As of today, KVM notes a quiescent state only in guest entry, which is good as it avoids the guest being interrupted for current RCU operations. While the guest vcpu runs, it can be interrupted by a timer IRQ that will check for any RCU operations waiting for this CPU. In case there are any of such, it invokes rcu_core() in order to sched-out the current thread and note a quiescent state. This occasional schedule work will introduce tens of microsseconds of latency, which is really bad for vcpus running latency-sensitive applications, such as real-time workloads. So, note a quiescent state in guest exit, so the interrupted guests is able to deal with any pending RCU operations before being required to invoke rcu_core(), and thus avoid the overhead of related scheduler work. Signed-off-by: Leonardo Bras <leobras@xxxxxxxxxx> --- ps: A patch fixing this same issue was discussed in this thread: https://lore.kernel.org/all/20240328171949.743211-1-leobras@xxxxxxxxxx/ Also, this can be paired with a new RCU option (rcutree.nocb_patience_delay) to avoid having invoke_rcu() being called on grace-periods starting between guest exit and the timer IRQ. This RCU option is being discussed in a sub-thread of this message: https://lore.kernel.org/all/5fd66909-1250-4a91-aa71-93cb36ed4ad5@paulmck-laptop/ include/linux/context_tracking.h | 6 ++++-- include/linux/kvm_host.h | 10 +++++++++- 2 files changed, 13 insertions(+), 3 deletions(-) diff --git a/include/linux/context_tracking.h b/include/linux/context_tracking.h index 6e76b9dba00e..8a78fabeafc3 100644 --- a/include/linux/context_tracking.h +++ b/include/linux/context_tracking.h @@ -73,39 +73,41 @@ static inline void exception_exit(enum ctx_state prev_ctx) } static __always_inline bool context_tracking_guest_enter(void) { if (context_tracking_enabled()) __ct_user_enter(CONTEXT_GUEST); return context_tracking_enabled_this_cpu(); } -static __always_inline void context_tracking_guest_exit(void) +static __always_inline bool context_tracking_guest_exit(void) { if (context_tracking_enabled()) __ct_user_exit(CONTEXT_GUEST); + + return context_tracking_enabled_this_cpu(); } #define CT_WARN_ON(cond) WARN_ON(context_tracking_enabled() && (cond)) #else static inline void user_enter(void) { } static inline void user_exit(void) { } static inline void user_enter_irqoff(void) { } static inline void user_exit_irqoff(void) { } static inline int exception_enter(void) { return 0; } static inline void exception_exit(enum ctx_state prev_ctx) { } static inline int ct_state(void) { return -1; } static inline int __ct_state(void) { return -1; } static __always_inline bool context_tracking_guest_enter(void) { return false; } -static __always_inline void context_tracking_guest_exit(void) { } +static __always_inline bool context_tracking_guest_exit(void) { return false; } #define CT_WARN_ON(cond) do { } while (0) #endif /* !CONFIG_CONTEXT_TRACKING_USER */ #ifdef CONFIG_CONTEXT_TRACKING_USER_FORCE extern void context_tracking_init(void); #else static inline void context_tracking_init(void) { } #endif /* CONFIG_CONTEXT_TRACKING_USER_FORCE */ #ifdef CONFIG_CONTEXT_TRACKING_IDLE diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 48f31dcd318a..e37724c44843 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -480,21 +480,29 @@ static __always_inline void guest_state_enter_irqoff(void) /* * Exit guest context and exit an RCU extended quiescent state. * * Between guest_context_enter_irqoff() and guest_context_exit_irqoff() it is * unsafe to use any code which may directly or indirectly use RCU, tracing * (including IRQ flag tracing), or lockdep. All code in this period must be * non-instrumentable. */ static __always_inline void guest_context_exit_irqoff(void) { - context_tracking_guest_exit(); + /* + * Guest mode is treated as a quiescent state, see + * guest_context_enter_irqoff() for more details. + */ + if (!context_tracking_guest_exit()) { + instrumentation_begin(); + rcu_virt_note_context_switch(); + instrumentation_end(); + } } /* * Stop accounting time towards a guest. * Must be called after exiting guest context. */ static __always_inline void guest_timing_exit_irqoff(void) { instrumentation_begin(); /* Flush the guest cputime we spent on the guest */ -- 2.45.0
