Merge tag 'kvm-4.20-1' of git://git.kernel.org/pub/scm/virt/kvm/kvm

Pull KVM updates from Radim Krčmář:
 "ARM:
   - Improved guest IPA space support (32 to 52 bits)

   - RAS event delivery for 32bit

   - PMU fixes

   - Guest entry hardening

   - Various cleanups

   - Port of dirty_log_test selftest

  PPC:
   - Nested HV KVM support for radix guests on POWER9. The performance
     is much better than with PR KVM. Migration and arbitrary level of
     nesting is supported.

   - Disable nested HV-KVM on early POWER9 chips that need a particular
     hardware bug workaround

   - One VM per core mode to prevent potential data leaks

   - PCI pass-through optimization

   - merge ppc-kvm topic branch and kvm-ppc-fixes to get a better base

  s390:
   - Initial version of AP crypto virtualization via vfio-mdev

   - Improvement for vfio-ap

   - Set the host program identifier

   - Optimize page table locking

  x86:
   - Enable nested virtualization by default

   - Implement Hyper-V IPI hypercalls

   - Improve #PF and #DB handling

   - Allow guests to use Enlightened VMCS

   - Add migration selftests for VMCS and Enlightened VMCS

   - Allow coalesced PIO accesses

   - Add an option to perform nested VMCS host state consistency check
     through hardware

   - Automatic tuning of lapic_timer_advance_ns

   - Many fixes, minor improvements, and cleanups"

* tag 'kvm-4.20-1' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (204 commits)
  KVM/nVMX: Do not validate that posted_intr_desc_addr is page aligned
  Revert "kvm: x86: optimize dr6 restore"
  KVM: PPC: Optimize clearing TCEs for sparse tables
  x86/kvm/nVMX: tweak shadow fields
  selftests/kvm: add missing executables to .gitignore
  KVM: arm64: Safety check PSTATE when entering guest and handle IL
  KVM: PPC: Book3S HV: Don't use streamlined entry path on early POWER9 chips
  arm/arm64: KVM: Enable 32 bits kvm vcpu events support
  arm/arm64: KVM: Rename function kvm_arch_dev_ioctl_check_extension()
  KVM: arm64: Fix caching of host MDCR_EL2 value
  KVM: VMX: enable nested virtualization by default
  KVM/x86: Use 32bit xor to clear registers in svm.c
  kvm: x86: Introduce KVM_CAP_EXCEPTION_PAYLOAD
  kvm: vmx: Defer setting of DR6 until #DB delivery
  kvm: x86: Defer setting of CR2 until #PF delivery
  kvm: x86: Add payload operands to kvm_multiple_exception
  kvm: x86: Add exception payload fields to kvm_vcpu_events
  kvm: x86: Add has_payload and payload to kvm_queued_exception
  KVM: Documentation: Fix omission in struct kvm_vcpu_events
  KVM: selftests: add Enlightened VMCS test
  ...

Documentation/virtual/kvm/api.txt

@@ -123,6 +123,37 @@ memory layout to fit in user mode), check KVM_CAP_MIPS_VZ and use the
 flag KVM_VM_MIPS_VZ.
 
 
+On arm64, the physical address size for a VM (IPA Size limit) is limited
+to 40bits by default. The limit can be configured if the host supports the
+extension KVM_CAP_ARM_VM_IPA_SIZE. When supported, use
+KVM_VM_TYPE_ARM_IPA_SIZE(IPA_Bits) to set the size in the machine type
+identifier, where IPA_Bits is the maximum width of any physical
+address used by the VM. The IPA_Bits is encoded in bits[7-0] of the
+machine type identifier.
+
+e.g, to configure a guest to use 48bit physical address size :
+
+    vm_fd = ioctl(dev_fd, KVM_CREATE_VM, KVM_VM_TYPE_ARM_IPA_SIZE(48));
+
+The requested size (IPA_Bits) must be :
+  0 - Implies default size, 40bits (for backward compatibility)
+
+  or
+
+  N - Implies N bits, where N is a positive integer such that,
+      32 <= N <= Host_IPA_Limit
+
+Host_IPA_Limit is the maximum possible value for IPA_Bits on the host and
+is dependent on the CPU capability and the kernel configuration. The limit can
+be retrieved using KVM_CAP_ARM_VM_IPA_SIZE of the KVM_CHECK_EXTENSION
+ioctl() at run-time.
+
+Please note that configuring the IPA size does not affect the capability
+exposed by the guest CPUs in ID_AA64MMFR0_EL1[PARange]. It only affects
+size of the address translated by the stage2 level (guest physical to
+host physical address translations).
+
+
 4.3 KVM_GET_MSR_INDEX_LIST, KVM_GET_MSR_FEATURE_INDEX_LIST
 
 Capability: basic, KVM_CAP_GET_MSR_FEATURES for KVM_GET_MSR_FEATURE_INDEX_LIST
@@ -850,7 +881,7 @@ struct kvm_vcpu_events {
 		__u8 injected;
 		__u8 nr;
 		__u8 has_error_code;
-		__u8 pad;
+		__u8 pending;
 		__u32 error_code;
 	} exception;
 	struct {
@@ -873,15 +904,23 @@ struct kvm_vcpu_events {
 		__u8 smm_inside_nmi;
 		__u8 latched_init;
 	} smi;
+	__u8 reserved[27];
+	__u8 exception_has_payload;
+	__u64 exception_payload;
 };
 
-Only two fields are defined in the flags field:
+The following bits are defined in the flags field:
 
-- KVM_VCPUEVENT_VALID_SHADOW may be set in the flags field to signal that
+- KVM_VCPUEVENT_VALID_SHADOW may be set to signal that
   interrupt.shadow contains a valid state.
 
-- KVM_VCPUEVENT_VALID_SMM may be set in the flags field to signal that
-  smi contains a valid state.
+- KVM_VCPUEVENT_VALID_SMM may be set to signal that smi contains a
+  valid state.
+
+- KVM_VCPUEVENT_VALID_PAYLOAD may be set to signal that the
+  exception_has_payload, exception_payload, and exception.pending
+  fields contain a valid state. This bit will be set whenever
+  KVM_CAP_EXCEPTION_PAYLOAD is enabled.
 
 ARM/ARM64:
 
@@ -961,6 +1000,11 @@ shall be written into the VCPU.
 
 KVM_VCPUEVENT_VALID_SMM can only be set if KVM_CAP_X86_SMM is available.
 
+If KVM_CAP_EXCEPTION_PAYLOAD is enabled, KVM_VCPUEVENT_VALID_PAYLOAD
+can be set in the flags field to signal that the
+exception_has_payload, exception_payload, and exception.pending fields
+contain a valid state and shall be written into the VCPU.
+
 ARM/ARM64:
 
 Set the pending SError exception state for this VCPU. It is not possible to
@@ -1922,6 +1966,7 @@ registers, find a list below:
   PPC   | KVM_REG_PPC_TIDR              | 64
   PPC   | KVM_REG_PPC_PSSCR             | 64
   PPC   | KVM_REG_PPC_DEC_EXPIRY        | 64
+  PPC   | KVM_REG_PPC_PTCR              | 64
   PPC   | KVM_REG_PPC_TM_GPR0           | 64
           ...
   PPC   | KVM_REG_PPC_TM_GPR31          | 64
@@ -2269,6 +2314,10 @@ The supported flags are:
         The emulated MMU supports 1T segments in addition to the
         standard 256M ones.
 
+    - KVM_PPC_NO_HASH
+	This flag indicates that HPT guests are not supported by KVM,
+	thus all guests must use radix MMU mode.
+
 The "slb_size" field indicates how many SLB entries are supported
 
 The "sps" array contains 8 entries indicating the supported base
@@ -3676,6 +3725,34 @@ Returns: 0 on success, -1 on error
 This copies the vcpu's kvm_nested_state struct from userspace to the kernel.  For
 the definition of struct kvm_nested_state, see KVM_GET_NESTED_STATE.
 
+4.116 KVM_(UN)REGISTER_COALESCED_MMIO
+
+Capability: KVM_CAP_COALESCED_MMIO (for coalesced mmio)
+	    KVM_CAP_COALESCED_PIO (for coalesced pio)
+Architectures: all
+Type: vm ioctl
+Parameters: struct kvm_coalesced_mmio_zone
+Returns: 0 on success, < 0 on error
+
+Coalesced I/O is a performance optimization that defers hardware
+register write emulation so that userspace exits are avoided.  It is
+typically used to reduce the overhead of emulating frequently accessed
+hardware registers.
+
+When a hardware register is configured for coalesced I/O, write accesses
+do not exit to userspace and their value is recorded in a ring buffer
+that is shared between kernel and userspace.
+
+Coalesced I/O is used if one or more write accesses to a hardware
+register can be deferred until a read or a write to another hardware
+register on the same device.  This last access will cause a vmexit and
+userspace will process accesses from the ring buffer before emulating
+it. That will avoid exiting to userspace on repeated writes.
+
+Coalesced pio is based on coalesced mmio. There is little difference
+between coalesced mmio and pio except that coalesced pio records accesses
+to I/O ports.
+
 5. The kvm_run structure
 ------------------------
 
@@ -4522,7 +4599,7 @@ hpage module parameter is not set to 1, -EINVAL is returned.
 While it is generally possible to create a huge page backed VM without
 this capability, the VM will not be able to run.
 
-7.14 KVM_CAP_MSR_PLATFORM_INFO
+7.15 KVM_CAP_MSR_PLATFORM_INFO
 
 Architectures: x86
 Parameters: args[0] whether feature should be enabled or not
@@ -4531,6 +4608,45 @@ With this capability, a guest may read the MSR_PLATFORM_INFO MSR. Otherwise,
 a #GP would be raised when the guest tries to access. Currently, this
 capability does not enable write permissions of this MSR for the guest.
 
+7.16 KVM_CAP_PPC_NESTED_HV
+
+Architectures: ppc
+Parameters: none
+Returns: 0 on success, -EINVAL when the implementation doesn't support
+	 nested-HV virtualization.
+
+HV-KVM on POWER9 and later systems allows for "nested-HV"
+virtualization, which provides a way for a guest VM to run guests that
+can run using the CPU's supervisor mode (privileged non-hypervisor
+state).  Enabling this capability on a VM depends on the CPU having
+the necessary functionality and on the facility being enabled with a
+kvm-hv module parameter.
+
+7.17 KVM_CAP_EXCEPTION_PAYLOAD
+
+Architectures: x86
+Parameters: args[0] whether feature should be enabled or not
+
+With this capability enabled, CR2 will not be modified prior to the
+emulated VM-exit when L1 intercepts a #PF exception that occurs in
+L2. Similarly, for kvm-intel only, DR6 will not be modified prior to
+the emulated VM-exit when L1 intercepts a #DB exception that occurs in
+L2. As a result, when KVM_GET_VCPU_EVENTS reports a pending #PF (or
+#DB) exception for L2, exception.has_payload will be set and the
+faulting address (or the new DR6 bits*) will be reported in the
+exception_payload field. Similarly, when userspace injects a #PF (or
+#DB) into L2 using KVM_SET_VCPU_EVENTS, it is expected to set
+exception.has_payload and to put the faulting address (or the new DR6
+bits*) in the exception_payload field.
+
+This capability also enables exception.pending in struct
+kvm_vcpu_events, which allows userspace to distinguish between pending
+and injected exceptions.
+
+
+* For the new DR6 bits, note that bit 16 is set iff the #DB exception
+  will clear DR6.RTM.
+
 8. Other capabilities.
 ----------------------
 
@@ -4772,3 +4888,10 @@ CPU when the exception is taken. If this virtual SError is taken to EL1 using
 AArch64, this value will be reported in the ISS field of ESR_ELx.
 
 See KVM_CAP_VCPU_EVENTS for more details.
+8.20 KVM_CAP_HYPERV_SEND_IPI
+
+Architectures: x86
+
+This capability indicates that KVM supports paravirtualized Hyper-V IPI send
+hypercalls:
+HvCallSendSyntheticClusterIpi, HvCallSendSyntheticClusterIpiEx.

MAINTAINERS

@@ -12800,6 +12800,18 @@ W:	http://www.ibm.com/developerworks/linux/linux390/
 S:	Supported
 F:	drivers/s390/crypto/
 
+S390 VFIO AP DRIVER
+M:	Tony Krowiak <[email protected]>
+M:	Pierre Morel <[email protected]>
+M:	Halil Pasic <[email protected]>
+L:	[email protected]
+W:	http://www.ibm.com/developerworks/linux/linux390/
+S:	Supported
+F:	drivers/s390/crypto/vfio_ap_drv.c
+F:	drivers/s390/crypto/vfio_ap_private.h
+F:	drivers/s390/crypto/vfio_ap_ops.c
+F:	Documentation/s390/vfio-ap.txt
+
 S390 ZFCP DRIVER
 M:	Steffen Maier <[email protected]>
 M:	Benjamin Block <[email protected]>

arch/arm/include/asm/kvm_arm.h

@@ -133,8 +133,7 @@
  * space.
  */
 #define KVM_PHYS_SHIFT	(40)
-#define KVM_PHYS_SIZE	(_AC(1, ULL) << KVM_PHYS_SHIFT)
-#define KVM_PHYS_MASK	(KVM_PHYS_SIZE - _AC(1, ULL))
+
 #define PTRS_PER_S2_PGD	(_AC(1, ULL) << (KVM_PHYS_SHIFT - 30))
 
 /* Virtualization Translation Control Register (VTCR) bits */

arch/arm/include/asm/kvm_host.h

@@ -273,7 +273,7 @@ static inline void __cpu_init_stage2(void)
 	kvm_call_hyp(__init_stage2_translation);
 }
 
-static inline int kvm_arch_dev_ioctl_check_extension(struct kvm *kvm, long ext)
+static inline int kvm_arch_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 {
 	return 0;
 }
@@ -354,4 +354,15 @@ static inline void kvm_vcpu_put_sysregs(struct kvm_vcpu *vcpu) {}
 struct kvm *kvm_arch_alloc_vm(void);
 void kvm_arch_free_vm(struct kvm *kvm);
 
+static inline int kvm_arm_setup_stage2(struct kvm *kvm, unsigned long type)
+{
+	/*
+	 * On 32bit ARM, VMs get a static 40bit IPA stage2 setup,
+	 * so any non-zero value used as type is illegal.
+	 */
+	if (type)
+		return -EINVAL;
+	return 0;
+}
+
 #endif /* __ARM_KVM_HOST_H__ */

arch/arm/include/asm/kvm_mmu.h

@@ -35,23 +35,26 @@
 		addr;							\
 	})
 
-/*
- * KVM_MMU_CACHE_MIN_PAGES is the number of stage2 page table translation levels.
- */
-#define KVM_MMU_CACHE_MIN_PAGES	2
-
 #ifndef __ASSEMBLY__
 
 #include <linux/highmem.h>
 #include <asm/cacheflush.h>
 #include <asm/cputype.h>
+#include <asm/kvm_arm.h>
 #include <asm/kvm_hyp.h>
 #include <asm/pgalloc.h>
 #include <asm/stage2_pgtable.h>
 
 /* Ensure compatibility with arm64 */
 #define VA_BITS			32
 
+#define kvm_phys_shift(kvm)		KVM_PHYS_SHIFT
+#define kvm_phys_size(kvm)		(1ULL << kvm_phys_shift(kvm))
+#define kvm_phys_mask(kvm)		(kvm_phys_size(kvm) - 1ULL)
+#define kvm_vttbr_baddr_mask(kvm)	VTTBR_BADDR_MASK
+
+#define stage2_pgd_size(kvm)		(PTRS_PER_S2_PGD * sizeof(pgd_t))
+
 int create_hyp_mappings(void *from, void *to, pgprot_t prot);
 int create_hyp_io_mappings(phys_addr_t phys_addr, size_t size,
 			   void __iomem **kaddr,
@@ -355,6 +358,8 @@ static inline int hyp_map_aux_data(void)
 
 #define kvm_phys_to_vttbr(addr)		(addr)
 
+static inline void kvm_set_ipa_limit(void) {}
+
 static inline bool kvm_cpu_has_cnp(void)
 {
 	return false;

arch/arm/include/asm/stage2_pgtable.h

@@ -19,43 +19,53 @@
 #ifndef __ARM_S2_PGTABLE_H_
 #define __ARM_S2_PGTABLE_H_
 
-#define stage2_pgd_none(pgd)			pgd_none(pgd)
-#define stage2_pgd_clear(pgd)			pgd_clear(pgd)
-#define stage2_pgd_present(pgd)			pgd_present(pgd)
-#define stage2_pgd_populate(pgd, pud)		pgd_populate(NULL, pgd, pud)
-#define stage2_pud_offset(pgd, address)		pud_offset(pgd, address)
-#define stage2_pud_free(pud)			pud_free(NULL, pud)
-
-#define stage2_pud_none(pud)			pud_none(pud)
-#define stage2_pud_clear(pud)			pud_clear(pud)
-#define stage2_pud_present(pud)			pud_present(pud)
-#define stage2_pud_populate(pud, pmd)		pud_populate(NULL, pud, pmd)
-#define stage2_pmd_offset(pud, address)		pmd_offset(pud, address)
-#define stage2_pmd_free(pmd)			pmd_free(NULL, pmd)
-
-#define stage2_pud_huge(pud)			pud_huge(pud)
+/*
+ * kvm_mmu_cache_min_pages() is the number of pages required
+ * to install a stage-2 translation. We pre-allocate the entry
+ * level table at VM creation. Since we have a 3 level page-table,
+ * we need only two pages to add a new mapping.
+ */
+#define kvm_mmu_cache_min_pages(kvm)	2
+
+#define stage2_pgd_none(kvm, pgd)		pgd_none(pgd)
+#define stage2_pgd_clear(kvm, pgd)		pgd_clear(pgd)
+#define stage2_pgd_present(kvm, pgd)		pgd_present(pgd)
+#define stage2_pgd_populate(kvm, pgd, pud)	pgd_populate(NULL, pgd, pud)
+#define stage2_pud_offset(kvm, pgd, address)	pud_offset(pgd, address)
+#define stage2_pud_free(kvm, pud)		pud_free(NULL, pud)
+
+#define stage2_pud_none(kvm, pud)		pud_none(pud)
+#define stage2_pud_clear(kvm, pud)		pud_clear(pud)
+#define stage2_pud_present(kvm, pud)		pud_present(pud)
+#define stage2_pud_populate(kvm, pud, pmd)	pud_populate(NULL, pud, pmd)
+#define stage2_pmd_offset(kvm, pud, address)	pmd_offset(pud, address)
+#define stage2_pmd_free(kvm, pmd)		pmd_free(NULL, pmd)
+
+#define stage2_pud_huge(kvm, pud)		pud_huge(pud)
 
 /* Open coded p*d_addr_end that can deal with 64bit addresses */
-static inline phys_addr_t stage2_pgd_addr_end(phys_addr_t addr, phys_addr_t end)
+static inline phys_addr_t
+stage2_pgd_addr_end(struct kvm *kvm, phys_addr_t addr, phys_addr_t end)
 {
 	phys_addr_t boundary = (addr + PGDIR_SIZE) & PGDIR_MASK;
 
 	return (boundary - 1 < end - 1) ? boundary : end;
 }
 
-#define stage2_pud_addr_end(addr, end)		(end)
+#define stage2_pud_addr_end(kvm, addr, end)	(end)
 
-static inline phys_addr_t stage2_pmd_addr_end(phys_addr_t addr, phys_addr_t end)
+static inline phys_addr_t
+stage2_pmd_addr_end(struct kvm *kvm, phys_addr_t addr, phys_addr_t end)
 {
 	phys_addr_t boundary = (addr + PMD_SIZE) & PMD_MASK;
 
 	return (boundary - 1 < end - 1) ? boundary : end;
 }
 
-#define stage2_pgd_index(addr)				pgd_index(addr)
+#define stage2_pgd_index(kvm, addr)		pgd_index(addr)
 
-#define stage2_pte_table_empty(ptep)			kvm_page_empty(ptep)
-#define stage2_pmd_table_empty(pmdp)			kvm_page_empty(pmdp)
-#define stage2_pud_table_empty(pudp)			false
+#define stage2_pte_table_empty(kvm, ptep)	kvm_page_empty(ptep)
+#define stage2_pmd_table_empty(kvm, pmdp)	kvm_page_empty(pmdp)
+#define stage2_pud_table_empty(kvm, pudp)	false
 
 #endif	/* __ARM_S2_PGTABLE_H_ */