diff mbox series

[v3,07/27] KVM: VMX: Initialize VMCS FRED fields

Message ID 20241001050110.3643764-8-xin@zytor.com (mailing list archive)
State New, archived
Headers show
Series Enable FRED with KVM VMX | expand

Commit Message

Xin Li Oct. 1, 2024, 5 a.m. UTC 
From: Xin Li <xin3.li@intel.com>

Initialize host VMCS FRED fields with host FRED MSRs' value and
guest VMCS FRED fields to 0.

FRED CPU states are managed in 9 new FRED MSRs, as well as a few
existing CPU registers and MSRs, e.g., CR4.FRED.  To support FRED
context management, new VMCS fields corresponding to most of FRED
CPU state MSRs are added to both the host-state and guest-state
areas of VMCS.

Specifically no VMCS fields are added for FRED RSP0 and SSP0 MSRs,
because the 2 FRED MSRs are used during ring 3 event delivery only,
thus KVM can run safely even with guest FRED RSP0 and SSP0.  Thus
save and restore of FRED RSP0 and SSP0 are deferred.

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>
---

Change since v2:
* Use structure kvm_host_values to keep host fred config & stack levels
  (Sean Christopherson).

Changes since v1:
* Use kvm_cpu_cap_has() instead of cpu_feature_enabled() to decouple
  KVM's capability to virtualize a feature and host's enabling of a
  feature (Chao Gao).
* Move guest FRED states init into __vmx_vcpu_reset() (Chao Gao).
---
 arch/x86/include/asm/vmx.h | 16 ++++++++++++++++
 arch/x86/kvm/vmx/vmx.c     | 34 ++++++++++++++++++++++++++++++++++
 arch/x86/kvm/x86.h         |  3 +++
 3 files changed, 53 insertions(+)

Comments

Chao Gao Oct. 22, 2024, 9:06 a.m. UTC | #1 
>@@ -1503,6 +1503,18 @@ void vmx_vcpu_load_vmcs(struct kvm_vcpu *vcpu, int cpu,
> 				    (unsigned long)(cpu_entry_stack(cpu) + 1));
> 		}
> 
>+		/* Per-CPU FRED MSRs */
>+		if (kvm_cpu_cap_has(X86_FEATURE_FRED)) {
>+#ifdef CONFIG_X86_64
>+			vmcs_write64(HOST_IA32_FRED_RSP1, __this_cpu_ist_top_va(DB));
>+			vmcs_write64(HOST_IA32_FRED_RSP2, __this_cpu_ist_top_va(NMI));
>+			vmcs_write64(HOST_IA32_FRED_RSP3, __this_cpu_ist_top_va(DF));
>+#endif
>+			vmcs_write64(HOST_IA32_FRED_SSP1, 0);
>+			vmcs_write64(HOST_IA32_FRED_SSP2, 0);
>+			vmcs_write64(HOST_IA32_FRED_SSP3, 0);

Given SSP[1-3] are constant for now, how about asserting that host SSP[1-3] are
all zeros when KVM is loaded and moving their writes to vmx_set_constant_host_state()?

>+		}
>+
> 		vmx->loaded_vmcs->cpu = cpu;
> 	}
> }
>@@ -4366,6 +4378,12 @@ void vmx_set_constant_host_state(struct vcpu_vmx *vmx)
> 	 */
> 	vmcs_write16(HOST_DS_SELECTOR, 0);
> 	vmcs_write16(HOST_ES_SELECTOR, 0);
>+
>+	/* FRED CONFIG and STKLVLS are the same on all CPUs. */
>+	if (kvm_cpu_cap_has(X86_FEATURE_FRED)) {
>+		vmcs_write64(HOST_IA32_FRED_CONFIG, kvm_host.fred_config);
>+		vmcs_write64(HOST_IA32_FRED_STKLVLS, kvm_host.fred_stklvls);
>+	}
> #else
> 	vmcs_write16(HOST_DS_SELECTOR, __KERNEL_DS);  /* 22.2.4 */
> 	vmcs_write16(HOST_ES_SELECTOR, __KERNEL_DS);  /* 22.2.4 */
Xin Li Oct. 22, 2024, 4:18 p.m. UTC | #2 
On 10/22/2024 2:06 AM, Chao Gao wrote:
>> @@ -1503,6 +1503,18 @@ void vmx_vcpu_load_vmcs(struct kvm_vcpu *vcpu, int cpu,
>> 				    (unsigned long)(cpu_entry_stack(cpu) + 1));
>> 		}
>>
>> +		/* Per-CPU FRED MSRs */
>> +		if (kvm_cpu_cap_has(X86_FEATURE_FRED)) {
>> +#ifdef CONFIG_X86_64
>> +			vmcs_write64(HOST_IA32_FRED_RSP1, __this_cpu_ist_top_va(DB));
>> +			vmcs_write64(HOST_IA32_FRED_RSP2, __this_cpu_ist_top_va(NMI));
>> +			vmcs_write64(HOST_IA32_FRED_RSP3, __this_cpu_ist_top_va(DF));
>> +#endif
>> +			vmcs_write64(HOST_IA32_FRED_SSP1, 0);
>> +			vmcs_write64(HOST_IA32_FRED_SSP2, 0);
>> +			vmcs_write64(HOST_IA32_FRED_SSP3, 0);
> 
> Given SSP[1-3] are constant for now, how about asserting that host SSP[1-3] are
> all zeros when KVM is loaded and moving their writes to vmx_set_constant_host_state()?

I like the idea :)
diff mbox series

Patch

diff --git a/arch/x86/include/asm/vmx.h b/arch/x86/include/asm/vmx.h
index 551f62892e1a..5184e03945dd 100644
--- a/arch/x86/include/asm/vmx.h
+++ b/arch/x86/include/asm/vmx.h
@@ -289,12 +289,28 @@  enum vmcs_field {
 	GUEST_BNDCFGS_HIGH              = 0x00002813,
 	GUEST_IA32_RTIT_CTL		= 0x00002814,
 	GUEST_IA32_RTIT_CTL_HIGH	= 0x00002815,
+	GUEST_IA32_FRED_CONFIG		= 0x0000281a,
+	GUEST_IA32_FRED_RSP1		= 0x0000281c,
+	GUEST_IA32_FRED_RSP2		= 0x0000281e,
+	GUEST_IA32_FRED_RSP3		= 0x00002820,
+	GUEST_IA32_FRED_STKLVLS		= 0x00002822,
+	GUEST_IA32_FRED_SSP1		= 0x00002824,
+	GUEST_IA32_FRED_SSP2		= 0x00002826,
+	GUEST_IA32_FRED_SSP3		= 0x00002828,
 	HOST_IA32_PAT			= 0x00002c00,
 	HOST_IA32_PAT_HIGH		= 0x00002c01,
 	HOST_IA32_EFER			= 0x00002c02,
 	HOST_IA32_EFER_HIGH		= 0x00002c03,
 	HOST_IA32_PERF_GLOBAL_CTRL	= 0x00002c04,
 	HOST_IA32_PERF_GLOBAL_CTRL_HIGH	= 0x00002c05,
+	HOST_IA32_FRED_CONFIG		= 0x00002c08,
+	HOST_IA32_FRED_RSP1		= 0x00002c0a,
+	HOST_IA32_FRED_RSP2		= 0x00002c0c,
+	HOST_IA32_FRED_RSP3		= 0x00002c0e,
+	HOST_IA32_FRED_STKLVLS		= 0x00002c10,
+	HOST_IA32_FRED_SSP1		= 0x00002c12,
+	HOST_IA32_FRED_SSP2		= 0x00002c14,
+	HOST_IA32_FRED_SSP3		= 0x00002c16,
 	PIN_BASED_VM_EXEC_CONTROL       = 0x00004000,
 	CPU_BASED_VM_EXEC_CONTROL       = 0x00004002,
 	EXCEPTION_BITMAP                = 0x00004004,
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index 9b4c30db911f..fee0df93e07c 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -1503,6 +1503,18 @@  void vmx_vcpu_load_vmcs(struct kvm_vcpu *vcpu, int cpu,
 				    (unsigned long)(cpu_entry_stack(cpu) + 1));
 		}
 
+		/* Per-CPU FRED MSRs */
+		if (kvm_cpu_cap_has(X86_FEATURE_FRED)) {
+#ifdef CONFIG_X86_64
+			vmcs_write64(HOST_IA32_FRED_RSP1, __this_cpu_ist_top_va(DB));
+			vmcs_write64(HOST_IA32_FRED_RSP2, __this_cpu_ist_top_va(NMI));
+			vmcs_write64(HOST_IA32_FRED_RSP3, __this_cpu_ist_top_va(DF));
+#endif
+			vmcs_write64(HOST_IA32_FRED_SSP1, 0);
+			vmcs_write64(HOST_IA32_FRED_SSP2, 0);
+			vmcs_write64(HOST_IA32_FRED_SSP3, 0);
+		}
+
 		vmx->loaded_vmcs->cpu = cpu;
 	}
 }
@@ -4366,6 +4378,12 @@  void vmx_set_constant_host_state(struct vcpu_vmx *vmx)
 	 */
 	vmcs_write16(HOST_DS_SELECTOR, 0);
 	vmcs_write16(HOST_ES_SELECTOR, 0);
+
+	/* FRED CONFIG and STKLVLS are the same on all CPUs. */
+	if (kvm_cpu_cap_has(X86_FEATURE_FRED)) {
+		vmcs_write64(HOST_IA32_FRED_CONFIG, kvm_host.fred_config);
+		vmcs_write64(HOST_IA32_FRED_STKLVLS, kvm_host.fred_stklvls);
+	}
 #else
 	vmcs_write16(HOST_DS_SELECTOR, __KERNEL_DS);  /* 22.2.4 */
 	vmcs_write16(HOST_ES_SELECTOR, __KERNEL_DS);  /* 22.2.4 */
@@ -4876,6 +4894,17 @@  static void init_vmcs(struct vcpu_vmx *vmx)
 	}
 
 	vmx_setup_uret_msrs(vmx);
+
+	if (kvm_cpu_cap_has(X86_FEATURE_FRED)) {
+		vmcs_write64(GUEST_IA32_FRED_CONFIG, 0);
+		vmcs_write64(GUEST_IA32_FRED_RSP1, 0);
+		vmcs_write64(GUEST_IA32_FRED_RSP2, 0);
+		vmcs_write64(GUEST_IA32_FRED_RSP3, 0);
+		vmcs_write64(GUEST_IA32_FRED_STKLVLS, 0);
+		vmcs_write64(GUEST_IA32_FRED_SSP1, 0);
+		vmcs_write64(GUEST_IA32_FRED_SSP2, 0);
+		vmcs_write64(GUEST_IA32_FRED_SSP3, 0);
+	}
 }
 
 static void __vmx_vcpu_reset(struct kvm_vcpu *vcpu)
@@ -8614,6 +8643,11 @@  __init int vmx_hardware_setup(void)
 
 	kvm_set_posted_intr_wakeup_handler(pi_wakeup_handler);
 
+	if (kvm_cpu_cap_has(X86_FEATURE_FRED)) {
+		rdmsrl(MSR_IA32_FRED_CONFIG, kvm_host.fred_config);
+		rdmsrl(MSR_IA32_FRED_STKLVLS, kvm_host.fred_stklvls);
+	}
+
 	return r;
 }
 
diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h
index a84c48ef5278..578fea05ff18 100644
--- a/arch/x86/kvm/x86.h
+++ b/arch/x86/kvm/x86.h
@@ -45,6 +45,9 @@  struct kvm_host_values {
 	u64 xcr0;
 	u64 xss;
 	u64 arch_capabilities;
+
+	u64 fred_config;
+	u64 fred_stklvls;
 };
 
 void kvm_spurious_fault(void);