diff options
Diffstat (limited to 'arch/x86')
32 files changed, 633 insertions, 510 deletions
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 7ab9db88ab6..dfabfefc21c 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -28,6 +28,7 @@ config X86 select HAVE_IRQ_WORK select HAVE_IOREMAP_PROT select HAVE_KPROBES + select HAVE_MEMBLOCK select ARCH_WANT_OPTIONAL_GPIOLIB select ARCH_WANT_FRAME_POINTERS select HAVE_DMA_ATTRS @@ -201,9 +202,6 @@ config ARCH_SUPPORTS_OPTIMIZED_INLINING config ARCH_SUPPORTS_DEBUG_PAGEALLOC def_bool y -config HAVE_EARLY_RES - def_bool y - config HAVE_INTEL_TXT def_bool y depends on EXPERIMENTAL && DMAR && ACPI @@ -548,16 +546,7 @@ config PARAVIRT_DEBUG a paravirt_op is missing when it is called. config NO_BOOTMEM - default y - bool "Disable Bootmem code" - ---help--- - Use early_res directly instead of bootmem before slab is ready. - - allocator (buddy) [generic] - - early allocator (bootmem) [generic] - - very early allocator (reserve_early*()) [x86] - - very very early allocator (early brk model) [x86] - So reduce one layer between early allocator to final allocator - + def_bool y config MEMTEST bool "Memtest" diff --git a/arch/x86/include/asm/e820.h b/arch/x86/include/asm/e820.h index ec8a52d14ab..5be1542fbfa 100644 --- a/arch/x86/include/asm/e820.h +++ b/arch/x86/include/asm/e820.h @@ -112,23 +112,13 @@ static inline void early_memtest(unsigned long start, unsigned long end) } #endif -extern unsigned long end_user_pfn; - -extern u64 find_e820_area(u64 start, u64 end, u64 size, u64 align); -extern u64 find_e820_area_size(u64 start, u64 *sizep, u64 align); -extern u64 early_reserve_e820(u64 startt, u64 sizet, u64 align); -#include <linux/early_res.h> - extern unsigned long e820_end_of_ram_pfn(void); extern unsigned long e820_end_of_low_ram_pfn(void); -extern int e820_find_active_region(const struct e820entry *ei, - unsigned long start_pfn, - unsigned long last_pfn, - unsigned long *ei_startpfn, - unsigned long *ei_endpfn); -extern void e820_register_active_regions(int nid, unsigned long start_pfn, - unsigned long end_pfn); -extern u64 e820_hole_size(u64 start, u64 end); +extern u64 early_reserve_e820(u64 startt, u64 sizet, u64 align); + +void memblock_x86_fill(void); +void memblock_find_dma_reserve(void); + extern void finish_e820_parsing(void); extern void e820_reserve_resources(void); extern void e820_reserve_resources_late(void); diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h index 8406ed7f992..8e4a16508d4 100644 --- a/arch/x86/include/asm/efi.h +++ b/arch/x86/include/asm/efi.h @@ -90,7 +90,7 @@ extern void __iomem *efi_ioremap(unsigned long addr, unsigned long size, #endif /* CONFIG_X86_32 */ extern int add_efi_memmap; -extern void efi_reserve_early(void); +extern void efi_memblock_x86_reserve_range(void); extern void efi_call_phys_prelog(void); extern void efi_call_phys_epilog(void); diff --git a/arch/x86/include/asm/io.h b/arch/x86/include/asm/io.h index 6a45ec41ec2..f0203f4791a 100644 --- a/arch/x86/include/asm/io.h +++ b/arch/x86/include/asm/io.h @@ -349,6 +349,7 @@ extern void __iomem *early_memremap(resource_size_t phys_addr, unsigned long size); extern void early_iounmap(void __iomem *addr, unsigned long size); extern void fixup_early_ioremap(void); +extern bool is_early_ioremap_ptep(pte_t *ptep); #define IO_SPACE_LIMIT 0xffff diff --git a/arch/x86/include/asm/memblock.h b/arch/x86/include/asm/memblock.h new file mode 100644 index 00000000000..19ae14ba697 --- /dev/null +++ b/arch/x86/include/asm/memblock.h @@ -0,0 +1,23 @@ +#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_to_bootmem(u64 start, u64 end); + +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); + +#endif diff --git a/arch/x86/kernel/acpi/sleep.c b/arch/x86/kernel/acpi/sleep.c index 33cec152070..e1252074ea4 100644 --- a/arch/x86/kernel/acpi/sleep.c +++ b/arch/x86/kernel/acpi/sleep.c @@ -7,6 +7,7 @@ #include <linux/acpi.h> #include <linux/bootmem.h> +#include <linux/memblock.h> #include <linux/dmi.h> #include <linux/cpumask.h> #include <asm/segment.h> @@ -125,7 +126,7 @@ void acpi_restore_state_mem(void) */ void __init acpi_reserve_wakeup_memory(void) { - unsigned long mem; + phys_addr_t mem; if ((&wakeup_code_end - &wakeup_code_start) > WAKEUP_SIZE) { printk(KERN_ERR @@ -133,15 +134,15 @@ void __init acpi_reserve_wakeup_memory(void) return; } - mem = find_e820_area(0, 1<<20, WAKEUP_SIZE, PAGE_SIZE); + mem = memblock_find_in_range(0, 1<<20, WAKEUP_SIZE, PAGE_SIZE); - if (mem == -1L) { + if (mem == MEMBLOCK_ERROR) { printk(KERN_ERR "ACPI: Cannot allocate lowmem, S3 disabled.\n"); return; } acpi_realmode = (unsigned long) phys_to_virt(mem); acpi_wakeup_address = mem; - reserve_early(mem, mem + WAKEUP_SIZE, "ACPI WAKEUP"); + memblock_x86_reserve_range(mem, mem + WAKEUP_SIZE, "ACPI WAKEUP"); } diff --git a/arch/x86/kernel/apic/numaq_32.c b/arch/x86/kernel/apic/numaq_32.c index 3e28401f161..960f26ab5c9 100644 --- a/arch/x86/kernel/apic/numaq_32.c +++ b/arch/x86/kernel/apic/numaq_32.c @@ -26,6 +26,7 @@ #include <linux/nodemask.h> #include <linux/topology.h> #include <linux/bootmem.h> +#include <linux/memblock.h> #include <linux/threads.h> #include <linux/cpumask.h> #include <linux/kernel.h> @@ -88,7 +89,7 @@ static inline void numaq_register_node(int node, struct sys_cfg_data *scd) node_end_pfn[node] = MB_TO_PAGES(eq->hi_shrd_mem_start + eq->hi_shrd_mem_size); - e820_register_active_regions(node, node_start_pfn[node], + memblock_x86_register_active_regions(node, node_start_pfn[node], node_end_pfn[node]); memory_present(node, node_start_pfn[node], node_end_pfn[node]); diff --git a/arch/x86/kernel/check.c b/arch/x86/kernel/check.c index fc999e6fc46..13a38917951 100644 --- a/arch/x86/kernel/check.c +++ b/arch/x86/kernel/check.c @@ -2,7 +2,8 @@ #include <linux/sched.h> #include <linux/kthread.h> #include <linux/workqueue.h> -#include <asm/e820.h> +#include <linux/memblock.h> + #include <asm/proto.h> /* @@ -18,10 +19,12 @@ static int __read_mostly memory_corruption_check = -1; static unsigned __read_mostly corruption_check_size = 64*1024; static unsigned __read_mostly corruption_check_period = 60; /* seconds */ -static struct e820entry scan_areas[MAX_SCAN_AREAS]; +static struct scan_area { + u64 addr; + u64 size; +} scan_areas[MAX_SCAN_AREAS]; static int num_scan_areas; - static __init int set_corruption_check(char *arg) { char *end; @@ -81,9 +84,9 @@ void __init setup_bios_corruption_check(void) while (addr < corruption_check_size && num_scan_areas < MAX_SCAN_AREAS) { u64 size; - addr = find_e820_area_size(addr, &size, PAGE_SIZE); + addr = memblock_x86_find_in_range_size(addr, &size, PAGE_SIZE); - if (!(addr + 1)) + if (addr == MEMBLOCK_ERROR) break; if (addr >= corruption_check_size) @@ -92,7 +95,7 @@ void __init setup_bios_corruption_check(void) if ((addr + size) > corruption_check_size) size = corruption_check_size - addr; - e820_update_range(addr, size, E820_RAM, E820_RESERVED); + 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++; @@ -105,7 +108,6 @@ void __init setup_bios_corruption_check(void) printk(KERN_INFO "Scanning %d areas for low memory corruption\n", num_scan_areas); - update_e820(); } diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c index 0d6fc71bedb..0c2b7ef7a34 100644 --- a/arch/x86/kernel/e820.c +++ b/arch/x86/kernel/e820.c @@ -15,6 +15,7 @@ #include <linux/pfn.h> #include <linux/suspend.h> #include <linux/firmware-map.h> +#include <linux/memblock.h> #include <asm/e820.h> #include <asm/proto.h> @@ -738,73 +739,7 @@ core_initcall(e820_mark_nvs_memory); #endif /* - * Find a free area with specified alignment in a specific range. - */ -u64 __init find_e820_area(u64 start, u64 end, u64 size, u64 align) -{ - int i; - - for (i = 0; i < e820.nr_map; i++) { - struct e820entry *ei = &e820.map[i]; - u64 addr; - u64 ei_start, ei_last; - - if (ei->type != E820_RAM) - continue; - - ei_last = ei->addr + ei->size; - ei_start = ei->addr; - addr = find_early_area(ei_start, ei_last, start, end, - size, align); - - if (addr != -1ULL) - return addr; - } - return -1ULL; -} - -u64 __init find_fw_memmap_area(u64 start, u64 end, u64 size, u64 align) -{ - return find_e820_area(start, end, size, align); -} - -u64 __init get_max_mapped(void) -{ - u64 end = max_pfn_mapped; - - end <<= PAGE_SHIFT; - - return end; -} -/* - * Find next free range after *start - */ -u64 __init find_e820_area_size(u64 start, u64 *sizep, u64 align) -{ - int i; - - for (i = 0; i < e820.nr_map; i++) { - struct e820entry *ei = &e820.map[i]; - u64 addr; - u64 ei_start, ei_last; - - if (ei->type != E820_RAM) - continue; - - ei_last = ei->addr + ei->size; - ei_start = ei->addr; - addr = find_early_area_size(ei_start, ei_last, start, - sizep, align); - - if (addr != -1ULL) - return addr; - } - - return -1ULL; -} - -/* - * pre allocated 4k and reserved it in e820 + * pre allocated 4k and reserved it in memblock and e820_saved */ u64 __init early_reserve_e820(u64 startt, u64 sizet, u64 align) { @@ -813,8 +748,8 @@ u64 __init early_reserve_e820(u64 startt, u64 sizet, u64 align) u64 start; for (start = startt; ; start += size) { - start = find_e820_area_size(start, &size, align); - if (!(start + 1)) + start = memblock_x86_find_in_range_size(start, &size, align); + if (start == MEMBLOCK_ERROR) return 0; if (size >= sizet) break; @@ -830,10 +765,9 @@ u64 __init early_reserve_e820(u64 startt, u64 sizet, u64 align) addr = round_down(start + size - sizet, align); if (addr < start) return 0; - e820_update_range(addr, sizet, E820_RAM, E820_RESERVED); + memblock_x86_reserve_range(addr, addr + sizet, "new next"); e820_update_range_saved(addr, sizet, E820_RAM, E820_RESERVED); - printk(KERN_INFO "update e820 for early_reserve_e820\n"); - update_e820(); + printk(KERN_INFO "update e820_saved for early_reserve_e820\n"); update_e820_saved(); return addr; @@ -895,74 +829,6 @@ unsigned long __init e820_end_of_low_ram_pfn(void) { return e820_end_pfn(1UL<<(32 - PAGE_SHIFT), E820_RAM); } -/* - * 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 e820 entry. - */ -int __init e820_find_active_region(const struct e820entry *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->addr, align) >> PAGE_SHIFT; - *ei_endpfn = round_down(ei->addr + 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->type != E820_RAM || *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 e820 map and register active regions within a node */ -void __init e820_register_active_regions(int nid, unsigned long start_pfn, - unsigned long last_pfn) -{ - unsigned long ei_startpfn; - unsigned long ei_endpfn; - int i; - - for (i = 0; i < e820.nr_map; i++) - if (e820_find_active_region(&e820.map[i], - 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 e820_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; - int i; - - for (i = 0; i < e820.nr_map; i++) { - if (e820_find_active_region(&e820.map[i], - start_pfn, last_pfn, - &ei_startpfn, &ei_endpfn)) - ram += ei_endpfn - ei_startpfn; - } - return end - start - ((u64)ram << PAGE_SHIFT); -} static void early_panic(char *msg) { @@ -1210,3 +1076,48 @@ void __init setup_memory_map(void) printk(KERN_INFO "BIOS-provided physical RAM map:\n"); e820_print_map(who); } + +void __init memblock_x86_fill(void) +{ + int i; + u64 end; + + /* + * EFI may have more than 128 entries + * We are safe to enable resizing, beause memblock_x86_fill() + * is rather later for x86 + */ + memblock_can_resize = 1; + + for (i = 0; i < e820.nr_map; i++) { + struct e820entry *ei = &e820.map[i]; + + end = ei->addr + ei->size; + if (end != (resource_size_t)end) + continue; + + if (ei->type != E820_RAM && ei->type != E820_RESERVED_KERN) + continue; + + memblock_add(ei->addr, ei->size); + } + + memblock_analyze(); + memblock_dump_all(); +} + +void __init memblock_find_dma_reserve(void) +{ +#ifdef CONFIG_X86_64 + u64 free_size_pfn; + u64 mem_size_pfn; + /* + * 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); +#endif +} diff --git a/arch/x86/kernel/efi.c b/arch/x86/kernel/efi.c index c2fa9b8b497..0fe27d7c625 100644 --- a/arch/x86/kernel/efi.c +++ b/arch/x86/kernel/efi.c @@ -30,6 +30,7 @@ #include <linux/init.h> #include <linux/efi.h> #include <linux/bootmem.h> +#include <linux/memblock.h> #include <linux/spinlock.h> #include <linux/uaccess.h> #include <linux/time.h> @@ -275,7 +276,7 @@ static void __init do_add_efi_memmap(void) sanitize_e820_map(e820.map, ARRAY_SIZE(e820.map), &e820.nr_map); } -void __init efi_reserve_early(void) +void __init efi_memblock_x86_reserve_range(void) { unsigned long pmap; @@ -290,7 +291,7 @@ void __init efi_reserve_early(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; - reserve_early(pmap, pmap + memmap.nr_map * memmap.desc_size, + memblock_x86_reserve_range(pmap, pmap + memmap.nr_map * memmap.desc_size, "EFI memmap"); } diff --git a/arch/x86/kernel/head.c b/arch/x86/kernel/head.c index 3e66bd364a9..af0699ba48c 100644 --- a/arch/x86/kernel/head.c +++ b/arch/x86/kernel/head.c @@ -1,5 +1,6 @@ #include <linux/kernel.h> #include <linux/init.h> +#include <linux/memblock.h> #include <asm/setup.h> #include <asm/bios_ebda.h> @@ -51,5 +52,5 @@ void __init reserve_ebda_region(void) lowmem = 0x9f000; /* reserve all memory between lowmem and the 1MB mark */ - reserve_early_overlap_ok(lowmem, 0x100000, "BIOS reserved"); + memblock_x86_reserve_range(lowmem, 0x100000, "* BIOS reserved"); } diff --git a/arch/x86/kernel/head32.c b/arch/x86/kernel/head32.c index 784360c0625..9a6ca239217 100644 --- a/arch/x86/kernel/head32.c +++ b/arch/x86/kernel/head32.c @@ -8,6 +8,7 @@ #include <linux/init.h> #include <linux/start_kernel.h> #include <linux/mm.h> +#include <linux/memblock.h> #include <asm/setup.h> #include <asm/sections.h> @@ -30,17 +31,18 @@ static void __init i386_default_early_setup(void) void __init i386_start_kernel(void) { + memblock_init(); + #ifdef CONFIG_X86_TRAMPOLINE /* * But first pinch a few for the stack/trampoline stuff * FIXME: Don't need the extra page at 4K, but need to fix * trampoline before removing it. (see the GDT stuff) */ - reserve_early_overlap_ok(PAGE_SIZE, PAGE_SIZE + PAGE_SIZE, - "EX TRAMPOLINE"); + memblock_x86_reserve_range(PAGE_SIZE, PAGE_SIZE + PAGE_SIZE, "EX TRAMPOLINE"); #endif - reserve_early(__pa_symbol(&_text), __pa_symbol(&__bss_stop), "TEXT DATA BSS"); + memblock_x86_reserve_range(__pa_symbol(&_text), __pa_symbol(&__bss_stop), "TEXT DATA BSS"); #ifdef CONFIG_BLK_DEV_INITRD /* Reserve INITRD */ @@ -49,7 +51,7 @@ 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); - reserve_early(ramdisk_image, ramdisk_end, "RAMDISK"); + memblock_x86_reserve_range(ramdisk_image, ramdisk_end, "RAMDISK"); } #endif diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c index 7147143fd61..2d2673c28af 100644 --- a/arch/x86/kernel/head64.c +++ b/arch/x86/kernel/head64.c @@ -12,6 +12,7 @@ #include <linux/percpu.h> #include <linux/start_kernel.h> #include <linux/io.h> +#include <linux/memblock.h> #include <asm/processor.h> #include <asm/proto.h> @@ -79,6 +80,8 @@ void __init x86_64_start_kernel(char * real_mode_data) /* Cleanup the over mapped high alias */ cleanup_highmap(); + max_pfn_mapped = KERNEL_IMAGE_SIZE >> PAGE_SHIFT; + for (i = 0; i < NUM_EXCEPTION_VECTORS; i++) { #ifdef CONFIG_EARLY_PRINTK set_intr_gate(i, &early_idt_handlers[i]); @@ -98,7 +101,9 @@ void __init x86_64_start_reservations(char *real_mode_data) { copy_bootdata(__va(real_mode_data)); - reserve_early(__pa_symbol(&_text), __pa_symbol(&__bss_stop), "TEXT DATA BSS"); + memblock_init(); + + memblock_x86_reserve_range(__pa_symbol(&_text), __pa_symbol(&__bss_stop), "TEXT DATA BSS"); #ifdef CONFIG_BLK_DEV_INITRD /* Reserve INITRD */ @@ -107,7 +112,7 @@ 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); - reserve_early(ramdisk_image, ramdisk_end, "RAMDISK"); + memblock_x86_reserve_range(ramdisk_image, ramdisk_end, "RAMDISK"); } #endif diff --git a/arch/x86/kernel/mpparse.c b/arch/x86/kernel/mpparse.c index d7b6f7fb4fe..9af64d9c4b6 100644 --- a/arch/x86/kernel/mpparse.c +++ b/arch/x86/kernel/mpparse.c @@ -11,6 +11,7 @@ #include <linux/init.h> #include <linux/delay.h> #include <linux/bootmem.h> +#include <linux/memblock.h> #include <linux/kernel_stat.h> #include <linux/mc146818rtc.h> #include <linux/bitops.h> @@ -657,7 +658,7 @@ static void __init smp_reserve_memory(struct mpf_intel *mpf) { unsigned long size = get_mpc_size(mpf->physptr); - reserve_early_overlap_ok(mpf->physptr, mpf->physptr+size, "MP-table mpc"); + memblock_x86_reserve_range(mpf->physptr, mpf->physptr+size, "* MP-table mpc"); } static int __init smp_scan_config(unsigned long base, unsigned long length) @@ -686,7 +687,7 @@ static int __init smp_scan_config(unsigned long base, unsigned long length) mpf, (u64)virt_to_phys(mpf)); mem = virt_to_phys(mpf); - reserve_early_overlap_ok(mem, mem + sizeof(*mpf), "MP-table mpf"); + memblock_x86_reserve_range(mem, mem + sizeof(*mpf), "* MP-table mpf"); if (mpf->physptr) smp_reserve_memory(mpf); diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index a59f6a6df5e..420e6419785 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -31,6 +31,7 @@ #include <linux/apm_bios.h> #include <linux/initrd.h> #include <linux/bootmem.h> +#include <linux/memblock.h> #include <linux/seq_file.h> #include <linux/console.h> #include <linux/mca.h> @@ -301,7 +302,7 @@ static inline void init_gbpages(void) static void __init reserve_brk(void) { if (_brk_end > _brk_start) - reserve_early(__pa(_brk_start), __pa(_brk_end), "BRK"); + memblock_x86_reserve_range(__pa(_brk_start), __pa(_brk_end), "BRK"); /* Mark brk area as locked down and no longer taking any new allocations */ @@ -323,17 +324,16 @@ static void __init relocate_initrd(void) char *p, *q; /* We need to move the initrd down into lowmem */ - ramdisk_here = find_e820_area(0, end_of_lowmem, area_size, + ramdisk_here = memblock_find_in_range(0, end_of_lowmem, area_size, PAGE_SIZE); - if (ramdisk_here == -1ULL) + if (ramdisk_here == MEMBLOCK_ERROR) 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. */ - reserve_early(ramdisk_here, ramdisk_here + area_size, - "NEW RAMDISK"); + memblock_x86_reserve_range(ramdisk_here, ramdisk_here + area_size, "NEW RAMDISK"); initrd_start = ramdisk_here + PAGE_OFFSET; initrd_end = initrd_start + ramdisk_size; printk(KERN_INFO "Allocated new RAMDISK: %08llx - %08llx\n", @@ -389,7 +389,7 @@ static void __init reserve_initrd(void) initrd_start = 0; if (ramdisk_size >= (end_of_lowmem>>1)) { - free_early(ramdisk_image, ramdisk_end); + memblock_x86_free_range(ramdisk_image, ramdisk_end); printk(KERN_ERR "initrd too large to handle, " "disabling initrd\n"); return; @@ -412,7 +412,7 @@ static void __init reserve_initrd(void) relocate_initrd(); - free_early(ramdisk_image, ramdisk_end); + memblock_x86_free_range(ramdisk_image, ramdisk_end); } #else static void __init reserve_initrd(void) @@ -468,7 +468,7 @@ static void __init e820_reserve_setup_data(void) e820_print_map("reserve setup_data"); } -static void __init reserve_early_setup_data(void) +static void __init memblock_x86_reserve_range_setup_data(void) { struct setup_data *data; u64 pa_data; @@ -480,7 +480,7 @@ static void __init reserve_early_setup_data(void) while (pa_data) { data = early_memremap(pa_data, sizeof(*data)); sprintf(buf, "setup data %x", data->type); - reserve_early(pa_data, pa_data+sizeof(*data)+data->len, buf); + memblock_x86_reserve_range(pa_data, pa_data+sizeof(*data)+data->len, buf); pa_data = data->next; early_iounmap(data, sizeof(*data)); } @@ -501,6 +501,7 @@ static inline unsigned long long get_total_mem(void) return total << PAGE_SHIFT; } +#define DEFAULT_BZIMAGE_ADDR_MAX 0x37FFFFFF static void __init reserve_crashkernel(void) { unsigned long long total_mem; @@ -518,23 +519,27 @@ static void __init reserve_crashkernel(void) if (crash_base <= 0) { const unsigned long long alignment = 16<<20; /* 16M */ - crash_base = find_e820_area(alignment, ULONG_MAX, crash_size, - alignment); - if (crash_base == -1ULL) { + /* + * kexec want bzImage is below DEFAULT_BZIMAGE_ADDR_MAX + */ + crash_base = memblock_find_in_range(alignment, + DEFAULT_BZIMAGE_ADDR_MAX, crash_size, alignment); + + if (crash_base == MEMBLOCK_ERROR) { pr_info("crashkernel reservation failed - No suitable area found.\n"); return; } } else { unsigned long long start; - start = find_e820_area(crash_base, ULONG_MAX, crash_size, - 1<<20); + start = memblock_find_in_range(crash_base, + crash_base + crash_size, crash_size, 1<<20); if (start != crash_base) { pr_info("crashkernel reservation failed - memory is in use.\n"); return; } } - reserve_early(crash_base, crash_base + crash_size, "CRASH KERNEL"); + memblock_x86_reserve_range(crash_base, crash_base + crash_size, "CRASH KERNEL"); printk(KERN_INFO "Reserving %ldMB of memory at %ldMB " "for crashkernel (System RAM: %ldMB)\n", @@ -614,7 +619,7 @@ static __init void reserve_ibft_region(void) addr = find_ibft_region(&size); if (size) - reserve_early_overlap_ok(addr, addr + size, "ibft"); + memblock_x86_reserve_range(addr, addr + size, "* ibft"); } static unsigned reserve_low = CONFIG_X86_RESERVE_LOW << 10; @@ -664,6 +669,15 @@ static int __init parse_reservelow(char *p) early_param("reservelow", parse_reservelow); +static u64 __init get_max_mapped(void) +{ + u64 end = max_pfn_mapped; + + end <<= PAGE_SHIFT; + + return end; +} + /* * Determine if we were loaded by an EFI loader. If so, then we have also been * passed the efi memmap, systab, etc., so we should use these data structures @@ -738,7 +752,7 @@ void __init setup_arch(char **cmdline_p) #endif 4)) { efi_enabled = 1; - efi_reserve_early(); + efi_memblock_x86_reserve_range(); } #endif @@ -795,7 +809,7 @@ void __init setup_arch(char **cmdline_p) x86_report_nx(); /* after early param, so could get panic from serial */ - reserve_early_setup_data(); + memblock_x86_reserve_range_setup_data(); if (acpi_mps_check()) { #ifdef CONFIG_X86_LOCAL_APIC @@ -848,8 +862,6 @@ void __init setup_arch(char **cmdline_p) */ max_pfn = e820_end_of_ram_pfn(); - /* preallocate 4k for mptable mpc */ - early_reserve_e820_mpc_new(); /* update e820 for memory not covered by WB MTRRs */ mtrr_bp_init(); if (mtrr_trim_uncached_memory(max_pfn)) @@ -871,18 +883,8 @@ void __init setup_arch(char **cmdline_p) max_low_pfn = max_pfn; high_memory = (void *)__va(max_pfn * PAGE_SIZE - 1) + 1; - max_pfn_mapped = KERNEL_IMAGE_SIZE >> PAGE_SHIFT; -#endif - -#ifdef CONFIG_X86_CHECK_BIOS_CORRUPTION - setup_bios_corruption_check(); #endif - printk(KERN_DEBUG "initial memory mapped : 0 - %08lx\n", - max_pfn_mapped<<PAGE_SHIFT); - - reserve_brk(); - /* * Find and reserve possible boot-time SMP configuration: */ @@ -890,6 +892,26 @@ void __init setup_arch(char **cmdline_p) reserve_ibft_region(); + /* + * Need to conclude brk, before memblock_x86_fill() + * it could use memblock_find_in_range, could overlap with + * brk area. + */ + reserve_brk(); + + memblock.current_limit = get_max_mapped(); + memblock_x86_fill(); + + /* preallocate 4k for mptable mpc */ + early_reserve_e820_mpc_new(); + +#ifdef CONFIG_X86_CHECK_BIOS_CORRUPTION + setup_bios_corruption_check(); +#endif + + printk(KERN_DEBUG "initial memory mapped : 0 - %08lx\n", + max_pfn_mapped<<PAGE_SHIFT); + reserve_trampoline_memory(); #ifdef CONFIG_ACPI_SLEEP @@ -913,6 +935,7 @@ void __init setup_arch(char **cmdline_p) max_low_pfn = max_pfn; } #endif + memblock.current_limit = get_max_mapped(); /* * NOTE: On x86-32, only from this point on, fixmaps are ready for use. @@ -951,10 +974,7 @@ void __init setup_arch(char **cmdline_p) #endif initmem_init(0, max_pfn, acpi, k8); -#ifndef CONFIG_NO_BOOTMEM - early_res_to_bootmem(0, max_low_pfn<<PAGE_SHIFT); -#endif - + memblock_find_dma_reserve(); dma32_reserve_bootmem(); #ifdef CONFIG_KVM_CLOCK diff --git a/arch/x86/kernel/setup_percpu.c b/arch/x86/kernel/setup_percpu.c index 2335c15c93a..002b79685f7 100644 --- a/arch/x86/kernel/setup_percpu.c +++ b/arch/x86/kernel/setup_percpu.c @@ -131,13 +131,7 @@ static void * __init pcpu_fc_alloc(unsigned int cpu, size_t size, size_t align) static void __init pcpu_fc_free(void *ptr, size_t size) { -#ifdef CONFIG_NO_BOOTMEM - u64 start = __pa(ptr); - u64 end = start + size; - free_early_partial(start, end); -#else free_bootmem(__pa(ptr), size); -#endif } static int __init pcpu_cpu_distance(unsigned int from, unsigned int to) diff --git a/arch/x86/kernel/trampoline.c b/arch/x86/kernel/trampoline.c index e2a59525739..4c3da5674e6 100644 --- a/arch/x86/kernel/trampoline.c +++ b/arch/x86/kernel/trampoline.c @@ -1,8 +1,8 @@ #include <linux/io.h> +#include <linux/memblock.h> #include <asm/trampoline.h> #include <asm/pgtable.h> -#include <asm/e820.h> #if defined(CONFIG_X86_64) && defined(CONFIG_ACPI_SLEEP) #define __trampinit @@ -17,15 +17,15 @@ unsigned char *__trampinitdata trampoline_base; void __init reserve_trampoline_memory(void) { - unsigned long mem; + phys_addr_t mem; /* Has to be in very low memory so we can execute real-mode AP code. */ - mem = find_e820_area(0, 1<<20, TRAMPOLINE_SIZE, PAGE_SIZE); - if (mem == -1L) + mem = memblock_find_in_range(0, 1<<20, TRAMPOLINE_SIZE, PAGE_SIZE); + if (mem == MEMBLOCK_ERROR) panic("Cannot allocate trampoline\n"); trampoline_base = __va(mem); - reserve_early(mem, mem + TRAMPOLINE_SIZE, "TRAMPOLINE"); + memblock_x86_reserve_range(mem, mem + TRAMPOLINE_SIZE, "TRAMPOLINE"); } /* diff --git a/arch/x86/mm/Makefile b/arch/x86/mm/Makefile index a4c768397ba..55543397a8a 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 b278535b14a..c0e28a13de7 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 558f2d33207..5d0a6711c28 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 c55f900fbf8..84346200e78 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 3ba6e0608c5..0369843511d 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 52d54bfc1eb..804a3b6c6e1 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 00000000000..aa1169392b8 --- /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 18d244f7020..92faf3a1c53 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 809baaaf48b..84a3e4c9f27 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 4962f1aeda6..60f498511dd 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 9324f13492d..a17dffd136c 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 9c0d0d399c3..a35cb9d8b06 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); diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c index 7d46c844141..63b83ceebd1 100644 --- a/arch/x86/xen/enlighten.c +++ b/arch/x86/xen/enlighten.c @@ -30,6 +30,7 @@ #include <linux/console.h> #include <linux/pci.h> #include <linux/gfp.h> +#include <linux/memblock.h> #include <xen/xen.h> #include <xen/interface/xen.h> @@ -1183,6 +1184,8 @@ asmlinkage void __init xen_start_kernel(void) local_irq_disable(); early_boot_irqs_off(); + memblock_init(); + xen_raw_console_write("mapping kernel into physical memory\n"); pgd = xen_setup_kernel_pagetable(pgd, xen_start_info->nr_pages); diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c index b2363fcbcd0..f72d18c6922 100644 --- a/arch/x86/xen/mmu.c +++ b/arch/x86/xen/mmu.c @@ -45,6 +45,7 @@ #include <linux/vmalloc.h> #include <linux/module.h> #include <linux/gfp.h> +#include <linux/memblock.h> #include <asm/pgtable.h> #include <asm/tlbflush.h> @@ -55,6 +56,7 @@ #include <asm/e820.h> #include <asm/linkage.h> #include <asm/page.h> +#include <asm/init.h> #include <asm/xen/hypercall.h> #include <asm/xen/hypervisor.h> @@ -359,7 +361,8 @@ void make_lowmem_page_readonly(void *vaddr) unsigned int level; pte = lookup_address(address, &level); - BUG_ON(pte == NULL); + if (pte == NULL) + return; /* vaddr missing */ ptev = pte_wrprotect(*pte); @@ -374,7 +377,8 @@ void make_lowmem_page_readwrite(void *vaddr) unsigned int level; pte = lookup_address(address, &level); - BUG_ON(pte == NULL); + if (pte == NULL) + return; /* vaddr missing */ ptev = pte_mkwrite(*pte); @@ -1508,13 +1512,25 @@ static void xen_pgd_free(struct mm_struct *mm, pgd_t *pgd) #endif } -#ifdef CONFIG_X86_32 static __init pte_t mask_rw_pte(pte_t *ptep, pte_t pte) { + unsigned long pfn = pte_pfn(pte); + +#ifdef CONFIG_X86_32 /* If there's an existing pte, then don't allow _PAGE_RW to be set */ if (pte_val_ma(*ptep) & _PAGE_PRESENT) pte = __pte_ma(((pte_val_ma(*ptep) & _PAGE_RW) | ~_PAGE_RW) & pte_val_ma(pte)); +#endif + + /* + * If the new pfn is within the range of the newly allocated + * kernel pagetable, and it isn't being mapped into an + * early_ioremap fixmap slot, make sure it is RO. + */ + if (!is_early_ioremap_ptep(ptep) && + pfn >= e820_table_start && pfn < e820_table_end) + pte = pte_wrprotect(pte); return pte; } @@ -1527,7 +1543,6 @@ static __init void xen_set_pte_init(pte_t *ptep, pte_t pte) xen_set_pte(ptep, pte); } -#endif static void pin_pagetable_pfn(unsigned cmd, unsigned long pfn) { @@ -1814,7 +1829,7 @@ __init pgd_t *xen_setup_kernel_pagetable(pgd_t *pgd, __xen_write_cr3(true, __pa(pgd)); xen_mc_issue(PARAVIRT_LAZY_CPU); - reserve_early(__pa(xen_start_info->pt_base), + 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"); @@ -1852,7 +1867,7 @@ __init pgd_t *xen_setup_kernel_pagetable(pgd_t *pgd, pin_pagetable_pfn(MMUEXT_PIN_L3_TABLE, PFN_DOWN(__pa(swapper_pg_dir))); - reserve_early(__pa(xen_start_info->pt_base), + 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"); @@ -1971,11 +1986,7 @@ static const struct pv_mmu_ops xen_mmu_ops __initdata = { .alloc_pmd = xen_alloc_pmd_init, .release_pmd = xen_release_pmd_init, -#ifdef CONFIG_X86_64 - .set_pte = xen_set_pte, -#else .set_pte = xen_set_pte_init, -#endif .set_pte_at = xen_set_pte_at, .set_pmd = xen_set_pmd_hyper, diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c index 328b0030542..9729c903404 100644 --- a/arch/x86/xen/setup.c +++ b/arch/x86/xen/setup.c @@ -8,6 +8,7 @@ #include <linux/sched.h> #include <linux/mm.h> #include <linux/pm.h> +#include <linux/memblock.h> #include <asm/elf.h> #include <asm/vdso.h> @@ -129,7 +130,7 @@ char * __init xen_memory_setup(void) * - xen_start_info * See comment above "struct start_info" in <xen/interface/xen.h> */ - reserve_early(__pa(xen_start_info->mfn_list), + memblock_x86_reserve_range(__pa(xen_start_info->mfn_list), __pa(xen_start_info->pt_base), "XEN START INFO"); |