summaryrefslogtreecommitdiff
path: root/arch/x86
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86')
-rw-r--r--arch/x86/kernel/cpu/intel.c22
-rw-r--r--arch/x86/kernel/cpu/intel_cacheinfo.c12
-rw-r--r--arch/x86/kernel/cpu/mcheck/mce.c10
-rw-r--r--arch/x86/kernel/cpu/perf_event.c3
-rw-r--r--arch/x86/kernel/cpu/perf_event.h12
-rw-r--r--arch/x86/kernel/cpu/perf_event_intel.c69
-rw-r--r--arch/x86/kernel/cpu/perf_event_intel_ds.c6
-rw-r--r--arch/x86/kernel/cpu/perf_event_intel_uncore.c11
-rw-r--r--arch/x86/kernel/entry_32.S9
-rw-r--r--arch/x86/kernel/kprobes/core.c3
-rw-r--r--arch/x86/kvm/x86.c12
11 files changed, 137 insertions, 32 deletions
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index a80029035bf2..f9e4fdd3b877 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -370,6 +370,17 @@ static void init_intel(struct cpuinfo_x86 *c)
*/
detect_extended_topology(c);
+ if (!cpu_has(c, X86_FEATURE_XTOPOLOGY)) {
+ /*
+ * let's use the legacy cpuid vector 0x1 and 0x4 for topology
+ * detection.
+ */
+ c->x86_max_cores = intel_num_cpu_cores(c);
+#ifdef CONFIG_X86_32
+ detect_ht(c);
+#endif
+ }
+
l2 = init_intel_cacheinfo(c);
if (c->cpuid_level > 9) {
unsigned eax = cpuid_eax(10);
@@ -438,17 +449,6 @@ static void init_intel(struct cpuinfo_x86 *c)
set_cpu_cap(c, X86_FEATURE_P3);
#endif
- if (!cpu_has(c, X86_FEATURE_XTOPOLOGY)) {
- /*
- * let's use the legacy cpuid vector 0x1 and 0x4 for topology
- * detection.
- */
- c->x86_max_cores = intel_num_cpu_cores(c);
-#ifdef CONFIG_X86_32
- detect_ht(c);
-#endif
- }
-
/* Work around errata */
srat_detect_node(c);
diff --git a/arch/x86/kernel/cpu/intel_cacheinfo.c b/arch/x86/kernel/cpu/intel_cacheinfo.c
index a952e9c85b6f..9c8f7394c612 100644
--- a/arch/x86/kernel/cpu/intel_cacheinfo.c
+++ b/arch/x86/kernel/cpu/intel_cacheinfo.c
@@ -730,6 +730,18 @@ unsigned int init_intel_cacheinfo(struct cpuinfo_x86 *c)
#endif
}
+#ifdef CONFIG_X86_HT
+ /*
+ * If cpu_llc_id is not yet set, this means cpuid_level < 4 which in
+ * turns means that the only possibility is SMT (as indicated in
+ * cpuid1). Since cpuid2 doesn't specify shared caches, and we know
+ * that SMT shares all caches, we can unconditionally set cpu_llc_id to
+ * c->phys_proc_id.
+ */
+ if (per_cpu(cpu_llc_id, cpu) == BAD_APICID)
+ per_cpu(cpu_llc_id, cpu) = c->phys_proc_id;
+#endif
+
c->x86_cache_size = l3 ? l3 : (l2 ? l2 : (l1i+l1d));
return l2;
diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index bb92f38153b2..9a79c8dbd8e8 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -2451,6 +2451,12 @@ static __init int mcheck_init_device(void)
for_each_online_cpu(i) {
err = mce_device_create(i);
if (err) {
+ /*
+ * Register notifier anyway (and do not unreg it) so
+ * that we don't leave undeleted timers, see notifier
+ * callback above.
+ */
+ __register_hotcpu_notifier(&mce_cpu_notifier);
cpu_notifier_register_done();
goto err_device_create;
}
@@ -2471,10 +2477,6 @@ static __init int mcheck_init_device(void)
err_register:
unregister_syscore_ops(&mce_syscore_ops);
- cpu_notifier_register_begin();
- __unregister_hotcpu_notifier(&mce_cpu_notifier);
- cpu_notifier_register_done();
-
err_device_create:
/*
* We didn't keep track of which devices were created above, but
diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index 2bdfbff8a4f6..2879ecdaac43 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -118,6 +118,9 @@ static int x86_pmu_extra_regs(u64 config, struct perf_event *event)
continue;
if (event->attr.config1 & ~er->valid_mask)
return -EINVAL;
+ /* Check if the extra msrs can be safely accessed*/
+ if (!er->extra_msr_access)
+ return -ENXIO;
reg->idx = er->idx;
reg->config = event->attr.config1;
diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h
index 3b2f9bdd974b..8ade93111e03 100644
--- a/arch/x86/kernel/cpu/perf_event.h
+++ b/arch/x86/kernel/cpu/perf_event.h
@@ -295,14 +295,16 @@ struct extra_reg {
u64 config_mask;
u64 valid_mask;
int idx; /* per_xxx->regs[] reg index */
+ bool extra_msr_access;
};
#define EVENT_EXTRA_REG(e, ms, m, vm, i) { \
- .event = (e), \
- .msr = (ms), \
- .config_mask = (m), \
- .valid_mask = (vm), \
- .idx = EXTRA_REG_##i, \
+ .event = (e), \
+ .msr = (ms), \
+ .config_mask = (m), \
+ .valid_mask = (vm), \
+ .idx = EXTRA_REG_##i, \
+ .extra_msr_access = true, \
}
#define INTEL_EVENT_EXTRA_REG(event, msr, vm, idx) \
diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index 07846d738bdb..2502d0d9d246 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -2182,6 +2182,41 @@ static void intel_snb_check_microcode(void)
}
}
+/*
+ * Under certain circumstances, access certain MSR may cause #GP.
+ * The function tests if the input MSR can be safely accessed.
+ */
+static bool check_msr(unsigned long msr, u64 mask)
+{
+ u64 val_old, val_new, val_tmp;
+
+ /*
+ * Read the current value, change it and read it back to see if it
+ * matches, this is needed to detect certain hardware emulators
+ * (qemu/kvm) that don't trap on the MSR access and always return 0s.
+ */
+ if (rdmsrl_safe(msr, &val_old))
+ return false;
+
+ /*
+ * Only change the bits which can be updated by wrmsrl.
+ */
+ val_tmp = val_old ^ mask;
+ if (wrmsrl_safe(msr, val_tmp) ||
+ rdmsrl_safe(msr, &val_new))
+ return false;
+
+ if (val_new != val_tmp)
+ return false;
+
+ /* Here it's sure that the MSR can be safely accessed.
+ * Restore the old value and return.
+ */
+ wrmsrl(msr, val_old);
+
+ return true;
+}
+
static __init void intel_sandybridge_quirk(void)
{
x86_pmu.check_microcode = intel_snb_check_microcode;
@@ -2271,7 +2306,8 @@ __init int intel_pmu_init(void)
union cpuid10_ebx ebx;
struct event_constraint *c;
unsigned int unused;
- int version;
+ struct extra_reg *er;
+ int version, i;
if (!cpu_has(&boot_cpu_data, X86_FEATURE_ARCH_PERFMON)) {
switch (boot_cpu_data.x86) {
@@ -2474,6 +2510,9 @@ __init int intel_pmu_init(void)
case 62: /* IvyBridge EP */
memcpy(hw_cache_event_ids, snb_hw_cache_event_ids,
sizeof(hw_cache_event_ids));
+ /* dTLB-load-misses on IVB is different than SNB */
+ hw_cache_event_ids[C(DTLB)][C(OP_READ)][C(RESULT_MISS)] = 0x8108; /* DTLB_LOAD_MISSES.DEMAND_LD_MISS_CAUSES_A_WALK */
+
memcpy(hw_cache_extra_regs, snb_hw_cache_extra_regs,
sizeof(hw_cache_extra_regs));
@@ -2574,6 +2613,34 @@ __init int intel_pmu_init(void)
}
}
+ /*
+ * Access LBR MSR may cause #GP under certain circumstances.
+ * E.g. KVM doesn't support LBR MSR
+ * Check all LBT MSR here.
+ * Disable LBR access if any LBR MSRs can not be accessed.
+ */
+ if (x86_pmu.lbr_nr && !check_msr(x86_pmu.lbr_tos, 0x3UL))
+ x86_pmu.lbr_nr = 0;
+ for (i = 0; i < x86_pmu.lbr_nr; i++) {
+ if (!(check_msr(x86_pmu.lbr_from + i, 0xffffUL) &&
+ check_msr(x86_pmu.lbr_to + i, 0xffffUL)))
+ x86_pmu.lbr_nr = 0;
+ }
+
+ /*
+ * Access extra MSR may cause #GP under certain circumstances.
+ * E.g. KVM doesn't support offcore event
+ * Check all extra_regs here.
+ */
+ if (x86_pmu.extra_regs) {
+ for (er = x86_pmu.extra_regs; er->msr; er++) {
+ er->extra_msr_access = check_msr(er->msr, 0x1ffUL);
+ /* Disable LBR select mapping */
+ if ((er->idx == EXTRA_REG_LBR) && !er->extra_msr_access)
+ x86_pmu.lbr_sel_map = NULL;
+ }
+ }
+
/* Support full width counters using alternative MSR range */
if (x86_pmu.intel_cap.full_width_write) {
x86_pmu.max_period = x86_pmu.cntval_mask;
diff --git a/arch/x86/kernel/cpu/perf_event_intel_ds.c b/arch/x86/kernel/cpu/perf_event_intel_ds.c
index 980970cb744d..696ade311ded 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_ds.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_ds.c
@@ -311,9 +311,11 @@ static int alloc_bts_buffer(int cpu)
if (!x86_pmu.bts)
return 0;
- buffer = kzalloc_node(BTS_BUFFER_SIZE, GFP_KERNEL, node);
- if (unlikely(!buffer))
+ buffer = kzalloc_node(BTS_BUFFER_SIZE, GFP_KERNEL | __GFP_NOWARN, node);
+ if (unlikely(!buffer)) {
+ WARN_ONCE(1, "%s: BTS buffer allocation failure\n", __func__);
return -ENOMEM;
+ }
max = BTS_BUFFER_SIZE / BTS_RECORD_SIZE;
thresh = max / 16;
diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.c b/arch/x86/kernel/cpu/perf_event_intel_uncore.c
index 65bbbea38b9c..ae6552a0701f 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_uncore.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.c
@@ -550,16 +550,16 @@ static struct extra_reg snbep_uncore_cbox_extra_regs[] = {
SNBEP_CBO_EVENT_EXTRA_REG(0x4134, 0xffff, 0x6),
SNBEP_CBO_EVENT_EXTRA_REG(0x0135, 0xffff, 0x8),
SNBEP_CBO_EVENT_EXTRA_REG(0x0335, 0xffff, 0x8),
- SNBEP_CBO_EVENT_EXTRA_REG(0x4135, 0xffff, 0xc),
- SNBEP_CBO_EVENT_EXTRA_REG(0x4335, 0xffff, 0xc),
+ SNBEP_CBO_EVENT_EXTRA_REG(0x4135, 0xffff, 0xa),
+ SNBEP_CBO_EVENT_EXTRA_REG(0x4335, 0xffff, 0xa),
SNBEP_CBO_EVENT_EXTRA_REG(0x4435, 0xffff, 0x2),
SNBEP_CBO_EVENT_EXTRA_REG(0x4835, 0xffff, 0x2),
SNBEP_CBO_EVENT_EXTRA_REG(0x4a35, 0xffff, 0x2),
SNBEP_CBO_EVENT_EXTRA_REG(0x5035, 0xffff, 0x2),
SNBEP_CBO_EVENT_EXTRA_REG(0x0136, 0xffff, 0x8),
SNBEP_CBO_EVENT_EXTRA_REG(0x0336, 0xffff, 0x8),
- SNBEP_CBO_EVENT_EXTRA_REG(0x4136, 0xffff, 0xc),
- SNBEP_CBO_EVENT_EXTRA_REG(0x4336, 0xffff, 0xc),
+ SNBEP_CBO_EVENT_EXTRA_REG(0x4136, 0xffff, 0xa),
+ SNBEP_CBO_EVENT_EXTRA_REG(0x4336, 0xffff, 0xa),
SNBEP_CBO_EVENT_EXTRA_REG(0x4436, 0xffff, 0x2),
SNBEP_CBO_EVENT_EXTRA_REG(0x4836, 0xffff, 0x2),
SNBEP_CBO_EVENT_EXTRA_REG(0x4a36, 0xffff, 0x2),
@@ -1222,6 +1222,7 @@ static struct extra_reg ivt_uncore_cbox_extra_regs[] = {
SNBEP_CBO_EVENT_EXTRA_REG(SNBEP_CBO_PMON_CTL_TID_EN,
SNBEP_CBO_PMON_CTL_TID_EN, 0x1),
SNBEP_CBO_EVENT_EXTRA_REG(0x1031, 0x10ff, 0x2),
+
SNBEP_CBO_EVENT_EXTRA_REG(0x1134, 0xffff, 0x4),
SNBEP_CBO_EVENT_EXTRA_REG(0x4134, 0xffff, 0xc),
SNBEP_CBO_EVENT_EXTRA_REG(0x5134, 0xffff, 0xc),
@@ -1245,7 +1246,7 @@ static struct extra_reg ivt_uncore_cbox_extra_regs[] = {
SNBEP_CBO_EVENT_EXTRA_REG(0x8335, 0xffff, 0x10),
SNBEP_CBO_EVENT_EXTRA_REG(0x0136, 0xffff, 0x10),
SNBEP_CBO_EVENT_EXTRA_REG(0x0336, 0xffff, 0x10),
- SNBEP_CBO_EVENT_EXTRA_REG(0x2336, 0xffff, 0x10),
+ SNBEP_CBO_EVENT_EXTRA_REG(0x2136, 0xffff, 0x10),
SNBEP_CBO_EVENT_EXTRA_REG(0x2336, 0xffff, 0x10),
SNBEP_CBO_EVENT_EXTRA_REG(0x4136, 0xffff, 0x18),
SNBEP_CBO_EVENT_EXTRA_REG(0x4336, 0xffff, 0x18),
diff --git a/arch/x86/kernel/entry_32.S b/arch/x86/kernel/entry_32.S
index dbaa23e78b36..0d0c9d4ab6d5 100644
--- a/arch/x86/kernel/entry_32.S
+++ b/arch/x86/kernel/entry_32.S
@@ -425,8 +425,8 @@ sysenter_do_call:
cmpl $(NR_syscalls), %eax
jae sysenter_badsys
call *sys_call_table(,%eax,4)
- movl %eax,PT_EAX(%esp)
sysenter_after_call:
+ movl %eax,PT_EAX(%esp)
LOCKDEP_SYS_EXIT
DISABLE_INTERRUPTS(CLBR_ANY)
TRACE_IRQS_OFF
@@ -502,6 +502,7 @@ ENTRY(system_call)
jae syscall_badsys
syscall_call:
call *sys_call_table(,%eax,4)
+syscall_after_call:
movl %eax,PT_EAX(%esp) # store the return value
syscall_exit:
LOCKDEP_SYS_EXIT
@@ -675,12 +676,12 @@ syscall_fault:
END(syscall_fault)
syscall_badsys:
- movl $-ENOSYS,PT_EAX(%esp)
- jmp syscall_exit
+ movl $-ENOSYS,%eax
+ jmp syscall_after_call
END(syscall_badsys)
sysenter_badsys:
- movl $-ENOSYS,PT_EAX(%esp)
+ movl $-ENOSYS,%eax
jmp sysenter_after_call
END(syscall_badsys)
CFI_ENDPROC
diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c
index 7596df664901..67e6d19ef1be 100644
--- a/arch/x86/kernel/kprobes/core.c
+++ b/arch/x86/kernel/kprobes/core.c
@@ -574,6 +574,9 @@ int kprobe_int3_handler(struct pt_regs *regs)
struct kprobe *p;
struct kprobe_ctlblk *kcb;
+ if (user_mode_vm(regs))
+ return 0;
+
addr = (kprobe_opcode_t *)(regs->ip - sizeof(kprobe_opcode_t));
/*
* We don't want to be preempted for the entire
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index f6449334ec45..ef432f891d30 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -5887,6 +5887,18 @@ static int inject_pending_event(struct kvm_vcpu *vcpu, bool req_int_win)
kvm_x86_ops->set_nmi(vcpu);
}
} else if (kvm_cpu_has_injectable_intr(vcpu)) {
+ /*
+ * Because interrupts can be injected asynchronously, we are
+ * calling check_nested_events again here to avoid a race condition.
+ * See https://lkml.org/lkml/2014/7/2/60 for discussion about this
+ * proposal and current concerns. Perhaps we should be setting
+ * KVM_REQ_EVENT only on certain events and not unconditionally?
+ */
+ if (is_guest_mode(vcpu) && kvm_x86_ops->check_nested_events) {
+ r = kvm_x86_ops->check_nested_events(vcpu, req_int_win);
+ if (r != 0)
+ return r;
+ }
if (kvm_x86_ops->interrupt_allowed(vcpu)) {
kvm_queue_interrupt(vcpu, kvm_cpu_get_interrupt(vcpu),
false);
generated by cgit v1.2.3 (git 2.39.0) at 2024-07-24 16:57:13 +0300