diff options
| author | Ingo Molnar <mingo@kernel.org> | 2017-04-11 08:56:05 +0200 |
|---|---|---|
| committer | Ingo Molnar <mingo@kernel.org> | 2017-04-11 08:56:05 +0200 |
| commit | e5185a76a23b2d56fb2327ad8bd58fb1bcaa52b1 (patch) | |
| tree | 07a09b5e19a4d55c4a097b280eb64bd159ca0eb9 /arch | |
| parent | b678c91aefa7ce05a5d195e0a5c7a357b62d3283 (diff) | |
| parent | 4729277156cf18acd9b9b04d6ef8c2a8a7bf00dc (diff) | |
Merge branch 'x86/boot' into x86/mm, to avoid conflict
There's a conflict between ongoing level-5 paging support and
the E820 rewrite. Since the E820 rewrite is essentially ready,
merge it into x86/mm to reduce tree conflicts.
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Diffstat (limited to 'arch')
62 files changed, 1042 insertions, 879 deletions
diff --git a/arch/x86/boot/compressed/eboot.c b/arch/x86/boot/compressed/eboot.c index 801c7a158e55..cbf4b87f55b9 100644 --- a/arch/x86/boot/compressed/eboot.c +++ b/arch/x86/boot/compressed/eboot.c @@ -9,7 +9,9 @@ #include <linux/efi.h> #include <linux/pci.h> + #include <asm/efi.h> +#include <asm/e820/types.h> #include <asm/setup.h> #include <asm/desc.h> @@ -729,7 +731,7 @@ static void add_e820ext(struct boot_params *params, unsigned long size; e820ext->type = SETUP_E820_EXT; - e820ext->len = nr_entries * sizeof(struct e820entry); + e820ext->len = nr_entries * sizeof(struct boot_e820_entry); e820ext->next = 0; data = (struct setup_data *)(unsigned long)params->hdr.setup_data; @@ -746,9 +748,9 @@ static void add_e820ext(struct boot_params *params, static efi_status_t setup_e820(struct boot_params *params, struct setup_data *e820ext, u32 e820ext_size) { - struct e820entry *e820_map = ¶ms->e820_map[0]; + struct boot_e820_entry *entry = params->e820_table; struct efi_info *efi = ¶ms->efi_info; - struct e820entry *prev = NULL; + struct boot_e820_entry *prev = NULL; u32 nr_entries; u32 nr_desc; int i; @@ -773,15 +775,15 @@ static efi_status_t setup_e820(struct boot_params *params, case EFI_MEMORY_MAPPED_IO: case EFI_MEMORY_MAPPED_IO_PORT_SPACE: case EFI_PAL_CODE: - e820_type = E820_RESERVED; + e820_type = E820_TYPE_RESERVED; break; case EFI_UNUSABLE_MEMORY: - e820_type = E820_UNUSABLE; + e820_type = E820_TYPE_UNUSABLE; break; case EFI_ACPI_RECLAIM_MEMORY: - e820_type = E820_ACPI; + e820_type = E820_TYPE_ACPI; break; case EFI_LOADER_CODE: @@ -789,15 +791,15 @@ static efi_status_t setup_e820(struct boot_params *params, case EFI_BOOT_SERVICES_CODE: case EFI_BOOT_SERVICES_DATA: case EFI_CONVENTIONAL_MEMORY: - e820_type = E820_RAM; + e820_type = E820_TYPE_RAM; break; case EFI_ACPI_MEMORY_NVS: - e820_type = E820_NVS; + e820_type = E820_TYPE_NVS; break; case EFI_PERSISTENT_MEMORY: - e820_type = E820_PMEM; + e820_type = E820_TYPE_PMEM; break; default: @@ -811,26 +813,26 @@ static efi_status_t setup_e820(struct boot_params *params, continue; } - if (nr_entries == ARRAY_SIZE(params->e820_map)) { - u32 need = (nr_desc - i) * sizeof(struct e820entry) + + if (nr_entries == ARRAY_SIZE(params->e820_table)) { + u32 need = (nr_desc - i) * sizeof(struct e820_entry) + sizeof(struct setup_data); if (!e820ext || e820ext_size < need) return EFI_BUFFER_TOO_SMALL; /* boot_params map full, switch to e820 extended */ - e820_map = (struct e820entry *)e820ext->data; + entry = (struct boot_e820_entry *)e820ext->data; } - e820_map->addr = d->phys_addr; - e820_map->size = d->num_pages << PAGE_SHIFT; - e820_map->type = e820_type; - prev = e820_map++; + entry->addr = d->phys_addr; + entry->size = d->num_pages << PAGE_SHIFT; + entry->type = e820_type; + prev = entry++; nr_entries++; } - if (nr_entries > ARRAY_SIZE(params->e820_map)) { - u32 nr_e820ext = nr_entries - ARRAY_SIZE(params->e820_map); + if (nr_entries > ARRAY_SIZE(params->e820_table)) { + u32 nr_e820ext = nr_entries - ARRAY_SIZE(params->e820_table); add_e820ext(params, e820ext, nr_e820ext); nr_entries -= nr_e820ext; @@ -848,7 +850,7 @@ static efi_status_t alloc_e820ext(u32 nr_desc, struct setup_data **e820ext, unsigned long size; size = sizeof(struct setup_data) + - sizeof(struct e820entry) * nr_desc; + sizeof(struct e820_entry) * nr_desc; if (*e820ext) { efi_call_early(free_pool, *e820ext); @@ -884,9 +886,9 @@ static efi_status_t exit_boot_func(efi_system_table_t *sys_table_arg, if (first) { nr_desc = *map->buff_size / *map->desc_size; - if (nr_desc > ARRAY_SIZE(p->boot_params->e820_map)) { + if (nr_desc > ARRAY_SIZE(p->boot_params->e820_table)) { u32 nr_e820ext = nr_desc - - ARRAY_SIZE(p->boot_params->e820_map); + ARRAY_SIZE(p->boot_params->e820_table); status = alloc_e820ext(nr_e820ext, &p->e820ext, &p->e820ext_size); diff --git a/arch/x86/boot/compressed/kaslr.c b/arch/x86/boot/compressed/kaslr.c index 8b7c9e75edcb..6d9a546ec7ae 100644 --- a/arch/x86/boot/compressed/kaslr.c +++ b/arch/x86/boot/compressed/kaslr.c @@ -426,7 +426,7 @@ static unsigned long slots_fetch_random(void) return 0; } -static void process_e820_entry(struct e820entry *entry, +static void process_e820_entry(struct boot_e820_entry *entry, unsigned long minimum, unsigned long image_size) { @@ -435,7 +435,7 @@ static void process_e820_entry(struct e820entry *entry, unsigned long start_orig; /* Skip non-RAM entries. */ - if (entry->type != E820_RAM) + if (entry->type != E820_TYPE_RAM) return; /* On 32-bit, ignore entries entirely above our maximum. */ @@ -518,7 +518,7 @@ static unsigned long find_random_phys_addr(unsigned long minimum, /* Verify potential e820 positions, appending to slots list. */ for (i = 0; i < boot_params->e820_entries; i++) { - process_e820_entry(&boot_params->e820_map[i], minimum, + process_e820_entry(&boot_params->e820_table[i], minimum, image_size); if (slot_area_index == MAX_SLOT_AREA) { debug_putstr("Aborted e820 scan (slot_areas full)!\n"); diff --git a/arch/x86/boot/header.S b/arch/x86/boot/header.S index 3dd5be33aaa7..2ed8f0c25def 100644 --- a/arch/x86/boot/header.S +++ b/arch/x86/boot/header.S @@ -18,7 +18,6 @@ #include <asm/segment.h> #include <generated/utsrelease.h> #include <asm/boot.h> -#include <asm/e820.h> #include <asm/page_types.h> #include <asm/setup.h> #include <asm/bootparam.h> diff --git a/arch/x86/boot/memory.c b/arch/x86/boot/memory.c index db75d07c3645..d9c28c87e477 100644 --- a/arch/x86/boot/memory.c +++ b/arch/x86/boot/memory.c @@ -21,8 +21,8 @@ static int detect_memory_e820(void) { int count = 0; struct biosregs ireg, oreg; - struct e820entry *desc = boot_params.e820_map; - static struct e820entry buf; /* static so it is zeroed */ + struct boot_e820_entry *desc = boot_params.e820_table; + static struct boot_e820_entry buf; /* static so it is zeroed */ initregs(&ireg); ireg.ax = 0xe820; @@ -66,7 +66,7 @@ static int detect_memory_e820(void) *desc++ = buf; count++; - } while (ireg.ebx && count < ARRAY_SIZE(boot_params.e820_map)); + } while (ireg.ebx && count < ARRAY_SIZE(boot_params.e820_table)); return boot_params.e820_entries = count; } diff --git a/arch/x86/include/asm/acpi.h b/arch/x86/include/asm/acpi.h index 395b69551fce..2efc768e4362 100644 --- a/arch/x86/include/asm/acpi.h +++ b/arch/x86/include/asm/acpi.h @@ -52,6 +52,8 @@ extern u8 acpi_sci_flags; extern int acpi_sci_override_gsi; void acpi_pic_sci_set_trigger(unsigned int, u16); +struct device; + extern int (*__acpi_register_gsi)(struct device *dev, u32 gsi, int trigger, int polarity); extern void (*__acpi_unregister_gsi)(u32 gsi); diff --git a/arch/x86/include/asm/e820.h b/arch/x86/include/asm/e820.h deleted file mode 100644 index 67313f3a9874..000000000000 --- a/arch/x86/include/asm/e820.h +++ /dev/null @@ -1,73 +0,0 @@ -#ifndef _ASM_X86_E820_H -#define _ASM_X86_E820_H - -/* - * E820_X_MAX is the maximum size of the extended E820 table. The extended - * table may contain up to 3 extra E820 entries per possible NUMA node, so we - * make room for 3 * MAX_NUMNODES possible entries, beyond the standard 128. - * Also note that E820_X_MAX *must* be defined before we include uapi/asm/e820.h. - */ -#include <linux/numa.h> -#define E820_X_MAX (E820MAX + 3 * MAX_NUMNODES) - -#include <uapi/asm/e820.h> - -#ifndef __ASSEMBLY__ -/* see comment in arch/x86/kernel/e820.c */ -extern struct e820map *e820; -extern struct e820map *e820_saved; - -extern unsigned long pci_mem_start; -extern int e820_any_mapped(u64 start, u64 end, unsigned type); -extern int e820_all_mapped(u64 start, u64 end, unsigned type); -extern void e820_add_region(u64 start, u64 size, int type); -extern void e820_print_map(char *who); -extern int -sanitize_e820_map(struct e820entry *biosmap, int max_nr_map, u32 *pnr_map); -extern u64 e820_update_range(u64 start, u64 size, unsigned old_type, - unsigned new_type); -extern u64 e820_remove_range(u64 start, u64 size, unsigned old_type, - int checktype); -extern void update_e820(void); -extern void e820_setup_gap(void); -struct setup_data; -extern void parse_e820_ext(u64 phys_addr, u32 data_len); - -#if defined(CONFIG_X86_64) || \ - (defined(CONFIG_X86_32) && defined(CONFIG_HIBERNATION)) -extern void e820_mark_nosave_regions(unsigned long limit_pfn); -#else -static inline void e820_mark_nosave_regions(unsigned long limit_pfn) -{ -} -#endif - -extern unsigned long e820_end_of_ram_pfn(void); -extern unsigned long e820_end_of_low_ram_pfn(void); -extern u64 early_reserve_e820(u64 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); -extern void setup_memory_map(void); -extern char *default_machine_specific_memory_setup(void); - -extern void e820_reallocate_tables(void); - -/* - * Returns true iff the specified range [s,e) is completely contained inside - * the ISA region. - */ -static inline bool is_ISA_range(u64 s, u64 e) -{ - return s >= ISA_START_ADDRESS && e <= ISA_END_ADDRESS; -} - -#endif /* __ASSEMBLY__ */ -#include <linux/ioport.h> - -#define HIGH_MEMORY (1024*1024) -#endif /* _ASM_X86_E820_H */ diff --git a/arch/x86/include/asm/e820/api.h b/arch/x86/include/asm/e820/api.h new file mode 100644 index 000000000000..8e0f8b85b209 --- /dev/null +++ b/arch/x86/include/asm/e820/api.h @@ -0,0 +1,50 @@ +#ifndef _ASM_E820_API_H +#define _ASM_E820_API_H + +#include <asm/e820/types.h> + +extern struct e820_table *e820_table; +extern struct e820_table *e820_table_firmware; + +extern unsigned long pci_mem_start; + +extern bool e820__mapped_any(u64 start, u64 end, enum e820_type type); +extern bool e820__mapped_all(u64 start, u64 end, enum e820_type type); + +extern void e820__range_add (u64 start, u64 size, enum e820_type type); +extern u64 e820__range_update(u64 start, u64 size, enum e820_type old_type, enum e820_type new_type); +extern u64 e820__range_remove(u64 start, u64 size, enum e820_type old_type, bool check_type); + +extern void e820__print_table(char *who); +extern int e820__update_table(struct e820_table *table); +extern void e820__update_table_print(void); + +extern unsigned long e820__end_of_ram_pfn(void); +extern unsigned long e820__end_of_low_ram_pfn(void); + +extern u64 e820__memblock_alloc_reserved(u64 size, u64 align); +extern void e820__memblock_setup(void); + +extern void e820__reserve_setup_data(void); +extern void e820__finish_early_params(void); +extern void e820__reserve_resources(void); +extern void e820__reserve_resources_late(void); + +extern void e820__memory_setup(void); +extern void e820__memory_setup_extended(u64 phys_addr, u32 data_len); +extern char *e820__memory_setup_default(void); +extern void e820__setup_pci_gap(void); + +extern void e820__reallocate_tables(void); +extern void e820__register_nosave_regions(unsigned long limit_pfn); + +/* + * Returns true iff the specified range [start,end) is completely contained inside + * the ISA region. + */ +static inline bool is_ISA_range(u64 start, u64 end) +{ + return start >= ISA_START_ADDRESS && end <= ISA_END_ADDRESS; +} + +#endif /* _ASM_E820_API_H */ diff --git a/arch/x86/include/asm/e820/types.h b/arch/x86/include/asm/e820/types.h new file mode 100644 index 000000000000..4adeed03a9a1 --- /dev/null +++ b/arch/x86/include/asm/e820/types.h @@ -0,0 +1,104 @@ +#ifndef _ASM_E820_TYPES_H +#define _ASM_E820_TYPES_H + +#include <uapi/asm/bootparam.h> + +/* + * These are the E820 types known to the kernel: + */ +enum e820_type { + E820_TYPE_RAM = 1, + E820_TYPE_RESERVED = 2, + E820_TYPE_ACPI = 3, + E820_TYPE_NVS = 4, + E820_TYPE_UNUSABLE = 5, + E820_TYPE_PMEM = 7, + + /* + * This is a non-standardized way to represent ADR or + * NVDIMM regions that persist over a reboot. + * + * The kernel will ignore their special capabilities + * unless the CONFIG_X86_PMEM_LEGACY=y option is set. + * + * ( Note that older platforms also used 6 for the same + * type of memory, but newer versions switched to 12 as + * 6 was assigned differently. Some time they will learn... ) + */ + E820_TYPE_PRAM = 12, + + /* + * Reserved RAM used by the kernel itself if + * CONFIG_INTEL_TXT=y is enabled, memory of this type + * will be included in the S3 integrity calculation + * and so should not include any memory that the BIOS + * might alter over the S3 transition: + */ + E820_TYPE_RESERVED_KERN = 128, +}; + +/* + * A single E820 map entry, describing a memory range of [addr...addr+size-1], + * of 'type' memory type: + * + * (We pack it because there can be thousands of them on large systems.) + */ +struct e820_entry { + u64 addr; + u64 size; + enum e820_type type; +} __attribute__((packed)); + +/* + * The legacy E820 BIOS limits us to 128 (E820_MAX_ENTRIES_ZEROPAGE) nodes + * due to the constrained space in the zeropage. + * + * On large systems we can easily have thousands of nodes with RAM, + * which cannot be fit into so few entries - so we have a mechanism + * to extend the e820 table size at build-time, via the E820_MAX_ENTRIES + * define below. + * + * ( Those extra entries are enumerated via the EFI memory map, not + * via the legacy zeropage mechanism. ) + * + * Size our internal memory map tables to have room for these additional + * entries, based on a heuristic calculation: up to three entries per + * NUMA node, plus E820_MAX_ENTRIES_ZEROPAGE for some extra space. + * + * This allows for bootstrap/firmware quirks such as possible duplicate + * E820 entries that might need room in the same arrays, prior to the + * call to e820__update_table() to remove duplicates. The allowance + * of three memory map entries per node is "enough" entries for + * the initial hardware platform motivating this mechanism to make + * use of additional EFI map entries. Future platforms may want + * to allow more than three entries per node or otherwise refine + * this size. + */ + +#include <linux/numa.h> + +#define E820_MAX_ENTRIES (E820_MAX_ENTRIES_ZEROPAGE + 3*MAX_NUMNODES) + +/* + * The whole array of E820 entries: + */ +struct e820_table { + __u32 nr_entries; + struct e820_entry entries[E820_MAX_ENTRIES]; +}; + +/* + * Various well-known legacy memory ranges in physical memory: + */ +#define ISA_START_ADDRESS 0x000a0000 +#define ISA_END_ADDRESS 0x00100000 + +#define BIOS_BEGIN 0x000a0000 +#define BIOS_END 0x00100000 + +#define HIGH_MEMORY 0x00100000 + +#define BIOS_ROM_BASE 0xffe00000 +#define BIOS_ROM_END 0xffffffff + +#endif /* _ASM_E820_TYPES_H */ diff --git a/arch/x86/include/asm/gart.h b/arch/x86/include/asm/gart.h index 156cd5d18d2a..1d268098ac2e 100644 --- a/arch/x86/include/asm/gart.h +++ b/arch/x86/include/asm/gart.h @@ -1,7 +1,7 @@ #ifndef _ASM_X86_GART_H #define _ASM_X86_GART_H -#include <asm/e820.h> +#include <asm/e820/api.h> extern void set_up_gart_resume(u32, u32); @@ -97,7 +97,7 @@ static inline int aperture_valid(u64 aper_base, u32 aper_size, u32 min_size) printk(KERN_INFO "Aperture beyond 4GB. Ignoring.\n"); return 0; } - if (e820_any_mapped(aper_base, aper_base + aper_size, E820_RAM)) { + if (e820__mapped_any(aper_base, aper_base + aper_size, E820_TYPE_RAM)) { printk(KERN_INFO "Aperture pointing to e820 RAM. Ignoring.\n"); return 0; } diff --git a/arch/x86/include/asm/mpspec.h b/arch/x86/include/asm/mpspec.h index 32007041ef8c..831eb7895535 100644 --- a/arch/x86/include/asm/mpspec.h +++ b/arch/x86/include/asm/mpspec.h @@ -64,7 +64,7 @@ static inline void find_smp_config(void) } #ifdef CONFIG_X86_MPPARSE -extern void early_reserve_e820_mpc_new(void); +extern void e820__memblock_alloc_reserved_mpc_new(void); extern int enable_update_mptable; extern int default_mpc_apic_id(struct mpc_cpu *m); extern void default_smp_read_mpc_oem(struct mpc_table *mpc); @@ -76,7 +76,7 @@ extern void default_mpc_oem_bus_info(struct mpc_bus *m, char *str); extern void default_find_smp_config(void); extern void default_get_smp_config(unsigned int early); #else -static inline void early_reserve_e820_mpc_new(void) { } +static inline void e820__memblock_alloc_reserved_mpc_new(void) { } #define enable_update_mptable 0 #define default_mpc_apic_id NULL #define default_smp_read_mpc_oem NULL diff --git a/arch/x86/include/asm/pci_x86.h b/arch/x86/include/asm/pci_x86.h index d08eacd298c2..9f1b21f372fe 100644 --- a/arch/x86/include/asm/pci_x86.h +++ b/arch/x86/include/asm/pci_x86.h @@ -4,6 +4,8 @@ * (c) 1999 Martin Mares <mj@ucw.cz> */ +#include <linux/ioport.h> + #undef DEBUG #ifdef DEBUG diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h index 473293a681e0..942482ac36a8 100644 --- a/arch/x86/include/asm/pgtable.h +++ b/arch/x86/include/asm/pgtable.h @@ -2,8 +2,6 @@ #define _ASM_X86_PGTABLE_H #include <asm/page.h> -#include <asm/e820.h> - #include <asm/pgtable_types.h> /* @@ -916,6 +914,7 @@ static inline int pgd_none(pgd_t pgd) extern int direct_gbpages; void init_mem_mapping(void); void early_alloc_pgt_buf(void); +extern void memblock_find_dma_reserve(void); #ifdef CONFIG_X86_64 /* Realmode trampoline initialization. */ diff --git a/arch/x86/include/asm/xen/page.h b/arch/x86/include/asm/xen/page.h index bf2ca56fba11..8a5a02b1dfba 100644 --- a/arch/x86/include/asm/xen/page.h +++ b/arch/x86/include/asm/xen/page.h @@ -6,6 +6,7 @@ #include <linux/spinlock.h> #include <linux/pfn.h> #include <linux/mm.h> +#include <linux/device.h> #include <linux/uaccess.h> #include <asm/page.h> diff --git a/arch/x86/include/uapi/asm/bootparam.h b/arch/x86/include/uapi/asm/bootparam.h index 07244ea16765..ddef37b16af2 100644 --- a/arch/x86/include/uapi/asm/bootparam.h +++ b/arch/x86/include/uapi/asm/bootparam.h @@ -34,7 +34,6 @@ #include <linux/screen_info.h> #include <linux/apm_bios.h> #include <linux/edd.h> -#include <asm/e820.h> #include <asm/ist.h> #include <video/edid.h> @@ -111,6 +110,21 @@ struct efi_info { __u32 efi_memmap_hi; }; +/* + * This is the maximum number of entries in struct boot_params::e820_table + * (the zeropage), which is part of the x86 boot protocol ABI: + */ +#define E820_MAX_ENTRIES_ZEROPAGE 128 + +/* + * The E820 memory region entry of the boot protocol ABI: + */ +struct boot_e820_entry { + __u64 addr; + __u64 size; + __u32 type; +} __attribute__((packed)); + /* The so-called "zeropage" */ struct boot_params { struct screen_info screen_info; /* 0x000 */ @@ -153,7 +167,7 @@ struct boot_params { struct setup_header hdr; /* setup header */ /* 0x1f1 */ __u8 _pad7[0x290-0x1f1-sizeof(struct setup_header)]; __u32 edd_mbr_sig_buffer[EDD_MBR_SIG_MAX]; /* 0x290 */ - struct e820entry e820_map[E820MAX]; /* 0x2d0 */ + struct boot_e820_entry e820_table[E820_MAX_ENTRIES_ZEROPAGE]; /* 0x2d0 */ __u8 _pad8[48]; /* 0xcd0 */ struct edd_info eddbuf[EDDMAXNR]; /* 0xd00 */ __u8 _pad9[276]; /* 0xeec */ diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c index b2879cc23db4..294eab07c209 100644 --- a/arch/x86/kernel/acpi/boot.c +++ b/arch/x86/kernel/acpi/boot.c @@ -37,6 +37,7 @@ #include <linux/pci.h> #include <linux/efi-bgrt.h> +#include <asm/e820/api.h> #include <asm/irqdomain.h> #include <asm/pci_x86.h> #include <asm/pgtable.h> @@ -1729,6 +1730,6 @@ int __acpi_release_global_lock(unsigned int *lock) void __init arch_reserve_mem_area(acpi_physical_address addr, size_t size) { - e820_add_region(addr, size, E820_ACPI); - update_e820(); + e820__range_add(addr, size, E820_TYPE_ACPI); + e820__update_table_print(); } diff --git a/arch/x86/kernel/aperture_64.c b/arch/x86/kernel/aperture_64.c index 0a2bb1f62e72..ef2859f9fcce 100644 --- a/arch/x86/kernel/aperture_64.c +++ b/arch/x86/kernel/aperture_64.c @@ -21,7 +21,7 @@ #include <linux/pci.h> #include <linux/bitops.h> #include <linux/suspend.h> -#include <asm/e820.h> +#include <asm/e820/api.h> #include <asm/io.h> #include <asm/iommu.h> #include <asm/gart.h> @@ -306,13 +306,13 @@ void __init early_gart_iommu_check(void) fix = 1; if (gart_fix_e820 && !fix && aper_enabled) { - if (e820_any_mapped(aper_base, aper_base + aper_size, - E820_RAM)) { + if (e820__mapped_any(aper_base, aper_base + aper_size, + E820_TYPE_RAM)) { /* reserve it, so we can reuse it in second kernel */ pr_info("e820: reserve [mem %#010Lx-%#010Lx] for GART\n", aper_base, aper_base + aper_size - 1); - e820_add_region(aper_base, aper_size, E820_RESERVED); - update_e820(); + e820__range_add(aper_base, aper_size, E820_TYPE_RESERVED); + e820__update_table_print(); } } diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index 8ccb7ef512e0..0b657bf3d350 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -2627,7 +2627,7 @@ static int __init lapic_insert_resource(void) } /* - * need call insert after e820_reserve_resources() + * need call insert after e820__reserve_resources() * that is using request_resource */ late_initcall(lapic_insert_resource); diff --git a/arch/x86/kernel/apic/apic_noop.c b/arch/x86/kernel/apic/apic_noop.c index b109e4389c92..2262eb6df796 100644 --- a/arch/x86/kernel/apic/apic_noop.c +++ b/arch/x86/kernel/apic/apic_noop.c @@ -26,7 +26,7 @@ #include <linux/interrupt.h> #include <asm/acpi.h> -#include <asm/e820.h> +#include <asm/e820/api.h> static void noop_init_apic_ldr(void) { } static void noop_send_IPI(int cpu, int vector) { } diff --git a/arch/x86/kernel/apic/probe_32.c b/arch/x86/kernel/apic/probe_32.c index c48264e202fd..2e8f7f048f4f 100644 --- a/arch/x86/kernel/apic/probe_32.c +++ b/arch/x86/kernel/apic/probe_32.c @@ -25,7 +25,7 @@ #include <linux/interrupt.h> #include <asm/acpi.h> -#include <asm/e820.h> +#include <asm/e820/api.h> #ifdef CONFIG_HOTPLUG_CPU #define DEFAULT_SEND_IPI (1) diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c index 86f20cc0a65e..b487b3a01615 100644 --- a/arch/x86/kernel/apic/x2apic_uv_x.c +++ b/arch/x86/kernel/apic/x2apic_uv_x.c @@ -34,6 +34,7 @@ #include <asm/uv/bios.h> #include <asm/uv/uv.h> #include <asm/apic.h> +#include <asm/e820/api.h> #include <asm/ipi.h> #include <asm/smp.h> #include <asm/x86_init.h> diff --git a/arch/x86/kernel/cpu/centaur.c b/arch/x86/kernel/cpu/centaur.c index 43955ee6715b..44207b71fee1 100644 --- a/arch/x86/kernel/cpu/centaur.c +++ b/arch/x86/kernel/cpu/centaur.c @@ -3,7 +3,7 @@ #include <linux/sched/clock.h> #include <asm/cpufeature.h> -#include <asm/e820.h> +#include <asm/e820/api.h> #include <asm/mtrr.h> #include <asm/msr.h> diff --git a/arch/x86/kernel/cpu/mtrr/cleanup.c b/arch/x86/kernel/cpu/mtrr/cleanup.c index 3b442b64c72d..765afd599039 100644 --- a/arch/x86/kernel/cpu/mtrr/cleanup.c +++ b/arch/x86/kernel/cpu/mtrr/cleanup.c @@ -27,7 +27,7 @@ #include <linux/range.h> #include <asm/processor.h> -#include <asm/e820.h> +#include <asm/e820/api.h> #include <asm/mtrr.h> #include <asm/msr.h> @@ -860,7 +860,7 @@ real_trim_memory(unsigned long start_pfn, unsigned long limit_pfn) trim_size <<= PAGE_SHIFT; trim_size -= trim_start; - return e820_update_range(trim_start, trim_size, E820_RAM, E820_RESERVED); + return e820__range_update(trim_start, trim_size, E820_TYPE_RAM, E820_TYPE_RESERVED); } /** @@ -978,7 +978,7 @@ int __init mtrr_trim_uncached_memory(unsigned long end_pfn) WARN_ON(1); pr_info("update e820 for mtrr\n"); - update_e820(); + e820__update_table_print(); return 1; } diff --git a/arch/x86/kernel/cpu/mtrr/main.c b/arch/x86/kernel/cpu/mtrr/main.c index 24e87e74990d..2bce84d91c2b 100644 --- a/arch/x86/kernel/cpu/mtrr/main.c +++ b/arch/x86/kernel/cpu/mtrr/main.c @@ -48,7 +48,7 @@ #include <linux/syscore_ops.h> #include <asm/cpufeature.h> -#include <asm/e820.h> +#include <asm/e820/api.h> #include <asm/mtrr.h> #include <asm/msr.h> #include <asm/pat.h> diff --git a/arch/x86/kernel/crash.c b/arch/x86/kernel/crash.c index 3741461c63a0..22217ece26c8 100644 --- a/arch/x86/kernel/crash.c +++ b/arch/x86/kernel/crash.c @@ -29,6 +29,7 @@ #include <asm/nmi.h> #include <asm/hw_irq.h> #include <asm/apic.h> +#include <asm/e820/types.h> #include <asm/io_apic.h> #include <asm/hpet.h> #include <linux/kdebug.h> @@ -503,16 +504,16 @@ static int prepare_elf_headers(struct kimage *image, void **addr, return ret; } -static int add_e820_entry(struct boot_params *params, struct e820entry *entry) +static int add_e820_entry(struct boot_params *params, struct e820_entry *entry) { unsigned int nr_e820_entries; nr_e820_entries = params->e820_entries; - if (nr_e820_entries >= E820MAX) + if (nr_e820_entries >= E820_MAX_ENTRIES_ZEROPAGE) return 1; - memcpy(¶ms->e820_map[nr_e820_entries], entry, - sizeof(struct e820entry)); + memcpy(¶ms->e820_table[nr_e820_entries], entry, + sizeof(struct e820_entry)); params->e820_entries++; return 0; } @@ -521,7 +522,7 @@ static int memmap_entry_callback(u64 start, u64 end, void *arg) { struct crash_memmap_data *cmd = arg; struct boot_params *params = cmd->params; - struct e820entry ei; + struct e820_entry ei; ei.addr = start; ei.size = end - start + 1; @@ -560,7 +561,7 @@ int crash_setup_memmap_entries(struct kimage *image, struct boot_params *params) { int i, ret = 0; unsigned long flags; - struct e820entry ei; + struct e820_entry ei; struct crash_memmap_data cmd; struct crash_mem *cmem; @@ -574,17 +575,17 @@ int crash_setup_memmap_entries(struct kimage *image, struct boot_params *params) /* Add first 640K segment */ ei.addr = image->arch.backup_src_start; ei.size = image->arch.backup_src_sz; - ei.type = E820_RAM; + ei.type = E820_TYPE_RAM; add_e820_entry(params, &ei); /* Add ACPI tables */ - cmd.type = E820_ACPI; + cmd.type = E820_TYPE_ACPI; flags = IORESOURCE_MEM | IORESOURCE_BUSY; walk_iomem_res_desc(IORES_DESC_ACPI_TABLES, flags, 0, -1, &cmd, memmap_entry_callback); /* Add ACPI Non-volatile Storage */ - cmd.type = E820_NVS; + cmd.type = E820_TYPE_NVS; walk_iomem_res_desc(IORES_DESC_ACPI_NV_STORAGE, flags, 0, -1, &cmd, memmap_entry_callback); @@ -592,7 +593,7 @@ int crash_setup_memmap_entries(struct kimage *image, struct boot_params *params) if (crashk_low_res.end) { ei.addr = crashk_low_res.start; ei.size = crashk_low_res.end - crashk_low_res.start + 1; - ei.type = E820_RAM; + ei.type = E820_TYPE_RAM; add_e820_entry(params, &ei); } @@ -609,7 +610,7 @@ int crash_setup_memmap_entries(struct kimage *image, struct boot_params *params) if (ei.size < PAGE_SIZE) continue; ei.addr = cmem->ranges[i].start; - ei.type = E820_RAM; + ei.type = E820_TYPE_RAM; add_e820_entry(params, &ei); } diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c index b2bbad6ebe4d..6e9b26fa6d05 100644 --- a/arch/x86/kernel/e820.c +++ b/arch/x86/kernel/e820.c @@ -1,49 +1,55 @@ /* - * Handle the memory map. - * The functions here do the job until bootmem takes over. + * Low level x86 E820 memory map handling functions. * - * Getting sanitize_e820_map() in sync with i386 version by applying change: - * - Provisions for empty E820 memory regions (reported by certain BIOSes). - * Alex Achenbach <xela@slit.de>, December 2002. - * Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> + * The firmware and bootloader passes us the "E820 table", which is the primary + * physical memory layout description available about x86 systems. * + * The kernel takes the E820 memory layout and optionally modifies it with + * quirks and other tweaks, and feeds that into the generic Linux memory + * allocation code routines via a platform independent interface (memblock, etc.). */ -#include <linux/kernel.h> -#include <linux/types.h> -#include <linux/init.h> #include <linux/crash_dump.h> -#include <linux/export.h> #include <linux/bootmem.h> -#include <linux/pfn.h> #include <linux/suspend.h> #include <linux/acpi.h> #include <linux/firmware-map.h> #include <linux/memblock.h> #include <linux/sort.h> -#include <asm/e820.h> -#include <asm/proto.h> +#include <asm/e820/api.h> #include <asm/setup.h> -#include <asm/cpufeature.h> /* - * The e820 map is the map that gets modified e.g. with command line parameters - * and that is also registered with modifications in the kernel resource tree - * with the iomem_resource as parent. + * We organize the E820 table into two main data structures: * - * The e820_saved is directly saved after the BIOS-provided memory map is - * copied. It doesn't get modified afterwards. It's registered for the - * /sys/firmware/memmap interface. + * - 'e820_table_firmware': the original firmware version passed to us by the + * bootloader - not modified by the kernel. We use this to: * - * That memory map is not modified and is used as base for kexec. The kexec'd - * kernel should get the same memory map as the firmware provides. Then the - * user can e.g. boot the original kernel with mem=1G while still booting the - * next kernel with full memory. + * - inform the user about the firmware's notion of memory layout + * via /sys/firmware/memmap + * + * - the hibernation code uses it to generate a kernel-independent MD5 + * fingerprint of the physical memory layout of a system. + * + * - kexec, which is a bootloader in disguise, uses the original E820 + * layout to pass to the kexec-ed kernel. This way the original kernel + * can have a restricted E820 map while the kexec()-ed kexec-kernel + * can have access to full memory - etc. + * + * - 'e820_table': this is the main E820 table that is massaged by the + * low level x86 platform code, or modified by boot parameters, before + * passed on to higher level MM layers. + * + * Once the E820 map has been converted to the standard Linux memory layout + * information its role stops - modifying it has no effect and does not get + * re-propagated. So itsmain role is a temporary bootstrap storage of firmware + * specific memory layout data during early bootup. */ -static struct e820map initial_e820 __initdata; -static struct e820map initial_e820_saved __initdata; -struct e820map *e820 __refdata = &initial_e820; -struct e820map *e820_saved __refdata = &initial_e820_saved; +static struct e820_table e820_table_init __initdata; +static struct e820_table e820_table_firmware_init __initdata; + +struct e820_table *e820_table __refdata = &e820_table_init; +struct e820_table *e820_table_firmware __refdata = &e820_table_firmware_init; /* For PCI or other memory-mapped resources */ unsigned long pci_mem_start = 0xaeedbabe; @@ -55,51 +61,53 @@ EXPORT_SYMBOL(pci_mem_start); * This function checks if any part of the range <start,end> is mapped * with type. */ -int -e820_any_mapped(u64 start, u64 end, unsigned type) +bool e820__mapped_any(u64 start, u64 end, enum e820_type type) { int i; - for (i = 0; i < e820->nr_map; i++) { - struct e820entry *ei = &e820->map[i]; + for (i = 0; i < e820_table->nr_entries; i++) { + struct e820_entry *entry = &e820_table->entries[i]; - if (type && ei->type != type) + if (type && entry->type != type) continue; - if (ei->addr >= end || ei->addr + ei->size <= start) + if (entry->addr >= end || entry->addr + entry->size <= start) continue; return 1; } return 0; } -EXPORT_SYMBOL_GPL(e820_any_mapped); +EXPORT_SYMBOL_GPL(e820__mapped_any); /* - * This function checks if the entire range <start,end> is mapped with type. + * This function checks if the entire <start,end> range is mapped with 'type'. * - * Note: this function only works correct if the e820 table is sorted and - * not-overlapping, which is the case + * Note: this function only works correctly once the E820 table is sorted and + * not-overlapping (at least for the range specified), which is the case normally. */ -int __init e820_all_mapped(u64 start, u64 end, unsigned type) +bool __init e820__mapped_all(u64 start, u64 end, enum e820_type type) { int i; - for (i = 0; i < e820->nr_map; i++) { - struct e820entry *ei = &e820->map[i]; + for (i = 0; i < e820_table->nr_entries; i++) { + struct e820_entry *entry = &e820_table->entries[i]; - if (type && ei->type != type) + if (type && entry->type != type) continue; - /* is the region (part) in overlap with the current region ?*/ - if (ei->addr >= end || ei->addr + ei->size <= start) + + /* Is the region (part) in overlap with the current region? */ + if (entry->addr >= end || entry->addr + entry->size <= start) continue; - /* if the region is at the beginning of <start,end> we move - * start to the end of the region since it's ok until there + /* + * If the region is at the beginning of <start,end> we move + * 'start' to the end of the region since it's ok until there */ - if (ei->addr <= start) - start = ei->addr + ei->size; + if (entry->addr <= start) + start = entry->addr + entry->size; + /* - * if start is now at or beyond end, we're done, full - * coverage + * If 'start' is now at or beyond 'end', we're done, full + * coverage of the desired range exists: */ if (start >= end) return 1; @@ -108,94 +116,77 @@ int __init e820_all_mapped(u64 start, u64 end, unsigned type) } /* - * Add a memory region to the kernel e820 map. + * Add a memory region to the kernel E820 map. */ -static void __init __e820_add_region(struct e820map *e820x, u64 start, u64 size, - int type) +static void __init __e820__range_add(struct e820_table *table, u64 start, u64 size, enum e820_type type) { - int x = e820x->nr_map; + int x = table->nr_entries; - if (x >= ARRAY_SIZE(e820x->map)) { - printk(KERN_ERR "e820: too many entries; ignoring [mem %#010llx-%#010llx]\n", - (unsigned long long) start, - (unsigned long long) (start + size - 1)); + if (x >= ARRAY_SIZE(table->entries)) { + pr_err("e820: too many entries; ignoring [mem %#010llx-%#010llx]\n", start, start + size - 1); return; } - e820x->map[x].addr = start; - e820x->map[x].size = size; - e820x->map[x].type = type; - e820x->nr_map++; + table->entries[x].addr = start; + table->entries[x].size = size; + table->entries[x].type = type; + table->nr_entries++; } -void __init e820_add_region(u64 start, u64 size, int type) +void __init e820__range_add(u64 start, u64 size, enum e820_type type) { - __e820_add_region(e820, start, size, type); + __e820__range_add(e820_table, start, size, type); } -static void __init e820_print_type(u32 type) +static void __init e820_print_type(enum e820_type type) { switch (type) { - case E820_RAM: - case E820_RESERVED_KERN: - printk(KERN_CONT "usable"); - break; - case E820_RESERVED: - printk(KERN_CONT "reserved"); - break; - case E820_ACPI: - printk(KERN_CONT "ACPI data"); - break; - case E820_NVS: - printk(KERN_CONT "ACPI NVS"); - break; - case E820_UNUSABLE: - printk(KERN_CONT "unusable"); - break; - case E820_PMEM: - case E820_PRAM: - printk(KERN_CONT "persistent (type %u)", type); - break; - default: - printk(KERN_CONT "type %u", type); - break; + case E820_TYPE_RAM: /* Fall through: */ + case E820_TYPE_RESERVED_KERN: pr_cont("usable"); break; + case E820_TYPE_RESERVED: pr_cont("reserved"); break; + case E820_TYPE_ACPI: pr_cont("ACPI data"); break; + case E820_TYPE_NVS: pr_cont("ACPI NVS"); break; + case E820_TYPE_UNUSABLE: pr_cont("unusable"); break; + case E820_TYPE_PMEM: /* Fall through: */ + case E820_TYPE_PRAM: pr_cont("persistent (type %u)", type); break; + default: pr_cont("type %u", type); break; } } -void __init e820_print_map(char *who) +void __init e820__print_table(char *who) { int i; - for (i = 0; i < e820->nr_map; i++) { - printk(KERN_INFO "%s: [mem %#018Lx-%#018Lx] ", who, - (unsigned long long) e820->map[i].addr, - (unsigned long long) - (e820->map[i].addr + e820->map[i].size - 1)); - e820_print_type(e820->map[i].type); - printk(KERN_CONT "\n"); + for (i = 0; i < e820_table->nr_entries; i++) { + pr_info("%s: [mem %#018Lx-%#018Lx] ", who, + e820_table->entries[i].addr, + e820_table->entries[i].addr + e820_table->entries[i].size - 1); + + e820_print_type(e820_table->entries[i].type); + pr_cont("\n"); } } /* - * Sanitize the BIOS e820 map. + * Sanitize an E820 map. * - * Some e820 responses include overlapping entries. The following - * replaces the original e820 map with a new one, removing overlaps, + * Some E820 layouts include overlapping entries. The following + * replaces the original E820 map with a new one, removing overlaps, * and resolving conflicting memory types in favor of highest * numbered type. * - * The input parameter biosmap points to an array of 'struct - * e820entry' which on entry has elements in the range [0, *pnr_map) - * valid, and which has space for up to max_nr_map entries. - * On return, the resulting sanitized e820 map entries will be in - * overwritten in the same location, starting at biosmap. + * The input parameter 'entries' points to an array of 'struct + * e820_entry' which on entry has elements in the range [0, *nr_entries) + * valid, and which has space for up to max_nr_entries entries. + * On return, the resulting sanitized E820 map entries will be in + * overwritten in the same location, starting at 'entries'. * - * The integer pointed to by pnr_map must be valid on entry (the - * current number of valid entries located at biosmap). If the - * sanitizing succeeds the *pnr_map will be updated with the new - * number of valid entries (something no more than max_nr_map). + * The integer pointed to by nr_entries must be valid on entry (the + * current number of valid entries located at 'entries'). If the + * sanitizing succeeds the *nr_entries will be updated with the new + * number of valid entries (something no more than max_nr_entries). * - * The return value from sanitize_e820_map() is zero if it + * The return value from e820__update_table() is zero if it * successfully 'sanitized' the map entries passed in, and is -1 * if it did nothing, which can happen if either of (1) it was * only passed one map entry, or (2) any of the input map entries @@ -238,10 +229,17 @@ void __init e820_print_map(char *who) * ______________________4_ */ struct change_member { - struct e820entry *pbios; /* pointer to original bios entry */ - unsigned long long addr; /* address for this change point */ + /* Pointer to the original entry: */ + struct e820_entry *entry; + /* Address for this change point: */ + unsigned long long addr; }; +static struct change_member change_point_list[2*E820_MAX_ENTRIES] __initdata; +static struct change_member *change_point[2*E820_MAX_ENTRIES] __initdata; +static struct e820_entry *overlap_list[E820_MAX_ENTRIES] __initdata; +static struct e820_entry new_entries[E820_MAX_ENTRIES] __initdata; + static int __init cpcompare(const void *a, const void *b) { struct change_member * const *app = a, * const *bpp = b; @@ -249,164 +247,141 @@ static int __init cpcompare(const void *a, const void *b) /* * Inputs are pointers to two elements of change_point[]. If their - * addresses are unequal, their difference dominates. If the addresses + * addresses are not equal, their difference dominates. If the addresses * are equal, then consider one that represents the end of its region * to be greater than one that does not. */ if (ap->addr != bp->addr) return ap->addr > bp->addr ? 1 : -1; - return (ap->addr != ap->pbios->addr) - (bp->addr != bp->pbios->addr); + return (ap->addr != ap->entry->addr) - (bp->addr != bp->entry->addr); } -int __init sanitize_e820_map(struct e820entry *biosmap, int max_nr_map, - u32 *pnr_map) +int __init e820__update_table(struct e820_table *table) { - static struct change_member change_point_list[2*E820_X_MAX] __initdata; - static struct change_member *change_point[2*E820_X_MAX] __initdata; - static struct e820entry *overlap_list[E820_X_MAX] __initdata; - static struct e820entry new_bios[E820_X_MAX] __initdata; - unsigned long current_type, last_type; + struct e820_entry *entries = table->entries; + u32 max_nr_entries = ARRAY_SIZE(table->entries); + enum e820_type current_type, last_type; unsigned long long last_addr; - int chgidx; - int overlap_entries; - int new_bios_entry; - int old_nr, new_nr, chg_nr; - int i; + u32 new_nr_entries, overlap_entries; + u32 i, chg_idx, chg_nr; - /* if there's only one memory region, don't bother */ - if (*pnr_map < 2) + /* If there's only one memory region, don't bother: */ + if (table->nr_entries < 2) return -1; - old_nr = *pnr_map; - BUG_ON(old_nr > max_nr_map); + table->nr_entries = table->nr_entries; + BUG_ON(table->nr_entries > max_nr_entries); - /* bail out if we find any unreasonable addresses in bios map */ - for (i = 0; i < old_nr; i++) - if (biosmap[i].addr + biosmap[i].size < biosmap[i].addr) + /* Bail out if we find any unreasonable addresses in the map: */ + for (i = 0; i < table->nr_entries; i++) { + if (entries[i].addr + entries[i].size < entries[i].addr) return -1; + } - /* create pointers for initial change-point information (for sorting) */ - for (i = 0; i < 2 * old_nr; i++) + /* Create pointers for initial change-point information (for sorting): */ + for (i = 0; i < 2 * table->nr_entries; i++) change_point[i] = &change_point_list[i]; - /* record all known change-points (starting and ending addresses), - omitting those that are for empty memory regions */ - chgidx = 0; - for (i = 0; i < old_nr; i++) { - if (biosmap[i].size != 0) { - change_point[chgidx]->addr = biosmap[i].addr; - change_point[chgidx++]->pbios = &biosmap[i]; - change_point[chgidx]->addr = biosmap[i].addr + - biosmap[i].size; - change_point[chgidx++]->pbios = &biosmap[i]; + /* + * Record all known change-points (starting and ending addresses), + * omitting empty memory regions: + */ + chg_idx = 0; + for (i = 0; i < table->nr_entries; i++) { + if (entries[i].size != 0) { + change_point[chg_idx]->addr = entries[i].addr; + change_point[chg_idx++]->entry = &entries[i]; + change_point[chg_idx]->addr = entries[i].addr + entries[i].size; + change_point[chg_idx++]->entry = &entries[i]; } } - chg_nr = chgidx; - - /* sort change-point list by memory addresses (low -> high) */ - sort(change_point, chg_nr, sizeof *change_point, cpcompare, NULL); - - /* create a new bios memory map, removing overlaps */ - overlap_entries = 0; /* number of entries in the overlap table */ - new_bios_entry = 0; /* index for creating new bios map entries */ - last_type = 0; /* start with undefined memory type */ - last_addr = 0; /* start with 0 as last starting address */ - - /* loop through change-points, determining affect on the new bios map */ - for (chgidx = 0; chgidx < chg_nr; chgidx++) { - /* keep track of all overlapping bios entries */ - if (change_point[chgidx]->addr == - change_point[chgidx]->pbios->addr) { - /* - * add map entry to overlap list (> 1 entry - * implies an overlap) - */ - overlap_list[overlap_entries++] = - change_point[chgidx]->pbios; + chg_nr = chg_idx; + + /* Sort change-point list by memory addresses (low -> high): */ + sort(change_point, chg_nr, sizeof(*change_point), cpcompare, NULL); + + /* Create a new memory map, removing overlaps: */ + overlap_entries = 0; /* Number of entries in the overlap table */ + new_nr_entries = 0; /* Index for creating new map entries */ + last_type = 0; /* Start with undefined memory type */ + last_addr = 0; /* Start with 0 as last starting address */ + + /* Loop through change-points, determining effect on the new map: */ + for (chg_idx = 0; chg_idx < chg_nr; chg_idx++) { + /* Keep track of all overlapping entries */ + if (change_point[chg_idx]->addr == change_point[chg_idx]->entry->addr) { + /* Add map entry to overlap list (> 1 entry implies an overlap) */ + overlap_list[overlap_entries++] = change_point[chg_idx]->entry; } else { - /* - * remove entry from list (order independent, - * so swap with last) - */ + /* Remove entry from list (order independent, so swap with last): */ for (i = 0; i < overlap_entries; i++) { - if (overlap_list[i] == - change_point[chgidx]->pbios) - overlap_list[i] = - overlap_list[overlap_entries-1]; + if (overlap_list[i] == change_point[chg_idx]->entry) + overlap_list[i] = overlap_list[overlap_entries-1]; } overlap_entries--; } /* - * if there are overlapping entries, decide which + * If there are overlapping entries, decide which * "type" to use (larger value takes precedence -- * 1=usable, 2,3,4,4+=unusable) */ current_type = 0; - for (i = 0; i < overlap_entries; i++) + for (i = 0; i < overlap_entries; i++) { if (overlap_list[i]->type > current_type) current_type = overlap_list[i]->type; - /* - * continue building up new bios map based on this - * information - */ - if (current_type != last_type || current_type == E820_PRAM) { + } + + /* Continue building up new map based on this information: */ + if (current_type != last_type || current_type == E820_TYPE_PRAM) { if (last_type != 0) { - new_bios[new_bios_entry].size = - change_point[chgidx]->addr - last_addr; - /* - * move forward only if the new size - * was non-zero - */ - if (new_bios[new_bios_entry].size != 0) - /* - * no more space left for new - * bios entries ? - */ - if (++new_bios_entry >= max_nr_map) + new_entries[new_nr_entries].size = change_point[chg_idx]->addr - last_addr; + /* Move forward only if the new size was non-zero: */ + if (new_entries[new_nr_entries].size != 0) + /* No more space left for new entries? */ + if (++new_nr_entries >= max_nr_entries) break; } if (current_type != 0) { - new_bios[new_bios_entry].addr = - change_point[chgidx]->addr; - new_bios[new_bios_entry].type = current_type; - last_addr = change_point[chgidx]->addr; + new_entries[new_nr_entries].addr = change_point[chg_idx]->addr; + new_entries[new_nr_entries].type = current_type; + last_addr = change_point[chg_idx]->addr; } last_type = current_type; } } - /* retain count for new bios entries */ - new_nr = new_bios_entry; - /* copy new bios mapping into original location */ - memcpy(biosmap, new_bios, new_nr * sizeof(struct e820entry)); - *pnr_map = new_nr; + /* Copy the new entries into the original location: */ + memcpy(entries, new_entries, new_nr_entries*sizeof(*entries)); + table->nr_entries = new_nr_entries; return 0; } -static int __init __append_e820_map(struct e820entry *biosmap, int nr_map) +static int __init __append_e820_table(struct boot_e820_entry *entries, u32 nr_entries) { - while (nr_map) { - u64 start = biosmap->addr; - u64 size = biosmap->size; + struct boot_e820_entry *entry = entries; + + while (nr_entries) { + u64 start = entry->addr; + u64 size = entry->size; u64 end = start + size - 1; - u32 type = biosmap->type; + u32 type = entry->type; - /* Overflow in 64 bits? Ignore the memory map. */ + /* Ignore the entry on 64-bit overflow: */ if (start > end && likely(size)) return -1; - e820_add_region(start, size, type); + e820__range_add(start, size, type); - biosmap++; - nr_map--; + entry++; + nr_entries--; } return 0; } /* - * Copy the BIOS e820 map into a safe place. + * Copy the BIOS E820 map into a safe place. * * Sanity-check it while we're at it.. * @@ -414,18 +389,17 @@ static int __init __append_e820_map(struct e820entry *biosmap, int nr_map) * will have given us a memory map that we can use to properly * set up memory. If we aren't, we'll fake a memory map. */ -static int __init append_e820_map(struct e820entry *biosmap, int nr_map) +static int __init append_e820_table(struct boot_e820_entry *entries, u32 nr_entries) { /* Only one memory region (or negative)? Ignore it */ - if (nr_map < 2) + if (nr_entries < 2) return -1; - return __append_e820_map(biosmap, nr_map); + return __append_e820_table(entries, nr_entries); } -static u64 __init __e820_update_range(struct e820map *e820x, u64 start, - u64 size, unsigned old_type, - unsigned new_type) +static u64 __init +__e820__range_update(struct e820_table *table, u64 start, u64 size, enum e820_type old_type, enum e820_type new_type) { u64 end; unsigned int i; @@ -437,77 +411,73 @@ static u64 __init __e820_update_range(struct e820map *e820x, u64 start, size = ULLONG_MAX - start; end = start + size; - printk(KERN_DEBUG "e820: update [mem %#010Lx-%#010Lx] ", - (unsigned long long) start, (unsigned long long) (end - 1)); + printk(KERN_DEBUG "e820: update [mem %#010Lx-%#010Lx] ", start, end - 1); e820_print_type(old_type); - printk(KERN_CONT " ==> "); + pr_cont(" ==> "); e820_print_type(new_type); - printk(KERN_CONT "\n"); + pr_cont("\n"); - for (i = 0; i < e820x->nr_map; i++) { - struct e820entry *ei = &e820x->map[i]; + for (i = 0; i < table->nr_entries; i++) { + struct e820_entry *entry = &table->entries[i]; u64 final_start, final_end; - u64 ei_end; + u64 entry_end; - if (ei->type != old_type) + if (entry->type != old_type) continue; - ei_end = ei->addr + ei->size; - /* totally covered by new range? */ - if (ei->addr >= start && ei_end <= end) { - ei->type = new_type; - real_updated_size += ei->size; + entry_end = entry->addr + entry->size; + + /* Completely covered by new range? */ + if (entry->addr >= start && entry_end <= end) { + entry->type = new_type; + real_updated_size += entry->size; continue; } - /* new range is totally covered? */ - if (ei->addr < start && ei_end > end) { - __e820_add_region(e820x, start, size, new_type); - __e820_add_region(e820x, end, ei_end - end, ei->type); - ei->size = start - ei->addr; + /* New range is completely covered? */ + if (entry->addr < start && entry_end > end) { + __e820__range_add(table, start, size, new_type); + __e820__range_add(table, end, entry_end - end, entry->type); + entry->size = start - entry->addr; real_updated_size += size; continue; } - /* partially covered */ - final_start = max(start, ei->addr); - final_end = min(end, ei_end); + /* Partially covered: */ + final_start = max(start, entry->addr); + final_end = min(end, entry_end); if (final_start >= final_end) continue; - __e820_add_region(e820x, final_start, final_end - final_start, - new_type); + __e820__range_add(table, final_start, final_end - final_start, new_type); real_updated_size += final_end - final_start; /* - * left range could be head or tail, so need to update - * size at first. + * Left range could be head or tail, so need to update + * its size first: */ - ei->size -= final_end - final_start; - if (ei->addr < final_start) + entry->size -= final_end - final_start; + if (entry->addr < final_start) continue; - ei->addr = final_end; + + entry->addr = final_end; } return real_updated_size; } -u64 __init e820_update_range(u64 start, u64 size, unsigned old_type, - unsigned new_type) +u64 __init e820__range_update(u64 start, u64 size, enum e820_type old_type, enum e820_type new_type) { - return __e820_update_range(e820, start, size, old_type, new_type); + return __e820__range_update(e820_table, start, size, old_type, new_type); } -static u64 __init e820_update_range_saved(u64 start, u64 size, - unsigned old_type, unsigned new_type) +static u64 __init e820__range_update_firmware(u64 start, u64 size, enum e820_type old_type, enum e820_type new_type) { - return __e820_update_range(e820_saved, start, size, old_type, - new_type); + return __e820__range_update(e820_table_firmware, start, size, old_type, new_type); } -/* make e820 not cover the range */ -u64 __init e820_remove_range(u64 start, u64 size, unsigned old_type, - int checktype) +/* Remove a range of memory from the E820 table: */ +u64 __init e820__range_remove(u64 start, u64 size, enum e820_type old_type, bool check_type) { int i; u64 end; @@ -517,85 +487,89 @@ u64 __init e820_remove_range(u64 start, u64 size, unsigned old_type, size = ULLONG_MAX - start; end = start + size; - printk(KERN_DEBUG "e820: remove [mem %#010Lx-%#010Lx] ", - (unsigned long long) start, (unsigned long long) (end - 1)); - if (checktype) + printk(KERN_DEBUG "e820: remove [mem %#010Lx-%#010Lx] ", start, end - 1); + if (check_type) e820_print_type(old_type); - printk(KERN_CONT "\n"); + pr_cont("\n"); - for (i = 0; i < e820->nr_map; i++) { - struct e820entry *ei = &e820->map[i]; + for (i = 0; i < e820_table->nr_entries; i++) { + struct e820_entry *entry = &e820_table->entries[i]; u64 final_start, final_end; - u64 ei_end; + u64 entry_end; - if (checktype && ei->type != old_type) + if (check_type && entry->type != old_type) continue; - ei_end = ei->addr + ei->size; - /* totally covered? */ - if (ei->addr >= start && ei_end <= end) { - real_removed_size += ei->size; - memset(ei, 0, sizeof(struct e820entry)); + entry_end = entry->addr + entry->size; + + /* Completely covered? */ + if (entry->addr >= start && entry_end <= end) { + real_removed_size += entry->size; + memset(entry, 0, sizeof(*entry)); continue; } - /* new range is totally covered? */ - if (ei->addr < start && ei_end > end) { - e820_add_region(end, ei_end - end, ei->type); - ei->size = start - ei->addr; + /* Is the new range completely covered? */ + if (entry->addr < start && entry_end > end) { + e820__range_add(end, entry_end - end, entry->type); + entry->size = start - entry->addr; real_removed_size += size; continue; } - /* partially covered */ - final_start = max(start, ei->addr); - final_end = min(end, ei_end); + /* Partially covered: */ + final_start = max(start, entry->addr); + final_end = min(end, entry_end); if (final_start >= final_end) continue; + real_removed_size += final_end - final_start; /* - * left range could be head or tail, so need to update - * size at first. + * Left range could be head or tail, so need to update + * the size first: */ - ei->size -= final_end - final_start; - if (ei->addr < final_start) + entry->size -= final_end - final_start; + if (entry->addr < final_start) continue; - ei->addr = final_end; + + entry->addr = final_end; } return real_removed_size; } -void __init update_e820(void) +void __init e820__update_table_print(void) { - if (sanitize_e820_map(e820->map, ARRAY_SIZE(e820->map), &e820->nr_map)) + if (e820__update_table(e820_table)) return; - printk(KERN_INFO "e820: modified physical RAM map:\n"); - e820_print_map("modified"); + + pr_info("e820: modified physical RAM map:\n"); + e820__print_table("modified"); } -static void __init update_e820_saved(void) + +static void __init e820__update_table_firmware(void) { - sanitize_e820_map(e820_saved->map, ARRAY_SIZE(e820_saved->map), - &e820_saved->nr_map); + e820__update_table(e820_table_firmware); } + #define MAX_GAP_END 0x100000000ull + /* - * Search for a gap in the e820 memory space from 0 to MAX_GAP_END. + * Search for a gap in the E820 memory space from 0 to MAX_GAP_END (4GB). */ -static int __init e820_search_gap(unsigned long *gapstart, - unsigned long *gapsize) +static int __init e820_search_gap(unsigned long *gapstart, unsigned long *gapsize) { unsigned long long last = MAX_GAP_END; - int i = e820->nr_map; + int i = e820_table->nr_entries; int found = 0; while (--i >= 0) { - unsigned long long start = e820->map[i].addr; - unsigned long long end = start + e820->map[i].size; + unsigned long long start = e820_table->entries[i].addr; + unsigned long long end = start + e820_table->entries[i].size; /* * Since "last" is at most 4GB, we know we'll - * fit in 32 bits if this condition is true + * fit in 32 bits if this condition is true: */ if (last > end) { unsigned long gap = last - end; @@ -613,12 +587,14 @@ static int __init e820_search_gap(unsigned long *gapstart, } /* - * Search for the biggest gap in the low 32 bits of the e820 - * memory space. We pass this space to PCI to assign MMIO resources - * for hotplug or unconfigured devices in. + * Search for the biggest gap in the low 32 bits of the E820 + * memory space. We pass this space to the PCI subsystem, so + * that it can assign MMIO resources for hotplug or + * unconfigured devices in. + * * Hopefully the BIOS let enough space left. */ -__init void e820_setup_gap(void) +__init void e820__setup_pci_gap(void) { unsigned long gapstart, gapsize; int found; @@ -629,138 +605,143 @@ __init void e820_setup_gap(void) if (!found) { #ifdef CONFIG_X86_64 gapstart = (max_pfn << PAGE_SHIFT) + 1024*1024; - printk(KERN_ERR - "e820: cannot find a gap in the 32bit address range\n" - "e820: PCI devices with unassigned 32bit BARs may break!\n"); + pr_err( + "e820: Cannot find an available gap in the 32-bit address range\n" + "e820: PCI devices with unassigned 32-bit BARs may not work!\n"); #else gapstart = 0x10000000; #endif } /* - * e820_reserve_resources_late protect stolen RAM already + * e820__reserve_resources_late() protects stolen RAM already: */ pci_mem_start = gapstart; - printk(KERN_INFO - "e820: [mem %#010lx-%#010lx] available for PCI devices\n", - gapstart, gapstart + gapsize - 1); + pr_info("e820: [mem %#010lx-%#010lx] available for PCI devices\n", gapstart, gapstart + gapsize - 1); } /* * Called late during init, in free_initmem(). * - * Initial e820 and e820_saved are largish __initdata arrays. - * Copy them to (usually much smaller) dynamically allocated area. - * This is done after all tweaks we ever do to them: - * all functions which modify them are __init functions, - * they won't exist after this point. + * Initial e820_table and e820_table_firmware are largish __initdata arrays. + * + * Copy them to a (usually much smaller) dynamically allocated area that is + * sized precisely after the number of e820 entries. + * + * This is done after we've performed all the fixes and tweaks to the tables. + * All functions which modify them are __init functions, which won't exist + * after free_initmem(). */ -__init void e820_reallocate_tables(void) +__init void e820__reallocate_tables(void) { - struct e820map *n; + struct e820_table *n; int size; - size = offsetof(struct e820map, map) + sizeof(struct e820entry) * e820->nr_map; + size = offsetof(struct e820_table, entries) + sizeof(struct e820_entry)*e820_table->nr_entries; n = kmalloc(size, GFP_KERNEL); BUG_ON(!n); - memcpy(n, e820, size); - e820 = n; + memcpy(n, e820_table, size); + e820_table = n; - size = offsetof(struct e820map, map) + sizeof(struct e820entry) * e820_saved->nr_map; + size = offsetof(struct e820_table, entries) + sizeof(struct e820_entry)*e820_table_firmware->nr_entries; n = kmalloc(size, GFP_KERNEL); BUG_ON(!n); - memcpy(n, e820_saved, size); - e820_saved = n; + memcpy(n, e820_table_firmware, size); + e820_table_firmware = n; } -/** - * Because of the size limitation of struct boot_params, only first - * 128 E820 memory entries are passed to kernel via - * boot_params.e820_map, others are passed via SETUP_E820_EXT node of - * linked list of struct setup_data, which is parsed here. +/* + * Because of the small fixed size of struct boot_params, only the first + * 128 E820 memory entries are passed to the kernel via boot_params.e820_table, + * the remaining (if any) entries are passed via the SETUP_E820_EXT node of + * struct setup_data, which is parsed here. */ -void __init parse_e820_ext(u64 phys_addr, u32 data_len) +void __init e820__memory_setup_extended(u64 phys_addr, u32 data_len) { int entries; - struct e820entry *extmap; + struct boot_e820_entry *extmap; struct setup_data *sdata; sdata = early_memremap(phys_addr, data_len); - entries = sdata->len / sizeof(struct e820entry); - extmap = (struct e820entry *)(sdata->data); - __append_e820_map(extmap, entries); - sanitize_e820_map(e820->map, ARRAY_SIZE(e820->map), &e820->nr_map); + entries = sdata->len / sizeof(*extmap); + extmap = (struct boot_e820_entry *)(sdata->data); + + __append_e820_table(extmap, entries); + e820__update_table(e820_table); + early_memunmap(sdata, data_len); - printk(KERN_INFO "e820: extended physical RAM map:\n"); - e820_print_map("extended"); + pr_info("e820: extended physical RAM map:\n"); + e820__print_table("extended"); } -#if defined(CONFIG_X86_64) || \ - (defined(CONFIG_X86_32) && defined(CONFIG_HIBERNATION)) -/** +/* * Find the ranges of physical addresses that do not correspond to - * e820 RAM areas and mark the corresponding pages as nosave for - * hibernation (32 bit) or software suspend and suspend to RAM (64 bit). + * E820 RAM areas and register the corresponding pages as 'nosave' for + * hibernation (32-bit) or software suspend and suspend to RAM (64-bit). * - * This function requires the e820 map to be sorted and without any + * This function requires the E820 map to be sorted and without any * overlapping entries. */ -void __init e820_mark_nosave_regions(unsigned long limit_pfn) +void __init e820__register_nosave_regions(unsigned long limit_pfn) { int i; unsigned long pfn = 0; - for (i = 0; i < e820->nr_map; i++) { - struct e820entry *ei = &e820->map[i]; + for (i = 0; i < e820_table->nr_entries; i++) { + struct e820_entry *entry = &e820_table->entries[i]; - if (pfn < PFN_UP(ei->addr)) - register_nosave_region(pfn, PFN_UP(ei->addr)); + if (pfn < PFN_UP(entry->addr)) + register_nosave_region(pfn, PFN_UP(entry->addr)); - pfn = PFN_DOWN(ei->addr + ei->size); + pfn = PFN_DOWN(entry->addr + entry->size); - if (ei->type != E820_RAM && ei->type != E820_RESERVED_KERN) - register_nosave_region(PFN_UP(ei->addr), pfn); + if (entry->type != E820_TYPE_RAM && entry->type != E820_TYPE_RESERVED_KERN) + register_nosave_region(PFN_UP(entry->addr), pfn); if (pfn >= limit_pfn) break; } } -#endif #ifdef CONFIG_ACPI -/** - * Mark ACPI NVS memory region, so that we can save/restore it during - * hibernation and the subsequent resume. +/* + * Register ACPI NVS memory regions, so that we can save/restore them during + * hibernation and the subsequent resume: */ -static int __init e820_mark_nvs_memory(void) +static int __init e820__register_nvs_regions(void) { int i; - for (i = 0; i < e820->nr_map; i++) { - struct e820entry *ei = &e820->map[i]; + for (i = 0; i < e820_table->nr_entries; i++) { + struct e820_entry *entry = &e820_table->entries[i]; - if (ei->type == E820_NVS) - acpi_nvs_register(ei->addr, ei->size); + if (entry->type == E820_TYPE_NVS) + acpi_nvs_register(entry->addr, entry->size); } return 0; } -core_initcall(e820_mark_nvs_memory); +core_initcall(e820__register_nvs_regions); #endif /* - * pre allocated 4k and reserved it in memblock and e820_saved + * Allocate the requested number of bytes with the requsted alignment + * and return (the physical address) to the caller. Also register this + * range in the 'firmware' E820 table as a reserved range. + * + * This allows kexec to fake a new mptable, as if it came from the real + * system. */ -u64 __init early_reserve_e820(u64 size, u64 align) +u64 __init e820__memblock_alloc_reserved(u64 size, u64 align) { u64 addr; addr = __memblock_alloc_base(size, align, MEMBLOCK_ALLOC_ACCESSIBLE); if (addr) { - e820_update_range_saved(addr, size, E820_RAM, E820_RESERVED); - printk(KERN_INFO "e820: update e820_saved for early_reserve_e820\n"); - update_e820_saved(); + e820__range_update_firmware(addr, size, E820_TYPE_RAM, E820_TYPE_RESERVED); + pr_info("e820: update e820_table_firmware for e820__memblock_alloc_reserved()\n"); + e820__update_table_firmware(); } return addr; @@ -779,22 +760,22 @@ u64 __init early_reserve_e820(u64 size, u64 align) /* * Find the highest page frame number we have available */ -static unsigned long __init e820_end_pfn(unsigned long limit_pfn, unsigned type) +static unsigned long __init e820_end_pfn(unsigned long limit_pfn, enum e820_type type) { int i; unsigned long last_pfn = 0; unsigned long max_arch_pfn = MAX_ARCH_PFN; - for (i = 0; i < e820->nr_map; i++) { - struct e820entry *ei = &e820->map[i]; + for (i = 0; i < e820_table->nr_entries; i++) { + struct e820_entry *entry = &e820_table->entries[i]; unsigned long start_pfn; unsigned long end_pfn; - if (ei->type != type) + if (entry->type != type) continue; - start_pfn = ei->addr >> PAGE_SHIFT; - end_pfn = (ei->addr + ei->size) >> PAGE_SHIFT; + start_pfn = entry->addr >> PAGE_SHIFT; + end_pfn = (entry->addr + entry->size) >> PAGE_SHIFT; if (start_pfn >= limit_pfn) continue; @@ -809,18 +790,19 @@ static unsigned long __init e820_end_pfn(unsigned long limit_pfn, unsigned type) if (last_pfn > max_arch_pfn) last_pfn = max_arch_pfn; - printk(KERN_INFO "e820: last_pfn = %#lx max_arch_pfn = %#lx\n", + pr_info("e820: last_pfn = %#lx max_arch_pfn = %#lx\n", last_pfn, max_arch_pfn); return last_pfn; } -unsigned long __init e820_end_of_ram_pfn(void) + +unsigned long __init e820__end_of_ram_pfn(void) { - return e820_end_pfn(MAX_ARCH_PFN, E820_RAM); + return e820_end_pfn(MAX_ARCH_PFN, E820_TYPE_RAM); } -unsigned long __init e820_end_of_low_ram_pfn(void) +unsigned long __init e820__end_of_low_ram_pfn(void) { - return e820_end_pfn(1UL << (32 - PAGE_SHIFT), E820_RAM); + return e820_end_pfn(1UL << (32 - PAGE_SHIFT), E820_TYPE_RAM); } static void __init early_panic(char *msg) @@ -831,7 +813,7 @@ static void __init early_panic(char *msg) static int userdef __initdata; -/* "mem=nopentium" disables the 4MB page tables. */ +/* The "mem=nopentium" boot option disables 4MB page tables on 32-bit kernels: */ static int __init parse_memopt(char *p) { u64 mem_size; @@ -844,17 +826,19 @@ static int __init parse_memopt(char *p) setup_clear_cpu_cap(X86_FEATURE_PSE); return 0; #else - printk(KERN_WARNING "mem=nopentium ignored! (only supported on x86_32)\n"); + pr_warn("mem=nopentium ignored! (only supported on x86_32)\n"); return -EINVAL; #endif } userdef = 1; mem_size = memparse(p, &p); - /* don't remove all of memory when handling "mem={invalid}" param */ + + /* Don't remove all memory when getting "mem={invalid}" parameter: */ if (mem_size == 0) return -EINVAL; - e820_remove_range(mem_size, ULLONG_MAX - mem_size, E820_RAM, 1); + + e820__range_remove(mem_size, ULLONG_MAX - mem_size, E820_TYPE_RAM, 1); return 0; } @@ -872,12 +856,12 @@ static int __init parse_memmap_one(char *p) #ifdef CONFIG_CRASH_DUMP /* * If we are doing a crash dump, we still need to know - * the real mem size before original memory map is + * the real memory size before the original memory map is * reset. */ - saved_max_pfn = e820_end_of_ram_pfn(); + saved_max_pfn = e820__end_of_ram_pfn(); #endif - e820->nr_map = 0; + e820_table->nr_entries = 0; userdef = 1; return 0; } @@ -890,21 +874,23 @@ static int __init parse_memmap_one(char *p) userdef = 1; if (*p == '@') { start_at = memparse(p+1, &p); - e820_add_region(start_at, mem_size, E820_RAM); + e820__range_add(start_at, mem_size, E820_TYPE_RAM); } else if (*p == '#') { start_at = memparse(p+1, &p); - e820_add_region(start_at, mem_size, E820_ACPI); + e820__range_add(start_at, mem_size, E820_TYPE_ACPI); } else if (*p == '$') { start_at = memparse(p+1, &p); - e820_add_region(start_at, mem_size, E820_RESERVED); + e820__range_add(start_at, mem_size, E820_TYPE_RESERVED); } else if (*p == '!') { start_at = memparse(p+1, &p); - e820_add_region(start_at, mem_size, E820_PRAM); - } else - e820_remove_range(mem_size, ULLONG_MAX - mem_size, E820_RAM, 1); + e820__range_add(start_at, mem_size, E820_TYPE_PRAM); + } else { + e820__range_remove(mem_size, ULLONG_MAX - mem_size, E820_TYPE_RAM, 1); + } return *p == '\0' ? 0 : -EINVAL; } + static int __init parse_memmap_opt(char *str) { while (str) { @@ -921,68 +907,97 @@ static int __init parse_memmap_opt(char *str) } early_param("memmap", parse_memmap_opt); -void __init finish_e820_parsing(void) +/* + * Reserve all entries from the bootloader's extensible data nodes list, + * because if present we are going to use it later on to fetch e820 + * entries from it: + */ +void __init e820__reserve_setup_data(void) +{ + struct setup_data *data; + u64 pa_data; + + pa_data = boot_params.hdr.setup_data; + if (!pa_data) + return; + + while (pa_data) { + data = early_memremap(pa_data, sizeof(*data)); + e820__range_update(pa_data, sizeof(*data)+data->len, E820_TYPE_RAM, E820_TYPE_RESERVED_KERN); + pa_data = data->next; + early_memunmap(data, sizeof(*data)); + } + + e820__update_table(e820_table); + + memcpy(e820_table_firmware, e820_table, sizeof(*e820_table_firmware)); + + pr_info("extended physical RAM map:\n"); + e820__print_table("reserve setup_data"); +} + +/* + * Called after parse_early_param(), after early parameters (such as mem=) + * have been processed, in which case we already have an E820 table filled in + * via the parameter callback function(s), but it's not sorted and printed yet: + */ +void __init e820__finish_early_params(void) { if (userdef) { - if (sanitize_e820_map(e820->map, ARRAY_SIZE(e820->map), - &e820->nr_map) < 0) + if (e820__update_table(e820_table) < 0) early_panic("Invalid user supplied memory map"); - printk(KERN_INFO "e820: user-defined physical RAM map:\n"); - e820_print_map("user"); + pr_info("e820: user-defined physical RAM map:\n"); + e820__print_table("user"); } } -static const char *__init e820_type_to_string(int e820_type) +static const char *__init e820_type_to_string(struct e820_entry *entry) { - switch (e820_type) { - case E820_RESERVED_KERN: - case E820_RAM: return "System RAM"; - case E820_ACPI: return "ACPI Tables"; - case E820_NVS: return "ACPI Non-volatile Storage"; - case E820_UNUSABLE: return "Unusable memory"; - case E820_PRAM: return "Persistent Memory (legacy)"; - case E820_PMEM: return "Persistent Memory"; - default: return "reserved"; + switch (entry->type) { + case E820_TYPE_RESERVED_KERN: /* Fall-through: */ + case E820_TYPE_RAM: return "System RAM"; + case E820_TYPE_ACPI: return "ACPI Tables"; + case E820_TYPE_NVS: return "ACPI Non-volatile Storage"; + case E820_TYPE_UNUSABLE: return "Unusable memory"; + case E820_TYPE_PRAM: return "Persistent Memory (legacy)"; + case E820_TYPE_PMEM: return "Persistent Memory"; + case E820_TYPE_RESERVED: return "Reserved"; + default: return "Unknown E820 type"; } } -static unsigned long __init e820_type_to_iomem_type(int e820_type) +static unsigned long __init e820_type_to_iomem_type(struct e820_entry *entry) { - switch (e820_type) { - case E820_RESERVED_KERN: - case E820_RAM: - return IORESOURCE_SYSTEM_RAM; - case E820_ACPI: - case E820_NVS: - case E820_UNUSABLE: - case E820_PRAM: - case E820_PMEM: - default: - return IORESOURCE_MEM; + switch (entry->type) { + case E820_TYPE_RESERVED_KERN: /* Fall-through: */ + case E820_TYPE_RAM: return IORESOURCE_SYSTEM_RAM; + case E820_TYPE_ACPI: /* Fall-through: */ + case E820_TYPE_NVS: /* Fall-through: */ + case E820_TYPE_UNUSABLE: /* Fall-through: */ + case E820_TYPE_PRAM: /* Fall-through: */ + case E820_TYPE_PMEM: /* Fall-through: */ + case E820_TYPE_RESERVED: /* Fall-through: */ + default: return IORESOURCE_MEM; } } -static unsigned long __init e820_type_to_iores_desc(int e820_type) +static unsigned long __init e820_type_to_iores_desc(struct e820_entry *entry) { - switch (e820_type) { - case E820_ACPI: - return IORES_DESC_ACPI_TABLES; - case E820_NVS: - return IORES_DESC_ACPI_NV_STORAGE; - case E820_PMEM: - return IORES_DESC_PERSISTENT_MEMORY; - case E820_PRAM: - return IORES_DESC_PERSISTENT_MEMORY_LEGACY; - case E820_RESERVED_KERN: - case E820_RAM: - case E820_UNUSABLE: - default: - return IORES_DESC_NONE; + switch (entry->type) { + case E820_TYPE_ACPI: return IORES_DESC_ACPI_TABLES; + case E820_TYPE_NVS: return IORES_DESC_ACPI_NV_STORAGE; + case E820_TYPE_PMEM: return IORES_DESC_PERSISTENT_MEMORY; + case E820_TYPE_PRAM: return IORES_DESC_PERSISTENT_MEMORY_LEGACY; + case E820_TYPE_RESERVED_KERN: /* Fall-through: */ + case E820_TYPE_RAM: /* Fall-through: */ + case E820_TYPE_UNUSABLE: /* Fall-through: */ + case E820_TYPE_RESERVED: /* Fall-through: */ + default: return IORES_DESC_NONE; } } -static bool __init do_mark_busy(u32 type, struct resource *res) +static bool __init do_mark_busy(enum e820_type type, struct resource *res) { /* this is the legacy bios/dos rom-shadow + mmio region */ if (res->start < (1ULL<<20)) @@ -993,61 +1008,71 @@ static bool __init do_mark_busy(u32 type, struct resource *res) * for exclusive use of a driver */ switch (type) { - case E820_RESERVED: - case E820_PRAM: - case E820_PMEM: + case E820_TYPE_RESERVED: + case E820_TYPE_PRAM: + case E820_TYPE_PMEM: return false; + case E820_TYPE_RESERVED_KERN: + case E820_TYPE_RAM: + case E820_TYPE_ACPI: + case E820_TYPE_NVS: + case E820_TYPE_UNUSABLE: default: return true; } } /* - * Mark e820 reserved areas as busy for the resource manager. + * Mark E820 reserved areas as busy for the resource manager: */ + static struct resource __initdata *e820_res; -void __init e820_reserve_resources(void) + +void __init e820__reserve_resources(void) { int i; struct resource *res; u64 end; - res = alloc_bootmem(sizeof(struct resource) * e820->nr_map); + res = alloc_bootmem(sizeof(*res) * e820_table->nr_entries); e820_res = res; - for (i = 0; i < e820->nr_map; i++) { - end = e820->map[i].addr + e820->map[i].size - 1; + + for (i = 0; i < e820_table->nr_entries; i++) { + struct e820_entry *entry = e820_table->entries + i; + + end = entry->addr + entry->size - 1; if (end != (resource_size_t)end) { res++; continue; } - res->name = e820_type_to_string(e820->map[i].type); - res->start = e820->map[i].addr; - res->end = end; - - res->flags = e820_type_to_iomem_type(e820->map[i].type); - res->desc = e820_type_to_iores_desc(e820->map[i].type); + res->start = entry->addr; + res->end = end; + res->name = e820_type_to_string(entry); + res->flags = e820_type_to_iomem_type(entry); + res->desc = e820_type_to_iores_desc(entry); /* - * don't register the region that could be conflicted with - * pci device BAR resource and insert them later in - * pcibios_resource_survey() + * Don't register the region that could be conflicted with + * PCI device BAR resources and insert them later in + * pcibios_resource_survey(): */ - if (do_mark_busy(e820->map[i].type, res)) { + if (do_mark_busy(entry->type, res)) { res->flags |= IORESOURCE_BUSY; insert_resource(&iomem_resource, res); } res++; } - for (i = 0; i < e820_saved->nr_map; i++) { - struct e820entry *entry = &e820_saved->map[i]; - firmware_map_add_early(entry->addr, - entry->addr + entry->size, - e820_type_to_string(entry->type)); + for (i = 0; i < e820_table_firmware->nr_entries; i++) { + struct e820_entry *entry = e820_table_firmware->entries + i; + + firmware_map_add_early(entry->addr, entry->addr + entry->size, e820_type_to_string(entry)); } } -/* How much should we pad RAM ending depending on where it is? */ +/* + * How much should we pad the end of RAM, depending on where it is? + */ static unsigned long __init ram_alignment(resource_size_t pos) { unsigned long mb = pos >> 20; @@ -1066,64 +1091,59 @@ static unsigned long __init ram_alignment(resource_size_t pos) #define MAX_RESOURCE_SIZE ((resource_size_t)-1) -void __init e820_reserve_resources_late(void) +void __init e820__reserve_resources_late(void) { int i; struct resource *res; res = e820_res; - for (i = 0; i < e820->nr_map; i++) { + for (i = 0; i < e820_table->nr_entries; i++) { if (!res->parent && res->end) insert_resource_expand_to_fit(&iomem_resource, res); res++; } /* - * Try to bump up RAM regions to reasonable boundaries to + * Try to bump up RAM regions to reasonable boundaries, to * avoid stolen RAM: */ - for (i = 0; i < e820->nr_map; i++) { - struct e820entry *entry = &e820->map[i]; + for (i = 0; i < e820_table->nr_entries; i++) { + struct e820_entry *entry = &e820_table->entries[i]; u64 start, end; - if (entry->type != E820_RAM) + if (entry->type != E820_TYPE_RAM) continue; + start = entry->addr + entry->size; end = round_up(start, ram_alignment(start)) - 1; if (end > MAX_RESOURCE_SIZE) end = MAX_RESOURCE_SIZE; if (start >= end) continue; - printk(KERN_DEBUG - "e820: reserve RAM buffer [mem %#010llx-%#010llx]\n", - start, end); - reserve_region_with_split(&iomem_resource, start, end, - "RAM buffer"); + + printk(KERN_DEBUG "e820: reserve RAM buffer [mem %#010llx-%#010llx]\n", start, end); + reserve_region_with_split(&iomem_resource, start, end, "RAM buffer"); } } -char *__init default_machine_specific_memory_setup(void) +/* + * Pass the firmware (bootloader) E820 map to the kernel and process it: + */ +char *__init e820__memory_setup_default(void) { char *who = "BIOS-e820"; - u32 new_nr; + /* * Try to copy the BIOS-supplied E820-map. * * Otherwise fake a memory map; one section from 0k->640k, * the next section from 1mb->appropriate_mem_k */ - new_nr = boot_params.e820_entries; - sanitize_e820_map(boot_params.e820_map, - ARRAY_SIZE(boot_params.e820_map), - &new_nr); - boot_params.e820_entries = new_nr; - if (append_e820_map(boot_params.e820_map, boot_params.e820_entries) - < 0) { + if (append_e820_table(boot_params.e820_table, boot_params.e820_entries) < 0) { u64 mem_size; - /* compare results from other methods and take the greater */ - if (boot_params.alt_mem_k - < boot_params.screen_info.ext_mem_k) { + /* Compare results from other methods and take the one that gives more RAM: */ + if (boot_params.alt_mem_k < boot_params.screen_info.ext_mem_k) { mem_size = boot_params.screen_info.ext_mem_k; who = "BIOS-88"; } else { @@ -1131,84 +1151,68 @@ char *__init default_machine_specific_memory_setup(void) who = "BIOS-e801"; } - e820->nr_map = 0; - e820_add_region(0, LOWMEMSIZE(), E820_RAM); - e820_add_region(HIGH_MEMORY, mem_size << 10, E820_RAM); + e820_table->nr_entries = 0; + e820__range_add(0, LOWMEMSIZE(), E820_TYPE_RAM); + e820__range_add(HIGH_MEMORY, mem_size << 10, E820_TYPE_RAM); } - /* In case someone cares... */ + /* We just appended a lot of ranges, sanitize the table: */ + e820__update_table(e820_table); + return who; } -void __init setup_memory_map(void) +/* + * Calls e820__memory_setup_default() in essence to pick up the firmware/bootloader + * E820 map - with an optional platform quirk available for virtual platforms + * to override this method of boot environment processing: + */ +void __init e820__memory_setup(void) { char *who; + /* This is a firmware interface ABI - make sure we don't break it: */ + BUILD_BUG_ON(sizeof(struct boot_e820_entry) != 20); + who = x86_init.resources.memory_setup(); - memcpy(e820_saved, e820, sizeof(struct e820map)); - printk(KERN_INFO "e820: BIOS-provided physical RAM map:\n"); - e820_print_map(who); + + memcpy(e820_table_firmware, e820_table, sizeof(*e820_table_firmware)); + + pr_info("e820: BIOS-provided physical RAM map:\n"); + e820__print_table(who); } -void __init memblock_x86_fill(void) +void __init e820__memblock_setup(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 + * The bootstrap memblock region count maximum is 128 entries + * (INIT_MEMBLOCK_REGIONS), but EFI might pass us more E820 entries + * than that - so allow memblock resizing. + * + * This is safe, because this call happens pretty late during x86 setup, + * so we know about reserved memory regions already. (This is important + * so that memblock resizing does no stomp over reserved areas.) */ memblock_allow_resize(); - for (i = 0; i < e820->nr_map; i++) { - struct e820entry *ei = &e820->map[i]; + for (i = 0; i < e820_table->nr_entries; i++) { + struct e820_entry *entry = &e820_table->entries[i]; - end = ei->addr + ei->size; + end = entry->addr + entry->size; if (end != (resource_size_t)end) continue; - if (ei->type != E820_RAM && ei->type != E820_RESERVED_KERN) + if (entry->type != E820_TYPE_RAM && entry->type != E820_TYPE_RESERVED_KERN) continue; - memblock_add(ei->addr, ei->size); + memblock_add(entry->addr, entry->size); } - /* throw away partial pages */ + /* Throw away partial pages: */ memblock_trim_memory(PAGE_SIZE); memblock_dump_all(); } - -void __init memblock_find_dma_reserve(void) -{ -#ifdef CONFIG_X86_64 - u64 nr_pages = 0, nr_free_pages = 0; - unsigned long start_pfn, end_pfn; - phys_addr_t start, end; - int i; - u64 u; - - /* - * need to find out used area below MAX_DMA_PFN - * need to use memblock to get free size in [0, MAX_DMA_PFN] - * at first, and assume boot_mem will not take below MAX_DMA_PFN - */ - for_each_mem_pfn_range(i, MAX_NUMNODES, &start_pfn, &end_pfn, NULL) { - start_pfn = min(start_pfn, MAX_DMA_PFN); - end_pfn = min(end_pfn, MAX_DMA_PFN); - nr_pages += end_pfn - start_pfn; - } - - for_each_free_mem_range(u, NUMA_NO_NODE, MEMBLOCK_NONE, &start, &end, - NULL) { - start_pfn = min_t(unsigned long, PFN_UP(start), MAX_DMA_PFN); - end_pfn = min_t(unsigned long, PFN_DOWN(end), MAX_DMA_PFN); - if (start_pfn < end_pfn) - nr_free_pages += end_pfn - start_pfn; - } - - set_dma_reserve(nr_pages - nr_free_pages); -#endif -} diff --git a/arch/x86/kernel/early-quirks.c b/arch/x86/kernel/early-quirks.c index 6a08e25a48d8..ff7e4b3988ed 100644 --- a/arch/x86/kernel/early-quirks.c +++ b/arch/x86/kernel/early-quirks.c @@ -546,8 +546,8 @@ intel_graphics_stolen(int num, int slot, int func, &base, &end); /* Mark this space as reserved */ - e820_add_region(base, size, E820_RESERVED); - sanitize_e820_map(e820->map, ARRAY_SIZE(e820->map), &e820->nr_map); + e820__range_add(base, size, E820_TYPE_RESERVED); + e820__update_table(e820_table); } static void __init intel_graphics_quirks(int num, int slot, int func) diff --git a/arch/x86/kernel/head32.c b/arch/x86/kernel/head32.c index e5fb436a6548..538ec012b371 100644 --- a/arch/x86/kernel/head32.c +++ b/arch/x86/kernel/head32.c @@ -12,7 +12,7 @@ #include <asm/setup.h> #include <asm/sections.h> -#include <asm/e820.h> +#include <asm/e820/api.h> #include <asm/page.h> #include <asm/apic.h> #include <asm/io_apic.h> diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c index b5785c197e53..43b7002f44fb 100644 --- a/arch/x86/kernel/head64.c +++ b/arch/x86/kernel/head64.c @@ -24,7 +24,7 @@ #include <asm/tlbflush.h> #include <asm/sections.h> #include <asm/kdebug.h> -#include <asm/e820.h> +#include <asm/e820/api.h> #include <asm/bios_ebda.h> #include <asm/bootparam_utils.h> #include <asm/microcode.h> diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S index b467b14b03eb..ac9d327d2e42 100644 --- a/arch/x86/kernel/head_64.S +++ b/arch/x86/kernel/head_64.S @@ -269,10 +269,8 @@ ENTRY(secondary_startup_64) /* rsi is pointer to real mode structure with interesting info. pass it to C */ movq %rsi, %rdi - jmp start_cpu -ENDPROC(secondary_startup_64) -ENTRY(start_cpu) +.Ljump_to_C_code: /* * Jump to run C code and to be on a real kernel address. * Since we are running on identity-mapped space we have to jump @@ -305,7 +303,7 @@ ENTRY(start_cpu) pushq %rax # target address in negative space lretq .Lafter_lret: -ENDPROC(start_cpu) +ENDPROC(secondary_startup_64) #include "verify_cpu.S" @@ -313,11 +311,11 @@ ENDPROC(start_cpu) /* * Boot CPU0 entry point. It's called from play_dead(). Everything has been set * up already except stack. We just set up stack here. Then call - * start_secondary() via start_cpu(). + * start_secondary() via .Ljump_to_C_code. */ ENTRY(start_cpu0) movq initial_stack(%rip), %rsp - jmp start_cpu + jmp .Ljump_to_C_code ENDPROC(start_cpu0) #endif diff --git a/arch/x86/kernel/kexec-bzimage64.c b/arch/x86/kernel/kexec-bzimage64.c index d0a814a9d96a..9d7fd5e6689a 100644 --- a/arch/x86/kernel/kexec-bzimage64.c +++ b/arch/x86/kernel/kexec-bzimage64.c @@ -25,6 +25,7 @@ #include <asm/setup.h> #include <asm/crash.h> #include <asm/efi.h> +#include <asm/e820/api.h> #include <asm/kexec-bzimage64.h> #define MAX_ELFCOREHDR_STR_LEN 30 /* elfcorehdr=0x<64bit-value> */ @@ -99,15 +100,14 @@ static int setup_e820_entries(struct boot_params *params) { unsigned int nr_e820_entries; - nr_e820_entries = e820_saved->nr_map; + nr_e820_entries = e820_table_firmware->nr_entries; - /* TODO: Pass entries more than E820MAX in bootparams setup data */ - if (nr_e820_entries > E820MAX) - nr_e820_entries = E820MAX; + /* TODO: Pass entries more than E820_MAX_ENTRIES_ZEROPAGE in bootparams setup data */ + if (nr_e820_entries > E820_MAX_ENTRIES_ZEROPAGE) + nr_e820_entries = E820_MAX_ENTRIES_ZEROPAGE; params->e820_entries = nr_e820_entries; - memcpy(¶ms->e820_map, &e820_saved->map, - nr_e820_entries * sizeof(struct e820entry)); + memcpy(¶ms->e820_table, &e820_table_firmware->entries, nr_e820_entries*sizeof(struct e820_entry)); return 0; } @@ -232,10 +232,10 @@ setup_boot_parameters(struct kimage *image, struct boot_params *params, nr_e820_entries = params->e820_entries; for (i = 0; i < nr_e820_entries; i++) { - if (params->e820_map[i].type != E820_RAM) + if (params->e820_table[i].type != E820_TYPE_RAM) continue; - start = params->e820_map[i].addr; - end = params->e820_map[i].addr + params->e820_map[i].size - 1; + start = params->e820_table[i].addr; + end = params->e820_table[i].addr + params->e820_table[i].size - 1; if ((start <= 0x100000) && end > 0x100000) { mem_k = (end >> 10) - (0x100000 >> 10); diff --git a/arch/x86/kernel/mpparse.c b/arch/x86/kernel/mpparse.c index 0f8d20497383..0d904d759ff1 100644 --- a/arch/x86/kernel/mpparse.c +++ b/arch/x86/kernel/mpparse.c @@ -26,7 +26,7 @@ #include <asm/io_apic.h> #include <asm/proto.h> #include <asm/bios_ebda.h> -#include <asm/e820.h> +#include <asm/e820/api.h> #include <asm/setup.h> #include <asm/smp.h> @@ -826,10 +826,10 @@ static int __init parse_alloc_mptable_opt(char *p) } early_param("alloc_mptable", parse_alloc_mptable_opt); -void __init early_reserve_e820_mpc_new(void) +void __init e820__memblock_alloc_reserved_mpc_new(void) { if (enable_update_mptable && alloc_mptable) - mpc_new_phys = early_reserve_e820(mpc_new_length, 4); + mpc_new_phys = e820__memblock_alloc_reserved(mpc_new_length, 4); } static int __init update_mp_table(void) diff --git a/arch/x86/kernel/probe_roms.c b/arch/x86/kernel/probe_roms.c index d5f15c3f7b25..963e3fb56437 100644 --- a/arch/x86/kernel/probe_roms.c +++ b/arch/x86/kernel/probe_roms.c @@ -14,7 +14,7 @@ #include <asm/probe_roms.h> #include <asm/pci-direct.h> -#include <asm/e820.h> +#include <asm/e820/api.h> #include <asm/mmzone.h> #include <asm/setup.h> #include <asm/sections.h> diff --git a/arch/x86/kernel/resource.c b/arch/x86/kernel/resource.c index 2408c1603438..5ab3895516ac 100644 --- a/arch/x86/kernel/resource.c +++ b/arch/x86/kernel/resource.c @@ -1,5 +1,5 @@ #include <linux/ioport.h> -#include <asm/e820.h> +#include <asm/e820/api.h> static void resource_clip(struct resource *res, resource_size_t start, resource_size_t end) @@ -25,10 +25,10 @@ static void resource_clip(struct resource *res, resource_size_t start, static void remove_e820_regions(struct resource *avail) { int i; - struct e820entry *entry; + struct e820_entry *entry; - for (i = 0; i < e820->nr_map; i++) { - entry = &e820->map[i]; + for (i = 0; i < e820_table->nr_entries; i++) { + entry = &e820_table->entries[i]; resource_clip(avail, entry->addr, entry->addr + entry->size - 1); diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index 1302c47c5ce1..21a3db1b9fec 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -75,7 +75,7 @@ #include <asm/mtrr.h> #include <asm/apic.h> #include <asm/realmode.h> -#include <asm/e820.h> +#include <asm/e820/api.h> #include <asm/mpspec.h> #include <asm/setup.h> #include <asm/efi.h> @@ -119,7 +119,7 @@ * max_low_pfn_mapped: highest direct mapped pfn under 4GB * max_pfn_mapped: highest direct mapped pfn over 4GB * - * The direct mapping only covers E820_RAM regions, so the ranges and gaps are + * The direct mapping only covers E820_TYPE_RAM regions, so the ranges and gaps are * represented by pfn_mapped */ unsigned long max_low_pfn_mapped; @@ -423,7 +423,7 @@ static void __init parse_setup_data(void) switch (data_type) { case SETUP_E820_EXT: - parse_e820_ext(pa_data, data_len); + e820__memory_setup_extended(pa_data, data_len); break; case SETUP_DTB: add_dtb(pa_data); @@ -438,29 +438,6 @@ static void __init parse_setup_data(void) } } -static void __init e820_reserve_setup_data(void) -{ - struct setup_data *data; - u64 pa_data; - - pa_data = boot_params.hdr.setup_data; - if (!pa_data) - return; - - while (pa_data) { - data = early_memremap(pa_data, sizeof(*data)); - e820_update_range(pa_data, sizeof(*data)+data->len, - E820_RAM, E820_RESERVED_KERN); - pa_data = data->next; - early_memunmap(data, sizeof(*data)); - } - - sanitize_e820_map(e820->map, ARRAY_SIZE(e820->map), &e820->nr_map); - memcpy(e820_saved, e820, sizeof(struct e820map)); - printk(KERN_INFO "extended physical RAM map:\n"); - e820_print_map("reserve setup_data"); -} - static void __init memblock_x86_reserve_range_setup_data(void) { struct setup_data *data; @@ -753,16 +730,16 @@ static void __init trim_bios_range(void) * since some BIOSes are known to corrupt low memory. See the * Kconfig help text for X86_RESERVE_LOW. */ - e820_update_range(0, PAGE_SIZE, E820_RAM, E820_RESERVED); + e820__range_update(0, PAGE_SIZE, E820_TYPE_RAM, E820_TYPE_RESERVED); /* * special case: Some BIOSen report the PC BIOS * area (640->1Mb) as ram even though it is not. * take them out. */ - e820_remove_range(BIOS_BEGIN, BIOS_END - BIOS_BEGIN, E820_RAM, 1); + e820__range_remove(BIOS_BEGIN, BIOS_END - BIOS_BEGIN, E820_TYPE_RAM, 1); - sanitize_e820_map(e820->map, ARRAY_SIZE(e820->map), &e820->nr_map); + e820__update_table(e820_table); } /* called before trim_bios_range() to spare extra sanitize */ @@ -772,18 +749,18 @@ static void __init e820_add_kernel_range(void) u64 size = __pa_symbol(_end) - start; /* - * Complain if .text .data and .bss are not marked as E820_RAM and + * Complain if .text .data and .bss are not marked as E820_TYPE_RAM and * attempt to fix it by adding the range. We may have a confused BIOS, * or the user may have used memmap=exactmap or memmap=xxM$yyM to * exclude kernel range. If we really are running on top non-RAM, * we will crash later anyways. */ - if (e820_all_mapped(start, start + size, E820_RAM)) + if (e820__mapped_all(start, start + size, E820_TYPE_RAM)) return; - pr_warn(".text .data .bss are not marked as E820_RAM!\n"); - e820_remove_range(start, size, E820_RAM, 0); - e820_add_region(start, size, E820_RAM); + pr_warn(".text .data .bss are not marked as E820_TYPE_RAM!\n"); + e820__range_remove(start, size, E820_TYPE_RAM, 0); + e820__range_add(start, size, E820_TYPE_RAM); } static unsigned reserve_low = CONFIG_X86_RESERVE_LOW << 10; @@ -936,7 +913,7 @@ void __init setup_arch(char **cmdline_p) x86_init.oem.arch_setup(); iomem_resource.end = (1ULL << boot_cpu_data.x86_phys_bits) - 1; - setup_memory_map(); + e820__memory_setup(); parse_setup_data(); copy_edd(); @@ -1025,9 +1002,8 @@ void __init setup_arch(char **cmdline_p) early_dump_pci_devices(); #endif - /* update the e820_saved too */ - e820_reserve_setup_data(); - finish_e820_parsing(); + e820__reserve_setup_data(); + e820__finish_early_params(); if (efi_enabled(EFI_BOOT)) efi_init(); @@ -1053,11 +1029,11 @@ void __init setup_arch(char **cmdline_p) trim_bios_range(); #ifdef CONFIG_X86_32 if (ppro_with_ram_bug()) { - e820_update_range(0x70000000ULL, 0x40000ULL, E820_RAM, - E820_RESERVED); - sanitize_e820_map(e820->map, ARRAY_SIZE(e820->map), &e820->nr_map); + e820__range_update(0x70000000ULL, 0x40000ULL, E820_TYPE_RAM, + E820_TYPE_RESERVED); + e820__update_table(e820_table); printk(KERN_INFO "fixed physical RAM map:\n"); - e820_print_map("bad_ppro"); + e820__print_table("bad_ppro"); } #else early_gart_iommu_check(); @@ -1067,12 +1043,12 @@ void __init setup_arch(char **cmdline_p) * partially used pages are not usable - thus * we are rounding upwards: */ - max_pfn = e820_end_of_ram_pfn(); + max_pfn = e820__end_of_ram_pfn(); /* update e820 for memory not covered by WB MTRRs */ mtrr_bp_init(); if (mtrr_trim_uncached_memory(max_pfn)) - max_pfn = e820_end_of_ram_pfn(); + max_pfn = e820__end_of_ram_pfn(); max_possible_pfn = max_pfn; @@ -1091,7 +1067,7 @@ void __init setup_arch(char **cmdline_p) /* How many end-of-memory variables you have, grandma! */ /* need this before calling reserve_initrd */ if (max_pfn > (1UL<<(32 - PAGE_SHIFT))) - max_low_pfn = e820_end_of_low_ram_pfn(); + max_low_pfn = e820__end_of_low_ram_pfn(); else max_low_pfn = max_pfn; @@ -1108,7 +1084,7 @@ void __init setup_arch(char **cmdline_p) early_alloc_pgt_buf(); /* - * Need to conclude brk, before memblock_x86_fill() + * Need to conclude brk, before e820__memblock_setup() * it could use memblock_find_in_range, could overlap with * brk area. */ @@ -1117,7 +1093,7 @@ void __init setup_arch(char **cmdline_p) cleanup_highmap(); memblock_set_current_limit(ISA_END_ADDRESS); - memblock_x86_fill(); + e820__memblock_setup(); reserve_bios_regions(); @@ -1134,7 +1110,7 @@ void __init setup_arch(char **cmdline_p) } /* preallocate 4k for mptable mpc */ - early_reserve_e820_mpc_new(); + e820__memblock_alloc_reserved_mpc_new(); #ifdef CONFIG_X86_CHECK_BIOS_CORRUPTION setup_bios_corruption_check(); @@ -1257,12 +1233,12 @@ void __init setup_arch(char **cmdline_p) kvm_guest_init(); - e820_reserve_resources(); - e820_mark_nosave_regions(max_low_pfn); + e820__reserve_resources(); + e820__register_nosave_regions(max_low_pfn); x86_init.resources.reserve_resources(); - e820_setup_gap(); + e820__setup_pci_gap(); #ifdef CONFIG_VT #if defined(CONFIG_VGA_CONSOLE) diff --git a/arch/x86/kernel/tboot.c b/arch/x86/kernel/tboot.c index 5db0f33cbf2c..d4c8011a2293 100644 --- a/arch/x86/kernel/tboot.c +++ b/arch/x86/kernel/tboot.c @@ -42,7 +42,7 @@ #include <asm/fixmap.h> #include <asm/proto.h> #include <asm/setup.h> -#include <asm/e820.h> +#include <asm/e820/api.h> #include <asm/io.h> #include "../realmode/rm/wakeup.h" @@ -68,9 +68,9 @@ void __init tboot_probe(void) * also verify that it is mapped as we expect it before calling * set_fixmap(), to reduce chance of garbage value causing crash */ - if (!e820_any_mapped(boot_params.tboot_addr, - boot_params.tboot_addr, E820_RESERVED)) { - pr_warning("non-0 tboot_addr but it is not of type E820_RESERVED\n"); + if (!e820__mapped_any(boot_params.tboot_addr, + boot_params.tboot_addr, E820_TYPE_RESERVED)) { + pr_warning("non-0 tboot_addr but it is not of type E820_TYPE_RESERVED\n"); return; } @@ -192,12 +192,12 @@ static int tboot_setup_sleep(void) tboot->num_mac_regions = 0; - for (i = 0; i < e820->nr_map; i++) { - if ((e820->map[i].type != E820_RAM) - && (e820->map[i].type != E820_RESERVED_KERN)) + for (i = 0; i < e820_table->nr_entries; i++) { + if ((e820_table->entries[i].type != E820_TYPE_RAM) + && (e820_table->entries[i].type != E820_TYPE_RESERVED_KERN)) continue; - add_mac_region(e820->map[i].addr, e820->map[i].size); + add_mac_region(e820_table->entries[i].addr, e820_table->entries[i].size); } tboot->acpi_sinfo.kernel_s3_resume_vector = diff --git a/arch/x86/kernel/x86_init.c b/arch/x86/kernel/x86_init.c index 11a93f005268..a088b2c47f73 100644 --- a/arch/x86/kernel/x86_init.c +++ b/arch/x86/kernel/x86_init.c @@ -14,7 +14,7 @@ #include <asm/mpspec.h> #include <asm/setup.h> #include <asm/apic.h> -#include <asm/e820.h> +#include <asm/e820/api.h> #include <asm/time.h> #include <asm/irq.h> #include <asm/io_apic.h> @@ -38,7 +38,7 @@ struct x86_init_ops x86_init __initdata = { .resources = { .probe_roms = probe_roms, .reserve_resources = reserve_standard_io_resources, - .memory_setup = default_machine_specific_memory_setup, + .memory_setup = e820__memory_setup_default, }, .mpparse = { diff --git a/arch/x86/lguest/boot.c b/arch/x86/lguest/boot.c index d3289d7e78fa..7aa633686295 100644 --- a/arch/x86/lguest/boot.c +++ b/arch/x86/lguest/boot.c @@ -67,7 +67,7 @@ #include <asm/pgtable.h> #include <asm/desc.h> #include <asm/setup.h> -#include <asm/e820.h> +#include <asm/e820/api.h> #include <asm/mce.h> #include <asm/io.h> #include <asm/fpu/api.h> @@ -1178,9 +1178,9 @@ static __init char *lguest_memory_setup(void) * The Linux bootloader header contains an "e820" memory map: the * Launcher populated the first entry with our memory limit. */ - e820_add_region(boot_params.e820_map[0].addr, - boot_params.e820_map[0].size, - boot_params.e820_map[0].type); + e820__range_add(boot_params.e820_table[0].addr, + boot_params.e820_table[0].size, + boot_params.e820_table[0].type); /* This string is for the boot messages. */ return "LGUEST"; diff --git a/arch/x86/lib/kaslr.c b/arch/x86/lib/kaslr.c index 121f59c6ee54..5761a4f19455 100644 --- a/arch/x86/lib/kaslr.c +++ b/arch/x86/lib/kaslr.c @@ -8,7 +8,7 @@ #include <asm/kaslr.h> #include <asm/msr.h> #include <asm/archrandom.h> -#include <asm/e820.h> +#include <asm/e820/api.h> #include <asm/io.h> /* diff --git a/arch/x86/mm/amdtopology.c b/arch/x86/mm/amdtopology.c index d1c7de095808..91f501b2da3b 100644 --- a/arch/x86/mm/amdtopology.c +++ b/arch/x86/mm/amdtopology.c @@ -19,7 +19,7 @@ #include <asm/types.h> #include <asm/mmzone.h> #include <asm/proto.h> -#include <asm/e820.h> +#include <asm/e820/api.h> #include <asm/pci-direct.h> #include <asm/numa.h> #include <asm/mpspec.h> diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c index 22af912d66d2..2193799ca800 100644 --- a/arch/x86/mm/init.c +++ b/arch/x86/mm/init.c @@ -6,7 +6,7 @@ #include <linux/bootmem.h> /* for max_low_pfn */ #include <asm/cacheflush.h> -#include <asm/e820.h> +#include <asm/e820/api.h> #include <asm/init.h> #include <asm/page.h> #include <asm/page_types.h> @@ -373,14 +373,14 @@ static int __meminit split_mem_range(struct map_range *mr, int nr_range, return nr_range; } -struct range pfn_mapped[E820_X_MAX]; +struct range pfn_mapped[E820_MAX_ENTRIES]; int nr_pfn_mapped; static void add_pfn_range_mapped(unsigned long start_pfn, unsigned long end_pfn) { - nr_pfn_mapped = add_range_with_merge(pfn_mapped, E820_X_MAX, + nr_pfn_mapped = add_range_with_merge(pfn_mapped, E820_MAX_ENTRIES, nr_pfn_mapped, start_pfn, end_pfn); - nr_pfn_mapped = clean_sort_range(pfn_mapped, E820_X_MAX); + nr_pfn_mapped = clean_sort_range(pfn_mapped, E820_MAX_ENTRIES); max_pfn_mapped = max(max_pfn_mapped, end_pfn); @@ -430,7 +430,7 @@ unsigned long __ref init_memory_mapping(unsigned long start, /* * We need to iterate through the E820 memory map and create direct mappings - * for only E820_RAM and E820_KERN_RESERVED regions. We cannot simply + * for only E820_TYPE_RAM and E820_KERN_RESERVED regions. We cannot simply * create direct mappings for all pfns from [0 to max_low_pfn) and * [4GB to max_pfn) because of possible memory holes in high addresses * that cannot be marked as UC by fixed/variable range MTRRs. @@ -701,7 +701,7 @@ void free_init_pages(char *what, unsigned long begin, unsigned long end) void __ref free_initmem(void) { - e820_reallocate_tables(); + e820__reallocate_tables(); free_init_pages("unused kernel", (unsigned long)(&__init_begin), @@ -724,6 +724,53 @@ void __init free_initrd_mem(unsigned long start, unsigned long end) } #endif +/* + * Calculate the precise size of the DMA zone (first 16 MB of RAM), + * and pass it to the MM layer - to help it set zone watermarks more + * accurately. + * + * Done on 64-bit systems only for the time being, although 32-bit systems + * might benefit from this as well. + */ +void __init memblock_find_dma_reserve(void) +{ +#ifdef CONFIG_X86_64 + u64 nr_pages = 0, nr_free_pages = 0; + unsigned long start_pfn, end_pfn; + phys_addr_t start_addr, end_addr; + int i; + u64 u; + + /* + * Iterate over all memory ranges (free and reserved ones alike), + * to calculate the total number of pages in the first 16 MB of RAM: + */ + nr_pages = 0; + for_each_mem_pfn_range(i, MAX_NUMNODES, &start_pfn, &end_pfn, NULL) { + start_pfn = min(start_pfn, MAX_DMA_PFN); + end_pfn = min(end_pfn, MAX_DMA_PFN); + + nr_pages += end_pfn - start_pfn; + } + + /* + * Iterate over free memory ranges to calculate the number of free + * pages in the DMA zone, while not counting potential partial + * pages at the beginning or the end of the range: + */ + nr_free_pages = 0; + for_each_free_mem_range(u, NUMA_NO_NODE, MEMBLOCK_NONE, &start_addr, &end_addr, NULL) { + start_pfn = min_t(unsigned long, PFN_UP(start_addr), MAX_DMA_PFN); + end_pfn = min_t(unsigned long, PFN_DOWN(end_addr), MAX_DMA_PFN); + + if (start_pfn < end_pfn) + nr_free_pages += end_pfn - start_pfn; + } + + set_dma_reserve(nr_pages - nr_free_pages); +#endif +} + void __init zone_sizes_init(void) { unsigned long max_zone_pfns[MAX_NR_ZONES]; diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c index 601b8e04e5c6..f34d275ee201 100644 --- a/arch/x86/mm/init_32.c +++ b/arch/x86/mm/init_32.c @@ -38,7 +38,7 @@ #include <asm/pgtable.h> #include <asm/dma.h> #include <asm/fixmap.h> -#include <asm/e820.h> +#include <asm/e820/api.h> #include <asm/apic.h> #include <asm/bugs.h> #include <asm/tlb.h> diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index 7bdda6f1d135..a242139df8fe 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -41,7 +41,7 @@ #include <asm/pgalloc.h> #include <asm/dma.h> #include <asm/fixmap.h> -#include <asm/e820.h> +#include <asm/e820/api.h> #include <asm/apic.h> #include <asm/tlb.h> #include <asm/mmu_context.h> @@ -379,10 +379,10 @@ phys_pte_init(pte_t *pte_page, unsigned long paddr, unsigned long paddr_end, paddr_next = (paddr & PAGE_MASK) + PAGE_SIZE; if (paddr >= paddr_end) { if (!after_bootmem && - !e820_any_mapped(paddr & PAGE_MASK, paddr_next, - E820_RAM) && - !e820_any_mapped(paddr & PAGE_MASK, paddr_next, - E820_RESERVED_KERN)) + !e820__mapped_any(paddr & PAGE_MASK, paddr_next, + E820_TYPE_RAM) && + !e820__mapped_any(paddr & PAGE_MASK, paddr_next, + E820_TYPE_RESERVED_KERN)) set_pte(pte, __pte(0)); continue; } @@ -434,10 +434,10 @@ phys_pmd_init(pmd_t *pmd_page, unsigned long paddr, unsigned long paddr_end, paddr_next = (paddr & PMD_MASK) + PMD_SIZE; if (paddr >= paddr_end) { if (!after_bootmem && - !e820_any_mapped(paddr & PMD_MASK, paddr_next, - E820_RAM) && - !e820_any_mapped(paddr & PMD_MASK, paddr_next, - E820_RESERVED_KERN)) + !e820__mapped_any(paddr & PMD_MASK, paddr_next, + E820_TYPE_RAM) && + !e820__mapped_any(paddr & PMD_MASK, paddr_next, + E820_TYPE_RESERVED_KERN)) set_pmd(pmd, __pmd(0)); continue; } @@ -520,10 +520,10 @@ phys_pud_init(pud_t *pud_page, unsigned long paddr, unsigned long paddr_end, if (paddr >= paddr_end) { if (!after_bootmem && - !e820_any_mapped(paddr & PUD_MASK, paddr_next, - E820_RAM) && - !e820_any_mapped(paddr & PUD_MASK, paddr_next, - E820_RESERVED_KERN)) + !e820__mapped_any(paddr & PUD_MASK, paddr_next, + E820_TYPE_RAM) && + !e820__mapped_any(paddr & PUD_MASK, paddr_next, + E820_TYPE_RESERVED_KERN)) set_pud(pud, __pud(0)); continue; } diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c index a5e1cda85974..e4f7b25df18e 100644 --- a/arch/x86/mm/ioremap.c +++ b/arch/x86/mm/ioremap.c @@ -9,12 +9,13 @@ #include <linux/bootmem.h> #include <linux/init.h> #include <linux/io.h> +#include <linux/ioport.h> #include <linux/slab.h> #include <linux/vmalloc.h> #include <linux/mmiotrace.h> #include <asm/cacheflush.h> -#include <asm/e820.h> +#include <asm/e820/api.h> #include <asm/fixmap.h> #include <asm/pgtable.h> #include <asm/tlbflush.h> diff --git a/arch/x86/mm/kasan_init_64.c b/arch/x86/mm/kasan_init_64.c index 47efdcfe7113..0c7d8129bed6 100644 --- a/arch/x86/mm/kasan_init_64.c +++ b/arch/x86/mm/kasan_init_64.c @@ -8,11 +8,12 @@ #include <linux/sched/task.h> #include <linux/vmalloc.h> +#include <asm/e820/types.h> #include <asm/tlbflush.h> #include <asm/sections.h> extern pgd_t early_level4_pgt[PTRS_PER_PGD]; -extern struct range pfn_mapped[E820_X_MAX]; +extern struct range pfn_mapped[E820_MAX_ENTRIES]; static int __init map_range(struct range *range) { @@ -129,7 +130,7 @@ void __init kasan_init(void) kasan_populate_zero_shadow((void *)KASAN_SHADOW_START, kasan_mem_to_shadow((void *)PAGE_OFFSET)); - for (i = 0; i < E820_X_MAX; i++) { + for (i = 0; i < E820_MAX_ENTRIES; i++) { if (pfn_mapped[i].end == 0) break; diff --git a/arch/x86/mm/mmio-mod.c b/arch/x86/mm/mmio-mod.c index bef36622e408..4d434ddb75db 100644 --- a/arch/x86/mm/mmio-mod.c +++ b/arch/x86/mm/mmio-mod.c @@ -32,7 +32,7 @@ #include <linux/kallsyms.h> #include <asm/pgtable.h> #include <linux/mmiotrace.h> -#include <asm/e820.h> /* for ISA_START_ADDRESS */ +#include <asm/e820/api.h> /* for ISA_START_ADDRESS */ #include <linux/atomic.h> #include <linux/percpu.h> #include <linux/cpu.h> diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c index 93671d8b3b0d..25504d5aa816 100644 --- a/arch/x86/mm/numa.c +++ b/arch/x86/mm/numa.c @@ -12,7 +12,7 @@ #include <linux/sched.h> #include <linux/topology.h> -#include <asm/e820.h> +#include <asm/e820/api.h> #include <asm/proto.h> #include <asm/dma.h> #include <asm/amd_nb.h> diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c index b5949017dead..56b22fa504df 100644 --- a/arch/x86/mm/pageattr.c +++ b/arch/x86/mm/pageattr.c @@ -15,7 +15,7 @@ #include <linux/pci.h> #include <linux/vmalloc.h> -#include <asm/e820.h> +#include <asm/e820/api.h> #include <asm/processor.h> #include <asm/tlbflush.h> #include <asm/sections.h> diff --git a/arch/x86/mm/pat.c b/arch/x86/mm/pat.c index efc32bc6862b..9b78685b66e6 100644 --- a/arch/x86/mm/pat.c +++ b/arch/x86/mm/pat.c @@ -10,6 +10,7 @@ #include <linux/seq_file.h> #include <linux/bootmem.h> #include <linux/debugfs.h> +#include <linux/ioport.h> #include <linux/kernel.h> #include <linux/pfn_t.h> #include <linux/slab.h> @@ -23,7 +24,7 @@ #include <asm/x86_init.h> #include <asm/pgtable.h> #include <asm/fcntl.h> -#include <asm/e820.h> +#include <asm/e820/api.h> #include <asm/mtrr.h> #include <asm/page.h> #include <asm/msr.h> diff --git a/arch/x86/mm/pgtable_32.c b/arch/x86/mm/pgtable_32.c index 3d275a791c76..b9bd5b8b14fa 100644 --- a/arch/x86/mm/pgtable_32.c +++ b/arch/x86/mm/pgtable_32.c @@ -12,7 +12,7 @@ #include <asm/pgtable.h> #include <asm/pgalloc.h> #include <asm/fixmap.h> -#include <asm/e820.h> +#include <asm/e820/api.h> #include <asm/tlb.h> #include <asm/tlbflush.h> #include <asm/io.h> diff --git a/arch/x86/mm/srat.c b/arch/x86/mm/srat.c index 35fe69529bc1..3ea20d61b523 100644 --- a/arch/x86/mm/srat.c +++ b/arch/x86/mm/srat.c @@ -18,7 +18,7 @@ #include <linux/mm.h> #include <asm/proto.h> #include <asm/numa.h> -#include <asm/e820.h> +#include <asm/e820/api.h> #include <asm/apic.h> #include <asm/uv/uv.h> diff --git a/arch/x86/pci/i386.c b/arch/x86/pci/i386.c index 0a9f2caf358f..6fa84d531f4f 100644 --- a/arch/x86/pci/i386.c +++ b/arch/x86/pci/i386.c @@ -34,7 +34,7 @@ #include <linux/bootmem.h> #include <asm/pat.h> -#include <asm/e820.h> +#include <asm/e820/api.h> #include <asm/pci_x86.h> #include <asm/io_apic.h> @@ -398,7 +398,7 @@ void __init pcibios_resource_survey(void) list_for_each_entry(bus, &pci_root_buses, node) pcibios_allocate_resources(bus, 1); - e820_reserve_resources_late(); + e820__reserve_resources_late(); /* * Insert the IO APIC resources after PCI initialization has * occurred to handle IO APICS that are mapped in on a BAR in diff --git a/arch/x86/pci/mmconfig-shared.c b/arch/x86/pci/mmconfig-shared.c index dd30b7e08bc2..d1b47d5bc9c3 100644 --- a/arch/x86/pci/mmconfig-shared.c +++ b/arch/x86/pci/mmconfig-shared.c @@ -18,7 +18,7 @@ #include <linux/slab.h> #include <linux/mutex.h> #include <linux/rculist.h> -#include <asm/e820.h> +#include <asm/e820/api.h> #include <asm/pci_x86.h> #include <asm/acpi.h> @@ -423,7 +423,7 @@ static acpi_status find_mboard_resource(acpi_handle handle, u32 lvl, return AE_OK; } -static int is_acpi_reserved(u64 start, u64 end, unsigned not_used) +static bool is_acpi_reserved(u64 start, u64 end, unsigned not_used) { struct resource mcfg_res; @@ -440,11 +440,11 @@ static int is_acpi_reserved(u64 start, u64 end, unsigned not_used) return mcfg_res.flags; } -typedef int (*check_reserved_t)(u64 start, u64 end, unsigned type); +typedef bool (*check_reserved_t)(u64 start, u64 end, unsigned type); -static int __ref is_mmconf_reserved(check_reserved_t is_reserved, - struct pci_mmcfg_region *cfg, - struct device *dev, int with_e820) +static bool __ref is_mmconf_reserved(check_reserved_t is_reserved, + struct pci_mmcfg_region *cfg, + struct device *dev, int with_e820) { u64 addr = cfg->res.start; u64 size = resource_size(&cfg->res); @@ -452,7 +452,7 @@ static int __ref is_mmconf_reserved(check_reserved_t is_reserved, int num_buses; char *method = with_e820 ? "E820" : "ACPI motherboard resources"; - while (!is_reserved(addr, addr + size, E820_RESERVED)) { + while (!is_reserved(addr, addr + size, E820_TYPE_RESERVED)) { size >>= 1; if (size < (16UL<<20)) break; @@ -494,8 +494,8 @@ static int __ref is_mmconf_reserved(check_reserved_t is_reserved, return 1; } -static int __ref pci_mmcfg_check_reserved(struct device *dev, - struct pci_mmcfg_region *cfg, int early) +static bool __ref +pci_mmcfg_check_reserved(struct device *dev, struct pci_mmcfg_region *cfg, int early) { if (!early && !acpi_disabled) { if (is_mmconf_reserved(is_acpi_reserved, cfg, dev, 0)) @@ -514,7 +514,7 @@ static int __ref pci_mmcfg_check_reserved(struct device *dev, } /* - * e820_all_mapped() is marked as __init. + * e820__mapped_all() is marked as __init. * All entries from ACPI MCFG table have been checked at boot time. * For MCFG information constructed from hotpluggable host bridge's * _CBA method, just assume it's reserved. @@ -525,7 +525,7 @@ static int __ref pci_mmcfg_check_reserved(struct device *dev, /* Don't try to do this check unless configuration type 1 is available. how about type 2 ?*/ if (raw_pci_ops) - return is_mmconf_reserved(e820_all_mapped, cfg, dev, 1); + return is_mmconf_reserved(e820__mapped_all, cfg, dev, 1); return 0; } diff --git a/arch/x86/pci/mmconfig_32.c b/arch/x86/pci/mmconfig_32.c index 43984bc1665a..3e9e166f6408 100644 --- a/arch/x86/pci/mmconfig_32.c +++ b/arch/x86/pci/mmconfig_32.c @@ -12,7 +12,7 @@ #include <linux/pci.h> #include <linux/init.h> #include <linux/rcupdate.h> -#include <asm/e820.h> +#include <asm/e820/api.h> #include <asm/pci_x86.h> /* Assume systems with more busses have correct MCFG */ diff --git a/arch/x86/pci/mmconfig_64.c b/arch/x86/pci/mmconfig_64.c index bea52496aea6..f1c1aa0430ae 100644 --- a/arch/x86/pci/mmconfig_64.c +++ b/arch/x86/pci/mmconfig_64.c @@ -10,7 +10,7 @@ #include <linux/acpi.h> #include <linux/bitmap.h> #include <linux/rcupdate.h> -#include <asm/e820.h> +#include <asm/e820/api.h> #include <asm/pci_x86.h> #define PREFIX "PCI: " diff --git a/arch/x86/pci/pcbios.c b/arch/x86/pci/pcbios.c index 1d97cea3b3a4..29e9ba6ace9d 100644 --- a/arch/x86/pci/pcbios.c +++ b/arch/x86/pci/pcbios.c @@ -7,7 +7,9 @@ #include <linux/slab.h> #include <linux/module.h> #include <linux/uaccess.h> + #include <asm/pci_x86.h> +#include <asm/e820/types.h> #include <asm/pci-functions.h> #include <asm/cacheflush.h> diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c index 565dff3c9a12..a15cf815ac4e 100644 --- a/arch/x86/platform/efi/efi.c +++ b/arch/x86/platform/efi/efi.c @@ -47,6 +47,7 @@ #include <asm/setup.h> #include <asm/efi.h> +#include <asm/e820/api.h> #include <asm/time.h> #include <asm/cacheflush.h> #include <asm/tlbflush.h> @@ -139,21 +140,21 @@ static void __init do_add_efi_memmap(void) case EFI_BOOT_SERVICES_DATA: case EFI_CONVENTIONAL_MEMORY: if (md->attribute & EFI_MEMORY_WB) - e820_type = E820_RAM; + e820_type = E820_TYPE_RAM; else - e820_type = E820_RESERVED; + e820_type = E820_TYPE_RESERVED; break; case EFI_ACPI_RECLAIM_MEMORY: - e820_type = E820_ACPI; + e820_type = E820_TYPE_ACPI; break; case EFI_ACPI_MEMORY_NVS: - e820_type = E820_NVS; + e820_type = E820_TYPE_NVS; break; case EFI_UNUSABLE_MEMORY: - e820_type = E820_UNUSABLE; + e820_type = E820_TYPE_UNUSABLE; break; case EFI_PERSISTENT_MEMORY: - e820_type = E820_PMEM; + e820_type = E820_TYPE_PMEM; break; default: /* @@ -161,12 +162,12 @@ static void __init do_add_efi_memmap(void) * EFI_RUNTIME_SERVICES_DATA EFI_MEMORY_MAPPED_IO * EFI_MEMORY_MAPPED_IO_PORT_SPACE EFI_PAL_CODE */ - e820_type = E820_RESERVED; + e820_type = E820_TYPE_RESERVED; break; } - e820_add_region(start, size, e820_type); + e820__range_add(start, size, e820_type); } - sanitize_e820_map(e820->map, ARRAY_SIZE(e820->map), &e820->nr_map); + e820__update_table(e820_table); } int __init efi_memblock_x86_reserve_range(void) diff --git a/arch/x86/platform/efi/efi_64.c b/arch/x86/platform/efi/efi_64.c index eb64e5b33e37..6b6b8e8d4ae7 100644 --- a/arch/x86/platform/efi/efi_64.c +++ b/arch/x86/platform/efi/efi_64.c @@ -35,7 +35,7 @@ #include <asm/setup.h> #include <asm/page.h> -#include <asm/e820.h> +#include <asm/e820/api.h> #include <asm/pgtable.h> #include <asm/tlbflush.h> #include <asm/proto.h> diff --git a/arch/x86/platform/efi/quirks.c b/arch/x86/platform/efi/quirks.c index 30031d5293c4..3c8d8e511fd4 100644 --- a/arch/x86/platform/efi/quirks.c +++ b/arch/x86/platform/efi/quirks.c @@ -11,6 +11,8 @@ #include <linux/bootmem.h> #include <linux/acpi.h> #include <linux/dmi.h> + +#include <asm/e820/api.h> #include <asm/efi.h> #include <asm/uv/uv.h> @@ -240,14 +242,14 @@ void __init efi_arch_mem_reserve(phys_addr_t addr, u64 size) * else. We must only reserve (and then free) regions: * * - Not within any part of the kernel - * - Not the BIOS reserved area (E820_RESERVED, E820_NVS, etc) + * - Not the BIOS reserved area (E820_TYPE_RESERVED, E820_TYPE_NVS, etc) */ static bool can_free_region(u64 start, u64 size) { if (start + size > __pa_symbol(_text) && start <= __pa_symbol(_end)) return false; - if (!e820_all_mapped(start, start+size, E820_RAM)) + if (!e820__mapped_all(start, start+size, E820_TYPE_RAM)) return false; return true; @@ -280,7 +282,7 @@ void __init efi_reserve_boot_services(void) * A good example of a critical region that must not be * freed is page zero (first 4Kb of memory), which may * contain boot services code/data but is marked - * E820_RESERVED by trim_bios_range(). + * E820_TYPE_RESERVED by trim_bios_range(). */ if (!already_reserved) { memblock_reserve(start, size); diff --git a/arch/x86/power/hibernate_64.c b/arch/x86/power/hibernate_64.c index 2a9f993bbbf0..6a61194ffd58 100644 --- a/arch/x86/power/hibernate_64.c +++ b/arch/x86/power/hibernate_64.c @@ -16,6 +16,7 @@ #include <crypto/hash.h> +#include <asm/e820/api.h> #include <asm/init.h> #include <asm/proto.h> #include <asm/page.h> @@ -214,12 +215,12 @@ struct restore_data_record { #if IS_BUILTIN(CONFIG_CRYPTO_MD5) /** - * get_e820_md5 - calculate md5 according to given e820 map + * get_e820_md5 - calculate md5 according to given e820 table * - * @map: the e820 map to be calculated + * @table: the e820 table to be calculated * @buf: the md5 result to be stored to */ -static int get_e820_md5(struct e820map *map, void *buf) +static int get_e820_md5(struct e820_table *table, void *buf) { struct scatterlist sg; struct crypto_ahash *tfm; @@ -232,10 +233,9 @@ static int get_e820_md5(struct e820map *map, void *buf) { AHASH_REQUEST_ON_STACK(req, tfm); - size = offsetof(struct e820map, map) - + sizeof(struct e820entry) * map->nr_map; + size = offsetof(struct e820_table, entries) + sizeof(struct e820_entry) * table->nr_entries; ahash_request_set_tfm(req, tfm); - sg_init_one(&sg, (u8 *)map, size); + sg_init_one(&sg, (u8 *)table, size); ahash_request_set_callback(req, 0, NULL, NULL); ahash_request_set_crypt(req, &sg, buf, size); @@ -250,7 +250,7 @@ static int get_e820_md5(struct e820map *map, void *buf) static void hibernation_e820_save(void *buf) { - get_e820_md5(e820_saved, buf); + get_e820_md5(e820_table_firmware, buf); } static bool hibernation_e820_mismatch(void *buf) @@ -263,7 +263,7 @@ static bool hibernation_e820_mismatch(void *buf) if (!memcmp(result, buf, MD5_DIGEST_SIZE)) return false; - ret = get_e820_md5(e820_saved, result); + ret = get_e820_md5(e820_table_firmware, result); if (ret) return true; diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c index 6efa0cc425a2..30822e8e64ac 100644 --- a/arch/x86/xen/enlighten.c +++ b/arch/x86/xen/enlighten.c @@ -76,6 +76,7 @@ #include <asm/mwait.h> #include <asm/pci_x86.h> #include <asm/cpu.h> +#include <asm/e820/api.h> #ifdef CONFIG_ACPI #include <linux/acpi.h> @@ -1689,34 +1690,32 @@ static void __init init_pvh_bootparams(void) memset(&pvh_bootparams, 0, sizeof(pvh_bootparams)); - memmap.nr_entries = ARRAY_SIZE(pvh_bootparams.e820_map); - set_xen_guest_handle(memmap.buffer, pvh_bootparams.e820_map); + memmap.nr_entries = ARRAY_SIZE(pvh_bootparams.e820_table); + set_xen_guest_handle(memmap.buffer, pvh_bootparams.e820_table); rc = HYPERVISOR_memory_op(XENMEM_memory_map, &memmap); if (rc) { xen_raw_printk("XENMEM_memory_map failed (%d)\n", rc); BUG(); } - if (memmap.nr_entries < E820MAX - 1) { - pvh_bootparams.e820_map[memmap.nr_entries].addr = + if (memmap.nr_entries < E820_MAX_ENTRIES_ZEROPAGE - 1) { + pvh_bootparams.e820_table[memmap.nr_entries].addr = ISA_START_ADDRESS; - pvh_bootparams.e820_map[memmap.nr_entries].size = + pvh_bootparams.e820_table[memmap.nr_entries].size = ISA_END_ADDRESS - ISA_START_ADDRESS; - pvh_bootparams.e820_map[memmap.nr_entries].type = - E820_RESERVED; + pvh_bootparams.e820_table[memmap.nr_entries].type = + E820_TYPE_RESERVED; memmap.nr_entries++; } else xen_raw_printk("Warning: Can fit ISA range into e820\n"); - sanitize_e820_map(pvh_bootparams.e820_map, - ARRAY_SIZE(pvh_bootparams.e820_map), - &memmap.nr_entries); - pvh_bootparams.e820_entries = memmap.nr_entries; for (i = 0; i < pvh_bootparams.e820_entries; i++) - e820_add_region(pvh_bootparams.e820_map[i].addr, - pvh_bootparams.e820_map[i].size, - pvh_bootparams.e820_map[i].type); + e820__range_add(pvh_bootparams.e820_table[i].addr, + pvh_bootparams.e820_table[i].size, + pvh_bootparams.e820_table[i].type); + + e820__update_table(e820_table); pvh_bootparams.hdr.cmd_line_ptr = pvh_start_info.cmdline_paddr; diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c index 4d4b7bc48f5d..f226038a39ca 100644 --- a/arch/x86/xen/mmu.c +++ b/arch/x86/xen/mmu.c @@ -58,7 +58,7 @@ #include <asm/mmu_context.h> #include <asm/setup.h> #include <asm/paravirt.h> -#include <asm/e820.h> +#include <asm/e820/api.h> #include <asm/linkage.h> #include <asm/page.h> #include <asm/init.h> diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c index a8c306cf8868..a5bf7c451435 100644 --- a/arch/x86/xen/setup.c +++ b/arch/x86/xen/setup.c @@ -14,7 +14,7 @@ #include <asm/elf.h> #include <asm/vdso.h> -#include <asm/e820.h> +#include <asm/e820/api.h> #include <asm/setup.h> #include <asm/acpi.h> #include <asm/numa.h> @@ -41,8 +41,7 @@ struct xen_memory_region xen_extra_mem[XEN_EXTRA_MEM_MAX_REGIONS] __initdata; unsigned long xen_released_pages; /* E820 map used during setting up memory. */ -static struct e820entry xen_e820_map[E820_X_MAX] __initdata; -static u32 xen_e820_map_entries __initdata; +static struct e820_table xen_e820_table __initdata; /* * Buffer used to remap identity mapped pages. We only need the virtual space. @@ -198,15 +197,15 @@ void __init xen_inv_extra_mem(void) */ static unsigned long __init xen_find_pfn_range(unsigned long *min_pfn) { - const struct e820entry *entry = xen_e820_map; + const struct e820_entry *entry = xen_e820_table.entries; unsigned int i; unsigned long done = 0; - for (i = 0; i < xen_e820_map_entries; i++, entry++) { + for (i = 0; i < xen_e820_table.nr_entries; i++, entry++) { unsigned long s_pfn; unsigned long e_pfn; - if (entry->type != E820_RAM) + if (entry->type != E820_TYPE_RAM) continue; e_pfn = PFN_DOWN(entry->addr + entry->size); @@ -457,7 +456,7 @@ static unsigned long __init xen_foreach_remap_area(unsigned long nr_pages, { phys_addr_t start = 0; unsigned long ret_val = 0; - const struct e820entry *entry = xen_e820_map; + const struct e820_entry *entry = xen_e820_table.entries; int i; /* @@ -471,13 +470,13 @@ static unsigned long __init xen_foreach_remap_area(unsigned long nr_pages, * example) the DMI tables in a reserved region that begins on * a non-page boundary. */ - for (i = 0; i < xen_e820_map_entries; i++, entry++) { + for (i = 0; i < xen_e820_table.nr_entries; i++, entry++) { phys_addr_t end = entry->addr + entry->size; - if (entry->type == E820_RAM || i == xen_e820_map_entries - 1) { + if (entry->type == E820_TYPE_RAM || i == xen_e820_table.nr_entries - 1) { unsigned long start_pfn = PFN_DOWN(start); unsigned long end_pfn = PFN_UP(end); - if (entry->type == E820_RAM) + if (entry->type == E820_TYPE_RAM) end_pfn = PFN_UP(entry->addr); if (start_pfn < end_pfn) @@ -591,28 +590,28 @@ static void __init xen_align_and_add_e820_region(phys_addr_t start, phys_addr_t end = start + size; /* Align RAM regions to page boundaries. */ - if (type == E820_RAM) { + if (type == E820_TYPE_RAM) { start = PAGE_ALIGN(start); end &= ~((phys_addr_t)PAGE_SIZE - 1); } - e820_add_region(start, end - start, type); + e820__range_add(start, end - start, type); } static void __init xen_ignore_unusable(void) { - struct e820entry *entry = xen_e820_map; + struct e820_entry *entry = xen_e820_table.entries; unsigned int i; - for (i = 0; i < xen_e820_map_entries; i++, entry++) { - if (entry->type == E820_UNUSABLE) - entry->type = E820_RAM; + for (i = 0; i < xen_e820_table.nr_entries; i++, entry++) { + if (entry->type == E820_TYPE_UNUSABLE) + entry->type = E820_TYPE_RAM; } } bool __init xen_is_e820_reserved(phys_addr_t start, phys_addr_t size) { - struct e820entry *entry; + struct e820_entry *entry; unsigned mapcnt; phys_addr_t end; @@ -620,10 +619,10 @@ bool __init xen_is_e820_reserved(phys_addr_t start, phys_addr_t size) return false; end = start + size; - entry = xen_e820_map; + entry = xen_e820_table.entries; - for (mapcnt = 0; mapcnt < xen_e820_map_entries; mapcnt++) { - if (entry->type == E820_RAM && entry->addr <= start && + for (mapcnt = 0; mapcnt < xen_e820_table.nr_entries; mapcnt++) { + if (entry->type == E820_TYPE_RAM && entry->addr <= start && (entry->addr + entry->size) >= end) return false; @@ -645,10 +644,10 @@ phys_addr_t __init xen_find_free_area(phys_addr_t size) { unsigned mapcnt; phys_addr_t addr, start; - struct e820entry *entry = xen_e820_map; + struct e820_entry *entry = xen_e820_table.entries; - for (mapcnt = 0; mapcnt < xen_e820_map_entries; mapcnt++, entry++) { - if (entry->type != E820_RAM || entry->size < size) + for (mapcnt = 0; mapcnt < xen_e820_table.nr_entries; mapcnt++, entry++) { + if (entry->type != E820_TYPE_RAM || entry->size < size) continue; start = entry->addr; for (addr = start; addr < start + size; addr += PAGE_SIZE) { @@ -750,8 +749,8 @@ char * __init xen_memory_setup(void) max_pfn = min(max_pfn, xen_start_info->nr_pages); mem_end = PFN_PHYS(max_pfn); - memmap.nr_entries = ARRAY_SIZE(xen_e820_map); - set_xen_guest_handle(memmap.buffer, xen_e820_map); + memmap.nr_entries = ARRAY_SIZE(xen_e820_table.entries); + set_xen_guest_handle(memmap.buffer, xen_e820_table.entries); op = xen_initial_domain() ? XENMEM_machine_memory_map : @@ -760,16 +759,16 @@ char * __init xen_memory_setup(void) if (rc == -ENOSYS) { BUG_ON(xen_initial_domain()); memmap.nr_entries = 1; - xen_e820_map[0].addr = 0ULL; - xen_e820_map[0].size = mem_end; + xen_e820_table.entries[0].addr = 0ULL; + xen_e820_table.entries[0].size = mem_end; /* 8MB slack (to balance backend allocations). */ - xen_e820_map[0].size += 8ULL << 20; - xen_e820_map[0].type = E820_RAM; + xen_e820_table.entries[0].size += 8ULL << 20; + xen_e820_table.entries[0].type = E820_TYPE_RAM; rc = 0; } BUG_ON(rc); BUG_ON(memmap.nr_entries == 0); - xen_e820_map_entries = memmap.nr_entries; + xen_e820_table.nr_entries = memmap.nr_entries; /* * Xen won't allow a 1:1 mapping to be created to UNUSABLE @@ -783,8 +782,7 @@ char * __init xen_memory_setup(void) xen_ignore_unusable(); /* Make sure the Xen-supplied memory map is well-ordered. */ - sanitize_e820_map(xen_e820_map, ARRAY_SIZE(xen_e820_map), - &xen_e820_map_entries); + e820__update_table(&xen_e820_table); max_pages = xen_get_max_pages(); @@ -811,15 +809,15 @@ char * __init xen_memory_setup(void) extra_pages = min3(EXTRA_MEM_RATIO * min(max_pfn, PFN_DOWN(MAXMEM)), extra_pages, max_pages - max_pfn); i = 0; - addr = xen_e820_map[0].addr; - size = xen_e820_map[0].size; - while (i < xen_e820_map_entries) { + addr = xen_e820_table.entries[0].addr; + size = xen_e820_table.entries[0].size; + while (i < xen_e820_table.nr_entries) { bool discard = false; chunk_size = size; - type = xen_e820_map[i].type; + type = xen_e820_table.entries[i].type; - if (type == E820_RAM) { + if (type == E820_TYPE_RAM) { if (addr < mem_end) { chunk_size = min(size, mem_end - addr); } else if (extra_pages) { @@ -840,9 +838,9 @@ char * __init xen_memory_setup(void) size -= chunk_size; if (size == 0) { i++; - if (i < xen_e820_map_entries) { - addr = xen_e820_map[i].addr; - size = xen_e820_map[i].size; + if (i < xen_e820_table.nr_entries) { + addr = xen_e820_table.entries[i].addr; + size = xen_e820_table.entries[i].size; } } } @@ -858,10 +856,9 @@ char * __init xen_memory_setup(void) * reserve ISA memory anyway because too many things poke * about in there. */ - e820_add_region(ISA_START_ADDRESS, ISA_END_ADDRESS - ISA_START_ADDRESS, - E820_RESERVED); + e820__range_add(ISA_START_ADDRESS, ISA_END_ADDRESS - ISA_START_ADDRESS, E820_TYPE_RESERVED); - sanitize_e820_map(e820->map, ARRAY_SIZE(e820->map), &e820->nr_map); + e820__update_table(e820_table); /* * Check whether the kernel itself conflicts with the target E820 map. @@ -915,6 +912,37 @@ char * __init xen_memory_setup(void) } /* + * Machine specific memory setup for auto-translated guests. + */ +char * __init xen_auto_xlated_memory_setup(void) +{ + struct xen_memory_map memmap; + int i; + int rc; + + memmap.nr_entries = ARRAY_SIZE(xen_e820_table.entries); + set_xen_guest_handle(memmap.buffer, xen_e820_table.entries); + + rc = HYPERVISOR_memory_op(XENMEM_memory_map, &memmap); + if (rc < 0) + panic("No memory map (%d)\n", rc); + + xen_e820_table.nr_entries = memmap.nr_entries; + + e820__update_table(&xen_e820_table); + + for (i = 0; i < xen_e820_table.nr_entries; i++) + e820__range_add(xen_e820_table.entries[i].addr, xen_e820_table.entries[i].size, xen_e820_table.entries[i].type); + + /* Remove p2m info, it is not needed. */ + xen_start_info->mfn_list = 0; + xen_start_info->first_p2m_pfn = 0; + xen_start_info->nr_p2m_frames = 0; + + return "Xen"; +} + +/* * Set the bit indicating "nosegneg" library variants should be used. * We only need to bother in pure 32-bit mode; compat 32-bit processes * can have un-truncated segments, so wrapping around is allowed. @@ -999,8 +1027,8 @@ void __init xen_pvmmu_arch_setup(void) void __init xen_arch_setup(void) { xen_panic_handler_init(); - - xen_pvmmu_arch_setup(); + if (!xen_feature(XENFEAT_auto_translated_physmap)) + xen_pvmmu_arch_setup(); #ifdef CONFIG_ACPI if (!(xen_start_info->flags & SIF_INITDOMAIN)) { |