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
  ...

5 files changed, 64 insertions, 5 deletions

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());