linux-kernel - [PATCH v2 7/7] mm: Optimize mprotect() through PTE-batching

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: <20250429052336.18912-8-dev.jain@arm.com>
Date: Tue, 29 Apr 2025 10:53:36 +0530
From: Dev Jain <dev.jain@....com>
To: akpm@...ux-foundation.org
Cc: ryan.roberts@....com,
	david@...hat.com,
	willy@...radead.org,
	linux-mm@...ck.org,
	linux-kernel@...r.kernel.org,
	catalin.marinas@....com,
	will@...nel.org,
	Liam.Howlett@...cle.com,
	lorenzo.stoakes@...cle.com,
	vbabka@...e.cz,
	jannh@...gle.com,
	anshuman.khandual@....com,
	peterx@...hat.com,
	joey.gouly@....com,
	ioworker0@...il.com,
	baohua@...nel.org,
	kevin.brodsky@....com,
	quic_zhenhuah@...cinc.com,
	christophe.leroy@...roup.eu,
	yangyicong@...ilicon.com,
	linux-arm-kernel@...ts.infradead.org,
	namit@...are.com,
	hughd@...gle.com,
	yang@...amperecomputing.com,
	ziy@...dia.com,
	Dev Jain <dev.jain@....com>
Subject: [PATCH v2 7/7] mm: Optimize mprotect() through PTE-batching

The common pte_present case does not require the folio. Elide the overhead of
vm_normal_folio() for the small folio case, by making an approximation:
for arm64, pte_batch_hint() is conclusive. For other arches, if the pfns
pointed to by the current and the next PTE are contiguous, check whether
a large folio is actually mapped, and only then make the batch optimization.
Reuse the folio from prot_numa case if possible. Since modify_prot_start_ptes()
gathers access/dirty bits, it lets us batch around pte_needs_flush()
(for parisc, the definition includes the access bit).

Signed-off-by: Dev Jain <dev.jain@....com>
---
 mm/mprotect.c | 49 +++++++++++++++++++++++++++++++++++--------------
 1 file changed, 35 insertions(+), 14 deletions(-)

diff --git a/mm/mprotect.c b/mm/mprotect.c
index baff009fc981..f8382806611f 100644
--- a/mm/mprotect.c
+++ b/mm/mprotect.c
@@ -129,7 +129,7 @@ static bool prot_numa_skip(struct vm_area_struct *vma, struct folio *folio,
 	return false;
 }
 
-static bool prot_numa_avoid_fault(struct vm_area_struct *vma,
+static struct folio *prot_numa_avoid_fault(struct vm_area_struct *vma,
 		unsigned long addr, pte_t *pte, pte_t oldpte, int target_node,
 		int max_nr, int *nr)
 {
@@ -139,25 +139,37 @@ static bool prot_numa_avoid_fault(struct vm_area_struct *vma,
 
 	/* Avoid TLB flush if possible */
 	if (pte_protnone(oldpte))
-		return true;
+		return NULL;
 
 	folio = vm_normal_folio(vma, addr, oldpte);
 	if (!folio)
-		return true;
+		return NULL;
 
 	ret = prot_numa_skip(vma, folio, target_node);
 	if (ret) {
 		if (folio_test_large(folio) && max_nr != 1)
 			*nr = folio_pte_batch(folio, addr, pte, oldpte,
 					      max_nr, flags, NULL, NULL, NULL);
-		return ret;
+		return NULL;
 	}
 	if (folio_use_access_time(folio))
 		folio_xchg_access_time(folio,
 			jiffies_to_msecs(jiffies));
-	return false;
+	return folio;
 }
 
+static bool maybe_contiguous_pte_pfns(pte_t *ptep, pte_t pte)
+{
+	pte_t *next_ptep, next_pte;
+
+	if (pte_batch_hint(ptep, pte) != 1)
+		return true;
+
+	next_ptep = ptep + 1;
+	next_pte = ptep_get(next_ptep);
+
+	return unlikely(pte_pfn(next_pte) - pte_pfn(pte) == PAGE_SIZE);
+}
 static long change_pte_range(struct mmu_gather *tlb,
 		struct vm_area_struct *vma, pmd_t *pmd, unsigned long addr,
 		unsigned long end, pgprot_t newprot, unsigned long cp_flags)
@@ -188,19 +200,28 @@ static long change_pte_range(struct mmu_gather *tlb,
 		oldpte = ptep_get(pte);
 		if (pte_present(oldpte)) {
 			int max_nr = (end - addr) >> PAGE_SHIFT;
+			const fpb_t flags = FPB_IGNORE_DIRTY;
+			struct folio *folio = NULL;
 			pte_t ptent;
 
 			/*
 			 * Avoid trapping faults against the zero or KSM
 			 * pages. See similar comment in change_huge_pmd.
 			 */
-			if (prot_numa &&
-			    prot_numa_avoid_fault(vma, addr, pte,
-						  oldpte, target_node,
-							  max_nr, &nr))
+			if (prot_numa) {
+				folio = prot_numa_avoid_fault(vma, addr, pte,
+					oldpte, target_node, max_nr, &nr);
+				if (!folio)
 					continue;
+			}
 
-			oldpte = ptep_modify_prot_start(vma, addr, pte);
+			if (!folio && (max_nr != 1) && maybe_contiguous_pte_pfns(pte, oldpte)) {
+				folio = vm_normal_folio(vma, addr, oldpte);
+				if (folio_test_large(folio))
+					nr = folio_pte_batch(folio, addr, pte,
+					oldpte, max_nr, flags, NULL, NULL, NULL);
+			}
+			oldpte = modify_prot_start_ptes(vma, addr, pte, nr);
 			ptent = pte_modify(oldpte, newprot);
 
 			if (uffd_wp)
@@ -223,13 +244,13 @@ static long change_pte_range(struct mmu_gather *tlb,
 			 */
 			if ((cp_flags & MM_CP_TRY_CHANGE_WRITABLE) &&
 			    !pte_write(ptent) &&
-			    can_change_ptes_writable(vma, addr, ptent, folio, 1))
+			    can_change_ptes_writable(vma, addr, ptent, folio, nr))
 				ptent = pte_mkwrite(ptent, vma);
 
-			ptep_modify_prot_commit(vma, addr, pte, oldpte, ptent);
+			modify_prot_commit_ptes(vma, addr, pte, oldpte, ptent, nr);
 			if (pte_needs_flush(oldpte, ptent))
-				tlb_flush_pte_range(tlb, addr, PAGE_SIZE);
-			pages++;
+				tlb_flush_pte_range(tlb, addr, nr * PAGE_SIZE);
+			pages += nr;
 		} else if (is_swap_pte(oldpte)) {
 			swp_entry_t entry = pte_to_swp_entry(oldpte);
 			pte_t newpte;
-- 
2.30.2