Merge tag 'kvm-3.10-1' of git://git.kernel.org/pub/scm/virt/kvm/kvm

Pull kvm updates from Gleb Natapov: "Highlights of the updates are: general: - new emulated device API - legacy device assignment is now optional - irqfd interface is more generic and can be shared between arches x86: - VMCS shadow support and other nested VMX improvements - APIC virtualization and Posted Interrupt hardware support - Optimize mmio spte zapping ppc: - BookE: in-kernel MPIC emulation with irqfd support - Book3S: in-kernel XICS emulation (incomplete) - Book3S: HV: migration fixes - BookE: more debug support preparation - BookE: e6500 support ARM: - reworking of Hyp idmaps s390: - ioeventfd for virtio-ccw And many other bug fixes, cleanups and improvements" * tag 'kvm-3.10-1' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (204 commits) kvm: Add compat_ioctl for device control API KVM: x86: Account for failing enable_irq_window for NMI window request KVM: PPC: Book3S: Add API for in-kernel XICS emulation kvm/ppc/mpic: fix missing unlock in set_base_addr() kvm/ppc: Hold srcu lock when calling kvm_io_bus_read/write kvm/ppc/mpic: remove users kvm/ppc/mpic: fix mmio region lists when multiple guests used kvm/ppc/mpic: remove default routes from documentation kvm: KVM_CAP_IOMMU only available with device assignment ARM: KVM: iterate over all CPUs for CPU compatibility check KVM: ARM: Fix spelling in error message ARM: KVM: define KVM_ARM_MAX_VCPUS unconditionally KVM: ARM: Fix API documentation for ONE_REG encoding ARM: KVM: promote vfp_host pointer to generic host cpu context ARM: KVM: add architecture specific hook for capabilities ARM: KVM: perform HYP initilization for hotplugged CPUs ARM: KVM: switch to a dual-step HYP init code ARM: KVM: rework HYP page table freeing ARM: KVM: enforce maximum size for identity mapped code ARM: KVM: move to a KVM provided HYP idmap ...
2026-05-01 15:00:59 -07:00 · 2013-05-05 14:47:31 -07:00
parent 9e6879460c db6ae61581
commit 01227a889e
110 changed files with 8607 additions and 2355 deletions
@@ -1486,15 +1486,23 @@ struct kvm_ioeventfd {
 	__u8  pad[36];
 };

+For the special case of virtio-ccw devices on s390, the ioevent is matched
+to a subchannel/virtqueue tuple instead.
+
 The following flags are defined:

 #define KVM_IOEVENTFD_FLAG_DATAMATCH (1 << kvm_ioeventfd_flag_nr_datamatch)
 #define KVM_IOEVENTFD_FLAG_PIO       (1 << kvm_ioeventfd_flag_nr_pio)
 #define KVM_IOEVENTFD_FLAG_DEASSIGN  (1 << kvm_ioeventfd_flag_nr_deassign)
+#define KVM_IOEVENTFD_FLAG_VIRTIO_CCW_NOTIFY \
+	(1 << kvm_ioeventfd_flag_nr_virtio_ccw_notify)

 If datamatch flag is set, the event will be signaled only if the written value
 to the registered address is equal to datamatch in struct kvm_ioeventfd.

+For virtio-ccw devices, addr contains the subchannel id and datamatch the
+virtqueue index.
+

 4.60 KVM_DIRTY_TLB

@@ -1780,27 +1788,48 @@ registers, find a list below:
  PPC   | KVM_REG_PPC_VPA_DTL   | 128
  PPC   | KVM_REG_PPC_EPCR	| 32
  PPC   | KVM_REG_PPC_EPR	| 32
+  PPC   | KVM_REG_PPC_TCR	| 32
+  PPC   | KVM_REG_PPC_TSR	| 32
+  PPC   | KVM_REG_PPC_OR_TSR	| 32
+  PPC   | KVM_REG_PPC_CLEAR_TSR	| 32
+  PPC   | KVM_REG_PPC_MAS0	| 32
+  PPC   | KVM_REG_PPC_MAS1	| 32
+  PPC   | KVM_REG_PPC_MAS2	| 64
+  PPC   | KVM_REG_PPC_MAS7_3	| 64
+  PPC   | KVM_REG_PPC_MAS4	| 32
+  PPC   | KVM_REG_PPC_MAS6	| 32
+  PPC   | KVM_REG_PPC_MMUCFG	| 32
+  PPC   | KVM_REG_PPC_TLB0CFG	| 32
+  PPC   | KVM_REG_PPC_TLB1CFG	| 32
+  PPC   | KVM_REG_PPC_TLB2CFG	| 32
+  PPC   | KVM_REG_PPC_TLB3CFG	| 32
+  PPC   | KVM_REG_PPC_TLB0PS	| 32
+  PPC   | KVM_REG_PPC_TLB1PS	| 32
+  PPC   | KVM_REG_PPC_TLB2PS	| 32
+  PPC   | KVM_REG_PPC_TLB3PS	| 32
+  PPC   | KVM_REG_PPC_EPTCFG	| 32
+  PPC   | KVM_REG_PPC_ICP_STATE | 64

 ARM registers are mapped using the lower 32 bits.  The upper 16 of that
 is the register group type, or coprocessor number:

 ARM core registers have the following id bit patterns:
-  0x4002 0000 0010 <index into the kvm_regs struct:16>
+  0x4020 0000 0010 <index into the kvm_regs struct:16>

 ARM 32-bit CP15 registers have the following id bit patterns:
-  0x4002 0000 000F <zero:1> <crn:4> <crm:4> <opc1:4> <opc2:3>
+  0x4020 0000 000F <zero:1> <crn:4> <crm:4> <opc1:4> <opc2:3>

 ARM 64-bit CP15 registers have the following id bit patterns:
-  0x4003 0000 000F <zero:1> <zero:4> <crm:4> <opc1:4> <zero:3>
+  0x4030 0000 000F <zero:1> <zero:4> <crm:4> <opc1:4> <zero:3>

 ARM CCSIDR registers are demultiplexed by CSSELR value:
-  0x4002 0000 0011 00 <csselr:8>
+  0x4020 0000 0011 00 <csselr:8>

 ARM 32-bit VFP control registers have the following id bit patterns:
-  0x4002 0000 0012 1 <regno:12>
+  0x4020 0000 0012 1 <regno:12>

 ARM 64-bit FP registers have the following id bit patterns:
-  0x4002 0000 0012 0 <regno:12>
+  0x4030 0000 0012 0 <regno:12>

 4.69 KVM_GET_ONE_REG

@@ -2161,6 +2190,76 @@ header; first `n_valid' valid entries with contents from the data
 written, then `n_invalid' invalid entries, invalidating any previously
 valid entries found.

+4.79 KVM_CREATE_DEVICE
+
+Capability: KVM_CAP_DEVICE_CTRL
+Type: vm ioctl
+Parameters: struct kvm_create_device (in/out)
+Returns: 0 on success, -1 on error
+Errors:
+  ENODEV: The device type is unknown or unsupported
+  EEXIST: Device already created, and this type of device may not
+          be instantiated multiple times
+
+  Other error conditions may be defined by individual device types or
+  have their standard meanings.
+
+Creates an emulated device in the kernel.  The file descriptor returned
+in fd can be used with KVM_SET/GET/HAS_DEVICE_ATTR.
+
+If the KVM_CREATE_DEVICE_TEST flag is set, only test whether the
+device type is supported (not necessarily whether it can be created
+in the current vm).
+
+Individual devices should not define flags.  Attributes should be used
+for specifying any behavior that is not implied by the device type
+number.
+
+struct kvm_create_device {
+	__u32	type;	/* in: KVM_DEV_TYPE_xxx */
+	__u32	fd;	/* out: device handle */
+	__u32	flags;	/* in: KVM_CREATE_DEVICE_xxx */
+};
+
+4.80 KVM_SET_DEVICE_ATTR/KVM_GET_DEVICE_ATTR
+
+Capability: KVM_CAP_DEVICE_CTRL
+Type: device ioctl
+Parameters: struct kvm_device_attr
+Returns: 0 on success, -1 on error
+Errors:
+  ENXIO:  The group or attribute is unknown/unsupported for this device
+  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)
+
+  Other error conditions may be defined by individual device types.
+
+Gets/sets a specified piece of device configuration and/or state.  The
+semantics are device-specific.  See individual device documentation in
+the "devices" directory.  As with ONE_REG, the size of the data
+transferred is defined by the particular attribute.
+
+struct kvm_device_attr {
+	__u32	flags;		/* no flags currently defined */
+	__u32	group;		/* device-defined */
+	__u64	attr;		/* group-defined */
+	__u64	addr;		/* userspace address of attr data */
+};
+
+4.81 KVM_HAS_DEVICE_ATTR
+
+Capability: KVM_CAP_DEVICE_CTRL
+Type: device ioctl
+Parameters: struct kvm_device_attr
+Returns: 0 on success, -1 on error
+Errors:
+  ENXIO:  The group or attribute is unknown/unsupported for this device
+
+Tests whether a device supports a particular attribute.  A successful
+return indicates the attribute is implemented.  It does not necessarily
+indicate that the attribute can be read or written in the device's
+current state.  "addr" is ignored.

 4.77 KVM_ARM_VCPU_INIT

@@ -2243,6 +2342,25 @@ and distributor interface, the ioctl 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.

+4.82 KVM_PPC_RTAS_DEFINE_TOKEN
+
+Capability: KVM_CAP_PPC_RTAS
+Architectures: ppc
+Type: vm ioctl
+Parameters: struct kvm_rtas_token_args
+Returns: 0 on success, -1 on error
+
+Defines a token value for a RTAS (Run Time Abstraction Services)
+service in order to allow it to be handled in the kernel.  The
+argument struct gives the name of the service, which must be the name
+of a service that has a kernel-side implementation.  If the token
+value is non-zero, it will be associated with that service, and
+subsequent RTAS calls by the guest specifying that token will be
+handled by the kernel.  If the token value is 0, then any token
+associated with the service will be forgotten, and subsequent RTAS
+calls by the guest for that service will be passed to userspace to be
+handled.
+

 5. The kvm_run structure
 ------------------------
@@ -2646,3 +2764,19 @@ to receive the topmost interrupt vector.
 When disabled (args[0] == 0), behavior is as if this facility is unsupported.

 When this capability is enabled, KVM_EXIT_EPR can occur.
+
+6.6 KVM_CAP_IRQ_MPIC
+
+Architectures: ppc
+Parameters: args[0] is the MPIC device fd
+            args[1] is the MPIC CPU number for this vcpu
+
+This capability connects the vcpu to an in-kernel MPIC device.
+
+6.7 KVM_CAP_IRQ_XICS
+
+Architectures: ppc
+Parameters: args[0] is the XICS device fd
+            args[1] is the XICS CPU number (server ID) for this vcpu
+
+This capability connects the vcpu to an in-kernel XICS device.
@@ -0,0 +1 @@
+This directory contains specific device bindings for KVM_CAP_DEVICE_CTRL.
@@ -0,0 +1,53 @@
+MPIC interrupt controller
+=========================
+
+Device types supported:
+  KVM_DEV_TYPE_FSL_MPIC_20     Freescale MPIC v2.0
+  KVM_DEV_TYPE_FSL_MPIC_42     Freescale MPIC v4.2
+
+Only one MPIC instance, of any type, may be instantiated.  The created
+MPIC will act as the system interrupt controller, connecting to each
+vcpu's interrupt inputs.
+
+Groups:
+  KVM_DEV_MPIC_GRP_MISC
+  Attributes:
+    KVM_DEV_MPIC_BASE_ADDR (rw, 64-bit)
+      Base address of the 256 KiB MPIC register space.  Must be
+      naturally aligned.  A value of zero disables the mapping.
+      Reset value is zero.
+
+  KVM_DEV_MPIC_GRP_REGISTER (rw, 32-bit)
+    Access an MPIC register, as if the access were made from the guest.
+    "attr" is the byte offset into the MPIC register space.  Accesses
+    must be 4-byte aligned.
+
+    MSIs may be signaled by using this attribute group to write
+    to the relevant MSIIR.
+
+  KVM_DEV_MPIC_GRP_IRQ_ACTIVE (rw, 32-bit)
+    IRQ input line for each standard openpic source.  0 is inactive and 1
+    is active, regardless of interrupt sense.
+
+    For edge-triggered interrupts:  Writing 1 is considered an activating
+    edge, and writing 0 is ignored.  Reading returns 1 if a previously
+    signaled edge has not been acknowledged, and 0 otherwise.
+
+    "attr" is the IRQ number.  IRQ numbers for standard sources are the
+    byte offset of the relevant IVPR from EIVPR0, divided by 32.
+
+IRQ Routing:
+
+  The MPIC emulation supports IRQ routing. Only a single MPIC device can
+  be instantiated. Once that device has been created, it's available as
+  irqchip id 0.
+
+  This irqchip 0 has 256 interrupt pins, which expose the interrupts in
+  the main array of interrupt sources (a.k.a. "SRC" interrupts).
+
+  The numbering is the same as the MPIC device tree binding -- based on
+  the register offset from the beginning of the sources array, without
+  regard to any subdivisions in chip documentation such as "internal"
+  or "external" interrupts.
+
+  Access to non-SRC interrupts is not implemented through IRQ routing mechanisms.
@@ -0,0 +1,66 @@
+XICS interrupt controller
+
+Device type supported: KVM_DEV_TYPE_XICS
+
+Groups:
+  KVM_DEV_XICS_SOURCES
+  Attributes: One per interrupt source, indexed by the source number.
+
+This device emulates the XICS (eXternal Interrupt Controller
+Specification) defined in PAPR.  The XICS has a set of interrupt
+sources, each identified by a 20-bit source number, and a set of
+Interrupt Control Presentation (ICP) entities, also called "servers",
+each associated with a virtual CPU.
+
+The ICP entities are created by enabling the KVM_CAP_IRQ_ARCH
+capability for each vcpu, specifying KVM_CAP_IRQ_XICS in args[0] and
+the interrupt server number (i.e. the vcpu number from the XICS's
+point of view) in args[1] of the kvm_enable_cap struct.  Each ICP has
+64 bits of state which can be read and written using the
+KVM_GET_ONE_REG and KVM_SET_ONE_REG ioctls on the vcpu.  The 64 bit
+state word has the following bitfields, starting at the
+least-significant end of the word:
+
+* Unused, 16 bits
+
+* Pending interrupt priority, 8 bits
+  Zero is the highest priority, 255 means no interrupt is pending.
+
+* Pending IPI (inter-processor interrupt) priority, 8 bits
+  Zero is the highest priority, 255 means no IPI is pending.
+
+* Pending interrupt source number, 24 bits
+  Zero means no interrupt pending, 2 means an IPI is pending
+
+* Current processor priority, 8 bits
+  Zero is the highest priority, meaning no interrupts can be
+  delivered, and 255 is the lowest priority.
+
+Each source has 64 bits of state that can be read and written using
+the KVM_GET_DEVICE_ATTR and KVM_SET_DEVICE_ATTR ioctls, specifying the
+KVM_DEV_XICS_SOURCES attribute group, with the attribute number being
+the interrupt source number.  The 64 bit state word has the following
+bitfields, starting from the least-significant end of the word:
+
+* Destination (server number), 32 bits
+  This specifies where the interrupt should be sent, and is the
+  interrupt server number specified for the destination vcpu.
+
+* Priority, 8 bits
+  This is the priority specified for this interrupt source, where 0 is
+  the highest priority and 255 is the lowest.  An interrupt with a
+  priority of 255 will never be delivered.
+
+* Level sensitive flag, 1 bit
+  This bit is 1 for a level-sensitive interrupt source, or 0 for
+  edge-sensitive (or MSI).
+
+* Masked flag, 1 bit
+  This bit is set to 1 if the interrupt is masked (cannot be delivered
+  regardless of its priority), for example by the ibm,int-off RTAS
+  call, or 0 if it is not masked.
+
+* Pending flag, 1 bit
+  This bit is 1 if the source has a pending interrupt, otherwise 0.
+
+Only one XICS instance may be created per VM.
@@ -8,7 +8,6 @@
 #define __idmap __section(.idmap.text) noinline notrace

 extern pgd_t *idmap_pgd;
-extern pgd_t *hyp_pgd;

 void setup_mm_for_reboot(void);

@@ -87,7 +87,7 @@ struct kvm_vcpu_fault_info {
 	u32 hyp_pc;		/* PC when exception was taken from Hyp mode */
 };

-typedef struct vfp_hard_struct kvm_kernel_vfp_t;
+typedef struct vfp_hard_struct kvm_cpu_context_t;

 struct kvm_vcpu_arch {
 	struct kvm_regs regs;
@@ -105,8 +105,10 @@ struct kvm_vcpu_arch {
 	struct kvm_vcpu_fault_info fault;

 	/* Floating point registers (VFP and Advanced SIMD/NEON) */
-	kvm_kernel_vfp_t vfp_guest;
-	kvm_kernel_vfp_t *vfp_host;
+	struct vfp_hard_struct vfp_guest;
+
+	/* Host FP context */
+	kvm_cpu_context_t *host_cpu_context;

 	/* VGIC state */
 	struct vgic_cpu vgic_cpu;
@@ -188,23 +190,38 @@ 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(unsigned long long pgd_ptr,
+static inline void __cpu_init_hyp_mode(unsigned long long boot_pgd_ptr,
+				       unsigned long long pgd_ptr,
 				       unsigned long hyp_stack_ptr,
 				       unsigned long vector_ptr)
 {
-	unsigned long pgd_low, pgd_high;
-
-	pgd_low = (pgd_ptr & ((1ULL << 32) - 1));
-	pgd_high = (pgd_ptr >> 32ULL);
-
 	/*
-	 * Call initialization code, and switch to the full blown
-	 * HYP code. The init code doesn't need to preserve these registers as
-	 * r1-r3 and r12 are already callee save according to the AAPCS.
-	 * Note that we slightly misuse the prototype by casing the pgd_low to
-	 * a void *.
+	 * Call initialization code, and switch to the full blown HYP
+	 * 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
+	 * 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((void *)pgd_low, pgd_high, hyp_stack_ptr, vector_ptr);
+
+	kvm_call_hyp(NULL, 0, boot_pgd_ptr);
+
+	kvm_call_hyp((void*)hyp_stack_ptr, vector_ptr, pgd_ptr);
 }

+static inline int kvm_arch_dev_ioctl_check_extension(long ext)
+{
+	return 0;
+}
+
+int kvm_perf_init(void);
+int kvm_perf_teardown(void);
+
 #endif /* __ARM_KVM_HOST_H__ */
@@ -19,21 +19,33 @@
 #ifndef __ARM_KVM_MMU_H__
 #define __ARM_KVM_MMU_H__

-#include <asm/cacheflush.h>
-#include <asm/pgalloc.h>
-#include <asm/idmap.h>
+#include <asm/memory.h>
+#include <asm/page.h>

 /*
 * We directly use the kernel VA for the HYP, as we can directly share
 * the mapping (HTTBR "covers" TTBR1).
 */
-#define HYP_PAGE_OFFSET_MASK	(~0UL)
+#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)
+
+#ifndef __ASSEMBLY__
+
+#include <asm/cacheflush.h>
+#include <asm/pgalloc.h>
+
 int create_hyp_mappings(void *from, void *to);
 int create_hyp_io_mappings(void *from, void *to, phys_addr_t);
-void free_hyp_pmds(void);
+void free_boot_hyp_pgd(void);
+void free_hyp_pgds(void);

 int kvm_alloc_stage2_pgd(struct kvm *kvm);
 void kvm_free_stage2_pgd(struct kvm *kvm);
@@ -45,6 +57,8 @@ 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);
 int kvm_mmu_init(void);
 void kvm_clear_hyp_idmap(void);

@@ -114,4 +128,8 @@ static inline void coherent_icache_guest_page(struct kvm *kvm, gfn_t gfn)
 	}
 }

+#define kvm_flush_dcache_to_poc(a,l)	__cpuc_flush_dcache_area((a), (l))
+
+#endif	/* !__ASSEMBLY__ */
+
 #endif /* __ARM_KVM_MMU_H__ */
@@ -158,7 +158,7 @@ int main(void)
  DEFINE(VCPU_MIDR,		offsetof(struct kvm_vcpu, arch.midr));
  DEFINE(VCPU_CP15,		offsetof(struct kvm_vcpu, arch.cp15));
  DEFINE(VCPU_VFP_GUEST,	offsetof(struct kvm_vcpu, arch.vfp_guest));
-  DEFINE(VCPU_VFP_HOST,		offsetof(struct kvm_vcpu, arch.vfp_host));
+  DEFINE(VCPU_VFP_HOST,		offsetof(struct kvm_vcpu, arch.host_cpu_context));
  DEFINE(VCPU_REGS,		offsetof(struct kvm_vcpu, arch.regs));
  DEFINE(VCPU_USR_REGS,		offsetof(struct kvm_vcpu, arch.regs.usr_regs));
  DEFINE(VCPU_SVC_REGS,		offsetof(struct kvm_vcpu, arch.regs.svc_regs));
@@ -20,7 +20,7 @@
 	VMLINUX_SYMBOL(__idmap_text_start) = .;				\
 	*(.idmap.text)							\
 	VMLINUX_SYMBOL(__idmap_text_end) = .;				\
-	ALIGN_FUNCTION();						\
+	. = ALIGN(32);							\
 	VMLINUX_SYMBOL(__hyp_idmap_text_start) = .;			\
 	*(.hyp.idmap.text)						\
 	VMLINUX_SYMBOL(__hyp_idmap_text_end) = .;
@@ -315,3 +315,8 @@ SECTIONS
 */
 ASSERT((__proc_info_end - __proc_info_begin), "missing CPU support")
 ASSERT((__arch_info_end - __arch_info_begin), "no machine record defined")
+/*
+ * The HYP init code can't be more than a page long.
+ * The above comment applies as well.
+ */
+ASSERT(((__hyp_idmap_text_end - __hyp_idmap_text_start) <= PAGE_SIZE), "HYP init code too big")
@@ -41,9 +41,9 @@ config KVM_ARM_HOST
 	  Provides host support for ARM processors.

 config KVM_ARM_MAX_VCPUS
-	int "Number maximum supported virtual CPUs per VM"
-	depends on KVM_ARM_HOST
-	default 4
+	int "Number maximum supported virtual CPUs per VM" if KVM_ARM_HOST
+	default 4 if KVM_ARM_HOST
+	default 0
 	help
 	  Static number of max supported virtual CPUs per VM.

@@ -18,6 +18,6 @@ kvm-arm-y = $(addprefix ../../../virt/kvm/, kvm_main.o coalesced_mmio.o)

 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 mmio.o psci.o
+obj-y += coproc.o coproc_a15.o mmio.o psci.o perf.o
 obj-$(CONFIG_KVM_ARM_VGIC) += vgic.o
 obj-$(CONFIG_KVM_ARM_TIMER) += arch_timer.o
@@ -22,6 +22,7 @@
 #include <linux/kvm_host.h>
 #include <linux/interrupt.h>

+#include <clocksource/arm_arch_timer.h>
 #include <asm/arch_timer.h>

 #include <asm/kvm_vgic.h>
@@ -64,7 +65,7 @@ static void kvm_timer_inject_irq(struct kvm_vcpu *vcpu)
 {
 	struct arch_timer_cpu *timer = &vcpu->arch.timer_cpu;

-	timer->cntv_ctl |= 1 << 1; /* Mask the interrupt in the guest */
+	timer->cntv_ctl |= ARCH_TIMER_CTRL_IT_MASK;
 	kvm_vgic_inject_irq(vcpu->kvm, vcpu->vcpu_id,
 			    vcpu->arch.timer_cpu.irq->irq,
 			    vcpu->arch.timer_cpu.irq->level);
@@ -133,8 +134,8 @@ void kvm_timer_sync_hwstate(struct kvm_vcpu *vcpu)
 	cycle_t cval, now;
 	u64 ns;

-	/* Check if the timer is enabled and unmasked first */
-	if ((timer->cntv_ctl & 3) != 1)
+	if ((timer->cntv_ctl & ARCH_TIMER_CTRL_IT_MASK) ||
+		!(timer->cntv_ctl & ARCH_TIMER_CTRL_ENABLE))
 		return;

 	cval = timer->cntv_cval;
@@ -16,6 +16,7 @@
 * Foundation, 51 Franklin Street, Fifth Floor, Boston, MA  02110-1301, USA.
 */

+#include <linux/cpu.h>
 #include <linux/errno.h>
 #include <linux/err.h>
 #include <linux/kvm_host.h>
@@ -48,7 +49,7 @@ __asm__(".arch_extension	virt");
 #endif

 static DEFINE_PER_CPU(unsigned long, kvm_arm_hyp_stack_page);
-static kvm_kernel_vfp_t __percpu *kvm_host_vfp_state;
+static kvm_cpu_context_t __percpu *kvm_host_cpu_state;
 static unsigned long hyp_default_vectors;

 /* Per-CPU variable containing the currently running vcpu. */
@@ -206,7 +207,7 @@ int kvm_dev_ioctl_check_extension(long ext)
 		r = KVM_MAX_VCPUS;
 		break;
 	default:
-		r = 0;
+		r = kvm_arch_dev_ioctl_check_extension(ext);
 		break;
 	}
 	return r;
@@ -218,27 +219,18 @@ long kvm_arch_dev_ioctl(struct file *filp,
 	return -EINVAL;
 }

-int kvm_arch_set_memory_region(struct kvm *kvm,
-			       struct kvm_userspace_memory_region *mem,
-			       struct kvm_memory_slot old,
-			       int user_alloc)
-{
-	return 0;
-}
-
 int kvm_arch_prepare_memory_region(struct kvm *kvm,
 				   struct kvm_memory_slot *memslot,
-				   struct kvm_memory_slot old,
 				   struct kvm_userspace_memory_region *mem,
-				   bool user_alloc)
+				   enum kvm_mr_change change)
 {
 	return 0;
 }

 void kvm_arch_commit_memory_region(struct kvm *kvm,
 				   struct kvm_userspace_memory_region *mem,
-				   struct kvm_memory_slot old,
-				   bool user_alloc)
+				   const struct kvm_memory_slot *old,
+				   enum kvm_mr_change change)
 {
 }

@@ -326,7 +318,7 @@ void kvm_arch_vcpu_uninit(struct kvm_vcpu *vcpu)
 void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 {
 	vcpu->cpu = cpu;
-	vcpu->arch.vfp_host = this_cpu_ptr(kvm_host_vfp_state);
+	vcpu->arch.host_cpu_context = this_cpu_ptr(kvm_host_cpu_state);

 	/*
 	 * Check whether this vcpu requires the cache to be flushed on
@@ -639,7 +631,8 @@ static int vcpu_interrupt_line(struct kvm_vcpu *vcpu, int number, bool level)
 	return 0;
 }

-int kvm_vm_ioctl_irq_line(struct kvm *kvm, struct kvm_irq_level *irq_level)
+int kvm_vm_ioctl_irq_line(struct kvm *kvm, struct kvm_irq_level *irq_level,
+			  bool line_status)
 {
 	u32 irq = irq_level->irq;
 	unsigned int irq_type, vcpu_idx, irq_num;
@@ -794,30 +787,48 @@ long kvm_arch_vm_ioctl(struct file *filp,
 	}
 }

-static void cpu_init_hyp_mode(void *vector)
+static void cpu_init_hyp_mode(void *dummy)
 {
+	unsigned long long boot_pgd_ptr;
 	unsigned long long pgd_ptr;
 	unsigned long hyp_stack_ptr;
 	unsigned long stack_page;
 	unsigned long vector_ptr;

 	/* Switch from the HYP stub to our own HYP init vector */
-	__hyp_set_vectors((unsigned long)vector);
+	__hyp_set_vectors(kvm_get_idmap_vector());

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

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

+static int hyp_init_cpu_notify(struct notifier_block *self,
+			       unsigned long action, void *cpu)
+{
+	switch (action) {
+	case CPU_STARTING:
+	case CPU_STARTING_FROZEN:
+		cpu_init_hyp_mode(NULL);
+		break;
+	}
+
+	return NOTIFY_OK;
+}
+
+static struct notifier_block hyp_init_cpu_nb = {
+	.notifier_call = hyp_init_cpu_notify,
+};
+
 /**
 * Inits Hyp-mode on all online CPUs
 */
 static int init_hyp_mode(void)
 {
-	phys_addr_t init_phys_addr;
 	int cpu;
 	int err = 0;

@@ -849,24 +860,6 @@ static int init_hyp_mode(void)
 		per_cpu(kvm_arm_hyp_stack_page, cpu) = stack_page;
 	}

-	/*
-	 * Execute the init code on each CPU.
-	 *
-	 * Note: The stack is not mapped yet, so don't do anything else than
-	 * initializing the hypervisor mode on each CPU using a local stack
-	 * space for temporary storage.
-	 */
-	init_phys_addr = virt_to_phys(__kvm_hyp_init);
-	for_each_online_cpu(cpu) {
-		smp_call_function_single(cpu, cpu_init_hyp_mode,
-					 (void *)(long)init_phys_addr, 1);
-	}
-
-	/*
-	 * Unmap the identity mapping
-	 */
-	kvm_clear_hyp_idmap();
-
 	/*
 	 * Map the Hyp-code called directly from the host
 	 */
@@ -890,33 +883,38 @@ static int init_hyp_mode(void)
 	}

 	/*
-	 * Map the host VFP structures
+	 * Map the host CPU structures
 	 */
-	kvm_host_vfp_state = alloc_percpu(kvm_kernel_vfp_t);
-	if (!kvm_host_vfp_state) {
+	kvm_host_cpu_state = alloc_percpu(kvm_cpu_context_t);
+	if (!kvm_host_cpu_state) {
 		err = -ENOMEM;
-		kvm_err("Cannot allocate host VFP state\n");
+		kvm_err("Cannot allocate host CPU state\n");
 		goto out_free_mappings;
 	}

 	for_each_possible_cpu(cpu) {
-		kvm_kernel_vfp_t *vfp;
+		kvm_cpu_context_t *cpu_ctxt;

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

 		if (err) {
-			kvm_err("Cannot map host VFP state: %d\n", err);
-			goto out_free_vfp;
+			kvm_err("Cannot map host CPU state: %d\n", err);
+			goto out_free_context;
 		}
 	}

+	/*
+	 * Execute the init code on each CPU.
+	 */
+	on_each_cpu(cpu_init_hyp_mode, NULL, 1);
+
 	/*
 	 * Init HYP view of VGIC
 	 */
 	err = kvm_vgic_hyp_init();
 	if (err)
-		goto out_free_vfp;
+		goto out_free_context;

 #ifdef CONFIG_KVM_ARM_VGIC
 		vgic_present = true;
@@ -929,12 +927,19 @@ static int init_hyp_mode(void)
 	if (err)
 		goto out_free_mappings;

+#ifndef CONFIG_HOTPLUG_CPU
+	free_boot_hyp_pgd();
+#endif
+
+	kvm_perf_init();
+
 	kvm_info("Hyp mode initialized successfully\n");
+
 	return 0;
-out_free_vfp:
-	free_percpu(kvm_host_vfp_state);
+out_free_context:
+	free_percpu(kvm_host_cpu_state);
 out_free_mappings:
-	free_hyp_pmds();
+	free_hyp_pgds();
 out_free_stack_pages:
 	for_each_possible_cpu(cpu)
 		free_page(per_cpu(kvm_arm_hyp_stack_page, cpu));
@@ -943,27 +948,42 @@ out_err:
 	return err;
 }

+static void check_kvm_target_cpu(void *ret)
+{
+	*(int *)ret = kvm_target_cpu();
+}
+
 /**
 * Initialize Hyp-mode and memory mappings on all CPUs.
 */
 int kvm_arch_init(void *opaque)
 {
 	int err;
+	int ret, cpu;

 	if (!is_hyp_mode_available()) {
 		kvm_err("HYP mode not available\n");
 		return -ENODEV;
 	}

-	if (kvm_target_cpu() < 0) {
-		kvm_err("Target CPU not supported!\n");
-		return -ENODEV;
+	for_each_online_cpu(cpu) {
+		smp_call_function_single(cpu, check_kvm_target_cpu, &ret, 1);
+		if (ret < 0) {
+			kvm_err("Error, CPU %d not supported!\n", cpu);
+			return -ENODEV;
+		}
 	}

 	err = init_hyp_mode();
 	if (err)
 		goto out_err;

+	err = register_cpu_notifier(&hyp_init_cpu_nb);
+	if (err) {
+		kvm_err("Cannot register HYP init CPU notifier (%d)\n", err);
+		goto out_err;
+	}
+
 	kvm_coproc_table_init();
 	return 0;
 out_err:
@@ -973,6 +993,7 @@ out_err:
 /* NOP: Compiling as a module not supported */
 void kvm_arch_exit(void)
 {
+	kvm_perf_teardown();
 }

 static int arm_init(void)
@@ -21,13 +21,33 @@
 #include <asm/asm-offsets.h>
 #include <asm/kvm_asm.h>
 #include <asm/kvm_arm.h>
+#include <asm/kvm_mmu.h>

 /********************************************************************
 * Hypervisor initialization
 *   - should be called with:
- *       r0,r1 = Hypervisor pgd pointer
- *       r2 = top of Hyp stack (kernel VA)
- *       r3 = pointer to hyp vectors
+ *       r0 = top of Hyp stack (kernel VA)
+ *       r1 = pointer to hyp vectors
+ *       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!)
+ * - Invalidate TLBs
+ * - Set stack and vectors
+ * - 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
@@ -47,22 +67,25 @@ __kvm_hyp_init:
 	W(b)	.

 __do_hyp_init:
+	cmp	r0, #0			@ We have a SP?
+	bne	phase2			@ Yes, second stage init
+
 	@ Set the HTTBR to point to the hypervisor PGD pointer passed
-	mcrr	p15, 4, r0, r1, c2
+	mcrr	p15, 4, r2, r3, c2

 	@ Set the HTCR and VTCR to the same shareability and cacheability
 	@ settings as the non-secure TTBCR and with T0SZ == 0.
 	mrc	p15, 4, r0, c2, c0, 2	@ HTCR
-	ldr	r12, =HTCR_MASK
-	bic	r0, r0, r12
+	ldr	r2, =HTCR_MASK
+	bic	r0, r0, r2
 	mrc	p15, 0, r1, c2, c0, 2	@ TTBCR
 	and	r1, r1, #(HTCR_MASK & ~TTBCR_T0SZ)
 	orr	r0, r0, r1
 	mcr	p15, 4, r0, c2, c0, 2	@ HTCR

 	mrc	p15, 4, r1, c2, c1, 2	@ VTCR
-	ldr	r12, =VTCR_MASK
-	bic	r1, r1, r12
+	ldr	r2, =VTCR_MASK
+	bic	r1, r1, r2
 	bic	r0, r0, #(~VTCR_HTCR_SH)	@ clear non-reusable HTCR bits
 	orr	r1, r0, r1
 	orr	r1, r1, #(KVM_VTCR_SL0 | KVM_VTCR_T0SZ | KVM_VTCR_S)
@@ -85,24 +108,41 @@ __do_hyp_init:
 	@  - Memory alignment checks: enabled
 	@  - MMU: enabled (this code must be run from an identity mapping)
 	mrc	p15, 4, r0, c1, c0, 0	@ HSCR
-	ldr	r12, =HSCTLR_MASK
-	bic	r0, r0, r12
+	ldr	r2, =HSCTLR_MASK
+	bic	r0, r0, r2
 	mrc	p15, 0, r1, c1, c0, 0	@ SCTLR
-	ldr	r12, =(HSCTLR_EE | HSCTLR_FI | HSCTLR_I | HSCTLR_C)
-	and	r1, r1, r12
- ARM(	ldr	r12, =(HSCTLR_M | HSCTLR_A)			)
- THUMB(	ldr	r12, =(HSCTLR_M | HSCTLR_A | HSCTLR_TE)		)
-	orr	r1, r1, r12
+	ldr	r2, =(HSCTLR_EE | HSCTLR_FI | HSCTLR_I | HSCTLR_C)
+	and	r1, r1, r2
+ ARM(	ldr	r2, =(HSCTLR_M | HSCTLR_A)			)
+ 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
-	isb

-	@ Set stack pointer and return to the kernel
-	mov	sp, r2
+	@ End of init phase-1
+	eret
+
+phase2:
+	@ Set stack pointer
+	mov	sp, r0

 	@ Set HVBAR to point to the HYP vectors
-	mcr	p15, 4, r3, c12, c0, 0	@ HVBAR
+	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
+	mov	pc, r0
+
+target:	@ We're now in the trampoline code, switch page tables
+	mcrr	p15, 4, r2, r3, c2
+	isb
+
+	@ Invalidate the old TLBs
+	mcr	p15, 4, r0, c8, c7, 0	@ TLBIALLH
+	dsb

 	eret

@@ -0,0 +1,68 @@
+/*
+ * Based on the x86 implementation.
+ *
+ * Copyright (C) 2012 ARM Ltd.
+ * Author: Marc Zyngier <marc.zyngier@arm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <linux/perf_event.h>
+#include <linux/kvm_host.h>
+
+#include <asm/kvm_emulate.h>
+
+static int kvm_is_in_guest(void)
+{
+        return kvm_arm_get_running_vcpu() != NULL;
+}
+
+static int kvm_is_user_mode(void)
+{
+	struct kvm_vcpu *vcpu;
+
+	vcpu = kvm_arm_get_running_vcpu();
+
+	if (vcpu)
+		return !vcpu_mode_priv(vcpu);
+
+	return 0;
+}
+
+static unsigned long kvm_get_guest_ip(void)
+{
+	struct kvm_vcpu *vcpu;
+
+	vcpu = kvm_arm_get_running_vcpu();
+
+	if (vcpu)
+		return *vcpu_pc(vcpu);
+
+	return 0;
+}
+
+static struct perf_guest_info_callbacks kvm_guest_cbs = {
+	.is_in_guest	= kvm_is_in_guest,
+	.is_user_mode	= kvm_is_user_mode,
+	.get_guest_ip	= kvm_get_guest_ip,
+};
+
+int kvm_perf_init(void)
+{
+	return perf_register_guest_info_callbacks(&kvm_guest_cbs);
+}
+
+int kvm_perf_teardown(void)
+{
+	return perf_unregister_guest_info_callbacks(&kvm_guest_cbs);
+}
@@ -8,7 +8,6 @@
 #include <asm/pgtable.h>
 #include <asm/sections.h>
 #include <asm/system_info.h>
-#include <asm/virt.h>

 pgd_t *idmap_pgd;

@@ -83,37 +82,10 @@ static void identity_mapping_add(pgd_t *pgd, const char *text_start,
 	} while (pgd++, addr = next, addr != end);
 }

-#if defined(CONFIG_ARM_VIRT_EXT) && defined(CONFIG_ARM_LPAE)
-pgd_t *hyp_pgd;
-
-extern char  __hyp_idmap_text_start[], __hyp_idmap_text_end[];
-
-static int __init init_static_idmap_hyp(void)
-{
-	hyp_pgd = kzalloc(PTRS_PER_PGD * sizeof(pgd_t), GFP_KERNEL);
-	if (!hyp_pgd)
-		return -ENOMEM;
-
-	pr_info("Setting up static HYP identity map for 0x%p - 0x%p\n",
-		__hyp_idmap_text_start, __hyp_idmap_text_end);
-	identity_mapping_add(hyp_pgd, __hyp_idmap_text_start,
-			     __hyp_idmap_text_end, PMD_SECT_AP1);
-
-	return 0;
-}
-#else
-static int __init init_static_idmap_hyp(void)
-{
-	return 0;
-}
-#endif
-
 extern char  __idmap_text_start[], __idmap_text_end[];

 static int __init init_static_idmap(void)
 {
-	int ret;
-
 	idmap_pgd = pgd_alloc(&init_mm);
 	if (!idmap_pgd)
 		return -ENOMEM;
@@ -123,12 +95,10 @@ static int __init init_static_idmap(void)
 	identity_mapping_add(idmap_pgd, __idmap_text_start,
 			     __idmap_text_end, 0);

-	ret = init_static_idmap_hyp();
-
 	/* Flush L1 for the hardware to see this page table content */
 	flush_cache_louis();

-	return ret;
+	return 0;
 }
 early_initcall(init_static_idmap);

@@ -26,6 +26,7 @@
 #define KVM_USER_MEM_SLOTS 32

 #define KVM_COALESCED_MMIO_PAGE_OFFSET 1
+#define KVM_IRQCHIP_NUM_PINS  KVM_IOAPIC_NUM_PINS

 /* define exit reasons from vmm to kvm*/
 #define EXIT_REASON_VM_PANIC		0
@@ -27,7 +27,6 @@
 /* Select x86 specific features in <linux/kvm.h> */
 #define __KVM_HAVE_IOAPIC
 #define __KVM_HAVE_IRQ_LINE
-#define __KVM_HAVE_DEVICE_ASSIGNMENT

 /* Architectural interrupt line count. */
 #define KVM_NR_INTERRUPTS 256
@@ -21,12 +21,11 @@ config KVM
 	tristate "Kernel-based Virtual Machine (KVM) support"
 	depends on BROKEN
 	depends on HAVE_KVM && MODULES
-	# for device assignment:
-	depends on PCI
 	depends on BROKEN
 	select PREEMPT_NOTIFIERS
 	select ANON_INODES
 	select HAVE_KVM_IRQCHIP
+	select HAVE_KVM_IRQ_ROUTING
 	select KVM_APIC_ARCHITECTURE
 	select KVM_MMIO
 	---help---
@@ -50,6 +49,17 @@ config KVM_INTEL
 	  Provides support for KVM on Itanium 2 processors equipped with the VT
 	  extensions.

+config KVM_DEVICE_ASSIGNMENT
+	bool "KVM legacy PCI device assignment support"
+	depends on KVM && PCI && IOMMU_API
+	default y
+	---help---
+	  Provide support for legacy PCI device assignment through KVM.  The
+	  kernel now also supports a full featured userspace device driver
+	  framework through VFIO, which supersedes much of this support.
+
+	  If unsure, say Y.
+
 source drivers/vhost/Kconfig

 endif # VIRTUALIZATION
--- a/Show More
+++ b/Show More
				`@@ -0,0 +1 @@`
				`This directory contains specific device bindings for KVM_CAP_DEVICE_CTRL.`