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,
martin.lau@kernel.org, mohsin.bashr@gmail.com, saeedm@nvidia.com,
tariqt@nvidia.com, mbloch@nvidia.com,
maciej.fijalkowski@intel.com, kernel-team@meta.com
Subject: [RFC bpf-next v1 7/7] selftests: drv-net: Pull data before parsing headers
Date: Mon, 25 Aug 2025 12:39:18 -0700 [thread overview]
Message-ID: <20250825193918.3445531-8-ameryhung@gmail.com> (raw)
In-Reply-To: <20250825193918.3445531-1-ameryhung@gmail.com>
It is possible for drivers to generate xdp packets with data residing
entirely in fragments. To keep parsing headers using direcy packet
access, call bpf_xdp_pull_data() to pull headers into the linear data
area.
Signed-off-by: Amery Hung <ameryhung@gmail.com>
---
.../selftests/net/lib/xdp_native.bpf.c | 90 +++++++++++++++----
1 file changed, 75 insertions(+), 15 deletions(-)
diff --git a/tools/testing/selftests/net/lib/xdp_native.bpf.c b/tools/testing/selftests/net/lib/xdp_native.bpf.c
index 521ba38f2ddd..68b2a08055ce 100644
--- a/tools/testing/selftests/net/lib/xdp_native.bpf.c
+++ b/tools/testing/selftests/net/lib/xdp_native.bpf.c
@@ -14,6 +14,9 @@
#define MAX_PAYLOAD_LEN 5000
#define MAX_HDR_LEN 64
+extern int bpf_xdp_pull_data(struct xdp_md *xdp, __u32 len,
+ __u64 flags) __ksym __weak;
+
enum {
XDP_MODE = 0,
XDP_PORT = 1,
@@ -68,30 +71,57 @@ static void record_stats(struct xdp_md *ctx, __u32 stat_type)
static struct udphdr *filter_udphdr(struct xdp_md *ctx, __u16 port)
{
- void *data_end = (void *)(long)ctx->data_end;
- void *data = (void *)(long)ctx->data;
struct udphdr *udph = NULL;
- struct ethhdr *eth = data;
+ void *data, *data_end;
+ struct ethhdr *eth;
+ int err;
+
+ err = bpf_xdp_pull_data(ctx, sizeof(*eth), 0);
+ if (err)
+ return NULL;
+
+ data_end = (void *)(long)ctx->data_end;
+ data = eth = (void *)(long)ctx->data;
if (data + sizeof(*eth) > data_end)
return NULL;
if (eth->h_proto == bpf_htons(ETH_P_IP)) {
- struct iphdr *iph = data + sizeof(*eth);
+ struct iphdr *iph;
+
+ err = bpf_xdp_pull_data(ctx, sizeof(*eth) + sizeof(*iph) +
+ sizeof(*udph), 0);
+ if (err)
+ return NULL;
+
+ data_end = (void *)(long)ctx->data_end;
+ data = (void *)(long)ctx->data;
+
+ iph = data + sizeof(*eth);
if (iph + 1 > (struct iphdr *)data_end ||
iph->protocol != IPPROTO_UDP)
return NULL;
- udph = (void *)eth + sizeof(*iph) + sizeof(*eth);
- } else if (eth->h_proto == bpf_htons(ETH_P_IPV6)) {
- struct ipv6hdr *ipv6h = data + sizeof(*eth);
+ udph = data + sizeof(*iph) + sizeof(*eth);
+ } else if (eth->h_proto == bpf_htons(ETH_P_IPV6)) {
+ struct ipv6hdr *ipv6h;
+
+ err = bpf_xdp_pull_data(ctx, sizeof(*eth) + sizeof(*ipv6h) +
+ sizeof(*udph), 0);
+ if (err)
+ return NULL;
+
+ data_end = (void *)(long)ctx->data_end;
+ data = (void *)(long)ctx->data;
+
+ ipv6h = data + sizeof(*eth);
if (ipv6h + 1 > (struct ipv6hdr *)data_end ||
ipv6h->nexthdr != IPPROTO_UDP)
return NULL;
- udph = (void *)eth + sizeof(*ipv6h) + sizeof(*eth);
+ udph = data + sizeof(*ipv6h) + sizeof(*eth);
} else {
return NULL;
}
@@ -145,17 +175,34 @@ static void swap_machdr(void *data)
static int xdp_mode_tx_handler(struct xdp_md *ctx, __u16 port)
{
- void *data_end = (void *)(long)ctx->data_end;
- void *data = (void *)(long)ctx->data;
struct udphdr *udph = NULL;
- struct ethhdr *eth = data;
+ void *data, *data_end;
+ struct ethhdr *eth;
+ int err;
+
+ err = bpf_xdp_pull_data(ctx, sizeof(*eth), 0);
+ if (err)
+ return XDP_PASS;
+
+ data_end = (void *)(long)ctx->data_end;
+ data = eth = (void *)(long)ctx->data;
if (data + sizeof(*eth) > data_end)
return XDP_PASS;
if (eth->h_proto == bpf_htons(ETH_P_IP)) {
- struct iphdr *iph = data + sizeof(*eth);
- __be32 tmp_ip = iph->saddr;
+ struct iphdr *iph;
+ __be32 tmp_ip;
+
+ err = bpf_xdp_pull_data(ctx, sizeof(*eth) + sizeof(*iph) +
+ sizeof(*udph), 0);
+ if (err)
+ return XDP_PASS;
+
+ data_end = (void *)(long)ctx->data_end;
+ data = (void *)(long)ctx->data;
+
+ iph = data + sizeof(*eth);
if (iph + 1 > (struct iphdr *)data_end ||
iph->protocol != IPPROTO_UDP)
@@ -169,8 +216,10 @@ static int xdp_mode_tx_handler(struct xdp_md *ctx, __u16 port)
return XDP_PASS;
record_stats(ctx, STATS_RX);
+ eth = data;
swap_machdr((void *)eth);
+ tmp_ip = iph->saddr;
iph->saddr = iph->daddr;
iph->daddr = tmp_ip;
@@ -178,9 +227,19 @@ static int xdp_mode_tx_handler(struct xdp_md *ctx, __u16 port)
return XDP_TX;
- } else if (eth->h_proto == bpf_htons(ETH_P_IPV6)) {
- struct ipv6hdr *ipv6h = data + sizeof(*eth);
+ } else if (eth->h_proto == bpf_htons(ETH_P_IPV6)) {
struct in6_addr tmp_ipv6;
+ struct ipv6hdr *ipv6h;
+
+ err = bpf_xdp_pull_data(ctx, sizeof(*eth) + sizeof(*ipv6h) +
+ sizeof(*udph), 0);
+ if (err)
+ return XDP_PASS;
+
+ data_end = (void *)(long)ctx->data_end;
+ data = (void *)(long)ctx->data;
+
+ ipv6h = data + sizeof(*eth);
if (ipv6h + 1 > (struct ipv6hdr *)data_end ||
ipv6h->nexthdr != IPPROTO_UDP)
@@ -194,6 +253,7 @@ static int xdp_mode_tx_handler(struct xdp_md *ctx, __u16 port)
return XDP_PASS;
record_stats(ctx, STATS_RX);
+ eth = data;
swap_machdr((void *)eth);
__builtin_memcpy(&tmp_ipv6, &ipv6h->saddr, sizeof(tmp_ipv6));
--
2.47.3
next prev parent reply other threads:[~2025-08-25 19:39 UTC|newest]
Thread overview: 31+ messages / expand[flat|nested] mbox.gz Atom feed top
2025-08-25 19:39 [RFC bpf-next v1 0/7] Add kfunc bpf_xdp_pull_data Amery Hung
2025-08-25 19:39 ` [RFC bpf-next v1 1/7] net/mlx5e: Fix generating skb from nonlinear xdp_buff Amery Hung
2025-08-27 13:45 ` Dragos Tatulea
2025-08-28 3:44 ` Amery Hung
2025-08-28 16:23 ` Dragos Tatulea
2025-08-28 13:41 ` Nimrod Oren
2025-08-25 19:39 ` [RFC bpf-next v1 2/7] bpf: Allow bpf_xdp_shrink_data to shrink a frag from head and tail Amery Hung
2025-08-28 13:43 ` Nimrod Oren
2025-08-25 19:39 ` [RFC bpf-next v1 3/7] bpf: Support pulling non-linear xdp data Amery Hung
2025-08-25 21:29 ` Stanislav Fomichev
2025-08-25 22:23 ` Amery Hung
2025-08-25 22:29 ` Jakub Kicinski
2025-08-25 22:36 ` Amery Hung
2025-08-25 22:46 ` Stanislav Fomichev
2025-08-25 22:58 ` Jakub Kicinski
2025-08-26 0:12 ` Stanislav Fomichev
2025-08-26 0:30 ` Jakub Kicinski
2025-08-25 22:39 ` Jakub Kicinski
2025-08-26 5:12 ` Amery Hung
2025-08-26 13:20 ` Jakub Kicinski
2025-08-26 13:44 ` Amery Hung
2025-08-25 19:39 ` [RFC bpf-next v1 4/7] bpf: Clear packet pointers after changing packet data in kfuncs Amery Hung
2025-08-25 19:39 ` [RFC bpf-next v1 5/7] bpf: Support specifying linear xdp packet data size in test_run Amery Hung
2025-08-25 19:39 ` [RFC bpf-next v1 6/7] selftests/bpf: Test bpf_xdp_pull_data Amery Hung
2025-08-25 19:39 ` Amery Hung [this message]
2025-08-25 22:41 ` [RFC bpf-next v1 0/7] Add kfunc bpf_xdp_pull_data Jakub Kicinski
2025-08-26 19:38 ` Gal Pressman
2025-08-28 13:39 ` Nimrod Oren
2025-08-29 7:26 ` Amery Hung
2025-08-30 0:09 ` Jakub Kicinski
2025-08-29 18:21 ` Martin KaFai Lau
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=20250825193918.3445531-8-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=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=saeedm@nvidia.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).