page allocator: do not check NUMA node ID when the caller knows the node is valid
Callers of alloc_pages_node() can optionally specify -1 as a node to mean
"allocate from the current node". However, a number of the callers in
fast paths know for a fact their node is valid. To avoid a comparison and
branch, this patch adds alloc_pages_exact_node() that only checks the nid
with VM_BUG_ON(). Callers that know their node is valid are then
converted.
Signed-off-by: Mel Gorman <mel@csn.ul.ie>
Reviewed-by: Christoph Lameter <cl@linux-foundation.org>
Reviewed-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Reviewed-by: Pekka Enberg <penberg@cs.helsinki.fi>
Acked-by: Paul Mundt <lethal@linux-sh.org> [for the SLOB NUMA bits]
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Nick Piggin <nickpiggin@yahoo.com.au>
Cc: Dave Hansen <dave@linux.vnet.ibm.com>
Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
diff --git a/arch/ia64/hp/common/sba_iommu.c b/arch/ia64/hp/common/sba_iommu.c
index 56ceb68..fe63b2dc9 100644
--- a/arch/ia64/hp/common/sba_iommu.c
+++ b/arch/ia64/hp/common/sba_iommu.c
@@ -1131,7 +1131,7 @@
#ifdef CONFIG_NUMA
{
struct page *page;
- page = alloc_pages_node(ioc->node == MAX_NUMNODES ?
+ page = alloc_pages_exact_node(ioc->node == MAX_NUMNODES ?
numa_node_id() : ioc->node, flags,
get_order(size));
diff --git a/arch/ia64/kernel/mca.c b/arch/ia64/kernel/mca.c
index 8f33a88..5b17bd4 100644
--- a/arch/ia64/kernel/mca.c
+++ b/arch/ia64/kernel/mca.c
@@ -1829,8 +1829,7 @@
data = mca_bootmem();
first_time = 0;
} else
- data = page_address(alloc_pages_node(numa_node_id(),
- GFP_KERNEL, get_order(sz)));
+ data = __get_free_pages(GFP_KERNEL, get_order(sz));
if (!data)
panic("Could not allocate MCA memory for cpu %d\n",
cpu);
diff --git a/arch/ia64/kernel/uncached.c b/arch/ia64/kernel/uncached.c
index 8eff8c1..6ba72ab 100644
--- a/arch/ia64/kernel/uncached.c
+++ b/arch/ia64/kernel/uncached.c
@@ -98,7 +98,8 @@
/* attempt to allocate a granule's worth of cached memory pages */
- page = alloc_pages_node(nid, GFP_KERNEL | __GFP_ZERO | GFP_THISNODE,
+ page = alloc_pages_exact_node(nid,
+ GFP_KERNEL | __GFP_ZERO | GFP_THISNODE,
IA64_GRANULE_SHIFT-PAGE_SHIFT);
if (!page) {
mutex_unlock(&uc_pool->add_chunk_mutex);
diff --git a/arch/ia64/sn/pci/pci_dma.c b/arch/ia64/sn/pci/pci_dma.c
index d876423..98b6849 100644
--- a/arch/ia64/sn/pci/pci_dma.c
+++ b/arch/ia64/sn/pci/pci_dma.c
@@ -90,7 +90,8 @@
*/
node = pcibus_to_node(pdev->bus);
if (likely(node >=0)) {
- struct page *p = alloc_pages_node(node, flags, get_order(size));
+ struct page *p = alloc_pages_exact_node(node,
+ flags, get_order(size));
if (likely(p))
cpuaddr = page_address(p);
diff --git a/arch/powerpc/platforms/cell/ras.c b/arch/powerpc/platforms/cell/ras.c
index 296b526..5e0a191 100644
--- a/arch/powerpc/platforms/cell/ras.c
+++ b/arch/powerpc/platforms/cell/ras.c
@@ -122,8 +122,8 @@
area->nid = nid;
area->order = order;
- area->pages = alloc_pages_node(area->nid, GFP_KERNEL | GFP_THISNODE,
- area->order);
+ area->pages = alloc_pages_exact_node(area->nid, GFP_KERNEL|GFP_THISNODE,
+ area->order);
if (!area->pages) {
printk(KERN_WARNING "%s: no page on node %d\n",
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 32d6ae8..e770bf3 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -1277,7 +1277,7 @@
struct page *pages;
struct vmcs *vmcs;
- pages = alloc_pages_node(node, GFP_KERNEL, vmcs_config.order);
+ pages = alloc_pages_exact_node(node, GFP_KERNEL, vmcs_config.order);
if (!pages)
return NULL;
vmcs = page_address(pages);
diff --git a/drivers/misc/sgi-gru/grufile.c b/drivers/misc/sgi-gru/grufile.c
index bbefe77..3ce2920 100644
--- a/drivers/misc/sgi-gru/grufile.c
+++ b/drivers/misc/sgi-gru/grufile.c
@@ -302,7 +302,7 @@
pnode = uv_node_to_pnode(nid);
if (bid < 0 || gru_base[bid])
continue;
- page = alloc_pages_node(nid, GFP_KERNEL, order);
+ page = alloc_pages_exact_node(nid, GFP_KERNEL, order);
if (!page)
goto fail;
gru_base[bid] = page_address(page);
diff --git a/drivers/misc/sgi-xp/xpc_uv.c b/drivers/misc/sgi-xp/xpc_uv.c
index 9172fcd..c76677a 100644
--- a/drivers/misc/sgi-xp/xpc_uv.c
+++ b/drivers/misc/sgi-xp/xpc_uv.c
@@ -232,7 +232,7 @@
mq->mmr_blade = uv_cpu_to_blade_id(cpu);
nid = cpu_to_node(cpu);
- page = alloc_pages_node(nid, GFP_KERNEL | __GFP_ZERO | GFP_THISNODE,
+ page = alloc_pages_exact_node(nid, GFP_KERNEL | __GFP_ZERO | GFP_THISNODE,
pg_order);
if (page == NULL) {
dev_err(xpc_part, "xpc_create_gru_mq_uv() failed to alloc %d "
diff --git a/include/linux/gfp.h b/include/linux/gfp.h
index c2d3fe0..4efa330 100644
--- a/include/linux/gfp.h
+++ b/include/linux/gfp.h
@@ -5,6 +5,7 @@
#include <linux/stddef.h>
#include <linux/linkage.h>
#include <linux/topology.h>
+#include <linux/mmdebug.h>
struct vm_area_struct;
@@ -192,6 +193,14 @@
return __alloc_pages(gfp_mask, order, node_zonelist(nid, gfp_mask));
}
+static inline struct page *alloc_pages_exact_node(int nid, gfp_t gfp_mask,
+ unsigned int order)
+{
+ VM_BUG_ON(nid < 0 || nid >= MAX_NUMNODES);
+
+ return __alloc_pages(gfp_mask, order, node_zonelist(nid, gfp_mask));
+}
+
#ifdef CONFIG_NUMA
extern struct page *alloc_pages_current(gfp_t gfp_mask, unsigned order);
diff --git a/include/linux/mm.h b/include/linux/mm.h
index a880161..7b548e7 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -7,7 +7,6 @@
#include <linux/gfp.h>
#include <linux/list.h>
-#include <linux/mmdebug.h>
#include <linux/mmzone.h>
#include <linux/rbtree.h>
#include <linux/prio_tree.h>
diff --git a/kernel/profile.c b/kernel/profile.c
index 28cf26a..69911b5 100644
--- a/kernel/profile.c
+++ b/kernel/profile.c
@@ -365,7 +365,7 @@
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,
+ page = alloc_pages_exact_node(node,
GFP_KERNEL | __GFP_ZERO,
0);
if (!page)
@@ -373,7 +373,7 @@
per_cpu(cpu_profile_hits, cpu)[1] = page_address(page);
}
if (!per_cpu(cpu_profile_hits, cpu)[0]) {
- page = alloc_pages_node(node,
+ page = alloc_pages_exact_node(node,
GFP_KERNEL | __GFP_ZERO,
0);
if (!page)
@@ -564,14 +564,14 @@
int node = cpu_to_node(cpu);
struct page *page;
- page = alloc_pages_node(node,
+ page = alloc_pages_exact_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,
+ page = alloc_pages_exact_node(node,
GFP_KERNEL | __GFP_ZERO | GFP_THISNODE,
0);
if (!page)
diff --git a/mm/filemap.c b/mm/filemap.c
index 6846a90..2239671 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -521,7 +521,7 @@
{
if (cpuset_do_page_mem_spread()) {
int n = cpuset_mem_spread_node();
- return alloc_pages_node(n, gfp, 0);
+ return alloc_pages_exact_node(n, gfp, 0);
}
return alloc_pages(gfp, 0);
}
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index e83ad2c..2f8241f 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -630,7 +630,7 @@
if (h->order >= MAX_ORDER)
return NULL;
- page = alloc_pages_node(nid,
+ page = alloc_pages_exact_node(nid,
htlb_alloc_mask|__GFP_COMP|__GFP_THISNODE|
__GFP_REPEAT|__GFP_NOWARN,
huge_page_order(h));
@@ -649,7 +649,7 @@
* Use a helper variable to find the next node and then
* copy it back to hugetlb_next_nid afterwards:
* otherwise there's a window in which a racer might
- * pass invalid nid MAX_NUMNODES to alloc_pages_node.
+ * pass invalid nid MAX_NUMNODES to alloc_pages_exact_node.
* But we don't need to use a spin_lock here: it really
* doesn't matter if occasionally a racer chooses the
* same nid as we do. Move nid forward in the mask even
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index 46bdf9d..e08e2c4 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -803,7 +803,7 @@
static struct page *new_node_page(struct page *page, unsigned long node, int **x)
{
- return alloc_pages_node(node, GFP_HIGHUSER_MOVABLE, 0);
+ return alloc_pages_exact_node(node, GFP_HIGHUSER_MOVABLE, 0);
}
/*
diff --git a/mm/migrate.c b/mm/migrate.c
index 068655d8..5a24923 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -802,7 +802,7 @@
*result = &pm->status;
- return alloc_pages_node(pm->node,
+ return alloc_pages_exact_node(pm->node,
GFP_HIGHUSER_MOVABLE | GFP_THISNODE, 0);
}
diff --git a/mm/slab.c b/mm/slab.c
index 18e3164..bb3254c9 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -1707,7 +1707,7 @@
if (cachep->flags & SLAB_RECLAIM_ACCOUNT)
flags |= __GFP_RECLAIMABLE;
- page = alloc_pages_node(nodeid, flags, cachep->gfporder);
+ page = alloc_pages_exact_node(nodeid, flags, cachep->gfporder);
if (!page)
return NULL;
@@ -3261,7 +3261,7 @@
if (local_flags & __GFP_WAIT)
local_irq_enable();
kmem_flagcheck(cache, flags);
- obj = kmem_getpages(cache, local_flags, -1);
+ obj = kmem_getpages(cache, local_flags, numa_node_id());
if (local_flags & __GFP_WAIT)
local_irq_disable();
if (obj) {
diff --git a/mm/slob.c b/mm/slob.c
index 12f2614..64f6db1 100644
--- a/mm/slob.c
+++ b/mm/slob.c
@@ -46,7 +46,7 @@
* NUMA support in SLOB is fairly simplistic, pushing most of the real
* logic down to the page allocator, and simply doing the node accounting
* on the upper levels. In the event that a node id is explicitly
- * provided, alloc_pages_node() with the specified node id is used
+ * provided, alloc_pages_exact_node() with the specified node id is used
* instead. The common case (or when the node id isn't explicitly provided)
* will default to the current node, as per numa_node_id().
*
@@ -244,7 +244,7 @@
#ifdef CONFIG_NUMA
if (node != -1)
- page = alloc_pages_node(node, gfp, order);
+ page = alloc_pages_exact_node(node, gfp, order);
else
#endif
page = alloc_pages(gfp, order);