From: Amery Hung <ameryhung@gmail.com>
To: bpf@vger.kernel.org
Cc: netdev@vger.kernel.org, alexei.starovoitov@gmail.com,
andrii@kernel.org, daniel@iogearbox.net, kuba@kernel.org,
stfomichev@gmail.com, martin.lau@kernel.org,
mohsin.bashr@gmail.com, noren@nvidia.com, dtatulea@nvidia.com,
saeedm@nvidia.com, tariqt@nvidia.com, mbloch@nvidia.com,
maciej.fijalkowski@intel.com, kernel-team@meta.com
Subject: [PATCH bpf-next v2 2/7] bpf: Allow bpf_xdp_shrink_data to shrink a frag from head and tail
Date: Fri, 5 Sep 2025 10:33:46 -0700 [thread overview]
Message-ID: <20250905173352.3759457-3-ameryhung@gmail.com> (raw)
In-Reply-To: <20250905173352.3759457-1-ameryhung@gmail.com>
Move skb_frag_t adjustment into bpf_xdp_shrink_data() and extend its
functionality to be able to shrink an xdp fragment from both head and
tail. In a later patch, bpf_xdp_pull_data() will reuse it to shrink an
xdp fragment from head.
Additionally, in bpf_xdp_frags_shrink_tail(), breaking the loop when
bpf_xdp_shrink_data() returns false (i.e., not releasing the current
fragment) is not necessary as the loop condition, offset > 0, has the
same effect. Remove the else branch to simplify the code.
Signed-off-by: Amery Hung <ameryhung@gmail.com>
---
include/net/xdp_sock_drv.h | 21 ++++++++++++++++++---
net/core/filter.c | 28 +++++++++++++++++-----------
2 files changed, 35 insertions(+), 14 deletions(-)
diff --git a/include/net/xdp_sock_drv.h b/include/net/xdp_sock_drv.h
index 513c8e9704f6..4f2d3268a676 100644
--- a/include/net/xdp_sock_drv.h
+++ b/include/net/xdp_sock_drv.h
@@ -160,13 +160,23 @@ static inline struct xdp_buff *xsk_buff_get_frag(const struct xdp_buff *first)
return ret;
}
-static inline void xsk_buff_del_tail(struct xdp_buff *tail)
+static inline void xsk_buff_del_frag(struct xdp_buff *xdp)
{
- struct xdp_buff_xsk *xskb = container_of(tail, struct xdp_buff_xsk, xdp);
+ struct xdp_buff_xsk *xskb = container_of(xdp, struct xdp_buff_xsk, xdp);
list_del(&xskb->list_node);
}
+static inline struct xdp_buff *xsk_buff_get_head(struct xdp_buff *first)
+{
+ struct xdp_buff_xsk *xskb = container_of(first, struct xdp_buff_xsk, xdp);
+ struct xdp_buff_xsk *frag;
+
+ frag = list_first_entry(&xskb->pool->xskb_list, struct xdp_buff_xsk,
+ list_node);
+ return &frag->xdp;
+}
+
static inline struct xdp_buff *xsk_buff_get_tail(struct xdp_buff *first)
{
struct xdp_buff_xsk *xskb = container_of(first, struct xdp_buff_xsk, xdp);
@@ -389,8 +399,13 @@ static inline struct xdp_buff *xsk_buff_get_frag(const struct xdp_buff *first)
return NULL;
}
-static inline void xsk_buff_del_tail(struct xdp_buff *tail)
+static inline void xsk_buff_del_frag(struct xdp_buff *xdp)
+{
+}
+
+static inline struct xdp_buff *xsk_buff_get_head(struct xdp_buff *first)
{
+ return NULL;
}
static inline struct xdp_buff *xsk_buff_get_tail(struct xdp_buff *first)
diff --git a/net/core/filter.c b/net/core/filter.c
index 63f3baee2daf..0b82cb348ce0 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -4153,27 +4153,31 @@ static int bpf_xdp_frags_increase_tail(struct xdp_buff *xdp, int offset)
return 0;
}
-static void bpf_xdp_shrink_data_zc(struct xdp_buff *xdp, int shrink,
+static void bpf_xdp_shrink_data_zc(struct xdp_buff *xdp, int shrink, bool tail,
enum xdp_mem_type mem_type, bool release)
{
- struct xdp_buff *zc_frag = xsk_buff_get_tail(xdp);
+ struct xdp_buff *zc_frag = tail ? xsk_buff_get_tail(xdp) :
+ xsk_buff_get_head(xdp);
if (release) {
- xsk_buff_del_tail(zc_frag);
+ xsk_buff_del_frag(zc_frag);
__xdp_return(0, mem_type, false, zc_frag);
} else {
- zc_frag->data_end -= shrink;
+ if (tail)
+ zc_frag->data_end -= shrink;
+ else
+ zc_frag->data += shrink;
}
}
static bool bpf_xdp_shrink_data(struct xdp_buff *xdp, skb_frag_t *frag,
- int shrink)
+ int shrink, bool tail)
{
enum xdp_mem_type mem_type = xdp->rxq->mem.type;
bool release = skb_frag_size(frag) == shrink;
if (mem_type == MEM_TYPE_XSK_BUFF_POOL) {
- bpf_xdp_shrink_data_zc(xdp, shrink, mem_type, release);
+ bpf_xdp_shrink_data_zc(xdp, shrink, tail, mem_type, release);
goto out;
}
@@ -4181,6 +4185,12 @@ static bool bpf_xdp_shrink_data(struct xdp_buff *xdp, skb_frag_t *frag,
__xdp_return(skb_frag_netmem(frag), mem_type, false, NULL);
out:
+ if (!release) {
+ if (!tail)
+ skb_frag_off_add(frag, shrink);
+ skb_frag_size_sub(frag, shrink);
+ }
+
return release;
}
@@ -4198,12 +4208,8 @@ static int bpf_xdp_frags_shrink_tail(struct xdp_buff *xdp, int offset)
len_free += shrink;
offset -= shrink;
- if (bpf_xdp_shrink_data(xdp, frag, shrink)) {
+ if (bpf_xdp_shrink_data(xdp, frag, shrink, true))
n_frags_free++;
- } else {
- skb_frag_size_sub(frag, shrink);
- break;
- }
}
sinfo->nr_frags -= n_frags_free;
sinfo->xdp_frags_size -= len_free;
--
2.47.3
next prev parent reply other threads:[~2025-09-05 17:33 UTC|newest]
Thread overview: 16+ messages / expand[flat|nested] mbox.gz Atom feed top
2025-09-05 17:33 [PATCH bpf-next v2 0/7] Add kfunc bpf_xdp_pull_data Amery Hung
2025-09-05 17:33 ` [PATCH bpf-next v2 1/7] net/mlx5e: Fix generating skb from nonlinear xdp_buff Amery Hung
2025-09-08 14:41 ` Dragos Tatulea
2025-09-08 17:23 ` Amery Hung
2025-09-05 17:33 ` Amery Hung [this message]
2025-09-05 17:33 ` [PATCH bpf-next v2 3/7] bpf: Support pulling non-linear xdp data Amery Hung
2025-09-08 19:27 ` Martin KaFai Lau
2025-09-08 22:28 ` Amery Hung
2025-09-09 1:54 ` Jakub Kicinski
2025-09-10 15:17 ` Amery Hung
2025-09-10 18:04 ` Jakub Kicinski
2025-09-10 19:11 ` Amery Hung
2025-09-05 17:33 ` [PATCH bpf-next v2 4/7] bpf: Clear packet pointers after changing packet data in kfuncs Amery Hung
2025-09-05 17:33 ` [PATCH bpf-next v2 5/7] bpf: Support specifying linear xdp packet data size in test_run Amery Hung
2025-09-05 17:33 ` [PATCH bpf-next v2 6/7] selftests/bpf: Test bpf_xdp_pull_data Amery Hung
2025-09-05 17:33 ` [PATCH bpf-next v2 7/7] selftests: drv-net: Pull data before parsing headers Amery Hung
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20250905173352.3759457-3-ameryhung@gmail.com \
--to=ameryhung@gmail.com \
--cc=alexei.starovoitov@gmail.com \
--cc=andrii@kernel.org \
--cc=bpf@vger.kernel.org \
--cc=daniel@iogearbox.net \
--cc=dtatulea@nvidia.com \
--cc=kernel-team@meta.com \
--cc=kuba@kernel.org \
--cc=maciej.fijalkowski@intel.com \
--cc=martin.lau@kernel.org \
--cc=mbloch@nvidia.com \
--cc=mohsin.bashr@gmail.com \
--cc=netdev@vger.kernel.org \
--cc=noren@nvidia.com \
--cc=saeedm@nvidia.com \
--cc=stfomichev@gmail.com \
--cc=tariqt@nvidia.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).