From fbf56346b855872db45af7c1274180f9d91f46cd Mon Sep 17 00:00:00 2001 From: Steven Price Date: Mon, 3 Feb 2020 17:35:54 -0800 Subject: mm: pagewalk: don't lock PTEs for walk_page_range_novma() walk_page_range_novma() can be used to walk page tables or the kernel or for firmware. These page tables may contain entries that are not backed by a struct page and so it isn't (in general) possible to take the PTE lock for the pte_entry() callback. So update walk_pte_range() to only take the lock when no_vma==false by splitting out the inner loop to a separate function and add a comment explaining the difference to walk_page_range_novma(). Link: http://lkml.kernel.org/r/20191218162402.45610-14-steven.price@arm.com Signed-off-by: Steven Price Cc: Albert Ou Cc: Alexandre Ghiti Cc: Andy Lutomirski Cc: Ard Biesheuvel Cc: Arnd Bergmann Cc: Benjamin Herrenschmidt Cc: Borislav Petkov Cc: Catalin Marinas Cc: Christian Borntraeger Cc: Dave Hansen Cc: David S. Miller Cc: Heiko Carstens Cc: "H. Peter Anvin" Cc: Ingo Molnar Cc: James Hogan Cc: James Morse Cc: Jerome Glisse Cc: "Liang, Kan" Cc: Mark Rutland Cc: Michael Ellerman Cc: Paul Burton Cc: Paul Mackerras Cc: Paul Walmsley Cc: Peter Zijlstra Cc: Ralf Baechle Cc: Russell King Cc: Thomas Gleixner Cc: Vasily Gorbik Cc: Vineet Gupta Cc: Will Deacon Cc: Zong Li Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/pagewalk.c | 35 ++++++++++++++++++++++++++++------- 1 file changed, 28 insertions(+), 7 deletions(-) (limited to 'mm/pagewalk.c') diff --git a/mm/pagewalk.c b/mm/pagewalk.c index d5773465f6da..4b5ee92ba079 100644 --- a/mm/pagewalk.c +++ b/mm/pagewalk.c @@ -4,15 +4,12 @@ #include #include -static int walk_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end, - struct mm_walk *walk) +static int walk_pte_range_inner(pte_t *pte, unsigned long addr, + unsigned long end, struct mm_walk *walk) { - pte_t *pte; - int err = 0; const struct mm_walk_ops *ops = walk->ops; - spinlock_t *ptl; + int err = 0; - pte = pte_offset_map_lock(walk->mm, pmd, addr, &ptl); for (;;) { err = ops->pte_entry(pte, addr, addr + PAGE_SIZE, walk); if (err) @@ -22,8 +19,26 @@ static int walk_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end, break; pte++; } + return err; +} + +static int walk_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end, + struct mm_walk *walk) +{ + pte_t *pte; + int err = 0; + spinlock_t *ptl; + + if (walk->no_vma) { + pte = pte_offset_map(pmd, addr); + err = walk_pte_range_inner(pte, addr, end, walk); + pte_unmap(pte); + } else { + pte = pte_offset_map_lock(walk->mm, pmd, addr, &ptl); + err = walk_pte_range_inner(pte, addr, end, walk); + pte_unmap_unlock(pte, ptl); + } - pte_unmap_unlock(pte, ptl); return err; } @@ -394,6 +409,12 @@ int walk_page_range(struct mm_struct *mm, unsigned long start, return err; } +/* + * Similar to walk_page_range() but can walk any page tables even if they are + * not backed by VMAs. Because 'unusual' entries may be walked this function + * will also not lock the PTEs for the pte_entry() callback. This is useful for + * walking the kernel pages tables or page tables for firmware. + */ int walk_page_range_novma(struct mm_struct *mm, unsigned long start, unsigned long end, const struct mm_walk_ops *ops, void *private) -- cgit v1.2.3