diff options
36 files changed, 791 insertions, 1120 deletions
diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c index b22a83a91cb8..261adbd3b55a 100644 --- a/arch/powerpc/mm/numa.c +++ b/arch/powerpc/mm/numa.c @@ -127,45 +127,25 @@ static int __cpuinit fake_numa_create_new_node(unsigned long end_pfn, } /* - * get_active_region_work_fn - A helper function for get_node_active_region - * Returns datax set to the start_pfn and end_pfn if they contain - * the initial value of datax->start_pfn between them - * @start_pfn: start page(inclusive) of region to check - * @end_pfn: end page(exclusive) of region to check - * @datax: comes in with ->start_pfn set to value to search for and - * goes out with active range if it contains it - * Returns 1 if search value is in range else 0 - */ -static int __init get_active_region_work_fn(unsigned long start_pfn, - unsigned long end_pfn, void *datax) -{ - struct node_active_region *data; - data = (struct node_active_region *)datax; - - if (start_pfn <= data->start_pfn && end_pfn > data->start_pfn) { - data->start_pfn = start_pfn; - data->end_pfn = end_pfn; - return 1; - } - return 0; - -} - -/* - * get_node_active_region - Return active region containing start_pfn + * get_node_active_region - Return active region containing pfn * Active range returned is empty if none found. - * @start_pfn: The page to return the region for. - * @node_ar: Returned set to the active region containing start_pfn + * @pfn: The page to return the region for + * @node_ar: Returned set to the active region containing @pfn */ -static void __init get_node_active_region(unsigned long start_pfn, - struct node_active_region *node_ar) +static void __init get_node_active_region(unsigned long pfn, + struct node_active_region *node_ar) { - int nid = early_pfn_to_nid(start_pfn); + unsigned long start_pfn, end_pfn; + int i, nid; - node_ar->nid = nid; - node_ar->start_pfn = start_pfn; - node_ar->end_pfn = start_pfn; - work_with_active_regions(nid, get_active_region_work_fn, node_ar); + for_each_mem_pfn_range(i, MAX_NUMNODES, &start_pfn, &end_pfn, &nid) { + if (pfn >= start_pfn && pfn < end_pfn) { + node_ar->nid = nid; + node_ar->start_pfn = start_pfn; + node_ar->end_pfn = end_pfn; + break; + } + } } static void map_cpu_to_node(int cpu, int node) diff --git a/arch/sparc/mm/init_64.c b/arch/sparc/mm/init_64.c index 8e073d802139..8584a25a9f0d 100644 --- a/arch/sparc/mm/init_64.c +++ b/arch/sparc/mm/init_64.c @@ -790,7 +790,7 @@ static int find_node(unsigned long addr) return -1; } -u64 memblock_nid_range(u64 start, u64 end, int *nid) +static u64 memblock_nid_range(u64 start, u64 end, int *nid) { *nid = find_node(start); start += PAGE_SIZE; @@ -808,7 +808,7 @@ u64 memblock_nid_range(u64 start, u64 end, int *nid) return start; } #else -u64 memblock_nid_range(u64 start, u64 end, int *nid) +static u64 memblock_nid_range(u64 start, u64 end, int *nid) { *nid = 0; return end; diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index cb9a1044a771..5d1514c263f8 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -26,6 +26,8 @@ config X86 select HAVE_IOREMAP_PROT select HAVE_KPROBES select HAVE_MEMBLOCK + select HAVE_MEMBLOCK_NODE_MAP + select ARCH_DISCARD_MEMBLOCK select ARCH_WANT_OPTIONAL_GPIOLIB select ARCH_WANT_FRAME_POINTERS select HAVE_DMA_ATTRS diff --git a/arch/x86/include/asm/e820.h b/arch/x86/include/asm/e820.h index 908b96957d88..37782566af24 100644 --- a/arch/x86/include/asm/e820.h +++ b/arch/x86/include/asm/e820.h @@ -117,7 +117,7 @@ static inline void early_memtest(unsigned long start, unsigned long end) extern unsigned long e820_end_of_ram_pfn(void); extern unsigned long e820_end_of_low_ram_pfn(void); -extern u64 early_reserve_e820(u64 startt, u64 sizet, u64 align); +extern u64 early_reserve_e820(u64 sizet, u64 align); void memblock_x86_fill(void); void memblock_find_dma_reserve(void); diff --git a/arch/x86/include/asm/memblock.h b/arch/x86/include/asm/memblock.h deleted file mode 100644 index 0cd3800f33b9..000000000000 --- a/arch/x86/include/asm/memblock.h +++ /dev/null @@ -1,23 +0,0 @@ -#ifndef _X86_MEMBLOCK_H -#define _X86_MEMBLOCK_H - -#define ARCH_DISCARD_MEMBLOCK - -u64 memblock_x86_find_in_range_size(u64 start, u64 *sizep, u64 align); - -void memblock_x86_reserve_range(u64 start, u64 end, char *name); -void memblock_x86_free_range(u64 start, u64 end); -struct range; -int __get_free_all_memory_range(struct range **range, int nodeid, - unsigned long start_pfn, unsigned long end_pfn); -int get_free_all_memory_range(struct range **rangep, int nodeid); - -void memblock_x86_register_active_regions(int nid, unsigned long start_pfn, - unsigned long last_pfn); -u64 memblock_x86_hole_size(u64 start, u64 end); -u64 memblock_x86_find_in_range_node(int nid, u64 start, u64 end, u64 size, u64 align); -u64 memblock_x86_free_memory_in_range(u64 addr, u64 limit); -u64 memblock_x86_memory_in_range(u64 addr, u64 limit); -bool memblock_x86_check_reserved_size(u64 *addrp, u64 *sizep, u64 align); - -#endif diff --git a/arch/x86/kernel/aperture_64.c b/arch/x86/kernel/aperture_64.c index 3d2661ca6542..6e76c191a835 100644 --- a/arch/x86/kernel/aperture_64.c +++ b/arch/x86/kernel/aperture_64.c @@ -88,13 +88,13 @@ static u32 __init allocate_aperture(void) */ addr = memblock_find_in_range(GART_MIN_ADDR, GART_MAX_ADDR, aper_size, aper_size); - if (addr == MEMBLOCK_ERROR || addr + aper_size > GART_MAX_ADDR) { + if (!addr || addr + aper_size > GART_MAX_ADDR) { printk(KERN_ERR "Cannot allocate aperture memory hole (%lx,%uK)\n", addr, aper_size>>10); return 0; } - memblock_x86_reserve_range(addr, addr + aper_size, "aperture64"); + memblock_reserve(addr, aper_size); /* * Kmemleak should not scan this block as it may not be mapped via the * kernel direct mapping. diff --git a/arch/x86/kernel/check.c b/arch/x86/kernel/check.c index 452932d34730..5da1269e8ddc 100644 --- a/arch/x86/kernel/check.c +++ b/arch/x86/kernel/check.c @@ -62,7 +62,8 @@ early_param("memory_corruption_check_size", set_corruption_check_size); void __init setup_bios_corruption_check(void) { - u64 addr = PAGE_SIZE; /* assume first page is reserved anyway */ + phys_addr_t start, end; + u64 i; if (memory_corruption_check == -1) { memory_corruption_check = @@ -82,28 +83,23 @@ void __init setup_bios_corruption_check(void) corruption_check_size = round_up(corruption_check_size, PAGE_SIZE); - while (addr < corruption_check_size && num_scan_areas < MAX_SCAN_AREAS) { - u64 size; - addr = memblock_x86_find_in_range_size(addr, &size, PAGE_SIZE); + for_each_free_mem_range(i, MAX_NUMNODES, &start, &end, NULL) { + start = clamp_t(phys_addr_t, round_up(start, PAGE_SIZE), + PAGE_SIZE, corruption_check_size); + end = clamp_t(phys_addr_t, round_down(end, PAGE_SIZE), + PAGE_SIZE, corruption_check_size); + if (start >= end) + continue; - if (addr == MEMBLOCK_ERROR) - break; - - if (addr >= corruption_check_size) - break; - - if ((addr + size) > corruption_check_size) - size = corruption_check_size - addr; - - memblock_x86_reserve_range(addr, addr + size, "SCAN RAM"); - scan_areas[num_scan_areas].addr = addr; - scan_areas[num_scan_areas].size = size; - num_scan_areas++; + memblock_reserve(start, end - start); + scan_areas[num_scan_areas].addr = start; + scan_areas[num_scan_areas].size = end - start; /* Assume we've already mapped this early memory */ - memset(__va(addr), 0, size); + memset(__va(start), 0, end - start); - addr += size; + if (++num_scan_areas >= MAX_SCAN_AREAS) + break; } if (num_scan_areas) diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c index 303a0e48f076..056e65d5012b 100644 --- a/arch/x86/kernel/e820.c +++ b/arch/x86/kernel/e820.c @@ -738,35 +738,17 @@ core_initcall(e820_mark_nvs_memory); /* * pre allocated 4k and reserved it in memblock and e820_saved */ -u64 __init early_reserve_e820(u64 startt, u64 sizet, u64 align) +u64 __init early_reserve_e820(u64 size, u64 align) { - u64 size = 0; u64 addr; - u64 start; - for (start = startt; ; start += size) { - start = memblock_x86_find_in_range_size(start, &size, align); - if (start == MEMBLOCK_ERROR) - return 0; - if (size >= sizet) - break; + addr = __memblock_alloc_base(size, align, MEMBLOCK_ALLOC_ACCESSIBLE); + if (addr) { + e820_update_range_saved(addr, size, E820_RAM, E820_RESERVED); + printk(KERN_INFO "update e820_saved for early_reserve_e820\n"); + update_e820_saved(); } -#ifdef CONFIG_X86_32 - if (start >= MAXMEM) - return 0; - if (start + size > MAXMEM) - size = MAXMEM - start; -#endif - - addr = round_down(start + size - sizet, align); - if (addr < start) - return 0; - memblock_x86_reserve_range(addr, addr + sizet, "new next"); - e820_update_range_saved(addr, sizet, E820_RAM, E820_RESERVED); - printk(KERN_INFO "update e820_saved for early_reserve_e820\n"); - update_e820_saved(); - return addr; } @@ -1112,15 +1094,30 @@ void __init memblock_x86_fill(void) void __init memblock_find_dma_reserve(void) { #ifdef CONFIG_X86_64 - u64 free_size_pfn; - u64 mem_size_pfn; + u64 nr_pages = 0, nr_free_pages = 0; + unsigned long start_pfn, end_pfn; + phys_addr_t start, end; + int i; + u64 u; + /* * need to find out used area below MAX_DMA_PFN * need to use memblock to get free size in [0, MAX_DMA_PFN] * at first, and assume boot_mem will not take below MAX_DMA_PFN */ - mem_size_pfn = memblock_x86_memory_in_range(0, MAX_DMA_PFN << PAGE_SHIFT) >> PAGE_SHIFT; - free_size_pfn = memblock_x86_free_memory_in_range(0, MAX_DMA_PFN << PAGE_SHIFT) >> PAGE_SHIFT; - set_dma_reserve(mem_size_pfn - free_size_pfn); + for_each_mem_pfn_range(i, MAX_NUMNODES, &start_pfn, &end_pfn, NULL) { + start_pfn = min_t(unsigned long, start_pfn, MAX_DMA_PFN); + end_pfn = min_t(unsigned long, end_pfn, MAX_DMA_PFN); + nr_pages += end_pfn - start_pfn; + } + + for_each_free_mem_range(u, MAX_NUMNODES, &start, &end, NULL) { + start_pfn = min_t(unsigned long, PFN_UP(start), MAX_DMA_PFN); + end_pfn = min_t(unsigned long, PFN_DOWN(end), MAX_DMA_PFN); + if (start_pfn < end_pfn) + nr_free_pages += end_pfn - start_pfn; + } + + set_dma_reserve(nr_pages - nr_free_pages); #endif } diff --git a/arch/x86/kernel/head.c b/arch/x86/kernel/head.c index af0699ba48cf..48d9d4ea1020 100644 --- a/arch/x86/kernel/head.c +++ b/arch/x86/kernel/head.c @@ -52,5 +52,5 @@ void __init reserve_ebda_region(void) lowmem = 0x9f000; /* reserve all memory between lowmem and the 1MB mark */ - memblock_x86_reserve_range(lowmem, 0x100000, "* BIOS reserved"); + memblock_reserve(lowmem, 0x100000 - lowmem); } diff --git a/arch/x86/kernel/head32.c b/arch/x86/kernel/head32.c index 3bb08509a7a1..be9282bcda72 100644 --- a/arch/x86/kernel/head32.c +++ b/arch/x86/kernel/head32.c @@ -33,7 +33,8 @@ void __init i386_start_kernel(void) { memblock_init(); - memblock_x86_reserve_range(__pa_symbol(&_text), __pa_symbol(&__bss_stop), "TEXT DATA BSS"); + memblock_reserve(__pa_symbol(&_text), + __pa_symbol(&__bss_stop) - __pa_symbol(&_text)); #ifdef CONFIG_BLK_DEV_INITRD /* Reserve INITRD */ @@ -42,7 +43,7 @@ void __init i386_start_kernel(void) u64 ramdisk_image = boot_params.hdr.ramdisk_image; u64 ramdisk_size = boot_params.hdr.ramdisk_size; u64 ramdisk_end = PAGE_ALIGN(ramdisk_image + ramdisk_size); - memblock_x86_reserve_range(ramdisk_image, ramdisk_end, "RAMDISK"); + memblock_reserve(ramdisk_image, ramdisk_end - ramdisk_image); } #endif diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c index 5655c2272adb..fd25b11549b8 100644 --- a/arch/x86/kernel/head64.c +++ b/arch/x86/kernel/head64.c @@ -100,7 +100,8 @@ void __init x86_64_start_reservations(char *real_mode_data) memblock_init(); - memblock_x86_reserve_range(__pa_symbol(&_text), __pa_symbol(&__bss_stop), "TEXT DATA BSS"); + memblock_reserve(__pa_symbol(&_text), + __pa_symbol(&__bss_stop) - __pa_symbol(&_text)); #ifdef CONFIG_BLK_DEV_INITRD /* Reserve INITRD */ @@ -109,7 +110,7 @@ void __init x86_64_start_reservations(char *real_mode_data) unsigned long ramdisk_image = boot_params.hdr.ramdisk_image; unsigned long ramdisk_size = boot_params.hdr.ramdisk_size; unsigned long ramdisk_end = PAGE_ALIGN(ramdisk_image + ramdisk_size); - memblock_x86_reserve_range(ramdisk_image, ramdisk_end, "RAMDISK"); + memblock_reserve(ramdisk_image, ramdisk_end - ramdisk_image); } #endif diff --git a/arch/x86/kernel/mpparse.c b/arch/x86/kernel/mpparse.c index 9103b89c145a..a6b79c16ec78 100644 --- a/arch/x86/kernel/mpparse.c +++ b/arch/x86/kernel/mpparse.c @@ -564,9 +564,7 @@ void __init default_get_smp_config(unsigned int early) static void __init smp_reserve_memory(struct mpf_intel *mpf) { - unsigned long size = get_mpc_size(mpf->physptr); - - memblock_x86_reserve_range(mpf->physptr, mpf->physptr+size, "* MP-table mpc"); + memblock_reserve(mpf->physptr, get_mpc_size(mpf->physptr)); } static int __init smp_scan_config(unsigned long base, unsigned long length) @@ -595,7 +593,7 @@ static int __init smp_scan_config(unsigned long base, unsigned long length) mpf, (u64)virt_to_phys(mpf)); mem = virt_to_phys(mpf); - memblock_x86_reserve_range(mem, mem + sizeof(*mpf), "* MP-table mpf"); + memblock_reserve(mem, sizeof(*mpf)); if (mpf->physptr) smp_reserve_memory(mpf); @@ -836,10 +834,8 @@ early_param("alloc_mptable", parse_alloc_mptable_opt); void __init early_reserve_e820_mpc_new(void) { - if (enable_update_mptable && alloc_mptable) { - u64 startt = 0; - mpc_new_phys = early_reserve_e820(startt, mpc_new_length, 4); - } + if (enable_update_mptable && alloc_mptable) + mpc_new_phys = early_reserve_e820(mpc_new_length, 4); } static int __init update_mp_table(void) diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index cf0ef986cb6d..d05444ac2aea 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -306,7 +306,8 @@ static void __init cleanup_highmap(void) static void __init reserve_brk(void) { if (_brk_end > _brk_start) - memblock_x86_reserve_range(__pa(_brk_start), __pa(_brk_end), "BRK"); + memblock_reserve(__pa(_brk_start), + __pa(_brk_end) - __pa(_brk_start)); /* Mark brk area as locked down and no longer taking any new allocations */ @@ -331,13 +332,13 @@ static void __init relocate_initrd(void) ramdisk_here = memblock_find_in_range(0, end_of_lowmem, area_size, PAGE_SIZE); - if (ramdisk_here == MEMBLOCK_ERROR) + if (!ramdisk_here) panic("Cannot find place for new RAMDISK of size %lld\n", ramdisk_size); /* Note: this includes all the lowmem currently occupied by the initrd, we rely on that fact to keep the data intact. */ - memblock_x86_reserve_range(ramdisk_here, ramdisk_here + area_size, "NEW RAMDISK"); + memblock_reserve(ramdisk_here, area_size); initrd_start = ramdisk_here + PAGE_OFFSET; initrd_end = initrd_start + ramdisk_size; printk(KERN_INFO "Allocated new RAMDISK: %08llx - %08llx\n", @@ -393,7 +394,7 @@ static void __init reserve_initrd(void) initrd_start = 0; if (ramdisk_size >= (end_of_lowmem>>1)) { - memblock_x86_free_range(ramdisk_image, ramdisk_end); + memblock_free(ramdisk_image, ramdisk_end - ramdisk_image); printk(KERN_ERR "initrd too large to handle, " "disabling initrd\n"); return; @@ -416,7 +417,7 @@ static void __init reserve_initrd(void) relocate_initrd(); - memblock_x86_free_range(ramdisk_image, ramdisk_end); + memblock_free(ramdisk_image, ramdisk_end - ramdisk_image); } #else static void __init reserve_initrd(void) @@ -490,15 +491,13 @@ static void __init memblock_x86_reserve_range_setup_data(void) { struct setup_data *data; u64 pa_data; - char buf[32]; if (boot_params.hdr.version < 0x0209) return; pa_data = boot_params.hdr.setup_data; while (pa_data) { data = early_memremap(pa_data, sizeof(*data)); - sprintf(buf, "setup data %x", data->type); - memblock_x86_reserve_range(pa_data, pa_data+sizeof(*data)+data->len, buf); + memblock_reserve(pa_data, sizeof(*data) + data->len); pa_data = data->next; early_iounmap(data, sizeof(*data)); } @@ -554,7 +553,7 @@ static void __init reserve_crashkernel(void) crash_base = memblock_find_in_range(alignment, CRASH_KERNEL_ADDR_MAX, crash_size, alignment); - if (crash_base == MEMBLOCK_ERROR) { + if (!crash_base) { pr_info("crashkernel reservation failed - No suitable area found.\n"); return; } @@ -568,7 +567,7 @@ static void __init reserve_crashkernel(void) return; } } - memblock_x86_reserve_range(crash_base, crash_base + crash_size, "CRASH KERNEL"); + memblock_reserve(crash_base, crash_size); printk(KERN_INFO "Reserving %ldMB of memory at %ldMB " "for crashkernel (System RAM: %ldMB)\n", @@ -626,7 +625,7 @@ static __init void reserve_ibft_region(void) addr = find_ibft_region(&size); if (size) - memblock_x86_reserve_range(addr, addr + size, "* ibft"); + memblock_reserve(addr, size); } static unsigned reserve_low = CONFIG_X86_RESERVE_LOW << 10; diff --git a/arch/x86/kernel/trampoline.c b/arch/x86/kernel/trampoline.c index a91ae7709b49..a73b61055ad6 100644 --- a/arch/x86/kernel/trampoline.c +++ b/arch/x86/kernel/trampoline.c @@ -14,11 +14,11 @@ void __init setup_trampolines(void) /* Has to be in very low memory so we can execute real-mode AP code. */ mem = memblock_find_in_range(0, 1<<20, size, PAGE_SIZE); - if (mem == MEMBLOCK_ERROR) + if (!mem) panic("Cannot allocate trampoline\n"); x86_trampoline_base = __va(mem); - memblock_x86_reserve_range(mem, mem + size, "TRAMPOLINE"); + memblock_reserve(mem, size); printk(KERN_DEBUG "Base memory trampoline at [%p] %llx size %zu\n", x86_trampoline_base, (unsigned long long)mem, size); diff --git a/arch/x86/mm/Makefile b/arch/x86/mm/Makefile index 3d11327c9ab4..23d8e5fecf76 100644 --- a/arch/x86/mm/Makefile +++ b/arch/x86/mm/Makefile @@ -27,6 +27,4 @@ obj-$(CONFIG_AMD_NUMA) += amdtopology.o obj-$(CONFIG_ACPI_NUMA) += srat.o obj-$(CONFIG_NUMA_EMU) += numa_emulation.o -obj-$(CONFIG_HAVE_MEMBLOCK) += memblock.o - obj-$(CONFIG_MEMTEST) += memtest.o diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c index 87488b93a65c..a298914058f9 100644 --- a/arch/x86/mm/init.c +++ b/arch/x86/mm/init.c @@ -67,7 +67,7 @@ static void __init find_early_table_space(unsigned long end, int use_pse, good_end = max_pfn_mapped << PAGE_SHIFT; base = memblock_find_in_range(start, good_end, tables, PAGE_SIZE); - if (base == MEMBLOCK_ERROR) + if (!base) panic("Cannot find space for the kernel page tables"); pgt_buf_start = base >> PAGE_SHIFT; @@ -80,7 +80,7 @@ static void __init find_early_table_space(unsigned long end, int use_pse, void __init native_pagetable_reserve(u64 start, u64 end) { - memblock_x86_reserve_range(start, end, "PGTABLE"); + memblock_reserve(start, end - start); } struct map_range { @@ -279,8 +279,8 @@ unsigned long __init_refok init_memory_mapping(unsigned long start, * pgt_buf_end) and free the other ones (pgt_buf_end - pgt_buf_top) * so that they can be reused for other purposes. * - * On native it just means calling memblock_x86_reserve_range, on Xen it - * also means marking RW the pagetable pages that we allocated before + * On native it just means calling memblock_reserve, on Xen it also + * means marking RW the pagetable pages that we allocated before * but that haven't been used. * * In fact on xen we mark RO the whole range pgt_buf_start - diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c index 29f7c6d98179..0c1da394a634 100644 --- a/arch/x86/mm/init_32.c +++ b/arch/x86/mm/init_32.c @@ -427,23 +427,17 @@ static void __init add_one_highpage_init(struct page *page) void __init add_highpages_with_active_regions(int nid, unsigned long start_pfn, unsigned long end_pfn) { - struct range *range; - int nr_range; - int i; - - nr_range = __get_free_all_memory_range(&range, nid, start_pfn, end_pfn); - - for (i = 0; i < nr_range; i++) { - struct page *page; - int node_pfn; - - for (node_pfn = range[i].start; node_pfn < range[i].end; - node_pfn++) { - if (!pfn_valid(node_pfn)) - continue; - page = pfn_to_page(node_pfn); - add_one_highpage_init(page); - } + phys_addr_t start, end; + u64 i; + + for_each_free_mem_range(i, nid, &start, &end, NULL) { + unsigned long pfn = clamp_t(unsigned long, PFN_UP(start), + start_pfn, end_pfn); + unsigned long e_pfn = clamp_t(unsigned long, PFN_DOWN(end), + start_pfn, end_pfn); + for ( ; pfn < e_pfn; pfn++) + if (pfn_valid(pfn)) + add_one_highpage_init(pfn_to_page(pfn)); } } #else @@ -650,18 +644,18 @@ void __init initmem_init(void) highstart_pfn = highend_pfn = max_pfn; if (max_pfn > max_low_pfn) highstart_pfn = max_low_pfn; - memblock_x86_register_active_regions(0, 0, highend_pfn); - sparse_memory_present_with_active_regions(0); printk(KERN_NOTICE "%ldMB HIGHMEM available.\n", pages_to_mb(highend_pfn - highstart_pfn)); num_physpages = highend_pfn; high_memory = (void *) __va(highstart_pfn * PAGE_SIZE - 1) + 1; #else - memblock_x86_register_active_regions(0, 0, max_low_pfn); - sparse_memory_present_with_active_regions(0); num_physpages = max_low_pfn; high_memory = (void *) __va(max_low_pfn * PAGE_SIZE - 1) + 1; #endif + + memblock_set_node(0, (phys_addr_t)ULLONG_MAX, 0); + sparse_memory_present_with_active_regions(0); + #ifdef CONFIG_FLATMEM max_mapnr = num_physpages; #endif diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index bbaaa005bf0e..a8a56ce3a962 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -608,7 +608,7 @@ kernel_physical_mapping_init(unsigned long start, #ifndef CONFIG_NUMA void __init initmem_init(void) { - memblock_x86_register_active_regions(0, 0, max_pfn); + memblock_set_node(0, (phys_addr_t)ULLONG_MAX, 0); } #endif diff --git a/arch/x86/mm/memblock.c b/arch/x86/mm/memblock.c deleted file mode 100644 index 992da5ec5a64..000000000000 --- a/arch/x86/mm/memblock.c +++ /dev/null @@ -1,348 +0,0 @@ -#include <linux/kernel.h> -#include <linux/types.h> -#include <linux/init.h> -#include <linux/bitops.h> -#include <linux/memblock.h> -#include <linux/bootmem.h> -#include <linux/mm.h> -#include <linux/range.h> - -/* Check for already reserved areas */ -bool __init memblock_x86_check_reserved_size(u64 *addrp, u64 *sizep, u64 align) -{ - struct memblock_region *r; - u64 addr = *addrp, last; - u64 size = *sizep; - bool changed = false; - -again: - last = addr + size; - for_each_memblock(reserved, r) { - if (last > r->base && addr < r->base) { - size = r->base - addr; - changed = true; - goto again; - } - if (last > (r->base + r->size) && addr < (r->base + r->size)) { - addr = round_up(r->base + r->size, align); - size = last - addr; - changed = true; - goto again; - } - if (last <= (r->base + r->size) && addr >= r->base) { - *sizep = 0; - return false; - } - } - if (changed) { - *addrp = addr; - *sizep = size; - } - return changed; -} - -/* - * Find next free range after start, and size is returned in *sizep - */ -u64 __init memblock_x86_find_in_range_size(u64 start, u64 *sizep, u64 align) -{ - struct memblock_region *r; - - for_each_memblock(memory, r) { - u64 ei_start = r->base; - u64 ei_last = ei_start + r->size; - u64 addr; - - addr = round_up(ei_start, align); - if (addr < start) - addr = round_up(start, align); - if (addr >= ei_last) - continue; - *sizep = ei_last - addr; - while (memblock_x86_check_reserved_size(&addr, sizep, align)) - ; - - if (*sizep) - return addr; - } - - return MEMBLOCK_ERROR; -} - -static __init struct range *find_range_array(int count) -{ - u64 end, size, mem; - struct range *range; - - size = sizeof(struct range) * count; - end = memblock.current_limit; - - mem = memblock_find_in_range(0, end, size, sizeof(struct range)); - if (mem == MEMBLOCK_ERROR) - panic("can not find more space for range array"); - - /* - * This range is tempoaray, so don't reserve it, it will not be - * overlapped because We will not alloccate new buffer before - * We discard this one - */ - range = __va(mem); - memset(range, 0, size); - - return range; -} - -static void __init memblock_x86_subtract_reserved(struct range *range, int az) -{ - u64 final_start, final_end; - struct memblock_region *r; - - /* Take out region array itself at first*/ - memblock_free_reserved_regions(); - - memblock_dbg("Subtract (%ld early reservations)\n", memblock.reserved.cnt); - - for_each_memblock(reserved, r) { - memblock_dbg(" [%010llx-%010llx]\n", (u64)r->base, (u64)r->base + r->size - 1); - final_start = PFN_DOWN(r->base); - final_end = PFN_UP(r->base + r->size); - if (final_start >= final_end) - continue; - subtract_range(range, az, final_start, final_end); - } - - /* Put region array back ? */ - memblock_reserve_reserved_regions(); -} - -struct count_data { - int nr; -}; - -static int __init count_work_fn(unsigned long start_pfn, - unsigned long end_pfn, void *datax) -{ - struct count_data *data = datax; - - data->nr++; - - return 0; -} - -static int __init count_early_node_map(int nodeid) -{ - struct count_data data; - - data.nr = 0; - work_with_active_regions(nodeid, count_work_fn, &data); - - return data.nr; -} - -int __init __get_free_all_memory_range(struct range **rangep, int nodeid, - unsigned long start_pfn, unsigned long end_pfn) -{ - int count; - struct range *range; - int nr_range; - - count = (memblock.reserved.cnt + count_early_node_map(nodeid)) * 2; - - range = find_range_array(count); - nr_range = 0; - - /* - * Use early_node_map[] and memblock.reserved.region to get range array - * at first - */ - nr_range = add_from_early_node_map(range, count, nr_range, nodeid); - subtract_range(range, count, 0, start_pfn); - subtract_range(range, count, end_pfn, -1ULL); - - memblock_x86_subtract_reserved(range, count); - nr_range = clean_sort_range(range, count); - - *rangep = range; - return nr_range; -} - -int __init get_free_all_memory_range(struct range **rangep, int nodeid) -{ - unsigned long end_pfn = -1UL; - -#ifdef CONFIG_X86_32 - end_pfn = max_low_pfn; -#endif - return __get_free_all_memory_range(rangep, nodeid, 0, end_pfn); -} - -static u64 __init __memblock_x86_memory_in_range(u64 addr, u64 limit, bool get_free) -{ - int i, count; - struct range *range; - int nr_range; - u64 final_start, final_end; - u64 free_size; - struct memblock_region *r; - - count = (memblock.reserved.cnt + memblock.memory.cnt) * 2; - - range = find_range_array(count); - nr_range = 0; - - addr = PFN_UP(addr); - limit = PFN_DOWN(limit); - - for_each_memblock(memory, r) { - final_start = PFN_UP(r->base); - final_end = PFN_DOWN(r->base + r->size); - if (final_start >= final_end) - continue; - if (final_start >= limit || final_end <= addr) - continue; - - nr_range = add_range(range, count, nr_range, final_start, final_end); - } - subtract_range(range, count, 0, addr); - subtract_range(range, count, limit, -1ULL); - - /* Subtract memblock.reserved.region in range ? */ - if (!get_free) - goto sort_and_count_them; - for_each_memblock(reserved, r) { - final_start = PFN_DOWN(r->base); - final_end = PFN_UP(r->base + r->size); - if (final_start >= final_end) - continue; - if (final_start >= limit || final_end <= addr) - continue; - - subtract_range(range, count, final_start, final_end); - } - -sort_and_count_them: - nr_range = clean_sort_range(range, count); - - free_size = 0; - for (i = 0; i < nr_range; i++) - free_size += range[i].end - range[i].start; - - return free_size << PAGE_SHIFT; -} - -u64 __init memblock_x86_free_memory_in_range(u64 addr, u64 limit) -{ - return __memblock_x86_memory_in_range(addr, limit, true); -} - -u64 __init memblock_x86_memory_in_range(u64 addr, u64 limit) -{ - return __memblock_x86_memory_in_range(addr, limit, false); -} - -void __init memblock_x86_reserve_range(u64 start, u64 end, char *name) -{ - if (start == end) - return; - - if (WARN_ONCE(start > end, "memblock_x86_reserve_range: wrong range [%#llx, %#llx)\n", start, end)) - return; - - memblock_dbg(" memblock_x86_reserve_range: [%#010llx-%#010llx] %16s\n", start, end - 1, name); - - memblock_reserve(start, end - start); -} - -void __init memblock_x86_free_range(u64 start, u64 end) -{ - if (start == end) - return; - - if (WARN_ONCE(start > end, "memblock_x86_free_range: wrong range [%#llx, %#llx)\n", start, end)) - return; - - memblock_dbg(" memblock_x86_free_range: [%#010llx-%#010llx]\n", start, end - 1); - - memblock_free(start, end - start); -} - -/* - * Need to call this function after memblock_x86_register_active_regions, - * so early_node_map[] is filled already. - */ -u64 __init memblock_x86_find_in_range_node(int nid, u64 start, u64 end, u64 size, u64 align) -{ - u64 addr; - addr = find_memory_core_early(nid, size, align, start, end); - if (addr != MEMBLOCK_ERROR) - return addr; - - /* Fallback, should already have start end within node range */ - return memblock_find_in_range(start, end, size, align); -} - -/* - * Finds an active region in the address range from start_pfn to last_pfn and - * returns its range in ei_startpfn and ei_endpfn for the memblock entry. - */ -static int __init memblock_x86_find_active_region(const struct memblock_region *ei, - unsigned long start_pfn, - unsigned long last_pfn, - unsigned long *ei_startpfn, - unsigned long *ei_endpfn) -{ - u64 align = PAGE_SIZE; - - *ei_startpfn = round_up(ei->base, align) >> PAGE_SHIFT; - *ei_endpfn = round_down(ei->base + ei->size, align) >> PAGE_SHIFT; - - /* Skip map entries smaller than a page */ - if (*ei_startpfn >= *ei_endpfn) - return 0; - - /* Skip if map is outside the node */ - if (*ei_endpfn <= start_pfn || *ei_startpfn >= last_pfn) - return 0; - - /* Check for overlaps */ - if (*ei_startpfn < start_pfn) - *ei_startpfn = start_pfn; - if (*ei_endpfn > last_pfn) - *ei_endpfn = last_pfn; - - return 1; -} - -/* Walk the memblock.memory map and register active regions within a node */ -void __init memblock_x86_register_active_regions(int nid, unsigned long start_pfn, - unsigned long last_pfn) -{ - unsigned long ei_startpfn; - unsigned long ei_endpfn; - struct memblock_region *r; - - for_each_memblock(memory, r) - if (memblock_x86_find_active_region(r, start_pfn, last_pfn, - &ei_startpfn, &ei_endpfn)) - add_active_range(nid, ei_startpfn, ei_endpfn); -} - -/* - * Find the hole size (in bytes) in the memory range. - * @start: starting address of the memory range to scan - * @end: ending address of the memory range to scan - */ -u64 __init memblock_x86_hole_size(u64 start, u64 end) -{ - unsigned long start_pfn = start >> PAGE_SHIFT; - unsigned long last_pfn = end >> PAGE_SHIFT; - unsigned long ei_startpfn, ei_endpfn, ram = 0; - struct memblock_region *r; - - for_each_memblock(memory, r) - if (memblock_x86_find_active_region(r, start_pfn, last_pfn, - &ei_startpfn, &ei_endpfn)) - ram += ei_endpfn - ei_startpfn; - - return end - start - ((u64)ram << PAGE_SHIFT); -} diff --git a/arch/x86/mm/memtest.c b/arch/x86/mm/memtest.c index 92faf3a1c53e..c80b9fb95734 100644 --- a/arch/x86/mm/memtest.c +++ b/arch/x86/mm/memtest.c @@ -34,7 +34,7 @@ static void __init reserve_bad_mem(u64 pattern, u64 start_bad, u64 end_bad) (unsigned long long) pattern, (unsigned long long) start_bad, (unsigned long long) end_bad); - memblock_x86_reserve_range(start_bad, end_bad, "BAD RAM"); + memblock_reserve(start_bad, end_bad - start_bad); } static void __init memtest(u64 pattern, u64 start_phys, u64 size) @@ -70,24 +70,19 @@ static void __init memtest(u64 pattern, u64 start_phys, u64 size) static void __init do_one_pass(u64 pattern, u64 start, u64 end) { - u64 size = 0; - - while (start < end) { - start = memblock_x86_find_in_range_size(start, &size, 1); - - /* done ? */ - if (start >= end) - break; - if (start + size > end) - size = end - start; - - printk(KERN_INFO " %010llx - %010llx pattern %016llx\n", - (unsigned long long) start, - (unsigned long long) start + size, - (unsigned long long) cpu_to_be64(pattern)); - memtest(pattern, start, size); - - start += size; + u64 i; + phys_addr_t this_start, this_end; + + for_each_free_mem_range(i, MAX_NUMNODES, &this_start, &this_end, NULL) { + this_start = clamp_t(phys_addr_t, this_start, start, end); + this_end = clamp_t(phys_addr_t, this_end, start, end); + if (this_start < this_end) { + printk(KERN_INFO " %010llx - %010llx pattern %016llx\n", + (unsigned long long)this_start, + (unsigned long long)this_end, + (unsigned long long)cpu_to_be64(pattern)); + memtest(pattern, this_start, this_end - this_start); + } } } diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c index fbeaaf416610..496f494593bf 100644 --- a/arch/x86/mm/numa.c +++ b/arch/x86/mm/numa.c @@ -192,8 +192,6 @@ int __init numa_add_memblk(int nid, u64 start, u64 end) /* Initialize NODE_DATA for a node on the local memory */ static void __init setup_node_data(int nid, u64 start, u64 end) { - const u64 nd_low = PFN_PHYS(MAX_DMA_PFN); - const u64 nd_high = PFN_PHYS(max_pfn_mapped); const size_t nd_size = roundup(sizeof(pg_data_t), PAGE_SIZE); bool remapped = false; u64 nd_pa; @@ -224,17 +222,12 @@ static void __init setup_node_data(int nid, u64 start, u64 end) nd_pa = __pa(nd); remapped = true; } else { - nd_pa = memblock_x86_find_in_range_node(nid, nd_low, nd_high, - nd_size, SMP_CACHE_BYTES); - if (nd_pa == MEMBLOCK_ERROR) - nd_pa = memblock_find_in_range(nd_low, nd_high, - nd_size, SMP_CACHE_BYTES); - if (nd_pa == MEMBLOCK_ERROR) { + nd_pa = memblock_alloc_nid(nd_size, SMP_CACHE_BYTES, nid); + if (!nd_pa) { pr_err("Cannot find %zu bytes in node %d\n", nd_size, nid); return; } - memblock_x86_reserve_range(nd_pa, nd_pa + nd_size, "NODE_DATA"); nd = __va(nd_pa); } @@ -371,8 +364,7 @@ void __init numa_reset_distance(void) /* numa_distance could be 1LU marking allocation failure, test cnt */ if (numa_distance_cnt) - memblock_x86_free_range(__pa(numa_distance), - __pa(numa_distance) + size); + memblock_free(__pa(numa_distance), size); numa_distance_cnt = 0; numa_distance = NULL; /* enable table creation */ } @@ -395,13 +387,13 @@ static int __init numa_alloc_distance(void) phys = memblock_find_in_range(0, PFN_PHYS(max_pfn_mapped), size, PAGE_SIZE); - if (phys == MEMBLOCK_ERROR) { + if (!phys) { pr_warning("NUMA: Warning: can't allocate distance table!\n"); /* don't retry until explicitly reset */ numa_distance = (void *)1LU; return -ENOMEM; } - memblock_x86_reserve_range(phys, phys + size, "NUMA DIST"); + memblock_reserve(phys, size); numa_distance = __va(phys); numa_distance_cnt = cnt; @@ -482,8 +474,8 @@ static bool __init numa_meminfo_cover_memory(const struct numa_meminfo *mi) numaram = 0; } - e820ram = max_pfn - (memblock_x86_hole_size(0, - PFN_PHYS(max_pfn)) >> PAGE_SHIFT); + e820ram = max_pfn - absent_pages_in_range(0, max_pfn); + /* We seem to lose 3 pages somewhere. Allow 1M of slack. */ if ((s64)(e820ram - numaram) >= (1 << (20 - PAGE_SHIFT))) { printk(KERN_ERR "NUMA: nodes only cover %LuMB of your %LuMB e820 RAM. Not used.\n", @@ -505,13 +497,10 @@ static int __init numa_register_memblks(struct numa_meminfo *mi) if (WARN_ON(nodes_empty(node_possible_map))) return -EINVAL; - for (i = 0; i < mi->nr_blks; i++) - memblock_x86_register_active_regions(mi->blk[i].nid, - mi->blk[i].start >> PAGE_SHIFT, - mi->blk[i].end >> PAGE_SHIFT); - - /* for out of order entries */ - sort_node_map(); + for (i = 0; i < mi->nr_blks; i++) { + struct numa_memblk *mb = &mi->blk[i]; + memblock_set_node(mb->start, mb->end - mb->start, mb->nid); + } /* * If sections array is gonna be used for pfn -> nid mapping, check @@ -545,6 +534,8 @@ static int __init numa_register_memblks(struct numa_meminfo *mi) setup_node_data(nid, start, end); } + /* Dump memblock with node info and return. */ + memblock_dump_all(); return 0; } @@ -582,7 +573,7 @@ static int __init numa_init(int (*init_func)(void)) nodes_clear(node_possible_map); nodes_clear(node_online_map); memset(&numa_meminfo, 0, sizeof(numa_meminfo)); - remove_all_active_ranges(); + WARN_ON(memblock_set_node(0, ULLONG_MAX, MAX_NUMNODES)); numa_reset_distance(); ret = init_func(); diff --git a/arch/x86/mm/numa_32.c b/arch/x86/mm/numa_32.c index 3adebe7e536a..534255a36b6b 100644 --- a/arch/x86/mm/numa_32.c +++ b/arch/x86/mm/numa_32.c @@ -199,23 +199,23 @@ void __init init_alloc_remap(int nid, u64 start, u64 end) /* allocate node memory and the lowmem remap area */ node_pa = memblock_find_in_range(start, end, size, LARGE_PAGE_BYTES); - if (node_pa == MEMBLOCK_ERROR) { + if (!node_pa) { pr_warning("remap_alloc: failed to allocate %lu bytes for node %d\n", size, nid); return; } - memblock_x86_reserve_range(node_pa, node_pa + size, "KVA RAM"); + memblock_reserve(node_pa, size); remap_pa = memblock_find_in_range(min_low_pfn << PAGE_SHIFT, max_low_pfn << PAGE_SHIFT, size, LARGE_PAGE_BYTES); - if (remap_pa == MEMBLOCK_ERROR) { + if (!remap_pa) { pr_warning("remap_alloc: failed to allocate %lu bytes remap area for node %d\n", size, nid); - memblock_x86_free_range(node_pa, node_pa + size); + memblock_free(node_pa, size); return; } - memblock_x86_reserve_range(remap_pa, remap_pa + size, "KVA PG"); + memblock_reserve(remap_pa, size); remap_va = phys_to_virt(remap_pa); /* perform actual remap */ diff --git a/arch/x86/mm/numa_64.c b/arch/x86/mm/numa_64.c index dd27f401f0a0..92e27119ee1a 100644 --- a/arch/x86/mm/numa_64.c +++ b/arch/x86/mm/numa_64.c @@ -19,7 +19,7 @@ unsigned long __init numa_free_all_bootmem(void) for_each_online_node(i) pages += free_all_bootmem_node(NODE_DATA(i)); - pages += free_all_memory_core_early(MAX_NUMNODES); + pages += free_low_memory_core_early(MAX_NUMNODES); return pages; } diff --git a/arch/x86/mm/numa_emulation.c b/arch/x86/mm/numa_emulation.c index d0ed086b6247..46db56845f18 100644 --- a/arch/x86/mm/numa_emulation.c +++ b/arch/x86/mm/numa_emulation.c @@ -28,6 +28,16 @@ static int __init emu_find_memblk_by_nid(int nid, const struct numa_meminfo *mi) return -ENOENT; } +static u64 mem_hole_size(u64 start, u64 end) +{ + unsigned long start_pfn = PFN_UP(start); + unsigned long end_pfn = PFN_DOWN(end); + + if (start_pfn < end_pfn) + return PFN_PHYS(absent_pages_in_range(start_pfn, end_pfn)); + return 0; +} + /* * Sets up nid to range from @start to @end. The return value is -errno if * something went wrong, 0 otherwise. @@ -89,7 +99,7 @@ static int __init split_nodes_interleave(struct numa_meminfo *ei, * Calculate target node size. x86_32 freaks on __udivdi3() so do * the division in ulong number of pages and convert back. */ - size = max_addr - addr - memblock_x86_hole_size(addr, max_addr); + size = max_addr - addr - mem_hole_size(addr, max_addr); size = PFN_PHYS((unsigned long)(size >> PAGE_SHIFT) / nr_nodes); /* @@ -135,8 +145,7 @@ static int __init split_nodes_interleave(struct numa_meminfo *ei, * Continue to add memory to this fake node if its * non-reserved memory is less than the per-node size. */ - while (end - start - - memblock_x86_hole_size(start, end) < size) { + while (end - start - mem_hole_size(start, end) < size) { end += FAKE_NODE_MIN_SIZE; if (end > limit) { end = limit; @@ -150,7 +159,7 @@ static int __init split_nodes_interleave(struct numa_meminfo *ei, * this one must extend to the boundary. */ if (end < dma32_end && dma32_end - end - - memblock_x86_hole_size(end, dma32_end) < FAKE_NODE_MIN_SIZE) + mem_hole_size(end, dma32_end) < FAKE_NODE_MIN_SIZE) end = dma32_end; /* @@ -158,8 +167,7 @@ static int __init split_nodes_interleave(struct numa_meminfo *ei, * next node, this one must extend to the end of the * physical node. */ - if (limit - end - - memblock_x86_hole_size(end, limit) < size) + if (limit - end - mem_hole_size(end, limit) < size) end = limit; ret = emu_setup_memblk(ei, pi, nid++ % nr_nodes, @@ -180,7 +188,7 @@ static u64 __init find_end_of_node(u64 start, u64 max_addr, u64 size) { u64 end = start + size; - while (end - start - memblock_x86_hole_size(start, end) < size) { + while (end - start - mem_hole_size(start, end) < size) { end += FAKE_NODE_MIN_SIZE; if (end > max_addr) { end = max_addr; @@ -211,8 +219,7 @@ static int __init split_nodes_size_interleave(struct numa_meminfo *ei, * creates a uniform distribution of node sizes across the entire * machine (but not necessarily over physical nodes). */ - min_size = (max_addr - addr - memblock_x86_hole_size(addr, max_addr)) / - MAX_NUMNODES; + min_size = (max_addr - addr - mem_hole_size(addr, max_addr)) / MAX_NUMNODES; min_size = max(min_size, FAKE_NODE_MIN_SIZE); if ((min_size & FAKE_NODE_MIN_HASH_MASK) < min_size) min_size = (min_size + FAKE_NODE_MIN_SIZE) & @@ -252,7 +259,7 @@ static int __init split_nodes_size_interleave(struct numa_meminfo *ei, * this one must extend to the boundary. */ if (end < dma32_end && dma32_end - end - - memblock_x86_hole_size(end, dma32_end) < FAKE_NODE_MIN_SIZE) + mem_hole_size(end, dma32_end) < FAKE_NODE_MIN_SIZE) end = dma32_end; /* @@ -260,8 +267,7 @@ static int __init split_nodes_size_interleave(struct numa_meminfo *ei, * next node, this one must extend to the end of the * physical node. */ - if (limit - end - - memblock_x86_hole_size(end, limit) < size) + if (limit - end - mem_hole_size(end, limit) < size) end = limit; ret = emu_setup_memblk(ei, pi, nid++ % MAX_NUMNODES, @@ -351,11 +357,11 @@ void __init numa_emulation(struct numa_meminfo *numa_meminfo, int numa_dist_cnt) phys = memblock_find_in_range(0, PFN_PHYS(max_pfn_mapped), phys_size, PAGE_SIZE); - if (phys == MEMBLOCK_ERROR) { + if (!phys) { pr_warning("NUMA: Warning: can't allocate copy of distance table, disabling emulation\n"); goto no_emu; } - memblock_x86_reserve_range(phys, phys + phys_size, "TMP NUMA DIST"); + memblock_reserve(phys, phys_size); phys_dist = __va(phys); for (i = 0; i < numa_dist_cnt; i++) @@ -424,7 +430,7 @@ void __init numa_emulation(struct numa_meminfo *numa_meminfo, int numa_dist_cnt) /* free the copied physical distance table */ if (phys_dist) - memblock_x86_free_range(__pa(phys_dist), __pa(phys_dist) + phys_size); + memblock_free(__pa(phys_dist), phys_size); return; no_emu: diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c index 37718f0f053d..4a01967f02e7 100644 --- a/arch/x86/platform/efi/efi.c +++ b/arch/x86/platform/efi/efi.c @@ -352,8 +352,7 @@ void __init efi_memblock_x86_reserve_range(void) boot_params.efi_info.efi_memdesc_size; memmap.desc_version = boot_params.efi_info.efi_memdesc_version; memmap.desc_size = boot_params.efi_info.efi_memdesc_size; - memblock_x86_reserve_range(pmap, pmap + memmap.nr_map * memmap.desc_size, - "EFI memmap"); + memblock_reserve(pmap, memmap.nr_map * memmap.desc_size); } #if EFI_DEBUG @@ -397,16 +396,14 @@ void __init efi_reserve_boot_services(void) if ((start+size >= virt_to_phys(_text) && start <= virt_to_phys(_end)) || !e820_all_mapped(start, start+size, E820_RAM) || - memblock_x86_check_reserved_size(&start, &size, - 1<<EFI_PAGE_SHIFT)) { + memblock_is_region_reserved(start, size)) { /* Could not reserve, skip it */ md->num_pages = 0; memblock_dbg(PFX "Could not reserve boot range " "[0x%010llx-0x%010llx]\n", start, start+size-1); } else - memblock_x86_reserve_range(start, start+size, - "EFI Boot"); + memblock_reserve(start, size); } } diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c index 87f6673b1207..f4bf8aa574f4 100644 --- a/arch/x86/xen/mmu.c +++ b/arch/x86/xen/mmu.c @@ -1774,10 +1774,8 @@ pgd_t * __init xen_setup_kernel_pagetable(pgd_t *pgd, __xen_write_cr3(true, __pa(pgd)); xen_mc_issue(PARAVIRT_LAZY_CPU); - memblock_x86_reserve_range(__pa(xen_start_info->pt_base), - __pa(xen_start_info->pt_base + - xen_start_info->nr_pt_frames * PAGE_SIZE), - "XEN PAGETABLES"); + memblock_reserve(__pa(xen_start_info->pt_base), + xen_start_info->nr_pt_frames * PAGE_SIZE); return pgd; } @@ -1853,10 +1851,8 @@ pgd_t * __init xen_setup_kernel_pagetable(pgd_t *pgd, PFN_DOWN(__pa(initial_page_table))); xen_write_cr3(__pa(initial_page_table)); - memblock_x86_reserve_range(__pa(xen_start_info->pt_base), - __pa(xen_start_info->pt_base + - xen_start_info->nr_pt_frames * PAGE_SIZE), - "XEN PAGETABLES"); + memblock_reserve(__pa(xen_start_info->pt_base), + xen_start_info->nr_pt_frames * PAGE_SIZE)); return initial_page_table; } diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c index 38d0af4fefec..f5e1362550e7 100644 --- a/arch/x86/xen/setup.c +++ b/arch/x86/xen/setup.c @@ -75,7 +75,7 @@ static void __init xen_add_extra_mem(u64 start, u64 size) if (i == XEN_EXTRA_MEM_MAX_REGIONS) printk(KERN_WARNING "Warning: not enough extra memory regions\n"); - memblock_x86_reserve_range(start, start + size, "XEN EXTRA"); + memblock_reserve(start, size); xen_max_p2m_pfn = PFN_DOWN(start + size); @@ -299,9 +299,8 @@ char * __init xen_memory_setup(void) * - xen_start_info * See comment above "struct start_info" in <xen/interface/xen.h> */ - memblock_x86_reserve_range(__pa(xen_start_info->mfn_list), - __pa(xen_start_info->pt_base), - "XEN START INFO"); + memblock_reserve(__pa(xen_start_info->mfn_list), + xen_start_info->pt_base - xen_start_info->mfn_list); sanitize_e820_map(e820.map, ARRAY_SIZE(e820.map), &e820.nr_map); diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c index c0c7820d4c46..bcbd693b351a 100644 --- a/drivers/iommu/intel-iommu.c +++ b/drivers/iommu/intel-iommu.c @@ -2185,18 +2185,6 @@ static inline void iommu_prepare_isa(void) static int md_domain_init(struct dmar_domain *domain, int guest_width); -static int __init si_domain_work_fn(unsigned long start_pfn, - unsigned long end_pfn, void *datax) -{ - int *ret = datax; - - *ret = iommu_domain_identity_map(si_domain, - (uint64_t)start_pfn << PAGE_SHIFT, - (uint64_t)end_pfn << PAGE_SHIFT); - return *ret; - -} - static int __init si_domain_init(int hw) { struct dmar_drhd_unit *drhd; @@ -2228,9 +2216,15 @@ static int __init si_domain_init(int hw) return 0; for_each_online_node(nid) { - work_with_active_regions(nid, si_domain_work_fn, &ret); - if (ret) - return ret; + unsigned long start_pfn, end_pfn; + int i; + + for_each_mem_pfn_range(i, nid, &start_pfn, &end_pfn, NULL) { + ret = iommu_domain_identity_map(si_domain, + PFN_PHYS(start_pfn), PFN_PHYS(end_pfn)); + if (ret) + return ret; + } } return 0; diff --git a/include/linux/bootmem.h b/include/linux/bootmem.h index ab344a521105..66d3e954eb6c 100644 --- a/include/linux/bootmem.h +++ b/include/linux/bootmem.h @@ -44,7 +44,7 @@ extern unsigned long init_bootmem_node(pg_data_t *pgdat, unsigned long endpfn); extern unsigned long init_bootmem(unsigned long addr, unsigned long memend); -unsigned long free_all_memory_core_early(int nodeid); +extern unsigned long free_low_memory_core_early(int nodeid); extern unsigned long free_all_bootmem_node(pg_data_t *pgdat); extern unsigned long free_all_bootmem(void); diff --git a/include/linux/memblock.h b/include/linux/memblock.h index e6b843e16e81..ab89b417655c 100644 --- a/include/linux/memblock.h +++ b/include/linux/memblock.h @@ -2,8 +2,6 @@ #define _LINUX_MEMBLOCK_H #ifdef __KERNEL__ -#define MEMBLOCK_ERROR 0 - #ifdef CONFIG_HAVE_MEMBLOCK /* * Logical memory blocks. @@ -19,13 +17,14 @@ #include <linux/init.h> #include <linux/mm.h> -#include <asm/memblock.h> - #define INIT_MEMBLOCK_REGIONS 128 struct memblock_region { phys_addr_t base; phys_addr_t size; +#ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP + int nid; +#endif }; struct memblock_type { @@ -48,7 +47,8 @@ extern int memblock_can_resize; #define memblock_dbg(fmt, ...) \ if (memblock_debug) printk(KERN_INFO pr_fmt(fmt), ##__VA_ARGS__) -u64 memblock_find_in_range(u64 start, u64 end, u64 size, u64 align); +phys_addr_t memblock_find_in_range(phys_addr_t start, phys_addr_t end, + phys_addr_t size, phys_addr_t align); int memblock_free_reserved_regions(void); int memblock_reserve_reserved_regions(void); @@ -59,9 +59,56 @@ extern long memblock_remove(phys_addr_t base, phys_addr_t size); extern long memblock_free(phys_addr_t base, phys_addr_t size); extern long memblock_reserve(phys_addr_t base, phys_addr_t size); +extern void __next_free_mem_range(u64 *idx, int nid, phys_addr_t *out_start, + phys_addr_t *out_end, int *out_nid); + +/** + * for_each_free_mem_range - iterate through free memblock areas + * @i: u64 used as loop variable + * @nid: node selector, %MAX_NUMNODES for all nodes + * @p_start: ptr to phys_addr_t for start address of the range, can be %NULL + * @p_end: ptr to phys_addr_t for end address of the range, can be %NULL + * @p_nid: ptr to int for nid of the range, can be %NULL + * + * Walks over free (memory && !reserved) areas of memblock. Available as + * soon as memblock is initialized. + */ +#define for_each_free_mem_range(i, nid, p_start, p_end, p_nid) \ + for (i = 0, \ + __next_free_mem_range(&i, nid, p_start, p_end, p_nid); \ + i != (u64)ULLONG_MAX; \ + __next_free_mem_range(&i, nid, p_start, p_end, p_nid)) + +#ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP +extern int memblock_set_node(phys_addr_t base, phys_addr_t size, int nid); + +static inline void memblock_set_region_node(struct memblock_region *r, int nid) +{ + r->nid = nid; +} + +static inline int memblock_get_region_node(const struct memblock_region *r) +{ + return r->nid; +} +#else +static inline void memblock_set_region_node(struct memblock_region *r, int nid) +{ +} + +static inline int memblock_get_region_node(const struct memblock_region *r) +{ + return 0; +} +#endif /* CONFIG_HAVE_MEMBLOCK_NODE_MAP */ + /* The numa aware allocator is only available if * CONFIG_ARCH_POPULATES_NODE_MAP is set */ +extern phys_addr_t memblock_find_in_range_node(phys_addr_t start, + phys_addr_t end, + phys_addr_t size, + phys_addr_t align, int nid); extern phys_addr_t memblock_alloc_nid(phys_addr_t size, phys_addr_t align, int nid); extern phys_addr_t memblock_alloc_try_nid(phys_addr_t size, phys_addr_t align, @@ -90,11 +137,6 @@ extern int memblock_is_region_reserved(phys_addr_t base, phys_addr_t size); extern void memblock_dump_all(void); -/* Provided by the architecture */ -extern phys_addr_t memblock_nid_range(phys_addr_t start, phys_addr_t end, int *nid); -extern int memblock_memory_can_coalesce(phys_addr_t addr1, phys_addr_t size1, - phys_addr_t addr2, phys_addr_t size2); - /** * memblock_set_current_limit - Set the current allocation limit to allow * limiting allocations to what is currently @@ -154,9 +196,9 @@ static inline unsigned long memblock_region_reserved_end_pfn(const struct memblo region++) -#ifdef ARCH_DISCARD_MEMBLOCK -#define __init_memblock __init -#define __initdata_memblock __initdata +#ifdef CONFIG_ARCH_DISCARD_MEMBLOCK +#define __init_memblock __meminit +#define __initdata_memblock __meminitdata #else #define __init_memblock #define __initdata_memblock @@ -165,7 +207,7 @@ static inline unsigned long memblock_region_reserved_end_pfn(const struct memblo #else static inline phys_addr_t memblock_alloc(phys_addr_t size, phys_addr_t align) { - return MEMBLOCK_ERROR; + return 0; } #endif /* CONFIG_HAVE_MEMBLOCK */ diff --git a/include/linux/mm.h b/include/linux/mm.h index 3dc3a8c2c485..6b365aee8396 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1281,12 +1281,14 @@ extern void free_area_init_node(int nid, unsigned long * zones_size, * CONFIG_ARCH_POPULATES_NODE_MAP */ extern void free_area_init_nodes(unsigned long *max_zone_pfn); +#ifndef CONFIG_HAVE_MEMBLOCK_NODE_MAP extern void add_active_range(unsigned int nid, unsigned long start_pfn, unsigned long end_pfn); extern void remove_active_range(unsigned int nid, unsigned long start_pfn, unsigned long end_pfn); extern void remove_all_active_ranges(void); void sort_node_map(void); +#endif unsigned long node_map_pfn_alignment(void); unsigned long __absent_pages_in_range(int nid, unsigned long start_pfn, unsigned long end_pfn); @@ -1299,11 +1301,27 @@ extern void free_bootmem_with_active_regions(int nid, unsigned long max_low_pfn); int add_from_early_node_map(struct range *range, int az, int nr_range, int nid); -u64 __init find_memory_core_early(int nid, u64 size, u64 align, - u64 goal, u64 limit); -typedef int (*work_fn_t)(unsigned long, unsigned long, void *); -extern void work_with_active_regions(int nid, work_fn_t work_fn, void *data); extern void sparse_memory_present_with_active_regions(int nid); + +extern void __next_mem_pfn_range(int *idx, int nid, + unsigned long *out_start_pfn, + unsigned long *out_end_pfn, int *out_nid); + +/** + * for_each_mem_pfn_range - early memory pfn range iterator + * @i: an integer used as loop variable + * @nid: node selector, %MAX_NUMNODES for all nodes + * @p_start: ptr to ulong for start pfn of the range, can be %NULL + * @p_end: ptr to ulong for end pfn of the range, can be %NULL + * @p_nid: ptr to int for nid of the range, can be %NULL + * + * Walks over configured memory ranges. Available after early_node_map is + * populated. + */ +#define for_each_mem_pfn_range(i, nid, p_start, p_end, p_nid) \ + for (i = -1, __next_mem_pfn_range(&i, nid, p_start, p_end, p_nid); \ + i >= 0; __next_mem_pfn_range(&i, nid, p_start, p_end, p_nid)) + #endif /* CONFIG_ARCH_POPULATES_NODE_MAP */ #if !defined(CONFIG_ARCH_POPULATES_NODE_MAP) && \ diff --git a/kernel/printk.c b/kernel/printk.c index 1455a0d4eedd..baf2aebd6970 100644 --- a/kernel/printk.c +++ b/kernel/printk.c @@ -199,7 +199,7 @@ void __init setup_log_buf(int early) unsigned long mem; mem = memblock_alloc(new_log_buf_len, PAGE_SIZE); - if (mem == MEMBLOCK_ERROR) + if (!mem) return; new_log_buf = __va(mem); } else { diff --git a/mm/Kconfig b/mm/Kconfig index 011b110365c8..e338407f1225 100644 --- a/mm/Kconfig +++ b/mm/Kconfig @@ -131,6 +131,12 @@ config SPARSEMEM_VMEMMAP config HAVE_MEMBLOCK boolean +config HAVE_MEMBLOCK_NODE_MAP + boolean + +config ARCH_DISCARD_MEMBLOCK + boolean + config NO_BOOTMEM boolean diff --git a/mm/memblock.c b/mm/memblock.c index 84bec4969ed5..a57092f63a86 100644 --- a/mm/memblock.c +++ b/mm/memblock.c @@ -41,17 +41,6 @@ static inline const char *memblock_type_name(struct memblock_type *type) /* * Address comparison utilities */ - -static phys_addr_t __init_memblock memblock_align_down(phys_addr_t addr, phys_addr_t size) -{ - return addr & ~(size - 1); -} - -static phys_addr_t __init_memblock memblock_align_up(phys_addr_t addr, phys_addr_t size) -{ - return (addr + (size - 1)) & ~(size - 1); -} - static unsigned long __init_memblock memblock_addrs_overlap(phys_addr_t base1, phys_addr_t size1, phys_addr_t base2, phys_addr_t size2) { @@ -86,9 +75,9 @@ static phys_addr_t __init_memblock memblock_find_region(phys_addr_t start, phys_ /* In case, huge size is requested */ if (end < size) - return MEMBLOCK_ERROR; + return 0; - base = memblock_align_down((end - size), align); + base = round_down(end - size, align); /* Prevent allocations returning 0 as it's also used to * indicate an allocation failure @@ -103,14 +92,17 @@ static phys_addr_t __init_memblock memblock_find_region(phys_addr_t start, phys_ res_base = memblock.reserved.regions[j].base; if (res_base < size) break; - base = memblock_align_down(res_base - size, align); + base = round_down(res_base - size, align); } - return MEMBLOCK_ERROR; + return 0; } -static phys_addr_t __init_memblock memblock_find_base(phys_addr_t size, - phys_addr_t align, phys_addr_t start, phys_addr_t end) +/* + * Find a free area with specified alignment in a specific range. + */ +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) { long i; @@ -138,18 +130,10 @@ static phys_addr_t __init_memblock memblock_find_base(phys_addr_t size, if (bottom >= top) continue; found = memblock_find_region(bottom, top, size, align); - if (found != MEMBLOCK_ERROR) + if (found) return found; } - return MEMBLOCK_ERROR; -} - -/* - * Find a free area with specified alignment in a specific range. - */ -u64 __init_memblock memblock_find_in_range(u64 start, u64 end, u64 size, u64 align) -{ - return memblock_find_base(size, align, start, end); + return 0; } /* @@ -178,12 +162,8 @@ int __init_memblock memblock_reserve_reserved_regions(void) static void __init_memblock memblock_remove_region(struct memblock_type *type, unsigned long r) { - unsigned long i; - - for (i = r; i < type->cnt - 1; i++) { - type->regions[i].base = type->regions[i + 1].base; - type->regions[i].size = type->regions[i + 1].size; - } + memmove(&type->regions[r], &type->regions[r + 1], + (type->cnt - (r + 1)) * sizeof(type->regions[r])); type->cnt--; /* Special case for empty arrays */ @@ -191,6 +171,7 @@ static void __init_memblock memblock_remove_region(struct memblock_type *type, u type->cnt = 1; type->regions[0].base = 0; type->regions[0].size = 0; + memblock_set_region_node(&type->regions[0], MAX_NUMNODES); } } @@ -226,10 +207,10 @@ static int __init_memblock memblock_double_array(struct memblock_type *type) */ if (use_slab) { new_array = kmalloc(new_size, GFP_KERNEL); - addr = new_array == NULL ? MEMBLOCK_ERROR : __pa(new_array); + addr = new_array ? __pa(new_array) : 0; } else - addr = memblock_find_base(new_size, sizeof(phys_addr_t), 0, MEMBLOCK_ALLOC_ACCESSIBLE); - if (addr == MEMBLOCK_ERROR) { + addr = memblock_find_in_range(0, MEMBLOCK_ALLOC_ACCESSIBLE, new_size, sizeof(phys_addr_t)); + if (!addr) { 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; @@ -268,146 +249,147 @@ static int __init_memblock memblock_double_array(struct memblock_type *type) return 0; } -int __init_memblock __weak memblock_memory_can_coalesce(phys_addr_t addr1, phys_addr_t size1, - phys_addr_t addr2, phys_addr_t size2) +/** + * memblock_merge_regions - merge neighboring compatible regions + * @type: memblock type to scan + * + * Scan @type and merge neighboring compatible regions. + */ +static void __init_memblock memblock_merge_regions(struct memblock_type *type) { - return 1; + int i = 0; + + /* cnt never goes below 1 */ + while (i < type->cnt - 1) { + struct memblock_region *this = &type->regions[i]; + struct memblock_region *next = &type->regions[i + 1]; + + if (this->base + this->size != next->base || + memblock_get_region_node(this) != + memblock_get_region_node(next)) { + BUG_ON(this->base + this->size > next->base); + i++; + continue; + } + + this->size += next->size; + memmove(next, next + 1, (type->cnt - (i + 1)) * sizeof(*next)); + type->cnt--; + } } -static long __init_memblock memblock_add_region(struct memblock_type *type, - phys_addr_t base, phys_addr_t size) +/** + * memblock_insert_region - insert new memblock region + * @type: memblock type to insert into + * @idx: index for the insertion point + * @base: base address of the new region + * @size: size of the new region + * + * Insert new memblock region [@base,@base+@size) into @type at @idx. + * @type must already have extra room to accomodate the new region. + */ +static void __init_memblock memblock_insert_region(struct memblock_type *type, + int idx, phys_addr_t base, + phys_addr_t size, int nid) { - phys_addr_t end = base + size; - int i, slot = -1; - - /* First try and coalesce this MEMBLOCK with others */ - for (i = 0; i < type->cnt; i++) { - struct memblock_region *rgn = &type->regions[i]; - phys_addr_t rend = rgn->base + rgn->size; - - /* Exit if there's no possible hits */ - if (rgn->base > end || rgn->size == 0) - break; - - /* Check if we are fully enclosed within an existing - * block - */ - if (rgn->base <= base && rend >= end) - return 0; - - /* Check if we overlap or are adjacent with the bottom - * of a block. - */ - if (base < rgn->base && end >= rgn->base) { - /* If we can't coalesce, create a new block */ - if (!memblock_memory_can_coalesce(base, size, - rgn->base, - rgn->size)) { - /* Overlap & can't coalesce are mutually - * exclusive, if you do that, be prepared - * for trouble - */ - WARN_ON(end != rgn->base); - goto new_block; - } - /* We extend the bottom of the block down to our - * base - */ - rgn->base = base; - rgn->size = rend - base; - - /* Return if we have nothing else to allocate - * (fully coalesced) - */ - if (rend >= end) - return 0; + struct memblock_region *rgn = &type->regions[idx]; - /* We continue processing from the end of the - * coalesced block. - */ - base = rend; - size = end - base; - } + BUG_ON(type->cnt >= type->max); + memmove(rgn + 1, rgn, (type->cnt - idx) * sizeof(*rgn)); + rgn->base = base; + rgn->size = size; + memblock_set_region_node(rgn, nid); + type->cnt++; +} - /* Now check if we overlap or are adjacent with the - * top of a block - */ - if (base <= rend && end >= rend) { - /* If we can't coalesce, create a new block */ - if (!memblock_memory_can_coalesce(rgn->base, - rgn->size, - base, size)) { - /* Overlap & can't coalesce are mutually - * exclusive, if you do that, be prepared - * for trouble - */ - WARN_ON(rend != base); - goto new_block; - } - /* We adjust our base down to enclose the - * original block and destroy it. It will be - * part of our new allocation. Since we've - * freed an entry, we know we won't fail - * to allocate one later, so we won't risk - * losing the original block allocation. - */ - size += (base - rgn->base); - base = rgn->base; - memblock_remove_region(type, i--); - } - } +/** + * memblock_add_region - add new memblock region + * @type: memblock type to add new region into + * @base: base address of the new region + * @size: size of the new region + * + * Add new memblock region [@base,@base+@size) into @type. The new region + * is allowed to overlap with existing ones - overlaps don't affect already + * existing regions. @type is guaranteed to be minimal (all neighbouring + * compatible regions are merged) after the addition. + * + * RETURNS: + * 0 on success, -errno on failure. + */ +static long __init_memblock memblock_add_region(struct memblock_type *type, + phys_addr_t base, phys_addr_t size) +{ + bool insert = false; + phys_addr_t obase = base, end = base + size; + int i, nr_new; - /* If the array is empty, special case, replace the fake - * filler region and return - */ - if ((type->cnt == 1) && (type->regions[0].size == 0)) { + /* special case for empty array */ + if (type->regions[0].size == 0) { + WARN_ON(type->cnt != 1); type->regions[0].base = base; type->regions[0].size = size; + memblock_set_region_node(&type->regions[0], MAX_NUMNODES); return 0; } - - new_block: - /* 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. +repeat: + /* + * The following is executed twice. Once with %false @insert and + * then with %true. The first counts the number of regions needed + * to accomodate the new area. The second actually inserts them. */ - if (WARN_ON(type->cnt >= type->max)) - return -1; + base = obase; + nr_new = 0; - /* Couldn't coalesce the MEMBLOCK, so add it to the sorted table. */ - for (i = type->cnt - 1; i >= 0; i--) { - if (base < type->regions[i].base) { - type->regions[i+1].base = type->regions[i].base; - type->regions[i+1].size = type->regions[i].size; - } else { - type->regions[i+1].base = base; - type->regions[i+1].size = size; - slot = i + 1; + for (i = 0; i < type->cnt; i++) { + struct memblock_region *rgn = &type->regions[i]; + phys_addr_t rbase = rgn->base; + phys_addr_t rend = rbase + rgn->size; + + if (rbase >= end) break; + if (rend <= base) + continue; + /* + * @rgn overlaps. If it separates the lower part of new + * area, insert that portion. + */ + if (rbase > base) { + nr_new++; + if (insert) + memblock_insert_region(type, i++, base, + rbase - base, MAX_NUMNODES); } + /* area below @rend is dealt with, forget about it */ + base = min(rend, end); } - if (base < type->regions[0].base) { - type->regions[0].base = base; - type->regions[0].size = size; - slot = 0; + + /* insert the remaining portion */ + if (base < end) { + nr_new++; + if (insert) + memblock_insert_region(type, i, base, end - base, + MAX_NUMNODES); } - type->cnt++; - /* The array is full ? Try to resize it. If that fails, we undo - * our allocation and return an error + /* + * If this was the first round, resize array and repeat for actual + * insertions; otherwise, merge and return. */ - if (type->cnt == type->max && memblock_double_array(type)) { - BUG_ON(slot < 0); - memblock_remove_region(type, slot); - return -1; + if (!insert) { + while (type->cnt + nr_new > type->max) + if (memblock_double_array(type) < 0) + return -ENOMEM; + insert = true; + goto repeat; + } else { + memblock_merge_regions(type); + return 0; } - - return 0; } long __init_memblock memblock_add(phys_addr_t base, phys_addr_t size) { return memblock_add_region(&memblock.memory, base, size); - } static long __init_memblock __memblock_remove(struct memblock_type *type, @@ -468,6 +450,11 @@ long __init_memblock memblock_remove(phys_addr_t base, phys_addr_t size) long __init_memblock memblock_free(phys_addr_t base, phys_addr_t size) { + memblock_dbg(" memblock_free: [%#016llx-%#016llx] %pF\n", + (unsigned long long)base, + (unsigned long long)base + size, + (void *)_RET_IP_); + return __memblock_remove(&memblock.reserved, base, size); } @@ -475,11 +462,186 @@ long __init_memblock memblock_reserve(phys_addr_t base, phys_addr_t size) { struct memblock_type *_rgn = &memblock.reserved; + memblock_dbg("memblock_reserve: [%#016llx-%#016llx] %pF\n", + (unsigned long long)base, + (unsigned long long)base + size, + (void *)_RET_IP_); BUG_ON(0 == size); return memblock_add_region(_rgn, base, size); } +/** + * __next_free_mem_range - next function for for_each_free_mem_range() + * @idx: pointer to u64 loop variable + * @nid: nid: node selector, %MAX_NUMNODES for all nodes + * @p_start: ptr to phys_addr_t for start address of the range, can be %NULL + * @p_end: ptr to phys_addr_t for end address of the range, can be %NULL + * @p_nid: ptr to int for nid of the range, can be %NULL + * + * Find the first free area from *@idx which matches @nid, fill the out + * parameters, and update *@idx for the next iteration. The lower 32bit of + * *@idx contains index into memory region and the upper 32bit indexes the + * areas before each reserved region. For example, if reserved regions + * look like the following, + * + * 0:[0-16), 1:[32-48), 2:[128-130) + * + * The upper 32bit indexes the following regions. + * + * 0:[0-0), 1:[16-32), 2:[48-128), 3:[130-MAX) + * + * As both region arrays are sorted, the function advances the two indices + * in lockstep and returns each intersection. + */ +void __init_memblock __next_free_mem_range(u64 *idx, int nid, + phys_addr_t *out_start, + phys_addr_t *out_end, int *out_nid) +{ + struct memblock_type *mem = &memblock.memory; + struct memblock_type *rsv = &memblock.reserved; + int mi = *idx & 0xffffffff; + int ri = *idx >> 32; + + for ( ; mi < mem->cnt; mi++) { + struct memblock_region *m = &mem->regions[mi]; + phys_addr_t m_start = m->base; + phys_addr_t m_end = m->base + m->size; + + /* only memory regions are associated with nodes, check it */ + if (nid != MAX_NUMNODES && nid != memblock_get_region_node(m)) + continue; + + /* scan areas before each reservation for intersection */ + for ( ; ri < rsv->cnt + 1; ri++) { + struct memblock_region *r = &rsv->regions[ri]; + phys_addr_t r_start = ri ? r[-1].base + r[-1].size : 0; + phys_addr_t r_end = ri < rsv->cnt ? r->base : ULLONG_MAX; + + /* if ri advanced past mi, break out to advance mi */ + if (r_start >= m_end) + break; + /* if the two regions intersect, we're done */ + if (m_start < r_end) { + if (out_start) + *out_start = max(m_start, r_start); + if (out_end) + *out_end = min(m_end, r_end); + if (out_nid) + *out_nid = memblock_get_region_node(m); + /* + * The region which ends first is advanced + * for the next iteration. + */ + if (m_end <= r_end) + mi++; + else + ri++; + *idx = (u32)mi | (u64)ri << 32; + return; + } + } + } + + /* signal end of iteration */ + *idx = ULLONG_MAX; +} + +#ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP +/* + * Common iterator interface used to define for_each_mem_range(). + */ +void __init_memblock __next_mem_pfn_range(int *idx, int nid, + unsigned long *out_start_pfn, + unsigned long *out_end_pfn, int *out_nid) +{ + struct memblock_type *type = &memblock.memory; + struct memblock_region *r; + + while (++*idx < type->cnt) { + r = &type->regions[*idx]; + + if (PFN_UP(r->base) >= PFN_DOWN(r->base + r->size)) + continue; + if (nid == MAX_NUMNODES || nid == r->nid) + break; + } + if (*idx >= type->cnt) { + *idx = -1; + return; + } + + if (out_start_pfn) + *out_start_pfn = PFN_UP(r->base); + if (out_end_pfn) + *out_end_pfn = PFN_DOWN(r->base + r->size); + if (out_nid) + *out_nid = r->nid; +} + +/** + * memblock_set_node - set node ID on memblock regions + * @base: base of area to set node ID for + * @size: size of area to set node ID for + * @nid: node ID to set + * + * Set the nid of memblock memory regions in [@base,@base+@size) to @nid. + * Regions which cross the area boundaries are split as necessary. + * + * RETURNS: + * 0 on success, -errno on failure. + */ +int __init_memblock memblock_set_node(phys_addr_t base, phys_addr_t size, + int nid) +{ + struct memblock_type *type = &memblock.memory; + phys_addr_t end = base + size; + int i; + + /* we'll create at most two more regions */ + while (type->cnt + 2 > type->max) + if (memblock_double_array(type) < 0) + return -ENOMEM; + + for (i = 0; i < type->cnt; i++) { + struct memblock_region *rgn = &type->regions[i]; + phys_addr_t rbase = rgn->base; + phys_addr_t rend = rbase + rgn->size; + + if (rbase >= end) + break; + if (rend <= base) + continue; + + if (rbase < base) { + /* + * @rgn intersects from below. Split and continue + * to process the next region - the new top half. + */ + rgn->base = base; + rgn->size = rend - rgn->base; + memblock_insert_region(type, i, rbase, base - rbase, + rgn->nid); + } else if (rend > end) { + /* + * @rgn intersects from above. Split and redo the + * current region - the new bottom half. + */ + rgn->base = end; + rgn->size = rend - rgn->base; + memblock_insert_region(type, i--, rbase, end - rbase, + rgn->nid); + } else { + /* @rgn is fully contained, set ->nid */ + rgn->nid = nid; + } + } + + memblock_merge_regions(type); + return 0; +} +#endif /* CONFIG_HAVE_MEMBLOCK_NODE_MAP */ + phys_addr_t __init __memblock_alloc_base(phys_addr_t size, phys_addr_t align, phys_addr_t max_addr) { phys_addr_t found; @@ -487,11 +649,10 @@ phys_addr_t __init __memblock_alloc_base(phys_addr_t size, phys_addr_t align, ph /* 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); + size = round_up(size, align); - found = memblock_find_base(size, align, 0, max_addr); - if (found != MEMBLOCK_ERROR && - !memblock_add_region(&memblock.reserved, found, size)) + found = memblock_find_in_range(0, max_addr, size, align); + if (found && !memblock_add_region(&memblock.reserved, found, size)) return found; return 0; @@ -517,92 +678,78 @@ phys_addr_t __init memblock_alloc(phys_addr_t size, phys_addr_t align) /* - * 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 + * Additional node-local top-down allocators. * * 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) +static phys_addr_t __init memblock_nid_range_rev(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)); - } + for_each_mem_pfn_range(i, MAX_NUMNODES, &start_pfn, &end_pfn, nid) + if (end > PFN_PHYS(start_pfn) && end <= PFN_PHYS(end_pfn)) + return max(start, PFN_PHYS(start_pfn)); #endif *nid = 0; - - return end; + return start; } -static phys_addr_t __init memblock_alloc_nid_region(struct memblock_region *mp, +phys_addr_t __init memblock_find_in_range_node(phys_addr_t start, + phys_addr_t end, phys_addr_t size, phys_addr_t align, int nid) { - phys_addr_t start, end; + struct memblock_type *mem = &memblock.memory; + int i; + + BUG_ON(0 == size); + + /* Pump up max_addr */ + if (end == MEMBLOCK_ALLOC_ACCESSIBLE) + end = memblock.current_limit; - start = mp->base; - end = start + mp->size; + for (i = mem->cnt - 1; i >= 0; i--) { + struct memblock_region *r = &mem->regions[i]; + phys_addr_t base = max(start, r->base); + phys_addr_t top = min(end, r->base + r->size); - start = memblock_align_up(start, align); - while (start < end) { - phys_addr_t this_end; - int this_nid; + while (base < top) { + phys_addr_t tbase, ret; + int tnid; - this_end = memblock_nid_range(start, end, &this_nid); - if (this_nid == nid) { - phys_addr_t ret = memblock_find_region(start, this_end, size, align); - if (ret != MEMBLOCK_ERROR && - !memblock_add_region(&memblock.reserved, ret, size)) - return ret; + tbase = memblock_nid_range_rev(base, top, &tnid); + if (nid == MAX_NUMNODES || tnid == nid) { + ret = memblock_find_region(tbase, top, size, align); + if (ret) + return ret; + } + top = tbase; } - start = this_end; } - return MEMBLOCK_ERROR; + return 0; } phys_addr_t __init memblock_alloc_nid(phys_addr_t size, phys_addr_t align, int nid) { - struct memblock_type *mem = &memblock.memory; - int i; - - BUG_ON(0 == size); + phys_addr_t found; - /* We align the size to limit fragmentation. Without this, a lot of + /* + * 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); + size = round_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 - */ - for (i = 0; i < mem->cnt; i++) { - phys_addr_t ret = memblock_alloc_nid_region(&mem->regions[i], - size, align, nid); - if (ret != MEMBLOCK_ERROR) - return ret; - } + found = memblock_find_in_range_node(0, MEMBLOCK_ALLOC_ACCESSIBLE, + size, align, nid); + if (found && !memblock_add_region(&memblock.reserved, found, size)) + return found; return 0; } @@ -613,7 +760,7 @@ phys_addr_t __init memblock_alloc_try_nid(phys_addr_t size, phys_addr_t align, i if (res) return res; - return memblock_alloc_base(size, align, MEMBLOCK_ALLOC_ANYWHERE); + return memblock_alloc_base(size, align, MEMBLOCK_ALLOC_ACCESSIBLE); } @@ -731,19 +878,26 @@ void __init_memblock memblock_set_current_limit(phys_addr_t limit) memblock.current_limit = limit; } -static void __init_memblock memblock_dump(struct memblock_type *region, char *name) +static void __init_memblock memblock_dump(struct memblock_type *type, 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.cnt = 0x%lx\n", name, type->cnt); - pr_info(" %s[%#x]\t[%#016llx-%#016llx], %#llx bytes\n", - name, i, base, base + size - 1, size); + for (i = 0; i < type->cnt; i++) { + struct memblock_region *rgn = &type->regions[i]; + char nid_buf[32] = ""; + + base = rgn->base; + size = rgn->size; +#ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP + if (memblock_get_region_node(rgn) != MAX_NUMNODES) + snprintf(nid_buf, sizeof(nid_buf), " on node %d", + memblock_get_region_node(rgn)); +#endif + pr_info(" %s[%#x]\t[%#016llx-%#016llx], %#llx bytes%s\n", + name, i, base, base + size - 1, size, nid_buf); } } @@ -801,11 +955,13 @@ void __init memblock_init(void) */ memblock.memory.regions[0].base = 0; memblock.memory.regions[0].size = 0; + memblock_set_region_node(&memblock.memory.regions[0], MAX_NUMNODES); memblock.memory.cnt = 1; /* Ditto. */ memblock.reserved.regions[0].base = 0; memblock.reserved.regions[0].size = 0; + memblock_set_region_node(&memblock.reserved.regions[0], MAX_NUMNODES); memblock.reserved.cnt = 1; memblock.current_limit = MEMBLOCK_ALLOC_ANYWHERE; @@ -819,7 +975,7 @@ static int __init early_memblock(char *p) } early_param("memblock", early_memblock); -#if defined(CONFIG_DEBUG_FS) && !defined(ARCH_DISCARD_MEMBLOCK) +#if defined(CONFIG_DEBUG_FS) && !defined(CONFIG_ARCH_DISCARD_MEMBLOCK) static int memblock_debug_show(struct seq_file *m, void *private) { diff --git a/mm/nobootmem.c b/mm/nobootmem.c index 7fa41b4a07bf..24f0fc1a56d6 100644 --- a/mm/nobootmem.c +++ b/mm/nobootmem.c @@ -41,14 +41,13 @@ static void * __init __alloc_memory_core_early(int nid, u64 size, u64 align, if (limit > memblock.current_limit) limit = memblock.current_limit; - addr = find_memory_core_early(nid, size, align, goal, limit); - - if (addr == MEMBLOCK_ERROR) + addr = memblock_find_in_range_node(goal, limit, size, align, nid); + if (!addr) return NULL; ptr = phys_to_virt(addr); memset(ptr, 0, size); - memblock_x86_reserve_range(addr, addr + size, "BOOTMEM"); + memblock_reserve(addr, size); /* * The min_count is set to 0 so that bootmem allocated blocks * are never reported as leaks. @@ -107,23 +106,27 @@ static void __init __free_pages_memory(unsigned long start, unsigned long end) __free_pages_bootmem(pfn_to_page(i), 0); } -unsigned long __init free_all_memory_core_early(int nodeid) +unsigned long __init free_low_memory_core_early(int nodeid) { - int i; - u64 start, end; unsigned long count = 0; - struct range *range = NULL; - int nr_range; - - nr_range = get_free_all_memory_range(&range, nodeid); - - for (i = 0; i < nr_range; i++) { - start = range[i].start; - end = range[i].end; - count += end - start; - __free_pages_memory(start, end); + phys_addr_t start, end; + u64 i; + + /* free reserved array temporarily so that it's treated as free area */ + memblock_free_reserved_regions(); + + for_each_free_mem_range(i, MAX_NUMNODES, &start, &end, NULL) { + 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) { + __free_pages_memory(start_pfn, end_pfn); + count += end_pfn - start_pfn; + } } + /* put region array back? */ + memblock_reserve_reserved_regions(); return count; } @@ -137,7 +140,7 @@ unsigned long __init free_all_bootmem_node(pg_data_t *pgdat) { register_page_bootmem_info_node(pgdat); - /* free_all_memory_core_early(MAX_NUMNODES) will be called later */ + /* free_low_memory_core_early(MAX_NUMNODES) will be called later */ return 0; } @@ -155,7 +158,7 @@ unsigned long __init free_all_bootmem(void) * Use MAX_NUMNODES will make sure all ranges in early_node_map[] * will be used instead of only Node0 related */ - return free_all_memory_core_early(MAX_NUMNODES); + return free_low_memory_core_early(MAX_NUMNODES); } /** @@ -172,7 +175,7 @@ void __init free_bootmem_node(pg_data_t *pgdat, unsigned long physaddr, unsigned long size) { kmemleak_free_part(__va(physaddr), size); - memblock_x86_free_range(physaddr, physaddr + size); + memblock_free(physaddr, size); } /** @@ -187,7 +190,7 @@ void __init free_bootmem_node(pg_data_t *pgdat, unsigned long physaddr, void __init free_bootmem(unsigned long addr, unsigned long size) { kmemleak_free_part(__va(addr), size); - memblock_x86_free_range(addr, addr + size); + memblock_free(addr, size); } static void * __init ___alloc_bootmem_nopanic(unsigned long size, diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 9dd443d89d8b..6ce27331834c 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -182,28 +182,31 @@ static unsigned long __meminitdata nr_all_pages; static unsigned long __meminitdata dma_reserve; #ifdef CONFIG_ARCH_POPULATES_NODE_MAP - /* - * MAX_ACTIVE_REGIONS determines the maximum number of distinct - * ranges of memory (RAM) that may be registered with add_active_range(). - * Ranges passed to add_active_range() will be merged if possible - * so the number of times add_active_range() can be called is - * related to the number of nodes and the number of holes - */ - #ifdef CONFIG_MAX_ACTIVE_REGIONS - /* Allow an architecture to set MAX_ACTIVE_REGIONS to save memory */ - #define MAX_ACTIVE_REGIONS CONFIG_MAX_ACTIVE_REGIONS - #else - #if MAX_NUMNODES >= 32 - /* If there can be many nodes, allow up to 50 holes per node */ - #define MAX_ACTIVE_REGIONS (MAX_NUMNODES*50) + #ifndef CONFIG_HAVE_MEMBLOCK_NODE_MAP + /* + * MAX_ACTIVE_REGIONS determines the maximum number of distinct ranges + * of memory (RAM) that may be registered with add_active_range(). + * Ranges passed to add_active_range() will be merged if possible so + * the number of times add_active_range() can be called is related to + * the number of nodes and the number of holes + */ + #ifdef CONFIG_MAX_ACTIVE_REGIONS + /* Allow an architecture to set MAX_ACTIVE_REGIONS to save memory */ + #define MAX_ACTIVE_REGIONS CONFIG_MAX_ACTIVE_REGIONS #else - /* By default, allow up to 256 distinct regions */ - #define MAX_ACTIVE_REGIONS 256 + #if MAX_NUMNODES >= 32 + /* If there can be many nodes, allow up to 50 holes per node */ + #define MAX_ACTIVE_REGIONS (MAX_NUMNODES*50) + #else + /* By default, allow up to 256 distinct regions */ + #define MAX_ACTIVE_REGIONS 256 + #endif #endif - #endif - static struct node_active_region __meminitdata early_node_map[MAX_ACTIVE_REGIONS]; - static int __meminitdata nr_nodemap_entries; + static struct node_active_region __meminitdata early_node_map[MAX_ACTIVE_REGIONS]; + static int __meminitdata nr_nodemap_entries; +#endif /* !CONFIG_HAVE_MEMBLOCK_NODE_MAP */ + static unsigned long __meminitdata arch_zone_lowest_possible_pfn[MAX_NR_ZONES]; static unsigned long __meminitdata arch_zone_highest_possible_pfn[MAX_NR_ZONES]; static unsigned long __initdata required_kernelcore; @@ -706,10 +709,10 @@ void __meminit __free_pages_bootmem(struct page *page, unsigned int order) int loop; prefetchw(page); - for (loop = 0; loop < BITS_PER_LONG; loop++) { + for (loop = 0; loop < (1 << order); loop++) { struct page *p = &page[loop]; - if (loop + 1 < BITS_PER_LONG) + if (loop + 1 < (1 << order)) prefetchw(p + 1); __ClearPageReserved(p); set_page_count(p, 0); @@ -3732,34 +3735,6 @@ __meminit int init_currently_empty_zone(struct zone *zone, } #ifdef CONFIG_ARCH_POPULATES_NODE_MAP -/* - * Basic iterator support. Return the first range of PFNs for a node - * Note: nid == MAX_NUMNODES returns first region regardless of node - */ -static int __meminit first_active_region_index_in_nid(int nid) -{ - int i; - - for (i = 0; i < nr_nodemap_entries; i++) - if (nid == MAX_NUMNODES || early_node_map[i].nid == nid) - return i; - - return -1; -} - -/* - * Basic iterator support. Return the next active range of PFNs for a node - * Note: nid == MAX_NUMNODES returns next region regardless of node - */ -static int __meminit next_active_region_index_in_nid(int index, int nid) -{ - for (index = index + 1; index < nr_nodemap_entries; index++) - if (nid == MAX_NUMNODES || early_node_map[index].nid == nid) - return index; - - return -1; -} - #ifndef CONFIG_HAVE_ARCH_EARLY_PFN_TO_NID /* * Required by SPARSEMEM. Given a PFN, return what node the PFN is on. @@ -3769,15 +3744,12 @@ static int __meminit next_active_region_index_in_nid(int index, int nid) */ int __meminit __early_pfn_to_nid(unsigned long pfn) { - int i; - - for (i = 0; i < nr_nodemap_entries; i++) { - unsigned long start_pfn = early_node_map[i].start_pfn; - unsigned long end_pfn = early_node_map[i].end_pfn; + unsigned long start_pfn, end_pfn; + int i, nid; + for_each_mem_pfn_range(i, MAX_NUMNODES, &start_pfn, &end_pfn, &nid) if (start_pfn <= pfn && pfn < end_pfn) - return early_node_map[i].nid; - } + return nid; /* This is a memory hole */ return -1; } @@ -3806,11 +3778,6 @@ bool __meminit early_pfn_in_nid(unsigned long pfn, int node) } #endif -/* Basic iterator support to walk early_node_map[] */ -#define for_each_active_range_index_in_nid(i, nid) \ - for (i = first_active_region_index_in_nid(nid); i != -1; \ - i = next_active_region_index_in_nid(i, nid)) - /** * free_bootmem_with_active_regions - Call free_bootmem_node for each active range * @nid: The node to free memory on. If MAX_NUMNODES, all nodes are freed. @@ -3820,122 +3787,34 @@ bool __meminit early_pfn_in_nid(unsigned long pfn, int node) * add_active_ranges() contain no holes and may be freed, this * this function may be used instead of calling free_bootmem() manually. */ -void __init free_bootmem_with_active_regions(int nid, - unsigned long max_low_pfn) +void __init free_bootmem_with_active_regions(int nid, unsigned long max_low_pfn) { - int i; - - for_each_active_range_index_in_nid(i, nid) { - unsigned long size_pages = 0; - unsigned long end_pfn = early_node_map[i].end_pfn; - - if (early_node_map[i].start_pfn >= max_low_pfn) - continue; + unsigned long start_pfn, end_pfn; + int i, this_nid; - if (end_pfn > max_low_pfn) - end_pfn = max_low_pfn; + for_each_mem_pfn_range(i, nid, &start_pfn, &end_pfn, &this_nid) { + start_pfn = min(start_pfn, max_low_pfn); + end_pfn = min(end_pfn, max_low_pfn); - size_pages = end_pfn - early_node_map[i].start_pfn; - free_bootmem_node(NODE_DATA(early_node_map[i].nid), - PFN_PHYS(early_node_map[i].start_pfn), - size_pages << PAGE_SHIFT); + if (start_pfn < end_pfn) + free_bootmem_node(NODE_DATA(this_nid), + PFN_PHYS(start_pfn), + (end_pfn - start_pfn) << PAGE_SHIFT); } } -#ifdef CONFIG_HAVE_MEMBLOCK -/* - * Basic iterator support. Return the last range of PFNs for a node - * Note: nid == MAX_NUMNODES returns last region regardless of node - */ -static int __meminit last_active_region_index_in_nid(int nid) -{ - int i; - - for (i = nr_nodemap_entries - 1; i >= 0; i--) - if (nid == MAX_NUMNODES || early_node_map[i].nid == nid) - return i; - - return -1; -} - -/* - * Basic iterator support. Return the previous active range of PFNs for a node - * Note: nid == MAX_NUMNODES returns next region regardless of node - */ -static int __meminit previous_active_region_index_in_nid(int index, int nid) -{ - for (index = index - 1; index >= 0; index--) - if (nid == MAX_NUMNODES || early_node_map[index].nid == nid) - return index; - - return -1; -} - -#define for_each_active_range_index_in_nid_reverse(i, nid) \ - for (i = last_active_region_index_in_nid(nid); i != -1; \ - i = previous_active_region_index_in_nid(i, nid)) - -u64 __init find_memory_core_early(int nid, u64 size, u64 align, - u64 goal, u64 limit) -{ - int i; - - /* Need to go over early_node_map to find out good range for node */ - for_each_active_range_index_in_nid_reverse(i, nid) { - u64 addr; - u64 ei_start, ei_last; - u64 final_start, final_end; - - ei_last = early_node_map[i].end_pfn; - ei_last <<= PAGE_SHIFT; - ei_start = early_node_map[i].start_pfn; - ei_start <<= PAGE_SHIFT; - - final_start = max(ei_start, goal); - final_end = min(ei_last, limit); - - if (final_start >= final_end) - continue; - - addr = memblock_find_in_range(final_start, final_end, size, align); - - if (addr == MEMBLOCK_ERROR) - continue; - - return addr; - } - - return MEMBLOCK_ERROR; -} -#endif - int __init add_from_early_node_map(struct range *range, int az, int nr_range, int nid) { + unsigned long start_pfn, end_pfn; int i; - u64 start, end; /* need to go over early_node_map to find out good range for node */ - for_each_active_range_index_in_nid(i, nid) { - start = early_node_map[i].start_pfn; - end = early_node_map[i].end_pfn; - nr_range = add_range(range, az, nr_range, start, end); - } + for_each_mem_pfn_range(i, nid, &start_pfn, &end_pfn, NULL) + nr_range = add_range(range, az, nr_range, start_pfn, end_pfn); return nr_range; } -void __init work_with_active_regions(int nid, work_fn_t work_fn, void *data) -{ - int i; - int ret; - - for_each_active_range_index_in_nid(i, nid) { - ret = work_fn(early_node_map[i].start_pfn, - early_node_map[i].end_pfn, data); - if (ret) - break; - } -} /** * sparse_memory_present_with_active_regions - Call memory_present for each active range * @nid: The node to call memory_present for. If MAX_NUMNODES, all nodes will be used. @@ -3946,12 +3825,11 @@ void __init work_with_active_regions(int nid, work_fn_t work_fn, void *data) */ void __init sparse_memory_present_with_active_regions(int nid) { - int i; + unsigned long start_pfn, end_pfn; + int i, this_nid; - for_each_active_range_index_in_nid(i, nid) - memory_present(early_node_map[i].nid, - early_node_map[i].start_pfn, - early_node_map[i].end_pfn); + for_each_mem_pfn_range(i, nid, &start_pfn, &end_pfn, &this_nid) + memory_present(this_nid, start_pfn, end_pfn); } /** @@ -3968,13 +3846,15 @@ void __init sparse_memory_present_with_active_regions(int nid) void __meminit get_pfn_range_for_nid(unsigned int nid, unsigned long *start_pfn, unsigned long *end_pfn) { + unsigned long this_start_pfn, this_end_pfn; int i; + *start_pfn = -1UL; *end_pfn = 0; - for_each_active_range_index_in_nid(i, nid) { - *start_pfn = min(*start_pfn, early_node_map[i].start_pfn); - *end_pfn = max(*end_pfn, early_node_map[i].end_pfn); + for_each_mem_pfn_range(i, nid, &this_start_pfn, &this_end_pfn, NULL) { + *start_pfn = min(*start_pfn, this_start_pfn); + *end_pfn = max(*end_pfn, this_end_pfn); } if (*start_pfn == -1UL) @@ -4077,46 +3957,16 @@ unsigned long __meminit __absent_pages_in_range(int nid, unsigned long range_start_pfn, unsigned long range_end_pfn) { - int i = 0; - unsigned long prev_end_pfn = 0, hole_pages = 0; - unsigned long start_pfn; - - /* Find the end_pfn of the first active range of pfns in the node */ - i = first_active_region_index_in_nid(nid); - if (i == -1) - return 0; - - prev_end_pfn = min(early_node_map[i].start_pfn, range_end_pfn); - - /* Account for ranges before physical memory on this node */ - if (early_node_map[i].start_pfn > range_start_pfn) - hole_pages = prev_end_pfn - range_start_pfn; - - /* Find all holes for the zone within the node */ - for (; i != -1; i = next_active_region_index_in_nid(i, nid)) { - - /* No need to continue if prev_end_pfn is outside the zone */ - if (prev_end_pfn >= range_end_pfn) - break; - - /* Make sure the end of the zone is not within the hole */ - start_pfn = min(early_node_map[i].start_pfn, range_end_pfn); - prev_end_pfn = max(prev_end_pfn, range_start_pfn); + unsigned long nr_absent = range_end_pfn - range_start_pfn; + unsigned long start_pfn, end_pfn; + int i; - /* Update the hole size cound and move on */ - if (start_pfn > range_start_pfn) { - BUG_ON(prev_end_pfn > start_pfn); - hole_pages += start_pfn - prev_end_pfn; - } - prev_end_pfn = early_node_map[i].end_pfn; + for_each_mem_pfn_range(i, nid, &start_pfn, &end_pfn, NULL) { + start_pfn = clamp(start_pfn, range_start_pfn, range_end_pfn); + end_pfn = clamp(end_pfn, range_start_pfn, range_end_pfn); + nr_absent -= end_pfn - start_pfn; } - - /* Account for ranges past physical memory on this node */ - if (range_end_pfn > prev_end_pfn) - hole_pages += range_end_pfn - - max(range_start_pfn, prev_end_pfn); - - return hole_pages; + return nr_absent; } /** @@ -4137,14 +3987,14 @@ static unsigned long __meminit zone_absent_pages_in_node(int nid, unsigned long zone_type, unsigned long *ignored) { + unsigned long zone_low = arch_zone_lowest_possible_pfn[zone_type]; + unsigned long zone_high = arch_zone_highest_possible_pfn[zone_type]; unsigned long node_start_pfn, node_end_pfn; unsigned long zone_start_pfn, zone_end_pfn; get_pfn_range_for_nid(nid, &node_start_pfn, &node_end_pfn); - zone_start_pfn = max(arch_zone_lowest_possible_pfn[zone_type], - node_start_pfn); - zone_end_pfn = min(arch_zone_highest_possible_pfn[zone_type], - node_end_pfn); + zone_start_pfn = clamp(node_start_pfn, zone_low, zone_high); + zone_end_pfn = clamp(node_end_pfn, zone_low, zone_high); adjust_zone_range_for_zone_movable(nid, zone_type, node_start_pfn, node_end_pfn, @@ -4442,6 +4292,35 @@ static inline void setup_nr_node_ids(void) } #endif +#ifndef CONFIG_HAVE_MEMBLOCK_NODE_MAP +/* + * Common iterator interface used to define for_each_mem_pfn_range(). + */ +void __meminit __next_mem_pfn_range(int *idx, int nid, + unsigned long *out_start_pfn, + unsigned long *out_end_pfn, int *out_nid) +{ + struct node_active_region *r = NULL; + + while (++*idx < nr_nodemap_entries) { + if (nid == MAX_NUMNODES || nid == early_node_map[*idx].nid) { + r = &early_node_map[*idx]; + break; + } + } + if (!r) { + *idx = -1; + return; + } + + if (out_start_pfn) + *out_start_pfn = r->start_pfn; + if (out_end_pfn) + *out_end_pfn = r->end_pfn; + if (out_nid) + *out_nid = r->nid; +} + /** * add_active_range - Register a range of PFNs backed by physical memory * @nid: The node ID the range resides on @@ -4519,6 +4398,7 @@ void __init add_active_range(unsigned int nid, unsigned long start_pfn, void __init remove_active_range(unsigned int nid, unsigned long start_pfn, unsigned long end_pfn) { + unsigned long this_start_pfn, this_end_pfn; int i, j; int removed = 0; @@ -4526,26 +4406,22 @@ void __init remove_active_range(unsigned int nid, unsigned long start_pfn, nid, start_pfn, end_pfn); /* Find the old active region end and shrink */ - for_each_active_range_index_in_nid(i, nid) { - if (early_node_map[i].start_pfn >= start_pfn && - early_node_map[i].end_pfn <= end_pfn) { + for_each_mem_pfn_range(i, nid, &this_start_pfn, &this_end_pfn, NULL) { + if (this_start_pfn >= start_pfn && this_end_pfn <= end_pfn) { /* clear it */ early_node_map[i].start_pfn = 0; early_node_map[i].end_pfn = 0; removed = 1; continue; } - if (early_node_map[i].start_pfn < start_pfn && - early_node_map[i].end_pfn > start_pfn) { - unsigned long temp_end_pfn = early_node_map[i].end_pfn; + if (this_start_pfn < start_pfn && this_end_pfn > start_pfn) { early_node_map[i].end_pfn = start_pfn; - if (temp_end_pfn > end_pfn) - add_active_range(nid, end_pfn, temp_end_pfn); + if (this_end_pfn > end_pfn) + add_active_range(nid, end_pfn, this_end_pfn); continue; } - if (early_node_map[i].start_pfn >= start_pfn && - early_node_map[i].end_pfn > end_pfn && - early_node_map[i].start_pfn < end_pfn) { + if (this_start_pfn >= start_pfn && this_end_pfn > end_pfn && + this_start_pfn < end_pfn) { early_node_map[i].start_pfn = end_pfn; continue; } @@ -4605,6 +4481,11 @@ void __init sort_node_map(void) sizeof(struct node_active_region), cmp_node_active_region, NULL); } +#else /* !CONFIG_HAVE_MEMBLOCK_NODE_MAP */ +static inline void sort_node_map(void) +{ +} +#endif /** * node_map_pfn_alignment - determine the maximum internode alignment @@ -4628,15 +4509,11 @@ void __init sort_node_map(void) unsigned long __init node_map_pfn_alignment(void) { unsigned long accl_mask = 0, last_end = 0; + unsigned long start, end, mask; int last_nid = -1; - int i; - - for_each_active_range_index_in_nid(i, MAX_NUMNODES) { - int nid = early_node_map[i].nid; - unsigned long start = early_node_map[i].start_pfn; - unsigned long end = early_node_map[i].end_pfn; - unsigned long mask; + int i, nid; + for_each_mem_pfn_range(i, MAX_NUMNODES, &start, &end, &nid) { if (!start || last_nid < 0 || last_nid == nid) { last_nid = nid; last_end = end; @@ -4663,12 +4540,12 @@ unsigned long __init node_map_pfn_alignment(void) /* Find the lowest pfn for a node */ static unsigned long __init find_min_pfn_for_node(int nid) { - int i; unsigned long min_pfn = ULONG_MAX; + unsigned long start_pfn; + int i; - /* Assuming a sorted map, the first range found has the starting pfn */ - for_each_active_range_index_in_nid(i, nid) - min_pfn = min(min_pfn, early_node_map[i].start_pfn); + for_each_mem_pfn_range(i, nid, &start_pfn, NULL, NULL) + min_pfn = min(min_pfn, start_pfn); if (min_pfn == ULONG_MAX) { printk(KERN_WARNING @@ -4697,15 +4574,16 @@ unsigned long __init find_min_pfn_with_active_regions(void) */ static unsigned long __init early_calculate_totalpages(void) { - int i; unsigned long totalpages = 0; + unsigned long start_pfn, end_pfn; + int i, nid; + + for_each_mem_pfn_range(i, MAX_NUMNODES, &start_pfn, &end_pfn, &nid) { + unsigned long pages = end_pfn - start_pfn; - for (i = 0; i < nr_nodemap_entries; i++) { - unsigned long pages = early_node_map[i].end_pfn - - early_node_map[i].start_pfn; totalpages += pages; if (pages) - node_set_state(early_node_map[i].nid, N_HIGH_MEMORY); + node_set_state(nid, N_HIGH_MEMORY); } return totalpages; } @@ -4760,6 +4638,8 @@ restart: /* Spread kernelcore memory as evenly as possible throughout nodes */ kernelcore_node = required_kernelcore / usable_nodes; for_each_node_state(nid, N_HIGH_MEMORY) { + unsigned long start_pfn, end_pfn; + /* * Recalculate kernelcore_node if the division per node * now exceeds what is necessary to satisfy the requested @@ -4776,13 +4656,10 @@ restart: kernelcore_remaining = kernelcore_node; /* Go through each range of PFNs within this node */ - for_each_active_range_index_in_nid(i, nid) { - unsigned long start_pfn, end_pfn; + for_each_mem_pfn_range(i, nid, &start_pfn, &end_pfn, NULL) { unsigned long size_pages; - start_pfn = max(early_node_map[i].start_pfn, - zone_movable_pfn[nid]); - end_pfn = early_node_map[i].end_pfn; + start_pfn = max(start_pfn, zone_movable_pfn[nid]); if (start_pfn >= end_pfn) continue; @@ -4884,8 +4761,8 @@ static void check_for_regular_memory(pg_data_t *pgdat) */ void __init free_area_init_nodes(unsigned long *max_zone_pfn) { - unsigned long nid; - int i; + unsigned long start_pfn, end_pfn; + int i, nid; /* Sort early_node_map as initialisation assumes it is sorted */ sort_node_map(); @@ -4935,11 +4812,9 @@ void __init free_area_init_nodes(unsigned long *max_zone_pfn) } /* Print out the early_node_map[] */ - printk("early_node_map[%d] active PFN ranges\n", nr_nodemap_entries); - for (i = 0; i < nr_nodemap_entries; i++) - printk(" %3d: %0#10lx -> %0#10lx\n", early_node_map[i].nid, - early_node_map[i].start_pfn, - early_node_map[i].end_pfn); + printk("Early memory PFN ranges\n"); + for_each_mem_pfn_range(i, MAX_NUMNODES, &start_pfn, &end_pfn, &nid) + printk(" %3d: %0#10lx -> %0#10lx\n", nid, start_pfn, end_pfn); /* Initialise every node */ mminit_verify_pageflags_layout(); |