From 890658b7ab48d1362a0362df842cecc73c83146f Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 23 Aug 2016 13:36:04 +0200 Subject: locking/mutex: Kill arch specific code Its all generic atomic_long_t stuff now. Tested-by: Jason Low Signed-off-by: Peter Zijlstra (Intel) Cc: Andrew Morton Cc: Linus Torvalds Cc: Paul E. McKenney Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: linux-arch@vger.kernel.org Cc: linux-kernel@vger.kernel.org Signed-off-by: Ingo Molnar --- arch/s390/include/asm/mutex.h | 9 --------- 1 file changed, 9 deletions(-) delete mode 100644 arch/s390/include/asm/mutex.h (limited to 'arch/s390') diff --git a/arch/s390/include/asm/mutex.h b/arch/s390/include/asm/mutex.h deleted file mode 100644 index 458c1f7..0000000 --- a/arch/s390/include/asm/mutex.h +++ /dev/null @@ -1,9 +0,0 @@ -/* - * Pull in the generic implementation for the mutex fastpath. - * - * TODO: implement optimized primitives instead, or leave the generic - * implementation in place, or pick the atomic_xchg() based generic - * implementation. (see asm-generic/mutex-xchg.h for details) - */ - -#include -- cgit v1.1 From 79ab11cdb90d8536817ab7357ecb6b1ff76be26c Mon Sep 17 00:00:00 2001 From: Christian Borntraeger Date: Tue, 25 Oct 2016 11:03:11 +0200 Subject: locking/core: Introduce cpu_relax_yield() For spinning loops people do often use barrier() or cpu_relax(). For most architectures cpu_relax and barrier are the same, but on some architectures cpu_relax can add some latency. For example on power,sparc64 and arc, cpu_relax can shift the CPU towards other hardware threads in an SMT environment. On s390 cpu_relax does even more, it uses an hypercall to the hypervisor to give up the timeslice. In contrast to the SMT yielding this can result in larger latencies. In some places this latency is unwanted, so another variant "cpu_relax_lowlatency" was introduced. Before this is used in more and more places, lets revert the logic and provide a cpu_relax_yield that can be called in places where yielding is more important than latency. By default this is the same as cpu_relax on all architectures. Signed-off-by: Christian Borntraeger Signed-off-by: Peter Zijlstra (Intel) Cc: Catalin Marinas Cc: Heiko Carstens Cc: Linus Torvalds Cc: Martin Schwidefsky Cc: Nicholas Piggin Cc: Noam Camus Cc: Peter Zijlstra Cc: Russell King Cc: Thomas Gleixner Cc: Will Deacon Cc: linuxppc-dev@lists.ozlabs.org Cc: virtualization@lists.linux-foundation.org Cc: xen-devel@lists.xenproject.org Link: http://lkml.kernel.org/r/1477386195-32736-2-git-send-email-borntraeger@de.ibm.com Signed-off-by: Ingo Molnar --- arch/s390/include/asm/processor.h | 3 ++- arch/s390/kernel/processor.c | 4 ++-- 2 files changed, 4 insertions(+), 3 deletions(-) (limited to 'arch/s390') diff --git a/arch/s390/include/asm/processor.h b/arch/s390/include/asm/processor.h index 602af69..5bb4433 100644 --- a/arch/s390/include/asm/processor.h +++ b/arch/s390/include/asm/processor.h @@ -234,8 +234,9 @@ static inline unsigned short stap(void) /* * Give up the time slice of the virtual PU. */ -void cpu_relax(void); +void cpu_relax_yield(void); +#define cpu_relax() cpu_relax_yield() #define cpu_relax_lowlatency() barrier() #define ECAG_CACHE_ATTRIBUTE 0 diff --git a/arch/s390/kernel/processor.c b/arch/s390/kernel/processor.c index 81d0808..9e60ef1 100644 --- a/arch/s390/kernel/processor.c +++ b/arch/s390/kernel/processor.c @@ -53,7 +53,7 @@ void s390_update_cpu_mhz(void) on_each_cpu(update_cpu_mhz, NULL, 0); } -void notrace cpu_relax(void) +void notrace cpu_relax_yield(void) { if (!smp_cpu_mtid && MACHINE_HAS_DIAG44) { diag_stat_inc(DIAG_STAT_X044); @@ -61,7 +61,7 @@ void notrace cpu_relax(void) } barrier(); } -EXPORT_SYMBOL(cpu_relax); +EXPORT_SYMBOL(cpu_relax_yield); /* * cpu_init - initializes state that is per-CPU. -- cgit v1.1 From 22b6430d36659b37ed139b7fd87fcc7237fb0cfd Mon Sep 17 00:00:00 2001 From: Christian Borntraeger Date: Tue, 25 Oct 2016 11:03:13 +0200 Subject: locking/core, s390: Make cpu_relax() a barrier again stop_machine() seemed to be the only important place for yielding during cpu_relax(). This was fixed by using cpu_relax_yield(). Therefore, we can now redefine cpu_relax() to be a barrier instead on s390, making s390 identical to all other architectures. Signed-off-by: Christian Borntraeger Signed-off-by: Peter Zijlstra (Intel) Cc: Catalin Marinas Cc: Heiko Carstens Cc: Linus Torvalds Cc: Martin Schwidefsky Cc: Nicholas Piggin Cc: Noam Camus Cc: Peter Zijlstra Cc: Russell King Cc: Thomas Gleixner Cc: Will Deacon Cc: linuxppc-dev@lists.ozlabs.org Cc: virtualization@lists.linux-foundation.org Cc: xen-devel@lists.xenproject.org Link: http://lkml.kernel.org/r/1477386195-32736-4-git-send-email-borntraeger@de.ibm.com Signed-off-by: Ingo Molnar --- arch/s390/include/asm/processor.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch/s390') diff --git a/arch/s390/include/asm/processor.h b/arch/s390/include/asm/processor.h index 5bb4433..79343e3 100644 --- a/arch/s390/include/asm/processor.h +++ b/arch/s390/include/asm/processor.h @@ -236,7 +236,7 @@ static inline unsigned short stap(void) */ void cpu_relax_yield(void); -#define cpu_relax() cpu_relax_yield() +#define cpu_relax() barrier() #define cpu_relax_lowlatency() barrier() #define ECAG_CACHE_ATTRIBUTE 0 -- cgit v1.1 From 5bd0b85ba8bb9de6f61f33f3752fc85f4c87fc22 Mon Sep 17 00:00:00 2001 From: Christian Borntraeger Date: Tue, 25 Oct 2016 11:03:15 +0200 Subject: locking/core, arch: Remove cpu_relax_lowlatency() As there are no users left, we can remove cpu_relax_lowlatency() implementations from every architecture. Signed-off-by: Christian Borntraeger Signed-off-by: Peter Zijlstra (Intel) Cc: Catalin Marinas Cc: Heiko Carstens Cc: Linus Torvalds Cc: Martin Schwidefsky Cc: Nicholas Piggin Cc: Noam Camus Cc: Peter Zijlstra Cc: Russell King Cc: Thomas Gleixner Cc: Will Deacon Cc: linuxppc-dev@lists.ozlabs.org Cc: virtualization@lists.linux-foundation.org Cc: xen-devel@lists.xenproject.org Cc: Link: http://lkml.kernel.org/r/1477386195-32736-6-git-send-email-borntraeger@de.ibm.com Signed-off-by: Ingo Molnar --- arch/s390/include/asm/processor.h | 1 - 1 file changed, 1 deletion(-) (limited to 'arch/s390') diff --git a/arch/s390/include/asm/processor.h b/arch/s390/include/asm/processor.h index 79343e3..9e32f25 100644 --- a/arch/s390/include/asm/processor.h +++ b/arch/s390/include/asm/processor.h @@ -237,7 +237,6 @@ static inline unsigned short stap(void) void cpu_relax_yield(void); #define cpu_relax() barrier() -#define cpu_relax_lowlatency() barrier() #define ECAG_CACHE_ATTRIBUTE 0 #define ECAG_CPU_ATTRIBUTE 1 -- cgit v1.1 From 6d0d287891a022ebba572327cbd70b5de69a63a2 Mon Sep 17 00:00:00 2001 From: Christian Borntraeger Date: Wed, 16 Nov 2016 13:23:05 +0100 Subject: locking/core: Provide common cpu_relax_yield() definition No need to duplicate the same define everywhere. Since the only user is stop-machine and the only provider is s390, we can use a default implementation of cpu_relax_yield() in sched.h. Suggested-by: Russell King Signed-off-by: Christian Borntraeger Reviewed-by: David Hildenbrand Acked-by: Russell King Cc: Andrew Morton Cc: Catalin Marinas Cc: Heiko Carstens Cc: Linus Torvalds Cc: Martin Schwidefsky Cc: Nicholas Piggin Cc: Noam Camus Cc: Paul E. McKenney Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: Will Deacon Cc: kvm@vger.kernel.org Cc: linux-arch@vger.kernel.org Cc: linux-s390 Cc: linuxppc-dev@lists.ozlabs.org Cc: sparclinux@vger.kernel.org Cc: virtualization@lists.linux-foundation.org Cc: xen-devel@lists.xenproject.org Link: http://lkml.kernel.org/r/1479298985-191589-1-git-send-email-borntraeger@de.ibm.com Signed-off-by: Ingo Molnar --- arch/s390/include/asm/processor.h | 1 + 1 file changed, 1 insertion(+) (limited to 'arch/s390') diff --git a/arch/s390/include/asm/processor.h b/arch/s390/include/asm/processor.h index 9e32f25..9d3a21a 100644 --- a/arch/s390/include/asm/processor.h +++ b/arch/s390/include/asm/processor.h @@ -234,6 +234,7 @@ static inline unsigned short stap(void) /* * Give up the time slice of the virtual PU. */ +#define cpu_relax_yield cpu_relax_yield void cpu_relax_yield(void); #define cpu_relax() barrier() -- cgit v1.1 From 760928c0dafc7d0faf0c0248e28e16d4c8dc7ad6 Mon Sep 17 00:00:00 2001 From: Christian Borntraeger Date: Wed, 2 Nov 2016 05:08:32 -0400 Subject: locking/spinlocks, s390: Implement vcpu_is_preempted(cpu) This implements the s390 version for vcpu_is_preempted(cpu), by reworking the existing smp_vcpu_scheduled() function into arch_vcpu_is_preempted(). We can then also get rid of the local cpu_is_preempted() function by moving the CIF_ENABLED_WAIT test into arch_vcpu_is_preempted(). Signed-off-by: Christian Borntraeger Signed-off-by: Peter Zijlstra (Intel) Acked-by: Heiko Carstens Cc: David.Laight@ACULAB.COM Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: benh@kernel.crashing.org Cc: boqun.feng@gmail.com Cc: bsingharora@gmail.com Cc: dave@stgolabs.net Cc: jgross@suse.com Cc: kernellwp@gmail.com Cc: konrad.wilk@oracle.com Cc: linuxppc-dev@lists.ozlabs.org Cc: mpe@ellerman.id.au Cc: paulmck@linux.vnet.ibm.com Cc: paulus@samba.org Cc: pbonzini@redhat.com Cc: rkrcmar@redhat.com Cc: virtualization@lists.linux-foundation.org Cc: will.deacon@arm.com Cc: xen-devel-request@lists.xenproject.org Cc: xen-devel@lists.xenproject.org Link: http://lkml.kernel.org/r/1478077718-37424-6-git-send-email-xinhui.pan@linux.vnet.ibm.com Signed-off-by: Ingo Molnar --- arch/s390/include/asm/spinlock.h | 8 ++++++++ arch/s390/kernel/smp.c | 9 +++++++-- arch/s390/lib/spinlock.c | 25 ++++++++----------------- 3 files changed, 23 insertions(+), 19 deletions(-) (limited to 'arch/s390') diff --git a/arch/s390/include/asm/spinlock.h b/arch/s390/include/asm/spinlock.h index 7e9e09f..7ecd890 100644 --- a/arch/s390/include/asm/spinlock.h +++ b/arch/s390/include/asm/spinlock.h @@ -23,6 +23,14 @@ _raw_compare_and_swap(unsigned int *lock, unsigned int old, unsigned int new) return __sync_bool_compare_and_swap(lock, old, new); } +#ifndef CONFIG_SMP +static inline bool arch_vcpu_is_preempted(int cpu) { return false; } +#else +bool arch_vcpu_is_preempted(int cpu); +#endif + +#define vcpu_is_preempted arch_vcpu_is_preempted + /* * Simple spin lock operations. There are two variants, one clears IRQ's * on the local processor, one does not. diff --git a/arch/s390/kernel/smp.c b/arch/s390/kernel/smp.c index 35531fe..b988ed1 100644 --- a/arch/s390/kernel/smp.c +++ b/arch/s390/kernel/smp.c @@ -368,10 +368,15 @@ int smp_find_processor_id(u16 address) return -1; } -int smp_vcpu_scheduled(int cpu) +bool arch_vcpu_is_preempted(int cpu) { - return pcpu_running(pcpu_devices + cpu); + if (test_cpu_flag_of(CIF_ENABLED_WAIT, cpu)) + return false; + if (pcpu_running(pcpu_devices + cpu)) + return false; + return true; } +EXPORT_SYMBOL(arch_vcpu_is_preempted); void smp_yield_cpu(int cpu) { diff --git a/arch/s390/lib/spinlock.c b/arch/s390/lib/spinlock.c index e5f50a7..e48a48e 100644 --- a/arch/s390/lib/spinlock.c +++ b/arch/s390/lib/spinlock.c @@ -37,15 +37,6 @@ static inline void _raw_compare_and_delay(unsigned int *lock, unsigned int old) asm(".insn rsy,0xeb0000000022,%0,0,%1" : : "d" (old), "Q" (*lock)); } -static inline int cpu_is_preempted(int cpu) -{ - if (test_cpu_flag_of(CIF_ENABLED_WAIT, cpu)) - return 0; - if (smp_vcpu_scheduled(cpu)) - return 0; - return 1; -} - void arch_spin_lock_wait(arch_spinlock_t *lp) { unsigned int cpu = SPINLOCK_LOCKVAL; @@ -62,7 +53,7 @@ void arch_spin_lock_wait(arch_spinlock_t *lp) continue; } /* First iteration: check if the lock owner is running. */ - if (first_diag && cpu_is_preempted(~owner)) { + if (first_diag && arch_vcpu_is_preempted(~owner)) { smp_yield_cpu(~owner); first_diag = 0; continue; @@ -81,7 +72,7 @@ void arch_spin_lock_wait(arch_spinlock_t *lp) * yield the CPU unconditionally. For LPAR rely on the * sense running status. */ - if (!MACHINE_IS_LPAR || cpu_is_preempted(~owner)) { + if (!MACHINE_IS_LPAR || arch_vcpu_is_preempted(~owner)) { smp_yield_cpu(~owner); first_diag = 0; } @@ -108,7 +99,7 @@ void arch_spin_lock_wait_flags(arch_spinlock_t *lp, unsigned long flags) continue; } /* Check if the lock owner is running. */ - if (first_diag && cpu_is_preempted(~owner)) { + if (first_diag && arch_vcpu_is_preempted(~owner)) { smp_yield_cpu(~owner); first_diag = 0; continue; @@ -127,7 +118,7 @@ void arch_spin_lock_wait_flags(arch_spinlock_t *lp, unsigned long flags) * yield the CPU unconditionally. For LPAR rely on the * sense running status. */ - if (!MACHINE_IS_LPAR || cpu_is_preempted(~owner)) { + if (!MACHINE_IS_LPAR || arch_vcpu_is_preempted(~owner)) { smp_yield_cpu(~owner); first_diag = 0; } @@ -165,7 +156,7 @@ void _raw_read_lock_wait(arch_rwlock_t *rw) owner = 0; while (1) { if (count-- <= 0) { - if (owner && cpu_is_preempted(~owner)) + if (owner && arch_vcpu_is_preempted(~owner)) smp_yield_cpu(~owner); count = spin_retry; } @@ -211,7 +202,7 @@ void _raw_write_lock_wait(arch_rwlock_t *rw, unsigned int prev) owner = 0; while (1) { if (count-- <= 0) { - if (owner && cpu_is_preempted(~owner)) + if (owner && arch_vcpu_is_preempted(~owner)) smp_yield_cpu(~owner); count = spin_retry; } @@ -241,7 +232,7 @@ void _raw_write_lock_wait(arch_rwlock_t *rw) owner = 0; while (1) { if (count-- <= 0) { - if (owner && cpu_is_preempted(~owner)) + if (owner && arch_vcpu_is_preempted(~owner)) smp_yield_cpu(~owner); count = spin_retry; } @@ -285,7 +276,7 @@ void arch_lock_relax(unsigned int cpu) { if (!cpu) return; - if (MACHINE_IS_LPAR && !cpu_is_preempted(~cpu)) + if (MACHINE_IS_LPAR && !arch_vcpu_is_preempted(~cpu)) return; smp_yield_cpu(~cpu); } -- cgit v1.1