aboutsummaryrefslogtreecommitdiffstats
path: root/arch/x86/kernel
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86/kernel')
-rw-r--r--arch/x86/kernel/asm-offsets_32.c3
-rw-r--r--arch/x86/kernel/asm-offsets_64.c1
-rw-r--r--arch/x86/kernel/cpu/perf_event_intel.c13
-rw-r--r--arch/x86/kernel/cpu/perf_event_intel_lbr.c27
-rw-r--r--arch/x86/kernel/cpu/perf_event_intel_uncore.c19
-rw-r--r--arch/x86/kernel/early-quirks.c20
-rw-r--r--arch/x86/kernel/entry_64.S5
-rw-r--r--arch/x86/kernel/head64.c3
-rw-r--r--arch/x86/kernel/head_64.S1
-rw-r--r--arch/x86/kernel/irq.c26
-rw-r--r--arch/x86/kernel/irqinit.c4
-rw-r--r--arch/x86/kernel/kvmclock.c9
12 files changed, 107 insertions, 24 deletions
diff --git a/arch/x86/kernel/asm-offsets_32.c b/arch/x86/kernel/asm-offsets_32.c
index 85d98ab..0ef4bba 100644
--- a/arch/x86/kernel/asm-offsets_32.c
+++ b/arch/x86/kernel/asm-offsets_32.c
@@ -60,6 +60,9 @@ void foo(void)
OFFSET(IA32_RT_SIGFRAME_sigcontext, rt_sigframe, uc.uc_mcontext);
BLANK();
+ OFFSET(saved_context_gdt_desc, saved_context, gdt_desc);
+ BLANK();
+
/* Offset from the sysenter stack to tss.sp0 */
DEFINE(TSS_sysenter_sp0, offsetof(struct tss_struct, x86_tss.sp0) -
sizeof(struct tss_struct));
diff --git a/arch/x86/kernel/asm-offsets_64.c b/arch/x86/kernel/asm-offsets_64.c
index 1b4754f..e7c798b 100644
--- a/arch/x86/kernel/asm-offsets_64.c
+++ b/arch/x86/kernel/asm-offsets_64.c
@@ -73,6 +73,7 @@ int main(void)
ENTRY(cr3);
ENTRY(cr4);
ENTRY(cr8);
+ ENTRY(gdt_desc);
BLANK();
#undef ENTRY
diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index ffd6050..f60d41f 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -128,10 +128,15 @@ static struct event_constraint intel_ivb_event_constraints[] __read_mostly =
INTEL_UEVENT_CONSTRAINT(0x08a3, 0x4), /* CYCLE_ACTIVITY.CYCLES_L1D_PENDING */
INTEL_UEVENT_CONSTRAINT(0x0ca3, 0x4), /* CYCLE_ACTIVITY.STALLS_L1D_PENDING */
INTEL_UEVENT_CONSTRAINT(0x01c0, 0x2), /* INST_RETIRED.PREC_DIST */
- INTEL_EVENT_CONSTRAINT(0xd0, 0xf), /* MEM_UOPS_RETIRED.* */
- INTEL_EVENT_CONSTRAINT(0xd1, 0xf), /* MEM_LOAD_UOPS_RETIRED.* */
- INTEL_EVENT_CONSTRAINT(0xd2, 0xf), /* MEM_LOAD_UOPS_LLC_HIT_RETIRED.* */
- INTEL_EVENT_CONSTRAINT(0xd3, 0xf), /* MEM_LOAD_UOPS_LLC_MISS_RETIRED.* */
+ /*
+ * Errata BV98 -- MEM_*_RETIRED events can leak between counters of SMT
+ * siblings; disable these events because they can corrupt unrelated
+ * counters.
+ */
+ INTEL_EVENT_CONSTRAINT(0xd0, 0x0), /* MEM_UOPS_RETIRED.* */
+ INTEL_EVENT_CONSTRAINT(0xd1, 0x0), /* MEM_LOAD_UOPS_RETIRED.* */
+ INTEL_EVENT_CONSTRAINT(0xd2, 0x0), /* MEM_LOAD_UOPS_LLC_HIT_RETIRED.* */
+ INTEL_EVENT_CONSTRAINT(0xd3, 0x0), /* MEM_LOAD_UOPS_LLC_MISS_RETIRED.* */
EVENT_CONSTRAINT_END
};
diff --git a/arch/x86/kernel/cpu/perf_event_intel_lbr.c b/arch/x86/kernel/cpu/perf_event_intel_lbr.c
index da02e9c..d978353 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_lbr.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_lbr.c
@@ -310,7 +310,7 @@ void intel_pmu_lbr_read(void)
* - in case there is no HW filter
* - in case the HW filter has errata or limitations
*/
-static void intel_pmu_setup_sw_lbr_filter(struct perf_event *event)
+static int intel_pmu_setup_sw_lbr_filter(struct perf_event *event)
{
u64 br_type = event->attr.branch_sample_type;
int mask = 0;
@@ -318,8 +318,11 @@ static void intel_pmu_setup_sw_lbr_filter(struct perf_event *event)
if (br_type & PERF_SAMPLE_BRANCH_USER)
mask |= X86_BR_USER;
- if (br_type & PERF_SAMPLE_BRANCH_KERNEL)
+ if (br_type & PERF_SAMPLE_BRANCH_KERNEL) {
+ if (perf_paranoid_kernel() && !capable(CAP_SYS_ADMIN))
+ return -EACCES;
mask |= X86_BR_KERNEL;
+ }
/* we ignore BRANCH_HV here */
@@ -339,6 +342,8 @@ static void intel_pmu_setup_sw_lbr_filter(struct perf_event *event)
* be used by fixup code for some CPU
*/
event->hw.branch_reg.reg = mask;
+
+ return 0;
}
/*
@@ -386,7 +391,9 @@ int intel_pmu_setup_lbr_filter(struct perf_event *event)
/*
* setup SW LBR filter
*/
- intel_pmu_setup_sw_lbr_filter(event);
+ ret = intel_pmu_setup_sw_lbr_filter(event);
+ if (ret)
+ return ret;
/*
* setup HW LBR filter, if any
@@ -442,8 +449,18 @@ static int branch_type(unsigned long from, unsigned long to)
return X86_BR_NONE;
addr = buf;
- } else
- addr = (void *)from;
+ } else {
+ /*
+ * The LBR logs any address in the IP, even if the IP just
+ * faulted. This means userspace can control the from address.
+ * Ensure we don't blindy read any address by validating it is
+ * a known text address.
+ */
+ if (kernel_text_address(from))
+ addr = (void *)from;
+ else
+ return X86_BR_NONE;
+ }
/*
* decoder needs to know the ABI especially
diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.c b/arch/x86/kernel/cpu/perf_event_intel_uncore.c
index d0f9e5a..52441a2 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_uncore.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.c
@@ -3093,7 +3093,7 @@ static void __init uncore_types_exit(struct intel_uncore_type **types)
static int __init uncore_type_init(struct intel_uncore_type *type)
{
struct intel_uncore_pmu *pmus;
- struct attribute_group *events_group;
+ struct attribute_group *attr_group;
struct attribute **attrs;
int i, j;
@@ -3120,19 +3120,19 @@ static int __init uncore_type_init(struct intel_uncore_type *type)
while (type->event_descs[i].attr.attr.name)
i++;
- events_group = kzalloc(sizeof(struct attribute *) * (i + 1) +
- sizeof(*events_group), GFP_KERNEL);
- if (!events_group)
+ attr_group = kzalloc(sizeof(struct attribute *) * (i + 1) +
+ sizeof(*attr_group), GFP_KERNEL);
+ if (!attr_group)
goto fail;
- attrs = (struct attribute **)(events_group + 1);
- events_group->name = "events";
- events_group->attrs = attrs;
+ attrs = (struct attribute **)(attr_group + 1);
+ attr_group->name = "events";
+ attr_group->attrs = attrs;
for (j = 0; j < i; j++)
attrs[j] = &type->event_descs[j].attr.attr;
- type->events_group = events_group;
+ type->events_group = attr_group;
}
type->pmu_group = &uncore_pmu_attr_group;
@@ -3545,11 +3545,12 @@ static int __init uncore_cpu_init(void)
msr_uncores = nhm_msr_uncores;
break;
case 42: /* Sandy Bridge */
+ case 58: /* Ivy Bridge */
if (snb_uncore_cbox.num_boxes > max_cores)
snb_uncore_cbox.num_boxes = max_cores;
msr_uncores = snb_msr_uncores;
break;
- case 45: /* Sandy Birdge-EP */
+ case 45: /* Sandy Bridge-EP */
if (snbep_uncore_cbox.num_boxes > max_cores)
snbep_uncore_cbox.num_boxes = max_cores;
msr_uncores = snbep_msr_uncores;
diff --git a/arch/x86/kernel/early-quirks.c b/arch/x86/kernel/early-quirks.c
index 3755ef4..94ab6b9 100644
--- a/arch/x86/kernel/early-quirks.c
+++ b/arch/x86/kernel/early-quirks.c
@@ -18,6 +18,7 @@
#include <asm/apic.h>
#include <asm/iommu.h>
#include <asm/gart.h>
+#include <asm/irq_remapping.h>
static void __init fix_hypertransport_config(int num, int slot, int func)
{
@@ -192,6 +193,21 @@ static void __init ati_bugs_contd(int num, int slot, int func)
}
#endif
+static void __init intel_remapping_check(int num, int slot, int func)
+{
+ u8 revision;
+
+ revision = read_pci_config_byte(num, slot, func, PCI_REVISION_ID);
+
+ /*
+ * Revision 0x13 of this chipset supports irq remapping
+ * but has an erratum that breaks its behavior, flag it as such
+ */
+ if (revision == 0x13)
+ set_irq_remapping_broken();
+
+}
+
#define QFLAG_APPLY_ONCE 0x1
#define QFLAG_APPLIED 0x2
#define QFLAG_DONE (QFLAG_APPLY_ONCE|QFLAG_APPLIED)
@@ -221,6 +237,10 @@ static struct chipset early_qrk[] __initdata = {
PCI_CLASS_SERIAL_SMBUS, PCI_ANY_ID, 0, ati_bugs },
{ PCI_VENDOR_ID_ATI, PCI_DEVICE_ID_ATI_SBX00_SMBUS,
PCI_CLASS_SERIAL_SMBUS, PCI_ANY_ID, 0, ati_bugs_contd },
+ { PCI_VENDOR_ID_INTEL, 0x3403, PCI_CLASS_BRIDGE_HOST,
+ PCI_BASE_CLASS_BRIDGE, 0, intel_remapping_check },
+ { PCI_VENDOR_ID_INTEL, 0x3406, PCI_CLASS_BRIDGE_HOST,
+ PCI_BASE_CLASS_BRIDGE, 0, intel_remapping_check },
{}
};
diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S
index c1d01e6..7272089 100644
--- a/arch/x86/kernel/entry_64.S
+++ b/arch/x86/kernel/entry_64.S
@@ -1166,6 +1166,11 @@ apicinterrupt LOCAL_TIMER_VECTOR \
apicinterrupt X86_PLATFORM_IPI_VECTOR \
x86_platform_ipi smp_x86_platform_ipi
+#ifdef CONFIG_HAVE_KVM
+apicinterrupt POSTED_INTR_VECTOR \
+ kvm_posted_intr_ipi smp_kvm_posted_intr_ipi
+#endif
+
apicinterrupt THRESHOLD_APIC_VECTOR \
threshold_interrupt smp_threshold_interrupt
apicinterrupt THERMAL_APIC_VECTOR \
diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c
index 101ac1a9..dab95a8 100644
--- a/arch/x86/kernel/head64.c
+++ b/arch/x86/kernel/head64.c
@@ -34,6 +34,7 @@
extern pgd_t early_level4_pgt[PTRS_PER_PGD];
extern pmd_t early_dynamic_pgts[EARLY_DYNAMIC_PAGE_TABLES][PTRS_PER_PMD];
static unsigned int __initdata next_early_pgt = 2;
+pmdval_t __initdata early_pmd_flags = __PAGE_KERNEL_LARGE & ~(_PAGE_GLOBAL | _PAGE_NX);
/* Wipe all early page tables except for the kernel symbol map */
static void __init reset_early_page_tables(void)
@@ -99,7 +100,7 @@ again:
pmd_p[i] = 0;
*pud_p = (pudval_t)pmd_p - __START_KERNEL_map + phys_base + _KERNPG_TABLE;
}
- pmd = (physaddr & PMD_MASK) + (__PAGE_KERNEL_LARGE & ~_PAGE_GLOBAL);
+ pmd = (physaddr & PMD_MASK) + early_pmd_flags;
pmd_p[pmd_index(address)] = pmd;
return 0;
diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S
index 6859e96..08f7e80 100644
--- a/arch/x86/kernel/head_64.S
+++ b/arch/x86/kernel/head_64.S
@@ -200,6 +200,7 @@ ENTRY(secondary_startup_64)
btl $20,%edi /* No Execute supported? */
jnc 1f
btsl $_EFER_NX, %eax
+ btsq $_PAGE_BIT_NX,early_pmd_flags(%rip)
1: wrmsr /* Make changes effective */
/* Setup cr0 */
diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c
index e4595f1..ac0631d 100644
--- a/arch/x86/kernel/irq.c
+++ b/arch/x86/kernel/irq.c
@@ -165,10 +165,6 @@ u64 arch_irq_stat_cpu(unsigned int cpu)
u64 arch_irq_stat(void)
{
u64 sum = atomic_read(&irq_err_count);
-
-#ifdef CONFIG_X86_IO_APIC
- sum += atomic_read(&irq_mis_count);
-#endif
return sum;
}
@@ -228,6 +224,28 @@ void smp_x86_platform_ipi(struct pt_regs *regs)
set_irq_regs(old_regs);
}
+#ifdef CONFIG_HAVE_KVM
+/*
+ * Handler for POSTED_INTERRUPT_VECTOR.
+ */
+void smp_kvm_posted_intr_ipi(struct pt_regs *regs)
+{
+ struct pt_regs *old_regs = set_irq_regs(regs);
+
+ ack_APIC_irq();
+
+ irq_enter();
+
+ exit_idle();
+
+ inc_irq_stat(kvm_posted_intr_ipis);
+
+ irq_exit();
+
+ set_irq_regs(old_regs);
+}
+#endif
+
EXPORT_SYMBOL_GPL(vector_used_by_percpu_irq);
#ifdef CONFIG_HOTPLUG_CPU
diff --git a/arch/x86/kernel/irqinit.c b/arch/x86/kernel/irqinit.c
index 7dc4e45..a2a1fbc 100644
--- a/arch/x86/kernel/irqinit.c
+++ b/arch/x86/kernel/irqinit.c
@@ -172,6 +172,10 @@ static void __init apic_intr_init(void)
/* IPI for X86 platform specific use */
alloc_intr_gate(X86_PLATFORM_IPI_VECTOR, x86_platform_ipi);
+#ifdef CONFIG_HAVE_KVM
+ /* IPI for KVM to deliver posted interrupt */
+ alloc_intr_gate(POSTED_INTR_VECTOR, kvm_posted_intr_ipi);
+#endif
/* IPI vectors for APIC spurious and error interrupts */
alloc_intr_gate(SPURIOUS_APIC_VECTOR, spurious_interrupt);
diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c
index 0732f00..d2c3812 100644
--- a/arch/x86/kernel/kvmclock.c
+++ b/arch/x86/kernel/kvmclock.c
@@ -160,8 +160,12 @@ int kvm_register_clock(char *txt)
{
int cpu = smp_processor_id();
int low, high, ret;
- struct pvclock_vcpu_time_info *src = &hv_clock[cpu].pvti;
+ struct pvclock_vcpu_time_info *src;
+
+ if (!hv_clock)
+ return 0;
+ src = &hv_clock[cpu].pvti;
low = (int)slow_virt_to_phys(src) | 1;
high = ((u64)slow_virt_to_phys(src) >> 32);
ret = native_write_msr_safe(msr_kvm_system_time, low, high);
@@ -276,6 +280,9 @@ int __init kvm_setup_vsyscall_timeinfo(void)
struct pvclock_vcpu_time_info *vcpu_time;
unsigned int size;
+ if (!hv_clock)
+ return 0;
+
size = PAGE_ALIGN(sizeof(struct pvclock_vsyscall_time_info)*NR_CPUS);
preempt_disable();
generated by cgit v1.1 at 2024-12-26 11:09:42 +0000