Skip to contentSkip to conversation

mm/hugetlb: Fix kernel crash with hugetlb mremap

PATCH Superseded Aneesh Kumar K.V 3 participants 3 messages Feb 10, 2022

Subsystems (2)

v1 of 2 Superseded Latest is v2 →

lore
Share & tools
lore
#0 lore raw

PATCH 1/1 mm/hugetlb: Fix kernel crash with hugetlb mremap

This fixes the below crash:

kernel BUG at include/linux/mm.h:2373!
cpu 0x5d: Vector: 700 (Program Check) at [c00000003c6e76e0]

    pc: c000000000581a54: pmd_to_page+0x54/0x80
    lr: c00000000058d184: move_hugetlb_page_tables+0x4e4/0x5b0
    sp: c00000003c6e7980

msr: 9000000000029033
current = 0xc00000003bd8d980
paca = 0xc000200fff610100 irqmask: 0x03 irq_happened: 0x01
pid = 9349, comm = hugepage-mremap
kernel BUG at include/linux/mm.h:2373!
[link register ] c00000000058d184 move_hugetlb_page_tables+0x4e4/0x5b0
[c00000003c6e7980] c00000000058cecc move_hugetlb_page_tables+0x22c/0x5b0 (unreliable) [c00000003c6e7a90] c00000000053b78c move_page_tables+0xdbc/0x1010 [c00000003c6e7bd0] c00000000053bc34 move_vma+0x254/0x5f0 [c00000003c6e7c90] c00000000053c790 sys_mremap+0x7c0/0x900 [c00000003c6e7db0] c00000000002c450 system_call_exception+0x160/0x2c0

the kernel can't use huge_pte_offset before it set the pte entry because a page table lookup check for huge PTE bit in the page table to differentiate between a huge pte entry and a pointer to pte page. A huge_pte_alloc won't mark the page table entry huge and hence kernel should not use huge_pte_offset after a huge_pte_alloc.

Cc Mina Almasry <[email protected]>
Cc Mike Kravetz <[email protected]>
---
 mm/hugetlb.c | 7 +++----
 1 file changed, 3 insertions(+), 4 deletions(-)
mm/hugetlb.c +3 -4
index 61895cc01d09..e57650a9404f 100644
@@ -4851,14 +4851,13 @@ int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src,
 }
 
 static void move_huge_pte(struct vm_area_struct *vma, unsigned long old_addr,
-			  unsigned long new_addr, pte_t *src_pte)
+			  unsigned long new_addr, pte_t *src_pte, pte_t *dst_pte)
 {
 	struct hstate *h = hstate_vma(vma);
 	struct mm_struct *mm = vma->vm_mm;
-	pte_t *dst_pte, pte;
 	spinlock_t *src_ptl, *dst_ptl;
+	pte_t pte;
 
-	dst_pte = huge_pte_offset(mm, new_addr, huge_page_size(h));
 	dst_ptl = huge_pte_lock(h, mm, dst_pte);
 	src_ptl = huge_pte_lockptr(h, mm, src_pte);
 
@@ -4917,7 +4916,7 @@ int move_hugetlb_page_tables(struct vm_area_struct *vma,
 		if (!dst_pte)
 			break;
 
-		move_huge_pte(vma, old_addr, new_addr, src_pte);
+		move_huge_pte(vma, old_addr, new_addr, src_pte, dst_pte);
 	}
 	flush_tlb_range(vma, old_end - len, old_end);
 	mmu_notifier_invalidate_range_end(&range);
Signature · 1 line
2.34.1
Reviewed-by on v1 1/1
#1 lore raw
Quoted 19 lines · Aneesh Kumar K.V

This fixes the below crash:

kernel BUG at include/linux/mm.h:2373!
cpu 0x5d: Vector: 700 (Program Check) at [c00000003c6e76e0]

    pc: c000000000581a54: pmd_to_page+0x54/0x80
    lr: c00000000058d184: move_hugetlb_page_tables+0x4e4/0x5b0
    sp: c00000003c6e7980

msr: 9000000000029033
current = 0xc00000003bd8d980
paca = 0xc000200fff610100 irqmask: 0x03 irq_happened: 0x01
pid = 9349, comm = hugepage-mremap
kernel BUG at include/linux/mm.h:2373!
[link register ] c00000000058d184 move_hugetlb_page_tables+0x4e4/0x5b0
[c00000003c6e7980] c00000000058cecc move_hugetlb_page_tables+0x22c/0x5b0 (unreliable) [c00000003c6e7a90] c00000000053b78c move_page_tables+0xdbc/0x1010 [c00000003c6e7bd0] c00000000053bc34 move_vma+0x254/0x5f0 [c00000003c6e7c90] c00000000053c790 sys_mremap+0x7c0/0x900 [c00000003c6e7db0] c00000000002c450 system_call_exception+0x160/0x2c0

Quoted 5 lines

the kernel can't use huge_pte_offset before it set the pte entry because a page table lookup check for huge PTE bit in the page table to differentiate between a huge pte entry and a pointer to pte page. A huge_pte_alloc won't mark the page table entry huge and hence kernel should not use huge_pte_offset after a huge_pte_alloc.

Thanks Aneesh!

Architectures that use the default version of huge_pte_offset (like X86) 'got away' with this because of the default return:

        pmd = pmd_offset(pud, addr);
        /* must be pmd huge, non-present or none */
        return (pte_t *)pmd;
Quoted 4 lines
Cc Mina Almasry <[email protected]>
Cc Mike Kravetz <[email protected]>

Should we add a Fixes: tag and cc stable?

Quoted 3 lines
---
 mm/hugetlb.c | 7 +++----
 1 file changed, 3 insertions(+), 4 deletions(-)
Signature · 1 line
Mike Kravetz
Quoted 31 lines
mm/hugetlb.c +3 -4
index 61895cc01d09..e57650a9404f 100644
@@ -4851,14 +4851,13 @@ int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src,
 }
 
 static void move_huge_pte(struct vm_area_struct *vma, unsigned long old_addr,
-			  unsigned long new_addr, pte_t *src_pte)
+			  unsigned long new_addr, pte_t *src_pte, pte_t *dst_pte)
 {
 	struct hstate *h = hstate_vma(vma);
 	struct mm_struct *mm = vma->vm_mm;
-	pte_t *dst_pte, pte;
 	spinlock_t *src_ptl, *dst_ptl;
+	pte_t pte;
 
-	dst_pte = huge_pte_offset(mm, new_addr, huge_page_size(h));
 	dst_ptl = huge_pte_lock(h, mm, dst_pte);
 	src_ptl = huge_pte_lockptr(h, mm, src_pte);
 
@@ -4917,7 +4916,7 @@ int move_hugetlb_page_tables(struct vm_area_struct *vma,
 		if (!dst_pte)
 			break;
 
-		move_huge_pte(vma, old_addr, new_addr, src_pte);
+		move_huge_pte(vma, old_addr, new_addr, src_pte, dst_pte);
 	}
 	flush_tlb_range(vma, old_end - len, old_end);
 	mmu_notifier_invalidate_range_end(&range);
Reviewed-by
#2 lore raw
Quoted 27 lines · Mike Kravetz
Quoted 19 lines · Aneesh Kumar K.V

This fixes the below crash:

kernel BUG at include/linux/mm.h:2373!
cpu 0x5d: Vector: 700 (Program Check) at [c00000003c6e76e0]

    pc: c000000000581a54: pmd_to_page+0x54/0x80
    lr: c00000000058d184: move_hugetlb_page_tables+0x4e4/0x5b0
    sp: c00000003c6e7980

msr: 9000000000029033
current = 0xc00000003bd8d980
paca = 0xc000200fff610100 irqmask: 0x03 irq_happened: 0x01
pid = 9349, comm = hugepage-mremap
kernel BUG at include/linux/mm.h:2373!
[link register ] c00000000058d184 move_hugetlb_page_tables+0x4e4/0x5b0
[c00000003c6e7980] c00000000058cecc move_hugetlb_page_tables+0x22c/0x5b0 (unreliable) [c00000003c6e7a90] c00000000053b78c move_page_tables+0xdbc/0x1010 [c00000003c6e7bd0] c00000000053bc34 move_vma+0x254/0x5f0 [c00000003c6e7c90] c00000000053c790 sys_mremap+0x7c0/0x900 [c00000003c6e7db0] c00000000002c450 system_call_exception+0x160/0x2c0

Quoted 5 lines

the kernel can't use huge_pte_offset before it set the pte entry because a page table lookup check for huge PTE bit in the page table to differentiate between a huge pte entry and a pointer to pte page. A huge_pte_alloc won't mark the page table entry huge and hence kernel should not use huge_pte_offset after a huge_pte_alloc.

Quoted 13 lines

Thanks Aneesh!

Architectures that use the default version of huge_pte_offset (like X86) 'got away' with this because of the default return:

        pmd = pmd_offset(pud, addr);
        /* must be pmd huge, non-present or none */
        return (pte_t *)pmd;
Quoted 4 lines
Cc Mina Almasry <[email protected]>
Cc Mike Kravetz <[email protected]>

Thanks Aneesh!

Quoted 3 lines

Should we add a Fixes: tag and cc stable?

Yes please if possible.

Quoted 40 lines
Quoted 3 lines
---
 mm/hugetlb.c | 7 +++----
 1 file changed, 3 insertions(+), 4 deletions(-)

--
Mike Kravetz

Quoted 31 lines
mm/hugetlb.c +3 -4
index 61895cc01d09..e57650a9404f 100644
@@ -4851,14 +4851,13 @@ int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src,
 }
 
 static void move_huge_pte(struct vm_area_struct *vma, unsigned long old_addr,
-                       unsigned long new_addr, pte_t *src_pte)
+                       unsigned long new_addr, pte_t *src_pte, pte_t *dst_pte)
 {
      struct hstate *h = hstate_vma(vma);
      struct mm_struct *mm = vma->vm_mm;
-     pte_t *dst_pte, pte;
      spinlock_t *src_ptl, *dst_ptl;
+     pte_t pte;
 
-     dst_pte = huge_pte_offset(mm, new_addr, huge_page_size(h));
      dst_ptl = huge_pte_lock(h, mm, dst_pte);
      src_ptl = huge_pte_lockptr(h, mm, src_pte);
 
@@ -4917,7 +4916,7 @@ int move_hugetlb_page_tables(struct vm_area_struct *vma,
              if (!dst_pte)
                      break;
 
-             move_huge_pte(vma, old_addr, new_addr, src_pte);
+             move_huge_pte(vma, old_addr, new_addr, src_pte, dst_pte);
      }
      flush_tlb_range(vma, old_end - len, old_end);
      mmu_notifier_invalidate_range_end(&range);