diff options
Diffstat (limited to '')
| -rw-r--r-- | mm/memblock.c | 495 |
1 files changed, 298 insertions, 197 deletions
diff --git a/mm/memblock.c b/mm/memblock.c index eba94ee3de0b..511d4783dcf1 100644 --- a/mm/memblock.c +++ b/mm/memblock.c @@ -29,6 +29,10 @@ # define INIT_MEMBLOCK_RESERVED_REGIONS INIT_MEMBLOCK_REGIONS #endif +#ifndef INIT_MEMBLOCK_MEMORY_REGIONS +#define INIT_MEMBLOCK_MEMORY_REGIONS INIT_MEMBLOCK_REGIONS +#endif + /** * DOC: memblock overview * @@ -44,19 +48,20 @@ * in the system, for instance when the memory is restricted with * ``mem=`` command line parameter * * ``reserved`` - describes the regions that were allocated - * * ``physmap`` - describes the actual physical memory regardless of - * the possible restrictions; the ``physmap`` type is only available - * on some architectures. + * * ``physmem`` - describes the actual physical memory available during + * boot regardless of the possible restrictions and memory hot(un)plug; + * the ``physmem`` type is only available on some architectures. * - * Each region is represented by :c:type:`struct memblock_region` that + * Each region is represented by struct memblock_region that * defines the region extents, its attributes and NUMA node id on NUMA - * systems. Every memory type is described by the :c:type:`struct - * memblock_type` which contains an array of memory regions along with - * the allocator metadata. The memory types are nicely wrapped with - * :c:type:`struct memblock`. This structure is statically initialzed - * at build time. The region arrays for the "memory" and "reserved" - * types are initially sized to %INIT_MEMBLOCK_REGIONS and for the - * "physmap" type to %INIT_PHYSMEM_REGIONS. + * systems. Every memory type is described by the struct memblock_type + * which contains an array of memory regions along with + * the allocator metadata. The "memory" and "reserved" types are nicely + * wrapped with struct memblock. This structure is statically + * initialized at build time. The region arrays are initially sized to + * %INIT_MEMBLOCK_MEMORY_REGIONS for "memory" and + * %INIT_MEMBLOCK_RESERVED_REGIONS for "reserved". The region array + * for "physmem" is initially sized to %INIT_PHYSMEM_REGIONS. * The memblock_allow_resize() enables automatic resizing of the region * arrays during addition of new regions. This feature should be used * with care so that memory allocated for the region array will not @@ -78,7 +83,7 @@ * * memblock_alloc*() - these functions return the **virtual** address * of the allocated memory. * - * Note, that both API variants use implict assumptions about allowed + * Note, that both API variants use implicit assumptions about allowed * memory ranges and the fallback methods. Consult the documentation * of memblock_alloc_internal() and memblock_alloc_range_nid() * functions for more elaborate description. @@ -87,11 +92,11 @@ * function frees all the memory to the buddy page allocator. * * Unless an architecture enables %CONFIG_ARCH_KEEP_MEMBLOCK, the - * memblock data structures will be discarded after the system - * initialization completes. + * memblock data structures (except "physmem") will be discarded after the + * system initialization completes. */ -#ifndef CONFIG_NEED_MULTIPLE_NODES +#ifndef CONFIG_NUMA struct pglist_data __refdata contig_page_data; EXPORT_SYMBOL(contig_page_data); #endif @@ -101,16 +106,16 @@ 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_memory_init_regions[INIT_MEMBLOCK_MEMORY_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; +static struct memblock_region memblock_physmem_init_regions[INIT_PHYSMEM_REGIONS]; #endif struct memblock memblock __initdata_memblock = { .memory.regions = memblock_memory_init_regions, .memory.cnt = 1, /* empty dummy entry */ - .memory.max = INIT_MEMBLOCK_REGIONS, + .memory.max = INIT_MEMBLOCK_MEMORY_REGIONS, .memory.name = "memory", .reserved.regions = memblock_reserved_init_regions, @@ -118,18 +123,39 @@ struct memblock memblock __initdata_memblock = { .reserved.max = INIT_MEMBLOCK_RESERVED_REGIONS, .reserved.name = "reserved", -#ifdef CONFIG_HAVE_MEMBLOCK_PHYS_MAP - .physmem.regions = memblock_physmem_init_regions, - .physmem.cnt = 1, /* empty dummy entry */ - .physmem.max = INIT_PHYSMEM_REGIONS, - .physmem.name = "physmem", -#endif - .bottom_up = false, .current_limit = MEMBLOCK_ALLOC_ANYWHERE, }; -int memblock_debug __initdata_memblock; +#ifdef CONFIG_HAVE_MEMBLOCK_PHYS_MAP +struct memblock_type physmem = { + .regions = memblock_physmem_init_regions, + .cnt = 1, /* empty dummy entry */ + .max = INIT_PHYSMEM_REGIONS, + .name = "physmem", +}; +#endif + +/* + * keep a pointer to &memblock.memory in the text section to use it in + * __next_mem_range() and its helpers. + * For architectures that do not keep memblock data after init, this + * pointer will be reset to NULL at memblock_discard() + */ +static __refdata struct memblock_type *memblock_memory = &memblock.memory; + +#define for_each_memblock_type(i, memblock_type, rgn) \ + for (i = 0, rgn = &memblock_type->regions[0]; \ + i < memblock_type->cnt; \ + i++, rgn = &memblock_type->regions[i]) + +#define memblock_dbg(fmt, ...) \ + do { \ + if (memblock_debug) \ + pr_info(fmt, ##__VA_ARGS__); \ + } while (0) + +static int memblock_debug __initdata_memblock; static bool system_has_some_mirror __initdata_memblock = false; static int memblock_can_resize __initdata_memblock; static int memblock_memory_in_slab __initdata_memblock = 0; @@ -160,6 +186,8 @@ bool __init_memblock memblock_overlaps_region(struct memblock_type *type, { unsigned long i; + memblock_cap_size(base, &size); + for (i = 0; i < type->cnt; i++) if (memblock_addrs_overlap(base, size, type->regions[i].base, type->regions[i].size)) @@ -253,14 +281,6 @@ __memblock_find_range_top_down(phys_addr_t start, phys_addr_t end, * * Find @size free area aligned to @align in the specified range and node. * - * When allocation direction is bottom-up, the @start should be greater - * than the end of the kernel image. Otherwise, it will be trimmed. The - * reason is that we want the bottom-up allocation just near the kernel - * image so it is highly likely that the allocated memory and the kernel - * will reside in the same node. - * - * If bottom-up allocation failed, will try to allocate memory top-down. - * * Return: * Found address on success, 0 on failure. */ @@ -269,50 +289,21 @@ static phys_addr_t __init_memblock memblock_find_in_range_node(phys_addr_t size, phys_addr_t end, int nid, enum memblock_flags flags) { - phys_addr_t kernel_end, ret; - /* pump up @end */ if (end == MEMBLOCK_ALLOC_ACCESSIBLE || - end == MEMBLOCK_ALLOC_KASAN) + end == MEMBLOCK_ALLOC_NOLEAKTRACE) end = memblock.current_limit; /* avoid allocating the first page */ start = max_t(phys_addr_t, start, PAGE_SIZE); end = max(start, end); - kernel_end = __pa_symbol(_end); - /* - * try bottom-up allocation only when bottom-up mode - * is set and @end is above the kernel image. - */ - if (memblock_bottom_up() && end > kernel_end) { - phys_addr_t bottom_up_start; - - /* make sure we will allocate above the kernel */ - bottom_up_start = max(start, kernel_end); - - /* ok, try bottom-up allocation first */ - ret = __memblock_find_range_bottom_up(bottom_up_start, end, - size, align, nid, flags); - if (ret) - return ret; - - /* - * we always limit bottom-up allocation above the kernel, - * but top-down allocation doesn't have the limit, so - * retrying top-down allocation may succeed when bottom-up - * allocation failed. - * - * bottom-up allocation is expected to be fail very rarely, - * so we use WARN_ONCE() here to see the stack trace if - * fail happens. - */ - WARN_ONCE(IS_ENABLED(CONFIG_MEMORY_HOTREMOVE), - "memblock: bottom-up allocation failed, memory hotremove may be affected\n"); - } - - return __memblock_find_range_top_down(start, end, size, align, nid, - flags); + if (memblock_bottom_up()) + return __memblock_find_range_bottom_up(start, end, size, align, + nid, flags); + else + return __memblock_find_range_top_down(start, end, size, align, + nid, flags); } /** @@ -328,7 +319,7 @@ static phys_addr_t __init_memblock memblock_find_in_range_node(phys_addr_t size, * Return: * Found address on success, 0 on failure. */ -phys_addr_t __init_memblock memblock_find_in_range(phys_addr_t start, +static phys_addr_t __init_memblock memblock_find_in_range(phys_addr_t start, phys_addr_t end, phys_addr_t size, phys_addr_t align) { @@ -340,7 +331,7 @@ again: NUMA_NO_NODE, flags); if (!ret && (flags & MEMBLOCK_MIRROR)) { - pr_warn("Could not allocate %pap bytes of mirrored memory\n", + pr_warn_ratelimited("Could not allocate %pap bytes of mirrored memory\n", &size); flags &= ~MEMBLOCK_MIRROR; goto again; @@ -379,15 +370,23 @@ void __init memblock_discard(void) addr = __pa(memblock.reserved.regions); size = PAGE_ALIGN(sizeof(struct memblock_region) * memblock.reserved.max); - __memblock_free_late(addr, size); + if (memblock_reserved_in_slab) + kfree(memblock.reserved.regions); + else + memblock_free_late(addr, size); } if (memblock.memory.regions != memblock_memory_init_regions) { addr = __pa(memblock.memory.regions); size = PAGE_ALIGN(sizeof(struct memblock_region) * memblock.memory.max); - __memblock_free_late(addr, size); + if (memblock_memory_in_slab) + kfree(memblock.memory.regions); + else + memblock_free_late(addr, size); } + + memblock_memory = NULL; } #endif @@ -483,7 +482,7 @@ static int __init_memblock memblock_double_array(struct memblock_type *type, kfree(old_array); else if (old_array != memblock_memory_init_regions && old_array != memblock_reserved_init_regions) - memblock_free(__pa(old_array), old_alloc_size); + memblock_free(old_array, old_alloc_size); /* * Reserve the new array if that comes from the memblock. Otherwise, we @@ -598,6 +597,17 @@ static int __init_memblock memblock_add_range(struct memblock_type *type, type->total_size = size; return 0; } + + /* + * The worst case is when new range overlaps all existing regions, + * then we'll need type->cnt + 1 empty regions in @type. So if + * type->cnt * 2 + 1 is less than type->max, we know + * that there is enough empty regions in @type, and we can insert + * regions directly. + */ + if (type->cnt * 2 + 1 < type->max) + insert = true; + repeat: /* * The following is executed twice. Once with %false @insert and @@ -620,7 +630,7 @@ repeat: * area, insert that portion. */ if (rbase > base) { -#ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP +#ifdef CONFIG_NUMA WARN_ON(nid != memblock_get_region_node(rgn)); #endif WARN_ON(flags != rgn->flags); @@ -666,6 +676,7 @@ repeat: * @base: base address of the new region * @size: size of the new region * @nid: nid of the new region + * @flags: flags of the new region * * Add new memblock region [@base, @base + @size) to the "memory" * type. See memblock_add_range() description for mode details @@ -674,9 +685,14 @@ repeat: * 0 on success, -errno on failure. */ int __init_memblock memblock_add_node(phys_addr_t base, phys_addr_t size, - int nid) + int nid, enum memblock_flags flags) { - return memblock_add_range(&memblock.memory, base, size, nid, 0); + phys_addr_t end = base + size - 1; + + memblock_dbg("%s: [%pa-%pa] nid=%d flags=%x %pS\n", __func__, + &base, &end, nid, flags, (void *)_RET_IP_); + + return memblock_add_range(&memblock.memory, base, size, nid, flags); } /** @@ -802,14 +818,28 @@ int __init_memblock memblock_remove(phys_addr_t base, phys_addr_t size) } /** - * memblock_free - free boot memory block + * memblock_free - free boot memory allocation + * @ptr: starting address of the boot memory allocation + * @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. + */ +void __init_memblock memblock_free(void *ptr, size_t size) +{ + if (ptr) + memblock_phys_free(__pa(ptr), size); +} + +/** + * memblock_phys_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) +int __init_memblock memblock_phys_free(phys_addr_t base, phys_addr_t size) { phys_addr_t end = base + size - 1; @@ -838,7 +868,7 @@ int __init_memblock memblock_physmem_add(phys_addr_t base, phys_addr_t size) memblock_dbg("%s: [%pa-%pa] %pS\n", __func__, &base, &end, (void *)_RET_IP_); - return memblock_add_range(&memblock.physmem, base, size, MAX_NUMNODES, 0); + return memblock_add_range(&physmem, base, size, MAX_NUMNODES, 0); } #endif @@ -847,7 +877,7 @@ int __init_memblock memblock_physmem_add(phys_addr_t base, phys_addr_t size) * @base: base address of the region * @size: size of the region * @set: set or clear the flag - * @flag: the flag to udpate + * @flag: the flag to update * * This function isolates region [@base, @base + @size), and sets/clears flag * @@ -909,6 +939,9 @@ int __init_memblock memblock_clear_hotplug(phys_addr_t base, phys_addr_t size) */ int __init_memblock memblock_mark_mirror(phys_addr_t base, phys_addr_t size) { + if (!mirrored_kernelcore) + return 0; + system_has_some_mirror = true; return memblock_setclr_flag(base, size, 1, MEMBLOCK_MIRROR); @@ -919,6 +952,14 @@ int __init_memblock memblock_mark_mirror(phys_addr_t base, phys_addr_t size) * @base: the base phys addr of the region * @size: the size of the region * + * The memory regions marked with %MEMBLOCK_NOMAP will not be added to the + * direct mapping of the physical memory. These regions will still be + * covered by the memory map. The struct page representing NOMAP memory + * frames in the memory map will be PageReserved() + * + * Note: if the memory being marked %MEMBLOCK_NOMAP was allocated from + * memblock, the caller must inform kmemleak to ignore that memory + * * Return: 0 on success, -errno on failure. */ int __init_memblock memblock_mark_nomap(phys_addr_t base, phys_addr_t size) @@ -938,48 +979,23 @@ int __init_memblock memblock_clear_nomap(phys_addr_t base, phys_addr_t size) return memblock_setclr_flag(base, size, 0, MEMBLOCK_NOMAP); } -/** - * __next_reserved_mem_region - next function for for_each_reserved_region() - * @idx: pointer to u64 loop variable - * @out_start: ptr to phys_addr_t for start address of the region, can be %NULL - * @out_end: ptr to phys_addr_t for end address of the region, can be %NULL - * - * Iterate over all reserved memory regions. - */ -void __init_memblock __next_reserved_mem_region(u64 *idx, - phys_addr_t *out_start, - phys_addr_t *out_end) -{ - struct memblock_type *type = &memblock.reserved; - - if (*idx < type->cnt) { - struct memblock_region *r = &type->regions[*idx]; - phys_addr_t base = r->base; - phys_addr_t size = r->size; - - if (out_start) - *out_start = base; - if (out_end) - *out_end = base + size - 1; - - *idx += 1; - return; - } - - /* signal end of iteration */ - *idx = ULLONG_MAX; -} - -static bool should_skip_region(struct memblock_region *m, int nid, int flags) +static bool should_skip_region(struct memblock_type *type, + struct memblock_region *m, + int nid, int flags) { int m_nid = memblock_get_region_node(m); + /* we never skip regions when iterating memblock.reserved or physmem */ + if (type != memblock_memory) + return false; + /* only memory regions are associated with nodes, check it */ if (nid != NUMA_NO_NODE && nid != m_nid) return true; /* skip hotpluggable memory regions if needed */ - if (movable_node_is_enabled() && memblock_is_hotpluggable(m)) + if (movable_node_is_enabled() && memblock_is_hotpluggable(m) && + !(flags & MEMBLOCK_HOTPLUG)) return true; /* if we want mirror memory skip non-mirror memory regions */ @@ -990,6 +1006,10 @@ static bool should_skip_region(struct memblock_region *m, int nid, int flags) if (!(flags & MEMBLOCK_NOMAP) && memblock_is_nomap(m)) return true; + /* skip driver-managed memory unless we were asked for it explicitly */ + if (!(flags & MEMBLOCK_DRIVER_MANAGED) && memblock_is_driver_managed(m)) + return true; + return false; } @@ -1019,12 +1039,10 @@ static bool should_skip_region(struct memblock_region *m, int nid, int flags) * As both region arrays are sorted, the function advances the two indices * in lockstep and returns each intersection. */ -void __init_memblock __next_mem_range(u64 *idx, int nid, - enum memblock_flags flags, - struct memblock_type *type_a, - struct memblock_type *type_b, - phys_addr_t *out_start, - phys_addr_t *out_end, int *out_nid) +void __next_mem_range(u64 *idx, int nid, enum memblock_flags flags, + struct memblock_type *type_a, + struct memblock_type *type_b, phys_addr_t *out_start, + phys_addr_t *out_end, int *out_nid) { int idx_a = *idx & 0xffffffff; int idx_b = *idx >> 32; @@ -1040,7 +1058,7 @@ void __init_memblock __next_mem_range(u64 *idx, int nid, phys_addr_t m_end = m->base + m->size; int m_nid = memblock_get_region_node(m); - if (should_skip_region(m, nid, flags)) + if (should_skip_region(type_a, m, nid, flags)) continue; if (!type_b) { @@ -1144,7 +1162,7 @@ void __init_memblock __next_mem_range_rev(u64 *idx, int nid, phys_addr_t m_end = m->base + m->size; int m_nid = memblock_get_region_node(m); - if (should_skip_region(m, nid, flags)) + if (should_skip_region(type_a, m, nid, flags)) continue; if (!type_b) { @@ -1197,7 +1215,6 @@ void __init_memblock __next_mem_range_rev(u64 *idx, int nid, *idx = ULLONG_MAX; } -#ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP /* * Common iterator interface used to define for_each_mem_pfn_range(). */ @@ -1207,13 +1224,15 @@ void __init_memblock __next_mem_pfn_range(int *idx, int nid, { struct memblock_type *type = &memblock.memory; struct memblock_region *r; + int r_nid; while (++*idx < type->cnt) { r = &type->regions[*idx]; + r_nid = memblock_get_region_node(r); if (PFN_UP(r->base) >= PFN_DOWN(r->base + r->size)) continue; - if (nid == MAX_NUMNODES || nid == r->nid) + if (nid == MAX_NUMNODES || nid == r_nid) break; } if (*idx >= type->cnt) { @@ -1226,7 +1245,7 @@ void __init_memblock __next_mem_pfn_range(int *idx, int nid, if (out_end_pfn) *out_end_pfn = PFN_DOWN(r->base + r->size); if (out_nid) - *out_nid = r->nid; + *out_nid = r_nid; } /** @@ -1245,6 +1264,7 @@ void __init_memblock __next_mem_pfn_range(int *idx, int nid, int __init_memblock memblock_set_node(phys_addr_t base, phys_addr_t size, struct memblock_type *type, int nid) { +#ifdef CONFIG_NUMA int start_rgn, end_rgn; int i, ret; @@ -1256,9 +1276,10 @@ int __init_memblock memblock_set_node(phys_addr_t base, phys_addr_t size, memblock_set_region_node(&type->regions[i], nid); memblock_merge_regions(type); +#endif return 0; } -#endif /* CONFIG_HAVE_MEMBLOCK_NODE_MAP */ + #ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT /** * __next_mem_pfn_range_in_zone - iterator for for_each_*_range_in_zone() @@ -1281,11 +1302,10 @@ __next_mem_pfn_range_in_zone(u64 *idx, struct zone *zone, { int zone_nid = zone_to_nid(zone); phys_addr_t spa, epa; - int nid; __next_mem_range(idx, zone_nid, MEMBLOCK_NONE, &memblock.memory, &memblock.reserved, - &spa, &epa, &nid); + &spa, &epa, NULL); while (*idx != U64_MAX) { unsigned long epfn = PFN_DOWN(epa); @@ -1312,7 +1332,7 @@ __next_mem_pfn_range_in_zone(u64 *idx, struct zone *zone, __next_mem_range(idx, zone_nid, MEMBLOCK_NONE, &memblock.memory, &memblock.reserved, - &spa, &epa, &nid); + &spa, &epa, NULL); } /* signal end of iteration */ @@ -1343,13 +1363,13 @@ __next_mem_pfn_range_in_zone(u64 *idx, struct zone *zone, * from the regions with mirroring enabled and then retried from any * memory region. * - * In addition, function sets the min_count to 0 using kmemleak_alloc_phys for - * allocated boot memory block, so that it is never reported as leaks. + * In addition, function using kmemleak_alloc_phys for allocated boot + * memory block, it is never reported as leaks. * * Return: * Physical address of allocated memory block on success, %0 on failure. */ -static phys_addr_t __init memblock_alloc_range_nid(phys_addr_t size, +phys_addr_t __init memblock_alloc_range_nid(phys_addr_t size, phys_addr_t align, phys_addr_t start, phys_addr_t end, int nid, bool exact_nid) @@ -1382,7 +1402,7 @@ again: if (flags & MEMBLOCK_MIRROR) { flags &= ~MEMBLOCK_MIRROR; - pr_warn("Could not allocate %pap bytes of mirrored memory\n", + pr_warn_ratelimited("Could not allocate %pap bytes of mirrored memory\n", &size); goto again; } @@ -1390,15 +1410,18 @@ again: return 0; done: - /* Skip kmemleak for kasan_init() due to high volume. */ - if (end != MEMBLOCK_ALLOC_KASAN) + /* + * Skip kmemleak for those places like kasan_init() and + * early_pgtable_alloc() due to high volume. + */ + if (end != MEMBLOCK_ALLOC_NOLEAKTRACE) /* - * The min_count is set to 0 so that memblock 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. + * Memblock 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_phys(found, size, 0, 0); + kmemleak_alloc_phys(found, size, 0); return found; } @@ -1420,12 +1443,15 @@ phys_addr_t __init memblock_phys_alloc_range(phys_addr_t size, phys_addr_t start, phys_addr_t end) { + memblock_dbg("%s: %llu bytes align=0x%llx from=%pa max_addr=%pa %pS\n", + __func__, (u64)size, (u64)align, &start, &end, + (void *)_RET_IP_); return memblock_alloc_range_nid(size, align, start, end, NUMA_NO_NODE, false); } /** - * memblock_phys_alloc_try_nid - allocate a memory block from specified MUMA node + * memblock_phys_alloc_try_nid - allocate a memory block from specified NUMA node * @size: size of memory block to be allocated in bytes * @align: alignment of the region and block's size * @nid: nid of the free area to find, %NUMA_NO_NODE for any node @@ -1518,18 +1544,12 @@ void * __init memblock_alloc_exact_nid_raw( phys_addr_t min_addr, phys_addr_t max_addr, int nid) { - void *ptr; - memblock_dbg("%s: %llu bytes align=0x%llx nid=%d from=%pa max_addr=%pa %pS\n", __func__, (u64)size, (u64)align, nid, &min_addr, &max_addr, (void *)_RET_IP_); - ptr = memblock_alloc_internal(size, align, - min_addr, max_addr, nid, true); - if (ptr && size > 0) - page_init_poison(ptr, size); - - return ptr; + return memblock_alloc_internal(size, align, min_addr, max_addr, nid, + true); } /** @@ -1556,18 +1576,12 @@ void * __init memblock_alloc_try_nid_raw( phys_addr_t min_addr, phys_addr_t max_addr, int nid) { - void *ptr; - memblock_dbg("%s: %llu bytes align=0x%llx nid=%d from=%pa max_addr=%pa %pS\n", __func__, (u64)size, (u64)align, nid, &min_addr, &max_addr, (void *)_RET_IP_); - ptr = memblock_alloc_internal(size, align, - min_addr, max_addr, nid, false); - if (ptr && size > 0) - page_init_poison(ptr, size); - - return ptr; + return memblock_alloc_internal(size, align, min_addr, max_addr, nid, + false); } /** @@ -1606,7 +1620,7 @@ void * __init memblock_alloc_try_nid( } /** - * __memblock_free_late - free pages directly to buddy allocator + * memblock_free_late - free pages directly to buddy allocator * @base: phys starting address of the boot memory block * @size: size of the boot memory block in bytes * @@ -1614,7 +1628,7 @@ void * __init memblock_alloc_try_nid( * down, but we are still initializing the system. Pages are released directly * to the buddy allocator. */ -void __init __memblock_free_late(phys_addr_t base, phys_addr_t size) +void __init memblock_free_late(phys_addr_t base, phys_addr_t size) { phys_addr_t cursor, end; @@ -1645,23 +1659,6 @@ phys_addr_t __init_memblock memblock_reserved_size(void) return memblock.reserved.total_size; } -phys_addr_t __init memblock_mem_size(unsigned long limit_pfn) -{ - unsigned long pages = 0; - struct memblock_region *r; - unsigned long start_pfn, end_pfn; - - for_each_memblock(memory, r) { - start_pfn = memblock_region_memory_base_pfn(r); - end_pfn = memblock_region_memory_end_pfn(r); - start_pfn = min_t(unsigned long, start_pfn, limit_pfn); - end_pfn = min_t(unsigned long, end_pfn, limit_pfn); - pages += end_pfn - start_pfn; - } - - return PFN_PHYS(pages); -} - /* lowest address */ phys_addr_t __init_memblock memblock_start_of_DRAM(void) { @@ -1685,7 +1682,7 @@ static phys_addr_t __init_memblock __find_max_addr(phys_addr_t limit) * the memory memblock regions, if the @limit exceeds the total size * of those regions, max_addr will keep original value PHYS_ADDR_MAX */ - for_each_memblock(memory, r) { + for_each_mem_region(r) { if (limit <= r->size) { max_addr = r->base + limit; break; @@ -1698,7 +1695,7 @@ static phys_addr_t __init_memblock __find_max_addr(phys_addr_t limit) void __init memblock_enforce_memory_limit(phys_addr_t limit) { - phys_addr_t max_addr = PHYS_ADDR_MAX; + phys_addr_t max_addr; if (!limit) return; @@ -1724,6 +1721,11 @@ void __init memblock_cap_memory_range(phys_addr_t base, phys_addr_t size) if (!size) return; + if (!memblock_memory->total_size) { + pr_warn("%s: No memory registered yet\n", __func__); + return; + } + ret = memblock_isolate_range(&memblock.memory, base, size, &start_rgn, &end_rgn); if (ret) @@ -1797,7 +1799,6 @@ bool __init_memblock memblock_is_map_memory(phys_addr_t addr) return !memblock_is_nomap(&memblock.memory.regions[i]); } -#ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP int __init_memblock memblock_search_pfn_nid(unsigned long pfn, unsigned long *start_pfn, unsigned long *end_pfn) { @@ -1810,9 +1811,8 @@ int __init_memblock memblock_search_pfn_nid(unsigned long pfn, *start_pfn = PFN_DOWN(type->regions[mid].base); *end_pfn = PFN_DOWN(type->regions[mid].base + type->regions[mid].size); - return type->regions[mid].nid; + return memblock_get_region_node(&type->regions[mid]); } -#endif /** * memblock_is_region_memory - check if a region is a subset of memory @@ -1848,7 +1848,6 @@ bool __init_memblock memblock_is_region_memory(phys_addr_t base, phys_addr_t siz */ bool __init_memblock memblock_is_region_reserved(phys_addr_t base, phys_addr_t size) { - memblock_cap_size(base, &size); return memblock_overlaps_region(&memblock.reserved, base, size); } @@ -1857,7 +1856,7 @@ void __init_memblock memblock_trim_memory(phys_addr_t align) phys_addr_t start, end, orig_start, orig_end; struct memblock_region *r; - for_each_memblock(memory, r) { + for_each_mem_region(r) { orig_start = r->base; orig_end = r->base + r->size; start = round_up(orig_start, align); @@ -1903,7 +1902,7 @@ static void __init_memblock memblock_dump(struct memblock_type *type) size = rgn->size; end = base + size - 1; flags = rgn->flags; -#ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP +#ifdef CONFIG_NUMA if (memblock_get_region_node(rgn) != MAX_NUMNODES) snprintf(nid_buf, sizeof(nid_buf), " on node %d", memblock_get_region_node(rgn)); @@ -1913,7 +1912,7 @@ static void __init_memblock memblock_dump(struct memblock_type *type) } } -void __init_memblock __memblock_dump_all(void) +static void __init_memblock __memblock_dump_all(void) { pr_info("MEMBLOCK configuration:\n"); pr_info(" memory size = %pa reserved size = %pa\n", @@ -1923,10 +1922,16 @@ void __init_memblock __memblock_dump_all(void) memblock_dump(&memblock.memory); memblock_dump(&memblock.reserved); #ifdef CONFIG_HAVE_MEMBLOCK_PHYS_MAP - memblock_dump(&memblock.physmem); + memblock_dump(&physmem); #endif } +void __init_memblock memblock_dump_all(void) +{ + if (memblock_debug) + __memblock_dump_all(); +} + void __init memblock_allow_resize(void) { memblock_can_resize = 1; @@ -1940,6 +1945,86 @@ static int __init early_memblock(char *p) } early_param("memblock", early_memblock); +static void __init free_memmap(unsigned long start_pfn, unsigned long end_pfn) +{ + struct page *start_pg, *end_pg; + phys_addr_t pg, pgend; + + /* + * Convert start_pfn/end_pfn to a struct page pointer. + */ + start_pg = pfn_to_page(start_pfn - 1) + 1; + end_pg = pfn_to_page(end_pfn - 1) + 1; + + /* + * Convert to physical addresses, and round start upwards and end + * downwards. + */ + pg = PAGE_ALIGN(__pa(start_pg)); + pgend = __pa(end_pg) & PAGE_MASK; + + /* + * If there are free pages between these, free the section of the + * memmap array. + */ + if (pg < pgend) + memblock_phys_free(pg, pgend - pg); +} + +/* + * The mem_map array can get very big. Free the unused area of the memory map. + */ +static void __init free_unused_memmap(void) +{ + unsigned long start, end, prev_end = 0; + int i; + + if (!IS_ENABLED(CONFIG_HAVE_ARCH_PFN_VALID) || + IS_ENABLED(CONFIG_SPARSEMEM_VMEMMAP)) + return; + + /* + * This relies on each bank being in address order. + * The banks are sorted previously in bootmem_init(). + */ + for_each_mem_pfn_range(i, MAX_NUMNODES, &start, &end, NULL) { +#ifdef CONFIG_SPARSEMEM + /* + * Take care not to free memmap entries that don't exist + * due to SPARSEMEM sections which aren't present. + */ + start = min(start, ALIGN(prev_end, PAGES_PER_SECTION)); +#endif + /* + * Align down here since many operations in VM subsystem + * presume that there are no holes in the memory map inside + * a pageblock + */ + start = pageblock_start_pfn(start); + + /* + * If we had a previous bank, and there is a space + * between the current bank and the previous, free it. + */ + if (prev_end && prev_end < start) + free_memmap(prev_end, start); + + /* + * Align up here since many operations in VM subsystem + * presume that there are no holes in the memory map inside + * a pageblock + */ + prev_end = pageblock_align(end); + } + +#ifdef CONFIG_SPARSEMEM + if (!IS_ALIGNED(prev_end, PAGES_PER_SECTION)) { + prev_end = pageblock_align(end); + free_memmap(prev_end, ALIGN(prev_end, PAGES_PER_SECTION)); + } +#endif +} + static void __init __free_pages_memory(unsigned long start, unsigned long end) { int order; @@ -1971,6 +2056,26 @@ static unsigned long __init __free_memory_core(phys_addr_t start, return end_pfn - start_pfn; } +static void __init memmap_init_reserved_pages(void) +{ + struct memblock_region *region; + phys_addr_t start, end; + u64 i; + + /* initialize struct pages for the reserved regions */ + for_each_reserved_mem_range(i, &start, &end) + reserve_bootmem_region(start, end); + + /* and also treat struct pages for the NOMAP regions as PageReserved */ + for_each_mem_region(region) { + if (memblock_is_nomap(region)) { + start = region->base; + end = start + region->size; + reserve_bootmem_region(start, end); + } + } +} + static unsigned long __init free_low_memory_core_early(void) { unsigned long count = 0; @@ -1979,8 +2084,7 @@ static unsigned long __init free_low_memory_core_early(void) memblock_clear_hotplug(0, -1); - for_each_reserved_mem_region(i, &start, &end) - reserve_bootmem_region(start, end); + memmap_init_reserved_pages(); /* * We need to use NUMA_NO_NODE instead of NODE_DATA(0)->node_id @@ -2019,19 +2123,16 @@ void __init reset_all_zones_managed_pages(void) /** * memblock_free_all - release free pages to the buddy allocator - * - * Return: the number of pages actually released. */ -unsigned long __init memblock_free_all(void) +void __init memblock_free_all(void) { unsigned long pages; + free_unused_memmap(); 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_KEEP_MEMBLOCK) @@ -2063,8 +2164,8 @@ static int __init memblock_init_debugfs(void) debugfs_create_file("reserved", 0444, root, &memblock.reserved, &memblock_debug_fops); #ifdef CONFIG_HAVE_MEMBLOCK_PHYS_MAP - debugfs_create_file("physmem", 0444, root, - &memblock.physmem, &memblock_debug_fops); + debugfs_create_file("physmem", 0444, root, &physmem, + &memblock_debug_fops); #endif return 0; |