mm, proc: reduce cost of /proc/pid/smaps for unpopulated shmem mappings
Following the previous patch, further reduction of /proc/pid/smaps cost
is possible for private writable shmem mappings with unpopulated areas
where the page walk invokes the .pte_hole function. We can use radix
tree iterator for each such area instead of calling find_get_entry() in
a loop. This is possible at the extra maintenance cost of introducing
another shmem function shmem_partial_swap_usage().
To demonstrate the diference, I have measured this on a process that
creates a private writable 2GB mapping of a partially swapped out
/dev/shm/file (which cannot employ the optimizations from the prvious
patch) and doesn't populate it at all. I time how long does it take to
cat /proc/pid/smaps of this process 100 times.
Before this patch:
real 0m3.831s
user 0m0.180s
sys 0m3.212s
After this patch:
real 0m1.176s
user 0m0.180s
sys 0m0.684s
The time is similar to the case where a radix tree iterator is employed
on the whole mapping.
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>
diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index 5830b2e..8a03759 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -488,42 +488,16 @@
}
#ifdef CONFIG_SHMEM
-static unsigned long smaps_shmem_swap(struct vm_area_struct *vma,
- unsigned long addr)
-{
- struct page *page;
-
- page = find_get_entry(vma->vm_file->f_mapping,
- linear_page_index(vma, addr));
- if (!page)
- return 0;
-
- if (radix_tree_exceptional_entry(page))
- return PAGE_SIZE;
-
- page_cache_release(page);
- return 0;
-
-}
-
static int smaps_pte_hole(unsigned long addr, unsigned long end,
struct mm_walk *walk)
{
struct mem_size_stats *mss = walk->private;
- while (addr < end) {
- mss->swap += smaps_shmem_swap(walk->vma, addr);
- addr += PAGE_SIZE;
- }
+ mss->swap += shmem_partial_swap_usage(
+ walk->vma->vm_file->f_mapping, addr, end);
return 0;
}
-#else
-static unsigned long smaps_shmem_swap(struct vm_area_struct *vma,
- unsigned long addr)
-{
- return 0;
-}
#endif
static void smaps_pte_entry(pte_t *pte, unsigned long addr,
@@ -555,7 +529,17 @@
page = migration_entry_to_page(swpent);
} else if (unlikely(IS_ENABLED(CONFIG_SHMEM) && mss->check_shmem_swap
&& pte_none(*pte))) {
- mss->swap += smaps_shmem_swap(vma, addr);
+ page = find_get_entry(vma->vm_file->f_mapping,
+ linear_page_index(vma, addr));
+ if (!page)
+ return;
+
+ if (radix_tree_exceptional_entry(page))
+ mss->swap += PAGE_SIZE;
+ else
+ page_cache_release(page);
+
+ return;
}
if (!page)