mm: move may_expand_vm() check in mmap_region()

The may_expand_vm() check requires the count of the pages within the
munmap range.  Since this is needed for accounting and obtained later, the
reodering of ma_expand_vm() to later in the call stack, after the vma
munmap struct (vms) is initialised and the gather stage is potentially
run, will allow for a single loop over the vmas.  The gather sage does not
commit any work and so everything can be undone in the case of a failure.

The MAP_FIXED page count is available after the vms_gather_munmap_vmas()
call, so use it instead of looping over the vmas twice.

Link: https://lkml.kernel.org/r/20240830040101.822209-20-Liam.Howlett@oracle.com
Signed-off-by: Liam R. Howlett <Liam.Howlett@Oracle.com>
Reviewed-by: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Cc: Bert Karwatzki <spasswolf@web.de>
Cc: Jeff Xu <jeffxu@chromium.org>
Cc: Jiri Olsa <olsajiri@gmail.com>
Cc: Kees Cook <kees@kernel.org>
Cc: Lorenzo Stoakes <lstoakes@gmail.com>
Cc: Mark Brown <broonie@kernel.org>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: "Paul E. McKenney" <paulmck@kernel.org>
Cc: Paul Moore <paul@paul-moore.com>
Cc: Sidhartha Kumar <sidhartha.kumar@oracle.com>
Cc: Suren Baghdasaryan <surenb@google.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

diff --git a/mm/mmap.c b/mm/mmap.c
index 6485f2300692fd64e099fc58e76fb2474996cc50..fc726c4e98bec8054e91fbaa7aa241dd592120ad 100644 (file)
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -1376,17 +1376,6 @@ unsigned long mmap_region(struct file *file, unsigned long addr,
        pgoff_t vm_pgoff;
        int error = -ENOMEM;
        VMA_ITERATOR(vmi, mm, addr);
-       unsigned long nr_pages, nr_accounted;
-
-       nr_pages = count_vma_pages_range(mm, addr, end, &nr_accounted);
-
-       /*
-        * Check against address space limit.
-        * MAP_FIXED may remove pages of mappings that intersects with requested
-        * mapping. Account for the pages it would unmap.
-        */
-       if (!may_expand_vm(mm, vm_flags, pglen - nr_pages))
-               return -ENOMEM;
 
        /* Find the first overlapping VMA */
        vma = vma_find(&vmi, end);
@@ -1410,6 +1399,10 @@ unsigned long mmap_region(struct file *file, unsigned long addr,
                        vma_iter_next_range(&vmi);
        }
 
+       /* Check against address space limit. */
+       if (!may_expand_vm(mm, vm_flags, pglen - vms.nr_pages))
+               goto abort_munmap;
+
        /*
         * Private writable mapping: check memory availability
         */

diff --git a/mm/vma.c b/mm/vma.c
index 713b2196d351a44f19fce1792f1e60068d5a1d56..3350fe2088bc298248c2636359a7e4879f411e7a 100644 (file)
--- a/mm/vma.c
+++ b/mm/vma.c
@@ -1640,27 +1640,6 @@ bool vma_wants_writenotify(struct vm_area_struct *vma, pgprot_t vm_page_prot)
        return vma_fs_can_writeback(vma);
 }
 
-unsigned long count_vma_pages_range(struct mm_struct *mm,
-               unsigned long addr, unsigned long end,
-               unsigned long *nr_accounted)
-{
-       VMA_ITERATOR(vmi, mm, addr);
-       struct vm_area_struct *vma;
-       unsigned long nr_pages = 0;
-
-       *nr_accounted = 0;
-       for_each_vma_range(vmi, vma, end) {
-               unsigned long vm_start = max(addr, vma->vm_start);
-               unsigned long vm_end = min(end, vma->vm_end);
-
-               nr_pages += PHYS_PFN(vm_end - vm_start);
-               if (vma->vm_flags & VM_ACCOUNT)
-                       *nr_accounted += PHYS_PFN(vm_end - vm_start);
-       }
-
-       return nr_pages;
-}
-
 static DEFINE_MUTEX(mm_all_locks_mutex);
 
 static void vm_lock_anon_vma(struct mm_struct *mm, struct anon_vma *anon_vma)

diff --git a/mm/vma.h b/mm/vma.h
index b59d470cc223f8bb9c3510bf7c11472a8f048004..45fbc56bc0b03b236cea238fbbc0226a470c2d34 100644 (file)
--- a/mm/vma.h
+++ b/mm/vma.h
@@ -319,9 +319,6 @@ bool vma_wants_writenotify(struct vm_area_struct *vma, pgprot_t vm_page_prot);
 
 int mm_take_all_locks(struct mm_struct *mm);
 void mm_drop_all_locks(struct mm_struct *mm);
-unsigned long count_vma_pages_range(struct mm_struct *mm,
-                                   unsigned long addr, unsigned long end,
-                                   unsigned long *nr_accounted);
 
 static inline bool vma_wants_manual_pte_write_upgrade(struct vm_area_struct *vma)
 {