Merge tag 'kvm-5.6-1' of git://git.kernel.org/pub/scm/virt/kvm/kvm

Pull KVM updates from Paolo Bonzini:
 "This is the first batch of KVM changes.

  ARM:
   - cleanups and corner case fixes.

  PPC:
   - Bugfixes

  x86:
   - Support for mapping DAX areas with large nested page table entries.

   - Cleanups and bugfixes here too. A particularly important one is a
     fix for FPU load when the thread has TIF_NEED_FPU_LOAD. There is
     also a race condition which could be used in guest userspace to
     exploit the guest kernel, for which the embargo expired today.

   - Fast path for IPI delivery vmexits, shaving about 200 clock cycles
     from IPI latency.

   - Protect against "Spectre-v1/L1TF" (bring data in the cache via
     speculative out of bound accesses, use L1TF on the sibling
     hyperthread to read it), which unfortunately is an even bigger
     whack-a-mole game than SpectreV1.

  Sean continues his mission to rewrite KVM. In addition to a sizable
  number of x86 patches, this time he contributed a pretty large
  refactoring of vCPU creation that affects all architectures but should
  not have any visible effect.

  s390 will come next week together with some more x86 patches"

* tag 'kvm-5.6-1' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (204 commits)
  x86/KVM: Clean up host's steal time structure
  x86/KVM: Make sure KVM_VCPU_FLUSH_TLB flag is not missed
  x86/kvm: Cache gfn to pfn translation
  x86/kvm: Introduce kvm_(un)map_gfn()
  x86/kvm: Be careful not to clear KVM_VCPU_FLUSH_TLB bit
  KVM: PPC: Book3S PR: Fix -Werror=return-type build failure
  KVM: PPC: Book3S HV: Release lock on page-out failure path
  KVM: arm64: Treat emulated TVAL TimerValue as a signed 32-bit integer
  KVM: arm64: pmu: Only handle supported event counters
  KVM: arm64: pmu: Fix chained SW_INCR counters
  KVM: arm64: pmu: Don't mark a counter as chained if the odd one is disabled
  KVM: arm64: pmu: Don't increment SW_INCR if PMCR.E is unset
  KVM: x86: Use a typedef for fastop functions
  KVM: X86: Add 'else' to unify fastop and execute call path
  KVM: x86: inline memslot_valid_for_gpte
  KVM: x86/mmu: Use huge pages for DAX-backed files
  KVM: x86/mmu: Remove lpage_is_disallowed() check from set_spte()
  KVM: x86/mmu: Fold max_mapping_level() into kvm_mmu_hugepage_adjust()
  KVM: x86/mmu: Zap any compound page when collapsing sptes
  KVM: x86/mmu: Remove obsolete gfn restoration in FNAME(fetch)
  ...

4 files changed, 48 insertions, 38 deletions

diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h
index 5efe5ca8fecf..688c63412cc2 100644
--- a/arch/arm64/include/asm/kvm_emulate.h
+++ b/arch/arm64/include/asm/kvm_emulate.h
@@ -17,7 +17,6 @@
 #include <asm/esr.h>
 #include <asm/kvm_arm.h>
 #include <asm/kvm_hyp.h>
-#include <asm/kvm_mmio.h>
 #include <asm/ptrace.h>
 #include <asm/cputype.h>
 #include <asm/virt.h>
@@ -219,6 +218,38 @@ static inline void vcpu_write_spsr(struct kvm_vcpu *vcpu, unsigned long v)
 		vcpu_gp_regs(vcpu)->spsr[KVM_SPSR_EL1] = v;
 }
 
+/*
+ * The layout of SPSR for an AArch32 state is different when observed from an
+ * AArch64 SPSR_ELx or an AArch32 SPSR_*. This function generates the AArch32
+ * view given an AArch64 view.
+ *
+ * In ARM DDI 0487E.a see:
+ *
+ * - The AArch64 view (SPSR_EL2) in section C5.2.18, page C5-426
+ * - The AArch32 view (SPSR_abt) in section G8.2.126, page G8-6256
+ * - The AArch32 view (SPSR_und) in section G8.2.132, page G8-6280
+ *
+ * Which show the following differences:
+ *
+ * | Bit | AA64 | AA32 | Notes                       |
+ * +-----+------+------+-----------------------------|
+ * | 24  | DIT  | J    | J is RES0 in ARMv8          |
+ * | 21  | SS   | DIT  | SS doesn't exist in AArch32 |
+ *
+ * ... and all other bits are (currently) common.
+ */
+static inline unsigned long host_spsr_to_spsr32(unsigned long spsr)
+{
+	const unsigned long overlap = BIT(24) | BIT(21);
+	unsigned long dit = !!(spsr & PSR_AA32_DIT_BIT);
+
+	spsr &= ~overlap;
+
+	spsr |= dit << 21;
+
+	return spsr;
+}
+
 static inline bool vcpu_mode_priv(const struct kvm_vcpu *vcpu)
 {
 	u32 mode;
@@ -283,6 +314,11 @@ static inline bool kvm_vcpu_dabt_issext(const struct kvm_vcpu *vcpu)
 	return !!(kvm_vcpu_get_hsr(vcpu) & ESR_ELx_SSE);
 }
 
+static inline bool kvm_vcpu_dabt_issf(const struct kvm_vcpu *vcpu)
+{
+	return !!(kvm_vcpu_get_hsr(vcpu) & ESR_ELx_SF);
+}
+
 static inline int kvm_vcpu_dabt_get_rd(const struct kvm_vcpu *vcpu)
 {
 	return (kvm_vcpu_get_hsr(vcpu) & ESR_ELx_SRT_MASK) >> ESR_ELx_SRT_SHIFT;
@@ -304,7 +340,7 @@ static inline bool kvm_vcpu_dabt_is_cm(const struct kvm_vcpu *vcpu)
 	return !!(kvm_vcpu_get_hsr(vcpu) & ESR_ELx_CM);
 }
 
-static inline int kvm_vcpu_dabt_get_as(const struct kvm_vcpu *vcpu)
+static inline unsigned int kvm_vcpu_dabt_get_as(const struct kvm_vcpu *vcpu)
 {
 	return 1 << ((kvm_vcpu_get_hsr(vcpu) & ESR_ELx_SAS) >> ESR_ELx_SAS_SHIFT);
 }
diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index f5acdde17f3b..d87aa609d2b6 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -24,7 +24,6 @@
 #include <asm/fpsimd.h>
 #include <asm/kvm.h>
 #include <asm/kvm_asm.h>
-#include <asm/kvm_mmio.h>
 #include <asm/thread_info.h>
 
 #define __KVM_HAVE_ARCH_INTC_INITIALIZED
@@ -53,7 +52,7 @@ int kvm_arm_init_sve(void);
 
 int __attribute_const__ kvm_target_cpu(void);
 int kvm_reset_vcpu(struct kvm_vcpu *vcpu);
-void kvm_arch_vcpu_uninit(struct kvm_vcpu *vcpu);
+void kvm_arm_vcpu_destroy(struct kvm_vcpu *vcpu);
 int kvm_arch_vm_ioctl_check_extension(struct kvm *kvm, long ext);
 void __extended_idmap_trampoline(phys_addr_t boot_pgd, phys_addr_t idmap_start);
 
@@ -325,9 +324,6 @@ struct kvm_vcpu_arch {
 	/* Don't run the guest (internal implementation need) */
 	bool pause;
 
-	/* IO related fields */
-	struct kvm_decode mmio_decode;
-
 	/* Cache some mmu pages needed inside spinlock regions */
 	struct kvm_mmu_memory_cache mmu_page_cache;
 
@@ -446,8 +442,6 @@ int kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte);
 int kvm_age_hva(struct kvm *kvm, unsigned long start, unsigned long end);
 int kvm_test_age_hva(struct kvm *kvm, unsigned long hva);
 
-struct kvm_vcpu *kvm_arm_get_running_vcpu(void);
-struct kvm_vcpu * __percpu *kvm_get_running_vcpus(void);
 void kvm_arm_halt_guest(struct kvm *kvm);
 void kvm_arm_resume_guest(struct kvm *kvm);
 
@@ -491,6 +485,14 @@ int handle_exit(struct kvm_vcpu *vcpu, struct kvm_run *run,
 void handle_exit_early(struct kvm_vcpu *vcpu, struct kvm_run *run,
 		       int exception_index);
 
+/* MMIO helpers */
+void kvm_mmio_write_buf(void *buf, unsigned int len, unsigned long data);
+unsigned long kvm_mmio_read_buf(const void *buf, unsigned int len);
+
+int kvm_handle_mmio_return(struct kvm_vcpu *vcpu, struct kvm_run *run);
+int io_mem_abort(struct kvm_vcpu *vcpu, struct kvm_run *run,
+		 phys_addr_t fault_ipa);
+
 int kvm_perf_init(void);
 int kvm_perf_teardown(void);
 
diff --git a/arch/arm64/include/asm/kvm_mmio.h b/arch/arm64/include/asm/kvm_mmio.h
deleted file mode 100644
index 02b5c48fd467..000000000000
--- a/arch/arm64/include/asm/kvm_mmio.h
+++ /dev/null
@@ -1,29 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * Copyright (C) 2012 - Virtual Open Systems and Columbia University
- * Author: Christoffer Dall <c.dall@virtualopensystems.com>
- */
-
-#ifndef __ARM64_KVM_MMIO_H__
-#define __ARM64_KVM_MMIO_H__
-
-#include <linux/kvm_host.h>
-#include <asm/kvm_arm.h>
-
-/*
- * This is annoying. The mmio code requires this, even if we don't
- * need any decoding. To be fixed.
- */
-struct kvm_decode {
-	unsigned long rt;
-	bool sign_extend;
-};
-
-void kvm_mmio_write_buf(void *buf, unsigned int len, unsigned long data);
-unsigned long kvm_mmio_read_buf(const void *buf, unsigned int len);
-
-int kvm_handle_mmio_return(struct kvm_vcpu *vcpu, struct kvm_run *run);
-int io_mem_abort(struct kvm_vcpu *vcpu, struct kvm_run *run,
-		 phys_addr_t fault_ipa);
-
-#endif	/* __ARM64_KVM_MMIO_H__ */
diff --git a/arch/arm64/include/asm/ptrace.h b/arch/arm64/include/asm/ptrace.h
index fbebb411ae20..bf57308fcd63 100644
--- a/arch/arm64/include/asm/ptrace.h
+++ b/arch/arm64/include/asm/ptrace.h
@@ -62,6 +62,7 @@
 #define PSR_AA32_I_BIT		0x00000080
 #define PSR_AA32_A_BIT		0x00000100
 #define PSR_AA32_E_BIT		0x00000200
+#define PSR_AA32_PAN_BIT	0x00400000
 #define PSR_AA32_SSBS_BIT	0x00800000
 #define PSR_AA32_DIT_BIT	0x01000000
 #define PSR_AA32_Q_BIT		0x08000000