Merge branch 'net-bpf_xdp_adjust_tail-and-intel-mbuf-fixes'

Maciej Fijalkowski says:

====================
net: bpf_xdp_adjust_tail() and Intel mbuf fixes

Hey,

after a break followed by dealing with sickness, here is a v6 that makes
bpf_xdp_adjust_tail() actually usable for ZC drivers that support XDP
multi-buffer. Since v4 I tried also using bpf_xdp_adjust_tail() with
positive offset which exposed yet another issues, which can be observed
by increased commit count when compared to v3.

John, in the end I think we should remove handling
MEM_TYPE_XSK_BUFF_POOL from __xdp_return(), but it is out of the scope
for fixes set, IMHO.

Thanks,
Maciej

v6:
- add acks [Magnus]
- fix spelling mistakes [Magnus]
- avoid touching xdp_buff in xp_alloc_{reused,new_from_fq}() [Magnus]
- s/shrink_data/bpf_xdp_shrink_data [Jakub]
- remove __shrink_data() [Jakub]
- check retvals from __xdp_rxq_info_reg() [Magnus]

v5:
- pick correct version of patch 5 [Simon]
- elaborate a bit more on what patch 2 fixes

v4:
- do not clear frags flag when deleting tail; xsk_buff_pool now does
  that
- skip some NULL tests for xsk_buff_get_tail [Martin, John]
- address problems around registering xdp_rxq_info
- fix bpf_xdp_frags_increase_tail() for ZC mbuf

v3:
- add acks
- s/xsk_buff_tail_del/xsk_buff_del_tail
- address i40e as well (thanks Tirthendu)

v2:
- fix !CONFIG_XDP_SOCKETS builds
- add reviewed-by tag to patch 3
====================

Link: https://lore.kernel.org/r/20240124191602.566724-1-maciej.fijalkowski@intel.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>

3 files changed, 47 insertions, 10 deletions

diff --git a/net/core/filter.c b/net/core/filter.c
index 24061f29c9dd..ef3e78b6a39c 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -83,6 +83,7 @@
 #include <net/netfilter/nf_conntrack_bpf.h>
 #include <net/netkit.h>
 #include <linux/un.h>
+#include <net/xdp_sock_drv.h>
 
 #include "dev.h"
 
@@ -4092,10 +4093,46 @@ static int bpf_xdp_frags_increase_tail(struct xdp_buff *xdp, int offset)
 	memset(skb_frag_address(frag) + skb_frag_size(frag), 0, offset);
 	skb_frag_size_add(frag, offset);
 	sinfo->xdp_frags_size += offset;
+	if (rxq->mem.type == MEM_TYPE_XSK_BUFF_POOL)
+		xsk_buff_get_tail(xdp)->data_end += offset;
 
 	return 0;
 }
 
+static void bpf_xdp_shrink_data_zc(struct xdp_buff *xdp, int shrink,
+				   struct xdp_mem_info *mem_info, bool release)
+{
+	struct xdp_buff *zc_frag = xsk_buff_get_tail(xdp);
+
+	if (release) {
+		xsk_buff_del_tail(zc_frag);
+		__xdp_return(NULL, mem_info, false, zc_frag);
+	} else {
+		zc_frag->data_end -= shrink;
+	}
+}
+
+static bool bpf_xdp_shrink_data(struct xdp_buff *xdp, skb_frag_t *frag,
+				int shrink)
+{
+	struct xdp_mem_info *mem_info = &xdp->rxq->mem;
+	bool release = skb_frag_size(frag) == shrink;
+
+	if (mem_info->type == MEM_TYPE_XSK_BUFF_POOL) {
+		bpf_xdp_shrink_data_zc(xdp, shrink, mem_info, release);
+		goto out;
+	}
+
+	if (release) {
+		struct page *page = skb_frag_page(frag);
+
+		__xdp_return(page_address(page), mem_info, false, NULL);
+	}
+
+out:
+	return release;
+}
+
 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);
@@ -4110,12 +4147,7 @@ static int bpf_xdp_frags_shrink_tail(struct xdp_buff *xdp, int offset)
 
 		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);
+		if (bpf_xdp_shrink_data(xdp, frag, shrink)) {
 			n_frags_free++;
 		} else {
 			skb_frag_size_sub(frag, shrink);
diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c
index 9f13aa3353e3..1eadfac03cc4 100644
--- a/net/xdp/xsk.c
+++ b/net/xdp/xsk.c
@@ -167,8 +167,10 @@ static int xsk_rcv_zc(struct xdp_sock *xs, struct xdp_buff *xdp, u32 len)
 		contd = XDP_PKT_CONTD;
 
 	err = __xsk_rcv_zc(xs, xskb, len, contd);
-	if (err || likely(!frags))
-		goto out;
+	if (err)
+		goto err;
+	if (likely(!frags))
+		return 0;
 
 	xskb_list = &xskb->pool->xskb_list;
 	list_for_each_entry_safe(pos, tmp, xskb_list, xskb_list_node) {
@@ -177,11 +179,13 @@ static int xsk_rcv_zc(struct xdp_sock *xs, struct xdp_buff *xdp, u32 len)
 		len = pos->xdp.data_end - pos->xdp.data;
 		err = __xsk_rcv_zc(xs, pos, len, contd);
 		if (err)
-			return err;
+			goto err;
 		list_del(&pos->xskb_list_node);
 	}
 
-out:
+	return 0;
+err:
+	xsk_buff_free(xdp);
 	return err;
 }
 
diff --git a/net/xdp/xsk_buff_pool.c b/net/xdp/xsk_buff_pool.c
index 28711cc44ced..ce60ecd48a4d 100644
--- a/net/xdp/xsk_buff_pool.c
+++ b/net/xdp/xsk_buff_pool.c
@@ -555,6 +555,7 @@ struct xdp_buff *xp_alloc(struct xsk_buff_pool *pool)
 
 	xskb->xdp.data = xskb->xdp.data_hard_start + XDP_PACKET_HEADROOM;
 	xskb->xdp.data_meta = xskb->xdp.data;
+	xskb->xdp.flags = 0;
 
 	if (pool->dma_need_sync) {
 		dma_sync_single_range_for_device(pool->dev, xskb->dma, 0,