* Re: [PATCH v9 4/6] x86/kvm/hyper-v: Add support for synthetic debugger capability
From: Vitaly Kuznetsov @ 2020-03-23 10:36 UTC (permalink / raw)
To: Jon Doron; +Cc: kvm, linux-hyperv
In-Reply-To: <20200320172839.1144395-5-arilou@gmail.com>
Jon Doron <arilou@gmail.com> writes:
> Add support for Hyper-V synthetic debugger (syndbg) interface.
> The syndbg interface is using MSRs to emulate a way to send/recv packets
> data.
>
> The debug transport dll (kdvm/kdnet) will identify if Hyper-V is enabled
> and if it supports the synthetic debugger interface it will attempt to
> use it, instead of trying to initialize a network adapter.
>
This commit seem to break tests, e.g.
# ./tools/testing/selftests/kvm/x86_64/state_test
==== Test Assertion Failure ====
lib/x86_64/processor.c:1023: r == nmsrs
pid=26436 tid=26436 - Argument list too long
1 0x000000000040a87f: vcpu_save_state at processor.c:1022 (discriminator 3)
2 0x00000000004011b3: main at state_test.c:171 (discriminator 4)
3 0x00007f0315cc63d4: ?? ??:0
4 0x0000000000401357: _start at ??:?
Unexpected result from KVM_GET_MSRS, r: 60 (failed MSR was 0x400000ff)
The problem is that the newly introduced MSRs don't allow
reading/writing by the host when KVM_CAP_HYPERV_SYNDBG is disabled, I
think we'll need to relax the requirement and allow at reading/writing by
the host. Something like
diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c
index f17156d36419..ca1f10498705 100644
--- a/arch/x86/kvm/hyperv.c
+++ b/arch/x86/kvm/hyperv.c
@@ -301,11 +301,11 @@ static void syndbg_exit(struct kvm_vcpu *vcpu, u32 msr)
kvm_make_request(KVM_REQ_HV_EXIT, vcpu);
}
-static int syndbg_set_msr(struct kvm_vcpu *vcpu, u32 msr, u64 data)
+static int syndbg_set_msr(struct kvm_vcpu *vcpu, u32 msr, u64 data, bool host)
{
struct kvm_hv_syndbg *syndbg = vcpu_to_hv_syndbg(vcpu);
- if (!syndbg->active)
+ if (!syndbg->active && !host)
return 1;
trace_kvm_hv_syndbg_set_msr(vcpu->vcpu_id,
@@ -313,7 +313,8 @@ static int syndbg_set_msr(struct kvm_vcpu *vcpu, u32 msr, u64 data)
switch (msr) {
case HV_X64_MSR_SYNDBG_CONTROL:
syndbg->control.control = data;
- syndbg_exit(vcpu, msr);
+ if (!host)
+ syndbg_exit(vcpu, msr);
break;
case HV_X64_MSR_SYNDBG_STATUS:
syndbg->control.status = data;
@@ -326,7 +327,8 @@ static int syndbg_set_msr(struct kvm_vcpu *vcpu, u32 msr, u64 data)
break;
case HV_X64_MSR_SYNDBG_PENDING_BUFFER:
syndbg->control.pending_page = data;
- syndbg_exit(vcpu, msr);
+ if (!host)
+ syndbg_exit(vcpu, msr);
break;
case HV_X64_MSR_SYNDBG_OPTIONS:
syndbg->options = data;
@@ -338,11 +340,11 @@ static int syndbg_set_msr(struct kvm_vcpu *vcpu, u32 msr, u64 data)
return 0;
}
-static int syndbg_get_msr(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata)
+static int syndbg_get_msr(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata, bool host)
{
struct kvm_hv_syndbg *syndbg = vcpu_to_hv_syndbg(vcpu);
- if (!syndbg->active)
+ if (!syndbg->active && !host)
return 1;
switch (msr) {
@@ -1174,7 +1176,7 @@ static int kvm_hv_set_msr_pw(struct kvm_vcpu *vcpu, u32 msr, u64 data,
break;
case HV_X64_MSR_SYNDBG_OPTIONS:
case HV_X64_MSR_SYNDBG_CONTROL ... HV_X64_MSR_SYNDBG_PENDING_BUFFER:
- return syndbg_set_msr(vcpu, msr, data);
+ return syndbg_set_msr(vcpu, msr, data, host);
default:
vcpu_unimpl(vcpu, "Hyper-V unhandled wrmsr: 0x%x data 0x%llx\n",
msr, data);
@@ -1304,7 +1306,7 @@ static int kvm_hv_set_msr(struct kvm_vcpu *vcpu, u32 msr, u64 data, bool host)
return 0;
}
-static int kvm_hv_get_msr_pw(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata)
+static int kvm_hv_get_msr_pw(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata, bool host)
{
u64 data = 0;
struct kvm *kvm = vcpu->kvm;
@@ -1343,7 +1345,7 @@ static int kvm_hv_get_msr_pw(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata)
break;
case HV_X64_MSR_SYNDBG_OPTIONS:
case HV_X64_MSR_SYNDBG_CONTROL ... HV_X64_MSR_SYNDBG_PENDING_BUFFER:
- return syndbg_get_msr(vcpu, msr, pdata);
+ return syndbg_get_msr(vcpu, msr, pdata, host);
default:
vcpu_unimpl(vcpu, "Hyper-V unhandled rdmsr: 0x%x\n", msr);
return 1;
@@ -1433,7 +1435,7 @@ int kvm_hv_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata, bool host)
int r;
mutex_lock(&vcpu->kvm->arch.hyperv.hv_lock);
- r = kvm_hv_get_msr_pw(vcpu, msr, pdata);
+ r = kvm_hv_get_msr_pw(vcpu, msr, pdata, host);
mutex_unlock(&vcpu->kvm->arch.hyperv.hv_lock);
return r;
} else
Note that I also omit syndbg_exit() when
HV_X64_MSR_SYNDBG_PENDING_BUFFER/HV_X64_MSR_SYNDBG_CONTROL are
written by the host to not get a self-induced exit to userspace, this is
likely not what we want on e.g. migration. Without it, we will fail
again:
==== Test Assertion Failure ====
x86_64/state_test.c:151: run->exit_reason == KVM_EXIT_IO
pid=7827 tid=7827 - Argument list too long
1 0x0000000000401109: main at state_test.c:148
2 0x00007ff5308d63d4: ?? ??:0
3 0x0000000000401357: _start at ??:?
Stage 2: unexpected exit reason: 27 (Unknown),
Alternatively, we may introduce a way to hide unsupported MSRs from
KVM_GET_MSRS but we don't do it for existing Hyper-V MSRs as of yet.
> Signed-off-by: Jon Doron <arilou@gmail.com>
> ---
> Documentation/virt/kvm/api.rst | 16 ++++
> arch/x86/include/asm/kvm_host.h | 14 +++
> arch/x86/kvm/hyperv.c | 158 +++++++++++++++++++++++++++++++-
> arch/x86/kvm/hyperv.h | 6 ++
> arch/x86/kvm/trace.h | 51 +++++++++++
> arch/x86/kvm/x86.c | 13 +++
> include/uapi/linux/kvm.h | 11 +++
> 7 files changed, 268 insertions(+), 1 deletion(-)
>
> diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst
> index 4872c47bbcff..fe992dcf4f93 100644
> --- a/Documentation/virt/kvm/api.rst
> +++ b/Documentation/virt/kvm/api.rst
> @@ -5024,6 +5024,7 @@ EOI was received.
> struct kvm_hyperv_exit {
> #define KVM_EXIT_HYPERV_SYNIC 1
> #define KVM_EXIT_HYPERV_HCALL 2
> + #define KVM_EXIT_HYPERV_SYNDBG 3
> __u32 type;
> __u32 pad1;
> union {
> @@ -5039,6 +5040,15 @@ EOI was received.
> __u64 result;
> __u64 params[2];
> } hcall;
> + struct {
> + __u32 msr;
> + __u32 pad2;
> + __u64 control;
> + __u64 status;
> + __u64 send_page;
> + __u64 recv_page;
> + __u64 pending_page;
> + } syndbg;
> } u;
> };
> /* KVM_EXIT_HYPERV */
> @@ -5055,6 +5065,12 @@ Hyper-V SynIC state change. Notification is used to remap SynIC
> event/message pages and to enable/disable SynIC messages/events processing
> in userspace.
>
> + - KVM_EXIT_HYPERV_SYNDBG -- synchronously notify user-space about
> +
> +Hyper-V Synthetic debugger state change. Notification is used to either update
> +the pending_page location or to send a control command (send the buffer located
> +in send_page or recv a buffer to recv_page).
> +
> ::
>
> /* KVM_EXIT_ARM_NISV */
> diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
> index 98959e8cd448..c09fa7401b13 100644
> --- a/arch/x86/include/asm/kvm_host.h
> +++ b/arch/x86/include/asm/kvm_host.h
> @@ -854,6 +854,19 @@ struct kvm_apic_map {
> struct kvm_lapic *phys_map[];
> };
>
> +/* Hyper-V synthetic debugger (SynDbg)*/
> +struct kvm_hv_syndbg {
> + struct {
> + u64 control;
> + u64 status;
> + u64 send_page;
> + u64 recv_page;
> + u64 pending_page;
> + } control;
> + u64 options;
> + bool active;
> +};
> +
> /* Hyper-V emulation context */
> struct kvm_hv {
> struct mutex hv_lock;
> @@ -877,6 +890,7 @@ struct kvm_hv {
> atomic_t num_mismatched_vp_indexes;
>
> struct hv_partition_assist_pg *hv_pa_pg;
> + struct kvm_hv_syndbg hv_syndbg;
> };
>
> enum kvm_irqchip_mode {
> diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c
> index 7383c7e7d4af..cd8d0142a841 100644
> --- a/arch/x86/kvm/hyperv.c
> +++ b/arch/x86/kvm/hyperv.c
> @@ -266,6 +266,115 @@ static int synic_set_msr(struct kvm_vcpu_hv_synic *synic,
> return ret;
> }
>
> +void kvm_hv_activate_syndbg(struct kvm_vcpu *vcpu)
> +{
> + struct kvm_hv_syndbg *syndbg = vcpu_to_hv_syndbg(vcpu);
> +
> + syndbg->active = true;
> +}
> +
> +static int kvm_hv_syndbg_complete_userspace(struct kvm_vcpu *vcpu)
> +{
> + struct kvm *kvm = vcpu->kvm;
> + struct kvm_hv *hv = &kvm->arch.hyperv;
> +
> + if (vcpu->run->hyperv.u.syndbg.msr == HV_X64_MSR_SYNDBG_CONTROL)
> + hv->hv_syndbg.control.status =
> + vcpu->run->hyperv.u.syndbg.status;
> + return 1;
> +}
> +
> +static void syndbg_exit(struct kvm_vcpu *vcpu, u32 msr)
> +{
> + struct kvm_hv_syndbg *syndbg = vcpu_to_hv_syndbg(vcpu);
> + struct kvm_vcpu_hv *hv_vcpu = &vcpu->arch.hyperv;
> +
> + hv_vcpu->exit.type = KVM_EXIT_HYPERV_SYNDBG;
> + hv_vcpu->exit.u.syndbg.msr = msr;
> + hv_vcpu->exit.u.syndbg.control = syndbg->control.control;
> + hv_vcpu->exit.u.syndbg.send_page = syndbg->control.send_page;
> + hv_vcpu->exit.u.syndbg.recv_page = syndbg->control.recv_page;
> + hv_vcpu->exit.u.syndbg.pending_page = syndbg->control.pending_page;
> + vcpu->arch.complete_userspace_io =
> + kvm_hv_syndbg_complete_userspace;
> +
> + kvm_make_request(KVM_REQ_HV_EXIT, vcpu);
> +}
> +
> +static int syndbg_set_msr(struct kvm_vcpu *vcpu, u32 msr, u64 data)
> +{
> + struct kvm_hv_syndbg *syndbg = vcpu_to_hv_syndbg(vcpu);
> +
> + if (!syndbg->active)
> + return 1;
> +
> + trace_kvm_hv_syndbg_set_msr(vcpu->vcpu_id,
> + vcpu_to_hv_vcpu(vcpu)->vp_index, msr, data);
> + switch (msr) {
> + case HV_X64_MSR_SYNDBG_CONTROL:
> + syndbg->control.control = data;
> + syndbg_exit(vcpu, msr);
> + break;
> + case HV_X64_MSR_SYNDBG_STATUS:
> + syndbg->control.status = data;
> + break;
> + case HV_X64_MSR_SYNDBG_SEND_BUFFER:
> + syndbg->control.send_page = data;
> + break;
> + case HV_X64_MSR_SYNDBG_RECV_BUFFER:
> + syndbg->control.recv_page = data;
> + break;
> + case HV_X64_MSR_SYNDBG_PENDING_BUFFER:
> + syndbg->control.pending_page = data;
> + syndbg_exit(vcpu, msr);
> + break;
> + case HV_X64_MSR_SYNDBG_OPTIONS:
> + syndbg->options = data;
> + break;
> + default:
> + break;
> + }
> +
> + return 0;
> +}
> +
> +static int syndbg_get_msr(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata)
> +{
> + struct kvm_hv_syndbg *syndbg = vcpu_to_hv_syndbg(vcpu);
> +
> + if (!syndbg->active)
> + return 1;
> +
> + switch (msr) {
> + case HV_X64_MSR_SYNDBG_CONTROL:
> + *pdata = syndbg->control.control;
> + break;
> + case HV_X64_MSR_SYNDBG_STATUS:
> + *pdata = syndbg->control.status;
> + break;
> + case HV_X64_MSR_SYNDBG_SEND_BUFFER:
> + *pdata = syndbg->control.send_page;
> + break;
> + case HV_X64_MSR_SYNDBG_RECV_BUFFER:
> + *pdata = syndbg->control.recv_page;
> + break;
> + case HV_X64_MSR_SYNDBG_PENDING_BUFFER:
> + *pdata = syndbg->control.pending_page;
> + break;
> + case HV_X64_MSR_SYNDBG_OPTIONS:
> + *pdata = syndbg->options;
> + break;
> + default:
> + break;
> + }
> +
> + trace_kvm_hv_syndbg_get_msr(vcpu->vcpu_id,
> + vcpu_to_hv_vcpu(vcpu)->vp_index, msr,
> + *pdata);
> +
> + return 0;
> +}
> +
> static int synic_get_msr(struct kvm_vcpu_hv_synic *synic, u32 msr, u64 *pdata,
> bool host)
> {
> @@ -800,6 +909,8 @@ static bool kvm_hv_msr_partition_wide(u32 msr)
> case HV_X64_MSR_REENLIGHTENMENT_CONTROL:
> case HV_X64_MSR_TSC_EMULATION_CONTROL:
> case HV_X64_MSR_TSC_EMULATION_STATUS:
> + case HV_X64_MSR_SYNDBG_OPTIONS:
> + case HV_X64_MSR_SYNDBG_CONTROL ... HV_X64_MSR_SYNDBG_PENDING_BUFFER:
> r = true;
> break;
> }
> @@ -1061,6 +1172,9 @@ static int kvm_hv_set_msr_pw(struct kvm_vcpu *vcpu, u32 msr, u64 data,
> if (!host)
> return 1;
> break;
> + case HV_X64_MSR_SYNDBG_OPTIONS:
> + case HV_X64_MSR_SYNDBG_CONTROL ... HV_X64_MSR_SYNDBG_PENDING_BUFFER:
> + return syndbg_set_msr(vcpu, msr, data);
> default:
> vcpu_unimpl(vcpu, "Hyper-V unhandled wrmsr: 0x%x data 0x%llx\n",
> msr, data);
> @@ -1227,6 +1341,9 @@ static int kvm_hv_get_msr_pw(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata)
> case HV_X64_MSR_TSC_EMULATION_STATUS:
> data = hv->hv_tsc_emulation_status;
> break;
> + case HV_X64_MSR_SYNDBG_OPTIONS:
> + case HV_X64_MSR_SYNDBG_CONTROL ... HV_X64_MSR_SYNDBG_PENDING_BUFFER:
> + return syndbg_get_msr(vcpu, msr, pdata);
> default:
> vcpu_unimpl(vcpu, "Hyper-V unhandled rdmsr: 0x%x\n", msr);
> return 1;
> @@ -1799,9 +1916,16 @@ static struct kvm_cpuid_entry2 evmcs_cpuid_entries[] = {
> { .function = HYPERV_CPUID_NESTED_FEATURES },
> };
>
> +static struct kvm_cpuid_entry2 syndbg_cpuid_entries[] = {
> + { .function = HYPERV_CPUID_SYNDBG_VENDOR_AND_MAX_FUNCTIONS },
> + { .function = HYPERV_CPUID_SYNDBG_INTERFACE },
> + { .function = HYPERV_CPUID_SYNDBG_PLATFORM_CAPABILITIES },
> +};
> +
> #define HV_MAX_CPUID_ENTRIES \
> ARRAY_SIZE(core_cpuid_entries) +\
> - ARRAY_SIZE(evmcs_cpuid_entries)
> + ARRAY_SIZE(evmcs_cpuid_entries) +\
> + ARRAY_SIZE(syndbg_cpuid_entries)
>
> int kvm_vcpu_ioctl_get_hv_cpuid(struct kvm_vcpu *vcpu, struct kvm_cpuid2 *cpuid,
> struct kvm_cpuid_entry2 __user *entries)
> @@ -1809,6 +1933,7 @@ int kvm_vcpu_ioctl_get_hv_cpuid(struct kvm_vcpu *vcpu, struct kvm_cpuid2 *cpuid,
> uint16_t evmcs_ver = 0;
> struct kvm_cpuid_entry2 cpuid_entries[HV_MAX_CPUID_ENTRIES];
> int i, nent = 0;
> + struct kvm_hv_syndbg *syndbg = vcpu_to_hv_syndbg(vcpu);
>
> /* Set the core cpuid entries required for Hyper-V */
> memcpy(&cpuid_entries[nent], &core_cpuid_entries,
> @@ -1825,6 +1950,13 @@ int kvm_vcpu_ioctl_get_hv_cpuid(struct kvm_vcpu *vcpu, struct kvm_cpuid2 *cpuid,
> nent += ARRAY_SIZE(evmcs_cpuid_entries);
> }
>
> + if (syndbg->active) {
> + /* Syndbg is enabled, add the required Syndbg CPUID leafs */
> + memcpy(&cpuid_entries[nent], &syndbg_cpuid_entries,
> + sizeof(syndbg_cpuid_entries));
> + nent += ARRAY_SIZE(syndbg_cpuid_entries);
> + }
> +
> if (cpuid->nent < nent)
> return -E2BIG;
>
> @@ -1878,6 +2010,12 @@ int kvm_vcpu_ioctl_get_hv_cpuid(struct kvm_vcpu *vcpu, struct kvm_cpuid2 *cpuid,
> ent->edx |= HV_FEATURE_FREQUENCY_MSRS_AVAILABLE;
> ent->edx |= HV_FEATURE_GUEST_CRASH_MSR_AVAILABLE;
>
> + if (syndbg->active) {
> + ent->ebx |= HV_X64_DEBUGGING;
> + ent->edx |= HV_X64_GUEST_DEBUGGING_AVAILABLE;
> + ent->edx |= HV_FEATURE_DEBUG_MSRS_AVAILABLE;
> + }
> +
> /*
> * Direct Synthetic timers only make sense with in-kernel
> * LAPIC
> @@ -1921,6 +2059,24 @@ int kvm_vcpu_ioctl_get_hv_cpuid(struct kvm_vcpu *vcpu, struct kvm_cpuid2 *cpuid,
>
> break;
>
> + case HYPERV_CPUID_SYNDBG_VENDOR_AND_MAX_FUNCTIONS:
> + memcpy(signature, "Linux KVM Hv", 12);
> +
> + ent->eax = 0;
> + ent->ebx = signature[0];
> + ent->ecx = signature[1];
> + ent->edx = signature[2];
> + break;
> +
> + case HYPERV_CPUID_SYNDBG_INTERFACE:
> + memcpy(signature, "VS#1\0\0\0\0\0\0\0\0", 12);
> + ent->eax = signature[0];
> + break;
> +
> + case HYPERV_CPUID_SYNDBG_PLATFORM_CAPABILITIES:
> + ent->eax |= HV_X64_SYNDBG_CAP_ALLOW_KERNEL_DEBUGGING;
> + break;
> +
> default:
> break;
> }
> diff --git a/arch/x86/kvm/hyperv.h b/arch/x86/kvm/hyperv.h
> index 5e4780bf6dd7..45aaaf08bf15 100644
> --- a/arch/x86/kvm/hyperv.h
> +++ b/arch/x86/kvm/hyperv.h
> @@ -73,6 +73,11 @@ static inline struct kvm_vcpu *synic_to_vcpu(struct kvm_vcpu_hv_synic *synic)
> return hv_vcpu_to_vcpu(container_of(synic, struct kvm_vcpu_hv, synic));
> }
>
> +static inline struct kvm_hv_syndbg *vcpu_to_hv_syndbg(struct kvm_vcpu *vcpu)
> +{
> + return &vcpu->kvm->arch.hyperv.hv_syndbg;
> +}
> +
> int kvm_hv_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data, bool host);
> int kvm_hv_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata, bool host);
>
> @@ -83,6 +88,7 @@ void kvm_hv_irq_routing_update(struct kvm *kvm);
> int kvm_hv_synic_set_irq(struct kvm *kvm, u32 vcpu_id, u32 sint);
> void kvm_hv_synic_send_eoi(struct kvm_vcpu *vcpu, int vector);
> int kvm_hv_activate_synic(struct kvm_vcpu *vcpu, bool dont_zero_synic_pages);
> +void kvm_hv_activate_syndbg(struct kvm_vcpu *vcpu);
>
> void kvm_hv_vcpu_init(struct kvm_vcpu *vcpu);
> void kvm_hv_vcpu_postcreate(struct kvm_vcpu *vcpu);
> diff --git a/arch/x86/kvm/trace.h b/arch/x86/kvm/trace.h
> index f194dd058470..bf6c3852868d 100644
> --- a/arch/x86/kvm/trace.h
> +++ b/arch/x86/kvm/trace.h
> @@ -1515,6 +1515,57 @@ TRACE_EVENT(kvm_nested_vmenter_failed,
> __print_symbolic(__entry->err, VMX_VMENTER_INSTRUCTION_ERRORS))
> );
>
> +/*
> + * Tracepoint for syndbg_set_msr.
> + */
> +TRACE_EVENT(kvm_hv_syndbg_set_msr,
> + TP_PROTO(int vcpu_id, u32 vp_index, u32 msr, u64 data),
> + TP_ARGS(vcpu_id, vp_index, msr, data),
> +
> + TP_STRUCT__entry(
> + __field(int, vcpu_id)
> + __field(u32, vp_index)
> + __field(u32, msr)
> + __field(u64, data)
> + ),
> +
> + TP_fast_assign(
> + __entry->vcpu_id = vcpu_id;
> + __entry->vp_index = vp_index;
> + __entry->msr = msr;
> + __entry->data = data;
> + ),
> +
> + TP_printk("vcpu_id %d vp_index %u msr 0x%x data 0x%llx",
> + __entry->vcpu_id, __entry->vp_index, __entry->msr,
> + __entry->data)
> +);
> +
> +/*
> + * Tracepoint for syndbg_get_msr.
> + */
> +TRACE_EVENT(kvm_hv_syndbg_get_msr,
> + TP_PROTO(int vcpu_id, u32 vp_index, u32 msr, u64 data),
> + TP_ARGS(vcpu_id, vp_index, msr, data),
> +
> + TP_STRUCT__entry(
> + __field(int, vcpu_id)
> + __field(u32, vp_index)
> + __field(u32, msr)
> + __field(u64, data)
> + ),
> +
> + TP_fast_assign(
> + __entry->vcpu_id = vcpu_id;
> + __entry->vp_index = vp_index;
> + __entry->msr = msr;
> + __entry->data = data;
> + ),
> +
> + TP_printk("vcpu_id %d vp_index %u msr 0x%x data 0x%llx",
> + __entry->vcpu_id, __entry->vp_index, __entry->msr,
> + __entry->data)
> +);
> #endif /* _TRACE_KVM_H */
>
> #undef TRACE_INCLUDE_PATH
> diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
> index 3156e25b0774..7bfa30d7a525 100644
> --- a/arch/x86/kvm/x86.c
> +++ b/arch/x86/kvm/x86.c
> @@ -1214,6 +1214,10 @@ static const u32 emulated_msrs_all[] = {
> HV_X64_MSR_VP_ASSIST_PAGE,
> HV_X64_MSR_REENLIGHTENMENT_CONTROL, HV_X64_MSR_TSC_EMULATION_CONTROL,
> HV_X64_MSR_TSC_EMULATION_STATUS,
> + HV_X64_MSR_SYNDBG_OPTIONS,
> + HV_X64_MSR_SYNDBG_CONTROL, HV_X64_MSR_SYNDBG_STATUS,
> + HV_X64_MSR_SYNDBG_SEND_BUFFER, HV_X64_MSR_SYNDBG_RECV_BUFFER,
> + HV_X64_MSR_SYNDBG_PENDING_BUFFER,
>
> MSR_KVM_ASYNC_PF_EN, MSR_KVM_STEAL_TIME,
> MSR_KVM_PV_EOI_EN,
> @@ -2906,6 +2910,8 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
> */
> break;
> case HV_X64_MSR_GUEST_OS_ID ... HV_X64_MSR_SINT15:
> + case HV_X64_MSR_SYNDBG_CONTROL ... HV_X64_MSR_SYNDBG_PENDING_BUFFER:
> + case HV_X64_MSR_SYNDBG_OPTIONS:
> case HV_X64_MSR_CRASH_P0 ... HV_X64_MSR_CRASH_P4:
> case HV_X64_MSR_CRASH_CTL:
> case HV_X64_MSR_STIMER0_CONFIG ... HV_X64_MSR_STIMER3_COUNT:
> @@ -3151,6 +3157,8 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
> msr_info->data = 0x20000000;
> break;
> case HV_X64_MSR_GUEST_OS_ID ... HV_X64_MSR_SINT15:
> + case HV_X64_MSR_SYNDBG_CONTROL ... HV_X64_MSR_SYNDBG_PENDING_BUFFER:
> + case HV_X64_MSR_SYNDBG_OPTIONS:
> case HV_X64_MSR_CRASH_P0 ... HV_X64_MSR_CRASH_P4:
> case HV_X64_MSR_CRASH_CTL:
> case HV_X64_MSR_STIMER0_CONFIG ... HV_X64_MSR_STIMER3_COUNT:
> @@ -3323,6 +3331,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
> case KVM_CAP_HYPERV_TLBFLUSH:
> case KVM_CAP_HYPERV_SEND_IPI:
> case KVM_CAP_HYPERV_CPUID:
> + case KVM_CAP_HYPERV_SYNDBG:
> case KVM_CAP_PCI_SEGMENT:
> case KVM_CAP_DEBUGREGS:
> case KVM_CAP_X86_ROBUST_SINGLESTEP:
> @@ -4178,6 +4187,10 @@ static int kvm_vcpu_ioctl_enable_cap(struct kvm_vcpu *vcpu,
> return -EINVAL;
>
> switch (cap->cap) {
> + case KVM_CAP_HYPERV_SYNDBG:
> + kvm_hv_activate_syndbg(vcpu);
> + return 0;
> +
> case KVM_CAP_HYPERV_SYNIC2:
> if (cap->args[0])
> return -EINVAL;
> diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
> index 7ee0ddc4c457..0b573e1155c8 100644
> --- a/include/uapi/linux/kvm.h
> +++ b/include/uapi/linux/kvm.h
> @@ -188,6 +188,7 @@ struct kvm_s390_cmma_log {
> struct kvm_hyperv_exit {
> #define KVM_EXIT_HYPERV_SYNIC 1
> #define KVM_EXIT_HYPERV_HCALL 2
> +#define KVM_EXIT_HYPERV_SYNDBG 3
> __u32 type;
> __u32 pad1;
> union {
> @@ -203,6 +204,15 @@ struct kvm_hyperv_exit {
> __u64 result;
> __u64 params[2];
> } hcall;
> + struct {
> + __u32 msr;
> + __u32 pad2;
> + __u64 control;
> + __u64 status;
> + __u64 send_page;
> + __u64 recv_page;
> + __u64 pending_page;
> + } syndbg;
> } u;
> };
>
> @@ -1012,6 +1022,7 @@ struct kvm_ppc_resize_hpt {
> #define KVM_CAP_ARM_NISV_TO_USER 177
> #define KVM_CAP_ARM_INJECT_EXT_DABT 178
> #define KVM_CAP_S390_VCPU_RESETS 179
> +#define KVM_CAP_HYPERV_SYNDBG 180
>
> #ifdef KVM_CAP_IRQ_ROUTING
--
Vitaly
^ permalink raw reply related
* [PATCH V2 0/6] x86/Hyper-V: Panic code path fixes
From: ltykernel @ 2020-03-23 13:09 UTC (permalink / raw)
To: kys, haiyangz, sthemmin, liuwe, tglx, mingo, bp, hpa, x86,
michael.h.kelley
Cc: Tianyu Lan, linux-hyperv, linux-kernel, vkuznets
From: Tianyu Lan <Tianyu.Lan@microsoft.com>
This patchset fixes some issues in the Hyper-V panic code path.
Patch 1 resolves issue that panic system still responses network
packets.
Patch 2-3,5-6 resolves crash enlightenment issues.
Patch 4 is to set crash_kexec_post_notifiers to true for Hyper-V
VM in order to report crash data or kmsg to host before running
kdump kernel.
Tianyu Lan (6):
x86/Hyper-V: Unload vmbus channel in hv panic callback
x86/Hyper-V: Free hv_panic_page when fail to register kmsg dump
x86/Hyper-V: Trigger crash enlightenment only once during system
crash.
x86/Hyper-V: Report crash register data or ksmg before running crash
kernel
x86/Hyper-V: Report crash register data when sysctl_record_panic_msg
is not set
x86/Hyper-V: Report crash data in die() when panic_on_oops is set
arch/x86/kernel/cpu/mshyperv.c | 10 ++++++++
drivers/hv/channel_mgmt.c | 3 +++
drivers/hv/vmbus_drv.c | 55 ++++++++++++++++++++++++++++--------------
3 files changed, 50 insertions(+), 18 deletions(-)
--
2.14.5
^ permalink raw reply
* [PATCH V2 3/6] x86/Hyper-V: Trigger crash enlightenment only once during system crash.
From: ltykernel @ 2020-03-23 13:09 UTC (permalink / raw)
To: kys, haiyangz, sthemmin, liuwe, tglx, mingo, bp, hpa, x86,
michael.h.kelley
Cc: Tianyu Lan, linux-hyperv, linux-kernel, vkuznets
In-Reply-To: <20200323130924.2968-1-Tianyu.Lan@microsoft.com>
From: Tianyu Lan <Tianyu.Lan@microsoft.com>
When a guest VM panics, Hyper-V should be notified only once via the
crash synthetic MSRs. Current Linux code might write these crash MSRs
twice during a system panic:
1) hyperv_panic/die_event() calling hyperv_report_panic()
2) hv_kmsg_dump() calling hyperv_report_panic_msg()
Fix this by not calling hyperv_report_panic() if a kmsg dump has been
successfully registered. The notification will happen later via
hyperv_report_panic_msg().
Signed-off-by: Tianyu Lan <Tianyu.Lan@microsoft.com>
---
Change since v1:
- Update commit log
---
drivers/hv/vmbus_drv.c | 14 ++++++++++++--
1 file changed, 12 insertions(+), 2 deletions(-)
diff --git a/drivers/hv/vmbus_drv.c b/drivers/hv/vmbus_drv.c
index 3a0472c8b7ae..d73fa8aa00a3 100644
--- a/drivers/hv/vmbus_drv.c
+++ b/drivers/hv/vmbus_drv.c
@@ -55,7 +55,12 @@ static int hyperv_panic_event(struct notifier_block *nb, unsigned long val,
vmbus_initiate_unload(true);
- if (ms_hyperv.misc_features & HV_FEATURE_GUEST_CRASH_MSR_AVAILABLE) {
+ /*
+ * Crash notify only can be triggered once. If crash notify
+ * message is available, just report kmsg to crash buffer.
+ */
+ if (ms_hyperv.misc_features & HV_FEATURE_GUEST_CRASH_MSR_AVAILABLE
+ && !hv_panic_page) {
regs = current_pt_regs();
hyperv_report_panic(regs, val);
}
@@ -68,7 +73,12 @@ static int hyperv_die_event(struct notifier_block *nb, unsigned long val,
struct die_args *die = (struct die_args *)args;
struct pt_regs *regs = die->regs;
- hyperv_report_panic(regs, val);
+ /*
+ * Crash notify only can be triggered once. If crash notify
+ * message is available, just report kmsg to crash buffer.
+ */
+ if (!hv_panic_page)
+ hyperv_report_panic(regs, val);
return NOTIFY_DONE;
}
--
2.14.5
^ permalink raw reply related
* [PATCH V2 6/6] x86/Hyper-V: Report crash data in die() when panic_on_oops is set
From: ltykernel @ 2020-03-23 13:09 UTC (permalink / raw)
To: kys, haiyangz, sthemmin, liuwe, michael.h.kelley
Cc: Tianyu Lan, linux-hyperv, linux-kernel, vkuznets
In-Reply-To: <20200323130924.2968-1-Tianyu.Lan@microsoft.com>
From: Tianyu Lan <Tianyu.Lan@microsoft.com>
When oops happens with panic_on_oops unset, the oops
thread is killed by die() and system continues to run.
In such case, guest should not report crash register
data to host since system still runs. Fix it.
Signed-off-by: Tianyu Lan <Tianyu.Lan@microsoft.com>
---
drivers/hv/vmbus_drv.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/hv/vmbus_drv.c b/drivers/hv/vmbus_drv.c
index 00447175c040..ecdb64db0e4a 100644
--- a/drivers/hv/vmbus_drv.c
+++ b/drivers/hv/vmbus_drv.c
@@ -89,7 +89,7 @@ static int hyperv_die_event(struct notifier_block *nb, unsigned long val,
* Crash notify only can be triggered once. If crash notify
* message is available, just report kmsg to crash buffer.
*/
- if (hyperv_report_reg())
+ if (hyperv_report_reg() && panic_on_oops)
hyperv_report_panic(regs, val);
return NOTIFY_DONE;
}
--
2.14.5
^ permalink raw reply related
* [PATCH V2 4/6] x86/Hyper-V: Report crash register data or ksmg before running crash kernel
From: ltykernel @ 2020-03-23 13:09 UTC (permalink / raw)
To: kys, haiyangz, sthemmin, liuwe, tglx, mingo, bp, hpa, x86,
michael.h.kelley
Cc: Tianyu Lan, linux-hyperv, linux-kernel, vkuznets
In-Reply-To: <20200323130924.2968-1-Tianyu.Lan@microsoft.com>
From: Tianyu Lan <Tianyu.Lan@microsoft.com>
When a guest VM panics, Hyper-V should be notified only once via the
crash synthetic MSRs. Current Linux code might write these crash MSRs
twice during a system panic:
1) hyperv_panic/die_event() calling hyperv_report_panic()
2) hv_kmsg_dump() calling hyperv_report_panic_msg()
Fix this by not calling hyperv_report_panic() if a kmsg dump has been
successfully registered. The notification will happen later via
hyperv_report_panic_msg().
Signed-off-by: Tianyu Lan <Tianyu.Lan@microsoft.com>
---
Change since v1:
Update commit log
---
arch/x86/kernel/cpu/mshyperv.c | 10 ++++++++++
1 file changed, 10 insertions(+)
diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c
index caa032ce3fe3..5e296a7e6036 100644
--- a/arch/x86/kernel/cpu/mshyperv.c
+++ b/arch/x86/kernel/cpu/mshyperv.c
@@ -263,6 +263,16 @@ static void __init ms_hyperv_init_platform(void)
cpuid_eax(HYPERV_CPUID_NESTED_FEATURES);
}
+ /*
+ * Hyper-V expects to get crash register data or kmsg when
+ * crash enlightment is available and system crashes. Set
+ * crash_kexec_post_notifiers to be true to make sure that
+ * calling crash enlightment interface before running kdump
+ * kernel.
+ */
+ if (ms_hyperv.misc_features & HV_FEATURE_GUEST_CRASH_MSR_AVAILABLE)
+ crash_kexec_post_notifiers = true;
+
#ifdef CONFIG_X86_LOCAL_APIC
if (ms_hyperv.features & HV_X64_ACCESS_FREQUENCY_MSRS &&
ms_hyperv.misc_features & HV_FEATURE_FREQUENCY_MSRS_AVAILABLE) {
--
2.14.5
^ permalink raw reply related
* [PATCH V2 5/6] x86/Hyper-V: Report crash register data when sysctl_record_panic_msg is not set
From: ltykernel @ 2020-03-23 13:09 UTC (permalink / raw)
To: kys, haiyangz, sthemmin, liuwe, michael.h.kelley
Cc: Tianyu Lan, linux-hyperv, linux-kernel, vkuznets
In-Reply-To: <20200323130924.2968-1-Tianyu.Lan@microsoft.com>
From: Tianyu Lan <Tianyu.Lan@microsoft.com>
When sysctl_record_panic_msg is not set, kmsg will
not be reported to Hyper-V. Crash register data should
be reported via hyperv_report_panic() in such case.
Signed-off-by: Tianyu Lan <Tianyu.Lan@microsoft.com>
---
drivers/hv/vmbus_drv.c | 23 ++++++++++++++---------
1 file changed, 14 insertions(+), 9 deletions(-)
diff --git a/drivers/hv/vmbus_drv.c b/drivers/hv/vmbus_drv.c
index d73fa8aa00a3..00447175c040 100644
--- a/drivers/hv/vmbus_drv.c
+++ b/drivers/hv/vmbus_drv.c
@@ -48,6 +48,18 @@ static int hyperv_cpuhp_online;
static void *hv_panic_page;
+/*
+ * Boolean to control whether to report panic messages over Hyper-V.
+ *
+ * It can be set via /proc/sys/kernel/hyperv/record_panic_msg
+ */
+static int sysctl_record_panic_msg = 1;
+
+static int hyperv_report_reg(void)
+{
+ return !sysctl_record_panic_msg || !hv_panic_page;
+}
+
static int hyperv_panic_event(struct notifier_block *nb, unsigned long val,
void *args)
{
@@ -60,7 +72,7 @@ static int hyperv_panic_event(struct notifier_block *nb, unsigned long val,
* message is available, just report kmsg to crash buffer.
*/
if (ms_hyperv.misc_features & HV_FEATURE_GUEST_CRASH_MSR_AVAILABLE
- && !hv_panic_page) {
+ && hyperv_report_reg()) {
regs = current_pt_regs();
hyperv_report_panic(regs, val);
}
@@ -77,7 +89,7 @@ static int hyperv_die_event(struct notifier_block *nb, unsigned long val,
* Crash notify only can be triggered once. If crash notify
* message is available, just report kmsg to crash buffer.
*/
- if (!hv_panic_page)
+ if (hyperv_report_reg())
hyperv_report_panic(regs, val);
return NOTIFY_DONE;
}
@@ -1265,13 +1277,6 @@ static void vmbus_isr(void)
add_interrupt_randomness(HYPERVISOR_CALLBACK_VECTOR, 0);
}
-/*
- * Boolean to control whether to report panic messages over Hyper-V.
- *
- * It can be set via /proc/sys/kernel/hyperv/record_panic_msg
- */
-static int sysctl_record_panic_msg = 1;
-
/*
* Callback from kmsg_dump. Grab as much as possible from the end of the kmsg
* buffer and call into Hyper-V to transfer the data.
--
2.14.5
^ permalink raw reply related
* [PATCH V2 1/6] x86/Hyper-V: Unload vmbus channel in hv panic callback
From: ltykernel @ 2020-03-23 13:09 UTC (permalink / raw)
To: kys, haiyangz, sthemmin, liuwe, tglx, mingo, bp, hpa, x86,
michael.h.kelley
Cc: Tianyu Lan, linux-hyperv, linux-kernel, vkuznets
In-Reply-To: <20200323130924.2968-1-Tianyu.Lan@microsoft.com>
From: Tianyu Lan <Tianyu.Lan@microsoft.com>
When kdump is not configured, a Hyper-V VM might still respond to
network traffic after a kernel panic when kernel parameter panic=0.
The panic CPU goes into an infinite loop with interrupts enabled,
and the VMbus driver interrupt handler still works because the
VMbus connection is unloaded only in the kdump path. The network
responses make the other end of the connection think the VM is
still functional even though it has panic'ed, which could affect any
failover actions that should be taken.
Fix this by unloading the VMbus connection during the panic process.
vmbus_initiate_unload() could then be called twice (e.g., by
hyperv_panic_event() and hv_crash_handler(), so reset the connection
state in vmbus_initiate_unload() to ensure the unload is done only
once.
Signed-off-by: Tianyu Lan <Tianyu.Lan@microsoft.com>
---
Change since v1:
- Update chnage log
- Use xchg() to change vmbus connection status
---
drivers/hv/channel_mgmt.c | 3 +++
drivers/hv/vmbus_drv.c | 17 +++++++++--------
2 files changed, 12 insertions(+), 8 deletions(-)
diff --git a/drivers/hv/channel_mgmt.c b/drivers/hv/channel_mgmt.c
index 0370364169c4..501c43c5851d 100644
--- a/drivers/hv/channel_mgmt.c
+++ b/drivers/hv/channel_mgmt.c
@@ -839,6 +839,9 @@ void vmbus_initiate_unload(bool crash)
{
struct vmbus_channel_message_header hdr;
+ if (xchg(&vmbus_connection.conn_state, DISCONNECTED) == DISCONNECTED)
+ return;
+
/* Pre-Win2012R2 hosts don't support reconnect */
if (vmbus_proto_version < VERSION_WIN8_1)
return;
diff --git a/drivers/hv/vmbus_drv.c b/drivers/hv/vmbus_drv.c
index 029378c27421..b56b9fb9bd90 100644
--- a/drivers/hv/vmbus_drv.c
+++ b/drivers/hv/vmbus_drv.c
@@ -53,9 +53,12 @@ static int hyperv_panic_event(struct notifier_block *nb, unsigned long val,
{
struct pt_regs *regs;
- regs = current_pt_regs();
+ vmbus_initiate_unload(true);
- hyperv_report_panic(regs, val);
+ if (ms_hyperv.misc_features & HV_FEATURE_GUEST_CRASH_MSR_AVAILABLE) {
+ regs = current_pt_regs();
+ hyperv_report_panic(regs, val);
+ }
return NOTIFY_DONE;
}
@@ -1391,10 +1394,12 @@ static int vmbus_bus_init(void)
}
register_die_notifier(&hyperv_die_block);
- atomic_notifier_chain_register(&panic_notifier_list,
- &hyperv_panic_block);
}
+ /* Vmbus channel is unloaded in panic callback when panic happens.*/
+ atomic_notifier_chain_register(&panic_notifier_list,
+ &hyperv_panic_block);
+
vmbus_request_offers();
return 0;
@@ -2204,8 +2209,6 @@ static int vmbus_bus_suspend(struct device *dev)
vmbus_initiate_unload(false);
- vmbus_connection.conn_state = DISCONNECTED;
-
/* Reset the event for the next resume. */
reinit_completion(&vmbus_connection.ready_for_resume_event);
@@ -2289,7 +2292,6 @@ static void hv_kexec_handler(void)
{
hv_stimer_global_cleanup();
vmbus_initiate_unload(false);
- vmbus_connection.conn_state = DISCONNECTED;
/* Make sure conn_state is set as hv_synic_cleanup checks for it */
mb();
cpuhp_remove_state(hyperv_cpuhp_online);
@@ -2306,7 +2308,6 @@ static void hv_crash_handler(struct pt_regs *regs)
* doing the cleanup for current CPU only. This should be sufficient
* for kdump.
*/
- vmbus_connection.conn_state = DISCONNECTED;
cpu = smp_processor_id();
hv_stimer_cleanup(cpu);
hv_synic_disable_regs(cpu);
--
2.14.5
^ permalink raw reply related
* [PATCH V2 2/6] x86/Hyper-V: Free hv_panic_page when fail to register kmsg dump
From: ltykernel @ 2020-03-23 13:09 UTC (permalink / raw)
To: kys, haiyangz, sthemmin, liuwe, tglx, mingo, bp, hpa, x86,
michael.h.kelley
Cc: Tianyu Lan, linux-hyperv, linux-kernel, vkuznets
In-Reply-To: <20200323130924.2968-1-Tianyu.Lan@microsoft.com>
From: Tianyu Lan <Tianyu.Lan@microsoft.com>
If kmsg_dump_register() fails, hv_panic_page will not be used
anywhere. So free and reset it.
Signed-off-by: Tianyu Lan <Tianyu.Lan@microsoft.com>
---
Change since v1:
- Update commit log
- Remove hv_free_hyperv_page() in the error path
---
drivers/hv/vmbus_drv.c | 7 +++++--
1 file changed, 5 insertions(+), 2 deletions(-)
diff --git a/drivers/hv/vmbus_drv.c b/drivers/hv/vmbus_drv.c
index b56b9fb9bd90..3a0472c8b7ae 100644
--- a/drivers/hv/vmbus_drv.c
+++ b/drivers/hv/vmbus_drv.c
@@ -1385,9 +1385,13 @@ static int vmbus_bus_init(void)
hv_panic_page = (void *)hv_alloc_hyperv_zeroed_page();
if (hv_panic_page) {
ret = kmsg_dump_register(&hv_kmsg_dumper);
- if (ret)
+ if (ret) {
pr_err("Hyper-V: kmsg dump register "
"error 0x%x\n", ret);
+ hv_free_hyperv_page(
+ (unsigned long)hv_panic_page);
+ hv_panic_page = NULL;
+ }
} else
pr_err("Hyper-V: panic message page memory "
"allocation failed");
@@ -1412,7 +1416,6 @@ static int vmbus_bus_init(void)
hv_remove_vmbus_irq();
bus_unregister(&hv_bus);
- hv_free_hyperv_page((unsigned long)hv_panic_page);
unregister_sysctl_table(hv_ctl_table_hdr);
hv_ctl_table_hdr = NULL;
return ret;
--
2.14.5
^ permalink raw reply related
* RE: [PATCH V2 1/6] x86/Hyper-V: Unload vmbus channel in hv panic callback
From: Michael Kelley @ 2020-03-23 17:11 UTC (permalink / raw)
To: ltykernel@gmail.com, KY Srinivasan, Haiyang Zhang,
Stephen Hemminger, Wei Liu, tglx@linutronix.de, mingo@redhat.com,
bp@alien8.de, hpa@zytor.com, x86@kernel.org
Cc: Tianyu Lan, linux-hyperv@vger.kernel.org,
linux-kernel@vger.kernel.org, vkuznets
In-Reply-To: <20200323130924.2968-2-Tianyu.Lan@microsoft.com>
From: Tianyu Lan <Tianyu.Lan@microsoft.com> Sent: Monday, March 23, 2020 6:09 AM
>
> When kdump is not configured, a Hyper-V VM might still respond to
> network traffic after a kernel panic when kernel parameter panic=0.
> The panic CPU goes into an infinite loop with interrupts enabled,
> and the VMbus driver interrupt handler still works because the
> VMbus connection is unloaded only in the kdump path. The network
> responses make the other end of the connection think the VM is
> still functional even though it has panic'ed, which could affect any
> failover actions that should be taken.
>
> Fix this by unloading the VMbus connection during the panic process.
> vmbus_initiate_unload() could then be called twice (e.g., by
> hyperv_panic_event() and hv_crash_handler(), so reset the connection
> state in vmbus_initiate_unload() to ensure the unload is done only
> once.
>
> Signed-off-by: Tianyu Lan <Tianyu.Lan@microsoft.com>
> ---
> Change since v1:
> - Update chnage log
> - Use xchg() to change vmbus connection status
> ---
> drivers/hv/channel_mgmt.c | 3 +++
> drivers/hv/vmbus_drv.c | 17 +++++++++--------
> 2 files changed, 12 insertions(+), 8 deletions(-)
>
> diff --git a/drivers/hv/channel_mgmt.c b/drivers/hv/channel_mgmt.c
> index 0370364169c4..501c43c5851d 100644
> --- a/drivers/hv/channel_mgmt.c
> +++ b/drivers/hv/channel_mgmt.c
> @@ -839,6 +839,9 @@ void vmbus_initiate_unload(bool crash)
> {
> struct vmbus_channel_message_header hdr;
>
> + if (xchg(&vmbus_connection.conn_state, DISCONNECTED) == DISCONNECTED)
> + return;
> +
> /* Pre-Win2012R2 hosts don't support reconnect */
> if (vmbus_proto_version < VERSION_WIN8_1)
> return;
> diff --git a/drivers/hv/vmbus_drv.c b/drivers/hv/vmbus_drv.c
> index 029378c27421..b56b9fb9bd90 100644
> --- a/drivers/hv/vmbus_drv.c
> +++ b/drivers/hv/vmbus_drv.c
> @@ -53,9 +53,12 @@ static int hyperv_panic_event(struct notifier_block *nb, unsigned
> long val,
> {
> struct pt_regs *regs;
>
> - regs = current_pt_regs();
> + vmbus_initiate_unload(true);
>
> - hyperv_report_panic(regs, val);
> + if (ms_hyperv.misc_features & HV_FEATURE_GUEST_CRASH_MSR_AVAILABLE) {
> + regs = current_pt_regs();
> + hyperv_report_panic(regs, val);
> + }
> return NOTIFY_DONE;
> }
>
> @@ -1391,10 +1394,12 @@ static int vmbus_bus_init(void)
> }
>
> register_die_notifier(&hyperv_die_block);
> - atomic_notifier_chain_register(&panic_notifier_list,
> - &hyperv_panic_block);
> }
>
> + /* Vmbus channel is unloaded in panic callback when panic happens.*/
Let me suggest a tweak to the above comment so it is super clear:
/*
* Always register the panic notifier because we need to unload
* the VMbus channel connection to prevent any VMbus
* activity after the VM panics.
*/
> + atomic_notifier_chain_register(&panic_notifier_list,
> + &hyperv_panic_block);
> +
> vmbus_request_offers();
>
> return 0;
^ permalink raw reply
* RE: [PATCH V2 3/6] x86/Hyper-V: Trigger crash enlightenment only once during system crash.
From: Michael Kelley @ 2020-03-23 17:15 UTC (permalink / raw)
To: ltykernel@gmail.com, KY Srinivasan, Haiyang Zhang,
Stephen Hemminger, Wei Liu, tglx@linutronix.de, mingo@redhat.com,
bp@alien8.de, hpa@zytor.com, x86@kernel.org
Cc: Tianyu Lan, linux-hyperv@vger.kernel.org,
linux-kernel@vger.kernel.org, vkuznets
In-Reply-To: <20200323130924.2968-4-Tianyu.Lan@microsoft.com>
From: Tianyu Lan <Tianyu.Lan@microsoft.com> Sent: Monday, March 23, 2020 6:09 AM
>
> When a guest VM panics, Hyper-V should be notified only once via the
> crash synthetic MSRs. Current Linux code might write these crash MSRs
> twice during a system panic:
> 1) hyperv_panic/die_event() calling hyperv_report_panic()
> 2) hv_kmsg_dump() calling hyperv_report_panic_msg()
>
> Fix this by not calling hyperv_report_panic() if a kmsg dump has been
> successfully registered. The notification will happen later via
> hyperv_report_panic_msg().
>
> Signed-off-by: Tianyu Lan <Tianyu.Lan@microsoft.com>
> ---
> Change since v1:
> - Update commit log
> ---
> drivers/hv/vmbus_drv.c | 14 ++++++++++++--
> 1 file changed, 12 insertions(+), 2 deletions(-)
>
> diff --git a/drivers/hv/vmbus_drv.c b/drivers/hv/vmbus_drv.c
> index 3a0472c8b7ae..d73fa8aa00a3 100644
> --- a/drivers/hv/vmbus_drv.c
> +++ b/drivers/hv/vmbus_drv.c
> @@ -55,7 +55,12 @@ static int hyperv_panic_event(struct notifier_block *nb, unsigned
> long val,
>
> vmbus_initiate_unload(true);
>
> - if (ms_hyperv.misc_features & HV_FEATURE_GUEST_CRASH_MSR_AVAILABLE) {
> + /*
> + * Crash notify only can be triggered once. If crash notify
> + * message is available, just report kmsg to crash buffer.
> + */
Just to clarify the above comment, let me suggest:
/*
* Hyper-V should be notified only once about a panic. If we will be
* doing hyperv_report_panic_msg() later with kmsg data, don't do
* the notification here.
*/
> + if (ms_hyperv.misc_features & HV_FEATURE_GUEST_CRASH_MSR_AVAILABLE
> + && !hv_panic_page) {
> regs = current_pt_regs();
> hyperv_report_panic(regs, val);
> }
> @@ -68,7 +73,12 @@ static int hyperv_die_event(struct notifier_block *nb, unsigned long
> val,
> struct die_args *die = (struct die_args *)args;
> struct pt_regs *regs = die->regs;
>
> - hyperv_report_panic(regs, val);
> + /*
> + * Crash notify only can be triggered once. If crash notify
> + * message is available, just report kmsg to crash buffer.
> + */
Same suggested clarification to the comment applies here.
> + if (!hv_panic_page)
> + hyperv_report_panic(regs, val);
> return NOTIFY_DONE;
> }
>
> --
> 2.14.5
^ permalink raw reply
* RE: [PATCH V2 4/6] x86/Hyper-V: Report crash register data or ksmg before running crash kernel
From: Michael Kelley @ 2020-03-23 17:16 UTC (permalink / raw)
To: ltykernel@gmail.com, KY Srinivasan, Haiyang Zhang,
Stephen Hemminger, Wei Liu, tglx@linutronix.de, mingo@redhat.com,
bp@alien8.de, hpa@zytor.com, x86@kernel.org
Cc: Tianyu Lan, linux-hyperv@vger.kernel.org,
linux-kernel@vger.kernel.org, vkuznets
In-Reply-To: <20200323130924.2968-5-Tianyu.Lan@microsoft.com>
From: Tianyu Lan <Tianyu.Lan@microsoft.com> Sent: Monday, March 23, 2020 6:09 AM
>
> When a guest VM panics, Hyper-V should be notified only once via the
> crash synthetic MSRs. Current Linux code might write these crash MSRs
> twice during a system panic:
> 1) hyperv_panic/die_event() calling hyperv_report_panic()
> 2) hv_kmsg_dump() calling hyperv_report_panic_msg()
>
> Fix this by not calling hyperv_report_panic() if a kmsg dump has been
> successfully registered. The notification will happen later via
> hyperv_report_panic_msg().
I think this patch got the wrong commit message. This message is the same
as in patch 3 of the series.
>
> Signed-off-by: Tianyu Lan <Tianyu.Lan@microsoft.com>
> ---
> Change since v1:
> Update commit log
> ---
> arch/x86/kernel/cpu/mshyperv.c | 10 ++++++++++
> 1 file changed, 10 insertions(+)
>
> diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c
> index caa032ce3fe3..5e296a7e6036 100644
> --- a/arch/x86/kernel/cpu/mshyperv.c
> +++ b/arch/x86/kernel/cpu/mshyperv.c
> @@ -263,6 +263,16 @@ static void __init ms_hyperv_init_platform(void)
> cpuid_eax(HYPERV_CPUID_NESTED_FEATURES);
> }
>
> + /*
> + * Hyper-V expects to get crash register data or kmsg when
> + * crash enlightment is available and system crashes. Set
> + * crash_kexec_post_notifiers to be true to make sure that
> + * calling crash enlightment interface before running kdump
> + * kernel.
> + */
> + if (ms_hyperv.misc_features & HV_FEATURE_GUEST_CRASH_MSR_AVAILABLE)
> + crash_kexec_post_notifiers = true;
> +
> #ifdef CONFIG_X86_LOCAL_APIC
> if (ms_hyperv.features & HV_X64_ACCESS_FREQUENCY_MSRS &&
> ms_hyperv.misc_features & HV_FEATURE_FREQUENCY_MSRS_AVAILABLE) {
> --
> 2.14.5
^ permalink raw reply
* RE: [PATCH V2 5/6] x86/Hyper-V: Report crash register data when sysctl_record_panic_msg is not set
From: Michael Kelley @ 2020-03-23 17:20 UTC (permalink / raw)
To: ltykernel@gmail.com, KY Srinivasan, Haiyang Zhang,
Stephen Hemminger, Wei Liu
Cc: Tianyu Lan, linux-hyperv@vger.kernel.org,
linux-kernel@vger.kernel.org, vkuznets
In-Reply-To: <20200323130924.2968-6-Tianyu.Lan@microsoft.com>
From: Tianyu Lan <Tianyu.Lan@microsoft.com> Sent: Monday, March 23, 2020 6:09 AM
>
> When sysctl_record_panic_msg is not set, kmsg will
> not be reported to Hyper-V. Crash register data should
> be reported via hyperv_report_panic() in such case.
Tweaking the wording:
When sysctl_record_panic_msg is not set, the panic will
not be reported to Hyper-V via hyperv_report_panic_msg().
So the crash should be reported via hyperv_report_panic().
>
> Signed-off-by: Tianyu Lan <Tianyu.Lan@microsoft.com>
> ---
> drivers/hv/vmbus_drv.c | 23 ++++++++++++++---------
> 1 file changed, 14 insertions(+), 9 deletions(-)
>
> diff --git a/drivers/hv/vmbus_drv.c b/drivers/hv/vmbus_drv.c
> index d73fa8aa00a3..00447175c040 100644
> --- a/drivers/hv/vmbus_drv.c
> +++ b/drivers/hv/vmbus_drv.c
> @@ -48,6 +48,18 @@ static int hyperv_cpuhp_online;
>
> static void *hv_panic_page;
>
> +/*
> + * Boolean to control whether to report panic messages over Hyper-V.
> + *
> + * It can be set via /proc/sys/kernel/hyperv/record_panic_msg
> + */
> +static int sysctl_record_panic_msg = 1;
> +
> +static int hyperv_report_reg(void)
> +{
> + return !sysctl_record_panic_msg || !hv_panic_page;
> +}
> +
> static int hyperv_panic_event(struct notifier_block *nb, unsigned long val,
> void *args)
> {
> @@ -60,7 +72,7 @@ static int hyperv_panic_event(struct notifier_block *nb, unsigned long
> val,
> * message is available, just report kmsg to crash buffer.
> */
> if (ms_hyperv.misc_features & HV_FEATURE_GUEST_CRASH_MSR_AVAILABLE
> - && !hv_panic_page) {
> + && hyperv_report_reg()) {
> regs = current_pt_regs();
> hyperv_report_panic(regs, val);
> }
> @@ -77,7 +89,7 @@ static int hyperv_die_event(struct notifier_block *nb, unsigned long
> val,
> * Crash notify only can be triggered once. If crash notify
> * message is available, just report kmsg to crash buffer.
> */
> - if (!hv_panic_page)
> + if (hyperv_report_reg())
> hyperv_report_panic(regs, val);
> return NOTIFY_DONE;
> }
> @@ -1265,13 +1277,6 @@ static void vmbus_isr(void)
> add_interrupt_randomness(HYPERVISOR_CALLBACK_VECTOR, 0);
> }
>
> -/*
> - * Boolean to control whether to report panic messages over Hyper-V.
> - *
> - * It can be set via /proc/sys/kernel/hyperv/record_panic_msg
> - */
> -static int sysctl_record_panic_msg = 1;
> -
> /*
> * Callback from kmsg_dump. Grab as much as possible from the end of the kmsg
> * buffer and call into Hyper-V to transfer the data.
> --
> 2.14.5
^ permalink raw reply
* [PATCH v10 0/7] x86/kvm/hyper-v: add support for synthetic debugger
From: Jon Doron @ 2020-03-24 7:43 UTC (permalink / raw)
To: kvm, linux-hyperv; +Cc: vkuznets, Jon Doron
Add support for the synthetic debugger interface of hyper-v, the
synthetic debugger has 2 modes.
1. Use a set of MSRs to send/recv information (undocumented so it's not
going to the hyperv-tlfs.h)
2. Use hypercalls
The first mode is based the following MSRs:
1. Control/Status MSRs which either asks for a send/recv .
2. Send/Recv MSRs each holds GPA where the send/recv buffers are.
3. Pending MSR, holds a GPA to a PAGE that simply has a boolean that
indicates if there is data pending to issue a recv VMEXIT.
The first mode implementation is to simply exit to user-space when
either the control MSR or the pending MSR are being set.
Then it's up-to userspace to implement the rest of the logic of sending/recving.
In the second mode instead of using MSRs KNet will simply issue
Hypercalls with the information to send/recv, in this mode the data
being transferred is UDP encapsulated, unlike in the previous mode in
which you get just the data to send.
The new hypercalls will exit to userspace which will be incharge of
re-encapsulating if needed the UDP packets to be sent.
There is an issue though in which KDNet does not respect the hypercall
page and simply issues vmcall/vmmcall instructions depending on the cpu
type expecting them to be handled as it a real hypercall was issued.
It's important to note that part of this feature has been subject to be
removed in future versions of Windows, which is why some of the
defintions will not be present the the TLFS but in the kvm hyperv header
instead.
Jon Doron (6):
x86/kvm/hyper-v: Explicitly align hcall param for kvm_hyperv_exit
x86/kvm/hyper-v: Simplify addition for custom cpuid leafs
x86/hyper-v: Add synthetic debugger definitions
x86/kvm/hyper-v: Add support for synthetic debugger capability
x86/kvm/hyper-v: enable hypercalls without hypercall page with syndbg
x86/kvm/hyper-v: Add support for synthetic debugger via hypercalls
Vitaly Kuznetsov (1):
KVM: selftests: update hyperv_cpuid with SynDBG tests
Documentation/virt/kvm/api.rst | 18 ++
arch/x86/include/asm/hyperv-tlfs.h | 6 +
arch/x86/include/asm/kvm_host.h | 14 +
arch/x86/kvm/hyperv.c | 242 ++++++++++++++++--
arch/x86/kvm/hyperv.h | 33 +++
arch/x86/kvm/trace.h | 51 ++++
arch/x86/kvm/x86.c | 13 +
include/uapi/linux/kvm.h | 13 +
.../selftests/kvm/x86_64/hyperv_cpuid.c | 139 ++++++----
9 files changed, 469 insertions(+), 60 deletions(-)
--
2.24.1
^ permalink raw reply
* [PATCH v10 1/7] x86/kvm/hyper-v: Explicitly align hcall param for kvm_hyperv_exit
From: Jon Doron @ 2020-03-24 7:43 UTC (permalink / raw)
To: kvm, linux-hyperv; +Cc: vkuznets, Jon Doron
In-Reply-To: <20200324074341.1770081-1-arilou@gmail.com>
The problem the patch is trying to address is the fact that 'struct
kvm_hyperv_exit' has different layout on when compiling in 32 and 64 bit
modes.
In 64-bit mode the default alignment boundary is 64 bits thus
forcing extra gaps after 'type' and 'msr' but in 32-bit mode the
boundary is at 32 bits thus no extra gaps.
This is an issue as even when the kernel is 64 bit, the userspace using
the interface can be both 32 and 64 bit but the same 32 bit userspace has
to work with 32 bit kernel.
The issue is fixed by forcing the 64 bit layout, this leads to ABI
change for 32 bit builds and while we are obviously breaking '32 bit
userspace with 32 bit kernel' case, we're fixing the '32 bit userspace
with 64 bit kernel' one.
As the interface has no (known) users and 32 bit KVM is rather baroque
nowadays, this seems like a reasonable decision.
Reviewed-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Signed-off-by: Jon Doron <arilou@gmail.com>
---
Documentation/virt/kvm/api.rst | 2 ++
include/uapi/linux/kvm.h | 2 ++
2 files changed, 4 insertions(+)
diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst
index ebd383fba939..4872c47bbcff 100644
--- a/Documentation/virt/kvm/api.rst
+++ b/Documentation/virt/kvm/api.rst
@@ -5025,9 +5025,11 @@ EOI was received.
#define KVM_EXIT_HYPERV_SYNIC 1
#define KVM_EXIT_HYPERV_HCALL 2
__u32 type;
+ __u32 pad1;
union {
struct {
__u32 msr;
+ __u32 pad2;
__u64 control;
__u64 evt_page;
__u64 msg_page;
diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
index 4b95f9a31a2f..7ee0ddc4c457 100644
--- a/include/uapi/linux/kvm.h
+++ b/include/uapi/linux/kvm.h
@@ -189,9 +189,11 @@ struct kvm_hyperv_exit {
#define KVM_EXIT_HYPERV_SYNIC 1
#define KVM_EXIT_HYPERV_HCALL 2
__u32 type;
+ __u32 pad1;
union {
struct {
__u32 msr;
+ __u32 pad2;
__u64 control;
__u64 evt_page;
__u64 msg_page;
--
2.24.1
^ permalink raw reply related
* [PATCH v10 2/7] x86/kvm/hyper-v: Simplify addition for custom cpuid leafs
From: Jon Doron @ 2020-03-24 7:43 UTC (permalink / raw)
To: kvm, linux-hyperv; +Cc: vkuznets, Jon Doron
In-Reply-To: <20200324074341.1770081-1-arilou@gmail.com>
Simlify the code to define a new cpuid leaf group by enabled feature.
This also fixes a bug in which the max cpuid leaf was always set to
HYPERV_CPUID_NESTED_FEATURES regardless if nesting is supported or not.
Any new CPUID group needs to consider the max leaf and be added in the
correct order, in this method there are two rules:
1. Each cpuid leaf group must be order in an ascending order
2. The appending for the cpuid leafs by features also needs to happen by
ascending order.
Reviewed-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Signed-off-by: Jon Doron <arilou@gmail.com>
---
arch/x86/kvm/hyperv.c | 46 ++++++++++++++++++++++++++++++-------------
1 file changed, 32 insertions(+), 14 deletions(-)
diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c
index a86fda7a1d03..5a7336d6b8ca 100644
--- a/arch/x86/kvm/hyperv.c
+++ b/arch/x86/kvm/hyperv.c
@@ -1785,27 +1785,45 @@ int kvm_vm_ioctl_hv_eventfd(struct kvm *kvm, struct kvm_hyperv_eventfd *args)
return kvm_hv_eventfd_assign(kvm, args->conn_id, args->fd);
}
+/* Must be sorted in ascending order by function */
+static struct kvm_cpuid_entry2 core_cpuid_entries[] = {
+ { .function = HYPERV_CPUID_VENDOR_AND_MAX_FUNCTIONS },
+ { .function = HYPERV_CPUID_INTERFACE },
+ { .function = HYPERV_CPUID_VERSION },
+ { .function = HYPERV_CPUID_FEATURES },
+ { .function = HYPERV_CPUID_ENLIGHTMENT_INFO },
+ { .function = HYPERV_CPUID_IMPLEMENT_LIMITS },
+};
+
+static struct kvm_cpuid_entry2 evmcs_cpuid_entries[] = {
+ { .function = HYPERV_CPUID_NESTED_FEATURES },
+};
+
+#define HV_MAX_CPUID_ENTRIES \
+ (ARRAY_SIZE(core_cpuid_entries) +\
+ ARRAY_SIZE(evmcs_cpuid_entries))
+
int kvm_vcpu_ioctl_get_hv_cpuid(struct kvm_vcpu *vcpu, struct kvm_cpuid2 *cpuid,
struct kvm_cpuid_entry2 __user *entries)
{
uint16_t evmcs_ver = 0;
- struct kvm_cpuid_entry2 cpuid_entries[] = {
- { .function = HYPERV_CPUID_VENDOR_AND_MAX_FUNCTIONS },
- { .function = HYPERV_CPUID_INTERFACE },
- { .function = HYPERV_CPUID_VERSION },
- { .function = HYPERV_CPUID_FEATURES },
- { .function = HYPERV_CPUID_ENLIGHTMENT_INFO },
- { .function = HYPERV_CPUID_IMPLEMENT_LIMITS },
- { .function = HYPERV_CPUID_NESTED_FEATURES },
- };
- int i, nent = ARRAY_SIZE(cpuid_entries);
+ struct kvm_cpuid_entry2 cpuid_entries[HV_MAX_CPUID_ENTRIES];
+ int i, nent = 0;
+
+ /* Set the core cpuid entries required for Hyper-V */
+ memcpy(&cpuid_entries[nent], &core_cpuid_entries,
+ sizeof(core_cpuid_entries));
+ nent = ARRAY_SIZE(core_cpuid_entries);
if (kvm_x86_ops->nested_get_evmcs_version)
evmcs_ver = kvm_x86_ops->nested_get_evmcs_version(vcpu);
- /* Skip NESTED_FEATURES if eVMCS is not supported */
- if (!evmcs_ver)
- --nent;
+ if (evmcs_ver) {
+ /* EVMCS is enabled, add the required EVMCS CPUID leafs */
+ memcpy(&cpuid_entries[nent], &evmcs_cpuid_entries,
+ sizeof(evmcs_cpuid_entries));
+ nent += ARRAY_SIZE(evmcs_cpuid_entries);
+ }
if (cpuid->nent < nent)
return -E2BIG;
@@ -1821,7 +1839,7 @@ int kvm_vcpu_ioctl_get_hv_cpuid(struct kvm_vcpu *vcpu, struct kvm_cpuid2 *cpuid,
case HYPERV_CPUID_VENDOR_AND_MAX_FUNCTIONS:
memcpy(signature, "Linux KVM Hv", 12);
- ent->eax = HYPERV_CPUID_NESTED_FEATURES;
+ ent->eax = cpuid_entries[nent - 1].function;
ent->ebx = signature[0];
ent->ecx = signature[1];
ent->edx = signature[2];
--
2.24.1
^ permalink raw reply related
* [PATCH v10 3/7] x86/hyper-v: Add synthetic debugger definitions
From: Jon Doron @ 2020-03-24 7:43 UTC (permalink / raw)
To: kvm, linux-hyperv; +Cc: vkuznets, Jon Doron, Michael Kelley
In-Reply-To: <20200324074341.1770081-1-arilou@gmail.com>
Hyper-V synthetic debugger has two modes, one that uses MSRs and
the other that use Hypercalls.
Add all the required definitions to both types of synthetic debugger
interface.
Some of the required new CPUIDs and MSRs are not documented in the TLFS
so they are in hyperv.h instead.
The reason they are not documented is because they are subjected to be
removed in future versions of Windows.
Reviewed-by: Michael Kelley <mikelley@microsoft.com>
Signed-off-by: Jon Doron <arilou@gmail.com>
---
arch/x86/include/asm/hyperv-tlfs.h | 6 ++++++
arch/x86/kvm/hyperv.h | 27 +++++++++++++++++++++++++++
2 files changed, 33 insertions(+)
diff --git a/arch/x86/include/asm/hyperv-tlfs.h b/arch/x86/include/asm/hyperv-tlfs.h
index 92abc1e42bfc..671ce2a39d4b 100644
--- a/arch/x86/include/asm/hyperv-tlfs.h
+++ b/arch/x86/include/asm/hyperv-tlfs.h
@@ -131,6 +131,8 @@
#define HV_FEATURE_FREQUENCY_MSRS_AVAILABLE BIT(8)
/* Crash MSR available */
#define HV_FEATURE_GUEST_CRASH_MSR_AVAILABLE BIT(10)
+/* Support for debug MSRs available */
+#define HV_FEATURE_DEBUG_MSRS_AVAILABLE BIT(11)
/* stimer Direct Mode is available */
#define HV_STIMER_DIRECT_MODE_AVAILABLE BIT(19)
@@ -376,6 +378,9 @@ struct hv_tsc_emulation_status {
#define HVCALL_SEND_IPI_EX 0x0015
#define HVCALL_POST_MESSAGE 0x005c
#define HVCALL_SIGNAL_EVENT 0x005d
+#define HVCALL_POST_DEBUG_DATA 0x0069
+#define HVCALL_RETRIEVE_DEBUG_DATA 0x006a
+#define HVCALL_RESET_DEBUG_SESSION 0x006b
#define HVCALL_FLUSH_GUEST_PHYSICAL_ADDRESS_SPACE 0x00af
#define HVCALL_FLUSH_GUEST_PHYSICAL_ADDRESS_LIST 0x00b0
@@ -419,6 +424,7 @@ enum HV_GENERIC_SET_FORMAT {
#define HV_STATUS_INVALID_HYPERCALL_INPUT 3
#define HV_STATUS_INVALID_ALIGNMENT 4
#define HV_STATUS_INVALID_PARAMETER 5
+#define HV_STATUS_OPERATION_DENIED 8
#define HV_STATUS_INSUFFICIENT_MEMORY 11
#define HV_STATUS_INVALID_PORT_ID 17
#define HV_STATUS_INVALID_CONNECTION_ID 18
diff --git a/arch/x86/kvm/hyperv.h b/arch/x86/kvm/hyperv.h
index 757cb578101c..7f50ff0bad07 100644
--- a/arch/x86/kvm/hyperv.h
+++ b/arch/x86/kvm/hyperv.h
@@ -23,6 +23,33 @@
#include <linux/kvm_host.h>
+/*
+ * The #defines related to the synthetic debugger are required by KDNet, but
+ * they are not documented in the Hyper-V TLFS because the synthetic debugger
+ * functionality has been deprecated and is subject to removal in future
+ * versions of Windows.
+ */
+#define HYPERV_CPUID_SYNDBG_VENDOR_AND_MAX_FUNCTIONS 0x40000080
+#define HYPERV_CPUID_SYNDBG_INTERFACE 0x40000081
+#define HYPERV_CPUID_SYNDBG_PLATFORM_CAPABILITIES 0x40000082
+
+/*
+ * Hyper-V synthetic debugger platform capabilities
+ * These are HYPERV_CPUID_SYNDBG_PLATFORM_CAPABILITIES.EAX bits.
+ */
+#define HV_X64_SYNDBG_CAP_ALLOW_KERNEL_DEBUGGING BIT(1)
+
+/* Hyper-V Synthetic debug options MSR */
+#define HV_X64_MSR_SYNDBG_CONTROL 0x400000F1
+#define HV_X64_MSR_SYNDBG_STATUS 0x400000F2
+#define HV_X64_MSR_SYNDBG_SEND_BUFFER 0x400000F3
+#define HV_X64_MSR_SYNDBG_RECV_BUFFER 0x400000F4
+#define HV_X64_MSR_SYNDBG_PENDING_BUFFER 0x400000F5
+#define HV_X64_MSR_SYNDBG_OPTIONS 0x400000FF
+
+/* Hyper-V HV_X64_MSR_SYNDBG_OPTIONS bits */
+#define HV_X64_SYNDBG_OPTION_USE_HCALLS BIT(2)
+
static inline struct kvm_vcpu_hv *vcpu_to_hv_vcpu(struct kvm_vcpu *vcpu)
{
return &vcpu->arch.hyperv;
--
2.24.1
^ permalink raw reply related
* [PATCH v10 5/7] x86/kvm/hyper-v: enable hypercalls without hypercall page with syndbg
From: Jon Doron @ 2020-03-24 7:43 UTC (permalink / raw)
To: kvm, linux-hyperv; +Cc: vkuznets, Jon Doron
In-Reply-To: <20200324074341.1770081-1-arilou@gmail.com>
Microsoft's kdvm.dll dbgtransport module does not respect the hypercall
page and simply identifies the CPU being used (AMD/Intel) and according
to it simply makes hypercalls with the relevant instruction
(vmmcall/vmcall respectively).
The relevant function in kdvm is KdHvConnectHypervisor which first checks
if the hypercall page has been enabled via HV_X64_MSR_HYPERCALL_ENABLE,
and in case it was not it simply sets the HV_X64_MSR_GUEST_OS_ID to
0x1000101010001 which means:
build_number = 0x0001
service_version = 0x01
minor_version = 0x01
major_version = 0x01
os_id = 0x00 (Undefined)
vendor_id = 1 (Microsoft)
os_type = 0 (A value of 0 indicates a proprietary, closed source OS)
and starts issuing the hypercall without setting the hypercall page.
To resolve this issue simply enable hypercalls also if the guest_os_id
is not 0 and the syndbg feature is enabled.
Signed-off-by: Jon Doron <arilou@gmail.com>
---
arch/x86/kvm/hyperv.c | 5 ++++-
1 file changed, 4 insertions(+), 1 deletion(-)
diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c
index befe5b3b9e20..59c6eadb7eca 100644
--- a/arch/x86/kvm/hyperv.c
+++ b/arch/x86/kvm/hyperv.c
@@ -1650,7 +1650,10 @@ static u64 kvm_hv_send_ipi(struct kvm_vcpu *current_vcpu, u64 ingpa, u64 outgpa,
bool kvm_hv_hypercall_enabled(struct kvm *kvm)
{
- return READ_ONCE(kvm->arch.hyperv.hv_hypercall) & HV_X64_MSR_HYPERCALL_ENABLE;
+ struct kvm_hv *hv = &kvm->arch.hyperv;
+
+ return READ_ONCE(hv->hv_hypercall) & HV_X64_MSR_HYPERCALL_ENABLE ||
+ (hv->hv_syndbg.active && READ_ONCE(hv->hv_guest_os_id) != 0);
}
static void kvm_hv_hypercall_set_result(struct kvm_vcpu *vcpu, u64 result)
--
2.24.1
^ permalink raw reply related
* [PATCH v10 4/7] x86/kvm/hyper-v: Add support for synthetic debugger capability
From: Jon Doron @ 2020-03-24 7:43 UTC (permalink / raw)
To: kvm, linux-hyperv; +Cc: vkuznets, Jon Doron
In-Reply-To: <20200324074341.1770081-1-arilou@gmail.com>
Add support for Hyper-V synthetic debugger (syndbg) interface.
The syndbg interface is using MSRs to emulate a way to send/recv packets
data.
The debug transport dll (kdvm/kdnet) will identify if Hyper-V is enabled
and if it supports the synthetic debugger interface it will attempt to
use it, instead of trying to initialize a network adapter.
Signed-off-by: Jon Doron <arilou@gmail.com>
---
Documentation/virt/kvm/api.rst | 16 ++++
arch/x86/include/asm/kvm_host.h | 14 +++
arch/x86/kvm/hyperv.c | 165 +++++++++++++++++++++++++++++++-
arch/x86/kvm/hyperv.h | 6 ++
arch/x86/kvm/trace.h | 51 ++++++++++
arch/x86/kvm/x86.c | 13 +++
include/uapi/linux/kvm.h | 11 +++
7 files changed, 273 insertions(+), 3 deletions(-)
diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst
index 4872c47bbcff..fe992dcf4f93 100644
--- a/Documentation/virt/kvm/api.rst
+++ b/Documentation/virt/kvm/api.rst
@@ -5024,6 +5024,7 @@ EOI was received.
struct kvm_hyperv_exit {
#define KVM_EXIT_HYPERV_SYNIC 1
#define KVM_EXIT_HYPERV_HCALL 2
+ #define KVM_EXIT_HYPERV_SYNDBG 3
__u32 type;
__u32 pad1;
union {
@@ -5039,6 +5040,15 @@ EOI was received.
__u64 result;
__u64 params[2];
} hcall;
+ struct {
+ __u32 msr;
+ __u32 pad2;
+ __u64 control;
+ __u64 status;
+ __u64 send_page;
+ __u64 recv_page;
+ __u64 pending_page;
+ } syndbg;
} u;
};
/* KVM_EXIT_HYPERV */
@@ -5055,6 +5065,12 @@ Hyper-V SynIC state change. Notification is used to remap SynIC
event/message pages and to enable/disable SynIC messages/events processing
in userspace.
+ - KVM_EXIT_HYPERV_SYNDBG -- synchronously notify user-space about
+
+Hyper-V Synthetic debugger state change. Notification is used to either update
+the pending_page location or to send a control command (send the buffer located
+in send_page or recv a buffer to recv_page).
+
::
/* KVM_EXIT_ARM_NISV */
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 98959e8cd448..c09fa7401b13 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -854,6 +854,19 @@ struct kvm_apic_map {
struct kvm_lapic *phys_map[];
};
+/* Hyper-V synthetic debugger (SynDbg)*/
+struct kvm_hv_syndbg {
+ struct {
+ u64 control;
+ u64 status;
+ u64 send_page;
+ u64 recv_page;
+ u64 pending_page;
+ } control;
+ u64 options;
+ bool active;
+};
+
/* Hyper-V emulation context */
struct kvm_hv {
struct mutex hv_lock;
@@ -877,6 +890,7 @@ struct kvm_hv {
atomic_t num_mismatched_vp_indexes;
struct hv_partition_assist_pg *hv_pa_pg;
+ struct kvm_hv_syndbg hv_syndbg;
};
enum kvm_irqchip_mode {
diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c
index 5a7336d6b8ca..befe5b3b9e20 100644
--- a/arch/x86/kvm/hyperv.c
+++ b/arch/x86/kvm/hyperv.c
@@ -266,6 +266,117 @@ static int synic_set_msr(struct kvm_vcpu_hv_synic *synic,
return ret;
}
+void kvm_hv_activate_syndbg(struct kvm_vcpu *vcpu)
+{
+ struct kvm_hv_syndbg *syndbg = vcpu_to_hv_syndbg(vcpu);
+
+ syndbg->active = true;
+}
+
+static int kvm_hv_syndbg_complete_userspace(struct kvm_vcpu *vcpu)
+{
+ struct kvm *kvm = vcpu->kvm;
+ struct kvm_hv *hv = &kvm->arch.hyperv;
+
+ if (vcpu->run->hyperv.u.syndbg.msr == HV_X64_MSR_SYNDBG_CONTROL)
+ hv->hv_syndbg.control.status =
+ vcpu->run->hyperv.u.syndbg.status;
+ return 1;
+}
+
+static void syndbg_exit(struct kvm_vcpu *vcpu, u32 msr)
+{
+ struct kvm_hv_syndbg *syndbg = vcpu_to_hv_syndbg(vcpu);
+ struct kvm_vcpu_hv *hv_vcpu = &vcpu->arch.hyperv;
+
+ hv_vcpu->exit.type = KVM_EXIT_HYPERV_SYNDBG;
+ hv_vcpu->exit.u.syndbg.msr = msr;
+ hv_vcpu->exit.u.syndbg.control = syndbg->control.control;
+ hv_vcpu->exit.u.syndbg.send_page = syndbg->control.send_page;
+ hv_vcpu->exit.u.syndbg.recv_page = syndbg->control.recv_page;
+ hv_vcpu->exit.u.syndbg.pending_page = syndbg->control.pending_page;
+ vcpu->arch.complete_userspace_io =
+ kvm_hv_syndbg_complete_userspace;
+
+ kvm_make_request(KVM_REQ_HV_EXIT, vcpu);
+}
+
+static int syndbg_set_msr(struct kvm_vcpu *vcpu, u32 msr, u64 data, bool host)
+{
+ struct kvm_hv_syndbg *syndbg = vcpu_to_hv_syndbg(vcpu);
+
+ if (!syndbg->active && !host)
+ return 1;
+
+ trace_kvm_hv_syndbg_set_msr(vcpu->vcpu_id,
+ vcpu_to_hv_vcpu(vcpu)->vp_index, msr, data);
+ switch (msr) {
+ case HV_X64_MSR_SYNDBG_CONTROL:
+ syndbg->control.control = data;
+ if (!host)
+ syndbg_exit(vcpu, msr);
+ break;
+ case HV_X64_MSR_SYNDBG_STATUS:
+ syndbg->control.status = data;
+ break;
+ case HV_X64_MSR_SYNDBG_SEND_BUFFER:
+ syndbg->control.send_page = data;
+ break;
+ case HV_X64_MSR_SYNDBG_RECV_BUFFER:
+ syndbg->control.recv_page = data;
+ break;
+ case HV_X64_MSR_SYNDBG_PENDING_BUFFER:
+ syndbg->control.pending_page = data;
+ if (!host)
+ syndbg_exit(vcpu, msr);
+ break;
+ case HV_X64_MSR_SYNDBG_OPTIONS:
+ syndbg->options = data;
+ break;
+ default:
+ break;
+ }
+
+ return 0;
+}
+
+static int syndbg_get_msr(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata, bool host)
+{
+ struct kvm_hv_syndbg *syndbg = vcpu_to_hv_syndbg(vcpu);
+
+ if (!syndbg->active && !host)
+ return 1;
+
+ switch (msr) {
+ case HV_X64_MSR_SYNDBG_CONTROL:
+ *pdata = syndbg->control.control;
+ break;
+ case HV_X64_MSR_SYNDBG_STATUS:
+ *pdata = syndbg->control.status;
+ break;
+ case HV_X64_MSR_SYNDBG_SEND_BUFFER:
+ *pdata = syndbg->control.send_page;
+ break;
+ case HV_X64_MSR_SYNDBG_RECV_BUFFER:
+ *pdata = syndbg->control.recv_page;
+ break;
+ case HV_X64_MSR_SYNDBG_PENDING_BUFFER:
+ *pdata = syndbg->control.pending_page;
+ break;
+ case HV_X64_MSR_SYNDBG_OPTIONS:
+ *pdata = syndbg->options;
+ break;
+ default:
+ break;
+ }
+
+ trace_kvm_hv_syndbg_get_msr(vcpu->vcpu_id,
+ vcpu_to_hv_vcpu(vcpu)->vp_index, msr,
+ *pdata);
+
+ return 0;
+}
+
static int synic_get_msr(struct kvm_vcpu_hv_synic *synic, u32 msr, u64 *pdata,
bool host)
{
@@ -800,6 +911,8 @@ static bool kvm_hv_msr_partition_wide(u32 msr)
case HV_X64_MSR_REENLIGHTENMENT_CONTROL:
case HV_X64_MSR_TSC_EMULATION_CONTROL:
case HV_X64_MSR_TSC_EMULATION_STATUS:
+ case HV_X64_MSR_SYNDBG_OPTIONS:
+ case HV_X64_MSR_SYNDBG_CONTROL ... HV_X64_MSR_SYNDBG_PENDING_BUFFER:
r = true;
break;
}
@@ -1061,6 +1174,9 @@ static int kvm_hv_set_msr_pw(struct kvm_vcpu *vcpu, u32 msr, u64 data,
if (!host)
return 1;
break;
+ case HV_X64_MSR_SYNDBG_OPTIONS:
+ case HV_X64_MSR_SYNDBG_CONTROL ... HV_X64_MSR_SYNDBG_PENDING_BUFFER:
+ return syndbg_set_msr(vcpu, msr, data, host);
default:
vcpu_unimpl(vcpu, "Hyper-V unhandled wrmsr: 0x%x data 0x%llx\n",
msr, data);
@@ -1190,7 +1306,8 @@ static int kvm_hv_set_msr(struct kvm_vcpu *vcpu, u32 msr, u64 data, bool host)
return 0;
}
-static int kvm_hv_get_msr_pw(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata)
+static int kvm_hv_get_msr_pw(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata,
+ bool host)
{
u64 data = 0;
struct kvm *kvm = vcpu->kvm;
@@ -1227,6 +1344,9 @@ static int kvm_hv_get_msr_pw(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata)
case HV_X64_MSR_TSC_EMULATION_STATUS:
data = hv->hv_tsc_emulation_status;
break;
+ case HV_X64_MSR_SYNDBG_OPTIONS:
+ case HV_X64_MSR_SYNDBG_CONTROL ... HV_X64_MSR_SYNDBG_PENDING_BUFFER:
+ return syndbg_get_msr(vcpu, msr, pdata, host);
default:
vcpu_unimpl(vcpu, "Hyper-V unhandled rdmsr: 0x%x\n", msr);
return 1;
@@ -1316,7 +1436,7 @@ int kvm_hv_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata, bool host)
int r;
mutex_lock(&vcpu->kvm->arch.hyperv.hv_lock);
- r = kvm_hv_get_msr_pw(vcpu, msr, pdata);
+ r = kvm_hv_get_msr_pw(vcpu, msr, pdata, host);
mutex_unlock(&vcpu->kvm->arch.hyperv.hv_lock);
return r;
} else
@@ -1799,9 +1919,16 @@ static struct kvm_cpuid_entry2 evmcs_cpuid_entries[] = {
{ .function = HYPERV_CPUID_NESTED_FEATURES },
};
+static struct kvm_cpuid_entry2 syndbg_cpuid_entries[] = {
+ { .function = HYPERV_CPUID_SYNDBG_VENDOR_AND_MAX_FUNCTIONS },
+ { .function = HYPERV_CPUID_SYNDBG_INTERFACE },
+ { .function = HYPERV_CPUID_SYNDBG_PLATFORM_CAPABILITIES },
+};
+
#define HV_MAX_CPUID_ENTRIES \
(ARRAY_SIZE(core_cpuid_entries) +\
- ARRAY_SIZE(evmcs_cpuid_entries))
+ ARRAY_SIZE(evmcs_cpuid_entries) +\
+ ARRAY_SIZE(syndbg_cpuid_entries))
int kvm_vcpu_ioctl_get_hv_cpuid(struct kvm_vcpu *vcpu, struct kvm_cpuid2 *cpuid,
struct kvm_cpuid_entry2 __user *entries)
@@ -1809,6 +1936,7 @@ int kvm_vcpu_ioctl_get_hv_cpuid(struct kvm_vcpu *vcpu, struct kvm_cpuid2 *cpuid,
uint16_t evmcs_ver = 0;
struct kvm_cpuid_entry2 cpuid_entries[HV_MAX_CPUID_ENTRIES];
int i, nent = 0;
+ struct kvm_hv_syndbg *syndbg = vcpu_to_hv_syndbg(vcpu);
/* Set the core cpuid entries required for Hyper-V */
memcpy(&cpuid_entries[nent], &core_cpuid_entries,
@@ -1825,6 +1953,13 @@ int kvm_vcpu_ioctl_get_hv_cpuid(struct kvm_vcpu *vcpu, struct kvm_cpuid2 *cpuid,
nent += ARRAY_SIZE(evmcs_cpuid_entries);
}
+ if (syndbg->active) {
+ /* Syndbg is enabled, add the required Syndbg CPUID leafs */
+ memcpy(&cpuid_entries[nent], &syndbg_cpuid_entries,
+ sizeof(syndbg_cpuid_entries));
+ nent += ARRAY_SIZE(syndbg_cpuid_entries);
+ }
+
if (cpuid->nent < nent)
return -E2BIG;
@@ -1878,6 +2013,12 @@ int kvm_vcpu_ioctl_get_hv_cpuid(struct kvm_vcpu *vcpu, struct kvm_cpuid2 *cpuid,
ent->edx |= HV_FEATURE_FREQUENCY_MSRS_AVAILABLE;
ent->edx |= HV_FEATURE_GUEST_CRASH_MSR_AVAILABLE;
+ if (syndbg->active) {
+ ent->ebx |= HV_X64_DEBUGGING;
+ ent->edx |= HV_X64_GUEST_DEBUGGING_AVAILABLE;
+ ent->edx |= HV_FEATURE_DEBUG_MSRS_AVAILABLE;
+ }
+
/*
* Direct Synthetic timers only make sense with in-kernel
* LAPIC
@@ -1921,6 +2062,24 @@ int kvm_vcpu_ioctl_get_hv_cpuid(struct kvm_vcpu *vcpu, struct kvm_cpuid2 *cpuid,
break;
+ case HYPERV_CPUID_SYNDBG_VENDOR_AND_MAX_FUNCTIONS:
+ memcpy(signature, "Linux KVM Hv", 12);
+
+ ent->eax = 0;
+ ent->ebx = signature[0];
+ ent->ecx = signature[1];
+ ent->edx = signature[2];
+ break;
+
+ case HYPERV_CPUID_SYNDBG_INTERFACE:
+ memcpy(signature, "VS#1\0\0\0\0\0\0\0\0", 12);
+ ent->eax = signature[0];
+ break;
+
+ case HYPERV_CPUID_SYNDBG_PLATFORM_CAPABILITIES:
+ ent->eax |= HV_X64_SYNDBG_CAP_ALLOW_KERNEL_DEBUGGING;
+ break;
+
default:
break;
}
diff --git a/arch/x86/kvm/hyperv.h b/arch/x86/kvm/hyperv.h
index 7f50ff0bad07..50cca85b5e48 100644
--- a/arch/x86/kvm/hyperv.h
+++ b/arch/x86/kvm/hyperv.h
@@ -73,6 +73,11 @@ static inline struct kvm_vcpu *synic_to_vcpu(struct kvm_vcpu_hv_synic *synic)
return hv_vcpu_to_vcpu(container_of(synic, struct kvm_vcpu_hv, synic));
}
+static inline struct kvm_hv_syndbg *vcpu_to_hv_syndbg(struct kvm_vcpu *vcpu)
+{
+ return &vcpu->kvm->arch.hyperv.hv_syndbg;
+}
+
int kvm_hv_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data, bool host);
int kvm_hv_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata, bool host);
@@ -83,6 +88,7 @@ void kvm_hv_irq_routing_update(struct kvm *kvm);
int kvm_hv_synic_set_irq(struct kvm *kvm, u32 vcpu_id, u32 sint);
void kvm_hv_synic_send_eoi(struct kvm_vcpu *vcpu, int vector);
int kvm_hv_activate_synic(struct kvm_vcpu *vcpu, bool dont_zero_synic_pages);
+void kvm_hv_activate_syndbg(struct kvm_vcpu *vcpu);
void kvm_hv_vcpu_init(struct kvm_vcpu *vcpu);
void kvm_hv_vcpu_postcreate(struct kvm_vcpu *vcpu);
diff --git a/arch/x86/kvm/trace.h b/arch/x86/kvm/trace.h
index f194dd058470..bf6c3852868d 100644
--- a/arch/x86/kvm/trace.h
+++ b/arch/x86/kvm/trace.h
@@ -1515,6 +1515,57 @@ TRACE_EVENT(kvm_nested_vmenter_failed,
__print_symbolic(__entry->err, VMX_VMENTER_INSTRUCTION_ERRORS))
);
+/*
+ * Tracepoint for syndbg_set_msr.
+ */
+TRACE_EVENT(kvm_hv_syndbg_set_msr,
+ TP_PROTO(int vcpu_id, u32 vp_index, u32 msr, u64 data),
+ TP_ARGS(vcpu_id, vp_index, msr, data),
+
+ TP_STRUCT__entry(
+ __field(int, vcpu_id)
+ __field(u32, vp_index)
+ __field(u32, msr)
+ __field(u64, data)
+ ),
+
+ TP_fast_assign(
+ __entry->vcpu_id = vcpu_id;
+ __entry->vp_index = vp_index;
+ __entry->msr = msr;
+ __entry->data = data;
+ ),
+
+ TP_printk("vcpu_id %d vp_index %u msr 0x%x data 0x%llx",
+ __entry->vcpu_id, __entry->vp_index, __entry->msr,
+ __entry->data)
+);
+
+/*
+ * Tracepoint for syndbg_get_msr.
+ */
+TRACE_EVENT(kvm_hv_syndbg_get_msr,
+ TP_PROTO(int vcpu_id, u32 vp_index, u32 msr, u64 data),
+ TP_ARGS(vcpu_id, vp_index, msr, data),
+
+ TP_STRUCT__entry(
+ __field(int, vcpu_id)
+ __field(u32, vp_index)
+ __field(u32, msr)
+ __field(u64, data)
+ ),
+
+ TP_fast_assign(
+ __entry->vcpu_id = vcpu_id;
+ __entry->vp_index = vp_index;
+ __entry->msr = msr;
+ __entry->data = data;
+ ),
+
+ TP_printk("vcpu_id %d vp_index %u msr 0x%x data 0x%llx",
+ __entry->vcpu_id, __entry->vp_index, __entry->msr,
+ __entry->data)
+);
#endif /* _TRACE_KVM_H */
#undef TRACE_INCLUDE_PATH
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 3156e25b0774..7bfa30d7a525 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -1214,6 +1214,10 @@ static const u32 emulated_msrs_all[] = {
HV_X64_MSR_VP_ASSIST_PAGE,
HV_X64_MSR_REENLIGHTENMENT_CONTROL, HV_X64_MSR_TSC_EMULATION_CONTROL,
HV_X64_MSR_TSC_EMULATION_STATUS,
+ HV_X64_MSR_SYNDBG_OPTIONS,
+ HV_X64_MSR_SYNDBG_CONTROL, HV_X64_MSR_SYNDBG_STATUS,
+ HV_X64_MSR_SYNDBG_SEND_BUFFER, HV_X64_MSR_SYNDBG_RECV_BUFFER,
+ HV_X64_MSR_SYNDBG_PENDING_BUFFER,
MSR_KVM_ASYNC_PF_EN, MSR_KVM_STEAL_TIME,
MSR_KVM_PV_EOI_EN,
@@ -2906,6 +2910,8 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
*/
break;
case HV_X64_MSR_GUEST_OS_ID ... HV_X64_MSR_SINT15:
+ case HV_X64_MSR_SYNDBG_CONTROL ... HV_X64_MSR_SYNDBG_PENDING_BUFFER:
+ case HV_X64_MSR_SYNDBG_OPTIONS:
case HV_X64_MSR_CRASH_P0 ... HV_X64_MSR_CRASH_P4:
case HV_X64_MSR_CRASH_CTL:
case HV_X64_MSR_STIMER0_CONFIG ... HV_X64_MSR_STIMER3_COUNT:
@@ -3151,6 +3157,8 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
msr_info->data = 0x20000000;
break;
case HV_X64_MSR_GUEST_OS_ID ... HV_X64_MSR_SINT15:
+ case HV_X64_MSR_SYNDBG_CONTROL ... HV_X64_MSR_SYNDBG_PENDING_BUFFER:
+ case HV_X64_MSR_SYNDBG_OPTIONS:
case HV_X64_MSR_CRASH_P0 ... HV_X64_MSR_CRASH_P4:
case HV_X64_MSR_CRASH_CTL:
case HV_X64_MSR_STIMER0_CONFIG ... HV_X64_MSR_STIMER3_COUNT:
@@ -3323,6 +3331,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
case KVM_CAP_HYPERV_TLBFLUSH:
case KVM_CAP_HYPERV_SEND_IPI:
case KVM_CAP_HYPERV_CPUID:
+ case KVM_CAP_HYPERV_SYNDBG:
case KVM_CAP_PCI_SEGMENT:
case KVM_CAP_DEBUGREGS:
case KVM_CAP_X86_ROBUST_SINGLESTEP:
@@ -4178,6 +4187,10 @@ static int kvm_vcpu_ioctl_enable_cap(struct kvm_vcpu *vcpu,
return -EINVAL;
switch (cap->cap) {
+ case KVM_CAP_HYPERV_SYNDBG:
+ kvm_hv_activate_syndbg(vcpu);
+ return 0;
+
case KVM_CAP_HYPERV_SYNIC2:
if (cap->args[0])
return -EINVAL;
diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
index 7ee0ddc4c457..0b573e1155c8 100644
--- a/include/uapi/linux/kvm.h
+++ b/include/uapi/linux/kvm.h
@@ -188,6 +188,7 @@ struct kvm_s390_cmma_log {
struct kvm_hyperv_exit {
#define KVM_EXIT_HYPERV_SYNIC 1
#define KVM_EXIT_HYPERV_HCALL 2
+#define KVM_EXIT_HYPERV_SYNDBG 3
__u32 type;
__u32 pad1;
union {
@@ -203,6 +204,15 @@ struct kvm_hyperv_exit {
__u64 result;
__u64 params[2];
} hcall;
+ struct {
+ __u32 msr;
+ __u32 pad2;
+ __u64 control;
+ __u64 status;
+ __u64 send_page;
+ __u64 recv_page;
+ __u64 pending_page;
+ } syndbg;
} u;
};
@@ -1012,6 +1022,7 @@ struct kvm_ppc_resize_hpt {
#define KVM_CAP_ARM_NISV_TO_USER 177
#define KVM_CAP_ARM_INJECT_EXT_DABT 178
#define KVM_CAP_S390_VCPU_RESETS 179
+#define KVM_CAP_HYPERV_SYNDBG 180
#ifdef KVM_CAP_IRQ_ROUTING
--
2.24.1
^ permalink raw reply related
* [PATCH v10 6/7] x86/kvm/hyper-v: Add support for synthetic debugger via hypercalls
From: Jon Doron @ 2020-03-24 7:43 UTC (permalink / raw)
To: kvm, linux-hyperv; +Cc: vkuznets, Jon Doron
In-Reply-To: <20200324074341.1770081-1-arilou@gmail.com>
There is another mode for the synthetic debugger which uses hypercalls
to send/recv network data instead of the MSR interface.
This interface is much slower and less recommended since you might get
a lot of VMExits while KDVM polling for new packets to recv, rather
than simply checking the pending page to see if there is data avialble
and then request.
Signed-off-by: Jon Doron <arilou@gmail.com>
---
arch/x86/kvm/hyperv.c | 28 ++++++++++++++++++++++++++++
1 file changed, 28 insertions(+)
diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c
index 59c6eadb7eca..45ff3098e079 100644
--- a/arch/x86/kvm/hyperv.c
+++ b/arch/x86/kvm/hyperv.c
@@ -1832,6 +1832,34 @@ int kvm_hv_hypercall(struct kvm_vcpu *vcpu)
}
ret = kvm_hv_send_ipi(vcpu, ingpa, outgpa, true, false);
break;
+ case HVCALL_POST_DEBUG_DATA:
+ case HVCALL_RETRIEVE_DEBUG_DATA:
+ if (unlikely(fast)) {
+ ret = HV_STATUS_INVALID_PARAMETER;
+ break;
+ }
+ fallthrough;
+ case HVCALL_RESET_DEBUG_SESSION: {
+ struct kvm_hv_syndbg *syndbg = vcpu_to_hv_syndbg(vcpu);
+
+ if (!syndbg->active) {
+ ret = HV_STATUS_INVALID_HYPERCALL_CODE;
+ break;
+ }
+
+ if (!(syndbg->options & HV_X64_SYNDBG_OPTION_USE_HCALLS)) {
+ ret = HV_STATUS_OPERATION_DENIED;
+ break;
+ }
+ vcpu->run->exit_reason = KVM_EXIT_HYPERV;
+ vcpu->run->hyperv.type = KVM_EXIT_HYPERV_HCALL;
+ vcpu->run->hyperv.u.hcall.input = param;
+ vcpu->run->hyperv.u.hcall.params[0] = ingpa;
+ vcpu->run->hyperv.u.hcall.params[1] = outgpa;
+ vcpu->arch.complete_userspace_io =
+ kvm_hv_hypercall_complete_userspace;
+ return 0;
+ }
default:
ret = HV_STATUS_INVALID_HYPERCALL_CODE;
break;
--
2.24.1
^ permalink raw reply related
* [PATCH v10 7/7] KVM: selftests: update hyperv_cpuid with SynDBG tests
From: Jon Doron @ 2020-03-24 7:43 UTC (permalink / raw)
To: kvm, linux-hyperv; +Cc: vkuznets
In-Reply-To: <20200324074341.1770081-1-arilou@gmail.com>
From: Vitaly Kuznetsov <vkuznets () redhat ! com>
Test all four combinations with eVMCS and SynDBG capabilities,
check that we get the right number of entries and that
0x40000000.EAX always returns the correct max leaf.
Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
---
.../selftests/kvm/x86_64/hyperv_cpuid.c | 139 ++++++++++++------
1 file changed, 96 insertions(+), 43 deletions(-)
diff --git a/tools/testing/selftests/kvm/x86_64/hyperv_cpuid.c b/tools/testing/selftests/kvm/x86_64/hyperv_cpuid.c
index 443a2b54645b..e63b0e1c253d 100644
--- a/tools/testing/selftests/kvm/x86_64/hyperv_cpuid.c
+++ b/tools/testing/selftests/kvm/x86_64/hyperv_cpuid.c
@@ -26,18 +26,18 @@ static void guest_code(void)
{
}
-static int smt_possible(void)
+static bool smt_possible(void)
{
char buf[16];
FILE *f;
- bool res = 1;
+ bool res = true;
f = fopen("/sys/devices/system/cpu/smt/control", "r");
if (f) {
if (fread(buf, sizeof(*buf), sizeof(buf), f) > 0) {
if (!strncmp(buf, "forceoff", 8) ||
!strncmp(buf, "notsupported", 12))
- res = 0;
+ res = false;
}
fclose(f);
}
@@ -45,30 +45,48 @@ static int smt_possible(void)
return res;
}
+void vcpu_enable_syndbg(struct kvm_vm *vm, int vcpu_id)
+{
+ struct kvm_enable_cap enable_syndbg_cap = {
+ .cap = KVM_CAP_HYPERV_SYNDBG,
+ };
+
+ vcpu_ioctl(vm, vcpu_id, KVM_ENABLE_CAP, &enable_syndbg_cap);
+}
+
static void test_hv_cpuid(struct kvm_cpuid2 *hv_cpuid_entries,
- int evmcs_enabled)
+ bool evmcs_enabled, bool syndbg_enabled)
{
int i;
+ int nent = 6;
+ u32 test_val;
+
+ if (evmcs_enabled)
+ nent += 1; /* 0x4000000A */
- if (!evmcs_enabled)
- TEST_ASSERT(hv_cpuid_entries->nent == 6,
- "KVM_GET_SUPPORTED_HV_CPUID should return 6 entries"
- " when Enlightened VMCS is disabled (returned %d)",
- hv_cpuid_entries->nent);
- else
- TEST_ASSERT(hv_cpuid_entries->nent == 7,
- "KVM_GET_SUPPORTED_HV_CPUID should return 7 entries"
- " when Enlightened VMCS is enabled (returned %d)",
- hv_cpuid_entries->nent);
+ if (syndbg_enabled)
+ nent += 3; /* 0x40000080 - 0x40000082 */
+
+ TEST_ASSERT(hv_cpuid_entries->nent == nent,
+ "KVM_GET_SUPPORTED_HV_CPUID should return %d entries"
+ " with evmcs=%d syndbg=%d (returned %d)",
+ nent, evmcs_enabled, syndbg_enabled,
+ hv_cpuid_entries->nent);
for (i = 0; i < hv_cpuid_entries->nent; i++) {
struct kvm_cpuid_entry2 *entry = &hv_cpuid_entries->entries[i];
TEST_ASSERT((entry->function >= 0x40000000) &&
- (entry->function <= 0x4000000A),
+ (entry->function <= 0x40000082),
"function %lx is our of supported range",
entry->function);
+ TEST_ASSERT(evmcs_enabled || (entry->function != 0x4000000A),
+ "0x4000000A leaf should not be reported");
+
+ TEST_ASSERT(syndbg_enabled || (entry->function <= 0x4000000A),
+ "SYNDBG leaves should not be reported");
+
TEST_ASSERT(entry->index == 0,
".index field should be zero");
@@ -78,12 +96,27 @@ static void test_hv_cpuid(struct kvm_cpuid2 *hv_cpuid_entries,
TEST_ASSERT(!entry->padding[0] && !entry->padding[1] &&
!entry->padding[2], "padding should be zero");
- if (entry->function == 0x40000004) {
- int nononarchcs = !!(entry->eax & (1UL << 18));
-
- TEST_ASSERT(nononarchcs == !smt_possible(),
+ switch (entry->function) {
+ case 0x40000000:
+ test_val = 0x40000005;
+ if (evmcs_enabled)
+ test_val = 0x4000000A;
+ if (syndbg_enabled)
+ test_val = 0x40000082;
+
+ TEST_ASSERT(entry->eax == test_val,
+ "Wrong max leaf report in 0x40000000.EAX: %x"
+ " (evmcs=%d syndbg=%d)",
+ entry->eax, evmcs_enabled, syndbg_enabled
+ );
+ break;
+ case 0x40000004:
+ test_val = entry->eax & (1UL << 18);
+
+ TEST_ASSERT(!!test_val == !smt_possible(),
"NoNonArchitecturalCoreSharing bit"
" doesn't reflect SMT setting");
+ break;
}
/*
@@ -133,8 +166,9 @@ struct kvm_cpuid2 *kvm_get_supported_hv_cpuid(struct kvm_vm *vm)
int main(int argc, char *argv[])
{
struct kvm_vm *vm;
- int rv;
+ int rv, stage;
struct kvm_cpuid2 *hv_cpuid_entries;
+ bool evmcs_enabled, syndbg_enabled;
/* Tell stdout not to buffer its content */
setbuf(stdout, NULL);
@@ -151,32 +185,51 @@ int main(int argc, char *argv[])
test_hv_cpuid_e2big(vm);
- hv_cpuid_entries = kvm_get_supported_hv_cpuid(vm);
- if (!hv_cpuid_entries)
- return 1;
-
- test_hv_cpuid(hv_cpuid_entries, 0);
+ kvm_vm_free(vm);
- free(hv_cpuid_entries);
+ for (stage = 0; stage < 5; stage++) {
+ evmcs_enabled = false;
+ syndbg_enabled = false;
+
+ vm = vm_create_default(VCPU_ID, 0, guest_code);
+ switch (stage) {
+ case 0:
+ test_hv_cpuid_e2big(vm);
+ continue;
+ case 1:
+ break;
+ case 2:
+ if (!kvm_check_cap(KVM_CAP_HYPERV_ENLIGHTENED_VMCS)) {
+ print_skip("Enlightened VMCS is unsupported");
+ continue;
+ }
+ vcpu_enable_evmcs(vm, VCPU_ID);
+ evmcs_enabled = true;
+ break;
+ case 3:
+ if (!kvm_check_cap(KVM_CAP_HYPERV_SYNDBG)) {
+ print_skip("Synthetic debugger is unsupported");
+ continue;
+ }
+ vcpu_enable_syndbg(vm, VCPU_ID);
+ syndbg_enabled = true;
+ break;
+ case 4:
+ if (!kvm_check_cap(KVM_CAP_HYPERV_ENLIGHTENED_VMCS) ||
+ !kvm_check_cap(KVM_CAP_HYPERV_SYNDBG))
+ continue;
+ vcpu_enable_evmcs(vm, VCPU_ID);
+ vcpu_enable_syndbg(vm, VCPU_ID);
+ evmcs_enabled = true;
+ syndbg_enabled = true;
+ break;
+ }
- if (!kvm_check_cap(KVM_CAP_HYPERV_ENLIGHTENED_VMCS)) {
- fprintf(stderr,
- "Enlightened VMCS is unsupported, skip related test\n");
- goto vm_free;
+ hv_cpuid_entries = kvm_get_supported_hv_cpuid(vm);
+ test_hv_cpuid(hv_cpuid_entries, evmcs_enabled, syndbg_enabled);
+ free(hv_cpuid_entries);
+ kvm_vm_free(vm);
}
- vcpu_enable_evmcs(vm, VCPU_ID);
-
- hv_cpuid_entries = kvm_get_supported_hv_cpuid(vm);
- if (!hv_cpuid_entries)
- return 1;
-
- test_hv_cpuid(hv_cpuid_entries, 1);
-
- free(hv_cpuid_entries);
-
-vm_free:
- kvm_vm_free(vm);
-
return 0;
}
--
2.24.1
^ permalink raw reply related
* [PATCH V3 1/6] x86/Hyper-V: Unload vmbus channel in hv panic callback
From: ltykernel @ 2020-03-24 7:57 UTC (permalink / raw)
To: kys, haiyangz, sthemmin, liuwe, tglx, mingo, bp, hpa, x86,
michael.h.kelley
Cc: Tianyu Lan, linux-hyperv, linux-kernel, vkuznets
In-Reply-To: <20200324075720.9462-1-Tianyu.Lan@microsoft.com>
From: Tianyu Lan <Tianyu.Lan@microsoft.com>
When kdump is not configured, a Hyper-V VM might still respond to
network traffic after a kernel panic when kernel parameter panic=0.
The panic CPU goes into an infinite loop with interrupts enabled,
and the VMbus driver interrupt handler still works because the
VMbus connection is unloaded only in the kdump path. The network
responses make the other end of the connection think the VM is
still functional even though it has panic'ed, which could affect any
failover actions that should be taken.
Fix this by unloading the VMbus connection during the panic process.
vmbus_initiate_unload() could then be called twice (e.g., by
hyperv_panic_event() and hv_crash_handler(), so reset the connection
state in vmbus_initiate_unload() to ensure the unload is done only
once.
Signed-off-by: Tianyu Lan <Tianyu.Lan@microsoft.com>
---
Change since v1:
- Update change log
- Use xchg() to change vmbus connection status
Change since v2:
- Update comment of registering panic callback.
---
drivers/hv/channel_mgmt.c | 3 +++
drivers/hv/vmbus_drv.c | 21 +++++++++++++--------
2 files changed, 16 insertions(+), 8 deletions(-)
diff --git a/drivers/hv/channel_mgmt.c b/drivers/hv/channel_mgmt.c
index 0370364169c4..501c43c5851d 100644
--- a/drivers/hv/channel_mgmt.c
+++ b/drivers/hv/channel_mgmt.c
@@ -839,6 +839,9 @@ void vmbus_initiate_unload(bool crash)
{
struct vmbus_channel_message_header hdr;
+ if (xchg(&vmbus_connection.conn_state, DISCONNECTED) == DISCONNECTED)
+ return;
+
/* Pre-Win2012R2 hosts don't support reconnect */
if (vmbus_proto_version < VERSION_WIN8_1)
return;
diff --git a/drivers/hv/vmbus_drv.c b/drivers/hv/vmbus_drv.c
index 029378c27421..6478240d11ab 100644
--- a/drivers/hv/vmbus_drv.c
+++ b/drivers/hv/vmbus_drv.c
@@ -53,9 +53,12 @@ static int hyperv_panic_event(struct notifier_block *nb, unsigned long val,
{
struct pt_regs *regs;
- regs = current_pt_regs();
+ vmbus_initiate_unload(true);
- hyperv_report_panic(regs, val);
+ if (ms_hyperv.misc_features & HV_FEATURE_GUEST_CRASH_MSR_AVAILABLE) {
+ regs = current_pt_regs();
+ hyperv_report_panic(regs, val);
+ }
return NOTIFY_DONE;
}
@@ -1391,10 +1394,16 @@ static int vmbus_bus_init(void)
}
register_die_notifier(&hyperv_die_block);
- atomic_notifier_chain_register(&panic_notifier_list,
- &hyperv_panic_block);
}
+ /*
+ * Always register the panic notifier because we need to unload
+ * the VMbus channel connection to prevent any VMbus
+ * activity after the VM panics.
+ */
+ atomic_notifier_chain_register(&panic_notifier_list,
+ &hyperv_panic_block);
+
vmbus_request_offers();
return 0;
@@ -2204,8 +2213,6 @@ static int vmbus_bus_suspend(struct device *dev)
vmbus_initiate_unload(false);
- vmbus_connection.conn_state = DISCONNECTED;
-
/* Reset the event for the next resume. */
reinit_completion(&vmbus_connection.ready_for_resume_event);
@@ -2289,7 +2296,6 @@ static void hv_kexec_handler(void)
{
hv_stimer_global_cleanup();
vmbus_initiate_unload(false);
- vmbus_connection.conn_state = DISCONNECTED;
/* Make sure conn_state is set as hv_synic_cleanup checks for it */
mb();
cpuhp_remove_state(hyperv_cpuhp_online);
@@ -2306,7 +2312,6 @@ static void hv_crash_handler(struct pt_regs *regs)
* doing the cleanup for current CPU only. This should be sufficient
* for kdump.
*/
- vmbus_connection.conn_state = DISCONNECTED;
cpu = smp_processor_id();
hv_stimer_cleanup(cpu);
hv_synic_disable_regs(cpu);
--
2.14.5
^ permalink raw reply related
* [PATCH V3 4/6] x86/Hyper-V: Report crash register data or ksmg before running crash kernel
From: ltykernel @ 2020-03-24 7:57 UTC (permalink / raw)
To: kys, haiyangz, sthemmin, liuwe, tglx, mingo, bp, hpa, x86,
michael.h.kelley
Cc: Tianyu Lan, linux-hyperv, linux-kernel, vkuznets
In-Reply-To: <20200324075720.9462-1-Tianyu.Lan@microsoft.com>
From: Tianyu Lan <Tianyu.Lan@microsoft.com>
We want to notify Hyper-V when a Linux guest VM crash occurs, so
there is a record of the crash even when kdump is enabled. But
crash_kexec_post_notifiers defaults to "false", so the kdump kernel
runs before the notifiers and Hyper-V never gets notified. Fix this by
always setting crash_kexec_post_notifiers to be true for Hyper-V VMs.
Signed-off-by: Tianyu Lan <Tianyu.Lan@microsoft.com>
---
Change since v1:
Update commit log
---
arch/x86/kernel/cpu/mshyperv.c | 10 ++++++++++
1 file changed, 10 insertions(+)
diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c
index caa032ce3fe3..5e296a7e6036 100644
--- a/arch/x86/kernel/cpu/mshyperv.c
+++ b/arch/x86/kernel/cpu/mshyperv.c
@@ -263,6 +263,16 @@ static void __init ms_hyperv_init_platform(void)
cpuid_eax(HYPERV_CPUID_NESTED_FEATURES);
}
+ /*
+ * Hyper-V expects to get crash register data or kmsg when
+ * crash enlightment is available and system crashes. Set
+ * crash_kexec_post_notifiers to be true to make sure that
+ * calling crash enlightment interface before running kdump
+ * kernel.
+ */
+ if (ms_hyperv.misc_features & HV_FEATURE_GUEST_CRASH_MSR_AVAILABLE)
+ crash_kexec_post_notifiers = true;
+
#ifdef CONFIG_X86_LOCAL_APIC
if (ms_hyperv.features & HV_X64_ACCESS_FREQUENCY_MSRS &&
ms_hyperv.misc_features & HV_FEATURE_FREQUENCY_MSRS_AVAILABLE) {
--
2.14.5
^ permalink raw reply related
* [PATCH V3 6/6] x86/Hyper-V: Report crash data in die() when panic_on_oops is set
From: ltykernel @ 2020-03-24 7:57 UTC (permalink / raw)
To: kys, haiyangz, sthemmin, liuwe, michael.h.kelley
Cc: Tianyu Lan, linux-hyperv, linux-kernel, vkuznets
In-Reply-To: <20200324075720.9462-1-Tianyu.Lan@microsoft.com>
From: Tianyu Lan <Tianyu.Lan@microsoft.com>
When oops happens with panic_on_oops unset, the oops
thread is killed by die() and system continues to run.
In such case, guest should not report crash register
data to host since system still runs. Fix it.
Signed-off-by: Tianyu Lan <Tianyu.Lan@microsoft.com>
---
drivers/hv/vmbus_drv.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/hv/vmbus_drv.c b/drivers/hv/vmbus_drv.c
index 172ceae69abb..8baca2881596 100644
--- a/drivers/hv/vmbus_drv.c
+++ b/drivers/hv/vmbus_drv.c
@@ -91,7 +91,7 @@ static int hyperv_die_event(struct notifier_block *nb, unsigned long val,
* doing hyperv_report_panic_msg() later with kmsg data, don't do
* the notification here.
*/
- if (hyperv_report_reg())
+ if (hyperv_report_reg() && panic_on_oops)
hyperv_report_panic(regs, val);
return NOTIFY_DONE;
}
--
2.14.5
^ permalink raw reply related
* [PATCH V3 5/6] x86/Hyper-V: Report crash register data when sysctl_record_panic_msg is not set
From: ltykernel @ 2020-03-24 7:57 UTC (permalink / raw)
To: kys, haiyangz, sthemmin, liuwe, michael.h.kelley
Cc: Tianyu Lan, linux-hyperv, linux-kernel, vkuznets
In-Reply-To: <20200324075720.9462-1-Tianyu.Lan@microsoft.com>
From: Tianyu Lan <Tianyu.Lan@microsoft.com>
When sysctl_record_panic_msg is not set, the panic will
not be reported to Hyper-V via hyperv_report_panic_msg().
So the crash should be reported via hyperv_report_panic().
Signed-off-by: Tianyu Lan <Tianyu.Lan@microsoft.com>
---
drivers/hv/vmbus_drv.c | 23 ++++++++++++++---------
1 file changed, 14 insertions(+), 9 deletions(-)
diff --git a/drivers/hv/vmbus_drv.c b/drivers/hv/vmbus_drv.c
index 333dad39b1c1..172ceae69abb 100644
--- a/drivers/hv/vmbus_drv.c
+++ b/drivers/hv/vmbus_drv.c
@@ -48,6 +48,18 @@ static int hyperv_cpuhp_online;
static void *hv_panic_page;
+/*
+ * Boolean to control whether to report panic messages over Hyper-V.
+ *
+ * It can be set via /proc/sys/kernel/hyperv/record_panic_msg
+ */
+static int sysctl_record_panic_msg = 1;
+
+static int hyperv_report_reg(void)
+{
+ return !sysctl_record_panic_msg || !hv_panic_page;
+}
+
static int hyperv_panic_event(struct notifier_block *nb, unsigned long val,
void *args)
{
@@ -61,7 +73,7 @@ static int hyperv_panic_event(struct notifier_block *nb, unsigned long val,
* the notification here.
*/
if (ms_hyperv.misc_features & HV_FEATURE_GUEST_CRASH_MSR_AVAILABLE
- && !hv_panic_page) {
+ && hyperv_report_reg()) {
regs = current_pt_regs();
hyperv_report_panic(regs, val);
}
@@ -79,7 +91,7 @@ static int hyperv_die_event(struct notifier_block *nb, unsigned long val,
* doing hyperv_report_panic_msg() later with kmsg data, don't do
* the notification here.
*/
- if (!hv_panic_page)
+ if (hyperv_report_reg())
hyperv_report_panic(regs, val);
return NOTIFY_DONE;
}
@@ -1267,13 +1279,6 @@ static void vmbus_isr(void)
add_interrupt_randomness(HYPERVISOR_CALLBACK_VECTOR, 0);
}
-/*
- * Boolean to control whether to report panic messages over Hyper-V.
- *
- * It can be set via /proc/sys/kernel/hyperv/record_panic_msg
- */
-static int sysctl_record_panic_msg = 1;
-
/*
* Callback from kmsg_dump. Grab as much as possible from the end of the kmsg
* buffer and call into Hyper-V to transfer the data.
--
2.14.5
^ permalink raw reply related
* [PATCH V3 2/6] x86/Hyper-V: Free hv_panic_page when fail to register kmsg dump
From: ltykernel @ 2020-03-24 7:57 UTC (permalink / raw)
To: kys, haiyangz, sthemmin, liuwe, tglx, mingo, bp, hpa, x86,
michael.h.kelley
Cc: Tianyu Lan, linux-hyperv, linux-kernel, vkuznets
In-Reply-To: <20200324075720.9462-1-Tianyu.Lan@microsoft.com>
From: Tianyu Lan <Tianyu.Lan@microsoft.com>
If kmsg_dump_register() fails, hv_panic_page will not be used
anywhere. So free and reset it.
Signed-off-by: Tianyu Lan <Tianyu.Lan@microsoft.com>
---
Change since v1:
- Update commit log
- Remove hv_free_hyperv_page() in the error path
---
drivers/hv/vmbus_drv.c | 7 +++++--
1 file changed, 5 insertions(+), 2 deletions(-)
diff --git a/drivers/hv/vmbus_drv.c b/drivers/hv/vmbus_drv.c
index 6478240d11ab..00a511f15926 100644
--- a/drivers/hv/vmbus_drv.c
+++ b/drivers/hv/vmbus_drv.c
@@ -1385,9 +1385,13 @@ static int vmbus_bus_init(void)
hv_panic_page = (void *)hv_alloc_hyperv_zeroed_page();
if (hv_panic_page) {
ret = kmsg_dump_register(&hv_kmsg_dumper);
- if (ret)
+ if (ret) {
pr_err("Hyper-V: kmsg dump register "
"error 0x%x\n", ret);
+ hv_free_hyperv_page(
+ (unsigned long)hv_panic_page);
+ hv_panic_page = NULL;
+ }
} else
pr_err("Hyper-V: panic message page memory "
"allocation failed");
@@ -1416,7 +1420,6 @@ static int vmbus_bus_init(void)
hv_remove_vmbus_irq();
bus_unregister(&hv_bus);
- hv_free_hyperv_page((unsigned long)hv_panic_page);
unregister_sysctl_table(hv_ctl_table_hdr);
hv_ctl_table_hdr = NULL;
return ret;
--
2.14.5
^ permalink raw reply related
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox