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

Pull KVM updates from Paolo Bonzini:
 "4.11 is going to be a relatively large release for KVM, with a little
  over 200 commits and noteworthy changes for most architectures.

  ARM:
   - GICv3 save/restore
   - cache flushing fixes
   - working MSI injection for GICv3 ITS
   - physical timer emulation

  MIPS:
   - various improvements under the hood
   - support for SMP guests
   - a large rewrite of MMU emulation. KVM MIPS can now use MMU
     notifiers to support copy-on-write, KSM, idle page tracking,
     swapping, ballooning and everything else. KVM_CAP_READONLY_MEM is
     also supported, so that writes to some memory regions can be
     treated as MMIO. The new MMU also paves the way for hardware
     virtualization support.

  PPC:
   - support for POWER9 using the radix-tree MMU for host and guest
   - resizable hashed page table
   - bugfixes.

  s390:
   - expose more features to the guest
   - more SIMD extensions
   - instruction execution protection
   - ESOP2

  x86:
   - improved hashing in the MMU
   - faster PageLRU tracking for Intel CPUs without EPT A/D bits
   - some refactoring of nested VMX entry/exit code, preparing for live
     migration support of nested hypervisors
   - expose yet another AVX512 CPUID bit
   - host-to-guest PTP support
   - refactoring of interrupt injection, with some optimizations thrown
     in and some duct tape removed.
   - remove lazy FPU handling
   - optimizations of user-mode exits
   - optimizations of vcpu_is_preempted() for KVM guests

  generic:
   - alternative signaling mechanism that doesn't pound on
     tsk->sighand->siglock"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (195 commits)
  x86/kvm: Provide optimized version of vcpu_is_preempted() for x86-64
  x86/paravirt: Change vcp_is_preempted() arg type to long
  KVM: VMX: use correct vmcs_read/write for guest segment selector/base
  x86/kvm/vmx: Defer TR reload after VM exit
  x86/asm/64: Drop __cacheline_aligned from struct x86_hw_tss
  x86/kvm/vmx: Simplify segment_base()
  x86/kvm/vmx: Get rid of segment_base() on 64-bit kernels
  x86/kvm/vmx: Don't fetch the TSS base from the GDT
  x86/asm: Define the kernel TSS limit in a macro
  kvm: fix page struct leak in handle_vmon
  KVM: PPC: Book3S HV: Disable HPT resizing on POWER9 for now
  KVM: Return an error code only as a constant in kvm_get_dirty_log()
  KVM: Return an error code only as a constant in kvm_get_dirty_log_protect()
  KVM: Return directly after a failed copy_from_user() in kvm_vm_compat_ioctl()
  KVM: x86: remove code for lazy FPU handling
  KVM: race-free exit from KVM_RUN without POSIX signals
  KVM: PPC: Book3S HV: Turn "KVM guest htab" message into a debug message
  KVM: PPC: Book3S PR: Ratelimit copy data failure error messages
  KVM: Support vCPU-based gfn->hva cache
  KVM: use separate generations for each address space
  ...

8 files changed, 71 insertions, 34 deletions

diff --git a/arch/arm/include/asm/kvm_host.h b/arch/arm/include/asm/kvm_host.h
index d5423ab15ed5..cc495d799c67 100644
--- a/arch/arm/include/asm/kvm_host.h
+++ b/arch/arm/include/asm/kvm_host.h
@@ -60,9 +60,6 @@ struct kvm_arch {
 	/* The last vcpu id that ran on each physical CPU */
 	int __percpu *last_vcpu_ran;
 
-	/* Timer */
-	struct arch_timer_kvm	timer;
-
 	/*
 	 * Anything that is not used directly from assembly code goes
 	 * here.
diff --git a/arch/arm/include/asm/kvm_mmu.h b/arch/arm/include/asm/kvm_mmu.h
index 74a44727f8e1..95f38dcd611d 100644
--- a/arch/arm/include/asm/kvm_mmu.h
+++ b/arch/arm/include/asm/kvm_mmu.h
@@ -129,8 +129,7 @@ static inline bool vcpu_has_cache_enabled(struct kvm_vcpu *vcpu)
 
 static inline void __coherent_cache_guest_page(struct kvm_vcpu *vcpu,
 					       kvm_pfn_t pfn,
-					       unsigned long size,
-					       bool ipa_uncached)
+					       unsigned long size)
 {
 	/*
 	 * If we are going to insert an instruction page and the icache is
@@ -150,18 +149,12 @@ static inline void __coherent_cache_guest_page(struct kvm_vcpu *vcpu,
 	 * and iterate over the range.
 	 */
 
-	bool need_flush = !vcpu_has_cache_enabled(vcpu) || ipa_uncached;
-
 	VM_BUG_ON(size & ~PAGE_MASK);
 
-	if (!need_flush && !icache_is_pipt())
-		goto vipt_cache;
-
 	while (size) {
 		void *va = kmap_atomic_pfn(pfn);
 
-		if (need_flush)
-			kvm_flush_dcache_to_poc(va, PAGE_SIZE);
+		kvm_flush_dcache_to_poc(va, PAGE_SIZE);
 
 		if (icache_is_pipt())
 			__cpuc_coherent_user_range((unsigned long)va,
@@ -173,7 +166,6 @@ static inline void __coherent_cache_guest_page(struct kvm_vcpu *vcpu,
 		kunmap_atomic(va);
 	}
 
-vipt_cache:
 	if (!icache_is_pipt() && !icache_is_vivt_asid_tagged()) {
 		/* any kind of VIPT cache */
 		__flush_icache_all();
diff --git a/arch/arm/include/uapi/asm/kvm.h b/arch/arm/include/uapi/asm/kvm.h
index af05f8e0903e..6ebd3e6a1fd1 100644
--- a/arch/arm/include/uapi/asm/kvm.h
+++ b/arch/arm/include/uapi/asm/kvm.h
@@ -181,10 +181,23 @@ struct kvm_arch_memory_slot {
 #define KVM_DEV_ARM_VGIC_GRP_CPU_REGS	2
 #define   KVM_DEV_ARM_VGIC_CPUID_SHIFT	32
 #define   KVM_DEV_ARM_VGIC_CPUID_MASK	(0xffULL << KVM_DEV_ARM_VGIC_CPUID_SHIFT)
+#define   KVM_DEV_ARM_VGIC_V3_MPIDR_SHIFT 32
+#define   KVM_DEV_ARM_VGIC_V3_MPIDR_MASK \
+			(0xffffffffULL << KVM_DEV_ARM_VGIC_V3_MPIDR_SHIFT)
 #define   KVM_DEV_ARM_VGIC_OFFSET_SHIFT	0
 #define   KVM_DEV_ARM_VGIC_OFFSET_MASK	(0xffffffffULL << KVM_DEV_ARM_VGIC_OFFSET_SHIFT)
+#define   KVM_DEV_ARM_VGIC_SYSREG_INSTR_MASK (0xffff)
 #define KVM_DEV_ARM_VGIC_GRP_NR_IRQS	3
 #define KVM_DEV_ARM_VGIC_GRP_CTRL       4
+#define KVM_DEV_ARM_VGIC_GRP_REDIST_REGS 5
+#define KVM_DEV_ARM_VGIC_GRP_CPU_SYSREGS 6
+#define KVM_DEV_ARM_VGIC_GRP_LEVEL_INFO  7
+#define KVM_DEV_ARM_VGIC_LINE_LEVEL_INFO_SHIFT	10
+#define KVM_DEV_ARM_VGIC_LINE_LEVEL_INFO_MASK \
+			(0x3fffffULL << KVM_DEV_ARM_VGIC_LINE_LEVEL_INFO_SHIFT)
+#define KVM_DEV_ARM_VGIC_LINE_LEVEL_INTID_MASK 0x3ff
+#define VGIC_LEVEL_INFO_LINE_LEVEL	0
+
 #define   KVM_DEV_ARM_VGIC_CTRL_INIT    0
 
 /* KVM_IRQ_LINE irq field index values */
diff --git a/arch/arm/kvm/Makefile b/arch/arm/kvm/Makefile
index d571243ab4d1..7b3670c2ae7b 100644
--- a/arch/arm/kvm/Makefile
+++ b/arch/arm/kvm/Makefile
@@ -7,7 +7,7 @@ ifeq ($(plus_virt),+virt)
 	plus_virt_def := -DREQUIRES_VIRT=1
 endif
 
-ccflags-y += -Iarch/arm/kvm
+ccflags-y += -Iarch/arm/kvm -Ivirt/kvm/arm/vgic
 CFLAGS_arm.o := -I. $(plus_virt_def)
 CFLAGS_mmu.o := -I.
 
@@ -20,7 +20,7 @@ kvm-arm-y = $(KVM)/kvm_main.o $(KVM)/coalesced_mmio.o $(KVM)/eventfd.o $(KVM)/vf
 obj-$(CONFIG_KVM_ARM_HOST) += hyp/
 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
+obj-y += coproc.o coproc_a15.o coproc_a7.o mmio.o psci.o perf.o vgic-v3-coproc.o
 obj-y += $(KVM)/arm/aarch32.o
 
 obj-y += $(KVM)/arm/vgic/vgic.o
@@ -33,5 +33,6 @@ obj-y += $(KVM)/arm/vgic/vgic-mmio-v2.o
 obj-y += $(KVM)/arm/vgic/vgic-mmio-v3.o
 obj-y += $(KVM)/arm/vgic/vgic-kvm-device.o
 obj-y += $(KVM)/arm/vgic/vgic-its.o
+obj-y += $(KVM)/arm/vgic/vgic-debug.o
 obj-y += $(KVM)/irqchip.o
 obj-y += $(KVM)/arm/arch_timer.o
diff --git a/arch/arm/kvm/arm.c b/arch/arm/kvm/arm.c
index 9d7446456e0c..c9a2103faeb9 100644
--- a/arch/arm/kvm/arm.c
+++ b/arch/arm/kvm/arm.c
@@ -135,7 +135,6 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
 		goto out_free_stage2_pgd;
 
 	kvm_vgic_early_init(kvm);
-	kvm_timer_init(kvm);
 
 	/* Mark the initial VMID generation invalid */
 	kvm->arch.vmid_gen = 0;
@@ -207,6 +206,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 	case KVM_CAP_ARM_PSCI_0_2:
 	case KVM_CAP_READONLY_MEM:
 	case KVM_CAP_MP_STATE:
+	case KVM_CAP_IMMEDIATE_EXIT:
 		r = 1;
 		break;
 	case KVM_CAP_COALESCED_MMIO:
@@ -301,7 +301,8 @@ void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu)
 
 int kvm_cpu_has_pending_timer(struct kvm_vcpu *vcpu)
 {
-	return kvm_timer_should_fire(vcpu);
+	return kvm_timer_should_fire(vcpu_vtimer(vcpu)) ||
+	       kvm_timer_should_fire(vcpu_ptimer(vcpu));
 }
 
 void kvm_arch_vcpu_blocking(struct kvm_vcpu *vcpu)
@@ -604,6 +605,9 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run)
 			return ret;
 	}
 
+	if (run->immediate_exit)
+		return -EINTR;
+
 	if (vcpu->sigset_active)
 		sigprocmask(SIG_SETMASK, &vcpu->sigset, &sigsaved);
 
diff --git a/arch/arm/kvm/mmu.c b/arch/arm/kvm/mmu.c
index a5265edbeeab..962616fd4ddd 100644
--- a/arch/arm/kvm/mmu.c
+++ b/arch/arm/kvm/mmu.c
@@ -1232,9 +1232,9 @@ void kvm_arch_mmu_enable_log_dirty_pt_masked(struct kvm *kvm,
 }
 
 static void coherent_cache_guest_page(struct kvm_vcpu *vcpu, kvm_pfn_t pfn,
-				      unsigned long size, bool uncached)
+				      unsigned long size)
 {
-	__coherent_cache_guest_page(vcpu, pfn, size, uncached);
+	__coherent_cache_guest_page(vcpu, pfn, size);
 }
 
 static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
@@ -1250,7 +1250,6 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 	struct vm_area_struct *vma;
 	kvm_pfn_t pfn;
 	pgprot_t mem_type = PAGE_S2;
-	bool fault_ipa_uncached;
 	bool logging_active = memslot_is_logging(memslot);
 	unsigned long flags = 0;
 
@@ -1337,8 +1336,6 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 	if (!hugetlb && !force_pte)
 		hugetlb = transparent_hugepage_adjust(&pfn, &fault_ipa);
 
-	fault_ipa_uncached = memslot->flags & KVM_MEMSLOT_INCOHERENT;
-
 	if (hugetlb) {
 		pmd_t new_pmd = pfn_pmd(pfn, mem_type);
 		new_pmd = pmd_mkhuge(new_pmd);
@@ -1346,7 +1343,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 			new_pmd = kvm_s2pmd_mkwrite(new_pmd);
 			kvm_set_pfn_dirty(pfn);
 		}
-		coherent_cache_guest_page(vcpu, pfn, PMD_SIZE, fault_ipa_uncached);
+		coherent_cache_guest_page(vcpu, pfn, PMD_SIZE);
 		ret = stage2_set_pmd_huge(kvm, memcache, fault_ipa, &new_pmd);
 	} else {
 		pte_t new_pte = pfn_pte(pfn, mem_type);
@@ -1356,7 +1353,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 			kvm_set_pfn_dirty(pfn);
 			mark_page_dirty(kvm, gfn);
 		}
-		coherent_cache_guest_page(vcpu, pfn, PAGE_SIZE, fault_ipa_uncached);
+		coherent_cache_guest_page(vcpu, pfn, PAGE_SIZE);
 		ret = stage2_set_pte(kvm, memcache, fault_ipa, &new_pte, flags);
 	}
 
@@ -1879,15 +1876,6 @@ void kvm_arch_free_memslot(struct kvm *kvm, struct kvm_memory_slot *free,
 int kvm_arch_create_memslot(struct kvm *kvm, struct kvm_memory_slot *slot,
 			    unsigned long npages)
 {
-	/*
-	 * Readonly memslots are not incoherent with the caches by definition,
-	 * but in practice, they are used mostly to emulate ROMs or NOR flashes
-	 * that the guest may consider devices and hence map as uncached.
-	 * To prevent incoherency issues in these cases, tag all readonly
-	 * regions as incoherent.
-	 */
-	if (slot->flags & KVM_MEM_READONLY)
-		slot->flags |= KVM_MEMSLOT_INCOHERENT;
 	return 0;
 }
 
diff --git a/arch/arm/kvm/reset.c b/arch/arm/kvm/reset.c
index 4b5e802e57d1..1da8b2d14550 100644
--- a/arch/arm/kvm/reset.c
+++ b/arch/arm/kvm/reset.c
@@ -37,6 +37,11 @@ static struct kvm_regs cortexa_regs_reset = {
 	.usr_regs.ARM_cpsr = SVC_MODE | PSR_A_BIT | PSR_I_BIT | PSR_F_BIT,
 };
 
+static const struct kvm_irq_level cortexa_ptimer_irq = {
+	{ .irq = 30 },
+	.level = 1,
+};
+
 static const struct kvm_irq_level cortexa_vtimer_irq = {
 	{ .irq = 27 },
 	.level = 1,
@@ -58,6 +63,7 @@ int kvm_reset_vcpu(struct kvm_vcpu *vcpu)
 {
 	struct kvm_regs *reset_regs;
 	const struct kvm_irq_level *cpu_vtimer_irq;
+	const struct kvm_irq_level *cpu_ptimer_irq;
 
 	switch (vcpu->arch.target) {
 	case KVM_ARM_TARGET_CORTEX_A7:
@@ -65,6 +71,7 @@ int kvm_reset_vcpu(struct kvm_vcpu *vcpu)
 		reset_regs = &cortexa_regs_reset;
 		vcpu->arch.midr = read_cpuid_id();
 		cpu_vtimer_irq = &cortexa_vtimer_irq;
+		cpu_ptimer_irq = &cortexa_ptimer_irq;
 		break;
 	default:
 		return -ENODEV;
@@ -77,5 +84,5 @@ int kvm_reset_vcpu(struct kvm_vcpu *vcpu)
 	kvm_reset_coprocs(vcpu);
 
 	/* Reset arch_timer context */
-	return kvm_timer_vcpu_reset(vcpu, cpu_vtimer_irq);
+	return kvm_timer_vcpu_reset(vcpu, cpu_vtimer_irq, cpu_ptimer_irq);
 }
diff --git a/arch/arm/kvm/vgic-v3-coproc.c b/arch/arm/kvm/vgic-v3-coproc.c
new file mode 100644
index 000000000000..f41abf76366f
--- /dev/null
+++ b/arch/arm/kvm/vgic-v3-coproc.c
@@ -0,0 +1,35 @@
+/*
+ * VGIC system registers handling functions for AArch32 mode
+ *
+ * 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.
+ */
+
+#include <linux/kvm.h>
+#include <linux/kvm_host.h>
+#include <asm/kvm_emulate.h>
+#include "vgic.h"
+
+int vgic_v3_has_cpu_sysregs_attr(struct kvm_vcpu *vcpu, bool is_write, u64 id,
+				 u64 *reg)
+{
+	/*
+	 * TODO: Implement for AArch32
+	 */
+	return -ENXIO;
+}
+
+int vgic_v3_cpu_sysregs_uaccess(struct kvm_vcpu *vcpu, bool is_write, u64 id,
+				u64 *reg)
+{
+	/*
+	 * TODO: Implement for AArch32
+	 */
+	return -ENXIO;
+}