From a5f56ba3b4ec8d2ad80da4c447d47e37e2b504fb Mon Sep 17 00:00:00 2001 From: Firo Yang Date: Thu, 23 Apr 2015 11:07:40 +0100 Subject: ARM: KVM: Remove pointless void pointer cast No need to cast the void pointer returned by kmalloc() in arch/arm/kvm/mmu.c::kvm_alloc_stage2_pgd(). Signed-off-by: Firo Yang Acked-by: Paolo Bonzini Signed-off-by: Marc Zyngier --- arch/arm/kvm/mmu.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'arch/arm') diff --git a/arch/arm/kvm/mmu.c b/arch/arm/kvm/mmu.c index 1d5accbd3dcf..ce0bce472455 100644 --- a/arch/arm/kvm/mmu.c +++ b/arch/arm/kvm/mmu.c @@ -691,8 +691,8 @@ int kvm_alloc_stage2_pgd(struct kvm *kvm) * work. This is not used by the hardware and we have no * alignment requirement for this allocation. */ - pgd = (pgd_t *)kmalloc(PTRS_PER_S2_PGD * sizeof(pgd_t), - GFP_KERNEL | __GFP_ZERO); + pgd = kmalloc(PTRS_PER_S2_PGD * sizeof(pgd_t), + GFP_KERNEL | __GFP_ZERO); if (!pgd) { kvm_free_hwpgd(hwpgd); -- cgit v1.2.3 From 85e84ba31039595995dae80b277378213602891b Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Mon, 16 Mar 2015 10:59:43 +0000 Subject: arm: KVM: force execution of HCPTR access on VM exit On VM entry, we disable access to the VFP registers in order to perform a lazy save/restore of these registers. On VM exit, we restore access, test if we did enable them before, and save/restore the guest/host registers if necessary. In this sequence, the FPEXC register is always accessed, irrespective of the trapping configuration. If the guest didn't touch the VFP registers, then the HCPTR access has now enabled such access, but we're missing a barrier to ensure architectural execution of the new HCPTR configuration. If the HCPTR access has been delayed/reordered, the subsequent access to FPEXC will cause a trap, which we aren't prepared to handle at all. The same condition exists when trapping to enable VFP for the guest. The fix is to introduce a barrier after enabling VFP access. In the vmexit case, it can be relaxed to only takes place if the guest hasn't accessed its view of the VFP registers, making the access to FPEXC safe. The set_hcptr macro is modified to deal with both vmenter/vmexit and vmtrap operations, and now takes an optional label that is branched to when the guest hasn't touched the VFP registers. Reported-by: Vikram Sethi Cc: stable@kernel.org # v3.9+ Signed-off-by: Marc Zyngier --- arch/arm/kvm/interrupts.S | 10 ++++------ arch/arm/kvm/interrupts_head.S | 20 ++++++++++++++++++-- 2 files changed, 22 insertions(+), 8 deletions(-) (limited to 'arch/arm') diff --git a/arch/arm/kvm/interrupts.S b/arch/arm/kvm/interrupts.S index 79caf79b304a..f7db3a5d80e3 100644 --- a/arch/arm/kvm/interrupts.S +++ b/arch/arm/kvm/interrupts.S @@ -170,13 +170,9 @@ __kvm_vcpu_return: @ Don't trap coprocessor accesses for host kernel set_hstr vmexit set_hdcr vmexit - set_hcptr vmexit, (HCPTR_TTA | HCPTR_TCP(10) | HCPTR_TCP(11)) + set_hcptr vmexit, (HCPTR_TTA | HCPTR_TCP(10) | HCPTR_TCP(11)), after_vfp_restore #ifdef CONFIG_VFPv3 - @ Save floating point registers we if let guest use them. - tst r2, #(HCPTR_TCP(10) | HCPTR_TCP(11)) - bne after_vfp_restore - @ Switch VFP/NEON hardware state to the host's add r7, vcpu, #VCPU_VFP_GUEST store_vfp_state r7 @@ -188,6 +184,8 @@ after_vfp_restore: @ Restore FPEXC_EN which we clobbered on entry pop {r2} VFPFMXR FPEXC, r2 +#else +after_vfp_restore: #endif @ Reset Hyp-role @@ -483,7 +481,7 @@ switch_to_guest_vfp: push {r3-r7} @ NEON/VFP used. Turn on VFP access. - set_hcptr vmexit, (HCPTR_TCP(10) | HCPTR_TCP(11)) + set_hcptr vmtrap, (HCPTR_TCP(10) | HCPTR_TCP(11)) @ Switch VFP/NEON hardware state to the guest's add r7, r0, #VCPU_VFP_HOST diff --git a/arch/arm/kvm/interrupts_head.S b/arch/arm/kvm/interrupts_head.S index 35e4a3a0c476..48efe2ee452c 100644 --- a/arch/arm/kvm/interrupts_head.S +++ b/arch/arm/kvm/interrupts_head.S @@ -591,8 +591,13 @@ ARM_BE8(rev r6, r6 ) .endm /* Configures the HCPTR (Hyp Coprocessor Trap Register) on entry/return - * (hardware reset value is 0). Keep previous value in r2. */ -.macro set_hcptr operation, mask + * (hardware reset value is 0). Keep previous value in r2. + * An ISB is emited on vmexit/vmtrap, but executed on vmexit only if + * VFP wasn't already enabled (always executed on vmtrap). + * If a label is specified with vmexit, it is branched to if VFP wasn't + * enabled. + */ +.macro set_hcptr operation, mask, label = none mrc p15, 4, r2, c1, c1, 2 ldr r3, =\mask .if \operation == vmentry @@ -601,6 +606,17 @@ ARM_BE8(rev r6, r6 ) bic r3, r2, r3 @ Don't trap defined coproc-accesses .endif mcr p15, 4, r3, c1, c1, 2 + .if \operation != vmentry + .if \operation == vmexit + tst r2, #(HCPTR_TCP(10) | HCPTR_TCP(11)) + beq 1f + .endif + isb + .if \label != none + b \label + .endif +1: + .endif .endm /* Configures the HDCR (Hyp Debug Configuration Register) on entry/return -- cgit v1.2.3 From ea2c6d9745c6698d9f820bc230aa1a80d9e908ac Mon Sep 17 00:00:00 2001 From: Tiejun Chen Date: Mon, 4 May 2015 10:48:49 +0800 Subject: kvm: remove one useless check extension We already check KVM_CAP_IRQFD in generic once enable CONFIG_HAVE_KVM_IRQFD, kvm_vm_ioctl_check_extension_generic() | + switch (arg) { + ... + #ifdef CONFIG_HAVE_KVM_IRQFD + case KVM_CAP_IRQFD: + #endif + ... + return 1; + ... + } | + kvm_vm_ioctl_check_extension() So its not necessary to check this in arch again, and also fix one typo, s/emlation/emulation. Signed-off-by: Tiejun Chen Acked-by: Paolo Bonzini Signed-off-by: Christoffer Dall --- arch/arm/kvm/arm.c | 1 - 1 file changed, 1 deletion(-) (limited to 'arch/arm') diff --git a/arch/arm/kvm/arm.c b/arch/arm/kvm/arm.c index e41cb11f71b2..7e8233015ad8 100644 --- a/arch/arm/kvm/arm.c +++ b/arch/arm/kvm/arm.c @@ -171,7 +171,6 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) int r; switch (ext) { case KVM_CAP_IRQCHIP: - case KVM_CAP_IRQFD: case KVM_CAP_IOEVENTFD: case KVM_CAP_DEVICE_CTRL: case KVM_CAP_USER_MEMORY: -- cgit v1.2.3 From 1b3d546daf85ed2bc9966e12cee3e6435fb65eca Mon Sep 17 00:00:00 2001 From: Christoffer Dall Date: Thu, 28 May 2015 19:49:10 +0100 Subject: arm/arm64: KVM: Properly account for guest CPU time Until now we have been calling kvm_guest_exit after re-enabling interrupts when we come back from the guest, but this has the unfortunate effect that CPU time accounting done in the context of timer interrupts occurring while the guest is running doesn't properly notice that the time since the last tick was spent in the guest. Inspired by the comment in the x86 code, move the kvm_guest_exit() call below the local_irq_enable() call and change __kvm_guest_exit() to kvm_guest_exit(), because we are now calling this function with interrupts enabled. We have to now explicitly disable preemption and not enable preemption before we've called kvm_guest_exit(), since otherwise we could be preempted and everything happening before we eventually get scheduled again would be accounted for as guest time. At the same time, move the trace_kvm_exit() call outside of the atomic section, since there is no reason for us to do that with interrupts disabled. Signed-off-by: Christoffer Dall Signed-off-by: Marc Zyngier --- arch/arm/kvm/arm.c | 21 +++++++++++++++++---- 1 file changed, 17 insertions(+), 4 deletions(-) (limited to 'arch/arm') diff --git a/arch/arm/kvm/arm.c b/arch/arm/kvm/arm.c index 7e8233015ad8..bc738d2b8392 100644 --- a/arch/arm/kvm/arm.c +++ b/arch/arm/kvm/arm.c @@ -531,6 +531,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run) kvm_vgic_flush_hwstate(vcpu); kvm_timer_flush_hwstate(vcpu); + preempt_disable(); local_irq_disable(); /* @@ -543,6 +544,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run) if (ret <= 0 || need_new_vmid_gen(vcpu->kvm)) { local_irq_enable(); + preempt_enable(); kvm_timer_sync_hwstate(vcpu); kvm_vgic_sync_hwstate(vcpu); continue; @@ -558,8 +560,10 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run) ret = kvm_call_hyp(__kvm_vcpu_run, vcpu); vcpu->mode = OUTSIDE_GUEST_MODE; - __kvm_guest_exit(); - trace_kvm_exit(kvm_vcpu_trap_get_class(vcpu), *vcpu_pc(vcpu)); + /* + * Back from guest + *************************************************************/ + /* * We may have taken a host interrupt in HYP mode (ie * while executing the guest). This interrupt is still @@ -573,8 +577,17 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run) local_irq_enable(); /* - * Back from guest - *************************************************************/ + * We do local_irq_enable() before calling kvm_guest_exit() so + * that if a timer interrupt hits while running the guest we + * account that tick as being spent in the guest. We enable + * preemption after calling kvm_guest_exit() so that if we get + * preempted we make sure ticks after that is not counted as + * guest time. + */ + kvm_guest_exit(); + trace_kvm_exit(kvm_vcpu_trap_get_class(vcpu), *vcpu_pc(vcpu)); + preempt_enable(); + kvm_timer_sync_hwstate(vcpu); kvm_vgic_sync_hwstate(vcpu); -- cgit v1.2.3 From 8889583c037c776041b08d7109acc2450e560036 Mon Sep 17 00:00:00 2001 From: Kim Phillips Date: Fri, 5 Jun 2015 16:21:49 +0100 Subject: KVM: arm/arm64: Enable the KVM-VFIO device The KVM-VFIO device is used by the QEMU VFIO device. It is used to record the list of in-use VFIO groups so that KVM can manipulate them. Signed-off-by: Kim Phillips Signed-off-by: Eric Auger Signed-off-by: Marc Zyngier --- arch/arm/kvm/Kconfig | 1 + arch/arm/kvm/Makefile | 2 +- 2 files changed, 2 insertions(+), 1 deletion(-) (limited to 'arch/arm') diff --git a/arch/arm/kvm/Kconfig b/arch/arm/kvm/Kconfig index f1f79d104309..bfb915d05665 100644 --- a/arch/arm/kvm/Kconfig +++ b/arch/arm/kvm/Kconfig @@ -28,6 +28,7 @@ config KVM select KVM_GENERIC_DIRTYLOG_READ_PROTECT select SRCU select MMU_NOTIFIER + select KVM_VFIO select HAVE_KVM_EVENTFD select HAVE_KVM_IRQFD depends on ARM_VIRT_EXT && ARM_LPAE && ARM_ARCH_TIMER diff --git a/arch/arm/kvm/Makefile b/arch/arm/kvm/Makefile index 139e46c08b6e..c5eef02c52ba 100644 --- a/arch/arm/kvm/Makefile +++ b/arch/arm/kvm/Makefile @@ -15,7 +15,7 @@ AFLAGS_init.o := -Wa,-march=armv7-a$(plus_virt) AFLAGS_interrupts.o := -Wa,-march=armv7-a$(plus_virt) KVM := ../../../virt/kvm -kvm-arm-y = $(KVM)/kvm_main.o $(KVM)/coalesced_mmio.o $(KVM)/eventfd.o +kvm-arm-y = $(KVM)/kvm_main.o $(KVM)/coalesced_mmio.o $(KVM)/eventfd.o $(KVM)/vfio.o obj-y += kvm-arm.o init.o interrupts.o obj-y += arm.o handle_exit.o guest.o mmu.o emulate.o reset.o -- cgit v1.2.3 From e2d997366dc5b6c9d14035867f73957f93e7578c Mon Sep 17 00:00:00 2001 From: Lorenzo Pieralisi Date: Wed, 10 Jun 2015 15:19:24 +0100 Subject: ARM: kvm: psci: fix handling of unimplemented functions According to the PSCI specification and the SMC/HVC calling convention, PSCI function_ids that are not implemented must return NOT_SUPPORTED as return value. Current KVM implementation takes an unhandled PSCI function_id as an error and injects an undefined instruction into the guest if PSCI implementation is called with a function_id that is not handled by the resident PSCI version (ie it is not implemented), which is not the behaviour expected by a guest when calling a PSCI function_id that is not implemented. This patch fixes this issue by returning NOT_SUPPORTED whenever the kvm PSCI call is executed for a function_id that is not implemented by the PSCI kvm layer. Cc: # 3.18+ Cc: Christoffer Dall Acked-by: Sudeep Holla Signed-off-by: Lorenzo Pieralisi Signed-off-by: Marc Zyngier --- arch/arm/kvm/psci.c | 16 +++------------- 1 file changed, 3 insertions(+), 13 deletions(-) (limited to 'arch/arm') diff --git a/arch/arm/kvm/psci.c b/arch/arm/kvm/psci.c index 02fa8eff6ae1..531e922486b2 100644 --- a/arch/arm/kvm/psci.c +++ b/arch/arm/kvm/psci.c @@ -230,10 +230,6 @@ static int kvm_psci_0_2_call(struct kvm_vcpu *vcpu) case PSCI_0_2_FN64_AFFINITY_INFO: val = kvm_psci_vcpu_affinity_info(vcpu); break; - case PSCI_0_2_FN_MIGRATE: - case PSCI_0_2_FN64_MIGRATE: - val = PSCI_RET_NOT_SUPPORTED; - break; case PSCI_0_2_FN_MIGRATE_INFO_TYPE: /* * Trusted OS is MP hence does not require migration @@ -242,10 +238,6 @@ static int kvm_psci_0_2_call(struct kvm_vcpu *vcpu) */ val = PSCI_0_2_TOS_MP; break; - case PSCI_0_2_FN_MIGRATE_INFO_UP_CPU: - case PSCI_0_2_FN64_MIGRATE_INFO_UP_CPU: - val = PSCI_RET_NOT_SUPPORTED; - break; case PSCI_0_2_FN_SYSTEM_OFF: kvm_psci_system_off(vcpu); /* @@ -271,7 +263,8 @@ static int kvm_psci_0_2_call(struct kvm_vcpu *vcpu) ret = 0; break; default: - return -EINVAL; + val = PSCI_RET_NOT_SUPPORTED; + break; } *vcpu_reg(vcpu, 0) = val; @@ -291,12 +284,9 @@ static int kvm_psci_0_1_call(struct kvm_vcpu *vcpu) case KVM_PSCI_FN_CPU_ON: val = kvm_psci_vcpu_on(vcpu); break; - case KVM_PSCI_FN_CPU_SUSPEND: - case KVM_PSCI_FN_MIGRATE: + default: val = PSCI_RET_NOT_SUPPORTED; break; - default: - return -EINVAL; } *vcpu_reg(vcpu, 0) = val; -- cgit v1.2.3 From 4642019dc4457486223e1fb75a6a4cba6e0e903a Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Thu, 11 Jun 2015 18:50:17 +0100 Subject: arm/arm64: KVM: vgic: Do not save GICH_HCR / ICH_HCR_EL2 The GIC Hypervisor Configuration Register is used to enable the delivery of virtual interupts to a guest, as well as to define in which conditions maintenance interrupts are delivered to the host. This register doesn't contain any information that we need to read back (the EOIcount is utterly useless for us). So let's save ourselves some cycles, and not save it before writing zero to it. Signed-off-by: Marc Zyngier --- arch/arm/kvm/interrupts_head.S | 3 --- 1 file changed, 3 deletions(-) (limited to 'arch/arm') diff --git a/arch/arm/kvm/interrupts_head.S b/arch/arm/kvm/interrupts_head.S index 48efe2ee452c..702740d37465 100644 --- a/arch/arm/kvm/interrupts_head.S +++ b/arch/arm/kvm/interrupts_head.S @@ -412,7 +412,6 @@ vcpu .req r0 @ vcpu pointer always in r0 add r11, vcpu, #VCPU_VGIC_CPU /* Save all interesting registers */ - ldr r3, [r2, #GICH_HCR] ldr r4, [r2, #GICH_VMCR] ldr r5, [r2, #GICH_MISR] ldr r6, [r2, #GICH_EISR0] @@ -420,7 +419,6 @@ vcpu .req r0 @ vcpu pointer always in r0 ldr r8, [r2, #GICH_ELRSR0] ldr r9, [r2, #GICH_ELRSR1] ldr r10, [r2, #GICH_APR] -ARM_BE8(rev r3, r3 ) ARM_BE8(rev r4, r4 ) ARM_BE8(rev r5, r5 ) ARM_BE8(rev r6, r6 ) @@ -429,7 +427,6 @@ ARM_BE8(rev r8, r8 ) ARM_BE8(rev r9, r9 ) ARM_BE8(rev r10, r10 ) - str r3, [r11, #VGIC_V2_CPU_HCR] str r4, [r11, #VGIC_V2_CPU_VMCR] str r5, [r11, #VGIC_V2_CPU_MISR] #ifdef CONFIG_CPU_ENDIAN_BE8 -- cgit v1.2.3