4 files changed, 383 insertions, 19 deletions

diff --git a/net/core/filter.c b/net/core/filter.c
index 4603b7cd3cd1..a06931c27eeb 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -3783,6 +3783,28 @@ static const struct bpf_func_proto sk_skb_change_head_proto = {
 	.arg2_type	= ARG_ANYTHING,
 	.arg3_type	= ARG_ANYTHING,
 };
+
+BPF_CALL_1(bpf_xdp_get_buff_len, struct  xdp_buff*, xdp)
+{
+	return xdp_get_buff_len(xdp);
+}
+
+static const struct bpf_func_proto bpf_xdp_get_buff_len_proto = {
+	.func		= bpf_xdp_get_buff_len,
+	.gpl_only	= false,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_CTX,
+};
+
+BTF_ID_LIST_SINGLE(bpf_xdp_get_buff_len_bpf_ids, struct, xdp_buff)
+
+const struct bpf_func_proto bpf_xdp_get_buff_len_trace_proto = {
+	.func		= bpf_xdp_get_buff_len,
+	.gpl_only	= false,
+	.arg1_type	= ARG_PTR_TO_BTF_ID,
+	.arg1_btf_id	= &bpf_xdp_get_buff_len_bpf_ids[0],
+};
+
 static unsigned long xdp_get_metalen(const struct xdp_buff *xdp)
 {
 	return xdp_data_meta_unsupported(xdp) ? 0 :
@@ -3817,11 +3839,208 @@ static const struct bpf_func_proto bpf_xdp_adjust_head_proto = {
 	.arg2_type	= ARG_ANYTHING,
 };
 
+static void bpf_xdp_copy_buf(struct xdp_buff *xdp, unsigned long off,
+			     void *buf, unsigned long len, bool flush)
+{
+	unsigned long ptr_len, ptr_off = 0;
+	skb_frag_t *next_frag, *end_frag;
+	struct skb_shared_info *sinfo;
+	void *src, *dst;
+	u8 *ptr_buf;
+
+	if (likely(xdp->data_end - xdp->data >= off + len)) {
+		src = flush ? buf : xdp->data + off;
+		dst = flush ? xdp->data + off : buf;
+		memcpy(dst, src, len);
+		return;
+	}
+
+	sinfo = xdp_get_shared_info_from_buff(xdp);
+	end_frag = &sinfo->frags[sinfo->nr_frags];
+	next_frag = &sinfo->frags[0];
+
+	ptr_len = xdp->data_end - xdp->data;
+	ptr_buf = xdp->data;
+
+	while (true) {
+		if (off < ptr_off + ptr_len) {
+			unsigned long copy_off = off - ptr_off;
+			unsigned long copy_len = min(len, ptr_len - copy_off);
+
+			src = flush ? buf : ptr_buf + copy_off;
+			dst = flush ? ptr_buf + copy_off : buf;
+			memcpy(dst, src, copy_len);
+
+			off += copy_len;
+			len -= copy_len;
+			buf += copy_len;
+		}
+
+		if (!len || next_frag == end_frag)
+			break;
+
+		ptr_off += ptr_len;
+		ptr_buf = skb_frag_address(next_frag);
+		ptr_len = skb_frag_size(next_frag);
+		next_frag++;
+	}
+}
+
+static void *bpf_xdp_pointer(struct xdp_buff *xdp, u32 offset, u32 len)
+{
+	struct skb_shared_info *sinfo = xdp_get_shared_info_from_buff(xdp);
+	u32 size = xdp->data_end - xdp->data;
+	void *addr = xdp->data;
+	int i;
+
+	if (unlikely(offset > 0xffff || len > 0xffff))
+		return ERR_PTR(-EFAULT);
+
+	if (offset + len > xdp_get_buff_len(xdp))
+		return ERR_PTR(-EINVAL);
+
+	if (offset < size) /* linear area */
+		goto out;
+
+	offset -= size;
+	for (i = 0; i < sinfo->nr_frags; i++) { /* paged area */
+		u32 frag_size = skb_frag_size(&sinfo->frags[i]);
+
+		if  (offset < frag_size) {
+			addr = skb_frag_address(&sinfo->frags[i]);
+			size = frag_size;
+			break;
+		}
+		offset -= frag_size;
+	}
+out:
+	return offset + len < size ? addr + offset : NULL;
+}
+
+BPF_CALL_4(bpf_xdp_load_bytes, struct xdp_buff *, xdp, u32, offset,
+	   void *, buf, u32, len)
+{
+	void *ptr;
+
+	ptr = bpf_xdp_pointer(xdp, offset, len);
+	if (IS_ERR(ptr))
+		return PTR_ERR(ptr);
+
+	if (!ptr)
+		bpf_xdp_copy_buf(xdp, offset, buf, len, false);
+	else
+		memcpy(buf, ptr, len);
+
+	return 0;
+}
+
+static const struct bpf_func_proto bpf_xdp_load_bytes_proto = {
+	.func		= bpf_xdp_load_bytes,
+	.gpl_only	= false,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_CTX,
+	.arg2_type	= ARG_ANYTHING,
+	.arg3_type	= ARG_PTR_TO_UNINIT_MEM,
+	.arg4_type	= ARG_CONST_SIZE,
+};
+
+BPF_CALL_4(bpf_xdp_store_bytes, struct xdp_buff *, xdp, u32, offset,
+	   void *, buf, u32, len)
+{
+	void *ptr;
+
+	ptr = bpf_xdp_pointer(xdp, offset, len);
+	if (IS_ERR(ptr))
+		return PTR_ERR(ptr);
+
+	if (!ptr)
+		bpf_xdp_copy_buf(xdp, offset, buf, len, true);
+	else
+		memcpy(ptr, buf, len);
+
+	return 0;
+}
+
+static const struct bpf_func_proto bpf_xdp_store_bytes_proto = {
+	.func		= bpf_xdp_store_bytes,
+	.gpl_only	= false,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_CTX,
+	.arg2_type	= ARG_ANYTHING,
+	.arg3_type	= ARG_PTR_TO_UNINIT_MEM,
+	.arg4_type	= ARG_CONST_SIZE,
+};
+
+static int bpf_xdp_frags_increase_tail(struct xdp_buff *xdp, int offset)
+{
+	struct skb_shared_info *sinfo = xdp_get_shared_info_from_buff(xdp);
+	skb_frag_t *frag = &sinfo->frags[sinfo->nr_frags - 1];
+	struct xdp_rxq_info *rxq = xdp->rxq;
+	unsigned int tailroom;
+
+	if (!rxq->frag_size || rxq->frag_size > xdp->frame_sz)
+		return -EOPNOTSUPP;
+
+	tailroom = rxq->frag_size - skb_frag_size(frag) - skb_frag_off(frag);
+	if (unlikely(offset > tailroom))
+		return -EINVAL;
+
+	memset(skb_frag_address(frag) + skb_frag_size(frag), 0, offset);
+	skb_frag_size_add(frag, offset);
+	sinfo->xdp_frags_size += offset;
+
+	return 0;
+}
+
+static int bpf_xdp_frags_shrink_tail(struct xdp_buff *xdp, int offset)
+{
+	struct skb_shared_info *sinfo = xdp_get_shared_info_from_buff(xdp);
+	int i, n_frags_free = 0, len_free = 0;
+
+	if (unlikely(offset > (int)xdp_get_buff_len(xdp) - ETH_HLEN))
+		return -EINVAL;
+
+	for (i = sinfo->nr_frags - 1; i >= 0 && offset > 0; i--) {
+		skb_frag_t *frag = &sinfo->frags[i];
+		int shrink = min_t(int, offset, skb_frag_size(frag));
+
+		len_free += shrink;
+		offset -= shrink;
+
+		if (skb_frag_size(frag) == shrink) {
+			struct page *page = skb_frag_page(frag);
+
+			__xdp_return(page_address(page), &xdp->rxq->mem,
+				     false, NULL);
+			n_frags_free++;
+		} else {
+			skb_frag_size_sub(frag, shrink);
+			break;
+		}
+	}
+	sinfo->nr_frags -= n_frags_free;
+	sinfo->xdp_frags_size -= len_free;
+
+	if (unlikely(!sinfo->nr_frags)) {
+		xdp_buff_clear_frags_flag(xdp);
+		xdp->data_end -= offset;
+	}
+
+	return 0;
+}
+
 BPF_CALL_2(bpf_xdp_adjust_tail, struct xdp_buff *, xdp, int, offset)
 {
 	void *data_hard_end = xdp_data_hard_end(xdp); /* use xdp->frame_sz */
 	void *data_end = xdp->data_end + offset;
 
+	if (unlikely(xdp_buff_has_frags(xdp))) { /* non-linear xdp buff */
+		if (offset < 0)
+			return bpf_xdp_frags_shrink_tail(xdp, -offset);
+
+		return bpf_xdp_frags_increase_tail(xdp, offset);
+	}
+
 	/* Notice that xdp_data_hard_end have reserved some tailroom */
 	if (unlikely(data_end > data_hard_end))
 		return -EINVAL;
@@ -4047,6 +4266,14 @@ int xdp_do_redirect(struct net_device *dev, struct xdp_buff *xdp,
 	struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info);
 	enum bpf_map_type map_type = ri->map_type;
 
+	/* XDP_REDIRECT is not fully supported yet for xdp frags since
+	 * not all XDP capable drivers can map non-linear xdp_frame in
+	 * ndo_xdp_xmit.
+	 */
+	if (unlikely(xdp_buff_has_frags(xdp) &&
+		     map_type != BPF_MAP_TYPE_CPUMAP))
+		return -EOPNOTSUPP;
+
 	if (map_type == BPF_MAP_TYPE_XSKMAP)
 		return __xdp_do_redirect_xsk(ri, dev, xdp, xdp_prog);
 
@@ -4590,10 +4817,12 @@ static const struct bpf_func_proto bpf_sk_ancestor_cgroup_id_proto = {
 };
 #endif
 
-static unsigned long bpf_xdp_copy(void *dst_buff, const void *src_buff,
+static unsigned long bpf_xdp_copy(void *dst, const void *ctx,
 				  unsigned long off, unsigned long len)
 {
-	memcpy(dst_buff, src_buff + off, len);
+	struct xdp_buff *xdp = (struct xdp_buff *)ctx;
+
+	bpf_xdp_copy_buf(xdp, off, dst, len, false);
 	return 0;
 }
 
@@ -4604,11 +4833,11 @@ BPF_CALL_5(bpf_xdp_event_output, struct xdp_buff *, xdp, struct bpf_map *, map,
 
 	if (unlikely(flags & ~(BPF_F_CTXLEN_MASK | BPF_F_INDEX_MASK)))
 		return -EINVAL;
-	if (unlikely(!xdp ||
-		     xdp_size > (unsigned long)(xdp->data_end - xdp->data)))
+
+	if (unlikely(!xdp || xdp_size > xdp_get_buff_len(xdp)))
 		return -EFAULT;
 
-	return bpf_event_output(map, flags, meta, meta_size, xdp->data,
+	return bpf_event_output(map, flags, meta, meta_size, xdp,
 				xdp_size, bpf_xdp_copy);
 }
 
@@ -7533,6 +7762,12 @@ xdp_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_xdp_redirect_map_proto;
 	case BPF_FUNC_xdp_adjust_tail:
 		return &bpf_xdp_adjust_tail_proto;
+	case BPF_FUNC_xdp_get_buff_len:
+		return &bpf_xdp_get_buff_len_proto;
+	case BPF_FUNC_xdp_load_bytes:
+		return &bpf_xdp_load_bytes_proto;
+	case BPF_FUNC_xdp_store_bytes:
+		return &bpf_xdp_store_bytes_proto;
 	case BPF_FUNC_fib_lookup:
 		return &bpf_xdp_fib_lookup_proto;
 	case BPF_FUNC_check_mtu:
@@ -10062,7 +10297,6 @@ const struct bpf_verifier_ops tc_cls_act_verifier_ops = {
 	.convert_ctx_access	= tc_cls_act_convert_ctx_access,
 	.gen_prologue		= tc_cls_act_prologue,
 	.gen_ld_abs		= bpf_gen_ld_abs,
-	.check_kfunc_call	= bpf_prog_test_check_kfunc_call,
 };
 
 const struct bpf_prog_ops tc_cls_act_prog_ops = {
diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c
index a5b5bb99c644..c53d9aab38ab 100644
--- a/net/core/net_namespace.c
+++ b/net/core/net_namespace.c
@@ -301,6 +301,7 @@ struct net *get_net_ns_by_id(const struct net *net, int id)
 
 	return peer;
 }
+EXPORT_SYMBOL_GPL(get_net_ns_by_id);
 
 /*
  * setup_net runs the initializers for the network namespace object.
diff --git a/net/core/sock_map.c b/net/core/sock_map.c
index 1827669eedd6..2d213c4011db 100644
--- a/net/core/sock_map.c
+++ b/net/core/sock_map.c
@@ -1416,38 +1416,50 @@ static struct sk_psock_progs *sock_map_progs(struct bpf_map *map)
 	return NULL;
 }
 
-static int sock_map_prog_update(struct bpf_map *map, struct bpf_prog *prog,
-				struct bpf_prog *old, u32 which)
+static int sock_map_prog_lookup(struct bpf_map *map, struct bpf_prog ***pprog,
+				u32 which)
 {
 	struct sk_psock_progs *progs = sock_map_progs(map);
-	struct bpf_prog **pprog;
 
 	if (!progs)
 		return -EOPNOTSUPP;
 
 	switch (which) {
 	case BPF_SK_MSG_VERDICT:
-		pprog = &progs->msg_parser;
+		*pprog = &progs->msg_parser;
 		break;
 #if IS_ENABLED(CONFIG_BPF_STREAM_PARSER)
 	case BPF_SK_SKB_STREAM_PARSER:
-		pprog = &progs->stream_parser;
+		*pprog = &progs->stream_parser;
 		break;
 #endif
 	case BPF_SK_SKB_STREAM_VERDICT:
 		if (progs->skb_verdict)
 			return -EBUSY;
-		pprog = &progs->stream_verdict;
+		*pprog = &progs->stream_verdict;
 		break;
 	case BPF_SK_SKB_VERDICT:
 		if (progs->stream_verdict)
 			return -EBUSY;
-		pprog = &progs->skb_verdict;
+		*pprog = &progs->skb_verdict;
 		break;
 	default:
 		return -EOPNOTSUPP;
 	}
 
+	return 0;
+}
+
+static int sock_map_prog_update(struct bpf_map *map, struct bpf_prog *prog,
+				struct bpf_prog *old, u32 which)
+{
+	struct bpf_prog **pprog;
+	int ret;
+
+	ret = sock_map_prog_lookup(map, &pprog, which);
+	if (ret)
+		return ret;
+
 	if (old)
 		return psock_replace_prog(pprog, prog, old);
 
@@ -1455,6 +1467,57 @@ static int sock_map_prog_update(struct bpf_map *map, struct bpf_prog *prog,
 	return 0;
 }
 
+int sock_map_bpf_prog_query(const union bpf_attr *attr,
+			    union bpf_attr __user *uattr)
+{
+	__u32 __user *prog_ids = u64_to_user_ptr(attr->query.prog_ids);
+	u32 prog_cnt = 0, flags = 0, ufd = attr->target_fd;
+	struct bpf_prog **pprog;
+	struct bpf_prog *prog;
+	struct bpf_map *map;
+	struct fd f;
+	u32 id = 0;
+	int ret;
+
+	if (attr->query.query_flags)
+		return -EINVAL;
+
+	f = fdget(ufd);
+	map = __bpf_map_get(f);
+	if (IS_ERR(map))
+		return PTR_ERR(map);
+
+	rcu_read_lock();
+
+	ret = sock_map_prog_lookup(map, &pprog, attr->query.attach_type);
+	if (ret)
+		goto end;
+
+	prog = *pprog;
+	prog_cnt = !prog ? 0 : 1;
+
+	if (!attr->query.prog_cnt || !prog_ids || !prog_cnt)
+		goto end;
+
+	/* we do not hold the refcnt, the bpf prog may be released
+	 * asynchronously and the id would be set to 0.
+	 */
+	id = data_race(prog->aux->id);
+	if (id == 0)
+		prog_cnt = 0;
+
+end:
+	rcu_read_unlock();
+
+	if (copy_to_user(&uattr->query.attach_flags, &flags, sizeof(flags)) ||
+	    (id != 0 && copy_to_user(prog_ids, &id, sizeof(u32))) ||
+	    copy_to_user(&uattr->query.prog_cnt, &prog_cnt, sizeof(prog_cnt)))
+		ret = -EFAULT;
+
+	fdput(f);
+	return ret;
+}
+
 static void sock_map_unlink(struct sock *sk, struct sk_psock_link *link)
 {
 	switch (link->map->map_type) {
diff --git a/net/core/xdp.c b/net/core/xdp.c
index 7aba35504986..361df312ee7f 100644
--- a/net/core/xdp.c
+++ b/net/core/xdp.c
@@ -162,8 +162,9 @@ static void xdp_rxq_info_init(struct xdp_rxq_info *xdp_rxq)
 }
 
 /* Returns 0 on success, negative on failure */
-int xdp_rxq_info_reg(struct xdp_rxq_info *xdp_rxq,
-		     struct net_device *dev, u32 queue_index, unsigned int napi_id)
+int __xdp_rxq_info_reg(struct xdp_rxq_info *xdp_rxq,
+		       struct net_device *dev, u32 queue_index,
+		       unsigned int napi_id, u32 frag_size)
 {
 	if (!dev) {
 		WARN(1, "Missing net_device from driver");
@@ -185,11 +186,12 @@ int xdp_rxq_info_reg(struct xdp_rxq_info *xdp_rxq,
 	xdp_rxq->dev = dev;
 	xdp_rxq->queue_index = queue_index;
 	xdp_rxq->napi_id = napi_id;
+	xdp_rxq->frag_size = frag_size;
 
 	xdp_rxq->reg_state = REG_STATE_REGISTERED;
 	return 0;
 }
-EXPORT_SYMBOL_GPL(xdp_rxq_info_reg);
+EXPORT_SYMBOL_GPL(__xdp_rxq_info_reg);
 
 void xdp_rxq_info_unused(struct xdp_rxq_info *xdp_rxq)
 {
@@ -369,8 +371,8 @@ EXPORT_SYMBOL_GPL(xdp_rxq_info_reg_mem_model);
  * is used for those calls sites.  Thus, allowing for faster recycling
  * of xdp_frames/pages in those cases.
  */
-static void __xdp_return(void *data, struct xdp_mem_info *mem, bool napi_direct,
-			 struct xdp_buff *xdp)
+void __xdp_return(void *data, struct xdp_mem_info *mem, bool napi_direct,
+		  struct xdp_buff *xdp)
 {
 	struct xdp_mem_allocator *xa;
 	struct page *page;
@@ -406,12 +408,38 @@ static void __xdp_return(void *data, struct xdp_mem_info *mem, bool napi_direct,
 
 void xdp_return_frame(struct xdp_frame *xdpf)
 {
+	struct skb_shared_info *sinfo;
+	int i;
+
+	if (likely(!xdp_frame_has_frags(xdpf)))
+		goto out;
+
+	sinfo = xdp_get_shared_info_from_frame(xdpf);
+	for (i = 0; i < sinfo->nr_frags; i++) {
+		struct page *page = skb_frag_page(&sinfo->frags[i]);
+
+		__xdp_return(page_address(page), &xdpf->mem, false, NULL);
+	}
+out:
 	__xdp_return(xdpf->data, &xdpf->mem, false, NULL);
 }
 EXPORT_SYMBOL_GPL(xdp_return_frame);
 
 void xdp_return_frame_rx_napi(struct xdp_frame *xdpf)
 {
+	struct skb_shared_info *sinfo;
+	int i;
+
+	if (likely(!xdp_frame_has_frags(xdpf)))
+		goto out;
+
+	sinfo = xdp_get_shared_info_from_frame(xdpf);
+	for (i = 0; i < sinfo->nr_frags; i++) {
+		struct page *page = skb_frag_page(&sinfo->frags[i]);
+
+		__xdp_return(page_address(page), &xdpf->mem, true, NULL);
+	}
+out:
 	__xdp_return(xdpf->data, &xdpf->mem, true, NULL);
 }
 EXPORT_SYMBOL_GPL(xdp_return_frame_rx_napi);
@@ -447,7 +475,7 @@ void xdp_return_frame_bulk(struct xdp_frame *xdpf,
 	struct xdp_mem_allocator *xa;
 
 	if (mem->type != MEM_TYPE_PAGE_POOL) {
-		__xdp_return(xdpf->data, &xdpf->mem, false, NULL);
+		xdp_return_frame(xdpf);
 		return;
 	}
 
@@ -466,12 +494,38 @@ void xdp_return_frame_bulk(struct xdp_frame *xdpf,
 		bq->xa = rhashtable_lookup(mem_id_ht, &mem->id, mem_id_rht_params);
 	}
 
+	if (unlikely(xdp_frame_has_frags(xdpf))) {
+		struct skb_shared_info *sinfo;
+		int i;
+
+		sinfo = xdp_get_shared_info_from_frame(xdpf);
+		for (i = 0; i < sinfo->nr_frags; i++) {
+			skb_frag_t *frag = &sinfo->frags[i];
+
+			bq->q[bq->count++] = skb_frag_address(frag);
+			if (bq->count == XDP_BULK_QUEUE_SIZE)
+				xdp_flush_frame_bulk(bq);
+		}
+	}
 	bq->q[bq->count++] = xdpf->data;
 }
 EXPORT_SYMBOL_GPL(xdp_return_frame_bulk);
 
 void xdp_return_buff(struct xdp_buff *xdp)
 {
+	struct skb_shared_info *sinfo;
+	int i;
+
+	if (likely(!xdp_buff_has_frags(xdp)))
+		goto out;
+
+	sinfo = xdp_get_shared_info_from_buff(xdp);
+	for (i = 0; i < sinfo->nr_frags; i++) {
+		struct page *page = skb_frag_page(&sinfo->frags[i]);
+
+		__xdp_return(page_address(page), &xdp->rxq->mem, true, xdp);
+	}
+out:
 	__xdp_return(xdp->data, &xdp->rxq->mem, true, xdp);
 }
 
@@ -561,8 +615,14 @@ struct sk_buff *__xdp_build_skb_from_frame(struct xdp_frame *xdpf,
 					   struct sk_buff *skb,
 					   struct net_device *dev)
 {
+	struct skb_shared_info *sinfo = xdp_get_shared_info_from_frame(xdpf);
 	unsigned int headroom, frame_size;
 	void *hard_start;
+	u8 nr_frags;
+
+	/* xdp frags frame */
+	if (unlikely(xdp_frame_has_frags(xdpf)))
+		nr_frags = sinfo->nr_frags;
 
 	/* Part of headroom was reserved to xdpf */
 	headroom = sizeof(*xdpf) + xdpf->headroom;
@@ -582,6 +642,12 @@ struct sk_buff *__xdp_build_skb_from_frame(struct xdp_frame *xdpf,
 	if (xdpf->metasize)
 		skb_metadata_set(skb, xdpf->metasize);
 
+	if (unlikely(xdp_frame_has_frags(xdpf)))
+		xdp_update_skb_shared_info(skb, nr_frags,
+					   sinfo->xdp_frags_size,
+					   nr_frags * xdpf->frame_sz,
+					   xdp_frame_is_frag_pfmemalloc(xdpf));
+
 	/* Essential SKB info: protocol and skb->dev */
 	skb->protocol = eth_type_trans(skb, dev);