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

Pull KVM fixes from Radim Krčmář:
 "ARM:
   - A number of issues in the vgic discovered using SMATCH
   - A bit one-off calculation in out stage base address mask (32-bit
     and 64-bit)
   - Fixes to single-step debugging instructions that trap for other
     reasons such as MMMIO aborts
   - Printing unavailable hyp mode as error
   - Potential spinlock deadlock in the vgic
   - Avoid calling vgic vcpu free more than once
   - Broken bit calculation for big endian systems

 s390:
   - SPDX tags
   - Fence storage key accesses from problem state
   - Make sure that irq_state.flags is not used in the future

  x86:
   - Intercept port 0x80 accesses to prevent host instability (CVE)
   - Use userspace FPU context for guest FPU (mainly an optimization
     that fixes a double use of kernel FPU)
   - Do not leak one page per module load
   - Flush APIC page address cache from MMU invalidation notifiers"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (28 commits)
  KVM: x86: fix APIC page invalidation
  KVM: s390: Fix skey emulation permission check
  KVM: s390: mark irq_state.flags as non-usable
  KVM: s390: Remove redundant license text
  KVM: s390: add SPDX identifiers to the remaining files
  KVM: VMX: fix page leak in hardware_setup()
  KVM: VMX: remove I/O port 0x80 bypass on Intel hosts
  x86,kvm: remove KVM emulator get_fpu / put_fpu
  x86,kvm: move qemu/guest FPU switching out to vcpu_run
  KVM: arm/arm64: Fix broken GICH_ELRSR big endian conversion
  KVM: arm/arm64: kvm_arch_destroy_vm cleanups
  KVM: arm/arm64: Fix spinlock acquisition in vgic_set_owner
  kvm: arm: don't treat unavailable HYP mode as an error
  KVM: arm/arm64: Avoid attempting to load timer vgic state without a vgic
  kvm: arm64: handle single-step of hyp emulated mmio instructions
  kvm: arm64: handle single-step during SError exceptions
  kvm: arm64: handle single-step of userspace mmio instructions
  kvm: arm64: handle single-stepping trapped instructions
  KVM: arm/arm64: debug: Introduce helper for single-step
  arm: KVM: Fix VTTBR_BADDR_MASK BUG_ON off-by-one
  ...

Author: torvalds

Documentation/virtual/kvm/api.txt

@@ -2901,14 +2901,19 @@ userspace buffer and its length:
 
 struct kvm_s390_irq_state {
 	__u64 buf;
-	__u32 flags;
+	__u32 flags;        /* will stay unused for compatibility reasons */
 	__u32 len;
-	__u32 reserved[4];
+	__u32 reserved[4];  /* will stay unused for compatibility reasons */
 };
 
 Userspace passes in the above struct and for each pending interrupt a
 struct kvm_s390_irq is copied to the provided buffer.
 
+The structure contains a flags and a reserved field for future extensions. As
+the kernel never checked for flags == 0 and QEMU never pre-zeroed flags and
+reserved, these fields can not be used in the future without breaking
+compatibility.
+
 If -ENOBUFS is returned the buffer provided was too small and userspace
 may retry with a bigger buffer.
 
@@ -2932,10 +2937,14 @@ containing a struct kvm_s390_irq_state:
 
 struct kvm_s390_irq_state {
 	__u64 buf;
+	__u32 flags;        /* will stay unused for compatibility reasons */
 	__u32 len;
-	__u32 pad;
+	__u32 reserved[4];  /* will stay unused for compatibility reasons */
 };
 
+The restrictions for flags and reserved apply as well.
+(see KVM_S390_GET_IRQ_STATE)
+
 The userspace memory referenced by buf contains a struct kvm_s390_irq
 for each interrupt to be injected into the guest.
 If one of the interrupts could not be injected for some reason the

arch/arm/include/asm/kvm_arm.h

@@ -161,8 +161,7 @@
 #else
 #define VTTBR_X		(5 - KVM_T0SZ)
 #endif
-#define VTTBR_BADDR_SHIFT (VTTBR_X - 1)
-#define VTTBR_BADDR_MASK  (((_AC(1, ULL) << (40 - VTTBR_X)) - 1) << VTTBR_BADDR_SHIFT)
+#define VTTBR_BADDR_MASK  (((_AC(1, ULL) << (40 - VTTBR_X)) - 1) << VTTBR_X)
 #define VTTBR_VMID_SHIFT  _AC(48, ULL)
 #define VTTBR_VMID_MASK(size)	(_AT(u64, (1 << size) - 1) << VTTBR_VMID_SHIFT)
 

arch/arm/include/asm/kvm_host.h

@@ -285,6 +285,11 @@ static inline void kvm_arm_init_debug(void) {}
 static inline void kvm_arm_setup_debug(struct kvm_vcpu *vcpu) {}
 static inline void kvm_arm_clear_debug(struct kvm_vcpu *vcpu) {}
 static inline void kvm_arm_reset_debug_ptr(struct kvm_vcpu *vcpu) {}
+static inline bool kvm_arm_handle_step_debug(struct kvm_vcpu *vcpu,
+					     struct kvm_run *run)
+{
+	return false;
+}
 
 int kvm_arm_vcpu_arch_set_attr(struct kvm_vcpu *vcpu,
 			       struct kvm_device_attr *attr);

arch/arm64/include/asm/kvm_arm.h

@@ -170,8 +170,7 @@
 #define VTCR_EL2_FLAGS			(VTCR_EL2_COMMON_BITS | VTCR_EL2_TGRAN_FLAGS)
 #define VTTBR_X				(VTTBR_X_TGRAN_MAGIC - VTCR_EL2_T0SZ_IPA)
 
-#define VTTBR_BADDR_SHIFT (VTTBR_X - 1)
-#define VTTBR_BADDR_MASK  (((UL(1) << (PHYS_MASK_SHIFT - VTTBR_X)) - 1) << VTTBR_BADDR_SHIFT)
+#define VTTBR_BADDR_MASK  (((UL(1) << (PHYS_MASK_SHIFT - VTTBR_X)) - 1) << VTTBR_X)
 #define VTTBR_VMID_SHIFT  (UL(48))
 #define VTTBR_VMID_MASK(size) (_AT(u64, (1 << size) - 1) << VTTBR_VMID_SHIFT)
 

arch/arm64/include/asm/kvm_host.h

@@ -370,6 +370,7 @@ void kvm_arm_init_debug(void);
 void kvm_arm_setup_debug(struct kvm_vcpu *vcpu);
 void kvm_arm_clear_debug(struct kvm_vcpu *vcpu);
 void kvm_arm_reset_debug_ptr(struct kvm_vcpu *vcpu);
+bool kvm_arm_handle_step_debug(struct kvm_vcpu *vcpu, struct kvm_run *run);
 int kvm_arm_vcpu_arch_set_attr(struct kvm_vcpu *vcpu,
 			       struct kvm_device_attr *attr);
 int kvm_arm_vcpu_arch_get_attr(struct kvm_vcpu *vcpu,

arch/arm64/kvm/debug.c

@@ -221,3 +221,24 @@ void kvm_arm_clear_debug(struct kvm_vcpu *vcpu)
 		}
 	}
 }
+
+
+/*
+ * After successfully emulating an instruction, we might want to
+ * return to user space with a KVM_EXIT_DEBUG. We can only do this
+ * once the emulation is complete, though, so for userspace emulations
+ * we have to wait until we have re-entered KVM before calling this
+ * helper.
+ *
+ * Return true (and set exit_reason) to return to userspace or false
+ * if no further action is required.
+ */
+bool kvm_arm_handle_step_debug(struct kvm_vcpu *vcpu, struct kvm_run *run)
+{
+	if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP) {
+		run->exit_reason = KVM_EXIT_DEBUG;
+		run->debug.arch.hsr = ESR_ELx_EC_SOFTSTP_LOW << ESR_ELx_EC_SHIFT;
+		return true;
+	}
+	return false;
+}

arch/arm64/kvm/handle_exit.c

@@ -28,6 +28,7 @@
 #include <asm/kvm_emulate.h>
 #include <asm/kvm_mmu.h>
 #include <asm/kvm_psci.h>
+#include <asm/debug-monitors.h>
 
 #define CREATE_TRACE_POINTS
 #include "trace.h"
@@ -186,15 +187,47 @@ static exit_handle_fn kvm_get_exit_handler(struct kvm_vcpu *vcpu)
 	return arm_exit_handlers[hsr_ec];
 }
 
+/*
+ * We may be single-stepping an emulated instruction. If the emulation
+ * has been completed in the kernel, we can return to userspace with a
+ * KVM_EXIT_DEBUG, otherwise userspace needs to complete its
+ * emulation first.
+ */
+static int handle_trap_exceptions(struct kvm_vcpu *vcpu, struct kvm_run *run)
+{
+	int handled;
+
+	/*
+	 * See ARM ARM B1.14.1: "Hyp traps on instructions
+	 * that fail their condition code check"
+	 */
+	if (!kvm_condition_valid(vcpu)) {
+		kvm_skip_instr(vcpu, kvm_vcpu_trap_il_is32bit(vcpu));
+		handled = 1;
+	} else {
+		exit_handle_fn exit_handler;
+
+		exit_handler = kvm_get_exit_handler(vcpu);
+		handled = exit_handler(vcpu, run);
+	}
+
+	/*
+	 * kvm_arm_handle_step_debug() sets the exit_reason on the kvm_run
+	 * structure if we need to return to userspace.
+	 */
+	if (handled > 0 && kvm_arm_handle_step_debug(vcpu, run))
+		handled = 0;
+
+	return handled;
+}
+
 /*
  * Return > 0 to return to guest, < 0 on error, 0 (and set exit_reason) on
  * proper exit to userspace.
  */
 int handle_exit(struct kvm_vcpu *vcpu, struct kvm_run *run,
 		       int exception_index)
 {
-	exit_handle_fn exit_handler;
-
 	if (ARM_SERROR_PENDING(exception_index)) {
 		u8 hsr_ec = ESR_ELx_EC(kvm_vcpu_get_hsr(vcpu));
 
@@ -220,20 +253,14 @@ int handle_exit(struct kvm_vcpu *vcpu, struct kvm_run *run,
 		return 1;
 	case ARM_EXCEPTION_EL1_SERROR:
 		kvm_inject_vabt(vcpu);
-		return 1;
-	case ARM_EXCEPTION_TRAP:
-		/*
-		 * See ARM ARM B1.14.1: "Hyp traps on instructions
-		 * that fail their condition code check"
-		 */
-		if (!kvm_condition_valid(vcpu)) {
-			kvm_skip_instr(vcpu, kvm_vcpu_trap_il_is32bit(vcpu));
+		/* We may still need to return for single-step */
+		if (!(*vcpu_cpsr(vcpu) & DBG_SPSR_SS)
+			&& kvm_arm_handle_step_debug(vcpu, run))
+			return 0;
+		else
 			return 1;
-		}
-
-		exit_handler = kvm_get_exit_handler(vcpu);
-
-		return exit_handler(vcpu, run);
+	case ARM_EXCEPTION_TRAP:
+		return handle_trap_exceptions(vcpu, run);
 	case ARM_EXCEPTION_HYP_GONE:
 		/*
 		 * EL2 has been reset to the hyp-stub. This happens when a guest

arch/arm64/kvm/hyp/switch.c

@@ -22,6 +22,7 @@
 #include <asm/kvm_emulate.h>
 #include <asm/kvm_hyp.h>
 #include <asm/fpsimd.h>
+#include <asm/debug-monitors.h>
 
 static bool __hyp_text __fpsimd_enabled_nvhe(void)
 {
@@ -269,7 +270,11 @@ static bool __hyp_text __populate_fault_info(struct kvm_vcpu *vcpu)
 	return true;
 }
 
-static void __hyp_text __skip_instr(struct kvm_vcpu *vcpu)
+/* Skip an instruction which has been emulated. Returns true if
+ * execution can continue or false if we need to exit hyp mode because
+ * single-step was in effect.
+ */
+static bool __hyp_text __skip_instr(struct kvm_vcpu *vcpu)
 {
 	*vcpu_pc(vcpu) = read_sysreg_el2(elr);
 
@@ -282,6 +287,14 @@ static void __hyp_text __skip_instr(struct kvm_vcpu *vcpu)
 	}
 
 	write_sysreg_el2(*vcpu_pc(vcpu), elr);
+
+	if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP) {
+		vcpu->arch.fault.esr_el2 =
+			(ESR_ELx_EC_SOFTSTP_LOW << ESR_ELx_EC_SHIFT) | 0x22;
+		return false;
+	} else {
+		return true;
+	}
 }
 
 int __hyp_text __kvm_vcpu_run(struct kvm_vcpu *vcpu)
@@ -342,13 +355,21 @@ int __hyp_text __kvm_vcpu_run(struct kvm_vcpu *vcpu)
 			int ret = __vgic_v2_perform_cpuif_access(vcpu);
 
 			if (ret == 1) {
-				__skip_instr(vcpu);
-				goto again;
+				if (__skip_instr(vcpu))
+					goto again;
+				else
+					exit_code = ARM_EXCEPTION_TRAP;
 			}
 
 			if (ret == -1) {
-				/* Promote an illegal access to an SError */
-				__skip_instr(vcpu);
+				/* Promote an illegal access to an
+				 * SError. If we would be returning
+				 * due to single-step clear the SS
+				 * bit so handle_exit knows what to
+				 * do after dealing with the error.
+				 */
+				if (!__skip_instr(vcpu))
+					*vcpu_cpsr(vcpu) &= ~DBG_SPSR_SS;
 				exit_code = ARM_EXCEPTION_EL1_SERROR;
 			}
 
@@ -363,8 +384,10 @@ int __hyp_text __kvm_vcpu_run(struct kvm_vcpu *vcpu)
 		int ret = __vgic_v3_perform_cpuif_access(vcpu);
 
 		if (ret == 1) {
-			__skip_instr(vcpu);
-			goto again;
+			if (__skip_instr(vcpu))
+				goto again;
+			else
+				exit_code = ARM_EXCEPTION_TRAP;
 		}
 
 		/* 0 falls through to be handled out of EL2 */

arch/s390/kvm/Makefile

@@ -1,10 +1,7 @@
+# SPDX-License-Identifier: GPL-2.0
 # Makefile for kernel virtual machines on s390
 #
 # Copyright IBM Corp. 2008
-#
-# This program is free software; you can redistribute it and/or modify
-# it under the terms of the GNU General Public License (version 2 only)
-# as published by the Free Software Foundation.
 
 KVM := ../../../virt/kvm
 common-objs = $(KVM)/kvm_main.o $(KVM)/eventfd.o  $(KVM)/async_pf.o $(KVM)/irqchip.o $(KVM)/vfio.o

arch/s390/kvm/diag.c

@@ -1,12 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * handling diagnose instructions
  *
  * Copyright IBM Corp. 2008, 2011
  *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License (version 2 only)
- * as published by the Free Software Foundation.
- *
  *    Author(s): Carsten Otte <[email protected]>
  *               Christian Borntraeger <[email protected]>
  */