From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org X-Spam-Level: X-Spam-Status: No, score=-9.9 required=3.0 tests=DKIMWL_WL_HIGH,DKIM_SIGNED, DKIM_VALID,DKIM_VALID_AU,HEADER_FROM_DIFFERENT_DOMAINS,INCLUDES_PATCH, MAILING_LIST_MULTI,SIGNED_OFF_BY,SPF_HELO_NONE,SPF_PASS,URIBL_BLOCKED, USER_AGENT_GIT autolearn=unavailable autolearn_force=no version=3.4.0 Received: from mail.kernel.org (mail.kernel.org [198.145.29.99]) by smtp.lore.kernel.org (Postfix) with ESMTP id 19603ECE595 for ; Tue, 15 Oct 2019 20:48:27 +0000 (UTC) Received: from kanga.kvack.org (kanga.kvack.org [205.233.56.17]) by mail.kernel.org (Postfix) with ESMTP id C0AFA20872 for ; Tue, 15 Oct 2019 20:48:26 +0000 (UTC) Authentication-Results: mail.kernel.org; dkim=pass (2048-bit key) header.d=nvidia.com header.i=@nvidia.com header.b="Hw/n59XS" DMARC-Filter: OpenDMARC Filter v1.3.2 mail.kernel.org C0AFA20872 Authentication-Results: mail.kernel.org; dmarc=fail (p=none dis=none) header.from=nvidia.com Authentication-Results: mail.kernel.org; spf=pass smtp.mailfrom=owner-linux-mm@kvack.org Received: by kanga.kvack.org (Postfix) id 688328E0005; Tue, 15 Oct 2019 16:48:26 -0400 (EDT) Received: by kanga.kvack.org (Postfix, from userid 40) id 639728E0001; Tue, 15 Oct 2019 16:48:26 -0400 (EDT) X-Delivered-To: int-list-linux-mm@kvack.org Received: by kanga.kvack.org (Postfix, from userid 63042) id 54F028E0005; Tue, 15 Oct 2019 16:48:26 -0400 (EDT) X-Delivered-To: linux-mm@kvack.org Received: from forelay.hostedemail.com (smtprelay0011.hostedemail.com [216.40.44.11]) by kanga.kvack.org (Postfix) with ESMTP id 358658E0001 for ; Tue, 15 Oct 2019 16:48:26 -0400 (EDT) Received: from smtpin07.hostedemail.com (10.5.19.251.rfc1918.com [10.5.19.251]) by forelay04.hostedemail.com (Postfix) with SMTP id AD65D5850 for ; Tue, 15 Oct 2019 20:48:25 +0000 (UTC) X-FDA: 76047206970.07.way38_497f2e510f920 X-HE-Tag: way38_497f2e510f920 X-Filterd-Recvd-Size: 9546 Received: from hqemgate16.nvidia.com (hqemgate16.nvidia.com [216.228.121.65]) by imf36.hostedemail.com (Postfix) with ESMTP for ; Tue, 15 Oct 2019 20:48:24 +0000 (UTC) Received: from hqpgpgate101.nvidia.com (Not Verified[216.228.121.13]) by hqemgate16.nvidia.com (using TLS: TLSv1.2, DES-CBC3-SHA) id ; Tue, 15 Oct 2019 13:48:25 -0700 Received: from hqmail.nvidia.com ([172.20.161.6]) by hqpgpgate101.nvidia.com (PGP Universal service); Tue, 15 Oct 2019 13:48:23 -0700 X-PGP-Universal: processed; by hqpgpgate101.nvidia.com on Tue, 15 Oct 2019 13:48:23 -0700 Received: from HQMAIL101.nvidia.com (172.20.187.10) by HQMAIL111.nvidia.com (172.20.187.18) with Microsoft SMTP Server (TLS) id 15.0.1473.3; Tue, 15 Oct 2019 20:48:22 +0000 Received: from hqnvemgw01.nvidia.com (172.20.150.20) by HQMAIL101.nvidia.com (172.20.187.10) with Microsoft SMTP Server (TLS) id 15.0.1473.3 via Frontend Transport; Tue, 15 Oct 2019 20:48:22 +0000 Received: from rcampbell-dev.nvidia.com (Not Verified[10.110.48.66]) by hqnvemgw01.nvidia.com with Trustwave SEG (v7,5,8,10121) id ; Tue, 15 Oct 2019 13:48:22 -0700 From: Ralph Campbell To: Jerome Glisse , John Hubbard , Christoph Hellwig , Jason Gunthorpe CC: , , Ralph Campbell Subject: [PATCH v2 1/3] mm/hmm: make full use of walk_page_range() Date: Tue, 15 Oct 2019 13:48:12 -0700 Message-ID: <20191015204814.30099-2-rcampbell@nvidia.com> X-Mailer: git-send-email 2.20.1 In-Reply-To: <20191015204814.30099-1-rcampbell@nvidia.com> References: <20191015204814.30099-1-rcampbell@nvidia.com> MIME-Version: 1.0 X-NVConfidentiality: public Content-Type: text/plain; charset="UTF-8" Content-Transfer-Encoding: quoted-printable DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=nvidia.com; s=n1; t=1571172506; bh=QwxewNyXzfZfuepmVwzO3XNBOMjKY9xTiFhnt408MdI=; h=X-PGP-Universal:From:To:CC:Subject:Date:Message-ID:X-Mailer: In-Reply-To:References:MIME-Version:X-NVConfidentiality: Content-Type:Content-Transfer-Encoding; b=Hw/n59XSWuFhDP4PRm8itMtwFrLTYByXO0MPfPJvYWuAk/+4ewIRTXRoKT5Q4A95p 0hjcNOyEqwM2AbbNq8ZtvkOx/4iF8bqInFuNE2o6ThWtRqa2xHclbsaw4Zh0n+xMAT 56uUjjbXekNAM/rxK7hJ3jT6V/I0XH8/0DLcHg0gonJyoprrN5dMVq0Czr7pDu4YcQ P87kAvqhslY+tlDMhJWZjbncqnRbJAzPmDqJTODlqfyQDAjAJ6zRLNH1ceMv4DcKlz gGwMBZf055jA21ll4+7/j0vcMX45rcu9P/36OvtV5ZpOS+othSqk6rI9WbMCbsrGy+ /6VHTdUBvLL3A== X-Bogosity: Ham, tests=bogofilter, spamicity=0.000000, version=1.2.4 Sender: owner-linux-mm@kvack.org Precedence: bulk X-Loop: owner-majordomo@kvack.org List-ID: hmm_range_fault() calls find_vma() and walk_page_range() in a loop. This is unnecessary duplication since walk_page_range() calls find_vma() in a loop already. Simplify hmm_range_fault() by defining a walk_test() callback function to filter unhandled vmas. This also fixes a bug where hmm_range_fault() was not checking start >=3D vma->vm_start before checking vma->vm_flags so hmm_range_fault() could return an error based on the wrong vma for the requested range. Signed-off-by: Ralph Campbell Cc: "J=C3=A9r=C3=B4me Glisse" Cc: Jason Gunthorpe Cc: Christoph Hellwig --- mm/hmm.c | 143 +++++++++++++++++++++++++++++++------------------------ 1 file changed, 80 insertions(+), 63 deletions(-) diff --git a/mm/hmm.c b/mm/hmm.c index 902f5fa6bf93..5df0dbf77e89 100644 --- a/mm/hmm.c +++ b/mm/hmm.c @@ -252,18 +252,15 @@ static int hmm_vma_do_fault(struct mm_walk *walk, uns= igned long addr, return -EFAULT; } =20 -static int hmm_pfns_bad(unsigned long addr, - unsigned long end, - struct mm_walk *walk) +static int hmm_pfns_fill(unsigned long addr, unsigned long end, + struct hmm_range *range, enum hmm_pfn_value_e value) { - struct hmm_vma_walk *hmm_vma_walk =3D walk->private; - struct hmm_range *range =3D hmm_vma_walk->range; uint64_t *pfns =3D range->pfns; unsigned long i; =20 i =3D (addr - range->start) >> PAGE_SHIFT; for (; addr < end; addr +=3D PAGE_SIZE, i++) - pfns[i] =3D range->values[HMM_PFN_ERROR]; + pfns[i] =3D range->values[value]; =20 return 0; } @@ -584,7 +581,7 @@ static int hmm_vma_walk_pmd(pmd_t *pmdp, } return 0; } else if (!pmd_present(pmd)) - return hmm_pfns_bad(start, end, walk); + return hmm_pfns_fill(start, end, range, HMM_PFN_ERROR); =20 if (pmd_devmap(pmd) || pmd_trans_huge(pmd)) { /* @@ -612,7 +609,7 @@ static int hmm_vma_walk_pmd(pmd_t *pmdp, * recover. */ if (pmd_bad(pmd)) - return hmm_pfns_bad(start, end, walk); + return hmm_pfns_fill(start, end, range, HMM_PFN_ERROR); =20 ptep =3D pte_offset_map(pmdp, addr); i =3D (addr - range->start) >> PAGE_SHIFT; @@ -770,13 +767,68 @@ static int hmm_vma_walk_hugetlb_entry(pte_t *pte, uns= igned long hmask, #define hmm_vma_walk_hugetlb_entry NULL #endif /* CONFIG_HUGETLB_PAGE */ =20 -static void hmm_pfns_clear(struct hmm_range *range, - uint64_t *pfns, - unsigned long addr, - unsigned long end) +static bool hmm_range_needs_fault(unsigned long addr, unsigned long end, + const struct hmm_vma_walk *hmm_vma_walk) { - for (; addr < end; addr +=3D PAGE_SIZE, pfns++) - *pfns =3D range->values[HMM_PFN_NONE]; + bool fault, write_fault; + unsigned long i; + uint64_t *pfns; + + if (hmm_vma_walk->flags & HMM_FAULT_SNAPSHOT) + return false; + + fault =3D false; + write_fault =3D false; + pfns =3D hmm_vma_walk->range->pfns; + i =3D (addr - hmm_vma_walk->range->start) >> PAGE_SHIFT; + for (; addr < end; addr +=3D PAGE_SIZE, i++) { + hmm_pte_need_fault(hmm_vma_walk, pfns[i], 0, + &fault, &write_fault); + if (fault || write_fault) + return true; + } + return false; +} + +static int hmm_vma_walk_test(unsigned long start, unsigned long end, + struct mm_walk *walk) +{ + struct hmm_vma_walk *hmm_vma_walk =3D walk->private; + struct hmm_range *range =3D hmm_vma_walk->range; + struct vm_area_struct *vma =3D walk->vma; + + /* If range is no longer valid, force retry. */ + if (!range->valid) + return -EBUSY; + + /* + * Skip vma ranges that don't have struct page backing them or + * map I/O devices directly. + */ + if (vma->vm_flags & (VM_IO | VM_PFNMAP | VM_MIXEDMAP)) + return -EFAULT; + + /* + * If the vma does not allow read access, then assume that it does not + * allow write access either. HMM does not support architectures + * that allow write without read. + */ + if (!(vma->vm_flags & VM_READ)) { + /* + * Check to see if a fault is requested for any page in the + * range. + */ + if (hmm_range_needs_fault(start, end, hmm_vma_walk)) + return -EFAULT; + + hmm_pfns_fill(start, end, range, HMM_PFN_NONE); + hmm_vma_walk->last =3D end; + + /* Skip this vma and continue processing the next vma. */ + return 1; + } + + return 0; } =20 /* @@ -857,6 +909,7 @@ static const struct mm_walk_ops hmm_walk_ops =3D { .pmd_entry =3D hmm_vma_walk_pmd, .pte_hole =3D hmm_vma_walk_hole, .hugetlb_entry =3D hmm_vma_walk_hugetlb_entry, + .test_walk =3D hmm_vma_walk_test, }; =20 /** @@ -889,63 +942,27 @@ static const struct mm_walk_ops hmm_walk_ops =3D { */ long hmm_range_fault(struct hmm_range *range, unsigned int flags) { - const unsigned long device_vma =3D VM_IO | VM_PFNMAP | VM_MIXEDMAP; - unsigned long start =3D range->start, end; - struct hmm_vma_walk hmm_vma_walk; + unsigned long start =3D range->start; + struct hmm_vma_walk hmm_vma_walk =3D { + .range =3D range, + .last =3D start, + .flags =3D flags, + }; struct hmm *hmm =3D range->hmm; - struct vm_area_struct *vma; int ret; =20 lockdep_assert_held(&hmm->mmu_notifier.mm->mmap_sem); =20 do { - /* If range is no longer valid force retry. */ - if (!range->valid) - return -EBUSY; + ret =3D walk_page_range(hmm->mmu_notifier.mm, start, range->end, + &hmm_walk_ops, &hmm_vma_walk); + start =3D hmm_vma_walk.last; =20 - vma =3D find_vma(hmm->mmu_notifier.mm, start); - if (vma =3D=3D NULL || (vma->vm_flags & device_vma)) - return -EFAULT; + /* Keep trying while the range is valid. */ + } while (ret =3D=3D -EBUSY && range->valid); =20 - if (!(vma->vm_flags & VM_READ)) { - /* - * If vma do not allow read access, then assume that it - * does not allow write access, either. HMM does not - * support architecture that allow write without read. - */ - hmm_pfns_clear(range, range->pfns, - range->start, range->end); - return -EPERM; - } - - hmm_vma_walk.pgmap =3D NULL; - hmm_vma_walk.last =3D start; - hmm_vma_walk.flags =3D flags; - hmm_vma_walk.range =3D range; - end =3D min(range->end, vma->vm_end); - - walk_page_range(vma->vm_mm, start, end, &hmm_walk_ops, - &hmm_vma_walk); - - do { - ret =3D walk_page_range(vma->vm_mm, start, end, - &hmm_walk_ops, &hmm_vma_walk); - start =3D hmm_vma_walk.last; - - /* Keep trying while the range is valid. */ - } while (ret =3D=3D -EBUSY && range->valid); - - if (ret) { - unsigned long i; - - i =3D (hmm_vma_walk.last - range->start) >> PAGE_SHIFT; - hmm_pfns_clear(range, &range->pfns[i], - hmm_vma_walk.last, range->end); - return ret; - } - start =3D end; - - } while (start < range->end); + if (ret) + return ret; =20 return (hmm_vma_walk.last - range->start) >> PAGE_SHIFT; } --=20 2.20.1