From f17c31c48e5cde9895a491d91c424eeeada3e134 Mon Sep 17 00:00:00 2001 From: "Maciej S. Szmigiero" Date: Mon, 2 May 2022 00:07:26 +0200 Subject: KVM: SVM: Don't BUG if userspace injects an interrupt with GIF=0 Don't BUG/WARN on interrupt injection due to GIF being cleared, since it's trivial for userspace to force the situation via KVM_SET_VCPU_EVENTS (even if having at least a WARN there would be correct for KVM internally generated injections). kernel BUG at arch/x86/kvm/svm/svm.c:3386! invalid opcode: 0000 [#1] SMP CPU: 15 PID: 926 Comm: smm_test Not tainted 5.17.0-rc3+ #264 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 0.0.0 02/06/2015 RIP: 0010:svm_inject_irq+0xab/0xb0 [kvm_amd] Code: <0f> 0b 0f 1f 00 0f 1f 44 00 00 80 3d ac b3 01 00 00 55 48 89 f5 53 RSP: 0018:ffffc90000b37d88 EFLAGS: 00010246 RAX: 0000000000000000 RBX: ffff88810a234ac0 RCX: 0000000000000006 RDX: 0000000000000000 RSI: ffffc90000b37df7 RDI: ffff88810a234ac0 RBP: ffffc90000b37df7 R08: ffff88810a1fa410 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000000 R12: 0000000000000000 R13: ffff888109571000 R14: ffff88810a234ac0 R15: 0000000000000000 FS: 0000000001821380(0000) GS:ffff88846fdc0000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007f74fc550008 CR3: 000000010a6fe000 CR4: 0000000000350ea0 Call Trace: inject_pending_event+0x2f7/0x4c0 [kvm] kvm_arch_vcpu_ioctl_run+0x791/0x17a0 [kvm] kvm_vcpu_ioctl+0x26d/0x650 [kvm] __x64_sys_ioctl+0x82/0xb0 do_syscall_64+0x3b/0xc0 entry_SYSCALL_64_after_hwframe+0x44/0xae Fixes: 219b65dcf6c0 ("KVM: SVM: Improve nested interrupt injection") Cc: stable@vger.kernel.org Co-developed-by: Sean Christopherson Signed-off-by: Sean Christopherson Signed-off-by: Maciej S. Szmigiero Message-Id: <35426af6e123cbe91ec7ce5132ce72521f02b1b5.1651440202.git.maciej.szmigiero@oracle.com> Signed-off-by: Paolo Bonzini --- arch/x86/kvm/svm/svm.c | 2 -- 1 file changed, 2 deletions(-) (limited to 'arch/x86/kvm/svm/svm.c') diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index 2628452a5156..a191ec138636 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -3392,8 +3392,6 @@ static void svm_inject_irq(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); - BUG_ON(!(gif_set(svm))); - trace_kvm_inj_virq(vcpu->arch.interrupt.nr); ++vcpu->stat.irq_injections; -- cgit v1.2.3 From cd9e6da8048c5b40315ee2d929b6230ce1252c3c Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Mon, 2 May 2022 00:07:27 +0200 Subject: KVM: SVM: Unwind "speculative" RIP advancement if INTn injection "fails" Unwind the RIP advancement done by svm_queue_exception() when injecting an INT3 ultimately "fails" due to the CPU encountering a VM-Exit while vectoring the injected event, even if the exception reported by the CPU isn't the same event that was injected. If vectoring INT3 encounters an exception, e.g. #NP, and vectoring the #NP encounters an intercepted exception, e.g. #PF when KVM is using shadow paging, then the #NP will be reported as the event that was in-progress. Note, this is still imperfect, as it will get a false positive if the INT3 is cleanly injected, no VM-Exit occurs before the IRET from the INT3 handler in the guest, the instruction following the INT3 generates an exception (directly or indirectly), _and_ vectoring that exception encounters an exception that is intercepted by KVM. The false positives could theoretically be solved by further analyzing the vectoring event, e.g. by comparing the error code against the expected error code were an exception to occur when vectoring the original injected exception, but SVM without NRIPS is a complete disaster, trying to make it 100% correct is a waste of time. Reviewed-by: Maxim Levitsky Fixes: 66b7138f9136 ("KVM: SVM: Emulate nRIP feature when reinjecting INT3") Signed-off-by: Sean Christopherson Signed-off-by: Maciej S. Szmigiero Message-Id: <450133cf0a026cb9825a2ff55d02cb136a1cb111.1651440202.git.maciej.szmigiero@oracle.com> Signed-off-by: Paolo Bonzini --- arch/x86/kvm/svm/svm.c | 23 +++++++++++++++-------- 1 file changed, 15 insertions(+), 8 deletions(-) (limited to 'arch/x86/kvm/svm/svm.c') diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index a191ec138636..c1506069e67c 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -3706,6 +3706,18 @@ static void svm_complete_interrupts(struct kvm_vcpu *vcpu) vector = exitintinfo & SVM_EXITINTINFO_VEC_MASK; type = exitintinfo & SVM_EXITINTINFO_TYPE_MASK; + /* + * If NextRIP isn't enabled, KVM must manually advance RIP prior to + * injecting the soft exception/interrupt. That advancement needs to + * be unwound if vectoring didn't complete. Note, the _new_ event may + * not be the injected event, e.g. if KVM injected an INTn, the INTn + * hit a #NP in the guest, and the #NP encountered a #PF, the #NP will + * be the reported vectored event, but RIP still needs to be unwound. + */ + if (int3_injected && type == SVM_EXITINTINFO_TYPE_EXEPT && + kvm_is_linear_rip(vcpu, svm->int3_rip)) + kvm_rip_write(vcpu, kvm_rip_read(vcpu) - int3_injected); + switch (type) { case SVM_EXITINTINFO_TYPE_NMI: vcpu->arch.nmi_injected = true; @@ -3719,16 +3731,11 @@ static void svm_complete_interrupts(struct kvm_vcpu *vcpu) /* * In case of software exceptions, do not reinject the vector, - * but re-execute the instruction instead. Rewind RIP first - * if we emulated INT3 before. + * but re-execute the instruction instead. */ - if (kvm_exception_is_soft(vector)) { - if (vector == BP_VECTOR && int3_injected && - kvm_is_linear_rip(vcpu, svm->int3_rip)) - kvm_rip_write(vcpu, - kvm_rip_read(vcpu) - int3_injected); + if (kvm_exception_is_soft(vector)) break; - } + if (exitintinfo & SVM_EXITINTINFO_VALID_ERR) { u32 err = svm->vmcb->control.exit_int_info_err; kvm_requeue_exception_e(vcpu, vector, err); -- cgit v1.2.3 From 3741aec4c38fa4123ab08ae552f05366d4fd05d8 Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Mon, 2 May 2022 00:07:28 +0200 Subject: KVM: SVM: Stuff next_rip on emulated INT3 injection if NRIPS is supported If NRIPS is supported in hardware but disabled in KVM, set next_rip to the next RIP when advancing RIP as part of emulating INT3 injection. There is no flag to tell the CPU that KVM isn't using next_rip, and so leaving next_rip is left as is will result in the CPU pushing garbage onto the stack when vectoring the injected event. Reviewed-by: Maxim Levitsky Fixes: 66b7138f9136 ("KVM: SVM: Emulate nRIP feature when reinjecting INT3") Signed-off-by: Sean Christopherson Signed-off-by: Maciej S. Szmigiero Message-Id: Signed-off-by: Paolo Bonzini --- arch/x86/kvm/svm/svm.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'arch/x86/kvm/svm/svm.c') diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index c1506069e67c..8c3c6bba6ccd 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -392,6 +392,10 @@ static void svm_queue_exception(struct kvm_vcpu *vcpu) */ (void)svm_skip_emulated_instruction(vcpu); rip = kvm_rip_read(vcpu); + + if (boot_cpu_has(X86_FEATURE_NRIPS)) + svm->vmcb->control.next_rip = rip; + svm->int3_rip = rip + svm->vmcb->save.cs.base; svm->int3_injected = rip - old_rip; } @@ -3709,7 +3713,7 @@ static void svm_complete_interrupts(struct kvm_vcpu *vcpu) /* * If NextRIP isn't enabled, KVM must manually advance RIP prior to * injecting the soft exception/interrupt. That advancement needs to - * be unwound if vectoring didn't complete. Note, the _new_ event may + * be unwound if vectoring didn't complete. Note, the new event may * not be the injected event, e.g. if KVM injected an INTn, the INTn * hit a #NP in the guest, and the #NP encountered a #PF, the #NP will * be the reported vectored event, but RIP still needs to be unwound. -- cgit v1.2.3 From 6ef88d6e36c2b4b3886ec9967cafabe4424d27d5 Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Mon, 2 May 2022 00:07:29 +0200 Subject: KVM: SVM: Re-inject INT3/INTO instead of retrying the instruction Re-inject INT3/INTO instead of retrying the instruction if the CPU encountered an intercepted exception while vectoring the software exception, e.g. if vectoring INT3 encounters a #PF and KVM is using shadow paging. Retrying the instruction is architecturally wrong, e.g. will result in a spurious #DB if there's a code breakpoint on the INT3/O, and lack of re-injection also breaks nested virtualization, e.g. if L1 injects a software exception and vectoring the injected exception encounters an exception that is intercepted by L0 but not L1. Due to, ahem, deficiencies in the SVM architecture, acquiring the next RIP may require flowing through the emulator even if NRIPS is supported, as the CPU clears next_rip if the VM-Exit is due to an exception other than "exceptions caused by the INT3, INTO, and BOUND instructions". To deal with this, "skip" the instruction to calculate next_rip (if it's not already known), and then unwind the RIP write and any side effects (RFLAGS updates). Save the computed next_rip and use it to re-stuff next_rip if injection doesn't complete. This allows KVM to do the right thing if next_rip was known prior to injection, e.g. if L1 injects a soft event into L2, and there is no backing INTn instruction, e.g. if L1 is injecting an arbitrary event. Note, it's impossible to guarantee architectural correctness given SVM's architectural flaws. E.g. if the guest executes INTn (no KVM injection), an exit occurs while vectoring the INTn, and the guest modifies the code stream while the exit is being handled, KVM will compute the incorrect next_rip due to "skipping" the wrong instruction. A future enhancement to make this less awful would be for KVM to detect that the decoded instruction is not the correct INTn and drop the to-be-injected soft event (retrying is a lesser evil compared to shoving the wrong RIP on the exception stack). Reported-by: Maciej S. Szmigiero Signed-off-by: Sean Christopherson Signed-off-by: Maciej S. Szmigiero Message-Id: <65cb88deab40bc1649d509194864312a89bbe02e.1651440202.git.maciej.szmigiero@oracle.com> Signed-off-by: Paolo Bonzini --- arch/x86/kvm/svm/nested.c | 26 +++++++++ arch/x86/kvm/svm/svm.c | 140 ++++++++++++++++++++++++++++++++-------------- arch/x86/kvm/svm/svm.h | 6 +- 3 files changed, 129 insertions(+), 43 deletions(-) (limited to 'arch/x86/kvm/svm/svm.c') diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c index e8aa95a74564..525117a49c18 100644 --- a/arch/x86/kvm/svm/nested.c +++ b/arch/x86/kvm/svm/nested.c @@ -609,6 +609,21 @@ static void nested_vmcb02_prepare_save(struct vcpu_svm *svm, struct vmcb *vmcb12 } } +static inline bool is_evtinj_soft(u32 evtinj) +{ + u32 type = evtinj & SVM_EVTINJ_TYPE_MASK; + u8 vector = evtinj & SVM_EVTINJ_VEC_MASK; + + if (!(evtinj & SVM_EVTINJ_VALID)) + return false; + + /* + * Intentionally return false for SOFT events, SVM doesn't yet support + * re-injecting soft interrupts. + */ + return type == SVM_EVTINJ_TYPE_EXEPT && kvm_exception_is_soft(vector); +} + static void nested_vmcb02_prepare_control(struct vcpu_svm *svm, unsigned long vmcb12_rip) { @@ -677,6 +692,16 @@ static void nested_vmcb02_prepare_control(struct vcpu_svm *svm, else if (boot_cpu_has(X86_FEATURE_NRIPS)) vmcb02->control.next_rip = vmcb12_rip; + if (is_evtinj_soft(vmcb02->control.event_inj)) { + svm->soft_int_injected = true; + svm->soft_int_csbase = svm->vmcb->save.cs.base; + svm->soft_int_old_rip = vmcb12_rip; + if (svm->nrips_enabled) + svm->soft_int_next_rip = svm->nested.ctl.next_rip; + else + svm->soft_int_next_rip = vmcb12_rip; + } + vmcb02->control.virt_ext = vmcb01->control.virt_ext & LBR_CTL_ENABLE_MASK; if (svm->lbrv_enabled) @@ -849,6 +874,7 @@ int nested_svm_vmrun(struct kvm_vcpu *vcpu) out_exit_err: svm->nested.nested_run_pending = 0; + svm->soft_int_injected = false; svm->vmcb->control.exit_code = SVM_EXIT_ERR; svm->vmcb->control.exit_code_hi = 0; diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index 8c3c6bba6ccd..ec37647ca068 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -342,9 +342,11 @@ static void svm_set_interrupt_shadow(struct kvm_vcpu *vcpu, int mask) } -static int svm_skip_emulated_instruction(struct kvm_vcpu *vcpu) +static int __svm_skip_emulated_instruction(struct kvm_vcpu *vcpu, + bool commit_side_effects) { struct vcpu_svm *svm = to_svm(vcpu); + unsigned long old_rflags; /* * SEV-ES does not expose the next RIP. The RIP update is controlled by @@ -359,18 +361,75 @@ static int svm_skip_emulated_instruction(struct kvm_vcpu *vcpu) } if (!svm->next_rip) { + if (unlikely(!commit_side_effects)) + old_rflags = svm->vmcb->save.rflags; + if (!kvm_emulate_instruction(vcpu, EMULTYPE_SKIP)) return 0; + + if (unlikely(!commit_side_effects)) + svm->vmcb->save.rflags = old_rflags; } else { kvm_rip_write(vcpu, svm->next_rip); } done: - svm_set_interrupt_shadow(vcpu, 0); + if (likely(commit_side_effects)) + svm_set_interrupt_shadow(vcpu, 0); return 1; } +static int svm_skip_emulated_instruction(struct kvm_vcpu *vcpu) +{ + return __svm_skip_emulated_instruction(vcpu, true); +} + +static int svm_update_soft_interrupt_rip(struct kvm_vcpu *vcpu) +{ + unsigned long rip, old_rip = kvm_rip_read(vcpu); + struct vcpu_svm *svm = to_svm(vcpu); + + /* + * Due to architectural shortcomings, the CPU doesn't always provide + * NextRIP, e.g. if KVM intercepted an exception that occurred while + * the CPU was vectoring an INTO/INT3 in the guest. Temporarily skip + * the instruction even if NextRIP is supported to acquire the next + * RIP so that it can be shoved into the NextRIP field, otherwise + * hardware will fail to advance guest RIP during event injection. + * Drop the exception/interrupt if emulation fails and effectively + * retry the instruction, it's the least awful option. If NRIPS is + * in use, the skip must not commit any side effects such as clearing + * the interrupt shadow or RFLAGS.RF. + */ + if (!__svm_skip_emulated_instruction(vcpu, !nrips)) + return -EIO; + + rip = kvm_rip_read(vcpu); + + /* + * Save the injection information, even when using next_rip, as the + * VMCB's next_rip will be lost (cleared on VM-Exit) if the injection + * doesn't complete due to a VM-Exit occurring while the CPU is + * vectoring the event. Decoding the instruction isn't guaranteed to + * work as there may be no backing instruction, e.g. if the event is + * being injected by L1 for L2, or if the guest is patching INT3 into + * a different instruction. + */ + svm->soft_int_injected = true; + svm->soft_int_csbase = svm->vmcb->save.cs.base; + svm->soft_int_old_rip = old_rip; + svm->soft_int_next_rip = rip; + + if (nrips) + kvm_rip_write(vcpu, old_rip); + + if (static_cpu_has(X86_FEATURE_NRIPS)) + svm->vmcb->control.next_rip = rip; + + return 0; +} + static void svm_queue_exception(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); @@ -380,25 +439,9 @@ static void svm_queue_exception(struct kvm_vcpu *vcpu) kvm_deliver_exception_payload(vcpu); - if (nr == BP_VECTOR && !nrips) { - unsigned long rip, old_rip = kvm_rip_read(vcpu); - - /* - * For guest debugging where we have to reinject #BP if some - * INT3 is guest-owned: - * Emulate nRIP by moving RIP forward. Will fail if injection - * raises a fault that is not intercepted. Still better than - * failing in all cases. - */ - (void)svm_skip_emulated_instruction(vcpu); - rip = kvm_rip_read(vcpu); - - if (boot_cpu_has(X86_FEATURE_NRIPS)) - svm->vmcb->control.next_rip = rip; - - svm->int3_rip = rip + svm->vmcb->save.cs.base; - svm->int3_injected = rip - old_rip; - } + if (kvm_exception_is_soft(nr) && + svm_update_soft_interrupt_rip(vcpu)) + return; svm->vmcb->control.event_inj = nr | SVM_EVTINJ_VALID @@ -3677,15 +3720,46 @@ static inline void sync_lapic_to_cr8(struct kvm_vcpu *vcpu) svm->vmcb->control.int_ctl |= cr8 & V_TPR_MASK; } +static void svm_complete_soft_interrupt(struct kvm_vcpu *vcpu, u8 vector, + int type) +{ + struct vcpu_svm *svm = to_svm(vcpu); + + /* + * If NRIPS is enabled, KVM must snapshot the pre-VMRUN next_rip that's + * associated with the original soft exception/interrupt. next_rip is + * cleared on all exits that can occur while vectoring an event, so KVM + * needs to manually set next_rip for re-injection. Unlike the !nrips + * case below, this needs to be done if and only if KVM is re-injecting + * the same event, i.e. if the event is a soft exception/interrupt, + * otherwise next_rip is unused on VMRUN. + */ + if (nrips && type == SVM_EXITINTINFO_TYPE_EXEPT && + kvm_exception_is_soft(vector) && + kvm_is_linear_rip(vcpu, svm->soft_int_old_rip + svm->soft_int_csbase)) + svm->vmcb->control.next_rip = svm->soft_int_next_rip; + /* + * If NRIPS isn't enabled, KVM must manually advance RIP prior to + * injecting the soft exception/interrupt. That advancement needs to + * be unwound if vectoring didn't complete. Note, the new event may + * not be the injected event, e.g. if KVM injected an INTn, the INTn + * hit a #NP in the guest, and the #NP encountered a #PF, the #NP will + * be the reported vectored event, but RIP still needs to be unwound. + */ + else if (!nrips && type == SVM_EXITINTINFO_TYPE_EXEPT && + kvm_is_linear_rip(vcpu, svm->soft_int_next_rip + svm->soft_int_csbase)) + kvm_rip_write(vcpu, svm->soft_int_old_rip); +} + static void svm_complete_interrupts(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); u8 vector; int type; u32 exitintinfo = svm->vmcb->control.exit_int_info; - unsigned int3_injected = svm->int3_injected; + bool soft_int_injected = svm->soft_int_injected; - svm->int3_injected = 0; + svm->soft_int_injected = false; /* * If we've made progress since setting HF_IRET_MASK, we've @@ -3710,17 +3784,8 @@ static void svm_complete_interrupts(struct kvm_vcpu *vcpu) vector = exitintinfo & SVM_EXITINTINFO_VEC_MASK; type = exitintinfo & SVM_EXITINTINFO_TYPE_MASK; - /* - * If NextRIP isn't enabled, KVM must manually advance RIP prior to - * injecting the soft exception/interrupt. That advancement needs to - * be unwound if vectoring didn't complete. Note, the new event may - * not be the injected event, e.g. if KVM injected an INTn, the INTn - * hit a #NP in the guest, and the #NP encountered a #PF, the #NP will - * be the reported vectored event, but RIP still needs to be unwound. - */ - if (int3_injected && type == SVM_EXITINTINFO_TYPE_EXEPT && - kvm_is_linear_rip(vcpu, svm->int3_rip)) - kvm_rip_write(vcpu, kvm_rip_read(vcpu) - int3_injected); + if (soft_int_injected) + svm_complete_soft_interrupt(vcpu, vector, type); switch (type) { case SVM_EXITINTINFO_TYPE_NMI: @@ -3733,13 +3798,6 @@ static void svm_complete_interrupts(struct kvm_vcpu *vcpu) if (vector == X86_TRAP_VC) break; - /* - * In case of software exceptions, do not reinject the vector, - * but re-execute the instruction instead. - */ - if (kvm_exception_is_soft(vector)) - break; - if (exitintinfo & SVM_EXITINTINFO_VALID_ERR) { u32 err = svm->vmcb->control.exit_int_info_err; kvm_requeue_exception_e(vcpu, vector, err); diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h index de076d658390..f0b6111ee5b1 100644 --- a/arch/x86/kvm/svm/svm.h +++ b/arch/x86/kvm/svm/svm.h @@ -230,8 +230,10 @@ struct vcpu_svm { bool nmi_singlestep; u64 nmi_singlestep_guest_rflags; - unsigned int3_injected; - unsigned long int3_rip; + unsigned long soft_int_csbase; + unsigned long soft_int_old_rip; + unsigned long soft_int_next_rip; + bool soft_int_injected; /* optional nested SVM features that are enabled for this guest */ bool nrips_enabled : 1; -- cgit v1.2.3 From 7e5b5ef8dca3229a5226eabf53bdc7b67ebd07ad Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Mon, 2 May 2022 00:07:30 +0200 Subject: KVM: SVM: Re-inject INTn instead of retrying the insn on "failure" Re-inject INTn software interrupts instead of retrying the instruction if the CPU encountered an intercepted exception while vectoring the INTn, e.g. if KVM intercepted a #PF when utilizing shadow paging. Retrying the instruction is architecturally wrong e.g. will result in a spurious #DB if there's a code breakpoint on the INT3/O, and lack of re-injection also breaks nested virtualization, e.g. if L1 injects a software interrupt and vectoring the injected interrupt encounters an exception that is intercepted by L0 but not L1. Signed-off-by: Sean Christopherson Signed-off-by: Maciej S. Szmigiero Message-Id: <1654ad502f860948e4f2d57b8bd881d67301f785.1651440202.git.maciej.szmigiero@oracle.com> Signed-off-by: Paolo Bonzini --- arch/x86/kvm/svm/nested.c | 7 +++---- arch/x86/kvm/svm/svm.c | 23 +++++++++++++++++++---- 2 files changed, 22 insertions(+), 8 deletions(-) (limited to 'arch/x86/kvm/svm/svm.c') diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c index 525117a49c18..0d25dea40796 100644 --- a/arch/x86/kvm/svm/nested.c +++ b/arch/x86/kvm/svm/nested.c @@ -617,10 +617,9 @@ static inline bool is_evtinj_soft(u32 evtinj) if (!(evtinj & SVM_EVTINJ_VALID)) return false; - /* - * Intentionally return false for SOFT events, SVM doesn't yet support - * re-injecting soft interrupts. - */ + if (type == SVM_EVTINJ_TYPE_SOFT) + return true; + return type == SVM_EVTINJ_TYPE_EXEPT && kvm_exception_is_soft(vector); } diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index ec37647ca068..6248967d4a77 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -3438,12 +3438,22 @@ static void svm_inject_nmi(struct kvm_vcpu *vcpu) static void svm_inject_irq(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); + u32 type; + + if (vcpu->arch.interrupt.soft) { + if (svm_update_soft_interrupt_rip(vcpu)) + return; + + type = SVM_EVTINJ_TYPE_SOFT; + } else { + type = SVM_EVTINJ_TYPE_INTR; + } trace_kvm_inj_virq(vcpu->arch.interrupt.nr); ++vcpu->stat.irq_injections; svm->vmcb->control.event_inj = vcpu->arch.interrupt.nr | - SVM_EVTINJ_VALID | SVM_EVTINJ_TYPE_INTR; + SVM_EVTINJ_VALID | type; } void svm_complete_interrupt_delivery(struct kvm_vcpu *vcpu, int delivery_mode, @@ -3723,6 +3733,8 @@ static inline void sync_lapic_to_cr8(struct kvm_vcpu *vcpu) static void svm_complete_soft_interrupt(struct kvm_vcpu *vcpu, u8 vector, int type) { + bool is_exception = (type == SVM_EXITINTINFO_TYPE_EXEPT); + bool is_soft = (type == SVM_EXITINTINFO_TYPE_SOFT); struct vcpu_svm *svm = to_svm(vcpu); /* @@ -3734,8 +3746,7 @@ static void svm_complete_soft_interrupt(struct kvm_vcpu *vcpu, u8 vector, * the same event, i.e. if the event is a soft exception/interrupt, * otherwise next_rip is unused on VMRUN. */ - if (nrips && type == SVM_EXITINTINFO_TYPE_EXEPT && - kvm_exception_is_soft(vector) && + if (nrips && (is_soft || (is_exception && kvm_exception_is_soft(vector))) && kvm_is_linear_rip(vcpu, svm->soft_int_old_rip + svm->soft_int_csbase)) svm->vmcb->control.next_rip = svm->soft_int_next_rip; /* @@ -3746,7 +3757,7 @@ static void svm_complete_soft_interrupt(struct kvm_vcpu *vcpu, u8 vector, * hit a #NP in the guest, and the #NP encountered a #PF, the #NP will * be the reported vectored event, but RIP still needs to be unwound. */ - else if (!nrips && type == SVM_EXITINTINFO_TYPE_EXEPT && + else if (!nrips && (is_soft || is_exception) && kvm_is_linear_rip(vcpu, svm->soft_int_next_rip + svm->soft_int_csbase)) kvm_rip_write(vcpu, svm->soft_int_old_rip); } @@ -3808,9 +3819,13 @@ static void svm_complete_interrupts(struct kvm_vcpu *vcpu) case SVM_EXITINTINFO_TYPE_INTR: kvm_queue_interrupt(vcpu, vector, false); break; + case SVM_EXITINTINFO_TYPE_SOFT: + kvm_queue_interrupt(vcpu, vector, true); + break; default: break; } + } static void svm_cancel_injection(struct kvm_vcpu *vcpu) -- cgit v1.2.3 From 2d61391270a3ceb95b3dd536ea13002e653323b6 Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Mon, 2 May 2022 00:07:33 +0200 Subject: KVM: x86: Differentiate Soft vs. Hard IRQs vs. reinjected in tracepoint In the IRQ injection tracepoint, differentiate between Hard IRQs and Soft "IRQs", i.e. interrupts that are reinjected after incomplete delivery of a software interrupt from an INTn instruction. Tag reinjected interrupts as such, even though the information is usually redundant since soft interrupts are only ever reinjected by KVM. Though rare in practice, a hard IRQ can be reinjected. Signed-off-by: Sean Christopherson [MSS: change "kvm_inj_virq" event "reinjected" field type to bool] Signed-off-by: Maciej S. Szmigiero Message-Id: <9664d49b3bd21e227caa501cff77b0569bebffe2.1651440202.git.maciej.szmigiero@oracle.com> Signed-off-by: Paolo Bonzini --- arch/x86/include/asm/kvm_host.h | 2 +- arch/x86/kvm/svm/svm.c | 5 +++-- arch/x86/kvm/trace.h | 16 +++++++++++----- arch/x86/kvm/vmx/vmx.c | 4 ++-- arch/x86/kvm/x86.c | 4 ++-- 5 files changed, 19 insertions(+), 12 deletions(-) (limited to 'arch/x86/kvm/svm/svm.c') diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 959d66b9be94..8109805b5429 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -1405,7 +1405,7 @@ struct kvm_x86_ops { u32 (*get_interrupt_shadow)(struct kvm_vcpu *vcpu); void (*patch_hypercall)(struct kvm_vcpu *vcpu, unsigned char *hypercall_addr); - void (*inject_irq)(struct kvm_vcpu *vcpu); + void (*inject_irq)(struct kvm_vcpu *vcpu, bool reinjected); void (*inject_nmi)(struct kvm_vcpu *vcpu); void (*queue_exception)(struct kvm_vcpu *vcpu); void (*cancel_injection)(struct kvm_vcpu *vcpu); diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index 6248967d4a77..0f4d38e5ceab 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -3435,7 +3435,7 @@ static void svm_inject_nmi(struct kvm_vcpu *vcpu) ++vcpu->stat.nmi_injections; } -static void svm_inject_irq(struct kvm_vcpu *vcpu) +static void svm_inject_irq(struct kvm_vcpu *vcpu, bool reinjected) { struct vcpu_svm *svm = to_svm(vcpu); u32 type; @@ -3449,7 +3449,8 @@ static void svm_inject_irq(struct kvm_vcpu *vcpu) type = SVM_EVTINJ_TYPE_INTR; } - trace_kvm_inj_virq(vcpu->arch.interrupt.nr); + trace_kvm_inj_virq(vcpu->arch.interrupt.nr, + vcpu->arch.interrupt.soft, reinjected); ++vcpu->stat.irq_injections; svm->vmcb->control.event_inj = vcpu->arch.interrupt.nr | diff --git a/arch/x86/kvm/trace.h b/arch/x86/kvm/trace.h index 385436d12024..fd28dd40b813 100644 --- a/arch/x86/kvm/trace.h +++ b/arch/x86/kvm/trace.h @@ -333,18 +333,24 @@ TRACE_EVENT_KVM_EXIT(kvm_exit); * Tracepoint for kvm interrupt injection: */ TRACE_EVENT(kvm_inj_virq, - TP_PROTO(unsigned int irq), - TP_ARGS(irq), + TP_PROTO(unsigned int vector, bool soft, bool reinjected), + TP_ARGS(vector, soft, reinjected), TP_STRUCT__entry( - __field( unsigned int, irq ) + __field( unsigned int, vector ) + __field( bool, soft ) + __field( bool, reinjected ) ), TP_fast_assign( - __entry->irq = irq; + __entry->vector = vector; + __entry->soft = soft; + __entry->reinjected = reinjected; ), - TP_printk("irq %u", __entry->irq) + TP_printk("%s 0x%x%s", + __entry->soft ? "Soft/INTn" : "IRQ", __entry->vector, + __entry->reinjected ? " [reinjected]" : "") ); #define EXS(x) { x##_VECTOR, "#" #x } diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index e1aa14743cdb..9714ae95589f 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -4573,13 +4573,13 @@ static void vmx_enable_nmi_window(struct kvm_vcpu *vcpu) exec_controls_setbit(to_vmx(vcpu), CPU_BASED_NMI_WINDOW_EXITING); } -static void vmx_inject_irq(struct kvm_vcpu *vcpu) +static void vmx_inject_irq(struct kvm_vcpu *vcpu, bool reinjected) { struct vcpu_vmx *vmx = to_vmx(vcpu); uint32_t intr; int irq = vcpu->arch.interrupt.nr; - trace_kvm_inj_virq(irq); + trace_kvm_inj_virq(irq, vcpu->arch.interrupt.soft, reinjected); ++vcpu->stat.irq_injections; if (vmx->rmode.vm86_active) { diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index c9f3ad89bf4c..501606e02688 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -9448,7 +9448,7 @@ static int inject_pending_event(struct kvm_vcpu *vcpu, bool *req_immediate_exit) static_call(kvm_x86_inject_nmi)(vcpu); can_inject = false; } else if (vcpu->arch.interrupt.injected) { - static_call(kvm_x86_inject_irq)(vcpu); + static_call(kvm_x86_inject_irq)(vcpu, true); can_inject = false; } } @@ -9539,7 +9539,7 @@ static int inject_pending_event(struct kvm_vcpu *vcpu, bool *req_immediate_exit) goto out; if (r) { kvm_queue_interrupt(vcpu, kvm_cpu_get_interrupt(vcpu), false); - static_call(kvm_x86_inject_irq)(vcpu); + static_call(kvm_x86_inject_irq)(vcpu, false); WARN_ON(static_call(kvm_x86_interrupt_allowed)(vcpu, true) < 0); } if (kvm_cpu_has_injectable_intr(vcpu)) -- cgit v1.2.3 From 159fc6fa3b7db24db85598115cc43dc47196919e Mon Sep 17 00:00:00 2001 From: "Maciej S. Szmigiero" Date: Mon, 2 May 2022 00:07:34 +0200 Subject: KVM: nSVM: Transparently handle L1 -> L2 NMI re-injection A NMI that L1 wants to inject into its L2 should be directly re-injected, without causing L0 side effects like engaging NMI blocking for L1. It's also worth noting that in this case it is L1 responsibility to track the NMI window status for its L2 guest. Signed-off-by: Maciej S. Szmigiero Message-Id: Signed-off-by: Paolo Bonzini --- arch/x86/kvm/svm/nested.c | 12 ++++++++++++ arch/x86/kvm/svm/svm.c | 7 +++++++ arch/x86/kvm/svm/svm.h | 1 + 3 files changed, 20 insertions(+) (limited to 'arch/x86/kvm/svm/svm.c') diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c index 0d25dea40796..688f86b9202a 100644 --- a/arch/x86/kvm/svm/nested.c +++ b/arch/x86/kvm/svm/nested.c @@ -623,6 +623,16 @@ static inline bool is_evtinj_soft(u32 evtinj) return type == SVM_EVTINJ_TYPE_EXEPT && kvm_exception_is_soft(vector); } +static bool is_evtinj_nmi(u32 evtinj) +{ + u32 type = evtinj & SVM_EVTINJ_TYPE_MASK; + + if (!(evtinj & SVM_EVTINJ_VALID)) + return false; + + return type == SVM_EVTINJ_TYPE_NMI; +} + static void nested_vmcb02_prepare_control(struct vcpu_svm *svm, unsigned long vmcb12_rip) { @@ -691,6 +701,7 @@ static void nested_vmcb02_prepare_control(struct vcpu_svm *svm, else if (boot_cpu_has(X86_FEATURE_NRIPS)) vmcb02->control.next_rip = vmcb12_rip; + svm->nmi_l1_to_l2 = is_evtinj_nmi(vmcb02->control.event_inj); if (is_evtinj_soft(vmcb02->control.event_inj)) { svm->soft_int_injected = true; svm->soft_int_csbase = svm->vmcb->save.cs.base; @@ -873,6 +884,7 @@ int nested_svm_vmrun(struct kvm_vcpu *vcpu) out_exit_err: svm->nested.nested_run_pending = 0; + svm->nmi_l1_to_l2 = false; svm->soft_int_injected = false; svm->vmcb->control.exit_code = SVM_EXIT_ERR; diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index 0f4d38e5ceab..5fda7e7102f2 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -3429,6 +3429,10 @@ static void svm_inject_nmi(struct kvm_vcpu *vcpu) struct vcpu_svm *svm = to_svm(vcpu); svm->vmcb->control.event_inj = SVM_EVTINJ_VALID | SVM_EVTINJ_TYPE_NMI; + + if (svm->nmi_l1_to_l2) + return; + vcpu->arch.hflags |= HF_NMI_MASK; if (!sev_es_guest(vcpu->kvm)) svm_set_intercept(svm, INTERCEPT_IRET); @@ -3769,8 +3773,10 @@ static void svm_complete_interrupts(struct kvm_vcpu *vcpu) u8 vector; int type; u32 exitintinfo = svm->vmcb->control.exit_int_info; + bool nmi_l1_to_l2 = svm->nmi_l1_to_l2; bool soft_int_injected = svm->soft_int_injected; + svm->nmi_l1_to_l2 = false; svm->soft_int_injected = false; /* @@ -3802,6 +3808,7 @@ static void svm_complete_interrupts(struct kvm_vcpu *vcpu) switch (type) { case SVM_EXITINTINFO_TYPE_NMI: vcpu->arch.nmi_injected = true; + svm->nmi_l1_to_l2 = nmi_l1_to_l2; break; case SVM_EXITINTINFO_TYPE_EXEPT: /* diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h index f0b6111ee5b1..24b5c73a8c87 100644 --- a/arch/x86/kvm/svm/svm.h +++ b/arch/x86/kvm/svm/svm.h @@ -229,6 +229,7 @@ struct vcpu_svm { bool nmi_singlestep; u64 nmi_singlestep_guest_rflags; + bool nmi_l1_to_l2; unsigned long soft_int_csbase; unsigned long soft_int_old_rip; -- cgit v1.2.3 From 938c8745bcf2f732ee928a0b9bd592198a88cfa4 Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Tue, 24 May 2022 21:56:23 +0800 Subject: KVM: x86: Introduce "struct kvm_caps" to track misc caps/settings Add kvm_caps to hold a variety of capabilites and defaults that aren't handled by kvm_cpu_caps because they aren't CPUID bits in order to reduce the amount of boilerplate code required to add a new feature. The vast majority (all?) of the caps interact with vendor code and are written only during initialization, i.e. should be tagged __read_mostly, declared extern in x86.h, and exported. No functional change intended. Signed-off-by: Sean Christopherson Message-Id: <20220524135624.22988-4-chenyi.qiang@intel.com> Signed-off-by: Paolo Bonzini --- arch/x86/include/asm/kvm_host.h | 15 ------- arch/x86/kvm/cpuid.c | 8 ++-- arch/x86/kvm/debugfs.c | 4 +- arch/x86/kvm/lapic.c | 2 +- arch/x86/kvm/svm/nested.c | 4 +- arch/x86/kvm/svm/svm.c | 13 +++--- arch/x86/kvm/vmx/nested.c | 4 +- arch/x86/kvm/vmx/vmx.c | 22 +++++----- arch/x86/kvm/x86.c | 97 ++++++++++++++++++----------------------- arch/x86/kvm/x86.h | 26 +++++++++-- 10 files changed, 94 insertions(+), 101 deletions(-) (limited to 'arch/x86/kvm/svm/svm.c') diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index d6c62276e131..4e00bca08cfa 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -1664,21 +1664,6 @@ extern bool tdp_enabled; u64 vcpu_tsc_khz(struct kvm_vcpu *vcpu); -/* control of guest tsc rate supported? */ -extern bool kvm_has_tsc_control; -/* maximum supported tsc_khz for guests */ -extern u32 kvm_max_guest_tsc_khz; -/* number of bits of the fractional part of the TSC scaling ratio */ -extern u8 kvm_tsc_scaling_ratio_frac_bits; -/* maximum allowed value of TSC scaling ratio */ -extern u64 kvm_max_tsc_scaling_ratio; -/* 1ull << kvm_tsc_scaling_ratio_frac_bits */ -extern u64 kvm_default_tsc_scaling_ratio; -/* bus lock detection supported? */ -extern bool kvm_has_bus_lock_exit; - -extern u64 kvm_mce_cap_supported; - /* * EMULTYPE_NO_DECODE - Set when re-emulating an instruction (after completing * userspace I/O) to indicate that the emulation context diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index 211f4566641e..d47222ab8e6e 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -200,7 +200,7 @@ void kvm_update_pv_runtime(struct kvm_vcpu *vcpu) /* * Calculate guest's supported XCR0 taking into account guest CPUID data and - * supported_xcr0 (comprised of host configuration and KVM_SUPPORTED_XCR0). + * KVM's supported XCR0 (comprised of host's XCR0 and KVM_SUPPORTED_XCR0). */ static u64 cpuid_get_supported_xcr0(struct kvm_cpuid_entry2 *entries, int nent) { @@ -210,7 +210,7 @@ static u64 cpuid_get_supported_xcr0(struct kvm_cpuid_entry2 *entries, int nent) if (!best) return 0; - return (best->eax | ((u64)best->edx << 32)) & supported_xcr0; + return (best->eax | ((u64)best->edx << 32)) & kvm_caps.supported_xcr0; } static void __kvm_update_cpuid_runtime(struct kvm_vcpu *vcpu, struct kvm_cpuid_entry2 *entries, @@ -912,8 +912,8 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function) } break; case 0xd: { - u64 permitted_xcr0 = supported_xcr0 & xstate_get_guest_group_perm(); - u64 permitted_xss = supported_xss; + u64 permitted_xcr0 = kvm_caps.supported_xcr0 & xstate_get_guest_group_perm(); + u64 permitted_xss = kvm_caps.supported_xss; entry->eax &= permitted_xcr0; entry->ebx = xstate_required_size(permitted_xcr0, false); diff --git a/arch/x86/kvm/debugfs.c b/arch/x86/kvm/debugfs.c index 9240b3b7f8dd..cfed36aba2f7 100644 --- a/arch/x86/kvm/debugfs.c +++ b/arch/x86/kvm/debugfs.c @@ -48,7 +48,7 @@ DEFINE_SIMPLE_ATTRIBUTE(vcpu_tsc_scaling_fops, vcpu_get_tsc_scaling_ratio, NULL, static int vcpu_get_tsc_scaling_frac_bits(void *data, u64 *val) { - *val = kvm_tsc_scaling_ratio_frac_bits; + *val = kvm_caps.tsc_scaling_ratio_frac_bits; return 0; } @@ -66,7 +66,7 @@ void kvm_arch_create_vcpu_debugfs(struct kvm_vcpu *vcpu, struct dentry *debugfs_ debugfs_dentry, vcpu, &vcpu_timer_advance_ns_fops); - if (kvm_has_tsc_control) { + if (kvm_caps.has_tsc_control) { debugfs_create_file("tsc-scaling-ratio", 0444, debugfs_dentry, vcpu, &vcpu_tsc_scaling_fops); diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index 39b805666a18..e69b83708f05 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -1603,7 +1603,7 @@ static inline void __wait_lapic_expire(struct kvm_vcpu *vcpu, u64 guest_cycles) * that __delay() uses delay_tsc whenever the hardware has TSC, thus * always for VMX enabled hardware. */ - if (vcpu->arch.tsc_scaling_ratio == kvm_default_tsc_scaling_ratio) { + if (vcpu->arch.tsc_scaling_ratio == kvm_caps.default_tsc_scaling_ratio) { __delay(min(guest_cycles, nsec_to_cycles(vcpu, timer_advance_ns))); } else { diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c index 688f86b9202a..f958a656ff29 100644 --- a/arch/x86/kvm/svm/nested.c +++ b/arch/x86/kvm/svm/nested.c @@ -674,7 +674,7 @@ static void nested_vmcb02_prepare_control(struct vcpu_svm *svm, vmcb02->control.tsc_offset = vcpu->arch.tsc_offset; - if (svm->tsc_ratio_msr != kvm_default_tsc_scaling_ratio) { + if (svm->tsc_ratio_msr != kvm_caps.default_tsc_scaling_ratio) { WARN_ON(!svm->tsc_scaling_enabled); nested_svm_update_tsc_ratio_msr(vcpu); } @@ -1031,7 +1031,7 @@ int nested_svm_vmexit(struct vcpu_svm *svm) vmcb_mark_dirty(vmcb01, VMCB_INTERCEPTS); } - if (svm->tsc_ratio_msr != kvm_default_tsc_scaling_ratio) { + if (svm->tsc_ratio_msr != kvm_caps.default_tsc_scaling_ratio) { WARN_ON(!svm->tsc_scaling_enabled); vcpu->arch.tsc_scaling_ratio = vcpu->arch.l1_tsc_scaling_ratio; __svm_write_tsc_multiplier(vcpu->arch.tsc_scaling_ratio); diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index 5fda7e7102f2..750933ca6b9f 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -1285,7 +1285,7 @@ static void __svm_vcpu_reset(struct kvm_vcpu *vcpu) svm_init_osvw(vcpu); vcpu->arch.microcode_version = 0x01000065; - svm->tsc_ratio_msr = kvm_default_tsc_scaling_ratio; + svm->tsc_ratio_msr = kvm_caps.default_tsc_scaling_ratio; if (sev_es_guest(vcpu->kvm)) sev_es_vcpu_reset(svm); @@ -4868,7 +4868,7 @@ static __init void svm_set_cpu_caps(void) { kvm_set_cpu_caps(); - supported_xss = 0; + kvm_caps.supported_xss = 0; /* CPUID 0x80000001 and 0x8000000A (SVM features) */ if (nested) { @@ -4944,7 +4944,8 @@ static __init int svm_hardware_setup(void) init_msrpm_offsets(); - supported_xcr0 &= ~(XFEATURE_MASK_BNDREGS | XFEATURE_MASK_BNDCSR); + kvm_caps.supported_xcr0 &= ~(XFEATURE_MASK_BNDREGS | + XFEATURE_MASK_BNDCSR); if (boot_cpu_has(X86_FEATURE_FXSR_OPT)) kvm_enable_efer_bits(EFER_FFXSR); @@ -4954,11 +4955,11 @@ static __init int svm_hardware_setup(void) tsc_scaling = false; } else { pr_info("TSC scaling supported\n"); - kvm_has_tsc_control = true; + kvm_caps.has_tsc_control = true; } } - kvm_max_tsc_scaling_ratio = SVM_TSC_RATIO_MAX; - kvm_tsc_scaling_ratio_frac_bits = 32; + kvm_caps.max_tsc_scaling_ratio = SVM_TSC_RATIO_MAX; + kvm_caps.tsc_scaling_ratio_frac_bits = 32; tsc_aux_uret_slot = kvm_add_user_return_msr(MSR_TSC_AUX); diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c index f5cb18e00e78..5c5f4e3762f5 100644 --- a/arch/x86/kvm/vmx/nested.c +++ b/arch/x86/kvm/vmx/nested.c @@ -2548,7 +2548,7 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, vmx_get_l2_tsc_multiplier(vcpu)); vmcs_write64(TSC_OFFSET, vcpu->arch.tsc_offset); - if (kvm_has_tsc_control) + if (kvm_caps.has_tsc_control) vmcs_write64(TSC_MULTIPLIER, vcpu->arch.tsc_scaling_ratio); nested_vmx_transition_tlb_flush(vcpu, vmcs12, true); @@ -4610,7 +4610,7 @@ void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 vm_exit_reason, vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, vmx->msr_autoload.host.nr); vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, vmx->msr_autoload.guest.nr); vmcs_write64(TSC_OFFSET, vcpu->arch.tsc_offset); - if (kvm_has_tsc_control) + if (kvm_caps.has_tsc_control) vmcs_write64(TSC_MULTIPLIER, vcpu->arch.tsc_scaling_ratio); if (vmx->nested.l1_tpr_threshold != -1) diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index 55a8578255cb..6d631941ac1a 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -1717,7 +1717,7 @@ u64 vmx_get_l2_tsc_multiplier(struct kvm_vcpu *vcpu) nested_cpu_has2(vmcs12, SECONDARY_EXEC_TSC_SCALING)) return vmcs12->tsc_multiplier; - return kvm_default_tsc_scaling_ratio; + return kvm_caps.default_tsc_scaling_ratio; } static void vmx_write_tsc_offset(struct kvm_vcpu *vcpu, u64 offset) @@ -7544,7 +7544,7 @@ static __init void vmx_set_cpu_caps(void) kvm_cpu_cap_set(X86_FEATURE_UMIP); /* CPUID 0xD.1 */ - supported_xss = 0; + kvm_caps.supported_xss = 0; if (!cpu_has_vmx_xsaves()) kvm_cpu_cap_clear(X86_FEATURE_XSAVES); @@ -7685,9 +7685,9 @@ static int vmx_set_hv_timer(struct kvm_vcpu *vcpu, u64 guest_deadline_tsc, delta_tsc = 0; /* Convert to host delta tsc if tsc scaling is enabled */ - if (vcpu->arch.l1_tsc_scaling_ratio != kvm_default_tsc_scaling_ratio && + if (vcpu->arch.l1_tsc_scaling_ratio != kvm_caps.default_tsc_scaling_ratio && delta_tsc && u64_shl_div_u64(delta_tsc, - kvm_tsc_scaling_ratio_frac_bits, + kvm_caps.tsc_scaling_ratio_frac_bits, vcpu->arch.l1_tsc_scaling_ratio, &delta_tsc)) return -ERANGE; @@ -8064,8 +8064,8 @@ static __init int hardware_setup(void) } if (!cpu_has_vmx_mpx()) - supported_xcr0 &= ~(XFEATURE_MASK_BNDREGS | - XFEATURE_MASK_BNDCSR); + kvm_caps.supported_xcr0 &= ~(XFEATURE_MASK_BNDREGS | + XFEATURE_MASK_BNDCSR); if (!cpu_has_vmx_vpid() || !cpu_has_vmx_invvpid() || !(cpu_has_vmx_invvpid_single() || cpu_has_vmx_invvpid_global())) @@ -8132,11 +8132,11 @@ static __init int hardware_setup(void) enable_ipiv = false; if (cpu_has_vmx_tsc_scaling()) - kvm_has_tsc_control = true; + kvm_caps.has_tsc_control = true; - kvm_max_tsc_scaling_ratio = KVM_VMX_TSC_MULTIPLIER_MAX; - kvm_tsc_scaling_ratio_frac_bits = 48; - kvm_has_bus_lock_exit = cpu_has_vmx_bus_lock_detection(); + kvm_caps.max_tsc_scaling_ratio = KVM_VMX_TSC_MULTIPLIER_MAX; + kvm_caps.tsc_scaling_ratio_frac_bits = 48; + kvm_caps.has_bus_lock_exit = cpu_has_vmx_bus_lock_detection(); set_bit(0, vmx_vpid_bitmap); /* 0 is reserved for host */ @@ -8193,7 +8193,7 @@ static __init int hardware_setup(void) vmx_x86_ops.request_immediate_exit = __kvm_request_immediate_exit; } - kvm_mce_cap_supported |= MCG_LMCE_P; + kvm_caps.supported_mce_cap |= MCG_LMCE_P; if (pt_mode != PT_MODE_SYSTEM && pt_mode != PT_MODE_HOST_GUEST) return -EINVAL; diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 422fbb0d7518..53e5f2ad2422 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -87,8 +87,11 @@ #define MAX_IO_MSRS 256 #define KVM_MAX_MCE_BANKS 32 -u64 __read_mostly kvm_mce_cap_supported = MCG_CTL_P | MCG_SER_P; -EXPORT_SYMBOL_GPL(kvm_mce_cap_supported); + +struct kvm_caps kvm_caps __read_mostly = { + .supported_mce_cap = MCG_CTL_P | MCG_SER_P, +}; +EXPORT_SYMBOL_GPL(kvm_caps); #define ERR_PTR_USR(e) ((void __user *)ERR_PTR(e)) @@ -151,19 +154,6 @@ module_param(min_timer_period_us, uint, S_IRUGO | S_IWUSR); static bool __read_mostly kvmclock_periodic_sync = true; module_param(kvmclock_periodic_sync, bool, S_IRUGO); -bool __read_mostly kvm_has_tsc_control; -EXPORT_SYMBOL_GPL(kvm_has_tsc_control); -u32 __read_mostly kvm_max_guest_tsc_khz; -EXPORT_SYMBOL_GPL(kvm_max_guest_tsc_khz); -u8 __read_mostly kvm_tsc_scaling_ratio_frac_bits; -EXPORT_SYMBOL_GPL(kvm_tsc_scaling_ratio_frac_bits); -u64 __read_mostly kvm_max_tsc_scaling_ratio; -EXPORT_SYMBOL_GPL(kvm_max_tsc_scaling_ratio); -u64 __read_mostly kvm_default_tsc_scaling_ratio; -EXPORT_SYMBOL_GPL(kvm_default_tsc_scaling_ratio); -bool __read_mostly kvm_has_bus_lock_exit; -EXPORT_SYMBOL_GPL(kvm_has_bus_lock_exit); - /* tsc tolerance in parts per million - default to 1/2 of the NTP threshold */ static u32 __read_mostly tsc_tolerance_ppm = 250; module_param(tsc_tolerance_ppm, uint, S_IRUGO | S_IWUSR); @@ -235,8 +225,6 @@ EXPORT_SYMBOL_GPL(enable_apicv); u64 __read_mostly host_xss; EXPORT_SYMBOL_GPL(host_xss); -u64 __read_mostly supported_xss; -EXPORT_SYMBOL_GPL(supported_xss); const struct _kvm_stats_desc kvm_vm_stats_desc[] = { KVM_GENERIC_VM_STATS(), @@ -309,8 +297,6 @@ const struct kvm_stats_header kvm_vcpu_stats_header = { }; u64 __read_mostly host_xcr0; -u64 __read_mostly supported_xcr0; -EXPORT_SYMBOL_GPL(supported_xcr0); static struct kmem_cache *x86_emulator_cache; @@ -2345,12 +2331,12 @@ static int set_tsc_khz(struct kvm_vcpu *vcpu, u32 user_tsc_khz, bool scale) /* Guest TSC same frequency as host TSC? */ if (!scale) { - kvm_vcpu_write_tsc_multiplier(vcpu, kvm_default_tsc_scaling_ratio); + kvm_vcpu_write_tsc_multiplier(vcpu, kvm_caps.default_tsc_scaling_ratio); return 0; } /* TSC scaling supported? */ - if (!kvm_has_tsc_control) { + if (!kvm_caps.has_tsc_control) { if (user_tsc_khz > tsc_khz) { vcpu->arch.tsc_catchup = 1; vcpu->arch.tsc_always_catchup = 1; @@ -2362,10 +2348,10 @@ static int set_tsc_khz(struct kvm_vcpu *vcpu, u32 user_tsc_khz, bool scale) } /* TSC scaling required - calculate ratio */ - ratio = mul_u64_u32_div(1ULL << kvm_tsc_scaling_ratio_frac_bits, + ratio = mul_u64_u32_div(1ULL << kvm_caps.tsc_scaling_ratio_frac_bits, user_tsc_khz, tsc_khz); - if (ratio == 0 || ratio >= kvm_max_tsc_scaling_ratio) { + if (ratio == 0 || ratio >= kvm_caps.max_tsc_scaling_ratio) { pr_warn_ratelimited("Invalid TSC scaling ratio - virtual-tsc-khz=%u\n", user_tsc_khz); return -1; @@ -2383,7 +2369,7 @@ static int kvm_set_tsc_khz(struct kvm_vcpu *vcpu, u32 user_tsc_khz) /* tsc_khz can be zero if TSC calibration fails */ if (user_tsc_khz == 0) { /* set tsc_scaling_ratio to a safe value */ - kvm_vcpu_write_tsc_multiplier(vcpu, kvm_default_tsc_scaling_ratio); + kvm_vcpu_write_tsc_multiplier(vcpu, kvm_caps.default_tsc_scaling_ratio); return -1; } @@ -2460,18 +2446,18 @@ static void kvm_track_tsc_matching(struct kvm_vcpu *vcpu) * (frac) represent the fractional part, ie. ratio represents a fixed * point number (mult + frac * 2^(-N)). * - * N equals to kvm_tsc_scaling_ratio_frac_bits. + * N equals to kvm_caps.tsc_scaling_ratio_frac_bits. */ static inline u64 __scale_tsc(u64 ratio, u64 tsc) { - return mul_u64_u64_shr(tsc, ratio, kvm_tsc_scaling_ratio_frac_bits); + return mul_u64_u64_shr(tsc, ratio, kvm_caps.tsc_scaling_ratio_frac_bits); } u64 kvm_scale_tsc(u64 tsc, u64 ratio) { u64 _tsc = tsc; - if (ratio != kvm_default_tsc_scaling_ratio) + if (ratio != kvm_caps.default_tsc_scaling_ratio) _tsc = __scale_tsc(ratio, tsc); return _tsc; @@ -2498,11 +2484,11 @@ u64 kvm_calc_nested_tsc_offset(u64 l1_offset, u64 l2_offset, u64 l2_multiplier) { u64 nested_offset; - if (l2_multiplier == kvm_default_tsc_scaling_ratio) + if (l2_multiplier == kvm_caps.default_tsc_scaling_ratio) nested_offset = l1_offset; else nested_offset = mul_s64_u64_shr((s64) l1_offset, l2_multiplier, - kvm_tsc_scaling_ratio_frac_bits); + kvm_caps.tsc_scaling_ratio_frac_bits); nested_offset += l2_offset; return nested_offset; @@ -2511,9 +2497,9 @@ EXPORT_SYMBOL_GPL(kvm_calc_nested_tsc_offset); u64 kvm_calc_nested_tsc_multiplier(u64 l1_multiplier, u64 l2_multiplier) { - if (l2_multiplier != kvm_default_tsc_scaling_ratio) + if (l2_multiplier != kvm_caps.default_tsc_scaling_ratio) return mul_u64_u64_shr(l1_multiplier, l2_multiplier, - kvm_tsc_scaling_ratio_frac_bits); + kvm_caps.tsc_scaling_ratio_frac_bits); return l1_multiplier; } @@ -2555,7 +2541,7 @@ static void kvm_vcpu_write_tsc_multiplier(struct kvm_vcpu *vcpu, u64 l1_multipli else vcpu->arch.tsc_scaling_ratio = l1_multiplier; - if (kvm_has_tsc_control) + if (kvm_caps.has_tsc_control) static_call(kvm_x86_write_tsc_multiplier)( vcpu, vcpu->arch.tsc_scaling_ratio); } @@ -2691,7 +2677,7 @@ static inline void adjust_tsc_offset_guest(struct kvm_vcpu *vcpu, static inline void adjust_tsc_offset_host(struct kvm_vcpu *vcpu, s64 adjustment) { - if (vcpu->arch.l1_tsc_scaling_ratio != kvm_default_tsc_scaling_ratio) + if (vcpu->arch.l1_tsc_scaling_ratio != kvm_caps.default_tsc_scaling_ratio) WARN_ON(adjustment < 0); adjustment = kvm_scale_tsc((u64) adjustment, vcpu->arch.l1_tsc_scaling_ratio); @@ -3104,7 +3090,7 @@ static int kvm_guest_time_update(struct kvm_vcpu *v) /* With all the info we got, fill in the values */ - if (kvm_has_tsc_control) + if (kvm_caps.has_tsc_control) tgt_tsc_khz = kvm_scale_tsc(tgt_tsc_khz, v->arch.l1_tsc_scaling_ratio); @@ -3613,7 +3599,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) * IA32_XSS[bit 8]. Guests have to use RDMSR/WRMSR rather than * XSAVES/XRSTORS to save/restore PT MSRs. */ - if (data & ~supported_xss) + if (data & ~kvm_caps.supported_xss) return 1; vcpu->arch.ia32_xss = data; kvm_update_cpuid_runtime(vcpu); @@ -4374,7 +4360,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) break; case KVM_CAP_TSC_CONTROL: case KVM_CAP_VM_TSC_CONTROL: - r = kvm_has_tsc_control; + r = kvm_caps.has_tsc_control; break; case KVM_CAP_X2APIC_API: r = KVM_X2APIC_API_VALID_FLAGS; @@ -4396,7 +4382,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) r = sched_info_on(); break; case KVM_CAP_X86_BUS_LOCK_EXIT: - if (kvm_has_bus_lock_exit) + if (kvm_caps.has_bus_lock_exit) r = KVM_BUS_LOCK_DETECTION_OFF | KVM_BUS_LOCK_DETECTION_EXIT; else @@ -4405,7 +4391,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_XSAVE2: { u64 guest_perm = xstate_get_guest_group_perm(); - r = xstate_required_size(supported_xcr0 & guest_perm, false); + r = xstate_required_size(kvm_caps.supported_xcr0 & guest_perm, false); if (r < sizeof(struct kvm_xsave)) r = sizeof(struct kvm_xsave); break; @@ -4443,7 +4429,7 @@ static int kvm_x86_dev_get_attr(struct kvm_device_attr *attr) switch (attr->attr) { case KVM_X86_XCOMP_GUEST_SUPP: - if (put_user(supported_xcr0, uaddr)) + if (put_user(kvm_caps.supported_xcr0, uaddr)) return -EFAULT; return 0; default: @@ -4520,8 +4506,8 @@ long kvm_arch_dev_ioctl(struct file *filp, } case KVM_X86_GET_MCE_CAP_SUPPORTED: r = -EFAULT; - if (copy_to_user(argp, &kvm_mce_cap_supported, - sizeof(kvm_mce_cap_supported))) + if (copy_to_user(argp, &kvm_caps.supported_mce_cap, + sizeof(kvm_caps.supported_mce_cap))) goto out; r = 0; break; @@ -4805,7 +4791,7 @@ static int kvm_vcpu_ioctl_x86_setup_mce(struct kvm_vcpu *vcpu, r = -EINVAL; if (!bank_num || bank_num > KVM_MAX_MCE_BANKS) goto out; - if (mcg_cap & ~(kvm_mce_cap_supported | 0xff | 0xff0000)) + if (mcg_cap & ~(kvm_caps.supported_mce_cap | 0xff | 0xff0000)) goto out; r = 0; vcpu->arch.mcg_cap = mcg_cap; @@ -5111,7 +5097,8 @@ static int kvm_vcpu_ioctl_x86_set_xsave(struct kvm_vcpu *vcpu, return fpu_copy_uabi_to_guest_fpstate(&vcpu->arch.guest_fpu, guest_xsave->region, - supported_xcr0, &vcpu->arch.pkru); + kvm_caps.supported_xcr0, + &vcpu->arch.pkru); } static void kvm_vcpu_ioctl_x86_get_xcrs(struct kvm_vcpu *vcpu, @@ -5616,8 +5603,8 @@ long kvm_arch_vcpu_ioctl(struct file *filp, r = -EINVAL; user_tsc_khz = (u32)arg; - if (kvm_has_tsc_control && - user_tsc_khz >= kvm_max_guest_tsc_khz) + if (kvm_caps.has_tsc_control && + user_tsc_khz >= kvm_caps.max_guest_tsc_khz) goto out; if (user_tsc_khz == 0) @@ -6061,7 +6048,7 @@ split_irqchip_unlock: (cap->args[0] & KVM_BUS_LOCK_DETECTION_EXIT)) break; - if (kvm_has_bus_lock_exit && + if (kvm_caps.has_bus_lock_exit && cap->args[0] & KVM_BUS_LOCK_DETECTION_EXIT) kvm->arch.bus_lock_detection_enabled = true; r = 0; @@ -6610,8 +6597,8 @@ set_pit2_out: r = -EINVAL; user_tsc_khz = (u32)arg; - if (kvm_has_tsc_control && - user_tsc_khz >= kvm_max_guest_tsc_khz) + if (kvm_caps.has_tsc_control && + user_tsc_khz >= kvm_caps.max_guest_tsc_khz) goto out; if (user_tsc_khz == 0) @@ -8774,7 +8761,7 @@ static void kvm_hyperv_tsc_notifier(void) /* TSC frequency always matches when on Hyper-V */ for_each_present_cpu(cpu) per_cpu(cpu_tsc_khz, cpu) = tsc_khz; - kvm_max_guest_tsc_khz = tsc_khz; + kvm_caps.max_guest_tsc_khz = tsc_khz; list_for_each_entry(kvm, &vm_list, vm_list) { __kvm_start_pvclock_update(kvm); @@ -9036,7 +9023,7 @@ int kvm_arch_init(void *opaque) if (boot_cpu_has(X86_FEATURE_XSAVE)) { host_xcr0 = xgetbv(XCR_XFEATURE_ENABLED_MASK); - supported_xcr0 = host_xcr0 & KVM_SUPPORTED_XCR0; + kvm_caps.supported_xcr0 = host_xcr0 & KVM_SUPPORTED_XCR0; } if (pi_inject_timer == -1) @@ -11748,13 +11735,13 @@ int kvm_arch_hardware_setup(void *opaque) kvm_register_perf_callbacks(ops->handle_intel_pt_intr); if (!kvm_cpu_cap_has(X86_FEATURE_XSAVES)) - supported_xss = 0; + kvm_caps.supported_xss = 0; #define __kvm_cpu_cap_has(UNUSED_, f) kvm_cpu_cap_has(f) cr4_reserved_bits = __cr4_reserved_bits(__kvm_cpu_cap_has, UNUSED_); #undef __kvm_cpu_cap_has - if (kvm_has_tsc_control) { + if (kvm_caps.has_tsc_control) { /* * Make sure the user can only configure tsc_khz values that * fit into a signed integer. @@ -11762,10 +11749,10 @@ int kvm_arch_hardware_setup(void *opaque) * be 1 on all machines. */ u64 max = min(0x7fffffffULL, - __scale_tsc(kvm_max_tsc_scaling_ratio, tsc_khz)); - kvm_max_guest_tsc_khz = max; + __scale_tsc(kvm_caps.max_tsc_scaling_ratio, tsc_khz)); + kvm_caps.max_guest_tsc_khz = max; } - kvm_default_tsc_scaling_ratio = 1ULL << kvm_tsc_scaling_ratio_frac_bits; + kvm_caps.default_tsc_scaling_ratio = 1ULL << kvm_caps.tsc_scaling_ratio_frac_bits; kvm_init_msr_list(); return 0; } diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h index 588792f00334..359d0454ad28 100644 --- a/arch/x86/kvm/x86.h +++ b/arch/x86/kvm/x86.h @@ -8,6 +8,25 @@ #include "kvm_cache_regs.h" #include "kvm_emulate.h" +struct kvm_caps { + /* control of guest tsc rate supported? */ + bool has_tsc_control; + /* maximum supported tsc_khz for guests */ + u32 max_guest_tsc_khz; + /* number of bits of the fractional part of the TSC scaling ratio */ + u8 tsc_scaling_ratio_frac_bits; + /* maximum allowed value of TSC scaling ratio */ + u64 max_tsc_scaling_ratio; + /* 1ull << kvm_caps.tsc_scaling_ratio_frac_bits */ + u64 default_tsc_scaling_ratio; + /* bus lock detection supported? */ + bool has_bus_lock_exit; + + u64 supported_mce_cap; + u64 supported_xcr0; + u64 supported_xss; +}; + void kvm_spurious_fault(void); #define KVM_NESTED_VMENTER_CONSISTENCY_CHECK(consistency_check) \ @@ -283,14 +302,15 @@ int x86_emulate_instruction(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, fastpath_t handle_fastpath_set_msr_irqoff(struct kvm_vcpu *vcpu); extern u64 host_xcr0; -extern u64 supported_xcr0; extern u64 host_xss; -extern u64 supported_xss; + +extern struct kvm_caps kvm_caps; + extern bool enable_pmu; static inline bool kvm_mpx_supported(void) { - return (supported_xcr0 & (XFEATURE_MASK_BNDREGS | XFEATURE_MASK_BNDCSR)) + return (kvm_caps.supported_xcr0 & (XFEATURE_MASK_BNDREGS | XFEATURE_MASK_BNDCSR)) == (XFEATURE_MASK_BNDREGS | XFEATURE_MASK_BNDCSR); } -- cgit v1.2.3 From 78c7d9001be704b7d13083333354c6ddf6e32fce Mon Sep 17 00:00:00 2001 From: Lai Jiangshan Date: Sun, 5 Jun 2022 14:34:17 +0800 Subject: KVM: X86/SVM: Use root_level in svm_load_mmu_pgd() Use root_level in svm_load_mmu_pg() rather that looking up the root level in vcpu->arch.mmu->root_role.level. svm_load_mmu_pgd() has only one caller, kvm_mmu_load_pgd(), which always passes vcpu->arch.mmu->root_role.level as root_level. Signed-off-by: Lai Jiangshan Message-Id: <20220605063417.308311-7-jiangshanlai@gmail.com> Signed-off-by: Paolo Bonzini --- arch/x86/kvm/svm/svm.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch/x86/kvm/svm/svm.c') diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index c6cca0ce127b..2ba0c62df8fb 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -4049,7 +4049,7 @@ static void svm_load_mmu_pgd(struct kvm_vcpu *vcpu, hpa_t root_hpa, hv_track_root_tdp(vcpu, root_hpa); cr3 = vcpu->arch.cr3; - } else if (vcpu->arch.mmu->root_role.level >= PT64_ROOT_4LEVEL) { + } else if (root_level >= PT64_ROOT_4LEVEL) { cr3 = __sme_set(root_hpa) | kvm_get_active_pcid(vcpu); } else { /* PCID in the guest should be impossible with a 32-bit MMU. */ -- cgit v1.2.3 From ce0a58f4756c14d7646cfdf279dbaada9d7712a0 Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Tue, 14 Jun 2022 23:05:47 +0000 Subject: KVM: x86: Move "apicv_active" into "struct kvm_lapic" Move the per-vCPU apicv_active flag into KVM's local APIC instance. APICv is fully dependent on an in-kernel local APIC, but that's not at all clear when reading the current code due to the flag being stored in the generic kvm_vcpu_arch struct. No functional change intended. Signed-off-by: Sean Christopherson Message-Id: <20220614230548.3852141-5-seanjc@google.com> Signed-off-by: Paolo Bonzini --- arch/x86/include/asm/kvm_host.h | 1 - arch/x86/kvm/lapic.c | 30 ++++++++++-------------------- arch/x86/kvm/lapic.h | 3 ++- arch/x86/kvm/svm/svm.c | 5 +++-- arch/x86/kvm/vmx/vmx.c | 3 ++- arch/x86/kvm/x86.c | 11 ++++++----- 6 files changed, 23 insertions(+), 30 deletions(-) (limited to 'arch/x86/kvm/svm/svm.c') diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 16acc54d49a7..1038ccb7056a 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -663,7 +663,6 @@ struct kvm_vcpu_arch { u64 efer; u64 apic_base; struct kvm_lapic *apic; /* kernel irqchip context */ - bool apicv_active; bool load_eoi_exitmap_pending; DECLARE_BITMAP(ioapic_handled_vectors, 256); unsigned long apic_attention; diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index cc0da5671eb9..43c42a580295 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -519,14 +519,11 @@ static inline int apic_find_highest_irr(struct kvm_lapic *apic) static inline void apic_clear_irr(int vec, struct kvm_lapic *apic) { - struct kvm_vcpu *vcpu; - - vcpu = apic->vcpu; - - if (unlikely(vcpu->arch.apicv_active)) { + if (unlikely(apic->apicv_active)) { /* need to update RVI */ kvm_lapic_clear_vector(vec, apic->regs + APIC_IRR); - static_call_cond(kvm_x86_hwapic_irr_update)(vcpu, apic_find_highest_irr(apic)); + static_call_cond(kvm_x86_hwapic_irr_update)(apic->vcpu, + apic_find_highest_irr(apic)); } else { apic->irr_pending = false; kvm_lapic_clear_vector(vec, apic->regs + APIC_IRR); @@ -543,19 +540,15 @@ EXPORT_SYMBOL_GPL(kvm_apic_clear_irr); static inline void apic_set_isr(int vec, struct kvm_lapic *apic) { - struct kvm_vcpu *vcpu; - if (__apic_test_and_set_vector(vec, apic->regs + APIC_ISR)) return; - vcpu = apic->vcpu; - /* * With APIC virtualization enabled, all caching is disabled * because the processor can modify ISR under the hood. Instead * just set SVI. */ - if (unlikely(vcpu->arch.apicv_active)) + if (unlikely(apic->apicv_active)) static_call_cond(kvm_x86_hwapic_isr_update)(vec); else { ++apic->isr_count; @@ -590,12 +583,9 @@ static inline int apic_find_highest_isr(struct kvm_lapic *apic) static inline void apic_clear_isr(int vec, struct kvm_lapic *apic) { - struct kvm_vcpu *vcpu; if (!__apic_test_and_clear_vector(vec, apic->regs + APIC_ISR)) return; - vcpu = apic->vcpu; - /* * We do get here for APIC virtualization enabled if the guest * uses the Hyper-V APIC enlightenment. In this case we may need @@ -603,7 +593,7 @@ static inline void apic_clear_isr(int vec, struct kvm_lapic *apic) * on the other hand isr_count and highest_isr_cache are unused * and must be left alone. */ - if (unlikely(vcpu->arch.apicv_active)) + if (unlikely(apic->apicv_active)) static_call_cond(kvm_x86_hwapic_isr_update)(apic_find_highest_isr(apic)); else { --apic->isr_count; @@ -1584,7 +1574,7 @@ static bool lapic_timer_int_injected(struct kvm_vcpu *vcpu) int vec = reg & APIC_VECTOR_MASK; void *bitmap = apic->regs + APIC_ISR; - if (vcpu->arch.apicv_active) + if (apic->apicv_active) bitmap = apic->regs + APIC_IRR; if (apic_test_vector(vec, bitmap)) @@ -1701,7 +1691,7 @@ static void apic_timer_expired(struct kvm_lapic *apic, bool from_timer_fn) if (apic_lvtt_tscdeadline(apic) || ktimer->hv_timer_in_use) ktimer->expired_tscdeadline = ktimer->tscdeadline; - if (!from_timer_fn && vcpu->arch.apicv_active) { + if (!from_timer_fn && apic->apicv_active) { WARN_ON(kvm_get_running_vcpu() != vcpu); kvm_apic_inject_pending_timer_irqs(apic); return; @@ -2379,7 +2369,7 @@ void kvm_apic_update_apicv(struct kvm_vcpu *vcpu) { struct kvm_lapic *apic = vcpu->arch.apic; - if (vcpu->arch.apicv_active) { + if (apic->apicv_active) { /* irr_pending is always true when apicv is activated. */ apic->irr_pending = true; apic->isr_count = 1; @@ -2454,7 +2444,7 @@ void kvm_lapic_reset(struct kvm_vcpu *vcpu, bool init_event) vcpu->arch.pv_eoi.msr_val = 0; apic_update_ppr(apic); - if (vcpu->arch.apicv_active) { + if (apic->apicv_active) { static_call_cond(kvm_x86_apicv_post_state_restore)(vcpu); static_call_cond(kvm_x86_hwapic_irr_update)(vcpu, -1); static_call_cond(kvm_x86_hwapic_isr_update)(-1); @@ -2734,7 +2724,7 @@ int kvm_apic_set_state(struct kvm_vcpu *vcpu, struct kvm_lapic_state *s) kvm_lapic_set_reg(apic, APIC_TMCCT, 0); kvm_apic_update_apicv(vcpu); apic->highest_isr_cache = -1; - if (vcpu->arch.apicv_active) { + if (apic->apicv_active) { static_call_cond(kvm_x86_apicv_post_state_restore)(vcpu); static_call_cond(kvm_x86_hwapic_irr_update)(vcpu, apic_find_highest_irr(apic)); static_call_cond(kvm_x86_hwapic_isr_update)(apic_find_highest_isr(apic)); diff --git a/arch/x86/kvm/lapic.h b/arch/x86/kvm/lapic.h index 65bb2a8cf145..e09ad97f3250 100644 --- a/arch/x86/kvm/lapic.h +++ b/arch/x86/kvm/lapic.h @@ -48,6 +48,7 @@ struct kvm_lapic { struct kvm_timer lapic_timer; u32 divide_count; struct kvm_vcpu *vcpu; + bool apicv_active; bool sw_enabled; bool irr_pending; bool lvt0_in_nmi_mode; @@ -204,7 +205,7 @@ static inline int apic_x2apic_mode(struct kvm_lapic *apic) static inline bool kvm_vcpu_apicv_active(struct kvm_vcpu *vcpu) { - return vcpu->arch.apic && vcpu->arch.apicv_active; + return vcpu->arch.apic && vcpu->arch.apic->apicv_active; } static inline bool kvm_apic_has_events(struct kvm_vcpu *vcpu) diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index 2ba0c62df8fb..136298cfb3fb 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -3465,12 +3465,13 @@ void svm_complete_interrupt_delivery(struct kvm_vcpu *vcpu, int delivery_mode, int trig_mode, int vector) { /* - * vcpu->arch.apicv_active must be read after vcpu->mode. + * apic->apicv_active must be read after vcpu->mode. * Pairs with smp_store_release in vcpu_enter_guest. */ bool in_guest_mode = (smp_load_acquire(&vcpu->mode) == IN_GUEST_MODE); - if (!READ_ONCE(vcpu->arch.apicv_active)) { + /* Note, this is called iff the local APIC is in-kernel. */ + if (!READ_ONCE(vcpu->arch.apic->apicv_active)) { /* Process the interrupt via inject_pending_event */ kvm_make_request(KVM_REQ_EVENT, vcpu); kvm_vcpu_kick(vcpu); diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index 380c8e7c1fb8..2609bcc8c130 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -4099,7 +4099,8 @@ static int vmx_deliver_posted_interrupt(struct kvm_vcpu *vcpu, int vector) if (!r) return 0; - if (!vcpu->arch.apicv_active) + /* Note, this is called iff the local APIC is in-kernel. */ + if (!vcpu->arch.apic->apicv_active) return -1; if (pi_test_and_set_pir(vector, &vmx->pi_desc)) diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index db35d40bf996..00e23dc518e0 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -9460,7 +9460,7 @@ static void update_cr8_intercept(struct kvm_vcpu *vcpu) if (!lapic_in_kernel(vcpu)) return; - if (vcpu->arch.apicv_active) + if (vcpu->arch.apic->apicv_active) return; if (!vcpu->arch.apic->vapic_addr) @@ -9913,6 +9913,7 @@ void kvm_make_scan_ioapic_request(struct kvm *kvm) void kvm_vcpu_update_apicv(struct kvm_vcpu *vcpu) { + struct kvm_lapic *apic = vcpu->arch.apic; bool activate; if (!lapic_in_kernel(vcpu)) @@ -9923,10 +9924,10 @@ void kvm_vcpu_update_apicv(struct kvm_vcpu *vcpu) activate = kvm_vcpu_apicv_activated(vcpu); - if (vcpu->arch.apicv_active == activate) + if (apic->apicv_active == activate) goto out; - vcpu->arch.apicv_active = activate; + apic->apicv_active = activate; kvm_apic_update_apicv(vcpu); static_call(kvm_x86_refresh_apicv_exec_ctrl)(vcpu); @@ -9936,7 +9937,7 @@ void kvm_vcpu_update_apicv(struct kvm_vcpu *vcpu) * still active when the interrupt got accepted. Make sure * inject_pending_event() is called to check for that. */ - if (!vcpu->arch.apicv_active) + if (!apic->apicv_active) kvm_make_request(KVM_REQ_EVENT, vcpu); out: @@ -11379,7 +11380,7 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu) * will ensure the vCPU gets the correct state before VM-Entry. */ if (enable_apicv) { - vcpu->arch.apicv_active = true; + vcpu->arch.apic->apicv_active = true; kvm_make_request(KVM_REQ_APICV_UPDATE, vcpu); } } else -- cgit v1.2.3 From 4bdec12aa8d6d0fd7f1ac6740c456bf726e53c0b Mon Sep 17 00:00:00 2001 From: Suravee Suthikulpanit Date: Thu, 19 May 2022 05:26:55 -0500 Subject: KVM: SVM: Detect X2APIC virtualization (x2AVIC) support Add CPUID check for the x2APIC virtualization (x2AVIC) feature. If available, the SVM driver can support both AVIC and x2AVIC modes when load the kvm_amd driver with avic=1. The operating mode will be determined at runtime depending on the guest APIC mode. Reviewed-by: Maxim Levitsky Reviewed-by: Pankaj Gupta Signed-off-by: Suravee Suthikulpanit Message-Id: <20220519102709.24125-4-suravee.suthikulpanit@amd.com> Signed-off-by: Paolo Bonzini --- arch/x86/include/asm/svm.h | 3 +++ arch/x86/kvm/svm/avic.c | 45 +++++++++++++++++++++++++++++++++++++++++++++ arch/x86/kvm/svm/svm.c | 15 ++------------- arch/x86/kvm/svm/svm.h | 9 +++++++++ 4 files changed, 59 insertions(+), 13 deletions(-) (limited to 'arch/x86/kvm/svm/svm.c') diff --git a/arch/x86/include/asm/svm.h b/arch/x86/include/asm/svm.h index 1b07fba11704..1d4d30cd84c2 100644 --- a/arch/x86/include/asm/svm.h +++ b/arch/x86/include/asm/svm.h @@ -195,6 +195,9 @@ struct __attribute__ ((__packed__)) vmcb_control_area { #define AVIC_ENABLE_SHIFT 31 #define AVIC_ENABLE_MASK (1 << AVIC_ENABLE_SHIFT) +#define X2APIC_MODE_SHIFT 30 +#define X2APIC_MODE_MASK (1 << X2APIC_MODE_SHIFT) + #define LBR_CTL_ENABLE_MASK BIT_ULL(0) #define VIRTUAL_VMLOAD_VMSAVE_ENABLE_MASK BIT_ULL(1) diff --git a/arch/x86/kvm/svm/avic.c b/arch/x86/kvm/svm/avic.c index 37016feb5ac4..509163833cbc 100644 --- a/arch/x86/kvm/svm/avic.c +++ b/arch/x86/kvm/svm/avic.c @@ -40,6 +40,9 @@ #define AVIC_GATAG_TO_VMID(x) ((x >> AVIC_VCPU_ID_BITS) & AVIC_VM_ID_MASK) #define AVIC_GATAG_TO_VCPUID(x) (x & AVIC_VCPU_ID_MASK) +static bool force_avic; +module_param_unsafe(force_avic, bool, 0444); + /* Note: * This hash table is used to map VM_ID to a struct kvm_svm, * when handling AMD IOMMU GALOG notification to schedule in @@ -50,6 +53,7 @@ static DEFINE_HASHTABLE(svm_vm_data_hash, SVM_VM_DATA_HASH_BITS); static u32 next_vm_id = 0; static bool next_vm_id_wrapped = 0; static DEFINE_SPINLOCK(svm_vm_data_hash_lock); +enum avic_modes avic_mode; /* * This is a wrapper of struct amd_iommu_ir_data. @@ -1058,3 +1062,44 @@ void avic_vcpu_unblocking(struct kvm_vcpu *vcpu) avic_vcpu_load(vcpu, vcpu->cpu); } + +/* + * Note: + * - The module param avic enable both xAPIC and x2APIC mode. + * - Hypervisor can support both xAVIC and x2AVIC in the same guest. + * - The mode can be switched at run-time. + */ +bool avic_hardware_setup(struct kvm_x86_ops *x86_ops) +{ + if (!npt_enabled) + return false; + + if (boot_cpu_has(X86_FEATURE_AVIC)) { + avic_mode = AVIC_MODE_X1; + pr_info("AVIC enabled\n"); + } else if (force_avic) { + /* + * Some older systems does not advertise AVIC support. + * See Revision Guide for specific AMD processor for more detail. + */ + avic_mode = AVIC_MODE_X1; + pr_warn("AVIC is not supported in CPUID but force enabled"); + pr_warn("Your system might crash and burn"); + } + + /* AVIC is a prerequisite for x2AVIC. */ + if (boot_cpu_has(X86_FEATURE_X2AVIC)) { + if (avic_mode == AVIC_MODE_X1) { + avic_mode = AVIC_MODE_X2; + pr_info("x2AVIC enabled\n"); + } else { + pr_warn(FW_BUG "Cannot support x2AVIC due to AVIC is disabled"); + pr_warn(FW_BUG "Try enable AVIC using force_avic option"); + } + } + + if (avic_mode != AVIC_MODE_NONE) + amd_iommu_register_ga_log_notifier(&avic_ga_log_notifier); + + return !!avic_mode; +} diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index 136298cfb3fb..e45568aea060 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -188,9 +188,6 @@ module_param(tsc_scaling, int, 0444); static bool avic; module_param(avic, bool, 0444); -static bool force_avic; -module_param_unsafe(force_avic, bool, 0444); - bool __read_mostly dump_invalid_vmcb; module_param(dump_invalid_vmcb, bool, 0644); @@ -5016,17 +5013,9 @@ static __init int svm_hardware_setup(void) nrips = false; } - enable_apicv = avic = avic && npt_enabled && (boot_cpu_has(X86_FEATURE_AVIC) || force_avic); + enable_apicv = avic = avic && avic_hardware_setup(&svm_x86_ops); - if (enable_apicv) { - if (!boot_cpu_has(X86_FEATURE_AVIC)) { - pr_warn("AVIC is not supported in CPUID but force enabled"); - pr_warn("Your system might crash and burn"); - } else - pr_info("AVIC enabled\n"); - - amd_iommu_register_ga_log_notifier(&avic_ga_log_notifier); - } else { + if (!enable_apicv) { svm_x86_ops.vcpu_blocking = NULL; svm_x86_ops.vcpu_unblocking = NULL; svm_x86_ops.vcpu_get_apicv_inhibit_reasons = NULL; diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h index d51de3c9264a..6d6390f785c5 100644 --- a/arch/x86/kvm/svm/svm.h +++ b/arch/x86/kvm/svm/svm.h @@ -36,6 +36,14 @@ extern bool npt_enabled; extern int vgif; extern bool intercept_smi; +enum avic_modes { + AVIC_MODE_NONE = 0, + AVIC_MODE_X1, + AVIC_MODE_X2, +}; + +extern enum avic_modes avic_mode; + /* * Clean bits in VMCB. * VMCB_ALL_CLEAN_MASK might also need to @@ -607,6 +615,7 @@ extern struct kvm_x86_nested_ops svm_nested_ops; /* avic.c */ +bool avic_hardware_setup(struct kvm_x86_ops *ops); int avic_ga_log_notifier(u32 ga_tag); void avic_vm_destroy(struct kvm *kvm); int avic_vm_init(struct kvm *kvm); -- cgit v1.2.3 From 5c127c85472c0c4c9d1f88e2807adcab9335d97c Mon Sep 17 00:00:00 2001 From: Suravee Suthikulpanit Date: Thu, 19 May 2022 05:26:59 -0500 Subject: KVM: SVM: Adding support for configuring x2APIC MSRs interception When enabling x2APIC virtualization (x2AVIC), the interception of x2APIC MSRs must be disabled to let the hardware virtualize guest MSR accesses. Current implementation keeps track of list of MSR interception state in the svm_direct_access_msrs array. Therefore, extends the array to include x2APIC MSRs. Reviewed-by: Maxim Levitsky Signed-off-by: Suravee Suthikulpanit Message-Id: <20220519102709.24125-8-suravee.suthikulpanit@amd.com> Signed-off-by: Paolo Bonzini --- arch/x86/kvm/svm/svm.c | 25 +++++++++++++++++++++++++ arch/x86/kvm/svm/svm.h | 4 ++-- 2 files changed, 27 insertions(+), 2 deletions(-) (limited to 'arch/x86/kvm/svm/svm.c') diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index e45568aea060..382edac728c7 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -100,6 +100,31 @@ static const struct svm_direct_access_msrs { { .index = MSR_IA32_CR_PAT, .always = false }, { .index = MSR_AMD64_SEV_ES_GHCB, .always = true }, { .index = MSR_TSC_AUX, .always = false }, + { .index = (APIC_BASE_MSR + APIC_ID), .always = false }, + { .index = (APIC_BASE_MSR + APIC_LVR), .always = false }, + { .index = (APIC_BASE_MSR + APIC_TASKPRI), .always = false }, + { .index = (APIC_BASE_MSR + APIC_ARBPRI), .always = false }, + { .index = (APIC_BASE_MSR + APIC_PROCPRI), .always = false }, + { .index = (APIC_BASE_MSR + APIC_EOI), .always = false }, + { .index = (APIC_BASE_MSR + APIC_RRR), .always = false }, + { .index = (APIC_BASE_MSR + APIC_LDR), .always = false }, + { .index = (APIC_BASE_MSR + APIC_DFR), .always = false }, + { .index = (APIC_BASE_MSR + APIC_SPIV), .always = false }, + { .index = (APIC_BASE_MSR + APIC_ISR), .always = false }, + { .index = (APIC_BASE_MSR + APIC_TMR), .always = false }, + { .index = (APIC_BASE_MSR + APIC_IRR), .always = false }, + { .index = (APIC_BASE_MSR + APIC_ESR), .always = false }, + { .index = (APIC_BASE_MSR + APIC_ICR), .always = false }, + { .index = (APIC_BASE_MSR + APIC_ICR2), .always = false }, + { .index = (APIC_BASE_MSR + APIC_LVTT), .always = false }, + { .index = (APIC_BASE_MSR + APIC_LVTTHMR), .always = false }, + { .index = (APIC_BASE_MSR + APIC_LVTPC), .always = false }, + { .index = (APIC_BASE_MSR + APIC_LVT0), .always = false }, + { .index = (APIC_BASE_MSR + APIC_LVT1), .always = false }, + { .index = (APIC_BASE_MSR + APIC_LVTERR), .always = false }, + { .index = (APIC_BASE_MSR + APIC_TMICT), .always = false }, + { .index = (APIC_BASE_MSR + APIC_TMCCT), .always = false }, + { .index = (APIC_BASE_MSR + APIC_TDCR), .always = false }, { .index = MSR_INVALID, .always = false }, }; diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h index 6d6390f785c5..172c2a37e60e 100644 --- a/arch/x86/kvm/svm/svm.h +++ b/arch/x86/kvm/svm/svm.h @@ -29,8 +29,8 @@ #define IOPM_SIZE PAGE_SIZE * 3 #define MSRPM_SIZE PAGE_SIZE * 2 -#define MAX_DIRECT_ACCESS_MSRS 21 -#define MSRPM_OFFSETS 16 +#define MAX_DIRECT_ACCESS_MSRS 46 +#define MSRPM_OFFSETS 32 extern u32 msrpm_offsets[MSRPM_OFFSETS] __read_mostly; extern bool npt_enabled; extern int vgif; -- cgit v1.2.3 From 05c4fe8c1bd94c6f59a8b82cbd535b1aea55945f Mon Sep 17 00:00:00 2001 From: Suravee Suthikulpanit Date: Thu, 19 May 2022 05:27:01 -0500 Subject: KVM: SVM: Refresh AVIC configuration when changing APIC mode AMD AVIC can support xAPIC and x2APIC virtualization, which requires changing x2APIC bit VMCB and MSR intercepton for x2APIC MSRs. Therefore, call avic_refresh_apicv_exec_ctrl() to refresh configuration accordingly. Reviewed-by: Maxim Levitsky Signed-off-by: Suravee Suthikulpanit Message-Id: <20220519102709.24125-10-suravee.suthikulpanit@amd.com> Signed-off-by: Paolo Bonzini --- arch/x86/kvm/svm/avic.c | 12 ++++++++++++ arch/x86/kvm/svm/svm.c | 1 + arch/x86/kvm/svm/svm.h | 2 ++ 3 files changed, 15 insertions(+) (limited to 'arch/x86/kvm/svm/svm.c') diff --git a/arch/x86/kvm/svm/avic.c b/arch/x86/kvm/svm/avic.c index cc4da232040c..eb7060d3327b 100644 --- a/arch/x86/kvm/svm/avic.c +++ b/arch/x86/kvm/svm/avic.c @@ -675,6 +675,18 @@ void avic_apicv_post_state_restore(struct kvm_vcpu *vcpu) avic_handle_ldr_update(vcpu); } +void avic_set_virtual_apic_mode(struct kvm_vcpu *vcpu) +{ + if (!lapic_in_kernel(vcpu) || avic_mode == AVIC_MODE_NONE) + return; + + if (kvm_get_apic_mode(vcpu) == LAPIC_MODE_INVALID) { + WARN_ONCE(true, "Invalid local APIC state (vcpu_id=%d)", vcpu->vcpu_id); + return; + } + avic_refresh_apicv_exec_ctrl(vcpu); +} + static int avic_set_pi_irte_mode(struct kvm_vcpu *vcpu, bool activate) { int ret = 0; diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index 382edac728c7..67ba0d3a7f62 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -4793,6 +4793,7 @@ static struct kvm_x86_ops svm_x86_ops __initdata = { .enable_nmi_window = svm_enable_nmi_window, .enable_irq_window = svm_enable_irq_window, .update_cr8_intercept = svm_update_cr8_intercept, + .set_virtual_apic_mode = avic_set_virtual_apic_mode, .refresh_apicv_exec_ctrl = avic_refresh_apicv_exec_ctrl, .check_apicv_inhibit_reasons = avic_check_apicv_inhibit_reasons, .apicv_post_state_restore = avic_apicv_post_state_restore, diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h index 172c2a37e60e..6d89842853cf 100644 --- a/arch/x86/kvm/svm/svm.h +++ b/arch/x86/kvm/svm/svm.h @@ -634,6 +634,8 @@ void avic_vcpu_blocking(struct kvm_vcpu *vcpu); void avic_vcpu_unblocking(struct kvm_vcpu *vcpu); void avic_ring_doorbell(struct kvm_vcpu *vcpu); unsigned long avic_vcpu_get_apicv_inhibit_reasons(struct kvm_vcpu *vcpu); +void avic_set_virtual_apic_mode(struct kvm_vcpu *vcpu); + /* sev.c */ -- cgit v1.2.3 From 4d1d7942e36add0aa741a62d0c8e3aba2d5b3ab1 Mon Sep 17 00:00:00 2001 From: Suravee Suthikulpanit Date: Thu, 19 May 2022 05:27:03 -0500 Subject: KVM: SVM: Introduce logic to (de)activate x2AVIC mode Introduce logic to (de)activate AVIC, which also allows switching between AVIC to x2AVIC mode at runtime. When an AVIC-enabled guest switches from APIC to x2APIC mode, the SVM driver needs to perform the following steps: 1. Set the x2APIC mode bit for AVIC in VMCB along with the maximum APIC ID support for each mode accodingly. 2. Disable x2APIC MSRs interception in order to allow the hardware to virtualize x2APIC MSRs accesses. Reported-by: kernel test robot Reviewed-by: Maxim Levitsky Signed-off-by: Suravee Suthikulpanit Message-Id: <20220519102709.24125-12-suravee.suthikulpanit@amd.com> Signed-off-by: Paolo Bonzini --- arch/x86/include/asm/svm.h | 1 + arch/x86/kvm/svm/avic.c | 39 ++++++++++++++++++++++++++++++++++----- arch/x86/kvm/svm/svm.c | 18 ++++++++++++++++++ arch/x86/kvm/svm/svm.h | 1 + 4 files changed, 54 insertions(+), 5 deletions(-) (limited to 'arch/x86/kvm/svm/svm.c') diff --git a/arch/x86/include/asm/svm.h b/arch/x86/include/asm/svm.h index ed4b83d7f09e..0361626841bc 100644 --- a/arch/x86/include/asm/svm.h +++ b/arch/x86/include/asm/svm.h @@ -256,6 +256,7 @@ enum avic_ipi_failure_cause { AVIC_IPI_FAILURE_INVALID_BACKING_PAGE, }; +#define AVIC_PHYSICAL_MAX_INDEX_MASK GENMASK_ULL(9, 0) /* * For AVIC, the max index allowed for physical APIC ID diff --git a/arch/x86/kvm/svm/avic.c b/arch/x86/kvm/svm/avic.c index eb7060d3327b..c7db96428b19 100644 --- a/arch/x86/kvm/svm/avic.c +++ b/arch/x86/kvm/svm/avic.c @@ -63,6 +63,36 @@ struct amd_svm_iommu_ir { void *data; /* Storing pointer to struct amd_ir_data */ }; +static void avic_activate_vmcb(struct vcpu_svm *svm) +{ + struct vmcb *vmcb = svm->vmcb01.ptr; + + vmcb->control.int_ctl &= ~(AVIC_ENABLE_MASK | X2APIC_MODE_MASK); + vmcb->control.avic_physical_id &= ~AVIC_PHYSICAL_MAX_INDEX_MASK; + + vmcb->control.int_ctl |= AVIC_ENABLE_MASK; + if (apic_x2apic_mode(svm->vcpu.arch.apic)) { + vmcb->control.int_ctl |= X2APIC_MODE_MASK; + vmcb->control.avic_physical_id |= X2AVIC_MAX_PHYSICAL_ID; + /* Disabling MSR intercept for x2APIC registers */ + svm_set_x2apic_msr_interception(svm, false); + } else { + vmcb->control.avic_physical_id |= AVIC_MAX_PHYSICAL_ID; + /* Enabling MSR intercept for x2APIC registers */ + svm_set_x2apic_msr_interception(svm, true); + } +} + +static void avic_deactivate_vmcb(struct vcpu_svm *svm) +{ + struct vmcb *vmcb = svm->vmcb01.ptr; + + vmcb->control.int_ctl &= ~(AVIC_ENABLE_MASK | X2APIC_MODE_MASK); + vmcb->control.avic_physical_id &= ~AVIC_PHYSICAL_MAX_INDEX_MASK; + + /* Enabling MSR intercept for x2APIC registers */ + svm_set_x2apic_msr_interception(svm, true); +} /* Note: * This function is called from IOMMU driver to notify @@ -179,13 +209,12 @@ void avic_init_vmcb(struct vcpu_svm *svm, struct vmcb *vmcb) vmcb->control.avic_backing_page = bpa & AVIC_HPA_MASK; vmcb->control.avic_logical_id = lpa & AVIC_HPA_MASK; vmcb->control.avic_physical_id = ppa & AVIC_HPA_MASK; - vmcb->control.avic_physical_id |= AVIC_MAX_PHYSICAL_ID; vmcb->control.avic_vapic_bar = APIC_DEFAULT_PHYS_BASE & VMCB_AVIC_APIC_BAR_MASK; if (kvm_apicv_activated(svm->vcpu.kvm)) - vmcb->control.int_ctl |= AVIC_ENABLE_MASK; + avic_activate_vmcb(svm); else - vmcb->control.int_ctl &= ~AVIC_ENABLE_MASK; + avic_deactivate_vmcb(svm); } static u64 *avic_get_physical_id_entry(struct kvm_vcpu *vcpu, @@ -1049,9 +1078,9 @@ void avic_refresh_apicv_exec_ctrl(struct kvm_vcpu *vcpu) * accordingly before re-activating. */ avic_apicv_post_state_restore(vcpu); - vmcb->control.int_ctl |= AVIC_ENABLE_MASK; + avic_activate_vmcb(svm); } else { - vmcb->control.int_ctl &= ~AVIC_ENABLE_MASK; + avic_deactivate_vmcb(svm); } vmcb_mark_dirty(vmcb, VMCB_AVIC); diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index 67ba0d3a7f62..491e4d549e2f 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -805,6 +805,24 @@ void svm_vcpu_init_msrpm(struct kvm_vcpu *vcpu, u32 *msrpm) } } +void svm_set_x2apic_msr_interception(struct vcpu_svm *svm, bool intercept) +{ + int i; + + if (avic_mode != AVIC_MODE_X2 || + !apic_x2apic_mode(svm->vcpu.arch.apic)) + return; + + for (i = 0; i < MAX_DIRECT_ACCESS_MSRS; i++) { + int index = direct_access_msrs[i].index; + + if ((index < APIC_BASE_MSR) || + (index > APIC_BASE_MSR + 0xff)) + continue; + set_msr_interception(&svm->vcpu, svm->msrpm, index, + !intercept, !intercept); + } +} void svm_vcpu_free_msrpm(u32 *msrpm) { diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h index 288a1384aa0f..ccaae7d160cd 100644 --- a/arch/x86/kvm/svm/svm.h +++ b/arch/x86/kvm/svm/svm.h @@ -555,6 +555,7 @@ void svm_set_gif(struct vcpu_svm *svm, bool value); int svm_invoke_exit_handler(struct kvm_vcpu *vcpu, u64 exit_code); void set_msr_interception(struct kvm_vcpu *vcpu, u32 *msrpm, u32 msr, int read, int write); +void svm_set_x2apic_msr_interception(struct vcpu_svm *svm, bool disable); void svm_complete_interrupt_delivery(struct kvm_vcpu *vcpu, int delivery_mode, int trig_mode, int vec); -- cgit v1.2.3 From 0e311d33bfbef86da130674e8528cc23e6acfe16 Mon Sep 17 00:00:00 2001 From: Suravee Suthikulpanit Date: Thu, 19 May 2022 05:27:05 -0500 Subject: KVM: SVM: Introduce hybrid-AVIC mode Currently, AVIC is inhibited when booting a VM w/ x2APIC support. because AVIC cannot virtualize x2APIC MSR register accesses. However, the AVIC doorbell can be used to accelerate interrupt injection into a running vCPU, while all guest accesses to x2APIC MSRs will be intercepted and emulated by KVM. With hybrid-AVIC support, the APICV_INHIBIT_REASON_X2APIC is no longer enforced. Suggested-by: Maxim Levitsky Reviewed-by: Maxim Levitsky Signed-off-by: Suravee Suthikulpanit Message-Id: <20220519102709.24125-14-suravee.suthikulpanit@amd.com> Signed-off-by: Paolo Bonzini --- arch/x86/include/asm/kvm_host.h | 5 ----- arch/x86/kvm/svm/avic.c | 13 +++++++++++-- arch/x86/kvm/svm/svm.c | 9 --------- 3 files changed, 11 insertions(+), 16 deletions(-) (limited to 'arch/x86/kvm/svm/svm.c') diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 88a3026ee163..de5a149d0971 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -1129,11 +1129,6 @@ enum kvm_apicv_inhibit { */ APICV_INHIBIT_REASON_PIT_REINJ, - /* - * AVIC is inhibited because the guest has x2apic in its CPUID. - */ - APICV_INHIBIT_REASON_X2APIC, - /* * AVIC is disabled because SEV doesn't support it. */ diff --git a/arch/x86/kvm/svm/avic.c b/arch/x86/kvm/svm/avic.c index fcff249e73cd..a8db5d2532bc 100644 --- a/arch/x86/kvm/svm/avic.c +++ b/arch/x86/kvm/svm/avic.c @@ -71,12 +71,22 @@ static void avic_activate_vmcb(struct vcpu_svm *svm) vmcb->control.avic_physical_id &= ~AVIC_PHYSICAL_MAX_INDEX_MASK; vmcb->control.int_ctl |= AVIC_ENABLE_MASK; - if (apic_x2apic_mode(svm->vcpu.arch.apic)) { + + /* Note: + * KVM can support hybrid-AVIC mode, where KVM emulates x2APIC + * MSR accesses, while interrupt injection to a running vCPU + * can be achieved using AVIC doorbell. The AVIC hardware still + * accelerate MMIO accesses, but this does not cause any harm + * as the guest is not supposed to access xAPIC mmio when uses x2APIC. + */ + if (apic_x2apic_mode(svm->vcpu.arch.apic) && + avic_mode == AVIC_MODE_X2) { vmcb->control.int_ctl |= X2APIC_MODE_MASK; vmcb->control.avic_physical_id |= X2AVIC_MAX_PHYSICAL_ID; /* Disabling MSR intercept for x2APIC registers */ svm_set_x2apic_msr_interception(svm, false); } else { + /* For xAVIC and hybrid-xAVIC modes */ vmcb->control.avic_physical_id |= AVIC_MAX_PHYSICAL_ID; /* Enabling MSR intercept for x2APIC registers */ svm_set_x2apic_msr_interception(svm, true); @@ -968,7 +978,6 @@ bool avic_check_apicv_inhibit_reasons(enum kvm_apicv_inhibit reason) BIT(APICV_INHIBIT_REASON_NESTED) | BIT(APICV_INHIBIT_REASON_IRQWIN) | BIT(APICV_INHIBIT_REASON_PIT_REINJ) | - BIT(APICV_INHIBIT_REASON_X2APIC) | BIT(APICV_INHIBIT_REASON_BLOCKIRQ) | BIT(APICV_INHIBIT_REASON_SEV) | BIT(APICV_INHIBIT_REASON_APIC_ID_MODIFIED) | diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index 491e4d549e2f..bb0457c1e41c 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -4160,7 +4160,6 @@ static void svm_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); struct kvm_cpuid_entry2 *best; - struct kvm *kvm = vcpu->kvm; vcpu->arch.xsaves_enabled = guest_cpuid_has(vcpu, X86_FEATURE_XSAVE) && boot_cpu_has(X86_FEATURE_XSAVE) && @@ -4192,14 +4191,6 @@ static void svm_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu) vcpu->arch.reserved_gpa_bits &= ~(1UL << (best->ebx & 0x3f)); } - if (kvm_vcpu_apicv_active(vcpu)) { - /* - * AVIC does not work with an x2APIC mode guest. If the X2APIC feature - * is exposed to the guest, disable AVIC. - */ - if (guest_cpuid_has(vcpu, X86_FEATURE_X2APIC)) - kvm_set_apicv_inhibit(kvm, APICV_INHIBIT_REASON_X2APIC); - } init_vmcb_after_set_cpuid(vcpu); } -- cgit v1.2.3 From 091abbf578f926e763adc0f577baeb7f405b4bdc Mon Sep 17 00:00:00 2001 From: Maxim Levitsky Date: Thu, 19 May 2022 05:27:09 -0500 Subject: KVM: x86: nSVM: optimize svm_set_x2apic_msr_interception - Avoid toggling the x2apic msr interception if it is already up to date. - Avoid touching L0 msr bitmap when AVIC is inhibited on entry to the guest mode, because in this case the guest usually uses its own msr bitmap. Later on VM exit, the 1st optimization will allow KVM to skip touching the L0 msr bitmap as well. Reviewed-by: Suravee Suthikulpanit Tested-by: Suravee Suthikulpanit Signed-off-by: Maxim Levitsky Message-Id: <20220519102709.24125-18-suravee.suthikulpanit@amd.com> Signed-off-by: Paolo Bonzini --- arch/x86/kvm/svm/avic.c | 8 ++++++++ arch/x86/kvm/svm/svm.c | 7 +++++++ arch/x86/kvm/svm/svm.h | 2 ++ 3 files changed, 17 insertions(+) (limited to 'arch/x86/kvm/svm/svm.c') diff --git a/arch/x86/kvm/svm/avic.c b/arch/x86/kvm/svm/avic.c index f18c852b6900..6919dee69f18 100644 --- a/arch/x86/kvm/svm/avic.c +++ b/arch/x86/kvm/svm/avic.c @@ -100,6 +100,14 @@ static void avic_deactivate_vmcb(struct vcpu_svm *svm) vmcb->control.int_ctl &= ~(AVIC_ENABLE_MASK | X2APIC_MODE_MASK); vmcb->control.avic_physical_id &= ~AVIC_PHYSICAL_MAX_INDEX_MASK; + /* + * If running nested and the guest uses its own MSR bitmap, there + * is no need to update L0's msr bitmap + */ + if (is_guest_mode(&svm->vcpu) && + vmcb12_is_intercept(&svm->nested.ctl, INTERCEPT_MSR_PROT)) + return; + /* Enabling MSR intercept for x2APIC registers */ svm_set_x2apic_msr_interception(svm, true); } diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index bb0457c1e41c..37ce061dfc76 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -809,6 +809,9 @@ void svm_set_x2apic_msr_interception(struct vcpu_svm *svm, bool intercept) { int i; + if (intercept == svm->x2avic_msrs_intercepted) + return; + if (avic_mode != AVIC_MODE_X2 || !apic_x2apic_mode(svm->vcpu.arch.apic)) return; @@ -822,6 +825,8 @@ void svm_set_x2apic_msr_interception(struct vcpu_svm *svm, bool intercept) set_msr_interception(&svm->vcpu, svm->msrpm, index, !intercept, !intercept); } + + svm->x2avic_msrs_intercepted = intercept; } void svm_vcpu_free_msrpm(u32 *msrpm) @@ -1393,6 +1398,8 @@ static int svm_vcpu_create(struct kvm_vcpu *vcpu) goto error_free_vmsa_page; } + svm->x2avic_msrs_intercepted = true; + svm->vmcb01.ptr = page_address(vmcb01_page); svm->vmcb01.pa = __sme_set(page_to_pfn(vmcb01_page) << PAGE_SHIFT); svm_switch_vmcb(svm, &svm->vmcb01); diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h index ccaae7d160cd..558ca1296d36 100644 --- a/arch/x86/kvm/svm/svm.h +++ b/arch/x86/kvm/svm/svm.h @@ -276,6 +276,8 @@ struct vcpu_svm { struct vcpu_sev_es_state sev_es; bool guest_state_loaded; + + bool x2avic_msrs_intercepted; }; struct svm_cpu_data { -- cgit v1.2.3 From bdc2d7ad10724de31463a0cdbd88b0ad7353a6de Mon Sep 17 00:00:00 2001 From: Maxim Levitsky Date: Thu, 14 Jul 2022 15:44:53 +0300 Subject: KVM: SVM: fix task switch emulation on INTn instruction. Recently KVM's SVM code switched to re-injecting software interrupt events, if something prevented their delivery. Task switch due to task gate in the IDT, however is an exception to this rule, because in this case, INTn instruction causes a task switch intercept and its emulation completes the INTn emulation as well. Add a missing case to task_switch_interception for that. This fixes 32 bit kvm unit test taskswitch2. Fixes: 7e5b5ef8dca322 ("KVM: SVM: Re-inject INTn instead of retrying the insn on "failure"") Signed-off-by: Maxim Levitsky Reviewed-by: Maciej S. Szmigiero Message-Id: <20220714124453.188655-1-mlevitsk@redhat.com> Signed-off-by: Paolo Bonzini --- arch/x86/kvm/svm/svm.c | 1 + 1 file changed, 1 insertion(+) (limited to 'arch/x86/kvm/svm/svm.c') diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index 37ce061dfc76..1d8eb3333f46 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -2446,6 +2446,7 @@ static int task_switch_interception(struct kvm_vcpu *vcpu) kvm_clear_exception_queue(vcpu); break; case SVM_EXITINTINFO_TYPE_INTR: + case SVM_EXITINTINFO_TYPE_SOFT: kvm_clear_interrupt_queue(vcpu); break; default: -- cgit v1.2.3 From 277ad7d58611b455662f2e3f7bd24ce5bfeb2fdc Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Tue, 12 Jul 2022 02:06:45 +0200 Subject: KVM: x86: Add dedicated helper to get CPUID entry with significant index Add a second CPUID helper, kvm_find_cpuid_entry_index(), to handle KVM queries for CPUID leaves whose index _may_ be significant, and drop the index param from the existing kvm_find_cpuid_entry(). Add a WARN in the inner helper, cpuid_entry2_find(), to detect attempts to retrieve a CPUID entry whose index is significant without explicitly providing an index. Using an explicit magic number and letting callers omit the index avoids confusion by eliminating the myriad cases where KVM specifies '0' as a dummy value. Suggested-by: Paolo Bonzini Signed-off-by: Sean Christopherson Signed-off-by: Paolo Bonzini --- arch/x86/kvm/cpuid.c | 80 +++++++++++++++++++++++++++++++++----------- arch/x86/kvm/cpuid.h | 16 +++++---- arch/x86/kvm/hyperv.c | 8 ++--- arch/x86/kvm/svm/svm.c | 2 +- arch/x86/kvm/vmx/pmu_intel.c | 4 +-- arch/x86/kvm/vmx/sgx.c | 8 ++--- arch/x86/kvm/vmx/vmx.c | 6 ++-- arch/x86/kvm/x86.c | 2 +- 8 files changed, 84 insertions(+), 42 deletions(-) (limited to 'arch/x86/kvm/svm/svm.c') diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index d47222ab8e6e..75dcf7a72605 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -67,9 +67,17 @@ u32 xstate_required_size(u64 xstate_bv, bool compacted) #define F feature_bit #define SF(name) (boot_cpu_has(X86_FEATURE_##name) ? F(name) : 0) +/* + * Magic value used by KVM when querying userspace-provided CPUID entries and + * doesn't care about the CPIUD index because the index of the function in + * question is not significant. Note, this magic value must have at least one + * bit set in bits[63:32] and must be consumed as a u64 by cpuid_entry2_find() + * to avoid false positives when processing guest CPUID input. + */ +#define KVM_CPUID_INDEX_NOT_SIGNIFICANT -1ull static inline struct kvm_cpuid_entry2 *cpuid_entry2_find( - struct kvm_cpuid_entry2 *entries, int nent, u32 function, u32 index) + struct kvm_cpuid_entry2 *entries, int nent, u32 function, u64 index) { struct kvm_cpuid_entry2 *e; int i; @@ -77,9 +85,31 @@ static inline struct kvm_cpuid_entry2 *cpuid_entry2_find( for (i = 0; i < nent; i++) { e = &entries[i]; - if (e->function == function && - (!(e->flags & KVM_CPUID_FLAG_SIGNIFCANT_INDEX) || e->index == index)) + if (e->function != function) + continue; + + /* + * If the index isn't significant, use the first entry with a + * matching function. It's userspace's responsibilty to not + * provide "duplicate" entries in all cases. + */ + if (!(e->flags & KVM_CPUID_FLAG_SIGNIFCANT_INDEX) || e->index == index) + return e; + + + /* + * Similarly, use the first matching entry if KVM is doing a + * lookup (as opposed to emulating CPUID) for a function that's + * architecturally defined as not having a significant index. + */ + if (index == KVM_CPUID_INDEX_NOT_SIGNIFICANT) { + /* + * Direct lookups from KVM should not diverge from what + * KVM defines internally (the architectural behavior). + */ + WARN_ON_ONCE(cpuid_function_is_indexed(function)); return e; + } } return NULL; @@ -96,7 +126,8 @@ static int kvm_check_cpuid(struct kvm_vcpu *vcpu, * The existing code assumes virtual address is 48-bit or 57-bit in the * canonical address checks; exit if it is ever changed. */ - best = cpuid_entry2_find(entries, nent, 0x80000008, 0); + best = cpuid_entry2_find(entries, nent, 0x80000008, + KVM_CPUID_INDEX_NOT_SIGNIFICANT); if (best) { int vaddr_bits = (best->eax & 0xff00) >> 8; @@ -151,7 +182,7 @@ static void kvm_update_kvm_cpuid_base(struct kvm_vcpu *vcpu) vcpu->arch.kvm_cpuid_base = 0; for_each_possible_hypervisor_cpuid_base(function) { - entry = kvm_find_cpuid_entry(vcpu, function, 0); + entry = kvm_find_cpuid_entry(vcpu, function); if (entry) { u32 signature[3]; @@ -177,7 +208,8 @@ static struct kvm_cpuid_entry2 *__kvm_find_kvm_cpuid_features(struct kvm_vcpu *v if (!base) return NULL; - return cpuid_entry2_find(entries, nent, base | KVM_CPUID_FEATURES, 0); + return cpuid_entry2_find(entries, nent, base | KVM_CPUID_FEATURES, + KVM_CPUID_INDEX_NOT_SIGNIFICANT); } static struct kvm_cpuid_entry2 *kvm_find_kvm_cpuid_features(struct kvm_vcpu *vcpu) @@ -219,7 +251,7 @@ static void __kvm_update_cpuid_runtime(struct kvm_vcpu *vcpu, struct kvm_cpuid_e struct kvm_cpuid_entry2 *best; u64 guest_supported_xcr0 = cpuid_get_supported_xcr0(entries, nent); - best = cpuid_entry2_find(entries, nent, 1, 0); + best = cpuid_entry2_find(entries, nent, 1, KVM_CPUID_INDEX_NOT_SIGNIFICANT); if (best) { /* Update OSXSAVE bit */ if (boot_cpu_has(X86_FEATURE_XSAVE)) @@ -250,7 +282,7 @@ static void __kvm_update_cpuid_runtime(struct kvm_vcpu *vcpu, struct kvm_cpuid_e best->eax &= ~(1 << KVM_FEATURE_PV_UNHALT); if (!kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_MISC_ENABLE_NO_MWAIT)) { - best = cpuid_entry2_find(entries, nent, 0x1, 0); + best = cpuid_entry2_find(entries, nent, 0x1, KVM_CPUID_INDEX_NOT_SIGNIFICANT); if (best) cpuid_entry_change(best, X86_FEATURE_MWAIT, vcpu->arch.ia32_misc_enable_msr & @@ -285,7 +317,7 @@ static void kvm_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu) struct kvm_cpuid_entry2 *best; u64 guest_supported_xcr0; - best = kvm_find_cpuid_entry(vcpu, 1, 0); + best = kvm_find_cpuid_entry(vcpu, 1); if (best && apic) { if (cpuid_entry_has(best, X86_FEATURE_TSC_DEADLINE_TIMER)) apic->lapic_timer.timer_mode_mask = 3 << 17; @@ -325,10 +357,10 @@ int cpuid_query_maxphyaddr(struct kvm_vcpu *vcpu) { struct kvm_cpuid_entry2 *best; - best = kvm_find_cpuid_entry(vcpu, 0x80000000, 0); + best = kvm_find_cpuid_entry(vcpu, 0x80000000); if (!best || best->eax < 0x80000008) goto not_found; - best = kvm_find_cpuid_entry(vcpu, 0x80000008, 0); + best = kvm_find_cpuid_entry(vcpu, 0x80000008); if (best) return best->eax & 0xff; not_found: @@ -1302,12 +1334,20 @@ out_free: return r; } -struct kvm_cpuid_entry2 *kvm_find_cpuid_entry(struct kvm_vcpu *vcpu, - u32 function, u32 index) +struct kvm_cpuid_entry2 *kvm_find_cpuid_entry_index(struct kvm_vcpu *vcpu, + u32 function, u32 index) { return cpuid_entry2_find(vcpu->arch.cpuid_entries, vcpu->arch.cpuid_nent, function, index); } +EXPORT_SYMBOL_GPL(kvm_find_cpuid_entry_index); + +struct kvm_cpuid_entry2 *kvm_find_cpuid_entry(struct kvm_vcpu *vcpu, + u32 function) +{ + return cpuid_entry2_find(vcpu->arch.cpuid_entries, vcpu->arch.cpuid_nent, + function, KVM_CPUID_INDEX_NOT_SIGNIFICANT); +} EXPORT_SYMBOL_GPL(kvm_find_cpuid_entry); /* @@ -1344,7 +1384,7 @@ get_out_of_range_cpuid_entry(struct kvm_vcpu *vcpu, u32 *fn_ptr, u32 index) struct kvm_cpuid_entry2 *basic, *class; u32 function = *fn_ptr; - basic = kvm_find_cpuid_entry(vcpu, 0, 0); + basic = kvm_find_cpuid_entry(vcpu, 0); if (!basic) return NULL; @@ -1353,11 +1393,11 @@ get_out_of_range_cpuid_entry(struct kvm_vcpu *vcpu, u32 *fn_ptr, u32 index) return NULL; if (function >= 0x40000000 && function <= 0x4fffffff) - class = kvm_find_cpuid_entry(vcpu, function & 0xffffff00, 0); + class = kvm_find_cpuid_entry(vcpu, function & 0xffffff00); else if (function >= 0xc0000000) - class = kvm_find_cpuid_entry(vcpu, 0xc0000000, 0); + class = kvm_find_cpuid_entry(vcpu, 0xc0000000); else - class = kvm_find_cpuid_entry(vcpu, function & 0x80000000, 0); + class = kvm_find_cpuid_entry(vcpu, function & 0x80000000); if (class && function <= class->eax) return NULL; @@ -1375,7 +1415,7 @@ get_out_of_range_cpuid_entry(struct kvm_vcpu *vcpu, u32 *fn_ptr, u32 index) * the effective CPUID entry is the max basic leaf. Note, the index of * the original requested leaf is observed! */ - return kvm_find_cpuid_entry(vcpu, basic->eax, index); + return kvm_find_cpuid_entry_index(vcpu, basic->eax, index); } bool kvm_cpuid(struct kvm_vcpu *vcpu, u32 *eax, u32 *ebx, @@ -1385,7 +1425,7 @@ bool kvm_cpuid(struct kvm_vcpu *vcpu, u32 *eax, u32 *ebx, struct kvm_cpuid_entry2 *entry; bool exact, used_max_basic = false; - entry = kvm_find_cpuid_entry(vcpu, function, index); + entry = kvm_find_cpuid_entry_index(vcpu, function, index); exact = !!entry; if (!entry && !exact_only) { @@ -1414,7 +1454,7 @@ bool kvm_cpuid(struct kvm_vcpu *vcpu, u32 *eax, u32 *ebx, * exists. EDX can be copied from any existing index. */ if (function == 0xb || function == 0x1f) { - entry = kvm_find_cpuid_entry(vcpu, function, 1); + entry = kvm_find_cpuid_entry_index(vcpu, function, 1); if (entry) { *ecx = index & 0xff; *edx = entry->edx; diff --git a/arch/x86/kvm/cpuid.h b/arch/x86/kvm/cpuid.h index ac72aabba981..b1658c0de847 100644 --- a/arch/x86/kvm/cpuid.h +++ b/arch/x86/kvm/cpuid.h @@ -13,8 +13,10 @@ void kvm_set_cpu_caps(void); void kvm_update_cpuid_runtime(struct kvm_vcpu *vcpu); void kvm_update_pv_runtime(struct kvm_vcpu *vcpu); +struct kvm_cpuid_entry2 *kvm_find_cpuid_entry_index(struct kvm_vcpu *vcpu, + u32 function, u32 index); struct kvm_cpuid_entry2 *kvm_find_cpuid_entry(struct kvm_vcpu *vcpu, - u32 function, u32 index); + u32 function); int kvm_dev_ioctl_get_cpuid(struct kvm_cpuid2 *cpuid, struct kvm_cpuid_entry2 __user *entries, unsigned int type); @@ -76,7 +78,7 @@ static __always_inline u32 *guest_cpuid_get_register(struct kvm_vcpu *vcpu, const struct cpuid_reg cpuid = x86_feature_cpuid(x86_feature); struct kvm_cpuid_entry2 *entry; - entry = kvm_find_cpuid_entry(vcpu, cpuid.function, cpuid.index); + entry = kvm_find_cpuid_entry_index(vcpu, cpuid.function, cpuid.index); if (!entry) return NULL; @@ -109,7 +111,7 @@ static inline bool guest_cpuid_is_amd_or_hygon(struct kvm_vcpu *vcpu) { struct kvm_cpuid_entry2 *best; - best = kvm_find_cpuid_entry(vcpu, 0, 0); + best = kvm_find_cpuid_entry(vcpu, 0); return best && (is_guest_vendor_amd(best->ebx, best->ecx, best->edx) || is_guest_vendor_hygon(best->ebx, best->ecx, best->edx)); @@ -119,7 +121,7 @@ static inline bool guest_cpuid_is_intel(struct kvm_vcpu *vcpu) { struct kvm_cpuid_entry2 *best; - best = kvm_find_cpuid_entry(vcpu, 0, 0); + best = kvm_find_cpuid_entry(vcpu, 0); return best && is_guest_vendor_intel(best->ebx, best->ecx, best->edx); } @@ -127,7 +129,7 @@ static inline int guest_cpuid_family(struct kvm_vcpu *vcpu) { struct kvm_cpuid_entry2 *best; - best = kvm_find_cpuid_entry(vcpu, 0x1, 0); + best = kvm_find_cpuid_entry(vcpu, 0x1); if (!best) return -1; @@ -138,7 +140,7 @@ static inline int guest_cpuid_model(struct kvm_vcpu *vcpu) { struct kvm_cpuid_entry2 *best; - best = kvm_find_cpuid_entry(vcpu, 0x1, 0); + best = kvm_find_cpuid_entry(vcpu, 0x1); if (!best) return -1; @@ -154,7 +156,7 @@ static inline int guest_cpuid_stepping(struct kvm_vcpu *vcpu) { struct kvm_cpuid_entry2 *best; - best = kvm_find_cpuid_entry(vcpu, 0x1, 0); + best = kvm_find_cpuid_entry(vcpu, 0x1); if (!best) return -1; diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c index e2e95a6fccfd..ed804447589c 100644 --- a/arch/x86/kvm/hyperv.c +++ b/arch/x86/kvm/hyperv.c @@ -1992,7 +1992,7 @@ void kvm_hv_set_cpuid(struct kvm_vcpu *vcpu) struct kvm_cpuid_entry2 *entry; struct kvm_vcpu_hv *hv_vcpu; - entry = kvm_find_cpuid_entry(vcpu, HYPERV_CPUID_INTERFACE, 0); + entry = kvm_find_cpuid_entry(vcpu, HYPERV_CPUID_INTERFACE); if (entry && entry->eax == HYPERV_CPUID_SIGNATURE_EAX) { vcpu->arch.hyperv_enabled = true; } else { @@ -2005,7 +2005,7 @@ void kvm_hv_set_cpuid(struct kvm_vcpu *vcpu) hv_vcpu = to_hv_vcpu(vcpu); - entry = kvm_find_cpuid_entry(vcpu, HYPERV_CPUID_FEATURES, 0); + entry = kvm_find_cpuid_entry(vcpu, HYPERV_CPUID_FEATURES); if (entry) { hv_vcpu->cpuid_cache.features_eax = entry->eax; hv_vcpu->cpuid_cache.features_ebx = entry->ebx; @@ -2016,7 +2016,7 @@ void kvm_hv_set_cpuid(struct kvm_vcpu *vcpu) hv_vcpu->cpuid_cache.features_edx = 0; } - entry = kvm_find_cpuid_entry(vcpu, HYPERV_CPUID_ENLIGHTMENT_INFO, 0); + entry = kvm_find_cpuid_entry(vcpu, HYPERV_CPUID_ENLIGHTMENT_INFO); if (entry) { hv_vcpu->cpuid_cache.enlightenments_eax = entry->eax; hv_vcpu->cpuid_cache.enlightenments_ebx = entry->ebx; @@ -2025,7 +2025,7 @@ void kvm_hv_set_cpuid(struct kvm_vcpu *vcpu) hv_vcpu->cpuid_cache.enlightenments_ebx = 0; } - entry = kvm_find_cpuid_entry(vcpu, HYPERV_CPUID_SYNDBG_PLATFORM_CAPABILITIES, 0); + entry = kvm_find_cpuid_entry(vcpu, HYPERV_CPUID_SYNDBG_PLATFORM_CAPABILITIES); if (entry) hv_vcpu->cpuid_cache.syndbg_cap_eax = entry->eax; else diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index 1d8eb3333f46..84414eafcd0d 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -4194,7 +4194,7 @@ static void svm_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu) /* For sev guests, the memory encryption bit is not reserved in CR3. */ if (sev_guest(vcpu->kvm)) { - best = kvm_find_cpuid_entry(vcpu, 0x8000001F, 0); + best = kvm_find_cpuid_entry(vcpu, 0x8000001F); if (best) vcpu->arch.reserved_gpa_bits &= ~(1UL << (best->ebx & 0x3f)); } diff --git a/arch/x86/kvm/vmx/pmu_intel.c b/arch/x86/kvm/vmx/pmu_intel.c index 53ccba896e77..4bc098fbec31 100644 --- a/arch/x86/kvm/vmx/pmu_intel.c +++ b/arch/x86/kvm/vmx/pmu_intel.c @@ -531,7 +531,7 @@ static void intel_pmu_refresh(struct kvm_vcpu *vcpu) pmu->pebs_enable_mask = ~0ull; pmu->pebs_data_cfg_mask = ~0ull; - entry = kvm_find_cpuid_entry(vcpu, 0xa, 0); + entry = kvm_find_cpuid_entry(vcpu, 0xa); if (!entry || !vcpu->kvm->arch.enable_pmu) return; eax.full = entry->eax; @@ -577,7 +577,7 @@ static void intel_pmu_refresh(struct kvm_vcpu *vcpu) pmu->global_ovf_ctrl_mask &= ~MSR_CORE_PERF_GLOBAL_OVF_CTRL_TRACE_TOPA_PMI; - entry = kvm_find_cpuid_entry(vcpu, 7, 0); + entry = kvm_find_cpuid_entry_index(vcpu, 7, 0); if (entry && (boot_cpu_has(X86_FEATURE_HLE) || boot_cpu_has(X86_FEATURE_RTM)) && (entry->ebx & (X86_FEATURE_HLE|X86_FEATURE_RTM))) { diff --git a/arch/x86/kvm/vmx/sgx.c b/arch/x86/kvm/vmx/sgx.c index 7ae8aa73724c..aba8cebdc587 100644 --- a/arch/x86/kvm/vmx/sgx.c +++ b/arch/x86/kvm/vmx/sgx.c @@ -148,8 +148,8 @@ static int __handle_encls_ecreate(struct kvm_vcpu *vcpu, u8 max_size_log2; int trapnr, ret; - sgx_12_0 = kvm_find_cpuid_entry(vcpu, 0x12, 0); - sgx_12_1 = kvm_find_cpuid_entry(vcpu, 0x12, 1); + sgx_12_0 = kvm_find_cpuid_entry_index(vcpu, 0x12, 0); + sgx_12_1 = kvm_find_cpuid_entry_index(vcpu, 0x12, 1); if (!sgx_12_0 || !sgx_12_1) { kvm_prepare_emulation_failure_exit(vcpu); return 0; @@ -431,7 +431,7 @@ static bool sgx_intercept_encls_ecreate(struct kvm_vcpu *vcpu) if (!vcpu->kvm->arch.sgx_provisioning_allowed) return true; - guest_cpuid = kvm_find_cpuid_entry(vcpu, 0x12, 0); + guest_cpuid = kvm_find_cpuid_entry_index(vcpu, 0x12, 0); if (!guest_cpuid) return true; @@ -439,7 +439,7 @@ static bool sgx_intercept_encls_ecreate(struct kvm_vcpu *vcpu) if (guest_cpuid->ebx != ebx || guest_cpuid->edx != edx) return true; - guest_cpuid = kvm_find_cpuid_entry(vcpu, 0x12, 1); + guest_cpuid = kvm_find_cpuid_entry_index(vcpu, 0x12, 1); if (!guest_cpuid) return true; diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index 3842e121070a..e6ab2c2c4d3b 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -7430,7 +7430,7 @@ static void nested_vmx_cr_fixed1_bits_update(struct kvm_vcpu *vcpu) vmx->nested.msrs.cr4_fixed1 |= (_cr4_mask); \ } while (0) - entry = kvm_find_cpuid_entry(vcpu, 0x1, 0); + entry = kvm_find_cpuid_entry(vcpu, 0x1); cr4_fixed1_update(X86_CR4_VME, edx, feature_bit(VME)); cr4_fixed1_update(X86_CR4_PVI, edx, feature_bit(VME)); cr4_fixed1_update(X86_CR4_TSD, edx, feature_bit(TSC)); @@ -7446,7 +7446,7 @@ static void nested_vmx_cr_fixed1_bits_update(struct kvm_vcpu *vcpu) cr4_fixed1_update(X86_CR4_PCIDE, ecx, feature_bit(PCID)); cr4_fixed1_update(X86_CR4_OSXSAVE, ecx, feature_bit(XSAVE)); - entry = kvm_find_cpuid_entry(vcpu, 0x7, 0); + entry = kvm_find_cpuid_entry_index(vcpu, 0x7, 0); cr4_fixed1_update(X86_CR4_FSGSBASE, ebx, feature_bit(FSGSBASE)); cr4_fixed1_update(X86_CR4_SMEP, ebx, feature_bit(SMEP)); cr4_fixed1_update(X86_CR4_SMAP, ebx, feature_bit(SMAP)); @@ -7481,7 +7481,7 @@ static void update_intel_pt_cfg(struct kvm_vcpu *vcpu) int i; for (i = 0; i < PT_CPUID_LEAVES; i++) { - best = kvm_find_cpuid_entry(vcpu, 0x14, i); + best = kvm_find_cpuid_entry_index(vcpu, 0x14, i); if (!best) return; vmx->pt_desc.caps[CPUID_EAX + i*PT_CPUID_REGS_NUM] = best->eax; diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 0729e434c51b..f389691d8c04 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -11735,7 +11735,7 @@ void kvm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) * i.e. it's impossible for kvm_find_cpuid_entry() to find a valid entry * on RESET. But, go through the motions in case that's ever remedied. */ - cpuid_0x1 = kvm_find_cpuid_entry(vcpu, 1, 0); + cpuid_0x1 = kvm_find_cpuid_entry(vcpu, 1); kvm_rdx_write(vcpu, cpuid_0x1 ? cpuid_0x1->eax : 0x600); static_call(kvm_x86_vcpu_reset)(vcpu, init_event); -- cgit v1.2.3 From ba28401bb93e5c779d5762c4eb0eb665493e5dd4 Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Thu, 14 Jul 2022 15:37:07 +0000 Subject: KVM: x86: Restrict get_mt_mask() to a u8, use KVM_X86_OP_OPTIONAL_RET0 Restrict get_mt_mask() to a u8 and reintroduce using a RET0 static_call for the SVM implementation. EPT stores the memtype information in the lower 8 bits (bits 6:3 to be precise), and even returns a shifted u8 without an explicit cast to a larger type; there's no need to return a full u64. Note, RET0 doesn't play nice with a u64 return on 32-bit kernels, see commit bf07be36cd88 ("KVM: x86: do not use KVM_X86_OP_OPTIONAL_RET0 for get_mt_mask"). Signed-off-by: Sean Christopherson Message-Id: <20220714153707.3239119-1-seanjc@google.com> Signed-off-by: Paolo Bonzini --- arch/x86/include/asm/kvm-x86-ops.h | 2 +- arch/x86/include/asm/kvm_host.h | 2 +- arch/x86/kvm/svm/svm.c | 6 ------ arch/x86/kvm/vmx/vmx.c | 2 +- 4 files changed, 3 insertions(+), 9 deletions(-) (limited to 'arch/x86/kvm/svm/svm.c') diff --git a/arch/x86/include/asm/kvm-x86-ops.h b/arch/x86/include/asm/kvm-x86-ops.h index 6f2f1affbb78..51f777071584 100644 --- a/arch/x86/include/asm/kvm-x86-ops.h +++ b/arch/x86/include/asm/kvm-x86-ops.h @@ -88,7 +88,7 @@ KVM_X86_OP(deliver_interrupt) KVM_X86_OP_OPTIONAL(sync_pir_to_irr) KVM_X86_OP_OPTIONAL_RET0(set_tss_addr) KVM_X86_OP_OPTIONAL_RET0(set_identity_map_addr) -KVM_X86_OP(get_mt_mask) +KVM_X86_OP_OPTIONAL_RET0(get_mt_mask) KVM_X86_OP(load_mmu_pgd) KVM_X86_OP(has_wbinvd_exit) KVM_X86_OP(get_l2_tsc_offset) diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index d4ece7bf2124..e8281d64a431 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -1545,7 +1545,7 @@ struct kvm_x86_ops { 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); - u64 (*get_mt_mask)(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio); + u8 (*get_mt_mask)(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio); void (*load_mmu_pgd)(struct kvm_vcpu *vcpu, hpa_t root_hpa, int root_level); diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index 84414eafcd0d..ba81a7e58f75 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -4159,11 +4159,6 @@ static bool svm_has_emulated_msr(struct kvm *kvm, u32 index) return true; } -static u64 svm_get_mt_mask(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio) -{ - return 0; -} - static void svm_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); @@ -4815,7 +4810,6 @@ static struct kvm_x86_ops svm_x86_ops __initdata = { .check_apicv_inhibit_reasons = avic_check_apicv_inhibit_reasons, .apicv_post_state_restore = avic_apicv_post_state_restore, - .get_mt_mask = svm_get_mt_mask, .get_exit_info = svm_get_exit_info, .vcpu_after_set_cpuid = svm_vcpu_after_set_cpuid, diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index e6ab2c2c4d3b..b0cc911a8f6f 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -7354,7 +7354,7 @@ static int __init vmx_check_processor_compat(void) return 0; } -static u64 vmx_get_mt_mask(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio) +static u8 vmx_get_mt_mask(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio) { u8 cache; -- cgit v1.2.3 From 01e69cef63f88d809181f62f03a01d7295f2d5a4 Mon Sep 17 00:00:00 2001 From: Suravee Suthikulpanit Date: Mon, 18 Jul 2022 03:38:33 -0500 Subject: KVM: SVM: Fix x2APIC MSRs interception The index for svm_direct_access_msrs was incorrectly initialized with the APIC MMIO register macros. Fix by introducing a macro for calculating x2APIC MSRs. Fixes: 5c127c85472c ("KVM: SVM: Adding support for configuring x2APIC MSRs interception") Cc: Maxim Levitsky Signed-off-by: Suravee Suthikulpanit Message-Id: <20220718083833.222117-1-suravee.suthikulpanit@amd.com> Reviewed-by: Maxim Levitsky Signed-off-by: Paolo Bonzini --- arch/x86/kvm/svm/svm.c | 52 ++++++++++++++++++++++++++------------------------ 1 file changed, 27 insertions(+), 25 deletions(-) (limited to 'arch/x86/kvm/svm/svm.c') diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index ba81a7e58f75..aef63aae922d 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -74,6 +74,8 @@ static uint64_t osvw_len = 4, osvw_status; static DEFINE_PER_CPU(u64, current_tsc_ratio); +#define X2APIC_MSR(x) (APIC_BASE_MSR + (x >> 4)) + static const struct svm_direct_access_msrs { u32 index; /* Index of the MSR */ bool always; /* True if intercept is initially cleared */ @@ -100,31 +102,31 @@ static const struct svm_direct_access_msrs { { .index = MSR_IA32_CR_PAT, .always = false }, { .index = MSR_AMD64_SEV_ES_GHCB, .always = true }, { .index = MSR_TSC_AUX, .always = false }, - { .index = (APIC_BASE_MSR + APIC_ID), .always = false }, - { .index = (APIC_BASE_MSR + APIC_LVR), .always = false }, - { .index = (APIC_BASE_MSR + APIC_TASKPRI), .always = false }, - { .index = (APIC_BASE_MSR + APIC_ARBPRI), .always = false }, - { .index = (APIC_BASE_MSR + APIC_PROCPRI), .always = false }, - { .index = (APIC_BASE_MSR + APIC_EOI), .always = false }, - { .index = (APIC_BASE_MSR + APIC_RRR), .always = false }, - { .index = (APIC_BASE_MSR + APIC_LDR), .always = false }, - { .index = (APIC_BASE_MSR + APIC_DFR), .always = false }, - { .index = (APIC_BASE_MSR + APIC_SPIV), .always = false }, - { .index = (APIC_BASE_MSR + APIC_ISR), .always = false }, - { .index = (APIC_BASE_MSR + APIC_TMR), .always = false }, - { .index = (APIC_BASE_MSR + APIC_IRR), .always = false }, - { .index = (APIC_BASE_MSR + APIC_ESR), .always = false }, - { .index = (APIC_BASE_MSR + APIC_ICR), .always = false }, - { .index = (APIC_BASE_MSR + APIC_ICR2), .always = false }, - { .index = (APIC_BASE_MSR + APIC_LVTT), .always = false }, - { .index = (APIC_BASE_MSR + APIC_LVTTHMR), .always = false }, - { .index = (APIC_BASE_MSR + APIC_LVTPC), .always = false }, - { .index = (APIC_BASE_MSR + APIC_LVT0), .always = false }, - { .index = (APIC_BASE_MSR + APIC_LVT1), .always = false }, - { .index = (APIC_BASE_MSR + APIC_LVTERR), .always = false }, - { .index = (APIC_BASE_MSR + APIC_TMICT), .always = false }, - { .index = (APIC_BASE_MSR + APIC_TMCCT), .always = false }, - { .index = (APIC_BASE_MSR + APIC_TDCR), .always = false }, + { .index = X2APIC_MSR(APIC_ID), .always = false }, + { .index = X2APIC_MSR(APIC_LVR), .always = false }, + { .index = X2APIC_MSR(APIC_TASKPRI), .always = false }, + { .index = X2APIC_MSR(APIC_ARBPRI), .always = false }, + { .index = X2APIC_MSR(APIC_PROCPRI), .always = false }, + { .index = X2APIC_MSR(APIC_EOI), .always = false }, + { .index = X2APIC_MSR(APIC_RRR), .always = false }, + { .index = X2APIC_MSR(APIC_LDR), .always = false }, + { .index = X2APIC_MSR(APIC_DFR), .always = false }, + { .index = X2APIC_MSR(APIC_SPIV), .always = false }, + { .index = X2APIC_MSR(APIC_ISR), .always = false }, + { .index = X2APIC_MSR(APIC_TMR), .always = false }, + { .index = X2APIC_MSR(APIC_IRR), .always = false }, + { .index = X2APIC_MSR(APIC_ESR), .always = false }, + { .index = X2APIC_MSR(APIC_ICR), .always = false }, + { .index = X2APIC_MSR(APIC_ICR2), .always = false }, + { .index = X2APIC_MSR(APIC_LVTT), .always = false }, + { .index = X2APIC_MSR(APIC_LVTTHMR), .always = false }, + { .index = X2APIC_MSR(APIC_LVTPC), .always = false }, + { .index = X2APIC_MSR(APIC_LVT0), .always = false }, + { .index = X2APIC_MSR(APIC_LVT1), .always = false }, + { .index = X2APIC_MSR(APIC_LVTERR), .always = false }, + { .index = X2APIC_MSR(APIC_TMICT), .always = false }, + { .index = X2APIC_MSR(APIC_TMCCT), .always = false }, + { .index = X2APIC_MSR(APIC_TDCR), .always = false }, { .index = MSR_INVALID, .always = false }, }; -- cgit v1.2.3 From 0a8735a6acf36ac35499563dc44f3e3d5034a2ce Mon Sep 17 00:00:00 2001 From: Suravee Suthikulpanit Date: Sun, 24 Jul 2022 22:34:28 -0500 Subject: KVM: SVM: Do not virtualize MSR accesses for APIC LVTT register AMD does not support APIC TSC-deadline timer mode. AVIC hardware will generate GP fault when guest kernel writes 1 to bits [18] of the APIC LVTT register (offset 0x32) to set the timer mode. (Note: bit 18 is reserved on AMD system). Therefore, always intercept and let KVM emulate the MSR accesses. Fixes: f3d7c8aa6882 ("KVM: SVM: Fix x2APIC MSRs interception") Signed-off-by: Suravee Suthikulpanit Message-Id: <20220725033428.3699-1-suravee.suthikulpanit@amd.com> Signed-off-by: Paolo Bonzini --- arch/x86/kvm/svm/svm.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) (limited to 'arch/x86/kvm/svm/svm.c') diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index aef63aae922d..3e0639a68385 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -118,7 +118,14 @@ static const struct svm_direct_access_msrs { { .index = X2APIC_MSR(APIC_ESR), .always = false }, { .index = X2APIC_MSR(APIC_ICR), .always = false }, { .index = X2APIC_MSR(APIC_ICR2), .always = false }, - { .index = X2APIC_MSR(APIC_LVTT), .always = false }, + + /* + * Note: + * AMD does not virtualize APIC TSC-deadline timer mode, but it is + * emulated by KVM. When setting APIC LVTT (0x832) register bit 18, + * the AVIC hardware would generate GP fault. Therefore, always + * intercept the MSR 0x832, and do not setup direct_access_msr. + */ { .index = X2APIC_MSR(APIC_LVTTHMR), .always = false }, { .index = X2APIC_MSR(APIC_LVTPC), .always = false }, { .index = X2APIC_MSR(APIC_LVT0), .always = false }, -- cgit v1.2.3