The patch titled
Profiling: require buffer allocation on the correct node
has been removed from the -mm tree. Its filename is
profiling-require-buffer-allocation-on-the-correct-node.patch
This patch was dropped because it was merged into mainline or a subsystem tree
------------------------------------------------------
Subject: Profiling: require buffer allocation on the correct node
From: Christoph Lameter <clameter@xxxxxxx>
Profiling really suffers with off node buffers. Fail if no memory is
available on the nodes. The profiling code can deal with these failures
should they occur.
Signed-off-by: Christoph Lameter <clameter@xxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxx>
---
kernel/profile.c | 16 ++++++++++++----
1 file changed, 12 insertions(+), 4 deletions(-)
diff -puN kernel/profile.c~profiling-require-buffer-allocation-on-the-correct-node kernel/profile.c
--- a/kernel/profile.c~profiling-require-buffer-allocation-on-the-correct-node
+++ a/kernel/profile.c
@@ -309,13 +309,17 @@ static int __devinit profile_cpu_callbac
node = cpu_to_node(cpu);
per_cpu(cpu_profile_flip, cpu) = 0;
if (!per_cpu(cpu_profile_hits, cpu)[1]) {
- page = alloc_pages_node(node, GFP_KERNEL | __GFP_ZERO, 0);
+ page = alloc_pages_node(node,
+ GFP_KERNEL | __GFP_ZERO | GFP_THISNODE,
+ 0);
if (!page)
return NOTIFY_BAD;
per_cpu(cpu_profile_hits, cpu)[1] = page_address(page);
}
if (!per_cpu(cpu_profile_hits, cpu)[0]) {
- page = alloc_pages_node(node, GFP_KERNEL | __GFP_ZERO, 0);
+ page = alloc_pages_node(node,
+ GFP_KERNEL | __GFP_ZERO | GFP_THISNODE,
+ 0);
if (!page)
goto out_free;
per_cpu(cpu_profile_hits, cpu)[0] = page_address(page);
@@ -491,12 +495,16 @@ static int __init create_hash_tables(voi
int node = cpu_to_node(cpu);
struct page *page;
- page = alloc_pages_node(node, GFP_KERNEL | __GFP_ZERO, 0);
+ page = alloc_pages_node(node,
+ GFP_KERNEL | __GFP_ZERO | GFP_THISNODE,
+ 0);
if (!page)
goto out_cleanup;
per_cpu(cpu_profile_hits, cpu)[1]
= (struct profile_hit *)page_address(page);
- page = alloc_pages_node(node, GFP_KERNEL | __GFP_ZERO, 0);
+ page = alloc_pages_node(node,
+ GFP_KERNEL | __GFP_ZERO | GFP_THISNODE,
+ 0);
if (!page)
goto out_cleanup;
per_cpu(cpu_profile_hits, cpu)[0]
_
Patches currently in -mm which might be from clameter@xxxxxxx are
origin.patch
git-ia64.patch
slab-fix-kmalloc_node-applying-memory-policies-if-nodeid-==-numa_node_id.patch
add-numa_build-definition-in-kernelh-to-avoid-ifdef.patch
disable-gfp_thisnode-in-the-non-numa-case.patch
gfp_thisnode-for-the-slab-allocator-v2.patch
gfp_thisnode-for-the-slab-allocator-v2-fix-3.patch
add-node-to-zone-for-the-numa-case.patch
add-node-to-zone-for-the-numa-case-fix.patch
get-rid-of-zone_table.patch
get-rid-of-zone_table-fix.patch
do-not-allocate-pagesets-for-unpopulated-zones.patch
zone_statistics-use-hot-node-instead-of-cold-zone_pgdat.patch
deal-with-cases-of-zone_dma-meaning-the-first-zone.patch
introduce-config_zone_dma.patch
optional-zone_dma-in-the-vm.patch
optional-zone_dma-for-i386.patch
optional-zone_dma-for-x86_64.patch
optional-zone_dma-for-ia64.patch
remove-zone_dma-remains-from-parisc.patch
remove-zone_dma-remains-from-sh-sh64.patch
radix-tree-rcu-lockless-readside.patch
scheduler-numa-aware-placement-of-sched_group_allnodes.patch
zvc-support-nr_slab_reclaimable--nr_slab_unreclaimable-swap_prefetch.patch
reduce-max_nr_zones-swap_prefetch-remove-incorrect-use-of-zone_highmem.patch
numa-add-zone_to_nid-function-swap_prefetch.patch
readahead-state-based-method-aging-accounting-apply-type-enum-zone_type-readahead.patch
-
To unsubscribe from this list: send the line "unsubscribe mm-commits" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
