diff options
Diffstat (limited to 'arch/x86_64')
| -rw-r--r-- | arch/x86_64/Kconfig | 5 | ||||
| -rw-r--r-- | arch/x86_64/ia32/ia32entry.S | 1 | ||||
| -rw-r--r-- | arch/x86_64/kernel/acpi/sleep.c | 7 | ||||
| -rw-r--r-- | arch/x86_64/kernel/apic.c | 2 | ||||
| -rw-r--r-- | arch/x86_64/kernel/i387.c | 2 | ||||
| -rw-r--r-- | arch/x86_64/kernel/setup.c | 95 | ||||
| -rw-r--r-- | arch/x86_64/mm/srat.c | 33 | ||||
| -rw-r--r-- | arch/x86_64/pci/mmconfig.c | 13 |
8 files changed, 115 insertions, 43 deletions
diff --git a/arch/x86_64/Kconfig b/arch/x86_64/Kconfig index 6527a368fb9..af44130f0d6 100644 --- a/arch/x86_64/Kconfig +++ b/arch/x86_64/Kconfig @@ -390,6 +390,7 @@ config GART_IOMMU bool "K8 GART IOMMU support" default y select SWIOTLB + select AGP depends on PCI help Support for hardware IOMMU in AMD's Opteron/Athlon64 Processors @@ -402,11 +403,9 @@ config GART_IOMMU northbridge and a software emulation used on other systems without hardware IOMMU. If unsure, say Y. -# need this always enabled with GART_IOMMU for the VIA workaround +# need this always selected by GART_IOMMU for the VIA workaround config SWIOTLB bool - default y - depends on GART_IOMMU config X86_MCE bool "Machine check support" if EMBEDDED diff --git a/arch/x86_64/ia32/ia32entry.S b/arch/x86_64/ia32/ia32entry.S index 5a92fed2d1d..4ec594ab1a9 100644 --- a/arch/x86_64/ia32/ia32entry.S +++ b/arch/x86_64/ia32/ia32entry.S @@ -696,4 +696,5 @@ ia32_sys_call_table: .quad sys_sync_file_range .quad sys_tee .quad compat_sys_vmsplice + .quad compat_sys_move_pages ia32_syscall_end: diff --git a/arch/x86_64/kernel/acpi/sleep.c b/arch/x86_64/kernel/acpi/sleep.c index 867a0ebee17..091bc79c888 100644 --- a/arch/x86_64/kernel/acpi/sleep.c +++ b/arch/x86_64/kernel/acpi/sleep.c @@ -35,6 +35,8 @@ #include <linux/pci.h> #include <linux/bootmem.h> #include <linux/acpi.h> +#include <linux/cpumask.h> + #include <asm/mpspec.h> #include <asm/io.h> #include <asm/apic.h> @@ -66,7 +68,8 @@ static void init_low_mapping(void) pgd_t *slot0 = pgd_offset(current->mm, 0UL); low_ptr = *slot0; set_pgd(slot0, *pgd_offset(current->mm, PAGE_OFFSET)); - flush_tlb_all(); + WARN_ON(num_online_cpus() != 1); + local_flush_tlb(); } /** @@ -92,7 +95,7 @@ int acpi_save_state_mem(void) void acpi_restore_state_mem(void) { set_pgd(pgd_offset(current->mm, 0UL), low_ptr); - flush_tlb_all(); + local_flush_tlb(); } /** diff --git a/arch/x86_64/kernel/apic.c b/arch/x86_64/kernel/apic.c index 100a30c4004..29ef99001e0 100644 --- a/arch/x86_64/kernel/apic.c +++ b/arch/x86_64/kernel/apic.c @@ -51,7 +51,7 @@ int disable_apic_timer __initdata; static cpumask_t timer_interrupt_broadcast_ipi_mask; /* Using APIC to generate smp_local_timer_interrupt? */ -int using_apic_timer = 0; +int using_apic_timer __read_mostly = 0; static void apic_pm_activate(void); diff --git a/arch/x86_64/kernel/i387.c b/arch/x86_64/kernel/i387.c index a5d7e16b928..44ddb1ec808 100644 --- a/arch/x86_64/kernel/i387.c +++ b/arch/x86_64/kernel/i387.c @@ -24,7 +24,7 @@ #include <asm/ptrace.h> #include <asm/uaccess.h> -unsigned int mxcsr_feature_mask = 0xffffffff; +unsigned int mxcsr_feature_mask __read_mostly = 0xffffffff; void mxcsr_feature_mask_init(void) { diff --git a/arch/x86_64/kernel/setup.c b/arch/x86_64/kernel/setup.c index 655b9192eeb..b8d5116d737 100644 --- a/arch/x86_64/kernel/setup.c +++ b/arch/x86_64/kernel/setup.c @@ -47,6 +47,7 @@ #include <linux/dmi.h> #include <linux/dma-mapping.h> #include <linux/ctype.h> +#include <linux/suspend.h> #include <asm/mtrr.h> #include <asm/uaccess.h> @@ -595,6 +596,100 @@ static void discover_ebda(void) ebda_size = 64*1024; } +#ifdef CONFIG_SOFTWARE_SUSPEND +static void __init mark_nosave_page_range(unsigned long start, unsigned long end) +{ + struct page *page; + while (start <= end) { + page = pfn_to_page(start); + SetPageNosave(page); + start++; + } +} + +static void __init e820_nosave_reserved_pages(void) +{ + int i; + unsigned long r_start = 0, r_end = 0; + + /* Assume e820 map is sorted */ + for (i = 0; i < e820.nr_map; i++) { + struct e820entry *ei = &e820.map[i]; + unsigned long start, end; + + start = round_down(ei->addr, PAGE_SIZE); + end = round_up(ei->addr + ei->size, PAGE_SIZE); + if (start >= end) + continue; + if (ei->type == E820_RESERVED) + continue; + r_end = start>>PAGE_SHIFT; + /* swsusp ignores invalid pfn, ignore these pages here */ + if (r_end > end_pfn) + r_end = end_pfn; + if (r_end > r_start) + mark_nosave_page_range(r_start, r_end-1); + if (r_end >= end_pfn) + break; + r_start = end>>PAGE_SHIFT; + } +} + +static void __init e820_save_acpi_pages(void) +{ + int i; + + /* Assume e820 map is sorted */ + for (i = 0; i < e820.nr_map; i++) { + struct e820entry *ei = &e820.map[i]; + unsigned long start, end; + + start = ei->addr, PAGE_SIZE; + end = ei->addr + ei->size; + if (start >= end) + continue; + if (ei->type != E820_ACPI && ei->type != E820_NVS) + continue; + /* + * If the region is below end_pfn, it will be + * saved/restored by swsusp follow 'RAM' type. + */ + if (start < (end_pfn << PAGE_SHIFT)) + start = end_pfn << PAGE_SHIFT; + if (end > start) + swsusp_add_arch_pages(start, end); + } +} + +extern char __start_rodata, __end_rodata; +/* + * BIOS reserved region/hole - no save/restore + * ACPI NVS - save/restore + * ACPI Data - this is a little tricky, the mem could be used by OS after OS + * reads tables from the region, but anyway save/restore the memory hasn't any + * side effect and Linux runtime module load/unload might use it. + * kernel rodata - no save/restore (kernel rodata isn't changed) + */ +static int __init mark_nosave_pages(void) +{ + unsigned long pfn_start, pfn_end; + + /* BIOS reserved regions & holes */ + e820_nosave_reserved_pages(); + + /* kernel rodata */ + pfn_start = round_up(__pa_symbol(&__start_rodata), PAGE_SIZE) >> PAGE_SHIFT; + pfn_end = round_down(__pa_symbol(&__end_rodata), PAGE_SIZE) >> PAGE_SHIFT; + mark_nosave_page_range(pfn_start, pfn_end-1); + + /* record ACPI Data/NVS as saveable */ + e820_save_acpi_pages(); + + return 0; +} +core_initcall(mark_nosave_pages); +#endif + void __init setup_arch(char **cmdline_p) { unsigned long kernel_end; diff --git a/arch/x86_64/mm/srat.c b/arch/x86_64/mm/srat.c index 474df22c6ed..502fce65e96 100644 --- a/arch/x86_64/mm/srat.c +++ b/arch/x86_64/mm/srat.c @@ -30,7 +30,6 @@ static struct acpi_table_slit *acpi_slit; static nodemask_t nodes_parsed __initdata; -static nodemask_t nodes_found __initdata; static struct bootnode nodes[MAX_NUMNODES] __initdata; static struct bootnode nodes_add[MAX_NUMNODES] __initdata; static int found_add_area __initdata; @@ -38,33 +37,14 @@ int hotadd_percent __initdata = 0; #ifndef RESERVE_HOTADD #define hotadd_percent 0 /* Ignore all settings */ #endif -static u8 pxm2node[256] = { [0 ... 255] = 0xff }; /* Too small nodes confuse the VM badly. Usually they result from BIOS bugs. */ #define NODE_MIN_SIZE (4*1024*1024) -static int node_to_pxm(int n); - -int pxm_to_node(int pxm) -{ - if ((unsigned)pxm >= 256) - return -1; - /* Extend 0xff to (int)-1 */ - return (signed char)pxm2node[pxm]; -} - static __init int setup_node(int pxm) { - unsigned node = pxm2node[pxm]; - if (node == 0xff) { - if (nodes_weight(nodes_found) >= MAX_NUMNODES) - return -1; - node = first_unset_node(nodes_found); - node_set(node, nodes_found); - pxm2node[pxm] = node; - } - return pxm2node[pxm]; + return acpi_map_pxm_to_node(pxm); } static __init int conflicting_nodes(unsigned long start, unsigned long end) @@ -440,17 +420,6 @@ int __init acpi_scan_nodes(unsigned long start, unsigned long end) return 0; } -static int node_to_pxm(int n) -{ - int i; - if (pxm2node[n] == n) - return n; - for (i = 0; i < 256; i++) - if (pxm2node[i] == n) - return i; - return 0; -} - void __init srat_reserve_add_area(int nodeid) { if (found_add_area && nodes_add[nodeid].end) { diff --git a/arch/x86_64/pci/mmconfig.c b/arch/x86_64/pci/mmconfig.c index a2060e4d5de..3c55c76c6fd 100644 --- a/arch/x86_64/pci/mmconfig.c +++ b/arch/x86_64/pci/mmconfig.c @@ -13,7 +13,10 @@ #include "pci.h" -#define MMCONFIG_APER_SIZE (256*1024*1024) +/* aperture is up to 256MB but BIOS may reserve less */ +#define MMCONFIG_APER_MIN (2 * 1024*1024) +#define MMCONFIG_APER_MAX (256 * 1024*1024) + /* Verify the first 16 busses. We assume that systems with more busses get MCFG right. */ #define MAX_CHECK_BUS 16 @@ -175,9 +178,10 @@ void __init pci_mmcfg_init(void) return; if (!e820_all_mapped(pci_mmcfg_config[0].base_address, - pci_mmcfg_config[0].base_address + MMCONFIG_APER_SIZE, + pci_mmcfg_config[0].base_address + MMCONFIG_APER_MIN, E820_RESERVED)) { - printk(KERN_ERR "PCI: BIOS Bug: MCFG area is not E820-reserved\n"); + printk(KERN_ERR "PCI: BIOS Bug: MCFG area at %x is not E820-reserved\n", + pci_mmcfg_config[0].base_address); printk(KERN_ERR "PCI: Not using MMCONFIG.\n"); return; } @@ -190,7 +194,8 @@ void __init pci_mmcfg_init(void) } for (i = 0; i < pci_mmcfg_config_num; ++i) { pci_mmcfg_virt[i].cfg = &pci_mmcfg_config[i]; - pci_mmcfg_virt[i].virt = ioremap_nocache(pci_mmcfg_config[i].base_address, MMCONFIG_APER_SIZE); + pci_mmcfg_virt[i].virt = ioremap_nocache(pci_mmcfg_config[i].base_address, + MMCONFIG_APER_MAX); if (!pci_mmcfg_virt[i].virt) { printk("PCI: Cannot map mmconfig aperture for segment %d\n", pci_mmcfg_config[i].pci_segment_group_number); |