From nobody Sat Nov 30 03:42:52 2024 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 D21291A2631; Thu, 12 Sep 2024 11:16:37 +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=1726139798; cv=none; b=oRyZ0hOsYFT7Ny9R1+hOJ9LYLnYS0jgblJgikJFX7VERaxaYc/Ny3lc3JFqYVtgX0bJhmcNy+RSZsLhcJv4AufiYUQquQ+1Oy8SkvDtDvXSMfvM8WDAcNtuOeswsGb1TorM5HKYugnh67RsOcxcrXuwA8hC7pWrMKFZCDnMNI28= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1726139798; c=relaxed/simple; bh=HCbYGqX249833/tdiRDBvFBjeuSolO9rH8wFEsCHmuw=; h=From:To:Cc:Subject:Date:Message-ID:In-Reply-To:References: MIME-Version; b=YdKnbLxAeyLXcSNF88gJNauvqRfctOqXiDQIAn8xPTBIGDTijzq4lztCRLb38JmfdPyH9sXcrbOz5MCm0sbhqyM9ziSjnhkjzyXllDLUHrk8qPk9fzecsBjhy9U9spgeyrM+1c3jQpEzggquwKg8Hhtk1YVGr/LGpbuNlWgVO18= ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=kernel.org header.i=@kernel.org header.b=utilRRP5; 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="utilRRP5" Received: by smtp.kernel.org (Postfix) with ESMTPSA id 95168C4CEC5; Thu, 12 Sep 2024 11:16:36 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=kernel.org; s=k20201202; t=1726139797; bh=HCbYGqX249833/tdiRDBvFBjeuSolO9rH8wFEsCHmuw=; h=From:To:Cc:Subject:Date:In-Reply-To:References:From; b=utilRRP5yDc5niZQdTcTGnzCnlrPS0S4L3Hb9vq/XwpoQFI0AVDbejOe0Qo42RRZR KkYQDJw1ZBH1+GhREn9IO3Aft1IbL0WfEet5f0emPRe8iuqT8w2AFuYT9rawGzAivh cQxvsrrXrX2aswijqPZVgD9EpT7cf20gG1iWYXmqsE07Ej+8c8FKOF4tQuWco24nd1 2lGYnudAW1yc+NprinXcSsQXcnqPmKubTJyZY5LKaiOnVKB5gOk1fdSCFyV62ullq/ IqZxh1M1CLXFDX8nzGm4+Sy2BP2yjU9370wTj3+xV+5K9S+8gyJXtfhxEhlqM50c+P tzPreaeQDm/dA== From: Leon Romanovsky To: Jens Axboe , Jason Gunthorpe , Robin Murphy , Joerg Roedel , Will Deacon , Keith Busch , Christoph Hellwig , "Zeng, Oak" , Chaitanya Kulkarni Cc: Leon Romanovsky , Sagi Grimberg , Bjorn Helgaas , Logan Gunthorpe , Yishai Hadas , Shameer Kolothum , Kevin Tian , Alex Williamson , Marek Szyprowski , =?UTF-8?q?J=C3=A9r=C3=B4me=20Glisse?= , Andrew Morton , linux-block@vger.kernel.org, linux-kernel@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 Subject: [RFC v2 09/21] dma-mapping: provide callbacks to link/unlink HMM PFNs to specific IOVA Date: Thu, 12 Sep 2024 14:15:44 +0300 Message-ID: X-Mailer: git-send-email 2.46.0 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: Leon Romanovsky Introduce new DMA link/unlink API to provide a way for HMM users to link pages to already preallocated IOVA. Signed-off-by: Leon Romanovsky --- include/linux/dma-mapping.h | 15 ++++++ kernel/dma/mapping.c | 102 ++++++++++++++++++++++++++++++++++++ 2 files changed, 117 insertions(+) diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h index bb541f8944e5..8c2a468c5420 100644 --- a/include/linux/dma-mapping.h +++ b/include/linux/dma-mapping.h @@ -123,6 +123,10 @@ static inline int dma_mapping_error(struct device *dev= , dma_addr_t dma_addr) int dma_alloc_iova_unaligned(struct dma_iova_state *state, phys_addr_t phy= s, size_t size); void dma_free_iova(struct dma_iova_state *state); +dma_addr_t dma_hmm_link_page(struct dma_iova_state *state, unsigned long *= pfn, + dma_addr_t dma_offset); +void dma_hmm_unlink_page(struct dma_iova_state *state, unsigned long *pfn, + dma_addr_t dma_offset); =20 dma_addr_t dma_map_page_attrs(struct device *dev, struct page *page, size_t offset, size_t size, enum dma_data_direction dir, @@ -189,6 +193,17 @@ static inline int dma_alloc_iova_unaligned(struct dma_= iova_state *state, static inline void dma_free_iova(struct dma_iova_state *state) { } +static inline dma_addr_t dma_hmm_link_page(struct dma_iova_state *state, + unsigned long *pfn, + dma_addr_t dma_offset) +{ + return DMA_MAPPING_ERROR; +} +static inline void dma_hmm_unlink_page(struct dma_iova_state *state, + unsigned long *pfn, + dma_addr_t dma_offset) +{ +} static inline dma_addr_t dma_map_page_attrs(struct device *dev, struct page *page, size_t offset, size_t size, enum dma_data_direction dir, unsigned long attrs) diff --git a/kernel/dma/mapping.c b/kernel/dma/mapping.c index 39fac8c21643..5354ddc3ac03 100644 --- a/kernel/dma/mapping.c +++ b/kernel/dma/mapping.c @@ -17,6 +17,7 @@ #include #include #include +#include #include "debug.h" #include "direct.h" =20 @@ -1084,3 +1085,104 @@ void dma_unlink_range_attrs(struct dma_iova_state *= state, unsigned long attrs) state->dir, attrs); } EXPORT_SYMBOL_GPL(dma_unlink_range_attrs); + +/** + * dma_hmm_link_page - Link a physical HMM page to DMA address + * @state: IOVA state + * @pfn: HMM PFN + * @dma_offset: DMA offset form which this page needs to be linked + * + * dma_alloc_iova() allocates IOVA based on the size specified by their us= e in + * iova->size. Call this function after IOVA allocation to link whole @page + * to get the DMA address. Note that very first call to this function + * will have @dma_offset set to 0 in the IOVA space allocated from + * dma_alloc_iova(). For subsequent calls to this function on same @iova, + * @dma_offset needs to be advanced by the caller with the size of previous + * page that was linked + DMA address returned for the previous page that = was + * linked by this function. + */ +dma_addr_t dma_hmm_link_page(struct dma_iova_state *state, unsigned long *= pfn, + dma_addr_t dma_offset) +{ + struct device *dev =3D state->dev; + struct page *page =3D hmm_pfn_to_page(*pfn); + phys_addr_t phys =3D page_to_phys(page); + bool coherent =3D dev_is_dma_coherent(dev); + dma_addr_t addr; + int ret; + + if (*pfn & HMM_PFN_DMA_MAPPED) + /* + * We are in this flow when there is a need to resync flags, + * for example when page was already linked in prefetch call + * with READ flag and now we need to add WRITE flag + * + * This page was already programmed to HW and we don't want/need + * to unlink and link it again just to resync flags. + * + * The DMA address calculation below is based on the fact that + * HMM doesn't work with swiotlb. + */ + return (state->addr) ? state->addr + dma_offset : + phys_to_dma(dev, phys); + + state->range_size =3D dma_offset; + + /* + * The below check is based on assumption that HMM range users + * don't work with swiotlb and hence can be or in direct mode + * or in IOMMU mode. + */ + if (!use_dma_iommu(dev)) { + if (!coherent) + arch_sync_dma_for_device(phys, PAGE_SIZE, state->dir); + + addr =3D phys_to_dma(dev, phys); + goto done; + } + + ret =3D dma_start_range(state); + if (ret) + return DMA_MAPPING_ERROR; + + addr =3D dma_link_range(state, phys, PAGE_SIZE); + dma_end_range(state); + if (dma_mapping_error(state->dev, addr)) + return addr; + +done: + kmsan_handle_dma(page, 0, PAGE_SIZE, state->dir); + *pfn |=3D HMM_PFN_DMA_MAPPED; + return addr; +} +EXPORT_SYMBOL_GPL(dma_hmm_link_page); + +/** + * dma_hmm_unlink_page - Unlink a physical HMM page from DMA address + * @state: IOVA state + * @pfn: HMM PFN + * @dma_offset: DMA offset form which this page needs to be unlinked + * from the IOVA space + */ +void dma_hmm_unlink_page(struct dma_iova_state *state, unsigned long *pfn, + dma_addr_t dma_offset) +{ + struct device *dev =3D state->dev; + struct page *page; + phys_addr_t phys; + + *pfn &=3D ~HMM_PFN_DMA_MAPPED; + + if (!use_dma_iommu(dev)) { + page =3D hmm_pfn_to_page(*pfn); + phys =3D page_to_phys(page); + + dma_direct_sync_single_for_cpu(dev, phys_to_dma(dev, phys), + PAGE_SIZE, state->dir); + return; + } + + iommu_dma_unlink_range(dev, state->addr + dma_offset, PAGE_SIZE, + state->dir, 0); +} +EXPORT_SYMBOL_GPL(dma_hmm_unlink_page); --=20 2.46.0