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

Pull KVM updates from Paolo Bonzini: - ARM: GICv3 ITS emulation and various fixes. Removal of the old VGIC implementation. - s390: support for trapping software breakpoints, nested virtualization (vSIE), the STHYI opcode, initial extensions for CPU model support. - MIPS: support for MIPS64 hosts (32-bit guests only) and lots of cleanups, preliminary to this and the upcoming support for hardware virtualization extensions. - x86: support for execute-only mappings in nested EPT; reduced vmexit latency for TSC deadline timer (by about 30%) on Intel hosts; support for more than 255 vCPUs. - PPC: bugfixes. * tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (302 commits) KVM: PPC: Introduce KVM_CAP_PPC_HTM MIPS: Select HAVE_KVM for MIPS64_R{2,6} MIPS: KVM: Reset CP0_PageMask during host TLB flush MIPS: KVM: Fix ptr->int cast via KVM_GUEST_KSEGX() MIPS: KVM: Sign extend MFC0/RDHWR results MIPS: KVM: Fix 64-bit big endian dynamic translation MIPS: KVM: Fail if ebase doesn't fit in CP0_EBase MIPS: KVM: Use 64-bit CP0_EBase when appropriate MIPS: KVM: Set CP0_Status.KX on MIPS64 MIPS: KVM: Make entry code MIPS64 friendly MIPS: KVM: Use kmap instead of CKSEG0ADDR() MIPS: KVM: Use virt_to_phys() to get commpage PFN MIPS: Fix definition of KSEGX() for 64-bit KVM: VMX: Add VMCS to CPU's loaded VMCSs before VMPTRLD kvm: x86: nVMX: maintain internal copy of current VMCS KVM: PPC: Book3S HV: Save/restore TM state in H_CEDE KVM: PPC: Book3S HV: Pull out TM state save/restore into separate procedures KVM: arm64: vgic-its: Simplify MAPI error handling KVM: arm64: vgic-its: Make vgic_its_cmd_handle_mapi similar to other handlers KVM: arm64: vgic-its: Turn device_id validation into generic ID validation ...
2026-05-01 15:00:59 -07:00 · 2016-08-02 16:11:27 -04:00
parent f7b32e4c02 23528bb21e
commit 221bb8a46e
167 changed files with 11788 additions and 9295 deletions
@@ -1482,6 +1482,11 @@ struct kvm_irq_routing_msi {
 	__u32 pad;
 };

+On x86, address_hi is ignored unless the KVM_X2APIC_API_USE_32BIT_IDS
+feature of KVM_CAP_X2APIC_API capability is enabled.  If it is enabled,
+address_hi bits 31-8 provide bits 31-8 of the destination id.  Bits 7-0 of
+address_hi must be zero.
+
 struct kvm_irq_routing_s390_adapter {
 	__u64 ind_addr;
 	__u64 summary_addr;
@@ -1583,6 +1588,17 @@ struct kvm_lapic_state {
 Reads the Local APIC registers and copies them into the input argument.  The
 data format and layout are the same as documented in the architecture manual.

+If KVM_X2APIC_API_USE_32BIT_IDS feature of KVM_CAP_X2APIC_API is
+enabled, then the format of APIC_ID register depends on the APIC mode
+(reported by MSR_IA32_APICBASE) of its VCPU.  x2APIC stores APIC ID in
+the APIC_ID register (bytes 32-35).  xAPIC only allows an 8-bit APIC ID
+which is stored in bits 31-24 of the APIC register, or equivalently in
+byte 35 of struct kvm_lapic_state's regs field.  KVM_GET_LAPIC must then
+be called after MSR_IA32_APICBASE has been set with KVM_SET_MSR.
+
+If KVM_X2APIC_API_USE_32BIT_IDS feature is disabled, struct kvm_lapic_state
+always uses xAPIC format.
+

 4.58 KVM_SET_LAPIC

@@ -1600,6 +1616,10 @@ struct kvm_lapic_state {
 Copies the input argument into the Local APIC registers.  The data format
 and layout are the same as documented in the architecture manual.

+The format of the APIC ID register (bytes 32-35 of struct kvm_lapic_state's
+regs field) depends on the state of the KVM_CAP_X2APIC_API capability.
+See the note in KVM_GET_LAPIC.
+

 4.59 KVM_IOEVENTFD

@@ -2032,6 +2052,12 @@ registers, find a list below:
  MIPS  | KVM_REG_MIPS_CP0_CONFIG5      | 32
  MIPS  | KVM_REG_MIPS_CP0_CONFIG7      | 32
  MIPS  | KVM_REG_MIPS_CP0_ERROREPC     | 64
+  MIPS  | KVM_REG_MIPS_CP0_KSCRATCH1    | 64
+  MIPS  | KVM_REG_MIPS_CP0_KSCRATCH2    | 64
+  MIPS  | KVM_REG_MIPS_CP0_KSCRATCH3    | 64
+  MIPS  | KVM_REG_MIPS_CP0_KSCRATCH4    | 64
+  MIPS  | KVM_REG_MIPS_CP0_KSCRATCH5    | 64
+  MIPS  | KVM_REG_MIPS_CP0_KSCRATCH6    | 64
  MIPS  | KVM_REG_MIPS_COUNT_CTL        | 64
  MIPS  | KVM_REG_MIPS_COUNT_RESUME     | 64
  MIPS  | KVM_REG_MIPS_COUNT_HZ         | 64
@@ -2156,7 +2182,7 @@ after pausing the vcpu, but before it is resumed.
 4.71 KVM_SIGNAL_MSI

 Capability: KVM_CAP_SIGNAL_MSI
-Architectures: x86
+Architectures: x86 arm64
 Type: vm ioctl
 Parameters: struct kvm_msi (in)
 Returns: >0 on delivery, 0 if guest blocked the MSI, and -1 on error
@@ -2169,10 +2195,22 @@ struct kvm_msi {
 	__u32 address_hi;
 	__u32 data;
 	__u32 flags;
-	__u8  pad[16];
+	__u32 devid;
+	__u8  pad[12];
 };

-No flags are defined so far. The corresponding field must be 0.
+flags: KVM_MSI_VALID_DEVID: devid contains a valid value
+devid: If KVM_MSI_VALID_DEVID is set, contains a unique device identifier
+       for the device that wrote the MSI message.
+       For PCI, this is usually a BFD identifier in the lower 16 bits.
+
+The per-VM KVM_CAP_MSI_DEVID capability advertises the need to provide
+the device ID. If this capability is not set, userland cannot rely on
+the kernel to allow the KVM_MSI_VALID_DEVID flag being set.
+
+On x86, address_hi is ignored unless the KVM_CAP_X2APIC_API capability is
+enabled.  If it is enabled, address_hi bits 31-8 provide bits 31-8 of the
+destination id.  Bits 7-0 of address_hi must be zero.


 4.71 KVM_CREATE_PIT2
@@ -2520,6 +2558,7 @@ Parameters: struct kvm_device_attr
 Returns: 0 on success, -1 on error
 Errors:
  ENXIO:  The group or attribute is unknown/unsupported for this device
+          or hardware support is missing.
  EPERM:  The attribute cannot (currently) be accessed this way
          (e.g. read-only attribute, or attribute that only makes
          sense when the device is in a different state)
@@ -2547,6 +2586,7 @@ Parameters: struct kvm_device_attr
 Returns: 0 on success, -1 on error
 Errors:
  ENXIO:  The group or attribute is unknown/unsupported for this device
+          or hardware support is missing.

 Tests whether a device supports a particular attribute.  A successful
 return indicates the attribute is implemented.  It does not necessarily
@@ -3803,6 +3843,42 @@ Allows use of runtime-instrumentation introduced with zEC12 processor.
 Will return -EINVAL if the machine does not support runtime-instrumentation.
 Will return -EBUSY if a VCPU has already been created.

+7.7 KVM_CAP_X2APIC_API
+
+Architectures: x86
+Parameters: args[0] - features that should be enabled
+Returns: 0 on success, -EINVAL when args[0] contains invalid features
+
+Valid feature flags in args[0] are
+
+#define KVM_X2APIC_API_USE_32BIT_IDS            (1ULL << 0)
+#define KVM_X2APIC_API_DISABLE_BROADCAST_QUIRK  (1ULL << 1)
+
+Enabling KVM_X2APIC_API_USE_32BIT_IDS changes the behavior of
+KVM_SET_GSI_ROUTING, KVM_SIGNAL_MSI, KVM_SET_LAPIC, and KVM_GET_LAPIC,
+allowing the use of 32-bit APIC IDs.  See KVM_CAP_X2APIC_API in their
+respective sections.
+
+KVM_X2APIC_API_DISABLE_BROADCAST_QUIRK must be enabled for x2APIC to work
+in logical mode or with more than 255 VCPUs.  Otherwise, KVM treats 0xff
+as a broadcast even in x2APIC mode in order to support physical x2APIC
+without interrupt remapping.  This is undesirable in logical mode,
+where 0xff represents CPUs 0-7 in cluster 0.
+
+7.8 KVM_CAP_S390_USER_INSTR0
+
+Architectures: s390
+Parameters: none
+
+With this capability enabled, all illegal instructions 0x0000 (2 bytes) will
+be intercepted and forwarded to user space. User space can use this
+mechanism e.g. to realize 2-byte software breakpoints. The kernel will
+not inject an operating exception for these instructions, user space has
+to take care of that.
+
+This capability can be enabled dynamically even if VCPUs were already
+created and are running.
+
 8. Other capabilities.
 ----------------------

@@ -4,16 +4,22 @@ ARM Virtual Generic Interrupt Controller (VGIC)
 Device types supported:
  KVM_DEV_TYPE_ARM_VGIC_V2     ARM Generic Interrupt Controller v2.0
  KVM_DEV_TYPE_ARM_VGIC_V3     ARM Generic Interrupt Controller v3.0
+  KVM_DEV_TYPE_ARM_VGIC_ITS    ARM Interrupt Translation Service Controller

-Only one VGIC instance may be instantiated through either this API or the
-legacy KVM_CREATE_IRQCHIP api.  The created VGIC will act as the VM interrupt
-controller, requiring emulated user-space devices to inject interrupts to the
-VGIC instead of directly to CPUs.
+Only one VGIC instance of the V2/V3 types above may be instantiated through
+either this API or the legacy KVM_CREATE_IRQCHIP api.  The created VGIC will
+act as the VM interrupt controller, requiring emulated user-space devices to
+inject interrupts to the VGIC instead of directly to CPUs.

 Creating a guest GICv3 device requires a host GICv3 as well.
 GICv3 implementations with hardware compatibility support allow a guest GICv2
 as well.

+Creating a virtual ITS controller requires a host GICv3 (but does not depend
+on having physical ITS controllers).
+There can be multiple ITS controllers per guest, each of them has to have
+a separate, non-overlapping MMIO region.
+
 Groups:
  KVM_DEV_ARM_VGIC_GRP_ADDR
  Attributes:
@@ -39,6 +45,13 @@ Groups:
      Only valid for KVM_DEV_TYPE_ARM_VGIC_V3.
      This address needs to be 64K aligned.

+    KVM_VGIC_V3_ADDR_TYPE_ITS (rw, 64-bit)
+      Base address in the guest physical address space of the GICv3 ITS
+      control register frame. The ITS allows MSI(-X) interrupts to be
+      injected into guests. This extension is optional. If the kernel
+      does not support the ITS, the call returns -ENODEV.
+      Only valid for KVM_DEV_TYPE_ARM_VGIC_ITS.
+      This address needs to be 64K aligned and the region covers 128K.

  KVM_DEV_ARM_VGIC_GRP_DIST_REGS
  Attributes:
@@ -109,8 +122,8 @@ Groups:
  KVM_DEV_ARM_VGIC_GRP_CTRL
  Attributes:
    KVM_DEV_ARM_VGIC_CTRL_INIT
-      request the initialization of the VGIC, no additional parameter in
-      kvm_device_attr.addr.
+      request the initialization of the VGIC or ITS, no additional parameter
+      in kvm_device_attr.addr.
  Errors:
    -ENXIO: VGIC not properly configured as required prior to calling
     this attribute
@@ -20,7 +20,8 @@ Enables Collaborative Memory Management Assist (CMMA) for the virtual machine.

 1.2. ATTRIBUTE: KVM_S390_VM_MEM_CLR_CMMA
 Parameters: none
-Returns: 0
+Returns: -EINVAL if CMMA was not enabled
+         0 otherwise

 Clear the CMMA status for all guest pages, so any pages the guest marked
 as unused are again used any may not be reclaimed by the host.
@@ -85,6 +86,90 @@ Returns:    -EBUSY in case 1 or more vcpus are already activated (only in write
 	    -ENOMEM if not enough memory is available to process the ioctl
 	    0 in case of success

+2.3. ATTRIBUTE: KVM_S390_VM_CPU_MACHINE_FEAT (r/o)
+
+Allows user space to retrieve available cpu features. A feature is available if
+provided by the hardware and supported by kvm. In theory, cpu features could
+even be completely emulated by kvm.
+
+struct kvm_s390_vm_cpu_feat {
+        __u64 feat[16]; # Bitmap (1 = feature available), MSB 0 bit numbering
+};
+
+Parameters: address of a buffer to load the feature list from.
+Returns:    -EFAULT if the given address is not accessible from kernel space.
+	    0 in case of success.
+
+2.4. ATTRIBUTE: KVM_S390_VM_CPU_PROCESSOR_FEAT (r/w)
+
+Allows user space to retrieve or change enabled cpu features for all VCPUs of a
+VM. Features that are not available cannot be enabled.
+
+See 2.3. for a description of the parameter struct.
+
+Parameters: address of a buffer to store/load the feature list from.
+Returns:    -EFAULT if the given address is not accessible from kernel space.
+	    -EINVAL if a cpu feature that is not available is to be enabled.
+	    -EBUSY if at least one VCPU has already been defined.
+	    0 in case of success.
+
+2.5. ATTRIBUTE: KVM_S390_VM_CPU_MACHINE_SUBFUNC (r/o)
+
+Allows user space to retrieve available cpu subfunctions without any filtering
+done by a set IBC. These subfunctions are indicated to the guest VCPU via
+query or "test bit" subfunctions and used e.g. by cpacf functions, plo and ptff.
+
+A subfunction block is only valid if KVM_S390_VM_CPU_MACHINE contains the
+STFL(E) bit introducing the affected instruction. If the affected instruction
+indicates subfunctions via a "query subfunction", the response block is
+contained in the returned struct. If the affected instruction
+indicates subfunctions via a "test bit" mechanism, the subfunction codes are
+contained in the returned struct in MSB 0 bit numbering.
+
+struct kvm_s390_vm_cpu_subfunc {
+       u8 plo[32];           # always valid (ESA/390 feature)
+       u8 ptff[16];          # valid with TOD-clock steering
+       u8 kmac[16];          # valid with Message-Security-Assist
+       u8 kmc[16];           # valid with Message-Security-Assist
+       u8 km[16];            # valid with Message-Security-Assist
+       u8 kimd[16];          # valid with Message-Security-Assist
+       u8 klmd[16];          # valid with Message-Security-Assist
+       u8 pckmo[16];         # valid with Message-Security-Assist-Extension 3
+       u8 kmctr[16];         # valid with Message-Security-Assist-Extension 4
+       u8 kmf[16];           # valid with Message-Security-Assist-Extension 4
+       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
+};
+
+Parameters: address of a buffer to load the subfunction blocks from.
+Returns:    -EFAULT if the given address is not accessible from kernel space.
+	    0 in case of success.
+
+2.6. ATTRIBUTE: KVM_S390_VM_CPU_PROCESSOR_SUBFUNC (r/w)
+
+Allows user space to retrieve or change cpu subfunctions to be indicated for
+all VCPUs of a VM. This attribute will only be available if kernel and
+hardware support are in place.
+
+The kernel uses the configured subfunction blocks for indication to
+the guest. A subfunction block will only be used if the associated STFL(E) bit
+has not been disabled by user space (so the instruction to be queried is
+actually available for the guest).
+
+As long as no data has been written, a read will fail. The IBC will be used
+to determine available subfunctions in this case, this will guarantee backward
+compatibility.
+
+See 2.5. for a description of the parameter struct.
+
+Parameters: address of a buffer to store/load the subfunction blocks from.
+Returns:    -EFAULT if the given address is not accessible from kernel space.
+	    -EINVAL when reading, if there was no write yet.
+	    -EBUSY if at least one VCPU has already been defined.
+	    0 in case of success.
+
 3. GROUP: KVM_S390_VM_TOD
 Architectures: s390

@@ -89,7 +89,7 @@ In mmu_spte_clear_track_bits():
   old_spte = *spte;

   /* 'if' condition is satisfied. */
-   if (old_spte.Accssed == 1 &&
+   if (old_spte.Accessed == 1 &&
        old_spte.W == 0)
      spte = 0ull;
                                         on fast page fault path:
@@ -102,7 +102,7 @@ In mmu_spte_clear_track_bits():
      old_spte = xchg(spte, 0ull)


-   if (old_spte.Accssed == 1)
+   if (old_spte.Accessed == 1)
      kvm_set_pfn_accessed(spte.pfn);
   if (old_spte.Dirty == 1)
      kvm_set_pfn_dirty(spte.pfn);
@@ -66,6 +66,8 @@ extern void __kvm_tlb_flush_vmid(struct kvm *kvm);
 extern int __kvm_vcpu_run(struct kvm_vcpu *vcpu);

 extern void __init_stage2_translation(void);
+
+extern void __kvm_hyp_reset(unsigned long);
 #endif

 #endif /* __ARM_KVM_ASM_H__ */
@@ -241,8 +241,7 @@ int kvm_arm_coproc_set_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *);
 int handle_exit(struct kvm_vcpu *vcpu, struct kvm_run *run,
 		int exception_index);

-static inline void __cpu_init_hyp_mode(phys_addr_t boot_pgd_ptr,
-				       phys_addr_t pgd_ptr,
+static inline void __cpu_init_hyp_mode(phys_addr_t pgd_ptr,
 				       unsigned long hyp_stack_ptr,
 				       unsigned long vector_ptr)
 {
@@ -251,18 +250,13 @@ static inline void __cpu_init_hyp_mode(phys_addr_t boot_pgd_ptr,
 	 * code. The init code doesn't need to preserve these
 	 * registers as r0-r3 are already callee saved according to
 	 * the AAPCS.
-	 * Note that we slightly misuse the prototype by casing the
+	 * Note that we slightly misuse the prototype by casting the
 	 * stack pointer to a void *.
-	 *
-	 * We don't have enough registers to perform the full init in
-	 * one go.  Install the boot PGD first, and then install the
-	 * runtime PGD, stack pointer and vectors. The PGDs are always
-	 * passed as the third argument, in order to be passed into
-	 * r2-r3 to the init code (yes, this is compliant with the
-	 * PCS!).
-	 */

-	kvm_call_hyp(NULL, 0, boot_pgd_ptr);
+	 * The PGDs are always passed as the third argument, in order
+	 * to be passed into r2-r3 to the init code (yes, this is
+	 * compliant with the PCS!).
+	 */

 	kvm_call_hyp((void*)hyp_stack_ptr, vector_ptr, pgd_ptr);
 }
@@ -272,16 +266,13 @@ static inline void __cpu_init_stage2(void)
 	kvm_call_hyp(__init_stage2_translation);
 }

-static inline void __cpu_reset_hyp_mode(phys_addr_t boot_pgd_ptr,
+static inline void __cpu_reset_hyp_mode(unsigned long vector_ptr,
 					phys_addr_t phys_idmap_start)
 {
-	/*
-	 * TODO
-	 * kvm_call_reset(boot_pgd_ptr, phys_idmap_start);
-	 */
+	kvm_call_hyp((void *)virt_to_idmap(__kvm_hyp_reset), vector_ptr);
 }

-static inline int kvm_arch_dev_ioctl_check_extension(long ext)
+static inline int kvm_arch_dev_ioctl_check_extension(struct kvm *kvm, long ext)
 {
 	return 0;
 }
@@ -25,9 +25,6 @@

 #define __hyp_text __section(.hyp.text) notrace

-#define kern_hyp_va(v) (v)
-#define hyp_kern_va(v) (v)
-
 #define __ACCESS_CP15(CRn, Op1, CRm, Op2)	\
 	"mrc", "mcr", __stringify(p15, Op1, %0, CRn, CRm, Op2), u32
 #define __ACCESS_CP15_64(Op1, CRm)		\
@@ -26,16 +26,7 @@
 * We directly use the kernel VA for the HYP, as we can directly share
 * the mapping (HTTBR "covers" TTBR1).
 */
-#define HYP_PAGE_OFFSET_MASK	UL(~0)
-#define HYP_PAGE_OFFSET		PAGE_OFFSET
-#define KERN_TO_HYP(kva)	(kva)
-
-/*
- * Our virtual mapping for the boot-time MMU-enable code. Must be
- * shared across all the page-tables. Conveniently, we use the vectors
- * page, where no kernel data will ever be shared with HYP.
- */
-#define TRAMPOLINE_VA		UL(CONFIG_VECTORS_BASE)
+#define kern_hyp_va(kva)	(kva)

 /*
 * KVM_MMU_CACHE_MIN_PAGES is the number of stage2 page table translation levels.
@@ -49,9 +40,8 @@
 #include <asm/pgalloc.h>
 #include <asm/stage2_pgtable.h>

-int create_hyp_mappings(void *from, void *to);
+int create_hyp_mappings(void *from, void *to, pgprot_t prot);
 int create_hyp_io_mappings(void *from, void *to, phys_addr_t);
-void free_boot_hyp_pgd(void);
 void free_hyp_pgds(void);

 void stage2_unmap_vm(struct kvm *kvm);
@@ -65,7 +55,6 @@ int kvm_handle_guest_abort(struct kvm_vcpu *vcpu, struct kvm_run *run);
 void kvm_mmu_free_memory_caches(struct kvm_vcpu *vcpu);

 phys_addr_t kvm_mmu_get_httbr(void);
-phys_addr_t kvm_mmu_get_boot_httbr(void);
 phys_addr_t kvm_get_idmap_vector(void);
 phys_addr_t kvm_get_idmap_start(void);
 int kvm_mmu_init(void);
@@ -97,7 +97,9 @@ extern pgprot_t		pgprot_s2_device;
 #define PAGE_READONLY_EXEC	_MOD_PROT(pgprot_user, L_PTE_USER | L_PTE_RDONLY)
 #define PAGE_KERNEL		_MOD_PROT(pgprot_kernel, L_PTE_XN)
 #define PAGE_KERNEL_EXEC	pgprot_kernel
-#define PAGE_HYP		_MOD_PROT(pgprot_kernel, L_PTE_HYP)
+#define PAGE_HYP		_MOD_PROT(pgprot_kernel, L_PTE_HYP | L_PTE_XN)
+#define PAGE_HYP_EXEC		_MOD_PROT(pgprot_kernel, L_PTE_HYP | L_PTE_RDONLY)
+#define PAGE_HYP_RO		_MOD_PROT(pgprot_kernel, L_PTE_HYP | L_PTE_RDONLY | L_PTE_XN)
 #define PAGE_HYP_DEVICE		_MOD_PROT(pgprot_hyp_device, L_PTE_HYP)
 #define PAGE_S2			_MOD_PROT(pgprot_s2, L_PTE_S2_RDONLY)
 #define PAGE_S2_DEVICE		_MOD_PROT(pgprot_s2_device, L_PTE_S2_RDONLY)
@@ -80,6 +80,10 @@ static inline bool is_kernel_in_hyp_mode(void)
 	return false;
 }

+/* The section containing the hypervisor idmap text */
+extern char __hyp_idmap_text_start[];
+extern char __hyp_idmap_text_end[];
+
 /* The section containing the hypervisor text */
 extern char __hyp_text_start[];
 extern char __hyp_text_end[];
@@ -46,13 +46,6 @@ config KVM_ARM_HOST
 	---help---
 	  Provides host support for ARM processors.

-config KVM_NEW_VGIC
-	bool "New VGIC implementation"
-	depends on KVM
-	default y
-	---help---
-	  uses the new VGIC implementation
-
 source drivers/vhost/Kconfig

 endif # VIRTUALIZATION
@@ -22,7 +22,6 @@ obj-y += kvm-arm.o init.o interrupts.o
 obj-y += arm.o handle_exit.o guest.o mmu.o emulate.o reset.o
 obj-y += coproc.o coproc_a15.o coproc_a7.o mmio.o psci.o perf.o

-ifeq ($(CONFIG_KVM_NEW_VGIC),y)
 obj-y += $(KVM)/arm/vgic/vgic.o
 obj-y += $(KVM)/arm/vgic/vgic-init.o
 obj-y += $(KVM)/arm/vgic/vgic-irqfd.o
@@ -30,9 +29,4 @@ obj-y += $(KVM)/arm/vgic/vgic-v2.o
 obj-y += $(KVM)/arm/vgic/vgic-mmio.o
 obj-y += $(KVM)/arm/vgic/vgic-mmio-v2.o
 obj-y += $(KVM)/arm/vgic/vgic-kvm-device.o
-else
-obj-y += $(KVM)/arm/vgic.o
-obj-y += $(KVM)/arm/vgic-v2.o
-obj-y += $(KVM)/arm/vgic-v2-emul.o
-endif
 obj-y += $(KVM)/arm/arch_timer.o
@@ -20,6 +20,7 @@
 #include <linux/errno.h>
 #include <linux/err.h>
 #include <linux/kvm_host.h>
+#include <linux/list.h>
 #include <linux/module.h>
 #include <linux/vmalloc.h>
 #include <linux/fs.h>
@@ -122,7 +123,7 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
 	if (ret)
 		goto out_fail_alloc;

-	ret = create_hyp_mappings(kvm, kvm + 1);
+	ret = create_hyp_mappings(kvm, kvm + 1, PAGE_HYP);
 	if (ret)
 		goto out_free_stage2_pgd;

@@ -201,7 +202,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 		r = KVM_MAX_VCPUS;
 		break;
 	default:
-		r = kvm_arch_dev_ioctl_check_extension(ext);
+		r = kvm_arch_dev_ioctl_check_extension(kvm, ext);
 		break;
 	}
 	return r;
@@ -239,7 +240,7 @@ struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm, unsigned int id)
 	if (err)
 		goto free_vcpu;

-	err = create_hyp_mappings(vcpu, vcpu + 1);
+	err = create_hyp_mappings(vcpu, vcpu + 1, PAGE_HYP);
 	if (err)
 		goto vcpu_uninit;

@@ -377,7 +378,7 @@ void force_vm_exit(const cpumask_t *mask)

 /**
 * need_new_vmid_gen - check that the VMID is still valid
- * @kvm: The VM's VMID to checkt
+ * @kvm: The VM's VMID to check
 *
 * return true if there is a new generation of VMIDs being used
 *
@@ -616,7 +617,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run)
 		 * Enter the guest
 		 */
 		trace_kvm_entry(*vcpu_pc(vcpu));
-		__kvm_guest_enter();
+		guest_enter_irqoff();
 		vcpu->mode = IN_GUEST_MODE;

 		ret = kvm_call_hyp(__kvm_vcpu_run, vcpu);
@@ -642,14 +643,14 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run)
 		local_irq_enable();

 		/*
-		 * We do local_irq_enable() before calling kvm_guest_exit() so
+		 * We do local_irq_enable() before calling guest_exit() so
 		 * that if a timer interrupt hits while running the guest we
 		 * account that tick as being spent in the guest.  We enable
-		 * preemption after calling kvm_guest_exit() so that if we get
+		 * preemption after calling guest_exit() so that if we get
 		 * preempted we make sure ticks after that is not counted as
 		 * guest time.
 		 */
-		kvm_guest_exit();
+		guest_exit();
 		trace_kvm_exit(ret, kvm_vcpu_trap_get_class(vcpu), *vcpu_pc(vcpu));

 		/*
@@ -1039,7 +1040,6 @@ long kvm_arch_vm_ioctl(struct file *filp,

 static void cpu_init_hyp_mode(void *dummy)
 {
-	phys_addr_t boot_pgd_ptr;
 	phys_addr_t pgd_ptr;
 	unsigned long hyp_stack_ptr;
 	unsigned long stack_page;
@@ -1048,13 +1048,12 @@ static void cpu_init_hyp_mode(void *dummy)
 	/* Switch from the HYP stub to our own HYP init vector */
 	__hyp_set_vectors(kvm_get_idmap_vector());

-	boot_pgd_ptr = kvm_mmu_get_boot_httbr();
 	pgd_ptr = kvm_mmu_get_httbr();
 	stack_page = __this_cpu_read(kvm_arm_hyp_stack_page);
 	hyp_stack_ptr = stack_page + PAGE_SIZE;
 	vector_ptr = (unsigned long)kvm_ksym_ref(__kvm_hyp_vector);

-	__cpu_init_hyp_mode(boot_pgd_ptr, pgd_ptr, hyp_stack_ptr, vector_ptr);
+	__cpu_init_hyp_mode(pgd_ptr, hyp_stack_ptr, vector_ptr);
 	__cpu_init_stage2();

 	kvm_arm_init_debug();
@@ -1076,15 +1075,9 @@ static void cpu_hyp_reinit(void)

 static void cpu_hyp_reset(void)
 {
-	phys_addr_t boot_pgd_ptr;
-	phys_addr_t phys_idmap_start;
-
-	if (!is_kernel_in_hyp_mode()) {
-		boot_pgd_ptr = kvm_mmu_get_boot_httbr();
-		phys_idmap_start = kvm_get_idmap_start();
-
-		__cpu_reset_hyp_mode(boot_pgd_ptr, phys_idmap_start);
-	}
+	if (!is_kernel_in_hyp_mode())
+		__cpu_reset_hyp_mode(hyp_default_vectors,
+				     kvm_get_idmap_start());
 }

 static void _kvm_arch_hardware_enable(void *discard)
@@ -1294,14 +1287,14 @@ static int init_hyp_mode(void)
 	 * Map the Hyp-code called directly from the host
 	 */
 	err = create_hyp_mappings(kvm_ksym_ref(__hyp_text_start),
-				  kvm_ksym_ref(__hyp_text_end));
+				  kvm_ksym_ref(__hyp_text_end), PAGE_HYP_EXEC);
 	if (err) {
 		kvm_err("Cannot map world-switch code\n");
 		goto out_err;
 	}

 	err = create_hyp_mappings(kvm_ksym_ref(__start_rodata),
-				  kvm_ksym_ref(__end_rodata));
+				  kvm_ksym_ref(__end_rodata), PAGE_HYP_RO);
 	if (err) {
 		kvm_err("Cannot map rodata section\n");
 		goto out_err;
@@ -1312,7 +1305,8 @@ static int init_hyp_mode(void)
 	 */
 	for_each_possible_cpu(cpu) {
 		char *stack_page = (char *)per_cpu(kvm_arm_hyp_stack_page, cpu);
-		err = create_hyp_mappings(stack_page, stack_page + PAGE_SIZE);
+		err = create_hyp_mappings(stack_page, stack_page + PAGE_SIZE,
+					  PAGE_HYP);

 		if (err) {
 			kvm_err("Cannot map hyp stack\n");
@@ -1324,7 +1318,7 @@ static int init_hyp_mode(void)
 		kvm_cpu_context_t *cpu_ctxt;

 		cpu_ctxt = per_cpu_ptr(kvm_host_cpu_state, cpu);
-		err = create_hyp_mappings(cpu_ctxt, cpu_ctxt + 1);
+		err = create_hyp_mappings(cpu_ctxt, cpu_ctxt + 1, PAGE_HYP);

 		if (err) {
 			kvm_err("Cannot map host CPU state: %d\n", err);
@@ -1332,10 +1326,6 @@ static int init_hyp_mode(void)
 		}
 	}

-#ifndef CONFIG_HOTPLUG_CPU
-	free_boot_hyp_pgd();
-#endif
-
 	/* set size of VMID supported by CPU */
 	kvm_vmid_bits = kvm_get_vmid_bits();
 	kvm_info("%d-bit VMID\n", kvm_vmid_bits);
@@ -210,7 +210,7 @@ bool kvm_condition_valid(struct kvm_vcpu *vcpu)
 * @vcpu:	The VCPU pointer
 *
 * When exceptions occur while instructions are executed in Thumb IF-THEN
- * blocks, the ITSTATE field of the CPSR is not advanved (updated), so we have
+ * blocks, the ITSTATE field of the CPSR is not advanced (updated), so we have
 * to do this little bit of work manually. The fields map like this:
 *
 * IT[7:0] -> CPSR[26:25],CPSR[15:10]
@@ -182,7 +182,7 @@ unsigned long kvm_arm_num_regs(struct kvm_vcpu *vcpu)
 /**
 * kvm_arm_copy_reg_indices - get indices of all registers.
 *
- * We do core registers right here, then we apppend coproc regs.
+ * We do core registers right here, then we append coproc regs.
 */
 int kvm_arm_copy_reg_indices(struct kvm_vcpu *vcpu, u64 __user *uindices)
 {
@@ -32,23 +32,13 @@
 *       r2,r3 = Hypervisor pgd pointer
 *
 * The init scenario is:
- * - We jump in HYP with four parameters: boot HYP pgd, runtime HYP pgd,
- *   runtime stack, runtime vectors
- * - Enable the MMU with the boot pgd
- * - Jump to a target into the trampoline page (remember, this is the same
- *   physical page!)
- * - Now switch to the runtime pgd (same VA, and still the same physical
- *   page!)
+ * - We jump in HYP with 3 parameters: runtime HYP pgd, runtime stack,
+ *   runtime vectors
 * - Invalidate TLBs
 * - Set stack and vectors
+ * - Setup the page tables
+ * - Enable the MMU
 * - Profit! (or eret, if you only care about the code).
- *
- * As we only have four registers available to pass parameters (and we
- * need six), we split the init in two phases:
- * - Phase 1: r0 = 0, r1 = 0, r2,r3 contain the boot PGD.
- *   Provides the basic HYP init, and enable the MMU.
- * - Phase 2: r0 = ToS, r1 = vectors, r2,r3 contain the runtime PGD.
- *   Switches to the runtime PGD, set stack and vectors.
 */

 	.text
@@ -68,8 +58,11 @@ __kvm_hyp_init:
 	W(b)	.

 __do_hyp_init:
-	cmp	r0, #0			@ We have a SP?
-	bne	phase2			@ Yes, second stage init
+	@ Set stack pointer
+	mov	sp, r0
+
+	@ Set HVBAR to point to the HYP vectors
+	mcr	p15, 4, r1, c12, c0, 0	@ HVBAR

 	@ Set the HTTBR to point to the hypervisor PGD pointer passed
 	mcrr	p15, 4, rr_lo_hi(r2, r3), c2
@@ -114,34 +107,25 @@ __do_hyp_init:
 THUMB(	ldr	r2, =(HSCTLR_M | HSCTLR_A | HSCTLR_TE)		)
 	orr	r1, r1, r2
 	orr	r0, r0, r1
-	isb
 	mcr	p15, 4, r0, c1, c0, 0	@ HSCR
-
-	@ End of init phase-1
-	eret
-
-phase2:
-	@ Set stack pointer
-	mov	sp, r0
-
-	@ Set HVBAR to point to the HYP vectors
-	mcr	p15, 4, r1, c12, c0, 0	@ HVBAR
-
-	@ Jump to the trampoline page
-	ldr	r0, =TRAMPOLINE_VA
-	adr	r1, target
-	bfi	r0, r1, #0, #PAGE_SHIFT
-	ret	r0
-
-target:	@ We're now in the trampoline code, switch page tables
-	mcrr	p15, 4, rr_lo_hi(r2, r3), c2
 	isb

-	@ Invalidate the old TLBs
-	mcr	p15, 4, r0, c8, c7, 0	@ TLBIALLH
-	dsb	ish
+	eret
+
+	@ r0 : stub vectors address
+ENTRY(__kvm_hyp_reset)
+	/* We're now in idmap, disable MMU */
+	mrc	p15, 4, r1, c1, c0, 0	@ HSCTLR
+	ldr	r2, =(HSCTLR_M | HSCTLR_A | HSCTLR_C | HSCTLR_I)
+	bic	r1, r1, r2
+	mcr	p15, 4, r1, c1, c0, 0	@ HSCTLR
+
+	/* Install stub vectors */
+	mcr	p15, 4, r0, c12, c0, 0	@ HVBAR
+	isb

 	eret
+ENDPROC(__kvm_hyp_reset)

 	.ltorg

@@ -32,8 +32,6 @@

 #include "trace.h"

-extern char  __hyp_idmap_text_start[], __hyp_idmap_text_end[];
-
 static pgd_t *boot_hyp_pgd;
 static pgd_t *hyp_pgd;
 static pgd_t *merged_hyp_pgd;
@@ -483,28 +481,6 @@ static void unmap_hyp_range(pgd_t *pgdp, phys_addr_t start, u64 size)
 	} while (pgd++, addr = next, addr != end);
 }

-/**
- * free_boot_hyp_pgd - free HYP boot page tables
- *
- * Free the HYP boot page tables. The bounce page is also freed.
- */
-void free_boot_hyp_pgd(void)
-{
-	mutex_lock(&kvm_hyp_pgd_mutex);
-
-	if (boot_hyp_pgd) {
-		unmap_hyp_range(boot_hyp_pgd, hyp_idmap_start, PAGE_SIZE);
-		unmap_hyp_range(boot_hyp_pgd, TRAMPOLINE_VA, PAGE_SIZE);
-		free_pages((unsigned long)boot_hyp_pgd, hyp_pgd_order);
-		boot_hyp_pgd = NULL;
-	}
-
-	if (hyp_pgd)
-		unmap_hyp_range(hyp_pgd, TRAMPOLINE_VA, PAGE_SIZE);
-
-	mutex_unlock(&kvm_hyp_pgd_mutex);
-}
-
 /**
 * free_hyp_pgds - free Hyp-mode page tables
 *
@@ -519,15 +495,20 @@ void free_hyp_pgds(void)
 {
 	unsigned long addr;

-	free_boot_hyp_pgd();
-
 	mutex_lock(&kvm_hyp_pgd_mutex);

+	if (boot_hyp_pgd) {
+		unmap_hyp_range(boot_hyp_pgd, hyp_idmap_start, PAGE_SIZE);
+		free_pages((unsigned long)boot_hyp_pgd, hyp_pgd_order);
+		boot_hyp_pgd = NULL;
+	}
+
 	if (hyp_pgd) {
+		unmap_hyp_range(hyp_pgd, hyp_idmap_start, PAGE_SIZE);
 		for (addr = PAGE_OFFSET; virt_addr_valid(addr); addr += PGDIR_SIZE)
-			unmap_hyp_range(hyp_pgd, KERN_TO_HYP(addr), PGDIR_SIZE);
+			unmap_hyp_range(hyp_pgd, kern_hyp_va(addr), PGDIR_SIZE);
 		for (addr = VMALLOC_START; is_vmalloc_addr((void*)addr); addr += PGDIR_SIZE)
-			unmap_hyp_range(hyp_pgd, KERN_TO_HYP(addr), PGDIR_SIZE);
+			unmap_hyp_range(hyp_pgd, kern_hyp_va(addr), PGDIR_SIZE);

 		free_pages((unsigned long)hyp_pgd, hyp_pgd_order);
 		hyp_pgd = NULL;
@@ -679,17 +660,18 @@ static phys_addr_t kvm_kaddr_to_phys(void *kaddr)
 * create_hyp_mappings - duplicate a kernel virtual address range in Hyp mode
 * @from:	The virtual kernel start address of the range
 * @to:		The virtual kernel end address of the range (exclusive)
+ * @prot:	The protection to be applied to this range
 *
 * The same virtual address as the kernel virtual address is also used
 * in Hyp-mode mapping (modulo HYP_PAGE_OFFSET) to the same underlying
 * physical pages.
 */
-int create_hyp_mappings(void *from, void *to)
+int create_hyp_mappings(void *from, void *to, pgprot_t prot)
 {
 	phys_addr_t phys_addr;
 	unsigned long virt_addr;
-	unsigned long start = KERN_TO_HYP((unsigned long)from);
-	unsigned long end = KERN_TO_HYP((unsigned long)to);
+	unsigned long start = kern_hyp_va((unsigned long)from);
+	unsigned long end = kern_hyp_va((unsigned long)to);

 	if (is_kernel_in_hyp_mode())
 		return 0;
@@ -704,7 +686,7 @@ int create_hyp_mappings(void *from, void *to)
 		err = __create_hyp_mappings(hyp_pgd, virt_addr,
 					    virt_addr + PAGE_SIZE,
 					    __phys_to_pfn(phys_addr),
-					    PAGE_HYP);
+					    prot);
 		if (err)
 			return err;
 	}
@@ -723,8 +705,8 @@ int create_hyp_mappings(void *from, void *to)
 */
 int create_hyp_io_mappings(void *from, void *to, phys_addr_t phys_addr)
 {
-	unsigned long start = KERN_TO_HYP((unsigned long)from);
-	unsigned long end = KERN_TO_HYP((unsigned long)to);
+	unsigned long start = kern_hyp_va((unsigned long)from);
+	unsigned long end = kern_hyp_va((unsigned long)to);

 	if (is_kernel_in_hyp_mode())
 		return 0;
@@ -1687,14 +1669,6 @@ phys_addr_t kvm_mmu_get_httbr(void)
 		return virt_to_phys(hyp_pgd);
 }

-phys_addr_t kvm_mmu_get_boot_httbr(void)
-{
-	if (__kvm_cpu_uses_extended_idmap())
-		return virt_to_phys(merged_hyp_pgd);
-	else
-		return virt_to_phys(boot_hyp_pgd);
-}
-
 phys_addr_t kvm_get_idmap_vector(void)
 {
 	return hyp_idmap_vector;
@@ -1705,6 +1679,22 @@ phys_addr_t kvm_get_idmap_start(void)
 	return hyp_idmap_start;
 }

+static int kvm_map_idmap_text(pgd_t *pgd)
+{
+	int err;
+
+	/* Create the idmap in the boot page tables */
+	err = 	__create_hyp_mappings(pgd,
+				      hyp_idmap_start, hyp_idmap_end,
+				      __phys_to_pfn(hyp_idmap_start),
+				      PAGE_HYP_EXEC);
+	if (err)
+		kvm_err("Failed to idmap %lx-%lx\n",
+			hyp_idmap_start, hyp_idmap_end);
+
+	return err;
+}
+
 int kvm_mmu_init(void)
 {
 	int err;
@@ -1719,28 +1709,41 @@ int kvm_mmu_init(void)
 	 */
 	BUG_ON((hyp_idmap_start ^ (hyp_idmap_end - 1)) & PAGE_MASK);

-	hyp_pgd = (pgd_t *)__get_free_pages(GFP_KERNEL | __GFP_ZERO, hyp_pgd_order);
-	boot_hyp_pgd = (pgd_t *)__get_free_pages(GFP_KERNEL | __GFP_ZERO, hyp_pgd_order);
+	kvm_info("IDMAP page: %lx\n", hyp_idmap_start);
+	kvm_info("HYP VA range: %lx:%lx\n",
+		 kern_hyp_va(PAGE_OFFSET), kern_hyp_va(~0UL));

-	if (!hyp_pgd || !boot_hyp_pgd) {
+	if (hyp_idmap_start >= kern_hyp_va(PAGE_OFFSET) &&
+	    hyp_idmap_start <  kern_hyp_va(~0UL)) {
+		/*
+		 * The idmap page is intersecting with the VA space,
+		 * it is not safe to continue further.
+		 */
+		kvm_err("IDMAP intersecting with HYP VA, unable to continue\n");
+		err = -EINVAL;
+		goto out;
+	}
+
+	hyp_pgd = (pgd_t *)__get_free_pages(GFP_KERNEL | __GFP_ZERO, hyp_pgd_order);
+	if (!hyp_pgd) {
 		kvm_err("Hyp mode PGD not allocated\n");
 		err = -ENOMEM;
 		goto out;
 	}

-	/* Create the idmap in the boot page tables */
-	err = 	__create_hyp_mappings(boot_hyp_pgd,
-				      hyp_idmap_start, hyp_idmap_end,
-				      __phys_to_pfn(hyp_idmap_start),
-				      PAGE_HYP);
-
-	if (err) {
-		kvm_err("Failed to idmap %lx-%lx\n",
-			hyp_idmap_start, hyp_idmap_end);
-		goto out;
-	}
-
 	if (__kvm_cpu_uses_extended_idmap()) {
+		boot_hyp_pgd = (pgd_t *)__get_free_pages(GFP_KERNEL | __GFP_ZERO,
+							 hyp_pgd_order);
+		if (!boot_hyp_pgd) {
+			kvm_err("Hyp boot PGD not allocated\n");
+			err = -ENOMEM;
+			goto out;
+		}
+
+		err = kvm_map_idmap_text(boot_hyp_pgd);
+		if (err)
+			goto out;
+
 		merged_hyp_pgd = (pgd_t *)__get_free_page(GFP_KERNEL | __GFP_ZERO);
 		if (!merged_hyp_pgd) {
 			kvm_err("Failed to allocate extra HYP pgd\n");
@@ -1748,29 +1751,10 @@ int kvm_mmu_init(void)
 		}
 		__kvm_extend_hypmap(boot_hyp_pgd, hyp_pgd, merged_hyp_pgd,
 				    hyp_idmap_start);
-		return 0;
-	}
-
-	/* Map the very same page at the trampoline VA */
-	err = 	__create_hyp_mappings(boot_hyp_pgd,
-				      TRAMPOLINE_VA, TRAMPOLINE_VA + PAGE_SIZE,
-				      __phys_to_pfn(hyp_idmap_start),
-				      PAGE_HYP);
-	if (err) {
-		kvm_err("Failed to map trampoline @%lx into boot HYP pgd\n",
-			TRAMPOLINE_VA);
-		goto out;
-	}
-
-	/* Map the same page again into the runtime page tables */
-	err = 	__create_hyp_mappings(hyp_pgd,
-				      TRAMPOLINE_VA, TRAMPOLINE_VA + PAGE_SIZE,
-				      __phys_to_pfn(hyp_idmap_start),
-				      PAGE_HYP);
-	if (err) {
-		kvm_err("Failed to map trampoline @%lx into runtime HYP pgd\n",
-			TRAMPOLINE_VA);
-		goto out;
+	} else {
+		err = kvm_map_idmap_text(hyp_pgd);
+		if (err)
+			goto out;
 	}

 	return 0;
@@ -52,7 +52,7 @@ static const struct kvm_irq_level cortexa_vtimer_irq = {
 * @vcpu: The VCPU pointer
 *
 * This function finds the right table above and sets the registers on the
- * virtual CPU struct to their architectually defined reset values.
+ * virtual CPU struct to their architecturally defined reset values.
 */
 int kvm_reset_vcpu(struct kvm_vcpu *vcpu)
 {
@@ -36,8 +36,9 @@
 #define ARM64_HAS_VIRT_HOST_EXTN		11
 #define ARM64_WORKAROUND_CAVIUM_27456		12
 #define ARM64_HAS_32BIT_EL0			13
+#define ARM64_HYP_OFFSET_LOW			14

-#define ARM64_NCAPS				14
+#define ARM64_NCAPS				15

 #ifndef __ASSEMBLY__

@@ -178,7 +178,7 @@
 /* Hyp System Trap Register */
 #define HSTR_EL2_T(x)	(1 << x)

-/* Hyp Coproccessor Trap Register Shifts */
+/* Hyp Coprocessor Trap Register Shifts */
 #define CPTR_EL2_TFP_SHIFT 10

 /* Hyp Coprocessor Trap Register */
--- a/Show More
+++ b/Show More