From nobody Sun Dec 14 02:00:55 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 879D425F99A; Mon, 28 Apr 2025 09:23:22 +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=1745832203; cv=none; b=P9/7rOossnq5RMt23Hqq7JnZHJNVvckxHgpbvnZcKy2GrF8jZ9PoXS7ESRJkRn2ZEG/XXJT0aEymD/KUpneI5GxyTVOWARICbj6jQy2cvXMh2Y99KxkXrXBBPpyUSg4XeJ764puyfezkVsoORPpuWHtjqsV0eYlgddajPJu1I5w= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1745832203; c=relaxed/simple; bh=DqmELyRaD+HKliKs+yhB7fshFSe2Z6G/xyJIpc/k6wk=; h=From:To:Cc:Subject:Date:Message-ID:In-Reply-To:References: MIME-Version; b=P73msq3t61U9sRwq56T13iDWhvljOdAVU+YkRxUpuRhq99Uu9loKVx5Uyu0DzOQvspY74939ifISoy4LNi3qP5xowXxB6ye79Bh50rVNxVayeAJtvi/JaWp3F3bmzy36iHwtQcQqk5FvryKqUmxGHam3v10rZtgvl32pJ9fj7qA= ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=kernel.org header.i=@kernel.org header.b=i33plADx; 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="i33plADx" Received: by smtp.kernel.org (Postfix) with ESMTPSA id 0A77BC4CEE4; Mon, 28 Apr 2025 09:23:22 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=kernel.org; s=k20201202; t=1745832202; bh=DqmELyRaD+HKliKs+yhB7fshFSe2Z6G/xyJIpc/k6wk=; h=From:To:Cc:Subject:Date:In-Reply-To:References:From; b=i33plADx4mBDh4Mg0JhS7PdQonorQCsmo5YRKErsBgYKa4z8vOidmkY/AfS0xrH1Z yFDIAo01whKRGniuFCRzbw1+F6BnXoeGa8ey25ORoO6MG2G3/eXqsW1FNher3MmIz0 +9dEW6mpOEwloxkUFgK2y3up8HxeJXMHWV+4XbrTQYL5Or5e//10k5C7G4pNzcKJ/m oANUDjKdfpR/c4GB4V24c0eKKek4BVX9/RgbDOjLjhU8rGCdF1gxhQqNesdw2rfrrL MyYaLBYM5LnbvqLH5GsIk9qtApa0VRVHM28Dg1Mr4VJ5Nm2VYTSsLzNp0HPAb/dB/M 4dv4HRnILcU/A== From: Leon Romanovsky To: Marek Szyprowski , Jens Axboe , Christoph Hellwig , Keith Busch Cc: Leon Romanovsky , 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 , Jason Gunthorpe Subject: [PATCH v10 10/24] mm/hmm: let users to tag specific PFN with DMA mapped bit Date: Mon, 28 Apr 2025 12:22:16 +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: Leon Romanovsky Introduce new sticky flag (HMM_PFN_DMA_MAPPED), which isn't overwritten by HMM range fault. Such flag allows users to tag specific PFNs with information if this specific PFN was already DMA mapped. Tested-by: Jens Axboe Reviewed-by: Christoph Hellwig Reviewed-by: Jason Gunthorpe Signed-off-by: Leon Romanovsky --- include/linux/hmm.h | 20 ++++++++++++++++-- mm/hmm.c | 51 ++++++++++++++++++++++++++++----------------- 2 files changed, 50 insertions(+), 21 deletions(-) diff --git a/include/linux/hmm.h b/include/linux/hmm.h index 126a36571667..a43e56f273a1 100644 --- a/include/linux/hmm.h +++ b/include/linux/hmm.h @@ -23,6 +23,8 @@ struct mmu_interval_notifier; * HMM_PFN_WRITE - if the page memory can be written to (requires HMM_PFN_= VALID) * HMM_PFN_ERROR - accessing the pfn is impossible and the device should * fail. ie poisoned memory, special pages, no vma, etc + * HMM_PFN_DMA_MAPPED - Flag preserved on input-to-output transformation + * to mark that page is already DMA mapped * * On input: * 0 - Return the current state of the page, do not fault = it. @@ -36,13 +38,19 @@ enum hmm_pfn_flags { HMM_PFN_VALID =3D 1UL << (BITS_PER_LONG - 1), HMM_PFN_WRITE =3D 1UL << (BITS_PER_LONG - 2), HMM_PFN_ERROR =3D 1UL << (BITS_PER_LONG - 3), - HMM_PFN_ORDER_SHIFT =3D (BITS_PER_LONG - 8), + /* + * Sticky flags, carried from input to output, + * don't forget to update HMM_PFN_INOUT_FLAGS + */ + HMM_PFN_DMA_MAPPED =3D 1UL << (BITS_PER_LONG - 4), + + HMM_PFN_ORDER_SHIFT =3D (BITS_PER_LONG - 9), =20 /* Input flags */ HMM_PFN_REQ_FAULT =3D HMM_PFN_VALID, HMM_PFN_REQ_WRITE =3D HMM_PFN_WRITE, =20 - HMM_PFN_FLAGS =3D 0xFFUL << HMM_PFN_ORDER_SHIFT, + HMM_PFN_FLAGS =3D ~((1UL << HMM_PFN_ORDER_SHIFT) - 1), }; =20 /* @@ -57,6 +65,14 @@ static inline struct page *hmm_pfn_to_page(unsigned long= hmm_pfn) return pfn_to_page(hmm_pfn & ~HMM_PFN_FLAGS); } =20 +/* + * hmm_pfn_to_phys() - return physical address pointed to by a device entry + */ +static inline phys_addr_t hmm_pfn_to_phys(unsigned long hmm_pfn) +{ + return __pfn_to_phys(hmm_pfn & ~HMM_PFN_FLAGS); +} + /* * hmm_pfn_to_map_order() - return the CPU mapping size order * diff --git a/mm/hmm.c b/mm/hmm.c index 082f7b7c0b9e..51fe8b011cc7 100644 --- a/mm/hmm.c +++ b/mm/hmm.c @@ -39,13 +39,20 @@ enum { HMM_NEED_ALL_BITS =3D HMM_NEED_FAULT | HMM_NEED_WRITE_FAULT, }; =20 +enum { + /* These flags are carried from input-to-output */ + HMM_PFN_INOUT_FLAGS =3D HMM_PFN_DMA_MAPPED, +}; + static int hmm_pfns_fill(unsigned long addr, unsigned long end, struct hmm_range *range, unsigned long cpu_flags) { unsigned long i =3D (addr - range->start) >> PAGE_SHIFT; =20 - for (; addr < end; addr +=3D PAGE_SIZE, i++) - range->hmm_pfns[i] =3D cpu_flags; + for (; addr < end; addr +=3D PAGE_SIZE, i++) { + range->hmm_pfns[i] &=3D HMM_PFN_INOUT_FLAGS; + range->hmm_pfns[i] |=3D cpu_flags; + } return 0; } =20 @@ -202,8 +209,10 @@ static int hmm_vma_handle_pmd(struct mm_walk *walk, un= signed long addr, return hmm_vma_fault(addr, end, required_fault, walk); =20 pfn =3D pmd_pfn(pmd) + ((addr & ~PMD_MASK) >> PAGE_SHIFT); - for (i =3D 0; addr < end; addr +=3D PAGE_SIZE, i++, pfn++) - hmm_pfns[i] =3D pfn | cpu_flags; + for (i =3D 0; addr < end; addr +=3D PAGE_SIZE, i++, pfn++) { + hmm_pfns[i] &=3D HMM_PFN_INOUT_FLAGS; + hmm_pfns[i] |=3D pfn | cpu_flags; + } return 0; } #else /* CONFIG_TRANSPARENT_HUGEPAGE */ @@ -230,14 +239,14 @@ static int hmm_vma_handle_pte(struct mm_walk *walk, u= nsigned long addr, unsigned long cpu_flags; pte_t pte =3D ptep_get(ptep); uint64_t pfn_req_flags =3D *hmm_pfn; + uint64_t new_pfn_flags =3D 0; =20 if (pte_none_mostly(pte)) { required_fault =3D hmm_pte_need_fault(hmm_vma_walk, pfn_req_flags, 0); if (required_fault) goto fault; - *hmm_pfn =3D 0; - return 0; + goto out; } =20 if (!pte_present(pte)) { @@ -253,16 +262,14 @@ static int hmm_vma_handle_pte(struct mm_walk *walk, u= nsigned long addr, cpu_flags =3D HMM_PFN_VALID; if (is_writable_device_private_entry(entry)) cpu_flags |=3D HMM_PFN_WRITE; - *hmm_pfn =3D swp_offset_pfn(entry) | cpu_flags; - return 0; + new_pfn_flags =3D swp_offset_pfn(entry) | cpu_flags; + goto out; } =20 required_fault =3D hmm_pte_need_fault(hmm_vma_walk, pfn_req_flags, 0); - if (!required_fault) { - *hmm_pfn =3D 0; - return 0; - } + if (!required_fault) + goto out; =20 if (!non_swap_entry(entry)) goto fault; @@ -304,11 +311,13 @@ static int hmm_vma_handle_pte(struct mm_walk *walk, u= nsigned long addr, pte_unmap(ptep); return -EFAULT; } - *hmm_pfn =3D HMM_PFN_ERROR; - return 0; + new_pfn_flags =3D HMM_PFN_ERROR; + goto out; } =20 - *hmm_pfn =3D pte_pfn(pte) | cpu_flags; + new_pfn_flags =3D pte_pfn(pte) | cpu_flags; +out: + *hmm_pfn =3D (*hmm_pfn & HMM_PFN_INOUT_FLAGS) | new_pfn_flags; return 0; =20 fault: @@ -448,8 +457,10 @@ static int hmm_vma_walk_pud(pud_t *pudp, unsigned long= start, unsigned long end, } =20 pfn =3D pud_pfn(pud) + ((addr & ~PUD_MASK) >> PAGE_SHIFT); - for (i =3D 0; i < npages; ++i, ++pfn) - hmm_pfns[i] =3D pfn | cpu_flags; + for (i =3D 0; i < npages; ++i, ++pfn) { + hmm_pfns[i] &=3D HMM_PFN_INOUT_FLAGS; + hmm_pfns[i] |=3D pfn | cpu_flags; + } goto out_unlock; } =20 @@ -507,8 +518,10 @@ static int hmm_vma_walk_hugetlb_entry(pte_t *pte, unsi= gned long hmask, } =20 pfn =3D pte_pfn(entry) + ((start & ~hmask) >> PAGE_SHIFT); - for (; addr < end; addr +=3D PAGE_SIZE, i++, pfn++) - range->hmm_pfns[i] =3D pfn | cpu_flags; + for (; addr < end; addr +=3D PAGE_SIZE, i++, pfn++) { + range->hmm_pfns[i] &=3D HMM_PFN_INOUT_FLAGS; + range->hmm_pfns[i] |=3D pfn | cpu_flags; + } =20 spin_unlock(ptl); return 0; --=20 2.49.0