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
  ...

93 files changed, 7424 insertions, 1849 deletions

diff --git a/arch/arm/include/asm/idmap.h b/arch/arm/include/asm/idmap.h
index 1a66f907e5c..bf863edb517 100644
--- a/arch/arm/include/asm/idmap.h
+++ b/arch/arm/include/asm/idmap.h
@@ -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);
 
diff --git a/arch/arm/include/asm/kvm_host.h b/arch/arm/include/asm/kvm_host.h
index 0c4e643d939..57cb786a620 100644
--- a/arch/arm/include/asm/kvm_host.h
+++ b/arch/arm/include/asm/kvm_host.h
@@ -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__ */
diff --git a/arch/arm/include/asm/kvm_mmu.h b/arch/arm/include/asm/kvm_mmu.h
index 970f3b5fa10..472ac709100 100644
--- a/arch/arm/include/asm/kvm_mmu.h
+++ b/arch/arm/include/asm/kvm_mmu.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__ */
diff --git a/arch/arm/kernel/asm-offsets.c b/arch/arm/kernel/asm-offsets.c
index a53efa99369..ee68cce6b48 100644
--- a/arch/arm/kernel/asm-offsets.c
+++ b/arch/arm/kernel/asm-offsets.c
@@ -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));
diff --git a/arch/arm/kernel/vmlinux.lds.S b/arch/arm/kernel/vmlinux.lds.S
index b571484e9f0..a871b8e00fc 100644
--- a/arch/arm/kernel/vmlinux.lds.S
+++ b/arch/arm/kernel/vmlinux.lds.S
@@ -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")
diff --git a/arch/arm/kvm/Kconfig b/arch/arm/kvm/Kconfig
index 49dd64e579c..370e1a8af6a 100644
--- a/arch/arm/kvm/Kconfig
+++ b/arch/arm/kvm/Kconfig
@@ -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.
 
diff --git a/arch/arm/kvm/Makefile b/arch/arm/kvm/Makefile
index 8dc5e76cb78..53c5ed83d16 100644
--- a/arch/arm/kvm/Makefile
+++ b/arch/arm/kvm/Makefile
@@ -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
diff --git a/arch/arm/kvm/arch_timer.c b/arch/arm/kvm/arch_timer.c
index 6ac938d4629..c55b6089e92 100644
--- a/arch/arm/kvm/arch_timer.c
+++ b/arch/arm/kvm/arch_timer.c
@@ -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;
diff --git a/arch/arm/kvm/arm.c b/arch/arm/kvm/arm.c
index a0dfc2a53f9..37d216d814c 100644
--- a/arch/arm/kvm/arm.c
+++ b/arch/arm/kvm/arm.c
@@ -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;
 }