From: Liu, Jinsong Date: Wed, 26 Sep 2012 10:05:10 +0000 (+0200) Subject: x86: vMCE injection X-Git-Tag: archive/raspbian/4.8.0-1+rpi1~1^2~7850 X-Git-Url: https://dgit.raspbian.org/?a=commitdiff_plain;h=513e591c04d9d4f9ffe9ec282daaba798c30c176;p=xen.git x86: vMCE injection In our test for win8 guest mce, we find a bug that no matter what SRAO/SRAR error xen inject to win8 guest, it always reboot. The root cause is, current Xen vMCE logic inject vMCE# only to vcpu0, this is not correct for Intel MCE (Under Intel arch, h/w generate MCE# to all CPUs). This patch fixes vMCE injection bug, injecting vMCE# to all vcpus on Intel platforms. Signed-off-by: Liu, Jinsong - increase flexibility be making new second argument of inject_vmce() a VCPU ID rather than just a boolean Acked-by: Christoph Egger (on just this change) - fix condition evaluation order in inject_vmce() Signed-off-by: Jan Beulich Committed-by: Jan Beulich --- diff --git a/xen/arch/x86/cpu/mcheck/mce.h b/xen/arch/x86/cpu/mcheck/mce.h index d9b0647661..5b33934851 100644 --- a/xen/arch/x86/cpu/mcheck/mce.h +++ b/xen/arch/x86/cpu/mcheck/mce.h @@ -168,7 +168,7 @@ void x86_mcinfo_dump(struct mc_info *mi); int fill_vmsr_data(struct mcinfo_bank *mc_bank, struct domain *d, uint64_t gstatus); -int inject_vmce(struct domain *d); +int inject_vmce(struct domain *d, int vcpu); static inline int mce_vendor_bank_msr(const struct vcpu *v, uint32_t msr) { diff --git a/xen/arch/x86/cpu/mcheck/mce_intel.c b/xen/arch/x86/cpu/mcheck/mce_intel.c index 993ec4ce56..2f7709bd06 100644 --- a/xen/arch/x86/cpu/mcheck/mce_intel.c +++ b/xen/arch/x86/cpu/mcheck/mce_intel.c @@ -359,7 +359,7 @@ static void intel_memerr_dhandler( } /* We will inject vMCE to DOMU*/ - if ( inject_vmce(d) < 0 ) + if ( inject_vmce(d, -1) < 0 ) { mce_printk(MCE_QUIET, "inject vMCE to DOM%d" " failed\n", d->domain_id); diff --git a/xen/arch/x86/cpu/mcheck/vmce.c b/xen/arch/x86/cpu/mcheck/vmce.c index 4ae2853e61..1432870e53 100644 --- a/xen/arch/x86/cpu/mcheck/vmce.c +++ b/xen/arch/x86/cpu/mcheck/vmce.c @@ -324,51 +324,39 @@ static int vmce_load_vcpu_ctxt(struct domain *d, hvm_domain_context_t *h) HVM_REGISTER_SAVE_RESTORE(VMCE_VCPU, vmce_save_vcpu_ctxt, vmce_load_vcpu_ctxt, 1, HVMSR_PER_VCPU); -int inject_vmce(struct domain *d) +/* + * for Intel MCE, broadcast vMCE to all vcpus + * for AMD MCE, only inject vMCE to vcpu0 + */ +int inject_vmce(struct domain *d, int vcpu) { - int cpu = smp_processor_id(); + struct vcpu *v; - /* PV guest and HVM guest have different vMCE# injection methods. */ - if ( !test_and_set_bool(d->vcpu[0]->mce_pending) ) + for_each_vcpu ( d, v ) { - if ( d->is_hvm ) + if ( vcpu >= 0 && v->vcpu_id != vcpu ) + continue; + + if ( (is_hvm_domain(d) || + guest_has_trap_callback(d, v->vcpu_id, TRAP_machine_check)) && + !test_and_set_bool(v->mce_pending) ) { - mce_printk(MCE_VERBOSE, "MCE: inject vMCE to HVM DOM %d\n", - d->domain_id); - vcpu_kick(d->vcpu[0]); + mce_printk(MCE_VERBOSE, "MCE: inject vMCE to d%d:v%d\n", + d->domain_id, v->vcpu_id); + vcpu_kick(v); } else { - mce_printk(MCE_VERBOSE, "MCE: inject vMCE to PV DOM%d\n", - d->domain_id); - if ( guest_has_trap_callback(d, 0, TRAP_machine_check) ) - { - cpumask_copy(d->vcpu[0]->cpu_affinity_tmp, - d->vcpu[0]->cpu_affinity); - mce_printk(MCE_VERBOSE, "MCE: CPU%d set affinity, old %d\n", - cpu, d->vcpu[0]->processor); - vcpu_set_affinity(d->vcpu[0], cpumask_of(cpu)); - vcpu_kick(d->vcpu[0]); - } - else - { - mce_printk(MCE_VERBOSE, - "MCE: Kill PV guest with No MCE handler\n"); - domain_crash(d); - } + mce_printk(MCE_QUIET, "Failed to inject vMCE to d%d:v%d\n", + d->domain_id, v->vcpu_id); + return -EBUSY; } + + if ( vcpu >= 0 ) + return 0; } - else - { - /* new vMCE comes while first one has not been injected yet, - * in this case, inject fail. [We can't lose this vMCE for - * the mce node's consistency]. - */ - mce_printk(MCE_QUIET, "There's a pending vMCE waiting to be injected " - " to this DOM%d!\n", d->domain_id); - return -1; - } - return 0; + + return v ? -ESRCH : 0; } int fill_vmsr_data(struct mcinfo_bank *mc_bank, struct domain *d,