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

Pull kvm updates from Paolo Bonzini:
 "ARM64:

   - Enable the per-vcpu dirty-ring tracking mechanism, together with an
     option to keep the good old dirty log around for pages that are
     dirtied by something other than a vcpu.

   - Switch to the relaxed parallel fault handling, using RCU to delay
     page table reclaim and giving better performance under load.

   - Relax the MTE ABI, allowing a VMM to use the MAP_SHARED mapping
     option, which multi-process VMMs such as crosvm rely on (see merge
     commit 382b5b87a97d: "Fix a number of issues with MTE, such as
     races on the tags being initialised vs the PG_mte_tagged flag as
     well as the lack of support for VM_SHARED when KVM is involved.
     Patches from Catalin Marinas and Peter Collingbourne").

   - Merge the pKVM shadow vcpu state tracking that allows the
     hypervisor to have its own view of a vcpu, keeping that state
     private.

   - Add support for the PMUv3p5 architecture revision, bringing support
     for 64bit counters on systems that support it, and fix the
     no-quite-compliant CHAIN-ed counter support for the machines that
     actually exist out there.

   - Fix a handful of minor issues around 52bit VA/PA support (64kB
     pages only) as a prefix of the oncoming support for 4kB and 16kB
     pages.

   - Pick a small set of documentation and spelling fixes, because no
     good merge window would be complete without those.

  s390:

   - Second batch of the lazy destroy patches

   - First batch of KVM changes for kernel virtual != physical address
     support

   - Removal of a unused function

  x86:

   - Allow compiling out SMM support

   - Cleanup and documentation of SMM state save area format

   - Preserve interrupt shadow in SMM state save area

   - Respond to generic signals during slow page faults

   - Fixes and optimizations for the non-executable huge page errata
     fix.

   - Reprogram all performance counters on PMU filter change

   - Cleanups to Hyper-V emulation and tests

   - Process Hyper-V TLB flushes from a nested guest (i.e. from a L2
     guest running on top of a L1 Hyper-V hypervisor)

   - Advertise several new Intel features

   - x86 Xen-for-KVM:

      - Allow the Xen runstate information to cross a page boundary

      - Allow XEN_RUNSTATE_UPDATE flag behaviour to be configured

      - Add support for 32-bit guests in SCHEDOP_poll

   - Notable x86 fixes and cleanups:

      - One-off fixes for various emulation flows (SGX, VMXON, NRIPS=0).

      - Reinstate IBPB on emulated VM-Exit that was incorrectly dropped
        a few years back when eliminating unnecessary barriers when
        switching between vmcs01 and vmcs02.

      - Clean up vmread_error_trampoline() to make it more obvious that
        params must be passed on the stack, even for x86-64.

      - Let userspace set all supported bits in MSR_IA32_FEAT_CTL
        irrespective of the current guest CPUID.

      - Fudge around a race with TSC refinement that results in KVM
        incorrectly thinking a guest needs TSC scaling when running on a
        CPU with a constant TSC, but no hardware-enumerated TSC
        frequency.

      - Advertise (on AMD) that the SMM_CTL MSR is not supported

      - Remove unnecessary exports

  Generic:

   - Support for responding to signals during page faults; introduces
     new FOLL_INTERRUPTIBLE flag that was reviewed by mm folks

  Selftests:

   - Fix an inverted check in the access tracking perf test, and restore
     support for asserting that there aren't too many idle pages when
     running on bare metal.

   - Fix build errors that occur in certain setups (unsure exactly what
     is unique about the problematic setup) due to glibc overriding
     static_assert() to a variant that requires a custom message.

   - Introduce actual atomics for clear/set_bit() in selftests

   - Add support for pinning vCPUs in dirty_log_perf_test.

   - Rename the so called "perf_util" framework to "memstress".

   - Add a lightweight psuedo RNG for guest use, and use it to randomize
     the access pattern and write vs. read percentage in the memstress
     tests.

   - Add a common ucall implementation; code dedup and pre-work for
     running SEV (and beyond) guests in selftests.

   - Provide a common constructor and arch hook, which will eventually
     be used by x86 to automatically select the right hypercall (AMD vs.
     Intel).

   - A bunch of added/enabled/fixed selftests for ARM64, covering
     memslots, breakpoints, stage-2 faults and access tracking.

   - x86-specific selftest changes:

      - Clean up x86's page table management.

      - Clean up and enhance the "smaller maxphyaddr" test, and add a
        related test to cover generic emulation failure.

      - Clean up the nEPT support checks.

      - Add X86_PROPERTY_* framework to retrieve multi-bit CPUID values.

      - Fix an ordering issue in the AMX test introduced by recent
        conversions to use kvm_cpu_has(), and harden the code to guard
        against similar bugs in the future. Anything that tiggers
        caching of KVM's supported CPUID, kvm_cpu_has() in this case,
        effectively hides opt-in XSAVE features if the caching occurs
        before the test opts in via prctl().

  Documentation:

   - Remove deleted ioctls from documentation

   - Clean up the docs for the x86 MSR filter.

   - Various fixes"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (361 commits)
  KVM: x86: Add proper ReST tables for userspace MSR exits/flags
  KVM: selftests: Allocate ucall pool from MEM_REGION_DATA
  KVM: arm64: selftests: Align VA space allocator with TTBR0
  KVM: arm64: Fix benign bug with incorrect use of VA_BITS
  KVM: arm64: PMU: Fix period computation for 64bit counters with 32bit overflow
  KVM: x86: Advertise that the SMM_CTL MSR is not supported
  KVM: x86: remove unnecessary exports
  KVM: selftests: Fix spelling mistake "probabalistic" -> "probabilistic"
  tools: KVM: selftests: Convert clear/set_bit() to actual atomics
  tools: Drop "atomic_" prefix from atomic test_and_set_bit()
  tools: Drop conflicting non-atomic test_and_{clear,set}_bit() helpers
  KVM: selftests: Use non-atomic clear/set bit helpers in KVM tests
  perf tools: Use dedicated non-atomic clear/set bit helpers
  tools: Take @bit as an "unsigned long" in {clear,set}_bit() helpers
  KVM: arm64: selftests: Enable single-step without a "full" ucall()
  KVM: x86: fix APICv/x2AVIC disabled when vm reboot by itself
  KVM: Remove stale comment about KVM_REQ_UNHALT
  KVM: Add missing arch for KVM_CREATE_DEVICE and KVM_{SET,GET}_DEVICE_ATTR
  KVM: Reference to kvm_userspace_memory_region in doc and comments
  KVM: Delete all references to removed KVM_SET_MEMORY_ALIAS ioctl
  ...

6 files changed, 188 insertions, 92 deletions

diff --git a/virt/kvm/Kconfig b/virt/kvm/Kconfig
index 800f9470e36b..9fb1ff6f19e5 100644
--- a/virt/kvm/Kconfig
+++ b/virt/kvm/Kconfig
@@ -33,6 +33,12 @@ config HAVE_KVM_DIRTY_RING_ACQ_REL
        bool
        select HAVE_KVM_DIRTY_RING
 
+# Allow enabling both the dirty bitmap and dirty ring. Only architectures
+# that need to dirty memory outside of a vCPU context should select this.
+config NEED_KVM_DIRTY_RING_WITH_BITMAP
+	bool
+	depends on HAVE_KVM_DIRTY_RING
+
 config HAVE_KVM_EVENTFD
        bool
        select EVENTFD
diff --git a/virt/kvm/dirty_ring.c b/virt/kvm/dirty_ring.c
index d6fabf238032..c1cd7dfe4a90 100644
--- a/virt/kvm/dirty_ring.c
+++ b/virt/kvm/dirty_ring.c
@@ -21,12 +21,26 @@ u32 kvm_dirty_ring_get_rsvd_entries(void)
 	return KVM_DIRTY_RING_RSVD_ENTRIES + kvm_cpu_dirty_log_size();
 }
 
+bool kvm_use_dirty_bitmap(struct kvm *kvm)
+{
+	lockdep_assert_held(&kvm->slots_lock);
+
+	return !kvm->dirty_ring_size || kvm->dirty_ring_with_bitmap;
+}
+
+#ifndef CONFIG_NEED_KVM_DIRTY_RING_WITH_BITMAP
+bool kvm_arch_allow_write_without_running_vcpu(struct kvm *kvm)
+{
+	return false;
+}
+#endif
+
 static u32 kvm_dirty_ring_used(struct kvm_dirty_ring *ring)
 {
 	return READ_ONCE(ring->dirty_index) - READ_ONCE(ring->reset_index);
 }
 
-bool kvm_dirty_ring_soft_full(struct kvm_dirty_ring *ring)
+static bool kvm_dirty_ring_soft_full(struct kvm_dirty_ring *ring)
 {
 	return kvm_dirty_ring_used(ring) >= ring->soft_limit;
 }
@@ -142,13 +156,19 @@ int kvm_dirty_ring_reset(struct kvm *kvm, struct kvm_dirty_ring *ring)
 
 	kvm_reset_dirty_gfn(kvm, cur_slot, cur_offset, mask);
 
+	/*
+	 * The request KVM_REQ_DIRTY_RING_SOFT_FULL will be cleared
+	 * by the VCPU thread next time when it enters the guest.
+	 */
+
 	trace_kvm_dirty_ring_reset(ring);
 
 	return count;
 }
 
-void kvm_dirty_ring_push(struct kvm_dirty_ring *ring, u32 slot, u64 offset)
+void kvm_dirty_ring_push(struct kvm_vcpu *vcpu, u32 slot, u64 offset)
 {
+	struct kvm_dirty_ring *ring = &vcpu->dirty_ring;
 	struct kvm_dirty_gfn *entry;
 
 	/* It should never get full */
@@ -166,6 +186,28 @@ void kvm_dirty_ring_push(struct kvm_dirty_ring *ring, u32 slot, u64 offset)
 	kvm_dirty_gfn_set_dirtied(entry);
 	ring->dirty_index++;
 	trace_kvm_dirty_ring_push(ring, slot, offset);
+
+	if (kvm_dirty_ring_soft_full(ring))
+		kvm_make_request(KVM_REQ_DIRTY_RING_SOFT_FULL, vcpu);
+}
+
+bool kvm_dirty_ring_check_request(struct kvm_vcpu *vcpu)
+{
+	/*
+	 * The VCPU isn't runnable when the dirty ring becomes soft full.
+	 * The KVM_REQ_DIRTY_RING_SOFT_FULL event is always set to prevent
+	 * the VCPU from running until the dirty pages are harvested and
+	 * the dirty ring is reset by userspace.
+	 */
+	if (kvm_check_request(KVM_REQ_DIRTY_RING_SOFT_FULL, vcpu) &&
+	    kvm_dirty_ring_soft_full(&vcpu->dirty_ring)) {
+		kvm_make_request(KVM_REQ_DIRTY_RING_SOFT_FULL, vcpu);
+		vcpu->run->exit_reason = KVM_EXIT_DIRTY_RING_FULL;
+		trace_kvm_dirty_ring_exit(vcpu);
+		return true;
+	}
+
+	return false;
 }
 
 struct page *kvm_dirty_ring_get_page(struct kvm_dirty_ring *ring, u32 offset)
diff --git a/virt/kvm/irqchip.c b/virt/kvm/irqchip.c
index 58e4f88b2b9f..1e567d1f6d3d 100644
--- a/virt/kvm/irqchip.c
+++ b/virt/kvm/irqchip.c
@@ -17,7 +17,6 @@
 #include <linux/srcu.h>
 #include <linux/export.h>
 #include <trace/events/kvm.h>
-#include "irq.h"
 
 int kvm_irq_map_gsi(struct kvm *kvm,
 		    struct kvm_kernel_irq_routing_entry *entries, int gsi)
@@ -50,7 +49,7 @@ int kvm_send_userspace_msi(struct kvm *kvm, struct kvm_msi *msi)
 {
 	struct kvm_kernel_irq_routing_entry route;
 
-	if (!irqchip_in_kernel(kvm) || (msi->flags & ~KVM_MSI_VALID_DEVID))
+	if (!kvm_arch_irqchip_in_kernel(kvm) || (msi->flags & ~KVM_MSI_VALID_DEVID))
 		return -EINVAL;
 
 	route.msi.address_lo = msi->address_lo;
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index fab4d3790578..13e88297f999 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -1615,7 +1615,7 @@ static int kvm_prepare_memory_region(struct kvm *kvm,
 			new->dirty_bitmap = NULL;
 		else if (old && old->dirty_bitmap)
 			new->dirty_bitmap = old->dirty_bitmap;
-		else if (!kvm->dirty_ring_size) {
+		else if (kvm_use_dirty_bitmap(kvm)) {
 			r = kvm_alloc_dirty_bitmap(new);
 			if (r)
 				return r;
@@ -1639,6 +1639,8 @@ static void kvm_commit_memory_region(struct kvm *kvm,
 				     const struct kvm_memory_slot *new,
 				     enum kvm_mr_change change)
 {
+	int old_flags = old ? old->flags : 0;
+	int new_flags = new ? new->flags : 0;
 	/*
 	 * Update the total number of memslot pages before calling the arch
 	 * hook so that architectures can consume the result directly.
@@ -1648,6 +1650,12 @@ static void kvm_commit_memory_region(struct kvm *kvm,
 	else if (change == KVM_MR_CREATE)
 		kvm->nr_memslot_pages += new->npages;
 
+	if ((old_flags ^ new_flags) & KVM_MEM_LOG_DIRTY_PAGES) {
+		int change = (new_flags & KVM_MEM_LOG_DIRTY_PAGES) ? 1 : -1;
+		atomic_set(&kvm->nr_memslots_dirty_logging,
+			   atomic_read(&kvm->nr_memslots_dirty_logging) + change);
+	}
+
 	kvm_arch_commit_memory_region(kvm, old, new, change);
 
 	switch (change) {
@@ -2058,8 +2066,8 @@ int kvm_get_dirty_log(struct kvm *kvm, struct kvm_dirty_log *log,
 	unsigned long n;
 	unsigned long any = 0;
 
-	/* Dirty ring tracking is exclusive to dirty log tracking */
-	if (kvm->dirty_ring_size)
+	/* Dirty ring tracking may be exclusive to dirty log tracking */
+	if (!kvm_use_dirty_bitmap(kvm))
 		return -ENXIO;
 
 	*memslot = NULL;
@@ -2123,8 +2131,8 @@ static int kvm_get_dirty_log_protect(struct kvm *kvm, struct kvm_dirty_log *log)
 	unsigned long *dirty_bitmap_buffer;
 	bool flush;
 
-	/* Dirty ring tracking is exclusive to dirty log tracking */
-	if (kvm->dirty_ring_size)
+	/* Dirty ring tracking may be exclusive to dirty log tracking */
+	if (!kvm_use_dirty_bitmap(kvm))
 		return -ENXIO;
 
 	as_id = log->slot >> 16;
@@ -2235,8 +2243,8 @@ static int kvm_clear_dirty_log_protect(struct kvm *kvm,
 	unsigned long *dirty_bitmap_buffer;
 	bool flush;
 
-	/* Dirty ring tracking is exclusive to dirty log tracking */
-	if (kvm->dirty_ring_size)
+	/* Dirty ring tracking may be exclusive to dirty log tracking */
+	if (!kvm_use_dirty_bitmap(kvm))
 		return -ENXIO;
 
 	as_id = log->slot >> 16;
@@ -2512,7 +2520,7 @@ static bool hva_to_pfn_fast(unsigned long addr, bool write_fault,
  * 1 indicates success, -errno is returned if error is detected.
  */
 static int hva_to_pfn_slow(unsigned long addr, bool *async, bool write_fault,
-			   bool *writable, kvm_pfn_t *pfn)
+			   bool interruptible, bool *writable, kvm_pfn_t *pfn)
 {
 	unsigned int flags = FOLL_HWPOISON;
 	struct page *page;
@@ -2527,6 +2535,8 @@ static int hva_to_pfn_slow(unsigned long addr, bool *async, bool write_fault,
 		flags |= FOLL_WRITE;
 	if (async)
 		flags |= FOLL_NOWAIT;
+	if (interruptible)
+		flags |= FOLL_INTERRUPTIBLE;
 
 	npages = get_user_pages_unlocked(addr, 1, &page, flags);
 	if (npages != 1)
@@ -2636,6 +2646,7 @@ out:
  * Pin guest page in memory and return its pfn.
  * @addr: host virtual address which maps memory to the guest
  * @atomic: whether this function can sleep
+ * @interruptible: whether the process can be interrupted by non-fatal signals
  * @async: whether this function need to wait IO complete if the
  *         host page is not in the memory
  * @write_fault: whether we should get a writable host page
@@ -2646,8 +2657,8 @@ out:
  * 2): @write_fault = false && @writable, @writable will tell the caller
  *     whether the mapping is writable.
  */
-kvm_pfn_t hva_to_pfn(unsigned long addr, bool atomic, bool *async,
-		     bool write_fault, bool *writable)
+kvm_pfn_t hva_to_pfn(unsigned long addr, bool atomic, bool interruptible,
+		     bool *async, bool write_fault, bool *writable)
 {
 	struct vm_area_struct *vma;
 	kvm_pfn_t pfn;
@@ -2662,9 +2673,12 @@ kvm_pfn_t hva_to_pfn(unsigned long addr, bool atomic, bool *async,
 	if (atomic)
 		return KVM_PFN_ERR_FAULT;
 
-	npages = hva_to_pfn_slow(addr, async, write_fault, writable, &pfn);
+	npages = hva_to_pfn_slow(addr, async, write_fault, interruptible,
+				 writable, &pfn);
 	if (npages == 1)
 		return pfn;
+	if (npages == -EINTR)
+		return KVM_PFN_ERR_SIGPENDING;
 
 	mmap_read_lock(current->mm);
 	if (npages == -EHWPOISON ||
@@ -2695,8 +2709,8 @@ exit:
 }
 
 kvm_pfn_t __gfn_to_pfn_memslot(const struct kvm_memory_slot *slot, gfn_t gfn,
-			       bool atomic, bool *async, bool write_fault,
-			       bool *writable, hva_t *hva)
+			       bool atomic, bool interruptible, bool *async,
+			       bool write_fault, bool *writable, hva_t *hva)
 {
 	unsigned long addr = __gfn_to_hva_many(slot, gfn, NULL, write_fault);
 
@@ -2721,7 +2735,7 @@ kvm_pfn_t __gfn_to_pfn_memslot(const struct kvm_memory_slot *slot, gfn_t gfn,
 		writable = NULL;
 	}
 
-	return hva_to_pfn(addr, atomic, async, write_fault,
+	return hva_to_pfn(addr, atomic, interruptible, async, write_fault,
 			  writable);
 }
 EXPORT_SYMBOL_GPL(__gfn_to_pfn_memslot);
@@ -2729,20 +2743,22 @@ EXPORT_SYMBOL_GPL(__gfn_to_pfn_memslot);
 kvm_pfn_t gfn_to_pfn_prot(struct kvm *kvm, gfn_t gfn, bool write_fault,
 		      bool *writable)
 {
-	return __gfn_to_pfn_memslot(gfn_to_memslot(kvm, gfn), gfn, false, NULL,
-				    write_fault, writable, NULL);
+	return __gfn_to_pfn_memslot(gfn_to_memslot(kvm, gfn), gfn, false, false,
+				    NULL, write_fault, writable, NULL);
 }
 EXPORT_SYMBOL_GPL(gfn_to_pfn_prot);
 
 kvm_pfn_t gfn_to_pfn_memslot(const struct kvm_memory_slot *slot, gfn_t gfn)
 {
-	return __gfn_to_pfn_memslot(slot, gfn, false, NULL, true, NULL, NULL);
+	return __gfn_to_pfn_memslot(slot, gfn, false, false, NULL, true,
+				    NULL, NULL);
 }
 EXPORT_SYMBOL_GPL(gfn_to_pfn_memslot);
 
 kvm_pfn_t gfn_to_pfn_memslot_atomic(const struct kvm_memory_slot *slot, gfn_t gfn)
 {
-	return __gfn_to_pfn_memslot(slot, gfn, true, NULL, true, NULL, NULL);
+	return __gfn_to_pfn_memslot(slot, gfn, true, false, NULL, true,
+				    NULL, NULL);
 }
 EXPORT_SYMBOL_GPL(gfn_to_pfn_memslot_atomic);
 
@@ -3303,18 +3319,19 @@ void mark_page_dirty_in_slot(struct kvm *kvm,
 	struct kvm_vcpu *vcpu = kvm_get_running_vcpu();
 
 #ifdef CONFIG_HAVE_KVM_DIRTY_RING
-	if (WARN_ON_ONCE(!vcpu) || WARN_ON_ONCE(vcpu->kvm != kvm))
+	if (WARN_ON_ONCE(vcpu && vcpu->kvm != kvm))
 		return;
+
+	WARN_ON_ONCE(!vcpu && !kvm_arch_allow_write_without_running_vcpu(kvm));
 #endif
 
 	if (memslot && kvm_slot_dirty_track_enabled(memslot)) {
 		unsigned long rel_gfn = gfn - memslot->base_gfn;
 		u32 slot = (memslot->as_id << 16) | memslot->id;
 
-		if (kvm->dirty_ring_size)
-			kvm_dirty_ring_push(&vcpu->dirty_ring,
-					    slot, rel_gfn);
-		else
+		if (kvm->dirty_ring_size && vcpu)
+			kvm_dirty_ring_push(vcpu, slot, rel_gfn);
+		else if (memslot->dirty_bitmap)
 			set_bit_le(rel_gfn, memslot->dirty_bitmap);
 	}
 }
@@ -3521,10 +3538,6 @@ void kvm_vcpu_halt(struct kvm_vcpu *vcpu)
 		ktime_t stop = ktime_add_ns(start, vcpu->halt_poll_ns);
 
 		do {
-			/*
-			 * This sets KVM_REQ_UNHALT if an interrupt
-			 * arrives.
-			 */
 			if (kvm_vcpu_check_block(vcpu) < 0)
 				goto out;
 			cpu_relax();
@@ -4506,6 +4519,9 @@ static long kvm_vm_ioctl_check_extension_generic(struct kvm *kvm, long arg)
 #else
 		return 0;
 #endif
+#ifdef CONFIG_NEED_KVM_DIRTY_RING_WITH_BITMAP
+	case KVM_CAP_DIRTY_LOG_RING_WITH_BITMAP:
+#endif
 	case KVM_CAP_BINARY_STATS_FD:
 	case KVM_CAP_SYSTEM_EVENT_DATA:
 		return 1;
@@ -4581,6 +4597,20 @@ int __attribute__((weak)) kvm_vm_ioctl_enable_cap(struct kvm *kvm,
 	return -EINVAL;
 }
 
+static bool kvm_are_all_memslots_empty(struct kvm *kvm)
+{
+	int i;
+
+	lockdep_assert_held(&kvm->slots_lock);
+
+	for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) {
+		if (!kvm_memslots_empty(__kvm_memslots(kvm, i)))
+			return false;
+	}
+
+	return true;
+}
+
 static int kvm_vm_ioctl_enable_cap_generic(struct kvm *kvm,
 					   struct kvm_enable_cap *cap)
 {
@@ -4621,6 +4651,29 @@ static int kvm_vm_ioctl_enable_cap_generic(struct kvm *kvm,
 			return -EINVAL;
 
 		return kvm_vm_ioctl_enable_dirty_log_ring(kvm, cap->args[0]);
+	case KVM_CAP_DIRTY_LOG_RING_WITH_BITMAP: {
+		int r = -EINVAL;
+
+		if (!IS_ENABLED(CONFIG_NEED_KVM_DIRTY_RING_WITH_BITMAP) ||
+		    !kvm->dirty_ring_size || cap->flags)
+			return r;
+
+		mutex_lock(&kvm->slots_lock);
+
+		/*
+		 * For simplicity, allow enabling ring+bitmap if and only if
+		 * there are no memslots, e.g. to ensure all memslots allocate
+		 * a bitmap after the capability is enabled.
+		 */
+		if (kvm_are_all_memslots_empty(kvm)) {
+			kvm->dirty_ring_with_bitmap = true;
+			r = 0;
+		}
+
+		mutex_unlock(&kvm->slots_lock);
+
+		return r;
+	}
 	default:
 		return kvm_vm_ioctl_enable_cap(kvm, cap);
 	}
diff --git a/virt/kvm/kvm_mm.h b/virt/kvm/kvm_mm.h
index 41da467d99c9..a1ab15006af3 100644
--- a/virt/kvm/kvm_mm.h
+++ b/virt/kvm/kvm_mm.h
@@ -24,8 +24,8 @@
 #define KVM_MMU_READ_UNLOCK(kvm)	spin_unlock(&(kvm)->mmu_lock)
 #endif /* KVM_HAVE_MMU_RWLOCK */
 
-kvm_pfn_t hva_to_pfn(unsigned long addr, bool atomic, bool *async,
-		     bool write_fault, bool *writable);
+kvm_pfn_t hva_to_pfn(unsigned long addr, bool atomic, bool interruptible,
+		     bool *async, bool write_fault, bool *writable);
 
 #ifdef CONFIG_HAVE_KVM_PFNCACHE
 void gfn_to_pfn_cache_invalidate_start(struct kvm *kvm,
diff --git a/virt/kvm/pfncache.c b/virt/kvm/pfncache.c
index 7c248193ca26..2d6aba677830 100644
--- a/virt/kvm/pfncache.c
+++ b/virt/kvm/pfncache.c
@@ -76,19 +76,17 @@ void gfn_to_pfn_cache_invalidate_start(struct kvm *kvm, unsigned long start,
 	}
 }
 
-bool kvm_gfn_to_pfn_cache_check(struct kvm *kvm, struct gfn_to_pfn_cache *gpc,
-				gpa_t gpa, unsigned long len)
+bool kvm_gpc_check(struct gfn_to_pfn_cache *gpc, unsigned long len)
 {
-	struct kvm_memslots *slots = kvm_memslots(kvm);
+	struct kvm_memslots *slots = kvm_memslots(gpc->kvm);
 
 	if (!gpc->active)
 		return false;
 
-	if ((gpa & ~PAGE_MASK) + len > PAGE_SIZE)
+	if ((gpc->gpa & ~PAGE_MASK) + len > PAGE_SIZE)
 		return false;
 
-	if (gpc->gpa != gpa || gpc->generation != slots->generation ||
-	    kvm_is_error_hva(gpc->uhva))
+	if (gpc->generation != slots->generation || kvm_is_error_hva(gpc->uhva))
 		return false;
 
 	if (!gpc->valid)
@@ -96,9 +94,9 @@ bool kvm_gfn_to_pfn_cache_check(struct kvm *kvm, struct gfn_to_pfn_cache *gpc,
 
 	return true;
 }
-EXPORT_SYMBOL_GPL(kvm_gfn_to_pfn_cache_check);
+EXPORT_SYMBOL_GPL(kvm_gpc_check);
 
-static void gpc_unmap_khva(struct kvm *kvm, kvm_pfn_t pfn, void *khva)
+static void gpc_unmap_khva(kvm_pfn_t pfn, void *khva)
 {
 	/* Unmap the old pfn/page if it was mapped before. */
 	if (!is_error_noslot_pfn(pfn) && khva) {
@@ -139,7 +137,7 @@ static inline bool mmu_notifier_retry_cache(struct kvm *kvm, unsigned long mmu_s
 	return kvm->mmu_invalidate_seq != mmu_seq;
 }
 
-static kvm_pfn_t hva_to_pfn_retry(struct kvm *kvm, struct gfn_to_pfn_cache *gpc)
+static kvm_pfn_t hva_to_pfn_retry(struct gfn_to_pfn_cache *gpc)
 {
 	/* Note, the new page offset may be different than the old! */
 	void *old_khva = gpc->khva - offset_in_page(gpc->khva);
@@ -159,7 +157,7 @@ static kvm_pfn_t hva_to_pfn_retry(struct kvm *kvm, struct gfn_to_pfn_cache *gpc)
 	gpc->valid = false;
 
 	do {
-		mmu_seq = kvm->mmu_invalidate_seq;
+		mmu_seq = gpc->kvm->mmu_invalidate_seq;
 		smp_rmb();
 
 		write_unlock_irq(&gpc->lock);
@@ -177,7 +175,7 @@ static kvm_pfn_t hva_to_pfn_retry(struct kvm *kvm, struct gfn_to_pfn_cache *gpc)
 			 * the existing mapping and didn't create a new one.
 			 */
 			if (new_khva != old_khva)
-				gpc_unmap_khva(kvm, new_pfn, new_khva);
+				gpc_unmap_khva(new_pfn, new_khva);
 
 			kvm_release_pfn_clean(new_pfn);
 
@@ -185,7 +183,7 @@ static kvm_pfn_t hva_to_pfn_retry(struct kvm *kvm, struct gfn_to_pfn_cache *gpc)
 		}
 
 		/* We always request a writeable mapping */
-		new_pfn = hva_to_pfn(gpc->uhva, false, NULL, true, NULL);
+		new_pfn = hva_to_pfn(gpc->uhva, false, false, NULL, true, NULL);
 		if (is_error_noslot_pfn(new_pfn))
 			goto out_error;
 
@@ -217,7 +215,7 @@ static kvm_pfn_t hva_to_pfn_retry(struct kvm *kvm, struct gfn_to_pfn_cache *gpc)
 		 * attempting to refresh.
 		 */
 		WARN_ON_ONCE(gpc->valid);
-	} while (mmu_notifier_retry_cache(kvm, mmu_seq));
+	} while (mmu_notifier_retry_cache(gpc->kvm, mmu_seq));
 
 	gpc->valid = true;
 	gpc->pfn = new_pfn;
@@ -238,10 +236,10 @@ out_error:
 	return -EFAULT;
 }
 
-int kvm_gfn_to_pfn_cache_refresh(struct kvm *kvm, struct gfn_to_pfn_cache *gpc,
-				 gpa_t gpa, unsigned long len)
+static int __kvm_gpc_refresh(struct gfn_to_pfn_cache *gpc, gpa_t gpa,
+			     unsigned long len)
 {
-	struct kvm_memslots *slots = kvm_memslots(kvm);
+	struct kvm_memslots *slots = kvm_memslots(gpc->kvm);
 	unsigned long page_offset = gpa & ~PAGE_MASK;
 	bool unmap_old = false;
 	unsigned long old_uhva;
@@ -295,7 +293,7 @@ int kvm_gfn_to_pfn_cache_refresh(struct kvm *kvm, struct gfn_to_pfn_cache *gpc,
 	 * drop the lock and do the HVA to PFN lookup again.
 	 */
 	if (!gpc->valid || old_uhva != gpc->uhva) {
-		ret = hva_to_pfn_retry(kvm, gpc);
+		ret = hva_to_pfn_retry(gpc);
 	} else {
 		/*
 		 * If the HVA→PFN mapping was already valid, don't unmap it.
@@ -303,9 +301,8 @@ int kvm_gfn_to_pfn_cache_refresh(struct kvm *kvm, struct gfn_to_pfn_cache *gpc,
 		 * may have changed.
 		 */
 		gpc->khva = old_khva + page_offset;
-		old_pfn = KVM_PFN_ERR_FAULT;
-		old_khva = NULL;
 		ret = 0;
+		goto out_unlock;
 	}
 
  out:
@@ -329,59 +326,41 @@ out_unlock:
 	mutex_unlock(&gpc->refresh_lock);
 
 	if (unmap_old)
-		gpc_unmap_khva(kvm, old_pfn, old_khva);
+		gpc_unmap_khva(old_pfn, old_khva);
 
 	return ret;
 }
-EXPORT_SYMBOL_GPL(kvm_gfn_to_pfn_cache_refresh);
 
-void kvm_gfn_to_pfn_cache_unmap(struct kvm *kvm, struct gfn_to_pfn_cache *gpc)
+int kvm_gpc_refresh(struct gfn_to_pfn_cache *gpc, unsigned long len)
 {
-	void *old_khva;
-	kvm_pfn_t old_pfn;
-
-	mutex_lock(&gpc->refresh_lock);
-	write_lock_irq(&gpc->lock);
-
-	gpc->valid = false;
-
-	old_khva = gpc->khva - offset_in_page(gpc->khva);
-	old_pfn = gpc->pfn;
-
-	/*
-	 * We can leave the GPA → uHVA map cache intact but the PFN
-	 * lookup will need to be redone even for the same page.
-	 */
-	gpc->khva = NULL;
-	gpc->pfn = KVM_PFN_ERR_FAULT;
-
-	write_unlock_irq(&gpc->lock);
-	mutex_unlock(&gpc->refresh_lock);
-
-	gpc_unmap_khva(kvm, old_pfn, old_khva);
+	return __kvm_gpc_refresh(gpc, gpc->gpa, len);
 }
-EXPORT_SYMBOL_GPL(kvm_gfn_to_pfn_cache_unmap);
+EXPORT_SYMBOL_GPL(kvm_gpc_refresh);
 
-void kvm_gpc_init(struct gfn_to_pfn_cache *gpc)
+void kvm_gpc_init(struct gfn_to_pfn_cache *gpc, struct kvm *kvm,
+		  struct kvm_vcpu *vcpu, enum pfn_cache_usage usage)
 {
+	WARN_ON_ONCE(!usage || (usage & KVM_GUEST_AND_HOST_USE_PFN) != usage);
+	WARN_ON_ONCE((usage & KVM_GUEST_USES_PFN) && !vcpu);
+
 	rwlock_init(&gpc->lock);
 	mutex_init(&gpc->refresh_lock);
+
+	gpc->kvm = kvm;
+	gpc->vcpu = vcpu;
+	gpc->usage = usage;
+	gpc->pfn = KVM_PFN_ERR_FAULT;
+	gpc->uhva = KVM_HVA_ERR_BAD;
 }
 EXPORT_SYMBOL_GPL(kvm_gpc_init);
 
-int kvm_gpc_activate(struct kvm *kvm, struct gfn_to_pfn_cache *gpc,
-		     struct kvm_vcpu *vcpu, enum pfn_cache_usage usage,
-		     gpa_t gpa, unsigned long len)
+int kvm_gpc_activate(struct gfn_to_pfn_cache *gpc, gpa_t gpa, unsigned long len)
 {
-	WARN_ON_ONCE(!usage || (usage & KVM_GUEST_AND_HOST_USE_PFN) != usage);
+	struct kvm *kvm = gpc->kvm;
 
 	if (!gpc->active) {
-		gpc->khva = NULL;
-		gpc->pfn = KVM_PFN_ERR_FAULT;
-		gpc->uhva = KVM_HVA_ERR_BAD;
-		gpc->vcpu = vcpu;
-		gpc->usage = usage;
-		gpc->valid = false;
+		if (KVM_BUG_ON(gpc->valid, kvm))
+			return -EIO;
 
 		spin_lock(&kvm->gpc_lock);
 		list_add(&gpc->list, &kvm->gpc_list);
@@ -396,12 +375,16 @@ int kvm_gpc_activate(struct kvm *kvm, struct gfn_to_pfn_cache *gpc,
 		gpc->active = true;
 		write_unlock_irq(&gpc->lock);
 	}
-	return kvm_gfn_to_pfn_cache_refresh(kvm, gpc, gpa, len);
+	return __kvm_gpc_refresh(gpc, gpa, len);
 }
 EXPORT_SYMBOL_GPL(kvm_gpc_activate);
 
-void kvm_gpc_deactivate(struct kvm *kvm, struct gfn_to_pfn_cache *gpc)
+void kvm_gpc_deactivate(struct gfn_to_pfn_cache *gpc)
 {
+	struct kvm *kvm = gpc->kvm;
+	kvm_pfn_t old_pfn;
+	void *old_khva;
+
 	if (gpc->active) {
 		/*
 		 * Deactivate the cache before removing it from the list, KVM
@@ -410,13 +393,26 @@ void kvm_gpc_deactivate(struct kvm *kvm, struct gfn_to_pfn_cache *gpc)
 		 */
 		write_lock_irq(&gpc->lock);
 		gpc->active = false;
+		gpc->valid = false;
+
+		/*
+		 * Leave the GPA => uHVA cache intact, it's protected by the
+		 * memslot generation.  The PFN lookup needs to be redone every
+		 * time as mmu_notifier protection is lost when the cache is
+		 * removed from the VM's gpc_list.
+		 */
+		old_khva = gpc->khva - offset_in_page(gpc->khva);
+		gpc->khva = NULL;
+
+		old_pfn = gpc->pfn;
+		gpc->pfn = KVM_PFN_ERR_FAULT;
 		write_unlock_irq(&gpc->lock);
 
 		spin_lock(&kvm->gpc_lock);
 		list_del(&gpc->list);
 		spin_unlock(&kvm->gpc_lock);
 
-		kvm_gfn_to_pfn_cache_unmap(kvm, gpc);
+		gpc_unmap_khva(old_pfn, old_khva);
 	}
 }
 EXPORT_SYMBOL_GPL(kvm_gpc_deactivate);