summaryrefslogtreecommitdiff
path: root/arch/x86
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86')
-rw-r--r--arch/x86/include/asm/msr-index.h1
-rw-r--r--arch/x86/include/asm/suspend_32.h2
-rw-r--r--arch/x86/include/asm/suspend_64.h2
-rw-r--r--arch/x86/include/asm/system.h2
-rw-r--r--arch/x86/kernel/acpi/cstate.c9
-rw-r--r--arch/x86/kernel/acpi/sleep.c2
-rw-r--r--arch/x86/kernel/apic/apic.c2
-rw-r--r--arch/x86/kernel/hpet.c2
-rw-r--r--arch/x86/kernel/pci-calgary_64.c17
-rw-r--r--arch/x86/kernel/traps.c11
-rw-r--r--arch/x86/kvm/mmu.c5
-rw-r--r--arch/x86/kvm/svm.c96
-rw-r--r--arch/x86/power/cpu.c4
13 files changed, 141 insertions, 14 deletions
diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index c51247426dbc..6a95ca18aceb 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -107,6 +107,7 @@
#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/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 e04740f7a0bb..2a19418940bc 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/cstate.c b/arch/x86/kernel/acpi/cstate.c
index 2e837f5080fe..fb7a5f052e2b 100644
--- a/arch/x86/kernel/acpi/cstate.c
+++ b/arch/x86/kernel/acpi/cstate.c
@@ -145,6 +145,15 @@ int acpi_processor_ffh_cstate_probe(unsigned int cpu,
percpu_entry->states[cx->index].eax = cx->address;
percpu_entry->states[cx->index].ecx = MWAIT_ECX_INTERRUPT_BREAK;
}
+
+ /*
+ * For _CST FFH on Intel, if GAS.access_size bit 1 is cleared,
+ * then we should skip checking BM_STS for this C-state.
+ * ref: "Intel Processor Vendor-Specific ACPI Interface Specification"
+ */
+ if ((c->x86_vendor == X86_VENDOR_INTEL) && !(reg->access_size & 0x2))
+ cx->bm_sts_skip = 1;
+
return retval;
}
EXPORT_SYMBOL_GPL(acpi_processor_ffh_cstate_probe);
diff --git a/arch/x86/kernel/acpi/sleep.c b/arch/x86/kernel/acpi/sleep.c
index f9961034e557..82e508677b91 100644
--- a/arch/x86/kernel/acpi/sleep.c
+++ b/arch/x86/kernel/acpi/sleep.c
@@ -162,8 +162,6 @@ static int __init acpi_sleep_setup(char *str)
#endif
if (strncmp(str, "old_ordering", 12) == 0)
acpi_old_suspend_ordering();
- if (strncmp(str, "sci_force_enable", 16) == 0)
- acpi_set_sci_en_on_resume();
str = strchr(str, ',');
if (str != NULL)
str += strspn(str, ", \t");
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index d4df51725290..7718bb3c97bf 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -920,7 +920,7 @@ void disable_local_APIC(void)
unsigned int value;
/* APIC hasn't been mapped yet */
- if (!apic_phys)
+ if (!x2apic_mode && !apic_phys)
return;
clear_local_APIC();
diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c
index 773afc9274a1..241c5b24b349 100644
--- a/arch/x86/kernel/hpet.c
+++ b/arch/x86/kernel/hpet.c
@@ -958,7 +958,7 @@ fs_initcall(hpet_late_init);
void hpet_disable(void)
{
- if (is_hpet_capable()) {
+ if (is_hpet_capable() && hpet_virt_address) {
unsigned int cfg = hpet_readl(HPET_CFG);
if (hpet_legacy_int_enabled) {
diff --git a/arch/x86/kernel/pci-calgary_64.c b/arch/x86/kernel/pci-calgary_64.c
index 2bbde6078143..aa740faa7eaa 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 256
+
+#define PHBS_PER_CALGARY 4
/* register offsets in Calgary's internal register space */
static const unsigned long tar_offsets[] = {
@@ -1051,8 +1056,6 @@ static int __init calgary_init_one(struct pci_dev *dev)
struct iommu_table *tbl;
int ret;
- BUG_ON(dev->bus->number >= MAX_PHB_BUS_NUM);
-
bbar = busno_to_bbar(dev->bus->number);
ret = calgary_setup_tar(dev, bbar);
if (ret)
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index 9288ccfcf6db..bd4308cf644d 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -531,11 +531,20 @@ asmlinkage __kprobes struct pt_regs *sync_regs(struct pt_regs *eregs)
dotraplinkage void __kprobes do_debug(struct pt_regs *regs, long error_code)
{
struct task_struct *tsk = current;
+ int user_icebp = 0;
unsigned long dr6;
int si_code;
get_debugreg(dr6, 6);
+ /*
+ * If dr6 has no reason to give us about the origin of this trap,
+ * then it's very likely the result of an icebp/int01 trap.
+ * User wants a sigtrap for that.
+ */
+ if (!(dr6 & ~0xffff0ff0) && user_mode(regs))
+ user_icebp = 1;
+
/* Catch kmemcheck conditions first of all! */
if ((dr6 & DR_STEP) && kmemcheck_trap(regs))
return;
@@ -577,7 +586,7 @@ dotraplinkage void __kprobes do_debug(struct pt_regs *regs, long error_code)
regs->flags &= ~X86_EFLAGS_TF;
}
si_code = get_si_code(tsk->thread.debugreg6);
- if (tsk->thread.debugreg6 & (DR_STEP | DR_TRAP_BITS))
+ if (tsk->thread.debugreg6 & (DR_STEP | DR_TRAP_BITS) || user_icebp)
send_sigtrap(tsk, regs, error_code, si_code);
preempt_conditional_cli(regs, DEBUG_STACK);
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index 88220210ed5e..ca7c5282addd 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -1849,6 +1849,9 @@ 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
@@ -1904,6 +1907,8 @@ 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 a2f839cbad01..8d128be24ddd 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -27,6 +27,7 @@
#include <linux/sched.h>
#include <linux/ftrace_event.h>
+#include <asm/tlbflush.h>
#include <asm/desc.h>
#include <asm/virtext.h>
@@ -54,6 +55,8 @@ 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,
@@ -297,6 +300,31 @@ static void skip_emulated_instruction(struct kvm_vcpu *vcpu)
svm_set_interrupt_shadow(vcpu, 0);
}
+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;
@@ -352,6 +380,8 @@ 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;
}
@@ -1255,8 +1285,59 @@ 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.
@@ -1265,6 +1346,11 @@ 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;
}
@@ -2820,6 +2906,14 @@ 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/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
*/