summaryrefslogtreecommitdiff
path: root/mm/sparse.c
diff options
context:
space:
mode:
authorAndy Whitcroft <apw@shadowen.org>2005-06-23 00:07:54 -0700
committerLinus Torvalds <torvalds@ppc970.osdl.org>2005-06-23 09:45:04 -0700
commitd41dee369bff3b9dcb6328d4d822926c28cc2594 (patch)
treea0405f3b7af3ebca21838a7d427bd75a067bf850 /mm/sparse.c
parentaf705362ab6018071310c5fcd436a6b457517d5f (diff)
downloadlwn-d41dee369bff3b9dcb6328d4d822926c28cc2594.tar.gz
lwn-d41dee369bff3b9dcb6328d4d822926c28cc2594.zip
[PATCH] sparsemem memory model
Sparsemem abstracts the use of discontiguous mem_maps[]. This kind of mem_map[] is needed by discontiguous memory machines (like in the old CONFIG_DISCONTIGMEM case) as well as memory hotplug systems. Sparsemem replaces DISCONTIGMEM when enabled, and it is hoped that it can eventually become a complete replacement. A significant advantage over DISCONTIGMEM is that it's completely separated from CONFIG_NUMA. When producing this patch, it became apparent in that NUMA and DISCONTIG are often confused. Another advantage is that sparse doesn't require each NUMA node's ranges to be contiguous. It can handle overlapping ranges between nodes with no problems, where DISCONTIGMEM currently throws away that memory. Sparsemem uses an array to provide different pfn_to_page() translations for each SECTION_SIZE area of physical memory. This is what allows the mem_map[] to be chopped up. In order to do quick pfn_to_page() operations, the section number of the page is encoded in page->flags. Part of the sparsemem infrastructure enables sharing of these bits more dynamically (at compile-time) between the page_zone() and sparsemem operations. However, on 32-bit architectures, the number of bits is quite limited, and may require growing the size of the page->flags type in certain conditions. Several things might force this to occur: a decrease in the SECTION_SIZE (if you want to hotplug smaller areas of memory), an increase in the physical address space, or an increase in the number of used page->flags. One thing to note is that, once sparsemem is present, the NUMA node information no longer needs to be stored in the page->flags. It might provide speed increases on certain platforms and will be stored there if there is room. But, if out of room, an alternate (theoretically slower) mechanism is used. This patch introduces CONFIG_FLATMEM. It is used in almost all cases where there used to be an #ifndef DISCONTIG, because SPARSEMEM and DISCONTIGMEM often have to compile out the same areas of code. Signed-off-by: Andy Whitcroft <apw@shadowen.org> Signed-off-by: Dave Hansen <haveblue@us.ibm.com> Signed-off-by: Martin Bligh <mbligh@aracnet.com> Signed-off-by: Adrian Bunk <bunk@stusta.de> Signed-off-by: Yasunori Goto <y-goto@jp.fujitsu.com> Signed-off-by: Bob Picco <bob.picco@hp.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Diffstat (limited to 'mm/sparse.c')
-rw-r--r--mm/sparse.c85
1 files changed, 85 insertions, 0 deletions
diff --git a/mm/sparse.c b/mm/sparse.c
new file mode 100644
index 000000000000..f888385b9e14
--- /dev/null
+++ b/mm/sparse.c
@@ -0,0 +1,85 @@
+/*
+ * sparse memory mappings.
+ */
+#include <linux/config.h>
+#include <linux/mm.h>
+#include <linux/mmzone.h>
+#include <linux/bootmem.h>
+#include <linux/module.h>
+#include <asm/dma.h>
+
+/*
+ * Permanent SPARSEMEM data:
+ *
+ * 1) mem_section - memory sections, mem_map's for valid memory
+ */
+struct mem_section mem_section[NR_MEM_SECTIONS];
+EXPORT_SYMBOL(mem_section);
+
+/* Record a memory area against a node. */
+void memory_present(int nid, unsigned long start, unsigned long end)
+{
+ unsigned long pfn;
+
+ start &= PAGE_SECTION_MASK;
+ for (pfn = start; pfn < end; pfn += PAGES_PER_SECTION) {
+ unsigned long section = pfn_to_section_nr(pfn);
+ if (!mem_section[section].section_mem_map)
+ mem_section[section].section_mem_map = (void *) -1;
+ }
+}
+
+/*
+ * Only used by the i386 NUMA architecures, but relatively
+ * generic code.
+ */
+unsigned long __init node_memmap_size_bytes(int nid, unsigned long start_pfn,
+ unsigned long end_pfn)
+{
+ unsigned long pfn;
+ unsigned long nr_pages = 0;
+
+ for (pfn = start_pfn; pfn < end_pfn; pfn += PAGES_PER_SECTION) {
+ if (nid != early_pfn_to_nid(pfn))
+ continue;
+
+ if (pfn_valid(pfn))
+ nr_pages += PAGES_PER_SECTION;
+ }
+
+ return nr_pages * sizeof(struct page);
+}
+
+/*
+ * Allocate the accumulated non-linear sections, allocate a mem_map
+ * for each and record the physical to section mapping.
+ */
+void sparse_init(void)
+{
+ unsigned long pnum;
+ struct page *map;
+ int nid;
+
+ for (pnum = 0; pnum < NR_MEM_SECTIONS; pnum++) {
+ if (!mem_section[pnum].section_mem_map)
+ continue;
+
+ nid = early_pfn_to_nid(section_nr_to_pfn(pnum));
+ map = alloc_remap(nid, sizeof(struct page) * PAGES_PER_SECTION);
+ if (!map)
+ map = alloc_bootmem_node(NODE_DATA(nid),
+ sizeof(struct page) * PAGES_PER_SECTION);
+ if (!map) {
+ mem_section[pnum].section_mem_map = 0;
+ continue;
+ }
+
+ /*
+ * Subtle, we encode the real pfn into the mem_map such that
+ * the identity pfn - section_mem_map will return the actual
+ * physical page frame number.
+ */
+ mem_section[pnum].section_mem_map = map -
+ section_nr_to_pfn(pnum);
+ }
+}