From: Sasha Levin <sashal@kernel.org>
To: stable@vger.kernel.org
Cc: Dragos Tatulea <dtatulea@nvidia.com>,
Cosmin Ratiu <cratiu@nvidia.com>,
Tariq Toukan <tariqt@nvidia.com>, Paolo Abeni <pabeni@redhat.com>,
Sasha Levin <sashal@kernel.org>
Subject: [PATCH 6.18.y 1/2] net/mlx5e: SHAMPO, Always calculate page size
Date: Wed, 9 Sep 2026 13:32:13 -0400 [thread overview]
Message-ID: <20260909173214.3296617-1-sashal@kernel.org> (raw)
In-Reply-To: <2026090308-macarena-speckled-769c@gregkh>
From: Dragos Tatulea <dtatulea@nvidia.com>
[ Upstream commit dff1c3164a69284ac9fedb1c25d4c008139e9fb8 ]
Adapt the rx path in SHAMPO mode to calculate page size based on
configured page_shift when dealing with payload data.
This is necessary as an upcoming patch will add support for using
different page sizes.
This change has no functional changes.
Signed-off-by: Dragos Tatulea <dtatulea@nvidia.com>
Reviewed-by: Cosmin Ratiu <cratiu@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Link: https://patch.msgid.link/20260223204155.1783580-9-tariqt@nvidia.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Backport to 6.18: preserve the XDP fragment accounting fix from
7d7342a18fadc ("net/mlx5e: RX, Fix XDP multi-buf frag counting for
striding RQ"). Keep new_nr_frags and the original frag_page endpoint;
only replace PAGE_SIZE with page_size in the truesize adjustment.
Reintroducing the old frag_page rewind would break page reference
accounting for fragments consumed by XDP.
Retain the page-size calculations and SHAMPO space-check changes so
e2466392a0b8496000e12181cb1ee1535eb0da25 ("net/mlx5e: do not HW-GRO
coalesce small frames") applies without modification. No functions
are added.
Stable-dep-of: e2466392a0b8 ("net/mlx5e: do not HW-GRO coalesce small frames")
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
.../net/ethernet/mellanox/mlx5/core/en_rx.c | 34 ++++++++++++-------
1 file changed, 22 insertions(+), 12 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
index 2ffa4e6b8c373..8a61c958c5679 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
@@ -2014,11 +2014,14 @@ mlx5e_shampo_fill_skb_data(struct sk_buff *skb, struct mlx5e_rq *rq,
struct mlx5e_frag_page *frag_page,
u32 data_bcnt, u32 data_offset)
{
+ u32 page_size = BIT(rq->mpwqe.page_shift);
+
net_prefetchw(skb->data);
do {
/* Non-linear mode, hence non-XSK, which always uses PAGE_SIZE. */
- u32 pg_consumed_bytes = min_t(u32, PAGE_SIZE - data_offset, data_bcnt);
+ u32 pg_consumed_bytes = min_t(u32, page_size - data_offset,
+ data_bcnt);
unsigned int truesize = pg_consumed_bytes;
mlx5e_add_skb_frag(rq, skb, frag_page, data_offset,
@@ -2039,6 +2042,7 @@ mlx5e_skb_from_cqe_mpwrq_nonlinear(struct mlx5e_rq *rq, struct mlx5e_mpw_info *w
u16 headlen = min_t(u16, MLX5E_RX_MAX_HEAD, cqe_bcnt);
struct mlx5e_frag_page *head_page = frag_page;
struct mlx5e_xdp_buff *mxbuf = &rq->mxbuf;
+ u32 page_size = BIT(rq->mpwqe.page_shift);
u32 frag_offset = head_offset;
u32 byte_cnt = cqe_bcnt;
struct skb_shared_info *sinfo;
@@ -2084,9 +2088,9 @@ mlx5e_skb_from_cqe_mpwrq_nonlinear(struct mlx5e_rq *rq, struct mlx5e_mpw_info *w
linear_hr = skb_headroom(skb);
linear_data_len = headlen;
linear_frame_sz = MLX5_SKB_FRAG_SZ(skb_end_offset(skb));
- if (unlikely(frag_offset >= PAGE_SIZE)) {
+ if (unlikely(frag_offset >= page_size)) {
frag_page++;
- frag_offset -= PAGE_SIZE;
+ frag_offset -= page_size;
}
}
@@ -2098,7 +2102,7 @@ mlx5e_skb_from_cqe_mpwrq_nonlinear(struct mlx5e_rq *rq, struct mlx5e_mpw_info *w
while (byte_cnt) {
/* Non-linear mode, hence non-XSK, which always uses PAGE_SIZE. */
pg_consumed_bytes =
- min_t(u32, PAGE_SIZE - frag_offset, byte_cnt);
+ min_t(u32, page_size - frag_offset, byte_cnt);
if (test_bit(MLX5E_RQ_STATE_SHAMPO, &rq->state))
truesize += pg_consumed_bytes;
@@ -2135,7 +2139,7 @@ mlx5e_skb_from_cqe_mpwrq_nonlinear(struct mlx5e_rq *rq, struct mlx5e_mpw_info *w
new_nr_frags = sinfo->nr_frags;
nr_frags_free = old_nr_frags - new_nr_frags;
if (unlikely(nr_frags_free))
- truesize -= (nr_frags_free - 1) * PAGE_SIZE +
+ truesize -= (nr_frags_free - 1) * page_size +
ALIGN(pg_consumed_bytes,
BIT(rq->mpwqe.log_stride_sz));
@@ -2349,15 +2353,16 @@ mlx5e_shampo_flush_skb(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe, bool match)
rq->hw_gro_data->skb = NULL;
}
-static bool
-mlx5e_hw_gro_skb_has_enough_space(struct sk_buff *skb, u16 data_bcnt)
+static bool mlx5e_hw_gro_skb_has_enough_space(struct sk_buff *skb,
+ u16 data_bcnt,
+ u32 page_size)
{
int nr_frags = skb_shinfo(skb)->nr_frags;
- if (PAGE_SIZE >= GRO_LEGACY_MAX_SIZE)
+ if (page_size >= GRO_LEGACY_MAX_SIZE)
return skb->len + data_bcnt <= GRO_LEGACY_MAX_SIZE;
else
- return PAGE_SIZE * nr_frags + data_bcnt <= GRO_LEGACY_MAX_SIZE;
+ return page_size * nr_frags + data_bcnt <= GRO_LEGACY_MAX_SIZE;
}
static void mlx5e_handle_rx_cqe_mpwrq_shampo(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe)
@@ -2366,18 +2371,19 @@ static void mlx5e_handle_rx_cqe_mpwrq_shampo(struct mlx5e_rq *rq, struct mlx5_cq
u16 header_index = mlx5e_shampo_get_cqe_header_index(rq, cqe);
u32 wqe_offset = be32_to_cpu(cqe->shampo.data_offset);
u16 cstrides = mpwrq_get_cqe_consumed_strides(cqe);
- u32 data_offset = wqe_offset & (PAGE_SIZE - 1);
u32 cqe_bcnt = mpwrq_get_cqe_byte_cnt(cqe);
u16 wqe_id = be16_to_cpu(cqe->wqe_id);
- u32 page_idx = wqe_offset >> PAGE_SHIFT;
u16 head_size = cqe->shampo.header_size;
struct sk_buff **skb = &rq->hw_gro_data->skb;
bool flush = cqe->shampo.flush;
bool match = cqe->shampo.match;
+ u32 page_size = BIT(rq->mpwqe.page_shift);
struct mlx5e_rq_stats *stats = rq->stats;
struct mlx5e_rx_wqe_ll *wqe;
struct mlx5e_mpw_info *wi;
struct mlx5_wq_ll *wq;
+ u32 data_offset;
+ u32 page_idx;
wi = mlx5e_get_mpw_info(rq, wqe_id);
wi->consumed_strides += cstrides;
@@ -2393,7 +2399,11 @@ static void mlx5e_handle_rx_cqe_mpwrq_shampo(struct mlx5e_rq *rq, struct mlx5_cq
goto mpwrq_cqe_out;
}
- if (*skb && (!match || !(mlx5e_hw_gro_skb_has_enough_space(*skb, data_bcnt)))) {
+ data_offset = wqe_offset & (page_size - 1);
+ page_idx = wqe_offset >> rq->mpwqe.page_shift;
+ if (*skb &&
+ !(match && mlx5e_hw_gro_skb_has_enough_space(*skb, data_bcnt,
+ page_size))) {
match = false;
mlx5e_shampo_flush_skb(rq, cqe, match);
}
--
2.53.0
next prev parent reply other threads:[~2026-09-09 17:32 UTC|newest]
Thread overview: 5+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-09-03 15:09 FAILED: patch "[PATCH] net/mlx5e: do not HW-GRO coalesce small frames" failed to apply to 6.18-stable tree gregkh
2026-09-09 17:32 ` Sasha Levin [this message]
2026-09-09 17:32 ` [PATCH 6.18.y 2/2] net/mlx5e: do not HW-GRO coalesce small frames Sasha Levin
2026-09-09 17:32 ` [PATCH 6.18.y 1/2] net/mlx5e: SHAMPO, Always calculate page size Sasha Levin
2026-09-09 17:32 ` [PATCH 6.18.y 2/2] net/mlx5e: do not HW-GRO coalesce small frames Sasha Levin
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=20260909173214.3296617-1-sashal@kernel.org \
--to=sashal@kernel.org \
--cc=cratiu@nvidia.com \
--cc=dtatulea@nvidia.com \
--cc=pabeni@redhat.com \
--cc=stable@vger.kernel.org \
--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