Merge branch 'bpf-sockaddr-wide-store'

Stanislav Fomichev says:

====================
Clang can generate 8-byte stores for user_ip6 & msg_src_ip6,
let's support that on the verifier side.

v3:
* fix comments spelling an -> and (Andrii Nakryiko)

v2:
* Add simple cover letter (Yonghong Song)
* Update comments (Yonghong Song)
* Remove [4] selftests (Yonghong Song)
====================

Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>

include/linux/filter.h

@@ -747,6 +747,12 @@ bpf_ctx_narrow_access_ok(u32 off, u32 size, u32 size_default)
 	return size <= size_default && (size & (size - 1)) == 0;
 }
 
+#define bpf_ctx_wide_store_ok(off, size, type, field)			\
+	(size == sizeof(__u64) &&					\
+	off >= offsetof(type, field) &&					\
+	off + sizeof(__u64) <= offsetofend(type, field) &&		\
+	off % sizeof(__u64) == 0)
+
 #define bpf_classic_proglen(fprog) (fprog->len * sizeof(fprog->filter[0]))
 
 static inline void bpf_prog_lock_ro(struct bpf_prog *fp)

include/uapi/linux/bpf.h

@@ -3247,7 +3247,7 @@ struct bpf_sock_addr {
 	__u32 user_ip4;		/* Allows 1,2,4-byte read and 4-byte write.
 				 * Stored in network byte order.
 				 */
-	__u32 user_ip6[4];	/* Allows 1,2,4-byte read an 4-byte write.
+	__u32 user_ip6[4];	/* Allows 1,2,4-byte read and 4,8-byte write.
 				 * Stored in network byte order.
 				 */
 	__u32 user_port;	/* Allows 4-byte read and write.
@@ -3256,10 +3256,10 @@ struct bpf_sock_addr {
 	__u32 family;		/* Allows 4-byte read, but no write */
 	__u32 type;		/* Allows 4-byte read, but no write */
 	__u32 protocol;		/* Allows 4-byte read, but no write */
-	__u32 msg_src_ip4;	/* Allows 1,2,4-byte read an 4-byte write.
+	__u32 msg_src_ip4;	/* Allows 1,2,4-byte read and 4-byte write.
 				 * Stored in network byte order.
 				 */
-	__u32 msg_src_ip6[4];	/* Allows 1,2,4-byte read an 4-byte write.
+	__u32 msg_src_ip6[4];	/* Allows 1,2,4-byte read and 4,8-byte write.
 				 * Stored in network byte order.
 				 */
 	__bpf_md_ptr(struct bpf_sock *, sk);

net/core/filter.c

@@ -6890,6 +6890,16 @@ static bool sock_addr_is_valid_access(int off, int size,
 			if (!bpf_ctx_narrow_access_ok(off, size, size_default))
 				return false;
 		} else {
+			if (bpf_ctx_wide_store_ok(off, size,
+						  struct bpf_sock_addr,
+						  user_ip6))
+				return true;
+
+			if (bpf_ctx_wide_store_ok(off, size,
+						  struct bpf_sock_addr,
+						  msg_src_ip6))
+				return true;
+
 			if (size != size_default)
 				return false;
 		}
@@ -7730,9 +7740,6 @@ static u32 xdp_convert_ctx_access(enum bpf_access_type type,
 /* SOCK_ADDR_STORE_NESTED_FIELD_OFF() has semantic similar to
  * SOCK_ADDR_LOAD_NESTED_FIELD_SIZE_OFF() but for store operation.
  *
- * It doesn't support SIZE argument though since narrow stores are not
- * supported for now.
- *
  * In addition it uses Temporary Field TF (member of struct S) as the 3rd
  * "register" since two registers available in convert_ctx_access are not
  * enough: we can't override neither SRC, since it contains value to store, nor
@@ -7740,7 +7747,7 @@ static u32 xdp_convert_ctx_access(enum bpf_access_type type,
  * instructions. But we need a temporary place to save pointer to nested
  * structure whose field we want to store to.
  */
-#define SOCK_ADDR_STORE_NESTED_FIELD_OFF(S, NS, F, NF, OFF, TF)		       \
+#define SOCK_ADDR_STORE_NESTED_FIELD_OFF(S, NS, F, NF, SIZE, OFF, TF)	       \
 	do {								       \
 		int tmp_reg = BPF_REG_9;				       \
 		if (si->src_reg == tmp_reg || si->dst_reg == tmp_reg)	       \
@@ -7751,8 +7758,7 @@ static u32 xdp_convert_ctx_access(enum bpf_access_type type,
 				      offsetof(S, TF));			       \
 		*insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(S, F), tmp_reg,	       \
 				      si->dst_reg, offsetof(S, F));	       \
-		*insn++ = BPF_STX_MEM(					       \
+		*insn++ = BPF_STX_MEM(SIZE, tmp_reg, si->src_reg,	       \
-			BPF_FIELD_SIZEOF(NS, NF), tmp_reg, si->src_reg,	       \
 			bpf_target_off(NS, NF, FIELD_SIZEOF(NS, NF),	       \
 				       target_size)			       \
 				+ OFF);					       \
@@ -7764,8 +7770,8 @@ static u32 xdp_convert_ctx_access(enum bpf_access_type type,
 						      TF)		       \
 	do {								       \
 		if (type == BPF_WRITE) {				       \
-			SOCK_ADDR_STORE_NESTED_FIELD_OFF(S, NS, F, NF, OFF,    \
+			SOCK_ADDR_STORE_NESTED_FIELD_OFF(S, NS, F, NF, SIZE,   \
-							 TF);		       \
+							 OFF, TF);	       \
 		} else {						       \
 			SOCK_ADDR_LOAD_NESTED_FIELD_SIZE_OFF(		       \
 				S, NS, F, NF, SIZE, OFF);  \

tools/include/uapi/linux/bpf.h

@@ -3244,7 +3244,7 @@ struct bpf_sock_addr {
 	__u32 user_ip4;		/* Allows 1,2,4-byte read and 4-byte write.
 				 * Stored in network byte order.
 				 */
-	__u32 user_ip6[4];	/* Allows 1,2,4-byte read an 4-byte write.
+	__u32 user_ip6[4];	/* Allows 1,2,4-byte read and 4,8-byte write.
 				 * Stored in network byte order.
 				 */
 	__u32 user_port;	/* Allows 4-byte read and write.
@@ -3253,10 +3253,10 @@ struct bpf_sock_addr {
 	__u32 family;		/* Allows 4-byte read, but no write */
 	__u32 type;		/* Allows 4-byte read, but no write */
 	__u32 protocol;		/* Allows 4-byte read, but no write */
-	__u32 msg_src_ip4;	/* Allows 1,2,4-byte read an 4-byte write.
+	__u32 msg_src_ip4;	/* Allows 1,2,4-byte read and 4-byte write.
 				 * Stored in network byte order.
 				 */
-	__u32 msg_src_ip6[4];	/* Allows 1,2,4-byte read an 4-byte write.
+	__u32 msg_src_ip6[4];	/* Allows 1,2,4-byte read and 4,8-byte write.
 				 * Stored in network byte order.
 				 */
 	__bpf_md_ptr(struct bpf_sock *, sk);

tools/testing/selftests/bpf/test_verifier.c

@@ -105,6 +105,7 @@ struct bpf_test {
 			__u64 data64[TEST_DATA_LEN / 8];
 		};
 	} retvals[MAX_TEST_RUNS];
+	enum bpf_attach_type expected_attach_type;
 };
 
 /* Note we want this to be 64 bit aligned so that the end of our array is
@@ -850,6 +851,7 @@ static void do_test_single(struct bpf_test *test, bool unpriv,
 	int fd_prog, expected_ret, alignment_prevented_execution;
 	int prog_len, prog_type = test->prog_type;
 	struct bpf_insn *prog = test->insns;
+	struct bpf_load_program_attr attr;
 	int run_errs, run_successes;
 	int map_fds[MAX_NR_MAPS];
 	const char *expected_err;
@@ -881,8 +883,17 @@ static void do_test_single(struct bpf_test *test, bool unpriv,
 		pflags |= BPF_F_STRICT_ALIGNMENT;
 	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), 4);
+	memset(&attr, 0, sizeof(attr));
+	attr.prog_type = prog_type;
+	attr.expected_attach_type = test->expected_attach_type;
+	attr.insns = prog;
+	attr.insns_cnt = prog_len;
+	attr.license = "GPL";
+	attr.log_level = 4;
+	attr.prog_flags = pflags;
+
+	fd_prog = bpf_load_program_xattr(&attr, bpf_vlog, sizeof(bpf_vlog));
 	if (fd_prog < 0 && !bpf_probe_prog_type(prog_type, 0)) {
 		printf("SKIP (unsupported program type %d)\n", prog_type);
 		skips++;
@@ -912,7 +923,7 @@ static void do_test_single(struct bpf_test *test, bool unpriv,
 			printf("FAIL\nUnexpected success to load!\n");
 			goto fail_log;
 		}
-		if (!strstr(bpf_vlog, expected_err)) {
+		if (!expected_err || !strstr(bpf_vlog, expected_err)) {
 			printf("FAIL\nUnexpected error message!\n\tEXP: %s\n\tRES: %s\n",
 			      expected_err, bpf_vlog);
 			goto fail_log;

tools/testing/selftests/bpf/verifier/wide_store.c

@@ -0,0 +1,36 @@
+#define BPF_SOCK_ADDR(field, off, res, err) \
+{ \
+	"wide store to bpf_sock_addr." #field "[" #off "]", \
+	.insns = { \
+	BPF_MOV64_IMM(BPF_REG_0, 1), \
+	BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_0, \
+		    offsetof(struct bpf_sock_addr, field[off])), \
+	BPF_EXIT_INSN(), \
+	}, \
+	.result = res, \
+	.prog_type = BPF_PROG_TYPE_CGROUP_SOCK_ADDR, \
+	.expected_attach_type = BPF_CGROUP_UDP6_SENDMSG, \
+	.errstr = err, \
+}
+
+/* user_ip6[0] is u64 aligned */
+BPF_SOCK_ADDR(user_ip6, 0, ACCEPT,
+	      NULL),
+BPF_SOCK_ADDR(user_ip6, 1, REJECT,
+	      "invalid bpf_context access off=12 size=8"),
+BPF_SOCK_ADDR(user_ip6, 2, ACCEPT,
+	      NULL),
+BPF_SOCK_ADDR(user_ip6, 3, REJECT,
+	      "invalid bpf_context access off=20 size=8"),
+
+/* msg_src_ip6[0] is _not_ u64 aligned */
+BPF_SOCK_ADDR(msg_src_ip6, 0, REJECT,
+	      "invalid bpf_context access off=44 size=8"),
+BPF_SOCK_ADDR(msg_src_ip6, 1, ACCEPT,
+	      NULL),
+BPF_SOCK_ADDR(msg_src_ip6, 2, REJECT,
+	      "invalid bpf_context access off=52 size=8"),
+BPF_SOCK_ADDR(msg_src_ip6, 3, REJECT,
+	      "invalid bpf_context access off=56 size=8"),
+
+#undef BPF_SOCK_ADDR