mremap: avoid sending one IPI per page

This replaces ptep_clear_flush() with ptep_get_and_clear() and a single
flush_tlb_range() at the end of the loop, to avoid sending one IPI for
each page.

The mmu_notifier_invalidate_range_start/end section is enlarged
accordingly but this is not going to fundamentally change things.  It was
more by accident that the region under mremap was for the most part still
available for secondary MMUs: the primary MMU was never allowed to
reliably access that region for the duration of the mremap (modulo
trapping SIGSEGV on the old address range which sounds unpractical and
flakey).  If users wants secondary MMUs not to lose access to a large
region under mremap they should reduce the mremap size accordingly in
userland and run multiple calls.  Overall this will run faster so it's
actually going to reduce the time the region is under mremap for the
primary MMU which should provide a net benefit to apps.

For KVM this is a noop because the guest physical memory is never
mremapped, there's just no point it ever moving it while guest runs.  One
target of this optimization is JVM GC (so unrelated to the mmu notifier
logic).

Signed-off-by: Andrea Arcangeli <aarcange@redhat.com>
Acked-by: Johannes Weiner <jweiner@redhat.com>
Acked-by: Mel Gorman <mgorman@suse.de>
Acked-by: Rik van Riel <riel@redhat.com>
Cc: Hugh Dickins <hughd@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/mm/mremap.c b/mm/mremap.c
index 195e866..a184f37 100644 (file)
--- a/mm/mremap.c
+++ b/mm/mremap.c
@@ -80,11 +80,7 @@ static void move_ptes(struct vm_area_struct *vma, pmd_t *old_pmd,
        struct mm_struct *mm = vma->vm_mm;
        pte_t *old_pte, *new_pte, pte;
        spinlock_t *old_ptl, *new_ptl;
-       unsigned long old_start;
 
-       old_start = old_addr;
-       mmu_notifier_invalidate_range_start(vma->vm_mm,
-                                           old_start, old_end);
        if (vma->vm_file) {
                /*
                 * Subtle point from Rajesh Venkatasubramanian: before
@@ -111,7 +107,7 @@ static void move_ptes(struct vm_area_struct *vma, pmd_t *old_pmd,
                                   new_pte++, new_addr += PAGE_SIZE) {
                if (pte_none(*old_pte))
                        continue;
-               pte = ptep_clear_flush(vma, old_addr, old_pte);
+               pte = ptep_get_and_clear(mm, old_addr, old_pte);
                pte = move_pte(pte, new_vma->vm_page_prot, old_addr, new_addr);
                set_pte_at(mm, new_addr, new_pte, pte);
        }
@@ -123,7 +119,6 @@ static void move_ptes(struct vm_area_struct *vma, pmd_t *old_pmd,
        pte_unmap_unlock(old_pte - 1, old_ptl);
        if (mapping)
                mutex_unlock(&mapping->i_mmap_mutex);
-       mmu_notifier_invalidate_range_end(vma->vm_mm, old_start, old_end);
 }
 
 #define LATENCY_LIMIT  (64 * PAGE_SIZE)
@@ -134,10 +129,13 @@ unsigned long move_page_tables(struct vm_area_struct *vma,
 {
        unsigned long extent, next, old_end;
        pmd_t *old_pmd, *new_pmd;
+       bool need_flush = false;
 
        old_end = old_addr + len;
        flush_cache_range(vma, old_addr, old_end);
 
+       mmu_notifier_invalidate_range_start(vma->vm_mm, old_addr, old_end);
+
        for (; old_addr < old_end; old_addr += extent, new_addr += extent) {
                cond_resched();
                next = (old_addr + PMD_SIZE) & PMD_MASK;
@@ -158,7 +156,12 @@ unsigned long move_page_tables(struct vm_area_struct *vma,
                        extent = LATENCY_LIMIT;
                move_ptes(vma, old_pmd, old_addr, old_addr + extent,
                                new_vma, new_pmd, new_addr);
+               need_flush = true;
        }
+       if (likely(need_flush))
+               flush_tlb_range(vma, old_end-len, old_addr);
+
+       mmu_notifier_invalidate_range_end(vma->vm_mm, old_end-len, old_end);
 
        return len + old_addr - old_end;        /* how much done */
 }