*/
#include <linux/kernel.h>
+#include <linux/slab.h>
#include <linux/init.h>
#include <linux/bitops.h>
#include <linux/poison.h>
+#include <linux/pfn.h>
+#include <linux/debugfs.h>
+#include <linux/seq_file.h>
#include <linux/memblock.h>
struct memblock memblock;
-static int memblock_debug;
+static int memblock_debug, memblock_can_resize;
static struct memblock_region memblock_memory_init_regions[INIT_MEMBLOCK_REGIONS + 1];
static struct memblock_region memblock_reserved_init_regions[INIT_MEMBLOCK_REGIONS + 1];
#define MEMBLOCK_ERROR (~(phys_addr_t)0)
-static int __init early_memblock(char *p)
+/* inline so we don't get a warning when pr_debug is compiled out */
+static inline const char *memblock_type_name(struct memblock_type *type)
{
- if (p && strstr(p, "debug"))
- memblock_debug = 1;
- return 0;
+ if (type == &memblock.memory)
+ return "memory";
+ else if (type == &memblock.reserved)
+ return "reserved";
+ else
+ return "unknown";
}
-early_param("memblock", early_memblock);
-
-static void memblock_dump(struct memblock_type *region, char *name)
-{
- unsigned long long base, size;
- int i;
-
- pr_info(" %s.cnt = 0x%lx\n", name, region->cnt);
- for (i = 0; i < region->cnt; i++) {
- base = region->regions[i].base;
- size = region->regions[i].size;
+/*
+ * Address comparison utilities
+ */
- pr_info(" %s[0x%x]\t0x%016llx - 0x%016llx, 0x%llx bytes\n",
- name, i, base, base + size - 1, size);
- }
+static phys_addr_t memblock_align_down(phys_addr_t addr, phys_addr_t size)
+{
+ return addr & ~(size - 1);
}
-void memblock_dump_all(void)
+static phys_addr_t memblock_align_up(phys_addr_t addr, phys_addr_t size)
{
- if (!memblock_debug)
- return;
-
- pr_info("MEMBLOCK configuration:\n");
- pr_info(" memory size = 0x%llx\n", (unsigned long long)memblock.memory_size);
-
- memblock_dump(&memblock.memory, "memory");
- memblock_dump(&memblock.reserved, "reserved");
+ return (addr + (size - 1)) & ~(size - 1);
}
static unsigned long memblock_addrs_overlap(phys_addr_t base1, phys_addr_t size1,
return memblock_addrs_adjacent(base1, size1, base2, size2);
}
+long memblock_overlaps_region(struct memblock_type *type, phys_addr_t base, phys_addr_t size)
+{
+ unsigned long i;
+
+ for (i = 0; i < type->cnt; i++) {
+ phys_addr_t rgnbase = type->regions[i].base;
+ phys_addr_t rgnsize = type->regions[i].size;
+ if (memblock_addrs_overlap(base, size, rgnbase, rgnsize))
+ break;
+ }
+
+ return (i < type->cnt) ? i : -1;
+}
+
+/*
+ * Find, allocate, deallocate or reserve unreserved regions. All allocations
+ * are top-down.
+ */
+
+static phys_addr_t __init memblock_find_region(phys_addr_t start, phys_addr_t end,
+ phys_addr_t size, phys_addr_t align)
+{
+ phys_addr_t base, res_base;
+ long j;
+
+ base = memblock_align_down((end - size), align);
+ while (start <= base) {
+ j = memblock_overlaps_region(&memblock.reserved, base, size);
+ if (j < 0)
+ return base;
+ res_base = memblock.reserved.regions[j].base;
+ if (res_base < size)
+ break;
+ base = memblock_align_down(res_base - size, align);
+ }
+
+ return MEMBLOCK_ERROR;
+}
+
+static phys_addr_t __init memblock_find_base(phys_addr_t size, phys_addr_t align,
+ phys_addr_t start, phys_addr_t end)
+{
+ long i;
+
+ BUG_ON(0 == size);
+
+ size = memblock_align_up(size, align);
+
+ /* Pump up max_addr */
+ if (end == MEMBLOCK_ALLOC_ACCESSIBLE)
+ end = memblock.current_limit;
+
+ /* We do a top-down search, this tends to limit memory
+ * fragmentation by keeping early boot allocs near the
+ * top of memory
+ */
+ for (i = memblock.memory.cnt - 1; i >= 0; i--) {
+ phys_addr_t memblockbase = memblock.memory.regions[i].base;
+ phys_addr_t memblocksize = memblock.memory.regions[i].size;
+ phys_addr_t bottom, top, found;
+
+ if (memblocksize < size)
+ continue;
+ if ((memblockbase + memblocksize) <= start)
+ break;
+ bottom = max(memblockbase, start);
+ top = min(memblockbase + memblocksize, end);
+ if (bottom >= top)
+ continue;
+ found = memblock_find_region(bottom, top, size, align);
+ if (found != MEMBLOCK_ERROR)
+ return found;
+ }
+ return MEMBLOCK_ERROR;
+}
+
static void memblock_remove_region(struct memblock_type *type, unsigned long r)
{
unsigned long i;
memblock_remove_region(type, r2);
}
-void __init memblock_init(void)
-{
- /* Hookup the initial arrays */
- memblock.memory.regions = memblock_memory_init_regions;
- memblock.memory.max = INIT_MEMBLOCK_REGIONS;
- memblock.reserved.regions = memblock_reserved_init_regions;
- memblock.reserved.max = INIT_MEMBLOCK_REGIONS;
+/* Defined below but needed now */
+static long memblock_add_region(struct memblock_type *type, phys_addr_t base, phys_addr_t size);
- /* Write a marker in the unused last array entry */
- memblock.memory.regions[INIT_MEMBLOCK_REGIONS].base = (phys_addr_t)RED_INACTIVE;
- memblock.reserved.regions[INIT_MEMBLOCK_REGIONS].base = (phys_addr_t)RED_INACTIVE;
+static int memblock_double_array(struct memblock_type *type)
+{
+ struct memblock_region *new_array, *old_array;
+ phys_addr_t old_size, new_size, addr;
+ int use_slab = slab_is_available();
- /* Create a dummy zero size MEMBLOCK which will get coalesced away later.
- * This simplifies the memblock_add() code below...
+ /* We don't allow resizing until we know about the reserved regions
+ * of memory that aren't suitable for allocation
*/
- memblock.memory.regions[0].base = 0;
- memblock.memory.regions[0].size = 0;
- memblock.memory.cnt = 1;
+ if (!memblock_can_resize)
+ return -1;
- /* Ditto. */
- memblock.reserved.regions[0].base = 0;
- memblock.reserved.regions[0].size = 0;
- memblock.reserved.cnt = 1;
+ pr_debug("memblock: %s array full, doubling...", memblock_type_name(type));
+
+ /* Calculate new doubled size */
+ old_size = type->max * sizeof(struct memblock_region);
+ new_size = old_size << 1;
+
+ /* Try to find some space for it.
+ *
+ * WARNING: We assume that either slab_is_available() and we use it or
+ * we use MEMBLOCK for allocations. That means that this is unsafe to use
+ * when bootmem is currently active (unless bootmem itself is implemented
+ * on top of MEMBLOCK which isn't the case yet)
+ *
+ * This should however not be an issue for now, as we currently only
+ * call into MEMBLOCK while it's still active, or much later when slab is
+ * active for memory hotplug operations
+ */
+ if (use_slab) {
+ new_array = kmalloc(new_size, GFP_KERNEL);
+ addr = new_array == NULL ? MEMBLOCK_ERROR : __pa(new_array);
+ } else
+ addr = memblock_find_base(new_size, sizeof(phys_addr_t), 0, MEMBLOCK_ALLOC_ACCESSIBLE);
+ if (addr == MEMBLOCK_ERROR) {
+ pr_err("memblock: Failed to double %s array from %ld to %ld entries !\n",
+ memblock_type_name(type), type->max, type->max * 2);
+ return -1;
+ }
+ new_array = __va(addr);
- memblock.current_limit = MEMBLOCK_ALLOC_ANYWHERE;
-}
+ /* Found space, we now need to move the array over before
+ * we add the reserved region since it may be our reserved
+ * array itself that is full.
+ */
+ memcpy(new_array, type->regions, old_size);
+ memset(new_array + type->max, 0, old_size);
+ old_array = type->regions;
+ type->regions = new_array;
+ type->max <<= 1;
+
+ /* If we use SLAB that's it, we are done */
+ if (use_slab)
+ return 0;
-void __init memblock_analyze(void)
-{
- int i;
+ /* Add the new reserved region now. Should not fail ! */
+ BUG_ON(memblock_add_region(&memblock.reserved, addr, new_size) < 0);
- /* Check marker in the unused last array entry */
- WARN_ON(memblock_memory_init_regions[INIT_MEMBLOCK_REGIONS].base
- != (phys_addr_t)RED_INACTIVE);
- WARN_ON(memblock_reserved_init_regions[INIT_MEMBLOCK_REGIONS].base
- != (phys_addr_t)RED_INACTIVE);
+ /* If the array wasn't our static init one, then free it. We only do
+ * that before SLAB is available as later on, we don't know whether
+ * to use kfree or free_bootmem_pages(). Shouldn't be a big deal
+ * anyways
+ */
+ if (old_array != memblock_memory_init_regions &&
+ old_array != memblock_reserved_init_regions)
+ memblock_free(__pa(old_array), old_size);
- memblock.memory_size = 0;
+ return 0;
+}
- for (i = 0; i < memblock.memory.cnt; i++)
- memblock.memory_size += memblock.memory.regions[i].size;
+extern int __weak memblock_memory_can_coalesce(phys_addr_t addr1, phys_addr_t size1,
+ phys_addr_t addr2, phys_addr_t size2)
+{
+ return 1;
}
static long memblock_add_region(struct memblock_type *type, phys_addr_t base, phys_addr_t size)
return 0;
adjacent = memblock_addrs_adjacent(base, size, rgnbase, rgnsize);
+ /* Check if arch allows coalescing */
+ if (adjacent != 0 && type == &memblock.memory &&
+ !memblock_memory_can_coalesce(base, size, rgnbase, rgnsize))
+ break;
if (adjacent > 0) {
type->regions[i].base -= size;
type->regions[i].size += size;
}
}
- if ((i < type->cnt - 1) && memblock_regions_adjacent(type, i, i+1)) {
+ /* If we plugged a hole, we may want to also coalesce with the
+ * next region
+ */
+ if ((i < type->cnt - 1) && memblock_regions_adjacent(type, i, i+1) &&
+ ((type != &memblock.memory || memblock_memory_can_coalesce(type->regions[i].base,
+ type->regions[i].size,
+ type->regions[i+1].base,
+ type->regions[i+1].size)))) {
memblock_coalesce_regions(type, i, i+1);
coalesced++;
}
if (coalesced)
return coalesced;
- if (type->cnt >= type->max)
+
+ /* If we are out of space, we fail. It's too late to resize the array
+ * but then this shouldn't have happened in the first place.
+ */
+ if (WARN_ON(type->cnt >= type->max))
return -1;
/* Couldn't coalesce the MEMBLOCK, so add it to the sorted table. */
}
type->cnt++;
+ /* The array is full ? Try to resize it. If that fails, we undo
+ * our allocation and return an error
+ */
+ if (type->cnt == type->max && memblock_double_array(type)) {
+ type->cnt--;
+ return -1;
+ }
+
return 0;
}
return memblock_add_region(_rgn, base, size);
}
-long memblock_overlaps_region(struct memblock_type *type, phys_addr_t base, phys_addr_t size)
+phys_addr_t __init __memblock_alloc_base(phys_addr_t size, phys_addr_t align, phys_addr_t max_addr)
{
- unsigned long i;
+ phys_addr_t found;
- for (i = 0; i < type->cnt; i++) {
- phys_addr_t rgnbase = type->regions[i].base;
- phys_addr_t rgnsize = type->regions[i].size;
- if (memblock_addrs_overlap(base, size, rgnbase, rgnsize))
- break;
- }
+ /* We align the size to limit fragmentation. Without this, a lot of
+ * small allocs quickly eat up the whole reserve array on sparc
+ */
+ size = memblock_align_up(size, align);
- return (i < type->cnt) ? i : -1;
-}
+ found = memblock_find_base(size, align, 0, max_addr);
+ if (found != MEMBLOCK_ERROR &&
+ memblock_add_region(&memblock.reserved, found, size) >= 0)
+ return found;
-static phys_addr_t memblock_align_down(phys_addr_t addr, phys_addr_t size)
-{
- return addr & ~(size - 1);
+ return 0;
}
-static phys_addr_t memblock_align_up(phys_addr_t addr, phys_addr_t size)
+phys_addr_t __init memblock_alloc_base(phys_addr_t size, phys_addr_t align, phys_addr_t max_addr)
{
- return (addr + (size - 1)) & ~(size - 1);
+ phys_addr_t alloc;
+
+ alloc = __memblock_alloc_base(size, align, max_addr);
+
+ if (alloc == 0)
+ panic("ERROR: Failed to allocate 0x%llx bytes below 0x%llx.\n",
+ (unsigned long long) size, (unsigned long long) max_addr);
+
+ return alloc;
}
-static phys_addr_t __init memblock_find_region(phys_addr_t start, phys_addr_t end,
- phys_addr_t size, phys_addr_t align)
+phys_addr_t __init memblock_alloc(phys_addr_t size, phys_addr_t align)
{
- phys_addr_t base, res_base;
- long j;
+ return memblock_alloc_base(size, align, MEMBLOCK_ALLOC_ACCESSIBLE);
+}
- base = memblock_align_down((end - size), align);
- while (start <= base) {
- j = memblock_overlaps_region(&memblock.reserved, base, size);
- if (j < 0)
- return base;
- res_base = memblock.reserved.regions[j].base;
- if (res_base < size)
- break;
- base = memblock_align_down(res_base - size, align);
- }
- return MEMBLOCK_ERROR;
-}
+/*
+ * Additional node-local allocators. Search for node memory is bottom up
+ * and walks memblock regions within that node bottom-up as well, but allocation
+ * within an memblock region is top-down. XXX I plan to fix that at some stage
+ *
+ * WARNING: Only available after early_node_map[] has been populated,
+ * on some architectures, that is after all the calls to add_active_range()
+ * have been done to populate it.
+ */
phys_addr_t __weak __init memblock_nid_range(phys_addr_t start, phys_addr_t end, int *nid)
{
+#ifdef CONFIG_ARCH_POPULATES_NODE_MAP
+ /*
+ * This code originates from sparc which really wants use to walk by addresses
+ * and returns the nid. This is not very convenient for early_pfn_map[] users
+ * as the map isn't sorted yet, and it really wants to be walked by nid.
+ *
+ * For now, I implement the inefficient method below which walks the early
+ * map multiple times. Eventually we may want to use an ARCH config option
+ * to implement a completely different method for both case.
+ */
+ unsigned long start_pfn, end_pfn;
+ int i;
+
+ for (i = 0; i < MAX_NUMNODES; i++) {
+ get_pfn_range_for_nid(i, &start_pfn, &end_pfn);
+ if (start < PFN_PHYS(start_pfn) || start >= PFN_PHYS(end_pfn))
+ continue;
+ *nid = i;
+ return min(end, PFN_PHYS(end_pfn));
+ }
+#endif
*nid = 0;
return end;
BUG_ON(0 == size);
+ /* We align the size to limit fragmentation. Without this, a lot of
+ * small allocs quickly eat up the whole reserve array on sparc
+ */
+ size = memblock_align_up(size, align);
+
/* We do a bottom-up search for a region with the right
* nid since that's easier considering how memblock_nid_range()
* works
*/
- size = memblock_align_up(size, align);
-
for (i = 0; i < mem->cnt; i++) {
phys_addr_t ret = memblock_alloc_nid_region(&mem->regions[i],
size, align, nid);
return ret;
}
- return memblock_alloc(size, align);
-}
-
-phys_addr_t __init memblock_alloc(phys_addr_t size, phys_addr_t align)
-{
- return memblock_alloc_base(size, align, MEMBLOCK_ALLOC_ACCESSIBLE);
+ return 0;
}
-phys_addr_t __init memblock_alloc_base(phys_addr_t size, phys_addr_t align, phys_addr_t max_addr)
+phys_addr_t __init memblock_alloc_try_nid(phys_addr_t size, phys_addr_t align, int nid)
{
- phys_addr_t alloc;
+ phys_addr_t res = memblock_alloc_nid(size, align, nid);
- alloc = __memblock_alloc_base(size, align, max_addr);
-
- if (alloc == 0)
- panic("ERROR: Failed to allocate 0x%llx bytes below 0x%llx.\n",
- (unsigned long long) size, (unsigned long long) max_addr);
-
- return alloc;
+ if (res)
+ return res;
+ return memblock_alloc_base(size, align, MEMBLOCK_ALLOC_ANYWHERE);
}
-phys_addr_t __init __memblock_alloc_base(phys_addr_t size, phys_addr_t align, phys_addr_t max_addr)
-{
- long i;
- phys_addr_t base = 0;
- phys_addr_t res_base;
-
- BUG_ON(0 == size);
-
- size = memblock_align_up(size, align);
-
- /* Pump up max_addr */
- if (max_addr == MEMBLOCK_ALLOC_ACCESSIBLE)
- max_addr = memblock.current_limit;
- /* We do a top-down search, this tends to limit memory
- * fragmentation by keeping early boot allocs near the
- * top of memory
- */
- for (i = memblock.memory.cnt - 1; i >= 0; i--) {
- phys_addr_t memblockbase = memblock.memory.regions[i].base;
- phys_addr_t memblocksize = memblock.memory.regions[i].size;
-
- if (memblocksize < size)
- continue;
- base = min(memblockbase + memblocksize, max_addr);
- res_base = memblock_find_region(memblockbase, base, size, align);
- if (res_base != MEMBLOCK_ERROR &&
- memblock_add_region(&memblock.reserved, res_base, size) >= 0)
- return res_base;
- }
- return 0;
-}
+/*
+ * Remaining API functions
+ */
/* You must call memblock_analyze() before this. */
phys_addr_t __init memblock_phys_mem_size(void)
memblock.current_limit = limit;
}
+static void memblock_dump(struct memblock_type *region, char *name)
+{
+ unsigned long long base, size;
+ int i;
+
+ pr_info(" %s.cnt = 0x%lx\n", name, region->cnt);
+
+ for (i = 0; i < region->cnt; i++) {
+ base = region->regions[i].base;
+ size = region->regions[i].size;
+
+ pr_info(" %s[0x%x]\t0x%016llx - 0x%016llx, 0x%llx bytes\n",
+ name, i, base, base + size - 1, size);
+ }
+}
+
+void memblock_dump_all(void)
+{
+ if (!memblock_debug)
+ return;
+
+ pr_info("MEMBLOCK configuration:\n");
+ pr_info(" memory size = 0x%llx\n", (unsigned long long)memblock.memory_size);
+
+ memblock_dump(&memblock.memory, "memory");
+ memblock_dump(&memblock.reserved, "reserved");
+}
+
+void __init memblock_analyze(void)
+{
+ int i;
+
+ /* Check marker in the unused last array entry */
+ WARN_ON(memblock_memory_init_regions[INIT_MEMBLOCK_REGIONS].base
+ != (phys_addr_t)RED_INACTIVE);
+ WARN_ON(memblock_reserved_init_regions[INIT_MEMBLOCK_REGIONS].base
+ != (phys_addr_t)RED_INACTIVE);
+
+ memblock.memory_size = 0;
+
+ for (i = 0; i < memblock.memory.cnt; i++)
+ memblock.memory_size += memblock.memory.regions[i].size;
+
+ /* We allow resizing from there */
+ memblock_can_resize = 1;
+}
+
+void __init memblock_init(void)
+{
+ /* Hookup the initial arrays */
+ memblock.memory.regions = memblock_memory_init_regions;
+ memblock.memory.max = INIT_MEMBLOCK_REGIONS;
+ memblock.reserved.regions = memblock_reserved_init_regions;
+ memblock.reserved.max = INIT_MEMBLOCK_REGIONS;
+
+ /* Write a marker in the unused last array entry */
+ memblock.memory.regions[INIT_MEMBLOCK_REGIONS].base = (phys_addr_t)RED_INACTIVE;
+ memblock.reserved.regions[INIT_MEMBLOCK_REGIONS].base = (phys_addr_t)RED_INACTIVE;
+
+ /* Create a dummy zero size MEMBLOCK which will get coalesced away later.
+ * This simplifies the memblock_add() code below...
+ */
+ memblock.memory.regions[0].base = 0;
+ memblock.memory.regions[0].size = 0;
+ memblock.memory.cnt = 1;
+
+ /* Ditto. */
+ memblock.reserved.regions[0].base = 0;
+ memblock.reserved.regions[0].size = 0;
+ memblock.reserved.cnt = 1;
+
+ memblock.current_limit = MEMBLOCK_ALLOC_ANYWHERE;
+}
+
+static int __init early_memblock(char *p)
+{
+ if (p && strstr(p, "debug"))
+ memblock_debug = 1;
+ return 0;
+}
+early_param("memblock", early_memblock);
+
+#ifdef CONFIG_DEBUG_FS
+
+static int memblock_debug_show(struct seq_file *m, void *private)
+{
+ struct memblock_type *type = m->private;
+ struct memblock_region *reg;
+ int i;
+
+ for (i = 0; i < type->cnt; i++) {
+ reg = &type->regions[i];
+ seq_printf(m, "%4d: ", i);
+ if (sizeof(phys_addr_t) == 4)
+ seq_printf(m, "0x%08lx..0x%08lx\n",
+ (unsigned long)reg->base,
+ (unsigned long)(reg->base + reg->size - 1));
+ else
+ seq_printf(m, "0x%016llx..0x%016llx\n",
+ (unsigned long long)reg->base,
+ (unsigned long long)(reg->base + reg->size - 1));
+
+ }
+ return 0;
+}
+
+static int memblock_debug_open(struct inode *inode, struct file *file)
+{
+ return single_open(file, memblock_debug_show, inode->i_private);
+}
+
+static const struct file_operations memblock_debug_fops = {
+ .open = memblock_debug_open,
+ .read = seq_read,
+ .llseek = seq_lseek,
+ .release = single_release,
+};
+
+static int __init memblock_init_debugfs(void)
+{
+ struct dentry *root = debugfs_create_dir("memblock", NULL);
+ if (!root)
+ return -ENXIO;
+ debugfs_create_file("memory", S_IRUGO, root, &memblock.memory, &memblock_debug_fops);
+ debugfs_create_file("reserved", S_IRUGO, root, &memblock.reserved, &memblock_debug_fops);
+
+ return 0;
+}
+__initcall(memblock_init_debugfs);
+
+#endif /* CONFIG_DEBUG_FS */
projects / deliverable / linux.git / blobdiff