From dd399ac9e343c7573c47d6820e4a23013c54749d Mon Sep 17 00:00:00 2001
From: Luca Boccassi
Date: Thu, 28 Mar 2019 11:33:53 +0000
Subject: tools/bpf: generate pkg-config file for libbpf

Generate a libbpf.pc file at build time so that users can rely
on pkg-config to find the library, its CFLAGS and LDFLAGS.

Signed-off-by: Luca Boccassi <bluca@debian.org>
Acked-by: Andrey Ignatov <rdna@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/lib/bpf/.gitignore         |  1 +
 tools/lib/bpf/Makefile           | 18 +++++++++++++++---
 tools/lib/bpf/libbpf.pc.template | 12 ++++++++++++
 3 files changed, 28 insertions(+), 3 deletions(-)
 create mode 100644 tools/lib/bpf/libbpf.pc.template

diff --git a/tools/lib/bpf/.gitignore b/tools/lib/bpf/.gitignore
index 4db74758c674..7d9e182a1f51 100644
--- a/tools/lib/bpf/.gitignore
+++ b/tools/lib/bpf/.gitignore
@@ -1,3 +1,4 @@
 libbpf_version.h
+libbpf.pc
 FEATURE-DUMP.libbpf
 test_libbpf
diff --git a/tools/lib/bpf/Makefile b/tools/lib/bpf/Makefile
index 5bf8e52c41fc..2a578bfc0bca 100644
--- a/tools/lib/bpf/Makefile
+++ b/tools/lib/bpf/Makefile
@@ -90,6 +90,7 @@ LIBBPF_VERSION	= $(BPF_VERSION).$(BPF_PATCHLEVEL).$(BPF_EXTRAVERSION)
 
 LIB_TARGET	= libbpf.a libbpf.so.$(LIBBPF_VERSION)
 LIB_FILE	= libbpf.a libbpf.so*
+PC_FILE		= libbpf.pc
 
 # Set compile option CFLAGS
 ifdef EXTRA_CFLAGS
@@ -134,13 +135,14 @@ VERSION_SCRIPT	:= libbpf.map
 
 LIB_TARGET	:= $(addprefix $(OUTPUT),$(LIB_TARGET))
 LIB_FILE	:= $(addprefix $(OUTPUT),$(LIB_FILE))
+PC_FILE		:= $(addprefix $(OUTPUT),$(PC_FILE))
 
 GLOBAL_SYM_COUNT = $(shell readelf -s --wide $(BPF_IN) | \
 			   awk '/GLOBAL/ && /DEFAULT/ && !/UND/ {s++} END{print s}')
 VERSIONED_SYM_COUNT = $(shell readelf -s --wide $(OUTPUT)libbpf.so | \
 			      grep -Eo '[^ ]+@LIBBPF_' | cut -d@ -f1 | sort -u | wc -l)
 
-CMD_TARGETS = $(LIB_TARGET)
+CMD_TARGETS = $(LIB_TARGET) $(PC_FILE)
 
 CXX_TEST_TARGET = $(OUTPUT)test_libbpf
 
@@ -187,6 +189,12 @@ $(OUTPUT)libbpf.a: $(BPF_IN)
 $(OUTPUT)test_libbpf: test_libbpf.cpp $(OUTPUT)libbpf.a
 	$(QUIET_LINK)$(CXX) $(INCLUDES) $^ -lelf -o $@
 
+$(OUTPUT)libbpf.pc:
+	$(QUIET_GEN)sed -e "s|@PREFIX@|$(prefix)|" \
+		-e "s|@LIBDIR@|$(libdir_SQ)|" \
+		-e "s|@VERSION@|$(LIBBPF_VERSION)|" \
+		< libbpf.pc.template > $@
+
 check: check_abi
 
 check_abi: $(OUTPUT)libbpf.so
@@ -223,7 +231,11 @@ install_headers:
 		$(call do_install,libbpf.h,$(prefix)/include/bpf,644);
 		$(call do_install,btf.h,$(prefix)/include/bpf,644);
 
-install: install_lib
+install_pkgconfig: $(PC_FILE)
+	$(call QUIET_INSTALL, $(PC_FILE)) \
+		$(call do_install,$(PC_FILE),$(libdir_SQ)/pkgconfig,644)
+
+install: install_lib install_pkgconfig
 
 ### Cleaning rules
 
@@ -233,7 +245,7 @@ config-clean:
 
 clean:
 	$(call QUIET_CLEAN, libbpf) $(RM) $(TARGETS) $(CXX_TEST_TARGET) \
-		*.o *~ *.a *.so *.so.$(VERSION) .*.d .*.cmd LIBBPF-CFLAGS
+		*.o *~ *.a *.so *.so.$(VERSION) .*.d .*.cmd *.pc LIBBPF-CFLAGS
 	$(call QUIET_CLEAN, core-gen) $(RM) $(OUTPUT)FEATURE-DUMP.libbpf
 
 
diff --git a/tools/lib/bpf/libbpf.pc.template b/tools/lib/bpf/libbpf.pc.template
new file mode 100644
index 000000000000..ac17fcef2108
--- /dev/null
+++ b/tools/lib/bpf/libbpf.pc.template
@@ -0,0 +1,12 @@
+# SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause)
+
+prefix=@PREFIX@
+libdir=@LIBDIR@
+includedir=${prefix}/include
+
+Name: libbpf
+Description: BPF library
+Version: @VERSION@
+Libs: -L${libdir} -lbpf
+Requires.private: libelf
+Cflags: -I${includedir}
-- 
cgit v1.2.3-55-g7522


From 2011fccfb61bbd1d7c8864b2b3ed7012342e9ba3 Mon Sep 17 00:00:00 2001
From: Andrey Ignatov
Date: Thu, 28 Mar 2019 18:01:57 -0700
Subject: bpf: Support variable offset stack access from helpers

Currently there is a difference in how verifier checks memory access for
helper arguments for PTR_TO_MAP_VALUE and PTR_TO_STACK with regard to
variable part of offset.

check_map_access, that is used for PTR_TO_MAP_VALUE, can handle variable
offsets just fine, so that BPF program can call a helper like this:

  some_helper(map_value_ptr + off, size);

, where offset is unknown at load time, but is checked by program to be
in a safe rage (off >= 0 && off + size < map_value_size).

But it's not the case for check_stack_boundary, that is used for
PTR_TO_STACK, and same code with pointer to stack is rejected by
verifier:

  some_helper(stack_value_ptr + off, size);

For example:
  0: (7a) *(u64 *)(r10 -16) = 0
  1: (7a) *(u64 *)(r10 -8) = 0
  2: (61) r2 = *(u32 *)(r1 +0)
  3: (57) r2 &= 4
  4: (17) r2 -= 16
  5: (0f) r2 += r10
  6: (18) r1 = 0xffff888111343a80
  8: (85) call bpf_map_lookup_elem#1
  invalid variable stack read R2 var_off=(0xfffffffffffffff0; 0x4)

Add support for variable offset access to check_stack_boundary so that
if offset is checked by program to be in a safe range it's accepted by
verifier.

Signed-off-by: Andrey Ignatov <rdna@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 kernel/bpf/verifier.c | 75 ++++++++++++++++++++++++++++++++++++---------------
 1 file changed, 54 insertions(+), 21 deletions(-)

diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 2fe89138309a..87221fda1321 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -2157,6 +2157,29 @@ static int check_xadd(struct bpf_verifier_env *env, int insn_idx, struct bpf_ins
 				BPF_SIZE(insn->code), BPF_WRITE, -1, true);
 }
 
+static int __check_stack_boundary(struct bpf_verifier_env *env, u32 regno,
+				  int off, int access_size,
+				  bool zero_size_allowed)
+{
+	struct bpf_reg_state *reg = reg_state(env, regno);
+
+	if (off >= 0 || off < -MAX_BPF_STACK || off + access_size > 0 ||
+	    access_size < 0 || (access_size == 0 && !zero_size_allowed)) {
+		if (tnum_is_const(reg->var_off)) {
+			verbose(env, "invalid stack type R%d off=%d access_size=%d\n",
+				regno, off, access_size);
+		} else {
+			char tn_buf[48];
+
+			tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off);
+			verbose(env, "invalid stack type R%d var_off=%s access_size=%d\n",
+				regno, tn_buf, access_size);
+		}
+		return -EACCES;
+	}
+	return 0;
+}
+
 /* when register 'regno' is passed into function that will read 'access_size'
  * bytes from that pointer, make sure that it's within stack boundary
  * and all elements of stack are initialized.
@@ -2169,7 +2192,7 @@ static int check_stack_boundary(struct bpf_verifier_env *env, int regno,
 {
 	struct bpf_reg_state *reg = reg_state(env, regno);
 	struct bpf_func_state *state = func(env, reg);
-	int off, i, slot, spi;
+	int err, min_off, max_off, i, slot, spi;
 
 	if (reg->type != PTR_TO_STACK) {
 		/* Allow zero-byte read from NULL, regardless of pointer type */
@@ -2183,21 +2206,23 @@ static int check_stack_boundary(struct bpf_verifier_env *env, int regno,
 		return -EACCES;
 	}
 
-	/* Only allow fixed-offset stack reads */
-	if (!tnum_is_const(reg->var_off)) {
-		char tn_buf[48];
-
-		tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off);
-		verbose(env, "invalid variable stack read R%d var_off=%s\n",
-			regno, tn_buf);
-		return -EACCES;
-	}
-	off = reg->off + reg->var_off.value;
-	if (off >= 0 || off < -MAX_BPF_STACK || off + access_size > 0 ||
-	    access_size < 0 || (access_size == 0 && !zero_size_allowed)) {
-		verbose(env, "invalid stack type R%d off=%d access_size=%d\n",
-			regno, off, access_size);
-		return -EACCES;
+	if (tnum_is_const(reg->var_off)) {
+		min_off = max_off = reg->var_off.value + reg->off;
+		err = __check_stack_boundary(env, regno, min_off, access_size,
+					     zero_size_allowed);
+		if (err)
+			return err;
+	} else {
+		min_off = reg->smin_value + reg->off;
+		max_off = reg->umax_value + reg->off;
+		err = __check_stack_boundary(env, regno, min_off, access_size,
+					     zero_size_allowed);
+		if (err)
+			return err;
+		err = __check_stack_boundary(env, regno, max_off, access_size,
+					     zero_size_allowed);
+		if (err)
+			return err;
 	}
 
 	if (meta && meta->raw_mode) {
@@ -2206,10 +2231,10 @@ static int check_stack_boundary(struct bpf_verifier_env *env, int regno,
 		return 0;
 	}
 
-	for (i = 0; i < access_size; i++) {
+	for (i = min_off; i < max_off + access_size; i++) {
 		u8 *stype;
 
-		slot = -(off + i) - 1;
+		slot = -i - 1;
 		spi = slot / BPF_REG_SIZE;
 		if (state->allocated_stack <= slot)
 			goto err;
@@ -2222,8 +2247,16 @@ static int check_stack_boundary(struct bpf_verifier_env *env, int regno,
 			goto mark;
 		}
 err:
-		verbose(env, "invalid indirect read from stack off %d+%d size %d\n",
-			off, i, access_size);
+		if (tnum_is_const(reg->var_off)) {
+			verbose(env, "invalid indirect read from stack off %d+%d size %d\n",
+				min_off, i - min_off, access_size);
+		} else {
+			char tn_buf[48];
+
+			tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off);
+			verbose(env, "invalid indirect read from stack var_off %s+%d size %d\n",
+				tn_buf, i - min_off, access_size);
+		}
 		return -EACCES;
 mark:
 		/* reading any byte out of 8-byte 'spill_slot' will cause
@@ -2232,7 +2265,7 @@ mark:
 		mark_reg_read(env, &state->stack[spi].spilled_ptr,
 			      state->stack[spi].spilled_ptr.parent);
 	}
-	return update_stack_depth(env, state, off);
+	return update_stack_depth(env, state, min_off);
 }
 
 static int check_helper_mem_access(struct bpf_verifier_env *env, int regno,
-- 
cgit v1.2.3-55-g7522


From 8ff80e96e3ccea5ff0a890d4f18997e0344dbec2 Mon Sep 17 00:00:00 2001
From: Andrey Ignatov
Date: Thu, 28 Mar 2019 18:01:58 -0700
Subject: selftests/bpf: Test variable offset stack access

Test different scenarios of indirect variable-offset stack access: out of
bound access (>0), min_off below initialized part of the stack,
max_off+size above initialized part of the stack, initialized stack.

Example of output:
  ...
  #856/p indirect variable-offset stack access, out of bound OK
  #857/p indirect variable-offset stack access, max_off+size > max_initialized OK
  #858/p indirect variable-offset stack access, min_off < min_initialized OK
  #859/p indirect variable-offset stack access, ok OK
  ...

Signed-off-by: Andrey Ignatov <rdna@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/testing/selftests/bpf/verifier/var_off.c | 79 +++++++++++++++++++++++++-
 1 file changed, 77 insertions(+), 2 deletions(-)

diff --git a/tools/testing/selftests/bpf/verifier/var_off.c b/tools/testing/selftests/bpf/verifier/var_off.c
index 1e536ff121a5..c4ebd0bb0781 100644
--- a/tools/testing/selftests/bpf/verifier/var_off.c
+++ b/tools/testing/selftests/bpf/verifier/var_off.c
@@ -40,7 +40,7 @@
 	.prog_type = BPF_PROG_TYPE_LWT_IN,
 },
 {
-	"indirect variable-offset stack access",
+	"indirect variable-offset stack access, out of bound",
 	.insns = {
 	/* Fill the top 8 bytes of the stack */
 	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
@@ -60,7 +60,82 @@
 	BPF_EXIT_INSN(),
 	},
 	.fixup_map_hash_8b = { 5 },
-	.errstr = "variable stack read R2",
+	.errstr = "invalid stack type R2 var_off",
 	.result = REJECT,
 	.prog_type = BPF_PROG_TYPE_LWT_IN,
 },
+{
+	"indirect variable-offset stack access, max_off+size > max_initialized",
+	.insns = {
+	/* Fill only the second from top 8 bytes of the stack. */
+	BPF_ST_MEM(BPF_DW, BPF_REG_10, -16, 0),
+	/* Get an unknown value. */
+	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, 0),
+	/* Make it small and 4-byte aligned. */
+	BPF_ALU64_IMM(BPF_AND, BPF_REG_2, 4),
+	BPF_ALU64_IMM(BPF_SUB, BPF_REG_2, 16),
+	/* Add it to fp.  We now have either fp-12 or fp-16, but we don't know
+	 * which. fp-12 size 8 is partially uninitialized stack.
+	 */
+	BPF_ALU64_REG(BPF_ADD, BPF_REG_2, BPF_REG_10),
+	/* Dereference it indirectly. */
+	BPF_LD_MAP_FD(BPF_REG_1, 0),
+	BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	},
+	.fixup_map_hash_8b = { 5 },
+	.errstr = "invalid indirect read from stack var_off",
+	.result = REJECT,
+	.prog_type = BPF_PROG_TYPE_LWT_IN,
+},
+{
+	"indirect variable-offset stack access, min_off < min_initialized",
+	.insns = {
+	/* Fill only the top 8 bytes of the stack. */
+	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
+	/* Get an unknown value */
+	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, 0),
+	/* Make it small and 4-byte aligned. */
+	BPF_ALU64_IMM(BPF_AND, BPF_REG_2, 4),
+	BPF_ALU64_IMM(BPF_SUB, BPF_REG_2, 16),
+	/* Add it to fp.  We now have either fp-12 or fp-16, but we don't know
+	 * which. fp-16 size 8 is partially uninitialized stack.
+	 */
+	BPF_ALU64_REG(BPF_ADD, BPF_REG_2, BPF_REG_10),
+	/* Dereference it indirectly. */
+	BPF_LD_MAP_FD(BPF_REG_1, 0),
+	BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	},
+	.fixup_map_hash_8b = { 5 },
+	.errstr = "invalid indirect read from stack var_off",
+	.result = REJECT,
+	.prog_type = BPF_PROG_TYPE_LWT_IN,
+},
+{
+	"indirect variable-offset stack access, ok",
+	.insns = {
+	/* Fill the top 16 bytes of the stack. */
+	BPF_ST_MEM(BPF_DW, BPF_REG_10, -16, 0),
+	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
+	/* Get an unknown value. */
+	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, 0),
+	/* Make it small and 4-byte aligned. */
+	BPF_ALU64_IMM(BPF_AND, BPF_REG_2, 4),
+	BPF_ALU64_IMM(BPF_SUB, BPF_REG_2, 16),
+	/* Add it to fp.  We now have either fp-12 or fp-16, we don't know
+	 * which, but either way it points to initialized stack.
+	 */
+	BPF_ALU64_REG(BPF_ADD, BPF_REG_2, BPF_REG_10),
+	/* Dereference it indirectly. */
+	BPF_LD_MAP_FD(BPF_REG_1, 0),
+	BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	},
+	.fixup_map_hash_8b = { 6 },
+	.result = ACCEPT,
+	.prog_type = BPF_PROG_TYPE_LWT_IN,
+},
-- 
cgit v1.2.3-55-g7522


From 9de2640b06ecf0e6ef4b24b07a5573a2804d77d0 Mon Sep 17 00:00:00 2001
From: Yonghong Song
Date: Thu, 28 Mar 2019 22:30:53 -0700
Subject: bpf: add bpffs multi-dimensional array tests in test_btf

For multiple dimensional arrays like below,
  int a[2][3]
both llvm and pahole generated one BTF_KIND_ARRAY type like
  . element_type: int
  . index_type: unsigned int
  . number of elements: 6

Such a collapsed BTF_KIND_ARRAY type will cause the divergence
in BTF vs. the user code. In the compile-once-run-everywhere
project, the header file is generated from BTF and used for bpf
program, and the definition in the header file will be different
from what user expects.

But the kernel actually supports chained multi-dimensional array
types properly. The above "int a[2][3]" can be represented as
  Type #n:
    . element_type: int
    . index_type: unsigned int
    . number of elements: 3
  Type #(n+1):
    . element_type: type #n
    . index_type: unsigned int
    . number of elements: 2

The following llvm commit
  https://reviews.llvm.org/rL357215
also enables llvm to generated proper chained multi-dimensional arrays.

The test_btf already has a raw test ("struct test #1") for chained
multi-dimensional arrays. This patch added amended bpffs test for
chained multi-dimensional arrays.

Acked-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/testing/selftests/bpf/test_btf.c | 32 ++++++++++++++++++++++++--------
 1 file changed, 24 insertions(+), 8 deletions(-)

diff --git a/tools/testing/selftests/bpf/test_btf.c b/tools/testing/selftests/bpf/test_btf.c
index 23e3b314ca60..5afc3f7dff81 100644
--- a/tools/testing/selftests/bpf/test_btf.c
+++ b/tools/testing/selftests/bpf/test_btf.c
@@ -3677,6 +3677,7 @@ struct pprint_mapv {
 	} aenum;
 	uint32_t ui32b;
 	uint32_t bits2c:2;
+	uint8_t si8_4[2][2];
 };
 
 #ifdef __SIZEOF_INT128__
@@ -3729,7 +3730,7 @@ static struct btf_raw_test pprint_test_template[] = {
 		BTF_ENUM_ENC(NAME_TBD, 2),
 		BTF_ENUM_ENC(NAME_TBD, 3),
 		/* struct pprint_mapv */		/* [16] */
-		BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_STRUCT, 0, 10), 40),
+		BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_STRUCT, 0, 11), 40),
 		BTF_MEMBER_ENC(NAME_TBD, 11, 0),	/* uint32_t ui32 */
 		BTF_MEMBER_ENC(NAME_TBD, 10, 32),	/* uint16_t ui16 */
 		BTF_MEMBER_ENC(NAME_TBD, 12, 64),	/* int32_t si32 */
@@ -3740,9 +3741,12 @@ static struct btf_raw_test pprint_test_template[] = {
 		BTF_MEMBER_ENC(NAME_TBD, 15, 192),	/* aenum */
 		BTF_MEMBER_ENC(NAME_TBD, 11, 224),	/* uint32_t ui32b */
 		BTF_MEMBER_ENC(NAME_TBD, 6, 256),	/* bits2c */
+		BTF_MEMBER_ENC(NAME_TBD, 17, 264),	/* si8_4 */
+		BTF_TYPE_ARRAY_ENC(18, 1, 2),		/* [17] */
+		BTF_TYPE_ARRAY_ENC(1, 1, 2),		/* [18] */
 		BTF_END_RAW,
 	},
-	BTF_STR_SEC("\0unsigned char\0unsigned short\0unsigned int\0int\0unsigned long long\0uint8_t\0uint16_t\0uint32_t\0int32_t\0uint64_t\0ui64\0ui8a\0ENUM_ZERO\0ENUM_ONE\0ENUM_TWO\0ENUM_THREE\0pprint_mapv\0ui32\0ui16\0si32\0unused_bits2a\0bits28\0unused_bits2b\0aenum\0ui32b\0bits2c"),
+	BTF_STR_SEC("\0unsigned char\0unsigned short\0unsigned int\0int\0unsigned long long\0uint8_t\0uint16_t\0uint32_t\0int32_t\0uint64_t\0ui64\0ui8a\0ENUM_ZERO\0ENUM_ONE\0ENUM_TWO\0ENUM_THREE\0pprint_mapv\0ui32\0ui16\0si32\0unused_bits2a\0bits28\0unused_bits2b\0aenum\0ui32b\0bits2c\0si8_4"),
 	.key_size = sizeof(unsigned int),
 	.value_size = sizeof(struct pprint_mapv),
 	.key_type_id = 3,	/* unsigned int */
@@ -3791,7 +3795,7 @@ static struct btf_raw_test pprint_test_template[] = {
 		BTF_ENUM_ENC(NAME_TBD, 2),
 		BTF_ENUM_ENC(NAME_TBD, 3),
 		/* struct pprint_mapv */		/* [16] */
-		BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_STRUCT, 1, 10), 40),
+		BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_STRUCT, 1, 11), 40),
 		BTF_MEMBER_ENC(NAME_TBD, 11, BTF_MEMBER_OFFSET(0, 0)),	/* uint32_t ui32 */
 		BTF_MEMBER_ENC(NAME_TBD, 10, BTF_MEMBER_OFFSET(0, 32)),	/* uint16_t ui16 */
 		BTF_MEMBER_ENC(NAME_TBD, 12, BTF_MEMBER_OFFSET(0, 64)),	/* int32_t si32 */
@@ -3802,9 +3806,12 @@ static struct btf_raw_test pprint_test_template[] = {
 		BTF_MEMBER_ENC(NAME_TBD, 15, BTF_MEMBER_OFFSET(0, 192)),	/* aenum */
 		BTF_MEMBER_ENC(NAME_TBD, 11, BTF_MEMBER_OFFSET(0, 224)),	/* uint32_t ui32b */
 		BTF_MEMBER_ENC(NAME_TBD, 6, BTF_MEMBER_OFFSET(2, 256)),	/* bits2c */
+		BTF_MEMBER_ENC(NAME_TBD, 17, 264),	/* si8_4 */
+		BTF_TYPE_ARRAY_ENC(18, 1, 2),		/* [17] */
+		BTF_TYPE_ARRAY_ENC(1, 1, 2),		/* [18] */
 		BTF_END_RAW,
 	},
-	BTF_STR_SEC("\0unsigned char\0unsigned short\0unsigned int\0int\0unsigned long long\0uint8_t\0uint16_t\0uint32_t\0int32_t\0uint64_t\0ui64\0ui8a\0ENUM_ZERO\0ENUM_ONE\0ENUM_TWO\0ENUM_THREE\0pprint_mapv\0ui32\0ui16\0si32\0unused_bits2a\0bits28\0unused_bits2b\0aenum\0ui32b\0bits2c"),
+	BTF_STR_SEC("\0unsigned char\0unsigned short\0unsigned int\0int\0unsigned long long\0uint8_t\0uint16_t\0uint32_t\0int32_t\0uint64_t\0ui64\0ui8a\0ENUM_ZERO\0ENUM_ONE\0ENUM_TWO\0ENUM_THREE\0pprint_mapv\0ui32\0ui16\0si32\0unused_bits2a\0bits28\0unused_bits2b\0aenum\0ui32b\0bits2c\0si8_4"),
 	.key_size = sizeof(unsigned int),
 	.value_size = sizeof(struct pprint_mapv),
 	.key_type_id = 3,	/* unsigned int */
@@ -3855,7 +3862,7 @@ static struct btf_raw_test pprint_test_template[] = {
 		BTF_ENUM_ENC(NAME_TBD, 2),
 		BTF_ENUM_ENC(NAME_TBD, 3),
 		/* struct pprint_mapv */		/* [16] */
-		BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_STRUCT, 1, 10), 40),
+		BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_STRUCT, 1, 11), 40),
 		BTF_MEMBER_ENC(NAME_TBD, 11, BTF_MEMBER_OFFSET(0, 0)),	/* uint32_t ui32 */
 		BTF_MEMBER_ENC(NAME_TBD, 10, BTF_MEMBER_OFFSET(0, 32)),	/* uint16_t ui16 */
 		BTF_MEMBER_ENC(NAME_TBD, 12, BTF_MEMBER_OFFSET(0, 64)),	/* int32_t si32 */
@@ -3866,13 +3873,16 @@ static struct btf_raw_test pprint_test_template[] = {
 		BTF_MEMBER_ENC(NAME_TBD, 15, BTF_MEMBER_OFFSET(0, 192)),	/* aenum */
 		BTF_MEMBER_ENC(NAME_TBD, 11, BTF_MEMBER_OFFSET(0, 224)),	/* uint32_t ui32b */
 		BTF_MEMBER_ENC(NAME_TBD, 17, BTF_MEMBER_OFFSET(2, 256)),	/* bits2c */
+		BTF_MEMBER_ENC(NAME_TBD, 20, BTF_MEMBER_OFFSET(0, 264)),	/* si8_4 */
 		/* typedef unsigned int ___int */	/* [17] */
 		BTF_TYPEDEF_ENC(NAME_TBD, 18),
 		BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_VOLATILE, 0, 0), 6),	/* [18] */
 		BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_CONST, 0, 0), 15),	/* [19] */
+		BTF_TYPE_ARRAY_ENC(21, 1, 2),					/* [20] */
+		BTF_TYPE_ARRAY_ENC(1, 1, 2),					/* [21] */
 		BTF_END_RAW,
 	},
-	BTF_STR_SEC("\0unsigned char\0unsigned short\0unsigned int\0int\0unsigned long long\0uint8_t\0uint16_t\0uint32_t\0int32_t\0uint64_t\0ui64\0ui8a\0ENUM_ZERO\0ENUM_ONE\0ENUM_TWO\0ENUM_THREE\0pprint_mapv\0ui32\0ui16\0si32\0unused_bits2a\0bits28\0unused_bits2b\0aenum\0ui32b\0bits2c\0___int"),
+	BTF_STR_SEC("\0unsigned char\0unsigned short\0unsigned int\0int\0unsigned long long\0uint8_t\0uint16_t\0uint32_t\0int32_t\0uint64_t\0ui64\0ui8a\0ENUM_ZERO\0ENUM_ONE\0ENUM_TWO\0ENUM_THREE\0pprint_mapv\0ui32\0ui16\0si32\0unused_bits2a\0bits28\0unused_bits2b\0aenum\0ui32b\0bits2c\0___int\0si8_4"),
 	.key_size = sizeof(unsigned int),
 	.value_size = sizeof(struct pprint_mapv),
 	.key_type_id = 3,	/* unsigned int */
@@ -4007,6 +4017,10 @@ static void set_pprint_mapv(enum pprint_mapv_kind_t mapv_kind,
 			v->aenum = i & 0x03;
 			v->ui32b = 4;
 			v->bits2c = 1;
+			v->si8_4[0][0] = (cpu + i) & 0xff;
+			v->si8_4[0][1] = (cpu + i + 1) & 0xff;
+			v->si8_4[1][0] = (cpu + i + 2) & 0xff;
+			v->si8_4[1][1] = (cpu + i + 3) & 0xff;
 			v = (void *)v + rounded_value_size;
 		}
 	}
@@ -4040,7 +4054,7 @@ ssize_t get_pprint_expected_line(enum pprint_mapv_kind_t mapv_kind,
 		nexpected_line = snprintf(expected_line, line_size,
 					  "%s%u: {%u,0,%d,0x%x,0x%x,0x%x,"
 					  "{%lu|[%u,%u,%u,%u,%u,%u,%u,%u]},%s,"
-					  "%u,0x%x}\n",
+					  "%u,0x%x,[[%d,%d],[%d,%d]]}\n",
 					  percpu_map ? "\tcpu" : "",
 					  percpu_map ? cpu : next_key,
 					  v->ui32, v->si32,
@@ -4054,7 +4068,9 @@ ssize_t get_pprint_expected_line(enum pprint_mapv_kind_t mapv_kind,
 					  v->ui8a[6], v->ui8a[7],
 					  pprint_enum_str[v->aenum],
 					  v->ui32b,
-					  v->bits2c);
+					  v->bits2c,
+					  v->si8_4[0][0], v->si8_4[0][1],
+					  v->si8_4[1][0], v->si8_4[1][1]);
 	}
 
 #ifdef __SIZEOF_INT128__
-- 
cgit v1.2.3-55-g7522


From 6b7b6995c43e17f994c51c107740daedd948255a Mon Sep 17 00:00:00 2001
From: Stanislav Fomichev
Date: Tue, 2 Apr 2019 10:08:32 -0700
Subject: selftests: bpf: tests.h should depend on .c files, not the output

This makes sure we don't put headers as input files when doing
compilation, because clang complains about the following:

clang-9: error: cannot specify -o when generating multiple output files
../lib.mk:152: recipe for target 'xxx/tools/testing/selftests/bpf/test_verifier' failed
make: *** [xxx/tools/testing/selftests/bpf/test_verifier] Error 1
make: *** Waiting for unfinished jobs....
clang-9: error: cannot specify -o when generating multiple output files
../lib.mk:152: recipe for target 'xxx/tools/testing/selftests/bpf/test_progs' failed

Signed-off-by: Stanislav Fomichev <sdf@google.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/testing/selftests/bpf/Makefile | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index 77b73b892136..078283d073b0 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -209,7 +209,7 @@ ifeq ($(DWARF2BTF),y)
 endif
 
 PROG_TESTS_H := $(OUTPUT)/prog_tests/tests.h
-$(OUTPUT)/test_progs: $(PROG_TESTS_H)
+test_progs.c: $(PROG_TESTS_H)
 $(OUTPUT)/test_progs: CFLAGS += $(TEST_PROGS_CFLAGS)
 $(OUTPUT)/test_progs: prog_tests/*.c
 
@@ -232,7 +232,7 @@ $(PROG_TESTS_H): $(PROG_TESTS_DIR) $(PROG_TESTS_FILES)
 		 ) > $(PROG_TESTS_H))
 
 VERIFIER_TESTS_H := $(OUTPUT)/verifier/tests.h
-$(OUTPUT)/test_verifier: $(VERIFIER_TESTS_H)
+test_verifier.c: $(VERIFIER_TESTS_H)
 $(OUTPUT)/test_verifier: CFLAGS += $(TEST_VERIFIER_CFLAGS)
 
 VERIFIER_TESTS_DIR = $(OUTPUT)/verifier
-- 
cgit v1.2.3-55-g7522


From 94e8f3c7125a36c6cedf37c8838cb77c8a8d8cf9 Mon Sep 17 00:00:00 2001
From: Stanislav Fomichev
Date: Tue, 2 Apr 2019 10:08:33 -0700
Subject: selftests: bpf: fix -Wformat-security warning for
 flow_dissector_load.c

flow_dissector_load.c:55:19: warning: format string is not a string literal (potentially insecure)
      [-Wformat-security]
                error(1, errno, command);
                                ^~~~~~~
flow_dissector_load.c:55:19: note: treat the string as an argument to avoid this
                error(1, errno, command);
                                ^
                                "%s",
1 warning generated.

Signed-off-by: Stanislav Fomichev <sdf@google.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/testing/selftests/bpf/flow_dissector_load.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/testing/selftests/bpf/flow_dissector_load.c b/tools/testing/selftests/bpf/flow_dissector_load.c
index 77cafa66d048..7136ab9ffa73 100644
--- a/tools/testing/selftests/bpf/flow_dissector_load.c
+++ b/tools/testing/selftests/bpf/flow_dissector_load.c
@@ -52,7 +52,7 @@ static void detach_program(void)
 	sprintf(command, "rm -r %s", cfg_pin_path);
 	ret = system(command);
 	if (ret)
-		error(1, errno, command);
+		error(1, errno, "%s", command);
 }
 
 static void parse_opts(int argc, char **argv)
-- 
cgit v1.2.3-55-g7522


From a918b03e8c956d159b13fdde8608847393d54ef9 Mon Sep 17 00:00:00 2001
From: Stanislav Fomichev
Date: Tue, 2 Apr 2019 10:08:34 -0700
Subject: selftests: bpf: fix -Wformat-invalid-specifier for bpf_obj_id.c

Use standard C99 %zu for sizeof, not GCC's custom %Zu:
bpf_obj_id.c:76:48: warning: invalid conversion specifier 'Z'

Signed-off-by: Stanislav Fomichev <sdf@google.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/testing/selftests/bpf/prog_tests/bpf_obj_id.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

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 a64f7a02139c..cb827383db4d 100644
--- a/tools/testing/selftests/bpf/prog_tests/bpf_obj_id.c
+++ b/tools/testing/selftests/bpf/prog_tests/bpf_obj_id.c
@@ -73,7 +73,7 @@ void test_bpf_obj_id(void)
 			  info_len != sizeof(struct bpf_map_info) ||
 			  strcmp((char *)map_infos[i].name, expected_map_name),
 			  "get-map-info(fd)",
-			  "err %d errno %d type %d(%d) info_len %u(%Zu) key_size %u value_size %u max_entries %u map_flags %X name %s(%s)\n",
+			  "err %d errno %d type %d(%d) info_len %u(%zu) key_size %u value_size %u max_entries %u map_flags %X name %s(%s)\n",
 			  err, errno,
 			  map_infos[i].type, BPF_MAP_TYPE_ARRAY,
 			  info_len, sizeof(struct bpf_map_info),
@@ -117,7 +117,7 @@ void test_bpf_obj_id(void)
 			  *(int *)(long)prog_infos[i].map_ids != map_infos[i].id ||
 			  strcmp((char *)prog_infos[i].name, expected_prog_name),
 			  "get-prog-info(fd)",
-			  "err %d errno %d i %d type %d(%d) info_len %u(%Zu) jit_enabled %d jited_prog_len %u xlated_prog_len %u jited_prog %d xlated_prog %d load_time %lu(%lu) uid %u(%u) nr_map_ids %u(%u) map_id %u(%u) name %s(%s)\n",
+			  "err %d errno %d i %d type %d(%d) info_len %u(%zu) jit_enabled %d jited_prog_len %u xlated_prog_len %u jited_prog %d xlated_prog %d load_time %lu(%lu) uid %u(%u) nr_map_ids %u(%u) map_id %u(%u) name %s(%s)\n",
 			  err, errno, i,
 			  prog_infos[i].type, BPF_PROG_TYPE_SOCKET_FILTER,
 			  info_len, sizeof(struct bpf_prog_info),
@@ -185,7 +185,7 @@ void test_bpf_obj_id(void)
 		      memcmp(&prog_info, &prog_infos[i], info_len) ||
 		      *(int *)(long)prog_info.map_ids != saved_map_id,
 		      "get-prog-info(next_id->fd)",
-		      "err %d errno %d info_len %u(%Zu) memcmp %d map_id %u(%u)\n",
+		      "err %d errno %d info_len %u(%zu) memcmp %d map_id %u(%u)\n",
 		      err, errno, info_len, sizeof(struct bpf_prog_info),
 		      memcmp(&prog_info, &prog_infos[i], info_len),
 		      *(int *)(long)prog_info.map_ids, saved_map_id);
@@ -231,7 +231,7 @@ void test_bpf_obj_id(void)
 		      memcmp(&map_info, &map_infos[i], info_len) ||
 		      array_value != array_magic_value,
 		      "check get-map-info(next_id->fd)",
-		      "err %d errno %d info_len %u(%Zu) memcmp %d array_value %llu(%llu)\n",
+		      "err %d errno %d info_len %u(%zu) memcmp %d array_value %llu(%llu)\n",
 		      err, errno, info_len, sizeof(struct bpf_map_info),
 		      memcmp(&map_info, &map_infos[i], info_len),
 		      array_value, array_magic_value);
-- 
cgit v1.2.3-55-g7522


From 7596aa3ea8a0b478a8a5c6207e69cc7fcc035d45 Mon Sep 17 00:00:00 2001
From: Stanislav Fomichev
Date: Tue, 2 Apr 2019 10:08:35 -0700
Subject: selftests: bpf: remove duplicate .flags initialization in ctx_skb.c

verifier/ctx_skb.c:708:11: warning: initializer overrides prior initialization of this subobject [-Winitializer-overrides]
        .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
                 ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

Signed-off-by: Stanislav Fomichev <sdf@google.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/testing/selftests/bpf/verifier/ctx_skb.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/tools/testing/selftests/bpf/verifier/ctx_skb.c b/tools/testing/selftests/bpf/verifier/ctx_skb.c
index c660deb582f1..b0fda2877119 100644
--- a/tools/testing/selftests/bpf/verifier/ctx_skb.c
+++ b/tools/testing/selftests/bpf/verifier/ctx_skb.c
@@ -705,7 +705,6 @@
 	.errstr = "invalid bpf_context access",
 	.result = REJECT,
 	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
-	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 },
 {
 	"check cb access: half, wrong type",
-- 
cgit v1.2.3-55-g7522


From e83b9f55448afce3fe1abcd1d10db9584f8042a6 Mon Sep 17 00:00:00 2001
From: Andrii Nakryiko
Date: Tue, 2 Apr 2019 09:49:50 -0700
Subject: kbuild: add ability to generate BTF type info for vmlinux

This patch adds new config option to trigger generation of BTF type
information from DWARF debuginfo for vmlinux and kernel modules through
pahole, which in turn relies on libbpf for btf_dedup() algorithm.

The intent is to record compact type information of all types used
inside kernel, including all the structs/unions/typedefs/etc. This
enables BPF's compile-once-run-everywhere ([0]) approach, in which
tracing programs that are inspecting kernel's internal data (e.g.,
struct task_struct) can be compiled on a system running some kernel
version, but would be possible to run on other kernel versions (and
configurations) without recompilation, even if the layout of structs
changed and/or some of the fields were added, removed, or renamed.

This is only possible if BPF loader can get kernel type info to adjust
all the offsets correctly. This patch is a first time in this direction,
making sure that BTF type info is part of Linux kernel image in
non-loadable ELF section.

BTF deduplication ([1]) algorithm typically provides 100x savings
compared to DWARF data, so resulting .BTF section is not big as is
typically about 2MB in size.

[0] http://vger.kernel.org/lpc-bpf2018.html#session-2
[1] https://facebookmicrosites.github.io/bpf/blog/2018/11/14/btf-enhancement.html

Cc: Masahiro Yamada <yamada.masahiro@socionext.com>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Cc: Alexei Starovoitov <ast@fb.com>
Cc: Yonghong Song <yhs@fb.com>
Cc: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Andrii Nakryiko <andriin@fb.com>
Acked-by: David S. Miller <davem@davemloft.net>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 Makefile                |  3 ++-
 lib/Kconfig.debug       |  8 ++++++++
 scripts/link-vmlinux.sh | 20 +++++++++++++++++++-
 3 files changed, 29 insertions(+), 2 deletions(-)

diff --git a/Makefile b/Makefile
index c0a34064c574..73c013378559 100644
--- a/Makefile
+++ b/Makefile
@@ -399,6 +399,7 @@ NM		= $(CROSS_COMPILE)nm
 STRIP		= $(CROSS_COMPILE)strip
 OBJCOPY		= $(CROSS_COMPILE)objcopy
 OBJDUMP		= $(CROSS_COMPILE)objdump
+PAHOLE		= pahole
 LEX		= flex
 YACC		= bison
 AWK		= awk
@@ -453,7 +454,7 @@ KBUILD_LDFLAGS :=
 GCC_PLUGINS_CFLAGS :=
 
 export ARCH SRCARCH CONFIG_SHELL HOSTCC KBUILD_HOSTCFLAGS CROSS_COMPILE AS LD CC
-export CPP AR NM STRIP OBJCOPY OBJDUMP KBUILD_HOSTLDFLAGS KBUILD_HOSTLDLIBS
+export CPP AR NM STRIP OBJCOPY OBJDUMP PAHOLE KBUILD_HOSTLDFLAGS KBUILD_HOSTLDLIBS
 export MAKE LEX YACC AWK INSTALLKERNEL PERL PYTHON PYTHON2 PYTHON3 UTS_MACHINE
 export HOSTCXX KBUILD_HOSTCXXFLAGS LDFLAGS_MODULE CHECK CHECKFLAGS
 
diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index 0d9e81779e37..188fc17c2202 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -219,6 +219,14 @@ config DEBUG_INFO_DWARF4
 	  But it significantly improves the success of resolving
 	  variables in gdb on optimized code.
 
+config DEBUG_INFO_BTF
+	bool "Generate BTF typeinfo"
+	depends on DEBUG_INFO
+	help
+	  Generate deduplicated BTF type information from DWARF debug info.
+	  Turning this on expects presence of pahole tool, which will convert
+	  DWARF type info into equivalent deduplicated BTF type info.
+
 config GDB_SCRIPTS
 	bool "Provide GDB scripts for kernel debugging"
 	depends on DEBUG_INFO
diff --git a/scripts/link-vmlinux.sh b/scripts/link-vmlinux.sh
index dc0e8c5a1402..dd2b31ccca6a 100755
--- a/scripts/link-vmlinux.sh
+++ b/scripts/link-vmlinux.sh
@@ -35,7 +35,7 @@ set -e
 info()
 {
 	if [ "${quiet}" != "silent_" ]; then
-		printf "  %-7s %s\n" ${1} ${2}
+		printf "  %-7s %s\n" "${1}" "${2}"
 	fi
 }
 
@@ -91,6 +91,20 @@ vmlinux_link()
 	fi
 }
 
+# generate .BTF typeinfo from DWARF debuginfo
+gen_btf()
+{
+	local pahole_ver;
+
+	pahole_ver=$(${PAHOLE} --version | sed -E 's/v([0-9]+)\.([0-9]+)/\1\2/')
+	if [ "${pahole_ver}" -lt "113" ]; then
+		info "BTF" "${1}: pahole version $(${PAHOLE} --version) is too old, need at least v1.13"
+		exit 0
+	fi
+
+	info "BTF" ${1}
+	LLVM_OBJCOPY=${OBJCOPY} ${PAHOLE} -J ${1}
+}
 
 # Create ${2} .o file with all symbols from the ${1} object file
 kallsyms()
@@ -248,6 +262,10 @@ fi
 info LD vmlinux
 vmlinux_link "${kallsymso}" vmlinux
 
+if [ -n "${CONFIG_DEBUG_INFO_BTF}" ]; then
+	gen_btf vmlinux
+fi
+
 if [ -n "${CONFIG_BUILDTIME_EXTABLE_SORT}" ]; then
 	info SORTEX vmlinux
 	sortextable vmlinux
-- 
cgit v1.2.3-55-g7522


From 06ee7115b0d1742de745ad143fb5e06d77d27fba Mon Sep 17 00:00:00 2001
From: Alexei Starovoitov
Date: Mon, 1 Apr 2019 21:27:40 -0700
Subject: bpf: add verifier stats and log_level bit 2

In order to understand the verifier bottlenecks add various stats
and extend log_level:
log_level 1 and 2 are kept as-is:
bit 0 - level=1 - print every insn and verifier state at branch points
bit 1 - level=2 - print every insn and verifier state at every insn
bit 2 - level=4 - print verifier error and stats at the end of verification

When verifier rejects the program the libbpf is trying to load the program twice.
Once with log_level=0 (no messages, only error code is reported to user space)
and second time with log_level=1 to tell the user why the verifier rejected it.

With introduction of bit 2 - level=4 the libbpf can choose to always use that
level and load programs once, since the verification speed is not affected and
in case of error the verbose message will be available.

Note that the verifier stats are not part of uapi just like all other
verbose messages. They're expected to change in the future.

Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 include/linux/bpf_verifier.h | 21 ++++++++++++
 kernel/bpf/verifier.c        | 76 ++++++++++++++++++++++++++++++--------------
 2 files changed, 73 insertions(+), 24 deletions(-)

diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h
index 7d8228d1c898..f7e15eeb60bb 100644
--- a/include/linux/bpf_verifier.h
+++ b/include/linux/bpf_verifier.h
@@ -248,6 +248,12 @@ static inline bool bpf_verifier_log_full(const struct bpf_verifier_log *log)
 	return log->len_used >= log->len_total - 1;
 }
 
+#define BPF_LOG_LEVEL1	1
+#define BPF_LOG_LEVEL2	2
+#define BPF_LOG_STATS	4
+#define BPF_LOG_LEVEL	(BPF_LOG_LEVEL1 | BPF_LOG_LEVEL2)
+#define BPF_LOG_MASK	(BPF_LOG_LEVEL | BPF_LOG_STATS)
+
 static inline bool bpf_verifier_log_needed(const struct bpf_verifier_log *log)
 {
 	return log->level && log->ubuf && !bpf_verifier_log_full(log);
@@ -284,6 +290,21 @@ struct bpf_verifier_env {
 	struct bpf_verifier_log log;
 	struct bpf_subprog_info subprog_info[BPF_MAX_SUBPROGS + 1];
 	u32 subprog_cnt;
+	/* number of instructions analyzed by the verifier */
+	u32 insn_processed;
+	/* total verification time */
+	u64 verification_time;
+	/* maximum number of verifier states kept in 'branching' instructions */
+	u32 max_states_per_insn;
+	/* total number of allocated verifier states */
+	u32 total_states;
+	/* some states are freed during program analysis.
+	 * this is peak number of states. this number dominates kernel
+	 * memory consumption during verification
+	 */
+	u32 peak_states;
+	/* longest register parentage chain walked for liveness marking */
+	u32 longest_mark_read_walk;
 };
 
 __printf(2, 0) void bpf_verifier_vlog(struct bpf_verifier_log *log,
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 87221fda1321..e2001c1e40b3 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -1092,7 +1092,7 @@ static int check_subprogs(struct bpf_verifier_env *env)
 	 */
 	subprog[env->subprog_cnt].start = insn_cnt;
 
-	if (env->log.level > 1)
+	if (env->log.level & BPF_LOG_LEVEL2)
 		for (i = 0; i < env->subprog_cnt; i++)
 			verbose(env, "func#%d @%d\n", i, subprog[i].start);
 
@@ -1139,6 +1139,7 @@ static int mark_reg_read(struct bpf_verifier_env *env,
 			 struct bpf_reg_state *parent)
 {
 	bool writes = parent == state->parent; /* Observe write marks */
+	int cnt = 0;
 
 	while (parent) {
 		/* if read wasn't screened by an earlier write ... */
@@ -1155,7 +1156,11 @@ static int mark_reg_read(struct bpf_verifier_env *env,
 		state = parent;
 		parent = state->parent;
 		writes = true;
+		cnt++;
 	}
+
+	if (env->longest_mark_read_walk < cnt)
+		env->longest_mark_read_walk = cnt;
 	return 0;
 }
 
@@ -1455,7 +1460,7 @@ static int check_map_access(struct bpf_verifier_env *env, u32 regno,
 	 * need to try adding each of min_value and max_value to off
 	 * to make sure our theoretical access will be safe.
 	 */
-	if (env->log.level)
+	if (env->log.level & BPF_LOG_LEVEL)
 		print_verifier_state(env, state);
 
 	/* The minimum value is only important with signed
@@ -2938,7 +2943,7 @@ static int check_func_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
 	/* and go analyze first insn of the callee */
 	*insn_idx = target_insn;
 
-	if (env->log.level) {
+	if (env->log.level & BPF_LOG_LEVEL) {
 		verbose(env, "caller:\n");
 		print_verifier_state(env, caller);
 		verbose(env, "callee:\n");
@@ -2978,7 +2983,7 @@ static int prepare_func_exit(struct bpf_verifier_env *env, int *insn_idx)
 		return err;
 
 	*insn_idx = callee->callsite + 1;
-	if (env->log.level) {
+	if (env->log.level & BPF_LOG_LEVEL) {
 		verbose(env, "returning from callee:\n");
 		print_verifier_state(env, callee);
 		verbose(env, "to caller at %d:\n", *insn_idx);
@@ -5001,7 +5006,7 @@ static int check_cond_jmp_op(struct bpf_verifier_env *env,
 			insn->dst_reg);
 		return -EACCES;
 	}
-	if (env->log.level)
+	if (env->log.level & BPF_LOG_LEVEL)
 		print_verifier_state(env, this_branch->frame[this_branch->curframe]);
 	return 0;
 }
@@ -6181,6 +6186,9 @@ static int is_state_visited(struct bpf_verifier_env *env, int insn_idx)
 		states_cnt++;
 	}
 
+	if (env->max_states_per_insn < states_cnt)
+		env->max_states_per_insn = states_cnt;
+
 	if (!env->allow_ptr_leaks && states_cnt > BPF_COMPLEXITY_LIMIT_STATES)
 		return 0;
 
@@ -6194,6 +6202,8 @@ static int is_state_visited(struct bpf_verifier_env *env, int insn_idx)
 	new_sl = kzalloc(sizeof(struct bpf_verifier_state_list), GFP_KERNEL);
 	if (!new_sl)
 		return -ENOMEM;
+	env->total_states++;
+	env->peak_states++;
 
 	/* add new state to the head of linked list */
 	new = &new_sl->state;
@@ -6278,8 +6288,7 @@ static int do_check(struct bpf_verifier_env *env)
 	struct bpf_verifier_state *state;
 	struct bpf_insn *insns = env->prog->insnsi;
 	struct bpf_reg_state *regs;
-	int insn_cnt = env->prog->len, i;
-	int insn_processed = 0;
+	int insn_cnt = env->prog->len;
 	bool do_print_state = false;
 
 	env->prev_linfo = NULL;
@@ -6314,10 +6323,10 @@ static int do_check(struct bpf_verifier_env *env)
 		insn = &insns[env->insn_idx];
 		class = BPF_CLASS(insn->code);
 
-		if (++insn_processed > BPF_COMPLEXITY_LIMIT_INSNS) {
+		if (++env->insn_processed > BPF_COMPLEXITY_LIMIT_INSNS) {
 			verbose(env,
 				"BPF program is too large. Processed %d insn\n",
-				insn_processed);
+				env->insn_processed);
 			return -E2BIG;
 		}
 
@@ -6326,7 +6335,7 @@ static int do_check(struct bpf_verifier_env *env)
 			return err;
 		if (err == 1) {
 			/* found equivalent state, can prune the search */
-			if (env->log.level) {
+			if (env->log.level & BPF_LOG_LEVEL) {
 				if (do_print_state)
 					verbose(env, "\nfrom %d to %d%s: safe\n",
 						env->prev_insn_idx, env->insn_idx,
@@ -6344,8 +6353,9 @@ static int do_check(struct bpf_verifier_env *env)
 		if (need_resched())
 			cond_resched();
 
-		if (env->log.level > 1 || (env->log.level && do_print_state)) {
-			if (env->log.level > 1)
+		if (env->log.level & BPF_LOG_LEVEL2 ||
+		    (env->log.level & BPF_LOG_LEVEL && do_print_state)) {
+			if (env->log.level & BPF_LOG_LEVEL2)
 				verbose(env, "%d:", env->insn_idx);
 			else
 				verbose(env, "\nfrom %d to %d%s:",
@@ -6356,7 +6366,7 @@ static int do_check(struct bpf_verifier_env *env)
 			do_print_state = false;
 		}
 
-		if (env->log.level) {
+		if (env->log.level & BPF_LOG_LEVEL) {
 			const struct bpf_insn_cbs cbs = {
 				.cb_print	= verbose,
 				.private_data	= env,
@@ -6621,16 +6631,6 @@ process_bpf_exit:
 		env->insn_idx++;
 	}
 
-	verbose(env, "processed %d insns (limit %d), stack depth ",
-		insn_processed, BPF_COMPLEXITY_LIMIT_INSNS);
-	for (i = 0; i < env->subprog_cnt; i++) {
-		u32 depth = env->subprog_info[i].stack_depth;
-
-		verbose(env, "%d", depth);
-		if (i + 1 < env->subprog_cnt)
-			verbose(env, "+");
-	}
-	verbose(env, "\n");
 	env->prog->aux->stack_depth = env->subprog_info[0].stack_depth;
 	return 0;
 }
@@ -7854,9 +7854,34 @@ static void free_states(struct bpf_verifier_env *env)
 	kfree(env->explored_states);
 }
 
+static void print_verification_stats(struct bpf_verifier_env *env)
+{
+	int i;
+
+	if (env->log.level & BPF_LOG_STATS) {
+		verbose(env, "verification time %lld usec\n",
+			div_u64(env->verification_time, 1000));
+		verbose(env, "stack depth ");
+		for (i = 0; i < env->subprog_cnt; i++) {
+			u32 depth = env->subprog_info[i].stack_depth;
+
+			verbose(env, "%d", depth);
+			if (i + 1 < env->subprog_cnt)
+				verbose(env, "+");
+		}
+		verbose(env, "\n");
+	}
+	verbose(env, "processed %d insns (limit %d) max_states_per_insn %d "
+		"total_states %d peak_states %d mark_read %d\n",
+		env->insn_processed, BPF_COMPLEXITY_LIMIT_INSNS,
+		env->max_states_per_insn, env->total_states,
+		env->peak_states, env->longest_mark_read_walk);
+}
+
 int bpf_check(struct bpf_prog **prog, union bpf_attr *attr,
 	      union bpf_attr __user *uattr)
 {
+	u64 start_time = ktime_get_ns();
 	struct bpf_verifier_env *env;
 	struct bpf_verifier_log *log;
 	int i, len, ret = -EINVAL;
@@ -7899,7 +7924,7 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr,
 		ret = -EINVAL;
 		/* log attributes have to be sane */
 		if (log->len_total < 128 || log->len_total > UINT_MAX >> 8 ||
-		    !log->level || !log->ubuf)
+		    !log->level || !log->ubuf || log->level & ~BPF_LOG_MASK)
 			goto err_unlock;
 	}
 
@@ -7980,6 +8005,9 @@ skip_full_check:
 	if (ret == 0)
 		ret = fixup_call_args(env);
 
+	env->verification_time = ktime_get_ns() - start_time;
+	print_verification_stats(env);
+
 	if (log->level && bpf_verifier_log_full(log))
 		ret = -ENOSPC;
 	if (log->level && !log->ubuf) {
-- 
cgit v1.2.3-55-g7522


From 9f4686c41bdff051f557accb531af79dd1773687 Mon Sep 17 00:00:00 2001
From: Alexei Starovoitov
Date: Mon, 1 Apr 2019 21:27:41 -0700
Subject: bpf: improve verification speed by droping states

Branch instructions, branch targets and calls in a bpf program are
the places where the verifier remembers states that led to successful
verification of the program.
These states are used to prune brute force program analysis.
For unprivileged programs there is a limit of 64 states per such
'branching' instructions (maximum length is tracked by max_states_per_insn
counter introduced in the previous patch).
Simply reducing this threshold to 32 or lower increases insn_processed
metric to the point that small valid programs get rejected.
For root programs there is no limit and cilium programs can have
max_states_per_insn to be 100 or higher.
Walking 100+ states multiplied by number of 'branching' insns during
verification consumes significant amount of cpu time.
Turned out simple LRU-like mechanism can be used to remove states
that unlikely will be helpful in future search pruning.
This patch introduces hit_cnt and miss_cnt counters:
hit_cnt - this many times this state successfully pruned the search
miss_cnt - this many times this state was not equivalent to other states
(and that other states were added to state list)

The heuristic introduced in this patch is:
if (sl->miss_cnt > sl->hit_cnt * 3 + 3)
  /* drop this state from future considerations */

Higher numbers increase max_states_per_insn (allow more states to be
considered for pruning) and slow verification speed, but do not meaningfully
reduce insn_processed metric.
Lower numbers drop too many states and insn_processed increases too much.
Many different formulas were considered.
This one is simple and works well enough in practice.
(the analysis was done on selftests/progs/* and on cilium programs)

The end result is this heuristic improves verification speed by 10 times.
Large synthetic programs that used to take a second more now take
1/10 of a second.
In cases where max_states_per_insn used to be 100 or more, now it's ~10.

There is a slight increase in insn_processed for cilium progs:
                       before   after
bpf_lb-DLB_L3.o 	1831	1838
bpf_lb-DLB_L4.o 	3029	3218
bpf_lb-DUNKNOWN.o 	1064	1064
bpf_lxc-DDROP_ALL.o	26309	26935
bpf_lxc-DUNKNOWN.o	33517	34439
bpf_netdev.o		9713	9721
bpf_overlay.o		6184	6184
bpf_lcx_jit.o		37335	39389
And 2-3 times improvement in the verification speed.

Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Reviewed-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 include/linux/bpf_verifier.h |  2 ++
 kernel/bpf/verifier.c        | 44 +++++++++++++++++++++++++++++++++++++++++---
 2 files changed, 43 insertions(+), 3 deletions(-)

diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h
index f7e15eeb60bb..fc8254d6b569 100644
--- a/include/linux/bpf_verifier.h
+++ b/include/linux/bpf_verifier.h
@@ -207,6 +207,7 @@ struct bpf_verifier_state {
 struct bpf_verifier_state_list {
 	struct bpf_verifier_state state;
 	struct bpf_verifier_state_list *next;
+	int miss_cnt, hit_cnt;
 };
 
 /* Possible states for alu_state member. */
@@ -280,6 +281,7 @@ struct bpf_verifier_env {
 	bool strict_alignment;		/* perform strict pointer alignment checks */
 	struct bpf_verifier_state *cur_state; /* current verifier state */
 	struct bpf_verifier_state_list **explored_states; /* search pruning optimization */
+	struct bpf_verifier_state_list *free_list;
 	struct bpf_map *used_maps[MAX_USED_MAPS]; /* array of map's used by eBPF program */
 	u32 used_map_cnt;		/* number of used maps */
 	u32 id_gen;			/* used to generate unique reg IDs */
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index e2001c1e40b3..a636db4a7a4e 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -6152,11 +6152,13 @@ static int propagate_liveness(struct bpf_verifier_env *env,
 static int is_state_visited(struct bpf_verifier_env *env, int insn_idx)
 {
 	struct bpf_verifier_state_list *new_sl;
-	struct bpf_verifier_state_list *sl;
+	struct bpf_verifier_state_list *sl, **pprev;
 	struct bpf_verifier_state *cur = env->cur_state, *new;
 	int i, j, err, states_cnt = 0;
 
-	sl = env->explored_states[insn_idx];
+	pprev = &env->explored_states[insn_idx];
+	sl = *pprev;
+
 	if (!sl)
 		/* this 'insn_idx' instruction wasn't marked, so we will not
 		 * be doing state search here
@@ -6167,6 +6169,7 @@ static int is_state_visited(struct bpf_verifier_env *env, int insn_idx)
 
 	while (sl != STATE_LIST_MARK) {
 		if (states_equal(env, &sl->state, cur)) {
+			sl->hit_cnt++;
 			/* reached equivalent register/stack state,
 			 * prune the search.
 			 * Registers read by the continuation are read by us.
@@ -6182,8 +6185,35 @@ static int is_state_visited(struct bpf_verifier_env *env, int insn_idx)
 				return err;
 			return 1;
 		}
-		sl = sl->next;
 		states_cnt++;
+		sl->miss_cnt++;
+		/* heuristic to determine whether this state is beneficial
+		 * to keep checking from state equivalence point of view.
+		 * Higher numbers increase max_states_per_insn and verification time,
+		 * but do not meaningfully decrease insn_processed.
+		 */
+		if (sl->miss_cnt > sl->hit_cnt * 3 + 3) {
+			/* the state is unlikely to be useful. Remove it to
+			 * speed up verification
+			 */
+			*pprev = sl->next;
+			if (sl->state.frame[0]->regs[0].live & REG_LIVE_DONE) {
+				free_verifier_state(&sl->state, false);
+				kfree(sl);
+				env->peak_states--;
+			} else {
+				/* cannot free this state, since parentage chain may
+				 * walk it later. Add it for free_list instead to
+				 * be freed at the end of verification
+				 */
+				sl->next = env->free_list;
+				env->free_list = sl;
+			}
+			sl = *pprev;
+			continue;
+		}
+		pprev = &sl->next;
+		sl = *pprev;
 	}
 
 	if (env->max_states_per_insn < states_cnt)
@@ -7836,6 +7866,14 @@ static void free_states(struct bpf_verifier_env *env)
 	struct bpf_verifier_state_list *sl, *sln;
 	int i;
 
+	sl = env->free_list;
+	while (sl) {
+		sln = sl->next;
+		free_verifier_state(&sl->state, false);
+		kfree(sl);
+		sl = sln;
+	}
+
 	if (!env->explored_states)
 		return;
 
-- 
cgit v1.2.3-55-g7522


From 25af32dad8047d180e70e233c85b909dd6587cc5 Mon Sep 17 00:00:00 2001
From: Alexei Starovoitov
Date: Mon, 1 Apr 2019 21:27:42 -0700
Subject: bpf: improve verification speed by not remarking live_read

With large verifier speed improvement brought by the previous patch
mark_reg_read() becomes the hottest function during verification.
On a typical program it consumes 40% of cpu.
mark_reg_read() walks parentage chain of registers to mark parents as LIVE_READ.
Once the register is marked there is no need to remark it again in the future.
Hence stop walking the chain once first LIVE_READ is seen.
This optimization drops mark_reg_read() time from 40% of cpu to <1%
and overall 2x improvement of verification speed.
For some programs the longest_mark_read_walk counter improves from ~500 to ~5

Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Reviewed-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Edward Cree <ecree@solarflare.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 kernel/bpf/verifier.c | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index a636db4a7a4e..94cf6efc5df6 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -1151,6 +1151,15 @@ static int mark_reg_read(struct bpf_verifier_env *env,
 				parent->var_off.value, parent->off);
 			return -EFAULT;
 		}
+		if (parent->live & REG_LIVE_READ)
+			/* The parentage chain never changes and
+			 * this parent was already marked as LIVE_READ.
+			 * There is no need to keep walking the chain again and
+			 * keep re-marking all parents as LIVE_READ.
+			 * This case happens when the same register is read
+			 * multiple times without writes into it in-between.
+			 */
+			break;
 		/* ... then we depend on parent's value */
 		parent->live |= REG_LIVE_READ;
 		state = parent;
-- 
cgit v1.2.3-55-g7522


From 71dde681a8cea1ccff2c7b3be83c043ab6b2a977 Mon Sep 17 00:00:00 2001
From: Alexei Starovoitov
Date: Mon, 1 Apr 2019 21:27:43 -0700
Subject: bpf: convert temp arrays to kvcalloc

Temporary arrays used during program verification need to be vmalloc-ed
to support large bpf programs.

Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 kernel/bpf/verifier.c | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 94cf6efc5df6..ad3494a881da 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -5313,13 +5313,13 @@ static int check_cfg(struct bpf_verifier_env *env)
 	int ret = 0;
 	int i, t;
 
-	insn_state = kcalloc(insn_cnt, sizeof(int), GFP_KERNEL);
+	insn_state = kvcalloc(insn_cnt, sizeof(int), GFP_KERNEL);
 	if (!insn_state)
 		return -ENOMEM;
 
-	insn_stack = kcalloc(insn_cnt, sizeof(int), GFP_KERNEL);
+	insn_stack = kvcalloc(insn_cnt, sizeof(int), GFP_KERNEL);
 	if (!insn_stack) {
-		kfree(insn_state);
+		kvfree(insn_state);
 		return -ENOMEM;
 	}
 
@@ -5417,8 +5417,8 @@ check_state:
 	ret = 0; /* cfg looks good */
 
 err_free:
-	kfree(insn_state);
-	kfree(insn_stack);
+	kvfree(insn_state);
+	kvfree(insn_stack);
 	return ret;
 }
 
@@ -7898,7 +7898,7 @@ static void free_states(struct bpf_verifier_env *env)
 			}
 	}
 
-	kfree(env->explored_states);
+	kvfree(env->explored_states);
 }
 
 static void print_verification_stats(struct bpf_verifier_env *env)
@@ -7994,7 +7994,7 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr,
 			goto skip_full_check;
 	}
 
-	env->explored_states = kcalloc(env->prog->len,
+	env->explored_states = kvcalloc(env->prog->len,
 				       sizeof(struct bpf_verifier_state_list *),
 				       GFP_USER);
 	ret = -ENOMEM;
-- 
cgit v1.2.3-55-g7522


From 4f73379ec5c2891598aa715c6df7ac9afdc86fbf Mon Sep 17 00:00:00 2001
From: Alexei Starovoitov
Date: Mon, 1 Apr 2019 21:27:44 -0700
Subject: bpf: verbose jump offset overflow check

Larger programs may trigger 16-bit jump offset overflow check
during instruction patching. Make this error verbose otherwise
users cannot decipher error code without printks in the verifier.

Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 kernel/bpf/core.c     | 11 ++++++-----
 kernel/bpf/verifier.c |  7 ++++++-
 2 files changed, 12 insertions(+), 6 deletions(-)

diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index ff09d32a8a1b..2966cb368bf4 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -438,6 +438,7 @@ struct bpf_prog *bpf_patch_insn_single(struct bpf_prog *prog, u32 off,
 	u32 insn_adj_cnt, insn_rest, insn_delta = len - 1;
 	const u32 cnt_max = S16_MAX;
 	struct bpf_prog *prog_adj;
+	int err;
 
 	/* Since our patchlet doesn't expand the image, we're done. */
 	if (insn_delta == 0) {
@@ -453,8 +454,8 @@ struct bpf_prog *bpf_patch_insn_single(struct bpf_prog *prog, u32 off,
 	 * we afterwards may not fail anymore.
 	 */
 	if (insn_adj_cnt > cnt_max &&
-	    bpf_adj_branches(prog, off, off + 1, off + len, true))
-		return NULL;
+	    (err = bpf_adj_branches(prog, off, off + 1, off + len, true)))
+		return ERR_PTR(err);
 
 	/* Several new instructions need to be inserted. Make room
 	 * for them. Likely, there's no need for a new allocation as
@@ -463,7 +464,7 @@ struct bpf_prog *bpf_patch_insn_single(struct bpf_prog *prog, u32 off,
 	prog_adj = bpf_prog_realloc(prog, bpf_prog_size(insn_adj_cnt),
 				    GFP_USER);
 	if (!prog_adj)
-		return NULL;
+		return ERR_PTR(-ENOMEM);
 
 	prog_adj->len = insn_adj_cnt;
 
@@ -1096,13 +1097,13 @@ struct bpf_prog *bpf_jit_blind_constants(struct bpf_prog *prog)
 			continue;
 
 		tmp = bpf_patch_insn_single(clone, i, insn_buff, rewritten);
-		if (!tmp) {
+		if (IS_ERR(tmp)) {
 			/* Patching may have repointed aux->prog during
 			 * realloc from the original one, so we need to
 			 * fix it up here on error.
 			 */
 			bpf_jit_prog_release_other(prog, clone);
-			return ERR_PTR(-ENOMEM);
+			return tmp;
 		}
 
 		clone = tmp;
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index ad3494a881da..6dcfeb44bb8e 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -6932,8 +6932,13 @@ static struct bpf_prog *bpf_patch_insn_data(struct bpf_verifier_env *env, u32 of
 	struct bpf_prog *new_prog;
 
 	new_prog = bpf_patch_insn_single(env->prog, off, patch, len);
-	if (!new_prog)
+	if (IS_ERR(new_prog)) {
+		if (PTR_ERR(new_prog) == -ERANGE)
+			verbose(env,
+				"insn %d cannot be patched due to 16-bit range\n",
+				env->insn_aux_data[off].orig_idx);
 		return NULL;
+	}
 	if (adjust_insn_aux_data(env, new_prog->len, off, len))
 		return NULL;
 	adjust_subprog_starts(env, off, len);
-- 
cgit v1.2.3-55-g7522


From c04c0d2b968ac45d6ef020316808ef6c82325a82 Mon Sep 17 00:00:00 2001
From: Alexei Starovoitov
Date: Mon, 1 Apr 2019 21:27:45 -0700
Subject: bpf: increase complexity limit and maximum program size

Large verifier speed improvements allow to increase
verifier complexity limit.
Now regardless of the program composition and its size it takes
little time for the verifier to hit insn_processed limit.
On typical x86 machine non-debug kernel processes 1M instructions
in 1/10 of a second.
(before these speed improvements specially crafted programs
could be hitting multi-second verification times)
Full kasan kernel with debug takes ~1 second for the same 1M insns.
Hence bump the BPF_COMPLEXITY_LIMIT_INSNS limit to 1M.
Also increase the number of instructions per program
from 4k to internal BPF_COMPLEXITY_LIMIT_INSNS limit.
4k limit was confusing to users, since small programs with hundreds
of insns could be hitting BPF_COMPLEXITY_LIMIT_INSNS limit.
Sometimes adding more insns and bpf_trace_printk debug statements
would make the verifier accept the program while removing
code would make the verifier reject it.
Some user space application started to add #define MAX_FOO to
their programs and do:
  MAX_FOO=100;
again:
  compile with MAX_FOO;
  try to load;
  if (fails_to_load) { reduce MAX_FOO; goto again; }
to be able to fit maximum amount of processing into single program.
Other users artificially split their single program into a set of programs
and use all 32 iterations of tail_calls to increase compute limits.
And the most advanced folks used unlimited tc-bpf filter list
to execute many bpf programs.
Essentially the users managed to workaround 4k insn limit.
This patch removes the limit for root programs from uapi.
BPF_COMPLEXITY_LIMIT_INSNS is the kernel internal limit
and success to load the program no longer depends on program size,
but on 'smartness' of the verifier only.
The verifier will continue to get smarter with every kernel release.

Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 include/linux/bpf.h   | 1 +
 kernel/bpf/syscall.c  | 3 ++-
 kernel/bpf/verifier.c | 1 -
 3 files changed, 3 insertions(+), 2 deletions(-)

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index f62897198844..a445194b5fb6 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -421,6 +421,7 @@ struct bpf_array {
 	};
 };
 
+#define BPF_COMPLEXITY_LIMIT_INSNS      1000000 /* yes. 1M insns */
 #define MAX_TAIL_CALL_CNT 32
 
 struct bpf_event_entry {
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index afca36f53c49..1d65e56594db 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -1557,7 +1557,8 @@ static int bpf_prog_load(union bpf_attr *attr, union bpf_attr __user *uattr)
 	/* eBPF programs must be GPL compatible to use GPL-ed functions */
 	is_gpl = license_is_gpl_compatible(license);
 
-	if (attr->insn_cnt == 0 || attr->insn_cnt > BPF_MAXINSNS)
+	if (attr->insn_cnt == 0 ||
+	    attr->insn_cnt > (capable(CAP_SYS_ADMIN) ? BPF_COMPLEXITY_LIMIT_INSNS : BPF_MAXINSNS))
 		return -E2BIG;
 	if (type != BPF_PROG_TYPE_SOCKET_FILTER &&
 	    type != BPF_PROG_TYPE_CGROUP_SKB &&
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 6dcfeb44bb8e..b631e89e7a51 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -176,7 +176,6 @@ struct bpf_verifier_stack_elem {
 	struct bpf_verifier_stack_elem *next;
 };
 
-#define BPF_COMPLEXITY_LIMIT_INSNS	131072
 #define BPF_COMPLEXITY_LIMIT_STACK	1024
 #define BPF_COMPLEXITY_LIMIT_STATES	64
 
-- 
cgit v1.2.3-55-g7522


From 7a9f5c65abcc9644b11738ca0815510cb5510eaf Mon Sep 17 00:00:00 2001
From: Alexei Starovoitov
Date: Mon, 1 Apr 2019 21:27:46 -0700
Subject: bpf: increase verifier log limit

The existing 16Mbyte verifier log limit is not enough for log_level=2
even for small programs. Increase it to 1Gbyte.
Note it's not a kernel memory limit.
It's an amount of memory user space provides to store
the verifier log. The kernel populates it 1k at a time.

Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Reviewed-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 kernel/bpf/verifier.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index b631e89e7a51..bb27b675923c 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -7974,7 +7974,7 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr,
 
 		ret = -EINVAL;
 		/* log attributes have to be sane */
-		if (log->len_total < 128 || log->len_total > UINT_MAX >> 8 ||
+		if (log->len_total < 128 || log->len_total > UINT_MAX >> 2 ||
 		    !log->level || !log->ubuf || log->level & ~BPF_LOG_MASK)
 			goto err_unlock;
 	}
-- 
cgit v1.2.3-55-g7522


From da11b417583ece875f862d84578259a2ab27ad86 Mon Sep 17 00:00:00 2001
From: Alexei Starovoitov
Date: Mon, 1 Apr 2019 21:27:47 -0700
Subject: libbpf: teach libbpf about log_level bit 2

Allow bpf_prog_load_xattr() to specify log_level for program loading.

Teach libbpf to accept log_level with bit 2 set.

Increase default BPF_LOG_BUF_SIZE from 256k to 16M.
There is no downside to increase it to a maximum allowed by old kernels.
Existing 256k limit caused ENOSPC errors and users were not able to see
verifier error which is printed at the end of the verifier log.

If ENOSPC is hit, double the verifier log and try again to capture
the verifier error.

Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/lib/bpf/bpf.c    |  2 +-
 tools/lib/bpf/bpf.h    |  2 +-
 tools/lib/bpf/libbpf.c | 16 ++++++++++++++--
 tools/lib/bpf/libbpf.h |  1 +
 4 files changed, 17 insertions(+), 4 deletions(-)

diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c
index 9cd015574e83..a1db869a6fda 100644
--- a/tools/lib/bpf/bpf.c
+++ b/tools/lib/bpf/bpf.c
@@ -223,7 +223,7 @@ int bpf_load_program_xattr(const struct bpf_load_program_attr *load_attr,
 		return -EINVAL;
 
 	log_level = load_attr->log_level;
-	if (log_level > 2 || (log_level && !log_buf))
+	if (log_level > (4 | 2 | 1) || (log_level && !log_buf))
 		return -EINVAL;
 
 	name_len = load_attr->name ? strlen(load_attr->name) : 0;
diff --git a/tools/lib/bpf/bpf.h b/tools/lib/bpf/bpf.h
index 6ffdd79bea89..e2c0df7b831f 100644
--- a/tools/lib/bpf/bpf.h
+++ b/tools/lib/bpf/bpf.h
@@ -92,7 +92,7 @@ struct bpf_load_program_attr {
 #define MAPS_RELAX_COMPAT	0x01
 
 /* Recommend log buffer size */
-#define BPF_LOG_BUF_SIZE (256 * 1024)
+#define BPF_LOG_BUF_SIZE (16 * 1024 * 1024) /* verifier maximum in kernels <= 5.1 */
 LIBBPF_API int
 bpf_load_program_xattr(const struct bpf_load_program_attr *load_attr,
 		       char *log_buf, size_t log_buf_sz);
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 11c25d9ea431..e1e4d35cf08e 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -152,6 +152,7 @@ struct bpf_program {
 		};
 	} *reloc_desc;
 	int nr_reloc;
+	int log_level;
 
 	struct {
 		int nr;
@@ -1494,6 +1495,7 @@ load_program(struct bpf_program *prog, struct bpf_insn *insns, int insns_cnt,
 {
 	struct bpf_load_program_attr load_attr;
 	char *cp, errmsg[STRERR_BUFSIZE];
+	int log_buf_size = BPF_LOG_BUF_SIZE;
 	char *log_buf;
 	int ret;
 
@@ -1514,21 +1516,30 @@ load_program(struct bpf_program *prog, struct bpf_insn *insns, int insns_cnt,
 	load_attr.line_info = prog->line_info;
 	load_attr.line_info_rec_size = prog->line_info_rec_size;
 	load_attr.line_info_cnt = prog->line_info_cnt;
+	load_attr.log_level = prog->log_level;
 	if (!load_attr.insns || !load_attr.insns_cnt)
 		return -EINVAL;
 
-	log_buf = malloc(BPF_LOG_BUF_SIZE);
+retry_load:
+	log_buf = malloc(log_buf_size);
 	if (!log_buf)
 		pr_warning("Alloc log buffer for bpf loader error, continue without log\n");
 
-	ret = bpf_load_program_xattr(&load_attr, log_buf, BPF_LOG_BUF_SIZE);
+	ret = bpf_load_program_xattr(&load_attr, log_buf, log_buf_size);
 
 	if (ret >= 0) {
+		if (load_attr.log_level)
+			pr_debug("verifier log:\n%s", log_buf);
 		*pfd = ret;
 		ret = 0;
 		goto out;
 	}
 
+	if (errno == ENOSPC) {
+		log_buf_size <<= 1;
+		free(log_buf);
+		goto retry_load;
+	}
 	ret = -LIBBPF_ERRNO__LOAD;
 	cp = libbpf_strerror_r(errno, errmsg, sizeof(errmsg));
 	pr_warning("load bpf program failed: %s\n", cp);
@@ -2938,6 +2949,7 @@ int bpf_prog_load_xattr(const struct bpf_prog_load_attr *attr,
 		bpf_program__set_expected_attach_type(prog,
 						      expected_attach_type);
 
+		prog->log_level = attr->log_level;
 		if (!first_prog)
 			first_prog = prog;
 	}
diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h
index c70785cc8ef5..531323391d07 100644
--- a/tools/lib/bpf/libbpf.h
+++ b/tools/lib/bpf/libbpf.h
@@ -314,6 +314,7 @@ struct bpf_prog_load_attr {
 	enum bpf_prog_type prog_type;
 	enum bpf_attach_type expected_attach_type;
 	int ifindex;
+	int log_level;
 };
 
 LIBBPF_API int bpf_prog_load_xattr(const struct bpf_prog_load_attr *attr,
-- 
cgit v1.2.3-55-g7522


From e5e7a8f2d858a91b79c4afc51a3f15edcbf9cb60 Mon Sep 17 00:00:00 2001
From: Alexei Starovoitov
Date: Mon, 1 Apr 2019 21:27:48 -0700
Subject: selftests/bpf: add few verifier scale tests

Add 3 basic tests that stress verifier scalability.

test_verif_scale1.c calls non-inlined jhash() function 90 times on
different position in the packet.
This test simulates network packet parsing.
jhash function is ~140 instructions and main program is ~1200 insns.

test_verif_scale2.c force inlines jhash() function 90 times.
This program is ~15k instructions long.

test_verif_scale3.c calls non-inlined jhash() function 90 times on
But this time jhash has to process 32-bytes from the packet
instead of 14-bytes in tests 1 and 2.
jhash function is ~230 insns and main program is ~1200 insns.

$ test_progs -s
can be used to see verifier stats.

Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 .../selftests/bpf/prog_tests/bpf_verif_scale.c     | 49 +++++++++++++++
 tools/testing/selftests/bpf/progs/test_jhash.h     | 70 ++++++++++++++++++++++
 .../selftests/bpf/progs/test_verif_scale1.c        | 30 ++++++++++
 .../selftests/bpf/progs/test_verif_scale2.c        | 30 ++++++++++
 .../selftests/bpf/progs/test_verif_scale3.c        | 30 ++++++++++
 tools/testing/selftests/bpf/test_progs.c           |  6 +-
 tools/testing/selftests/bpf/test_progs.h           |  1 +
 7 files changed, 215 insertions(+), 1 deletion(-)
 create mode 100644 tools/testing/selftests/bpf/prog_tests/bpf_verif_scale.c
 create mode 100644 tools/testing/selftests/bpf/progs/test_jhash.h
 create mode 100644 tools/testing/selftests/bpf/progs/test_verif_scale1.c
 create mode 100644 tools/testing/selftests/bpf/progs/test_verif_scale2.c
 create mode 100644 tools/testing/selftests/bpf/progs/test_verif_scale3.c

diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_verif_scale.c b/tools/testing/selftests/bpf/prog_tests/bpf_verif_scale.c
new file mode 100644
index 000000000000..23b159d95c3f
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/bpf_verif_scale.c
@@ -0,0 +1,49 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2019 Facebook
+#include <test_progs.h>
+static int libbpf_debug_print(enum libbpf_print_level level,
+			      const char *format, va_list args)
+{
+	if (level != LIBBPF_DEBUG)
+		return 0;
+
+	if (!strstr(format, "verifier log"))
+		return 0;
+	return vfprintf(stderr, "%s", args);
+}
+
+static int check_load(const char *file)
+{
+	struct bpf_prog_load_attr attr;
+	struct bpf_object *obj;
+	int err, prog_fd;
+
+	memset(&attr, 0, sizeof(struct bpf_prog_load_attr));
+	attr.file = file;
+	attr.prog_type = BPF_PROG_TYPE_SCHED_CLS;
+	attr.log_level = 4;
+	err = bpf_prog_load_xattr(&attr, &obj, &prog_fd);
+	bpf_object__close(obj);
+	if (err)
+		error_cnt++;
+	return err;
+}
+
+void test_bpf_verif_scale(void)
+{
+	const char *file1 = "./test_verif_scale1.o";
+	const char *file2 = "./test_verif_scale2.o";
+	const char *file3 = "./test_verif_scale3.o";
+	int err;
+
+	if (verifier_stats)
+		libbpf_set_print(libbpf_debug_print);
+
+	err = check_load(file1);
+	err |= check_load(file2);
+	err |= check_load(file3);
+	if (!err)
+		printf("test_verif_scale:OK\n");
+	else
+		printf("test_verif_scale:FAIL\n");
+}
diff --git a/tools/testing/selftests/bpf/progs/test_jhash.h b/tools/testing/selftests/bpf/progs/test_jhash.h
new file mode 100644
index 000000000000..3d12c11a8d47
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_jhash.h
@@ -0,0 +1,70 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2019 Facebook
+
+typedef unsigned int u32;
+
+static __attribute__((always_inline)) u32 rol32(u32 word, unsigned int shift)
+{
+	return (word << shift) | (word >> ((-shift) & 31));
+}
+
+#define __jhash_mix(a, b, c)			\
+{						\
+	a -= c;  a ^= rol32(c, 4);  c += b;	\
+	b -= a;  b ^= rol32(a, 6);  a += c;	\
+	c -= b;  c ^= rol32(b, 8);  b += a;	\
+	a -= c;  a ^= rol32(c, 16); c += b;	\
+	b -= a;  b ^= rol32(a, 19); a += c;	\
+	c -= b;  c ^= rol32(b, 4);  b += a;	\
+}
+
+#define __jhash_final(a, b, c)			\
+{						\
+	c ^= b; c -= rol32(b, 14);		\
+	a ^= c; a -= rol32(c, 11);		\
+	b ^= a; b -= rol32(a, 25);		\
+	c ^= b; c -= rol32(b, 16);		\
+	a ^= c; a -= rol32(c, 4);		\
+	b ^= a; b -= rol32(a, 14);		\
+	c ^= b; c -= rol32(b, 24);		\
+}
+
+#define JHASH_INITVAL		0xdeadbeef
+
+static ATTR
+u32 jhash(const void *key, u32 length, u32 initval)
+{
+	u32 a, b, c;
+	const unsigned char *k = key;
+
+	a = b = c = JHASH_INITVAL + length + initval;
+
+	while (length > 12) {
+		a += *(volatile u32 *)(k);
+		b += *(volatile u32 *)(k + 4);
+		c += *(volatile u32 *)(k + 8);
+		__jhash_mix(a, b, c);
+		length -= 12;
+		k += 12;
+	}
+	switch (length) {
+	case 12: c += (u32)k[11]<<24;
+	case 11: c += (u32)k[10]<<16;
+	case 10: c += (u32)k[9]<<8;
+	case 9:  c += k[8];
+	case 8:  b += (u32)k[7]<<24;
+	case 7:  b += (u32)k[6]<<16;
+	case 6:  b += (u32)k[5]<<8;
+	case 5:  b += k[4];
+	case 4:  a += (u32)k[3]<<24;
+	case 3:  a += (u32)k[2]<<16;
+	case 2:  a += (u32)k[1]<<8;
+	case 1:  a += k[0];
+		 c ^= a;
+		 __jhash_final(a, b, c);
+	case 0: /* Nothing left to add */
+		break;
+	}
+
+	return c;
+}
diff --git a/tools/testing/selftests/bpf/progs/test_verif_scale1.c b/tools/testing/selftests/bpf/progs/test_verif_scale1.c
new file mode 100644
index 000000000000..f3236ce35f31
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_verif_scale1.c
@@ -0,0 +1,30 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2019 Facebook
+#include <linux/bpf.h>
+#include "bpf_helpers.h"
+#define ATTR __attribute__((noinline))
+#include "test_jhash.h"
+
+SEC("scale90_noinline")
+int balancer_ingress(struct __sk_buff *ctx)
+{
+	void *data_end = (void *)(long)ctx->data_end;
+	void *data = (void *)(long)ctx->data;
+	void *ptr;
+	int ret = 0, nh_off, i = 0;
+
+	nh_off = 14;
+
+	/* pragma unroll doesn't work on large loops */
+
+#define C do { \
+	ptr = data + i; \
+	if (ptr + nh_off > data_end) \
+		break; \
+	ctx->tc_index = jhash(ptr, nh_off, ctx->cb[0] + i++); \
+	} while (0);
+#define C30 C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;
+	C30;C30;C30; /* 90 calls */
+	return 0;
+}
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/test_verif_scale2.c b/tools/testing/selftests/bpf/progs/test_verif_scale2.c
new file mode 100644
index 000000000000..77830693eccb
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_verif_scale2.c
@@ -0,0 +1,30 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2019 Facebook
+#include <linux/bpf.h>
+#include "bpf_helpers.h"
+#define ATTR __attribute__((always_inline))
+#include "test_jhash.h"
+
+SEC("scale90_inline")
+int balancer_ingress(struct __sk_buff *ctx)
+{
+	void *data_end = (void *)(long)ctx->data_end;
+	void *data = (void *)(long)ctx->data;
+	void *ptr;
+	int ret = 0, nh_off, i = 0;
+
+	nh_off = 14;
+
+	/* pragma unroll doesn't work on large loops */
+
+#define C do { \
+	ptr = data + i; \
+	if (ptr + nh_off > data_end) \
+		break; \
+	ctx->tc_index = jhash(ptr, nh_off, ctx->cb[0] + i++); \
+	} while (0);
+#define C30 C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;
+	C30;C30;C30; /* 90 calls */
+	return 0;
+}
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/test_verif_scale3.c b/tools/testing/selftests/bpf/progs/test_verif_scale3.c
new file mode 100644
index 000000000000..1848da04ea41
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_verif_scale3.c
@@ -0,0 +1,30 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2019 Facebook
+#include <linux/bpf.h>
+#include "bpf_helpers.h"
+#define ATTR __attribute__((noinline))
+#include "test_jhash.h"
+
+SEC("scale90_noinline32")
+int balancer_ingress(struct __sk_buff *ctx)
+{
+	void *data_end = (void *)(long)ctx->data_end;
+	void *data = (void *)(long)ctx->data;
+	void *ptr;
+	int ret = 0, nh_off, i = 0;
+
+	nh_off = 32;
+
+	/* pragma unroll doesn't work on large loops */
+
+#define C do { \
+	ptr = data + i; \
+	if (ptr + nh_off > data_end) \
+		break; \
+	ctx->tc_index = jhash(ptr, nh_off, ctx->cb[0] + i++); \
+	} while (0);
+#define C30 C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;C;
+	C30;C30;C30; /* 90 calls */
+	return 0;
+}
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/test_progs.c b/tools/testing/selftests/bpf/test_progs.c
index 5d10aee9e277..bf5c90998916 100644
--- a/tools/testing/selftests/bpf/test_progs.c
+++ b/tools/testing/selftests/bpf/test_progs.c
@@ -9,6 +9,7 @@
 
 int error_cnt, pass_cnt;
 bool jit_enabled;
+bool verifier_stats = false;
 
 struct ipv4_packet pkt_v4 = {
 	.eth.h_proto = __bpf_constant_htons(ETH_P_IP),
@@ -162,12 +163,15 @@ void *spin_lock_thread(void *arg)
 #include <prog_tests/tests.h>
 #undef DECLARE
 
-int main(void)
+int main(int ac, char **av)
 {
 	srand(time(NULL));
 
 	jit_enabled = is_jit_enabled();
 
+	if (ac == 2 && strcmp(av[1], "-s") == 0)
+		verifier_stats = true;
+
 #define CALL
 #include <prog_tests/tests.h>
 #undef CALL
diff --git a/tools/testing/selftests/bpf/test_progs.h b/tools/testing/selftests/bpf/test_progs.h
index 51a07367cd43..f095e1d4c657 100644
--- a/tools/testing/selftests/bpf/test_progs.h
+++ b/tools/testing/selftests/bpf/test_progs.h
@@ -40,6 +40,7 @@ typedef __u16 __sum16;
 
 extern int error_cnt, pass_cnt;
 extern bool jit_enabled;
+extern bool verifier_stats;
 
 #define MAGIC_BYTES 123
 
-- 
cgit v1.2.3-55-g7522


From 8aa2d4b4b92cd534d53353b0c2fb079572b97fdf Mon Sep 17 00:00:00 2001
From: Alexei Starovoitov
Date: Mon, 1 Apr 2019 21:27:49 -0700
Subject: selftests/bpf: synthetic tests to push verifier limits

Add a test to generate 1m ld_imm64 insns to stress the verifier.

Bump the size of fill_ld_abs_vlan_push_pop test from 4k to 29k
and jump_around_ld_abs from 4k to 5.5k.
Larger sizes are not possible due to 16-bit offset encoding
in jump instructions.

Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/testing/selftests/bpf/test_verifier.c  | 35 +++++++++++++++++++++-------
 tools/testing/selftests/bpf/verifier/ld_dw.c |  9 +++++++
 2 files changed, 35 insertions(+), 9 deletions(-)

diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c
index 19b5d03acc2a..75ef63b42f2c 100644
--- a/tools/testing/selftests/bpf/test_verifier.c
+++ b/tools/testing/selftests/bpf/test_verifier.c
@@ -50,6 +50,7 @@
 #include "../../../include/linux/filter.h"
 
 #define MAX_INSNS	BPF_MAXINSNS
+#define MAX_TEST_INSNS	1000000
 #define MAX_FIXUPS	8
 #define MAX_NR_MAPS	14
 #define MAX_TEST_RUNS	8
@@ -66,6 +67,7 @@ static int skips;
 struct bpf_test {
 	const char *descr;
 	struct bpf_insn	insns[MAX_INSNS];
+	struct bpf_insn	*fill_insns;
 	int fixup_map_hash_8b[MAX_FIXUPS];
 	int fixup_map_hash_48b[MAX_FIXUPS];
 	int fixup_map_hash_16b[MAX_FIXUPS];
@@ -83,6 +85,7 @@ struct bpf_test {
 	const char *errstr;
 	const char *errstr_unpriv;
 	uint32_t retval, retval_unpriv, insn_processed;
+	int prog_len;
 	enum {
 		UNDEF,
 		ACCEPT,
@@ -119,10 +122,11 @@ struct other_val {
 
 static void bpf_fill_ld_abs_vlan_push_pop(struct bpf_test *self)
 {
-	/* test: {skb->data[0], vlan_push} x 68 + {skb->data[0], vlan_pop} x 68 */
+	/* test: {skb->data[0], vlan_push} x 51 + {skb->data[0], vlan_pop} x 51 */
 #define PUSH_CNT 51
-	unsigned int len = BPF_MAXINSNS;
-	struct bpf_insn *insn = self->insns;
+	/* jump range is limited to 16 bit. PUSH_CNT of ld_abs needs room */
+	unsigned int len = (1 << 15) - PUSH_CNT * 2 * 5 * 6;
+	struct bpf_insn *insn = self->fill_insns;
 	int i = 0, j, k = 0;
 
 	insn[i++] = BPF_MOV64_REG(BPF_REG_6, BPF_REG_1);
@@ -156,12 +160,14 @@ loop:
 	for (; i < len - 1; i++)
 		insn[i] = BPF_ALU32_IMM(BPF_MOV, BPF_REG_0, 0xbef);
 	insn[len - 1] = BPF_EXIT_INSN();
+	self->prog_len = len;
 }
 
 static void bpf_fill_jump_around_ld_abs(struct bpf_test *self)
 {
-	struct bpf_insn *insn = self->insns;
-	unsigned int len = BPF_MAXINSNS;
+	struct bpf_insn *insn = self->fill_insns;
+	/* jump range is limited to 16 bit. every ld_abs is replaced by 6 insns */
+	unsigned int len = (1 << 15) / 6;
 	int i = 0;
 
 	insn[i++] = BPF_MOV64_REG(BPF_REG_6, BPF_REG_1);
@@ -171,11 +177,12 @@ static void bpf_fill_jump_around_ld_abs(struct bpf_test *self)
 	while (i < len - 1)
 		insn[i++] = BPF_LD_ABS(BPF_B, 1);
 	insn[i] = BPF_EXIT_INSN();
+	self->prog_len = i + 1;
 }
 
 static void bpf_fill_rand_ld_dw(struct bpf_test *self)
 {
-	struct bpf_insn *insn = self->insns;
+	struct bpf_insn *insn = self->fill_insns;
 	uint64_t res = 0;
 	int i = 0;
 
@@ -193,6 +200,7 @@ static void bpf_fill_rand_ld_dw(struct bpf_test *self)
 	insn[i++] = BPF_ALU64_IMM(BPF_RSH, BPF_REG_1, 32);
 	insn[i++] = BPF_ALU64_REG(BPF_XOR, BPF_REG_0, BPF_REG_1);
 	insn[i] = BPF_EXIT_INSN();
+	self->prog_len = i + 1;
 	res ^= (res >> 32);
 	self->retval = (uint32_t)res;
 }
@@ -520,8 +528,10 @@ static void do_test_fixup(struct bpf_test *test, enum bpf_prog_type prog_type,
 	int *fixup_percpu_cgroup_storage = test->fixup_percpu_cgroup_storage;
 	int *fixup_map_spin_lock = test->fixup_map_spin_lock;
 
-	if (test->fill_helper)
+	if (test->fill_helper) {
+		test->fill_insns = calloc(MAX_TEST_INSNS, sizeof(struct bpf_insn));
 		test->fill_helper(test);
+	}
 
 	/* Allocating HTs with 1 elem is fine here, since we only test
 	 * for verifier and not do a runtime lookup, so the only thing
@@ -718,12 +728,17 @@ static void do_test_single(struct bpf_test *test, bool unpriv,
 		prog_type = BPF_PROG_TYPE_SOCKET_FILTER;
 	fixup_skips = skips;
 	do_test_fixup(test, prog_type, prog, map_fds);
+	if (test->fill_insns) {
+		prog = test->fill_insns;
+		prog_len = test->prog_len;
+	} else {
+		prog_len = probe_filter_length(prog);
+	}
 	/* If there were some map skips during fixup due to missing bpf
 	 * features, skip this test.
 	 */
 	if (fixup_skips != skips)
 		return;
-	prog_len = probe_filter_length(prog);
 
 	pflags = 0;
 	if (test->flags & F_LOAD_WITH_STRICT_ALIGNMENT)
@@ -731,7 +746,7 @@ static void do_test_single(struct bpf_test *test, bool unpriv,
 	if (test->flags & F_NEEDS_EFFICIENT_UNALIGNED_ACCESS)
 		pflags |= BPF_F_ANY_ALIGNMENT;
 	fd_prog = bpf_verify_program(prog_type, prog, prog_len, pflags,
-				     "GPL", 0, bpf_vlog, sizeof(bpf_vlog), 1);
+				     "GPL", 0, bpf_vlog, sizeof(bpf_vlog), 4);
 	if (fd_prog < 0 && !bpf_probe_prog_type(prog_type, 0)) {
 		printf("SKIP (unsupported program type %d)\n", prog_type);
 		skips++;
@@ -830,6 +845,8 @@ static void do_test_single(struct bpf_test *test, bool unpriv,
 		goto fail_log;
 	}
 close_fds:
+	if (test->fill_insns)
+		free(test->fill_insns);
 	close(fd_prog);
 	for (i = 0; i < MAX_NR_MAPS; i++)
 		close(map_fds[i]);
diff --git a/tools/testing/selftests/bpf/verifier/ld_dw.c b/tools/testing/selftests/bpf/verifier/ld_dw.c
index d2c75b889598..0f18e62f0099 100644
--- a/tools/testing/selftests/bpf/verifier/ld_dw.c
+++ b/tools/testing/selftests/bpf/verifier/ld_dw.c
@@ -34,3 +34,12 @@
 	.result = ACCEPT,
 	.retval = 5,
 },
+{
+	"ld_dw: xor semi-random 64 bit imms, test 5",
+	.insns = { },
+	.data = { },
+	.fill_helper = bpf_fill_rand_ld_dw,
+	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+	.result = ACCEPT,
+	.retval = 1000000 - 6,
+},
-- 
cgit v1.2.3-55-g7522


From 0979ff7992fb6f4eb837995b12f4071dcafebd2d Mon Sep 17 00:00:00 2001
From: Daniel T. Lee
Date: Thu, 4 Apr 2019 07:17:55 +0900
Subject: selftests/bpf: ksym_search won't check symbols exists

Currently, ksym_search located at trace_helpers won't check symbols are
existing or not.

In ksym_search, when symbol is not found, it will return &syms[0](_stext).
But when the kernel symbols are not loaded, it will return NULL, which is
not a desired action.

This commit will add verification logic whether symbols are loaded prior
to the symbol search.

Signed-off-by: Daniel T. Lee <danieltimlee@gmail.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/testing/selftests/bpf/trace_helpers.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/tools/testing/selftests/bpf/trace_helpers.c b/tools/testing/selftests/bpf/trace_helpers.c
index 4cdb63bf0521..9a9fc6c9b70b 100644
--- a/tools/testing/selftests/bpf/trace_helpers.c
+++ b/tools/testing/selftests/bpf/trace_helpers.c
@@ -52,6 +52,10 @@ struct ksym *ksym_search(long key)
 	int start = 0, end = sym_cnt;
 	int result;
 
+	/* kallsyms not loaded. return NULL */
+	if (sym_cnt <= 0)
+		return NULL;
+
 	while (start < end) {
 		size_t mid = start + (end - start) / 2;
 
-- 
cgit v1.2.3-55-g7522


From e67b2c715415b121339049b630f0b4e1ede888dc Mon Sep 17 00:00:00 2001
From: Daniel T. Lee
Date: Thu, 4 Apr 2019 07:17:56 +0900
Subject: samples, selftests/bpf: add NULL check for ksym_search

Since, ksym_search added with verification logic for symbols existence,
it could return NULL when the kernel symbols are not loaded.

This commit will add NULL check logic after ksym_search.

Signed-off-by: Daniel T. Lee <danieltimlee@gmail.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 samples/bpf/offwaketime_user.c                            | 5 +++++
 samples/bpf/sampleip_user.c                               | 5 +++++
 samples/bpf/spintest_user.c                               | 7 ++++++-
 samples/bpf/trace_event_user.c                            | 5 +++++
 tools/testing/selftests/bpf/prog_tests/get_stack_raw_tp.c | 4 ++--
 5 files changed, 23 insertions(+), 3 deletions(-)

diff --git a/samples/bpf/offwaketime_user.c b/samples/bpf/offwaketime_user.c
index f06063af9fcb..bb315ce1b866 100644
--- a/samples/bpf/offwaketime_user.c
+++ b/samples/bpf/offwaketime_user.c
@@ -28,6 +28,11 @@ static void print_ksym(__u64 addr)
 	if (!addr)
 		return;
 	sym = ksym_search(addr);
+	if (!sym) {
+		printf("ksym not found. Is kallsyms loaded?\n");
+		return;
+	}
+
 	if (PRINT_RAW_ADDR)
 		printf("%s/%llx;", sym->name, addr);
 	else
diff --git a/samples/bpf/sampleip_user.c b/samples/bpf/sampleip_user.c
index 216c7ecbbbe9..23b90a45c802 100644
--- a/samples/bpf/sampleip_user.c
+++ b/samples/bpf/sampleip_user.c
@@ -109,6 +109,11 @@ static void print_ip_map(int fd)
 	for (i = 0; i < max; i++) {
 		if (counts[i].ip > PAGE_OFFSET) {
 			sym = ksym_search(counts[i].ip);
+			if (!sym) {
+				printf("ksym not found. Is kallsyms loaded?\n");
+				continue;
+			}
+
 			printf("0x%-17llx %-32s %u\n", counts[i].ip, sym->name,
 			       counts[i].count);
 		} else {
diff --git a/samples/bpf/spintest_user.c b/samples/bpf/spintest_user.c
index 8d3e9cfa1909..2556af2d9b3e 100644
--- a/samples/bpf/spintest_user.c
+++ b/samples/bpf/spintest_user.c
@@ -37,8 +37,13 @@ int main(int ac, char **argv)
 			bpf_map_lookup_elem(map_fd[0], &next_key, &value);
 			assert(next_key == value);
 			sym = ksym_search(value);
-			printf(" %s", sym->name);
 			key = next_key;
+			if (!sym) {
+				printf("ksym not found. Is kallsyms loaded?\n");
+				continue;
+			}
+
+			printf(" %s", sym->name);
 		}
 		if (key)
 			printf("\n");
diff --git a/samples/bpf/trace_event_user.c b/samples/bpf/trace_event_user.c
index d08046ab81f0..d4178f60e075 100644
--- a/samples/bpf/trace_event_user.c
+++ b/samples/bpf/trace_event_user.c
@@ -34,6 +34,11 @@ static void print_ksym(__u64 addr)
 	if (!addr)
 		return;
 	sym = ksym_search(addr);
+	if (!sym) {
+		printf("ksym not found. Is kallsyms loaded?\n");
+		return;
+	}
+
 	printf("%s;", sym->name);
 	if (!strcmp(sym->name, "sys_read"))
 		sys_read_seen = true;
diff --git a/tools/testing/selftests/bpf/prog_tests/get_stack_raw_tp.c b/tools/testing/selftests/bpf/prog_tests/get_stack_raw_tp.c
index d7bb5beb1c57..c2a0a9d5591b 100644
--- a/tools/testing/selftests/bpf/prog_tests/get_stack_raw_tp.c
+++ b/tools/testing/selftests/bpf/prog_tests/get_stack_raw_tp.c
@@ -39,7 +39,7 @@ static int get_stack_print_output(void *data, int size)
 		} else {
 			for (i = 0; i < num_stack; i++) {
 				ks = ksym_search(raw_data[i]);
-				if (strcmp(ks->name, nonjit_func) == 0) {
+				if (ks && (strcmp(ks->name, nonjit_func) == 0)) {
 					found = true;
 					break;
 				}
@@ -56,7 +56,7 @@ static int get_stack_print_output(void *data, int size)
 		} else {
 			for (i = 0; i < num_stack; i++) {
 				ks = ksym_search(e->kern_stack[i]);
-				if (strcmp(ks->name, nonjit_func) == 0) {
+				if (ks && (strcmp(ks->name, nonjit_func) == 0)) {
 					good_kern_stack = true;
 					break;
 				}
-- 
cgit v1.2.3-55-g7522


From 636e78b1cdb40b77a79b143dbd9d94847b360efa Mon Sep 17 00:00:00 2001
From: Alexei Starovoitov
Date: Thu, 4 Apr 2019 14:37:14 -0700
Subject: samples/bpf: fix build with new clang

clang started to error on invalid asm clobber usage in x86 headers
and many bpf program samples failed to build with the message:

  CLANG-bpf  /data/users/ast/bpf-next/samples/bpf/xdp_redirect_kern.o
In file included from /data/users/ast/bpf-next/samples/bpf/xdp_redirect_kern.c:14:
In file included from ../include/linux/in.h:23:
In file included from ../include/uapi/linux/in.h:24:
In file included from ../include/linux/socket.h:8:
In file included from ../include/linux/uio.h:14:
In file included from ../include/crypto/hash.h:16:
In file included from ../include/linux/crypto.h:26:
In file included from ../include/linux/uaccess.h:5:
In file included from ../include/linux/sched.h:15:
In file included from ../include/linux/sem.h:5:
In file included from ../include/uapi/linux/sem.h:5:
In file included from ../include/linux/ipc.h:9:
In file included from ../include/linux/refcount.h:72:
../arch/x86/include/asm/refcount.h:72:36: error: asm-specifier for input or output variable conflicts with asm clobber list
                                         r->refs.counter, e, "er", i, "cx");
                                                                      ^
../arch/x86/include/asm/refcount.h:86:27: error: asm-specifier for input or output variable conflicts with asm clobber list
                                         r->refs.counter, e, "cx");
                                                             ^
2 errors generated.

Override volatile() to workaround the problem.

Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 samples/bpf/asm_goto_workaround.h | 1 +
 1 file changed, 1 insertion(+)

diff --git a/samples/bpf/asm_goto_workaround.h b/samples/bpf/asm_goto_workaround.h
index 5cd7c1d1a5d5..7409722727ca 100644
--- a/samples/bpf/asm_goto_workaround.h
+++ b/samples/bpf/asm_goto_workaround.h
@@ -13,4 +13,5 @@
 #define asm_volatile_goto(x...) asm volatile("invalid use of asm_volatile_goto")
 #endif
 
+#define volatile(x...) volatile("")
 #endif
-- 
cgit v1.2.3-55-g7522


From f2bcd05ec7b839ff826d2008506ad2d2dff46a59 Mon Sep 17 00:00:00 2001
From: Andrey Ignatov
Date: Wed, 3 Apr 2019 23:22:37 -0700
Subject: bpf: Reject indirect var_off stack access in raw mode

It's hard to guarantee that whole memory is marked as initialized on
helper return if uninitialized stack is accessed with variable offset
since specific bounds are unknown to verifier. This may cause
uninitialized stack leaking.

Reject such an access in check_stack_boundary to prevent possible
leaking.

There are no known use-cases for indirect uninitialized stack access
with variable offset so it shouldn't break anything.

Fixes: 2011fccfb61b ("bpf: Support variable offset stack access from helpers")
Reported-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Andrey Ignatov <rdna@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 kernel/bpf/verifier.c | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index bb27b675923c..0f12fda35626 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -2226,6 +2226,15 @@ static int check_stack_boundary(struct bpf_verifier_env *env, int regno,
 		if (err)
 			return err;
 	} else {
+		/* Only initialized buffer on stack is allowed to be accessed
+		 * with variable offset. With uninitialized buffer it's hard to
+		 * guarantee that whole memory is marked as initialized on
+		 * helper return since specific bounds are unknown what may
+		 * cause uninitialized stack leaking.
+		 */
+		if (meta && meta->raw_mode)
+			meta = NULL;
+
 		min_off = reg->smin_value + reg->off;
 		max_off = reg->umax_value + reg->off;
 		err = __check_stack_boundary(env, regno, min_off, access_size,
-- 
cgit v1.2.3-55-g7522


From f68a5b44647bce6c34b10d5560c5b2c0aff31afc Mon Sep 17 00:00:00 2001
From: Andrey Ignatov
Date: Wed, 3 Apr 2019 23:22:38 -0700
Subject: selftests/bpf: Test indirect var_off stack access in raw mode

Test that verifier rejects indirect access to uninitialized stack with
variable offset.

Example of output:
  # ./test_verifier
  ...
  #859/p indirect variable-offset stack access, uninitialized OK

Signed-off-by: Andrey Ignatov <rdna@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/testing/selftests/bpf/verifier/var_off.c | 27 ++++++++++++++++++++++++++
 1 file changed, 27 insertions(+)

diff --git a/tools/testing/selftests/bpf/verifier/var_off.c b/tools/testing/selftests/bpf/verifier/var_off.c
index c4ebd0bb0781..3840bd16e173 100644
--- a/tools/testing/selftests/bpf/verifier/var_off.c
+++ b/tools/testing/selftests/bpf/verifier/var_off.c
@@ -114,6 +114,33 @@
 	.result = REJECT,
 	.prog_type = BPF_PROG_TYPE_LWT_IN,
 },
+{
+	"indirect variable-offset stack access, uninitialized",
+	.insns = {
+	BPF_MOV64_IMM(BPF_REG_2, 6),
+	BPF_MOV64_IMM(BPF_REG_3, 28),
+	/* Fill the top 16 bytes of the stack. */
+	BPF_ST_MEM(BPF_W, BPF_REG_10, -16, 0),
+	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
+	/* Get an unknown value. */
+	BPF_LDX_MEM(BPF_W, BPF_REG_4, BPF_REG_1, 0),
+	/* Make it small and 4-byte aligned. */
+	BPF_ALU64_IMM(BPF_AND, BPF_REG_4, 4),
+	BPF_ALU64_IMM(BPF_SUB, BPF_REG_4, 16),
+	/* Add it to fp.  We now have either fp-12 or fp-16, we don't know
+	 * which, but either way it points to initialized stack.
+	 */
+	BPF_ALU64_REG(BPF_ADD, BPF_REG_4, BPF_REG_10),
+	BPF_MOV64_IMM(BPF_REG_5, 8),
+	/* Dereference it indirectly. */
+	BPF_EMIT_CALL(BPF_FUNC_getsockopt),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	},
+	.errstr = "invalid indirect read from stack var_off",
+	.result = REJECT,
+	.prog_type = BPF_PROG_TYPE_SOCK_OPS,
+},
 {
 	"indirect variable-offset stack access, ok",
 	.insns = {
-- 
cgit v1.2.3-55-g7522


From 088ec26d9c2da9d879ab73e3f4117f9df6c566ee Mon Sep 17 00:00:00 2001
From: Andrey Ignatov
Date: Wed, 3 Apr 2019 23:22:39 -0700
Subject: bpf: Reject indirect var_off stack access in unpriv mode

Proper support of indirect stack access with variable offset in
unprivileged mode (!root) requires corresponding support in Spectre
masking for stack ALU in retrieve_ptr_limit().

There are no use-case for variable offset in unprivileged mode though so
make verifier reject such accesses for simplicity.

Pointer arithmetics is one (and only?) way to cause variable offset and
it's already rejected in unpriv mode so that verifier won't even get to
helper function whose argument contains variable offset, e.g.:

  0: (7a) *(u64 *)(r10 -16) = 0
  1: (7a) *(u64 *)(r10 -8) = 0
  2: (61) r2 = *(u32 *)(r1 +0)
  3: (57) r2 &= 4
  4: (17) r2 -= 16
  5: (0f) r2 += r10
  variable stack access var_off=(0xfffffffffffffff0; 0x4) off=-16 size=1R2
  stack pointer arithmetic goes out of range, prohibited for !root

Still it looks like a good idea to reject variable offset indirect stack
access for unprivileged mode in check_stack_boundary() explicitly.

Fixes: 2011fccfb61b ("bpf: Support variable offset stack access from helpers")
Reported-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Andrey Ignatov <rdna@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 kernel/bpf/verifier.c | 16 ++++++++++++++++
 1 file changed, 16 insertions(+)

diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 0f12fda35626..8400c1f33cd4 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -2226,6 +2226,19 @@ static int check_stack_boundary(struct bpf_verifier_env *env, int regno,
 		if (err)
 			return err;
 	} else {
+		/* Variable offset is prohibited for unprivileged mode for
+		 * simplicity since it requires corresponding support in
+		 * Spectre masking for stack ALU.
+		 * See also retrieve_ptr_limit().
+		 */
+		if (!env->allow_ptr_leaks) {
+			char tn_buf[48];
+
+			tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off);
+			verbose(env, "R%d indirect variable offset stack access prohibited for !root, var_off=%s\n",
+				regno, tn_buf);
+			return -EACCES;
+		}
 		/* Only initialized buffer on stack is allowed to be accessed
 		 * with variable offset. With uninitialized buffer it's hard to
 		 * guarantee that whole memory is marked as initialized on
@@ -3339,6 +3352,9 @@ static int retrieve_ptr_limit(const struct bpf_reg_state *ptr_reg,
 
 	switch (ptr_reg->type) {
 	case PTR_TO_STACK:
+		/* Indirect variable offset stack access is prohibited in
+		 * unprivileged mode so it's not handled here.
+		 */
 		off = ptr_reg->off + ptr_reg->var_off.value;
 		if (mask_to_left)
 			*ptr_limit = MAX_BPF_STACK + off;
-- 
cgit v1.2.3-55-g7522


From 2c6927dbdc3fbd41207e671212f53a98bbebf6ba Mon Sep 17 00:00:00 2001
From: Andrey Ignatov
Date: Wed, 3 Apr 2019 23:22:40 -0700
Subject: selftests/bpf: Test indirect var_off stack access in unpriv mode

Test that verifier rejects indirect stack access with variable offset in
unprivileged mode and accepts same code in privileged mode.

Since pointer arithmetics is prohibited in unprivileged mode verifier
should reject the program even before it gets to helper call that uses
variable offset, at the time when that variable offset is trying to be
constructed.

Example of output:
  # ./test_verifier
  ...
  #859/u indirect variable-offset stack access, priv vs unpriv OK
  #859/p indirect variable-offset stack access, priv vs unpriv OK

Signed-off-by: Andrey Ignatov <rdna@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/testing/selftests/bpf/verifier/var_off.c | 27 ++++++++++++++++++++++++++
 1 file changed, 27 insertions(+)

diff --git a/tools/testing/selftests/bpf/verifier/var_off.c b/tools/testing/selftests/bpf/verifier/var_off.c
index 3840bd16e173..f5d5ff18ef22 100644
--- a/tools/testing/selftests/bpf/verifier/var_off.c
+++ b/tools/testing/selftests/bpf/verifier/var_off.c
@@ -114,6 +114,33 @@
 	.result = REJECT,
 	.prog_type = BPF_PROG_TYPE_LWT_IN,
 },
+{
+	"indirect variable-offset stack access, priv vs unpriv",
+	.insns = {
+	/* Fill the top 16 bytes of the stack. */
+	BPF_ST_MEM(BPF_DW, BPF_REG_10, -16, 0),
+	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
+	/* Get an unknown value. */
+	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, 0),
+	/* Make it small and 4-byte aligned. */
+	BPF_ALU64_IMM(BPF_AND, BPF_REG_2, 4),
+	BPF_ALU64_IMM(BPF_SUB, BPF_REG_2, 16),
+	/* Add it to fp.  We now have either fp-12 or fp-16, we don't know
+	 * which, but either way it points to initialized stack.
+	 */
+	BPF_ALU64_REG(BPF_ADD, BPF_REG_2, BPF_REG_10),
+	/* Dereference it indirectly. */
+	BPF_LD_MAP_FD(BPF_REG_1, 0),
+	BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	},
+	.fixup_map_hash_8b = { 6 },
+	.errstr_unpriv = "R2 stack pointer arithmetic goes out of range, prohibited for !root",
+	.result_unpriv = REJECT,
+	.result = ACCEPT,
+	.prog_type = BPF_PROG_TYPE_CGROUP_SKB,
+},
 {
 	"indirect variable-offset stack access, uninitialized",
 	.insns = {
-- 
cgit v1.2.3-55-g7522


From 107c26a70ca81bfc33657366ad69d02fdc9efc9d Mon Sep 17 00:00:00 2001
From: Andrey Ignatov
Date: Wed, 3 Apr 2019 23:22:41 -0700
Subject: bpf: Sanity check max value for var_off stack access

As discussed in [1] max value of variable offset has to be checked for
overflow on stack access otherwise verifier would accept code like this:

  0: (b7) r2 = 6
  1: (b7) r3 = 28
  2: (7a) *(u64 *)(r10 -16) = 0
  3: (7a) *(u64 *)(r10 -8) = 0
  4: (79) r4 = *(u64 *)(r1 +168)
  5: (c5) if r4 s< 0x0 goto pc+4
   R1=ctx(id=0,off=0,imm=0) R2=inv6 R3=inv28
   R4=inv(id=0,umax_value=9223372036854775807,var_off=(0x0;
   0x7fffffffffffffff)) R10=fp0,call_-1 fp-8=mmmmmmmm fp-16=mmmmmmmm
  6: (17) r4 -= 16
  7: (0f) r4 += r10
  8: (b7) r5 = 8
  9: (85) call bpf_getsockopt#57
  10: (b7) r0 = 0
  11: (95) exit

, where R4 obviosly has unbounded max value.

Fix it by checking that reg->smax_value is inside (-BPF_MAX_VAR_OFF;
BPF_MAX_VAR_OFF) range.

reg->smax_value is used instead of reg->umax_value because stack
pointers are calculated using negative offset from fp. This is opposite
to e.g. map access where offset must be non-negative and where
umax_value is used.

Also dedicated verbose logs are added for both min and max bound check
failures to have diagnostics consistent with variable offset handling in
check_map_access().

[1] https://marc.info/?l=linux-netdev&m=155433357510597&w=2

Fixes: 2011fccfb61b ("bpf: Support variable offset stack access from helpers")
Reported-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Andrey Ignatov <rdna@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 kernel/bpf/verifier.c | 18 +++++++++++++++---
 1 file changed, 15 insertions(+), 3 deletions(-)

diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 8400c1f33cd4..f2d600199e66 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -2248,16 +2248,28 @@ static int check_stack_boundary(struct bpf_verifier_env *env, int regno,
 		if (meta && meta->raw_mode)
 			meta = NULL;
 
+		if (reg->smax_value >= BPF_MAX_VAR_OFF ||
+		    reg->smax_value <= -BPF_MAX_VAR_OFF) {
+			verbose(env, "R%d unbounded indirect variable offset stack access\n",
+				regno);
+			return -EACCES;
+		}
 		min_off = reg->smin_value + reg->off;
-		max_off = reg->umax_value + reg->off;
+		max_off = reg->smax_value + reg->off;
 		err = __check_stack_boundary(env, regno, min_off, access_size,
 					     zero_size_allowed);
-		if (err)
+		if (err) {
+			verbose(env, "R%d min value is outside of stack bound\n",
+				regno);
 			return err;
+		}
 		err = __check_stack_boundary(env, regno, max_off, access_size,
 					     zero_size_allowed);
-		if (err)
+		if (err) {
+			verbose(env, "R%d max value is outside of stack bound\n",
+				regno);
 			return err;
+		}
 	}
 
 	if (meta && meta->raw_mode) {
-- 
cgit v1.2.3-55-g7522


From 07f9196241f8bceef975dd15f894f8ed51425d55 Mon Sep 17 00:00:00 2001
From: Andrey Ignatov
Date: Wed, 3 Apr 2019 23:22:42 -0700
Subject: selftests/bpf: Test unbounded var_off stack access

Test the case when reg->smax_value is too small/big and can overflow,
and separately min and max values outside of stack bounds.

Example of output:
  # ./test_verifier
  #856/p indirect variable-offset stack access, unbounded OK
  #857/p indirect variable-offset stack access, max out of bound OK
  #858/p indirect variable-offset stack access, min out of bound OK

Signed-off-by: Andrey Ignatov <rdna@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/testing/selftests/bpf/verifier/var_off.c | 57 +++++++++++++++++++++++++-
 1 file changed, 55 insertions(+), 2 deletions(-)

diff --git a/tools/testing/selftests/bpf/verifier/var_off.c b/tools/testing/selftests/bpf/verifier/var_off.c
index f5d5ff18ef22..8504ac937809 100644
--- a/tools/testing/selftests/bpf/verifier/var_off.c
+++ b/tools/testing/selftests/bpf/verifier/var_off.c
@@ -40,7 +40,35 @@
 	.prog_type = BPF_PROG_TYPE_LWT_IN,
 },
 {
-	"indirect variable-offset stack access, out of bound",
+	"indirect variable-offset stack access, unbounded",
+	.insns = {
+	BPF_MOV64_IMM(BPF_REG_2, 6),
+	BPF_MOV64_IMM(BPF_REG_3, 28),
+	/* Fill the top 16 bytes of the stack. */
+	BPF_ST_MEM(BPF_DW, BPF_REG_10, -16, 0),
+	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
+	/* Get an unknown value. */
+	BPF_LDX_MEM(BPF_DW, BPF_REG_4, BPF_REG_1, offsetof(struct bpf_sock_ops,
+							   bytes_received)),
+	/* Check the lower bound but don't check the upper one. */
+	BPF_JMP_IMM(BPF_JSLT, BPF_REG_4, 0, 4),
+	/* Point the lower bound to initialized stack. Offset is now in range
+	 * from fp-16 to fp+0x7fffffffffffffef, i.e. max value is unbounded.
+	 */
+	BPF_ALU64_IMM(BPF_SUB, BPF_REG_4, 16),
+	BPF_ALU64_REG(BPF_ADD, BPF_REG_4, BPF_REG_10),
+	BPF_MOV64_IMM(BPF_REG_5, 8),
+	/* Dereference it indirectly. */
+	BPF_EMIT_CALL(BPF_FUNC_getsockopt),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	},
+	.errstr = "R4 unbounded indirect variable offset stack access",
+	.result = REJECT,
+	.prog_type = BPF_PROG_TYPE_SOCK_OPS,
+},
+{
+	"indirect variable-offset stack access, max out of bound",
 	.insns = {
 	/* Fill the top 8 bytes of the stack */
 	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
@@ -60,7 +88,32 @@
 	BPF_EXIT_INSN(),
 	},
 	.fixup_map_hash_8b = { 5 },
-	.errstr = "invalid stack type R2 var_off",
+	.errstr = "R2 max value is outside of stack bound",
+	.result = REJECT,
+	.prog_type = BPF_PROG_TYPE_LWT_IN,
+},
+{
+	"indirect variable-offset stack access, min out of bound",
+	.insns = {
+	/* Fill the top 8 bytes of the stack */
+	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
+	/* Get an unknown value */
+	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, 0),
+	/* Make it small and 4-byte aligned */
+	BPF_ALU64_IMM(BPF_AND, BPF_REG_2, 4),
+	BPF_ALU64_IMM(BPF_SUB, BPF_REG_2, 516),
+	/* add it to fp.  We now have either fp-516 or fp-512, but
+	 * we don't know which
+	 */
+	BPF_ALU64_REG(BPF_ADD, BPF_REG_2, BPF_REG_10),
+	/* dereference it indirectly */
+	BPF_LD_MAP_FD(BPF_REG_1, 0),
+	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
+	BPF_MOV64_IMM(BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	},
+	.fixup_map_hash_8b = { 5 },
+	.errstr = "R2 min value is outside of stack bound",
 	.result = REJECT,
 	.prog_type = BPF_PROG_TYPE_LWT_IN,
 },
-- 
cgit v1.2.3-55-g7522


From 1fbd20f8b77b366ea4aeb92ade72daa7f36a7e3b Mon Sep 17 00:00:00 2001
From: Andrey Ignatov
Date: Wed, 3 Apr 2019 23:22:43 -0700
Subject: bpf: Add missed newline in verifier verbose log

check_stack_access() that prints verbose log is used in
adjust_ptr_min_max_vals() that prints its own verbose log and now they
stick together, e.g.:

  variable stack access var_off=(0xfffffffffffffff0; 0x4) off=-16
  size=1R2 stack pointer arithmetic goes out of range, prohibited for
  !root

Add missing newline so that log is more readable:
  variable stack access var_off=(0xfffffffffffffff0; 0x4) off=-16 size=1
  R2 stack pointer arithmetic goes out of range, prohibited for !root

Fixes: f1174f77b50c ("bpf/verifier: rework value tracking")
Signed-off-by: Andrey Ignatov <rdna@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 kernel/bpf/verifier.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index f2d600199e66..48718e1da16d 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -1426,7 +1426,7 @@ static int check_stack_access(struct bpf_verifier_env *env,
 		char tn_buf[48];
 
 		tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off);
-		verbose(env, "variable stack access var_off=%s off=%d size=%d",
+		verbose(env, "variable stack access var_off=%s off=%d size=%d\n",
 			tn_buf, off, size);
 		return -EACCES;
 	}
-- 
cgit v1.2.3-55-g7522


From ff466b58055f2d28d8ddc1388af312e87a693efe Mon Sep 17 00:00:00 2001
From: Andrey Ignatov
Date: Sat, 6 Apr 2019 22:37:34 -0700
Subject: libbpf: Ignore -Wformat-nonliteral warning

vsprintf() in __base_pr() uses nonliteral format string and it breaks
compilation for those who provide corresponding extra CFLAGS, e.g.:
https://github.com/libbpf/libbpf/issues/27

If libbpf is built with the flags from PR:

  libbpf.c:68:26: error: format string is not a string literal
  [-Werror,-Wformat-nonliteral]
          return vfprintf(stderr, format, args);
                                  ^~~~~~
  1 error generated.

Ignore this warning since the use case in libbpf.c is legit.

Signed-off-by: Andrey Ignatov <rdna@fb.com>
Acked-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/lib/bpf/libbpf.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index e1e4d35cf08e..1ebfe7943d53 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -52,6 +52,11 @@
 #define BPF_FS_MAGIC		0xcafe4a11
 #endif
 
+/* vsprintf() in __base_pr() uses nonliteral format string. It may break
+ * compilation if user enables corresponding warning. Disable it explicitly.
+ */
+#pragma GCC diagnostic ignored "-Wformat-nonliteral"
+
 #define __printf(a, b)	__attribute__((format(printf, a, b)))
 
 static int __base_pr(enum libbpf_print_level level, const char *format,
-- 
cgit v1.2.3-55-g7522


From d8eca5bbb2be9bc7546f9e733786fa2f1a594c67 Mon Sep 17 00:00:00 2001
From: Daniel Borkmann
Date: Tue, 9 Apr 2019 23:20:03 +0200
Subject: bpf: implement lookup-free direct value access for maps

This generic extension to BPF maps allows for directly loading
an address residing inside a BPF map value as a single BPF
ldimm64 instruction!

The idea is similar to what BPF_PSEUDO_MAP_FD does today, which
is a special src_reg flag for ldimm64 instruction that indicates
that inside the first part of the double insns's imm field is a
file descriptor which the verifier then replaces as a full 64bit
address of the map into both imm parts. For the newly added
BPF_PSEUDO_MAP_VALUE src_reg flag, the idea is the following:
the first part of the double insns's imm field is again a file
descriptor corresponding to the map, and the second part of the
imm field is an offset into the value. The verifier will then
replace both imm parts with an address that points into the BPF
map value at the given value offset for maps that support this
operation. Currently supported is array map with single entry.
It is possible to support more than just single map element by
reusing both 16bit off fields of the insns as a map index, so
full array map lookup could be expressed that way. It hasn't
been implemented here due to lack of concrete use case, but
could easily be done so in future in a compatible way, since
both off fields right now have to be 0 and would correctly
denote a map index 0.

The BPF_PSEUDO_MAP_VALUE is a distinct flag as otherwise with
BPF_PSEUDO_MAP_FD we could not differ offset 0 between load of
map pointer versus load of map's value at offset 0, and changing
BPF_PSEUDO_MAP_FD's encoding into off by one to differ between
regular map pointer and map value pointer would add unnecessary
complexity and increases barrier for debugability thus less
suitable. Using the second part of the imm field as an offset
into the value does /not/ come with limitations since maximum
possible value size is in u32 universe anyway.

This optimization allows for efficiently retrieving an address
to a map value memory area without having to issue a helper call
which needs to prepare registers according to calling convention,
etc, without needing the extra NULL test, and without having to
add the offset in an additional instruction to the value base
pointer. The verifier then treats the destination register as
PTR_TO_MAP_VALUE with constant reg->off from the user passed
offset from the second imm field, and guarantees that this is
within bounds of the map value. Any subsequent operations are
normally treated as typical map value handling without anything
extra needed from verification side.

The two map operations for direct value access have been added to
array map for now. In future other types could be supported as
well depending on the use case. The main use case for this commit
is to allow for BPF loader support for global variables that
reside in .data/.rodata/.bss sections such that we can directly
load the address of them with minimal additional infrastructure
required. Loader support has been added in subsequent commits for
libbpf library.

Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/linux/bpf.h               |  6 +++
 include/linux/bpf_verifier.h      |  4 ++
 include/uapi/linux/bpf.h          | 13 +++++-
 kernel/bpf/arraymap.c             | 32 +++++++++++++++
 kernel/bpf/core.c                 |  3 +-
 kernel/bpf/disasm.c               |  5 ++-
 kernel/bpf/syscall.c              | 28 +++++++++----
 kernel/bpf/verifier.c             | 86 ++++++++++++++++++++++++++++++---------
 tools/bpf/bpftool/xlated_dumper.c |  3 ++
 9 files changed, 149 insertions(+), 31 deletions(-)

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index a445194b5fb6..bd93a592dd29 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -57,6 +57,12 @@ struct bpf_map_ops {
 			     const struct btf *btf,
 			     const struct btf_type *key_type,
 			     const struct btf_type *value_type);
+
+	/* Direct value access helpers. */
+	int (*map_direct_value_addr)(const struct bpf_map *map,
+				     u64 *imm, u32 off);
+	int (*map_direct_value_meta)(const struct bpf_map *map,
+				     u64 imm, u32 *off);
 };
 
 struct bpf_map {
diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h
index fc8254d6b569..b3ab61fe1932 100644
--- a/include/linux/bpf_verifier.h
+++ b/include/linux/bpf_verifier.h
@@ -224,6 +224,10 @@ struct bpf_insn_aux_data {
 		unsigned long map_state;	/* pointer/poison value for maps */
 		s32 call_imm;			/* saved imm field of call insn */
 		u32 alu_limit;			/* limit for add/sub register with pointer */
+		struct {
+			u32 map_index;		/* index into used_maps[] */
+			u32 map_off;		/* offset from value base address */
+		};
 	};
 	int ctx_field_size; /* the ctx field size for load insn, maybe 0 */
 	int sanitize_stack_off; /* stack slot to be cleared */
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 837024512baf..26cfb5b2c964 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -255,8 +255,19 @@ enum bpf_attach_type {
  */
 #define BPF_F_ANY_ALIGNMENT	(1U << 1)
 
-/* when bpf_ldimm64->src_reg == BPF_PSEUDO_MAP_FD, bpf_ldimm64->imm == fd */
+/* When BPF ldimm64's insn[0].src_reg != 0 then this can have
+ * two extensions:
+ *
+ * insn[0].src_reg:  BPF_PSEUDO_MAP_FD   BPF_PSEUDO_MAP_VALUE
+ * insn[0].imm:      map fd              map fd
+ * insn[1].imm:      0                   offset into value
+ * insn[0].off:      0                   0
+ * insn[1].off:      0                   0
+ * ldimm64 rewrite:  address of map      address of map[0]+offset
+ * verifier type:    CONST_PTR_TO_MAP    PTR_TO_MAP_VALUE
+ */
 #define BPF_PSEUDO_MAP_FD	1
+#define BPF_PSEUDO_MAP_VALUE	2
 
 /* when bpf_call->src_reg == BPF_PSEUDO_CALL, bpf_call->imm == pc-relative
  * offset to another bpf function
diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c
index c72e0d8e1e65..1a6e9861d554 100644
--- a/kernel/bpf/arraymap.c
+++ b/kernel/bpf/arraymap.c
@@ -160,6 +160,36 @@ static void *array_map_lookup_elem(struct bpf_map *map, void *key)
 	return array->value + array->elem_size * (index & array->index_mask);
 }
 
+static int array_map_direct_value_addr(const struct bpf_map *map, u64 *imm,
+				       u32 off)
+{
+	struct bpf_array *array = container_of(map, struct bpf_array, map);
+
+	if (map->max_entries != 1)
+		return -ENOTSUPP;
+	if (off >= map->value_size)
+		return -EINVAL;
+
+	*imm = (unsigned long)array->value;
+	return 0;
+}
+
+static int array_map_direct_value_meta(const struct bpf_map *map, u64 imm,
+				       u32 *off)
+{
+	struct bpf_array *array = container_of(map, struct bpf_array, map);
+	u64 base = (unsigned long)array->value;
+	u64 range = array->elem_size;
+
+	if (map->max_entries != 1)
+		return -ENOTSUPP;
+	if (imm < base || imm >= base + range)
+		return -ENOENT;
+
+	*off = imm - base;
+	return 0;
+}
+
 /* emit BPF instructions equivalent to C code of array_map_lookup_elem() */
 static u32 array_map_gen_lookup(struct bpf_map *map, struct bpf_insn *insn_buf)
 {
@@ -419,6 +449,8 @@ const struct bpf_map_ops array_map_ops = {
 	.map_update_elem = array_map_update_elem,
 	.map_delete_elem = array_map_delete_elem,
 	.map_gen_lookup = array_map_gen_lookup,
+	.map_direct_value_addr = array_map_direct_value_addr,
+	.map_direct_value_meta = array_map_direct_value_meta,
 	.map_seq_show_elem = array_map_seq_show_elem,
 	.map_check_btf = array_map_check_btf,
 };
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index 2966cb368bf4..ace8c22c8b0e 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -292,7 +292,8 @@ int bpf_prog_calc_tag(struct bpf_prog *fp)
 		dst[i] = fp->insnsi[i];
 		if (!was_ld_map &&
 		    dst[i].code == (BPF_LD | BPF_IMM | BPF_DW) &&
-		    dst[i].src_reg == BPF_PSEUDO_MAP_FD) {
+		    (dst[i].src_reg == BPF_PSEUDO_MAP_FD ||
+		     dst[i].src_reg == BPF_PSEUDO_MAP_VALUE)) {
 			was_ld_map = true;
 			dst[i].imm = 0;
 		} else if (was_ld_map &&
diff --git a/kernel/bpf/disasm.c b/kernel/bpf/disasm.c
index de73f55e42fd..d9ce383c0f9c 100644
--- a/kernel/bpf/disasm.c
+++ b/kernel/bpf/disasm.c
@@ -205,10 +205,11 @@ void print_bpf_insn(const struct bpf_insn_cbs *cbs,
 			 * part of the ldimm64 insn is accessible.
 			 */
 			u64 imm = ((u64)(insn + 1)->imm << 32) | (u32)insn->imm;
-			bool map_ptr = insn->src_reg == BPF_PSEUDO_MAP_FD;
+			bool is_ptr = insn->src_reg == BPF_PSEUDO_MAP_FD ||
+				      insn->src_reg == BPF_PSEUDO_MAP_VALUE;
 			char tmp[64];
 
-			if (map_ptr && !allow_ptr_leaks)
+			if (is_ptr && !allow_ptr_leaks)
 				imm = 0;
 
 			verbose(cbs->private_data, "(%02x) r%d = %s\n",
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 1d65e56594db..828518bb947b 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -2072,13 +2072,26 @@ static int bpf_map_get_fd_by_id(const union bpf_attr *attr)
 }
 
 static const struct bpf_map *bpf_map_from_imm(const struct bpf_prog *prog,
-					      unsigned long addr)
+					      unsigned long addr, u32 *off,
+					      u32 *type)
 {
+	const struct bpf_map *map;
 	int i;
 
-	for (i = 0; i < prog->aux->used_map_cnt; i++)
-		if (prog->aux->used_maps[i] == (void *)addr)
-			return prog->aux->used_maps[i];
+	for (i = 0, *off = 0; i < prog->aux->used_map_cnt; i++) {
+		map = prog->aux->used_maps[i];
+		if (map == (void *)addr) {
+			*type = BPF_PSEUDO_MAP_FD;
+			return map;
+		}
+		if (!map->ops->map_direct_value_meta)
+			continue;
+		if (!map->ops->map_direct_value_meta(map, addr, off)) {
+			*type = BPF_PSEUDO_MAP_VALUE;
+			return map;
+		}
+	}
+
 	return NULL;
 }
 
@@ -2086,6 +2099,7 @@ static struct bpf_insn *bpf_insn_prepare_dump(const struct bpf_prog *prog)
 {
 	const struct bpf_map *map;
 	struct bpf_insn *insns;
+	u32 off, type;
 	u64 imm;
 	int i;
 
@@ -2113,11 +2127,11 @@ static struct bpf_insn *bpf_insn_prepare_dump(const struct bpf_prog *prog)
 			continue;
 
 		imm = ((u64)insns[i + 1].imm << 32) | (u32)insns[i].imm;
-		map = bpf_map_from_imm(prog, imm);
+		map = bpf_map_from_imm(prog, imm, &off, &type);
 		if (map) {
-			insns[i].src_reg = BPF_PSEUDO_MAP_FD;
+			insns[i].src_reg = type;
 			insns[i].imm = map->id;
-			insns[i + 1].imm = 0;
+			insns[i + 1].imm = off;
 			continue;
 		}
 	}
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 48718e1da16d..6ab7a23fc924 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -5056,18 +5056,12 @@ static int check_cond_jmp_op(struct bpf_verifier_env *env,
 	return 0;
 }
 
-/* return the map pointer stored inside BPF_LD_IMM64 instruction */
-static struct bpf_map *ld_imm64_to_map_ptr(struct bpf_insn *insn)
-{
-	u64 imm64 = ((u64) (u32) insn[0].imm) | ((u64) (u32) insn[1].imm) << 32;
-
-	return (struct bpf_map *) (unsigned long) imm64;
-}
-
 /* verify BPF_LD_IMM64 instruction */
 static int check_ld_imm(struct bpf_verifier_env *env, struct bpf_insn *insn)
 {
+	struct bpf_insn_aux_data *aux = cur_aux(env);
 	struct bpf_reg_state *regs = cur_regs(env);
+	struct bpf_map *map;
 	int err;
 
 	if (BPF_SIZE(insn->code) != BPF_DW) {
@@ -5091,11 +5085,22 @@ static int check_ld_imm(struct bpf_verifier_env *env, struct bpf_insn *insn)
 		return 0;
 	}
 
-	/* replace_map_fd_with_map_ptr() should have caught bad ld_imm64 */
-	BUG_ON(insn->src_reg != BPF_PSEUDO_MAP_FD);
+	map = env->used_maps[aux->map_index];
+	mark_reg_known_zero(env, regs, insn->dst_reg);
+	regs[insn->dst_reg].map_ptr = map;
+
+	if (insn->src_reg == BPF_PSEUDO_MAP_VALUE) {
+		regs[insn->dst_reg].type = PTR_TO_MAP_VALUE;
+		regs[insn->dst_reg].off = aux->map_off;
+		if (map_value_has_spin_lock(map))
+			regs[insn->dst_reg].id = ++env->id_gen;
+	} else if (insn->src_reg == BPF_PSEUDO_MAP_FD) {
+		regs[insn->dst_reg].type = CONST_PTR_TO_MAP;
+	} else {
+		verbose(env, "bpf verifier is misconfigured\n");
+		return -EINVAL;
+	}
 
-	regs[insn->dst_reg].type = CONST_PTR_TO_MAP;
-	regs[insn->dst_reg].map_ptr = ld_imm64_to_map_ptr(insn);
 	return 0;
 }
 
@@ -6803,8 +6808,10 @@ static int replace_map_fd_with_map_ptr(struct bpf_verifier_env *env)
 		}
 
 		if (insn[0].code == (BPF_LD | BPF_IMM | BPF_DW)) {
+			struct bpf_insn_aux_data *aux;
 			struct bpf_map *map;
 			struct fd f;
+			u64 addr;
 
 			if (i == insn_cnt - 1 || insn[1].code != 0 ||
 			    insn[1].dst_reg != 0 || insn[1].src_reg != 0 ||
@@ -6813,13 +6820,19 @@ static int replace_map_fd_with_map_ptr(struct bpf_verifier_env *env)
 				return -EINVAL;
 			}
 
-			if (insn->src_reg == 0)
+			if (insn[0].src_reg == 0)
 				/* valid generic load 64-bit imm */
 				goto next_insn;
 
-			if (insn[0].src_reg != BPF_PSEUDO_MAP_FD ||
-			    insn[1].imm != 0) {
-				verbose(env, "unrecognized bpf_ld_imm64 insn\n");
+			/* In final convert_pseudo_ld_imm64() step, this is
+			 * converted into regular 64-bit imm load insn.
+			 */
+			if ((insn[0].src_reg != BPF_PSEUDO_MAP_FD &&
+			     insn[0].src_reg != BPF_PSEUDO_MAP_VALUE) ||
+			    (insn[0].src_reg == BPF_PSEUDO_MAP_FD &&
+			     insn[1].imm != 0)) {
+				verbose(env,
+					"unrecognized bpf_ld_imm64 insn\n");
 				return -EINVAL;
 			}
 
@@ -6837,16 +6850,47 @@ static int replace_map_fd_with_map_ptr(struct bpf_verifier_env *env)
 				return err;
 			}
 
-			/* store map pointer inside BPF_LD_IMM64 instruction */
-			insn[0].imm = (u32) (unsigned long) map;
-			insn[1].imm = ((u64) (unsigned long) map) >> 32;
+			aux = &env->insn_aux_data[i];
+			if (insn->src_reg == BPF_PSEUDO_MAP_FD) {
+				addr = (unsigned long)map;
+			} else {
+				u32 off = insn[1].imm;
+
+				if (off >= BPF_MAX_VAR_OFF) {
+					verbose(env, "direct value offset of %u is not allowed\n", off);
+					fdput(f);
+					return -EINVAL;
+				}
+
+				if (!map->ops->map_direct_value_addr) {
+					verbose(env, "no direct value access support for this map type\n");
+					fdput(f);
+					return -EINVAL;
+				}
+
+				err = map->ops->map_direct_value_addr(map, &addr, off);
+				if (err) {
+					verbose(env, "invalid access to map value pointer, value_size=%u off=%u\n",
+						map->value_size, off);
+					fdput(f);
+					return err;
+				}
+
+				aux->map_off = off;
+				addr += off;
+			}
+
+			insn[0].imm = (u32)addr;
+			insn[1].imm = addr >> 32;
 
 			/* check whether we recorded this map already */
-			for (j = 0; j < env->used_map_cnt; j++)
+			for (j = 0; j < env->used_map_cnt; j++) {
 				if (env->used_maps[j] == map) {
+					aux->map_index = j;
 					fdput(f);
 					goto next_insn;
 				}
+			}
 
 			if (env->used_map_cnt >= MAX_USED_MAPS) {
 				fdput(f);
@@ -6863,6 +6907,8 @@ static int replace_map_fd_with_map_ptr(struct bpf_verifier_env *env)
 				fdput(f);
 				return PTR_ERR(map);
 			}
+
+			aux->map_index = env->used_map_cnt;
 			env->used_maps[env->used_map_cnt++] = map;
 
 			if (bpf_map_is_cgroup_storage(map) &&
diff --git a/tools/bpf/bpftool/xlated_dumper.c b/tools/bpf/bpftool/xlated_dumper.c
index 7073dbe1ff27..0bb17bf88b18 100644
--- a/tools/bpf/bpftool/xlated_dumper.c
+++ b/tools/bpf/bpftool/xlated_dumper.c
@@ -195,6 +195,9 @@ static const char *print_imm(void *private_data,
 	if (insn->src_reg == BPF_PSEUDO_MAP_FD)
 		snprintf(dd->scratch_buff, sizeof(dd->scratch_buff),
 			 "map[id:%u]", insn->imm);
+	else if (insn->src_reg == BPF_PSEUDO_MAP_VALUE)
+		snprintf(dd->scratch_buff, sizeof(dd->scratch_buff),
+			 "map[id:%u][0]+%u", insn->imm, (insn + 1)->imm);
 	else
 		snprintf(dd->scratch_buff, sizeof(dd->scratch_buff),
 			 "0x%llx", (unsigned long long)full_imm);
-- 
cgit v1.2.3-55-g7522


From be70bcd53de66e86f2726e576307cbdaebd3b1a5 Mon Sep 17 00:00:00 2001
From: Daniel Borkmann
Date: Tue, 9 Apr 2019 23:20:04 +0200
Subject: bpf: do not retain flags that are not tied to map lifetime

Both BPF_F_WRONLY / BPF_F_RDONLY flags are tied to the map file
descriptor, but not to the map object itself! Meaning, at map
creation time BPF_F_RDONLY can be set to make the map read-only
from syscall side, but this holds only for the returned fd, so
any other fd either retrieved via bpf file system or via map id
for the very same underlying map object can have read-write access
instead.

Given that, keeping the two flags around in the map_flags attribute
and exposing them to user space upon map dump is misleading and
may lead to false conclusions. Since these two flags are not
tied to the map object lets also not store them as map property.

Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 kernel/bpf/syscall.c | 14 +++++++++++++-
 1 file changed, 13 insertions(+), 1 deletion(-)

diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 828518bb947b..56b4b0e08b3b 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -166,13 +166,25 @@ void bpf_map_area_free(void *area)
 	kvfree(area);
 }
 
+static u32 bpf_map_flags_retain_permanent(u32 flags)
+{
+	/* Some map creation flags are not tied to the map object but
+	 * rather to the map fd instead, so they have no meaning upon
+	 * map object inspection since multiple file descriptors with
+	 * different (access) properties can exist here. Thus, given
+	 * this has zero meaning for the map itself, lets clear these
+	 * from here.
+	 */
+	return flags & ~(BPF_F_RDONLY | BPF_F_WRONLY);
+}
+
 void bpf_map_init_from_attr(struct bpf_map *map, union bpf_attr *attr)
 {
 	map->map_type = attr->map_type;
 	map->key_size = attr->key_size;
 	map->value_size = attr->value_size;
 	map->max_entries = attr->max_entries;
-	map->map_flags = attr->map_flags;
+	map->map_flags = bpf_map_flags_retain_permanent(attr->map_flags);
 	map->numa_node = bpf_map_attr_numa_node(attr);
 }
 
-- 
cgit v1.2.3-55-g7522


From 591fe9888d7809d9ee5c828020b6c6ae27c37229 Mon Sep 17 00:00:00 2001
From: Daniel Borkmann
Date: Tue, 9 Apr 2019 23:20:05 +0200
Subject: bpf: add program side {rd, wr}only support for maps

This work adds two new map creation flags BPF_F_RDONLY_PROG
and BPF_F_WRONLY_PROG in order to allow for read-only or
write-only BPF maps from a BPF program side.

Today we have BPF_F_RDONLY and BPF_F_WRONLY, but this only
applies to system call side, meaning the BPF program has full
read/write access to the map as usual while bpf(2) calls with
map fd can either only read or write into the map depending
on the flags. BPF_F_RDONLY_PROG and BPF_F_WRONLY_PROG allows
for the exact opposite such that verifier is going to reject
program loads if write into a read-only map or a read into a
write-only map is detected. For read-only map case also some
helpers are forbidden for programs that would alter the map
state such as map deletion, update, etc. As opposed to the two
BPF_F_RDONLY / BPF_F_WRONLY flags, BPF_F_RDONLY_PROG as well
as BPF_F_WRONLY_PROG really do correspond to the map lifetime.

We've enabled this generic map extension to various non-special
maps holding normal user data: array, hash, lru, lpm, local
storage, queue and stack. Further generic map types could be
followed up in future depending on use-case. Main use case
here is to forbid writes into .rodata map values from verifier
side.

Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/linux/bpf.h           | 29 +++++++++++++++++++++++++++
 include/uapi/linux/bpf.h      |  6 +++++-
 kernel/bpf/arraymap.c         |  6 +++++-
 kernel/bpf/hashtab.c          |  6 +++---
 kernel/bpf/local_storage.c    |  6 +++---
 kernel/bpf/lpm_trie.c         |  3 ++-
 kernel/bpf/queue_stack_maps.c |  6 +++---
 kernel/bpf/syscall.c          |  2 ++
 kernel/bpf/verifier.c         | 46 +++++++++++++++++++++++++++++++++++++++++--
 9 files changed, 96 insertions(+), 14 deletions(-)

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index bd93a592dd29..be20804631b5 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -430,6 +430,35 @@ struct bpf_array {
 #define BPF_COMPLEXITY_LIMIT_INSNS      1000000 /* yes. 1M insns */
 #define MAX_TAIL_CALL_CNT 32
 
+#define BPF_F_ACCESS_MASK	(BPF_F_RDONLY |		\
+				 BPF_F_RDONLY_PROG |	\
+				 BPF_F_WRONLY |		\
+				 BPF_F_WRONLY_PROG)
+
+#define BPF_MAP_CAN_READ	BIT(0)
+#define BPF_MAP_CAN_WRITE	BIT(1)
+
+static inline u32 bpf_map_flags_to_cap(struct bpf_map *map)
+{
+	u32 access_flags = map->map_flags & (BPF_F_RDONLY_PROG | BPF_F_WRONLY_PROG);
+
+	/* Combination of BPF_F_RDONLY_PROG | BPF_F_WRONLY_PROG is
+	 * not possible.
+	 */
+	if (access_flags & BPF_F_RDONLY_PROG)
+		return BPF_MAP_CAN_READ;
+	else if (access_flags & BPF_F_WRONLY_PROG)
+		return BPF_MAP_CAN_WRITE;
+	else
+		return BPF_MAP_CAN_READ | BPF_MAP_CAN_WRITE;
+}
+
+static inline bool bpf_map_flags_access_ok(u32 access_flags)
+{
+	return (access_flags & (BPF_F_RDONLY_PROG | BPF_F_WRONLY_PROG)) !=
+	       (BPF_F_RDONLY_PROG | BPF_F_WRONLY_PROG);
+}
+
 struct bpf_event_entry {
 	struct perf_event *event;
 	struct file *perf_file;
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 26cfb5b2c964..d275446d807c 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -294,7 +294,7 @@ enum bpf_attach_type {
 
 #define BPF_OBJ_NAME_LEN 16U
 
-/* Flags for accessing BPF object */
+/* Flags for accessing BPF object from syscall side. */
 #define BPF_F_RDONLY		(1U << 3)
 #define BPF_F_WRONLY		(1U << 4)
 
@@ -304,6 +304,10 @@ enum bpf_attach_type {
 /* Zero-initialize hash function seed. This should only be used for testing. */
 #define BPF_F_ZERO_SEED		(1U << 6)
 
+/* Flags for accessing BPF object from program side. */
+#define BPF_F_RDONLY_PROG	(1U << 7)
+#define BPF_F_WRONLY_PROG	(1U << 8)
+
 /* flags for BPF_PROG_QUERY */
 #define BPF_F_QUERY_EFFECTIVE	(1U << 0)
 
diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c
index 1a6e9861d554..217b10bd9f48 100644
--- a/kernel/bpf/arraymap.c
+++ b/kernel/bpf/arraymap.c
@@ -22,7 +22,7 @@
 #include "map_in_map.h"
 
 #define ARRAY_CREATE_FLAG_MASK \
-	(BPF_F_NUMA_NODE | BPF_F_RDONLY | BPF_F_WRONLY)
+	(BPF_F_NUMA_NODE | BPF_F_ACCESS_MASK)
 
 static void bpf_array_free_percpu(struct bpf_array *array)
 {
@@ -63,6 +63,7 @@ int array_map_alloc_check(union bpf_attr *attr)
 	if (attr->max_entries == 0 || attr->key_size != 4 ||
 	    attr->value_size == 0 ||
 	    attr->map_flags & ~ARRAY_CREATE_FLAG_MASK ||
+	    !bpf_map_flags_access_ok(attr->map_flags) ||
 	    (percpu && numa_node != NUMA_NO_NODE))
 		return -EINVAL;
 
@@ -472,6 +473,9 @@ static int fd_array_map_alloc_check(union bpf_attr *attr)
 	/* only file descriptors can be stored in this type of map */
 	if (attr->value_size != sizeof(u32))
 		return -EINVAL;
+	/* Program read-only/write-only not supported for special maps yet. */
+	if (attr->map_flags & (BPF_F_RDONLY_PROG | BPF_F_WRONLY_PROG))
+		return -EINVAL;
 	return array_map_alloc_check(attr);
 }
 
diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c
index fed15cf94dca..192d32e77db3 100644
--- a/kernel/bpf/hashtab.c
+++ b/kernel/bpf/hashtab.c
@@ -23,7 +23,7 @@
 
 #define HTAB_CREATE_FLAG_MASK						\
 	(BPF_F_NO_PREALLOC | BPF_F_NO_COMMON_LRU | BPF_F_NUMA_NODE |	\
-	 BPF_F_RDONLY | BPF_F_WRONLY | BPF_F_ZERO_SEED)
+	 BPF_F_ACCESS_MASK | BPF_F_ZERO_SEED)
 
 struct bucket {
 	struct hlist_nulls_head head;
@@ -262,8 +262,8 @@ static int htab_map_alloc_check(union bpf_attr *attr)
 		/* Guard against local DoS, and discourage production use. */
 		return -EPERM;
 
-	if (attr->map_flags & ~HTAB_CREATE_FLAG_MASK)
-		/* reserved bits should not be used */
+	if (attr->map_flags & ~HTAB_CREATE_FLAG_MASK ||
+	    !bpf_map_flags_access_ok(attr->map_flags))
 		return -EINVAL;
 
 	if (!lru && percpu_lru)
diff --git a/kernel/bpf/local_storage.c b/kernel/bpf/local_storage.c
index 6b572e2de7fb..980e8f1f6cb5 100644
--- a/kernel/bpf/local_storage.c
+++ b/kernel/bpf/local_storage.c
@@ -14,7 +14,7 @@ DEFINE_PER_CPU(struct bpf_cgroup_storage*, bpf_cgroup_storage[MAX_BPF_CGROUP_STO
 #ifdef CONFIG_CGROUP_BPF
 
 #define LOCAL_STORAGE_CREATE_FLAG_MASK					\
-	(BPF_F_NUMA_NODE | BPF_F_RDONLY | BPF_F_WRONLY)
+	(BPF_F_NUMA_NODE | BPF_F_ACCESS_MASK)
 
 struct bpf_cgroup_storage_map {
 	struct bpf_map map;
@@ -282,8 +282,8 @@ static struct bpf_map *cgroup_storage_map_alloc(union bpf_attr *attr)
 	if (attr->value_size > PAGE_SIZE)
 		return ERR_PTR(-E2BIG);
 
-	if (attr->map_flags & ~LOCAL_STORAGE_CREATE_FLAG_MASK)
-		/* reserved bits should not be used */
+	if (attr->map_flags & ~LOCAL_STORAGE_CREATE_FLAG_MASK ||
+	    !bpf_map_flags_access_ok(attr->map_flags))
 		return ERR_PTR(-EINVAL);
 
 	if (attr->max_entries)
diff --git a/kernel/bpf/lpm_trie.c b/kernel/bpf/lpm_trie.c
index 93a5cbbde421..e61630c2e50b 100644
--- a/kernel/bpf/lpm_trie.c
+++ b/kernel/bpf/lpm_trie.c
@@ -538,7 +538,7 @@ out:
 #define LPM_KEY_SIZE_MIN	LPM_KEY_SIZE(LPM_DATA_SIZE_MIN)
 
 #define LPM_CREATE_FLAG_MASK	(BPF_F_NO_PREALLOC | BPF_F_NUMA_NODE |	\
-				 BPF_F_RDONLY | BPF_F_WRONLY)
+				 BPF_F_ACCESS_MASK)
 
 static struct bpf_map *trie_alloc(union bpf_attr *attr)
 {
@@ -553,6 +553,7 @@ static struct bpf_map *trie_alloc(union bpf_attr *attr)
 	if (attr->max_entries == 0 ||
 	    !(attr->map_flags & BPF_F_NO_PREALLOC) ||
 	    attr->map_flags & ~LPM_CREATE_FLAG_MASK ||
+	    !bpf_map_flags_access_ok(attr->map_flags) ||
 	    attr->key_size < LPM_KEY_SIZE_MIN ||
 	    attr->key_size > LPM_KEY_SIZE_MAX ||
 	    attr->value_size < LPM_VAL_SIZE_MIN ||
diff --git a/kernel/bpf/queue_stack_maps.c b/kernel/bpf/queue_stack_maps.c
index b384ea9f3254..0b140d236889 100644
--- a/kernel/bpf/queue_stack_maps.c
+++ b/kernel/bpf/queue_stack_maps.c
@@ -11,8 +11,7 @@
 #include "percpu_freelist.h"
 
 #define QUEUE_STACK_CREATE_FLAG_MASK \
-	(BPF_F_NUMA_NODE | BPF_F_RDONLY | BPF_F_WRONLY)
-
+	(BPF_F_NUMA_NODE | BPF_F_ACCESS_MASK)
 
 struct bpf_queue_stack {
 	struct bpf_map map;
@@ -52,7 +51,8 @@ static int queue_stack_map_alloc_check(union bpf_attr *attr)
 	/* check sanity of attributes */
 	if (attr->max_entries == 0 || attr->key_size != 0 ||
 	    attr->value_size == 0 ||
-	    attr->map_flags & ~QUEUE_STACK_CREATE_FLAG_MASK)
+	    attr->map_flags & ~QUEUE_STACK_CREATE_FLAG_MASK ||
+	    !bpf_map_flags_access_ok(attr->map_flags))
 		return -EINVAL;
 
 	if (attr->value_size > KMALLOC_MAX_SIZE)
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 56b4b0e08b3b..0c9276b54c88 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -501,6 +501,8 @@ static int map_check_btf(struct bpf_map *map, const struct btf *btf,
 	map->spin_lock_off = btf_find_spin_lock(btf, value_type);
 
 	if (map_value_has_spin_lock(map)) {
+		if (map->map_flags & BPF_F_RDONLY_PROG)
+			return -EACCES;
 		if (map->map_type != BPF_MAP_TYPE_HASH &&
 		    map->map_type != BPF_MAP_TYPE_ARRAY &&
 		    map->map_type != BPF_MAP_TYPE_CGROUP_STORAGE)
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 6ab7a23fc924..b747434df89c 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -1439,6 +1439,28 @@ static int check_stack_access(struct bpf_verifier_env *env,
 	return 0;
 }
 
+static int check_map_access_type(struct bpf_verifier_env *env, u32 regno,
+				 int off, int size, enum bpf_access_type type)
+{
+	struct bpf_reg_state *regs = cur_regs(env);
+	struct bpf_map *map = regs[regno].map_ptr;
+	u32 cap = bpf_map_flags_to_cap(map);
+
+	if (type == BPF_WRITE && !(cap & BPF_MAP_CAN_WRITE)) {
+		verbose(env, "write into map forbidden, value_size=%d off=%d size=%d\n",
+			map->value_size, off, size);
+		return -EACCES;
+	}
+
+	if (type == BPF_READ && !(cap & BPF_MAP_CAN_READ)) {
+		verbose(env, "read from map forbidden, value_size=%d off=%d size=%d\n",
+			map->value_size, off, size);
+		return -EACCES;
+	}
+
+	return 0;
+}
+
 /* check read/write into map element returned by bpf_map_lookup_elem() */
 static int __check_map_access(struct bpf_verifier_env *env, u32 regno, int off,
 			      int size, bool zero_size_allowed)
@@ -2024,7 +2046,9 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn
 			verbose(env, "R%d leaks addr into map\n", value_regno);
 			return -EACCES;
 		}
-
+		err = check_map_access_type(env, regno, off, size, t);
+		if (err)
+			return err;
 		err = check_map_access(env, regno, off, size, false);
 		if (!err && t == BPF_READ && value_regno >= 0)
 			mark_reg_unknown(env, regs, value_regno);
@@ -2327,6 +2351,10 @@ static int check_helper_mem_access(struct bpf_verifier_env *env, int regno,
 		return check_packet_access(env, regno, reg->off, access_size,
 					   zero_size_allowed);
 	case PTR_TO_MAP_VALUE:
+		if (check_map_access_type(env, regno, reg->off, access_size,
+					  meta && meta->raw_mode ? BPF_WRITE :
+					  BPF_READ))
+			return -EACCES;
 		return check_map_access(env, regno, reg->off, access_size,
 					zero_size_allowed);
 	default: /* scalar_value|ptr_to_stack or invalid ptr */
@@ -3059,6 +3087,7 @@ record_func_map(struct bpf_verifier_env *env, struct bpf_call_arg_meta *meta,
 		int func_id, int insn_idx)
 {
 	struct bpf_insn_aux_data *aux = &env->insn_aux_data[insn_idx];
+	struct bpf_map *map = meta->map_ptr;
 
 	if (func_id != BPF_FUNC_tail_call &&
 	    func_id != BPF_FUNC_map_lookup_elem &&
@@ -3069,11 +3098,24 @@ record_func_map(struct bpf_verifier_env *env, struct bpf_call_arg_meta *meta,
 	    func_id != BPF_FUNC_map_peek_elem)
 		return 0;
 
-	if (meta->map_ptr == NULL) {
+	if (map == NULL) {
 		verbose(env, "kernel subsystem misconfigured verifier\n");
 		return -EINVAL;
 	}
 
+	/* In case of read-only, some additional restrictions
+	 * need to be applied in order to prevent altering the
+	 * state of the map from program side.
+	 */
+	if ((map->map_flags & BPF_F_RDONLY_PROG) &&
+	    (func_id == BPF_FUNC_map_delete_elem ||
+	     func_id == BPF_FUNC_map_update_elem ||
+	     func_id == BPF_FUNC_map_push_elem ||
+	     func_id == BPF_FUNC_map_pop_elem)) {
+		verbose(env, "write into map forbidden\n");
+		return -EACCES;
+	}
+
 	if (!BPF_MAP_PTR(aux->map_state))
 		bpf_map_ptr_store(aux, meta->map_ptr,
 				  meta->map_ptr->unpriv_array);
-- 
cgit v1.2.3-55-g7522


From 87df15de441bd4add7876ef584da8cabdd9a042a Mon Sep 17 00:00:00 2001
From: Daniel Borkmann
Date: Tue, 9 Apr 2019 23:20:06 +0200
Subject: bpf: add syscall side map freeze support

This patch adds a new BPF_MAP_FREEZE command which allows to
"freeze" the map globally as read-only / immutable from syscall
side.

Map permission handling has been refactored into map_get_sys_perms()
and drops FMODE_CAN_WRITE in case of locked map. Main use case is
to allow for setting up .rodata sections from the BPF ELF which
are loaded into the kernel, meaning BPF loader first allocates
map, sets up map value by copying .rodata section into it and once
complete, it calls BPF_MAP_FREEZE on the map fd to prevent further
modifications.

Right now BPF_MAP_FREEZE only takes map fd as argument while remaining
bpf_attr members are required to be zero. I didn't add write-only
locking here as counterpart since I don't have a concrete use-case
for it on my side, and I think it makes probably more sense to wait
once there is actually one. In that case bpf_attr can be extended
as usual with a flag field and/or others where flag 0 means that
we lock the map read-only hence this doesn't prevent to add further
extensions to BPF_MAP_FREEZE upon need.

A map creation flag like BPF_F_WRONCE was not considered for couple
of reasons: i) in case of a generic implementation, a map can consist
of more than just one element, thus there could be multiple map
updates needed to set the map into a state where it can then be
made immutable, ii) WRONCE indicates exact one-time write before
it is then set immutable. A generic implementation would set a bit
atomically on map update entry (if unset), indicating that every
subsequent update from then onwards will need to bail out there.
However, map updates can fail, so upon failure that flag would need
to be unset again and the update attempt would need to be repeated
for it to be eventually made immutable. While this can be made
race-free, this approach feels less clean and in combination with
reason i), it's not generic enough. A dedicated BPF_MAP_FREEZE
command directly sets the flag and caller has the guarantee that
map is immutable from syscall side upon successful return for any
future syscall invocations that would alter the map state, which
is also more intuitive from an API point of view. A command name
such as BPF_MAP_LOCK has been avoided as it's too close with BPF
map spin locks (which already has BPF_F_LOCK flag). BPF_MAP_FREEZE
is so far only enabled for privileged users.

Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/linux/bpf.h      |  3 ++-
 include/uapi/linux/bpf.h |  1 +
 kernel/bpf/syscall.c     | 66 +++++++++++++++++++++++++++++++++++++++---------
 3 files changed, 57 insertions(+), 13 deletions(-)

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index be20804631b5..65f7094c40b4 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -87,7 +87,8 @@ struct bpf_map {
 	struct btf *btf;
 	u32 pages;
 	bool unpriv_array;
-	/* 51 bytes hole */
+	bool frozen; /* write-once */
+	/* 48 bytes hole */
 
 	/* The 3rd and 4th cacheline with misc members to avoid false sharing
 	 * particularly with refcounting.
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index d275446d807c..af1cbd951f26 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -105,6 +105,7 @@ enum bpf_cmd {
 	BPF_BTF_GET_FD_BY_ID,
 	BPF_TASK_FD_QUERY,
 	BPF_MAP_LOOKUP_AND_DELETE_ELEM,
+	BPF_MAP_FREEZE,
 };
 
 enum bpf_map_type {
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 0c9276b54c88..b3ce516e5a20 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -355,6 +355,18 @@ static int bpf_map_release(struct inode *inode, struct file *filp)
 	return 0;
 }
 
+static fmode_t map_get_sys_perms(struct bpf_map *map, struct fd f)
+{
+	fmode_t mode = f.file->f_mode;
+
+	/* Our file permissions may have been overridden by global
+	 * map permissions facing syscall side.
+	 */
+	if (READ_ONCE(map->frozen))
+		mode &= ~FMODE_CAN_WRITE;
+	return mode;
+}
+
 #ifdef CONFIG_PROC_FS
 static void bpf_map_show_fdinfo(struct seq_file *m, struct file *filp)
 {
@@ -376,14 +388,16 @@ static void bpf_map_show_fdinfo(struct seq_file *m, struct file *filp)
 		   "max_entries:\t%u\n"
 		   "map_flags:\t%#x\n"
 		   "memlock:\t%llu\n"
-		   "map_id:\t%u\n",
+		   "map_id:\t%u\n"
+		   "frozen:\t%u\n",
 		   map->map_type,
 		   map->key_size,
 		   map->value_size,
 		   map->max_entries,
 		   map->map_flags,
 		   map->pages * 1ULL << PAGE_SHIFT,
-		   map->id);
+		   map->id,
+		   READ_ONCE(map->frozen));
 
 	if (owner_prog_type) {
 		seq_printf(m, "owner_prog_type:\t%u\n",
@@ -727,8 +741,7 @@ static int map_lookup_elem(union bpf_attr *attr)
 	map = __bpf_map_get(f);
 	if (IS_ERR(map))
 		return PTR_ERR(map);
-
-	if (!(f.file->f_mode & FMODE_CAN_READ)) {
+	if (!(map_get_sys_perms(map, f) & FMODE_CAN_READ)) {
 		err = -EPERM;
 		goto err_put;
 	}
@@ -857,8 +870,7 @@ static int map_update_elem(union bpf_attr *attr)
 	map = __bpf_map_get(f);
 	if (IS_ERR(map))
 		return PTR_ERR(map);
-
-	if (!(f.file->f_mode & FMODE_CAN_WRITE)) {
+	if (!(map_get_sys_perms(map, f) & FMODE_CAN_WRITE)) {
 		err = -EPERM;
 		goto err_put;
 	}
@@ -969,8 +981,7 @@ static int map_delete_elem(union bpf_attr *attr)
 	map = __bpf_map_get(f);
 	if (IS_ERR(map))
 		return PTR_ERR(map);
-
-	if (!(f.file->f_mode & FMODE_CAN_WRITE)) {
+	if (!(map_get_sys_perms(map, f) & FMODE_CAN_WRITE)) {
 		err = -EPERM;
 		goto err_put;
 	}
@@ -1021,8 +1032,7 @@ static int map_get_next_key(union bpf_attr *attr)
 	map = __bpf_map_get(f);
 	if (IS_ERR(map))
 		return PTR_ERR(map);
-
-	if (!(f.file->f_mode & FMODE_CAN_READ)) {
+	if (!(map_get_sys_perms(map, f) & FMODE_CAN_READ)) {
 		err = -EPERM;
 		goto err_put;
 	}
@@ -1089,8 +1099,7 @@ static int map_lookup_and_delete_elem(union bpf_attr *attr)
 	map = __bpf_map_get(f);
 	if (IS_ERR(map))
 		return PTR_ERR(map);
-
-	if (!(f.file->f_mode & FMODE_CAN_WRITE)) {
+	if (!(map_get_sys_perms(map, f) & FMODE_CAN_WRITE)) {
 		err = -EPERM;
 		goto err_put;
 	}
@@ -1132,6 +1141,36 @@ err_put:
 	return err;
 }
 
+#define BPF_MAP_FREEZE_LAST_FIELD map_fd
+
+static int map_freeze(const union bpf_attr *attr)
+{
+	int err = 0, ufd = attr->map_fd;
+	struct bpf_map *map;
+	struct fd f;
+
+	if (CHECK_ATTR(BPF_MAP_FREEZE))
+		return -EINVAL;
+
+	f = fdget(ufd);
+	map = __bpf_map_get(f);
+	if (IS_ERR(map))
+		return PTR_ERR(map);
+	if (READ_ONCE(map->frozen)) {
+		err = -EBUSY;
+		goto err_put;
+	}
+	if (!capable(CAP_SYS_ADMIN)) {
+		err = -EPERM;
+		goto err_put;
+	}
+
+	WRITE_ONCE(map->frozen, true);
+err_put:
+	fdput(f);
+	return err;
+}
+
 static const struct bpf_prog_ops * const bpf_prog_types[] = {
 #define BPF_PROG_TYPE(_id, _name) \
 	[_id] = & _name ## _prog_ops,
@@ -2735,6 +2774,9 @@ SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, siz
 	case BPF_MAP_GET_NEXT_KEY:
 		err = map_get_next_key(&attr);
 		break;
+	case BPF_MAP_FREEZE:
+		err = map_freeze(&attr);
+		break;
 	case BPF_PROG_LOAD:
 		err = bpf_prog_load(&attr, uattr);
 		break;
-- 
cgit v1.2.3-55-g7522


From 3e0ddc4f3ff1436970e96e76f3df3c3b5f5173b6 Mon Sep 17 00:00:00 2001
From: Daniel Borkmann
Date: Tue, 9 Apr 2019 23:20:07 +0200
Subject: bpf: allow . char as part of the object name

Trivial addition to allow '.' aside from '_' as "special" characters
in the object name. Used to allow for substrings in maps from loader
side such as ".bss", ".data", ".rodata", but could also be useful for
other purposes.

Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Andrii Nakryiko <andriin@fb.com>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 kernel/bpf/syscall.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index b3ce516e5a20..198c9680bf0d 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -474,10 +474,10 @@ static int bpf_obj_name_cpy(char *dst, const char *src)
 	const char *end = src + BPF_OBJ_NAME_LEN;
 
 	memset(dst, 0, BPF_OBJ_NAME_LEN);
-
-	/* Copy all isalnum() and '_' char */
+	/* Copy all isalnum(), '_' and '.' chars. */
 	while (src < end && *src) {
-		if (!isalnum(*src) && *src != '_')
+		if (!isalnum(*src) &&
+		    *src != '_' && *src != '.')
 			return -EINVAL;
 		*dst++ = *src++;
 	}
-- 
cgit v1.2.3-55-g7522


From f063c889c9458354a92b235a51cbb60d30321070 Mon Sep 17 00:00:00 2001
From: Daniel Borkmann
Date: Tue, 9 Apr 2019 23:20:08 +0200
Subject: bpf: add specification for BTF Var and DataSec kinds

This adds the BTF specification and UAPI bits for supporting BTF Var
and DataSec kinds. This is following LLVM upstream commit ac4082b77e07
("[BPF] Add BTF Var and DataSec Support") which has been merged recently.
Var itself is for describing a global variable and DataSec to describe
ELF sections e.g. data/bss/rodata sections that hold one or multiple
global variables.

Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 Documentation/bpf/btf.rst | 57 +++++++++++++++++++++++++++++++++++++++++++++++
 include/uapi/linux/btf.h  | 32 ++++++++++++++++++++++----
 2 files changed, 85 insertions(+), 4 deletions(-)

diff --git a/Documentation/bpf/btf.rst b/Documentation/bpf/btf.rst
index 9a60a5d60e38..60d87d7363ec 100644
--- a/Documentation/bpf/btf.rst
+++ b/Documentation/bpf/btf.rst
@@ -82,6 +82,8 @@ sequentially and type id is assigned to each recognized type starting from id
     #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      */
 
 Note that the type section encodes debug info, not just pure types.
 ``BTF_KIND_FUNC`` is not a type, and it represents a defined subprogram.
@@ -393,6 +395,61 @@ refers to parameter type.
 If the function has variable arguments, the last parameter is encoded with
 ``name_off = 0`` and ``type = 0``.
 
+2.2.14 BTF_KIND_VAR
+~~~~~~~~~~~~~~~~~~~
+
+``struct btf_type`` encoding requirement:
+  * ``name_off``: offset to a valid C identifier
+  * ``info.kind_flag``: 0
+  * ``info.kind``: BTF_KIND_VAR
+  * ``info.vlen``: 0
+  * ``type``: the type of the variable
+
+``btf_type`` is followed by a single ``struct btf_variable`` with the
+following data::
+
+    struct btf_var {
+        __u32   linkage;
+    };
+
+``struct btf_var`` encoding:
+  * ``linkage``: currently only static variable 0, or globally allocated
+                 variable in ELF sections 1
+
+Not all type of global variables are supported by LLVM at this point.
+The following is currently available:
+
+  * static variables with or without section attributes
+  * global variables with section attributes
+
+The latter is for future extraction of map key/value type id's from a
+map definition.
+
+2.2.15 BTF_KIND_DATASEC
+~~~~~~~~~~~~~~~~~~~~~~~
+
+``struct btf_type`` encoding requirement:
+  * ``name_off``: offset to a valid name associated with a variable or
+                  one of .data/.bss/.rodata
+  * ``info.kind_flag``: 0
+  * ``info.kind``: BTF_KIND_DATASEC
+  * ``info.vlen``: # of variables
+  * ``size``: total section size in bytes (0 at compilation time, patched
+              to actual size by BPF loaders such as libbpf)
+
+``btf_type`` is followed by ``info.vlen`` number of ``struct btf_var_secinfo``.::
+
+    struct btf_var_secinfo {
+        __u32   type;
+        __u32   offset;
+        __u32   size;
+    };
+
+``struct btf_var_secinfo`` encoding:
+  * ``type``: the type of the BTF_KIND_VAR variable
+  * ``offset``: the in-section offset of the variable
+  * ``size``: the size of the variable in bytes
+
 3. BTF Kernel API
 *****************
 
diff --git a/include/uapi/linux/btf.h b/include/uapi/linux/btf.h
index 7b7475ef2f17..9310652ca4f9 100644
--- a/include/uapi/linux/btf.h
+++ b/include/uapi/linux/btf.h
@@ -39,11 +39,11 @@ struct btf_type {
 	 *             struct, union and fwd
 	 */
 	__u32 info;
-	/* "size" is used by INT, ENUM, STRUCT and UNION.
+	/* "size" is used by INT, ENUM, STRUCT, UNION and DATASEC.
 	 * "size" tells the size of the type it is describing.
 	 *
 	 * "type" is used by PTR, TYPEDEF, VOLATILE, CONST, RESTRICT,
-	 * FUNC and FUNC_PROTO.
+	 * FUNC, FUNC_PROTO and VAR.
 	 * "type" is a type_id referring to another type.
 	 */
 	union {
@@ -70,8 +70,10 @@ struct btf_type {
 #define BTF_KIND_RESTRICT	11	/* Restrict	*/
 #define BTF_KIND_FUNC		12	/* Function	*/
 #define BTF_KIND_FUNC_PROTO	13	/* Function Proto	*/
-#define BTF_KIND_MAX		13
-#define NR_BTF_KINDS		14
+#define BTF_KIND_VAR		14	/* Variable	*/
+#define BTF_KIND_DATASEC	15	/* Section	*/
+#define BTF_KIND_MAX		BTF_KIND_DATASEC
+#define NR_BTF_KINDS		(BTF_KIND_MAX + 1)
 
 /* For some specific BTF_KIND, "struct btf_type" is immediately
  * followed by extra data.
@@ -138,4 +140,26 @@ struct btf_param {
 	__u32	type;
 };
 
+enum {
+	BTF_VAR_STATIC = 0,
+	BTF_VAR_GLOBAL_ALLOCATED,
+};
+
+/* BTF_KIND_VAR is followed by a single "struct btf_var" to describe
+ * additional information related to the variable such as its linkage.
+ */
+struct btf_var {
+	__u32	linkage;
+};
+
+/* BTF_KIND_DATASEC is followed by multiple "struct btf_var_secinfo"
+ * to describe all BTF_KIND_VAR types it contains along with it's
+ * in-section offset as well as size.
+ */
+struct btf_var_secinfo {
+	__u32	type;
+	__u32	offset;
+	__u32	size;
+};
+
 #endif /* _UAPI__LINUX_BTF_H__ */
-- 
cgit v1.2.3-55-g7522


From 1dc92851849cc2235a1efef8f8d5a9255efc5f13 Mon Sep 17 00:00:00 2001
From: Daniel Borkmann
Date: Tue, 9 Apr 2019 23:20:09 +0200
Subject: bpf: kernel side support for BTF Var and DataSec

This work adds kernel-side verification, logging and seq_show dumping
of BTF Var and DataSec kinds which are emitted with latest LLVM. The
following constraints apply:

BTF Var must have:

- Its kind_flag is 0
- Its vlen is 0
- Must point to a valid type
- Type must not resolve to a forward type
- Size of underlying type must be > 0
- Must have a valid name
- Can only be a source type, not sink or intermediate one
- Name may include dots (e.g. in case of static variables
  inside functions)
- Cannot be a member of a struct/union
- Linkage so far can either only be static or global/allocated

BTF DataSec must have:

- Its kind_flag is 0
- Its vlen cannot be 0
- Its size cannot be 0
- Must have a valid name
- Can only be a source type, not sink or intermediate one
- Name may include dots (e.g. to represent .bss, .data, .rodata etc)
- Cannot be a member of a struct/union
- Inner btf_var_secinfo array with {type,offset,size} triple
  must be sorted by offset in ascending order
- Type must always point to BTF Var
- BTF resolved size of Var must be <= size provided by triple
- DataSec size must be >= sum of triple sizes (thus holes
  are allowed)

btf_var_resolve(), btf_ptr_resolve() and btf_modifier_resolve()
are on a high level quite similar but each come with slight,
subtle differences. They could potentially be a bit refactored
in future which hasn't been done here to ease review.

Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 kernel/bpf/btf.c | 417 ++++++++++++++++++++++++++++++++++++++++++++++++++++---
 1 file changed, 397 insertions(+), 20 deletions(-)

diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index bd3921b1514b..0cecf6bab61b 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -185,6 +185,16 @@
 	     i < btf_type_vlen(struct_type);				\
 	     i++, member++)
 
+#define for_each_vsi(i, struct_type, member)			\
+	for (i = 0, member = btf_type_var_secinfo(struct_type);	\
+	     i < btf_type_vlen(struct_type);			\
+	     i++, member++)
+
+#define for_each_vsi_from(i, from, struct_type, member)				\
+	for (i = from, member = btf_type_var_secinfo(struct_type) + from;	\
+	     i < btf_type_vlen(struct_type);					\
+	     i++, member++)
+
 static DEFINE_IDR(btf_idr);
 static DEFINE_SPINLOCK(btf_idr_lock);
 
@@ -262,6 +272,8 @@ static const char * const btf_kind_str[NR_BTF_KINDS] = {
 	[BTF_KIND_RESTRICT]	= "RESTRICT",
 	[BTF_KIND_FUNC]		= "FUNC",
 	[BTF_KIND_FUNC_PROTO]	= "FUNC_PROTO",
+	[BTF_KIND_VAR]		= "VAR",
+	[BTF_KIND_DATASEC]	= "DATASEC",
 };
 
 struct btf_kind_operations {
@@ -375,13 +387,36 @@ static bool btf_type_is_int(const struct btf_type *t)
 	return BTF_INFO_KIND(t->info) == BTF_KIND_INT;
 }
 
+static bool btf_type_is_var(const struct btf_type *t)
+{
+	return BTF_INFO_KIND(t->info) == BTF_KIND_VAR;
+}
+
+static bool btf_type_is_datasec(const struct btf_type *t)
+{
+	return BTF_INFO_KIND(t->info) == BTF_KIND_DATASEC;
+}
+
+/* Types that act only as a source, not sink or intermediate
+ * type when resolving.
+ */
+static bool btf_type_is_resolve_source_only(const struct btf_type *t)
+{
+	return btf_type_is_var(t) ||
+	       btf_type_is_datasec(t);
+}
+
 /* What types need to be resolved?
  *
  * btf_type_is_modifier() is an obvious one.
  *
  * btf_type_is_struct() because its member refers to
  * another type (through member->type).
-
+ *
+ * btf_type_is_var() because the variable refers to
+ * another type. btf_type_is_datasec() holds multiple
+ * btf_type_is_var() types that need resolving.
+ *
  * btf_type_is_array() because its element (array->type)
  * refers to another type.  Array can be thought of a
  * special case of struct while array just has the same
@@ -390,9 +425,11 @@ static bool btf_type_is_int(const struct btf_type *t)
 static bool btf_type_needs_resolve(const struct btf_type *t)
 {
 	return btf_type_is_modifier(t) ||
-		btf_type_is_ptr(t) ||
-		btf_type_is_struct(t) ||
-		btf_type_is_array(t);
+	       btf_type_is_ptr(t) ||
+	       btf_type_is_struct(t) ||
+	       btf_type_is_array(t) ||
+	       btf_type_is_var(t) ||
+	       btf_type_is_datasec(t);
 }
 
 /* t->size can be used */
@@ -403,6 +440,7 @@ static bool btf_type_has_size(const struct btf_type *t)
 	case BTF_KIND_STRUCT:
 	case BTF_KIND_UNION:
 	case BTF_KIND_ENUM:
+	case BTF_KIND_DATASEC:
 		return true;
 	}
 
@@ -467,6 +505,16 @@ static const struct btf_enum *btf_type_enum(const struct btf_type *t)
 	return (const struct btf_enum *)(t + 1);
 }
 
+static const struct btf_var *btf_type_var(const struct btf_type *t)
+{
+	return (const struct btf_var *)(t + 1);
+}
+
+static const struct btf_var_secinfo *btf_type_var_secinfo(const struct btf_type *t)
+{
+	return (const struct btf_var_secinfo *)(t + 1);
+}
+
 static const struct btf_kind_operations *btf_type_ops(const struct btf_type *t)
 {
 	return kind_ops[BTF_INFO_KIND(t->info)];
@@ -478,23 +526,31 @@ static bool btf_name_offset_valid(const struct btf *btf, u32 offset)
 		offset < btf->hdr.str_len;
 }
 
-/* Only C-style identifier is permitted. This can be relaxed if
- * necessary.
- */
-static bool btf_name_valid_identifier(const struct btf *btf, u32 offset)
+static bool __btf_name_char_ok(char c, bool first, bool dot_ok)
+{
+	if ((first ? !isalpha(c) :
+		     !isalnum(c)) &&
+	    c != '_' &&
+	    ((c == '.' && !dot_ok) ||
+	      c != '.'))
+		return false;
+	return true;
+}
+
+static bool __btf_name_valid(const struct btf *btf, u32 offset, bool dot_ok)
 {
 	/* offset must be valid */
 	const char *src = &btf->strings[offset];
 	const char *src_limit;
 
-	if (!isalpha(*src) && *src != '_')
+	if (!__btf_name_char_ok(*src, true, dot_ok))
 		return false;
 
 	/* set a limit on identifier length */
 	src_limit = src + KSYM_NAME_LEN;
 	src++;
 	while (*src && src < src_limit) {
-		if (!isalnum(*src) && *src != '_')
+		if (!__btf_name_char_ok(*src, false, dot_ok))
 			return false;
 		src++;
 	}
@@ -502,6 +558,19 @@ static bool btf_name_valid_identifier(const struct btf *btf, u32 offset)
 	return !*src;
 }
 
+/* Only C-style identifier is permitted. This can be relaxed if
+ * necessary.
+ */
+static bool btf_name_valid_identifier(const struct btf *btf, u32 offset)
+{
+	return __btf_name_valid(btf, offset, false);
+}
+
+static bool btf_name_valid_section(const struct btf *btf, u32 offset)
+{
+	return __btf_name_valid(btf, offset, true);
+}
+
 static const char *__btf_name_by_offset(const struct btf *btf, u32 offset)
 {
 	if (!offset)
@@ -697,6 +766,32 @@ static void btf_verifier_log_member(struct btf_verifier_env *env,
 	__btf_verifier_log(log, "\n");
 }
 
+__printf(4, 5)
+static void btf_verifier_log_vsi(struct btf_verifier_env *env,
+				 const struct btf_type *datasec_type,
+				 const struct btf_var_secinfo *vsi,
+				 const char *fmt, ...)
+{
+	struct bpf_verifier_log *log = &env->log;
+	va_list args;
+
+	if (!bpf_verifier_log_needed(log))
+		return;
+	if (env->phase != CHECK_META)
+		btf_verifier_log_type(env, datasec_type, NULL);
+
+	__btf_verifier_log(log, "\t type_id=%u offset=%u size=%u",
+			   vsi->type, vsi->offset, vsi->size);
+	if (fmt && *fmt) {
+		__btf_verifier_log(log, " ");
+		va_start(args, fmt);
+		bpf_verifier_vlog(log, fmt, args);
+		va_end(args);
+	}
+
+	__btf_verifier_log(log, "\n");
+}
+
 static void btf_verifier_log_hdr(struct btf_verifier_env *env,
 				 u32 btf_data_size)
 {
@@ -974,7 +1069,8 @@ const struct btf_type *btf_type_id_size(const struct btf *btf,
 	} else if (btf_type_is_ptr(size_type)) {
 		size = sizeof(void *);
 	} else {
-		if (WARN_ON_ONCE(!btf_type_is_modifier(size_type)))
+		if (WARN_ON_ONCE(!btf_type_is_modifier(size_type) &&
+				 !btf_type_is_var(size_type)))
 			return NULL;
 
 		size = btf->resolved_sizes[size_type_id];
@@ -1509,7 +1605,7 @@ static int btf_modifier_resolve(struct btf_verifier_env *env,
 	u32 next_type_size = 0;
 
 	next_type = btf_type_by_id(btf, next_type_id);
-	if (!next_type) {
+	if (!next_type || btf_type_is_resolve_source_only(next_type)) {
 		btf_verifier_log_type(env, v->t, "Invalid type_id");
 		return -EINVAL;
 	}
@@ -1542,6 +1638,53 @@ static int btf_modifier_resolve(struct btf_verifier_env *env,
 	return 0;
 }
 
+static int btf_var_resolve(struct btf_verifier_env *env,
+			   const struct resolve_vertex *v)
+{
+	const struct btf_type *next_type;
+	const struct btf_type *t = v->t;
+	u32 next_type_id = t->type;
+	struct btf *btf = env->btf;
+	u32 next_type_size;
+
+	next_type = btf_type_by_id(btf, next_type_id);
+	if (!next_type || btf_type_is_resolve_source_only(next_type)) {
+		btf_verifier_log_type(env, v->t, "Invalid type_id");
+		return -EINVAL;
+	}
+
+	if (!env_type_is_resolve_sink(env, next_type) &&
+	    !env_type_is_resolved(env, next_type_id))
+		return env_stack_push(env, next_type, next_type_id);
+
+	if (btf_type_is_modifier(next_type)) {
+		const struct btf_type *resolved_type;
+		u32 resolved_type_id;
+
+		resolved_type_id = next_type_id;
+		resolved_type = btf_type_id_resolve(btf, &resolved_type_id);
+
+		if (btf_type_is_ptr(resolved_type) &&
+		    !env_type_is_resolve_sink(env, resolved_type) &&
+		    !env_type_is_resolved(env, resolved_type_id))
+			return env_stack_push(env, resolved_type,
+					      resolved_type_id);
+	}
+
+	/* We must resolve to something concrete at this point, no
+	 * forward types or similar that would resolve to size of
+	 * zero is allowed.
+	 */
+	if (!btf_type_id_size(btf, &next_type_id, &next_type_size)) {
+		btf_verifier_log_type(env, v->t, "Invalid type_id");
+		return -EINVAL;
+	}
+
+	env_stack_pop_resolved(env, next_type_id, next_type_size);
+
+	return 0;
+}
+
 static int btf_ptr_resolve(struct btf_verifier_env *env,
 			   const struct resolve_vertex *v)
 {
@@ -1551,7 +1694,7 @@ static int btf_ptr_resolve(struct btf_verifier_env *env,
 	struct btf *btf = env->btf;
 
 	next_type = btf_type_by_id(btf, next_type_id);
-	if (!next_type) {
+	if (!next_type || btf_type_is_resolve_source_only(next_type)) {
 		btf_verifier_log_type(env, v->t, "Invalid type_id");
 		return -EINVAL;
 	}
@@ -1609,6 +1752,15 @@ static void btf_modifier_seq_show(const struct btf *btf,
 	btf_type_ops(t)->seq_show(btf, t, type_id, data, bits_offset, m);
 }
 
+static void btf_var_seq_show(const struct btf *btf, const struct btf_type *t,
+			     u32 type_id, void *data, u8 bits_offset,
+			     struct seq_file *m)
+{
+	t = btf_type_id_resolve(btf, &type_id);
+
+	btf_type_ops(t)->seq_show(btf, t, type_id, data, bits_offset, m);
+}
+
 static void btf_ptr_seq_show(const struct btf *btf, const struct btf_type *t,
 			     u32 type_id, void *data, u8 bits_offset,
 			     struct seq_file *m)
@@ -1776,7 +1928,8 @@ static int btf_array_resolve(struct btf_verifier_env *env,
 	/* Check array->index_type */
 	index_type_id = array->index_type;
 	index_type = btf_type_by_id(btf, index_type_id);
-	if (btf_type_nosize_or_null(index_type)) {
+	if (btf_type_is_resolve_source_only(index_type) ||
+	    btf_type_nosize_or_null(index_type)) {
 		btf_verifier_log_type(env, v->t, "Invalid index");
 		return -EINVAL;
 	}
@@ -1795,7 +1948,8 @@ static int btf_array_resolve(struct btf_verifier_env *env,
 	/* Check array->type */
 	elem_type_id = array->type;
 	elem_type = btf_type_by_id(btf, elem_type_id);
-	if (btf_type_nosize_or_null(elem_type)) {
+	if (btf_type_is_resolve_source_only(elem_type) ||
+	    btf_type_nosize_or_null(elem_type)) {
 		btf_verifier_log_type(env, v->t,
 				      "Invalid elem");
 		return -EINVAL;
@@ -2016,7 +2170,8 @@ static int btf_struct_resolve(struct btf_verifier_env *env,
 		const struct btf_type *member_type = btf_type_by_id(env->btf,
 								member_type_id);
 
-		if (btf_type_nosize_or_null(member_type)) {
+		if (btf_type_is_resolve_source_only(member_type) ||
+		    btf_type_nosize_or_null(member_type)) {
 			btf_verifier_log_member(env, v->t, member,
 						"Invalid member");
 			return -EINVAL;
@@ -2411,6 +2566,222 @@ static struct btf_kind_operations func_ops = {
 	.seq_show = btf_df_seq_show,
 };
 
+static s32 btf_var_check_meta(struct btf_verifier_env *env,
+			      const struct btf_type *t,
+			      u32 meta_left)
+{
+	const struct btf_var *var;
+	u32 meta_needed = sizeof(*var);
+
+	if (meta_left < meta_needed) {
+		btf_verifier_log_basic(env, t,
+				       "meta_left:%u meta_needed:%u",
+				       meta_left, meta_needed);
+		return -EINVAL;
+	}
+
+	if (btf_type_vlen(t)) {
+		btf_verifier_log_type(env, t, "vlen != 0");
+		return -EINVAL;
+	}
+
+	if (btf_type_kflag(t)) {
+		btf_verifier_log_type(env, t, "Invalid btf_info kind_flag");
+		return -EINVAL;
+	}
+
+	if (!t->name_off ||
+	    !__btf_name_valid(env->btf, t->name_off, true)) {
+		btf_verifier_log_type(env, t, "Invalid name");
+		return -EINVAL;
+	}
+
+	/* A var cannot be in type void */
+	if (!t->type || !BTF_TYPE_ID_VALID(t->type)) {
+		btf_verifier_log_type(env, t, "Invalid type_id");
+		return -EINVAL;
+	}
+
+	var = btf_type_var(t);
+	if (var->linkage != BTF_VAR_STATIC &&
+	    var->linkage != BTF_VAR_GLOBAL_ALLOCATED) {
+		btf_verifier_log_type(env, t, "Linkage not supported");
+		return -EINVAL;
+	}
+
+	btf_verifier_log_type(env, t, NULL);
+
+	return meta_needed;
+}
+
+static void btf_var_log(struct btf_verifier_env *env, const struct btf_type *t)
+{
+	const struct btf_var *var = btf_type_var(t);
+
+	btf_verifier_log(env, "type_id=%u linkage=%u", t->type, var->linkage);
+}
+
+static const struct btf_kind_operations var_ops = {
+	.check_meta		= btf_var_check_meta,
+	.resolve		= btf_var_resolve,
+	.check_member		= btf_df_check_member,
+	.check_kflag_member	= btf_df_check_kflag_member,
+	.log_details		= btf_var_log,
+	.seq_show		= btf_var_seq_show,
+};
+
+static s32 btf_datasec_check_meta(struct btf_verifier_env *env,
+				  const struct btf_type *t,
+				  u32 meta_left)
+{
+	const struct btf_var_secinfo *vsi;
+	u64 last_vsi_end_off = 0, sum = 0;
+	u32 i, meta_needed;
+
+	meta_needed = btf_type_vlen(t) * sizeof(*vsi);
+	if (meta_left < meta_needed) {
+		btf_verifier_log_basic(env, t,
+				       "meta_left:%u meta_needed:%u",
+				       meta_left, meta_needed);
+		return -EINVAL;
+	}
+
+	if (!btf_type_vlen(t)) {
+		btf_verifier_log_type(env, t, "vlen == 0");
+		return -EINVAL;
+	}
+
+	if (!t->size) {
+		btf_verifier_log_type(env, t, "size == 0");
+		return -EINVAL;
+	}
+
+	if (btf_type_kflag(t)) {
+		btf_verifier_log_type(env, t, "Invalid btf_info kind_flag");
+		return -EINVAL;
+	}
+
+	if (!t->name_off ||
+	    !btf_name_valid_section(env->btf, t->name_off)) {
+		btf_verifier_log_type(env, t, "Invalid name");
+		return -EINVAL;
+	}
+
+	btf_verifier_log_type(env, t, NULL);
+
+	for_each_vsi(i, t, vsi) {
+		/* A var cannot be in type void */
+		if (!vsi->type || !BTF_TYPE_ID_VALID(vsi->type)) {
+			btf_verifier_log_vsi(env, t, vsi,
+					     "Invalid type_id");
+			return -EINVAL;
+		}
+
+		if (vsi->offset < last_vsi_end_off || vsi->offset >= t->size) {
+			btf_verifier_log_vsi(env, t, vsi,
+					     "Invalid offset");
+			return -EINVAL;
+		}
+
+		if (!vsi->size || vsi->size > t->size) {
+			btf_verifier_log_vsi(env, t, vsi,
+					     "Invalid size");
+			return -EINVAL;
+		}
+
+		last_vsi_end_off = vsi->offset + vsi->size;
+		if (last_vsi_end_off > t->size) {
+			btf_verifier_log_vsi(env, t, vsi,
+					     "Invalid offset+size");
+			return -EINVAL;
+		}
+
+		btf_verifier_log_vsi(env, t, vsi, NULL);
+		sum += vsi->size;
+	}
+
+	if (t->size < sum) {
+		btf_verifier_log_type(env, t, "Invalid btf_info size");
+		return -EINVAL;
+	}
+
+	return meta_needed;
+}
+
+static int btf_datasec_resolve(struct btf_verifier_env *env,
+			       const struct resolve_vertex *v)
+{
+	const struct btf_var_secinfo *vsi;
+	struct btf *btf = env->btf;
+	u16 i;
+
+	for_each_vsi_from(i, v->next_member, v->t, vsi) {
+		u32 var_type_id = vsi->type, type_id, type_size = 0;
+		const struct btf_type *var_type = btf_type_by_id(env->btf,
+								 var_type_id);
+		if (!var_type || !btf_type_is_var(var_type)) {
+			btf_verifier_log_vsi(env, v->t, vsi,
+					     "Not a VAR kind member");
+			return -EINVAL;
+		}
+
+		if (!env_type_is_resolve_sink(env, var_type) &&
+		    !env_type_is_resolved(env, var_type_id)) {
+			env_stack_set_next_member(env, i + 1);
+			return env_stack_push(env, var_type, var_type_id);
+		}
+
+		type_id = var_type->type;
+		if (!btf_type_id_size(btf, &type_id, &type_size)) {
+			btf_verifier_log_vsi(env, v->t, vsi, "Invalid type");
+			return -EINVAL;
+		}
+
+		if (vsi->size < type_size) {
+			btf_verifier_log_vsi(env, v->t, vsi, "Invalid size");
+			return -EINVAL;
+		}
+	}
+
+	env_stack_pop_resolved(env, 0, 0);
+	return 0;
+}
+
+static void btf_datasec_log(struct btf_verifier_env *env,
+			    const struct btf_type *t)
+{
+	btf_verifier_log(env, "size=%u vlen=%u", t->size, btf_type_vlen(t));
+}
+
+static void btf_datasec_seq_show(const struct btf *btf,
+				 const struct btf_type *t, u32 type_id,
+				 void *data, u8 bits_offset,
+				 struct seq_file *m)
+{
+	const struct btf_var_secinfo *vsi;
+	const struct btf_type *var;
+	u32 i;
+
+	seq_printf(m, "section (\"%s\") = {", __btf_name_by_offset(btf, t->name_off));
+	for_each_vsi(i, t, vsi) {
+		var = btf_type_by_id(btf, vsi->type);
+		if (i)
+			seq_puts(m, ",");
+		btf_type_ops(var)->seq_show(btf, var, vsi->type,
+					    data + vsi->offset, bits_offset, m);
+	}
+	seq_puts(m, "}");
+}
+
+static const struct btf_kind_operations datasec_ops = {
+	.check_meta		= btf_datasec_check_meta,
+	.resolve		= btf_datasec_resolve,
+	.check_member		= btf_df_check_member,
+	.check_kflag_member	= btf_df_check_kflag_member,
+	.log_details		= btf_datasec_log,
+	.seq_show		= btf_datasec_seq_show,
+};
+
 static int btf_func_proto_check(struct btf_verifier_env *env,
 				const struct btf_type *t)
 {
@@ -2542,6 +2913,8 @@ static const struct btf_kind_operations * const kind_ops[NR_BTF_KINDS] = {
 	[BTF_KIND_RESTRICT] = &modifier_ops,
 	[BTF_KIND_FUNC] = &func_ops,
 	[BTF_KIND_FUNC_PROTO] = &func_proto_ops,
+	[BTF_KIND_VAR] = &var_ops,
+	[BTF_KIND_DATASEC] = &datasec_ops,
 };
 
 static s32 btf_check_meta(struct btf_verifier_env *env,
@@ -2622,13 +2995,17 @@ static bool btf_resolve_valid(struct btf_verifier_env *env,
 	if (!env_type_is_resolved(env, type_id))
 		return false;
 
-	if (btf_type_is_struct(t))
+	if (btf_type_is_struct(t) || btf_type_is_datasec(t))
 		return !btf->resolved_ids[type_id] &&
-			!btf->resolved_sizes[type_id];
+		       !btf->resolved_sizes[type_id];
 
-	if (btf_type_is_modifier(t) || btf_type_is_ptr(t)) {
+	if (btf_type_is_modifier(t) || btf_type_is_ptr(t) ||
+	    btf_type_is_var(t)) {
 		t = btf_type_id_resolve(btf, &type_id);
-		return t && !btf_type_is_modifier(t);
+		return t &&
+		       !btf_type_is_modifier(t) &&
+		       !btf_type_is_var(t) &&
+		       !btf_type_is_datasec(t);
 	}
 
 	if (btf_type_is_array(t)) {
-- 
cgit v1.2.3-55-g7522


From 2824ecb7010f6a20e9a4140512b798469ab066cc Mon Sep 17 00:00:00 2001
From: Daniel Borkmann
Date: Tue, 9 Apr 2019 23:20:10 +0200
Subject: bpf: allow for key-less BTF in array map

Given we'll be reusing BPF array maps for global data/bss/rodata
sections, we need a way to associate BTF DataSec type as its map
value type. In usual cases we have this ugly BPF_ANNOTATE_KV_PAIR()
macro hack e.g. via 38d5d3b3d5db ("bpf: Introduce BPF_ANNOTATE_KV_PAIR")
to get initial map to type association going. While more use cases
for it are discouraged, this also won't work for global data since
the use of array map is a BPF loader detail and therefore unknown
at compilation time. For array maps with just a single entry we make
an exception in terms of BTF in that key type is declared optional
if value type is of DataSec type. The latter LLVM is guaranteed to
emit and it also aligns with how we regard global data maps as just
a plain buffer area reusing existing map facilities for allowing
things like introspection with existing tools.

Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/linux/btf.h   |  1 +
 kernel/bpf/arraymap.c | 15 ++++++++++++++-
 kernel/bpf/btf.c      |  2 +-
 kernel/bpf/syscall.c  | 15 +++++++++++----
 4 files changed, 27 insertions(+), 6 deletions(-)

diff --git a/include/linux/btf.h b/include/linux/btf.h
index 455d31b55828..64cdf2a23d42 100644
--- a/include/linux/btf.h
+++ b/include/linux/btf.h
@@ -51,6 +51,7 @@ bool btf_member_is_reg_int(const struct btf *btf, const struct btf_type *s,
 			   const struct btf_member *m,
 			   u32 expected_offset, u32 expected_size);
 int btf_find_spin_lock(const struct btf *btf, const struct btf_type *t);
+bool btf_type_is_void(const struct btf_type *t);
 
 #ifdef CONFIG_BPF_SYSCALL
 const struct btf_type *btf_type_by_id(const struct btf *btf, u32 type_id);
diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c
index 217b10bd9f48..584636c9e2eb 100644
--- a/kernel/bpf/arraymap.c
+++ b/kernel/bpf/arraymap.c
@@ -391,7 +391,8 @@ static void array_map_seq_show_elem(struct bpf_map *map, void *key,
 		return;
 	}
 
-	seq_printf(m, "%u: ", *(u32 *)key);
+	if (map->btf_key_type_id)
+		seq_printf(m, "%u: ", *(u32 *)key);
 	btf_type_seq_show(map->btf, map->btf_value_type_id, value, m);
 	seq_puts(m, "\n");
 
@@ -428,6 +429,18 @@ static int array_map_check_btf(const struct bpf_map *map,
 {
 	u32 int_data;
 
+	/* One exception for keyless BTF: .bss/.data/.rodata map */
+	if (btf_type_is_void(key_type)) {
+		if (map->map_type != BPF_MAP_TYPE_ARRAY ||
+		    map->max_entries != 1)
+			return -EINVAL;
+
+		if (BTF_INFO_KIND(value_type->info) != BTF_KIND_DATASEC)
+			return -EINVAL;
+
+		return 0;
+	}
+
 	if (BTF_INFO_KIND(key_type->info) != BTF_KIND_INT)
 		return -EINVAL;
 
diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index 0cecf6bab61b..cad09858a5f2 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -326,7 +326,7 @@ static bool btf_type_is_modifier(const struct btf_type *t)
 	return false;
 }
 
-static bool btf_type_is_void(const struct btf_type *t)
+bool btf_type_is_void(const struct btf_type *t)
 {
 	return t == &btf_void;
 }
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 198c9680bf0d..438199e2eca4 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -504,9 +504,16 @@ static int map_check_btf(struct bpf_map *map, const struct btf *btf,
 	u32 key_size, value_size;
 	int ret = 0;
 
-	key_type = btf_type_id_size(btf, &btf_key_id, &key_size);
-	if (!key_type || key_size != map->key_size)
-		return -EINVAL;
+	/* Some maps allow key to be unspecified. */
+	if (btf_key_id) {
+		key_type = btf_type_id_size(btf, &btf_key_id, &key_size);
+		if (!key_type || key_size != map->key_size)
+			return -EINVAL;
+	} else {
+		key_type = btf_type_by_id(btf, 0);
+		if (!map->ops->map_check_btf)
+			return -EINVAL;
+	}
 
 	value_type = btf_type_id_size(btf, &btf_value_id, &value_size);
 	if (!value_type || value_size != map->value_size)
@@ -573,7 +580,7 @@ static int map_create(union bpf_attr *attr)
 	if (attr->btf_key_type_id || attr->btf_value_type_id) {
 		struct btf *btf;
 
-		if (!attr->btf_key_type_id || !attr->btf_value_type_id) {
+		if (!attr->btf_value_type_id) {
 			err = -EINVAL;
 			goto free_map_nouncharge;
 		}
-- 
cgit v1.2.3-55-g7522


From c83fef6bc5627bd0484a151212449270ab294cd9 Mon Sep 17 00:00:00 2001
From: Daniel Borkmann
Date: Tue, 9 Apr 2019 23:20:11 +0200
Subject: bpf: sync {btf, bpf}.h uapi header from tools infrastructure

Pull in latest changes from both headers, so we can make use of
them in libbpf.

Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/include/uapi/linux/bpf.h | 20 ++++++++++++++++++--
 tools/include/uapi/linux/btf.h | 32 ++++++++++++++++++++++++++++----
 2 files changed, 46 insertions(+), 6 deletions(-)

diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 837024512baf..af1cbd951f26 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -105,6 +105,7 @@ enum bpf_cmd {
 	BPF_BTF_GET_FD_BY_ID,
 	BPF_TASK_FD_QUERY,
 	BPF_MAP_LOOKUP_AND_DELETE_ELEM,
+	BPF_MAP_FREEZE,
 };
 
 enum bpf_map_type {
@@ -255,8 +256,19 @@ enum bpf_attach_type {
  */
 #define BPF_F_ANY_ALIGNMENT	(1U << 1)
 
-/* when bpf_ldimm64->src_reg == BPF_PSEUDO_MAP_FD, bpf_ldimm64->imm == fd */
+/* When BPF ldimm64's insn[0].src_reg != 0 then this can have
+ * two extensions:
+ *
+ * insn[0].src_reg:  BPF_PSEUDO_MAP_FD   BPF_PSEUDO_MAP_VALUE
+ * insn[0].imm:      map fd              map fd
+ * insn[1].imm:      0                   offset into value
+ * insn[0].off:      0                   0
+ * insn[1].off:      0                   0
+ * ldimm64 rewrite:  address of map      address of map[0]+offset
+ * verifier type:    CONST_PTR_TO_MAP    PTR_TO_MAP_VALUE
+ */
 #define BPF_PSEUDO_MAP_FD	1
+#define BPF_PSEUDO_MAP_VALUE	2
 
 /* when bpf_call->src_reg == BPF_PSEUDO_CALL, bpf_call->imm == pc-relative
  * offset to another bpf function
@@ -283,7 +295,7 @@ enum bpf_attach_type {
 
 #define BPF_OBJ_NAME_LEN 16U
 
-/* Flags for accessing BPF object */
+/* Flags for accessing BPF object from syscall side. */
 #define BPF_F_RDONLY		(1U << 3)
 #define BPF_F_WRONLY		(1U << 4)
 
@@ -293,6 +305,10 @@ enum bpf_attach_type {
 /* Zero-initialize hash function seed. This should only be used for testing. */
 #define BPF_F_ZERO_SEED		(1U << 6)
 
+/* Flags for accessing BPF object from program side. */
+#define BPF_F_RDONLY_PROG	(1U << 7)
+#define BPF_F_WRONLY_PROG	(1U << 8)
+
 /* flags for BPF_PROG_QUERY */
 #define BPF_F_QUERY_EFFECTIVE	(1U << 0)
 
diff --git a/tools/include/uapi/linux/btf.h b/tools/include/uapi/linux/btf.h
index 7b7475ef2f17..9310652ca4f9 100644
--- a/tools/include/uapi/linux/btf.h
+++ b/tools/include/uapi/linux/btf.h
@@ -39,11 +39,11 @@ struct btf_type {
 	 *             struct, union and fwd
 	 */
 	__u32 info;
-	/* "size" is used by INT, ENUM, STRUCT and UNION.
+	/* "size" is used by INT, ENUM, STRUCT, UNION and DATASEC.
 	 * "size" tells the size of the type it is describing.
 	 *
 	 * "type" is used by PTR, TYPEDEF, VOLATILE, CONST, RESTRICT,
-	 * FUNC and FUNC_PROTO.
+	 * FUNC, FUNC_PROTO and VAR.
 	 * "type" is a type_id referring to another type.
 	 */
 	union {
@@ -70,8 +70,10 @@ struct btf_type {
 #define BTF_KIND_RESTRICT	11	/* Restrict	*/
 #define BTF_KIND_FUNC		12	/* Function	*/
 #define BTF_KIND_FUNC_PROTO	13	/* Function Proto	*/
-#define BTF_KIND_MAX		13
-#define NR_BTF_KINDS		14
+#define BTF_KIND_VAR		14	/* Variable	*/
+#define BTF_KIND_DATASEC	15	/* Section	*/
+#define BTF_KIND_MAX		BTF_KIND_DATASEC
+#define NR_BTF_KINDS		(BTF_KIND_MAX + 1)
 
 /* For some specific BTF_KIND, "struct btf_type" is immediately
  * followed by extra data.
@@ -138,4 +140,26 @@ struct btf_param {
 	__u32	type;
 };
 
+enum {
+	BTF_VAR_STATIC = 0,
+	BTF_VAR_GLOBAL_ALLOCATED,
+};
+
+/* BTF_KIND_VAR is followed by a single "struct btf_var" to describe
+ * additional information related to the variable such as its linkage.
+ */
+struct btf_var {
+	__u32	linkage;
+};
+
+/* BTF_KIND_DATASEC is followed by multiple "struct btf_var_secinfo"
+ * to describe all BTF_KIND_VAR types it contains along with it's
+ * in-section offset as well as size.
+ */
+struct btf_var_secinfo {
+	__u32	type;
+	__u32	offset;
+	__u32	size;
+};
+
 #endif /* _UAPI__LINUX_BTF_H__ */
-- 
cgit v1.2.3-55-g7522


From f8c7a4d4dc39991c1bc05847ea4378282708f935 Mon Sep 17 00:00:00 2001
From: Joe Stringer
Date: Tue, 9 Apr 2019 23:20:12 +0200
Subject: bpf, libbpf: refactor relocation handling

Adjust the code for relocations slightly with no functional changes,
so that upcoming patches that will introduce support for relocations
into the .data, .rodata and .bss sections can be added independent
of these changes.

Signed-off-by: Joe Stringer <joe@wand.net.nz>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Andrii Nakryiko <andriin@fb.com>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/lib/bpf/libbpf.c | 62 ++++++++++++++++++++++++++------------------------
 1 file changed, 32 insertions(+), 30 deletions(-)

diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 1ebfe7943d53..6dba0f01673b 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -871,20 +871,20 @@ static int bpf_object__elf_collect(struct bpf_object *obj, int flags)
 				obj->efile.symbols = data;
 				obj->efile.strtabidx = sh.sh_link;
 			}
-		} else if ((sh.sh_type == SHT_PROGBITS) &&
-			   (sh.sh_flags & SHF_EXECINSTR) &&
-			   (data->d_size > 0)) {
-			if (strcmp(name, ".text") == 0)
-				obj->efile.text_shndx = idx;
-			err = bpf_object__add_program(obj, data->d_buf,
-						      data->d_size, name, idx);
-			if (err) {
-				char errmsg[STRERR_BUFSIZE];
-				char *cp = libbpf_strerror_r(-err, errmsg,
-							     sizeof(errmsg));
-
-				pr_warning("failed to alloc program %s (%s): %s",
-					   name, obj->path, cp);
+		} 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_program(obj, data->d_buf,
+							      data->d_size, name, idx);
+				if (err) {
+					char errmsg[STRERR_BUFSIZE];
+					char *cp = libbpf_strerror_r(-err, errmsg,
+								     sizeof(errmsg));
+
+					pr_warning("failed to alloc program %s (%s): %s",
+						   name, obj->path, cp);
+				}
 			}
 		} else if (sh.sh_type == SHT_REL) {
 			void *reloc = obj->efile.reloc;
@@ -1046,24 +1046,26 @@ bpf_program__collect_reloc(struct bpf_program *prog, GElf_Shdr *shdr,
 			return -LIBBPF_ERRNO__RELOC;
 		}
 
-		/* TODO: 'maps' is sorted. We can use bsearch to make it faster. */
-		for (map_idx = 0; map_idx < nr_maps; map_idx++) {
-			if (maps[map_idx].offset == sym.st_value) {
-				pr_debug("relocation: find map %zd (%s) for insn %u\n",
-					 map_idx, maps[map_idx].name, insn_idx);
-				break;
+		if (sym.st_shndx == maps_shndx) {
+			/* TODO: 'maps' is sorted. We can use bsearch to make it faster. */
+			for (map_idx = 0; map_idx < nr_maps; map_idx++) {
+				if (maps[map_idx].offset == sym.st_value) {
+					pr_debug("relocation: find map %zd (%s) for insn %u\n",
+						 map_idx, maps[map_idx].name, insn_idx);
+					break;
+				}
 			}
-		}
 
-		if (map_idx >= nr_maps) {
-			pr_warning("bpf relocation: map_idx %d large than %d\n",
-				   (int)map_idx, (int)nr_maps - 1);
-			return -LIBBPF_ERRNO__RELOC;
-		}
+			if (map_idx >= nr_maps) {
+				pr_warning("bpf relocation: map_idx %d large than %d\n",
+					   (int)map_idx, (int)nr_maps - 1);
+				return -LIBBPF_ERRNO__RELOC;
+			}
 
-		prog->reloc_desc[i].type = RELO_LD64;
-		prog->reloc_desc[i].insn_idx = insn_idx;
-		prog->reloc_desc[i].map_idx = map_idx;
+			prog->reloc_desc[i].type = RELO_LD64;
+			prog->reloc_desc[i].insn_idx = insn_idx;
+			prog->reloc_desc[i].map_idx = map_idx;
+		}
 	}
 	return 0;
 }
@@ -1425,7 +1427,7 @@ bpf_program__relocate(struct bpf_program *prog, struct bpf_object *obj)
 			}
 			insns[insn_idx].src_reg = BPF_PSEUDO_MAP_FD;
 			insns[insn_idx].imm = obj->maps[map_idx].fd;
-		} else {
+		} else if (prog->reloc_desc[i].type == RELO_CALL) {
 			err = bpf_program__reloc_text(prog, obj,
 						      &prog->reloc_desc[i]);
 			if (err)
-- 
cgit v1.2.3-55-g7522


From d859900c4c56dc4f0f8894c92a01dad86917453e Mon Sep 17 00:00:00 2001
From: Daniel Borkmann
Date: Tue, 9 Apr 2019 23:20:13 +0200
Subject: bpf, libbpf: support global data/bss/rodata sections

This work adds BPF loader support for global data sections
to libbpf. This allows to write BPF programs in more natural
C-like way by being able to define global variables and const
data.

Back at LPC 2018 [0] we presented a first prototype which
implemented support for global data sections by extending BPF
syscall where union bpf_attr would get additional memory/size
pair for each section passed during prog load in order to later
add this base address into the ldimm64 instruction along with
the user provided offset when accessing a variable. Consensus
from LPC was that for proper upstream support, it would be
more desirable to use maps instead of bpf_attr extension as
this would allow for introspection of these sections as well
as potential live updates of their content. This work follows
this path by taking the following steps from loader side:

 1) In bpf_object__elf_collect() step we pick up ".data",
    ".rodata", and ".bss" section information.

 2) If present, in bpf_object__init_internal_map() we add
    maps to the obj's map array that corresponds to each
    of the present sections. Given section size and access
    properties can differ, a single entry array map is
    created with value size that is corresponding to the
    ELF section size of .data, .bss or .rodata. These
    internal maps are integrated into the normal map
    handling of libbpf such that when user traverses all
    obj maps, they can be differentiated from user-created
    ones via bpf_map__is_internal(). In later steps when
    we actually create these maps in the kernel via
    bpf_object__create_maps(), then for .data and .rodata
    sections their content is copied into the map through
    bpf_map_update_elem(). For .bss this is not necessary
    since array map is already zero-initialized by default.
    Additionally, for .rodata the map is frozen as read-only
    after setup, such that neither from program nor syscall
    side writes would be possible.

 3) In bpf_program__collect_reloc() step, we record the
    corresponding map, insn index, and relocation type for
    the global data.

 4) And last but not least in the actual relocation step in
    bpf_program__relocate(), we mark the ldimm64 instruction
    with src_reg = BPF_PSEUDO_MAP_VALUE where in the first
    imm field the map's file descriptor is stored as similarly
    done as in BPF_PSEUDO_MAP_FD, and in the second imm field
    (as ldimm64 is 2-insn wide) we store the access offset
    into the section. Given these maps have only single element
    ldimm64's off remains zero in both parts.

 5) On kernel side, this special marked BPF_PSEUDO_MAP_VALUE
    load will then store the actual target address in order
    to have a 'map-lookup'-free access. That is, the actual
    map value base address + offset. The destination register
    in the verifier will then be marked as PTR_TO_MAP_VALUE,
    containing the fixed offset as reg->off and backing BPF
    map as reg->map_ptr. Meaning, it's treated as any other
    normal map value from verification side, only with
    efficient, direct value access instead of actual call to
    map lookup helper as in the typical case.

Currently, only support for static global variables has been
added, and libbpf rejects non-static global variables from
loading. This can be lifted until we have proper semantics
for how BPF will treat multi-object BPF loads. From BTF side,
libbpf will set the value type id of the types corresponding
to the ".bss", ".data" and ".rodata" names which LLVM will
emit without the object name prefix. The key type will be
left as zero, thus making use of the key-less BTF option in
array maps.

Simple example dump of program using globals vars in each
section:

  # bpftool prog
  [...]
  6784: sched_cls  name load_static_dat  tag a7e1291567277844  gpl
        loaded_at 2019-03-11T15:39:34+0000  uid 0
        xlated 1776B  jited 993B  memlock 4096B  map_ids 2238,2237,2235,2236,2239,2240

  # bpftool map show id 2237
  2237: array  name test_glo.bss  flags 0x0
        key 4B  value 64B  max_entries 1  memlock 4096B
  # bpftool map show id 2235
  2235: array  name test_glo.data  flags 0x0
        key 4B  value 64B  max_entries 1  memlock 4096B
  # bpftool map show id 2236
  2236: array  name test_glo.rodata  flags 0x80
        key 4B  value 96B  max_entries 1  memlock 4096B

  # bpftool prog dump xlated id 6784
  int load_static_data(struct __sk_buff * skb):
  ; int load_static_data(struct __sk_buff *skb)
     0: (b7) r6 = 0
  ; test_reloc(number, 0, &num0);
     1: (63) *(u32 *)(r10 -4) = r6
     2: (bf) r2 = r10
  ; int load_static_data(struct __sk_buff *skb)
     3: (07) r2 += -4
  ; test_reloc(number, 0, &num0);
     4: (18) r1 = map[id:2238]
     6: (18) r3 = map[id:2237][0]+0    <-- direct addr in .bss area
     8: (b7) r4 = 0
     9: (85) call array_map_update_elem#100464
    10: (b7) r1 = 1
  ; test_reloc(number, 1, &num1);
  [...]
  ; test_reloc(string, 2, str2);
   120: (18) r8 = map[id:2237][0]+16   <-- same here at offset +16
   122: (18) r1 = map[id:2239]
   124: (18) r3 = map[id:2237][0]+16
   126: (b7) r4 = 0
   127: (85) call array_map_update_elem#100464
   128: (b7) r1 = 120
  ; str1[5] = 'x';
   129: (73) *(u8 *)(r9 +5) = r1
  ; test_reloc(string, 3, str1);
   130: (b7) r1 = 3
   131: (63) *(u32 *)(r10 -4) = r1
   132: (b7) r9 = 3
   133: (bf) r2 = r10
  ; int load_static_data(struct __sk_buff *skb)
   134: (07) r2 += -4
  ; test_reloc(string, 3, str1);
   135: (18) r1 = map[id:2239]
   137: (18) r3 = map[id:2235][0]+16   <-- direct addr in .data area
   139: (b7) r4 = 0
   140: (85) call array_map_update_elem#100464
   141: (b7) r1 = 111
  ; __builtin_memcpy(&str2[2], "hello", sizeof("hello"));
   142: (73) *(u8 *)(r8 +6) = r1       <-- further access based on .bss data
   143: (b7) r1 = 108
   144: (73) *(u8 *)(r8 +5) = r1
  [...]

For Cilium use-case in particular, this enables migrating configuration
constants from Cilium daemon's generated header defines into global
data sections such that expensive runtime recompilations with LLVM can
be avoided altogether. Instead, the ELF file becomes effectively a
"template", meaning, it is compiled only once (!) and the Cilium daemon
will then rewrite relevant configuration data from the ELF's .data or
.rodata sections directly instead of recompiling the program. The
updated ELF is then loaded into the kernel and atomically replaces
the existing program in the networking datapath. More info in [0].

Based upon recent fix in LLVM, commit c0db6b6bd444 ("[BPF] Don't fail
for static variables").

  [0] LPC 2018, BPF track, "ELF relocation for static data in BPF",
      http://vger.kernel.org/lpc-bpf2018.html#session-3

Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Andrii Nakryiko <andriin@fb.com>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/lib/bpf/Makefile   |   2 +-
 tools/lib/bpf/bpf.c      |  10 ++
 tools/lib/bpf/bpf.h      |   1 +
 tools/lib/bpf/libbpf.c   | 342 ++++++++++++++++++++++++++++++++++++++++-------
 tools/lib/bpf/libbpf.h   |   1 +
 tools/lib/bpf/libbpf.map |   6 +
 6 files changed, 314 insertions(+), 48 deletions(-)

diff --git a/tools/lib/bpf/Makefile b/tools/lib/bpf/Makefile
index 2a578bfc0bca..008344507700 100644
--- a/tools/lib/bpf/Makefile
+++ b/tools/lib/bpf/Makefile
@@ -3,7 +3,7 @@
 
 BPF_VERSION = 0
 BPF_PATCHLEVEL = 0
-BPF_EXTRAVERSION = 2
+BPF_EXTRAVERSION = 3
 
 MAKEFLAGS += --no-print-directory
 
diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c
index a1db869a6fda..c039094ad3aa 100644
--- a/tools/lib/bpf/bpf.c
+++ b/tools/lib/bpf/bpf.c
@@ -429,6 +429,16 @@ int bpf_map_get_next_key(int fd, const void *key, void *next_key)
 	return sys_bpf(BPF_MAP_GET_NEXT_KEY, &attr, sizeof(attr));
 }
 
+int bpf_map_freeze(int fd)
+{
+	union bpf_attr attr;
+
+	memset(&attr, 0, sizeof(attr));
+	attr.map_fd = fd;
+
+	return sys_bpf(BPF_MAP_FREEZE, &attr, sizeof(attr));
+}
+
 int bpf_obj_pin(int fd, const char *pathname)
 {
 	union bpf_attr attr;
diff --git a/tools/lib/bpf/bpf.h b/tools/lib/bpf/bpf.h
index e2c0df7b831f..c9d218d21453 100644
--- a/tools/lib/bpf/bpf.h
+++ b/tools/lib/bpf/bpf.h
@@ -117,6 +117,7 @@ LIBBPF_API int bpf_map_lookup_and_delete_elem(int fd, const void *key,
 					      void *value);
 LIBBPF_API int bpf_map_delete_elem(int fd, const void *key);
 LIBBPF_API int bpf_map_get_next_key(int fd, const void *key, void *next_key);
+LIBBPF_API int bpf_map_freeze(int fd);
 LIBBPF_API int bpf_obj_pin(int fd, const char *pathname);
 LIBBPF_API int bpf_obj_get(const char *pathname);
 LIBBPF_API int bpf_prog_attach(int prog_fd, int attachable_fd,
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 6dba0f01673b..f7b245fbb960 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -7,6 +7,7 @@
  * Copyright (C) 2015 Wang Nan <wangnan0@huawei.com>
  * Copyright (C) 2015 Huawei Inc.
  * Copyright (C) 2017 Nicira, Inc.
+ * Copyright (C) 2019 Isovalent, Inc.
  */
 
 #ifndef _GNU_SOURCE
@@ -149,6 +150,7 @@ struct bpf_program {
 		enum {
 			RELO_LD64,
 			RELO_CALL,
+			RELO_DATA,
 		} type;
 		int insn_idx;
 		union {
@@ -182,6 +184,19 @@ struct bpf_program {
 	__u32 line_info_cnt;
 };
 
+enum libbpf_map_type {
+	LIBBPF_MAP_UNSPEC,
+	LIBBPF_MAP_DATA,
+	LIBBPF_MAP_BSS,
+	LIBBPF_MAP_RODATA,
+};
+
+static const char * const libbpf_type_to_btf_name[] = {
+	[LIBBPF_MAP_DATA]	= ".data",
+	[LIBBPF_MAP_BSS]	= ".bss",
+	[LIBBPF_MAP_RODATA]	= ".rodata",
+};
+
 struct bpf_map {
 	int fd;
 	char *name;
@@ -193,11 +208,18 @@ struct bpf_map {
 	__u32 btf_value_type_id;
 	void *priv;
 	bpf_map_clear_priv_t clear_priv;
+	enum libbpf_map_type libbpf_type;
+};
+
+struct bpf_secdata {
+	void *rodata;
+	void *data;
 };
 
 static LIST_HEAD(bpf_objects_list);
 
 struct bpf_object {
+	char name[BPF_OBJ_NAME_LEN];
 	char license[64];
 	__u32 kern_version;
 
@@ -205,6 +227,7 @@ struct bpf_object {
 	size_t nr_programs;
 	struct bpf_map *maps;
 	size_t nr_maps;
+	struct bpf_secdata sections;
 
 	bool loaded;
 	bool has_pseudo_calls;
@@ -220,6 +243,9 @@ struct bpf_object {
 		Elf *elf;
 		GElf_Ehdr ehdr;
 		Elf_Data *symbols;
+		Elf_Data *data;
+		Elf_Data *rodata;
+		Elf_Data *bss;
 		size_t strtabidx;
 		struct {
 			GElf_Shdr shdr;
@@ -228,6 +254,9 @@ struct bpf_object {
 		int nr_reloc;
 		int maps_shndx;
 		int text_shndx;
+		int data_shndx;
+		int rodata_shndx;
+		int bss_shndx;
 	} efile;
 	/*
 	 * All loaded bpf_object is linked in a list, which is
@@ -449,6 +478,7 @@ static struct bpf_object *bpf_object__new(const char *path,
 					  size_t obj_buf_sz)
 {
 	struct bpf_object *obj;
+	char *end;
 
 	obj = calloc(1, sizeof(struct bpf_object) + strlen(path) + 1);
 	if (!obj) {
@@ -457,8 +487,14 @@ static struct bpf_object *bpf_object__new(const char *path,
 	}
 
 	strcpy(obj->path, path);
-	obj->efile.fd = -1;
+	/* Using basename() GNU version which doesn't modify arg. */
+	strncpy(obj->name, basename((void *)path),
+		sizeof(obj->name) - 1);
+	end = strchr(obj->name, '.');
+	if (end)
+		*end = 0;
 
+	obj->efile.fd = -1;
 	/*
 	 * Caller of this function should also calls
 	 * bpf_object__elf_finish() after data collection to return
@@ -468,6 +504,9 @@ static struct bpf_object *bpf_object__new(const char *path,
 	obj->efile.obj_buf = obj_buf;
 	obj->efile.obj_buf_sz = obj_buf_sz;
 	obj->efile.maps_shndx = -1;
+	obj->efile.data_shndx = -1;
+	obj->efile.rodata_shndx = -1;
+	obj->efile.bss_shndx = -1;
 
 	obj->loaded = false;
 
@@ -486,6 +525,9 @@ 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;
 
 	zfree(&obj->efile.reloc);
 	obj->efile.nr_reloc = 0;
@@ -627,27 +669,76 @@ static bool bpf_map_type__is_map_in_map(enum bpf_map_type type)
 	return false;
 }
 
+static bool bpf_object__has_maps(const struct bpf_object *obj)
+{
+	return obj->efile.maps_shndx >= 0 ||
+	       obj->efile.data_shndx >= 0 ||
+	       obj->efile.rodata_shndx >= 0 ||
+	       obj->efile.bss_shndx >= 0;
+}
+
+static int
+bpf_object__init_internal_map(struct bpf_object *obj, struct bpf_map *map,
+			      enum libbpf_map_type type, Elf_Data *data,
+			      void **data_buff)
+{
+	struct bpf_map_def *def = &map->def;
+	char map_name[BPF_OBJ_NAME_LEN];
+
+	map->libbpf_type = type;
+	map->offset = ~(typeof(map->offset))0;
+	snprintf(map_name, sizeof(map_name), "%.8s%.7s", obj->name,
+		 libbpf_type_to_btf_name[type]);
+	map->name = strdup(map_name);
+	if (!map->name) {
+		pr_warning("failed to alloc map name\n");
+		return -ENOMEM;
+	}
+
+	def->type = BPF_MAP_TYPE_ARRAY;
+	def->key_size = sizeof(int);
+	def->value_size = data->d_size;
+	def->max_entries = 1;
+	def->map_flags = type == LIBBPF_MAP_RODATA ?
+			 BPF_F_RDONLY_PROG : 0;
+	if (data_buff) {
+		*data_buff = malloc(data->d_size);
+		if (!*data_buff) {
+			zfree(&map->name);
+			pr_warning("failed to alloc map content buffer\n");
+			return -ENOMEM;
+		}
+		memcpy(*data_buff, data->d_buf, data->d_size);
+	}
+
+	pr_debug("map %ld is \"%s\"\n", map - obj->maps, map->name);
+	return 0;
+}
+
 static int
 bpf_object__init_maps(struct bpf_object *obj, int flags)
 {
+	int i, map_idx, map_def_sz, nr_syms, nr_maps = 0, nr_maps_glob = 0;
 	bool strict = !(flags & MAPS_RELAX_COMPAT);
-	int i, map_idx, map_def_sz, nr_maps = 0;
-	Elf_Scn *scn;
-	Elf_Data *data = NULL;
 	Elf_Data *symbols = obj->efile.symbols;
+	Elf_Data *data = NULL;
+	int ret = 0;
 
-	if (obj->efile.maps_shndx < 0)
-		return -EINVAL;
 	if (!symbols)
 		return -EINVAL;
+	nr_syms = symbols->d_size / sizeof(GElf_Sym);
 
-	scn = elf_getscn(obj->efile.elf, obj->efile.maps_shndx);
-	if (scn)
-		data = elf_getdata(scn, NULL);
-	if (!scn || !data) {
-		pr_warning("failed to get Elf_Data from map section %d\n",
-			   obj->efile.maps_shndx);
-		return -EINVAL;
+	if (obj->efile.maps_shndx >= 0) {
+		Elf_Scn *scn = elf_getscn(obj->efile.elf,
+					  obj->efile.maps_shndx);
+
+		if (scn)
+			data = elf_getdata(scn, NULL);
+		if (!scn || !data) {
+			pr_warning("failed to get Elf_Data from map section %d\n",
+				   obj->efile.maps_shndx);
+			return -EINVAL;
+		}
 	}
 
 	/*
@@ -657,7 +748,13 @@ bpf_object__init_maps(struct bpf_object *obj, int flags)
 	 *
 	 * TODO: Detect array of map and report error.
 	 */
-	for (i = 0; i < symbols->d_size / sizeof(GElf_Sym); i++) {
+	if (obj->efile.data_shndx >= 0)
+		nr_maps_glob++;
+	if (obj->efile.rodata_shndx >= 0)
+		nr_maps_glob++;
+	if (obj->efile.bss_shndx >= 0)
+		nr_maps_glob++;
+	for (i = 0; data && i < nr_syms; i++) {
 		GElf_Sym sym;
 
 		if (!gelf_getsym(symbols, i, &sym))
@@ -670,19 +767,21 @@ bpf_object__init_maps(struct bpf_object *obj, int flags)
 	/* Alloc obj->maps and fill nr_maps. */
 	pr_debug("maps in %s: %d maps in %zd bytes\n", obj->path,
 		 nr_maps, data->d_size);
-
-	if (!nr_maps)
+	if (!nr_maps && !nr_maps_glob)
 		return 0;
 
 	/* Assume equally sized map definitions */
-	map_def_sz = data->d_size / nr_maps;
-	if (!data->d_size || (data->d_size % nr_maps) != 0) {
-		pr_warning("unable to determine map definition size "
-			   "section %s, %d maps in %zd bytes\n",
-			   obj->path, nr_maps, data->d_size);
-		return -EINVAL;
+	if (data) {
+		map_def_sz = data->d_size / nr_maps;
+		if (!data->d_size || (data->d_size % nr_maps) != 0) {
+			pr_warning("unable to determine map definition size "
+				   "section %s, %d maps in %zd bytes\n",
+				   obj->path, nr_maps, data->d_size);
+			return -EINVAL;
+		}
 	}
 
+	nr_maps += nr_maps_glob;
 	obj->maps = calloc(nr_maps, sizeof(obj->maps[0]));
 	if (!obj->maps) {
 		pr_warning("alloc maps for object failed\n");
@@ -703,7 +802,7 @@ bpf_object__init_maps(struct bpf_object *obj, int flags)
 	/*
 	 * Fill obj->maps using data in "maps" section.
 	 */
-	for (i = 0, map_idx = 0; i < symbols->d_size / sizeof(GElf_Sym); i++) {
+	for (i = 0, map_idx = 0; data && i < nr_syms; i++) {
 		GElf_Sym sym;
 		const char *map_name;
 		struct bpf_map_def *def;
@@ -716,6 +815,8 @@ bpf_object__init_maps(struct bpf_object *obj, int flags)
 		map_name = elf_strptr(obj->efile.elf,
 				      obj->efile.strtabidx,
 				      sym.st_name);
+
+		obj->maps[map_idx].libbpf_type = LIBBPF_MAP_UNSPEC;
 		obj->maps[map_idx].offset = sym.st_value;
 		if (sym.st_value + map_def_sz > data->d_size) {
 			pr_warning("corrupted maps section in %s: last map \"%s\" too small\n",
@@ -764,8 +865,27 @@ bpf_object__init_maps(struct bpf_object *obj, int flags)
 		map_idx++;
 	}
 
-	qsort(obj->maps, obj->nr_maps, sizeof(obj->maps[0]), compare_bpf_map);
-	return 0;
+	/*
+	 * Populate rest of obj->maps with libbpf internal maps.
+	 */
+	if (obj->efile.data_shndx >= 0)
+		ret = bpf_object__init_internal_map(obj, &obj->maps[map_idx++],
+						    LIBBPF_MAP_DATA,
+						    obj->efile.data,
+						    &obj->sections.data);
+	if (!ret && obj->efile.rodata_shndx >= 0)
+		ret = bpf_object__init_internal_map(obj, &obj->maps[map_idx++],
+						    LIBBPF_MAP_RODATA,
+						    obj->efile.rodata,
+						    &obj->sections.rodata);
+	if (!ret && obj->efile.bss_shndx >= 0)
+		ret = bpf_object__init_internal_map(obj, &obj->maps[map_idx++],
+						    LIBBPF_MAP_BSS,
+						    obj->efile.bss, NULL);
+	if (!ret)
+		qsort(obj->maps, obj->nr_maps, sizeof(obj->maps[0]),
+		      compare_bpf_map);
+	return ret;
 }
 
 static bool section_have_execinstr(struct bpf_object *obj, int idx)
@@ -885,6 +1005,14 @@ static int bpf_object__elf_collect(struct bpf_object *obj, int flags)
 					pr_warning("failed to alloc program %s (%s): %s",
 						   name, obj->path, cp);
 				}
+			} else if (strcmp(name, ".data") == 0) {
+				obj->efile.data = data;
+				obj->efile.data_shndx = idx;
+			} else if (strcmp(name, ".rodata") == 0) {
+				obj->efile.rodata = data;
+				obj->efile.rodata_shndx = idx;
+			} else {
+				pr_debug("skip section(%d) %s\n", idx, name);
 			}
 		} else if (sh.sh_type == SHT_REL) {
 			void *reloc = obj->efile.reloc;
@@ -912,6 +1040,9 @@ static int bpf_object__elf_collect(struct bpf_object *obj, int flags)
 				obj->efile.reloc[n].shdr = sh;
 				obj->efile.reloc[n].data = data;
 			}
+		} else if (sh.sh_type == SHT_NOBITS && strcmp(name, ".bss") == 0) {
+			obj->efile.bss = data;
+			obj->efile.bss_shndx = idx;
 		} else {
 			pr_debug("skip section(%d) %s\n", idx, name);
 		}
@@ -938,7 +1069,7 @@ static int bpf_object__elf_collect(struct bpf_object *obj, int flags)
 			}
 		}
 	}
-	if (obj->efile.maps_shndx >= 0) {
+	if (bpf_object__has_maps(obj)) {
 		err = bpf_object__init_maps(obj, flags);
 		if (err)
 			goto out;
@@ -974,13 +1105,46 @@ bpf_object__find_program_by_title(struct bpf_object *obj, const char *title)
 	return NULL;
 }
 
+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;
+}
+
+static bool bpf_object__shndx_is_maps(const struct bpf_object *obj,
+				      int shndx)
+{
+	return shndx == obj->efile.maps_shndx;
+}
+
+static bool bpf_object__relo_in_known_section(const struct bpf_object *obj,
+					      int shndx)
+{
+	return shndx == obj->efile.text_shndx ||
+	       bpf_object__shndx_is_maps(obj, shndx) ||
+	       bpf_object__shndx_is_data(obj, shndx);
+}
+
+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)
+		return LIBBPF_MAP_BSS;
+	else if (shndx == obj->efile.rodata_shndx)
+		return LIBBPF_MAP_RODATA;
+	else
+		return LIBBPF_MAP_UNSPEC;
+}
+
 static int
 bpf_program__collect_reloc(struct bpf_program *prog, GElf_Shdr *shdr,
 			   Elf_Data *data, struct bpf_object *obj)
 {
 	Elf_Data *symbols = obj->efile.symbols;
-	int text_shndx = obj->efile.text_shndx;
-	int maps_shndx = obj->efile.maps_shndx;
 	struct bpf_map *maps = obj->maps;
 	size_t nr_maps = obj->nr_maps;
 	int i, nrels;
@@ -1000,7 +1164,10 @@ bpf_program__collect_reloc(struct bpf_program *prog, GElf_Shdr *shdr,
 		GElf_Sym sym;
 		GElf_Rel rel;
 		unsigned int insn_idx;
+		unsigned int shdr_idx;
 		struct bpf_insn *insns = prog->insns;
+		enum libbpf_map_type type;
+		const char *name;
 		size_t map_idx;
 
 		if (!gelf_getrel(data, i, &rel)) {
@@ -1015,13 +1182,18 @@ bpf_program__collect_reloc(struct bpf_program *prog, GElf_Shdr *shdr,
 				   GELF_R_SYM(rel.r_info));
 			return -LIBBPF_ERRNO__FORMAT;
 		}
-		pr_debug("relo for %lld value %lld name %d\n",
+
+		name = elf_strptr(obj->efile.elf, obj->efile.strtabidx,
+				  sym.st_name) ? : "<?>";
+
+		pr_debug("relo for %lld value %lld name %d (\'%s\')\n",
 			 (long long) (rel.r_info >> 32),
-			 (long long) sym.st_value, sym.st_name);
+			 (long long) sym.st_value, sym.st_name, name);
 
-		if (sym.st_shndx != maps_shndx && sym.st_shndx != text_shndx) {
-			pr_warning("Program '%s' contains non-map related relo data pointing to section %u\n",
-				   prog->section_name, sym.st_shndx);
+		shdr_idx = sym.st_shndx;
+		if (!bpf_object__relo_in_known_section(obj, shdr_idx)) {
+			pr_warning("Program '%s' contains unrecognized relo data pointing to section %u\n",
+				   prog->section_name, shdr_idx);
 			return -LIBBPF_ERRNO__RELOC;
 		}
 
@@ -1046,10 +1218,22 @@ bpf_program__collect_reloc(struct bpf_program *prog, GElf_Shdr *shdr,
 			return -LIBBPF_ERRNO__RELOC;
 		}
 
-		if (sym.st_shndx == maps_shndx) {
-			/* TODO: 'maps' is sorted. We can use bsearch to make it faster. */
+		if (bpf_object__shndx_is_maps(obj, shdr_idx) ||
+		    bpf_object__shndx_is_data(obj, shdr_idx)) {
+			type = bpf_object__section_to_libbpf_map_type(obj, shdr_idx);
+			if (type != LIBBPF_MAP_UNSPEC &&
+			    GELF_ST_BIND(sym.st_info) == STB_GLOBAL) {
+				pr_warning("bpf: relocation: not yet supported relo for non-static global \'%s\' variable found in insns[%d].code 0x%x\n",
+					   name, insn_idx, insns[insn_idx].code);
+				return -LIBBPF_ERRNO__RELOC;
+			}
+
 			for (map_idx = 0; map_idx < nr_maps; map_idx++) {
-				if (maps[map_idx].offset == sym.st_value) {
+				if (maps[map_idx].libbpf_type != type)
+					continue;
+				if (type != LIBBPF_MAP_UNSPEC ||
+				    (type == LIBBPF_MAP_UNSPEC &&
+				     maps[map_idx].offset == sym.st_value)) {
 					pr_debug("relocation: find map %zd (%s) for insn %u\n",
 						 map_idx, maps[map_idx].name, insn_idx);
 					break;
@@ -1062,7 +1246,8 @@ bpf_program__collect_reloc(struct bpf_program *prog, GElf_Shdr *shdr,
 				return -LIBBPF_ERRNO__RELOC;
 			}
 
-			prog->reloc_desc[i].type = RELO_LD64;
+			prog->reloc_desc[i].type = type != LIBBPF_MAP_UNSPEC ?
+						   RELO_DATA : RELO_LD64;
 			prog->reloc_desc[i].insn_idx = insn_idx;
 			prog->reloc_desc[i].map_idx = map_idx;
 		}
@@ -1073,18 +1258,27 @@ bpf_program__collect_reloc(struct bpf_program *prog, GElf_Shdr *shdr,
 static int bpf_map_find_btf_info(struct bpf_map *map, const struct btf *btf)
 {
 	struct bpf_map_def *def = &map->def;
-	__u32 key_type_id, value_type_id;
+	__u32 key_type_id = 0, value_type_id = 0;
 	int ret;
 
-	ret = btf__get_map_kv_tids(btf, map->name, def->key_size,
-				   def->value_size, &key_type_id,
-				   &value_type_id);
-	if (ret)
+	if (!bpf_map__is_internal(map)) {
+		ret = btf__get_map_kv_tids(btf, map->name, def->key_size,
+					   def->value_size, &key_type_id,
+					   &value_type_id);
+	} else {
+		/*
+		 * LLVM annotates global data differently in BTF, that is,
+		 * only as '.data', '.bss' or '.rodata'.
+		 */
+		ret = btf__find_by_name(btf,
+				libbpf_type_to_btf_name[map->libbpf_type]);
+	}
+	if (ret < 0)
 		return ret;
 
 	map->btf_key_type_id = key_type_id;
-	map->btf_value_type_id = value_type_id;
-
+	map->btf_value_type_id = bpf_map__is_internal(map) ?
+				 ret : value_type_id;
 	return 0;
 }
 
@@ -1195,6 +1389,34 @@ bpf_object__probe_caps(struct bpf_object *obj)
 	return bpf_object__probe_name(obj);
 }
 
+static int
+bpf_object__populate_internal_map(struct bpf_object *obj, struct bpf_map *map)
+{
+	char *cp, errmsg[STRERR_BUFSIZE];
+	int err, zero = 0;
+	__u8 *data;
+
+	/* Nothing to do here since kernel already zero-initializes .bss map. */
+	if (map->libbpf_type == LIBBPF_MAP_BSS)
+		return 0;
+
+	data = map->libbpf_type == LIBBPF_MAP_DATA ?
+	       obj->sections.data : obj->sections.rodata;
+
+	err = bpf_map_update_elem(map->fd, &zero, data, 0);
+	/* Freeze .rodata map as read-only from syscall side. */
+	if (!err && map->libbpf_type == LIBBPF_MAP_RODATA) {
+		err = bpf_map_freeze(map->fd);
+		if (err) {
+			cp = libbpf_strerror_r(errno, errmsg, sizeof(errmsg));
+			pr_warning("Error freezing map(%s) as read-only: %s\n",
+				   map->name, cp);
+			err = 0;
+		}
+	}
+	return err;
+}
+
 static int
 bpf_object__create_maps(struct bpf_object *obj)
 {
@@ -1252,6 +1474,7 @@ bpf_object__create_maps(struct bpf_object *obj)
 			size_t j;
 
 			err = *pfd;
+err_out:
 			cp = libbpf_strerror_r(errno, errmsg, sizeof(errmsg));
 			pr_warning("failed to create map (name: '%s'): %s\n",
 				   map->name, cp);
@@ -1259,6 +1482,15 @@ bpf_object__create_maps(struct bpf_object *obj)
 				zclose(obj->maps[j].fd);
 			return err;
 		}
+
+		if (bpf_map__is_internal(map)) {
+			err = bpf_object__populate_internal_map(obj, map);
+			if (err < 0) {
+				zclose(*pfd);
+				goto err_out;
+			}
+		}
+
 		pr_debug("create map %s: fd=%d\n", map->name, *pfd);
 	}
 
@@ -1413,19 +1645,27 @@ bpf_program__relocate(struct bpf_program *prog, struct bpf_object *obj)
 		return 0;
 
 	for (i = 0; i < prog->nr_reloc; i++) {
-		if (prog->reloc_desc[i].type == RELO_LD64) {
+		if (prog->reloc_desc[i].type == RELO_LD64 ||
+		    prog->reloc_desc[i].type == RELO_DATA) {
+			bool relo_data = prog->reloc_desc[i].type == RELO_DATA;
 			struct bpf_insn *insns = prog->insns;
 			int insn_idx, map_idx;
 
 			insn_idx = prog->reloc_desc[i].insn_idx;
 			map_idx = prog->reloc_desc[i].map_idx;
 
-			if (insn_idx >= (int)prog->insns_cnt) {
+			if (insn_idx + 1 >= (int)prog->insns_cnt) {
 				pr_warning("relocation out of range: '%s'\n",
 					   prog->section_name);
 				return -LIBBPF_ERRNO__RELOC;
 			}
-			insns[insn_idx].src_reg = BPF_PSEUDO_MAP_FD;
+
+			if (!relo_data) {
+				insns[insn_idx].src_reg = BPF_PSEUDO_MAP_FD;
+			} else {
+				insns[insn_idx].src_reg = BPF_PSEUDO_MAP_VALUE;
+				insns[insn_idx + 1].imm = insns[insn_idx].imm;
+			}
 			insns[insn_idx].imm = obj->maps[map_idx].fd;
 		} else if (prog->reloc_desc[i].type == RELO_CALL) {
 			err = bpf_program__reloc_text(prog, obj,
@@ -2321,6 +2561,9 @@ void bpf_object__close(struct bpf_object *obj)
 		obj->maps[i].priv = NULL;
 		obj->maps[i].clear_priv = NULL;
 	}
+
+	zfree(&obj->sections.rodata);
+	zfree(&obj->sections.data);
 	zfree(&obj->maps);
 	obj->nr_maps = 0;
 
@@ -2798,6 +3041,11 @@ bool bpf_map__is_offload_neutral(struct bpf_map *map)
 	return map->def.type == BPF_MAP_TYPE_PERF_EVENT_ARRAY;
 }
 
+bool bpf_map__is_internal(struct bpf_map *map)
+{
+	return map->libbpf_type != LIBBPF_MAP_UNSPEC;
+}
+
 void bpf_map__set_ifindex(struct bpf_map *map, __u32 ifindex)
 {
 	map->map_ifindex = ifindex;
diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h
index 531323391d07..12db2822c8e7 100644
--- a/tools/lib/bpf/libbpf.h
+++ b/tools/lib/bpf/libbpf.h
@@ -301,6 +301,7 @@ LIBBPF_API void *bpf_map__priv(struct bpf_map *map);
 LIBBPF_API int bpf_map__reuse_fd(struct bpf_map *map, int fd);
 LIBBPF_API int bpf_map__resize(struct bpf_map *map, __u32 max_entries);
 LIBBPF_API bool bpf_map__is_offload_neutral(struct bpf_map *map);
+LIBBPF_API bool bpf_map__is_internal(struct bpf_map *map);
 LIBBPF_API void bpf_map__set_ifindex(struct bpf_map *map, __u32 ifindex);
 LIBBPF_API int bpf_map__pin(struct bpf_map *map, const char *path);
 LIBBPF_API int bpf_map__unpin(struct bpf_map *map, const char *path);
diff --git a/tools/lib/bpf/libbpf.map b/tools/lib/bpf/libbpf.map
index f3ce50500cf2..be42bdffc8de 100644
--- a/tools/lib/bpf/libbpf.map
+++ b/tools/lib/bpf/libbpf.map
@@ -157,3 +157,9 @@ LIBBPF_0.0.2 {
 		bpf_program__bpil_addr_to_offs;
 		bpf_program__bpil_offs_to_addr;
 } LIBBPF_0.0.1;
+
+LIBBPF_0.0.3 {
+	global:
+		bpf_map__is_internal;
+		bpf_map_freeze;
+} LIBBPF_0.0.2;
-- 
cgit v1.2.3-55-g7522


From 1713d68b3bf039d029afd74653c9325f5003ccbe Mon Sep 17 00:00:00 2001
From: Daniel Borkmann
Date: Tue, 9 Apr 2019 23:20:14 +0200
Subject: bpf, libbpf: add support for BTF Var and DataSec

This adds libbpf support for BTF Var and DataSec kinds. Main point
here is that libbpf needs to do some preparatory work before the
whole BTF object can be loaded into the kernel, that is, fixing up
of DataSec size taken from the ELF section size and non-static
variable offset which needs to be taken from the ELF's string section.

Upstream LLVM doesn't fix these up since at time of BTF emission
it is too early in the compilation process thus this information
isn't available yet, hence loader needs to take care of it.

Note, deduplication handling has not been in the scope of this work
and needs to be addressed in a future commit.

Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://reviews.llvm.org/D59441
Acked-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/lib/bpf/btf.c      |  97 +++++++++++++++++++++++++++++-
 tools/lib/bpf/btf.h      |   3 +
 tools/lib/bpf/libbpf.c   | 150 +++++++++++++++++++++++++++++++++++++++++------
 tools/lib/bpf/libbpf.h   |   4 ++
 tools/lib/bpf/libbpf.map |   1 +
 5 files changed, 235 insertions(+), 20 deletions(-)

diff --git a/tools/lib/bpf/btf.c b/tools/lib/bpf/btf.c
index 87e3020ac1bc..0f9079b9539e 100644
--- a/tools/lib/bpf/btf.c
+++ b/tools/lib/bpf/btf.c
@@ -24,6 +24,8 @@
 		((k) == BTF_KIND_CONST) || \
 		((k) == BTF_KIND_RESTRICT))
 
+#define IS_VAR(k) ((k) == BTF_KIND_VAR)
+
 static struct btf_type btf_void;
 
 struct btf {
@@ -212,6 +214,10 @@ static int btf_type_size(struct btf_type *t)
 		return base_size + vlen * sizeof(struct btf_member);
 	case BTF_KIND_FUNC_PROTO:
 		return base_size + vlen * sizeof(struct btf_param);
+	case BTF_KIND_VAR:
+		return base_size + sizeof(struct btf_var);
+	case BTF_KIND_DATASEC:
+		return base_size + vlen * sizeof(struct btf_var_secinfo);
 	default:
 		pr_debug("Unsupported BTF_KIND:%u\n", BTF_INFO_KIND(t->info));
 		return -EINVAL;
@@ -283,6 +289,7 @@ __s64 btf__resolve_size(const struct btf *btf, __u32 type_id)
 		case BTF_KIND_STRUCT:
 		case BTF_KIND_UNION:
 		case BTF_KIND_ENUM:
+		case BTF_KIND_DATASEC:
 			size = t->size;
 			goto done;
 		case BTF_KIND_PTR:
@@ -292,6 +299,7 @@ __s64 btf__resolve_size(const struct btf *btf, __u32 type_id)
 		case BTF_KIND_VOLATILE:
 		case BTF_KIND_CONST:
 		case BTF_KIND_RESTRICT:
+		case BTF_KIND_VAR:
 			type_id = t->type;
 			break;
 		case BTF_KIND_ARRAY:
@@ -326,7 +334,8 @@ int btf__resolve_type(const struct btf *btf, __u32 type_id)
 	t = btf__type_by_id(btf, type_id);
 	while (depth < MAX_RESOLVE_DEPTH &&
 	       !btf_type_is_void_or_null(t) &&
-	       IS_MODIFIER(BTF_INFO_KIND(t->info))) {
+	       (IS_MODIFIER(BTF_INFO_KIND(t->info)) ||
+		IS_VAR(BTF_INFO_KIND(t->info)))) {
 		type_id = t->type;
 		t = btf__type_by_id(btf, type_id);
 		depth++;
@@ -408,6 +417,92 @@ done:
 	return btf;
 }
 
+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_INFO_VLEN(t->info);
+	const char *name = btf__name_by_offset(btf, t->name_off);
+	const struct btf_type *t_var;
+	struct btf_var_secinfo *vsi;
+	struct btf_var *var;
+	int ret;
+
+	if (!name) {
+		pr_debug("No name found in string section for DATASEC kind.\n");
+		return -ENOENT;
+	}
+
+	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 = (struct btf_var_secinfo *)(t + 1);
+	     i < vars; i++, vsi++) {
+		t_var = btf__type_by_id(btf, vsi->type);
+		var = (struct btf_var *)(t_var + 1);
+
+		if (BTF_INFO_KIND(t_var->info) != BTF_KIND_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;
+	}
+
+	qsort(t + 1, 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->types[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_INFO_KIND(t->info) == BTF_KIND_DATASEC) {
+			err = btf_fixup_datasec(obj, btf, t);
+			if (err)
+				break;
+		}
+	}
+
+	return err;
+}
+
 int btf__load(struct btf *btf)
 {
 	__u32 log_buf_size = BPF_LOG_BUF_SIZE;
diff --git a/tools/lib/bpf/btf.h b/tools/lib/bpf/btf.h
index 28a1e1e59861..c7b399e81fce 100644
--- a/tools/lib/bpf/btf.h
+++ b/tools/lib/bpf/btf.h
@@ -21,6 +21,8 @@ struct btf;
 struct btf_ext;
 struct btf_type;
 
+struct bpf_object;
+
 /*
  * The .BTF.ext ELF section layout defined as
  *   struct btf_ext_header
@@ -57,6 +59,7 @@ struct btf_ext_header {
 
 LIBBPF_API void btf__free(struct btf *btf);
 LIBBPF_API struct btf *btf__new(__u8 *data, __u32 size);
+LIBBPF_API int btf__finalize_data(struct bpf_object *obj, struct btf *btf);
 LIBBPF_API int btf__load(struct btf *btf);
 LIBBPF_API __s32 btf__find_by_name(const struct btf *btf,
 				   const char *type_name);
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index f7b245fbb960..e2a457e7c318 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -669,6 +669,112 @@ static bool bpf_map_type__is_map_in_map(enum bpf_map_type type)
 	return false;
 }
 
+static int bpf_object_search_section_size(const struct bpf_object *obj,
+					  const char *name, size_t *d_size)
+{
+	const GElf_Ehdr *ep = &obj->efile.ehdr;
+	Elf *elf = obj->efile.elf;
+	Elf_Scn *scn = NULL;
+	int idx = 0;
+
+	while ((scn = elf_nextscn(elf, scn)) != NULL) {
+		const char *sec_name;
+		Elf_Data *data;
+		GElf_Shdr sh;
+
+		idx++;
+		if (gelf_getshdr(scn, &sh) != &sh) {
+			pr_warning("failed to get section(%d) header from %s\n",
+				   idx, obj->path);
+			return -EIO;
+		}
+
+		sec_name = elf_strptr(elf, ep->e_shstrndx, sh.sh_name);
+		if (!sec_name) {
+			pr_warning("failed to get section(%d) name from %s\n",
+				   idx, obj->path);
+			return -EIO;
+		}
+
+		if (strcmp(name, sec_name))
+			continue;
+
+		data = elf_getdata(scn, 0);
+		if (!data) {
+			pr_warning("failed to get section(%d) data from %s(%s)\n",
+				   idx, name, obj->path);
+			return -EIO;
+		}
+
+		*d_size = data->d_size;
+		return 0;
+	}
+
+	return -ENOENT;
+}
+
+int bpf_object__section_size(const struct bpf_object *obj, const char *name,
+			     __u32 *size)
+{
+	int ret = -ENOENT;
+	size_t d_size;
+
+	*size = 0;
+	if (!name) {
+		return -EINVAL;
+	} else if (!strcmp(name, ".data")) {
+		if (obj->efile.data)
+			*size = obj->efile.data->d_size;
+	} else if (!strcmp(name, ".bss")) {
+		if (obj->efile.bss)
+			*size = obj->efile.bss->d_size;
+	} else if (!strcmp(name, ".rodata")) {
+		if (obj->efile.rodata)
+			*size = obj->efile.rodata->d_size;
+	} else {
+		ret = bpf_object_search_section_size(obj, name, &d_size);
+		if (!ret)
+			*size = d_size;
+	}
+
+	return *size ? 0 : ret;
+}
+
+int bpf_object__variable_offset(const struct bpf_object *obj, const char *name,
+				__u32 *off)
+{
+	Elf_Data *symbols = obj->efile.symbols;
+	const char *sname;
+	size_t si;
+
+	if (!name || !off)
+		return -EINVAL;
+
+	for (si = 0; si < symbols->d_size / sizeof(GElf_Sym); si++) {
+		GElf_Sym sym;
+
+		if (!gelf_getsym(symbols, si, &sym))
+			continue;
+		if (GELF_ST_BIND(sym.st_info) != STB_GLOBAL ||
+		    GELF_ST_TYPE(sym.st_info) != STT_OBJECT)
+			continue;
+
+		sname = elf_strptr(obj->efile.elf, obj->efile.strtabidx,
+				   sym.st_name);
+		if (!sname) {
+			pr_warning("failed to get sym name string for var %s\n",
+				   name);
+			return -EIO;
+		}
+		if (strcmp(name, sname) == 0) {
+			*off = sym.st_value;
+			return 0;
+		}
+	}
+
+	return -ENOENT;
+}
+
 static bool bpf_object__has_maps(const struct bpf_object *obj)
 {
 	return obj->efile.maps_shndx >= 0 ||
@@ -911,6 +1017,7 @@ static int bpf_object__elf_collect(struct bpf_object *obj, int flags)
 	Elf *elf = obj->efile.elf;
 	GElf_Ehdr *ep = &obj->efile.ehdr;
 	Elf_Data *btf_ext_data = NULL;
+	Elf_Data *btf_data = NULL;
 	Elf_Scn *scn = NULL;
 	int idx = 0, err = 0;
 
@@ -954,32 +1061,18 @@ static int bpf_object__elf_collect(struct bpf_object *obj, int flags)
 			 (int)sh.sh_link, (unsigned long)sh.sh_flags,
 			 (int)sh.sh_type);
 
-		if (strcmp(name, "license") == 0)
+		if (strcmp(name, "license") == 0) {
 			err = bpf_object__init_license(obj,
 						       data->d_buf,
 						       data->d_size);
-		else if (strcmp(name, "version") == 0)
+		} else if (strcmp(name, "version") == 0) {
 			err = bpf_object__init_kversion(obj,
 							data->d_buf,
 							data->d_size);
-		else if (strcmp(name, "maps") == 0)
+		} else if (strcmp(name, "maps") == 0) {
 			obj->efile.maps_shndx = idx;
-		else if (strcmp(name, BTF_ELF_SEC) == 0) {
-			obj->btf = btf__new(data->d_buf, data->d_size);
-			if (IS_ERR(obj->btf)) {
-				pr_warning("Error loading ELF section %s: %ld. Ignored and continue.\n",
-					   BTF_ELF_SEC, PTR_ERR(obj->btf));
-				obj->btf = NULL;
-				continue;
-			}
-			err = btf__load(obj->btf);
-			if (err) {
-				pr_warning("Error loading %s into kernel: %d. Ignored and continue.\n",
-					   BTF_ELF_SEC, err);
-				btf__free(obj->btf);
-				obj->btf = NULL;
-				err = 0;
-			}
+		} else if (strcmp(name, BTF_ELF_SEC) == 0) {
+			btf_data = data;
 		} else if (strcmp(name, BTF_EXT_ELF_SEC) == 0) {
 			btf_ext_data = data;
 		} else if (sh.sh_type == SHT_SYMTAB) {
@@ -1054,6 +1147,25 @@ static int bpf_object__elf_collect(struct bpf_object *obj, int flags)
 		pr_warning("Corrupted ELF file: index of strtab invalid\n");
 		return LIBBPF_ERRNO__FORMAT;
 	}
+	if (btf_data) {
+		obj->btf = btf__new(btf_data->d_buf, btf_data->d_size);
+		if (IS_ERR(obj->btf)) {
+			pr_warning("Error loading ELF section %s: %ld. Ignored and continue.\n",
+				   BTF_ELF_SEC, PTR_ERR(obj->btf));
+			obj->btf = NULL;
+		} else {
+			err = btf__finalize_data(obj, obj->btf);
+			if (!err)
+				err = btf__load(obj->btf);
+			if (err) {
+				pr_warning("Error finalizing and loading %s into kernel: %d. Ignored and continue.\n",
+					   BTF_ELF_SEC, err);
+				btf__free(obj->btf);
+				obj->btf = NULL;
+				err = 0;
+			}
+		}
+	}
 	if (btf_ext_data) {
 		if (!obj->btf) {
 			pr_debug("Ignore ELF section %s because its depending ELF section %s is not found.\n",
diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h
index 12db2822c8e7..c5ff00515ce7 100644
--- a/tools/lib/bpf/libbpf.h
+++ b/tools/lib/bpf/libbpf.h
@@ -75,6 +75,10 @@ struct bpf_object *__bpf_object__open_xattr(struct bpf_object_open_attr *attr,
 LIBBPF_API struct bpf_object *bpf_object__open_buffer(void *obj_buf,
 						      size_t obj_buf_sz,
 						      const char *name);
+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);
 LIBBPF_API int bpf_object__pin_maps(struct bpf_object *obj, const char *path);
 LIBBPF_API int bpf_object__unpin_maps(struct bpf_object *obj,
 				      const char *path);
diff --git a/tools/lib/bpf/libbpf.map b/tools/lib/bpf/libbpf.map
index be42bdffc8de..673001787cba 100644
--- a/tools/lib/bpf/libbpf.map
+++ b/tools/lib/bpf/libbpf.map
@@ -162,4 +162,5 @@ LIBBPF_0.0.3 {
 	global:
 		bpf_map__is_internal;
 		bpf_map_freeze;
+		btf__finalize_data;
 } LIBBPF_0.0.2;
-- 
cgit v1.2.3-55-g7522


From 817998afa038c156bbc1a6e69c48aa26282cc41f Mon Sep 17 00:00:00 2001
From: Daniel Borkmann
Date: Tue, 9 Apr 2019 23:20:15 +0200
Subject: bpf: bpftool support for dumping data/bss/rodata sections

Add the ability to bpftool to handle BTF Var and DataSec kinds
in order to dump them out of btf_dumper_type(). The value has a
single object with the section name, which itself holds an array
of variables it dumps. A single variable is an object by itself
printed along with its name. From there further type information
is dumped along with corresponding value information.

Example output from .rodata:

  # ./bpftool m d i 150
  [{
          "value": {
              ".rodata": [{
                      "load_static_data.bar": 18446744073709551615
                  },{
                      "num2": 24
                  },{
                      "num5": 43947
                  },{
                      "num6": 171
                  },{
                      "str0": [97,98,99,100,101,102,103,104,105,106,107,108,109,110,111,112,113,114,115,116,117,118,119,120,121,122,0,0,0,0,0,0
                      ]
                  },{
                      "struct0": {
                          "a": 42,
                          "b": 4278120431,
                          "c": 1229782938247303441
                      }
                  },{
                      "struct2": {
                          "a": 0,
                          "b": 0,
                          "c": 0
                      }
                  }
              ]
          }
      }
  ]

Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/bpf/bpftool/btf_dumper.c | 59 ++++++++++++++++++++++++++++++++++++++++++
 tools/bpf/bpftool/map.c        | 10 ++++---
 2 files changed, 65 insertions(+), 4 deletions(-)

diff --git a/tools/bpf/bpftool/btf_dumper.c b/tools/bpf/bpftool/btf_dumper.c
index e63bce0755eb..8cafb9b31467 100644
--- a/tools/bpf/bpftool/btf_dumper.c
+++ b/tools/bpf/bpftool/btf_dumper.c
@@ -309,6 +309,48 @@ static int btf_dumper_struct(const struct btf_dumper *d, __u32 type_id,
 	return ret;
 }
 
+static int btf_dumper_var(const struct btf_dumper *d, __u32 type_id,
+			  __u8 bit_offset, const void *data)
+{
+	const struct btf_type *t = btf__type_by_id(d->btf, type_id);
+	int ret;
+
+	jsonw_start_object(d->jw);
+	jsonw_name(d->jw, btf__name_by_offset(d->btf, t->name_off));
+	ret = btf_dumper_do_type(d, t->type, bit_offset, data);
+	jsonw_end_object(d->jw);
+
+	return ret;
+}
+
+static int btf_dumper_datasec(const struct btf_dumper *d, __u32 type_id,
+			      const void *data)
+{
+	struct btf_var_secinfo *vsi;
+	const struct btf_type *t;
+	int ret = 0, i, vlen;
+
+	t = btf__type_by_id(d->btf, type_id);
+	if (!t)
+		return -EINVAL;
+
+	vlen = BTF_INFO_VLEN(t->info);
+	vsi = (struct btf_var_secinfo *)(t + 1);
+
+	jsonw_start_object(d->jw);
+	jsonw_name(d->jw, btf__name_by_offset(d->btf, t->name_off));
+	jsonw_start_array(d->jw);
+	for (i = 0; i < vlen; i++) {
+		ret = btf_dumper_do_type(d, vsi[i].type, 0, data + vsi[i].offset);
+		if (ret)
+			break;
+	}
+	jsonw_end_array(d->jw);
+	jsonw_end_object(d->jw);
+
+	return ret;
+}
+
 static int btf_dumper_do_type(const struct btf_dumper *d, __u32 type_id,
 			      __u8 bit_offset, const void *data)
 {
@@ -341,6 +383,10 @@ static int btf_dumper_do_type(const struct btf_dumper *d, __u32 type_id,
 	case BTF_KIND_CONST:
 	case BTF_KIND_RESTRICT:
 		return btf_dumper_modifier(d, type_id, bit_offset, data);
+	case BTF_KIND_VAR:
+		return btf_dumper_var(d, type_id, bit_offset, data);
+	case BTF_KIND_DATASEC:
+		return btf_dumper_datasec(d, type_id, data);
 	default:
 		jsonw_printf(d->jw, "(unsupported-kind");
 		return -EINVAL;
@@ -377,6 +423,7 @@ static int __btf_dumper_type_only(const struct btf *btf, __u32 type_id,
 {
 	const struct btf_type *proto_type;
 	const struct btf_array *array;
+	const struct btf_var *var;
 	const struct btf_type *t;
 
 	if (!type_id) {
@@ -440,6 +487,18 @@ static int __btf_dumper_type_only(const struct btf *btf, __u32 type_id,
 		if (pos == -1)
 			return -1;
 		break;
+	case BTF_KIND_VAR:
+		var = (struct btf_var *)(t + 1);
+		if (var->linkage == BTF_VAR_STATIC)
+			BTF_PRINT_ARG("static ");
+		BTF_PRINT_TYPE(t->type);
+		BTF_PRINT_ARG(" %s",
+			      btf__name_by_offset(btf, t->name_off));
+		break;
+	case BTF_KIND_DATASEC:
+		BTF_PRINT_ARG("section (\"%s\") ",
+			      btf__name_by_offset(btf, t->name_off));
+		break;
 	case BTF_KIND_UNKN:
 	default:
 		return -1;
diff --git a/tools/bpf/bpftool/map.c b/tools/bpf/bpftool/map.c
index e0c650d91784..e96903078991 100644
--- a/tools/bpf/bpftool/map.c
+++ b/tools/bpf/bpftool/map.c
@@ -153,11 +153,13 @@ static int do_dump_btf(const struct btf_dumper *d,
 	/* start of key-value pair */
 	jsonw_start_object(d->jw);
 
-	jsonw_name(d->jw, "key");
+	if (map_info->btf_key_type_id) {
+		jsonw_name(d->jw, "key");
 
-	ret = btf_dumper_type(d, map_info->btf_key_type_id, key);
-	if (ret)
-		goto err_end_obj;
+		ret = btf_dumper_type(d, map_info->btf_key_type_id, key);
+		if (ret)
+			goto err_end_obj;
+	}
 
 	if (!map_is_per_cpu(map_info->type)) {
 		jsonw_name(d->jw, "value");
-- 
cgit v1.2.3-55-g7522


From fb2abb73e575b6fcb428f803faf928ef04d5bb1e Mon Sep 17 00:00:00 2001
From: Daniel Borkmann
Date: Tue, 9 Apr 2019 23:20:16 +0200
Subject: bpf, selftest: test {rd, wr}only flags and direct value access

Extend test_verifier with various test cases around the two kernel
extensions, that is, {rd,wr}only map support as well as direct map
value access. All passing, one skipped due to xskmap not present
on test machine:

  # ./test_verifier
  [...]
  #948/p XDP pkt read, pkt_meta' <= pkt_data, bad access 1 OK
  #949/p XDP pkt read, pkt_meta' <= pkt_data, bad access 2 OK
  #950/p XDP pkt read, pkt_data <= pkt_meta', good access OK
  #951/p XDP pkt read, pkt_data <= pkt_meta', bad access 1 OK
  #952/p XDP pkt read, pkt_data <= pkt_meta', bad access 2 OK
  Summary: 1410 PASSED, 1 SKIPPED, 0 FAILED

Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/include/linux/filter.h                       |  21 +-
 tools/testing/selftests/bpf/test_verifier.c        |  51 ++-
 .../testing/selftests/bpf/verifier/array_access.c  | 159 ++++++++++
 .../selftests/bpf/verifier/direct_value_access.c   | 347 +++++++++++++++++++++
 4 files changed, 573 insertions(+), 5 deletions(-)
 create mode 100644 tools/testing/selftests/bpf/verifier/direct_value_access.c

diff --git a/tools/include/linux/filter.h b/tools/include/linux/filter.h
index cce0b02c0e28..ca28b6ab8db7 100644
--- a/tools/include/linux/filter.h
+++ b/tools/include/linux/filter.h
@@ -278,10 +278,29 @@
 		.off   = 0,					\
 		.imm   = ((__u64) (IMM)) >> 32 })
 
+#define BPF_LD_IMM64_RAW_FULL(DST, SRC, OFF1, OFF2, IMM1, IMM2)	\
+	((struct bpf_insn) {					\
+		.code  = BPF_LD | BPF_DW | BPF_IMM,		\
+		.dst_reg = DST,					\
+		.src_reg = SRC,					\
+		.off   = OFF1,					\
+		.imm   = IMM1 }),				\
+	((struct bpf_insn) {					\
+		.code  = 0, /* zero is reserved opcode */	\
+		.dst_reg = 0,					\
+		.src_reg = 0,					\
+		.off   = OFF2,					\
+		.imm   = IMM2 })
+
 /* pseudo BPF_LD_IMM64 insn used to refer to process-local map_fd */
 
 #define BPF_LD_MAP_FD(DST, MAP_FD)				\
-	BPF_LD_IMM64_RAW(DST, BPF_PSEUDO_MAP_FD, MAP_FD)
+	BPF_LD_IMM64_RAW_FULL(DST, BPF_PSEUDO_MAP_FD, 0, 0,	\
+			      MAP_FD, 0)
+
+#define BPF_LD_MAP_VALUE(DST, MAP_FD, VALUE_OFF)		\
+	BPF_LD_IMM64_RAW_FULL(DST, BPF_PSEUDO_MAP_VALUE, 0, 0,	\
+			      MAP_FD, VALUE_OFF)
 
 /* Relative call */
 
diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c
index 75ef63b42f2c..e2ebcaddbe78 100644
--- a/tools/testing/selftests/bpf/test_verifier.c
+++ b/tools/testing/selftests/bpf/test_verifier.c
@@ -52,7 +52,7 @@
 #define MAX_INSNS	BPF_MAXINSNS
 #define MAX_TEST_INSNS	1000000
 #define MAX_FIXUPS	8
-#define MAX_NR_MAPS	14
+#define MAX_NR_MAPS	16
 #define MAX_TEST_RUNS	8
 #define POINTER_VALUE	0xcafe4all
 #define TEST_DATA_LEN	64
@@ -82,6 +82,9 @@ struct bpf_test {
 	int fixup_cgroup_storage[MAX_FIXUPS];
 	int fixup_percpu_cgroup_storage[MAX_FIXUPS];
 	int fixup_map_spin_lock[MAX_FIXUPS];
+	int fixup_map_array_ro[MAX_FIXUPS];
+	int fixup_map_array_wo[MAX_FIXUPS];
+	int fixup_map_array_small[MAX_FIXUPS];
 	const char *errstr;
 	const char *errstr_unpriv;
 	uint32_t retval, retval_unpriv, insn_processed;
@@ -285,13 +288,15 @@ static bool skip_unsupported_map(enum bpf_map_type map_type)
 	return false;
 }
 
-static int create_map(uint32_t type, uint32_t size_key,
-		      uint32_t size_value, uint32_t max_elem)
+static int __create_map(uint32_t type, uint32_t size_key,
+			uint32_t size_value, uint32_t max_elem,
+			uint32_t extra_flags)
 {
 	int fd;
 
 	fd = bpf_create_map(type, size_key, size_value, max_elem,
-			    type == BPF_MAP_TYPE_HASH ? BPF_F_NO_PREALLOC : 0);
+			    (type == BPF_MAP_TYPE_HASH ?
+			     BPF_F_NO_PREALLOC : 0) | extra_flags);
 	if (fd < 0) {
 		if (skip_unsupported_map(type))
 			return -1;
@@ -301,6 +306,12 @@ static int create_map(uint32_t type, uint32_t size_key,
 	return fd;
 }
 
+static int create_map(uint32_t type, uint32_t size_key,
+		      uint32_t size_value, uint32_t max_elem)
+{
+	return __create_map(type, size_key, size_value, max_elem, 0);
+}
+
 static void update_map(int fd, int index)
 {
 	struct test_val value = {
@@ -527,6 +538,9 @@ static void do_test_fixup(struct bpf_test *test, enum bpf_prog_type prog_type,
 	int *fixup_cgroup_storage = test->fixup_cgroup_storage;
 	int *fixup_percpu_cgroup_storage = test->fixup_percpu_cgroup_storage;
 	int *fixup_map_spin_lock = test->fixup_map_spin_lock;
+	int *fixup_map_array_ro = test->fixup_map_array_ro;
+	int *fixup_map_array_wo = test->fixup_map_array_wo;
+	int *fixup_map_array_small = test->fixup_map_array_small;
 
 	if (test->fill_helper) {
 		test->fill_insns = calloc(MAX_TEST_INSNS, sizeof(struct bpf_insn));
@@ -652,6 +666,35 @@ static void do_test_fixup(struct bpf_test *test, enum bpf_prog_type prog_type,
 			fixup_map_spin_lock++;
 		} while (*fixup_map_spin_lock);
 	}
+	if (*fixup_map_array_ro) {
+		map_fds[14] = __create_map(BPF_MAP_TYPE_ARRAY, sizeof(int),
+					   sizeof(struct test_val), 1,
+					   BPF_F_RDONLY_PROG);
+		update_map(map_fds[14], 0);
+		do {
+			prog[*fixup_map_array_ro].imm = map_fds[14];
+			fixup_map_array_ro++;
+		} while (*fixup_map_array_ro);
+	}
+	if (*fixup_map_array_wo) {
+		map_fds[15] = __create_map(BPF_MAP_TYPE_ARRAY, sizeof(int),
+					   sizeof(struct test_val), 1,
+					   BPF_F_WRONLY_PROG);
+		update_map(map_fds[15], 0);
+		do {
+			prog[*fixup_map_array_wo].imm = map_fds[15];
+			fixup_map_array_wo++;
+		} while (*fixup_map_array_wo);
+	}
+	if (*fixup_map_array_small) {
+		map_fds[16] = __create_map(BPF_MAP_TYPE_ARRAY, sizeof(int),
+					   1, 1, 0);
+		update_map(map_fds[16], 0);
+		do {
+			prog[*fixup_map_array_small].imm = map_fds[16];
+			fixup_map_array_small++;
+		} while (*fixup_map_array_small);
+	}
 }
 
 static int set_admin(bool admin)
diff --git a/tools/testing/selftests/bpf/verifier/array_access.c b/tools/testing/selftests/bpf/verifier/array_access.c
index 0dcecaf3ec6f..bcb83196e459 100644
--- a/tools/testing/selftests/bpf/verifier/array_access.c
+++ b/tools/testing/selftests/bpf/verifier/array_access.c
@@ -217,3 +217,162 @@
 	.result = REJECT,
 	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 },
+{
+	"valid read map access into a read-only array 1",
+	.insns = {
+	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
+	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+	BPF_LD_MAP_FD(BPF_REG_1, 0),
+	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
+	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 1),
+	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	},
+	.fixup_map_array_ro = { 3 },
+	.result = ACCEPT,
+	.retval = 28,
+},
+{
+	"valid read map access into a read-only array 2",
+	.insns = {
+	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
+	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+	BPF_LD_MAP_FD(BPF_REG_1, 0),
+	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
+	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 6),
+
+	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+	BPF_MOV64_IMM(BPF_REG_2, 4),
+	BPF_MOV64_IMM(BPF_REG_3, 0),
+	BPF_MOV64_IMM(BPF_REG_4, 0),
+	BPF_MOV64_IMM(BPF_REG_5, 0),
+	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+		     BPF_FUNC_csum_diff),
+	BPF_EXIT_INSN(),
+	},
+	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+	.fixup_map_array_ro = { 3 },
+	.result = ACCEPT,
+	.retval = -29,
+},
+{
+	"invalid write map access into a read-only array 1",
+	.insns = {
+	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
+	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+	BPF_LD_MAP_FD(BPF_REG_1, 0),
+	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
+	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 1),
+	BPF_ST_MEM(BPF_DW, BPF_REG_0, 0, 42),
+	BPF_EXIT_INSN(),
+	},
+	.fixup_map_array_ro = { 3 },
+	.result = REJECT,
+	.errstr = "write into map forbidden",
+},
+{
+	"invalid write map access into a read-only array 2",
+	.insns = {
+	BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
+	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
+	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+	BPF_LD_MAP_FD(BPF_REG_1, 0),
+	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
+	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 5),
+	BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
+	BPF_MOV64_IMM(BPF_REG_2, 0),
+	BPF_MOV64_REG(BPF_REG_3, BPF_REG_0),
+	BPF_MOV64_IMM(BPF_REG_4, 8),
+	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+		     BPF_FUNC_skb_load_bytes),
+	BPF_EXIT_INSN(),
+	},
+	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+	.fixup_map_array_ro = { 4 },
+	.result = REJECT,
+	.errstr = "write into map forbidden",
+},
+{
+	"valid write map access into a write-only array 1",
+	.insns = {
+	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
+	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+	BPF_LD_MAP_FD(BPF_REG_1, 0),
+	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
+	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 1),
+	BPF_ST_MEM(BPF_DW, BPF_REG_0, 0, 42),
+	BPF_MOV64_IMM(BPF_REG_0, 1),
+	BPF_EXIT_INSN(),
+	},
+	.fixup_map_array_wo = { 3 },
+	.result = ACCEPT,
+	.retval = 1,
+},
+{
+	"valid write map access into a write-only array 2",
+	.insns = {
+	BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
+	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
+	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+	BPF_LD_MAP_FD(BPF_REG_1, 0),
+	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
+	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 5),
+	BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
+	BPF_MOV64_IMM(BPF_REG_2, 0),
+	BPF_MOV64_REG(BPF_REG_3, BPF_REG_0),
+	BPF_MOV64_IMM(BPF_REG_4, 8),
+	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+		     BPF_FUNC_skb_load_bytes),
+	BPF_EXIT_INSN(),
+	},
+	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+	.fixup_map_array_wo = { 4 },
+	.result = ACCEPT,
+	.retval = 0,
+},
+{
+	"invalid read map access into a write-only array 1",
+	.insns = {
+	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
+	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+	BPF_LD_MAP_FD(BPF_REG_1, 0),
+	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
+	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 1),
+	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_0, 0),
+	BPF_EXIT_INSN(),
+	},
+	.fixup_map_array_wo = { 3 },
+	.result = REJECT,
+	.errstr = "read from map forbidden",
+},
+{
+	"invalid read map access into a write-only array 2",
+	.insns = {
+	BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
+	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+	BPF_LD_MAP_FD(BPF_REG_1, 0),
+	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
+	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 6),
+
+	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+	BPF_MOV64_IMM(BPF_REG_2, 4),
+	BPF_MOV64_IMM(BPF_REG_3, 0),
+	BPF_MOV64_IMM(BPF_REG_4, 0),
+	BPF_MOV64_IMM(BPF_REG_5, 0),
+	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+		     BPF_FUNC_csum_diff),
+	BPF_EXIT_INSN(),
+	},
+	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+	.fixup_map_array_wo = { 3 },
+	.result = REJECT,
+	.errstr = "read from map forbidden",
+},
diff --git a/tools/testing/selftests/bpf/verifier/direct_value_access.c b/tools/testing/selftests/bpf/verifier/direct_value_access.c
new file mode 100644
index 000000000000..b9fb28e8e224
--- /dev/null
+++ b/tools/testing/selftests/bpf/verifier/direct_value_access.c
@@ -0,0 +1,347 @@
+{
+	"direct map access, write test 1",
+	.insns = {
+	BPF_MOV64_IMM(BPF_REG_0, 1),
+	BPF_LD_MAP_VALUE(BPF_REG_1, 0, 0),
+	BPF_ST_MEM(BPF_DW, BPF_REG_1, 0, 4242),
+	BPF_EXIT_INSN(),
+	},
+	.fixup_map_array_48b = { 1 },
+	.result = ACCEPT,
+	.retval = 1,
+},
+{
+	"direct map access, write test 2",
+	.insns = {
+	BPF_MOV64_IMM(BPF_REG_0, 1),
+	BPF_LD_MAP_VALUE(BPF_REG_1, 0, 8),
+	BPF_ST_MEM(BPF_DW, BPF_REG_1, 0, 4242),
+	BPF_EXIT_INSN(),
+	},
+	.fixup_map_array_48b = { 1 },
+	.result = ACCEPT,
+	.retval = 1,
+},
+{
+	"direct map access, write test 3",
+	.insns = {
+	BPF_MOV64_IMM(BPF_REG_0, 1),
+	BPF_LD_MAP_VALUE(BPF_REG_1, 0, 8),
+	BPF_ST_MEM(BPF_DW, BPF_REG_1, 8, 4242),
+	BPF_EXIT_INSN(),
+	},
+	.fixup_map_array_48b = { 1 },
+	.result = ACCEPT,
+	.retval = 1,
+},
+{
+	"direct map access, write test 4",
+	.insns = {
+	BPF_MOV64_IMM(BPF_REG_0, 1),
+	BPF_LD_MAP_VALUE(BPF_REG_1, 0, 40),
+	BPF_ST_MEM(BPF_DW, BPF_REG_1, 0, 4242),
+	BPF_EXIT_INSN(),
+	},
+	.fixup_map_array_48b = { 1 },
+	.result = ACCEPT,
+	.retval = 1,
+},
+{
+	"direct map access, write test 5",
+	.insns = {
+	BPF_MOV64_IMM(BPF_REG_0, 1),
+	BPF_LD_MAP_VALUE(BPF_REG_1, 0, 32),
+	BPF_ST_MEM(BPF_DW, BPF_REG_1, 8, 4242),
+	BPF_EXIT_INSN(),
+	},
+	.fixup_map_array_48b = { 1 },
+	.result = ACCEPT,
+	.retval = 1,
+},
+{
+	"direct map access, write test 6",
+	.insns = {
+	BPF_MOV64_IMM(BPF_REG_0, 1),
+	BPF_LD_MAP_VALUE(BPF_REG_1, 0, 40),
+	BPF_ST_MEM(BPF_DW, BPF_REG_1, 4, 4242),
+	BPF_EXIT_INSN(),
+	},
+	.fixup_map_array_48b = { 1 },
+	.result = REJECT,
+	.errstr = "R1 min value is outside of the array range",
+},
+{
+	"direct map access, write test 7",
+	.insns = {
+	BPF_MOV64_IMM(BPF_REG_0, 1),
+	BPF_LD_MAP_VALUE(BPF_REG_1, 0, -1),
+	BPF_ST_MEM(BPF_DW, BPF_REG_1, 4, 4242),
+	BPF_EXIT_INSN(),
+	},
+	.fixup_map_array_48b = { 1 },
+	.result = REJECT,
+	.errstr = "direct value offset of 4294967295 is not allowed",
+},
+{
+	"direct map access, write test 8",
+	.insns = {
+	BPF_MOV64_IMM(BPF_REG_0, 1),
+	BPF_LD_MAP_VALUE(BPF_REG_1, 0, 1),
+	BPF_ST_MEM(BPF_DW, BPF_REG_1, -1, 4242),
+	BPF_EXIT_INSN(),
+	},
+	.fixup_map_array_48b = { 1 },
+	.result = ACCEPT,
+	.retval = 1,
+},
+{
+	"direct map access, write test 9",
+	.insns = {
+	BPF_MOV64_IMM(BPF_REG_0, 1),
+	BPF_LD_MAP_VALUE(BPF_REG_1, 0, 48),
+	BPF_ST_MEM(BPF_DW, BPF_REG_1, 0, 4242),
+	BPF_EXIT_INSN(),
+	},
+	.fixup_map_array_48b = { 1 },
+	.result = REJECT,
+	.errstr = "invalid access to map value pointer",
+},
+{
+	"direct map access, write test 10",
+	.insns = {
+	BPF_MOV64_IMM(BPF_REG_0, 1),
+	BPF_LD_MAP_VALUE(BPF_REG_1, 0, 47),
+	BPF_ST_MEM(BPF_B, BPF_REG_1, 0, 4),
+	BPF_EXIT_INSN(),
+	},
+	.fixup_map_array_48b = { 1 },
+	.result = ACCEPT,
+	.retval = 1,
+},
+{
+	"direct map access, write test 11",
+	.insns = {
+	BPF_MOV64_IMM(BPF_REG_0, 1),
+	BPF_LD_MAP_VALUE(BPF_REG_1, 0, 48),
+	BPF_ST_MEM(BPF_B, BPF_REG_1, 0, 4),
+	BPF_EXIT_INSN(),
+	},
+	.fixup_map_array_48b = { 1 },
+	.result = REJECT,
+	.errstr = "invalid access to map value pointer",
+},
+{
+	"direct map access, write test 12",
+	.insns = {
+	BPF_MOV64_IMM(BPF_REG_0, 1),
+	BPF_LD_MAP_VALUE(BPF_REG_1, 0, (1<<29)),
+	BPF_ST_MEM(BPF_B, BPF_REG_1, 0, 4),
+	BPF_EXIT_INSN(),
+	},
+	.fixup_map_array_48b = { 1 },
+	.result = REJECT,
+	.errstr = "direct value offset of 536870912 is not allowed",
+},
+{
+	"direct map access, write test 13",
+	.insns = {
+	BPF_MOV64_IMM(BPF_REG_0, 1),
+	BPF_LD_MAP_VALUE(BPF_REG_1, 0, (1<<29)-1),
+	BPF_ST_MEM(BPF_B, BPF_REG_1, 0, 4),
+	BPF_EXIT_INSN(),
+	},
+	.fixup_map_array_48b = { 1 },
+	.result = REJECT,
+	.errstr = "invalid access to map value pointer, value_size=48 off=536870911",
+},
+{
+	"direct map access, write test 14",
+	.insns = {
+	BPF_MOV64_IMM(BPF_REG_0, 1),
+	BPF_LD_MAP_VALUE(BPF_REG_1, 0, 47),
+	BPF_LD_MAP_VALUE(BPF_REG_2, 0, 46),
+	BPF_ST_MEM(BPF_H, BPF_REG_2, 0, 0xffff),
+	BPF_LDX_MEM(BPF_B, BPF_REG_0, BPF_REG_1, 0),
+	BPF_EXIT_INSN(),
+	},
+	.fixup_map_array_48b = { 1, 3 },
+	.result = ACCEPT,
+	.retval = 0xff,
+},
+{
+	"direct map access, write test 15",
+	.insns = {
+	BPF_MOV64_IMM(BPF_REG_0, 1),
+	BPF_LD_MAP_VALUE(BPF_REG_1, 0, 46),
+	BPF_LD_MAP_VALUE(BPF_REG_2, 0, 46),
+	BPF_ST_MEM(BPF_H, BPF_REG_2, 0, 0xffff),
+	BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_1, 0),
+	BPF_EXIT_INSN(),
+	},
+	.fixup_map_array_48b = { 1, 3 },
+	.result = ACCEPT,
+	.retval = 0xffff,
+},
+{
+	"direct map access, write test 16",
+	.insns = {
+	BPF_MOV64_IMM(BPF_REG_0, 1),
+	BPF_LD_MAP_VALUE(BPF_REG_1, 0, 46),
+	BPF_LD_MAP_VALUE(BPF_REG_2, 0, 47),
+	BPF_ST_MEM(BPF_H, BPF_REG_2, 0, 0xffff),
+	BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_1, 0),
+	BPF_EXIT_INSN(),
+	},
+	.fixup_map_array_48b = { 1, 3 },
+	.result = REJECT,
+	.errstr = "invalid access to map value, value_size=48 off=47 size=2",
+},
+{
+	"direct map access, write test 17",
+	.insns = {
+	BPF_MOV64_IMM(BPF_REG_0, 1),
+	BPF_LD_MAP_VALUE(BPF_REG_1, 0, 46),
+	BPF_LD_MAP_VALUE(BPF_REG_2, 0, 46),
+	BPF_ST_MEM(BPF_H, BPF_REG_2, 1, 0xffff),
+	BPF_LDX_MEM(BPF_H, BPF_REG_0, BPF_REG_1, 0),
+	BPF_EXIT_INSN(),
+	},
+	.fixup_map_array_48b = { 1, 3 },
+	.result = REJECT,
+	.errstr = "invalid access to map value, value_size=48 off=47 size=2",
+},
+{
+	"direct map access, write test 18",
+	.insns = {
+	BPF_MOV64_IMM(BPF_REG_0, 1),
+	BPF_LD_MAP_VALUE(BPF_REG_1, 0, 0),
+	BPF_ST_MEM(BPF_H, BPF_REG_1, 0, 42),
+	BPF_EXIT_INSN(),
+	},
+	.fixup_map_array_small = { 1 },
+	.result = REJECT,
+	.errstr = "R1 min value is outside of the array range",
+},
+{
+	"direct map access, write test 19",
+	.insns = {
+	BPF_MOV64_IMM(BPF_REG_0, 1),
+	BPF_LD_MAP_VALUE(BPF_REG_1, 0, 0),
+	BPF_ST_MEM(BPF_B, BPF_REG_1, 0, 42),
+	BPF_EXIT_INSN(),
+	},
+	.fixup_map_array_small = { 1 },
+	.result = ACCEPT,
+	.retval = 1,
+},
+{
+	"direct map access, write test 20",
+	.insns = {
+	BPF_MOV64_IMM(BPF_REG_0, 1),
+	BPF_LD_MAP_VALUE(BPF_REG_1, 0, 1),
+	BPF_ST_MEM(BPF_B, BPF_REG_1, 0, 42),
+	BPF_EXIT_INSN(),
+	},
+	.fixup_map_array_small = { 1 },
+	.result = REJECT,
+	.errstr = "invalid access to map value pointer",
+},
+{
+	"direct map access, invalid insn test 1",
+	.insns = {
+	BPF_MOV64_IMM(BPF_REG_0, 1),
+	BPF_LD_IMM64_RAW_FULL(BPF_REG_1, BPF_PSEUDO_MAP_VALUE, 0, 1, 0, 47),
+	BPF_EXIT_INSN(),
+	},
+	.fixup_map_array_48b = { 1 },
+	.result = REJECT,
+	.errstr = "invalid bpf_ld_imm64 insn",
+},
+{
+	"direct map access, invalid insn test 2",
+	.insns = {
+	BPF_MOV64_IMM(BPF_REG_0, 1),
+	BPF_LD_IMM64_RAW_FULL(BPF_REG_1, BPF_PSEUDO_MAP_VALUE, 1, 0, 0, 47),
+	BPF_EXIT_INSN(),
+	},
+	.fixup_map_array_48b = { 1 },
+	.result = REJECT,
+	.errstr = "BPF_LD_IMM64 uses reserved fields",
+},
+{
+	"direct map access, invalid insn test 3",
+	.insns = {
+	BPF_MOV64_IMM(BPF_REG_0, 1),
+	BPF_LD_IMM64_RAW_FULL(BPF_REG_1, BPF_PSEUDO_MAP_VALUE, ~0, 0, 0, 47),
+	BPF_EXIT_INSN(),
+	},
+	.fixup_map_array_48b = { 1 },
+	.result = REJECT,
+	.errstr = "BPF_LD_IMM64 uses reserved fields",
+},
+{
+	"direct map access, invalid insn test 4",
+	.insns = {
+	BPF_MOV64_IMM(BPF_REG_0, 1),
+	BPF_LD_IMM64_RAW_FULL(BPF_REG_1, BPF_PSEUDO_MAP_VALUE, 0, ~0, 0, 47),
+	BPF_EXIT_INSN(),
+	},
+	.fixup_map_array_48b = { 1 },
+	.result = REJECT,
+	.errstr = "invalid bpf_ld_imm64 insn",
+},
+{
+	"direct map access, invalid insn test 5",
+	.insns = {
+	BPF_MOV64_IMM(BPF_REG_0, 1),
+	BPF_LD_IMM64_RAW_FULL(BPF_REG_1, BPF_PSEUDO_MAP_VALUE, ~0, ~0, 0, 47),
+	BPF_EXIT_INSN(),
+	},
+	.fixup_map_array_48b = { 1 },
+	.result = REJECT,
+	.errstr = "invalid bpf_ld_imm64 insn",
+},
+{
+	"direct map access, invalid insn test 6",
+	.insns = {
+	BPF_MOV64_IMM(BPF_REG_0, 1),
+	BPF_LD_IMM64_RAW_FULL(BPF_REG_1, BPF_PSEUDO_MAP_FD, ~0, 0, 0, 0),
+	BPF_EXIT_INSN(),
+	},
+	.fixup_map_array_48b = { 1 },
+	.result = REJECT,
+	.errstr = "BPF_LD_IMM64 uses reserved fields",
+},
+{
+	"direct map access, invalid insn test 7",
+	.insns = {
+	BPF_MOV64_IMM(BPF_REG_0, 1),
+	BPF_LD_IMM64_RAW_FULL(BPF_REG_1, BPF_PSEUDO_MAP_FD, 0, ~0, 0, 0),
+	BPF_EXIT_INSN(),
+	},
+	.fixup_map_array_48b = { 1 },
+	.result = REJECT,
+	.errstr = "invalid bpf_ld_imm64 insn",
+},
+{
+	"direct map access, invalid insn test 8",
+	.insns = {
+	BPF_MOV64_IMM(BPF_REG_0, 1),
+	BPF_LD_IMM64_RAW_FULL(BPF_REG_1, BPF_PSEUDO_MAP_FD, ~0, ~0, 0, 0),
+	BPF_EXIT_INSN(),
+	},
+	.fixup_map_array_48b = { 1 },
+	.result = REJECT,
+	.errstr = "invalid bpf_ld_imm64 insn",
+},
+{
+	"direct map access, invalid insn test 9",
+	.insns = {
+	BPF_MOV64_IMM(BPF_REG_0, 1),
+	BPF_LD_IMM64_RAW_FULL(BPF_REG_1, BPF_PSEUDO_MAP_FD, 0, 0, 0, 47),
+	BPF_EXIT_INSN(),
+	},
+	.fixup_map_array_48b = { 1 },
+	.result = REJECT,
+	.errstr = "unrecognized bpf_ld_imm64 insn",
+},
-- 
cgit v1.2.3-55-g7522


From b915ebe6d9c8c6b5427e606c0ecee53df921382b Mon Sep 17 00:00:00 2001
From: Joe Stringer
Date: Tue, 9 Apr 2019 23:20:17 +0200
Subject: bpf, selftest: test global data/bss/rodata sections

Add tests for libbpf relocation of static variable references
into the .data, .rodata and .bss sections of the ELF, also add
read-only test for .rodata. All passing:

  # ./test_progs
  [...]
  test_global_data:PASS:load program 0 nsec
  test_global_data:PASS:pass global data run 925 nsec
  test_global_data_number:PASS:relocate .bss reference 925 nsec
  test_global_data_number:PASS:relocate .data reference 925 nsec
  test_global_data_number:PASS:relocate .rodata reference 925 nsec
  test_global_data_number:PASS:relocate .bss reference 925 nsec
  test_global_data_number:PASS:relocate .data reference 925 nsec
  test_global_data_number:PASS:relocate .rodata reference 925 nsec
  test_global_data_number:PASS:relocate .bss reference 925 nsec
  test_global_data_number:PASS:relocate .bss reference 925 nsec
  test_global_data_number:PASS:relocate .rodata reference 925 nsec
  test_global_data_number:PASS:relocate .rodata reference 925 nsec
  test_global_data_number:PASS:relocate .rodata reference 925 nsec
  test_global_data_string:PASS:relocate .rodata reference 925 nsec
  test_global_data_string:PASS:relocate .data reference 925 nsec
  test_global_data_string:PASS:relocate .bss reference 925 nsec
  test_global_data_string:PASS:relocate .data reference 925 nsec
  test_global_data_string:PASS:relocate .bss reference 925 nsec
  test_global_data_struct:PASS:relocate .rodata reference 925 nsec
  test_global_data_struct:PASS:relocate .bss reference 925 nsec
  test_global_data_struct:PASS:relocate .rodata reference 925 nsec
  test_global_data_struct:PASS:relocate .data reference 925 nsec
  test_global_data_rdonly:PASS:test .rodata read-only map 925 nsec
  [...]
  Summary: 229 PASSED, 0 FAILED

Note map helper signatures have been changed to avoid warnings
when passing in const data.

Joint work with Daniel Borkmann.

Signed-off-by: Joe Stringer <joe@wand.net.nz>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Andrii Nakryiko <andriin@fb.com>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/testing/selftests/bpf/bpf_helpers.h          |   8 +-
 .../testing/selftests/bpf/prog_tests/global_data.c | 157 +++++++++++++++++++++
 .../testing/selftests/bpf/progs/test_global_data.c | 106 ++++++++++++++
 3 files changed, 267 insertions(+), 4 deletions(-)
 create mode 100644 tools/testing/selftests/bpf/prog_tests/global_data.c
 create mode 100644 tools/testing/selftests/bpf/progs/test_global_data.c

diff --git a/tools/testing/selftests/bpf/bpf_helpers.h b/tools/testing/selftests/bpf/bpf_helpers.h
index 97d140961438..e85d62cb53d0 100644
--- a/tools/testing/selftests/bpf/bpf_helpers.h
+++ b/tools/testing/selftests/bpf/bpf_helpers.h
@@ -9,14 +9,14 @@
 #define SEC(NAME) __attribute__((section(NAME), used))
 
 /* helper functions called from eBPF programs written in C */
-static void *(*bpf_map_lookup_elem)(void *map, void *key) =
+static void *(*bpf_map_lookup_elem)(void *map, const void *key) =
 	(void *) BPF_FUNC_map_lookup_elem;
-static int (*bpf_map_update_elem)(void *map, void *key, void *value,
+static int (*bpf_map_update_elem)(void *map, const void *key, const void *value,
 				  unsigned long long flags) =
 	(void *) BPF_FUNC_map_update_elem;
-static int (*bpf_map_delete_elem)(void *map, void *key) =
+static int (*bpf_map_delete_elem)(void *map, const void *key) =
 	(void *) BPF_FUNC_map_delete_elem;
-static int (*bpf_map_push_elem)(void *map, void *value,
+static int (*bpf_map_push_elem)(void *map, const void *value,
 				unsigned long long flags) =
 	(void *) BPF_FUNC_map_push_elem;
 static int (*bpf_map_pop_elem)(void *map, void *value) =
diff --git a/tools/testing/selftests/bpf/prog_tests/global_data.c b/tools/testing/selftests/bpf/prog_tests/global_data.c
new file mode 100644
index 000000000000..d011079fb0bf
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/global_data.c
@@ -0,0 +1,157 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <test_progs.h>
+
+static void test_global_data_number(struct bpf_object *obj, __u32 duration)
+{
+	int i, err, map_fd;
+	uint64_t num;
+
+	map_fd = bpf_find_map(__func__, obj, "result_number");
+	if (map_fd < 0) {
+		error_cnt++;
+		return;
+	}
+
+	struct {
+		char *name;
+		uint32_t key;
+		uint64_t num;
+	} tests[] = {
+		{ "relocate .bss reference",     0, 0 },
+		{ "relocate .data reference",    1, 42 },
+		{ "relocate .rodata reference",  2, 24 },
+		{ "relocate .bss reference",     3, 0 },
+		{ "relocate .data reference",    4, 0xffeeff },
+		{ "relocate .rodata reference",  5, 0xabab },
+		{ "relocate .bss reference",     6, 1234 },
+		{ "relocate .bss reference",     7, 0 },
+		{ "relocate .rodata reference",  8, 0xab },
+		{ "relocate .rodata reference",  9, 0x1111111111111111 },
+		{ "relocate .rodata reference", 10, ~0 },
+	};
+
+	for (i = 0; i < sizeof(tests) / sizeof(tests[0]); i++) {
+		err = bpf_map_lookup_elem(map_fd, &tests[i].key, &num);
+		CHECK(err || num != tests[i].num, tests[i].name,
+		      "err %d result %lx expected %lx\n",
+		      err, num, tests[i].num);
+	}
+}
+
+static void test_global_data_string(struct bpf_object *obj, __u32 duration)
+{
+	int i, err, map_fd;
+	char str[32];
+
+	map_fd = bpf_find_map(__func__, obj, "result_string");
+	if (map_fd < 0) {
+		error_cnt++;
+		return;
+	}
+
+	struct {
+		char *name;
+		uint32_t key;
+		char str[32];
+	} tests[] = {
+		{ "relocate .rodata reference", 0, "abcdefghijklmnopqrstuvwxyz" },
+		{ "relocate .data reference",   1, "abcdefghijklmnopqrstuvwxyz" },
+		{ "relocate .bss reference",    2, "" },
+		{ "relocate .data reference",   3, "abcdexghijklmnopqrstuvwxyz" },
+		{ "relocate .bss reference",    4, "\0\0hello" },
+	};
+
+	for (i = 0; i < sizeof(tests) / sizeof(tests[0]); i++) {
+		err = bpf_map_lookup_elem(map_fd, &tests[i].key, str);
+		CHECK(err || memcmp(str, tests[i].str, sizeof(str)),
+		      tests[i].name, "err %d result \'%s\' expected \'%s\'\n",
+		      err, str, tests[i].str);
+	}
+}
+
+struct foo {
+	__u8  a;
+	__u32 b;
+	__u64 c;
+};
+
+static void test_global_data_struct(struct bpf_object *obj, __u32 duration)
+{
+	int i, err, map_fd;
+	struct foo val;
+
+	map_fd = bpf_find_map(__func__, obj, "result_struct");
+	if (map_fd < 0) {
+		error_cnt++;
+		return;
+	}
+
+	struct {
+		char *name;
+		uint32_t key;
+		struct foo val;
+	} tests[] = {
+		{ "relocate .rodata reference", 0, { 42, 0xfefeefef, 0x1111111111111111ULL, } },
+		{ "relocate .bss reference",    1, { } },
+		{ "relocate .rodata reference", 2, { } },
+		{ "relocate .data reference",   3, { 41, 0xeeeeefef, 0x2111111111111111ULL, } },
+	};
+
+	for (i = 0; i < sizeof(tests) / sizeof(tests[0]); i++) {
+		err = bpf_map_lookup_elem(map_fd, &tests[i].key, &val);
+		CHECK(err || memcmp(&val, &tests[i].val, sizeof(val)),
+		      tests[i].name, "err %d result { %u, %u, %llu } expected { %u, %u, %llu }\n",
+		      err, val.a, val.b, val.c, tests[i].val.a, tests[i].val.b, tests[i].val.c);
+	}
+}
+
+static void test_global_data_rdonly(struct bpf_object *obj, __u32 duration)
+{
+	int err = -ENOMEM, map_fd, zero = 0;
+	struct bpf_map *map;
+	__u8 *buff;
+
+	map = bpf_object__find_map_by_name(obj, "test_glo.rodata");
+	if (!map || !bpf_map__is_internal(map)) {
+		error_cnt++;
+		return;
+	}
+
+	map_fd = bpf_map__fd(map);
+	if (map_fd < 0) {
+		error_cnt++;
+		return;
+	}
+
+	buff = malloc(bpf_map__def(map)->value_size);
+	if (buff)
+		err = bpf_map_update_elem(map_fd, &zero, buff, 0);
+	free(buff);
+	CHECK(!err || errno != EPERM, "test .rodata read-only map",
+	      "err %d errno %d\n", err, errno);
+}
+
+void test_global_data(void)
+{
+	const char *file = "./test_global_data.o";
+	__u32 duration = 0, retval;
+	struct bpf_object *obj;
+	int err, prog_fd;
+
+	err = bpf_prog_load(file, BPF_PROG_TYPE_SCHED_CLS, &obj, &prog_fd);
+	if (CHECK(err, "load program", "error %d loading %s\n", err, file))
+		return;
+
+	err = bpf_prog_test_run(prog_fd, 1, &pkt_v4, sizeof(pkt_v4),
+				NULL, NULL, &retval, &duration);
+	CHECK(err || retval, "pass global data run",
+	      "err %d errno %d retval %d duration %d\n",
+	      err, errno, retval, duration);
+
+	test_global_data_number(obj, duration);
+	test_global_data_string(obj, duration);
+	test_global_data_struct(obj, duration);
+	test_global_data_rdonly(obj, duration);
+
+	bpf_object__close(obj);
+}
diff --git a/tools/testing/selftests/bpf/progs/test_global_data.c b/tools/testing/selftests/bpf/progs/test_global_data.c
new file mode 100644
index 000000000000..5ab14e941980
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_global_data.c
@@ -0,0 +1,106 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2019 Isovalent, Inc.
+
+#include <linux/bpf.h>
+#include <linux/pkt_cls.h>
+#include <string.h>
+
+#include "bpf_helpers.h"
+
+struct bpf_map_def SEC("maps") result_number = {
+	.type		= BPF_MAP_TYPE_ARRAY,
+	.key_size	= sizeof(__u32),
+	.value_size	= sizeof(__u64),
+	.max_entries	= 11,
+};
+
+struct bpf_map_def SEC("maps") result_string = {
+	.type		= BPF_MAP_TYPE_ARRAY,
+	.key_size	= sizeof(__u32),
+	.value_size	= 32,
+	.max_entries	= 5,
+};
+
+struct foo {
+	__u8  a;
+	__u32 b;
+	__u64 c;
+};
+
+struct bpf_map_def SEC("maps") result_struct = {
+	.type		= BPF_MAP_TYPE_ARRAY,
+	.key_size	= sizeof(__u32),
+	.value_size	= sizeof(struct foo),
+	.max_entries	= 5,
+};
+
+/* Relocation tests for __u64s. */
+static       __u64 num0;
+static       __u64 num1 = 42;
+static const __u64 num2 = 24;
+static       __u64 num3 = 0;
+static       __u64 num4 = 0xffeeff;
+static const __u64 num5 = 0xabab;
+static const __u64 num6 = 0xab;
+
+/* Relocation tests for strings. */
+static const char str0[32] = "abcdefghijklmnopqrstuvwxyz";
+static       char str1[32] = "abcdefghijklmnopqrstuvwxyz";
+static       char str2[32];
+
+/* Relocation tests for structs. */
+static const struct foo struct0 = {
+	.a = 42,
+	.b = 0xfefeefef,
+	.c = 0x1111111111111111ULL,
+};
+static struct foo struct1;
+static const struct foo struct2;
+static struct foo struct3 = {
+	.a = 41,
+	.b = 0xeeeeefef,
+	.c = 0x2111111111111111ULL,
+};
+
+#define test_reloc(map, num, var)					\
+	do {								\
+		__u32 key = num;					\
+		bpf_map_update_elem(&result_##map, &key, var, 0);	\
+	} while (0)
+
+SEC("static_data_load")
+int load_static_data(struct __sk_buff *skb)
+{
+	static const __u64 bar = ~0;
+
+	test_reloc(number, 0, &num0);
+	test_reloc(number, 1, &num1);
+	test_reloc(number, 2, &num2);
+	test_reloc(number, 3, &num3);
+	test_reloc(number, 4, &num4);
+	test_reloc(number, 5, &num5);
+	num4 = 1234;
+	test_reloc(number, 6, &num4);
+	test_reloc(number, 7, &num0);
+	test_reloc(number, 8, &num6);
+
+	test_reloc(string, 0, str0);
+	test_reloc(string, 1, str1);
+	test_reloc(string, 2, str2);
+	str1[5] = 'x';
+	test_reloc(string, 3, str1);
+	__builtin_memcpy(&str2[2], "hello", sizeof("hello"));
+	test_reloc(string, 4, str2);
+
+	test_reloc(struct, 0, &struct0);
+	test_reloc(struct, 1, &struct1);
+	test_reloc(struct, 2, &struct2);
+	test_reloc(struct, 3, &struct3);
+
+	test_reloc(number,  9, &struct0.c);
+	test_reloc(number, 10, &bar);
+
+	return TC_ACT_OK;
+}
+
+char _license[] SEC("license") = "GPL";
-- 
cgit v1.2.3-55-g7522


From c861168b7c219838637aaa8c3acc81707aa495f6 Mon Sep 17 00:00:00 2001
From: Daniel Borkmann
Date: Tue, 9 Apr 2019 23:20:18 +0200
Subject: bpf, selftest: add test cases for BTF Var and DataSec

Extend test_btf with various positive and negative tests around
BTF verification of kind Var and DataSec. All passing as well:

  # ./test_btf
  [...]
  BTF raw test[4] (global data test #1): OK
  BTF raw test[5] (global data test #2): OK
  BTF raw test[6] (global data test #3): OK
  BTF raw test[7] (global data test #4, unsupported linkage): OK
  BTF raw test[8] (global data test #5, invalid var type): OK
  BTF raw test[9] (global data test #6, invalid var type (fwd type)): OK
  BTF raw test[10] (global data test #7, invalid var type (fwd type)): OK
  BTF raw test[11] (global data test #8, invalid var size): OK
  BTF raw test[12] (global data test #9, invalid var size): OK
  BTF raw test[13] (global data test #10, invalid var size): OK
  BTF raw test[14] (global data test #11, multiple section members): OK
  BTF raw test[15] (global data test #12, invalid offset): OK
  BTF raw test[16] (global data test #13, invalid offset): OK
  BTF raw test[17] (global data test #14, invalid offset): OK
  BTF raw test[18] (global data test #15, not var kind): OK
  BTF raw test[19] (global data test #16, invalid var referencing sec): OK
  BTF raw test[20] (global data test #17, invalid var referencing var): OK
  BTF raw test[21] (global data test #18, invalid var loop): OK
  BTF raw test[22] (global data test #19, invalid var referencing var): OK
  BTF raw test[23] (global data test #20, invalid ptr referencing var): OK
  BTF raw test[24] (global data test #21, var included in struct): OK
  BTF raw test[25] (global data test #22, array of var): OK
  [...]
  PASS:167 SKIP:0 FAIL:0

Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/testing/selftests/bpf/test_btf.c | 665 ++++++++++++++++++++++++++++++++-
 1 file changed, 663 insertions(+), 2 deletions(-)

diff --git a/tools/testing/selftests/bpf/test_btf.c b/tools/testing/selftests/bpf/test_btf.c
index 5afc3f7dff81..08010e619a1c 100644
--- a/tools/testing/selftests/bpf/test_btf.c
+++ b/tools/testing/selftests/bpf/test_btf.c
@@ -85,6 +85,11 @@ static int __base_pr(enum libbpf_print_level level __attribute__((unused)),
 #define BTF_UNION_ENC(name, nr_elems, sz)	\
 	BTF_TYPE_ENC(name, BTF_INFO_ENC(BTF_KIND_UNION, 0, nr_elems), sz)
 
+#define BTF_VAR_ENC(name, type, linkage)	\
+	BTF_TYPE_ENC(name, BTF_INFO_ENC(BTF_KIND_VAR, 0, 0), type), (linkage)
+#define BTF_VAR_SECINFO_ENC(type, offset, size)	\
+	(type), (offset), (size)
+
 #define BTF_MEMBER_ENC(name, type, bits_offset)	\
 	(name), (type), (bits_offset)
 #define BTF_ENUM_ENC(name, val) (name), (val)
@@ -291,7 +296,6 @@ static struct btf_raw_test raw_tests[] = {
 	.value_type_id = 3,
 	.max_entries = 4,
 },
-
 {
 	.descr = "struct test #3 Invalid member offset",
 	.raw_types = {
@@ -319,7 +323,664 @@ static struct btf_raw_test raw_tests[] = {
 	.btf_load_err = true,
 	.err_str = "Invalid member bits_offset",
 },
-
+/*
+ * struct A {
+ *	unsigned long long m;
+ *	int n;
+ *	char o;
+ *	[3 bytes hole]
+ *	int p[8];
+ * };
+ */
+{
+	.descr = "global data test #1",
+	.raw_types = {
+		/* int */
+		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),	/* [1] */
+		/* unsigned long long */
+		BTF_TYPE_INT_ENC(0, 0, 0, 64, 8),		/* [2] */
+		/* char */
+		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 8, 1),	/* [3] */
+		/* int[8] */
+		BTF_TYPE_ARRAY_ENC(1, 1, 8),			/* [4] */
+		/* struct A { */				/* [5] */
+		BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_STRUCT, 0, 4), 48),
+		BTF_MEMBER_ENC(NAME_TBD, 2, 0),	/* unsigned long long m;*/
+		BTF_MEMBER_ENC(NAME_TBD, 1, 64),/* int n;		*/
+		BTF_MEMBER_ENC(NAME_TBD, 3, 96),/* char o;		*/
+		BTF_MEMBER_ENC(NAME_TBD, 4, 128),/* int p[8]		*/
+		/* } */
+		BTF_END_RAW,
+	},
+	.str_sec = "\0A\0m\0n\0o\0p",
+	.str_sec_size = sizeof("\0A\0m\0n\0o\0p"),
+	.map_type = BPF_MAP_TYPE_ARRAY,
+	.map_name = "struct_test1_map",
+	.key_size = sizeof(int),
+	.value_size = 48,
+	.key_type_id = 1,
+	.value_type_id = 5,
+	.max_entries = 4,
+},
+/*
+ * struct A {
+ *	unsigned long long m;
+ *	int n;
+ *	char o;
+ *	[3 bytes hole]
+ *	int p[8];
+ * };
+ * static struct A t; <- in .bss
+ */
+{
+	.descr = "global data test #2",
+	.raw_types = {
+		/* int */
+		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),	/* [1] */
+		/* unsigned long long */
+		BTF_TYPE_INT_ENC(0, 0, 0, 64, 8),		/* [2] */
+		/* char */
+		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 8, 1),	/* [3] */
+		/* int[8] */
+		BTF_TYPE_ARRAY_ENC(1, 1, 8),			/* [4] */
+		/* struct A { */				/* [5] */
+		BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_STRUCT, 0, 4), 48),
+		BTF_MEMBER_ENC(NAME_TBD, 2, 0),	/* unsigned long long m;*/
+		BTF_MEMBER_ENC(NAME_TBD, 1, 64),/* int n;		*/
+		BTF_MEMBER_ENC(NAME_TBD, 3, 96),/* char o;		*/
+		BTF_MEMBER_ENC(NAME_TBD, 4, 128),/* int p[8]		*/
+		/* } */
+		/* static struct A t */
+		BTF_VAR_ENC(NAME_TBD, 5, 0),			/* [6] */
+		/* .bss section */				/* [7] */
+		BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_DATASEC, 0, 1), 48),
+		BTF_VAR_SECINFO_ENC(6, 0, 48),
+		BTF_END_RAW,
+	},
+	.str_sec = "\0A\0m\0n\0o\0p\0t\0.bss",
+	.str_sec_size = sizeof("\0A\0m\0n\0o\0p\0t\0.bss"),
+	.map_type = BPF_MAP_TYPE_ARRAY,
+	.map_name = ".bss",
+	.key_size = sizeof(int),
+	.value_size = 48,
+	.key_type_id = 0,
+	.value_type_id = 7,
+	.max_entries = 1,
+},
+{
+	.descr = "global data test #3",
+	.raw_types = {
+		/* int */
+		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),	/* [1] */
+		/* static int t */
+		BTF_VAR_ENC(NAME_TBD, 1, 0),			/* [2] */
+		/* .bss section */				/* [3] */
+		BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_DATASEC, 0, 1), 4),
+		BTF_VAR_SECINFO_ENC(2, 0, 4),
+		BTF_END_RAW,
+	},
+	.str_sec = "\0t\0.bss",
+	.str_sec_size = sizeof("\0t\0.bss"),
+	.map_type = BPF_MAP_TYPE_ARRAY,
+	.map_name = ".bss",
+	.key_size = sizeof(int),
+	.value_size = 4,
+	.key_type_id = 0,
+	.value_type_id = 3,
+	.max_entries = 1,
+},
+{
+	.descr = "global data test #4, unsupported linkage",
+	.raw_types = {
+		/* int */
+		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),	/* [1] */
+		/* static int t */
+		BTF_VAR_ENC(NAME_TBD, 1, 2),			/* [2] */
+		/* .bss section */				/* [3] */
+		BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_DATASEC, 0, 1), 4),
+		BTF_VAR_SECINFO_ENC(2, 0, 4),
+		BTF_END_RAW,
+	},
+	.str_sec = "\0t\0.bss",
+	.str_sec_size = sizeof("\0t\0.bss"),
+	.map_type = BPF_MAP_TYPE_ARRAY,
+	.map_name = ".bss",
+	.key_size = sizeof(int),
+	.value_size = 4,
+	.key_type_id = 0,
+	.value_type_id = 3,
+	.max_entries = 1,
+	.btf_load_err = true,
+	.err_str = "Linkage not supported",
+},
+{
+	.descr = "global data test #5, invalid var type",
+	.raw_types = {
+		/* static void t */
+		BTF_VAR_ENC(NAME_TBD, 0, 0),			/* [1] */
+		/* .bss section */				/* [2] */
+		BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_DATASEC, 0, 1), 4),
+		BTF_VAR_SECINFO_ENC(1, 0, 4),
+		BTF_END_RAW,
+	},
+	.str_sec = "\0t\0.bss",
+	.str_sec_size = sizeof("\0t\0.bss"),
+	.map_type = BPF_MAP_TYPE_ARRAY,
+	.map_name = ".bss",
+	.key_size = sizeof(int),
+	.value_size = 4,
+	.key_type_id = 0,
+	.value_type_id = 2,
+	.max_entries = 1,
+	.btf_load_err = true,
+	.err_str = "Invalid type_id",
+},
+{
+	.descr = "global data test #6, invalid var type (fwd type)",
+	.raw_types = {
+		/* union A */
+		BTF_TYPE_ENC(NAME_TBD,
+			     BTF_INFO_ENC(BTF_KIND_FWD, 1, 0), 0), /* [1] */
+		/* static union A t */
+		BTF_VAR_ENC(NAME_TBD, 1, 0),			/* [2] */
+		/* .bss section */				/* [3] */
+		BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_DATASEC, 0, 1), 4),
+		BTF_VAR_SECINFO_ENC(2, 0, 4),
+		BTF_END_RAW,
+	},
+	.str_sec = "\0A\0t\0.bss",
+	.str_sec_size = sizeof("\0A\0t\0.bss"),
+	.map_type = BPF_MAP_TYPE_ARRAY,
+	.map_name = ".bss",
+	.key_size = sizeof(int),
+	.value_size = 4,
+	.key_type_id = 0,
+	.value_type_id = 2,
+	.max_entries = 1,
+	.btf_load_err = true,
+	.err_str = "Invalid type",
+},
+{
+	.descr = "global data test #7, invalid var type (fwd type)",
+	.raw_types = {
+		/* union A */
+		BTF_TYPE_ENC(NAME_TBD,
+			     BTF_INFO_ENC(BTF_KIND_FWD, 1, 0), 0), /* [1] */
+		/* static union A t */
+		BTF_VAR_ENC(NAME_TBD, 1, 0),			/* [2] */
+		/* .bss section */				/* [3] */
+		BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_DATASEC, 0, 1), 4),
+		BTF_VAR_SECINFO_ENC(1, 0, 4),
+		BTF_END_RAW,
+	},
+	.str_sec = "\0A\0t\0.bss",
+	.str_sec_size = sizeof("\0A\0t\0.bss"),
+	.map_type = BPF_MAP_TYPE_ARRAY,
+	.map_name = ".bss",
+	.key_size = sizeof(int),
+	.value_size = 4,
+	.key_type_id = 0,
+	.value_type_id = 2,
+	.max_entries = 1,
+	.btf_load_err = true,
+	.err_str = "Invalid type",
+},
+{
+	.descr = "global data test #8, invalid var size",
+	.raw_types = {
+		/* int */
+		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),	/* [1] */
+		/* unsigned long long */
+		BTF_TYPE_INT_ENC(0, 0, 0, 64, 8),		/* [2] */
+		/* char */
+		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 8, 1),	/* [3] */
+		/* int[8] */
+		BTF_TYPE_ARRAY_ENC(1, 1, 8),			/* [4] */
+		/* struct A { */				/* [5] */
+		BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_STRUCT, 0, 4), 48),
+		BTF_MEMBER_ENC(NAME_TBD, 2, 0),	/* unsigned long long m;*/
+		BTF_MEMBER_ENC(NAME_TBD, 1, 64),/* int n;		*/
+		BTF_MEMBER_ENC(NAME_TBD, 3, 96),/* char o;		*/
+		BTF_MEMBER_ENC(NAME_TBD, 4, 128),/* int p[8]		*/
+		/* } */
+		/* static struct A t */
+		BTF_VAR_ENC(NAME_TBD, 5, 0),			/* [6] */
+		/* .bss section */				/* [7] */
+		BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_DATASEC, 0, 1), 48),
+		BTF_VAR_SECINFO_ENC(6, 0, 47),
+		BTF_END_RAW,
+	},
+	.str_sec = "\0A\0m\0n\0o\0p\0t\0.bss",
+	.str_sec_size = sizeof("\0A\0m\0n\0o\0p\0t\0.bss"),
+	.map_type = BPF_MAP_TYPE_ARRAY,
+	.map_name = ".bss",
+	.key_size = sizeof(int),
+	.value_size = 48,
+	.key_type_id = 0,
+	.value_type_id = 7,
+	.max_entries = 1,
+	.btf_load_err = true,
+	.err_str = "Invalid size",
+},
+{
+	.descr = "global data test #9, invalid var size",
+	.raw_types = {
+		/* int */
+		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),	/* [1] */
+		/* unsigned long long */
+		BTF_TYPE_INT_ENC(0, 0, 0, 64, 8),		/* [2] */
+		/* char */
+		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 8, 1),	/* [3] */
+		/* int[8] */
+		BTF_TYPE_ARRAY_ENC(1, 1, 8),			/* [4] */
+		/* struct A { */				/* [5] */
+		BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_STRUCT, 0, 4), 48),
+		BTF_MEMBER_ENC(NAME_TBD, 2, 0),	/* unsigned long long m;*/
+		BTF_MEMBER_ENC(NAME_TBD, 1, 64),/* int n;		*/
+		BTF_MEMBER_ENC(NAME_TBD, 3, 96),/* char o;		*/
+		BTF_MEMBER_ENC(NAME_TBD, 4, 128),/* int p[8]		*/
+		/* } */
+		/* static struct A t */
+		BTF_VAR_ENC(NAME_TBD, 5, 0),			/* [6] */
+		/* .bss section */				/* [7] */
+		BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_DATASEC, 0, 1), 46),
+		BTF_VAR_SECINFO_ENC(6, 0, 48),
+		BTF_END_RAW,
+	},
+	.str_sec = "\0A\0m\0n\0o\0p\0t\0.bss",
+	.str_sec_size = sizeof("\0A\0m\0n\0o\0p\0t\0.bss"),
+	.map_type = BPF_MAP_TYPE_ARRAY,
+	.map_name = ".bss",
+	.key_size = sizeof(int),
+	.value_size = 48,
+	.key_type_id = 0,
+	.value_type_id = 7,
+	.max_entries = 1,
+	.btf_load_err = true,
+	.err_str = "Invalid size",
+},
+{
+	.descr = "global data test #10, invalid var size",
+	.raw_types = {
+		/* int */
+		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),	/* [1] */
+		/* unsigned long long */
+		BTF_TYPE_INT_ENC(0, 0, 0, 64, 8),		/* [2] */
+		/* char */
+		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 8, 1),	/* [3] */
+		/* int[8] */
+		BTF_TYPE_ARRAY_ENC(1, 1, 8),			/* [4] */
+		/* struct A { */				/* [5] */
+		BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_STRUCT, 0, 4), 48),
+		BTF_MEMBER_ENC(NAME_TBD, 2, 0),	/* unsigned long long m;*/
+		BTF_MEMBER_ENC(NAME_TBD, 1, 64),/* int n;		*/
+		BTF_MEMBER_ENC(NAME_TBD, 3, 96),/* char o;		*/
+		BTF_MEMBER_ENC(NAME_TBD, 4, 128),/* int p[8]		*/
+		/* } */
+		/* static struct A t */
+		BTF_VAR_ENC(NAME_TBD, 5, 0),			/* [6] */
+		/* .bss section */				/* [7] */
+		BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_DATASEC, 0, 1), 46),
+		BTF_VAR_SECINFO_ENC(6, 0, 46),
+		BTF_END_RAW,
+	},
+	.str_sec = "\0A\0m\0n\0o\0p\0t\0.bss",
+	.str_sec_size = sizeof("\0A\0m\0n\0o\0p\0t\0.bss"),
+	.map_type = BPF_MAP_TYPE_ARRAY,
+	.map_name = ".bss",
+	.key_size = sizeof(int),
+	.value_size = 48,
+	.key_type_id = 0,
+	.value_type_id = 7,
+	.max_entries = 1,
+	.btf_load_err = true,
+	.err_str = "Invalid size",
+},
+{
+	.descr = "global data test #11, multiple section members",
+	.raw_types = {
+		/* int */
+		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),	/* [1] */
+		/* unsigned long long */
+		BTF_TYPE_INT_ENC(0, 0, 0, 64, 8),		/* [2] */
+		/* char */
+		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 8, 1),	/* [3] */
+		/* int[8] */
+		BTF_TYPE_ARRAY_ENC(1, 1, 8),			/* [4] */
+		/* struct A { */				/* [5] */
+		BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_STRUCT, 0, 4), 48),
+		BTF_MEMBER_ENC(NAME_TBD, 2, 0),	/* unsigned long long m;*/
+		BTF_MEMBER_ENC(NAME_TBD, 1, 64),/* int n;		*/
+		BTF_MEMBER_ENC(NAME_TBD, 3, 96),/* char o;		*/
+		BTF_MEMBER_ENC(NAME_TBD, 4, 128),/* int p[8]		*/
+		/* } */
+		/* static struct A t */
+		BTF_VAR_ENC(NAME_TBD, 5, 0),			/* [6] */
+		/* static int u */
+		BTF_VAR_ENC(NAME_TBD, 1, 0),			/* [7] */
+		/* .bss section */				/* [8] */
+		BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_DATASEC, 0, 2), 62),
+		BTF_VAR_SECINFO_ENC(6, 10, 48),
+		BTF_VAR_SECINFO_ENC(7, 58, 4),
+		BTF_END_RAW,
+	},
+	.str_sec = "\0A\0m\0n\0o\0p\0t\0u\0.bss",
+	.str_sec_size = sizeof("\0A\0m\0n\0o\0p\0t\0u\0.bss"),
+	.map_type = BPF_MAP_TYPE_ARRAY,
+	.map_name = ".bss",
+	.key_size = sizeof(int),
+	.value_size = 62,
+	.key_type_id = 0,
+	.value_type_id = 8,
+	.max_entries = 1,
+},
+{
+	.descr = "global data test #12, invalid offset",
+	.raw_types = {
+		/* int */
+		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),	/* [1] */
+		/* unsigned long long */
+		BTF_TYPE_INT_ENC(0, 0, 0, 64, 8),		/* [2] */
+		/* char */
+		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 8, 1),	/* [3] */
+		/* int[8] */
+		BTF_TYPE_ARRAY_ENC(1, 1, 8),			/* [4] */
+		/* struct A { */				/* [5] */
+		BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_STRUCT, 0, 4), 48),
+		BTF_MEMBER_ENC(NAME_TBD, 2, 0),	/* unsigned long long m;*/
+		BTF_MEMBER_ENC(NAME_TBD, 1, 64),/* int n;		*/
+		BTF_MEMBER_ENC(NAME_TBD, 3, 96),/* char o;		*/
+		BTF_MEMBER_ENC(NAME_TBD, 4, 128),/* int p[8]		*/
+		/* } */
+		/* static struct A t */
+		BTF_VAR_ENC(NAME_TBD, 5, 0),			/* [6] */
+		/* static int u */
+		BTF_VAR_ENC(NAME_TBD, 1, 0),			/* [7] */
+		/* .bss section */				/* [8] */
+		BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_DATASEC, 0, 2), 62),
+		BTF_VAR_SECINFO_ENC(6, 10, 48),
+		BTF_VAR_SECINFO_ENC(7, 60, 4),
+		BTF_END_RAW,
+	},
+	.str_sec = "\0A\0m\0n\0o\0p\0t\0u\0.bss",
+	.str_sec_size = sizeof("\0A\0m\0n\0o\0p\0t\0u\0.bss"),
+	.map_type = BPF_MAP_TYPE_ARRAY,
+	.map_name = ".bss",
+	.key_size = sizeof(int),
+	.value_size = 62,
+	.key_type_id = 0,
+	.value_type_id = 8,
+	.max_entries = 1,
+	.btf_load_err = true,
+	.err_str = "Invalid offset+size",
+},
+{
+	.descr = "global data test #13, invalid offset",
+	.raw_types = {
+		/* int */
+		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),	/* [1] */
+		/* unsigned long long */
+		BTF_TYPE_INT_ENC(0, 0, 0, 64, 8),		/* [2] */
+		/* char */
+		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 8, 1),	/* [3] */
+		/* int[8] */
+		BTF_TYPE_ARRAY_ENC(1, 1, 8),			/* [4] */
+		/* struct A { */				/* [5] */
+		BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_STRUCT, 0, 4), 48),
+		BTF_MEMBER_ENC(NAME_TBD, 2, 0),	/* unsigned long long m;*/
+		BTF_MEMBER_ENC(NAME_TBD, 1, 64),/* int n;		*/
+		BTF_MEMBER_ENC(NAME_TBD, 3, 96),/* char o;		*/
+		BTF_MEMBER_ENC(NAME_TBD, 4, 128),/* int p[8]		*/
+		/* } */
+		/* static struct A t */
+		BTF_VAR_ENC(NAME_TBD, 5, 0),			/* [6] */
+		/* static int u */
+		BTF_VAR_ENC(NAME_TBD, 1, 0),			/* [7] */
+		/* .bss section */				/* [8] */
+		BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_DATASEC, 0, 2), 62),
+		BTF_VAR_SECINFO_ENC(6, 10, 48),
+		BTF_VAR_SECINFO_ENC(7, 12, 4),
+		BTF_END_RAW,
+	},
+	.str_sec = "\0A\0m\0n\0o\0p\0t\0u\0.bss",
+	.str_sec_size = sizeof("\0A\0m\0n\0o\0p\0t\0u\0.bss"),
+	.map_type = BPF_MAP_TYPE_ARRAY,
+	.map_name = ".bss",
+	.key_size = sizeof(int),
+	.value_size = 62,
+	.key_type_id = 0,
+	.value_type_id = 8,
+	.max_entries = 1,
+	.btf_load_err = true,
+	.err_str = "Invalid offset",
+},
+{
+	.descr = "global data test #14, invalid offset",
+	.raw_types = {
+		/* int */
+		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),	/* [1] */
+		/* unsigned long long */
+		BTF_TYPE_INT_ENC(0, 0, 0, 64, 8),		/* [2] */
+		/* char */
+		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 8, 1),	/* [3] */
+		/* int[8] */
+		BTF_TYPE_ARRAY_ENC(1, 1, 8),			/* [4] */
+		/* struct A { */				/* [5] */
+		BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_STRUCT, 0, 4), 48),
+		BTF_MEMBER_ENC(NAME_TBD, 2, 0),	/* unsigned long long m;*/
+		BTF_MEMBER_ENC(NAME_TBD, 1, 64),/* int n;		*/
+		BTF_MEMBER_ENC(NAME_TBD, 3, 96),/* char o;		*/
+		BTF_MEMBER_ENC(NAME_TBD, 4, 128),/* int p[8]		*/
+		/* } */
+		/* static struct A t */
+		BTF_VAR_ENC(NAME_TBD, 5, 0),			/* [6] */
+		/* static int u */
+		BTF_VAR_ENC(NAME_TBD, 1, 0),			/* [7] */
+		/* .bss section */				/* [8] */
+		BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_DATASEC, 0, 2), 62),
+		BTF_VAR_SECINFO_ENC(7, 58, 4),
+		BTF_VAR_SECINFO_ENC(6, 10, 48),
+		BTF_END_RAW,
+	},
+	.str_sec = "\0A\0m\0n\0o\0p\0t\0u\0.bss",
+	.str_sec_size = sizeof("\0A\0m\0n\0o\0p\0t\0u\0.bss"),
+	.map_type = BPF_MAP_TYPE_ARRAY,
+	.map_name = ".bss",
+	.key_size = sizeof(int),
+	.value_size = 62,
+	.key_type_id = 0,
+	.value_type_id = 8,
+	.max_entries = 1,
+	.btf_load_err = true,
+	.err_str = "Invalid offset",
+},
+{
+	.descr = "global data test #15, not var kind",
+	.raw_types = {
+		/* int */
+		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),	/* [1] */
+		BTF_VAR_ENC(NAME_TBD, 1, 0),			/* [2] */
+		/* .bss section */				/* [3] */
+		BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_DATASEC, 0, 1), 4),
+		BTF_VAR_SECINFO_ENC(1, 0, 4),
+		BTF_END_RAW,
+	},
+	.str_sec = "\0A\0t\0.bss",
+	.str_sec_size = sizeof("\0A\0t\0.bss"),
+	.map_type = BPF_MAP_TYPE_ARRAY,
+	.map_name = ".bss",
+	.key_size = sizeof(int),
+	.value_size = 4,
+	.key_type_id = 0,
+	.value_type_id = 3,
+	.max_entries = 1,
+	.btf_load_err = true,
+	.err_str = "Not a VAR kind member",
+},
+{
+	.descr = "global data test #16, invalid var referencing sec",
+	.raw_types = {
+		/* int */
+		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),	/* [1] */
+		BTF_VAR_ENC(NAME_TBD, 5, 0),			/* [2] */
+		BTF_VAR_ENC(NAME_TBD, 2, 0),			/* [3] */
+		/* a section */					/* [4] */
+		BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_DATASEC, 0, 1), 4),
+		BTF_VAR_SECINFO_ENC(3, 0, 4),
+		/* a section */					/* [5] */
+		BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_DATASEC, 0, 1), 4),
+		BTF_VAR_SECINFO_ENC(6, 0, 4),
+		BTF_VAR_ENC(NAME_TBD, 1, 0),			/* [6] */
+		BTF_END_RAW,
+	},
+	.str_sec = "\0A\0t\0s\0a\0a",
+	.str_sec_size = sizeof("\0A\0t\0s\0a\0a"),
+	.map_type = BPF_MAP_TYPE_ARRAY,
+	.map_name = ".bss",
+	.key_size = sizeof(int),
+	.value_size = 4,
+	.key_type_id = 0,
+	.value_type_id = 4,
+	.max_entries = 1,
+	.btf_load_err = true,
+	.err_str = "Invalid type_id",
+},
+{
+	.descr = "global data test #17, invalid var referencing var",
+	.raw_types = {
+		/* int */
+		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, 2, 0),			/* [3] */
+		/* a section */					/* [4] */
+		BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_DATASEC, 0, 1), 4),
+		BTF_VAR_SECINFO_ENC(3, 0, 4),
+		BTF_END_RAW,
+	},
+	.str_sec = "\0A\0t\0s\0a\0a",
+	.str_sec_size = sizeof("\0A\0t\0s\0a\0a"),
+	.map_type = BPF_MAP_TYPE_ARRAY,
+	.map_name = ".bss",
+	.key_size = sizeof(int),
+	.value_size = 4,
+	.key_type_id = 0,
+	.value_type_id = 4,
+	.max_entries = 1,
+	.btf_load_err = true,
+	.err_str = "Invalid type_id",
+},
+{
+	.descr = "global data test #18, invalid var loop",
+	.raw_types = {
+		/* int */
+		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),	/* [1] */
+		BTF_VAR_ENC(NAME_TBD, 2, 0),			/* [2] */
+		/* .bss section */				/* [3] */
+		BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_DATASEC, 0, 1), 4),
+		BTF_VAR_SECINFO_ENC(2, 0, 4),
+		BTF_END_RAW,
+	},
+	.str_sec = "\0A\0t\0aaa",
+	.str_sec_size = sizeof("\0A\0t\0aaa"),
+	.map_type = BPF_MAP_TYPE_ARRAY,
+	.map_name = ".bss",
+	.key_size = sizeof(int),
+	.value_size = 4,
+	.key_type_id = 0,
+	.value_type_id = 4,
+	.max_entries = 1,
+	.btf_load_err = true,
+	.err_str = "Invalid type_id",
+},
+{
+	.descr = "global data test #19, invalid var referencing var",
+	.raw_types = {
+		/* int */
+		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),	/* [1] */
+		BTF_VAR_ENC(NAME_TBD, 3, 0),			/* [2] */
+		BTF_VAR_ENC(NAME_TBD, 1, 0),			/* [3] */
+		BTF_END_RAW,
+	},
+	.str_sec = "\0A\0t\0s\0a\0a",
+	.str_sec_size = sizeof("\0A\0t\0s\0a\0a"),
+	.map_type = BPF_MAP_TYPE_ARRAY,
+	.map_name = ".bss",
+	.key_size = sizeof(int),
+	.value_size = 4,
+	.key_type_id = 0,
+	.value_type_id = 4,
+	.max_entries = 1,
+	.btf_load_err = true,
+	.err_str = "Invalid type_id",
+},
+{
+	.descr = "global data test #20, invalid ptr referencing var",
+	.raw_types = {
+		/* int */
+		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),	/* [1] */
+		/* PTR type_id=3	*/			/* [2] */
+		BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_PTR, 0, 0), 3),
+		BTF_VAR_ENC(NAME_TBD, 1, 0),			/* [3] */
+		BTF_END_RAW,
+	},
+	.str_sec = "\0A\0t\0s\0a\0a",
+	.str_sec_size = sizeof("\0A\0t\0s\0a\0a"),
+	.map_type = BPF_MAP_TYPE_ARRAY,
+	.map_name = ".bss",
+	.key_size = sizeof(int),
+	.value_size = 4,
+	.key_type_id = 0,
+	.value_type_id = 4,
+	.max_entries = 1,
+	.btf_load_err = true,
+	.err_str = "Invalid type_id",
+},
+{
+	.descr = "global data test #21, var included in struct",
+	.raw_types = {
+		/* int */
+		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),	/* [1] */
+		/* struct A { */				/* [2] */
+		BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_STRUCT, 0, 2), sizeof(int) * 2),
+		BTF_MEMBER_ENC(NAME_TBD, 1, 0),	/* int m; */
+		BTF_MEMBER_ENC(NAME_TBD, 3, 32),/* VAR type_id=3; */
+		/* } */
+		BTF_VAR_ENC(NAME_TBD, 1, 0),			/* [3] */
+		BTF_END_RAW,
+	},
+	.str_sec = "\0A\0t\0s\0a\0a",
+	.str_sec_size = sizeof("\0A\0t\0s\0a\0a"),
+	.map_type = BPF_MAP_TYPE_ARRAY,
+	.map_name = ".bss",
+	.key_size = sizeof(int),
+	.value_size = 4,
+	.key_type_id = 0,
+	.value_type_id = 4,
+	.max_entries = 1,
+	.btf_load_err = true,
+	.err_str = "Invalid member",
+},
+{
+	.descr = "global data test #22, array of var",
+	.raw_types = {
+		/* int */
+		BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4),	/* [1] */
+		BTF_TYPE_ARRAY_ENC(3, 1, 4),			/* [2] */
+		BTF_VAR_ENC(NAME_TBD, 1, 0),			/* [3] */
+		BTF_END_RAW,
+	},
+	.str_sec = "\0A\0t\0s\0a\0a",
+	.str_sec_size = sizeof("\0A\0t\0s\0a\0a"),
+	.map_type = BPF_MAP_TYPE_ARRAY,
+	.map_name = ".bss",
+	.key_size = sizeof(int),
+	.value_size = 4,
+	.key_type_id = 0,
+	.value_type_id = 4,
+	.max_entries = 1,
+	.btf_load_err = true,
+	.err_str = "Invalid elem",
+},
 /* Test member exceeds the size of struct.
  *
  * struct A {
-- 
cgit v1.2.3-55-g7522


From 69a0f9ecef22131982ba328e6b74ebb082bc0992 Mon Sep 17 00:00:00 2001
From: Yonghong Song
Date: Tue, 9 Apr 2019 17:37:41 -0700
Subject: bpf, bpftool: fix a few ubsan warnings

The issue is reported at https://github.com/libbpf/libbpf/issues/28.

Basically, per C standard, for
  void *memcpy(void *dest, const void *src, size_t n)
if "dest" or "src" is NULL, regardless of whether "n" is 0 or not,
the result of memcpy is undefined. clang ubsan reported three such
instances in bpf.c with the following pattern:
  memcpy(dest, 0, 0).

Although in practice, no known compiler will cause issues when
copy size is 0. Let us still fix the issue to silence ubsan
warnings.

Signed-off-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/lib/bpf/bpf.c | 19 +++++++++----------
 1 file changed, 9 insertions(+), 10 deletions(-)

diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c
index c039094ad3aa..dababce68f0b 100644
--- a/tools/lib/bpf/bpf.c
+++ b/tools/lib/bpf/bpf.c
@@ -79,7 +79,6 @@ static inline int sys_bpf_prog_load(union bpf_attr *attr, unsigned int size)
 
 int bpf_create_map_xattr(const struct bpf_create_map_attr *create_attr)
 {
-	__u32 name_len = create_attr->name ? strlen(create_attr->name) : 0;
 	union bpf_attr attr;
 
 	memset(&attr, '\0', sizeof(attr));
@@ -89,8 +88,9 @@ int bpf_create_map_xattr(const struct bpf_create_map_attr *create_attr)
 	attr.value_size = create_attr->value_size;
 	attr.max_entries = create_attr->max_entries;
 	attr.map_flags = create_attr->map_flags;
-	memcpy(attr.map_name, create_attr->name,
-	       min(name_len, BPF_OBJ_NAME_LEN - 1));
+	if (create_attr->name)
+		memcpy(attr.map_name, create_attr->name,
+		       min(strlen(create_attr->name), BPF_OBJ_NAME_LEN - 1));
 	attr.numa_node = create_attr->numa_node;
 	attr.btf_fd = create_attr->btf_fd;
 	attr.btf_key_type_id = create_attr->btf_key_type_id;
@@ -155,7 +155,6 @@ int bpf_create_map_in_map_node(enum bpf_map_type map_type, const char *name,
 			       int key_size, int inner_map_fd, int max_entries,
 			       __u32 map_flags, int node)
 {
-	__u32 name_len = name ? strlen(name) : 0;
 	union bpf_attr attr;
 
 	memset(&attr, '\0', sizeof(attr));
@@ -166,7 +165,9 @@ int bpf_create_map_in_map_node(enum bpf_map_type map_type, const char *name,
 	attr.inner_map_fd = inner_map_fd;
 	attr.max_entries = max_entries;
 	attr.map_flags = map_flags;
-	memcpy(attr.map_name, name, min(name_len, BPF_OBJ_NAME_LEN - 1));
+	if (name)
+		memcpy(attr.map_name, name,
+		       min(strlen(name), BPF_OBJ_NAME_LEN - 1));
 
 	if (node >= 0) {
 		attr.map_flags |= BPF_F_NUMA_NODE;
@@ -216,7 +217,6 @@ int bpf_load_program_xattr(const struct bpf_load_program_attr *load_attr,
 	void *finfo = NULL, *linfo = NULL;
 	union bpf_attr attr;
 	__u32 log_level;
-	__u32 name_len;
 	int fd;
 
 	if (!load_attr || !log_buf != !log_buf_sz)
@@ -226,8 +226,6 @@ int bpf_load_program_xattr(const struct bpf_load_program_attr *load_attr,
 	if (log_level > (4 | 2 | 1) || (log_level && !log_buf))
 		return -EINVAL;
 
-	name_len = load_attr->name ? strlen(load_attr->name) : 0;
-
 	memset(&attr, 0, sizeof(attr));
 	attr.prog_type = load_attr->prog_type;
 	attr.expected_attach_type = load_attr->expected_attach_type;
@@ -253,8 +251,9 @@ int bpf_load_program_xattr(const struct bpf_load_program_attr *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);
-	memcpy(attr.prog_name, load_attr->name,
-	       min(name_len, BPF_OBJ_NAME_LEN - 1));
+	if (load_attr->name)
+		memcpy(attr.prog_name, load_attr->name,
+		       min(strlen(load_attr->name), BPF_OBJ_NAME_LEN - 1));
 
 	fd = sys_bpf_prog_load(&attr, sizeof(attr));
 	if (fd >= 0)
-- 
cgit v1.2.3-55-g7522


From 50bd645b3a21a374dbd0fa8273a5f4e98001fb05 Mon Sep 17 00:00:00 2001
From: Magnus Karlsson
Date: Wed, 10 Apr 2019 08:54:16 +0200
Subject: libbpf: fix crash in XDP socket part with new larger BPF_LOG_BUF_SIZE

In commit da11b417583e ("libbpf: teach libbpf about log_level bit 2"),
the BPF_LOG_BUF_SIZE was increased to 16M. The XDP socket part of
libbpf allocated the log_buf on the stack, but for the new 16M buffer
size this is not going to work. Change the code so it uses a 16K buffer
instead.

Fixes: da11b417583e ("libbpf: teach libbpf about log_level bit 2")
Signed-off-by: Magnus Karlsson <magnus.karlsson@intel.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/lib/bpf/xsk.c | 9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)

diff --git a/tools/lib/bpf/xsk.c b/tools/lib/bpf/xsk.c
index 8d0078b65486..557ef8d1250d 100644
--- a/tools/lib/bpf/xsk.c
+++ b/tools/lib/bpf/xsk.c
@@ -259,7 +259,8 @@ out_umem_alloc:
 
 static int xsk_load_xdp_prog(struct xsk_socket *xsk)
 {
-	char bpf_log_buf[BPF_LOG_BUF_SIZE];
+	static const int log_buf_size = 16 * 1024;
+	char log_buf[log_buf_size];
 	int err, prog_fd;
 
 	/* This is the C-program:
@@ -308,10 +309,10 @@ static int xsk_load_xdp_prog(struct xsk_socket *xsk)
 	size_t insns_cnt = sizeof(prog) / sizeof(struct bpf_insn);
 
 	prog_fd = bpf_load_program(BPF_PROG_TYPE_XDP, prog, insns_cnt,
-				   "LGPL-2.1 or BSD-2-Clause", 0, bpf_log_buf,
-				   BPF_LOG_BUF_SIZE);
+				   "LGPL-2.1 or BSD-2-Clause", 0, log_buf,
+				   log_buf_size);
 	if (prog_fd < 0) {
-		pr_warning("BPF log buffer:\n%s", bpf_log_buf);
+		pr_warning("BPF log buffer:\n%s", log_buf);
 		return prog_fd;
 	}
 
-- 
cgit v1.2.3-55-g7522


From fa0dcb3fe2ca3d51b8a9485e8a23fa70ecc8ba7e Mon Sep 17 00:00:00 2001
From: Daniel Borkmann
Date: Wed, 10 Apr 2019 11:07:14 +0200
Subject: mailmap: add entry for email addresses

Redirect email addresses from git log to the mainly used ones
for Alexei and myself such that it is consistent with the ones
in MAINTAINERS file. Useful in particular when git mailmap is
enabled on broader scope, for example:

  $ git config --global log.mailmap true

Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Alexei Starovoitov <ast@kernel.org>
---
 .mailmap | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/.mailmap b/.mailmap
index 37e1847c7988..e7984bb6b4b0 100644
--- a/.mailmap
+++ b/.mailmap
@@ -16,6 +16,9 @@ Alan Cox <alan@lxorguk.ukuu.org.uk>
 Alan Cox <root@hraefn.swansea.linux.org.uk>
 Aleksey Gorelov <aleksey_gorelov@phoenix.com>
 Aleksandar Markovic <aleksandar.markovic@mips.com> <aleksandar.markovic@imgtec.com>
+Alexei Starovoitov <ast@kernel.org> <ast@plumgrid.com>
+Alexei Starovoitov <ast@kernel.org> <alexei.starovoitov@gmail.com>
+Alexei Starovoitov <ast@kernel.org> <ast@fb.com>
 Al Viro <viro@ftp.linux.org.uk>
 Al Viro <viro@zenIV.linux.org.uk>
 Andi Shyti <andi@etezian.org> <andi.shyti@samsung.com>
@@ -46,6 +49,12 @@ Christoph Hellwig <hch@lst.de>
 Christophe Ricard <christophe.ricard@gmail.com>
 Corey Minyard <minyard@acm.org>
 Damian Hobson-Garcia <dhobsong@igel.co.jp>
+Daniel Borkmann <daniel@iogearbox.net> <dborkman@redhat.com>
+Daniel Borkmann <daniel@iogearbox.net> <dborkmann@redhat.com>
+Daniel Borkmann <daniel@iogearbox.net> <danborkmann@iogearbox.net>
+Daniel Borkmann <daniel@iogearbox.net> <daniel.borkmann@tik.ee.ethz.ch>
+Daniel Borkmann <daniel@iogearbox.net> <danborkmann@googlemail.com>
+Daniel Borkmann <daniel@iogearbox.net> <dxchgb@gmail.com>
 David Brownell <david-b@pacbell.net>
 David Woodhouse <dwmw2@shinybook.infradead.org>
 Dengcheng Zhu <dzhu@wavecomp.com> <dengcheng.zhu@mips.com>
-- 
cgit v1.2.3-55-g7522


From d5adbdd77ecc1d841af244a10958792141830d30 Mon Sep 17 00:00:00 2001
From: Andrey Ignatov
Date: Wed, 10 Apr 2019 18:36:43 -0700
Subject: libbpf: Fix build with gcc-8

Reported in [1].

With gcc 8.3.0 the following error is issued:

  cc -Ibpf@sta -I. -I.. -I.././include -I.././include/uapi
  -fdiagnostics-color=always -fsanitize=address,undefined -fno-omit-frame-pointer
  -pipe -D_FILE_OFFSET_BITS=64 -Wall -Winvalid-pch -Werror -g -fPIC -g -O2
  -Werror -Wall -Wno-pointer-arith -Wno-sign-compare  -MD -MQ
  'bpf@sta/src_libbpf.c.o' -MF 'bpf@sta/src_libbpf.c.o.d' -o
  'bpf@sta/src_libbpf.c.o' -c ../src/libbpf.c
  ../src/libbpf.c: In function 'bpf_object__elf_collect':
  ../src/libbpf.c:947:18: error: 'map_def_sz' may be used uninitialized in this
  function [-Werror=maybe-uninitialized]
     if (map_def_sz <= sizeof(struct bpf_map_def)) {
         ~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~
  ../src/libbpf.c:827:18: note: 'map_def_sz' was declared here
    int i, map_idx, map_def_sz, nr_syms, nr_maps = 0, nr_maps_glob = 0;
                    ^~~~~~~~~~

According to [2] -Wmaybe-uninitialized is enabled by -Wall.
Same error is generated by clang's -Wconditional-uninitialized.

[1] https://github.com/libbpf/libbpf/pull/29#issuecomment-481902601
[2] https://gcc.gnu.org/onlinedocs/gcc/Warning-Options.html

Fixes: d859900c4c56 ("bpf, libbpf: support global data/bss/rodata sections")
Reported-by: Evgeny Vereshchagin <evvers@ya.ru>
Signed-off-by: Andrey Ignatov <rdna@fb.com>
Acked-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/lib/bpf/libbpf.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index e2a457e7c318..67484cf32b2e 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -824,7 +824,7 @@ bpf_object__init_internal_map(struct bpf_object *obj, struct bpf_map *map,
 static int
 bpf_object__init_maps(struct bpf_object *obj, int flags)
 {
-	int i, map_idx, map_def_sz, nr_syms, nr_maps = 0, nr_maps_glob = 0;
+	int i, map_idx, map_def_sz = 0, nr_syms, nr_maps = 0, nr_maps_glob = 0;
 	bool strict = !(flags & MAPS_RELAX_COMPAT);
 	Elf_Data *symbols = obj->efile.symbols;
 	Elf_Data *data = NULL;
-- 
cgit v1.2.3-55-g7522


From 569b0c77735d1567963cb4601390877b30458be4 Mon Sep 17 00:00:00 2001
From: Prashant Bhole
Date: Wed, 10 Apr 2019 13:56:42 +0900
Subject: tools/bpftool: show btf id in program information

Let's add a way to know whether a program has btf context.
Patch adds 'btf_id' in the output of program listing.
When btf_id is present, it means program has btf context.

Sample output:
user@test# bpftool prog list
25: xdp  name xdp_prog1  tag 539ec6ce11b52f98  gpl
	loaded_at 2019-04-10T11:44:20+0900  uid 0
	xlated 488B  not jited  memlock 4096B  map_ids 23
	btf_id 1

Signed-off-by: Prashant Bhole <bhole_prashant_q7@lab.ntt.co.jp>
Acked-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/bpf/bpftool/prog.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/tools/bpf/bpftool/prog.c b/tools/bpf/bpftool/prog.c
index d2be5a06c339..81067803189e 100644
--- a/tools/bpf/bpftool/prog.c
+++ b/tools/bpf/bpftool/prog.c
@@ -249,6 +249,9 @@ static void print_prog_json(struct bpf_prog_info *info, int fd)
 	if (info->nr_map_ids)
 		show_prog_maps(fd, info->nr_map_ids);
 
+	if (info->btf_id)
+		jsonw_int_field(json_wtr, "btf_id", info->btf_id);
+
 	if (!hash_empty(prog_table.table)) {
 		struct pinned_obj *obj;
 
@@ -319,6 +322,9 @@ static void print_prog_plain(struct bpf_prog_info *info, int fd)
 		}
 	}
 
+	if (info->btf_id)
+		printf("\n\tbtf_id %d\n", info->btf_id);
+
 	printf("\n");
 }
 
-- 
cgit v1.2.3-55-g7522


From b0b9395d865e3060d97658fbc9ba3f77fecc8da1 Mon Sep 17 00:00:00 2001
From: Stanislav Fomichev
Date: Tue, 9 Apr 2019 11:49:09 -0700
Subject: bpf: support input __sk_buff context in BPF_PROG_TEST_RUN

Add new set of arguments to bpf_attr for BPF_PROG_TEST_RUN:
* ctx_in/ctx_size_in - input context
* ctx_out/ctx_size_out - output context

The intended use case is to pass some meta data to the test runs that
operate on skb (this has being brought up on recent LPC).

For programs that use bpf_prog_test_run_skb, support __sk_buff input and
output. Initially, from input __sk_buff, copy _only_ cb and priority into
skb, all other non-zero fields are prohibited (with EINVAL).
If the user has set ctx_out/ctx_size_out, copy the potentially modified
__sk_buff back to the userspace.

We require all fields of input __sk_buff except the ones we explicitly
support to be set to zero. The expectation is that in the future we might
add support for more fields and we want to fail explicitly if the user
runs the program on the kernel where we don't yet support them.

The API is intentionally vague (i.e. we don't explicitly add __sk_buff
to bpf_attr, but ctx_in) to potentially let other test_run types use
this interface in the future (this can be xdp_md for xdp types for
example).

v4:
  * don't copy more than allowed in bpf_ctx_init [Martin]

v3:
  * handle case where ctx_in is NULL, but ctx_out is not [Martin]
  * convert size==0 checks to ptr==NULL checks and add some extra ptr
    checks [Martin]

v2:
  * Addressed comments from Martin Lau

Signed-off-by: Stanislav Fomichev <sdf@google.com>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 include/uapi/linux/bpf.h |   7 +++
 kernel/bpf/syscall.c     |  10 +++-
 net/bpf/test_run.c       | 143 ++++++++++++++++++++++++++++++++++++++++++++---
 3 files changed, 151 insertions(+), 9 deletions(-)

diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index af1cbd951f26..31a27dd337dc 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -412,6 +412,13 @@ union bpf_attr {
 		__aligned_u64	data_out;
 		__u32		repeat;
 		__u32		duration;
+		__u32		ctx_size_in;	/* input: len of ctx_in */
+		__u32		ctx_size_out;	/* input/output: len of ctx_out
+						 *   returns ENOSPC if ctx_out
+						 *   is too small.
+						 */
+		__aligned_u64	ctx_in;
+		__aligned_u64	ctx_out;
 	} test;
 
 	struct { /* anonymous struct used by BPF_*_GET_*_ID */
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 438199e2eca4..d995eedfdd16 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -2009,7 +2009,7 @@ static int bpf_prog_query(const union bpf_attr *attr,
 	return cgroup_bpf_prog_query(attr, uattr);
 }
 
-#define BPF_PROG_TEST_RUN_LAST_FIELD test.duration
+#define BPF_PROG_TEST_RUN_LAST_FIELD test.ctx_out
 
 static int bpf_prog_test_run(const union bpf_attr *attr,
 			     union bpf_attr __user *uattr)
@@ -2022,6 +2022,14 @@ static int bpf_prog_test_run(const union bpf_attr *attr,
 	if (CHECK_ATTR(BPF_PROG_TEST_RUN))
 		return -EINVAL;
 
+	if ((attr->test.ctx_size_in && !attr->test.ctx_in) ||
+	    (!attr->test.ctx_size_in && attr->test.ctx_in))
+		return -EINVAL;
+
+	if ((attr->test.ctx_size_out && !attr->test.ctx_out) ||
+	    (!attr->test.ctx_size_out && attr->test.ctx_out))
+		return -EINVAL;
+
 	prog = bpf_prog_get(attr->test.prog_fd);
 	if (IS_ERR(prog))
 		return PTR_ERR(prog);
diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c
index fab142b796ef..cbd4fb65aa4f 100644
--- a/net/bpf/test_run.c
+++ b/net/bpf/test_run.c
@@ -123,12 +123,126 @@ static void *bpf_test_init(const union bpf_attr *kattr, u32 size,
 	return data;
 }
 
+static void *bpf_ctx_init(const union bpf_attr *kattr, u32 max_size)
+{
+	void __user *data_in = u64_to_user_ptr(kattr->test.ctx_in);
+	void __user *data_out = u64_to_user_ptr(kattr->test.ctx_out);
+	u32 size = kattr->test.ctx_size_in;
+	void *data;
+	int err;
+
+	if (!data_in && !data_out)
+		return NULL;
+
+	data = kzalloc(max_size, GFP_USER);
+	if (!data)
+		return ERR_PTR(-ENOMEM);
+
+	if (data_in) {
+		err = bpf_check_uarg_tail_zero(data_in, max_size, size);
+		if (err) {
+			kfree(data);
+			return ERR_PTR(err);
+		}
+
+		size = min_t(u32, max_size, size);
+		if (copy_from_user(data, data_in, size)) {
+			kfree(data);
+			return ERR_PTR(-EFAULT);
+		}
+	}
+	return data;
+}
+
+static int bpf_ctx_finish(const union bpf_attr *kattr,
+			  union bpf_attr __user *uattr, const void *data,
+			  u32 size)
+{
+	void __user *data_out = u64_to_user_ptr(kattr->test.ctx_out);
+	int err = -EFAULT;
+	u32 copy_size = size;
+
+	if (!data || !data_out)
+		return 0;
+
+	if (copy_size > kattr->test.ctx_size_out) {
+		copy_size = kattr->test.ctx_size_out;
+		err = -ENOSPC;
+	}
+
+	if (copy_to_user(data_out, data, copy_size))
+		goto out;
+	if (copy_to_user(&uattr->test.ctx_size_out, &size, sizeof(size)))
+		goto out;
+	if (err != -ENOSPC)
+		err = 0;
+out:
+	return err;
+}
+
+/**
+ * range_is_zero - test whether buffer is initialized
+ * @buf: buffer to check
+ * @from: check from this position
+ * @to: check up until (excluding) this position
+ *
+ * This function returns true if the there is a non-zero byte
+ * in the buf in the range [from,to).
+ */
+static inline bool range_is_zero(void *buf, size_t from, size_t to)
+{
+	return !memchr_inv((u8 *)buf + from, 0, to - from);
+}
+
+static int convert___skb_to_skb(struct sk_buff *skb, struct __sk_buff *__skb)
+{
+	struct qdisc_skb_cb *cb = (struct qdisc_skb_cb *)skb->cb;
+
+	if (!__skb)
+		return 0;
+
+	/* make sure the fields we don't use are zeroed */
+	if (!range_is_zero(__skb, 0, offsetof(struct __sk_buff, priority)))
+		return -EINVAL;
+
+	/* priority is allowed */
+
+	if (!range_is_zero(__skb, offsetof(struct __sk_buff, priority) +
+			   FIELD_SIZEOF(struct __sk_buff, priority),
+			   offsetof(struct __sk_buff, cb)))
+		return -EINVAL;
+
+	/* cb is allowed */
+
+	if (!range_is_zero(__skb, offsetof(struct __sk_buff, cb) +
+			   FIELD_SIZEOF(struct __sk_buff, cb),
+			   sizeof(struct __sk_buff)))
+		return -EINVAL;
+
+	skb->priority = __skb->priority;
+	memcpy(&cb->data, __skb->cb, QDISC_CB_PRIV_LEN);
+
+	return 0;
+}
+
+static void convert_skb_to___skb(struct sk_buff *skb, struct __sk_buff *__skb)
+{
+	struct qdisc_skb_cb *cb = (struct qdisc_skb_cb *)skb->cb;
+
+	if (!__skb)
+		return;
+
+	__skb->priority = skb->priority;
+	memcpy(__skb->cb, &cb->data, QDISC_CB_PRIV_LEN);
+}
+
 int bpf_prog_test_run_skb(struct bpf_prog *prog, const union bpf_attr *kattr,
 			  union bpf_attr __user *uattr)
 {
 	bool is_l2 = false, is_direct_pkt_access = false;
 	u32 size = kattr->test.data_size_in;
 	u32 repeat = kattr->test.repeat;
+	struct __sk_buff *ctx = NULL;
 	u32 retval, duration;
 	int hh_len = ETH_HLEN;
 	struct sk_buff *skb;
@@ -141,6 +255,12 @@ int bpf_prog_test_run_skb(struct bpf_prog *prog, const union bpf_attr *kattr,
 	if (IS_ERR(data))
 		return PTR_ERR(data);
 
+	ctx = bpf_ctx_init(kattr, sizeof(struct __sk_buff));
+	if (IS_ERR(ctx)) {
+		kfree(data);
+		return PTR_ERR(ctx);
+	}
+
 	switch (prog->type) {
 	case BPF_PROG_TYPE_SCHED_CLS:
 	case BPF_PROG_TYPE_SCHED_ACT:
@@ -158,6 +278,7 @@ int bpf_prog_test_run_skb(struct bpf_prog *prog, const union bpf_attr *kattr,
 	sk = kzalloc(sizeof(struct sock), GFP_USER);
 	if (!sk) {
 		kfree(data);
+		kfree(ctx);
 		return -ENOMEM;
 	}
 	sock_net_set(sk, current->nsproxy->net_ns);
@@ -166,6 +287,7 @@ int bpf_prog_test_run_skb(struct bpf_prog *prog, const union bpf_attr *kattr,
 	skb = build_skb(data, 0);
 	if (!skb) {
 		kfree(data);
+		kfree(ctx);
 		kfree(sk);
 		return -ENOMEM;
 	}
@@ -180,32 +302,37 @@ int bpf_prog_test_run_skb(struct bpf_prog *prog, const union bpf_attr *kattr,
 		__skb_push(skb, hh_len);
 	if (is_direct_pkt_access)
 		bpf_compute_data_pointers(skb);
+	ret = convert___skb_to_skb(skb, ctx);
+	if (ret)
+		goto out;
 	ret = bpf_test_run(prog, skb, repeat, &retval, &duration);
-	if (ret) {
-		kfree_skb(skb);
-		kfree(sk);
-		return ret;
-	}
+	if (ret)
+		goto out;
 	if (!is_l2) {
 		if (skb_headroom(skb) < hh_len) {
 			int nhead = HH_DATA_ALIGN(hh_len - skb_headroom(skb));
 
 			if (pskb_expand_head(skb, nhead, 0, GFP_USER)) {
-				kfree_skb(skb);
-				kfree(sk);
-				return -ENOMEM;
+				ret = -ENOMEM;
+				goto out;
 			}
 		}
 		memset(__skb_push(skb, hh_len), 0, hh_len);
 	}
+	convert_skb_to___skb(skb, ctx);
 
 	size = skb->len;
 	/* bpf program can never convert linear skb to non-linear */
 	if (WARN_ON_ONCE(skb_is_nonlinear(skb)))
 		size = skb_headlen(skb);
 	ret = bpf_test_finish(kattr, uattr, skb->data, size, retval, duration);
+	if (!ret)
+		ret = bpf_ctx_finish(kattr, uattr, ctx,
+				     sizeof(struct __sk_buff));
+out:
 	kfree_skb(skb);
 	kfree(sk);
+	kfree(ctx);
 	return ret;
 }
 
-- 
cgit v1.2.3-55-g7522


From 5e903c656b98614698a891c6e098186272cbba14 Mon Sep 17 00:00:00 2001
From: Stanislav Fomichev
Date: Tue, 9 Apr 2019 11:49:10 -0700
Subject: libbpf: add support for ctx_{size, }_{in, out} in BPF_PROG_TEST_RUN

Support recently introduced input/output context for test runs.
We extend only bpf_prog_test_run_xattr. bpf_prog_test_run is
unextendable and left as is.

Signed-off-by: Stanislav Fomichev <sdf@google.com>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/include/uapi/linux/bpf.h | 7 +++++++
 tools/lib/bpf/bpf.c            | 5 +++++
 tools/lib/bpf/bpf.h            | 5 +++++
 3 files changed, 17 insertions(+)

diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index af1cbd951f26..31a27dd337dc 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -412,6 +412,13 @@ union bpf_attr {
 		__aligned_u64	data_out;
 		__u32		repeat;
 		__u32		duration;
+		__u32		ctx_size_in;	/* input: len of ctx_in */
+		__u32		ctx_size_out;	/* input/output: len of ctx_out
+						 *   returns ENOSPC if ctx_out
+						 *   is too small.
+						 */
+		__aligned_u64	ctx_in;
+		__aligned_u64	ctx_out;
 	} test;
 
 	struct { /* anonymous struct used by BPF_*_GET_*_ID */
diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c
index dababce68f0b..955191c64b64 100644
--- a/tools/lib/bpf/bpf.c
+++ b/tools/lib/bpf/bpf.c
@@ -554,10 +554,15 @@ int bpf_prog_test_run_xattr(struct bpf_prog_test_run_attr *test_attr)
 	attr.test.data_out = ptr_to_u64(test_attr->data_out);
 	attr.test.data_size_in = test_attr->data_size_in;
 	attr.test.data_size_out = test_attr->data_size_out;
+	attr.test.ctx_in = ptr_to_u64(test_attr->ctx_in);
+	attr.test.ctx_out = ptr_to_u64(test_attr->ctx_out);
+	attr.test.ctx_size_in = test_attr->ctx_size_in;
+	attr.test.ctx_size_out = test_attr->ctx_size_out;
 	attr.test.repeat = test_attr->repeat;
 
 	ret = sys_bpf(BPF_PROG_TEST_RUN, &attr, sizeof(attr));
 	test_attr->data_size_out = attr.test.data_size_out;
+	test_attr->ctx_size_out = attr.test.ctx_size_out;
 	test_attr->retval = attr.test.retval;
 	test_attr->duration = attr.test.duration;
 	return ret;
diff --git a/tools/lib/bpf/bpf.h b/tools/lib/bpf/bpf.h
index c9d218d21453..bc30783d1403 100644
--- a/tools/lib/bpf/bpf.h
+++ b/tools/lib/bpf/bpf.h
@@ -136,6 +136,11 @@ struct bpf_prog_test_run_attr {
 			      * out: length of data_out */
 	__u32 retval;        /* out: return code of the BPF program */
 	__u32 duration;      /* out: average per repetition in ns */
+	const void *ctx_in; /* optional */
+	__u32 ctx_size_in;
+	void *ctx_out;      /* optional */
+	__u32 ctx_size_out; /* in: max length of ctx_out
+			     * out: length of cxt_out */
 };
 
 LIBBPF_API int bpf_prog_test_run_xattr(struct bpf_prog_test_run_attr *test_attr);
-- 
cgit v1.2.3-55-g7522


From 3daf8e703ec3dcf73a27a7dcabbac152793eb114 Mon Sep 17 00:00:00 2001
From: Stanislav Fomichev
Date: Tue, 9 Apr 2019 11:49:11 -0700
Subject: selftests: bpf: add selftest for __sk_buff context in
 BPF_PROG_TEST_RUN

Simple test that sets cb to {1,2,3,4,5} and priority to 6, runs bpf
program that fails if cb is not what we expect and increments cb[i] and
priority. When the test finishes, we check that cb is now {2,3,4,5,6}
and priority is 7.

We also test the sanity checks:
* ctx_in is provided, but ctx_size_in is zero (same for
  ctx_out/ctx_size_out)
* unexpected non-zero fields in __sk_buff return EINVAL

Signed-off-by: Stanislav Fomichev <sdf@google.com>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/testing/selftests/bpf/prog_tests/skb_ctx.c | 89 ++++++++++++++++++++++++
 tools/testing/selftests/bpf/progs/test_skb_ctx.c | 21 ++++++
 2 files changed, 110 insertions(+)
 create mode 100644 tools/testing/selftests/bpf/prog_tests/skb_ctx.c
 create mode 100644 tools/testing/selftests/bpf/progs/test_skb_ctx.c

diff --git a/tools/testing/selftests/bpf/prog_tests/skb_ctx.c b/tools/testing/selftests/bpf/prog_tests/skb_ctx.c
new file mode 100644
index 000000000000..e95baa32e277
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/skb_ctx.c
@@ -0,0 +1,89 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <test_progs.h>
+
+void test_skb_ctx(void)
+{
+	struct __sk_buff skb = {
+		.cb[0] = 1,
+		.cb[1] = 2,
+		.cb[2] = 3,
+		.cb[3] = 4,
+		.cb[4] = 5,
+		.priority = 6,
+	};
+	struct bpf_prog_test_run_attr tattr = {
+		.data_in = &pkt_v4,
+		.data_size_in = sizeof(pkt_v4),
+		.ctx_in = &skb,
+		.ctx_size_in = sizeof(skb),
+		.ctx_out = &skb,
+		.ctx_size_out = sizeof(skb),
+	};
+	struct bpf_object *obj;
+	int err;
+	int i;
+
+	err = bpf_prog_load("./test_skb_ctx.o", BPF_PROG_TYPE_SCHED_CLS, &obj,
+			    &tattr.prog_fd);
+	if (CHECK_ATTR(err, "load", "err %d errno %d\n", err, errno))
+		return;
+
+	/* ctx_in != NULL, ctx_size_in == 0 */
+
+	tattr.ctx_size_in = 0;
+	err = bpf_prog_test_run_xattr(&tattr);
+	CHECK_ATTR(err == 0, "ctx_size_in", "err %d errno %d\n", err, errno);
+	tattr.ctx_size_in = sizeof(skb);
+
+	/* ctx_out != NULL, ctx_size_out == 0 */
+
+	tattr.ctx_size_out = 0;
+	err = bpf_prog_test_run_xattr(&tattr);
+	CHECK_ATTR(err == 0, "ctx_size_out", "err %d errno %d\n", err, errno);
+	tattr.ctx_size_out = sizeof(skb);
+
+	/* non-zero [len, tc_index] fields should be rejected*/
+
+	skb.len = 1;
+	err = bpf_prog_test_run_xattr(&tattr);
+	CHECK_ATTR(err == 0, "len", "err %d errno %d\n", err, errno);
+	skb.len = 0;
+
+	skb.tc_index = 1;
+	err = bpf_prog_test_run_xattr(&tattr);
+	CHECK_ATTR(err == 0, "tc_index", "err %d errno %d\n", err, errno);
+	skb.tc_index = 0;
+
+	/* non-zero [hash, sk] fields should be rejected */
+
+	skb.hash = 1;
+	err = bpf_prog_test_run_xattr(&tattr);
+	CHECK_ATTR(err == 0, "hash", "err %d errno %d\n", err, errno);
+	skb.hash = 0;
+
+	skb.sk = (struct bpf_sock *)1;
+	err = bpf_prog_test_run_xattr(&tattr);
+	CHECK_ATTR(err == 0, "sk", "err %d errno %d\n", err, errno);
+	skb.sk = 0;
+
+	err = bpf_prog_test_run_xattr(&tattr);
+	CHECK_ATTR(err != 0 || tattr.retval,
+		   "run",
+		   "err %d errno %d retval %d\n",
+		   err, errno, tattr.retval);
+
+	CHECK_ATTR(tattr.ctx_size_out != sizeof(skb),
+		   "ctx_size_out",
+		   "incorrect output size, want %lu have %u\n",
+		   sizeof(skb), tattr.ctx_size_out);
+
+	for (i = 0; i < 5; i++)
+		CHECK_ATTR(skb.cb[i] != i + 2,
+			   "ctx_out_cb",
+			   "skb->cb[i] == %d, expected %d\n",
+			   skb.cb[i], i + 2);
+	CHECK_ATTR(skb.priority != 7,
+		   "ctx_out_priority",
+		   "skb->priority == %d, expected %d\n",
+		   skb.priority, 7);
+}
diff --git a/tools/testing/selftests/bpf/progs/test_skb_ctx.c b/tools/testing/selftests/bpf/progs/test_skb_ctx.c
new file mode 100644
index 000000000000..7a80960d7df1
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/test_skb_ctx.c
@@ -0,0 +1,21 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/bpf.h>
+#include "bpf_helpers.h"
+
+int _version SEC("version") = 1;
+char _license[] SEC("license") = "GPL";
+
+SEC("skb_ctx")
+int process(struct __sk_buff *skb)
+{
+	#pragma clang loop unroll(full)
+	for (int i = 0; i < 5; i++) {
+		if (skb->cb[i] != i + 1)
+			return 1;
+		skb->cb[i]++;
+	}
+	skb->priority++;
+
+	return 0;
+}
-- 
cgit v1.2.3-55-g7522


From c695865c5c9803f14eef2c99d8a49d9ad60a3383 Mon Sep 17 00:00:00 2001
From: Stanislav Fomichev
Date: Thu, 11 Apr 2019 09:12:02 -0700
Subject: bpf: fix missing bpf_check_uarg_tail_zero in BPF_PROG_TEST_RUN

Commit b0b9395d865e ("bpf: support input __sk_buff context in
BPF_PROG_TEST_RUN") started using bpf_check_uarg_tail_zero in
BPF_PROG_TEST_RUN. However, bpf_check_uarg_tail_zero is not defined
for !CONFIG_BPF_SYSCALL:

net/bpf/test_run.c: In function ‘bpf_ctx_init’:
net/bpf/test_run.c:142:9: error: implicit declaration of function ‘bpf_check_uarg_tail_zero’ [-Werror=implicit-function-declaration]
   err = bpf_check_uarg_tail_zero(data_in, max_size, size);
         ^~~~~~~~~~~~~~~~~~~~~~~~

Let's not build net/bpf/test_run.c when CONFIG_BPF_SYSCALL is not set.

Reported-by: kbuild test robot <lkp@intel.com>
Fixes: b0b9395d865e ("bpf: support input __sk_buff context in BPF_PROG_TEST_RUN")
Signed-off-by: Stanislav Fomichev <sdf@google.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 include/linux/bpf.h | 36 ++++++++++++++++++++++++++++--------
 net/bpf/Makefile    |  2 +-
 2 files changed, 29 insertions(+), 9 deletions(-)

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 65f7094c40b4..e4d4c1771ab0 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -483,14 +483,6 @@ typedef u32 (*bpf_convert_ctx_access_t)(enum bpf_access_type type,
 u64 bpf_event_output(struct bpf_map *map, u64 flags, void *meta, u64 meta_size,
 		     void *ctx, u64 ctx_size, bpf_ctx_copy_t ctx_copy);
 
-int bpf_prog_test_run_xdp(struct bpf_prog *prog, const union bpf_attr *kattr,
-			  union bpf_attr __user *uattr);
-int bpf_prog_test_run_skb(struct bpf_prog *prog, const union bpf_attr *kattr,
-			  union bpf_attr __user *uattr);
-int bpf_prog_test_run_flow_dissector(struct bpf_prog *prog,
-				     const union bpf_attr *kattr,
-				     union bpf_attr __user *uattr);
-
 /* an array of programs to be executed under rcu_lock.
  *
  * Typical usage:
@@ -681,6 +673,13 @@ static inline int bpf_map_attr_numa_node(const union bpf_attr *attr)
 struct bpf_prog *bpf_prog_get_type_path(const char *name, enum bpf_prog_type type);
 int array_map_alloc_check(union bpf_attr *attr);
 
+int bpf_prog_test_run_xdp(struct bpf_prog *prog, const union bpf_attr *kattr,
+			  union bpf_attr __user *uattr);
+int bpf_prog_test_run_skb(struct bpf_prog *prog, const union bpf_attr *kattr,
+			  union bpf_attr __user *uattr);
+int bpf_prog_test_run_flow_dissector(struct bpf_prog *prog,
+				     const union bpf_attr *kattr,
+				     union bpf_attr __user *uattr);
 #else /* !CONFIG_BPF_SYSCALL */
 static inline struct bpf_prog *bpf_prog_get(u32 ufd)
 {
@@ -792,6 +791,27 @@ static inline struct bpf_prog *bpf_prog_get_type_path(const char *name,
 {
 	return ERR_PTR(-EOPNOTSUPP);
 }
+
+static inline int bpf_prog_test_run_xdp(struct bpf_prog *prog,
+					const union bpf_attr *kattr,
+					union bpf_attr __user *uattr)
+{
+	return -ENOTSUPP;
+}
+
+static inline int bpf_prog_test_run_skb(struct bpf_prog *prog,
+					const union bpf_attr *kattr,
+					union bpf_attr __user *uattr)
+{
+	return -ENOTSUPP;
+}
+
+static inline int bpf_prog_test_run_flow_dissector(struct bpf_prog *prog,
+						   const union bpf_attr *kattr,
+						   union bpf_attr __user *uattr)
+{
+	return -ENOTSUPP;
+}
 #endif /* CONFIG_BPF_SYSCALL */
 
 static inline struct bpf_prog *bpf_prog_get_type(u32 ufd,
diff --git a/net/bpf/Makefile b/net/bpf/Makefile
index 27b2992a0692..b0ca361742e4 100644
--- a/net/bpf/Makefile
+++ b/net/bpf/Makefile
@@ -1 +1 @@
-obj-y	:= test_run.o
+obj-$(CONFIG_BPF_SYSCALL)	:= test_run.o
-- 
cgit v1.2.3-55-g7522


From 166b5a7f2ca3803ab0a7bb33ac2300e616de2470 Mon Sep 17 00:00:00 2001
From: Alan Maguire
Date: Tue, 9 Apr 2019 15:06:40 +0100
Subject: selftests_bpf: extend test_tc_tunnel for UDP encap

commit 868d523535c2 ("bpf: add bpf_skb_adjust_room encap flags")
introduced support to bpf_skb_adjust_room for GSO-friendly GRE
and UDP encapsulation and later introduced associated test_tc_tunnel
tests.  Here those tests are extended to cover UDP encapsulation also.

Signed-off-by: Alan Maguire <alan.maguire@oracle.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/testing/selftests/bpf/config                 |   4 +
 tools/testing/selftests/bpf/progs/test_tc_tunnel.c | 140 ++++++++++++++-------
 tools/testing/selftests/bpf/test_tc_tunnel.sh      |  47 ++++++-
 3 files changed, 143 insertions(+), 48 deletions(-)

diff --git a/tools/testing/selftests/bpf/config b/tools/testing/selftests/bpf/config
index a42f4fc4dc11..8e749c1f5bf6 100644
--- a/tools/testing/selftests/bpf/config
+++ b/tools/testing/selftests/bpf/config
@@ -25,3 +25,7 @@ CONFIG_XDP_SOCKETS=y
 CONFIG_FTRACE_SYSCALLS=y
 CONFIG_IPV6_TUNNEL=y
 CONFIG_IPV6_GRE=y
+CONFIG_NET_FOU=m
+CONFIG_NET_FOU_IP_TUNNELS=y
+CONFIG_IPV6_FOU=m
+CONFIG_IPV6_FOU_TUNNEL=m
diff --git a/tools/testing/selftests/bpf/progs/test_tc_tunnel.c b/tools/testing/selftests/bpf/progs/test_tc_tunnel.c
index f541c2de947d..33b338e6cf09 100644
--- a/tools/testing/selftests/bpf/progs/test_tc_tunnel.c
+++ b/tools/testing/selftests/bpf/progs/test_tc_tunnel.c
@@ -12,6 +12,7 @@
 #include <linux/ip.h>
 #include <linux/ipv6.h>
 #include <linux/tcp.h>
+#include <linux/udp.h>
 #include <linux/pkt_cls.h>
 #include <linux/types.h>
 
@@ -20,16 +21,27 @@
 
 static const int cfg_port = 8000;
 
-struct grev4hdr {
-	struct iphdr ip;
+static const int cfg_udp_src = 20000;
+static const int cfg_udp_dst = 5555;
+
+struct gre_hdr {
 	__be16 flags;
 	__be16 protocol;
 } __attribute__((packed));
 
-struct grev6hdr {
+union l4hdr {
+	struct udphdr udp;
+	struct gre_hdr gre;
+};
+
+struct v4hdr {
+	struct iphdr ip;
+	union l4hdr l4hdr;
+} __attribute__((packed));
+
+struct v6hdr {
 	struct ipv6hdr ip;
-	__be16 flags;
-	__be16 protocol;
+	union l4hdr l4hdr;
 } __attribute__((packed));
 
 static __always_inline void set_ipv4_csum(struct iphdr *iph)
@@ -47,10 +59,10 @@ static __always_inline void set_ipv4_csum(struct iphdr *iph)
 	iph->check = ~((csum & 0xffff) + (csum >> 16));
 }
 
-static __always_inline int encap_ipv4(struct __sk_buff *skb, bool with_gre)
+static __always_inline int encap_ipv4(struct __sk_buff *skb, __u8 encap_proto)
 {
-	struct grev4hdr h_outer;
 	struct iphdr iph_inner;
+	struct v4hdr h_outer;
 	struct tcphdr tcph;
 	__u64 flags;
 	int olen;
@@ -70,12 +82,29 @@ static __always_inline int encap_ipv4(struct __sk_buff *skb, bool with_gre)
 	if (tcph.dest != __bpf_constant_htons(cfg_port))
 		return TC_ACT_OK;
 
+	olen = sizeof(h_outer.ip);
+
 	flags = BPF_F_ADJ_ROOM_FIXED_GSO | BPF_F_ADJ_ROOM_ENCAP_L3_IPV4;
-	if (with_gre) {
+	switch (encap_proto) {
+	case IPPROTO_GRE:
 		flags |= BPF_F_ADJ_ROOM_ENCAP_L4_GRE;
-		olen = sizeof(h_outer);
-	} else {
-		olen = sizeof(h_outer.ip);
+		olen += sizeof(h_outer.l4hdr.gre);
+		h_outer.l4hdr.gre.protocol = bpf_htons(ETH_P_IP);
+		h_outer.l4hdr.gre.flags = 0;
+		break;
+	case IPPROTO_UDP:
+		flags |= BPF_F_ADJ_ROOM_ENCAP_L4_UDP;
+		olen += sizeof(h_outer.l4hdr.udp);
+		h_outer.l4hdr.udp.source = __bpf_constant_htons(cfg_udp_src);
+		h_outer.l4hdr.udp.dest = __bpf_constant_htons(cfg_udp_dst);
+		h_outer.l4hdr.udp.check = 0;
+		h_outer.l4hdr.udp.len = bpf_htons(bpf_ntohs(iph_inner.tot_len) +
+						  sizeof(h_outer.l4hdr.udp));
+		break;
+	case IPPROTO_IPIP:
+		break;
+	default:
+		return TC_ACT_OK;
 	}
 
 	/* add room between mac and network header */
@@ -85,16 +114,10 @@ static __always_inline int encap_ipv4(struct __sk_buff *skb, bool with_gre)
 	/* prepare new outer network header */
 	h_outer.ip = iph_inner;
 	h_outer.ip.tot_len = bpf_htons(olen +
-				      bpf_htons(h_outer.ip.tot_len));
-	if (with_gre) {
-		h_outer.ip.protocol = IPPROTO_GRE;
-		h_outer.protocol = bpf_htons(ETH_P_IP);
-		h_outer.flags = 0;
-	} else {
-		h_outer.ip.protocol = IPPROTO_IPIP;
-	}
+				       bpf_ntohs(h_outer.ip.tot_len));
+	h_outer.ip.protocol = encap_proto;
 
-	set_ipv4_csum((void *)&h_outer.ip);
+	set_ipv4_csum(&h_outer.ip);
 
 	/* store new outer network header */
 	if (bpf_skb_store_bytes(skb, ETH_HLEN, &h_outer, olen,
@@ -104,11 +127,12 @@ static __always_inline int encap_ipv4(struct __sk_buff *skb, bool with_gre)
 	return TC_ACT_OK;
 }
 
-static __always_inline int encap_ipv6(struct __sk_buff *skb, bool with_gre)
+static __always_inline int encap_ipv6(struct __sk_buff *skb, __u8 encap_proto)
 {
 	struct ipv6hdr iph_inner;
-	struct grev6hdr h_outer;
+	struct v6hdr h_outer;
 	struct tcphdr tcph;
+	__u16 tot_len;
 	__u64 flags;
 	int olen;
 
@@ -124,15 +148,32 @@ static __always_inline int encap_ipv6(struct __sk_buff *skb, bool with_gre)
 	if (tcph.dest != __bpf_constant_htons(cfg_port))
 		return TC_ACT_OK;
 
+	olen = sizeof(h_outer.ip);
+
 	flags = BPF_F_ADJ_ROOM_FIXED_GSO | BPF_F_ADJ_ROOM_ENCAP_L3_IPV6;
-	if (with_gre) {
+	switch (encap_proto) {
+	case IPPROTO_GRE:
 		flags |= BPF_F_ADJ_ROOM_ENCAP_L4_GRE;
-		olen = sizeof(h_outer);
-	} else {
-		olen = sizeof(h_outer.ip);
+		olen += sizeof(h_outer.l4hdr.gre);
+		h_outer.l4hdr.gre.protocol = bpf_htons(ETH_P_IPV6);
+		h_outer.l4hdr.gre.flags = 0;
+		break;
+	case IPPROTO_UDP:
+		flags |= BPF_F_ADJ_ROOM_ENCAP_L4_UDP;
+		olen += sizeof(h_outer.l4hdr.udp);
+		h_outer.l4hdr.udp.source = __bpf_constant_htons(cfg_udp_src);
+		h_outer.l4hdr.udp.dest = __bpf_constant_htons(cfg_udp_dst);
+		tot_len = bpf_ntohs(iph_inner.payload_len) + sizeof(iph_inner) +
+			  sizeof(h_outer.l4hdr.udp);
+		h_outer.l4hdr.udp.check = 0;
+		h_outer.l4hdr.udp.len = bpf_htons(tot_len);
+		break;
+	case IPPROTO_IPV6:
+		break;
+	default:
+		return TC_ACT_OK;
 	}
 
-
 	/* add room between mac and network header */
 	if (bpf_skb_adjust_room(skb, olen, BPF_ADJ_ROOM_MAC, flags))
 		return TC_ACT_SHOT;
@@ -141,13 +182,8 @@ static __always_inline int encap_ipv6(struct __sk_buff *skb, bool with_gre)
 	h_outer.ip = iph_inner;
 	h_outer.ip.payload_len = bpf_htons(olen +
 					   bpf_ntohs(h_outer.ip.payload_len));
-	if (with_gre) {
-		h_outer.ip.nexthdr = IPPROTO_GRE;
-		h_outer.protocol = bpf_htons(ETH_P_IPV6);
-		h_outer.flags = 0;
-	} else {
-		h_outer.ip.nexthdr = IPPROTO_IPV6;
-	}
+
+	h_outer.ip.nexthdr = encap_proto;
 
 	/* store new outer network header */
 	if (bpf_skb_store_bytes(skb, ETH_HLEN, &h_outer, olen,
@@ -161,7 +197,7 @@ SEC("encap_ipip")
 int __encap_ipip(struct __sk_buff *skb)
 {
 	if (skb->protocol == __bpf_constant_htons(ETH_P_IP))
-		return encap_ipv4(skb, false);
+		return encap_ipv4(skb, IPPROTO_IPIP);
 	else
 		return TC_ACT_OK;
 }
@@ -170,7 +206,16 @@ SEC("encap_gre")
 int __encap_gre(struct __sk_buff *skb)
 {
 	if (skb->protocol == __bpf_constant_htons(ETH_P_IP))
-		return encap_ipv4(skb, true);
+		return encap_ipv4(skb, IPPROTO_GRE);
+	else
+		return TC_ACT_OK;
+}
+
+SEC("encap_udp")
+int __encap_udp(struct __sk_buff *skb)
+{
+	if (skb->protocol == __bpf_constant_htons(ETH_P_IP))
+		return encap_ipv4(skb, IPPROTO_UDP);
 	else
 		return TC_ACT_OK;
 }
@@ -179,7 +224,7 @@ SEC("encap_ip6tnl")
 int __encap_ip6tnl(struct __sk_buff *skb)
 {
 	if (skb->protocol == __bpf_constant_htons(ETH_P_IPV6))
-		return encap_ipv6(skb, false);
+		return encap_ipv6(skb, IPPROTO_IPV6);
 	else
 		return TC_ACT_OK;
 }
@@ -188,23 +233,34 @@ SEC("encap_ip6gre")
 int __encap_ip6gre(struct __sk_buff *skb)
 {
 	if (skb->protocol == __bpf_constant_htons(ETH_P_IPV6))
-		return encap_ipv6(skb, true);
+		return encap_ipv6(skb, IPPROTO_GRE);
+	else
+		return TC_ACT_OK;
+}
+
+SEC("encap_ip6udp")
+int __encap_ip6udp(struct __sk_buff *skb)
+{
+	if (skb->protocol == __bpf_constant_htons(ETH_P_IPV6))
+		return encap_ipv6(skb, IPPROTO_UDP);
 	else
 		return TC_ACT_OK;
 }
 
 static int decap_internal(struct __sk_buff *skb, int off, int len, char proto)
 {
-	char buf[sizeof(struct grev6hdr)];
-	int olen;
+	char buf[sizeof(struct v6hdr)];
+	int olen = len;
 
 	switch (proto) {
 	case IPPROTO_IPIP:
 	case IPPROTO_IPV6:
-		olen = len;
 		break;
 	case IPPROTO_GRE:
-		olen = len + 4 /* gre hdr */;
+		olen += sizeof(struct gre_hdr);
+		break;
+	case IPPROTO_UDP:
+		olen += sizeof(struct udphdr);
 		break;
 	default:
 		return TC_ACT_OK;
diff --git a/tools/testing/selftests/bpf/test_tc_tunnel.sh b/tools/testing/selftests/bpf/test_tc_tunnel.sh
index c805adb88f3a..64f30910d39a 100755
--- a/tools/testing/selftests/bpf/test_tc_tunnel.sh
+++ b/tools/testing/selftests/bpf/test_tc_tunnel.sh
@@ -15,6 +15,9 @@ readonly ns2_v4=192.168.1.2
 readonly ns1_v6=fd::1
 readonly ns2_v6=fd::2
 
+# Must match port used by bpf program
+readonly udpport=5555
+
 readonly infile="$(mktemp)"
 readonly outfile="$(mktemp)"
 
@@ -38,8 +41,8 @@ setup() {
 	# clamp route to reserve room for tunnel headers
 	ip -netns "${ns1}" -4 route flush table main
 	ip -netns "${ns1}" -6 route flush table main
-	ip -netns "${ns1}" -4 route add "${ns2_v4}" mtu 1476 dev veth1
-	ip -netns "${ns1}" -6 route add "${ns2_v6}" mtu 1456 dev veth1
+	ip -netns "${ns1}" -4 route add "${ns2_v4}" mtu 1472 dev veth1
+	ip -netns "${ns1}" -6 route add "${ns2_v6}" mtu 1452 dev veth1
 
 	sleep 1
 
@@ -103,6 +106,18 @@ if [[ "$#" -eq "0" ]]; then
 	echo "ip6 gre gso"
 	$0 ipv6 ip6gre 2000
 
+	echo "ip udp"
+	$0 ipv4 udp 100
+
+	echo "ip6 udp"
+	$0 ipv6 ip6udp 100
+
+	echo "ip udp gso"
+	$0 ipv4 udp 2000
+
+	echo "ip6 udp gso"
+	$0 ipv6 ip6udp 2000
+
 	echo "OK. All tests passed"
 	exit 0
 fi
@@ -117,12 +132,20 @@ case "$1" in
 "ipv4")
 	readonly addr1="${ns1_v4}"
 	readonly addr2="${ns2_v4}"
-	readonly netcat_opt=-4
+	readonly ipproto=4
+	readonly netcat_opt=-${ipproto}
+	readonly foumod=fou
+	readonly foutype=ipip
+	readonly fouproto=4
 	;;
 "ipv6")
 	readonly addr1="${ns1_v6}"
 	readonly addr2="${ns2_v6}"
-	readonly netcat_opt=-6
+	readonly ipproto=6
+	readonly netcat_opt=-${ipproto}
+	readonly foumod=fou6
+	readonly foutype=ip6tnl
+	readonly fouproto="41 -6"
 	;;
 *)
 	echo "unknown arg: $1"
@@ -155,11 +178,23 @@ echo "test bpf encap without decap (expect failure)"
 server_listen
 ! client_connect
 
+if [[ "$tuntype" =~ "udp" ]]; then
+	# Set up fou tunnel.
+	ttype="${foutype}"
+	targs="encap fou encap-sport auto encap-dport $udpport"
+	# fou may be a module; allow this to fail.
+	modprobe "${foumod}" ||true
+	ip netns exec "${ns2}" ip fou add port 5555 ipproto ${fouproto}
+else
+	ttype=$tuntype
+	targs=""
+fi
+
 # serverside, insert decap module
 # server is still running
 # client can connect again
-ip netns exec "${ns2}" ip link add dev testtun0 type "${tuntype}" \
-	remote "${addr1}" local "${addr2}"
+ip netns exec "${ns2}" ip link add name testtun0 type "${ttype}" \
+	remote "${addr1}" local "${addr2}" $targs
 # Because packets are decapped by the tunnel they arrive on testtun0 from
 # the IP stack perspective.  Ensure reverse path filtering is disabled
 # otherwise we drop the TCP SYN as arriving on testtun0 instead of the
-- 
cgit v1.2.3-55-g7522


From 58dfc900faff6db7eb9bf01555622e0b6c74c262 Mon Sep 17 00:00:00 2001
From: Alan Maguire
Date: Tue, 9 Apr 2019 15:06:41 +0100
Subject: bpf: add layer 2 encap support to bpf_skb_adjust_room

commit 868d523535c2 ("bpf: add bpf_skb_adjust_room encap flags")
introduced support to bpf_skb_adjust_room for GSO-friendly GRE
and UDP encapsulation.

For GSO to work for skbs, the inner headers (mac and network) need to
be marked.  For L3 encapsulation using bpf_skb_adjust_room, the mac
and network headers are identical.  Here we provide a way of specifying
the inner mac header length for cases where L2 encap is desired.  Such
an approach can support encapsulated ethernet headers, MPLS headers etc.
For example to convert from a packet of form [eth][ip][tcp] to
[eth][ip][udp][inner mac][ip][tcp], something like the following could
be done:

	headroom = sizeof(iph) + sizeof(struct udphdr) + inner_maclen;

	ret = bpf_skb_adjust_room(skb, headroom, BPF_ADJ_ROOM_MAC,
				  BPF_F_ADJ_ROOM_ENCAP_L4_UDP |
				  BPF_F_ADJ_ROOM_ENCAP_L3_IPV4 |
				  BPF_F_ADJ_ROOM_ENCAP_L2(inner_maclen));

Signed-off-by: Alan Maguire <alan.maguire@oracle.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 include/uapi/linux/bpf.h | 10 ++++++++++
 net/core/filter.c        | 12 ++++++++----
 2 files changed, 18 insertions(+), 4 deletions(-)

diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 31a27dd337dc..2e96d0b4bf65 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -1523,6 +1523,10 @@ union bpf_attr {
  *		* **BPF_F_ADJ_ROOM_ENCAP_L4_UDP **:
  *		  Use with ENCAP_L3 flags to further specify the tunnel type.
  *
+ *		* **BPF_F_ADJ_ROOM_ENCAP_L2(len) **:
+ *		  Use with ENCAP_L3/L4 flags to further specify the tunnel
+ *		  type; **len** is the length of the inner MAC header.
+ *
  * 		A call to this helper is susceptible to change the underlaying
  * 		packet buffer. Therefore, at load time, all checks on pointers
  * 		previously done by the verifier are invalidated and must be
@@ -2664,10 +2668,16 @@ enum bpf_func_id {
 /* BPF_FUNC_skb_adjust_room flags. */
 #define BPF_F_ADJ_ROOM_FIXED_GSO	(1ULL << 0)
 
+#define	BPF_ADJ_ROOM_ENCAP_L2_MASK	0xff
+#define	BPF_ADJ_ROOM_ENCAP_L2_SHIFT	56
+
 #define BPF_F_ADJ_ROOM_ENCAP_L3_IPV4	(1ULL << 1)
 #define BPF_F_ADJ_ROOM_ENCAP_L3_IPV6	(1ULL << 2)
 #define BPF_F_ADJ_ROOM_ENCAP_L4_GRE	(1ULL << 3)
 #define BPF_F_ADJ_ROOM_ENCAP_L4_UDP	(1ULL << 4)
+#define	BPF_F_ADJ_ROOM_ENCAP_L2(len)	(((__u64)len & \
+					  BPF_ADJ_ROOM_ENCAP_L2_MASK) \
+					 << BPF_ADJ_ROOM_ENCAP_L2_SHIFT)
 
 /* Mode for BPF_FUNC_skb_adjust_room helper. */
 enum bpf_adj_room_mode {
diff --git a/net/core/filter.c b/net/core/filter.c
index 22eb2edf5573..a1654ef62533 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -2969,11 +2969,14 @@ static u32 bpf_skb_net_base_len(const struct sk_buff *skb)
 #define BPF_F_ADJ_ROOM_MASK		(BPF_F_ADJ_ROOM_FIXED_GSO | \
 					 BPF_F_ADJ_ROOM_ENCAP_L3_MASK | \
 					 BPF_F_ADJ_ROOM_ENCAP_L4_GRE | \
-					 BPF_F_ADJ_ROOM_ENCAP_L4_UDP)
+					 BPF_F_ADJ_ROOM_ENCAP_L4_UDP | \
+					 BPF_F_ADJ_ROOM_ENCAP_L2( \
+					  BPF_ADJ_ROOM_ENCAP_L2_MASK))
 
 static int bpf_skb_net_grow(struct sk_buff *skb, u32 off, u32 len_diff,
 			    u64 flags)
 {
+	u8 inner_mac_len = flags >> BPF_ADJ_ROOM_ENCAP_L2_SHIFT;
 	bool encap = flags & BPF_F_ADJ_ROOM_ENCAP_L3_MASK;
 	u16 mac_len = 0, inner_net = 0, inner_trans = 0;
 	unsigned int gso_type = SKB_GSO_DODGY;
@@ -3008,6 +3011,8 @@ static int bpf_skb_net_grow(struct sk_buff *skb, u32 off, u32 len_diff,
 
 		mac_len = skb->network_header - skb->mac_header;
 		inner_net = skb->network_header;
+		if (inner_mac_len > len_diff)
+			return -EINVAL;
 		inner_trans = skb->transport_header;
 	}
 
@@ -3016,8 +3021,7 @@ static int bpf_skb_net_grow(struct sk_buff *skb, u32 off, u32 len_diff,
 		return ret;
 
 	if (encap) {
-		/* inner mac == inner_net on l3 encap */
-		skb->inner_mac_header = inner_net;
+		skb->inner_mac_header = inner_net - inner_mac_len;
 		skb->inner_network_header = inner_net;
 		skb->inner_transport_header = inner_trans;
 		skb_set_inner_protocol(skb, skb->protocol);
@@ -3031,7 +3035,7 @@ static int bpf_skb_net_grow(struct sk_buff *skb, u32 off, u32 len_diff,
 			gso_type |= SKB_GSO_GRE;
 		else if (flags & BPF_F_ADJ_ROOM_ENCAP_L3_IPV6)
 			gso_type |= SKB_GSO_IPXIP6;
-		else
+		else if (flags & BPF_F_ADJ_ROOM_ENCAP_L3_IPV4)
 			gso_type |= SKB_GSO_IPXIP4;
 
 		if (flags & BPF_F_ADJ_ROOM_ENCAP_L4_GRE ||
-- 
cgit v1.2.3-55-g7522


From 1db04c300a41e17892bf83ed0d1aa681416ee150 Mon Sep 17 00:00:00 2001
From: Alan Maguire
Date: Tue, 9 Apr 2019 15:06:42 +0100
Subject: bpf: sync bpf.h to tools/ for BPF_F_ADJ_ROOM_ENCAP_L2

Sync include/uapi/linux/bpf.h with tools/ equivalent to add
BPF_F_ADJ_ROOM_ENCAP_L2(len) macro.

Signed-off-by: Alan Maguire <alan.maguire@oracle.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/include/uapi/linux/bpf.h | 10 ++++++++++
 1 file changed, 10 insertions(+)

diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 31a27dd337dc..2e96d0b4bf65 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -1523,6 +1523,10 @@ union bpf_attr {
  *		* **BPF_F_ADJ_ROOM_ENCAP_L4_UDP **:
  *		  Use with ENCAP_L3 flags to further specify the tunnel type.
  *
+ *		* **BPF_F_ADJ_ROOM_ENCAP_L2(len) **:
+ *		  Use with ENCAP_L3/L4 flags to further specify the tunnel
+ *		  type; **len** is the length of the inner MAC header.
+ *
  * 		A call to this helper is susceptible to change the underlaying
  * 		packet buffer. Therefore, at load time, all checks on pointers
  * 		previously done by the verifier are invalidated and must be
@@ -2664,10 +2668,16 @@ enum bpf_func_id {
 /* BPF_FUNC_skb_adjust_room flags. */
 #define BPF_F_ADJ_ROOM_FIXED_GSO	(1ULL << 0)
 
+#define	BPF_ADJ_ROOM_ENCAP_L2_MASK	0xff
+#define	BPF_ADJ_ROOM_ENCAP_L2_SHIFT	56
+
 #define BPF_F_ADJ_ROOM_ENCAP_L3_IPV4	(1ULL << 1)
 #define BPF_F_ADJ_ROOM_ENCAP_L3_IPV6	(1ULL << 2)
 #define BPF_F_ADJ_ROOM_ENCAP_L4_GRE	(1ULL << 3)
 #define BPF_F_ADJ_ROOM_ENCAP_L4_UDP	(1ULL << 4)
+#define	BPF_F_ADJ_ROOM_ENCAP_L2(len)	(((__u64)len & \
+					  BPF_ADJ_ROOM_ENCAP_L2_MASK) \
+					 << BPF_ADJ_ROOM_ENCAP_L2_SHIFT)
 
 /* Mode for BPF_FUNC_skb_adjust_room helper. */
 enum bpf_adj_room_mode {
-- 
cgit v1.2.3-55-g7522


From 3ec61df82ba0c2d2455da838ee46bf60f2256b56 Mon Sep 17 00:00:00 2001
From: Alan Maguire
Date: Tue, 9 Apr 2019 15:06:43 +0100
Subject: selftests_bpf: add L2 encap to test_tc_tunnel

Update test_tc_tunnel to verify adding inner L2 header
encapsulation (an MPLS label or ethernet header) works.

Signed-off-by: Alan Maguire <alan.maguire@oracle.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/testing/selftests/bpf/config                 |   4 +
 tools/testing/selftests/bpf/progs/test_tc_tunnel.c | 219 ++++++++++++++++++---
 tools/testing/selftests/bpf/test_tc_tunnel.sh      | 113 ++++++++---
 3 files changed, 277 insertions(+), 59 deletions(-)

diff --git a/tools/testing/selftests/bpf/config b/tools/testing/selftests/bpf/config
index 8e749c1f5bf6..8c976476f6fd 100644
--- a/tools/testing/selftests/bpf/config
+++ b/tools/testing/selftests/bpf/config
@@ -29,3 +29,7 @@ CONFIG_NET_FOU=m
 CONFIG_NET_FOU_IP_TUNNELS=y
 CONFIG_IPV6_FOU=m
 CONFIG_IPV6_FOU_TUNNEL=m
+CONFIG_MPLS=y
+CONFIG_NET_MPLS_GSO=m
+CONFIG_MPLS_ROUTING=m
+CONFIG_MPLS_IPTUNNEL=m
diff --git a/tools/testing/selftests/bpf/progs/test_tc_tunnel.c b/tools/testing/selftests/bpf/progs/test_tc_tunnel.c
index 33b338e6cf09..bcb00d737e95 100644
--- a/tools/testing/selftests/bpf/progs/test_tc_tunnel.c
+++ b/tools/testing/selftests/bpf/progs/test_tc_tunnel.c
@@ -11,6 +11,7 @@
 #include <linux/in.h>
 #include <linux/ip.h>
 #include <linux/ipv6.h>
+#include <linux/mpls.h>
 #include <linux/tcp.h>
 #include <linux/udp.h>
 #include <linux/pkt_cls.h>
@@ -22,7 +23,14 @@
 static const int cfg_port = 8000;
 
 static const int cfg_udp_src = 20000;
-static const int cfg_udp_dst = 5555;
+
+#define	UDP_PORT		5555
+#define	MPLS_OVER_UDP_PORT	6635
+#define	ETH_OVER_UDP_PORT	7777
+
+/* MPLS label 1000 with S bit (last label) set and ttl of 255. */
+static const __u32 mpls_label = __bpf_constant_htonl(1000 << 12 |
+						     MPLS_LS_S_MASK | 0xff);
 
 struct gre_hdr {
 	__be16 flags;
@@ -37,11 +45,13 @@ union l4hdr {
 struct v4hdr {
 	struct iphdr ip;
 	union l4hdr l4hdr;
+	__u8 pad[16];			/* enough space for L2 header */
 } __attribute__((packed));
 
 struct v6hdr {
 	struct ipv6hdr ip;
 	union l4hdr l4hdr;
+	__u8 pad[16];			/* enough space for L2 header */
 } __attribute__((packed));
 
 static __always_inline void set_ipv4_csum(struct iphdr *iph)
@@ -59,13 +69,15 @@ static __always_inline void set_ipv4_csum(struct iphdr *iph)
 	iph->check = ~((csum & 0xffff) + (csum >> 16));
 }
 
-static __always_inline int encap_ipv4(struct __sk_buff *skb, __u8 encap_proto)
+static __always_inline int encap_ipv4(struct __sk_buff *skb, __u8 encap_proto,
+				      __u16 l2_proto)
 {
+	__u16 udp_dst = UDP_PORT;
 	struct iphdr iph_inner;
 	struct v4hdr h_outer;
 	struct tcphdr tcph;
+	int olen, l2_len;
 	__u64 flags;
-	int olen;
 
 	if (bpf_skb_load_bytes(skb, ETH_HLEN, &iph_inner,
 			       sizeof(iph_inner)) < 0)
@@ -83,23 +95,38 @@ static __always_inline int encap_ipv4(struct __sk_buff *skb, __u8 encap_proto)
 		return TC_ACT_OK;
 
 	olen = sizeof(h_outer.ip);
+	l2_len = 0;
 
 	flags = BPF_F_ADJ_ROOM_FIXED_GSO | BPF_F_ADJ_ROOM_ENCAP_L3_IPV4;
+
+	switch (l2_proto) {
+	case ETH_P_MPLS_UC:
+		l2_len = sizeof(mpls_label);
+		udp_dst = MPLS_OVER_UDP_PORT;
+		break;
+	case ETH_P_TEB:
+		l2_len = ETH_HLEN;
+		udp_dst = ETH_OVER_UDP_PORT;
+		break;
+	}
+	flags |= BPF_F_ADJ_ROOM_ENCAP_L2(l2_len);
+
 	switch (encap_proto) {
 	case IPPROTO_GRE:
 		flags |= BPF_F_ADJ_ROOM_ENCAP_L4_GRE;
 		olen += sizeof(h_outer.l4hdr.gre);
-		h_outer.l4hdr.gre.protocol = bpf_htons(ETH_P_IP);
+		h_outer.l4hdr.gre.protocol = bpf_htons(l2_proto);
 		h_outer.l4hdr.gre.flags = 0;
 		break;
 	case IPPROTO_UDP:
 		flags |= BPF_F_ADJ_ROOM_ENCAP_L4_UDP;
 		olen += sizeof(h_outer.l4hdr.udp);
 		h_outer.l4hdr.udp.source = __bpf_constant_htons(cfg_udp_src);
-		h_outer.l4hdr.udp.dest = __bpf_constant_htons(cfg_udp_dst);
+		h_outer.l4hdr.udp.dest = bpf_htons(udp_dst);
 		h_outer.l4hdr.udp.check = 0;
 		h_outer.l4hdr.udp.len = bpf_htons(bpf_ntohs(iph_inner.tot_len) +
-						  sizeof(h_outer.l4hdr.udp));
+						  sizeof(h_outer.l4hdr.udp) +
+						  l2_len);
 		break;
 	case IPPROTO_IPIP:
 		break;
@@ -107,6 +134,19 @@ static __always_inline int encap_ipv4(struct __sk_buff *skb, __u8 encap_proto)
 		return TC_ACT_OK;
 	}
 
+	/* add L2 encap (if specified) */
+	switch (l2_proto) {
+	case ETH_P_MPLS_UC:
+		*((__u32 *)((__u8 *)&h_outer + olen)) = mpls_label;
+		break;
+	case ETH_P_TEB:
+		if (bpf_skb_load_bytes(skb, 0, (__u8 *)&h_outer + olen,
+				       ETH_HLEN))
+			return TC_ACT_SHOT;
+		break;
+	}
+	olen += l2_len;
+
 	/* add room between mac and network header */
 	if (bpf_skb_adjust_room(skb, olen, BPF_ADJ_ROOM_MAC, flags))
 		return TC_ACT_SHOT;
@@ -127,14 +167,16 @@ static __always_inline int encap_ipv4(struct __sk_buff *skb, __u8 encap_proto)
 	return TC_ACT_OK;
 }
 
-static __always_inline int encap_ipv6(struct __sk_buff *skb, __u8 encap_proto)
+static __always_inline int encap_ipv6(struct __sk_buff *skb, __u8 encap_proto,
+				      __u16 l2_proto)
 {
+	__u16 udp_dst = UDP_PORT;
 	struct ipv6hdr iph_inner;
 	struct v6hdr h_outer;
 	struct tcphdr tcph;
+	int olen, l2_len;
 	__u16 tot_len;
 	__u64 flags;
-	int olen;
 
 	if (bpf_skb_load_bytes(skb, ETH_HLEN, &iph_inner,
 			       sizeof(iph_inner)) < 0)
@@ -149,20 +191,34 @@ static __always_inline int encap_ipv6(struct __sk_buff *skb, __u8 encap_proto)
 		return TC_ACT_OK;
 
 	olen = sizeof(h_outer.ip);
+	l2_len = 0;
 
 	flags = BPF_F_ADJ_ROOM_FIXED_GSO | BPF_F_ADJ_ROOM_ENCAP_L3_IPV6;
+
+	switch (l2_proto) {
+	case ETH_P_MPLS_UC:
+		l2_len = sizeof(mpls_label);
+		udp_dst = MPLS_OVER_UDP_PORT;
+		break;
+	case ETH_P_TEB:
+		l2_len = ETH_HLEN;
+		udp_dst = ETH_OVER_UDP_PORT;
+		break;
+	}
+	flags |= BPF_F_ADJ_ROOM_ENCAP_L2(l2_len);
+
 	switch (encap_proto) {
 	case IPPROTO_GRE:
 		flags |= BPF_F_ADJ_ROOM_ENCAP_L4_GRE;
 		olen += sizeof(h_outer.l4hdr.gre);
-		h_outer.l4hdr.gre.protocol = bpf_htons(ETH_P_IPV6);
+		h_outer.l4hdr.gre.protocol = bpf_htons(l2_proto);
 		h_outer.l4hdr.gre.flags = 0;
 		break;
 	case IPPROTO_UDP:
 		flags |= BPF_F_ADJ_ROOM_ENCAP_L4_UDP;
 		olen += sizeof(h_outer.l4hdr.udp);
 		h_outer.l4hdr.udp.source = __bpf_constant_htons(cfg_udp_src);
-		h_outer.l4hdr.udp.dest = __bpf_constant_htons(cfg_udp_dst);
+		h_outer.l4hdr.udp.dest = bpf_htons(udp_dst);
 		tot_len = bpf_ntohs(iph_inner.payload_len) + sizeof(iph_inner) +
 			  sizeof(h_outer.l4hdr.udp);
 		h_outer.l4hdr.udp.check = 0;
@@ -174,6 +230,19 @@ static __always_inline int encap_ipv6(struct __sk_buff *skb, __u8 encap_proto)
 		return TC_ACT_OK;
 	}
 
+	/* add L2 encap (if specified) */
+	switch (l2_proto) {
+	case ETH_P_MPLS_UC:
+		*((__u32 *)((__u8 *)&h_outer + olen)) = mpls_label;
+		break;
+	case ETH_P_TEB:
+		if (bpf_skb_load_bytes(skb, 0, (__u8 *)&h_outer + olen,
+				       ETH_HLEN))
+			return TC_ACT_SHOT;
+		break;
+	}
+	olen += l2_len;
+
 	/* add room between mac and network header */
 	if (bpf_skb_adjust_room(skb, olen, BPF_ADJ_ROOM_MAC, flags))
 		return TC_ACT_SHOT;
@@ -193,56 +262,128 @@ static __always_inline int encap_ipv6(struct __sk_buff *skb, __u8 encap_proto)
 	return TC_ACT_OK;
 }
 
-SEC("encap_ipip")
-int __encap_ipip(struct __sk_buff *skb)
+SEC("encap_ipip_none")
+int __encap_ipip_none(struct __sk_buff *skb)
+{
+	if (skb->protocol == __bpf_constant_htons(ETH_P_IP))
+		return encap_ipv4(skb, IPPROTO_IPIP, ETH_P_IP);
+	else
+		return TC_ACT_OK;
+}
+
+SEC("encap_gre_none")
+int __encap_gre_none(struct __sk_buff *skb)
+{
+	if (skb->protocol == __bpf_constant_htons(ETH_P_IP))
+		return encap_ipv4(skb, IPPROTO_GRE, ETH_P_IP);
+	else
+		return TC_ACT_OK;
+}
+
+SEC("encap_gre_mpls")
+int __encap_gre_mpls(struct __sk_buff *skb)
+{
+	if (skb->protocol == __bpf_constant_htons(ETH_P_IP))
+		return encap_ipv4(skb, IPPROTO_GRE, ETH_P_MPLS_UC);
+	else
+		return TC_ACT_OK;
+}
+
+SEC("encap_gre_eth")
+int __encap_gre_eth(struct __sk_buff *skb)
 {
 	if (skb->protocol == __bpf_constant_htons(ETH_P_IP))
-		return encap_ipv4(skb, IPPROTO_IPIP);
+		return encap_ipv4(skb, IPPROTO_GRE, ETH_P_TEB);
 	else
 		return TC_ACT_OK;
 }
 
-SEC("encap_gre")
-int __encap_gre(struct __sk_buff *skb)
+SEC("encap_udp_none")
+int __encap_udp_none(struct __sk_buff *skb)
 {
 	if (skb->protocol == __bpf_constant_htons(ETH_P_IP))
-		return encap_ipv4(skb, IPPROTO_GRE);
+		return encap_ipv4(skb, IPPROTO_UDP, ETH_P_IP);
 	else
 		return TC_ACT_OK;
 }
 
-SEC("encap_udp")
-int __encap_udp(struct __sk_buff *skb)
+SEC("encap_udp_mpls")
+int __encap_udp_mpls(struct __sk_buff *skb)
 {
 	if (skb->protocol == __bpf_constant_htons(ETH_P_IP))
-		return encap_ipv4(skb, IPPROTO_UDP);
+		return encap_ipv4(skb, IPPROTO_UDP, ETH_P_MPLS_UC);
+	else
+		return TC_ACT_OK;
+}
+
+SEC("encap_udp_eth")
+int __encap_udp_eth(struct __sk_buff *skb)
+{
+	if (skb->protocol == __bpf_constant_htons(ETH_P_IP))
+		return encap_ipv4(skb, IPPROTO_UDP, ETH_P_TEB);
+	else
+		return TC_ACT_OK;
+}
+
+SEC("encap_ip6tnl_none")
+int __encap_ip6tnl_none(struct __sk_buff *skb)
+{
+	if (skb->protocol == __bpf_constant_htons(ETH_P_IPV6))
+		return encap_ipv6(skb, IPPROTO_IPV6, ETH_P_IPV6);
+	else
+		return TC_ACT_OK;
+}
+
+SEC("encap_ip6gre_none")
+int __encap_ip6gre_none(struct __sk_buff *skb)
+{
+	if (skb->protocol == __bpf_constant_htons(ETH_P_IPV6))
+		return encap_ipv6(skb, IPPROTO_GRE, ETH_P_IPV6);
+	else
+		return TC_ACT_OK;
+}
+
+SEC("encap_ip6gre_mpls")
+int __encap_ip6gre_mpls(struct __sk_buff *skb)
+{
+	if (skb->protocol == __bpf_constant_htons(ETH_P_IPV6))
+		return encap_ipv6(skb, IPPROTO_GRE, ETH_P_MPLS_UC);
+	else
+		return TC_ACT_OK;
+}
+
+SEC("encap_ip6gre_eth")
+int __encap_ip6gre_eth(struct __sk_buff *skb)
+{
+	if (skb->protocol == __bpf_constant_htons(ETH_P_IPV6))
+		return encap_ipv6(skb, IPPROTO_GRE, ETH_P_TEB);
 	else
 		return TC_ACT_OK;
 }
 
-SEC("encap_ip6tnl")
-int __encap_ip6tnl(struct __sk_buff *skb)
+SEC("encap_ip6udp_none")
+int __encap_ip6udp_none(struct __sk_buff *skb)
 {
 	if (skb->protocol == __bpf_constant_htons(ETH_P_IPV6))
-		return encap_ipv6(skb, IPPROTO_IPV6);
+		return encap_ipv6(skb, IPPROTO_UDP, ETH_P_IPV6);
 	else
 		return TC_ACT_OK;
 }
 
-SEC("encap_ip6gre")
-int __encap_ip6gre(struct __sk_buff *skb)
+SEC("encap_ip6udp_mpls")
+int __encap_ip6udp_mpls(struct __sk_buff *skb)
 {
 	if (skb->protocol == __bpf_constant_htons(ETH_P_IPV6))
-		return encap_ipv6(skb, IPPROTO_GRE);
+		return encap_ipv6(skb, IPPROTO_UDP, ETH_P_MPLS_UC);
 	else
 		return TC_ACT_OK;
 }
 
-SEC("encap_ip6udp")
-int __encap_ip6udp(struct __sk_buff *skb)
+SEC("encap_ip6udp_eth")
+int __encap_ip6udp_eth(struct __sk_buff *skb)
 {
 	if (skb->protocol == __bpf_constant_htons(ETH_P_IPV6))
-		return encap_ipv6(skb, IPPROTO_UDP);
+		return encap_ipv6(skb, IPPROTO_UDP, ETH_P_TEB);
 	else
 		return TC_ACT_OK;
 }
@@ -250,6 +391,8 @@ int __encap_ip6udp(struct __sk_buff *skb)
 static int decap_internal(struct __sk_buff *skb, int off, int len, char proto)
 {
 	char buf[sizeof(struct v6hdr)];
+	struct gre_hdr greh;
+	struct udphdr udph;
 	int olen = len;
 
 	switch (proto) {
@@ -258,9 +401,29 @@ static int decap_internal(struct __sk_buff *skb, int off, int len, char proto)
 		break;
 	case IPPROTO_GRE:
 		olen += sizeof(struct gre_hdr);
+		if (bpf_skb_load_bytes(skb, off + len, &greh, sizeof(greh)) < 0)
+			return TC_ACT_OK;
+		switch (bpf_ntohs(greh.protocol)) {
+		case ETH_P_MPLS_UC:
+			olen += sizeof(mpls_label);
+			break;
+		case ETH_P_TEB:
+			olen += ETH_HLEN;
+			break;
+		}
 		break;
 	case IPPROTO_UDP:
 		olen += sizeof(struct udphdr);
+		if (bpf_skb_load_bytes(skb, off + len, &udph, sizeof(udph)) < 0)
+			return TC_ACT_OK;
+		switch (bpf_ntohs(udph.dest)) {
+		case MPLS_OVER_UDP_PORT:
+			olen += sizeof(mpls_label);
+			break;
+		case ETH_OVER_UDP_PORT:
+			olen += ETH_HLEN;
+			break;
+		}
 		break;
 	default:
 		return TC_ACT_OK;
diff --git a/tools/testing/selftests/bpf/test_tc_tunnel.sh b/tools/testing/selftests/bpf/test_tc_tunnel.sh
index 64f30910d39a..d4d8d5d3b06e 100755
--- a/tools/testing/selftests/bpf/test_tc_tunnel.sh
+++ b/tools/testing/selftests/bpf/test_tc_tunnel.sh
@@ -17,6 +17,9 @@ readonly ns2_v6=fd::2
 
 # Must match port used by bpf program
 readonly udpport=5555
+# MPLSoverUDP
+readonly mplsudpport=6635
+readonly mplsproto=137
 
 readonly infile="$(mktemp)"
 readonly outfile="$(mktemp)"
@@ -41,8 +44,8 @@ setup() {
 	# clamp route to reserve room for tunnel headers
 	ip -netns "${ns1}" -4 route flush table main
 	ip -netns "${ns1}" -6 route flush table main
-	ip -netns "${ns1}" -4 route add "${ns2_v4}" mtu 1472 dev veth1
-	ip -netns "${ns1}" -6 route add "${ns2_v6}" mtu 1452 dev veth1
+	ip -netns "${ns1}" -4 route add "${ns2_v4}" mtu 1458 dev veth1
+	ip -netns "${ns1}" -6 route add "${ns2_v6}" mtu 1438 dev veth1
 
 	sleep 1
 
@@ -89,42 +92,44 @@ set -e
 # no arguments: automated test, run all
 if [[ "$#" -eq "0" ]]; then
 	echo "ipip"
-	$0 ipv4 ipip 100
+	$0 ipv4 ipip none 100
 
 	echo "ip6ip6"
-	$0 ipv6 ip6tnl 100
+	$0 ipv6 ip6tnl none 100
 
-	echo "ip gre"
-	$0 ipv4 gre 100
+	for mac in none mpls eth ; do
+		echo "ip gre $mac"
+		$0 ipv4 gre $mac 100
 
-	echo "ip6 gre"
-	$0 ipv6 ip6gre 100
+		echo "ip6 gre $mac"
+		$0 ipv6 ip6gre $mac 100
 
-	echo "ip gre gso"
-	$0 ipv4 gre 2000
+		echo "ip gre $mac gso"
+		$0 ipv4 gre $mac 2000
 
-	echo "ip6 gre gso"
-	$0 ipv6 ip6gre 2000
+		echo "ip6 gre $mac gso"
+		$0 ipv6 ip6gre $mac 2000
 
-	echo "ip udp"
-	$0 ipv4 udp 100
+		echo "ip udp $mac"
+		$0 ipv4 udp $mac 100
 
-	echo "ip6 udp"
-	$0 ipv6 ip6udp 100
+		echo "ip6 udp $mac"
+		$0 ipv6 ip6udp $mac 100
 
-	echo "ip udp gso"
-	$0 ipv4 udp 2000
+		echo "ip udp $mac gso"
+		$0 ipv4 udp $mac 2000
 
-	echo "ip6 udp gso"
-	$0 ipv6 ip6udp 2000
+		echo "ip6 udp $mac gso"
+		$0 ipv6 ip6udp $mac 2000
+	done
 
 	echo "OK. All tests passed"
 	exit 0
 fi
 
-if [[ "$#" -ne "3" ]]; then
+if [[ "$#" -ne "4" ]]; then
 	echo "Usage: $0"
-	echo "   or: $0 <ipv4|ipv6> <tuntype> <data_len>"
+	echo "   or: $0 <ipv4|ipv6> <tuntype> <none|mpls|eth> <data_len>"
 	exit 1
 fi
 
@@ -137,6 +142,8 @@ case "$1" in
 	readonly foumod=fou
 	readonly foutype=ipip
 	readonly fouproto=4
+	readonly fouproto_mpls=${mplsproto}
+	readonly gretaptype=gretap
 	;;
 "ipv6")
 	readonly addr1="${ns1_v6}"
@@ -146,6 +153,8 @@ case "$1" in
 	readonly foumod=fou6
 	readonly foutype=ip6tnl
 	readonly fouproto="41 -6"
+	readonly fouproto_mpls="${mplsproto} -6"
+	readonly gretaptype=ip6gretap
 	;;
 *)
 	echo "unknown arg: $1"
@@ -154,9 +163,10 @@ case "$1" in
 esac
 
 readonly tuntype=$2
-readonly datalen=$3
+readonly mac=$3
+readonly datalen=$4
 
-echo "encap ${addr1} to ${addr2}, type ${tuntype}, len ${datalen}"
+echo "encap ${addr1} to ${addr2}, type ${tuntype}, mac ${mac} len ${datalen}"
 
 trap cleanup EXIT
 
@@ -173,7 +183,7 @@ verify_data
 ip netns exec "${ns1}" tc qdisc add dev veth1 clsact
 ip netns exec "${ns1}" tc filter add dev veth1 egress \
 	bpf direct-action object-file ./test_tc_tunnel.o \
-	section "encap_${tuntype}"
+	section "encap_${tuntype}_${mac}"
 echo "test bpf encap without decap (expect failure)"
 server_listen
 ! client_connect
@@ -184,7 +194,18 @@ if [[ "$tuntype" =~ "udp" ]]; then
 	targs="encap fou encap-sport auto encap-dport $udpport"
 	# fou may be a module; allow this to fail.
 	modprobe "${foumod}" ||true
-	ip netns exec "${ns2}" ip fou add port 5555 ipproto ${fouproto}
+	if [[ "$mac" == "mpls" ]]; then
+		dport=${mplsudpport}
+		dproto=${fouproto_mpls}
+		tmode="mode any ttl 255"
+	else
+		dport=${udpport}
+		dproto=${fouproto}
+	fi
+	ip netns exec "${ns2}" ip fou add port $dport ipproto ${dproto}
+	targs="encap fou encap-sport auto encap-dport $dport"
+elif [[ "$tuntype" =~ "gre" && "$mac" == "eth" ]]; then
+	ttype=$gretaptype
 else
 	ttype=$tuntype
 	targs=""
@@ -194,7 +215,31 @@ fi
 # server is still running
 # client can connect again
 ip netns exec "${ns2}" ip link add name testtun0 type "${ttype}" \
-	remote "${addr1}" local "${addr2}" $targs
+	${tmode} remote "${addr1}" local "${addr2}" $targs
+
+expect_tun_fail=0
+
+if [[ "$tuntype" == "ip6udp" && "$mac" == "mpls" ]]; then
+	# No support for MPLS IPv6 fou tunnel; expect failure.
+	expect_tun_fail=1
+elif [[ "$tuntype" =~ "udp" && "$mac" == "eth" ]]; then
+	# No support for TEB fou tunnel; expect failure.
+	expect_tun_fail=1
+elif [[ "$tuntype" =~ "gre" && "$mac" == "eth" ]]; then
+	# Share ethernet address between tunnel/veth2 so L2 decap works.
+	ethaddr=$(ip netns exec "${ns2}" ip link show veth2 | \
+		  awk '/ether/ { print $2 }')
+	ip netns exec "${ns2}" ip link set testtun0 address $ethaddr
+elif [[ "$mac" == "mpls" ]]; then
+	modprobe mpls_iptunnel ||true
+	modprobe mpls_gso ||true
+	ip netns exec "${ns2}" sysctl -qw net.mpls.platform_labels=65536
+	ip netns exec "${ns2}" ip -f mpls route add 1000 dev lo
+	ip netns exec "${ns2}" ip link set lo up
+	ip netns exec "${ns2}" sysctl -qw net.mpls.conf.testtun0.input=1
+	ip netns exec "${ns2}" sysctl -qw net.ipv4.conf.lo.rp_filter=0
+fi
+
 # Because packets are decapped by the tunnel they arrive on testtun0 from
 # the IP stack perspective.  Ensure reverse path filtering is disabled
 # otherwise we drop the TCP SYN as arriving on testtun0 instead of the
@@ -204,16 +249,22 @@ ip netns exec "${ns2}" sysctl -qw net.ipv4.conf.all.rp_filter=0
 # selected as the max of the "all" and device-specific values.
 ip netns exec "${ns2}" sysctl -qw net.ipv4.conf.testtun0.rp_filter=0
 ip netns exec "${ns2}" ip link set dev testtun0 up
-echo "test bpf encap with tunnel device decap"
-client_connect
-verify_data
+if [[ "$expect_tun_fail" == 1 ]]; then
+	# This tunnel mode is not supported, so we expect failure.
+	echo "test bpf encap with tunnel device decap (expect failure)"
+	! client_connect
+else
+	echo "test bpf encap with tunnel device decap"
+	client_connect
+	verify_data
+	server_listen
+fi
 
 # serverside, use BPF for decap
 ip netns exec "${ns2}" ip link del dev testtun0
 ip netns exec "${ns2}" tc qdisc add dev veth2 clsact
 ip netns exec "${ns2}" tc filter add dev veth2 ingress \
 	bpf direct-action object-file ./test_tc_tunnel.o section decap
-server_listen
 echo "test bpf encap with bpf decap"
 client_connect
 verify_data
-- 
cgit v1.2.3-55-g7522


From 6b7a21140fca461c6d8d5c65a3746e7da50a409e Mon Sep 17 00:00:00 2001
From: Daniel Borkmann
Date: Tue, 9 Apr 2019 11:44:46 +0200
Subject: tools: add smp_* barrier variants to include infrastructure

Add the definition for smp_rmb(), smp_wmb(), and smp_mb() to the
tools include infrastructure: this patch adds the implementation
for x86-64 and arm64, and have it fall back as currently is for
other archs which do not have it implemented at this point. The
x86-64 one uses lock + add combination for smp_mb() with address
below red zone.

This is on top of 09d62154f613 ("tools, perf: add and use optimized
ring_buffer_{read_head, write_tail} helpers"), which didn't touch
smp_* barrier implementations. Magnus recently rightfully reported
however that the latter on x86-64 still wrongly falls back to sfence,
lfence and mfence respectively, thus fix that for applications under
tools making use of these to avoid such ugly surprises. The main
header under tools (include/asm/barrier.h) will in that case not
select the fallback implementation.

Reported-by: Magnus Karlsson <magnus.karlsson@intel.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/arch/arm64/include/asm/barrier.h | 10 ++++++++++
 tools/arch/x86/include/asm/barrier.h   |  7 +++++--
 2 files changed, 15 insertions(+), 2 deletions(-)

diff --git a/tools/arch/arm64/include/asm/barrier.h b/tools/arch/arm64/include/asm/barrier.h
index 378c051fa177..3b9b41331c4f 100644
--- a/tools/arch/arm64/include/asm/barrier.h
+++ b/tools/arch/arm64/include/asm/barrier.h
@@ -14,6 +14,16 @@
 #define wmb()		asm volatile("dmb ishst" ::: "memory")
 #define rmb()		asm volatile("dmb ishld" ::: "memory")
 
+/*
+ * Kernel uses dmb variants on arm64 for smp_*() barriers. Pretty much the same
+ * implementation as above mb()/wmb()/rmb(), though for the latter kernel uses
+ * dsb. In any case, should above mb()/wmb()/rmb() change, make sure the below
+ * smp_*() don't.
+ */
+#define smp_mb()	asm volatile("dmb ish" ::: "memory")
+#define smp_wmb()	asm volatile("dmb ishst" ::: "memory")
+#define smp_rmb()	asm volatile("dmb ishld" ::: "memory")
+
 #define smp_store_release(p, v)						\
 do {									\
 	union { typeof(*p) __val; char __c[1]; } __u =			\
diff --git a/tools/arch/x86/include/asm/barrier.h b/tools/arch/x86/include/asm/barrier.h
index 58919868473c..0adf295dd5b6 100644
--- a/tools/arch/x86/include/asm/barrier.h
+++ b/tools/arch/x86/include/asm/barrier.h
@@ -21,9 +21,12 @@
 #define rmb()	asm volatile("lock; addl $0,0(%%esp)" ::: "memory")
 #define wmb()	asm volatile("lock; addl $0,0(%%esp)" ::: "memory")
 #elif defined(__x86_64__)
-#define mb() 	asm volatile("mfence":::"memory")
-#define rmb()	asm volatile("lfence":::"memory")
+#define mb()	asm volatile("mfence" ::: "memory")
+#define rmb()	asm volatile("lfence" ::: "memory")
 #define wmb()	asm volatile("sfence" ::: "memory")
+#define smp_rmb() barrier()
+#define smp_wmb() barrier()
+#define smp_mb()  asm volatile("lock; addl $0,-132(%%rsp)" ::: "memory", "cc")
 #endif
 
 #if defined(__x86_64__)
-- 
cgit v1.2.3-55-g7522


From 947e8b595b82d3551750641445d0a97b8f29b536 Mon Sep 17 00:00:00 2001
From: Stanislav Fomichev
Date: Thu, 11 Apr 2019 15:47:07 -0700
Subject: bpf: explicitly prohibit ctx_{in, out} in non-skb BPF_PROG_TEST_RUN

This should allow us later to extend BPF_PROG_TEST_RUN for non-skb case
and be sure that nobody is erroneously setting ctx_{in,out}.

Fixes: b0b9395d865e ("bpf: support input __sk_buff context in BPF_PROG_TEST_RUN")
Reported-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Stanislav Fomichev <sdf@google.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 net/bpf/test_run.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c
index cbd4fb65aa4f..2221573dacdb 100644
--- a/net/bpf/test_run.c
+++ b/net/bpf/test_run.c
@@ -347,6 +347,9 @@ int bpf_prog_test_run_xdp(struct bpf_prog *prog, const union bpf_attr *kattr,
 	void *data;
 	int ret;
 
+	if (kattr->test.ctx_in || kattr->test.ctx_out)
+		return -EINVAL;
+
 	data = bpf_test_init(kattr, size, XDP_PACKET_HEADROOM + NET_IP_ALIGN, 0);
 	if (IS_ERR(data))
 		return PTR_ERR(data);
@@ -390,6 +393,9 @@ int bpf_prog_test_run_flow_dissector(struct bpf_prog *prog,
 	if (prog->type != BPF_PROG_TYPE_FLOW_DISSECTOR)
 		return -EINVAL;
 
+	if (kattr->test.ctx_in || kattr->test.ctx_out)
+		return -EINVAL;
+
 	data = bpf_test_init(kattr, size, NET_SKB_PAD + NET_IP_ALIGN,
 			     SKB_DATA_ALIGN(sizeof(struct skb_shared_info)));
 	if (IS_ERR(data))
-- 
cgit v1.2.3-55-g7522