hvm: Build guest timers on monotonic system time.

Move hvm platform timers from underlying physical CPU TSC to Xen
system time and ensure domain-wide monotonicity. TSC on many systems
may skew between processors leading to 'time going backwards' messages
from some guests.

Signed-off-by: Dan Magenheimer <dan.magenheimer@oracle.com>
Signed-off-by: Keir Fraser <keir.fraser@citrix.com>

diff --git a/xen/arch/x86/hvm/hpet.c b/xen/arch/x86/hvm/hpet.c
index 3b9f84250a647aed9a9d2a6cca631b73c40fa5d5..e8a83949f1e3d711c9b92f49e3690f0d6b01569f 100644 (file)
--- a/xen/arch/x86/hvm/hpet.c
+++ b/xen/arch/x86/hvm/hpet.c
@@ -29,9 +29,9 @@
 #define S_TO_NS  1000000000ULL           /* 1s  = 10^9  ns */
 #define S_TO_FS  1000000000000000ULL     /* 1s  = 10^15 fs */
 
-/* Frequency_of_TSC / frequency_of_HPET = 32 */
-#define TSC_PER_HPET_TICK 32
-#define guest_time_hpet(v) (hvm_get_guest_time(v) / TSC_PER_HPET_TICK)
+/* Frequency_of_Xen_systeme_time / frequency_of_HPET = 16 */
+#define STIME_PER_HPET_TICK 16
+#define guest_time_hpet(v) (hvm_get_guest_time(v) / STIME_PER_HPET_TICK)
 
 #define HPET_ID         0x000
 #define HPET_PERIOD     0x004
@@ -192,7 +192,7 @@ static void hpet_stop_timer(HPETState *h, unsigned int tn)
 
 /* the number of HPET tick that stands for
  * 1/(2^10) second, namely, 0.9765625 milliseconds */
-#define  HPET_TINY_TIME_SPAN  ((h->tsc_freq >> 10) / TSC_PER_HPET_TICK)
+#define  HPET_TINY_TIME_SPAN  ((h->stime_freq >> 10) / STIME_PER_HPET_TICK)
 
 static void hpet_set_timer(HPETState *h, unsigned int tn)
 {
@@ -558,17 +558,17 @@ void hpet_init(struct vcpu *v)
     spin_lock_init(&h->lock);
 
     h->vcpu = v;
-    h->tsc_freq = ticks_per_sec(v);
+    h->stime_freq = S_TO_NS;
 
-    h->hpet_to_ns_scale = ((S_TO_NS * TSC_PER_HPET_TICK) << 10) / h->tsc_freq;
+    h->hpet_to_ns_scale = ((S_TO_NS * STIME_PER_HPET_TICK) << 10) / h->stime_freq;
     h->hpet_to_ns_limit = ~0ULL / h->hpet_to_ns_scale;
 
     /* 64-bit main counter; 3 timers supported; LegacyReplacementRoute. */
     h->hpet.capability = 0x8086A201ULL;
 
     /* This is the number of femptoseconds per HPET tick. */
-    /* Here we define HPET's frequency to be 1/32 of the TSC's */
-    h->hpet.capability |= ((S_TO_FS*TSC_PER_HPET_TICK/h->tsc_freq) << 32);
+    /* Here we define HPET's frequency to be 1/16 of Xen system time */
+    h->hpet.capability |= ((S_TO_FS*STIME_PER_HPET_TICK/h->stime_freq) << 32);
 
     for ( i = 0; i < HPET_TIMER_NUM; i++ )
     {

diff --git a/xen/arch/x86/hvm/hvm.c b/xen/arch/x86/hvm/hvm.c
index 5052da58d882bbd33d6d30478c97bf9fa716cd16..80f494f584ef7e4938b5acaf01ed9ee29895d03d 100644 (file)
--- a/xen/arch/x86/hvm/hvm.c
+++ b/xen/arch/x86/hvm/hvm.c
@@ -296,6 +296,8 @@ int hvm_domain_initialise(struct domain *d)
     spin_lock_init(&d->arch.hvm_domain.irq_lock);
     spin_lock_init(&d->arch.hvm_domain.uc_lock);
 
+    hvm_init_guest_time(d);
+
     d->arch.hvm_domain.params[HVM_PARAM_HPET_ENABLED] = 1;
 
     hvm_init_cacheattr_region_list(d);
@@ -661,7 +663,7 @@ int hvm_vcpu_initialise(struct vcpu *v)
         hpet_init(v);
  
         /* Init guest TSC to start from zero. */
-        hvm_set_guest_time(v, 0);
+        hvm_set_guest_tsc(v, 0);
 
         /* Can start up without SIPI-SIPI or setvcpucontext domctl. */
         v->is_initialised = 1;
@@ -1632,7 +1634,7 @@ int hvm_msr_read_intercept(struct cpu_user_regs *regs)
     switch ( ecx )
     {
     case MSR_IA32_TSC:
-        msr_content = hvm_get_guest_time(v);
+        msr_content = hvm_get_guest_tsc(v);
         break;
 
     case MSR_IA32_APICBASE:
@@ -1725,7 +1727,7 @@ int hvm_msr_write_intercept(struct cpu_user_regs *regs)
     switch ( ecx )
     {
      case MSR_IA32_TSC:
-        hvm_set_guest_time(v, msr_content);
+        hvm_set_guest_tsc(v, msr_content);
         pt_reset(v);
         break;
 

diff --git a/xen/arch/x86/hvm/i8254.c b/xen/arch/x86/hvm/i8254.c
index ea6d1f11fcfe134dbfeab0dbac6a53b109ad8892..090dbf7193b05862bb7c9005aa1c88742b5ab087 100644 (file)
--- a/xen/arch/x86/hvm/i8254.c
+++ b/xen/arch/x86/hvm/i8254.c
@@ -31,6 +31,7 @@
 #include <xen/lib.h>
 #include <xen/errno.h>
 #include <xen/sched.h>
+#include <asm/time.h>
 #include <asm/hvm/hvm.h>
 #include <asm/hvm/io.h>
 #include <asm/hvm/support.h>
@@ -87,7 +88,7 @@ static int pit_get_count(PITState *pit, int channel)
     ASSERT(spin_is_locked(&pit->lock));
 
     d = muldiv64(hvm_get_guest_time(v) - pit->count_load_time[channel],
-                 PIT_FREQ, ticks_per_sec(v));
+                 PIT_FREQ, SYSTEM_TIME_HZ);
 
     switch ( c->mode )
     {
@@ -118,7 +119,7 @@ static int pit_get_out(PITState *pit, int channel)
     ASSERT(spin_is_locked(&pit->lock));
 
     d = muldiv64(hvm_get_guest_time(v) - pit->count_load_time[channel], 
-                 PIT_FREQ, ticks_per_sec(v));
+                 PIT_FREQ, SYSTEM_TIME_HZ);
 
     switch ( s->mode )
     {
@@ -195,11 +196,11 @@ static void pit_load_count(PITState *pit, int channel, int val)
         val = 0x10000;
 
     if ( v == NULL )
-        rdtscll(pit->count_load_time[channel]);
+        pit->count_load_time[channel] = 0;
     else
         pit->count_load_time[channel] = hvm_get_guest_time(v);
     s->count = val;
-    period = DIV_ROUND((val * 1000000000ULL), PIT_FREQ);
+    period = DIV_ROUND(val * SYSTEM_TIME_HZ, PIT_FREQ);
 
     if ( (v == NULL) || !is_hvm_vcpu(v) || (channel != 0) )
         return;

diff --git a/xen/arch/x86/hvm/pmtimer.c b/xen/arch/x86/hvm/pmtimer.c
index ee5b58f37d6d328cb146c21fea55d54b07796835..15bb3c3ef6ed224ed1297f54dfc3da88debf0632 100644 (file)
--- a/xen/arch/x86/hvm/pmtimer.c
+++ b/xen/arch/x86/hvm/pmtimer.c
@@ -257,7 +257,7 @@ void pmtimer_init(struct vcpu *v)
 
     spin_lock_init(&s->lock);
 
-    s->scale = ((uint64_t)FREQUENCE_PMTIMER << 32) / ticks_per_sec(v);
+    s->scale = ((uint64_t)FREQUENCE_PMTIMER << 32) / SYSTEM_TIME_HZ;
     s->vcpu = v;
 
     /* Intercept port I/O (need two handlers because PM1a_CNT is between

diff --git a/xen/arch/x86/hvm/svm/svm.c b/xen/arch/x86/hvm/svm/svm.c
index 3468770bcbd56b59fc7140f56f16c4ee5ef0ed92..8183e4665d62450797c0dd9f6afa71be803c4312 100644 (file)
--- a/xen/arch/x86/hvm/svm/svm.c
+++ b/xen/arch/x86/hvm/svm/svm.c
@@ -299,7 +299,7 @@ static void svm_save_cpu_state(struct vcpu *v, struct hvm_hw_cpu *data)
     data->msr_efer         = v->arch.hvm_vcpu.guest_efer;
     data->msr_flags        = -1ULL;
 
-    data->tsc = hvm_get_guest_time(v);
+    data->tsc = hvm_get_guest_tsc(v);
 }
 
 
@@ -315,7 +315,7 @@ static void svm_load_cpu_state(struct vcpu *v, struct hvm_hw_cpu *data)
     v->arch.hvm_vcpu.guest_efer = data->msr_efer;
     svm_update_guest_efer(v);
 
-    hvm_set_guest_time(v, data->tsc);
+    hvm_set_guest_tsc(v, data->tsc);
 }
 
 static void svm_save_vmcb_ctxt(struct vcpu *v, struct hvm_hw_cpu *ctxt)

diff --git a/xen/arch/x86/hvm/vlapic.c b/xen/arch/x86/hvm/vlapic.c
index 5efff29d66b077db419861fd001c44151d59a456..bb6b44d2e188bb4f15f2f8bc31f2ec037d48c4bf 100644 (file)
--- a/xen/arch/x86/hvm/vlapic.c
+++ b/xen/arch/x86/hvm/vlapic.c
@@ -473,7 +473,6 @@ static uint32_t vlapic_get_tmcct(struct vlapic *vlapic)
     uint64_t counter_passed;
 
     counter_passed = ((hvm_get_guest_time(v) - vlapic->timer_last_update)
-                      * 1000000000ULL / ticks_per_sec(v)
                       / APIC_BUS_CYCLE_NS / vlapic->hw.timer_divisor);
     tmcct = tmict - counter_passed;
 

diff --git a/xen/arch/x86/hvm/vmx/vmx.c b/xen/arch/x86/hvm/vmx/vmx.c
index 4d80cf067fa903148418d6cb1716af4b766b9ee1..503b333f57cd8d017d8fbe6097537ecf22198f10 100644 (file)
--- a/xen/arch/x86/hvm/vmx/vmx.c
+++ b/xen/arch/x86/hvm/vmx/vmx.c
@@ -607,7 +607,7 @@ static void vmx_save_cpu_state(struct vcpu *v, struct hvm_hw_cpu *data)
     data->msr_syscall_mask = guest_state->msrs[VMX_INDEX_MSR_SYSCALL_MASK];
 #endif
 
-    data->tsc = hvm_get_guest_time(v);
+    data->tsc = hvm_get_guest_tsc(v);
 }
 
 static void vmx_load_cpu_state(struct vcpu *v, struct hvm_hw_cpu *data)
@@ -625,7 +625,7 @@ static void vmx_load_cpu_state(struct vcpu *v, struct hvm_hw_cpu *data)
     v->arch.hvm_vmx.shadow_gs = data->shadow_gs;
 #endif
 
-    hvm_set_guest_time(v, data->tsc);
+    hvm_set_guest_tsc(v, data->tsc);
 }
 
 

diff --git a/xen/arch/x86/hvm/vpt.c b/xen/arch/x86/hvm/vpt.c
index 832c9042d717bbb5f7716aa9977654bbd00c6d03..cb62e5e083b986ce8c73004ce1de28eb2ad4bee1 100644 (file)
--- a/xen/arch/x86/hvm/vpt.c
+++ b/xen/arch/x86/hvm/vpt.c
@@ -25,6 +25,36 @@
 #define mode_is(d, name) \
     ((d)->arch.hvm_domain.params[HVM_PARAM_TIMER_MODE] == HVMPTM_##name)
 
+void hvm_init_guest_time(struct domain *d)
+{
+    struct pl_time *pl = &d->arch.hvm_domain.pl_time;
+
+    spin_lock_init(&pl->pl_time_lock);
+    pl->stime_offset = -(u64)get_s_time();
+    pl->last_guest_time = 0;
+}
+
+u64 hvm_get_guest_time(struct vcpu *v)
+{
+    struct pl_time *pl = &v->domain->arch.hvm_domain.pl_time;
+    u64 now;
+
+    spin_lock(&pl->pl_time_lock);
+    now = get_s_time() + pl->stime_offset;
+    if ( (int64_t)(now - pl->last_guest_time) >= 0 )
+        pl->last_guest_time = now;
+    else
+        now = pl->last_guest_time;
+    spin_unlock(&pl->pl_time_lock);
+
+    return now + v->arch.hvm_vcpu.stime_offset;
+}
+
+void hvm_set_guest_time(struct vcpu *v, u64 guest_time)
+{
+    v->arch.hvm_vcpu.stime_offset += guest_time - hvm_get_guest_time(v);
+}
+
 static int pt_irq_vector(struct periodic_time *pt, enum hvm_intsrc src)
 {
     struct vcpu *v = pt->vcpu;
@@ -348,7 +378,7 @@ void create_periodic_time(
     pt->vcpu = v;
     pt->last_plt_gtime = hvm_get_guest_time(pt->vcpu);
     pt->irq = irq;
-    pt->period_cycles = (u64)period * cpu_khz / 1000000L;
+    pt->period_cycles = (u64)period;
     pt->one_shot = one_shot;
     pt->scheduled = NOW() + period;
     /*

diff --git a/xen/include/asm-x86/hvm/hvm.h b/xen/include/asm-x86/hvm/hvm.h
index 815a5c2b02240b7ec4dd35544df0dbb1cd76fbc6..e871bf8be79c94ecae70e001b18b507edf1372b2 100644 (file)
--- a/xen/include/asm-x86/hvm/hvm.h
+++ b/xen/include/asm-x86/hvm/hvm.h
@@ -147,8 +147,10 @@ void hvm_send_assist_req(struct vcpu *v);
 
 void hvm_set_guest_tsc(struct vcpu *v, u64 guest_tsc);
 u64 hvm_get_guest_tsc(struct vcpu *v);
-#define hvm_set_guest_time(vcpu, gtime) hvm_set_guest_tsc(vcpu, gtime)
-#define hvm_get_guest_time(vcpu)        hvm_get_guest_tsc(vcpu)
+
+void hvm_init_guest_time(struct domain *d);
+void hvm_set_guest_time(struct vcpu *v, u64 guest_time);
+u64 hvm_get_guest_time(struct vcpu *v);
 
 #define hvm_paging_enabled(v) \
     (!!((v)->arch.hvm_vcpu.guest_cr[0] & X86_CR0_PG))

diff --git a/xen/include/asm-x86/hvm/vcpu.h b/xen/include/asm-x86/hvm/vcpu.h
index fc43d5d20d43e09471928d4442dac0dbebffd5f8..6eb9d67b731cc67d1dd7455c4f37bab446964bf5 100644 (file)
--- a/xen/include/asm-x86/hvm/vcpu.h
+++ b/xen/include/asm-x86/hvm/vcpu.h
@@ -68,6 +68,9 @@ struct hvm_vcpu {
     struct mtrr_state   mtrr;
     u64                 pat_cr;
 
+    /* In mode delay_for_missed_ticks, VCPUs have differing guest times. */
+    int64_t             stime_offset;
+
     /* Which cache mode is this VCPU in (CR0:CD/NW)? */
     u8                  cache_mode;
 

diff --git a/xen/include/asm-x86/hvm/vmx/vmx.h b/xen/include/asm-x86/hvm/vmx/vmx.h
index b7681f0e29fa75c81ba8d21056ac206a4409d02b..0e381f7e1dc2dfa1347de8f28d349f27c4d3ba6a 100644 (file)
--- a/xen/include/asm-x86/hvm/vmx/vmx.h
+++ b/xen/include/asm-x86/hvm/vmx/vmx.h
@@ -49,7 +49,6 @@ void vmx_asm_vmexit_handler(struct cpu_user_regs);
 void vmx_asm_do_vmentry(void);
 void vmx_intr_assist(void);
 void vmx_do_resume(struct vcpu *);
-void set_guest_time(struct vcpu *v, u64 gtime);
 void vmx_vlapic_msr_changed(struct vcpu *v);
 void vmx_realmode(struct cpu_user_regs *regs);
 

diff --git a/xen/include/asm-x86/hvm/vpt.h b/xen/include/asm-x86/hvm/vpt.h
index ddc099975d235d13a9832e03c1b391afbac12f0e..24026fb1180da57806b132f494445491c208647e 100644 (file)
--- a/xen/include/asm-x86/hvm/vpt.h
+++ b/xen/include/asm-x86/hvm/vpt.h
@@ -57,7 +57,7 @@ struct hpet_registers {
 typedef struct HPETState {
     struct hpet_registers hpet;
     struct vcpu *vcpu;
-    uint64_t tsc_freq;
+    uint64_t stime_freq;
     uint64_t hpet_to_ns_scale; /* hpet ticks to ns (multiplied by 2^10) */
     uint64_t hpet_to_ns_limit; /* max hpet ticks convertable to ns      */
     uint64_t mc_offset;
@@ -137,6 +137,11 @@ struct pl_time {    /* platform time */
     struct RTCState  vrtc;
     struct HPETState vhpet;
     struct PMTState  vpmt;
+    /* guest_time = Xen sys time + stime_offset */
+    int64_t stime_offset;
+    /* Ensures monotonicity in appropriate timer modes. */
+    uint64_t last_guest_time;
+    spinlock_t pl_time_lock;
 };
 
 #define ticks_per_sec(v) (v->domain->arch.hvm_domain.tsc_frequency)

diff --git a/xen/include/xen/time.h b/xen/include/xen/time.h
index c7c13909a030e30ea3e6d9ef549b6de8ca777080..f11caa2ba4d526bf1b5f025452dec7e61e2e59bd 100644 (file)
--- a/xen/include/xen/time.h
+++ b/xen/include/xen/time.h
@@ -47,6 +47,7 @@ struct tm {
 };
 struct tm gmtime(unsigned long t);
 
+#define SYSTEM_TIME_HZ  1000000000ULL
 #define NOW()           ((s_time_t)get_s_time())
 #define SECONDS(_s)     ((s_time_t)((_s)  * 1000000000ULL))
 #define MILLISECS(_ms)  ((s_time_t)((_ms) * 1000000ULL))