mm: wrap calls to set_pte_at_notify with invalidate_range_start and invalidate_range_end

In order to allow sleeping during invalidate_page mmu notifier calls, we
need to avoid calling when holding the PT lock.  In addition to its direct
calls, invalidate_page can also be called as a substitute for a change_pte
call, in case the notifier client hasn't implemented change_pte.

This patch drops the invalidate_page call from change_pte, and instead
wraps all calls to change_pte with invalidate_range_start and
invalidate_range_end calls.

Note that change_pte still cannot sleep after this patch, and that clients
implementing change_pte should not take action on it in case the number of
outstanding invalidate_range_start calls is larger than one, otherwise
they might miss a later invalidation.

Signed-off-by: Haggai Eran <haggaie@mellanox.com>
Cc: Andrea Arcangeli <andrea@qumranet.com>
Cc: Sagi Grimberg <sagig@mellanox.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Xiao Guangrong <xiaoguangrong@linux.vnet.ibm.com>
Cc: Or Gerlitz <ogerlitz@mellanox.com>
Cc: Haggai Eran <haggaie@mellanox.com>
Cc: Shachar Raindel <raindel@mellanox.com>
Cc: Liran Liss <liranl@mellanox.com>
Cc: Christoph Lameter <cl@linux-foundation.org>
Cc: Avi Kivity <avi@redhat.com>
Cc: Hugh Dickins <hughd@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c
index 468d91a7e0b79275009ccafd697effb390673801..88e72547a690a465090fc4deacbf64b3d867e259 100644 (file)
--- a/kernel/events/uprobes.c
+++ b/kernel/events/uprobes.c
@@ -141,10 +141,14 @@ static int __replace_page(struct vm_area_struct *vma, unsigned long addr,
        spinlock_t *ptl;
        pte_t *ptep;
        int err;
+       /* For mmu_notifiers */
+       const unsigned long mmun_start = addr;
+       const unsigned long mmun_end   = addr + PAGE_SIZE;
 
        /* For try_to_free_swap() and munlock_vma_page() below */
        lock_page(page);
 
+       mmu_notifier_invalidate_range_start(mm, mmun_start, mmun_end);
        err = -EAGAIN;
        ptep = page_check_address(page, mm, addr, &ptl, 0);
        if (!ptep)
@@ -173,6 +177,7 @@ static int __replace_page(struct vm_area_struct *vma, unsigned long addr,
 
        err = 0;
  unlock:
+       mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end);
        unlock_page(page);
        return err;
 }

diff --git a/mm/ksm.c b/mm/ksm.c
index 9638620a7530ed2b35ab381e751ab0ab90018cdb..eea2cabd2965d0fea41ff301658ee376884de9c6 100644 (file)
--- a/mm/ksm.c
+++ b/mm/ksm.c
@@ -709,15 +709,22 @@ static int write_protect_page(struct vm_area_struct *vma, struct page *page,
        spinlock_t *ptl;
        int swapped;
        int err = -EFAULT;
+       unsigned long mmun_start;       /* For mmu_notifiers */
+       unsigned long mmun_end;         /* For mmu_notifiers */
 
        addr = page_address_in_vma(page, vma);
        if (addr == -EFAULT)
                goto out;
 
        BUG_ON(PageTransCompound(page));
+
+       mmun_start = addr;
+       mmun_end   = addr + PAGE_SIZE;
+       mmu_notifier_invalidate_range_start(mm, mmun_start, mmun_end);
+
        ptep = page_check_address(page, mm, addr, &ptl, 0);
        if (!ptep)
-               goto out;
+               goto out_mn;
 
        if (pte_write(*ptep) || pte_dirty(*ptep)) {
                pte_t entry;
@@ -752,6 +759,8 @@ static int write_protect_page(struct vm_area_struct *vma, struct page *page,
 
 out_unlock:
        pte_unmap_unlock(ptep, ptl);
+out_mn:
+       mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end);
 out:
        return err;
 }
@@ -776,6 +785,8 @@ static int replace_page(struct vm_area_struct *vma, struct page *page,
        spinlock_t *ptl;
        unsigned long addr;
        int err = -EFAULT;
+       unsigned long mmun_start;       /* For mmu_notifiers */
+       unsigned long mmun_end;         /* For mmu_notifiers */
 
        addr = page_address_in_vma(page, vma);
        if (addr == -EFAULT)
@@ -794,10 +805,14 @@ static int replace_page(struct vm_area_struct *vma, struct page *page,
        if (!pmd_present(*pmd))
                goto out;
 
+       mmun_start = addr;
+       mmun_end   = addr + PAGE_SIZE;
+       mmu_notifier_invalidate_range_start(mm, mmun_start, mmun_end);
+
        ptep = pte_offset_map_lock(mm, pmd, addr, &ptl);
        if (!pte_same(*ptep, orig_pte)) {
                pte_unmap_unlock(ptep, ptl);
-               goto out;
+               goto out_mn;
        }
 
        get_page(kpage);
@@ -814,6 +829,8 @@ static int replace_page(struct vm_area_struct *vma, struct page *page,
 
        pte_unmap_unlock(ptep, ptl);
        err = 0;
+out_mn:
+       mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end);
 out:
        return err;
 }

diff --git a/mm/memory.c b/mm/memory.c
index ef003fecea9d002848a32a11c26f4188ad3fbd4f..10e9b38db1867fd1e5412e95278571ecfe602457 100644 (file)
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -2526,6 +2526,8 @@ static int do_wp_page(struct mm_struct *mm, struct vm_area_struct *vma,
        int ret = 0;
        int page_mkwrite = 0;
        struct page *dirty_page = NULL;
+       unsigned long mmun_start;       /* For mmu_notifiers */
+       unsigned long mmun_end;         /* For mmu_notifiers */
 
        old_page = vm_normal_page(vma, address, orig_pte);
        if (!old_page) {
@@ -2703,6 +2705,10 @@ gotten:
        if (mem_cgroup_newpage_charge(new_page, mm, GFP_KERNEL))
                goto oom_free_new;
 
+       mmun_start = address & PAGE_MASK;
+       mmun_end   = (address & PAGE_MASK) + PAGE_SIZE;
+       mmu_notifier_invalidate_range_start(mm, mmun_start, mmun_end);
+
        /*
         * Re-check the pte - we dropped the lock
         */
@@ -2765,14 +2771,13 @@ gotten:
        } else
                mem_cgroup_uncharge_page(new_page);
 
+       if (new_page)
+               page_cache_release(new_page);
 unlock:
        pte_unmap_unlock(page_table, ptl);
-       if (new_page) {
-               if (new_page == old_page)
-                       /* cow happened, notify before releasing old_page */
-                       mmu_notifier_invalidate_page(mm, address);
-               page_cache_release(new_page);
-       }
+       if (new_page)
+               /* Only call the end notifier if the begin was called. */
+               mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end);
        if (old_page) {
                /*
                 * Don't let another task, with possibly unlocked vma,

diff --git a/mm/mmu_notifier.c b/mm/mmu_notifier.c
index c297142f0fe6dd096e5d3eb78df66f1d5f71cb46..479a1e751a73fb4781e1b856db60b2381909c9e6 100644 (file)
--- a/mm/mmu_notifier.c
+++ b/mm/mmu_notifier.c
@@ -137,12 +137,6 @@ void __mmu_notifier_change_pte(struct mm_struct *mm, unsigned long address,
        hlist_for_each_entry_rcu(mn, n, &mm->mmu_notifier_mm->list, hlist) {
                if (mn->ops->change_pte)
                        mn->ops->change_pte(mn, mm, address, pte);
-               /*
-                * Some drivers don't have change_pte,
-                * so we must call invalidate_page in that case.
-                */
-               else if (mn->ops->invalidate_page)
-                       mn->ops->invalidate_page(mn, mm, address);
        }
        srcu_read_unlock(&srcu, id);
 }