[PATCH v4 0/5] KVM: x86: dump_vmcs: don't assume GUEST_IA32_EFER, show MSR autoloads/autosaves

[PATCH v4 0/5] KVM: x86: dump_vmcs: don't assume GUEST_IA32_EFER, show MSR autoloads/autosaves

[David Edmondson]

v2:
- Don't use vcpu->arch.efer when GUEST_IA32_EFER is not available (Paolo).
- Dump the MSR autoload/autosave lists (Paolo).

v3:
- Rebase to master.
- Check only the load controls (Sean).
- Always show the PTPRs from the VMCS if they exist (Jim/Sean).
- Dig EFER out of the MSR autoload list if it's there (Paulo).
- Calculate and show the effective EFER if it is not coming from
  either the VMCS or the MSR autoload list (Sean).

v4:
- Ensure that each changeset builds with just the previous set.

David Edmondson (5):
  KVM: x86: dump_vmcs should not assume GUEST_IA32_EFER is valid
  KVM: x86: dump_vmcs should not conflate EFER and PAT presence in VMCS
  KVM: x86: dump_vmcs should consider only the load controls of EFER/PAT
  KVM: x86: dump_vmcs should show the effective EFER
  KVM: x86: dump_vmcs should include the autoload/autostore MSR lists

 arch/x86/kvm/vmx/vmx.c | 58 +++++++++++++++++++++++++++++-------------
 arch/x86/kvm/vmx/vmx.h |  2 +-
 2 files changed, 42 insertions(+), 18 deletions(-)

-- 
2.30.0

[PATCH v4 1/5] KVM: x86: dump_vmcs should not assume GUEST_IA32_EFER is valid

[David Edmondson]

If the VM entry/exit controls for loading/saving MSR_EFER are either
not available (an older processor or explicitly disabled) or not
used (host and guest values are the same), reading GUEST_IA32_EFER
from the VMCS returns an inaccurate value.

Because of this, in dump_vmcs() don't use GUEST_IA32_EFER to decide
whether to print the PDPTRs - always do so if the fields exist.

Fixes: 4eb64dce8d0a ("KVM: x86: dump VMCS on invalid entry")
Signed-off-by: David Edmondson <david.edmondson@oracle.com>

if valid
---
 arch/x86/kvm/vmx/vmx.c | 9 +++------
 1 file changed, 3 insertions(+), 6 deletions(-)

diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index e0a3a9be654b..ea1b3a671d51 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -5815,7 +5815,6 @@ void dump_vmcs(void)
 	u32 vmentry_ctl, vmexit_ctl;
 	u32 cpu_based_exec_ctrl, pin_based_exec_ctrl, secondary_exec_control;
 	unsigned long cr4;
-	u64 efer;
 
 	if (!dump_invalid_vmcs) {
 		pr_warn_ratelimited("set kvm_intel.dump_invalid_vmcs=1 to dump internal KVM state.\n");
@@ -5827,7 +5826,6 @@ void dump_vmcs(void)
 	cpu_based_exec_ctrl = vmcs_read32(CPU_BASED_VM_EXEC_CONTROL);
 	pin_based_exec_ctrl = vmcs_read32(PIN_BASED_VM_EXEC_CONTROL);
 	cr4 = vmcs_readl(GUEST_CR4);
-	efer = vmcs_read64(GUEST_IA32_EFER);
 	secondary_exec_control = 0;
 	if (cpu_has_secondary_exec_ctrls())
 		secondary_exec_control = vmcs_read32(SECONDARY_VM_EXEC_CONTROL);
@@ -5839,9 +5837,7 @@ void dump_vmcs(void)
 	pr_err("CR4: actual=0x%016lx, shadow=0x%016lx, gh_mask=%016lx\n",
 	       cr4, vmcs_readl(CR4_READ_SHADOW), vmcs_readl(CR4_GUEST_HOST_MASK));
 	pr_err("CR3 = 0x%016lx\n", vmcs_readl(GUEST_CR3));
-	if ((secondary_exec_control & SECONDARY_EXEC_ENABLE_EPT) &&
-	    (cr4 & X86_CR4_PAE) && !(efer & EFER_LMA))
-	{
+	if (cpu_has_vmx_ept()) {
 		pr_err("PDPTR0 = 0x%016llx  PDPTR1 = 0x%016llx\n",
 		       vmcs_read64(GUEST_PDPTR0), vmcs_read64(GUEST_PDPTR1));
 		pr_err("PDPTR2 = 0x%016llx  PDPTR3 = 0x%016llx\n",
@@ -5867,7 +5863,8 @@ void dump_vmcs(void)
 	if ((vmexit_ctl & (VM_EXIT_SAVE_IA32_PAT | VM_EXIT_SAVE_IA32_EFER)) ||
 	    (vmentry_ctl & (VM_ENTRY_LOAD_IA32_PAT | VM_ENTRY_LOAD_IA32_EFER)))
 		pr_err("EFER =     0x%016llx  PAT = 0x%016llx\n",
-		       efer, vmcs_read64(GUEST_IA32_PAT));
+		       vmcs_read64(GUEST_IA32_EFER),
+		       vmcs_read64(GUEST_IA32_PAT));
 	pr_err("DebugCtl = 0x%016llx  DebugExceptions = 0x%016lx\n",
 	       vmcs_read64(GUEST_IA32_DEBUGCTL),
 	       vmcs_readl(GUEST_PENDING_DBG_EXCEPTIONS));
-- 
2.30.0

[PATCH v4 2/5] KVM: x86: dump_vmcs should not conflate EFER and PAT presence in VMCS

[David Edmondson]

Show EFER and PAT based on their individual entry/exit controls.

Signed-off-by: David Edmondson <david.edmondson@oracle.com>
---
 arch/x86/kvm/vmx/vmx.c | 19 ++++++++++---------
 1 file changed, 10 insertions(+), 9 deletions(-)

diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index ea1b3a671d51..90d677d72502 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -5860,11 +5860,12 @@ void dump_vmcs(void)
 	vmx_dump_sel("LDTR:", GUEST_LDTR_SELECTOR);
 	vmx_dump_dtsel("IDTR:", GUEST_IDTR_LIMIT);
 	vmx_dump_sel("TR:  ", GUEST_TR_SELECTOR);
-	if ((vmexit_ctl & (VM_EXIT_SAVE_IA32_PAT | VM_EXIT_SAVE_IA32_EFER)) ||
-	    (vmentry_ctl & (VM_ENTRY_LOAD_IA32_PAT | VM_ENTRY_LOAD_IA32_EFER)))
-		pr_err("EFER =     0x%016llx  PAT = 0x%016llx\n",
-		       vmcs_read64(GUEST_IA32_EFER),
-		       vmcs_read64(GUEST_IA32_PAT));
+	if ((vmexit_ctl & VM_EXIT_SAVE_IA32_EFER) ||
+	    (vmentry_ctl & VM_ENTRY_LOAD_IA32_EFER))
+		pr_err("EFER= 0x%016llx\n", vmcs_read64(GUEST_IA32_EFER));
+	if ((vmexit_ctl & VM_EXIT_SAVE_IA32_PAT) ||
+	    (vmentry_ctl & VM_ENTRY_LOAD_IA32_PAT))
+		pr_err("PAT = 0x%016llx\n", vmcs_read64(GUEST_IA32_PAT));
 	pr_err("DebugCtl = 0x%016llx  DebugExceptions = 0x%016lx\n",
 	       vmcs_read64(GUEST_IA32_DEBUGCTL),
 	       vmcs_readl(GUEST_PENDING_DBG_EXCEPTIONS));
@@ -5901,10 +5902,10 @@ void dump_vmcs(void)
 	       vmcs_readl(HOST_IA32_SYSENTER_ESP),
 	       vmcs_read32(HOST_IA32_SYSENTER_CS),
 	       vmcs_readl(HOST_IA32_SYSENTER_EIP));
-	if (vmexit_ctl & (VM_EXIT_LOAD_IA32_PAT | VM_EXIT_LOAD_IA32_EFER))
-		pr_err("EFER = 0x%016llx  PAT = 0x%016llx\n",
-		       vmcs_read64(HOST_IA32_EFER),
-		       vmcs_read64(HOST_IA32_PAT));
+	if (vmexit_ctl & VM_EXIT_LOAD_IA32_EFER)
+		pr_err("EFER= 0x%016llx\n", vmcs_read64(HOST_IA32_EFER));
+	if (vmexit_ctl & VM_EXIT_LOAD_IA32_PAT)
+		pr_err("PAT = 0x%016llx\n", vmcs_read64(HOST_IA32_PAT));
 	if (cpu_has_load_perf_global_ctrl() &&
 	    vmexit_ctl & VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL)
 		pr_err("PerfGlobCtl = 0x%016llx\n",
-- 
2.30.0

[PATCH v4 3/5] KVM: x86: dump_vmcs should consider only the load controls of EFER/PAT

[David Edmondson]

When deciding whether to dump the GUEST_IA32_EFER and GUEST_IA32_PAT
fields of the VMCS, examine only the VM entry load controls, as saving
on VM exit has no effect on whether VM entry succeeds or fails.

Suggested-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: David Edmondson <david.edmondson@oracle.com>
---
 arch/x86/kvm/vmx/vmx.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index 90d677d72502..faeb3d3bd1b8 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -5860,11 +5860,9 @@ void dump_vmcs(void)
 	vmx_dump_sel("LDTR:", GUEST_LDTR_SELECTOR);
 	vmx_dump_dtsel("IDTR:", GUEST_IDTR_LIMIT);
 	vmx_dump_sel("TR:  ", GUEST_TR_SELECTOR);
-	if ((vmexit_ctl & VM_EXIT_SAVE_IA32_EFER) ||
-	    (vmentry_ctl & VM_ENTRY_LOAD_IA32_EFER))
+	if (vmentry_ctl & VM_ENTRY_LOAD_IA32_EFER)
 		pr_err("EFER= 0x%016llx\n", vmcs_read64(GUEST_IA32_EFER));
-	if ((vmexit_ctl & VM_EXIT_SAVE_IA32_PAT) ||
-	    (vmentry_ctl & VM_ENTRY_LOAD_IA32_PAT))
+	if (vmentry_ctl & VM_ENTRY_LOAD_IA32_PAT)
 		pr_err("PAT = 0x%016llx\n", vmcs_read64(GUEST_IA32_PAT));
 	pr_err("DebugCtl = 0x%016llx  DebugExceptions = 0x%016lx\n",
 	       vmcs_read64(GUEST_IA32_DEBUGCTL),
-- 
2.30.0

[PATCH v4 4/5] KVM: x86: dump_vmcs should show the effective EFER

[David Edmondson]

If EFER is not being loaded from the VMCS, show the effective value by
reference to the MSR autoload list or calculation.

Signed-off-by: David Edmondson <david.edmondson@oracle.com>
---
 arch/x86/kvm/vmx/vmx.c | 20 ++++++++++++++++----
 arch/x86/kvm/vmx/vmx.h |  2 +-
 2 files changed, 17 insertions(+), 5 deletions(-)

diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index faeb3d3bd1b8..b9bb66ad2ac4 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -5810,11 +5810,13 @@ static void vmx_dump_dtsel(char *name, uint32_t limit)
 	       vmcs_readl(limit + GUEST_GDTR_BASE - GUEST_GDTR_LIMIT));
 }
 
-void dump_vmcs(void)
+void dump_vmcs(struct kvm_vcpu *vcpu)
 {
+	struct vcpu_vmx *vmx = to_vmx(vcpu);
 	u32 vmentry_ctl, vmexit_ctl;
 	u32 cpu_based_exec_ctrl, pin_based_exec_ctrl, secondary_exec_control;
 	unsigned long cr4;
+	int efer_slot;
 
 	if (!dump_invalid_vmcs) {
 		pr_warn_ratelimited("set kvm_intel.dump_invalid_vmcs=1 to dump internal KVM state.\n");
@@ -5860,8 +5862,18 @@ void dump_vmcs(void)
 	vmx_dump_sel("LDTR:", GUEST_LDTR_SELECTOR);
 	vmx_dump_dtsel("IDTR:", GUEST_IDTR_LIMIT);
 	vmx_dump_sel("TR:  ", GUEST_TR_SELECTOR);
+	efer_slot = vmx_find_loadstore_msr_slot(&vmx->msr_autoload.guest, MSR_EFER);
 	if (vmentry_ctl & VM_ENTRY_LOAD_IA32_EFER)
 		pr_err("EFER= 0x%016llx\n", vmcs_read64(GUEST_IA32_EFER));
+	else if (efer_slot >= 0)
+		pr_err("EFER= 0x%016llx (autoload)\n",
+		       vmx->msr_autoload.guest.val[efer_slot].value);
+	else if (vmentry_ctl & VM_ENTRY_IA32E_MODE)
+		pr_err("EFER= 0x%016llx (effective)\n",
+		       vcpu->arch.efer | (EFER_LMA | EFER_LME));
+	else
+		pr_err("EFER= 0x%016llx (effective)\n",
+		       vcpu->arch.efer & ~(EFER_LMA | EFER_LME));
 	if (vmentry_ctl & VM_ENTRY_LOAD_IA32_PAT)
 		pr_err("PAT = 0x%016llx\n", vmcs_read64(GUEST_IA32_PAT));
 	pr_err("DebugCtl = 0x%016llx  DebugExceptions = 0x%016lx\n",
@@ -6008,7 +6020,7 @@ static int __vmx_handle_exit(struct kvm_vcpu *vcpu, fastpath_t exit_fastpath)
 	}
 
 	if (exit_reason.failed_vmentry) {
-		dump_vmcs();
+		dump_vmcs(vcpu);
 		vcpu->run->exit_reason = KVM_EXIT_FAIL_ENTRY;
 		vcpu->run->fail_entry.hardware_entry_failure_reason
 			= exit_reason.full;
@@ -6017,7 +6029,7 @@ static int __vmx_handle_exit(struct kvm_vcpu *vcpu, fastpath_t exit_fastpath)
 	}
 
 	if (unlikely(vmx->fail)) {
-		dump_vmcs();
+		dump_vmcs(vcpu);
 		vcpu->run->exit_reason = KVM_EXIT_FAIL_ENTRY;
 		vcpu->run->fail_entry.hardware_entry_failure_reason
 			= vmcs_read32(VM_INSTRUCTION_ERROR);
@@ -6103,7 +6115,7 @@ static int __vmx_handle_exit(struct kvm_vcpu *vcpu, fastpath_t exit_fastpath)
 unexpected_vmexit:
 	vcpu_unimpl(vcpu, "vmx: unexpected exit reason 0x%x\n",
 		    exit_reason.full);
-	dump_vmcs();
+	dump_vmcs(vcpu);
 	vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
 	vcpu->run->internal.suberror =
 			KVM_INTERNAL_ERROR_UNEXPECTED_EXIT_REASON;
diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h
index 12c53d05a902..4d4a24e00012 100644
--- a/arch/x86/kvm/vmx/vmx.h
+++ b/arch/x86/kvm/vmx/vmx.h
@@ -541,6 +541,6 @@ static inline bool vmx_guest_state_valid(struct kvm_vcpu *vcpu)
 	return is_unrestricted_guest(vcpu) || __vmx_guest_state_valid(vcpu);
 }
 
-void dump_vmcs(void);
+void dump_vmcs(struct kvm_vcpu *vcpu);
 
 #endif /* __KVM_X86_VMX_H */
-- 
2.30.0

[PATCH v4 5/5] KVM: x86: dump_vmcs should include the autoload/autostore MSR lists

[David Edmondson]

When dumping the current VMCS state, include the MSRs that are being
automatically loaded/stored during VM entry/exit.

Signed-off-by: David Edmondson <david.edmondson@oracle.com>
---
 arch/x86/kvm/vmx/vmx.c | 16 ++++++++++++++++
 1 file changed, 16 insertions(+)

diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index b9bb66ad2ac4..de42b8c14a38 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -5810,6 +5810,16 @@ static void vmx_dump_dtsel(char *name, uint32_t limit)
 	       vmcs_readl(limit + GUEST_GDTR_BASE - GUEST_GDTR_LIMIT));
 }
 
+static void vmx_dump_msrs(char *name, struct vmx_msrs *m)
+{
+	unsigned int i;
+	struct vmx_msr_entry *e;
+
+	pr_err("MSR %s:\n", name);
+	for (i = 0, e = m->val; i < m->nr; ++i, ++e)
+		pr_err("  %2d: msr=0x%08x value=0x%016llx\n", i, e->index, e->value);
+}
+
 void dump_vmcs(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
@@ -5891,6 +5901,10 @@ void dump_vmcs(struct kvm_vcpu *vcpu)
 	if (secondary_exec_control & SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY)
 		pr_err("InterruptStatus = %04x\n",
 		       vmcs_read16(GUEST_INTR_STATUS));
+	if (vmcs_read32(VM_ENTRY_MSR_LOAD_COUNT) > 0)
+		vmx_dump_msrs("guest autoload", &vmx->msr_autoload.guest);
+	if (vmcs_read32(VM_EXIT_MSR_STORE_COUNT) > 0)
+		vmx_dump_msrs("guest autostore", &vmx->msr_autostore.guest);
 
 	pr_err("*** Host State ***\n");
 	pr_err("RIP = 0x%016lx  RSP = 0x%016lx\n",
@@ -5920,6 +5934,8 @@ void dump_vmcs(struct kvm_vcpu *vcpu)
 	    vmexit_ctl & VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL)
 		pr_err("PerfGlobCtl = 0x%016llx\n",
 		       vmcs_read64(HOST_IA32_PERF_GLOBAL_CTRL));
+	if (vmcs_read32(VM_EXIT_MSR_LOAD_COUNT) > 0)
+		vmx_dump_msrs("host autoload", &vmx->msr_autoload.host);
 
 	pr_err("*** Control State ***\n");
 	pr_err("PinBased=%08x CPUBased=%08x SecondaryExec=%08x\n",
-- 
2.30.0