FAILED: patch "[PATCH] net: mana: Sync page pool RX frags for CPU" failed to apply to 6.18-stable tree
Subsystems (5)
[email protected]
maintainerThe patch below does not apply to the 6.18-stable tree.
If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <[email protected]>.
To reproduce the conflict and resubmit, you may use the following commands:
git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-6.18.y
git checkout FETCH_HEAD
git cherry-pick -x c72a0f09c57f92113df69f9b902d11c9e4b132f5
# <resolve conflicts, build, test, etc.>
git commit -s
git send-email --to '<[email protected]>' --in-reply-to '2026072020-cathedral-preoccupy-0b9c@gregkh' --subject-prefix 'PATCH 6.18.y' 'HEAD^..'
Possible dependencies:
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
From c72a0f09c57f92113df69f9b902d11c9e4b132f5 Mon Sep 17 00:00:00 2001
From: Dexuan Cui <[email protected]>
Date: Wed, 1 Jul 2026 21:12:37 -0700
Subject: [PATCH] net: mana: Sync page pool RX frags for CPU
MANA allocates RX buffers from page pool fragments when frag_count is greater than 1. In that case the buffers remain DMA mapped by page pool and the RX completion path does not call dma_unmap_single(). As a result, the implicit sync-for-CPU normally performed by dma_unmap_single() is missing before the packet data is passed to the networking stack.
This breaks RX on configurations which require explicit DMA syncing, for example when booted with swiotlb=force.
Fix this by recording the page pool page and DMA sync offset when the RX buffer is allocated, and syncing the received packet range for CPU access before handing the RX buffer to the stack.
drivers/net/ethernet/microsoft/mana/mana_en.c +33 -7
@@ -2120,12 +2120,16 @@ static void mana_rx_skb(void *buf_va, bool from_pool, }static void *mana_get_rxfrag (struct mana_rxq *rxq,struct device *dev, -dma_addr_t *da,bool *from_pool) +dma_addr_t *da,bool *from_pool, +struct page **pp_page,u32 *dma_sync_offset) {struct page *page;u32 offset;void *va; + *from_pool = false; + *pp_page =NULL ; + *dma_sync_offset =0 ;/* Don't use fragments for jumbo frames or XDP where it's 1 fragment * per page.
@@ -2163,31 +2167,47 @@ static void *mana_get_rxfrag(struct mana_rxq *rxq, struct device *dev, va =page_to_virt (page) + offset; *da =page_pool_get_dma_addr (page) + offset + rxq->headroom; *from_pool = true; + *pp_page = page; + *dma_sync_offset = offset + rxq->headroom;return va; }/* Allocate frag for rx buffer, and save the old buf */ static void mana_refill_rx_oob (struct device *dev,struct mana_rxq *rxq, -struct mana_recv_buf_oob *rxoob,void **old_buf, -bool *old_fp) +struct mana_recv_buf_oob *rxoob,u32 pktlen, +void **old_buf,bool *old_fp) { +struct page *pp_page; +u32 dma_sync_offset;bool from_pool;dma_addr_t da;void *va; - va =mana_get_rxfrag (rxq, dev, &da, &from_pool); + va =mana_get_rxfrag (rxq, dev, &da, &from_pool, &pp_page, + &dma_sync_offset);if (!va)return ; -if (!rxoob->from_pool || rxq->frag_count ==1 ) +if (!rxoob->from_pool || rxq->frag_count ==1 ) {dma_unmap_single (dev, rxoob->sgl[0 ].address, rxq->datasize,DMA_FROM_DEVICE ); + }else { +/* The page pool maps the whole page and only syncs for device +* automatically (PP_FLAG_DMA_SYNC_DEV). Sync the received bytes +* for the CPU before they are read: this is required if DMA +* is incoherent or bounce buffers are used. +*/ +page_pool_dma_sync_for_cpu (rxq->page_pool, rxoob->pp_page, + rxoob->dma_sync_offset, pktlen); + } *old_buf = rxoob->buf_va; *old_fp = rxoob->from_pool; rxoob->buf_va = va; rxoob->sgl[0 ].address = da; rxoob->from_pool = from_pool; + rxoob->pp_page = pp_page; + rxoob->dma_sync_offset = dma_sync_offset; } static void mana_process_rx_cqe(struct mana_rxq *rxq, struct mana_cq *cq,
@@ -2258,7 +2278,8 @@ static void mana_process_rx_cqe(struct mana_rxq *rxq, struct mana_cq *cq,/* Reuse the RX buffer since rxbuf_oob is unchanged. */ }else { -mana_refill_rx_oob (dev, rxq, rxbuf_oob, &old_buf, &old_fp); +mana_refill_rx_oob (dev, rxq, rxbuf_oob, pktlen, + &old_buf, &old_fp);/* Unsuccessful refill will have old_buf == NULL. * In this case, mana_rx_skb() will drop the packet.
@@ -2668,6 +2689,8 @@ static int mana_fill_rx_oob(struct mana_recv_buf_oob *rx_oob, u32 mem_key, struct mana_rxq *rxq, struct device *dev) { struct mana_port_context *mpc = netdev_priv(rxq->ndev); +struct page *pp_page =NULL ; +u32 dma_sync_offset =0 ;bool from_pool = false;dma_addr_t da;void *va;
@@ -2675,13 +2698,16 @@ static int mana_fill_rx_oob(struct mana_recv_buf_oob *rx_oob, u32 mem_key,if (mpc->rxbufs_pre) va =mana_get_rxbuf_pre (rxq, &da);else - va =mana_get_rxfrag (rxq, dev, &da, &from_pool); + va =mana_get_rxfrag (rxq, dev, &da, &from_pool, &pp_page, + &dma_sync_offset);if (!va)return -ENOMEM ; rx_oob->buf_va = va; rx_oob->from_pool = from_pool; + rx_oob->pp_page = pp_page; + rx_oob->dma_sync_offset = dma_sync_offset; rx_oob->sgl[0 ].address = da; rx_oob->sgl[0 ].size = rxq->datasize;
include/net/mana/mana.h +8 -0
@@ -305,6 +305,14 @@ struct mana_recv_buf_oob {void *buf_va;bool from_pool;/* allocated from a page pool */ +/* head page of the page_pool fragment; valid only when +* from_pool && frag_count > 1. +*/ +struct page *pp_page; +/* Fragment offset plus rxq->headroom, passed to +* page_pool_dma_sync_for_cpu(). +*/ +u32 dma_sync_offset;/* SGL of the buffer going to be sent as part of the work request. */ u32 num_sge;
Sasha Levin
maintainerPATCH 1/2 net: mana: Validate the packet length reported by the NIC
From: Dexuan Cui <[email protected]>
[ Upstream commit 2e2a83b4998af4384e677d3b2ac08565274279bf ]
Validate the packet length reported in the RX CQE before passing it to skb processing. The CQE is supplied by the NIC device and should not be blindly trusted.
Stable-dep-of: c72a0f09c57f ("net: mana: Sync page pool RX frags for CPU")
--- drivers/net/ethernet/microsoft/mana/mana_en.c | 23 +++++++++++++++---- 1 file changed, 18 insertions(+), 5 deletions(-)
drivers/net/ethernet/microsoft/mana/mana_en.c +18 -5
@@ -2160,12 +2160,25 @@ static void mana_process_rx_cqe(struct mana_rxq *rxq, struct mana_cq *cq, rxbuf_oob = &rxq->rx_oobs[curr];WARN_ON_ONCE (rxbuf_oob->wqe_inf.wqe_size_in_bu !=1 ); -mana_refill_rx_oob (dev, rxq, rxbuf_oob, &old_buf, &old_fp); +if (unlikely (pktlen > rxq->datasize)) { +/* Increase it even if mana_rx_skb() isn't called. */ + rxq->rx_cq.work_done++; -/* Unsuccessful refill will have old_buf == NULL. -* In this case, mana_rx_skb() will drop the packet. -*/ -mana_rx_skb (old_buf, old_fp, oob, rxq); + ++ndev->stats.rx_dropped; +netdev_warn_once (ndev, +"Dropped oversized RX packet: len=%u, datasize=%u\n" , + pktlen, rxq->datasize); + +/* Reuse the RX buffer since rxbuf_oob is unchanged. */ + }else { + +mana_refill_rx_oob (dev, rxq, rxbuf_oob, &old_buf, &old_fp); + +/* Unsuccessful refill will have old_buf == NULL. +* In this case, mana_rx_skb() will drop the packet. +*/ +mana_rx_skb (old_buf, old_fp, oob, rxq); + } drop:mana_move_wq_tail (rxq->gdma_rq, rxbuf_oob->wqe_inf.wqe_size_in_bu);
Signature · 1 line
2.53.0
Sasha Levin
maintainerPATCH 2/2 net: mana: Sync page pool RX frags for CPU
From: Dexuan Cui <[email protected]>
[ Upstream commit c72a0f09c57f92113df69f9b902d11c9e4b132f5 ]
MANA allocates RX buffers from page pool fragments when frag_count is greater than 1. In that case the buffers remain DMA mapped by page pool and the RX completion path does not call dma_unmap_single(). As a result, the implicit sync-for-CPU normally performed by dma_unmap_single() is missing before the packet data is passed to the networking stack.
This breaks RX on configurations which require explicit DMA syncing, for example when booted with swiotlb=force.
Fix this by recording the page pool page and DMA sync offset when the RX buffer is allocated, and syncing the received packet range for CPU access before handing the RX buffer to the stack.
--- drivers/net/ethernet/microsoft/mana/mana_en.c | 40 +++++++++++++++---- include/net/mana/mana.h | 8 ++++ 2 files changed, 41 insertions(+), 7 deletions(-)
drivers/net/ethernet/microsoft/mana/mana_en.c +33 -7
@@ -2036,12 +2036,16 @@ static void mana_rx_skb(void *buf_va, bool from_pool, }static void *mana_get_rxfrag (struct mana_rxq *rxq,struct device *dev, -dma_addr_t *da,bool *from_pool) +dma_addr_t *da,bool *from_pool, +struct page **pp_page,u32 *dma_sync_offset) {struct page *page;u32 offset;void *va; + *from_pool = false; + *pp_page =NULL ; + *dma_sync_offset =0 ;/* Don't use fragments for jumbo frames or XDP where it's 1 fragment * per page.
@@ -2079,31 +2083,47 @@ static void *mana_get_rxfrag(struct mana_rxq *rxq, struct device *dev, va =page_to_virt (page) + offset; *da =page_pool_get_dma_addr (page) + offset + rxq->headroom; *from_pool = true; + *pp_page = page; + *dma_sync_offset = offset + rxq->headroom;return va; }/* Allocate frag for rx buffer, and save the old buf */ static void mana_refill_rx_oob (struct device *dev,struct mana_rxq *rxq, -struct mana_recv_buf_oob *rxoob,void **old_buf, -bool *old_fp) +struct mana_recv_buf_oob *rxoob,u32 pktlen, +void **old_buf,bool *old_fp) { +struct page *pp_page; +u32 dma_sync_offset;bool from_pool;dma_addr_t da;void *va; - va =mana_get_rxfrag (rxq, dev, &da, &from_pool); + va =mana_get_rxfrag (rxq, dev, &da, &from_pool, &pp_page, + &dma_sync_offset);if (!va)return ; -if (!rxoob->from_pool || rxq->frag_count ==1 ) +if (!rxoob->from_pool || rxq->frag_count ==1 ) {dma_unmap_single (dev, rxoob->sgl[0 ].address, rxq->datasize,DMA_FROM_DEVICE ); + }else { +/* The page pool maps the whole page and only syncs for device +* automatically (PP_FLAG_DMA_SYNC_DEV). Sync the received bytes +* for the CPU before they are read: this is required if DMA +* is incoherent or bounce buffers are used. +*/ +page_pool_dma_sync_for_cpu (rxq->page_pool, rxoob->pp_page, + rxoob->dma_sync_offset, pktlen); + } *old_buf = rxoob->buf_va; *old_fp = rxoob->from_pool; rxoob->buf_va = va; rxoob->sgl[0 ].address = da; rxoob->from_pool = from_pool; + rxoob->pp_page = pp_page; + rxoob->dma_sync_offset = dma_sync_offset; } static void mana_process_rx_cqe(struct mana_rxq *rxq, struct mana_cq *cq,
@@ -2172,7 +2192,8 @@ static void mana_process_rx_cqe(struct mana_rxq *rxq, struct mana_cq *cq,/* Reuse the RX buffer since rxbuf_oob is unchanged. */ }else { -mana_refill_rx_oob (dev, rxq, rxbuf_oob, &old_buf, &old_fp); +mana_refill_rx_oob (dev, rxq, rxbuf_oob, pktlen, + &old_buf, &old_fp);/* Unsuccessful refill will have old_buf == NULL. * In this case, mana_rx_skb() will drop the packet.
@@ -2548,6 +2569,8 @@ static int mana_fill_rx_oob(struct mana_recv_buf_oob *rx_oob, u32 mem_key, struct mana_rxq *rxq, struct device *dev) { struct mana_port_context *mpc = netdev_priv(rxq->ndev); +struct page *pp_page =NULL ; +u32 dma_sync_offset =0 ;bool from_pool = false;dma_addr_t da;void *va;
@@ -2555,13 +2578,16 @@ static int mana_fill_rx_oob(struct mana_recv_buf_oob *rx_oob, u32 mem_key,if (mpc->rxbufs_pre) va =mana_get_rxbuf_pre (rxq, &da);else - va =mana_get_rxfrag (rxq, dev, &da, &from_pool); + va =mana_get_rxfrag (rxq, dev, &da, &from_pool, &pp_page, + &dma_sync_offset);if (!va)return -ENOMEM ; rx_oob->buf_va = va; rx_oob->from_pool = from_pool; + rx_oob->pp_page = pp_page; + rx_oob->dma_sync_offset = dma_sync_offset; rx_oob->sgl[0 ].address = da; rx_oob->sgl[0 ].size = rxq->datasize;
include/net/mana/mana.h +8 -0
@@ -302,6 +302,14 @@ struct mana_recv_buf_oob {void *buf_va;bool from_pool;/* allocated from a page pool */ +/* head page of the page_pool fragment; valid only when +* from_pool && frag_count > 1. +*/ +struct page *pp_page; +/* Fragment offset plus rxq->headroom, passed to +* page_pool_dma_sync_for_cpu(). +*/ +u32 dma_sync_offset;/* SGL of the buffer going to be sent as part of the work request. */ u32 num_sge;
Signature · 1 line
2.53.0
Re: [PATCH 6.18.y 2/2] net: mana: Sync page pool RX frags for CPU
Quoted 163 lines · Sasha Levin
From: Dexuan Cui <[email protected]>
[ Upstream commit
c72a0f09c57f92113df69f9b902d11c9e4b132f5]MANA allocates RX buffers from page pool fragments when
frag_countis greater than 1. In that case the buffers remain DMA mapped by page pool and the RX completion path does not calldma_unmap_single(). As a result, the implicit sync-for-CPU normally performed bydma_unmap_single()is missing before the packet data is passed to the networking stack.This breaks RX on configurations which require explicit DMA syncing, for example when booted with swiotlb=force.
Fix this by recording the page pool page and DMA sync offset when the RX buffer is allocated, and syncing the received packet range for CPU access before handing the RX buffer to the stack.
Fixes 730ff06d3f5c ("net: mana: Use page pool fragments for RX buffers instead of full pages to improve memory efficiency.")Reviewed-by Haiyang Zhang <[email protected]>Signed-off-by Dexuan Cui <[email protected]>Signed-off-by Paolo Abeni <[email protected]>Signed-off-by Sasha Levin <[email protected]>--- drivers/net/ethernet/microsoft/mana/mana_en.c | 40 +++++++++++++++---- include/net/mana/mana.h | 8 ++++ 2 files changed, 41 insertions(+), 7 deletions(-)drivers/net/ethernet/microsoft/mana/mana_en.c +33
-7@@ -2036,12 +2036,16 @@ static void mana_rx_skb(void *buf_va, bool from_pool, }static void *mana_get_rxfrag (struct mana_rxq *rxq,struct device *dev, -dma_addr_t *da,bool *from_pool) +dma_addr_t *da,bool *from_pool, +struct page **pp_page,u32 *dma_sync_offset) {struct page *page;u32 offset;void *va; + *from_pool = false; + *pp_page =NULL ; + *dma_sync_offset =0 ;/* Don't use fragments for jumbo frames or XDP where it's 1 fragment * per page. @@ -2079,31 +2083,47 @@ static void *mana_get_rxfrag(struct mana_rxq *rxq, struct device *dev, va =page_to_virt (page) + offset; *da =page_pool_get_dma_addr (page) + offset + rxq->headroom; *from_pool = true; + *pp_page = page; + *dma_sync_offset = offset + rxq->headroom;return va; }/* Allocate frag for rx buffer, and save the old buf */ static void mana_refill_rx_oob (struct device *dev,struct mana_rxq *rxq, -struct mana_recv_buf_oob *rxoob,void **old_buf, -bool *old_fp) +struct mana_recv_buf_oob *rxoob,u32 pktlen, +void **old_buf,bool *old_fp) { +struct page *pp_page; +u32 dma_sync_offset;bool from_pool;dma_addr_t da;void *va; - va =mana_get_rxfrag (rxq, dev, &da, &from_pool); + va =mana_get_rxfrag (rxq, dev, &da, &from_pool, &pp_page, + &dma_sync_offset);if (!va)return ; -if (!rxoob->from_pool || rxq->frag_count ==1 ) +if (!rxoob->from_pool || rxq->frag_count ==1 ) {dma_unmap_single (dev, rxoob->sgl[0 ].address, rxq->datasize,DMA_FROM_DEVICE ); + }else { +/* The page pool maps the whole page and only syncs for device +* automatically (PP_FLAG_DMA_SYNC_DEV). Sync the received bytes +* for the CPU before they are read: this is required if DMA +* is incoherent or bounce buffers are used. +*/ +page_pool_dma_sync_for_cpu (rxq->page_pool, rxoob->pp_page, + rxoob->dma_sync_offset, pktlen); + } *old_buf = rxoob->buf_va; *old_fp = rxoob->from_pool; rxoob->buf_va = va; rxoob->sgl[0 ].address = da; rxoob->from_pool = from_pool; + rxoob->pp_page = pp_page; + rxoob->dma_sync_offset = dma_sync_offset; } static void mana_process_rx_cqe(struct mana_rxq *rxq, struct mana_cq *cq,@@ -2172,7 +2192,8 @@ static void mana_process_rx_cqe(struct mana_rxq *rxq, struct mana_cq *cq,/* Reuse the RX buffer since rxbuf_oob is unchanged. */ }else { -mana_refill_rx_oob (dev, rxq, rxbuf_oob, &old_buf, &old_fp); +mana_refill_rx_oob (dev, rxq, rxbuf_oob, pktlen, + &old_buf, &old_fp);/* Unsuccessful refill will have old_buf == NULL. * In this case, mana_rx_skb() will drop the packet. @@ -2548,6 +2569,8 @@ static int mana_fill_rx_oob(struct mana_recv_buf_oob *rx_oob, u32 mem_key, struct mana_rxq *rxq, struct device *dev) { struct mana_port_context *mpc = netdev_priv(rxq->ndev); +struct page *pp_page =NULL ; +u32 dma_sync_offset =0 ;bool from_pool = false;dma_addr_t da;void *va;@@ -2555,13 +2578,16 @@ static int mana_fill_rx_oob(struct mana_recv_buf_oob *rx_oob, u32 mem_key,if (mpc->rxbufs_pre) va =mana_get_rxbuf_pre (rxq, &da);else - va =mana_get_rxfrag (rxq, dev, &da, &from_pool); + va =mana_get_rxfrag (rxq, dev, &da, &from_pool, &pp_page, + &dma_sync_offset);if (!va)return -ENOMEM ; rx_oob->buf_va = va; rx_oob->from_pool = from_pool; + rx_oob->pp_page = pp_page; + rx_oob->dma_sync_offset = dma_sync_offset; rx_oob->sgl[0 ].address = da; rx_oob->sgl[0 ].size = rxq->datasize;include/net/mana/mana.h +8
-0@@ -302,6 +302,14 @@ struct mana_recv_buf_oob {void *buf_va;bool from_pool;/* allocated from a page pool */ +/* head page of the page_pool fragment; valid only when +* from_pool && frag_count > 1. +*/ +struct page *pp_page; +/* Fragment offset plus rxq->headroom, passed to +* page_pool_dma_sync_for_cpu(). +*/ +u32 dma_sync_offset;/* SGL of the buffer going to be sent as part of the work request. */ u32 num_sge;Signature · 1 line
2.53.0
Does not apply :(