Merge branch 'next' of git://git.kernel.org/pub/scm/virt/kvm/kvm

Pull KVM changes from Avi Kivity:
 "Changes include additional instruction emulation, page-crossing MMIO,
  faster dirty logging, preventing the watchdog from killing a stopped
  guest, module autoload, a new MSI ABI, and some minor optimizations
  and fixes.  Outside x86 we have a small s390 and a very large ppc
  update.

  Regarding the new (for kvm) rebaseless workflow, some of the patches
  that were merged before we switch trees had to be rebased, while
  others are true pulls.  In either case the signoffs should be correct
  now."

Fix up trivial conflicts in Documentation/feature-removal-schedule.txt
arch/powerpc/kvm/book3s_segment.S and arch/x86/include/asm/kvm_para.h.

I suspect the kvm_para.h resolution ends up doing the "do I have cpuid"
check effectively twice (it was done differently in two different
commits), but better safe than sorry ;)

* 'next' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (125 commits)
  KVM: make asm-generic/kvm_para.h have an ifdef __KERNEL__ block
  KVM: s390: onereg for timer related registers
  KVM: s390: epoch difference and TOD programmable field
  KVM: s390: KVM_GET/SET_ONEREG for s390
  KVM: s390: add capability indicating COW support
  KVM: Fix mmu_reload() clash with nested vmx event injection
  KVM: MMU: Don't use RCU for lockless shadow walking
  KVM: VMX: Optimize %ds, %es reload
  KVM: VMX: Fix %ds/%es clobber
  KVM: x86 emulator: convert bsf/bsr instructions to emulate_2op_SrcV_nobyte()
  KVM: VMX: unlike vmcs on fail path
  KVM: PPC: Emulator: clean up SPR reads and writes
  KVM: PPC: Emulator: clean up instruction parsing
  kvm/powerpc: Add new ioctl to retreive server MMU infos
  kvm/book3s: Make kernel emulated H_PUT_TCE available for "PR" KVM
  KVM: PPC: bookehv: Fix r8/r13 storing in level exception handler
  KVM: PPC: Book3S: Enable IRQs during exit handling
  KVM: PPC: Fix PR KVM on POWER7 bare metal
  KVM: PPC: Fix stbux emulation
  KVM: PPC: bookehv: Use lwz/stw instead of PPC_LL/PPC_STL for 32-bit fields
  ...

1 files changed, 154 insertions, 126 deletions

diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 185a2b823a2..be6d54929fa 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -2147,6 +2147,7 @@ int kvm_dev_ioctl_check_extension(long ext)
 	case KVM_CAP_ASYNC_PF:
 	case KVM_CAP_GET_TSC_KHZ:
 	case KVM_CAP_PCI_2_3:
+	case KVM_CAP_KVMCLOCK_CTRL:
 		r = 1;
 		break;
 	case KVM_CAP_COALESCED_MMIO:
@@ -2597,6 +2598,23 @@ static int kvm_vcpu_ioctl_x86_set_xcrs(struct kvm_vcpu *vcpu,
 	return r;
 }
 
+/*
+ * kvm_set_guest_paused() indicates to the guest kernel that it has been
+ * stopped by the hypervisor.  This function will be called from the host only.
+ * EINVAL is returned when the host attempts to set the flag for a guest that
+ * does not support pv clocks.
+ */
+static int kvm_set_guest_paused(struct kvm_vcpu *vcpu)
+{
+	struct pvclock_vcpu_time_info *src = &vcpu->arch.hv_clock;
+	if (!vcpu->arch.time_page)
+		return -EINVAL;
+	src->flags |= PVCLOCK_GUEST_STOPPED;
+	mark_page_dirty(vcpu->kvm, vcpu->arch.time >> PAGE_SHIFT);
+	kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu);
+	return 0;
+}
+
 long kvm_arch_vcpu_ioctl(struct file *filp,
 			 unsigned int ioctl, unsigned long arg)
 {
@@ -2873,6 +2891,10 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
 		r = vcpu->arch.virtual_tsc_khz;
 		goto out;
 	}
+	case KVM_KVMCLOCK_CTRL: {
+		r = kvm_set_guest_paused(vcpu);
+		goto out;
+	}
 	default:
 		r = -EINVAL;
 	}
@@ -3045,57 +3067,32 @@ static int kvm_vm_ioctl_reinject(struct kvm *kvm,
 }
 
 /**
- * write_protect_slot - write protect a slot for dirty logging
- * @kvm: the kvm instance
- * @memslot: the slot we protect
- * @dirty_bitmap: the bitmap indicating which pages are dirty
- * @nr_dirty_pages: the number of dirty pages
+ * kvm_vm_ioctl_get_dirty_log - get and clear the log of dirty pages in a slot
+ * @kvm: kvm instance
+ * @log: slot id and address to which we copy the log
  *
- * We have two ways to find all sptes to protect:
- * 1. Use kvm_mmu_slot_remove_write_access() which walks all shadow pages and
- *    checks ones that have a spte mapping a page in the slot.
- * 2. Use kvm_mmu_rmap_write_protect() for each gfn found in the bitmap.
+ * We need to keep it in mind that VCPU threads can write to the bitmap
+ * concurrently.  So, to avoid losing data, we keep the following order for
+ * each bit:
  *
- * Generally speaking, if there are not so many dirty pages compared to the
- * number of shadow pages, we should use the latter.
+ *   1. Take a snapshot of the bit and clear it if needed.
+ *   2. Write protect the corresponding page.
+ *   3. Flush TLB's if needed.
+ *   4. Copy the snapshot to the userspace.
  *
- * Note that letting others write into a page marked dirty in the old bitmap
- * by using the remaining tlb entry is not a problem.  That page will become
- * write protected again when we flush the tlb and then be reported dirty to
- * the user space by copying the old bitmap.
- */
-static void write_protect_slot(struct kvm *kvm,
-			       struct kvm_memory_slot *memslot,
-			       unsigned long *dirty_bitmap,
-			       unsigned long nr_dirty_pages)
-{
-	spin_lock(&kvm->mmu_lock);
-
-	/* Not many dirty pages compared to # of shadow pages. */
-	if (nr_dirty_pages < kvm->arch.n_used_mmu_pages) {
-		unsigned long gfn_offset;
-
-		for_each_set_bit(gfn_offset, dirty_bitmap, memslot->npages) {
-			unsigned long gfn = memslot->base_gfn + gfn_offset;
-
-			kvm_mmu_rmap_write_protect(kvm, gfn, memslot);
-		}
-		kvm_flush_remote_tlbs(kvm);
-	} else
-		kvm_mmu_slot_remove_write_access(kvm, memslot->id);
-
-	spin_unlock(&kvm->mmu_lock);
-}
-
-/*
- * Get (and clear) the dirty memory log for a memory slot.
+ * Between 2 and 3, the guest may write to the page using the remaining TLB
+ * entry.  This is not a problem because the page will be reported dirty at
+ * step 4 using the snapshot taken before and step 3 ensures that successive
+ * writes will be logged for the next call.
  */
-int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm,
-				      struct kvm_dirty_log *log)
+int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm, struct kvm_dirty_log *log)
 {
 	int r;
 	struct kvm_memory_slot *memslot;
-	unsigned long n, nr_dirty_pages;
+	unsigned long n, i;
+	unsigned long *dirty_bitmap;
+	unsigned long *dirty_bitmap_buffer;
+	bool is_dirty = false;
 
 	mutex_lock(&kvm->slots_lock);
 
@@ -3104,49 +3101,42 @@ int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm,
 		goto out;
 
 	memslot = id_to_memslot(kvm->memslots, log->slot);
+
+	dirty_bitmap = memslot->dirty_bitmap;
 	r = -ENOENT;
-	if (!memslot->dirty_bitmap)
+	if (!dirty_bitmap)
 		goto out;
 
 	n = kvm_dirty_bitmap_bytes(memslot);
-	nr_dirty_pages = memslot->nr_dirty_pages;
 
-	/* If nothing is dirty, don't bother messing with page tables. */
-	if (nr_dirty_pages) {
-		struct kvm_memslots *slots, *old_slots;
-		unsigned long *dirty_bitmap, *dirty_bitmap_head;
+	dirty_bitmap_buffer = dirty_bitmap + n / sizeof(long);
+	memset(dirty_bitmap_buffer, 0, n);
 
-		dirty_bitmap = memslot->dirty_bitmap;
-		dirty_bitmap_head = memslot->dirty_bitmap_head;
-		if (dirty_bitmap == dirty_bitmap_head)
-			dirty_bitmap_head += n / sizeof(long);
-		memset(dirty_bitmap_head, 0, n);
+	spin_lock(&kvm->mmu_lock);
 
-		r = -ENOMEM;
-		slots = kmemdup(kvm->memslots, sizeof(*kvm->memslots), GFP_KERNEL);
-		if (!slots)
-			goto out;
+	for (i = 0; i < n / sizeof(long); i++) {
+		unsigned long mask;
+		gfn_t offset;
 
-		memslot = id_to_memslot(slots, log->slot);
-		memslot->nr_dirty_pages = 0;
-		memslot->dirty_bitmap = dirty_bitmap_head;
-		update_memslots(slots, NULL);
+		if (!dirty_bitmap[i])
+			continue;
 
-		old_slots = kvm->memslots;
-		rcu_assign_pointer(kvm->memslots, slots);
-		synchronize_srcu_expedited(&kvm->srcu);
-		kfree(old_slots);
+		is_dirty = true;
 
-		write_protect_slot(kvm, memslot, dirty_bitmap, nr_dirty_pages);
+		mask = xchg(&dirty_bitmap[i], 0);
+		dirty_bitmap_buffer[i] = mask;
 
-		r = -EFAULT;
-		if (copy_to_user(log->dirty_bitmap, dirty_bitmap, n))
-			goto out;
-	} else {
-		r = -EFAULT;
-		if (clear_user(log->dirty_bitmap, n))
-			goto out;
+		offset = i * BITS_PER_LONG;
+		kvm_mmu_write_protect_pt_masked(kvm, memslot, offset, mask);
 	}
+	if (is_dirty)
+		kvm_flush_remote_tlbs(kvm);
+
+	spin_unlock(&kvm->mmu_lock);
+
+	r = -EFAULT;
+	if (copy_to_user(log->dirty_bitmap, dirty_bitmap_buffer, n))
+		goto out;
 
 	r = 0;
 out:
@@ -3728,9 +3718,8 @@ struct read_write_emulator_ops {
 static int read_prepare(struct kvm_vcpu *vcpu, void *val, int bytes)
 {
 	if (vcpu->mmio_read_completed) {
-		memcpy(val, vcpu->mmio_data, bytes);
 		trace_kvm_mmio(KVM_TRACE_MMIO_READ, bytes,
-			       vcpu->mmio_phys_addr, *(u64 *)val);
+			       vcpu->mmio_fragments[0].gpa, *(u64 *)val);
 		vcpu->mmio_read_completed = 0;
 		return 1;
 	}
@@ -3766,8 +3755,9 @@ static int read_exit_mmio(struct kvm_vcpu *vcpu, gpa_t gpa,
 static int write_exit_mmio(struct kvm_vcpu *vcpu, gpa_t gpa,
 			   void *val, int bytes)
 {
-	memcpy(vcpu->mmio_data, val, bytes);
-	memcpy(vcpu->run->mmio.data, vcpu->mmio_data, 8);
+	struct kvm_mmio_fragment *frag = &vcpu->mmio_fragments[0];
+
+	memcpy(vcpu->run->mmio.data, frag->data, frag->len);
 	return X86EMUL_CONTINUE;
 }
 
@@ -3794,10 +3784,7 @@ static int emulator_read_write_onepage(unsigned long addr, void *val,
 	gpa_t gpa;
 	int handled, ret;
 	bool write = ops->write;
-
-	if (ops->read_write_prepare &&
-		  ops->read_write_prepare(vcpu, val, bytes))
-		return X86EMUL_CONTINUE;
+	struct kvm_mmio_fragment *frag;
 
 	ret = vcpu_mmio_gva_to_gpa(vcpu, addr, &gpa, exception, write);
 
@@ -3823,15 +3810,19 @@ mmio:
 	bytes -= handled;
 	val += handled;
 
-	vcpu->mmio_needed = 1;
-	vcpu->run->exit_reason = KVM_EXIT_MMIO;
-	vcpu->run->mmio.phys_addr = vcpu->mmio_phys_addr = gpa;
-	vcpu->mmio_size = bytes;
-	vcpu->run->mmio.len = min(vcpu->mmio_size, 8);
-	vcpu->run->mmio.is_write = vcpu->mmio_is_write = write;
-	vcpu->mmio_index = 0;
+	while (bytes) {
+		unsigned now = min(bytes, 8U);
 
-	return ops->read_write_exit_mmio(vcpu, gpa, val, bytes);
+		frag = &vcpu->mmio_fragments[vcpu->mmio_nr_fragments++];
+		frag->gpa = gpa;
+		frag->data = val;
+		frag->len = now;
+
+		gpa += now;
+		val += now;
+		bytes -= now;
+	}
+	return X86EMUL_CONTINUE;
 }
 
 int emulator_read_write(struct x86_emulate_ctxt *ctxt, unsigned long addr,
@@ -3840,10 +3831,18 @@ int emulator_read_write(struct x86_emulate_ctxt *ctxt, unsigned long addr,
 			struct read_write_emulator_ops *ops)
 {
 	struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt);
+	gpa_t gpa;
+	int rc;
+
+	if (ops->read_write_prepare &&
+		  ops->read_write_prepare(vcpu, val, bytes))
+		return X86EMUL_CONTINUE;
+
+	vcpu->mmio_nr_fragments = 0;
 
 	/* Crossing a page boundary? */
 	if (((addr + bytes - 1) ^ addr) & PAGE_MASK) {
-		int rc, now;
+		int now;
 
 		now = -addr & ~PAGE_MASK;
 		rc = emulator_read_write_onepage(addr, val, now, exception,
@@ -3856,8 +3855,25 @@ int emulator_read_write(struct x86_emulate_ctxt *ctxt, unsigned long addr,
 		bytes -= now;
 	}
 
-	return emulator_read_write_onepage(addr, val, bytes, exception,
-					   vcpu, ops);
+	rc = emulator_read_write_onepage(addr, val, bytes, exception,
+					 vcpu, ops);
+	if (rc != X86EMUL_CONTINUE)
+		return rc;
+
+	if (!vcpu->mmio_nr_fragments)
+		return rc;
+
+	gpa = vcpu->mmio_fragments[0].gpa;
+
+	vcpu->mmio_needed = 1;
+	vcpu->mmio_cur_fragment = 0;
+
+	vcpu->run->mmio.len = vcpu->mmio_fragments[0].len;
+	vcpu->run->mmio.is_write = vcpu->mmio_is_write = ops->write;
+	vcpu->run->exit_reason = KVM_EXIT_MMIO;
+	vcpu->run->mmio.phys_addr = gpa;
+
+	return ops->read_write_exit_mmio(vcpu, gpa, val, bytes);
 }
 
 static int emulator_read_emulated(struct x86_emulate_ctxt *ctxt,
@@ -5263,10 +5279,6 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 			kvm_deliver_pmi(vcpu);
 	}
 
-	r = kvm_mmu_reload(vcpu);
-	if (unlikely(r))
-		goto out;
-
 	if (kvm_check_request(KVM_REQ_EVENT, vcpu) || req_int_win) {
 		inject_pending_event(vcpu);
 
@@ -5282,6 +5294,12 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 		}
 	}
 
+	r = kvm_mmu_reload(vcpu);
+	if (unlikely(r)) {
+		kvm_x86_ops->cancel_injection(vcpu);
+		goto out;
+	}
+
 	preempt_disable();
 
 	kvm_x86_ops->prepare_guest_switch(vcpu);
@@ -5456,33 +5474,55 @@ static int __vcpu_run(struct kvm_vcpu *vcpu)
 	return r;
 }
 
+/*
+ * Implements the following, as a state machine:
+ *
+ * read:
+ *   for each fragment
+ *     write gpa, len
+ *     exit
+ *     copy data
+ *   execute insn
+ *
+ * write:
+ *   for each fragment
+ *      write gpa, len
+ *      copy data
+ *      exit
+ */
 static int complete_mmio(struct kvm_vcpu *vcpu)
 {
 	struct kvm_run *run = vcpu->run;
+	struct kvm_mmio_fragment *frag;
 	int r;
 
 	if (!(vcpu->arch.pio.count || vcpu->mmio_needed))
 		return 1;
 
 	if (vcpu->mmio_needed) {
-		vcpu->mmio_needed = 0;
+		/* Complete previous fragment */
+		frag = &vcpu->mmio_fragments[vcpu->mmio_cur_fragment++];
 		if (!vcpu->mmio_is_write)
-			memcpy(vcpu->mmio_data + vcpu->mmio_index,
-			       run->mmio.data, 8);
-		vcpu->mmio_index += 8;
-		if (vcpu->mmio_index < vcpu->mmio_size) {
-			run->exit_reason = KVM_EXIT_MMIO;
-			run->mmio.phys_addr = vcpu->mmio_phys_addr + vcpu->mmio_index;
-			memcpy(run->mmio.data, vcpu->mmio_data + vcpu->mmio_index, 8);
-			run->mmio.len = min(vcpu->mmio_size - vcpu->mmio_index, 8);
-			run->mmio.is_write = vcpu->mmio_is_write;
-			vcpu->mmio_needed = 1;
-			return 0;
+			memcpy(frag->data, run->mmio.data, frag->len);
+		if (vcpu->mmio_cur_fragment == vcpu->mmio_nr_fragments) {
+			vcpu->mmio_needed = 0;
+			if (vcpu->mmio_is_write)
+				return 1;
+			vcpu->mmio_read_completed = 1;
+			goto done;
 		}
+		/* Initiate next fragment */
+		++frag;
+		run->exit_reason = KVM_EXIT_MMIO;
+		run->mmio.phys_addr = frag->gpa;
 		if (vcpu->mmio_is_write)
-			return 1;
-		vcpu->mmio_read_completed = 1;
+			memcpy(run->mmio.data, frag->data, frag->len);
+		run->mmio.len = frag->len;
+		run->mmio.is_write = vcpu->mmio_is_write;
+		return 0;
+
 	}
+done:
 	vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu);
 	r = emulate_instruction(vcpu, EMULTYPE_NO_DECODE);
 	srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx);
@@ -6399,21 +6439,9 @@ int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu)
 		 kvm_cpu_has_interrupt(vcpu));
 }
 
-void kvm_vcpu_kick(struct kvm_vcpu *vcpu)
+int kvm_arch_vcpu_should_kick(struct kvm_vcpu *vcpu)
 {
-	int me;
-	int cpu = vcpu->cpu;
-
-	if (waitqueue_active(&vcpu->wq)) {
-		wake_up_interruptible(&vcpu->wq);
-		++vcpu->stat.halt_wakeup;
-	}
-
-	me = get_cpu();
-	if (cpu != me && (unsigned)cpu < nr_cpu_ids && cpu_online(cpu))
-		if (kvm_vcpu_exiting_guest_mode(vcpu) == IN_GUEST_MODE)
-			smp_send_reschedule(cpu);
-	put_cpu();
+	return kvm_vcpu_exiting_guest_mode(vcpu) == IN_GUEST_MODE;
 }
 
 int kvm_arch_interrupt_allowed(struct kvm_vcpu *vcpu)