On Sun, May 12, 2024 at 06:44:23PM -0300, Marcelo Tosatti wrote: > On Fri, May 10, 2024 at 11:05:56PM -0300, Leonardo Bras wrote: > > 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. > > This does not properly fix the current problem, as RCU work might be > scheduled after the VM exit, followed by a timer interrupt. > > Correct? Correct, for this case, check the note below: > > > > > 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/ ^ This one above. The idea is to use this rcutree.nocb_patience_delay=N : a new option we added on RCU that allow us to avoid invoking rcu_core() if the grace_period < N miliseconds. This only works on nohz_full cpus. So with both the current patch and the one in above link, we have the same effect as we previously had with last_guest_exit, with a cherry on top: we can avoid rcu_core() getting called in situations where a grace period just started after going into kernel code, and a timer interrupt happened before it can report quiescent state again. For our nohz_full vcpu thread scenario, we have: - guest_exit note a quiescent state - let's say we start a grace period in the next cycle - If timer interrupts, it requires the grace period to be older than N miliseconds - If we configure a proper value for patience, it will never reach the end of patience before going guest_entry, and thus noting a quiescent state What do you think? Thanks! Leo > > > > > > 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 > > > > > > >
