diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2010-10-22 01:52:11 (GMT) |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2010-10-22 01:52:11 (GMT) |
commit | 3044100e58c84e133791c8b60a2f5bef69d732e4 (patch) | |
tree | f9ed0d1f3df89c31dd81ccaf0cf3478f57b08440 /arch/x86/mm | |
parent | b5153163ed580e00c67bdfecb02b2e3843817b3e (diff) | |
parent | 67e87f0a1c5cbc750f81ebf6a128e8ff6f4376cc (diff) | |
download | linux-3044100e58c84e133791c8b60a2f5bef69d732e4.tar.xz |
Merge branch 'core-memblock-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip
* 'core-memblock-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: (74 commits)
x86-64: Only set max_pfn_mapped to 512 MiB if we enter via head_64.S
xen: Cope with unmapped pages when initializing kernel pagetable
memblock, bootmem: Round pfn properly for memory and reserved regions
memblock: Annotate memblock functions with __init_memblock
memblock: Allow memblock_init to be called early
memblock/arm: Fix memblock_region_is_memory() typo
x86, memblock: Remove __memblock_x86_find_in_range_size()
memblock: Fix wraparound in find_region()
x86-32, memblock: Make add_highpages honor early reserved ranges
x86, memblock: Fix crashkernel allocation
arm, memblock: Fix the sparsemem build
memblock: Fix section mismatch warnings
powerpc, memblock: Fix memblock API change fallout
memblock, microblaze: Fix memblock API change fallout
x86: Remove old bootmem code
x86, memblock: Use memblock_memory_size()/memblock_free_memory_size() to get correct dma_reserve
x86: Remove not used early_res code
x86, memblock: Replace e820_/_early string with memblock_
x86: Use memblock to replace early_res
x86, memblock: Use memblock_debug to control debug message print out
...
Fix up trivial conflicts in arch/x86/kernel/setup.c and kernel/Makefile
Diffstat (limited to 'arch/x86/mm')
-rw-r--r-- | arch/x86/mm/Makefile | 2 | ||||
-rw-r--r-- | arch/x86/mm/init.c | 10 | ||||
-rw-r--r-- | arch/x86/mm/init_32.c | 119 | ||||
-rw-r--r-- | arch/x86/mm/init_64.c | 67 | ||||
-rw-r--r-- | arch/x86/mm/ioremap.c | 5 | ||||
-rw-r--r-- | arch/x86/mm/k8topology_64.c | 4 | ||||
-rw-r--r-- | arch/x86/mm/memblock.c | 348 | ||||
-rw-r--r-- | arch/x86/mm/memtest.c | 7 | ||||
-rw-r--r-- | arch/x86/mm/numa_32.c | 30 | ||||
-rw-r--r-- | arch/x86/mm/numa_64.c | 84 | ||||
-rw-r--r-- | arch/x86/mm/srat_32.c | 3 | ||||
-rw-r--r-- | arch/x86/mm/srat_64.c | 11 |
12 files changed, 428 insertions, 262 deletions
diff --git a/arch/x86/mm/Makefile b/arch/x86/mm/Makefile index a4c7683..5554339 100644 --- a/arch/x86/mm/Makefile +++ b/arch/x86/mm/Makefile @@ -26,4 +26,6 @@ obj-$(CONFIG_NUMA) += numa.o numa_$(BITS).o obj-$(CONFIG_K8_NUMA) += k8topology_64.o obj-$(CONFIG_ACPI_NUMA) += srat_$(BITS).o +obj-$(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 b278535..c0e28a1 100644 --- a/arch/x86/mm/init.c +++ b/arch/x86/mm/init.c @@ -2,6 +2,7 @@ #include <linux/initrd.h> #include <linux/ioport.h> #include <linux/swap.h> +#include <linux/memblock.h> #include <asm/cacheflush.h> #include <asm/e820.h> @@ -33,6 +34,7 @@ static void __init find_early_table_space(unsigned long end, int use_pse, int use_gbpages) { unsigned long puds, pmds, ptes, tables, start; + phys_addr_t base; puds = (end + PUD_SIZE - 1) >> PUD_SHIFT; tables = roundup(puds * sizeof(pud_t), PAGE_SIZE); @@ -75,12 +77,12 @@ static void __init find_early_table_space(unsigned long end, int use_pse, #else start = 0x8000; #endif - e820_table_start = find_e820_area(start, max_pfn_mapped<<PAGE_SHIFT, + base = memblock_find_in_range(start, max_pfn_mapped<<PAGE_SHIFT, tables, PAGE_SIZE); - if (e820_table_start == -1UL) + if (base == MEMBLOCK_ERROR) panic("Cannot find space for the kernel page tables"); - e820_table_start >>= PAGE_SHIFT; + e820_table_start = base >> PAGE_SHIFT; e820_table_end = e820_table_start; e820_table_top = e820_table_start + (tables >> PAGE_SHIFT); @@ -299,7 +301,7 @@ unsigned long __init_refok init_memory_mapping(unsigned long start, __flush_tlb_all(); if (!after_bootmem && e820_table_end > e820_table_start) - reserve_early(e820_table_start << PAGE_SHIFT, + memblock_x86_reserve_range(e820_table_start << PAGE_SHIFT, e820_table_end << PAGE_SHIFT, "PGTABLE"); if (!after_bootmem) diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c index 558f2d3..5d0a671 100644 --- a/arch/x86/mm/init_32.c +++ b/arch/x86/mm/init_32.c @@ -25,6 +25,7 @@ #include <linux/pfn.h> #include <linux/poison.h> #include <linux/bootmem.h> +#include <linux/memblock.h> #include <linux/proc_fs.h> #include <linux/memory_hotplug.h> #include <linux/initrd.h> @@ -422,49 +423,28 @@ static void __init add_one_highpage_init(struct page *page) totalhigh_pages++; } -struct add_highpages_data { - unsigned long start_pfn; - unsigned long end_pfn; -}; - -static int __init add_highpages_work_fn(unsigned long start_pfn, - unsigned long end_pfn, void *datax) +void __init add_highpages_with_active_regions(int nid, + unsigned long start_pfn, unsigned long end_pfn) { - int node_pfn; - struct page *page; - unsigned long final_start_pfn, final_end_pfn; - struct add_highpages_data *data; + struct range *range; + int nr_range; + int i; - data = (struct add_highpages_data *)datax; + nr_range = __get_free_all_memory_range(&range, nid, start_pfn, end_pfn); - final_start_pfn = max(start_pfn, data->start_pfn); - final_end_pfn = min(end_pfn, data->end_pfn); - if (final_start_pfn >= final_end_pfn) - return 0; + for (i = 0; i < nr_range; i++) { + struct page *page; + int node_pfn; - for (node_pfn = final_start_pfn; node_pfn < final_end_pfn; - node_pfn++) { - if (!pfn_valid(node_pfn)) - continue; - page = pfn_to_page(node_pfn); - add_one_highpage_init(page); + 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); + } } - - return 0; - } - -void __init add_highpages_with_active_regions(int nid, unsigned long start_pfn, - unsigned long end_pfn) -{ - struct add_highpages_data data; - - data.start_pfn = start_pfn; - data.end_pfn = end_pfn; - - work_with_active_regions(nid, add_highpages_work_fn, &data); -} - #else static inline void permanent_kmaps_init(pgd_t *pgd_base) { @@ -712,14 +692,14 @@ void __init initmem_init(unsigned long start_pfn, unsigned long end_pfn, highstart_pfn = highend_pfn = max_pfn; if (max_pfn > max_low_pfn) highstart_pfn = max_low_pfn; - e820_register_active_regions(0, 0, highend_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 - e820_register_active_regions(0, 0, max_low_pfn); + 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; @@ -750,68 +730,12 @@ static void __init zone_sizes_init(void) free_area_init_nodes(max_zone_pfns); } -#ifndef CONFIG_NO_BOOTMEM -static unsigned long __init setup_node_bootmem(int nodeid, - unsigned long start_pfn, - unsigned long end_pfn, - unsigned long bootmap) -{ - unsigned long bootmap_size; - - /* don't touch min_low_pfn */ - bootmap_size = init_bootmem_node(NODE_DATA(nodeid), - bootmap >> PAGE_SHIFT, - start_pfn, end_pfn); - printk(KERN_INFO " node %d low ram: %08lx - %08lx\n", - nodeid, start_pfn<<PAGE_SHIFT, end_pfn<<PAGE_SHIFT); - printk(KERN_INFO " node %d bootmap %08lx - %08lx\n", - nodeid, bootmap, bootmap + bootmap_size); - free_bootmem_with_active_regions(nodeid, end_pfn); - - return bootmap + bootmap_size; -} -#endif - void __init setup_bootmem_allocator(void) { -#ifndef CONFIG_NO_BOOTMEM - int nodeid; - unsigned long bootmap_size, bootmap; - /* - * Initialize the boot-time allocator (with low memory only): - */ - bootmap_size = bootmem_bootmap_pages(max_low_pfn)<<PAGE_SHIFT; - bootmap = find_e820_area(0, max_pfn_mapped<<PAGE_SHIFT, bootmap_size, - PAGE_SIZE); - if (bootmap == -1L) - panic("Cannot find bootmem map of size %ld\n", bootmap_size); - reserve_early(bootmap, bootmap + bootmap_size, "BOOTMAP"); -#endif - printk(KERN_INFO " mapped low ram: 0 - %08lx\n", max_pfn_mapped<<PAGE_SHIFT); printk(KERN_INFO " low ram: 0 - %08lx\n", max_low_pfn<<PAGE_SHIFT); -#ifndef CONFIG_NO_BOOTMEM - for_each_online_node(nodeid) { - unsigned long start_pfn, end_pfn; - -#ifdef CONFIG_NEED_MULTIPLE_NODES - start_pfn = node_start_pfn[nodeid]; - end_pfn = node_end_pfn[nodeid]; - if (start_pfn > max_low_pfn) - continue; - if (end_pfn > max_low_pfn) - end_pfn = max_low_pfn; -#else - start_pfn = 0; - end_pfn = max_low_pfn; -#endif - bootmap = setup_node_bootmem(nodeid, start_pfn, end_pfn, - bootmap); - } -#endif - after_bootmem = 1; } @@ -1070,8 +994,3 @@ void mark_rodata_ro(void) } #endif -int __init reserve_bootmem_generic(unsigned long phys, unsigned long len, - int flags) -{ - return reserve_bootmem(phys, len, flags); -} diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index c55f900..8434620 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -21,6 +21,7 @@ #include <linux/initrd.h> #include <linux/pagemap.h> #include <linux/bootmem.h> +#include <linux/memblock.h> #include <linux/proc_fs.h> #include <linux/pci.h> #include <linux/pfn.h> @@ -52,8 +53,6 @@ #include <asm/init.h> #include <linux/bootmem.h> -static unsigned long dma_reserve __initdata; - static int __init parse_direct_gbpages_off(char *arg) { direct_gbpages = 0; @@ -617,23 +616,7 @@ kernel_physical_mapping_init(unsigned long start, void __init initmem_init(unsigned long start_pfn, unsigned long end_pfn, int acpi, int k8) { -#ifndef CONFIG_NO_BOOTMEM - unsigned long bootmap_size, bootmap; - - bootmap_size = bootmem_bootmap_pages(end_pfn)<<PAGE_SHIFT; - bootmap = find_e820_area(0, end_pfn<<PAGE_SHIFT, bootmap_size, - PAGE_SIZE); - if (bootmap == -1L) - panic("Cannot find bootmem map of size %ld\n", bootmap_size); - reserve_early(bootmap, bootmap + bootmap_size, "BOOTMAP"); - /* don't touch min_low_pfn */ - bootmap_size = init_bootmem_node(NODE_DATA(0), bootmap >> PAGE_SHIFT, - 0, end_pfn); - e820_register_active_regions(0, start_pfn, end_pfn); - free_bootmem_with_active_regions(0, end_pfn); -#else - e820_register_active_regions(0, start_pfn, end_pfn); -#endif + memblock_x86_register_active_regions(0, start_pfn, end_pfn); } #endif @@ -843,52 +826,6 @@ void mark_rodata_ro(void) #endif -int __init reserve_bootmem_generic(unsigned long phys, unsigned long len, - int flags) -{ -#ifdef CONFIG_NUMA - int nid, next_nid; - int ret; -#endif - unsigned long pfn = phys >> PAGE_SHIFT; - - if (pfn >= max_pfn) { - /* - * This can happen with kdump kernels when accessing - * firmware tables: - */ - if (pfn < max_pfn_mapped) - return -EFAULT; - - printk(KERN_ERR "reserve_bootmem: illegal reserve %lx %lu\n", - phys, len); - return -EFAULT; - } - - /* Should check here against the e820 map to avoid double free */ -#ifdef CONFIG_NUMA - nid = phys_to_nid(phys); - next_nid = phys_to_nid(phys + len - 1); - if (nid == next_nid) - ret = reserve_bootmem_node(NODE_DATA(nid), phys, len, flags); - else - ret = reserve_bootmem(phys, len, flags); - - if (ret != 0) - return ret; - -#else - reserve_bootmem(phys, len, flags); -#endif - - if (phys+len <= MAX_DMA_PFN*PAGE_SIZE) { - dma_reserve += len / PAGE_SIZE; - set_dma_reserve(dma_reserve); - } - - return 0; -} - int kern_addr_valid(unsigned long addr) { unsigned long above = ((long)addr) >> __VIRTUAL_MASK_SHIFT; diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c index 3ba6e06..0369843 100644 --- a/arch/x86/mm/ioremap.c +++ b/arch/x86/mm/ioremap.c @@ -362,6 +362,11 @@ static inline pte_t * __init early_ioremap_pte(unsigned long addr) return &bm_pte[pte_index(addr)]; } +bool __init is_early_ioremap_ptep(pte_t *ptep) +{ + return ptep >= &bm_pte[0] && ptep < &bm_pte[PAGE_SIZE/sizeof(pte_t)]; +} + static unsigned long slot_virt[FIX_BTMAPS_SLOTS] __initdata; void __init early_ioremap_init(void) diff --git a/arch/x86/mm/k8topology_64.c b/arch/x86/mm/k8topology_64.c index 52d54bf..804a3b6 100644 --- a/arch/x86/mm/k8topology_64.c +++ b/arch/x86/mm/k8topology_64.c @@ -11,6 +11,8 @@ #include <linux/string.h> #include <linux/module.h> #include <linux/nodemask.h> +#include <linux/memblock.h> + #include <asm/io.h> #include <linux/pci_ids.h> #include <linux/acpi.h> @@ -222,7 +224,7 @@ int __init k8_scan_nodes(void) for_each_node_mask(i, node_possible_map) { int j; - e820_register_active_regions(i, + memblock_x86_register_active_regions(i, nodes[i].start >> PAGE_SHIFT, nodes[i].end >> PAGE_SHIFT); for (j = apicid_base; j < cores + apicid_base; j++) diff --git a/arch/x86/mm/memblock.c b/arch/x86/mm/memblock.c new file mode 100644 index 0000000..aa11693 --- /dev/null +++ b/arch/x86/mm/memblock.c @@ -0,0 +1,348 @@ +#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 */ +static bool __init check_with_memblock_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 (check_with_memblock_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 18d244f..92faf3a 100644 --- a/arch/x86/mm/memtest.c +++ b/arch/x86/mm/memtest.c @@ -6,8 +6,7 @@ #include <linux/smp.h> #include <linux/init.h> #include <linux/pfn.h> - -#include <asm/e820.h> +#include <linux/memblock.h> static u64 patterns[] __initdata = { 0, @@ -35,7 +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); - reserve_early(start_bad, end_bad, "BAD RAM"); + memblock_x86_reserve_range(start_bad, end_bad, "BAD RAM"); } static void __init memtest(u64 pattern, u64 start_phys, u64 size) @@ -74,7 +73,7 @@ static void __init do_one_pass(u64 pattern, u64 start, u64 end) u64 size = 0; while (start < end) { - start = find_e820_area_size(start, &size, 1); + start = memblock_x86_find_in_range_size(start, &size, 1); /* done ? */ if (start >= end) diff --git a/arch/x86/mm/numa_32.c b/arch/x86/mm/numa_32.c index 809baaa..84a3e4c 100644 --- a/arch/x86/mm/numa_32.c +++ b/arch/x86/mm/numa_32.c @@ -24,6 +24,7 @@ #include <linux/mm.h> #include <linux/bootmem.h> +#include <linux/memblock.h> #include <linux/mmzone.h> #include <linux/highmem.h> #include <linux/initrd.h> @@ -120,7 +121,7 @@ int __init get_memcfg_numa_flat(void) node_start_pfn[0] = 0; node_end_pfn[0] = max_pfn; - e820_register_active_regions(0, 0, max_pfn); + memblock_x86_register_active_regions(0, 0, max_pfn); memory_present(0, 0, max_pfn); node_remap_size[0] = node_memmap_size_bytes(0, 0, max_pfn); @@ -161,14 +162,14 @@ static void __init allocate_pgdat(int nid) NODE_DATA(nid) = (pg_data_t *)node_remap_start_vaddr[nid]; else { unsigned long pgdat_phys; - pgdat_phys = find_e820_area(min_low_pfn<<PAGE_SHIFT, + pgdat_phys = memblock_find_in_range(min_low_pfn<<PAGE_SHIFT, max_pfn_mapped<<PAGE_SHIFT, sizeof(pg_data_t), PAGE_SIZE); NODE_DATA(nid) = (pg_data_t *)(pfn_to_kaddr(pgdat_phys>>PAGE_SHIFT)); memset(buf, 0, sizeof(buf)); sprintf(buf, "NODE_DATA %d", nid); - reserve_early(pgdat_phys, pgdat_phys + sizeof(pg_data_t), buf); + memblock_x86_reserve_range(pgdat_phys, pgdat_phys + sizeof(pg_data_t), buf); } printk(KERN_DEBUG "allocate_pgdat: node %d NODE_DATA %08lx\n", nid, (unsigned long)NODE_DATA(nid)); @@ -291,15 +292,15 @@ static __init unsigned long calculate_numa_remap_pages(void) PTRS_PER_PTE); node_kva_target <<= PAGE_SHIFT; do { - node_kva_final = find_e820_area(node_kva_target, + node_kva_final = memblock_find_in_range(node_kva_target, ((u64)node_end_pfn[nid])<<PAGE_SHIFT, ((u64)size)<<PAGE_SHIFT, LARGE_PAGE_BYTES); node_kva_target -= LARGE_PAGE_BYTES; - } while (node_kva_final == -1ULL && + } while (node_kva_final == MEMBLOCK_ERROR && (node_kva_target>>PAGE_SHIFT) > (node_start_pfn[nid])); - if (node_kva_final == -1ULL) + if (node_kva_final == MEMBLOCK_ERROR) panic("Can not get kva ram\n"); node_remap_size[nid] = size; @@ -318,15 +319,13 @@ static __init unsigned long calculate_numa_remap_pages(void) * but we could have some hole in high memory, and it will only * check page_is_ram(pfn) && !page_is_reserved_early(pfn) to decide * to use it as free. - * So reserve_early here, hope we don't run out of that array + * So memblock_x86_reserve_range here, hope we don't run out of that array */ - reserve_early(node_kva_final, + memblock_x86_reserve_range(node_kva_final, node_kva_final+(((u64)size)<<PAGE_SHIFT), "KVA RAM"); node_remap_start_pfn[nid] = node_kva_final>>PAGE_SHIFT; - remove_active_range(nid, node_remap_start_pfn[nid], - node_remap_start_pfn[nid] + size); } printk(KERN_INFO "Reserving total of %lx pages for numa KVA remap\n", reserve_pages); @@ -367,14 +366,14 @@ void __init initmem_init(unsigned long start_pfn, unsigned long end_pfn, kva_target_pfn = round_down(max_low_pfn - kva_pages, PTRS_PER_PTE); do { - kva_start_pfn = find_e820_area(kva_target_pfn<<PAGE_SHIFT, + kva_start_pfn = memblock_find_in_range(kva_target_pfn<<PAGE_SHIFT, max_low_pfn<<PAGE_SHIFT, kva_pages<<PAGE_SHIFT, PTRS_PER_PTE<<PAGE_SHIFT) >> PAGE_SHIFT; kva_target_pfn -= PTRS_PER_PTE; - } while (kva_start_pfn == -1UL && kva_target_pfn > min_low_pfn); + } while (kva_start_pfn == MEMBLOCK_ERROR && kva_target_pfn > min_low_pfn); - if (kva_start_pfn == -1UL) + if (kva_start_pfn == MEMBLOCK_ERROR) panic("Can not get kva space\n"); printk(KERN_INFO "kva_start_pfn ~ %lx max_low_pfn ~ %lx\n", @@ -382,7 +381,7 @@ void __init initmem_init(unsigned long start_pfn, unsigned long end_pfn, printk(KERN_INFO "max_pfn = %lx\n", max_pfn); /* avoid clash with initrd */ - reserve_early(kva_start_pfn<<PAGE_SHIFT, + memblock_x86_reserve_range(kva_start_pfn<<PAGE_SHIFT, (kva_start_pfn + kva_pages)<<PAGE_SHIFT, "KVA PG"); #ifdef CONFIG_HIGHMEM @@ -419,9 +418,6 @@ void __init initmem_init(unsigned long start_pfn, unsigned long end_pfn, for_each_online_node(nid) { memset(NODE_DATA(nid), 0, sizeof(struct pglist_data)); NODE_DATA(nid)->node_id = nid; -#ifndef CONFIG_NO_BOOTMEM - NODE_DATA(nid)->bdata = &bootmem_node_data[nid]; -#endif } setup_bootmem_allocator(); diff --git a/arch/x86/mm/numa_64.c b/arch/x86/mm/numa_64.c index 4962f1a..60f4985 100644 --- a/arch/x86/mm/numa_64.c +++ b/arch/x86/mm/numa_64.c @@ -7,6 +7,7 @@ #include <linux/string.h> #include <linux/init.h> #include <linux/bootmem.h> +#include <linux/memblock.h> #include <linux/mmzone.h> #include <linux/ctype.h> #include <linux/module.h> @@ -86,16 +87,16 @@ static int __init allocate_cachealigned_memnodemap(void) addr = 0x8000; nodemap_size = roundup(sizeof(s16) * memnodemapsize, L1_CACHE_BYTES); - nodemap_addr = find_e820_area(addr, max_pfn<<PAGE_SHIFT, + nodemap_addr = memblock_find_in_range(addr, max_pfn<<PAGE_SHIFT, nodemap_size, L1_CACHE_BYTES); - if (nodemap_addr == -1UL) { + if (nodemap_addr == MEMBLOCK_ERROR) { printk(KERN_ERR "NUMA: Unable to allocate Memory to Node hash map\n"); nodemap_addr = nodemap_size = 0; return -1; } memnodemap = phys_to_virt(nodemap_addr); - reserve_early(nodemap_addr, nodemap_addr + nodemap_size, "MEMNODEMAP"); + memblock_x86_reserve_range(nodemap_addr, nodemap_addr + nodemap_size, "MEMNODEMAP"); printk(KERN_DEBUG "NUMA: Allocated memnodemap from %lx - %lx\n", nodemap_addr, nodemap_addr + nodemap_size); @@ -171,8 +172,8 @@ static void * __init early_node_mem(int nodeid, unsigned long start, if (start < (MAX_DMA32_PFN<<PAGE_SHIFT) && end > (MAX_DMA32_PFN<<PAGE_SHIFT)) start = MAX_DMA32_PFN<<PAGE_SHIFT; - mem = find_e820_area(start, end, size, align); - if (mem != -1L) + mem = memblock_x86_find_in_range_node(nodeid, start, end, size, align); + if (mem != MEMBLOCK_ERROR) return __va(mem); /* extend the search scope */ @@ -181,8 +182,8 @@ static void * __init early_node_mem(int nodeid, unsigned long start, start = MAX_DMA32_PFN<<PAGE_SHIFT; else start = MAX_DMA_PFN<<PAGE_SHIFT; - mem = find_e820_area(start, end, size, align); - if (mem != -1L) + mem = memblock_x86_find_in_range_node(nodeid, start, end, size, align); + if (mem != MEMBLOCK_ERROR) return __va(mem); printk(KERN_ERR "Cannot find %lu bytes in node %d\n", @@ -198,10 +199,6 @@ setup_node_bootmem(int nodeid, unsigned long start, unsigned long end) unsigned long start_pfn, last_pfn, nodedata_phys; const int pgdat_size = roundup(sizeof(pg_data_t), PAGE_SIZE); int nid; -#ifndef CONFIG_NO_BOOTMEM - unsigned long bootmap_start, bootmap_pages, bootmap_size; - void *bootmap; -#endif if (!end) return; @@ -226,7 +223,7 @@ setup_node_bootmem(int nodeid, unsigned long start, unsigned long end) if (node_data[nodeid] == NULL) return; nodedata_phys = __pa(node_data[nodeid]); - reserve_early(nodedata_phys, nodedata_phys + pgdat_size, "NODE_DATA"); + memblock_x86_reserve_range(nodedata_phys, nodedata_phys + pgdat_size, "NODE_DATA"); printk(KERN_INFO " NODE_DATA [%016lx - %016lx]\n", nodedata_phys, nodedata_phys + pgdat_size - 1); nid = phys_to_nid(nodedata_phys); @@ -238,47 +235,6 @@ setup_node_bootmem(int nodeid, unsigned long start, unsigned long end) NODE_DATA(nodeid)->node_start_pfn = start_pfn; NODE_DATA(nodeid)->node_spanned_pages = last_pfn - start_pfn; -#ifndef CONFIG_NO_BOOTMEM - NODE_DATA(nodeid)->bdata = &bootmem_node_data[nodeid]; - - /* - * Find a place for the bootmem map - * nodedata_phys could be on other nodes by alloc_bootmem, - * so need to sure bootmap_start not to be small, otherwise - * early_node_mem will get that with find_e820_area instead - * of alloc_bootmem, that could clash with reserved range - */ - bootmap_pages = bootmem_bootmap_pages(last_pfn - start_pfn); - bootmap_start = roundup(nodedata_phys + pgdat_size, PAGE_SIZE); - /* - * SMP_CACHE_BYTES could be enough, but init_bootmem_node like - * to use that to align to PAGE_SIZE - */ - bootmap = early_node_mem(nodeid, bootmap_start, end, - bootmap_pages<<PAGE_SHIFT, PAGE_SIZE); - if (bootmap == NULL) { - free_early(nodedata_phys, nodedata_phys + pgdat_size); - node_data[nodeid] = NULL; - return; - } - bootmap_start = __pa(bootmap); - reserve_early(bootmap_start, bootmap_start+(bootmap_pages<<PAGE_SHIFT), - "BOOTMAP"); - - bootmap_size = init_bootmem_node(NODE_DATA(nodeid), - bootmap_start >> PAGE_SHIFT, - start_pfn, last_pfn); - - printk(KERN_INFO " bootmap [%016lx - %016lx] pages %lx\n", - bootmap_start, bootmap_start + bootmap_size - 1, - bootmap_pages); - nid = phys_to_nid(bootmap_start); - if (nid != nodeid) - printk(KERN_INFO " bootmap(%d) on node %d\n", nodeid, nid); - - free_bootmem_with_active_regions(nodeid, end); -#endif - node_set_online(nodeid); } @@ -416,7 +372,7 @@ static int __init split_nodes_interleave(u64 addr, u64 max_addr, nr_nodes = MAX_NUMNODES; } - size = (max_addr - addr - e820_hole_size(addr, max_addr)) / nr_nodes; + size = (max_addr - addr - memblock_x86_hole_size(addr, max_addr)) / nr_nodes; /* * Calculate the number of big nodes that can be allocated as a result * of consolidating the remainder. @@ -452,7 +408,7 @@ static int __init split_nodes_interleave(u64 addr, u64 max_addr, * non-reserved memory is less than the per-node size. */ while (end - physnodes[i].start - - e820_hole_size(physnodes[i].start, end) < size) { + memblock_x86_hole_size(physnodes[i].start, end) < size) { end += FAKE_NODE_MIN_SIZE; if (end > physnodes[i].end) { end = physnodes[i].end; @@ -466,7 +422,7 @@ static int __init split_nodes_interleave(u64 addr, u64 max_addr, * this one must extend to the boundary. */ if (end < dma32_end && dma32_end - end - - e820_hole_size(end, dma32_end) < FAKE_NODE_MIN_SIZE) + memblock_x86_hole_size(end, dma32_end) < FAKE_NODE_MIN_SIZE) end = dma32_end; /* @@ -475,7 +431,7 @@ static int __init split_nodes_interleave(u64 addr, u64 max_addr, * physical node. */ if (physnodes[i].end - end - - e820_hole_size(end, physnodes[i].end) < size) + memblock_x86_hole_size(end, physnodes[i].end) < size) end = physnodes[i].end; /* @@ -503,7 +459,7 @@ static u64 __init find_end_of_node(u64 start, u64 max_addr, u64 size) { u64 end = start + size; - while (end - start - e820_hole_size(start, end) < size) { + while (end - start - memblock_x86_hole_size(start, end) < size) { end += FAKE_NODE_MIN_SIZE; if (end > max_addr) { end = max_addr; @@ -532,7 +488,7 @@ static int __init split_nodes_size_interleave(u64 addr, u64 max_addr, u64 size) * creates a uniform distribution of node sizes across the entire * machine (but not necessarily over physical nodes). */ - min_size = (max_addr - addr - e820_hole_size(addr, max_addr)) / + min_size = (max_addr - addr - memblock_x86_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) @@ -565,7 +521,7 @@ static int __init split_nodes_size_interleave(u64 addr, u64 max_addr, u64 size) * this one must extend to the boundary. */ if (end < dma32_end && dma32_end - end - - e820_hole_size(end, dma32_end) < FAKE_NODE_MIN_SIZE) + memblock_x86_hole_size(end, dma32_end) < FAKE_NODE_MIN_SIZE) end = dma32_end; /* @@ -574,7 +530,7 @@ static int __init split_nodes_size_interleave(u64 addr, u64 max_addr, u64 size) * physical node. */ if (physnodes[i].end - end - - e820_hole_size(end, physnodes[i].end) < size) + memblock_x86_hole_size(end, physnodes[i].end) < size) end = physnodes[i].end; /* @@ -638,7 +594,7 @@ static int __init numa_emulation(unsigned long start_pfn, */ remove_all_active_ranges(); for_each_node_mask(i, node_possible_map) { - e820_register_active_regions(i, nodes[i].start >> PAGE_SHIFT, + memblock_x86_register_active_regions(i, nodes[i].start >> PAGE_SHIFT, nodes[i].end >> PAGE_SHIFT); setup_node_bootmem(i, nodes[i].start, nodes[i].end); } @@ -691,7 +647,7 @@ void __init initmem_init(unsigned long start_pfn, unsigned long last_pfn, node_set(0, node_possible_map); for (i = 0; i < nr_cpu_ids; i++) numa_set_node(i, 0); - e820_register_active_regions(0, start_pfn, last_pfn); + memblock_x86_register_active_regions(0, start_pfn, last_pfn); setup_node_bootmem(0, start_pfn << PAGE_SHIFT, last_pfn << PAGE_SHIFT); } @@ -703,9 +659,7 @@ unsigned long __init numa_free_all_bootmem(void) for_each_online_node(i) pages += free_all_bootmem_node(NODE_DATA(i)); -#ifdef CONFIG_NO_BOOTMEM pages += free_all_memory_core_early(MAX_NUMNODES); -#endif return pages; } diff --git a/arch/x86/mm/srat_32.c b/arch/x86/mm/srat_32.c index 9324f13..a17dffd 100644 --- a/arch/x86/mm/srat_32.c +++ b/arch/x86/mm/srat_32.c @@ -25,6 +25,7 @@ */ #include <linux/mm.h> #include <linux/bootmem.h> +#include <linux/memblock.h> #include <linux/mmzone.h> #include <linux/acpi.h> #include <linux/nodemask.h> @@ -264,7 +265,7 @@ int __init get_memcfg_from_srat(void) if (node_read_chunk(chunk->nid, chunk)) continue; - e820_register_active_regions(chunk->nid, chunk->start_pfn, + memblock_x86_register_active_regions(chunk->nid, chunk->start_pfn, min(chunk->end_pfn, max_pfn)); } /* for out of order entries in SRAT */ diff --git a/arch/x86/mm/srat_64.c b/arch/x86/mm/srat_64.c index 9c0d0d3..a35cb9d 100644 --- a/arch/x86/mm/srat_64.c +++ b/arch/x86/mm/srat_64.c @@ -16,6 +16,7 @@ #include <linux/module.h> #include <linux/topology.h> #include <linux/bootmem.h> +#include <linux/memblock.h> #include <linux/mm.h> #include <asm/proto.h> #include <asm/numa.h> @@ -98,15 +99,15 @@ void __init acpi_numa_slit_init(struct acpi_table_slit *slit) unsigned long phys; length = slit->header.length; - phys = find_e820_area(0, max_pfn_mapped<<PAGE_SHIFT, length, + phys = memblock_find_in_range(0, max_pfn_mapped<<PAGE_SHIFT, length, PAGE_SIZE); - if (phys == -1L) + if (phys == MEMBLOCK_ERROR) panic(" Can not save slit!\n"); acpi_slit = __va(phys); memcpy(acpi_slit, slit, length); - reserve_early(phys, phys + length, "ACPI SLIT"); + memblock_x86_reserve_range(phys, phys + length, "ACPI SLIT"); } /* Callback for Proximity Domain -> x2APIC mapping */ @@ -324,7 +325,7 @@ static int __init nodes_cover_memory(const struct bootnode *nodes) pxmram = 0; } - e820ram = max_pfn - (e820_hole_size(0, max_pfn<<PAGE_SHIFT)>>PAGE_SHIFT); + e820ram = max_pfn - (memblock_x86_hole_size(0, max_pfn<<PAGE_SHIFT)>>PAGE_SHIFT); /* We seem to lose 3 pages somewhere. Allow 1M of slack. */ if ((long)(e820ram - pxmram) >= (1<<(20 - PAGE_SHIFT))) { printk(KERN_ERR @@ -421,7 +422,7 @@ int __init acpi_scan_nodes(unsigned long start, unsigned long end) } for (i = 0; i < num_node_memblks; i++) - e820_register_active_regions(memblk_nodeid[i], + memblock_x86_register_active_regions(memblk_nodeid[i], node_memblk_range[i].start >> PAGE_SHIFT, node_memblk_range[i].end >> PAGE_SHIFT); |