netdev - [PATCH bpf-next v2 3/7] bpf: Support pulling non-linear xdp data

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <20250905173352.3759457-4-ameryhung@gmail.com>
Date: Fri,  5 Sep 2025 10:33:47 -0700
From: Amery Hung <ameryhung@...il.com>
To: bpf@...r.kernel.org
Cc: netdev@...r.kernel.org,
	alexei.starovoitov@...il.com,
	andrii@...nel.org,
	daniel@...earbox.net,
	kuba@...nel.org,
	stfomichev@...il.com,
	martin.lau@...nel.org,
	mohsin.bashr@...il.com,
	noren@...dia.com,
	dtatulea@...dia.com,
	saeedm@...dia.com,
	tariqt@...dia.com,
	mbloch@...dia.com,
	maciej.fijalkowski@...el.com,
	kernel-team@...a.com
Subject: [PATCH bpf-next v2 3/7] bpf: Support pulling non-linear xdp data

Add kfunc, bpf_xdp_pull_data(), to support pulling data from xdp
fragments. Similar to bpf_skb_pull_data(), bpf_xdp_pull_data() makes
the first len bytes of data directly readable and writable in bpf
programs. If the "len" argument is larger than the linear data size,
data in fragments will be copied to the linear region when there
is enough room between xdp->data_end and xdp_data_hard_end(xdp),
which is subject to driver implementation.

A use case of the kfunc is to decapsulate headers residing in xdp
fragments. It is possible for a NIC driver to place headers in xdp
fragments. To keep using direct packet access for parsing and
decapsulating headers, users can pull headers into the linear data
area by calling bpf_xdp_pull_data() and then pop the header with
bpf_xdp_adjust_head().

An unused argument, flags is reserved for future extension (e.g.,
tossing the data instead of copying it to the linear data area).

Signed-off-by: Amery Hung <ameryhung@...il.com>
---
 net/core/filter.c | 76 +++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 76 insertions(+)

diff --git a/net/core/filter.c b/net/core/filter.c
index 0b82cb348ce0..0b161106debd 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -12212,6 +12212,81 @@ __bpf_kfunc int bpf_sock_ops_enable_tx_tstamp(struct bpf_sock_ops_kern *skops,
 	return 0;
 }
 
+/**
+ * bpf_xdp_pull_data() - Pull in non-linear xdp data.
+ * @x: &xdp_md associated with the XDP buffer
+ * @len: length of data to be made directly accessible in the linear part
+ * @flags: future use, must be zero
+ *
+ * Pull in non-linear data in case the XDP buffer associated with @x is
+ * non-linear and not all @len are in the linear data area.
+ *
+ * Direct packet access allows reading and writing linear XDP data through
+ * packet pointers (i.e., &xdp_md->data + offsets). When an eBPF program wants
+ * to directly access data that may be in the non-linear area, call this kfunc
+ * to make sure the data is available in the linear area.
+ *
+ * This kfunc can also be used with bpf_xdp_adjust_head() to decapsulate
+ * headers in the non-linear data area.
+ *
+ * A call to this kfunc is susceptible to change the underlying packet buffer.
+ * Therefore, at load time, all checks on pointers previously done by the
+ * verifier are invalidated and must be performed again, if the kfunc is used
+ * in combination with direct packet access.
+ *
+ * Return:
+ * * %0         - success
+ * * %-EINVAL   - invalid len or flags
+ */
+__bpf_kfunc int bpf_xdp_pull_data(struct xdp_md *x, u32 len, u64 flags)
+{
+	struct xdp_buff *xdp = (struct xdp_buff *)x;
+	struct skb_shared_info *sinfo = xdp_get_shared_info_from_buff(xdp);
+	void *data_hard_end = xdp_data_hard_end(xdp);
+	void *data_end = xdp->data + len;
+	int i, delta, n_frags_free = 0, len_free = 0;
+
+	if (flags)
+		return -EINVAL;
+
+	if (unlikely(len > xdp_get_buff_len(xdp)))
+		return -EINVAL;
+
+	if (unlikely(data_end < xdp->data || data_end > data_hard_end))
+		return -EINVAL;
+
+	delta = data_end - xdp->data_end;
+	if (delta <= 0)
+		return 0;
+
+	for (i = 0; i < sinfo->nr_frags && delta; i++) {
+		skb_frag_t *frag = &sinfo->frags[i];
+		u32 shrink = min_t(u32, delta, skb_frag_size(frag));
+
+		memcpy(xdp->data_end + len_free, skb_frag_address(frag), shrink);
+
+		len_free += shrink;
+		delta -= shrink;
+		if (bpf_xdp_shrink_data(xdp, frag, shrink, false))
+			n_frags_free++;
+	}
+
+	if (unlikely(n_frags_free)) {
+		memmove(sinfo->frags, sinfo->frags + n_frags_free,
+			(sinfo->nr_frags - n_frags_free) * sizeof(skb_frag_t));
+
+		sinfo->nr_frags -= n_frags_free;
+
+		if (!sinfo->nr_frags)
+			xdp_buff_clear_frags_flag(xdp);
+	}
+
+	sinfo->xdp_frags_size -= len_free;
+	xdp->data_end = data_end;
+
+	return 0;
+}
+
 __bpf_kfunc_end_defs();
 
 int bpf_dynptr_from_skb_rdonly(struct __sk_buff *skb, u64 flags,
@@ -12239,6 +12314,7 @@ BTF_KFUNCS_END(bpf_kfunc_check_set_skb_meta)
 
 BTF_KFUNCS_START(bpf_kfunc_check_set_xdp)
 BTF_ID_FLAGS(func, bpf_dynptr_from_xdp)
+BTF_ID_FLAGS(func, bpf_xdp_pull_data)
 BTF_KFUNCS_END(bpf_kfunc_check_set_xdp)
 
 BTF_KFUNCS_START(bpf_kfunc_check_set_sock_addr)
-- 
2.47.3