bpf: allow wide (u64) aligned stores for some fields of bpf_sock_addr

Since commit cd17d77705 ("bpf/tools: sync bpf.h") clang decided
that it can do a single u64 store into user_ip6[2] instead of two
separate u32 ones:

 #  17: (18) r2 = 0x100000000000000
 #  ; ctx->user_ip6[2] = bpf_htonl(DST_REWRITE_IP6_2);
 #  19: (7b) *(u64 *)(r1 +16) = r2
 #  invalid bpf_context access off=16 size=8

>From the compiler point of view it does look like a correct thing
to do, so let's support it on the kernel side.

Credit to Andrii Nakryiko for a proper implementation of
bpf_ctx_wide_store_ok.

Cc: Andrii Nakryiko <andriin@fb.com>
Cc: Yonghong Song <yhs@fb.com>
Fixes: cd17d77705 ("bpf/tools: sync bpf.h")
Reported-by: kernel test robot <rong.a.chen@intel.com>
Acked-by: Yonghong Song <yhs@fb.com>
Acked-by: Andrii Nakryiko <andriin@fb.com>
Signed-off-by: Stanislav Fomichev <sdf@google.com>
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);  \