summaryrefslogtreecommitdiffstats
path: root/mm/shmem.c
diff options
context:
space:
mode:
authorVlastimil Babka <vbabka@suse.cz>2016-01-14 15:19:20 -0800
committerLinus Torvalds <torvalds@linux-foundation.org>2016-01-14 16:00:49 -0800
commit6a15a37097c7e02390bb08d83dac433c9f10144f (patch)
tree6571e0fd8b882842d89f36897706977936c75c1d /mm/shmem.c
parentc261e7d94f0dd33a34b6cf98686e8b9699b62340 (diff)
downloadlinux-6a15a37097c7e02390bb08d83dac433c9f10144f.tar.bz2
mm, proc: reduce cost of /proc/pid/smaps for shmem mappings
The previous patch has improved swap accounting for shmem mapping, which however made /proc/pid/smaps more expensive for shmem mappings, as we consult the radix tree for each pte_none entry, so the overal complexity is O(n*log(n)). We can reduce this significantly for mappings that cannot contain COWed pages, because then we can either use the statistics tha shmem object itself tracks (if the mapping contains the whole object, or the swap usage of the whole object is zero), or use the radix tree iterator, which is much more effective than repeated find_get_entry() calls. This patch therefore introduces a function shmem_swap_usage(vma) and makes /proc/pid/smaps use it when possible. Only for writable private mappings of shmem objects (i.e. tmpfs files) with the shmem object itself (partially) swapped outwe have to resort to the find_get_entry() approach. Hopefully such mappings are relatively uncommon. To demonstrate the diference, I have measured this on a process that creates a 2GB mapping and dirties single pages with a stride of 2MB, and time how long does it take to cat /proc/pid/smaps of this process 100 times. Private writable mapping of a /dev/shm/file (the most complex case): real 0m3.831s user 0m0.180s sys 0m3.212s Shared mapping of an almost full mapping of a partially swapped /dev/shm/file (which needs to employ the radix tree iterator). real 0m1.351s user 0m0.096s sys 0m0.768s Same, but with /dev/shm/file not swapped (so no radix tree walk needed) real 0m0.935s user 0m0.128s sys 0m0.344s Private anonymous mapping: real 0m0.949s user 0m0.116s sys 0m0.348s The cost is now much closer to the private anonymous mapping case, unless the shmem mapping is private and writable. Signed-off-by: Vlastimil Babka <vbabka@suse.cz> Cc: Hugh Dickins <hughd@google.com> Cc: Jerome Marchand <jmarchan@redhat.com> Cc: Konstantin Khlebnikov <khlebnikov@yandex-team.ru> Acked-by: Michal Hocko <mhocko@suse.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Diffstat (limited to 'mm/shmem.c')
-rw-r--r--mm/shmem.c70
1 files changed, 70 insertions, 0 deletions
diff --git a/mm/shmem.c b/mm/shmem.c
index 9e60093aca3f..e978621de1ef 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -360,6 +360,76 @@ static int shmem_free_swap(struct address_space *mapping,
}
/*
+ * Determine (in bytes) how many of the shmem object's pages mapped by the
+ * given vma is swapped out.
+ *
+ * This is safe to call without i_mutex or mapping->tree_lock thanks to RCU,
+ * as long as the inode doesn't go away and racy results are not a problem.
+ */
+unsigned long shmem_swap_usage(struct vm_area_struct *vma)
+{
+ struct inode *inode = file_inode(vma->vm_file);
+ struct shmem_inode_info *info = SHMEM_I(inode);
+ struct address_space *mapping = inode->i_mapping;
+ unsigned long swapped;
+ pgoff_t start, end;
+ struct radix_tree_iter iter;
+ void **slot;
+ struct page *page;
+
+ /* Be careful as we don't hold info->lock */
+ swapped = READ_ONCE(info->swapped);
+
+ /*
+ * The easier cases are when the shmem object has nothing in swap, or
+ * the vma maps it whole. Then we can simply use the stats that we
+ * already track.
+ */
+ if (!swapped)
+ return 0;
+
+ if (!vma->vm_pgoff && vma->vm_end - vma->vm_start >= inode->i_size)
+ return swapped << PAGE_SHIFT;
+
+ swapped = 0;
+
+ /* Here comes the more involved part */
+ start = linear_page_index(vma, vma->vm_start);
+ end = linear_page_index(vma, vma->vm_end);
+
+ rcu_read_lock();
+
+restart:
+ radix_tree_for_each_slot(slot, &mapping->page_tree, &iter, start) {
+ if (iter.index >= end)
+ break;
+
+ page = radix_tree_deref_slot(slot);
+
+ /*
+ * This should only be possible to happen at index 0, so we
+ * don't need to reset the counter, nor do we risk infinite
+ * restarts.
+ */
+ if (radix_tree_deref_retry(page))
+ goto restart;
+
+ if (radix_tree_exceptional_entry(page))
+ swapped++;
+
+ if (need_resched()) {
+ cond_resched_rcu();
+ start = iter.index + 1;
+ goto restart;
+ }
+ }
+
+ rcu_read_unlock();
+
+ return swapped << PAGE_SHIFT;
+}
+
+/*
* SysV IPC SHM_UNLOCK restore Unevictable pages to their evictable lists.
*/
void shmem_unlock_mapping(struct address_space *mapping)