From c1f18fa634719a4622be9ca02660dd8e194b0532 Mon Sep 17 00:00:00 2001
From: Jinank Jain <jinankjain@microsoft.com>
Date: Wed, 17 Jul 2024 17:39:01 +0530
Subject: [PATCH] arch: x86_64: Don't expose TSC deadline timer for MSHV guests

HV APIC(i.e., synthetic APIC controller exposed by Microsoft Hypervisor)
does not support one-shot operation using a TSC deadline value. Due to
which we see the following backtrace inside the guest when running with
hypervisor-fw/OVMF:

[    0.560765] unchecked MSR access error: WRMSR to 0x832 (tried to
write 0x00000000000400ec) at rIP: 0xffffffff8f473594
(native_write_msr+0x4/0x30)
[    0.560765] Call Trace:
[    0.560765]  ? native_apic_msr_write+0x2b/0x30
[    0.560765]  __setup_APIC_LVTT+0xbc/0xe0
[    0.560765]  lapic_timer_set_oneshot+0x27/0x30
[    0.560765]  clockevents_switch_state+0xaf/0xf0
[    0.560765]  tick_setup_periodic+0x47/0x90
[    0.560765]  tick_setup_device.isra.0+0x7c/0x110
[    0.560765]  tick_check_new_device+0xce/0xf0
[    0.560765]  clockevents_register_device+0x82/0x170
[    0.560765]  clockevents_config_and_register+0x2f/0x40
[    0.560765]  setup_APIC_timer+0xe1/0xf0
[    0.560765]  setup_boot_APIC_clock+0x5f/0x66
[    0.560765]  native_smp_prepare_cpus+0x1d6/0x286
[    0.560765]  kernel_init_freeable+0xcf/0x255
[    0.560765]  ? rest_init+0xb0/0xb0
[    0.560765]  kernel_init+0xe/0x110
[    0.560765]  ret_from_fork+0x22/0x40

Also, if this feature is exposed guest would not finish booting and get
stuck right before unpacking the root filesystem.

Fixes: 06e8d1c40 ("hypervisor: mshv: fix topology for Intel HW on MSHV")
Signed-off-by: Jinank Jain <jinankjain@microsoft.com>
---
 arch/Cargo.toml        |  1 +
 arch/src/x86_64/mod.rs | 31 ++++++++++++++++++++-----------
 vmm/Cargo.toml         | 10 ++++++++--
 3 files changed, 29 insertions(+), 13 deletions(-)

diff --git a/arch/Cargo.toml b/arch/Cargo.toml
index 74e6409c1..70bc61fbb 100644
--- a/arch/Cargo.toml
+++ b/arch/Cargo.toml
@@ -6,6 +6,7 @@ version = "0.1.0"
 
 [features]
 default = []
+kvm = []
 sev_snp = []
 tdx = []
 
diff --git a/arch/src/x86_64/mod.rs b/arch/src/x86_64/mod.rs
index a4bbe4a73..a412663e2 100644
--- a/arch/src/x86_64/mod.rs
+++ b/arch/src/x86_64/mod.rs
@@ -34,6 +34,7 @@ use std::arch::x86_64;
 pub mod tdx;
 
 // CPUID feature bits
+#[cfg(feature = "kvm")]
 const TSC_DEADLINE_TIMER_ECX_BIT: u8 = 24; // tsc deadline timer ecx bit.
 const HYPERVISOR_ECX_BIT: u8 = 31; // Hypervisor ecx bit.
 const MTRR_EDX_BIT: u8 = 12; // Hypervisor ecx bit.
@@ -619,17 +620,8 @@ pub fn generate_common_cpuid(
         "Generating guest CPUID for with physical address size: {}",
         config.phys_bits
     );
-    let cpuid_patches = vec![
-        // Patch tsc deadline timer bit
-        CpuidPatch {
-            function: 1,
-            index: 0,
-            flags_bit: None,
-            eax_bit: None,
-            ebx_bit: None,
-            ecx_bit: Some(TSC_DEADLINE_TIMER_ECX_BIT),
-            edx_bit: None,
-        },
+    #[allow(unused_mut)]
+    let mut cpuid_patches = vec![
         // Patch hypervisor bit
         CpuidPatch {
             function: 1,
@@ -652,6 +644,23 @@ pub fn generate_common_cpuid(
         },
     ];
 
+    #[cfg(feature = "kvm")]
+    if matches!(
+        hypervisor.hypervisor_type(),
+        hypervisor::HypervisorType::Kvm
+    ) {
+        // Patch tsc deadline timer bit
+        cpuid_patches.push(CpuidPatch {
+            function: 1,
+            index: 0,
+            flags_bit: None,
+            eax_bit: None,
+            ebx_bit: None,
+            ecx_bit: Some(TSC_DEADLINE_TIMER_ECX_BIT),
+            edx_bit: None,
+        });
+    }
+
     // Supported CPUID
     let mut cpuid = hypervisor
         .get_supported_cpuid()
diff --git a/vmm/Cargo.toml b/vmm/Cargo.toml
index 492540f90..9e9773c61 100644
--- a/vmm/Cargo.toml
+++ b/vmm/Cargo.toml
@@ -7,11 +7,17 @@ version = "0.1.0"
 [features]
 dbus_api = ["blocking", "futures", "zbus"]
 default = []
-dhat-heap = ["dhat"]                                                         # For heap profiling
+dhat-heap = ["dhat"] # For heap profiling
 guest_debug = ["gdbstub", "gdbstub_arch", "kvm"]
 igvm = ["dep:igvm", "hex", "igvm_defs", "mshv-bindings", "range_map_vec"]
 io_uring = ["block/io_uring"]
-kvm = ["hypervisor/kvm", "pci/kvm", "vfio-ioctls/kvm", "vm-device/kvm"]
+kvm = [
+  "arch/kvm",
+  "hypervisor/kvm",
+  "pci/kvm",
+  "vfio-ioctls/kvm",
+  "vm-device/kvm",
+]
 mshv = ["hypervisor/mshv", "pci/mshv", "vfio-ioctls/mshv", "vm-device/mshv"]
 sev_snp = ["arch/sev_snp", "hypervisor/sev_snp", "virtio-devices/sev_snp"]
 tdx = ["arch/tdx", "hypervisor/tdx"]