From 72d7c3b33c980843e756681fb4867dc1efd62a76 Mon Sep 17 00:00:00 2001 From: Yinghai Lu Date: Wed, 25 Aug 2010 13:39:17 -0700 Subject: [PATCH] x86: Use memblock to replace early_res 1. replace find_e820_area with memblock_find_in_range 2. replace reserve_early with memblock_x86_reserve_range 3. replace free_early with memblock_x86_free_range. 4. NO_BOOTMEM will switch to use memblock too. 5. use _e820, _early wrap in the patch, in following patch, will replace them all 6. because memblock_x86_free_range support partial free, we can remove some special care 7. Need to make sure that memblock_find_in_range() is called after memblock_x86_fill() so adjust some calling later in setup.c::setup_arch() -- corruption_check and mptable_update -v2: Move reserve_brk() early Before fill_memblock_area, to avoid overlap between brk and memblock_find_in_range() that could happen We have more then 128 RAM entry in E820 tables, and memblock_x86_fill() could use memblock_find_in_range() to find a new place for memblock.memory.region array. and We don't need to use extend_brk() after fill_memblock_area() So move reserve_brk() early before fill_memblock_area(). -v3: Move find_smp_config early To make sure memblock_find_in_range not find wrong place, if BIOS doesn't put mptable in right place. -v4: Treat RESERVED_KERN as RAM in memblock.memory. and they are already in memblock.reserved already.. use __NOT_KEEP_MEMBLOCK to make sure memblock related code could be freed later. -v5: Generic version __memblock_find_in_range() is going from high to low, and for 32bit active_region for 32bit does include high pages need to replace the limit with memblock.default_alloc_limit, aka get_max_mapped() -v6: Use current_limit instead -v7: check with MEMBLOCK_ERROR instead of -1ULL or -1L -v8: Set memblock_can_resize early to handle EFI with more RAM entries -v9: update after kmemleak changes in mainline Suggested-by: David S. Miller Suggested-by: Benjamin Herrenschmidt Suggested-by: Thomas Gleixner Signed-off-by: Yinghai Lu Signed-off-by: H. Peter Anvin --- arch/x86/Kconfig | 9 +- arch/x86/include/asm/e820.h | 14 +-- arch/x86/kernel/check.c | 16 ++-- arch/x86/kernel/e820.c | 159 +++++++++++---------------------- arch/x86/kernel/head.c | 3 +- arch/x86/kernel/head32.c | 6 +- arch/x86/kernel/head64.c | 3 + arch/x86/kernel/mpparse.c | 5 +- arch/x86/kernel/setup.c | 46 +++++++--- arch/x86/kernel/setup_percpu.c | 6 -- arch/x86/mm/numa_64.c | 9 +- mm/bootmem.c | 3 + mm/page_alloc.c | 50 ++++------- mm/sparse-vmemmap.c | 11 --- 14 files changed, 141 insertions(+), 199 deletions(-) diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index dcb0593b4a66..542bb2610cbb 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -27,6 +27,7 @@ config X86 select HAVE_PERF_EVENTS if (!M386 && !M486) select HAVE_IOREMAP_PROT select HAVE_KPROBES + select HAVE_MEMBLOCK select ARCH_WANT_OPTIONAL_GPIOLIB select ARCH_WANT_FRAME_POINTERS select HAVE_DMA_ATTRS @@ -195,9 +196,6 @@ 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 @@ -590,14 +588,13 @@ config NO_BOOTMEM default y bool "Disable Bootmem code" ---help--- - Use early_res directly instead of bootmem before slab is ready. + Use memblock directly instead of bootmem before slab is ready. - allocator (buddy) [generic] - early allocator (bootmem) [generic] - - very early allocator (reserve_early*()) [x86] + - very early allocator (memblock) [some generic] - very very early allocator (early brk model) [x86] So reduce one layer between early allocator to final allocator - config MEMTEST bool "Memtest" ---help--- diff --git a/arch/x86/include/asm/e820.h b/arch/x86/include/asm/e820.h index ec8a52d14ab1..388fed291467 100644 --- a/arch/x86/include/asm/e820.h +++ b/arch/x86/include/asm/e820.h @@ -117,24 +117,26 @@ 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 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); + extern void finish_e820_parsing(void); extern void e820_reserve_resources(void); extern void e820_reserve_resources_late(void); extern void setup_memory_map(void); extern char *default_machine_specific_memory_setup(void); +void reserve_early(u64 start, u64 end, char *name); +void free_early(u64 start, u64 end); + /* * Returns true iff the specified range [s,e) is completely contained inside * the ISA region. diff --git a/arch/x86/kernel/check.c b/arch/x86/kernel/check.c index fc999e6fc46a..13a389179514 100644 --- a/arch/x86/kernel/check.c +++ b/arch/x86/kernel/check.c @@ -2,7 +2,8 @@ #include #include #include -#include +#include + #include /* @@ -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 0d6fc71bedb1..a9221d18a5ed 100644 --- a/arch/x86/kernel/e820.c +++ b/arch/x86/kernel/e820.c @@ -15,6 +15,7 @@ #include #include #include +#include #include #include @@ -742,69 +743,29 @@ core_initcall(e820_mark_nvs_memory); */ u64 __init find_e820_area(u64 start, u64 end, u64 size, u64 align) { - int i; + u64 mem = memblock_find_in_range(start, end, size, align); - for (i = 0; i < e820.nr_map; i++) { - struct e820entry *ei = &e820.map[i]; - u64 addr; - u64 ei_start, ei_last; + if (mem == MEMBLOCK_ERROR) + return -1ULL; - 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; + return mem; } -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; + u64 mem = memblock_x86_find_in_range_size(start, sizep, align); - for (i = 0; i < e820.nr_map; i++) { - struct e820entry *ei = &e820.map[i]; - u64 addr; - u64 ei_start, ei_last; + if (mem == MEMBLOCK_ERROR) + return -1ULL - 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; + return mem; } /* - * 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 +774,8 @@ 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 +791,9 @@ 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; @@ -895,52 +855,12 @@ 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); + memblock_x86_register_active_regions(nid, start_pfn, last_pfn); } /* @@ -950,18 +870,16 @@ void __init e820_register_active_regions(int nid, unsigned long start_pfn, */ 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; + return memblock_x86_hole_size(start, end); +} - 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); +void reserve_early(u64 start, u64 end, char *name) +{ + memblock_x86_reserve_range(start, end, name); +} +void free_early(u64 start, u64 end) +{ + memblock_x86_free_range(start, end); } static void early_panic(char *msg) @@ -1210,3 +1128,32 @@ 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(); +} diff --git a/arch/x86/kernel/head.c b/arch/x86/kernel/head.c index 3e66bd364a9d..af0699ba48cf 100644 --- a/arch/x86/kernel/head.c +++ b/arch/x86/kernel/head.c @@ -1,5 +1,6 @@ #include #include +#include #include #include @@ -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 b2e246037392..da60aa8a850f 100644 --- a/arch/x86/kernel/head32.c +++ b/arch/x86/kernel/head32.c @@ -8,6 +8,7 @@ #include #include #include +#include #include #include @@ -30,14 +31,15 @@ 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"); diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c index 7147143fd614..8ee930fdeeb9 100644 --- a/arch/x86/kernel/head64.c +++ b/arch/x86/kernel/head64.c @@ -12,6 +12,7 @@ #include #include #include +#include #include #include @@ -98,6 +99,8 @@ void __init x86_64_start_reservations(char *real_mode_data) { copy_bootdata(__va(real_mode_data)); + memblock_init(); + reserve_early(__pa_symbol(&_text), __pa_symbol(&__bss_stop), "TEXT DATA BSS"); #ifdef CONFIG_BLK_DEV_INITRD diff --git a/arch/x86/kernel/mpparse.c b/arch/x86/kernel/mpparse.c index d86dbf7e54be..8252545ae6f3 100644 --- a/arch/x86/kernel/mpparse.c +++ b/arch/x86/kernel/mpparse.c @@ -11,6 +11,7 @@ #include #include #include +#include #include #include #include @@ -641,7 +642,7 @@ 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) @@ -670,7 +671,7 @@ 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 b4ae4acbd031..bbe0aaf77494 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -31,6 +31,7 @@ #include #include #include +#include #include #include #include @@ -614,7 +615,7 @@ 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"); } #ifdef CONFIG_X86_RESERVE_LOW_64K @@ -708,6 +709,15 @@ static void __init trim_bios_range(void) sanitize_e820_map(e820.map, ARRAY_SIZE(e820.map), &e820.nr_map); } +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 @@ -891,8 +901,6 @@ 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)) @@ -917,15 +925,6 @@ void __init setup_arch(char **cmdline_p) 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< #include #include +#include #include #include #include @@ -171,8 +172,8 @@ static void * __init early_node_mem(int nodeid, unsigned long start, if (start < (MAX_DMA32_PFN< (MAX_DMA32_PFN< #include #include +#include #include #include @@ -434,6 +435,7 @@ void __init free_bootmem_node(pg_data_t *pgdat, unsigned long physaddr, unsigned long size) { #ifdef CONFIG_NO_BOOTMEM + kmemleak_free_part(__va(physaddr), size); free_early(physaddr, physaddr + size); #else unsigned long start, end; @@ -459,6 +461,7 @@ void __init free_bootmem_node(pg_data_t *pgdat, unsigned long physaddr, void __init free_bootmem(unsigned long addr, unsigned long size) { #ifdef CONFIG_NO_BOOTMEM + kmemleak_free_part(__va(addr), size); free_early(addr, addr + size); #else unsigned long start, end; diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 8c9b34674d83..f2cd7450fa76 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -3667,46 +3667,26 @@ int __init add_from_early_node_map(struct range *range, int az, void * __init __alloc_memory_core_early(int nid, u64 size, u64 align, u64 goal, u64 limit) { - int i; void *ptr; + u64 addr; - if (limit > get_max_mapped()) - limit = get_max_mapped(); + if (limit > memblock.current_limit) + limit = memblock.current_limit; - /* need to go over early_node_map to find out good range for node */ - for_each_active_range_index_in_nid(i, nid) { - u64 addr; - u64 ei_start, ei_last; + addr = find_memory_core_early(nid, size, align, goal, limit); - ei_last = early_node_map[i].end_pfn; - ei_last <<= PAGE_SHIFT; - ei_start = early_node_map[i].start_pfn; - ei_start <<= PAGE_SHIFT; - addr = find_early_area(ei_start, ei_last, - goal, limit, size, align); + if (addr == MEMBLOCK_ERROR) + return NULL; - if (addr == -1ULL) - continue; - -#if 0 - printk(KERN_DEBUG "alloc (nid=%d %llx - %llx) (%llx - %llx) %llx %llx => %llx\n", - nid, - ei_start, ei_last, goal, limit, size, - align, addr); -#endif - - ptr = phys_to_virt(addr); - memset(ptr, 0, size); - reserve_early_without_check(addr, addr + size, "BOOTMEM"); - /* - * The min_count is set to 0 so that bootmem allocated blocks - * are never reported as leaks. - */ - kmemleak_alloc(ptr, size, 0, 0); - return ptr; - } - - return NULL; + ptr = phys_to_virt(addr); + memset(ptr, 0, size); + memblock_x86_reserve_range(addr, addr + size, "BOOTMEM"); + /* + * The min_count is set to 0 so that bootmem allocated blocks + * are never reported as leaks. + */ + kmemleak_alloc(ptr, size, 0, 0); + return ptr; } #endif diff --git a/mm/sparse-vmemmap.c b/mm/sparse-vmemmap.c index aa33fd67fa41..29d6cbffb283 100644 --- a/mm/sparse-vmemmap.c +++ b/mm/sparse-vmemmap.c @@ -220,18 +220,7 @@ void __init sparse_mem_maps_populate_node(struct page **map_map, if (vmemmap_buf_start) { /* need to free left buf */ -#ifdef CONFIG_NO_BOOTMEM - free_early(__pa(vmemmap_buf_start), __pa(vmemmap_buf_end)); - if (vmemmap_buf_start < vmemmap_buf) { - char name[15]; - - snprintf(name, sizeof(name), "MEMMAP %d", nodeid); - reserve_early_without_check(__pa(vmemmap_buf_start), - __pa(vmemmap_buf), name); - } -#else free_bootmem(__pa(vmemmap_buf), vmemmap_buf_end - vmemmap_buf); -#endif vmemmap_buf = NULL; vmemmap_buf_end = NULL; }