From 21b5ee59ef18e27d85810584caf1f7ddc705ea83 Mon Sep 17 00:00:00 2001 From: Kim Phillips Date: Wed, 19 Feb 2020 18:52:43 +0100 Subject: x86/cpu/amd: Enable the fixed Instructions Retired counter IRPERF Commit aaf248848db50 ("perf/x86/msr: Add AMD IRPERF (Instructions Retired) performance counter") added support for access to the free-running counter via 'perf -e msr/irperf/', but when exercised, it always returns a 0 count: BEFORE: $ perf stat -e instructions,msr/irperf/ true Performance counter stats for 'true': 624,833 instructions 0 msr/irperf/ Simply set its enable bit - HWCR bit 30 - to make it start counting. Enablement is restricted to all machines advertising IRPERF capability, except those susceptible to an erratum that makes the IRPERF return bad values. That erratum occurs in Family 17h models 00-1fh [1], but not in F17h models 20h and above [2]. AFTER (on a family 17h model 31h machine): $ perf stat -e instructions,msr/irperf/ true Performance counter stats for 'true': 621,690 instructions 622,490 msr/irperf/ [1] Revision Guide for AMD Family 17h Models 00h-0Fh Processors [2] Revision Guide for AMD Family 17h Models 30h-3Fh Processors The revision guides are available from the bugzilla Link below. [ bp: Massage commit message. ] Fixes: aaf248848db50 ("perf/x86/msr: Add AMD IRPERF (Instructions Retired) performance counter") Signed-off-by: Kim Phillips Signed-off-by: Borislav Petkov Cc: Peter Zijlstra Cc: stable@vger.kernel.org Link: https://bugzilla.kernel.org/show_bug.cgi?id=206537 Link: http://lkml.kernel.org/r/20200214201805.13830-1-kim.phillips@amd.com --- arch/x86/include/asm/msr-index.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'arch/x86/include/asm') diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index ebe1685e92dd..d5e517d1c3dd 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -512,6 +512,8 @@ #define MSR_K7_HWCR 0xc0010015 #define MSR_K7_HWCR_SMMLOCK_BIT 0 #define MSR_K7_HWCR_SMMLOCK BIT_ULL(MSR_K7_HWCR_SMMLOCK_BIT) +#define MSR_K7_HWCR_IRPERF_EN_BIT 30 +#define MSR_K7_HWCR_IRPERF_EN BIT_ULL(MSR_K7_HWCR_IRPERF_EN_BIT) #define MSR_K7_FID_VID_CTL 0xc0010041 #define MSR_K7_FID_VID_STATUS 0xc0010042 -- cgit v1.2.3 From b78a8552d77f8efb7c4fbd92a91b890c32b89528 Mon Sep 17 00:00:00 2001 From: Qian Cai Date: Mon, 17 Feb 2020 11:48:26 -0500 Subject: kvm/emulate: fix a -Werror=cast-function-type arch/x86/kvm/emulate.c: In function 'x86_emulate_insn': arch/x86/kvm/emulate.c:5686:22: error: cast between incompatible function types from 'int (*)(struct x86_emulate_ctxt *)' to 'void (*)(struct fastop *)' [-Werror=cast-function-type] rc = fastop(ctxt, (fastop_t)ctxt->execute); Fix it by using an unnamed union of a (*execute) function pointer and a (*fastop) function pointer. Fixes: 3009afc6e39e ("KVM: x86: Use a typedef for fastop functions") Suggested-by: Paolo Bonzini Signed-off-by: Qian Cai Signed-off-by: Paolo Bonzini --- arch/x86/include/asm/kvm_emulate.h | 13 ++++++++++++- arch/x86/kvm/emulate.c | 36 ++++++++++++++---------------------- 2 files changed, 26 insertions(+), 23 deletions(-) (limited to 'arch/x86/include/asm') diff --git a/arch/x86/include/asm/kvm_emulate.h b/arch/x86/include/asm/kvm_emulate.h index 03946eb3e2b9..2a8f2bd2e5cf 100644 --- a/arch/x86/include/asm/kvm_emulate.h +++ b/arch/x86/include/asm/kvm_emulate.h @@ -292,6 +292,14 @@ enum x86emul_mode { #define X86EMUL_SMM_MASK (1 << 6) #define X86EMUL_SMM_INSIDE_NMI_MASK (1 << 7) +/* + * fastop functions are declared as taking a never-defined fastop parameter, + * so they can't be called from C directly. + */ +struct fastop; + +typedef void (*fastop_t)(struct fastop *); + struct x86_emulate_ctxt { const struct x86_emulate_ops *ops; @@ -324,7 +332,10 @@ struct x86_emulate_ctxt { struct operand src; struct operand src2; struct operand dst; - int (*execute)(struct x86_emulate_ctxt *ctxt); + union { + int (*execute)(struct x86_emulate_ctxt *ctxt); + fastop_t fop; + }; int (*check_perm)(struct x86_emulate_ctxt *ctxt); /* * The following six fields are cleared together, diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index ddbc61984227..dd19fb3539e0 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -191,25 +191,6 @@ #define NR_FASTOP (ilog2(sizeof(ulong)) + 1) #define FASTOP_SIZE 8 -/* - * fastop functions have a special calling convention: - * - * dst: rax (in/out) - * src: rdx (in/out) - * src2: rcx (in) - * flags: rflags (in/out) - * ex: rsi (in:fastop pointer, out:zero if exception) - * - * Moreover, they are all exactly FASTOP_SIZE bytes long, so functions for - * different operand sizes can be reached by calculation, rather than a jump - * table (which would be bigger than the code). - * - * fastop functions are declared as taking a never-defined fastop parameter, - * so they can't be called from C directly. - */ - -struct fastop; - struct opcode { u64 flags : 56; u64 intercept : 8; @@ -311,8 +292,19 @@ static void invalidate_registers(struct x86_emulate_ctxt *ctxt) #define ON64(x) #endif -typedef void (*fastop_t)(struct fastop *); - +/* + * fastop functions have a special calling convention: + * + * dst: rax (in/out) + * src: rdx (in/out) + * src2: rcx (in) + * flags: rflags (in/out) + * ex: rsi (in:fastop pointer, out:zero if exception) + * + * Moreover, they are all exactly FASTOP_SIZE bytes long, so functions for + * different operand sizes can be reached by calculation, rather than a jump + * table (which would be bigger than the code). + */ static int fastop(struct x86_emulate_ctxt *ctxt, fastop_t fop); #define __FOP_FUNC(name) \ @@ -5683,7 +5675,7 @@ special_insn: if (ctxt->execute) { if (ctxt->d & Fastop) - rc = fastop(ctxt, (fastop_t)ctxt->execute); + rc = fastop(ctxt, ctxt->fop); else rc = ctxt->execute(ctxt); if (rc != X86EMUL_CONTINUE) -- cgit v1.2.3 From 624e18f92f2ec449c2b3a6d388c0dccc45e4c4d7 Mon Sep 17 00:00:00 2001 From: Xiaoyao Li Date: Sun, 16 Feb 2020 18:48:57 +0800 Subject: KVM: VMX: Add VMX_FEATURE_USR_WAIT_PAUSE Commit 159348784ff0 ("x86/vmx: Introduce VMX_FEATURES_*") missed bit 26 (enable user wait and pause) of Secondary Processor-based VM-Execution Controls. Add VMX_FEATURE_USR_WAIT_PAUSE flag so that it shows up in /proc/cpuinfo, and use it to define SECONDARY_EXEC_ENABLE_USR_WAIT_PAUSE to make them uniform. Signed-off-by: Xiaoyao Li Reviewed-by: Vitaly Kuznetsov Signed-off-by: Paolo Bonzini --- arch/x86/include/asm/vmx.h | 2 +- arch/x86/include/asm/vmxfeatures.h | 1 + 2 files changed, 2 insertions(+), 1 deletion(-) (limited to 'arch/x86/include/asm') diff --git a/arch/x86/include/asm/vmx.h b/arch/x86/include/asm/vmx.h index 2a85287b3685..8521af3fef27 100644 --- a/arch/x86/include/asm/vmx.h +++ b/arch/x86/include/asm/vmx.h @@ -72,7 +72,7 @@ #define SECONDARY_EXEC_MODE_BASED_EPT_EXEC VMCS_CONTROL_BIT(MODE_BASED_EPT_EXEC) #define SECONDARY_EXEC_PT_USE_GPA VMCS_CONTROL_BIT(PT_USE_GPA) #define SECONDARY_EXEC_TSC_SCALING VMCS_CONTROL_BIT(TSC_SCALING) -#define SECONDARY_EXEC_ENABLE_USR_WAIT_PAUSE 0x04000000 +#define SECONDARY_EXEC_ENABLE_USR_WAIT_PAUSE VMCS_CONTROL_BIT(USR_WAIT_PAUSE) #define PIN_BASED_EXT_INTR_MASK VMCS_CONTROL_BIT(INTR_EXITING) #define PIN_BASED_NMI_EXITING VMCS_CONTROL_BIT(NMI_EXITING) diff --git a/arch/x86/include/asm/vmxfeatures.h b/arch/x86/include/asm/vmxfeatures.h index a50e4a0de315..9915990fd8cf 100644 --- a/arch/x86/include/asm/vmxfeatures.h +++ b/arch/x86/include/asm/vmxfeatures.h @@ -81,6 +81,7 @@ #define VMX_FEATURE_MODE_BASED_EPT_EXEC ( 2*32+ 22) /* "ept_mode_based_exec" Enable separate EPT EXEC bits for supervisor vs. user */ #define VMX_FEATURE_PT_USE_GPA ( 2*32+ 24) /* "" Processor Trace logs GPAs */ #define VMX_FEATURE_TSC_SCALING ( 2*32+ 25) /* Scale hardware TSC when read in guest */ +#define VMX_FEATURE_USR_WAIT_PAUSE ( 2*32+ 26) /* Enable TPAUSE, UMONITOR, UMWAIT in guest */ #define VMX_FEATURE_ENCLV_EXITING ( 2*32+ 28) /* "" VM-Exit on ENCLV (leaf dependent) */ #endif /* _ASM_X86_VMXFEATURES_H */ -- cgit v1.2.3 From 91a5f413af596ad01097e59bf487eb07cb3f1331 Mon Sep 17 00:00:00 2001 From: Vitaly Kuznetsov Date: Thu, 20 Feb 2020 18:22:05 +0100 Subject: KVM: nVMX: handle nested posted interrupts when apicv is disabled for L1 Even when APICv is disabled for L1 it can (and, actually, is) still available for L2, this means we need to always call vmx_deliver_nested_posted_interrupt() when attempting an interrupt delivery. Suggested-by: Paolo Bonzini Signed-off-by: Vitaly Kuznetsov Cc: stable@vger.kernel.org Signed-off-by: Paolo Bonzini --- arch/x86/include/asm/kvm_host.h | 2 +- arch/x86/kvm/lapic.c | 5 +---- arch/x86/kvm/svm.c | 7 ++++++- arch/x86/kvm/vmx/vmx.c | 13 +++++++++---- 4 files changed, 17 insertions(+), 10 deletions(-) (limited to 'arch/x86/include/asm') diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 40a0c0fd95ca..a84e8c5acda8 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -1146,7 +1146,7 @@ struct kvm_x86_ops { void (*load_eoi_exitmap)(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap); void (*set_virtual_apic_mode)(struct kvm_vcpu *vcpu); void (*set_apic_access_page_addr)(struct kvm_vcpu *vcpu, hpa_t hpa); - void (*deliver_posted_interrupt)(struct kvm_vcpu *vcpu, int vector); + int (*deliver_posted_interrupt)(struct kvm_vcpu *vcpu, int vector); int (*sync_pir_to_irr)(struct kvm_vcpu *vcpu); int (*set_tss_addr)(struct kvm *kvm, unsigned int addr); int (*set_identity_map_addr)(struct kvm *kvm, u64 ident_addr); diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index afcd30d44cbb..cc8ee8125712 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -1046,11 +1046,8 @@ static int __apic_accept_irq(struct kvm_lapic *apic, int delivery_mode, apic->regs + APIC_TMR); } - if (vcpu->arch.apicv_active) - kvm_x86_ops->deliver_posted_interrupt(vcpu, vector); - else { + if (kvm_x86_ops->deliver_posted_interrupt(vcpu, vector)) { kvm_lapic_set_irr(vector, apic); - kvm_make_request(KVM_REQ_EVENT, vcpu); kvm_vcpu_kick(vcpu); } diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index a391b29138f0..8787a123b8e7 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -5258,8 +5258,11 @@ static void svm_load_eoi_exitmap(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap) return; } -static void svm_deliver_avic_intr(struct kvm_vcpu *vcpu, int vec) +static int svm_deliver_avic_intr(struct kvm_vcpu *vcpu, int vec) { + if (!vcpu->arch.apicv_active) + return -1; + kvm_lapic_set_irr(vec, vcpu->arch.apic); smp_mb__after_atomic(); @@ -5271,6 +5274,8 @@ static void svm_deliver_avic_intr(struct kvm_vcpu *vcpu, int vec) put_cpu(); } else kvm_vcpu_wake_up(vcpu); + + return 0; } static bool svm_dy_apicv_has_pending_interrupt(struct kvm_vcpu *vcpu) diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index dafe4df893c8..63ccc435a602 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -3822,24 +3822,29 @@ static int vmx_deliver_nested_posted_interrupt(struct kvm_vcpu *vcpu, * 2. If target vcpu isn't running(root mode), kick it to pick up the * interrupt from PIR in next vmentry. */ -static void vmx_deliver_posted_interrupt(struct kvm_vcpu *vcpu, int vector) +static int vmx_deliver_posted_interrupt(struct kvm_vcpu *vcpu, int vector) { struct vcpu_vmx *vmx = to_vmx(vcpu); int r; r = vmx_deliver_nested_posted_interrupt(vcpu, vector); if (!r) - return; + return 0; + + if (!vcpu->arch.apicv_active) + return -1; if (pi_test_and_set_pir(vector, &vmx->pi_desc)) - return; + return 0; /* If a previous notification has sent the IPI, nothing to do. */ if (pi_test_and_set_on(&vmx->pi_desc)) - return; + return 0; if (!kvm_vcpu_trigger_posted_interrupt(vcpu, false)) kvm_vcpu_kick(vcpu); + + return 0; } /* -- cgit v1.2.3 From 5ef8acbdd687c9d72582e2c05c0b9756efb37863 Mon Sep 17 00:00:00 2001 From: Oliver Upton Date: Fri, 7 Feb 2020 02:36:07 -0800 Subject: KVM: nVMX: Emulate MTF when performing instruction emulation Since commit 5f3d45e7f282 ("kvm/x86: add support for MONITOR_TRAP_FLAG"), KVM has allowed an L1 guest to use the monitor trap flag processor-based execution control for its L2 guest. KVM simply forwards any MTF VM-exits to the L1 guest, which works for normal instruction execution. However, when KVM needs to emulate an instruction on the behalf of an L2 guest, the monitor trap flag is not emulated. Add the necessary logic to kvm_skip_emulated_instruction() to synthesize an MTF VM-exit to L1 upon instruction emulation for L2. Fixes: 5f3d45e7f282 ("kvm/x86: add support for MONITOR_TRAP_FLAG") Signed-off-by: Oliver Upton Signed-off-by: Paolo Bonzini --- arch/x86/include/asm/kvm_host.h | 1 + arch/x86/include/uapi/asm/kvm.h | 1 + arch/x86/kvm/svm.c | 1 + arch/x86/kvm/vmx/nested.c | 35 ++++++++++++++++++++++++++++++++++- arch/x86/kvm/vmx/nested.h | 5 +++++ arch/x86/kvm/vmx/vmx.c | 37 ++++++++++++++++++++++++++++++++++++- arch/x86/kvm/vmx/vmx.h | 3 +++ arch/x86/kvm/x86.c | 2 ++ 8 files changed, 83 insertions(+), 2 deletions(-) (limited to 'arch/x86/include/asm') diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index a84e8c5acda8..98959e8cd448 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -1122,6 +1122,7 @@ struct kvm_x86_ops { int (*handle_exit)(struct kvm_vcpu *vcpu, enum exit_fastpath_completion exit_fastpath); int (*skip_emulated_instruction)(struct kvm_vcpu *vcpu); + void (*update_emulated_instruction)(struct kvm_vcpu *vcpu); void (*set_interrupt_shadow)(struct kvm_vcpu *vcpu, int mask); u32 (*get_interrupt_shadow)(struct kvm_vcpu *vcpu); void (*patch_hypercall)(struct kvm_vcpu *vcpu, diff --git a/arch/x86/include/uapi/asm/kvm.h b/arch/x86/include/uapi/asm/kvm.h index 503d3f42da16..3f3f780c8c65 100644 --- a/arch/x86/include/uapi/asm/kvm.h +++ b/arch/x86/include/uapi/asm/kvm.h @@ -390,6 +390,7 @@ struct kvm_sync_regs { #define KVM_STATE_NESTED_GUEST_MODE 0x00000001 #define KVM_STATE_NESTED_RUN_PENDING 0x00000002 #define KVM_STATE_NESTED_EVMCS 0x00000004 +#define KVM_STATE_NESTED_MTF_PENDING 0x00000008 #define KVM_STATE_NESTED_SMM_GUEST_MODE 0x00000001 #define KVM_STATE_NESTED_SMM_VMXON 0x00000002 diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index d9b5add5a211..ad3f5b178a03 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -7439,6 +7439,7 @@ static struct kvm_x86_ops svm_x86_ops __ro_after_init = { .run = svm_vcpu_run, .handle_exit = handle_exit, .skip_emulated_instruction = skip_emulated_instruction, + .update_emulated_instruction = NULL, .set_interrupt_shadow = svm_set_interrupt_shadow, .get_interrupt_shadow = svm_get_interrupt_shadow, .patch_hypercall = svm_patch_hypercall, diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c index 2b3ba7d27be4..50d8dbb3616d 100644 --- a/arch/x86/kvm/vmx/nested.c +++ b/arch/x86/kvm/vmx/nested.c @@ -3609,8 +3609,15 @@ static int vmx_check_nested_events(struct kvm_vcpu *vcpu, bool external_intr) unsigned long exit_qual; bool block_nested_events = vmx->nested.nested_run_pending || kvm_event_needs_reinjection(vcpu); + bool mtf_pending = vmx->nested.mtf_pending; struct kvm_lapic *apic = vcpu->arch.apic; + /* + * Clear the MTF state. If a higher priority VM-exit is delivered first, + * this state is discarded. + */ + vmx->nested.mtf_pending = false; + if (lapic_in_kernel(vcpu) && test_bit(KVM_APIC_INIT, &apic->pending_events)) { if (block_nested_events) @@ -3621,8 +3628,28 @@ static int vmx_check_nested_events(struct kvm_vcpu *vcpu, bool external_intr) return 0; } + /* + * Process any exceptions that are not debug traps before MTF. + */ + if (vcpu->arch.exception.pending && + !vmx_pending_dbg_trap(vcpu) && + nested_vmx_check_exception(vcpu, &exit_qual)) { + if (block_nested_events) + return -EBUSY; + nested_vmx_inject_exception_vmexit(vcpu, exit_qual); + return 0; + } + + if (mtf_pending) { + if (block_nested_events) + return -EBUSY; + nested_vmx_update_pending_dbg(vcpu); + nested_vmx_vmexit(vcpu, EXIT_REASON_MONITOR_TRAP_FLAG, 0, 0); + return 0; + } + if (vcpu->arch.exception.pending && - nested_vmx_check_exception(vcpu, &exit_qual)) { + nested_vmx_check_exception(vcpu, &exit_qual)) { if (block_nested_events) return -EBUSY; nested_vmx_inject_exception_vmexit(vcpu, exit_qual); @@ -5712,6 +5739,9 @@ static int vmx_get_nested_state(struct kvm_vcpu *vcpu, if (vmx->nested.nested_run_pending) kvm_state.flags |= KVM_STATE_NESTED_RUN_PENDING; + + if (vmx->nested.mtf_pending) + kvm_state.flags |= KVM_STATE_NESTED_MTF_PENDING; } } @@ -5892,6 +5922,9 @@ static int vmx_set_nested_state(struct kvm_vcpu *vcpu, vmx->nested.nested_run_pending = !!(kvm_state->flags & KVM_STATE_NESTED_RUN_PENDING); + vmx->nested.mtf_pending = + !!(kvm_state->flags & KVM_STATE_NESTED_MTF_PENDING); + ret = -EINVAL; if (nested_cpu_has_shadow_vmcs(vmcs12) && vmcs12->vmcs_link_pointer != -1ull) { diff --git a/arch/x86/kvm/vmx/nested.h b/arch/x86/kvm/vmx/nested.h index 1c5fbff45d69..1db388f2a444 100644 --- a/arch/x86/kvm/vmx/nested.h +++ b/arch/x86/kvm/vmx/nested.h @@ -174,6 +174,11 @@ static inline bool nested_cpu_has_virtual_nmis(struct vmcs12 *vmcs12) return vmcs12->pin_based_vm_exec_control & PIN_BASED_VIRTUAL_NMIS; } +static inline int nested_cpu_has_mtf(struct vmcs12 *vmcs12) +{ + return nested_cpu_has(vmcs12, CPU_BASED_MONITOR_TRAP_FLAG); +} + static inline int nested_cpu_has_ept(struct vmcs12 *vmcs12) { return nested_cpu_has2(vmcs12, SECONDARY_EXEC_ENABLE_EPT); diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index 404dafedd778..dcca514ffd42 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -1603,6 +1603,40 @@ static int skip_emulated_instruction(struct kvm_vcpu *vcpu) return 1; } + +/* + * Recognizes a pending MTF VM-exit and records the nested state for later + * delivery. + */ +static void vmx_update_emulated_instruction(struct kvm_vcpu *vcpu) +{ + struct vmcs12 *vmcs12 = get_vmcs12(vcpu); + struct vcpu_vmx *vmx = to_vmx(vcpu); + + if (!is_guest_mode(vcpu)) + return; + + /* + * Per the SDM, MTF takes priority over debug-trap exceptions besides + * T-bit traps. As instruction emulation is completed (i.e. at the + * instruction boundary), any #DB exception pending delivery must be a + * debug-trap. Record the pending MTF state to be delivered in + * vmx_check_nested_events(). + */ + if (nested_cpu_has_mtf(vmcs12) && + (!vcpu->arch.exception.pending || + vcpu->arch.exception.nr == DB_VECTOR)) + vmx->nested.mtf_pending = true; + else + vmx->nested.mtf_pending = false; +} + +static int vmx_skip_emulated_instruction(struct kvm_vcpu *vcpu) +{ + vmx_update_emulated_instruction(vcpu); + return skip_emulated_instruction(vcpu); +} + static void vmx_clear_hlt(struct kvm_vcpu *vcpu) { /* @@ -7796,7 +7830,8 @@ static struct kvm_x86_ops vmx_x86_ops __ro_after_init = { .run = vmx_vcpu_run, .handle_exit = vmx_handle_exit, - .skip_emulated_instruction = skip_emulated_instruction, + .skip_emulated_instruction = vmx_skip_emulated_instruction, + .update_emulated_instruction = vmx_update_emulated_instruction, .set_interrupt_shadow = vmx_set_interrupt_shadow, .get_interrupt_shadow = vmx_get_interrupt_shadow, .patch_hypercall = vmx_patch_hypercall, diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h index 7f42cf3dcd70..e64da06c7009 100644 --- a/arch/x86/kvm/vmx/vmx.h +++ b/arch/x86/kvm/vmx/vmx.h @@ -150,6 +150,9 @@ struct nested_vmx { /* L2 must run next, and mustn't decide to exit to L1. */ bool nested_run_pending; + /* Pending MTF VM-exit into L1. */ + bool mtf_pending; + struct loaded_vmcs vmcs02; /* diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index fb5d64ebc35d..359fcd395132 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -6891,6 +6891,8 @@ restart: kvm_rip_write(vcpu, ctxt->eip); if (r && ctxt->tf) r = kvm_vcpu_do_singlestep(vcpu); + if (kvm_x86_ops->update_emulated_instruction) + kvm_x86_ops->update_emulated_instruction(vcpu); __kvm_set_rflags(vcpu, ctxt->eflags); } -- cgit v1.2.3 From 99bcd4a6e5b8ba201fdd252f1054689884899fee Mon Sep 17 00:00:00 2001 From: Juergen Gross Date: Tue, 18 Feb 2020 16:47:12 +0100 Subject: x86/ioperm: Add new paravirt function update_io_bitmap() Commit 111e7b15cf10f6 ("x86/ioperm: Extend IOPL config to control ioperm() as well") reworked the iopl syscall to use I/O bitmaps. Unfortunately this broke Xen PV domains using that syscall as there is currently no I/O bitmap support in PV domains. Add I/O bitmap support via a new paravirt function update_io_bitmap which Xen PV domains can use to update their I/O bitmaps via a hypercall. Fixes: 111e7b15cf10f6 ("x86/ioperm: Extend IOPL config to control ioperm() as well") Reported-by: Jan Beulich Signed-off-by: Juergen Gross Signed-off-by: Thomas Gleixner Tested-by: Jan Beulich Reviewed-by: Jan Beulich Cc: # 5.5 Link: https://lkml.kernel.org/r/20200218154712.25490-1-jgross@suse.com --- arch/x86/include/asm/io_bitmap.h | 9 ++++++++- arch/x86/include/asm/paravirt.h | 7 +++++++ arch/x86/include/asm/paravirt_types.h | 4 ++++ arch/x86/kernel/paravirt.c | 5 +++++ arch/x86/kernel/process.c | 2 +- arch/x86/xen/enlighten_pv.c | 25 +++++++++++++++++++++++++ 6 files changed, 50 insertions(+), 2 deletions(-) (limited to 'arch/x86/include/asm') diff --git a/arch/x86/include/asm/io_bitmap.h b/arch/x86/include/asm/io_bitmap.h index 02c6ef8f7667..07344d82e88e 100644 --- a/arch/x86/include/asm/io_bitmap.h +++ b/arch/x86/include/asm/io_bitmap.h @@ -19,7 +19,14 @@ struct task_struct; void io_bitmap_share(struct task_struct *tsk); void io_bitmap_exit(void); -void tss_update_io_bitmap(void); +void native_tss_update_io_bitmap(void); + +#ifdef CONFIG_PARAVIRT_XXL +#include +#else +#define tss_update_io_bitmap native_tss_update_io_bitmap +#endif + #else static inline void io_bitmap_share(struct task_struct *tsk) { } static inline void io_bitmap_exit(void) { } diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h index 86e7317eb31f..694d8daf4983 100644 --- a/arch/x86/include/asm/paravirt.h +++ b/arch/x86/include/asm/paravirt.h @@ -295,6 +295,13 @@ static inline void write_idt_entry(gate_desc *dt, int entry, const gate_desc *g) PVOP_VCALL3(cpu.write_idt_entry, dt, entry, g); } +#ifdef CONFIG_X86_IOPL_IOPERM +static inline void tss_update_io_bitmap(void) +{ + PVOP_VCALL0(cpu.update_io_bitmap); +} +#endif + static inline void paravirt_activate_mm(struct mm_struct *prev, struct mm_struct *next) { diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h index 84812964d3dd..732f62e04ddb 100644 --- a/arch/x86/include/asm/paravirt_types.h +++ b/arch/x86/include/asm/paravirt_types.h @@ -140,6 +140,10 @@ struct pv_cpu_ops { void (*load_sp0)(unsigned long sp0); +#ifdef CONFIG_X86_IOPL_IOPERM + void (*update_io_bitmap)(void); +#endif + void (*wbinvd)(void); /* cpuid emulation, mostly so that caps bits can be disabled */ diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c index 789f5e4f89de..c131ba4e70ef 100644 --- a/arch/x86/kernel/paravirt.c +++ b/arch/x86/kernel/paravirt.c @@ -30,6 +30,7 @@ #include #include #include +#include /* * nop stub, which must not clobber anything *including the stack* to @@ -341,6 +342,10 @@ struct paravirt_patch_template pv_ops = { .cpu.iret = native_iret, .cpu.swapgs = native_swapgs, +#ifdef CONFIG_X86_IOPL_IOPERM + .cpu.update_io_bitmap = native_tss_update_io_bitmap, +#endif + .cpu.start_context_switch = paravirt_nop, .cpu.end_context_switch = paravirt_nop, diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index 839b5244e3b7..3053c85e0e42 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -374,7 +374,7 @@ static void tss_copy_io_bitmap(struct tss_struct *tss, struct io_bitmap *iobm) /** * tss_update_io_bitmap - Update I/O bitmap before exiting to usermode */ -void tss_update_io_bitmap(void) +void native_tss_update_io_bitmap(void) { struct tss_struct *tss = this_cpu_ptr(&cpu_tss_rw); struct thread_struct *t = ¤t->thread; diff --git a/arch/x86/xen/enlighten_pv.c b/arch/x86/xen/enlighten_pv.c index 79409120a603..507f4fb88fa7 100644 --- a/arch/x86/xen/enlighten_pv.c +++ b/arch/x86/xen/enlighten_pv.c @@ -72,6 +72,9 @@ #include #include #include +#ifdef CONFIG_X86_IOPL_IOPERM +#include +#endif #ifdef CONFIG_ACPI #include @@ -837,6 +840,25 @@ static void xen_load_sp0(unsigned long sp0) this_cpu_write(cpu_tss_rw.x86_tss.sp0, sp0); } +#ifdef CONFIG_X86_IOPL_IOPERM +static void xen_update_io_bitmap(void) +{ + struct physdev_set_iobitmap iobitmap; + struct tss_struct *tss = this_cpu_ptr(&cpu_tss_rw); + + native_tss_update_io_bitmap(); + + iobitmap.bitmap = (uint8_t *)(&tss->x86_tss) + + tss->x86_tss.io_bitmap_base; + if (tss->x86_tss.io_bitmap_base == IO_BITMAP_OFFSET_INVALID) + iobitmap.nr_ports = 0; + else + iobitmap.nr_ports = IO_BITMAP_BITS; + + HYPERVISOR_physdev_op(PHYSDEVOP_set_iobitmap, &iobitmap); +} +#endif + static void xen_io_delay(void) { } @@ -1047,6 +1069,9 @@ static const struct pv_cpu_ops xen_cpu_ops __initconst = { .write_idt_entry = xen_write_idt_entry, .load_sp0 = xen_load_sp0, +#ifdef CONFIG_X86_IOPL_IOPERM + .update_io_bitmap = xen_update_io_bitmap, +#endif .io_delay = xen_io_delay, /* Xen takes care of %gs when switching to usermode for us */ -- cgit v1.2.3