From patchwork Sun Oct 27 14:21:10 2024 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Leon Romanovsky X-Patchwork-Id: 13852605 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 178631684AC; Sun, 27 Oct 2024 14:22:28 +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=1730038949; cv=none; b=KIzE/8gZi8Jd15ThWJ+xItWnpjuKVTZM+ZWpefiTP7K0bpCdo41nnnb+BKJP2BURhyI0YsHLulSFV6fyp3+q6ahWqNvk13e0KQQZWcPObo+3GuXUaWr2ouGJmBpeeLzNkJYQxaKLA7M0ck+OgLBKsSaNrH9QeKNNfMHoejNbe+Q= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1730038949; c=relaxed/simple; bh=LyGbooKE736rWckmyvuR6Y2aUxxUKiIhQ25bI43LeHo=; h=From:To:Cc:Subject:Date:Message-ID:In-Reply-To:References: MIME-Version; b=pTnNwAdpMpFuyAf2SIG2nyz0PArQJK4GvrKwJljfOKXff4GiH2oURWzL+50kzzqbK3vDUbv8lHryE4NBd0Ng/h6tAI28qIPyw8SVHzJaFwtaEYfbARQY2doZ3hKU7WVXuBpxt3fx3yJg+cc1qivD62psabV3GQS5QAXsn4wRNls= ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=kernel.org header.i=@kernel.org header.b=iCkLbrpn; 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="iCkLbrpn" Received: by smtp.kernel.org (Postfix) with ESMTPSA id CBBC4C4CEC3; Sun, 27 Oct 2024 14:22:27 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=kernel.org; s=k20201202; t=1730038948; bh=LyGbooKE736rWckmyvuR6Y2aUxxUKiIhQ25bI43LeHo=; h=From:To:Cc:Subject:Date:In-Reply-To:References:From; b=iCkLbrpnlImhB9B2714xCMDVyAnzWG7MsfR2tObG6bSGDFDz4Bf4CI0mqKt+rhuYq oH9+qokY2xOMGvGOGy85p6vNn6z9dqDdwZ9MAzJ/Y7n8iQv0e0nn5FsdeSoMXGJcFj B+Zi8xW0UVh0uK/OidgiacDE2NCdMWAyryo2eQ61nfECpDk59aRsqWtCbWH4zdhzfH EE5mWIwZYs2U2XkGvGVAKEq7GkstM4Q+7cbJ824WG2VF+/8pl7vlytQS/XVuNbujES urNdKuuovQ1egFVlgv0jTDSmxVbzWG5blHyNDBWJJkFVst1jo9u8sMvdVfv9ThBNkJ kD4ta2u0CCROg== From: Leon Romanovsky To: Jens Axboe , Jason Gunthorpe , Robin Murphy , Joerg Roedel , Will Deacon , Christoph Hellwig , Sagi Grimberg Cc: Leon Romanovsky , Keith Busch , Bjorn Helgaas , Logan Gunthorpe , Yishai Hadas , Shameer Kolothum , Kevin Tian , Alex Williamson , Marek Szyprowski , =?utf-8?b?SsOpcsO0bWUgR2xpc3Nl?= , Andrew Morton , Jonathan Corbet , 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 Subject: [PATCH 10/18] mm/hmm: let users to tag specific PFN with DMA mapped bit Date: Sun, 27 Oct 2024 16:21:10 +0200 Message-ID: <6c79710ccc5d9fec36172fea13498e30132a0600.1730037276.git.leon@kernel.org> X-Mailer: git-send-email 2.46.2 In-Reply-To: References: Precedence: bulk X-Mailing-List: linux-rdma@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 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. Signed-off-by: Leon Romanovsky --- include/linux/hmm.h | 14 ++++++++++++++ mm/hmm.c | 34 +++++++++++++++++++++------------- 2 files changed, 35 insertions(+), 13 deletions(-) diff --git a/include/linux/hmm.h b/include/linux/hmm.h index 126a36571667..5dd655f6766b 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. @@ -36,6 +38,10 @@ enum hmm_pfn_flags { HMM_PFN_VALID = 1UL << (BITS_PER_LONG - 1), HMM_PFN_WRITE = 1UL << (BITS_PER_LONG - 2), HMM_PFN_ERROR = 1UL << (BITS_PER_LONG - 3), + + /* Sticky flag, carried from Input to Output */ + HMM_PFN_DMA_MAPPED = 1UL << (BITS_PER_LONG - 7), + HMM_PFN_ORDER_SHIFT = (BITS_PER_LONG - 8), /* Input flags */ @@ -57,6 +63,14 @@ static inline struct page *hmm_pfn_to_page(unsigned long hmm_pfn) return pfn_to_page(hmm_pfn & ~HMM_PFN_FLAGS); } +/* + * 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 7e0229ae4a5a..2a0c34d7cb2b 100644 --- a/mm/hmm.c +++ b/mm/hmm.c @@ -44,8 +44,10 @@ static int hmm_pfns_fill(unsigned long addr, unsigned long end, { unsigned long i = (addr - range->start) >> PAGE_SHIFT; - for (; addr < end; addr += PAGE_SIZE, i++) - range->hmm_pfns[i] = cpu_flags; + for (; addr < end; addr += PAGE_SIZE, i++) { + range->hmm_pfns[i] &= HMM_PFN_DMA_MAPPED; + range->hmm_pfns[i] |= cpu_flags; + } return 0; } @@ -202,8 +204,10 @@ static int hmm_vma_handle_pmd(struct mm_walk *walk, unsigned long addr, return hmm_vma_fault(addr, end, required_fault, walk); pfn = pmd_pfn(pmd) + ((addr & ~PMD_MASK) >> PAGE_SHIFT); - for (i = 0; addr < end; addr += PAGE_SIZE, i++, pfn++) - hmm_pfns[i] = pfn | cpu_flags; + for (i = 0; addr < end; addr += PAGE_SIZE, i++, pfn++) { + hmm_pfns[i] &= HMM_PFN_DMA_MAPPED; + hmm_pfns[i] |= pfn | cpu_flags; + } return 0; } #else /* CONFIG_TRANSPARENT_HUGEPAGE */ @@ -236,7 +240,7 @@ static int hmm_vma_handle_pte(struct mm_walk *walk, unsigned long addr, hmm_pte_need_fault(hmm_vma_walk, pfn_req_flags, 0); if (required_fault) goto fault; - *hmm_pfn = 0; + *hmm_pfn = *hmm_pfn & HMM_PFN_DMA_MAPPED; return 0; } @@ -253,14 +257,14 @@ static int hmm_vma_handle_pte(struct mm_walk *walk, unsigned long addr, cpu_flags = HMM_PFN_VALID; if (is_writable_device_private_entry(entry)) cpu_flags |= HMM_PFN_WRITE; - *hmm_pfn = swp_offset_pfn(entry) | cpu_flags; + *hmm_pfn = (*hmm_pfn & HMM_PFN_DMA_MAPPED) | swp_offset_pfn(entry) | cpu_flags; return 0; } required_fault = hmm_pte_need_fault(hmm_vma_walk, pfn_req_flags, 0); if (!required_fault) { - *hmm_pfn = 0; + *hmm_pfn = *hmm_pfn & HMM_PFN_DMA_MAPPED; return 0; } @@ -304,11 +308,11 @@ static int hmm_vma_handle_pte(struct mm_walk *walk, unsigned long addr, pte_unmap(ptep); return -EFAULT; } - *hmm_pfn = HMM_PFN_ERROR; + *hmm_pfn = (*hmm_pfn & HMM_PFN_DMA_MAPPED) | HMM_PFN_ERROR; return 0; } - *hmm_pfn = pte_pfn(pte) | cpu_flags; + *hmm_pfn = (*hmm_pfn & HMM_PFN_DMA_MAPPED) | pte_pfn(pte) | cpu_flags; return 0; fault: @@ -448,8 +452,10 @@ static int hmm_vma_walk_pud(pud_t *pudp, unsigned long start, unsigned long end, } pfn = pud_pfn(pud) + ((addr & ~PUD_MASK) >> PAGE_SHIFT); - for (i = 0; i < npages; ++i, ++pfn) - hmm_pfns[i] = pfn | cpu_flags; + for (i = 0; i < npages; ++i, ++pfn) { + hmm_pfns[i] &= HMM_PFN_DMA_MAPPED; + hmm_pfns[i] |= pfn | cpu_flags; + } goto out_unlock; } @@ -507,8 +513,10 @@ static int hmm_vma_walk_hugetlb_entry(pte_t *pte, unsigned long hmask, } pfn = pte_pfn(entry) + ((start & ~hmask) >> PAGE_SHIFT); - for (; addr < end; addr += PAGE_SIZE, i++, pfn++) - range->hmm_pfns[i] = pfn | cpu_flags; + for (; addr < end; addr += PAGE_SIZE, i++, pfn++) { + range->hmm_pfns[i] &= HMM_PFN_DMA_MAPPED; + range->hmm_pfns[i] |= pfn | cpu_flags; + } spin_unlock(ptl); return 0;