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

Pull KVM updates from Paolo Bonzini:
 "ARM:
   - HYP mode stub supports kexec/kdump on 32-bit
   - improved PMU support
   - virtual interrupt controller performance improvements
   - support for userspace virtual interrupt controller (slower, but
     necessary for KVM on the weird Broadcom SoCs used by the Raspberry
     Pi 3)

  MIPS:
   - basic support for hardware virtualization (ImgTec P5600/P6600/I6400
     and Cavium Octeon III)

  PPC:
   - in-kernel acceleration for VFIO

  s390:
   - support for guests without storage keys
   - adapter interruption suppression

  x86:
   - usual range of nVMX improvements, notably nested EPT support for
     accessed and dirty bits
   - emulation of CPL3 CPUID faulting

  generic:
   - first part of VCPU thread request API
   - kvm_stat improvements"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (227 commits)
  kvm: nVMX: Don't validate disabled secondary controls
  KVM: put back #ifndef CONFIG_S390 around kvm_vcpu_kick
  Revert "KVM: Support vCPU-based gfn->hva cache"
  tools/kvm: fix top level makefile
  KVM: x86: don't hold kvm->lock in KVM_SET_GSI_ROUTING
  KVM: Documentation: remove VM mmap documentation
  kvm: nVMX: Remove superfluous VMX instruction fault checks
  KVM: x86: fix emulation of RSM and IRET instructions
  KVM: mark requests that need synchronization
  KVM: return if kvm_vcpu_wake_up() did wake up the VCPU
  KVM: add explicit barrier to kvm_vcpu_kick
  KVM: perform a wake_up in kvm_make_all_cpus_request
  KVM: mark requests that do not need a wakeup
  KVM: remove #ifndef CONFIG_S390 around kvm_vcpu_wake_up
  KVM: x86: always use kvm_make_request instead of set_bit
  KVM: add kvm_{test,clear}_request to replace {test,clear}_bit
  s390: kvm: Cpu model support for msa6, msa7 and msa8
  KVM: x86: remove irq disablement around KVM_SET_CLOCK/KVM_GET_CLOCK
  kvm: better MWAIT emulation for guests
  KVM: x86: virtualize cpuid faulting
  ...

Documentation/virtual/kvm/arm/hyp-abi.txt

@@ -0,0 +1,53 @@
+* Internal ABI between the kernel and HYP
+
+This file documents the interaction between the Linux kernel and the
+hypervisor layer when running Linux as a hypervisor (for example
+KVM). It doesn't cover the interaction of the kernel with the
+hypervisor when running as a guest (under Xen, KVM or any other
+hypervisor), or any hypervisor-specific interaction when the kernel is
+used as a host.
+
+On arm and arm64 (without VHE), the kernel doesn't run in hypervisor
+mode, but still needs to interact with it, allowing a built-in
+hypervisor to be either installed or torn down.
+
+In order to achieve this, the kernel must be booted at HYP (arm) or
+EL2 (arm64), allowing it to install a set of stubs before dropping to
+SVC/EL1. These stubs are accessible by using a 'hvc #0' instruction,
+and only act on individual CPUs.
+
+Unless specified otherwise, any built-in hypervisor must implement
+these functions (see arch/arm{,64}/include/asm/virt.h):
+
+* r0/x0 = HVC_SET_VECTORS
+  r1/x1 = vectors
+
+  Set HVBAR/VBAR_EL2 to 'vectors' to enable a hypervisor. 'vectors'
+  must be a physical address, and respect the alignment requirements
+  of the architecture. Only implemented by the initial stubs, not by
+  Linux hypervisors.
+
+* r0/x0 = HVC_RESET_VECTORS
+
+  Turn HYP/EL2 MMU off, and reset HVBAR/VBAR_EL2 to the initials
+  stubs' exception vector value. This effectively disables an existing
+  hypervisor.
+
+* r0/x0 = HVC_SOFT_RESTART
+  r1/x1 = restart address
+  x2 = x0's value when entering the next payload (arm64)
+  x3 = x1's value when entering the next payload (arm64)
+  x4 = x2's value when entering the next payload (arm64)
+
+  Mask all exceptions, disable the MMU, move the arguments into place
+  (arm64 only), and jump to the restart address while at HYP/EL2. This
+  hypercall is not expected to return to its caller.
+
+Any other value of r0/x0 triggers a hypervisor-specific handling,
+which is not documented here.
+
+The return value of a stub hypercall is held by r0/x0, and is 0 on
+success, and HVC_STUB_ERR on error. A stub hypercall is allowed to
+clobber any of the caller-saved registers (x0-x18 on arm64, r0-r3 and
+ip on arm). It is thus recommended to use a function call to perform
+the hypercall.

Documentation/virtual/kvm/devices/s390_flic.txt

@@ -14,6 +14,8 @@ FLIC provides support to
 - purge one pending floating I/O interrupt (KVM_DEV_FLIC_CLEAR_IO_IRQ)
 - enable/disable for the guest transparent async page faults
 - register and modify adapter interrupt sources (KVM_DEV_FLIC_ADAPTER_*)
+- modify AIS (adapter-interruption-suppression) mode state (KVM_DEV_FLIC_AISM)
+- inject adapter interrupts on a specified adapter (KVM_DEV_FLIC_AIRQ_INJECT)
 
 Groups:
   KVM_DEV_FLIC_ENQUEUE
@@ -64,12 +66,18 @@ struct kvm_s390_io_adapter {
 	__u8 isc;
 	__u8 maskable;
 	__u8 swap;
-	__u8 pad;
+	__u8 flags;
 };
 
    id contains the unique id for the adapter, isc the I/O interruption subclass
-   to use, maskable whether this adapter may be masked (interrupts turned off)
-   and swap whether the indicators need to be byte swapped.
+   to use, maskable whether this adapter may be masked (interrupts turned off),
+   swap whether the indicators need to be byte swapped, and flags contains
+   further characteristics of the adapter.
+   Currently defined values for 'flags' are:
+   - KVM_S390_ADAPTER_SUPPRESSIBLE: adapter is subject to AIS
+     (adapter-interrupt-suppression) facility. This flag only has an effect if
+     the AIS capability is enabled.
+   Unknown flag values are ignored.
 
 
   KVM_DEV_FLIC_ADAPTER_MODIFY
@@ -101,6 +109,33 @@ struct kvm_s390_io_adapter_req {
       release a userspace page for the translated address specified in addr
       from the list of mappings
 
+  KVM_DEV_FLIC_AISM
+    modify the adapter-interruption-suppression mode for a given isc if the
+    AIS capability is enabled. Takes a kvm_s390_ais_req describing:
+
+struct kvm_s390_ais_req {
+	__u8 isc;
+	__u16 mode;
+};
+
+    isc contains the target I/O interruption subclass, mode the target
+    adapter-interruption-suppression mode. The following modes are
+    currently supported:
+    - KVM_S390_AIS_MODE_ALL: ALL-Interruptions Mode, i.e. airq injection
+      is always allowed;
+    - KVM_S390_AIS_MODE_SINGLE: SINGLE-Interruption Mode, i.e. airq
+      injection is only allowed once and the following adapter interrupts
+      will be suppressed until the mode is set again to ALL-Interruptions
+      or SINGLE-Interruption mode.
+
+  KVM_DEV_FLIC_AIRQ_INJECT
+    Inject adapter interrupts on a specified adapter.
+    attr->attr contains the unique id for the adapter, which allows for
+    adapter-specific checks and actions.
+    For adapters subject to AIS, handle the airq injection suppression for
+    an isc according to the adapter-interruption-suppression mode on condition
+    that the AIS capability is enabled.
+
 Note: The KVM_SET_DEVICE_ATTR/KVM_GET_DEVICE_ATTR device ioctls executed on
 FLIC with an unknown group or attribute gives the error code EINVAL (instead of
 ENXIO, as specified in the API documentation). It is not possible to conclude

Documentation/virtual/kvm/devices/vfio.txt

@@ -16,7 +16,21 @@ Groups:
 
 KVM_DEV_VFIO_GROUP attributes:
   KVM_DEV_VFIO_GROUP_ADD: Add a VFIO group to VFIO-KVM device tracking
+	kvm_device_attr.addr points to an int32_t file descriptor
+	for the VFIO group.
   KVM_DEV_VFIO_GROUP_DEL: Remove a VFIO group from VFIO-KVM device tracking
+	kvm_device_attr.addr points to an int32_t file descriptor
+	for the VFIO group.
+  KVM_DEV_VFIO_GROUP_SET_SPAPR_TCE: attaches a guest visible TCE table
+	allocated by sPAPR KVM.
+	kvm_device_attr.addr points to a struct:
 
-For each, kvm_device_attr.addr points to an int32_t file descriptor
-for the VFIO group.
+	struct kvm_vfio_spapr_tce {
+		__s32	groupfd;
+		__s32	tablefd;
+	};
+
+	where
+	@groupfd is a file descriptor for a VFIO group;
+	@tablefd is a file descriptor for a TCE table allocated via
+		KVM_CREATE_SPAPR_TCE.

Documentation/virtual/kvm/devices/vm.txt

@@ -140,7 +140,8 @@ struct kvm_s390_vm_cpu_subfunc {
        u8 kmo[16];           # valid with Message-Security-Assist-Extension 4
        u8 pcc[16];           # valid with Message-Security-Assist-Extension 4
        u8 ppno[16];          # valid with Message-Security-Assist-Extension 5
-       u8 reserved[1824];    # reserved for future instructions
+       u8 kma[16];           # valid with Message-Security-Assist-Extension 8
+       u8 reserved[1808];    # reserved for future instructions
 };
 
 Parameters: address of a buffer to load the subfunction blocks from.

Documentation/virtual/kvm/hypercalls.txt

@@ -28,6 +28,11 @@ S390:
   property inside the device tree's /hypervisor node.
   For more information refer to Documentation/virtual/kvm/ppc-pv.txt
 
+MIPS:
+  KVM hypercalls use the HYPCALL instruction with code 0 and the hypercall
+  number in $2 (v0). Up to four arguments may be placed in $4-$7 (a0-a3) and
+  the return value is placed in $2 (v0).
+
 KVM Hypercalls Documentation
 ===========================
 The template for each hypercall is:

arch/arm/boot/compressed/head.S

@@ -422,7 +422,17 @@ dtb_check_done:
 		cmp	r0, #HYP_MODE
 		bne	1f
 
-		bl	__hyp_get_vectors
+		/*
+		 * Compute the address of the hyp vectors after relocation.
+		 * This requires some arithmetic since we cannot directly
+		 * reference __hyp_stub_vectors in a PC-relative way.
+		 * Call __hyp_set_vectors with the new address so that we
+		 * can HVC again after the copy.
+		 */
+0:		adr	r0, 0b
+		movw	r1, #:lower16:__hyp_stub_vectors - 0b
+		movt	r1, #:upper16:__hyp_stub_vectors - 0b
+		add	r0, r0, r1
 		sub	r0, r0, r5
 		add	r0, r0, r10
 		bl	__hyp_set_vectors

arch/arm/include/asm/kvm_asm.h

@@ -33,7 +33,7 @@
 #define ARM_EXCEPTION_IRQ	  5
 #define ARM_EXCEPTION_FIQ	  6
 #define ARM_EXCEPTION_HVC	  7
-
+#define ARM_EXCEPTION_HYP_GONE	  HVC_STUB_ERR
 /*
  * The rr_lo_hi macro swaps a pair of registers depending on
  * current endianness. It is used in conjunction with ldrd and strd
@@ -72,10 +72,11 @@ extern int __kvm_vcpu_run(struct kvm_vcpu *vcpu);
 
 extern void __init_stage2_translation(void);
 
-extern void __kvm_hyp_reset(unsigned long);
-
 extern u64 __vgic_v3_get_ich_vtr_el2(void);
+extern u64 __vgic_v3_read_vmcr(void);
+extern void __vgic_v3_write_vmcr(u32 vmcr);
 extern void __vgic_v3_init_lrs(void);
+
 #endif
 
 #endif /* __ARM_KVM_ASM_H__ */

arch/arm/include/asm/kvm_host.h

@@ -30,7 +30,6 @@
 #define __KVM_HAVE_ARCH_INTC_INITIALIZED
 
 #define KVM_USER_MEM_SLOTS 32
-#define KVM_COALESCED_MMIO_PAGE_OFFSET 1
 #define KVM_HAVE_ONE_REG
 #define KVM_HALT_POLL_NS_DEFAULT 500000
 
@@ -45,7 +44,7 @@
 #define KVM_MAX_VCPUS VGIC_V2_MAX_CPUS
 #endif
 
-#define KVM_REQ_VCPU_EXIT	8
+#define KVM_REQ_VCPU_EXIT	(8 | KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP)
 
 u32 *kvm_vcpu_reg(struct kvm_vcpu *vcpu, u8 reg_num, u32 mode);
 int __attribute_const__ kvm_target_cpu(void);
@@ -270,12 +269,6 @@ static inline void __cpu_init_stage2(void)
 	kvm_call_hyp(__init_stage2_translation);
 }
 
-static inline void __cpu_reset_hyp_mode(unsigned long vector_ptr,
-					phys_addr_t phys_idmap_start)
-{
-	kvm_call_hyp((void *)virt_to_idmap(__kvm_hyp_reset), vector_ptr);
-}
-
 static inline int kvm_arch_dev_ioctl_check_extension(struct kvm *kvm, long ext)
 {
 	return 0;

arch/arm/include/asm/kvm_mmu.h

@@ -56,7 +56,6 @@ void kvm_mmu_free_memory_caches(struct kvm_vcpu *vcpu);
 
 phys_addr_t kvm_mmu_get_httbr(void);
 phys_addr_t kvm_get_idmap_vector(void);
-phys_addr_t kvm_get_idmap_start(void);
 int kvm_mmu_init(void);
 void kvm_clear_hyp_idmap(void);
 

arch/arm/include/asm/proc-fns.h

@@ -43,7 +43,7 @@ extern struct processor {
 	/*
 	 * Special stuff for a reset
 	 */
-	void (*reset)(unsigned long addr) __attribute__((noreturn));
+	void (*reset)(unsigned long addr, bool hvc) __attribute__((noreturn));
 	/*
 	 * Idle the processor
 	 */
@@ -88,7 +88,7 @@ extern void cpu_set_pte_ext(pte_t *ptep, pte_t pte);
 #else
 extern void cpu_set_pte_ext(pte_t *ptep, pte_t pte, unsigned int ext);
 #endif
-extern void cpu_reset(unsigned long addr) __attribute__((noreturn));
+extern void cpu_reset(unsigned long addr, bool hvc) __attribute__((noreturn));
 
 /* These three are private to arch/arm/kernel/suspend.c */
 extern void cpu_do_suspend(void *);

arch/arm/include/asm/virt.h

@@ -53,7 +53,7 @@ static inline void sync_boot_mode(void)
 }
 
 void __hyp_set_vectors(unsigned long phys_vector_base);
-unsigned long __hyp_get_vectors(void);
+void __hyp_reset_vectors(void);
 #else
 #define __boot_cpu_mode	(SVC_MODE)
 #define sync_boot_mode()
@@ -94,6 +94,18 @@ extern char __hyp_text_start[];
 extern char __hyp_text_end[];
 #endif
 
+#else
+
+/* Only assembly code should need those */
+
+#define HVC_SET_VECTORS 0
+#define HVC_SOFT_RESTART 1
+#define HVC_RESET_VECTORS 2
+
+#define HVC_STUB_HCALL_NR 3
+
 #endif /* __ASSEMBLY__ */
 
+#define HVC_STUB_ERR	0xbadca11
+
 #endif /* ! VIRT_H */

arch/arm/include/uapi/asm/kvm.h

@@ -27,6 +27,8 @@
 #define __KVM_HAVE_IRQ_LINE
 #define __KVM_HAVE_READONLY_MEM
 
+#define KVM_COALESCED_MMIO_PAGE_OFFSET 1
+
 #define KVM_REG_SIZE(id)						\
 	(1U << (((id) & KVM_REG_SIZE_MASK) >> KVM_REG_SIZE_SHIFT))
 
@@ -114,6 +116,8 @@ struct kvm_debug_exit_arch {
 };
 
 struct kvm_sync_regs {
+	/* Used with KVM_CAP_ARM_USER_IRQ */
+	__u64 device_irq_level;
 };
 
 struct kvm_arch_memory_slot {

arch/arm/kernel/hyp-stub.S

@@ -125,7 +125,7 @@ ENTRY(__hyp_stub_install_secondary)
  * (see safe_svcmode_maskall).
  */
 	@ Now install the hypervisor stub:
-	adr	r7, __hyp_stub_vectors
+	W(adr)	r7, __hyp_stub_vectors
 	mcr	p15, 4, r7, c12, c0, 0	@ set hypervisor vector base (HVBAR)
 
 	@ Disable all traps, so we don't get any nasty surprise
@@ -202,9 +202,23 @@ ARM_BE8(orr	r7, r7, #(1 << 25))     @ HSCTLR.EE
 ENDPROC(__hyp_stub_install_secondary)
 
 __hyp_stub_do_trap:
-	cmp	r0, #-1
-	mrceq	p15, 4, r0, c12, c0, 0	@ get HVBAR
-	mcrne	p15, 4, r0, c12, c0, 0	@ set HVBAR
+	teq	r0, #HVC_SET_VECTORS
+	bne	1f
+	mcr	p15, 4, r1, c12, c0, 0	@ set HVBAR
+	b	__hyp_stub_exit
+
+1:	teq	r0, #HVC_SOFT_RESTART
+	bne	1f
+	bx	r1
+
+1:	teq	r0, #HVC_RESET_VECTORS
+	beq	__hyp_stub_exit
+
+	ldr	r0, =HVC_STUB_ERR
+	__ERET
+
+__hyp_stub_exit:
+	mov	r0, #0
 	__ERET
 ENDPROC(__hyp_stub_do_trap)
 
@@ -230,23 +244,34 @@ ENDPROC(__hyp_stub_do_trap)
  * so you will need to set that to something sensible at the new hypervisor's
  * initialisation entry point.
  */
-ENTRY(__hyp_get_vectors)
-	mov	r0, #-1
-ENDPROC(__hyp_get_vectors)
-	@ fall through
 ENTRY(__hyp_set_vectors)
+	mov	r1, r0
+	mov	r0, #HVC_SET_VECTORS
 	__HVC(0)
 	ret	lr
 ENDPROC(__hyp_set_vectors)
 
+ENTRY(__hyp_soft_restart)
+	mov	r1, r0
+	mov	r0, #HVC_SOFT_RESTART
+	__HVC(0)
+	ret	lr
+ENDPROC(__hyp_soft_restart)
+
+ENTRY(__hyp_reset_vectors)
+	mov	r0, #HVC_RESET_VECTORS
+	__HVC(0)
+	ret	lr
+ENDPROC(__hyp_reset_vectors)
+
 #ifndef ZIMAGE
 .align 2
 .L__boot_cpu_mode_offset:
 	.long	__boot_cpu_mode - .
 #endif
 
 .align 5
-__hyp_stub_vectors:
+ENTRY(__hyp_stub_vectors)
 __hyp_stub_reset:	W(b)	.
 __hyp_stub_und:		W(b)	.
 __hyp_stub_svc:		W(b)	.