Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20;
From:   David Hildenbrand <david@redhat.com>
To:     linux-kernel@vger.kernel.org
Cc:     x86@kernel.org, linux-alpha@vger.kernel.org,
        linux-arm-kernel@lists.infradead.org, linux-ia64@vger.kernel.org,
        linux-mips@vger.kernel.org, linuxppc-dev@lists.ozlabs.org,
        sparclinux@vger.kernel.org, linux-um@lists.infradead.org,
        etnaviv@lists.freedesktop.org, dri-devel@lists.freedesktop.org,
        linux-samsung-soc@vger.kernel.org, linux-rdma@vger.kernel.org,
        linux-media@vger.kernel.org, linux-fsdevel@vger.kernel.org,
        linux-mm@kvack.org, linux-perf-users@vger.kernel.org,
        linux-security-module@vger.kernel.org,
        linux-kselftest@vger.kernel.org,
        Linus Torvalds <torvalds@linux-foundation.org>,
        Andrew Morton <akpm@linux-foundation.org>,
        Jason Gunthorpe <jgg@ziepe.ca>,
        John Hubbard <jhubbard@nvidia.com>,
        Peter Xu <peterx@redhat.com>,
        Greg Kroah-Hartman <gregkh@linuxfoundation.org>,
        Andrea Arcangeli <aarcange@redhat.com>,
        Hugh Dickins <hughd@google.com>, Nadav Amit <namit@vmware.com>,
        Vlastimil Babka <vbabka@suse.cz>,
        Matthew Wilcox <willy@infradead.org>,
        Mike Kravetz <mike.kravetz@oracle.com>,
        Muchun Song <songmuchun@bytedance.com>,
        Shuah Khan <shuah@kernel.org>,
        Lucas Stach <l.stach@pengutronix.de>,
        David Airlie <airlied@gmail.com>,
        Oded Gabbay <ogabbay@kernel.org>,
        Arnd Bergmann <arnd@arndb.de>,
        Christoph Hellwig <hch@infradead.org>,
        Alex Williamson <alex.williamson@redhat.com>,
        David Hildenbrand <david@redhat.com>
Subject: [PATCH mm-unstable v1 06/20] mm: rework handling in do_wp_page() based on private vs. shared mappings
Date:   Wed, 16 Nov 2022 11:26:45 +0100
Message-Id: <20221116102659.70287-7-david@redhat.com>
In-Reply-To: <20221116102659.70287-1-david@redhat.com>
References: <20221116102659.70287-1-david@redhat.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Precedence: bulk

We want to extent FAULT_FLAG_UNSHARE support to anything mapped into a
COW mapping (pagecache page, zeropage, PFN, ...), not just anonymous pages.
Let's prepare for that by handling shared mappings first such that we can
handle private mappings last.

While at it, use folio-based functions instead of page-based functions
where we touch the code either way.

Signed-off-by: David Hildenbrand <david@redhat.com>
---
 mm/memory.c | 38 +++++++++++++++++---------------------
 1 file changed, 17 insertions(+), 21 deletions(-)

diff --git a/mm/memory.c b/mm/memory.c
index c4fa378ec2a0..c35e6cd32b6a 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -3342,7 +3342,7 @@ static vm_fault_t do_wp_page(struct vm_fault *vmf)
 {
 	const bool unshare = vmf->flags & FAULT_FLAG_UNSHARE;
 	struct vm_area_struct *vma = vmf->vma;
-	struct folio *folio;
+	struct folio *folio = NULL;
 
 	if (likely(!unshare)) {
 		if (userfaultfd_pte_wp(vma, *vmf->pte)) {
@@ -3360,13 +3360,12 @@ static vm_fault_t do_wp_page(struct vm_fault *vmf)
 	}
 
 	vmf->page = vm_normal_page(vma, vmf->address, vmf->orig_pte);
-	if (!vmf->page) {
-		if (unlikely(unshare)) {
-			/* No anonymous page -> nothing to do. */
-			pte_unmap_unlock(vmf->pte, vmf->ptl);
-			return 0;
-		}
 
+	/*
+	 * Shared mapping: we are guaranteed to have VM_WRITE and
+	 * FAULT_FLAG_WRITE set at this point.
+	 */
+	if (vma->vm_flags & (VM_SHARED | VM_MAYSHARE)) {
 		/*
 		 * VM_MIXEDMAP !pfn_valid() case, or VM_SOFTDIRTY clear on a
 		 * VM_PFNMAP VMA.
@@ -3374,20 +3373,19 @@ static vm_fault_t do_wp_page(struct vm_fault *vmf)
 		 * We should not cow pages in a shared writeable mapping.
 		 * Just mark the pages writable and/or call ops->pfn_mkwrite.
 		 */
-		if ((vma->vm_flags & (VM_WRITE|VM_SHARED)) ==
-				     (VM_WRITE|VM_SHARED))
+		if (!vmf->page)
 			return wp_pfn_shared(vmf);
-
-		pte_unmap_unlock(vmf->pte, vmf->ptl);
-		return wp_page_copy(vmf);
+		return wp_page_shared(vmf);
 	}
 
+	if (vmf->page)
+		folio = page_folio(vmf->page);
+
 	/*
-	 * Take out anonymous pages first, anonymous shared vmas are
-	 * not dirty accountable.
+	 * Private mapping: create an exclusive anonymous page copy if reuse
+	 * is impossible. We might miss VM_WRITE for FOLL_FORCE handling.
 	 */
-	folio = page_folio(vmf->page);
-	if (folio_test_anon(folio)) {
+	if (folio && folio_test_anon(folio)) {
 		/*
 		 * If the page is exclusive to this process we must reuse the
 		 * page without further checks.
@@ -3438,19 +3436,17 @@ static vm_fault_t do_wp_page(struct vm_fault *vmf)
 		/* No anonymous page -> nothing to do. */
 		pte_unmap_unlock(vmf->pte, vmf->ptl);
 		return 0;
-	} else if (unlikely((vma->vm_flags & (VM_WRITE|VM_SHARED)) ==
-					(VM_WRITE|VM_SHARED))) {
-		return wp_page_shared(vmf);
 	}
 copy:
 	/*
 	 * Ok, we need to copy. Oh, well..
 	 */
-	get_page(vmf->page);
+	if (folio)
+		folio_get(folio);
 
 	pte_unmap_unlock(vmf->pte, vmf->ptl);
 #ifdef CONFIG_KSM
-	if (PageKsm(vmf->page))
+	if (folio && folio_test_ksm(folio))
 		count_vm_event(COW_KSM);
 #endif
 	return wp_page_copy(vmf);
-- 
2.38.1