* sparse memory mappings.
*/
#include <linux/mm.h>
+#include <linux/slab.h>
#include <linux/mmzone.h>
#include <linux/bootmem.h>
#include <linux/highmem.h>
unsigned long array_size = SECTIONS_PER_ROOT *
sizeof(struct mem_section);
- if (slab_is_available())
- section = kmalloc_node(array_size, GFP_KERNEL, nid);
- else
+ if (slab_is_available()) {
+ if (node_state(nid, N_HIGH_MEMORY))
+ section = kmalloc_node(array_size, GFP_KERNEL, nid);
+ else
+ section = kmalloc(array_size, GFP_KERNEL);
+ } else
section = alloc_bootmem_node(NODE_DATA(nid), array_size);
if (section)
return (section->section_mem_map >> SECTION_NID_SHIFT);
}
-/* Record a memory area against a node. */
-void __init memory_present(int nid, unsigned long start, unsigned long end)
+/* Validate the physical addressing limitations of the model */
+void __meminit mminit_validate_memmodel_limits(unsigned long *start_pfn,
+ unsigned long *end_pfn)
{
- unsigned long max_arch_pfn = 1UL << (MAX_PHYSMEM_BITS-PAGE_SHIFT);
- unsigned long pfn;
+ unsigned long max_sparsemem_pfn = 1UL << (MAX_PHYSMEM_BITS-PAGE_SHIFT);
/*
* Sanity checks - do not allow an architecture to pass
* in larger pfns than the maximum scope of sparsemem:
*/
- if (start >= max_arch_pfn)
- return;
- if (end >= max_arch_pfn)
- end = max_arch_pfn;
+ if (*start_pfn > max_sparsemem_pfn) {
+ mminit_dprintk(MMINIT_WARNING, "pfnvalidation",
+ "Start of range %lu -> %lu exceeds SPARSEMEM max %lu\n",
+ *start_pfn, *end_pfn, max_sparsemem_pfn);
+ WARN_ON_ONCE(1);
+ *start_pfn = max_sparsemem_pfn;
+ *end_pfn = max_sparsemem_pfn;
+ } else if (*end_pfn > max_sparsemem_pfn) {
+ mminit_dprintk(MMINIT_WARNING, "pfnvalidation",
+ "End of range %lu -> %lu exceeds SPARSEMEM max %lu\n",
+ *start_pfn, *end_pfn, max_sparsemem_pfn);
+ WARN_ON_ONCE(1);
+ *end_pfn = max_sparsemem_pfn;
+ }
+}
+
+/* Record a memory area against a node. */
+void __init memory_present(int nid, unsigned long start, unsigned long end)
+{
+ unsigned long pfn;
start &= PAGE_SECTION_MASK;
+ mminit_validate_memmodel_limits(&start, &end);
for (pfn = start; pfn < end; pfn += PAGES_PER_SECTION) {
unsigned long section = pfn_to_section_nr(pfn);
struct mem_section *ms;
unsigned long pfn;
unsigned long nr_pages = 0;
+ mminit_validate_memmodel_limits(&start_pfn, &end_pfn);
for (pfn = start_pfn; pfn < end_pfn; pfn += PAGES_PER_SECTION) {
if (nid != early_pfn_to_nid(pfn))
continue;
}
#endif /* CONFIG_MEMORY_HOTPLUG */
-static unsigned long *__init sparse_early_usemap_alloc(unsigned long pnum)
+#ifdef CONFIG_MEMORY_HOTREMOVE
+static unsigned long * __init
+sparse_early_usemaps_alloc_pgdat_section(struct pglist_data *pgdat,
+ unsigned long count)
{
- unsigned long *usemap, section_nr;
- struct mem_section *ms = __nr_to_section(pnum);
- int nid = sparse_early_nid(ms);
- struct pglist_data *pgdat = NODE_DATA(nid);
+ unsigned long section_nr;
/*
- * Usemap's page can't be freed until freeing other sections
- * which use it. And, Pgdat has same feature.
- * If section A has pgdat and section B has usemap for other
- * sections (includes section A), both sections can't be removed,
- * because there is the dependency each other.
- * To solve above issue, this collects all usemap on the same section
- * which has pgdat.
+ * A page may contain usemaps for other sections preventing the
+ * page being freed and making a section unremovable while
+ * other sections referencing the usemap retmain active. Similarly,
+ * a pgdat can prevent a section being removed. If section A
+ * contains a pgdat and section B contains the usemap, both
+ * sections become inter-dependent. This allocates usemaps
+ * from the same section as the pgdat where possible to avoid
+ * this problem.
*/
section_nr = pfn_to_section_nr(__pa(pgdat) >> PAGE_SHIFT);
- usemap = alloc_bootmem_section(usemap_size(), section_nr);
- if (usemap)
- return usemap;
+ return alloc_bootmem_section(usemap_size() * count, section_nr);
+}
+
+static void __init check_usemap_section_nr(int nid, unsigned long *usemap)
+{
+ unsigned long usemap_snr, pgdat_snr;
+ static unsigned long old_usemap_snr = NR_MEM_SECTIONS;
+ static unsigned long old_pgdat_snr = NR_MEM_SECTIONS;
+ struct pglist_data *pgdat = NODE_DATA(nid);
+ int usemap_nid;
- /* Stupid: suppress gcc warning for SPARSEMEM && !NUMA */
- nid = 0;
+ usemap_snr = pfn_to_section_nr(__pa(usemap) >> PAGE_SHIFT);
+ pgdat_snr = pfn_to_section_nr(__pa(pgdat) >> PAGE_SHIFT);
+ if (usemap_snr == pgdat_snr)
+ return;
- printk(KERN_WARNING "%s: allocation failed\n", __func__);
+ if (old_usemap_snr == usemap_snr && old_pgdat_snr == pgdat_snr)
+ /* skip redundant message */
+ return;
+
+ old_usemap_snr = usemap_snr;
+ old_pgdat_snr = pgdat_snr;
+
+ usemap_nid = sparse_early_nid(__nr_to_section(usemap_snr));
+ if (usemap_nid != nid) {
+ printk(KERN_INFO
+ "node %d must be removed before remove section %ld\n",
+ nid, usemap_snr);
+ return;
+ }
+ /*
+ * There is a circular dependency.
+ * Some platforms allow un-removable section because they will just
+ * gather other removable sections for dynamic partitioning.
+ * Just notify un-removable section's number here.
+ */
+ printk(KERN_INFO "Section %ld and %ld (node %d)", usemap_snr,
+ pgdat_snr, nid);
+ printk(KERN_CONT
+ " have a circular dependency on usemap and pgdat allocations\n");
+}
+#else
+static unsigned long * __init
+sparse_early_usemaps_alloc_pgdat_section(struct pglist_data *pgdat,
+ unsigned long count)
+{
return NULL;
}
+static void __init check_usemap_section_nr(int nid, unsigned long *usemap)
+{
+}
+#endif /* CONFIG_MEMORY_HOTREMOVE */
+
+static void __init sparse_early_usemaps_alloc_node(unsigned long**usemap_map,
+ unsigned long pnum_begin,
+ unsigned long pnum_end,
+ unsigned long usemap_count, int nodeid)
+{
+ void *usemap;
+ unsigned long pnum;
+ int size = usemap_size();
+
+ usemap = sparse_early_usemaps_alloc_pgdat_section(NODE_DATA(nodeid),
+ usemap_count);
+ if (usemap) {
+ for (pnum = pnum_begin; pnum < pnum_end; pnum++) {
+ if (!present_section_nr(pnum))
+ continue;
+ usemap_map[pnum] = usemap;
+ usemap += size;
+ }
+ return;
+ }
+
+ usemap = alloc_bootmem_node(NODE_DATA(nodeid), size * usemap_count);
+ if (usemap) {
+ for (pnum = pnum_begin; pnum < pnum_end; pnum++) {
+ if (!present_section_nr(pnum))
+ continue;
+ usemap_map[pnum] = usemap;
+ usemap += size;
+ check_usemap_section_nr(nodeid, usemap_map[pnum]);
+ }
+ return;
+ }
+
+ printk(KERN_WARNING "%s: allocation failed\n", __func__);
+}
+
#ifndef CONFIG_SPARSEMEM_VMEMMAP
struct page __init *sparse_mem_map_populate(unsigned long pnum, int nid)
{
struct page *map;
+ unsigned long size;
map = alloc_remap(nid, sizeof(struct page) * PAGES_PER_SECTION);
if (map)
return map;
- map = alloc_bootmem_pages_node(NODE_DATA(nid),
- PAGE_ALIGN(sizeof(struct page) * PAGES_PER_SECTION));
+ size = PAGE_ALIGN(sizeof(struct page) * PAGES_PER_SECTION);
+ map = __alloc_bootmem_node_high(NODE_DATA(nid), size,
+ PAGE_SIZE, __pa(MAX_DMA_ADDRESS));
return map;
}
+void __init sparse_mem_maps_populate_node(struct page **map_map,
+ unsigned long pnum_begin,
+ unsigned long pnum_end,
+ unsigned long map_count, int nodeid)
+{
+ void *map;
+ unsigned long pnum;
+ unsigned long size = sizeof(struct page) * PAGES_PER_SECTION;
+
+ map = alloc_remap(nodeid, size * map_count);
+ if (map) {
+ for (pnum = pnum_begin; pnum < pnum_end; pnum++) {
+ if (!present_section_nr(pnum))
+ continue;
+ map_map[pnum] = map;
+ map += size;
+ }
+ return;
+ }
+
+ size = PAGE_ALIGN(size);
+ map = __alloc_bootmem_node_high(NODE_DATA(nodeid), size * map_count,
+ PAGE_SIZE, __pa(MAX_DMA_ADDRESS));
+ if (map) {
+ for (pnum = pnum_begin; pnum < pnum_end; pnum++) {
+ if (!present_section_nr(pnum))
+ continue;
+ map_map[pnum] = map;
+ map += size;
+ }
+ return;
+ }
+
+ /* fallback */
+ for (pnum = pnum_begin; pnum < pnum_end; pnum++) {
+ struct mem_section *ms;
+
+ if (!present_section_nr(pnum))
+ continue;
+ map_map[pnum] = sparse_mem_map_populate(pnum, nodeid);
+ if (map_map[pnum])
+ continue;
+ ms = __nr_to_section(pnum);
+ printk(KERN_ERR "%s: sparsemem memory map backing failed "
+ "some memory will not be available.\n", __func__);
+ ms->section_mem_map = 0;
+ }
+}
#endif /* !CONFIG_SPARSEMEM_VMEMMAP */
-struct page __init *sparse_early_mem_map_alloc(unsigned long pnum)
+#ifdef CONFIG_SPARSEMEM_ALLOC_MEM_MAP_TOGETHER
+static void __init sparse_early_mem_maps_alloc_node(struct page **map_map,
+ unsigned long pnum_begin,
+ unsigned long pnum_end,
+ unsigned long map_count, int nodeid)
+{
+ sparse_mem_maps_populate_node(map_map, pnum_begin, pnum_end,
+ map_count, nodeid);
+}
+#else
+static struct page __init *sparse_early_mem_map_alloc(unsigned long pnum)
{
struct page *map;
struct mem_section *ms = __nr_to_section(pnum);
ms->section_mem_map = 0;
return NULL;
}
+#endif
void __attribute__((weak)) __meminit vmemmap_populate_print_last(void)
{
}
+
/*
* Allocate the accumulated non-linear sections, allocate a mem_map
* for each and record the physical to section mapping.
unsigned long *usemap;
unsigned long **usemap_map;
int size;
+ int nodeid_begin = 0;
+ unsigned long pnum_begin = 0;
+ unsigned long usemap_count;
+#ifdef CONFIG_SPARSEMEM_ALLOC_MEM_MAP_TOGETHER
+ unsigned long map_count;
+ int size2;
+ struct page **map_map;
+#endif
/*
* map is using big page (aka 2M in x86 64 bit)
panic("can not allocate usemap_map\n");
for (pnum = 0; pnum < NR_MEM_SECTIONS; pnum++) {
+ struct mem_section *ms;
+
if (!present_section_nr(pnum))
continue;
- usemap_map[pnum] = sparse_early_usemap_alloc(pnum);
+ ms = __nr_to_section(pnum);
+ nodeid_begin = sparse_early_nid(ms);
+ pnum_begin = pnum;
+ break;
}
+ usemap_count = 1;
+ for (pnum = pnum_begin + 1; pnum < NR_MEM_SECTIONS; pnum++) {
+ struct mem_section *ms;
+ int nodeid;
+
+ if (!present_section_nr(pnum))
+ continue;
+ ms = __nr_to_section(pnum);
+ nodeid = sparse_early_nid(ms);
+ if (nodeid == nodeid_begin) {
+ usemap_count++;
+ continue;
+ }
+ /* ok, we need to take cake of from pnum_begin to pnum - 1*/
+ sparse_early_usemaps_alloc_node(usemap_map, pnum_begin, pnum,
+ usemap_count, nodeid_begin);
+ /* new start, update count etc*/
+ nodeid_begin = nodeid;
+ pnum_begin = pnum;
+ usemap_count = 1;
+ }
+ /* ok, last chunk */
+ sparse_early_usemaps_alloc_node(usemap_map, pnum_begin, NR_MEM_SECTIONS,
+ usemap_count, nodeid_begin);
+
+#ifdef CONFIG_SPARSEMEM_ALLOC_MEM_MAP_TOGETHER
+ size2 = sizeof(struct page *) * NR_MEM_SECTIONS;
+ map_map = alloc_bootmem(size2);
+ if (!map_map)
+ panic("can not allocate map_map\n");
+
+ for (pnum = 0; pnum < NR_MEM_SECTIONS; pnum++) {
+ struct mem_section *ms;
+
+ if (!present_section_nr(pnum))
+ continue;
+ ms = __nr_to_section(pnum);
+ nodeid_begin = sparse_early_nid(ms);
+ pnum_begin = pnum;
+ break;
+ }
+ map_count = 1;
+ for (pnum = pnum_begin + 1; pnum < NR_MEM_SECTIONS; pnum++) {
+ struct mem_section *ms;
+ int nodeid;
+
+ if (!present_section_nr(pnum))
+ continue;
+ ms = __nr_to_section(pnum);
+ nodeid = sparse_early_nid(ms);
+ if (nodeid == nodeid_begin) {
+ map_count++;
+ continue;
+ }
+ /* ok, we need to take cake of from pnum_begin to pnum - 1*/
+ sparse_early_mem_maps_alloc_node(map_map, pnum_begin, pnum,
+ map_count, nodeid_begin);
+ /* new start, update count etc*/
+ nodeid_begin = nodeid;
+ pnum_begin = pnum;
+ map_count = 1;
+ }
+ /* ok, last chunk */
+ sparse_early_mem_maps_alloc_node(map_map, pnum_begin, NR_MEM_SECTIONS,
+ map_count, nodeid_begin);
+#endif
for (pnum = 0; pnum < NR_MEM_SECTIONS; pnum++) {
if (!present_section_nr(pnum))
if (!usemap)
continue;
+#ifdef CONFIG_SPARSEMEM_ALLOC_MEM_MAP_TOGETHER
+ map = map_map[pnum];
+#else
map = sparse_early_mem_map_alloc(pnum);
+#endif
if (!map)
continue;
vmemmap_populate_print_last();
+#ifdef CONFIG_SPARSEMEM_ALLOC_MEM_MAP_TOGETHER
+ free_bootmem(__pa(map_map), size2);
+#endif
free_bootmem(__pa(usemap_map), size);
}
* 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(struct zone *zone, unsigned long start_pfn,
+int __meminit sparse_add_one_section(struct zone *zone, unsigned long start_pfn,
int nr_pages)
{
unsigned long section_nr = pfn_to_section_nr(start_pfn);
Code Review / linux-2.6.git / blobdiff