Google Git
Sign in
kernel/pub/scm/linux/kernel/git/cxl/cxl/d45111e52b81e0da6307bde9de8f2a5ac72d9ca9^1..d45111e52b81e0da6307bde9de8f2a5ac72d9ca9/.
commit
d45111e52b81e0da6307bde9de8f2a5ac72d9ca9
[log]
author
Linus Torvalds <torvalds@linux-foundation.org>
Fri Sep 06 12:45:43 2024 -0700
committer
Linus Torvalds <torvalds@linux-foundation.org>
Fri Sep 06 12:45:43 2024 -0700
tree
437f28bd98a607d793e29bf14cab46b824fd50a5
parent
788220eee30d67a485a13c34c02f51a82485f337 [diff]
parent
59cbd4eea48fdbc68fc17a29ad71188fea74b28b [diff]
Merge tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm

Pull x86 kvm fixes from Paolo Bonzini:
 "Many small fixes that accumulated while I was on vacation...

   - Fixup missed comments from the REMOVED_SPTE => FROZEN_SPTE rename

   - Ensure a root is successfully loaded when pre-faulting SPTEs

   - Grab kvm->srcu when handling KVM_SET_VCPU_EVENTS to guard against
     accessing memslots if toggling SMM happens to force a VM-Exit

   - Emulate MSR_{FS,GS}_BASE on SVM even though interception is always
     disabled, so that KVM does the right thing if KVM's emulator
     encounters {RD,WR}MSR

   - Explicitly clear BUS_LOCK_DETECT from KVM's caps on AMD, as KVM
     doesn't yet virtualize BUS_LOCK_DETECT on AMD

   - Cleanup the help message for CONFIG_KVM_AMD_SEV, and call out that
     KVM now supports SEV-SNP too

   - Specialize return value of
     KVM_CHECK_EXTENSION(KVM_CAP_READONLY_MEM), based on VM type

   - Remove unnecessary dependency on CONFIG_HIGH_RES_TIMERS

   - Note an RCU quiescent state on guest exit. This avoids a call to
     rcu_core() if there was a grace period request while guest was
     running"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm:
  KVM: Remove HIGH_RES_TIMERS dependency
  kvm: Note an RCU quiescent state on guest exit
  KVM: x86: Only advertise KVM_CAP_READONLY_MEM when supported by VM
  KVM: SEV: Update KVM_AMD_SEV Kconfig entry and mention SEV-SNP
  KVM: SVM: Don't advertise Bus Lock Detect to guest if SVM support is missing
  KVM: SVM: fix emulation of msr reads/writes of MSR_FS_BASE and MSR_GS_BASE
  KVM: x86: Acquire kvm->srcu when handling KVM_SET_VCPU_EVENTS
  KVM: x86/mmu: Check that root is valid/loaded when pre-faulting SPTEs
  KVM: x86/mmu: Fixup comments missed by the REMOVED_SPTE=>FROZEN_SPTE rename

diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig
index 472a153..730c2f3 100644
--- a/arch/x86/kvm/Kconfig
+++ b/arch/x86/kvm/Kconfig

@@ -19,7 +19,6 @@
 
 config KVM
 	tristate "Kernel-based Virtual Machine (KVM) support"
-	depends on HIGH_RES_TIMERS
 	depends on X86_LOCAL_APIC
 	select KVM_COMMON
 	select KVM_GENERIC_MMU_NOTIFIER
@@ -144,8 +143,10 @@
 	select HAVE_KVM_ARCH_GMEM_PREPARE
 	select HAVE_KVM_ARCH_GMEM_INVALIDATE
 	help
-	  Provides support for launching Encrypted VMs (SEV) and Encrypted VMs
-	  with Encrypted State (SEV-ES) on AMD processors.
+	  Provides support for launching encrypted VMs which use Secure
+	  Encrypted Virtualization (SEV), Secure Encrypted Virtualization with
+	  Encrypted State (SEV-ES), and Secure Encrypted Virtualization with
+	  Secure Nested Paging (SEV-SNP) technologies on AMD processors.
 
 config KVM_SMM
 	bool "System Management Mode emulation"

diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index 928cf84..de05a26 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c

@@ -4750,7 +4750,9 @@ long kvm_arch_vcpu_pre_fault_memory(struct kvm_vcpu *vcpu,
 	 * reload is efficient when called repeatedly, so we can do it on
 	 * every iteration.
 	 */
-	kvm_mmu_reload(vcpu);
+	r = kvm_mmu_reload(vcpu);
+	if (r)
+		return r;
 
 	if (kvm_arch_has_private_mem(vcpu->kvm) &&
 	    kvm_mem_is_private(vcpu->kvm, gpa_to_gfn(range->gpa)))

diff --git a/arch/x86/kvm/mmu/spte.c b/arch/x86/kvm/mmu/spte.c
index d452796..8f7eb3a 100644
--- a/arch/x86/kvm/mmu/spte.c
+++ b/arch/x86/kvm/mmu/spte.c

@@ -391,9 +391,9 @@ void kvm_mmu_set_mmio_spte_mask(u64 mmio_value, u64 mmio_mask, u64 access_mask)
 		mmio_value = 0;
 
 	/*
-	 * The masked MMIO value must obviously match itself and a removed SPTE
-	 * must not get a false positive.  Removed SPTEs and MMIO SPTEs should
-	 * never collide as MMIO must set some RWX bits, and removed SPTEs must
+	 * The masked MMIO value must obviously match itself and a frozen SPTE
+	 * must not get a false positive.  Frozen SPTEs and MMIO SPTEs should
+	 * never collide as MMIO must set some RWX bits, and frozen SPTEs must
 	 * not set any RWX bits.
 	 */
 	if (WARN_ON((mmio_value & mmio_mask) != mmio_value) ||

diff --git a/arch/x86/kvm/mmu/spte.h b/arch/x86/kvm/mmu/spte.h
index ef793c4..2cb816e 100644
--- a/arch/x86/kvm/mmu/spte.h
+++ b/arch/x86/kvm/mmu/spte.h

@@ -214,7 +214,7 @@ extern u64 __read_mostly shadow_nonpresent_or_rsvd_mask;
  */
 #define FROZEN_SPTE	(SHADOW_NONPRESENT_VALUE | 0x5a0ULL)
 
-/* Removed SPTEs must not be misconstrued as shadow present PTEs. */
+/* Frozen SPTEs must not be misconstrued as shadow present PTEs. */
 static_assert(!(FROZEN_SPTE & SPTE_MMU_PRESENT_MASK));
 
 static inline bool is_frozen_spte(u64 spte)

diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c
index c7dc49e..3c55955 100644
--- a/arch/x86/kvm/mmu/tdp_mmu.c
+++ b/arch/x86/kvm/mmu/tdp_mmu.c

@@ -359,10 +359,10 @@ static void handle_removed_pt(struct kvm *kvm, tdp_ptep_t pt, bool shared)
 			/*
 			 * Set the SPTE to a nonpresent value that other
 			 * threads will not overwrite. If the SPTE was
-			 * already marked as removed then another thread
+			 * already marked as frozen then another thread
 			 * handling a page fault could overwrite it, so
 			 * set the SPTE until it is set from some other
-			 * value to the removed SPTE value.
+			 * value to the frozen SPTE value.
 			 */
 			for (;;) {
 				old_spte = kvm_tdp_mmu_write_spte_atomic(sptep, FROZEN_SPTE);
@@ -536,8 +536,8 @@ static inline int __must_check __tdp_mmu_set_spte_atomic(struct tdp_iter *iter,
 	u64 *sptep = rcu_dereference(iter->sptep);
 
 	/*
-	 * The caller is responsible for ensuring the old SPTE is not a REMOVED
-	 * SPTE.  KVM should never attempt to zap or manipulate a REMOVED SPTE,
+	 * The caller is responsible for ensuring the old SPTE is not a FROZEN
+	 * SPTE.  KVM should never attempt to zap or manipulate a FROZEN SPTE,
 	 * and pre-checking before inserting a new SPTE is advantageous as it
 	 * avoids unnecessary work.
 	 */

diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index d6f2525..5ab2c92 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c

@@ -2876,6 +2876,12 @@ static int svm_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 	case MSR_CSTAR:
 		msr_info->data = svm->vmcb01.ptr->save.cstar;
 		break;
+	case MSR_GS_BASE:
+		msr_info->data = svm->vmcb01.ptr->save.gs.base;
+		break;
+	case MSR_FS_BASE:
+		msr_info->data = svm->vmcb01.ptr->save.fs.base;
+		break;
 	case MSR_KERNEL_GS_BASE:
 		msr_info->data = svm->vmcb01.ptr->save.kernel_gs_base;
 		break;
@@ -3101,6 +3107,12 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr)
 	case MSR_CSTAR:
 		svm->vmcb01.ptr->save.cstar = data;
 		break;
+	case MSR_GS_BASE:
+		svm->vmcb01.ptr->save.gs.base = data;
+		break;
+	case MSR_FS_BASE:
+		svm->vmcb01.ptr->save.fs.base = data;
+		break;
 	case MSR_KERNEL_GS_BASE:
 		svm->vmcb01.ptr->save.kernel_gs_base = data;
 		break;
@@ -5224,6 +5236,9 @@ static __init void svm_set_cpu_caps(void)
 
 	/* CPUID 0x8000001F (SME/SEV features) */
 	sev_set_cpu_caps();
+
+	/* Don't advertise Bus Lock Detect to guest if SVM support is absent */
+	kvm_cpu_cap_clear(X86_FEATURE_BUS_LOCK_DETECT);
 }
 
 static __init int svm_hardware_setup(void)

diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 70219e4..0f80180 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c

@@ -4656,7 +4656,6 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 	case KVM_CAP_ASYNC_PF_INT:
 	case KVM_CAP_GET_TSC_KHZ:
 	case KVM_CAP_KVMCLOCK_CTRL:
-	case KVM_CAP_READONLY_MEM:
 	case KVM_CAP_IOAPIC_POLARITY_IGNORED:
 	case KVM_CAP_TSC_DEADLINE_TIMER:
 	case KVM_CAP_DISABLE_QUIRKS:
@@ -4815,6 +4814,8 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 	case KVM_CAP_VM_TYPES:
 		r = kvm_caps.supported_vm_types;
 		break;
+	case KVM_CAP_READONLY_MEM:
+		r = kvm ? kvm_arch_has_readonly_mem(kvm) : 1;
 	default:
 		break;
 	}
@@ -6040,7 +6041,9 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
 		if (copy_from_user(&events, argp, sizeof(struct kvm_vcpu_events)))
 			break;
 
+		kvm_vcpu_srcu_read_lock(vcpu);
 		r = kvm_vcpu_ioctl_x86_set_vcpu_events(vcpu, &events);
+		kvm_vcpu_srcu_read_unlock(vcpu);
 		break;
 	}
 	case KVM_GET_DEBUGREGS: {

diff --git a/include/linux/context_tracking.h b/include/linux/context_tracking.h
index 6e76b9d..8a78fabe 100644
--- a/include/linux/context_tracking.h
+++ b/include/linux/context_tracking.h

@@ -80,10 +80,12 @@ static __always_inline bool context_tracking_guest_enter(void)
 	return context_tracking_enabled_this_cpu();
 }
 
-static __always_inline void context_tracking_guest_exit(void)
+static __always_inline bool context_tracking_guest_exit(void)
 {
 	if (context_tracking_enabled())
 		__ct_user_exit(CONTEXT_GUEST);
+
+	return context_tracking_enabled_this_cpu();
 }
 
 #define CT_WARN_ON(cond) WARN_ON(context_tracking_enabled() && (cond))
@@ -98,7 +100,7 @@ static inline void exception_exit(enum ctx_state prev_ctx) { }
 static inline int ct_state(void) { return -1; }
 static inline int __ct_state(void) { return -1; }
 static __always_inline bool context_tracking_guest_enter(void) { return false; }
-static __always_inline void context_tracking_guest_exit(void) { }
+static __always_inline bool context_tracking_guest_exit(void) { return false; }
 #define CT_WARN_ON(cond) do { } while (0)
 #endif /* !CONFIG_CONTEXT_TRACKING_USER */
 

diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index b23c6d4..0d5125a 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h

@@ -485,7 +485,15 @@ static __always_inline void guest_state_enter_irqoff(void)
  */
 static __always_inline void guest_context_exit_irqoff(void)
 {
-	context_tracking_guest_exit();
+	/*
+	 * Guest mode is treated as a quiescent state, see
+	 * guest_context_enter_irqoff() for more details.
+	 */
+	if (!context_tracking_guest_exit()) {
+		instrumentation_begin();
+		rcu_virt_note_context_switch();
+		instrumentation_end();
+	}
 }
 
 /*