mmu-notifiers: core

[mirror_ubuntu-artful-kernel.git] / mm / memory.c

diff --git a/mm/memory.c b/mm/memory.c
index a8ca04faaea62c6d28e9dc908a0615e927d73ddb..67f0ab9077d9472f99387aa66013bd2665d58887 100644 (file)
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -51,6 +51,7 @@
 #include <linux/init.h>
 #include <linux/writeback.h>
 #include <linux/memcontrol.h>
+#include <linux/mmu_notifier.h>
 
 #include <asm/pgalloc.h>
 #include <asm/uaccess.h>
@@ -652,6 +653,7 @@ int copy_page_range(struct mm_struct *dst_mm, struct mm_struct *src_mm,
        unsigned long next;
        unsigned long addr = vma->vm_start;
        unsigned long end = vma->vm_end;
+       int ret;
 
        /*
         * Don't copy ptes where a page fault will fill them correctly.
@@ -667,17 +669,33 @@ int copy_page_range(struct mm_struct *dst_mm, struct mm_struct *src_mm,
        if (is_vm_hugetlb_page(vma))
                return copy_hugetlb_page_range(dst_mm, src_mm, vma);
 
+       /*
+        * We need to invalidate the secondary MMU mappings only when
+        * there could be a permission downgrade on the ptes of the
+        * parent mm. And a permission downgrade will only happen if
+        * is_cow_mapping() returns true.
+        */
+       if (is_cow_mapping(vma->vm_flags))
+               mmu_notifier_invalidate_range_start(src_mm, addr, end);
+
+       ret = 0;
        dst_pgd = pgd_offset(dst_mm, addr);
        src_pgd = pgd_offset(src_mm, addr);
        do {
                next = pgd_addr_end(addr, end);
                if (pgd_none_or_clear_bad(src_pgd))
                        continue;
-               if (copy_pud_range(dst_mm, src_mm, dst_pgd, src_pgd,
-                                               vma, addr, next))
-                       return -ENOMEM;
+               if (unlikely(copy_pud_range(dst_mm, src_mm, dst_pgd, src_pgd,
+                                           vma, addr, next))) {
+                       ret = -ENOMEM;
+                       break;
+               }
        } while (dst_pgd++, src_pgd++, addr = next, addr != end);
-       return 0;
+
+       if (is_cow_mapping(vma->vm_flags))
+               mmu_notifier_invalidate_range_end(src_mm,
+                                                 vma->vm_start, end);
+       return ret;
 }
 
 static unsigned long zap_pte_range(struct mmu_gather *tlb,
@@ -881,7 +899,9 @@ unsigned long unmap_vmas(struct mmu_gather **tlbp,
        unsigned long start = start_addr;
        spinlock_t *i_mmap_lock = details? details->i_mmap_lock: NULL;
        int fullmm = (*tlbp)->fullmm;
+       struct mm_struct *mm = vma->vm_mm;
 
+       mmu_notifier_invalidate_range_start(mm, start_addr, end_addr);
        for ( ; vma && vma->vm_start < end_addr; vma = vma->vm_next) {
                unsigned long end;
 
@@ -946,6 +966,7 @@ unsigned long unmap_vmas(struct mmu_gather **tlbp,
                }
        }
 out:
+       mmu_notifier_invalidate_range_end(mm, start_addr, end_addr);
        return start;   /* which is now the end (or restart) address */
 }
 
@@ -1616,10 +1637,11 @@ int apply_to_page_range(struct mm_struct *mm, unsigned long addr,
 {
        pgd_t *pgd;
        unsigned long next;
-       unsigned long end = addr + size;
+       unsigned long start = addr, end = addr + size;
        int err;
 
        BUG_ON(addr >= end);
+       mmu_notifier_invalidate_range_start(mm, start, end);
        pgd = pgd_offset(mm, addr);
        do {
                next = pgd_addr_end(addr, end);
@@ -1627,6 +1649,7 @@ int apply_to_page_range(struct mm_struct *mm, unsigned long addr,
                if (err)
                        break;
        } while (pgd++, addr = next, addr != end);
+       mmu_notifier_invalidate_range_end(mm, start, end);
        return err;
 }
 EXPORT_SYMBOL_GPL(apply_to_page_range);
@@ -1839,7 +1862,7 @@ gotten:
                 * seen in the presence of one thread doing SMC and another
                 * thread doing COW.
                 */
-               ptep_clear_flush(vma, address, page_table);
+               ptep_clear_flush_notify(vma, address, page_table);
                set_pte_at(mm, address, page_table, entry);
                update_mmu_cache(vma, address, entry);
                lru_cache_add_active(new_page);