| Message ID | 20200424054837.5138-6-dave@stgolabs.net (mailing list archive) |
|---|---|
| State | New, archived |
| Headers | show |
| Series | kvm: Use rcuwait for vcpu blocking | expand |
I'm squashing this in to keep the changes compared to the current code minimal,
and queuing the series.
Thanks,
Paolo
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index bbefa2a7f950..feca3118b17f 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -230,10 +230,10 @@ static bool kvmppc_ipi_thread(int cpu)
static void kvmppc_fast_vcpu_kick_hv(struct kvm_vcpu *vcpu)
{
int cpu;
- struct rcuwait *wait;
+ struct rcuwait *waitp;
- wait = kvm_arch_vcpu_get_wait(vcpu);
- if (rcuwait_wake_up(wait))
+ waitp = kvm_arch_vcpu_get_wait(vcpu);
+ if (rcuwait_wake_up(waitp))
++vcpu->stat.halt_wakeup;
cpu = READ_ONCE(vcpu->arch.thread_cpu);
@@ -3814,7 +3814,10 @@ static void kvmppc_vcore_blocked(struct kvmppc_vcore *vc)
}
}
+ prepare_to_rcuwait(&vc->wait);
+ set_current_state(TASK_INTERRUPTIBLE);
if (kvmppc_vcore_check_block(vc)) {
+ finish_rcuwait(&vc->wait);
do_sleep = 0;
/* If we polled, count this as a successful poll */
if (vc->halt_poll_ns)
@@ -3827,8 +3830,8 @@ static void kvmppc_vcore_blocked(struct kvmppc_vcore *vc)
vc->vcore_state = VCORE_SLEEPING;
trace_kvmppc_vcore_blocked(vc, 0);
spin_unlock(&vc->lock);
- rcuwait_wait_event(&vc->wait,
- kvmppc_vcore_check_block(vc), TASK_INTERRUPTIBLE);
+ schedule();
+ finish_rcuwait(&vc->wait);
spin_lock(&vc->lock);
vc->vcore_state = VCORE_INACTIVE;
trace_kvmppc_vcore_blocked(vc, 1);
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 7c2d18c12d87..c671de51a753 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -2737,10 +2737,10 @@ EXPORT_SYMBOL_GPL(kvm_vcpu_block);
bool kvm_vcpu_wake_up(struct kvm_vcpu *vcpu)
{
- struct rcuwait *wait;
+ struct rcuwait *waitp;
- wait = kvm_arch_vcpu_get_wait(vcpu);
- if (rcuwait_wake_up(wait)) {
+ waitp = kvm_arch_vcpu_get_wait(vcpu);
+ if (rcuwait_wake_up(waitp)) {
WRITE_ONCE(vcpu->ready, true);
++vcpu->stat.halt_wakeup;
return true;
On Sat, 25 Apr 2020, Paolo Bonzini wrote: >I'm squashing this in to keep the changes compared to the current code minimal, >and queuing the series. Thanks!
On Fri, 24 Apr 2020 at 13:53, Davidlohr Bueso <dave@stgolabs.net> wrote: > > The use of any sort of waitqueue (simple or regular) for > wait/waking vcpus has always been an overkill and semantically > wrong. Because this is per-vcpu (which is blocked) there is > only ever a single waiting vcpu, thus no need for any sort of > queue. > > As such, make use of the rcuwait primitive, with the following > considerations: > > - rcuwait already provides the proper barriers that serialize > concurrent waiter and waker. > > - Task wakeup is done in rcu read critical region, with a > stable task pointer. > > - Because there is no concurrency among waiters, we need > not worry about rcuwait_wait_event() calls corrupting > the wait->task. As a consequence, this saves the locking > done in swait when modifying the queue. This also applies > to per-vcore wait for powerpc kvm-hv. > > The x86 tscdeadline_latency test mentioned in 8577370fb0cb > ("KVM: Use simple waitqueue for vcpu->wq") shows that, on avg, > latency is reduced by around 15-20% with this change. > This is splatting when I run linux guest on latest kvm/queue. [24726.009187] ============================= [24726.009193] WARNING: suspicious RCU usage [24726.009201] 5.7.0-rc2+ #3 Not tainted [24726.009207] ----------------------------- [24726.009215] ./include/linux/rcuwait.h:34 suspicious rcu_dereference_check() usage! [24726.009222] other info that might help us debug this: [24726.009229] rcu_scheduler_active = 2, debug_locks = 1 [24726.009237] 2 locks held by qemu-system-x86/6094: [24726.009244] #0: ffff88837b6cb990 (&vcpu->mutex){+.+.}-{3:3}, at: kvm_vcpu_ioctl+0x191/0xbb0 [kvm] [24726.009347] #1: ffffc900036c2c68 (&kvm->srcu){....}-{0:0}, at: kvm_arch_vcpu_ioctl_run+0x17f1/0x5680 [kvm] [24726.009386] stack backtrace: [24726.009394] CPU: 5 PID: 6094 Comm: qemu-system-x86 Not tainted 5.7.0-rc2+ #3 [24726.009400] Hardware name: LENOVO ThinkCentre M8500t-N000/SHARKBAY, BIOS FBKTC1AUS 02/16/2016 [24726.009405] Call Trace: [24726.009418] dump_stack+0x98/0xd5 [24726.009432] lockdep_rcu_suspicious+0x123/0x170 [24726.009465] kvm_vcpu_on_spin+0x46f/0x5d0 [kvm] [24726.009497] handle_pause+0x7e/0x3e0 [kvm_intel] [24726.009517] vmx_handle_exit+0x1fe/0x1000 [kvm_intel] [24726.009547] ? kvm_arch_vcpu_ioctl_run+0x17c5/0x5680 [kvm] [24726.009586] kvm_arch_vcpu_ioctl_run+0x18f5/0x5680 [kvm] [24726.009595] ? check_chain_key+0x26e/0x670 [24726.009651] ? kvm_arch_vcpu_runnable+0x540/0x540 [kvm] [24726.009667] ? tomoyo_execute_permission+0x4b0/0x4b0 [24726.009677] ? sched_clock+0x31/0x40 [24726.009726] kvm_vcpu_ioctl+0x5d2/0xbb0 [kvm] [24726.009754] ? kvm_vcpu_ioctl+0x5d2/0xbb0 [kvm] [24726.009786] ? kvm_set_memory_region+0x90/0x90 [kvm] [24726.009819] ? __fget_files+0x2d4/0x420 [24726.009837] ? do_dup2+0x660/0x660 [24726.009847] ? lock_acquire+0x1e5/0x660 [24726.009864] ? tomoyo_file_ioctl+0x19/0x20 [24726.009880] ksys_ioctl+0x3d2/0x1390 [24726.009900] ? generic_block_fiemap+0x70/0x70 [24726.009911] ? rcu_read_lock_sched_held+0xb4/0xe0 [24726.009920] ? rcu_read_lock_any_held.part.9+0x20/0x20 [24726.009935] ? __x64_sys_futex+0x1a1/0x400 [24726.009943] ? __kasan_check_write+0x14/0x20 [24726.009951] ? switch_fpu_return+0x181/0x3e0 [24726.009963] ? do_futex+0x14e0/0x14e0 [24726.009970] ? lockdep_hardirqs_off+0x1df/0x2d0 [24726.009977] ? syscall_return_slowpath+0x66/0x9d0 [24726.009987] ? do_syscall_64+0x8e/0xae0 [24726.009995] ? entry_SYSCALL_64_after_hwframe+0x49/0xb3 [24726.010012] __x64_sys_ioctl+0x73/0xb0 [24726.010023] do_syscall_64+0x108/0xae0 [24726.010032] ? trace_hardirqs_on_thunk+0x1a/0x1c [24726.010042] ? syscall_return_slowpath+0x9d0/0x9d0 [24726.010048] ? trace_hardirqs_off_thunk+0x1a/0x1c [24726.010059] ? trace_hardirqs_off_caller+0x28/0x1b0 [24726.010074] ? trace_hardirqs_off_thunk+0x1a/0x1c [24726.010092] entry_SYSCALL_64_after_hwframe+0x49/0xb3 [25372.530417] ============================= [25372.530420] WARNING: suspicious RCU usage [25372.530425] 5.7.0-rc2+ #3 Not tainted [25372.530428] ----------------------------- [25372.530432] ./include/linux/rcuwait.h:34 suspicious rcu_dereference_check() usage! [25372.530436] other info that might help us debug this: [25372.530440] rcu_scheduler_active = 2, debug_locks = 1 [25372.530443] 1 lock held by qemu-system-x86/6433: [25372.530447] #0: ffff88837b6cb990 (&vcpu->mutex){+.+.}-{3:3}, at: kvm_vcpu_ioctl+0x191/0xbb0 [kvm] [25372.530483] stack backtrace: [25372.530487] CPU: 1 PID: 6433 Comm: qemu-system-x86 Not tainted 5.7.0-rc2+ #3 [25372.530491] Hardware name: LENOVO ThinkCentre M8500t-N000/SHARKBAY, BIOS FBKTC1AUS 02/16/2016 [25372.530495] Call Trace: [25372.530504] dump_stack+0x98/0xd5 [25372.530513] lockdep_rcu_suspicious+0x123/0x170 [25372.530547] kvm_lapic_expired_hv_timer+0x1ad/0x1f0 [kvm] [25372.530559] vmx_vcpu_run+0x1892/0x2c60 [kvm_intel] [25372.530568] ? rcu_preempt_deferred_qs_handler+0x20/0x40 [25372.530579] ? clear_atomic_switch_msr+0x970/0x970 [kvm_intel] [25372.530586] ? rcu_read_lock_any_held.part.9+0x20/0x20 [25372.530613] kvm_arch_vcpu_ioctl_run+0x1579/0x5680 [kvm] [25372.530619] ? check_chain_key+0x26e/0x670 [25372.530654] ? kvm_arch_vcpu_runnable+0x540/0x540 [kvm] [25372.530665] ? tomoyo_execute_permission+0x4b0/0x4b0 [25372.530671] ? sched_clock+0x31/0x40 [25372.530678] ? sched_clock_cpu+0x1b/0x1b0 [25372.530706] kvm_vcpu_ioctl+0x5d2/0xbb0 [kvm] [25372.530724] ? kvm_vcpu_ioctl+0x5d2/0xbb0 [kvm] [25372.530744] ? kvm_set_memory_region+0x90/0x90 [kvm] [25372.530764] ? __fget_files+0x2d4/0x420 [25372.530775] ? do_dup2+0x660/0x660 [25372.530779] ? vfs_iter_write+0xb0/0xb0 [25372.530785] ? rcu_read_lock_held+0xb4/0xc0 [25372.530795] ? tomoyo_file_ioctl+0x19/0x20 [25372.530806] ksys_ioctl+0x3d2/0x1390 [25372.530814] ? do_dup2+0x660/0x660 [25372.530821] ? generic_block_fiemap+0x70/0x70 [25372.530833] ? __kasan_check_write+0x14/0x20 [25372.530838] ? fput_many+0x20/0x140 [25372.530844] ? fput+0x13/0x20 [25372.530848] ? do_writev+0x175/0x320 [25372.530856] ? lockdep_hardirqs_off+0x1df/0x2d0 [25372.530861] ? syscall_return_slowpath+0x66/0x9d0 [25372.530867] ? do_syscall_64+0x8e/0xae0 [25372.530872] ? entry_SYSCALL_64_after_hwframe+0x49/0xb3 [25372.530883] __x64_sys_ioctl+0x73/0xb0 [25372.530890] do_syscall_64+0x108/0xae0 [25372.530894] ? switch_fpu_return+0x181/0x3e0 [25372.530899] ? trace_hardirqs_on_thunk+0x1a/0x1c [25372.530905] ? syscall_return_slowpath+0x9d0/0x9d0 [25372.530908] ? trace_hardirqs_off_thunk+0x1a/0x1c [25372.530917] ? trace_hardirqs_off_caller+0x28/0x1b0 [25372.530926] ? trace_hardirqs_off_thunk+0x1a/0x1c [25372.530937] entry_SYSCALL_64_after_hwframe+0x49/0xb3
diff --git a/arch/mips/kvm/mips.c b/arch/mips/kvm/mips.c index 8f05dd0a0f4e..fad6acce46e4 100644 --- a/arch/mips/kvm/mips.c +++ b/arch/mips/kvm/mips.c @@ -284,8 +284,7 @@ static enum hrtimer_restart kvm_mips_comparecount_wakeup(struct hrtimer *timer) kvm_mips_callbacks->queue_timer_int(vcpu); vcpu->arch.wait = 0; - if (swq_has_sleeper(&vcpu->wq)) - swake_up_one(&vcpu->wq); + rcuwait_wake_up(&vcpu->wait); return kvm_mips_count_timeout(vcpu); } @@ -511,8 +510,7 @@ int kvm_vcpu_ioctl_interrupt(struct kvm_vcpu *vcpu, dvcpu->arch.wait = 0; - if (swq_has_sleeper(&dvcpu->wq)) - swake_up_one(&dvcpu->wq); + rcuwait_wake_up(&dvcpu->wait); return 0; } diff --git a/arch/powerpc/include/asm/kvm_book3s.h b/arch/powerpc/include/asm/kvm_book3s.h index 506e4df2d730..6e5d85ba588d 100644 --- a/arch/powerpc/include/asm/kvm_book3s.h +++ b/arch/powerpc/include/asm/kvm_book3s.h @@ -78,7 +78,7 @@ struct kvmppc_vcore { struct kvm_vcpu *runnable_threads[MAX_SMT_THREADS]; struct list_head preempt_list; spinlock_t lock; - struct swait_queue_head wq; + struct rcuwait wait; spinlock_t stoltb_lock; /* protects stolen_tb and preempt_tb */ u64 stolen_tb; u64 preempt_tb; diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h index 1dc63101ffe1..337047ba4a56 100644 --- a/arch/powerpc/include/asm/kvm_host.h +++ b/arch/powerpc/include/asm/kvm_host.h @@ -751,7 +751,7 @@ struct kvm_vcpu_arch { u8 irq_pending; /* Used by XIVE to signal pending guest irqs */ u32 last_inst; - struct swait_queue_head *wqp; + struct rcuwait *waitp; struct kvmppc_vcore *vcore; int ret; int trap; diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c index 93493f0cbfe8..b8d42f523ca7 100644 --- a/arch/powerpc/kvm/book3s_hv.c +++ b/arch/powerpc/kvm/book3s_hv.c @@ -230,13 +230,11 @@ static bool kvmppc_ipi_thread(int cpu) static void kvmppc_fast_vcpu_kick_hv(struct kvm_vcpu *vcpu) { int cpu; - struct swait_queue_head *wqp; + struct rcuwait *wait; - wqp = kvm_arch_vcpu_wq(vcpu); - if (swq_has_sleeper(wqp)) { - swake_up_one(wqp); + wait = kvm_arch_vcpu_get_wait(vcpu); + if (rcuwait_wake_up(wait)) ++vcpu->stat.halt_wakeup; - } cpu = READ_ONCE(vcpu->arch.thread_cpu); if (cpu >= 0 && kvmppc_ipi_thread(cpu)) @@ -2125,7 +2123,7 @@ static struct kvmppc_vcore *kvmppc_vcore_create(struct kvm *kvm, int id) spin_lock_init(&vcore->lock); spin_lock_init(&vcore->stoltb_lock); - init_swait_queue_head(&vcore->wq); + rcuwait_init(&vcore->wait); vcore->preempt_tb = TB_NIL; vcore->lpcr = kvm->arch.lpcr; vcore->first_vcpuid = id; @@ -3784,7 +3782,6 @@ static void kvmppc_vcore_blocked(struct kvmppc_vcore *vc) ktime_t cur, start_poll, start_wait; int do_sleep = 1; u64 block_ns; - DECLARE_SWAITQUEUE(wait); /* Poll for pending exceptions and ceded state */ cur = start_poll = ktime_get(); @@ -3812,10 +3809,7 @@ static void kvmppc_vcore_blocked(struct kvmppc_vcore *vc) } } - prepare_to_swait_exclusive(&vc->wq, &wait, TASK_INTERRUPTIBLE); - if (kvmppc_vcore_check_block(vc)) { - finish_swait(&vc->wq, &wait); do_sleep = 0; /* If we polled, count this as a successful poll */ if (vc->halt_poll_ns) @@ -3828,8 +3822,8 @@ static void kvmppc_vcore_blocked(struct kvmppc_vcore *vc) vc->vcore_state = VCORE_SLEEPING; trace_kvmppc_vcore_blocked(vc, 0); spin_unlock(&vc->lock); - schedule(); - finish_swait(&vc->wq, &wait); + rcuwait_wait_event(&vc->wait, + kvmppc_vcore_check_block(vc), TASK_INTERRUPTIBLE); spin_lock(&vc->lock); vc->vcore_state = VCORE_INACTIVE; trace_kvmppc_vcore_blocked(vc, 1); @@ -3940,7 +3934,7 @@ static int kvmppc_run_vcpu(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu) kvmppc_start_thread(vcpu, vc); trace_kvm_guest_enter(vcpu); } else if (vc->vcore_state == VCORE_SLEEPING) { - swake_up_one(&vc->wq); + rcuwait_wake_up(&vc->wait); } } @@ -4279,7 +4273,7 @@ static int kvmppc_vcpu_run_hv(struct kvm_run *run, struct kvm_vcpu *vcpu) } user_vrsave = mfspr(SPRN_VRSAVE); - vcpu->arch.wqp = &vcpu->arch.vcore->wq; + vcpu->arch.waitp = &vcpu->arch.vcore->wait; vcpu->arch.pgdir = kvm->mm->pgd; vcpu->arch.state = KVMPPC_VCPU_BUSY_IN_HOST; diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c index e15166b0a16d..4a074b587520 100644 --- a/arch/powerpc/kvm/powerpc.c +++ b/arch/powerpc/kvm/powerpc.c @@ -751,7 +751,7 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu) if (err) goto out_vcpu_uninit; - vcpu->arch.wqp = &vcpu->wq; + vcpu->arch.waitp = &vcpu->wait; kvmppc_create_vcpu_debugfs(vcpu, vcpu->vcpu_id); return 0; diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index 9af25c97612a..54345dc645ba 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -1833,7 +1833,7 @@ void kvm_lapic_expired_hv_timer(struct kvm_vcpu *vcpu) /* If the preempt notifier has already run, it also called apic_timer_expired */ if (!apic->lapic_timer.hv_timer_in_use) goto out; - WARN_ON(swait_active(&vcpu->wq)); + WARN_ON(rcuwait_active(&vcpu->wait)); cancel_hv_timer(apic); apic_timer_expired(apic); diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 6d58beb65454..fc34021546bd 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -23,7 +23,7 @@ #include <linux/irqflags.h> #include <linux/context_tracking.h> #include <linux/irqbypass.h> -#include <linux/swait.h> +#include <linux/rcuwait.h> #include <linux/refcount.h> #include <linux/nospec.h> #include <asm/signal.h> @@ -277,7 +277,7 @@ struct kvm_vcpu { struct mutex mutex; struct kvm_run *run; - struct swait_queue_head wq; + struct rcuwait wait; struct pid __rcu *pid; int sigset_active; sigset_t sigset; @@ -956,12 +956,12 @@ static inline bool kvm_arch_has_assigned_device(struct kvm *kvm) } #endif -static inline struct swait_queue_head *kvm_arch_vcpu_wq(struct kvm_vcpu *vcpu) +static inline struct rcuwait *kvm_arch_vcpu_get_wait(struct kvm_vcpu *vcpu) { #ifdef __KVM_HAVE_ARCH_WQP - return vcpu->arch.wqp; + return vcpu->arch.waitp; #else - return &vcpu->wq; + return &vcpu->wait; #endif } diff --git a/virt/kvm/arm/arch_timer.c b/virt/kvm/arm/arch_timer.c index 93bd59b46848..d5024416e722 100644 --- a/virt/kvm/arm/arch_timer.c +++ b/virt/kvm/arm/arch_timer.c @@ -571,6 +571,7 @@ void kvm_timer_vcpu_put(struct kvm_vcpu *vcpu) { struct arch_timer_cpu *timer = vcpu_timer(vcpu); struct timer_map map; + struct rcuwait *wait = kvm_arch_vcpu_get_wait(vcpu); if (unlikely(!timer->enabled)) return; @@ -593,7 +594,7 @@ void kvm_timer_vcpu_put(struct kvm_vcpu *vcpu) if (map.emul_ptimer) soft_timer_cancel(&map.emul_ptimer->hrtimer); - if (swait_active(kvm_arch_vcpu_wq(vcpu))) + if (rcuwait_active(wait)) kvm_timer_blocking(vcpu); /* diff --git a/virt/kvm/arm/arm.c b/virt/kvm/arm/arm.c index 48d0ec44ad77..479f36d02418 100644 --- a/virt/kvm/arm/arm.c +++ b/virt/kvm/arm/arm.c @@ -579,16 +579,17 @@ void kvm_arm_resume_guest(struct kvm *kvm) kvm_for_each_vcpu(i, vcpu, kvm) { vcpu->arch.pause = false; - swake_up_one(kvm_arch_vcpu_wq(vcpu)); + rcuwait_wake_up(kvm_arch_vcpu_get_wait(vcpu)); } } static void vcpu_req_sleep(struct kvm_vcpu *vcpu) { - struct swait_queue_head *wq = kvm_arch_vcpu_wq(vcpu); + struct rcuwait *wait = kvm_arch_vcpu_get_wait(vcpu); - swait_event_interruptible_exclusive(*wq, ((!vcpu->arch.power_off) && - (!vcpu->arch.pause))); + rcuwait_wait_event(wait, + (!vcpu->arch.power_off) &&(!vcpu->arch.pause), + TASK_INTERRUPTIBLE); if (vcpu->arch.power_off || vcpu->arch.pause) { /* Awaken to handle a signal, request we sleep again later. */ diff --git a/virt/kvm/async_pf.c b/virt/kvm/async_pf.c index 15e5b037f92d..10b533f641a6 100644 --- a/virt/kvm/async_pf.c +++ b/virt/kvm/async_pf.c @@ -80,8 +80,7 @@ static void async_pf_execute(struct work_struct *work) trace_kvm_async_pf_completed(addr, cr2_or_gpa); - if (swq_has_sleeper(&vcpu->wq)) - swake_up_one(&vcpu->wq); + rcuwait_wake_up(&vcpu->wait); mmput(mm); kvm_put_kvm(vcpu->kvm); diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 74bdb7bf3295..f027ae3598e8 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -341,7 +341,7 @@ static void kvm_vcpu_init(struct kvm_vcpu *vcpu, struct kvm *kvm, unsigned id) vcpu->kvm = kvm; vcpu->vcpu_id = id; vcpu->pid = NULL; - init_swait_queue_head(&vcpu->wq); + rcuwait_init(&vcpu->wait); kvm_async_pf_vcpu_init(vcpu); vcpu->pre_pcpu = -1; @@ -2671,7 +2671,6 @@ static int kvm_vcpu_check_block(struct kvm_vcpu *vcpu) void kvm_vcpu_block(struct kvm_vcpu *vcpu) { ktime_t start, cur; - DECLARE_SWAITQUEUE(wait); bool waited = false; u64 block_ns; @@ -2697,8 +2696,9 @@ void kvm_vcpu_block(struct kvm_vcpu *vcpu) } while (single_task_running() && ktime_before(cur, stop)); } + prepare_to_rcuwait(&vcpu->wait); for (;;) { - prepare_to_swait_exclusive(&vcpu->wq, &wait, TASK_INTERRUPTIBLE); + set_current_state(TASK_INTERRUPTIBLE); if (kvm_vcpu_check_block(vcpu) < 0) break; @@ -2706,8 +2706,7 @@ void kvm_vcpu_block(struct kvm_vcpu *vcpu) waited = true; schedule(); } - - finish_swait(&vcpu->wq, &wait); + finish_rcuwait(&vcpu->wait); cur = ktime_get(); out: kvm_arch_vcpu_unblocking(vcpu); @@ -2738,11 +2737,10 @@ EXPORT_SYMBOL_GPL(kvm_vcpu_block); bool kvm_vcpu_wake_up(struct kvm_vcpu *vcpu) { - struct swait_queue_head *wqp; + struct rcuwait *wait; - wqp = kvm_arch_vcpu_wq(vcpu); - if (swq_has_sleeper(wqp)) { - swake_up_one(wqp); + wait = kvm_arch_vcpu_get_wait(vcpu); + if (rcuwait_wake_up(wait)) { WRITE_ONCE(vcpu->ready, true); ++vcpu->stat.halt_wakeup; return true; @@ -2884,7 +2882,8 @@ void kvm_vcpu_on_spin(struct kvm_vcpu *me, bool yield_to_kernel_mode) continue; if (vcpu == me) continue; - if (swait_active(&vcpu->wq) && !vcpu_dy_runnable(vcpu)) + if (rcuwait_active(&vcpu->wait) && + !vcpu_dy_runnable(vcpu)) continue; if (READ_ONCE(vcpu->preempted) && yield_to_kernel_mode && !kvm_arch_vcpu_in_kernel(vcpu))
The use of any sort of waitqueue (simple or regular) for wait/waking vcpus has always been an overkill and semantically wrong. Because this is per-vcpu (which is blocked) there is only ever a single waiting vcpu, thus no need for any sort of queue. As such, make use of the rcuwait primitive, with the following considerations: - rcuwait already provides the proper barriers that serialize concurrent waiter and waker. - Task wakeup is done in rcu read critical region, with a stable task pointer. - Because there is no concurrency among waiters, we need not worry about rcuwait_wait_event() calls corrupting the wait->task. As a consequence, this saves the locking done in swait when modifying the queue. This also applies to per-vcore wait for powerpc kvm-hv. The x86 tscdeadline_latency test mentioned in 8577370fb0cb ("KVM: Use simple waitqueue for vcpu->wq") shows that, on avg, latency is reduced by around 15-20% with this change. Cc: Paul Mackerras <paulus@ozlabs.org> Cc: kvmarm@lists.cs.columbia.edu Cc: linux-mips@vger.kernel.org Reviewed-by: Marc Zyngier <maz@kernel.org> Signed-off-by: Davidlohr Bueso <dbueso@suse.de> --- arch/mips/kvm/mips.c | 6 ++---- arch/powerpc/include/asm/kvm_book3s.h | 2 +- arch/powerpc/include/asm/kvm_host.h | 2 +- arch/powerpc/kvm/book3s_hv.c | 22 ++++++++-------------- arch/powerpc/kvm/powerpc.c | 2 +- arch/x86/kvm/lapic.c | 2 +- include/linux/kvm_host.h | 10 +++++----- virt/kvm/arm/arch_timer.c | 3 ++- virt/kvm/arm/arm.c | 9 +++++---- virt/kvm/async_pf.c | 3 +-- virt/kvm/kvm_main.c | 19 +++++++++---------- 11 files changed, 36 insertions(+), 44 deletions(-)