diff options
Diffstat (limited to 'arch/x86')
59 files changed, 576 insertions, 351 deletions
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index ac2fb0641a0..68d91c8233f 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -951,9 +951,9 @@ config NUMA local memory controller of the CPU and add some more NUMA awareness to the kernel. - For i386 this is currently highly experimental and should be only + For 32-bit this is currently highly experimental and should be only used for kernel development. It might also cause boot failures. - For x86_64 this is recommended on all multiprocessor Opteron systems. + For 64-bit this is recommended on all multiprocessor Opteron systems. If the system is EM64T, you should say N unless your system is EM64T NUMA. @@ -1263,7 +1263,7 @@ config KEXEC strongly in flux, so no good recommendation can be made. config CRASH_DUMP - bool "kernel crash dumps (EXPERIMENTAL)" + bool "kernel crash dumps" depends on X86_64 || (X86_32 && HIGHMEM) help Generate crash dump after being started by kexec. diff --git a/arch/x86/boot/boot.h b/arch/x86/boot/boot.h index a34b9982c7c..cc0ef13fba7 100644 --- a/arch/x86/boot/boot.h +++ b/arch/x86/boot/boot.h @@ -24,10 +24,14 @@ #include <linux/edd.h> #include <asm/boot.h> #include <asm/setup.h> +#include "bitops.h" +#include <asm/cpufeature.h> /* Useful macros */ #define BUILD_BUG_ON(condition) ((void)sizeof(char[1 - 2*!!(condition)])) +#define ARRAY_SIZE(x) (sizeof(x) / sizeof(*(x))) + extern struct setup_header hdr; extern struct boot_params boot_params; @@ -242,6 +246,12 @@ int cmdline_find_option(const char *option, char *buffer, int bufsize); int cmdline_find_option_bool(const char *option); /* cpu.c, cpucheck.c */ +struct cpu_features { + int level; /* Family, or 64 for x86-64 */ + int model; + u32 flags[NCAPINTS]; +}; +extern struct cpu_features cpu; int check_cpu(int *cpu_level_ptr, int *req_level_ptr, u32 **err_flags_ptr); int validate_cpu(void); diff --git a/arch/x86/boot/cpu.c b/arch/x86/boot/cpu.c index 92d6fd73dc7..75298fe2edc 100644 --- a/arch/x86/boot/cpu.c +++ b/arch/x86/boot/cpu.c @@ -16,9 +16,6 @@ */ #include "boot.h" -#include "bitops.h" -#include <asm/cpufeature.h> - #include "cpustr.h" static char *cpu_name(int level) diff --git a/arch/x86/boot/cpucheck.c b/arch/x86/boot/cpucheck.c index 7804389ee00..4b9ae7c5674 100644 --- a/arch/x86/boot/cpucheck.c +++ b/arch/x86/boot/cpucheck.c @@ -22,21 +22,13 @@ #ifdef _SETUP # include "boot.h" -# include "bitops.h" #endif #include <linux/types.h> -#include <asm/cpufeature.h> #include <asm/processor-flags.h> #include <asm/required-features.h> #include <asm/msr-index.h> -struct cpu_features { - int level; /* Family, or 64 for x86-64 */ - int model; - u32 flags[NCAPINTS]; -}; - -static struct cpu_features cpu; +struct cpu_features cpu; static u32 cpu_vendor[3]; static u32 err_flags[NCAPINTS]; diff --git a/arch/x86/boot/main.c b/arch/x86/boot/main.c index 2296164b54d..197421db1af 100644 --- a/arch/x86/boot/main.c +++ b/arch/x86/boot/main.c @@ -73,6 +73,11 @@ static void keyboard_set_repeat(void) */ static void query_ist(void) { + /* Some older BIOSes apparently crash on this call, so filter + it from machines too old to have SpeedStep at all. */ + if (cpu.level < 6) + return; + asm("int $0x15" : "=a" (boot_params.ist_info.signature), "=b" (boot_params.ist_info.command), diff --git a/arch/x86/boot/memory.c b/arch/x86/boot/memory.c index 53165c97336..8c3c25f3557 100644 --- a/arch/x86/boot/memory.c +++ b/arch/x86/boot/memory.c @@ -13,7 +13,6 @@ */ #include "boot.h" -#include <linux/kernel.h> #define SMAP 0x534d4150 /* ASCII "SMAP" */ diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c index fa88a1d7129..bfd10fd211c 100644 --- a/arch/x86/kernel/acpi/boot.c +++ b/arch/x86/kernel/acpi/boot.c @@ -97,6 +97,8 @@ static u64 acpi_lapic_addr __initdata = APIC_DEFAULT_PHYS_BASE; #warning ACPI uses CMPXCHG, i486 and later hardware #endif +static int acpi_mcfg_64bit_base_addr __initdata = FALSE; + /* -------------------------------------------------------------------------- Boot-time Configuration -------------------------------------------------------------------------- */ @@ -158,6 +160,14 @@ char *__init __acpi_map_table(unsigned long phys, unsigned long size) struct acpi_mcfg_allocation *pci_mmcfg_config; int pci_mmcfg_config_num; +static int __init acpi_mcfg_oem_check(struct acpi_table_mcfg *mcfg) +{ + if (!strcmp(mcfg->header.oem_id, "SGI")) + acpi_mcfg_64bit_base_addr = TRUE; + + return 0; +} + int __init acpi_parse_mcfg(struct acpi_table_header *header) { struct acpi_table_mcfg *mcfg; @@ -190,8 +200,12 @@ int __init acpi_parse_mcfg(struct acpi_table_header *header) } memcpy(pci_mmcfg_config, &mcfg[1], config_size); + + acpi_mcfg_oem_check(mcfg); + for (i = 0; i < pci_mmcfg_config_num; ++i) { - if (pci_mmcfg_config[i].address > 0xFFFFFFFF) { + if ((pci_mmcfg_config[i].address > 0xFFFFFFFF) && + !acpi_mcfg_64bit_base_addr) { printk(KERN_ERR PREFIX "MMCONFIG not in low 4GB of memory\n"); kfree(pci_mmcfg_config); diff --git a/arch/x86/kernel/acpi/sleep.c b/arch/x86/kernel/acpi/sleep.c index fa2161d5003..426e5d91b63 100644 --- a/arch/x86/kernel/acpi/sleep.c +++ b/arch/x86/kernel/acpi/sleep.c @@ -20,7 +20,7 @@ unsigned long acpi_realmode_flags; /* address in low memory of the wakeup routine. */ static unsigned long acpi_realmode; -#ifdef CONFIG_64BIT +#if defined(CONFIG_SMP) && defined(CONFIG_64BIT) static char temp_stack[10240]; #endif @@ -86,7 +86,7 @@ int acpi_save_state_mem(void) #endif /* !CONFIG_64BIT */ header->pmode_cr0 = read_cr0(); - header->pmode_cr4 = read_cr4(); + header->pmode_cr4 = read_cr4_safe(); header->realmode_flags = acpi_realmode_flags; header->real_magic = 0x12345678; diff --git a/arch/x86/kernel/amd_iommu.c b/arch/x86/kernel/amd_iommu.c index 22d7d050905..69b4d060b21 100644 --- a/arch/x86/kernel/amd_iommu.c +++ b/arch/x86/kernel/amd_iommu.c @@ -65,7 +65,7 @@ static int __iommu_queue_command(struct amd_iommu *iommu, struct iommu_cmd *cmd) u8 *target; tail = readl(iommu->mmio_base + MMIO_CMD_TAIL_OFFSET); - target = (iommu->cmd_buf + tail); + target = iommu->cmd_buf + tail; memcpy_toio(target, cmd, sizeof(*cmd)); tail = (tail + sizeof(*cmd)) % iommu->cmd_buf_size; head = readl(iommu->mmio_base + MMIO_CMD_HEAD_OFFSET); @@ -101,16 +101,13 @@ static int iommu_queue_command(struct amd_iommu *iommu, struct iommu_cmd *cmd) */ static int iommu_completion_wait(struct amd_iommu *iommu) { - int ret; + int ret, ready = 0; + unsigned status = 0; struct iommu_cmd cmd; - volatile u64 ready = 0; - unsigned long ready_phys = virt_to_phys(&ready); unsigned long i = 0; memset(&cmd, 0, sizeof(cmd)); - cmd.data[0] = LOW_U32(ready_phys) | CMD_COMPL_WAIT_STORE_MASK; - cmd.data[1] = upper_32_bits(ready_phys); - cmd.data[2] = 1; /* value written to 'ready' */ + cmd.data[0] = CMD_COMPL_WAIT_INT_MASK; CMD_SET_TYPE(&cmd, CMD_COMPL_WAIT); iommu->need_sync = 0; @@ -122,9 +119,15 @@ static int iommu_completion_wait(struct amd_iommu *iommu) while (!ready && (i < EXIT_LOOP_COUNT)) { ++i; - cpu_relax(); + /* wait for the bit to become one */ + status = readl(iommu->mmio_base + MMIO_STATUS_OFFSET); + ready = status & MMIO_STATUS_COM_WAIT_INT_MASK; } + /* set bit back to zero */ + status &= ~MMIO_STATUS_COM_WAIT_INT_MASK; + writel(status, iommu->mmio_base + MMIO_STATUS_OFFSET); + if (unlikely((i == EXIT_LOOP_COUNT) && printk_ratelimit())) printk(KERN_WARNING "AMD IOMMU: Completion wait loop failed\n"); @@ -161,7 +164,7 @@ static int iommu_queue_inv_iommu_pages(struct amd_iommu *iommu, address &= PAGE_MASK; CMD_SET_TYPE(&cmd, CMD_INV_IOMMU_PAGES); cmd.data[1] |= domid; - cmd.data[2] = LOW_U32(address); + cmd.data[2] = lower_32_bits(address); cmd.data[3] = upper_32_bits(address); if (s) /* size bit - we flush more than one 4kb page */ cmd.data[2] |= CMD_INV_IOMMU_PAGES_SIZE_MASK; diff --git a/arch/x86/kernel/amd_iommu_init.c b/arch/x86/kernel/amd_iommu_init.c index d9a9da597e7..a69cc0f5204 100644 --- a/arch/x86/kernel/amd_iommu_init.c +++ b/arch/x86/kernel/amd_iommu_init.c @@ -801,6 +801,21 @@ static int __init init_memory_definitions(struct acpi_table_header *table) } /* + * Init the device table to not allow DMA access for devices and + * suppress all page faults + */ +static void init_device_table(void) +{ + u16 devid; + + for (devid = 0; devid <= amd_iommu_last_bdf; ++devid) { + set_dev_entry_bit(devid, DEV_ENTRY_VALID); + set_dev_entry_bit(devid, DEV_ENTRY_TRANSLATION); + set_dev_entry_bit(devid, DEV_ENTRY_NO_PAGE_FAULT); + } +} + +/* * This function finally enables all IOMMUs found in the system after * they have been initialized */ @@ -931,6 +946,9 @@ int __init amd_iommu_init(void) if (amd_iommu_pd_alloc_bitmap == NULL) goto free; + /* init the device table */ + init_device_table(); + /* * let all alias entries point to itself */ @@ -954,15 +972,15 @@ int __init amd_iommu_init(void) if (acpi_table_parse("IVRS", init_memory_definitions) != 0) goto free; - ret = amd_iommu_init_dma_ops(); + ret = sysdev_class_register(&amd_iommu_sysdev_class); if (ret) goto free; - ret = sysdev_class_register(&amd_iommu_sysdev_class); + ret = sysdev_register(&device_amd_iommu); if (ret) goto free; - ret = sysdev_register(&device_amd_iommu); + ret = amd_iommu_init_dma_ops(); if (ret) goto free; diff --git a/arch/x86/kernel/apic_32.c b/arch/x86/kernel/apic_32.c index 039a8d4aaf6..f88bd0d982b 100644 --- a/arch/x86/kernel/apic_32.c +++ b/arch/x86/kernel/apic_32.c @@ -1454,8 +1454,6 @@ void disconnect_bsp_APIC(int virt_wire_setup) } } -unsigned int __cpuinitdata maxcpus = NR_CPUS; - void __cpuinit generic_processor_info(int apicid, int version) { int cpu; @@ -1482,12 +1480,6 @@ void __cpuinit generic_processor_info(int apicid, int version) return; } - if (num_processors >= maxcpus) { - printk(KERN_WARNING "WARNING: maxcpus limit of %i reached." - " Processor ignored.\n", maxcpus); - return; - } - num_processors++; cpus_complement(tmp_map, cpu_present_map); cpu = first_cpu(tmp_map); diff --git a/arch/x86/kernel/apic_64.c b/arch/x86/kernel/apic_64.c index 7f1f030da7e..446c062e831 100644 --- a/arch/x86/kernel/apic_64.c +++ b/arch/x86/kernel/apic_64.c @@ -90,7 +90,6 @@ static unsigned long apic_phys; unsigned long mp_lapic_addr; -unsigned int __cpuinitdata maxcpus = NR_CPUS; /* * Get the LAPIC version */ @@ -1062,12 +1061,6 @@ void __cpuinit generic_processor_info(int apicid, int version) return; } - if (num_processors >= maxcpus) { - printk(KERN_WARNING "WARNING: maxcpus limit of %i reached." - " Processor ignored.\n", maxcpus); - return; - } - num_processors++; cpus_complement(tmp_map, cpu_present_map); cpu = first_cpu(tmp_map); diff --git a/arch/x86/kernel/cpu/addon_cpuid_features.c b/arch/x86/kernel/cpu/addon_cpuid_features.c index 84a8220a607..a6ef672adbb 100644 --- a/arch/x86/kernel/cpu/addon_cpuid_features.c +++ b/arch/x86/kernel/cpu/addon_cpuid_features.c @@ -56,9 +56,22 @@ void __cpuinit validate_pat_support(struct cpuinfo_x86 *c) switch (c->x86_vendor) { case X86_VENDOR_INTEL: - if (c->x86 == 0xF || (c->x86 == 6 && c->x86_model >= 15)) + /* + * There is a known erratum on Pentium III and Core Solo + * and Core Duo CPUs. + * " Page with PAT set to WC while associated MTRR is UC + * may consolidate to UC " + * Because of this erratum, it is better to stick with + * setting WC in MTRR rather than using PAT on these CPUs. + * + * Enable PAT WC only on P4, Core 2 or later CPUs. + */ + if (c->x86 > 0x6 || (c->x86 == 6 && c->x86_model >= 15)) return; - break; + + pat_disable("PAT WC disabled due to known CPU erratum."); + return; + case X86_VENDOR_AMD: case X86_VENDOR_CENTAUR: case X86_VENDOR_TRANSMETA: diff --git a/arch/x86/kernel/cpu/cpufreq/powernow-k8.c b/arch/x86/kernel/cpu/cpufreq/powernow-k8.c index 4e7271999a7..84bb395038d 100644 --- a/arch/x86/kernel/cpu/cpufreq/powernow-k8.c +++ b/arch/x86/kernel/cpu/cpufreq/powernow-k8.c @@ -737,63 +737,44 @@ static int find_psb_table(struct powernow_k8_data *data) #ifdef CONFIG_X86_POWERNOW_K8_ACPI static void powernow_k8_acpi_pst_values(struct powernow_k8_data *data, unsigned int index) { - if (!data->acpi_data->state_count || (cpu_family == CPU_HW_PSTATE)) + if (!data->acpi_data.state_count || (cpu_family == CPU_HW_PSTATE)) return; - data->irt = (data->acpi_data->states[index].control >> IRT_SHIFT) & IRT_MASK; - data->rvo = (data->acpi_data->states[index].control >> RVO_SHIFT) & RVO_MASK; - data->exttype = (data->acpi_data->states[index].control >> EXT_TYPE_SHIFT) & EXT_TYPE_MASK; - data->plllock = (data->acpi_data->states[index].control >> PLL_L_SHIFT) & PLL_L_MASK; - data->vidmvs = 1 << ((data->acpi_data->states[index].control >> MVS_SHIFT) & MVS_MASK); - data->vstable = (data->acpi_data->states[index].control >> VST_SHIFT) & VST_MASK; -} - - -static struct acpi_processor_performance *acpi_perf_data; -static int preregister_valid; - -static int powernow_k8_cpu_preinit_acpi(void) -{ - acpi_perf_data = alloc_percpu(struct acpi_processor_performance); - if (!acpi_perf_data) - return -ENODEV; - - if (acpi_processor_preregister_performance(acpi_perf_data)) - return -ENODEV; - else - preregister_valid = 1; - return 0; + data->irt = (data->acpi_data.states[index].control >> IRT_SHIFT) & IRT_MASK; + data->rvo = (data->acpi_data.states[index].control >> RVO_SHIFT) & RVO_MASK; + data->exttype = (data->acpi_data.states[index].control >> EXT_TYPE_SHIFT) & EXT_TYPE_MASK; + data->plllock = (data->acpi_data.states[index].control >> PLL_L_SHIFT) & PLL_L_MASK; + data->vidmvs = 1 << ((data->acpi_data.states[index].control >> MVS_SHIFT) & MVS_MASK); + data->vstable = (data->acpi_data.states[index].control >> VST_SHIFT) & VST_MASK; } static int powernow_k8_cpu_init_acpi(struct powernow_k8_data *data) { struct cpufreq_frequency_table *powernow_table; int ret_val; - int cpu = 0; - data->acpi_data = percpu_ptr(acpi_perf_data, cpu); - if (acpi_processor_register_performance(data->acpi_data, data->cpu)) { + if (acpi_processor_register_performance(&data->acpi_data, data->cpu)) { dprintk("register performance failed: bad ACPI data\n"); return -EIO; } /* verify the data contained in the ACPI structures */ - if (data->acpi_data->state_count <= 1) { + if (data->acpi_data.state_count <= 1) { dprintk("No ACPI P-States\n"); goto err_out; } - if ((data->acpi_data->control_register.space_id != ACPI_ADR_SPACE_FIXED_HARDWARE) || - (data->acpi_data->status_register.space_id != ACPI_ADR_SPACE_FIXED_HARDWARE)) { + if ((data->acpi_data.control_register.space_id != ACPI_ADR_SPACE_FIXED_HARDWARE) || + (data->acpi_data.status_register.space_id != ACPI_ADR_SPACE_FIXED_HARDWARE)) { dprintk("Invalid control/status registers (%x - %x)\n", - data->acpi_data->control_register.space_id, - data->acpi_data->status_register.space_id); + data->acpi_data.control_register.space_id, + data->acpi_data.status_register.space_id); goto err_out; } /* fill in data->powernow_table */ powernow_table = kmalloc((sizeof(struct cpufreq_frequency_table) - * (data->acpi_data->state_count + 1)), GFP_KERNEL); + * (data->acpi_data.state_count + 1)), GFP_KERNEL); if (!powernow_table) { dprintk("powernow_table memory alloc failure\n"); goto err_out; @@ -806,12 +787,12 @@ static int powernow_k8_cpu_init_acpi(struct powernow_k8_data *data) if (ret_val) goto err_out_mem; - powernow_table[data->acpi_data->state_count].frequency = CPUFREQ_TABLE_END; - powernow_table[data->acpi_data->state_count].index = 0; + powernow_table[data->acpi_data.state_count].frequency = CPUFREQ_TABLE_END; + powernow_table[data->acpi_data.state_count].index = 0; data->powernow_table = powernow_table; /* fill in data */ - data->numps = data->acpi_data->state_count; + data->numps = data->acpi_data.state_count; if (first_cpu(per_cpu(cpu_core_map, data->cpu)) == data->cpu) print_basics(data); powernow_k8_acpi_pst_values(data, 0); @@ -819,31 +800,16 @@ static int powernow_k8_cpu_init_acpi(struct powernow_k8_data *data) /* notify BIOS that we exist */ acpi_processor_notify_smm(THIS_MODULE); - /* determine affinity, from ACPI if available */ - if (preregister_valid) { - if ((data->acpi_data->shared_type == CPUFREQ_SHARED_TYPE_ALL) || - (data->acpi_data->shared_type == CPUFREQ_SHARED_TYPE_ANY)) - data->starting_core_affinity = data->acpi_data->shared_cpu_map; - else - data->starting_core_affinity = cpumask_of_cpu(data->cpu); - } else { - /* best guess from family if not */ - if (cpu_family == CPU_HW_PSTATE) - data->starting_core_affinity = cpumask_of_cpu(data->cpu); - else - data->starting_core_affinity = per_cpu(cpu_core_map, data->cpu); - } - return 0; err_out_mem: kfree(powernow_table); err_out: - acpi_processor_unregister_performance(data->acpi_data, data->cpu); + acpi_processor_unregister_performance(&data->acpi_data, data->cpu); /* data->acpi_data.state_count informs us at ->exit() whether ACPI was used */ - data->acpi_data->state_count = 0; + data->acpi_data.state_count = 0; return -ENODEV; } @@ -855,10 +821,10 @@ static int fill_powernow_table_pstate(struct powernow_k8_data *data, struct cpuf rdmsr(MSR_PSTATE_CUR_LIMIT, hi, lo); data->max_hw_pstate = (hi & HW_PSTATE_MAX_MASK) >> HW_PSTATE_MAX_SHIFT; - for (i = 0; i < data->acpi_data->state_count; i++) { + for (i = 0; i < data->acpi_data.state_count; i++) { u32 index; - index = data->acpi_data->states[i].control & HW_PSTATE_MASK; + index = data->acpi_data.states[i].control & HW_PSTATE_MASK; if (index > data->max_hw_pstate) { printk(KERN_ERR PFX "invalid pstate %d - bad value %d.\n", i, index); printk(KERN_ERR PFX "Please report to BIOS manufacturer\n"); @@ -874,7 +840,7 @@ static int fill_powernow_table_pstate(struct powernow_k8_data *data, struct cpuf powernow_table[i].index = index; - powernow_table[i].frequency = data->acpi_data->states[i].core_frequency * 1000; + powernow_table[i].frequency = data->acpi_data.states[i].core_frequency * 1000; } return 0; } @@ -883,16 +849,16 @@ static int fill_powernow_table_fidvid(struct powernow_k8_data *data, struct cpuf { int i; int cntlofreq = 0; - for (i = 0; i < data->acpi_data->state_count; i++) { + for (i = 0; i < data->acpi_data.state_count; i++) { u32 fid; u32 vid; if (data->exttype) { - fid = data->acpi_data->states[i].status & EXT_FID_MASK; - vid = (data->acpi_data->states[i].status >> VID_SHIFT) & EXT_VID_MASK; + fid = data->acpi_data.states[i].status & EXT_FID_MASK; + vid = (data->acpi_data.states[i].status >> VID_SHIFT) & EXT_VID_MASK; } else { - fid = data->acpi_data->states[i].control & FID_MASK; - vid = (data->acpi_data->states[i].control >> VID_SHIFT) & VID_MASK; + fid = data->acpi_data.states[i].control & FID_MASK; + vid = (data->acpi_data.states[i].control >> VID_SHIFT) & VID_MASK; } dprintk(" %d : fid 0x%x, vid 0x%x\n", i, fid, vid); @@ -933,10 +899,10 @@ static int fill_powernow_table_fidvid(struct powernow_k8_data *data, struct cpuf cntlofreq = i; } - if (powernow_table[i].frequency != (data->acpi_data->states[i].core_frequency * 1000)) { + if (powernow_table[i].frequency != (data->acpi_data.states[i].core_frequency * 1000)) { printk(KERN_INFO PFX "invalid freq entries %u kHz vs. %u kHz\n", powernow_table[i].frequency, - (unsigned int) (data->acpi_data->states[i].core_frequency * 1000)); + (unsigned int) (data->acpi_data.states[i].core_frequency * 1000)); powernow_table[i].frequency = CPUFREQ_ENTRY_INVALID; continue; } @@ -946,12 +912,11 @@ static int fill_powernow_table_fidvid(struct powernow_k8_data *data, struct cpuf static void powernow_k8_cpu_exit_acpi(struct powernow_k8_data *data) { - if (data->acpi_data->state_count) - acpi_processor_unregister_performance(data->acpi_data, data->cpu); + if (data->acpi_data.state_count) + acpi_processor_unregister_performance(&data->acpi_data, data->cpu); } #else -static int powernow_k8_cpu_preinit_acpi(void) { return -ENODEV; } static int powernow_k8_cpu_init_acpi(struct powernow_k8_data *data) { return -ENODEV; } static void powernow_k8_cpu_exit_acpi(struct powernow_k8_data *data) { return; } static void powernow_k8_acpi_pst_values(struct powernow_k8_data *data, unsigned int index) { return; } @@ -1136,7 +1101,7 @@ static int powernowk8_verify(struct cpufreq_policy *pol) static int __cpuinit powernowk8_cpu_init(struct cpufreq_policy *pol) { struct powernow_k8_data *data; - cpumask_t oldmask = CPU_MASK_ALL; + cpumask_t oldmask; int rc; if (!cpu_online(pol->cpu)) @@ -1209,7 +1174,10 @@ static int __cpuinit powernowk8_cpu_init(struct cpufreq_policy *pol) /* run on any CPU again */ set_cpus_allowed_ptr(current, &oldmask); - pol->cpus = data->starting_core_affinity; + if (cpu_family == CPU_HW_PSTATE) + pol->cpus = cpumask_of_cpu(pol->cpu); + else + pol->cpus = per_cpu(cpu_core_map, pol->cpu); data->available_cores = &(pol->cpus); /* Take a crude guess here. @@ -1332,7 +1300,6 @@ static int __cpuinit powernowk8_init(void) } if (supported_cpus == num_online_cpus()) { - powernow_k8_cpu_preinit_acpi(); printk(KERN_INFO PFX "Found %d %s " "processors (%d cpu cores) (" VERSION ")\n", num_online_nodes(), @@ -1349,10 +1316,6 @@ static void __exit powernowk8_exit(void) dprintk("exit\n"); cpufreq_unregister_driver(&cpufreq_amd64_driver); - -#ifdef CONFIG_X86_POWERNOW_K8_ACPI - free_percpu(acpi_perf_data); -#endif } MODULE_AUTHOR("Paul Devriendt <paul.devriendt@amd.com> and Mark Langsdorf <mark.langsdorf@amd.com>"); diff --git a/arch/x86/kernel/cpu/cpufreq/powernow-k8.h b/arch/x86/kernel/cpu/cpufreq/powernow-k8.h index a62612cd4be..ab48cfed4d9 100644 --- a/arch/x86/kernel/cpu/cpufreq/powernow-k8.h +++ b/arch/x86/kernel/cpu/cpufreq/powernow-k8.h @@ -33,13 +33,12 @@ struct powernow_k8_data { #ifdef CONFIG_X86_POWERNOW_K8_ACPI /* the acpi table needs to be kept. it's only available if ACPI was * used to determine valid frequency/vid/fid states */ - struct acpi_processor_performance *acpi_data; + struct acpi_processor_performance acpi_data; #endif /* we need to keep track of associated cores, but let cpufreq * handle hotplug events - so just point at cpufreq pol->cpus * structure */ cpumask_t *available_cores; - cpumask_t starting_core_affinity; }; diff --git a/arch/x86/kernel/cpu/cyrix.c b/arch/x86/kernel/cpu/cyrix.c index 3fd7a67bb06..e710a21bb6e 100644 --- a/arch/x86/kernel/cpu/cyrix.c +++ b/arch/x86/kernel/cpu/cyrix.c @@ -134,23 +134,6 @@ static void __cpuinit set_cx86_memwb(void) setCx86(CX86_CCR2, getCx86(CX86_CCR2) | 0x14); } -static void __cpuinit set_cx86_inc(void) -{ - unsigned char ccr3; - - printk(KERN_INFO "Enable Incrementor on Cyrix/NSC processor.\n"); - - ccr3 = getCx86(CX86_CCR3); - setCx86(CX86_CCR3, (ccr3 & 0x0f) | 0x10); /* enable MAPEN */ - /* PCR1 -- Performance Control */ - /* Incrementor on, whatever that is */ - setCx86(CX86_PCR1, getCx86(CX86_PCR1) | 0x02); - /* PCR0 -- Performance Control */ - /* Incrementor Margin 10 */ - setCx86(CX86_PCR0, getCx86(CX86_PCR0) | 0x04); - setCx86(CX86_CCR3, ccr3); /* disable MAPEN */ -} - /* * Configure later MediaGX and/or Geode processor. */ @@ -174,7 +157,6 @@ static void __cpuinit geode_configure(void) set_cx86_memwb(); set_cx86_reorder(); - set_cx86_inc(); local_irq_restore(flags); } diff --git a/arch/x86/kernel/cpu/mtrr/generic.c b/arch/x86/kernel/cpu/mtrr/generic.c index 509bd3d9eac..cb7d3b6a80e 100644 --- a/arch/x86/kernel/cpu/mtrr/generic.c +++ b/arch/x86/kernel/cpu/mtrr/generic.c @@ -379,6 +379,7 @@ static void generic_get_mtrr(unsigned int reg, unsigned long *base, unsigned long *size, mtrr_type *type) { unsigned int mask_lo, mask_hi, base_lo, base_hi; + unsigned int tmp, hi; rdmsr(MTRRphysMask_MSR(reg), mask_lo, mask_hi); if ((mask_lo & 0x800) == 0) { @@ -392,8 +393,23 @@ static void generic_get_mtrr(unsigned int reg, unsigned long *base, rdmsr(MTRRphysBase_MSR(reg), base_lo, base_hi); /* Work out the shifted address mask. */ - mask_lo = size_or_mask | mask_hi << (32 - PAGE_SHIFT) - | mask_lo >> PAGE_SHIFT; + tmp = mask_hi << (32 - PAGE_SHIFT) | mask_lo >> PAGE_SHIFT; + mask_lo = size_or_mask | tmp; + /* Expand tmp with high bits to all 1s*/ + hi = fls(tmp); + if (hi > 0) { + tmp |= ~((1<<(hi - 1)) - 1); + + if (tmp != mask_lo) { + static int once = 1; + + if (once) { + printk(KERN_INFO "mtrr: your BIOS has set up an incorrect mask, fixing it up.\n"); + once = 0; + } + mask_lo = tmp; + } + } /* This works correctly if size is a power of two, i.e. a contiguous range. */ diff --git a/arch/x86/kernel/cpu/mtrr/main.c b/arch/x86/kernel/cpu/mtrr/main.c index 6f23969c8fa..b117d7f8a56 100644 --- a/arch/x86/kernel/cpu/mtrr/main.c +++ b/arch/x86/kernel/cpu/mtrr/main.c @@ -1496,11 +1496,8 @@ int __init mtrr_trim_uncached_memory(unsigned long end_pfn) /* kvm/qemu doesn't have mtrr set right, don't trim them all */ if (!highest_pfn) { - if (!kvm_para_available()) { - printk(KERN_WARNING + WARN(!kvm_para_available(), KERN_WARNING "WARNING: strange, CPU MTRRs all blank?\n"); - WARN_ON(1); - } return 0; } diff --git a/arch/x86/kernel/cpu/perfctr-watchdog.c b/arch/x86/kernel/cpu/perfctr-watchdog.c index de7439f82b9..05cc22dbd4f 100644 --- a/arch/x86/kernel/cpu/perfctr-watchdog.c +++ b/arch/x86/kernel/cpu/perfctr-watchdog.c @@ -478,7 +478,13 @@ static int setup_p4_watchdog(unsigned nmi_hz) perfctr_msr = MSR_P4_IQ_PERFCTR1; evntsel_msr = MSR_P4_CRU_ESCR0; cccr_msr = MSR_P4_IQ_CCCR1; - cccr_val = P4_CCCR_OVF_PMI1 | P4_CCCR_ESCR_SELECT(4); + + /* Pentium 4 D processors don't support P4_CCCR_OVF_PMI1 */ + if (boot_cpu_data.x86_model == 4 && boot_cpu_data.x86_mask == 4) + cccr_val = P4_CCCR_OVF_PMI0; + else + cccr_val = P4_CCCR_OVF_PMI1; + cccr_val |= P4_CCCR_ESCR_SELECT(4); } evntsel = P4_ESCR_EVENT_SELECT(0x3F) diff --git a/arch/x86/kernel/efi_32.c b/arch/x86/kernel/efi_32.c index 4b63c8e1f13..5cab48ee61a 100644 --- a/arch/x86/kernel/efi_32.c +++ b/arch/x86/kernel/efi_32.c @@ -53,7 +53,7 @@ void efi_call_phys_prelog(void) * directory. If I have PAE, I just need to duplicate one entry in * page directory. */ - cr4 = read_cr4(); + cr4 = read_cr4_safe(); if (cr4 & X86_CR4_PAE) { efi_bak_pg_dir_pointer[0].pgd = @@ -91,7 +91,7 @@ void efi_call_phys_epilog(void) gdt_descr.size = GDT_SIZE - 1; load_gdt(&gdt_descr); - cr4 = read_cr4(); + cr4 = read_cr4_safe(); if (cr4 & X86_CR4_PAE) { swapper_pg_dir[pgd_index(0)].pgd = diff --git a/arch/x86/kernel/genx2apic_uv_x.c b/arch/x86/kernel/genx2apic_uv_x.c index 2cfcbded888..bfa837cb16b 100644 --- a/arch/x86/kernel/genx2apic_uv_x.c +++ b/arch/x86/kernel/genx2apic_uv_x.c @@ -222,7 +222,7 @@ static __init void map_low_mmrs(void) enum map_type {map_wb, map_uc}; -static void map_high(char *id, unsigned long base, int shift, enum map_type map_type) +static __init void map_high(char *id, unsigned long base, int shift, enum map_type map_type) { unsigned long bytes, paddr; @@ -293,7 +293,9 @@ static __init void uv_rtc_init(void) sn_rtc_cycles_per_second = ticks_per_sec; } -static __init void uv_system_init(void) +static bool uv_system_inited; + +void __init uv_system_init(void) { union uvh_si_addr_map_config_u m_n_config; union uvh_node_id_u node_id; @@ -383,6 +385,7 @@ static __init void uv_system_init(void) map_mmr_high(max_pnode); map_config_high(max_pnode); map_mmioh_high(max_pnode); + uv_system_inited = true; } /* @@ -391,8 +394,7 @@ static __init void uv_system_init(void) */ void __cpuinit uv_cpu_init(void) { - if (!uv_node_to_blade) - uv_system_init(); + BUG_ON(!uv_system_inited); uv_blade_info[uv_numa_blade_id()].nr_online_cpus++; diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c index 1b318e903bf..9bfc4d72fb2 100644 --- a/arch/x86/kernel/head64.c +++ b/arch/x86/kernel/head64.c @@ -88,6 +88,7 @@ void __init x86_64_start_kernel(char * real_mode_data) BUILD_BUG_ON(!(MODULES_VADDR > __START_KERNEL)); BUILD_BUG_ON(!(((MODULES_END - 1) & PGDIR_MASK) == (__START_KERNEL & PGDIR_MASK))); + BUILD_BUG_ON(__fix_to_virt(__end_of_fixed_addresses) <= MODULES_END); /* clear bss before set_intr_gate with early_idt_handler */ clear_bss(); diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c index ad2b15a1334..59fd3b6b130 100644 --- a/arch/x86/kernel/hpet.c +++ b/arch/x86/kernel/hpet.c @@ -359,6 +359,7 @@ static int hpet_clocksource_register(void) int __init hpet_enable(void) { unsigned long id; + int i; if (!is_hpet_capable()) return 0; @@ -369,6 +370,29 @@ int __init hpet_enable(void) * Read the period and check for a sane value: */ hpet_period = hpet_readl(HPET_PERIOD); + + /* + * AMD SB700 based systems with spread spectrum enabled use a + * SMM based HPET emulation to provide proper frequency + * setting. The SMM code is initialized with the first HPET + * register access and takes some time to complete. During + * this time the config register reads 0xffffffff. We check + * for max. 1000 loops whether the config register reads a non + * 0xffffffff value to make sure that HPET is up and running + * before we go further. A counting loop is safe, as the HPET + * access takes thousands of CPU cycles. On non SB700 based + * machines this check is only done once and has no side + * effects. + */ + for (i = 0; hpet_readl(HPET_CFG) == 0xFFFFFFFF; i++) { + if (i == 1000) { + printk(KERN_WARNING + "HPET config register value = 0xFFFFFFFF. " + "Disabling HPET\n"); + goto out_nohpet; + } + } + if (hpet_period < HPET_MIN_PERIOD || hpet_period > HPET_MAX_PERIOD) goto out_nohpet; diff --git a/arch/x86/kernel/machine_kexec_32.c b/arch/x86/kernel/machine_kexec_32.c index 9fe478d9840..0732adba05c 100644 --- a/arch/x86/kernel/machine_kexec_32.c +++ b/arch/x86/kernel/machine_kexec_32.c @@ -12,6 +12,7 @@ #include <linux/init.h> #include <linux/numa.h> #include <linux/ftrace.h> +#include <linux/suspend.h> #include <asm/pgtable.h> #include <asm/pgalloc.h> @@ -78,7 +79,7 @@ static void load_segments(void) /* * A architecture hook called to validate the * proposed image and prepare the control pages - * as needed. The pages for KEXEC_CONTROL_CODE_SIZE + * as needed. The pages for KEXEC_CONTROL_PAGE_SIZE * have been allocated, but the segments have yet * been copied into the kernel. * @@ -113,6 +114,7 @@ void machine_kexec(struct kimage *image) { unsigned long page_list[PAGES_NR]; void *control_page; + int save_ftrace_enabled; asmlinkage unsigned long (*relocate_kernel_ptr)(unsigned long indirection_page, unsigned long control_page, @@ -120,7 +122,12 @@ void machine_kexec(struct kimage *image) unsigned int has_pae, unsigned int preserve_context); - tracer_disable(); +#ifdef CONFIG_KEXEC_JUMP + if (kexec_image->preserve_context) + save_processor_state(); +#endif + + save_ftrace_enabled = __ftrace_enabled_save(); /* Interrupts aren't acceptable while we reboot */ local_irq_disable(); @@ -138,7 +145,7 @@ void machine_kexec(struct kimage *image) } control_page = page_address(image->control_code_page); - memcpy(control_page, relocate_kernel, PAGE_SIZE/2); + memcpy(control_page, relocate_kernel, KEXEC_CONTROL_CODE_MAX_SIZE); relocate_kernel_ptr = control_page; page_list[PA_CONTROL_PAGE] = __pa(control_page); @@ -178,6 +185,13 @@ void machine_kexec(struct kimage *image) (unsigned long)page_list, image->start, cpu_has_pae, image->preserve_context); + +#ifdef CONFIG_KEXEC_JUMP + if (kexec_image->preserve_context) + restore_processor_state(); +#endif + + __ftrace_enabled_restore(save_ftrace_enabled); } void arch_crash_save_vmcoreinfo(void) diff --git a/arch/x86/kernel/mfgpt_32.c b/arch/x86/kernel/mfgpt_32.c index 07c0f828f48..3b599518c32 100644 --- a/arch/x86/kernel/mfgpt_32.c +++ b/arch/x86/kernel/mfgpt_32.c @@ -33,6 +33,8 @@ #include <linux/module.h> #include <asm/geode.h> +#define MFGPT_DEFAULT_IRQ 7 + static struct mfgpt_timer_t { unsigned int avail:1; } mfgpt_timers[MFGPT_MAX_TIMERS]; @@ -157,29 +159,48 @@ int geode_mfgpt_toggle_event(int timer, int cmp, int event, int enable) } EXPORT_SYMBOL_GPL(geode_mfgpt_toggle_event); -int geode_mfgpt_set_irq(int timer, int cmp, int irq, int enable) +int geode_mfgpt_set_irq(int timer, int cmp, int *irq, int enable) { - u32 val, dummy; - int offset; + u32 zsel, lpc, dummy; + int shift; if (timer < 0 || timer >= MFGPT_MAX_TIMERS) return -EIO; - if (geode_mfgpt_toggle_event(timer, cmp, MFGPT_EVENT_IRQ, enable)) + /* + * Unfortunately, MFGPTs come in pairs sharing their IRQ lines. If VSA + * is using the same CMP of the timer's Siamese twin, the IRQ is set to + * 2, and we mustn't use nor change it. + * XXX: Likewise, 2 Linux drivers might clash if the 2nd overwrites the + * IRQ of the 1st. This can only happen if forcing an IRQ, calling this + * with *irq==0 is safe. Currently there _are_ no 2 drivers. + */ + rdmsr(MSR_PIC_ZSEL_LOW, zsel, dummy); + shift = ((cmp == MFGPT_CMP1 ? 0 : 4) + timer % 4) * 4; + if (((zsel >> shift) & 0xF) == 2) return -EIO; - rdmsr(MSR_PIC_ZSEL_LOW, val, dummy); + /* Choose IRQ: if none supplied, keep IRQ already set or use default */ + if (!*irq) + *irq = (zsel >> shift) & 0xF; + if (!*irq) + *irq = MFGPT_DEFAULT_IRQ; - offset = (timer % 4) * 4; - - val &= ~((0xF << offset) | (0xF << (offset + 16))); + /* Can't use IRQ if it's 0 (=disabled), 2, or routed to LPC */ + if (*irq < 1 || *irq == 2 || *irq > 15) + return -EIO; + rdmsr(MSR_PIC_IRQM_LPC, lpc, dummy); + if (lpc & (1 << *irq)) + return -EIO; + /* All chosen and checked - go for it */ + if (geode_mfgpt_toggle_event(timer, cmp, MFGPT_EVENT_IRQ, enable)) + return -EIO; if (enable) { - val |= (irq & 0x0F) << (offset); - val |= (irq & 0x0F) << (offset + 16); + zsel = (zsel & ~(0xF << shift)) | (*irq << shift); + wrmsr(MSR_PIC_ZSEL_LOW, zsel, dummy); } - wrmsr(MSR_PIC_ZSEL_LOW, val, dummy); return 0; } @@ -242,7 +263,7 @@ EXPORT_SYMBOL_GPL(geode_mfgpt_alloc_timer); static unsigned int mfgpt_tick_mode = CLOCK_EVT_MODE_SHUTDOWN; static u16 mfgpt_event_clock; -static int irq = 7; +static int irq; static int __init mfgpt_setup(char *str) { get_option(&str, &irq); @@ -346,7 +367,7 @@ int __init mfgpt_timer_setup(void) mfgpt_event_clock = timer; /* Set up the IRQ on the MFGPT side */ - if (geode_mfgpt_setup_irq(mfgpt_event_clock, MFGPT_CMP2, irq)) { + if (geode_mfgpt_setup_irq(mfgpt_event_clock, MFGPT_CMP2, &irq)) { printk(KERN_ERR "mfgpt-timer: Could not set up IRQ %d\n", irq); return -EIO; } @@ -374,13 +395,14 @@ int __init mfgpt_timer_setup(void) &mfgpt_clockevent); printk(KERN_INFO - "mfgpt-timer: registering the MFGPT timer as a clock event.\n"); + "mfgpt-timer: Registering MFGPT timer %d as a clock event, using IRQ %d\n", + timer, irq); clockevents_register_device(&mfgpt_clockevent); return 0; err: - geode_mfgpt_release_irq(mfgpt_event_clock, MFGPT_CMP2, irq); + geode_mfgpt_release_irq(mfgpt_event_clock, MFGPT_CMP2, &irq); printk(KERN_ERR "mfgpt-timer: Unable to set up the MFGPT clock source\n"); return -EIO; diff --git a/arch/x86/kernel/mmconf-fam10h_64.c b/arch/x86/kernel/mmconf-fam10h_64.c index fdfdc550b36..efc2f361fe8 100644 --- a/arch/x86/kernel/mmconf-fam10h_64.c +++ b/arch/x86/kernel/mmconf-fam10h_64.c @@ -238,7 +238,7 @@ static struct dmi_system_id __devinitdata mmconf_dmi_table[] = { {} }; -void __init check_enable_amd_mmconf_dmi(void) +void __cpuinit check_enable_amd_mmconf_dmi(void) { dmi_check_system(mmconf_dmi_table); } diff --git a/arch/x86/kernel/mpparse.c b/arch/x86/kernel/mpparse.c index 678090508a6..b3fb430725c 100644 --- a/arch/x86/kernel/mpparse.c +++ b/arch/x86/kernel/mpparse.c @@ -49,7 +49,7 @@ static int __init mpf_checksum(unsigned char *mp, int len) return sum & 0xFF; } -static void __cpuinit MP_processor_info(struct mpc_config_processor *m) +static void __init MP_processor_info(struct mpc_config_processor *m) { int apicid; char *bootup_cpu = ""; @@ -484,7 +484,7 @@ static void __init construct_default_ioirq_mptable(int mpc_default_type) } -static void construct_ioapic_table(int mpc_default_type) +static void __init construct_ioapic_table(int mpc_default_type) { struct mpc_config_ioapic ioapic; struct mpc_config_bus bus; @@ -529,7 +529,7 @@ static void construct_ioapic_table(int mpc_default_type) construct_default_ioirq_mptable(mpc_default_type); } #else -static inline void construct_ioapic_table(int mpc_default_type) { } +static inline void __init construct_ioapic_table(int mpc_default_type) { } #endif static inline void __init construct_default_ISA_mptable(int mpc_default_type) diff --git a/arch/x86/kernel/msr.c b/arch/x86/kernel/msr.c index 9fd80955244..e4393808688 100644 --- a/arch/x86/kernel/msr.c +++ b/arch/x86/kernel/msr.c @@ -131,7 +131,7 @@ static int msr_open(struct inode *inode, struct file *file) ret = -EIO; /* MSR not supported */ out: unlock_kernel(); - return 0; + return ret; } /* diff --git a/arch/x86/kernel/nmi.c b/arch/x86/kernel/nmi.c index ac6d51222e7..abb78a2cc4a 100644 --- a/arch/x86/kernel/nmi.c +++ b/arch/x86/kernel/nmi.c @@ -114,6 +114,23 @@ static __init void nmi_cpu_busy(void *data) } #endif +static void report_broken_nmi(int cpu, int *prev_nmi_count) +{ + printk(KERN_CONT "\n"); + + printk(KERN_WARNING + "WARNING: CPU#%d: NMI appears to be stuck (%d->%d)!\n", + cpu, prev_nmi_count[cpu], get_nmi_count(cpu)); + + printk(KERN_WARNING + "Please report this to bugzilla.kernel.org,\n"); + printk(KERN_WARNING + "and attach the output of the 'dmesg' command.\n"); + + per_cpu(wd_enabled, cpu) = 0; + atomic_dec(&nmi_active); +} + int __init check_nmi_watchdog(void) { unsigned int *prev_nmi_count; @@ -141,15 +158,8 @@ int __init check_nmi_watchdog(void) for_each_online_cpu(cpu) { if (!per_cpu(wd_enabled, cpu)) continue; - if (get_nmi_count(cpu) - prev_nmi_count[cpu] <= 5) { - printk(KERN_WARNING "WARNING: CPU#%d: NMI " - "appears to be stuck (%d->%d)!\n", - cpu, - prev_nmi_count[cpu], - get_nmi_count(cpu)); - per_cpu(wd_enabled, cpu) = 0; - atomic_dec(&nmi_active); - } + if (get_nmi_count(cpu) - prev_nmi_count[cpu] <= 5) + report_broken_nmi(cpu, prev_nmi_count); } endflag = 1; if (!atomic_read(&nmi_active)) { diff --git a/arch/x86/kernel/numaq_32.c b/arch/x86/kernel/numaq_32.c index b8c45610b20..eecc8c18f01 100644 --- a/arch/x86/kernel/numaq_32.c +++ b/arch/x86/kernel/numaq_32.c @@ -73,7 +73,7 @@ static void __init smp_dump_qct(void) } -void __init numaq_tsc_disable(void) +void __cpuinit numaq_tsc_disable(void) { if (!found_numaq) return; diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c index 94da4d52d79..300da17e61c 100644 --- a/arch/x86/kernel/paravirt.c +++ b/arch/x86/kernel/paravirt.c @@ -471,7 +471,7 @@ struct pv_lock_ops pv_lock_ops = { .spin_unlock = __ticket_spin_unlock, #endif }; -EXPORT_SYMBOL_GPL(pv_lock_ops); +EXPORT_SYMBOL(pv_lock_ops); EXPORT_SYMBOL_GPL(pv_time_ops); EXPORT_SYMBOL (pv_cpu_ops); diff --git a/arch/x86/kernel/pci-calgary_64.c b/arch/x86/kernel/pci-calgary_64.c index 02d19328525..dcdac6c826e 100644 --- a/arch/x86/kernel/pci-calgary_64.c +++ b/arch/x86/kernel/pci-calgary_64.c @@ -343,9 +343,8 @@ static void iommu_free(struct iommu_table *tbl, dma_addr_t dma_addr, /* were we called with bad_dma_address? */ badend = bad_dma_address + (EMERGENCY_PAGES * PAGE_SIZE); if (unlikely((dma_addr >= bad_dma_address) && (dma_addr < badend))) { - printk(KERN_ERR "Calgary: driver tried unmapping bad DMA " + WARN(1, KERN_ERR "Calgary: driver tried unmapping bad DMA " "address 0x%Lx\n", dma_addr); - WARN_ON(1); return; } @@ -1269,13 +1268,15 @@ static inline int __init determine_tce_table_size(u64 ram) static int __init build_detail_arrays(void) { unsigned long ptr; - int i, scal_detail_size, rio_detail_size; + unsigned numnodes, i; + int scal_detail_size, rio_detail_size; - if (rio_table_hdr->num_scal_dev > MAX_NUMNODES){ + numnodes = rio_table_hdr->num_scal_dev; + if (numnodes > MAX_NUMNODES){ printk(KERN_WARNING "Calgary: MAX_NUMNODES too low! Defined as %d, " "but system has %d nodes.\n", - MAX_NUMNODES, rio_table_hdr->num_scal_dev); + MAX_NUMNODES, numnodes); return -ENODEV; } @@ -1296,8 +1297,7 @@ static int __init build_detail_arrays(void) } ptr = ((unsigned long)rio_table_hdr) + 3; - for (i = 0; i < rio_table_hdr->num_scal_dev; - i++, ptr += scal_detail_size) + for (i = 0; i < numnodes; i++, ptr += scal_detail_size) scal_devs[i] = (struct scal_detail *)ptr; for (i = 0; i < rio_table_hdr->num_rio_dev; @@ -1350,7 +1350,7 @@ static void calgary_init_bitmap_from_tce_table(struct iommu_table *tbl) * Function for kdump case. Get the tce tables from first kernel * by reading the contents of the base adress register of calgary iommu */ -static void get_tce_space_from_tar(void) +static void __init get_tce_space_from_tar(void) { int bus; void __iomem *target; diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c index 53bc653ed5c..3b7a1ddcc0b 100644 --- a/arch/x86/kernel/process_32.c +++ b/arch/x86/kernel/process_32.c @@ -95,7 +95,6 @@ static inline void play_dead(void) { /* This must be done before dead CPU ack */ cpu_exit_clear(); - wbinvd(); mb(); /* Ack it */ __get_cpu_var(cpu_state) = CPU_DEAD; @@ -104,8 +103,8 @@ static inline void play_dead(void) * With physical CPU hotplug, we should halt the cpu */ local_irq_disable(); - while (1) - halt(); + /* mask all interrupts, flush any and all caches, and halt */ + wbinvd_halt(); } #else static inline void play_dead(void) diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index 3fb62a7d9a1..71553b664e2 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -93,14 +93,13 @@ DECLARE_PER_CPU(int, cpu_state); static inline void play_dead(void) { idle_task_exit(); - wbinvd(); mb(); /* Ack it */ __get_cpu_var(cpu_state) = CPU_DEAD; local_irq_disable(); - while (1) - halt(); + /* mask all interrupts, flush any and all caches, and halt */ + wbinvd_halt(); } #else static inline void play_dead(void) diff --git a/arch/x86/kernel/relocate_kernel_32.S b/arch/x86/kernel/relocate_kernel_32.S index 703310a9902..6f50664b2ba 100644 --- a/arch/x86/kernel/relocate_kernel_32.S +++ b/arch/x86/kernel/relocate_kernel_32.S @@ -20,10 +20,11 @@ #define PAGE_ATTR (_PAGE_PRESENT | _PAGE_RW | _PAGE_ACCESSED | _PAGE_DIRTY) #define PAE_PGD_ATTR (_PAGE_PRESENT) -/* control_page + PAGE_SIZE/2 ~ control_page + PAGE_SIZE * 3/4 are - * used to save some data for jumping back +/* control_page + KEXEC_CONTROL_CODE_MAX_SIZE + * ~ control_page + PAGE_SIZE are used as data storage and stack for + * jumping back */ -#define DATA(offset) (PAGE_SIZE/2+(offset)) +#define DATA(offset) (KEXEC_CONTROL_CODE_MAX_SIZE+(offset)) /* Minimal CPU state */ #define ESP DATA(0x0) @@ -376,3 +377,6 @@ swap_pages: popl %ebx popl %ebp ret + + .globl kexec_control_code_size +.set kexec_control_code_size, . - relocate_kernel diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index 68b48e3fbcb..362d4e7f2d3 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -445,7 +445,7 @@ static void __init reserve_early_setup_data(void) * @size: Size of the crashkernel memory to reserve. * Returns the base address on success, and -1ULL on failure. */ -unsigned long long find_and_reserve_crashkernel(unsigned long long size) +unsigned long long __init find_and_reserve_crashkernel(unsigned long long size) { const unsigned long long alignment = 16<<20; /* 16M */ unsigned long long start = 0LL; @@ -604,14 +604,6 @@ void __init setup_arch(char **cmdline_p) early_cpu_init(); early_ioremap_init(); -#if defined(CONFIG_VMI) && defined(CONFIG_X86_32) - /* - * Must be before kernel pagetables are setup - * or fixmap area is touched. - */ - vmi_init(); -#endif - ROOT_DEV = old_decode_dev(boot_params.hdr.root_dev); screen_info = boot_params.screen_info; edid_info = boot_params.edid_info; @@ -678,6 +670,14 @@ void __init setup_arch(char **cmdline_p) parse_early_param(); +#if defined(CONFIG_VMI) && defined(CONFIG_X86_32) + /* + * Must be before kernel pagetables are setup + * or fixmap area is touched. + */ + vmi_init(); +#endif + /* after early param, so could get panic from serial */ reserve_early_setup_data(); diff --git a/arch/x86/kernel/signal_64.c b/arch/x86/kernel/signal_64.c index b45ef8ddd65..ca316b5b742 100644 --- a/arch/x86/kernel/signal_64.c +++ b/arch/x86/kernel/signal_64.c @@ -104,7 +104,16 @@ static inline int restore_i387(struct _fpstate __user *buf) clts(); task_thread_info(current)->status |= TS_USEDFPU; } - return restore_fpu_checking((__force struct i387_fxsave_struct *)buf); + err = restore_fpu_checking((__force struct i387_fxsave_struct *)buf); + if (unlikely(err)) { + /* + * Encountered an error while doing the restore from the + * user buffer, clear the fpu state. + */ + clear_fpu(tsk); + clear_used_math(); + } + return err; } /* diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index 91055d7fc1b..7985c5b3f91 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -756,6 +756,14 @@ static void __cpuinit do_fork_idle(struct work_struct *work) } #ifdef CONFIG_X86_64 + +/* __ref because it's safe to call free_bootmem when after_bootmem == 0. */ +static void __ref free_bootmem_pda(struct x8664_pda *oldpda) +{ + if (!after_bootmem) + free_bootmem((unsigned long)oldpda, sizeof(*oldpda)); +} + /* * Allocate node local memory for the AP pda. * @@ -784,8 +792,7 @@ int __cpuinit get_local_pda(int cpu) if (oldpda) { memcpy(newpda, oldpda, size); - if (!after_bootmem) - free_bootmem((unsigned long)oldpda, size); + free_bootmem_pda(oldpda); } newpda->in_bootmem = 0; @@ -994,17 +1001,7 @@ int __cpuinit native_cpu_up(unsigned int cpu) flush_tlb_all(); low_mappings = 1; -#ifdef CONFIG_X86_PC - if (def_to_bigsmp && apicid > 8) { - printk(KERN_WARNING - "More than 8 CPUs detected - skipping them.\n" - "Use CONFIG_X86_GENERICARCH and CONFIG_X86_BIGSMP.\n"); - err = -1; - } else - err = do_boot_cpu(apicid, cpu); -#else err = do_boot_cpu(apicid, cpu); -#endif zap_low_mappings(); low_mappings = 0; @@ -1058,6 +1055,34 @@ static __init void disable_smp(void) static int __init smp_sanity_check(unsigned max_cpus) { preempt_disable(); + +#if defined(CONFIG_X86_PC) && defined(CONFIG_X86_32) + if (def_to_bigsmp && nr_cpu_ids > 8) { + unsigned int cpu; + unsigned nr; + + printk(KERN_WARNING + "More than 8 CPUs detected - skipping them.\n" + "Use CONFIG_X86_GENERICARCH and CONFIG_X86_BIGSMP.\n"); + + nr = 0; + for_each_present_cpu(cpu) { + if (nr >= 8) + cpu_clear(cpu, cpu_present_map); + nr++; + } + + nr = 0; + for_each_possible_cpu(cpu) { + if (nr >= 8) + cpu_clear(cpu, cpu_possible_map); + nr++; + } + + nr_cpu_ids = 8; + } +#endif + if (!physid_isset(hard_smp_processor_id(), phys_cpu_present_map)) { printk(KERN_WARNING "weird, boot CPU (#%d) not listed" "by the BIOS.\n", hard_smp_processor_id()); @@ -1196,6 +1221,9 @@ void __init native_smp_prepare_cpus(unsigned int max_cpus) printk(KERN_INFO "CPU%d: ", 0); print_cpu_info(&cpu_data(0)); setup_boot_clock(); + + if (is_uv_system()) + uv_system_init(); out: preempt_enable(); } @@ -1386,17 +1414,3 @@ void __cpu_die(unsigned int cpu) BUG(); } #endif - -/* - * If the BIOS enumerates physical processors before logical, - * maxcpus=N at enumeration-time can be used to disable HT. - */ -static int __init parse_maxcpus(char *arg) -{ - extern unsigned int maxcpus; - - if (arg) - maxcpus = simple_strtoul(arg, NULL, 0); - return 0; -} -early_param("maxcpus", parse_maxcpus); diff --git a/arch/x86/kernel/smpcommon.c b/arch/x86/kernel/smpcommon.c index 99941b37eca..397e309839d 100644 --- a/arch/x86/kernel/smpcommon.c +++ b/arch/x86/kernel/smpcommon.c @@ -8,18 +8,21 @@ DEFINE_PER_CPU(unsigned long, this_cpu_off); EXPORT_PER_CPU_SYMBOL(this_cpu_off); -/* Initialize the CPU's GDT. This is either the boot CPU doing itself - (still using the master per-cpu area), or a CPU doing it for a - secondary which will soon come up. */ +/* + * Initialize the CPU's GDT. This is either the boot CPU doing itself + * (still using the master per-cpu area), or a CPU doing it for a + * secondary which will soon come up. + */ __cpuinit void init_gdt(int cpu) { - struct desc_struct *gdt = get_cpu_gdt_table(cpu); + struct desc_struct gdt; - pack_descriptor(&gdt[GDT_ENTRY_PERCPU], - __per_cpu_offset[cpu], 0xFFFFF, + pack_descriptor(&gdt, __per_cpu_offset[cpu], 0xFFFFF, 0x2 | DESCTYPE_S, 0x8); + gdt.s = 1; - gdt[GDT_ENTRY_PERCPU].s = 1; + write_gdt_entry(get_cpu_gdt_table(cpu), + GDT_ENTRY_PERCPU, &gdt, DESCTYPE_S); per_cpu(this_cpu_off, cpu) = __per_cpu_offset[cpu]; per_cpu(cpu_number, cpu) = cpu; diff --git a/arch/x86/kernel/tlb_uv.c b/arch/x86/kernel/tlb_uv.c index d0fbb7712ab..8b8c0d6640f 100644 --- a/arch/x86/kernel/tlb_uv.c +++ b/arch/x86/kernel/tlb_uv.c @@ -17,6 +17,7 @@ #include <asm/genapic.h> #include <asm/idle.h> #include <asm/tsc.h> +#include <asm/irq_vectors.h> #include <mach_apic.h> @@ -783,7 +784,7 @@ static int __init uv_bau_init(void) uv_init_blade(blade, node, cur_cpu); cur_cpu += uv_blade_nr_possible_cpus(blade); } - set_intr_gate(UV_BAU_MESSAGE, uv_bau_message_intr1); + alloc_intr_gate(UV_BAU_MESSAGE, uv_bau_message_intr1); uv_enable_timeouts(); return 0; diff --git a/arch/x86/kernel/traps_64.c b/arch/x86/kernel/traps_64.c index 3f18d73f420..513caaca711 100644 --- a/arch/x86/kernel/traps_64.c +++ b/arch/x86/kernel/traps_64.c @@ -1131,7 +1131,14 @@ asmlinkage void math_state_restore(void) } clts(); /* Allow maths ops (or we recurse) */ - restore_fpu_checking(&me->thread.xstate->fxsave); + /* + * Paranoid restore. send a SIGSEGV if we fail to restore the state. + */ + if (unlikely(restore_fpu_checking(&me->thread.xstate->fxsave))) { + stts(); + force_sig(SIGSEGV, me); + return; + } task_thread_info(me)->status |= TS_USEDFPU; me->fpu_counter++; } diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c index 7603c055390..46af7167673 100644 --- a/arch/x86/kernel/tsc.c +++ b/arch/x86/kernel/tsc.c @@ -104,7 +104,7 @@ __setup("notsc", notsc_setup); /* * Read TSC and the reference counters. Take care of SMI disturbance */ -static u64 __init tsc_read_refs(u64 *pm, u64 *hpet) +static u64 tsc_read_refs(u64 *pm, u64 *hpet) { u64 t1, t2; int i; diff --git a/arch/x86/kernel/tsc_sync.c b/arch/x86/kernel/tsc_sync.c index 0577825cf89..9ffb01c31c4 100644 --- a/arch/x86/kernel/tsc_sync.c +++ b/arch/x86/kernel/tsc_sync.c @@ -88,11 +88,9 @@ static __cpuinit void check_tsc_warp(void) __raw_spin_unlock(&sync_lock); } } - if (!(now-start)) { - printk("Warning: zero tsc calibration delta: %Ld [max: %Ld]\n", + WARN(!(now-start), + "Warning: zero tsc calibration delta: %Ld [max: %Ld]\n", now-start, end-start); - WARN_ON(1); - } } /* diff --git a/arch/x86/kernel/visws_quirks.c b/arch/x86/kernel/visws_quirks.c index 41e01b145c4..594ef47f0a6 100644 --- a/arch/x86/kernel/visws_quirks.c +++ b/arch/x86/kernel/visws_quirks.c @@ -184,8 +184,6 @@ static int __init visws_get_smp_config(unsigned int early) return 1; } -extern unsigned int __cpuinitdata maxcpus; - /* * The Visual Workstation is Intel MP compliant in the hardware * sense, but it doesn't have a BIOS(-configuration table). @@ -244,8 +242,8 @@ static int __init visws_find_smp_config(unsigned int reserve) ncpus = CO_CPU_MAX; } - if (ncpus > maxcpus) - ncpus = maxcpus; + if (ncpus > setup_max_cpus) + ncpus = setup_max_cpus; #ifdef CONFIG_X86_LOCAL_APIC smp_found_config = 1; diff --git a/arch/x86/kernel/vmlinux_32.lds.S b/arch/x86/kernel/vmlinux_32.lds.S index cdb2363697d..af5bdad8460 100644 --- a/arch/x86/kernel/vmlinux_32.lds.S +++ b/arch/x86/kernel/vmlinux_32.lds.S @@ -209,3 +209,11 @@ SECTIONS DWARF_DEBUG } + +#ifdef CONFIG_KEXEC +/* Link time checks */ +#include <asm/kexec.h> + +ASSERT(kexec_control_code_size <= KEXEC_CONTROL_CODE_MAX_SIZE, + "kexec control code size is too big") +#endif diff --git a/arch/x86/mach-rdc321x/platform.c b/arch/x86/mach-rdc321x/platform.c index a037041817c..4f4e50c3ad3 100644 --- a/arch/x86/mach-rdc321x/platform.c +++ b/arch/x86/mach-rdc321x/platform.c @@ -25,7 +25,6 @@ #include <linux/list.h> #include <linux/device.h> #include <linux/platform_device.h> -#include <linux/version.h> #include <linux/leds.h> #include <asm/gpio.h> diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index 129618ca0ea..d3746efb060 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -60,7 +60,7 @@ static unsigned long dma_reserve __initdata; DEFINE_PER_CPU(struct mmu_gather, mmu_gathers); -int direct_gbpages __meminitdata +int direct_gbpages #ifdef CONFIG_DIRECT_GBPAGES = 1 #endif @@ -88,7 +88,11 @@ early_param("gbpages", parse_direct_gbpages_on); int after_bootmem; -static __init void *spp_getpage(void) +/* + * NOTE: This function is marked __ref because it calls __init function + * (alloc_bootmem_pages). It's safe to do it ONLY when after_bootmem == 0. + */ +static __ref void *spp_getpage(void) { void *ptr; @@ -237,7 +241,7 @@ static unsigned long __initdata table_start; static unsigned long __meminitdata table_end; static unsigned long __meminitdata table_top; -static __meminit void *alloc_low_page(unsigned long *phys) +static __ref void *alloc_low_page(unsigned long *phys) { unsigned long pfn = table_end++; void *adr; @@ -258,7 +262,7 @@ static __meminit void *alloc_low_page(unsigned long *phys) return adr; } -static __meminit void unmap_low_page(void *adr) +static __ref void unmap_low_page(void *adr) { if (after_bootmem) return; @@ -314,6 +318,7 @@ phys_pmd_init(pmd_t *pmd_page, unsigned long address, unsigned long end, { unsigned long pages = 0; unsigned long last_map_addr = end; + unsigned long start = address; int i = pmd_index(address); @@ -331,16 +336,24 @@ phys_pmd_init(pmd_t *pmd_page, unsigned long address, unsigned long end, } if (pmd_val(*pmd)) { - if (!pmd_large(*pmd)) + if (!pmd_large(*pmd)) { + spin_lock(&init_mm.page_table_lock); last_map_addr = phys_pte_update(pmd, address, - end); + end); + spin_unlock(&init_mm.page_table_lock); + } + /* Count entries we're using from level2_ident_pgt */ + if (start == 0) + pages++; continue; } if (page_size_mask & (1<<PG_LEVEL_2M)) { pages++; + spin_lock(&init_mm.page_table_lock); set_pte((pte_t *)pmd, pfn_pte(address >> PAGE_SHIFT, PAGE_KERNEL_LARGE)); + spin_unlock(&init_mm.page_table_lock); last_map_addr = (address & PMD_MASK) + PMD_SIZE; continue; } @@ -349,7 +362,9 @@ phys_pmd_init(pmd_t *pmd_page, unsigned long address, unsigned long end, last_map_addr = phys_pte_init(pte, address, end); unmap_low_page(pte); + spin_lock(&init_mm.page_table_lock); pmd_populate_kernel(&init_mm, pmd, __va(pte_phys)); + spin_unlock(&init_mm.page_table_lock); } update_page_count(PG_LEVEL_2M, pages); return last_map_addr; @@ -362,9 +377,7 @@ phys_pmd_update(pud_t *pud, unsigned long address, unsigned long end, pmd_t *pmd = pmd_offset(pud, 0); unsigned long last_map_addr; - spin_lock(&init_mm.page_table_lock); last_map_addr = phys_pmd_init(pmd, address, end, page_size_mask); - spin_unlock(&init_mm.page_table_lock); __flush_tlb_all(); return last_map_addr; } @@ -400,20 +413,21 @@ phys_pud_init(pud_t *pud_page, unsigned long addr, unsigned long end, if (page_size_mask & (1<<PG_LEVEL_1G)) { pages++; + spin_lock(&init_mm.page_table_lock); set_pte((pte_t *)pud, pfn_pte(addr >> PAGE_SHIFT, PAGE_KERNEL_LARGE)); + spin_unlock(&init_mm.page_table_lock); last_map_addr = (addr & PUD_MASK) + PUD_SIZE; continue; } pmd = alloc_low_page(&pmd_phys); - - spin_lock(&init_mm.page_table_lock); last_map_addr = phys_pmd_init(pmd, addr, end, page_size_mask); unmap_low_page(pmd); + + spin_lock(&init_mm.page_table_lock); pud_populate(&init_mm, pud, __va(pmd_phys)); spin_unlock(&init_mm.page_table_lock); - } __flush_tlb_all(); update_page_count(PG_LEVEL_1G, pages); @@ -505,16 +519,14 @@ static unsigned long __init kernel_physical_mapping_init(unsigned long start, continue; } - if (after_bootmem) - pud = pud_offset(pgd, start & PGDIR_MASK); - else - pud = alloc_low_page(&pud_phys); - + pud = alloc_low_page(&pud_phys); last_map_addr = phys_pud_init(pud, __pa(start), __pa(next), page_size_mask); unmap_low_page(pud); - pgd_populate(&init_mm, pgd_offset_k(start), - __va(pud_phys)); + + spin_lock(&init_mm.page_table_lock); + pgd_populate(&init_mm, pgd, __va(pud_phys)); + spin_unlock(&init_mm.page_table_lock); } return last_map_addr; diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c index 016f335bbee..d4b6e6a29ae 100644 --- a/arch/x86/mm/ioremap.c +++ b/arch/x86/mm/ioremap.c @@ -170,7 +170,7 @@ static void __iomem *__ioremap_caller(resource_size_t phys_addr, phys_addr &= PAGE_MASK; size = PAGE_ALIGN(last_addr+1) - phys_addr; - retval = reserve_memtype(phys_addr, phys_addr + size, + retval = reserve_memtype(phys_addr, (u64)phys_addr + size, prot_val, &new_prot_val); if (retval) { pr_debug("Warning: reserve_memtype returned %d\n", retval); @@ -553,13 +553,11 @@ static int __init check_early_ioremap_leak(void) { if (!early_ioremap_nested) return 0; - - printk(KERN_WARNING + WARN(1, KERN_WARNING "Debug warning: early ioremap leak of %d areas detected.\n", - early_ioremap_nested); + early_ioremap_nested); printk(KERN_WARNING - "please boot with early_ioremap_debug and report the dmesg.\n"); - WARN_ON(1); + "please boot with early_ioremap_debug and report the dmesg.\n"); return 1; } diff --git a/arch/x86/mm/mmio-mod.c b/arch/x86/mm/mmio-mod.c index e7397e108be..635b50e8558 100644 --- a/arch/x86/mm/mmio-mod.c +++ b/arch/x86/mm/mmio-mod.c @@ -430,7 +430,9 @@ static void enter_uniprocessor(void) "may miss events.\n"); } -static void leave_uniprocessor(void) +/* __ref because leave_uniprocessor calls cpu_up which is __cpuinit, + but this whole function is ifdefed CONFIG_HOTPLUG_CPU */ +static void __ref leave_uniprocessor(void) { int cpu; int err; diff --git a/arch/x86/mm/pageattr-test.c b/arch/x86/mm/pageattr-test.c index 0dcd42eb94e..d4aa503caaa 100644 --- a/arch/x86/mm/pageattr-test.c +++ b/arch/x86/mm/pageattr-test.c @@ -221,8 +221,7 @@ static int pageattr_test(void) failed += print_split(&sc); if (failed) { - printk(KERN_ERR "NOT PASSED. Please report.\n"); - WARN_ON(1); + WARN(1, KERN_ERR "NOT PASSED. Please report.\n"); return -EINVAL; } else { if (print) diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c index 65c6e46bf05..43e2f8483e4 100644 --- a/arch/x86/mm/pageattr.c +++ b/arch/x86/mm/pageattr.c @@ -55,13 +55,19 @@ static void split_page_count(int level) int arch_report_meminfo(char *page) { - int n = sprintf(page, "DirectMap4k: %8lu\n" - "DirectMap2M: %8lu\n", - direct_pages_count[PG_LEVEL_4K], - direct_pages_count[PG_LEVEL_2M]); + int n = sprintf(page, "DirectMap4k: %8lu kB\n", + direct_pages_count[PG_LEVEL_4K] << 2); +#if defined(CONFIG_X86_64) || defined(CONFIG_X86_PAE) + n += sprintf(page + n, "DirectMap2M: %8lu kB\n", + direct_pages_count[PG_LEVEL_2M] << 11); +#else + n += sprintf(page + n, "DirectMap4M: %8lu kB\n", + direct_pages_count[PG_LEVEL_2M] << 12); +#endif #ifdef CONFIG_X86_64 - n += sprintf(page + n, "DirectMap1G: %8lu\n", - direct_pages_count[PG_LEVEL_1G]); + if (direct_gbpages) + n += sprintf(page + n, "DirectMap1G: %8lu kB\n", + direct_pages_count[PG_LEVEL_1G] << 20); #endif return n; } @@ -592,10 +598,9 @@ repeat: if (!pte_val(old_pte)) { if (!primary) return 0; - printk(KERN_WARNING "CPA: called for zero pte. " + WARN(1, KERN_WARNING "CPA: called for zero pte. " "vaddr = %lx cpa->vaddr = %lx\n", address, cpa->vaddr); - WARN_ON(1); return -EINVAL; } @@ -844,7 +849,7 @@ int set_memory_uc(unsigned long addr, int numpages) /* * for now UC MINUS. see comments in ioremap_nocache() */ - if (reserve_memtype(addr, addr + numpages * PAGE_SIZE, + if (reserve_memtype(__pa(addr), __pa(addr) + numpages * PAGE_SIZE, _PAGE_CACHE_UC_MINUS, NULL)) return -EINVAL; @@ -863,7 +868,7 @@ int set_memory_wc(unsigned long addr, int numpages) if (!pat_enabled) return set_memory_uc(addr, numpages); - if (reserve_memtype(addr, addr + numpages * PAGE_SIZE, + if (reserve_memtype(__pa(addr), __pa(addr) + numpages * PAGE_SIZE, _PAGE_CACHE_WC, NULL)) return -EINVAL; @@ -879,7 +884,7 @@ int _set_memory_wb(unsigned long addr, int numpages) int set_memory_wb(unsigned long addr, int numpages) { - free_memtype(addr, addr + numpages * PAGE_SIZE); + free_memtype(__pa(addr), __pa(addr) + numpages * PAGE_SIZE); return _set_memory_wb(addr, numpages); } diff --git a/arch/x86/mm/pat.c b/arch/x86/mm/pat.c index 2fe30916d4b..2a50e0fa64a 100644 --- a/arch/x86/mm/pat.c +++ b/arch/x86/mm/pat.c @@ -207,6 +207,9 @@ static int chk_conflict(struct memtype *new, struct memtype *entry, return -EBUSY; } +static struct memtype *cached_entry; +static u64 cached_start; + /* * req_type typically has one of the: * - _PAGE_CACHE_WB @@ -280,11 +283,17 @@ int reserve_memtype(u64 start, u64 end, unsigned long req_type, spin_lock(&memtype_lock); + if (cached_entry && start >= cached_start) + entry = cached_entry; + else + entry = list_entry(&memtype_list, struct memtype, nd); + /* Search for existing mapping that overlaps the current range */ where = NULL; - list_for_each_entry(entry, &memtype_list, nd) { + list_for_each_entry_continue(entry, &memtype_list, nd) { if (end <= entry->start) { where = entry->nd.prev; + cached_entry = list_entry(where, struct memtype, nd); break; } else if (start <= entry->start) { /* end > entry->start */ err = chk_conflict(new, entry, new_type); @@ -292,6 +301,8 @@ int reserve_memtype(u64 start, u64 end, unsigned long req_type, dprintk("Overlap at 0x%Lx-0x%Lx\n", entry->start, entry->end); where = entry->nd.prev; + cached_entry = list_entry(where, + struct memtype, nd); } break; } else if (start < entry->end) { /* start > entry->start */ @@ -299,7 +310,20 @@ int reserve_memtype(u64 start, u64 end, unsigned long req_type, if (!err) { dprintk("Overlap at 0x%Lx-0x%Lx\n", entry->start, entry->end); - where = &entry->nd; + cached_entry = list_entry(entry->nd.prev, + struct memtype, nd); + + /* + * Move to right position in the linked + * list to add this new entry + */ + list_for_each_entry_continue(entry, + &memtype_list, nd) { + if (start <= entry->start) { + where = entry->nd.prev; + break; + } + } } break; } @@ -314,6 +338,8 @@ int reserve_memtype(u64 start, u64 end, unsigned long req_type, return err; } + cached_start = start; + if (where) list_add(&new->nd, where); else @@ -343,6 +369,9 @@ int free_memtype(u64 start, u64 end) spin_lock(&memtype_lock); list_for_each_entry(entry, &memtype_list, nd) { if (entry->start == start && entry->end == end) { + if (cached_entry == entry || cached_start == start) + cached_entry = NULL; + list_del(&entry->nd); kfree(entry); err = 0; @@ -361,14 +390,6 @@ int free_memtype(u64 start, u64 end) } -/* - * /dev/mem mmap interface. The memtype used for mapping varies: - * - Use UC for mappings with O_SYNC flag - * - Without O_SYNC flag, if there is any conflict in reserve_memtype, - * inherit the memtype from existing mapping. - * - Else use UC_MINUS memtype (for backward compatibility with existing - * X drivers. - */ pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn, unsigned long size, pgprot_t vma_prot) { @@ -406,14 +427,14 @@ int phys_mem_access_prot_allowed(struct file *file, unsigned long pfn, unsigned long size, pgprot_t *vma_prot) { u64 offset = ((u64) pfn) << PAGE_SHIFT; - unsigned long flags = _PAGE_CACHE_UC_MINUS; + unsigned long flags = -1; int retval; if (!range_is_allowed(pfn, size)) return 0; if (file->f_flags & O_SYNC) { - flags = _PAGE_CACHE_UC; + flags = _PAGE_CACHE_UC_MINUS; } #ifdef CONFIG_X86_32 @@ -436,13 +457,14 @@ int phys_mem_access_prot_allowed(struct file *file, unsigned long pfn, #endif /* - * With O_SYNC, we can only take UC mapping. Fail if we cannot. + * With O_SYNC, we can only take UC_MINUS mapping. Fail if we cannot. + * * Without O_SYNC, we want to get * - WB for WB-able memory and no other conflicting mappings * - UC_MINUS for non-WB-able memory with no other conflicting mappings * - Inherit from confliting mappings otherwise */ - if (flags != _PAGE_CACHE_UC_MINUS) { + if (flags != -1) { retval = reserve_memtype(offset, offset + size, flags, NULL); } else { retval = reserve_memtype(offset, offset + size, -1, &flags); diff --git a/arch/x86/mm/srat_32.c b/arch/x86/mm/srat_32.c index 1eb2973a301..16ae70fc57e 100644 --- a/arch/x86/mm/srat_32.c +++ b/arch/x86/mm/srat_32.c @@ -178,7 +178,7 @@ void acpi_numa_arch_fixup(void) * start of the node, and that the current "end" address is after * the previous one. */ -static __init void node_read_chunk(int nid, struct node_memory_chunk_s *memory_chunk) +static __init int node_read_chunk(int nid, struct node_memory_chunk_s *memory_chunk) { /* * Only add present memory as told by the e820. @@ -189,10 +189,10 @@ static __init void node_read_chunk(int nid, struct node_memory_chunk_s *memory_c if (memory_chunk->start_pfn >= max_pfn) { printk(KERN_INFO "Ignoring SRAT pfns: %08lx - %08lx\n", memory_chunk->start_pfn, memory_chunk->end_pfn); - return; + return -1; } if (memory_chunk->nid != nid) - return; + return -1; if (!node_has_online_mem(nid)) node_start_pfn[nid] = memory_chunk->start_pfn; @@ -202,6 +202,8 @@ static __init void node_read_chunk(int nid, struct node_memory_chunk_s *memory_c if (node_end_pfn[nid] < memory_chunk->end_pfn) node_end_pfn[nid] = memory_chunk->end_pfn; + + return 0; } int __init get_memcfg_from_srat(void) @@ -259,7 +261,9 @@ int __init get_memcfg_from_srat(void) printk(KERN_DEBUG "chunk %d nid %d start_pfn %08lx end_pfn %08lx\n", j, chunk->nid, chunk->start_pfn, chunk->end_pfn); - node_read_chunk(chunk->nid, chunk); + if (node_read_chunk(chunk->nid, chunk)) + continue; + e820_register_active_regions(chunk->nid, chunk->start_pfn, min(chunk->end_pfn, max_pfn)); } diff --git a/arch/x86/oprofile/nmi_int.c b/arch/x86/oprofile/nmi_int.c index 3f90289410e..0227694f7da 100644 --- a/arch/x86/oprofile/nmi_int.c +++ b/arch/x86/oprofile/nmi_int.c @@ -15,6 +15,7 @@ #include <linux/slab.h> #include <linux/moduleparam.h> #include <linux/kdebug.h> +#include <linux/cpu.h> #include <asm/nmi.h> #include <asm/msr.h> #include <asm/apic.h> @@ -28,23 +29,48 @@ static DEFINE_PER_CPU(unsigned long, saved_lvtpc); static int nmi_start(void); static void nmi_stop(void); +static void nmi_cpu_start(void *dummy); +static void nmi_cpu_stop(void *dummy); /* 0 == registered but off, 1 == registered and on */ static int nmi_enabled = 0; +#ifdef CONFIG_SMP +static int oprofile_cpu_notifier(struct notifier_block *b, unsigned long action, + void *data) +{ + int cpu = (unsigned long)data; + switch (action) { + case CPU_DOWN_FAILED: + case CPU_ONLINE: + smp_call_function_single(cpu, nmi_cpu_start, NULL, 0); + break; + case CPU_DOWN_PREPARE: + smp_call_function_single(cpu, nmi_cpu_stop, NULL, 1); + break; + } + return NOTIFY_DONE; +} + +static struct notifier_block oprofile_cpu_nb = { + .notifier_call = oprofile_cpu_notifier +}; +#endif + #ifdef CONFIG_PM static int nmi_suspend(struct sys_device *dev, pm_message_t state) { + /* Only one CPU left, just stop that one */ if (nmi_enabled == 1) - nmi_stop(); + nmi_cpu_stop(NULL); return 0; } static int nmi_resume(struct sys_device *dev) { if (nmi_enabled == 1) - nmi_start(); + nmi_cpu_start(NULL); return 0; } @@ -463,6 +489,9 @@ int __init op_nmi_init(struct oprofile_operations *ops) } init_sysfs(); +#ifdef CONFIG_SMP + register_cpu_notifier(&oprofile_cpu_nb); +#endif using_nmi = 1; ops->create_files = nmi_create_files; ops->setup = nmi_setup; @@ -476,6 +505,10 @@ int __init op_nmi_init(struct oprofile_operations *ops) void op_nmi_exit(void) { - if (using_nmi) + if (using_nmi) { exit_sysfs(); +#ifdef CONFIG_SMP + unregister_cpu_notifier(&oprofile_cpu_nb); +#endif + } } diff --git a/arch/x86/pci/irq.c b/arch/x86/pci/irq.c index fec0123b33a..8e077185e18 100644 --- a/arch/x86/pci/irq.c +++ b/arch/x86/pci/irq.c @@ -590,6 +590,8 @@ static __init int intel_router_probe(struct irq_router *r, struct pci_dev *route case PCI_DEVICE_ID_INTEL_ICH10_1: case PCI_DEVICE_ID_INTEL_ICH10_2: case PCI_DEVICE_ID_INTEL_ICH10_3: + case PCI_DEVICE_ID_INTEL_PCH_0: + case PCI_DEVICE_ID_INTEL_PCH_1: r->name = "PIIX/ICH"; r->get = pirq_piix_get; r->set = pirq_piix_set; diff --git a/arch/x86/pci/legacy.c b/arch/x86/pci/legacy.c index ec9ce35e44d..b722dd481b3 100644 --- a/arch/x86/pci/legacy.c +++ b/arch/x86/pci/legacy.c @@ -14,7 +14,7 @@ static void __devinit pcibios_fixup_peer_bridges(void) int n, devfn; long node; - if (pcibios_last_bus <= 0 || pcibios_last_bus >= 0xff) + if (pcibios_last_bus <= 0 || pcibios_last_bus > 0xff) return; DBG("PCI: Peer bridge fixup\n"); diff --git a/arch/x86/pci/mmconfig-shared.c b/arch/x86/pci/mmconfig-shared.c index 23faaa890ff..d9635764ce3 100644 --- a/arch/x86/pci/mmconfig-shared.c +++ b/arch/x86/pci/mmconfig-shared.c @@ -293,7 +293,7 @@ static acpi_status __init find_mboard_resource(acpi_handle handle, u32 lvl, return AE_OK; } -static int __init is_acpi_reserved(unsigned long start, unsigned long end) +static int __init is_acpi_reserved(u64 start, u64 end, unsigned not_used) { struct resource mcfg_res; @@ -310,6 +310,41 @@ static int __init is_acpi_reserved(unsigned long start, unsigned long end) return mcfg_res.flags; } +typedef int (*check_reserved_t)(u64 start, u64 end, unsigned type); + +static int __init is_mmconf_reserved(check_reserved_t is_reserved, + u64 addr, u64 size, int i, + typeof(pci_mmcfg_config[0]) *cfg, int with_e820) +{ + u64 old_size = size; + int valid = 0; + + while (!is_reserved(addr, addr + size - 1, E820_RESERVED)) { + size >>= 1; + if (size < (16UL<<20)) + break; + } + + if (size >= (16UL<<20) || size == old_size) { + printk(KERN_NOTICE + "PCI: MCFG area at %Lx reserved in %s\n", + addr, with_e820?"E820":"ACPI motherboard resources"); + valid = 1; + + if (old_size != size) { + /* update end_bus_number */ + cfg->end_bus_number = cfg->start_bus_number + ((size>>20) - 1); + printk(KERN_NOTICE "PCI: updated MCFG configuration %d: base %lx " + "segment %hu buses %u - %u\n", + i, (unsigned long)cfg->address, cfg->pci_segment, + (unsigned int)cfg->start_bus_number, + (unsigned int)cfg->end_bus_number); + } + } + + return valid; +} + static void __init pci_mmcfg_reject_broken(int early) { typeof(pci_mmcfg_config[0]) *cfg; @@ -324,21 +359,22 @@ static void __init pci_mmcfg_reject_broken(int early) for (i = 0; i < pci_mmcfg_config_num; i++) { int valid = 0; - u32 size = (cfg->end_bus_number + 1) << 20; + u64 addr, size; + cfg = &pci_mmcfg_config[i]; + addr = cfg->start_bus_number; + addr <<= 20; + addr += cfg->address; + size = cfg->end_bus_number + 1 - cfg->start_bus_number; + size <<= 20; printk(KERN_NOTICE "PCI: MCFG configuration %d: base %lx " "segment %hu buses %u - %u\n", i, (unsigned long)cfg->address, cfg->pci_segment, (unsigned int)cfg->start_bus_number, (unsigned int)cfg->end_bus_number); - if (!early && - is_acpi_reserved(cfg->address, cfg->address + size - 1)) { - printk(KERN_NOTICE "PCI: MCFG area at %Lx reserved " - "in ACPI motherboard resources\n", - cfg->address); - valid = 1; - } + if (!early) + valid = is_mmconf_reserved(is_acpi_reserved, addr, size, i, cfg, 0); if (valid) continue; @@ -347,16 +383,11 @@ static void __init pci_mmcfg_reject_broken(int early) printk(KERN_ERR "PCI: BIOS Bug: MCFG area at %Lx is not" " reserved in ACPI motherboard resources\n", cfg->address); + /* Don't try to do this check unless configuration type 1 is available. how about type 2 ?*/ - if (raw_pci_ops && e820_all_mapped(cfg->address, - cfg->address + size - 1, - E820_RESERVED)) { - printk(KERN_NOTICE - "PCI: MCFG area at %Lx reserved in E820\n", - cfg->address); - valid = 1; - } + if (raw_pci_ops) + valid = is_mmconf_reserved(e820_all_mapped, addr, size, i, cfg, 1); if (!valid) goto reject; @@ -365,7 +396,7 @@ static void __init pci_mmcfg_reject_broken(int early) return; reject: - printk(KERN_ERR "PCI: Not using MMCONFIG.\n"); + printk(KERN_INFO "PCI: Not using MMCONFIG.\n"); pci_mmcfg_arch_free(); kfree(pci_mmcfg_config); pci_mmcfg_config = NULL; diff --git a/arch/x86/power/cpu_32.c b/arch/x86/power/cpu_32.c index 7dc5d5cf50a..d3e083dea72 100644 --- a/arch/x86/power/cpu_32.c +++ b/arch/x86/power/cpu_32.c @@ -45,7 +45,7 @@ static void __save_processor_state(struct saved_context *ctxt) ctxt->cr0 = read_cr0(); ctxt->cr2 = read_cr2(); ctxt->cr3 = read_cr3(); - ctxt->cr4 = read_cr4(); + ctxt->cr4 = read_cr4_safe(); } /* Needed by apm.c */ @@ -98,7 +98,9 @@ static void __restore_processor_state(struct saved_context *ctxt) /* * control registers */ - write_cr4(ctxt->cr4); + /* cr4 was introduced in the Pentium CPU */ + if (ctxt->cr4) + write_cr4(ctxt->cr4); write_cr3(ctxt->cr3); write_cr2(ctxt->cr2); write_cr0(ctxt->cr0); diff --git a/arch/x86/power/hibernate_asm_32.S b/arch/x86/power/hibernate_asm_32.S index b95aa6cfe3c..4fc7e872c85 100644 --- a/arch/x86/power/hibernate_asm_32.S +++ b/arch/x86/power/hibernate_asm_32.S @@ -28,9 +28,9 @@ ENTRY(swsusp_arch_suspend) ret ENTRY(restore_image) - movl resume_pg_dir, %ecx - subl $__PAGE_OFFSET, %ecx - movl %ecx, %cr3 + movl resume_pg_dir, %eax + subl $__PAGE_OFFSET, %eax + movl %eax, %cr3 movl restore_pblist, %edx .p2align 4,,7 @@ -52,17 +52,21 @@ copy_loop: done: /* go back to the original page tables */ - movl $swapper_pg_dir, %ecx - subl $__PAGE_OFFSET, %ecx - movl %ecx, %cr3 + movl $swapper_pg_dir, %eax + subl $__PAGE_OFFSET, %eax + movl %eax, %cr3 /* Flush TLB, including "global" things (vmalloc) */ - movl mmu_cr4_features, %eax - movl %eax, %edx + movl mmu_cr4_features, %ecx + jecxz 1f # cr4 Pentium and higher, skip if zero + movl %ecx, %edx andl $~(1<<7), %edx; # PGE movl %edx, %cr4; # turn off PGE - movl %cr3, %ecx; # flush TLB - movl %ecx, %cr3 - movl %eax, %cr4; # turn PGE back on +1: + movl %cr3, %eax; # flush TLB + movl %eax, %cr3 + jecxz 1f # cr4 Pentium and higher, skip if zero + movl %ecx, %cr4; # turn PGE back on +1: movl saved_context_esp, %esp movl saved_context_ebp, %ebp |