diff mbox series

[v9,net-next,3/4] xdp: add multi-buff support for xdp running in generic mode

Message ID 1044d6412b1c3e95b40d34993fd5f37cd2f319fd.1707729884.git.lorenzo@kernel.org (mailing list archive)
State Accepted
Commit e6d5dbdd20aa6a86974af51deb9414cd2e7794cb
Delegated to: Netdev Maintainers
Headers show
Series add multi-buff support for xdp running in generic mode | expand

Checks

Context Check Description
netdev/series_format success Posting correctly formatted
netdev/tree_selection success Clearly marked for net-next, async
netdev/ynl success Generated files up to date; no warnings/errors; no diff in generated;
netdev/fixes_present success Fixes tag not required for -next series
netdev/header_inline success No static functions without inline keyword in header files
netdev/build_32bit success Errors and warnings before: 6001 this patch: 6001
netdev/build_tools success Errors and warnings before: 0 this patch: 0
netdev/cc_maintainers warning 3 maintainers not CCed: ast@kernel.org daniel@iogearbox.net john.fastabend@gmail.com
netdev/build_clang success Errors and warnings before: 2130 this patch: 2130
netdev/verify_signedoff success Signed-off-by tag matches author and committer
netdev/deprecated_api success None detected
netdev/check_selftest success No net selftest shell script
netdev/verify_fixes success No Fixes tag
netdev/build_allmodconfig_warn success Errors and warnings before: 6317 this patch: 6317
netdev/checkpatch success total: 0 errors, 0 warnings, 0 checks, 221 lines checked
netdev/build_clang_rust success No Rust files in patch. Skipping build
netdev/kdoc success Errors and warnings before: 0 this patch: 0
netdev/source_inline success Was 0 now: 0
netdev/contest success net-next-2024-02-13--21-00 (tests: 1437)

Commit Message

Lorenzo Bianconi Feb. 12, 2024, 9:50 a.m. UTC
Similar to native xdp, do not always linearize the skb in
netif_receive_generic_xdp routine but create a non-linear xdp_buff to be
processed by the eBPF program. This allow to add multi-buffer support
for xdp running in generic mode.

Acked-by: Jesper Dangaard Brouer <hawk@kernel.org>
Reviewed-by: Toke Hoiland-Jorgensen <toke@redhat.com>
Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
---
 include/linux/skbuff.h |  2 +
 net/core/dev.c         | 70 +++++++++++++++++++++++---------
 net/core/skbuff.c      | 91 ++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 144 insertions(+), 19 deletions(-)

Comments

Julian Wiedmann Feb. 17, 2024, 10:07 a.m. UTC | #1
On 12.02.24 11:50, Lorenzo Bianconi wrote:
> Similar to native xdp, do not always linearize the skb in
> netif_receive_generic_xdp routine but create a non-linear xdp_buff to be
> processed by the eBPF program. This allow to add multi-buffer support
> for xdp running in generic mode.
> 
> Acked-by: Jesper Dangaard Brouer <hawk@kernel.org>
> Reviewed-by: Toke Hoiland-Jorgensen <toke@redhat.com>
> Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
> ---
>  include/linux/skbuff.h |  2 +
>  net/core/dev.c         | 70 +++++++++++++++++++++++---------
>  net/core/skbuff.c      | 91 ++++++++++++++++++++++++++++++++++++++++++
>  3 files changed, 144 insertions(+), 19 deletions(-)
> 

[...]

> diff --git a/net/core/skbuff.c b/net/core/skbuff.c
> index 9e5eb47b4025..bdb94749f05d 100644
> --- a/net/core/skbuff.c
> +++ b/net/core/skbuff.c
> @@ -895,6 +895,97 @@ static bool is_pp_page(struct page *page)
>  	return (page->pp_magic & ~0x3UL) == PP_SIGNATURE;
>  }
>  
> +static int skb_pp_cow_data(struct page_pool *pool, struct sk_buff **pskb,
> +			   unsigned int headroom)
> +{
> +#if IS_ENABLED(CONFIG_PAGE_POOL)
> +	u32 size, truesize, len, max_head_size, off;
> +	struct sk_buff *skb = *pskb, *nskb;
> +	int err, i, head_off;
> +	void *data;
> +
> +	/* XDP does not support fraglist so we need to linearize
> +	 * the skb.
> +	 */
> +	if (skb_has_frag_list(skb))
> +		return -EOPNOTSUPP;
> +
> +	max_head_size = SKB_WITH_OVERHEAD(PAGE_SIZE - headroom);
> +	if (skb->len > max_head_size + MAX_SKB_FRAGS * PAGE_SIZE)
> +		return -ENOMEM;
> +
> +	size = min_t(u32, skb->len, max_head_size);
> +	truesize = SKB_HEAD_ALIGN(size) + headroom;
> +	data = page_pool_dev_alloc_va(pool, &truesize);
> +	if (!data)
> +		return -ENOMEM;
> +
> +	nskb = napi_build_skb(data, truesize);
> +	if (!nskb) {
> +		page_pool_free_va(pool, data, true);
> +		return -ENOMEM;
> +	}
> +
> +	skb_reserve(nskb, headroom);
> +	skb_copy_header(nskb, skb);
> +	skb_mark_for_recycle(nskb);
> +
> +	err = skb_copy_bits(skb, 0, nskb->data, size);
> +	if (err) {
> +		consume_skb(nskb);
> +		return err;
> +	}
> +	skb_put(nskb, size);
> +
> +	head_off = skb_headroom(nskb) - skb_headroom(skb);
> +	skb_headers_offset_update(nskb, head_off);
> +
> +	off = size;
> +	len = skb->len - off;
> +	for (i = 0; i < MAX_SKB_FRAGS && off < skb->len; i++) {
> +		struct page *page;
> +		u32 page_off;
> +
> +		size = min_t(u32, len, PAGE_SIZE);
> +		truesize = size;
> +
> +		page = page_pool_dev_alloc(pool, &page_off, &truesize);
> +		if (!data) {
> +			consume_skb(nskb);
> +			return -ENOMEM;
> +		}
> +

This should check for !page instead, no?

(picked up as CID 1583654 by the coverity scan for linux-next)
Lorenzo Bianconi Feb. 17, 2024, 10:34 a.m. UTC | #2
[...]
> > +	nskb = napi_build_skb(data, truesize);
> > +	if (!nskb) {
> > +		page_pool_free_va(pool, data, true);
> > +		return -ENOMEM;
> > +	}
> > +
> > +	skb_reserve(nskb, headroom);
> > +	skb_copy_header(nskb, skb);
> > +	skb_mark_for_recycle(nskb);
> > +
> > +	err = skb_copy_bits(skb, 0, nskb->data, size);
> > +	if (err) {
> > +		consume_skb(nskb);
> > +		return err;
> > +	}
> > +	skb_put(nskb, size);
> > +
> > +	head_off = skb_headroom(nskb) - skb_headroom(skb);
> > +	skb_headers_offset_update(nskb, head_off);
> > +
> > +	off = size;
> > +	len = skb->len - off;
> > +	for (i = 0; i < MAX_SKB_FRAGS && off < skb->len; i++) {
> > +		struct page *page;
> > +		u32 page_off;
> > +
> > +		size = min_t(u32, len, PAGE_SIZE);
> > +		truesize = size;
> > +
> > +		page = page_pool_dev_alloc(pool, &page_off, &truesize);
> > +		if (!data) {

ack, right. I will post a fix, thx for reporting the issue.

Regards,
Lorenzo

> > +			consume_skb(nskb);
> > +			return -ENOMEM;
> > +		}
> > +
> 
> This should check for !page instead, no?
> 
> (picked up as CID 1583654 by the coverity scan for linux-next)
>
diff mbox series

Patch

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 2dde34c29203..def3d8689c3d 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -3446,6 +3446,8 @@  static inline void skb_frag_ref(struct sk_buff *skb, int f)
 	__skb_frag_ref(&skb_shinfo(skb)->frags[f]);
 }
 
+int skb_cow_data_for_xdp(struct page_pool *pool, struct sk_buff **pskb,
+			 struct bpf_prog *prog);
 bool napi_pp_put_page(struct page *page, bool napi_safe);
 
 static inline void
diff --git a/net/core/dev.c b/net/core/dev.c
index 1482c3058fc2..97de7700d3cb 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -4874,6 +4874,12 @@  u32 bpf_prog_run_generic_xdp(struct sk_buff *skb, struct xdp_buff *xdp,
 	xdp_init_buff(xdp, frame_sz, &rxqueue->xdp_rxq);
 	xdp_prepare_buff(xdp, hard_start, skb_headroom(skb) - mac_len,
 			 skb_headlen(skb) + mac_len, true);
+	if (skb_is_nonlinear(skb)) {
+		skb_shinfo(skb)->xdp_frags_size = skb->data_len;
+		xdp_buff_set_frags_flag(xdp);
+	} else {
+		xdp_buff_clear_frags_flag(xdp);
+	}
 
 	orig_data_end = xdp->data_end;
 	orig_data = xdp->data;
@@ -4903,6 +4909,14 @@  u32 bpf_prog_run_generic_xdp(struct sk_buff *skb, struct xdp_buff *xdp,
 		skb->len += off; /* positive on grow, negative on shrink */
 	}
 
+	/* XDP frag metadata (e.g. nr_frags) are updated in eBPF helpers
+	 * (e.g. bpf_xdp_adjust_tail), we need to update data_len here.
+	 */
+	if (xdp_buff_has_frags(xdp))
+		skb->data_len = skb_shinfo(skb)->xdp_frags_size;
+	else
+		skb->data_len = 0;
+
 	/* check if XDP changed eth hdr such SKB needs update */
 	eth = (struct ethhdr *)xdp->data;
 	if ((orig_eth_type != eth->h_proto) ||
@@ -4936,12 +4950,35 @@  u32 bpf_prog_run_generic_xdp(struct sk_buff *skb, struct xdp_buff *xdp,
 	return act;
 }
 
+static int
+netif_skb_check_for_xdp(struct sk_buff **pskb, struct bpf_prog *prog)
+{
+	struct sk_buff *skb = *pskb;
+	int err, hroom, troom;
+
+	if (!skb_cow_data_for_xdp(this_cpu_read(system_page_pool), pskb, prog))
+		return 0;
+
+	/* In case we have to go down the path and also linearize,
+	 * then lets do the pskb_expand_head() work just once here.
+	 */
+	hroom = XDP_PACKET_HEADROOM - skb_headroom(skb);
+	troom = skb->tail + skb->data_len - skb->end;
+	err = pskb_expand_head(skb,
+			       hroom > 0 ? ALIGN(hroom, NET_SKB_PAD) : 0,
+			       troom > 0 ? troom + 128 : 0, GFP_ATOMIC);
+	if (err)
+		return err;
+
+	return skb_linearize(skb);
+}
+
 static u32 netif_receive_generic_xdp(struct sk_buff **pskb,
 				     struct xdp_buff *xdp,
 				     struct bpf_prog *xdp_prog)
 {
 	struct sk_buff *skb = *pskb;
-	u32 act = XDP_DROP;
+	u32 mac_len, act = XDP_DROP;
 
 	/* Reinjected packets coming from act_mirred or similar should
 	 * not get XDP generic processing.
@@ -4949,41 +4986,36 @@  static u32 netif_receive_generic_xdp(struct sk_buff **pskb,
 	if (skb_is_redirected(skb))
 		return XDP_PASS;
 
-	/* XDP packets must be linear and must have sufficient headroom
-	 * of XDP_PACKET_HEADROOM bytes. This is the guarantee that also
-	 * native XDP provides, thus we need to do it here as well.
+	/* XDP packets must have sufficient headroom of XDP_PACKET_HEADROOM
+	 * bytes. This is the guarantee that also native XDP provides,
+	 * thus we need to do it here as well.
 	 */
+	mac_len = skb->data - skb_mac_header(skb);
+	__skb_push(skb, mac_len);
+
 	if (skb_cloned(skb) || skb_is_nonlinear(skb) ||
 	    skb_headroom(skb) < XDP_PACKET_HEADROOM) {
-		int hroom = XDP_PACKET_HEADROOM - skb_headroom(skb);
-		int troom = skb->tail + skb->data_len - skb->end;
-
-		/* In case we have to go down the path and also linearize,
-		 * then lets do the pskb_expand_head() work just once here.
-		 */
-		if (pskb_expand_head(skb,
-				     hroom > 0 ? ALIGN(hroom, NET_SKB_PAD) : 0,
-				     troom > 0 ? troom + 128 : 0, GFP_ATOMIC))
-			goto do_drop;
-		if (skb_linearize(skb))
+		if (netif_skb_check_for_xdp(pskb, xdp_prog))
 			goto do_drop;
 	}
 
-	act = bpf_prog_run_generic_xdp(skb, xdp, xdp_prog);
+	__skb_pull(*pskb, mac_len);
+
+	act = bpf_prog_run_generic_xdp(*pskb, xdp, xdp_prog);
 	switch (act) {
 	case XDP_REDIRECT:
 	case XDP_TX:
 	case XDP_PASS:
 		break;
 	default:
-		bpf_warn_invalid_xdp_action(skb->dev, xdp_prog, act);
+		bpf_warn_invalid_xdp_action((*pskb)->dev, xdp_prog, act);
 		fallthrough;
 	case XDP_ABORTED:
-		trace_xdp_exception(skb->dev, xdp_prog, act);
+		trace_xdp_exception((*pskb)->dev, xdp_prog, act);
 		fallthrough;
 	case XDP_DROP:
 	do_drop:
-		kfree_skb(skb);
+		kfree_skb(*pskb);
 		break;
 	}
 
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 9e5eb47b4025..bdb94749f05d 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -895,6 +895,97 @@  static bool is_pp_page(struct page *page)
 	return (page->pp_magic & ~0x3UL) == PP_SIGNATURE;
 }
 
+static int skb_pp_cow_data(struct page_pool *pool, struct sk_buff **pskb,
+			   unsigned int headroom)
+{
+#if IS_ENABLED(CONFIG_PAGE_POOL)
+	u32 size, truesize, len, max_head_size, off;
+	struct sk_buff *skb = *pskb, *nskb;
+	int err, i, head_off;
+	void *data;
+
+	/* XDP does not support fraglist so we need to linearize
+	 * the skb.
+	 */
+	if (skb_has_frag_list(skb))
+		return -EOPNOTSUPP;
+
+	max_head_size = SKB_WITH_OVERHEAD(PAGE_SIZE - headroom);
+	if (skb->len > max_head_size + MAX_SKB_FRAGS * PAGE_SIZE)
+		return -ENOMEM;
+
+	size = min_t(u32, skb->len, max_head_size);
+	truesize = SKB_HEAD_ALIGN(size) + headroom;
+	data = page_pool_dev_alloc_va(pool, &truesize);
+	if (!data)
+		return -ENOMEM;
+
+	nskb = napi_build_skb(data, truesize);
+	if (!nskb) {
+		page_pool_free_va(pool, data, true);
+		return -ENOMEM;
+	}
+
+	skb_reserve(nskb, headroom);
+	skb_copy_header(nskb, skb);
+	skb_mark_for_recycle(nskb);
+
+	err = skb_copy_bits(skb, 0, nskb->data, size);
+	if (err) {
+		consume_skb(nskb);
+		return err;
+	}
+	skb_put(nskb, size);
+
+	head_off = skb_headroom(nskb) - skb_headroom(skb);
+	skb_headers_offset_update(nskb, head_off);
+
+	off = size;
+	len = skb->len - off;
+	for (i = 0; i < MAX_SKB_FRAGS && off < skb->len; i++) {
+		struct page *page;
+		u32 page_off;
+
+		size = min_t(u32, len, PAGE_SIZE);
+		truesize = size;
+
+		page = page_pool_dev_alloc(pool, &page_off, &truesize);
+		if (!data) {
+			consume_skb(nskb);
+			return -ENOMEM;
+		}
+
+		skb_add_rx_frag(nskb, i, page, page_off, size, truesize);
+		err = skb_copy_bits(skb, off, page_address(page) + page_off,
+				    size);
+		if (err) {
+			consume_skb(nskb);
+			return err;
+		}
+
+		len -= size;
+		off += size;
+	}
+
+	consume_skb(skb);
+	*pskb = nskb;
+
+	return 0;
+#else
+	return -EOPNOTSUPP;
+#endif
+}
+
+int skb_cow_data_for_xdp(struct page_pool *pool, struct sk_buff **pskb,
+			 struct bpf_prog *prog)
+{
+	if (!prog->aux->xdp_has_frags)
+		return -EINVAL;
+
+	return skb_pp_cow_data(pool, pskb, XDP_PACKET_HEADROOM);
+}
+EXPORT_SYMBOL(skb_cow_data_for_xdp);
+
 #if IS_ENABLED(CONFIG_PAGE_POOL)
 bool napi_pp_put_page(struct page *page, bool napi_safe)
 {