summaryrefslogtreecommitdiff
path: root/arch/x86
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86')
-rw-r--r--arch/x86/include/asm/mutex.h5
-rw-r--r--arch/x86/include/asm/mutex_32.h110
-rw-r--r--arch/x86/include/asm/mutex_64.h127
-rw-r--r--arch/x86/include/asm/paravirt.h5
-rw-r--r--arch/x86/include/asm/paravirt_types.h16
-rw-r--r--arch/x86/include/asm/processor.h2
-rw-r--r--arch/x86/include/asm/qspinlock.h6
-rw-r--r--arch/x86/include/uapi/asm/kvm_para.h4
-rw-r--r--arch/x86/kernel/kvm.c13
-rw-r--r--arch/x86/kernel/paravirt-spinlocks.c14
-rw-r--r--arch/x86/kernel/paravirt_patch_32.c12
-rw-r--r--arch/x86/kernel/paravirt_patch_64.c12
-rw-r--r--arch/x86/kvm/x86.c16
-rw-r--r--arch/x86/um/asm/processor.h1
-rw-r--r--arch/x86/xen/spinlock.c2
15 files changed, 97 insertions, 248 deletions
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 <asm/mutex_32.h>
-#else
-# include <asm/mutex_64.h>
-#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 <mingo@redhat.com>
- */
-#ifndef _ASM_X86_MUTEX_32_H
-#define _ASM_X86_MUTEX_32_H
-
-#include <asm/alternative.h>
-
-/**
- * __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 <fn> 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 <fail_fn>.
- * 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 <mingo@redhat.com>
- */
-#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 <fail_fn> 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 <fail_fn> 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 */
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 0f400c0e4979..3f2bc0f0d3e8 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);
+
+ struct paravirt_callee_save vcpu_is_preempted;
};
/* This contains all the paravirt structures: we get a convenient
@@ -508,6 +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, ...) \
({ \
@@ -535,7 +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; \
})
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index 984a7bf17f6a..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_lowlatency() cpu_relax()
-
/* Stop speculative execution and prefetching of modified code. */
static inline void sync_core(void)
{
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/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
diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index edbbfc854e39..52e90d6054fb 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -592,6 +592,14 @@ out:
local_irq_restore(flags);
}
+__visible bool __kvm_vcpu_is_preempted(int cpu)
+{
+ struct kvm_steal_time *src = &per_cpu(steal_time, cpu);
+
+ return !!src->preempted;
+}
+PV_CALLEE_SAVE_REGS_THUNK(__kvm_vcpu_is_preempted);
+
/*
* Setup pv_lock_ops to exploit KVM_FEATURE_PV_UNHALT if present.
*/
@@ -608,6 +616,11 @@ void __init kvm_spinlock_init(void)
pv_lock_ops.queued_spin_unlock = PV_CALLEE_SAVE(__pv_queued_spin_unlock);
pv_lock_ops.wait = kvm_wait;
pv_lock_ops.kick = kvm_kick_cpu;
+
+ if (kvm_para_has_feature(KVM_FEATURE_STEAL_TIME)) {
+ pv_lock_ops.vcpu_is_preempted =
+ PV_CALLEE_SAVE(__kvm_vcpu_is_preempted);
+ }
}
static __init int kvm_spinlock_init_jump(void)
diff --git a/arch/x86/kernel/paravirt-spinlocks.c b/arch/x86/kernel/paravirt-spinlocks.c
index 2c55a003b793..6d4bf812af45 100644
--- a/arch/x86/kernel/paravirt-spinlocks.c
+++ b/arch/x86/kernel/paravirt-spinlocks.c
@@ -12,7 +12,6 @@ __visible void __native_queued_spin_unlock(struct qspinlock *lock)
{
native_queued_spin_unlock(lock);
}
-
PV_CALLEE_SAVE_REGS_THUNK(__native_queued_spin_unlock);
bool pv_is_native_spin_unlock(void)
@@ -21,12 +20,25 @@ bool pv_is_native_spin_unlock(void)
__raw_callee_save___native_queued_spin_unlock;
}
+__visible bool __native_vcpu_is_preempted(int cpu)
+{
+ return false;
+}
+PV_CALLEE_SAVE_REGS_THUNK(__native_vcpu_is_preempted);
+
+bool pv_is_native_vcpu_is_preempted(void)
+{
+ return pv_lock_ops.vcpu_is_preempted.func ==
+ __raw_callee_save___native_vcpu_is_preempted;
+}
+
struct pv_lock_ops pv_lock_ops = {
#ifdef CONFIG_SMP
.queued_spin_lock_slowpath = native_queued_spin_lock_slowpath,
.queued_spin_unlock = PV_CALLEE_SAVE(__native_queued_spin_unlock),
.wait = paravirt_nop,
.kick = paravirt_nop,
+ .vcpu_is_preempted = PV_CALLEE_SAVE(__native_vcpu_is_preempted),
#endif /* SMP */
};
EXPORT_SYMBOL(pv_lock_ops);
diff --git a/arch/x86/kernel/paravirt_patch_32.c b/arch/x86/kernel/paravirt_patch_32.c
index 920c6ae08592..33cdec221f3d 100644
--- a/arch/x86/kernel/paravirt_patch_32.c
+++ b/arch/x86/kernel/paravirt_patch_32.c
@@ -12,6 +12,7 @@ DEF_NATIVE(pv_cpu_ops, clts, "clts");
#if defined(CONFIG_PARAVIRT_SPINLOCKS)
DEF_NATIVE(pv_lock_ops, queued_spin_unlock, "movb $0, (%eax)");
+DEF_NATIVE(pv_lock_ops, vcpu_is_preempted, "xor %eax, %eax");
#endif
unsigned paravirt_patch_ident_32(void *insnbuf, unsigned len)
@@ -27,6 +28,7 @@ unsigned paravirt_patch_ident_64(void *insnbuf, unsigned len)
}
extern bool pv_is_native_spin_unlock(void);
+extern bool pv_is_native_vcpu_is_preempted(void);
unsigned native_patch(u8 type, u16 clobbers, void *ibuf,
unsigned long addr, unsigned len)
@@ -56,9 +58,19 @@ unsigned native_patch(u8 type, u16 clobbers, void *ibuf,
end = end_pv_lock_ops_queued_spin_unlock;
goto patch_site;
}
+ goto patch_default;
+
+ case PARAVIRT_PATCH(pv_lock_ops.vcpu_is_preempted):
+ if (pv_is_native_vcpu_is_preempted()) {
+ start = start_pv_lock_ops_vcpu_is_preempted;
+ end = end_pv_lock_ops_vcpu_is_preempted;
+ goto patch_site;
+ }
+ goto patch_default;
#endif
default:
+patch_default:
ret = paravirt_patch_default(type, clobbers, ibuf, addr, len);
break;
diff --git a/arch/x86/kernel/paravirt_patch_64.c b/arch/x86/kernel/paravirt_patch_64.c
index bb3840cedb4f..b0fceff502b3 100644
--- a/arch/x86/kernel/paravirt_patch_64.c
+++ b/arch/x86/kernel/paravirt_patch_64.c
@@ -21,6 +21,7 @@ DEF_NATIVE(, mov64, "mov %rdi, %rax");
#if defined(CONFIG_PARAVIRT_SPINLOCKS)
DEF_NATIVE(pv_lock_ops, queued_spin_unlock, "movb $0, (%rdi)");
+DEF_NATIVE(pv_lock_ops, vcpu_is_preempted, "xor %rax, %rax");
#endif
unsigned paravirt_patch_ident_32(void *insnbuf, unsigned len)
@@ -36,6 +37,7 @@ unsigned paravirt_patch_ident_64(void *insnbuf, unsigned len)
}
extern bool pv_is_native_spin_unlock(void);
+extern bool pv_is_native_vcpu_is_preempted(void);
unsigned native_patch(u8 type, u16 clobbers, void *ibuf,
unsigned long addr, unsigned len)
@@ -68,9 +70,19 @@ unsigned native_patch(u8 type, u16 clobbers, void *ibuf,
end = end_pv_lock_ops_queued_spin_unlock;
goto patch_site;
}
+ goto patch_default;
+
+ case PARAVIRT_PATCH(pv_lock_ops.vcpu_is_preempted):
+ if (pv_is_native_vcpu_is_preempted()) {
+ start = start_pv_lock_ops_vcpu_is_preempted;
+ end = end_pv_lock_ops_vcpu_is_preempted;
+ goto patch_site;
+ }
+ goto patch_default;
#endif
default:
+patch_default:
ret = paravirt_patch_default(type, clobbers, ibuf, addr, len);
break;
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 04c5d96b1d67..59c2d6f1b131 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -2071,6 +2071,8 @@ static void record_steal_time(struct kvm_vcpu *vcpu)
&vcpu->arch.st.steal, sizeof(struct kvm_steal_time))))
return;
+ vcpu->arch.st.steal.preempted = 0;
+
if (vcpu->arch.st.steal.version & 1)
vcpu->arch.st.steal.version += 1; /* first time write, random junk */
@@ -2826,8 +2828,22 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
kvm_make_request(KVM_REQ_STEAL_UPDATE, vcpu);
}
+static void kvm_steal_time_set_preempted(struct kvm_vcpu *vcpu)
+{
+ if (!(vcpu->arch.st.msr_val & KVM_MSR_ENABLED))
+ return;
+
+ vcpu->arch.st.steal.preempted = 1;
+
+ kvm_write_guest_offset_cached(vcpu->kvm, &vcpu->arch.st.stime,
+ &vcpu->arch.st.steal.preempted,
+ offsetof(struct kvm_steal_time, preempted),
+ sizeof(vcpu->arch.st.steal.preempted));
+}
+
void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
{
+ kvm_steal_time_set_preempted(vcpu);
kvm_x86_ops->vcpu_put(vcpu);
kvm_put_guest_fpu(vcpu);
vcpu->arch.last_host_tsc = rdtsc();
diff --git a/arch/x86/um/asm/processor.h b/arch/x86/um/asm/processor.h
index 233ee09c1ce8..c77db2288982 100644
--- a/arch/x86/um/asm/processor.h
+++ b/arch/x86/um/asm/processor.h
@@ -26,7 +26,6 @@ static inline void rep_nop(void)
}
#define cpu_relax() rep_nop()
-#define cpu_relax_lowlatency() cpu_relax()
#define task_pt_regs(t) (&(t)->thread.regs)
diff --git a/arch/x86/xen/spinlock.c b/arch/x86/xen/spinlock.c
index 3d6e0064cbfc..e8a9ea7d7a21 100644
--- a/arch/x86/xen/spinlock.c
+++ b/arch/x86/xen/spinlock.c
@@ -114,6 +114,7 @@ void xen_uninit_lock_cpu(int cpu)
per_cpu(irq_name, cpu) = NULL;
}
+PV_CALLEE_SAVE_REGS_THUNK(xen_vcpu_stolen);
/*
* Our init of PV spinlocks is split in two init functions due to us
@@ -137,6 +138,7 @@ void __init xen_init_spinlocks(void)
pv_lock_ops.queued_spin_unlock = PV_CALLEE_SAVE(__pv_queued_spin_unlock);
pv_lock_ops.wait = xen_qlock_wait;
pv_lock_ops.kick = xen_qlock_kick;
+ pv_lock_ops.vcpu_is_preempted = PV_CALLEE_SAVE(xen_vcpu_stolen);
}
/*
generated by cgit v1.2.3 (git 2.39.0) at 2024-12-16 12:01:48 +0300