| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-Id: <20200320180034.672927065@linutronix.de>
Date: Fri, 20 Mar 2020 19:00:19 +0100
From: Thomas Gleixner <tglx@...utronix.de>
To: LKML <linux-kernel@...r.kernel.org>
Cc: x86@...nel.org, Paul McKenney <paulmck@...nel.org>,
Josh Poimboeuf <jpoimboe@...hat.com>,
"Joel Fernandes (Google)" <joel@...lfernandes.org>,
"Steven Rostedt (VMware)" <rostedt@...dmis.org>,
Masami Hiramatsu <mhiramat@...nel.org>,
Alexei Starovoitov <ast@...nel.org>,
Frederic Weisbecker <frederic@...nel.org>,
Mathieu Desnoyers <mathieu.desnoyers@...icios.com>,
Brian Gerst <brgerst@...il.com>,
Juergen Gross <jgross@...e.com>,
Alexandre Chartre <alexandre.chartre@...cle.com>,
Tom Lendacky <thomas.lendacky@....com>,
Paolo Bonzini <pbonzini@...hat.com>, kvm@...r.kernel.org,
Peter Zijlstra <peterz@...radead.org>
Subject: [patch V3 23/23] x86/kvm/svm: Move guest enter/exit into .noinstr.text
Split out the really last steps of guest enter and the early guest exit
code and mark it .noinstr.text. Add the required instr_begin()/end() pairs
around "safe" code and replace the wrmsr() with native_wrmsr() to prevent a
tracepoint injection.
Signed-off-by: Thomas Gleixner <tglx@...utronix.de>
Cc: Tom Lendacky <thomas.lendacky@....com>
Cc: Paolo Bonzini <pbonzini@...hat.com>
Cc: kvm@...r.kernel.org
---
arch/x86/kvm/svm.c | 114 ++++++++++++++++++++++++++++-------------------------
1 file changed, 62 insertions(+), 52 deletions(-)
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -5714,58 +5714,9 @@ static void svm_cancel_injection(struct
svm_complete_interrupts(svm);
}
-static void svm_vcpu_run(struct kvm_vcpu *vcpu)
+static noinstr void svm_vcpu_enter_exit(struct kvm_vcpu *vcpu,
+ struct vcpu_svm *svm)
{
- struct vcpu_svm *svm = to_svm(vcpu);
-
- svm->vmcb->save.rax = vcpu->arch.regs[VCPU_REGS_RAX];
- svm->vmcb->save.rsp = vcpu->arch.regs[VCPU_REGS_RSP];
- svm->vmcb->save.rip = vcpu->arch.regs[VCPU_REGS_RIP];
-
- /*
- * A vmexit emulation is required before the vcpu can be executed
- * again.
- */
- if (unlikely(svm->nested.exit_required))
- return;
-
- /*
- * Disable singlestep if we're injecting an interrupt/exception.
- * We don't want our modified rflags to be pushed on the stack where
- * we might not be able to easily reset them if we disabled NMI
- * singlestep later.
- */
- if (svm->nmi_singlestep && svm->vmcb->control.event_inj) {
- /*
- * Event injection happens before external interrupts cause a
- * vmexit and interrupts are disabled here, so smp_send_reschedule
- * is enough to force an immediate vmexit.
- */
- disable_nmi_singlestep(svm);
- smp_send_reschedule(vcpu->cpu);
- }
-
- pre_svm_run(svm);
-
- sync_lapic_to_cr8(vcpu);
-
- svm->vmcb->save.cr2 = vcpu->arch.cr2;
-
- clgi();
- kvm_load_guest_xsave_state(vcpu);
-
- if (lapic_in_kernel(vcpu) &&
- vcpu->arch.apic->lapic_timer.timer_advance_ns)
- kvm_wait_lapic_expire(vcpu);
-
- /*
- * If this vCPU has touched SPEC_CTRL, restore the guest's value if
- * it's non-zero. Since vmentry is serialising on affected CPUs, there
- * is no need to worry about the conditional branch over the wrmsr
- * being speculatively taken.
- */
- x86_spec_ctrl_set_guest(svm->spec_ctrl, svm->virt_spec_ctrl);
-
/*
* VMENTER enables interrupts (host state), but the kernel state is
* interrupts disabled when this is invoked. Also tell RCU about
@@ -5780,8 +5731,10 @@ static void svm_vcpu_run(struct kvm_vcpu
* take locks (lockdep needs RCU) and calls into world and some
* more.
*/
+ instr_begin();
__trace_hardirqs_on();
lockdep_hardirqs_on_prepare(CALLER_ADDR0);
+ instr_end();
guest_enter_irqoff();
lockdep_hardirqs_on(CALLER_ADDR0);
@@ -5881,7 +5834,7 @@ static void svm_vcpu_run(struct kvm_vcpu
vmexit_fill_RSB();
#ifdef CONFIG_X86_64
- wrmsrl(MSR_GS_BASE, svm->host.gs_base);
+ native_wrmsrl(MSR_GS_BASE, svm->host.gs_base);
#else
loadsegment(fs, svm->host.fs);
#ifndef CONFIG_X86_32_LAZY_GS
@@ -5904,7 +5857,64 @@ static void svm_vcpu_run(struct kvm_vcpu
*/
lockdep_hardirqs_off(CALLER_ADDR0);
guest_exit_irqoff();
+ instr_begin();
__trace_hardirqs_off();
+ instr_end();
+}
+
+static void svm_vcpu_run(struct kvm_vcpu *vcpu)
+{
+ struct vcpu_svm *svm = to_svm(vcpu);
+
+ svm->vmcb->save.rax = vcpu->arch.regs[VCPU_REGS_RAX];
+ svm->vmcb->save.rsp = vcpu->arch.regs[VCPU_REGS_RSP];
+ svm->vmcb->save.rip = vcpu->arch.regs[VCPU_REGS_RIP];
+
+ /*
+ * A vmexit emulation is required before the vcpu can be executed
+ * again.
+ */
+ if (unlikely(svm->nested.exit_required))
+ return;
+
+ /*
+ * Disable singlestep if we're injecting an interrupt/exception.
+ * We don't want our modified rflags to be pushed on the stack where
+ * we might not be able to easily reset them if we disabled NMI
+ * singlestep later.
+ */
+ if (svm->nmi_singlestep && svm->vmcb->control.event_inj) {
+ /*
+ * Event injection happens before external interrupts cause a
+ * vmexit and interrupts are disabled here, so smp_send_reschedule
+ * is enough to force an immediate vmexit.
+ */
+ disable_nmi_singlestep(svm);
+ smp_send_reschedule(vcpu->cpu);
+ }
+
+ pre_svm_run(svm);
+
+ sync_lapic_to_cr8(vcpu);
+
+ svm->vmcb->save.cr2 = vcpu->arch.cr2;
+
+ clgi();
+ kvm_load_guest_xsave_state(vcpu);
+
+ if (lapic_in_kernel(vcpu) &&
+ vcpu->arch.apic->lapic_timer.timer_advance_ns)
+ kvm_wait_lapic_expire(vcpu);
+
+ /*
+ * If this vCPU has touched SPEC_CTRL, restore the guest's value if
+ * it's non-zero. Since vmentry is serialising on affected CPUs, there
+ * is no need to worry about the conditional branch over the wrmsr
+ * being speculatively taken.
+ */
+ x86_spec_ctrl_set_guest(svm->spec_ctrl, svm->virt_spec_ctrl);
+
+ svm_vcpu_enter_exit(vcpu, svm);
/*
* We do not use IBRS in the kernel. If this vCPU has used the
Powered by blists - more mailing lists