filemap: batch PTE mappings

Call set_pte_range() once per contiguous range of the folio instead of
once per page.  This batches the updates to mm counters and the rmap.

With a will-it-scale.page_fault3 like app (change file write fault testing
to read fault testing.  Trying to upstream it to will-it-scale at [1]) got
15% performance gain on a 48C/96T Cascade Lake test box with 96 processes
running against xfs.

Perf data collected before/after the change:
  18.73%--page_add_file_rmap
          |
           --11.60%--__mod_lruvec_page_state
                     |
                     |--7.40%--__mod_memcg_lruvec_state
                     |          |
                     |           --5.58%--cgroup_rstat_updated
                     |
                      --2.53%--__mod_lruvec_state
                                |
                                 --1.48%--__mod_node_page_state

  9.93%--page_add_file_rmap_range
         |
          --2.67%--__mod_lruvec_page_state
                    |
                    |--1.95%--__mod_memcg_lruvec_state
                    |          |
                    |           --1.57%--cgroup_rstat_updated
                    |
                     --0.61%--__mod_lruvec_state
                               |
                                --0.54%--__mod_node_page_state

The running time of __mode_lruvec_page_state() is reduced about 9%.

[1]: https://github.com/antonblanchard/will-it-scale/pull/37

Link: https://lkml.kernel.org/r/20230802151406.3735276-38-willy@infradead.org
Signed-off-by: Yin Fengwei <fengwei.yin@intel.com>
Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

diff --git a/mm/filemap.c b/mm/filemap.c
index c06e9d3314166157bae22cc1956fb2f35a48ab36..014b73eb96a1d16aa889aaf064cc4a46e75d42a2 100644 (file)
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -3480,11 +3480,12 @@ static vm_fault_t filemap_map_folio_range(struct vm_fault *vmf,
        struct file *file = vma->vm_file;
        struct page *page = folio_page(folio, start);
        unsigned int mmap_miss = READ_ONCE(file->f_ra.mmap_miss);
-       unsigned int ref_count = 0, count = 0;
+       unsigned int count = 0;
+       pte_t *old_ptep = vmf->pte;
 
        do {
-               if (PageHWPoison(page))
-                       continue;
+               if (PageHWPoison(page + count))
+                       goto skip;
 
                if (mmap_miss > 0)
                        mmap_miss--;
@@ -3494,20 +3495,34 @@ static vm_fault_t filemap_map_folio_range(struct vm_fault *vmf,
                 * handled in the specific fault path, and it'll prohibit the
                 * fault-around logic.
                 */
-               if (!pte_none(*vmf->pte))
-                       continue;
-
-               if (vmf->address == addr)
-                       ret = VM_FAULT_NOPAGE;
+               if (!pte_none(vmf->pte[count]))
+                       goto skip;
 
-               ref_count++;
-               set_pte_range(vmf, folio, page, 1, addr);
-       } while (vmf->pte++, page++, addr += PAGE_SIZE, ++count < nr_pages);
+               count++;
+               continue;
+skip:
+               if (count) {
+                       set_pte_range(vmf, folio, page, count, addr);
+                       folio_ref_add(folio, count);
+                       if (in_range(vmf->address, addr, count))
+                               ret = VM_FAULT_NOPAGE;
+               }
 
-       /* Restore the vmf->pte */
-       vmf->pte -= nr_pages;
+               count++;
+               page += count;
+               vmf->pte += count;
+               addr += count * PAGE_SIZE;
+               count = 0;
+       } while (--nr_pages > 0);
+
+       if (count) {
+               set_pte_range(vmf, folio, page, count, addr);
+               folio_ref_add(folio, count);
+               if (in_range(vmf->address, addr, count))
+                       ret = VM_FAULT_NOPAGE;
+       }
 
-       folio_ref_add(folio, ref_count);
+       vmf->pte = old_ptep;
        WRITE_ONCE(file->f_ra.mmap_miss, mmap_miss);
 
        return ret;