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: <20250903011900.3657435-5-balbirs@nvidia.com>
Date: Wed,  3 Sep 2025 11:18:49 +1000
From: Balbir Singh <balbirs@...dia.com>
To: linux-kernel@...r.kernel.org,
	linux-mm@...ck.org
Cc: damon@...ts.linux.dev,
	dri-devel@...ts.freedesktop.org,
	Balbir Singh <balbirs@...dia.com>,
	Andrew Morton <akpm@...ux-foundation.org>,
	David Hildenbrand <david@...hat.com>,
	Zi Yan <ziy@...dia.com>,
	Joshua Hahn <joshua.hahnjy@...il.com>,
	Rakie Kim <rakie.kim@...com>,
	Byungchul Park <byungchul@...com>,
	Gregory Price <gourry@...rry.net>,
	Ying Huang <ying.huang@...ux.alibaba.com>,
	Alistair Popple <apopple@...dia.com>,
	Oscar Salvador <osalvador@...e.de>,
	Lorenzo Stoakes <lorenzo.stoakes@...cle.com>,
	Baolin Wang <baolin.wang@...ux.alibaba.com>,
	"Liam R. Howlett" <Liam.Howlett@...cle.com>,
	Nico Pache <npache@...hat.com>,
	Ryan Roberts <ryan.roberts@....com>,
	Dev Jain <dev.jain@....com>,
	Barry Song <baohua@...nel.org>,
	Lyude Paul <lyude@...hat.com>,
	Danilo Krummrich <dakr@...nel.org>,
	David Airlie <airlied@...il.com>,
	Simona Vetter <simona@...ll.ch>,
	Ralph Campbell <rcampbell@...dia.com>,
	Mika Penttilä <mpenttil@...hat.com>,
	Matthew Brost <matthew.brost@...el.com>,
	Francois Dugast <francois.dugast@...el.com>
Subject: [v4 04/15] mm/huge_memory: implement device-private THP splitting

Add support for splitting device-private THP folios, enabling fallback
to smaller page sizes when large page allocation or migration fails.

Key changes:
- split_huge_pmd(): Handle device-private PMD entries during splitting
- Preserve RMAP_EXCLUSIVE semantics for anonymous exclusive folios
- Skip RMP_USE_SHARED_ZEROPAGE for device-private entries as they
  don't support shared zero page semantics

Cc: Andrew Morton <akpm@...ux-foundation.org>
Cc: David Hildenbrand <david@...hat.com>
Cc: Zi Yan <ziy@...dia.com>
Cc: Joshua Hahn <joshua.hahnjy@...il.com>
Cc: Rakie Kim <rakie.kim@...com>
Cc: Byungchul Park <byungchul@...com>
Cc: Gregory Price <gourry@...rry.net>
Cc: Ying Huang <ying.huang@...ux.alibaba.com>
Cc: Alistair Popple <apopple@...dia.com>
Cc: Oscar Salvador <osalvador@...e.de>
Cc: Lorenzo Stoakes <lorenzo.stoakes@...cle.com>
Cc: Baolin Wang <baolin.wang@...ux.alibaba.com>
Cc: "Liam R. Howlett" <Liam.Howlett@...cle.com>
Cc: Nico Pache <npache@...hat.com>
Cc: Ryan Roberts <ryan.roberts@....com>
Cc: Dev Jain <dev.jain@....com>
Cc: Barry Song <baohua@...nel.org>
Cc: Lyude Paul <lyude@...hat.com>
Cc: Danilo Krummrich <dakr@...nel.org>
Cc: David Airlie <airlied@...il.com>
Cc: Simona Vetter <simona@...ll.ch>
Cc: Ralph Campbell <rcampbell@...dia.com>
Cc: Mika Penttilä <mpenttil@...hat.com>
Cc: Matthew Brost <matthew.brost@...el.com>
Cc: Francois Dugast <francois.dugast@...el.com>

Signed-off-by: Balbir Singh <balbirs@...dia.com>
---
 mm/huge_memory.c | 129 +++++++++++++++++++++++++++++++++--------------
 1 file changed, 91 insertions(+), 38 deletions(-)

diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 0c811d34f418..47fe07b9fee4 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -2888,16 +2888,19 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd,
 	struct page *page;
 	pgtable_t pgtable;
 	pmd_t old_pmd, _pmd;
-	bool young, write, soft_dirty, pmd_migration = false, uffd_wp = false;
-	bool anon_exclusive = false, dirty = false;
+	bool young, write, soft_dirty, uffd_wp = false;
+	bool anon_exclusive = false, dirty = false, present = false;
 	unsigned long addr;
 	pte_t *pte;
 	int i;
+	swp_entry_t swp_entry;
 
 	VM_BUG_ON(haddr & ~HPAGE_PMD_MASK);
 	VM_BUG_ON_VMA(vma->vm_start > haddr, vma);
 	VM_BUG_ON_VMA(vma->vm_end < haddr + HPAGE_PMD_SIZE, vma);
-	VM_BUG_ON(!is_pmd_migration_entry(*pmd) && !pmd_trans_huge(*pmd));
+
+	VM_WARN_ON(!is_pmd_migration_entry(*pmd) && !pmd_trans_huge(*pmd) &&
+			!is_pmd_device_private_entry(*pmd));
 
 	count_vm_event(THP_SPLIT_PMD);
 
@@ -2945,18 +2948,43 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd,
 		return __split_huge_zero_page_pmd(vma, haddr, pmd);
 	}
 
-	pmd_migration = is_pmd_migration_entry(*pmd);
-	if (unlikely(pmd_migration)) {
-		swp_entry_t entry;
 
+	present = pmd_present(*pmd);
+	if (unlikely(!present)) {
+		swp_entry = pmd_to_swp_entry(*pmd);
 		old_pmd = *pmd;
-		entry = pmd_to_swp_entry(old_pmd);
-		page = pfn_swap_entry_to_page(entry);
-		write = is_writable_migration_entry(entry);
-		if (PageAnon(page))
-			anon_exclusive = is_readable_exclusive_migration_entry(entry);
-		young = is_migration_entry_young(entry);
-		dirty = is_migration_entry_dirty(entry);
+
+		folio = pfn_swap_entry_folio(swp_entry);
+		VM_WARN_ON(!is_migration_entry(swp_entry) &&
+				!is_device_private_entry(swp_entry));
+		page = pfn_swap_entry_to_page(swp_entry);
+
+		if (is_pmd_migration_entry(old_pmd)) {
+			write = is_writable_migration_entry(swp_entry);
+			if (PageAnon(page))
+				anon_exclusive =
+					is_readable_exclusive_migration_entry(
+								swp_entry);
+			young = is_migration_entry_young(swp_entry);
+			dirty = is_migration_entry_dirty(swp_entry);
+		} else if (is_pmd_device_private_entry(old_pmd)) {
+			write = is_writable_device_private_entry(swp_entry);
+			anon_exclusive = PageAnonExclusive(page);
+			if (freeze && anon_exclusive &&
+			    folio_try_share_anon_rmap_pmd(folio, page))
+				freeze = false;
+			if (!freeze) {
+				rmap_t rmap_flags = RMAP_NONE;
+
+				folio_ref_add(folio, HPAGE_PMD_NR - 1);
+				if (anon_exclusive)
+					rmap_flags |= RMAP_EXCLUSIVE;
+
+				folio_add_anon_rmap_ptes(folio, page, HPAGE_PMD_NR,
+						 vma, haddr, rmap_flags);
+			}
+		}
+
 		soft_dirty = pmd_swp_soft_dirty(old_pmd);
 		uffd_wp = pmd_swp_uffd_wp(old_pmd);
 	} else {
@@ -3042,30 +3070,49 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd,
 	 * Note that NUMA hinting access restrictions are not transferred to
 	 * avoid any possibility of altering permissions across VMAs.
 	 */
-	if (freeze || pmd_migration) {
+	if (freeze || !present) {
 		for (i = 0, addr = haddr; i < HPAGE_PMD_NR; i++, addr += PAGE_SIZE) {
 			pte_t entry;
-			swp_entry_t swp_entry;
-
-			if (write)
-				swp_entry = make_writable_migration_entry(
-							page_to_pfn(page + i));
-			else if (anon_exclusive)
-				swp_entry = make_readable_exclusive_migration_entry(
-							page_to_pfn(page + i));
-			else
-				swp_entry = make_readable_migration_entry(
-							page_to_pfn(page + i));
-			if (young)
-				swp_entry = make_migration_entry_young(swp_entry);
-			if (dirty)
-				swp_entry = make_migration_entry_dirty(swp_entry);
-			entry = swp_entry_to_pte(swp_entry);
-			if (soft_dirty)
-				entry = pte_swp_mksoft_dirty(entry);
-			if (uffd_wp)
-				entry = pte_swp_mkuffd_wp(entry);
-
+			if (freeze || is_migration_entry(swp_entry)) {
+				if (write)
+					swp_entry = make_writable_migration_entry(
+								page_to_pfn(page + i));
+				else if (anon_exclusive)
+					swp_entry = make_readable_exclusive_migration_entry(
+								page_to_pfn(page + i));
+				else
+					swp_entry = make_readable_migration_entry(
+								page_to_pfn(page + i));
+				if (young)
+					swp_entry = make_migration_entry_young(swp_entry);
+				if (dirty)
+					swp_entry = make_migration_entry_dirty(swp_entry);
+				entry = swp_entry_to_pte(swp_entry);
+				if (soft_dirty)
+					entry = pte_swp_mksoft_dirty(entry);
+				if (uffd_wp)
+					entry = pte_swp_mkuffd_wp(entry);
+			} else {
+				/*
+				 * anon_exclusive was already propagated to the relevant
+				 * pages corresponding to the pte entries when freeze
+				 * is false.
+				 */
+				if (write)
+					swp_entry = make_writable_device_private_entry(
+								page_to_pfn(page + i));
+				else
+					swp_entry = make_readable_device_private_entry(
+								page_to_pfn(page + i));
+				/*
+				 * Young and dirty bits are not progated via swp_entry
+				 */
+				entry = swp_entry_to_pte(swp_entry);
+				if (soft_dirty)
+					entry = pte_swp_mksoft_dirty(entry);
+				if (uffd_wp)
+					entry = pte_swp_mkuffd_wp(entry);
+			}
 			VM_WARN_ON(!pte_none(ptep_get(pte + i)));
 			set_pte_at(mm, addr, pte + i, entry);
 		}
@@ -3092,7 +3139,7 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd,
 	}
 	pte_unmap(pte);
 
-	if (!pmd_migration)
+	if (!is_pmd_migration_entry(*pmd))
 		folio_remove_rmap_pmd(folio, page, vma);
 	if (freeze)
 		put_page(page);
@@ -3104,8 +3151,10 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd,
 void split_huge_pmd_locked(struct vm_area_struct *vma, unsigned long address,
 			   pmd_t *pmd, bool freeze)
 {
+
 	VM_WARN_ON_ONCE(!IS_ALIGNED(address, HPAGE_PMD_SIZE));
-	if (pmd_trans_huge(*pmd) || is_pmd_migration_entry(*pmd))
+	if (pmd_trans_huge(*pmd) || is_pmd_migration_entry(*pmd) ||
+		is_pmd_device_private_entry(*pmd))
 		__split_huge_pmd_locked(vma, pmd, address, freeze);
 }
 
@@ -3284,6 +3333,9 @@ static void lru_add_split_folio(struct folio *folio, struct folio *new_folio,
 	VM_BUG_ON_FOLIO(folio_test_lru(new_folio), folio);
 	lockdep_assert_held(&lruvec->lru_lock);
 
+	if (folio_is_device_private(folio))
+		return;
+
 	if (list) {
 		/* page reclaim is reclaiming a huge page */
 		VM_WARN_ON(folio_test_lru(folio));
@@ -3904,8 +3956,9 @@ static int __folio_split(struct folio *folio, unsigned int new_order,
 	if (nr_shmem_dropped)
 		shmem_uncharge(mapping->host, nr_shmem_dropped);
 
-	if (!ret && is_anon)
+	if (!ret && is_anon && !folio_is_device_private(folio))
 		remap_flags = RMP_USE_SHARED_ZEROPAGE;
+
 	remap_page(folio, 1 << order, remap_flags);
 
 	/*
-- 
2.50.1


Powered by blists - more mailing lists

Powered by Openwall GNU/*/Linux Powered by OpenVZ