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: <64f1664980bed3da01b771afdfc4056825b61277.1725941415.git-series.apopple@nvidia.com>
Date: Tue, 10 Sep 2024 14:14:34 +1000
From: Alistair Popple <apopple@...dia.com>
To: dan.j.williams@...el.com,
	linux-mm@...ck.org
Cc: Alistair Popple <apopple@...dia.com>,
	vishal.l.verma@...el.com,
	dave.jiang@...el.com,
	logang@...tatee.com,
	bhelgaas@...gle.com,
	jack@...e.cz,
	jgg@...pe.ca,
	catalin.marinas@....com,
	will@...nel.org,
	mpe@...erman.id.au,
	npiggin@...il.com,
	dave.hansen@...ux.intel.com,
	ira.weiny@...el.com,
	willy@...radead.org,
	djwong@...nel.org,
	tytso@....edu,
	linmiaohe@...wei.com,
	david@...hat.com,
	peterx@...hat.com,
	linux-doc@...r.kernel.org,
	linux-kernel@...r.kernel.org,
	linux-arm-kernel@...ts.infradead.org,
	linuxppc-dev@...ts.ozlabs.org,
	nvdimm@...ts.linux.dev,
	linux-cxl@...r.kernel.org,
	linux-fsdevel@...r.kernel.org,
	linux-ext4@...r.kernel.org,
	linux-xfs@...r.kernel.org,
	jhubbard@...dia.com,
	hch@....de,
	david@...morbit.com
Subject: [PATCH 09/12] mm: Update vm_normal_page() callers to accept FS DAX pages

Currently if a PTE points to a FS DAX page vm_normal_page() will
return NULL as these have their own special refcounting scheme. A
future change will allow FS DAX pages to be refcounted the same as any
other normal page.

Therefore vm_normal_page() will start returning FS DAX pages. To avoid
any change in behaviour callers that don't expect FS DAX pages will
need to explicitly check for this. As vm_normal_page() can already
return ZONE_DEVICE pages most callers already include a check for any
ZONE_DEVICE page.

However some callers don't, so add explicit checks where required.

Signed-off-by: Alistair Popple <apopple@...dia.com>
---
 arch/x86/mm/pat/memtype.c |  4 +++-
 fs/proc/task_mmu.c        | 16 ++++++++++++----
 mm/memcontrol-v1.c        |  2 +-
 3 files changed, 16 insertions(+), 6 deletions(-)

diff --git a/arch/x86/mm/pat/memtype.c b/arch/x86/mm/pat/memtype.c
index 1fa0bf6..eb84593 100644
--- a/arch/x86/mm/pat/memtype.c
+++ b/arch/x86/mm/pat/memtype.c
@@ -951,6 +951,7 @@ static void free_pfn_range(u64 paddr, unsigned long size)
 static int follow_phys(struct vm_area_struct *vma, unsigned long *prot,
 		resource_size_t *phys)
 {
+	struct folio *folio;
 	pte_t *ptep, pte;
 	spinlock_t *ptl;
 
@@ -960,7 +961,8 @@ static int follow_phys(struct vm_area_struct *vma, unsigned long *prot,
 	pte = ptep_get(ptep);
 
 	/* Never return PFNs of anon folios in COW mappings. */
-	if (vm_normal_folio(vma, vma->vm_start, pte)) {
+	folio = vm_normal_folio(vma, vma->vm_start, pte);
+	if (folio || (folio && !folio_is_device_dax(folio))) {
 		pte_unmap_unlock(ptep, ptl);
 		return -EINVAL;
 	}
diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index 5f171ad..456b010 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -816,6 +816,8 @@ static void smaps_pte_entry(pte_t *pte, unsigned long addr,
 
 	if (pte_present(ptent)) {
 		page = vm_normal_page(vma, addr, ptent);
+		if (page && is_device_dax_page(page))
+			page = NULL;
 		young = pte_young(ptent);
 		dirty = pte_dirty(ptent);
 		present = true;
@@ -864,6 +866,8 @@ static void smaps_pmd_entry(pmd_t *pmd, unsigned long addr,
 
 	if (pmd_present(*pmd)) {
 		page = vm_normal_page_pmd(vma, addr, *pmd);
+		if (page && is_device_dax_page(page))
+			page = NULL;
 		present = true;
 	} else if (unlikely(thp_migration_supported() && is_swap_pmd(*pmd))) {
 		swp_entry_t entry = pmd_to_swp_entry(*pmd);
@@ -1385,7 +1389,7 @@ static inline bool pte_is_pinned(struct vm_area_struct *vma, unsigned long addr,
 	if (likely(!test_bit(MMF_HAS_PINNED, &vma->vm_mm->flags)))
 		return false;
 	folio = vm_normal_folio(vma, addr, pte);
-	if (!folio)
+	if (!folio || folio_is_device_dax(folio))
 		return false;
 	return folio_maybe_dma_pinned(folio);
 }
@@ -1710,6 +1714,8 @@ static pagemap_entry_t pte_to_pagemap_entry(struct pagemapread *pm,
 			frame = pte_pfn(pte);
 		flags |= PM_PRESENT;
 		page = vm_normal_page(vma, addr, pte);
+		if (page && is_device_dax_page(page))
+			page = NULL;
 		if (pte_soft_dirty(pte))
 			flags |= PM_SOFT_DIRTY;
 		if (pte_uffd_wp(pte))
@@ -2096,7 +2102,8 @@ static unsigned long pagemap_page_category(struct pagemap_scan_private *p,
 
 		if (p->masks_of_interest & PAGE_IS_FILE) {
 			page = vm_normal_page(vma, addr, pte);
-			if (page && !PageAnon(page))
+			if (page && !PageAnon(page) &&
+			    !is_device_dax_page(page))
 				categories |= PAGE_IS_FILE;
 		}
 
@@ -2158,7 +2165,8 @@ static unsigned long pagemap_thp_category(struct pagemap_scan_private *p,
 
 		if (p->masks_of_interest & PAGE_IS_FILE) {
 			page = vm_normal_page_pmd(vma, addr, pmd);
-			if (page && !PageAnon(page))
+			if (page && !PageAnon(page) &&
+			    !is_device_dax_page(page))
 				categories |= PAGE_IS_FILE;
 		}
 
@@ -2919,7 +2927,7 @@ static struct page *can_gather_numa_stats_pmd(pmd_t pmd,
 		return NULL;
 
 	page = vm_normal_page_pmd(vma, addr, pmd);
-	if (!page)
+	if (!page || is_device_dax_page(page))
 		return NULL;
 
 	if (PageReserved(page))
diff --git a/mm/memcontrol-v1.c b/mm/memcontrol-v1.c
index b37c0d8..e16053c 100644
--- a/mm/memcontrol-v1.c
+++ b/mm/memcontrol-v1.c
@@ -667,7 +667,7 @@ static struct page *mc_handle_present_pte(struct vm_area_struct *vma,
 {
 	struct page *page = vm_normal_page(vma, addr, ptent);
 
-	if (!page)
+	if (!page || is_device_dax_page(page))
 		return NULL;
 	if (PageAnon(page)) {
 		if (!(mc.flags & MOVE_ANON))
-- 
git-series 0.9.1

Powered by blists - more mailing lists

Powered by Openwall GNU/*/Linux Powered by OpenVZ