summaryrefslogtreecommitdiff
path: root/arch/x86
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86')
-rw-r--r--arch/x86/events/amd/core.c140
-rw-r--r--arch/x86/events/core.c13
-rw-r--r--arch/x86/events/intel/core.c8
-rw-r--r--arch/x86/include/asm/bitops.h41
-rw-r--r--arch/x86/include/asm/kvm_emulate.h4
-rw-r--r--arch/x86/include/asm/kvm_host.h17
-rw-r--r--arch/x86/include/uapi/asm/vmx.h1
-rw-r--r--arch/x86/kernel/cpu/resctrl/rdtgroup.c6
-rw-r--r--arch/x86/kvm/emulate.c191
-rw-r--r--arch/x86/kvm/lapic.c4
-rw-r--r--arch/x86/kvm/mmu.c15
-rw-r--r--arch/x86/kvm/mmu.h2
-rw-r--r--arch/x86/kvm/pmu.c4
-rw-r--r--arch/x86/kvm/svm.c57
-rw-r--r--arch/x86/kvm/trace.h4
-rw-r--r--arch/x86/kvm/vmx/nested.c47
-rw-r--r--arch/x86/kvm/vmx/vmx.c35
-rw-r--r--arch/x86/kvm/vmx/vmx.h2
-rw-r--r--arch/x86/kvm/x86.c64
-rw-r--r--arch/x86/kvm/x86.h2
20 files changed, 434 insertions, 223 deletions
diff --git a/arch/x86/events/amd/core.c b/arch/x86/events/amd/core.c
index 7d2d7c801dba..0ecfac84ba91 100644
--- a/arch/x86/events/amd/core.c
+++ b/arch/x86/events/amd/core.c
@@ -3,10 +3,14 @@
#include <linux/types.h>
#include <linux/init.h>
#include <linux/slab.h>
+#include <linux/delay.h>
#include <asm/apicdef.h>
+#include <asm/nmi.h>
#include "../perf_event.h"
+static DEFINE_PER_CPU(unsigned int, perf_nmi_counter);
+
static __initconst const u64 amd_hw_cache_event_ids
[PERF_COUNT_HW_CACHE_MAX]
[PERF_COUNT_HW_CACHE_OP_MAX]
@@ -429,6 +433,132 @@ static void amd_pmu_cpu_dead(int cpu)
}
}
+/*
+ * When a PMC counter overflows, an NMI is used to process the event and
+ * reset the counter. NMI latency can result in the counter being updated
+ * before the NMI can run, which can result in what appear to be spurious
+ * NMIs. This function is intended to wait for the NMI to run and reset
+ * the counter to avoid possible unhandled NMI messages.
+ */
+#define OVERFLOW_WAIT_COUNT 50
+
+static void amd_pmu_wait_on_overflow(int idx)
+{
+ unsigned int i;
+ u64 counter;
+
+ /*
+ * Wait for the counter to be reset if it has overflowed. This loop
+ * should exit very, very quickly, but just in case, don't wait
+ * forever...
+ */
+ for (i = 0; i < OVERFLOW_WAIT_COUNT; i++) {
+ rdmsrl(x86_pmu_event_addr(idx), counter);
+ if (counter & (1ULL << (x86_pmu.cntval_bits - 1)))
+ break;
+
+ /* Might be in IRQ context, so can't sleep */
+ udelay(1);
+ }
+}
+
+static void amd_pmu_disable_all(void)
+{
+ struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+ int idx;
+
+ x86_pmu_disable_all();
+
+ /*
+ * This shouldn't be called from NMI context, but add a safeguard here
+ * to return, since if we're in NMI context we can't wait for an NMI
+ * to reset an overflowed counter value.
+ */
+ if (in_nmi())
+ return;
+
+ /*
+ * Check each counter for overflow and wait for it to be reset by the
+ * NMI if it has overflowed. This relies on the fact that all active
+ * counters are always enabled when this function is caled and
+ * ARCH_PERFMON_EVENTSEL_INT is always set.
+ */
+ for (idx = 0; idx < x86_pmu.num_counters; idx++) {
+ if (!test_bit(idx, cpuc->active_mask))
+ continue;
+
+ amd_pmu_wait_on_overflow(idx);
+ }
+}
+
+static void amd_pmu_disable_event(struct perf_event *event)
+{
+ x86_pmu_disable_event(event);
+
+ /*
+ * This can be called from NMI context (via x86_pmu_stop). The counter
+ * may have overflowed, but either way, we'll never see it get reset
+ * by the NMI if we're already in the NMI. And the NMI latency support
+ * below will take care of any pending NMI that might have been
+ * generated by the overflow.
+ */
+ if (in_nmi())
+ return;
+
+ amd_pmu_wait_on_overflow(event->hw.idx);
+}
+
+/*
+ * Because of NMI latency, if multiple PMC counters are active or other sources
+ * of NMIs are received, the perf NMI handler can handle one or more overflowed
+ * PMC counters outside of the NMI associated with the PMC overflow. If the NMI
+ * doesn't arrive at the LAPIC in time to become a pending NMI, then the kernel
+ * back-to-back NMI support won't be active. This PMC handler needs to take into
+ * account that this can occur, otherwise this could result in unknown NMI
+ * messages being issued. Examples of this is PMC overflow while in the NMI
+ * handler when multiple PMCs are active or PMC overflow while handling some
+ * other source of an NMI.
+ *
+ * Attempt to mitigate this by using the number of active PMCs to determine
+ * whether to return NMI_HANDLED if the perf NMI handler did not handle/reset
+ * any PMCs. The per-CPU perf_nmi_counter variable is set to a minimum of the
+ * number of active PMCs or 2. The value of 2 is used in case an NMI does not
+ * arrive at the LAPIC in time to be collapsed into an already pending NMI.
+ */
+static int amd_pmu_handle_irq(struct pt_regs *regs)
+{
+ struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+ int active, handled;
+
+ /*
+ * Obtain the active count before calling x86_pmu_handle_irq() since
+ * it is possible that x86_pmu_handle_irq() may make a counter
+ * inactive (through x86_pmu_stop).
+ */
+ active = __bitmap_weight(cpuc->active_mask, X86_PMC_IDX_MAX);
+
+ /* Process any counter overflows */
+ handled = x86_pmu_handle_irq(regs);
+
+ /*
+ * If a counter was handled, record the number of possible remaining
+ * NMIs that can occur.
+ */
+ if (handled) {
+ this_cpu_write(perf_nmi_counter,
+ min_t(unsigned int, 2, active));
+
+ return handled;
+ }
+
+ if (!this_cpu_read(perf_nmi_counter))
+ return NMI_DONE;
+
+ this_cpu_dec(perf_nmi_counter);
+
+ return NMI_HANDLED;
+}
+
static struct event_constraint *
amd_get_event_constraints(struct cpu_hw_events *cpuc, int idx,
struct perf_event *event)
@@ -621,11 +751,11 @@ static ssize_t amd_event_sysfs_show(char *page, u64 config)
static __initconst const struct x86_pmu amd_pmu = {
.name = "AMD",
- .handle_irq = x86_pmu_handle_irq,
- .disable_all = x86_pmu_disable_all,
+ .handle_irq = amd_pmu_handle_irq,
+ .disable_all = amd_pmu_disable_all,
.enable_all = x86_pmu_enable_all,
.enable = x86_pmu_enable_event,
- .disable = x86_pmu_disable_event,
+ .disable = amd_pmu_disable_event,
.hw_config = amd_pmu_hw_config,
.schedule_events = x86_schedule_events,
.eventsel = MSR_K7_EVNTSEL0,
@@ -732,7 +862,7 @@ void amd_pmu_enable_virt(void)
cpuc->perf_ctr_virt_mask = 0;
/* Reload all events */
- x86_pmu_disable_all();
+ amd_pmu_disable_all();
x86_pmu_enable_all(0);
}
EXPORT_SYMBOL_GPL(amd_pmu_enable_virt);
@@ -750,7 +880,7 @@ void amd_pmu_disable_virt(void)
cpuc->perf_ctr_virt_mask = AMD64_EVENTSEL_HOSTONLY;
/* Reload all events */
- x86_pmu_disable_all();
+ amd_pmu_disable_all();
x86_pmu_enable_all(0);
}
EXPORT_SYMBOL_GPL(amd_pmu_disable_virt);
diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
index e2b1447192a8..81911e11a15d 100644
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -1349,8 +1349,9 @@ void x86_pmu_stop(struct perf_event *event, int flags)
struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
struct hw_perf_event *hwc = &event->hw;
- if (__test_and_clear_bit(hwc->idx, cpuc->active_mask)) {
+ if (test_bit(hwc->idx, cpuc->active_mask)) {
x86_pmu.disable(event);
+ __clear_bit(hwc->idx, cpuc->active_mask);
cpuc->events[hwc->idx] = NULL;
WARN_ON_ONCE(hwc->state & PERF_HES_STOPPED);
hwc->state |= PERF_HES_STOPPED;
@@ -1447,16 +1448,8 @@ int x86_pmu_handle_irq(struct pt_regs *regs)
apic_write(APIC_LVTPC, APIC_DM_NMI);
for (idx = 0; idx < x86_pmu.num_counters; idx++) {
- if (!test_bit(idx, cpuc->active_mask)) {
- /*
- * Though we deactivated the counter some cpus
- * might still deliver spurious interrupts still
- * in flight. Catch them:
- */
- if (__test_and_clear_bit(idx, cpuc->running))
- handled++;
+ if (!test_bit(idx, cpuc->active_mask))
continue;
- }
event = cpuc->events[idx];
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index 8baa441d8000..f61dcbef20ff 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -3185,7 +3185,7 @@ static int intel_pmu_hw_config(struct perf_event *event)
return ret;
if (event->attr.precise_ip) {
- if (!event->attr.freq) {
+ if (!(event->attr.freq || event->attr.wakeup_events)) {
event->hw.flags |= PERF_X86_EVENT_AUTO_RELOAD;
if (!(event->attr.sample_type &
~intel_pmu_large_pebs_flags(event)))
@@ -3575,6 +3575,12 @@ static void intel_pmu_cpu_starting(int cpu)
cpuc->lbr_sel = NULL;
+ if (x86_pmu.flags & PMU_FL_TFA) {
+ WARN_ON_ONCE(cpuc->tfa_shadow);
+ cpuc->tfa_shadow = ~0ULL;
+ intel_set_tfa(cpuc, false);
+ }
+
if (x86_pmu.version > 1)
flip_smm_bit(&x86_pmu.attr_freeze_on_smi);
diff --git a/arch/x86/include/asm/bitops.h b/arch/x86/include/asm/bitops.h
index d153d570bb04..8e790ec219a5 100644
--- a/arch/x86/include/asm/bitops.h
+++ b/arch/x86/include/asm/bitops.h
@@ -36,16 +36,17 @@
* bit 0 is the LSB of addr; bit 32 is the LSB of (addr+1).
*/
-#define BITOP_ADDR(x) "+m" (*(volatile long *) (x))
+#define RLONG_ADDR(x) "m" (*(volatile long *) (x))
+#define WBYTE_ADDR(x) "+m" (*(volatile char *) (x))
-#define ADDR BITOP_ADDR(addr)
+#define ADDR RLONG_ADDR(addr)
/*
* We do the locked ops that don't return the old value as
* a mask operation on a byte.
*/
#define IS_IMMEDIATE(nr) (__builtin_constant_p(nr))
-#define CONST_MASK_ADDR(nr, addr) BITOP_ADDR((void *)(addr) + ((nr)>>3))
+#define CONST_MASK_ADDR(nr, addr) WBYTE_ADDR((void *)(addr) + ((nr)>>3))
#define CONST_MASK(nr) (1 << ((nr) & 7))
/**
@@ -73,7 +74,7 @@ set_bit(long nr, volatile unsigned long *addr)
: "memory");
} else {
asm volatile(LOCK_PREFIX __ASM_SIZE(bts) " %1,%0"
- : BITOP_ADDR(addr) : "Ir" (nr) : "memory");
+ : : RLONG_ADDR(addr), "Ir" (nr) : "memory");
}
}
@@ -88,7 +89,7 @@ set_bit(long nr, volatile unsigned long *addr)
*/
static __always_inline void __set_bit(long nr, volatile unsigned long *addr)
{
- asm volatile(__ASM_SIZE(bts) " %1,%0" : ADDR : "Ir" (nr) : "memory");
+ asm volatile(__ASM_SIZE(bts) " %1,%0" : : ADDR, "Ir" (nr) : "memory");
}
/**
@@ -110,8 +111,7 @@ clear_bit(long nr, volatile unsigned long *addr)
: "iq" ((u8)~CONST_MASK(nr)));
} else {
asm volatile(LOCK_PREFIX __ASM_SIZE(btr) " %1,%0"
- : BITOP_ADDR(addr)
- : "Ir" (nr));
+ : : RLONG_ADDR(addr), "Ir" (nr) : "memory");
}
}
@@ -131,7 +131,7 @@ static __always_inline void clear_bit_unlock(long nr, volatile unsigned long *ad
static __always_inline void __clear_bit(long nr, volatile unsigned long *addr)
{
- asm volatile(__ASM_SIZE(btr) " %1,%0" : ADDR : "Ir" (nr));
+ asm volatile(__ASM_SIZE(btr) " %1,%0" : : ADDR, "Ir" (nr) : "memory");
}
static __always_inline bool clear_bit_unlock_is_negative_byte(long nr, volatile unsigned long *addr)
@@ -139,7 +139,7 @@ static __always_inline bool clear_bit_unlock_is_negative_byte(long nr, volatile
bool negative;
asm volatile(LOCK_PREFIX "andb %2,%1"
CC_SET(s)
- : CC_OUT(s) (negative), ADDR
+ : CC_OUT(s) (negative), WBYTE_ADDR(addr)
: "ir" ((char) ~(1 << nr)) : "memory");
return negative;
}
@@ -155,13 +155,9 @@ static __always_inline bool clear_bit_unlock_is_negative_byte(long nr, volatile
* __clear_bit() is non-atomic and implies release semantics before the memory
* operation. It can be used for an unlock if no other CPUs can concurrently
* modify other bits in the word.
- *
- * No memory barrier is required here, because x86 cannot reorder stores past
- * older loads. Same principle as spin_unlock.
*/
static __always_inline void __clear_bit_unlock(long nr, volatile unsigned long *addr)
{
- barrier();
__clear_bit(nr, addr);
}
@@ -176,7 +172,7 @@ static __always_inline void __clear_bit_unlock(long nr, volatile unsigned long *
*/
static __always_inline void __change_bit(long nr, volatile unsigned long *addr)
{
- asm volatile(__ASM_SIZE(btc) " %1,%0" : ADDR : "Ir" (nr));
+ asm volatile(__ASM_SIZE(btc) " %1,%0" : : ADDR, "Ir" (nr) : "memory");
}
/**
@@ -196,8 +192,7 @@ static __always_inline void change_bit(long nr, volatile unsigned long *addr)
: "iq" ((u8)CONST_MASK(nr)));
} else {
asm volatile(LOCK_PREFIX __ASM_SIZE(btc) " %1,%0"
- : BITOP_ADDR(addr)
- : "Ir" (nr));
+ : : RLONG_ADDR(addr), "Ir" (nr) : "memory");
}
}
@@ -242,8 +237,8 @@ static __always_inline bool __test_and_set_bit(long nr, volatile unsigned long *
asm(__ASM_SIZE(bts) " %2,%1"
CC_SET(c)
- : CC_OUT(c) (oldbit), ADDR
- : "Ir" (nr));
+ : CC_OUT(c) (oldbit)
+ : ADDR, "Ir" (nr) : "memory");
return oldbit;
}
@@ -282,8 +277,8 @@ static __always_inline bool __test_and_clear_bit(long nr, volatile unsigned long
asm volatile(__ASM_SIZE(btr) " %2,%1"
CC_SET(c)
- : CC_OUT(c) (oldbit), ADDR
- : "Ir" (nr));
+ : CC_OUT(c) (oldbit)
+ : ADDR, "Ir" (nr) : "memory");
return oldbit;
}
@@ -294,8 +289,8 @@ static __always_inline bool __test_and_change_bit(long nr, volatile unsigned lon
asm volatile(__ASM_SIZE(btc) " %2,%1"
CC_SET(c)
- : CC_OUT(c) (oldbit), ADDR
- : "Ir" (nr) : "memory");
+ : CC_OUT(c) (oldbit)
+ : ADDR, "Ir" (nr) : "memory");
return oldbit;
}
@@ -326,7 +321,7 @@ static __always_inline bool variable_test_bit(long nr, volatile const unsigned l
asm volatile(__ASM_SIZE(bt) " %2,%1"
CC_SET(c)
: CC_OUT(c) (oldbit)
- : "m" (*(unsigned long *)addr), "Ir" (nr));
+ : "m" (*(unsigned long *)addr), "Ir" (nr) : "memory");
return oldbit;
}
diff --git a/arch/x86/include/asm/kvm_emulate.h b/arch/x86/include/asm/kvm_emulate.h
index 93c4bf598fb0..feab24cac610 100644
--- a/arch/x86/include/asm/kvm_emulate.h
+++ b/arch/x86/include/asm/kvm_emulate.h
@@ -226,7 +226,9 @@ struct x86_emulate_ops {
unsigned (*get_hflags)(struct x86_emulate_ctxt *ctxt);
void (*set_hflags)(struct x86_emulate_ctxt *ctxt, unsigned hflags);
- int (*pre_leave_smm)(struct x86_emulate_ctxt *ctxt, u64 smbase);
+ int (*pre_leave_smm)(struct x86_emulate_ctxt *ctxt,
+ const char *smstate);
+ void (*post_leave_smm)(struct x86_emulate_ctxt *ctxt);
};
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 159b5988292f..a9d03af34030 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -126,7 +126,7 @@ static inline gfn_t gfn_to_index(gfn_t gfn, gfn_t base_gfn, int level)
}
#define KVM_PERMILLE_MMU_PAGES 20
-#define KVM_MIN_ALLOC_MMU_PAGES 64
+#define KVM_MIN_ALLOC_MMU_PAGES 64UL
#define KVM_MMU_HASH_SHIFT 12
#define KVM_NUM_MMU_PAGES (1 << KVM_MMU_HASH_SHIFT)
#define KVM_MIN_FREE_MMU_PAGES 5
@@ -844,9 +844,9 @@ enum kvm_irqchip_mode {
};
struct kvm_arch {
- unsigned int n_used_mmu_pages;
- unsigned int n_requested_mmu_pages;
- unsigned int n_max_mmu_pages;
+ unsigned long n_used_mmu_pages;
+ unsigned long n_requested_mmu_pages;
+ unsigned long n_max_mmu_pages;
unsigned int indirect_shadow_pages;
struct hlist_head mmu_page_hash[KVM_NUM_MMU_PAGES];
/*
@@ -1182,7 +1182,7 @@ struct kvm_x86_ops {
int (*smi_allowed)(struct kvm_vcpu *vcpu);
int (*pre_enter_smm)(struct kvm_vcpu *vcpu, char *smstate);
- int (*pre_leave_smm)(struct kvm_vcpu *vcpu, u64 smbase);
+ int (*pre_leave_smm)(struct kvm_vcpu *vcpu, const char *smstate);
int (*enable_smi_window)(struct kvm_vcpu *vcpu);
int (*mem_enc_op)(struct kvm *kvm, void __user *argp);
@@ -1256,8 +1256,8 @@ void kvm_mmu_clear_dirty_pt_masked(struct kvm *kvm,
gfn_t gfn_offset, unsigned long mask);
void kvm_mmu_zap_all(struct kvm *kvm);
void kvm_mmu_invalidate_mmio_sptes(struct kvm *kvm, u64 gen);
-unsigned int kvm_mmu_calculate_default_mmu_pages(struct kvm *kvm);
-void kvm_mmu_change_mmu_pages(struct kvm *kvm, unsigned int kvm_nr_mmu_pages);
+unsigned long kvm_mmu_calculate_default_mmu_pages(struct kvm *kvm);
+void kvm_mmu_change_mmu_pages(struct kvm *kvm, unsigned long kvm_nr_mmu_pages);
int load_pdptrs(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, unsigned long cr3);
bool pdptrs_changed(struct kvm_vcpu *vcpu);
@@ -1592,4 +1592,7 @@ static inline int kvm_cpu_get_apicid(int mps_cpu)
#define put_smstate(type, buf, offset, val) \
*(type *)((buf) + (offset) - 0x7e00) = val
+#define GET_SMSTATE(type, buf, offset) \
+ (*(type *)((buf) + (offset) - 0x7e00))
+
#endif /* _ASM_X86_KVM_HOST_H */
diff --git a/arch/x86/include/uapi/asm/vmx.h b/arch/x86/include/uapi/asm/vmx.h
index f0b0c90dd398..d213ec5c3766 100644
--- a/arch/x86/include/uapi/asm/vmx.h
+++ b/arch/x86/include/uapi/asm/vmx.h
@@ -146,6 +146,7 @@
#define VMX_ABORT_SAVE_GUEST_MSR_FAIL 1
#define VMX_ABORT_LOAD_HOST_PDPTE_FAIL 2
+#define VMX_ABORT_VMCS_CORRUPTED 3
#define VMX_ABORT_LOAD_HOST_MSR_FAIL 4
#endif /* _UAPIVMX_H */
diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
index 399601eda8e4..54b9eef3eea9 100644
--- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c
+++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
@@ -2039,14 +2039,14 @@ out:
enum rdt_param {
Opt_cdp,
Opt_cdpl2,
- Opt_mba_mpbs,
+ Opt_mba_mbps,
nr__rdt_params
};
static const struct fs_parameter_spec rdt_param_specs[] = {
fsparam_flag("cdp", Opt_cdp),
fsparam_flag("cdpl2", Opt_cdpl2),
- fsparam_flag("mba_mpbs", Opt_mba_mpbs),
+ fsparam_flag("mba_MBps", Opt_mba_mbps),
{}
};
@@ -2072,7 +2072,7 @@ static int rdt_parse_param(struct fs_context *fc, struct fs_parameter *param)
case Opt_cdpl2:
ctx->enable_cdpl2 = true;
return 0;
- case Opt_mba_mpbs:
+ case Opt_mba_mbps:
if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL)
return -EINVAL;
ctx->enable_mba_mbps = true;
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index c338984c850d..d0d5dd44b4f4 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -2331,24 +2331,18 @@ static int em_lseg(struct x86_emulate_ctxt *ctxt)
static int emulator_has_longmode(struct x86_emulate_ctxt *ctxt)
{
+#ifdef CONFIG_X86_64
u32 eax, ebx, ecx, edx;
eax = 0x80000001;
ecx = 0;
ctxt->ops->get_cpuid(ctxt, &eax, &ebx, &ecx, &edx, false);
return edx & bit(X86_FEATURE_LM);
+#else
+ return false;
+#endif
}
-#define GET_SMSTATE(type, smbase, offset) \
- ({ \
- type __val; \
- int r = ctxt->ops->read_phys(ctxt, smbase + offset, &__val, \
- sizeof(__val)); \
- if (r != X86EMUL_CONTINUE) \
- return X86EMUL_UNHANDLEABLE; \
- __val; \
- })
-
static void rsm_set_desc_flags(struct desc_struct *desc, u32 flags)
{
desc->g = (flags >> 23) & 1;
@@ -2361,27 +2355,30 @@ static void rsm_set_desc_flags(struct desc_struct *desc, u32 flags)
desc->type = (flags >> 8) & 15;
}
-static int rsm_load_seg_32(struct x86_emulate_ctxt *ctxt, u64 smbase, int n)
+static int rsm_load_seg_32(struct x86_emulate_ctxt *ctxt, const char *smstate,
+ int n)
{
struct desc_struct desc;
int offset;
u16 selector;
- selector = GET_SMSTATE(u32, smbase, 0x7fa8 + n * 4);
+ selector = GET_SMSTATE(u32, smstate, 0x7fa8 + n * 4);
if (n < 3)
offset = 0x7f84 + n * 12;
else
offset = 0x7f2c + (n - 3) * 12;
- set_desc_base(&desc, GET_SMSTATE(u32, smbase, offset + 8));
- set_desc_limit(&desc, GET_SMSTATE(u32, smbase, offset + 4));
- rsm_set_desc_flags(&desc, GET_SMSTATE(u32, smbase, offset));
+ set_desc_base(&desc, GET_SMSTATE(u32, smstate, offset + 8));
+ set_desc_limit(&desc, GET_SMSTATE(u32, smstate, offset + 4));
+ rsm_set_desc_flags(&desc, GET_SMSTATE(u32, smstate, offset));
ctxt->ops->set_segment(ctxt, selector, &desc, 0, n);
return X86EMUL_CONTINUE;
}
-static int rsm_load_seg_64(struct x86_emulate_ctxt *ctxt, u64 smbase, int n)
+#ifdef CONFIG_X86_64
+static int rsm_load_seg_64(struct x86_emulate_ctxt *ctxt, const char *smstate,
+ int n)
{
struct desc_struct desc;
int offset;
@@ -2390,15 +2387,16 @@ static int rsm_load_seg_64(struct x86_emulate_ctxt *ctxt, u64 smbase, int n)
offset = 0x7e00 + n * 16;
- selector = GET_SMSTATE(u16, smbase, offset);
- rsm_set_desc_flags(&desc, GET_SMSTATE(u16, smbase, offset + 2) << 8);
- set_desc_limit(&desc, GET_SMSTATE(u32, smbase, offset + 4));
- set_desc_base(&desc, GET_SMSTATE(u32, smbase, offset + 8));
- base3 = GET_SMSTATE(u32, smbase, offset + 12);
+ selector = GET_SMSTATE(u16, smstate, offset);
+ rsm_set_desc_flags(&desc, GET_SMSTATE(u16, smstate, offset + 2) << 8);
+ set_desc_limit(&desc, GET_SMSTATE(u32, smstate, offset + 4));
+ set_desc_base(&desc, GET_SMSTATE(u32, smstate, offset + 8));
+ base3 = GET_SMSTATE(u32, smstate, offset + 12);
ctxt->ops->set_segment(ctxt, selector, &desc, base3, n);
return X86EMUL_CONTINUE;
}
+#endif
static int rsm_enter_protected_mode(struct x86_emulate_ctxt *ctxt,
u64 cr0, u64 cr3, u64 cr4)
@@ -2445,7 +2443,8 @@ static int rsm_enter_protected_mode(struct x86_emulate_ctxt *ctxt,
return X86EMUL_CONTINUE;
}
-static int rsm_load_state_32(struct x86_emulate_ctxt *ctxt, u64 smbase)
+static int rsm_load_state_32(struct x86_emulate_ctxt *ctxt,
+ const char *smstate)
{
struct desc_struct desc;
struct desc_ptr dt;
@@ -2453,53 +2452,55 @@ static int rsm_load_state_32(struct x86_emulate_ctxt *ctxt, u64 smbase)
u32 val, cr0, cr3, cr4;
int i;
- cr0 = GET_SMSTATE(u32, smbase, 0x7ffc);
- cr3 = GET_SMSTATE(u32, smbase, 0x7ff8);
- ctxt->eflags = GET_SMSTATE(u32, smbase, 0x7ff4) | X86_EFLAGS_FIXED;
- ctxt->_eip = GET_SMSTATE(u32, smbase, 0x7ff0);
+ cr0 = GET_SMSTATE(u32, smstate, 0x7ffc);
+ cr3 = GET_SMSTATE(u32, smstate, 0x7ff8);
+ ctxt->eflags = GET_SMSTATE(u32, smstate, 0x7ff4) | X86_EFLAGS_FIXED;
+ ctxt->_eip = GET_SMSTATE(u32, smstate, 0x7ff0);
for (i = 0; i < 8; i++)
- *reg_write(ctxt, i) = GET_SMSTATE(u32, smbase, 0x7fd0 + i * 4);
+ *reg_write(ctxt, i) = GET_SMSTATE(u32, smstate, 0x7fd0 + i * 4);
- val = GET_SMSTATE(u32, smbase, 0x7fcc);
+ val = GET_SMSTATE(u32, smstate, 0x7fcc);
ctxt->ops->set_dr(ctxt, 6, (val & DR6_VOLATILE) | DR6_FIXED_1);
- val = GET_SMSTATE(u32, smbase, 0x7fc8);
+ val = GET_SMSTATE(u32, smstate, 0x7fc8);
ctxt->ops->set_dr(ctxt, 7, (val & DR7_VOLATILE) | DR7_FIXED_1);
- selector = GET_SMSTATE(u32, smbase, 0x7fc4);
- set_desc_base(&desc, GET_SMSTATE(u32, smbase, 0x7f64));
- set_desc_limit(&desc, GET_SMSTATE(u32, smbase, 0x7f60));
- rsm_set_desc_flags(&desc, GET_SMSTATE(u32, smbase, 0x7f5c));
+ selector = GET_SMSTATE(u32, smstate, 0x7fc4);
+ set_desc_base(&desc, GET_SMSTATE(u32, smstate, 0x7f64));
+ set_desc_limit(&desc, GET_SMSTATE(u32, smstate, 0x7f60));
+ rsm_set_desc_flags(&desc, GET_SMSTATE(u32, smstate, 0x7f5c));
ctxt->ops->set_segment(ctxt, selector, &desc, 0, VCPU_SREG_TR);
- selector = GET_SMSTATE(u32, smbase, 0x7fc0);
- set_desc_base(&desc, GET_SMSTATE(u32, smbase, 0x7f80));
- set_desc_limit(&desc, GET_SMSTATE(u32, smbase, 0x7f7c));
- rsm_set_desc_flags(&desc, GET_SMSTATE(u32, smbase, 0x7f78));
+ selector = GET_SMSTATE(u32, smstate, 0x7fc0);
+ set_desc_base(&desc, GET_SMSTATE(u32, smstate, 0x7f80));
+ set_desc_limit(&desc, GET_SMSTATE(u32, smstate, 0x7f7c));
+ rsm_set_desc_flags(&desc, GET_SMSTATE(u32, smstate, 0x7f78));
ctxt->ops->set_segment(ctxt, selector, &desc, 0, VCPU_SREG_LDTR);
- dt.address = GET_SMSTATE(u32, smbase, 0x7f74);
- dt.size = GET_SMSTATE(u32, smbase, 0x7f70);
+ dt.address = GET_SMSTATE(u32, smstate, 0x7f74);
+ dt.size = GET_SMSTATE(u32, smstate, 0x7f70);
ctxt->ops->set_gdt(ctxt, &dt);
- dt.address = GET_SMSTATE(u32, smbase, 0x7f58);
- dt.size = GET_SMSTATE(u32, smbase, 0x7f54);
+ dt.address = GET_SMSTATE(u32, smstate, 0x7f58);
+ dt.size = GET_SMSTATE(u32, smstate, 0x7f54);
ctxt->ops->set_idt(ctxt, &dt);
for (i = 0; i < 6; i++) {
- int r = rsm_load_seg_32(ctxt, smbase, i);
+ int r = rsm_load_seg_32(ctxt, smstate, i);
if (r != X86EMUL_CONTINUE)
return r;
}
- cr4 = GET_SMSTATE(u32, smbase, 0x7f14);
+ cr4 = GET_SMSTATE(u32, smstate, 0x7f14);
- ctxt->ops->set_smbase(ctxt, GET_SMSTATE(u32, smbase, 0x7ef8));
+ ctxt->ops->set_smbase(ctxt, GET_SMSTATE(u32, smstate, 0x7ef8));
return rsm_enter_protected_mode(ctxt, cr0, cr3, cr4);
}
-static int rsm_load_state_64(struct x86_emulate_ctxt *ctxt, u64 smbase)
+#ifdef CONFIG_X86_64
+static int rsm_load_state_64(struct x86_emulate_ctxt *ctxt,
+ const char *smstate)
{
struct desc_struct desc;
struct desc_ptr dt;
@@ -2509,43 +2510,43 @@ static int rsm_load_state_64(struct x86_emulate_ctxt *ctxt, u64 smbase)
int i, r;
for (i = 0; i < 16; i++)
- *reg_write(ctxt, i) = GET_SMSTATE(u64, smbase, 0x7ff8 - i * 8);
+ *reg_write(ctxt, i) = GET_SMSTATE(u64, smstate, 0x7ff8 - i * 8);
- ctxt->_eip = GET_SMSTATE(u64, smbase, 0x7f78);
- ctxt->eflags = GET_SMSTATE(u32, smbase, 0x7f70) | X86_EFLAGS_FIXED;
+ ctxt->_eip = GET_SMSTATE(u64, smstate, 0x7f78);
+ ctxt->eflags = GET_SMSTATE(u32, smstate, 0x7f70) | X86_EFLAGS_FIXED;
- val = GET_SMSTATE(u32, smbase, 0x7f68);
+ val = GET_SMSTATE(u32, smstate, 0x7f68);
ctxt->ops->set_dr(ctxt, 6, (val & DR6_VOLATILE) | DR6_FIXED_1);
- val = GET_SMSTATE(u32, smbase, 0x7f60);
+ val = GET_SMSTATE(u32, smstate, 0x7f60);
ctxt->ops->set_dr(ctxt, 7, (val & DR7_VOLATILE) | DR7_FIXED_1);
- cr0 = GET_SMSTATE(u64, smbase, 0x7f58);
- cr3 = GET_SMSTATE(u64, smbase, 0x7f50);
- cr4 = GET_SMSTATE(u64, smbase, 0x7f48);
- ctxt->ops->set_smbase(ctxt, GET_SMSTATE(u32, smbase, 0x7f00));
- val = GET_SMSTATE(u64, smbase, 0x7ed0);
+ cr0 = GET_SMSTATE(u64, smstate, 0x7f58);
+ cr3 = GET_SMSTATE(u64, smstate, 0x7f50);
+ cr4 = GET_SMSTATE(u64, smstate, 0x7f48);
+ ctxt->ops->set_smbase(ctxt, GET_SMSTATE(u32, smstate, 0x7f00));
+ val = GET_SMSTATE(u64, smstate, 0x7ed0);
ctxt->ops->set_msr(ctxt, MSR_EFER, val & ~EFER_LMA);
- selector = GET_SMSTATE(u32, smbase, 0x7e90);
- rsm_set_desc_flags(&desc, GET_SMSTATE(u32, smbase, 0x7e92) << 8);
- set_desc_limit(&desc, GET_SMSTATE(u32, smbase, 0x7e94));
- set_desc_base(&desc, GET_SMSTATE(u32, smbase, 0x7e98));
- base3 = GET_SMSTATE(u32, smbase, 0x7e9c);
+ selector = GET_SMSTATE(u32, smstate, 0x7e90);
+ rsm_set_desc_flags(&desc, GET_SMSTATE(u32, smstate, 0x7e92) << 8);
+ set_desc_limit(&desc, GET_SMSTATE(u32, smstate, 0x7e94));
+ set_desc_base(&desc, GET_SMSTATE(u32, smstate, 0x7e98));
+ base3 = GET_SMSTATE(u32, smstate, 0x7e9c);
ctxt->ops->set_segment(ctxt, selector, &desc, base3, VCPU_SREG_TR);
- dt.size = GET_SMSTATE(u32, smbase, 0x7e84);
- dt.address = GET_SMSTATE(u64, smbase, 0x7e88);
+ dt.size = GET_SMSTATE(u32, smstate, 0x7e84);
+ dt.address = GET_SMSTATE(u64, smstate, 0x7e88);
ctxt->ops->set_idt(ctxt, &dt);
- selector = GET_SMSTATE(u32, smbase, 0x7e70);
- rsm_set_desc_flags(&desc, GET_SMSTATE(u32, smbase, 0x7e72) << 8);
- set_desc_limit(&desc, GET_SMSTATE(u32, smbase, 0x7e74));
- set_desc_base(&desc, GET_SMSTATE(u32, smbase, 0x7e78));
- base3 = GET_SMSTATE(u32, smbase, 0x7e7c);
+ selector = GET_SMSTATE(u32, smstate, 0x7e70);
+ rsm_set_desc_flags(&desc, GET_SMSTATE(u32, smstate, 0x7e72) << 8);
+ set_desc_limit(&desc, GET_SMSTATE(u32, smstate, 0x7e74));
+ set_desc_base(&desc, GET_SMSTATE(u32, smstate, 0x7e78));
+ base3 = GET_SMSTATE(u32, smstate, 0x7e7c);
ctxt->ops->set_segment(ctxt, selector, &desc, base3, VCPU_SREG_LDTR);
- dt.size = GET_SMSTATE(u32, smbase, 0x7e64);
- dt.address = GET_SMSTATE(u64, smbase, 0x7e68);
+ dt.size = GET_SMSTATE(u32, smstate, 0x7e64);
+ dt.address = GET_SMSTATE(u64, smstate, 0x7e68);
ctxt->ops->set_gdt(ctxt, &dt);
r = rsm_enter_protected_mode(ctxt, cr0, cr3, cr4);
@@ -2553,37 +2554,49 @@ static int rsm_load_state_64(struct x86_emulate_ctxt *ctxt, u64 smbase)
return r;
for (i = 0; i < 6; i++) {
- r = rsm_load_seg_64(ctxt, smbase, i);
+ r = rsm_load_seg_64(ctxt, smstate, i);
if (r != X86EMUL_CONTINUE)
return r;
}
return X86EMUL_CONTINUE;
}
+#endif
static int em_rsm(struct x86_emulate_ctxt *ctxt)
{
unsigned long cr0, cr4, efer;
+ char buf[512];
u64 smbase;
int ret;
if ((ctxt->ops->get_hflags(ctxt) & X86EMUL_SMM_MASK) == 0)
return emulate_ud(ctxt);
+ smbase = ctxt->ops->get_smbase(ctxt);
+
+ ret = ctxt->ops->read_phys(ctxt, smbase + 0xfe00, buf, sizeof(buf));
+ if (ret != X86EMUL_CONTINUE)
+ return X86EMUL_UNHANDLEABLE;
+
+ if ((ctxt->ops->get_hflags(ctxt) & X86EMUL_SMM_INSIDE_NMI_MASK) == 0)
+ ctxt->ops->set_nmi_mask(ctxt, false);
+
+ ctxt->ops->set_hflags(ctxt, ctxt->ops->get_hflags(ctxt) &
+ ~(X86EMUL_SMM_INSIDE_NMI_MASK | X86EMUL_SMM_MASK));
+
/*
* Get back to real mode, to prepare a safe state in which to load
* CR0/CR3/CR4/EFER. It's all a bit more complicated if the vCPU
* supports long mode.
*/
- cr4 = ctxt->ops->get_cr(ctxt, 4);
if (emulator_has_longmode(ctxt)) {
struct desc_struct cs_desc;
/* Zero CR4.PCIDE before CR0.PG. */
- if (cr4 & X86_CR4_PCIDE) {
+ cr4 = ctxt->ops->get_cr(ctxt, 4);
+ if (cr4 & X86_CR4_PCIDE)
ctxt->ops->set_cr(ctxt, 4, cr4 & ~X86_CR4_PCIDE);
- cr4 &= ~X86_CR4_PCIDE;
- }
/* A 32-bit code segment is required to clear EFER.LMA. */
memset(&cs_desc, 0, sizeof(cs_desc));
@@ -2597,39 +2610,39 @@ static int em_rsm(struct x86_emulate_ctxt *ctxt)
if (cr0 & X86_CR0_PE)
ctxt->ops->set_cr(ctxt, 0, cr0 & ~(X86_CR0_PG | X86_CR0_PE));
- /* Now clear CR4.PAE (which must be done before clearing EFER.LME). */
- if (cr4 & X86_CR4_PAE)
- ctxt->ops->set_cr(ctxt, 4, cr4 & ~X86_CR4_PAE);
-
- /* And finally go back to 32-bit mode. */
- efer = 0;
- ctxt->ops->set_msr(ctxt, MSR_EFER, efer);
+ if (emulator_has_longmode(ctxt)) {
+ /* Clear CR4.PAE before clearing EFER.LME. */
+ cr4 = ctxt->ops->get_cr(ctxt, 4);
+ if (cr4 & X86_CR4_PAE)
+ ctxt->ops->set_cr(ctxt, 4, cr4 & ~X86_CR4_PAE);
- smbase = ctxt->ops->get_smbase(ctxt);
+ /* And finally go back to 32-bit mode. */
+ efer = 0;
+ ctxt->ops->set_msr(ctxt, MSR_EFER, efer);
+ }
/*
* Give pre_leave_smm() a chance to make ISA-specific changes to the
* vCPU state (e.g. enter guest mode) before loading state from the SMM
* state-save area.
*/
- if (ctxt->ops->pre_leave_smm(ctxt, smbase))
+ if (ctxt->ops->pre_leave_smm(ctxt, buf))
return X86EMUL_UNHANDLEABLE;
+#ifdef CONFIG_X86_64
if (emulator_has_longmode(ctxt))
- ret = rsm_load_state_64(ctxt, smbase + 0x8000);
+ ret = rsm_load_state_64(ctxt, buf);
else
- ret = rsm_load_state_32(ctxt, smbase + 0x8000);
+#endif
+ ret = rsm_load_state_32(ctxt, buf);
if (ret != X86EMUL_CONTINUE) {
/* FIXME: should triple fault */
return X86EMUL_UNHANDLEABLE;
}
- if ((ctxt->ops->get_hflags(ctxt) & X86EMUL_SMM_INSIDE_NMI_MASK) == 0)
- ctxt->ops->set_nmi_mask(ctxt, false);
+ ctxt->ops->post_leave_smm(ctxt);
- ctxt->ops->set_hflags(ctxt, ctxt->ops->get_hflags(ctxt) &
- ~(X86EMUL_SMM_INSIDE_NMI_MASK | X86EMUL_SMM_MASK));
return X86EMUL_CONTINUE;
}
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index 991fdf7fc17f..9bf70cf84564 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -138,6 +138,7 @@ static inline bool kvm_apic_map_get_logical_dest(struct kvm_apic_map *map,
if (offset <= max_apic_id) {
u8 cluster_size = min(max_apic_id - offset + 1, 16U);
+ offset = array_index_nospec(offset, map->max_apic_id + 1);
*cluster = &map->phys_map[offset];
*mask = dest_id & (0xffff >> (16 - cluster_size));
} else {
@@ -901,7 +902,8 @@ static inline bool kvm_apic_map_get_dest_lapic(struct kvm *kvm,
if (irq->dest_id > map->max_apic_id) {
*bitmap = 0;
} else {
- *dst = &map->phys_map[irq->dest_id];
+ u32 dest_id = array_index_nospec(irq->dest_id, map->max_apic_id + 1);
+ *dst = &map->phys_map[dest_id];
*bitmap = 1;
}
return true;
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index eee455a8a612..e10962dfc203 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -2007,7 +2007,7 @@ static int is_empty_shadow_page(u64 *spt)
* aggregate version in order to make the slab shrinker
* faster
*/
-static inline void kvm_mod_used_mmu_pages(struct kvm *kvm, int nr)
+static inline void kvm_mod_used_mmu_pages(struct kvm *kvm, unsigned long nr)
{
kvm->arch.n_used_mmu_pages += nr;
percpu_counter_add(&kvm_total_used_mmu_pages, nr);
@@ -2238,7 +2238,7 @@ static bool kvm_mmu_remote_flush_or_zap(struct kvm *kvm,
struct list_head *invalid_list,
bool remote_flush)
{
- if (!remote_flush && !list_empty(invalid_list))
+ if (!remote_flush && list_empty(invalid_list))
return false;
if (!list_empty(invalid_list))
@@ -2763,7 +2763,7 @@ static bool prepare_zap_oldest_mmu_page(struct kvm *kvm,
* Changing the number of mmu pages allocated to the vm
* Note: if goal_nr_mmu_pages is too small, you will get dead lock
*/
-void kvm_mmu_change_mmu_pages(struct kvm *kvm, unsigned int goal_nr_mmu_pages)
+void kvm_mmu_change_mmu_pages(struct kvm *kvm, unsigned long goal_nr_mmu_pages)
{
LIST_HEAD(invalid_list);
@@ -6031,10 +6031,10 @@ out:
/*
* Calculate mmu pages needed for kvm.
*/
-unsigned int kvm_mmu_calculate_default_mmu_pages(struct kvm *kvm)
+unsigned long kvm_mmu_calculate_default_mmu_pages(struct kvm *kvm)
{
- unsigned int nr_mmu_pages;
- unsigned int nr_pages = 0;
+ unsigned long nr_mmu_pages;
+ unsigned long nr_pages = 0;
struct kvm_memslots *slots;
struct kvm_memory_slot *memslot;
int i;
@@ -6047,8 +6047,7 @@ unsigned int kvm_mmu_calculate_default_mmu_pages(struct kvm *kvm)
}
nr_mmu_pages = nr_pages * KVM_PERMILLE_MMU_PAGES / 1000;
- nr_mmu_pages = max(nr_mmu_pages,
- (unsigned int) KVM_MIN_ALLOC_MMU_PAGES);
+ nr_mmu_pages = max(nr_mmu_pages, KVM_MIN_ALLOC_MMU_PAGES);
return nr_mmu_pages;
}
diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h
index bbdc60f2fae8..54c2a377795b 100644
--- a/arch/x86/kvm/mmu.h
+++ b/arch/x86/kvm/mmu.h
@@ -64,7 +64,7 @@ bool kvm_can_do_async_pf(struct kvm_vcpu *vcpu);
int kvm_handle_page_fault(struct kvm_vcpu *vcpu, u64 error_code,
u64 fault_address, char *insn, int insn_len);
-static inline unsigned int kvm_mmu_available_pages(struct kvm *kvm)
+static inline unsigned long kvm_mmu_available_pages(struct kvm *kvm)
{
if (kvm->arch.n_max_mmu_pages > kvm->arch.n_used_mmu_pages)
return kvm->arch.n_max_mmu_pages -
diff --git a/arch/x86/kvm/pmu.c b/arch/x86/kvm/pmu.c
index 58ead7db71a3..e39741997893 100644
--- a/arch/x86/kvm/pmu.c
+++ b/arch/x86/kvm/pmu.c
@@ -281,9 +281,13 @@ static int kvm_pmu_rdpmc_vmware(struct kvm_vcpu *vcpu, unsigned idx, u64 *data)
int kvm_pmu_rdpmc(struct kvm_vcpu *vcpu, unsigned idx, u64 *data)
{
bool fast_mode = idx & (1u << 31);
+ struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
struct kvm_pmc *pmc;
u64 ctr_val;
+ if (!pmu->version)
+ return 1;
+
if (is_vmware_backdoor_pmc(idx))
return kvm_pmu_rdpmc_vmware(vcpu, idx, data);
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index e0a791c3d4fc..406b558abfef 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -262,6 +262,7 @@ struct amd_svm_iommu_ir {
};
#define AVIC_LOGICAL_ID_ENTRY_GUEST_PHYSICAL_ID_MASK (0xFF)
+#define AVIC_LOGICAL_ID_ENTRY_VALID_BIT 31
#define AVIC_LOGICAL_ID_ENTRY_VALID_MASK (1 << 31)
#define AVIC_PHYSICAL_ID_ENTRY_HOST_PHYSICAL_ID_MASK (0xFFULL)
@@ -2692,6 +2693,7 @@ static int npf_interception(struct vcpu_svm *svm)
static int db_interception(struct vcpu_svm *svm)
{
struct kvm_run *kvm_run = svm->vcpu.run;
+ struct kvm_vcpu *vcpu = &svm->vcpu;
if (!(svm->vcpu.guest_debug &
(KVM_GUESTDBG_SINGLESTEP | KVM_GUESTDBG_USE_HW_BP)) &&
@@ -2702,6 +2704,8 @@ static int db_interception(struct vcpu_svm *svm)
if (svm->nmi_singlestep) {
disable_nmi_singlestep(svm);
+ /* Make sure we check for pending NMIs upon entry */
+ kvm_make_request(KVM_REQ_EVENT, vcpu);
}
if (svm->vcpu.guest_debug &
@@ -4517,14 +4521,25 @@ static int avic_incomplete_ipi_interception(struct vcpu_svm *svm)
kvm_lapic_reg_write(apic, APIC_ICR, icrl);
break;
case AVIC_IPI_FAILURE_TARGET_NOT_RUNNING: {
+ int i;
+ struct kvm_vcpu *vcpu;
+ struct kvm *kvm = svm->vcpu.kvm;
struct kvm_lapic *apic = svm->vcpu.arch.apic;
/*
- * Update ICR high and low, then emulate sending IPI,
- * which is handled when writing APIC_ICR.
+ * At this point, we expect that the AVIC HW has already
+ * set the appropriate IRR bits on the valid target
+ * vcpus. So, we just need to kick the appropriate vcpu.
*/
- kvm_lapic_reg_write(apic, APIC_ICR2, icrh);
- kvm_lapic_reg_write(apic, APIC_ICR, icrl);
+ kvm_for_each_vcpu(i, vcpu, kvm) {
+ bool m = kvm_apic_match_dest(vcpu, apic,
+ icrl & KVM_APIC_SHORT_MASK,
+ GET_APIC_DEST_FIELD(icrh),
+ icrl & KVM_APIC_DEST_MASK);
+
+ if (m && !avic_vcpu_is_running(vcpu))
+ kvm_vcpu_wake_up(vcpu);
+ }
break;
}
case AVIC_IPI_FAILURE_INVALID_TARGET:
@@ -4596,7 +4611,7 @@ static void avic_invalidate_logical_id_entry(struct kvm_vcpu *vcpu)
u32 *entry = avic_get_logical_id_entry(vcpu, svm->ldr_reg, flat);
if (entry)
- WRITE_ONCE(*entry, (u32) ~AVIC_LOGICAL_ID_ENTRY_VALID_MASK);
+ clear_bit(AVIC_LOGICAL_ID_ENTRY_VALID_BIT, (unsigned long *)entry);
}
static int avic_handle_ldr_update(struct kvm_vcpu *vcpu)
@@ -5621,6 +5636,7 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu)
svm->vmcb->save.cr2 = vcpu->arch.cr2;
clgi();
+ kvm_load_guest_xcr0(vcpu);
/*
* If this vCPU has touched SPEC_CTRL, restore the guest's value if
@@ -5766,6 +5782,7 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu)
if (unlikely(svm->vmcb->control.exit_code == SVM_EXIT_NMI))
kvm_before_interrupt(&svm->vcpu);
+ kvm_put_guest_xcr0(vcpu);
stgi();
/* Any pending NMI will happen here */
@@ -6215,32 +6232,24 @@ static int svm_pre_enter_smm(struct kvm_vcpu *vcpu, char *smstate)
return 0;
}
-static int svm_pre_leave_smm(struct kvm_vcpu *vcpu, u64 smbase)
+static int svm_pre_leave_smm(struct kvm_vcpu *vcpu, const char *smstate)
{
struct vcpu_svm *svm = to_svm(vcpu);
struct vmcb *nested_vmcb;
struct page *page;
- struct {
- u64 guest;
- u64 vmcb;
- } svm_state_save;
- int ret;
+ u64 guest;
+ u64 vmcb;
- ret = kvm_vcpu_read_guest(vcpu, smbase + 0xfed8, &svm_state_save,
- sizeof(svm_state_save));
- if (ret)
- return ret;
+ guest = GET_SMSTATE(u64, smstate, 0x7ed8);
+ vmcb = GET_SMSTATE(u64, smstate, 0x7ee0);
- if (svm_state_save.guest) {
- vcpu->arch.hflags &= ~HF_SMM_MASK;
- nested_vmcb = nested_svm_map(svm, svm_state_save.vmcb, &page);
- if (nested_vmcb)
- enter_svm_guest_mode(svm, svm_state_save.vmcb, nested_vmcb, page);
- else
- ret = 1;
- vcpu->arch.hflags |= HF_SMM_MASK;
+ if (guest) {
+ nested_vmcb = nested_svm_map(svm, vmcb, &page);
+ if (!nested_vmcb)
+ return 1;
+ enter_svm_guest_mode(svm, vmcb, nested_vmcb, page);
}
- return ret;
+ return 0;
}
static int enable_smi_window(struct kvm_vcpu *vcpu)
diff --git a/arch/x86/kvm/trace.h b/arch/x86/kvm/trace.h
index 6432d08c7de7..4d47a2631d1f 100644
--- a/arch/x86/kvm/trace.h
+++ b/arch/x86/kvm/trace.h
@@ -438,13 +438,13 @@ TRACE_EVENT(kvm_apic_ipi,
);
TRACE_EVENT(kvm_apic_accept_irq,
- TP_PROTO(__u32 apicid, __u16 dm, __u8 tm, __u8 vec),
+ TP_PROTO(__u32 apicid, __u16 dm, __u16 tm, __u8 vec),
TP_ARGS(apicid, dm, tm, vec),
TP_STRUCT__entry(
__field( __u32, apicid )
__field( __u16, dm )
- __field( __u8, tm )
+ __field( __u16, tm )
__field( __u8, vec )
),
diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c
index 7ec9bb1dd723..6401eb7ef19c 100644
--- a/arch/x86/kvm/vmx/nested.c
+++ b/arch/x86/kvm/vmx/nested.c
@@ -2873,20 +2873,27 @@ static void nested_get_vmcs12_pages(struct kvm_vcpu *vcpu)
/*
* If translation failed, VM entry will fail because
* prepare_vmcs02 set VIRTUAL_APIC_PAGE_ADDR to -1ull.
- * Failing the vm entry is _not_ what the processor
- * does but it's basically the only possibility we
- * have. We could still enter the guest if CR8 load
- * exits are enabled, CR8 store exits are enabled, and
- * virtualize APIC access is disabled; in this case
- * the processor would never use the TPR shadow and we
- * could simply clear the bit from the execution
- * control. But such a configuration is useless, so
- * let's keep the code simple.
*/
if (!is_error_page(page)) {
vmx->nested.virtual_apic_page = page;
hpa = page_to_phys(vmx->nested.virtual_apic_page);
vmcs_write64(VIRTUAL_APIC_PAGE_ADDR, hpa);
+ } else if (nested_cpu_has(vmcs12, CPU_BASED_CR8_LOAD_EXITING) &&
+ nested_cpu_has(vmcs12, CPU_BASED_CR8_STORE_EXITING) &&
+ !nested_cpu_has2(vmcs12, SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES)) {
+ /*
+ * The processor will never use the TPR shadow, simply
+ * clear the bit from the execution control. Such a
+ * configuration is useless, but it happens in tests.
+ * For any other configuration, failing the vm entry is
+ * _not_ what the processor does but it's basically the
+ * only possibility we have.
+ */
+ vmcs_clear_bits(CPU_BASED_VM_EXEC_CONTROL,
+ CPU_BASED_TPR_SHADOW);
+ } else {
+ printk("bad virtual-APIC page address\n");
+ dump_vmcs();
}
}
@@ -3789,8 +3796,18 @@ static void nested_vmx_restore_host_state(struct kvm_vcpu *vcpu)
vmx_set_cr4(vcpu, vmcs_readl(CR4_READ_SHADOW));
nested_ept_uninit_mmu_context(vcpu);
- vcpu->arch.cr3 = vmcs_readl(GUEST_CR3);
- __set_bit(VCPU_EXREG_CR3, (ulong *)&vcpu->arch.regs_avail);
+
+ /*
+ * This is only valid if EPT is in use, otherwise the vmcs01 GUEST_CR3
+ * points to shadow pages! Fortunately we only get here after a WARN_ON
+ * if EPT is disabled, so a VMabort is perfectly fine.
+ */
+ if (enable_ept) {
+ vcpu->arch.cr3 = vmcs_readl(GUEST_CR3);
+ __set_bit(VCPU_EXREG_CR3, (ulong *)&vcpu->arch.regs_avail);
+ } else {
+ nested_vmx_abort(vcpu, VMX_ABORT_VMCS_CORRUPTED);
+ }
/*
* Use ept_save_pdptrs(vcpu) to load the MMU's cached PDPTRs
@@ -5738,6 +5755,14 @@ __init int nested_vmx_hardware_setup(int (*exit_handlers[])(struct kvm_vcpu *))
{
int i;
+ /*
+ * Without EPT it is not possible to restore L1's CR3 and PDPTR on
+ * VMfail, because they are not available in vmcs01. Just always
+ * use hardware checks.
+ */
+ if (!enable_ept)
+ nested_early_check = 1;
+
if (!cpu_has_vmx_shadow_vmcs())
enable_shadow_vmcs = 0;
if (enable_shadow_vmcs) {
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index ab432a930ae8..b4e7d645275a 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -5603,7 +5603,7 @@ static void vmx_dump_dtsel(char *name, uint32_t limit)
vmcs_readl(limit + GUEST_GDTR_BASE - GUEST_GDTR_LIMIT));
}
-static void dump_vmcs(void)
+void dump_vmcs(void)
{
u32 vmentry_ctl = vmcs_read32(VM_ENTRY_CONTROLS);
u32 vmexit_ctl = vmcs_read32(VM_EXIT_CONTROLS);
@@ -6410,6 +6410,8 @@ static void vmx_vcpu_run(struct kvm_vcpu *vcpu)
if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP)
vmx_set_interrupt_shadow(vcpu, 0);
+ kvm_load_guest_xcr0(vcpu);
+
if (static_cpu_has(X86_FEATURE_PKU) &&
kvm_read_cr4_bits(vcpu, X86_CR4_PKE) &&
vcpu->arch.pkru != vmx->host_pkru)
@@ -6506,6 +6508,8 @@ static void vmx_vcpu_run(struct kvm_vcpu *vcpu)
__write_pkru(vmx->host_pkru);
}
+ kvm_put_guest_xcr0(vcpu);
+
vmx->nested.nested_run_pending = 0;
vmx->idt_vectoring_info = 0;
@@ -6852,6 +6856,30 @@ static void nested_vmx_entry_exit_ctls_update(struct kvm_vcpu *vcpu)
}
}
+static bool guest_cpuid_has_pmu(struct kvm_vcpu *vcpu)
+{
+ struct kvm_cpuid_entry2 *entry;
+ union cpuid10_eax eax;
+
+ entry = kvm_find_cpuid_entry(vcpu, 0xa, 0);
+ if (!entry)
+ return false;
+
+ eax.full = entry->eax;
+ return (eax.split.version_id > 0);
+}
+
+static void nested_vmx_procbased_ctls_update(struct kvm_vcpu *vcpu)
+{
+ struct vcpu_vmx *vmx = to_vmx(vcpu);
+ bool pmu_enabled = guest_cpuid_has_pmu(vcpu);
+
+ if (pmu_enabled)
+ vmx->nested.msrs.procbased_ctls_high |= CPU_BASED_RDPMC_EXITING;
+ else
+ vmx->nested.msrs.procbased_ctls_high &= ~CPU_BASED_RDPMC_EXITING;
+}
+
static void update_intel_pt_cfg(struct kvm_vcpu *vcpu)
{
struct vcpu_vmx *vmx = to_vmx(vcpu);
@@ -6940,6 +6968,7 @@ static void vmx_cpuid_update(struct kvm_vcpu *vcpu)
if (nested_vmx_allowed(vcpu)) {
nested_vmx_cr_fixed1_bits_update(vcpu);
nested_vmx_entry_exit_ctls_update(vcpu);
+ nested_vmx_procbased_ctls_update(vcpu);
}
if (boot_cpu_has(X86_FEATURE_INTEL_PT) &&
@@ -7369,7 +7398,7 @@ static int vmx_pre_enter_smm(struct kvm_vcpu *vcpu, char *smstate)
return 0;
}
-static int vmx_pre_leave_smm(struct kvm_vcpu *vcpu, u64 smbase)
+static int vmx_pre_leave_smm(struct kvm_vcpu *vcpu, const char *smstate)
{
struct vcpu_vmx *vmx = to_vmx(vcpu);
int ret;
@@ -7380,9 +7409,7 @@ static int vmx_pre_leave_smm(struct kvm_vcpu *vcpu, u64 smbase)
}
if (vmx->nested.smm.guest_mode) {
- vcpu->arch.hflags &= ~HF_SMM_MASK;
ret = nested_vmx_enter_non_root_mode(vcpu, false);
- vcpu->arch.hflags |= HF_SMM_MASK;
if (ret)
return ret;
diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h
index a1e00d0a2482..f879529906b4 100644
--- a/arch/x86/kvm/vmx/vmx.h
+++ b/arch/x86/kvm/vmx/vmx.h
@@ -517,4 +517,6 @@ static inline void decache_tsc_multiplier(struct vcpu_vmx *vmx)
vmcs_write64(TSC_MULTIPLIER, vmx->current_tsc_ratio);
}
+void dump_vmcs(void);
+
#endif /* __KVM_X86_VMX_H */
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 099b851dabaf..a0d1fc80ac5a 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -800,7 +800,7 @@ void kvm_lmsw(struct kvm_vcpu *vcpu, unsigned long msw)
}
EXPORT_SYMBOL_GPL(kvm_lmsw);
-static void kvm_load_guest_xcr0(struct kvm_vcpu *vcpu)
+void kvm_load_guest_xcr0(struct kvm_vcpu *vcpu)
{
if (kvm_read_cr4_bits(vcpu, X86_CR4_OSXSAVE) &&
!vcpu->guest_xcr0_loaded) {
@@ -810,8 +810,9 @@ static void kvm_load_guest_xcr0(struct kvm_vcpu *vcpu)
vcpu->guest_xcr0_loaded = 1;
}
}
+EXPORT_SYMBOL_GPL(kvm_load_guest_xcr0);
-static void kvm_put_guest_xcr0(struct kvm_vcpu *vcpu)
+void kvm_put_guest_xcr0(struct kvm_vcpu *vcpu)
{
if (vcpu->guest_xcr0_loaded) {
if (vcpu->arch.xcr0 != host_xcr0)
@@ -819,6 +820,7 @@ static void kvm_put_guest_xcr0(struct kvm_vcpu *vcpu)
vcpu->guest_xcr0_loaded = 0;
}
}
+EXPORT_SYMBOL_GPL(kvm_put_guest_xcr0);
static int __kvm_set_xcr(struct kvm_vcpu *vcpu, u32 index, u64 xcr)
{
@@ -3093,7 +3095,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
break;
case KVM_CAP_NESTED_STATE:
r = kvm_x86_ops->get_nested_state ?
- kvm_x86_ops->get_nested_state(NULL, 0, 0) : 0;
+ kvm_x86_ops->get_nested_state(NULL, NULL, 0) : 0;
break;
default:
break;
@@ -3528,7 +3530,7 @@ static void kvm_vcpu_ioctl_x86_get_vcpu_events(struct kvm_vcpu *vcpu,
memset(&events->reserved, 0, sizeof(events->reserved));
}
-static void kvm_set_hflags(struct kvm_vcpu *vcpu, unsigned emul_flags);
+static void kvm_smm_changed(struct kvm_vcpu *vcpu);
static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu,
struct kvm_vcpu_events *events)
@@ -3588,12 +3590,13 @@ static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu,
vcpu->arch.apic->sipi_vector = events->sipi_vector;
if (events->flags & KVM_VCPUEVENT_VALID_SMM) {
- u32 hflags = vcpu->arch.hflags;
- if (events->smi.smm)
- hflags |= HF_SMM_MASK;
- else
- hflags &= ~HF_SMM_MASK;
- kvm_set_hflags(vcpu, hflags);
+ if (!!(vcpu->arch.hflags & HF_SMM_MASK) != events->smi.smm) {
+ if (events->smi.smm)
+ vcpu->arch.hflags |= HF_SMM_MASK;
+ else
+ vcpu->arch.hflags &= ~HF_SMM_MASK;
+ kvm_smm_changed(vcpu);
+ }
vcpu->arch.smi_pending = events->smi.pending;
@@ -4270,7 +4273,7 @@ static int kvm_vm_ioctl_set_identity_map_addr(struct kvm *kvm,
}
static int kvm_vm_ioctl_set_nr_mmu_pages(struct kvm *kvm,
- u32 kvm_nr_mmu_pages)
+ unsigned long kvm_nr_mmu_pages)
{
if (kvm_nr_mmu_pages < KVM_MIN_ALLOC_MMU_PAGES)
return -EINVAL;
@@ -4284,7 +4287,7 @@ static int kvm_vm_ioctl_set_nr_mmu_pages(struct kvm *kvm,
return 0;
}
-static int kvm_vm_ioctl_get_nr_mmu_pages(struct kvm *kvm)
+static unsigned long kvm_vm_ioctl_get_nr_mmu_pages(struct kvm *kvm)
{
return kvm->arch.n_max_mmu_pages;
}
@@ -5958,12 +5961,18 @@ static unsigned emulator_get_hflags(struct x86_emulate_ctxt *ctxt)
static void emulator_set_hflags(struct x86_emulate_ctxt *ctxt, unsigned emul_flags)
{
- kvm_set_hflags(emul_to_vcpu(ctxt), emul_flags);
+ emul_to_vcpu(ctxt)->arch.hflags = emul_flags;
+}
+
+static int emulator_pre_leave_smm(struct x86_emulate_ctxt *ctxt,
+ const char *smstate)
+{
+ return kvm_x86_ops->pre_leave_smm(emul_to_vcpu(ctxt), smstate);
}
-static int emulator_pre_leave_smm(struct x86_emulate_ctxt *ctxt, u64 smbase)
+static void emulator_post_leave_smm(struct x86_emulate_ctxt *ctxt)
{
- return kvm_x86_ops->pre_leave_smm(emul_to_vcpu(ctxt), smbase);
+ kvm_smm_changed(emul_to_vcpu(ctxt));
}
static const struct x86_emulate_ops emulate_ops = {
@@ -6006,6 +6015,7 @@ static const struct x86_emulate_ops emulate_ops = {
.get_hflags = emulator_get_hflags,
.set_hflags = emulator_set_hflags,
.pre_leave_smm = emulator_pre_leave_smm,
+ .post_leave_smm = emulator_post_leave_smm,
};
static void toggle_interruptibility(struct kvm_vcpu *vcpu, u32 mask)
@@ -6247,16 +6257,6 @@ static void kvm_smm_changed(struct kvm_vcpu *vcpu)
kvm_mmu_reset_context(vcpu);
}
-static void kvm_set_hflags(struct kvm_vcpu *vcpu, unsigned emul_flags)
-{
- unsigned changed = vcpu->arch.hflags ^ emul_flags;
-
- vcpu->arch.hflags = emul_flags;
-
- if (changed & HF_SMM_MASK)
- kvm_smm_changed(vcpu);
-}
-
static int kvm_vcpu_check_hw_bp(unsigned long addr, u32 type, u32 dr7,
unsigned long *db)
{
@@ -7441,9 +7441,9 @@ static void enter_smm_save_state_32(struct kvm_vcpu *vcpu, char *buf)
put_smstate(u32, buf, 0x7ef8, vcpu->arch.smbase);
}
+#ifdef CONFIG_X86_64
static void enter_smm_save_state_64(struct kvm_vcpu *vcpu, char *buf)
{
-#ifdef CONFIG_X86_64
struct desc_ptr dt;
struct kvm_segment seg;
unsigned long val;
@@ -7493,10 +7493,8 @@ static void enter_smm_save_state_64(struct kvm_vcpu *vcpu, char *buf)
for (i = 0; i < 6; i++)
enter_smm_save_seg_64(vcpu, buf, i);
-#else
- WARN_ON_ONCE(1);
-#endif
}
+#endif
static void enter_smm(struct kvm_vcpu *vcpu)
{
@@ -7507,9 +7505,11 @@ static void enter_smm(struct kvm_vcpu *vcpu)
trace_kvm_enter_smm(vcpu->vcpu_id, vcpu->arch.smbase, true);
memset(buf, 0, 512);
+#ifdef CONFIG_X86_64
if (guest_cpuid_has(vcpu, X86_FEATURE_LM))
enter_smm_save_state_64(vcpu, buf);
else
+#endif
enter_smm_save_state_32(vcpu, buf);
/*
@@ -7567,8 +7567,10 @@ static void enter_smm(struct kvm_vcpu *vcpu)
kvm_set_segment(vcpu, &ds, VCPU_SREG_GS);
kvm_set_segment(vcpu, &ds, VCPU_SREG_SS);
+#ifdef CONFIG_X86_64
if (guest_cpuid_has(vcpu, X86_FEATURE_LM))
kvm_x86_ops->set_efer(vcpu, 0);
+#endif
kvm_update_cpuid(vcpu);
kvm_mmu_reset_context(vcpu);
@@ -7865,8 +7867,6 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
goto cancel_injection;
}
- kvm_load_guest_xcr0(vcpu);
-
if (req_immediate_exit) {
kvm_make_request(KVM_REQ_EVENT, vcpu);
kvm_x86_ops->request_immediate_exit(vcpu);
@@ -7919,8 +7919,6 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
vcpu->mode = OUTSIDE_GUEST_MODE;
smp_wmb();
- kvm_put_guest_xcr0(vcpu);
-
kvm_before_interrupt(vcpu);
kvm_x86_ops->handle_external_intr(vcpu);
kvm_after_interrupt(vcpu);
diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h
index 28406aa1136d..aedc5d0d4989 100644
--- a/arch/x86/kvm/x86.h
+++ b/arch/x86/kvm/x86.h
@@ -347,4 +347,6 @@ static inline void kvm_after_interrupt(struct kvm_vcpu *vcpu)
__this_cpu_write(current_vcpu, NULL);
}
+void kvm_load_guest_xcr0(struct kvm_vcpu *vcpu);
+void kvm_put_guest_xcr0(struct kvm_vcpu *vcpu);
#endif