Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs

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

diff --git a/mm/mmap.c b/mm/mmap.c
index 2ffca2181a382e33d39ce225d0cf5bfa86f4578d..bfbe8856d134f367464e3582d9a432260487777c 100644 (file)
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -176,7 +176,7 @@ static struct vm_area_struct *remove_vma(struct vm_area_struct *vma)
        return next;
 }
 
-static int do_brk(unsigned long addr, unsigned long len);
+static int do_brk(unsigned long addr, unsigned long len, struct list_head *uf);
 
 SYSCALL_DEFINE1(brk, unsigned long, brk)
 {
@@ -185,6 +185,7 @@ SYSCALL_DEFINE1(brk, unsigned long, brk)
        struct mm_struct *mm = current->mm;
        unsigned long min_brk;
        bool populate;
+       LIST_HEAD(uf);
 
        if (down_write_killable(&mm->mmap_sem))
                return -EINTR;
@@ -222,7 +223,7 @@ SYSCALL_DEFINE1(brk, unsigned long, brk)
 
        /* Always allow shrinking brk. */
        if (brk <= mm->brk) {
-               if (!do_munmap(mm, newbrk, oldbrk-newbrk))
+               if (!do_munmap(mm, newbrk, oldbrk-newbrk, &uf))
                        goto set_brk;
                goto out;
        }
@@ -232,13 +233,14 @@ SYSCALL_DEFINE1(brk, unsigned long, brk)
                goto out;
 
        /* Ok, looks good - let it rip. */
-       if (do_brk(oldbrk, newbrk-oldbrk) < 0)
+       if (do_brk(oldbrk, newbrk-oldbrk, &uf) < 0)
                goto out;
 
 set_brk:
        mm->brk = brk;
        populate = newbrk > oldbrk && (mm->def_flags & VM_LOCKED) != 0;
        up_write(&mm->mmap_sem);
+       userfaultfd_unmap_complete(mm, &uf);
        if (populate)
                mm_populate(oldbrk, newbrk - oldbrk);
        return brk;
@@ -1304,7 +1306,8 @@ static inline int mlock_future_check(struct mm_struct *mm,
 unsigned long do_mmap(struct file *file, unsigned long addr,
                        unsigned long len, unsigned long prot,
                        unsigned long flags, vm_flags_t vm_flags,
-                       unsigned long pgoff, unsigned long *populate)
+                       unsigned long pgoff, unsigned long *populate,
+                       struct list_head *uf)
 {
        struct mm_struct *mm = current->mm;
        int pkey = 0;
@@ -1447,7 +1450,7 @@ unsigned long do_mmap(struct file *file, unsigned long addr,
                        vm_flags |= VM_NORESERVE;
        }
 
-       addr = mmap_region(file, addr, len, vm_flags, pgoff);
+       addr = mmap_region(file, addr, len, vm_flags, pgoff, uf);
        if (!IS_ERR_VALUE(addr) &&
            ((vm_flags & VM_LOCKED) ||
             (flags & (MAP_POPULATE | MAP_NONBLOCK)) == MAP_POPULATE))
@@ -1583,7 +1586,8 @@ static inline int accountable_mapping(struct file *file, vm_flags_t vm_flags)
 }
 
 unsigned long mmap_region(struct file *file, unsigned long addr,
-               unsigned long len, vm_flags_t vm_flags, unsigned long pgoff)
+               unsigned long len, vm_flags_t vm_flags, unsigned long pgoff,
+               struct list_head *uf)
 {
        struct mm_struct *mm = current->mm;
        struct vm_area_struct *vma, *prev;
@@ -1609,7 +1613,7 @@ unsigned long mmap_region(struct file *file, unsigned long addr,
        /* Clear old maps */
        while (find_vma_links(mm, addr, addr + len, &prev, &rb_link,
                              &rb_parent)) {
-               if (do_munmap(mm, addr, len))
+               if (do_munmap(mm, addr, len, uf))
                        return -ENOMEM;
        }
 
@@ -2495,11 +2499,11 @@ detach_vmas_to_be_unmapped(struct mm_struct *mm, struct vm_area_struct *vma,
 }
 
 /*
- * __split_vma() bypasses sysctl_max_map_count checking.  We use this on the
- * munmap path where it doesn't make sense to fail.
+ * __split_vma() bypasses sysctl_max_map_count checking.  We use this where it
+ * has already been checked or doesn't make sense to fail.
  */
-static int __split_vma(struct mm_struct *mm, struct vm_area_struct *vma,
-             unsigned long addr, int new_below)
+int __split_vma(struct mm_struct *mm, struct vm_area_struct *vma,
+               unsigned long addr, int new_below)
 {
        struct vm_area_struct *new;
        int err;
@@ -2579,7 +2583,8 @@ int split_vma(struct mm_struct *mm, struct vm_area_struct *vma,
  * work.  This now handles partial unmappings.
  * Jeremy Fitzhardinge <jeremy@goop.org>
  */
-int do_munmap(struct mm_struct *mm, unsigned long start, size_t len)
+int do_munmap(struct mm_struct *mm, unsigned long start, size_t len,
+             struct list_head *uf)
 {
        unsigned long end;
        struct vm_area_struct *vma, *prev, *last;
@@ -2603,6 +2608,13 @@ int do_munmap(struct mm_struct *mm, unsigned long start, size_t len)
        if (vma->vm_start >= end)
                return 0;
 
+       if (uf) {
+               int error = userfaultfd_unmap_prep(vma, start, end, uf);
+
+               if (error)
+                       return error;
+       }
+
        /*
         * If we need to split any vma, do it now to save pain later.
         *
@@ -2668,27 +2680,22 @@ int vm_munmap(unsigned long start, size_t len)
 {
        int ret;
        struct mm_struct *mm = current->mm;
+       LIST_HEAD(uf);
 
        if (down_write_killable(&mm->mmap_sem))
                return -EINTR;
 
-       ret = do_munmap(mm, start, len);
+       ret = do_munmap(mm, start, len, &uf);
        up_write(&mm->mmap_sem);
+       userfaultfd_unmap_complete(mm, &uf);
        return ret;
 }
 EXPORT_SYMBOL(vm_munmap);
 
 SYSCALL_DEFINE2(munmap, unsigned long, addr, size_t, len)
 {
-       int ret;
-       struct mm_struct *mm = current->mm;
-
        profile_munmap(addr);
-       if (down_write_killable(&mm->mmap_sem))
-               return -EINTR;
-       ret = do_munmap(mm, addr, len);
-       up_write(&mm->mmap_sem);
-       return ret;
+       return vm_munmap(addr, len);
 }
 
 
@@ -2780,7 +2787,7 @@ SYSCALL_DEFINE5(remap_file_pages, unsigned long, start, unsigned long, size,
 
        file = get_file(vma->vm_file);
        ret = do_mmap_pgoff(vma->vm_file, start, size,
-                       prot, flags, pgoff, &populate);
+                       prot, flags, pgoff, &populate, NULL);
        fput(file);
 out:
        up_write(&mm->mmap_sem);
@@ -2806,7 +2813,7 @@ static inline void verify_mm_writelocked(struct mm_struct *mm)
  *  anonymous maps.  eventually we may be able to do some
  *  brk-specific accounting here.
  */
-static int do_brk_flags(unsigned long addr, unsigned long request, unsigned long flags)
+static int do_brk_flags(unsigned long addr, unsigned long request, unsigned long flags, struct list_head *uf)
 {
        struct mm_struct *mm = current->mm;
        struct vm_area_struct *vma, *prev;
@@ -2845,7 +2852,7 @@ static int do_brk_flags(unsigned long addr, unsigned long request, unsigned long
         */
        while (find_vma_links(mm, addr, addr + len, &prev, &rb_link,
                              &rb_parent)) {
-               if (do_munmap(mm, addr, len))
+               if (do_munmap(mm, addr, len, uf))
                        return -ENOMEM;
        }
 
@@ -2892,9 +2899,9 @@ out:
        return 0;
 }
 
-static int do_brk(unsigned long addr, unsigned long len)
+static int do_brk(unsigned long addr, unsigned long len, struct list_head *uf)
 {
-       return do_brk_flags(addr, len, 0);
+       return do_brk_flags(addr, len, 0, uf);
 }
 
 int vm_brk_flags(unsigned long addr, unsigned long len, unsigned long flags)
@@ -2902,13 +2909,15 @@ int vm_brk_flags(unsigned long addr, unsigned long len, unsigned long flags)
        struct mm_struct *mm = current->mm;
        int ret;
        bool populate;
+       LIST_HEAD(uf);
 
        if (down_write_killable(&mm->mmap_sem))
                return -EINTR;
 
-       ret = do_brk_flags(addr, len, flags);
+       ret = do_brk_flags(addr, len, flags, &uf);
        populate = ((mm->def_flags & VM_LOCKED) != 0);
        up_write(&mm->mmap_sem);
+       userfaultfd_unmap_complete(mm, &uf);
        if (populate && !ret)
                mm_populate(addr, len);
        return ret;
@@ -3125,8 +3134,7 @@ void vm_stat_account(struct mm_struct *mm, vm_flags_t flags, long npages)
                mm->data_vm += npages;
 }
 
-static int special_mapping_fault(struct vm_area_struct *vma,
-                                struct vm_fault *vmf);
+static int special_mapping_fault(struct vm_fault *vmf);
 
 /*
  * Having a close hook prevents vma merging regardless of flags.
@@ -3161,9 +3169,9 @@ static const struct vm_operations_struct legacy_special_mapping_vmops = {
        .fault = special_mapping_fault,
 };
 
-static int special_mapping_fault(struct vm_area_struct *vma,
-                               struct vm_fault *vmf)
+static int special_mapping_fault(struct vm_fault *vmf)
 {
+       struct vm_area_struct *vma = vmf->vma;
        pgoff_t pgoff;
        struct page **pages;
 
@@ -3173,7 +3181,7 @@ static int special_mapping_fault(struct vm_area_struct *vma,
                struct vm_special_mapping *sm = vma->vm_private_data;
 
                if (sm->fault)
-                       return sm->fault(sm, vma, vmf);
+                       return sm->fault(sm, vmf->vma, vmf);
 
                pages = sm->pages;
        }
@@ -3447,7 +3455,7 @@ void mm_drop_all_locks(struct mm_struct *mm)
 }
 
 /*
- * initialise the VMA slab
+ * initialise the percpu counter for VM
  */
 void __init mmap_init(void)
 {