From d241aac798eb042e605f78c31a4122e583b2cd13 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Fri, 2 Aug 2013 11:41:13 +0100 Subject: [PATCH 1/3] arm64: KVM: Yield CPU when vcpu executes a WFE On an (even slightly) oversubscribed system, spinlocks are quickly becoming a bottleneck, as some vcpus are spinning, waiting for a lock to be released, while the vcpu holding the lock may not be running at all. The solution is to trap blocking WFEs and tell KVM that we're now spinning. This ensures that other vpus will get a scheduling boost, allowing the lock to be released more quickly. Also, using CONFIG_HAVE_KVM_CPU_RELAX_INTERCEPT slightly improves the performance when the VM is severely overcommited. Acked-by: Christoffer Dall Signed-off-by: Marc Zyngier --- arch/arm64/include/asm/kvm_arm.h | 8 ++++++-- arch/arm64/kvm/Kconfig | 1 + arch/arm64/kvm/handle_exit.c | 18 +++++++++++++----- 3 files changed, 20 insertions(+), 7 deletions(-) diff --git a/arch/arm64/include/asm/kvm_arm.h b/arch/arm64/include/asm/kvm_arm.h index a5f28e2720c7..c98ef4771c73 100644 --- a/arch/arm64/include/asm/kvm_arm.h +++ b/arch/arm64/include/asm/kvm_arm.h @@ -63,6 +63,7 @@ * TAC: Trap ACTLR * TSC: Trap SMC * TSW: Trap cache operations by set/way + * TWE: Trap WFE * TWI: Trap WFI * TIDCP: Trap L2CTLR/L2ECTLR * BSU_IS: Upgrade barriers to the inner shareable domain @@ -72,8 +73,9 @@ * FMO: Override CPSR.F and enable signaling with VF * SWIO: Turn set/way invalidates into set/way clean+invalidate */ -#define HCR_GUEST_FLAGS (HCR_TSC | HCR_TSW | HCR_TWI | HCR_VM | HCR_BSU_IS | \ - HCR_FB | HCR_TAC | HCR_AMO | HCR_IMO | HCR_FMO | \ +#define HCR_GUEST_FLAGS (HCR_TSC | HCR_TSW | HCR_TWE | HCR_TWI | HCR_VM | \ + HCR_BSU_IS | HCR_FB | HCR_TAC | \ + HCR_AMO | HCR_IMO | HCR_FMO | \ HCR_SWIO | HCR_TIDCP | HCR_RW) #define HCR_VIRT_EXCP_MASK (HCR_VA | HCR_VI | HCR_VF) @@ -242,4 +244,6 @@ #define ESR_EL2_EC_xABT_xFSR_EXTABT 0x10 +#define ESR_EL2_EC_WFI_ISS_WFE (1 << 0) + #endif /* __ARM64_KVM_ARM_H__ */ diff --git a/arch/arm64/kvm/Kconfig b/arch/arm64/kvm/Kconfig index 21e90820bd23..4480ab339a00 100644 --- a/arch/arm64/kvm/Kconfig +++ b/arch/arm64/kvm/Kconfig @@ -21,6 +21,7 @@ config KVM select MMU_NOTIFIER select PREEMPT_NOTIFIERS select ANON_INODES + select HAVE_KVM_CPU_RELAX_INTERCEPT select KVM_MMIO select KVM_ARM_HOST select KVM_ARM_VGIC diff --git a/arch/arm64/kvm/handle_exit.c b/arch/arm64/kvm/handle_exit.c index 9beaca033437..8da56067c304 100644 --- a/arch/arm64/kvm/handle_exit.c +++ b/arch/arm64/kvm/handle_exit.c @@ -47,21 +47,29 @@ static int handle_smc(struct kvm_vcpu *vcpu, struct kvm_run *run) } /** - * kvm_handle_wfi - handle a wait-for-interrupts instruction executed by a guest + * kvm_handle_wfx - handle a wait-for-interrupts or wait-for-event + * instruction executed by a guest + * * @vcpu: the vcpu pointer * - * Simply call kvm_vcpu_block(), which will halt execution of + * WFE: Yield the CPU and come back to this vcpu when the scheduler + * decides to. + * WFI: Simply call kvm_vcpu_block(), which will halt execution of * world-switches and schedule other host processes until there is an * incoming IRQ or FIQ to the VM. */ -static int kvm_handle_wfi(struct kvm_vcpu *vcpu, struct kvm_run *run) +static int kvm_handle_wfx(struct kvm_vcpu *vcpu, struct kvm_run *run) { - kvm_vcpu_block(vcpu); + if (kvm_vcpu_get_hsr(vcpu) & ESR_EL2_EC_WFI_ISS_WFE) + kvm_vcpu_on_spin(vcpu); + else + kvm_vcpu_block(vcpu); + return 1; } static exit_handle_fn arm_exit_handlers[] = { - [ESR_EL2_EC_WFI] = kvm_handle_wfi, + [ESR_EL2_EC_WFI] = kvm_handle_wfx, [ESR_EL2_EC_CP15_32] = kvm_handle_cp15_32, [ESR_EL2_EC_CP15_64] = kvm_handle_cp15_64, [ESR_EL2_EC_CP14_MR] = kvm_handle_cp14_access, From 6d89d2d9b5bac9dbe40ee106ceda9307b6265234 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Tue, 12 Feb 2013 12:40:22 +0000 Subject: [PATCH 2/3] arm/arm64: KVM: MMIO support for BE guest Do the necessary byteswap when host and guest have different views of the universe. Actually, the only case we need to take care of is when the guest is BE. All the other cases are naturally handled. Also be careful about endianness when the data is being memcopy-ed from/to the run buffer. Acked-by: Christoffer Dall Signed-off-by: Marc Zyngier --- arch/arm/include/asm/kvm_emulate.h | 41 +++++++++++++ arch/arm/kvm/mmio.c | 86 ++++++++++++++++++++++++---- arch/arm64/include/asm/kvm_emulate.h | 48 ++++++++++++++++ 3 files changed, 164 insertions(+), 11 deletions(-) diff --git a/arch/arm/include/asm/kvm_emulate.h b/arch/arm/include/asm/kvm_emulate.h index a464e8d7b6c5..8a6be05a46d7 100644 --- a/arch/arm/include/asm/kvm_emulate.h +++ b/arch/arm/include/asm/kvm_emulate.h @@ -157,4 +157,45 @@ static inline u32 kvm_vcpu_hvc_get_imm(struct kvm_vcpu *vcpu) return kvm_vcpu_get_hsr(vcpu) & HSR_HVC_IMM_MASK; } +static inline bool kvm_vcpu_is_be(struct kvm_vcpu *vcpu) +{ + return !!(*vcpu_cpsr(vcpu) & PSR_E_BIT); +} + +static inline unsigned long vcpu_data_guest_to_host(struct kvm_vcpu *vcpu, + unsigned long data, + unsigned int len) +{ + if (kvm_vcpu_is_be(vcpu)) { + switch (len) { + case 1: + return data & 0xff; + case 2: + return be16_to_cpu(data & 0xffff); + default: + return be32_to_cpu(data); + } + } + + return data; /* Leave LE untouched */ +} + +static inline unsigned long vcpu_data_host_to_guest(struct kvm_vcpu *vcpu, + unsigned long data, + unsigned int len) +{ + if (kvm_vcpu_is_be(vcpu)) { + switch (len) { + case 1: + return data & 0xff; + case 2: + return cpu_to_be16(data & 0xffff); + default: + return cpu_to_be32(data); + } + } + + return data; /* Leave LE untouched */ +} + #endif /* __ARM_KVM_EMULATE_H__ */ diff --git a/arch/arm/kvm/mmio.c b/arch/arm/kvm/mmio.c index 0c25d9487d53..4cb5a93182e9 100644 --- a/arch/arm/kvm/mmio.c +++ b/arch/arm/kvm/mmio.c @@ -23,6 +23,68 @@ #include "trace.h" +static void mmio_write_buf(char *buf, unsigned int len, unsigned long data) +{ + void *datap = NULL; + union { + u8 byte; + u16 hword; + u32 word; + u64 dword; + } tmp; + + switch (len) { + case 1: + tmp.byte = data; + datap = &tmp.byte; + break; + case 2: + tmp.hword = data; + datap = &tmp.hword; + break; + case 4: + tmp.word = data; + datap = &tmp.word; + break; + case 8: + tmp.dword = data; + datap = &tmp.dword; + break; + } + + memcpy(buf, datap, len); +} + +static unsigned long mmio_read_buf(char *buf, unsigned int len) +{ + unsigned long data = 0; + union { + u16 hword; + u32 word; + u64 dword; + } tmp; + + switch (len) { + case 1: + data = buf[0]; + break; + case 2: + memcpy(&tmp.hword, buf, len); + data = tmp.hword; + break; + case 4: + memcpy(&tmp.word, buf, len); + data = tmp.word; + break; + case 8: + memcpy(&tmp.dword, buf, len); + data = tmp.dword; + break; + } + + return data; +} + /** * kvm_handle_mmio_return -- Handle MMIO loads after user space emulation * @vcpu: The VCPU pointer @@ -33,28 +95,27 @@ */ int kvm_handle_mmio_return(struct kvm_vcpu *vcpu, struct kvm_run *run) { - unsigned long *dest; + unsigned long data; unsigned int len; int mask; if (!run->mmio.is_write) { - dest = vcpu_reg(vcpu, vcpu->arch.mmio_decode.rt); - *dest = 0; - len = run->mmio.len; if (len > sizeof(unsigned long)) return -EINVAL; - memcpy(dest, run->mmio.data, len); - - trace_kvm_mmio(KVM_TRACE_MMIO_READ, len, run->mmio.phys_addr, - *((u64 *)run->mmio.data)); + data = mmio_read_buf(run->mmio.data, len); if (vcpu->arch.mmio_decode.sign_extend && len < sizeof(unsigned long)) { mask = 1U << ((len * 8) - 1); - *dest = (*dest ^ mask) - mask; + data = (data ^ mask) - mask; } + + trace_kvm_mmio(KVM_TRACE_MMIO_READ, len, run->mmio.phys_addr, + data); + data = vcpu_data_host_to_guest(vcpu, data, len); + *vcpu_reg(vcpu, vcpu->arch.mmio_decode.rt) = data; } return 0; @@ -105,6 +166,7 @@ int io_mem_abort(struct kvm_vcpu *vcpu, struct kvm_run *run, phys_addr_t fault_ipa) { struct kvm_exit_mmio mmio; + unsigned long data; unsigned long rt; int ret; @@ -125,13 +187,15 @@ int io_mem_abort(struct kvm_vcpu *vcpu, struct kvm_run *run, } rt = vcpu->arch.mmio_decode.rt; + data = vcpu_data_guest_to_host(vcpu, *vcpu_reg(vcpu, rt), mmio.len); + trace_kvm_mmio((mmio.is_write) ? KVM_TRACE_MMIO_WRITE : KVM_TRACE_MMIO_READ_UNSATISFIED, mmio.len, fault_ipa, - (mmio.is_write) ? *vcpu_reg(vcpu, rt) : 0); + (mmio.is_write) ? data : 0); if (mmio.is_write) - memcpy(mmio.data, vcpu_reg(vcpu, rt), mmio.len); + mmio_write_buf(mmio.data, mmio.len, data); if (vgic_handle_mmio(vcpu, run, &mmio)) return 1; diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h index eec073875218..b016577e37a4 100644 --- a/arch/arm64/include/asm/kvm_emulate.h +++ b/arch/arm64/include/asm/kvm_emulate.h @@ -177,4 +177,52 @@ static inline u8 kvm_vcpu_trap_get_fault(const struct kvm_vcpu *vcpu) return kvm_vcpu_get_hsr(vcpu) & ESR_EL2_FSC_TYPE; } +static inline bool kvm_vcpu_is_be(struct kvm_vcpu *vcpu) +{ + if (vcpu_mode_is_32bit(vcpu)) + return !!(*vcpu_cpsr(vcpu) & COMPAT_PSR_E_BIT); + + return !!(vcpu_sys_reg(vcpu, SCTLR_EL1) & (1 << 25)); +} + +static inline unsigned long vcpu_data_guest_to_host(struct kvm_vcpu *vcpu, + unsigned long data, + unsigned int len) +{ + if (kvm_vcpu_is_be(vcpu)) { + switch (len) { + case 1: + return data & 0xff; + case 2: + return be16_to_cpu(data & 0xffff); + case 4: + return be32_to_cpu(data & 0xffffffff); + default: + return be64_to_cpu(data); + } + } + + return data; /* Leave LE untouched */ +} + +static inline unsigned long vcpu_data_host_to_guest(struct kvm_vcpu *vcpu, + unsigned long data, + unsigned int len) +{ + if (kvm_vcpu_is_be(vcpu)) { + switch (len) { + case 1: + return data & 0xff; + case 2: + return cpu_to_be16(data & 0xffff); + case 4: + return cpu_to_be32(data & 0xffffffff); + default: + return cpu_to_be64(data); + } + } + + return data; /* Leave LE untouched */ +} + #endif /* __ARM64_KVM_EMULATE_H__ */ From ce94fe93d566bf381c6ecbd45010d36c5f04d692 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Tue, 5 Nov 2013 14:12:15 +0000 Subject: [PATCH 3/3] arm/arm64: KVM: PSCI: propagate caller endianness to the incoming vcpu When booting a vcpu using PSCI, make sure we start it with the endianness of the caller. Otherwise, secondaries can be pretty unhappy to execute a BE kernel in LE mode... This conforms to PSCI spec Rev B, 5.13.3. Acked-by: Christoffer Dall Signed-off-by: Marc Zyngier --- arch/arm/include/asm/kvm_emulate.h | 5 +++++ arch/arm/kvm/psci.c | 4 ++++ arch/arm64/include/asm/kvm_emulate.h | 8 ++++++++ 3 files changed, 17 insertions(+) diff --git a/arch/arm/include/asm/kvm_emulate.h b/arch/arm/include/asm/kvm_emulate.h index 8a6be05a46d7..e844b335e33a 100644 --- a/arch/arm/include/asm/kvm_emulate.h +++ b/arch/arm/include/asm/kvm_emulate.h @@ -157,6 +157,11 @@ static inline u32 kvm_vcpu_hvc_get_imm(struct kvm_vcpu *vcpu) return kvm_vcpu_get_hsr(vcpu) & HSR_HVC_IMM_MASK; } +static inline void kvm_vcpu_set_be(struct kvm_vcpu *vcpu) +{ + *vcpu_cpsr(vcpu) |= PSR_E_BIT; +} + static inline bool kvm_vcpu_is_be(struct kvm_vcpu *vcpu) { return !!(*vcpu_cpsr(vcpu) & PSR_E_BIT); diff --git a/arch/arm/kvm/psci.c b/arch/arm/kvm/psci.c index 86a693a02ba3..ae0e06b6a492 100644 --- a/arch/arm/kvm/psci.c +++ b/arch/arm/kvm/psci.c @@ -62,6 +62,10 @@ static unsigned long kvm_psci_vcpu_on(struct kvm_vcpu *source_vcpu) vcpu_set_thumb(vcpu); } + /* Propagate caller endianness */ + if (kvm_vcpu_is_be(source_vcpu)) + kvm_vcpu_set_be(vcpu); + *vcpu_pc(vcpu) = target_pc; vcpu->arch.pause = false; smp_mb(); /* Make sure the above is visible */ diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h index b016577e37a4..db805092698c 100644 --- a/arch/arm64/include/asm/kvm_emulate.h +++ b/arch/arm64/include/asm/kvm_emulate.h @@ -177,6 +177,14 @@ static inline u8 kvm_vcpu_trap_get_fault(const struct kvm_vcpu *vcpu) return kvm_vcpu_get_hsr(vcpu) & ESR_EL2_FSC_TYPE; } +static inline void kvm_vcpu_set_be(struct kvm_vcpu *vcpu) +{ + if (vcpu_mode_is_32bit(vcpu)) + *vcpu_cpsr(vcpu) |= COMPAT_PSR_E_BIT; + else + vcpu_sys_reg(vcpu, SCTLR_EL1) |= (1 << 25); +} + static inline bool kvm_vcpu_is_be(struct kvm_vcpu *vcpu) { if (vcpu_mode_is_32bit(vcpu))