linux-kernel - [PATCH 2/8] mm: memory: extend finish

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-Id: <e3f4ae78ef2d565a65fadaa843e53a24bf5b57e4.1714978902.git.baolin.wang@linux.alibaba.com>
Date: Mon,  6 May 2024 16:46:26 +0800
From: Baolin Wang <baolin.wang@...ux.alibaba.com>
To: akpm@...ux-foundation.org,
	hughd@...gle.com
Cc: willy@...radead.org,
	david@...hat.com,
	ioworker0@...il.com,
	wangkefeng.wang@...wei.com,
	ying.huang@...el.com,
	21cnbao@...il.com,
	ryan.roberts@....com,
	shy828301@...il.com,
	ziy@...dia.com,
	baolin.wang@...ux.alibaba.com,
	linux-mm@...ck.org,
	linux-kernel@...r.kernel.org
Subject: [PATCH 2/8] mm: memory: extend finish_fault() to support large folio

Add large folio mapping establishment support for finish_fault() as a preparation,
to support multi-size THP allocation of anonymous shmem pages in the following
patches.

Signed-off-by: Baolin Wang <baolin.wang@...ux.alibaba.com>
---
 mm/memory.c | 43 +++++++++++++++++++++++++++++++++----------
 1 file changed, 33 insertions(+), 10 deletions(-)

diff --git a/mm/memory.c b/mm/memory.c
index eea6e4984eae..936377220b77 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -4747,9 +4747,12 @@ vm_fault_t finish_fault(struct vm_fault *vmf)
 {
 	struct vm_area_struct *vma = vmf->vma;
 	struct page *page;
+	struct folio *folio;
 	vm_fault_t ret;
 	bool is_cow = (vmf->flags & FAULT_FLAG_WRITE) &&
 		      !(vma->vm_flags & VM_SHARED);
+	int type, nr_pages, i;
+	unsigned long addr = vmf->address;
 
 	/* Did we COW the page? */
 	if (is_cow)
@@ -4780,24 +4783,44 @@ vm_fault_t finish_fault(struct vm_fault *vmf)
 			return VM_FAULT_OOM;
 	}
 
+	folio = page_folio(page);
+	nr_pages = folio_nr_pages(folio);
+
+	if (unlikely(userfaultfd_armed(vma))) {
+		nr_pages = 1;
+	} else if (nr_pages > 1) {
+		unsigned long start = ALIGN_DOWN(vmf->address, nr_pages * PAGE_SIZE);
+		unsigned long end = start + nr_pages * PAGE_SIZE;
+
+		/* In case the folio size in page cache beyond the VMA limits. */
+		addr = max(start, vma->vm_start);
+		nr_pages = (min(end, vma->vm_end) - addr) >> PAGE_SHIFT;
+
+		page = folio_page(folio, (addr - start) >> PAGE_SHIFT);
+	}
 	vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd,
-				      vmf->address, &vmf->ptl);
+				       addr, &vmf->ptl);
 	if (!vmf->pte)
 		return VM_FAULT_NOPAGE;
 
 	/* Re-check under ptl */
-	if (likely(!vmf_pte_changed(vmf))) {
-		struct folio *folio = page_folio(page);
-		int type = is_cow ? MM_ANONPAGES : mm_counter_file(folio);
-
-		set_pte_range(vmf, folio, page, 1, vmf->address);
-		add_mm_counter(vma->vm_mm, type, 1);
-		ret = 0;
-	} else {
-		update_mmu_tlb(vma, vmf->address, vmf->pte);
+	if (nr_pages == 1 && unlikely(vmf_pte_changed(vmf))) {
+		update_mmu_tlb(vma, addr, vmf->pte);
+		ret = VM_FAULT_NOPAGE;
+		goto unlock;
+	} else if (nr_pages > 1 && !pte_range_none(vmf->pte, nr_pages)) {
+		for (i = 0; i < nr_pages; i++)
+			update_mmu_tlb(vma, addr + PAGE_SIZE * i, vmf->pte + i);
 		ret = VM_FAULT_NOPAGE;
+		goto unlock;
 	}
 
+	set_pte_range(vmf, folio, page, nr_pages, addr);
+	type = is_cow ? MM_ANONPAGES : mm_counter_file(folio);
+	add_mm_counter(vma->vm_mm, type, nr_pages);
+	ret = 0;
+
+unlock:
 	pte_unmap_unlock(vmf->pte, vmf->ptl);
 	return ret;
 }
-- 
2.39.3