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

Daniel Borkmann says:

====================
pull-request: bpf-next 2018-03-21

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

The main changes are:

1) Add a BPF hook for sendmsg and sendfile by reusing the ULP infrastructure
   and sockmap. Three helpers are added along with this, bpf_msg_apply_bytes(),
   bpf_msg_cork_bytes(), and bpf_msg_pull_data(). The first is used to tell
   for how many bytes the verdict should be applied to, the second to tell
   that x bytes need to be queued first to retrigger the BPF program for a
   verdict, and the third helper is mainly for the sendfile case to pull in
   data for making it private for reading and/or writing, from John.

2) Improve address to symbol resolution of user stack traces in BPF stackmap.
   Currently, the latter stores the address for each entry in the call trace,
   however to map these addresses to user space files, it is necessary to
   maintain the mapping from these virtual addresses to symbols in the binary
   which is not practical for system-wide profiling. Instead, this option for
   the stackmap rather stores the ELF build id and offset for the call trace
   entries, from Song.

3) Add support that allows BPF programs attached to perf events to read the
   address values recorded with the perf events. They are requested through
   PERF_SAMPLE_ADDR via perf_event_open(). Main motivation behind it is to
   support building memory or lock access profiling and tracing tools with
   the help of BPF, from Teng.

4) Several improvements to the tools/bpf/ Makefiles. The 'make bpf' in the
   tools directory does not provide the standard quiet output except for
   bpftool and it also does not respect specifying a build output directory.
   'make bpf_install' command neither respects specified destination nor
   prefix, all from Jiri. In addition, Jakub fixes several other minor issues
   in the Makefiles on top of that, e.g. fixing dependency paths, phony
   targets and more.

5) Various doc updates e.g. add a comment for BPF fs about reserved names
   to make the dentry lookup from there a bit more obvious, and a comment
   to the bpf_devel_QA file in order to explain the diff between native
   and bpf target clang usage with regards to pointer size, from Quentin
   and Daniel.
====================

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

4 files changed, 343 insertions, 64 deletions

diff --git a/net/core/filter.c b/net/core/filter.c
index 33edfa8372fd..c86f03fd9ea5 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -1890,6 +1890,202 @@ static const struct bpf_func_proto bpf_sk_redirect_map_proto = {
 	.arg4_type      = ARG_ANYTHING,
 };
 
+BPF_CALL_4(bpf_msg_redirect_map, struct sk_msg_buff *, msg,
+	   struct bpf_map *, map, u32, key, u64, flags)
+{
+	/* If user passes invalid input drop the packet. */
+	if (unlikely(flags))
+		return SK_DROP;
+
+	msg->key = key;
+	msg->flags = flags;
+	msg->map = map;
+
+	return SK_PASS;
+}
+
+struct sock *do_msg_redirect_map(struct sk_msg_buff *msg)
+{
+	struct sock *sk = NULL;
+
+	if (msg->map) {
+		sk = __sock_map_lookup_elem(msg->map, msg->key);
+
+		msg->key = 0;
+		msg->map = NULL;
+	}
+
+	return sk;
+}
+
+static const struct bpf_func_proto bpf_msg_redirect_map_proto = {
+	.func           = bpf_msg_redirect_map,
+	.gpl_only       = false,
+	.ret_type       = RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_CTX,
+	.arg2_type      = ARG_CONST_MAP_PTR,
+	.arg3_type      = ARG_ANYTHING,
+	.arg4_type      = ARG_ANYTHING,
+};
+
+BPF_CALL_2(bpf_msg_apply_bytes, struct sk_msg_buff *, msg, u32, bytes)
+{
+	msg->apply_bytes = bytes;
+	return 0;
+}
+
+static const struct bpf_func_proto bpf_msg_apply_bytes_proto = {
+	.func           = bpf_msg_apply_bytes,
+	.gpl_only       = false,
+	.ret_type       = RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_CTX,
+	.arg2_type      = ARG_ANYTHING,
+};
+
+BPF_CALL_2(bpf_msg_cork_bytes, struct sk_msg_buff *, msg, u32, bytes)
+{
+	msg->cork_bytes = bytes;
+	return 0;
+}
+
+static const struct bpf_func_proto bpf_msg_cork_bytes_proto = {
+	.func           = bpf_msg_cork_bytes,
+	.gpl_only       = false,
+	.ret_type       = RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_CTX,
+	.arg2_type      = ARG_ANYTHING,
+};
+
+BPF_CALL_4(bpf_msg_pull_data,
+	   struct sk_msg_buff *, msg, u32, start, u32, end, u64, flags)
+{
+	unsigned int len = 0, offset = 0, copy = 0;
+	struct scatterlist *sg = msg->sg_data;
+	int first_sg, last_sg, i, shift;
+	unsigned char *p, *to, *from;
+	int bytes = end - start;
+	struct page *page;
+
+	if (unlikely(flags || end <= start))
+		return -EINVAL;
+
+	/* First find the starting scatterlist element */
+	i = msg->sg_start;
+	do {
+		len = sg[i].length;
+		offset += len;
+		if (start < offset + len)
+			break;
+		i++;
+		if (i == MAX_SKB_FRAGS)
+			i = 0;
+	} while (i != msg->sg_end);
+
+	if (unlikely(start >= offset + len))
+		return -EINVAL;
+
+	if (!msg->sg_copy[i] && bytes <= len)
+		goto out;
+
+	first_sg = i;
+
+	/* At this point we need to linearize multiple scatterlist
+	 * elements or a single shared page. Either way we need to
+	 * copy into a linear buffer exclusively owned by BPF. Then
+	 * place the buffer in the scatterlist and fixup the original
+	 * entries by removing the entries now in the linear buffer
+	 * and shifting the remaining entries. For now we do not try
+	 * to copy partial entries to avoid complexity of running out
+	 * of sg_entry slots. The downside is reading a single byte
+	 * will copy the entire sg entry.
+	 */
+	do {
+		copy += sg[i].length;
+		i++;
+		if (i == MAX_SKB_FRAGS)
+			i = 0;
+		if (bytes < copy)
+			break;
+	} while (i != msg->sg_end);
+	last_sg = i;
+
+	if (unlikely(copy < end - start))
+		return -EINVAL;
+
+	page = alloc_pages(__GFP_NOWARN | GFP_ATOMIC, get_order(copy));
+	if (unlikely(!page))
+		return -ENOMEM;
+	p = page_address(page);
+	offset = 0;
+
+	i = first_sg;
+	do {
+		from = sg_virt(&sg[i]);
+		len = sg[i].length;
+		to = p + offset;
+
+		memcpy(to, from, len);
+		offset += len;
+		sg[i].length = 0;
+		put_page(sg_page(&sg[i]));
+
+		i++;
+		if (i == MAX_SKB_FRAGS)
+			i = 0;
+	} while (i != last_sg);
+
+	sg[first_sg].length = copy;
+	sg_set_page(&sg[first_sg], page, copy, 0);
+
+	/* To repair sg ring we need to shift entries. If we only
+	 * had a single entry though we can just replace it and
+	 * be done. Otherwise walk the ring and shift the entries.
+	 */
+	shift = last_sg - first_sg - 1;
+	if (!shift)
+		goto out;
+
+	i = first_sg + 1;
+	do {
+		int move_from;
+
+		if (i + shift >= MAX_SKB_FRAGS)
+			move_from = i + shift - MAX_SKB_FRAGS;
+		else
+			move_from = i + shift;
+
+		if (move_from == msg->sg_end)
+			break;
+
+		sg[i] = sg[move_from];
+		sg[move_from].length = 0;
+		sg[move_from].page_link = 0;
+		sg[move_from].offset = 0;
+
+		i++;
+		if (i == MAX_SKB_FRAGS)
+			i = 0;
+	} while (1);
+	msg->sg_end -= shift;
+	if (msg->sg_end < 0)
+		msg->sg_end += MAX_SKB_FRAGS;
+out:
+	msg->data = sg_virt(&sg[i]) + start - offset;
+	msg->data_end = msg->data + bytes;
+
+	return 0;
+}
+
+static const struct bpf_func_proto bpf_msg_pull_data_proto = {
+	.func		= bpf_msg_pull_data,
+	.gpl_only	= false,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_CTX,
+	.arg2_type	= ARG_ANYTHING,
+	.arg3_type	= ARG_ANYTHING,
+	.arg4_type	= ARG_ANYTHING,
+};
+
 BPF_CALL_1(bpf_get_cgroup_classid, const struct sk_buff *, skb)
 {
 	return task_get_classid(skb);
@@ -2831,7 +3027,8 @@ bool bpf_helper_changes_pkt_data(void *func)
 	    func == bpf_l3_csum_replace ||
 	    func == bpf_l4_csum_replace ||
 	    func == bpf_xdp_adjust_head ||
-	    func == bpf_xdp_adjust_meta)
+	    func == bpf_xdp_adjust_meta ||
+	    func == bpf_msg_pull_data)
 		return true;
 
 	return false;
@@ -3591,6 +3788,22 @@ static const struct bpf_func_proto *
 	}
 }
 
+static const struct bpf_func_proto *sk_msg_func_proto(enum bpf_func_id func_id)
+{
+	switch (func_id) {
+	case BPF_FUNC_msg_redirect_map:
+		return &bpf_msg_redirect_map_proto;
+	case BPF_FUNC_msg_apply_bytes:
+		return &bpf_msg_apply_bytes_proto;
+	case BPF_FUNC_msg_cork_bytes:
+		return &bpf_msg_cork_bytes_proto;
+	case BPF_FUNC_msg_pull_data:
+		return &bpf_msg_pull_data_proto;
+	default:
+		return bpf_base_func_proto(func_id);
+	}
+}
+
 static const struct bpf_func_proto *sk_skb_func_proto(enum bpf_func_id func_id)
 {
 	switch (func_id) {
@@ -3980,6 +4193,32 @@ static bool sk_skb_is_valid_access(int off, int size,
 	return bpf_skb_is_valid_access(off, size, type, info);
 }
 
+static bool sk_msg_is_valid_access(int off, int size,
+				   enum bpf_access_type type,
+				   struct bpf_insn_access_aux *info)
+{
+	if (type == BPF_WRITE)
+		return false;
+
+	switch (off) {
+	case offsetof(struct sk_msg_md, data):
+		info->reg_type = PTR_TO_PACKET;
+		break;
+	case offsetof(struct sk_msg_md, data_end):
+		info->reg_type = PTR_TO_PACKET_END;
+		break;
+	}
+
+	if (off < 0 || off >= sizeof(struct sk_msg_md))
+		return false;
+	if (off % size != 0)
+		return false;
+	if (size != sizeof(__u64))
+		return false;
+
+	return true;
+}
+
 static u32 bpf_convert_ctx_access(enum bpf_access_type type,
 				  const struct bpf_insn *si,
 				  struct bpf_insn *insn_buf,
@@ -4778,6 +5017,29 @@ static u32 sk_skb_convert_ctx_access(enum bpf_access_type type,
 	return insn - insn_buf;
 }
 
+static u32 sk_msg_convert_ctx_access(enum bpf_access_type type,
+				     const struct bpf_insn *si,
+				     struct bpf_insn *insn_buf,
+				     struct bpf_prog *prog, u32 *target_size)
+{
+	struct bpf_insn *insn = insn_buf;
+
+	switch (si->off) {
+	case offsetof(struct sk_msg_md, data):
+		*insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_msg_buff, data),
+				      si->dst_reg, si->src_reg,
+				      offsetof(struct sk_msg_buff, data));
+		break;
+	case offsetof(struct sk_msg_md, data_end):
+		*insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_msg_buff, data_end),
+				      si->dst_reg, si->src_reg,
+				      offsetof(struct sk_msg_buff, data_end));
+		break;
+	}
+
+	return insn - insn_buf;
+}
+
 const struct bpf_verifier_ops sk_filter_verifier_ops = {
 	.get_func_proto		= sk_filter_func_proto,
 	.is_valid_access	= sk_filter_is_valid_access,
@@ -4868,6 +5130,15 @@ const struct bpf_verifier_ops sk_skb_verifier_ops = {
 const struct bpf_prog_ops sk_skb_prog_ops = {
 };
 
+const struct bpf_verifier_ops sk_msg_verifier_ops = {
+	.get_func_proto		= sk_msg_func_proto,
+	.is_valid_access	= sk_msg_is_valid_access,
+	.convert_ctx_access	= sk_msg_convert_ctx_access,
+};
+
+const struct bpf_prog_ops sk_msg_prog_ops = {
+};
+
 int sk_detach_filter(struct sock *sk)
 {
 	int ret = -ENOENT;
diff --git a/net/core/sock.c b/net/core/sock.c
index a8962d912895..f704324d1219 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -2237,6 +2237,67 @@ bool sk_page_frag_refill(struct sock *sk, struct page_frag *pfrag)
 }
 EXPORT_SYMBOL(sk_page_frag_refill);
 
+int sk_alloc_sg(struct sock *sk, int len, struct scatterlist *sg,
+		int sg_start, int *sg_curr_index, unsigned int *sg_curr_size,
+		int first_coalesce)
+{
+	int sg_curr = *sg_curr_index, use = 0, rc = 0;
+	unsigned int size = *sg_curr_size;
+	struct page_frag *pfrag;
+	struct scatterlist *sge;
+
+	len -= size;
+	pfrag = sk_page_frag(sk);
+
+	while (len > 0) {
+		unsigned int orig_offset;
+
+		if (!sk_page_frag_refill(sk, pfrag)) {
+			rc = -ENOMEM;
+			goto out;
+		}
+
+		use = min_t(int, len, pfrag->size - pfrag->offset);
+
+		if (!sk_wmem_schedule(sk, use)) {
+			rc = -ENOMEM;
+			goto out;
+		}
+
+		sk_mem_charge(sk, use);
+		size += use;
+		orig_offset = pfrag->offset;
+		pfrag->offset += use;
+
+		sge = sg + sg_curr - 1;
+		if (sg_curr > first_coalesce && sg_page(sg) == pfrag->page &&
+		    sg->offset + sg->length == orig_offset) {
+			sg->length += use;
+		} else {
+			sge = sg + sg_curr;
+			sg_unmark_end(sge);
+			sg_set_page(sge, pfrag->page, use, orig_offset);
+			get_page(pfrag->page);
+			sg_curr++;
+
+			if (sg_curr == MAX_SKB_FRAGS)
+				sg_curr = 0;
+
+			if (sg_curr == sg_start) {
+				rc = -ENOSPC;
+				break;
+			}
+		}
+
+		len -= use;
+	}
+out:
+	*sg_curr_size = size;
+	*sg_curr_index = sg_curr;
+	return rc;
+}
+EXPORT_SYMBOL(sk_alloc_sg);
+
 static void __lock_sock(struct sock *sk)
 	__releases(&sk->sk_lock.slock)
 	__acquires(&sk->sk_lock.slock)
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index e553f84bde83..d763fae1b574 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -994,7 +994,9 @@ new_segment:
 			get_page(page);
 			skb_fill_page_desc(skb, i, page, offset, copy);
 		}
-		skb_shinfo(skb)->tx_flags |= SKBTX_SHARED_FRAG;
+
+		if (!(flags & MSG_NO_SHARED_FRAGS))
+			skb_shinfo(skb)->tx_flags |= SKBTX_SHARED_FRAG;
 
 		skb->len += copy;
 		skb->data_len += copy;
diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c
index f26376e954ae..057a558ed6d7 100644
--- a/net/tls/tls_sw.c
+++ b/net/tls/tls_sw.c
@@ -87,71 +87,16 @@ static void trim_both_sgl(struct sock *sk, int target_size)
 		target_size);
 }
 
-static int alloc_sg(struct sock *sk, int len, struct scatterlist *sg,
-		    int *sg_num_elem, unsigned int *sg_size,
-		    int first_coalesce)
-{
-	struct page_frag *pfrag;
-	unsigned int size = *sg_size;
-	int num_elem = *sg_num_elem, use = 0, rc = 0;
-	struct scatterlist *sge;
-	unsigned int orig_offset;
-
-	len -= size;
-	pfrag = sk_page_frag(sk);
-
-	while (len > 0) {
-		if (!sk_page_frag_refill(sk, pfrag)) {
-			rc = -ENOMEM;
-			goto out;
-		}
-
-		use = min_t(int, len, pfrag->size - pfrag->offset);
-
-		if (!sk_wmem_schedule(sk, use)) {
-			rc = -ENOMEM;
-			goto out;
-		}
-
-		sk_mem_charge(sk, use);
-		size += use;
-		orig_offset = pfrag->offset;
-		pfrag->offset += use;
-
-		sge = sg + num_elem - 1;
-		if (num_elem > first_coalesce && sg_page(sg) == pfrag->page &&
-		    sg->offset + sg->length == orig_offset) {
-			sg->length += use;
-		} else {
-			sge++;
-			sg_unmark_end(sge);
-			sg_set_page(sge, pfrag->page, use, orig_offset);
-			get_page(pfrag->page);
-			++num_elem;
-			if (num_elem == MAX_SKB_FRAGS) {
-				rc = -ENOSPC;
-				break;
-			}
-		}
-
-		len -= use;
-	}
-	goto out;
-
-out:
-	*sg_size = size;
-	*sg_num_elem = num_elem;
-	return rc;
-}
-
 static int alloc_encrypted_sg(struct sock *sk, int len)
 {
 	struct tls_context *tls_ctx = tls_get_ctx(sk);
 	struct tls_sw_context *ctx = tls_sw_ctx(tls_ctx);
 	int rc = 0;
 
-	rc = alloc_sg(sk, len, ctx->sg_encrypted_data,
-		      &ctx->sg_encrypted_num_elem, &ctx->sg_encrypted_size, 0);
+	rc = sk_alloc_sg(sk, len,
+			 ctx->sg_encrypted_data, 0,
+			 &ctx->sg_encrypted_num_elem,
+			 &ctx->sg_encrypted_size, 0);
 
 	return rc;
 }
@@ -162,9 +107,9 @@ static int alloc_plaintext_sg(struct sock *sk, int len)
 	struct tls_sw_context *ctx = tls_sw_ctx(tls_ctx);
 	int rc = 0;
 
-	rc = alloc_sg(sk, len, ctx->sg_plaintext_data,
-		      &ctx->sg_plaintext_num_elem, &ctx->sg_plaintext_size,
-		      tls_ctx->pending_open_record_frags);
+	rc = sk_alloc_sg(sk, len, ctx->sg_plaintext_data, 0,
+			 &ctx->sg_plaintext_num_elem, &ctx->sg_plaintext_size,
+			 tls_ctx->pending_open_record_frags);
 
 	return rc;
 }