mm/mmu_notifier: kill invalidate_page

The invalidate_page callback suffered from two pitfalls.  First it used
to happen after the page table lock was release and thus a new page
might have setup before the call to invalidate_page() happened.

This is in a weird way fixed by commit c7ab0d2fdc84 ("mm: convert
try_to_unmap_one() to use page_vma_mapped_walk()") that moved the
callback under the page table lock but this also broke several existing
users of the mmu_notifier API that assumed they could sleep inside this
callback.

The second pitfall was invalidate_page() being the only callback not
taking a range of address in respect to invalidation but was giving an
address and a page.  Lots of the callback implementers assumed this
could never be THP and thus failed to invalidate the appropriate range
for THP.

By killing this callback we unify the mmu_notifier callback API to
always take a virtual address range as input.

Finally this also simplifies the end user life as there is now two clear
choices:
  - invalidate_range_start()/end() callback (which allow you to sleep)
  - invalidate_range() where you can not sleep but happen right after
    page table update under page table lock

Signed-off-by: Jérôme Glisse <jglisse@redhat.com>
Cc: Bernhard Held <berny156@gmx.de>
Cc: Adam Borowski <kilobyte@angband.pl>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Radim Krčmář <rkrcmar@redhat.com>
Cc: Wanpeng Li <kernellwp@gmail.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Takashi Iwai <tiwai@suse.de>
Cc: Nadav Amit <nadav.amit@gmail.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: axie <axie@amd.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/include/linux/mmu_notifier.h b/include/linux/mmu_notifier.h
index c91b3bcd158f8fa8b2dbc3d4738ade5fdcc600cb..7b2e31b1745aaf3a7d3e8af0ca915c6c2dc04516 100644 (file)
--- a/include/linux/mmu_notifier.h
+++ b/include/linux/mmu_notifier.h
@@ -94,17 +94,6 @@ struct mmu_notifier_ops {
                           unsigned long address,
                           pte_t pte);
 
-       /*
-        * Before this is invoked any secondary MMU is still ok to
-        * read/write to the page previously pointed to by the Linux
-        * pte because the page hasn't been freed yet and it won't be
-        * freed until this returns. If required set_page_dirty has to
-        * be called internally to this method.
-        */
-       void (*invalidate_page)(struct mmu_notifier *mn,
-                               struct mm_struct *mm,
-                               unsigned long address);
-
        /*
         * invalidate_range_start() and invalidate_range_end() must be
         * paired and are called only when the mmap_sem and/or the
@@ -220,8 +209,6 @@ extern int __mmu_notifier_test_young(struct mm_struct *mm,
                                     unsigned long address);
 extern void __mmu_notifier_change_pte(struct mm_struct *mm,
                                      unsigned long address, pte_t pte);
-extern void __mmu_notifier_invalidate_page(struct mm_struct *mm,
-                                         unsigned long address);
 extern void __mmu_notifier_invalidate_range_start(struct mm_struct *mm,
                                  unsigned long start, unsigned long end);
 extern void __mmu_notifier_invalidate_range_end(struct mm_struct *mm,
@@ -268,13 +255,6 @@ static inline void mmu_notifier_change_pte(struct mm_struct *mm,
                __mmu_notifier_change_pte(mm, address, pte);
 }
 
-static inline void mmu_notifier_invalidate_page(struct mm_struct *mm,
-                                         unsigned long address)
-{
-       if (mm_has_notifiers(mm))
-               __mmu_notifier_invalidate_page(mm, address);
-}
-
 static inline void mmu_notifier_invalidate_range_start(struct mm_struct *mm,
                                  unsigned long start, unsigned long end)
 {
@@ -442,11 +422,6 @@ static inline void mmu_notifier_change_pte(struct mm_struct *mm,
 {
 }
 
-static inline void mmu_notifier_invalidate_page(struct mm_struct *mm,
-                                         unsigned long address)
-{
-}
-
 static inline void mmu_notifier_invalidate_range_start(struct mm_struct *mm,
                                  unsigned long start, unsigned long end)
 {

diff --git a/mm/mmu_notifier.c b/mm/mmu_notifier.c
index 54ca545629286223a16ef931830a3757b29da77d..314285284e6e6a4c764d0f8126dd0fecf8f7f84e 100644 (file)
--- a/mm/mmu_notifier.c
+++ b/mm/mmu_notifier.c
@@ -174,20 +174,6 @@ void __mmu_notifier_change_pte(struct mm_struct *mm, unsigned long address,
        srcu_read_unlock(&srcu, id);
 }
 
-void __mmu_notifier_invalidate_page(struct mm_struct *mm,
-                                         unsigned long address)
-{
-       struct mmu_notifier *mn;
-       int id;
-
-       id = srcu_read_lock(&srcu);
-       hlist_for_each_entry_rcu(mn, &mm->mmu_notifier_mm->list, hlist) {
-               if (mn->ops->invalidate_page)
-                       mn->ops->invalidate_page(mn, mm, address);
-       }
-       srcu_read_unlock(&srcu, id);
-}
-
 void __mmu_notifier_invalidate_range_start(struct mm_struct *mm,
                                  unsigned long start, unsigned long end)
 {