From nobody Sun Dec 14 06:20:51 2025 Received: from smtp.kernel.org (aws-us-west-2-korg-mail-1.web.codeaurora.org [10.30.226.201]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id 3694E278E44; Mon, 28 Apr 2025 09:24:09 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=10.30.226.201 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1745832250; cv=none; b=jEZgmRw2xp5/jFJuI6pXJ0AaA2jIhFFD5wMbpA3725330E+N86h8SL5289qVmoaBGqO66k4bpDQS+wnwe016qD7O9fpz5HICas1N8POvi8m/3FlnoKkHTKOm45B0dH8ywIdMrXsoBcuJumzRxQXNtCHUfPM8rmCFqFIDVwzApXw= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1745832250; c=relaxed/simple; bh=o9rUJvhmsdRR03YWE52xBlknh79MIWTsCmYUjg7Cbqs=; h=From:To:Cc:Subject:Date:Message-ID:In-Reply-To:References: MIME-Version; b=SzSVbtxohgsqAbQZesRQFjy/wJTbaafYYFSyLVU8qmzy4p8ZvJHsDF/p9z81tXDZjGlAiVQQnzdia6f2NaRqChsYqpwZIxgjzAvo5UwLznl++xmZXbNyfW1q2evEY/JgHJDtyanXvkIPLoKkI0AOs46chjdnEvKHRMfuOEWSoO4= ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=kernel.org header.i=@kernel.org header.b=ltrLv3YB; arc=none smtp.client-ip=10.30.226.201 Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=kernel.org header.i=@kernel.org header.b="ltrLv3YB" Received: by smtp.kernel.org (Postfix) with ESMTPSA id D8E77C4CEE9; Mon, 28 Apr 2025 09:24:08 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=kernel.org; s=k20201202; t=1745832249; bh=o9rUJvhmsdRR03YWE52xBlknh79MIWTsCmYUjg7Cbqs=; h=From:To:Cc:Subject:Date:In-Reply-To:References:From; b=ltrLv3YB0fnSj7N1PfR4mUaSmfOQaR15pMstnUdv3blO6wa7TLBiupO1Qc9uTWN/D qL+Dmw0jaiH/F6BDohX9UQbeve9saTFctay+nWuJmg3kPhQBkYu5ai/9vrvFW5M0MT jt7zztCyEcSj/YyXMxnnO/gFuND0R6EdJ8q4A3kUfd4+Sa5OSwKuHZD3FtoKTvChVU xbVgHwQ1XYVasCaroM1RE0VY4rdG9FRfHhGx0Smf61xyRArCRJ5fe+VCTHRPBaQzEp u2o8MiK33JiaLeDxoJ1LBaOJ0MElGPSOJm1lzFyZkvvzDK1Q9Ei4V7lveThmLGVJ57 8zI62VvtG9iuA== From: Leon Romanovsky To: Marek Szyprowski , Jens Axboe , Christoph Hellwig , Keith Busch Cc: Jake Edge , Jonathan Corbet , Jason Gunthorpe , Zhu Yanjun , Robin Murphy , Joerg Roedel , Will Deacon , Sagi Grimberg , Bjorn Helgaas , Logan Gunthorpe , Yishai Hadas , Shameer Kolothum , Kevin Tian , Alex Williamson , =?UTF-8?q?J=C3=A9r=C3=B4me=20Glisse?= , Andrew Morton , linux-doc@vger.kernel.org, linux-kernel@vger.kernel.org, linux-block@vger.kernel.org, linux-rdma@vger.kernel.org, iommu@lists.linux.dev, linux-nvme@lists.infradead.org, linux-pci@vger.kernel.org, kvm@vger.kernel.org, linux-mm@kvack.org, Niklas Schnelle , Chuck Lever , Luis Chamberlain , Matthew Wilcox , Dan Williams , Kanchan Joshi , Chaitanya Kulkarni , Leon Romanovsky Subject: [PATCH v10 22/24] nvme-pci: use a better encoding for small prp pool allocations Date: Mon, 28 Apr 2025 12:22:28 +0300 Message-ID: X-Mailer: git-send-email 2.49.0 In-Reply-To: References: Precedence: bulk X-Mailing-List: linux-kernel@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 Content-Transfer-Encoding: quoted-printable Content-Type: text/plain; charset="utf-8" From: Christoph Hellwig There is plenty of unused space in the iod next to nr_descriptors. Add a separate flag to encode that the transfer is using the full page sized pool, and use a normal 0..n count for the number of descriptors. Signed-off-by: Christoph Hellwig Tested-by: Jens Axboe [ Leon: changed original bool variable to be flag as was proposed by Kancha= n ] Signed-off-by: Kanchan Joshi Signed-off-by: Leon Romanovsky --- drivers/nvme/host/pci.c | 94 ++++++++++++++++++++--------------------- 1 file changed, 47 insertions(+), 47 deletions(-) diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index 638e759b29ad..270fb5146b5b 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -44,6 +44,7 @@ #define NVME_MAX_SEGS 128 #define NVME_MAX_META_SEGS 15 #define NVME_MAX_NR_DESCRIPTORS 5 +#define NVME_SMALL_DESCRIPTOR_SIZE 256 =20 static int use_threaded_interrupts; module_param(use_threaded_interrupts, int, 0444); @@ -219,6 +220,10 @@ struct nvme_queue { struct completion delete_done; }; =20 +enum { + IOD_LARGE_DESCRIPTORS =3D 1 << 0, /* uses the full page sized descriptor = pool */ +}; + /* * The nvme_iod describes the data in an I/O. */ @@ -226,8 +231,8 @@ struct nvme_iod { struct nvme_request req; struct nvme_command cmd; bool aborted; - /* # of PRP/SGL descriptors: (0 for small pool) */ - s8 nr_descriptors; + u8 nr_descriptors; /* # of PRP/SGL descriptors */ + u8 flags; unsigned int dma_len; /* length of single DMA segment mapping */ dma_addr_t first_dma; dma_addr_t meta_dma; @@ -529,13 +534,27 @@ static inline bool nvme_pci_use_sgls(struct nvme_dev = *dev, struct request *req, return true; } =20 -static void nvme_free_prps(struct nvme_dev *dev, struct request *req) +static inline struct dma_pool *nvme_dma_pool(struct nvme_dev *dev, + struct nvme_iod *iod) +{ + if (iod->flags & IOD_LARGE_DESCRIPTORS) + return dev->prp_page_pool; + return dev->prp_small_pool; +} + +static void nvme_free_descriptors(struct nvme_dev *dev, struct request *re= q) { const int last_prp =3D NVME_CTRL_PAGE_SIZE / sizeof(__le64) - 1; struct nvme_iod *iod =3D blk_mq_rq_to_pdu(req); dma_addr_t dma_addr =3D iod->first_dma; int i; =20 + if (iod->nr_descriptors =3D=3D 1) { + dma_pool_free(nvme_dma_pool(dev, iod), iod->descriptors[0], + dma_addr); + return; + } + for (i =3D 0; i < iod->nr_descriptors; i++) { __le64 *prp_list =3D iod->descriptors[i]; dma_addr_t next_dma_addr =3D le64_to_cpu(prp_list[last_prp]); @@ -558,15 +577,7 @@ static void nvme_unmap_data(struct nvme_dev *dev, stru= ct request *req) WARN_ON_ONCE(!iod->sgt.nents); =20 dma_unmap_sgtable(dev->dev, &iod->sgt, rq_dma_dir(req), 0); - - if (iod->nr_descriptors =3D=3D 0) - dma_pool_free(dev->prp_small_pool, iod->descriptors[0], - iod->first_dma); - else if (iod->nr_descriptors =3D=3D 1) - dma_pool_free(dev->prp_page_pool, iod->descriptors[0], - iod->first_dma); - else - nvme_free_prps(dev, req); + nvme_free_descriptors(dev, req); mempool_free(iod->sgt.sgl, dev->iod_mempool); } =20 @@ -588,7 +599,6 @@ static blk_status_t nvme_pci_setup_prps(struct nvme_dev= *dev, struct request *req, struct nvme_rw_command *cmnd) { struct nvme_iod *iod =3D blk_mq_rq_to_pdu(req); - struct dma_pool *pool; int length =3D blk_rq_payload_bytes(req); struct scatterlist *sg =3D iod->sgt.sgl; int dma_len =3D sg_dma_len(sg); @@ -596,7 +606,7 @@ static blk_status_t nvme_pci_setup_prps(struct nvme_dev= *dev, int offset =3D dma_addr & (NVME_CTRL_PAGE_SIZE - 1); __le64 *prp_list; dma_addr_t prp_dma; - int nprps, i; + int i; =20 length -=3D (NVME_CTRL_PAGE_SIZE - offset); if (length <=3D 0) { @@ -618,27 +628,23 @@ static blk_status_t nvme_pci_setup_prps(struct nvme_d= ev *dev, goto done; } =20 - nprps =3D DIV_ROUND_UP(length, NVME_CTRL_PAGE_SIZE); - if (nprps <=3D (256 / 8)) { - pool =3D dev->prp_small_pool; - iod->nr_descriptors =3D 0; - } else { - pool =3D dev->prp_page_pool; - iod->nr_descriptors =3D 1; - } + if (DIV_ROUND_UP(length, NVME_CTRL_PAGE_SIZE) > + NVME_SMALL_DESCRIPTOR_SIZE / sizeof(__le64)) + iod->flags |=3D IOD_LARGE_DESCRIPTORS; =20 - prp_list =3D dma_pool_alloc(pool, GFP_ATOMIC, &prp_dma); - if (!prp_list) { - iod->nr_descriptors =3D -1; + prp_list =3D dma_pool_alloc(nvme_dma_pool(dev, iod), GFP_ATOMIC, + &prp_dma); + if (!prp_list) return BLK_STS_RESOURCE; - } - iod->descriptors[0] =3D prp_list; + iod->descriptors[iod->nr_descriptors++] =3D prp_list; iod->first_dma =3D prp_dma; i =3D 0; for (;;) { if (i =3D=3D NVME_CTRL_PAGE_SIZE >> 3) { __le64 *old_prp_list =3D prp_list; - prp_list =3D dma_pool_alloc(pool, GFP_ATOMIC, &prp_dma); + + prp_list =3D dma_pool_alloc(dev->prp_page_pool, + GFP_ATOMIC, &prp_dma); if (!prp_list) goto free_prps; iod->descriptors[iod->nr_descriptors++] =3D prp_list; @@ -665,7 +671,7 @@ static blk_status_t nvme_pci_setup_prps(struct nvme_dev= *dev, cmnd->dptr.prp2 =3D cpu_to_le64(iod->first_dma); return BLK_STS_OK; free_prps: - nvme_free_prps(dev, req); + nvme_free_descriptors(dev, req); return BLK_STS_RESOURCE; bad_sgl: WARN(DO_ONCE(nvme_print_sgl, iod->sgt.sgl, iod->sgt.nents), @@ -694,7 +700,6 @@ static blk_status_t nvme_pci_setup_sgls(struct nvme_dev= *dev, struct request *req, struct nvme_rw_command *cmd) { struct nvme_iod *iod =3D blk_mq_rq_to_pdu(req); - struct dma_pool *pool; struct nvme_sgl_desc *sg_list; struct scatterlist *sg =3D iod->sgt.sgl; unsigned int entries =3D iod->sgt.nents; @@ -709,21 +714,13 @@ static blk_status_t nvme_pci_setup_sgls(struct nvme_d= ev *dev, return BLK_STS_OK; } =20 - if (entries <=3D (256 / sizeof(struct nvme_sgl_desc))) { - pool =3D dev->prp_small_pool; - iod->nr_descriptors =3D 0; - } else { - pool =3D dev->prp_page_pool; - iod->nr_descriptors =3D 1; - } + if (entries > NVME_SMALL_DESCRIPTOR_SIZE / sizeof(*sg_list)) + iod->flags |=3D IOD_LARGE_DESCRIPTORS; =20 - sg_list =3D dma_pool_alloc(pool, GFP_ATOMIC, &sgl_dma); - if (!sg_list) { - iod->nr_descriptors =3D -1; + sg_list =3D dma_pool_alloc(nvme_dma_pool(dev, iod), GFP_ATOMIC, &sgl_dma); + if (!sg_list) return BLK_STS_RESOURCE; - } - - iod->descriptors[0] =3D sg_list; + iod->descriptors[iod->nr_descriptors++] =3D sg_list; iod->first_dma =3D sgl_dma; =20 nvme_pci_sgl_set_seg(&cmd->dptr.sgl, sgl_dma, entries); @@ -915,7 +912,8 @@ static blk_status_t nvme_prep_rq(struct nvme_dev *dev, = struct request *req) blk_status_t ret; =20 iod->aborted =3D false; - iod->nr_descriptors =3D -1; + iod->nr_descriptors =3D 0; + iod->flags =3D 0; iod->sgt.nents =3D 0; iod->meta_sgt.nents =3D 0; =20 @@ -2833,7 +2831,7 @@ static int nvme_disable_prepare_reset(struct nvme_dev= *dev, bool shutdown) =20 static int nvme_setup_prp_pools(struct nvme_dev *dev) { - size_t small_align =3D 256; + size_t small_align =3D NVME_SMALL_DESCRIPTOR_SIZE; =20 dev->prp_page_pool =3D dma_pool_create("prp list page", dev->dev, NVME_CTRL_PAGE_SIZE, @@ -2841,12 +2839,14 @@ static int nvme_setup_prp_pools(struct nvme_dev *de= v) if (!dev->prp_page_pool) return -ENOMEM; =20 + BUILD_BUG_ON(NVME_SMALL_DESCRIPTOR_SIZE !=3D 256); if (dev->ctrl.quirks & NVME_QUIRK_DMAPOOL_ALIGN_512) - small_align =3D 512; + small_align *=3D 2; =20 /* Optimisation for I/Os between 4k and 128k */ dev->prp_small_pool =3D dma_pool_create("prp list 256", dev->dev, - 256, small_align, 0); + NVME_SMALL_DESCRIPTOR_SIZE, + small_align, 0); if (!dev->prp_small_pool) { dma_pool_destroy(dev->prp_page_pool); return -ENOMEM; --=20 2.49.0