From feb5dc3de03711d846f0b729cb12fc05cbe49ccb Mon Sep 17 00:00:00 2001 From: Alexandru Elisei Date: Wed, 7 Apr 2021 15:48:56 +0100 Subject: Documentation: KVM: Document KVM_GUESTDBG_USE_HW control flag for arm64 Commit 21b6f32f9471 ("KVM: arm64: guest debug, define API headers") added the arm64 KVM_GUESTDBG_USE_HW flag for the KVM_SET_GUEST_DEBUG ioctl and commit 834bf88726f0 ("KVM: arm64: enable KVM_CAP_SET_GUEST_DEBUG") documented and implemented the flag functionality. Since its introduction, at no point was the flag known by any name other than KVM_GUESTDBG_USE_HW for the arm64 architecture, so refer to it as such in the documentation. CC: Paolo Bonzini Signed-off-by: Alexandru Elisei Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20210407144857.199746-2-alexandru.elisei@arm.com --- Documentation/virt/kvm/api.rst | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst index 38e327d4b479..62ffcb2dafee 100644 --- a/Documentation/virt/kvm/api.rst +++ b/Documentation/virt/kvm/api.rst @@ -3334,7 +3334,8 @@ The top 16 bits of the control field are architecture specific control flags which can include the following: - KVM_GUESTDBG_USE_SW_BP: using software breakpoints [x86, arm64] - - KVM_GUESTDBG_USE_HW_BP: using hardware breakpoints [x86, s390, arm64] + - KVM_GUESTDBG_USE_HW_BP: using hardware breakpoints [x86, s390] + - KVM_GUESTDBG_USE_HW: using hardware debug events [arm64] - KVM_GUESTDBG_INJECT_DB: inject DB type exception [x86] - KVM_GUESTDBG_INJECT_BP: inject BP type exception [x86] - KVM_GUESTDBG_EXIT_PENDING: trigger an immediate guest exit [s390] -- cgit v1.2.3 From 263d6287da1433aba11c5b4046388f2cdf49675c Mon Sep 17 00:00:00 2001 From: Alexandru Elisei Date: Wed, 7 Apr 2021 15:48:57 +0100 Subject: KVM: arm64: Initialize VCPU mdcr_el2 before loading it When a VCPU is created, the kvm_vcpu struct is initialized to zero in kvm_vm_ioctl_create_vcpu(). On VHE systems, the first time vcpu.arch.mdcr_el2 is loaded on hardware is in vcpu_load(), before it is set to a sensible value in kvm_arm_setup_debug() later in the run loop. The result is that KVM executes for a short time with MDCR_EL2 set to zero. This has several unintended consequences: * Setting MDCR_EL2.HPMN to 0 is constrained unpredictable according to ARM DDI 0487G.a, page D13-3820. The behavior specified by the architecture in this case is for the PE to behave as if MDCR_EL2.HPMN is set to a value less than or equal to PMCR_EL0.N, which means that an unknown number of counters are now disabled by MDCR_EL2.HPME, which is zero. * The host configuration for the other debug features controlled by MDCR_EL2 is temporarily lost. This has been harmless so far, as Linux doesn't use the other fields, but that might change in the future. Let's avoid both issues by initializing the VCPU's mdcr_el2 field in kvm_vcpu_vcpu_first_run_init(), thus making sure that the MDCR_EL2 register has a consistent value after each vcpu_load(). Fixes: d5a21bcc2995 ("KVM: arm64: Move common VHE/non-VHE trap config in separate functions") Signed-off-by: Alexandru Elisei Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20210407144857.199746-3-alexandru.elisei@arm.com --- arch/arm64/include/asm/kvm_host.h | 1 + arch/arm64/kvm/arm.c | 2 + arch/arm64/kvm/debug.c | 88 ++++++++++++++++++++++++++------------- 3 files changed, 63 insertions(+), 28 deletions(-) diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index 3d10e6527f7d..858c2fcfc043 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -713,6 +713,7 @@ static inline void kvm_arch_sched_in(struct kvm_vcpu *vcpu, int cpu) {} static inline void kvm_arch_vcpu_block_finish(struct kvm_vcpu *vcpu) {} void kvm_arm_init_debug(void); +void kvm_arm_vcpu_init_debug(struct kvm_vcpu *vcpu); void kvm_arm_setup_debug(struct kvm_vcpu *vcpu); void kvm_arm_clear_debug(struct kvm_vcpu *vcpu); void kvm_arm_reset_debug_ptr(struct kvm_vcpu *vcpu); diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c index 7f06ba76698d..455274c704b8 100644 --- a/arch/arm64/kvm/arm.c +++ b/arch/arm64/kvm/arm.c @@ -580,6 +580,8 @@ static int kvm_vcpu_first_run_init(struct kvm_vcpu *vcpu) vcpu->arch.has_run_once = true; + kvm_arm_vcpu_init_debug(vcpu); + if (likely(irqchip_in_kernel(kvm))) { /* * Map the VGIC hardware resources before running a vcpu the diff --git a/arch/arm64/kvm/debug.c b/arch/arm64/kvm/debug.c index dbc890511631..2484b2cca74b 100644 --- a/arch/arm64/kvm/debug.c +++ b/arch/arm64/kvm/debug.c @@ -68,6 +68,64 @@ void kvm_arm_init_debug(void) __this_cpu_write(mdcr_el2, kvm_call_hyp_ret(__kvm_get_mdcr_el2)); } +/** + * kvm_arm_setup_mdcr_el2 - configure vcpu mdcr_el2 value + * + * @vcpu: the vcpu pointer + * + * This ensures we will trap access to: + * - Performance monitors (MDCR_EL2_TPM/MDCR_EL2_TPMCR) + * - Debug ROM Address (MDCR_EL2_TDRA) + * - OS related registers (MDCR_EL2_TDOSA) + * - Statistical profiler (MDCR_EL2_TPMS/MDCR_EL2_E2PB) + * - Self-hosted Trace Filter controls (MDCR_EL2_TTRF) + */ +static void kvm_arm_setup_mdcr_el2(struct kvm_vcpu *vcpu) +{ + /* + * This also clears MDCR_EL2_E2PB_MASK to disable guest access + * to the profiling buffer. + */ + vcpu->arch.mdcr_el2 = __this_cpu_read(mdcr_el2) & MDCR_EL2_HPMN_MASK; + vcpu->arch.mdcr_el2 |= (MDCR_EL2_TPM | + MDCR_EL2_TPMS | + MDCR_EL2_TTRF | + MDCR_EL2_TPMCR | + MDCR_EL2_TDRA | + MDCR_EL2_TDOSA); + + /* Is the VM being debugged by userspace? */ + if (vcpu->guest_debug) + /* Route all software debug exceptions to EL2 */ + vcpu->arch.mdcr_el2 |= MDCR_EL2_TDE; + + /* + * Trap debug register access when one of the following is true: + * - Userspace is using the hardware to debug the guest + * (KVM_GUESTDBG_USE_HW is set). + * - The guest is not using debug (KVM_ARM64_DEBUG_DIRTY is clear). + */ + if ((vcpu->guest_debug & KVM_GUESTDBG_USE_HW) || + !(vcpu->arch.flags & KVM_ARM64_DEBUG_DIRTY)) + vcpu->arch.mdcr_el2 |= MDCR_EL2_TDA; + + trace_kvm_arm_set_dreg32("MDCR_EL2", vcpu->arch.mdcr_el2); +} + +/** + * kvm_arm_vcpu_init_debug - setup vcpu debug traps + * + * @vcpu: the vcpu pointer + * + * Set vcpu initial mdcr_el2 value. + */ +void kvm_arm_vcpu_init_debug(struct kvm_vcpu *vcpu) +{ + preempt_disable(); + kvm_arm_setup_mdcr_el2(vcpu); + preempt_enable(); +} + /** * kvm_arm_reset_debug_ptr - reset the debug ptr to point to the vcpu state */ @@ -83,13 +141,7 @@ void kvm_arm_reset_debug_ptr(struct kvm_vcpu *vcpu) * @vcpu: the vcpu pointer * * This is called before each entry into the hypervisor to setup any - * debug related registers. Currently this just ensures we will trap - * access to: - * - Performance monitors (MDCR_EL2_TPM/MDCR_EL2_TPMCR) - * - Debug ROM Address (MDCR_EL2_TDRA) - * - OS related registers (MDCR_EL2_TDOSA) - * - Statistical profiler (MDCR_EL2_TPMS/MDCR_EL2_E2PB) - * - Self-hosted Trace Filter controls (MDCR_EL2_TTRF) + * debug related registers. * * Additionally, KVM only traps guest accesses to the debug registers if * the guest is not actively using them (see the KVM_ARM64_DEBUG_DIRTY @@ -101,28 +153,14 @@ void kvm_arm_reset_debug_ptr(struct kvm_vcpu *vcpu) void kvm_arm_setup_debug(struct kvm_vcpu *vcpu) { - bool trap_debug = !(vcpu->arch.flags & KVM_ARM64_DEBUG_DIRTY); unsigned long mdscr, orig_mdcr_el2 = vcpu->arch.mdcr_el2; trace_kvm_arm_setup_debug(vcpu, vcpu->guest_debug); - /* - * This also clears MDCR_EL2_E2PB_MASK to disable guest access - * to the profiling buffer. - */ - vcpu->arch.mdcr_el2 = __this_cpu_read(mdcr_el2) & MDCR_EL2_HPMN_MASK; - vcpu->arch.mdcr_el2 |= (MDCR_EL2_TPM | - MDCR_EL2_TPMS | - MDCR_EL2_TTRF | - MDCR_EL2_TPMCR | - MDCR_EL2_TDRA | - MDCR_EL2_TDOSA); + kvm_arm_setup_mdcr_el2(vcpu); /* Is Guest debugging in effect? */ if (vcpu->guest_debug) { - /* Route all software debug exceptions to EL2 */ - vcpu->arch.mdcr_el2 |= MDCR_EL2_TDE; - /* Save guest debug state */ save_guest_debug_regs(vcpu); @@ -176,7 +214,6 @@ void kvm_arm_setup_debug(struct kvm_vcpu *vcpu) vcpu->arch.debug_ptr = &vcpu->arch.external_debug_state; vcpu->arch.flags |= KVM_ARM64_DEBUG_DIRTY; - trap_debug = true; trace_kvm_arm_set_regset("BKPTS", get_num_brps(), &vcpu->arch.debug_ptr->dbg_bcr[0], @@ -191,10 +228,6 @@ void kvm_arm_setup_debug(struct kvm_vcpu *vcpu) BUG_ON(!vcpu->guest_debug && vcpu->arch.debug_ptr != &vcpu->arch.vcpu_debug_state); - /* Trap debug register access */ - if (trap_debug) - vcpu->arch.mdcr_el2 |= MDCR_EL2_TDA; - /* If KDE or MDE are set, perform a full save/restore cycle. */ if (vcpu_read_sys_reg(vcpu, MDSCR_EL1) & (DBG_MDSCR_KDE | DBG_MDSCR_MDE)) vcpu->arch.flags |= KVM_ARM64_DEBUG_DIRTY; @@ -203,7 +236,6 @@ void kvm_arm_setup_debug(struct kvm_vcpu *vcpu) if (has_vhe() && orig_mdcr_el2 != vcpu->arch.mdcr_el2) write_sysreg(vcpu->arch.mdcr_el2, mdcr_el2); - trace_kvm_arm_set_dreg32("MDCR_EL2", vcpu->arch.mdcr_el2); trace_kvm_arm_set_dreg32("MDSCR_EL1", vcpu_read_sys_reg(vcpu, MDSCR_EL1)); } -- cgit v1.2.3 From 13611bc80d3da162aaf32b01ceffc804e027d406 Mon Sep 17 00:00:00 2001 From: Alexandru Elisei Date: Fri, 9 Apr 2021 16:21:53 +0100 Subject: KVM: arm64: Don't print warning when trapping SPE registers KVM sets up MDCR_EL2 to trap accesses to the SPE buffer and sampling control registers and it relies on the fact that KVM injects an undefined exception for unknown registers. This mechanism of injecting undefined exceptions also prints a warning message for the host kernel; for example, when a guest tries to access PMSIDR_EL1: [ 2.691830] kvm [142]: Unsupported guest sys_reg access at: 80009e78 [800003c5] [ 2.691830] { Op0( 3), Op1( 0), CRn( 9), CRm( 9), Op2( 7), func_read }, This is unnecessary, because KVM has explicitly configured trapping of those registers and is well aware of their existence. Prevent the warning by adding the SPE registers to the list of registers that KVM emulates. The access function will inject the undefined exception. Signed-off-by: Alexandru Elisei Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20210409152154.198566-2-alexandru.elisei@arm.com --- arch/arm64/include/asm/sysreg.h | 2 ++ arch/arm64/kvm/sys_regs.c | 13 +++++++++++++ 2 files changed, 15 insertions(+) diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h index d4a5fca984c3..43bca834c477 100644 --- a/arch/arm64/include/asm/sysreg.h +++ b/arch/arm64/include/asm/sysreg.h @@ -283,6 +283,8 @@ #define SYS_PMSIRR_EL1_INTERVAL_MASK 0xffffffUL /* Filtering controls */ +#define SYS_PMSNEVFR_EL1 sys_reg(3, 0, 9, 9, 1) + #define SYS_PMSFCR_EL1 sys_reg(3, 0, 9, 9, 4) #define SYS_PMSFCR_EL1_FE_SHIFT 0 #define SYS_PMSFCR_EL1_FT_SHIFT 1 diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c index 4f2f1e3145de..402cd11aa4fc 100644 --- a/arch/arm64/kvm/sys_regs.c +++ b/arch/arm64/kvm/sys_regs.c @@ -1501,6 +1501,19 @@ static const struct sys_reg_desc sys_reg_descs[] = { { SYS_DESC(SYS_FAR_EL1), access_vm_reg, reset_unknown, FAR_EL1 }, { SYS_DESC(SYS_PAR_EL1), NULL, reset_unknown, PAR_EL1 }, + { SYS_DESC(SYS_PMSCR_EL1), undef_access }, + { SYS_DESC(SYS_PMSNEVFR_EL1), undef_access }, + { SYS_DESC(SYS_PMSICR_EL1), undef_access }, + { SYS_DESC(SYS_PMSIRR_EL1), undef_access }, + { SYS_DESC(SYS_PMSFCR_EL1), undef_access }, + { SYS_DESC(SYS_PMSEVFR_EL1), undef_access }, + { SYS_DESC(SYS_PMSLATFR_EL1), undef_access }, + { SYS_DESC(SYS_PMSIDR_EL1), undef_access }, + { SYS_DESC(SYS_PMBLIMITR_EL1), undef_access }, + { SYS_DESC(SYS_PMBPTR_EL1), undef_access }, + { SYS_DESC(SYS_PMBSR_EL1), undef_access }, + /* PMBIDR_EL1 is not trapped */ + { PMU_SYS_REG(SYS_PMINTENSET_EL1), .access = access_pminten, .reg = PMINTENSET_EL1 }, { PMU_SYS_REG(SYS_PMINTENCLR_EL1), -- cgit v1.2.3 From 96f4f6809beec1bb2338e1aeac408e6a733f8135 Mon Sep 17 00:00:00 2001 From: Alexandru Elisei Date: Fri, 9 Apr 2021 16:21:54 +0100 Subject: KVM: arm64: Don't advertise FEAT_SPE to guests Even though KVM sets up MDCR_EL2 to trap accesses to the SPE buffer and sampling control registers and to inject an undefined exception, the presence of FEAT_SPE is still advertised in the ID_AA64DFR0_EL1 register, if the hardware supports it. Getting an undefined exception when accessing a register usually happens for a hardware feature which is not implemented, and indeed this is how PMU emulation is handled when the virtual machine has been created without the KVM_ARM_VCPU_PMU_V3 feature. Let's be consistent and never advertise FEAT_SPE, because KVM doesn't have support for emulating it yet. Signed-off-by: Alexandru Elisei Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20210409152154.198566-3-alexandru.elisei@arm.com --- arch/arm64/kvm/sys_regs.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c index 402cd11aa4fc..61ee9bfb8826 100644 --- a/arch/arm64/kvm/sys_regs.c +++ b/arch/arm64/kvm/sys_regs.c @@ -1063,6 +1063,8 @@ static u64 read_id_reg(const struct kvm_vcpu *vcpu, val = cpuid_feature_cap_perfmon_field(val, ID_AA64DFR0_PMUVER_SHIFT, kvm_vcpu_has_pmu(vcpu) ? ID_AA64DFR0_PMUVER_8_4 : 0); + /* Hide SPE from guests */ + val &= ~FEATURE(ID_AA64DFR0_PMSVER); break; case SYS_ID_DFR0_EL1: /* Limit guests to PMUv3 for ARMv8.4 */ -- cgit v1.2.3