Frag allocators, such as netdev_alloc_frag(), were not designed to work for fragsz > PAGE_SIZE.
So, switch to page pool for jumbo frames instead of using page frag allocators. This driver is using page pool for smaller MTUs already.
Cc: stable@vger.kernel.org Fixes: 80f6215b450e ("net: mana: Add support for jumbo frame") Signed-off-by: Haiyang Zhang haiyangz@microsoft.com --- v2: updated the commit msg as suggested by Jakub Kicinski.
--- drivers/net/ethernet/microsoft/mana/mana_en.c | 46 ++++--------------- 1 file changed, 9 insertions(+), 37 deletions(-)
diff --git a/drivers/net/ethernet/microsoft/mana/mana_en.c b/drivers/net/ethernet/microsoft/mana/mana_en.c index 9a8171f099b6..4d41f4cca3d8 100644 --- a/drivers/net/ethernet/microsoft/mana/mana_en.c +++ b/drivers/net/ethernet/microsoft/mana/mana_en.c @@ -661,30 +661,16 @@ int mana_pre_alloc_rxbufs(struct mana_port_context *mpc, int new_mtu, int num_qu mpc->rxbpre_total = 0;
for (i = 0; i < num_rxb; i++) { - if (mpc->rxbpre_alloc_size > PAGE_SIZE) { - va = netdev_alloc_frag(mpc->rxbpre_alloc_size); - if (!va) - goto error; - - page = virt_to_head_page(va); - /* Check if the frag falls back to single page */ - if (compound_order(page) < - get_order(mpc->rxbpre_alloc_size)) { - put_page(page); - goto error; - } - } else { - page = dev_alloc_page(); - if (!page) - goto error; + page = dev_alloc_pages(get_order(mpc->rxbpre_alloc_size)); + if (!page) + goto error;
- va = page_to_virt(page); - } + va = page_to_virt(page);
da = dma_map_single(dev, va + mpc->rxbpre_headroom, mpc->rxbpre_datasize, DMA_FROM_DEVICE); if (dma_mapping_error(dev, da)) { - put_page(virt_to_head_page(va)); + put_page(page); goto error; }
@@ -1672,7 +1658,7 @@ 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, bool is_napi) + dma_addr_t *da, bool *from_pool) { struct page *page; void *va; @@ -1683,21 +1669,6 @@ static void *mana_get_rxfrag(struct mana_rxq *rxq, struct device *dev, if (rxq->xdp_save_va) { va = rxq->xdp_save_va; rxq->xdp_save_va = NULL; - } else if (rxq->alloc_size > PAGE_SIZE) { - if (is_napi) - va = napi_alloc_frag(rxq->alloc_size); - else - va = netdev_alloc_frag(rxq->alloc_size); - - if (!va) - return NULL; - - page = virt_to_head_page(va); - /* Check if the frag falls back to single page */ - if (compound_order(page) < get_order(rxq->alloc_size)) { - put_page(page); - return NULL; - } } else { page = page_pool_dev_alloc_pages(rxq->page_pool); if (!page) @@ -1730,7 +1701,7 @@ static void mana_refill_rx_oob(struct device *dev, struct mana_rxq *rxq, dma_addr_t da; void *va;
- va = mana_get_rxfrag(rxq, dev, &da, &from_pool, true); + va = mana_get_rxfrag(rxq, dev, &da, &from_pool); if (!va) return;
@@ -2172,7 +2143,7 @@ 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, false); + va = mana_get_rxfrag(rxq, dev, &da, &from_pool);
if (!va) return -ENOMEM; @@ -2258,6 +2229,7 @@ static int mana_create_page_pool(struct mana_rxq *rxq, struct gdma_context *gc) pprm.nid = gc->numa_node; pprm.napi = &rxq->rx_cq.napi; pprm.netdev = rxq->ndev; + pprm.order = get_order(rxq->alloc_size);
rxq->page_pool = page_pool_create(&pprm);
-----Original Message----- From: LKML haiyangz lkmlhyz@microsoft.com On Behalf Of Haiyang Zhang Sent: Tuesday, March 25, 2025 9:33 AM To: linux-hyperv@vger.kernel.org; netdev@vger.kernel.org Cc: Haiyang Zhang haiyangz@microsoft.com; Dexuan Cui decui@microsoft.com; stephen@networkplumber.org; KY Srinivasan kys@microsoft.com; Paul Rosswurm paulros@microsoft.com; olaf@aepfle.de; vkuznets vkuznets@redhat.com; davem@davemloft.net; wei.liu@kernel.org; edumazet@google.com; kuba@kernel.org; pabeni@redhat.com; leon@kernel.org; Long Li longli@microsoft.com; ssengar@linux.microsoft.com; linux-rdma@vger.kernel.org; daniel@iogearbox.net; john.fastabend@gmail.com; bpf@vger.kernel.org; ast@kernel.org; hawk@kernel.org; tglx@linutronix.de; shradhagupta@linux.microsoft.com; jesse.brandeburg@intel.com; andrew+netdev@lunn.ch; linux-kernel@vger.kernel.org; stable@vger.kernel.org Subject: [PATCH net,v2] net: mana: Switch to page pool for jumbo frames
Frag allocators, such as netdev_alloc_frag(), were not designed to work for fragsz > PAGE_SIZE.
So, switch to page pool for jumbo frames instead of using page frag allocators. This driver is using page pool for smaller MTUs already.
Cc: stable@vger.kernel.org Fixes: 80f6215b450e ("net: mana: Add support for jumbo frame") Signed-off-by: Haiyang Zhang haiyangz@microsoft.com
v2: updated the commit msg as suggested by Jakub Kicinski.
drivers/net/ethernet/microsoft/mana/mana_en.c | 46 ++++--------------- 1 file changed, 9 insertions(+), 37 deletions(-)
diff --git a/drivers/net/ethernet/microsoft/mana/mana_en.c b/drivers/net/ethernet/microsoft/mana/mana_en.c index 9a8171f099b6..4d41f4cca3d8 100644 --- a/drivers/net/ethernet/microsoft/mana/mana_en.c +++ b/drivers/net/ethernet/microsoft/mana/mana_en.c @@ -661,30 +661,16 @@ int mana_pre_alloc_rxbufs(struct mana_port_context *mpc, int new_mtu, int num_qu mpc->rxbpre_total = 0;
for (i = 0; i < num_rxb; i++) {
if (mpc->rxbpre_alloc_size > PAGE_SIZE) {va = netdev_alloc_frag(mpc->rxbpre_alloc_size);if (!va)goto error;page = virt_to_head_page(va);/* Check if the frag falls back to single page */if (compound_order(page) <get_order(mpc->rxbpre_alloc_size)) {put_page(page);goto error;}} else {page = dev_alloc_page();if (!page)goto error;
page = dev_alloc_pages(get_order(mpc->rxbpre_alloc_size));if (!page)goto error;
va = page_to_virt(page);}
va = page_to_virt(page);da = dma_map_single(dev, va + mpc->rxbpre_headroom, mpc->rxbpre_datasize, DMA_FROM_DEVICE); if (dma_mapping_error(dev, da)) {
put_page(virt_to_head_page(va));
put_page(page);
Should we use __free_pages()?
-----Original Message----- From: Long Li longli@microsoft.com Sent: Tuesday, March 25, 2025 1:06 PM To: Haiyang Zhang haiyangz@microsoft.com; linux-hyperv@vger.kernel.org; netdev@vger.kernel.org Cc: Dexuan Cui decui@microsoft.com; stephen@networkplumber.org; KY Srinivasan kys@microsoft.com; Paul Rosswurm paulros@microsoft.com; olaf@aepfle.de; vkuznets vkuznets@redhat.com; davem@davemloft.net; wei.liu@kernel.org; edumazet@google.com; kuba@kernel.org; pabeni@redhat.com; leon@kernel.org; ssengar@linux.microsoft.com; linux- rdma@vger.kernel.org; daniel@iogearbox.net; john.fastabend@gmail.com; bpf@vger.kernel.org; ast@kernel.org; hawk@kernel.org; tglx@linutronix.de; shradhagupta@linux.microsoft.com; jesse.brandeburg@intel.com; andrew+netdev@lunn.ch; linux-kernel@vger.kernel.org; stable@vger.kernel.org Subject: RE: [PATCH net,v2] net: mana: Switch to page pool for jumbo frames
-----Original Message----- From: LKML haiyangz lkmlhyz@microsoft.com On Behalf Of Haiyang Zhang Sent: Tuesday, March 25, 2025 9:33 AM To: linux-hyperv@vger.kernel.org; netdev@vger.kernel.org Cc: Haiyang Zhang haiyangz@microsoft.com; Dexuan Cui decui@microsoft.com; stephen@networkplumber.org; KY Srinivasan kys@microsoft.com; Paul Rosswurm paulros@microsoft.com; olaf@aepfle.de; vkuznets vkuznets@redhat.com; davem@davemloft.net; wei.liu@kernel.org; edumazet@google.com; kuba@kernel.org; pabeni@redhat.com; leon@kernel.org; Long Li longli@microsoft.com; ssengar@linux.microsoft.com; linux-rdma@vger.kernel.org; daniel@iogearbox.net; john.fastabend@gmail.com; bpf@vger.kernel.org; ast@kernel.org; hawk@kernel.org; tglx@linutronix.de; shradhagupta@linux.microsoft.com; jesse.brandeburg@intel.com; andrew+netdev@lunn.ch; linux-kernel@vger.kernel.org;
stable@vger.kernel.org
Subject: [PATCH net,v2] net: mana: Switch to page pool for jumbo frames
Frag allocators, such as netdev_alloc_frag(), were not designed to work
for
fragsz > PAGE_SIZE.
So, switch to page pool for jumbo frames instead of using page frag
allocators.
This driver is using page pool for smaller MTUs already.
Cc: stable@vger.kernel.org Fixes: 80f6215b450e ("net: mana: Add support for jumbo frame") Signed-off-by: Haiyang Zhang haiyangz@microsoft.com
v2: updated the commit msg as suggested by Jakub Kicinski.
drivers/net/ethernet/microsoft/mana/mana_en.c | 46 ++++--------------- 1 file changed, 9 insertions(+), 37 deletions(-)
diff --git a/drivers/net/ethernet/microsoft/mana/mana_en.c b/drivers/net/ethernet/microsoft/mana/mana_en.c index 9a8171f099b6..4d41f4cca3d8 100644 --- a/drivers/net/ethernet/microsoft/mana/mana_en.c +++ b/drivers/net/ethernet/microsoft/mana/mana_en.c @@ -661,30 +661,16 @@ int mana_pre_alloc_rxbufs(struct mana_port_context *mpc, int new_mtu, int num_qu mpc->rxbpre_total = 0;
for (i = 0; i < num_rxb; i++) {
if (mpc->rxbpre_alloc_size > PAGE_SIZE) {va = netdev_alloc_frag(mpc->rxbpre_alloc_size);if (!va)goto error;page = virt_to_head_page(va);/* Check if the frag falls back to single page */if (compound_order(page) <get_order(mpc->rxbpre_alloc_size)) {put_page(page);goto error;}} else {page = dev_alloc_page();if (!page)goto error;
page = dev_alloc_pages(get_order(mpc->rxbpre_alloc_size));if (!page)goto error;
va = page_to_virt(page);}
va = page_to_virt(page);da = dma_map_single(dev, va + mpc->rxbpre_headroom, mpc->rxbpre_datasize, DMA_FROM_DEVICE); if (dma_mapping_error(dev, da)) {
put_page(virt_to_head_page(va));
put_page(page);Should we use __free_pages()?
Quote from doc: https://www.kernel.org/doc/html/next/core-api/mm-api.html ___free_pages(): "This function can free multi-page allocations that are not compound pages." "If you want to use the page's reference count to decide when to free the allocation, you should allocate a compound page, and use put_page() instead of __free_pages()."
And, since dev_alloc_pages returns compound page for high order page, we use put_page() which works for both compound & single page.
Thanks, - Haiyang
Subject: [PATCH net,v2] net: mana: Switch to page pool for jumbo frames
Frag allocators, such as netdev_alloc_frag(), were not designed to work
for
fragsz > PAGE_SIZE.
So, switch to page pool for jumbo frames instead of using page frag
allocators.
This driver is using page pool for smaller MTUs already.
Cc: stable@vger.kernel.org Fixes: 80f6215b450e ("net: mana: Add support for jumbo frame") Signed-off-by: Haiyang Zhang haiyangz@microsoft.com
Reviewed-by: Long Li longli@microsoft.com
v2: updated the commit msg as suggested by Jakub Kicinski.
drivers/net/ethernet/microsoft/mana/mana_en.c | 46 ++++--------------- 1 file changed, 9 insertions(+), 37 deletions(-)
diff --git a/drivers/net/ethernet/microsoft/mana/mana_en.c b/drivers/net/ethernet/microsoft/mana/mana_en.c index 9a8171f099b6..4d41f4cca3d8 100644 --- a/drivers/net/ethernet/microsoft/mana/mana_en.c +++ b/drivers/net/ethernet/microsoft/mana/mana_en.c @@ -661,30 +661,16 @@ int mana_pre_alloc_rxbufs(struct mana_port_context *mpc, int new_mtu, int num_qu mpc->rxbpre_total = 0;
for (i = 0; i < num_rxb; i++) {
if (mpc->rxbpre_alloc_size > PAGE_SIZE) {va = netdev_alloc_frag(mpc->rxbpre_alloc_size);if (!va)goto error;page = virt_to_head_page(va);/* Check if the frag falls back to single page */if (compound_order(page) <get_order(mpc->rxbpre_alloc_size)) {put_page(page);goto error;}} else {page = dev_alloc_page();if (!page)goto error;
page = dev_alloc_pages(get_order(mpc->rxbpre_alloc_size));if (!page)goto error;
va = page_to_virt(page);}
va = page_to_virt(page); da = dma_map_single(dev, va + mpc->rxbpre_headroom, mpc->rxbpre_datasize, DMA_FROM_DEVICE); if (dma_mapping_error(dev, da)) {
put_page(virt_to_head_page(va));
put_page(page);Should we use __free_pages()?
Quote from doc: https://www.ker/ nel.org%2Fdoc%2Fhtml%2Fnext%2Fcore-api%2Fmm- api.html&data=05%7C02%7Clongli%40microsoft.com%7Cada2b7bad76e4ab7286 508dd6bc87430%7C72f988bf86f141af91ab2d7cd011db47%7C1%7C0%7C638785 230869082534%7CUnknown%7CTWFpbGZsb3d8eyJFbXB0eU1hcGkiOnRydWUsIl YiOiIwLjAuMDAwMCIsIlAiOiJXaW4zMiIsIkFOIjoiTWFpbCIsIldUIjoyfQ%3D%3D%7C 0%7C%7C%7C&sdata=VINKfrv80MzhE1mmibv1RrRz4WCmr%2BZhWDf1ZaOv47 w%3D&reserved=0 ___free_pages(): "This function can free multi-page allocations that are not compound pages." "If you want to use the page's reference count to decide when to free the allocation, you should allocate a compound page, and use put_page() instead of __free_pages()."
And, since dev_alloc_pages returns compound page for high order page, we use put_page() which works for both compound & single page.
Thanks,
- Haiyang
On Tue, Mar 25, 2025 at 09:32:37AM -0700, Haiyang Zhang wrote:
Frag allocators, such as netdev_alloc_frag(), were not designed to work for fragsz > PAGE_SIZE.
So, switch to page pool for jumbo frames instead of using page frag allocators. This driver is using page pool for smaller MTUs already.
Cc: stable@vger.kernel.org Fixes: 80f6215b450e ("net: mana: Add support for jumbo frame") Signed-off-by: Haiyang Zhang haiyangz@microsoft.com
v2: updated the commit msg as suggested by Jakub Kicinski.
drivers/net/ethernet/microsoft/mana/mana_en.c | 46 ++++--------------- 1 file changed, 9 insertions(+), 37 deletions(-)
diff --git a/drivers/net/ethernet/microsoft/mana/mana_en.c b/drivers/net/ethernet/microsoft/mana/mana_en.c index 9a8171f099b6..4d41f4cca3d8 100644 --- a/drivers/net/ethernet/microsoft/mana/mana_en.c +++ b/drivers/net/ethernet/microsoft/mana/mana_en.c @@ -661,30 +661,16 @@ int mana_pre_alloc_rxbufs(struct mana_port_context *mpc, int new_mtu, int num_qu mpc->rxbpre_total = 0; for (i = 0; i < num_rxb; i++) {
if (mpc->rxbpre_alloc_size > PAGE_SIZE) {va = netdev_alloc_frag(mpc->rxbpre_alloc_size);if (!va)goto error;page = virt_to_head_page(va);/* Check if the frag falls back to single page */if (compound_order(page) <get_order(mpc->rxbpre_alloc_size)) {put_page(page);goto error;}} else {page = dev_alloc_page();if (!page)goto error;
page = dev_alloc_pages(get_order(mpc->rxbpre_alloc_size));if (!page)goto error;
va = page_to_virt(page);}
va = page_to_virt(page);da = dma_map_single(dev, va + mpc->rxbpre_headroom, mpc->rxbpre_datasize, DMA_FROM_DEVICE); if (dma_mapping_error(dev, da)) {
put_page(virt_to_head_page(va));
put_page(page); goto error;@@ -1672,7 +1658,7 @@ 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, bool is_napi)
dma_addr_t *da, bool *from_pool){ struct page *page; void *va; @@ -1683,21 +1669,6 @@ static void *mana_get_rxfrag(struct mana_rxq *rxq, struct device *dev, if (rxq->xdp_save_va) { va = rxq->xdp_save_va; rxq->xdp_save_va = NULL;
- } else if (rxq->alloc_size > PAGE_SIZE) {
if (is_napi)va = napi_alloc_frag(rxq->alloc_size);elseva = netdev_alloc_frag(rxq->alloc_size);if (!va)return NULL;page = virt_to_head_page(va);/* Check if the frag falls back to single page */if (compound_order(page) < get_order(rxq->alloc_size)) {put_page(page);return NULL;}@@ -1730,7 +1701,7 @@ static void mana_refill_rx_oob(struct device *dev, struct mana_rxq *rxq, dma_addr_t da; void *va;
- va = mana_get_rxfrag(rxq, dev, &da, &from_pool, true);
- va = mana_get_rxfrag(rxq, dev, &da, &from_pool); if (!va) return;
@@ -2172,7 +2143,7 @@ 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, false);
va = mana_get_rxfrag(rxq, dev, &da, &from_pool);if (!va) return -ENOMEM; @@ -2258,6 +2229,7 @@ static int mana_create_page_pool(struct mana_rxq *rxq, struct gdma_context *gc) pprm.nid = gc->numa_node; pprm.napi = &rxq->rx_cq.napi; pprm.netdev = rxq->ndev;
- pprm.order = get_order(rxq->alloc_size);
rxq->page_pool = page_pool_create(&pprm); --
Reviewed-by: Shradha Gupta shradhagupta@linux.microsoft.com
2.34.1
Hello:
This patch was applied to netdev/net.git (main) by Jakub Kicinski kuba@kernel.org:
On Tue, 25 Mar 2025 09:32:37 -0700 you wrote:
Frag allocators, such as netdev_alloc_frag(), were not designed to work for fragsz > PAGE_SIZE.
So, switch to page pool for jumbo frames instead of using page frag allocators. This driver is using page pool for smaller MTUs already.
Cc: stable@vger.kernel.org Fixes: 80f6215b450e ("net: mana: Add support for jumbo frame") Signed-off-by: Haiyang Zhang haiyangz@microsoft.com
[...]
Here is the summary with links: - [net,v2] net: mana: Switch to page pool for jumbo frames https://git.kernel.org/netdev/net/c/fa37a8849634
You are awesome, thank you!
linux-stable-mirror@lists.linaro.org
-
Haiyang Zhang -
Long Li -
patchwork-bot+netdevbpf＠kernel.org -
Shradha Gupta