Ok, here is the updated version. Better commentry on what we are doing
and how long the data is kept (suggested by Dave Hansen). Also added a
SECTION_NID_SHIFT to better describe its use. This showed a small
buglett as we were shifting by 4 (1<<2) instead of 2; now fixed.
-apw
=== 8< ===
sparsemem record nid during memory present
Record the node id as we mark sections for instantiation. Use this
nid during instantiation to direct allocations.
Signed-off-by: Andy Whitcroft <[email protected]>
---
include/linux/mmzone.h | 5 +++++
mm/sparse.c | 22 ++++++++++++++++++++--
2 files changed, 25 insertions(+), 2 deletions(-)
diff -upN reference/include/linux/mmzone.h current/include/linux/mmzone.h
--- reference/include/linux/mmzone.h
+++ current/include/linux/mmzone.h
@@ -508,6 +508,10 @@ struct mem_section {
* pages. However, it is stored with some other magic.
* (see sparse.c::sparse_init_one_section())
*
+ * Additionally during early boot we encode node id of
+ * the location of the section here to guide allocation.
+ * (see sparse.c::memory_present())
+ *
* Making it a UL at least makes someone do a cast
* before using it wrong.
*/
@@ -547,6 +551,7 @@ extern int __section_nr(struct mem_secti
#define SECTION_HAS_MEM_MAP (1UL<<1)
#define SECTION_MAP_LAST_BIT (1UL<<2)
#define SECTION_MAP_MASK (~(SECTION_MAP_LAST_BIT-1))
+#define SECTION_NID_SHIFT 2
static inline struct page *__section_mem_map_addr(struct mem_section *section)
{
diff -upN reference/mm/sparse.c current/mm/sparse.c
--- reference/mm/sparse.c
+++ current/mm/sparse.c
@@ -102,6 +102,22 @@ int __section_nr(struct mem_section* ms)
return (root_nr * SECTIONS_PER_ROOT) + (ms - root);
}
+/*
+ * During early boot, before section_mem_map is used for an actual
+ * mem_map, we use section_mem_map to store the section's NUMA
+ * node. This keeps us from having to use another data structure. The
+ * node information is cleared just before we store the real mem_map.
+ */
+static inline unsigned long sparse_encode_early_nid(int nid)
+{
+ return (nid << SECTION_NID_SHIFT);
+}
+
+static inline int sparse_early_nid(struct mem_section *section)
+{
+ return (section->section_mem_map >> SECTION_NID_SHIFT);
+}
+
/* Record a memory area against a node. */
void memory_present(int nid, unsigned long start, unsigned long end)
{
@@ -116,7 +132,8 @@ void memory_present(int nid, unsigned lo
ms = __nr_to_section(section);
if (!ms->section_mem_map)
- ms->section_mem_map = SECTION_MARKED_PRESENT;
+ ms->section_mem_map = sparse_encode_early_nid(nid) |
+ SECTION_MARKED_PRESENT;
}
}
@@ -167,6 +184,7 @@ static int sparse_init_one_section(struc
if (!valid_section(ms))
return -EINVAL;
+ ms->section_mem_map &= ~SECTION_MAP_MASK;
ms->section_mem_map |= sparse_encode_mem_map(mem_map, pnum);
return 1;
@@ -175,8 +193,8 @@ static int sparse_init_one_section(struc
static struct page *sparse_early_mem_map_alloc(unsigned long pnum)
{
struct page *map;
- int nid = early_pfn_to_nid(section_nr_to_pfn(pnum));
struct mem_section *ms = __nr_to_section(pnum);
+ int nid = sparse_early_nid(ms);
map = alloc_remap(nid, sizeof(struct page) * PAGES_PER_SECTION);
if (map)
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to [email protected]
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
[Index of Archives]
[Kernel Newbies]
[Netfilter]
[Bugtraq]
[Photo]
[Stuff]
[Gimp]
[Yosemite News]
[MIPS Linux]
[ARM Linux]
[Linux Security]
[Linux RAID]
[Video 4 Linux]
[Linux for the blind]
[Linux Resources]
