From: "Xin Li (Intel)" <xin@zytor.com>
To: linux-kernel@vger.kernel.org, kvm@vger.kernel.org,
linux-doc@vger.kernel.org
Cc: pbonzini@redhat.com, seanjc@google.com, corbet@lwn.net,
tglx@linutronix.de, mingo@redhat.com, bp@alien8.de,
dave.hansen@linux.intel.com, x86@kernel.org, hpa@zytor.com,
xin@zytor.com, luto@kernel.org, peterz@infradead.org,
andrew.cooper3@citrix.com, chao.gao@intel.com, hch@infradead.org
Subject: [PATCH v6 16/20] KVM: nVMX: Add support for the secondary VM exit controls
Date: Thu, 21 Aug 2025 15:36:25 -0700 [thread overview]
Message-ID: <20250821223630.984383-17-xin@zytor.com> (raw)
In-Reply-To: <20250821223630.984383-1-xin@zytor.com>
From: Xin Li <xin3.li@intel.com>
Enable the secondary VM exit controls to prepare for nested FRED.
Signed-off-by: Xin Li <xin3.li@intel.com>
Signed-off-by: Xin Li (Intel) <xin@zytor.com>
Tested-by: Shan Kang <shan.kang@intel.com>
Tested-by: Xuelian Guo <xuelian.guo@intel.com>
---
Changes in v5:
* Allow writing MSR_IA32_VMX_EXIT_CTLS2 (Sean).
* Add TB from Xuelian Guo.
Change in v3:
* Read secondary VM exit controls from vmcs_conf insteasd of the hardware
MSR MSR_IA32_VMX_EXIT_CTLS2 to avoid advertising features to L1 that KVM
itself doesn't support, e.g. because the expected entry+exit pairs aren't
supported. (Sean Christopherson)
---
Documentation/virt/kvm/x86/nested-vmx.rst | 1 +
arch/x86/kvm/vmx/capabilities.h | 1 +
arch/x86/kvm/vmx/nested.c | 26 ++++++++++++++++++++++-
arch/x86/kvm/vmx/vmcs12.c | 1 +
arch/x86/kvm/vmx/vmcs12.h | 2 ++
arch/x86/kvm/x86.h | 2 +-
6 files changed, 31 insertions(+), 2 deletions(-)
diff --git a/Documentation/virt/kvm/x86/nested-vmx.rst b/Documentation/virt/kvm/x86/nested-vmx.rst
index ac2095d41f02..e64ef231f310 100644
--- a/Documentation/virt/kvm/x86/nested-vmx.rst
+++ b/Documentation/virt/kvm/x86/nested-vmx.rst
@@ -217,6 +217,7 @@ struct shadow_vmcs is ever changed.
u16 host_fs_selector;
u16 host_gs_selector;
u16 host_tr_selector;
+ u64 secondary_vm_exit_controls;
};
diff --git a/arch/x86/kvm/vmx/capabilities.h b/arch/x86/kvm/vmx/capabilities.h
index 7fe95a601c9f..c9f00b6594d9 100644
--- a/arch/x86/kvm/vmx/capabilities.h
+++ b/arch/x86/kvm/vmx/capabilities.h
@@ -37,6 +37,7 @@ struct nested_vmx_msrs {
u32 pinbased_ctls_high;
u32 exit_ctls_low;
u32 exit_ctls_high;
+ u64 secondary_exit_ctls;
u32 entry_ctls_low;
u32 entry_ctls_high;
u32 misc_low;
diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c
index d7e2fb30fc1a..e4de8372b9f9 100644
--- a/arch/x86/kvm/vmx/nested.c
+++ b/arch/x86/kvm/vmx/nested.c
@@ -1531,6 +1531,11 @@ int vmx_set_vmx_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 data)
return -EINVAL;
vmx->nested.msrs.vmfunc_controls = data;
return 0;
+ case MSR_IA32_VMX_EXIT_CTLS2:
+ if (data & ~vmcs_config.nested.secondary_exit_ctls)
+ return -EINVAL;
+ vmx->nested.msrs.secondary_exit_ctls = data;
+ return 0;
default:
/*
* The rest of the VMX capability MSRs do not support restore.
@@ -1570,6 +1575,9 @@ int vmx_get_vmx_msr(struct nested_vmx_msrs *msrs, u32 msr_index, u64 *pdata)
if (msr_index == MSR_IA32_VMX_EXIT_CTLS)
*pdata |= VM_EXIT_ALWAYSON_WITHOUT_TRUE_MSR;
break;
+ case MSR_IA32_VMX_EXIT_CTLS2:
+ *pdata = msrs->secondary_exit_ctls;
+ break;
case MSR_IA32_VMX_TRUE_ENTRY_CTLS:
case MSR_IA32_VMX_ENTRY_CTLS:
*pdata = vmx_control_msr(
@@ -2520,6 +2528,11 @@ static void prepare_vmcs02_early(struct vcpu_vmx *vmx, struct loaded_vmcs *vmcs0
exec_control &= ~VM_EXIT_LOAD_IA32_EFER;
vm_exit_controls_set(vmx, exec_control);
+ if (exec_control & VM_EXIT_ACTIVATE_SECONDARY_CONTROLS) {
+ exec_control = __secondary_vm_exit_controls_get(vmcs01);
+ secondary_vm_exit_controls_set(vmx, exec_control);
+ }
+
/*
* Interrupt/Exception Fields
*/
@@ -7176,7 +7189,8 @@ static void nested_vmx_setup_exit_ctls(struct vmcs_config *vmcs_conf,
VM_EXIT_HOST_ADDR_SPACE_SIZE |
#endif
VM_EXIT_LOAD_IA32_PAT | VM_EXIT_SAVE_IA32_PAT |
- VM_EXIT_CLEAR_BNDCFGS | VM_EXIT_LOAD_CET_STATE;
+ VM_EXIT_CLEAR_BNDCFGS | VM_EXIT_LOAD_CET_STATE |
+ VM_EXIT_ACTIVATE_SECONDARY_CONTROLS;
msrs->exit_ctls_high |=
VM_EXIT_ALWAYSON_WITHOUT_TRUE_MSR |
VM_EXIT_LOAD_IA32_EFER | VM_EXIT_SAVE_IA32_EFER |
@@ -7185,6 +7199,16 @@ static void nested_vmx_setup_exit_ctls(struct vmcs_config *vmcs_conf,
/* We support free control of debug control saving. */
msrs->exit_ctls_low &= ~VM_EXIT_SAVE_DEBUG_CONTROLS;
+
+ if (msrs->exit_ctls_high & VM_EXIT_ACTIVATE_SECONDARY_CONTROLS) {
+ msrs->secondary_exit_ctls = vmcs_conf->vmexit_2nd_ctrl;
+ /*
+ * As the secondary VM exit control is always loaded, do not
+ * advertise any feature in it to nVMX until its nVMX support
+ * is ready.
+ */
+ msrs->secondary_exit_ctls &= 0;
+ }
}
static void nested_vmx_setup_entry_ctls(struct vmcs_config *vmcs_conf,
diff --git a/arch/x86/kvm/vmx/vmcs12.c b/arch/x86/kvm/vmx/vmcs12.c
index 4233b5ca9461..3b01175f392a 100644
--- a/arch/x86/kvm/vmx/vmcs12.c
+++ b/arch/x86/kvm/vmx/vmcs12.c
@@ -66,6 +66,7 @@ const unsigned short vmcs12_field_offsets[] = {
FIELD64(HOST_IA32_PAT, host_ia32_pat),
FIELD64(HOST_IA32_EFER, host_ia32_efer),
FIELD64(HOST_IA32_PERF_GLOBAL_CTRL, host_ia32_perf_global_ctrl),
+ FIELD64(SECONDARY_VM_EXIT_CONTROLS, secondary_vm_exit_controls),
FIELD(PIN_BASED_VM_EXEC_CONTROL, pin_based_vm_exec_control),
FIELD(CPU_BASED_VM_EXEC_CONTROL, cpu_based_vm_exec_control),
FIELD(EXCEPTION_BITMAP, exception_bitmap),
diff --git a/arch/x86/kvm/vmx/vmcs12.h b/arch/x86/kvm/vmx/vmcs12.h
index 4ad6b16525b9..7866fdce7a23 100644
--- a/arch/x86/kvm/vmx/vmcs12.h
+++ b/arch/x86/kvm/vmx/vmcs12.h
@@ -191,6 +191,7 @@ struct __packed vmcs12 {
u16 host_gs_selector;
u16 host_tr_selector;
u16 guest_pml_index;
+ u64 secondary_vm_exit_controls;
};
/*
@@ -372,6 +373,7 @@ static inline void vmx_check_vmcs12_offsets(void)
CHECK_OFFSET(host_gs_selector, 992);
CHECK_OFFSET(host_tr_selector, 994);
CHECK_OFFSET(guest_pml_index, 996);
+ CHECK_OFFSET(secondary_vm_exit_controls, 998);
}
extern const unsigned short vmcs12_field_offsets[];
diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h
index c9f010862b2a..88a4eaafc81b 100644
--- a/arch/x86/kvm/x86.h
+++ b/arch/x86/kvm/x86.h
@@ -95,7 +95,7 @@ do { \
* associated feature that KVM supports for nested virtualization.
*/
#define KVM_FIRST_EMULATED_VMX_MSR MSR_IA32_VMX_BASIC
-#define KVM_LAST_EMULATED_VMX_MSR MSR_IA32_VMX_VMFUNC
+#define KVM_LAST_EMULATED_VMX_MSR MSR_IA32_VMX_EXIT_CTLS2
#define KVM_DEFAULT_PLE_GAP 128
#define KVM_VMX_DEFAULT_PLE_WINDOW 4096
--
2.50.1
next prev parent reply other threads:[~2025-08-21 22:37 UTC|newest]
Thread overview: 33+ messages / expand[flat|nested] mbox.gz Atom feed top
2025-08-21 22:36 [PATCH v6 00/20] Enable FRED with KVM VMX Xin Li (Intel)
2025-08-21 22:36 ` [PATCH v6 01/20] KVM: VMX: Add support for the secondary VM exit controls Xin Li (Intel)
2025-08-21 22:36 ` [PATCH v6 02/20] KVM: VMX: Initialize VM entry/exit FRED controls in vmcs_config Xin Li (Intel)
2025-08-21 22:36 ` [PATCH v6 03/20] KVM: VMX: Disable FRED if FRED consistency checks fail Xin Li (Intel)
2025-08-21 22:36 ` [PATCH v6 04/20] x86/cea: Export an API to get per CPU exception stacks for KVM to use Xin Li (Intel)
2025-08-27 17:33 ` Dave Hansen
2025-08-27 22:18 ` Xin Li
2025-08-21 22:36 ` [PATCH v6 05/20] KVM: VMX: Initialize VMCS FRED fields Xin Li (Intel)
2025-08-21 22:36 ` [PATCH v6 06/20] KVM: VMX: Set FRED MSR intercepts Xin Li (Intel)
2025-08-25 2:51 ` Xin Li
2025-08-26 18:11 ` Sean Christopherson
2025-08-26 21:59 ` Xin Li
2025-08-26 22:17 ` Sean Christopherson
2025-08-27 22:24 ` Xin Li
2025-08-27 22:43 ` Xin Li
2025-08-28 23:32 ` Sean Christopherson
2025-08-26 18:50 ` Andrew Cooper
2025-08-26 22:03 ` Xin Li
2025-08-26 22:20 ` Andrew Cooper
2025-08-21 22:36 ` [PATCH v6 07/20] KVM: VMX: Save/restore guest FRED RSP0 Xin Li (Intel)
2025-08-21 22:36 ` [PATCH v6 08/20] KVM: VMX: Add support for FRED context save/restore Xin Li (Intel)
2025-08-21 22:36 ` [PATCH v6 09/20] KVM: x86: Add a helper to detect if FRED is enabled for a vCPU Xin Li (Intel)
2025-08-21 22:36 ` [PATCH v6 10/20] KVM: VMX: Virtualize FRED event_data Xin Li (Intel)
2025-08-21 22:36 ` [PATCH v6 11/20] KVM: VMX: Virtualize FRED nested exception tracking Xin Li (Intel)
2025-08-21 22:36 ` [PATCH v6 12/20] KVM: x86: Save/restore the nested flag of an exception Xin Li (Intel)
2025-08-21 22:36 ` [PATCH v6 13/20] KVM: x86: Mark CR4.FRED as not reserved Xin Li (Intel)
2025-08-21 22:36 ` [PATCH v6 14/20] KVM: VMX: Dump FRED context in dump_vmcs() Xin Li (Intel)
2025-08-21 22:36 ` [PATCH v6 15/20] KVM: x86: Advertise support for FRED Xin Li (Intel)
2025-08-21 22:36 ` Xin Li (Intel) [this message]
2025-08-21 22:36 ` [PATCH v6 17/20] KVM: nVMX: Add FRED VMCS fields to nested VMX context handling Xin Li (Intel)
2025-08-21 22:36 ` [PATCH v6 18/20] KVM: nVMX: Add FRED-related VMCS field checks Xin Li (Intel)
2025-08-21 22:36 ` [PATCH v6 19/20] KVM: nVMX: Add prerequisites to SHADOW_FIELD_R[OW] macros Xin Li (Intel)
2025-08-21 22:36 ` [PATCH v6 20/20] KVM: nVMX: Allow VMX FRED controls Xin Li (Intel)
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20250821223630.984383-17-xin@zytor.com \
--to=xin@zytor.com \
--cc=andrew.cooper3@citrix.com \
--cc=bp@alien8.de \
--cc=chao.gao@intel.com \
--cc=corbet@lwn.net \
--cc=dave.hansen@linux.intel.com \
--cc=hch@infradead.org \
--cc=hpa@zytor.com \
--cc=kvm@vger.kernel.org \
--cc=linux-doc@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=luto@kernel.org \
--cc=mingo@redhat.com \
--cc=pbonzini@redhat.com \
--cc=peterz@infradead.org \
--cc=seanjc@google.com \
--cc=tglx@linutronix.de \
--cc=x86@kernel.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).