swapin_readahead: excise NUMA bogosity

For three years swapin_readahead has been cluttered with fanciful CONFIG_NUMA
code, advancing addr, and stepping on to the next vma at the boundary, to line
up the mempolicy for each page allocation.

It _might_ be a good idea to allocate swap more according to vma layout; but
the fact is, that's not how we do it at all, 2.6 even less than 2.4: swap is
allocated as needed for pages as they sink to the bottom of the inactive LRUs.
 Sometimes that may match vma layout, but not so often that it's worth going
to these misleading vma->vm_next lengths: rip all that out.

Originally I intended to retain the incrementation of addr, but correct its
initial value: valid_swaphandles generally supplies an offset below the target
addr (this is readaround rather than readahead), but addr has not been
adjusted accordingly, so in the interleave case it has usually been allocating
the target page from the "wrong" node (though that may not matter very much).

But look at the equivalent shmem_swapin code: either by oversight or by
design, though it has all the apparatus for choosing a new mempolicy per page,
it uses the same idx throughout, choosing the same mempolicy and interleave
node for each page of the cluster.

Which is actually a much better strategy: each node has its own LRUs and its
own kswapd, so if you're betting on any particular relationship between swap
and node, the best bet is that nearby swap entries belong to pages from the
same node - even when the mempolicy of the target page is to interleave.  And
examining a map of nodes corresponding to swap entries on a numa=fake system
bears this out.  (We could later tweak swap allocation to make it even more
likely, but this patch is merely about removing cruft.)

So, neither adjust nor increment addr in swapin_readahead, and then
shmem_swapin can use it too; the pseudo-vma to pass policy need only be set up
once per cluster, and so few fields of pvma are used, let's skip the memset -
from shmem_alloc_page also.

Signed-off-by: Hugh Dickins <hugh@veritas.com>
Acked-by: Rik van Riel <riel@redhat.com>
Cc: Andi Kleen <ak@suse.de>
Cc: Christoph Lameter <clameter@sgi.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/mm/memory.c b/mm/memory.c
index 1b8ca160f1d04fadee04fedd82955b1c40585927..1d803c2d01848dedb1e9eb57d640eaa81bd8a4cc 100644 (file)
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -1998,45 +1998,26 @@ int vmtruncate_range(struct inode *inode, loff_t offset, loff_t end)
  */
 void swapin_readahead(swp_entry_t entry, unsigned long addr,struct vm_area_struct *vma)
 {
-#ifdef CONFIG_NUMA
-       struct vm_area_struct *next_vma = vma ? vma->vm_next : NULL;
-#endif
-       int i, num;
-       struct page *new_page;
+       int nr_pages;
+       struct page *page;
        unsigned long offset;
+       unsigned long end_offset;
 
        /*
-        * Get the number of handles we should do readahead io to.
+        * Get starting offset for readaround, and number of pages to read.
+        * Adjust starting address by readbehind (for NUMA interleave case)?
+        * No, it's very unlikely that swap layout would follow vma layout,
+        * more likely that neighbouring swap pages came from the same node:
+        * so use the same "addr" to choose the same node for each swap read.
         */
-       num = valid_swaphandles(entry, &offset);
-       for (i = 0; i < num; offset++, i++) {
+       nr_pages = valid_swaphandles(entry, &offset);
+       for (end_offset = offset + nr_pages; offset < end_offset; offset++) {
                /* Ok, do the async read-ahead now */
-               new_page = read_swap_cache_async(swp_entry(swp_type(entry),
-                                                          offset), vma, addr);
-               if (!new_page)
+               page = read_swap_cache_async(swp_entry(swp_type(entry), offset),
+                                               vma, addr);
+               if (!page)
                        break;
-               page_cache_release(new_page);
-#ifdef CONFIG_NUMA
-               /*
-                * Find the next applicable VMA for the NUMA policy.
-                */
-               addr += PAGE_SIZE;
-               if (addr == 0)
-                       vma = NULL;
-               if (vma) {
-                       if (addr >= vma->vm_end) {
-                               vma = next_vma;
-                               next_vma = vma ? vma->vm_next : NULL;
-                       }
-                       if (vma && addr < vma->vm_start)
-                               vma = NULL;
-               } else {
-                       if (next_vma && addr >= next_vma->vm_start) {
-                               vma = next_vma;
-                               next_vma = vma->vm_next;
-                       }
-               }
-#endif
+               page_cache_release(page);
        }
        lru_add_drain();        /* Push any new pages onto the LRU now */
 }

diff --git a/mm/shmem.c b/mm/shmem.c
index 51b3d6ccddab75ba33b7fded5ffaf75700770ccd..88c6685f16b715b00378fc26cf7d7b9a43dd79bd 100644 (file)
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -1025,53 +1025,34 @@ out:
        return err;
 }
 
-static struct page *shmem_swapin_async(struct shared_policy *p,
+static struct page *shmem_swapin(struct shmem_inode_info *info,
                                       swp_entry_t entry, unsigned long idx)
 {
-       struct page *page;
        struct vm_area_struct pvma;
+       struct page *page;
 
        /* Create a pseudo vma that just contains the policy */
-       memset(&pvma, 0, sizeof(struct vm_area_struct));
-       pvma.vm_end = PAGE_SIZE;
+       pvma.vm_start = 0;
        pvma.vm_pgoff = idx;
-       pvma.vm_policy = mpol_shared_policy_lookup(p, idx);
+       pvma.vm_ops = NULL;
+       pvma.vm_policy = mpol_shared_policy_lookup(&info->policy, idx);
+       swapin_readahead(entry, 0, &pvma);
        page = read_swap_cache_async(entry, &pvma, 0);
        mpol_free(pvma.vm_policy);
        return page;
 }
 
-static struct page *shmem_swapin(struct shmem_inode_info *info,
-                                swp_entry_t entry, unsigned long idx)
-{
-       struct shared_policy *p = &info->policy;
-       int i, num;
-       struct page *page;
-       unsigned long offset;
-
-       num = valid_swaphandles(entry, &offset);
-       for (i = 0; i < num; offset++, i++) {
-               page = shmem_swapin_async(p,
-                               swp_entry(swp_type(entry), offset), idx);
-               if (!page)
-                       break;
-               page_cache_release(page);
-       }
-       lru_add_drain();        /* Push any new pages onto the LRU now */
-       return shmem_swapin_async(p, entry, idx);
-}
-
-static struct page *
-shmem_alloc_page(gfp_t gfp, struct shmem_inode_info *info,
-                unsigned long idx)
+static struct page *shmem_alloc_page(gfp_t gfp, struct shmem_inode_info *info,
+                                       unsigned long idx)
 {
        struct vm_area_struct pvma;
        struct page *page;
 
-       memset(&pvma, 0, sizeof(struct vm_area_struct));
-       pvma.vm_policy = mpol_shared_policy_lookup(&info->policy, idx);
+       /* Create a pseudo vma that just contains the policy */
+       pvma.vm_start = 0;
        pvma.vm_pgoff = idx;
-       pvma.vm_end = PAGE_SIZE;
+       pvma.vm_ops = NULL;
+       pvma.vm_policy = mpol_shared_policy_lookup(&info->policy, idx);
        page = alloc_page_vma(gfp, &pvma, 0);
        mpol_free(pvma.vm_policy);
        return page;