..d907b445524d 100644
--- a/tools/testing/selftests/bpf/trace_helpers.h
+++ b/tools/testing/selftests/bpf/trace_helpers.h
@@ -16,11 +16,6 @@ long ksym_get_addr(const char *name);
 /* open kallsyms and find addresses on the fly, faster than load + search. */
 int kallsyms_find(const char *sym, unsigned long long *addr);
 
-/* find the address of the next symbol, this can be used to determine the
- * end of a function
- */
-int kallsyms_find_next(const char *sym, unsigned long long *addr);
-
 void read_trace_pipe(void);
 
 ssize_t get_uprobe_offset(const void *addr, ssize_t base);
-- 
cgit v1.2.3


From 152f98e7c5cb472e37d44ff8bb07029e77e9508d Mon Sep 17 00:00:00 2001
From: Danielle Ratson <danieller@nvidia.com>
Date: Tue, 26 Oct 2021 12:42:22 +0300
Subject: selftests: mlxsw: Add a scale test for RIF MAC profiles

Query the maximum number of supported RIF MAC profiles using
devlink-resource and verify that all available MAC profiles can be utilized
and that an error is generated when user space tries to exceed this number.

Output example in Spectrum-2:

$ TESTS='rif_mac_profile' ./resource_scale.sh
TEST: 'rif_mac_profile' 4                                           [ OK ]
TEST: 'rif_mac_profile' overflow 5                                  [ OK ]

Signed-off-by: Danielle Ratson <danieller@nvidia.com>
Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../drivers/net/mlxsw/rif_mac_profile_scale.sh     | 72 ++++++++++++++++++++++
 .../drivers/net/mlxsw/spectrum-2/resource_scale.sh |  2 +-
 .../net/mlxsw/spectrum-2/rif_mac_profile_scale.sh  | 16 +++++
 .../drivers/net/mlxsw/spectrum/resource_scale.sh   |  2 +-
 .../net/mlxsw/spectrum/rif_mac_profile_scale.sh    | 16 +++++
 5 files changed, 106 insertions(+), 2 deletions(-)
 create mode 100644 tools/testing/selftests/drivers/net/mlxsw/rif_mac_profile_scale.sh
 create mode 100644 tools/testing/selftests/drivers/net/mlxsw/spectrum-2/rif_mac_profile_scale.sh
 create mode 100644 tools/testing/selftests/drivers/net/mlxsw/spectrum/rif_mac_profile_scale.sh

(limited to 'tools')

diff --git a/tools/testing/selftests/drivers/net/mlxsw/rif_mac_profile_scale.sh b/tools/testing/selftests/drivers/net/mlxsw/rif_mac_profile_scale.sh
new file mode 100644
index 000000000000..71e7681f15f6
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/mlxsw/rif_mac_profile_scale.sh
@@ -0,0 +1,72 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+# Test for RIF MAC profiles resource. The test adds VLAN netdevices according to
+# the maximum number of RIF MAC profiles, sets each of them with a random
+# MAC address, and checks that eventually the number of occupied RIF MAC
+# profiles equals the maximum number of RIF MAC profiles.
+
+
+RIF_MAC_PROFILE_NUM_NETIFS=2
+
+rif_mac_profiles_create()
+{
+	local count=$1; shift
+	local should_fail=$1; shift
+	local batch_file="$(mktemp)"
+
+	for ((i = 1; i <= count; i++)); do
+		vlan=$(( i*10 ))
+		m=$(( i*11 ))
+
+		cat >> $batch_file <<-EOF
+			link add link $h1 name $h1.$vlan \
+				address 00:$m:$m:$m:$m:$m type vlan id $vlan
+			address add 192.0.$m.1/24 dev $h1.$vlan
+		EOF
+	done
+
+	ip -b $batch_file &> /dev/null
+	check_err_fail $should_fail $? "RIF creation"
+
+	rm -f $batch_file
+}
+
+rif_mac_profile_test()
+{
+	local count=$1; shift
+	local should_fail=$1; shift
+
+	rif_mac_profiles_create $count $should_fail
+
+	occ=$(devlink -j resource show $DEVLINK_DEV \
+	      | jq '.[][][] | select(.name=="rif_mac_profiles") |.["occ"]')
+
+	[[ $occ -eq $count ]]
+	check_err_fail $should_fail $? "Attempt to use $count profiles (actual result $occ)"
+}
+
+rif_mac_profile_setup_prepare()
+{
+	h1=${NETIFS[p1]}
+	h2=${NETIFS[p2]}
+
+	# Disable IPv6 on the two interfaces to avoid IPv6 link-local addresses
+	# being generated and RIFs being created.
+	sysctl_set net.ipv6.conf.$h1.disable_ipv6 1
+	sysctl_set net.ipv6.conf.$h2.disable_ipv6 1
+
+	ip link set $h1 up
+	ip link set $h2 up
+}
+
+rif_mac_profile_cleanup()
+{
+	pre_cleanup
+
+	ip link set $h2 down
+	ip link set $h1 down
+
+	sysctl_restore net.ipv6.conf.$h2.disable_ipv6
+	sysctl_restore net.ipv6.conf.$h1.disable_ipv6
+}
diff --git a/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/resource_scale.sh b/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/resource_scale.sh
index 02b7eea19743..e9f65bd2e299 100755
--- a/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/resource_scale.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/resource_scale.sh
@@ -25,7 +25,7 @@ cleanup()
 
 trap cleanup EXIT
 
-ALL_TESTS="router tc_flower mirror_gre tc_police port"
+ALL_TESTS="router tc_flower mirror_gre tc_police port rif_mac_profile"
 for current_test in ${TESTS:-$ALL_TESTS}; do
 	RET_FIN=0
 	source ${current_test}_scale.sh
diff --git a/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/rif_mac_profile_scale.sh b/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/rif_mac_profile_scale.sh
new file mode 100644
index 000000000000..303d7cbe3c45
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/rif_mac_profile_scale.sh
@@ -0,0 +1,16 @@
+# SPDX-License-Identifier: GPL-2.0
+source ../rif_mac_profile_scale.sh
+
+rif_mac_profile_get_target()
+{
+	local should_fail=$1
+	local target
+
+	target=$(devlink_resource_size_get rif_mac_profiles)
+
+	if ((! should_fail)); then
+		echo $target
+	else
+		echo $((target + 1))
+	fi
+}
diff --git a/tools/testing/selftests/drivers/net/mlxsw/spectrum/resource_scale.sh b/tools/testing/selftests/drivers/net/mlxsw/spectrum/resource_scale.sh
index 685dfb3478b3..bcb110e830ce 100755
--- a/tools/testing/selftests/drivers/net/mlxsw/spectrum/resource_scale.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/spectrum/resource_scale.sh
@@ -22,7 +22,7 @@ cleanup()
 devlink_sp_read_kvd_defaults
 trap cleanup EXIT
 
-ALL_TESTS="router tc_flower mirror_gre tc_police port"
+ALL_TESTS="router tc_flower mirror_gre tc_police port rif_mac_profile"
 for current_test in ${TESTS:-$ALL_TESTS}; do
 	RET_FIN=0
 	source ${current_test}_scale.sh
diff --git a/tools/testing/selftests/drivers/net/mlxsw/spectrum/rif_mac_profile_scale.sh b/tools/testing/selftests/drivers/net/mlxsw/spectrum/rif_mac_profile_scale.sh
new file mode 100644
index 000000000000..303d7cbe3c45
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/mlxsw/spectrum/rif_mac_profile_scale.sh
@@ -0,0 +1,16 @@
+# SPDX-License-Identifier: GPL-2.0
+source ../rif_mac_profile_scale.sh
+
+rif_mac_profile_get_target()
+{
+	local should_fail=$1
+	local target
+
+	target=$(devlink_resource_size_get rif_mac_profiles)
+
+	if ((! should_fail)); then
+		echo $target
+	else
+		echo $((target + 1))
+	fi
+}
-- 
cgit v1.2.3


From a10b7bacde60894b999cf9b5fa194ad55f7ded41 Mon Sep 17 00:00:00 2001
From: Danielle Ratson <danieller@nvidia.com>
Date: Tue, 26 Oct 2021 12:42:23 +0300
Subject: selftests: mlxsw: Add forwarding test for RIF MAC profiles

Verify that MAC profile changes are indeed applied and that packets are
forwarded with the correct source MAC.

Output example:

$ ./rif_mac_profiles.sh
TEST: h1->h2: new mac profile                                       [ OK ]
TEST: h2->h1: new mac profile                                       [ OK ]
TEST: h1->h2: edit mac profile                                      [ OK ]
TEST: h2->h1: edit mac profile                                      [ OK ]

Signed-off-by: Danielle Ratson <danieller@nvidia.com>
Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../drivers/net/mlxsw/rif_mac_profiles.sh          | 213 +++++++++++++++++++++
 1 file changed, 213 insertions(+)
 create mode 100755 tools/testing/selftests/drivers/net/mlxsw/rif_mac_profiles.sh

(limited to 'tools')

diff --git a/tools/testing/selftests/drivers/net/mlxsw/rif_mac_profiles.sh b/tools/testing/selftests/drivers/net/mlxsw/rif_mac_profiles.sh
new file mode 100755
index 000000000000..c18340cee55d
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/mlxsw/rif_mac_profiles.sh
@@ -0,0 +1,213 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+lib_dir=$(dirname $0)/../../../net/forwarding
+
+ALL_TESTS="
+	mac_profile_test
+"
+NUM_NETIFS=4
+source $lib_dir/lib.sh
+source $lib_dir/tc_common.sh
+source $lib_dir/devlink_lib.sh
+
+h1_create()
+{
+	simple_if_init $h1 192.0.2.1/24
+	ip route add 198.51.100.0/24 vrf v$h1 nexthop via 192.0.2.2
+
+	tc qdisc add dev $h1 ingress
+}
+
+h1_destroy()
+{
+	tc qdisc del dev $h1 ingress
+
+	ip route del 198.51.100.0/24 vrf v$h1
+	simple_if_fini $h1 192.0.2.1/24
+}
+
+h2_create()
+{
+	simple_if_init $h2 198.51.100.1/24
+	ip route add 192.0.2.0/24 vrf v$h2 nexthop via 198.51.100.2
+
+	tc qdisc add dev $h2 ingress
+}
+
+h2_destroy()
+{
+	tc qdisc del dev $h2 ingress
+
+	ip route del 192.0.2.0/24 vrf v$h2
+	simple_if_fini $h2 198.51.100.1/24
+}
+
+router_create()
+{
+	ip link set dev $rp1 up
+	ip link set dev $rp2 up
+
+	tc qdisc add dev $rp1 clsact
+	tc qdisc add dev $rp2 clsact
+	ip address add 192.0.2.2/24 dev $rp1
+	ip address add 198.51.100.2/24 dev $rp2
+}
+
+router_destroy()
+{
+	ip address del 198.51.100.2/24 dev $rp2
+	ip address del 192.0.2.2/24 dev $rp1
+	tc qdisc del dev $rp2 clsact
+	tc qdisc del dev $rp1 clsact
+
+	ip link set dev $rp2 down
+	ip link set dev $rp1 down
+}
+
+setup_prepare()
+{
+	h1=${NETIFS[p1]}
+	rp1=${NETIFS[p2]}
+
+	rp2=${NETIFS[p3]}
+	h2=${NETIFS[p4]}
+
+	vrf_prepare
+
+	h1_create
+	h2_create
+
+	router_create
+
+	forwarding_enable
+}
+
+cleanup()
+{
+	pre_cleanup
+
+	forwarding_restore
+
+	router_destroy
+
+	h2_destroy
+	h1_destroy
+
+	vrf_cleanup
+}
+
+h1_to_h2()
+{
+	local test_name=$@; shift
+	local smac=$(mac_get $rp2)
+
+	RET=0
+
+	# Replace neighbour to avoid first packet being forwarded in software
+	ip neigh replace dev $rp2 198.51.100.1 lladdr $(mac_get $h2)
+
+	# Add a filter to ensure that packets are forwarded in hardware. Cannot
+	# match on source MAC because it is not set in eACL after routing
+	tc filter add dev $rp2 egress proto ip pref 1 handle 101 \
+		flower skip_sw ip_proto udp src_port 12345 dst_port 54321 \
+		action pass
+
+	# Add a filter to ensure that packets are received with the correct
+	# source MAC
+	tc filter add dev $h2 ingress proto ip pref 1 handle 101 \
+		flower skip_sw src_mac $smac ip_proto udp src_port 12345 \
+		dst_port 54321 action pass
+
+	$MZ $h1 -a own -b $(mac_get $rp1) -t udp "sp=12345,dp=54321" \
+		-A 192.0.2.1 -B 198.51.100.1 -c 10 -p 100 -d 1msec -q
+
+	tc_check_packets "dev $rp2 egress" 101 10
+	check_err $? "packets not forwarded in hardware"
+
+	tc_check_packets "dev $h2 ingress" 101 10
+	check_err $? "packets not forwarded with correct source mac"
+
+	log_test "h1->h2: $test_name"
+
+	tc filter del dev $h2 ingress protocol ip pref 1 handle 101 flower
+	tc filter del dev $rp2 egress protocol ip pref 1 handle 101 flower
+	ip neigh del dev $rp2 198.51.100.1 lladdr $(mac_get $h2)
+}
+
+h2_to_h1()
+{
+	local test_name=$@; shift
+	local rp1_mac=$(mac_get $rp1)
+
+	RET=0
+
+	ip neigh replace dev $rp1 192.0.2.1 lladdr $(mac_get $h1)
+
+	tc filter add dev $rp1 egress proto ip pref 1 handle 101 \
+		flower skip_sw ip_proto udp src_port 54321 dst_port 12345 \
+		action pass
+
+	tc filter add dev $h1 ingress proto ip pref 1 handle 101 \
+		flower skip_sw src_mac $rp1_mac ip_proto udp src_port 54321 \
+		dst_port 12345 action pass
+
+	$MZ $h2 -a own -b $(mac_get $rp2) -t udp "sp=54321,dp=12345" \
+		-A 198.51.100.1 -B 192.0.2.1 -c 10 -p 100 -d 1msec -q
+
+	tc_check_packets "dev $rp1 egress" 101 10
+	check_err $? "packets not forwarded in hardware"
+
+	tc_check_packets "dev $h1 ingress" 101 10
+	check_err $? "packets not forwarded with correct source mac"
+
+	log_test "h2->h1: $test_name"
+
+	tc filter del dev $h1 ingress protocol ip pref 1 handle 101 flower
+	tc filter del dev $rp1 egress protocol ip pref 1 handle 101 flower
+	ip neigh del dev $rp1 192.0.2.1 lladdr $(mac_get $h1)
+}
+
+smac_test()
+{
+	local test_name=$@; shift
+
+	# Test that packets forwarded to $h2 via $rp2 are forwarded with the
+	# current source MAC of $rp2
+	h1_to_h2 $test_name
+
+	# Test that packets forwarded to $h1 via $rp1 are forwarded with the
+	# current source MAC of $rp1. This MAC is never changed during the test,
+	# but given the shared nature of MAC profile, the point is to see that
+	# changes to the MAC of $rp2 do not affect that of $rp1
+	h2_to_h1 $test_name
+}
+
+mac_profile_test()
+{
+	local rp2_mac=$(mac_get $rp2)
+
+	# Test behavior when the RIF backing $rp2 is transitioned to use
+	# a new MAC profile
+	ip link set dev $rp2 addr 00:11:22:33:44:55
+	smac_test "new mac profile"
+
+	# Test behavior when the MAC profile used by the RIF is edited
+	ip link set dev $rp2 address 00:22:22:22:22:22
+	smac_test "edit mac profile"
+
+	# Restore original MAC
+	ip link set dev $rp2 addr $rp2_mac
+}
+
+trap cleanup EXIT
+
+setup_prepare
+setup_wait
+
+mac_profiles=$(devlink_resource_size_get rif_mac_profiles)
+if [[ $mac_profiles -ne 1 ]]; then
+	tests_run
+fi
+
+exit $EXIT_STATUS
-- 
cgit v1.2.3


From 20d446db6144ff2d60dfebb9db7bea885d7b726b Mon Sep 17 00:00:00 2001
From: Danielle Ratson <danieller@nvidia.com>
Date: Tue, 26 Oct 2021 12:42:24 +0300
Subject: selftests: Add an occupancy test for RIF MAC profiles

When all the RIF MAC profiles are in use, test that it is possible to
change the MAC of a netdev (i.e., a RIF) when its MAC profile is not
shared with other RIFs. Test that replacement fails when the MAC profile
is shared.

Signed-off-by: Danielle Ratson <danieller@nvidia.com>
Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../drivers/net/mlxsw/rif_mac_profiles_occ.sh      | 117 +++++++++++++++++++++
 1 file changed, 117 insertions(+)
 create mode 100755 tools/testing/selftests/drivers/net/mlxsw/rif_mac_profiles_occ.sh

(limited to 'tools')

diff --git a/tools/testing/selftests/drivers/net/mlxsw/rif_mac_profiles_occ.sh b/tools/testing/selftests/drivers/net/mlxsw/rif_mac_profiles_occ.sh
new file mode 100755
index 000000000000..b513f64d9092
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/mlxsw/rif_mac_profiles_occ.sh
@@ -0,0 +1,117 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+lib_dir=$(dirname $0)/../../../net/forwarding
+
+ALL_TESTS="
+	rif_mac_profile_edit_test
+"
+NUM_NETIFS=2
+source $lib_dir/lib.sh
+source $lib_dir/devlink_lib.sh
+
+setup_prepare()
+{
+	h1=${NETIFS[p1]}
+	h2=${NETIFS[p2]}
+
+	# Disable IPv6 on the two interfaces to avoid IPv6 link-local addresses
+	# being generated and RIFs being created
+	sysctl_set net.ipv6.conf.$h1.disable_ipv6 1
+	sysctl_set net.ipv6.conf.$h2.disable_ipv6 1
+
+	ip link set $h1 up
+	ip link set $h2 up
+}
+
+cleanup()
+{
+	pre_cleanup
+
+	ip link set $h2 down
+	ip link set $h1 down
+
+	sysctl_restore net.ipv6.conf.$h2.disable_ipv6
+	sysctl_restore net.ipv6.conf.$h1.disable_ipv6
+
+	# Reload in order to clean all the RIFs and RIF MAC profiles created
+	devlink_reload
+}
+
+create_max_rif_mac_profiles()
+{
+	local count=$1; shift
+	local batch_file="$(mktemp)"
+
+	for ((i = 1; i <= count; i++)); do
+		vlan=$(( i*10 ))
+		m=$(( i*11 ))
+
+		cat >> $batch_file <<-EOF
+			link add link $h1 name $h1.$vlan \
+				address 00:$m:$m:$m:$m:$m type vlan id $vlan
+			address add 192.0.$m.1/24 dev $h1.$vlan
+		EOF
+	done
+
+	ip -b $batch_file &> /dev/null
+	rm -f $batch_file
+}
+
+rif_mac_profile_replacement_test()
+{
+	local h1_10_mac=$(mac_get $h1.10)
+
+	RET=0
+
+	ip link set $h1.10 address 00:12:34:56:78:99
+	check_err $?
+
+	log_test "RIF MAC profile replacement"
+
+	ip link set $h1.10 address $h1_10_mac
+}
+
+rif_mac_profile_shared_replacement_test()
+{
+	local count=$1; shift
+	local i=$((count + 1))
+	local vlan=$(( i*10 ))
+	local m=11
+
+	RET=0
+
+	# Create a VLAN netdevice that has the same MAC as the first one.
+	ip link add link $h1 name $h1.$vlan address 00:$m:$m:$m:$m:$m \
+		type vlan id $vlan
+	ip address add 192.0.$m.1/24 dev $h1.$vlan
+
+	# MAC replacement should fail because all the MAC profiles are in use
+	# and the profile is shared between multiple RIFs
+	m=$(( i*11 ))
+	ip link set $h1.$vlan address 00:$m:$m:$m:$m:$m &> /dev/null
+	check_fail $?
+
+	log_test "RIF MAC profile shared replacement"
+
+	ip link del dev $h1.$vlan
+}
+
+rif_mac_profile_edit_test()
+{
+	local count=$(devlink_resource_size_get rif_mac_profiles)
+
+	create_max_rif_mac_profiles $count
+
+	rif_mac_profile_replacement_test
+	rif_mac_profile_shared_replacement_test $count
+}
+
+trap cleanup EXIT
+
+setup_prepare
+setup_wait
+
+tests_run
+
+exit $EXIT_STATUS
-- 
cgit v1.2.3


From c24dbf3d4f884527bce85417db3065fd5d65dc89 Mon Sep 17 00:00:00 2001
From: Danielle Ratson <danieller@nvidia.com>
Date: Tue, 26 Oct 2021 12:42:25 +0300
Subject: selftests: mlxsw: Remove deprecated test cases

After adding the previous patches, the constraint that all the router
interface MAC addresses have the same prefix is no longer relevant.

Remove the test cases that validated that this constraint is honored.

Signed-off-by: Danielle Ratson <danieller@nvidia.com>
Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../selftests/drivers/net/mlxsw/rtnetlink.sh       | 90 ----------------------
 1 file changed, 90 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/drivers/net/mlxsw/rtnetlink.sh b/tools/testing/selftests/drivers/net/mlxsw/rtnetlink.sh
index 1075d70e8f25..04f03ae9d8fb 100755
--- a/tools/testing/selftests/drivers/net/mlxsw/rtnetlink.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/rtnetlink.sh
@@ -10,9 +10,7 @@
 lib_dir=$(dirname $0)/../../../net/forwarding
 
 ALL_TESTS="
-	rif_set_addr_test
 	rif_vrf_set_addr_test
-	rif_inherit_bridge_addr_test
 	rif_non_inherit_bridge_addr_test
 	vlan_interface_deletion_test
 	bridge_deletion_test
@@ -60,55 +58,6 @@ cleanup()
 	ip link set dev $swp1 down
 }
 
-rif_set_addr_test()
-{
-	local swp1_mac=$(mac_get $swp1)
-	local swp2_mac=$(mac_get $swp2)
-
-	RET=0
-
-	# $swp1 and $swp2 likely got their IPv6 local addresses already, but
-	# here we need to test the transition to RIF.
-	ip addr flush dev $swp1
-	ip addr flush dev $swp2
-	sleep .1
-
-	ip addr add dev $swp1 192.0.2.1/28
-	check_err $?
-
-	ip link set dev $swp1 addr 00:11:22:33:44:55
-	check_err $?
-
-	# IP address enablement should be rejected if the MAC address prefix
-	# doesn't match other RIFs.
-	ip addr add dev $swp2 192.0.2.2/28 &>/dev/null
-	check_fail $? "IP address addition passed for a device with a wrong MAC"
-	ip addr add dev $swp2 192.0.2.2/28 2>&1 >/dev/null \
-	    | grep -q mlxsw_spectrum
-	check_err $? "no extack for IP address addition"
-
-	ip link set dev $swp2 addr 00:11:22:33:44:66
-	check_err $?
-	ip addr add dev $swp2 192.0.2.2/28 &>/dev/null
-	check_err $?
-
-	# Change of MAC address of a RIF should be forbidden if the new MAC
-	# doesn't share the prefix with other MAC addresses.
-	ip link set dev $swp2 addr 00:11:22:33:00:66 &>/dev/null
-	check_fail $? "change of MAC address passed for a wrong MAC"
-	ip link set dev $swp2 addr 00:11:22:33:00:66 2>&1 >/dev/null \
-	    | grep -q mlxsw_spectrum
-	check_err $? "no extack for MAC address change"
-
-	log_test "RIF - bad MAC change"
-
-	ip addr del dev $swp2 192.0.2.2/28
-	ip addr del dev $swp1 192.0.2.1/28
-
-	ip link set dev $swp2 addr $swp2_mac
-	ip link set dev $swp1 addr $swp1_mac
-}
-
 rif_vrf_set_addr_test()
 {
 	# Test that it is possible to set an IP address on a VRF upper despite
@@ -128,45 +77,6 @@ rif_vrf_set_addr_test()
 	ip link del dev vrf-test
 }
 
-rif_inherit_bridge_addr_test()
-{
-	RET=0
-
-	# Create first RIF
-	ip addr add dev $swp1 192.0.2.1/28
-	check_err $?
-
-	# Create a FID RIF
-	ip link add name br1 up type bridge vlan_filtering 0
-	ip link set dev $swp2 master br1
-	ip addr add dev br1 192.0.2.17/28
-	check_err $?
-
-	# Prepare a device with a low MAC address
-	ip link add name d up type dummy
-	ip link set dev d addr 00:11:22:33:44:55
-
-	# Attach the device to br1. That prompts bridge address change, which
-	# should be vetoed, thus preventing the attachment.
-	ip link set dev d master br1 &>/dev/null
-	check_fail $? "Device with low MAC was permitted to attach a bridge with RIF"
-	ip link set dev d master br1 2>&1 >/dev/null \
-	    | grep -q mlxsw_spectrum
-	check_err $? "no extack for bridge attach rejection"
-
-	ip link set dev $swp2 addr 00:11:22:33:44:55 &>/dev/null
-	check_fail $? "Changing swp2's MAC address permitted"
-	ip link set dev $swp2 addr 00:11:22:33:44:55 2>&1 >/dev/null \
-	    | grep -q mlxsw_spectrum
-	check_err $? "no extack for bridge port MAC address change rejection"
-
-	log_test "RIF - attach port with bad MAC to bridge"
-
-	ip link del dev d
-	ip link del dev br1
-	ip addr del dev $swp1 192.0.2.1/28
-}
-
 rif_non_inherit_bridge_addr_test()
 {
 	local swp2_mac=$(mac_get $swp2)
-- 
cgit v1.2.3


From 689624f037ce219d42312534eff4dc470b54dec4 Mon Sep 17 00:00:00 2001
From: Joe Burton <jevburton@google.com>
Date: Tue, 26 Oct 2021 22:35:28 +0000
Subject: libbpf: Deprecate bpf_objects_list

Add a flag to `enum libbpf_strict_mode' to disable the global
`bpf_objects_list', preventing race conditions when concurrent threads
call bpf_object__open() or bpf_object__close().

bpf_object__next() will return NULL if this option is set.

Callers may achieve the same workflow by tracking bpf_objects in
application code.

  [0] Closes: https://github.com/libbpf/libbpf/issues/293

Signed-off-by: Joe Burton <jevburton@google.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20211026223528.413950-1-jevburton.kernel@gmail.com
---
 tools/lib/bpf/libbpf.c        | 8 +++++++-
 tools/lib/bpf/libbpf.h        | 3 ++-
 tools/lib/bpf/libbpf_legacy.h | 6 ++++++
 3 files changed, 15 insertions(+), 2 deletions(-)

(limited to 'tools')

diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 2fbed2d4a645..59d39ce9f375 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -1148,6 +1148,7 @@ static struct bpf_object *bpf_object__new(const char *path,
 					  size_t obj_buf_sz,
 					  const char *obj_name)
 {
+	bool strict = (libbpf_mode & LIBBPF_STRICT_NO_OBJECT_LIST);
 	struct bpf_object *obj;
 	char *end;
 
@@ -1188,7 +1189,8 @@ static struct bpf_object *bpf_object__new(const char *path,
 	obj->loaded = false;
 
 	INIT_LIST_HEAD(&obj->list);
-	list_add(&obj->list, &bpf_objects_list);
+	if (!strict)
+		list_add(&obj->list, &bpf_objects_list);
 	return obj;
 }
 
@@ -7935,6 +7937,10 @@ struct bpf_object *
 bpf_object__next(struct bpf_object *prev)
 {
 	struct bpf_object *next;
+	bool strict = (libbpf_mode & LIBBPF_STRICT_NO_OBJECT_LIST);
+
+	if (strict)
+		return NULL;
 
 	if (!prev)
 		next = list_first_entry(&bpf_objects_list,
diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h
index e1900819bfab..defabdbe7760 100644
--- a/tools/lib/bpf/libbpf.h
+++ b/tools/lib/bpf/libbpf.h
@@ -168,7 +168,8 @@ LIBBPF_API struct bpf_program *
 bpf_object__find_program_by_name(const struct bpf_object *obj,
 				 const char *name);
 
-LIBBPF_API struct bpf_object *bpf_object__next(struct bpf_object *prev);
+LIBBPF_API LIBBPF_DEPRECATED_SINCE(0, 7, "track bpf_objects in application code instead")
+struct bpf_object *bpf_object__next(struct bpf_object *prev);
 #define bpf_object__for_each_safe(pos, tmp)			\
 	for ((pos) = bpf_object__next(NULL),		\
 		(tmp) = bpf_object__next(pos);		\
diff --git a/tools/lib/bpf/libbpf_legacy.h b/tools/lib/bpf/libbpf_legacy.h
index 29ccafab11a8..5ba5c9beccfa 100644
--- a/tools/lib/bpf/libbpf_legacy.h
+++ b/tools/lib/bpf/libbpf_legacy.h
@@ -57,6 +57,12 @@ enum libbpf_strict_mode {
 	 * function name instead of section name.
 	 */
 	LIBBPF_STRICT_SEC_NAME = 0x04,
+	/*
+	 * Disable the global 'bpf_objects_list'. Maintaining this list adds
+	 * a race condition to bpf_object__open() and bpf_object__close().
+	 * Clients can maintain it on their own if it is valuable for them.
+	 */
+	LIBBPF_STRICT_NO_OBJECT_LIST = 0x08,
 
 	__LIBBPF_STRICT_LAST,
 };
-- 
cgit v1.2.3


From 547208a386fa2066fa2d6d48bda145f78c38604f Mon Sep 17 00:00:00 2001
From: Yucong Sun <sunyucong@gmail.com>
Date: Mon, 25 Oct 2021 15:33:42 -0700
Subject: selfetests/bpf: Update vmtest.sh defaults

Increase memory to 4G, 8 SMP core with host cpu passthrough. This
make it run faster in parallel mode and more likely to succeed.

Signed-off-by: Yucong Sun <sunyucong@gmail.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20211025223345.2136168-2-fallentree@fb.com
---
 tools/testing/selftests/bpf/vmtest.sh | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/vmtest.sh b/tools/testing/selftests/bpf/vmtest.sh
index 8889b3f55236..027198768fad 100755
--- a/tools/testing/selftests/bpf/vmtest.sh
+++ b/tools/testing/selftests/bpf/vmtest.sh
@@ -224,10 +224,10 @@ EOF
 		-nodefaults \
 		-display none \
 		-serial mon:stdio \
-		-cpu kvm64 \
+		-cpu host \
 		-enable-kvm \
-		-smp 4 \
-		-m 2G \
+		-smp 8 \
+		-m 4G \
 		-drive file="${rootfs_img}",format=raw,index=1,media=disk,if=virtio,cache=none \
 		-kernel "${kernel_bzimage}" \
 		-append "root=/dev/vda rw console=ttyS0,115200"
-- 
cgit v1.2.3


From 9e7240fb2d6e0ed3944724ae1d224fdf22b3dea3 Mon Sep 17 00:00:00 2001
From: Yucong Sun <sunyucong@gmail.com>
Date: Mon, 25 Oct 2021 15:33:44 -0700
Subject: selftests/bpf: Fix attach_probe in parallel mode

This patch makes attach_probe uses its own method as attach point,
avoiding conflict with other tests like bpf_cookie.

Signed-off-by: Yucong Sun <sunyucong@gmail.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20211025223345.2136168-4-fallentree@fb.com
---
 tools/testing/selftests/bpf/prog_tests/attach_probe.c | 9 +++++++--
 1 file changed, 7 insertions(+), 2 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/prog_tests/attach_probe.c b/tools/testing/selftests/bpf/prog_tests/attach_probe.c
index 6c511dcd1465..d0bd51eb23c8 100644
--- a/tools/testing/selftests/bpf/prog_tests/attach_probe.c
+++ b/tools/testing/selftests/bpf/prog_tests/attach_probe.c
@@ -5,6 +5,11 @@
 /* this is how USDT semaphore is actually defined, except volatile modifier */
 volatile unsigned short uprobe_ref_ctr __attribute__((unused)) __attribute((section(".probes")));
 
+/* attach point */
+static void method(void) {
+	return ;
+}
+
 void test_attach_probe(void)
 {
 	DECLARE_LIBBPF_OPTS(bpf_uprobe_opts, uprobe_opts);
@@ -33,7 +38,7 @@ void test_attach_probe(void)
 	if (CHECK(base_addr < 0, "get_base_addr",
 		  "failed to find base addr: %zd", base_addr))
 		return;
-	uprobe_offset = get_uprobe_offset(&get_base_addr, base_addr);
+	uprobe_offset = get_uprobe_offset(&method, base_addr);
 
 	ref_ctr_offset = get_rel_offset((uintptr_t)&uprobe_ref_ctr);
 	if (!ASSERT_GE(ref_ctr_offset, 0, "ref_ctr_offset"))
@@ -98,7 +103,7 @@ void test_attach_probe(void)
 		goto cleanup;
 
 	/* trigger & validate uprobe & uretprobe */
-	get_base_addr();
+	method();
 
 	if (CHECK(skel->bss->uprobe_res != 3, "check_uprobe_res",
 		  "wrong uprobe res: %d\n", skel->bss->uprobe_res))
-- 
cgit v1.2.3


From e1ef62a4dd0e66ede4e73791ec1bcec947d4d0b3 Mon Sep 17 00:00:00 2001
From: Yucong Sun <sunyucong@gmail.com>
Date: Mon, 25 Oct 2021 15:33:45 -0700
Subject: selftests/bpf: Adding a namespace reset for tc_redirect

This patch delete ns_src/ns_dst/ns_redir namespaces before recreating
them, making the test more robust.

Signed-off-by: Yucong Sun <sunyucong@gmail.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20211025223345.2136168-5-fallentree@fb.com
---
 tools/testing/selftests/bpf/prog_tests/tc_redirect.c | 14 ++++++++++++++
 1 file changed, 14 insertions(+)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/prog_tests/tc_redirect.c b/tools/testing/selftests/bpf/prog_tests/tc_redirect.c
index 53672634bc52..4b18b73df10b 100644
--- a/tools/testing/selftests/bpf/prog_tests/tc_redirect.c
+++ b/tools/testing/selftests/bpf/prog_tests/tc_redirect.c
@@ -176,6 +176,18 @@ static int netns_setup_namespaces(const char *verb)
 	return 0;
 }
 
+static void netns_setup_namespaces_nofail(const char *verb)
+{
+	const char * const *ns = namespaces;
+	char cmd[128];
+
+	while (*ns) {
+		snprintf(cmd, sizeof(cmd), "ip netns %s %s > /dev/null 2>&1", verb, *ns);
+		system(cmd);
+		ns++;
+	}
+}
+
 struct netns_setup_result {
 	int ifindex_veth_src_fwd;
 	int ifindex_veth_dst_fwd;
@@ -762,6 +774,8 @@ fail:
 
 static void *test_tc_redirect_run_tests(void *arg)
 {
+	netns_setup_namespaces_nofail("delete");
+
 	RUN_TEST(tc_redirect_peer);
 	RUN_TEST(tc_redirect_peer_l3);
 	RUN_TEST(tc_redirect_neigh);
-- 
cgit v1.2.3


From 9330986c03006ab1d33d243b7cfe598a7a3c1baa Mon Sep 17 00:00:00 2001
From: Joanne Koong <joannekoong@fb.com>
Date: Wed, 27 Oct 2021 16:45:00 -0700
Subject: bpf: Add bloom filter map implementation

This patch adds the kernel-side changes for the implementation of
a bpf bloom filter map.

The bloom filter map supports peek (determining whether an element
is present in the map) and push (adding an element to the map)
operations.These operations are exposed to userspace applications
through the already existing syscalls in the following way:

BPF_MAP_LOOKUP_ELEM -> peek
BPF_MAP_UPDATE_ELEM -> push

The bloom filter map does not have keys, only values. In light of
this, the bloom filter map's API matches that of queue stack maps:
user applications use BPF_MAP_LOOKUP_ELEM/BPF_MAP_UPDATE_ELEM
which correspond internally to bpf_map_peek_elem/bpf_map_push_elem,
and bpf programs must use the bpf_map_peek_elem and bpf_map_push_elem
APIs to query or add an element to the bloom filter map. When the
bloom filter map is created, it must be created with a key_size of 0.

For updates, the user will pass in the element to add to the map
as the value, with a NULL key. For lookups, the user will pass in the
element to query in the map as the value, with a NULL key. In the
verifier layer, this requires us to modify the argument type of
a bloom filter's BPF_FUNC_map_peek_elem call to ARG_PTR_TO_MAP_VALUE;
as well, in the syscall layer, we need to copy over the user value
so that in bpf_map_peek_elem, we know which specific value to query.

A few things to please take note of:
 * If there are any concurrent lookups + updates, the user is
responsible for synchronizing this to ensure no false negative lookups
occur.
 * The number of hashes to use for the bloom filter is configurable from
userspace. If no number is specified, the default used will be 5 hash
functions. The benchmarks later in this patchset can help compare the
performance of using different number of hashes on different entry
sizes. In general, using more hashes decreases both the false positive
rate and the speed of a lookup.
 * Deleting an element in the bloom filter map is not supported.
 * The bloom filter map may be used as an inner map.
 * The "max_entries" size that is specified at map creation time is used
to approximate a reasonable bitmap size for the bloom filter, and is not
otherwise strictly enforced. If the user wishes to insert more entries
into the bloom filter than "max_entries", they may do so but they should
be aware that this may lead to a higher false positive rate.

Signed-off-by: Joanne Koong <joannekoong@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20211027234504.30744-2-joannekoong@fb.com
---
 tools/include/uapi/linux/bpf.h | 9 +++++++++
 1 file changed, 9 insertions(+)

(limited to 'tools')

diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index c10820037883..8bead4aa3ad0 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -906,6 +906,7 @@ enum bpf_map_type {
 	BPF_MAP_TYPE_RINGBUF,
 	BPF_MAP_TYPE_INODE_STORAGE,
 	BPF_MAP_TYPE_TASK_STORAGE,
+	BPF_MAP_TYPE_BLOOM_FILTER,
 };
 
 /* Note that tracing related programs such as
@@ -1274,6 +1275,13 @@ union bpf_attr {
 						   * struct stored as the
 						   * map value
 						   */
+		/* Any per-map-type extra fields
+		 *
+		 * BPF_MAP_TYPE_BLOOM_FILTER - the lowest 4 bits indicate the
+		 * number of hash functions (if 0, the bloom filter will default
+		 * to using 5 hash functions).
+		 */
+		__u64	map_extra;
 	};
 
 	struct { /* anonymous struct used by BPF_MAP_*_ELEM commands */
@@ -5638,6 +5646,7 @@ struct bpf_map_info {
 	__u32 btf_id;
 	__u32 btf_key_type_id;
 	__u32 btf_value_type_id;
+	__u64 map_extra;
 } __attribute__((aligned(8)));
 
 struct bpf_btf_info {
-- 
cgit v1.2.3


From 47512102cde2d252d7b984d9675cfd3420b48ad9 Mon Sep 17 00:00:00 2001
From: Joanne Koong <joannekoong@fb.com>
Date: Wed, 27 Oct 2021 16:45:01 -0700
Subject: libbpf: Add "map_extra" as a per-map-type extra flag

This patch adds the libbpf infrastructure for supporting a
per-map-type "map_extra" field, whose definition will be
idiosyncratic depending on map type.

For example, for the bloom filter map, the lower 4 bits of
map_extra is used to denote the number of hash functions.

Please note that until libbpf 1.0 is here, the
"bpf_create_map_params" struct is used as a temporary
means for propagating the map_extra field to the kernel.

Signed-off-by: Joanne Koong <joannekoong@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20211027234504.30744-3-joannekoong@fb.com
---
 tools/lib/bpf/bpf.c              | 27 ++++++++++++++++++++++++++-
 tools/lib/bpf/bpf_gen_internal.h |  2 +-
 tools/lib/bpf/gen_loader.c       |  3 ++-
 tools/lib/bpf/libbpf.c           | 38 +++++++++++++++++++++++++++++++++-----
 tools/lib/bpf/libbpf.h           |  3 +++
 tools/lib/bpf/libbpf.map         |  2 ++
 tools/lib/bpf/libbpf_internal.h  | 25 ++++++++++++++++++++++++-
 7 files changed, 91 insertions(+), 9 deletions(-)

(limited to 'tools')

diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c
index 7d1741ceaa32..fe4b6ebc9b8f 100644
--- a/tools/lib/bpf/bpf.c
+++ b/tools/lib/bpf/bpf.c
@@ -77,7 +77,7 @@ static inline int sys_bpf_prog_load(union bpf_attr *attr, unsigned int size)
 	return fd;
 }
 
-int bpf_create_map_xattr(const struct bpf_create_map_attr *create_attr)
+int libbpf__bpf_create_map_xattr(const struct bpf_create_map_params *create_attr)
 {
 	union bpf_attr attr;
 	int fd;
@@ -102,11 +102,36 @@ int bpf_create_map_xattr(const struct bpf_create_map_attr *create_attr)
 			create_attr->btf_vmlinux_value_type_id;
 	else
 		attr.inner_map_fd = create_attr->inner_map_fd;
+	attr.map_extra = create_attr->map_extra;
 
 	fd = sys_bpf(BPF_MAP_CREATE, &attr, sizeof(attr));
 	return libbpf_err_errno(fd);
 }
 
+int bpf_create_map_xattr(const struct bpf_create_map_attr *create_attr)
+{
+	struct bpf_create_map_params p = {};
+
+	p.map_type = create_attr->map_type;
+	p.key_size = create_attr->key_size;
+	p.value_size = create_attr->value_size;
+	p.max_entries = create_attr->max_entries;
+	p.map_flags = create_attr->map_flags;
+	p.name = create_attr->name;
+	p.numa_node = create_attr->numa_node;
+	p.btf_fd = create_attr->btf_fd;
+	p.btf_key_type_id = create_attr->btf_key_type_id;
+	p.btf_value_type_id = create_attr->btf_value_type_id;
+	p.map_ifindex = create_attr->map_ifindex;
+	if (p.map_type == BPF_MAP_TYPE_STRUCT_OPS)
+		p.btf_vmlinux_value_type_id =
+			create_attr->btf_vmlinux_value_type_id;
+	else
+		p.inner_map_fd = create_attr->inner_map_fd;
+
+	return libbpf__bpf_create_map_xattr(&p);
+}
+
 int bpf_create_map_node(enum bpf_map_type map_type, const char *name,
 			int key_size, int value_size, int max_entries,
 			__u32 map_flags, int node)
diff --git a/tools/lib/bpf/bpf_gen_internal.h b/tools/lib/bpf/bpf_gen_internal.h
index 70eccbffefb1..b8d41d6fbc40 100644
--- a/tools/lib/bpf/bpf_gen_internal.h
+++ b/tools/lib/bpf/bpf_gen_internal.h
@@ -43,7 +43,7 @@ void bpf_gen__init(struct bpf_gen *gen, int log_level);
 int bpf_gen__finish(struct bpf_gen *gen);
 void bpf_gen__free(struct bpf_gen *gen);
 void bpf_gen__load_btf(struct bpf_gen *gen, const void *raw_data, __u32 raw_size);
-void bpf_gen__map_create(struct bpf_gen *gen, struct bpf_create_map_attr *map_attr, int map_idx);
+void bpf_gen__map_create(struct bpf_gen *gen, struct bpf_create_map_params *map_attr, int map_idx);
 struct bpf_prog_load_params;
 void bpf_gen__prog_load(struct bpf_gen *gen, struct bpf_prog_load_params *load_attr, int prog_idx);
 void bpf_gen__map_update_elem(struct bpf_gen *gen, int map_idx, void *value, __u32 value_size);
diff --git a/tools/lib/bpf/gen_loader.c b/tools/lib/bpf/gen_loader.c
index 937bfc7db41e..e552484ae4a4 100644
--- a/tools/lib/bpf/gen_loader.c
+++ b/tools/lib/bpf/gen_loader.c
@@ -431,7 +431,7 @@ void bpf_gen__load_btf(struct bpf_gen *gen, const void *btf_raw_data,
 }
 
 void bpf_gen__map_create(struct bpf_gen *gen,
-			 struct bpf_create_map_attr *map_attr, int map_idx)
+			 struct bpf_create_map_params *map_attr, int map_idx)
 {
 	int attr_size = offsetofend(union bpf_attr, btf_vmlinux_value_type_id);
 	bool close_inner_map_fd = false;
@@ -443,6 +443,7 @@ void bpf_gen__map_create(struct bpf_gen *gen,
 	attr.key_size = map_attr->key_size;
 	attr.value_size = map_attr->value_size;
 	attr.map_flags = map_attr->map_flags;
+	attr.map_extra = map_attr->map_extra;
 	memcpy(attr.map_name, map_attr->name,
 	       min((unsigned)strlen(map_attr->name), BPF_OBJ_NAME_LEN - 1));
 	attr.numa_node = map_attr->numa_node;
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 59d39ce9f375..232e4efe82e9 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -400,6 +400,7 @@ struct bpf_map {
 	char *pin_path;
 	bool pinned;
 	bool reused;
+	__u64 map_extra;
 };
 
 enum extern_type {
@@ -2324,6 +2325,13 @@ int parse_btf_map_def(const char *map_name, struct btf *btf,
 			}
 			map_def->pinning = val;
 			map_def->parts |= MAP_DEF_PINNING;
+		} else if (strcmp(name, "map_extra") == 0) {
+			__u32 map_extra;
+
+			if (!get_map_field_int(map_name, btf, m, &map_extra))
+				return -EINVAL;
+			map_def->map_extra = map_extra;
+			map_def->parts |= MAP_DEF_MAP_EXTRA;
 		} else {
 			if (strict) {
 				pr_warn("map '%s': unknown field '%s'.\n", map_name, name);
@@ -2348,6 +2356,7 @@ static void fill_map_from_def(struct bpf_map *map, const struct btf_map_def *def
 	map->def.value_size = def->value_size;
 	map->def.max_entries = def->max_entries;
 	map->def.map_flags = def->map_flags;
+	map->map_extra = def->map_extra;
 
 	map->numa_node = def->numa_node;
 	map->btf_key_type_id = def->key_type_id;
@@ -2371,7 +2380,10 @@ static void fill_map_from_def(struct bpf_map *map, const struct btf_map_def *def
 	if (def->parts & MAP_DEF_MAX_ENTRIES)
 		pr_debug("map '%s': found max_entries = %u.\n", map->name, def->max_entries);
 	if (def->parts & MAP_DEF_MAP_FLAGS)
-		pr_debug("map '%s': found map_flags = %u.\n", map->name, def->map_flags);
+		pr_debug("map '%s': found map_flags = 0x%x.\n", map->name, def->map_flags);
+	if (def->parts & MAP_DEF_MAP_EXTRA)
+		pr_debug("map '%s': found map_extra = 0x%llx.\n", map->name,
+			 (unsigned long long)def->map_extra);
 	if (def->parts & MAP_DEF_PINNING)
 		pr_debug("map '%s': found pinning = %u.\n", map->name, def->pinning);
 	if (def->parts & MAP_DEF_NUMA_NODE)
@@ -4210,6 +4222,7 @@ int bpf_map__reuse_fd(struct bpf_map *map, int fd)
 	map->btf_key_type_id = info.btf_key_type_id;
 	map->btf_value_type_id = info.btf_value_type_id;
 	map->reused = true;
+	map->map_extra = info.map_extra;
 
 	return 0;
 
@@ -4724,7 +4737,8 @@ static bool map_is_reuse_compat(const struct bpf_map *map, int map_fd)
 		map_info.key_size == map->def.key_size &&
 		map_info.value_size == map->def.value_size &&
 		map_info.max_entries == map->def.max_entries &&
-		map_info.map_flags == map->def.map_flags);
+		map_info.map_flags == map->def.map_flags &&
+		map_info.map_extra == map->map_extra);
 }
 
 static int
@@ -4807,7 +4821,7 @@ static void bpf_map__destroy(struct bpf_map *map);
 
 static int bpf_object__create_map(struct bpf_object *obj, struct bpf_map *map, bool is_inner)
 {
-	struct bpf_create_map_attr create_attr;
+	struct bpf_create_map_params create_attr;
 	struct bpf_map_def *def = &map->def;
 	int err = 0;
 
@@ -4821,6 +4835,7 @@ static int bpf_object__create_map(struct bpf_object *obj, struct bpf_map *map, b
 	create_attr.key_size = def->key_size;
 	create_attr.value_size = def->value_size;
 	create_attr.numa_node = map->numa_node;
+	create_attr.map_extra = map->map_extra;
 
 	if (def->type == BPF_MAP_TYPE_PERF_EVENT_ARRAY && !def->max_entries) {
 		int nr_cpus;
@@ -4895,7 +4910,7 @@ static int bpf_object__create_map(struct bpf_object *obj, struct bpf_map *map, b
 		 */
 		map->fd = 0;
 	} else {
-		map->fd = bpf_create_map_xattr(&create_attr);
+		map->fd = libbpf__bpf_create_map_xattr(&create_attr);
 	}
 	if (map->fd < 0 && (create_attr.btf_key_type_id ||
 			    create_attr.btf_value_type_id)) {
@@ -4910,7 +4925,7 @@ static int bpf_object__create_map(struct bpf_object *obj, struct bpf_map *map, b
 		create_attr.btf_value_type_id = 0;
 		map->btf_key_type_id = 0;
 		map->btf_value_type_id = 0;
-		map->fd = bpf_create_map_xattr(&create_attr);
+		map->fd = libbpf__bpf_create_map_xattr(&create_attr);
 	}
 
 	err = map->fd < 0 ? -errno : 0;
@@ -8880,6 +8895,19 @@ int bpf_map__set_map_flags(struct bpf_map *map, __u32 flags)
 	return 0;
 }
 
+__u64 bpf_map__map_extra(const struct bpf_map *map)
+{
+	return map->map_extra;
+}
+
+int bpf_map__set_map_extra(struct bpf_map *map, __u64 map_extra)
+{
+	if (map->fd >= 0)
+		return libbpf_err(-EBUSY);
+	map->map_extra = map_extra;
+	return 0;
+}
+
 __u32 bpf_map__numa_node(const struct bpf_map *map)
 {
 	return map->numa_node;
diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h
index defabdbe7760..9de0f299706b 100644
--- a/tools/lib/bpf/libbpf.h
+++ b/tools/lib/bpf/libbpf.h
@@ -600,6 +600,9 @@ LIBBPF_API __u32 bpf_map__btf_value_type_id(const struct bpf_map *map);
 /* get/set map if_index */
 LIBBPF_API __u32 bpf_map__ifindex(const struct bpf_map *map);
 LIBBPF_API int bpf_map__set_ifindex(struct bpf_map *map, __u32 ifindex);
+/* get/set map map_extra flags */
+LIBBPF_API __u64 bpf_map__map_extra(const struct bpf_map *map);
+LIBBPF_API int bpf_map__set_map_extra(struct bpf_map *map, __u64 map_extra);
 
 typedef void (*bpf_map_clear_priv_t)(struct bpf_map *, void *);
 LIBBPF_API int bpf_map__set_priv(struct bpf_map *map, void *priv,
diff --git a/tools/lib/bpf/libbpf.map b/tools/lib/bpf/libbpf.map
index 15239c05659c..43580eb47740 100644
--- a/tools/lib/bpf/libbpf.map
+++ b/tools/lib/bpf/libbpf.map
@@ -389,6 +389,8 @@ LIBBPF_0.5.0 {
 
 LIBBPF_0.6.0 {
 	global:
+		bpf_map__map_extra;
+		bpf_map__set_map_extra;
 		bpf_object__next_map;
 		bpf_object__next_program;
 		bpf_object__prev_map;
diff --git a/tools/lib/bpf/libbpf_internal.h b/tools/lib/bpf/libbpf_internal.h
index 13bc7950e304..a6dd7e25747f 100644
--- a/tools/lib/bpf/libbpf_internal.h
+++ b/tools/lib/bpf/libbpf_internal.h
@@ -193,8 +193,9 @@ enum map_def_parts {
 	MAP_DEF_NUMA_NODE	= 0x080,
 	MAP_DEF_PINNING		= 0x100,
 	MAP_DEF_INNER_MAP	= 0x200,
+	MAP_DEF_MAP_EXTRA	= 0x400,
 
-	MAP_DEF_ALL		= 0x3ff, /* combination of all above */
+	MAP_DEF_ALL		= 0x7ff, /* combination of all above */
 };
 
 struct btf_map_def {
@@ -208,6 +209,7 @@ struct btf_map_def {
 	__u32 map_flags;
 	__u32 numa_node;
 	__u32 pinning;
+	__u64 map_extra;
 };
 
 int parse_btf_map_def(const char *map_name, struct btf *btf,
@@ -303,6 +305,27 @@ struct bpf_prog_load_params {
 
 int libbpf__bpf_prog_load(const struct bpf_prog_load_params *load_attr);
 
+struct bpf_create_map_params {
+	const char *name;
+	enum bpf_map_type map_type;
+	__u32 map_flags;
+	__u32 key_size;
+	__u32 value_size;
+	__u32 max_entries;
+	__u32 numa_node;
+	__u32 btf_fd;
+	__u32 btf_key_type_id;
+	__u32 btf_value_type_id;
+	__u32 map_ifindex;
+	union {
+		__u32 inner_map_fd;
+		__u32 btf_vmlinux_value_type_id;
+	};
+	__u64 map_extra;
+};
+
+int libbpf__bpf_create_map_xattr(const struct bpf_create_map_params *create_attr);
+
 struct btf *btf_get_from_fd(int btf_fd, struct btf *base_btf);
 void btf_get_kernel_prefix_kind(enum bpf_attach_type attach_type,
 				const char **prefix, int *kind);
-- 
cgit v1.2.3


From ed9109ad643cfbe69670a37cdbaf2da9f409fed0 Mon Sep 17 00:00:00 2001
From: Joanne Koong <joannekoong@fb.com>
Date: Wed, 27 Oct 2021 16:45:02 -0700
Subject: selftests/bpf: Add bloom filter map test cases

This patch adds test cases for bpf bloom filter maps. They include tests
checking against invalid operations by userspace, tests for using the
bloom filter map as an inner map, and a bpf program that queries the
bloom filter map for values added by a userspace program.

Signed-off-by: Joanne Koong <joannekoong@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20211027234504.30744-4-joannekoong@fb.com
---
 .../selftests/bpf/prog_tests/bloom_filter_map.c    | 204 +++++++++++++++++++++
 .../testing/selftests/bpf/progs/bloom_filter_map.c |  82 +++++++++
 2 files changed, 286 insertions(+)
 create mode 100644 tools/testing/selftests/bpf/prog_tests/bloom_filter_map.c
 create mode 100644 tools/testing/selftests/bpf/progs/bloom_filter_map.c

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/prog_tests/bloom_filter_map.c b/tools/testing/selftests/bpf/prog_tests/bloom_filter_map.c
new file mode 100644
index 000000000000..9aa3fbed918b
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/bloom_filter_map.c
@@ -0,0 +1,204 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2021 Facebook */
+
+#include <sys/syscall.h>
+#include <test_progs.h>
+#include "bloom_filter_map.skel.h"
+
+static void test_fail_cases(void)
+{
+	struct bpf_create_map_attr xattr = {
+		.name = "bloom_filter_map",
+		.map_type = BPF_MAP_TYPE_BLOOM_FILTER,
+		.max_entries = 100,
+		.value_size = 11,
+	};
+	__u32 value;
+	int fd, err;
+
+	/* Invalid key size */
+	xattr.key_size = 4;
+	fd = bpf_create_map_xattr(&xattr);
+	if (!ASSERT_LT(fd, 0, "bpf_create_map bloom filter invalid key size"))
+		close(fd);
+	xattr.key_size = 0;
+
+	/* Invalid value size */
+	xattr.value_size = 0;
+	fd = bpf_create_map_xattr(&xattr);
+	if (!ASSERT_LT(fd, 0, "bpf_create_map bloom filter invalid value size 0"))
+		close(fd);
+	xattr.value_size = 11;
+
+	/* Invalid max entries size */
+	xattr.max_entries = 0;
+	fd = bpf_create_map_xattr(&xattr);
+	if (!ASSERT_LT(fd, 0, "bpf_create_map bloom filter invalid max entries size"))
+		close(fd);
+	xattr.max_entries = 100;
+
+	/* Bloom filter maps do not support BPF_F_NO_PREALLOC */
+	xattr.map_flags = BPF_F_NO_PREALLOC;
+	fd = bpf_create_map_xattr(&xattr);
+	if (!ASSERT_LT(fd, 0, "bpf_create_map bloom filter invalid flags"))
+		close(fd);
+	xattr.map_flags = 0;
+
+	fd = bpf_create_map_xattr(&xattr);
+	if (!ASSERT_GE(fd, 0, "bpf_create_map bloom filter"))
+		return;
+
+	/* Test invalid flags */
+	err = bpf_map_update_elem(fd, NULL, &value, -1);
+	ASSERT_EQ(err, -EINVAL, "bpf_map_update_elem bloom filter invalid flags");
+
+	err = bpf_map_update_elem(fd, NULL, &value, BPF_EXIST);
+	ASSERT_EQ(err, -EINVAL, "bpf_map_update_elem bloom filter invalid flags");
+
+	err = bpf_map_update_elem(fd, NULL, &value, BPF_F_LOCK);
+	ASSERT_EQ(err, -EINVAL, "bpf_map_update_elem bloom filter invalid flags");
+
+	err = bpf_map_update_elem(fd, NULL, &value, BPF_NOEXIST);
+	ASSERT_EQ(err, -EINVAL, "bpf_map_update_elem bloom filter invalid flags");
+
+	err = bpf_map_update_elem(fd, NULL, &value, 10000);
+	ASSERT_EQ(err, -EINVAL, "bpf_map_update_elem bloom filter invalid flags");
+
+	close(fd);
+}
+
+static void check_bloom(struct bloom_filter_map *skel)
+{
+	struct bpf_link *link;
+
+	link = bpf_program__attach(skel->progs.check_bloom);
+	if (!ASSERT_OK_PTR(link, "link"))
+		return;
+
+	syscall(SYS_getpgid);
+
+	ASSERT_EQ(skel->bss->error, 0, "error");
+
+	bpf_link__destroy(link);
+}
+
+static void test_inner_map(struct bloom_filter_map *skel, const __u32 *rand_vals,
+			   __u32 nr_rand_vals)
+{
+	int outer_map_fd, inner_map_fd, err, i, key = 0;
+	struct bpf_create_map_attr xattr = {
+		.name = "bloom_filter_inner_map",
+		.map_type = BPF_MAP_TYPE_BLOOM_FILTER,
+		.value_size = sizeof(__u32),
+		.max_entries = nr_rand_vals,
+	};
+	struct bpf_link *link;
+
+	/* Create a bloom filter map that will be used as the inner map */
+	inner_map_fd = bpf_create_map_xattr(&xattr);
+	if (!ASSERT_GE(inner_map_fd, 0, "bpf_create_map bloom filter inner map"))
+		return;
+
+	for (i = 0; i < nr_rand_vals; i++) {
+		err = bpf_map_update_elem(inner_map_fd, NULL, rand_vals + i, BPF_ANY);
+		if (!ASSERT_OK(err, "Add random value to inner_map_fd"))
+			goto done;
+	}
+
+	/* Add the bloom filter map to the outer map */
+	outer_map_fd = bpf_map__fd(skel->maps.outer_map);
+	err = bpf_map_update_elem(outer_map_fd, &key, &inner_map_fd, BPF_ANY);
+	if (!ASSERT_OK(err, "Add bloom filter map to outer map"))
+		goto done;
+
+	/* Attach the bloom_filter_inner_map prog */
+	link = bpf_program__attach(skel->progs.inner_map);
+	if (!ASSERT_OK_PTR(link, "link"))
+		goto delete_inner_map;
+
+	syscall(SYS_getpgid);
+
+	ASSERT_EQ(skel->bss->error, 0, "error");
+
+	bpf_link__destroy(link);
+
+delete_inner_map:
+	/* Ensure the inner bloom filter map can be deleted */
+	err = bpf_map_delete_elem(outer_map_fd, &key);
+	ASSERT_OK(err, "Delete inner bloom filter map");
+
+done:
+	close(inner_map_fd);
+}
+
+static int setup_progs(struct bloom_filter_map **out_skel, __u32 **out_rand_vals,
+		       __u32 *out_nr_rand_vals)
+{
+	struct bloom_filter_map *skel;
+	int random_data_fd, bloom_fd;
+	__u32 *rand_vals = NULL;
+	__u32 map_size, val;
+	int err, i;
+
+	/* Set up a bloom filter map skeleton */
+	skel = bloom_filter_map__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "bloom_filter_map__open_and_load"))
+		return -EINVAL;
+
+	/* Set up rand_vals */
+	map_size = bpf_map__max_entries(skel->maps.map_random_data);
+	rand_vals = malloc(sizeof(*rand_vals) * map_size);
+	if (!rand_vals) {
+		err = -ENOMEM;
+		goto error;
+	}
+
+	/* Generate random values and populate both skeletons */
+	random_data_fd = bpf_map__fd(skel->maps.map_random_data);
+	bloom_fd = bpf_map__fd(skel->maps.map_bloom);
+	for (i = 0; i < map_size; i++) {
+		val = rand();
+
+		err = bpf_map_update_elem(random_data_fd, &i, &val, BPF_ANY);
+		if (!ASSERT_OK(err, "Add random value to map_random_data"))
+			goto error;
+
+		err = bpf_map_update_elem(bloom_fd, NULL, &val, BPF_ANY);
+		if (!ASSERT_OK(err, "Add random value to map_bloom"))
+			goto error;
+
+		rand_vals[i] = val;
+	}
+
+	*out_skel = skel;
+	*out_rand_vals = rand_vals;
+	*out_nr_rand_vals = map_size;
+
+	return 0;
+
+error:
+	bloom_filter_map__destroy(skel);
+	if (rand_vals)
+		free(rand_vals);
+	return err;
+}
+
+void test_bloom_filter_map(void)
+{
+	__u32 *rand_vals, nr_rand_vals;
+	struct bloom_filter_map *skel;
+	int err;
+
+	test_fail_cases();
+
+	err = setup_progs(&skel, &rand_vals, &nr_rand_vals);
+	if (err)
+		return;
+
+	test_inner_map(skel, rand_vals, nr_rand_vals);
+	free(rand_vals);
+
+	check_bloom(skel);
+
+	bloom_filter_map__destroy(skel);
+}
diff --git a/tools/testing/selftests/bpf/progs/bloom_filter_map.c b/tools/testing/selftests/bpf/progs/bloom_filter_map.c
new file mode 100644
index 000000000000..1316f3db79d9
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/bloom_filter_map.c
@@ -0,0 +1,82 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2021 Facebook */
+
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+
+char _license[] SEC("license") = "GPL";
+
+struct bpf_map;
+
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__type(key, __u32);
+	__type(value, __u32);
+	__uint(max_entries, 1000);
+} map_random_data SEC(".maps");
+
+struct map_bloom_type {
+	__uint(type, BPF_MAP_TYPE_BLOOM_FILTER);
+	__type(value, __u32);
+	__uint(max_entries, 10000);
+	__uint(map_extra, 5);
+} map_bloom SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY_OF_MAPS);
+	__type(key, int);
+	__type(value, int);
+	__uint(max_entries, 1);
+	__array(values, struct map_bloom_type);
+} outer_map SEC(".maps");
+
+struct callback_ctx {
+	struct bpf_map *map;
+};
+
+int error = 0;
+
+static __u64
+check_elem(struct bpf_map *map, __u32 *key, __u32 *val,
+	   struct callback_ctx *data)
+{
+	int err;
+
+	err = bpf_map_peek_elem(data->map, val);
+	if (err) {
+		error |= 1;
+		return 1; /* stop the iteration */
+	}
+
+	return 0;
+}
+
+SEC("fentry/__x64_sys_getpgid")
+int inner_map(void *ctx)
+{
+	struct bpf_map *inner_map;
+	struct callback_ctx data;
+	int key = 0;
+
+	inner_map = bpf_map_lookup_elem(&outer_map, &key);
+	if (!inner_map) {
+		error |= 2;
+		return 0;
+	}
+
+	data.map = inner_map;
+	bpf_for_each_map_elem(&map_random_data, check_elem, &data, 0);
+
+	return 0;
+}
+
+SEC("fentry/__x64_sys_getpgid")
+int check_bloom(void *ctx)
+{
+	struct callback_ctx data;
+
+	data.map = (struct bpf_map *)&map_bloom;
+	bpf_for_each_map_elem(&map_random_data, check_elem, &data, 0);
+
+	return 0;
+}
-- 
cgit v1.2.3


From 57fd1c63c9a687c5fdc86fa628c490d6733e8d0b Mon Sep 17 00:00:00 2001
From: Joanne Koong <joannekoong@fb.com>
Date: Wed, 27 Oct 2021 16:45:03 -0700
Subject: bpf/benchs: Add benchmark tests for bloom filter throughput + false
 positive

This patch adds benchmark tests for the throughput (for lookups + updates)
and the false positive rate of bloom filter lookups, as well as some
minor refactoring of the bash script for running the benchmarks.

These benchmarks show that as the number of hash functions increases,
the throughput and the false positive rate of the bloom filter decreases.
>From the benchmark data, the approximate average false-positive rates
are roughly as follows:

1 hash function = ~30%
2 hash functions = ~15%
3 hash functions = ~5%
4 hash functions = ~2.5%
5 hash functions = ~1%
6 hash functions = ~0.5%
7 hash functions  = ~0.35%
8 hash functions = ~0.15%
9 hash functions = ~0.1%
10 hash functions = ~0%

For reference data, the benchmarks run on one thread on a machine
with one numa node for 1 to 5 hash functions for 8-byte and 64-byte
values are as follows:

1 hash function:
  50k entries
	8-byte value
	    Lookups - 51.1 M/s operations
	    Updates - 33.6 M/s operations
	    False positive rate: 24.15%
	64-byte value
	    Lookups - 15.7 M/s operations
	    Updates - 15.1 M/s operations
	    False positive rate: 24.2%
  100k entries
	8-byte value
	    Lookups - 51.0 M/s operations
	    Updates - 33.4 M/s operations
	    False positive rate: 24.04%
	64-byte value
	    Lookups - 15.6 M/s operations
	    Updates - 14.6 M/s operations
	    False positive rate: 24.06%
  500k entries
	8-byte value
	    Lookups - 50.5 M/s operations
	    Updates - 33.1 M/s operations
	    False positive rate: 27.45%
	64-byte value
	    Lookups - 15.6 M/s operations
	    Updates - 14.2 M/s operations
	    False positive rate: 27.42%
  1 mil entries
	8-byte value
	    Lookups - 49.7 M/s operations
	    Updates - 32.9 M/s operations
	    False positive rate: 27.45%
	64-byte value
	    Lookups - 15.4 M/s operations
	    Updates - 13.7 M/s operations
	    False positive rate: 27.58%
  2.5 mil entries
	8-byte value
	    Lookups - 47.2 M/s operations
	    Updates - 31.8 M/s operations
	    False positive rate: 30.94%
	64-byte value
	    Lookups - 15.3 M/s operations
	    Updates - 13.2 M/s operations
	    False positive rate: 30.95%
  5 mil entries
	8-byte value
	    Lookups - 41.1 M/s operations
	    Updates - 28.1 M/s operations
	    False positive rate: 31.01%
	64-byte value
	    Lookups - 13.3 M/s operations
	    Updates - 11.4 M/s operations
	    False positive rate: 30.98%

2 hash functions:
  50k entries
	8-byte value
	    Lookups - 34.1 M/s operations
	    Updates - 20.1 M/s operations
	    False positive rate: 9.13%
	64-byte value
	    Lookups - 8.4 M/s operations
	    Updates - 7.9 M/s operations
	    False positive rate: 9.21%
  100k entries
	8-byte value
	    Lookups - 33.7 M/s operations
	    Updates - 18.9 M/s operations
	    False positive rate: 9.13%
	64-byte value
	    Lookups - 8.4 M/s operations
	    Updates - 7.7 M/s operations
	    False positive rate: 9.19%
  500k entries
	8-byte value
	    Lookups - 32.7 M/s operations
	    Updates - 18.1 M/s operations
	    False positive rate: 12.61%
	64-byte value
	    Lookups - 8.4 M/s operations
	    Updates - 7.5 M/s operations
	    False positive rate: 12.61%
  1 mil entries
	8-byte value
	    Lookups - 30.6 M/s operations
	    Updates - 18.9 M/s operations
	    False positive rate: 12.54%
	64-byte value
	    Lookups - 8.0 M/s operations
	    Updates - 7.0 M/s operations
	    False positive rate: 12.52%
  2.5 mil entries
	8-byte value
	    Lookups - 25.3 M/s operations
	    Updates - 16.7 M/s operations
	    False positive rate: 16.77%
	64-byte value
	    Lookups - 7.9 M/s operations
	    Updates - 6.5 M/s operations
	    False positive rate: 16.88%
  5 mil entries
	8-byte value
	    Lookups - 20.8 M/s operations
	    Updates - 14.7 M/s operations
	    False positive rate: 16.78%
	64-byte value
	    Lookups - 7.0 M/s operations
	    Updates - 6.0 M/s operations
	    False positive rate: 16.78%

3 hash functions:
  50k entries
	8-byte value
	    Lookups - 25.1 M/s operations
	    Updates - 14.6 M/s operations
	    False positive rate: 7.65%
	64-byte value
	    Lookups - 5.8 M/s operations
	    Updates - 5.5 M/s operations
	    False positive rate: 7.58%
  100k entries
	8-byte value
	    Lookups - 24.7 M/s operations
	    Updates - 14.1 M/s operations
	    False positive rate: 7.71%
	64-byte value
	    Lookups - 5.8 M/s operations
	    Updates - 5.3 M/s operations
	    False positive rate: 7.62%
  500k entries
	8-byte value
	    Lookups - 22.9 M/s operations
	    Updates - 13.9 M/s operations
	    False positive rate: 2.62%
	64-byte value
	    Lookups - 5.6 M/s operations
	    Updates - 4.8 M/s operations
	    False positive rate: 2.7%
  1 mil entries
	8-byte value
	    Lookups - 19.8 M/s operations
	    Updates - 12.6 M/s operations
	    False positive rate: 2.60%
	64-byte value
	    Lookups - 5.3 M/s operations
	    Updates - 4.4 M/s operations
	    False positive rate: 2.69%
  2.5 mil entries
	8-byte value
	    Lookups - 16.2 M/s operations
	    Updates - 10.7 M/s operations
	    False positive rate: 4.49%
	64-byte value
	    Lookups - 4.9 M/s operations
	    Updates - 4.1 M/s operations
	    False positive rate: 4.41%
  5 mil entries
	8-byte value
	    Lookups - 18.8 M/s operations
	    Updates - 9.2 M/s operations
	    False positive rate: 4.45%
	64-byte value
	    Lookups - 5.2 M/s operations
	    Updates - 3.9 M/s operations
	    False positive rate: 4.54%

4 hash functions:
  50k entries
	8-byte value
	    Lookups - 19.7 M/s operations
	    Updates - 11.1 M/s operations
	    False positive rate: 1.01%
	64-byte value
	    Lookups - 4.4 M/s operations
	    Updates - 4.0 M/s operations
	    False positive rate: 1.00%
  100k entries
	8-byte value
	    Lookups - 19.5 M/s operations
	    Updates - 10.9 M/s operations
	    False positive rate: 1.00%
	64-byte value
	    Lookups - 4.3 M/s operations
	    Updates - 3.9 M/s operations
	    False positive rate: 0.97%
  500k entries
	8-byte value
	    Lookups - 18.2 M/s operations
	    Updates - 10.6 M/s operations
	    False positive rate: 2.05%
	64-byte value
	    Lookups - 4.3 M/s operations
	    Updates - 3.7 M/s operations
	    False positive rate: 2.05%
  1 mil entries
	8-byte value
	    Lookups - 15.5 M/s operations
	    Updates - 9.6 M/s operations
	    False positive rate: 1.99%
	64-byte value
	    Lookups - 4.0 M/s operations
	    Updates - 3.4 M/s operations
	    False positive rate: 1.99%
  2.5 mil entries
	8-byte value
	    Lookups - 13.8 M/s operations
	    Updates - 7.7 M/s operations
	    False positive rate: 3.91%
	64-byte value
	    Lookups - 3.7 M/s operations
	    Updates - 3.6 M/s operations
	    False positive rate: 3.78%
  5 mil entries
	8-byte value
	    Lookups - 13.0 M/s operations
	    Updates - 6.9 M/s operations
	    False positive rate: 3.93%
	64-byte value
	    Lookups - 3.5 M/s operations
	    Updates - 3.7 M/s operations
	    False positive rate: 3.39%

5 hash functions:
  50k entries
	8-byte value
	    Lookups - 16.4 M/s operations
	    Updates - 9.1 M/s operations
	    False positive rate: 0.78%
	64-byte value
	    Lookups - 3.5 M/s operations
	    Updates - 3.2 M/s operations
	    False positive rate: 0.77%
  100k entries
	8-byte value
	    Lookups - 16.3 M/s operations
	    Updates - 9.0 M/s operations
	    False positive rate: 0.79%
	64-byte value
	    Lookups - 3.5 M/s operations
	    Updates - 3.2 M/s operations
	    False positive rate: 0.78%
  500k entries
	8-byte value
	    Lookups - 15.1 M/s operations
	    Updates - 8.8 M/s operations
	    False positive rate: 1.82%
	64-byte value
	    Lookups - 3.4 M/s operations
	    Updates - 3.0 M/s operations
	    False positive rate: 1.78%
  1 mil entries
	8-byte value
	    Lookups - 13.2 M/s operations
	    Updates - 7.8 M/s operations
	    False positive rate: 1.81%
	64-byte value
	    Lookups - 3.2 M/s operations
	    Updates - 2.8 M/s operations
	    False positive rate: 1.80%
  2.5 mil entries
	8-byte value
	    Lookups - 10.5 M/s operations
	    Updates - 5.9 M/s operations
	    False positive rate: 0.29%
	64-byte value
	    Lookups - 3.2 M/s operations
	    Updates - 2.4 M/s operations
	    False positive rate: 0.28%
  5 mil entries
	8-byte value
	    Lookups - 9.6 M/s operations
	    Updates - 5.7 M/s operations
	    False positive rate: 0.30%
	64-byte value
	    Lookups - 3.2 M/s operations
	    Updates - 2.7 M/s operations
	    False positive rate: 0.30%

Signed-off-by: Joanne Koong <joannekoong@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20211027234504.30744-5-joannekoong@fb.com
---
 tools/testing/selftests/bpf/Makefile               |   6 +-
 tools/testing/selftests/bpf/bench.c                |  37 ++
 tools/testing/selftests/bpf/bench.h                |   3 +
 .../selftests/bpf/benchs/bench_bloom_filter_map.c  | 420 +++++++++++++++++++++
 .../bpf/benchs/run_bench_bloom_filter_map.sh       |  28 ++
 .../selftests/bpf/benchs/run_bench_ringbufs.sh     |  30 +-
 tools/testing/selftests/bpf/benchs/run_common.sh   |  48 +++
 .../selftests/bpf/progs/bloom_filter_bench.c       | 153 ++++++++
 8 files changed, 695 insertions(+), 30 deletions(-)
 create mode 100644 tools/testing/selftests/bpf/benchs/bench_bloom_filter_map.c
 create mode 100755 tools/testing/selftests/bpf/benchs/run_bench_bloom_filter_map.sh
 create mode 100644 tools/testing/selftests/bpf/benchs/run_common.sh
 create mode 100644 tools/testing/selftests/bpf/progs/bloom_filter_bench.c

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index ac47cf9760fc..2c464cb78d6b 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -524,18 +524,20 @@ $(OUTPUT)/test_cpp: test_cpp.cpp $(OUTPUT)/test_core_extern.skel.h $(BPFOBJ)
 # Benchmark runner
 $(OUTPUT)/bench_%.o: benchs/bench_%.c bench.h $(BPFOBJ)
 	$(call msg,CC,,$@)
-	$(Q)$(CC) $(CFLAGS) -c $(filter %.c,$^) $(LDLIBS) -o $@
+	$(Q)$(CC) $(CFLAGS) -O2 -c $(filter %.c,$^) $(LDLIBS) -o $@
 $(OUTPUT)/bench_rename.o: $(OUTPUT)/test_overhead.skel.h
 $(OUTPUT)/bench_trigger.o: $(OUTPUT)/trigger_bench.skel.h
 $(OUTPUT)/bench_ringbufs.o: $(OUTPUT)/ringbuf_bench.skel.h \
 			    $(OUTPUT)/perfbuf_bench.skel.h
+$(OUTPUT)/bench_bloom_filter_map.o: $(OUTPUT)/bloom_filter_bench.skel.h
 $(OUTPUT)/bench.o: bench.h testing_helpers.h $(BPFOBJ)
 $(OUTPUT)/bench: LDLIBS += -lm
 $(OUTPUT)/bench: $(OUTPUT)/bench.o $(OUTPUT)/testing_helpers.o \
 		 $(OUTPUT)/bench_count.o \
 		 $(OUTPUT)/bench_rename.o \
 		 $(OUTPUT)/bench_trigger.o \
-		 $(OUTPUT)/bench_ringbufs.o
+		 $(OUTPUT)/bench_ringbufs.o \
+		 $(OUTPUT)/bench_bloom_filter_map.o
 	$(call msg,BINARY,,$@)
 	$(Q)$(CC) $(LDFLAGS) -o $@ $(filter %.a %.o,$^) $(LDLIBS)
 
diff --git a/tools/testing/selftests/bpf/bench.c b/tools/testing/selftests/bpf/bench.c
index 6ea15b93a2f8..a1d5dffe5ef6 100644
--- a/tools/testing/selftests/bpf/bench.c
+++ b/tools/testing/selftests/bpf/bench.c
@@ -51,6 +51,35 @@ void setup_libbpf()
 		fprintf(stderr, "failed to increase RLIMIT_MEMLOCK: %d", err);
 }
 
+void false_hits_report_progress(int iter, struct bench_res *res, long delta_ns)
+{
+	long total = res->false_hits  + res->hits + res->drops;
+
+	printf("Iter %3d (%7.3lfus): ",
+	       iter, (delta_ns - 1000000000) / 1000.0);
+
+	printf("%ld false hits of %ld total operations. Percentage = %2.2f %%\n",
+	       res->false_hits, total, ((float)res->false_hits / total) * 100);
+}
+
+void false_hits_report_final(struct bench_res res[], int res_cnt)
+{
+	long total_hits = 0, total_drops = 0, total_false_hits = 0, total_ops = 0;
+	int i;
+
+	for (i = 0; i < res_cnt; i++) {
+		total_hits += res[i].hits;
+		total_false_hits += res[i].false_hits;
+		total_drops += res[i].drops;
+	}
+	total_ops = total_hits + total_false_hits + total_drops;
+
+	printf("Summary: %ld false hits of %ld total operations. ",
+	       total_false_hits, total_ops);
+	printf("Percentage =  %2.2f %%\n",
+	       ((float)total_false_hits / total_ops) * 100);
+}
+
 void hits_drops_report_progress(int iter, struct bench_res *res, long delta_ns)
 {
 	double hits_per_sec, drops_per_sec;
@@ -132,9 +161,11 @@ static const struct argp_option opts[] = {
 };
 
 extern struct argp bench_ringbufs_argp;
+extern struct argp bench_bloom_map_argp;
 
 static const struct argp_child bench_parsers[] = {
 	{ &bench_ringbufs_argp, 0, "Ring buffers benchmark", 0 },
+	{ &bench_bloom_map_argp, 0, "Bloom filter map benchmark", 0 },
 	{},
 };
 
@@ -323,6 +354,9 @@ extern const struct bench bench_rb_libbpf;
 extern const struct bench bench_rb_custom;
 extern const struct bench bench_pb_libbpf;
 extern const struct bench bench_pb_custom;
+extern const struct bench bench_bloom_lookup;
+extern const struct bench bench_bloom_update;
+extern const struct bench bench_bloom_false_positive;
 
 static const struct bench *benchs[] = {
 	&bench_count_global,
@@ -344,6 +378,9 @@ static const struct bench *benchs[] = {
 	&bench_rb_custom,
 	&bench_pb_libbpf,
 	&bench_pb_custom,
+	&bench_bloom_lookup,
+	&bench_bloom_update,
+	&bench_bloom_false_positive,
 };
 
 static void setup_benchmark()
diff --git a/tools/testing/selftests/bpf/bench.h b/tools/testing/selftests/bpf/bench.h
index c1f48a473b02..624c6b11501f 100644
--- a/tools/testing/selftests/bpf/bench.h
+++ b/tools/testing/selftests/bpf/bench.h
@@ -33,6 +33,7 @@ struct env {
 struct bench_res {
 	long hits;
 	long drops;
+	long false_hits;
 };
 
 struct bench {
@@ -56,6 +57,8 @@ extern const struct bench *bench;
 void setup_libbpf();
 void hits_drops_report_progress(int iter, struct bench_res *res, long delta_ns);
 void hits_drops_report_final(struct bench_res res[], int res_cnt);
+void false_hits_report_progress(int iter, struct bench_res *res, long delta_ns);
+void false_hits_report_final(struct bench_res res[], int res_cnt);
 
 static inline __u64 get_time_ns() {
 	struct timespec t;
diff --git a/tools/testing/selftests/bpf/benchs/bench_bloom_filter_map.c b/tools/testing/selftests/bpf/benchs/bench_bloom_filter_map.c
new file mode 100644
index 000000000000..4bafad418a8a
--- /dev/null
+++ b/tools/testing/selftests/bpf/benchs/bench_bloom_filter_map.c
@@ -0,0 +1,420 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2021 Facebook */
+
+#include <argp.h>
+#include <linux/log2.h>
+#include <pthread.h>
+#include "bench.h"
+#include "bloom_filter_bench.skel.h"
+#include "bpf_util.h"
+
+static struct ctx {
+	bool use_array_map;
+	bool use_hashmap;
+	bool hashmap_use_bloom;
+	bool count_false_hits;
+
+	struct bloom_filter_bench *skel;
+
+	int bloom_fd;
+	int hashmap_fd;
+	int array_map_fd;
+
+	pthread_mutex_t map_done_mtx;
+	pthread_cond_t map_done_cv;
+	bool map_done;
+	bool map_prepare_err;
+
+	__u32 next_map_idx;
+} ctx = {
+	.map_done_mtx = PTHREAD_MUTEX_INITIALIZER,
+	.map_done_cv = PTHREAD_COND_INITIALIZER,
+};
+
+struct stat {
+	__u32 stats[3];
+};
+
+static struct {
+	__u32 nr_entries;
+	__u8 nr_hash_funcs;
+	__u8 value_size;
+} args = {
+	.nr_entries = 1000,
+	.nr_hash_funcs = 3,
+	.value_size = 8,
+};
+
+enum {
+	ARG_NR_ENTRIES = 3000,
+	ARG_NR_HASH_FUNCS = 3001,
+	ARG_VALUE_SIZE = 3002,
+};
+
+static const struct argp_option opts[] = {
+	{ "nr_entries", ARG_NR_ENTRIES, "NR_ENTRIES", 0,
+		"Set number of expected unique entries in the bloom filter"},
+	{ "nr_hash_funcs", ARG_NR_HASH_FUNCS, "NR_HASH_FUNCS", 0,
+		"Set number of hash functions in the bloom filter"},
+	{ "value_size", ARG_VALUE_SIZE, "VALUE_SIZE", 0,
+		"Set value size (in bytes) of bloom filter entries"},
+	{},
+};
+
+static error_t parse_arg(int key, char *arg, struct argp_state *state)
+{
+	switch (key) {
+	case ARG_NR_ENTRIES:
+		args.nr_entries = strtol(arg, NULL, 10);
+		if (args.nr_entries == 0) {
+			fprintf(stderr, "Invalid nr_entries count.");
+			argp_usage(state);
+		}
+		break;
+	case ARG_NR_HASH_FUNCS:
+		args.nr_hash_funcs = strtol(arg, NULL, 10);
+		if (args.nr_hash_funcs == 0 || args.nr_hash_funcs > 15) {
+			fprintf(stderr,
+				"The bloom filter must use 1 to 15 hash functions.");
+			argp_usage(state);
+		}
+		break;
+	case ARG_VALUE_SIZE:
+		args.value_size = strtol(arg, NULL, 10);
+		if (args.value_size < 2 || args.value_size > 256) {
+			fprintf(stderr,
+				"Invalid value size. Must be between 2 and 256 bytes");
+			argp_usage(state);
+		}
+		break;
+	default:
+		return ARGP_ERR_UNKNOWN;
+	}
+
+	return 0;
+}
+
+/* exported into benchmark runner */
+const struct argp bench_bloom_map_argp = {
+	.options = opts,
+	.parser = parse_arg,
+};
+
+static void validate(void)
+{
+	if (env.consumer_cnt != 1) {
+		fprintf(stderr,
+			"The bloom filter benchmarks do not support multi-consumer use\n");
+		exit(1);
+	}
+}
+
+static inline void trigger_bpf_program(void)
+{
+	syscall(__NR_getpgid);
+}
+
+static void *producer(void *input)
+{
+	while (true)
+		trigger_bpf_program();
+
+	return NULL;
+}
+
+static void *map_prepare_thread(void *arg)
+{
+	__u32 val_size, i;
+	void *val = NULL;
+	int err;
+
+	val_size = args.value_size;
+	val = malloc(val_size);
+	if (!val) {
+		ctx.map_prepare_err = true;
+		goto done;
+	}
+
+	while (true) {
+		i = __atomic_add_fetch(&ctx.next_map_idx, 1, __ATOMIC_RELAXED);
+		if (i > args.nr_entries)
+			break;
+
+again:
+		/* Populate hashmap, bloom filter map, and array map with the same
+		 * random values
+		 */
+		err = syscall(__NR_getrandom, val, val_size, 0);
+		if (err != val_size) {
+			ctx.map_prepare_err = true;
+			fprintf(stderr, "failed to get random value: %d\n", -errno);
+			break;
+		}
+
+		if (ctx.use_hashmap) {
+			err = bpf_map_update_elem(ctx.hashmap_fd, val, val, BPF_NOEXIST);
+			if (err) {
+				if (err != -EEXIST) {
+					ctx.map_prepare_err = true;
+					fprintf(stderr, "failed to add elem to hashmap: %d\n",
+						-errno);
+					break;
+				}
+				goto again;
+			}
+		}
+
+		i--;
+
+		if (ctx.use_array_map) {
+			err = bpf_map_update_elem(ctx.array_map_fd, &i, val, 0);
+			if (err) {
+				ctx.map_prepare_err = true;
+				fprintf(stderr, "failed to add elem to array map: %d\n", -errno);
+				break;
+			}
+		}
+
+		if (ctx.use_hashmap && !ctx.hashmap_use_bloom)
+			continue;
+
+		err = bpf_map_update_elem(ctx.bloom_fd, NULL, val, 0);
+		if (err) {
+			ctx.map_prepare_err = true;
+			fprintf(stderr,
+				"failed to add elem to bloom filter map: %d\n", -errno);
+			break;
+		}
+	}
+done:
+	pthread_mutex_lock(&ctx.map_done_mtx);
+	ctx.map_done = true;
+	pthread_cond_signal(&ctx.map_done_cv);
+	pthread_mutex_unlock(&ctx.map_done_mtx);
+
+	if (val)
+		free(val);
+
+	return NULL;
+}
+
+static void populate_maps(void)
+{
+	unsigned int nr_cpus = bpf_num_possible_cpus();
+	pthread_t map_thread;
+	int i, err, nr_rand_bytes;
+
+	ctx.bloom_fd = bpf_map__fd(ctx.skel->maps.bloom_map);
+	ctx.hashmap_fd = bpf_map__fd(ctx.skel->maps.hashmap);
+	ctx.array_map_fd = bpf_map__fd(ctx.skel->maps.array_map);
+
+	for (i = 0; i < nr_cpus; i++) {
+		err = pthread_create(&map_thread, NULL, map_prepare_thread,
+				     NULL);
+		if (err) {
+			fprintf(stderr, "failed to create pthread: %d\n", -errno);
+			exit(1);
+		}
+	}
+
+	pthread_mutex_lock(&ctx.map_done_mtx);
+	while (!ctx.map_done)
+		pthread_cond_wait(&ctx.map_done_cv, &ctx.map_done_mtx);
+	pthread_mutex_unlock(&ctx.map_done_mtx);
+
+	if (ctx.map_prepare_err)
+		exit(1);
+
+	nr_rand_bytes = syscall(__NR_getrandom, ctx.skel->bss->rand_vals,
+				ctx.skel->rodata->nr_rand_bytes, 0);
+	if (nr_rand_bytes != ctx.skel->rodata->nr_rand_bytes) {
+		fprintf(stderr, "failed to get random bytes\n");
+		exit(1);
+	}
+}
+
+static void check_args(void)
+{
+	if (args.value_size < 8)  {
+		__u64 nr_unique_entries = 1ULL << (args.value_size * 8);
+
+		if (args.nr_entries > nr_unique_entries) {
+			fprintf(stderr,
+				"Not enough unique values for the nr_entries requested\n");
+			exit(1);
+		}
+	}
+}
+
+static struct bloom_filter_bench *setup_skeleton(void)
+{
+	struct bloom_filter_bench *skel;
+
+	check_args();
+
+	setup_libbpf();
+
+	skel = bloom_filter_bench__open();
+	if (!skel) {
+		fprintf(stderr, "failed to open skeleton\n");
+		exit(1);
+	}
+
+	skel->rodata->hashmap_use_bloom = ctx.hashmap_use_bloom;
+	skel->rodata->count_false_hits = ctx.count_false_hits;
+
+	/* Resize number of entries */
+	bpf_map__set_max_entries(skel->maps.hashmap, args.nr_entries);
+
+	bpf_map__set_max_entries(skel->maps.array_map, args.nr_entries);
+
+	bpf_map__set_max_entries(skel->maps.bloom_map, args.nr_entries);
+
+	/* Set value size */
+	bpf_map__set_value_size(skel->maps.array_map, args.value_size);
+
+	bpf_map__set_value_size(skel->maps.bloom_map, args.value_size);
+
+	bpf_map__set_value_size(skel->maps.hashmap, args.value_size);
+
+	/* For the hashmap, we use the value as the key as well */
+	bpf_map__set_key_size(skel->maps.hashmap, args.value_size);
+
+	skel->bss->value_size = args.value_size;
+
+	/* Set number of hash functions */
+	bpf_map__set_map_extra(skel->maps.bloom_map, args.nr_hash_funcs);
+
+	if (bloom_filter_bench__load(skel)) {
+		fprintf(stderr, "failed to load skeleton\n");
+		exit(1);
+	}
+
+	return skel;
+}
+
+static void bloom_lookup_setup(void)
+{
+	struct bpf_link *link;
+
+	ctx.use_array_map = true;
+
+	ctx.skel = setup_skeleton();
+
+	populate_maps();
+
+	link = bpf_program__attach(ctx.skel->progs.bloom_lookup);
+	if (!link) {
+		fprintf(stderr, "failed to attach program!\n");
+		exit(1);
+	}
+}
+
+static void bloom_update_setup(void)
+{
+	struct bpf_link *link;
+
+	ctx.use_array_map = true;
+
+	ctx.skel = setup_skeleton();
+
+	populate_maps();
+
+	link = bpf_program__attach(ctx.skel->progs.bloom_update);
+	if (!link) {
+		fprintf(stderr, "failed to attach program!\n");
+		exit(1);
+	}
+}
+
+static void false_positive_setup(void)
+{
+	struct bpf_link *link;
+
+	ctx.use_hashmap = true;
+	ctx.hashmap_use_bloom = true;
+	ctx.count_false_hits = true;
+
+	ctx.skel = setup_skeleton();
+
+	populate_maps();
+
+	link = bpf_program__attach(ctx.skel->progs.bloom_hashmap_lookup);
+	if (!link) {
+		fprintf(stderr, "failed to attach program!\n");
+		exit(1);
+	}
+}
+
+static void measure(struct bench_res *res)
+{
+	unsigned long total_hits = 0, total_drops = 0, total_false_hits = 0;
+	static unsigned long last_hits, last_drops, last_false_hits;
+	unsigned int nr_cpus = bpf_num_possible_cpus();
+	int hit_key, drop_key, false_hit_key;
+	int i;
+
+	hit_key = ctx.skel->rodata->hit_key;
+	drop_key = ctx.skel->rodata->drop_key;
+	false_hit_key = ctx.skel->rodata->false_hit_key;
+
+	if (ctx.skel->bss->error != 0) {
+		fprintf(stderr, "error (%d) when searching the bloom filter\n",
+			ctx.skel->bss->error);
+		exit(1);
+	}
+
+	for (i = 0; i < nr_cpus; i++) {
+		struct stat *s = (void *)&ctx.skel->bss->percpu_stats[i];
+
+		total_hits += s->stats[hit_key];
+		total_drops += s->stats[drop_key];
+		total_false_hits += s->stats[false_hit_key];
+	}
+
+	res->hits = total_hits - last_hits;
+	res->drops = total_drops - last_drops;
+	res->false_hits = total_false_hits - last_false_hits;
+
+	last_hits = total_hits;
+	last_drops = total_drops;
+	last_false_hits = total_false_hits;
+}
+
+static void *consumer(void *input)
+{
+	return NULL;
+}
+
+const struct bench bench_bloom_lookup = {
+	.name = "bloom-lookup",
+	.validate = validate,
+	.setup = bloom_lookup_setup,
+	.producer_thread = producer,
+	.consumer_thread = consumer,
+	.measure = measure,
+	.report_progress = hits_drops_report_progress,
+	.report_final = hits_drops_report_final,
+};
+
+const struct bench bench_bloom_update = {
+	.name = "bloom-update",
+	.validate = validate,
+	.setup = bloom_update_setup,
+	.producer_thread = producer,
+	.consumer_thread = consumer,
+	.measure = measure,
+	.report_progress = hits_drops_report_progress,
+	.report_final = hits_drops_report_final,
+};
+
+const struct bench bench_bloom_false_positive = {
+	.name = "bloom-false-positive",
+	.validate = validate,
+	.setup = false_positive_setup,
+	.producer_thread = producer,
+	.consumer_thread = consumer,
+	.measure = measure,
+	.report_progress = false_hits_report_progress,
+	.report_final = false_hits_report_final,
+};
diff --git a/tools/testing/selftests/bpf/benchs/run_bench_bloom_filter_map.sh b/tools/testing/selftests/bpf/benchs/run_bench_bloom_filter_map.sh
new file mode 100755
index 000000000000..d03d0e5c91cd
--- /dev/null
+++ b/tools/testing/selftests/bpf/benchs/run_bench_bloom_filter_map.sh
@@ -0,0 +1,28 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+source ./benchs/run_common.sh
+
+set -eufo pipefail
+
+header "Bloom filter map"
+for v in 2 4 8 16 40; do
+for t in 1 4 8 12 16; do
+for h in {1..10}; do
+subtitle "value_size: $v bytes, # threads: $t, # hashes: $h"
+	for e in 10000 50000 75000 100000 250000 500000 750000 1000000 2500000 5000000; do
+		printf "%'d entries -\n" $e
+		printf "\t"
+		summarize "Lookups, total operations: " \
+			"$($RUN_BENCH -p $t --nr_hash_funcs $h --nr_entries $e --value_size $v bloom-lookup)"
+		printf "\t"
+		summarize "Updates, total operations: " \
+			"$($RUN_BENCH -p $t --nr_hash_funcs $h --nr_entries $e --value_size $v bloom-update)"
+		printf "\t"
+		summarize_percentage "False positive rate: " \
+			"$($RUN_BENCH -p $t --nr_hash_funcs $h --nr_entries $e --value_size $v bloom-false-positive)"
+	done
+	printf "\n"
+done
+done
+done
diff --git a/tools/testing/selftests/bpf/benchs/run_bench_ringbufs.sh b/tools/testing/selftests/bpf/benchs/run_bench_ringbufs.sh
index af4aa04caba6..ada028aa9007 100755
--- a/tools/testing/selftests/bpf/benchs/run_bench_ringbufs.sh
+++ b/tools/testing/selftests/bpf/benchs/run_bench_ringbufs.sh
@@ -1,34 +1,8 @@
 #!/bin/bash
 
-set -eufo pipefail
-
-RUN_BENCH="sudo ./bench -w3 -d10 -a"
-
-function hits()
-{
-	echo "$*" | sed -E "s/.*hits\s+([0-9]+\.[0-9]+ ± [0-9]+\.[0-9]+M\/s).*/\1/"
-}
-
-function drops()
-{
-	echo "$*" | sed -E "s/.*drops\s+([0-9]+\.[0-9]+ ± [0-9]+\.[0-9]+M\/s).*/\1/"
-}
+source ./benchs/run_common.sh
 
-function header()
-{
-	local len=${#1}
-
-	printf "\n%s\n" "$1"
-	for i in $(seq 1 $len); do printf '='; done
-	printf '\n'
-}
-
-function summarize()
-{
-	bench="$1"
-	summary=$(echo $2 | tail -n1)
-	printf "%-20s %s (drops %s)\n" "$bench" "$(hits $summary)" "$(drops $summary)"
-}
+set -eufo pipefail
 
 header "Single-producer, parallel producer"
 for b in rb-libbpf rb-custom pb-libbpf pb-custom; do
diff --git a/tools/testing/selftests/bpf/benchs/run_common.sh b/tools/testing/selftests/bpf/benchs/run_common.sh
new file mode 100644
index 000000000000..670f23b037c4
--- /dev/null
+++ b/tools/testing/selftests/bpf/benchs/run_common.sh
@@ -0,0 +1,48 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+RUN_BENCH="sudo ./bench -w3 -d10 -a"
+
+function header()
+{
+	local len=${#1}
+
+	printf "\n%s\n" "$1"
+	for i in $(seq 1 $len); do printf '='; done
+	printf '\n'
+}
+
+function subtitle()
+{
+	local len=${#1}
+	printf "\t%s\n" "$1"
+}
+
+function hits()
+{
+	echo "$*" | sed -E "s/.*hits\s+([0-9]+\.[0-9]+ ± [0-9]+\.[0-9]+M\/s).*/\1/"
+}
+
+function drops()
+{
+	echo "$*" | sed -E "s/.*drops\s+([0-9]+\.[0-9]+ ± [0-9]+\.[0-9]+M\/s).*/\1/"
+}
+
+function percentage()
+{
+	echo "$*" | sed -E "s/.*Percentage\s=\s+([0-9]+\.[0-9]+).*/\1/"
+}
+
+function summarize()
+{
+	bench="$1"
+	summary=$(echo $2 | tail -n1)
+	printf "%-20s %s (drops %s)\n" "$bench" "$(hits $summary)" "$(drops $summary)"
+}
+
+function summarize_percentage()
+{
+	bench="$1"
+	summary=$(echo $2 | tail -n1)
+	printf "%-20s %s%%\n" "$bench" "$(percentage $summary)"
+}
diff --git a/tools/testing/selftests/bpf/progs/bloom_filter_bench.c b/tools/testing/selftests/bpf/progs/bloom_filter_bench.c
new file mode 100644
index 000000000000..d9a88dd1ea65
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/bloom_filter_bench.c
@@ -0,0 +1,153 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2021 Facebook */
+
+#include <errno.h>
+#include <linux/bpf.h>
+#include <stdbool.h>
+#include <bpf/bpf_helpers.h>
+
+char _license[] SEC("license") = "GPL";
+
+struct bpf_map;
+
+__u8 rand_vals[2500000];
+const __u32 nr_rand_bytes = 2500000;
+
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__uint(key_size, sizeof(__u32));
+	/* max entries and value_size will be set programmatically.
+	 * They are configurable from the userspace bench program.
+	 */
+} array_map SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_BLOOM_FILTER);
+	/* max entries,  value_size, and # of hash functions will be set
+	 * programmatically. They are configurable from the userspace
+	 * bench program.
+	 */
+	__uint(map_extra, 3);
+} bloom_map SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_HASH);
+	/* max entries, key_size, and value_size, will be set
+	 * programmatically. They are configurable from the userspace
+	 * bench program.
+	 */
+} hashmap SEC(".maps");
+
+struct callback_ctx {
+	struct bpf_map *map;
+	bool update;
+};
+
+/* Tracks the number of hits, drops, and false hits */
+struct {
+	__u32 stats[3];
+} __attribute__((__aligned__(256))) percpu_stats[256];
+
+const __u32 hit_key  = 0;
+const __u32 drop_key  = 1;
+const __u32 false_hit_key = 2;
+
+__u8 value_size;
+
+const volatile bool hashmap_use_bloom;
+const volatile bool count_false_hits;
+
+int error = 0;
+
+static __always_inline void log_result(__u32 key)
+{
+	__u32 cpu = bpf_get_smp_processor_id();
+
+	percpu_stats[cpu & 255].stats[key]++;
+}
+
+static __u64
+bloom_callback(struct bpf_map *map, __u32 *key, void *val,
+	       struct callback_ctx *data)
+{
+	int err;
+
+	if (data->update)
+		err = bpf_map_push_elem(data->map, val, 0);
+	else
+		err = bpf_map_peek_elem(data->map, val);
+
+	if (err) {
+		error |= 1;
+		return 1; /* stop the iteration */
+	}
+
+	log_result(hit_key);
+
+	return 0;
+}
+
+SEC("fentry/__x64_sys_getpgid")
+int bloom_lookup(void *ctx)
+{
+	struct callback_ctx data;
+
+	data.map = (struct bpf_map *)&bloom_map;
+	data.update = false;
+
+	bpf_for_each_map_elem(&array_map, bloom_callback, &data, 0);
+
+	return 0;
+}
+
+SEC("fentry/__x64_sys_getpgid")
+int bloom_update(void *ctx)
+{
+	struct callback_ctx data;
+
+	data.map = (struct bpf_map *)&bloom_map;
+	data.update = true;
+
+	bpf_for_each_map_elem(&array_map, bloom_callback, &data, 0);
+
+	return 0;
+}
+
+SEC("fentry/__x64_sys_getpgid")
+int bloom_hashmap_lookup(void *ctx)
+{
+	__u64 *result;
+	int i, err;
+
+	__u32 index = bpf_get_prandom_u32();
+	__u32 bitmask = (1ULL << 21) - 1;
+
+	for (i = 0; i < 1024; i++, index += value_size) {
+		index = index & bitmask;
+
+		if (hashmap_use_bloom) {
+			err = bpf_map_peek_elem(&bloom_map,
+						rand_vals + index);
+			if (err) {
+				if (err != -ENOENT) {
+					error |= 2;
+					return 0;
+				}
+				log_result(hit_key);
+				continue;
+			}
+		}
+
+		result = bpf_map_lookup_elem(&hashmap,
+					     rand_vals + index);
+		if (result) {
+			log_result(hit_key);
+		} else {
+			if (hashmap_use_bloom && count_false_hits)
+				log_result(false_hit_key);
+			log_result(drop_key);
+		}
+	}
+
+	return 0;
+}
-- 
cgit v1.2.3


From f44bc543a079c2ebc534cbfabd6fbfcfc2b09f72 Mon Sep 17 00:00:00 2001
From: Joanne Koong <joannekoong@fb.com>
Date: Wed, 27 Oct 2021 16:45:04 -0700
Subject: bpf/benchs: Add benchmarks for comparing hashmap lookups w/ vs. w/out
 bloom filter

This patch adds benchmark tests for comparing the performance of hashmap
lookups without the bloom filter vs. hashmap lookups with the bloom filter.

Checking the bloom filter first for whether the element exists should
overall enable a higher throughput for hashmap lookups, since if the
element does not exist in the bloom filter, we can avoid a costly lookup in
the hashmap.

On average, using 5 hash functions in the bloom filter tended to perform
the best across the widest range of different entry sizes. The benchmark
results using 5 hash functions (running on 8 threads on a machine with one
numa node, and taking the average of 3 runs) were roughly as follows:

value_size = 4 bytes -
	10k entries: 30% faster
	50k entries: 40% faster
	100k entries: 40% faster
	500k entres: 70% faster
	1 million entries: 90% faster
	5 million entries: 140% faster

value_size = 8 bytes -
	10k entries: 30% faster
	50k entries: 40% faster
	100k entries: 50% faster
	500k entres: 80% faster
	1 million entries: 100% faster
	5 million entries: 150% faster

value_size = 16 bytes -
	10k entries: 20% faster
	50k entries: 30% faster
	100k entries: 35% faster
	500k entres: 65% faster
	1 million entries: 85% faster
	5 million entries: 110% faster

value_size = 40 bytes -
	10k entries: 5% faster
	50k entries: 15% faster
	100k entries: 20% faster
	500k entres: 65% faster
	1 million entries: 75% faster
	5 million entries: 120% faster

Signed-off-by: Joanne Koong <joannekoong@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20211027234504.30744-6-joannekoong@fb.com
---
 tools/testing/selftests/bpf/bench.c                | 23 +++++++--
 .../selftests/bpf/benchs/bench_bloom_filter_map.c  | 57 ++++++++++++++++++++++
 .../bpf/benchs/run_bench_bloom_filter_map.sh       | 17 +++++++
 tools/testing/selftests/bpf/benchs/run_common.sh   | 12 +++++
 4 files changed, 104 insertions(+), 5 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/bench.c b/tools/testing/selftests/bpf/bench.c
index a1d5dffe5ef6..cc4722f693e9 100644
--- a/tools/testing/selftests/bpf/bench.c
+++ b/tools/testing/selftests/bpf/bench.c
@@ -92,20 +92,22 @@ void hits_drops_report_progress(int iter, struct bench_res *res, long delta_ns)
 	printf("Iter %3d (%7.3lfus): ",
 	       iter, (delta_ns - 1000000000) / 1000.0);
 
-	printf("hits %8.3lfM/s (%7.3lfM/prod), drops %8.3lfM/s\n",
-	       hits_per_sec, hits_per_prod, drops_per_sec);
+	printf("hits %8.3lfM/s (%7.3lfM/prod), drops %8.3lfM/s, total operations %8.3lfM/s\n",
+	       hits_per_sec, hits_per_prod, drops_per_sec, hits_per_sec + drops_per_sec);
 }
 
 void hits_drops_report_final(struct bench_res res[], int res_cnt)
 {
 	int i;
-	double hits_mean = 0.0, drops_mean = 0.0;
-	double hits_stddev = 0.0, drops_stddev = 0.0;
+	double hits_mean = 0.0, drops_mean = 0.0, total_ops_mean = 0.0;
+	double hits_stddev = 0.0, drops_stddev = 0.0, total_ops_stddev = 0.0;
+	double total_ops;
 
 	for (i = 0; i < res_cnt; i++) {
 		hits_mean += res[i].hits / 1000000.0 / (0.0 + res_cnt);
 		drops_mean += res[i].drops / 1000000.0 / (0.0 + res_cnt);
 	}
+	total_ops_mean = hits_mean + drops_mean;
 
 	if (res_cnt > 1)  {
 		for (i = 0; i < res_cnt; i++) {
@@ -115,14 +117,21 @@ void hits_drops_report_final(struct bench_res res[], int res_cnt)
 			drops_stddev += (drops_mean - res[i].drops / 1000000.0) *
 					(drops_mean - res[i].drops / 1000000.0) /
 					(res_cnt - 1.0);
+			total_ops = res[i].hits + res[i].drops;
+			total_ops_stddev += (total_ops_mean - total_ops / 1000000.0) *
+					(total_ops_mean - total_ops / 1000000.0) /
+					(res_cnt - 1.0);
 		}
 		hits_stddev = sqrt(hits_stddev);
 		drops_stddev = sqrt(drops_stddev);
+		total_ops_stddev = sqrt(total_ops_stddev);
 	}
 	printf("Summary: hits %8.3lf \u00B1 %5.3lfM/s (%7.3lfM/prod), ",
 	       hits_mean, hits_stddev, hits_mean / env.producer_cnt);
-	printf("drops %8.3lf \u00B1 %5.3lfM/s\n",
+	printf("drops %8.3lf \u00B1 %5.3lfM/s, ",
 	       drops_mean, drops_stddev);
+	printf("total operations %8.3lf \u00B1 %5.3lfM/s\n",
+	       total_ops_mean, total_ops_stddev);
 }
 
 const char *argp_program_version = "benchmark";
@@ -357,6 +366,8 @@ extern const struct bench bench_pb_custom;
 extern const struct bench bench_bloom_lookup;
 extern const struct bench bench_bloom_update;
 extern const struct bench bench_bloom_false_positive;
+extern const struct bench bench_hashmap_without_bloom;
+extern const struct bench bench_hashmap_with_bloom;
 
 static const struct bench *benchs[] = {
 	&bench_count_global,
@@ -381,6 +392,8 @@ static const struct bench *benchs[] = {
 	&bench_bloom_lookup,
 	&bench_bloom_update,
 	&bench_bloom_false_positive,
+	&bench_hashmap_without_bloom,
+	&bench_hashmap_with_bloom,
 };
 
 static void setup_benchmark()
diff --git a/tools/testing/selftests/bpf/benchs/bench_bloom_filter_map.c b/tools/testing/selftests/bpf/benchs/bench_bloom_filter_map.c
index 4bafad418a8a..6eeeed2913e6 100644
--- a/tools/testing/selftests/bpf/benchs/bench_bloom_filter_map.c
+++ b/tools/testing/selftests/bpf/benchs/bench_bloom_filter_map.c
@@ -346,6 +346,41 @@ static void false_positive_setup(void)
 	}
 }
 
+static void hashmap_with_bloom_setup(void)
+{
+	struct bpf_link *link;
+
+	ctx.use_hashmap = true;
+	ctx.hashmap_use_bloom = true;
+
+	ctx.skel = setup_skeleton();
+
+	populate_maps();
+
+	link = bpf_program__attach(ctx.skel->progs.bloom_hashmap_lookup);
+	if (!link) {
+		fprintf(stderr, "failed to attach program!\n");
+		exit(1);
+	}
+}
+
+static void hashmap_no_bloom_setup(void)
+{
+	struct bpf_link *link;
+
+	ctx.use_hashmap = true;
+
+	ctx.skel = setup_skeleton();
+
+	populate_maps();
+
+	link = bpf_program__attach(ctx.skel->progs.bloom_hashmap_lookup);
+	if (!link) {
+		fprintf(stderr, "failed to attach program!\n");
+		exit(1);
+	}
+}
+
 static void measure(struct bench_res *res)
 {
 	unsigned long total_hits = 0, total_drops = 0, total_false_hits = 0;
@@ -418,3 +453,25 @@ const struct bench bench_bloom_false_positive = {
 	.report_progress = false_hits_report_progress,
 	.report_final = false_hits_report_final,
 };
+
+const struct bench bench_hashmap_without_bloom = {
+	.name = "hashmap-without-bloom",
+	.validate = validate,
+	.setup = hashmap_no_bloom_setup,
+	.producer_thread = producer,
+	.consumer_thread = consumer,
+	.measure = measure,
+	.report_progress = hits_drops_report_progress,
+	.report_final = hits_drops_report_final,
+};
+
+const struct bench bench_hashmap_with_bloom = {
+	.name = "hashmap-with-bloom",
+	.validate = validate,
+	.setup = hashmap_with_bloom_setup,
+	.producer_thread = producer,
+	.consumer_thread = consumer,
+	.measure = measure,
+	.report_progress = hits_drops_report_progress,
+	.report_final = hits_drops_report_final,
+};
diff --git a/tools/testing/selftests/bpf/benchs/run_bench_bloom_filter_map.sh b/tools/testing/selftests/bpf/benchs/run_bench_bloom_filter_map.sh
index d03d0e5c91cd..8ffd385ab2f4 100755
--- a/tools/testing/selftests/bpf/benchs/run_bench_bloom_filter_map.sh
+++ b/tools/testing/selftests/bpf/benchs/run_bench_bloom_filter_map.sh
@@ -26,3 +26,20 @@ subtitle "value_size: $v bytes, # threads: $t, # hashes: $h"
 done
 done
 done
+
+header "Hashmap without bloom filter vs. hashmap with bloom filter (throughput, 8 threads)"
+for v in 2 4 8 16 40; do
+for h in {1..10}; do
+subtitle "value_size: $v, # hashes: $h"
+	for e in 10000 50000 75000 100000 250000 500000 750000 1000000 2500000 5000000; do
+		printf "%'d entries -\n" $e
+		printf "\t"
+		summarize_total "Hashmap without bloom filter: " \
+			"$($RUN_BENCH --nr_hash_funcs $h --nr_entries $e --value_size $v -p 8 hashmap-without-bloom)"
+		printf "\t"
+		summarize_total "Hashmap with bloom filter: " \
+			"$($RUN_BENCH --nr_hash_funcs $h --nr_entries $e --value_size $v -p 8 hashmap-with-bloom)"
+	done
+	printf "\n"
+done
+done
diff --git a/tools/testing/selftests/bpf/benchs/run_common.sh b/tools/testing/selftests/bpf/benchs/run_common.sh
index 670f23b037c4..9a16be78b180 100644
--- a/tools/testing/selftests/bpf/benchs/run_common.sh
+++ b/tools/testing/selftests/bpf/benchs/run_common.sh
@@ -33,6 +33,11 @@ function percentage()
 	echo "$*" | sed -E "s/.*Percentage\s=\s+([0-9]+\.[0-9]+).*/\1/"
 }
 
+function total()
+{
+	echo "$*" | sed -E "s/.*total operations\s+([0-9]+\.[0-9]+ ± [0-9]+\.[0-9]+M\/s).*/\1/"
+}
+
 function summarize()
 {
 	bench="$1"
@@ -46,3 +51,10 @@ function summarize_percentage()
 	summary=$(echo $2 | tail -n1)
 	printf "%-20s %s%%\n" "$bench" "$(percentage $summary)"
 }
+
+function summarize_total()
+{
+	bench="$1"
+	summary=$(echo $2 | tail -n1)
+	printf "%-20s %s\n" "$bench" "$(total $summary)"
+}
-- 
cgit v1.2.3


From d6aef08a872b9e23eecc92d0e92393473b13c497 Mon Sep 17 00:00:00 2001
From: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Date: Thu, 28 Oct 2021 12:04:54 +0530
Subject: bpf: Add bpf_kallsyms_lookup_name helper

This helper allows us to get the address of a kernel symbol from inside
a BPF_PROG_TYPE_SYSCALL prog (used by gen_loader), so that we can
relocate typeless ksym vars.

Signed-off-by: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Song Liu <songliubraving@fb.com>
Link: https://lore.kernel.org/bpf/20211028063501.2239335-2-memxor@gmail.com
---
 tools/include/uapi/linux/bpf.h | 16 ++++++++++++++++
 1 file changed, 16 insertions(+)

(limited to 'tools')

diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 8bead4aa3ad0..bd0c9f0487f6 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -4923,6 +4923,21 @@ union bpf_attr {
  *		Dynamically cast a *sk* pointer to a *unix_sock* pointer.
  *	Return
  *		*sk* if casting is valid, or **NULL** otherwise.
+ *
+ * long bpf_kallsyms_lookup_name(const char *name, int name_sz, int flags, u64 *res)
+ *	Description
+ *		Get the address of a kernel symbol, returned in *res*. *res* is
+ *		set to 0 if the symbol is not found.
+ *	Return
+ *		On success, zero. On error, a negative value.
+ *
+ *		**-EINVAL** if *flags* is not zero.
+ *
+ *		**-EINVAL** if string *name* is not the same size as *name_sz*.
+ *
+ *		**-ENOENT** if symbol is not found.
+ *
+ *		**-EPERM** if caller does not have permission to obtain kernel address.
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -5104,6 +5119,7 @@ union bpf_attr {
 	FN(get_branch_snapshot),	\
 	FN(trace_vprintk),		\
 	FN(skc_to_unix_sock),		\
+	FN(kallsyms_lookup_name),	\
 	/* */
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
-- 
cgit v1.2.3


From c24941cd3766b6de682dbe6809bd6af12271ab5b Mon Sep 17 00:00:00 2001
From: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Date: Thu, 28 Oct 2021 12:04:55 +0530
Subject: libbpf: Add typeless ksym support to gen_loader

This uses the bpf_kallsyms_lookup_name helper added in previous patches
to relocate typeless ksyms. The return value ENOENT can be ignored, and
the value written to 'res' can be directly stored to the insn, as it is
overwritten to 0 on lookup failure. For repeating symbols, we can simply
copy the previously populated bpf_insn.

Also, we need to take care to not close fds for typeless ksym_desc, so
reuse the 'off' member's space to add a marker for typeless ksym and use
that to skip them in cleanup_relos.

We add a emit_ksym_relo_log helper that avoids duplicating common
logging instructions between typeless and weak ksym (for future commit).

Signed-off-by: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20211028063501.2239335-3-memxor@gmail.com
---
 tools/lib/bpf/bpf_gen_internal.h | 12 +++--
 tools/lib/bpf/gen_loader.c       | 97 +++++++++++++++++++++++++++++++++++-----
 tools/lib/bpf/libbpf.c           | 13 +++---
 3 files changed, 99 insertions(+), 23 deletions(-)

(limited to 'tools')

diff --git a/tools/lib/bpf/bpf_gen_internal.h b/tools/lib/bpf/bpf_gen_internal.h
index b8d41d6fbc40..d26e5472fe50 100644
--- a/tools/lib/bpf/bpf_gen_internal.h
+++ b/tools/lib/bpf/bpf_gen_internal.h
@@ -8,13 +8,19 @@ struct ksym_relo_desc {
 	int kind;
 	int insn_idx;
 	bool is_weak;
+	bool is_typeless;
 };
 
 struct ksym_desc {
 	const char *name;
 	int ref;
 	int kind;
-	int off;
+	union {
+		/* used for kfunc */
+		int off;
+		/* used for typeless ksym */
+		bool typeless;
+	};
 	int insn;
 };
 
@@ -49,7 +55,7 @@ void bpf_gen__prog_load(struct bpf_gen *gen, struct bpf_prog_load_params *load_a
 void bpf_gen__map_update_elem(struct bpf_gen *gen, int map_idx, void *value, __u32 value_size);
 void bpf_gen__map_freeze(struct bpf_gen *gen, int map_idx);
 void bpf_gen__record_attach_target(struct bpf_gen *gen, const char *name, enum bpf_attach_type type);
-void bpf_gen__record_extern(struct bpf_gen *gen, const char *name, bool is_weak, int kind,
-			    int insn_idx);
+void bpf_gen__record_extern(struct bpf_gen *gen, const char *name, bool is_weak,
+			    bool is_typeless, int kind, int insn_idx);
 
 #endif
diff --git a/tools/lib/bpf/gen_loader.c b/tools/lib/bpf/gen_loader.c
index e552484ae4a4..bae065a9dbec 100644
--- a/tools/lib/bpf/gen_loader.c
+++ b/tools/lib/bpf/gen_loader.c
@@ -560,7 +560,7 @@ static void emit_find_attach_target(struct bpf_gen *gen)
 }
 
 void bpf_gen__record_extern(struct bpf_gen *gen, const char *name, bool is_weak,
-			    int kind, int insn_idx)
+			    bool is_typeless, int kind, int insn_idx)
 {
 	struct ksym_relo_desc *relo;
 
@@ -573,6 +573,7 @@ void bpf_gen__record_extern(struct bpf_gen *gen, const char *name, bool is_weak,
 	relo += gen->relo_cnt;
 	relo->name = name;
 	relo->is_weak = is_weak;
+	relo->is_typeless = is_typeless;
 	relo->kind = kind;
 	relo->insn_idx = insn_idx;
 	gen->relo_cnt++;
@@ -622,6 +623,29 @@ static void emit_bpf_find_by_name_kind(struct bpf_gen *gen, struct ksym_relo_des
 	debug_ret(gen, "find_by_name_kind(%s,%d)", relo->name, relo->kind);
 }
 
+/* Overwrites BPF_REG_{0, 1, 2, 3, 4, 7}
+ * Returns result in BPF_REG_7
+ * Returns u64 symbol addr in BPF_REG_9
+ */
+static void emit_bpf_kallsyms_lookup_name(struct bpf_gen *gen, struct ksym_relo_desc *relo)
+{
+	int name_off, len = strlen(relo->name) + 1, res_off;
+
+	name_off = add_data(gen, relo->name, len);
+	res_off = add_data(gen, NULL, 8); /* res is u64 */
+	emit2(gen, BPF_LD_IMM64_RAW_FULL(BPF_REG_1, BPF_PSEUDO_MAP_IDX_VALUE,
+					 0, 0, 0, name_off));
+	emit(gen, BPF_MOV64_IMM(BPF_REG_2, len));
+	emit(gen, BPF_MOV64_IMM(BPF_REG_3, 0));
+	emit2(gen, BPF_LD_IMM64_RAW_FULL(BPF_REG_4, BPF_PSEUDO_MAP_IDX_VALUE,
+					 0, 0, 0, res_off));
+	emit(gen, BPF_MOV64_REG(BPF_REG_7, BPF_REG_4));
+	emit(gen, BPF_EMIT_CALL(BPF_FUNC_kallsyms_lookup_name));
+	emit(gen, BPF_LDX_MEM(BPF_DW, BPF_REG_9, BPF_REG_7, 0));
+	emit(gen, BPF_MOV64_REG(BPF_REG_7, BPF_REG_0));
+	debug_ret(gen, "kallsyms_lookup_name(%s,%d)", relo->name, relo->kind);
+}
+
 /* Expects:
  * BPF_REG_8 - pointer to instruction
  *
@@ -701,6 +725,58 @@ log:
 		   relo->name, kdesc->ref);
 }
 
+static void emit_ksym_relo_log(struct bpf_gen *gen, struct ksym_relo_desc *relo,
+			       int ref)
+{
+	if (!gen->log_level)
+		return;
+	emit(gen, BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_8,
+			      offsetof(struct bpf_insn, imm)));
+	emit(gen, BPF_LDX_MEM(BPF_H, BPF_REG_9, BPF_REG_8, sizeof(struct bpf_insn) +
+			      offsetof(struct bpf_insn, imm)));
+	debug_regs(gen, BPF_REG_7, BPF_REG_9, " var t=%d w=%d (%s:count=%d): imm[0]: %%d, imm[1]: %%d",
+		   relo->is_typeless, relo->is_weak, relo->name, ref);
+	emit(gen, BPF_LDX_MEM(BPF_B, BPF_REG_9, BPF_REG_8, offsetofend(struct bpf_insn, code)));
+	debug_regs(gen, BPF_REG_9, -1, " var t=%d w=%d (%s:count=%d): insn.reg",
+		   relo->is_typeless, relo->is_weak, relo->name, ref);
+}
+
+/* Expects:
+ * BPF_REG_8 - pointer to instruction
+ */
+static void emit_relo_ksym_typeless(struct bpf_gen *gen,
+				    struct ksym_relo_desc *relo, int insn)
+{
+	struct ksym_desc *kdesc;
+
+	kdesc = get_ksym_desc(gen, relo);
+	if (!kdesc)
+		return;
+	/* try to copy from existing ldimm64 insn */
+	if (kdesc->ref > 1) {
+		move_blob2blob(gen, insn + offsetof(struct bpf_insn, imm), 4,
+			       kdesc->insn + offsetof(struct bpf_insn, imm));
+		move_blob2blob(gen, insn + sizeof(struct bpf_insn) + offsetof(struct bpf_insn, imm), 4,
+			       kdesc->insn + sizeof(struct bpf_insn) + offsetof(struct bpf_insn, imm));
+		goto log;
+	}
+	/* remember insn offset, so we can copy ksym addr later */
+	kdesc->insn = insn;
+	/* skip typeless ksym_desc in fd closing loop in cleanup_relos */
+	kdesc->typeless = true;
+	emit_bpf_kallsyms_lookup_name(gen, relo);
+	emit(gen, BPF_JMP_IMM(BPF_JEQ, BPF_REG_7, -ENOENT, 1));
+	emit_check_err(gen);
+	/* store lower half of addr into insn[insn_idx].imm */
+	emit(gen, BPF_STX_MEM(BPF_W, BPF_REG_8, BPF_REG_9, offsetof(struct bpf_insn, imm)));
+	/* store upper half of addr into insn[insn_idx + 1].imm */
+	emit(gen, BPF_ALU64_IMM(BPF_RSH, BPF_REG_9, 32));
+	emit(gen, BPF_STX_MEM(BPF_W, BPF_REG_8, BPF_REG_9,
+		      sizeof(struct bpf_insn) + offsetof(struct bpf_insn, imm)));
+log:
+	emit_ksym_relo_log(gen, relo, kdesc->ref);
+}
+
 /* Expects:
  * BPF_REG_8 - pointer to instruction
  */
@@ -730,14 +806,7 @@ static void emit_relo_ksym_btf(struct bpf_gen *gen, struct ksym_relo_desc *relo,
 	emit(gen, BPF_STX_MEM(BPF_W, BPF_REG_8, BPF_REG_7,
 			      sizeof(struct bpf_insn) + offsetof(struct bpf_insn, imm)));
 log:
-	if (!gen->log_level)
-		return;
-	emit(gen, BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_8,
-			      offsetof(struct bpf_insn, imm)));
-	emit(gen, BPF_LDX_MEM(BPF_H, BPF_REG_9, BPF_REG_8, sizeof(struct bpf_insn) +
-			      offsetof(struct bpf_insn, imm)));
-	debug_regs(gen, BPF_REG_7, BPF_REG_9, " var (%s:count=%d): imm: %%d, fd: %%d",
-		   relo->name, kdesc->ref);
+	emit_ksym_relo_log(gen, relo, kdesc->ref);
 }
 
 static void emit_relo(struct bpf_gen *gen, struct ksym_relo_desc *relo, int insns)
@@ -749,7 +818,10 @@ static void emit_relo(struct bpf_gen *gen, struct ksym_relo_desc *relo, int insn
 	emit2(gen, BPF_LD_IMM64_RAW_FULL(BPF_REG_8, BPF_PSEUDO_MAP_IDX_VALUE, 0, 0, 0, insn));
 	switch (relo->kind) {
 	case BTF_KIND_VAR:
-		emit_relo_ksym_btf(gen, relo, insn);
+		if (relo->is_typeless)
+			emit_relo_ksym_typeless(gen, relo, insn);
+		else
+			emit_relo_ksym_btf(gen, relo, insn);
 		break;
 	case BTF_KIND_FUNC:
 		emit_relo_kfunc_btf(gen, relo, insn);
@@ -774,12 +846,13 @@ static void cleanup_relos(struct bpf_gen *gen, int insns)
 	int i, insn;
 
 	for (i = 0; i < gen->nr_ksyms; i++) {
-		if (gen->ksyms[i].kind == BTF_KIND_VAR) {
+		/* only close fds for typed ksyms and kfuncs */
+		if (gen->ksyms[i].kind == BTF_KIND_VAR && !gen->ksyms[i].typeless) {
 			/* close fd recorded in insn[insn_idx + 1].imm */
 			insn = gen->ksyms[i].insn;
 			insn += sizeof(struct bpf_insn) + offsetof(struct bpf_insn, imm);
 			emit_sys_close_blob(gen, insn);
-		} else { /* BTF_KIND_FUNC */
+		} else if (gen->ksyms[i].kind == BTF_KIND_FUNC) {
 			emit_sys_close_blob(gen, blob_fd_array_off(gen, gen->ksyms[i].off));
 			if (gen->ksyms[i].off < MAX_FD_ARRAY_SZ)
 				gen->nr_fd_array--;
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 232e4efe82e9..73e1e70a722f 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -6575,17 +6575,14 @@ static int bpf_program__record_externs(struct bpf_program *prog)
 		case RELO_EXTERN_VAR:
 			if (ext->type != EXT_KSYM)
 				continue;
-			if (!ext->ksym.type_id) {
-				pr_warn("typeless ksym %s is not supported yet\n",
-					ext->name);
-				return -ENOTSUP;
-			}
-			bpf_gen__record_extern(obj->gen_loader, ext->name, ext->is_weak,
+			bpf_gen__record_extern(obj->gen_loader, ext->name,
+					       ext->is_weak, !ext->ksym.type_id,
 					       BTF_KIND_VAR, relo->insn_idx);
 			break;
 		case RELO_EXTERN_FUNC:
-			bpf_gen__record_extern(obj->gen_loader, ext->name, ext->is_weak,
-					       BTF_KIND_FUNC, relo->insn_idx);
+			bpf_gen__record_extern(obj->gen_loader, ext->name,
+					       ext->is_weak, false, BTF_KIND_FUNC,
+					       relo->insn_idx);
 			break;
 		default:
 			continue;
-- 
cgit v1.2.3


From 585a3571981d8a93e2211e1ac835d31a63e68cd8 Mon Sep 17 00:00:00 2001
From: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Date: Thu, 28 Oct 2021 12:04:56 +0530
Subject: libbpf: Add weak ksym support to gen_loader

This extends existing ksym relocation code to also support relocating
weak ksyms. Care needs to be taken to zero out the src_reg (currently
BPF_PSEUOD_BTF_ID, always set for gen_loader by bpf_object__relocate_data)
when the BTF ID lookup fails at runtime.  This is not a problem for
libbpf as it only sets ext->is_set when BTF ID lookup succeeds (and only
proceeds in case of failure if ext->is_weak, leading to src_reg
remaining as 0 for weak unresolved ksym).

A pattern similar to emit_relo_kfunc_btf is followed of first storing
the default values and then jumping over actual stores in case of an
error. For src_reg adjustment, we also need to perform it when copying
the populated instruction, so depending on if copied insn[0].imm is 0 or
not, we decide to jump over the adjustment.

We cannot reach that point unless the ksym was weak and resolved and
zeroed out, as the emit_check_err will cause us to jump to cleanup
label, so we do not need to recheck whether the ksym is weak before
doing the adjustment after copying BTF ID and BTF FD.

This is consistent with how libbpf relocates weak ksym. Logging
statements are added to show the relocation result and aid debugging.

Signed-off-by: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20211028063501.2239335-4-memxor@gmail.com
---
 tools/lib/bpf/gen_loader.c | 35 ++++++++++++++++++++++++++++++++---
 1 file changed, 32 insertions(+), 3 deletions(-)

(limited to 'tools')

diff --git a/tools/lib/bpf/gen_loader.c b/tools/lib/bpf/gen_loader.c
index bae065a9dbec..502dea53a742 100644
--- a/tools/lib/bpf/gen_loader.c
+++ b/tools/lib/bpf/gen_loader.c
@@ -13,6 +13,7 @@
 #include "hashmap.h"
 #include "bpf_gen_internal.h"
 #include "skel_internal.h"
+#include <asm/byteorder.h>
 
 #define MAX_USED_MAPS	64
 #define MAX_USED_PROGS	32
@@ -777,12 +778,24 @@ log:
 	emit_ksym_relo_log(gen, relo, kdesc->ref);
 }
 
+static __u32 src_reg_mask(void)
+{
+#if defined(__LITTLE_ENDIAN_BITFIELD)
+	return 0x0f; /* src_reg,dst_reg,... */
+#elif defined(__BIG_ENDIAN_BITFIELD)
+	return 0xf0; /* dst_reg,src_reg,... */
+#else
+#error "Unsupported bit endianness, cannot proceed"
+#endif
+}
+
 /* Expects:
  * BPF_REG_8 - pointer to instruction
  */
 static void emit_relo_ksym_btf(struct bpf_gen *gen, struct ksym_relo_desc *relo, int insn)
 {
 	struct ksym_desc *kdesc;
+	__u32 reg_mask;
 
 	kdesc = get_ksym_desc(gen, relo);
 	if (!kdesc)
@@ -793,19 +806,35 @@ static void emit_relo_ksym_btf(struct bpf_gen *gen, struct ksym_relo_desc *relo,
 			       kdesc->insn + offsetof(struct bpf_insn, imm));
 		move_blob2blob(gen, insn + sizeof(struct bpf_insn) + offsetof(struct bpf_insn, imm), 4,
 			       kdesc->insn + sizeof(struct bpf_insn) + offsetof(struct bpf_insn, imm));
-		goto log;
+		emit(gen, BPF_LDX_MEM(BPF_W, BPF_REG_9, BPF_REG_8, offsetof(struct bpf_insn, imm)));
+		/* jump over src_reg adjustment if imm is not 0 */
+		emit(gen, BPF_JMP_IMM(BPF_JNE, BPF_REG_9, 0, 3));
+		goto clear_src_reg;
 	}
 	/* remember insn offset, so we can copy BTF ID and FD later */
 	kdesc->insn = insn;
 	emit_bpf_find_by_name_kind(gen, relo);
-	emit_check_err(gen);
+	if (!relo->is_weak)
+		emit_check_err(gen);
+	/* set default values as 0 */
+	emit(gen, BPF_ST_MEM(BPF_W, BPF_REG_8, offsetof(struct bpf_insn, imm), 0));
+	emit(gen, BPF_ST_MEM(BPF_W, BPF_REG_8, sizeof(struct bpf_insn) + offsetof(struct bpf_insn, imm), 0));
+	/* skip success case stores if ret < 0 */
+	emit(gen, BPF_JMP_IMM(BPF_JSLT, BPF_REG_7, 0, 4));
 	/* store btf_id into insn[insn_idx].imm */
 	emit(gen, BPF_STX_MEM(BPF_W, BPF_REG_8, BPF_REG_7, offsetof(struct bpf_insn, imm)));
 	/* store btf_obj_fd into insn[insn_idx + 1].imm */
 	emit(gen, BPF_ALU64_IMM(BPF_RSH, BPF_REG_7, 32));
 	emit(gen, BPF_STX_MEM(BPF_W, BPF_REG_8, BPF_REG_7,
 			      sizeof(struct bpf_insn) + offsetof(struct bpf_insn, imm)));
-log:
+	emit(gen, BPF_JMP_IMM(BPF_JSGE, BPF_REG_7, 0, 3));
+clear_src_reg:
+	/* clear bpf_object__relocate_data's src_reg assignment, otherwise we get a verifier failure */
+	reg_mask = src_reg_mask();
+	emit(gen, BPF_LDX_MEM(BPF_B, BPF_REG_9, BPF_REG_8, offsetofend(struct bpf_insn, code)));
+	emit(gen, BPF_ALU32_IMM(BPF_AND, BPF_REG_9, reg_mask));
+	emit(gen, BPF_STX_MEM(BPF_B, BPF_REG_8, BPF_REG_9, offsetofend(struct bpf_insn, code)));
+
 	emit_ksym_relo_log(gen, relo, kdesc->ref);
 }
 
-- 
cgit v1.2.3


From 549a63238603103fa33cecd49487cf6c0f52e503 Mon Sep 17 00:00:00 2001
From: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Date: Thu, 28 Oct 2021 12:04:57 +0530
Subject: libbpf: Ensure that BPF syscall fds are never 0, 1, or 2

Add a simple wrapper for passing an fd and getting a new one >= 3 if it
is one of 0, 1, or 2. There are two primary reasons to make this change:
First, libbpf relies on the assumption a certain BPF fd is never 0 (e.g.
most recently noticed in [0]). Second, Alexei pointed out in [1] that
some environments reset stdin, stdout, and stderr if they notice an
invalid fd at these numbers. To protect against both these cases, switch
all internal BPF syscall wrappers in libbpf to always return an fd >= 3.
We only need to modify the syscall wrappers and not other code that
assumes a valid fd by doing >= 0, to avoid pointless churn, and because
it is still a valid assumption. The cost paid is two additional syscalls
if fd is in range [0, 2].

  [0]: e31eec77e4ab ("bpf: selftests: Fix fd cleanup in get_branch_snapshot")
  [1]: https://lore.kernel.org/bpf/CAADnVQKVKY8o_3aU8Gzke443+uHa-eGoM0h7W4srChMXU1S4Bg@mail.gmail.com

Signed-off-by: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Song Liu <songliubraving@fb.com>
Acked-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20211028063501.2239335-5-memxor@gmail.com
---
 tools/lib/bpf/bpf.c             | 35 ++++++++++++++++++++++-------------
 tools/lib/bpf/libbpf_internal.h | 24 ++++++++++++++++++++++++
 2 files changed, 46 insertions(+), 13 deletions(-)

(limited to 'tools')

diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c
index fe4b6ebc9b8f..c09cbb868c9f 100644
--- a/tools/lib/bpf/bpf.c
+++ b/tools/lib/bpf/bpf.c
@@ -65,13 +65,22 @@ static inline int sys_bpf(enum bpf_cmd cmd, union bpf_attr *attr,
 	return syscall(__NR_bpf, cmd, attr, size);
 }
 
+static inline int sys_bpf_fd(enum bpf_cmd cmd, union bpf_attr *attr,
+			     unsigned int size)
+{
+	int fd;
+
+	fd = sys_bpf(cmd, attr, size);
+	return ensure_good_fd(fd);
+}
+
 static inline int sys_bpf_prog_load(union bpf_attr *attr, unsigned int size)
 {
 	int retries = 5;
 	int fd;
 
 	do {
-		fd = sys_bpf(BPF_PROG_LOAD, attr, size);
+		fd = sys_bpf_fd(BPF_PROG_LOAD, attr, size);
 	} while (fd < 0 && errno == EAGAIN && retries-- > 0);
 
 	return fd;
@@ -104,7 +113,7 @@ int libbpf__bpf_create_map_xattr(const struct bpf_create_map_params *create_attr
 		attr.inner_map_fd = create_attr->inner_map_fd;
 	attr.map_extra = create_attr->map_extra;
 
-	fd = sys_bpf(BPF_MAP_CREATE, &attr, sizeof(attr));
+	fd = sys_bpf_fd(BPF_MAP_CREATE, &attr, sizeof(attr));
 	return libbpf_err_errno(fd);
 }
 
@@ -206,7 +215,7 @@ int bpf_create_map_in_map_node(enum bpf_map_type map_type, const char *name,
 		attr.numa_node = node;
 	}
 
-	fd = sys_bpf(BPF_MAP_CREATE, &attr, sizeof(attr));
+	fd = sys_bpf_fd(BPF_MAP_CREATE, &attr, sizeof(attr));
 	return libbpf_err_errno(fd);
 }
 
@@ -634,7 +643,7 @@ int bpf_obj_get(const char *pathname)
 	memset(&attr, 0, sizeof(attr));
 	attr.pathname = ptr_to_u64((void *)pathname);
 
-	fd = sys_bpf(BPF_OBJ_GET, &attr, sizeof(attr));
+	fd = sys_bpf_fd(BPF_OBJ_GET, &attr, sizeof(attr));
 	return libbpf_err_errno(fd);
 }
 
@@ -745,7 +754,7 @@ int bpf_link_create(int prog_fd, int target_fd,
 		break;
 	}
 proceed:
-	fd = sys_bpf(BPF_LINK_CREATE, &attr, sizeof(attr));
+	fd = sys_bpf_fd(BPF_LINK_CREATE, &attr, sizeof(attr));
 	return libbpf_err_errno(fd);
 }
 
@@ -788,7 +797,7 @@ int bpf_iter_create(int link_fd)
 	memset(&attr, 0, sizeof(attr));
 	attr.iter_create.link_fd = link_fd;
 
-	fd = sys_bpf(BPF_ITER_CREATE, &attr, sizeof(attr));
+	fd = sys_bpf_fd(BPF_ITER_CREATE, &attr, sizeof(attr));
 	return libbpf_err_errno(fd);
 }
 
@@ -946,7 +955,7 @@ int bpf_prog_get_fd_by_id(__u32 id)
 	memset(&attr, 0, sizeof(attr));
 	attr.prog_id = id;
 
-	fd = sys_bpf(BPF_PROG_GET_FD_BY_ID, &attr, sizeof(attr));
+	fd = sys_bpf_fd(BPF_PROG_GET_FD_BY_ID, &attr, sizeof(attr));
 	return libbpf_err_errno(fd);
 }
 
@@ -958,7 +967,7 @@ int bpf_map_get_fd_by_id(__u32 id)
 	memset(&attr, 0, sizeof(attr));
 	attr.map_id = id;
 
-	fd = sys_bpf(BPF_MAP_GET_FD_BY_ID, &attr, sizeof(attr));
+	fd = sys_bpf_fd(BPF_MAP_GET_FD_BY_ID, &attr, sizeof(attr));
 	return libbpf_err_errno(fd);
 }
 
@@ -970,7 +979,7 @@ int bpf_btf_get_fd_by_id(__u32 id)
 	memset(&attr, 0, sizeof(attr));
 	attr.btf_id = id;
 
-	fd = sys_bpf(BPF_BTF_GET_FD_BY_ID, &attr, sizeof(attr));
+	fd = sys_bpf_fd(BPF_BTF_GET_FD_BY_ID, &attr, sizeof(attr));
 	return libbpf_err_errno(fd);
 }
 
@@ -982,7 +991,7 @@ int bpf_link_get_fd_by_id(__u32 id)
 	memset(&attr, 0, sizeof(attr));
 	attr.link_id = id;
 
-	fd = sys_bpf(BPF_LINK_GET_FD_BY_ID, &attr, sizeof(attr));
+	fd = sys_bpf_fd(BPF_LINK_GET_FD_BY_ID, &attr, sizeof(attr));
 	return libbpf_err_errno(fd);
 }
 
@@ -1013,7 +1022,7 @@ int bpf_raw_tracepoint_open(const char *name, int prog_fd)
 	attr.raw_tracepoint.name = ptr_to_u64(name);
 	attr.raw_tracepoint.prog_fd = prog_fd;
 
-	fd = sys_bpf(BPF_RAW_TRACEPOINT_OPEN, &attr, sizeof(attr));
+	fd = sys_bpf_fd(BPF_RAW_TRACEPOINT_OPEN, &attr, sizeof(attr));
 	return libbpf_err_errno(fd);
 }
 
@@ -1033,7 +1042,7 @@ retry:
 		attr.btf_log_buf = ptr_to_u64(log_buf);
 	}
 
-	fd = sys_bpf(BPF_BTF_LOAD, &attr, sizeof(attr));
+	fd = sys_bpf_fd(BPF_BTF_LOAD, &attr, sizeof(attr));
 
 	if (fd < 0 && !do_log && log_buf && log_buf_size) {
 		do_log = true;
@@ -1075,7 +1084,7 @@ int bpf_enable_stats(enum bpf_stats_type type)
 	memset(&attr, 0, sizeof(attr));
 	attr.enable_stats.type = type;
 
-	fd = sys_bpf(BPF_ENABLE_STATS, &attr, sizeof(attr));
+	fd = sys_bpf_fd(BPF_ENABLE_STATS, &attr, sizeof(attr));
 	return libbpf_err_errno(fd);
 }
 
diff --git a/tools/lib/bpf/libbpf_internal.h b/tools/lib/bpf/libbpf_internal.h
index a6dd7e25747f..aeb79e3a8ff9 100644
--- a/tools/lib/bpf/libbpf_internal.h
+++ b/tools/lib/bpf/libbpf_internal.h
@@ -13,6 +13,8 @@
 #include <limits.h>
 #include <errno.h>
 #include <linux/err.h>
+#include <fcntl.h>
+#include <unistd.h>
 #include "libbpf_legacy.h"
 #include "relo_core.h"
 
@@ -491,4 +493,26 @@ static inline bool is_ldimm64_insn(struct bpf_insn *insn)
 	return insn->code == (BPF_LD | BPF_IMM | BPF_DW);
 }
 
+/* if fd is stdin, stdout, or stderr, dup to a fd greater than 2
+ * Takes ownership of the fd passed in, and closes it if calling
+ * fcntl(fd, F_DUPFD_CLOEXEC, 3).
+ */
+static inline int ensure_good_fd(int fd)
+{
+	int old_fd = fd, saved_errno;
+
+	if (fd < 0)
+		return fd;
+	if (fd < 3) {
+		fd = fcntl(fd, F_DUPFD_CLOEXEC, 3);
+		saved_errno = errno;
+		close(old_fd);
+		if (fd < 0) {
+			pr_warn("failed to dup FD %d to FD > 2: %d\n", old_fd, -saved_errno);
+			errno = saved_errno;
+		}
+	}
+	return fd;
+}
+
 #endif /* __LIBBPF_LIBBPF_INTERNAL_H */
-- 
cgit v1.2.3


From 92274e24b01b331ef7a4227135933e6163fe94aa Mon Sep 17 00:00:00 2001
From: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Date: Thu, 28 Oct 2021 12:04:58 +0530
Subject: libbpf: Use O_CLOEXEC uniformly when opening fds

There are some instances where we don't use O_CLOEXEC when opening an
fd, fix these up. Otherwise, it is possible that a parallel fork causes
these fds to leak into a child process on execve.

Signed-off-by: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20211028063501.2239335-6-memxor@gmail.com
---
 tools/lib/bpf/btf.c           | 2 +-
 tools/lib/bpf/libbpf.c        | 6 +++---
 tools/lib/bpf/libbpf_probes.c | 2 +-
 tools/lib/bpf/linker.c        | 4 ++--
 tools/lib/bpf/xsk.c           | 6 +++---
 5 files changed, 10 insertions(+), 10 deletions(-)

(limited to 'tools')

diff --git a/tools/lib/bpf/btf.c b/tools/lib/bpf/btf.c
index 0c628c33e23b..7e4c5586bd87 100644
--- a/tools/lib/bpf/btf.c
+++ b/tools/lib/bpf/btf.c
@@ -897,7 +897,7 @@ static struct btf *btf_parse_elf(const char *path, struct btf *base_btf,
 		return ERR_PTR(-LIBBPF_ERRNO__LIBELF);
 	}
 
-	fd = open(path, O_RDONLY);
+	fd = open(path, O_RDONLY | O_CLOEXEC);
 	if (fd < 0) {
 		err = -errno;
 		pr_warn("failed to open %s: %s\n", path, strerror(errno));
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 73e1e70a722f..742d1a388179 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -1232,7 +1232,7 @@ static int bpf_object__elf_init(struct bpf_object *obj)
 		 */
 		elf = elf_memory((char *)obj->efile.obj_buf, obj->efile.obj_buf_sz);
 	} else {
-		obj->efile.fd = open(obj->path, O_RDONLY);
+		obj->efile.fd = open(obj->path, O_RDONLY | O_CLOEXEC);
 		if (obj->efile.fd < 0) {
 			char errmsg[STRERR_BUFSIZE], *cp;
 
@@ -9615,7 +9615,7 @@ static int append_to_file(const char *file, const char *fmt, ...)
 	int fd, n, err = 0;
 	va_list ap;
 
-	fd = open(file, O_WRONLY | O_APPEND, 0);
+	fd = open(file, O_WRONLY | O_APPEND | O_CLOEXEC, 0);
 	if (fd < 0)
 		return -errno;
 
@@ -11260,7 +11260,7 @@ int parse_cpu_mask_file(const char *fcpu, bool **mask, int *mask_sz)
 	int fd, err = 0, len;
 	char buf[128];
 
-	fd = open(fcpu, O_RDONLY);
+	fd = open(fcpu, O_RDONLY | O_CLOEXEC);
 	if (fd < 0) {
 		err = -errno;
 		pr_warn("Failed to open cpu mask file %s: %d\n", fcpu, err);
diff --git a/tools/lib/bpf/libbpf_probes.c b/tools/lib/bpf/libbpf_probes.c
index cd8c703dde71..68f2dbf364aa 100644
--- a/tools/lib/bpf/libbpf_probes.c
+++ b/tools/lib/bpf/libbpf_probes.c
@@ -33,7 +33,7 @@ static int get_vendor_id(int ifindex)
 
 	snprintf(path, sizeof(path), "/sys/class/net/%s/device/vendor", ifname);
 
-	fd = open(path, O_RDONLY);
+	fd = open(path, O_RDONLY | O_CLOEXEC);
 	if (fd < 0)
 		return -1;
 
diff --git a/tools/lib/bpf/linker.c b/tools/lib/bpf/linker.c
index ce0800e61dc7..f677dccdeae4 100644
--- a/tools/lib/bpf/linker.c
+++ b/tools/lib/bpf/linker.c
@@ -301,7 +301,7 @@ static int init_output_elf(struct bpf_linker *linker, const char *file)
 	if (!linker->filename)
 		return -ENOMEM;
 
-	linker->fd = open(file, O_WRONLY | O_CREAT | O_TRUNC, 0644);
+	linker->fd = open(file, O_WRONLY | O_CREAT | O_TRUNC | O_CLOEXEC, 0644);
 	if (linker->fd < 0) {
 		err = -errno;
 		pr_warn("failed to create '%s': %d\n", file, err);
@@ -556,7 +556,7 @@ static int linker_load_obj_file(struct bpf_linker *linker, const char *filename,
 
 	obj->filename = filename;
 
-	obj->fd = open(filename, O_RDONLY);
+	obj->fd = open(filename, O_RDONLY | O_CLOEXEC);
 	if (obj->fd < 0) {
 		err = -errno;
 		pr_warn("failed to open file '%s': %d\n", filename, err);
diff --git a/tools/lib/bpf/xsk.c b/tools/lib/bpf/xsk.c
index a2111696ba91..81f8fbc85e70 100644
--- a/tools/lib/bpf/xsk.c
+++ b/tools/lib/bpf/xsk.c
@@ -300,7 +300,7 @@ int xsk_umem__create_v0_0_4(struct xsk_umem **umem_ptr, void *umem_area,
 	if (!umem)
 		return -ENOMEM;
 
-	umem->fd = socket(AF_XDP, SOCK_RAW, 0);
+	umem->fd = socket(AF_XDP, SOCK_RAW | SOCK_CLOEXEC, 0);
 	if (umem->fd < 0) {
 		err = -errno;
 		goto out_umem_alloc;
@@ -549,7 +549,7 @@ static int xsk_get_max_queues(struct xsk_socket *xsk)
 	struct ifreq ifr = {};
 	int fd, err, ret;
 
-	fd = socket(AF_LOCAL, SOCK_DGRAM, 0);
+	fd = socket(AF_LOCAL, SOCK_DGRAM | SOCK_CLOEXEC, 0);
 	if (fd < 0)
 		return -errno;
 
@@ -1046,7 +1046,7 @@ int xsk_socket__create_shared(struct xsk_socket **xsk_ptr,
 	}
 
 	if (umem->refcount++ > 0) {
-		xsk->fd = socket(AF_XDP, SOCK_RAW, 0);
+		xsk->fd = socket(AF_XDP, SOCK_RAW | SOCK_CLOEXEC, 0);
 		if (xsk->fd < 0) {
 			err = -errno;
 			goto out_xsk_alloc;
-- 
cgit v1.2.3


From 087cba799ced0573df499ddd3b2d8777e50cfb62 Mon Sep 17 00:00:00 2001
From: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Date: Thu, 28 Oct 2021 12:04:59 +0530
Subject: selftests/bpf: Add weak/typeless ksym test for light skeleton

Also, avoid using CO-RE features, as lskel doesn't support CO-RE, yet.
Include both light and libbpf skeleton in same file to test both of them
together.

In c48e51c8b07a ("bpf: selftests: Add selftests for module kfunc support"),
I added support for generating both lskel and libbpf skel for a BPF
object, however the name parameter for bpftool caused collisions when
included in same file together. This meant that every test needed a
separate file for a libbpf/light skeleton separation instead of
subtests.

Change that by appending a "_lskel" suffix to the name for files using
light skeleton, and convert all existing users.

Signed-off-by: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20211028063501.2239335-7-memxor@gmail.com
---
 tools/testing/selftests/bpf/Makefile               |  4 +--
 tools/testing/selftests/bpf/prog_tests/atomics.c   | 34 +++++++++---------
 .../selftests/bpf/prog_tests/fentry_fexit.c        | 16 ++++-----
 .../testing/selftests/bpf/prog_tests/fentry_test.c | 14 ++++----
 .../testing/selftests/bpf/prog_tests/fexit_sleep.c | 12 +++----
 .../testing/selftests/bpf/prog_tests/fexit_test.c  | 14 ++++----
 .../testing/selftests/bpf/prog_tests/kfunc_call.c  |  6 ++--
 tools/testing/selftests/bpf/prog_tests/ksyms_btf.c | 35 +++++++++++++++++--
 .../selftests/bpf/prog_tests/ksyms_module.c        | 40 +++++++++++++++++++---
 .../selftests/bpf/prog_tests/ksyms_module_libbpf.c | 28 ---------------
 tools/testing/selftests/bpf/prog_tests/ringbuf.c   | 12 +++----
 .../selftests/bpf/prog_tests/trace_printk.c        | 14 ++++----
 .../selftests/bpf/prog_tests/trace_vprintk.c       | 12 +++----
 .../testing/selftests/bpf/prog_tests/verif_stats.c |  6 ++--
 .../testing/selftests/bpf/progs/test_ksyms_weak.c  |  2 +-
 15 files changed, 142 insertions(+), 107 deletions(-)
 delete mode 100644 tools/testing/selftests/bpf/prog_tests/ksyms_module_libbpf.c

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index 2c464cb78d6b..f49cb5fc85af 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -325,7 +325,7 @@ LINKED_SKELS := test_static_linked.skel.h linked_funcs.skel.h		\
 LSKELS := kfunc_call_test.c fentry_test.c fexit_test.c fexit_sleep.c \
 	test_ringbuf.c atomics.c trace_printk.c trace_vprintk.c
 # Generate both light skeleton and libbpf skeleton for these
-LSKELS_EXTRA := test_ksyms_module.c
+LSKELS_EXTRA := test_ksyms_module.c test_ksyms_weak.c
 SKEL_BLACKLIST += $$(LSKELS)
 
 test_static_linked.skel.h-deps := test_static_linked1.o test_static_linked2.o
@@ -404,7 +404,7 @@ $(TRUNNER_BPF_LSKELS): %.lskel.h: %.o $(BPFTOOL) | $(TRUNNER_OUTPUT)
 	$(Q)$$(BPFTOOL) gen object $$(<:.o=.linked2.o) $$(<:.o=.linked1.o)
 	$(Q)$$(BPFTOOL) gen object $$(<:.o=.linked3.o) $$(<:.o=.linked2.o)
 	$(Q)diff $$(<:.o=.linked2.o) $$(<:.o=.linked3.o)
-	$(Q)$$(BPFTOOL) gen skeleton -L $$(<:.o=.linked3.o) name $$(notdir $$(<:.o=)) > $$@
+	$(Q)$$(BPFTOOL) gen skeleton -L $$(<:.o=.linked3.o) name $$(notdir $$(<:.o=_lskel)) > $$@
 
 $(TRUNNER_BPF_SKELS_LINKED): $(TRUNNER_BPF_OBJS) $(BPFTOOL) | $(TRUNNER_OUTPUT)
 	$$(call msg,LINK-BPF,$(TRUNNER_BINARY),$$(@:.skel.h=.o))
diff --git a/tools/testing/selftests/bpf/prog_tests/atomics.c b/tools/testing/selftests/bpf/prog_tests/atomics.c
index 1486be5d3209..0f9525293881 100644
--- a/tools/testing/selftests/bpf/prog_tests/atomics.c
+++ b/tools/testing/selftests/bpf/prog_tests/atomics.c
@@ -4,13 +4,13 @@
 
 #include "atomics.lskel.h"
 
-static void test_add(struct atomics *skel)
+static void test_add(struct atomics_lskel *skel)
 {
 	int err, prog_fd;
 	__u32 duration = 0, retval;
 	int link_fd;
 
-	link_fd = atomics__add__attach(skel);
+	link_fd = atomics_lskel__add__attach(skel);
 	if (!ASSERT_GT(link_fd, 0, "attach(add)"))
 		return;
 
@@ -36,13 +36,13 @@ cleanup:
 	close(link_fd);
 }
 
-static void test_sub(struct atomics *skel)
+static void test_sub(struct atomics_lskel *skel)
 {
 	int err, prog_fd;
 	__u32 duration = 0, retval;
 	int link_fd;
 
-	link_fd = atomics__sub__attach(skel);
+	link_fd = atomics_lskel__sub__attach(skel);
 	if (!ASSERT_GT(link_fd, 0, "attach(sub)"))
 		return;
 
@@ -69,13 +69,13 @@ cleanup:
 	close(link_fd);
 }
 
-static void test_and(struct atomics *skel)
+static void test_and(struct atomics_lskel *skel)
 {
 	int err, prog_fd;
 	__u32 duration = 0, retval;
 	int link_fd;
 
-	link_fd = atomics__and__attach(skel);
+	link_fd = atomics_lskel__and__attach(skel);
 	if (!ASSERT_GT(link_fd, 0, "attach(and)"))
 		return;
 
@@ -97,13 +97,13 @@ cleanup:
 	close(link_fd);
 }
 
-static void test_or(struct atomics *skel)
+static void test_or(struct atomics_lskel *skel)
 {
 	int err, prog_fd;
 	__u32 duration = 0, retval;
 	int link_fd;
 
-	link_fd = atomics__or__attach(skel);
+	link_fd = atomics_lskel__or__attach(skel);
 	if (!ASSERT_GT(link_fd, 0, "attach(or)"))
 		return;
 
@@ -126,13 +126,13 @@ cleanup:
 	close(link_fd);
 }
 
-static void test_xor(struct atomics *skel)
+static void test_xor(struct atomics_lskel *skel)
 {
 	int err, prog_fd;
 	__u32 duration = 0, retval;
 	int link_fd;
 
-	link_fd = atomics__xor__attach(skel);
+	link_fd = atomics_lskel__xor__attach(skel);
 	if (!ASSERT_GT(link_fd, 0, "attach(xor)"))
 		return;
 
@@ -154,13 +154,13 @@ cleanup:
 	close(link_fd);
 }
 
-static void test_cmpxchg(struct atomics *skel)
+static void test_cmpxchg(struct atomics_lskel *skel)
 {
 	int err, prog_fd;
 	__u32 duration = 0, retval;
 	int link_fd;
 
-	link_fd = atomics__cmpxchg__attach(skel);
+	link_fd = atomics_lskel__cmpxchg__attach(skel);
 	if (!ASSERT_GT(link_fd, 0, "attach(cmpxchg)"))
 		return;
 
@@ -183,13 +183,13 @@ cleanup:
 	close(link_fd);
 }
 
-static void test_xchg(struct atomics *skel)
+static void test_xchg(struct atomics_lskel *skel)
 {
 	int err, prog_fd;
 	__u32 duration = 0, retval;
 	int link_fd;
 
-	link_fd = atomics__xchg__attach(skel);
+	link_fd = atomics_lskel__xchg__attach(skel);
 	if (!ASSERT_GT(link_fd, 0, "attach(xchg)"))
 		return;
 
@@ -212,10 +212,10 @@ cleanup:
 
 void test_atomics(void)
 {
-	struct atomics *skel;
+	struct atomics_lskel *skel;
 	__u32 duration = 0;
 
-	skel = atomics__open_and_load();
+	skel = atomics_lskel__open_and_load();
 	if (CHECK(!skel, "skel_load", "atomics skeleton failed\n"))
 		return;
 
@@ -243,5 +243,5 @@ void test_atomics(void)
 		test_xchg(skel);
 
 cleanup:
-	atomics__destroy(skel);
+	atomics_lskel__destroy(skel);
 }
diff --git a/tools/testing/selftests/bpf/prog_tests/fentry_fexit.c b/tools/testing/selftests/bpf/prog_tests/fentry_fexit.c
index 91154c2ba256..4374ac8a8a91 100644
--- a/tools/testing/selftests/bpf/prog_tests/fentry_fexit.c
+++ b/tools/testing/selftests/bpf/prog_tests/fentry_fexit.c
@@ -6,23 +6,23 @@
 
 void test_fentry_fexit(void)
 {
-	struct fentry_test *fentry_skel = NULL;
-	struct fexit_test *fexit_skel = NULL;
+	struct fentry_test_lskel *fentry_skel = NULL;
+	struct fexit_test_lskel *fexit_skel = NULL;
 	__u64 *fentry_res, *fexit_res;
 	__u32 duration = 0, retval;
 	int err, prog_fd, i;
 
-	fentry_skel = fentry_test__open_and_load();
+	fentry_skel = fentry_test_lskel__open_and_load();
 	if (CHECK(!fentry_skel, "fentry_skel_load", "fentry skeleton failed\n"))
 		goto close_prog;
-	fexit_skel = fexit_test__open_and_load();
+	fexit_skel = fexit_test_lskel__open_and_load();
 	if (CHECK(!fexit_skel, "fexit_skel_load", "fexit skeleton failed\n"))
 		goto close_prog;
 
-	err = fentry_test__attach(fentry_skel);
+	err = fentry_test_lskel__attach(fentry_skel);
 	if (CHECK(err, "fentry_attach", "fentry attach failed: %d\n", err))
 		goto close_prog;
-	err = fexit_test__attach(fexit_skel);
+	err = fexit_test_lskel__attach(fexit_skel);
 	if (CHECK(err, "fexit_attach", "fexit attach failed: %d\n", err))
 		goto close_prog;
 
@@ -44,6 +44,6 @@ void test_fentry_fexit(void)
 	}
 
 close_prog:
-	fentry_test__destroy(fentry_skel);
-	fexit_test__destroy(fexit_skel);
+	fentry_test_lskel__destroy(fentry_skel);
+	fexit_test_lskel__destroy(fexit_skel);
 }
diff --git a/tools/testing/selftests/bpf/prog_tests/fentry_test.c b/tools/testing/selftests/bpf/prog_tests/fentry_test.c
index 174c89e7456e..12921b3850d2 100644
--- a/tools/testing/selftests/bpf/prog_tests/fentry_test.c
+++ b/tools/testing/selftests/bpf/prog_tests/fentry_test.c
@@ -3,19 +3,19 @@
 #include <test_progs.h>
 #include "fentry_test.lskel.h"
 
-static int fentry_test(struct fentry_test *fentry_skel)
+static int fentry_test(struct fentry_test_lskel *fentry_skel)
 {
 	int err, prog_fd, i;
 	__u32 duration = 0, retval;
 	int link_fd;
 	__u64 *result;
 
-	err = fentry_test__attach(fentry_skel);
+	err = fentry_test_lskel__attach(fentry_skel);
 	if (!ASSERT_OK(err, "fentry_attach"))
 		return err;
 
 	/* Check that already linked program can't be attached again. */
-	link_fd = fentry_test__test1__attach(fentry_skel);
+	link_fd = fentry_test_lskel__test1__attach(fentry_skel);
 	if (!ASSERT_LT(link_fd, 0, "fentry_attach_link"))
 		return -1;
 
@@ -31,7 +31,7 @@ static int fentry_test(struct fentry_test *fentry_skel)
 			return -1;
 	}
 
-	fentry_test__detach(fentry_skel);
+	fentry_test_lskel__detach(fentry_skel);
 
 	/* zero results for re-attach test */
 	memset(fentry_skel->bss, 0, sizeof(*fentry_skel->bss));
@@ -40,10 +40,10 @@ static int fentry_test(struct fentry_test *fentry_skel)
 
 void test_fentry_test(void)
 {
-	struct fentry_test *fentry_skel = NULL;
+	struct fentry_test_lskel *fentry_skel = NULL;
 	int err;
 
-	fentry_skel = fentry_test__open_and_load();
+	fentry_skel = fentry_test_lskel__open_and_load();
 	if (!ASSERT_OK_PTR(fentry_skel, "fentry_skel_load"))
 		goto cleanup;
 
@@ -55,5 +55,5 @@ void test_fentry_test(void)
 	ASSERT_OK(err, "fentry_second_attach");
 
 cleanup:
-	fentry_test__destroy(fentry_skel);
+	fentry_test_lskel__destroy(fentry_skel);
 }
diff --git a/tools/testing/selftests/bpf/prog_tests/fexit_sleep.c b/tools/testing/selftests/bpf/prog_tests/fexit_sleep.c
index 4e7f4b42ea29..f949647dbbc2 100644
--- a/tools/testing/selftests/bpf/prog_tests/fexit_sleep.c
+++ b/tools/testing/selftests/bpf/prog_tests/fexit_sleep.c
@@ -10,7 +10,7 @@
 
 static int do_sleep(void *skel)
 {
-	struct fexit_sleep *fexit_skel = skel;
+	struct fexit_sleep_lskel *fexit_skel = skel;
 	struct timespec ts1 = { .tv_nsec = 1 };
 	struct timespec ts2 = { .tv_sec = 10 };
 
@@ -25,16 +25,16 @@ static char child_stack[STACK_SIZE];
 
 void test_fexit_sleep(void)
 {
-	struct fexit_sleep *fexit_skel = NULL;
+	struct fexit_sleep_lskel *fexit_skel = NULL;
 	int wstatus, duration = 0;
 	pid_t cpid;
 	int err, fexit_cnt;
 
-	fexit_skel = fexit_sleep__open_and_load();
+	fexit_skel = fexit_sleep_lskel__open_and_load();
 	if (CHECK(!fexit_skel, "fexit_skel_load", "fexit skeleton failed\n"))
 		goto cleanup;
 
-	err = fexit_sleep__attach(fexit_skel);
+	err = fexit_sleep_lskel__attach(fexit_skel);
 	if (CHECK(err, "fexit_attach", "fexit attach failed: %d\n", err))
 		goto cleanup;
 
@@ -60,7 +60,7 @@ void test_fexit_sleep(void)
 	 */
 	close(fexit_skel->progs.nanosleep_fentry.prog_fd);
 	close(fexit_skel->progs.nanosleep_fexit.prog_fd);
-	fexit_sleep__detach(fexit_skel);
+	fexit_sleep_lskel__detach(fexit_skel);
 
 	/* kill the thread to unwind sys_nanosleep stack through the trampoline */
 	kill(cpid, 9);
@@ -78,5 +78,5 @@ void test_fexit_sleep(void)
 		goto cleanup;
 
 cleanup:
-	fexit_sleep__destroy(fexit_skel);
+	fexit_sleep_lskel__destroy(fexit_skel);
 }
diff --git a/tools/testing/selftests/bpf/prog_tests/fexit_test.c b/tools/testing/selftests/bpf/prog_tests/fexit_test.c
index af3dba726701..d4887d8bb396 100644
--- a/tools/testing/selftests/bpf/prog_tests/fexit_test.c
+++ b/tools/testing/selftests/bpf/prog_tests/fexit_test.c
@@ -3,19 +3,19 @@
 #include <test_progs.h>
 #include "fexit_test.lskel.h"
 
-static int fexit_test(struct fexit_test *fexit_skel)
+static int fexit_test(struct fexit_test_lskel *fexit_skel)
 {
 	int err, prog_fd, i;
 	__u32 duration = 0, retval;
 	int link_fd;
 	__u64 *result;
 
-	err = fexit_test__attach(fexit_skel);
+	err = fexit_test_lskel__attach(fexit_skel);
 	if (!ASSERT_OK(err, "fexit_attach"))
 		return err;
 
 	/* Check that already linked program can't be attached again. */
-	link_fd = fexit_test__test1__attach(fexit_skel);
+	link_fd = fexit_test_lskel__test1__attach(fexit_skel);
 	if (!ASSERT_LT(link_fd, 0, "fexit_attach_link"))
 		return -1;
 
@@ -31,7 +31,7 @@ static int fexit_test(struct fexit_test *fexit_skel)
 			return -1;
 	}
 
-	fexit_test__detach(fexit_skel);
+	fexit_test_lskel__detach(fexit_skel);
 
 	/* zero results for re-attach test */
 	memset(fexit_skel->bss, 0, sizeof(*fexit_skel->bss));
@@ -40,10 +40,10 @@ static int fexit_test(struct fexit_test *fexit_skel)
 
 void test_fexit_test(void)
 {
-	struct fexit_test *fexit_skel = NULL;
+	struct fexit_test_lskel *fexit_skel = NULL;
 	int err;
 
-	fexit_skel = fexit_test__open_and_load();
+	fexit_skel = fexit_test_lskel__open_and_load();
 	if (!ASSERT_OK_PTR(fexit_skel, "fexit_skel_load"))
 		goto cleanup;
 
@@ -55,5 +55,5 @@ void test_fexit_test(void)
 	ASSERT_OK(err, "fexit_second_attach");
 
 cleanup:
-	fexit_test__destroy(fexit_skel);
+	fexit_test_lskel__destroy(fexit_skel);
 }
diff --git a/tools/testing/selftests/bpf/prog_tests/kfunc_call.c b/tools/testing/selftests/bpf/prog_tests/kfunc_call.c
index 9611f2bc50df..5c9c0176991b 100644
--- a/tools/testing/selftests/bpf/prog_tests/kfunc_call.c
+++ b/tools/testing/selftests/bpf/prog_tests/kfunc_call.c
@@ -7,10 +7,10 @@
 
 static void test_main(void)
 {
-	struct kfunc_call_test *skel;
+	struct kfunc_call_test_lskel *skel;
 	int prog_fd, retval, err;
 
-	skel = kfunc_call_test__open_and_load();
+	skel = kfunc_call_test_lskel__open_and_load();
 	if (!ASSERT_OK_PTR(skel, "skel"))
 		return;
 
@@ -26,7 +26,7 @@ static void test_main(void)
 	ASSERT_OK(err, "bpf_prog_test_run(test2)");
 	ASSERT_EQ(retval, 3, "test2-retval");
 
-	kfunc_call_test__destroy(skel);
+	kfunc_call_test_lskel__destroy(skel);
 }
 
 static void test_subprog(void)
diff --git a/tools/testing/selftests/bpf/prog_tests/ksyms_btf.c b/tools/testing/selftests/bpf/prog_tests/ksyms_btf.c
index cf3acfa5a91d..79f6bd1e50d6 100644
--- a/tools/testing/selftests/bpf/prog_tests/ksyms_btf.c
+++ b/tools/testing/selftests/bpf/prog_tests/ksyms_btf.c
@@ -7,6 +7,7 @@
 #include "test_ksyms_btf.skel.h"
 #include "test_ksyms_btf_null_check.skel.h"
 #include "test_ksyms_weak.skel.h"
+#include "test_ksyms_weak.lskel.h"
 
 static int duration;
 
@@ -89,11 +90,11 @@ static void test_weak_syms(void)
 	int err;
 
 	skel = test_ksyms_weak__open_and_load();
-	if (CHECK(!skel, "test_ksyms_weak__open_and_load", "failed\n"))
+	if (!ASSERT_OK_PTR(skel, "test_ksyms_weak__open_and_load"))
 		return;
 
 	err = test_ksyms_weak__attach(skel);
-	if (CHECK(err, "test_ksyms_weak__attach", "skeleton attach failed: %d\n", err))
+	if (!ASSERT_OK(err, "test_ksyms_weak__attach"))
 		goto cleanup;
 
 	/* trigger tracepoint */
@@ -109,6 +110,33 @@ cleanup:
 	test_ksyms_weak__destroy(skel);
 }
 
+static void test_weak_syms_lskel(void)
+{
+	struct test_ksyms_weak_lskel *skel;
+	struct test_ksyms_weak_lskel__data *data;
+	int err;
+
+	skel = test_ksyms_weak_lskel__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "test_ksyms_weak_lskel__open_and_load"))
+		return;
+
+	err = test_ksyms_weak_lskel__attach(skel);
+	if (!ASSERT_OK(err, "test_ksyms_weak_lskel__attach"))
+		goto cleanup;
+
+	/* trigger tracepoint */
+	usleep(1);
+
+	data = skel->data;
+	ASSERT_EQ(data->out__existing_typed, 0, "existing typed ksym");
+	ASSERT_NEQ(data->out__existing_typeless, -1, "existing typeless ksym");
+	ASSERT_EQ(data->out__non_existent_typeless, 0, "nonexistent typeless ksym");
+	ASSERT_EQ(data->out__non_existent_typed, 0, "nonexistent typed ksym");
+
+cleanup:
+	test_ksyms_weak_lskel__destroy(skel);
+}
+
 void test_ksyms_btf(void)
 {
 	int percpu_datasec;
@@ -136,4 +164,7 @@ void test_ksyms_btf(void)
 
 	if (test__start_subtest("weak_ksyms"))
 		test_weak_syms();
+
+	if (test__start_subtest("weak_ksyms_lskel"))
+		test_weak_syms_lskel();
 }
diff --git a/tools/testing/selftests/bpf/prog_tests/ksyms_module.c b/tools/testing/selftests/bpf/prog_tests/ksyms_module.c
index 831447878d7b..d490ad80eccb 100644
--- a/tools/testing/selftests/bpf/prog_tests/ksyms_module.c
+++ b/tools/testing/selftests/bpf/prog_tests/ksyms_module.c
@@ -4,10 +4,11 @@
 #include <test_progs.h>
 #include <network_helpers.h>
 #include "test_ksyms_module.lskel.h"
+#include "test_ksyms_module.skel.h"
 
-void test_ksyms_module(void)
+void test_ksyms_module_lskel(void)
 {
-	struct test_ksyms_module *skel;
+	struct test_ksyms_module_lskel *skel;
 	int retval;
 	int err;
 
@@ -16,8 +17,8 @@ void test_ksyms_module(void)
 		return;
 	}
 
-	skel = test_ksyms_module__open_and_load();
-	if (!ASSERT_OK_PTR(skel, "test_ksyms_module__open_and_load"))
+	skel = test_ksyms_module_lskel__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "test_ksyms_module_lskel__open_and_load"))
 		return;
 	err = bpf_prog_test_run(skel->progs.load.prog_fd, 1, &pkt_v4, sizeof(pkt_v4),
 				NULL, NULL, (__u32 *)&retval, NULL);
@@ -25,6 +26,37 @@ void test_ksyms_module(void)
 		goto cleanup;
 	ASSERT_EQ(retval, 0, "retval");
 	ASSERT_EQ(skel->bss->out_bpf_testmod_ksym, 42, "bpf_testmod_ksym");
+cleanup:
+	test_ksyms_module_lskel__destroy(skel);
+}
+
+void test_ksyms_module_libbpf(void)
+{
+	struct test_ksyms_module *skel;
+	int retval, err;
+
+	if (!env.has_testmod) {
+		test__skip();
+		return;
+	}
+
+	skel = test_ksyms_module__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "test_ksyms_module__open"))
+		return;
+	err = bpf_prog_test_run(bpf_program__fd(skel->progs.load), 1, &pkt_v4,
+				sizeof(pkt_v4), NULL, NULL, (__u32 *)&retval, NULL);
+	if (!ASSERT_OK(err, "bpf_prog_test_run"))
+		goto cleanup;
+	ASSERT_EQ(retval, 0, "retval");
+	ASSERT_EQ(skel->bss->out_bpf_testmod_ksym, 42, "bpf_testmod_ksym");
 cleanup:
 	test_ksyms_module__destroy(skel);
 }
+
+void test_ksyms_module(void)
+{
+	if (test__start_subtest("lskel"))
+		test_ksyms_module_lskel();
+	if (test__start_subtest("libbpf"))
+		test_ksyms_module_libbpf();
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/ksyms_module_libbpf.c b/tools/testing/selftests/bpf/prog_tests/ksyms_module_libbpf.c
deleted file mode 100644
index e6343ef63af9..000000000000
--- a/tools/testing/selftests/bpf/prog_tests/ksyms_module_libbpf.c
+++ /dev/null
@@ -1,28 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-
-#include <test_progs.h>
-#include <network_helpers.h>
-#include "test_ksyms_module.skel.h"
-
-void test_ksyms_module_libbpf(void)
-{
-	struct test_ksyms_module *skel;
-	int retval, err;
-
-	if (!env.has_testmod) {
-		test__skip();
-		return;
-	}
-
-	skel = test_ksyms_module__open_and_load();
-	if (!ASSERT_OK_PTR(skel, "test_ksyms_module__open"))
-		return;
-	err = bpf_prog_test_run(bpf_program__fd(skel->progs.load), 1, &pkt_v4,
-				sizeof(pkt_v4), NULL, NULL, (__u32 *)&retval, NULL);
-	if (!ASSERT_OK(err, "bpf_prog_test_run"))
-		goto cleanup;
-	ASSERT_EQ(retval, 0, "retval");
-	ASSERT_EQ(skel->bss->out_bpf_testmod_ksym, 42, "bpf_testmod_ksym");
-cleanup:
-	test_ksyms_module__destroy(skel);
-}
diff --git a/tools/testing/selftests/bpf/prog_tests/ringbuf.c b/tools/testing/selftests/bpf/prog_tests/ringbuf.c
index 4706cee84360..9a80fe8a6427 100644
--- a/tools/testing/selftests/bpf/prog_tests/ringbuf.c
+++ b/tools/testing/selftests/bpf/prog_tests/ringbuf.c
@@ -58,7 +58,7 @@ static int process_sample(void *ctx, void *data, size_t len)
 	}
 }
 
-static struct test_ringbuf *skel;
+static struct test_ringbuf_lskel *skel;
 static struct ring_buffer *ringbuf;
 
 static void trigger_samples()
@@ -90,13 +90,13 @@ void test_ringbuf(void)
 	int page_size = getpagesize();
 	void *mmap_ptr, *tmp_ptr;
 
-	skel = test_ringbuf__open();
+	skel = test_ringbuf_lskel__open();
 	if (CHECK(!skel, "skel_open", "skeleton open failed\n"))
 		return;
 
 	skel->maps.ringbuf.max_entries = page_size;
 
-	err = test_ringbuf__load(skel);
+	err = test_ringbuf_lskel__load(skel);
 	if (CHECK(err != 0, "skel_load", "skeleton load failed\n"))
 		goto cleanup;
 
@@ -154,7 +154,7 @@ void test_ringbuf(void)
 	if (CHECK(!ringbuf, "ringbuf_create", "failed to create ringbuf\n"))
 		goto cleanup;
 
-	err = test_ringbuf__attach(skel);
+	err = test_ringbuf_lskel__attach(skel);
 	if (CHECK(err, "skel_attach", "skeleton attachment failed: %d\n", err))
 		goto cleanup;
 
@@ -292,8 +292,8 @@ void test_ringbuf(void)
 	CHECK(skel->bss->discarded != 1, "err_discarded", "exp %ld, got %ld\n",
 	      1L, skel->bss->discarded);
 
-	test_ringbuf__detach(skel);
+	test_ringbuf_lskel__detach(skel);
 cleanup:
 	ring_buffer__free(ringbuf);
-	test_ringbuf__destroy(skel);
+	test_ringbuf_lskel__destroy(skel);
 }
diff --git a/tools/testing/selftests/bpf/prog_tests/trace_printk.c b/tools/testing/selftests/bpf/prog_tests/trace_printk.c
index 3f7a7141265e..cade7f12315f 100644
--- a/tools/testing/selftests/bpf/prog_tests/trace_printk.c
+++ b/tools/testing/selftests/bpf/prog_tests/trace_printk.c
@@ -10,27 +10,27 @@
 
 void serial_test_trace_printk(void)
 {
+	struct trace_printk_lskel__bss *bss;
 	int err = 0, iter = 0, found = 0;
-	struct trace_printk__bss *bss;
-	struct trace_printk *skel;
+	struct trace_printk_lskel *skel;
 	char *buf = NULL;
 	FILE *fp = NULL;
 	size_t buflen;
 
-	skel = trace_printk__open();
+	skel = trace_printk_lskel__open();
 	if (!ASSERT_OK_PTR(skel, "trace_printk__open"))
 		return;
 
 	ASSERT_EQ(skel->rodata->fmt[0], 'T', "skel->rodata->fmt[0]");
 	skel->rodata->fmt[0] = 't';
 
-	err = trace_printk__load(skel);
+	err = trace_printk_lskel__load(skel);
 	if (!ASSERT_OK(err, "trace_printk__load"))
 		goto cleanup;
 
 	bss = skel->bss;
 
-	err = trace_printk__attach(skel);
+	err = trace_printk_lskel__attach(skel);
 	if (!ASSERT_OK(err, "trace_printk__attach"))
 		goto cleanup;
 
@@ -43,7 +43,7 @@ void serial_test_trace_printk(void)
 
 	/* wait for tracepoint to trigger */
 	usleep(1);
-	trace_printk__detach(skel);
+	trace_printk_lskel__detach(skel);
 
 	if (!ASSERT_GT(bss->trace_printk_ran, 0, "bss->trace_printk_ran"))
 		goto cleanup;
@@ -65,7 +65,7 @@ void serial_test_trace_printk(void)
 		goto cleanup;
 
 cleanup:
-	trace_printk__destroy(skel);
+	trace_printk_lskel__destroy(skel);
 	free(buf);
 	if (fp)
 		fclose(fp);
diff --git a/tools/testing/selftests/bpf/prog_tests/trace_vprintk.c b/tools/testing/selftests/bpf/prog_tests/trace_vprintk.c
index 46101270cb1a..7a4e313e8558 100644
--- a/tools/testing/selftests/bpf/prog_tests/trace_vprintk.c
+++ b/tools/testing/selftests/bpf/prog_tests/trace_vprintk.c
@@ -10,20 +10,20 @@
 
 void serial_test_trace_vprintk(void)
 {
+	struct trace_vprintk_lskel__bss *bss;
 	int err = 0, iter = 0, found = 0;
-	struct trace_vprintk__bss *bss;
-	struct trace_vprintk *skel;
+	struct trace_vprintk_lskel *skel;
 	char *buf = NULL;
 	FILE *fp = NULL;
 	size_t buflen;
 
-	skel = trace_vprintk__open_and_load();
+	skel = trace_vprintk_lskel__open_and_load();
 	if (!ASSERT_OK_PTR(skel, "trace_vprintk__open_and_load"))
 		goto cleanup;
 
 	bss = skel->bss;
 
-	err = trace_vprintk__attach(skel);
+	err = trace_vprintk_lskel__attach(skel);
 	if (!ASSERT_OK(err, "trace_vprintk__attach"))
 		goto cleanup;
 
@@ -36,7 +36,7 @@ void serial_test_trace_vprintk(void)
 
 	/* wait for tracepoint to trigger */
 	usleep(1);
-	trace_vprintk__detach(skel);
+	trace_vprintk_lskel__detach(skel);
 
 	if (!ASSERT_GT(bss->trace_vprintk_ran, 0, "bss->trace_vprintk_ran"))
 		goto cleanup;
@@ -61,7 +61,7 @@ void serial_test_trace_vprintk(void)
 		goto cleanup;
 
 cleanup:
-	trace_vprintk__destroy(skel);
+	trace_vprintk_lskel__destroy(skel);
 	free(buf);
 	if (fp)
 		fclose(fp);
diff --git a/tools/testing/selftests/bpf/prog_tests/verif_stats.c b/tools/testing/selftests/bpf/prog_tests/verif_stats.c
index b4bae1340cf1..a47e7c0e1ffd 100644
--- a/tools/testing/selftests/bpf/prog_tests/verif_stats.c
+++ b/tools/testing/selftests/bpf/prog_tests/verif_stats.c
@@ -8,11 +8,11 @@
 void test_verif_stats(void)
 {
 	__u32 len = sizeof(struct bpf_prog_info);
+	struct trace_vprintk_lskel *skel;
 	struct bpf_prog_info info = {};
-	struct trace_vprintk *skel;
 	int err;
 
-	skel = trace_vprintk__open_and_load();
+	skel = trace_vprintk_lskel__open_and_load();
 	if (!ASSERT_OK_PTR(skel, "trace_vprintk__open_and_load"))
 		goto cleanup;
 
@@ -24,5 +24,5 @@ void test_verif_stats(void)
 		goto cleanup;
 
 cleanup:
-	trace_vprintk__destroy(skel);
+	trace_vprintk_lskel__destroy(skel);
 }
diff --git a/tools/testing/selftests/bpf/progs/test_ksyms_weak.c b/tools/testing/selftests/bpf/progs/test_ksyms_weak.c
index 5f8379aadb29..8eadbd4caf7a 100644
--- a/tools/testing/selftests/bpf/progs/test_ksyms_weak.c
+++ b/tools/testing/selftests/bpf/progs/test_ksyms_weak.c
@@ -38,7 +38,7 @@ int pass_handler(const void *ctx)
 	/* tests existing symbols. */
 	rq = (struct rq *)bpf_per_cpu_ptr(&runqueues, 0);
 	if (rq)
-		out__existing_typed = rq->cpu;
+		out__existing_typed = 0;
 	out__existing_typeless = (__u64)&bpf_prog_active;
 
 	/* tests non-existent symbols. */
-- 
cgit v1.2.3


From c3fc706e94f5653def2783ffcd809a38676b7551 Mon Sep 17 00:00:00 2001
From: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Date: Thu, 28 Oct 2021 12:05:00 +0530
Subject: selftests/bpf: Fix fd cleanup in sk_lookup test

Similar to the fix in commit:
e31eec77e4ab ("bpf: selftests: Fix fd cleanup in get_branch_snapshot")

We use designated initializer to set fds to -1 without breaking on
future changes to MAX_SERVER constant denoting the array size.

The particular close(0) occurs on non-reuseport tests, so it can be seen
with -n 115/{2,3} but not 115/4. This can cause problems with future
tests if they depend on BTF fd never being acquired as fd 0, breaking
internal libbpf assumptions.

Fixes: 0ab5539f8584 ("selftests/bpf: Tests for BPF_SK_LOOKUP attach point")
Signed-off-by: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Reviewed-by: Jakub Sitnicki <jakub@cloudflare.com>
Acked-by: Song Liu <songliubraving@fb.com>
Link: https://lore.kernel.org/bpf/20211028063501.2239335-8-memxor@gmail.com
---
 tools/testing/selftests/bpf/prog_tests/sk_lookup.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/prog_tests/sk_lookup.c b/tools/testing/selftests/bpf/prog_tests/sk_lookup.c
index aee41547e7f4..6db07401bc49 100644
--- a/tools/testing/selftests/bpf/prog_tests/sk_lookup.c
+++ b/tools/testing/selftests/bpf/prog_tests/sk_lookup.c
@@ -598,7 +598,7 @@ close:
 
 static void run_lookup_prog(const struct test *t)
 {
-	int server_fds[MAX_SERVERS] = { -1 };
+	int server_fds[] = { [0 ... MAX_SERVERS - 1] = -1 };
 	int client_fd, reuse_conn_fd = -1;
 	struct bpf_link *lookup_link;
 	int i, err;
@@ -1053,7 +1053,7 @@ static void run_sk_assign(struct test_sk_lookup *skel,
 			  struct bpf_program *lookup_prog,
 			  const char *remote_ip, const char *local_ip)
 {
-	int server_fds[MAX_SERVERS] = { -1 };
+	int server_fds[] = { [0 ... MAX_SERVERS - 1] = -1 };
 	struct bpf_sk_lookup ctx;
 	__u64 server_cookie;
 	int i, err;
-- 
cgit v1.2.3


From efadf2ad17a2d5dc90bda4e6e8b2f96af4c62dae Mon Sep 17 00:00:00 2001
From: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Date: Thu, 28 Oct 2021 12:05:01 +0530
Subject: selftests/bpf: Fix memory leak in test_ima

The allocated ring buffer is never freed, do so in the cleanup path.

Fixes: f446b570ac7e ("bpf/selftests: Update the IMA test to use BPF ring buffer")
Signed-off-by: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Andrii Nakryiko <andrii@kernel.org>
Acked-by: Song Liu <songliubraving@fb.com>
Link: https://lore.kernel.org/bpf/20211028063501.2239335-9-memxor@gmail.com
---
 tools/testing/selftests/bpf/prog_tests/test_ima.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/prog_tests/test_ima.c b/tools/testing/selftests/bpf/prog_tests/test_ima.c
index 0252f61d611a..97d8a6f84f4a 100644
--- a/tools/testing/selftests/bpf/prog_tests/test_ima.c
+++ b/tools/testing/selftests/bpf/prog_tests/test_ima.c
@@ -43,7 +43,7 @@ static int process_sample(void *ctx, void *data, size_t len)
 void test_test_ima(void)
 {
 	char measured_dir_template[] = "/tmp/ima_measuredXXXXXX";
-	struct ring_buffer *ringbuf;
+	struct ring_buffer *ringbuf = NULL;
 	const char *measured_dir;
 	char cmd[256];
 
@@ -85,5 +85,6 @@ close_clean:
 	err = system(cmd);
 	CHECK(err, "failed to run command", "%s, errno = %d\n", cmd, errno);
 close_prog:
+	ring_buffer__free(ringbuf);
 	ima__destroy(skel);
 }
-- 
cgit v1.2.3


From 3d5290ea1daeee5da2e46abda730351c2e5b1faa Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@nvidia.com>
Date: Wed, 27 Oct 2021 18:20:00 +0300
Subject: selftests: mlxsw: Test offloadability of root TBF

TBF can be used as a root qdisc, with the usual ETS/RED/TBF hierarchy below
it. This use should now be offloaded. Add a test that verifies that it is.

Signed-off-by: Petr Machata <petrm@nvidia.com>
Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/drivers/net/mlxsw/sch_offload.sh | 14 ++++++++++++++
 1 file changed, 14 insertions(+)

(limited to 'tools')

diff --git a/tools/testing/selftests/drivers/net/mlxsw/sch_offload.sh b/tools/testing/selftests/drivers/net/mlxsw/sch_offload.sh
index ade79ef08de3..071a33d10c20 100755
--- a/tools/testing/selftests/drivers/net/mlxsw/sch_offload.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/sch_offload.sh
@@ -6,7 +6,9 @@
 
 ALL_TESTS="
 	test_root
+	test_port_tbf
 	test_etsprio
+	test_etsprio_port_tbf
 "
 NUM_NETIFS=1
 lib_dir=$(dirname $0)/../../../net/forwarding
@@ -221,6 +223,12 @@ test_root()
 	do_test_combinations 1 0
 }
 
+test_port_tbf()
+{
+	with_tbf 1: root \
+		do_test_combinations 8 1
+}
+
 do_test_etsprio()
 {
 	local parent=$1; shift
@@ -264,6 +272,12 @@ test_etsprio()
 	do_test_etsprio root ""
 }
 
+test_etsprio_port_tbf()
+{
+	with_tbf 1: root \
+		do_test_etsprio "parent 1:1" "-TBF"
+}
+
 cleanup()
 {
 	tc qdisc del dev $h1 root &>/dev/null
-- 
cgit v1.2.3


From 2b11e24ebaef77e7151ddcc1762429798b9f75d5 Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@nvidia.com>
Date: Wed, 27 Oct 2021 18:20:01 +0300
Subject: selftests: mlxsw: Test port shaper

TBF can be used as a root qdisc, in which case it is supposed to configure
port shaper. Add a test that verifies that this is so by installing a root
TBF with a ETS or PRIO below it, and then expecting individual bands to all
be shaped according to the root TBF configuration.

Signed-off-by: Petr Machata <petrm@nvidia.com>
Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../selftests/net/forwarding/sch_tbf_etsprio.sh    | 28 ++++++++++++++++++++++
 1 file changed, 28 insertions(+)

(limited to 'tools')

diff --git a/tools/testing/selftests/net/forwarding/sch_tbf_etsprio.sh b/tools/testing/selftests/net/forwarding/sch_tbf_etsprio.sh
index 8bd85da1905a..75a37c189ef3 100644
--- a/tools/testing/selftests/net/forwarding/sch_tbf_etsprio.sh
+++ b/tools/testing/selftests/net/forwarding/sch_tbf_etsprio.sh
@@ -4,9 +4,12 @@
 ALL_TESTS="
 	ping_ipv4
 	tbf_test
+	tbf_root_test
 "
 source $lib_dir/sch_tbf_core.sh
 
+QDISC_TYPE=${QDISC% *}
+
 tbf_test_one()
 {
 	local bs=$1; shift
@@ -22,6 +25,8 @@ tbf_test_one()
 
 tbf_test()
 {
+	log_info "Testing root-$QDISC_TYPE-tbf"
+
 	# This test is used for both ETS and PRIO. Even though we only need two
 	# bands, PRIO demands a minimum of three.
 	tc qdisc add dev $swp2 root handle 10: $QDISC 3 priomap 2 1 0
@@ -29,6 +34,29 @@ tbf_test()
 	tc qdisc del dev $swp2 root
 }
 
+tbf_root_test()
+{
+	local bs=128K
+
+	log_info "Testing root-tbf-$QDISC_TYPE"
+
+	tc qdisc replace dev $swp2 root handle 1: \
+		tbf rate 400Mbit burst $bs limit 1M
+	tc qdisc replace dev $swp2 parent 1:1 handle 10: \
+		$QDISC 3 priomap 2 1 0
+	tc qdisc replace dev $swp2 parent 10:3 handle 103: \
+		bfifo limit 1M
+	tc qdisc replace dev $swp2 parent 10:2 handle 102: \
+		bfifo limit 1M
+	tc qdisc replace dev $swp2 parent 10:1 handle 101: \
+		bfifo limit 1M
+
+	do_tbf_test 10 400 $bs
+	do_tbf_test 11 400 $bs
+
+	tc qdisc del dev $swp2 root
+}
+
 trap cleanup EXIT
 
 setup_prepare
-- 
cgit v1.2.3


From e300a85db1f16a5805033feb56ec1861f02c7b1c Mon Sep 17 00:00:00 2001
From: Shuah Khan <skhan@linuxfoundation.org>
Date: Wed, 27 Oct 2021 14:28:46 -0600
Subject: selftests/net: update .gitignore with newly added tests

Update .gitignore with newly added tests:
	tools/testing/selftests/net/af_unix/test_unix_oob
	tools/testing/selftests/net/gro
	tools/testing/selftests/net/ioam6_parser
	tools/testing/selftests/net/toeplitz

Signed-off-by: Shuah Khan <skhan@linuxfoundation.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/.gitignore | 4 ++++
 1 file changed, 4 insertions(+)

(limited to 'tools')

diff --git a/tools/testing/selftests/net/.gitignore b/tools/testing/selftests/net/.gitignore
index 19deb9cdf72f..501550501216 100644
--- a/tools/testing/selftests/net/.gitignore
+++ b/tools/testing/selftests/net/.gitignore
@@ -31,3 +31,7 @@ rxtimestamp
 timestamping
 txtimestamp
 so_netns_cookie
+test_unix_oob
+gro
+ioam6_parser
+toeplitz
-- 
cgit v1.2.3


From 34d7ecb3d4f772eb00ce1f7195ae30886ddf4d2e Mon Sep 17 00:00:00 2001
From: Nikolay Aleksandrov <nikolay@nvidia.com>
Date: Fri, 29 Oct 2021 15:05:27 +0300
Subject: selftests: net: bridge: update IGMP/MLD membership interval value

When I fixed IGMPv3/MLDv2 to use the bridge's multicast_membership_interval
value which is chosen by user-space instead of calculating it based on
multicast_query_interval and multicast_query_response_interval I forgot
to update the selftests relying on that behaviour. Now we have to
manually set the expected GMI value to perform the tests correctly and get
proper results (similar to IGMPv2 behaviour).

Fixes: fac3cb82a54a ("net: bridge: mcast: use multicast_membership_interval for IGMPv3")
Signed-off-by: Nikolay Aleksandrov <nikolay@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/forwarding/bridge_igmp.sh | 12 +++++++++---
 tools/testing/selftests/net/forwarding/bridge_mld.sh  | 12 +++++++++---
 2 files changed, 18 insertions(+), 6 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/net/forwarding/bridge_igmp.sh b/tools/testing/selftests/net/forwarding/bridge_igmp.sh
index 675eff45b037..1162836f8f32 100755
--- a/tools/testing/selftests/net/forwarding/bridge_igmp.sh
+++ b/tools/testing/selftests/net/forwarding/bridge_igmp.sh
@@ -482,10 +482,15 @@ v3exc_timeout_test()
 	local X=("192.0.2.20" "192.0.2.30")
 
 	# GMI should be 3 seconds
-	ip link set dev br0 type bridge mcast_query_interval 100 mcast_query_response_interval 100
+	ip link set dev br0 type bridge mcast_query_interval 100 \
+					mcast_query_response_interval 100 \
+					mcast_membership_interval 300
 
 	v3exclude_prepare $h1 $ALL_MAC $ALL_GROUP
-	ip link set dev br0 type bridge mcast_query_interval 500 mcast_query_response_interval 500
+	ip link set dev br0 type bridge mcast_query_interval 500 \
+					mcast_query_response_interval 500 \
+					mcast_membership_interval 1500
+
 	$MZ $h1 -c 1 -b $ALL_MAC -B $ALL_GROUP -t ip "proto=2,p=$MZPKT_ALLOW2" -q
 	sleep 3
 	bridge -j -d -s mdb show dev br0 \
@@ -517,7 +522,8 @@ v3exc_timeout_test()
 	log_test "IGMPv3 group $TEST_GROUP exclude timeout"
 
 	ip link set dev br0 type bridge mcast_query_interval 12500 \
-					mcast_query_response_interval 1000
+					mcast_query_response_interval 1000 \
+					mcast_membership_interval 26000
 
 	v3cleanup $swp1 $TEST_GROUP
 }
diff --git a/tools/testing/selftests/net/forwarding/bridge_mld.sh b/tools/testing/selftests/net/forwarding/bridge_mld.sh
index ffdcfa87ca2b..e2b9ff773c6b 100755
--- a/tools/testing/selftests/net/forwarding/bridge_mld.sh
+++ b/tools/testing/selftests/net/forwarding/bridge_mld.sh
@@ -479,10 +479,15 @@ mldv2exc_timeout_test()
 	local X=("2001:db8:1::20" "2001:db8:1::30")
 
 	# GMI should be 3 seconds
-	ip link set dev br0 type bridge mcast_query_interval 100 mcast_query_response_interval 100
+	ip link set dev br0 type bridge mcast_query_interval 100 \
+					mcast_query_response_interval 100 \
+					mcast_membership_interval 300
 
 	mldv2exclude_prepare $h1
-	ip link set dev br0 type bridge mcast_query_interval 500 mcast_query_response_interval 500
+	ip link set dev br0 type bridge mcast_query_interval 500 \
+					mcast_query_response_interval 500 \
+					mcast_membership_interval 1500
+
 	$MZ $h1 -c 1 $MZPKT_ALLOW2 -q
 	sleep 3
 	bridge -j -d -s mdb show dev br0 \
@@ -514,7 +519,8 @@ mldv2exc_timeout_test()
 	log_test "MLDv2 group $TEST_GROUP exclude timeout"
 
 	ip link set dev br0 type bridge mcast_query_interval 12500 \
-					mcast_query_response_interval 1000
+					mcast_query_response_interval 1000 \
+					mcast_membership_interval 26000
 
 	mldv2cleanup $swp1
 }
-- 
cgit v1.2.3


From f48ad69097fe79d1de13c4d8fef556d4c11c5e68 Mon Sep 17 00:00:00 2001
From: Andrea Righi <andrea.righi@canonical.com>
Date: Tue, 26 Oct 2021 16:34:09 +0200
Subject: selftests/bpf: Fix fclose/pclose mismatch in test_progs

Make sure to use pclose() to properly close the pipe opened by popen().

Fixes: 81f77fd0deeb ("bpf: add selftest for stackmap with BPF_F_STACK_BUILD_ID")
Signed-off-by: Andrea Righi <andrea.righi@canonical.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Shuah Khan <skhan@linuxfoundation.org>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Link: https://lore.kernel.org/bpf/20211026143409.42666-1-andrea.righi@canonical.com
---
 tools/testing/selftests/bpf/test_progs.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/test_progs.c b/tools/testing/selftests/bpf/test_progs.c
index 1f4a48566991..c65986bd9d07 100644
--- a/tools/testing/selftests/bpf/test_progs.c
+++ b/tools/testing/selftests/bpf/test_progs.c
@@ -382,7 +382,7 @@ int extract_build_id(char *build_id, size_t size)
 
 	if (getline(&line, &len, fp) == -1)
 		goto err;
-	fclose(fp);
+	pclose(fp);
 
 	if (len > size)
 		len = size;
@@ -391,7 +391,7 @@ int extract_build_id(char *build_id, size_t size)
 	free(line);
 	return 0;
 err:
-	fclose(fp);
+	pclose(fp);
 	return -1;
 }
 
-- 
cgit v1.2.3


From b0ced8f290fb7bb03d23c4c3c3355e92a4be6e95 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Fri, 29 Oct 2021 08:51:35 -0700
Subject: selftests: udp: test for passing SO_MARK as cmsg

Before fix:
|  Case IPv6 rejection returned 0, expected 1
|FAIL - 1/4 cases failed

With the fix:
| OK

Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Reviewed-by: David Ahern <dsahern@kernel.org>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/.gitignore      |  1 +
 tools/testing/selftests/net/Makefile        |  2 +
 tools/testing/selftests/net/cmsg_so_mark.c  | 67 +++++++++++++++++++++++++++++
 tools/testing/selftests/net/cmsg_so_mark.sh | 61 ++++++++++++++++++++++++++
 4 files changed, 131 insertions(+)
 create mode 100644 tools/testing/selftests/net/cmsg_so_mark.c
 create mode 100755 tools/testing/selftests/net/cmsg_so_mark.sh

(limited to 'tools')

diff --git a/tools/testing/selftests/net/.gitignore b/tools/testing/selftests/net/.gitignore
index 501550501216..7581a7348e1b 100644
--- a/tools/testing/selftests/net/.gitignore
+++ b/tools/testing/selftests/net/.gitignore
@@ -35,3 +35,4 @@ test_unix_oob
 gro
 ioam6_parser
 toeplitz
+cmsg_so_mark
diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile
index 492b273743b4..f56b652d5cc6 100644
--- a/tools/testing/selftests/net/Makefile
+++ b/tools/testing/selftests/net/Makefile
@@ -28,6 +28,7 @@ TEST_PROGS += veth.sh
 TEST_PROGS += ioam6.sh
 TEST_PROGS += gro.sh
 TEST_PROGS += gre_gso.sh
+TEST_PROGS += cmsg_so_mark.sh
 TEST_PROGS_EXTENDED := in_netns.sh
 TEST_GEN_FILES =  socket nettest
 TEST_GEN_FILES += psock_fanout psock_tpacket msg_zerocopy reuseport_addr_any
@@ -44,6 +45,7 @@ TEST_GEN_FILES += gro
 TEST_GEN_PROGS = reuseport_bpf reuseport_bpf_cpu reuseport_bpf_numa
 TEST_GEN_PROGS += reuseport_dualstack reuseaddr_conflict tls
 TEST_GEN_FILES += toeplitz
+TEST_GEN_FILES += cmsg_so_mark
 
 TEST_FILES := settings
 
diff --git a/tools/testing/selftests/net/cmsg_so_mark.c b/tools/testing/selftests/net/cmsg_so_mark.c
new file mode 100644
index 000000000000..27f2804892a7
--- /dev/null
+++ b/tools/testing/selftests/net/cmsg_so_mark.c
@@ -0,0 +1,67 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+#include <errno.h>
+#include <netdb.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <unistd.h>
+#include <linux/types.h>
+#include <sys/socket.h>
+
+int main(int argc, const char **argv)
+{
+	char cbuf[CMSG_SPACE(sizeof(__u32))];
+	struct addrinfo hints, *ai;
+	struct cmsghdr *cmsg;
+	struct iovec iov[1];
+	struct msghdr msg;
+	int mark;
+	int err;
+	int fd;
+
+	if (argc != 4) {
+		fprintf(stderr, "Usage: %s <dst_ip> <port> <mark>\n", argv[0]);
+		return 1;
+	}
+	mark = atoi(argv[3]);
+
+	memset(&hints, 0, sizeof(hints));
+	hints.ai_family = AF_UNSPEC;
+	hints.ai_socktype = SOCK_DGRAM;
+
+	ai = NULL;
+	err = getaddrinfo(argv[1], argv[2], &hints, &ai);
+	if (err) {
+		fprintf(stderr, "Can't resolve address: %s\n", strerror(errno));
+		return 1;
+	}
+
+	fd = socket(ai->ai_family, SOCK_DGRAM, IPPROTO_UDP);
+	if (fd < 0) {
+		fprintf(stderr, "Can't open socket: %s\n", strerror(errno));
+		freeaddrinfo(ai);
+		return 1;
+	}
+
+	iov[0].iov_base = "bla";
+	iov[0].iov_len = 4;
+
+	msg.msg_name = ai->ai_addr;
+	msg.msg_namelen = ai->ai_addrlen;
+	msg.msg_iov = iov;
+	msg.msg_iovlen = 1;
+	msg.msg_control = cbuf;
+	msg.msg_controllen = sizeof(cbuf);
+
+	cmsg = CMSG_FIRSTHDR(&msg);
+	cmsg->cmsg_level = SOL_SOCKET;
+	cmsg->cmsg_type = SO_MARK;
+	cmsg->cmsg_len = CMSG_LEN(sizeof(__u32));
+	*(__u32 *)CMSG_DATA(cmsg) = mark;
+
+	err = sendmsg(fd, &msg, 0);
+
+	close(fd);
+	freeaddrinfo(ai);
+	return err != 4;
+}
diff --git a/tools/testing/selftests/net/cmsg_so_mark.sh b/tools/testing/selftests/net/cmsg_so_mark.sh
new file mode 100755
index 000000000000..19c6aab8d0e9
--- /dev/null
+++ b/tools/testing/selftests/net/cmsg_so_mark.sh
@@ -0,0 +1,61 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+NS=ns
+IP4=172.16.0.1/24
+TGT4=172.16.0.2
+IP6=2001:db8:1::1/64
+TGT6=2001:db8:1::2
+MARK=1000
+
+cleanup()
+{
+    ip netns del $NS
+}
+
+trap cleanup EXIT
+
+# Namespaces
+ip netns add $NS
+
+# Connectivity
+ip -netns $NS link add type dummy
+ip -netns $NS link set dev dummy0 up
+ip -netns $NS addr add $IP4 dev dummy0
+ip -netns $NS addr add $IP6 dev dummy0
+
+ip -netns $NS rule add fwmark $MARK lookup 300
+ip -6 -netns $NS rule add fwmark $MARK lookup 300
+ip -netns $NS route add prohibit any table 300
+ip -6 -netns $NS route add prohibit any table 300
+
+# Test
+BAD=0
+TOTAL=0
+
+check_result() {
+    ((TOTAL++))
+    if [ $1 -ne $2 ]; then
+	echo "  Case $3 returned $1, expected $2"
+	((BAD++))
+    fi
+}
+
+ip netns exec $NS ./cmsg_so_mark $TGT4 1234 $((MARK + 1))
+check_result $? 0 "IPv4 pass"
+ip netns exec $NS ./cmsg_so_mark $TGT6 1234 $((MARK + 1))
+check_result $? 0 "IPv6 pass"
+
+ip netns exec $NS ./cmsg_so_mark $TGT4 1234 $MARK
+check_result $? 1 "IPv4 rejection"
+ip netns exec $NS ./cmsg_so_mark $TGT6 1234 $MARK
+check_result $? 1 "IPv6 rejection"
+
+# Summary
+if [ $BAD -ne 0 ]; then
+    echo "FAIL - $BAD/$TOTAL cases failed"
+    exit 1
+else
+    echo "OK"
+    exit 0
+fi
-- 
cgit v1.2.3


From 7c909a98042ce403c8497c5d6ff94dd53bdd2131 Mon Sep 17 00:00:00 2001
From: Geliang Tang <geliang.tang@suse.com>
Date: Fri, 29 Oct 2021 16:55:58 -0700
Subject: selftests: mptcp: fix proto type in link_failure tests

In listener_ns, we should pass srv_proto argument to mptcp_connect command,
not cl_proto.

Fixes: 7d1e6f1639044 ("selftests: mptcp: add testcase for active-back")
Signed-off-by: Geliang Tang <geliang.tang@suse.com>
Signed-off-by: Matthieu Baerts <matthieu.baerts@tessares.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/mptcp/mptcp_join.sh | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh
index 293d349e21fe..7ef639a9d4a6 100755
--- a/tools/testing/selftests/net/mptcp/mptcp_join.sh
+++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh
@@ -297,7 +297,7 @@ do_transfer()
 	if [ "$test_link_fail" -eq 2 ];then
 		timeout ${timeout_test} \
 			ip netns exec ${listener_ns} \
-				$mptcp_connect -t ${timeout_poll} -l -p $port -s ${cl_proto} \
+				$mptcp_connect -t ${timeout_poll} -l -p $port -s ${srv_proto} \
 					${local_addr} < "$sinfail" > "$sout" &
 	else
 		timeout ${timeout_test} \
-- 
cgit v1.2.3


From b6ab64b074f29b42ff272793806efc913f7cc742 Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Fri, 29 Oct 2021 16:55:59 -0700
Subject: selftests: mptcp: more stable simult_flows tests

Currently the simult_flows.sh self-tests are not very stable,
especially when running on slow VMs.

The tests measure runtime for transfers on multiple subflows
and check that the time is near the theoretical maximum.

The current test infra introduces a bit of jitter in test
runtime, due to multiple explicit delays. Additionally the
runtime is measured by the shell script wrapper. On a slow
VM, the script overhead is measurable and subject to relevant
jitter.

One solution to make the test more stable would be adding more
slack to the expected time; that could possibly hide real
regressions. Instead move the measurement inside the command
doing the transfer, and drop most unneeded sleeps.

Reviewed-by: Matthieu Baerts <matthieu.baerts@tessares.net>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: Mat Martineau <mathew.j.martineau@linux.intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/mptcp/mptcp_connect.c | 72 ++++++++++++++++++-----
 tools/testing/selftests/net/mptcp/simult_flows.sh | 36 +++++-------
 2 files changed, 72 insertions(+), 36 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/net/mptcp/mptcp_connect.c b/tools/testing/selftests/net/mptcp/mptcp_connect.c
index 89c4753c2760..95e81d557b08 100644
--- a/tools/testing/selftests/net/mptcp/mptcp_connect.c
+++ b/tools/testing/selftests/net/mptcp/mptcp_connect.c
@@ -14,6 +14,7 @@
 #include <strings.h>
 #include <signal.h>
 #include <unistd.h>
+#include <time.h>
 
 #include <sys/poll.h>
 #include <sys/sendfile.h>
@@ -64,6 +65,7 @@ static int cfg_sndbuf;
 static int cfg_rcvbuf;
 static bool cfg_join;
 static bool cfg_remove;
+static unsigned int cfg_time;
 static unsigned int cfg_do_w;
 static int cfg_wait;
 static uint32_t cfg_mark;
@@ -78,9 +80,10 @@ static struct cfg_cmsg_types cfg_cmsg_types;
 static void die_usage(void)
 {
 	fprintf(stderr, "Usage: mptcp_connect [-6] [-u] [-s MPTCP|TCP] [-p port] [-m mode]"
-		"[-l] [-w sec] connect_address\n");
+		"[-l] [-w sec] [-t num] [-T num] connect_address\n");
 	fprintf(stderr, "\t-6 use ipv6\n");
 	fprintf(stderr, "\t-t num -- set poll timeout to num\n");
+	fprintf(stderr, "\t-T num -- set expected runtime to num ms\n");
 	fprintf(stderr, "\t-S num -- set SO_SNDBUF to num\n");
 	fprintf(stderr, "\t-R num -- set SO_RCVBUF to num\n");
 	fprintf(stderr, "\t-p num -- use port num\n");
@@ -448,7 +451,7 @@ static void set_nonblock(int fd)
 	fcntl(fd, F_SETFL, flags | O_NONBLOCK);
 }
 
-static int copyfd_io_poll(int infd, int peerfd, int outfd)
+static int copyfd_io_poll(int infd, int peerfd, int outfd, bool *in_closed_after_out)
 {
 	struct pollfd fds = {
 		.fd = peerfd,
@@ -487,9 +490,11 @@ static int copyfd_io_poll(int infd, int peerfd, int outfd)
 				 */
 				fds.events &= ~POLLIN;
 
-				if ((fds.events & POLLOUT) == 0)
+				if ((fds.events & POLLOUT) == 0) {
+					*in_closed_after_out = true;
 					/* and nothing more to send */
 					break;
+				}
 
 			/* Else, still have data to transmit */
 			} else if (len < 0) {
@@ -547,7 +552,7 @@ static int copyfd_io_poll(int infd, int peerfd, int outfd)
 	}
 
 	/* leave some time for late join/announce */
-	if (cfg_join || cfg_remove)
+	if (cfg_remove)
 		usleep(cfg_wait);
 
 	close(peerfd);
@@ -646,7 +651,7 @@ static int do_sendfile(int infd, int outfd, unsigned int count)
 }
 
 static int copyfd_io_mmap(int infd, int peerfd, int outfd,
-			  unsigned int size)
+			  unsigned int size, bool *in_closed_after_out)
 {
 	int err;
 
@@ -664,13 +669,14 @@ static int copyfd_io_mmap(int infd, int peerfd, int outfd,
 		shutdown(peerfd, SHUT_WR);
 
 		err = do_recvfile(peerfd, outfd);
+		*in_closed_after_out = true;
 	}
 
 	return err;
 }
 
 static int copyfd_io_sendfile(int infd, int peerfd, int outfd,
-			      unsigned int size)
+			      unsigned int size, bool *in_closed_after_out)
 {
 	int err;
 
@@ -685,6 +691,7 @@ static int copyfd_io_sendfile(int infd, int peerfd, int outfd,
 		if (err)
 			return err;
 		err = do_recvfile(peerfd, outfd);
+		*in_closed_after_out = true;
 	}
 
 	return err;
@@ -692,27 +699,62 @@ static int copyfd_io_sendfile(int infd, int peerfd, int outfd,
 
 static int copyfd_io(int infd, int peerfd, int outfd)
 {
+	bool in_closed_after_out = false;
+	struct timespec start, end;
 	int file_size;
+	int ret;
+
+	if (cfg_time && (clock_gettime(CLOCK_MONOTONIC, &start) < 0))
+		xerror("can not fetch start time %d", errno);
 
 	switch (cfg_mode) {
 	case CFG_MODE_POLL:
-		return copyfd_io_poll(infd, peerfd, outfd);
+		ret = copyfd_io_poll(infd, peerfd, outfd, &in_closed_after_out);
+		break;
+
 	case CFG_MODE_MMAP:
 		file_size = get_infd_size(infd);
 		if (file_size < 0)
 			return file_size;
-		return copyfd_io_mmap(infd, peerfd, outfd, file_size);
+		ret = copyfd_io_mmap(infd, peerfd, outfd, file_size, &in_closed_after_out);
+		break;
+
 	case CFG_MODE_SENDFILE:
 		file_size = get_infd_size(infd);
 		if (file_size < 0)
 			return file_size;
-		return copyfd_io_sendfile(infd, peerfd, outfd, file_size);
+		ret = copyfd_io_sendfile(infd, peerfd, outfd, file_size, &in_closed_after_out);
+		break;
+
+	default:
+		fprintf(stderr, "Invalid mode %d\n", cfg_mode);
+
+		die_usage();
+		return 1;
 	}
 
-	fprintf(stderr, "Invalid mode %d\n", cfg_mode);
+	if (ret)
+		return ret;
 
-	die_usage();
-	return 1;
+	if (cfg_time) {
+		unsigned int delta_ms;
+
+		if (clock_gettime(CLOCK_MONOTONIC, &end) < 0)
+			xerror("can not fetch end time %d", errno);
+		delta_ms = (end.tv_sec - start.tv_sec) * 1000 + (end.tv_nsec - start.tv_nsec) / 1000000;
+		if (delta_ms > cfg_time) {
+			xerror("transfer slower than expected! runtime %d ms, expected %d ms",
+			       delta_ms, cfg_time);
+		}
+
+		/* show the runtime only if this end shutdown(wr) before receiving the EOF,
+		 * (that is, if this end got the longer runtime)
+		 */
+		if (in_closed_after_out)
+			fprintf(stderr, "%d", delta_ms);
+	}
+
+	return 0;
 }
 
 static void check_sockaddr(int pf, struct sockaddr_storage *ss,
@@ -1005,12 +1047,11 @@ static void parse_opts(int argc, char **argv)
 {
 	int c;
 
-	while ((c = getopt(argc, argv, "6jr:lp:s:hut:m:S:R:w:M:P:c:")) != -1) {
+	while ((c = getopt(argc, argv, "6jr:lp:s:hut:T:m:S:R:w:M:P:c:")) != -1) {
 		switch (c) {
 		case 'j':
 			cfg_join = true;
 			cfg_mode = CFG_MODE_POLL;
-			cfg_wait = 400000;
 			break;
 		case 'r':
 			cfg_remove = true;
@@ -1043,6 +1084,9 @@ static void parse_opts(int argc, char **argv)
 			if (poll_timeout <= 0)
 				poll_timeout = -1;
 			break;
+		case 'T':
+			cfg_time = atoi(optarg);
+			break;
 		case 'm':
 			cfg_mode = parse_mode(optarg);
 			break;
diff --git a/tools/testing/selftests/net/mptcp/simult_flows.sh b/tools/testing/selftests/net/mptcp/simult_flows.sh
index 910d8126af8f..f441ff7904fc 100755
--- a/tools/testing/selftests/net/mptcp/simult_flows.sh
+++ b/tools/testing/selftests/net/mptcp/simult_flows.sh
@@ -51,7 +51,7 @@ setup()
 	sout=$(mktemp)
 	cout=$(mktemp)
 	capout=$(mktemp)
-	size=$((2048 * 4096))
+	size=$((2 * 2048 * 4096))
 	dd if=/dev/zero of=$small bs=4096 count=20 >/dev/null 2>&1
 	dd if=/dev/zero of=$large bs=4096 count=$((size / 4096)) >/dev/null 2>&1
 
@@ -161,17 +161,15 @@ do_transfer()
 
 	timeout ${timeout_test} \
 		ip netns exec ${ns3} \
-			./mptcp_connect -jt ${timeout_poll} -l -p $port \
+			./mptcp_connect -jt ${timeout_poll} -l -p $port -T $time \
 				0.0.0.0 < "$sin" > "$sout" &
 	local spid=$!
 
 	wait_local_port_listen "${ns3}" "${port}"
 
-	local start
-	start=$(date +%s%3N)
 	timeout ${timeout_test} \
 		ip netns exec ${ns1} \
-			./mptcp_connect -jt ${timeout_poll} -p $port \
+			./mptcp_connect -jt ${timeout_poll} -p $port -T $time \
 				10.0.3.3 < "$cin" > "$cout" &
 	local cpid=$!
 
@@ -180,27 +178,20 @@ do_transfer()
 	wait $spid
 	local rets=$?
 
-	local stop
-	stop=$(date +%s%3N)
-
 	if $capture; then
 		sleep 1
 		kill ${cappid_listener}
 		kill ${cappid_connector}
 	fi
 
-	local duration
-	duration=$((stop-start))
-
 	cmp $sin $cout > /dev/null 2>&1
 	local cmps=$?
 	cmp $cin $sout > /dev/null 2>&1
 	local cmpc=$?
 
-	printf "%16s" "$duration max $max_time "
+	printf "%-16s" " max $max_time "
 	if [ $retc -eq 0 ] && [ $rets -eq 0 ] && \
-	   [ $cmpc -eq 0 ] && [ $cmps -eq 0 ] && \
-	   [ $duration -lt $max_time ]; then
+	   [ $cmpc -eq 0 ] && [ $cmps -eq 0 ]; then
 		echo "[ OK ]"
 		cat "$capout"
 		return 0
@@ -244,23 +235,24 @@ run_test()
 	tc -n $ns2 qdisc add dev ns2eth1 root netem rate ${rate1}mbit $delay1
 	tc -n $ns2 qdisc add dev ns2eth2 root netem rate ${rate2}mbit $delay2
 
-	# time is measure in ms
-	local time=$((size * 8 * 1000 / (( $rate1 + $rate2) * 1024 *1024) ))
+	# time is measured in ms, account for transfer size, affegated link speed
+	# and header overhead (10%)
+	local time=$((size * 8 * 1000 * 10 / (( $rate1 + $rate2) * 1024 *1024 * 9) ))
 
 	# mptcp_connect will do some sleeps to allow the mp_join handshake
-	# completion
-	time=$((time + 1350))
+	# completion (see mptcp_connect): 200ms on each side, add some slack
+	time=$((time + 450))
 
-	printf "%-50s" "$msg"
-	do_transfer $small $large $((time * 11 / 10))
+	printf "%-60s" "$msg"
+	do_transfer $small $large $time
 	lret=$?
 	if [ $lret -ne 0 ]; then
 		ret=$lret
 		[ $bail -eq 0 ] || exit $ret
 	fi
 
-	printf "%-50s" "$msg - reverse direction"
-	do_transfer $large $small $((time * 11 / 10))
+	printf "%-60s" "$msg - reverse direction"
+	do_transfer $large $small $time
 	lret=$?
 	if [ $lret -ne 0 ]; then
 		ret=$lret
-- 
cgit v1.2.3


From c08e8baea78e472383d6b295bb8db2132068c358 Mon Sep 17 00:00:00 2001
From: Taehee Yoo <ap420073@gmail.com>
Date: Sun, 31 Oct 2021 16:00:06 +0000
Subject: selftests: add amt interface selftest script

This is selftest script for amt interface.
This script includes basic forwarding scenarion and torture scenario.

Signed-off-by: Taehee Yoo <ap420073@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/Makefile |   1 +
 tools/testing/selftests/net/amt.sh   | 284 +++++++++++++++++++++++++++++++++++
 tools/testing/selftests/net/config   |   1 +
 3 files changed, 286 insertions(+)
 create mode 100644 tools/testing/selftests/net/amt.sh

(limited to 'tools')

diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile
index 492b273743b4..d27c98a32244 100644
--- a/tools/testing/selftests/net/Makefile
+++ b/tools/testing/selftests/net/Makefile
@@ -22,6 +22,7 @@ TEST_PROGS += devlink_port_split.py
 TEST_PROGS += drop_monitor_tests.sh
 TEST_PROGS += vrf_route_leaking.sh
 TEST_PROGS += bareudp.sh
+TEST_PROGS += amt.sh
 TEST_PROGS += unicast_extensions.sh
 TEST_PROGS += udpgro_fwd.sh
 TEST_PROGS += veth.sh
diff --git a/tools/testing/selftests/net/amt.sh b/tools/testing/selftests/net/amt.sh
new file mode 100644
index 000000000000..75528788cb95
--- /dev/null
+++ b/tools/testing/selftests/net/amt.sh
@@ -0,0 +1,284 @@
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
+
+# Author: Taehee Yoo <ap420073@gmail.com>
+#
+# This script evaluates the AMT driver.
+# There are four network-namespaces, LISTENER, SOURCE, GATEWAY, RELAY.
+# The role of LISTENER is to listen multicast traffic.
+# In order to do that, it send IGMP group join message.
+# The role of SOURCE is to send multicast traffic to listener.
+# The role of GATEWAY is to work Gateway role of AMT interface.
+# The role of RELAY is to work Relay role of AMT interface.
+#
+#
+#       +------------------------+
+#       |    LISTENER netns      |
+#       |                        |
+#       |  +------------------+  |
+#       |  |       l_gw       |  |
+#       |  |  192.168.0.2/24  |  |
+#       |  |  2001:db8::2/64  |  |
+#       |  +------------------+  |
+#       |            .           |
+#       +------------------------+
+#                    .
+#                    .
+#       +-----------------------------------------------------+
+#       |            .         GATEWAY netns                  |
+#       |            .                                        |
+#       |+---------------------------------------------------+|
+#       ||           .          br0                          ||
+#       || +------------------+       +------------------+   ||
+#       || |       gw_l       |       |       amtg       |   ||
+#       || |  192.168.0.1/24  |       +--------+---------+   ||
+#       || |  2001:db8::1/64  |                |             ||
+#       || +------------------+                |             ||
+#       |+-------------------------------------|-------------+|
+#       |                                      |              |
+#       |                             +--------+---------+    |
+#       |                             |     gw_relay     |    |
+#       |                             |    10.0.0.1/24   |    |
+#       |                             +------------------+    |
+#       |                                      .              |
+#       +-----------------------------------------------------+
+#                                              .
+#                                              .
+#       +-----------------------------------------------------+
+#       |                       RELAY netns    .              |
+#       |                             +------------------+    |
+#       |                             |     relay_gw     |    |
+#       |                             |    10.0.0.2/24   |    |
+#       |                             +--------+---------+    |
+#       |                                      |              |
+#       |                                      |              |
+#       |  +------------------+       +--------+---------+    |
+#       |  |     relay_src    |       |       amtr       |    |
+#       |  |   172.17.0.1/24  |       +------------------+    |
+#       |  | 2001:db8:3::1/64 |                               |
+#       |  +------------------+                               |
+#       |            .                                        |
+#       |            .                                        |
+#       +-----------------------------------------------------+
+#                    .
+#                    .
+#       +------------------------+
+#       |            .           |
+#       |  +------------------+  |
+#       |  |     src_relay    |  |
+#       |  |   172.17.0.2/24  |  |
+#       |  | 2001:db8:3::2/64 |  |
+#       |  +------------------+  |
+#       |      SOURCE netns      |
+#       +------------------------+
+#==============================================================================
+
+readonly LISTENER=$(mktemp -u listener-XXXXXXXX)
+readonly GATEWAY=$(mktemp -u gateway-XXXXXXXX)
+readonly RELAY=$(mktemp -u relay-XXXXXXXX)
+readonly SOURCE=$(mktemp -u source-XXXXXXXX)
+ERR=4
+err=0
+
+exit_cleanup()
+{
+	for ns in "$@"; do
+		ip netns delete "${ns}" 2>/dev/null || true
+	done
+
+	exit $ERR
+}
+
+create_namespaces()
+{
+	ip netns add "${LISTENER}" || exit_cleanup
+	ip netns add "${GATEWAY}" || exit_cleanup "${LISTENER}"
+	ip netns add "${RELAY}" || exit_cleanup "${LISTENER}" "${GATEWAY}"
+	ip netns add "${SOURCE}" || exit_cleanup "${LISTENER}" "${GATEWAY}" \
+		"${RELAY}"
+}
+
+# The trap function handler
+#
+exit_cleanup_all()
+{
+	exit_cleanup "${LISTENER}" "${GATEWAY}" "${RELAY}" "${SOURCE}"
+}
+
+setup_interface()
+{
+	for ns in "${LISTENER}" "${GATEWAY}" "${RELAY}" "${SOURCE}"; do
+		ip -netns "${ns}" link set dev lo up
+	done;
+
+	ip link add l_gw type veth peer name gw_l
+	ip link add gw_relay type veth peer name relay_gw
+	ip link add relay_src type veth peer name src_relay
+
+	ip link set l_gw netns "${LISTENER}" up
+	ip link set gw_l netns "${GATEWAY}" up
+	ip link set gw_relay netns "${GATEWAY}" up
+	ip link set relay_gw netns "${RELAY}" up
+	ip link set relay_src netns "${RELAY}" up
+	ip link set src_relay netns "${SOURCE}" up mtu 1400
+
+	ip netns exec "${LISTENER}" ip a a 192.168.0.2/24 dev l_gw
+	ip netns exec "${LISTENER}" ip r a default via 192.168.0.1 dev l_gw
+	ip netns exec "${LISTENER}" ip a a 2001:db8::2/64 dev l_gw
+	ip netns exec "${LISTENER}" ip r a default via 2001:db8::1 dev l_gw
+	ip netns exec "${LISTENER}" ip a a 239.0.0.1/32 dev l_gw autojoin
+	ip netns exec "${LISTENER}" ip a a ff0e::5:6/128 dev l_gw autojoin
+
+	ip netns exec "${GATEWAY}" ip a a 192.168.0.1/24 dev gw_l
+	ip netns exec "${GATEWAY}" ip a a 2001:db8::1/64 dev gw_l
+	ip netns exec "${GATEWAY}" ip a a 10.0.0.1/24 dev gw_relay
+	ip netns exec "${GATEWAY}" ip link add br0 type bridge
+	ip netns exec "${GATEWAY}" ip link set br0 up
+	ip netns exec "${GATEWAY}" ip link set gw_l master br0
+	ip netns exec "${GATEWAY}" ip link set gw_l up
+	ip netns exec "${GATEWAY}" ip link add amtg master br0 type amt \
+		mode gateway local 10.0.0.1 discovery 10.0.0.2 dev gw_relay \
+		gateway_port 2268 relay_port 2268
+	ip netns exec "${RELAY}" ip a a 10.0.0.2/24 dev relay_gw
+	ip netns exec "${RELAY}" ip link add amtr type amt mode relay \
+		local 10.0.0.2 dev relay_gw relay_port 2268 max_tunnels 4
+	ip netns exec "${RELAY}" ip a a 172.17.0.1/24 dev relay_src
+	ip netns exec "${RELAY}" ip a a 2001:db8:3::1/64 dev relay_src
+	ip netns exec "${SOURCE}" ip a a 172.17.0.2/24 dev src_relay
+	ip netns exec "${SOURCE}" ip a a 2001:db8:3::2/64 dev src_relay
+	ip netns exec "${SOURCE}" ip r a default via 172.17.0.1 dev src_relay
+	ip netns exec "${SOURCE}" ip r a default via 2001:db8:3::1 dev src_relay
+	ip netns exec "${RELAY}" ip link set amtr up
+	ip netns exec "${GATEWAY}" ip link set amtg up
+}
+
+setup_sysctl()
+{
+	ip netns exec "${RELAY}" sysctl net.ipv4.ip_forward=1 -w -q
+}
+
+setup_iptables()
+{
+	ip netns exec "${RELAY}" iptables -t mangle -I PREROUTING \
+		-d 239.0.0.1 -j TTL --ttl-set 2
+	ip netns exec "${RELAY}" ip6tables -t mangle -I PREROUTING \
+		-j HL --hl-set 2
+}
+
+setup_mcast_routing()
+{
+	ip netns exec "${RELAY}" smcrouted
+	ip netns exec "${RELAY}" smcroutectl a relay_src \
+		172.17.0.2 239.0.0.1 amtr
+	ip netns exec "${RELAY}" smcroutectl a relay_src \
+		2001:db8:3::2 ff0e::5:6 amtr
+}
+
+test_remote_ip()
+{
+	REMOTE=$(ip netns exec "${GATEWAY}" \
+		ip -d -j link show amtg | jq .[0].linkinfo.info_data.remote)
+	if [ $REMOTE == "\"10.0.0.2\"" ]; then
+		printf "TEST: %-60s  [ OK ]\n" "amt discovery"
+	else
+		printf "TEST: %-60s  [FAIL]\n" "amt discovery"
+		ERR=1
+	fi
+}
+
+send_mcast_torture4()
+{
+	ip netns exec "${SOURCE}" bash -c \
+		'cat /dev/urandom | head -c 1G | nc -w 1 -u 239.0.0.1 4001'
+}
+
+
+send_mcast_torture6()
+{
+	ip netns exec "${SOURCE}" bash -c \
+		'cat /dev/urandom | head -c 1G | nc -w 1 -u ff0e::5:6 6001'
+}
+
+check_features()
+{
+        ip link help 2>&1 | grep -q amt
+        if [ $? -ne 0 ]; then
+                echo "Missing amt support in iproute2" >&2
+                exit_cleanup
+        fi
+}
+
+test_ipv4_forward()
+{
+	RESULT4=$(ip netns exec "${LISTENER}" nc -w 1 -l -u 239.0.0.1 4000)
+	if [ "$RESULT4" == "172.17.0.2" ]; then
+		printf "TEST: %-60s  [ OK ]\n" "IPv4 amt multicast forwarding"
+		exit 0
+	else
+		printf "TEST: %-60s  [FAIL]\n" "IPv4 amt multicast forwarding"
+		exit 1
+	fi
+}
+
+test_ipv6_forward()
+{
+	RESULT6=$(ip netns exec "${LISTENER}" nc -w 1 -l -u ff0e::5:6 6000)
+	if [ "$RESULT6" == "2001:db8:3::2" ]; then
+		printf "TEST: %-60s  [ OK ]\n" "IPv6 amt multicast forwarding"
+		exit 0
+	else
+		printf "TEST: %-60s  [FAIL]\n" "IPv6 amt multicast forwarding"
+		exit 1
+	fi
+}
+
+send_mcast4()
+{
+	sleep 2
+	ip netns exec "${SOURCE}" bash -c \
+		'echo 172.17.0.2 | nc -w 1 -u 239.0.0.1 4000' &
+}
+
+send_mcast6()
+{
+	sleep 2
+	ip netns exec "${SOURCE}" bash -c \
+		'echo 2001:db8:3::2 | nc -w 1 -u ff0e::5:6 6000' &
+}
+
+check_features
+
+create_namespaces
+
+set -e
+trap exit_cleanup_all EXIT
+
+setup_interface
+setup_sysctl
+setup_iptables
+setup_mcast_routing
+test_remote_ip
+test_ipv4_forward &
+pid=$!
+send_mcast4
+wait $pid || err=$?
+if [ $err -eq 1 ]; then
+	ERR=1
+fi
+test_ipv6_forward &
+pid=$!
+send_mcast6
+wait $pid || err=$?
+if [ $err -eq 1 ]; then
+	ERR=1
+fi
+send_mcast_torture4
+printf "TEST: %-60s  [ OK ]\n" "IPv4 amt traffic forwarding torture"
+send_mcast_torture6
+printf "TEST: %-60s  [ OK ]\n" "IPv6 amt traffic forwarding torture"
+sleep 5
+if [ "${ERR}" -eq 1 ]; then
+        echo "Some tests failed." >&2
+else
+        ERR=0
+fi
diff --git a/tools/testing/selftests/net/config b/tools/testing/selftests/net/config
index 86ab429fe7f3..ead7963b9bf0 100644
--- a/tools/testing/selftests/net/config
+++ b/tools/testing/selftests/net/config
@@ -44,3 +44,4 @@ CONFIG_NET_ACT_MIRRED=m
 CONFIG_BAREUDP=m
 CONFIG_IPV6_IOAM6_LWTUNNEL=y
 CONFIG_CRYPTO_SM4=y
+CONFIG_AMT=m
-- 
cgit v1.2.3


From 0133c20480b14820d43c37c0e9502da4bffcad3a Mon Sep 17 00:00:00 2001
From: Andrii Nakryiko <andrii@kernel.org>
Date: Fri, 29 Oct 2021 11:29:07 -0700
Subject: selftests/bpf: Fix strobemeta selftest regression

After most recent nightly Clang update strobemeta selftests started
failing with the following error (relevant portion of assembly included):

  1624: (85) call bpf_probe_read_user_str#114
  1625: (bf) r1 = r0
  1626: (18) r2 = 0xfffffffe
  1628: (5f) r1 &= r2
  1629: (55) if r1 != 0x0 goto pc+7
  1630: (07) r9 += 104
  1631: (6b) *(u16 *)(r9 +0) = r0
  1632: (67) r0 <<= 32
  1633: (77) r0 >>= 32
  1634: (79) r1 = *(u64 *)(r10 -456)
  1635: (0f) r1 += r0
  1636: (7b) *(u64 *)(r10 -456) = r1
  1637: (79) r1 = *(u64 *)(r10 -368)
  1638: (c5) if r1 s< 0x1 goto pc+778
  1639: (bf) r6 = r8
  1640: (0f) r6 += r7
  1641: (b4) w1 = 0
  1642: (6b) *(u16 *)(r6 +108) = r1
  1643: (79) r3 = *(u64 *)(r10 -352)
  1644: (79) r9 = *(u64 *)(r10 -456)
  1645: (bf) r1 = r9
  1646: (b4) w2 = 1
  1647: (85) call bpf_probe_read_user_str#114

  R1 unbounded memory access, make sure to bounds check any such access

In the above code r0 and r1 are implicitly related. Clang knows that,
but verifier isn't able to infer this relationship.

Yonghong Song narrowed down this "regression" in code generation to
a recent Clang optimization change ([0]), which for BPF target generates
code pattern that BPF verifier can't handle and loses track of register
boundaries.

This patch works around the issue by adding an BPF assembly-based helper
that helps to prove to the verifier that upper bound of the register is
a given constant by controlling the exact share of generated BPF
instruction sequence. This fixes the immediate issue for strobemeta
selftest.

  [0] https://github.com/llvm/llvm-project/commit/acabad9ff6bf13e00305d9d8621ee8eafc1f8b08

Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Yonghong Song <yhs@fb.com>
Link: https://lore.kernel.org/bpf/20211029182907.166910-1-andrii@kernel.org
---
 tools/testing/selftests/bpf/progs/strobemeta.h | 11 +++++++++++
 1 file changed, 11 insertions(+)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/progs/strobemeta.h b/tools/testing/selftests/bpf/progs/strobemeta.h
index 7de534f38c3f..3687ea755ab5 100644
--- a/tools/testing/selftests/bpf/progs/strobemeta.h
+++ b/tools/testing/selftests/bpf/progs/strobemeta.h
@@ -10,6 +10,14 @@
 #include <linux/types.h>
 #include <bpf/bpf_helpers.h>
 
+#define bpf_clamp_umax(VAR, UMAX)					\
+	asm volatile (							\
+		"if %0 <= %[max] goto +1\n"				\
+		"%0 = %[max]\n"						\
+		: "+r"(VAR)						\
+		: [max]"i"(UMAX)					\
+	)
+
 typedef uint32_t pid_t;
 struct task_struct {};
 
@@ -413,6 +421,7 @@ static __always_inline void *read_map_var(struct strobemeta_cfg *cfg,
 
 	len = bpf_probe_read_user_str(payload, STROBE_MAX_STR_LEN, map.tag);
 	if (len <= STROBE_MAX_STR_LEN) {
+		bpf_clamp_umax(len, STROBE_MAX_STR_LEN);
 		descr->tag_len = len;
 		payload += len;
 	}
@@ -430,6 +439,7 @@ static __always_inline void *read_map_var(struct strobemeta_cfg *cfg,
 		len = bpf_probe_read_user_str(payload, STROBE_MAX_STR_LEN,
 					      map.entries[i].key);
 		if (len <= STROBE_MAX_STR_LEN) {
+			bpf_clamp_umax(len, STROBE_MAX_STR_LEN);
 			descr->key_lens[i] = len;
 			payload += len;
 		}
@@ -437,6 +447,7 @@ static __always_inline void *read_map_var(struct strobemeta_cfg *cfg,
 		len = bpf_probe_read_user_str(payload, STROBE_MAX_STR_LEN,
 					      map.entries[i].val);
 		if (len <= STROBE_MAX_STR_LEN) {
+			bpf_clamp_umax(len, STROBE_MAX_STR_LEN);
 			descr->val_lens[i] = len;
 			payload += len;
 		}
-- 
cgit v1.2.3


From b556c3fd467628341cc7680e4271790cafd79dc4 Mon Sep 17 00:00:00 2001
From: Liu Jian <liujian56@huawei.com>
Date: Fri, 29 Oct 2021 22:12:15 +0800
Subject: selftests, bpf: Fix test_txmsg_ingress_parser error

After "skmsg: lose offset info in sk_psock_skb_ingress", the test case
with ktls failed. This because ktls parser(tls_read_size) return value
is 285 not 256.

The case like this:

	tls_sk1 --> redir_sk --> tls_sk2

tls_sk1 sent out 512 bytes data, after tls related processing redir_sk
recved 570 btyes data, and redirect 512 (skb_use_parser) bytes data to
tls_sk2; but tls_sk2 needs 285 * 2 bytes data, receive timeout occurred.

Signed-off-by: Liu Jian <liujian56@huawei.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: John Fastabend <john.fastabend@gmail.com>
Link: https://lore.kernel.org/bpf/20211029141216.211899-2-liujian56@huawei.com
---
 tools/testing/selftests/bpf/test_sockmap.c | 2 ++
 1 file changed, 2 insertions(+)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/test_sockmap.c b/tools/testing/selftests/bpf/test_sockmap.c
index eefd445b96fc..06924917ad77 100644
--- a/tools/testing/selftests/bpf/test_sockmap.c
+++ b/tools/testing/selftests/bpf/test_sockmap.c
@@ -1680,6 +1680,8 @@ static void test_txmsg_ingress_parser(int cgrp, struct sockmap_options *opt)
 {
 	txmsg_pass = 1;
 	skb_use_parser = 512;
+	if (ktls == 1)
+		skb_use_parser = 570;
 	opt->iov_length = 256;
 	opt->iov_count = 1;
 	opt->rate = 2;
-- 
cgit v1.2.3


From d69672147faa2a7671c0779fa5b9ad99e4fca4e3 Mon Sep 17 00:00:00 2001
From: Liu Jian <liujian56@huawei.com>
Date: Fri, 29 Oct 2021 22:12:16 +0800
Subject: selftests, bpf: Add one test for sockmap with strparser

Add the test to check sockmap with strparser is working well.

Signed-off-by: Liu Jian <liujian56@huawei.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: John Fastabend <john.fastabend@gmail.com>
Link: https://lore.kernel.org/bpf/20211029141216.211899-3-liujian56@huawei.com
---
 tools/testing/selftests/bpf/test_sockmap.c | 33 +++++++++++++++++++++++++++---
 1 file changed, 30 insertions(+), 3 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/test_sockmap.c b/tools/testing/selftests/bpf/test_sockmap.c
index 06924917ad77..1ba7e7346afb 100644
--- a/tools/testing/selftests/bpf/test_sockmap.c
+++ b/tools/testing/selftests/bpf/test_sockmap.c
@@ -139,6 +139,7 @@ struct sockmap_options {
 	bool sendpage;
 	bool data_test;
 	bool drop_expected;
+	bool check_recved_len;
 	int iov_count;
 	int iov_length;
 	int rate;
@@ -556,8 +557,12 @@ static int msg_loop(int fd, int iov_count, int iov_length, int cnt,
 	int err, i, flags = MSG_NOSIGNAL;
 	bool drop = opt->drop_expected;
 	bool data = opt->data_test;
+	int iov_alloc_length = iov_length;
 
-	err = msg_alloc_iov(&msg, iov_count, iov_length, data, tx);
+	if (!tx && opt->check_recved_len)
+		iov_alloc_length *= 2;
+
+	err = msg_alloc_iov(&msg, iov_count, iov_alloc_length, data, tx);
 	if (err)
 		goto out_errno;
 	if (peek_flag) {
@@ -665,6 +670,13 @@ static int msg_loop(int fd, int iov_count, int iov_length, int cnt,
 
 			s->bytes_recvd += recv;
 
+			if (opt->check_recved_len && s->bytes_recvd > total_bytes) {
+				errno = EMSGSIZE;
+				fprintf(stderr, "recv failed(), bytes_recvd:%zd, total_bytes:%f\n",
+						s->bytes_recvd, total_bytes);
+				goto out_errno;
+			}
+
 			if (data) {
 				int chunk_sz = opt->sendpage ?
 						iov_length * cnt :
@@ -744,7 +756,8 @@ static int sendmsg_test(struct sockmap_options *opt)
 
 	rxpid = fork();
 	if (rxpid == 0) {
-		iov_buf -= (txmsg_pop - txmsg_start_pop + 1);
+		if (txmsg_pop || txmsg_start_pop)
+			iov_buf -= (txmsg_pop - txmsg_start_pop + 1);
 		if (opt->drop_expected || txmsg_ktls_skb_drop)
 			_exit(0);
 
@@ -1688,6 +1701,19 @@ static void test_txmsg_ingress_parser(int cgrp, struct sockmap_options *opt)
 	test_exec(cgrp, opt);
 }
 
+static void test_txmsg_ingress_parser2(int cgrp, struct sockmap_options *opt)
+{
+	if (ktls == 1)
+		return;
+	skb_use_parser = 10;
+	opt->iov_length = 20;
+	opt->iov_count = 1;
+	opt->rate = 1;
+	opt->check_recved_len = true;
+	test_exec(cgrp, opt);
+	opt->check_recved_len = false;
+}
+
 char *map_names[] = {
 	"sock_map",
 	"sock_map_txmsg",
@@ -1786,7 +1812,8 @@ struct _test test[] = {
 	{"txmsg test pull-data", test_txmsg_pull},
 	{"txmsg test pop-data", test_txmsg_pop},
 	{"txmsg test push/pop data", test_txmsg_push_pop},
-	{"txmsg text ingress parser", test_txmsg_ingress_parser},
+	{"txmsg test ingress parser", test_txmsg_ingress_parser},
+	{"txmsg test ingress parser2", test_txmsg_ingress_parser2},
 };
 
 static int check_whitelist(struct _test *t, struct sockmap_options *opt)
-- 
cgit v1.2.3


From b390d69831ee30e10a4ef410bee157e73b149036 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Bj=C3=B6rn=20T=C3=B6pel?= <bjorn@kernel.org>
Date: Thu, 28 Oct 2021 18:10:55 +0200
Subject: tools, build: Add RISC-V to HOSTARCH parsing
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add RISC-V to the HOSTARCH parsing, so that ARCH is "riscv", and not
"riscv32" or "riscv64".

This affects the perf and libbpf builds, so that arch specific
includes are correctly picked up for RISC-V.

Signed-off-by: Björn Töpel <bjorn@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/bpf/20211028161057.520552-3-bjorn@kernel.org
---
 tools/scripts/Makefile.arch | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

(limited to 'tools')

diff --git a/tools/scripts/Makefile.arch b/tools/scripts/Makefile.arch
index b10b7a27c33f..0c6c7f456887 100644
--- a/tools/scripts/Makefile.arch
+++ b/tools/scripts/Makefile.arch
@@ -4,7 +4,8 @@ HOSTARCH := $(shell uname -m | sed -e s/i.86/x86/ -e s/x86_64/x86/ \
                                   -e /arm64/!s/arm.*/arm/ -e s/sa110/arm/ \
                                   -e s/s390x/s390/ -e s/parisc64/parisc/ \
                                   -e s/ppc.*/powerpc/ -e s/mips.*/mips/ \
-                                  -e s/sh[234].*/sh/ -e s/aarch64.*/arm64/ )
+                                  -e s/sh[234].*/sh/ -e s/aarch64.*/arm64/ \
+                                  -e s/riscv.*/riscv/)
 
 ifndef ARCH
 ARCH := $(HOSTARCH)
-- 
cgit v1.2.3


From 589fed479ba1e93f94d9772aa6162cd81f7e491c Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Bj=C3=B6rn=20T=C3=B6pel?= <bjorn@kernel.org>
Date: Thu, 28 Oct 2021 18:10:56 +0200
Subject: riscv, libbpf: Add RISC-V (RV64) support to bpf_tracing.h
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add macros for 64-bit RISC-V PT_REGS to bpf_tracing.h.

Signed-off-by: Björn Töpel <bjorn@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/bpf/20211028161057.520552-4-bjorn@kernel.org
---
 tools/lib/bpf/bpf_tracing.h | 32 ++++++++++++++++++++++++++++++++
 1 file changed, 32 insertions(+)

(limited to 'tools')

diff --git a/tools/lib/bpf/bpf_tracing.h b/tools/lib/bpf/bpf_tracing.h
index d6bfbe009296..db05a5937105 100644
--- a/tools/lib/bpf/bpf_tracing.h
+++ b/tools/lib/bpf/bpf_tracing.h
@@ -24,6 +24,9 @@
 #elif defined(__TARGET_ARCH_sparc)
 	#define bpf_target_sparc
 	#define bpf_target_defined
+#elif defined(__TARGET_ARCH_riscv)
+	#define bpf_target_riscv
+	#define bpf_target_defined
 #else
 
 /* Fall back to what the compiler says */
@@ -48,6 +51,9 @@
 #elif defined(__sparc__)
 	#define bpf_target_sparc
 	#define bpf_target_defined
+#elif defined(__riscv) && __riscv_xlen == 64
+	#define bpf_target_riscv
+	#define bpf_target_defined
 #endif /* no compiler target */
 
 #endif
@@ -288,6 +294,32 @@ struct pt_regs;
 #define PT_REGS_IP_CORE(x) BPF_CORE_READ((x), pc)
 #endif
 
+#elif defined(bpf_target_riscv)
+
+struct pt_regs;
+#define PT_REGS_RV const volatile struct user_regs_struct
+#define PT_REGS_PARM1(x) (((PT_REGS_RV *)(x))->a0)
+#define PT_REGS_PARM2(x) (((PT_REGS_RV *)(x))->a1)
+#define PT_REGS_PARM3(x) (((PT_REGS_RV *)(x))->a2)
+#define PT_REGS_PARM4(x) (((PT_REGS_RV *)(x))->a3)
+#define PT_REGS_PARM5(x) (((PT_REGS_RV *)(x))->a4)
+#define PT_REGS_RET(x) (((PT_REGS_RV *)(x))->ra)
+#define PT_REGS_FP(x) (((PT_REGS_RV *)(x))->s5)
+#define PT_REGS_RC(x) (((PT_REGS_RV *)(x))->a5)
+#define PT_REGS_SP(x) (((PT_REGS_RV *)(x))->sp)
+#define PT_REGS_IP(x) (((PT_REGS_RV *)(x))->epc)
+
+#define PT_REGS_PARM1_CORE(x) BPF_CORE_READ((PT_REGS_RV *)(x), a0)
+#define PT_REGS_PARM2_CORE(x) BPF_CORE_READ((PT_REGS_RV *)(x), a1)
+#define PT_REGS_PARM3_CORE(x) BPF_CORE_READ((PT_REGS_RV *)(x), a2)
+#define PT_REGS_PARM4_CORE(x) BPF_CORE_READ((PT_REGS_RV *)(x), a3)
+#define PT_REGS_PARM5_CORE(x) BPF_CORE_READ((PT_REGS_RV *)(x), a4)
+#define PT_REGS_RET_CORE(x) BPF_CORE_READ((PT_REGS_RV *)(x), ra)
+#define PT_REGS_FP_CORE(x) BPF_CORE_READ((PT_REGS_RV *)(x), fp)
+#define PT_REGS_RC_CORE(x) BPF_CORE_READ((PT_REGS_RV *)(x), a5)
+#define PT_REGS_SP_CORE(x) BPF_CORE_READ((PT_REGS_RV *)(x), sp)
+#define PT_REGS_IP_CORE(x) BPF_CORE_READ((PT_REGS_RV *)(x), epc)
+
 #endif
 
 #if defined(bpf_target_powerpc)
-- 
cgit v1.2.3


From 36e70b9b06bf14a0fac87315f0e73d6e17e80aad Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Bj=C3=B6rn=20T=C3=B6pel?= <bjorn@kernel.org>
Date: Thu, 28 Oct 2021 18:10:57 +0200
Subject: selftests, bpf: Fix broken riscv build
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This patch is closely related to commit 6016df8fe874 ("selftests/bpf:
Fix broken riscv build"). When clang includes the system include
directories, but targeting BPF program, __BITS_PER_LONG defaults to
32, unless explicitly set. Work around this problem, by explicitly
setting __BITS_PER_LONG to __riscv_xlen.

Signed-off-by: Björn Töpel <bjorn@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/bpf/20211028161057.520552-5-bjorn@kernel.org
---
 tools/testing/selftests/bpf/Makefile | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index f49cb5fc85af..54b0a41a3775 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -277,7 +277,7 @@ $(RESOLVE_BTFIDS): $(HOST_BPFOBJ) | $(HOST_BUILD_DIR)/resolve_btfids	\
 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 }') \
-$(shell $(1) -dM -E - </dev/null | grep '#define __riscv_xlen ' | sed 's/#define /-D/' | sed 's/ /=/')
+$(shell $(1) -dM -E - </dev/null | grep '__riscv_xlen ' | awk '{printf("-D__riscv_xlen=%d -D__BITS_PER_LONG=%d", $$3, $$3)}')
 endef
 
 # Determine target endianness.
-- 
cgit v1.2.3


From 31122b2f768bde5281037141bb658f117bea102e Mon Sep 17 00:00:00 2001
From: Hou Tao <houtao1@huawei.com>
Date: Mon, 25 Oct 2021 14:40:25 +0800
Subject: selftests/bpf: Add test cases for struct_ops prog

Running a BPF_PROG_TYPE_STRUCT_OPS prog for dummy_st_ops::test_N()
through bpf_prog_test_run(). Four test cases are added:
(1) attach dummy_st_ops should fail
(2) function return value of bpf_dummy_ops::test_1() is expected
(3) pointer argument of bpf_dummy_ops::test_1() works as expected
(4) multiple arguments passed to bpf_dummy_ops::test_2() are correct

Signed-off-by: Hou Tao <houtao1@huawei.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Link: https://lore.kernel.org/bpf/20211025064025.2567443-5-houtao1@huawei.com
---
 .../selftests/bpf/prog_tests/dummy_st_ops.c        | 115 +++++++++++++++++++++
 tools/testing/selftests/bpf/progs/dummy_st_ops.c   |  50 +++++++++
 2 files changed, 165 insertions(+)
 create mode 100644 tools/testing/selftests/bpf/prog_tests/dummy_st_ops.c
 create mode 100644 tools/testing/selftests/bpf/progs/dummy_st_ops.c

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/prog_tests/dummy_st_ops.c b/tools/testing/selftests/bpf/prog_tests/dummy_st_ops.c
new file mode 100644
index 000000000000..cbaa44ffb8c6
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/dummy_st_ops.c
@@ -0,0 +1,115 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (C) 2021. Huawei Technologies Co., Ltd */
+#include <test_progs.h>
+#include "dummy_st_ops.skel.h"
+
+/* Need to keep consistent with definition in include/linux/bpf.h */
+struct bpf_dummy_ops_state {
+	int val;
+};
+
+static void test_dummy_st_ops_attach(void)
+{
+	struct dummy_st_ops *skel;
+	struct bpf_link *link;
+
+	skel = dummy_st_ops__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "dummy_st_ops_load"))
+		return;
+
+	link = bpf_map__attach_struct_ops(skel->maps.dummy_1);
+	ASSERT_EQ(libbpf_get_error(link), -EOPNOTSUPP, "dummy_st_ops_attach");
+
+	dummy_st_ops__destroy(skel);
+}
+
+static void test_dummy_init_ret_value(void)
+{
+	__u64 args[1] = {0};
+	struct bpf_prog_test_run_attr attr = {
+		.ctx_size_in = sizeof(args),
+		.ctx_in = args,
+	};
+	struct dummy_st_ops *skel;
+	int fd, err;
+
+	skel = dummy_st_ops__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "dummy_st_ops_load"))
+		return;
+
+	fd = bpf_program__fd(skel->progs.test_1);
+	attr.prog_fd = fd;
+	err = bpf_prog_test_run_xattr(&attr);
+	ASSERT_OK(err, "test_run");
+	ASSERT_EQ(attr.retval, 0xf2f3f4f5, "test_ret");
+
+	dummy_st_ops__destroy(skel);
+}
+
+static void test_dummy_init_ptr_arg(void)
+{
+	int exp_retval = 0xbeef;
+	struct bpf_dummy_ops_state in_state = {
+		.val = exp_retval,
+	};
+	__u64 args[1] = {(unsigned long)&in_state};
+	struct bpf_prog_test_run_attr attr = {
+		.ctx_size_in = sizeof(args),
+		.ctx_in = args,
+	};
+	struct dummy_st_ops *skel;
+	int fd, err;
+
+	skel = dummy_st_ops__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "dummy_st_ops_load"))
+		return;
+
+	fd = bpf_program__fd(skel->progs.test_1);
+	attr.prog_fd = fd;
+	err = bpf_prog_test_run_xattr(&attr);
+	ASSERT_OK(err, "test_run");
+	ASSERT_EQ(in_state.val, 0x5a, "test_ptr_ret");
+	ASSERT_EQ(attr.retval, exp_retval, "test_ret");
+
+	dummy_st_ops__destroy(skel);
+}
+
+static void test_dummy_multiple_args(void)
+{
+	__u64 args[5] = {0, -100, 0x8a5f, 'c', 0x1234567887654321ULL};
+	struct bpf_prog_test_run_attr attr = {
+		.ctx_size_in = sizeof(args),
+		.ctx_in = args,
+	};
+	struct dummy_st_ops *skel;
+	int fd, err;
+	size_t i;
+	char name[8];
+
+	skel = dummy_st_ops__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "dummy_st_ops_load"))
+		return;
+
+	fd = bpf_program__fd(skel->progs.test_2);
+	attr.prog_fd = fd;
+	err = bpf_prog_test_run_xattr(&attr);
+	ASSERT_OK(err, "test_run");
+	for (i = 0; i < ARRAY_SIZE(args); i++) {
+		snprintf(name, sizeof(name), "arg %zu", i);
+		ASSERT_EQ(skel->bss->test_2_args[i], args[i], name);
+	}
+
+	dummy_st_ops__destroy(skel);
+}
+
+void test_dummy_st_ops(void)
+{
+	if (test__start_subtest("dummy_st_ops_attach"))
+		test_dummy_st_ops_attach();
+	if (test__start_subtest("dummy_init_ret_value"))
+		test_dummy_init_ret_value();
+	if (test__start_subtest("dummy_init_ptr_arg"))
+		test_dummy_init_ptr_arg();
+	if (test__start_subtest("dummy_multiple_args"))
+		test_dummy_multiple_args();
+}
diff --git a/tools/testing/selftests/bpf/progs/dummy_st_ops.c b/tools/testing/selftests/bpf/progs/dummy_st_ops.c
new file mode 100644
index 000000000000..ead87edb75e2
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/dummy_st_ops.c
@@ -0,0 +1,50 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (C) 2021. Huawei Technologies Co., Ltd */
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+
+struct bpf_dummy_ops_state {
+	int val;
+} __attribute__((preserve_access_index));
+
+struct bpf_dummy_ops {
+	int (*test_1)(struct bpf_dummy_ops_state *state);
+	int (*test_2)(struct bpf_dummy_ops_state *state, int a1, unsigned short a2,
+		      char a3, unsigned long a4);
+};
+
+char _license[] SEC("license") = "GPL";
+
+SEC("struct_ops/test_1")
+int BPF_PROG(test_1, struct bpf_dummy_ops_state *state)
+{
+	int ret;
+
+	if (!state)
+		return 0xf2f3f4f5;
+
+	ret = state->val;
+	state->val = 0x5a;
+	return ret;
+}
+
+__u64 test_2_args[5];
+
+SEC("struct_ops/test_2")
+int BPF_PROG(test_2, struct bpf_dummy_ops_state *state, int a1, unsigned short a2,
+	     char a3, unsigned long a4)
+{
+	test_2_args[0] = (unsigned long)state;
+	test_2_args[1] = a1;
+	test_2_args[2] = a2;
+	test_2_args[3] = a3;
+	test_2_args[4] = a4;
+	return 0;
+}
+
+SEC(".struct_ops")
+struct bpf_dummy_ops dummy_1 = {
+	.test_1 = (void *)test_1,
+	.test_2 = (void *)test_2,
+};
-- 
cgit v1.2.3


From 8845b4681bf44b9d2d2badf2c67cf476e42a86bd Mon Sep 17 00:00:00 2001
From: Joanne Koong <joannekoong@fb.com>
Date: Fri, 29 Oct 2021 15:49:08 -0700
Subject: bpf: Add alignment padding for "map_extra" + consolidate holes

This patch makes 2 changes regarding alignment padding
for the "map_extra" field.

1) In the kernel header, "map_extra" and "btf_value_type_id"
are rearranged to consolidate the hole.

Before:
struct bpf_map {
	...
        u32		max_entries;	/*    36     4	*/
        u32		map_flags;	/*    40     4	*/

        /* XXX 4 bytes hole, try to pack */

        u64		map_extra;	/*    48     8	*/
        int		spin_lock_off;	/*    56     4	*/
        int		timer_off;	/*    60     4	*/
        /* --- cacheline 1 boundary (64 bytes) --- */
        u32		id;		/*    64     4	*/
        int		numa_node;	/*    68     4	*/
	...
        bool		frozen;		/*   117     1	*/

        /* XXX 10 bytes hole, try to pack */

        /* --- cacheline 2 boundary (128 bytes) --- */
	...
        struct work_struct	work;	/*   144    72	*/

        /* --- cacheline 3 boundary (192 bytes) was 24 bytes ago --- */
	struct mutex	freeze_mutex;	/*   216   144 	*/

        /* --- cacheline 5 boundary (320 bytes) was 40 bytes ago --- */
        u64		writecnt; 	/*   360     8	*/

    /* size: 384, cachelines: 6, members: 26 */
    /* sum members: 354, holes: 2, sum holes: 14 */
    /* padding: 16 */
    /* forced alignments: 2, forced holes: 1, sum forced holes: 10 */

} __attribute__((__aligned__(64)));

After:
struct bpf_map {
	...
        u32		max_entries;	/*    36     4	*/
        u64		map_extra;	/*    40     8 	*/
        u32		map_flags;	/*    48     4	*/
        int		spin_lock_off;	/*    52     4	*/
        int		timer_off;	/*    56     4	*/
        u32		id;		/*    60     4	*/

        /* --- cacheline 1 boundary (64 bytes) --- */
        int		numa_node;	/*    64     4	*/
	...
	bool		frozen		/*   113     1  */

        /* XXX 14 bytes hole, try to pack */

        /* --- cacheline 2 boundary (128 bytes) --- */
	...
        struct work_struct	work;	/*   144    72	*/

        /* --- cacheline 3 boundary (192 bytes) was 24 bytes ago --- */
        struct mutex	freeze_mutex;	/*   216   144	*/

        /* --- cacheline 5 boundary (320 bytes) was 40 bytes ago --- */
        u64		writecnt;       /*   360     8	*/

    /* size: 384, cachelines: 6, members: 26 */
    /* sum members: 354, holes: 1, sum holes: 14 */
    /* padding: 16 */
    /* forced alignments: 2, forced holes: 1, sum forced holes: 14 */

} __attribute__((__aligned__(64)));

2) Add alignment padding to the bpf_map_info struct
More details can be found in commit 36f9814a494a ("bpf: fix uapi hole
for 32 bit compat applications")

Signed-off-by: Joanne Koong <joannekoong@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Yonghong Song <yhs@fb.com>
Link: https://lore.kernel.org/bpf/20211029224909.1721024-3-joannekoong@fb.com
---
 tools/include/uapi/linux/bpf.h | 1 +
 1 file changed, 1 insertion(+)

(limited to 'tools')

diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index bd0c9f0487f6..ba5af15e25f5 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -5662,6 +5662,7 @@ struct bpf_map_info {
 	__u32 btf_id;
 	__u32 btf_key_type_id;
 	__u32 btf_value_type_id;
+	__u32 :32;	/* alignment pad */
 	__u64 map_extra;
 } __attribute__((aligned(8)));
 
-- 
cgit v1.2.3


From 7a67087250f0003acc1b9e20eda01635e1e51f9a Mon Sep 17 00:00:00 2001
From: Joanne Koong <joannekoong@fb.com>
Date: Fri, 29 Oct 2021 15:49:09 -0700
Subject: selftests/bpf: Add bloom map success test for userspace calls

This patch has two changes:
1) Adds a new function "test_success_cases" to test
successfully creating + adding + looking up a value
in a bloom filter map from the userspace side.

2) Use bpf_create_map instead of bpf_create_map_xattr in
the "test_fail_cases" and test_inner_map to make the
code look cleaner.

Signed-off-by: Joanne Koong <joannekoong@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Yonghong Song <yhs@fb.com>
Link: https://lore.kernel.org/bpf/20211029224909.1721024-4-joannekoong@fb.com
---
 .../selftests/bpf/prog_tests/bloom_filter_map.c    | 59 ++++++++++++----------
 1 file changed, 33 insertions(+), 26 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/prog_tests/bloom_filter_map.c b/tools/testing/selftests/bpf/prog_tests/bloom_filter_map.c
index 9aa3fbed918b..be73e3de6668 100644
--- a/tools/testing/selftests/bpf/prog_tests/bloom_filter_map.c
+++ b/tools/testing/selftests/bpf/prog_tests/bloom_filter_map.c
@@ -7,44 +7,31 @@
 
 static void test_fail_cases(void)
 {
-	struct bpf_create_map_attr xattr = {
-		.name = "bloom_filter_map",
-		.map_type = BPF_MAP_TYPE_BLOOM_FILTER,
-		.max_entries = 100,
-		.value_size = 11,
-	};
 	__u32 value;
 	int fd, err;
 
 	/* Invalid key size */
-	xattr.key_size = 4;
-	fd = bpf_create_map_xattr(&xattr);
+	fd = bpf_create_map(BPF_MAP_TYPE_BLOOM_FILTER, 4, sizeof(value), 100, 0);
 	if (!ASSERT_LT(fd, 0, "bpf_create_map bloom filter invalid key size"))
 		close(fd);
-	xattr.key_size = 0;
 
 	/* Invalid value size */
-	xattr.value_size = 0;
-	fd = bpf_create_map_xattr(&xattr);
+	fd = bpf_create_map(BPF_MAP_TYPE_BLOOM_FILTER, 0, 0, 100, 0);
 	if (!ASSERT_LT(fd, 0, "bpf_create_map bloom filter invalid value size 0"))
 		close(fd);
-	xattr.value_size = 11;
 
 	/* Invalid max entries size */
-	xattr.max_entries = 0;
-	fd = bpf_create_map_xattr(&xattr);
+	fd = bpf_create_map(BPF_MAP_TYPE_BLOOM_FILTER, 0, sizeof(value), 0, 0);
 	if (!ASSERT_LT(fd, 0, "bpf_create_map bloom filter invalid max entries size"))
 		close(fd);
-	xattr.max_entries = 100;
 
 	/* Bloom filter maps do not support BPF_F_NO_PREALLOC */
-	xattr.map_flags = BPF_F_NO_PREALLOC;
-	fd = bpf_create_map_xattr(&xattr);
+	fd = bpf_create_map(BPF_MAP_TYPE_BLOOM_FILTER, 0, sizeof(value), 100,
+			    BPF_F_NO_PREALLOC);
 	if (!ASSERT_LT(fd, 0, "bpf_create_map bloom filter invalid flags"))
 		close(fd);
-	xattr.map_flags = 0;
 
-	fd = bpf_create_map_xattr(&xattr);
+	fd = bpf_create_map(BPF_MAP_TYPE_BLOOM_FILTER, 0, sizeof(value), 100, 0);
 	if (!ASSERT_GE(fd, 0, "bpf_create_map bloom filter"))
 		return;
 
@@ -67,6 +54,30 @@ static void test_fail_cases(void)
 	close(fd);
 }
 
+static void test_success_cases(void)
+{
+	char value[11];
+	int fd, err;
+
+	/* Create a map */
+	fd = bpf_create_map(BPF_MAP_TYPE_BLOOM_FILTER, 0, sizeof(value), 100,
+			    BPF_F_ZERO_SEED | BPF_F_NUMA_NODE);
+	if (!ASSERT_GE(fd, 0, "bpf_create_map bloom filter success case"))
+		return;
+
+	/* Add a value to the bloom filter */
+	err = bpf_map_update_elem(fd, NULL, &value, 0);
+	if (!ASSERT_OK(err, "bpf_map_update_elem bloom filter success case"))
+		goto done;
+
+	 /* Lookup a value in the bloom filter */
+	err = bpf_map_lookup_elem(fd, NULL, &value);
+	ASSERT_OK(err, "bpf_map_update_elem bloom filter success case");
+
+done:
+	close(fd);
+}
+
 static void check_bloom(struct bloom_filter_map *skel)
 {
 	struct bpf_link *link;
@@ -86,16 +97,11 @@ static void test_inner_map(struct bloom_filter_map *skel, const __u32 *rand_vals
 			   __u32 nr_rand_vals)
 {
 	int outer_map_fd, inner_map_fd, err, i, key = 0;
-	struct bpf_create_map_attr xattr = {
-		.name = "bloom_filter_inner_map",
-		.map_type = BPF_MAP_TYPE_BLOOM_FILTER,
-		.value_size = sizeof(__u32),
-		.max_entries = nr_rand_vals,
-	};
 	struct bpf_link *link;
 
 	/* Create a bloom filter map that will be used as the inner map */
-	inner_map_fd = bpf_create_map_xattr(&xattr);
+	inner_map_fd = bpf_create_map(BPF_MAP_TYPE_BLOOM_FILTER, 0, sizeof(*rand_vals),
+				      nr_rand_vals, 0);
 	if (!ASSERT_GE(inner_map_fd, 0, "bpf_create_map bloom filter inner map"))
 		return;
 
@@ -190,6 +196,7 @@ void test_bloom_filter_map(void)
 	int err;
 
 	test_fail_cases();
+	test_success_cases();
 
 	err = setup_progs(&skel, &rand_vals, &nr_rand_vals);
 	if (err)
-- 
cgit v1.2.3


From a20eac0af02810669e187cb623bc904908c423af Mon Sep 17 00:00:00 2001
From: Andrii Nakryiko <andrii@kernel.org>
Date: Mon, 1 Nov 2021 16:01:18 -0700
Subject: selftests/bpf: Fix also no-alu32 strobemeta selftest

Previous fix aded bpf_clamp_umax() helper use to re-validate boundaries.
While that works correctly, it introduces more branches, which blows up
past 1 million instructions in no-alu32 variant of strobemeta selftests.

Switching len variable from u32 to u64 also fixes the issue and reduces
the number of validated instructions, so use that instead. Fix this
patch and bpf_clamp_umax() removed, both alu32 and no-alu32 selftests
pass.

Fixes: 0133c20480b1 ("selftests/bpf: Fix strobemeta selftest regression")
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20211101230118.1273019-1-andrii@kernel.org
---
 tools/testing/selftests/bpf/progs/strobemeta.h | 15 ++-------------
 1 file changed, 2 insertions(+), 13 deletions(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/progs/strobemeta.h b/tools/testing/selftests/bpf/progs/strobemeta.h
index 3687ea755ab5..60c93aee2f4a 100644
--- a/tools/testing/selftests/bpf/progs/strobemeta.h
+++ b/tools/testing/selftests/bpf/progs/strobemeta.h
@@ -10,14 +10,6 @@
 #include <linux/types.h>
 #include <bpf/bpf_helpers.h>
 
-#define bpf_clamp_umax(VAR, UMAX)					\
-	asm volatile (							\
-		"if %0 <= %[max] goto +1\n"				\
-		"%0 = %[max]\n"						\
-		: "+r"(VAR)						\
-		: [max]"i"(UMAX)					\
-	)
-
 typedef uint32_t pid_t;
 struct task_struct {};
 
@@ -366,7 +358,7 @@ static __always_inline uint64_t read_str_var(struct strobemeta_cfg *cfg,
 					     void *payload)
 {
 	void *location;
-	uint32_t len;
+	uint64_t len;
 
 	data->str_lens[idx] = 0;
 	location = calc_location(&cfg->str_locs[idx], tls_base);
@@ -398,7 +390,7 @@ static __always_inline void *read_map_var(struct strobemeta_cfg *cfg,
 	struct strobe_map_descr* descr = &data->map_descrs[idx];
 	struct strobe_map_raw map;
 	void *location;
-	uint32_t len;
+	uint64_t len;
 	int i;
 
 	descr->tag_len = 0; /* presume no tag is set */
@@ -421,7 +413,6 @@ static __always_inline void *read_map_var(struct strobemeta_cfg *cfg,
 
 	len = bpf_probe_read_user_str(payload, STROBE_MAX_STR_LEN, map.tag);
 	if (len <= STROBE_MAX_STR_LEN) {
-		bpf_clamp_umax(len, STROBE_MAX_STR_LEN);
 		descr->tag_len = len;
 		payload += len;
 	}
@@ -439,7 +430,6 @@ static __always_inline void *read_map_var(struct strobemeta_cfg *cfg,
 		len = bpf_probe_read_user_str(payload, STROBE_MAX_STR_LEN,
 					      map.entries[i].key);
 		if (len <= STROBE_MAX_STR_LEN) {
-			bpf_clamp_umax(len, STROBE_MAX_STR_LEN);
 			descr->key_lens[i] = len;
 			payload += len;
 		}
@@ -447,7 +437,6 @@ static __always_inline void *read_map_var(struct strobemeta_cfg *cfg,
 		len = bpf_probe_read_user_str(payload, STROBE_MAX_STR_LEN,
 					      map.entries[i].val);
 		if (len <= STROBE_MAX_STR_LEN) {
-			bpf_clamp_umax(len, STROBE_MAX_STR_LEN);
 			descr->val_lens[i] = len;
 			payload += len;
 		}
-- 
cgit v1.2.3


From b9979db8340154526d9ab38a1883d6f6ba9b6d47 Mon Sep 17 00:00:00 2001
From: Alexei Starovoitov <ast@kernel.org>
Date: Mon, 1 Nov 2021 15:21:51 -0700
Subject: bpf: Fix propagation of bounds from 64-bit min/max into 32-bit and
 var_off.

Before this fix:
166: (b5) if r2 <= 0x1 goto pc+22
from 166 to 189: R2=invP(id=1,umax_value=1,var_off=(0x0; 0xffffffff))

After this fix:
166: (b5) if r2 <= 0x1 goto pc+22
from 166 to 189: R2=invP(id=1,umax_value=1,var_off=(0x0; 0x1))

While processing BPF_JLE the reg_set_min_max() would set true_reg->umax_value = 1
and call __reg_combine_64_into_32(true_reg).

Without the fix it would not pass the condition:
if (__reg64_bound_u32(reg->umin_value) && __reg64_bound_u32(reg->umax_value))

since umin_value == 0 at this point.
Before commit 10bf4e83167c the umin was incorrectly ingored.
The commit 10bf4e83167c fixed the correctness issue, but pessimized
propagation of 64-bit min max into 32-bit min max and corresponding var_off.

Fixes: 10bf4e83167c ("bpf: Fix propagation of 32 bit unsigned bounds from 64 bit bounds")
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Acked-by: Yonghong Song <yhs@fb.com>
Link: https://lore.kernel.org/bpf/20211101222153.78759-1-alexei.starovoitov@gmail.com
---
 tools/testing/selftests/bpf/verifier/array_access.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/verifier/array_access.c b/tools/testing/selftests/bpf/verifier/array_access.c
index 1b1c798e9248..1b138cd2b187 100644
--- a/tools/testing/selftests/bpf/verifier/array_access.c
+++ b/tools/testing/selftests/bpf/verifier/array_access.c
@@ -186,7 +186,7 @@
 	},
 	.fixup_map_hash_48b = { 3 },
 	.errstr_unpriv = "R0 leaks addr",
-	.errstr = "R0 unbounded memory access",
+	.errstr = "invalid access to map value, value_size=48 off=44 size=8",
 	.result_unpriv = REJECT,
 	.result = REJECT,
 	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
-- 
cgit v1.2.3


From 0869e5078afbd1b22c20832b391b2d85291bc0a8 Mon Sep 17 00:00:00 2001
From: Alexei Starovoitov <ast@kernel.org>
Date: Mon, 1 Nov 2021 15:21:53 -0700
Subject: selftests/bpf: Add a testcase for 64-bit bounds propagation issue.

./test_progs-no_alu32 -vv -t twfw

Before the 64-bit_into_32-bit fix:
19: (25) if r1 > 0x3f goto pc+6
 R1_w=inv(id=0,umax_value=63,var_off=(0x0; 0xff),s32_max_value=255,u32_max_value=255)

and eventually:

invalid access to map value, value_size=8 off=7 size=8
R6 max value is outside of the allowed memory range
libbpf: failed to load object 'no_alu32/twfw.o'

After the fix:
19: (25) if r1 > 0x3f goto pc+6
 R1_w=inv(id=0,umax_value=63,var_off=(0x0; 0x3f))

verif_twfw:OK

Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Acked-by: Yonghong Song <yhs@fb.com>
Link: https://lore.kernel.org/bpf/20211101222153.78759-3-alexei.starovoitov@gmail.com
---
 .../selftests/bpf/prog_tests/bpf_verif_scale.c     |  5 ++
 tools/testing/selftests/bpf/progs/twfw.c           | 58 ++++++++++++++++++++++
 2 files changed, 63 insertions(+)
 create mode 100644 tools/testing/selftests/bpf/progs/twfw.c

(limited to 'tools')

diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_verif_scale.c b/tools/testing/selftests/bpf/prog_tests/bpf_verif_scale.c
index 867349e4ed9e..27f5d8ea7964 100644
--- a/tools/testing/selftests/bpf/prog_tests/bpf_verif_scale.c
+++ b/tools/testing/selftests/bpf/prog_tests/bpf_verif_scale.c
@@ -202,3 +202,8 @@ void test_verif_scale_seg6_loop()
 {
 	scale_test("test_seg6_loop.o", BPF_PROG_TYPE_LWT_SEG6LOCAL, false);
 }
+
+void test_verif_twfw()
+{
+	scale_test("twfw.o", BPF_PROG_TYPE_CGROUP_SKB, false);
+}
diff --git a/tools/testing/selftests/bpf/progs/twfw.c b/tools/testing/selftests/bpf/progs/twfw.c
new file mode 100644
index 000000000000..de1b18a62b46
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/twfw.c
@@ -0,0 +1,58 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2021 Facebook */
+#include <linux/types.h>
+#include <bpf/bpf_helpers.h>
+#include <linux/bpf.h>
+#include <stdint.h>
+
+#define TWFW_MAX_TIERS (64)
+/*
+ * load is successful
+ * #define TWFW_MAX_TIERS (64u)$
+ */
+
+struct twfw_tier_value {
+	unsigned long mask[1];
+};
+
+struct rule {
+	uint8_t seqnum;
+};
+
+struct rules_map {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__type(key, __u32);
+	__type(value, struct rule);
+	__uint(max_entries, 1);
+};
+
+struct tiers_map {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__type(key, __u32);
+	__type(value, struct twfw_tier_value);
+	__uint(max_entries, 1);
+};
+
+struct rules_map rules SEC(".maps");
+struct tiers_map tiers SEC(".maps");
+
+SEC("cgroup_skb/ingress")
+int twfw_verifier(struct __sk_buff* skb)
+{
+	const uint32_t key = 0;
+	const struct twfw_tier_value* tier = bpf_map_lookup_elem(&tiers, &key);
+	if (!tier)
+		return 1;
+
+	struct rule* rule = bpf_map_lookup_elem(&rules, &key);
+	if (!rule)
+		return 1;
+
+	if (rule && rule->seqnum < TWFW_MAX_TIERS) {
+		/* rule->seqnum / 64 should always be 0 */
+		unsigned long mask = tier->mask[rule->seqnum / 64];
+		if (mask)
+			return 0;
+	}
+	return 1;
+}
-- 
cgit v1.2.3


From 0b170456e0dda92b8925d40e217461fcc4e1efc9 Mon Sep 17 00:00:00 2001
From: Magnus Karlsson <magnus.karlsson@intel.com>
Date: Fri, 29 Oct 2021 11:01:11 +0200
Subject: libbpf: Deprecate AF_XDP support
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Deprecate AF_XDP support in libbpf ([0]). This has been moved to
libxdp as it is a better fit for that library. The AF_XDP support only
uses the public libbpf functions and can therefore just use libbpf as
a library from libxdp. The libxdp APIs are exactly the same so it
should just be linking with libxdp instead of libbpf for the AF_XDP
functionality. If not, please submit a bug report. Linking with both
libraries is supported but make sure you link in the correct order so
that the new functions in libxdp are used instead of the deprecated
ones in libbpf.

Libxdp can be found at https://github.com/xdp-project/xdp-tools.

  [0] Closes: https://github.com/libbpf/libbpf/issues/270

Signed-off-by: Magnus Karlsson <magnus.karlsson@intel.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Acked-by: Toke Høiland-Jørgensen <toke@redhat.com>
Link: https://lore.kernel.org/bpf/20211029090111.4733-1-magnus.karlsson@gmail.com
---
 tools/lib/bpf/xsk.h | 90 +++++++++++++++++++++++++++++++----------------------
 1 file changed, 52 insertions(+), 38 deletions(-)

(limited to 'tools')

diff --git a/tools/lib/bpf/xsk.h b/tools/lib/bpf/xsk.h
index 01c12dca9c10..64e9c57fd792 100644
--- a/tools/lib/bpf/xsk.h
+++ b/tools/lib/bpf/xsk.h
@@ -23,6 +23,12 @@
 extern "C" {
 #endif
 
+/* This whole API has been deprecated and moved to libxdp that can be found at
+ * https://github.com/xdp-project/xdp-tools. The APIs are exactly the same so
+ * it should just be linking with libxdp instead of libbpf for this set of
+ * functionality. If not, please submit a bug report on the aforementioned page.
+ */
+
 /* Load-Acquire Store-Release barriers used by the XDP socket
  * library. The following macros should *NOT* be considered part of
  * the xsk.h API, and is subject to change anytime.
@@ -245,8 +251,10 @@ static inline __u64 xsk_umem__add_offset_to_addr(__u64 addr)
 	return xsk_umem__extract_addr(addr) + xsk_umem__extract_offset(addr);
 }
 
-LIBBPF_API int xsk_umem__fd(const struct xsk_umem *umem);
-LIBBPF_API int xsk_socket__fd(const struct xsk_socket *xsk);
+LIBBPF_API LIBBPF_DEPRECATED_SINCE(0, 7, "AF_XDP support deprecated and moved to libxdp")
+int xsk_umem__fd(const struct xsk_umem *umem);
+LIBBPF_API LIBBPF_DEPRECATED_SINCE(0, 7, "AF_XDP support deprecated and moved to libxdp")
+int xsk_socket__fd(const struct xsk_socket *xsk);
 
 #define XSK_RING_CONS__DEFAULT_NUM_DESCS      2048
 #define XSK_RING_PROD__DEFAULT_NUM_DESCS      2048
@@ -263,10 +271,10 @@ struct xsk_umem_config {
 	__u32 flags;
 };
 
-LIBBPF_API int xsk_setup_xdp_prog(int ifindex,
-				  int *xsks_map_fd);
-LIBBPF_API int xsk_socket__update_xskmap(struct xsk_socket *xsk,
-					 int xsks_map_fd);
+LIBBPF_API LIBBPF_DEPRECATED_SINCE(0, 7, "AF_XDP support deprecated and moved to libxdp")
+int xsk_setup_xdp_prog(int ifindex, int *xsks_map_fd);
+LIBBPF_API LIBBPF_DEPRECATED_SINCE(0, 7, "AF_XDP support deprecated and moved to libxdp")
+int xsk_socket__update_xskmap(struct xsk_socket *xsk, int xsks_map_fd);
 
 /* Flags for the libbpf_flags field. */
 #define XSK_LIBBPF_FLAGS__INHIBIT_PROG_LOAD (1 << 0)
@@ -280,40 +288,46 @@ struct xsk_socket_config {
 };
 
 /* Set config to NULL to get the default configuration. */
-LIBBPF_API int xsk_umem__create(struct xsk_umem **umem,
-				void *umem_area, __u64 size,
-				struct xsk_ring_prod *fill,
-				struct xsk_ring_cons *comp,
-				const struct xsk_umem_config *config);
-LIBBPF_API int xsk_umem__create_v0_0_2(struct xsk_umem **umem,
-				       void *umem_area, __u64 size,
-				       struct xsk_ring_prod *fill,
-				       struct xsk_ring_cons *comp,
-				       const struct xsk_umem_config *config);
-LIBBPF_API int xsk_umem__create_v0_0_4(struct xsk_umem **umem,
-				       void *umem_area, __u64 size,
-				       struct xsk_ring_prod *fill,
-				       struct xsk_ring_cons *comp,
-				       const struct xsk_umem_config *config);
-LIBBPF_API int xsk_socket__create(struct xsk_socket **xsk,
-				  const char *ifname, __u32 queue_id,
-				  struct xsk_umem *umem,
-				  struct xsk_ring_cons *rx,
-				  struct xsk_ring_prod *tx,
-				  const struct xsk_socket_config *config);
-LIBBPF_API int
-xsk_socket__create_shared(struct xsk_socket **xsk_ptr,
-			  const char *ifname,
-			  __u32 queue_id, struct xsk_umem *umem,
-			  struct xsk_ring_cons *rx,
-			  struct xsk_ring_prod *tx,
-			  struct xsk_ring_prod *fill,
-			  struct xsk_ring_cons *comp,
-			  const struct xsk_socket_config *config);
+LIBBPF_API LIBBPF_DEPRECATED_SINCE(0, 7, "AF_XDP support deprecated and moved to libxdp")
+int xsk_umem__create(struct xsk_umem **umem,
+		     void *umem_area, __u64 size,
+		     struct xsk_ring_prod *fill,
+		     struct xsk_ring_cons *comp,
+		     const struct xsk_umem_config *config);
+LIBBPF_API LIBBPF_DEPRECATED_SINCE(0, 7, "AF_XDP support deprecated and moved to libxdp")
+int xsk_umem__create_v0_0_2(struct xsk_umem **umem,
+			    void *umem_area, __u64 size,
+			    struct xsk_ring_prod *fill,
+			    struct xsk_ring_cons *comp,
+			    const struct xsk_umem_config *config);
+LIBBPF_API LIBBPF_DEPRECATED_SINCE(0, 7, "AF_XDP support deprecated and moved to libxdp")
+int xsk_umem__create_v0_0_4(struct xsk_umem **umem,
+			    void *umem_area, __u64 size,
+			    struct xsk_ring_prod *fill,
+			    struct xsk_ring_cons *comp,
+			    const struct xsk_umem_config *config);
+LIBBPF_API LIBBPF_DEPRECATED_SINCE(0, 7, "AF_XDP support deprecated and moved to libxdp")
+int xsk_socket__create(struct xsk_socket **xsk,
+		       const char *ifname, __u32 queue_id,
+		       struct xsk_umem *umem,
+		       struct xsk_ring_cons *rx,
+		       struct xsk_ring_prod *tx,
+		       const struct xsk_socket_config *config);
+LIBBPF_API LIBBPF_DEPRECATED_SINCE(0, 7, "AF_XDP support deprecated and moved to libxdp")
+int xsk_socket__create_shared(struct xsk_socket **xsk_ptr,
+			      const char *ifname,
+			      __u32 queue_id, struct xsk_umem *umem,
+			      struct xsk_ring_cons *rx,
+			      struct xsk_ring_prod *tx,
+			      struct xsk_ring_prod *fill,
+			      struct xsk_ring_cons *comp,
+			      const struct xsk_socket_config *config);
 
 /* Returns 0 for success and -EBUSY if the umem is still in use. */
-LIBBPF_API int xsk_umem__delete(struct xsk_umem *umem);
-LIBBPF_API void xsk_socket__delete(struct xsk_socket *xsk);
+LIBBPF_API LIBBPF_DEPRECATED_SINCE(0, 7, "AF_XDP support deprecated and moved to libxdp")
+int xsk_umem__delete(struct xsk_umem *umem);
+LIBBPF_API LIBBPF_DEPRECATED_SINCE(0, 7, "AF_XDP support deprecated and moved to libxdp")
+void xsk_socket__delete(struct xsk_socket *xsk);
 
 #ifdef __cplusplus
 } /* extern "C" */
-- 
cgit v1.2.3


From f86ca07eb5310a1bdc7032458c7f76862f5a1552 Mon Sep 17 00:00:00 2001
From: James Prestwood <prestwoj@gmail.com>
Date: Mon, 1 Nov 2021 10:36:30 -0700
Subject: selftests: net: add arp_ndisc_evict_nocarrier

This tests the sysctl options for ARP/ND:

/net/ipv4/conf/<iface>/arp_evict_nocarrier
/net/ipv4/conf/all/arp_evict_nocarrier
/net/ipv6/conf/<iface>/ndisc_evict_nocarrier
/net/ipv6/conf/all/ndisc_evict_nocarrier

Signed-off-by: James Prestwood <prestwoj@gmail.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../selftests/net/arp_ndisc_evict_nocarrier.sh     | 220 +++++++++++++++++++++
 1 file changed, 220 insertions(+)
 create mode 100755 tools/testing/selftests/net/arp_ndisc_evict_nocarrier.sh

(limited to 'tools')

diff --git a/tools/testing/selftests/net/arp_ndisc_evict_nocarrier.sh b/tools/testing/selftests/net/arp_ndisc_evict_nocarrier.sh
new file mode 100755
index 000000000000..b5af08af8559
--- /dev/null
+++ b/tools/testing/selftests/net/arp_ndisc_evict_nocarrier.sh
@@ -0,0 +1,220 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+#
+# Tests sysctl options {arp,ndisc}_evict_nocarrier={0,1}
+#
+# Create a veth pair and set IPs/routes on both. Then ping to establish
+# an entry in the ARP/ND table. Depending on the test set sysctl option to
+# 1 or 0. Set remote veth down which will cause local veth to go into a no
+# carrier state. Depending on the test check the ARP/ND table:
+#
+# {arp,ndisc}_evict_nocarrier=1 should contain no ARP/ND after no carrier
+# {arp,ndisc}_evict_nocarrer=0 should still contain the single ARP/ND entry
+#
+
+readonly PEER_NS="ns-peer-$(mktemp -u XXXXXX)"
+readonly V4_ADDR0=10.0.10.1
+readonly V4_ADDR1=10.0.10.2
+readonly V6_ADDR0=2001:db8:91::1
+readonly V6_ADDR1=2001:db8:91::2
+nsid=100
+
+cleanup_v6()
+{
+    ip netns del me
+    ip netns del peer
+
+    sysctl -w net.ipv4.conf.veth0.ndisc_evict_nocarrier=1 >/dev/null 2>&1
+    sysctl -w net.ipv4.conf.all.ndisc_evict_nocarrier=1 >/dev/null 2>&1
+}
+
+create_ns()
+{
+    local n=${1}
+
+    ip netns del ${n} 2>/dev/null
+
+    ip netns add ${n}
+    ip netns set ${n} $((nsid++))
+    ip -netns ${n} link set lo up
+}
+
+
+setup_v6() {
+    create_ns me
+    create_ns peer
+
+    IP="ip -netns me"
+
+    $IP li add veth1 type veth peer name veth2
+    $IP li set veth1 up
+    $IP -6 addr add $V6_ADDR0/64 dev veth1 nodad
+    $IP li set veth2 netns peer up
+    ip -netns peer -6 addr add $V6_ADDR1/64 dev veth2 nodad
+
+    ip netns exec me sysctl -w $1 >/dev/null 2>&1
+
+    # Establish an ND cache entry
+    ip netns exec me ping -6 -c1 -Iveth1 $V6_ADDR1 >/dev/null 2>&1
+    # Should have the veth1 entry in ND table
+    ip netns exec me ip -6 neigh get $V6_ADDR1 dev veth1 >/dev/null 2>&1
+    if [ $? -ne 0 ]; then
+        cleanup_v6
+        echo "failed"
+        exit
+    fi
+
+    # Set veth2 down, which will put veth1 in NOCARRIER state
+    ip netns exec peer ip link set veth2 down
+}
+
+setup_v4() {
+    ip netns add "${PEER_NS}"
+    ip link add name veth0 type veth peer name veth1
+    ip link set dev veth0 up
+    ip link set dev veth1 netns "${PEER_NS}"
+    ip netns exec "${PEER_NS}" ip link set dev veth1 up
+    ip addr add $V4_ADDR0/24 dev veth0
+    ip netns exec "${PEER_NS}" ip addr add $V4_ADDR1/24 dev veth1
+    ip netns exec ${PEER_NS} ip route add default via $V4_ADDR1 dev veth1
+    ip route add default via $V4_ADDR0 dev veth0
+
+    sysctl -w "$1" >/dev/null 2>&1
+
+    # Establish an ARP cache entry
+    ping -c1 -I veth0 $V4_ADDR1 -q >/dev/null 2>&1
+    # Should have the veth1 entry in ARP table
+    ip neigh get $V4_ADDR1 dev veth0 >/dev/null 2>&1
+    if [ $? -ne 0 ]; then
+        cleanup_v4
+        echo "failed"
+        exit
+    fi
+
+    # Set veth1 down, which will put veth0 in NOCARRIER state
+    ip netns exec "${PEER_NS}" ip link set veth1 down
+}
+
+cleanup_v4() {
+    ip neigh flush dev veth0
+    ip link del veth0
+    local -r ns="$(ip netns list|grep $PEER_NS)"
+    [ -n "$ns" ] && ip netns del $ns 2>/dev/null
+
+    sysctl -w net.ipv4.conf.veth0.arp_evict_nocarrier=1 >/dev/null 2>&1
+    sysctl -w net.ipv4.conf.all.arp_evict_nocarrier=1 >/dev/null 2>&1
+}
+
+# Run test when arp_evict_nocarrier = 1 (default).
+run_arp_evict_nocarrier_enabled() {
+    echo "run arp_evict_nocarrier=1 test"
+    setup_v4 "net.ipv4.conf.veth0.arp_evict_nocarrier=1"
+
+    # ARP table should be empty
+    ip neigh get $V4_ADDR1 dev veth0 >/dev/null 2>&1
+
+    if [ $? -eq 0 ];then
+        echo "failed"
+    else
+        echo "ok"
+    fi
+
+    cleanup_v4
+}
+
+# Run test when arp_evict_nocarrier = 0
+run_arp_evict_nocarrier_disabled() {
+    echo "run arp_evict_nocarrier=0 test"
+    setup_v4 "net.ipv4.conf.veth0.arp_evict_nocarrier=0"
+
+    # ARP table should still contain the entry
+    ip neigh get $V4_ADDR1 dev veth0 >/dev/null 2>&1
+
+    if [ $? -eq 0 ];then
+        echo "ok"
+    else
+        echo "failed"
+    fi
+
+    cleanup_v4
+}
+
+run_arp_evict_nocarrier_disabled_all() {
+    echo "run all.arp_evict_nocarrier=0 test"
+    setup_v4 "net.ipv4.conf.all.arp_evict_nocarrier=0"
+
+    # ARP table should still contain the entry
+    ip neigh get $V4_ADDR1 dev veth0 >/dev/null 2>&1
+
+    if [ $? -eq 0 ];then
+        echo "ok"
+    else
+        echo "failed"
+    fi
+
+    cleanup_v4
+}
+
+run_ndisc_evict_nocarrier_enabled() {
+    echo "run ndisc_evict_nocarrier=1 test"
+
+    setup_v6 "net.ipv6.conf.veth1.ndisc_evict_nocarrier=1"
+
+    ip netns exec me ip -6 neigh get $V6_ADDR1 dev veth1 >/dev/null 2>&1
+
+    if [ $? -eq 0 ];then
+        echo "failed"
+    else
+        echo "ok"
+    fi
+
+    cleanup_v6
+}
+
+run_ndisc_evict_nocarrier_disabled() {
+    echo "run ndisc_evict_nocarrier=0 test"
+
+    setup_v6 "net.ipv6.conf.veth1.ndisc_evict_nocarrier=0"
+
+    ip netns exec me ip -6 neigh get $V6_ADDR1 dev veth1 >/dev/null 2>&1
+
+    if [ $? -eq 0 ];then
+        echo "ok"
+    else
+        echo "failed"
+    fi
+
+    cleanup_v6
+}
+
+run_ndisc_evict_nocarrier_disabled_all() {
+    echo "run all.ndisc_evict_nocarrier=0 test"
+
+    setup_v6 "net.ipv6.conf.all.ndisc_evict_nocarrier=0"
+
+    ip netns exec me ip -6 neigh get $V6_ADDR1 dev veth1 >/dev/null 2>&1
+
+    if [ $? -eq 0 ];then
+        echo "ok"
+    else
+        echo "failed"
+    fi
+
+    cleanup_v6
+}
+
+run_all_tests() {
+    run_arp_evict_nocarrier_enabled
+    run_arp_evict_nocarrier_disabled
+    run_arp_evict_nocarrier_disabled_all
+    run_ndisc_evict_nocarrier_enabled
+    run_ndisc_evict_nocarrier_disabled
+    run_ndisc_evict_nocarrier_disabled_all
+}
+
+if [ "$(id -u)" -ne 0 ];then
+	echo "SKIP: Need root privileges"
+	exit $ksft_skip;
+fi
+
+run_all_tests
-- 
cgit v1.2.3