Merge branch 'fixes' of git://git.kernel.org/pub/scm/virt/kvm/kvm

Pull kvm bugfixes from Gleb Natapov:
 "The bulk of the fixes is in MIPS KVM kernel<->userspace ABI.  MIPS KVM
  is new for 3.10 and some problems were found with current ABI.  It is
  better to fix them now and do not have a kernel with broken one"

* 'fixes' of git://git.kernel.org/pub/scm/virt/kvm/kvm:
  KVM: Fix race in apic->pending_events processing
  KVM: fix sil/dil/bpl/spl in the mod/rm fields
  KVM: Emulate multibyte NOP
  ARM: KVM: be more thorough when invalidating TLBs
  ARM: KVM: prevent NULL pointer dereferences with KVM VCPU ioctl
  mips/kvm: Use ENOIOCTLCMD to indicate unimplemented ioctls.
  mips/kvm: Fix ABI by moving manipulation of CP0 registers to KVM_{G,S}ET_ONE_REG
  mips/kvm: Use ARRAY_SIZE() instead of hardcoded constants in kvm_arch_vcpu_ioctl_{s,g}et_regs
  mips/kvm: Fix name of gpr field in struct kvm_regs.
  mips/kvm: Fix ABI for use of 64-bit registers.
  mips/kvm: Fix ABI for use of FPU.

arch/arm/kvm/arm.c

@@ -492,6 +492,11 @@ static void vcpu_pause(struct kvm_vcpu *vcpu)
 	wait_event_interruptible(*wq, !vcpu->arch.pause);
 }
 
+static int kvm_vcpu_initialized(struct kvm_vcpu *vcpu)
+{
+	return vcpu->arch.target >= 0;
+}
+
 /**
  * kvm_arch_vcpu_ioctl_run - the main VCPU run function to execute guest code
  * @vcpu:	The VCPU pointer
@@ -508,8 +513,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run)
 	int ret;
 	sigset_t sigsaved;
 
-	/* Make sure they initialize the vcpu with KVM_ARM_VCPU_INIT */
-	if (unlikely(vcpu->arch.target < 0))
+	if (unlikely(!kvm_vcpu_initialized(vcpu)))
 		return -ENOEXEC;
 
 	ret = kvm_vcpu_first_run_init(vcpu);
@@ -710,6 +714,10 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
 	case KVM_SET_ONE_REG:
 	case KVM_GET_ONE_REG: {
 		struct kvm_one_reg reg;
+
+		if (unlikely(!kvm_vcpu_initialized(vcpu)))
+			return -ENOEXEC;
+
 		if (copy_from_user(&reg, argp, sizeof(reg)))
 			return -EFAULT;
 		if (ioctl == KVM_SET_ONE_REG)
@@ -722,6 +730,9 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
 		struct kvm_reg_list reg_list;
 		unsigned n;
 
+		if (unlikely(!kvm_vcpu_initialized(vcpu)))
+			return -ENOEXEC;
+
 		if (copy_from_user(&reg_list, user_list, sizeof(reg_list)))
 			return -EFAULT;
 		n = reg_list.n;

arch/arm/kvm/mmu.c

@@ -43,6 +43,13 @@ static phys_addr_t hyp_idmap_vector;
 
 static void kvm_tlb_flush_vmid_ipa(struct kvm *kvm, phys_addr_t ipa)
 {
+	/*
+	 * This function also gets called when dealing with HYP page
+	 * tables. As HYP doesn't have an associated struct kvm (and
+	 * the HYP page tables are fairly static), we don't do
+	 * anything there.
+	 */
+	if (kvm)
 		kvm_call_hyp(__kvm_tlb_flush_vmid_ipa, kvm, ipa);
 }
 
@@ -78,18 +85,20 @@ static void *mmu_memory_cache_alloc(struct kvm_mmu_memory_cache *mc)
 	return p;
 }
 
-static void clear_pud_entry(pud_t *pud)
+static void clear_pud_entry(struct kvm *kvm, pud_t *pud, phys_addr_t addr)
 {
 	pmd_t *pmd_table = pmd_offset(pud, 0);
 	pud_clear(pud);
+	kvm_tlb_flush_vmid_ipa(kvm, addr);
 	pmd_free(NULL, pmd_table);
 	put_page(virt_to_page(pud));
 }
 
-static void clear_pmd_entry(pmd_t *pmd)
+static void clear_pmd_entry(struct kvm *kvm, pmd_t *pmd, phys_addr_t addr)
 {
 	pte_t *pte_table = pte_offset_kernel(pmd, 0);
 	pmd_clear(pmd);
+	kvm_tlb_flush_vmid_ipa(kvm, addr);
 	pte_free_kernel(NULL, pte_table);
 	put_page(virt_to_page(pmd));
 }
@@ -100,11 +109,12 @@ static bool pmd_empty(pmd_t *pmd)
 	return page_count(pmd_page) == 1;
 }
 
-static void clear_pte_entry(pte_t *pte)
+static void clear_pte_entry(struct kvm *kvm, pte_t *pte, phys_addr_t addr)
 {
 	if (pte_present(*pte)) {
 		kvm_set_pte(pte, __pte(0));
 		put_page(virt_to_page(pte));
+		kvm_tlb_flush_vmid_ipa(kvm, addr);
 	}
 }
 
@@ -114,7 +124,8 @@ static bool pte_empty(pte_t *pte)
 	return page_count(pte_page) == 1;
 }
 
-static void unmap_range(pgd_t *pgdp, unsigned long long start, u64 size)
+static void unmap_range(struct kvm *kvm, pgd_t *pgdp,
+			unsigned long long start, u64 size)
 {
 	pgd_t *pgd;
 	pud_t *pud;
@@ -138,15 +149,15 @@ static void unmap_range(pgd_t *pgdp, unsigned long long start, u64 size)
 		}
 
 		pte = pte_offset_kernel(pmd, addr);
-		clear_pte_entry(pte);
+		clear_pte_entry(kvm, pte, addr);
 		range = PAGE_SIZE;
 
 		/* If we emptied the pte, walk back up the ladder */
 		if (pte_empty(pte)) {
-			clear_pmd_entry(pmd);
+			clear_pmd_entry(kvm, pmd, addr);
 			range = PMD_SIZE;
 			if (pmd_empty(pmd)) {
-				clear_pud_entry(pud);
+				clear_pud_entry(kvm, pud, addr);
 				range = PUD_SIZE;
 			}
 		}
@@ -165,14 +176,14 @@ void free_boot_hyp_pgd(void)
 	mutex_lock(&kvm_hyp_pgd_mutex);
 
 	if (boot_hyp_pgd) {
-		unmap_range(boot_hyp_pgd, hyp_idmap_start, PAGE_SIZE);
-		unmap_range(boot_hyp_pgd, TRAMPOLINE_VA, PAGE_SIZE);
+		unmap_range(NULL, boot_hyp_pgd, hyp_idmap_start, PAGE_SIZE);
+		unmap_range(NULL, boot_hyp_pgd, TRAMPOLINE_VA, PAGE_SIZE);
 		kfree(boot_hyp_pgd);
 		boot_hyp_pgd = NULL;
 	}
 
 	if (hyp_pgd)
-		unmap_range(hyp_pgd, TRAMPOLINE_VA, PAGE_SIZE);
+		unmap_range(NULL, hyp_pgd, TRAMPOLINE_VA, PAGE_SIZE);
 
 	kfree(init_bounce_page);
 	init_bounce_page = NULL;
@@ -200,9 +211,10 @@ void free_hyp_pgds(void)
 
 	if (hyp_pgd) {
 		for (addr = PAGE_OFFSET; virt_addr_valid(addr); addr += PGDIR_SIZE)
-			unmap_range(hyp_pgd, KERN_TO_HYP(addr), PGDIR_SIZE);
+			unmap_range(NULL, hyp_pgd, KERN_TO_HYP(addr), PGDIR_SIZE);
 		for (addr = VMALLOC_START; is_vmalloc_addr((void*)addr); addr += PGDIR_SIZE)
-			unmap_range(hyp_pgd, KERN_TO_HYP(addr), PGDIR_SIZE);
+			unmap_range(NULL, hyp_pgd, KERN_TO_HYP(addr), PGDIR_SIZE);
+
 		kfree(hyp_pgd);
 		hyp_pgd = NULL;
 	}
@@ -393,7 +405,7 @@ int kvm_alloc_stage2_pgd(struct kvm *kvm)
  */
 static void unmap_stage2_range(struct kvm *kvm, phys_addr_t start, u64 size)
 {
-	unmap_range(kvm->arch.pgd, start, size);
+	unmap_range(kvm, kvm->arch.pgd, start, size);
 }
 
 /**
@@ -675,7 +687,6 @@ static void handle_hva_to_gpa(struct kvm *kvm,
 static void kvm_unmap_hva_handler(struct kvm *kvm, gpa_t gpa, void *data)
 {
 	unmap_stage2_range(kvm, gpa, PAGE_SIZE);
-	kvm_tlb_flush_vmid_ipa(kvm, gpa);
 }
 
 int kvm_unmap_hva(struct kvm *kvm, unsigned long hva)

arch/mips/include/asm/kvm_host.h

@@ -496,10 +496,6 @@ struct kvm_mips_callbacks {
 			    uint32_t cause);
 	int (*irq_clear) (struct kvm_vcpu *vcpu, unsigned int priority,
 			  uint32_t cause);
-	int (*vcpu_ioctl_get_regs) (struct kvm_vcpu *vcpu,
-				    struct kvm_regs *regs);
-	int (*vcpu_ioctl_set_regs) (struct kvm_vcpu *vcpu,
-				    struct kvm_regs *regs);
 };
 extern struct kvm_mips_callbacks *kvm_mips_callbacks;
 int kvm_mips_emulation_init(struct kvm_mips_callbacks **install_callbacks);

arch/mips/include/uapi/asm/kvm.h

 /*
-* This file is subject to the terms and conditions of the GNU General Public
-* License.  See the file "COPYING" in the main directory of this archive
-* for more details.
-*
-* Copyright (C) 2012  MIPS Technologies, Inc.  All rights reserved.
-* Authors: Sanjay Lal <sanjayl@kymasys.com>
-*/
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ *
+ * Copyright (C) 2012  MIPS Technologies, Inc.  All rights reserved.
+ * Copyright (C) 2013 Cavium, Inc.
+ * Authors: Sanjay Lal <sanjayl@kymasys.com>
+ */
 
 #ifndef __LINUX_KVM_MIPS_H
 #define __LINUX_KVM_MIPS_H
 
 #include <linux/types.h>
 
-#define __KVM_MIPS
-
-#define N_MIPS_COPROC_REGS      32
-#define N_MIPS_COPROC_SEL   	8
+/*
+ * KVM MIPS specific structures and definitions.
+ *
+ * Some parts derived from the x86 version of this file.
+ */
 
-/* for KVM_GET_REGS and KVM_SET_REGS */
+/*
+ * for KVM_GET_REGS and KVM_SET_REGS
+ *
+ * If Config[AT] is zero (32-bit CPU), the register contents are
+ * stored in the lower 32-bits of the struct kvm_regs fields and sign
+ * extended to 64-bits.
+ */
 struct kvm_regs {
-	__u32 gprs[32];
-	__u32 hi;
-	__u32 lo;
-	__u32 pc;
-
-	__u32 cp0reg[N_MIPS_COPROC_REGS][N_MIPS_COPROC_SEL];
-};
-
-/* for KVM_GET_SREGS and KVM_SET_SREGS */
-struct kvm_sregs {
+	/* out (KVM_GET_REGS) / in (KVM_SET_REGS) */
+	__u64 gpr[32];
+	__u64 hi;
+	__u64 lo;
+	__u64 pc;
 };
 
-/* for KVM_GET_FPU and KVM_SET_FPU */
+/*
+ * for KVM_GET_FPU and KVM_SET_FPU
+ *
+ * If Status[FR] is zero (32-bit FPU), the upper 32-bits of the FPRs
+ * are zero filled.
+ */
 struct kvm_fpu {
+	__u64 fpr[32];
+	__u32 fir;
+	__u32 fccr;
+	__u32 fexr;
+	__u32 fenr;
+	__u32 fcsr;
+	__u32 pad;
 };
 
+
+/*
+ * For MIPS, we use KVM_SET_ONE_REG and KVM_GET_ONE_REG to access CP0
+ * registers.  The id field is broken down as follows:
+ *
+ *  bits[2..0]   - Register 'sel' index.
+ *  bits[7..3]   - Register 'rd'  index.
+ *  bits[15..8]  - Must be zero.
+ *  bits[63..16] - 1 -> CP0 registers.
+ *
+ * Other sets registers may be added in the future.  Each set would
+ * have its own identifier in bits[63..16].
+ *
+ * The addr field of struct kvm_one_reg must point to an aligned
+ * 64-bit wide location.  For registers that are narrower than
+ * 64-bits, the value is stored in the low order bits of the location,
+ * and sign extended to 64-bits.
+ *
+ * The registers defined in struct kvm_regs are also accessible, the
+ * id values for these are below.
+ */
+
+#define KVM_REG_MIPS_R0 0
+#define KVM_REG_MIPS_R1 1
+#define KVM_REG_MIPS_R2 2
+#define KVM_REG_MIPS_R3 3
+#define KVM_REG_MIPS_R4 4
+#define KVM_REG_MIPS_R5 5
+#define KVM_REG_MIPS_R6 6
+#define KVM_REG_MIPS_R7 7
+#define KVM_REG_MIPS_R8 8
+#define KVM_REG_MIPS_R9 9
+#define KVM_REG_MIPS_R10 10
+#define KVM_REG_MIPS_R11 11
+#define KVM_REG_MIPS_R12 12
+#define KVM_REG_MIPS_R13 13
+#define KVM_REG_MIPS_R14 14
+#define KVM_REG_MIPS_R15 15
+#define KVM_REG_MIPS_R16 16
+#define KVM_REG_MIPS_R17 17
+#define KVM_REG_MIPS_R18 18
+#define KVM_REG_MIPS_R19 19
+#define KVM_REG_MIPS_R20 20
+#define KVM_REG_MIPS_R21 21
+#define KVM_REG_MIPS_R22 22
+#define KVM_REG_MIPS_R23 23
+#define KVM_REG_MIPS_R24 24
+#define KVM_REG_MIPS_R25 25
+#define KVM_REG_MIPS_R26 26
+#define KVM_REG_MIPS_R27 27
+#define KVM_REG_MIPS_R28 28
+#define KVM_REG_MIPS_R29 29
+#define KVM_REG_MIPS_R30 30
+#define KVM_REG_MIPS_R31 31
+
+#define KVM_REG_MIPS_HI 32
+#define KVM_REG_MIPS_LO 33
+#define KVM_REG_MIPS_PC 34
+
+/*
+ * KVM MIPS specific structures and definitions
+ *
+ */
 struct kvm_debug_exit_arch {
+	__u64 epc;
 };
 
 /* for KVM_SET_GUEST_DEBUG */
 struct kvm_guest_debug_arch {
 };
 
+/* definition of registers in kvm_run */
+struct kvm_sync_regs {
+};
+
+/* dummy definition */
+struct kvm_sregs {
+};
+
 struct kvm_mips_interrupt {
 	/* in */
 	__u32 cpu;
 	__u32 irq;
 };
 
-/* definition of registers in kvm_run */
-struct kvm_sync_regs {
-};
-
 #endif /* __LINUX_KVM_MIPS_H */

arch/mips/kvm/kvm_trap_emul.c

@@ -345,54 +345,6 @@ static int kvm_trap_emul_handle_break(struct kvm_vcpu *vcpu)
 	return ret;
 }
 
-static int
-kvm_trap_emul_ioctl_set_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
-{
-	struct mips_coproc *cop0 = vcpu->arch.cop0;
-
-	kvm_write_c0_guest_index(cop0, regs->cp0reg[MIPS_CP0_TLB_INDEX][0]);
-	kvm_write_c0_guest_context(cop0, regs->cp0reg[MIPS_CP0_TLB_CONTEXT][0]);
-	kvm_write_c0_guest_badvaddr(cop0, regs->cp0reg[MIPS_CP0_BAD_VADDR][0]);
-	kvm_write_c0_guest_entryhi(cop0, regs->cp0reg[MIPS_CP0_TLB_HI][0]);
-	kvm_write_c0_guest_epc(cop0, regs->cp0reg[MIPS_CP0_EXC_PC][0]);
-
-	kvm_write_c0_guest_status(cop0, regs->cp0reg[MIPS_CP0_STATUS][0]);
-	kvm_write_c0_guest_cause(cop0, regs->cp0reg[MIPS_CP0_CAUSE][0]);
-	kvm_write_c0_guest_pagemask(cop0,
-				    regs->cp0reg[MIPS_CP0_TLB_PG_MASK][0]);
-	kvm_write_c0_guest_wired(cop0, regs->cp0reg[MIPS_CP0_TLB_WIRED][0]);
-	kvm_write_c0_guest_errorepc(cop0, regs->cp0reg[MIPS_CP0_ERROR_PC][0]);
-
-	return 0;
-}
-
-static int
-kvm_trap_emul_ioctl_get_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
-{
-	struct mips_coproc *cop0 = vcpu->arch.cop0;
-
-	regs->cp0reg[MIPS_CP0_TLB_INDEX][0] = kvm_read_c0_guest_index(cop0);
-	regs->cp0reg[MIPS_CP0_TLB_CONTEXT][0] = kvm_read_c0_guest_context(cop0);
-	regs->cp0reg[MIPS_CP0_BAD_VADDR][0] = kvm_read_c0_guest_badvaddr(cop0);
-	regs->cp0reg[MIPS_CP0_TLB_HI][0] = kvm_read_c0_guest_entryhi(cop0);
-	regs->cp0reg[MIPS_CP0_EXC_PC][0] = kvm_read_c0_guest_epc(cop0);
-
-	regs->cp0reg[MIPS_CP0_STATUS][0] = kvm_read_c0_guest_status(cop0);
-	regs->cp0reg[MIPS_CP0_CAUSE][0] = kvm_read_c0_guest_cause(cop0);
-	regs->cp0reg[MIPS_CP0_TLB_PG_MASK][0] =
-	    kvm_read_c0_guest_pagemask(cop0);
-	regs->cp0reg[MIPS_CP0_TLB_WIRED][0] = kvm_read_c0_guest_wired(cop0);
-	regs->cp0reg[MIPS_CP0_ERROR_PC][0] = kvm_read_c0_guest_errorepc(cop0);
-
-	regs->cp0reg[MIPS_CP0_CONFIG][0] = kvm_read_c0_guest_config(cop0);
-	regs->cp0reg[MIPS_CP0_CONFIG][1] = kvm_read_c0_guest_config1(cop0);
-	regs->cp0reg[MIPS_CP0_CONFIG][2] = kvm_read_c0_guest_config2(cop0);
-	regs->cp0reg[MIPS_CP0_CONFIG][3] = kvm_read_c0_guest_config3(cop0);
-	regs->cp0reg[MIPS_CP0_CONFIG][7] = kvm_read_c0_guest_config7(cop0);
-
-	return 0;
-}
-
 static int kvm_trap_emul_vm_init(struct kvm *kvm)
 {
 	return 0;
@@ -471,8 +423,6 @@ static struct kvm_mips_callbacks kvm_trap_emul_callbacks = {
 	.dequeue_io_int = kvm_mips_dequeue_io_int_cb,
 	.irq_deliver = kvm_mips_irq_deliver_cb,
 	.irq_clear = kvm_mips_irq_clear_cb,
-	.vcpu_ioctl_get_regs = kvm_trap_emul_ioctl_get_regs,
-	.vcpu_ioctl_set_regs = kvm_trap_emul_ioctl_set_regs,
 };
 
 int kvm_mips_emulation_init(struct kvm_mips_callbacks **install_callbacks)

arch/x86/kvm/emulate.c

@@ -1240,9 +1240,12 @@ static int decode_modrm(struct x86_emulate_ctxt *ctxt,
 	ctxt->modrm_seg = VCPU_SREG_DS;
 
 	if (ctxt->modrm_mod == 3) {
+		int highbyte_regs = ctxt->rex_prefix == 0;
+
 		op->type = OP_REG;
 		op->bytes = (ctxt->d & ByteOp) ? 1 : ctxt->op_bytes;
-		op->addr.reg = decode_register(ctxt, ctxt->modrm_rm, ctxt->d & ByteOp);
+		op->addr.reg = decode_register(ctxt, ctxt->modrm_rm,
+					       highbyte_regs && (ctxt->d & ByteOp));
 		if (ctxt->d & Sse) {
 			op->type = OP_XMM;
 			op->bytes = 16;
@@ -3997,7 +4000,8 @@ static const struct opcode twobyte_table[256] = {
 	DI(ImplicitOps | Priv, invd), DI(ImplicitOps | Priv, wbinvd), N, N,
 	N, D(ImplicitOps | ModRM), N, N,
 	/* 0x10 - 0x1F */
-	N, N, N, N, N, N, N, N, D(ImplicitOps | ModRM), N, N, N, N, N, N, N,
+	N, N, N, N, N, N, N, N,
+	D(ImplicitOps | ModRM), N, N, N, N, N, N, D(ImplicitOps | ModRM),
 	/* 0x20 - 0x2F */
 	DIP(ModRM | DstMem | Priv | Op3264, cr_read, check_cr_read),
 	DIP(ModRM | DstMem | Priv | Op3264, dr_read, check_dr_read),
@@ -4836,6 +4840,7 @@ int x86_emulate_insn(struct x86_emulate_ctxt *ctxt)
 	case 0x08:		/* invd */
 	case 0x0d:		/* GrpP (prefetch) */
 	case 0x18:		/* Grp16 (prefetch/nop) */
+	case 0x1f:		/* nop */
 		break;
 	case 0x20: /* mov cr, reg */
 		ctxt->dst.val = ops->get_cr(ctxt, ctxt->modrm_reg);

arch/x86/kvm/lapic.c

@@ -1861,11 +1861,14 @@ void kvm_apic_accept_events(struct kvm_vcpu *vcpu)
 {
 	struct kvm_lapic *apic = vcpu->arch.apic;
 	unsigned int sipi_vector;
+	unsigned long pe;
 
-	if (!kvm_vcpu_has_lapic(vcpu))
+	if (!kvm_vcpu_has_lapic(vcpu) || !apic->pending_events)
 		return;
 
-	if (test_and_clear_bit(KVM_APIC_INIT, &apic->pending_events)) {
+	pe = xchg(&apic->pending_events, 0);
+
+	if (test_bit(KVM_APIC_INIT, &pe)) {
 		kvm_lapic_reset(vcpu);
 		kvm_vcpu_reset(vcpu);
 		if (kvm_vcpu_is_bsp(apic->vcpu))
@@ -1873,7 +1876,7 @@ void kvm_apic_accept_events(struct kvm_vcpu *vcpu)
 		else
 			vcpu->arch.mp_state = KVM_MP_STATE_INIT_RECEIVED;
 	}
-	if (test_and_clear_bit(KVM_APIC_SIPI, &apic->pending_events) &&
+	if (test_bit(KVM_APIC_SIPI, &pe) &&
 	    vcpu->arch.mp_state == KVM_MP_STATE_INIT_RECEIVED) {
 		/* evaluate pending_events before reading the vector */
 		smp_rmb();