[patch 099/178] mm: apply_to_pte_range warn and fail if a large pte is encountered

[Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>]

From: Nicholas Piggin <npiggin@xxxxxxxxx>
Subject: mm: apply_to_pte_range warn and fail if a large pte is encountered

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.

Link: https://lkml.kernel.org/r/20210317062402.533919-4-npiggin@xxxxxxxxx
Signed-off-by: Nicholas Piggin <npiggin@xxxxxxxxx>
Reviewed-by: Miaohe Lin <linmiaohe@xxxxxxxxxx>
Reviewed-by: Christoph Hellwig <hch@xxxxxx>
Cc: Borislav Petkov <bp@xxxxxxxxx>
Cc: Catalin Marinas <catalin.marinas@xxxxxxx>
Cc: Ding Tianhong <dingtianhong@xxxxxxxxxx>
Cc: "H. Peter Anvin" <hpa@xxxxxxxxx>
Cc: Ingo Molnar <mingo@xxxxxxxxxx>
Cc: Michael Ellerman <mpe@xxxxxxxxxxxxxx>
Cc: Russell King <linux@xxxxxxxxxxxxxxx>
Cc: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
Cc: Uladzislau Rezki (Sony) <urezki@xxxxxxxxx>
Cc: Will Deacon <will@xxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---

 mm/memory.c |   66 +++++++++++++++++++++++++++++++++++++-------------
 1 file changed, 49 insertions(+), 17 deletions(-)

--- a/mm/memory.c~mm-apply_to_pte_range-warn-and-fail-if-a-large-pte-is-encountered
+++ a/mm/memory.c
@@ -2457,13 +2457,21 @@ static int apply_to_pmd_range(struct mm_
 	}
 	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;
 }
 
@@ -2485,13 +2493,21 @@ static int apply_to_pud_range(struct mm_
 	}
 	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;
 }
 
@@ -2513,13 +2529,21 @@ static int apply_to_p4d_range(struct mm_
 	}
 	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;
 }
 
@@ -2539,9 +2563,17 @@ static int __apply_to_page_range(struct
 	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);
_