Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 23.128.96.18 as permitted sender) client-ip=23.128.96.18;
From:   Nicholas Piggin <npiggin@gmail.com>
To:     linux-mm@kvack.org, Andrew Morton <akpm@linux-foundation.org>
Cc:     Nicholas Piggin <npiggin@gmail.com>, linux-kernel@vger.kernel.org,
        linux-arch@vger.kernel.org, linuxppc-dev@lists.ozlabs.org,
        Zefan Li <lizefan@huawei.com>,
        Jonathan Cameron <Jonathan.Cameron@Huawei.com>,
        Christoph Hellwig <hch@infradead.org>,
        Christophe Leroy <christophe.leroy@csgroup.eu>,
        Rick Edgecombe <rick.p.edgecombe@intel.com>
Subject: [PATCH v9 02/12] mm: apply_to_pte_range warn and fail if a large pte is encountered
Date:   Sat,  5 Dec 2020 16:57:15 +1000
Message-Id: <20201205065725.1286370-3-npiggin@gmail.com>
In-Reply-To: <20201205065725.1286370-1-npiggin@gmail.com>
References: <20201205065725.1286370-1-npiggin@gmail.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Precedence: bulk

apply_to_pte_range might mistake a large pte for bad, or treat it as a
page table, resulting in a crash or corruption. Add a test to warn and
return error if large entries are found.

Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
 mm/memory.c | 66 +++++++++++++++++++++++++++++++++++++++--------------
 1 file changed, 49 insertions(+), 17 deletions(-)

diff --git a/mm/memory.c b/mm/memory.c
index c48f8df6e502..3d0f0bc5d573 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -2429,13 +2429,21 @@ static int apply_to_pmd_range(struct mm_struct *mm, pud_t *pud,
 	}
 	do {
 		next = pmd_addr_end(addr, end);
-		if (create || !pmd_none_or_clear_bad(pmd)) {
-			err = apply_to_pte_range(mm, pmd, addr, next, fn, data,
-						 create, mask);
-			if (err)
-				break;
+		if (pmd_none(*pmd) && !create)
+			continue;
+		if (WARN_ON_ONCE(pmd_leaf(*pmd)))
+			return -EINVAL;
+		if (!pmd_none(*pmd) && WARN_ON_ONCE(pmd_bad(*pmd))) {
+			if (!create)
+				continue;
+			pmd_clear_bad(pmd);
 		}
+		err = apply_to_pte_range(mm, pmd, addr, next,
+					 fn, data, create, mask);
+		if (err)
+			break;
 	} while (pmd++, addr = next, addr != end);
+
 	return err;
 }
 
@@ -2457,13 +2465,21 @@ static int apply_to_pud_range(struct mm_struct *mm, p4d_t *p4d,
 	}
 	do {
 		next = pud_addr_end(addr, end);
-		if (create || !pud_none_or_clear_bad(pud)) {
-			err = apply_to_pmd_range(mm, pud, addr, next, fn, data,
-						 create, mask);
-			if (err)
-				break;
+		if (pud_none(*pud) && !create)
+			continue;
+		if (WARN_ON_ONCE(pud_leaf(*pud)))
+			return -EINVAL;
+		if (!pud_none(*pud) && WARN_ON_ONCE(pud_bad(*pud))) {
+			if (!create)
+				continue;
+			pud_clear_bad(pud);
 		}
+		err = apply_to_pmd_range(mm, pud, addr, next,
+					 fn, data, create, mask);
+		if (err)
+			break;
 	} while (pud++, addr = next, addr != end);
+
 	return err;
 }
 
@@ -2485,13 +2501,21 @@ static int apply_to_p4d_range(struct mm_struct *mm, pgd_t *pgd,
 	}
 	do {
 		next = p4d_addr_end(addr, end);
-		if (create || !p4d_none_or_clear_bad(p4d)) {
-			err = apply_to_pud_range(mm, p4d, addr, next, fn, data,
-						 create, mask);
-			if (err)
-				break;
+		if (p4d_none(*p4d) && !create)
+			continue;
+		if (WARN_ON_ONCE(p4d_leaf(*p4d)))
+			return -EINVAL;
+		if (!p4d_none(*p4d) && WARN_ON_ONCE(p4d_bad(*p4d))) {
+			if (!create)
+				continue;
+			p4d_clear_bad(p4d);
 		}
+		err = apply_to_pud_range(mm, p4d, addr, next,
+					 fn, data, create, mask);
+		if (err)
+			break;
 	} while (p4d++, addr = next, addr != end);
+
 	return err;
 }
 
@@ -2511,9 +2535,17 @@ static int __apply_to_page_range(struct mm_struct *mm, unsigned long addr,
 	pgd = pgd_offset(mm, addr);
 	do {
 		next = pgd_addr_end(addr, end);
-		if (!create && pgd_none_or_clear_bad(pgd))
+		if (pgd_none(*pgd) && !create)
 			continue;
-		err = apply_to_p4d_range(mm, pgd, addr, next, fn, data, create, &mask);
+		if (WARN_ON_ONCE(pgd_leaf(*pgd)))
+			return -EINVAL;
+		if (!pgd_none(*pgd) && WARN_ON_ONCE(pgd_bad(*pgd))) {
+			if (!create)
+				continue;
+			pgd_clear_bad(pgd);
+		}
+		err = apply_to_p4d_range(mm, pgd, addr, next,
+					 fn, data, create, &mask);
 		if (err)
 			break;
 	} while (pgd++, addr = next, addr != end);
-- 
2.23.0