Merge tag 'kvm-3.7-1' of git://git.kernel.org/pub/scm/virt/kvm/kvm

Pull KVM updates from Avi Kivity:
 "Highlights of the changes for this release include support for vfio
  level triggered interrupts, improved big real mode support on older
  Intels, a streamlines guest page table walker, guest APIC speedups,
  PIO optimizations, better overcommit handling, and read-only memory."

* tag 'kvm-3.7-1' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (138 commits)
  KVM: s390: Fix vcpu_load handling in interrupt code
  KVM: x86: Fix guest debug across vcpu INIT reset
  KVM: Add resampling irqfds for level triggered interrupts
  KVM: optimize apic interrupt delivery
  KVM: MMU: Eliminate pointless temporary 'ac'
  KVM: MMU: Avoid access/dirty update loop if all is well
  KVM: MMU: Eliminate eperm temporary
  KVM: MMU: Optimize is_last_gpte()
  KVM: MMU: Simplify walk_addr_generic() loop
  KVM: MMU: Optimize pte permission checks
  KVM: MMU: Update accessed and dirty bits after guest pagetable walk
  KVM: MMU: Move gpte_access() out of paging_tmpl.h
  KVM: MMU: Optimize gpte_access() slightly
  KVM: MMU: Push clean gpte write protection out of gpte_access()
  KVM: clarify kvmclock documentation
  KVM: make processes waiting on vcpu mutex killable
  KVM: SVM: Make use of asm.h
  KVM: VMX: Make use of asm.h
  KVM: VMX: Make lto-friendly
  KVM: x86: lapic: Clean up find_highest_vector() and count_vectors()
  ...

Conflicts:
	arch/s390/include/asm/processor.h
	arch/x86/kvm/i8259.c

Documentation/virtual/kvm/api.txt

@@ -857,7 +857,8 @@ struct kvm_userspace_memory_region {
 };
 
 /* for kvm_memory_region::flags */
-#define KVM_MEM_LOG_DIRTY_PAGES  1UL
+#define KVM_MEM_LOG_DIRTY_PAGES	(1UL << 0)
+#define KVM_MEM_READONLY	(1UL << 1)
 
 This ioctl allows the user to create or modify a guest physical memory
 slot.  When changing an existing slot, it may be moved in the guest
@@ -873,14 +874,17 @@ It is recommended that the lower 21 bits of guest_phys_addr and userspace_addr
 be identical.  This allows large pages in the guest to be backed by large
 pages in the host.
 
-The flags field supports just one flag, KVM_MEM_LOG_DIRTY_PAGES, which
+The flags field supports two flag, KVM_MEM_LOG_DIRTY_PAGES, which instructs
-instructs kvm to keep track of writes to memory within the slot.  See
+kvm to keep track of writes to memory within the slot.  See KVM_GET_DIRTY_LOG
-the KVM_GET_DIRTY_LOG ioctl.
+ioctl.  The KVM_CAP_READONLY_MEM capability indicates the availability of the
+KVM_MEM_READONLY flag.  When this flag is set for a memory region, KVM only
+allows read accesses.  Writes will be posted to userspace as KVM_EXIT_MMIO
+exits.
 
-When the KVM_CAP_SYNC_MMU capability, changes in the backing of the memory
+When the KVM_CAP_SYNC_MMU capability is available, changes in the backing of
-region are automatically reflected into the guest.  For example, an mmap()
+the memory region are automatically reflected into the guest.  For example, an
-that affects the region will be made visible immediately.  Another example
+mmap() that affects the region will be made visible immediately.  Another
-is madvise(MADV_DROP).
+example is madvise(MADV_DROP).
 
 It is recommended to use this API instead of the KVM_SET_MEMORY_REGION ioctl.
 The KVM_SET_MEMORY_REGION does not allow fine grained control over memory
@@ -1946,6 +1950,19 @@ the guest using the specified gsi pin.  The irqfd is removed using
 the KVM_IRQFD_FLAG_DEASSIGN flag, specifying both kvm_irqfd.fd
 and kvm_irqfd.gsi.
 
+With KVM_CAP_IRQFD_RESAMPLE, KVM_IRQFD supports a de-assert and notify
+mechanism allowing emulation of level-triggered, irqfd-based
+interrupts.  When KVM_IRQFD_FLAG_RESAMPLE is set the user must pass an
+additional eventfd in the kvm_irqfd.resamplefd field.  When operating
+in resample mode, posting of an interrupt through kvm_irq.fd asserts
+the specified gsi in the irqchip.  When the irqchip is resampled, such
+as from an EOI, the gsi is de-asserted and the user is notifed via
+kvm_irqfd.resamplefd.  It is the user's responsibility to re-queue
+the interrupt if the device making use of it still requires service.
+Note that closing the resamplefd is not sufficient to disable the
+irqfd.  The KVM_IRQFD_FLAG_RESAMPLE is only necessary on assignment
+and need not be specified with KVM_IRQFD_FLAG_DEASSIGN.
+
 4.76 KVM_PPC_ALLOCATE_HTAB
 
 Capability: KVM_CAP_PPC_ALLOC_HTAB

Documentation/virtual/kvm/hypercalls.txt

@@ -0,0 +1,66 @@
+Linux KVM Hypercall:
+===================
+X86:
+ KVM Hypercalls have a three-byte sequence of either the vmcall or the vmmcall
+ instruction. The hypervisor can replace it with instructions that are
+ guaranteed to be supported.
+
+ Up to four arguments may be passed in rbx, rcx, rdx, and rsi respectively.
+ The hypercall number should be placed in rax and the return value will be
+ placed in rax.  No other registers will be clobbered unless explicitly stated
+ by the particular hypercall.
+
+S390:
+  R2-R7 are used for parameters 1-6. In addition, R1 is used for hypercall
+  number. The return value is written to R2.
+
+  S390 uses diagnose instruction as hypercall (0x500) along with hypercall
+  number in R1.
+
+ PowerPC:
+  It uses R3-R10 and hypercall number in R11. R4-R11 are used as output registers.
+  Return value is placed in R3.
+
+  KVM hypercalls uses 4 byte opcode, that are patched with 'hypercall-instructions'
+  property inside the device tree's /hypervisor node.
+  For more information refer to Documentation/virtual/kvm/ppc-pv.txt
+
+KVM Hypercalls Documentation
+===========================
+The template for each hypercall is:
+1. Hypercall name.
+2. Architecture(s)
+3. Status (deprecated, obsolete, active)
+4. Purpose
+
+1. KVM_HC_VAPIC_POLL_IRQ
+------------------------
+Architecture: x86
+Status: active
+Purpose: Trigger guest exit so that the host can check for pending
+interrupts on reentry.
+
+2. KVM_HC_MMU_OP
+------------------------
+Architecture: x86
+Status: deprecated.
+Purpose: Support MMU operations such as writing to PTE,
+flushing TLB, release PT.
+
+3. KVM_HC_FEATURES
+------------------------
+Architecture: PPC
+Status: active
+Purpose: Expose hypercall availability to the guest. On x86 platforms, cpuid
+used to enumerate which hypercalls are available. On PPC, either device tree
+based lookup ( which is also what EPAPR dictates) OR KVM specific enumeration
+mechanism (which is this hypercall) can be used.
+
+4. KVM_HC_PPC_MAP_MAGIC_PAGE
+------------------------
+Architecture: PPC
+Status: active
+Purpose: To enable communication between the hypervisor and guest there is a
+shared page that contains parts of supervisor visible register state.
+The guest can map this shared page to access its supervisor register through
+memory using this hypercall.

Documentation/virtual/kvm/msr.txt

@@ -34,9 +34,12 @@ MSR_KVM_WALL_CLOCK_NEW:   0x4b564d00
 		time information and check that they are both equal and even.
 		An odd version indicates an in-progress update.
 
-		sec: number of seconds for wallclock.
+		sec: number of seconds for wallclock at time of boot.
 
-		nsec: number of nanoseconds for wallclock.
+		nsec: number of nanoseconds for wallclock at time of boot.
+
+	In order to get the current wallclock time, the system_time from
+	MSR_KVM_SYSTEM_TIME_NEW needs to be added.
 
 	Note that although MSRs are per-CPU entities, the effect of this
 	particular MSR is global.
@@ -82,20 +85,25 @@ MSR_KVM_SYSTEM_TIME_NEW:  0x4b564d01
 		time at the time this structure was last updated. Unit is
 		nanoseconds.
 
-		tsc_to_system_mul: a function of the tsc frequency. One has
+		tsc_to_system_mul: multiplier to be used when converting
-		to multiply any tsc-related quantity by this value to get
+		tsc-related quantity to nanoseconds
-		a value in nanoseconds, besides dividing by 2^tsc_shift
 
-		tsc_shift: cycle to nanosecond divider, as a power of two, to
+		tsc_shift: shift to be used when converting tsc-related
-		allow for shift rights. One has to shift right any tsc-related
+		quantity to nanoseconds. This shift will ensure that
-		quantity by this value to get a value in nanoseconds, besides
+		multiplication with tsc_to_system_mul does not overflow.
-		multiplying by tsc_to_system_mul.
+		A positive value denotes a left shift, a negative value
+		a right shift.
 
-		With this information, guests can derive per-CPU time by
+		The conversion from tsc to nanoseconds involves an additional
-		doing:
+		right shift by 32 bits. With this information, guests can
+		derive per-CPU time by doing:
 
 			time = (current_tsc - tsc_timestamp)
-			time = (time * tsc_to_system_mul) >> tsc_shift
+			if (tsc_shift >= 0)
+				time <<= tsc_shift;
+			else
+				time >>= -tsc_shift;
+			time = (time * tsc_to_system_mul) >> 32
 			time = time + system_time
 
 		flags: bits in this field indicate extended capabilities

Documentation/virtual/kvm/ppc-pv.txt

@@ -174,3 +174,25 @@ following:
 That way we can inject an arbitrary amount of code as replacement for a single
 instruction. This allows us to check for pending interrupts when setting EE=1
 for example.
+
+Hypercall ABIs in KVM on PowerPC
+=================================
+1) KVM hypercalls (ePAPR)
+
+These are ePAPR compliant hypercall implementation (mentioned above). Even
+generic hypercalls are implemented here, like the ePAPR idle hcall. These are
+available on all targets.
+
+2) PAPR hypercalls
+
+PAPR hypercalls are needed to run server PowerPC PAPR guests (-M pseries in QEMU).
+These are the same hypercalls that pHyp, the POWER hypervisor implements. Some of
+them are handled in the kernel, some are handled in user space. This is only
+available on book3s_64.
+
+3) OSI hypercalls
+
+Mac-on-Linux is another user of KVM on PowerPC, which has its own hypercall (long
+before KVM). This is supported to maintain compatibility. All these hypercalls get
+forwarded to user space. This is only useful on book3s_32, but can be used with
+book3s_64 as well.

arch/ia64/kvm/kvm-ia64.c

@@ -924,6 +924,16 @@ int kvm_arch_vcpu_ioctl_set_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
 	return 0;
 }
 
+int kvm_vm_ioctl_irq_line(struct kvm *kvm, struct kvm_irq_level *irq_event)
+{
+	if (!irqchip_in_kernel(kvm))
+		return -ENXIO;
+
+	irq_event->status = kvm_set_irq(kvm, KVM_USERSPACE_IRQ_SOURCE_ID,
+					irq_event->irq, irq_event->level);
+	return 0;
+}
+
 long kvm_arch_vm_ioctl(struct file *filp,
 		unsigned int ioctl, unsigned long arg)
 {
@@ -963,29 +973,6 @@ long kvm_arch_vm_ioctl(struct file *filp,
 			goto out;
 		}
 		break;
-	case KVM_IRQ_LINE_STATUS:
-	case KVM_IRQ_LINE: {
-		struct kvm_irq_level irq_event;
-
-		r = -EFAULT;
-		if (copy_from_user(&irq_event, argp, sizeof irq_event))
-			goto out;
-		r = -ENXIO;
-		if (irqchip_in_kernel(kvm)) {
-			__s32 status;
-			status = kvm_set_irq(kvm, KVM_USERSPACE_IRQ_SOURCE_ID,
-				    irq_event.irq, irq_event.level);
-			if (ioctl == KVM_IRQ_LINE_STATUS) {
-				r = -EFAULT;
-				irq_event.status = status;
-				if (copy_to_user(argp, &irq_event,
-							sizeof irq_event))
-					goto out;
-			}
-			r = 0;
-		}
-		break;
-		}
 	case KVM_GET_IRQCHIP: {
 		/* 0: PIC master, 1: PIC slave, 2: IOAPIC */
 		struct kvm_irqchip chip;
@@ -1626,11 +1613,17 @@ void kvm_arch_commit_memory_region(struct kvm *kvm,
 	return;
 }
 
-void kvm_arch_flush_shadow(struct kvm *kvm)
+void kvm_arch_flush_shadow_all(struct kvm *kvm)
 {
 	kvm_flush_remote_tlbs(kvm);
 }
 
+void kvm_arch_flush_shadow_memslot(struct kvm *kvm,
+				   struct kvm_memory_slot *slot)
+{
+	kvm_arch_flush_shadow_all();
+}
+
 long kvm_arch_dev_ioctl(struct file *filp,
 			unsigned int ioctl, unsigned long arg)
 {

arch/powerpc/include/asm/kvm_host.h

@@ -53,6 +53,8 @@
 
 struct kvm;
 extern int kvm_unmap_hva(struct kvm *kvm, unsigned long hva);
+extern int kvm_unmap_hva_range(struct kvm *kvm,
+			       unsigned long start, unsigned long end);
 extern int kvm_age_hva(struct kvm *kvm, unsigned long hva);
 extern int kvm_test_age_hva(struct kvm *kvm, unsigned long hva);
 extern void kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte);
@@ -220,6 +222,7 @@ struct revmap_entry {
 #define KVMPPC_GOT_PAGE		0x80
 
 struct kvm_arch_memory_slot {
+	unsigned long *rmap;
 };
 
 struct kvm_arch {

arch/powerpc/kvm/44x_tlb.c

@@ -319,7 +319,6 @@ void kvmppc_mmu_map(struct kvm_vcpu *vcpu, u64 gvaddr, gpa_t gpaddr,
 	if (is_error_page(new_page)) {
 		printk(KERN_ERR "Couldn't get guest page for gfn %llx!\n",
 			(unsigned long long)gfn);
-		kvm_release_page_clean(new_page);
 		return;
 	}
 	hpaddr = page_to_phys(new_page);

arch/powerpc/kvm/book3s_64_mmu_hv.c

@@ -705,7 +705,7 @@ int kvmppc_book3s_hv_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu,
 		goto out_unlock;
 	hpte[0] = (hpte[0] & ~HPTE_V_ABSENT) | HPTE_V_VALID;
 
-	rmap = &memslot->rmap[gfn - memslot->base_gfn];
+	rmap = &memslot->arch.rmap[gfn - memslot->base_gfn];
 	lock_rmap(rmap);
 
 	/* Check if we might have been invalidated; let the guest retry if so */
@@ -756,8 +756,11 @@ int kvmppc_book3s_hv_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu,
 	goto out_put;
 }
 
-static int kvm_handle_hva(struct kvm *kvm, unsigned long hva,
+static int kvm_handle_hva_range(struct kvm *kvm,
-			  int (*handler)(struct kvm *kvm, unsigned long *rmapp,
+				unsigned long start,
+				unsigned long end,
+				int (*handler)(struct kvm *kvm,
+					       unsigned long *rmapp,
 					       unsigned long gfn))
 {
 	int ret;
@@ -767,15 +770,25 @@ static int kvm_handle_hva(struct kvm *kvm, unsigned long hva,
 
 	slots = kvm_memslots(kvm);
 	kvm_for_each_memslot(memslot, slots) {
-		unsigned long start = memslot->userspace_addr;
+		unsigned long hva_start, hva_end;
-		unsigned long end;
+		gfn_t gfn, gfn_end;
 
-		end = start + (memslot->npages << PAGE_SHIFT);
+		hva_start = max(start, memslot->userspace_addr);
-		if (hva >= start && hva < end) {
+		hva_end = min(end, memslot->userspace_addr +
-			gfn_t gfn_offset = (hva - start) >> PAGE_SHIFT;
+					(memslot->npages << PAGE_SHIFT));
+		if (hva_start >= hva_end)
+			continue;
+		/*
+		 * {gfn(page) | page intersects with [hva_start, hva_end)} =
+		 * {gfn, gfn+1, ..., gfn_end-1}.
+		 */
+		gfn = hva_to_gfn_memslot(hva_start, memslot);
+		gfn_end = hva_to_gfn_memslot(hva_end + PAGE_SIZE - 1, memslot);
 
-			ret = handler(kvm, &memslot->rmap[gfn_offset],
+		for (; gfn < gfn_end; ++gfn) {
-				      memslot->base_gfn + gfn_offset);
+			gfn_t gfn_offset = gfn - memslot->base_gfn;
+
+			ret = handler(kvm, &memslot->arch.rmap[gfn_offset], gfn);
 			retval |= ret;
 		}
 	}
@@ -783,6 +796,13 @@ static int kvm_handle_hva(struct kvm *kvm, unsigned long hva,
 	return retval;
 }
 
+static int kvm_handle_hva(struct kvm *kvm, unsigned long hva,
+			  int (*handler)(struct kvm *kvm, unsigned long *rmapp,
+					 unsigned long gfn))
+{
+	return kvm_handle_hva_range(kvm, hva, hva + 1, handler);
+}
+
 static int kvm_unmap_rmapp(struct kvm *kvm, unsigned long *rmapp,
 			   unsigned long gfn)
 {
@@ -850,6 +870,13 @@ int kvm_unmap_hva(struct kvm *kvm, unsigned long hva)
 	return 0;
 }
 
+int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end)
+{
+	if (kvm->arch.using_mmu_notifiers)
+		kvm_handle_hva_range(kvm, start, end, kvm_unmap_rmapp);
+	return 0;
+}
+
 static int kvm_age_rmapp(struct kvm *kvm, unsigned long *rmapp,
 			 unsigned long gfn)
 {
@@ -1009,7 +1036,7 @@ long kvmppc_hv_get_dirty_log(struct kvm *kvm, struct kvm_memory_slot *memslot)
 	unsigned long *rmapp, *map;
 
 	preempt_disable();
-	rmapp = memslot->rmap;
+	rmapp = memslot->arch.rmap;
 	map = memslot->dirty_bitmap;
 	for (i = 0; i < memslot->npages; ++i) {
 		if (kvm_test_clear_dirty(kvm, rmapp))

arch/powerpc/kvm/book3s_hv_rm_mmu.c

@@ -84,7 +84,7 @@ static void remove_revmap_chain(struct kvm *kvm, long pte_index,
 	if (!memslot || (memslot->flags & KVM_MEMSLOT_INVALID))
 		return;
 
-	rmap = real_vmalloc_addr(&memslot->rmap[gfn - memslot->base_gfn]);
+	rmap = real_vmalloc_addr(&memslot->arch.rmap[gfn - memslot->base_gfn]);
 	lock_rmap(rmap);
 
 	head = *rmap & KVMPPC_RMAP_INDEX;
@@ -180,7 +180,7 @@ long kvmppc_h_enter(struct kvm_vcpu *vcpu, unsigned long flags,
 	if (!slot_is_aligned(memslot, psize))
 		return H_PARAMETER;
 	slot_fn = gfn - memslot->base_gfn;
-	rmap = &memslot->rmap[slot_fn];
+	rmap = &memslot->arch.rmap[slot_fn];
 
 	if (!kvm->arch.using_mmu_notifiers) {
 		physp = kvm->arch.slot_phys[memslot->id];
@@ -197,7 +197,7 @@ long kvmppc_h_enter(struct kvm_vcpu *vcpu, unsigned long flags,
 		pa &= PAGE_MASK;
 	} else {
 		/* Translate to host virtual address */
-		hva = gfn_to_hva_memslot(memslot, gfn);
+		hva = __gfn_to_hva_memslot(memslot, gfn);
 
 		/* Look up the Linux PTE for the backing page */
 		pte_size = psize;

arch/powerpc/kvm/book3s_pr.c

@@ -242,10 +242,8 @@ static void kvmppc_patch_dcbz(struct kvm_vcpu *vcpu, struct kvmppc_pte *pte)
 	int i;
 
 	hpage = gfn_to_page(vcpu->kvm, pte->raddr >> PAGE_SHIFT);
-	if (is_error_page(hpage)) {
+	if (is_error_page(hpage))
-		kvm_release_page_clean(hpage);
 		return;
-	}
 
 	hpage_offset = pte->raddr & ~PAGE_MASK;
 	hpage_offset &= ~0xFFFULL;

arch/powerpc/kvm/e500_tlb.c

@@ -520,11 +520,10 @@ static inline void kvmppc_e500_shadow_map(struct kvmppc_vcpu_e500 *vcpu_e500,
 
 	if (likely(!pfnmap)) {
 		unsigned long tsize_pages = 1 << (tsize + 10 - PAGE_SHIFT);
-		pfn = gfn_to_pfn_memslot(vcpu_e500->vcpu.kvm, slot, gfn);
+		pfn = gfn_to_pfn_memslot(slot, gfn);
 		if (is_error_pfn(pfn)) {
 			printk(KERN_ERR "Couldn't get real page for gfn %lx!\n",
 					(long)gfn);
-			kvm_release_pfn_clean(pfn);
 			return;
 		}
 

arch/powerpc/kvm/powerpc.c

@@ -302,10 +302,18 @@ long kvm_arch_dev_ioctl(struct file *filp,
 void kvm_arch_free_memslot(struct kvm_memory_slot *free,
 			   struct kvm_memory_slot *dont)
 {
+	if (!dont || free->arch.rmap != dont->arch.rmap) {
+		vfree(free->arch.rmap);
+		free->arch.rmap = NULL;
+	}
 }
 
 int kvm_arch_create_memslot(struct kvm_memory_slot *slot, unsigned long npages)
 {
+	slot->arch.rmap = vzalloc(npages * sizeof(*slot->arch.rmap));
+	if (!slot->arch.rmap)
+		return -ENOMEM;
+
 	return 0;
 }
 
@@ -326,8 +334,12 @@ void kvm_arch_commit_memory_region(struct kvm *kvm,
 	kvmppc_core_commit_memory_region(kvm, mem);
 }
 
+void kvm_arch_flush_shadow_all(struct kvm *kvm)
+{
+}
 
-void kvm_arch_flush_shadow(struct kvm *kvm)
+void kvm_arch_flush_shadow_memslot(struct kvm *kvm,
+				   struct kvm_memory_slot *slot)
 {
 }
 

arch/s390/include/asm/processor.h

@@ -159,6 +159,7 @@ extern unsigned long thread_saved_pc(struct task_struct *t);
 
 extern void show_code(struct pt_regs *regs);
 extern void print_fn_code(unsigned char *code, unsigned long len);
+extern int insn_to_mnemonic(unsigned char *instruction, char buf[8]);
 
 unsigned long get_wchan(struct task_struct *p);
 #define task_pt_regs(tsk) ((struct pt_regs *) \

arch/s390/kernel/dis.c

@@ -1501,6 +1501,33 @@ static struct insn *find_insn(unsigned char *code)
 	return NULL;
 }
 
+/**
+ * insn_to_mnemonic - decode an s390 instruction
+ * @instruction: instruction to decode
+ * @buf: buffer to fill with mnemonic
+ *
+ * Decode the instruction at @instruction and store the corresponding
+ * mnemonic into @buf.
+ * @buf is left unchanged if the instruction could not be decoded.
+ * Returns:
+ *  %0 on success, %-ENOENT if the instruction was not found.
+ */
+int insn_to_mnemonic(unsigned char *instruction, char buf[8])
+{
+	struct insn *insn;
+
+	insn = find_insn(instruction);
+	if (!insn)
+		return -ENOENT;
+	if (insn->name[0] == '\0')
+		snprintf(buf, sizeof(buf), "%s",
+			 long_insn_name[(int) insn->name[1]]);
+	else
+		snprintf(buf, sizeof(buf), "%.5s", insn->name);
+	return 0;
+}
+EXPORT_SYMBOL_GPL(insn_to_mnemonic);
+
 static int print_insn(char *buffer, unsigned char *code, unsigned long addr)
 {
 	struct insn *insn;

arch/s390/kvm/Kconfig

@@ -21,6 +21,7 @@ config KVM
 	depends on HAVE_KVM && EXPERIMENTAL
 	select PREEMPT_NOTIFIERS
 	select ANON_INODES
+	select HAVE_KVM_CPU_RELAX_INTERCEPT
 	---help---
 	  Support hosting paravirtualized guest machines using the SIE
 	  virtualization capability on the mainframe. This should work

arch/s390/kvm/diag.c

@@ -14,6 +14,8 @@
 #include <linux/kvm.h>
 #include <linux/kvm_host.h>
 #include "kvm-s390.h"
+#include "trace.h"
+#include "trace-s390.h"
 
 static int diag_release_pages(struct kvm_vcpu *vcpu)
 {
@@ -98,6 +100,7 @@ static int __diag_ipl_functions(struct kvm_vcpu *vcpu)
 	vcpu->run->exit_reason = KVM_EXIT_S390_RESET;
 	VCPU_EVENT(vcpu, 3, "requesting userspace resets %llx",
 	  vcpu->run->s390_reset_flags);
+	trace_kvm_s390_request_resets(vcpu->run->s390_reset_flags);
 	return -EREMOTE;
 }
 
@@ -105,6 +108,7 @@ int kvm_s390_handle_diag(struct kvm_vcpu *vcpu)
 {
 	int code = (vcpu->arch.sie_block->ipb & 0xfff0000) >> 16;
 
+	trace_kvm_s390_handle_diag(vcpu, code);
 	switch (code) {
 	case 0x10:
 		return diag_release_pages(vcpu);

arch/s390/kvm/intercept.c

@@ -19,6 +19,8 @@
 
 #include "kvm-s390.h"
 #include "gaccess.h"
+#include "trace.h"
+#include "trace-s390.h"
 
 static int handle_lctlg(struct kvm_vcpu *vcpu)
 {
@@ -45,6 +47,7 @@ static int handle_lctlg(struct kvm_vcpu *vcpu)
 
 	VCPU_EVENT(vcpu, 5, "lctlg r1:%x, r3:%x,b2:%x,d2:%x", reg1, reg3, base2,
 		   disp2);
+	trace_kvm_s390_handle_lctl(vcpu, 1, reg1, reg3, useraddr);
 
 	do {
 		rc = get_guest_u64(vcpu, useraddr,
@@ -82,6 +85,7 @@ static int handle_lctl(struct kvm_vcpu *vcpu)
 
 	VCPU_EVENT(vcpu, 5, "lctl r1:%x, r3:%x,b2:%x,d2:%x", reg1, reg3, base2,
 		   disp2);
+	trace_kvm_s390_handle_lctl(vcpu, 0, reg1, reg3, useraddr);
 
 	reg = reg1;
 	do {
@@ -135,6 +139,8 @@ static int handle_stop(struct kvm_vcpu *vcpu)
 	vcpu->stat.exit_stop_request++;
 	spin_lock_bh(&vcpu->arch.local_int.lock);
 
+	trace_kvm_s390_stop_request(vcpu->arch.local_int.action_bits);
+
 	if (vcpu->arch.local_int.action_bits & ACTION_RELOADVCPU_ON_STOP) {
 		vcpu->arch.local_int.action_bits &= ~ACTION_RELOADVCPU_ON_STOP;
 		rc = SIE_INTERCEPT_RERUNVCPU;
@@ -171,6 +177,7 @@ static int handle_validity(struct kvm_vcpu *vcpu)
 	int rc;
 
 	vcpu->stat.exit_validity++;
+	trace_kvm_s390_intercept_validity(vcpu, viwhy);
 	if (viwhy == 0x37) {
 		vmaddr = gmap_fault(vcpu->arch.sie_block->prefix,
 				    vcpu->arch.gmap);
@@ -213,6 +220,9 @@ static int handle_instruction(struct kvm_vcpu *vcpu)
 	intercept_handler_t handler;
 
 	vcpu->stat.exit_instruction++;
+	trace_kvm_s390_intercept_instruction(vcpu,
+					     vcpu->arch.sie_block->ipa,
+					     vcpu->arch.sie_block->ipb);
 	handler = instruction_handlers[vcpu->arch.sie_block->ipa >> 8];
 	if (handler)
 		return handler(vcpu);
@@ -222,6 +232,7 @@ static int handle_instruction(struct kvm_vcpu *vcpu)
 static int handle_prog(struct kvm_vcpu *vcpu)
 {
 	vcpu->stat.exit_program_interruption++;
+	trace_kvm_s390_intercept_prog(vcpu, vcpu->arch.sie_block->iprcc);
 	return kvm_s390_inject_program_int(vcpu, vcpu->arch.sie_block->iprcc);
 }
 

arch/s390/kvm/interrupt.c

@@ -19,6 +19,7 @@
 #include <asm/uaccess.h>
 #include "kvm-s390.h"
 #include "gaccess.h"
+#include "trace-s390.h"
 
 static int psw_extint_disabled(struct kvm_vcpu *vcpu)
 {
@@ -130,6 +131,8 @@ static void __do_deliver_interrupt(struct kvm_vcpu *vcpu,
 	case KVM_S390_INT_EMERGENCY:
 		VCPU_EVENT(vcpu, 4, "%s", "interrupt: sigp emerg");
 		vcpu->stat.deliver_emergency_signal++;
+		trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, inti->type,
+						 inti->emerg.code, 0);
 		rc = put_guest_u16(vcpu, __LC_EXT_INT_CODE, 0x1201);
 		if (rc == -EFAULT)
 			exception = 1;
@@ -152,6 +155,8 @@ static void __do_deliver_interrupt(struct kvm_vcpu *vcpu,
 	case KVM_S390_INT_EXTERNAL_CALL:
 		VCPU_EVENT(vcpu, 4, "%s", "interrupt: sigp ext call");
 		vcpu->stat.deliver_external_call++;
+		trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, inti->type,
+						 inti->extcall.code, 0);
 		rc = put_guest_u16(vcpu, __LC_EXT_INT_CODE, 0x1202);
 		if (rc == -EFAULT)
 			exception = 1;
@@ -175,6 +180,8 @@ static void __do_deliver_interrupt(struct kvm_vcpu *vcpu,
 		VCPU_EVENT(vcpu, 4, "interrupt: sclp parm:%x",
 			   inti->ext.ext_params);
 		vcpu->stat.deliver_service_signal++;
+		trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, inti->type,
+						 inti->ext.ext_params, 0);
 		rc = put_guest_u16(vcpu, __LC_EXT_INT_CODE, 0x2401);
 		if (rc == -EFAULT)
 			exception = 1;
@@ -198,6 +205,9 @@ static void __do_deliver_interrupt(struct kvm_vcpu *vcpu,
 		VCPU_EVENT(vcpu, 4, "interrupt: virtio parm:%x,parm64:%llx",
 			   inti->ext.ext_params, inti->ext.ext_params2);
 		vcpu->stat.deliver_virtio_interrupt++;
+		trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, inti->type,
+						 inti->ext.ext_params,
+						 inti->ext.ext_params2);
 		rc = put_guest_u16(vcpu, __LC_EXT_INT_CODE, 0x2603);
 		if (rc == -EFAULT)
 			exception = 1;
@@ -229,6 +239,8 @@ static void __do_deliver_interrupt(struct kvm_vcpu *vcpu,
 	case KVM_S390_SIGP_STOP:
 		VCPU_EVENT(vcpu, 4, "%s", "interrupt: cpu stop");
 		vcpu->stat.deliver_stop_signal++;
+		trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, inti->type,
+						 0, 0);
 		__set_intercept_indicator(vcpu, inti);
 		break;
 
@@ -236,12 +248,16 @@ static void __do_deliver_interrupt(struct kvm_vcpu *vcpu,
 		VCPU_EVENT(vcpu, 4, "interrupt: set prefix to %x",
 			   inti->prefix.address);
 		vcpu->stat.deliver_prefix_signal++;
+		trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, inti->type,
+						 inti->prefix.address, 0);
 		kvm_s390_set_prefix(vcpu, inti->prefix.address);
 		break;
 
 	case KVM_S390_RESTART:
 		VCPU_EVENT(vcpu, 4, "%s", "interrupt: cpu restart");
 		vcpu->stat.deliver_restart_signal++;
+		trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, inti->type,
+						 0, 0);
 		rc = copy_to_guest(vcpu, offsetof(struct _lowcore,
 		  restart_old_psw), &vcpu->arch.sie_block->gpsw, sizeof(psw_t));
 		if (rc == -EFAULT)
@@ -259,6 +275,8 @@ static void __do_deliver_interrupt(struct kvm_vcpu *vcpu,
 			   inti->pgm.code,
 			   table[vcpu->arch.sie_block->ipa >> 14]);
 		vcpu->stat.deliver_program_int++;
+		trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, inti->type,
+						 inti->pgm.code, 0);
 		rc = put_guest_u16(vcpu, __LC_PGM_INT_CODE, inti->pgm.code);
 		if (rc == -EFAULT)
 			exception = 1;
@@ -405,9 +423,7 @@ no_timer:
 		set_current_state(TASK_INTERRUPTIBLE);
 		spin_unlock_bh(&vcpu->arch.local_int.lock);
 		spin_unlock(&vcpu->arch.local_int.float_int->lock);
-		vcpu_put(vcpu);
 		schedule();
-		vcpu_load(vcpu);
 		spin_lock(&vcpu->arch.local_int.float_int->lock);
 		spin_lock_bh(&vcpu->arch.local_int.lock);
 	}
@@ -515,6 +531,7 @@ int kvm_s390_inject_program_int(struct kvm_vcpu *vcpu, u16 code)
 	inti->pgm.code = code;
 
 	VCPU_EVENT(vcpu, 3, "inject: program check %d (from kernel)", code);
+	trace_kvm_s390_inject_vcpu(vcpu->vcpu_id, inti->type, code, 0, 1);
 	spin_lock_bh(&li->lock);
 	list_add(&inti->list, &li->list);
 	atomic_set(&li->active, 1);
@@ -556,6 +573,8 @@ int kvm_s390_inject_vm(struct kvm *kvm,
 		kfree(inti);
 		return -EINVAL;
 	}
+	trace_kvm_s390_inject_vm(s390int->type, s390int->parm, s390int->parm64,
+				 2);
 
 	mutex_lock(&kvm->lock);
 	fi = &kvm->arch.float_int;
@@ -621,6 +640,8 @@ int kvm_s390_inject_vcpu(struct kvm_vcpu *vcpu,
 		kfree(inti);
 		return -EINVAL;
 	}
+	trace_kvm_s390_inject_vcpu(vcpu->vcpu_id, s390int->type, s390int->parm,
+				   s390int->parm64, 2);
 
 	mutex_lock(&vcpu->kvm->lock);
 	li = &vcpu->arch.local_int;

arch/s390/kvm/kvm-s390.c

@@ -32,6 +32,10 @@
 #include "kvm-s390.h"
 #include "gaccess.h"
 
+#define CREATE_TRACE_POINTS
+#include "trace.h"
+#include "trace-s390.h"
+
 #define VCPU_STAT(x) offsetof(struct kvm_vcpu, stat.x), KVM_STAT_VCPU
 
 struct kvm_stats_debugfs_item debugfs_entries[] = {
@@ -242,6 +246,7 @@ out_err:
 void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu)
 {
 	VCPU_EVENT(vcpu, 3, "%s", "free cpu");
+	trace_kvm_s390_destroy_vcpu(vcpu->vcpu_id);
 	if (!kvm_is_ucontrol(vcpu->kvm)) {
 		clear_bit(63 - vcpu->vcpu_id,
 			  (unsigned long *) &vcpu->kvm->arch.sca->mcn);
@@ -417,6 +422,7 @@ struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm,
 		goto out_free_sie_block;
 	VM_EVENT(kvm, 3, "create cpu %d at %p, sie block at %p", id, vcpu,
 		 vcpu->arch.sie_block);
+	trace_kvm_s390_create_vcpu(id, vcpu, vcpu->arch.sie_block);
 
 	return vcpu;
 out_free_sie_block:
@@ -607,18 +613,22 @@ static int __vcpu_run(struct kvm_vcpu *vcpu)
 	local_irq_enable();
 	VCPU_EVENT(vcpu, 6, "entering sie flags %x",
 		   atomic_read(&vcpu->arch.sie_block->cpuflags));
+	trace_kvm_s390_sie_enter(vcpu,
+				 atomic_read(&vcpu->arch.sie_block->cpuflags));
 	rc = sie64a(vcpu->arch.sie_block, vcpu->run->s.regs.gprs);
 	if (rc) {
 		if (kvm_is_ucontrol(vcpu->kvm)) {
 			rc = SIE_INTERCEPT_UCONTROL;
 		} else {
 			VCPU_EVENT(vcpu, 3, "%s", "fault in sie instruction");
+			trace_kvm_s390_sie_fault(vcpu);
 			kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING);
 			rc = 0;
 		}
 	}
 	VCPU_EVENT(vcpu, 6, "exit sie icptcode %d",
 		   vcpu->arch.sie_block->icptcode);
+	trace_kvm_s390_sie_exit(vcpu, vcpu->arch.sie_block->icptcode);
 	local_irq_disable();
 	kvm_guest_exit();
 	local_irq_enable();
@@ -959,7 +969,12 @@ void kvm_arch_commit_memory_region(struct kvm *kvm,
 	return;
 }
 
-void kvm_arch_flush_shadow(struct kvm *kvm)
+void kvm_arch_flush_shadow_all(struct kvm *kvm)
+{
+}
+
+void kvm_arch_flush_shadow_memslot(struct kvm *kvm,
+				   struct kvm_memory_slot *slot)
 {
 }
 

arch/s390/kvm/priv.c

@@ -20,6 +20,7 @@
 #include <asm/sysinfo.h>
 #include "gaccess.h"
 #include "kvm-s390.h"
+#include "trace.h"
 
 static int handle_set_prefix(struct kvm_vcpu *vcpu)
 {
@@ -59,6 +60,7 @@ static int handle_set_prefix(struct kvm_vcpu *vcpu)
 	kvm_s390_set_prefix(vcpu, address);
 
 	VCPU_EVENT(vcpu, 5, "setting prefix to %x", address);
+	trace_kvm_s390_handle_prefix(vcpu, 1, address);
 out:
 	return 0;
 }
@@ -91,6 +93,7 @@ static int handle_store_prefix(struct kvm_vcpu *vcpu)
 	}
 
 	VCPU_EVENT(vcpu, 5, "storing prefix to %x", address);
+	trace_kvm_s390_handle_prefix(vcpu, 0, address);
 out:
 	return 0;
 }
@@ -119,6 +122,7 @@ static int handle_store_cpu_address(struct kvm_vcpu *vcpu)
 	}
 
 	VCPU_EVENT(vcpu, 5, "storing cpu address to %llx", useraddr);
+	trace_kvm_s390_handle_stap(vcpu, useraddr);
 out:
 	return 0;
 }
@@ -164,9 +168,11 @@ static int handle_stfl(struct kvm_vcpu *vcpu)
 			   &facility_list, sizeof(facility_list));
 	if (rc == -EFAULT)
 		kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING);
-	else
+	else {
 		VCPU_EVENT(vcpu, 5, "store facility list value %x",
 			   facility_list);
+		trace_kvm_s390_handle_stfl(vcpu, facility_list);
+	}
 	return 0;
 }
 
@@ -278,6 +284,7 @@ static int handle_stsi(struct kvm_vcpu *vcpu)
 		kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING);
 		goto out_mem;
 	}
+	trace_kvm_s390_handle_stsi(vcpu, fc, sel1, sel2, operand2);
 	free_page(mem);
 	vcpu->arch.sie_block->gpsw.mask &= ~(3ul << 44);
 	vcpu->run->s.regs.gprs[0] = 0;

arch/s390/kvm/sigp.c

@@ -18,6 +18,7 @@
 #include <asm/sigp.h>
 #include "gaccess.h"
 #include "kvm-s390.h"
+#include "trace.h"
 
 static int __sigp_sense(struct kvm_vcpu *vcpu, u16 cpu_addr,
 			u64 *reg)
@@ -344,6 +345,7 @@ int kvm_s390_handle_sigp(struct kvm_vcpu *vcpu)
 	else
 		parameter = vcpu->run->s.regs.gprs[r1 + 1];
 
+	trace_kvm_s390_handle_sigp(vcpu, order_code, cpu_addr, parameter);
 	switch (order_code) {
 	case SIGP_SENSE:
 		vcpu->stat.instruction_sigp_sense++;

arch/s390/kvm/trace-s390.h

@@ -0,0 +1,210 @@
+#if !defined(_TRACE_KVMS390_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_KVMS390_H
+
+#include <linux/tracepoint.h>
+
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM kvm-s390
+#define TRACE_INCLUDE_PATH .
+#undef TRACE_INCLUDE_FILE
+#define TRACE_INCLUDE_FILE trace-s390
+
+/*
+ * Trace point for the creation of the kvm instance.
+ */
+TRACE_EVENT(kvm_s390_create_vm,
+	    TP_PROTO(unsigned long type),
+	    TP_ARGS(type),
+
+	    TP_STRUCT__entry(
+		    __field(unsigned long, type)
+		    ),
+
+	    TP_fast_assign(
+		    __entry->type = type;
+		    ),
+
+	    TP_printk("create vm%s",
+		      __entry->type & KVM_VM_S390_UCONTROL ? " (UCONTROL)" : "")
+	);
+
+/*
+ * Trace points for creation and destruction of vpcus.
+ */
+TRACE_EVENT(kvm_s390_create_vcpu,
+	    TP_PROTO(unsigned int id, struct kvm_vcpu *vcpu,
+		     struct kvm_s390_sie_block *sie_block),
+	    TP_ARGS(id, vcpu, sie_block),
+
+	    TP_STRUCT__entry(
+		    __field(unsigned int, id)
+		    __field(struct kvm_vcpu *, vcpu)
+		    __field(struct kvm_s390_sie_block *, sie_block)
+		    ),
+
+	    TP_fast_assign(
+		    __entry->id = id;
+		    __entry->vcpu = vcpu;
+		    __entry->sie_block = sie_block;
+		    ),
+
+	    TP_printk("create cpu %d at %p, sie block at %p", __entry->id,
+		      __entry->vcpu, __entry->sie_block)
+	);
+
+TRACE_EVENT(kvm_s390_destroy_vcpu,
+	    TP_PROTO(unsigned int id),
+	    TP_ARGS(id),
+
+	    TP_STRUCT__entry(
+		    __field(unsigned int, id)
+		    ),
+
+	    TP_fast_assign(
+		    __entry->id = id;
+		    ),
+
+	    TP_printk("destroy cpu %d", __entry->id)
+	);
+
+/*
+ * Trace points for injection of interrupts, either per machine or
+ * per vcpu.
+ */
+
+#define kvm_s390_int_type						\
+	{KVM_S390_SIGP_STOP, "sigp stop"},				\
+	{KVM_S390_PROGRAM_INT, "program interrupt"},			\
+	{KVM_S390_SIGP_SET_PREFIX, "sigp set prefix"},			\
+	{KVM_S390_RESTART, "sigp restart"},				\
+	{KVM_S390_INT_VIRTIO, "virtio interrupt"},			\
+	{KVM_S390_INT_SERVICE, "sclp interrupt"},			\
+	{KVM_S390_INT_EMERGENCY, "sigp emergency"},			\
+	{KVM_S390_INT_EXTERNAL_CALL, "sigp ext call"}
+
+TRACE_EVENT(kvm_s390_inject_vm,
+	    TP_PROTO(__u64 type, __u32 parm, __u64 parm64, int who),
+	    TP_ARGS(type, parm, parm64, who),
+
+	    TP_STRUCT__entry(
+		    __field(__u32, inttype)
+		    __field(__u32, parm)
+		    __field(__u64, parm64)
+		    __field(int, who)
+		    ),
+
+	    TP_fast_assign(
+		    __entry->inttype = type & 0x00000000ffffffff;
+		    __entry->parm = parm;
+		    __entry->parm64 = parm64;
+		    __entry->who = who;
+		    ),
+
+	    TP_printk("inject%s: type:%x (%s) parm:%x parm64:%llx",
+		      (__entry->who == 1) ? " (from kernel)" :
+		      (__entry->who == 2) ? " (from user)" : "",
+		      __entry->inttype,
+		      __print_symbolic(__entry->inttype, kvm_s390_int_type),
+		      __entry->parm, __entry->parm64)
+	);
+
+TRACE_EVENT(kvm_s390_inject_vcpu,
+	    TP_PROTO(unsigned int id, __u64 type, __u32 parm, __u64 parm64, \
+		     int who),
+	    TP_ARGS(id, type, parm, parm64, who),
+
+	    TP_STRUCT__entry(
+		    __field(int, id)
+		    __field(__u32, inttype)
+		    __field(__u32, parm)
+		    __field(__u64, parm64)
+		    __field(int, who)
+		    ),
+
+	    TP_fast_assign(
+		    __entry->id = id;
+		    __entry->inttype = type & 0x00000000ffffffff;
+		    __entry->parm = parm;
+		    __entry->parm64 = parm64;
+		    __entry->who = who;
+		    ),
+
+	    TP_printk("inject%s (vcpu %d): type:%x (%s) parm:%x parm64:%llx",
+		      (__entry->who == 1) ? " (from kernel)" :
+		      (__entry->who == 2) ? " (from user)" : "",
+		      __entry->id, __entry->inttype,
+		      __print_symbolic(__entry->inttype, kvm_s390_int_type),
+		      __entry->parm, __entry->parm64)
+	);
+
+/*
+ * Trace point for the actual delivery of interrupts.
+ */
+TRACE_EVENT(kvm_s390_deliver_interrupt,
+	    TP_PROTO(unsigned int id, __u64 type, __u32 data0, __u64 data1),
+	    TP_ARGS(id, type, data0, data1),
+
+	    TP_STRUCT__entry(
+		    __field(int, id)
+		    __field(__u32, inttype)
+		    __field(__u32, data0)
+		    __field(__u64, data1)
+		    ),
+
+	    TP_fast_assign(
+		    __entry->id = id;
+		    __entry->inttype = type & 0x00000000ffffffff;
+		    __entry->data0 = data0;
+		    __entry->data1 = data1;
+		    ),
+
+	    TP_printk("deliver interrupt (vcpu %d): type:%x (%s) "	\
+		      "data:%08x %016llx",
+		      __entry->id, __entry->inttype,
+		      __print_symbolic(__entry->inttype, kvm_s390_int_type),
+		      __entry->data0, __entry->data1)
+	);
+
+/*
+ * Trace point for resets that may be requested from userspace.
+ */
+TRACE_EVENT(kvm_s390_request_resets,
+	    TP_PROTO(__u64 resets),
+	    TP_ARGS(resets),
+
+	    TP_STRUCT__entry(
+		    __field(__u64, resets)
+		    ),
+
+	    TP_fast_assign(
+		    __entry->resets = resets;
+		    ),
+
+	    TP_printk("requesting userspace resets %llx",
+		      __entry->resets)
+	);
+
+/*
+ * Trace point for a vcpu's stop requests.
+ */
+TRACE_EVENT(kvm_s390_stop_request,
+	    TP_PROTO(unsigned int action_bits),
+	    TP_ARGS(action_bits),
+
+	    TP_STRUCT__entry(
+		    __field(unsigned int, action_bits)
+		    ),
+
+	    TP_fast_assign(
+		    __entry->action_bits = action_bits;
+		    ),
+
+	    TP_printk("stop request, action_bits = %08x",
+		      __entry->action_bits)
+	);
+
+
+#endif /* _TRACE_KVMS390_H */
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>

arch/s390/kvm/trace.h

@@ -0,0 +1,341 @@
+#if !defined(_TRACE_KVM_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_KVM_H
+
+#include <linux/tracepoint.h>
+#include <asm/sigp.h>
+#include <asm/debug.h>
+
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM kvm
+#define TRACE_INCLUDE_PATH .
+#undef TRACE_INCLUDE_FILE
+#define TRACE_INCLUDE_FILE trace
+
+/*
+ * Helpers for vcpu-specific tracepoints containing the same information
+ * as s390dbf VCPU_EVENTs.
+ */
+#define VCPU_PROTO_COMMON struct kvm_vcpu *vcpu
+#define VCPU_ARGS_COMMON vcpu
+#define VCPU_FIELD_COMMON __field(int, id)			\
+	__field(unsigned long, pswmask)				\
+	__field(unsigned long, pswaddr)
+#define VCPU_ASSIGN_COMMON do {						\
+	__entry->id = vcpu->vcpu_id;					\
+	__entry->pswmask = vcpu->arch.sie_block->gpsw.mask;		\
+	__entry->pswaddr = vcpu->arch.sie_block->gpsw.addr;		\
+	} while (0);
+#define VCPU_TP_PRINTK(p_str, p_args...)				\
+	TP_printk("%02d[%016lx-%016lx]: " p_str, __entry->id,		\
+		  __entry->pswmask, __entry->pswaddr, p_args)
+
+/*
+ * Tracepoints for SIE entry and exit.
+ */
+TRACE_EVENT(kvm_s390_sie_enter,
+	    TP_PROTO(VCPU_PROTO_COMMON, int cpuflags),
+	    TP_ARGS(VCPU_ARGS_COMMON, cpuflags),
+
+	    TP_STRUCT__entry(
+		    VCPU_FIELD_COMMON
+		    __field(int, cpuflags)
+		    ),
+
+	    TP_fast_assign(
+		    VCPU_ASSIGN_COMMON
+		    __entry->cpuflags = cpuflags;
+		    ),
+
+	    VCPU_TP_PRINTK("entering sie flags %x", __entry->cpuflags)
+	);
+
+TRACE_EVENT(kvm_s390_sie_fault,
+	    TP_PROTO(VCPU_PROTO_COMMON),
+	    TP_ARGS(VCPU_ARGS_COMMON),
+
+	    TP_STRUCT__entry(
+		    VCPU_FIELD_COMMON
+		    ),
+
+	    TP_fast_assign(
+		    VCPU_ASSIGN_COMMON
+		    ),
+
+	    VCPU_TP_PRINTK("%s", "fault in sie instruction")
+	);
+
+#define sie_intercept_code				\
+	{0x04, "Instruction"},				\
+	{0x08, "Program interruption"},			\
+	{0x0C, "Instruction and program interuption"},	\
+	{0x10, "External request"},			\
+	{0x14, "External interruption"},		\
+	{0x18, "I/O request"},				\
+	{0x1C, "Wait state"},				\
+	{0x20, "Validity"},				\
+	{0x28, "Stop request"}
+
+TRACE_EVENT(kvm_s390_sie_exit,
+	    TP_PROTO(VCPU_PROTO_COMMON, u8 icptcode),
+	    TP_ARGS(VCPU_ARGS_COMMON, icptcode),
+
+	    TP_STRUCT__entry(
+		    VCPU_FIELD_COMMON
+		    __field(u8, icptcode)
+		    ),
+
+	    TP_fast_assign(
+		    VCPU_ASSIGN_COMMON
+		    __entry->icptcode = icptcode;
+		    ),
+
+	    VCPU_TP_PRINTK("exit sie icptcode %d (%s)", __entry->icptcode,
+			   __print_symbolic(__entry->icptcode,
+					    sie_intercept_code))
+	);
+
+/*
+ * Trace point for intercepted instructions.
+ */
+TRACE_EVENT(kvm_s390_intercept_instruction,
+	    TP_PROTO(VCPU_PROTO_COMMON, __u16 ipa, __u32 ipb),
+	    TP_ARGS(VCPU_ARGS_COMMON, ipa, ipb),
+
+	    TP_STRUCT__entry(
+		    VCPU_FIELD_COMMON
+		    __field(__u64, instruction)
+		    __field(char, insn[8])
+		    ),
+
+	    TP_fast_assign(
+		    VCPU_ASSIGN_COMMON
+		    __entry->instruction = ((__u64)ipa << 48) |
+		    ((__u64)ipb << 16);
+		    ),
+
+	    VCPU_TP_PRINTK("intercepted instruction %016llx (%s)",
+			   __entry->instruction,
+			   insn_to_mnemonic((unsigned char *)
+					    &__entry->instruction,
+					 __entry->insn) ?
+			   "unknown" : __entry->insn)
+	);
+
+/*
+ * Trace point for intercepted program interruptions.
+ */
+TRACE_EVENT(kvm_s390_intercept_prog,
+	    TP_PROTO(VCPU_PROTO_COMMON, __u16 code),
+	    TP_ARGS(VCPU_ARGS_COMMON, code),
+
+	    TP_STRUCT__entry(
+		    VCPU_FIELD_COMMON
+		    __field(__u16, code)
+		    ),
+
+	    TP_fast_assign(
+		    VCPU_ASSIGN_COMMON
+		    __entry->code = code;
+		    ),
+
+	    VCPU_TP_PRINTK("intercepted program interruption %04x",
+			   __entry->code)
+	);
+
+/*
+ * Trace point for validity intercepts.
+ */
+TRACE_EVENT(kvm_s390_intercept_validity,
+	    TP_PROTO(VCPU_PROTO_COMMON, __u16 viwhy),
+	    TP_ARGS(VCPU_ARGS_COMMON, viwhy),
+
+	    TP_STRUCT__entry(
+		    VCPU_FIELD_COMMON
+		    __field(__u16, viwhy)
+		    ),
+
+	    TP_fast_assign(
+		    VCPU_ASSIGN_COMMON
+		    __entry->viwhy = viwhy;
+		    ),
+
+	    VCPU_TP_PRINTK("got validity intercept %04x", __entry->viwhy)
+	);
+
+/*
+ * Trace points for instructions that are of special interest.
+ */
+
+#define sigp_order_codes					\
+	{SIGP_SENSE, "sense"},					\
+	{SIGP_EXTERNAL_CALL, "external call"},			\
+	{SIGP_EMERGENCY_SIGNAL, "emergency signal"},		\
+	{SIGP_STOP, "stop"},					\
+	{SIGP_STOP_AND_STORE_STATUS, "stop and store status"},	\
+	{SIGP_SET_ARCHITECTURE, "set architecture"},		\
+	{SIGP_SET_PREFIX, "set prefix"},			\
+	{SIGP_SENSE_RUNNING, "sense running"},			\
+	{SIGP_RESTART, "restart"}
+
+TRACE_EVENT(kvm_s390_handle_sigp,
+	    TP_PROTO(VCPU_PROTO_COMMON, __u8 order_code, __u16 cpu_addr, \
+		     __u32 parameter),
+	    TP_ARGS(VCPU_ARGS_COMMON, order_code, cpu_addr, parameter),
+
+	    TP_STRUCT__entry(
+		    VCPU_FIELD_COMMON
+		    __field(__u8, order_code)
+		    __field(__u16, cpu_addr)
+		    __field(__u32, parameter)
+		    ),
+
+	    TP_fast_assign(
+		    VCPU_ASSIGN_COMMON
+		    __entry->order_code = order_code;
+		    __entry->cpu_addr = cpu_addr;
+		    __entry->parameter = parameter;
+		    ),
+
+	    VCPU_TP_PRINTK("handle sigp order %02x (%s), cpu address %04x, " \
+			   "parameter %08x", __entry->order_code,
+			   __print_symbolic(__entry->order_code,
+					    sigp_order_codes),
+			   __entry->cpu_addr, __entry->parameter)
+	);
+
+#define diagnose_codes				\
+	{0x10, "release pages"},		\
+	{0x44, "time slice end"},		\
+	{0x308, "ipl functions"},		\
+	{0x500, "kvm hypercall"},		\
+	{0x501, "kvm breakpoint"}
+
+TRACE_EVENT(kvm_s390_handle_diag,
+	    TP_PROTO(VCPU_PROTO_COMMON, __u16 code),
+	    TP_ARGS(VCPU_ARGS_COMMON, code),
+
+	    TP_STRUCT__entry(
+		    VCPU_FIELD_COMMON
+		    __field(__u16, code)
+		    ),
+
+	    TP_fast_assign(
+		    VCPU_ASSIGN_COMMON
+		    __entry->code = code;
+		    ),
+
+	    VCPU_TP_PRINTK("handle diagnose call %04x (%s)", __entry->code,
+			   __print_symbolic(__entry->code, diagnose_codes))
+	);
+
+TRACE_EVENT(kvm_s390_handle_lctl,
+	    TP_PROTO(VCPU_PROTO_COMMON, int g, int reg1, int reg3, u64 addr),
+	    TP_ARGS(VCPU_ARGS_COMMON, g, reg1, reg3, addr),
+
+	    TP_STRUCT__entry(
+		    VCPU_FIELD_COMMON
+		    __field(int, g)
+		    __field(int, reg1)
+		    __field(int, reg3)
+		    __field(u64, addr)
+		    ),
+
+	    TP_fast_assign(
+		    VCPU_ASSIGN_COMMON
+		    __entry->g = g;
+		    __entry->reg1 = reg1;
+		    __entry->reg3 = reg3;
+		    __entry->addr = addr;
+		    ),
+
+	    VCPU_TP_PRINTK("%s: loading cr %x-%x from %016llx",
+			   __entry->g ? "lctlg" : "lctl",
+			   __entry->reg1, __entry->reg3, __entry->addr)
+	);
+
+TRACE_EVENT(kvm_s390_handle_prefix,
+	    TP_PROTO(VCPU_PROTO_COMMON, int set, u32 address),
+	    TP_ARGS(VCPU_ARGS_COMMON, set, address),
+
+	    TP_STRUCT__entry(
+		    VCPU_FIELD_COMMON
+		    __field(int, set)
+		    __field(u32, address)
+		    ),
+
+	    TP_fast_assign(
+		    VCPU_ASSIGN_COMMON
+		    __entry->set = set;
+		    __entry->address = address;
+		    ),
+
+	    VCPU_TP_PRINTK("%s prefix to %08x",
+			   __entry->set ? "setting" : "storing",
+			   __entry->address)
+	);
+
+TRACE_EVENT(kvm_s390_handle_stap,
+	    TP_PROTO(VCPU_PROTO_COMMON, u64 address),
+	    TP_ARGS(VCPU_ARGS_COMMON, address),
+
+	    TP_STRUCT__entry(
+		    VCPU_FIELD_COMMON
+		    __field(u64, address)
+		    ),
+
+	    TP_fast_assign(
+		    VCPU_ASSIGN_COMMON
+		    __entry->address = address;
+		    ),
+
+	    VCPU_TP_PRINTK("storing cpu address to %016llx",
+			   __entry->address)
+	);
+
+TRACE_EVENT(kvm_s390_handle_stfl,
+	    TP_PROTO(VCPU_PROTO_COMMON, unsigned int facility_list),
+	    TP_ARGS(VCPU_ARGS_COMMON, facility_list),
+
+	    TP_STRUCT__entry(
+		    VCPU_FIELD_COMMON
+		    __field(unsigned int, facility_list)
+		    ),
+
+	    TP_fast_assign(
+		    VCPU_ASSIGN_COMMON
+		    __entry->facility_list = facility_list;
+		    ),
+
+	    VCPU_TP_PRINTK("store facility list value %08x",
+			   __entry->facility_list)
+	);
+
+TRACE_EVENT(kvm_s390_handle_stsi,
+	    TP_PROTO(VCPU_PROTO_COMMON, int fc, int sel1, int sel2, u64 addr),
+	    TP_ARGS(VCPU_ARGS_COMMON, fc, sel1, sel2, addr),
+
+	    TP_STRUCT__entry(
+		    VCPU_FIELD_COMMON
+		    __field(int, fc)
+		    __field(int, sel1)
+		    __field(int, sel2)
+		    __field(u64, addr)
+		    ),
+
+	    TP_fast_assign(
+		    VCPU_ASSIGN_COMMON
+		    __entry->fc = fc;
+		    __entry->sel1 = sel1;
+		    __entry->sel2 = sel2;
+		    __entry->addr = addr;
+		    ),
+
+	    VCPU_TP_PRINTK("STSI %d.%d.%d information stored to %016llx",
+			   __entry->fc, __entry->sel1, __entry->sel2,
+			   __entry->addr)
+	);
+
+#endif /* _TRACE_KVM_H */
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>

arch/x86/Kconfig

@@ -586,23 +586,18 @@ config PARAVIRT_TIME_ACCOUNTING
 
 source "arch/x86/xen/Kconfig"
 
-config KVM_CLOCK
+config KVM_GUEST
-	bool "KVM paravirtualized clock"
+	bool "KVM Guest support (including kvmclock)"
+	select PARAVIRT
 	select PARAVIRT
 	select PARAVIRT_CLOCK
-	---help---
+	default y if PARAVIRT_GUEST
-	  Turning on this option will allow you to run a paravirtualized clock
-	  when running over the KVM hypervisor. Instead of relying on a PIT
-	  (or probably other) emulation by the underlying device model, the host
-	  provides the guest with timing infrastructure such as time of day, and
-	  system time
-
-config KVM_GUEST
-	bool "KVM Guest support"
-	select PARAVIRT
 	---help---
 	  This option enables various optimizations for running under the KVM
-	  hypervisor.
+	  hypervisor. It includes a paravirtualized clock, so that instead
+	  of relying on a PIT (or probably other) emulation by the
+	  underlying device model, the host provides the guest with
+	  timing infrastructure such as time of day, and system time
 
 source "arch/x86/lguest/Kconfig"
 

arch/x86/include/asm/kvm.h

@@ -41,6 +41,7 @@
 #define __KVM_HAVE_DEBUGREGS
 #define __KVM_HAVE_XSAVE
 #define __KVM_HAVE_XCRS
+#define __KVM_HAVE_READONLY_MEM
 
 /* Architectural interrupt line count. */
 #define KVM_NR_INTERRUPTS 256

arch/x86/include/asm/kvm_emulate.h

@@ -85,6 +85,19 @@ struct x86_instruction_info {
 #define X86EMUL_INTERCEPTED     6 /* Intercepted by nested VMCB/VMCS */
 
 struct x86_emulate_ops {
+	/*
+	 * read_gpr: read a general purpose register (rax - r15)
+	 *
+	 * @reg: gpr number.
+	 */
+	ulong (*read_gpr)(struct x86_emulate_ctxt *ctxt, unsigned reg);
+	/*
+	 * write_gpr: write a general purpose register (rax - r15)
+	 *
+	 * @reg: gpr number.
+	 * @val: value to write.
+	 */
+	void (*write_gpr)(struct x86_emulate_ctxt *ctxt, unsigned reg, ulong val);
 	/*
 	 * read_std: Read bytes of standard (non-emulated/special) memory.
 	 *           Used for descriptor reading.
@@ -200,8 +213,9 @@ typedef u32 __attribute__((vector_size(16))) sse128_t;
 
 /* Type, address-of, and value of an instruction's operand. */
 struct operand {
-	enum { OP_REG, OP_MEM, OP_IMM, OP_XMM, OP_MM, OP_NONE } type;
+	enum { OP_REG, OP_MEM, OP_MEM_STR, OP_IMM, OP_XMM, OP_MM, OP_NONE } type;
 	unsigned int bytes;
+	unsigned int count;
 	union {
 		unsigned long orig_val;
 		u64 orig_val64;
@@ -221,6 +235,7 @@ struct operand {
 		char valptr[sizeof(unsigned long) + 2];
 		sse128_t vec_val;
 		u64 mm_val;
+		void *data;
 	};
 };
 
@@ -236,14 +251,23 @@ struct read_cache {
 	unsigned long end;
 };
 
+/* Execution mode, passed to the emulator. */
+enum x86emul_mode {
+	X86EMUL_MODE_REAL,	/* Real mode.             */
+	X86EMUL_MODE_VM86,	/* Virtual 8086 mode.     */
+	X86EMUL_MODE_PROT16,	/* 16-bit protected mode. */
+	X86EMUL_MODE_PROT32,	/* 32-bit protected mode. */
+	X86EMUL_MODE_PROT64,	/* 64-bit (long) mode.    */
+};
+
 struct x86_emulate_ctxt {
-	struct x86_emulate_ops *ops;
+	const struct x86_emulate_ops *ops;
 
 	/* Register state before/after emulation. */
 	unsigned long eflags;
 	unsigned long eip; /* eip before instruction emulation */
 	/* Emulated execution mode, represented by an X86EMUL_MODE value. */
-	int mode;
+	enum x86emul_mode mode;
 
 	/* interruptibility state, as a result of execution of STI or MOV SS */
 	int interruptibility;
@@ -281,8 +305,10 @@ struct x86_emulate_ctxt {
 	bool rip_relative;
 	unsigned long _eip;
 	struct operand memop;
+	u32 regs_valid;  /* bitmaps of registers in _regs[] that can be read */
+	u32 regs_dirty;  /* bitmaps of registers in _regs[] that have been written */
 	/* Fields above regs are cleared together. */
-	unsigned long regs[NR_VCPU_REGS];
+	unsigned long _regs[NR_VCPU_REGS];
 	struct operand *memopp;
 	struct fetch_cache fetch;
 	struct read_cache io_read;
@@ -293,17 +319,6 @@ struct x86_emulate_ctxt {
 #define REPE_PREFIX	0xf3
 #define REPNE_PREFIX	0xf2
 
-/* Execution mode, passed to the emulator. */
-#define X86EMUL_MODE_REAL     0	/* Real mode.             */
-#define X86EMUL_MODE_VM86     1	/* Virtual 8086 mode.     */
-#define X86EMUL_MODE_PROT16   2	/* 16-bit protected mode. */
-#define X86EMUL_MODE_PROT32   4	/* 32-bit protected mode. */
-#define X86EMUL_MODE_PROT64   8	/* 64-bit (long) mode.    */
-
-/* any protected mode   */
-#define X86EMUL_MODE_PROT     (X86EMUL_MODE_PROT16|X86EMUL_MODE_PROT32| \
-			       X86EMUL_MODE_PROT64)
-
 /* CPUID vendors */
 #define X86EMUL_CPUID_VENDOR_AuthenticAMD_ebx 0x68747541
 #define X86EMUL_CPUID_VENDOR_AuthenticAMD_ecx 0x444d4163
@@ -394,4 +409,7 @@ int emulator_task_switch(struct x86_emulate_ctxt *ctxt,
 			 u16 tss_selector, int idt_index, int reason,
 			 bool has_error_code, u32 error_code);
 int emulate_int_real(struct x86_emulate_ctxt *ctxt, int irq);
+void emulator_invalidate_register_cache(struct x86_emulate_ctxt *ctxt);
+void emulator_writeback_register_cache(struct x86_emulate_ctxt *ctxt);
+
 #endif /* _ASM_X86_KVM_X86_EMULATE_H */

arch/x86/include/asm/kvm_host.h

@@ -271,10 +271,24 @@ struct kvm_mmu {
 	union kvm_mmu_page_role base_role;
 	bool direct_map;
 
+	/*
+	 * Bitmap; bit set = permission fault
+	 * Byte index: page fault error code [4:1]
+	 * Bit index: pte permissions in ACC_* format
+	 */
+	u8 permissions[16];
+
 	u64 *pae_root;
 	u64 *lm_root;
 	u64 rsvd_bits_mask[2][4];
 
+	/*
+	 * Bitmap: bit set = last pte in walk
+	 * index[0:1]: level (zero-based)
+	 * index[2]: pte.ps
+	 */
+	u8 last_pte_bitmap;
+
 	bool nx;
 
 	u64 pdptrs[4]; /* pae */
@@ -398,12 +412,15 @@ struct kvm_vcpu_arch {
 	struct x86_emulate_ctxt emulate_ctxt;
 	bool emulate_regs_need_sync_to_vcpu;
 	bool emulate_regs_need_sync_from_vcpu;
+	int (*complete_userspace_io)(struct kvm_vcpu *vcpu);
 
 	gpa_t time;
 	struct pvclock_vcpu_time_info hv_clock;
 	unsigned int hw_tsc_khz;
 	unsigned int time_offset;
 	struct page *time_page;
+	/* set guest stopped flag in pvclock flags field */
+	bool pvclock_set_guest_stopped_request;
 
 	struct {
 		u64 msr_val;
@@ -438,6 +455,7 @@ struct kvm_vcpu_arch {
 	unsigned long dr6;
 	unsigned long dr7;
 	unsigned long eff_db[KVM_NR_DB_REGS];
+	unsigned long guest_debug_dr7;
 
 	u64 mcg_cap;
 	u64 mcg_status;
@@ -484,14 +502,24 @@ struct kvm_vcpu_arch {
 };
 
 struct kvm_lpage_info {
-	unsigned long rmap_pde;
 	int write_count;
 };
 
 struct kvm_arch_memory_slot {
+	unsigned long *rmap[KVM_NR_PAGE_SIZES];
 	struct kvm_lpage_info *lpage_info[KVM_NR_PAGE_SIZES - 1];
 };
 
+struct kvm_apic_map {
+	struct rcu_head rcu;
+	u8 ldr_bits;
+	/* fields bellow are used to decode ldr values in different modes */
+	u32 cid_shift, cid_mask, lid_mask;
+	struct kvm_lapic *phys_map[256];
+	/* first index is cluster id second is cpu id in a cluster */
+	struct kvm_lapic *logical_map[16][16];
+};
+
 struct kvm_arch {
 	unsigned int n_used_mmu_pages;
 	unsigned int n_requested_mmu_pages;
@@ -509,6 +537,8 @@ struct kvm_arch {
 	struct kvm_ioapic *vioapic;
 	struct kvm_pit *vpit;
 	int vapics_in_nmi_mode;
+	struct mutex apic_map_lock;
+	struct kvm_apic_map *apic_map;
 
 	unsigned int tss_addr;
 	struct page *apic_access_page;
@@ -602,8 +632,7 @@ struct kvm_x86_ops {
 	void (*vcpu_load)(struct kvm_vcpu *vcpu, int cpu);
 	void (*vcpu_put)(struct kvm_vcpu *vcpu);
 
-	void (*set_guest_debug)(struct kvm_vcpu *vcpu,
+	void (*update_db_bp_intercept)(struct kvm_vcpu *vcpu);
-				struct kvm_guest_debug *dbg);
 	int (*get_msr)(struct kvm_vcpu *vcpu, u32 msr_index, u64 *pdata);
 	int (*set_msr)(struct kvm_vcpu *vcpu, u32 msr_index, u64 data);
 	u64 (*get_segment_base)(struct kvm_vcpu *vcpu, int seg);
@@ -941,6 +970,7 @@ extern bool kvm_rebooting;
 
 #define KVM_ARCH_WANT_MMU_NOTIFIER
 int kvm_unmap_hva(struct kvm *kvm, unsigned long hva);
+int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end);
 int kvm_age_hva(struct kvm *kvm, unsigned long hva);
 int kvm_test_age_hva(struct kvm *kvm, unsigned long hva);
 void kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte);

arch/x86/include/asm/kvm_para.h

@@ -102,21 +102,21 @@ struct kvm_vcpu_pv_apf_data {
 extern void kvmclock_init(void);
 extern int kvm_register_clock(char *txt);
 
-#ifdef CONFIG_KVM_CLOCK
+#ifdef CONFIG_KVM_GUEST
 bool kvm_check_and_clear_guest_paused(void);
 #else
 static inline bool kvm_check_and_clear_guest_paused(void)
 {
 	return false;
 }
-#endif /* CONFIG_KVMCLOCK */
+#endif /* CONFIG_KVM_GUEST */
 
 /* This instruction is vmcall.  On non-VT architectures, it will generate a
  * trap that we will then rewrite to the appropriate instruction.
  */
 #define KVM_HYPERCALL ".byte 0x0f,0x01,0xc1"
 
-/* For KVM hypercalls, a three-byte sequence of either the vmrun or the vmmrun
+/* For KVM hypercalls, a three-byte sequence of either the vmcall or the vmmcall
  * instruction.  The hypervisor may replace it with something else but only the
  * instructions are guaranteed to be supported.
  *

arch/x86/kernel/Makefile

@@ -81,8 +81,7 @@ obj-$(CONFIG_DEBUG_RODATA_TEST)	+= test_rodata.o
 obj-$(CONFIG_DEBUG_NX_TEST)	+= test_nx.o
 obj-$(CONFIG_DEBUG_NMI_SELFTEST) += nmi_selftest.o
 
-obj-$(CONFIG_KVM_GUEST)		+= kvm.o
+obj-$(CONFIG_KVM_GUEST)		+= kvm.o kvmclock.o
-obj-$(CONFIG_KVM_CLOCK)		+= kvmclock.o
 obj-$(CONFIG_PARAVIRT)		+= paravirt.o paravirt_patch_$(BITS).o
 obj-$(CONFIG_PARAVIRT_SPINLOCKS)+= paravirt-spinlocks.o
 obj-$(CONFIG_PARAVIRT_CLOCK)	+= pvclock.o

arch/x86/kernel/kvm.c

@@ -354,6 +354,7 @@ static void kvm_pv_guest_cpu_reboot(void *unused)
 	if (kvm_para_has_feature(KVM_FEATURE_PV_EOI))
 		wrmsrl(MSR_KVM_PV_EOI_EN, 0);
 	kvm_pv_disable_apf();
+	kvm_disable_steal_time();
 }
 
 static int kvm_pv_reboot_notify(struct notifier_block *nb,
@@ -396,9 +397,7 @@ void kvm_disable_steal_time(void)
 #ifdef CONFIG_SMP
 static void __init kvm_smp_prepare_boot_cpu(void)
 {
-#ifdef CONFIG_KVM_CLOCK
 	WARN_ON(kvm_register_clock("primary cpu clock"));
-#endif
 	kvm_guest_cpu_init();
 	native_smp_prepare_boot_cpu();
 }

arch/x86/kernel/setup.c

@@ -957,7 +957,7 @@ void __init setup_arch(char **cmdline_p)
 	initmem_init();
 	memblock_find_dma_reserve();
 
-#ifdef CONFIG_KVM_CLOCK
+#ifdef CONFIG_KVM_GUEST
 	kvmclock_init();
 #endif
 

arch/x86/kvm/Kconfig

@@ -20,6 +20,7 @@ if VIRTUALIZATION
 config KVM
 	tristate "Kernel-based Virtual Machine (KVM) support"
 	depends on HAVE_KVM
+	depends on HIGH_RES_TIMERS
 	# for device assignment:
 	depends on PCI
 	# for TASKSTATS/TASK_DELAY_ACCT:
@@ -37,6 +38,7 @@ config KVM
 	select TASK_DELAY_ACCT
 	select PERF_EVENTS
 	select HAVE_KVM_MSI
+	select HAVE_KVM_CPU_RELAX_INTERCEPT
 	---help---
 	  Support hosting fully virtualized guest machines using hardware
 	  virtualization extensions.  You will need a fairly recent

arch/x86/kvm/Makefile

@@ -12,7 +12,7 @@ kvm-$(CONFIG_IOMMU_API)	+= $(addprefix ../../../virt/kvm/, iommu.o)
 kvm-$(CONFIG_KVM_ASYNC_PF)	+= $(addprefix ../../../virt/kvm/, async_pf.o)
 
 kvm-y			+= x86.o mmu.o emulate.o i8259.o irq.o lapic.o \
-			   i8254.o timer.o cpuid.o pmu.o
+			   i8254.o cpuid.o pmu.o
 kvm-intel-y		+= vmx.o
 kvm-amd-y		+= svm.o
 

arch/x86/kvm/cpuid.c

@@ -316,7 +316,7 @@ static int do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function,
 	}
 	case 7: {
 		entry->flags |= KVM_CPUID_FLAG_SIGNIFCANT_INDEX;
-		/* Mask ebx against host capbability word 9 */
+		/* Mask ebx against host capability word 9 */
 		if (index == 0) {
 			entry->ebx &= kvm_supported_word9_x86_features;
 			cpuid_mask(&entry->ebx, 9);
@@ -397,8 +397,8 @@ static int do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function,
 		break;
 	}
 	case KVM_CPUID_SIGNATURE: {
-		char signature[12] = "KVMKVMKVM\0\0";
+		static const char signature[12] = "KVMKVMKVM\0\0";
-		u32 *sigptr = (u32 *)signature;
+		const u32 *sigptr = (const u32 *)signature;
 		entry->eax = KVM_CPUID_FEATURES;
 		entry->ebx = sigptr[0];
 		entry->ecx = sigptr[1];
@@ -484,10 +484,10 @@ struct kvm_cpuid_param {
 	u32 func;
 	u32 idx;
 	bool has_leaf_count;
-	bool (*qualifier)(struct kvm_cpuid_param *param);
+	bool (*qualifier)(const struct kvm_cpuid_param *param);
 };
 
-static bool is_centaur_cpu(struct kvm_cpuid_param *param)
+static bool is_centaur_cpu(const struct kvm_cpuid_param *param)
 {
 	return boot_cpu_data.x86_vendor == X86_VENDOR_CENTAUR;
 }
@@ -498,7 +498,7 @@ int kvm_dev_ioctl_get_supported_cpuid(struct kvm_cpuid2 *cpuid,
 	struct kvm_cpuid_entry2 *cpuid_entries;
 	int limit, nent = 0, r = -E2BIG, i;
 	u32 func;
-	static struct kvm_cpuid_param param[] = {
+	static const struct kvm_cpuid_param param[] = {
 		{ .func = 0, .has_leaf_count = true },
 		{ .func = 0x80000000, .has_leaf_count = true },
 		{ .func = 0xC0000000, .qualifier = is_centaur_cpu, .has_leaf_count = true },
@@ -517,7 +517,7 @@ int kvm_dev_ioctl_get_supported_cpuid(struct kvm_cpuid2 *cpuid,
 
 	r = 0;
 	for (i = 0; i < ARRAY_SIZE(param); i++) {
-		struct kvm_cpuid_param *ent = &param[i];
+		const struct kvm_cpuid_param *ent = &param[i];
 
 		if (ent->qualifier && !ent->qualifier(ent))
 			continue;

arch/x86/kvm/i8254.c

@@ -108,7 +108,7 @@ static s64 __kpit_elapsed(struct kvm *kvm)
 	ktime_t remaining;
 	struct kvm_kpit_state *ps = &kvm->arch.vpit->pit_state;
 
-	if (!ps->pit_timer.period)
+	if (!ps->period)
 		return 0;
 
 	/*
@@ -120,9 +120,9 @@ static s64 __kpit_elapsed(struct kvm *kvm)
 	 * itself with the initial count and continues counting
 	 * from there.
 	 */
-	remaining = hrtimer_get_remaining(&ps->pit_timer.timer);
+	remaining = hrtimer_get_remaining(&ps->timer);
-	elapsed = ps->pit_timer.period - ktime_to_ns(remaining);
+	elapsed = ps->period - ktime_to_ns(remaining);
-	elapsed = mod_64(elapsed, ps->pit_timer.period);
+	elapsed = mod_64(elapsed, ps->period);
 
 	return elapsed;
 }
@@ -238,12 +238,12 @@ static void kvm_pit_ack_irq(struct kvm_irq_ack_notifier *kian)
 	int value;
 
 	spin_lock(&ps->inject_lock);
-	value = atomic_dec_return(&ps->pit_timer.pending);
+	value = atomic_dec_return(&ps->pending);
 	if (value < 0)
 		/* spurious acks can be generated if, for example, the
 		 * PIC is being reset.  Handle it gracefully here
 		 */
-		atomic_inc(&ps->pit_timer.pending);
+		atomic_inc(&ps->pending);
 	else if (value > 0)
 		/* in this case, we had multiple outstanding pit interrupts
 		 * that we needed to inject.  Reinject
@@ -261,28 +261,17 @@ void __kvm_migrate_pit_timer(struct kvm_vcpu *vcpu)
 	if (!kvm_vcpu_is_bsp(vcpu) || !pit)
 		return;
 
-	timer = &pit->pit_state.pit_timer.timer;
+	timer = &pit->pit_state.timer;
 	if (hrtimer_cancel(timer))
 		hrtimer_start_expires(timer, HRTIMER_MODE_ABS);
 }
 
 static void destroy_pit_timer(struct kvm_pit *pit)
 {
-	hrtimer_cancel(&pit->pit_state.pit_timer.timer);
+	hrtimer_cancel(&pit->pit_state.timer);
 	flush_kthread_work(&pit->expired);
 }
 
-static bool kpit_is_periodic(struct kvm_timer *ktimer)
-{
-	struct kvm_kpit_state *ps = container_of(ktimer, struct kvm_kpit_state,
-						 pit_timer);
-	return ps->is_periodic;
-}
-
-static struct kvm_timer_ops kpit_ops = {
-	.is_periodic = kpit_is_periodic,
-};
-
 static void pit_do_work(struct kthread_work *work)
 {
 	struct kvm_pit *pit = container_of(work, struct kvm_pit, expired);
@@ -322,16 +311,16 @@ static void pit_do_work(struct kthread_work *work)
 
 static enum hrtimer_restart pit_timer_fn(struct hrtimer *data)
 {
-	struct kvm_timer *ktimer = container_of(data, struct kvm_timer, timer);
+	struct kvm_kpit_state *ps = container_of(data, struct kvm_kpit_state, timer);
-	struct kvm_pit *pt = ktimer->kvm->arch.vpit;
+	struct kvm_pit *pt = ps->kvm->arch.vpit;
 
-	if (ktimer->reinject || !atomic_read(&ktimer->pending)) {
+	if (ps->reinject || !atomic_read(&ps->pending)) {
-		atomic_inc(&ktimer->pending);
+		atomic_inc(&ps->pending);
 		queue_kthread_work(&pt->worker, &pt->expired);
 	}
 
-	if (ktimer->t_ops->is_periodic(ktimer)) {
+	if (ps->is_periodic) {
-		hrtimer_add_expires_ns(&ktimer->timer, ktimer->period);
+		hrtimer_add_expires_ns(&ps->timer, ps->period);
 		return HRTIMER_RESTART;
 	} else
 		return HRTIMER_NORESTART;
@@ -340,7 +329,6 @@ static enum hrtimer_restart pit_timer_fn(struct hrtimer *data)
 static void create_pit_timer(struct kvm *kvm, u32 val, int is_period)
 {
 	struct kvm_kpit_state *ps = &kvm->arch.vpit->pit_state;
-	struct kvm_timer *pt = &ps->pit_timer;
 	s64 interval;
 
 	if (!irqchip_in_kernel(kvm) || ps->flags & KVM_PIT_FLAGS_HPET_LEGACY)
@@ -351,19 +339,18 @@ static void create_pit_timer(struct kvm *kvm, u32 val, int is_period)
 	pr_debug("create pit timer, interval is %llu nsec\n", interval);
 
 	/* TODO The new value only affected after the retriggered */
-	hrtimer_cancel(&pt->timer);
+	hrtimer_cancel(&ps->timer);
 	flush_kthread_work(&ps->pit->expired);
-	pt->period = interval;
+	ps->period = interval;
 	ps->is_periodic = is_period;
 
-	pt->timer.function = pit_timer_fn;
+	ps->timer.function = pit_timer_fn;
-	pt->t_ops = &kpit_ops;
+	ps->kvm = ps->pit->kvm;
-	pt->kvm = ps->pit->kvm;
 
-	atomic_set(&pt->pending, 0);
+	atomic_set(&ps->pending, 0);
 	ps->irq_ack = 1;
 
-	hrtimer_start(&pt->timer, ktime_add_ns(ktime_get(), interval),
+	hrtimer_start(&ps->timer, ktime_add_ns(ktime_get(), interval),
 		      HRTIMER_MODE_ABS);
 }
 
@@ -639,7 +626,7 @@ void kvm_pit_reset(struct kvm_pit *pit)
 	}
 	mutex_unlock(&pit->pit_state.lock);
 
-	atomic_set(&pit->pit_state.pit_timer.pending, 0);
+	atomic_set(&pit->pit_state.pending, 0);
 	pit->pit_state.irq_ack = 1;
 }
 
@@ -648,7 +635,7 @@ static void pit_mask_notifer(struct kvm_irq_mask_notifier *kimn, bool mask)
 	struct kvm_pit *pit = container_of(kimn, struct kvm_pit, mask_notifier);
 
 	if (!mask) {
-		atomic_set(&pit->pit_state.pit_timer.pending, 0);
+		atomic_set(&pit->pit_state.pending, 0);
 		pit->pit_state.irq_ack = 1;
 	}
 }
@@ -706,12 +693,11 @@ struct kvm_pit *kvm_create_pit(struct kvm *kvm, u32 flags)
 
 	pit_state = &pit->pit_state;
 	pit_state->pit = pit;
-	hrtimer_init(&pit_state->pit_timer.timer,
+	hrtimer_init(&pit_state->timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS);
-		     CLOCK_MONOTONIC, HRTIMER_MODE_ABS);
 	pit_state->irq_ack_notifier.gsi = 0;
 	pit_state->irq_ack_notifier.irq_acked = kvm_pit_ack_irq;
 	kvm_register_irq_ack_notifier(kvm, &pit_state->irq_ack_notifier);
-	pit_state->pit_timer.reinject = true;
+	pit_state->reinject = true;
 	mutex_unlock(&pit->pit_state.lock);
 
 	kvm_pit_reset(pit);
@@ -761,7 +747,7 @@ void kvm_free_pit(struct kvm *kvm)
 		kvm_unregister_irq_ack_notifier(kvm,
 				&kvm->arch.vpit->pit_state.irq_ack_notifier);
 		mutex_lock(&kvm->arch.vpit->pit_state.lock);
-		timer = &kvm->arch.vpit->pit_state.pit_timer.timer;
+		timer = &kvm->arch.vpit->pit_state.timer;
 		hrtimer_cancel(timer);
 		flush_kthread_work(&kvm->arch.vpit->expired);
 		kthread_stop(kvm->arch.vpit->worker_task);

arch/x86/kvm/i8254.h

@@ -24,8 +24,12 @@ struct kvm_kpit_channel_state {
 struct kvm_kpit_state {
 	struct kvm_kpit_channel_state channels[3];
 	u32 flags;
-	struct kvm_timer pit_timer;
 	bool is_periodic;
+	s64 period; 				/* unit: ns */
+	struct hrtimer timer;
+	atomic_t pending;			/* accumulated triggered timers */
+	bool reinject;
+	struct kvm *kvm;
 	u32    speaker_data_on;
 	struct mutex lock;
 	struct kvm_pit *pit;

arch/x86/kvm/i8259.c

@@ -190,17 +190,17 @@ void kvm_pic_update_irq(struct kvm_pic *s)
 
 int kvm_pic_set_irq(struct kvm_pic *s, int irq, int irq_source_id, int level)
 {
-	int ret = -1;
+	int ret, irq_level;
+
+	BUG_ON(irq < 0 || irq >= PIC_NUM_PINS);
 
 	pic_lock(s);
-	if (irq >= 0 && irq < PIC_NUM_PINS) {
+	irq_level = __kvm_irq_line_state(&s->irq_states[irq],
-		int irq_level = __kvm_irq_line_state(&s->irq_states[irq],
 					 irq_source_id, level);
 	ret = pic_set_irq1(&s->pics[irq >> 3], irq & 7, irq_level);
 	pic_update_irq(s);
 	trace_kvm_pic_set_irq(irq >> 3, irq & 7, s->pics[irq >> 3].elcr,
 			      s->pics[irq >> 3].imr, ret == 0);
-	}
 	pic_unlock(s);
 
 	return ret;
@@ -275,23 +275,20 @@ void kvm_pic_reset(struct kvm_kpic_state *s)
 {
 	int irq, i;
 	struct kvm_vcpu *vcpu;
-	u8 irr = s->irr, isr = s->imr;
+	u8 edge_irr = s->irr & ~s->elcr;
 	bool found = false;
 
 	s->last_irr = 0;
-	s->irr = 0;
+	s->irr &= s->elcr;
 	s->imr = 0;
-	s->isr = 0;
 	s->priority_add = 0;
-	s->irq_base = 0;
-	s->read_reg_select = 0;
-	s->poll = 0;
 	s->special_mask = 0;
-	s->init_state = 0;
+	s->read_reg_select = 0;
-	s->auto_eoi = 0;
+	if (!s->init4) {
-	s->rotate_on_auto_eoi = 0;
 		s->special_fully_nested_mode = 0;
-	s->init4 = 0;
+		s->auto_eoi = 0;
+	}
+	s->init_state = 1;
 
 	kvm_for_each_vcpu(i, vcpu, s->pics_state->kvm)
 		if (kvm_apic_accept_pic_intr(vcpu)) {
@@ -304,7 +301,7 @@ void kvm_pic_reset(struct kvm_kpic_state *s)
 		return;
 
 	for (irq = 0; irq < PIC_NUM_PINS/2; irq++)
-		if (irr & (1 << irq) || isr & (1 << irq))
+		if (edge_irr & (1 << irq))
 			pic_clear_isr(s, irq);
 }
 
@@ -316,40 +313,13 @@ static void pic_ioport_write(void *opaque, u32 addr, u32 val)
 	addr &= 1;
 	if (addr == 0) {
 		if (val & 0x10) {
-			u8 edge_irr = s->irr & ~s->elcr;
-			int i;
-			bool found = false;
-			struct kvm_vcpu *vcpu;
-
 			s->init4 = val & 1;
-			s->last_irr = 0;
-			s->irr &= s->elcr;
-			s->imr = 0;
-			s->priority_add = 0;
-			s->special_mask = 0;
-			s->read_reg_select = 0;
-			if (!s->init4) {
-				s->special_fully_nested_mode = 0;
-				s->auto_eoi = 0;
-			}
-			s->init_state = 1;
 			if (val & 0x02)
 				pr_pic_unimpl("single mode not supported");
 			if (val & 0x08)
 				pr_pic_unimpl(
 						"level sensitive irq not supported");
-
+			kvm_pic_reset(s);
-			kvm_for_each_vcpu(i, vcpu, s->pics_state->kvm)
-				if (kvm_apic_accept_pic_intr(vcpu)) {
-					found = true;
-					break;
-				}
-
-
-			if (found)
-				for (irq = 0; irq < PIC_NUM_PINS/2; irq++)
-					if (edge_irr & (1 << irq))
-						pic_clear_isr(s, irq);
 		} else if (val & 0x08) {
 			if (val & 0x04)
 				s->poll = 1;

arch/x86/kvm/irq.h

@@ -70,7 +70,7 @@ struct kvm_pic {
 	struct kvm_io_device dev_slave;
 	struct kvm_io_device dev_eclr;
 	void (*ack_notifier)(void *opaque, int irq);
-	unsigned long irq_states[16];
+	unsigned long irq_states[PIC_NUM_PINS];
 };
 
 struct kvm_pic *kvm_create_pic(struct kvm *kvm);

arch/x86/kvm/kvm_timer.h

@@ -1,18 +0,0 @@
-
-struct kvm_timer {
-	struct hrtimer timer;
-	s64 period; 				/* unit: ns */
-	u32 timer_mode_mask;
-	u64 tscdeadline;
-	atomic_t pending;			/* accumulated triggered timers */
-	bool reinject;
-	struct kvm_timer_ops *t_ops;
-	struct kvm *kvm;
-	struct kvm_vcpu *vcpu;
-};
-
-struct kvm_timer_ops {
-	bool (*is_periodic)(struct kvm_timer *);
-};
-
-enum hrtimer_restart kvm_timer_fn(struct hrtimer *data);

arch/x86/kvm/lapic.c

@@ -34,6 +34,7 @@
 #include <asm/current.h>
 #include <asm/apicdef.h>
 #include <linux/atomic.h>
+#include <linux/jump_label.h>
 #include "kvm_cache_regs.h"
 #include "irq.h"
 #include "trace.h"
@@ -65,6 +66,7 @@
 #define APIC_DEST_NOSHORT		0x0
 #define APIC_DEST_MASK			0x800
 #define MAX_APIC_VECTOR			256
+#define APIC_VECTORS_PER_REG		32
 
 #define VEC_POS(v) ((v) & (32 - 1))
 #define REG_POS(v) (((v) >> 5) << 4)
@@ -72,11 +74,6 @@
 static unsigned int min_timer_period_us = 500;
 module_param(min_timer_period_us, uint, S_IRUGO | S_IWUSR);
 
-static inline u32 apic_get_reg(struct kvm_lapic *apic, int reg_off)
-{
-	return *((u32 *) (apic->regs + reg_off));
-}
-
 static inline void apic_set_reg(struct kvm_lapic *apic, int reg_off, u32 val)
 {
 	*((u32 *) (apic->regs + reg_off)) = val;
@@ -117,19 +114,23 @@ static inline int __apic_test_and_clear_vector(int vec, void *bitmap)
 	return __test_and_clear_bit(VEC_POS(vec), (bitmap) + REG_POS(vec));
 }
 
-static inline int apic_hw_enabled(struct kvm_lapic *apic)
+struct static_key_deferred apic_hw_disabled __read_mostly;
-{
+struct static_key_deferred apic_sw_disabled __read_mostly;
-	return (apic)->vcpu->arch.apic_base & MSR_IA32_APICBASE_ENABLE;
-}
 
-static inline int  apic_sw_enabled(struct kvm_lapic *apic)
+static inline void apic_set_spiv(struct kvm_lapic *apic, u32 val)
 {
-	return apic_get_reg(apic, APIC_SPIV) & APIC_SPIV_APIC_ENABLED;
+	if ((kvm_apic_get_reg(apic, APIC_SPIV) ^ val) & APIC_SPIV_APIC_ENABLED) {
+		if (val & APIC_SPIV_APIC_ENABLED)
+			static_key_slow_dec_deferred(&apic_sw_disabled);
+		else
+			static_key_slow_inc(&apic_sw_disabled.key);
+	}
+	apic_set_reg(apic, APIC_SPIV, val);
 }
 
 static inline int apic_enabled(struct kvm_lapic *apic)
 {
-	return apic_sw_enabled(apic) &&	apic_hw_enabled(apic);
+	return kvm_apic_sw_enabled(apic) &&	kvm_apic_hw_enabled(apic);
 }
 
 #define LVT_MASK	\
@@ -139,36 +140,135 @@ static inline int apic_enabled(struct kvm_lapic *apic)
 	(LVT_MASK | APIC_MODE_MASK | APIC_INPUT_POLARITY | \
 	 APIC_LVT_REMOTE_IRR | APIC_LVT_LEVEL_TRIGGER)
 
+static inline int apic_x2apic_mode(struct kvm_lapic *apic)
+{
+	return apic->vcpu->arch.apic_base & X2APIC_ENABLE;
+}
+
 static inline int kvm_apic_id(struct kvm_lapic *apic)
 {
-	return (apic_get_reg(apic, APIC_ID) >> 24) & 0xff;
+	return (kvm_apic_get_reg(apic, APIC_ID) >> 24) & 0xff;
+}
+
+static inline u16 apic_cluster_id(struct kvm_apic_map *map, u32 ldr)
+{
+	u16 cid;
+	ldr >>= 32 - map->ldr_bits;
+	cid = (ldr >> map->cid_shift) & map->cid_mask;
+
+	BUG_ON(cid >= ARRAY_SIZE(map->logical_map));
+
+	return cid;
+}
+
+static inline u16 apic_logical_id(struct kvm_apic_map *map, u32 ldr)
+{
+	ldr >>= (32 - map->ldr_bits);
+	return ldr & map->lid_mask;
+}
+
+static void recalculate_apic_map(struct kvm *kvm)
+{
+	struct kvm_apic_map *new, *old = NULL;
+	struct kvm_vcpu *vcpu;
+	int i;
+
+	new = kzalloc(sizeof(struct kvm_apic_map), GFP_KERNEL);
+
+	mutex_lock(&kvm->arch.apic_map_lock);
+
+	if (!new)
+		goto out;
+
+	new->ldr_bits = 8;
+	/* flat mode is default */
+	new->cid_shift = 8;
+	new->cid_mask = 0;
+	new->lid_mask = 0xff;
+
+	kvm_for_each_vcpu(i, vcpu, kvm) {
+		struct kvm_lapic *apic = vcpu->arch.apic;
+		u16 cid, lid;
+		u32 ldr;
+
+		if (!kvm_apic_present(vcpu))
+			continue;
+
+		/*
+		 * All APICs have to be configured in the same mode by an OS.
+		 * We take advatage of this while building logical id loockup
+		 * table. After reset APICs are in xapic/flat mode, so if we
+		 * find apic with different setting we assume this is the mode
+		 * OS wants all apics to be in; build lookup table accordingly.
+		 */
+		if (apic_x2apic_mode(apic)) {
+			new->ldr_bits = 32;
+			new->cid_shift = 16;
+			new->cid_mask = new->lid_mask = 0xffff;
+		} else if (kvm_apic_sw_enabled(apic) &&
+				!new->cid_mask /* flat mode */ &&
+				kvm_apic_get_reg(apic, APIC_DFR) == APIC_DFR_CLUSTER) {
+			new->cid_shift = 4;
+			new->cid_mask = 0xf;
+			new->lid_mask = 0xf;
+		}
+
+		new->phys_map[kvm_apic_id(apic)] = apic;
+
+		ldr = kvm_apic_get_reg(apic, APIC_LDR);
+		cid = apic_cluster_id(new, ldr);
+		lid = apic_logical_id(new, ldr);
+
+		if (lid)
+			new->logical_map[cid][ffs(lid) - 1] = apic;
+	}
+out:
+	old = rcu_dereference_protected(kvm->arch.apic_map,
+			lockdep_is_held(&kvm->arch.apic_map_lock));
+	rcu_assign_pointer(kvm->arch.apic_map, new);
+	mutex_unlock(&kvm->arch.apic_map_lock);
+
+	if (old)
+		kfree_rcu(old, rcu);
+}
+
+static inline void kvm_apic_set_id(struct kvm_lapic *apic, u8 id)
+{
+	apic_set_reg(apic, APIC_ID, id << 24);
+	recalculate_apic_map(apic->vcpu->kvm);
+}
+
+static inline void kvm_apic_set_ldr(struct kvm_lapic *apic, u32 id)
+{
+	apic_set_reg(apic, APIC_LDR, id);
+	recalculate_apic_map(apic->vcpu->kvm);
 }
 
 static inline int apic_lvt_enabled(struct kvm_lapic *apic, int lvt_type)
 {
-	return !(apic_get_reg(apic, lvt_type) & APIC_LVT_MASKED);
+	return !(kvm_apic_get_reg(apic, lvt_type) & APIC_LVT_MASKED);
 }
 
 static inline int apic_lvt_vector(struct kvm_lapic *apic, int lvt_type)
 {
-	return apic_get_reg(apic, lvt_type) & APIC_VECTOR_MASK;
+	return kvm_apic_get_reg(apic, lvt_type) & APIC_VECTOR_MASK;
 }
 
 static inline int apic_lvtt_oneshot(struct kvm_lapic *apic)
 {
-	return ((apic_get_reg(apic, APIC_LVTT) &
+	return ((kvm_apic_get_reg(apic, APIC_LVTT) &
 		apic->lapic_timer.timer_mode_mask) == APIC_LVT_TIMER_ONESHOT);
 }
 
 static inline int apic_lvtt_period(struct kvm_lapic *apic)
 {
-	return ((apic_get_reg(apic, APIC_LVTT) &
+	return ((kvm_apic_get_reg(apic, APIC_LVTT) &
 		apic->lapic_timer.timer_mode_mask) == APIC_LVT_TIMER_PERIODIC);
 }
 
 static inline int apic_lvtt_tscdeadline(struct kvm_lapic *apic)
 {
-	return ((apic_get_reg(apic, APIC_LVTT) &
+	return ((kvm_apic_get_reg(apic, APIC_LVTT) &
 		apic->lapic_timer.timer_mode_mask) ==
 			APIC_LVT_TIMER_TSCDEADLINE);
 }
@@ -184,7 +284,7 @@ void kvm_apic_set_version(struct kvm_vcpu *vcpu)
 	struct kvm_cpuid_entry2 *feat;
 	u32 v = APIC_VERSION;
 
-	if (!irqchip_in_kernel(vcpu->kvm))
+	if (!kvm_vcpu_has_lapic(vcpu))
 		return;
 
 	feat = kvm_find_cpuid_entry(apic->vcpu, 0x1, 0);
@@ -193,12 +293,7 @@ void kvm_apic_set_version(struct kvm_vcpu *vcpu)
 	apic_set_reg(apic, APIC_LVR, v);
 }
 
-static inline int apic_x2apic_mode(struct kvm_lapic *apic)
+static const unsigned int apic_lvt_mask[APIC_LVT_NUM] = {
-{
-	return apic->vcpu->arch.apic_base & X2APIC_ENABLE;
-}
-
-static unsigned int apic_lvt_mask[APIC_LVT_NUM] = {
 	LVT_MASK ,      /* part LVTT mask, timer mode mask added at runtime */
 	LVT_MASK | APIC_MODE_MASK,	/* LVTTHMR */
 	LVT_MASK | APIC_MODE_MASK,	/* LVTPC */
@@ -208,25 +303,30 @@ static unsigned int apic_lvt_mask[APIC_LVT_NUM] = {
 
 static int find_highest_vector(void *bitmap)
 {
-	u32 *word = bitmap;
+	int vec;
-	int word_offset = MAX_APIC_VECTOR >> 5;
+	u32 *reg;
 
-	while ((word_offset != 0) && (word[(--word_offset) << 2] == 0))
+	for (vec = MAX_APIC_VECTOR - APIC_VECTORS_PER_REG;
-		continue;
+	     vec >= 0; vec -= APIC_VECTORS_PER_REG) {
+		reg = bitmap + REG_POS(vec);
+		if (*reg)
+			return fls(*reg) - 1 + vec;
+	}
 
-	if (likely(!word_offset && !word[0]))
 	return -1;
-	else
-		return fls(word[word_offset << 2]) - 1 + (word_offset << 5);
 }
 
 static u8 count_vectors(void *bitmap)
 {
-	u32 *word = bitmap;
+	int vec;
-	int word_offset;
+	u32 *reg;
 	u8 count = 0;
-	for (word_offset = 0; word_offset < MAX_APIC_VECTOR >> 5; ++word_offset)
+
-		count += hweight32(word[word_offset << 2]);
+	for (vec = 0; vec < MAX_APIC_VECTOR; vec += APIC_VECTORS_PER_REG) {
+		reg = bitmap + REG_POS(vec);
+		count += hweight32(*reg);
+	}
+
 	return count;
 }
 
@@ -285,7 +385,6 @@ static inline void apic_clear_isr(int vec, struct kvm_lapic *apic)
 
 int kvm_lapic_find_highest_irr(struct kvm_vcpu *vcpu)
 {
-	struct kvm_lapic *apic = vcpu->arch.apic;
 	int highest_irr;
 
 	/* This may race with setting of irr in __apic_accept_irq() and
@@ -293,9 +392,9 @@ int kvm_lapic_find_highest_irr(struct kvm_vcpu *vcpu)
 	 * will cause vmexit immediately and the value will be recalculated
 	 * on the next vmentry.
 	 */
-	if (!apic)
+	if (!kvm_vcpu_has_lapic(vcpu))
 		return 0;
-	highest_irr = apic_find_highest_irr(apic);
+	highest_irr = apic_find_highest_irr(vcpu->arch.apic);
 
 	return highest_irr;
 }
@@ -378,8 +477,8 @@ static void apic_update_ppr(struct kvm_lapic *apic)
 	u32 tpr, isrv, ppr, old_ppr;
 	int isr;
 
-	old_ppr = apic_get_reg(apic, APIC_PROCPRI);
+	old_ppr = kvm_apic_get_reg(apic, APIC_PROCPRI);
-	tpr = apic_get_reg(apic, APIC_TASKPRI);
+	tpr = kvm_apic_get_reg(apic, APIC_TASKPRI);
 	isr = apic_find_highest_isr(apic);
 	isrv = (isr != -1) ? isr : 0;
 
@@ -415,13 +514,13 @@ int kvm_apic_match_logical_addr(struct kvm_lapic *apic, u8 mda)
 	u32 logical_id;
 
 	if (apic_x2apic_mode(apic)) {
-		logical_id = apic_get_reg(apic, APIC_LDR);
+		logical_id = kvm_apic_get_reg(apic, APIC_LDR);
 		return logical_id & mda;
 	}
 
-	logical_id = GET_APIC_LOGICAL_ID(apic_get_reg(apic, APIC_LDR));
+	logical_id = GET_APIC_LOGICAL_ID(kvm_apic_get_reg(apic, APIC_LDR));
 
-	switch (apic_get_reg(apic, APIC_DFR)) {
+	switch (kvm_apic_get_reg(apic, APIC_DFR)) {
 	case APIC_DFR_FLAT:
 		if (logical_id & mda)
 			result = 1;
@@ -433,7 +532,7 @@ int kvm_apic_match_logical_addr(struct kvm_lapic *apic, u8 mda)
 		break;
 	default:
 		apic_debug("Bad DFR vcpu %d: %08x\n",
-			   apic->vcpu->vcpu_id, apic_get_reg(apic, APIC_DFR));
+			   apic->vcpu->vcpu_id, kvm_apic_get_reg(apic, APIC_DFR));
 		break;
 	}
 
@@ -478,6 +577,72 @@ int kvm_apic_match_dest(struct kvm_vcpu *vcpu, struct kvm_lapic *source,
 	return result;
 }
 
+bool kvm_irq_delivery_to_apic_fast(struct kvm *kvm, struct kvm_lapic *src,
+		struct kvm_lapic_irq *irq, int *r)
+{
+	struct kvm_apic_map *map;
+	unsigned long bitmap = 1;
+	struct kvm_lapic **dst;
+	int i;
+	bool ret = false;
+
+	*r = -1;
+
+	if (irq->shorthand == APIC_DEST_SELF) {
+		*r = kvm_apic_set_irq(src->vcpu, irq);
+		return true;
+	}
+
+	if (irq->shorthand)
+		return false;
+
+	rcu_read_lock();
+	map = rcu_dereference(kvm->arch.apic_map);
+
+	if (!map)
+		goto out;
+
+	if (irq->dest_mode == 0) { /* physical mode */
+		if (irq->delivery_mode == APIC_DM_LOWEST ||
+				irq->dest_id == 0xff)
+			goto out;
+		dst = &map->phys_map[irq->dest_id & 0xff];
+	} else {
+		u32 mda = irq->dest_id << (32 - map->ldr_bits);
+
+		dst = map->logical_map[apic_cluster_id(map, mda)];
+
+		bitmap = apic_logical_id(map, mda);
+
+		if (irq->delivery_mode == APIC_DM_LOWEST) {
+			int l = -1;
+			for_each_set_bit(i, &bitmap, 16) {
+				if (!dst[i])
+					continue;
+				if (l < 0)
+					l = i;
+				else if (kvm_apic_compare_prio(dst[i]->vcpu, dst[l]->vcpu) < 0)
+					l = i;
+			}
+
+			bitmap = (l >= 0) ? 1 << l : 0;
+		}
+	}
+
+	for_each_set_bit(i, &bitmap, 16) {
+		if (!dst[i])
+			continue;
+		if (*r < 0)
+			*r = 0;
+		*r += kvm_apic_set_irq(dst[i]->vcpu, irq);
+	}
+
+	ret = true;
+out:
+	rcu_read_unlock();
+	return ret;
+}
+
 /*
  * Add a pending IRQ into lapic.
  * Return 1 if successfully added and 0 if discarded.
@@ -591,7 +756,7 @@ static int apic_set_eoi(struct kvm_lapic *apic)
 	apic_clear_isr(vector, apic);
 	apic_update_ppr(apic);
 
-	if (!(apic_get_reg(apic, APIC_SPIV) & APIC_SPIV_DIRECTED_EOI) &&
+	if (!(kvm_apic_get_reg(apic, APIC_SPIV) & APIC_SPIV_DIRECTED_EOI) &&
 	    kvm_ioapic_handles_vector(apic->vcpu->kvm, vector)) {
 		int trigger_mode;
 		if (apic_test_vector(vector, apic->regs + APIC_TMR))
@@ -606,8 +771,8 @@ static int apic_set_eoi(struct kvm_lapic *apic)
 
 static void apic_send_ipi(struct kvm_lapic *apic)
 {
-	u32 icr_low = apic_get_reg(apic, APIC_ICR);
+	u32 icr_low = kvm_apic_get_reg(apic, APIC_ICR);
-	u32 icr_high = apic_get_reg(apic, APIC_ICR2);
+	u32 icr_high = kvm_apic_get_reg(apic, APIC_ICR2);
 	struct kvm_lapic_irq irq;
 
 	irq.vector = icr_low & APIC_VECTOR_MASK;
@@ -642,7 +807,7 @@ static u32 apic_get_tmcct(struct kvm_lapic *apic)
 	ASSERT(apic != NULL);
 
 	/* if initial count is 0, current count should also be 0 */
-	if (apic_get_reg(apic, APIC_TMICT) == 0)
+	if (kvm_apic_get_reg(apic, APIC_TMICT) == 0)
 		return 0;
 
 	remaining = hrtimer_get_remaining(&apic->lapic_timer.timer);
@@ -696,13 +861,15 @@ static u32 __apic_read(struct kvm_lapic *apic, unsigned int offset)
 
 		val = apic_get_tmcct(apic);
 		break;
-
+	case APIC_PROCPRI:
+		apic_update_ppr(apic);
+		val = kvm_apic_get_reg(apic, offset);
+		break;
 	case APIC_TASKPRI:
 		report_tpr_access(apic, false);
 		/* fall thru */
 	default:
-		apic_update_ppr(apic);
+		val = kvm_apic_get_reg(apic, offset);
-		val = apic_get_reg(apic, offset);
 		break;
 	}
 
@@ -719,7 +886,7 @@ static int apic_reg_read(struct kvm_lapic *apic, u32 offset, int len,
 {
 	unsigned char alignment = offset & 0xf;
 	u32 result;
-	/* this bitmask has a bit cleared for each reserver register */
+	/* this bitmask has a bit cleared for each reserved register */
 	static const u64 rmask = 0x43ff01ffffffe70cULL;
 
 	if ((alignment + len) > 4) {
@@ -754,7 +921,7 @@ static int apic_reg_read(struct kvm_lapic *apic, u32 offset, int len,
 
 static int apic_mmio_in_range(struct kvm_lapic *apic, gpa_t addr)
 {
-	return apic_hw_enabled(apic) &&
+	return kvm_apic_hw_enabled(apic) &&
 	    addr >= apic->base_address &&
 	    addr < apic->base_address + LAPIC_MMIO_LENGTH;
 }
@@ -777,7 +944,7 @@ static void update_divide_count(struct kvm_lapic *apic)
 {
 	u32 tmp1, tmp2, tdcr;
 
-	tdcr = apic_get_reg(apic, APIC_TDCR);
+	tdcr = kvm_apic_get_reg(apic, APIC_TDCR);
 	tmp1 = tdcr & 0xf;
 	tmp2 = ((tmp1 & 0x3) | ((tmp1 & 0x8) >> 1)) + 1;
 	apic->divide_count = 0x1 << (tmp2 & 0x7);
@@ -792,9 +959,9 @@ static void start_apic_timer(struct kvm_lapic *apic)
 	atomic_set(&apic->lapic_timer.pending, 0);
 
 	if (apic_lvtt_period(apic) || apic_lvtt_oneshot(apic)) {
-		/* lapic timer in oneshot or peroidic mode */
+		/* lapic timer in oneshot or periodic mode */
 		now = apic->lapic_timer.timer.base->get_time();
-		apic->lapic_timer.period = (u64)apic_get_reg(apic, APIC_TMICT)
+		apic->lapic_timer.period = (u64)kvm_apic_get_reg(apic, APIC_TMICT)
 			    * APIC_BUS_CYCLE_NS * apic->divide_count;
 
 		if (!apic->lapic_timer.period)
@@ -826,7 +993,7 @@ static void start_apic_timer(struct kvm_lapic *apic)
 			   "timer initial count 0x%x, period %lldns, "
 			   "expire @ 0x%016" PRIx64 ".\n", __func__,
 			   APIC_BUS_CYCLE_NS, ktime_to_ns(now),
-			   apic_get_reg(apic, APIC_TMICT),
+			   kvm_apic_get_reg(apic, APIC_TMICT),
 			   apic->lapic_timer.period,
 			   ktime_to_ns(ktime_add_ns(now,
 					apic->lapic_timer.period)));
@@ -858,7 +1025,7 @@ static void start_apic_timer(struct kvm_lapic *apic)
 
 static void apic_manage_nmi_watchdog(struct kvm_lapic *apic, u32 lvt0_val)
 {
-	int nmi_wd_enabled = apic_lvt_nmi_mode(apic_get_reg(apic, APIC_LVT0));
+	int nmi_wd_enabled = apic_lvt_nmi_mode(kvm_apic_get_reg(apic, APIC_LVT0));
 
 	if (apic_lvt_nmi_mode(lvt0_val)) {
 		if (!nmi_wd_enabled) {
@@ -879,7 +1046,7 @@ static int apic_reg_write(struct kvm_lapic *apic, u32 reg, u32 val)
 	switch (reg) {
 	case APIC_ID:		/* Local APIC ID */
 		if (!apic_x2apic_mode(apic))
-			apic_set_reg(apic, APIC_ID, val);
+			kvm_apic_set_id(apic, val >> 24);
 		else
 			ret = 1;
 		break;
@@ -895,29 +1062,30 @@ static int apic_reg_write(struct kvm_lapic *apic, u32 reg, u32 val)
 
 	case APIC_LDR:
 		if (!apic_x2apic_mode(apic))
-			apic_set_reg(apic, APIC_LDR, val & APIC_LDR_MASK);
+			kvm_apic_set_ldr(apic, val & APIC_LDR_MASK);
 		else
 			ret = 1;
 		break;
 
 	case APIC_DFR:
-		if (!apic_x2apic_mode(apic))
+		if (!apic_x2apic_mode(apic)) {
 			apic_set_reg(apic, APIC_DFR, val | 0x0FFFFFFF);
-		else
+			recalculate_apic_map(apic->vcpu->kvm);
+		} else
 			ret = 1;
 		break;
 
 	case APIC_SPIV: {
 		u32 mask = 0x3ff;
-		if (apic_get_reg(apic, APIC_LVR) & APIC_LVR_DIRECTED_EOI)
+		if (kvm_apic_get_reg(apic, APIC_LVR) & APIC_LVR_DIRECTED_EOI)
 			mask |= APIC_SPIV_DIRECTED_EOI;
-		apic_set_reg(apic, APIC_SPIV, val & mask);
+		apic_set_spiv(apic, val & mask);
 		if (!(val & APIC_SPIV_APIC_ENABLED)) {
 			int i;
 			u32 lvt_val;
 
 			for (i = 0; i < APIC_LVT_NUM; i++) {
-				lvt_val = apic_get_reg(apic,
+				lvt_val = kvm_apic_get_reg(apic,
 						       APIC_LVTT + 0x10 * i);
 				apic_set_reg(apic, APIC_LVTT + 0x10 * i,
 					     lvt_val | APIC_LVT_MASKED);
@@ -946,7 +1114,7 @@ static int apic_reg_write(struct kvm_lapic *apic, u32 reg, u32 val)
 	case APIC_LVT1:
 	case APIC_LVTERR:
 		/* TODO: Check vector */
-		if (!apic_sw_enabled(apic))
+		if (!kvm_apic_sw_enabled(apic))
 			val |= APIC_LVT_MASKED;
 
 		val &= apic_lvt_mask[(reg - APIC_LVTT) >> 4];
@@ -955,12 +1123,12 @@ static int apic_reg_write(struct kvm_lapic *apic, u32 reg, u32 val)
 		break;
 
 	case APIC_LVTT:
-		if ((apic_get_reg(apic, APIC_LVTT) &
+		if ((kvm_apic_get_reg(apic, APIC_LVTT) &
 		    apic->lapic_timer.timer_mode_mask) !=
 		   (val & apic->lapic_timer.timer_mode_mask))
 			hrtimer_cancel(&apic->lapic_timer.timer);
 
-		if (!apic_sw_enabled(apic))
+		if (!kvm_apic_sw_enabled(apic))
 			val |= APIC_LVT_MASKED;
 		val &= (apic_lvt_mask[0] | apic->lapic_timer.timer_mode_mask);
 		apic_set_reg(apic, APIC_LVTT, val);
@@ -1039,24 +1207,30 @@ static int apic_mmio_write(struct kvm_io_device *this,
 
 void kvm_lapic_set_eoi(struct kvm_vcpu *vcpu)
 {
-	struct kvm_lapic *apic = vcpu->arch.apic;
+	if (kvm_vcpu_has_lapic(vcpu))
-
-	if (apic)
 		apic_reg_write(vcpu->arch.apic, APIC_EOI, 0);
 }
 EXPORT_SYMBOL_GPL(kvm_lapic_set_eoi);
 
 void kvm_free_lapic(struct kvm_vcpu *vcpu)
 {
+	struct kvm_lapic *apic = vcpu->arch.apic;
+
 	if (!vcpu->arch.apic)
 		return;
 
-	hrtimer_cancel(&vcpu->arch.apic->lapic_timer.timer);
+	hrtimer_cancel(&apic->lapic_timer.timer);
 
-	if (vcpu->arch.apic->regs)
+	if (!(vcpu->arch.apic_base & MSR_IA32_APICBASE_ENABLE))
-		free_page((unsigned long)vcpu->arch.apic->regs);
+		static_key_slow_dec_deferred(&apic_hw_disabled);
 
-	kfree(vcpu->arch.apic);
+	if (!(kvm_apic_get_reg(apic, APIC_SPIV) & APIC_SPIV_APIC_ENABLED))
+		static_key_slow_dec_deferred(&apic_sw_disabled);
+
+	if (apic->regs)
+		free_page((unsigned long)apic->regs);
+
+	kfree(apic);
 }
 
 /*
@@ -1068,10 +1242,9 @@ void kvm_free_lapic(struct kvm_vcpu *vcpu)
 u64 kvm_get_lapic_tscdeadline_msr(struct kvm_vcpu *vcpu)
 {
 	struct kvm_lapic *apic = vcpu->arch.apic;
-	if (!apic)
-		return 0;
 
-	if (apic_lvtt_oneshot(apic) || apic_lvtt_period(apic))
+	if (!kvm_vcpu_has_lapic(vcpu) || apic_lvtt_oneshot(apic) ||
+			apic_lvtt_period(apic))
 		return 0;
 
 	return apic->lapic_timer.tscdeadline;
@@ -1080,10 +1253,9 @@ u64 kvm_get_lapic_tscdeadline_msr(struct kvm_vcpu *vcpu)
 void kvm_set_lapic_tscdeadline_msr(struct kvm_vcpu *vcpu, u64 data)
 {
 	struct kvm_lapic *apic = vcpu->arch.apic;
-	if (!apic)
-		return;
 
-	if (apic_lvtt_oneshot(apic) || apic_lvtt_period(apic))
+	if (!kvm_vcpu_has_lapic(vcpu) || apic_lvtt_oneshot(apic) ||
+			apic_lvtt_period(apic))
 		return;
 
 	hrtimer_cancel(&apic->lapic_timer.timer);
@@ -1095,20 +1267,21 @@ void kvm_lapic_set_tpr(struct kvm_vcpu *vcpu, unsigned long cr8)
 {
 	struct kvm_lapic *apic = vcpu->arch.apic;
 
-	if (!apic)
+	if (!kvm_vcpu_has_lapic(vcpu))
 		return;
+
 	apic_set_tpr(apic, ((cr8 & 0x0f) << 4)
-		     | (apic_get_reg(apic, APIC_TASKPRI) & 4));
+		     | (kvm_apic_get_reg(apic, APIC_TASKPRI) & 4));
 }
 
 u64 kvm_lapic_get_cr8(struct kvm_vcpu *vcpu)
 {
-	struct kvm_lapic *apic = vcpu->arch.apic;
 	u64 tpr;
 
-	if (!apic)
+	if (!kvm_vcpu_has_lapic(vcpu))
 		return 0;
-	tpr = (u64) apic_get_reg(apic, APIC_TASKPRI);
+
+	tpr = (u64) kvm_apic_get_reg(vcpu->arch.apic, APIC_TASKPRI);
 
 	return (tpr & 0xf0) >> 4;
 }
@@ -1123,6 +1296,15 @@ void kvm_lapic_set_base(struct kvm_vcpu *vcpu, u64 value)
 		return;
 	}
 
+	/* update jump label if enable bit changes */
+	if ((vcpu->arch.apic_base ^ value) & MSR_IA32_APICBASE_ENABLE) {
+		if (value & MSR_IA32_APICBASE_ENABLE)
+			static_key_slow_dec_deferred(&apic_hw_disabled);
+		else
+			static_key_slow_inc(&apic_hw_disabled.key);
+		recalculate_apic_map(vcpu->kvm);
+	}
+
 	if (!kvm_vcpu_is_bsp(apic->vcpu))
 		value &= ~MSR_IA32_APICBASE_BSP;
 
@@ -1130,7 +1312,7 @@ void kvm_lapic_set_base(struct kvm_vcpu *vcpu, u64 value)
 	if (apic_x2apic_mode(apic)) {
 		u32 id = kvm_apic_id(apic);
 		u32 ldr = ((id & ~0xf) << 16) | (1 << (id & 0xf));
-		apic_set_reg(apic, APIC_LDR, ldr);
+		kvm_apic_set_ldr(apic, ldr);
 	}
 	apic->base_address = apic->vcpu->arch.apic_base &
 			     MSR_IA32_APICBASE_BASE;
@@ -1155,7 +1337,7 @@ void kvm_lapic_reset(struct kvm_vcpu *vcpu)
 	/* Stop the timer in case it's a reset to an active apic */
 	hrtimer_cancel(&apic->lapic_timer.timer);
 
-	apic_set_reg(apic, APIC_ID, vcpu->vcpu_id << 24);
+	kvm_apic_set_id(apic, vcpu->vcpu_id);
 	kvm_apic_set_version(apic->vcpu);
 
 	for (i = 0; i < APIC_LVT_NUM; i++)
@@ -1164,9 +1346,9 @@ void kvm_lapic_reset(struct kvm_vcpu *vcpu)
 		     SET_APIC_DELIVERY_MODE(0, APIC_MODE_EXTINT));
 
 	apic_set_reg(apic, APIC_DFR, 0xffffffffU);
-	apic_set_reg(apic, APIC_SPIV, 0xff);
+	apic_set_spiv(apic, 0xff);
 	apic_set_reg(apic, APIC_TASKPRI, 0);
-	apic_set_reg(apic, APIC_LDR, 0);
+	kvm_apic_set_ldr(apic, 0);
 	apic_set_reg(apic, APIC_ESR, 0);
 	apic_set_reg(apic, APIC_ICR, 0);
 	apic_set_reg(apic, APIC_ICR2, 0);
@@ -1183,7 +1365,8 @@ void kvm_lapic_reset(struct kvm_vcpu *vcpu)
 	update_divide_count(apic);
 	atomic_set(&apic->lapic_timer.pending, 0);
 	if (kvm_vcpu_is_bsp(vcpu))
-		vcpu->arch.apic_base |= MSR_IA32_APICBASE_BSP;
+		kvm_lapic_set_base(vcpu,
+				vcpu->arch.apic_base | MSR_IA32_APICBASE_BSP);
 	vcpu->arch.pv_eoi.msr_val = 0;
 	apic_update_ppr(apic);
 
@@ -1196,45 +1379,34 @@ void kvm_lapic_reset(struct kvm_vcpu *vcpu)
 		   vcpu->arch.apic_base, apic->base_address);
 }
 
-bool kvm_apic_present(struct kvm_vcpu *vcpu)
-{
-	return vcpu->arch.apic && apic_hw_enabled(vcpu->arch.apic);
-}
-
-int kvm_lapic_enabled(struct kvm_vcpu *vcpu)
-{
-	return kvm_apic_present(vcpu) && apic_sw_enabled(vcpu->arch.apic);
-}
-
 /*
  *----------------------------------------------------------------------
  * timer interface
  *----------------------------------------------------------------------
  */
 
-static bool lapic_is_periodic(struct kvm_timer *ktimer)
+static bool lapic_is_periodic(struct kvm_lapic *apic)
 {
-	struct kvm_lapic *apic = container_of(ktimer, struct kvm_lapic,
-					      lapic_timer);
 	return apic_lvtt_period(apic);
 }
 
 int apic_has_pending_timer(struct kvm_vcpu *vcpu)
 {
-	struct kvm_lapic *lapic = vcpu->arch.apic;
+	struct kvm_lapic *apic = vcpu->arch.apic;
 
-	if (lapic && apic_enabled(lapic) && apic_lvt_enabled(lapic, APIC_LVTT))
+	if (kvm_vcpu_has_lapic(vcpu) && apic_enabled(apic) &&
-		return atomic_read(&lapic->lapic_timer.pending);
+			apic_lvt_enabled(apic, APIC_LVTT))
+		return atomic_read(&apic->lapic_timer.pending);
 
 	return 0;
 }
 
 int kvm_apic_local_deliver(struct kvm_lapic *apic, int lvt_type)
 {
-	u32 reg = apic_get_reg(apic, lvt_type);
+	u32 reg = kvm_apic_get_reg(apic, lvt_type);
 	int vector, mode, trig_mode;
 
-	if (apic_hw_enabled(apic) && !(reg & APIC_LVT_MASKED)) {
+	if (kvm_apic_hw_enabled(apic) && !(reg & APIC_LVT_MASKED)) {
 		vector = reg & APIC_VECTOR_MASK;
 		mode = reg & APIC_MODE_MASK;
 		trig_mode = reg & APIC_LVT_LEVEL_TRIGGER;
@@ -1251,15 +1423,40 @@ void kvm_apic_nmi_wd_deliver(struct kvm_vcpu *vcpu)
 		kvm_apic_local_deliver(apic, APIC_LVT0);
 }
 
-static struct kvm_timer_ops lapic_timer_ops = {
-	.is_periodic = lapic_is_periodic,
-};
-
 static const struct kvm_io_device_ops apic_mmio_ops = {
 	.read     = apic_mmio_read,
 	.write    = apic_mmio_write,
 };
 
+static enum hrtimer_restart apic_timer_fn(struct hrtimer *data)
+{
+	struct kvm_timer *ktimer = container_of(data, struct kvm_timer, timer);
+	struct kvm_lapic *apic = container_of(ktimer, struct kvm_lapic, lapic_timer);
+	struct kvm_vcpu *vcpu = apic->vcpu;
+	wait_queue_head_t *q = &vcpu->wq;
+
+	/*
+	 * There is a race window between reading and incrementing, but we do
+	 * not care about potentially losing timer events in the !reinject
+	 * case anyway. Note: KVM_REQ_PENDING_TIMER is implicitly checked
+	 * in vcpu_enter_guest.
+	 */
+	if (!atomic_read(&ktimer->pending)) {
+		atomic_inc(&ktimer->pending);
+		/* FIXME: this code should not know anything about vcpus */
+		kvm_make_request(KVM_REQ_PENDING_TIMER, vcpu);
+	}
+
+	if (waitqueue_active(q))
+		wake_up_interruptible(q);
+
+	if (lapic_is_periodic(apic)) {
+		hrtimer_add_expires_ns(&ktimer->timer, ktimer->period);
+		return HRTIMER_RESTART;
+	} else
+		return HRTIMER_NORESTART;
+}
+
 int kvm_create_lapic(struct kvm_vcpu *vcpu)
 {
 	struct kvm_lapic *apic;
@@ -1283,14 +1480,17 @@ int kvm_create_lapic(struct kvm_vcpu *vcpu)
 
 	hrtimer_init(&apic->lapic_timer.timer, CLOCK_MONOTONIC,
 		     HRTIMER_MODE_ABS);
-	apic->lapic_timer.timer.function = kvm_timer_fn;
+	apic->lapic_timer.timer.function = apic_timer_fn;
-	apic->lapic_timer.t_ops = &lapic_timer_ops;
-	apic->lapic_timer.kvm = vcpu->kvm;
-	apic->lapic_timer.vcpu = vcpu;
 
-	apic->base_address = APIC_DEFAULT_PHYS_BASE;
+	/*
-	vcpu->arch.apic_base = APIC_DEFAULT_PHYS_BASE;
+	 * APIC is created enabled. This will prevent kvm_lapic_set_base from
+	 * thinking that APIC satet has changed.
+	 */
+	vcpu->arch.apic_base = MSR_IA32_APICBASE_ENABLE;
+	kvm_lapic_set_base(vcpu,
+			APIC_DEFAULT_PHYS_BASE | MSR_IA32_APICBASE_ENABLE);
 
+	static_key_slow_inc(&apic_sw_disabled.key); /* sw disabled at reset */
 	kvm_lapic_reset(vcpu);
 	kvm_iodevice_init(&apic->dev, &apic_mmio_ops);
 
@@ -1306,23 +1506,23 @@ int kvm_apic_has_interrupt(struct kvm_vcpu *vcpu)
 	struct kvm_lapic *apic = vcpu->arch.apic;
 	int highest_irr;
 
-	if (!apic || !apic_enabled(apic))
+	if (!kvm_vcpu_has_lapic(vcpu) || !apic_enabled(apic))
 		return -1;
 
 	apic_update_ppr(apic);
 	highest_irr = apic_find_highest_irr(apic);
 	if ((highest_irr == -1) ||
-	    ((highest_irr & 0xF0) <= apic_get_reg(apic, APIC_PROCPRI)))
+	    ((highest_irr & 0xF0) <= kvm_apic_get_reg(apic, APIC_PROCPRI)))
 		return -1;
 	return highest_irr;
 }
 
 int kvm_apic_accept_pic_intr(struct kvm_vcpu *vcpu)
 {
-	u32 lvt0 = apic_get_reg(vcpu->arch.apic, APIC_LVT0);
+	u32 lvt0 = kvm_apic_get_reg(vcpu->arch.apic, APIC_LVT0);
 	int r = 0;
 
-	if (!apic_hw_enabled(vcpu->arch.apic))
+	if (!kvm_apic_hw_enabled(vcpu->arch.apic))
 		r = 1;
 	if ((lvt0 & APIC_LVT_MASKED) == 0 &&
 	    GET_APIC_DELIVERY_MODE(lvt0) == APIC_MODE_EXTINT)
@@ -1334,7 +1534,10 @@ void kvm_inject_apic_timer_irqs(struct kvm_vcpu *vcpu)
 {
 	struct kvm_lapic *apic = vcpu->arch.apic;
 
-	if (apic && atomic_read(&apic->lapic_timer.pending) > 0) {
+	if (!kvm_vcpu_has_lapic(vcpu))
+		return;
+
+	if (atomic_read(&apic->lapic_timer.pending) > 0) {
 		if (kvm_apic_local_deliver(apic, APIC_LVTT))
 			atomic_dec(&apic->lapic_timer.pending);
 	}
@@ -1354,12 +1557,17 @@ int kvm_get_apic_interrupt(struct kvm_vcpu *vcpu)
 	return vector;
 }
 
-void kvm_apic_post_state_restore(struct kvm_vcpu *vcpu)
+void kvm_apic_post_state_restore(struct kvm_vcpu *vcpu,
+		struct kvm_lapic_state *s)
 {
 	struct kvm_lapic *apic = vcpu->arch.apic;
 
-	apic->base_address = vcpu->arch.apic_base &
+	kvm_lapic_set_base(vcpu, vcpu->arch.apic_base);
-			     MSR_IA32_APICBASE_BASE;
+	/* set SPIV separately to get count of SW disabled APICs right */
+	apic_set_spiv(apic, *((u32 *)(s->regs + APIC_SPIV)));
+	memcpy(vcpu->arch.apic->regs, s->regs, sizeof *s);
+	/* call kvm_apic_set_id() to put apic into apic_map */
+	kvm_apic_set_id(apic, kvm_apic_id(apic));
 	kvm_apic_set_version(vcpu);
 
 	apic_update_ppr(apic);
@@ -1374,13 +1582,12 @@ void kvm_apic_post_state_restore(struct kvm_vcpu *vcpu)
 
 void __kvm_migrate_apic_timer(struct kvm_vcpu *vcpu)
 {
-	struct kvm_lapic *apic = vcpu->arch.apic;
 	struct hrtimer *timer;
 
-	if (!apic)
+	if (!kvm_vcpu_has_lapic(vcpu))
 		return;
 
-	timer = &apic->lapic_timer.timer;
+	timer = &vcpu->arch.apic->lapic_timer.timer;
 	if (hrtimer_cancel(timer))
 		hrtimer_start_expires(timer, HRTIMER_MODE_ABS);
 }
@@ -1478,7 +1685,7 @@ void kvm_lapic_sync_to_vapic(struct kvm_vcpu *vcpu)
 	if (!test_bit(KVM_APIC_CHECK_VAPIC, &vcpu->arch.apic_attention))
 		return;
 
-	tpr = apic_get_reg(apic, APIC_TASKPRI) & 0xff;
+	tpr = kvm_apic_get_reg(apic, APIC_TASKPRI) & 0xff;
 	max_irr = apic_find_highest_irr(apic);
 	if (max_irr < 0)
 		max_irr = 0;
@@ -1537,7 +1744,7 @@ int kvm_hv_vapic_msr_write(struct kvm_vcpu *vcpu, u32 reg, u64 data)
 {
 	struct kvm_lapic *apic = vcpu->arch.apic;
 
-	if (!irqchip_in_kernel(vcpu->kvm))
+	if (!kvm_vcpu_has_lapic(vcpu))
 		return 1;
 
 	/* if this is ICR write vector before command */
@@ -1551,7 +1758,7 @@ int kvm_hv_vapic_msr_read(struct kvm_vcpu *vcpu, u32 reg, u64 *data)
 	struct kvm_lapic *apic = vcpu->arch.apic;
 	u32 low, high = 0;
 
-	if (!irqchip_in_kernel(vcpu->kvm))
+	if (!kvm_vcpu_has_lapic(vcpu))
 		return 1;
 
 	if (apic_reg_read(apic, reg, 4, &low))
@@ -1576,3 +1783,10 @@ int kvm_lapic_enable_pv_eoi(struct kvm_vcpu *vcpu, u64 data)
 	return kvm_gfn_to_hva_cache_init(vcpu->kvm, &vcpu->arch.pv_eoi.data,
 					 addr);
 }
+
+void kvm_lapic_init(void)
+{
+	/* do not patch jump label more than once per second */
+	jump_label_rate_limit(&apic_hw_disabled, HZ);
+	jump_label_rate_limit(&apic_sw_disabled, HZ);
+}

arch/x86/kvm/lapic.h

@@ -2,10 +2,17 @@
 #define __KVM_X86_LAPIC_H
 
 #include "iodev.h"
-#include "kvm_timer.h"
 
 #include <linux/kvm_host.h>
 
+struct kvm_timer {
+	struct hrtimer timer;
+	s64 period; 				/* unit: ns */
+	u32 timer_mode_mask;
+	u64 tscdeadline;
+	atomic_t pending;			/* accumulated triggered timers */
+};
+
 struct kvm_lapic {
 	unsigned long base_address;
 	struct kvm_io_device dev;
@@ -45,11 +52,13 @@ int kvm_apic_match_logical_addr(struct kvm_lapic *apic, u8 mda);
 int kvm_apic_set_irq(struct kvm_vcpu *vcpu, struct kvm_lapic_irq *irq);
 int kvm_apic_local_deliver(struct kvm_lapic *apic, int lvt_type);
 
+bool kvm_irq_delivery_to_apic_fast(struct kvm *kvm, struct kvm_lapic *src,
+		struct kvm_lapic_irq *irq, int *r);
+
 u64 kvm_get_apic_base(struct kvm_vcpu *vcpu);
 void kvm_set_apic_base(struct kvm_vcpu *vcpu, u64 data);
-void kvm_apic_post_state_restore(struct kvm_vcpu *vcpu);
+void kvm_apic_post_state_restore(struct kvm_vcpu *vcpu,
-int kvm_lapic_enabled(struct kvm_vcpu *vcpu);
+		struct kvm_lapic_state *s);
-bool kvm_apic_present(struct kvm_vcpu *vcpu);
 int kvm_lapic_find_highest_irr(struct kvm_vcpu *vcpu);
 
 u64 kvm_get_lapic_tscdeadline_msr(struct kvm_vcpu *vcpu);
@@ -71,4 +80,48 @@ static inline bool kvm_hv_vapic_assist_page_enabled(struct kvm_vcpu *vcpu)
 }
 
 int kvm_lapic_enable_pv_eoi(struct kvm_vcpu *vcpu, u64 data);
+void kvm_lapic_init(void);
+
+static inline u32 kvm_apic_get_reg(struct kvm_lapic *apic, int reg_off)
+{
+	        return *((u32 *) (apic->regs + reg_off));
+}
+
+extern struct static_key kvm_no_apic_vcpu;
+
+static inline bool kvm_vcpu_has_lapic(struct kvm_vcpu *vcpu)
+{
+	if (static_key_false(&kvm_no_apic_vcpu))
+		return vcpu->arch.apic;
+	return true;
+}
+
+extern struct static_key_deferred apic_hw_disabled;
+
+static inline int kvm_apic_hw_enabled(struct kvm_lapic *apic)
+{
+	if (static_key_false(&apic_hw_disabled.key))
+		return apic->vcpu->arch.apic_base & MSR_IA32_APICBASE_ENABLE;
+	return MSR_IA32_APICBASE_ENABLE;
+}
+
+extern struct static_key_deferred apic_sw_disabled;
+
+static inline int kvm_apic_sw_enabled(struct kvm_lapic *apic)
+{
+	if (static_key_false(&apic_sw_disabled.key))
+		return kvm_apic_get_reg(apic, APIC_SPIV) & APIC_SPIV_APIC_ENABLED;
+	return APIC_SPIV_APIC_ENABLED;
+}
+
+static inline bool kvm_apic_present(struct kvm_vcpu *vcpu)
+{
+	return kvm_vcpu_has_lapic(vcpu) && kvm_apic_hw_enabled(vcpu->arch.apic);
+}
+
+static inline int kvm_lapic_enabled(struct kvm_vcpu *vcpu)
+{
+	return kvm_apic_present(vcpu) && kvm_apic_sw_enabled(vcpu->arch.apic);
+}
+
 #endif

arch/x86/kvm/mmu.c

@@ -556,6 +556,14 @@ static int mmu_spte_clear_track_bits(u64 *sptep)
 		return 0;
 
 	pfn = spte_to_pfn(old_spte);
+
+	/*
+	 * KVM does not hold the refcount of the page used by
+	 * kvm mmu, before reclaiming the page, we should
+	 * unmap it from mmu first.
+	 */
+	WARN_ON(!kvm_is_mmio_pfn(pfn) && !page_count(pfn_to_page(pfn)));
+
 	if (!shadow_accessed_mask || old_spte & shadow_accessed_mask)
 		kvm_set_pfn_accessed(pfn);
 	if (!shadow_dirty_mask || (old_spte & shadow_dirty_mask))
@@ -960,13 +968,10 @@ static void pte_list_walk(unsigned long *pte_list, pte_list_walk_fn fn)
 static unsigned long *__gfn_to_rmap(gfn_t gfn, int level,
 				    struct kvm_memory_slot *slot)
 {
-	struct kvm_lpage_info *linfo;
+	unsigned long idx;
 
-	if (likely(level == PT_PAGE_TABLE_LEVEL))
+	idx = gfn_to_index(gfn, slot->base_gfn, level);
-		return &slot->rmap[gfn - slot->base_gfn];
+	return &slot->arch.rmap[level - PT_PAGE_TABLE_LEVEL][idx];
-
-	linfo = lpage_info_slot(gfn, slot, level);
-	return &linfo->rmap_pde;
 }
 
 /*
@@ -1173,7 +1178,8 @@ void kvm_mmu_write_protect_pt_masked(struct kvm *kvm,
 	unsigned long *rmapp;
 
 	while (mask) {
-		rmapp = &slot->rmap[gfn_offset + __ffs(mask)];
+		rmapp = __gfn_to_rmap(slot->base_gfn + gfn_offset + __ffs(mask),
+				      PT_PAGE_TABLE_LEVEL, slot);
 		__rmap_write_protect(kvm, rmapp, PT_PAGE_TABLE_LEVEL, false);
 
 		/* clear the first set bit */
@@ -1200,7 +1206,7 @@ static bool rmap_write_protect(struct kvm *kvm, u64 gfn)
 }
 
 static int kvm_unmap_rmapp(struct kvm *kvm, unsigned long *rmapp,
-			   unsigned long data)
+			   struct kvm_memory_slot *slot, unsigned long data)
 {
 	u64 *sptep;
 	struct rmap_iterator iter;
@@ -1218,7 +1224,7 @@ static int kvm_unmap_rmapp(struct kvm *kvm, unsigned long *rmapp,
 }
 
 static int kvm_set_pte_rmapp(struct kvm *kvm, unsigned long *rmapp,
-			     unsigned long data)
+			     struct kvm_memory_slot *slot, unsigned long data)
 {
 	u64 *sptep;
 	struct rmap_iterator iter;
@@ -1259,43 +1265,67 @@ static int kvm_set_pte_rmapp(struct kvm *kvm, unsigned long *rmapp,
 	return 0;
 }
 
-static int kvm_handle_hva(struct kvm *kvm, unsigned long hva,
+static int kvm_handle_hva_range(struct kvm *kvm,
+				unsigned long start,
+				unsigned long end,
 				unsigned long data,
-			  int (*handler)(struct kvm *kvm, unsigned long *rmapp,
+				int (*handler)(struct kvm *kvm,
+					       unsigned long *rmapp,
+					       struct kvm_memory_slot *slot,
 					       unsigned long data))
 {
 	int j;
-	int ret;
+	int ret = 0;
-	int retval = 0;
 	struct kvm_memslots *slots;
 	struct kvm_memory_slot *memslot;
 
 	slots = kvm_memslots(kvm);
 
 	kvm_for_each_memslot(memslot, slots) {
-		unsigned long start = memslot->userspace_addr;
+		unsigned long hva_start, hva_end;
-		unsigned long end;
+		gfn_t gfn_start, gfn_end;
 
-		end = start + (memslot->npages << PAGE_SHIFT);
+		hva_start = max(start, memslot->userspace_addr);
-		if (hva >= start && hva < end) {
+		hva_end = min(end, memslot->userspace_addr +
-			gfn_t gfn_offset = (hva - start) >> PAGE_SHIFT;
+					(memslot->npages << PAGE_SHIFT));
-			gfn_t gfn = memslot->base_gfn + gfn_offset;
+		if (hva_start >= hva_end)
+			continue;
+		/*
+		 * {gfn(page) | page intersects with [hva_start, hva_end)} =
+		 * {gfn_start, gfn_start+1, ..., gfn_end-1}.
+		 */
+		gfn_start = hva_to_gfn_memslot(hva_start, memslot);
+		gfn_end = hva_to_gfn_memslot(hva_end + PAGE_SIZE - 1, memslot);
 
-			ret = handler(kvm, &memslot->rmap[gfn_offset], data);
+		for (j = PT_PAGE_TABLE_LEVEL;
+		     j < PT_PAGE_TABLE_LEVEL + KVM_NR_PAGE_SIZES; ++j) {
+			unsigned long idx, idx_end;
+			unsigned long *rmapp;
 
-			for (j = 0; j < KVM_NR_PAGE_SIZES - 1; ++j) {
+			/*
-				struct kvm_lpage_info *linfo;
+			 * {idx(page_j) | page_j intersects with
+			 *  [hva_start, hva_end)} = {idx, idx+1, ..., idx_end}.
+			 */
+			idx = gfn_to_index(gfn_start, memslot->base_gfn, j);
+			idx_end = gfn_to_index(gfn_end - 1, memslot->base_gfn, j);
 
-				linfo = lpage_info_slot(gfn, memslot,
+			rmapp = __gfn_to_rmap(gfn_start, j, memslot);
-							PT_DIRECTORY_LEVEL + j);
+
-				ret |= handler(kvm, &linfo->rmap_pde, data);
+			for (; idx <= idx_end; ++idx)
-			}
+				ret |= handler(kvm, rmapp++, memslot, data);
-			trace_kvm_age_page(hva, memslot, ret);
-			retval |= ret;
 		}
 	}
 
-	return retval;
+	return ret;
+}
+
+static int kvm_handle_hva(struct kvm *kvm, unsigned long hva,
+			  unsigned long data,
+			  int (*handler)(struct kvm *kvm, unsigned long *rmapp,
+					 struct kvm_memory_slot *slot,
+					 unsigned long data))
+{
+	return kvm_handle_hva_range(kvm, hva, hva + 1, data, handler);
 }
 
 int kvm_unmap_hva(struct kvm *kvm, unsigned long hva)
@@ -1303,13 +1333,18 @@ int kvm_unmap_hva(struct kvm *kvm, unsigned long hva)
 	return kvm_handle_hva(kvm, hva, 0, kvm_unmap_rmapp);
 }
 
+int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end)
+{
+	return kvm_handle_hva_range(kvm, start, end, 0, kvm_unmap_rmapp);
+}
+
 void kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte)
 {
 	kvm_handle_hva(kvm, hva, (unsigned long)&pte, kvm_set_pte_rmapp);
 }
 
 static int kvm_age_rmapp(struct kvm *kvm, unsigned long *rmapp,
-			 unsigned long data)
+			 struct kvm_memory_slot *slot, unsigned long data)
 {
 	u64 *sptep;
 	struct rmap_iterator uninitialized_var(iter);
@@ -1323,8 +1358,10 @@ static int kvm_age_rmapp(struct kvm *kvm, unsigned long *rmapp,
 	 * This has some overhead, but not as much as the cost of swapping
 	 * out actively used pages or breaking up actively used hugepages.
 	 */
-	if (!shadow_accessed_mask)
+	if (!shadow_accessed_mask) {
-		return kvm_unmap_rmapp(kvm, rmapp, data);
+		young = kvm_unmap_rmapp(kvm, rmapp, slot, data);
+		goto out;
+	}
 
 	for (sptep = rmap_get_first(*rmapp, &iter); sptep;
 	     sptep = rmap_get_next(&iter)) {
@@ -1336,12 +1373,14 @@ static int kvm_age_rmapp(struct kvm *kvm, unsigned long *rmapp,
 				 (unsigned long *)sptep);
 		}
 	}
-
+out:
+	/* @data has hva passed to kvm_age_hva(). */
+	trace_kvm_age_page(data, slot, young);
 	return young;
 }
 
 static int kvm_test_age_rmapp(struct kvm *kvm, unsigned long *rmapp,
-			      unsigned long data)
+			      struct kvm_memory_slot *slot, unsigned long data)
 {
 	u64 *sptep;
 	struct rmap_iterator iter;
@@ -1379,13 +1418,13 @@ static void rmap_recycle(struct kvm_vcpu *vcpu, u64 *spte, gfn_t gfn)
 
 	rmapp = gfn_to_rmap(vcpu->kvm, gfn, sp->role.level);
 
-	kvm_unmap_rmapp(vcpu->kvm, rmapp, 0);
+	kvm_unmap_rmapp(vcpu->kvm, rmapp, NULL, 0);
 	kvm_flush_remote_tlbs(vcpu->kvm);
 }
 
 int kvm_age_hva(struct kvm *kvm, unsigned long hva)
 {
-	return kvm_handle_hva(kvm, hva, 0, kvm_age_rmapp);
+	return kvm_handle_hva(kvm, hva, hva, kvm_age_rmapp);
 }
 
 int kvm_test_age_hva(struct kvm *kvm, unsigned long hva)
@@ -2457,6 +2496,8 @@ static void mmu_set_spte(struct kvm_vcpu *vcpu, u64 *sptep,
 				rmap_recycle(vcpu, sptep, gfn);
 		}
 	}
+
+	if (!is_error_pfn(pfn))
 		kvm_release_pfn_clean(pfn);
 }
 
@@ -2469,17 +2510,12 @@ static pfn_t pte_prefetch_gfn_to_pfn(struct kvm_vcpu *vcpu, gfn_t gfn,
 				     bool no_dirty_log)
 {
 	struct kvm_memory_slot *slot;
-	unsigned long hva;
 
 	slot = gfn_to_memslot_dirty_bitmap(vcpu, gfn, no_dirty_log);
-	if (!slot) {
+	if (!slot)
-		get_page(fault_page);
+		return KVM_PFN_ERR_FAULT;
-		return page_to_pfn(fault_page);
-	}
 
-	hva = gfn_to_hva_memslot(slot, gfn);
+	return gfn_to_pfn_memslot_atomic(slot, gfn);
-
-	return hva_to_pfn_atomic(vcpu->kvm, hva);
 }
 
 static int direct_pte_prefetch_many(struct kvm_vcpu *vcpu,
@@ -2580,11 +2616,6 @@ static int __direct_map(struct kvm_vcpu *vcpu, gpa_t v, int write,
 			sp = kvm_mmu_get_page(vcpu, pseudo_gfn, iterator.addr,
 					      iterator.level - 1,
 					      1, ACC_ALL, iterator.sptep);
-			if (!sp) {
-				pgprintk("nonpaging_map: ENOMEM\n");
-				kvm_release_pfn_clean(pfn);
-				return -ENOMEM;
-			}
 
 			mmu_spte_set(iterator.sptep,
 				     __pa(sp->spt)
@@ -2611,8 +2642,16 @@ static void kvm_send_hwpoison_signal(unsigned long address, struct task_struct *
 
 static int kvm_handle_bad_page(struct kvm_vcpu *vcpu, gfn_t gfn, pfn_t pfn)
 {
-	kvm_release_pfn_clean(pfn);
+	/*
-	if (is_hwpoison_pfn(pfn)) {
+	 * Do not cache the mmio info caused by writing the readonly gfn
+	 * into the spte otherwise read access on readonly gfn also can
+	 * caused mmio page fault and treat it as mmio access.
+	 * Return 1 to tell kvm to emulate it.
+	 */
+	if (pfn == KVM_PFN_ERR_RO_FAULT)
+		return 1;
+
+	if (pfn == KVM_PFN_ERR_HWPOISON) {
 		kvm_send_hwpoison_signal(gfn_to_hva(vcpu->kvm, gfn), current);
 		return 0;
 	}
@@ -3236,8 +3275,6 @@ static bool try_async_pf(struct kvm_vcpu *vcpu, bool prefault, gfn_t gfn,
 	if (!async)
 		return false; /* *pfn has correct page already */
 
-	put_page(pfn_to_page(*pfn));
-
 	if (!prefault && can_do_async_pf(vcpu)) {
 		trace_kvm_try_async_get_page(gva, gfn);
 		if (kvm_find_async_pf_gfn(vcpu, gfn)) {
@@ -3371,6 +3408,18 @@ static bool is_rsvd_bits_set(struct kvm_mmu *mmu, u64 gpte, int level)
 	return (gpte & mmu->rsvd_bits_mask[bit7][level-1]) != 0;
 }
 
+static inline void protect_clean_gpte(unsigned *access, unsigned gpte)
+{
+	unsigned mask;
+
+	BUILD_BUG_ON(PT_WRITABLE_MASK != ACC_WRITE_MASK);
+
+	mask = (unsigned)~ACC_WRITE_MASK;
+	/* Allow write access to dirty gptes */
+	mask |= (gpte >> (PT_DIRTY_SHIFT - PT_WRITABLE_SHIFT)) & PT_WRITABLE_MASK;
+	*access &= mask;
+}
+
 static bool sync_mmio_spte(u64 *sptep, gfn_t gfn, unsigned access,
 			   int *nr_present)
 {
@@ -3388,6 +3437,25 @@ static bool sync_mmio_spte(u64 *sptep, gfn_t gfn, unsigned access,
 	return false;
 }
 
+static inline unsigned gpte_access(struct kvm_vcpu *vcpu, u64 gpte)
+{
+	unsigned access;
+
+	access = (gpte & (PT_WRITABLE_MASK | PT_USER_MASK)) | ACC_EXEC_MASK;
+	access &= ~(gpte >> PT64_NX_SHIFT);
+
+	return access;
+}
+
+static inline bool is_last_gpte(struct kvm_mmu *mmu, unsigned level, unsigned gpte)
+{
+	unsigned index;
+
+	index = level - 1;
+	index |= (gpte & PT_PAGE_SIZE_MASK) >> (PT_PAGE_SIZE_SHIFT - 2);
+	return mmu->last_pte_bitmap & (1 << index);
+}
+
 #define PTTYPE 64
 #include "paging_tmpl.h"
 #undef PTTYPE
@@ -3457,6 +3525,56 @@ static void reset_rsvds_bits_mask(struct kvm_vcpu *vcpu,
 	}
 }
 
+static void update_permission_bitmask(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu)
+{
+	unsigned bit, byte, pfec;
+	u8 map;
+	bool fault, x, w, u, wf, uf, ff, smep;
+
+	smep = kvm_read_cr4_bits(vcpu, X86_CR4_SMEP);
+	for (byte = 0; byte < ARRAY_SIZE(mmu->permissions); ++byte) {
+		pfec = byte << 1;
+		map = 0;
+		wf = pfec & PFERR_WRITE_MASK;
+		uf = pfec & PFERR_USER_MASK;
+		ff = pfec & PFERR_FETCH_MASK;
+		for (bit = 0; bit < 8; ++bit) {
+			x = bit & ACC_EXEC_MASK;
+			w = bit & ACC_WRITE_MASK;
+			u = bit & ACC_USER_MASK;
+
+			/* Not really needed: !nx will cause pte.nx to fault */
+			x |= !mmu->nx;
+			/* Allow supervisor writes if !cr0.wp */
+			w |= !is_write_protection(vcpu) && !uf;
+			/* Disallow supervisor fetches of user code if cr4.smep */
+			x &= !(smep && u && !uf);
+
+			fault = (ff && !x) || (uf && !u) || (wf && !w);
+			map |= fault << bit;
+		}
+		mmu->permissions[byte] = map;
+	}
+}
+
+static void update_last_pte_bitmap(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu)
+{
+	u8 map;
+	unsigned level, root_level = mmu->root_level;
+	const unsigned ps_set_index = 1 << 2;  /* bit 2 of index: ps */
+
+	if (root_level == PT32E_ROOT_LEVEL)
+		--root_level;
+	/* PT_PAGE_TABLE_LEVEL always terminates */
+	map = 1 | (1 << ps_set_index);
+	for (level = PT_DIRECTORY_LEVEL; level <= root_level; ++level) {
+		if (level <= PT_PDPE_LEVEL
+		    && (mmu->root_level >= PT32E_ROOT_LEVEL || is_pse(vcpu)))
+			map |= 1 << (ps_set_index | (level - 1));
+	}
+	mmu->last_pte_bitmap = map;
+}
+
 static int paging64_init_context_common(struct kvm_vcpu *vcpu,
 					struct kvm_mmu *context,
 					int level)
@@ -3465,6 +3583,8 @@ static int paging64_init_context_common(struct kvm_vcpu *vcpu,
 	context->root_level = level;
 
 	reset_rsvds_bits_mask(vcpu, context);
+	update_permission_bitmask(vcpu, context);
+	update_last_pte_bitmap(vcpu, context);
 
 	ASSERT(is_pae(vcpu));
 	context->new_cr3 = paging_new_cr3;
@@ -3493,6 +3613,8 @@ static int paging32_init_context(struct kvm_vcpu *vcpu,
 	context->root_level = PT32_ROOT_LEVEL;
 
 	reset_rsvds_bits_mask(vcpu, context);
+	update_permission_bitmask(vcpu, context);
+	update_last_pte_bitmap(vcpu, context);
 
 	context->new_cr3 = paging_new_cr3;
 	context->page_fault = paging32_page_fault;
@@ -3553,6 +3675,9 @@ static int init_kvm_tdp_mmu(struct kvm_vcpu *vcpu)
 		context->gva_to_gpa = paging32_gva_to_gpa;
 	}
 
+	update_permission_bitmask(vcpu, context);
+	update_last_pte_bitmap(vcpu, context);
+
 	return 0;
 }
 
@@ -3628,6 +3753,9 @@ static int init_kvm_nested_mmu(struct kvm_vcpu *vcpu)
 		g_context->gva_to_gpa = paging32_gva_to_gpa_nested;
 	}
 
+	update_permission_bitmask(vcpu, g_context);
+	update_last_pte_bitmap(vcpu, g_context);
+
 	return 0;
 }
 

arch/x86/kvm/mmu.h

@@ -18,8 +18,10 @@
 #define PT_PCD_MASK (1ULL << 4)
 #define PT_ACCESSED_SHIFT 5
 #define PT_ACCESSED_MASK (1ULL << PT_ACCESSED_SHIFT)
-#define PT_DIRTY_MASK (1ULL << 6)
+#define PT_DIRTY_SHIFT 6
-#define PT_PAGE_SIZE_MASK (1ULL << 7)
+#define PT_DIRTY_MASK (1ULL << PT_DIRTY_SHIFT)
+#define PT_PAGE_SIZE_SHIFT 7
+#define PT_PAGE_SIZE_MASK (1ULL << PT_PAGE_SIZE_SHIFT)
 #define PT_PAT_MASK (1ULL << 7)
 #define PT_GLOBAL_MASK (1ULL << 8)
 #define PT64_NX_SHIFT 63
@@ -88,17 +90,14 @@ static inline bool is_write_protection(struct kvm_vcpu *vcpu)
 	return kvm_read_cr0_bits(vcpu, X86_CR0_WP);
 }
 
-static inline bool check_write_user_access(struct kvm_vcpu *vcpu,
+/*
-					   bool write_fault, bool user_fault,
+ * Will a fault with a given page-fault error code (pfec) cause a permission
-					   unsigned long pte)
+ * fault with the given access (in ACC_* format)?
+ */
+static inline bool permission_fault(struct kvm_mmu *mmu, unsigned pte_access,
+				    unsigned pfec)
 {
-	if (unlikely(write_fault && !is_writable_pte(pte)
+	return (mmu->permissions[pfec >> 1] >> pte_access) & 1;
-	      && (user_fault || is_write_protection(vcpu))))
-		return false;
-
-	if (unlikely(user_fault && !(pte & PT_USER_MASK)))
-		return false;
-
-	return true;
 }
+
 #endif

arch/x86/kvm/mmu_audit.c

@@ -116,10 +116,8 @@ static void audit_mappings(struct kvm_vcpu *vcpu, u64 *sptep, int level)
 	gfn = kvm_mmu_page_get_gfn(sp, sptep - sp->spt);
 	pfn = gfn_to_pfn_atomic(vcpu->kvm, gfn);
 
-	if (is_error_pfn(pfn)) {
+	if (is_error_pfn(pfn))
-		kvm_release_pfn_clean(pfn);
 		return;
-	}
 
 	hpa =  pfn << PAGE_SHIFT;
 	if ((*sptep & PT64_BASE_ADDR_MASK) != hpa)
@@ -190,7 +188,6 @@ static void check_mappings_rmap(struct kvm *kvm, struct kvm_mmu_page *sp)
 
 static void audit_write_protection(struct kvm *kvm, struct kvm_mmu_page *sp)
 {
-	struct kvm_memory_slot *slot;
 	unsigned long *rmapp;
 	u64 *sptep;
 	struct rmap_iterator iter;
@@ -198,8 +195,7 @@ static void audit_write_protection(struct kvm *kvm, struct kvm_mmu_page *sp)
 	if (sp->role.direct || sp->unsync || sp->role.invalid)
 		return;
 
-	slot = gfn_to_memslot(kvm, sp->gfn);
+	rmapp = gfn_to_rmap(kvm, sp->gfn, PT_PAGE_TABLE_LEVEL);
-	rmapp = &slot->rmap[sp->gfn - slot->base_gfn];
 
 	for (sptep = rmap_get_first(*rmapp, &iter); sptep;
 	     sptep = rmap_get_next(&iter)) {

arch/x86/kvm/paging_tmpl.h

@@ -63,10 +63,12 @@
  */
 struct guest_walker {
 	int level;
+	unsigned max_level;
 	gfn_t table_gfn[PT_MAX_FULL_LEVELS];
 	pt_element_t ptes[PT_MAX_FULL_LEVELS];
 	pt_element_t prefetch_ptes[PTE_PREFETCH_NUM];
 	gpa_t pte_gpa[PT_MAX_FULL_LEVELS];
+	pt_element_t __user *ptep_user[PT_MAX_FULL_LEVELS];
 	unsigned pt_access;
 	unsigned pte_access;
 	gfn_t gfn;
@@ -101,38 +103,41 @@ static int FNAME(cmpxchg_gpte)(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu,
 	return (ret != orig_pte);
 }
 
-static unsigned FNAME(gpte_access)(struct kvm_vcpu *vcpu, pt_element_t gpte,
+static int FNAME(update_accessed_dirty_bits)(struct kvm_vcpu *vcpu,
-				   bool last)
+					     struct kvm_mmu *mmu,
+					     struct guest_walker *walker,
+					     int write_fault)
 {
-	unsigned access;
+	unsigned level, index;
+	pt_element_t pte, orig_pte;
+	pt_element_t __user *ptep_user;
+	gfn_t table_gfn;
+	int ret;
 
-	access = (gpte & (PT_WRITABLE_MASK | PT_USER_MASK)) | ACC_EXEC_MASK;
+	for (level = walker->max_level; level >= walker->level; --level) {
-	if (last && !is_dirty_gpte(gpte))
+		pte = orig_pte = walker->ptes[level - 1];
-		access &= ~ACC_WRITE_MASK;
+		table_gfn = walker->table_gfn[level - 1];
+		ptep_user = walker->ptep_user[level - 1];
+		index = offset_in_page(ptep_user) / sizeof(pt_element_t);
+		if (!(pte & PT_ACCESSED_MASK)) {
+			trace_kvm_mmu_set_accessed_bit(table_gfn, index, sizeof(pte));
+			pte |= PT_ACCESSED_MASK;
+		}
+		if (level == walker->level && write_fault && !is_dirty_gpte(pte)) {
+			trace_kvm_mmu_set_dirty_bit(table_gfn, index, sizeof(pte));
+			pte |= PT_DIRTY_MASK;
+		}
+		if (pte == orig_pte)
+			continue;
 
-#if PTTYPE == 64
+		ret = FNAME(cmpxchg_gpte)(vcpu, mmu, ptep_user, index, orig_pte, pte);
-	if (vcpu->arch.mmu.nx)
+		if (ret)
-		access &= ~(gpte >> PT64_NX_SHIFT);
+			return ret;
-#endif
-	return access;
-}
 
-static bool FNAME(is_last_gpte)(struct guest_walker *walker,
+		mark_page_dirty(vcpu->kvm, table_gfn);
-				struct kvm_vcpu *vcpu, struct kvm_mmu *mmu,
+		walker->ptes[level] = pte;
-				pt_element_t gpte)
+	}
-{
+	return 0;
-	if (walker->level == PT_PAGE_TABLE_LEVEL)
-		return true;
-
-	if ((walker->level == PT_DIRECTORY_LEVEL) && is_large_pte(gpte) &&
-	    (PTTYPE == 64 || is_pse(vcpu)))
-		return true;
-
-	if ((walker->level == PT_PDPE_LEVEL) && is_large_pte(gpte) &&
-	    (mmu->root_level == PT64_ROOT_LEVEL))
-		return true;
-
-	return false;
 }
 
 /*
@@ -142,21 +147,22 @@ static int FNAME(walk_addr_generic)(struct guest_walker *walker,
 				    struct kvm_vcpu *vcpu, struct kvm_mmu *mmu,
 				    gva_t addr, u32 access)
 {
+	int ret;
 	pt_element_t pte;
 	pt_element_t __user *uninitialized_var(ptep_user);
 	gfn_t table_gfn;
-	unsigned index, pt_access, uninitialized_var(pte_access);
+	unsigned index, pt_access, pte_access, accessed_dirty, shift;
 	gpa_t pte_gpa;
-	bool eperm, last_gpte;
 	int offset;
 	const int write_fault = access & PFERR_WRITE_MASK;
 	const int user_fault  = access & PFERR_USER_MASK;
 	const int fetch_fault = access & PFERR_FETCH_MASK;
 	u16 errcode = 0;
+	gpa_t real_gpa;
+	gfn_t gfn;
 
 	trace_kvm_mmu_pagetable_walk(addr, access);
 retry_walk:
-	eperm = false;
 	walker->level = mmu->root_level;
 	pte           = mmu->get_cr3(vcpu);
 
@@ -169,15 +175,21 @@ retry_walk:
 		--walker->level;
 	}
 #endif
+	walker->max_level = walker->level;
 	ASSERT((!is_long_mode(vcpu) && is_pae(vcpu)) ||
 	       (mmu->get_cr3(vcpu) & CR3_NONPAE_RESERVED_BITS) == 0);
 
-	pt_access = ACC_ALL;
+	accessed_dirty = PT_ACCESSED_MASK;
+	pt_access = pte_access = ACC_ALL;
+	++walker->level;
 
-	for (;;) {
+	do {
 		gfn_t real_gfn;
 		unsigned long host_addr;
 
+		pt_access &= pte_access;
+		--walker->level;
+
 		index = PT_INDEX(addr, walker->level);
 
 		table_gfn = gpte_to_gfn(pte);
@@ -199,6 +211,7 @@ retry_walk:
 		ptep_user = (pt_element_t __user *)((void *)host_addr + offset);
 		if (unlikely(__copy_from_user(&pte, ptep_user, sizeof(pte))))
 			goto error;
+		walker->ptep_user[walker->level - 1] = ptep_user;
 
 		trace_kvm_mmu_paging_element(pte, walker->level);
 
@@ -211,92 +224,48 @@ retry_walk:
 			goto error;
 		}
 
-		if (!check_write_user_access(vcpu, write_fault, user_fault,
+		accessed_dirty &= pte;
-					  pte))
+		pte_access = pt_access & gpte_access(vcpu, pte);
-			eperm = true;
-
-#if PTTYPE == 64
-		if (unlikely(fetch_fault && (pte & PT64_NX_MASK)))
-			eperm = true;
-#endif
-
-		last_gpte = FNAME(is_last_gpte)(walker, vcpu, mmu, pte);
-		if (last_gpte) {
-			pte_access = pt_access &
-				     FNAME(gpte_access)(vcpu, pte, true);
-			/* check if the kernel is fetching from user page */
-			if (unlikely(pte_access & PT_USER_MASK) &&
-			    kvm_read_cr4_bits(vcpu, X86_CR4_SMEP))
-				if (fetch_fault && !user_fault)
-					eperm = true;
-		}
-
-		if (!eperm && unlikely(!(pte & PT_ACCESSED_MASK))) {
-			int ret;
-			trace_kvm_mmu_set_accessed_bit(table_gfn, index,
-						       sizeof(pte));
-			ret = FNAME(cmpxchg_gpte)(vcpu, mmu, ptep_user, index,
-						  pte, pte|PT_ACCESSED_MASK);
-			if (unlikely(ret < 0))
-				goto error;
-			else if (ret)
-				goto retry_walk;
-
-			mark_page_dirty(vcpu->kvm, table_gfn);
-			pte |= PT_ACCESSED_MASK;
-		}
 
 		walker->ptes[walker->level - 1] = pte;
+	} while (!is_last_gpte(mmu, walker->level, pte));
 
-		if (last_gpte) {
+	if (unlikely(permission_fault(mmu, pte_access, access))) {
-			int lvl = walker->level;
+		errcode |= PFERR_PRESENT_MASK;
-			gpa_t real_gpa;
+		goto error;
-			gfn_t gfn;
+	}
-			u32 ac;
 
-			gfn = gpte_to_gfn_lvl(pte, lvl);
+	gfn = gpte_to_gfn_lvl(pte, walker->level);
-			gfn += (addr & PT_LVL_OFFSET_MASK(lvl)) >> PAGE_SHIFT;
+	gfn += (addr & PT_LVL_OFFSET_MASK(walker->level)) >> PAGE_SHIFT;
 
-			if (PTTYPE == 32 &&
+	if (PTTYPE == 32 && walker->level == PT_DIRECTORY_LEVEL && is_cpuid_PSE36())
-			    walker->level == PT_DIRECTORY_LEVEL &&
-			    is_cpuid_PSE36())
 		gfn += pse36_gfn_delta(pte);
 
-			ac = write_fault | fetch_fault | user_fault;
+	real_gpa = mmu->translate_gpa(vcpu, gfn_to_gpa(gfn), access);
-
-			real_gpa = mmu->translate_gpa(vcpu, gfn_to_gpa(gfn),
-						      ac);
 	if (real_gpa == UNMAPPED_GVA)
 		return 0;
 
 	walker->gfn = real_gpa >> PAGE_SHIFT;
 
-			break;
+	if (!write_fault)
-		}
+		protect_clean_gpte(&pte_access, pte);
 
-		pt_access &= FNAME(gpte_access)(vcpu, pte, false);
+	/*
-		--walker->level;
+	 * On a write fault, fold the dirty bit into accessed_dirty by shifting it one
-	}
+	 * place right.
+	 *
+	 * On a read fault, do nothing.
+	 */
+	shift = write_fault >> ilog2(PFERR_WRITE_MASK);
+	shift *= PT_DIRTY_SHIFT - PT_ACCESSED_SHIFT;
+	accessed_dirty &= pte >> shift;
 
-	if (unlikely(eperm)) {
+	if (unlikely(!accessed_dirty)) {
-		errcode |= PFERR_PRESENT_MASK;
+		ret = FNAME(update_accessed_dirty_bits)(vcpu, mmu, walker, write_fault);
-		goto error;
-	}
-
-	if (write_fault && unlikely(!is_dirty_gpte(pte))) {
-		int ret;
-
-		trace_kvm_mmu_set_dirty_bit(table_gfn, index, sizeof(pte));
-		ret = FNAME(cmpxchg_gpte)(vcpu, mmu, ptep_user, index,
-					  pte, pte|PT_DIRTY_MASK);
 		if (unlikely(ret < 0))
 			goto error;
 		else if (ret)
 			goto retry_walk;
-
-		mark_page_dirty(vcpu->kvm, table_gfn);
-		pte |= PT_DIRTY_MASK;
-		walker->ptes[walker->level - 1] = pte;
 	}
 
 	walker->pt_access = pt_access;
@@ -368,12 +337,11 @@ static void FNAME(update_pte)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp,
 		return;
 
 	pgprintk("%s: gpte %llx spte %p\n", __func__, (u64)gpte, spte);
-	pte_access = sp->role.access & FNAME(gpte_access)(vcpu, gpte, true);
+	pte_access = sp->role.access & gpte_access(vcpu, gpte);
+	protect_clean_gpte(&pte_access, gpte);
 	pfn = gfn_to_pfn_atomic(vcpu->kvm, gpte_to_gfn(gpte));
-	if (mmu_invalid_pfn(pfn)) {
+	if (mmu_invalid_pfn(pfn))
-		kvm_release_pfn_clean(pfn);
 		return;
-	}
 
 	/*
 	 * we call mmu_set_spte() with host_writable = true because that
@@ -443,15 +411,13 @@ static void FNAME(pte_prefetch)(struct kvm_vcpu *vcpu, struct guest_walker *gw,
 		if (FNAME(prefetch_invalid_gpte)(vcpu, sp, spte, gpte))
 			continue;
 
-		pte_access = sp->role.access & FNAME(gpte_access)(vcpu, gpte,
+		pte_access = sp->role.access & gpte_access(vcpu, gpte);
-								  true);
+		protect_clean_gpte(&pte_access, gpte);
 		gfn = gpte_to_gfn(gpte);
 		pfn = pte_prefetch_gfn_to_pfn(vcpu, gfn,
 				      pte_access & ACC_WRITE_MASK);
-		if (mmu_invalid_pfn(pfn)) {
+		if (mmu_invalid_pfn(pfn))
-			kvm_release_pfn_clean(pfn);
 			break;
-		}
 
 		mmu_set_spte(vcpu, spte, sp->role.access, pte_access, 0, 0,
 			     NULL, PT_PAGE_TABLE_LEVEL, gfn,
@@ -798,7 +764,8 @@ static int FNAME(sync_page)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp)
 
 		gfn = gpte_to_gfn(gpte);
 		pte_access = sp->role.access;
-		pte_access &= FNAME(gpte_access)(vcpu, gpte, true);
+		pte_access &= gpte_access(vcpu, gpte);
+		protect_clean_gpte(&pte_access, gpte);
 
 		if (sync_mmio_spte(&sp->spt[i], gfn, pte_access, &nr_present))
 			continue;

arch/x86/kvm/pmu.c

@@ -1,5 +1,5 @@
 /*
- * Kernel-based Virtual Machine -- Performane Monitoring Unit support
+ * Kernel-based Virtual Machine -- Performance Monitoring Unit support
  *
  * Copyright 2011 Red Hat, Inc. and/or its affiliates.
  *

arch/x86/kvm/svm.c

@@ -163,7 +163,7 @@ static DEFINE_PER_CPU(u64, current_tsc_ratio);
 
 #define MSR_INVALID			0xffffffffU
 
-static struct svm_direct_access_msrs {
+static const struct svm_direct_access_msrs {
 	u32 index;   /* Index of the MSR */
 	bool always; /* True if intercept is always on */
 } direct_access_msrs[] = {
@@ -400,7 +400,7 @@ struct svm_init_data {
 	int r;
 };
 
-static u32 msrpm_ranges[] = {0, 0xc0000000, 0xc0010000};
+static const u32 msrpm_ranges[] = {0, 0xc0000000, 0xc0010000};
 
 #define NUM_MSR_MAPS ARRAY_SIZE(msrpm_ranges)
 #define MSRS_RANGE_SIZE 2048
@@ -1146,7 +1146,6 @@ static void init_vmcb(struct vcpu_svm *svm)
 
 	svm_set_efer(&svm->vcpu, 0);
 	save->dr6 = 0xffff0ff0;
-	save->dr7 = 0x400;
 	kvm_set_rflags(&svm->vcpu, 2);
 	save->rip = 0x0000fff0;
 	svm->vcpu.arch.regs[VCPU_REGS_RIP] = save->rip;
@@ -1643,7 +1642,7 @@ static void svm_set_segment(struct kvm_vcpu *vcpu,
 	mark_dirty(svm->vmcb, VMCB_SEG);
 }
 
-static void update_db_intercept(struct kvm_vcpu *vcpu)
+static void update_db_bp_intercept(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
 
@@ -1663,20 +1662,6 @@ static void update_db_intercept(struct kvm_vcpu *vcpu)
 		vcpu->guest_debug = 0;
 }
 
-static void svm_guest_debug(struct kvm_vcpu *vcpu, struct kvm_guest_debug *dbg)
-{
-	struct vcpu_svm *svm = to_svm(vcpu);
-
-	if (vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP)
-		svm->vmcb->save.dr7 = dbg->arch.debugreg[7];
-	else
-		svm->vmcb->save.dr7 = vcpu->arch.dr7;
-
-	mark_dirty(svm->vmcb, VMCB_DR);
-
-	update_db_intercept(vcpu);
-}
-
 static void new_asid(struct vcpu_svm *svm, struct svm_cpu_data *sd)
 {
 	if (sd->next_asid > sd->max_asid) {
@@ -1748,7 +1733,7 @@ static int db_interception(struct vcpu_svm *svm)
 		if (!(svm->vcpu.guest_debug & KVM_GUESTDBG_SINGLESTEP))
 			svm->vmcb->save.rflags &=
 				~(X86_EFLAGS_TF | X86_EFLAGS_RF);
-		update_db_intercept(&svm->vcpu);
+		update_db_bp_intercept(&svm->vcpu);
 	}
 
 	if (svm->vcpu.guest_debug &
@@ -2063,7 +2048,7 @@ static inline bool nested_svm_intr(struct vcpu_svm *svm)
 	if (svm->nested.intercept & 1ULL) {
 		/*
 		 * The #vmexit can't be emulated here directly because this
-		 * code path runs with irqs and preemtion disabled. A
+		 * code path runs with irqs and preemption disabled. A
 		 * #vmexit emulation might sleep. Only signal request for
 		 * the #vmexit here.
 		 */
@@ -2105,7 +2090,6 @@ static void *nested_svm_map(struct vcpu_svm *svm, u64 gpa, struct page **_page)
 	return kmap(page);
 
 error:
-	kvm_release_page_clean(page);
 	kvm_inject_gp(&svm->vcpu, 0);
 
 	return NULL;
@@ -2409,7 +2393,7 @@ static bool nested_svm_vmrun_msrpm(struct vcpu_svm *svm)
 {
 	/*
 	 * This function merges the msr permission bitmaps of kvm and the
-	 * nested vmcb. It is omptimized in that it only merges the parts where
+	 * nested vmcb. It is optimized in that it only merges the parts where
 	 * the kvm msr permission bitmap may contain zero bits
 	 */
 	int i;
@@ -3268,7 +3252,7 @@ static int pause_interception(struct vcpu_svm *svm)
 	return 1;
 }
 
-static int (*svm_exit_handlers[])(struct vcpu_svm *svm) = {
+static int (*const svm_exit_handlers[])(struct vcpu_svm *svm) = {
 	[SVM_EXIT_READ_CR0]			= cr_interception,
 	[SVM_EXIT_READ_CR3]			= cr_interception,
 	[SVM_EXIT_READ_CR4]			= cr_interception,
@@ -3660,7 +3644,7 @@ static void enable_nmi_window(struct kvm_vcpu *vcpu)
 	 */
 	svm->nmi_singlestep = true;
 	svm->vmcb->save.rflags |= (X86_EFLAGS_TF | X86_EFLAGS_RF);
-	update_db_intercept(vcpu);
+	update_db_bp_intercept(vcpu);
 }
 
 static int svm_set_tss_addr(struct kvm *kvm, unsigned int addr)
@@ -3783,12 +3767,6 @@ static void svm_cancel_injection(struct kvm_vcpu *vcpu)
 	svm_complete_interrupts(svm);
 }
 
-#ifdef CONFIG_X86_64
-#define R "r"
-#else
-#define R "e"
-#endif
-
 static void svm_vcpu_run(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
@@ -3815,13 +3793,13 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu)
 	local_irq_enable();
 
 	asm volatile (
-		"push %%"R"bp; \n\t"
+		"push %%" _ASM_BP "; \n\t"
-		"mov %c[rbx](%[svm]), %%"R"bx \n\t"
+		"mov %c[rbx](%[svm]), %%" _ASM_BX " \n\t"
-		"mov %c[rcx](%[svm]), %%"R"cx \n\t"
+		"mov %c[rcx](%[svm]), %%" _ASM_CX " \n\t"
-		"mov %c[rdx](%[svm]), %%"R"dx \n\t"
+		"mov %c[rdx](%[svm]), %%" _ASM_DX " \n\t"
-		"mov %c[rsi](%[svm]), %%"R"si \n\t"
+		"mov %c[rsi](%[svm]), %%" _ASM_SI " \n\t"
-		"mov %c[rdi](%[svm]), %%"R"di \n\t"
+		"mov %c[rdi](%[svm]), %%" _ASM_DI " \n\t"
-		"mov %c[rbp](%[svm]), %%"R"bp \n\t"
+		"mov %c[rbp](%[svm]), %%" _ASM_BP " \n\t"
 #ifdef CONFIG_X86_64
 		"mov %c[r8](%[svm]),  %%r8  \n\t"
 		"mov %c[r9](%[svm]),  %%r9  \n\t"
@@ -3834,20 +3812,20 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu)
 #endif
 
 		/* Enter guest mode */
-		"push %%"R"ax \n\t"
+		"push %%" _ASM_AX " \n\t"
-		"mov %c[vmcb](%[svm]), %%"R"ax \n\t"
+		"mov %c[vmcb](%[svm]), %%" _ASM_AX " \n\t"
 		__ex(SVM_VMLOAD) "\n\t"
 		__ex(SVM_VMRUN) "\n\t"
 		__ex(SVM_VMSAVE) "\n\t"
-		"pop %%"R"ax \n\t"
+		"pop %%" _ASM_AX " \n\t"
 
 		/* Save guest registers, load host registers */
-		"mov %%"R"bx, %c[rbx](%[svm]) \n\t"
+		"mov %%" _ASM_BX ", %c[rbx](%[svm]) \n\t"
-		"mov %%"R"cx, %c[rcx](%[svm]) \n\t"
+		"mov %%" _ASM_CX ", %c[rcx](%[svm]) \n\t"
-		"mov %%"R"dx, %c[rdx](%[svm]) \n\t"
+		"mov %%" _ASM_DX ", %c[rdx](%[svm]) \n\t"
-		"mov %%"R"si, %c[rsi](%[svm]) \n\t"
+		"mov %%" _ASM_SI ", %c[rsi](%[svm]) \n\t"
-		"mov %%"R"di, %c[rdi](%[svm]) \n\t"
+		"mov %%" _ASM_DI ", %c[rdi](%[svm]) \n\t"
-		"mov %%"R"bp, %c[rbp](%[svm]) \n\t"
+		"mov %%" _ASM_BP ", %c[rbp](%[svm]) \n\t"
 #ifdef CONFIG_X86_64
 		"mov %%r8,  %c[r8](%[svm]) \n\t"
 		"mov %%r9,  %c[r9](%[svm]) \n\t"
@@ -3858,7 +3836,7 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu)
 		"mov %%r14, %c[r14](%[svm]) \n\t"
 		"mov %%r15, %c[r15](%[svm]) \n\t"
 #endif
-		"pop %%"R"bp"
+		"pop %%" _ASM_BP
 		:
 		: [svm]"a"(svm),
 		  [vmcb]"i"(offsetof(struct vcpu_svm, vmcb_pa)),
@@ -3879,9 +3857,11 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu)
 		  [r15]"i"(offsetof(struct vcpu_svm, vcpu.arch.regs[VCPU_REGS_R15]))
 #endif
 		: "cc", "memory"
-		, R"bx", R"cx", R"dx", R"si", R"di"
 #ifdef CONFIG_X86_64
+		, "rbx", "rcx", "rdx", "rsi", "rdi"
 		, "r8", "r9", "r10", "r11" , "r12", "r13", "r14", "r15"
+#else
+		, "ebx", "ecx", "edx", "esi", "edi"
 #endif
 		);
 
@@ -3941,8 +3921,6 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu)
 	mark_all_clean(svm->vmcb);
 }
 
-#undef R
-
 static void svm_set_cr3(struct kvm_vcpu *vcpu, unsigned long root)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
@@ -4069,7 +4047,7 @@ static void svm_fpu_deactivate(struct kvm_vcpu *vcpu)
 #define POST_MEM(exit) { .exit_code = (exit), \
 			.stage = X86_ICPT_POST_MEMACCESS, }
 
-static struct __x86_intercept {
+static const struct __x86_intercept {
 	u32 exit_code;
 	enum x86_intercept_stage stage;
 } x86_intercept_map[] = {
@@ -4260,7 +4238,7 @@ static struct kvm_x86_ops svm_x86_ops = {
 	.vcpu_load = svm_vcpu_load,
 	.vcpu_put = svm_vcpu_put,
 
-	.set_guest_debug = svm_guest_debug,
+	.update_db_bp_intercept = update_db_bp_intercept,
 	.get_msr = svm_get_msr,
 	.set_msr = svm_set_msr,
 	.get_segment_base = svm_get_segment_base,

arch/x86/kvm/timer.c

@@ -1,47 +0,0 @@
-/*
- * Kernel-based Virtual Machine driver for Linux
- *
- * This module enables machines with Intel VT-x extensions to run virtual
- * machines without emulation or binary translation.
- *
- * timer support
- *
- * Copyright 2010 Red Hat, Inc. and/or its affiliates.
- *
- * This work is licensed under the terms of the GNU GPL, version 2.  See
- * the COPYING file in the top-level directory.
- */
-
-#include <linux/kvm_host.h>
-#include <linux/kvm.h>
-#include <linux/hrtimer.h>
-#include <linux/atomic.h>
-#include "kvm_timer.h"
-
-enum hrtimer_restart kvm_timer_fn(struct hrtimer *data)
-{
-	struct kvm_timer *ktimer = container_of(data, struct kvm_timer, timer);
-	struct kvm_vcpu *vcpu = ktimer->vcpu;
-	wait_queue_head_t *q = &vcpu->wq;
-
-	/*
-	 * There is a race window between reading and incrementing, but we do
-	 * not care about potentially losing timer events in the !reinject
-	 * case anyway. Note: KVM_REQ_PENDING_TIMER is implicitly checked
-	 * in vcpu_enter_guest.
-	 */
-	if (ktimer->reinject || !atomic_read(&ktimer->pending)) {
-		atomic_inc(&ktimer->pending);
-		/* FIXME: this code should not know anything about vcpus */
-		kvm_make_request(KVM_REQ_PENDING_TIMER, vcpu);
-	}
-
-	if (waitqueue_active(q))
-		wake_up_interruptible(q);
-
-	if (ktimer->t_ops->is_periodic(ktimer)) {
-		hrtimer_add_expires_ns(&ktimer->timer, ktimer->period);
-		return HRTIMER_RESTART;
-	} else
-		return HRTIMER_NORESTART;
-}

arch/x86/kvm/vmx.c

@@ -127,6 +127,8 @@ module_param(ple_gap, int, S_IRUGO);
 static int ple_window = KVM_VMX_DEFAULT_PLE_WINDOW;
 module_param(ple_window, int, S_IRUGO);
 
+extern const ulong vmx_return;
+
 #define NR_AUTOLOAD_MSRS 8
 #define VMCS02_POOL_SIZE 1
 
@@ -405,16 +407,16 @@ struct vcpu_vmx {
 	struct {
 		int vm86_active;
 		ulong save_rflags;
+		struct kvm_segment segs[8];
+	} rmode;
+	struct {
+		u32 bitmask; /* 4 bits per segment (1 bit per field) */
 		struct kvm_save_segment {
 			u16 selector;
 			unsigned long base;
 			u32 limit;
 			u32 ar;
-		} tr, es, ds, fs, gs;
+		} seg[8];
-	} rmode;
-	struct {
-		u32 bitmask; /* 4 bits per segment (1 bit per field) */
-		struct kvm_save_segment seg[8];
 	} segment_cache;
 	int vpid;
 	bool emulation_required;
@@ -450,7 +452,7 @@ static inline struct vcpu_vmx *to_vmx(struct kvm_vcpu *vcpu)
 #define FIELD64(number, name)	[number] = VMCS12_OFFSET(name), \
 				[number##_HIGH] = VMCS12_OFFSET(name)+4
 
-static unsigned short vmcs_field_to_offset_table[] = {
+static const unsigned short vmcs_field_to_offset_table[] = {
 	FIELD(VIRTUAL_PROCESSOR_ID, virtual_processor_id),
 	FIELD(GUEST_ES_SELECTOR, guest_es_selector),
 	FIELD(GUEST_CS_SELECTOR, guest_cs_selector),
@@ -596,10 +598,9 @@ static inline struct vmcs12 *get_vmcs12(struct kvm_vcpu *vcpu)
 static struct page *nested_get_page(struct kvm_vcpu *vcpu, gpa_t addr)
 {
 	struct page *page = gfn_to_page(vcpu->kvm, addr >> PAGE_SHIFT);
-	if (is_error_page(page)) {
+	if (is_error_page(page))
-		kvm_release_page_clean(page);
 		return NULL;
-	}
+
 	return page;
 }
 
@@ -667,7 +668,7 @@ static struct vmx_capability {
 		.ar_bytes = GUEST_##seg##_AR_BYTES,	   	\
 	}
 
-static struct kvm_vmx_segment_field {
+static const struct kvm_vmx_segment_field {
 	unsigned selector;
 	unsigned base;
 	unsigned limit;
@@ -1343,7 +1344,7 @@ static bool update_transition_efer(struct vcpu_vmx *vmx, int efer_offset)
 	guest_efer = vmx->vcpu.arch.efer;
 
 	/*
-	 * NX is emulated; LMA and LME handled by hardware; SCE meaninless
+	 * NX is emulated; LMA and LME handled by hardware; SCE meaningless
 	 * outside long mode
 	 */
 	ignore_bits = EFER_NX | EFER_SCE;
@@ -1995,7 +1996,7 @@ static __init void nested_vmx_setup_ctls_msrs(void)
 #endif
 		CPU_BASED_MOV_DR_EXITING | CPU_BASED_UNCOND_IO_EXITING |
 		CPU_BASED_USE_IO_BITMAPS | CPU_BASED_MONITOR_EXITING |
-		CPU_BASED_RDPMC_EXITING |
+		CPU_BASED_RDPMC_EXITING | CPU_BASED_RDTSC_EXITING |
 		CPU_BASED_ACTIVATE_SECONDARY_CONTROLS;
 	/*
 	 * We can allow some features even when not supported by the
@@ -2291,16 +2292,6 @@ static void vmx_cache_reg(struct kvm_vcpu *vcpu, enum kvm_reg reg)
 	}
 }
 
-static void set_guest_debug(struct kvm_vcpu *vcpu, struct kvm_guest_debug *dbg)
-{
-	if (vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP)
-		vmcs_writel(GUEST_DR7, dbg->arch.debugreg[7]);
-	else
-		vmcs_writel(GUEST_DR7, vcpu->arch.dr7);
-
-	update_exception_bitmap(vcpu);
-}
-
 static __init int cpu_has_kvm_support(void)
 {
 	return cpu_has_vmx();
@@ -2698,20 +2689,17 @@ static __exit void hardware_unsetup(void)
 	free_kvm_area();
 }
 
-static void fix_pmode_dataseg(int seg, struct kvm_save_segment *save)
+static void fix_pmode_dataseg(struct kvm_vcpu *vcpu, int seg, struct kvm_segment *save)
 {
-	struct kvm_vmx_segment_field *sf = &kvm_vmx_segment_fields[seg];
+	const struct kvm_vmx_segment_field *sf = &kvm_vmx_segment_fields[seg];
+	struct kvm_segment tmp = *save;
 
-	if (vmcs_readl(sf->base) == save->base && (save->base & AR_S_MASK)) {
+	if (!(vmcs_readl(sf->base) == tmp.base && tmp.s)) {
-		vmcs_write16(sf->selector, save->selector);
+		tmp.base = vmcs_readl(sf->base);
-		vmcs_writel(sf->base, save->base);
+		tmp.selector = vmcs_read16(sf->selector);
-		vmcs_write32(sf->limit, save->limit);
+		tmp.s = 1;
-		vmcs_write32(sf->ar_bytes, save->ar);
-	} else {
-		u32 dpl = (vmcs_read16(sf->selector) & SELECTOR_RPL_MASK)
-			<< AR_DPL_SHIFT;
-		vmcs_write32(sf->ar_bytes, 0x93 | dpl);
 	}
+	vmx_set_segment(vcpu, &tmp, seg);
 }
 
 static void enter_pmode(struct kvm_vcpu *vcpu)
@@ -2724,10 +2712,7 @@ static void enter_pmode(struct kvm_vcpu *vcpu)
 
 	vmx_segment_cache_clear(vmx);
 
-	vmcs_write16(GUEST_TR_SELECTOR, vmx->rmode.tr.selector);
+	vmx_set_segment(vcpu, &vmx->rmode.segs[VCPU_SREG_TR], VCPU_SREG_TR);
-	vmcs_writel(GUEST_TR_BASE, vmx->rmode.tr.base);
-	vmcs_write32(GUEST_TR_LIMIT, vmx->rmode.tr.limit);
-	vmcs_write32(GUEST_TR_AR_BYTES, vmx->rmode.tr.ar);
 
 	flags = vmcs_readl(GUEST_RFLAGS);
 	flags &= RMODE_GUEST_OWNED_EFLAGS_BITS;
@@ -2742,10 +2727,10 @@ static void enter_pmode(struct kvm_vcpu *vcpu)
 	if (emulate_invalid_guest_state)
 		return;
 
-	fix_pmode_dataseg(VCPU_SREG_ES, &vmx->rmode.es);
+	fix_pmode_dataseg(vcpu, VCPU_SREG_ES, &vmx->rmode.segs[VCPU_SREG_ES]);
-	fix_pmode_dataseg(VCPU_SREG_DS, &vmx->rmode.ds);
+	fix_pmode_dataseg(vcpu, VCPU_SREG_DS, &vmx->rmode.segs[VCPU_SREG_DS]);
-	fix_pmode_dataseg(VCPU_SREG_GS, &vmx->rmode.gs);
+	fix_pmode_dataseg(vcpu, VCPU_SREG_FS, &vmx->rmode.segs[VCPU_SREG_FS]);
-	fix_pmode_dataseg(VCPU_SREG_FS, &vmx->rmode.fs);
+	fix_pmode_dataseg(vcpu, VCPU_SREG_GS, &vmx->rmode.segs[VCPU_SREG_GS]);
 
 	vmx_segment_cache_clear(vmx);
 
@@ -2773,14 +2758,10 @@ static gva_t rmode_tss_base(struct kvm *kvm)
 	return kvm->arch.tss_addr;
 }
 
-static void fix_rmode_seg(int seg, struct kvm_save_segment *save)
+static void fix_rmode_seg(int seg, struct kvm_segment *save)
 {
-	struct kvm_vmx_segment_field *sf = &kvm_vmx_segment_fields[seg];
+	const struct kvm_vmx_segment_field *sf = &kvm_vmx_segment_fields[seg];
 
-	save->selector = vmcs_read16(sf->selector);
-	save->base = vmcs_readl(sf->base);
-	save->limit = vmcs_read32(sf->limit);
-	save->ar = vmcs_read32(sf->ar_bytes);
 	vmcs_write16(sf->selector, save->base >> 4);
 	vmcs_write32(sf->base, save->base & 0xffff0);
 	vmcs_write32(sf->limit, 0xffff);
@@ -2800,9 +2781,16 @@ static void enter_rmode(struct kvm_vcpu *vcpu)
 	if (enable_unrestricted_guest)
 		return;
 
+	vmx_get_segment(vcpu, &vmx->rmode.segs[VCPU_SREG_TR], VCPU_SREG_TR);
+	vmx_get_segment(vcpu, &vmx->rmode.segs[VCPU_SREG_ES], VCPU_SREG_ES);
+	vmx_get_segment(vcpu, &vmx->rmode.segs[VCPU_SREG_DS], VCPU_SREG_DS);
+	vmx_get_segment(vcpu, &vmx->rmode.segs[VCPU_SREG_FS], VCPU_SREG_FS);
+	vmx_get_segment(vcpu, &vmx->rmode.segs[VCPU_SREG_GS], VCPU_SREG_GS);
+
 	vmx->emulation_required = 1;
 	vmx->rmode.vm86_active = 1;
 
+
 	/*
 	 * Very old userspace does not call KVM_SET_TSS_ADDR before entering
 	 * vcpu. Call it here with phys address pointing 16M below 4G.
@@ -2817,14 +2805,8 @@ static void enter_rmode(struct kvm_vcpu *vcpu)
 
 	vmx_segment_cache_clear(vmx);
 
-	vmx->rmode.tr.selector = vmcs_read16(GUEST_TR_SELECTOR);
-	vmx->rmode.tr.base = vmcs_readl(GUEST_TR_BASE);
 	vmcs_writel(GUEST_TR_BASE, rmode_tss_base(vcpu->kvm));
-
-	vmx->rmode.tr.limit = vmcs_read32(GUEST_TR_LIMIT);
 	vmcs_write32(GUEST_TR_LIMIT, RMODE_TSS_SIZE - 1);
-
-	vmx->rmode.tr.ar = vmcs_read32(GUEST_TR_AR_BYTES);
 	vmcs_write32(GUEST_TR_AR_BYTES, 0x008b);
 
 	flags = vmcs_readl(GUEST_RFLAGS);
@@ -3117,35 +3099,24 @@ static void vmx_get_segment(struct kvm_vcpu *vcpu,
 			    struct kvm_segment *var, int seg)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
-	struct kvm_save_segment *save;
 	u32 ar;
 
 	if (vmx->rmode.vm86_active
 	    && (seg == VCPU_SREG_TR || seg == VCPU_SREG_ES
 		|| seg == VCPU_SREG_DS || seg == VCPU_SREG_FS
-		|| seg == VCPU_SREG_GS)
+		|| seg == VCPU_SREG_GS)) {
-	    && !emulate_invalid_guest_state) {
+		*var = vmx->rmode.segs[seg];
-		switch (seg) {
-		case VCPU_SREG_TR: save = &vmx->rmode.tr; break;
-		case VCPU_SREG_ES: save = &vmx->rmode.es; break;
-		case VCPU_SREG_DS: save = &vmx->rmode.ds; break;
-		case VCPU_SREG_FS: save = &vmx->rmode.fs; break;
-		case VCPU_SREG_GS: save = &vmx->rmode.gs; break;
-		default: BUG();
-		}
-		var->selector = save->selector;
-		var->base = save->base;
-		var->limit = save->limit;
-		ar = save->ar;
 		if (seg == VCPU_SREG_TR
 		    || var->selector == vmx_read_guest_seg_selector(vmx, seg))
-			goto use_saved_rmode_seg;
+			return;
+		var->base = vmx_read_guest_seg_base(vmx, seg);
+		var->selector = vmx_read_guest_seg_selector(vmx, seg);
+		return;
 	}
 	var->base = vmx_read_guest_seg_base(vmx, seg);
 	var->limit = vmx_read_guest_seg_limit(vmx, seg);
 	var->selector = vmx_read_guest_seg_selector(vmx, seg);
 	ar = vmx_read_guest_seg_ar(vmx, seg);
-use_saved_rmode_seg:
 	if ((ar & AR_UNUSABLE_MASK) && !emulate_invalid_guest_state)
 		ar = 0;
 	var->type = ar & 15;
@@ -3227,23 +3198,21 @@ static void vmx_set_segment(struct kvm_vcpu *vcpu,
 			    struct kvm_segment *var, int seg)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
-	struct kvm_vmx_segment_field *sf = &kvm_vmx_segment_fields[seg];
+	const struct kvm_vmx_segment_field *sf = &kvm_vmx_segment_fields[seg];
 	u32 ar;
 
 	vmx_segment_cache_clear(vmx);
 
 	if (vmx->rmode.vm86_active && seg == VCPU_SREG_TR) {
 		vmcs_write16(sf->selector, var->selector);
-		vmx->rmode.tr.selector = var->selector;
+		vmx->rmode.segs[VCPU_SREG_TR] = *var;
-		vmx->rmode.tr.base = var->base;
-		vmx->rmode.tr.limit = var->limit;
-		vmx->rmode.tr.ar = vmx_segment_access_rights(var);
 		return;
 	}
 	vmcs_writel(sf->base, var->base);
 	vmcs_write32(sf->limit, var->limit);
 	vmcs_write16(sf->selector, var->selector);
 	if (vmx->rmode.vm86_active && var->s) {
+		vmx->rmode.segs[seg] = *var;
 		/*
 		 * Hack real-mode segments into vm86 compatibility.
 		 */
@@ -3258,7 +3227,7 @@ static void vmx_set_segment(struct kvm_vcpu *vcpu,
 	 * qemu binaries.
 	 *   IA32 arch specifies that at the time of processor reset the
 	 * "Accessed" bit in the AR field of segment registers is 1. And qemu
-	 * is setting it to 0 in the usedland code. This causes invalid guest
+	 * is setting it to 0 in the userland code. This causes invalid guest
 	 * state vmexit when "unrestricted guest" mode is turned on.
 	 *    Fix for this setup issue in cpu_reset is being pushed in the qemu
 	 * tree. Newer qemu binaries with that qemu fix would not need this
@@ -3288,16 +3257,10 @@ static void vmx_set_segment(struct kvm_vcpu *vcpu,
 				     vmcs_readl(GUEST_CS_BASE) >> 4);
 			break;
 		case VCPU_SREG_ES:
-			fix_rmode_seg(VCPU_SREG_ES, &vmx->rmode.es);
-			break;
 		case VCPU_SREG_DS:
-			fix_rmode_seg(VCPU_SREG_DS, &vmx->rmode.ds);
-			break;
 		case VCPU_SREG_GS:
-			fix_rmode_seg(VCPU_SREG_GS, &vmx->rmode.gs);
-			break;
 		case VCPU_SREG_FS:
-			fix_rmode_seg(VCPU_SREG_FS, &vmx->rmode.fs);
+			fix_rmode_seg(seg, &vmx->rmode.segs[seg]);
 			break;
 		case VCPU_SREG_SS:
 			vmcs_write16(GUEST_SS_SELECTOR,
@@ -3351,9 +3314,9 @@ static bool rmode_segment_valid(struct kvm_vcpu *vcpu, int seg)
 
 	if (var.base != (var.selector << 4))
 		return false;
-	if (var.limit != 0xffff)
+	if (var.limit < 0xffff)
 		return false;
-	if (ar != 0xf3)
+	if (((ar | (3 << AR_DPL_SHIFT)) & ~(AR_G_MASK | AR_DB_MASK)) != 0xf3)
 		return false;
 
 	return true;
@@ -3605,7 +3568,7 @@ out:
 
 static void seg_setup(int seg)
 {
-	struct kvm_vmx_segment_field *sf = &kvm_vmx_segment_fields[seg];
+	const struct kvm_vmx_segment_field *sf = &kvm_vmx_segment_fields[seg];
 	unsigned int ar;
 
 	vmcs_write16(sf->selector, 0);
@@ -3770,8 +3733,7 @@ static void vmx_set_constant_host_state(void)
 	native_store_idt(&dt);
 	vmcs_writel(HOST_IDTR_BASE, dt.address);   /* 22.2.4 */
 
-	asm("mov $.Lkvm_vmx_return, %0" : "=r"(tmpl));
+	vmcs_writel(HOST_RIP, vmx_return); /* 22.2.5 */
-	vmcs_writel(HOST_RIP, tmpl); /* 22.2.5 */
 
 	rdmsr(MSR_IA32_SYSENTER_CS, low32, high32);
 	vmcs_write32(HOST_IA32_SYSENTER_CS, low32);
@@ -4005,8 +3967,6 @@ static int vmx_vcpu_reset(struct kvm_vcpu *vcpu)
 		kvm_rip_write(vcpu, 0);
 	kvm_register_write(vcpu, VCPU_REGS_RSP, 0);
 
-	vmcs_writel(GUEST_DR7, 0x400);
-
 	vmcs_writel(GUEST_GDTR_BASE, 0);
 	vmcs_write32(GUEST_GDTR_LIMIT, 0xffff);
 
@@ -4456,7 +4416,7 @@ vmx_patch_hypercall(struct kvm_vcpu *vcpu, unsigned char *hypercall)
 	hypercall[2] = 0xc1;
 }
 
-/* called to set cr0 as approriate for a mov-to-cr0 exit. */
+/* called to set cr0 as appropriate for a mov-to-cr0 exit. */
 static int handle_set_cr0(struct kvm_vcpu *vcpu, unsigned long val)
 {
 	if (to_vmx(vcpu)->nested.vmxon &&
@@ -5701,7 +5661,7 @@ static int handle_vmptrst(struct kvm_vcpu *vcpu)
  * may resume.  Otherwise they set the kvm_run parameter to indicate what needs
  * to be done to userspace and return 0.
  */
-static int (*kvm_vmx_exit_handlers[])(struct kvm_vcpu *vcpu) = {
+static int (*const kvm_vmx_exit_handlers[])(struct kvm_vcpu *vcpu) = {
 	[EXIT_REASON_EXCEPTION_NMI]           = handle_exception,
 	[EXIT_REASON_EXTERNAL_INTERRUPT]      = handle_external_interrupt,
 	[EXIT_REASON_TRIPLE_FAULT]            = handle_triple_fault,
@@ -6229,17 +6189,10 @@ static void atomic_switch_perf_msrs(struct vcpu_vmx *vmx)
 					msrs[i].host);
 }
 
-#ifdef CONFIG_X86_64
-#define R "r"
-#define Q "q"
-#else
-#define R "e"
-#define Q "l"
-#endif
-
 static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
+	unsigned long debugctlmsr;
 
 	if (is_guest_mode(vcpu) && !vmx->nested.nested_run_pending) {
 		struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
@@ -6279,34 +6232,35 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu)
 		vmx_set_interrupt_shadow(vcpu, 0);
 
 	atomic_switch_perf_msrs(vmx);
+	debugctlmsr = get_debugctlmsr();
 
 	vmx->__launched = vmx->loaded_vmcs->launched;
 	asm(
 		/* Store host registers */
-		"push %%"R"dx; push %%"R"bp;"
+		"push %%" _ASM_DX "; push %%" _ASM_BP ";"
-		"push %%"R"cx \n\t" /* placeholder for guest rcx */
+		"push %%" _ASM_CX " \n\t" /* placeholder for guest rcx */
-		"push %%"R"cx \n\t"
+		"push %%" _ASM_CX " \n\t"
-		"cmp %%"R"sp, %c[host_rsp](%0) \n\t"
+		"cmp %%" _ASM_SP ", %c[host_rsp](%0) \n\t"
 		"je 1f \n\t"
-		"mov %%"R"sp, %c[host_rsp](%0) \n\t"
+		"mov %%" _ASM_SP ", %c[host_rsp](%0) \n\t"
 		__ex(ASM_VMX_VMWRITE_RSP_RDX) "\n\t"
 		"1: \n\t"
 		/* Reload cr2 if changed */
-		"mov %c[cr2](%0), %%"R"ax \n\t"
+		"mov %c[cr2](%0), %%" _ASM_AX " \n\t"
-		"mov %%cr2, %%"R"dx \n\t"
+		"mov %%cr2, %%" _ASM_DX " \n\t"
-		"cmp %%"R"ax, %%"R"dx \n\t"
+		"cmp %%" _ASM_AX ", %%" _ASM_DX " \n\t"
 		"je 2f \n\t"
-		"mov %%"R"ax, %%cr2 \n\t"
+		"mov %%" _ASM_AX", %%cr2 \n\t"
 		"2: \n\t"
 		/* Check if vmlaunch of vmresume is needed */
 		"cmpl $0, %c[launched](%0) \n\t"
 		/* Load guest registers.  Don't clobber flags. */
-		"mov %c[rax](%0), %%"R"ax \n\t"
+		"mov %c[rax](%0), %%" _ASM_AX " \n\t"
-		"mov %c[rbx](%0), %%"R"bx \n\t"
+		"mov %c[rbx](%0), %%" _ASM_BX " \n\t"
-		"mov %c[rdx](%0), %%"R"dx \n\t"
+		"mov %c[rdx](%0), %%" _ASM_DX " \n\t"
-		"mov %c[rsi](%0), %%"R"si \n\t"
+		"mov %c[rsi](%0), %%" _ASM_SI " \n\t"
-		"mov %c[rdi](%0), %%"R"di \n\t"
+		"mov %c[rdi](%0), %%" _ASM_DI " \n\t"
-		"mov %c[rbp](%0), %%"R"bp \n\t"
+		"mov %c[rbp](%0), %%" _ASM_BP " \n\t"
 #ifdef CONFIG_X86_64
 		"mov %c[r8](%0),  %%r8  \n\t"
 		"mov %c[r9](%0),  %%r9  \n\t"
@@ -6317,24 +6271,24 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu)
 		"mov %c[r14](%0), %%r14 \n\t"
 		"mov %c[r15](%0), %%r15 \n\t"
 #endif
-		"mov %c[rcx](%0), %%"R"cx \n\t" /* kills %0 (ecx) */
+		"mov %c[rcx](%0), %%" _ASM_CX " \n\t" /* kills %0 (ecx) */
 
 		/* Enter guest mode */
-		"jne .Llaunched \n\t"
+		"jne 1f \n\t"
 		__ex(ASM_VMX_VMLAUNCH) "\n\t"
-		"jmp .Lkvm_vmx_return \n\t"
+		"jmp 2f \n\t"
-		".Llaunched: " __ex(ASM_VMX_VMRESUME) "\n\t"
+		"1: " __ex(ASM_VMX_VMRESUME) "\n\t"
-		".Lkvm_vmx_return: "
+		"2: "
 		/* Save guest registers, load host registers, keep flags */
-		"mov %0, %c[wordsize](%%"R"sp) \n\t"
+		"mov %0, %c[wordsize](%%" _ASM_SP ") \n\t"
 		"pop %0 \n\t"
-		"mov %%"R"ax, %c[rax](%0) \n\t"
+		"mov %%" _ASM_AX ", %c[rax](%0) \n\t"
-		"mov %%"R"bx, %c[rbx](%0) \n\t"
+		"mov %%" _ASM_BX ", %c[rbx](%0) \n\t"
-		"pop"Q" %c[rcx](%0) \n\t"
+		__ASM_SIZE(pop) " %c[rcx](%0) \n\t"
-		"mov %%"R"dx, %c[rdx](%0) \n\t"
+		"mov %%" _ASM_DX ", %c[rdx](%0) \n\t"
-		"mov %%"R"si, %c[rsi](%0) \n\t"
+		"mov %%" _ASM_SI ", %c[rsi](%0) \n\t"
-		"mov %%"R"di, %c[rdi](%0) \n\t"
+		"mov %%" _ASM_DI ", %c[rdi](%0) \n\t"
-		"mov %%"R"bp, %c[rbp](%0) \n\t"
+		"mov %%" _ASM_BP ", %c[rbp](%0) \n\t"
 #ifdef CONFIG_X86_64
 		"mov %%r8,  %c[r8](%0) \n\t"
 		"mov %%r9,  %c[r9](%0) \n\t"
@@ -6345,11 +6299,15 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu)
 		"mov %%r14, %c[r14](%0) \n\t"
 		"mov %%r15, %c[r15](%0) \n\t"
 #endif
-		"mov %%cr2, %%"R"ax   \n\t"
+		"mov %%cr2, %%" _ASM_AX "   \n\t"
-		"mov %%"R"ax, %c[cr2](%0) \n\t"
+		"mov %%" _ASM_AX ", %c[cr2](%0) \n\t"
 
-		"pop  %%"R"bp; pop  %%"R"dx \n\t"
+		"pop  %%" _ASM_BP "; pop  %%" _ASM_DX " \n\t"
 		"setbe %c[fail](%0) \n\t"
+		".pushsection .rodata \n\t"
+		".global vmx_return \n\t"
+		"vmx_return: " _ASM_PTR " 2b \n\t"
+		".popsection"
 	      : : "c"(vmx), "d"((unsigned long)HOST_RSP),
 		[launched]"i"(offsetof(struct vcpu_vmx, __launched)),
 		[fail]"i"(offsetof(struct vcpu_vmx, fail)),
@@ -6374,12 +6332,18 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu)
 		[cr2]"i"(offsetof(struct vcpu_vmx, vcpu.arch.cr2)),
 		[wordsize]"i"(sizeof(ulong))
 	      : "cc", "memory"
-		, R"ax", R"bx", R"di", R"si"
 #ifdef CONFIG_X86_64
+		, "rax", "rbx", "rdi", "rsi"
 		, "r8", "r9", "r10", "r11", "r12", "r13", "r14", "r15"
+#else
+		, "eax", "ebx", "edi", "esi"
 #endif
 	      );
 
+	/* MSR_IA32_DEBUGCTLMSR is zeroed on vmexit. Restore it if needed */
+	if (debugctlmsr)
+		update_debugctlmsr(debugctlmsr);
+
 #ifndef CONFIG_X86_64
 	/*
 	 * The sysexit path does not restore ds/es, so we must set them to
@@ -6424,9 +6388,6 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu)
 	vmx_complete_interrupts(vmx);
 }
 
-#undef R
-#undef Q
-
 static void vmx_free_vcpu(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
@@ -7281,7 +7242,7 @@ static struct kvm_x86_ops vmx_x86_ops = {
 	.vcpu_load = vmx_vcpu_load,
 	.vcpu_put = vmx_vcpu_put,
 
-	.set_guest_debug = set_guest_debug,
+	.update_db_bp_intercept = update_exception_bitmap,
 	.get_msr = vmx_get_msr,
 	.set_msr = vmx_set_msr,
 	.get_segment_base = vmx_get_segment_base,

arch/x86/kvm/x86.c

@@ -246,9 +246,6 @@ static void drop_user_return_notifiers(void *ignore)
 
 u64 kvm_get_apic_base(struct kvm_vcpu *vcpu)
 {
-	if (irqchip_in_kernel(vcpu->kvm))
-		return vcpu->arch.apic_base;
-	else
 	return vcpu->arch.apic_base;
 }
 EXPORT_SYMBOL_GPL(kvm_get_apic_base);
@@ -256,10 +253,7 @@ EXPORT_SYMBOL_GPL(kvm_get_apic_base);
 void kvm_set_apic_base(struct kvm_vcpu *vcpu, u64 data)
 {
 	/* TODO: reserve bits check */
-	if (irqchip_in_kernel(vcpu->kvm))
 	kvm_lapic_set_base(vcpu, data);
-	else
-		vcpu->arch.apic_base = data;
 }
 EXPORT_SYMBOL_GPL(kvm_set_apic_base);
 
@@ -698,6 +692,18 @@ unsigned long kvm_get_cr8(struct kvm_vcpu *vcpu)
 }
 EXPORT_SYMBOL_GPL(kvm_get_cr8);
 
+static void kvm_update_dr7(struct kvm_vcpu *vcpu)
+{
+	unsigned long dr7;
+
+	if (vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP)
+		dr7 = vcpu->arch.guest_debug_dr7;
+	else
+		dr7 = vcpu->arch.dr7;
+	kvm_x86_ops->set_dr7(vcpu, dr7);
+	vcpu->arch.switch_db_regs = (dr7 & DR7_BP_EN_MASK);
+}
+
 static int __kvm_set_dr(struct kvm_vcpu *vcpu, int dr, unsigned long val)
 {
 	switch (dr) {
@@ -723,10 +729,7 @@ static int __kvm_set_dr(struct kvm_vcpu *vcpu, int dr, unsigned long val)
 		if (val & 0xffffffff00000000ULL)
 			return -1; /* #GP */
 		vcpu->arch.dr7 = (val & DR7_VOLATILE) | DR7_FIXED_1;
-		if (!(vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP)) {
+		kvm_update_dr7(vcpu);
-			kvm_x86_ops->set_dr7(vcpu, vcpu->arch.dr7);
-			vcpu->arch.switch_db_regs = (val & DR7_BP_EN_MASK);
-		}
 		break;
 	}
 
@@ -823,7 +826,7 @@ static u32 msrs_to_save[] = {
 
 static unsigned num_msrs_to_save;
 
-static u32 emulated_msrs[] = {
+static const u32 emulated_msrs[] = {
 	MSR_IA32_TSCDEADLINE,
 	MSR_IA32_MISC_ENABLE,
 	MSR_IA32_MCG_STATUS,
@@ -1097,7 +1100,7 @@ void kvm_write_tsc(struct kvm_vcpu *vcpu, u64 data)
 		 * For each generation, we track the original measured
 		 * nanosecond time, offset, and write, so if TSCs are in
 		 * sync, we can match exact offset, and if not, we can match
-		 * exact software computaion in compute_guest_tsc()
+		 * exact software computation in compute_guest_tsc()
 		 *
 		 * These values are tracked in kvm->arch.cur_xxx variables.
 		 */
@@ -1140,6 +1143,7 @@ static int kvm_guest_time_update(struct kvm_vcpu *v)
 	unsigned long this_tsc_khz;
 	s64 kernel_ns, max_kernel_ns;
 	u64 tsc_timestamp;
+	u8 pvclock_flags;
 
 	/* Keep irq disabled to prevent changes to the clock */
 	local_irq_save(flags);
@@ -1221,7 +1225,14 @@ static int kvm_guest_time_update(struct kvm_vcpu *v)
 	vcpu->hv_clock.system_time = kernel_ns + v->kvm->arch.kvmclock_offset;
 	vcpu->last_kernel_ns = kernel_ns;
 	vcpu->last_guest_tsc = tsc_timestamp;
-	vcpu->hv_clock.flags = 0;
+
+	pvclock_flags = 0;
+	if (vcpu->pvclock_set_guest_stopped_request) {
+		pvclock_flags |= PVCLOCK_GUEST_STOPPED;
+		vcpu->pvclock_set_guest_stopped_request = false;
+	}
+
+	vcpu->hv_clock.flags = pvclock_flags;
 
 	/*
 	 * The interface expects us to write an even number signaling that the
@@ -1504,7 +1515,7 @@ static int kvm_pv_enable_async_pf(struct kvm_vcpu *vcpu, u64 data)
 {
 	gpa_t gpa = data & ~0x3f;
 
-	/* Bits 2:5 are resrved, Should be zero */
+	/* Bits 2:5 are reserved, Should be zero */
 	if (data & 0x3c)
 		return 1;
 
@@ -1639,10 +1650,9 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data)
 		vcpu->arch.time_page =
 				gfn_to_page(vcpu->kvm, data >> PAGE_SHIFT);
 
-		if (is_error_page(vcpu->arch.time_page)) {
+		if (is_error_page(vcpu->arch.time_page))
-			kvm_release_page_clean(vcpu->arch.time_page);
 			vcpu->arch.time_page = NULL;
-		}
+
 		break;
 	}
 	case MSR_KVM_ASYNC_PF_EN:
@@ -1727,7 +1737,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data)
 		 * Ignore all writes to this no longer documented MSR.
 		 * Writes are only relevant for old K7 processors,
 		 * all pre-dating SVM, but a recommended workaround from
-		 * AMD for these chips. It is possible to speicify the
+		 * AMD for these chips. It is possible to specify the
 		 * affected processor models on the command line, hence
 		 * the need to ignore the workaround.
 		 */
@@ -2177,6 +2187,8 @@ int kvm_dev_ioctl_check_extension(long ext)
 	case KVM_CAP_GET_TSC_KHZ:
 	case KVM_CAP_PCI_2_3:
 	case KVM_CAP_KVMCLOCK_CTRL:
+	case KVM_CAP_READONLY_MEM:
+	case KVM_CAP_IRQFD_RESAMPLE:
 		r = 1;
 		break;
 	case KVM_CAP_COALESCED_MMIO:
@@ -2358,8 +2370,7 @@ static int kvm_vcpu_ioctl_get_lapic(struct kvm_vcpu *vcpu,
 static int kvm_vcpu_ioctl_set_lapic(struct kvm_vcpu *vcpu,
 				    struct kvm_lapic_state *s)
 {
-	memcpy(vcpu->arch.apic->regs, s->regs, sizeof *s);
+	kvm_apic_post_state_restore(vcpu, s);
-	kvm_apic_post_state_restore(vcpu);
 	update_cr8_intercept(vcpu);
 
 	return 0;
@@ -2368,7 +2379,7 @@ static int kvm_vcpu_ioctl_set_lapic(struct kvm_vcpu *vcpu,
 static int kvm_vcpu_ioctl_interrupt(struct kvm_vcpu *vcpu,
 				    struct kvm_interrupt *irq)
 {
-	if (irq->irq < 0 || irq->irq >= 256)
+	if (irq->irq < 0 || irq->irq >= KVM_NR_INTERRUPTS)
 		return -EINVAL;
 	if (irqchip_in_kernel(vcpu->kvm))
 		return -ENXIO;
@@ -2635,11 +2646,9 @@ static int kvm_vcpu_ioctl_x86_set_xcrs(struct kvm_vcpu *vcpu,
  */
 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;
+	vcpu->arch.pvclock_set_guest_stopped_request = true;
-	mark_page_dirty(vcpu->kvm, vcpu->arch.time >> PAGE_SHIFT);
 	kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu);
 	return 0;
 }
@@ -3090,7 +3099,7 @@ static int kvm_vm_ioctl_reinject(struct kvm *kvm,
 	if (!kvm->arch.vpit)
 		return -ENXIO;
 	mutex_lock(&kvm->arch.vpit->pit_state.lock);
-	kvm->arch.vpit->pit_state.pit_timer.reinject = control->pit_reinject;
+	kvm->arch.vpit->pit_state.reinject = control->pit_reinject;
 	mutex_unlock(&kvm->arch.vpit->pit_state.lock);
 	return 0;
 }
@@ -3173,6 +3182,16 @@ out:
 	return r;
 }
 
+int kvm_vm_ioctl_irq_line(struct kvm *kvm, struct kvm_irq_level *irq_event)
+{
+	if (!irqchip_in_kernel(kvm))
+		return -ENXIO;
+
+	irq_event->status = kvm_set_irq(kvm, KVM_USERSPACE_IRQ_SOURCE_ID,
+					irq_event->irq, irq_event->level);
+	return 0;
+}
+
 long kvm_arch_vm_ioctl(struct file *filp,
 		       unsigned int ioctl, unsigned long arg)
 {
@@ -3279,29 +3298,6 @@ long kvm_arch_vm_ioctl(struct file *filp,
 	create_pit_unlock:
 		mutex_unlock(&kvm->slots_lock);
 		break;
-	case KVM_IRQ_LINE_STATUS:
-	case KVM_IRQ_LINE: {
-		struct kvm_irq_level irq_event;
-
-		r = -EFAULT;
-		if (copy_from_user(&irq_event, argp, sizeof irq_event))
-			goto out;
-		r = -ENXIO;
-		if (irqchip_in_kernel(kvm)) {
-			__s32 status;
-			status = kvm_set_irq(kvm, KVM_USERSPACE_IRQ_SOURCE_ID,
-					irq_event.irq, irq_event.level);
-			if (ioctl == KVM_IRQ_LINE_STATUS) {
-				r = -EFAULT;
-				irq_event.status = status;
-				if (copy_to_user(argp, &irq_event,
-							sizeof irq_event))
-					goto out;
-			}
-			r = 0;
-		}
-		break;
-	}
 	case KVM_GET_IRQCHIP: {
 		/* 0: PIC master, 1: PIC slave, 2: IOAPIC */
 		struct kvm_irqchip *chip;
@@ -3689,20 +3685,17 @@ static int vcpu_mmio_gva_to_gpa(struct kvm_vcpu *vcpu, unsigned long gva,
 				gpa_t *gpa, struct x86_exception *exception,
 				bool write)
 {
-	u32 access = (kvm_x86_ops->get_cpl(vcpu) == 3) ? PFERR_USER_MASK : 0;
+	u32 access = ((kvm_x86_ops->get_cpl(vcpu) == 3) ? PFERR_USER_MASK : 0)
+		| (write ? PFERR_WRITE_MASK : 0);
 
-	if (vcpu_match_mmio_gva(vcpu, gva) &&
+	if (vcpu_match_mmio_gva(vcpu, gva)
-		  check_write_user_access(vcpu, write, access,
+	    && !permission_fault(vcpu->arch.walk_mmu, vcpu->arch.access, access)) {
-		  vcpu->arch.access)) {
 		*gpa = vcpu->arch.mmio_gfn << PAGE_SHIFT |
 					(gva & (PAGE_SIZE - 1));
 		trace_vcpu_match_mmio(gva, *gpa, write, false);
 		return 1;
 	}
 
-	if (write)
-		access |= PFERR_WRITE_MASK;
-
 	*gpa = vcpu->arch.walk_mmu->gva_to_gpa(vcpu, gva, access, exception);
 
 	if (*gpa == UNMAPPED_GVA)
@@ -3790,14 +3783,14 @@ static int write_exit_mmio(struct kvm_vcpu *vcpu, gpa_t gpa,
 	return X86EMUL_CONTINUE;
 }
 
-static struct read_write_emulator_ops read_emultor = {
+static const struct read_write_emulator_ops read_emultor = {
 	.read_write_prepare = read_prepare,
 	.read_write_emulate = read_emulate,
 	.read_write_mmio = vcpu_mmio_read,
 	.read_write_exit_mmio = read_exit_mmio,
 };
 
-static struct read_write_emulator_ops write_emultor = {
+static const struct read_write_emulator_ops write_emultor = {
 	.read_write_emulate = write_emulate,
 	.read_write_mmio = write_mmio,
 	.read_write_exit_mmio = write_exit_mmio,
@@ -3808,7 +3801,7 @@ static int emulator_read_write_onepage(unsigned long addr, void *val,
 				       unsigned int bytes,
 				       struct x86_exception *exception,
 				       struct kvm_vcpu *vcpu,
-				       struct read_write_emulator_ops *ops)
+				       const struct read_write_emulator_ops *ops)
 {
 	gpa_t gpa;
 	int handled, ret;
@@ -3857,7 +3850,7 @@ mmio:
 int emulator_read_write(struct x86_emulate_ctxt *ctxt, unsigned long addr,
 			void *val, unsigned int bytes,
 			struct x86_exception *exception,
-			struct read_write_emulator_ops *ops)
+			const struct read_write_emulator_ops *ops)
 {
 	struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt);
 	gpa_t gpa;
@@ -3962,10 +3955,8 @@ static int emulator_cmpxchg_emulated(struct x86_emulate_ctxt *ctxt,
 		goto emul_write;
 
 	page = gfn_to_page(vcpu->kvm, gpa >> PAGE_SHIFT);
-	if (is_error_page(page)) {
+	if (is_error_page(page))
-		kvm_release_page_clean(page);
 		goto emul_write;
-	}
 
 	kaddr = kmap_atomic(page);
 	kaddr += offset_in_page(gpa);
@@ -4332,7 +4323,19 @@ static void emulator_get_cpuid(struct x86_emulate_ctxt *ctxt,
 	kvm_cpuid(emul_to_vcpu(ctxt), eax, ebx, ecx, edx);
 }
 
-static struct x86_emulate_ops emulate_ops = {
+static ulong emulator_read_gpr(struct x86_emulate_ctxt *ctxt, unsigned reg)
+{
+	return kvm_register_read(emul_to_vcpu(ctxt), reg);
+}
+
+static void emulator_write_gpr(struct x86_emulate_ctxt *ctxt, unsigned reg, ulong val)
+{
+	kvm_register_write(emul_to_vcpu(ctxt), reg, val);
+}
+
+static const struct x86_emulate_ops emulate_ops = {
+	.read_gpr            = emulator_read_gpr,
+	.write_gpr           = emulator_write_gpr,
 	.read_std            = kvm_read_guest_virt_system,
 	.write_std           = kvm_write_guest_virt_system,
 	.fetch               = kvm_fetch_guest_virt,
@@ -4367,14 +4370,6 @@ static struct x86_emulate_ops emulate_ops = {
 	.get_cpuid           = emulator_get_cpuid,
 };
 
-static void cache_all_regs(struct kvm_vcpu *vcpu)
-{
-	kvm_register_read(vcpu, VCPU_REGS_RAX);
-	kvm_register_read(vcpu, VCPU_REGS_RSP);
-	kvm_register_read(vcpu, VCPU_REGS_RIP);
-	vcpu->arch.regs_dirty = ~0;
-}
-
 static void toggle_interruptibility(struct kvm_vcpu *vcpu, u32 mask)
 {
 	u32 int_shadow = kvm_x86_ops->get_interrupt_shadow(vcpu, mask);
@@ -4401,12 +4396,10 @@ static void inject_emulated_exception(struct kvm_vcpu *vcpu)
 		kvm_queue_exception(vcpu, ctxt->exception.vector);
 }
 
-static void init_decode_cache(struct x86_emulate_ctxt *ctxt,
+static void init_decode_cache(struct x86_emulate_ctxt *ctxt)
-			      const unsigned long *regs)
 {
 	memset(&ctxt->twobyte, 0,
-	       (void *)&ctxt->regs - (void *)&ctxt->twobyte);
+	       (void *)&ctxt->_regs - (void *)&ctxt->twobyte);
-	memcpy(ctxt->regs, regs, sizeof(ctxt->regs));
 
 	ctxt->fetch.start = 0;
 	ctxt->fetch.end = 0;
@@ -4421,14 +4414,6 @@ static void init_emulate_ctxt(struct kvm_vcpu *vcpu)
 	struct x86_emulate_ctxt *ctxt = &vcpu->arch.emulate_ctxt;
 	int cs_db, cs_l;
 
-	/*
-	 * TODO: fix emulate.c to use guest_read/write_register
-	 * instead of direct ->regs accesses, can save hundred cycles
-	 * on Intel for instructions that don't read/change RSP, for
-	 * for example.
-	 */
-	cache_all_regs(vcpu);
-
 	kvm_x86_ops->get_cs_db_l_bits(vcpu, &cs_db, &cs_l);
 
 	ctxt->eflags = kvm_get_rflags(vcpu);
@@ -4440,7 +4425,7 @@ static void init_emulate_ctxt(struct kvm_vcpu *vcpu)
 							  X86EMUL_MODE_PROT16;
 	ctxt->guest_mode = is_guest_mode(vcpu);
 
-	init_decode_cache(ctxt, vcpu->arch.regs);
+	init_decode_cache(ctxt);
 	vcpu->arch.emulate_regs_need_sync_from_vcpu = false;
 }
 
@@ -4460,7 +4445,6 @@ int kvm_inject_realmode_interrupt(struct kvm_vcpu *vcpu, int irq, int inc_eip)
 		return EMULATE_FAIL;
 
 	ctxt->eip = ctxt->_eip;
-	memcpy(vcpu->arch.regs, ctxt->regs, sizeof ctxt->regs);
 	kvm_rip_write(vcpu, ctxt->eip);
 	kvm_set_rflags(vcpu, ctxt->eflags);
 
@@ -4493,13 +4477,14 @@ static int handle_emulation_failure(struct kvm_vcpu *vcpu)
 static bool reexecute_instruction(struct kvm_vcpu *vcpu, gva_t gva)
 {
 	gpa_t gpa;
+	pfn_t pfn;
 
 	if (tdp_enabled)
 		return false;
 
 	/*
 	 * if emulation was due to access to shadowed page table
-	 * and it failed try to unshadow page and re-entetr the
+	 * and it failed try to unshadow page and re-enter the
 	 * guest to let CPU execute the instruction.
 	 */
 	if (kvm_mmu_unprotect_page_virt(vcpu, gva))
@@ -4510,8 +4495,17 @@ static bool reexecute_instruction(struct kvm_vcpu *vcpu, gva_t gva)
 	if (gpa == UNMAPPED_GVA)
 		return true; /* let cpu generate fault */
 
-	if (!kvm_is_error_hva(gfn_to_hva(vcpu->kvm, gpa >> PAGE_SHIFT)))
+	/*
+	 * Do not retry the unhandleable instruction if it faults on the
+	 * readonly host memory, otherwise it will goto a infinite loop:
+	 * retry instruction -> write #PF -> emulation fail -> retry
+	 * instruction -> ...
+	 */
+	pfn = gfn_to_pfn(vcpu->kvm, gpa_to_gfn(gpa));
+	if (!is_error_pfn(pfn)) {
+		kvm_release_pfn_clean(pfn);
 		return true;
+	}
 
 	return false;
 }
@@ -4560,6 +4554,9 @@ static bool retry_instruction(struct x86_emulate_ctxt *ctxt,
 	return true;
 }
 
+static int complete_emulated_mmio(struct kvm_vcpu *vcpu);
+static int complete_emulated_pio(struct kvm_vcpu *vcpu);
+
 int x86_emulate_instruction(struct kvm_vcpu *vcpu,
 			    unsigned long cr2,
 			    int emulation_type,
@@ -4608,7 +4605,7 @@ int x86_emulate_instruction(struct kvm_vcpu *vcpu,
 	   changes registers values  during IO operation */
 	if (vcpu->arch.emulate_regs_need_sync_from_vcpu) {
 		vcpu->arch.emulate_regs_need_sync_from_vcpu = false;
-		memcpy(ctxt->regs, vcpu->arch.regs, sizeof ctxt->regs);
+		emulator_invalidate_register_cache(ctxt);
 	}
 
 restart:
@@ -4630,13 +4627,16 @@ restart:
 	} else if (vcpu->arch.pio.count) {
 		if (!vcpu->arch.pio.in)
 			vcpu->arch.pio.count = 0;
-		else
+		else {
 			writeback = false;
+			vcpu->arch.complete_userspace_io = complete_emulated_pio;
+		}
 		r = EMULATE_DO_MMIO;
 	} else if (vcpu->mmio_needed) {
 		if (!vcpu->mmio_is_write)
 			writeback = false;
 		r = EMULATE_DO_MMIO;
+		vcpu->arch.complete_userspace_io = complete_emulated_mmio;
 	} else if (r == EMULATION_RESTART)
 		goto restart;
 	else
@@ -4646,7 +4646,6 @@ restart:
 		toggle_interruptibility(vcpu, ctxt->interruptibility);
 		kvm_set_rflags(vcpu, ctxt->eflags);
 		kvm_make_request(KVM_REQ_EVENT, vcpu);
-		memcpy(vcpu->arch.regs, ctxt->regs, sizeof ctxt->regs);
 		vcpu->arch.emulate_regs_need_sync_to_vcpu = false;
 		kvm_rip_write(vcpu, ctxt->eip);
 	} else
@@ -4929,6 +4928,7 @@ int kvm_arch_init(void *opaque)
 	if (cpu_has_xsave)
 		host_xcr0 = xgetbv(XCR_XFEATURE_ENABLED_MASK);
 
+	kvm_lapic_init();
 	return 0;
 
 out:
@@ -5499,6 +5499,24 @@ static int __vcpu_run(struct kvm_vcpu *vcpu)
 	return r;
 }
 
+static inline int complete_emulated_io(struct kvm_vcpu *vcpu)
+{
+	int r;
+	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);
+	if (r != EMULATE_DONE)
+		return 0;
+	return 1;
+}
+
+static int complete_emulated_pio(struct kvm_vcpu *vcpu)
+{
+	BUG_ON(!vcpu->arch.pio.count);
+
+	return complete_emulated_io(vcpu);
+}
+
 /*
  * Implements the following, as a state machine:
  *
@@ -5515,16 +5533,13 @@ static int __vcpu_run(struct kvm_vcpu *vcpu)
  *      copy data
  *      exit
  */
-static int complete_mmio(struct kvm_vcpu *vcpu)
+static int complete_emulated_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))
+	BUG_ON(!vcpu->mmio_needed);
-		return 1;
 
-	if (vcpu->mmio_needed) {
 	/* Complete previous fragment */
 	frag = &vcpu->mmio_fragments[vcpu->mmio_cur_fragment++];
 	if (!vcpu->mmio_is_write)
@@ -5534,7 +5549,7 @@ static int complete_mmio(struct kvm_vcpu *vcpu)
 		if (vcpu->mmio_is_write)
 			return 1;
 		vcpu->mmio_read_completed = 1;
-			goto done;
+		return complete_emulated_io(vcpu);
 	}
 	/* Initiate next fragment */
 	++frag;
@@ -5544,18 +5559,11 @@ static int complete_mmio(struct kvm_vcpu *vcpu)
 		memcpy(run->mmio.data, frag->data, frag->len);
 	run->mmio.len = frag->len;
 	run->mmio.is_write = vcpu->mmio_is_write;
+	vcpu->arch.complete_userspace_io = complete_emulated_mmio;
 	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);
-	if (r != EMULATE_DONE)
-		return 0;
-	return 1;
 }
 
+
 int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 {
 	int r;
@@ -5582,9 +5590,14 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 		}
 	}
 
-	r = complete_mmio(vcpu);
+	if (unlikely(vcpu->arch.complete_userspace_io)) {
+		int (*cui)(struct kvm_vcpu *) = vcpu->arch.complete_userspace_io;
+		vcpu->arch.complete_userspace_io = NULL;
+		r = cui(vcpu);
 		if (r <= 0)
 			goto out;
+	} else
+		WARN_ON(vcpu->arch.pio.count || vcpu->mmio_needed);
 
 	r = __vcpu_run(vcpu);
 
@@ -5602,12 +5615,11 @@ int kvm_arch_vcpu_ioctl_get_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
 		/*
 		 * We are here if userspace calls get_regs() in the middle of
 		 * instruction emulation. Registers state needs to be copied
-		 * back from emulation context to vcpu. Usrapace shouldn't do
+		 * back from emulation context to vcpu. Userspace shouldn't do
 		 * that usually, but some bad designed PV devices (vmware
 		 * backdoor interface) need this to work
 		 */
-		struct x86_emulate_ctxt *ctxt = &vcpu->arch.emulate_ctxt;
+		emulator_writeback_register_cache(&vcpu->arch.emulate_ctxt);
-		memcpy(vcpu->arch.regs, ctxt->regs, sizeof ctxt->regs);
 		vcpu->arch.emulate_regs_need_sync_to_vcpu = false;
 	}
 	regs->rax = kvm_register_read(vcpu, VCPU_REGS_RAX);
@@ -5747,7 +5759,6 @@ int kvm_task_switch(struct kvm_vcpu *vcpu, u16 tss_selector, int idt_index,
 	if (ret)
 		return EMULATE_FAIL;
 
-	memcpy(vcpu->arch.regs, ctxt->regs, sizeof ctxt->regs);
 	kvm_rip_write(vcpu, ctxt->eip);
 	kvm_set_rflags(vcpu, ctxt->eflags);
 	kvm_make_request(KVM_REQ_EVENT, vcpu);
@@ -5799,7 +5810,7 @@ int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu,
 	if (mmu_reset_needed)
 		kvm_mmu_reset_context(vcpu);
 
-	max_bits = (sizeof sregs->interrupt_bitmap) << 3;
+	max_bits = KVM_NR_INTERRUPTS;
 	pending_vec = find_first_bit(
 		(const unsigned long *)sregs->interrupt_bitmap, max_bits);
 	if (pending_vec < max_bits) {
@@ -5859,13 +5870,12 @@ int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu,
 	if (vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP) {
 		for (i = 0; i < KVM_NR_DB_REGS; ++i)
 			vcpu->arch.eff_db[i] = dbg->arch.debugreg[i];
-		vcpu->arch.switch_db_regs =
+		vcpu->arch.guest_debug_dr7 = dbg->arch.debugreg[7];
-			(dbg->arch.debugreg[7] & DR7_BP_EN_MASK);
 	} else {
 		for (i = 0; i < KVM_NR_DB_REGS; i++)
 			vcpu->arch.eff_db[i] = vcpu->arch.db[i];
-		vcpu->arch.switch_db_regs = (vcpu->arch.dr7 & DR7_BP_EN_MASK);
 	}
+	kvm_update_dr7(vcpu);
 
 	if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP)
 		vcpu->arch.singlestep_rip = kvm_rip_read(vcpu) +
@@ -5877,7 +5887,7 @@ int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu,
 	 */
 	kvm_set_rflags(vcpu, rflags);
 
-	kvm_x86_ops->set_guest_debug(vcpu, dbg);
+	kvm_x86_ops->update_db_bp_intercept(vcpu);
 
 	r = 0;
 
@@ -6023,7 +6033,9 @@ int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu)
 	int r;
 
 	vcpu->arch.mtrr_state.have_fixed = 1;
-	vcpu_load(vcpu);
+	r = vcpu_load(vcpu);
+	if (r)
+		return r;
 	r = kvm_arch_vcpu_reset(vcpu);
 	if (r == 0)
 		r = kvm_mmu_setup(vcpu);
@@ -6034,9 +6046,11 @@ int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu)
 
 void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu)
 {
+	int r;
 	vcpu->arch.apf.msr_val = 0;
 
-	vcpu_load(vcpu);
+	r = vcpu_load(vcpu);
+	BUG_ON(r);
 	kvm_mmu_unload(vcpu);
 	vcpu_put(vcpu);
 
@@ -6050,10 +6064,10 @@ int kvm_arch_vcpu_reset(struct kvm_vcpu *vcpu)
 	vcpu->arch.nmi_pending = 0;
 	vcpu->arch.nmi_injected = false;
 
-	vcpu->arch.switch_db_regs = 0;
 	memset(vcpu->arch.db, 0, sizeof(vcpu->arch.db));
 	vcpu->arch.dr6 = DR6_FIXED_1;
 	vcpu->arch.dr7 = DR7_FIXED_1;
+	kvm_update_dr7(vcpu);
 
 	kvm_make_request(KVM_REQ_EVENT, vcpu);
 	vcpu->arch.apf.msr_val = 0;
@@ -6132,7 +6146,7 @@ int kvm_arch_hardware_enable(void *garbage)
 	 * as we reset last_host_tsc on all VCPUs to stop this from being
 	 * called multiple times (one for each physical CPU bringup).
 	 *
-	 * Platforms with unnreliable TSCs don't have to deal with this, they
+	 * Platforms with unreliable TSCs don't have to deal with this, they
 	 * will be compensated by the logic in vcpu_load, which sets the TSC to
 	 * catchup mode.  This will catchup all VCPUs to real time, but cannot
 	 * guarantee that they stay in perfect synchronization.
@@ -6185,6 +6199,8 @@ bool kvm_vcpu_compatible(struct kvm_vcpu *vcpu)
 	return irqchip_in_kernel(vcpu->kvm) == (vcpu->arch.apic != NULL);
 }
 
+struct static_key kvm_no_apic_vcpu __read_mostly;
+
 int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
 {
 	struct page *page;
@@ -6217,7 +6233,8 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
 		r = kvm_create_lapic(vcpu);
 		if (r < 0)
 			goto fail_mmu_destroy;
-	}
+	} else
+		static_key_slow_inc(&kvm_no_apic_vcpu);
 
 	vcpu->arch.mce_banks = kzalloc(KVM_MAX_MCE_BANKS * sizeof(u64) * 4,
 				       GFP_KERNEL);
@@ -6257,6 +6274,8 @@ void kvm_arch_vcpu_uninit(struct kvm_vcpu *vcpu)
 	kvm_mmu_destroy(vcpu);
 	srcu_read_unlock(&vcpu->kvm->srcu, idx);
 	free_page((unsigned long)vcpu->arch.pio_data);
+	if (!irqchip_in_kernel(vcpu->kvm))
+		static_key_slow_dec(&kvm_no_apic_vcpu);
 }
 
 int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
@@ -6269,15 +6288,21 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
 
 	/* Reserve bit 0 of irq_sources_bitmap for userspace irq source */
 	set_bit(KVM_USERSPACE_IRQ_SOURCE_ID, &kvm->arch.irq_sources_bitmap);
+	/* Reserve bit 1 of irq_sources_bitmap for irqfd-resampler */
+	set_bit(KVM_IRQFD_RESAMPLE_IRQ_SOURCE_ID,
+		&kvm->arch.irq_sources_bitmap);
 
 	raw_spin_lock_init(&kvm->arch.tsc_write_lock);
+	mutex_init(&kvm->arch.apic_map_lock);
 
 	return 0;
 }
 
 static void kvm_unload_vcpu_mmu(struct kvm_vcpu *vcpu)
 {
-	vcpu_load(vcpu);
+	int r;
+	r = vcpu_load(vcpu);
+	BUG_ON(r);
 	kvm_mmu_unload(vcpu);
 	vcpu_put(vcpu);
 }
@@ -6321,6 +6346,7 @@ void kvm_arch_destroy_vm(struct kvm *kvm)
 		put_page(kvm->arch.apic_access_page);
 	if (kvm->arch.ept_identity_pagetable)
 		put_page(kvm->arch.ept_identity_pagetable);
+	kfree(rcu_dereference_check(kvm->arch.apic_map, 1));
 }
 
 void kvm_arch_free_memslot(struct kvm_memory_slot *free,
@@ -6328,10 +6354,18 @@ void kvm_arch_free_memslot(struct kvm_memory_slot *free,
 {
 	int i;
 
-	for (i = 0; i < KVM_NR_PAGE_SIZES - 1; ++i) {
+	for (i = 0; i < KVM_NR_PAGE_SIZES; ++i) {
-		if (!dont || free->arch.lpage_info[i] != dont->arch.lpage_info[i]) {
+		if (!dont || free->arch.rmap[i] != dont->arch.rmap[i]) {
-			kvm_kvfree(free->arch.lpage_info[i]);
+			kvm_kvfree(free->arch.rmap[i]);
-			free->arch.lpage_info[i] = NULL;
+			free->arch.rmap[i] = NULL;
+		}
+		if (i == 0)
+			continue;
+
+		if (!dont || free->arch.lpage_info[i - 1] !=
+			     dont->arch.lpage_info[i - 1]) {
+			kvm_kvfree(free->arch.lpage_info[i - 1]);
+			free->arch.lpage_info[i - 1] = NULL;
 		}
 	}
 }
@@ -6340,23 +6374,30 @@ int kvm_arch_create_memslot(struct kvm_memory_slot *slot, unsigned long npages)
 {
 	int i;
 
-	for (i = 0; i < KVM_NR_PAGE_SIZES - 1; ++i) {
+	for (i = 0; i < KVM_NR_PAGE_SIZES; ++i) {
 		unsigned long ugfn;
 		int lpages;
-		int level = i + 2;
+		int level = i + 1;
 
 		lpages = gfn_to_index(slot->base_gfn + npages - 1,
 				      slot->base_gfn, level) + 1;
 
-		slot->arch.lpage_info[i] =
+		slot->arch.rmap[i] =
-			kvm_kvzalloc(lpages * sizeof(*slot->arch.lpage_info[i]));
+			kvm_kvzalloc(lpages * sizeof(*slot->arch.rmap[i]));
-		if (!slot->arch.lpage_info[i])
+		if (!slot->arch.rmap[i])
+			goto out_free;
+		if (i == 0)
+			continue;
+
+		slot->arch.lpage_info[i - 1] = kvm_kvzalloc(lpages *
+					sizeof(*slot->arch.lpage_info[i - 1]));
+		if (!slot->arch.lpage_info[i - 1])
 			goto out_free;
 
 		if (slot->base_gfn & (KVM_PAGES_PER_HPAGE(level) - 1))
-			slot->arch.lpage_info[i][0].write_count = 1;
+			slot->arch.lpage_info[i - 1][0].write_count = 1;
 		if ((slot->base_gfn + npages) & (KVM_PAGES_PER_HPAGE(level) - 1))
-			slot->arch.lpage_info[i][lpages - 1].write_count = 1;
+			slot->arch.lpage_info[i - 1][lpages - 1].write_count = 1;
 		ugfn = slot->userspace_addr >> PAGE_SHIFT;
 		/*
 		 * If the gfn and userspace address are not aligned wrt each
@@ -6368,16 +6409,21 @@ int kvm_arch_create_memslot(struct kvm_memory_slot *slot, unsigned long npages)
 			unsigned long j;
 
 			for (j = 0; j < lpages; ++j)
-				slot->arch.lpage_info[i][j].write_count = 1;
+				slot->arch.lpage_info[i - 1][j].write_count = 1;
 		}
 	}
 
 	return 0;
 
 out_free:
-	for (i = 0; i < KVM_NR_PAGE_SIZES - 1; ++i) {
+	for (i = 0; i < KVM_NR_PAGE_SIZES; ++i) {
-		kvm_kvfree(slot->arch.lpage_info[i]);
+		kvm_kvfree(slot->arch.rmap[i]);
-		slot->arch.lpage_info[i] = NULL;
+		slot->arch.rmap[i] = NULL;
+		if (i == 0)
+			continue;
+
+		kvm_kvfree(slot->arch.lpage_info[i - 1]);
+		slot->arch.lpage_info[i - 1] = NULL;
 	}
 	return -ENOMEM;
 }
@@ -6396,10 +6442,10 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm,
 		map_flags = MAP_SHARED | MAP_ANONYMOUS;
 
 	/*To keep backward compatibility with older userspace,
-	 *x86 needs to hanlde !user_alloc case.
+	 *x86 needs to handle !user_alloc case.
 	 */
 	if (!user_alloc) {
-		if (npages && !old.rmap) {
+		if (npages && !old.npages) {
 			unsigned long userspace_addr;
 
 			userspace_addr = vm_mmap(NULL, 0,
@@ -6427,7 +6473,7 @@ void kvm_arch_commit_memory_region(struct kvm *kvm,
 
 	int nr_mmu_pages = 0, npages = mem->memory_size >> PAGE_SHIFT;
 
-	if (!user_alloc && !old.user_alloc && old.rmap && !npages) {
+	if (!user_alloc && !old.user_alloc && old.npages && !npages) {
 		int ret;
 
 		ret = vm_munmap(old.userspace_addr,
@@ -6446,14 +6492,28 @@ void kvm_arch_commit_memory_region(struct kvm *kvm,
 		kvm_mmu_change_mmu_pages(kvm, nr_mmu_pages);
 	kvm_mmu_slot_remove_write_access(kvm, mem->slot);
 	spin_unlock(&kvm->mmu_lock);
+	/*
+	 * If memory slot is created, or moved, we need to clear all
+	 * mmio sptes.
+	 */
+	if (npages && old.base_gfn != mem->guest_phys_addr >> PAGE_SHIFT) {
+		kvm_mmu_zap_all(kvm);
+		kvm_reload_remote_mmus(kvm);
+	}
 }
 
-void kvm_arch_flush_shadow(struct kvm *kvm)
+void kvm_arch_flush_shadow_all(struct kvm *kvm)
 {
 	kvm_mmu_zap_all(kvm);
 	kvm_reload_remote_mmus(kvm);
 }
 
+void kvm_arch_flush_shadow_memslot(struct kvm *kvm,
+				   struct kvm_memory_slot *slot)
+{
+	kvm_arch_flush_shadow_all(kvm);
+}
+
 int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu)
 {
 	return (vcpu->arch.mp_state == KVM_MP_STATE_RUNNABLE &&

arch/x86/kvm/x86.h

@@ -124,4 +124,5 @@ int kvm_write_guest_virt_system(struct x86_emulate_ctxt *ctxt,
 
 extern u64 host_xcr0;
 
+extern struct static_key kvm_no_apic_vcpu;
 #endif

include/linux/kvm.h

@@ -101,9 +101,13 @@ struct kvm_userspace_memory_region {
 	__u64 userspace_addr; /* start of the userspace allocated memory */
 };
 
-/* for kvm_memory_region::flags */
+/*
-#define KVM_MEM_LOG_DIRTY_PAGES  1UL
+ * The bit 0 ~ bit 15 of kvm_memory_region::flags are visible for userspace,
-#define KVM_MEMSLOT_INVALID      (1UL << 1)
+ * other bits are reserved for kvm internal use which are defined in
+ * include/linux/kvm_host.h.
+ */
+#define KVM_MEM_LOG_DIRTY_PAGES	(1UL << 0)
+#define KVM_MEM_READONLY	(1UL << 1)
 
 /* for KVM_IRQ_LINE */
 struct kvm_irq_level {
@@ -618,6 +622,10 @@ struct kvm_ppc_smmu_info {
 #define KVM_CAP_PPC_GET_SMMU_INFO 78
 #define KVM_CAP_S390_COW 79
 #define KVM_CAP_PPC_ALLOC_HTAB 80
+#ifdef __KVM_HAVE_READONLY_MEM
+#define KVM_CAP_READONLY_MEM 81
+#endif
+#define KVM_CAP_IRQFD_RESAMPLE 82
 
 #ifdef KVM_CAP_IRQ_ROUTING
 
@@ -683,12 +691,21 @@ struct kvm_xen_hvm_config {
 #endif
 
 #define KVM_IRQFD_FLAG_DEASSIGN (1 << 0)
+/*
+ * Available with KVM_CAP_IRQFD_RESAMPLE
+ *
+ * KVM_IRQFD_FLAG_RESAMPLE indicates resamplefd is valid and specifies
+ * the irqfd to operate in resampling mode for level triggered interrupt
+ * emlation.  See Documentation/virtual/kvm/api.txt.
+ */
+#define KVM_IRQFD_FLAG_RESAMPLE (1 << 1)
 
 struct kvm_irqfd {
 	__u32 fd;
 	__u32 gsi;
 	__u32 flags;
-	__u8  pad[20];
+	__u32 resamplefd;
+	__u8  pad[16];
 };
 
 struct kvm_clock_data {

include/linux/kvm_host.h

@@ -21,6 +21,7 @@
 #include <linux/slab.h>
 #include <linux/rcupdate.h>
 #include <linux/ratelimit.h>
+#include <linux/err.h>
 #include <asm/signal.h>
 
 #include <linux/kvm.h>
@@ -34,6 +35,13 @@
 #define KVM_MMIO_SIZE 8
 #endif
 
+/*
+ * The bit 16 ~ bit 31 of kvm_memory_region::flags are internally used
+ * in kvm, other bits are visible for userspace which are defined in
+ * include/linux/kvm_h.
+ */
+#define KVM_MEMSLOT_INVALID	(1UL << 16)
+
 /*
  * If we support unaligned MMIO, at most one fragment will be split into two:
  */
@@ -48,6 +56,47 @@
 #define KVM_MAX_MMIO_FRAGMENTS \
 	(KVM_MMIO_SIZE / KVM_USER_MMIO_SIZE + KVM_EXTRA_MMIO_FRAGMENTS)
 
+/*
+ * For the normal pfn, the highest 12 bits should be zero,
+ * so we can mask these bits to indicate the error.
+ */
+#define KVM_PFN_ERR_MASK	(0xfffULL << 52)
+
+#define KVM_PFN_ERR_FAULT	(KVM_PFN_ERR_MASK)
+#define KVM_PFN_ERR_HWPOISON	(KVM_PFN_ERR_MASK + 1)
+#define KVM_PFN_ERR_BAD		(KVM_PFN_ERR_MASK + 2)
+#define KVM_PFN_ERR_RO_FAULT	(KVM_PFN_ERR_MASK + 3)
+
+static inline bool is_error_pfn(pfn_t pfn)
+{
+	return !!(pfn & KVM_PFN_ERR_MASK);
+}
+
+static inline bool is_noslot_pfn(pfn_t pfn)
+{
+	return pfn == KVM_PFN_ERR_BAD;
+}
+
+static inline bool is_invalid_pfn(pfn_t pfn)
+{
+	return !is_noslot_pfn(pfn) && is_error_pfn(pfn);
+}
+
+#define KVM_HVA_ERR_BAD		(PAGE_OFFSET)
+#define KVM_HVA_ERR_RO_BAD	(PAGE_OFFSET + PAGE_SIZE)
+
+static inline bool kvm_is_error_hva(unsigned long addr)
+{
+	return addr >= PAGE_OFFSET;
+}
+
+#define KVM_ERR_PTR_BAD_PAGE	(ERR_PTR(-ENOENT))
+
+static inline bool is_error_page(struct page *page)
+{
+	return IS_ERR(page);
+}
+
 /*
  * vcpu->requests bit members
  */
@@ -71,6 +120,7 @@
 #define KVM_REQ_PMI               17
 
 #define KVM_USERSPACE_IRQ_SOURCE_ID		0
+#define KVM_IRQFD_RESAMPLE_IRQ_SOURCE_ID	1
 
 struct kvm;
 struct kvm_vcpu;
@@ -183,6 +233,18 @@ struct kvm_vcpu {
 	} async_pf;
 #endif
 
+#ifdef CONFIG_HAVE_KVM_CPU_RELAX_INTERCEPT
+	/*
+	 * Cpu relax intercept or pause loop exit optimization
+	 * in_spin_loop: set when a vcpu does a pause loop exit
+	 *  or cpu relax intercepted.
+	 * dy_eligible: indicates whether vcpu is eligible for directed yield.
+	 */
+	struct {
+		bool in_spin_loop;
+		bool dy_eligible;
+	} spin_loop;
+#endif
 	struct kvm_vcpu_arch arch;
 };
 
@@ -201,7 +263,6 @@ struct kvm_memory_slot {
 	gfn_t base_gfn;
 	unsigned long npages;
 	unsigned long flags;
-	unsigned long *rmap;
 	unsigned long *dirty_bitmap;
 	struct kvm_arch_memory_slot arch;
 	unsigned long userspace_addr;
@@ -283,6 +344,8 @@ struct kvm {
 	struct {
 		spinlock_t        lock;
 		struct list_head  items;
+		struct list_head  resampler_list;
+		struct mutex      resampler_lock;
 	} irqfds;
 	struct list_head ioeventfds;
 #endif
@@ -348,7 +411,7 @@ static inline struct kvm_vcpu *kvm_get_vcpu(struct kvm *kvm, int i)
 int kvm_vcpu_init(struct kvm_vcpu *vcpu, struct kvm *kvm, unsigned id);
 void kvm_vcpu_uninit(struct kvm_vcpu *vcpu);
 
-void vcpu_load(struct kvm_vcpu *vcpu);
+int __must_check vcpu_load(struct kvm_vcpu *vcpu);
 void vcpu_put(struct kvm_vcpu *vcpu);
 
 int kvm_init(void *opaque, unsigned vcpu_size, unsigned vcpu_align,
@@ -378,23 +441,6 @@ id_to_memslot(struct kvm_memslots *slots, int id)
 	return slot;
 }
 
-#define HPA_MSB ((sizeof(hpa_t) * 8) - 1)
-#define HPA_ERR_MASK ((hpa_t)1 << HPA_MSB)
-static inline int is_error_hpa(hpa_t hpa) { return hpa >> HPA_MSB; }
-
-extern struct page *bad_page;
-extern struct page *fault_page;
-
-extern pfn_t bad_pfn;
-extern pfn_t fault_pfn;
-
-int is_error_page(struct page *page);
-int is_error_pfn(pfn_t pfn);
-int is_hwpoison_pfn(pfn_t pfn);
-int is_fault_pfn(pfn_t pfn);
-int is_noslot_pfn(pfn_t pfn);
-int is_invalid_pfn(pfn_t pfn);
-int kvm_is_error_hva(unsigned long addr);
 int kvm_set_memory_region(struct kvm *kvm,
 			  struct kvm_userspace_memory_region *mem,
 			  int user_alloc);
@@ -415,28 +461,33 @@ void kvm_arch_commit_memory_region(struct kvm *kvm,
 				int user_alloc);
 bool kvm_largepages_enabled(void);
 void kvm_disable_largepages(void);
-void kvm_arch_flush_shadow(struct kvm *kvm);
+/* flush all memory translations */
+void kvm_arch_flush_shadow_all(struct kvm *kvm);
+/* flush memory translations pointing to 'slot' */
+void kvm_arch_flush_shadow_memslot(struct kvm *kvm,
+				   struct kvm_memory_slot *slot);
 
 int gfn_to_page_many_atomic(struct kvm *kvm, gfn_t gfn, struct page **pages,
 			    int nr_pages);
 
 struct page *gfn_to_page(struct kvm *kvm, gfn_t gfn);
 unsigned long gfn_to_hva(struct kvm *kvm, gfn_t gfn);
+unsigned long gfn_to_hva_memslot(struct kvm_memory_slot *slot, gfn_t gfn);
 void kvm_release_page_clean(struct page *page);
 void kvm_release_page_dirty(struct page *page);
 void kvm_set_page_dirty(struct page *page);
 void kvm_set_page_accessed(struct page *page);
 
-pfn_t hva_to_pfn_atomic(struct kvm *kvm, unsigned long addr);
 pfn_t gfn_to_pfn_atomic(struct kvm *kvm, gfn_t gfn);
 pfn_t gfn_to_pfn_async(struct kvm *kvm, gfn_t gfn, bool *async,
 		       bool write_fault, bool *writable);
 pfn_t gfn_to_pfn(struct kvm *kvm, gfn_t gfn);
 pfn_t gfn_to_pfn_prot(struct kvm *kvm, gfn_t gfn, bool write_fault,
 		      bool *writable);
-pfn_t gfn_to_pfn_memslot(struct kvm *kvm,
+pfn_t gfn_to_pfn_memslot(struct kvm_memory_slot *slot, gfn_t gfn);
-			 struct kvm_memory_slot *slot, gfn_t gfn);
+pfn_t gfn_to_pfn_memslot_atomic(struct kvm_memory_slot *slot, gfn_t gfn);
-void kvm_release_pfn_dirty(pfn_t);
+
+void kvm_release_pfn_dirty(pfn_t pfn);
 void kvm_release_pfn_clean(pfn_t pfn);
 void kvm_set_pfn_dirty(pfn_t pfn);
 void kvm_set_pfn_accessed(pfn_t pfn);
@@ -494,6 +545,7 @@ int kvm_vm_ioctl_set_memory_region(struct kvm *kvm,
 				   struct
 				   kvm_userspace_memory_region *mem,
 				   int user_alloc);
+int kvm_vm_ioctl_irq_line(struct kvm *kvm, struct kvm_irq_level *irq_level);
 long kvm_arch_vm_ioctl(struct file *filp,
 		       unsigned int ioctl, unsigned long arg);
 
@@ -573,7 +625,7 @@ void kvm_arch_sync_events(struct kvm *kvm);
 int kvm_cpu_has_pending_timer(struct kvm_vcpu *vcpu);
 void kvm_vcpu_kick(struct kvm_vcpu *vcpu);
 
-int kvm_is_mmio_pfn(pfn_t pfn);
+bool kvm_is_mmio_pfn(pfn_t pfn);
 
 struct kvm_irq_ack_notifier {
 	struct hlist_node link;
@@ -728,6 +780,12 @@ __gfn_to_memslot(struct kvm_memslots *slots, gfn_t gfn)
 	return search_memslots(slots, gfn);
 }
 
+static inline unsigned long
+__gfn_to_hva_memslot(struct kvm_memory_slot *slot, gfn_t gfn)
+{
+	return slot->userspace_addr + (gfn - slot->base_gfn) * PAGE_SIZE;
+}
+
 static inline int memslot_id(struct kvm *kvm, gfn_t gfn)
 {
 	return gfn_to_memslot(kvm, gfn)->id;
@@ -740,10 +798,12 @@ static inline gfn_t gfn_to_index(gfn_t gfn, gfn_t base_gfn, int level)
 		(base_gfn >> KVM_HPAGE_GFN_SHIFT(level));
 }
 
-static inline unsigned long gfn_to_hva_memslot(struct kvm_memory_slot *slot,
+static inline gfn_t
-					       gfn_t gfn)
+hva_to_gfn_memslot(unsigned long hva, struct kvm_memory_slot *slot)
 {
-	return slot->userspace_addr + (gfn - slot->base_gfn) * PAGE_SIZE;
+	gfn_t gfn_offset = (hva - slot->userspace_addr) >> PAGE_SHIFT;
+
+	return slot->base_gfn + gfn_offset;
 }
 
 static inline gpa_t gfn_to_gpa(gfn_t gfn)
@@ -899,5 +959,32 @@ static inline bool kvm_check_request(int req, struct kvm_vcpu *vcpu)
 	}
 }
 
+#ifdef CONFIG_HAVE_KVM_CPU_RELAX_INTERCEPT
+
+static inline void kvm_vcpu_set_in_spin_loop(struct kvm_vcpu *vcpu, bool val)
+{
+	vcpu->spin_loop.in_spin_loop = val;
+}
+static inline void kvm_vcpu_set_dy_eligible(struct kvm_vcpu *vcpu, bool val)
+{
+	vcpu->spin_loop.dy_eligible = val;
+}
+
+#else /* !CONFIG_HAVE_KVM_CPU_RELAX_INTERCEPT */
+
+static inline void kvm_vcpu_set_in_spin_loop(struct kvm_vcpu *vcpu, bool val)
+{
+}
+
+static inline void kvm_vcpu_set_dy_eligible(struct kvm_vcpu *vcpu, bool val)
+{
+}
+
+static inline bool kvm_vcpu_eligible_for_directed_yield(struct kvm_vcpu *vcpu)
+{
+	return true;
+}
+
+#endif /* CONFIG_HAVE_KVM_CPU_RELAX_INTERCEPT */
 #endif
 

kernel/jump_label.c

@@ -118,6 +118,7 @@ void jump_label_rate_limit(struct static_key_deferred *key,
 	key->timeout = rl;
 	INIT_DELAYED_WORK(&key->work, jump_label_update_timeout);
 }
+EXPORT_SYMBOL_GPL(jump_label_rate_limit);
 
 static int addr_conflict(struct jump_entry *entry, void *start, void *end)
 {

virt/kvm/Kconfig

@@ -21,3 +21,6 @@ config KVM_ASYNC_PF
 
 config HAVE_KVM_MSI
        bool
+
+config HAVE_KVM_CPU_RELAX_INTERCEPT
+       bool

virt/kvm/async_pf.c

@@ -111,8 +111,8 @@ void kvm_clear_async_pf_completion_queue(struct kvm_vcpu *vcpu)
 			list_entry(vcpu->async_pf.done.next,
 				   typeof(*work), link);
 		list_del(&work->link);
-		if (work->page)
+		if (!is_error_page(work->page))
-			put_page(work->page);
+			kvm_release_page_clean(work->page);
 		kmem_cache_free(async_pf_cache, work);
 	}
 	spin_unlock(&vcpu->async_pf.lock);
@@ -138,8 +138,8 @@ void kvm_check_async_pf_completion(struct kvm_vcpu *vcpu)
 
 		list_del(&work->queue);
 		vcpu->async_pf.queued--;
-		if (work->page)
+		if (!is_error_page(work->page))
-			put_page(work->page);
+			kvm_release_page_clean(work->page);
 		kmem_cache_free(async_pf_cache, work);
 	}
 }
@@ -203,8 +203,7 @@ int kvm_async_pf_wakeup_all(struct kvm_vcpu *vcpu)
 	if (!work)
 		return -ENOMEM;
 
-	work->page = bad_page;
+	work->page = KVM_ERR_PTR_BAD_PAGE;
-	get_page(bad_page);
 	INIT_LIST_HEAD(&work->queue); /* for list_del to work */
 
 	spin_lock(&vcpu->async_pf.lock);

virt/kvm/eventfd.c

@@ -43,6 +43,31 @@
  * --------------------------------------------------------------------
  */
 
+/*
+ * Resampling irqfds are a special variety of irqfds used to emulate
+ * level triggered interrupts.  The interrupt is asserted on eventfd
+ * trigger.  On acknowledgement through the irq ack notifier, the
+ * interrupt is de-asserted and userspace is notified through the
+ * resamplefd.  All resamplers on the same gsi are de-asserted
+ * together, so we don't need to track the state of each individual
+ * user.  We can also therefore share the same irq source ID.
+ */
+struct _irqfd_resampler {
+	struct kvm *kvm;
+	/*
+	 * List of resampling struct _irqfd objects sharing this gsi.
+	 * RCU list modified under kvm->irqfds.resampler_lock
+	 */
+	struct list_head list;
+	struct kvm_irq_ack_notifier notifier;
+	/*
+	 * Entry in list of kvm->irqfd.resampler_list.  Use for sharing
+	 * resamplers among irqfds on the same gsi.
+	 * Accessed and modified under kvm->irqfds.resampler_lock
+	 */
+	struct list_head link;
+};
+
 struct _irqfd {
 	/* Used for MSI fast-path */
 	struct kvm *kvm;
@@ -52,6 +77,12 @@ struct _irqfd {
 	/* Used for level IRQ fast-path */
 	int gsi;
 	struct work_struct inject;
+	/* The resampler used by this irqfd (resampler-only) */
+	struct _irqfd_resampler *resampler;
+	/* Eventfd notified on resample (resampler-only) */
+	struct eventfd_ctx *resamplefd;
+	/* Entry in list of irqfds for a resampler (resampler-only) */
+	struct list_head resampler_link;
 	/* Used for setup/shutdown */
 	struct eventfd_ctx *eventfd;
 	struct list_head list;
@@ -67,8 +98,58 @@ irqfd_inject(struct work_struct *work)
 	struct _irqfd *irqfd = container_of(work, struct _irqfd, inject);
 	struct kvm *kvm = irqfd->kvm;
 
+	if (!irqfd->resampler) {
 		kvm_set_irq(kvm, KVM_USERSPACE_IRQ_SOURCE_ID, irqfd->gsi, 1);
 		kvm_set_irq(kvm, KVM_USERSPACE_IRQ_SOURCE_ID, irqfd->gsi, 0);
+	} else
+		kvm_set_irq(kvm, KVM_IRQFD_RESAMPLE_IRQ_SOURCE_ID,
+			    irqfd->gsi, 1);
+}
+
+/*
+ * Since resampler irqfds share an IRQ source ID, we de-assert once
+ * then notify all of the resampler irqfds using this GSI.  We can't
+ * do multiple de-asserts or we risk racing with incoming re-asserts.
+ */
+static void
+irqfd_resampler_ack(struct kvm_irq_ack_notifier *kian)
+{
+	struct _irqfd_resampler *resampler;
+	struct _irqfd *irqfd;
+
+	resampler = container_of(kian, struct _irqfd_resampler, notifier);
+
+	kvm_set_irq(resampler->kvm, KVM_IRQFD_RESAMPLE_IRQ_SOURCE_ID,
+		    resampler->notifier.gsi, 0);
+
+	rcu_read_lock();
+
+	list_for_each_entry_rcu(irqfd, &resampler->list, resampler_link)
+		eventfd_signal(irqfd->resamplefd, 1);
+
+	rcu_read_unlock();
+}
+
+static void
+irqfd_resampler_shutdown(struct _irqfd *irqfd)
+{
+	struct _irqfd_resampler *resampler = irqfd->resampler;
+	struct kvm *kvm = resampler->kvm;
+
+	mutex_lock(&kvm->irqfds.resampler_lock);
+
+	list_del_rcu(&irqfd->resampler_link);
+	synchronize_rcu();
+
+	if (list_empty(&resampler->list)) {
+		list_del(&resampler->link);
+		kvm_unregister_irq_ack_notifier(kvm, &resampler->notifier);
+		kvm_set_irq(kvm, KVM_IRQFD_RESAMPLE_IRQ_SOURCE_ID,
+			    resampler->notifier.gsi, 0);
+		kfree(resampler);
+	}
+
+	mutex_unlock(&kvm->irqfds.resampler_lock);
 }
 
 /*
@@ -92,6 +173,11 @@ irqfd_shutdown(struct work_struct *work)
 	 */
 	flush_work(&irqfd->inject);
 
+	if (irqfd->resampler) {
+		irqfd_resampler_shutdown(irqfd);
+		eventfd_ctx_put(irqfd->resamplefd);
+	}
+
 	/*
 	 * It is now safe to release the object's resources
 	 */
@@ -203,7 +289,7 @@ kvm_irqfd_assign(struct kvm *kvm, struct kvm_irqfd *args)
 	struct kvm_irq_routing_table *irq_rt;
 	struct _irqfd *irqfd, *tmp;
 	struct file *file = NULL;
-	struct eventfd_ctx *eventfd = NULL;
+	struct eventfd_ctx *eventfd = NULL, *resamplefd = NULL;
 	int ret;
 	unsigned int events;
 
@@ -231,6 +317,54 @@ kvm_irqfd_assign(struct kvm *kvm, struct kvm_irqfd *args)
 
 	irqfd->eventfd = eventfd;
 
+	if (args->flags & KVM_IRQFD_FLAG_RESAMPLE) {
+		struct _irqfd_resampler *resampler;
+
+		resamplefd = eventfd_ctx_fdget(args->resamplefd);
+		if (IS_ERR(resamplefd)) {
+			ret = PTR_ERR(resamplefd);
+			goto fail;
+		}
+
+		irqfd->resamplefd = resamplefd;
+		INIT_LIST_HEAD(&irqfd->resampler_link);
+
+		mutex_lock(&kvm->irqfds.resampler_lock);
+
+		list_for_each_entry(resampler,
+				    &kvm->irqfds.resampler_list, list) {
+			if (resampler->notifier.gsi == irqfd->gsi) {
+				irqfd->resampler = resampler;
+				break;
+			}
+		}
+
+		if (!irqfd->resampler) {
+			resampler = kzalloc(sizeof(*resampler), GFP_KERNEL);
+			if (!resampler) {
+				ret = -ENOMEM;
+				mutex_unlock(&kvm->irqfds.resampler_lock);
+				goto fail;
+			}
+
+			resampler->kvm = kvm;
+			INIT_LIST_HEAD(&resampler->list);
+			resampler->notifier.gsi = irqfd->gsi;
+			resampler->notifier.irq_acked = irqfd_resampler_ack;
+			INIT_LIST_HEAD(&resampler->link);
+
+			list_add(&resampler->link, &kvm->irqfds.resampler_list);
+			kvm_register_irq_ack_notifier(kvm,
+						      &resampler->notifier);
+			irqfd->resampler = resampler;
+		}
+
+		list_add_rcu(&irqfd->resampler_link, &irqfd->resampler->list);
+		synchronize_rcu();
+
+		mutex_unlock(&kvm->irqfds.resampler_lock);
+	}
+
 	/*
 	 * Install our own custom wake-up handling so we are notified via
 	 * a callback whenever someone signals the underlying eventfd
@@ -276,6 +410,12 @@ kvm_irqfd_assign(struct kvm *kvm, struct kvm_irqfd *args)
 	return 0;
 
 fail:
+	if (irqfd->resampler)
+		irqfd_resampler_shutdown(irqfd);
+
+	if (resamplefd && !IS_ERR(resamplefd))
+		eventfd_ctx_put(resamplefd);
+
 	if (eventfd && !IS_ERR(eventfd))
 		eventfd_ctx_put(eventfd);
 
@@ -291,6 +431,8 @@ kvm_eventfd_init(struct kvm *kvm)
 {
 	spin_lock_init(&kvm->irqfds.lock);
 	INIT_LIST_HEAD(&kvm->irqfds.items);
+	INIT_LIST_HEAD(&kvm->irqfds.resampler_list);
+	mutex_init(&kvm->irqfds.resampler_lock);
 	INIT_LIST_HEAD(&kvm->ioeventfds);
 }
 
@@ -340,7 +482,7 @@ kvm_irqfd_deassign(struct kvm *kvm, struct kvm_irqfd *args)
 int
 kvm_irqfd(struct kvm *kvm, struct kvm_irqfd *args)
 {
-	if (args->flags & ~KVM_IRQFD_FLAG_DEASSIGN)
+	if (args->flags & ~(KVM_IRQFD_FLAG_DEASSIGN | KVM_IRQFD_FLAG_RESAMPLE))
 		return -EINVAL;
 
 	if (args->flags & KVM_IRQFD_FLAG_DEASSIGN)

virt/kvm/ioapic.c

@@ -197,18 +197,20 @@ int kvm_ioapic_set_irq(struct kvm_ioapic *ioapic, int irq, int irq_source_id,
 	u32 old_irr;
 	u32 mask = 1 << irq;
 	union kvm_ioapic_redirect_entry entry;
-	int ret = 1;
+	int ret, irq_level;
+
+	BUG_ON(irq < 0 || irq >= IOAPIC_NUM_PINS);
 
 	spin_lock(&ioapic->lock);
 	old_irr = ioapic->irr;
-	if (irq >= 0 && irq < IOAPIC_NUM_PINS) {
+	irq_level = __kvm_irq_line_state(&ioapic->irq_states[irq],
-		int irq_level = __kvm_irq_line_state(&ioapic->irq_states[irq],
 					 irq_source_id, level);
 	entry = ioapic->redirtbl[irq];
 	irq_level ^= entry.fields.polarity;
-		if (!irq_level)
+	if (!irq_level) {
 		ioapic->irr &= ~mask;
-		else {
+		ret = 1;
+	} else {
 		int edge = (entry.fields.trig_mode == IOAPIC_EDGE_TRIG);
 		ioapic->irr |= mask;
 		if ((edge && old_irr != ioapic->irr) ||
@@ -218,7 +220,6 @@ int kvm_ioapic_set_irq(struct kvm_ioapic *ioapic, int irq, int irq_source_id,
 			ret = 0; /* report coalesced interrupt */
 	}
 	trace_kvm_ioapic_set_irq(entry.bits, irq, ret == 0);
-	}
 	spin_unlock(&ioapic->lock);
 
 	return ret;

virt/kvm/iommu.c

@@ -42,13 +42,13 @@ static int kvm_iommu_unmap_memslots(struct kvm *kvm);
 static void kvm_iommu_put_pages(struct kvm *kvm,
 				gfn_t base_gfn, unsigned long npages);
 
-static pfn_t kvm_pin_pages(struct kvm *kvm, struct kvm_memory_slot *slot,
+static pfn_t kvm_pin_pages(struct kvm_memory_slot *slot, gfn_t gfn,
-			   gfn_t gfn, unsigned long size)
+			   unsigned long size)
 {
 	gfn_t end_gfn;
 	pfn_t pfn;
 
-	pfn     = gfn_to_pfn_memslot(kvm, slot, gfn);
+	pfn     = gfn_to_pfn_memslot(slot, gfn);
 	end_gfn = gfn + (size >> PAGE_SHIFT);
 	gfn    += 1;
 
@@ -56,7 +56,7 @@ static pfn_t kvm_pin_pages(struct kvm *kvm, struct kvm_memory_slot *slot,
 		return pfn;
 
 	while (gfn < end_gfn)
-		gfn_to_pfn_memslot(kvm, slot, gfn++);
+		gfn_to_pfn_memslot(slot, gfn++);
 
 	return pfn;
 }
@@ -105,7 +105,7 @@ int kvm_iommu_map_pages(struct kvm *kvm, struct kvm_memory_slot *slot)
 		 * Pin all pages we are about to map in memory. This is
 		 * important because we unmap and unpin in 4kb steps later.
 		 */
-		pfn = kvm_pin_pages(kvm, slot, gfn, page_size);
+		pfn = kvm_pin_pages(slot, gfn, page_size);
 		if (is_error_pfn(pfn)) {
 			gfn += 1;
 			continue;
@@ -300,6 +300,12 @@ static void kvm_iommu_put_pages(struct kvm *kvm,
 
 		/* Get physical address */
 		phys = iommu_iova_to_phys(domain, gfn_to_gpa(gfn));
+
+		if (!phys) {
+			gfn++;
+			continue;
+		}
+
 		pfn  = phys >> PAGE_SHIFT;
 
 		/* Unmap address from IO address space */

virt/kvm/irq_comm.c

@@ -68,8 +68,13 @@ int kvm_irq_delivery_to_apic(struct kvm *kvm, struct kvm_lapic *src,
 	struct kvm_vcpu *vcpu, *lowest = NULL;
 
 	if (irq->dest_mode == 0 && irq->dest_id == 0xff &&
-			kvm_is_dm_lowest_prio(irq))
+			kvm_is_dm_lowest_prio(irq)) {
 		printk(KERN_INFO "kvm: apic: phys broadcast and lowest prio\n");
+		irq->delivery_mode = APIC_DM_FIXED;
+	}
+
+	if (kvm_irq_delivery_to_apic_fast(kvm, src, irq, &r))
+		return r;
 
 	kvm_for_each_vcpu(i, vcpu, kvm) {
 		if (!kvm_apic_present(vcpu))
@@ -223,6 +228,9 @@ int kvm_request_irq_source_id(struct kvm *kvm)
 	}
 
 	ASSERT(irq_source_id != KVM_USERSPACE_IRQ_SOURCE_ID);
+#ifdef CONFIG_X86
+	ASSERT(irq_source_id != KVM_IRQFD_RESAMPLE_IRQ_SOURCE_ID);
+#endif
 	set_bit(irq_source_id, bitmap);
 unlock:
 	mutex_unlock(&kvm->irq_lock);
@@ -233,6 +241,9 @@ unlock:
 void kvm_free_irq_source_id(struct kvm *kvm, int irq_source_id)
 {
 	ASSERT(irq_source_id != KVM_USERSPACE_IRQ_SOURCE_ID);
+#ifdef CONFIG_X86
+	ASSERT(irq_source_id != KVM_IRQFD_RESAMPLE_IRQ_SOURCE_ID);
+#endif
 
 	mutex_lock(&kvm->irq_lock);
 	if (irq_source_id < 0 ||
@@ -321,11 +332,11 @@ static int setup_routing_entry(struct kvm_irq_routing_table *rt,
 		switch (ue->u.irqchip.irqchip) {
 		case KVM_IRQCHIP_PIC_MASTER:
 			e->set = kvm_set_pic_irq;
-			max_pin = 16;
+			max_pin = PIC_NUM_PINS;
 			break;
 		case KVM_IRQCHIP_PIC_SLAVE:
 			e->set = kvm_set_pic_irq;
-			max_pin = 16;
+			max_pin = PIC_NUM_PINS;
 			delta = 8;
 			break;
 		case KVM_IRQCHIP_IOAPIC:

virt/kvm/kvm_main.c

@@ -100,13 +100,7 @@ EXPORT_SYMBOL_GPL(kvm_rebooting);
 
 static bool largepages_enabled = true;
 
-static struct page *hwpoison_page;
+bool kvm_is_mmio_pfn(pfn_t pfn)
-static pfn_t hwpoison_pfn;
-
-struct page *fault_page;
-pfn_t fault_pfn;
-
-inline int kvm_is_mmio_pfn(pfn_t pfn)
 {
 	if (pfn_valid(pfn)) {
 		int reserved;
@@ -137,11 +131,12 @@ inline int kvm_is_mmio_pfn(pfn_t pfn)
 /*
  * Switches to specified vcpu, until a matching vcpu_put()
  */
-void vcpu_load(struct kvm_vcpu *vcpu)
+int vcpu_load(struct kvm_vcpu *vcpu)
 {
 	int cpu;
 
-	mutex_lock(&vcpu->mutex);
+	if (mutex_lock_killable(&vcpu->mutex))
+		return -EINTR;
 	if (unlikely(vcpu->pid != current->pids[PIDTYPE_PID].pid)) {
 		/* The thread running this VCPU changed. */
 		struct pid *oldpid = vcpu->pid;
@@ -154,6 +149,7 @@ void vcpu_load(struct kvm_vcpu *vcpu)
 	preempt_notifier_register(&vcpu->preempt_notifier);
 	kvm_arch_vcpu_load(vcpu, cpu);
 	put_cpu();
+	return 0;
 }
 
 void vcpu_put(struct kvm_vcpu *vcpu)
@@ -236,6 +232,9 @@ int kvm_vcpu_init(struct kvm_vcpu *vcpu, struct kvm *kvm, unsigned id)
 	}
 	vcpu->run = page_address(page);
 
+	kvm_vcpu_set_in_spin_loop(vcpu, false);
+	kvm_vcpu_set_dy_eligible(vcpu, false);
+
 	r = kvm_arch_vcpu_init(vcpu);
 	if (r < 0)
 		goto fail_free_run;
@@ -332,8 +331,7 @@ static void kvm_mmu_notifier_invalidate_range_start(struct mmu_notifier *mn,
 	 * count is also read inside the mmu_lock critical section.
 	 */
 	kvm->mmu_notifier_count++;
-	for (; start < end; start += PAGE_SIZE)
+	need_tlb_flush = kvm_unmap_hva_range(kvm, start, end);
-		need_tlb_flush |= kvm_unmap_hva(kvm, start);
 	need_tlb_flush |= kvm->tlbs_dirty;
 	/* we've to flush the tlb before the pages can be freed */
 	if (need_tlb_flush)
@@ -412,7 +410,7 @@ static void kvm_mmu_notifier_release(struct mmu_notifier *mn,
 	int idx;
 
 	idx = srcu_read_lock(&kvm->srcu);
-	kvm_arch_flush_shadow(kvm);
+	kvm_arch_flush_shadow_all(kvm);
 	srcu_read_unlock(&kvm->srcu, idx);
 }
 
@@ -551,16 +549,12 @@ static void kvm_destroy_dirty_bitmap(struct kvm_memory_slot *memslot)
 static void kvm_free_physmem_slot(struct kvm_memory_slot *free,
 				  struct kvm_memory_slot *dont)
 {
-	if (!dont || free->rmap != dont->rmap)
-		vfree(free->rmap);
-
 	if (!dont || free->dirty_bitmap != dont->dirty_bitmap)
 		kvm_destroy_dirty_bitmap(free);
 
 	kvm_arch_free_memslot(free, dont);
 
 	free->npages = 0;
-	free->rmap = NULL;
 }
 
 void kvm_free_physmem(struct kvm *kvm)
@@ -590,7 +584,7 @@ static void kvm_destroy_vm(struct kvm *kvm)
 #if defined(CONFIG_MMU_NOTIFIER) && defined(KVM_ARCH_WANT_MMU_NOTIFIER)
 	mmu_notifier_unregister(&kvm->mmu_notifier, kvm->mm);
 #else
-	kvm_arch_flush_shadow(kvm);
+	kvm_arch_flush_shadow_all(kvm);
 #endif
 	kvm_arch_destroy_vm(kvm);
 	kvm_free_physmem(kvm);
@@ -686,6 +680,20 @@ void update_memslots(struct kvm_memslots *slots, struct kvm_memory_slot *new)
 	slots->generation++;
 }
 
+static int check_memory_region_flags(struct kvm_userspace_memory_region *mem)
+{
+	u32 valid_flags = KVM_MEM_LOG_DIRTY_PAGES;
+
+#ifdef KVM_CAP_READONLY_MEM
+	valid_flags |= KVM_MEM_READONLY;
+#endif
+
+	if (mem->flags & ~valid_flags)
+		return -EINVAL;
+
+	return 0;
+}
+
 /*
  * Allocate some memory and give it an address in the guest physical address
  * space.
@@ -706,6 +714,10 @@ int __kvm_set_memory_region(struct kvm *kvm,
 	struct kvm_memory_slot old, new;
 	struct kvm_memslots *slots, *old_memslots;
 
+	r = check_memory_region_flags(mem);
+	if (r)
+		goto out;
+
 	r = -EINVAL;
 	/* General sanity checks */
 	if (mem->memory_size & (PAGE_SIZE - 1))
@@ -769,11 +781,7 @@ int __kvm_set_memory_region(struct kvm *kvm,
 	if (npages && !old.npages) {
 		new.user_alloc = user_alloc;
 		new.userspace_addr = mem->userspace_addr;
-#ifndef CONFIG_S390
+
-		new.rmap = vzalloc(npages * sizeof(*new.rmap));
-		if (!new.rmap)
-			goto out_free;
-#endif /* not defined CONFIG_S390 */
 		if (kvm_arch_create_memslot(&new, npages))
 			goto out_free;
 	}
@@ -785,7 +793,7 @@ int __kvm_set_memory_region(struct kvm *kvm,
 		/* destroy any largepage mappings for dirty tracking */
 	}
 
-	if (!npages) {
+	if (!npages || base_gfn != old.base_gfn) {
 		struct kvm_memory_slot *slot;
 
 		r = -ENOMEM;
@@ -801,14 +809,14 @@ int __kvm_set_memory_region(struct kvm *kvm,
 		old_memslots = kvm->memslots;
 		rcu_assign_pointer(kvm->memslots, slots);
 		synchronize_srcu_expedited(&kvm->srcu);
-		/* From this point no new shadow pages pointing to a deleted
+		/* From this point no new shadow pages pointing to a deleted,
-		 * memslot will be created.
+		 * or moved, memslot will be created.
 		 *
 		 * validation of sp->gfn happens in:
 		 * 	- gfn_to_hva (kvm_read_guest, gfn_to_pfn)
 		 * 	- kvm_is_visible_gfn (mmu_check_roots)
 		 */
-		kvm_arch_flush_shadow(kvm);
+		kvm_arch_flush_shadow_memslot(kvm, slot);
 		kfree(old_memslots);
 	}
 
@@ -832,7 +840,6 @@ int __kvm_set_memory_region(struct kvm *kvm,
 
 	/* actual memory is freed via old in kvm_free_physmem_slot below */
 	if (!npages) {
-		new.rmap = NULL;
 		new.dirty_bitmap = NULL;
 		memset(&new.arch, 0, sizeof(new.arch));
 	}
@@ -844,13 +851,6 @@ int __kvm_set_memory_region(struct kvm *kvm,
 
 	kvm_arch_commit_memory_region(kvm, mem, old, user_alloc);
 
-	/*
-	 * If the new memory slot is created, we need to clear all
-	 * mmio sptes.
-	 */
-	if (npages && old.base_gfn != mem->guest_phys_addr >> PAGE_SHIFT)
-		kvm_arch_flush_shadow(kvm);
-
 	kvm_free_physmem_slot(&old, &new);
 	kfree(old_memslots);
 
@@ -932,53 +932,6 @@ void kvm_disable_largepages(void)
 }
 EXPORT_SYMBOL_GPL(kvm_disable_largepages);
 
-int is_error_page(struct page *page)
-{
-	return page == bad_page || page == hwpoison_page || page == fault_page;
-}
-EXPORT_SYMBOL_GPL(is_error_page);
-
-int is_error_pfn(pfn_t pfn)
-{
-	return pfn == bad_pfn || pfn == hwpoison_pfn || pfn == fault_pfn;
-}
-EXPORT_SYMBOL_GPL(is_error_pfn);
-
-int is_hwpoison_pfn(pfn_t pfn)
-{
-	return pfn == hwpoison_pfn;
-}
-EXPORT_SYMBOL_GPL(is_hwpoison_pfn);
-
-int is_fault_pfn(pfn_t pfn)
-{
-	return pfn == fault_pfn;
-}
-EXPORT_SYMBOL_GPL(is_fault_pfn);
-
-int is_noslot_pfn(pfn_t pfn)
-{
-	return pfn == bad_pfn;
-}
-EXPORT_SYMBOL_GPL(is_noslot_pfn);
-
-int is_invalid_pfn(pfn_t pfn)
-{
-	return pfn == hwpoison_pfn || pfn == fault_pfn;
-}
-EXPORT_SYMBOL_GPL(is_invalid_pfn);
-
-static inline unsigned long bad_hva(void)
-{
-	return PAGE_OFFSET;
-}
-
-int kvm_is_error_hva(unsigned long addr)
-{
-	return addr == bad_hva();
-}
-EXPORT_SYMBOL_GPL(kvm_is_error_hva);
-
 struct kvm_memory_slot *gfn_to_memslot(struct kvm *kvm, gfn_t gfn)
 {
 	return __gfn_to_memslot(kvm_memslots(kvm), gfn);
@@ -1021,28 +974,62 @@ out:
 	return size;
 }
 
-static unsigned long gfn_to_hva_many(struct kvm_memory_slot *slot, gfn_t gfn,
+static bool memslot_is_readonly(struct kvm_memory_slot *slot)
-				     gfn_t *nr_pages)
+{
+	return slot->flags & KVM_MEM_READONLY;
+}
+
+static unsigned long __gfn_to_hva_many(struct kvm_memory_slot *slot, gfn_t gfn,
+				       gfn_t *nr_pages, bool write)
 {
 	if (!slot || slot->flags & KVM_MEMSLOT_INVALID)
-		return bad_hva();
+		return KVM_HVA_ERR_BAD;
+
+	if (memslot_is_readonly(slot) && write)
+		return KVM_HVA_ERR_RO_BAD;
 
 	if (nr_pages)
 		*nr_pages = slot->npages - (gfn - slot->base_gfn);
 
-	return gfn_to_hva_memslot(slot, gfn);
+	return __gfn_to_hva_memslot(slot, gfn);
 }
 
+static unsigned long gfn_to_hva_many(struct kvm_memory_slot *slot, gfn_t gfn,
+				     gfn_t *nr_pages)
+{
+	return __gfn_to_hva_many(slot, gfn, nr_pages, true);
+}
+
+unsigned long gfn_to_hva_memslot(struct kvm_memory_slot *slot,
+				 gfn_t gfn)
+{
+	return gfn_to_hva_many(slot, gfn, NULL);
+}
+EXPORT_SYMBOL_GPL(gfn_to_hva_memslot);
+
 unsigned long gfn_to_hva(struct kvm *kvm, gfn_t gfn)
 {
 	return gfn_to_hva_many(gfn_to_memslot(kvm, gfn), gfn, NULL);
 }
 EXPORT_SYMBOL_GPL(gfn_to_hva);
 
-static pfn_t get_fault_pfn(void)
+/*
+ * The hva returned by this function is only allowed to be read.
+ * It should pair with kvm_read_hva() or kvm_read_hva_atomic().
+ */
+static unsigned long gfn_to_hva_read(struct kvm *kvm, gfn_t gfn)
 {
-	get_page(fault_page);
+	return __gfn_to_hva_many(gfn_to_memslot(kvm, gfn), gfn, NULL, false);
-	return fault_pfn;
+}
+
+static int kvm_read_hva(void *data, void __user *hva, int len)
+{
+	return __copy_from_user(data, hva, len);
+}
+
+static int kvm_read_hva_atomic(void *data, void __user *hva, int len)
+{
+	return __copy_from_user_inatomic(data, hva, len);
 }
 
 int get_user_page_nowait(struct task_struct *tsk, struct mm_struct *mm,
@@ -1065,25 +1052,49 @@ static inline int check_user_page_hwpoison(unsigned long addr)
 	return rc == -EHWPOISON;
 }
 
-static pfn_t hva_to_pfn(struct kvm *kvm, unsigned long addr, bool atomic,
+/*
-			bool *async, bool write_fault, bool *writable)
+ * The atomic path to get the writable pfn which will be stored in @pfn,
+ * true indicates success, otherwise false is returned.
+ */
+static bool hva_to_pfn_fast(unsigned long addr, bool atomic, bool *async,
+			    bool write_fault, bool *writable, pfn_t *pfn)
 {
 	struct page *page[1];
-	int npages = 0;
+	int npages;
-	pfn_t pfn;
 
-	/* we can do it either atomically or asynchronously, not both */
+	if (!(async || atomic))
-	BUG_ON(atomic && async);
+		return false;
 
-	BUG_ON(!write_fault && !writable);
+	/*
+	 * Fast pin a writable pfn only if it is a write fault request
+	 * or the caller allows to map a writable pfn for a read fault
+	 * request.
+	 */
+	if (!(write_fault || writable))
+		return false;
+
+	npages = __get_user_pages_fast(addr, 1, 1, page);
+	if (npages == 1) {
+		*pfn = page_to_pfn(page[0]);
 
 		if (writable)
 			*writable = true;
+		return true;
+	}
 
-	if (atomic || async)
+	return false;
-		npages = __get_user_pages_fast(addr, 1, 1, page);
+}
+
+/*
+ * The slow path to get the pfn of the specified host virtual address,
+ * 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, pfn_t *pfn)
+{
+	struct page *page[1];
+	int npages = 0;
 
-	if (unlikely(npages != 1) && !atomic) {
 	might_sleep();
 
 	if (writable)
@@ -1097,9 +1108,11 @@ static pfn_t hva_to_pfn(struct kvm *kvm, unsigned long addr, bool atomic,
 	} else
 		npages = get_user_pages_fast(addr, 1, write_fault,
 					     page);
+	if (npages != 1)
+		return npages;
 
 	/* map read fault as writable if possible */
-		if (unlikely(!write_fault) && npages == 1) {
+	if (unlikely(!write_fault) && writable) {
 		struct page *wpage[1];
 
 		npages = __get_user_pages_fast(addr, 1, 1, wpage);
@@ -1108,65 +1121,117 @@ static pfn_t hva_to_pfn(struct kvm *kvm, unsigned long addr, bool atomic,
 			put_page(page[0]);
 			page[0] = wpage[0];
 		}
+
 		npages = 1;
 	}
-	}
+	*pfn = page_to_pfn(page[0]);
+	return npages;
+}
 
-	if (unlikely(npages != 1)) {
+static bool vma_is_valid(struct vm_area_struct *vma, bool write_fault)
+{
+	if (unlikely(!(vma->vm_flags & VM_READ)))
+		return false;
+
+	if (write_fault && (unlikely(!(vma->vm_flags & VM_WRITE))))
+		return false;
+
+	return true;
+}
+
+/*
+ * 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
+ * @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
+ * @writable: whether it allows to map a writable host page for !@write_fault
+ *
+ * The function will map a writable host page for these two cases:
+ * 1): @write_fault = true
+ * 2): @write_fault = false && @writable, @writable will tell the caller
+ *     whether the mapping is writable.
+ */
+static pfn_t hva_to_pfn(unsigned long addr, bool atomic, bool *async,
+			bool write_fault, bool *writable)
+{
 	struct vm_area_struct *vma;
+	pfn_t pfn = 0;
+	int npages;
+
+	/* we can do it either atomically or asynchronously, not both */
+	BUG_ON(atomic && async);
+
+	if (hva_to_pfn_fast(addr, atomic, async, write_fault, writable, &pfn))
+		return pfn;
 
 	if (atomic)
-			return get_fault_pfn();
+		return KVM_PFN_ERR_FAULT;
+
+	npages = hva_to_pfn_slow(addr, async, write_fault, writable, &pfn);
+	if (npages == 1)
+		return pfn;
 
 	down_read(&current->mm->mmap_sem);
 	if (npages == -EHWPOISON ||
 	      (!async && check_user_page_hwpoison(addr))) {
-			up_read(&current->mm->mmap_sem);
+		pfn = KVM_PFN_ERR_HWPOISON;
-			get_page(hwpoison_page);
+		goto exit;
-			return page_to_pfn(hwpoison_page);
 	}
 
-		vma = find_vma_intersection(current->mm, addr, addr+1);
+	vma = find_vma_intersection(current->mm, addr, addr + 1);
 
 	if (vma == NULL)
-			pfn = get_fault_pfn();
+		pfn = KVM_PFN_ERR_FAULT;
 	else if ((vma->vm_flags & VM_PFNMAP)) {
 		pfn = ((addr - vma->vm_start) >> PAGE_SHIFT) +
 			vma->vm_pgoff;
 		BUG_ON(!kvm_is_mmio_pfn(pfn));
 	} else {
-			if (async && (vma->vm_flags & VM_WRITE))
+		if (async && vma_is_valid(vma, write_fault))
 			*async = true;
-			pfn = get_fault_pfn();
+		pfn = KVM_PFN_ERR_FAULT;
 	}
+exit:
 	up_read(&current->mm->mmap_sem);
-	} else
-		pfn = page_to_pfn(page[0]);
-
 	return pfn;
 }
 
-pfn_t hva_to_pfn_atomic(struct kvm *kvm, unsigned long addr)
+static pfn_t
+__gfn_to_pfn_memslot(struct kvm_memory_slot *slot, gfn_t gfn, bool atomic,
+		     bool *async, bool write_fault, bool *writable)
 {
-	return hva_to_pfn(kvm, addr, true, NULL, true, NULL);
+	unsigned long addr = __gfn_to_hva_many(slot, gfn, NULL, write_fault);
+
+	if (addr == KVM_HVA_ERR_RO_BAD)
+		return KVM_PFN_ERR_RO_FAULT;
+
+	if (kvm_is_error_hva(addr))
+		return KVM_PFN_ERR_BAD;
+
+	/* Do not map writable pfn in the readonly memslot. */
+	if (writable && memslot_is_readonly(slot)) {
+		*writable = false;
+		writable = NULL;
+	}
+
+	return hva_to_pfn(addr, atomic, async, write_fault,
+			  writable);
 }
-EXPORT_SYMBOL_GPL(hva_to_pfn_atomic);
 
 static pfn_t __gfn_to_pfn(struct kvm *kvm, gfn_t gfn, bool atomic, bool *async,
 			  bool write_fault, bool *writable)
 {
-	unsigned long addr;
+	struct kvm_memory_slot *slot;
 
 	if (async)
 		*async = false;
 
-	addr = gfn_to_hva(kvm, gfn);
+	slot = gfn_to_memslot(kvm, gfn);
-	if (kvm_is_error_hva(addr)) {
-		get_page(bad_page);
-		return page_to_pfn(bad_page);
-	}
 
-	return hva_to_pfn(kvm, addr, atomic, async, write_fault, writable);
+	return __gfn_to_pfn_memslot(slot, gfn, atomic, async, write_fault,
+				    writable);
 }
 
 pfn_t gfn_to_pfn_atomic(struct kvm *kvm, gfn_t gfn)
@@ -1195,13 +1260,17 @@ pfn_t gfn_to_pfn_prot(struct kvm *kvm, gfn_t gfn, bool write_fault,
 }
 EXPORT_SYMBOL_GPL(gfn_to_pfn_prot);
 
-pfn_t gfn_to_pfn_memslot(struct kvm *kvm,
+pfn_t gfn_to_pfn_memslot(struct kvm_memory_slot *slot, gfn_t gfn)
-			 struct kvm_memory_slot *slot, gfn_t gfn)
 {
-	unsigned long addr = gfn_to_hva_memslot(slot, gfn);
+	return __gfn_to_pfn_memslot(slot, gfn, false, NULL, true, NULL);
-	return hva_to_pfn(kvm, addr, false, NULL, true, NULL);
 }
 
+pfn_t gfn_to_pfn_memslot_atomic(struct kvm_memory_slot *slot, gfn_t gfn)
+{
+	return __gfn_to_pfn_memslot(slot, gfn, true, NULL, true, NULL);
+}
+EXPORT_SYMBOL_GPL(gfn_to_pfn_memslot_atomic);
+
 int gfn_to_page_many_atomic(struct kvm *kvm, gfn_t gfn, struct page **pages,
 								  int nr_pages)
 {
@@ -1219,30 +1288,42 @@ int gfn_to_page_many_atomic(struct kvm *kvm, gfn_t gfn, struct page **pages,
 }
 EXPORT_SYMBOL_GPL(gfn_to_page_many_atomic);
 
+static struct page *kvm_pfn_to_page(pfn_t pfn)
+{
+	if (is_error_pfn(pfn))
+		return KVM_ERR_PTR_BAD_PAGE;
+
+	if (kvm_is_mmio_pfn(pfn)) {
+		WARN_ON(1);
+		return KVM_ERR_PTR_BAD_PAGE;
+	}
+
+	return pfn_to_page(pfn);
+}
+
 struct page *gfn_to_page(struct kvm *kvm, gfn_t gfn)
 {
 	pfn_t pfn;
 
 	pfn = gfn_to_pfn(kvm, gfn);
-	if (!kvm_is_mmio_pfn(pfn))
-		return pfn_to_page(pfn);
 
-	WARN_ON(kvm_is_mmio_pfn(pfn));
+	return kvm_pfn_to_page(pfn);
-
-	get_page(bad_page);
-	return bad_page;
 }
 
 EXPORT_SYMBOL_GPL(gfn_to_page);
 
 void kvm_release_page_clean(struct page *page)
 {
+	WARN_ON(is_error_page(page));
+
 	kvm_release_pfn_clean(page_to_pfn(page));
 }
 EXPORT_SYMBOL_GPL(kvm_release_page_clean);
 
 void kvm_release_pfn_clean(pfn_t pfn)
 {
+	WARN_ON(is_error_pfn(pfn));
+
 	if (!kvm_is_mmio_pfn(pfn))
 		put_page(pfn_to_page(pfn));
 }
@@ -1250,6 +1331,8 @@ EXPORT_SYMBOL_GPL(kvm_release_pfn_clean);
 
 void kvm_release_page_dirty(struct page *page)
 {
+	WARN_ON(is_error_page(page));
+
 	kvm_release_pfn_dirty(page_to_pfn(page));
 }
 EXPORT_SYMBOL_GPL(kvm_release_page_dirty);
@@ -1305,10 +1388,10 @@ int kvm_read_guest_page(struct kvm *kvm, gfn_t gfn, void *data, int offset,
 	int r;
 	unsigned long addr;
 
-	addr = gfn_to_hva(kvm, gfn);
+	addr = gfn_to_hva_read(kvm, gfn);
 	if (kvm_is_error_hva(addr))
 		return -EFAULT;
-	r = __copy_from_user(data, (void __user *)addr + offset, len);
+	r = kvm_read_hva(data, (void __user *)addr + offset, len);
 	if (r)
 		return -EFAULT;
 	return 0;
@@ -1343,11 +1426,11 @@ int kvm_read_guest_atomic(struct kvm *kvm, gpa_t gpa, void *data,
 	gfn_t gfn = gpa >> PAGE_SHIFT;
 	int offset = offset_in_page(gpa);
 
-	addr = gfn_to_hva(kvm, gfn);
+	addr = gfn_to_hva_read(kvm, gfn);
 	if (kvm_is_error_hva(addr))
 		return -EFAULT;
 	pagefault_disable();
-	r = __copy_from_user_inatomic(data, (void __user *)addr + offset, len);
+	r = kvm_read_hva_atomic(data, (void __user *)addr + offset, len);
 	pagefault_enable();
 	if (r)
 		return -EFAULT;
@@ -1580,6 +1663,43 @@ bool kvm_vcpu_yield_to(struct kvm_vcpu *target)
 }
 EXPORT_SYMBOL_GPL(kvm_vcpu_yield_to);
 
+#ifdef CONFIG_HAVE_KVM_CPU_RELAX_INTERCEPT
+/*
+ * Helper that checks whether a VCPU is eligible for directed yield.
+ * Most eligible candidate to yield is decided by following heuristics:
+ *
+ *  (a) VCPU which has not done pl-exit or cpu relax intercepted recently
+ *  (preempted lock holder), indicated by @in_spin_loop.
+ *  Set at the beiginning and cleared at the end of interception/PLE handler.
+ *
+ *  (b) VCPU which has done pl-exit/ cpu relax intercepted but did not get
+ *  chance last time (mostly it has become eligible now since we have probably
+ *  yielded to lockholder in last iteration. This is done by toggling
+ *  @dy_eligible each time a VCPU checked for eligibility.)
+ *
+ *  Yielding to a recently pl-exited/cpu relax intercepted VCPU before yielding
+ *  to preempted lock-holder could result in wrong VCPU selection and CPU
+ *  burning. Giving priority for a potential lock-holder increases lock
+ *  progress.
+ *
+ *  Since algorithm is based on heuristics, accessing another VCPU data without
+ *  locking does not harm. It may result in trying to yield to  same VCPU, fail
+ *  and continue with next VCPU and so on.
+ */
+bool kvm_vcpu_eligible_for_directed_yield(struct kvm_vcpu *vcpu)
+{
+	bool eligible;
+
+	eligible = !vcpu->spin_loop.in_spin_loop ||
+			(vcpu->spin_loop.in_spin_loop &&
+			 vcpu->spin_loop.dy_eligible);
+
+	if (vcpu->spin_loop.in_spin_loop)
+		kvm_vcpu_set_dy_eligible(vcpu, !vcpu->spin_loop.dy_eligible);
+
+	return eligible;
+}
+#endif
 void kvm_vcpu_on_spin(struct kvm_vcpu *me)
 {
 	struct kvm *kvm = me->kvm;
@@ -1589,6 +1709,7 @@ void kvm_vcpu_on_spin(struct kvm_vcpu *me)
 	int pass;
 	int i;
 
+	kvm_vcpu_set_in_spin_loop(me, true);
 	/*
 	 * We boost the priority of a VCPU that is runnable but not
 	 * currently running, because it got preempted by something
@@ -1607,6 +1728,8 @@ void kvm_vcpu_on_spin(struct kvm_vcpu *me)
 				continue;
 			if (waitqueue_active(&vcpu->wq))
 				continue;
+			if (!kvm_vcpu_eligible_for_directed_yield(vcpu))
+				continue;
 			if (kvm_vcpu_yield_to(vcpu)) {
 				kvm->last_boosted_vcpu = i;
 				yielded = 1;
@@ -1614,6 +1737,10 @@ void kvm_vcpu_on_spin(struct kvm_vcpu *me)
 			}
 		}
 	}
+	kvm_vcpu_set_in_spin_loop(me, false);
+
+	/* Ensure vcpu is not eligible during next spinloop */
+	kvm_vcpu_set_dy_eligible(me, false);
 }
 EXPORT_SYMBOL_GPL(kvm_vcpu_on_spin);
 
@@ -1766,7 +1893,9 @@ static long kvm_vcpu_ioctl(struct file *filp,
 #endif
 
 
-	vcpu_load(vcpu);
+	r = vcpu_load(vcpu);
+	if (r)
+		return r;
 	switch (ioctl) {
 	case KVM_RUN:
 		r = -EINVAL;
@@ -2093,6 +2222,29 @@ static long kvm_vm_ioctl(struct file *filp,
 		r = kvm_send_userspace_msi(kvm, &msi);
 		break;
 	}
+#endif
+#ifdef __KVM_HAVE_IRQ_LINE
+	case KVM_IRQ_LINE_STATUS:
+	case KVM_IRQ_LINE: {
+		struct kvm_irq_level irq_event;
+
+		r = -EFAULT;
+		if (copy_from_user(&irq_event, argp, sizeof irq_event))
+			goto out;
+
+		r = kvm_vm_ioctl_irq_line(kvm, &irq_event);
+		if (r)
+			goto out;
+
+		r = -EFAULT;
+		if (ioctl == KVM_IRQ_LINE_STATUS) {
+			if (copy_to_user(argp, &irq_event, sizeof irq_event))
+				goto out;
+		}
+
+		r = 0;
+		break;
+	}
 #endif
 	default:
 		r = kvm_arch_vm_ioctl(filp, ioctl, arg);
@@ -2698,9 +2850,6 @@ static struct syscore_ops kvm_syscore_ops = {
 	.resume = kvm_resume,
 };
 
-struct page *bad_page;
-pfn_t bad_pfn;
-
 static inline
 struct kvm_vcpu *preempt_notifier_to_vcpu(struct preempt_notifier *pn)
 {
@@ -2732,33 +2881,6 @@ int kvm_init(void *opaque, unsigned vcpu_size, unsigned vcpu_align,
 	if (r)
 		goto out_fail;
 
-	bad_page = alloc_page(GFP_KERNEL | __GFP_ZERO);
-
-	if (bad_page == NULL) {
-		r = -ENOMEM;
-		goto out;
-	}
-
-	bad_pfn = page_to_pfn(bad_page);
-
-	hwpoison_page = alloc_page(GFP_KERNEL | __GFP_ZERO);
-
-	if (hwpoison_page == NULL) {
-		r = -ENOMEM;
-		goto out_free_0;
-	}
-
-	hwpoison_pfn = page_to_pfn(hwpoison_page);
-
-	fault_page = alloc_page(GFP_KERNEL | __GFP_ZERO);
-
-	if (fault_page == NULL) {
-		r = -ENOMEM;
-		goto out_free_0;
-	}
-
-	fault_pfn = page_to_pfn(fault_page);
-
 	if (!zalloc_cpumask_var(&cpus_hardware_enabled, GFP_KERNEL)) {
 		r = -ENOMEM;
 		goto out_free_0;
@@ -2833,12 +2955,6 @@ out_free_1:
 out_free_0a:
 	free_cpumask_var(cpus_hardware_enabled);
 out_free_0:
-	if (fault_page)
-		__free_page(fault_page);
-	if (hwpoison_page)
-		__free_page(hwpoison_page);
-	__free_page(bad_page);
-out:
 	kvm_arch_exit();
 out_fail:
 	return r;
@@ -2858,8 +2974,5 @@ void kvm_exit(void)
 	kvm_arch_hardware_unsetup();
 	kvm_arch_exit();
 	free_cpumask_var(cpus_hardware_enabled);
-	__free_page(fault_page);
-	__free_page(hwpoison_page);
-	__free_page(bad_page);
 }
 EXPORT_SYMBOL_GPL(kvm_exit);