#include <asm/reg.h>
#include <asm/cputable.h>
-#include <asm/cache.h>
#include <asm/cacheflush.h>
#include <asm/tlbflush.h>
#include <asm/uaccess.h>
static DECLARE_BITMAP(default_enabled_hcalls, MAX_HCALL_OPCODE/4 + 1);
-#if defined(CONFIG_PPC_64K_PAGES)
-#define MPP_BUFFER_ORDER 0
-#elif defined(CONFIG_PPC_4K_PAGES)
-#define MPP_BUFFER_ORDER 3
-#endif
-
static int dynamic_mt_modes = 6;
module_param(dynamic_mt_modes, int, S_IRUGO | S_IWUSR);
MODULE_PARM_DESC(dynamic_mt_modes, "Set of allowed dynamic micro-threading modes: 0 (= none), 2, 4, or 6 (= 2 or 4)");
vcore->kvm = kvm;
INIT_LIST_HEAD(&vcore->preempt_list);
- vcore->mpp_buffer_is_valid = false;
-
- if (cpu_has_feature(CPU_FTR_ARCH_207S))
- vcore->mpp_buffer = (void *)__get_free_pages(
- GFP_KERNEL|__GFP_ZERO,
- MPP_BUFFER_ORDER);
-
return vcore;
}
return 1;
}
-static void kvmppc_start_saving_l2_cache(struct kvmppc_vcore *vc)
-{
- phys_addr_t phy_addr, mpp_addr;
-
- phy_addr = (phys_addr_t)virt_to_phys(vc->mpp_buffer);
- mpp_addr = phy_addr & PPC_MPPE_ADDRESS_MASK;
-
- mtspr(SPRN_MPPR, mpp_addr | PPC_MPPR_FETCH_ABORT);
- logmpp(mpp_addr | PPC_LOGMPP_LOG_L2);
-
- vc->mpp_buffer_is_valid = true;
-}
-
-static void kvmppc_start_restoring_l2_cache(const struct kvmppc_vcore *vc)
-{
- phys_addr_t phy_addr, mpp_addr;
-
- phy_addr = virt_to_phys(vc->mpp_buffer);
- mpp_addr = phy_addr & PPC_MPPE_ADDRESS_MASK;
-
- /* We must abort any in-progress save operations to ensure
- * the table is valid so that prefetch engine knows when to
- * stop prefetching. */
- logmpp(mpp_addr | PPC_LOGMPP_LOG_ABORT);
- mtspr(SPRN_MPPR, mpp_addr | PPC_MPPR_FETCH_WHOLE_TABLE);
-}
-
/*
* A list of virtual cores for each physical CPU.
* These are vcores that could run but their runner VCPU tasks are
return false;
n_subcores += (cip->subcore_threads[sub] - 1) >> 1;
}
- if (n_subcores > 3 || large_sub < 0)
+ if (large_sub < 0 || !subcore_config_ok(n_subcores + 1, 2))
return false;
/*
srcu_idx = srcu_read_lock(&vc->kvm->srcu);
- if (vc->mpp_buffer_is_valid)
- kvmppc_start_restoring_l2_cache(vc);
-
__kvmppc_vcore_entry();
- if (vc->mpp_buffer)
- kvmppc_start_saving_l2_cache(vc);
-
srcu_read_unlock(&vc->kvm->srcu, srcu_idx);
spin_lock(&vc->lock);
{
long int i;
- for (i = 0; i < KVM_MAX_VCORES; ++i) {
- if (kvm->arch.vcores[i] && kvm->arch.vcores[i]->mpp_buffer) {
- struct kvmppc_vcore *vc = kvm->arch.vcores[i];
- free_pages((unsigned long)vc->mpp_buffer,
- MPP_BUFFER_ORDER);
- }
+ for (i = 0; i < KVM_MAX_VCORES; ++i)
kfree(kvm->arch.vcores[i]);
- }
kvm->arch.online_vcores = 0;
}
static void process_nmi(struct kvm_vcpu *vcpu);
static void __kvm_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags);
- struct kvm_x86_ops *kvm_x86_ops;
+ struct kvm_x86_ops *kvm_x86_ops __read_mostly;
EXPORT_SYMBOL_GPL(kvm_x86_ops);
- static bool ignore_msrs = 0;
+ static bool __read_mostly ignore_msrs = 0;
module_param(ignore_msrs, bool, S_IRUGO | S_IWUSR);
unsigned int min_timer_period_us = 500;
static bool __read_mostly kvmclock_periodic_sync = true;
module_param(kvmclock_periodic_sync, bool, S_IRUGO);
- bool kvm_has_tsc_control;
+ bool __read_mostly kvm_has_tsc_control;
EXPORT_SYMBOL_GPL(kvm_has_tsc_control);
- u32 kvm_max_guest_tsc_khz;
+ u32 __read_mostly kvm_max_guest_tsc_khz;
EXPORT_SYMBOL_GPL(kvm_max_guest_tsc_khz);
+ u8 __read_mostly kvm_tsc_scaling_ratio_frac_bits;
+ EXPORT_SYMBOL_GPL(kvm_tsc_scaling_ratio_frac_bits);
+ u64 __read_mostly kvm_max_tsc_scaling_ratio;
+ EXPORT_SYMBOL_GPL(kvm_max_tsc_scaling_ratio);
+ static u64 __read_mostly kvm_default_tsc_scaling_ratio;
/* tsc tolerance in parts per million - default to 1/2 of the NTP threshold */
- static u32 tsc_tolerance_ppm = 250;
+ static u32 __read_mostly tsc_tolerance_ppm = 250;
module_param(tsc_tolerance_ppm, uint, S_IRUGO | S_IWUSR);
/* lapic timer advance (tscdeadline mode only) in nanoseconds */
- unsigned int lapic_timer_advance_ns = 0;
+ unsigned int __read_mostly lapic_timer_advance_ns = 0;
module_param(lapic_timer_advance_ns, uint, S_IRUGO | S_IWUSR);
- static bool backwards_tsc_observed = false;
+ static bool __read_mostly backwards_tsc_observed = false;
#define KVM_NR_SHARED_MSRS 16
/* Only support XCR_XFEATURE_ENABLED_MASK(xcr0) now */
if (index != XCR_XFEATURE_ENABLED_MASK)
return 1;
- if (!(xcr0 & XSTATE_FP))
+ if (!(xcr0 & XFEATURE_MASK_FP))
return 1;
- if ((xcr0 & XSTATE_YMM) && !(xcr0 & XSTATE_SSE))
+ if ((xcr0 & XFEATURE_MASK_YMM) && !(xcr0 & XFEATURE_MASK_SSE))
return 1;
/*
* saving. However, xcr0 bit 0 is always set, even if the
* emulated CPU does not support XSAVE (see fx_init).
*/
- valid_bits = vcpu->arch.guest_supported_xcr0 | XSTATE_FP;
+ valid_bits = vcpu->arch.guest_supported_xcr0 | XFEATURE_MASK_FP;
if (xcr0 & ~valid_bits)
return 1;
- if ((!(xcr0 & XSTATE_BNDREGS)) != (!(xcr0 & XSTATE_BNDCSR)))
+ if ((!(xcr0 & XFEATURE_MASK_BNDREGS)) !=
+ (!(xcr0 & XFEATURE_MASK_BNDCSR)))
return 1;
- if (xcr0 & XSTATE_AVX512) {
- if (!(xcr0 & XSTATE_YMM))
+ if (xcr0 & XFEATURE_MASK_AVX512) {
+ if (!(xcr0 & XFEATURE_MASK_YMM))
return 1;
- if ((xcr0 & XSTATE_AVX512) != XSTATE_AVX512)
+ if ((xcr0 & XFEATURE_MASK_AVX512) != XFEATURE_MASK_AVX512)
return 1;
}
kvm_put_guest_xcr0(vcpu);
vcpu->arch.xcr0 = xcr0;
- if ((xcr0 ^ old_xcr0) & XSTATE_EXTEND_MASK)
+ if ((xcr0 ^ old_xcr0) & XFEATURE_MASK_EXTEND)
kvm_update_cpuid(vcpu);
return 0;
}
return v;
}
- static void kvm_set_tsc_khz(struct kvm_vcpu *vcpu, u32 this_tsc_khz)
+ static int set_tsc_khz(struct kvm_vcpu *vcpu, u32 user_tsc_khz, bool scale)
+ {
+ u64 ratio;
+
+ /* Guest TSC same frequency as host TSC? */
+ if (!scale) {
+ vcpu->arch.tsc_scaling_ratio = kvm_default_tsc_scaling_ratio;
+ return 0;
+ }
+
+ /* TSC scaling supported? */
+ if (!kvm_has_tsc_control) {
+ if (user_tsc_khz > tsc_khz) {
+ vcpu->arch.tsc_catchup = 1;
+ vcpu->arch.tsc_always_catchup = 1;
+ return 0;
+ } else {
+ WARN(1, "user requested TSC rate below hardware speed\n");
+ return -1;
+ }
+ }
+
+ /* TSC scaling required - calculate ratio */
+ ratio = mul_u64_u32_div(1ULL << kvm_tsc_scaling_ratio_frac_bits,
+ user_tsc_khz, tsc_khz);
+
+ if (ratio == 0 || ratio >= kvm_max_tsc_scaling_ratio) {
+ WARN_ONCE(1, "Invalid TSC scaling ratio - virtual-tsc-khz=%u\n",
+ user_tsc_khz);
+ return -1;
+ }
+
+ vcpu->arch.tsc_scaling_ratio = ratio;
+ return 0;
+ }
+
+ static int kvm_set_tsc_khz(struct kvm_vcpu *vcpu, u32 this_tsc_khz)
{
u32 thresh_lo, thresh_hi;
int use_scaling = 0;
/* tsc_khz can be zero if TSC calibration fails */
- if (this_tsc_khz == 0)
- return;
+ if (this_tsc_khz == 0) {
+ /* set tsc_scaling_ratio to a safe value */
+ vcpu->arch.tsc_scaling_ratio = kvm_default_tsc_scaling_ratio;
+ return -1;
+ }
/* Compute a scale to convert nanoseconds in TSC cycles */
kvm_get_time_scale(this_tsc_khz, NSEC_PER_SEC / 1000,
pr_debug("kvm: requested TSC rate %u falls outside tolerance [%u,%u]\n", this_tsc_khz, thresh_lo, thresh_hi);
use_scaling = 1;
}
- kvm_x86_ops->set_tsc_khz(vcpu, this_tsc_khz, use_scaling);
+ return set_tsc_khz(vcpu, this_tsc_khz, use_scaling);
}
static u64 compute_guest_tsc(struct kvm_vcpu *vcpu, s64 kernel_ns)
vcpu->arch.ia32_tsc_adjust_msr += offset - curr_offset;
}
+ /*
+ * Multiply tsc by a fixed point number represented by ratio.
+ *
+ * The most significant 64-N bits (mult) of ratio represent the
+ * integral part of the fixed point number; the remaining N bits
+ * (frac) represent the fractional part, ie. ratio represents a fixed
+ * point number (mult + frac * 2^(-N)).
+ *
+ * N equals to kvm_tsc_scaling_ratio_frac_bits.
+ */
+ static inline u64 __scale_tsc(u64 ratio, u64 tsc)
+ {
+ return mul_u64_u64_shr(tsc, ratio, kvm_tsc_scaling_ratio_frac_bits);
+ }
+
+ u64 kvm_scale_tsc(struct kvm_vcpu *vcpu, u64 tsc)
+ {
+ u64 _tsc = tsc;
+ u64 ratio = vcpu->arch.tsc_scaling_ratio;
+
+ if (ratio != kvm_default_tsc_scaling_ratio)
+ _tsc = __scale_tsc(ratio, tsc);
+
+ return _tsc;
+ }
+ EXPORT_SYMBOL_GPL(kvm_scale_tsc);
+
+ static u64 kvm_compute_tsc_offset(struct kvm_vcpu *vcpu, u64 target_tsc)
+ {
+ u64 tsc;
+
+ tsc = kvm_scale_tsc(vcpu, rdtsc());
+
+ return target_tsc - tsc;
+ }
+
+ u64 kvm_read_l1_tsc(struct kvm_vcpu *vcpu, u64 host_tsc)
+ {
+ return kvm_x86_ops->read_l1_tsc(vcpu, kvm_scale_tsc(vcpu, host_tsc));
+ }
+ EXPORT_SYMBOL_GPL(kvm_read_l1_tsc);
+
void kvm_write_tsc(struct kvm_vcpu *vcpu, struct msr_data *msr)
{
struct kvm *kvm = vcpu->kvm;
u64 data = msr->data;
raw_spin_lock_irqsave(&kvm->arch.tsc_write_lock, flags);
- offset = kvm_x86_ops->compute_tsc_offset(vcpu, data);
+ offset = kvm_compute_tsc_offset(vcpu, data);
ns = get_kernel_ns();
elapsed = ns - kvm->arch.last_tsc_nsec;
} else {
u64 delta = nsec_to_cycles(vcpu, elapsed);
data += delta;
- offset = kvm_x86_ops->compute_tsc_offset(vcpu, data);
+ offset = kvm_compute_tsc_offset(vcpu, data);
pr_debug("kvm: adjusted tsc offset by %llu\n", delta);
}
matched = true;
EXPORT_SYMBOL_GPL(kvm_write_tsc);
+ static inline void adjust_tsc_offset_guest(struct kvm_vcpu *vcpu,
+ s64 adjustment)
+ {
+ kvm_x86_ops->adjust_tsc_offset_guest(vcpu, adjustment);
+ }
+
+ static inline void adjust_tsc_offset_host(struct kvm_vcpu *vcpu, s64 adjustment)
+ {
+ if (vcpu->arch.tsc_scaling_ratio != kvm_default_tsc_scaling_ratio)
+ WARN_ON(adjustment < 0);
+ adjustment = kvm_scale_tsc(vcpu, (u64) adjustment);
+ kvm_x86_ops->adjust_tsc_offset_guest(vcpu, adjustment);
+ }
+
#ifdef CONFIG_X86_64
static cycle_t read_tsc(void)
static int kvm_guest_time_update(struct kvm_vcpu *v)
{
- unsigned long flags, this_tsc_khz;
+ unsigned long flags, this_tsc_khz, tgt_tsc_khz;
struct kvm_vcpu_arch *vcpu = &v->arch;
struct kvm_arch *ka = &v->kvm->arch;
s64 kernel_ns;
kernel_ns = get_kernel_ns();
}
- tsc_timestamp = kvm_x86_ops->read_l1_tsc(v, host_tsc);
+ tsc_timestamp = kvm_read_l1_tsc(v, host_tsc);
/*
* We may have to catch up the TSC to match elapsed wall clock
return 0;
if (unlikely(vcpu->hw_tsc_khz != this_tsc_khz)) {
- kvm_get_time_scale(NSEC_PER_SEC / 1000, this_tsc_khz,
+ tgt_tsc_khz = kvm_has_tsc_control ?
+ vcpu->virtual_tsc_khz : this_tsc_khz;
+ kvm_get_time_scale(NSEC_PER_SEC / 1000, tgt_tsc_khz,
&vcpu->hv_clock.tsc_shift,
&vcpu->hv_clock.tsc_to_system_mul);
vcpu->hw_tsc_khz = this_tsc_khz;
if (tsc_delta < 0)
mark_tsc_unstable("KVM discovered backwards TSC");
if (check_tsc_unstable()) {
- u64 offset = kvm_x86_ops->compute_tsc_offset(vcpu,
+ u64 offset = kvm_compute_tsc_offset(vcpu,
vcpu->arch.last_guest_tsc);
kvm_x86_ops->write_tsc_offset(vcpu, offset);
vcpu->arch.tsc_catchup = 1;
* Copy each region from the possibly compacted offset to the
* non-compacted offset.
*/
- valid = xstate_bv & ~XSTATE_FPSSE;
+ valid = xstate_bv & ~XFEATURE_MASK_FPSSE;
while (valid) {
u64 feature = valid & -valid;
int index = fls64(feature) - 1;
* Copy each region from the non-compacted offset to the
* possibly compacted offset.
*/
- valid = xstate_bv & ~XSTATE_FPSSE;
+ valid = xstate_bv & ~XFEATURE_MASK_FPSSE;
while (valid) {
u64 feature = valid & -valid;
int index = fls64(feature) - 1;
&vcpu->arch.guest_fpu.state.fxsave,
sizeof(struct fxregs_state));
*(u64 *)&guest_xsave->region[XSAVE_HDR_OFFSET / sizeof(u32)] =
- XSTATE_FPSSE;
+ XFEATURE_MASK_FPSSE;
}
}
return -EINVAL;
load_xsave(vcpu, (u8 *)guest_xsave->region);
} else {
- if (xstate_bv & ~XSTATE_FPSSE)
+ if (xstate_bv & ~XFEATURE_MASK_FPSSE)
return -EINVAL;
memcpy(&vcpu->arch.guest_fpu.state.fxsave,
guest_xsave->region, sizeof(struct fxregs_state));
if (user_tsc_khz == 0)
user_tsc_khz = tsc_khz;
- kvm_set_tsc_khz(vcpu, user_tsc_khz);
+ if (!kvm_set_tsc_khz(vcpu, user_tsc_khz))
+ r = 0;
- r = 0;
goto out;
}
case KVM_GET_TSC_KHZ: {
if (hw_breakpoint_active())
hw_breakpoint_restore();
- vcpu->arch.last_guest_tsc = kvm_x86_ops->read_l1_tsc(vcpu,
- rdtsc());
+ vcpu->arch.last_guest_tsc = kvm_read_l1_tsc(vcpu, rdtsc());
vcpu->mode = OUTSIDE_GUEST_MODE;
smp_wmb();
*/
kvm_set_rflags(vcpu, rflags);
- kvm_x86_ops->update_db_bp_intercept(vcpu);
+ kvm_x86_ops->update_bp_intercept(vcpu);
r = 0;
/*
* Ensure guest xcr0 is valid for loading
*/
- vcpu->arch.xcr0 = XSTATE_FP;
+ vcpu->arch.xcr0 = XFEATURE_MASK_FP;
vcpu->arch.cr0 |= X86_CR0_ET;
}
if (r != 0)
return r;
+ if (kvm_has_tsc_control) {
+ /*
+ * Make sure the user can only configure tsc_khz values that
+ * fit into a signed integer.
+ * A min value is not calculated needed because it will always
+ * be 1 on all machines.
+ */
+ u64 max = min(0x7fffffffULL,
+ __scale_tsc(kvm_max_tsc_scaling_ratio, tsc_khz));
+ kvm_max_guest_tsc_khz = max;
+
+ kvm_default_tsc_scaling_ratio = 1ULL << kvm_tsc_scaling_ratio_frac_bits;
+ }
+
kvm_init_msr_list();
return 0;
}