[PATCH RFC V9 10/19] x86/ticketlock: Add slowpath logic
x86/ticketlock: Add slowpath logic From: Jeremy Fitzhardinge Maintain a flag in the LSB of the ticket lock tail which indicates whether anyone is in the lock slowpath and may need kicking when the current holder unlocks. The flags are set when the first locker enters the slowpath, and cleared when unlocking to an empty queue (ie, no contention). In the specific implementation of lock_spinning(), make sure to set the slowpath flags on the lock just before blocking. We must do this before the last-chance pickup test to prevent a deadlock with the unlocker: UnlockerLocker test for lock pickup -> fail unlock test slowpath -> false set slowpath flags block Whereas this works in any ordering: UnlockerLocker set slowpath flags test for lock pickup -> fail block unlock test slowpath -> true, kick If the unlocker finds that the lock has the slowpath flag set but it is actually uncontended (ie, head == tail, so nobody is waiting), then it clears the slowpath flag. The unlock code uses a locked add to update the head counter. This also acts as a full memory barrier so that its safe to subsequently read back the slowflag state, knowing that the updated lock is visible to the other CPUs. If it were an unlocked add, then the flag read may just be forwarded from the store buffer before it was visible to the other CPUs, which could result in a deadlock. Unfortunately this means we need to do a locked instruction when unlocking with PV ticketlocks. However, if PV ticketlocks are not enabled, then the old non-locked "add" is the only unlocking code. Note: this code relies on gcc making sure that unlikely() code is out of line of the fastpath, which only happens when OPTIMIZE_SIZE=n. If it doesn't the generated code isn't too bad, but its definitely suboptimal. Thanks to Srivatsa Vaddagiri for providing a bugfix to the original version of this change, which has been folded in. Thanks to Stephan Diestelhorst for commenting on some code which relied on an inaccurate reading of the x86 memory ordering rules. Signed-off-by: Jeremy Fitzhardinge Signed-off-by: Srivatsa Vaddagiri Reviewed-by: Konrad Rzeszutek Wilk Cc: Stephan Diestelhorst Signed-off-by: Raghavendra K T --- arch/x86/include/asm/paravirt.h |2 - arch/x86/include/asm/spinlock.h | 86 - arch/x86/include/asm/spinlock_types.h |2 + arch/x86/kernel/paravirt-spinlocks.c |3 + arch/x86/xen/spinlock.c |6 ++ 5 files changed, 74 insertions(+), 25 deletions(-) diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h index 7131e12c..401f350 100644 --- a/arch/x86/include/asm/paravirt.h +++ b/arch/x86/include/asm/paravirt.h @@ -718,7 +718,7 @@ static __always_inline void __ticket_lock_spinning(struct arch_spinlock *lock, PVOP_VCALLEE2(pv_lock_ops.lock_spinning, lock, ticket); } -static __always_inline void ticket_unlock_kick(struct arch_spinlock *lock, +static __always_inline void __ticket_unlock_kick(struct arch_spinlock *lock, __ticket_t ticket) { PVOP_VCALL2(pv_lock_ops.unlock_kick, lock, ticket); diff --git a/arch/x86/include/asm/spinlock.h b/arch/x86/include/asm/spinlock.h index 04a5cd5..d68883d 100644 --- a/arch/x86/include/asm/spinlock.h +++ b/arch/x86/include/asm/spinlock.h @@ -1,11 +1,14 @@ #ifndef _ASM_X86_SPINLOCK_H #define _ASM_X86_SPINLOCK_H +#include #include #include #include #include #include +#include + /* * Your basic SMP spinlocks, allowing only a single CPU anywhere * @@ -37,32 +40,28 @@ /* How long a lock should spin before we consider blocking */ #define SPIN_THRESHOLD (1 << 15) -#ifndef CONFIG_PARAVIRT_SPINLOCKS +extern struct static_key paravirt_ticketlocks_enabled; +static __always_inline bool static_key_false(struct static_key *key); -static __always_inline void __ticket_lock_spinning(struct arch_spinlock *lock, - __ticket_t ticket) +#ifdef CONFIG_PARAVIRT_SPINLOCKS + +static inline void __ticket_enter_slowpath(arch_spinlock_t *lock) { + set_bit(0, (volatile unsigned long *)>tickets.tail); } -static __always_inline void ticket_unlock_kick(struct arch_spinlock *lock, -__ticket_t ticket) +#else /* !CONFIG_PARAVIRT_SPINLOCKS */ +static __always_inline void __ticket_lock_spinning(arch_spinlock_t *lock, + __ticket_t ticket) { } - -#endif /* CONFIG_PARAVIRT_SPINLOCKS */ - - -/* - * If a spinlock has someone waiting on it,
[PATCH RFC V9 10/19] x86/ticketlock: Add slowpath logic
x86/ticketlock: Add slowpath logic From: Jeremy Fitzhardinge jeremy.fitzhardi...@citrix.com Maintain a flag in the LSB of the ticket lock tail which indicates whether anyone is in the lock slowpath and may need kicking when the current holder unlocks. The flags are set when the first locker enters the slowpath, and cleared when unlocking to an empty queue (ie, no contention). In the specific implementation of lock_spinning(), make sure to set the slowpath flags on the lock just before blocking. We must do this before the last-chance pickup test to prevent a deadlock with the unlocker: UnlockerLocker test for lock pickup - fail unlock test slowpath - false set slowpath flags block Whereas this works in any ordering: UnlockerLocker set slowpath flags test for lock pickup - fail block unlock test slowpath - true, kick If the unlocker finds that the lock has the slowpath flag set but it is actually uncontended (ie, head == tail, so nobody is waiting), then it clears the slowpath flag. The unlock code uses a locked add to update the head counter. This also acts as a full memory barrier so that its safe to subsequently read back the slowflag state, knowing that the updated lock is visible to the other CPUs. If it were an unlocked add, then the flag read may just be forwarded from the store buffer before it was visible to the other CPUs, which could result in a deadlock. Unfortunately this means we need to do a locked instruction when unlocking with PV ticketlocks. However, if PV ticketlocks are not enabled, then the old non-locked add is the only unlocking code. Note: this code relies on gcc making sure that unlikely() code is out of line of the fastpath, which only happens when OPTIMIZE_SIZE=n. If it doesn't the generated code isn't too bad, but its definitely suboptimal. Thanks to Srivatsa Vaddagiri for providing a bugfix to the original version of this change, which has been folded in. Thanks to Stephan Diestelhorst for commenting on some code which relied on an inaccurate reading of the x86 memory ordering rules. Signed-off-by: Jeremy Fitzhardinge jeremy.fitzhardi...@citrix.com Signed-off-by: Srivatsa Vaddagiri va...@linux.vnet.ibm.com Reviewed-by: Konrad Rzeszutek Wilk konrad.w...@oracle.com Cc: Stephan Diestelhorst stephan.diestelho...@amd.com Signed-off-by: Raghavendra K T raghavendra...@linux.vnet.ibm.com --- arch/x86/include/asm/paravirt.h |2 - arch/x86/include/asm/spinlock.h | 86 - arch/x86/include/asm/spinlock_types.h |2 + arch/x86/kernel/paravirt-spinlocks.c |3 + arch/x86/xen/spinlock.c |6 ++ 5 files changed, 74 insertions(+), 25 deletions(-) diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h index 7131e12c..401f350 100644 --- a/arch/x86/include/asm/paravirt.h +++ b/arch/x86/include/asm/paravirt.h @@ -718,7 +718,7 @@ static __always_inline void __ticket_lock_spinning(struct arch_spinlock *lock, PVOP_VCALLEE2(pv_lock_ops.lock_spinning, lock, ticket); } -static __always_inline void ticket_unlock_kick(struct arch_spinlock *lock, +static __always_inline void __ticket_unlock_kick(struct arch_spinlock *lock, __ticket_t ticket) { PVOP_VCALL2(pv_lock_ops.unlock_kick, lock, ticket); diff --git a/arch/x86/include/asm/spinlock.h b/arch/x86/include/asm/spinlock.h index 04a5cd5..d68883d 100644 --- a/arch/x86/include/asm/spinlock.h +++ b/arch/x86/include/asm/spinlock.h @@ -1,11 +1,14 @@ #ifndef _ASM_X86_SPINLOCK_H #define _ASM_X86_SPINLOCK_H +#include linux/jump_label.h #include linux/atomic.h #include asm/page.h #include asm/processor.h #include linux/compiler.h #include asm/paravirt.h +#include asm/bitops.h + /* * Your basic SMP spinlocks, allowing only a single CPU anywhere * @@ -37,32 +40,28 @@ /* How long a lock should spin before we consider blocking */ #define SPIN_THRESHOLD (1 15) -#ifndef CONFIG_PARAVIRT_SPINLOCKS +extern struct static_key paravirt_ticketlocks_enabled; +static __always_inline bool static_key_false(struct static_key *key); -static __always_inline void __ticket_lock_spinning(struct arch_spinlock *lock, - __ticket_t ticket) +#ifdef CONFIG_PARAVIRT_SPINLOCKS + +static inline void __ticket_enter_slowpath(arch_spinlock_t *lock) { + set_bit(0, (volatile unsigned long *)lock-tickets.tail); } -static __always_inline void ticket_unlock_kick(struct arch_spinlock *lock, -__ticket_t ticket) +#else /*