From f05eda16037f9363297561bd28f318a6d7833d35 Mon Sep 17 00:00:00 2001 From: Yan Zhao Date: Fri, 8 Mar 2024 17:09:27 -0800 Subject: srcu: Add an API for a memory barrier after SRCU read lock To avoid redundant memory barriers, add smp_mb__after_srcu_read_lock() to pair with smp_mb__after_srcu_read_unlock() for use in paths that need to emit a memory barrier, but already do srcu_read_lock(), which includes a full memory barrier. Provide an API, e.g. as opposed to having callers document the behavior via a comment, as the full memory barrier provided by srcu_read_lock() is an implementation detail that shouldn't bleed into random subsystems. KVM will use smp_mb__after_srcu_read_lock() in it's VM-Exit path to ensure a memory barrier is emitted, which is necessary to ensure correctness of mixed memory types on CPUs that support self-snoop. Cc: Paolo Bonzini Cc: Sean Christopherson Cc: Kevin Tian Signed-off-by: Yan Zhao [sean: massage changelog] Tested-by: Xiangfei Ma Tested-by: Yongwei Ma Reviewed-by: Paul E. McKenney --- include/linux/srcu.h | 14 ++++++++++++++ 1 file changed, 14 insertions(+) (limited to 'include/linux/srcu.h') diff --git a/include/linux/srcu.h b/include/linux/srcu.h index 236610e4a8fa..1cb4527076de 100644 --- a/include/linux/srcu.h +++ b/include/linux/srcu.h @@ -343,6 +343,20 @@ static inline void smp_mb__after_srcu_read_unlock(void) /* __srcu_read_unlock has smp_mb() internally so nothing to do here. */ } +/** + * smp_mb__after_srcu_read_lock - ensure full ordering after srcu_read_lock + * + * Converts the preceding srcu_read_lock into a two-way memory barrier. + * + * Call this after srcu_read_lock, to guarantee that all memory operations + * that occur after smp_mb__after_srcu_read_lock will appear to happen after + * the preceding srcu_read_lock. + */ +static inline void smp_mb__after_srcu_read_lock(void) +{ + /* __srcu_read_lock has smp_mb() internally so nothing to do here. */ +} + DEFINE_LOCK_GUARD_1(srcu, struct srcu_struct, _T->idx = srcu_read_lock(_T->lock), srcu_read_unlock(_T->lock, _T->idx), -- cgit From 395e73bd8d35fa9b8505e44f63a2a10abde09cce Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Sun, 9 Jun 2024 20:12:19 -0700 Subject: srcu: Add NUM_ACTIVE_SRCU_POLL_OLDSTATE This commit adds NUM_ACTIVE_SRCU_POLL_OLDSTATE, which gives the maximum number of distinct return values from get_state_synchronize_rcu() that can, at a given point in time, correspond to not-completed SRCU grace periods. Reported-by: Kent Overstreet Closes: https://lore.kernel.org/all/irycqy4sinjdgm2hkyix2bffunpcmuwgeufsx6nlljvqme3wiu@ify3zdnrmzph/ Signed-off-by: Paul E. McKenney --- include/linux/srcu.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux/srcu.h') diff --git a/include/linux/srcu.h b/include/linux/srcu.h index 236610e4a8fa..f664cba7a80c 100644 --- a/include/linux/srcu.h +++ b/include/linux/srcu.h @@ -61,6 +61,10 @@ unsigned long get_state_synchronize_srcu(struct srcu_struct *ssp); unsigned long start_poll_synchronize_srcu(struct srcu_struct *ssp); bool poll_state_synchronize_srcu(struct srcu_struct *ssp, unsigned long cookie); +// Maximum number of unsigned long values corresponding to +// not-yet-completed SRCU grace periods. +#define NUM_ACTIVE_SRCU_POLL_OLDSTATE 2 + #ifdef CONFIG_NEED_SRCU_NMI_SAFE int __srcu_read_lock_nmisafe(struct srcu_struct *ssp) __acquires(ssp); void __srcu_read_unlock_nmisafe(struct srcu_struct *ssp, int idx) __releases(ssp); -- cgit From e206f33e2c0774276a0497fe538472e12016a362 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Fri, 14 Jun 2024 13:26:44 -0700 Subject: srcu: Fill out polled grace-period APIs This commit adds the get_completed_synchronize_srcu() and the same_state_synchronize_srcu() functions. The first returns a cookie that is always interpreted as corresponding to an expired grace period. The second does an equality comparison of a pair of cookies. Signed-off-by: Paul E. McKenney Cc: Kent Overstreet --- include/linux/srcu.h | 31 +++++++++++++++++++++++++++++++ 1 file changed, 31 insertions(+) (limited to 'include/linux/srcu.h') diff --git a/include/linux/srcu.h b/include/linux/srcu.h index f664cba7a80c..6f6cb5fc1242 100644 --- a/include/linux/srcu.h +++ b/include/linux/srcu.h @@ -57,6 +57,20 @@ void cleanup_srcu_struct(struct srcu_struct *ssp); int __srcu_read_lock(struct srcu_struct *ssp) __acquires(ssp); void __srcu_read_unlock(struct srcu_struct *ssp, int idx) __releases(ssp); void synchronize_srcu(struct srcu_struct *ssp); + +#define SRCU_GET_STATE_COMPLETED 0x1 + +/** + * get_completed_synchronize_srcu - Return a pre-completed polled state cookie + * + * Returns a value that poll_state_synchronize_srcu() will always treat + * as a cookie whose grace period has already completed. + */ +static inline unsigned long get_completed_synchronize_srcu(void) +{ + return SRCU_GET_STATE_COMPLETED; +} + unsigned long get_state_synchronize_srcu(struct srcu_struct *ssp); unsigned long start_poll_synchronize_srcu(struct srcu_struct *ssp); bool poll_state_synchronize_srcu(struct srcu_struct *ssp, unsigned long cookie); @@ -65,6 +79,23 @@ bool poll_state_synchronize_srcu(struct srcu_struct *ssp, unsigned long cookie); // not-yet-completed SRCU grace periods. #define NUM_ACTIVE_SRCU_POLL_OLDSTATE 2 +/** + * same_state_synchronize_srcu - Are two old-state values identical? + * @oldstate1: First old-state value. + * @oldstate2: Second old-state value. + * + * The two old-state values must have been obtained from either + * get_state_synchronize_srcu(), start_poll_synchronize_srcu(), or + * get_completed_synchronize_srcu(). Returns @true if the two values are + * identical and @false otherwise. This allows structures whose lifetimes + * are tracked by old-state values to push these values to a list header, + * allowing those structures to be slightly smaller. + */ +static inline bool same_state_synchronize_srcu(unsigned long oldstate1, unsigned long oldstate2) +{ + return oldstate1 == oldstate2; +} + #ifdef CONFIG_NEED_SRCU_NMI_SAFE int __srcu_read_lock_nmisafe(struct srcu_struct *ssp) __acquires(ssp); void __srcu_read_unlock_nmisafe(struct srcu_struct *ssp, int idx) __releases(ssp); -- cgit