linux_dsm_epyc7002/mm/sparse.c
Bob Picco 3e347261a8 [PATCH] sparsemem extreme implementation
With cleanups from Dave Hansen <haveblue@us.ibm.com>

SPARSEMEM_EXTREME makes mem_section a one dimensional array of pointers to
mem_sections.  This two level layout scheme is able to achieve smaller
memory requirements for SPARSEMEM with the tradeoff of an additional shift
and load when fetching the memory section.  The current SPARSEMEM
implementation is a one dimensional array of mem_sections which is the
default SPARSEMEM configuration.  The patch attempts isolates the
implementation details of the physical layout of the sparsemem section
array.

SPARSEMEM_EXTREME requires bootmem to be functioning at the time of
memory_present() calls.  This is not always feasible, so architectures
which do not need it may allocate everything statically by using
SPARSEMEM_STATIC.

Signed-off-by: Andy Whitcroft <apw@shadowen.org>
Signed-off-by: Bob Picco <bob.picco@hp.com>
Signed-off-by: Dave Hansen <haveblue@us.ibm.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-09-05 00:05:38 -07:00

172 lines
4.1 KiB
C

/*
* 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
*/
#ifdef CONFIG_SPARSEMEM_EXTREME
struct mem_section *mem_section[NR_SECTION_ROOTS]
____cacheline_maxaligned_in_smp;
#else
struct mem_section mem_section[NR_SECTION_ROOTS][SECTIONS_PER_ROOT]
____cacheline_maxaligned_in_smp;
#endif
EXPORT_SYMBOL(mem_section);
static void sparse_alloc_root(unsigned long root, int nid)
{
#ifdef CONFIG_SPARSEMEM_EXTREME
mem_section[root] = alloc_bootmem_node(NODE_DATA(nid), PAGE_SIZE);
#endif
}
static void sparse_index_init(unsigned long section, int nid)
{
unsigned long root = SECTION_NR_TO_ROOT(section);
if (mem_section[root])
return;
sparse_alloc_root(root, nid);
if (mem_section[root])
memset(mem_section[root], 0, PAGE_SIZE);
else
panic("memory_present: NO MEMORY\n");
}
/* 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);
struct mem_section *ms;
sparse_index_init(section, nid);
ms = __nr_to_section(section);
if (!ms->section_mem_map)
ms->section_mem_map = SECTION_MARKED_PRESENT;
}
}
/*
* 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);
}
/*
* 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.
*/
static unsigned long sparse_encode_mem_map(struct page *mem_map, unsigned long pnum)
{
return (unsigned long)(mem_map - (section_nr_to_pfn(pnum)));
}
/*
* We need this if we ever free the mem_maps. While not implemented yet,
* this function is included for parity with its sibling.
*/
static __attribute((unused))
struct page *sparse_decode_mem_map(unsigned long coded_mem_map, unsigned long pnum)
{
return ((struct page *)coded_mem_map) + section_nr_to_pfn(pnum);
}
static int sparse_init_one_section(struct mem_section *ms,
unsigned long pnum, struct page *mem_map)
{
if (!valid_section(ms))
return -EINVAL;
ms->section_mem_map |= sparse_encode_mem_map(mem_map, pnum);
return 1;
}
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);
map = alloc_remap(nid, sizeof(struct page) * PAGES_PER_SECTION);
if (map)
return map;
map = alloc_bootmem_node(NODE_DATA(nid),
sizeof(struct page) * PAGES_PER_SECTION);
if (map)
return map;
printk(KERN_WARNING "%s: allocation failed\n", __FUNCTION__);
ms->section_mem_map = 0;
return NULL;
}
/*
* 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;
for (pnum = 0; pnum < NR_MEM_SECTIONS; pnum++) {
if (!valid_section_nr(pnum))
continue;
map = sparse_early_mem_map_alloc(pnum);
if (!map)
continue;
sparse_init_one_section(__nr_to_section(pnum), pnum, map);
}
}
/*
* returns the number of sections whose mem_maps were properly
* set. If this is <=0, then that means that the passed-in
* map was not consumed and must be freed.
*/
int sparse_add_one_section(unsigned long start_pfn, int nr_pages, struct page *map)
{
struct mem_section *ms = __pfn_to_section(start_pfn);
if (ms->section_mem_map & SECTION_MARKED_PRESENT)
return -EEXIST;
ms->section_mem_map |= SECTION_MARKED_PRESENT;
return sparse_init_one_section(ms, pfn_to_section_nr(start_pfn), map);
}