[PATCH v4] mm: vmalloc: WARN_ON if mapping size is not PAGE_SIZE aligned

[Yadong Qi <yadong.qi@linux.alibaba.com>]

In mm/vmalloc.c, the function vmap_pte_range() assumes that the
mapping size is aligned to PAGE_SIZE. If this assumption is
violated, the loop will become infinite because the termination
condition (`addr != end`) will never be met. This can lead to
overwriting other VA ranges and/or random pages physically follow
the page table.

It's the caller's responsibility to ensure that the mapping size
is aligned to PAGE_SIZE. However, the memory corruption is hard
to root cause. To identify the programming error in the caller
easier, check whether the mapping size is PAGE_SIZE aligned with
WARN_ON_ONCE().

Signed-off-by: Yadong Qi <yadong.qi@linux.alibaba.com>
Reviewed-by: Huang Ying <ying.huang@linux.alibaba.com>
---
v3 -> v4:
  * replace WARN_ON with WARN_ON_ONCE
v2 -> v3:
  * change error code from ENOMEM to EINVAL
  * modify callers of vmap_pte_range to handle return code
v1 -> v2:
  * Use WARN_ON instead of BUG_ON
---
 mm/vmalloc.c | 29 ++++++++++++++++++-----------
 1 file changed, 18 insertions(+), 11 deletions(-)

diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index 5edd536ba9d2..c0213118a75e 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -100,6 +100,9 @@ static int vmap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
 	struct page *page;
 	unsigned long size = PAGE_SIZE;
 
+	if (WARN_ON_ONCE(!PAGE_ALIGNED(end - addr)))
+		return -EINVAL;
+
 	pfn = phys_addr >> PAGE_SHIFT;
 	pte = pte_alloc_kernel_track(pmd, addr, mask);
 	if (!pte)
@@ -167,6 +170,7 @@ static int vmap_pmd_range(pud_t *pud, unsigned long addr, unsigned long end,
 {
 	pmd_t *pmd;
 	unsigned long next;
+	int err;
 
 	pmd = pmd_alloc_track(&init_mm, pud, addr, mask);
 	if (!pmd)
@@ -180,10 +184,11 @@ static int vmap_pmd_range(pud_t *pud, unsigned long addr, unsigned long end,
 			continue;
 		}
 
-		if (vmap_pte_range(pmd, addr, next, phys_addr, prot, max_page_shift, mask))
-			return -ENOMEM;
+		err = vmap_pte_range(pmd, addr, next, phys_addr, prot, max_page_shift, mask);
+		if (err)
+			break;
 	} while (pmd++, phys_addr += (next - addr), addr = next, addr != end);
-	return 0;
+	return err;
 }
 
 static int vmap_try_huge_pud(pud_t *pud, unsigned long addr, unsigned long end,
@@ -217,6 +222,7 @@ static int vmap_pud_range(p4d_t *p4d, unsigned long addr, unsigned long end,
 {
 	pud_t *pud;
 	unsigned long next;
+	int err;
 
 	pud = pud_alloc_track(&init_mm, p4d, addr, mask);
 	if (!pud)
@@ -230,11 +236,11 @@ static int vmap_pud_range(p4d_t *p4d, unsigned long addr, unsigned long end,
 			continue;
 		}
 
-		if (vmap_pmd_range(pud, addr, next, phys_addr, prot,
-					max_page_shift, mask))
-			return -ENOMEM;
+		err = vmap_pmd_range(pud, addr, next, phys_addr, prot, max_page_shift, mask);
+		if (err)
+			break;
 	} while (pud++, phys_addr += (next - addr), addr = next, addr != end);
-	return 0;
+	return err;
 }
 
 static int vmap_try_huge_p4d(p4d_t *p4d, unsigned long addr, unsigned long end,
@@ -268,6 +274,7 @@ static int vmap_p4d_range(pgd_t *pgd, unsigned long addr, unsigned long end,
 {
 	p4d_t *p4d;
 	unsigned long next;
+	int err;
 
 	p4d = p4d_alloc_track(&init_mm, pgd, addr, mask);
 	if (!p4d)
@@ -281,11 +288,11 @@ static int vmap_p4d_range(pgd_t *pgd, unsigned long addr, unsigned long end,
 			continue;
 		}
 
-		if (vmap_pud_range(p4d, addr, next, phys_addr, prot,
-					max_page_shift, mask))
-			return -ENOMEM;
+		err = vmap_pud_range(p4d, addr, next, phys_addr, prot, max_page_shift, mask);
+		if (err)
+			break;
 	} while (p4d++, phys_addr += (next - addr), addr = next, addr != end);
-	return 0;
+	return err;
 }
 
 static int vmap_range_noflush(unsigned long addr, unsigned long end,
-- 
2.43.5