From 1de14c3c5cbc9bb17e9dcc648cda51c0c85d54b9 Mon Sep 17 00:00:00 2001 From: Dave Hansen Date: Fri, 12 Apr 2013 16:23:54 -0700 Subject: x86-32: Fix possible incomplete TLB invalidate with PAE pagetables This patch attempts to fix: https://bugzilla.kernel.org/show_bug.cgi?id=56461 The symptom is a crash and messages like this: chrome: Corrupted page table at address 34a03000 *pdpt = 0000000000000000 *pde = 0000000000000000 Bad pagetable: 000f [#1] PREEMPT SMP Ingo guesses this got introduced by commit 611ae8e3f520 ("x86/tlb: enable tlb flush range support for x86") since that code started to free unused pagetables. On x86-32 PAE kernels, that new code has the potential to free an entire PMD page and will clear one of the four page-directory-pointer-table (aka pgd_t entries). The hardware aggressively "caches" these top-level entries and invlpg does not actually affect the CPU's copy. If we clear one we *HAVE* to do a full TLB flush, otherwise we might continue using a freed pmd page. (note, we do this properly on the population side in pud_populate()). This patch tracks whenever we clear one of these entries in the 'struct mmu_gather', and ensures that we follow up with a full tlb flush. BTW, I disassembled and checked that: if (tlb->fullmm == 0) and if (!tlb->fullmm && !tlb->need_flush_all) generate essentially the same code, so there should be zero impact there to the !PAE case. Signed-off-by: Dave Hansen Cc: Peter Anvin Cc: Ingo Molnar Cc: Artem S Tashkinov Signed-off-by: Linus Torvalds --- include/asm-generic/tlb.h | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) (limited to 'include/asm-generic') diff --git a/include/asm-generic/tlb.h b/include/asm-generic/tlb.h index 25f01d0bc14..b1b1fa6ffff 100644 --- a/include/asm-generic/tlb.h +++ b/include/asm-generic/tlb.h @@ -99,7 +99,12 @@ struct mmu_gather { unsigned int need_flush : 1, /* Did free PTEs */ fast_mode : 1; /* No batching */ - unsigned int fullmm; + /* we are in the middle of an operation to clear + * a full mm and can make some optimizations */ + unsigned int fullmm : 1, + /* we have performed an operation which + * requires a complete flush of the tlb */ + need_flush_all : 1; struct mmu_gather_batch *active; struct mmu_gather_batch local; -- cgit v1.2.3-70-g09d2 From a0a9434dd50aac5971d63207ff1e25e69c9abdb3 Mon Sep 17 00:00:00 2001 From: Hugh Dickins Date: Tue, 23 Apr 2013 11:20:35 +0100 Subject: ARM: 7701/1: mm: Allow arch code to control the user page table ceiling On architectures where a pgd entry may be shared between user and kernel (e.g. ARM+LPAE), freeing page tables needs a ceiling other than 0. This patch introduces a generic USER_PGTABLES_CEILING that arch code can override. It is the responsibility of the arch code setting the ceiling to ensure the complete freeing of the page tables (usually in pgd_free()). [catalin.marinas@arm.com: commit log; shift_arg_pages(), asm-generic/pgtables.h changes] Signed-off-by: Hugh Dickins Signed-off-by: Catalin Marinas Cc: Andrew Morton Cc: # 3.3+ Signed-off-by: Russell King --- fs/exec.c | 4 ++-- include/asm-generic/pgtable.h | 10 ++++++++++ mm/mmap.c | 4 ++-- 3 files changed, 14 insertions(+), 4 deletions(-) (limited to 'include/asm-generic') diff --git a/fs/exec.c b/fs/exec.c index a96a4885bbb..87e731f020f 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -613,7 +613,7 @@ static int shift_arg_pages(struct vm_area_struct *vma, unsigned long shift) * when the old and new regions overlap clear from new_end. */ free_pgd_range(&tlb, new_end, old_end, new_end, - vma->vm_next ? vma->vm_next->vm_start : 0); + vma->vm_next ? vma->vm_next->vm_start : USER_PGTABLES_CEILING); } else { /* * otherwise, clean from old_start; this is done to not touch @@ -622,7 +622,7 @@ static int shift_arg_pages(struct vm_area_struct *vma, unsigned long shift) * for the others its just a little faster. */ free_pgd_range(&tlb, old_start, old_end, new_end, - vma->vm_next ? vma->vm_next->vm_start : 0); + vma->vm_next ? vma->vm_next->vm_start : USER_PGTABLES_CEILING); } tlb_finish_mmu(&tlb, new_end, old_end); diff --git a/include/asm-generic/pgtable.h b/include/asm-generic/pgtable.h index bfd87685fc1..a59ff51b016 100644 --- a/include/asm-generic/pgtable.h +++ b/include/asm-generic/pgtable.h @@ -7,6 +7,16 @@ #include #include +/* + * On almost all architectures and configurations, 0 can be used as the + * upper ceiling to free_pgtables(): on many architectures it has the same + * effect as using TASK_SIZE. However, there is one configuration which + * must impose a more careful limit, to avoid freeing kernel pgtables. + */ +#ifndef USER_PGTABLES_CEILING +#define USER_PGTABLES_CEILING 0UL +#endif + #ifndef __HAVE_ARCH_PTEP_SET_ACCESS_FLAGS extern int ptep_set_access_flags(struct vm_area_struct *vma, unsigned long address, pte_t *ptep, diff --git a/mm/mmap.c b/mm/mmap.c index 2664a47cec9..067ac4d1f29 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -2303,7 +2303,7 @@ static void unmap_region(struct mm_struct *mm, update_hiwater_rss(mm); unmap_vmas(&tlb, vma, start, end); free_pgtables(&tlb, vma, prev ? prev->vm_end : FIRST_USER_ADDRESS, - next ? next->vm_start : 0); + next ? next->vm_start : USER_PGTABLES_CEILING); tlb_finish_mmu(&tlb, start, end); } @@ -2683,7 +2683,7 @@ void exit_mmap(struct mm_struct *mm) /* Use -1 here to ensure all VMAs in the mm are unmapped */ unmap_vmas(&tlb, vma, 0, -1); - free_pgtables(&tlb, vma, FIRST_USER_ADDRESS, 0); + free_pgtables(&tlb, vma, FIRST_USER_ADDRESS, USER_PGTABLES_CEILING); tlb_finish_mmu(&tlb, 0, -1); /* -- cgit v1.2.3-70-g09d2