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

Pull KVM changes from Paolo Bonzini:
 "Here are the 3.13 KVM changes.  There was a lot of work on the PPC
  side: the HV and emulation flavors can now coexist in a single kernel
  is probably the most interesting change from a user point of view.

  On the x86 side there are nested virtualization improvements and a few
  bugfixes.

  ARM got transparent huge page support, improved overcommit, and
  support for big endian guests.

  Finally, there is a new interface to connect KVM with VFIO.  This
  helps with devices that use NoSnoop PCI transactions, letting the
  driver in the guest execute WBINVD instructions.  This includes some
  nVidia cards on Windows, that fail to start without these patches and
  the corresponding userspace changes"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (146 commits)
  kvm, vmx: Fix lazy FPU on nested guest
  arm/arm64: KVM: PSCI: propagate caller endianness to the incoming vcpu
  arm/arm64: KVM: MMIO support for BE guest
  kvm, cpuid: Fix sparse warning
  kvm: Delete prototype for non-existent function kvm_check_iopl
  kvm: Delete prototype for non-existent function complete_pio
  hung_task: add method to reset detector
  pvclock: detect watchdog reset at pvclock read
  kvm: optimize out smp_mb after srcu_read_unlock
  srcu: API for barrier after srcu read unlock
  KVM: remove vm mmap method
  KVM: IOMMU: hva align mapping page size
  KVM: x86: trace cpuid emulation when called from emulator
  KVM: emulator: cleanup decode_register_operand() a bit
  KVM: emulator: check rex prefix inside decode_register()
  KVM: x86: fix emulation of "movzbl %bpl, %eax"
  kvm_host: typo fix
  KVM: x86: emulate SAHF instruction
  MAINTAINERS: add tree for kvm.git
  Documentation/kvm: add a 00-INDEX file
  ...

5 files changed, 215 insertions, 9 deletions

diff --git a/Documentation/virtual/kvm/00-INDEX b/Documentation/virtual/kvm/00-INDEX
new file mode 100644
index 00000000000..641ec922017
--- /dev/null
+++ b/Documentation/virtual/kvm/00-INDEX
@@ -0,0 +1,24 @@
+00-INDEX
+	- this file.
+api.txt
+	- KVM userspace API.
+cpuid.txt
+	- KVM-specific cpuid leaves (x86).
+devices/
+	- KVM_CAP_DEVICE_CTRL userspace API.
+hypercalls.txt
+	- KVM hypercalls.
+locking.txt
+	- notes on KVM locks.
+mmu.txt
+	- the x86 kvm shadow mmu.
+msr.txt
+	- KVM-specific MSRs (x86).
+nested-vmx.txt
+	- notes on nested virtualization for Intel x86 processors.
+ppc-pv.txt
+	- the paravirtualization interface on PowerPC.
+review-checklist.txt
+	- review checklist for KVM patches.
+timekeeping.txt
+	- timekeeping virtualization for x86-based architectures.
diff --git a/Documentation/virtual/kvm/api.txt b/Documentation/virtual/kvm/api.txt
index 858aecf21db..a30035dd4c2 100644
--- a/Documentation/virtual/kvm/api.txt
+++ b/Documentation/virtual/kvm/api.txt
@@ -1122,9 +1122,9 @@ struct kvm_cpuid2 {
 	struct kvm_cpuid_entry2 entries[0];
 };
 
-#define KVM_CPUID_FLAG_SIGNIFCANT_INDEX 1
-#define KVM_CPUID_FLAG_STATEFUL_FUNC    2
-#define KVM_CPUID_FLAG_STATE_READ_NEXT  4
+#define KVM_CPUID_FLAG_SIGNIFCANT_INDEX		BIT(0)
+#define KVM_CPUID_FLAG_STATEFUL_FUNC		BIT(1)
+#define KVM_CPUID_FLAG_STATE_READ_NEXT		BIT(2)
 
 struct kvm_cpuid_entry2 {
 	__u32 function;
@@ -1810,6 +1810,50 @@ registers, find a list below:
   PPC   | KVM_REG_PPC_TLB3PS	| 32
   PPC   | KVM_REG_PPC_EPTCFG	| 32
   PPC   | KVM_REG_PPC_ICP_STATE | 64
+  PPC   | KVM_REG_PPC_TB_OFFSET	| 64
+  PPC   | KVM_REG_PPC_SPMC1	| 32
+  PPC   | KVM_REG_PPC_SPMC2	| 32
+  PPC   | KVM_REG_PPC_IAMR	| 64
+  PPC   | KVM_REG_PPC_TFHAR	| 64
+  PPC   | KVM_REG_PPC_TFIAR	| 64
+  PPC   | KVM_REG_PPC_TEXASR	| 64
+  PPC   | KVM_REG_PPC_FSCR	| 64
+  PPC   | KVM_REG_PPC_PSPB	| 32
+  PPC   | KVM_REG_PPC_EBBHR	| 64
+  PPC   | KVM_REG_PPC_EBBRR	| 64
+  PPC   | KVM_REG_PPC_BESCR	| 64
+  PPC   | KVM_REG_PPC_TAR	| 64
+  PPC   | KVM_REG_PPC_DPDES	| 64
+  PPC   | KVM_REG_PPC_DAWR	| 64
+  PPC   | KVM_REG_PPC_DAWRX	| 64
+  PPC   | KVM_REG_PPC_CIABR	| 64
+  PPC   | KVM_REG_PPC_IC	| 64
+  PPC   | KVM_REG_PPC_VTB	| 64
+  PPC   | KVM_REG_PPC_CSIGR	| 64
+  PPC   | KVM_REG_PPC_TACR	| 64
+  PPC   | KVM_REG_PPC_TCSCR	| 64
+  PPC   | KVM_REG_PPC_PID	| 64
+  PPC   | KVM_REG_PPC_ACOP	| 64
+  PPC   | KVM_REG_PPC_VRSAVE	| 32
+  PPC   | KVM_REG_PPC_LPCR	| 64
+  PPC   | KVM_REG_PPC_PPR	| 64
+  PPC   | KVM_REG_PPC_ARCH_COMPAT 32
+  PPC   | KVM_REG_PPC_TM_GPR0	| 64
+          ...
+  PPC   | KVM_REG_PPC_TM_GPR31	| 64
+  PPC   | KVM_REG_PPC_TM_VSR0	| 128
+          ...
+  PPC   | KVM_REG_PPC_TM_VSR63	| 128
+  PPC   | KVM_REG_PPC_TM_CR	| 64
+  PPC   | KVM_REG_PPC_TM_LR	| 64
+  PPC   | KVM_REG_PPC_TM_CTR	| 64
+  PPC   | KVM_REG_PPC_TM_FPSCR	| 64
+  PPC   | KVM_REG_PPC_TM_AMR	| 64
+  PPC   | KVM_REG_PPC_TM_PPR	| 64
+  PPC   | KVM_REG_PPC_TM_VRSAVE	| 64
+  PPC   | KVM_REG_PPC_TM_VSCR	| 32
+  PPC   | KVM_REG_PPC_TM_DSCR	| 64
+  PPC   | KVM_REG_PPC_TM_TAR	| 64
 
 ARM registers are mapped using the lower 32 bits.  The upper 16 of that
 is the register group type, or coprocessor number:
@@ -2304,7 +2348,31 @@ Possible features:
 	  Depends on KVM_CAP_ARM_EL1_32BIT (arm64 only).
 
 
-4.83 KVM_GET_REG_LIST
+4.83 KVM_ARM_PREFERRED_TARGET
+
+Capability: basic
+Architectures: arm, arm64
+Type: vm ioctl
+Parameters: struct struct kvm_vcpu_init (out)
+Returns: 0 on success; -1 on error
+Errors:
+  ENODEV:    no preferred target available for the host
+
+This queries KVM for preferred CPU target type which can be emulated
+by KVM on underlying host.
+
+The ioctl returns struct kvm_vcpu_init instance containing information
+about preferred CPU target type and recommended features for it.  The
+kvm_vcpu_init->features bitmap returned will have feature bits set if
+the preferred target recommends setting these features, but this is
+not mandatory.
+
+The information returned by this ioctl can be used to prepare an instance
+of struct kvm_vcpu_init for KVM_ARM_VCPU_INIT ioctl which will result in
+in VCPU matching underlying host.
+
+
+4.84 KVM_GET_REG_LIST
 
 Capability: basic
 Architectures: arm, arm64
@@ -2323,8 +2391,7 @@ struct kvm_reg_list {
 This ioctl returns the guest registers that are supported for the
 KVM_GET_ONE_REG/KVM_SET_ONE_REG calls.
 
-
-4.84 KVM_ARM_SET_DEVICE_ADDR
+4.85 KVM_ARM_SET_DEVICE_ADDR
 
 Capability: KVM_CAP_ARM_SET_DEVICE_ADDR
 Architectures: arm, arm64
@@ -2362,7 +2429,7 @@ must be called after calling KVM_CREATE_IRQCHIP, but before calling
 KVM_RUN on any of the VCPUs.  Calling this ioctl twice for any of the
 base addresses will return -EEXIST.
 
-4.85 KVM_PPC_RTAS_DEFINE_TOKEN
+4.86 KVM_PPC_RTAS_DEFINE_TOKEN
 
 Capability: KVM_CAP_PPC_RTAS
 Architectures: ppc
@@ -2661,6 +2728,77 @@ and usually define the validity of a groups of registers. (e.g. one bit
 };
 
 
+4.81 KVM_GET_EMULATED_CPUID
+
+Capability: KVM_CAP_EXT_EMUL_CPUID
+Architectures: x86
+Type: system ioctl
+Parameters: struct kvm_cpuid2 (in/out)
+Returns: 0 on success, -1 on error
+
+struct kvm_cpuid2 {
+	__u32 nent;
+	__u32 flags;
+	struct kvm_cpuid_entry2 entries[0];
+};
+
+The member 'flags' is used for passing flags from userspace.
+
+#define KVM_CPUID_FLAG_SIGNIFCANT_INDEX		BIT(0)
+#define KVM_CPUID_FLAG_STATEFUL_FUNC		BIT(1)
+#define KVM_CPUID_FLAG_STATE_READ_NEXT		BIT(2)
+
+struct kvm_cpuid_entry2 {
+	__u32 function;
+	__u32 index;
+	__u32 flags;
+	__u32 eax;
+	__u32 ebx;
+	__u32 ecx;
+	__u32 edx;
+	__u32 padding[3];
+};
+
+This ioctl returns x86 cpuid features which are emulated by
+kvm.Userspace can use the information returned by this ioctl to query
+which features are emulated by kvm instead of being present natively.
+
+Userspace invokes KVM_GET_EMULATED_CPUID by passing a kvm_cpuid2
+structure with the 'nent' field indicating the number of entries in
+the variable-size array 'entries'. If the number of entries is too low
+to describe the cpu capabilities, an error (E2BIG) is returned. If the
+number is too high, the 'nent' field is adjusted and an error (ENOMEM)
+is returned. If the number is just right, the 'nent' field is adjusted
+to the number of valid entries in the 'entries' array, which is then
+filled.
+
+The entries returned are the set CPUID bits of the respective features
+which kvm emulates, as returned by the CPUID instruction, with unknown
+or unsupported feature bits cleared.
+
+Features like x2apic, for example, may not be present in the host cpu
+but are exposed by kvm in KVM_GET_SUPPORTED_CPUID because they can be
+emulated efficiently and thus not included here.
+
+The fields in each entry are defined as follows:
+
+  function: the eax value used to obtain the entry
+  index: the ecx value used to obtain the entry (for entries that are
+         affected by ecx)
+  flags: an OR of zero or more of the following:
+        KVM_CPUID_FLAG_SIGNIFCANT_INDEX:
+           if the index field is valid
+        KVM_CPUID_FLAG_STATEFUL_FUNC:
+           if cpuid for this function returns different values for successive
+           invocations; there will be several entries with the same function,
+           all with this flag set
+        KVM_CPUID_FLAG_STATE_READ_NEXT:
+           for KVM_CPUID_FLAG_STATEFUL_FUNC entries, set if this entry is
+           the first entry to be read by a cpu
+   eax, ebx, ecx, edx: the values returned by the cpuid instruction for
+         this function/index combination
+
+
 6. Capabilities that can be enabled
 -----------------------------------
 
diff --git a/Documentation/virtual/kvm/cpuid.txt b/Documentation/virtual/kvm/cpuid.txt
index 22ff659bc0f..3c65feb8301 100644
--- a/Documentation/virtual/kvm/cpuid.txt
+++ b/Documentation/virtual/kvm/cpuid.txt
@@ -43,6 +43,13 @@ KVM_FEATURE_CLOCKSOURCE2           ||     3 || kvmclock available at msrs
 KVM_FEATURE_ASYNC_PF               ||     4 || async pf can be enabled by
                                    ||       || writing to msr 0x4b564d02
 ------------------------------------------------------------------------------
+KVM_FEATURE_STEAL_TIME             ||     5 || steal time can be enabled by
+                                   ||       || writing to msr 0x4b564d03.
+------------------------------------------------------------------------------
+KVM_FEATURE_PV_EOI                 ||     6 || paravirtualized end of interrupt
+                                   ||       || handler can be enabled by writing
+                                   ||       || to msr 0x4b564d04.
+------------------------------------------------------------------------------
 KVM_FEATURE_PV_UNHALT              ||     7 || guest checks this feature bit
                                    ||       || before enabling paravirtualized
                                    ||       || spinlock support.
diff --git a/Documentation/virtual/kvm/devices/vfio.txt b/Documentation/virtual/kvm/devices/vfio.txt
new file mode 100644
index 00000000000..ef51740c67c
--- /dev/null
+++ b/Documentation/virtual/kvm/devices/vfio.txt
@@ -0,0 +1,22 @@
+VFIO virtual device
+===================
+
+Device types supported:
+  KVM_DEV_TYPE_VFIO
+
+Only one VFIO instance may be created per VM.  The created device
+tracks VFIO groups in use by the VM and features of those groups
+important to the correctness and acceleration of the VM.  As groups
+are enabled and disabled for use by the VM, KVM should be updated
+about their presence.  When registered with KVM, a reference to the
+VFIO-group is held by KVM.
+
+Groups:
+  KVM_DEV_VFIO_GROUP
+
+KVM_DEV_VFIO_GROUP attributes:
+  KVM_DEV_VFIO_GROUP_ADD: Add a VFIO group to VFIO-KVM device tracking
+  KVM_DEV_VFIO_GROUP_DEL: Remove a VFIO group from VFIO-KVM device tracking
+
+For each, kvm_device_attr.addr points to an int32_t file descriptor
+for the VFIO group.
diff --git a/Documentation/virtual/kvm/locking.txt b/Documentation/virtual/kvm/locking.txt
index 41b7ac9884b..f8869410d40 100644
--- a/Documentation/virtual/kvm/locking.txt
+++ b/Documentation/virtual/kvm/locking.txt
@@ -132,10 +132,14 @@ See the comments in spte_has_volatile_bits() and mmu_spte_update().
 ------------
 
 Name:		kvm_lock
-Type:		raw_spinlock
+Type:		spinlock_t
 Arch:		any
 Protects:	- vm_list
-		- hardware virtualization enable/disable
+
+Name:		kvm_count_lock
+Type:		raw_spinlock_t
+Arch:		any
+Protects:	- hardware virtualization enable/disable
 Comment:	'raw' because hardware enabling/disabling must be atomic /wrt
 		migration.
 
@@ -151,3 +155,14 @@ Type:		spinlock_t
 Arch:		any
 Protects:	-shadow page/shadow tlb entry
 Comment:	it is a spinlock since it is used in mmu notifier.
+
+Name:		kvm->srcu
+Type:		srcu lock
+Arch:		any
+Protects:	- kvm->memslots
+		- kvm->buses
+Comment:	The srcu read lock must be held while accessing memslots (e.g.
+		when using gfn_to_* functions) and while accessing in-kernel
+		MMIO/PIO address->device structure mapping (kvm->buses).
+		The srcu index can be stored in kvm_vcpu->srcu_idx per vcpu
+		if it is needed by multiple functions.