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

Alexei Starovoitov says:

====================
pull-request: bpf 2020-06-17

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

We've added 10 non-merge commits during the last 2 day(s) which contain
a total of 14 files changed, 158 insertions(+), 59 deletions(-).

The main changes are:

1) Important fix for bpf_probe_read_kernel_str() return value, from Andrii.

2) [gs]etsockopt fix for large optlen, from Stanislav.

3) devmap allocation fix, from Toke.
====================

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

5 files changed, 95 insertions, 12 deletions

diff --git a/tools/bpf/bpftool/Documentation/bpftool-map.rst b/tools/bpf/bpftool/Documentation/bpftool-map.rst
index 31101643e57c..70c78faa47ab 100644
--- a/tools/bpf/bpftool/Documentation/bpftool-map.rst
+++ b/tools/bpf/bpftool/Documentation/bpftool-map.rst
@@ -49,7 +49,7 @@ MAP COMMANDS
 |		| **lru_percpu_hash** | **lpm_trie** | **array_of_maps** | **hash_of_maps**
 |		| **devmap** | **devmap_hash** | **sockmap** | **cpumap** | **xskmap** | **sockhash**
 |		| **cgroup_storage** | **reuseport_sockarray** | **percpu_cgroup_storage**
-|		| **queue** | **stack** | **sk_storage** | **struct_ops** }
+|		| **queue** | **stack** | **sk_storage** | **struct_ops** | **ringbuf** }
 
 DESCRIPTION
 ===========
diff --git a/tools/bpf/bpftool/map.c b/tools/bpf/bpftool/map.c
index c5fac8068ba1..1d3b60651078 100644
--- a/tools/bpf/bpftool/map.c
+++ b/tools/bpf/bpftool/map.c
@@ -49,6 +49,7 @@ const char * const map_type_name[] = {
 	[BPF_MAP_TYPE_STACK]			= "stack",
 	[BPF_MAP_TYPE_SK_STORAGE]		= "sk_storage",
 	[BPF_MAP_TYPE_STRUCT_OPS]		= "struct_ops",
+	[BPF_MAP_TYPE_RINGBUF]			= "ringbuf",
 };
 
 const size_t map_type_name_size = ARRAY_SIZE(map_type_name);
@@ -1590,7 +1591,7 @@ static int do_help(int argc, char **argv)
 		"                 lru_percpu_hash | lpm_trie | array_of_maps | hash_of_maps |\n"
 		"                 devmap | devmap_hash | sockmap | cpumap | xskmap | sockhash |\n"
 		"                 cgroup_storage | reuseport_sockarray | percpu_cgroup_storage |\n"
-		"                 queue | stack | sk_storage | struct_ops }\n"
+		"                 queue | stack | sk_storage | struct_ops | ringbuf }\n"
 		"       " HELP_SPEC_OPTIONS "\n"
 		"",
 		bin_name, argv[-2]);
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 19684813faae..974a71342aea 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -3168,7 +3168,7 @@ union bpf_attr {
  *	Return
  *		The id is returned or 0 in case the id could not be retrieved.
  *
- * void *bpf_ringbuf_output(void *ringbuf, void *data, u64 size, u64 flags)
+ * int bpf_ringbuf_output(void *ringbuf, void *data, u64 size, u64 flags)
  * 	Description
  * 		Copy *size* bytes from *data* into a ring buffer *ringbuf*.
  * 		If BPF_RB_NO_WAKEUP is specified in *flags*, no notification of
diff --git a/tools/testing/selftests/bpf/prog_tests/sockopt_sk.c b/tools/testing/selftests/bpf/prog_tests/sockopt_sk.c
index 2061a6beac0f..5f54c6aec7f0 100644
--- a/tools/testing/selftests/bpf/prog_tests/sockopt_sk.c
+++ b/tools/testing/selftests/bpf/prog_tests/sockopt_sk.c
@@ -13,6 +13,7 @@ static int getsetsockopt(void)
 		char cc[16]; /* TCP_CA_NAME_MAX */
 	} buf = {};
 	socklen_t optlen;
+	char *big_buf = NULL;
 
 	fd = socket(AF_INET, SOCK_STREAM, 0);
 	if (fd < 0) {
@@ -22,24 +23,31 @@ static int getsetsockopt(void)
 
 	/* IP_TOS - BPF bypass */
 
-	buf.u8[0] = 0x08;
-	err = setsockopt(fd, SOL_IP, IP_TOS, &buf, 1);
+	optlen = getpagesize() * 2;
+	big_buf = calloc(1, optlen);
+	if (!big_buf) {
+		log_err("Couldn't allocate two pages");
+		goto err;
+	}
+
+	*(int *)big_buf = 0x08;
+	err = setsockopt(fd, SOL_IP, IP_TOS, big_buf, optlen);
 	if (err) {
 		log_err("Failed to call setsockopt(IP_TOS)");
 		goto err;
 	}
 
-	buf.u8[0] = 0x00;
+	memset(big_buf, 0, optlen);
 	optlen = 1;
-	err = getsockopt(fd, SOL_IP, IP_TOS, &buf, &optlen);
+	err = getsockopt(fd, SOL_IP, IP_TOS, big_buf, &optlen);
 	if (err) {
 		log_err("Failed to call getsockopt(IP_TOS)");
 		goto err;
 	}
 
-	if (buf.u8[0] != 0x08) {
-		log_err("Unexpected getsockopt(IP_TOS) buf[0] 0x%02x != 0x08",
-			buf.u8[0]);
+	if (*(int *)big_buf != 0x08) {
+		log_err("Unexpected getsockopt(IP_TOS) optval 0x%x != 0x08",
+			*(int *)big_buf);
 		goto err;
 	}
 
@@ -78,6 +86,28 @@ static int getsetsockopt(void)
 		goto err;
 	}
 
+	/* IP_FREEBIND - BPF can't access optval past PAGE_SIZE */
+
+	optlen = getpagesize() * 2;
+	memset(big_buf, 0, optlen);
+
+	err = setsockopt(fd, SOL_IP, IP_FREEBIND, big_buf, optlen);
+	if (err != 0) {
+		log_err("Failed to call setsockopt, ret=%d", err);
+		goto err;
+	}
+
+	err = getsockopt(fd, SOL_IP, IP_FREEBIND, big_buf, &optlen);
+	if (err != 0) {
+		log_err("Failed to call getsockopt, ret=%d", err);
+		goto err;
+	}
+
+	if (optlen != 1 || *(__u8 *)big_buf != 0x55) {
+		log_err("Unexpected IP_FREEBIND getsockopt, optlen=%d, optval=0x%x",
+			optlen, *(__u8 *)big_buf);
+	}
+
 	/* SO_SNDBUF is overwritten */
 
 	buf.u32 = 0x01010101;
@@ -124,9 +154,11 @@ static int getsetsockopt(void)
 		goto err;
 	}
 
+	free(big_buf);
 	close(fd);
 	return 0;
 err:
+	free(big_buf);
 	close(fd);
 	return -1;
 }
diff --git a/tools/testing/selftests/bpf/progs/sockopt_sk.c b/tools/testing/selftests/bpf/progs/sockopt_sk.c
index d5a5eeb5fb52..712df7b49cb1 100644
--- a/tools/testing/selftests/bpf/progs/sockopt_sk.c
+++ b/tools/testing/selftests/bpf/progs/sockopt_sk.c
@@ -8,6 +8,10 @@
 char _license[] SEC("license") = "GPL";
 __u32 _version SEC("version") = 1;
 
+#ifndef PAGE_SIZE
+#define PAGE_SIZE 4096
+#endif
+
 #define SOL_CUSTOM			0xdeadbeef
 
 struct sockopt_sk {
@@ -28,12 +32,14 @@ int _getsockopt(struct bpf_sockopt *ctx)
 	__u8 *optval = ctx->optval;
 	struct sockopt_sk *storage;
 
-	if (ctx->level == SOL_IP && ctx->optname == IP_TOS)
+	if (ctx->level == SOL_IP && ctx->optname == IP_TOS) {
 		/* Not interested in SOL_IP:IP_TOS;
 		 * let next BPF program in the cgroup chain or kernel
 		 * handle it.
 		 */
+		ctx->optlen = 0; /* bypass optval>PAGE_SIZE */
 		return 1;
+	}
 
 	if (ctx->level == SOL_SOCKET && ctx->optname == SO_SNDBUF) {
 		/* Not interested in SOL_SOCKET:SO_SNDBUF;
@@ -51,6 +57,26 @@ int _getsockopt(struct bpf_sockopt *ctx)
 		return 1;
 	}
 
+	if (ctx->level == SOL_IP && ctx->optname == IP_FREEBIND) {
+		if (optval + 1 > optval_end)
+			return 0; /* EPERM, bounds check */
+
+		ctx->retval = 0; /* Reset system call return value to zero */
+
+		/* Always export 0x55 */
+		optval[0] = 0x55;
+		ctx->optlen = 1;
+
+		/* Userspace buffer is PAGE_SIZE * 2, but BPF
+		 * program can only see the first PAGE_SIZE
+		 * bytes of data.
+		 */
+		if (optval_end - optval != PAGE_SIZE)
+			return 0; /* EPERM, unexpected data size */
+
+		return 1;
+	}
+
 	if (ctx->level != SOL_CUSTOM)
 		return 0; /* EPERM, deny everything except custom level */
 
@@ -81,12 +107,14 @@ int _setsockopt(struct bpf_sockopt *ctx)
 	__u8 *optval = ctx->optval;
 	struct sockopt_sk *storage;
 
-	if (ctx->level == SOL_IP && ctx->optname == IP_TOS)
+	if (ctx->level == SOL_IP && ctx->optname == IP_TOS) {
 		/* Not interested in SOL_IP:IP_TOS;
 		 * let next BPF program in the cgroup chain or kernel
 		 * handle it.
 		 */
+		ctx->optlen = 0; /* bypass optval>PAGE_SIZE */
 		return 1;
+	}
 
 	if (ctx->level == SOL_SOCKET && ctx->optname == SO_SNDBUF) {
 		/* Overwrite SO_SNDBUF value */
@@ -112,6 +140,28 @@ int _setsockopt(struct bpf_sockopt *ctx)
 		return 1;
 	}
 
+	if (ctx->level == SOL_IP && ctx->optname == IP_FREEBIND) {
+		/* Original optlen is larger than PAGE_SIZE. */
+		if (ctx->optlen != PAGE_SIZE * 2)
+			return 0; /* EPERM, unexpected data size */
+
+		if (optval + 1 > optval_end)
+			return 0; /* EPERM, bounds check */
+
+		/* Make sure we can trim the buffer. */
+		optval[0] = 0;
+		ctx->optlen = 1;
+
+		/* Usepace buffer is PAGE_SIZE * 2, but BPF
+		 * program can only see the first PAGE_SIZE
+		 * bytes of data.
+		 */
+		if (optval_end - optval != PAGE_SIZE)
+			return 0; /* EPERM, unexpected data size */
+
+		return 1;
+	}
+
 	if (ctx->level != SOL_CUSTOM)
 		return 0; /* EPERM, deny everything except custom level */