From: Alexander Lobakin <aleksander.lobakin@intel.com>
To: "David S. Miller" <davem@davemloft.net>,
Eric Dumazet <edumazet@google.com>,
Jakub Kicinski <kuba@kernel.org>, Paolo Abeni <pabeni@redhat.com>
Cc: "Alexander Lobakin" <aleksander.lobakin@intel.com>,
"Toke Høiland-Jørgensen" <toke@redhat.com>,
"Alexei Starovoitov" <ast@kernel.org>,
"Daniel Borkmann" <daniel@iogearbox.net>,
"John Fastabend" <john.fastabend@gmail.com>,
"Andrii Nakryiko" <andrii@kernel.org>,
"Stanislav Fomichev" <sdf@fomichev.me>,
"Magnus Karlsson" <magnus.karlsson@intel.com>,
nex.sw.ncis.osdt.itp.upstreaming@intel.com, bpf@vger.kernel.org,
netdev@vger.kernel.org, linux-kernel@vger.kernel.org
Subject: [PATCH net-next v2 11/18] xdp: add generic xdp_buff_add_frag()
Date: Tue, 15 Oct 2024 16:53:43 +0200 [thread overview]
Message-ID: <20241015145350.4077765-12-aleksander.lobakin@intel.com> (raw)
In-Reply-To: <20241015145350.4077765-1-aleksander.lobakin@intel.com>
The code piece which would attach a frag to &xdp_buff is almost
identical across the drivers supporting XDP multi-buffer on Rx.
Make it a generic elegant onelner.
Also, I see lots of drivers calculating frags_truesize as
`xdp->frame_sz * nr_frags`. I can't say this is fully correct, since
frags might be backed by chunks of different sizes, especially with
stuff like the header split. Even page_pool_alloc() can give you two
different truesizes on two subsequent requests to allocate the same
buffer size. Add a field to &skb_shared_info (unionized as there's no
free slot currently on x6_64) to track the "true" truesize. It can be
used later when updating an skb.
Signed-off-by: Alexander Lobakin <aleksander.lobakin@intel.com>
---
include/linux/skbuff.h | 16 ++++++--
include/net/xdp.h | 90 +++++++++++++++++++++++++++++++++++++++++-
2 files changed, 101 insertions(+), 5 deletions(-)
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index c867df5b1051..6ec78c1598fe 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -607,11 +607,19 @@ struct skb_shared_info {
* Warning : all fields before dataref are cleared in __alloc_skb()
*/
atomic_t dataref;
- unsigned int xdp_frags_size;
- /* Intermediate layers must ensure that destructor_arg
- * remains valid until skb destructor */
- void * destructor_arg;
+ union {
+ struct {
+ u32 xdp_frags_size;
+ u32 xdp_frags_truesize;
+ };
+
+ /*
+ * Intermediate layers must ensure that destructor_arg
+ * remains valid until skb destructor.
+ */
+ void *destructor_arg;
+ };
/* must be last field, see pskb_expand_head() */
skb_frag_t frags[MAX_SKB_FRAGS];
diff --git a/include/net/xdp.h b/include/net/xdp.h
index c4b408d22669..19d2b283b845 100644
--- a/include/net/xdp.h
+++ b/include/net/xdp.h
@@ -167,6 +167,88 @@ xdp_get_buff_len(const struct xdp_buff *xdp)
return len;
}
+/**
+ * __xdp_buff_add_frag - attach a frag to an &xdp_buff
+ * @xdp: XDP buffer to attach the frag to
+ * @page: page containing the frag
+ * @offset: page offset at which the frag starts
+ * @size: size of the frag
+ * @truesize: truesize (page / page frag size) of the frag
+ * @try_coalesce: whether to try coalescing the frags
+ *
+ * Attach a frag to an XDP buffer. If it currently has no frags attached,
+ * initialize the related fields, otherwise check that the frag number
+ * didn't reach the limit of ``MAX_SKB_FRAGS``. If possible, try coalescing
+ * the frag with the previous one.
+ * The function doesn't check/update the pfmemalloc bit. Please use the
+ * non-underscored wrapper in drivers.
+ *
+ * Return: true on success, false if there's no space for the frag in
+ * the shared info struct.
+ */
+static inline bool __xdp_buff_add_frag(struct xdp_buff *xdp, struct page *page,
+ u32 offset, u32 size, u32 truesize,
+ bool try_coalesce)
+{
+ struct skb_shared_info *sinfo = xdp_get_shared_info_from_buff(xdp);
+ skb_frag_t *prev;
+ u32 nr_frags;
+
+ if (!xdp_buff_has_frags(xdp)) {
+ xdp_buff_set_frags_flag(xdp);
+
+ nr_frags = 0;
+ sinfo->xdp_frags_size = 0;
+ sinfo->xdp_frags_truesize = 0;
+
+ goto fill;
+ }
+
+ nr_frags = sinfo->nr_frags;
+ if (unlikely(nr_frags == MAX_SKB_FRAGS))
+ return false;
+
+ prev = &sinfo->frags[nr_frags - 1];
+ if (try_coalesce && page == skb_frag_page(prev) &&
+ offset == skb_frag_off(prev) + skb_frag_size(prev))
+ skb_frag_size_add(prev, size);
+ else
+fill:
+ __skb_fill_page_desc_noacc(sinfo, nr_frags++, page,
+ offset, size);
+
+ sinfo->nr_frags = nr_frags;
+ sinfo->xdp_frags_size += size;
+ sinfo->xdp_frags_truesize += truesize;
+
+ return true;
+}
+
+/**
+ * xdp_buff_add_frag - attach a frag to an &xdp_buff
+ * @xdp: XDP buffer to attach the frag to
+ * @page: page containing the frag
+ * @offset: page offset at which the frag starts
+ * @size: size of the frag
+ * @truesize: truesize (page / page frag size) of the frag
+ *
+ * Version of __xdp_buff_add_frag() which takes care of the pfmemalloc bit.
+ *
+ * Return: true on success, false if there's no space for the frag in
+ * the shared info struct.
+ */
+static inline bool xdp_buff_add_frag(struct xdp_buff *xdp, struct page *page,
+ u32 offset, u32 size, u32 truesize)
+{
+ if (!__xdp_buff_add_frag(xdp, page, offset, size, truesize, true))
+ return false;
+
+ if (unlikely(page_is_pfmemalloc(page)))
+ xdp_buff_set_frag_pfmemalloc(xdp);
+
+ return true;
+}
+
struct xdp_frame {
void *data;
u32 len;
@@ -230,7 +312,13 @@ xdp_update_skb_shared_info(struct sk_buff *skb, u8 nr_frags,
unsigned int size, unsigned int truesize,
bool pfmemalloc)
{
- skb_shinfo(skb)->nr_frags = nr_frags;
+ struct skb_shared_info *sinfo = skb_shinfo(skb);
+
+ sinfo->nr_frags = nr_frags;
+ /* ``destructor_arg`` is unionized with ``xdp_frags_{,true}size``,
+ * reset it after that these fields aren't used anymore.
+ */
+ sinfo->destructor_arg = NULL;
skb->len += size;
skb->data_len += size;
--
2.46.2
next prev parent reply other threads:[~2024-10-15 14:54 UTC|newest]
Thread overview: 42+ messages / expand[flat|nested] mbox.gz Atom feed top
2024-10-15 14:53 [PATCH net-next v2 00/18] idpf: XDP chapter III: core XDP changes (+libeth_xdp) Alexander Lobakin
2024-10-15 14:53 ` [PATCH net-next v2 01/18] jump_label: export static_key_slow_{inc,dec}_cpuslocked() Alexander Lobakin
2024-10-17 11:06 ` Maciej Fijalkowski
2024-10-21 13:53 ` Alexander Lobakin
2024-10-22 12:52 ` Maciej Fijalkowski
2024-10-15 14:53 ` [PATCH net-next v2 02/18] skbuff: allow 2-4-argument skb_frag_dma_map() Alexander Lobakin
2024-10-15 14:53 ` [PATCH net-next v2 03/18] unroll: add generic loop unroll helpers Alexander Lobakin
2024-10-15 14:53 ` [PATCH net-next v2 04/18] bpf, xdp: constify some bpf_prog * function arguments Alexander Lobakin
2024-10-17 11:12 ` Maciej Fijalkowski
2024-10-21 13:56 ` Alexander Lobakin
2024-10-22 12:55 ` Maciej Fijalkowski
2024-10-15 14:53 ` [PATCH net-next v2 05/18] xdp, xsk: constify read-only arguments of some static inline helpers Alexander Lobakin
2024-10-17 11:14 ` Maciej Fijalkowski
2024-10-21 13:57 ` Alexander Lobakin
2024-10-15 14:53 ` [PATCH net-next v2 06/18] xdp: allow attaching already registered memory model to xdp_rxq_info Alexander Lobakin
2024-10-15 14:53 ` [PATCH net-next v2 07/18] net: Register system page pool as an XDP memory model Alexander Lobakin
2024-10-17 11:32 ` Maciej Fijalkowski
2024-10-21 14:00 ` Alexander Lobakin
2024-10-15 14:53 ` [PATCH net-next v2 08/18] page_pool: make page_pool_put_page_bulk() actually handle array of pages Alexander Lobakin
2024-10-17 11:33 ` Maciej Fijalkowski
2024-10-21 14:03 ` Alexander Lobakin
2024-10-15 14:53 ` [PATCH net-next v2 09/18] page_pool: allow mixing PPs within one bulk Alexander Lobakin
2024-10-15 14:53 ` [PATCH net-next v2 10/18] xdp: get rid of xdp_frame::mem.id Alexander Lobakin
2024-10-15 14:53 ` Alexander Lobakin [this message]
2024-10-17 12:26 ` [PATCH net-next v2 11/18] xdp: add generic xdp_buff_add_frag() Maciej Fijalkowski
2024-10-21 14:10 ` Alexander Lobakin
2024-10-22 13:00 ` Maciej Fijalkowski
2024-10-15 14:53 ` [PATCH net-next v2 12/18] xdp: add generic xdp_build_skb_from_buff() Alexander Lobakin
2024-10-17 12:34 ` Maciej Fijalkowski
2024-10-21 14:20 ` Alexander Lobakin
2024-10-15 14:53 ` [PATCH net-next v2 13/18] xsk: allow attaching XSk pool via xdp_rxq_info_reg_mem_model() Alexander Lobakin
2024-10-17 12:49 ` Maciej Fijalkowski
2024-10-21 14:23 ` Alexander Lobakin
2024-10-15 14:53 ` [PATCH net-next v2 14/18] xsk: make xsk_buff_add_frag really add a frag via __xdp_buff_add_frag() Alexander Lobakin
2024-10-17 13:04 ` Maciej Fijalkowski
2024-10-15 14:53 ` [PATCH net-next v2 15/18] xsk: add generic XSk &xdp_buff -> skb conversion Alexander Lobakin
2024-10-18 12:48 ` Maciej Fijalkowski
2024-10-15 14:53 ` [PATCH net-next v2 16/18] xsk: add helper to get &xdp_desc's DMA and meta pointer in one go Alexander Lobakin
2024-10-22 15:42 ` Maciej Fijalkowski
2024-10-23 14:50 ` Alexander Lobakin
2024-10-15 14:53 ` [PATCH net-next v2 17/18] libeth: support native XDP and register memory model Alexander Lobakin
2024-10-15 14:53 ` [PATCH net-next v2 18/18] libeth: add a couple of XDP helpers (libeth_xdp) Alexander Lobakin
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=20241015145350.4077765-12-aleksander.lobakin@intel.com \
--to=aleksander.lobakin@intel.com \
--cc=andrii@kernel.org \
--cc=ast@kernel.org \
--cc=bpf@vger.kernel.org \
--cc=daniel@iogearbox.net \
--cc=davem@davemloft.net \
--cc=edumazet@google.com \
--cc=john.fastabend@gmail.com \
--cc=kuba@kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=magnus.karlsson@intel.com \
--cc=netdev@vger.kernel.org \
--cc=nex.sw.ncis.osdt.itp.upstreaming@intel.com \
--cc=pabeni@redhat.com \
--cc=sdf@fomichev.me \
--cc=toke@redhat.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