[PATCH 08/14] x86, mm, numa: use numa_meminfo to check node_map_pfn alignment
From: Yinghai Lu
Date: Fri Mar 08 2013 - 00:02:15 EST
We could use numa_meminfo directly instead of memblock nid.
So we could move down set memblock nid down and only do it one time
for successful path
Move node_map_pfn_alignment() to arch/x86/mm as no other user for it.
Signed-off-by: Yinghai Lu <yinghai@xxxxxxxxxx>
Cc: Tejun Heo <tj@xxxxxxxxxx>
---
arch/x86/mm/numa.c | 76 +++++++++++++++++++++++++++++++++++++++++++++-------
include/linux/mm.h | 1 -
mm/page_alloc.c | 50 ----------------------------------
3 files changed, 67 insertions(+), 60 deletions(-)
diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c
index 6df5028..b8cc248 100644
--- a/arch/x86/mm/numa.c
+++ b/arch/x86/mm/numa.c
@@ -477,9 +477,69 @@ static bool __init numa_meminfo_cover_memory(const struct numa_meminfo *mi)
return true;
}
+/**
+ * node_map_pfn_alignment - determine the maximum internode alignment
+ *
+ * This function should be called after node map is populated and sorted.
+ * It calculates the maximum power of two alignment which can distinguish
+ * all the nodes.
+ *
+ * For example, if all nodes are 1GiB and aligned to 1GiB, the return value
+ * would indicate 1GiB alignment with (1 << (30 - PAGE_SHIFT)). If the
+ * nodes are shifted by 256MiB, 256MiB. Note that if only the last node is
+ * shifted, 1GiB is enough and this function will indicate so.
+ *
+ * This is used to test whether pfn -> nid mapping of the chosen memory
+ * model has fine enough granularity to avoid incorrect mapping for the
+ * populated node map.
+ *
+ * Returns the determined alignment in pfn's. 0 if there is no alignment
+ * requirement (single node).
+ */
+#ifdef NODE_NOT_IN_PAGE_FLAGS
+static unsigned long __init node_map_pfn_alignment(struct numa_meminfo *mi)
+{
+ unsigned long accl_mask = 0, last_end = 0;
+ unsigned long start, end, mask;
+ int last_nid = -1;
+ int i, nid;
+
+ for (i = 0; i < mi->nr_blks; i++) {
+ start = mi->blk[i].start >> PAGE_SHIFT;
+ end = mi->blk[i].end >> PAGE_SHIFT;
+ nid = mi->blk[i].nid;
+ if (!start || last_nid < 0 || last_nid == nid) {
+ last_nid = nid;
+ last_end = end;
+ continue;
+ }
+
+ /*
+ * Start with a mask granular enough to pin-point to the
+ * start pfn and tick off bits one-by-one until it becomes
+ * too coarse to separate the current node from the last.
+ */
+ mask = ~((1 << __ffs(start)) - 1);
+ while (mask && last_end <= (start & (mask << 1)))
+ mask <<= 1;
+
+ /* accumulate all internode masks */
+ accl_mask |= mask;
+ }
+
+ /* convert mask to number of pages */
+ return ~accl_mask + 1;
+}
+#else
+static unsigned long __init node_map_pfn_alignment(struct numa_meminfo *mi)
+{
+ return 0;
+}
+#endif
+
static int __init numa_register_memblks(struct numa_meminfo *mi)
{
- unsigned long uninitialized_var(pfn_align);
+ unsigned long pfn_align;
int i;
/* Account for nodes with cpus and no memory */
@@ -491,24 +551,22 @@ static int __init numa_register_memblks(struct numa_meminfo *mi)
if (!numa_meminfo_cover_memory(mi))
return -EINVAL;
- for (i = 0; i < mi->nr_blks; i++) {
- struct numa_memblk *mb = &mi->blk[i];
- memblock_set_node(mb->start, mb->end - mb->start, mb->nid);
- }
-
/*
* If sections array is gonna be used for pfn -> nid mapping, check
* whether its granularity is fine enough.
*/
-#ifdef NODE_NOT_IN_PAGE_FLAGS
- pfn_align = node_map_pfn_alignment();
+ pfn_align = node_map_pfn_alignment(mi);
if (pfn_align && pfn_align < PAGES_PER_SECTION) {
printk(KERN_WARNING "Node alignment %LuMB < min %LuMB, rejecting NUMA config\n",
PFN_PHYS(pfn_align) >> 20,
PFN_PHYS(PAGES_PER_SECTION) >> 20);
return -EINVAL;
}
-#endif
+
+ for (i = 0; i < mi->nr_blks; i++) {
+ struct numa_memblk *mb = &mi->blk[i];
+ memblock_set_node(mb->start, mb->end - mb->start, mb->nid);
+ }
return 0;
}
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 2ae2050..1c79b10 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1323,7 +1323,6 @@ extern void free_initmem(void);
* CONFIG_HAVE_MEMBLOCK_NODE_MAP.
*/
extern void free_area_init_nodes(unsigned long *max_zone_pfn);
-unsigned long node_map_pfn_alignment(void);
extern unsigned long absent_pages_in_range(unsigned long start_pfn,
unsigned long end_pfn);
extern void get_pfn_range_for_nid(unsigned int nid,
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 580d919..f368db4 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -4725,56 +4725,6 @@ static inline void setup_nr_node_ids(void)
}
#endif
-/**
- * node_map_pfn_alignment - determine the maximum internode alignment
- *
- * This function should be called after node map is populated and sorted.
- * It calculates the maximum power of two alignment which can distinguish
- * all the nodes.
- *
- * For example, if all nodes are 1GiB and aligned to 1GiB, the return value
- * would indicate 1GiB alignment with (1 << (30 - PAGE_SHIFT)). If the
- * nodes are shifted by 256MiB, 256MiB. Note that if only the last node is
- * shifted, 1GiB is enough and this function will indicate so.
- *
- * This is used to test whether pfn -> nid mapping of the chosen memory
- * model has fine enough granularity to avoid incorrect mapping for the
- * populated node map.
- *
- * Returns the determined alignment in pfn's. 0 if there is no alignment
- * requirement (single node).
- */
-unsigned long __init node_map_pfn_alignment(void)
-{
- unsigned long accl_mask = 0, last_end = 0;
- unsigned long start, end, mask;
- int last_nid = -1;
- int i, nid;
-
- for_each_mem_pfn_range(i, MAX_NUMNODES, &start, &end, &nid) {
- if (!start || last_nid < 0 || last_nid == nid) {
- last_nid = nid;
- last_end = end;
- continue;
- }
-
- /*
- * Start with a mask granular enough to pin-point to the
- * start pfn and tick off bits one-by-one until it becomes
- * too coarse to separate the current node from the last.
- */
- mask = ~((1 << __ffs(start)) - 1);
- while (mask && last_end <= (start & (mask << 1)))
- mask <<= 1;
-
- /* accumulate all internode masks */
- accl_mask |= mask;
- }
-
- /* convert mask to number of pages */
- return ~accl_mask + 1;
-}
-
/* Find the lowest pfn for a node */
static unsigned long __init find_min_pfn_for_node(int nid)
{
--
1.7.10.4
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/