From: Lorenzo Bianconi <lorenzo@kernel.org>
To: bpf@vger.kernel.org, netdev@vger.kernel.org
Cc: lorenzo.bianconi@redhat.com, davem@davemloft.net,
kuba@kernel.org, ast@kernel.org, daniel@iogearbox.net,
shayagr@amazon.com, sameehj@amazon.com, john.fastabend@gmail.com,
dsahern@kernel.org, brouer@redhat.com, echaudro@redhat.com,
jasowang@redhat.com, alexander.duyck@gmail.com, saeed@kernel.org,
maciej.fijalkowski@intel.com, magnus.karlsson@intel.com,
tirthendu.sarkar@intel.com
Subject: [PATCH v9 bpf-next 03/14] net: mvneta: update mb bit before passing the xdp buffer to eBPF layer
Date: Mon, 14 Jun 2021 14:49:41 +0200 [thread overview]
Message-ID: <0cb1664066f6a29d27264cb02ca69e812442bc53.1623674025.git.lorenzo@kernel.org> (raw)
In-Reply-To: <cover.1623674025.git.lorenzo@kernel.org>
Update multi-buffer bit (mb) in xdp_buff to notify XDP/eBPF layer and
XDP remote drivers if this is a "non-linear" XDP buffer. Access
xdp_shared_info only if xdp_buff mb is set.
Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
---
drivers/net/ethernet/marvell/mvneta.c | 21 ++++++++++++++++-----
1 file changed, 16 insertions(+), 5 deletions(-)
diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c
index 7d5cd9bc6c99..f8993f7488b9 100644
--- a/drivers/net/ethernet/marvell/mvneta.c
+++ b/drivers/net/ethernet/marvell/mvneta.c
@@ -2041,9 +2041,14 @@ mvneta_xdp_put_buff(struct mvneta_port *pp, struct mvneta_rx_queue *rxq,
{
int i;
+ if (likely(!xdp_buff_is_mb(xdp)))
+ goto out;
+
for (i = 0; i < sinfo->nr_frags; i++)
page_pool_put_full_page(rxq->page_pool,
skb_frag_page(&sinfo->frags[i]), true);
+
+out:
page_pool_put_page(rxq->page_pool, virt_to_head_page(xdp->data),
sync_len, true);
}
@@ -2245,7 +2250,6 @@ mvneta_swbm_rx_frame(struct mvneta_port *pp,
int data_len = -MVNETA_MH_SIZE, len;
struct net_device *dev = pp->dev;
enum dma_data_direction dma_dir;
- struct skb_shared_info *sinfo;
if (*size > MVNETA_MAX_RX_BUF_SIZE) {
len = MVNETA_MAX_RX_BUF_SIZE;
@@ -2267,9 +2271,6 @@ mvneta_swbm_rx_frame(struct mvneta_port *pp,
prefetch(data);
xdp_prepare_buff(xdp, data, pp->rx_offset_correction + MVNETA_MH_SIZE,
data_len, false);
-
- sinfo = xdp_get_shared_info_from_buff(xdp);
- sinfo->nr_frags = 0;
}
static void
@@ -2304,12 +2305,18 @@ mvneta_swbm_add_rx_fragment(struct mvneta_port *pp,
skb_frag_size_set(frag, data_len);
__skb_frag_set_page(frag, page);
+ if (!xdp_buff_is_mb(xdp)) {
+ xdp_sinfo->data_len = *size;
+ xdp_buff_set_mb(xdp);
+ }
/* last fragment */
if (len == *size) {
struct skb_shared_info *sinfo;
sinfo = xdp_get_shared_info_from_buff(xdp);
sinfo->nr_frags = xdp_sinfo->nr_frags;
+ sinfo->data_len = xdp_sinfo->data_len;
+
memcpy(sinfo->frags, xdp_sinfo->frags,
sinfo->nr_frags * sizeof(skb_frag_t));
}
@@ -2324,9 +2331,12 @@ mvneta_swbm_build_skb(struct mvneta_port *pp, struct mvneta_rx_queue *rxq,
struct xdp_buff *xdp, u32 desc_status)
{
struct skb_shared_info *sinfo = xdp_get_shared_info_from_buff(xdp);
- int i, num_frags = sinfo->nr_frags;
+ int i, num_frags = 0;
struct sk_buff *skb;
+ if (unlikely(xdp_buff_is_mb(xdp)))
+ num_frags = sinfo->nr_frags;
+
skb = build_skb(xdp->data_hard_start, PAGE_SIZE);
if (!skb)
return ERR_PTR(-ENOMEM);
@@ -2398,6 +2408,7 @@ static int mvneta_rx_swbm(struct napi_struct *napi,
frame_sz = size - ETH_FCS_LEN;
desc_status = rx_status;
+ xdp_buff_clear_mb(&xdp_buf);
mvneta_swbm_rx_frame(pp, rx_desc, rxq, &xdp_buf,
&size, page);
} else {
--
2.31.1
next prev parent reply other threads:[~2021-06-14 12:50 UTC|newest]
Thread overview: 53+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-06-14 12:49 [PATCH v9 bpf-next 00/14] mvneta: introduce XDP multi-buffer support Lorenzo Bianconi
2021-06-14 12:49 ` [PATCH v9 bpf-next 01/14] net: skbuff: add data_len field to skb_shared_info Lorenzo Bianconi
2021-06-28 19:58 ` Alexander Duyck
2021-06-29 12:44 ` Lorenzo Bianconi
2021-06-29 17:08 ` Jakub Kicinski
2021-06-29 18:18 ` Alexander Duyck
2021-06-29 18:37 ` Jakub Kicinski
2021-06-29 19:11 ` Jesper Dangaard Brouer
2021-06-29 19:18 ` Lorenzo Bianconi
2021-06-29 20:45 ` Alexander Duyck
2021-06-14 12:49 ` [PATCH v9 bpf-next 02/14] xdp: introduce flags field in xdp_buff/xdp_frame Lorenzo Bianconi
2021-06-28 20:14 ` Alexander Duyck
2021-06-29 12:43 ` Lorenzo Bianconi
2021-06-29 13:07 ` Alexander Duyck
2021-06-29 13:25 ` Lorenzo Bianconi
2021-07-05 15:52 ` Lorenzo Bianconi
2021-07-05 21:35 ` Alexander Duyck
2021-07-06 11:53 ` Lorenzo Bianconi
2021-07-06 14:04 ` Alexander Duyck
2021-07-06 17:47 ` Lorenzo Bianconi
2021-06-14 12:49 ` Lorenzo Bianconi [this message]
2021-06-14 12:49 ` [PATCH v9 bpf-next 04/14] xdp: add multi-buff support to xdp_return_{buff/frame} Lorenzo Bianconi
2021-06-14 12:49 ` [PATCH v9 bpf-next 05/14] net: mvneta: add multi buffer support to XDP_TX Lorenzo Bianconi
2021-06-14 12:49 ` [PATCH v9 bpf-next 06/14] net: mvneta: enable jumbo frames for XDP Lorenzo Bianconi
2021-06-14 12:49 ` [PATCH v9 bpf-next 07/14] net: xdp: add multi-buff support to xdp_build_skb_from_frame Lorenzo Bianconi
2021-06-28 21:05 ` Alexander Duyck
2021-06-29 18:34 ` Lorenzo Bianconi
2021-06-14 12:49 ` [PATCH v9 bpf-next 08/14] bpf: add multi-buff support to the bpf_xdp_adjust_tail() API Lorenzo Bianconi
2021-06-22 23:37 ` John Fastabend
2021-06-24 9:26 ` Eelco Chaudron
2021-06-24 14:24 ` John Fastabend
2021-06-24 15:16 ` Zvi Effron
2021-06-29 13:19 ` Lorenzo Bianconi
2021-06-29 13:27 ` Toke Høiland-Jørgensen
2021-07-06 21:44 ` Backwards compatibility for XDP multi-buff (was: Re: [PATCH v9 bpf-next 08/14] bpf: add multi-buff support to the bpf_xdp_adjust_tail() API) Toke Høiland-Jørgensen
2021-06-14 12:49 ` [PATCH v9 bpf-next 09/14] bpf: introduce bpf_xdp_get_buff_len helper Lorenzo Bianconi
2021-06-14 12:49 ` [PATCH v9 bpf-next 10/14] bpf: add multi-buffer support to xdp copy helpers Lorenzo Bianconi
2021-06-22 23:49 ` John Fastabend
2021-06-24 9:42 ` Eelco Chaudron
2021-06-24 14:28 ` John Fastabend
2021-06-25 8:25 ` Eelco Chaudron
2021-06-29 13:23 ` Lorenzo Bianconi
2021-07-06 10:15 ` Eelco Chaudron
2021-06-14 12:49 ` [PATCH v9 bpf-next 11/14] bpf: move user_size out of bpf_test_init Lorenzo Bianconi
2021-06-14 12:49 ` [PATCH v9 bpf-next 12/14] bpf: introduce multibuff support to bpf_prog_test_run_xdp() Lorenzo Bianconi
2021-06-14 12:49 ` [PATCH v9 bpf-next 13/14] bpf: test_run: add xdp_shared_info pointer in bpf_test_finish signature Lorenzo Bianconi
2021-06-14 12:49 ` [PATCH v9 bpf-next 14/14] bpf: update xdp_adjust_tail selftest to include multi-buffer Lorenzo Bianconi
2021-06-22 23:18 ` [PATCH v9 bpf-next 00/14] mvneta: introduce XDP multi-buffer support John Fastabend
2021-06-23 3:41 ` David Ahern
2021-06-23 5:48 ` John Fastabend
2021-06-23 14:40 ` David Ahern
2021-06-24 14:22 ` John Fastabend
2021-07-01 7:56 ` Magnus Karlsson
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=0cb1664066f6a29d27264cb02ca69e812442bc53.1623674025.git.lorenzo@kernel.org \
--to=lorenzo@kernel.org \
--cc=alexander.duyck@gmail.com \
--cc=ast@kernel.org \
--cc=bpf@vger.kernel.org \
--cc=brouer@redhat.com \
--cc=daniel@iogearbox.net \
--cc=davem@davemloft.net \
--cc=dsahern@kernel.org \
--cc=echaudro@redhat.com \
--cc=jasowang@redhat.com \
--cc=john.fastabend@gmail.com \
--cc=kuba@kernel.org \
--cc=lorenzo.bianconi@redhat.com \
--cc=maciej.fijalkowski@intel.com \
--cc=magnus.karlsson@intel.com \
--cc=netdev@vger.kernel.org \
--cc=saeed@kernel.org \
--cc=sameehj@amazon.com \
--cc=shayagr@amazon.com \
--cc=tirthendu.sarkar@intel.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).