linux-kernel - [PATCH RFC v2 04/12] mm: Convert vmf_insert_mixed() from using pte_devmap to pte

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: <a642ce4101077e4493153f482639d1f34382d364.1739941374.git-series.apopple@nvidia.com>
Date: Wed, 19 Feb 2025 16:04:48 +1100
From: Alistair Popple <apopple@...dia.com>
To: akpm@...ux-foundation.org,
	linux-mm@...ck.org
Cc: Alistair Popple <apopple@...dia.com>,
	gerald.schaefer@...ux.ibm.com,
	dan.j.williams@...el.com,
	jgg@...pe.ca,
	willy@...radead.org,
	david@...hat.com,
	linux-kernel@...r.kernel.org,
	nvdimm@...ts.linux.dev,
	linux-fsdevel@...r.kernel.org,
	linux-ext4@...r.kernel.org,
	linux-xfs@...r.kernel.org,
	jhubbard@...dia.com,
	hch@....de,
	zhang.lyra@...il.com,
	debug@...osinc.com,
	bjorn@...nel.org,
	balbirs@...dia.com
Subject: [PATCH RFC v2 04/12] mm: Convert vmf_insert_mixed() from using pte_devmap to pte_special

DAX no longer requires device PTEs as it always has a ZONE_DEVICE page
associated with the PTE that can be reference counted normally. Other users
of pte_devmap are drivers that set PFN_DEV when calling vmf_insert_mixed()
which ensures vm_normal_page() returns NULL for these entries.

There is no reason to distinguish these pte_devmap users so in order to
free up a PTE bit use pte_special instead for entries created with
vmf_insert_mixed(). This will ensure vm_normal_page() will continue to
return NULL for these pages.

Architectures that don't support pte_special also don't support pte_devmap
so those will continue to rely on pfn_valid() to determine if the page can
be mapped.

Signed-off-by: Alistair Popple <apopple@...dia.com>
---
 mm/hmm.c    |  3 ---
 mm/memory.c | 20 ++------------------
 mm/vmscan.c |  2 +-
 3 files changed, 3 insertions(+), 22 deletions(-)

diff --git a/mm/hmm.c b/mm/hmm.c
index db12c0a..9e43008 100644
--- a/mm/hmm.c
+++ b/mm/hmm.c
@@ -292,13 +292,10 @@ static int hmm_vma_handle_pte(struct mm_walk *walk, unsigned long addr,
 		goto fault;
 
 	/*
-	 * Bypass devmap pte such as DAX page when all pfn requested
-	 * flags(pfn_req_flags) are fulfilled.
 	 * Since each architecture defines a struct page for the zero page, just
 	 * fall through and treat it like a normal page.
 	 */
 	if (!vm_normal_page(walk->vma, addr, pte) &&
-	    !pte_devmap(pte) &&
 	    !is_zero_pfn(pte_pfn(pte))) {
 		if (hmm_pte_need_fault(hmm_vma_walk, pfn_req_flags, 0)) {
 			pte_unmap(ptep);
diff --git a/mm/memory.c b/mm/memory.c
index bdc8dce..84447c7 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -605,16 +605,6 @@ struct page *vm_normal_page(struct vm_area_struct *vma, unsigned long addr,
 			return NULL;
 		if (is_zero_pfn(pfn))
 			return NULL;
-		if (pte_devmap(pte))
-		/*
-		 * NOTE: New users of ZONE_DEVICE will not set pte_devmap()
-		 * and will have refcounts incremented on their struct pages
-		 * when they are inserted into PTEs, thus they are safe to
-		 * return here. Legacy ZONE_DEVICE pages that set pte_devmap()
-		 * do not have refcounts. Example of legacy ZONE_DEVICE is
-		 * MEMORY_DEVICE_FS_DAX type in pmem or virtio_fs drivers.
-		 */
-			return NULL;
 
 		print_bad_pte(vma, addr, pte, NULL);
 		return NULL;
@@ -2454,10 +2444,7 @@ static vm_fault_t insert_pfn(struct vm_area_struct *vma, unsigned long addr,
 	}
 
 	/* Ok, finally just insert the thing.. */
-	if (pfn_t_devmap(pfn))
-		entry = pte_mkdevmap(pfn_t_pte(pfn, prot));
-	else
-		entry = pte_mkspecial(pfn_t_pte(pfn, prot));
+	entry = pte_mkspecial(pfn_t_pte(pfn, prot));
 
 	if (mkwrite) {
 		entry = pte_mkyoung(entry);
@@ -2568,8 +2555,6 @@ static bool vm_mixed_ok(struct vm_area_struct *vma, pfn_t pfn, bool mkwrite)
 	/* these checks mirror the abort conditions in vm_normal_page */
 	if (vma->vm_flags & VM_MIXEDMAP)
 		return true;
-	if (pfn_t_devmap(pfn))
-		return true;
 	if (is_zero_pfn(pfn_t_to_pfn(pfn)))
 		return true;
 	return false;
@@ -2599,8 +2584,7 @@ static vm_fault_t __vm_insert_mixed(struct vm_area_struct *vma,
 	 * than insert_pfn).  If a zero_pfn were inserted into a VM_MIXEDMAP
 	 * without pte special, it would there be refcounted as a normal page.
 	 */
-	if (!IS_ENABLED(CONFIG_ARCH_HAS_PTE_SPECIAL) &&
-	    !pfn_t_devmap(pfn) && pfn_t_valid(pfn)) {
+	if (!IS_ENABLED(CONFIG_ARCH_HAS_PTE_SPECIAL) && pfn_t_valid(pfn)) {
 		struct page *page;
 
 		/*
diff --git a/mm/vmscan.c b/mm/vmscan.c
index fcca38b..b7b4b7f 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -3377,7 +3377,7 @@ static unsigned long get_pte_pfn(pte_t pte, struct vm_area_struct *vma, unsigned
 	if (!pte_present(pte) || is_zero_pfn(pfn))
 		return -1;
 
-	if (WARN_ON_ONCE(pte_devmap(pte) || pte_special(pte)))
+	if (WARN_ON_ONCE(pte_special(pte)))
 		return -1;
 
 	if (!pte_young(pte) && !mm_has_notifiers(vma->vm_mm))
-- 
git-series 0.9.1