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>

1 files changed, 12 insertions, 31 deletions

diff --git a/mm/shmem.c b/mm/shmem.c
index 51b3d6c..88c6685 100644
--- 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;