diff options
| -rw-r--r-- | kernel/arch/x86/configs/opnfv.config | 20 | ||||
| -rw-r--r-- | kernel/drivers/vfio/pci/vfio_pci_intrs.c | 2 | ||||
| -rw-r--r-- | kernel/kernel/time/hrtimer.c | 11 | ||||
| -rw-r--r-- | kernel/kernel/time/tick-sched.c | 64 | ||||
| -rw-r--r-- | qemu/hw/i386/kvm/clock.c | 18 | ||||
| -rw-r--r-- | qemu/migration/savevm.c | 2 | ||||
| -rw-r--r-- | qemu/target-i386/kvm.c | 45 | ||||
| -rw-r--r-- | qemu/target-i386/kvm_i386.h | 1 |
8 files changed, 94 insertions, 69 deletions
diff --git a/kernel/arch/x86/configs/opnfv.config b/kernel/arch/x86/configs/opnfv.config index 573bcc915..c73eaf29c 100644 --- a/kernel/arch/x86/configs/opnfv.config +++ b/kernel/arch/x86/configs/opnfv.config @@ -734,15 +734,15 @@ CONFIG_IP_PNP_BOOTP=y CONFIG_IP_PNP_RARP=y # CONFIG_NET_IPIP is not set # CONFIG_NET_IPGRE_DEMUX is not set -# CONFIG_NET_IP_TUNNEL is not set +CONFIG_NET_IP_TUNNEL=y CONFIG_IP_MROUTE=y # CONFIG_IP_MROUTE_MULTIPLE_TABLES is not set CONFIG_IP_PIMSM_V1=y CONFIG_IP_PIMSM_V2=y CONFIG_SYN_COOKIES=y -# CONFIG_NET_UDP_TUNNEL is not set +CONFIG_NET_UDP_TUNNEL=y # CONFIG_NET_FOU is not set -# CONFIG_GENEVE is not set +CONFIG_GENEVE=y # CONFIG_INET_AH is not set # CONFIG_INET_ESP is not set # CONFIG_INET_IPCOMP is not set @@ -972,11 +972,15 @@ CONFIG_NET_SCH_FIFO=y # CONFIG_DCB is not set CONFIG_DNS_RESOLVER=y # CONFIG_BATMAN_ADV is not set -# CONFIG_OPENVSWITCH is not set +CONFIG_OPENVSWITCH=m +CONFIG_OPENVSWITCH_VXLAN=m +CONFIG_OPENVSWITCH_GENEVE=m # CONFIG_VSOCKETS is not set # CONFIG_NETLINK_MMAP is not set # CONFIG_NETLINK_DIAG is not set -# CONFIG_MPLS is not set +CONFIG_MPLS=y +CONFIG_NET_MPLS_GSO=m +# CONFIG_MPLS_ROUTING is not set # CONFIG_HSR is not set # CONFIG_NET_SWITCHDEV is not set CONFIG_RPS=y @@ -1352,7 +1356,7 @@ CONFIG_NET_CORE=y # CONFIG_NET_TEAM is not set # CONFIG_MACVLAN is not set # CONFIG_IPVLAN is not set -# CONFIG_VXLAN is not set +CONFIG_VXLAN=y CONFIG_NETCONSOLE=y CONFIG_NETPOLL=y CONFIG_NET_POLL_CONTROLLER=y @@ -1448,9 +1452,11 @@ CONFIG_IGB=y CONFIG_IGBVF=y CONFIG_IXGB=y CONFIG_IXGBE=y +CONFIG_IXGBE_VXLAN=y # CONFIG_IXGBE_HWMON is not set -# CONFIG_IXGBEVF is not set +CONFIG_IXGBEVF=y CONFIG_I40E=y +CONFIG_I40E_VXLAN=y # CONFIG_I40EVF is not set # CONFIG_FM10K is not set CONFIG_NET_VENDOR_I825XX=y diff --git a/kernel/drivers/vfio/pci/vfio_pci_intrs.c b/kernel/drivers/vfio/pci/vfio_pci_intrs.c index 1f577b4ac..a21d8e1e3 100644 --- a/kernel/drivers/vfio/pci/vfio_pci_intrs.c +++ b/kernel/drivers/vfio/pci/vfio_pci_intrs.c @@ -352,7 +352,7 @@ static int vfio_msi_set_vector_signal(struct vfio_pci_device *vdev, pci_write_msi_msg(irq, &msg); } - ret = request_irq(irq, vfio_msihandler, 0, + ret = request_irq(irq, vfio_msihandler, IRQF_NO_THREAD, vdev->ctx[vector].name, trigger); if (ret) { kfree(vdev->ctx[vector].name); diff --git a/kernel/kernel/time/hrtimer.c b/kernel/kernel/time/hrtimer.c index 2c6be169b..5d193396e 100644 --- a/kernel/kernel/time/hrtimer.c +++ b/kernel/kernel/time/hrtimer.c @@ -583,6 +583,12 @@ static int hrtimer_reprogram(struct hrtimer *timer, if (hrtimer_callback_running(timer)) return 0; + if (base->cpu_base != cpu_base) + return 0; + + if (cpu_base->in_hrtirq) + return 0; + /* * CLOCK_REALTIME timer might be requested with an absolute * expiry time which is less than base->offset. Nothing wrong @@ -613,12 +619,11 @@ static int hrtimer_reprogram(struct hrtimer *timer, if (cpu_base->hang_detected) return 0; + cpu_base->expires_next = expires; /* * Clockevents returns -ETIME, when the event was in the past. */ - res = tick_program_event(expires, 0); - if (!IS_ERR_VALUE(res)) - cpu_base->expires_next = expires; + res = tick_program_event(expires, 1); return res; } diff --git a/kernel/kernel/time/tick-sched.c b/kernel/kernel/time/tick-sched.c index b3841ba00..f61dbf202 100644 --- a/kernel/kernel/time/tick-sched.c +++ b/kernel/kernel/time/tick-sched.c @@ -576,6 +576,20 @@ u64 get_cpu_iowait_time_us(int cpu, u64 *last_update_time) } EXPORT_SYMBOL_GPL(get_cpu_iowait_time_us); +static void tick_nohz_restart(struct tick_sched *ts, ktime_t now) +{ + hrtimer_cancel(&ts->sched_timer); + hrtimer_set_expires(&ts->sched_timer, ts->last_tick); + + /* Forward the time to expire in the future */ + hrtimer_forward(&ts->sched_timer, now, tick_period); + + if (ts->nohz_mode == NOHZ_MODE_HIGHRES) + hrtimer_start_expires(&ts->sched_timer, HRTIMER_MODE_ABS_PINNED); + else + tick_program_event(hrtimer_get_expires(&ts->sched_timer), 1); +} + static ktime_t tick_nohz_stop_sched_tick(struct tick_sched *ts, ktime_t now, int cpu) { @@ -704,22 +718,16 @@ static ktime_t tick_nohz_stop_sched_tick(struct tick_sched *ts, goto out; } - if (ts->nohz_mode == NOHZ_MODE_HIGHRES) { - hrtimer_start(&ts->sched_timer, expires, - HRTIMER_MODE_ABS_PINNED); - /* Check, if the timer was already in the past */ - if (hrtimer_active(&ts->sched_timer)) - goto out; - } else if (!tick_program_event(expires, 0)) - goto out; - /* - * We are past the event already. So we crossed a - * jiffie boundary. Update jiffies and raise the - * softirq. - */ - tick_do_update_jiffies64(ktime_get()); + if (ts->nohz_mode == NOHZ_MODE_HIGHRES) + hrtimer_start(&ts->sched_timer, expires, + HRTIMER_MODE_ABS_PINNED); + else + tick_program_event(expires, 1); + } else { + /* Tick is stopped, but required now. Enforce it */ + tick_nohz_restart(ts, now); + } - raise_softirq_irqoff(TIMER_SOFTIRQ); out: ts->next_jiffies = next_jiffies; ts->last_jiffies = last_jiffies; @@ -880,32 +888,6 @@ ktime_t tick_nohz_get_sleep_length(void) return ts->sleep_length; } -static void tick_nohz_restart(struct tick_sched *ts, ktime_t now) -{ - hrtimer_cancel(&ts->sched_timer); - hrtimer_set_expires(&ts->sched_timer, ts->last_tick); - - while (1) { - /* Forward the time to expire in the future */ - hrtimer_forward(&ts->sched_timer, now, tick_period); - - if (ts->nohz_mode == NOHZ_MODE_HIGHRES) { - hrtimer_start_expires(&ts->sched_timer, - HRTIMER_MODE_ABS_PINNED); - /* Check, if the timer was already in the past */ - if (hrtimer_active(&ts->sched_timer)) - break; - } else { - if (!tick_program_event( - hrtimer_get_expires(&ts->sched_timer), 0)) - break; - } - /* Reread time and update jiffies */ - now = ktime_get(); - tick_do_update_jiffies64(now); - } -} - static void tick_nohz_restart_sched_tick(struct tick_sched *ts, ktime_t now) { /* Update jiffies first */ diff --git a/qemu/hw/i386/kvm/clock.c b/qemu/hw/i386/kvm/clock.c index efdf16584..0593a3f1f 100644 --- a/qemu/hw/i386/kvm/clock.c +++ b/qemu/hw/i386/kvm/clock.c @@ -17,7 +17,7 @@ #include "qemu/host-utils.h" #include "sysemu/sysemu.h" #include "sysemu/kvm.h" -#include "sysemu/cpus.h" +#include "kvm_i386.h" #include "hw/sysbus.h" #include "hw/kvm/clock.h" @@ -125,21 +125,7 @@ static void kvmclock_vm_state_change(void *opaque, int running, return; } - cpu_synchronize_all_states(); - /* In theory, the cpu_synchronize_all_states() call above wouldn't - * affect the rest of the code, as the VCPU state inside CPUState - * is supposed to always match the VCPU state on the kernel side. - * - * In practice, calling cpu_synchronize_state() too soon will load the - * kernel-side APIC state into X86CPU.apic_state too early, APIC state - * won't be reloaded later because CPUState.vcpu_dirty==true, and - * outdated APIC state may be migrated to another host. - * - * The real fix would be to make sure outdated APIC state is read - * from the kernel again when necessary. While this is not fixed, we - * need the cpu_clean_all_dirty() call below. - */ - cpu_clean_all_dirty(); + kvm_synchronize_all_tsc(); ret = kvm_vm_ioctl(kvm_state, KVM_GET_CLOCK, &data); if (ret < 0) { diff --git a/qemu/migration/savevm.c b/qemu/migration/savevm.c index 60712153f..a42874b10 100644 --- a/qemu/migration/savevm.c +++ b/qemu/migration/savevm.c @@ -945,8 +945,8 @@ static int qemu_savevm_state(QEMUFile *f, Error **errp) qemu_savevm_state_complete(f); ret = qemu_file_get_error(f); } + qemu_savevm_state_cancel(); if (ret != 0) { - qemu_savevm_state_cancel(); error_setg_errno(errp, -ret, "Error while writing VM state"); } return ret; diff --git a/qemu/target-i386/kvm.c b/qemu/target-i386/kvm.c index 066d03d99..721c580ed 100644 --- a/qemu/target-i386/kvm.c +++ b/qemu/target-i386/kvm.c @@ -96,6 +96,51 @@ bool kvm_allows_irq0_override(void) return !kvm_irqchip_in_kernel() || kvm_has_gsi_routing(); } +static int kvm_get_tsc(CPUState *cs) +{ + X86CPU *cpu = X86_CPU(cs); + CPUX86State *env = &cpu->env; + struct { + struct kvm_msrs info; + struct kvm_msr_entry entries[1]; + } msr_data; + int ret; + + if (env->tsc_valid) { + return 0; + } + + msr_data.info.nmsrs = 1; + msr_data.entries[0].index = MSR_IA32_TSC; + env->tsc_valid = !runstate_is_running(); + + ret = kvm_vcpu_ioctl(CPU(cpu), KVM_GET_MSRS, &msr_data); + if (ret < 0) { + return ret; + } + + env->tsc = msr_data.entries[0].data; + return 0; +} + +static inline void do_kvm_synchronize_tsc(void *arg) +{ + CPUState *cpu = arg; + + kvm_get_tsc(cpu); +} + +void kvm_synchronize_all_tsc(void) +{ + CPUState *cpu; + + if (kvm_enabled()) { + CPU_FOREACH(cpu) { + run_on_cpu(cpu, do_kvm_synchronize_tsc, cpu); + } + } +} + static struct kvm_cpuid2 *try_get_cpuid(KVMState *s, int max) { struct kvm_cpuid2 *cpuid; diff --git a/qemu/target-i386/kvm_i386.h b/qemu/target-i386/kvm_i386.h index e557e94f4..c1b312ba2 100644 --- a/qemu/target-i386/kvm_i386.h +++ b/qemu/target-i386/kvm_i386.h @@ -15,6 +15,7 @@ bool kvm_allows_irq0_override(void); bool kvm_has_smm(void); +void kvm_synchronize_all_tsc(void); void kvm_arch_reset_vcpu(X86CPU *cs); void kvm_arch_do_init_vcpu(X86CPU *cs); |