linux-kernel - [PATCH] riscv: Fix hugetlb retrieval of number of ptes in case of !present 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 for Android: free password hash cracker in your pocket

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

Message-Id: <20250317072551.572169-1-alexghiti@rivosinc.com>
Date: Mon, 17 Mar 2025 08:25:51 +0100
From: Alexandre Ghiti <alexghiti@...osinc.com>
To: Paul Walmsley <paul.walmsley@...ive.com>,
	Palmer Dabbelt <palmer@...belt.com>,
	Alexandre Ghiti <alex@...ti.fr>,
	Qinglin Pan <panqinglin2020@...as.ac.cn>,
	Andrew Jones <ajones@...tanamicro.com>,
	Ryan Roberts <ryan.roberts@....com>,
	linux-riscv@...ts.infradead.org,
	linux-kernel@...r.kernel.org
Cc: Alexandre Ghiti <alexghiti@...osinc.com>
Subject: [PATCH] riscv: Fix hugetlb retrieval of number of ptes in case of !present pte

Ryan sent a fix [1] for arm64 that applies to riscv too: in some hugetlb
functions, we must not use the pte value to get the size of a mapping
because the pte may not be present.

So use the already present size parameter for huge_pte_clear() and the
newly introduced size parameter for huge_ptep_get_and_clear(). And make
sure to gather A/D bits only on present ptes.

Fixes: 82a1a1f3bfb6 ("riscv: mm: support Svnapot in hugetlb page")
Link: https://lore.kernel.org/all/20250217140419.1702389-1-ryan.roberts@arm.com/ [1]
Signed-off-by: Alexandre Ghiti <alexghiti@...osinc.com>
---
 arch/riscv/mm/hugetlbpage.c | 76 ++++++++++++++++++++++---------------
 1 file changed, 45 insertions(+), 31 deletions(-)

diff --git a/arch/riscv/mm/hugetlbpage.c b/arch/riscv/mm/hugetlbpage.c
index b4a78a4b35cf..375dd96bb4a0 100644
--- a/arch/riscv/mm/hugetlbpage.c
+++ b/arch/riscv/mm/hugetlbpage.c
@@ -148,22 +148,25 @@ unsigned long hugetlb_mask_last_page(struct hstate *h)
 static pte_t get_clear_contig(struct mm_struct *mm,
 			      unsigned long addr,
 			      pte_t *ptep,
-			      unsigned long pte_num)
+			      unsigned long ncontig)
 {
-	pte_t orig_pte = ptep_get(ptep);
-	unsigned long i;
-
-	for (i = 0; i < pte_num; i++, addr += PAGE_SIZE, ptep++) {
-		pte_t pte = ptep_get_and_clear(mm, addr, ptep);
-
-		if (pte_dirty(pte))
-			orig_pte = pte_mkdirty(orig_pte);
-
-		if (pte_young(pte))
-			orig_pte = pte_mkyoung(orig_pte);
+	pte_t pte, tmp_pte;
+	bool present;
+
+	pte = ptep_get_and_clear(mm, addr, ptep);
+	present = pte_present(pte);
+	while (--ncontig) {
+		ptep++;
+		addr += PAGE_SIZE;
+		tmp_pte = ptep_get_and_clear(mm, addr, ptep);
+		if (present) {
+			if (pte_dirty(tmp_pte))
+				pte = pte_mkdirty(pte);
+			if (pte_young(tmp_pte))
+				pte = pte_mkyoung(pte);
+		}
 	}
-
-	return orig_pte;
+	return pte;
 }
 
 static pte_t get_clear_contig_flush(struct mm_struct *mm,
@@ -212,6 +215,26 @@ static void clear_flush(struct mm_struct *mm,
 	flush_tlb_range(&vma, saddr, addr);
 }
 
+static int num_contig_ptes_from_size(unsigned long sz, size_t *pgsize)
+{
+	unsigned long hugepage_shift;
+
+	if (sz >= PGDIR_SIZE)
+		hugepage_shift = PGDIR_SHIFT;
+	else if (sz >= P4D_SIZE)
+		hugepage_shift = P4D_SHIFT;
+	else if (sz >= PUD_SIZE)
+		hugepage_shift = PUD_SHIFT;
+	else if (sz >= PMD_SIZE)
+		hugepage_shift = PMD_SHIFT;
+	else
+		hugepage_shift = PAGE_SHIFT;
+
+	*pgsize = 1 << hugepage_shift;
+
+	return sz >> hugepage_shift;
+}
+
 /*
  * When dealing with NAPOT mappings, the privileged specification indicates that
  * "if an update needs to be made, the OS generally should first mark all of the
@@ -226,22 +249,10 @@ void set_huge_pte_at(struct mm_struct *mm,
 		     pte_t pte,
 		     unsigned long sz)
 {
-	unsigned long hugepage_shift, pgsize;
+	size_t pgsize;
 	int i, pte_num;
 
-	if (sz >= PGDIR_SIZE)
-		hugepage_shift = PGDIR_SHIFT;
-	else if (sz >= P4D_SIZE)
-		hugepage_shift = P4D_SHIFT;
-	else if (sz >= PUD_SIZE)
-		hugepage_shift = PUD_SHIFT;
-	else if (sz >= PMD_SIZE)
-		hugepage_shift = PMD_SHIFT;
-	else
-		hugepage_shift = PAGE_SHIFT;
-
-	pte_num = sz >> hugepage_shift;
-	pgsize = 1 << hugepage_shift;
+	pte_num = num_contig_ptes_from_size(sz, &pgsize);
 
 	if (!pte_present(pte)) {
 		for (i = 0; i < pte_num; i++, ptep++, addr += pgsize)
@@ -295,13 +306,14 @@ pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
 			      unsigned long addr,
 			      pte_t *ptep, unsigned long sz)
 {
+	size_t pgsize;
 	pte_t orig_pte = ptep_get(ptep);
 	int pte_num;
 
 	if (!pte_napot(orig_pte))
 		return ptep_get_and_clear(mm, addr, ptep);
 
-	pte_num = napot_pte_num(napot_cont_order(orig_pte));
+	pte_num = num_contig_ptes_from_size(sz, &pgsize);
 
 	return get_clear_contig(mm, addr, ptep, pte_num);
 }
@@ -351,6 +363,7 @@ void huge_pte_clear(struct mm_struct *mm,
 		    pte_t *ptep,
 		    unsigned long sz)
 {
+	size_t pgsize;
 	pte_t pte = ptep_get(ptep);
 	int i, pte_num;
 
@@ -359,8 +372,9 @@ void huge_pte_clear(struct mm_struct *mm,
 		return;
 	}
 
-	pte_num = napot_pte_num(napot_cont_order(pte));
-	for (i = 0; i < pte_num; i++, addr += PAGE_SIZE, ptep++)
+	pte_num = num_contig_ptes_from_size(sz, &pgsize);
+
+	for (i = 0; i < pte_num; i++, addr += pgsize, ptep++)
 		pte_clear(mm, addr, ptep);
 }
 
-- 
2.39.2