diff options
Diffstat (limited to 'arch/x86')
32 files changed, 240 insertions, 68 deletions
diff --git a/arch/x86/boot/video-vga.c b/arch/x86/boot/video-vga.c index ed7aeff786b2..45bc9402aa49 100644 --- a/arch/x86/boot/video-vga.c +++ b/arch/x86/boot/video-vga.c @@ -41,13 +41,12 @@ static __videocard video_vga; static u8 vga_set_basic_mode(void) { struct biosregs ireg, oreg; - u16 ax; u8 mode; initregs(&ireg); /* Query current mode */ - ax = 0x0f00; + ireg.ax = 0x0f00; intcall(0x10, &ireg, &oreg); mode = oreg.al; diff --git a/arch/x86/include/asm/io_apic.h b/arch/x86/include/asm/io_apic.h index 63cb4096c3dc..9cb2edb87c2f 100644 --- a/arch/x86/include/asm/io_apic.h +++ b/arch/x86/include/asm/io_apic.h @@ -183,7 +183,7 @@ struct mp_ioapic_gsi{ u32 gsi_end; }; extern struct mp_ioapic_gsi mp_gsi_routing[]; -extern u32 gsi_end; +extern u32 gsi_top; int mp_find_ioapic(u32 gsi); int mp_find_ioapic_pin(int ioapic, u32 gsi); void __init mp_register_ioapic(int id, u32 address, u32 gsi_base); @@ -197,7 +197,7 @@ static const int timer_through_8259 = 0; static inline void ioapic_init_mappings(void) { } static inline void ioapic_insert_resources(void) { } static inline void probe_nr_irqs_gsi(void) { } -#define gsi_end (NR_IRQS_LEGACY - 1) +#define gsi_top (NR_IRQS_LEGACY) static inline int mp_find_ioapic(u32 gsi) { return 0; } struct io_apic_irq_attr; diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index b49d8ca228f6..8c7ae4318629 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -110,6 +110,7 @@ #define MSR_AMD64_PATCH_LOADER 0xc0010020 #define MSR_AMD64_OSVW_ID_LENGTH 0xc0010140 #define MSR_AMD64_OSVW_STATUS 0xc0010141 +#define MSR_AMD64_DC_CFG 0xc0011022 #define MSR_AMD64_IBSFETCHCTL 0xc0011030 #define MSR_AMD64_IBSFETCHLINAD 0xc0011031 #define MSR_AMD64_IBSFETCHPHYSAD 0xc0011032 diff --git a/arch/x86/include/asm/pci_x86.h b/arch/x86/include/asm/pci_x86.h index 8d8797eae5d7..cd2a31dc5fb8 100644 --- a/arch/x86/include/asm/pci_x86.h +++ b/arch/x86/include/asm/pci_x86.h @@ -53,6 +53,8 @@ extern int pcibios_last_bus; extern struct pci_bus *pci_root_bus; extern struct pci_ops pci_root_ops; +void pcibios_scan_specific_bus(int busn); + /* pci-irq.c */ struct irq_info { diff --git a/arch/x86/include/asm/percpu.h b/arch/x86/include/asm/percpu.h index 0797e748d280..cd28f9ad910d 100644 --- a/arch/x86/include/asm/percpu.h +++ b/arch/x86/include/asm/percpu.h @@ -77,6 +77,7 @@ do { \ if (0) { \ pto_T__ pto_tmp__; \ pto_tmp__ = (val); \ + (void)pto_tmp__; \ } \ switch (sizeof(var)) { \ case 1: \ @@ -115,6 +116,7 @@ do { \ if (0) { \ pao_T__ pao_tmp__; \ pao_tmp__ = (val); \ + (void)pao_tmp__; \ } \ switch (sizeof(var)) { \ case 1: \ diff --git a/arch/x86/include/asm/pgtable_32_types.h b/arch/x86/include/asm/pgtable_32_types.h index 5e67c1532314..ed5903be26fe 100644 --- a/arch/x86/include/asm/pgtable_32_types.h +++ b/arch/x86/include/asm/pgtable_32_types.h @@ -26,7 +26,7 @@ */ #define VMALLOC_OFFSET (8 * 1024 * 1024) -#ifndef __ASSEMBLER__ +#ifndef __ASSEMBLY__ extern bool __vmalloc_start_set; /* set once high_memory is set */ #endif diff --git a/arch/x86/include/asm/suspend_32.h b/arch/x86/include/asm/suspend_32.h index 48dcfa62ea07..fd921c3a6841 100644 --- a/arch/x86/include/asm/suspend_32.h +++ b/arch/x86/include/asm/suspend_32.h @@ -15,6 +15,8 @@ static inline int arch_prepare_suspend(void) { return 0; } struct saved_context { u16 es, fs, gs, ss; unsigned long cr0, cr2, cr3, cr4; + u64 misc_enable; + bool misc_enable_saved; struct desc_ptr gdt; struct desc_ptr idt; u16 ldt; diff --git a/arch/x86/include/asm/suspend_64.h b/arch/x86/include/asm/suspend_64.h index 06284f42b759..8d942afae681 100644 --- a/arch/x86/include/asm/suspend_64.h +++ b/arch/x86/include/asm/suspend_64.h @@ -27,6 +27,8 @@ struct saved_context { u16 ds, es, fs, gs, ss; unsigned long gs_base, gs_kernel_base, fs_base; unsigned long cr0, cr2, cr3, cr4, cr8; + u64 misc_enable; + bool misc_enable_saved; unsigned long efer; u16 gdt_pad; u16 gdt_limit; diff --git a/arch/x86/include/asm/system.h b/arch/x86/include/asm/system.h index b8fe48ee2ed9..e7f4d33c55ed 100644 --- a/arch/x86/include/asm/system.h +++ b/arch/x86/include/asm/system.h @@ -451,7 +451,7 @@ void stop_this_cpu(void *dummy); * * (Could use an alternative three way for this if there was one.) */ -static inline void rdtsc_barrier(void) +static __always_inline void rdtsc_barrier(void) { alternative(ASM_NOP3, "mfence", X86_FEATURE_MFENCE_RDTSC); alternative(ASM_NOP3, "lfence", X86_FEATURE_LFENCE_RDTSC); diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c index 60cc4058ed5f..c05872aa3ce0 100644 --- a/arch/x86/kernel/acpi/boot.c +++ b/arch/x86/kernel/acpi/boot.c @@ -118,7 +118,7 @@ static unsigned int gsi_to_irq(unsigned int gsi) if (gsi >= NR_IRQS_LEGACY) irq = gsi; else - irq = gsi_end + 1 + gsi; + irq = gsi_top + gsi; return irq; } @@ -129,10 +129,10 @@ static u32 irq_to_gsi(int irq) if (irq < NR_IRQS_LEGACY) gsi = isa_irq_to_gsi[irq]; - else if (irq <= gsi_end) + else if (irq < gsi_top) gsi = irq; - else if (irq <= (gsi_end + NR_IRQS_LEGACY)) - gsi = irq - gsi_end; + else if (irq < (gsi_top + NR_IRQS_LEGACY)) + gsi = irq - gsi_top; else gsi = 0xffffffff; diff --git a/arch/x86/kernel/amd_iommu.c b/arch/x86/kernel/amd_iommu.c index fa5a1474cd18..0d20286d78c6 100644 --- a/arch/x86/kernel/amd_iommu.c +++ b/arch/x86/kernel/amd_iommu.c @@ -1487,6 +1487,7 @@ static int __attach_device(struct device *dev, struct protection_domain *domain) { struct iommu_dev_data *dev_data, *alias_data; + int ret; dev_data = get_dev_data(dev); alias_data = get_dev_data(dev_data->alias); @@ -1498,13 +1499,14 @@ static int __attach_device(struct device *dev, spin_lock(&domain->lock); /* Some sanity checks */ + ret = -EBUSY; if (alias_data->domain != NULL && alias_data->domain != domain) - return -EBUSY; + goto out_unlock; if (dev_data->domain != NULL && dev_data->domain != domain) - return -EBUSY; + goto out_unlock; /* Do real assignment */ if (dev_data->alias != dev) { @@ -1520,10 +1522,14 @@ static int __attach_device(struct device *dev, atomic_inc(&dev_data->bind); + ret = 0; + +out_unlock: + /* ready */ spin_unlock(&domain->lock); - return 0; + return ret; } /* @@ -2324,10 +2330,6 @@ int __init amd_iommu_init_dma_ops(void) iommu_detected = 1; swiotlb = 0; -#ifdef CONFIG_GART_IOMMU - gart_iommu_aperture_disabled = 1; - gart_iommu_aperture = 0; -#endif /* Make the driver finally visible to the drivers */ dma_ops = &amd_iommu_dma_ops; diff --git a/arch/x86/kernel/amd_iommu_init.c b/arch/x86/kernel/amd_iommu_init.c index 3bacb4d0844c..3cc63e2b8dd4 100644 --- a/arch/x86/kernel/amd_iommu_init.c +++ b/arch/x86/kernel/amd_iommu_init.c @@ -287,8 +287,12 @@ static u8 * __init iommu_map_mmio_space(u64 address) { u8 *ret; - if (!request_mem_region(address, MMIO_REGION_LENGTH, "amd_iommu")) + if (!request_mem_region(address, MMIO_REGION_LENGTH, "amd_iommu")) { + pr_err("AMD-Vi: Can not reserve memory region %llx for mmio\n", + address); + pr_err("AMD-Vi: This is a BIOS bug. Please contact your hardware vendor\n"); return NULL; + } ret = ioremap_nocache(address, MMIO_REGION_LENGTH); if (ret != NULL) @@ -1314,7 +1318,7 @@ static int __init amd_iommu_init(void) ret = amd_iommu_init_dma_ops(); if (ret) - goto free; + goto free_disable; amd_iommu_init_api(); @@ -1332,9 +1336,10 @@ static int __init amd_iommu_init(void) out: return ret; -free: +free_disable: disable_iommus(); +free: amd_iommu_uninit_devices(); free_pages((unsigned long)amd_iommu_pd_alloc_bitmap, @@ -1353,6 +1358,15 @@ free: free_unity_maps(); +#ifdef CONFIG_GART_IOMMU + /* + * We failed to initialize the AMD IOMMU - try fallback to GART + * if possible. + */ + gart_iommu_init(); + +#endif + goto out; } diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c index 33f3563a2a52..e41ed24ab26d 100644 --- a/arch/x86/kernel/apic/io_apic.c +++ b/arch/x86/kernel/apic/io_apic.c @@ -89,8 +89,8 @@ int nr_ioapics; /* IO APIC gsi routing info */ struct mp_ioapic_gsi mp_gsi_routing[MAX_IO_APICS]; -/* The last gsi number used */ -u32 gsi_end; +/* The one past the highest gsi number used */ +u32 gsi_top; /* MP IRQ source entries */ struct mpc_intsrc mp_irqs[MAX_IRQ_SOURCES]; @@ -1035,7 +1035,7 @@ static int pin_2_irq(int idx, int apic, int pin) if (gsi >= NR_IRQS_LEGACY) irq = gsi; else - irq = gsi_end + 1 + gsi; + irq = gsi_top + gsi; } #ifdef CONFIG_X86_32 @@ -3853,7 +3853,7 @@ void __init probe_nr_irqs_gsi(void) { int nr; - nr = gsi_end + 1 + NR_IRQS_LEGACY; + nr = gsi_top + NR_IRQS_LEGACY; if (nr > nr_irqs_gsi) nr_irqs_gsi = nr; @@ -4294,8 +4294,8 @@ void __init mp_register_ioapic(int id, u32 address, u32 gsi_base) */ nr_ioapic_registers[idx] = entries; - if (mp_gsi_routing[idx].gsi_end > gsi_end) - gsi_end = mp_gsi_routing[idx].gsi_end; + if (mp_gsi_routing[idx].gsi_end >= gsi_top) + gsi_top = mp_gsi_routing[idx].gsi_end + 1; printk(KERN_INFO "IOAPIC[%d]: apic_id %d, version %d, address 0x%x, " "GSI %d-%d\n", idx, mp_ioapics[idx].apicid, diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c index 707165dbc203..18cc42562250 100644 --- a/arch/x86/kernel/cpu/mcheck/mce.c +++ b/arch/x86/kernel/cpu/mcheck/mce.c @@ -36,6 +36,7 @@ #include <linux/fs.h> #include <linux/mm.h> #include <linux/debugfs.h> +#include <linux/edac_mce.h> #include <asm/processor.h> #include <asm/hw_irq.h> @@ -169,6 +170,15 @@ void mce_log(struct mce *mce) entry = rcu_dereference_check_mce(mcelog.next); for (;;) { /* + * If edac_mce is enabled, it will check the error type + * and will process it, if it is a known error. + * Otherwise, the error will be sent through mcelog + * interface + */ + if (edac_mce_parse(mce)) + return; + + /* * When the buffer fills up discard new entries. * Assume that the earlier errors are the more * interesting ones: diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c index c77586061bcb..5db5b7d65a18 100644 --- a/arch/x86/kernel/cpu/perf_event.c +++ b/arch/x86/kernel/cpu/perf_event.c @@ -106,6 +106,7 @@ struct cpu_hw_events { int n_events; int n_added; + int n_txn; int assign[X86_PMC_IDX_MAX]; /* event to counter assignment */ u64 tags[X86_PMC_IDX_MAX]; struct perf_event *event_list[X86_PMC_IDX_MAX]; /* in enabled order */ @@ -983,6 +984,7 @@ static int x86_pmu_enable(struct perf_event *event) out: cpuc->n_events = n; cpuc->n_added += n - n0; + cpuc->n_txn += n - n0; return 0; } @@ -1089,6 +1091,14 @@ static void x86_pmu_disable(struct perf_event *event) struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); int i; + /* + * If we're called during a txn, we don't need to do anything. + * The events never got scheduled and ->cancel_txn will truncate + * the event_list. + */ + if (cpuc->group_flag & PERF_EVENT_TXN_STARTED) + return; + x86_pmu_stop(event); for (i = 0; i < cpuc->n_events; i++) { @@ -1379,6 +1389,7 @@ static void x86_pmu_start_txn(const struct pmu *pmu) struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); cpuc->group_flag |= PERF_EVENT_TXN_STARTED; + cpuc->n_txn = 0; } /* @@ -1391,6 +1402,11 @@ static void x86_pmu_cancel_txn(const struct pmu *pmu) struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); cpuc->group_flag &= ~PERF_EVENT_TXN_STARTED; + /* + * Truncate the collected events. + */ + cpuc->n_added -= cpuc->n_txn; + cpuc->n_events -= cpuc->n_txn; } /* @@ -1419,6 +1435,12 @@ static int x86_pmu_commit_txn(const struct pmu *pmu) */ memcpy(cpuc->assign, assign, n*sizeof(int)); + /* + * Clear out the txn count so that ->cancel_txn() which gets + * run after ->commit_txn() doesn't undo things. + */ + cpuc->n_txn = 0; + return 0; } diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c index fdbc652d3feb..214ac860ebe0 100644 --- a/arch/x86/kernel/cpu/perf_event_intel.c +++ b/arch/x86/kernel/cpu/perf_event_intel.c @@ -72,6 +72,7 @@ static struct event_constraint intel_westmere_event_constraints[] = INTEL_EVENT_CONSTRAINT(0x51, 0x3), /* L1D */ INTEL_EVENT_CONSTRAINT(0x60, 0x1), /* OFFCORE_REQUESTS_OUTSTANDING */ INTEL_EVENT_CONSTRAINT(0x63, 0x3), /* CACHE_LOCK_CYCLES */ + INTEL_EVENT_CONSTRAINT(0xb3, 0x1), /* SNOOPQ_REQUEST_OUTSTANDING */ EVENT_CONSTRAINT_END }; diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c index 7bca3c6a02fb..0d6fc71bedb1 100644 --- a/arch/x86/kernel/e820.c +++ b/arch/x86/kernel/e820.c @@ -729,7 +729,7 @@ static int __init e820_mark_nvs_memory(void) struct e820entry *ei = &e820.map[i]; if (ei->type == E820_NVS) - hibernate_nvs_register(ei->addr, ei->size); + suspend_nvs_register(ei->addr, ei->size); } return 0; diff --git a/arch/x86/kernel/mpparse.c b/arch/x86/kernel/mpparse.c index 5ae5d2426edf..d86dbf7e54be 100644 --- a/arch/x86/kernel/mpparse.c +++ b/arch/x86/kernel/mpparse.c @@ -123,7 +123,7 @@ static void __init MP_ioapic_info(struct mpc_ioapic *m) printk(KERN_INFO "I/O APIC #%d Version %d at 0x%X.\n", m->apicid, m->apicver, m->apicaddr); - mp_register_ioapic(m->apicid, m->apicaddr, gsi_end + 1); + mp_register_ioapic(m->apicid, m->apicaddr, gsi_top); } static void print_MP_intsrc_info(struct mpc_intsrc *m) diff --git a/arch/x86/kernel/pci-calgary_64.c b/arch/x86/kernel/pci-calgary_64.c index fb99f7edb341..0b96b5589f08 100644 --- a/arch/x86/kernel/pci-calgary_64.c +++ b/arch/x86/kernel/pci-calgary_64.c @@ -103,11 +103,16 @@ int use_calgary __read_mostly = 0; #define PMR_SOFTSTOPFAULT 0x40000000 #define PMR_HARDSTOP 0x20000000 -#define MAX_NUM_OF_PHBS 8 /* how many PHBs in total? */ -#define MAX_NUM_CHASSIS 8 /* max number of chassis */ -/* MAX_PHB_BUS_NUM is the maximal possible dev->bus->number */ -#define MAX_PHB_BUS_NUM (MAX_NUM_OF_PHBS * MAX_NUM_CHASSIS * 2) -#define PHBS_PER_CALGARY 4 +/* + * The maximum PHB bus number. + * x3950M2 (rare): 8 chassis, 48 PHBs per chassis = 384 + * x3950M2: 4 chassis, 48 PHBs per chassis = 192 + * x3950 (PCIE): 8 chassis, 32 PHBs per chassis = 256 + * x3950 (PCIX): 8 chassis, 16 PHBs per chassis = 128 + */ +#define MAX_PHB_BUS_NUM 384 + +#define PHBS_PER_CALGARY 4 /* register offsets in Calgary's internal register space */ static const unsigned long tar_offsets[] = { diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c index 8e1aac86b50c..e3af342fe83a 100644 --- a/arch/x86/kernel/reboot.c +++ b/arch/x86/kernel/reboot.c @@ -228,6 +228,14 @@ static struct dmi_system_id __initdata reboot_dmi_table[] = { DMI_MATCH(DMI_PRODUCT_NAME, "Precision WorkStation T5400"), }, }, + { /* Handle problems with rebooting on Dell T7400's */ + .callback = set_bios_reboot, + .ident = "Dell Precision T7400", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."), + DMI_MATCH(DMI_PRODUCT_NAME, "Precision WorkStation T7400"), + }, + }, { /* Handle problems with rebooting on HP laptops */ .callback = set_bios_reboot, .ident = "HP Compaq Laptop", diff --git a/arch/x86/kernel/setup_percpu.c b/arch/x86/kernel/setup_percpu.c index cf592767812e..de3b63ae3da2 100644 --- a/arch/x86/kernel/setup_percpu.c +++ b/arch/x86/kernel/setup_percpu.c @@ -21,12 +21,6 @@ #include <asm/cpu.h> #include <asm/stackprotector.h> -#ifdef CONFIG_DEBUG_PER_CPU_MAPS -# define DBG(fmt, ...) pr_dbg(fmt, ##__VA_ARGS__) -#else -# define DBG(fmt, ...) do { if (0) pr_dbg(fmt, ##__VA_ARGS__); } while (0) -#endif - DEFINE_PER_CPU(int, cpu_number); EXPORT_PER_CPU_SYMBOL(cpu_number); diff --git a/arch/x86/kernel/sfi.c b/arch/x86/kernel/sfi.c index 7ded57896c0a..cb22acf3ed09 100644 --- a/arch/x86/kernel/sfi.c +++ b/arch/x86/kernel/sfi.c @@ -93,7 +93,7 @@ static int __init sfi_parse_ioapic(struct sfi_table_header *table) pentry = (struct sfi_apic_table_entry *)sb->pentry; for (i = 0; i < num; i++) { - mp_register_ioapic(i, pentry->phys_addr, gsi_end + 1); + mp_register_ioapic(i, pentry->phys_addr, gsi_top); pentry++; } diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index 37462f1ddba5..c4f33b2e77d6 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -686,7 +686,7 @@ static void __cpuinit do_fork_idle(struct work_struct *work) static void __cpuinit announce_cpu(int cpu, int apicid) { static int current_node = -1; - int node = cpu_to_node(cpu); + int node = early_cpu_to_node(cpu); if (system_state == SYSTEM_BOOTING) { if (node != current_node) { diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index 81563e76e28f..a6f695d76928 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -1815,6 +1815,9 @@ static int set_spte(struct kvm_vcpu *vcpu, u64 *sptep, spte |= PT_WRITABLE_MASK; + if (!tdp_enabled && !(pte_access & ACC_WRITE_MASK)) + spte &= ~PT_USER_MASK; + /* * Optimization: for pte sync, if spte was writable the hash * lookup is unnecessary (and expensive). Write protection @@ -1870,6 +1873,8 @@ static void mmu_set_spte(struct kvm_vcpu *vcpu, u64 *sptep, child = page_header(pte & PT64_BASE_ADDR_MASK); mmu_page_remove_parent_pte(child, sptep); + __set_spte(sptep, shadow_trap_nonpresent_pte); + kvm_flush_remote_tlbs(vcpu->kvm); } else if (pfn != spte_to_pfn(*sptep)) { pgprintk("hfn old %lx new %lx\n", spte_to_pfn(*sptep), pfn); diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index 96dc232bfc56..ce438e0fdd26 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -28,6 +28,7 @@ #include <linux/ftrace_event.h> #include <linux/slab.h> +#include <asm/tlbflush.h> #include <asm/desc.h> #include <asm/virtext.h> @@ -56,6 +57,8 @@ MODULE_LICENSE("GPL"); #define DEBUGCTL_RESERVED_BITS (~(0x3fULL)) +static bool erratum_383_found __read_mostly; + static const u32 host_save_user_msrs[] = { #ifdef CONFIG_X86_64 MSR_STAR, MSR_LSTAR, MSR_CSTAR, MSR_SYSCALL_MASK, MSR_KERNEL_GS_BASE, @@ -374,6 +377,31 @@ static void svm_queue_exception(struct kvm_vcpu *vcpu, unsigned nr, svm->vmcb->control.event_inj_err = error_code; } +static void svm_init_erratum_383(void) +{ + u32 low, high; + int err; + u64 val; + + /* Only Fam10h is affected */ + if (boot_cpu_data.x86 != 0x10) + return; + + /* Use _safe variants to not break nested virtualization */ + val = native_read_msr_safe(MSR_AMD64_DC_CFG, &err); + if (err) + return; + + val |= (1ULL << 47); + + low = lower_32_bits(val); + high = upper_32_bits(val); + + native_write_msr_safe(MSR_AMD64_DC_CFG, low, high); + + erratum_383_found = true; +} + static int has_svm(void) { const char *msg; @@ -429,6 +457,8 @@ static int svm_hardware_enable(void *garbage) wrmsrl(MSR_VM_HSAVE_PA, page_to_pfn(sd->save_area) << PAGE_SHIFT); + svm_init_erratum_383(); + return 0; } @@ -1410,8 +1440,59 @@ static int nm_interception(struct vcpu_svm *svm) return 1; } -static int mc_interception(struct vcpu_svm *svm) +static bool is_erratum_383(void) { + int err, i; + u64 value; + + if (!erratum_383_found) + return false; + + value = native_read_msr_safe(MSR_IA32_MC0_STATUS, &err); + if (err) + return false; + + /* Bit 62 may or may not be set for this mce */ + value &= ~(1ULL << 62); + + if (value != 0xb600000000010015ULL) + return false; + + /* Clear MCi_STATUS registers */ + for (i = 0; i < 6; ++i) + native_write_msr_safe(MSR_IA32_MCx_STATUS(i), 0, 0); + + value = native_read_msr_safe(MSR_IA32_MCG_STATUS, &err); + if (!err) { + u32 low, high; + + value &= ~(1ULL << 2); + low = lower_32_bits(value); + high = upper_32_bits(value); + + native_write_msr_safe(MSR_IA32_MCG_STATUS, low, high); + } + + /* Flush tlb to evict multi-match entries */ + __flush_tlb_all(); + + return true; +} + +static void svm_handle_mce(struct vcpu_svm *svm) +{ + if (is_erratum_383()) { + /* + * Erratum 383 triggered. Guest state is corrupt so kill the + * guest. + */ + pr_err("KVM: Guest triggered AMD Erratum 383\n"); + + set_bit(KVM_REQ_TRIPLE_FAULT, &svm->vcpu.requests); + + return; + } + /* * On an #MC intercept the MCE handler is not called automatically in * the host. So do it by hand here. @@ -1420,6 +1501,11 @@ static int mc_interception(struct vcpu_svm *svm) "int $0x12\n"); /* not sure if we ever come back to this point */ + return; +} + +static int mc_interception(struct vcpu_svm *svm) +{ return 1; } @@ -3088,6 +3174,14 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu) vcpu->arch.regs_avail &= ~(1 << VCPU_EXREG_PDPTR); vcpu->arch.regs_dirty &= ~(1 << VCPU_EXREG_PDPTR); } + + /* + * We need to handle MC intercepts here before the vcpu has a chance to + * change the physical cpu + */ + if (unlikely(svm->vmcb->control.exit_code == + SVM_EXIT_EXCP_BASE + MC_VECTOR)) + svm_handle_mce(svm); } #undef R diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c index 550df481accd..787c52ca49c3 100644 --- a/arch/x86/mm/numa.c +++ b/arch/x86/mm/numa.c @@ -3,12 +3,6 @@ #include <linux/module.h> #include <linux/bootmem.h> -#ifdef CONFIG_DEBUG_PER_CPU_MAPS -# define DBG(x...) printk(KERN_DEBUG x) -#else -# define DBG(x...) -#endif - /* * Which logical CPUs are on which nodes */ diff --git a/arch/x86/mm/pat.c b/arch/x86/mm/pat.c index acc15b23b743..64121a18b8cb 100644 --- a/arch/x86/mm/pat.c +++ b/arch/x86/mm/pat.c @@ -302,7 +302,7 @@ int reserve_memtype(u64 start, u64 end, unsigned long req_type, return -EINVAL; } - new = kmalloc(sizeof(struct memtype), GFP_KERNEL); + new = kzalloc(sizeof(struct memtype), GFP_KERNEL); if (!new) return -ENOMEM; diff --git a/arch/x86/mm/pat_rbtree.c b/arch/x86/mm/pat_rbtree.c index f537087bb740..f20eeec85a86 100644 --- a/arch/x86/mm/pat_rbtree.c +++ b/arch/x86/mm/pat_rbtree.c @@ -226,6 +226,7 @@ int rbt_memtype_check_insert(struct memtype *new, unsigned long *ret_type) if (ret_type) new->type = *ret_type; + new->subtree_max_end = new->end; memtype_rb_insert(&memtype_rbroot, new); } return err; diff --git a/arch/x86/pci/i386.c b/arch/x86/pci/i386.c index 97da2ba9344b..6fdb3ec30c31 100644 --- a/arch/x86/pci/i386.c +++ b/arch/x86/pci/i386.c @@ -96,6 +96,7 @@ EXPORT_SYMBOL(pcibios_align_resource); * the fact the PCI specs explicitly allow address decoders to be * shared between expansion ROMs and other resource regions, it's * at least dangerous) + * - bad resource sizes or overlaps with other regions * * Our solution: * (1) Allocate resources for all buses behind PCI-to-PCI bridges. @@ -136,6 +137,7 @@ static void __init pcibios_allocate_bus_resources(struct list_head *bus_list) * child resource allocations in this * range. */ + r->start = r->end = 0; r->flags = 0; } } diff --git a/arch/x86/pci/legacy.c b/arch/x86/pci/legacy.c index 0db5eaf54560..8d460eaf524f 100644 --- a/arch/x86/pci/legacy.c +++ b/arch/x86/pci/legacy.c @@ -11,28 +11,14 @@ */ static void __devinit pcibios_fixup_peer_bridges(void) { - int n, devfn; - long node; + int n; if (pcibios_last_bus <= 0 || pcibios_last_bus > 0xff) return; DBG("PCI: Peer bridge fixup\n"); - for (n=0; n <= pcibios_last_bus; n++) { - u32 l; - if (pci_find_bus(0, n)) - continue; - node = get_mp_bus_to_node(n); - for (devfn = 0; devfn < 256; devfn += 8) { - if (!raw_pci_read(0, n, devfn, PCI_VENDOR_ID, 2, &l) && - l != 0x0000 && l != 0xffff) { - DBG("Found device at %02x:%02x [%04x]\n", n, devfn, l); - printk(KERN_INFO "PCI: Discovered peer bus %02x\n", n); - pci_scan_bus_on_node(n, &pci_root_ops, node); - break; - } - } - } + for (n=0; n <= pcibios_last_bus; n++) + pcibios_scan_specific_bus(n); } int __init pci_legacy_init(void) @@ -50,6 +36,28 @@ int __init pci_legacy_init(void) return 0; } +void pcibios_scan_specific_bus(int busn) +{ + int devfn; + long node; + u32 l; + + if (pci_find_bus(0, busn)) + return; + + node = get_mp_bus_to_node(busn); + for (devfn = 0; devfn < 256; devfn += 8) { + if (!raw_pci_read(0, busn, devfn, PCI_VENDOR_ID, 2, &l) && + l != 0x0000 && l != 0xffff) { + DBG("Found device at %02x:%02x [%04x]\n", busn, devfn, l); + printk(KERN_INFO "PCI: Discovered peer bus %02x\n", busn); + pci_scan_bus_on_node(busn, &pci_root_ops, node); + return; + } + } +} +EXPORT_SYMBOL_GPL(pcibios_scan_specific_bus); + int __init pci_subsys_init(void) { /* diff --git a/arch/x86/power/cpu.c b/arch/x86/power/cpu.c index 0a979f3e5b8a..1290ba54b350 100644 --- a/arch/x86/power/cpu.c +++ b/arch/x86/power/cpu.c @@ -105,6 +105,8 @@ static void __save_processor_state(struct saved_context *ctxt) ctxt->cr4 = read_cr4(); ctxt->cr8 = read_cr8(); #endif + ctxt->misc_enable_saved = !rdmsrl_safe(MSR_IA32_MISC_ENABLE, + &ctxt->misc_enable); } /* Needed by apm.c */ @@ -152,6 +154,8 @@ static void fix_processor_context(void) */ static void __restore_processor_state(struct saved_context *ctxt) { + if (ctxt->misc_enable_saved) + wrmsrl(MSR_IA32_MISC_ENABLE, ctxt->misc_enable); /* * control registers */ diff --git a/arch/x86/xen/suspend.c b/arch/x86/xen/suspend.c index 987267f79bf5..a9c661108034 100644 --- a/arch/x86/xen/suspend.c +++ b/arch/x86/xen/suspend.c @@ -60,6 +60,6 @@ static void xen_vcpu_notify_restore(void *data) void xen_arch_resume(void) { - smp_call_function(xen_vcpu_notify_restore, - (void *)CLOCK_EVT_NOTIFY_RESUME, 1); + on_each_cpu(xen_vcpu_notify_restore, + (void *)CLOCK_EVT_NOTIFY_RESUME, 1); } |