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/x86/include/asm/mutex.h | 5 -- arch/x86/include/asm/mutex_32.h | 110 ---------------------------------- arch/x86/include/asm/mutex_64.h | 127 ---------------------------------------- 3 files changed, 242 deletions(-) delete mode 100644 arch/x86/include/asm/mutex.h delete mode 100644 arch/x86/include/asm/mutex_32.h delete mode 100644 arch/x86/include/asm/mutex_64.h (limited to 'arch/x86/include') diff --git a/arch/x86/include/asm/mutex.h b/arch/x86/include/asm/mutex.h deleted file mode 100644 index 7d3a48275394..000000000000 --- a/arch/x86/include/asm/mutex.h +++ /dev/null @@ -1,5 +0,0 @@ -#ifdef CONFIG_X86_32 -# include -#else -# include -#endif diff --git a/arch/x86/include/asm/mutex_32.h b/arch/x86/include/asm/mutex_32.h deleted file mode 100644 index e9355a84fc67..000000000000 --- a/arch/x86/include/asm/mutex_32.h +++ /dev/null @@ -1,110 +0,0 @@ -/* - * Assembly implementation of the mutex fastpath, based on atomic - * decrement/increment. - * - * started by Ingo Molnar: - * - * Copyright (C) 2004, 2005, 2006 Red Hat, Inc., Ingo Molnar - */ -#ifndef _ASM_X86_MUTEX_32_H -#define _ASM_X86_MUTEX_32_H - -#include - -/** - * __mutex_fastpath_lock - try to take the lock by moving the count - * from 1 to a 0 value - * @count: pointer of type atomic_t - * @fn: function to call if the original value was not 1 - * - * Change the count from 1 to a value lower than 1, and call if it - * wasn't 1 originally. This function MUST leave the value lower than 1 - * even when the "1" assertion wasn't true. - */ -#define __mutex_fastpath_lock(count, fail_fn) \ -do { \ - unsigned int dummy; \ - \ - typecheck(atomic_t *, count); \ - typecheck_fn(void (*)(atomic_t *), fail_fn); \ - \ - asm volatile(LOCK_PREFIX " decl (%%eax)\n" \ - " jns 1f \n" \ - " call " #fail_fn "\n" \ - "1:\n" \ - : "=a" (dummy) \ - : "a" (count) \ - : "memory", "ecx", "edx"); \ -} while (0) - - -/** - * __mutex_fastpath_lock_retval - try to take the lock by moving the count - * from 1 to a 0 value - * @count: pointer of type atomic_t - * - * Change the count from 1 to a value lower than 1. This function returns 0 - * if the fastpath succeeds, or -1 otherwise. - */ -static inline int __mutex_fastpath_lock_retval(atomic_t *count) -{ - if (unlikely(atomic_dec_return(count) < 0)) - return -1; - else - return 0; -} - -/** - * __mutex_fastpath_unlock - try to promote the mutex from 0 to 1 - * @count: pointer of type atomic_t - * @fail_fn: function to call if the original value was not 0 - * - * try to promote the mutex from 0 to 1. if it wasn't 0, call . - * In the failure case, this function is allowed to either set the value - * to 1, or to set it to a value lower than 1. - * - * If the implementation sets it to a value of lower than 1, the - * __mutex_slowpath_needs_to_unlock() macro needs to return 1, it needs - * to return 0 otherwise. - */ -#define __mutex_fastpath_unlock(count, fail_fn) \ -do { \ - unsigned int dummy; \ - \ - typecheck(atomic_t *, count); \ - typecheck_fn(void (*)(atomic_t *), fail_fn); \ - \ - asm volatile(LOCK_PREFIX " incl (%%eax)\n" \ - " jg 1f\n" \ - " call " #fail_fn "\n" \ - "1:\n" \ - : "=a" (dummy) \ - : "a" (count) \ - : "memory", "ecx", "edx"); \ -} while (0) - -#define __mutex_slowpath_needs_to_unlock() 1 - -/** - * __mutex_fastpath_trylock - try to acquire the mutex, without waiting - * - * @count: pointer of type atomic_t - * @fail_fn: fallback function - * - * Change the count from 1 to a value lower than 1, and return 0 (failure) - * if it wasn't 1 originally, or return 1 (success) otherwise. This function - * MUST leave the value lower than 1 even when the "1" assertion wasn't true. - * Additionally, if the value was < 0 originally, this function must not leave - * it to 0 on failure. - */ -static inline int __mutex_fastpath_trylock(atomic_t *count, - int (*fail_fn)(atomic_t *)) -{ - /* cmpxchg because it never induces a false contention state. */ - if (likely(atomic_read(count) == 1 && atomic_cmpxchg(count, 1, 0) == 1)) - return 1; - - return 0; -} - -#endif /* _ASM_X86_MUTEX_32_H */ diff --git a/arch/x86/include/asm/mutex_64.h b/arch/x86/include/asm/mutex_64.h deleted file mode 100644 index d9850758464e..000000000000 --- a/arch/x86/include/asm/mutex_64.h +++ /dev/null @@ -1,127 +0,0 @@ -/* - * Assembly implementation of the mutex fastpath, based on atomic - * decrement/increment. - * - * started by Ingo Molnar: - * - * Copyright (C) 2004, 2005, 2006 Red Hat, Inc., Ingo Molnar - */ -#ifndef _ASM_X86_MUTEX_64_H -#define _ASM_X86_MUTEX_64_H - -/** - * __mutex_fastpath_lock - decrement and call function if negative - * @v: pointer of type atomic_t - * @fail_fn: function to call if the result is negative - * - * Atomically decrements @v and calls if the result is negative. - */ -#ifdef CC_HAVE_ASM_GOTO -static inline void __mutex_fastpath_lock(atomic_t *v, - void (*fail_fn)(atomic_t *)) -{ - asm_volatile_goto(LOCK_PREFIX " decl %0\n" - " jns %l[exit]\n" - : : "m" (v->counter) - : "memory", "cc" - : exit); - fail_fn(v); -exit: - return; -} -#else -#define __mutex_fastpath_lock(v, fail_fn) \ -do { \ - unsigned long dummy; \ - \ - typecheck(atomic_t *, v); \ - typecheck_fn(void (*)(atomic_t *), fail_fn); \ - \ - asm volatile(LOCK_PREFIX " decl (%%rdi)\n" \ - " jns 1f \n" \ - " call " #fail_fn "\n" \ - "1:" \ - : "=D" (dummy) \ - : "D" (v) \ - : "rax", "rsi", "rdx", "rcx", \ - "r8", "r9", "r10", "r11", "memory"); \ -} while (0) -#endif - -/** - * __mutex_fastpath_lock_retval - try to take the lock by moving the count - * from 1 to a 0 value - * @count: pointer of type atomic_t - * - * Change the count from 1 to a value lower than 1. This function returns 0 - * if the fastpath succeeds, or -1 otherwise. - */ -static inline int __mutex_fastpath_lock_retval(atomic_t *count) -{ - if (unlikely(atomic_dec_return(count) < 0)) - return -1; - else - return 0; -} - -/** - * __mutex_fastpath_unlock - increment and call function if nonpositive - * @v: pointer of type atomic_t - * @fail_fn: function to call if the result is nonpositive - * - * Atomically increments @v and calls if the result is nonpositive. - */ -#ifdef CC_HAVE_ASM_GOTO -static inline void __mutex_fastpath_unlock(atomic_t *v, - void (*fail_fn)(atomic_t *)) -{ - asm_volatile_goto(LOCK_PREFIX " incl %0\n" - " jg %l[exit]\n" - : : "m" (v->counter) - : "memory", "cc" - : exit); - fail_fn(v); -exit: - return; -} -#else -#define __mutex_fastpath_unlock(v, fail_fn) \ -do { \ - unsigned long dummy; \ - \ - typecheck(atomic_t *, v); \ - typecheck_fn(void (*)(atomic_t *), fail_fn); \ - \ - asm volatile(LOCK_PREFIX " incl (%%rdi)\n" \ - " jg 1f\n" \ - " call " #fail_fn "\n" \ - "1:" \ - : "=D" (dummy) \ - : "D" (v) \ - : "rax", "rsi", "rdx", "rcx", \ - "r8", "r9", "r10", "r11", "memory"); \ -} while (0) -#endif - -#define __mutex_slowpath_needs_to_unlock() 1 - -/** - * __mutex_fastpath_trylock - try to acquire the mutex, without waiting - * - * @count: pointer of type atomic_t - * @fail_fn: fallback function - * - * Change the count from 1 to 0 and return 1 (success), or return 0 (failure) - * if it wasn't 1 originally. [the fallback function is never used on - * x86_64, because all x86_64 CPUs have a CMPXCHG instruction.] - */ -static inline int __mutex_fastpath_trylock(atomic_t *count, - int (*fail_fn)(atomic_t *)) -{ - if (likely(atomic_read(count) == 1 && atomic_cmpxchg(count, 1, 0) == 1)) - return 1; - - return 0; -} - -#endif /* _ASM_X86_MUTEX_64_H */ -- cgit v1.2.3 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/x86/include/asm/processor.h | 1 + 1 file changed, 1 insertion(+) (limited to 'arch/x86/include') diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index 984a7bf17f6a..44adadab44d6 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -588,6 +588,7 @@ static __always_inline void cpu_relax(void) rep_nop(); } +#define cpu_relax_yield() cpu_relax() #define cpu_relax_lowlatency() cpu_relax() /* Stop speculative execution and prefetching of modified code. */ -- cgit v1.2.3 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/x86/include/asm/processor.h | 1 - 1 file changed, 1 deletion(-) (limited to 'arch/x86/include') diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index 44adadab44d6..7513c996f673 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -589,7 +589,6 @@ static __always_inline void cpu_relax(void) } #define cpu_relax_yield() cpu_relax() -#define cpu_relax_lowlatency() cpu_relax() /* Stop speculative execution and prefetching of modified code. */ static inline void sync_core(void) -- cgit v1.2.3 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/x86/include/asm/processor.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'arch/x86/include') diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index 7513c996f673..c84605bb2a15 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -588,8 +588,6 @@ static __always_inline void cpu_relax(void) rep_nop(); } -#define cpu_relax_yield() cpu_relax() - /* Stop speculative execution and prefetching of modified code. */ static inline void sync_core(void) { -- cgit v1.2.3 From 446f3dc8cc0af59259c6c8b898726fae7ed2c055 Mon Sep 17 00:00:00 2001 From: Pan Xinhui Date: Wed, 2 Nov 2016 05:08:33 -0400 Subject: locking/core, x86/paravirt: Implement vcpu_is_preempted(cpu) for KVM and Xen guests Optimize spinlock and mutex busy-loops by providing a vcpu_is_preempted(cpu) function on KVM and Xen platforms. Extend the pv_lock_ops interface accordingly and implement the callbacks on KVM and Xen. Signed-off-by: Pan Xinhui Signed-off-by: Peter Zijlstra (Intel) [ Translated to English. ] Acked-by: Paolo Bonzini 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: borntraeger@de.ibm.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: 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/1478077718-37424-7-git-send-email-xinhui.pan@linux.vnet.ibm.com Signed-off-by: Ingo Molnar --- arch/x86/include/asm/paravirt_types.h | 2 ++ arch/x86/include/asm/spinlock.h | 8 ++++++++ 2 files changed, 10 insertions(+) (limited to 'arch/x86/include') diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h index 0f400c0e4979..38c3bb74740f 100644 --- a/arch/x86/include/asm/paravirt_types.h +++ b/arch/x86/include/asm/paravirt_types.h @@ -310,6 +310,8 @@ struct pv_lock_ops { void (*wait)(u8 *ptr, u8 val); void (*kick)(int cpu); + + bool (*vcpu_is_preempted)(int cpu); }; /* This contains all the paravirt structures: we get a convenient diff --git a/arch/x86/include/asm/spinlock.h b/arch/x86/include/asm/spinlock.h index 921bea7a2708..0526f596e399 100644 --- a/arch/x86/include/asm/spinlock.h +++ b/arch/x86/include/asm/spinlock.h @@ -26,6 +26,14 @@ extern struct static_key paravirt_ticketlocks_enabled; static __always_inline bool static_key_false(struct static_key *key); +#ifdef CONFIG_PARAVIRT_SPINLOCKS +#define vcpu_is_preempted vcpu_is_preempted +static inline bool vcpu_is_preempted(int cpu) +{ + return pv_lock_ops.vcpu_is_preempted(cpu); +} +#endif + #include /* -- cgit v1.2.3 From 0b9f6c4615c993d2b552e0d2bd1ade49b56e5beb Mon Sep 17 00:00:00 2001 From: Pan Xinhui Date: Wed, 2 Nov 2016 05:08:35 -0400 Subject: x86/kvm: Support the vCPU preemption check Support the vcpu_is_preempted() functionality under KVM. This will enhance lock performance on overcommitted hosts (more runnable vCPUs than physical CPUs in the system) as doing busy waits for preempted vCPUs will hurt system performance far worse than early yielding. Use struct kvm_steal_time::preempted to indicate that if a vCPU is running or not. Signed-off-by: Pan Xinhui Signed-off-by: Peter Zijlstra (Intel) Acked-by: Paolo Bonzini 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: borntraeger@de.ibm.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: 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/1478077718-37424-9-git-send-email-xinhui.pan@linux.vnet.ibm.com [ Typo fixes. ] Signed-off-by: Ingo Molnar --- arch/x86/include/uapi/asm/kvm_para.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'arch/x86/include') diff --git a/arch/x86/include/uapi/asm/kvm_para.h b/arch/x86/include/uapi/asm/kvm_para.h index 94dc8ca434e0..1421a6585126 100644 --- a/arch/x86/include/uapi/asm/kvm_para.h +++ b/arch/x86/include/uapi/asm/kvm_para.h @@ -45,7 +45,9 @@ struct kvm_steal_time { __u64 steal; __u32 version; __u32 flags; - __u32 pad[12]; + __u8 preempted; + __u8 u8_pad[3]; + __u32 pad[11]; }; #define KVM_STEAL_ALIGNMENT_BITS 5 -- cgit v1.2.3 From 3cded41794818d788aa1dc028ede4a1c1222d937 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 15 Nov 2016 16:47:06 +0100 Subject: x86/paravirt: Optimize native pv_lock_ops.vcpu_is_preempted() Avoid the pointless function call to pv_lock_ops.vcpu_is_preempted() when a paravirt spinlock enabled kernel is ran on native hardware. Do this by patching out the CALL instruction with "XOR %RAX,%RAX" which has the same effect (0 return value). Signed-off-by: Peter Zijlstra (Intel) Cc: David.Laight@ACULAB.COM Cc: Linus Torvalds Cc: Pan Xinhui Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: benh@kernel.crashing.org Cc: boqun.feng@gmail.com Cc: borntraeger@de.ibm.com Cc: bsingharora@gmail.com Cc: dave@stgolabs.net Cc: jgross@suse.com Cc: kernellwp@gmail.com Cc: konrad.wilk@oracle.com Cc: mpe@ellerman.id.au Cc: paulmck@linux.vnet.ibm.com Cc: paulus@samba.org Cc: pbonzini@redhat.com Cc: rkrcmar@redhat.com Cc: will.deacon@arm.com Signed-off-by: Ingo Molnar --- arch/x86/include/asm/paravirt.h | 5 +++++ arch/x86/include/asm/paravirt_types.h | 2 +- arch/x86/include/asm/qspinlock.h | 6 ++++++ arch/x86/include/asm/spinlock.h | 8 -------- 4 files changed, 12 insertions(+), 9 deletions(-) (limited to 'arch/x86/include') diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h index ce932812f142..6108b1fada2b 100644 --- a/arch/x86/include/asm/paravirt.h +++ b/arch/x86/include/asm/paravirt.h @@ -678,6 +678,11 @@ static __always_inline void pv_kick(int cpu) PVOP_VCALL1(pv_lock_ops.kick, cpu); } +static __always_inline bool pv_vcpu_is_preempted(int cpu) +{ + return PVOP_CALLEE1(bool, pv_lock_ops.vcpu_is_preempted, cpu); +} + #endif /* SMP && PARAVIRT_SPINLOCKS */ #ifdef CONFIG_X86_32 diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h index 38c3bb74740f..2614bd7a7839 100644 --- a/arch/x86/include/asm/paravirt_types.h +++ b/arch/x86/include/asm/paravirt_types.h @@ -311,7 +311,7 @@ struct pv_lock_ops { void (*wait)(u8 *ptr, u8 val); void (*kick)(int cpu); - bool (*vcpu_is_preempted)(int cpu); + struct paravirt_callee_save vcpu_is_preempted; }; /* This contains all the paravirt structures: we get a convenient diff --git a/arch/x86/include/asm/qspinlock.h b/arch/x86/include/asm/qspinlock.h index eaba08076030..c343ab52579f 100644 --- a/arch/x86/include/asm/qspinlock.h +++ b/arch/x86/include/asm/qspinlock.h @@ -32,6 +32,12 @@ static inline void queued_spin_unlock(struct qspinlock *lock) { pv_queued_spin_unlock(lock); } + +#define vcpu_is_preempted vcpu_is_preempted +static inline bool vcpu_is_preempted(int cpu) +{ + return pv_vcpu_is_preempted(cpu); +} #else static inline void queued_spin_unlock(struct qspinlock *lock) { diff --git a/arch/x86/include/asm/spinlock.h b/arch/x86/include/asm/spinlock.h index 0526f596e399..921bea7a2708 100644 --- a/arch/x86/include/asm/spinlock.h +++ b/arch/x86/include/asm/spinlock.h @@ -26,14 +26,6 @@ extern struct static_key paravirt_ticketlocks_enabled; static __always_inline bool static_key_false(struct static_key *key); -#ifdef CONFIG_PARAVIRT_SPINLOCKS -#define vcpu_is_preempted vcpu_is_preempted -static inline bool vcpu_is_preempted(int cpu) -{ - return pv_lock_ops.vcpu_is_preempted(cpu); -} -#endif - #include /* -- cgit v1.2.3 From 11f254dbb3a2e3f0d8552d0dd37f4faa432b6b16 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Thu, 8 Dec 2016 16:42:15 +0100 Subject: x86/paravirt: Fix bool return type for PVOP_CALL() Commit: 3cded4179481 ("x86/paravirt: Optimize native pv_lock_ops.vcpu_is_preempted()") introduced a paravirt op with bool return type [*] It turns out that the PVOP_CALL*() macros miscompile when rettype is bool. Code that looked like: 83 ef 01 sub $0x1,%edi ff 15 32 a0 d8 00 callq *0xd8a032(%rip) # ffffffff81e28120 84 c0 test %al,%al ended up looking like so after PVOP_CALL1() was applied: 83 ef 01 sub $0x1,%edi 48 63 ff movslq %edi,%rdi ff 14 25 20 81 e2 81 callq *0xffffffff81e28120 48 85 c0 test %rax,%rax Note how it tests the whole of %rax, even though a typical bool return function only sets %al, like: 0f 95 c0 setne %al c3 retq This is because ____PVOP_CALL() does: __ret = (rettype)__eax; and while regular integer type casts truncate the result, a cast to bool tests for any !0 value. Fix this by explicitly truncating to sizeof(rettype) before casting. [*] The actual bug should've been exposed in commit: 446f3dc8cc0a ("locking/core, x86/paravirt: Implement vcpu_is_preempted(cpu) for KVM and Xen guests") but that didn't properly implement the paravirt call. Reported-by: kernel test robot Signed-off-by: Peter Zijlstra (Intel) Cc: Alok Kataria Cc: Borislav Petkov Cc: Chris Wright Cc: Jeremy Fitzhardinge Cc: Linus Torvalds Cc: Pan Xinhui Cc: Paolo Bonzini Cc: Peter Anvin Cc: Peter Zijlstra Cc: Rusty Russell Cc: Thomas Gleixner Fixes: 3cded4179481 ("x86/paravirt: Optimize native pv_lock_ops.vcpu_is_preempted()") Link: http://lkml.kernel.org/r/20161208154349.346057680@infradead.org Signed-off-by: Ingo Molnar --- arch/x86/include/asm/paravirt_types.h | 14 +++++++++++++- 1 file changed, 13 insertions(+), 1 deletion(-) (limited to 'arch/x86/include') diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h index 2614bd7a7839..3f2bc0f0d3e8 100644 --- a/arch/x86/include/asm/paravirt_types.h +++ b/arch/x86/include/asm/paravirt_types.h @@ -510,6 +510,18 @@ int paravirt_disable_iospace(void); #define PVOP_TEST_NULL(op) ((void)op) #endif +#define PVOP_RETMASK(rettype) \ + ({ unsigned long __mask = ~0UL; \ + switch (sizeof(rettype)) { \ + case 1: __mask = 0xffUL; break; \ + case 2: __mask = 0xffffUL; break; \ + case 4: __mask = 0xffffffffUL; break; \ + default: break; \ + } \ + __mask; \ + }) + + #define ____PVOP_CALL(rettype, op, clbr, call_clbr, extra_clbr, \ pre, post, ...) \ ({ \ @@ -537,7 +549,7 @@ int paravirt_disable_iospace(void); paravirt_clobber(clbr), \ ##__VA_ARGS__ \ : "memory", "cc" extra_clbr); \ - __ret = (rettype)__eax; \ + __ret = (rettype)(__eax & PVOP_RETMASK(rettype)); \ } \ __ret; \ }) -- cgit v1.2.3