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

Pull KVM updates from Paolo Bonzini:
 "x86:

   - Support for userspace to emulate Xen hypercalls

   - Raise the maximum number of user memslots

   - Scalability improvements for the new MMU.

     Instead of the complex "fast page fault" logic that is used in
     mmu.c, tdp_mmu.c uses an rwlock so that page faults are concurrent,
     but the code that can run against page faults is limited. Right now
     only page faults take the lock for reading; in the future this will
     be extended to some cases of page table destruction. I hope to
     switch the default MMU around 5.12-rc3 (some testing was delayed
     due to Chinese New Year).

   - Cleanups for MAXPHYADDR checks

   - Use static calls for vendor-specific callbacks

   - On AMD, use VMLOAD/VMSAVE to save and restore host state

   - Stop using deprecated jump label APIs

   - Workaround for AMD erratum that made nested virtualization
     unreliable

   - Support for LBR emulation in the guest

   - Support for communicating bus lock vmexits to userspace

   - Add support for SEV attestation command

   - Miscellaneous cleanups

  PPC:

   - Support for second data watchpoint on POWER10

   - Remove some complex workarounds for buggy early versions of POWER9

   - Guest entry/exit fixes

  ARM64:

   - Make the nVHE EL2 object relocatable

   - Cleanups for concurrent translation faults hitting the same page

   - Support for the standard TRNG hypervisor call

   - A bunch of small PMU/Debug fixes

   - Simplification of the early init hypercall handling

  Non-KVM changes (with acks):

   - Detection of contended rwlocks (implemented only for qrwlocks,
     because KVM only needs it for x86)

   - Allow __DISABLE_EXPORTS from assembly code

   - Provide a saner follow_pfn replacements for modules"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (192 commits)
  KVM: x86/xen: Explicitly pad struct compat_vcpu_info to 64 bytes
  KVM: selftests: Don't bother mapping GVA for Xen shinfo test
  KVM: selftests: Fix hex vs. decimal snafu in Xen test
  KVM: selftests: Fix size of memslots created by Xen tests
  KVM: selftests: Ignore recently added Xen tests' build output
  KVM: selftests: Add missing header file needed by xAPIC IPI tests
  KVM: selftests: Add operand to vmsave/vmload/vmrun in svm.c
  KVM: SVM: Make symbol 'svm_gp_erratum_intercept' static
  locking/arch: Move qrwlock.h include after qspinlock.h
  KVM: PPC: Book3S HV: Fix host radix SLB optimisation with hash guests
  KVM: PPC: Book3S HV: Ensure radix guest has no SLB entries
  KVM: PPC: Don't always report hash MMU capability for P9 < DD2.2
  KVM: PPC: Book3S HV: Save and restore FSCR in the P9 path
  KVM: PPC: remove unneeded semicolon
  KVM: PPC: Book3S HV: Use POWER9 SLBIA IH=6 variant to clear SLB
  KVM: PPC: Book3S HV: No need to clear radix host SLB before loading HPT guest
  KVM: PPC: Book3S HV: Fix radix guest SLB side channel
  KVM: PPC: Book3S HV: Remove support for running HPT guest on RPT host without mixed mode support
  KVM: PPC: Book3S HV: Introduce new capability for 2nd DAWR
  KVM: PPC: Book3S HV: Add infrastructure to support 2nd DAWR
  ...

9 files changed, 161 insertions, 13 deletions

diff --git a/include/asm-generic/export.h b/include/asm-generic/export.h
index 365345f9a9e3..07a36a874dca 100644
--- a/include/asm-generic/export.h
+++ b/include/asm-generic/export.h
@@ -33,7 +33,7 @@
  */
 
 .macro ___EXPORT_SYMBOL name,val,sec
-#ifdef CONFIG_MODULES
+#if defined(CONFIG_MODULES) && !defined(__DISABLE_EXPORTS)
 	.section ___ksymtab\sec+\name,"a"
 	.balign KSYM_ALIGN
 __ksymtab_\name:
diff --git a/include/asm-generic/qrwlock.h b/include/asm-generic/qrwlock.h
index 84ce841ce735..7ae0ece07b4e 100644
--- a/include/asm-generic/qrwlock.h
+++ b/include/asm-generic/qrwlock.h
@@ -15,6 +15,8 @@
 
 #include <asm-generic/qrwlock_types.h>
 
+/* Must be included from asm/spinlock.h after defining arch_spin_is_locked.  */
+
 /*
  * Writer states & reader shift and bias.
  */
@@ -116,15 +118,26 @@ static inline void queued_write_unlock(struct qrwlock *lock)
 	smp_store_release(&lock->wlocked, 0);
 }
 
+/**
+ * queued_rwlock_is_contended - check if the lock is contended
+ * @lock : Pointer to queue rwlock structure
+ * Return: 1 if lock contended, 0 otherwise
+ */
+static inline int queued_rwlock_is_contended(struct qrwlock *lock)
+{
+	return arch_spin_is_locked(&lock->wait_lock);
+}
+
 /*
  * Remapping rwlock architecture specific functions to the corresponding
  * queue rwlock functions.
  */
-#define arch_read_lock(l)	queued_read_lock(l)
-#define arch_write_lock(l)	queued_write_lock(l)
-#define arch_read_trylock(l)	queued_read_trylock(l)
-#define arch_write_trylock(l)	queued_write_trylock(l)
-#define arch_read_unlock(l)	queued_read_unlock(l)
-#define arch_write_unlock(l)	queued_write_unlock(l)
+#define arch_read_lock(l)		queued_read_lock(l)
+#define arch_write_lock(l)		queued_write_lock(l)
+#define arch_read_trylock(l)		queued_read_trylock(l)
+#define arch_write_trylock(l)		queued_write_trylock(l)
+#define arch_read_unlock(l)		queued_read_unlock(l)
+#define arch_write_unlock(l)		queued_write_unlock(l)
+#define arch_rwlock_is_contended(l)	queued_rwlock_is_contended(l)
 
 #endif /* __ASM_GENERIC_QRWLOCK_H */
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index f3b1013fb22c..e126ebda36d0 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -425,9 +425,8 @@ struct kvm_irq_routing_table {
 #define KVM_PRIVATE_MEM_SLOTS 0
 #endif
 
-#ifndef KVM_MEM_SLOTS_NUM
-#define KVM_MEM_SLOTS_NUM (KVM_USER_MEM_SLOTS + KVM_PRIVATE_MEM_SLOTS)
-#endif
+#define KVM_MEM_SLOTS_NUM SHRT_MAX
+#define KVM_USER_MEM_SLOTS (KVM_MEM_SLOTS_NUM - KVM_PRIVATE_MEM_SLOTS)
 
 #ifndef __KVM_VCPU_MULTIPLE_ADDRESS_SPACE
 static inline int kvm_arch_vcpu_memslots_id(struct kvm_vcpu *vcpu)
@@ -451,7 +450,12 @@ struct kvm_memslots {
 };
 
 struct kvm {
+#ifdef KVM_HAVE_MMU_RWLOCK
+	rwlock_t mmu_lock;
+#else
 	spinlock_t mmu_lock;
+#endif /* KVM_HAVE_MMU_RWLOCK */
+
 	struct mutex slots_lock;
 	struct mm_struct *mm; /* userspace tied to this vm */
 	struct kvm_memslots __rcu *memslots[KVM_ADDRESS_SPACE_NUM];
diff --git a/include/linux/mm.h b/include/linux/mm.h
index ab959488bc0f..1696ee6ab22d 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1663,9 +1663,11 @@ void free_pgd_range(struct mmu_gather *tlb, unsigned long addr,
 		unsigned long end, unsigned long floor, unsigned long ceiling);
 int
 copy_page_range(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma);
+int follow_invalidate_pte(struct mm_struct *mm, unsigned long address,
+			  struct mmu_notifier_range *range, pte_t **ptepp,
+			  pmd_t **pmdpp, spinlock_t **ptlp);
 int follow_pte(struct mm_struct *mm, unsigned long address,
-		struct mmu_notifier_range *range, pte_t **ptepp, pmd_t **pmdpp,
-		spinlock_t **ptlp);
+	       pte_t **ptepp, spinlock_t **ptlp);
 int follow_pfn(struct vm_area_struct *vma, unsigned long address,
 	unsigned long *pfn);
 int follow_phys(struct vm_area_struct *vma, unsigned long address,
diff --git a/include/linux/psp-sev.h b/include/linux/psp-sev.h
index 49d155cd2dfe..b801ead1e2bb 100644
--- a/include/linux/psp-sev.h
+++ b/include/linux/psp-sev.h
@@ -66,6 +66,7 @@ enum sev_cmd {
 	SEV_CMD_LAUNCH_MEASURE		= 0x033,
 	SEV_CMD_LAUNCH_UPDATE_SECRET	= 0x034,
 	SEV_CMD_LAUNCH_FINISH		= 0x035,
+	SEV_CMD_ATTESTATION_REPORT	= 0x036,
 
 	/* Guest migration commands (outgoing) */
 	SEV_CMD_SEND_START		= 0x040,
@@ -483,6 +484,22 @@ struct sev_data_dbg {
 	u32 len;				/* In */
 } __packed;
 
+/**
+ * struct sev_data_attestation_report - SEV_ATTESTATION_REPORT command parameters
+ *
+ * @handle: handle of the VM
+ * @mnonce: a random nonce that will be included in the report.
+ * @address: physical address where the report will be copied.
+ * @len: length of the physical buffer.
+ */
+struct sev_data_attestation_report {
+	u32 handle;				/* In */
+	u32 reserved;
+	u64 address;				/* In */
+	u8 mnonce[16];				/* In */
+	u32 len;				/* In/Out */
+} __packed;
+
 #ifdef CONFIG_CRYPTO_DEV_SP_PSP
 
 /**
diff --git a/include/linux/rwlock.h b/include/linux/rwlock.h
index 3dcd617e65ae..7ce9a51ae5c0 100644
--- a/include/linux/rwlock.h
+++ b/include/linux/rwlock.h
@@ -128,4 +128,11 @@ do {								\
 	1 : ({ local_irq_restore(flags); 0; }); \
 })
 
+#ifdef arch_rwlock_is_contended
+#define rwlock_is_contended(lock) \
+	 arch_rwlock_is_contended(&(lock)->raw_lock)
+#else
+#define rwlock_is_contended(lock)	((void)(lock), 0)
+#endif /* arch_rwlock_is_contended */
+
 #endif /* __LINUX_RWLOCK_H */
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 4d568288abf9..26f499810dfa 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1904,12 +1904,24 @@ static inline int _cond_resched(void) { return 0; }
 })
 
 extern int __cond_resched_lock(spinlock_t *lock);
+extern int __cond_resched_rwlock_read(rwlock_t *lock);
+extern int __cond_resched_rwlock_write(rwlock_t *lock);
 
 #define cond_resched_lock(lock) ({				\
 	___might_sleep(__FILE__, __LINE__, PREEMPT_LOCK_OFFSET);\
 	__cond_resched_lock(lock);				\
 })
 
+#define cond_resched_rwlock_read(lock) ({			\
+	__might_sleep(__FILE__, __LINE__, PREEMPT_LOCK_OFFSET);	\
+	__cond_resched_rwlock_read(lock);			\
+})
+
+#define cond_resched_rwlock_write(lock) ({			\
+	__might_sleep(__FILE__, __LINE__, PREEMPT_LOCK_OFFSET);	\
+	__cond_resched_rwlock_write(lock);			\
+})
+
 static inline void cond_resched_rcu(void)
 {
 #if defined(CONFIG_DEBUG_ATOMIC_SLEEP) || !defined(CONFIG_PREEMPT_RCU)
@@ -1933,6 +1945,23 @@ static inline int spin_needbreak(spinlock_t *lock)
 #endif
 }
 
+/*
+ * Check if a rwlock is contended.
+ * Returns non-zero if there is another task waiting on the rwlock.
+ * Returns zero if the lock is not contended or the system / underlying
+ * rwlock implementation does not support contention detection.
+ * Technically does not depend on CONFIG_PREEMPTION, but a general need
+ * for low latency.
+ */
+static inline int rwlock_needbreak(rwlock_t *lock)
+{
+#ifdef CONFIG_PREEMPTION
+	return rwlock_is_contended(lock);
+#else
+	return 0;
+#endif
+}
+
 static __always_inline bool need_resched(void)
 {
 	return unlikely(tif_need_resched());
diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
index 374c67875cdb..8b281f722e5b 100644
--- a/include/uapi/linux/kvm.h
+++ b/include/uapi/linux/kvm.h
@@ -216,6 +216,20 @@ struct kvm_hyperv_exit {
 	} u;
 };
 
+struct kvm_xen_exit {
+#define KVM_EXIT_XEN_HCALL          1
+	__u32 type;
+	union {
+		struct {
+			__u32 longmode;
+			__u32 cpl;
+			__u64 input;
+			__u64 result;
+			__u64 params[6];
+		} hcall;
+	} u;
+};
+
 #define KVM_S390_GET_SKEYS_NONE   1
 #define KVM_S390_SKEYS_MAX        1048576
 
@@ -252,6 +266,8 @@ struct kvm_hyperv_exit {
 #define KVM_EXIT_X86_WRMSR        30
 #define KVM_EXIT_DIRTY_RING_FULL  31
 #define KVM_EXIT_AP_RESET_HOLD    32
+#define KVM_EXIT_X86_BUS_LOCK     33
+#define KVM_EXIT_XEN              34
 
 /* For KVM_EXIT_INTERNAL_ERROR */
 /* Emulate instruction failed. */
@@ -428,6 +444,8 @@ struct kvm_run {
 			__u32 index; /* kernel -> user */
 			__u64 data; /* kernel <-> user */
 		} msr;
+		/* KVM_EXIT_XEN */
+		struct kvm_xen_exit xen;
 		/* Fix the size of the union. */
 		char padding[256];
 	};
@@ -1058,6 +1076,8 @@ struct kvm_ppc_resize_hpt {
 #define KVM_CAP_ENFORCE_PV_FEATURE_CPUID 190
 #define KVM_CAP_SYS_HYPERV_CPUID 191
 #define KVM_CAP_DIRTY_LOG_RING 192
+#define KVM_CAP_X86_BUS_LOCK_EXIT 193
+#define KVM_CAP_PPC_DAWR1 194
 
 #ifdef KVM_CAP_IRQ_ROUTING
 
@@ -1131,6 +1151,10 @@ struct kvm_x86_mce {
 #endif
 
 #ifdef KVM_CAP_XEN_HVM
+#define KVM_XEN_HVM_CONFIG_HYPERCALL_MSR	(1 << 0)
+#define KVM_XEN_HVM_CONFIG_INTERCEPT_HCALL	(1 << 1)
+#define KVM_XEN_HVM_CONFIG_SHARED_INFO		(1 << 2)
+
 struct kvm_xen_hvm_config {
 	__u32 flags;
 	__u32 msr;
@@ -1565,6 +1589,45 @@ struct kvm_pv_cmd {
 /* Available with KVM_CAP_DIRTY_LOG_RING */
 #define KVM_RESET_DIRTY_RINGS		_IO(KVMIO, 0xc7)
 
+/* Per-VM Xen attributes */
+#define KVM_XEN_HVM_GET_ATTR	_IOWR(KVMIO, 0xc8, struct kvm_xen_hvm_attr)
+#define KVM_XEN_HVM_SET_ATTR	_IOW(KVMIO,  0xc9, struct kvm_xen_hvm_attr)
+
+struct kvm_xen_hvm_attr {
+	__u16 type;
+	__u16 pad[3];
+	union {
+		__u8 long_mode;
+		__u8 vector;
+		struct {
+			__u64 gfn;
+		} shared_info;
+		__u64 pad[8];
+	} u;
+};
+
+/* Available with KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_SHARED_INFO */
+#define KVM_XEN_ATTR_TYPE_LONG_MODE		0x0
+#define KVM_XEN_ATTR_TYPE_SHARED_INFO		0x1
+#define KVM_XEN_ATTR_TYPE_UPCALL_VECTOR		0x2
+
+/* Per-vCPU Xen attributes */
+#define KVM_XEN_VCPU_GET_ATTR	_IOWR(KVMIO, 0xca, struct kvm_xen_vcpu_attr)
+#define KVM_XEN_VCPU_SET_ATTR	_IOW(KVMIO,  0xcb, struct kvm_xen_vcpu_attr)
+
+struct kvm_xen_vcpu_attr {
+	__u16 type;
+	__u16 pad[3];
+	union {
+		__u64 gpa;
+		__u64 pad[8];
+	} u;
+};
+
+/* Available with KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_SHARED_INFO */
+#define KVM_XEN_VCPU_ATTR_TYPE_VCPU_INFO	0x0
+#define KVM_XEN_VCPU_ATTR_TYPE_VCPU_TIME_INFO	0x1
+
 /* Secure Encrypted Virtualization command */
 enum sev_cmd_id {
 	/* Guest initialization commands */
@@ -1593,6 +1656,8 @@ enum sev_cmd_id {
 	KVM_SEV_DBG_ENCRYPT,
 	/* Guest certificates commands */
 	KVM_SEV_CERT_EXPORT,
+	/* Attestation report */
+	KVM_SEV_GET_ATTESTATION_REPORT,
 
 	KVM_SEV_NR_MAX,
 };
@@ -1645,6 +1710,12 @@ struct kvm_sev_dbg {
 	__u32 len;
 };
 
+struct kvm_sev_attestation_report {
+	__u8 mnonce[16];
+	__u64 uaddr;
+	__u32 len;
+};
+
 #define KVM_DEV_ASSIGN_ENABLE_IOMMU	(1 << 0)
 #define KVM_DEV_ASSIGN_PCI_2_3		(1 << 1)
 #define KVM_DEV_ASSIGN_MASK_INTX	(1 << 2)
@@ -1766,4 +1837,7 @@ struct kvm_dirty_gfn {
 	__u64 offset;
 };
 
+#define KVM_BUS_LOCK_DETECTION_OFF             (1 << 0)
+#define KVM_BUS_LOCK_DETECTION_EXIT            (1 << 1)
+
 #endif /* __LINUX_KVM_H */
diff --git a/include/xen/interface/xen.h b/include/xen/interface/xen.h
index 8bfb242f433e..5ee37a296481 100644
--- a/include/xen/interface/xen.h
+++ b/include/xen/interface/xen.h
@@ -598,7 +598,9 @@ struct shared_info {
 	 * their gettimeofday() syscall on this wallclock-base value.
 	 */
 	struct pvclock_wall_clock wc;
-
+#ifndef CONFIG_X86_32
+	uint32_t wc_sec_hi;
+#endif
 	struct arch_shared_info arch;
 
 };