From 411c5f36805c02c7c412f1ad6bfa4459a1148011 Mon Sep 17 00:00:00 2001 From: Yunsheng Lin Date: Wed, 28 Feb 2024 17:30:08 +0800 Subject: mm/page_alloc: modify page_frag_alloc_align() to accept align as an argument napi_alloc_frag_align() and netdev_alloc_frag_align() accept align as an argument, and they are thin wrappers around the __napi_alloc_frag_align() and __netdev_alloc_frag_align() APIs doing the alignment checking and align mask conversion, in order to call page_frag_alloc_align() directly. The intention here is to keep the alignment checking and the alignmask conversion in in-line wrapper to avoid those kind of operations during execution time since it can usually be handled during compile time. We are going to use page_frag_alloc_align() in vhost_net.c, it need the same kind of alignment checking and alignmask conversion, so split up page_frag_alloc_align into an inline wrapper doing the above operation, and add __page_frag_alloc_align() which is passed with the align mask the original function expected as suggested by Alexander. Signed-off-by: Yunsheng Lin CC: Alexander Duyck Acked-by: Michael S. Tsirkin Signed-off-by: Paolo Abeni --- mm/page_alloc.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'mm/page_alloc.c') diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 150d4f23b010..c0f7e67c4250 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -4708,9 +4708,9 @@ void __page_frag_cache_drain(struct page *page, unsigned int count) } EXPORT_SYMBOL(__page_frag_cache_drain); -void *page_frag_alloc_align(struct page_frag_cache *nc, - unsigned int fragsz, gfp_t gfp_mask, - unsigned int align_mask) +void *__page_frag_alloc_align(struct page_frag_cache *nc, + unsigned int fragsz, gfp_t gfp_mask, + unsigned int align_mask) { unsigned int size = PAGE_SIZE; struct page *page; @@ -4779,7 +4779,7 @@ refill: return nc->va + offset; } -EXPORT_SYMBOL(page_frag_alloc_align); +EXPORT_SYMBOL(__page_frag_alloc_align); /* * Frees a page fragment allocated out of either a compound or order 0 page. -- cgit v1.2.3-59-g8ed1b From 4bc0d63a23957262b01b5848bd5e1739e98bbf36 Mon Sep 17 00:00:00 2001 From: Yunsheng Lin Date: Wed, 28 Feb 2024 17:30:09 +0800 Subject: page_frag: unify gfp bits for order 3 page allocation Currently there seems to be three page frag implementations which all try to allocate order 3 page, if that fails, it then fail back to allocate order 0 page, and each of them all allow order 3 page allocation to fail under certain condition by using specific gfp bits. The gfp bits for order 3 page allocation are different between different implementation, __GFP_NOMEMALLOC is or'd to forbid access to emergency reserves memory for __page_frag_cache_refill(), but it is not or'd in other implementions, __GFP_DIRECT_RECLAIM is masked off to avoid direct reclaim in vhost_net_page_frag_refill(), but it is not masked off in __page_frag_cache_refill(). This patch unifies the gfp bits used between different implementions by or'ing __GFP_NOMEMALLOC and masking off __GFP_DIRECT_RECLAIM for order 3 page allocation to avoid possible pressure for mm. Leave the gfp unifying for page frag implementation in sock.c for now as suggested by Paolo Abeni. Signed-off-by: Yunsheng Lin Reviewed-by: Alexander Duyck CC: Alexander Duyck Acked-by: Michael S. Tsirkin Signed-off-by: Paolo Abeni --- drivers/vhost/net.c | 2 +- mm/page_alloc.c | 4 ++-- 2 files changed, 3 insertions(+), 3 deletions(-) (limited to 'mm/page_alloc.c') diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c index f2ed7167c848..e574e21cc0ca 100644 --- a/drivers/vhost/net.c +++ b/drivers/vhost/net.c @@ -670,7 +670,7 @@ static bool vhost_net_page_frag_refill(struct vhost_net *net, unsigned int sz, /* Avoid direct reclaim but allow kswapd to wake */ pfrag->page = alloc_pages((gfp & ~__GFP_DIRECT_RECLAIM) | __GFP_COMP | __GFP_NOWARN | - __GFP_NORETRY, + __GFP_NORETRY | __GFP_NOMEMALLOC, SKB_FRAG_PAGE_ORDER); if (likely(pfrag->page)) { pfrag->size = PAGE_SIZE << SKB_FRAG_PAGE_ORDER; diff --git a/mm/page_alloc.c b/mm/page_alloc.c index c0f7e67c4250..636145c29f70 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -4685,8 +4685,8 @@ static struct page *__page_frag_cache_refill(struct page_frag_cache *nc, gfp_t gfp = gfp_mask; #if (PAGE_SIZE < PAGE_FRAG_CACHE_MAX_SIZE) - gfp_mask |= __GFP_COMP | __GFP_NOWARN | __GFP_NORETRY | - __GFP_NOMEMALLOC; + gfp_mask = (gfp_mask & ~__GFP_DIRECT_RECLAIM) | __GFP_COMP | + __GFP_NOWARN | __GFP_NORETRY | __GFP_NOMEMALLOC; page = alloc_pages_node(NUMA_NO_NODE, gfp_mask, PAGE_FRAG_CACHE_MAX_ORDER); nc->size = page ? PAGE_FRAG_CACHE_MAX_SIZE : PAGE_SIZE; -- cgit v1.2.3-59-g8ed1b From a0727489ac22d6fbd2e390d38a51193bba61da83 Mon Sep 17 00:00:00 2001 From: Yunsheng Lin Date: Wed, 28 Feb 2024 17:30:10 +0800 Subject: net: introduce page_frag_cache_drain() When draining a page_frag_cache, most user are doing the similar steps, so introduce an API to avoid code duplication. Signed-off-by: Yunsheng Lin Acked-by: Jason Wang Reviewed-by: Alexander Duyck Acked-by: Michael S. Tsirkin Signed-off-by: Paolo Abeni --- drivers/net/ethernet/google/gve/gve_main.c | 11 ++--------- drivers/net/ethernet/mediatek/mtk_wed_wo.c | 17 ++--------------- drivers/nvme/host/tcp.c | 7 +------ drivers/nvme/target/tcp.c | 4 +--- include/linux/gfp.h | 1 + mm/page_alloc.c | 10 ++++++++++ 6 files changed, 17 insertions(+), 33 deletions(-) (limited to 'mm/page_alloc.c') diff --git a/drivers/net/ethernet/google/gve/gve_main.c b/drivers/net/ethernet/google/gve/gve_main.c index 7b89b66adb53..166bd827a6d7 100644 --- a/drivers/net/ethernet/google/gve/gve_main.c +++ b/drivers/net/ethernet/google/gve/gve_main.c @@ -1276,17 +1276,10 @@ static void gve_unreg_xdp_info(struct gve_priv *priv) static void gve_drain_page_cache(struct gve_priv *priv) { - struct page_frag_cache *nc; int i; - for (i = 0; i < priv->rx_cfg.num_queues; i++) { - nc = &priv->rx[i].page_cache; - if (nc->va) { - __page_frag_cache_drain(virt_to_page(nc->va), - nc->pagecnt_bias); - nc->va = NULL; - } - } + for (i = 0; i < priv->rx_cfg.num_queues; i++) + page_frag_cache_drain(&priv->rx[i].page_cache); } static void gve_qpls_get_curr_alloc_cfg(struct gve_priv *priv, diff --git a/drivers/net/ethernet/mediatek/mtk_wed_wo.c b/drivers/net/ethernet/mediatek/mtk_wed_wo.c index d58b07e7e123..7063c78bd35f 100644 --- a/drivers/net/ethernet/mediatek/mtk_wed_wo.c +++ b/drivers/net/ethernet/mediatek/mtk_wed_wo.c @@ -286,7 +286,6 @@ mtk_wed_wo_queue_free(struct mtk_wed_wo *wo, struct mtk_wed_wo_queue *q) static void mtk_wed_wo_queue_tx_clean(struct mtk_wed_wo *wo, struct mtk_wed_wo_queue *q) { - struct page *page; int i; for (i = 0; i < q->n_desc; i++) { @@ -301,19 +300,12 @@ mtk_wed_wo_queue_tx_clean(struct mtk_wed_wo *wo, struct mtk_wed_wo_queue *q) entry->buf = NULL; } - if (!q->cache.va) - return; - - page = virt_to_page(q->cache.va); - __page_frag_cache_drain(page, q->cache.pagecnt_bias); - memset(&q->cache, 0, sizeof(q->cache)); + page_frag_cache_drain(&q->cache); } static void mtk_wed_wo_queue_rx_clean(struct mtk_wed_wo *wo, struct mtk_wed_wo_queue *q) { - struct page *page; - for (;;) { void *buf = mtk_wed_wo_dequeue(wo, q, NULL, true); @@ -323,12 +315,7 @@ mtk_wed_wo_queue_rx_clean(struct mtk_wed_wo *wo, struct mtk_wed_wo_queue *q) skb_free_frag(buf); } - if (!q->cache.va) - return; - - page = virt_to_page(q->cache.va); - __page_frag_cache_drain(page, q->cache.pagecnt_bias); - memset(&q->cache, 0, sizeof(q->cache)); + page_frag_cache_drain(&q->cache); } static void diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c index a6d596e05602..3692b56cb58d 100644 --- a/drivers/nvme/host/tcp.c +++ b/drivers/nvme/host/tcp.c @@ -1344,7 +1344,6 @@ static int nvme_tcp_alloc_async_req(struct nvme_tcp_ctrl *ctrl) static void nvme_tcp_free_queue(struct nvme_ctrl *nctrl, int qid) { - struct page *page; struct nvme_tcp_ctrl *ctrl = to_tcp_ctrl(nctrl); struct nvme_tcp_queue *queue = &ctrl->queues[qid]; unsigned int noreclaim_flag; @@ -1355,11 +1354,7 @@ static void nvme_tcp_free_queue(struct nvme_ctrl *nctrl, int qid) if (queue->hdr_digest || queue->data_digest) nvme_tcp_free_crypto(queue); - if (queue->pf_cache.va) { - page = virt_to_head_page(queue->pf_cache.va); - __page_frag_cache_drain(page, queue->pf_cache.pagecnt_bias); - queue->pf_cache.va = NULL; - } + page_frag_cache_drain(&queue->pf_cache); noreclaim_flag = memalloc_noreclaim_save(); /* ->sock will be released by fput() */ diff --git a/drivers/nvme/target/tcp.c b/drivers/nvme/target/tcp.c index c8655fc5aa5b..2aa5762e9f50 100644 --- a/drivers/nvme/target/tcp.c +++ b/drivers/nvme/target/tcp.c @@ -1591,7 +1591,6 @@ static void nvmet_tcp_free_cmd_data_in_buffers(struct nvmet_tcp_queue *queue) static void nvmet_tcp_release_queue_work(struct work_struct *w) { - struct page *page; struct nvmet_tcp_queue *queue = container_of(w, struct nvmet_tcp_queue, release_work); @@ -1615,8 +1614,7 @@ static void nvmet_tcp_release_queue_work(struct work_struct *w) if (queue->hdr_digest || queue->data_digest) nvmet_tcp_free_crypto(queue); ida_free(&nvmet_tcp_queue_ida, queue->idx); - page = virt_to_head_page(queue->pf_cache.va); - __page_frag_cache_drain(page, queue->pf_cache.pagecnt_bias); + page_frag_cache_drain(&queue->pf_cache); kfree(queue); } diff --git a/include/linux/gfp.h b/include/linux/gfp.h index 28aea17fa59b..6cef1c241180 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -311,6 +311,7 @@ extern void __free_pages(struct page *page, unsigned int order); extern void free_pages(unsigned long addr, unsigned int order); struct page_frag_cache; +void page_frag_cache_drain(struct page_frag_cache *nc); extern void __page_frag_cache_drain(struct page *page, unsigned int count); void *__page_frag_alloc_align(struct page_frag_cache *nc, unsigned int fragsz, gfp_t gfp_mask, unsigned int align_mask); diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 636145c29f70..06aa1ebbd21c 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -4699,6 +4699,16 @@ static struct page *__page_frag_cache_refill(struct page_frag_cache *nc, return page; } +void page_frag_cache_drain(struct page_frag_cache *nc) +{ + if (!nc->va) + return; + + __page_frag_cache_drain(virt_to_head_page(nc->va), nc->pagecnt_bias); + nc->va = NULL; +} +EXPORT_SYMBOL(page_frag_cache_drain); + void __page_frag_cache_drain(struct page *page, unsigned int count) { VM_BUG_ON_PAGE(page_ref_count(page) == 0, page); -- cgit v1.2.3-59-g8ed1b