From 08677214e318297f228237be0042aac754f48f1d Mon Sep 17 00:00:00 2001 From: Yinghai Lu Date: Wed, 10 Feb 2010 01:20:20 -0800 Subject: x86: Make 64 bit use early_res instead of bootmem before slab Finally we can use early_res to replace bootmem for x86_64 now. Still can use CONFIG_NO_BOOTMEM to enable it or not. -v2: fix 32bit compiling about MAX_DMA32_PFN -v3: folded bug fix from LKML message below Signed-off-by: Yinghai Lu LKML-Reference: <4B747239.4070907@kernel.org> Signed-off-by: H. Peter Anvin --- arch/x86/Kconfig | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'arch/x86/Kconfig') diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index eb4092568f9..95439843ceb 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -568,6 +568,19 @@ config PARAVIRT_DEBUG Enable to debug paravirt_ops internals. Specifically, BUG if a paravirt_op is missing when it is called. +config NO_BOOTMEM + default y + bool "Disable Bootmem code" + depends on X86_64 + ---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 + + config MEMTEST bool "Memtest" ---help--- -- cgit v1.2.3-70-g09d2 From 59be5a8e8ce765cf739ec7f07176219972de7481 Mon Sep 17 00:00:00 2001 From: Yinghai Lu Date: Wed, 10 Feb 2010 01:20:28 -0800 Subject: x86: Make 32bit support NO_BOOTMEM Let's make 32bit consistent with 64bit. -v2: Andrew pointed out for 32bit that we should use -1ULL Signed-off-by: Yinghai Lu LKML-Reference: <1265793639-15071-25-git-send-email-yinghai@kernel.org> Signed-off-by: H. Peter Anvin --- arch/x86/Kconfig | 1 - arch/x86/kernel/early_res.c | 3 +++ arch/x86/mm/init_32.c | 6 ++++++ arch/x86/mm/numa_32.c | 3 +++ 4 files changed, 12 insertions(+), 1 deletion(-) (limited to 'arch/x86/Kconfig') diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 95439843ceb..29f9efb74fc 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -571,7 +571,6 @@ config PARAVIRT_DEBUG config NO_BOOTMEM default y bool "Disable Bootmem code" - depends on X86_64 ---help--- Use early_res directly instead of bootmem before slab is ready. - allocator (buddy) [generic] diff --git a/arch/x86/kernel/early_res.c b/arch/x86/kernel/early_res.c index dbf08bd0125..656cdf86a2f 100644 --- a/arch/x86/kernel/early_res.c +++ b/arch/x86/kernel/early_res.c @@ -354,6 +354,9 @@ int __init get_free_all_memory_range(struct range **rangep, int nodeid) /* need to go over early_node_map to find out good range for node */ nr_range = add_from_early_node_map(range, count, nr_range, nodeid); +#ifdef CONFIG_X86_32 + subtract_range(range, count, max_low_pfn, -1ULL); +#endif subtract_early_res(range, count); nr_range = clean_sort_range(range, count); diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c index 2dccde06d22..262867a7d43 100644 --- a/arch/x86/mm/init_32.c +++ b/arch/x86/mm/init_32.c @@ -748,6 +748,7 @@ 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, @@ -767,9 +768,11 @@ static unsigned long __init setup_node_bootmem(int nodeid, return bootmap + bootmap_size; } +#endif void __init setup_bootmem_allocator(void) { +#ifndef CONFIG_NO_BOOTMEM int nodeid; unsigned long bootmap_size, bootmap; /* @@ -781,11 +784,13 @@ void __init setup_bootmem_allocator(void) 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<node_id = nid; +#ifndef CONFIG_NO_BOOTMEM NODE_DATA(nid)->bdata = &bootmem_node_data[nid]; +#endif } setup_bootmem_allocator(); -- cgit v1.2.3-70-g09d2 From 580e0ad21d6d6f932461d24b47041e3dd499c23f Mon Sep 17 00:00:00 2001 From: Yinghai Lu Date: Tue, 16 Feb 2010 18:40:35 -0800 Subject: core: Move early_res from arch/x86 to kernel/ This makes the range reservation feature available to other architectures. -v2: add get_max_mapped, max_pfn_mapped only defined in x86... to fix PPC compiling -v3: according to hpa, add CONFIG_HAVE_EARLY_RES -v4: fix typo about EARLY_RES in config Signed-off-by: Yinghai Lu LKML-Reference: <4B7B5723.4070009@kernel.org> Signed-off-by: H. Peter Anvin --- arch/x86/Kconfig | 3 + arch/x86/include/asm/e820.h | 2 +- arch/x86/include/asm/early_res.h | 21 -- arch/x86/kernel/Makefile | 2 +- arch/x86/kernel/e820.c | 10 +- arch/x86/kernel/early_res.c | 521 --------------------------------------- include/linux/early_res.h | 22 ++ kernel/Makefile | 1 + kernel/early_res.c | 513 ++++++++++++++++++++++++++++++++++++++ 9 files changed, 550 insertions(+), 545 deletions(-) delete mode 100644 arch/x86/include/asm/early_res.h delete mode 100644 arch/x86/kernel/early_res.c create mode 100644 include/linux/early_res.h create mode 100644 kernel/early_res.c (limited to 'arch/x86/Kconfig') diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 29f9efb74fc..0e9f8b10de5 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -183,6 +183,9 @@ 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 diff --git a/arch/x86/include/asm/e820.h b/arch/x86/include/asm/e820.h index a8299e13443..0e22296790d 100644 --- a/arch/x86/include/asm/e820.h +++ b/arch/x86/include/asm/e820.h @@ -112,7 +112,7 @@ 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 +#include extern unsigned long e820_end_of_ram_pfn(void); extern unsigned long e820_end_of_low_ram_pfn(void); diff --git a/arch/x86/include/asm/early_res.h b/arch/x86/include/asm/early_res.h deleted file mode 100644 index 9758f3df9da..00000000000 --- a/arch/x86/include/asm/early_res.h +++ /dev/null @@ -1,21 +0,0 @@ -#ifndef _ASM_X86_EARLY_RES_H -#define _ASM_X86_EARLY_RES_H -#ifdef __KERNEL__ - -extern void reserve_early(u64 start, u64 end, char *name); -extern void reserve_early_overlap_ok(u64 start, u64 end, char *name); -extern void free_early(u64 start, u64 end); -extern void early_res_to_bootmem(u64 start, u64 end); - -void reserve_early_without_check(u64 start, u64 end, char *name); -u64 find_early_area(u64 ei_start, u64 ei_last, u64 start, u64 end, - u64 size, u64 align); -u64 find_early_area_size(u64 ei_start, u64 ei_last, u64 start, - u64 *sizep, u64 align); -u64 find_fw_memmap_area(u64 start, u64 end, u64 size, u64 align); -#include -int get_free_all_memory_range(struct range **rangep, int nodeid); - -#endif /* __KERNEL__ */ - -#endif /* _ASM_X86_EARLY_RES_H */ diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile index f5fb9f0b627..d87f09bc5a5 100644 --- a/arch/x86/kernel/Makefile +++ b/arch/x86/kernel/Makefile @@ -38,7 +38,7 @@ obj-$(CONFIG_X86_32) += probe_roms_32.o obj-$(CONFIG_X86_32) += sys_i386_32.o i386_ksyms_32.o obj-$(CONFIG_X86_64) += sys_x86_64.o x8664_ksyms_64.o obj-$(CONFIG_X86_64) += syscall_64.o vsyscall_64.o -obj-y += bootflag.o e820.o early_res.o +obj-y += bootflag.o e820.o obj-y += pci-dma.o quirks.o i8237.o topology.o kdebugfs.o obj-y += alternative.o i8253.o pci-nommu.o hw_breakpoint.o obj-y += tsc.o io_delay.o rtc.o diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c index 36918d8463a..740b440fbd7 100644 --- a/arch/x86/kernel/e820.c +++ b/arch/x86/kernel/e820.c @@ -17,7 +17,6 @@ #include #include -#include #include #include @@ -752,6 +751,15 @@ 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 */ diff --git a/arch/x86/kernel/early_res.c b/arch/x86/kernel/early_res.c deleted file mode 100644 index 1458dc02234..00000000000 --- a/arch/x86/kernel/early_res.c +++ /dev/null @@ -1,521 +0,0 @@ -/* - * early_res, could be used to replace bootmem - */ -#include -#include -#include -#include -#include - -#include - -/* - * Early reserved memory areas. - */ -/* - * need to make sure this one is bigger enough before - * find_fw_memmap_area could be used - */ -#define MAX_EARLY_RES_X 32 - -struct early_res { - u64 start, end; - char name[15]; - char overlap_ok; -}; -static struct early_res early_res_x[MAX_EARLY_RES_X] __initdata; - -static int max_early_res __initdata = MAX_EARLY_RES_X; -static struct early_res *early_res __initdata = &early_res_x[0]; -static int early_res_count __initdata; - -static int __init find_overlapped_early(u64 start, u64 end) -{ - int i; - struct early_res *r; - - for (i = 0; i < max_early_res && early_res[i].end; i++) { - r = &early_res[i]; - if (end > r->start && start < r->end) - break; - } - - return i; -} - -/* - * Drop the i-th range from the early reservation map, - * by copying any higher ranges down one over it, and - * clearing what had been the last slot. - */ -static void __init drop_range(int i) -{ - int j; - - for (j = i + 1; j < max_early_res && early_res[j].end; j++) - ; - - memmove(&early_res[i], &early_res[i + 1], - (j - 1 - i) * sizeof(struct early_res)); - - early_res[j - 1].end = 0; - early_res_count--; -} - -/* - * Split any existing ranges that: - * 1) are marked 'overlap_ok', and - * 2) overlap with the stated range [start, end) - * into whatever portion (if any) of the existing range is entirely - * below or entirely above the stated range. Drop the portion - * of the existing range that overlaps with the stated range, - * which will allow the caller of this routine to then add that - * stated range without conflicting with any existing range. - */ -static void __init drop_overlaps_that_are_ok(u64 start, u64 end) -{ - int i; - struct early_res *r; - u64 lower_start, lower_end; - u64 upper_start, upper_end; - char name[15]; - - for (i = 0; i < max_early_res && early_res[i].end; i++) { - r = &early_res[i]; - - /* Continue past non-overlapping ranges */ - if (end <= r->start || start >= r->end) - continue; - - /* - * Leave non-ok overlaps as is; let caller - * panic "Overlapping early reservations" - * when it hits this overlap. - */ - if (!r->overlap_ok) - return; - - /* - * We have an ok overlap. We will drop it from the early - * reservation map, and add back in any non-overlapping - * portions (lower or upper) as separate, overlap_ok, - * non-overlapping ranges. - */ - - /* 1. Note any non-overlapping (lower or upper) ranges. */ - strncpy(name, r->name, sizeof(name) - 1); - - lower_start = lower_end = 0; - upper_start = upper_end = 0; - if (r->start < start) { - lower_start = r->start; - lower_end = start; - } - if (r->end > end) { - upper_start = end; - upper_end = r->end; - } - - /* 2. Drop the original ok overlapping range */ - drop_range(i); - - i--; /* resume for-loop on copied down entry */ - - /* 3. Add back in any non-overlapping ranges. */ - if (lower_end) - reserve_early_overlap_ok(lower_start, lower_end, name); - if (upper_end) - reserve_early_overlap_ok(upper_start, upper_end, name); - } -} - -static void __init __reserve_early(u64 start, u64 end, char *name, - int overlap_ok) -{ - int i; - struct early_res *r; - - i = find_overlapped_early(start, end); - if (i >= max_early_res) - panic("Too many early reservations"); - r = &early_res[i]; - if (r->end) - panic("Overlapping early reservations " - "%llx-%llx %s to %llx-%llx %s\n", - start, end - 1, name ? name : "", r->start, - r->end - 1, r->name); - r->start = start; - r->end = end; - r->overlap_ok = overlap_ok; - if (name) - strncpy(r->name, name, sizeof(r->name) - 1); - early_res_count++; -} - -/* - * A few early reservtations come here. - * - * The 'overlap_ok' in the name of this routine does -not- mean it - * is ok for these reservations to overlap an earlier reservation. - * Rather it means that it is ok for subsequent reservations to - * overlap this one. - * - * Use this entry point to reserve early ranges when you are doing - * so out of "Paranoia", reserving perhaps more memory than you need, - * just in case, and don't mind a subsequent overlapping reservation - * that is known to be needed. - * - * The drop_overlaps_that_are_ok() call here isn't really needed. - * It would be needed if we had two colliding 'overlap_ok' - * reservations, so that the second such would not panic on the - * overlap with the first. We don't have any such as of this - * writing, but might as well tolerate such if it happens in - * the future. - */ -void __init reserve_early_overlap_ok(u64 start, u64 end, char *name) -{ - drop_overlaps_that_are_ok(start, end); - __reserve_early(start, end, name, 1); -} - -u64 __init __weak find_fw_memmap_area(u64 start, u64 end, u64 size, u64 align) -{ - panic("should have find_fw_memmap_area defined with arch"); - - return -1ULL; -} - -static void __init __check_and_double_early_res(u64 ex_start, u64 ex_end) -{ - u64 start, end, size, mem; - struct early_res *new; - - /* do we have enough slots left ? */ - if ((max_early_res - early_res_count) > max(max_early_res/8, 2)) - return; - - /* double it */ - mem = -1ULL; - size = sizeof(struct early_res) * max_early_res * 2; - if (early_res == early_res_x) - start = 0; - else - start = early_res[0].end; - end = ex_start; - if (start + size < end) - mem = find_fw_memmap_area(start, end, size, - sizeof(struct early_res)); - if (mem == -1ULL) { - start = ex_end; - end = max_pfn_mapped << PAGE_SHIFT; - if (start + size < end) - mem = find_fw_memmap_area(start, end, size, - sizeof(struct early_res)); - } - if (mem == -1ULL) - panic("can not find more space for early_res array"); - - new = __va(mem); - /* save the first one for own */ - new[0].start = mem; - new[0].end = mem + size; - new[0].overlap_ok = 0; - /* copy old to new */ - if (early_res == early_res_x) { - memcpy(&new[1], &early_res[0], - sizeof(struct early_res) * max_early_res); - memset(&new[max_early_res+1], 0, - sizeof(struct early_res) * (max_early_res - 1)); - early_res_count++; - } else { - memcpy(&new[1], &early_res[1], - sizeof(struct early_res) * (max_early_res - 1)); - memset(&new[max_early_res], 0, - sizeof(struct early_res) * max_early_res); - } - memset(&early_res[0], 0, sizeof(struct early_res) * max_early_res); - early_res = new; - max_early_res *= 2; - printk(KERN_DEBUG "early_res array is doubled to %d at [%llx - %llx]\n", - max_early_res, mem, mem + size - 1); -} - -/* - * Most early reservations come here. - * - * We first have drop_overlaps_that_are_ok() drop any pre-existing - * 'overlap_ok' ranges, so that we can then reserve this memory - * range without risk of panic'ing on an overlapping overlap_ok - * early reservation. - */ -void __init reserve_early(u64 start, u64 end, char *name) -{ - if (start >= end) - return; - - __check_and_double_early_res(start, end); - - drop_overlaps_that_are_ok(start, end); - __reserve_early(start, end, name, 0); -} - -void __init reserve_early_without_check(u64 start, u64 end, char *name) -{ - struct early_res *r; - - if (start >= end) - return; - - __check_and_double_early_res(start, end); - - r = &early_res[early_res_count]; - - r->start = start; - r->end = end; - r->overlap_ok = 0; - if (name) - strncpy(r->name, name, sizeof(r->name) - 1); - early_res_count++; -} - -void __init free_early(u64 start, u64 end) -{ - struct early_res *r; - int i; - - i = find_overlapped_early(start, end); - r = &early_res[i]; - if (i >= max_early_res || r->end != end || r->start != start) - panic("free_early on not reserved area: %llx-%llx!", - start, end - 1); - - drop_range(i); -} - -#ifdef CONFIG_NO_BOOTMEM -static void __init subtract_early_res(struct range *range, int az) -{ - int i, count; - u64 final_start, final_end; - int idx = 0; - - count = 0; - for (i = 0; i < max_early_res && early_res[i].end; i++) - count++; - - /* need to skip first one ?*/ - if (early_res != early_res_x) - idx = 1; - -#define DEBUG_PRINT_EARLY_RES 1 - -#if DEBUG_PRINT_EARLY_RES - printk(KERN_INFO "Subtract (%d early reservations)\n", count); -#endif - for (i = idx; i < count; i++) { - struct early_res *r = &early_res[i]; -#if DEBUG_PRINT_EARLY_RES - printk(KERN_INFO " #%d [%010llx - %010llx] %15s\n", i, - r->start, r->end, r->name); -#endif - final_start = PFN_DOWN(r->start); - final_end = PFN_UP(r->end); - if (final_start >= final_end) - continue; - subtract_range(range, az, final_start, final_end); - } - -} - -int __init get_free_all_memory_range(struct range **rangep, int nodeid) -{ - int i, count; - u64 start = 0, end; - u64 size; - u64 mem; - struct range *range; - int nr_range; - - count = 0; - for (i = 0; i < max_early_res && early_res[i].end; i++) - count++; - - count *= 2; - - size = sizeof(struct range) * count; -#ifdef MAX_DMA32_PFN - if (max_pfn_mapped > MAX_DMA32_PFN) - start = MAX_DMA32_PFN << PAGE_SHIFT; -#endif - end = max_pfn_mapped << PAGE_SHIFT; - mem = find_fw_memmap_area(start, end, size, sizeof(struct range)); - if (mem == -1ULL) - panic("can not find more space for range free"); - - range = __va(mem); - /* use early_node_map[] and early_res to get range array at first */ - memset(range, 0, size); - nr_range = 0; - - /* need to go over early_node_map to find out good range for node */ - nr_range = add_from_early_node_map(range, count, nr_range, nodeid); -#ifdef CONFIG_X86_32 - subtract_range(range, count, max_low_pfn, -1ULL); -#endif - subtract_early_res(range, count); - nr_range = clean_sort_range(range, count); - - /* need to clear it ? */ - if (nodeid == MAX_NUMNODES) { - memset(&early_res[0], 0, - sizeof(struct early_res) * max_early_res); - early_res = NULL; - max_early_res = 0; - } - - *rangep = range; - return nr_range; -} -#else -void __init early_res_to_bootmem(u64 start, u64 end) -{ - int i, count; - u64 final_start, final_end; - int idx = 0; - - count = 0; - for (i = 0; i < max_early_res && early_res[i].end; i++) - count++; - - /* need to skip first one ?*/ - if (early_res != early_res_x) - idx = 1; - - printk(KERN_INFO "(%d/%d early reservations) ==> bootmem [%010llx - %010llx]\n", - count - idx, max_early_res, start, end); - for (i = idx; i < count; i++) { - struct early_res *r = &early_res[i]; - printk(KERN_INFO " #%d [%010llx - %010llx] %16s", i, - r->start, r->end, r->name); - final_start = max(start, r->start); - final_end = min(end, r->end); - if (final_start >= final_end) { - printk(KERN_CONT "\n"); - continue; - } - printk(KERN_CONT " ==> [%010llx - %010llx]\n", - final_start, final_end); - reserve_bootmem_generic(final_start, final_end - final_start, - BOOTMEM_DEFAULT); - } - /* clear them */ - memset(&early_res[0], 0, sizeof(struct early_res) * max_early_res); - early_res = NULL; - max_early_res = 0; - early_res_count = 0; -} -#endif - -/* Check for already reserved areas */ -static inline int __init bad_addr(u64 *addrp, u64 size, u64 align) -{ - int i; - u64 addr = *addrp; - int changed = 0; - struct early_res *r; -again: - i = find_overlapped_early(addr, addr + size); - r = &early_res[i]; - if (i < max_early_res && r->end) { - *addrp = addr = round_up(r->end, align); - changed = 1; - goto again; - } - return changed; -} - -/* Check for already reserved areas */ -static inline int __init bad_addr_size(u64 *addrp, u64 *sizep, u64 align) -{ - int i; - u64 addr = *addrp, last; - u64 size = *sizep; - int changed = 0; -again: - last = addr + size; - for (i = 0; i < max_early_res && early_res[i].end; i++) { - struct early_res *r = &early_res[i]; - if (last > r->start && addr < r->start) { - size = r->start - addr; - changed = 1; - goto again; - } - if (last > r->end && addr < r->end) { - addr = round_up(r->end, align); - size = last - addr; - changed = 1; - goto again; - } - if (last <= r->end && addr >= r->start) { - (*sizep)++; - return 0; - } - } - if (changed) { - *addrp = addr; - *sizep = size; - } - return changed; -} - -/* - * Find a free area with specified alignment in a specific range. - * only with the area.between start to end is active range from early_node_map - * so they are good as RAM - */ -u64 __init find_early_area(u64 ei_start, u64 ei_last, u64 start, u64 end, - u64 size, u64 align) -{ - u64 addr, last; - - addr = round_up(ei_start, align); - if (addr < start) - addr = round_up(start, align); - if (addr >= ei_last) - goto out; - while (bad_addr(&addr, size, align) && addr+size <= ei_last) - ; - last = addr + size; - if (last > ei_last) - goto out; - if (last > end) - goto out; - - return addr; - -out: - return -1ULL; -} - -u64 __init find_early_area_size(u64 ei_start, u64 ei_last, u64 start, - u64 *sizep, u64 align) -{ - u64 addr, last; - - addr = round_up(ei_start, align); - if (addr < start) - addr = round_up(start, align); - if (addr >= ei_last) - goto out; - *sizep = ei_last - addr; - while (bad_addr_size(&addr, sizep, align) && addr + *sizep <= ei_last) - ; - last = addr + *sizep; - if (last > ei_last) - goto out; - - return addr; - -out: - return -1ULL; -} diff --git a/include/linux/early_res.h b/include/linux/early_res.h new file mode 100644 index 00000000000..50f7663bb8b --- /dev/null +++ b/include/linux/early_res.h @@ -0,0 +1,22 @@ +#ifndef _LINUX_EARLY_RES_H +#define _LINUX_EARLY_RES_H +#ifdef __KERNEL__ + +extern void reserve_early(u64 start, u64 end, char *name); +extern void reserve_early_overlap_ok(u64 start, u64 end, char *name); +extern void free_early(u64 start, u64 end); +extern void early_res_to_bootmem(u64 start, u64 end); + +void reserve_early_without_check(u64 start, u64 end, char *name); +u64 find_early_area(u64 ei_start, u64 ei_last, u64 start, u64 end, + u64 size, u64 align); +u64 find_early_area_size(u64 ei_start, u64 ei_last, u64 start, + u64 *sizep, u64 align); +u64 find_fw_memmap_area(u64 start, u64 end, u64 size, u64 align); +u64 get_max_mapped(void); +#include +int get_free_all_memory_range(struct range **rangep, int nodeid); + +#endif /* __KERNEL__ */ + +#endif /* _LINUX_EARLY_RES_H */ diff --git a/kernel/Makefile b/kernel/Makefile index ad47330ccf3..1292b863d66 100644 --- a/kernel/Makefile +++ b/kernel/Makefile @@ -11,6 +11,7 @@ obj-y = sched.o fork.o exec_domain.o panic.o printk.o \ hrtimer.o rwsem.o nsproxy.o srcu.o semaphore.o \ notifier.o ksysfs.o pm_qos_params.o sched_clock.o cred.o \ async.o range.o +obj-$(CONFIG_HAVE_EARLY_RES) += early_res.o obj-y += groups.o ifdef CONFIG_FUNCTION_TRACER diff --git a/kernel/early_res.c b/kernel/early_res.c new file mode 100644 index 00000000000..aa5494ac446 --- /dev/null +++ b/kernel/early_res.c @@ -0,0 +1,513 @@ +/* + * early_res, could be used to replace bootmem + */ +#include +#include +#include +#include +#include +#include + +/* + * Early reserved memory areas. + */ +/* + * need to make sure this one is bigger enough before + * find_fw_memmap_area could be used + */ +#define MAX_EARLY_RES_X 32 + +struct early_res { + u64 start, end; + char name[15]; + char overlap_ok; +}; +static struct early_res early_res_x[MAX_EARLY_RES_X] __initdata; + +static int max_early_res __initdata = MAX_EARLY_RES_X; +static struct early_res *early_res __initdata = &early_res_x[0]; +static int early_res_count __initdata; + +static int __init find_overlapped_early(u64 start, u64 end) +{ + int i; + struct early_res *r; + + for (i = 0; i < max_early_res && early_res[i].end; i++) { + r = &early_res[i]; + if (end > r->start && start < r->end) + break; + } + + return i; +} + +/* + * Drop the i-th range from the early reservation map, + * by copying any higher ranges down one over it, and + * clearing what had been the last slot. + */ +static void __init drop_range(int i) +{ + int j; + + for (j = i + 1; j < max_early_res && early_res[j].end; j++) + ; + + memmove(&early_res[i], &early_res[i + 1], + (j - 1 - i) * sizeof(struct early_res)); + + early_res[j - 1].end = 0; + early_res_count--; +} + +/* + * Split any existing ranges that: + * 1) are marked 'overlap_ok', and + * 2) overlap with the stated range [start, end) + * into whatever portion (if any) of the existing range is entirely + * below or entirely above the stated range. Drop the portion + * of the existing range that overlaps with the stated range, + * which will allow the caller of this routine to then add that + * stated range without conflicting with any existing range. + */ +static void __init drop_overlaps_that_are_ok(u64 start, u64 end) +{ + int i; + struct early_res *r; + u64 lower_start, lower_end; + u64 upper_start, upper_end; + char name[15]; + + for (i = 0; i < max_early_res && early_res[i].end; i++) { + r = &early_res[i]; + + /* Continue past non-overlapping ranges */ + if (end <= r->start || start >= r->end) + continue; + + /* + * Leave non-ok overlaps as is; let caller + * panic "Overlapping early reservations" + * when it hits this overlap. + */ + if (!r->overlap_ok) + return; + + /* + * We have an ok overlap. We will drop it from the early + * reservation map, and add back in any non-overlapping + * portions (lower or upper) as separate, overlap_ok, + * non-overlapping ranges. + */ + + /* 1. Note any non-overlapping (lower or upper) ranges. */ + strncpy(name, r->name, sizeof(name) - 1); + + lower_start = lower_end = 0; + upper_start = upper_end = 0; + if (r->start < start) { + lower_start = r->start; + lower_end = start; + } + if (r->end > end) { + upper_start = end; + upper_end = r->end; + } + + /* 2. Drop the original ok overlapping range */ + drop_range(i); + + i--; /* resume for-loop on copied down entry */ + + /* 3. Add back in any non-overlapping ranges. */ + if (lower_end) + reserve_early_overlap_ok(lower_start, lower_end, name); + if (upper_end) + reserve_early_overlap_ok(upper_start, upper_end, name); + } +} + +static void __init __reserve_early(u64 start, u64 end, char *name, + int overlap_ok) +{ + int i; + struct early_res *r; + + i = find_overlapped_early(start, end); + if (i >= max_early_res) + panic("Too many early reservations"); + r = &early_res[i]; + if (r->end) + panic("Overlapping early reservations " + "%llx-%llx %s to %llx-%llx %s\n", + start, end - 1, name ? name : "", r->start, + r->end - 1, r->name); + r->start = start; + r->end = end; + r->overlap_ok = overlap_ok; + if (name) + strncpy(r->name, name, sizeof(r->name) - 1); + early_res_count++; +} + +/* + * A few early reservtations come here. + * + * The 'overlap_ok' in the name of this routine does -not- mean it + * is ok for these reservations to overlap an earlier reservation. + * Rather it means that it is ok for subsequent reservations to + * overlap this one. + * + * Use this entry point to reserve early ranges when you are doing + * so out of "Paranoia", reserving perhaps more memory than you need, + * just in case, and don't mind a subsequent overlapping reservation + * that is known to be needed. + * + * The drop_overlaps_that_are_ok() call here isn't really needed. + * It would be needed if we had two colliding 'overlap_ok' + * reservations, so that the second such would not panic on the + * overlap with the first. We don't have any such as of this + * writing, but might as well tolerate such if it happens in + * the future. + */ +void __init reserve_early_overlap_ok(u64 start, u64 end, char *name) +{ + drop_overlaps_that_are_ok(start, end); + __reserve_early(start, end, name, 1); +} + +static void __init __check_and_double_early_res(u64 ex_start, u64 ex_end) +{ + u64 start, end, size, mem; + struct early_res *new; + + /* do we have enough slots left ? */ + if ((max_early_res - early_res_count) > max(max_early_res/8, 2)) + return; + + /* double it */ + mem = -1ULL; + size = sizeof(struct early_res) * max_early_res * 2; + if (early_res == early_res_x) + start = 0; + else + start = early_res[0].end; + end = ex_start; + if (start + size < end) + mem = find_fw_memmap_area(start, end, size, + sizeof(struct early_res)); + if (mem == -1ULL) { + start = ex_end; + end = get_max_mapped(); + if (start + size < end) + mem = find_fw_memmap_area(start, end, size, + sizeof(struct early_res)); + } + if (mem == -1ULL) + panic("can not find more space for early_res array"); + + new = __va(mem); + /* save the first one for own */ + new[0].start = mem; + new[0].end = mem + size; + new[0].overlap_ok = 0; + /* copy old to new */ + if (early_res == early_res_x) { + memcpy(&new[1], &early_res[0], + sizeof(struct early_res) * max_early_res); + memset(&new[max_early_res+1], 0, + sizeof(struct early_res) * (max_early_res - 1)); + early_res_count++; + } else { + memcpy(&new[1], &early_res[1], + sizeof(struct early_res) * (max_early_res - 1)); + memset(&new[max_early_res], 0, + sizeof(struct early_res) * max_early_res); + } + memset(&early_res[0], 0, sizeof(struct early_res) * max_early_res); + early_res = new; + max_early_res *= 2; + printk(KERN_DEBUG "early_res array is doubled to %d at [%llx - %llx]\n", + max_early_res, mem, mem + size - 1); +} + +/* + * Most early reservations come here. + * + * We first have drop_overlaps_that_are_ok() drop any pre-existing + * 'overlap_ok' ranges, so that we can then reserve this memory + * range without risk of panic'ing on an overlapping overlap_ok + * early reservation. + */ +void __init reserve_early(u64 start, u64 end, char *name) +{ + if (start >= end) + return; + + __check_and_double_early_res(start, end); + + drop_overlaps_that_are_ok(start, end); + __reserve_early(start, end, name, 0); +} + +void __init reserve_early_without_check(u64 start, u64 end, char *name) +{ + struct early_res *r; + + if (start >= end) + return; + + __check_and_double_early_res(start, end); + + r = &early_res[early_res_count]; + + r->start = start; + r->end = end; + r->overlap_ok = 0; + if (name) + strncpy(r->name, name, sizeof(r->name) - 1); + early_res_count++; +} + +void __init free_early(u64 start, u64 end) +{ + struct early_res *r; + int i; + + i = find_overlapped_early(start, end); + r = &early_res[i]; + if (i >= max_early_res || r->end != end || r->start != start) + panic("free_early on not reserved area: %llx-%llx!", + start, end - 1); + + drop_range(i); +} + +#ifdef CONFIG_NO_BOOTMEM +static void __init subtract_early_res(struct range *range, int az) +{ + int i, count; + u64 final_start, final_end; + int idx = 0; + + count = 0; + for (i = 0; i < max_early_res && early_res[i].end; i++) + count++; + + /* need to skip first one ?*/ + if (early_res != early_res_x) + idx = 1; + +#define DEBUG_PRINT_EARLY_RES 1 + +#if DEBUG_PRINT_EARLY_RES + printk(KERN_INFO "Subtract (%d early reservations)\n", count); +#endif + for (i = idx; i < count; i++) { + struct early_res *r = &early_res[i]; +#if DEBUG_PRINT_EARLY_RES + printk(KERN_INFO " #%d [%010llx - %010llx] %15s\n", i, + r->start, r->end, r->name); +#endif + final_start = PFN_DOWN(r->start); + final_end = PFN_UP(r->end); + if (final_start >= final_end) + continue; + subtract_range(range, az, final_start, final_end); + } + +} + +int __init get_free_all_memory_range(struct range **rangep, int nodeid) +{ + int i, count; + u64 start = 0, end; + u64 size; + u64 mem; + struct range *range; + int nr_range; + + count = 0; + for (i = 0; i < max_early_res && early_res[i].end; i++) + count++; + + count *= 2; + + size = sizeof(struct range) * count; + end = get_max_mapped(); +#ifdef MAX_DMA32_PFN + if (end > (MAX_DMA32_PFN << PAGE_SHIFT)) + start = MAX_DMA32_PFN << PAGE_SHIFT; +#endif + mem = find_fw_memmap_area(start, end, size, sizeof(struct range)); + if (mem == -1ULL) + panic("can not find more space for range free"); + + range = __va(mem); + /* use early_node_map[] and early_res to get range array at first */ + memset(range, 0, size); + nr_range = 0; + + /* need to go over early_node_map to find out good range for node */ + nr_range = add_from_early_node_map(range, count, nr_range, nodeid); +#ifdef CONFIG_X86_32 + subtract_range(range, count, max_low_pfn, -1ULL); +#endif + subtract_early_res(range, count); + nr_range = clean_sort_range(range, count); + + /* need to clear it ? */ + if (nodeid == MAX_NUMNODES) { + memset(&early_res[0], 0, + sizeof(struct early_res) * max_early_res); + early_res = NULL; + max_early_res = 0; + } + + *rangep = range; + return nr_range; +} +#else +void __init early_res_to_bootmem(u64 start, u64 end) +{ + int i, count; + u64 final_start, final_end; + int idx = 0; + + count = 0; + for (i = 0; i < max_early_res && early_res[i].end; i++) + count++; + + /* need to skip first one ?*/ + if (early_res != early_res_x) + idx = 1; + + printk(KERN_INFO "(%d/%d early reservations) ==> bootmem [%010llx - %010llx]\n", + count - idx, max_early_res, start, end); + for (i = idx; i < count; i++) { + struct early_res *r = &early_res[i]; + printk(KERN_INFO " #%d [%010llx - %010llx] %16s", i, + r->start, r->end, r->name); + final_start = max(start, r->start); + final_end = min(end, r->end); + if (final_start >= final_end) { + printk(KERN_CONT "\n"); + continue; + } + printk(KERN_CONT " ==> [%010llx - %010llx]\n", + final_start, final_end); + reserve_bootmem_generic(final_start, final_end - final_start, + BOOTMEM_DEFAULT); + } + /* clear them */ + memset(&early_res[0], 0, sizeof(struct early_res) * max_early_res); + early_res = NULL; + max_early_res = 0; + early_res_count = 0; +} +#endif + +/* Check for already reserved areas */ +static inline int __init bad_addr(u64 *addrp, u64 size, u64 align) +{ + int i; + u64 addr = *addrp; + int changed = 0; + struct early_res *r; +again: + i = find_overlapped_early(addr, addr + size); + r = &early_res[i]; + if (i < max_early_res && r->end) { + *addrp = addr = round_up(r->end, align); + changed = 1; + goto again; + } + return changed; +} + +/* Check for already reserved areas */ +static inline int __init bad_addr_size(u64 *addrp, u64 *sizep, u64 align) +{ + int i; + u64 addr = *addrp, last; + u64 size = *sizep; + int changed = 0; +again: + last = addr + size; + for (i = 0; i < max_early_res && early_res[i].end; i++) { + struct early_res *r = &early_res[i]; + if (last > r->start && addr < r->start) { + size = r->start - addr; + changed = 1; + goto again; + } + if (last > r->end && addr < r->end) { + addr = round_up(r->end, align); + size = last - addr; + changed = 1; + goto again; + } + if (last <= r->end && addr >= r->start) { + (*sizep)++; + return 0; + } + } + if (changed) { + *addrp = addr; + *sizep = size; + } + return changed; +} + +/* + * Find a free area with specified alignment in a specific range. + * only with the area.between start to end is active range from early_node_map + * so they are good as RAM + */ +u64 __init find_early_area(u64 ei_start, u64 ei_last, u64 start, u64 end, + u64 size, u64 align) +{ + u64 addr, last; + + addr = round_up(ei_start, align); + if (addr < start) + addr = round_up(start, align); + if (addr >= ei_last) + goto out; + while (bad_addr(&addr, size, align) && addr+size <= ei_last) + ; + last = addr + size; + if (last > ei_last) + goto out; + if (last > end) + goto out; + + return addr; + +out: + return -1ULL; +} + +u64 __init find_early_area_size(u64 ei_start, u64 ei_last, u64 start, + u64 *sizep, u64 align) +{ + u64 addr, last; + + addr = round_up(ei_start, align); + if (addr < start) + addr = round_up(start, align); + if (addr >= ei_last) + goto out; + *sizep = ei_last - addr; + while (bad_addr_size(&addr, sizep, align) && addr + *sizep <= ei_last) + ; + last = addr + *sizep; + if (last > ei_last) + goto out; + + return addr; + +out: + return -1ULL; +} -- cgit v1.2.3-70-g09d2