From a8b48a4dccea77e29462e59f1dbf0d5aa1ff167c Mon Sep 17 00:00:00 2001 From: Paul Mackerras Date: Wed, 7 Mar 2018 22:17:20 +1100 Subject: KVM: PPC: Book3S HV: Fix trap number return from __kvmppc_vcore_entry This fixes a bug where the trap number that is returned by __kvmppc_vcore_entry gets corrupted. The effect of the corruption is that IPIs get ignored on POWER9 systems when the IPI is sent via a doorbell interrupt to a CPU which is executing in a KVM guest. The effect of the IPI being ignored is often that another CPU locks up inside smp_call_function_many() (and if that CPU is holding a spinlock, other CPUs then lock up inside raw_spin_lock()). The trap number is currently held in register r12 for most of the assembly-language part of the guest exit path. In that path, we call kvmppc_subcore_exit_guest(), which is a C function, without restoring r12 afterwards. Depending on the kernel config and the compiler, it may modify r12 or it may not, so some config/compiler combinations see the bug and others don't. To fix this, we arrange for the trap number to be stored on the stack from the 'guest_bypass:' label until the end of the function, then the trap number is loaded and returned in r12 as before. Cc: stable@vger.kernel.org # v4.8+ Fixes: fd7bacbca47a ("KVM: PPC: Book3S HV: Fix TB corruption in guest exit path on HMI interrupt") Signed-off-by: Paul Mackerras --- arch/powerpc/kvm/book3s_hv_rmhandlers.S | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'arch') diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S index f31f357b8c5a..d33264697a31 100644 --- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S +++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S @@ -320,7 +320,6 @@ kvm_novcpu_exit: stw r12, STACK_SLOT_TRAP(r1) bl kvmhv_commence_exit nop - lwz r12, STACK_SLOT_TRAP(r1) b kvmhv_switch_to_host /* @@ -1220,6 +1219,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300) secondary_too_late: li r12, 0 + stw r12, STACK_SLOT_TRAP(r1) cmpdi r4, 0 beq 11f stw r12, VCPU_TRAP(r4) @@ -1558,12 +1558,12 @@ mc_cont: 3: stw r5,VCPU_SLB_MAX(r9) guest_bypass: + stw r12, STACK_SLOT_TRAP(r1) mr r3, r12 /* Increment exit count, poke other threads to exit */ bl kvmhv_commence_exit nop ld r9, HSTATE_KVM_VCPU(r13) - lwz r12, VCPU_TRAP(r9) /* Stop others sending VCPU interrupts to this physical CPU */ li r0, -1 @@ -1898,6 +1898,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_POWER9_DD1) * POWER7/POWER8 guest -> host partition switch code. * We don't have to lock against tlbies but we do * have to coordinate the hardware threads. + * Here STACK_SLOT_TRAP(r1) contains the trap number. */ kvmhv_switch_to_host: /* Secondary threads wait for primary to do partition switch */ @@ -1950,12 +1951,12 @@ BEGIN_FTR_SECTION END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S) /* If HMI, call kvmppc_realmode_hmi_handler() */ + lwz r12, STACK_SLOT_TRAP(r1) cmpwi r12, BOOK3S_INTERRUPT_HMI bne 27f bl kvmppc_realmode_hmi_handler nop cmpdi r3, 0 - li r12, BOOK3S_INTERRUPT_HMI /* * At this point kvmppc_realmode_hmi_handler may have resync-ed * the TB, and if it has, we must not subtract the guest timebase @@ -2008,10 +2009,8 @@ BEGIN_FTR_SECTION lwz r8, KVM_SPLIT_DO_RESTORE(r3) cmpwi r8, 0 beq 47f - stw r12, STACK_SLOT_TRAP(r1) bl kvmhv_p9_restore_lpcr nop - lwz r12, STACK_SLOT_TRAP(r1) b 48f 47: END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300) @@ -2049,6 +2048,7 @@ END_MMU_FTR_SECTION_IFSET(MMU_FTR_TYPE_RADIX) li r0, KVM_GUEST_MODE_NONE stb r0, HSTATE_IN_GUEST(r13) + lwz r12, STACK_SLOT_TRAP(r1) /* return trap # in r12 */ ld r0, SFS+PPC_LR_STKOFF(r1) addi r1, r1, SFS mtlr r0 -- cgit v1.2.3 From e21a4f3a930cda6e4902cb5b3213365e5ff3ce7c Mon Sep 17 00:00:00 2001 From: Christoffer Dall Date: Tue, 27 Feb 2018 12:33:50 +0100 Subject: KVM: arm/arm64: Avoid vcpu_load for other vcpu ioctls than KVM_RUN Calling vcpu_load() registers preempt notifiers for this vcpu and calls kvm_arch_vcpu_load(). The latter will soon be doing a lot of heavy lifting on arm/arm64 and will try to do things such as enabling the virtual timer and setting us up to handle interrupts from the timer hardware. Loading state onto hardware registers and enabling hardware to signal interrupts can be problematic when we're not actually about to run the VCPU, because it makes it difficult to establish the right context when handling interrupts from the timer, and it makes the register access code difficult to reason about. Luckily, now when we call vcpu_load in each ioctl implementation, we can simply remove the call from the non-KVM_RUN vcpu ioctls, and our kvm_arch_vcpu_load() is only used for loading vcpu content to the physical CPU when we're actually going to run the vcpu. Cc: stable@vger.kernel.org Fixes: 9b062471e52a ("KVM: Move vcpu_load to arch-specific kvm_arch_vcpu_ioctl") Reviewed-by: Julien Grall Reviewed-by: Marc Zyngier Reviewed-by: Andrew Jones Signed-off-by: Christoffer Dall Signed-off-by: Marc Zyngier --- arch/arm64/kvm/guest.c | 3 --- virt/kvm/arm/arm.c | 9 --------- 2 files changed, 12 deletions(-) (limited to 'arch') diff --git a/arch/arm64/kvm/guest.c b/arch/arm64/kvm/guest.c index d7e3299a7734..959e50d2588c 100644 --- a/arch/arm64/kvm/guest.c +++ b/arch/arm64/kvm/guest.c @@ -363,8 +363,6 @@ int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu, { int ret = 0; - vcpu_load(vcpu); - trace_kvm_set_guest_debug(vcpu, dbg->control); if (dbg->control & ~KVM_GUESTDBG_VALID_MASK) { @@ -386,7 +384,6 @@ int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu, } out: - vcpu_put(vcpu); return ret; } diff --git a/virt/kvm/arm/arm.c b/virt/kvm/arm/arm.c index 86941f6181bb..53572304843b 100644 --- a/virt/kvm/arm/arm.c +++ b/virt/kvm/arm/arm.c @@ -384,14 +384,11 @@ static void vcpu_power_off(struct kvm_vcpu *vcpu) int kvm_arch_vcpu_ioctl_get_mpstate(struct kvm_vcpu *vcpu, struct kvm_mp_state *mp_state) { - vcpu_load(vcpu); - if (vcpu->arch.power_off) mp_state->mp_state = KVM_MP_STATE_STOPPED; else mp_state->mp_state = KVM_MP_STATE_RUNNABLE; - vcpu_put(vcpu); return 0; } @@ -400,8 +397,6 @@ int kvm_arch_vcpu_ioctl_set_mpstate(struct kvm_vcpu *vcpu, { int ret = 0; - vcpu_load(vcpu); - switch (mp_state->mp_state) { case KVM_MP_STATE_RUNNABLE: vcpu->arch.power_off = false; @@ -413,7 +408,6 @@ int kvm_arch_vcpu_ioctl_set_mpstate(struct kvm_vcpu *vcpu, ret = -EINVAL; } - vcpu_put(vcpu); return ret; } @@ -1036,8 +1030,6 @@ long kvm_arch_vcpu_ioctl(struct file *filp, struct kvm_device_attr attr; long r; - vcpu_load(vcpu); - switch (ioctl) { case KVM_ARM_VCPU_INIT: { struct kvm_vcpu_init init; @@ -1114,7 +1106,6 @@ long kvm_arch_vcpu_ioctl(struct file *filp, r = -EINVAL; } - vcpu_put(vcpu); return r; } -- cgit v1.2.3 From daaf216c06fba4ee4dc3f62715667da929d68774 Mon Sep 17 00:00:00 2001 From: Tom Lendacky Date: Thu, 8 Mar 2018 17:17:31 -0600 Subject: KVM: x86: Fix device passthrough when SME is active When using device passthrough with SME active, the MMIO range that is mapped for the device should not be mapped encrypted. Add a check in set_spte() to insure that a page is not mapped encrypted if that page is a device MMIO page as indicated by kvm_is_mmio_pfn(). Cc: # 4.14.x- Signed-off-by: Tom Lendacky Signed-off-by: Paolo Bonzini --- arch/x86/kvm/mmu.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'arch') diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index f551962ac294..763bb3bade63 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -2770,8 +2770,10 @@ static int set_spte(struct kvm_vcpu *vcpu, u64 *sptep, else pte_access &= ~ACC_WRITE_MASK; + if (!kvm_is_mmio_pfn(pfn)) + spte |= shadow_me_mask; + spte |= (u64)pfn << PAGE_SHIFT; - spte |= shadow_me_mask; if (pte_access & ACC_WRITE_MASK) { -- cgit v1.2.3