| 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
| ||
|
Message-Id: <25997f03a1cea18f29bc41ba991d1c411ea3f0ab.1628854454.git.lorenzo@kernel.org>
Date: Fri, 13 Aug 2021 13:47:51 +0200
From: Lorenzo Bianconi <lorenzo@...nel.org>
To: bpf@...r.kernel.org, netdev@...r.kernel.org
Cc: lorenzo.bianconi@...hat.com, davem@...emloft.net, kuba@...nel.org,
ast@...nel.org, daniel@...earbox.net, shayagr@...zon.com,
john.fastabend@...il.com, dsahern@...nel.org, brouer@...hat.com,
echaudro@...hat.com, jasowang@...hat.com,
alexander.duyck@...il.com, saeed@...nel.org,
maciej.fijalkowski@...el.com, magnus.karlsson@...el.com,
tirthendu.sarkar@...el.com, toke@...hat.com
Subject: [PATCH v11 bpf-next 10/18] bpf: add multi-buff support to the bpf_xdp_adjust_tail() API
From: Eelco Chaudron <echaudro@...hat.com>
This change adds support for tail growing and shrinking for XDP multi-buff.
When called on a multi-buffer packet with a grow request, it will always
work on the last fragment of the packet. So the maximum grow size is the
last fragments tailroom, i.e. no new buffer will be allocated.
When shrinking, it will work from the last fragment, all the way down to
the base buffer depending on the shrinking size. It's important to mention
that once you shrink down the fragment(s) are freed, so you can not grow
again to the original size.
Co-developed-by: Lorenzo Bianconi <lorenzo@...nel.org>
Signed-off-by: Lorenzo Bianconi <lorenzo@...nel.org>
Signed-off-by: Eelco Chaudron <echaudro@...hat.com>
---
include/net/xdp.h | 9 +++++++
net/core/filter.c | 60 +++++++++++++++++++++++++++++++++++++++++++++++
net/core/xdp.c | 5 ++--
3 files changed, 72 insertions(+), 2 deletions(-)
diff --git a/include/net/xdp.h b/include/net/xdp.h
index d66e9877d773..cdaecf8d4d61 100644
--- a/include/net/xdp.h
+++ b/include/net/xdp.h
@@ -145,6 +145,13 @@ xdp_get_shared_info_from_buff(struct xdp_buff *xdp)
return (struct skb_shared_info *)xdp_data_hard_end(xdp);
}
+static inline unsigned int xdp_get_frag_tailroom(const skb_frag_t *frag)
+{
+ struct page *page = skb_frag_page(frag);
+
+ return page_size(page) - skb_frag_size(frag) - skb_frag_off(frag);
+}
+
struct xdp_frame {
void *data;
u16 len;
@@ -290,6 +297,8 @@ struct xdp_frame *xdp_convert_buff_to_frame(struct xdp_buff *xdp)
return xdp_frame;
}
+void __xdp_return(void *data, struct xdp_mem_info *mem, bool napi_direct,
+ struct xdp_buff *xdp);
void xdp_return_frame(struct xdp_frame *xdpf);
void xdp_return_frame_rx_napi(struct xdp_frame *xdpf);
void xdp_return_buff(struct xdp_buff *xdp);
diff --git a/net/core/filter.c b/net/core/filter.c
index 3aca07c44fad..1b931824161c 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -3818,11 +3818,71 @@ static const struct bpf_func_proto bpf_xdp_adjust_head_proto = {
.arg2_type = ARG_ANYTHING,
};
+static int bpf_xdp_mb_adjust_tail(struct xdp_buff *xdp, int offset)
+{
+ struct skb_shared_info *sinfo;
+
+ sinfo = xdp_get_shared_info_from_buff(xdp);
+ if (offset >= 0) {
+ skb_frag_t *frag = &sinfo->frags[sinfo->nr_frags - 1];
+ int size;
+
+ if (unlikely(offset > xdp_get_frag_tailroom(frag)))
+ return -EINVAL;
+
+ size = skb_frag_size(frag);
+ memset(skb_frag_address(frag) + size, 0, offset);
+ skb_frag_size_set(frag, size + offset);
+ sinfo->xdp_frags_size += offset;
+ } else {
+ int i, n_frags_free = 0, len_free = 0, tlen_free = 0;
+
+ offset = abs(offset);
+ if (unlikely(offset > ((int)(xdp->data_end - xdp->data) +
+ sinfo->xdp_frags_size - ETH_HLEN)))
+ return -EINVAL;
+
+ for (i = sinfo->nr_frags - 1; i >= 0 && offset > 0; i--) {
+ skb_frag_t *frag = &sinfo->frags[i];
+ int size = skb_frag_size(frag);
+ int shrink = min_t(int, offset, size);
+
+ len_free += shrink;
+ offset -= shrink;
+
+ if (unlikely(size == shrink)) {
+ struct page *page = skb_frag_page(frag);
+
+ __xdp_return(page_address(page), &xdp->rxq->mem,
+ false, NULL);
+ tlen_free += page_size(page);
+ n_frags_free++;
+ } else {
+ skb_frag_size_set(frag, size - shrink);
+ break;
+ }
+ }
+ sinfo->nr_frags -= n_frags_free;
+ sinfo->xdp_frags_size -= len_free;
+ sinfo->xdp_frags_tsize -= tlen_free;
+
+ if (unlikely(offset > 0)) {
+ xdp_buff_clear_mb(xdp);
+ xdp->data_end -= offset;
+ }
+ }
+
+ return 0;
+}
+
BPF_CALL_2(bpf_xdp_adjust_tail, struct xdp_buff *, xdp, int, offset)
{
void *data_hard_end = xdp_data_hard_end(xdp); /* use xdp->frame_sz */
void *data_end = xdp->data_end + offset;
+ if (unlikely(xdp_buff_is_mb(xdp)))
+ return bpf_xdp_mb_adjust_tail(xdp, offset);
+
/* Notice that xdp_data_hard_end have reserved some tailroom */
if (unlikely(data_end > data_hard_end))
return -EINVAL;
diff --git a/net/core/xdp.c b/net/core/xdp.c
index 1346fb8b3f50..a71cdea75306 100644
--- a/net/core/xdp.c
+++ b/net/core/xdp.c
@@ -339,8 +339,8 @@ EXPORT_SYMBOL_GPL(xdp_rxq_info_reg_mem_model);
* is used for those calls sites. Thus, allowing for faster recycling
* of xdp_frames/pages in those cases.
*/
-static void __xdp_return(void *data, struct xdp_mem_info *mem, bool napi_direct,
- struct xdp_buff *xdp)
+void __xdp_return(void *data, struct xdp_mem_info *mem, bool napi_direct,
+ struct xdp_buff *xdp)
{
struct xdp_mem_allocator *xa;
struct page *page;
@@ -373,6 +373,7 @@ static void __xdp_return(void *data, struct xdp_mem_info *mem, bool napi_direct,
break;
}
}
+EXPORT_SYMBOL_GPL(__xdp_return);
void xdp_return_frame(struct xdp_frame *xdpf)
{
--
2.31.1
Powered by blists - more mailing lists