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
  ...

24 files changed, 173 insertions, 142 deletions

diff --git a/arch/arm/include/asm/kvm_arm.h b/arch/arm/include/asm/kvm_arm.h
index c8781450905b..3ab8b3781bfe 100644
--- a/arch/arm/include/asm/kvm_arm.h
+++ b/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)
 
diff --git a/arch/arm/include/asm/kvm_host.h b/arch/arm/include/asm/kvm_host.h
index 242151ea6908..a9f7d3f47134 100644
--- a/arch/arm/include/asm/kvm_host.h
+++ b/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);
diff --git a/arch/arm64/include/asm/kvm_arm.h b/arch/arm64/include/asm/kvm_arm.h
index 7f069ff37f06..715d395ef45b 100644
--- a/arch/arm64/include/asm/kvm_arm.h
+++ b/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)
 
diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index 674912d7a571..ea6cb5b24258 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/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,
diff --git a/arch/arm64/kvm/debug.c b/arch/arm64/kvm/debug.c
index dbadfaf850a7..fa63b28c65e0 100644
--- a/arch/arm64/kvm/debug.c
+++ b/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;
+}
diff --git a/arch/arm64/kvm/handle_exit.c b/arch/arm64/kvm/handle_exit.c
index b71247995469..304203fa9e33 100644
--- a/arch/arm64/kvm/handle_exit.c
+++ b/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"
@@ -187,14 +188,46 @@ static exit_handle_fn kvm_get_exit_handler(struct kvm_vcpu *vcpu)
 }
 
 /*
+ * 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
diff --git a/arch/arm64/kvm/hyp/switch.c b/arch/arm64/kvm/hyp/switch.c
index 525c01f48867..f7c651f3a8c0 100644
--- a/arch/arm64/kvm/hyp/switch.c
+++ b/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 @@ again:
 			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 @@ again:
 		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 */
diff --git a/arch/s390/kvm/Makefile b/arch/s390/kvm/Makefile
index 6048b1c6e580..05ee90a5ea08 100644
--- a/arch/s390/kvm/Makefile
+++ b/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
diff --git a/arch/s390/kvm/diag.c b/arch/s390/kvm/diag.c
index d93a2c0474bf..89aa114a2cba 100644
--- a/arch/s390/kvm/diag.c
+++ b/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 <cotte@de.ibm.com>
  *               Christian Borntraeger <borntraeger@de.ibm.com>
  */
diff --git a/arch/s390/kvm/gaccess.h b/arch/s390/kvm/gaccess.h
index bec42b852246..f4c51756c462 100644
--- a/arch/s390/kvm/gaccess.h
+++ b/arch/s390/kvm/gaccess.h
@@ -1,12 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * access guest memory
  *
  * Copyright IBM Corp. 2008, 2014
  *
- * 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 <cotte@de.ibm.com>
  */
 
diff --git a/arch/s390/kvm/guestdbg.c b/arch/s390/kvm/guestdbg.c
index bcbd86621d01..b5f3e82006d0 100644
--- a/arch/s390/kvm/guestdbg.c
+++ b/arch/s390/kvm/guestdbg.c
@@ -1,12 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * kvm guest debug support
  *
  * Copyright IBM Corp. 2014
  *
- * 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): David Hildenbrand <dahi@linux.vnet.ibm.com>
  */
 #include <linux/kvm_host.h>
diff --git a/arch/s390/kvm/intercept.c b/arch/s390/kvm/intercept.c
index 8fe034beb623..9c7d70715862 100644
--- a/arch/s390/kvm/intercept.c
+++ b/arch/s390/kvm/intercept.c
@@ -1,12 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * in-kernel handling for sie intercepts
  *
  * Copyright IBM Corp. 2008, 2014
  *
- * 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 <cotte@de.ibm.com>
  *               Christian Borntraeger <borntraeger@de.ibm.com>
  */
diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c
index fa557372d600..024ad8bcc516 100644
--- a/arch/s390/kvm/interrupt.c
+++ b/arch/s390/kvm/interrupt.c
@@ -1,12 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * handling kvm guest interrupts
  *
  * Copyright IBM Corp. 2008, 2015
  *
- * 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 <cotte@de.ibm.com>
  */
 
diff --git a/arch/s390/kvm/irq.h b/arch/s390/kvm/irq.h
index d98e4159643d..484608c71dd0 100644
--- a/arch/s390/kvm/irq.h
+++ b/arch/s390/kvm/irq.h
@@ -1,12 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * s390 irqchip routines
  *
  * Copyright IBM Corp. 2014
  *
- * 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): Cornelia Huck <cornelia.huck@de.ibm.com>
  */
 #ifndef __KVM_IRQ_H
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index 9614aea5839b..ec8b68e97d3c 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -1,11 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
- * hosting zSeries kernel virtual machines
+ * hosting IBM Z kernel virtual machines (s390x)
  *
- * Copyright IBM Corp. 2008, 2009
- *
- * 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.
+ * Copyright IBM Corp. 2008, 2017
  *
  *    Author(s): Carsten Otte <cotte@de.ibm.com>
  *               Christian Borntraeger <borntraeger@de.ibm.com>
@@ -3808,6 +3805,7 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
 			r = -EINVAL;
 			break;
 		}
+		/* do not use irq_state.flags, it will break old QEMUs */
 		r = kvm_s390_set_irq_state(vcpu,
 					   (void __user *) irq_state.buf,
 					   irq_state.len);
@@ -3823,6 +3821,7 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
 			r = -EINVAL;
 			break;
 		}
+		/* do not use irq_state.flags, it will break old QEMUs */
 		r = kvm_s390_get_irq_state(vcpu,
 					   (__u8 __user *)  irq_state.buf,
 					   irq_state.len);
diff --git a/arch/s390/kvm/kvm-s390.h b/arch/s390/kvm/kvm-s390.h
index 10d65dfbc306..5e46ba429bcb 100644
--- a/arch/s390/kvm/kvm-s390.h
+++ b/arch/s390/kvm/kvm-s390.h
@@ -1,12 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * definition for kvm on s390
  *
  * Copyright IBM Corp. 2008, 2009
  *
- * 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 <cotte@de.ibm.com>
  *               Christian Borntraeger <borntraeger@de.ibm.com>
  *               Christian Ehrhardt <ehrhardt@de.ibm.com>
diff --git a/arch/s390/kvm/priv.c b/arch/s390/kvm/priv.c
index c954ac49eee4..572496c688cc 100644
--- a/arch/s390/kvm/priv.c
+++ b/arch/s390/kvm/priv.c
@@ -1,12 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * handling privileged instructions
  *
  * Copyright IBM Corp. 2008, 2013
  *
- * 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 <cotte@de.ibm.com>
  *               Christian Borntraeger <borntraeger@de.ibm.com>
  */
@@ -235,8 +232,6 @@ static int try_handle_skey(struct kvm_vcpu *vcpu)
 		VCPU_EVENT(vcpu, 4, "%s", "retrying storage key operation");
 		return -EAGAIN;
 	}
-	if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE)
-		return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP);
 	return 0;
 }
 
@@ -247,6 +242,9 @@ static int handle_iske(struct kvm_vcpu *vcpu)
 	int reg1, reg2;
 	int rc;
 
+	if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE)
+		return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP);
+
 	rc = try_handle_skey(vcpu);
 	if (rc)
 		return rc != -EAGAIN ? rc : 0;
@@ -276,6 +274,9 @@ static int handle_rrbe(struct kvm_vcpu *vcpu)
 	int reg1, reg2;
 	int rc;
 
+	if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE)
+		return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP);
+
 	rc = try_handle_skey(vcpu);
 	if (rc)
 		return rc != -EAGAIN ? rc : 0;
@@ -311,6 +312,9 @@ static int handle_sske(struct kvm_vcpu *vcpu)
 	int reg1, reg2;
 	int rc;
 
+	if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE)
+		return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP);
+
 	rc = try_handle_skey(vcpu);
 	if (rc)
 		return rc != -EAGAIN ? rc : 0;
diff --git a/arch/s390/kvm/sigp.c b/arch/s390/kvm/sigp.c
index 9d592ef4104b..c1f5cde2c878 100644
--- a/arch/s390/kvm/sigp.c
+++ b/arch/s390/kvm/sigp.c
@@ -1,12 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * handling interprocessor communication
  *
  * Copyright IBM Corp. 2008, 2013
  *
- * 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 <cotte@de.ibm.com>
  *               Christian Borntraeger <borntraeger@de.ibm.com>
  *               Christian Ehrhardt <ehrhardt@de.ibm.com>
diff --git a/arch/s390/kvm/vsie.c b/arch/s390/kvm/vsie.c
index a311938b63b3..5d6ae0326d9e 100644
--- a/arch/s390/kvm/vsie.c
+++ b/arch/s390/kvm/vsie.c
@@ -1,12 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * kvm nested virtualization support for s390x
  *
  * Copyright IBM Corp. 2016
  *
- * 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): David Hildenbrand <dahi@linux.vnet.ibm.com>
  */
 #include <linux/vmalloc.h>
diff --git a/arch/x86/include/asm/kvm_emulate.h b/arch/x86/include/asm/kvm_emulate.h
index 034caa1a084e..b24b1c8b3979 100644
--- a/arch/x86/include/asm/kvm_emulate.h
+++ b/arch/x86/include/asm/kvm_emulate.h
@@ -214,8 +214,6 @@ struct x86_emulate_ops {
 	void (*halt)(struct x86_emulate_ctxt *ctxt);
 	void (*wbinvd)(struct x86_emulate_ctxt *ctxt);
 	int (*fix_hypercall)(struct x86_emulate_ctxt *ctxt);
-	void (*get_fpu)(struct x86_emulate_ctxt *ctxt); /* disables preempt */
-	void (*put_fpu)(struct x86_emulate_ctxt *ctxt); /* reenables preempt */
 	int (*intercept)(struct x86_emulate_ctxt *ctxt,
 			 struct x86_instruction_info *info,
 			 enum x86_intercept_stage stage);
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 977de5fb968b..516798431328 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -536,7 +536,20 @@ struct kvm_vcpu_arch {
 	struct kvm_mmu_memory_cache mmu_page_cache;
 	struct kvm_mmu_memory_cache mmu_page_header_cache;
 
+	/*
+	 * QEMU userspace and the guest each have their own FPU state.
+	 * In vcpu_run, we switch between the user and guest FPU contexts.
+	 * While running a VCPU, the VCPU thread will have the guest FPU
+	 * context.
+	 *
+	 * Note that while the PKRU state lives inside the fpu registers,
+	 * it is switched out separately at VMENTER and VMEXIT time. The
+	 * "guest_fpu" state here contains the guest FPU context, with the
+	 * host PRKU bits.
+	 */
+	struct fpu user_fpu;
 	struct fpu guest_fpu;
+
 	u64 xcr0;
 	u64 guest_supported_xcr0;
 	u32 guest_xstate_size;
@@ -1435,4 +1448,7 @@ static inline int kvm_cpu_get_apicid(int mps_cpu)
 #define put_smstate(type, buf, offset, val)                      \
 	*(type *)((buf) + (offset) - 0x7e00) = val
 
+void kvm_arch_mmu_notifier_invalidate_range(struct kvm *kvm,
+		unsigned long start, unsigned long end);
+
 #endif /* _ASM_X86_KVM_HOST_H */
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index e7d04d0c8008..abe74f779f9d 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -1046,7 +1046,6 @@ static void fetch_register_operand(struct operand *op)
 
 static void read_sse_reg(struct x86_emulate_ctxt *ctxt, sse128_t *data, int reg)
 {
-	ctxt->ops->get_fpu(ctxt);
 	switch (reg) {
 	case 0: asm("movdqa %%xmm0, %0" : "=m"(*data)); break;
 	case 1: asm("movdqa %%xmm1, %0" : "=m"(*data)); break;
@@ -1068,13 +1067,11 @@ static void read_sse_reg(struct x86_emulate_ctxt *ctxt, sse128_t *data, int reg)
 #endif
 	default: BUG();
 	}
-	ctxt->ops->put_fpu(ctxt);
 }
 
 static void write_sse_reg(struct x86_emulate_ctxt *ctxt, sse128_t *data,
 			  int reg)
 {
-	ctxt->ops->get_fpu(ctxt);
 	switch (reg) {
 	case 0: asm("movdqa %0, %%xmm0" : : "m"(*data)); break;
 	case 1: asm("movdqa %0, %%xmm1" : : "m"(*data)); break;
@@ -1096,12 +1093,10 @@ static void write_sse_reg(struct x86_emulate_ctxt *ctxt, sse128_t *data,
 #endif
 	default: BUG();
 	}
-	ctxt->ops->put_fpu(ctxt);
 }
 
 static void read_mmx_reg(struct x86_emulate_ctxt *ctxt, u64 *data, int reg)
 {
-	ctxt->ops->get_fpu(ctxt);
 	switch (reg) {
 	case 0: asm("movq %%mm0, %0" : "=m"(*data)); break;
 	case 1: asm("movq %%mm1, %0" : "=m"(*data)); break;
@@ -1113,12 +1108,10 @@ static void read_mmx_reg(struct x86_emulate_ctxt *ctxt, u64 *data, int reg)
 	case 7: asm("movq %%mm7, %0" : "=m"(*data)); break;
 	default: BUG();
 	}
-	ctxt->ops->put_fpu(ctxt);
 }
 
 static void write_mmx_reg(struct x86_emulate_ctxt *ctxt, u64 *data, int reg)
 {
-	ctxt->ops->get_fpu(ctxt);
 	switch (reg) {
 	case 0: asm("movq %0, %%mm0" : : "m"(*data)); break;
 	case 1: asm("movq %0, %%mm1" : : "m"(*data)); break;
@@ -1130,7 +1123,6 @@ static void write_mmx_reg(struct x86_emulate_ctxt *ctxt, u64 *data, int reg)
 	case 7: asm("movq %0, %%mm7" : : "m"(*data)); break;
 	default: BUG();
 	}
-	ctxt->ops->put_fpu(ctxt);
 }
 
 static int em_fninit(struct x86_emulate_ctxt *ctxt)
@@ -1138,9 +1130,7 @@ static int em_fninit(struct x86_emulate_ctxt *ctxt)
 	if (ctxt->ops->get_cr(ctxt, 0) & (X86_CR0_TS | X86_CR0_EM))
 		return emulate_nm(ctxt);
 
-	ctxt->ops->get_fpu(ctxt);
 	asm volatile("fninit");
-	ctxt->ops->put_fpu(ctxt);
 	return X86EMUL_CONTINUE;
 }
 
@@ -1151,9 +1141,7 @@ static int em_fnstcw(struct x86_emulate_ctxt *ctxt)
 	if (ctxt->ops->get_cr(ctxt, 0) & (X86_CR0_TS | X86_CR0_EM))
 		return emulate_nm(ctxt);
 
-	ctxt->ops->get_fpu(ctxt);
 	asm volatile("fnstcw %0": "+m"(fcw));
-	ctxt->ops->put_fpu(ctxt);
 
 	ctxt->dst.val = fcw;
 
@@ -1167,9 +1155,7 @@ static int em_fnstsw(struct x86_emulate_ctxt *ctxt)
 	if (ctxt->ops->get_cr(ctxt, 0) & (X86_CR0_TS | X86_CR0_EM))
 		return emulate_nm(ctxt);
 
-	ctxt->ops->get_fpu(ctxt);
 	asm volatile("fnstsw %0": "+m"(fsw));
-	ctxt->ops->put_fpu(ctxt);
 
 	ctxt->dst.val = fsw;
 
@@ -4001,12 +3987,8 @@ static int em_fxsave(struct x86_emulate_ctxt *ctxt)
 	if (rc != X86EMUL_CONTINUE)
 		return rc;
 
-	ctxt->ops->get_fpu(ctxt);
-
 	rc = asm_safe("fxsave %[fx]", , [fx] "+m"(fx_state));
 
-	ctxt->ops->put_fpu(ctxt);
-
 	if (rc != X86EMUL_CONTINUE)
 		return rc;
 
@@ -4049,8 +4031,6 @@ static int em_fxrstor(struct x86_emulate_ctxt *ctxt)
 	if (rc != X86EMUL_CONTINUE)
 		return rc;
 
-	ctxt->ops->get_fpu(ctxt);
-
 	if (size < __fxstate_size(16)) {
 		rc = fxregs_fixup(&fx_state, size);
 		if (rc != X86EMUL_CONTINUE)
@@ -4066,8 +4046,6 @@ static int em_fxrstor(struct x86_emulate_ctxt *ctxt)
 		rc = asm_safe("fxrstor %[fx]", : [fx] "m"(fx_state));
 
 out:
-	ctxt->ops->put_fpu(ctxt);
-
 	return rc;
 }
 
@@ -5317,9 +5295,7 @@ static int flush_pending_x87_faults(struct x86_emulate_ctxt *ctxt)
 {
 	int rc;
 
-	ctxt->ops->get_fpu(ctxt);
 	rc = asm_safe("fwait");
-	ctxt->ops->put_fpu(ctxt);
 
 	if (unlikely(rc != X86EMUL_CONTINUE))
 		return emulate_exception(ctxt, MF_VECTOR, 0, false);
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 4704aaf6d19e..8eba631c4dbd 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -6751,16 +6751,10 @@ static __init int hardware_setup(void)
 			goto out;
 	}
 
-	vmx_io_bitmap_b = (unsigned long *)__get_free_page(GFP_KERNEL);
 	memset(vmx_vmread_bitmap, 0xff, PAGE_SIZE);
 	memset(vmx_vmwrite_bitmap, 0xff, PAGE_SIZE);
 
-	/*
-	 * Allow direct access to the PC debug port (it is often used for I/O
-	 * delays, but the vmexits simply slow things down).
-	 */
 	memset(vmx_io_bitmap_a, 0xff, PAGE_SIZE);
-	clear_bit(0x80, vmx_io_bitmap_a);
 
 	memset(vmx_io_bitmap_b, 0xff, PAGE_SIZE);
 
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index eee8e7faf1af..faf843c9b916 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -2937,7 +2937,6 @@ void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
 	srcu_read_unlock(&vcpu->kvm->srcu, idx);
 	pagefault_enable();
 	kvm_x86_ops->vcpu_put(vcpu);
-	kvm_put_guest_fpu(vcpu);
 	vcpu->arch.last_host_tsc = rdtsc();
 }
 
@@ -5252,17 +5251,6 @@ static void emulator_halt(struct x86_emulate_ctxt *ctxt)
 	emul_to_vcpu(ctxt)->arch.halt_request = 1;
 }
 
-static void emulator_get_fpu(struct x86_emulate_ctxt *ctxt)
-{
-	preempt_disable();
-	kvm_load_guest_fpu(emul_to_vcpu(ctxt));
-}
-
-static void emulator_put_fpu(struct x86_emulate_ctxt *ctxt)
-{
-	preempt_enable();
-}
-
 static int emulator_intercept(struct x86_emulate_ctxt *ctxt,
 			      struct x86_instruction_info *info,
 			      enum x86_intercept_stage stage)
@@ -5340,8 +5328,6 @@ static const struct x86_emulate_ops emulate_ops = {
 	.halt                = emulator_halt,
 	.wbinvd              = emulator_wbinvd,
 	.fix_hypercall       = emulator_fix_hypercall,
-	.get_fpu             = emulator_get_fpu,
-	.put_fpu             = emulator_put_fpu,
 	.intercept           = emulator_intercept,
 	.get_cpuid           = emulator_get_cpuid,
 	.set_nmi_mask        = emulator_set_nmi_mask,
@@ -6778,6 +6764,20 @@ static void kvm_vcpu_flush_tlb(struct kvm_vcpu *vcpu)
 	kvm_x86_ops->tlb_flush(vcpu);
 }
 
+void kvm_arch_mmu_notifier_invalidate_range(struct kvm *kvm,
+		unsigned long start, unsigned long end)
+{
+	unsigned long apic_address;
+
+	/*
+	 * The physical address of apic access page is stored in the VMCS.
+	 * Update it when it becomes invalid.
+	 */
+	apic_address = gfn_to_hva(kvm, APIC_DEFAULT_PHYS_BASE >> PAGE_SHIFT);
+	if (start <= apic_address && apic_address < end)
+		kvm_make_all_cpus_request(kvm, KVM_REQ_APIC_PAGE_RELOAD);
+}
+
 void kvm_vcpu_reload_apic_access_page(struct kvm_vcpu *vcpu)
 {
 	struct page *page = NULL;
@@ -6952,7 +6952,6 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 	preempt_disable();
 
 	kvm_x86_ops->prepare_guest_switch(vcpu);
-	kvm_load_guest_fpu(vcpu);
 
 	/*
 	 * Disable IRQs before setting IN_GUEST_MODE.  Posted interrupt
@@ -7297,12 +7296,14 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 		}
 	}
 
+	kvm_load_guest_fpu(vcpu);
+
 	if (unlikely(vcpu->arch.complete_userspace_io)) {
 		int (*cui)(struct kvm_vcpu *) = vcpu->arch.complete_userspace_io;
 		vcpu->arch.complete_userspace_io = NULL;
 		r = cui(vcpu);
 		if (r <= 0)
-			goto out;
+			goto out_fpu;
 	} else
 		WARN_ON(vcpu->arch.pio.count || vcpu->mmio_needed);
 
@@ -7311,6 +7312,8 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 	else
 		r = vcpu_run(vcpu);
 
+out_fpu:
+	kvm_put_guest_fpu(vcpu);
 out:
 	post_kvm_run_save(vcpu);
 	kvm_sigset_deactivate(vcpu);
@@ -7704,32 +7707,25 @@ static void fx_init(struct kvm_vcpu *vcpu)
 	vcpu->arch.cr0 |= X86_CR0_ET;
 }
 
+/* Swap (qemu) user FPU context for the guest FPU context. */
 void kvm_load_guest_fpu(struct kvm_vcpu *vcpu)
 {
-	if (vcpu->guest_fpu_loaded)
-		return;
-
-	/*
-	 * Restore all possible states in the guest,
-	 * and assume host would use all available bits.
-	 * Guest xcr0 would be loaded later.
-	 */
-	vcpu->guest_fpu_loaded = 1;
-	__kernel_fpu_begin();
+	preempt_disable();
+	copy_fpregs_to_fpstate(&vcpu->arch.user_fpu);
 	/* PKRU is separately restored in kvm_x86_ops->run.  */
 	__copy_kernel_to_fpregs(&vcpu->arch.guest_fpu.state,
 				~XFEATURE_MASK_PKRU);
+	preempt_enable();
 	trace_kvm_fpu(1);
 }
 
+/* When vcpu_run ends, restore user space FPU context. */
 void kvm_put_guest_fpu(struct kvm_vcpu *vcpu)
 {
-	if (!vcpu->guest_fpu_loaded)
-		return;
-
-	vcpu->guest_fpu_loaded = 0;
+	preempt_disable();
 	copy_fpregs_to_fpstate(&vcpu->arch.guest_fpu);
-	__kernel_fpu_end();
+	copy_kernel_to_fpregs(&vcpu->arch.user_fpu.state);
+	preempt_enable();
 	++vcpu->stat.fpu_reload;
 	trace_kvm_fpu(0);
 }
@@ -7846,7 +7842,8 @@ void kvm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event)
 		 * To avoid have the INIT path from kvm_apic_has_events() that be
 		 * called with loaded FPU and does not let userspace fix the state.
 		 */
-		kvm_put_guest_fpu(vcpu);
+		if (init_event)
+			kvm_put_guest_fpu(vcpu);
 		mpx_state_buffer = get_xsave_addr(&vcpu->arch.guest_fpu.state.xsave,
 					XFEATURE_MASK_BNDREGS);
 		if (mpx_state_buffer)
@@ -7855,6 +7852,8 @@ void kvm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event)
 					XFEATURE_MASK_BNDCSR);
 		if (mpx_state_buffer)
 			memset(mpx_state_buffer, 0, sizeof(struct mpx_bndcsr));
+		if (init_event)
+			kvm_load_guest_fpu(vcpu);
 	}
 
 	if (!init_event) {