Merge tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm

Pull KVM updates from Paolo Bonzini:
 "ARM:

   - Support for userspace handling of synchronous external aborts
     (SEAs), allowing the VMM to potentially handle the abort in a
     non-fatal manner

   - Large rework of the VGIC's list register handling with the goal of
     supporting more active/pending IRQs than available list registers
     in hardware. In addition, the VGIC now supports EOImode==1 style
     deactivations for IRQs which may occur on a separate vCPU than the
     one that acked the IRQ

   - Support for FEAT_XNX (user / privileged execute permissions) and
     FEAT_HAF (hardware update to the Access Flag) in the software page
     table walkers and shadow MMU

   - Allow page table destruction to reschedule, fixing long
     need_resched latencies observed when destroying a large VM

   - Minor fixes to KVM and selftests

  Loongarch:

   - Get VM PMU capability from HW GCFG register

   - Add AVEC basic support

   - Use 64-bit register definition for EIOINTC

   - Add KVM timer test cases for tools/selftests

  RISC/V:

   - SBI message passing (MPXY) support for KVM guest

   - Give a new, more specific error subcode for the case when in-kernel
     AIA virtualization fails to allocate IMSIC VS-file

   - Support KVM_DIRTY_LOG_INITIALLY_SET, enabling dirty log gradually
     in small chunks

   - Fix guest page fault within HLV* instructions

   - Flush VS-stage TLB after VCPU migration for Andes cores

  s390:

   - Always allocate ESCA (Extended System Control Area), instead of
     starting with the basic SCA and converting to ESCA with the
     addition of the 65th vCPU. The price is increased number of exits
     (and worse performance) on z10 and earlier processor; ESCA was
     introduced by z114/z196 in 2010

   - VIRT_XFER_TO_GUEST_WORK support

   - Operation exception forwarding support

   - Cleanups

  x86:

   - Skip the costly "zap all SPTEs" on an MMIO generation wrap if MMIO
     SPTE caching is disabled, as there can't be any relevant SPTEs to
     zap

   - Relocate a misplaced export

   - Fix an async #PF bug where KVM would clear the completion queue
     when the guest transitioned in and out of paging mode, e.g. when
     handling an SMI and then returning to paged mode via RSM

   - Leave KVM's user-return notifier registered even when disabling
     virtualization, as long as kvm.ko is loaded. On reboot/shutdown,
     keeping the notifier registered is ok; the kernel does not use the
     MSRs and the callback will run cleanly and restore host MSRs if the
     CPU manages to return to userspace before the system goes down

   - Use the checked version of {get,put}_user()

   - Fix a long-lurking bug where KVM's lack of catch-up logic for
     periodic APIC timers can result in a hard lockup in the host

   - Revert the periodic kvmclock sync logic now that KVM doesn't use a
     clocksource that's subject to NTP corrections

   - Clean up KVM's handling of MMIO Stale Data and L1TF, and bury the
     latter behind CONFIG_CPU_MITIGATIONS

   - Context switch XCR0, XSS, and PKRU outside of the entry/exit fast
     path; the only reason they were handled in the fast path was to
     paper of a bug in the core #MC code, and that has long since been
     fixed

   - Add emulator support for AVX MOV instructions, to play nice with
     emulated devices whose guest drivers like to access PCI BARs with
     large multi-byte instructions

  x86 (AMD):

   - Fix a few missing "VMCB dirty" bugs

   - Fix the worst of KVM's lack of EFER.LMSLE emulation

   - Add AVIC support for addressing 4k vCPUs in x2AVIC mode

   - Fix incorrect handling of selective CR0 writes when checking
     intercepts during emulation of L2 instructions

   - Fix a currently-benign bug where KVM would clobber SPEC_CTRL[63:32]
     on VMRUN and #VMEXIT

   - Fix a bug where KVM corrupt the guest code stream when re-injecting
     a soft interrupt if the guest patched the underlying code after the
     VM-Exit, e.g. when Linux patches code with a temporary INT3

   - Add KVM_X86_SNP_POLICY_BITS to advertise supported SNP policy bits
     to userspace, and extend KVM "support" to all policy bits that
     don't require any actual support from KVM

  x86 (Intel):

   - Use the root role from kvm_mmu_page to construct EPTPs instead of
     the current vCPU state, partly as worthwhile cleanup, but mostly to
     pave the way for tracking per-root TLB flushes, and elide EPT
     flushes on pCPU migration if the root is clean from a previous
     flush

   - Add a few missing nested consistency checks

   - Rip out support for doing "early" consistency checks via hardware
     as the functionality hasn't been used in years and is no longer
     useful in general; replace it with an off-by-default module param
     to WARN if hardware fails a check that KVM does not perform

   - Fix a currently-benign bug where KVM would drop the guest's
     SPEC_CTRL[63:32] on VM-Enter

   - Misc cleanups

   - Overhaul the TDX code to address systemic races where KVM (acting
     on behalf of userspace) could inadvertantly trigger lock contention
     in the TDX-Module; KVM was either working around these in weird,
     ugly ways, or was simply oblivious to them (though even Yan's
     devilish selftests could only break individual VMs, not the host
     kernel)

   - Fix a bug where KVM could corrupt a vCPU's cpu_list when freeing a
     TDX vCPU, if creating said vCPU failed partway through

   - Fix a few sparse warnings (bad annotation, 0 != NULL)

   - Use struct_size() to simplify copying TDX capabilities to userspace

   - Fix a bug where TDX would effectively corrupt user-return MSR
     values if the TDX Module rejects VP.ENTER and thus doesn't clobber
     host MSRs as expected

  Selftests:

   - Fix a math goof in mmu_stress_test when running on a single-CPU
     system/VM

   - Forcefully override ARCH from x86_64 to x86 to play nice with
     specifying ARCH=x86_64 on the command line

   - Extend a bunch of nested VMX to validate nested SVM as well

   - Add support for LA57 in the core VM_MODE_xxx macro, and add a test
     to verify KVM can save/restore nested VMX state when L1 is using
     5-level paging, but L2 is not

   - Clean up the guest paging code in anticipation of sharing the core
     logic for nested EPT and nested NPT

  guest_memfd:

   - Add NUMA mempolicy support for guest_memfd, and clean up a variety
     of rough edges in guest_memfd along the way

   - Define a CLASS to automatically handle get+put when grabbing a
     guest_memfd from a memslot to make it harder to leak references

   - Enhance KVM selftests to make it easer to develop and debug
     selftests like those added for guest_memfd NUMA support, e.g. where
     test and/or KVM bugs often result in hard-to-debug SIGBUS errors

   - Misc cleanups

  Generic:

   - Use the recently-added WQ_PERCPU when creating the per-CPU
     workqueue for irqfd cleanup

   - Fix a goof in the dirty ring documentation

   - Fix choice of target for directed yield across different calls to
     kvm_vcpu_on_spin(); the function was always starting from the first
     vCPU instead of continuing the round-robin search"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (260 commits)
  KVM: arm64: at: Update AF on software walk only if VM has FEAT_HAFDBS
  KVM: arm64: at: Use correct HA bit in TCR_EL2 when regime is EL2
  KVM: arm64: Document KVM_PGTABLE_PROT_{UX,PX}
  KVM: arm64: Fix spelling mistake "Unexpeced" -> "Unexpected"
  KVM: arm64: Add break to default case in kvm_pgtable_stage2_pte_prot()
  KVM: arm64: Add endian casting to kvm_swap_s[12]_desc()
  KVM: arm64: Fix compilation when CONFIG_ARM64_USE_LSE_ATOMICS=n
  KVM: arm64: selftests: Add test for AT emulation
  KVM: arm64: nv: Expose hardware access flag management to NV guests
  KVM: arm64: nv: Implement HW access flag management in stage-2 SW PTW
  KVM: arm64: Implement HW access flag management in stage-1 SW PTW
  KVM: arm64: Propagate PTW errors up to AT emulation
  KVM: arm64: Add helper for swapping guest descriptor
  KVM: arm64: nv: Use pgtable definitions in stage-2 walk
  KVM: arm64: Handle endianness in read helper for emulated PTW
  KVM: arm64: nv: Stop passing vCPU through void ptr in S2 PTW
  KVM: arm64: Call helper for reading descriptors directly
  KVM: arm64: nv: Advertise support for FEAT_XNX
  KVM: arm64: Teach ptdump about FEAT_XNX permissions
  KVM: s390: Use generic VIRT_XFER_TO_GUEST_WORK functions
  ...

8 files changed, 91 insertions, 27 deletions

diff --git a/include/kvm/arm_vgic.h b/include/kvm/arm_vgic.h
index 7a0b972eb1b1..b261fb3968d0 100644
--- a/include/kvm/arm_vgic.h
+++ b/include/kvm/arm_vgic.h
@@ -59,6 +59,9 @@ struct vgic_global {
 	/* virtual control interface mapping, HYP VA */
 	void __iomem		*vctrl_hyp;
 
+	/* Physical CPU interface, kernel VA */
+	void __iomem		*gicc_base;
+
 	/* Number of implemented list registers */
 	int			nr_lr;
 
@@ -120,6 +123,7 @@ struct irq_ops {
 
 struct vgic_irq {
 	raw_spinlock_t irq_lock;	/* Protects the content of the struct */
+	u32 intid;			/* Guest visible INTID */
 	struct rcu_head rcu;
 	struct list_head ap_list;
 
@@ -134,17 +138,18 @@ struct vgic_irq {
 					 * affinity reg (v3).
 					 */
 
-	u32 intid;			/* Guest visible INTID */
-	bool line_level;		/* Level only */
-	bool pending_latch;		/* The pending latch state used to calculate
-					 * the pending state for both level
-					 * and edge triggered IRQs. */
-	bool active;
-	bool pending_release;		/* Used for LPIs only, unreferenced IRQ
+	bool pending_release:1;		/* Used for LPIs only, unreferenced IRQ
 					 * pending a release */
 
-	bool enabled;
-	bool hw;			/* Tied to HW IRQ */
+	bool pending_latch:1;		/* The pending latch state used to calculate
+					 * the pending state for both level
+					 * and edge triggered IRQs. */
+	enum vgic_irq_config config:1;	/* Level or edge */
+	bool line_level:1;		/* Level only */
+	bool enabled:1;
+	bool active:1;
+	bool hw:1;			/* Tied to HW IRQ */
+	bool on_lr:1;			/* Present in a CPU LR */
 	refcount_t refcount;		/* Used for LPIs */
 	u32 hwintid;			/* HW INTID number */
 	unsigned int host_irq;		/* linux irq corresponding to hwintid */
@@ -156,7 +161,6 @@ struct vgic_irq {
 	u8 active_source;		/* GICv2 SGIs only */
 	u8 priority;
 	u8 group;			/* 0 == group 0, 1 == group 1 */
-	enum vgic_irq_config config;	/* Level or edge */
 
 	struct irq_ops *ops;
 
@@ -259,6 +263,9 @@ struct vgic_dist {
 	/* The GIC maintenance IRQ for nested hypervisors. */
 	u32			mi_intid;
 
+	/* Track the number of in-flight active SPIs */
+	atomic_t		active_spis;
+
 	/* base addresses in guest physical address space: */
 	gpa_t			vgic_dist_base;		/* distributor */
 	union {
@@ -280,6 +287,7 @@ struct vgic_dist {
 	struct vgic_irq		*spis;
 
 	struct vgic_io_device	dist_iodev;
+	struct vgic_io_device	cpuif_iodev;
 
 	bool			has_its;
 	bool			table_write_in_progress;
@@ -417,6 +425,7 @@ bool kvm_vcpu_has_pending_irqs(struct kvm_vcpu *vcpu);
 void kvm_vgic_sync_hwstate(struct kvm_vcpu *vcpu);
 void kvm_vgic_flush_hwstate(struct kvm_vcpu *vcpu);
 void kvm_vgic_reset_mapped_irq(struct kvm_vcpu *vcpu, u32 vintid);
+void kvm_vgic_process_async_update(struct kvm_vcpu *vcpu);
 
 void vgic_v3_dispatch_sgi(struct kvm_vcpu *vcpu, u64 reg, bool allow_group1);
 
diff --git a/include/linux/irqchip/arm-gic.h b/include/linux/irqchip/arm-gic.h
index 2223f95079ce..d45fa19f9e47 100644
--- a/include/linux/irqchip/arm-gic.h
+++ b/include/linux/irqchip/arm-gic.h
@@ -86,7 +86,13 @@
 
 #define GICH_HCR_EN			(1 << 0)
 #define GICH_HCR_UIE			(1 << 1)
+#define GICH_HCR_LRENPIE		(1 << 2)
 #define GICH_HCR_NPIE			(1 << 3)
+#define GICH_HCR_VGrp0EIE		(1 << 4)
+#define GICH_HCR_VGrp0DIE		(1 << 5)
+#define GICH_HCR_VGrp1EIE		(1 << 6)
+#define GICH_HCR_VGrp1DIE		(1 << 7)
+#define GICH_HCR_EOICOUNT		GENMASK(31, 27)
 
 #define GICH_LR_VIRTUALID		(0x3ff << 0)
 #define GICH_LR_PHYSID_CPUID_SHIFT	(10)
diff --git a/include/linux/irqchip/arm-vgic-info.h b/include/linux/irqchip/arm-vgic-info.h
index a470a73a805a..67d9d960273b 100644
--- a/include/linux/irqchip/arm-vgic-info.h
+++ b/include/linux/irqchip/arm-vgic-info.h
@@ -24,6 +24,8 @@ struct gic_kvm_info {
 	enum gic_type	type;
 	/* Virtual CPU interface */
 	struct resource vcpu;
+	/* GICv2 GICC VA */
+	void __iomem	*gicc_base;
 	/* Interrupt number */
 	unsigned int	maint_irq;
 	/* No interrupt mask, no need to use the above field */
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 5bd76cf394fa..d93f75b05ae2 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -1557,6 +1557,8 @@ long kvm_arch_dev_ioctl(struct file *filp,
 			unsigned int ioctl, unsigned long arg);
 long kvm_arch_vcpu_ioctl(struct file *filp,
 			 unsigned int ioctl, unsigned long arg);
+long kvm_arch_vcpu_unlocked_ioctl(struct file *filp,
+				  unsigned int ioctl, unsigned long arg);
 vm_fault_t kvm_arch_vcpu_fault(struct kvm_vcpu *vcpu, struct vm_fault *vmf);
 
 int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext);
@@ -2437,18 +2439,6 @@ static inline bool kvm_arch_no_poll(struct kvm_vcpu *vcpu)
 }
 #endif /* CONFIG_HAVE_KVM_NO_POLL */
 
-#ifdef CONFIG_HAVE_KVM_VCPU_ASYNC_IOCTL
-long kvm_arch_vcpu_async_ioctl(struct file *filp,
-			       unsigned int ioctl, unsigned long arg);
-#else
-static inline long kvm_arch_vcpu_async_ioctl(struct file *filp,
-					     unsigned int ioctl,
-					     unsigned long arg)
-{
-	return -ENOIOCTLCMD;
-}
-#endif /* CONFIG_HAVE_KVM_VCPU_ASYNC_IOCTL */
-
 void kvm_arch_guest_memory_reclaimed(struct kvm *kvm);
 
 #ifdef CONFIG_HAVE_KVM_VCPU_RUN_PID_CHANGE
diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index e601a3144f28..31a848485ad9 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -651,9 +651,11 @@ static inline void *detach_page_private(struct page *page)
 }
 
 #ifdef CONFIG_NUMA
-struct folio *filemap_alloc_folio_noprof(gfp_t gfp, unsigned int order);
+struct folio *filemap_alloc_folio_noprof(gfp_t gfp, unsigned int order,
+		struct mempolicy *policy);
 #else
-static inline struct folio *filemap_alloc_folio_noprof(gfp_t gfp, unsigned int order)
+static inline struct folio *filemap_alloc_folio_noprof(gfp_t gfp, unsigned int order,
+		struct mempolicy *policy)
 {
 	return folio_alloc_noprof(gfp, order);
 }
@@ -664,7 +666,7 @@ static inline struct folio *filemap_alloc_folio_noprof(gfp_t gfp, unsigned int o
 
 static inline struct page *__page_cache_alloc(gfp_t gfp)
 {
-	return &filemap_alloc_folio(gfp, 0)->page;
+	return &filemap_alloc_folio(gfp, 0, NULL)->page;
 }
 
 static inline gfp_t readahead_gfp_mask(struct address_space *x)
@@ -750,11 +752,17 @@ static inline fgf_t fgf_set_order(size_t size)
 }
 
 void *filemap_get_entry(struct address_space *mapping, pgoff_t index);
-struct folio *__filemap_get_folio(struct address_space *mapping, pgoff_t index,
-		fgf_t fgp_flags, gfp_t gfp);
+struct folio *__filemap_get_folio_mpol(struct address_space *mapping,
+		pgoff_t index, fgf_t fgf_flags, gfp_t gfp, struct mempolicy *policy);
 struct page *pagecache_get_page(struct address_space *mapping, pgoff_t index,
 		fgf_t fgp_flags, gfp_t gfp);
 
+static inline struct folio *__filemap_get_folio(struct address_space *mapping,
+		pgoff_t index, fgf_t fgf_flags, gfp_t gfp)
+{
+	return __filemap_get_folio_mpol(mapping, index, fgf_flags, gfp, NULL);
+}
+
 /**
  * write_begin_get_folio - Get folio for write_begin with flags.
  * @iocb: The kiocb passed from write_begin (may be NULL).
diff --git a/include/linux/psp-sev.h b/include/linux/psp-sev.h
index e0dbcb4b4fd9..abcdee256c65 100644
--- a/include/linux/psp-sev.h
+++ b/include/linux/psp-sev.h
@@ -14,6 +14,39 @@
 
 #include <uapi/linux/psp-sev.h>
 
+/* As defined by SEV API, under "Guest Policy". */
+#define SEV_POLICY_MASK_NODBG			BIT(0)
+#define SEV_POLICY_MASK_NOKS			BIT(1)
+#define SEV_POLICY_MASK_ES			BIT(2)
+#define SEV_POLICY_MASK_NOSEND			BIT(3)
+#define SEV_POLICY_MASK_DOMAIN			BIT(4)
+#define SEV_POLICY_MASK_SEV			BIT(5)
+#define SEV_POLICY_MASK_API_MAJOR		GENMASK(23, 16)
+#define SEV_POLICY_MASK_API_MINOR		GENMASK(31, 24)
+
+/* As defined by SEV-SNP Firmware ABI, under "Guest Policy". */
+#define SNP_POLICY_MASK_API_MINOR		GENMASK_ULL(7, 0)
+#define SNP_POLICY_MASK_API_MAJOR		GENMASK_ULL(15, 8)
+#define SNP_POLICY_MASK_SMT			BIT_ULL(16)
+#define SNP_POLICY_MASK_RSVD_MBO		BIT_ULL(17)
+#define SNP_POLICY_MASK_MIGRATE_MA		BIT_ULL(18)
+#define SNP_POLICY_MASK_DEBUG			BIT_ULL(19)
+#define SNP_POLICY_MASK_SINGLE_SOCKET		BIT_ULL(20)
+#define SNP_POLICY_MASK_CXL_ALLOW		BIT_ULL(21)
+#define SNP_POLICY_MASK_MEM_AES_256_XTS		BIT_ULL(22)
+#define SNP_POLICY_MASK_RAPL_DIS		BIT_ULL(23)
+#define SNP_POLICY_MASK_CIPHERTEXT_HIDING_DRAM	BIT_ULL(24)
+#define SNP_POLICY_MASK_PAGE_SWAP_DISABLE	BIT_ULL(25)
+
+/* Base SEV-SNP policy bitmask for minimum supported SEV firmware version */
+#define SNP_POLICY_MASK_BASE	(SNP_POLICY_MASK_API_MINOR		| \
+				 SNP_POLICY_MASK_API_MAJOR		| \
+				 SNP_POLICY_MASK_SMT			| \
+				 SNP_POLICY_MASK_RSVD_MBO		| \
+				 SNP_POLICY_MASK_MIGRATE_MA		| \
+				 SNP_POLICY_MASK_DEBUG			| \
+				 SNP_POLICY_MASK_SINGLE_SOCKET)
+
 #define SEV_FW_BLOB_MAX_SIZE	0x4000	/* 16KB */
 
 /**
@@ -849,7 +882,10 @@ struct snp_feature_info {
 	u32 edx;
 } __packed;
 
+#define SNP_RAPL_DISABLE_SUPPORTED		BIT(2)
 #define SNP_CIPHER_TEXT_HIDING_SUPPORTED	BIT(3)
+#define SNP_AES_256_XTS_POLICY_SUPPORTED	BIT(4)
+#define SNP_CXL_ALLOW_POLICY_SUPPORTED		BIT(5)
 
 #ifdef CONFIG_CRYPTO_DEV_SP_PSP
 
@@ -995,6 +1031,7 @@ void *snp_alloc_firmware_page(gfp_t mask);
 void snp_free_firmware_page(void *addr);
 void sev_platform_shutdown(void);
 bool sev_is_snp_ciphertext_hiding_supported(void);
+u64 sev_get_snp_policy_bits(void);
 
 #else	/* !CONFIG_CRYPTO_DEV_SP_PSP */
 
diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
index 52f6000ab020..dddb781b0507 100644
--- a/include/uapi/linux/kvm.h
+++ b/include/uapi/linux/kvm.h
@@ -179,6 +179,7 @@ struct kvm_xen_exit {
 #define KVM_EXIT_LOONGARCH_IOCSR  38
 #define KVM_EXIT_MEMORY_FAULT     39
 #define KVM_EXIT_TDX              40
+#define KVM_EXIT_ARM_SEA          41
 
 /* For KVM_EXIT_INTERNAL_ERROR */
 /* Emulate instruction failed. */
@@ -473,6 +474,14 @@ struct kvm_run {
 				} setup_event_notify;
 			};
 		} tdx;
+		/* KVM_EXIT_ARM_SEA */
+		struct {
+#define KVM_EXIT_ARM_SEA_FLAG_GPA_VALID	(1ULL << 0)
+			__u64 flags;
+			__u64 esr;
+			__u64 gva;
+			__u64 gpa;
+		} arm_sea;
 		/* Fix the size of the union. */
 		char padding[256];
 	};
@@ -963,6 +972,8 @@ struct kvm_enable_cap {
 #define KVM_CAP_RISCV_MP_STATE_RESET 242
 #define KVM_CAP_ARM_CACHEABLE_PFNMAP_SUPPORTED 243
 #define KVM_CAP_GUEST_MEMFD_FLAGS 244
+#define KVM_CAP_ARM_SEA_TO_USER 245
+#define KVM_CAP_S390_USER_OPEREXEC 246
 
 struct kvm_irq_routing_irqchip {
 	__u32 irqchip;
diff --git a/include/uapi/linux/magic.h b/include/uapi/linux/magic.h
index bb575f3ab45e..638ca21b7a90 100644
--- a/include/uapi/linux/magic.h
+++ b/include/uapi/linux/magic.h
@@ -103,5 +103,6 @@
 #define DEVMEM_MAGIC		0x454d444d	/* "DMEM" */
 #define SECRETMEM_MAGIC		0x5345434d	/* "SECM" */
 #define PID_FS_MAGIC		0x50494446	/* "PIDF" */
+#define GUEST_MEMFD_MAGIC	0x474d454d	/* "GMEM" */
 
 #endif /* __LINUX_MAGIC_H__ */