diff options
Diffstat (limited to 'mm/memblock.c')
| -rw-r--r-- | mm/memblock.c | 233 |
1 files changed, 167 insertions, 66 deletions
diff --git a/mm/memblock.c b/mm/memblock.c index 237944479d25..470601115892 100644 --- a/mm/memblock.c +++ b/mm/memblock.c @@ -20,13 +20,19 @@ #include <linux/kmemleak.h> #include <linux/seq_file.h> #include <linux/memblock.h> -#include <linux/bootmem.h> #include <asm/sections.h> #include <linux/io.h> #include "internal.h" +#define INIT_MEMBLOCK_REGIONS 128 +#define INIT_PHYSMEM_REGIONS 4 + +#ifndef INIT_MEMBLOCK_RESERVED_REGIONS +# define INIT_MEMBLOCK_RESERVED_REGIONS INIT_MEMBLOCK_REGIONS +#endif + /** * DOC: memblock overview * @@ -82,8 +88,18 @@ * initialization compltes. */ +#ifndef CONFIG_NEED_MULTIPLE_NODES +struct pglist_data __refdata contig_page_data; +EXPORT_SYMBOL(contig_page_data); +#endif + +unsigned long max_low_pfn; +unsigned long min_low_pfn; +unsigned long max_pfn; +unsigned long long max_possible_pfn; + static struct memblock_region memblock_memory_init_regions[INIT_MEMBLOCK_REGIONS] __initdata_memblock; -static struct memblock_region memblock_reserved_init_regions[INIT_MEMBLOCK_REGIONS] __initdata_memblock; +static struct memblock_region memblock_reserved_init_regions[INIT_MEMBLOCK_RESERVED_REGIONS] __initdata_memblock; #ifdef CONFIG_HAVE_MEMBLOCK_PHYS_MAP static struct memblock_region memblock_physmem_init_regions[INIT_PHYSMEM_REGIONS] __initdata_memblock; #endif @@ -96,7 +112,7 @@ struct memblock memblock __initdata_memblock = { .reserved.regions = memblock_reserved_init_regions, .reserved.cnt = 1, /* empty dummy entry */ - .reserved.max = INIT_MEMBLOCK_REGIONS, + .reserved.max = INIT_MEMBLOCK_RESERVED_REGIONS, .reserved.name = "reserved", #ifdef CONFIG_HAVE_MEMBLOCK_PHYS_MAP @@ -253,7 +269,8 @@ phys_addr_t __init_memblock memblock_find_in_range_node(phys_addr_t size, phys_addr_t kernel_end, ret; /* pump up @end */ - if (end == MEMBLOCK_ALLOC_ACCESSIBLE) + if (end == MEMBLOCK_ALLOC_ACCESSIBLE || + end == MEMBLOCK_ALLOC_KASAN) end = memblock.current_limit; /* avoid allocating the first page */ @@ -791,7 +808,14 @@ int __init_memblock memblock_remove(phys_addr_t base, phys_addr_t size) return memblock_remove_range(&memblock.memory, base, size); } - +/** + * memblock_free - free boot memory block + * @base: phys starting address of the boot memory block + * @size: size of the boot memory block in bytes + * + * Free boot memory block previously allocated by memblock_alloc_xx() API. + * The freeing memory will not be released to the buddy allocator. + */ int __init_memblock memblock_free(phys_addr_t base, phys_addr_t size) { phys_addr_t end = base + size - 1; @@ -1170,7 +1194,7 @@ void __init_memblock __next_mem_range_rev(u64 *idx, int nid, #ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP /* - * Common iterator interface used to define for_each_mem_range(). + * Common iterator interface used to define for_each_mem_pfn_range(). */ void __init_memblock __next_mem_pfn_range(int *idx, int nid, unsigned long *out_start_pfn, @@ -1238,8 +1262,11 @@ static phys_addr_t __init memblock_alloc_range_nid(phys_addr_t size, { phys_addr_t found; - if (!align) + if (!align) { + /* Can't use WARNs this early in boot on powerpc */ + dump_stack(); align = SMP_CACHE_BYTES; + } found = memblock_find_in_range_node(size, align, start, end, nid, flags); @@ -1269,7 +1296,7 @@ phys_addr_t __init memblock_alloc_base_nid(phys_addr_t size, return memblock_alloc_range_nid(size, align, 0, max_addr, nid, flags); } -phys_addr_t __init memblock_alloc_nid(phys_addr_t size, phys_addr_t align, int nid) +phys_addr_t __init memblock_phys_alloc_nid(phys_addr_t size, phys_addr_t align, int nid) { enum memblock_flags flags = choose_memblock_flags(); phys_addr_t ret; @@ -1304,23 +1331,22 @@ phys_addr_t __init memblock_alloc_base(phys_addr_t size, phys_addr_t align, phys return alloc; } -phys_addr_t __init memblock_alloc(phys_addr_t size, phys_addr_t align) +phys_addr_t __init memblock_phys_alloc(phys_addr_t size, phys_addr_t align) { return memblock_alloc_base(size, align, MEMBLOCK_ALLOC_ACCESSIBLE); } -phys_addr_t __init memblock_alloc_try_nid(phys_addr_t size, phys_addr_t align, int nid) +phys_addr_t __init memblock_phys_alloc_try_nid(phys_addr_t size, phys_addr_t align, int nid) { - phys_addr_t res = memblock_alloc_nid(size, align, nid); + phys_addr_t res = memblock_phys_alloc_nid(size, align, nid); if (res) return res; return memblock_alloc_base(size, align, MEMBLOCK_ALLOC_ACCESSIBLE); } -#if defined(CONFIG_NO_BOOTMEM) /** - * memblock_virt_alloc_internal - allocate boot memory block + * memblock_alloc_internal - allocate boot memory block * @size: size of memory block to be allocated in bytes * @align: alignment of the region and block's size * @min_addr: the lower bound of the memory region to allocate (phys address) @@ -1333,9 +1359,7 @@ phys_addr_t __init memblock_alloc_try_nid(phys_addr_t size, phys_addr_t align, i * hold the requested memory. * * The allocation is performed from memory region limited by - * memblock.current_limit if @max_addr == %BOOTMEM_ALLOC_ACCESSIBLE. - * - * The memory block is aligned on %SMP_CACHE_BYTES if @align == 0. + * memblock.current_limit if @max_addr == %MEMBLOCK_ALLOC_ACCESSIBLE. * * The phys address of allocated boot memory block is converted to virtual and * allocated memory is reset to 0. @@ -1346,7 +1370,7 @@ phys_addr_t __init memblock_alloc_try_nid(phys_addr_t size, phys_addr_t align, i * Return: * Virtual address of allocated memory block on success, NULL on failure. */ -static void * __init memblock_virt_alloc_internal( +static void * __init memblock_alloc_internal( phys_addr_t size, phys_addr_t align, phys_addr_t min_addr, phys_addr_t max_addr, int nid) @@ -1361,13 +1385,15 @@ static void * __init memblock_virt_alloc_internal( /* * Detect any accidental use of these APIs after slab is ready, as at * this moment memblock may be deinitialized already and its - * internal data may be destroyed (after execution of free_all_bootmem) + * internal data may be destroyed (after execution of memblock_free_all) */ if (WARN_ON_ONCE(slab_is_available())) return kzalloc_node(size, GFP_NOWAIT, nid); - if (!align) + if (!align) { + dump_stack(); align = SMP_CACHE_BYTES; + } if (max_addr > memblock.current_limit) max_addr = memblock.current_limit; @@ -1401,26 +1427,28 @@ again: done: ptr = phys_to_virt(alloc); - /* - * The min_count is set to 0 so that bootmem allocated blocks - * are never reported as leaks. This is because many of these blocks - * are only referred via the physical address which is not - * looked up by kmemleak. - */ - kmemleak_alloc(ptr, size, 0, 0); + /* Skip kmemleak for kasan_init() due to high volume. */ + if (max_addr != MEMBLOCK_ALLOC_KASAN) + /* + * The min_count is set to 0 so that bootmem allocated + * blocks are never reported as leaks. This is because many + * of these blocks are only referred via the physical + * address which is not looked up by kmemleak. + */ + kmemleak_alloc(ptr, size, 0, 0); return ptr; } /** - * memblock_virt_alloc_try_nid_raw - allocate boot memory block without zeroing + * memblock_alloc_try_nid_raw - allocate boot memory block without zeroing * memory and without panicking * @size: size of memory block to be allocated in bytes * @align: alignment of the region and block's size * @min_addr: the lower bound of the memory region from where the allocation * is preferred (phys address) * @max_addr: the upper bound of the memory region from where the allocation - * is preferred (phys address), or %BOOTMEM_ALLOC_ACCESSIBLE to + * is preferred (phys address), or %MEMBLOCK_ALLOC_ACCESSIBLE to * allocate only from memory limited by memblock.current_limit value * @nid: nid of the free area to find, %NUMA_NO_NODE for any node * @@ -1431,7 +1459,7 @@ done: * Return: * Virtual address of allocated memory block on success, NULL on failure. */ -void * __init memblock_virt_alloc_try_nid_raw( +void * __init memblock_alloc_try_nid_raw( phys_addr_t size, phys_addr_t align, phys_addr_t min_addr, phys_addr_t max_addr, int nid) @@ -1442,23 +1470,22 @@ void * __init memblock_virt_alloc_try_nid_raw( __func__, (u64)size, (u64)align, nid, &min_addr, &max_addr, (void *)_RET_IP_); - ptr = memblock_virt_alloc_internal(size, align, + ptr = memblock_alloc_internal(size, align, min_addr, max_addr, nid); -#ifdef CONFIG_DEBUG_VM if (ptr && size > 0) - memset(ptr, PAGE_POISON_PATTERN, size); -#endif + page_init_poison(ptr, size); + return ptr; } /** - * memblock_virt_alloc_try_nid_nopanic - allocate boot memory block + * memblock_alloc_try_nid_nopanic - allocate boot memory block * @size: size of memory block to be allocated in bytes * @align: alignment of the region and block's size * @min_addr: the lower bound of the memory region from where the allocation * is preferred (phys address) * @max_addr: the upper bound of the memory region from where the allocation - * is preferred (phys address), or %BOOTMEM_ALLOC_ACCESSIBLE to + * is preferred (phys address), or %MEMBLOCK_ALLOC_ACCESSIBLE to * allocate only from memory limited by memblock.current_limit value * @nid: nid of the free area to find, %NUMA_NO_NODE for any node * @@ -1468,7 +1495,7 @@ void * __init memblock_virt_alloc_try_nid_raw( * Return: * Virtual address of allocated memory block on success, NULL on failure. */ -void * __init memblock_virt_alloc_try_nid_nopanic( +void * __init memblock_alloc_try_nid_nopanic( phys_addr_t size, phys_addr_t align, phys_addr_t min_addr, phys_addr_t max_addr, int nid) @@ -1479,7 +1506,7 @@ void * __init memblock_virt_alloc_try_nid_nopanic( __func__, (u64)size, (u64)align, nid, &min_addr, &max_addr, (void *)_RET_IP_); - ptr = memblock_virt_alloc_internal(size, align, + ptr = memblock_alloc_internal(size, align, min_addr, max_addr, nid); if (ptr) memset(ptr, 0, size); @@ -1487,24 +1514,24 @@ void * __init memblock_virt_alloc_try_nid_nopanic( } /** - * memblock_virt_alloc_try_nid - allocate boot memory block with panicking + * memblock_alloc_try_nid - allocate boot memory block with panicking * @size: size of memory block to be allocated in bytes * @align: alignment of the region and block's size * @min_addr: the lower bound of the memory region from where the allocation * is preferred (phys address) * @max_addr: the upper bound of the memory region from where the allocation - * is preferred (phys address), or %BOOTMEM_ALLOC_ACCESSIBLE to + * is preferred (phys address), or %MEMBLOCK_ALLOC_ACCESSIBLE to * allocate only from memory limited by memblock.current_limit value * @nid: nid of the free area to find, %NUMA_NO_NODE for any node * - * Public panicking version of memblock_virt_alloc_try_nid_nopanic() + * Public panicking version of memblock_alloc_try_nid_nopanic() * which provides debug information (including caller info), if enabled, * and panics if the request can not be satisfied. * * Return: * Virtual address of allocated memory block on success, NULL on failure. */ -void * __init memblock_virt_alloc_try_nid( +void * __init memblock_alloc_try_nid( phys_addr_t size, phys_addr_t align, phys_addr_t min_addr, phys_addr_t max_addr, int nid) @@ -1514,7 +1541,7 @@ void * __init memblock_virt_alloc_try_nid( memblock_dbg("%s: %llu bytes align=0x%llx nid=%d from=%pa max_addr=%pa %pF\n", __func__, (u64)size, (u64)align, nid, &min_addr, &max_addr, (void *)_RET_IP_); - ptr = memblock_virt_alloc_internal(size, align, + ptr = memblock_alloc_internal(size, align, min_addr, max_addr, nid); if (ptr) { memset(ptr, 0, size); @@ -1525,25 +1552,6 @@ void * __init memblock_virt_alloc_try_nid( __func__, (u64)size, (u64)align, nid, &min_addr, &max_addr); return NULL; } -#endif - -/** - * __memblock_free_early - free boot memory block - * @base: phys starting address of the boot memory block - * @size: size of the boot memory block in bytes - * - * Free boot memory block previously allocated by memblock_virt_alloc_xx() API. - * The freeing memory will not be released to the buddy allocator. - */ -void __init __memblock_free_early(phys_addr_t base, phys_addr_t size) -{ - phys_addr_t end = base + size - 1; - - memblock_dbg("%s: [%pa-%pa] %pF\n", - __func__, &base, &end, (void *)_RET_IP_); - kmemleak_free_part_phys(base, size); - memblock_remove_range(&memblock.reserved, base, size); -} /** * __memblock_free_late - free bootmem block pages directly to buddy allocator @@ -1566,8 +1574,8 @@ void __init __memblock_free_late(phys_addr_t base, phys_addr_t size) end = PFN_DOWN(base + size); for (; cursor < end; cursor++) { - __free_pages_bootmem(pfn_to_page(cursor), cursor, 0); - totalram_pages++; + memblock_free_pages(pfn_to_page(cursor), cursor, 0); + totalram_pages_inc(); } } @@ -1718,7 +1726,7 @@ static int __init_memblock memblock_search(struct memblock_type *type, phys_addr return -1; } -bool __init memblock_is_reserved(phys_addr_t addr) +bool __init_memblock memblock_is_reserved(phys_addr_t addr) { return memblock_search(&memblock.reserved, addr) != -1; } @@ -1880,6 +1888,100 @@ static int __init early_memblock(char *p) } early_param("memblock", early_memblock); +static void __init __free_pages_memory(unsigned long start, unsigned long end) +{ + int order; + + while (start < end) { + order = min(MAX_ORDER - 1UL, __ffs(start)); + + while (start + (1UL << order) > end) + order--; + + memblock_free_pages(pfn_to_page(start), start, order); + + start += (1UL << order); + } +} + +static unsigned long __init __free_memory_core(phys_addr_t start, + phys_addr_t end) +{ + unsigned long start_pfn = PFN_UP(start); + unsigned long end_pfn = min_t(unsigned long, + PFN_DOWN(end), max_low_pfn); + + if (start_pfn >= end_pfn) + return 0; + + __free_pages_memory(start_pfn, end_pfn); + + return end_pfn - start_pfn; +} + +static unsigned long __init free_low_memory_core_early(void) +{ + unsigned long count = 0; + phys_addr_t start, end; + u64 i; + + memblock_clear_hotplug(0, -1); + + for_each_reserved_mem_region(i, &start, &end) + reserve_bootmem_region(start, end); + + /* + * We need to use NUMA_NO_NODE instead of NODE_DATA(0)->node_id + * because in some case like Node0 doesn't have RAM installed + * low ram will be on Node1 + */ + for_each_free_mem_range(i, NUMA_NO_NODE, MEMBLOCK_NONE, &start, &end, + NULL) + count += __free_memory_core(start, end); + + return count; +} + +static int reset_managed_pages_done __initdata; + +void reset_node_managed_pages(pg_data_t *pgdat) +{ + struct zone *z; + + for (z = pgdat->node_zones; z < pgdat->node_zones + MAX_NR_ZONES; z++) + atomic_long_set(&z->managed_pages, 0); +} + +void __init reset_all_zones_managed_pages(void) +{ + struct pglist_data *pgdat; + + if (reset_managed_pages_done) + return; + + for_each_online_pgdat(pgdat) + reset_node_managed_pages(pgdat); + + reset_managed_pages_done = 1; +} + +/** + * memblock_free_all - release free pages to the buddy allocator + * + * Return: the number of pages actually released. + */ +unsigned long __init memblock_free_all(void) +{ + unsigned long pages; + + reset_all_zones_managed_pages(); + + pages = free_low_memory_core_early(); + totalram_pages_add(pages); + + return pages; +} + #if defined(CONFIG_DEBUG_FS) && !defined(CONFIG_ARCH_DISCARD_MEMBLOCK) static int memblock_debug_show(struct seq_file *m, void *private) @@ -1903,8 +2005,7 @@ DEFINE_SHOW_ATTRIBUTE(memblock_debug); static int __init memblock_init_debugfs(void) { struct dentry *root = debugfs_create_dir("memblock", NULL); - if (!root) - return -ENXIO; + debugfs_create_file("memory", 0444, root, &memblock.memory, &memblock_debug_fops); debugfs_create_file("reserved", 0444, root, |