15 files changed, 169 insertions, 62 deletions

diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c
index 3d525c6124f6..803b684676ff 100644
--- a/arch/x86/kernel/acpi/boot.c
+++ b/arch/x86/kernel/acpi/boot.c
@@ -1338,6 +1338,26 @@ static int __init dmi_ignore_irq0_timer_override(const struct dmi_system_id *d)
 }
 
 /*
+ * ACPI offers an alternative platform interface model that removes
+ * ACPI hardware requirements for platforms that do not implement
+ * the PC Architecture.
+ *
+ * We initialize the Hardware-reduced ACPI model here:
+ */
+static void __init acpi_reduced_hw_init(void)
+{
+	if (acpi_gbl_reduced_hardware) {
+		/*
+		 * Override x86_init functions and bypass legacy pic
+		 * in Hardware-reduced ACPI mode
+		 */
+		x86_init.timers.timer_init	= x86_init_noop;
+		x86_init.irqs.pre_vector_init	= x86_init_noop;
+		legacy_pic			= &null_legacy_pic;
+	}
+}
+
+/*
  * If your system is blacklisted here, but you find that acpi=force
  * works for you, please contact linux-acpi@vger.kernel.org
  */
@@ -1536,6 +1556,11 @@ int __init early_acpi_boot_init(void)
 	 */
 	early_acpi_process_madt();
 
+	/*
+	 * Hardware-reduced ACPI mode initialization:
+	 */
+	acpi_reduced_hw_init();
+
 	return 0;
 }
 
diff --git a/arch/x86/kernel/apic/apic_numachip.c b/arch/x86/kernel/apic/apic_numachip.c
index c2fd21fed002..017149cded07 100644
--- a/arch/x86/kernel/apic/apic_numachip.c
+++ b/arch/x86/kernel/apic/apic_numachip.c
@@ -37,10 +37,12 @@ static const struct apic apic_numachip;
 static unsigned int get_apic_id(unsigned long x)
 {
 	unsigned long value;
-	unsigned int id;
+	unsigned int id = (x >> 24) & 0xff;
 
-	rdmsrl(MSR_FAM10H_NODE_ID, value);
-	id = ((x >> 24) & 0xffU) | ((value << 2) & 0xff00U);
+	if (static_cpu_has_safe(X86_FEATURE_NODEID_MSR)) {
+		rdmsrl(MSR_FAM10H_NODE_ID, value);
+		id |= (value << 2) & 0xff00;
+	}
 
 	return id;
 }
@@ -155,10 +157,18 @@ static int __init numachip_probe(void)
 
 static void fixup_cpu_id(struct cpuinfo_x86 *c, int node)
 {
-	if (c->phys_proc_id != node) {
-		c->phys_proc_id = node;
-		per_cpu(cpu_llc_id, smp_processor_id()) = node;
+	u64 val;
+	u32 nodes = 1;
+
+	this_cpu_write(cpu_llc_id, node);
+
+	/* Account for nodes per socket in multi-core-module processors */
+	if (static_cpu_has_safe(X86_FEATURE_NODEID_MSR)) {
+		rdmsrl(MSR_FAM10H_NODE_ID, val);
+		nodes = ((val >> 3) & 7) + 1;
 	}
+
+	c->phys_proc_id = node / nodes;
 }
 
 static int __init numachip_system_init(void)
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index b5c8ff5e9dfc..2346c95c6ab1 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -1396,6 +1396,12 @@ void cpu_init(void)
 
 	wait_for_master_cpu(cpu);
 
+	/*
+	 * Initialize the CR4 shadow before doing anything that could
+	 * try to read it.
+	 */
+	cr4_init_shadow();
+
 	show_ucode_info_early();
 
 	printk(KERN_INFO "Initializing CPU#%d\n", cpu);
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index 94d7dcb12145..50163fa9034f 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -565,8 +565,8 @@ static const struct _tlb_table intel_tlb_table[] = {
 	{ 0xb2, TLB_INST_4K,		64,	" TLB_INST 4KByte pages, 4-way set associative" },
 	{ 0xb3, TLB_DATA_4K,		128,	" TLB_DATA 4 KByte pages, 4-way set associative" },
 	{ 0xb4, TLB_DATA_4K,		256,	" TLB_DATA 4 KByte pages, 4-way associative" },
-	{ 0xb5, TLB_INST_4K,		64,	" TLB_INST 4 KByte pages, 8-way set ssociative" },
-	{ 0xb6, TLB_INST_4K,		128,	" TLB_INST 4 KByte pages, 8-way set ssociative" },
+	{ 0xb5, TLB_INST_4K,		64,	" TLB_INST 4 KByte pages, 8-way set associative" },
+	{ 0xb6, TLB_INST_4K,		128,	" TLB_INST 4 KByte pages, 8-way set associative" },
 	{ 0xba, TLB_DATA_4K,		64,	" TLB_DATA 4 KByte pages, 4-way associative" },
 	{ 0xc0, TLB_DATA_4K_4M,		8,	" TLB_DATA 4 KByte and 4 MByte pages, 4-way associative" },
 	{ 0xc1, STLB_4K_2M,		1024,	" STLB 4 KByte and 2 MByte pages, 8-way associative" },
diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index 498b6d967138..258990688a5e 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -212,11 +212,11 @@ static struct event_constraint intel_hsw_event_constraints[] = {
 	INTEL_UEVENT_CONSTRAINT(0x01c0, 0x2), /* INST_RETIRED.PREC_DIST */
 	INTEL_EVENT_CONSTRAINT(0xcd, 0x8), /* MEM_TRANS_RETIRED.LOAD_LATENCY */
 	/* CYCLE_ACTIVITY.CYCLES_L1D_PENDING */
-	INTEL_EVENT_CONSTRAINT(0x08a3, 0x4),
+	INTEL_UEVENT_CONSTRAINT(0x08a3, 0x4),
 	/* CYCLE_ACTIVITY.STALLS_L1D_PENDING */
-	INTEL_EVENT_CONSTRAINT(0x0ca3, 0x4),
+	INTEL_UEVENT_CONSTRAINT(0x0ca3, 0x4),
 	/* CYCLE_ACTIVITY.CYCLES_NO_EXECUTE */
-	INTEL_EVENT_CONSTRAINT(0x04a3, 0xf),
+	INTEL_UEVENT_CONSTRAINT(0x04a3, 0xf),
 	EVENT_CONSTRAINT_END
 };
 
@@ -1649,11 +1649,11 @@ intel_get_event_constraints(struct cpu_hw_events *cpuc, struct perf_event *event
 	if (c)
 		return c;
 
-	c = intel_pebs_constraints(event);
+	c = intel_shared_regs_constraints(cpuc, event);
 	if (c)
 		return c;
 
-	c = intel_shared_regs_constraints(cpuc, event);
+	c = intel_pebs_constraints(event);
 	if (c)
 		return c;
 
diff --git a/arch/x86/kernel/entry_32.S b/arch/x86/kernel/entry_32.S
index 000d4199b03e..31e2d5bf3e38 100644
--- a/arch/x86/kernel/entry_32.S
+++ b/arch/x86/kernel/entry_32.S
@@ -982,6 +982,9 @@ ENTRY(xen_hypervisor_callback)
 ENTRY(xen_do_upcall)
 1:	mov %esp, %eax
 	call xen_evtchn_do_upcall
+#ifndef CONFIG_PREEMPT
+	call xen_maybe_preempt_hcall
+#endif
 	jmp  ret_from_intr
 	CFI_ENDPROC
 ENDPROC(xen_hypervisor_callback)
diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S
index db13655c3a2a..f0095a76c182 100644
--- a/arch/x86/kernel/entry_64.S
+++ b/arch/x86/kernel/entry_64.S
@@ -269,11 +269,14 @@ ENTRY(ret_from_fork)
 	testl $3, CS-ARGOFFSET(%rsp)		# from kernel_thread?
 	jz   1f
 
-	testl $_TIF_IA32, TI_flags(%rcx)	# 32-bit compat task needs IRET
-	jnz  int_ret_from_sys_call
-
-	RESTORE_TOP_OF_STACK %rdi, -ARGOFFSET
-	jmp ret_from_sys_call			# go to the SYSRET fastpath
+	/*
+	 * By the time we get here, we have no idea whether our pt_regs,
+	 * ti flags, and ti status came from the 64-bit SYSCALL fast path,
+	 * the slow path, or one of the ia32entry paths.
+	 * Use int_ret_from_sys_call to return, since it can safely handle
+	 * all of the above.
+	 */
+	jmp  int_ret_from_sys_call
 
 1:
 	subq $REST_SKIP, %rsp	# leave space for volatiles
@@ -361,12 +364,21 @@ system_call_fastpath:
  * Has incomplete stack frame and undefined top of stack.
  */
 ret_from_sys_call:
-	testl $_TIF_ALLWORK_MASK,TI_flags+THREAD_INFO(%rsp,RIP-ARGOFFSET)
-	jnz int_ret_from_sys_call_fixup	/* Go the the slow path */
-
 	LOCKDEP_SYS_EXIT
 	DISABLE_INTERRUPTS(CLBR_NONE)
 	TRACE_IRQS_OFF
+
+	/*
+	 * We must check ti flags with interrupts (or at least preemption)
+	 * off because we must *never* return to userspace without
+	 * processing exit work that is enqueued if we're preempted here.
+	 * In particular, returning to userspace with any of the one-shot
+	 * flags (TIF_NOTIFY_RESUME, TIF_USER_RETURN_NOTIFY, etc) set is
+	 * very bad.
+	 */
+	testl $_TIF_ALLWORK_MASK,TI_flags+THREAD_INFO(%rsp,RIP-ARGOFFSET)
+	jnz int_ret_from_sys_call_fixup	/* Go the the slow path */
+
 	CFI_REMEMBER_STATE
 	/*
 	 * sysretq will re-enable interrupts:
@@ -383,7 +395,7 @@ ret_from_sys_call:
 
 int_ret_from_sys_call_fixup:
 	FIXUP_TOP_OF_STACK %r11, -ARGOFFSET
-	jmp int_ret_from_sys_call
+	jmp int_ret_from_sys_call_irqs_off
 
 	/* Do syscall tracing */
 tracesys:
@@ -429,6 +441,7 @@ tracesys_phase2:
 GLOBAL(int_ret_from_sys_call)
 	DISABLE_INTERRUPTS(CLBR_NONE)
 	TRACE_IRQS_OFF
+int_ret_from_sys_call_irqs_off:
 	movl $_TIF_ALLWORK_MASK,%edi
 	/* edi:	mask to check */
 GLOBAL(int_with_check)
@@ -786,7 +799,21 @@ retint_swapgs:		/* return to user-space */
 	cmpq %r11,(EFLAGS-ARGOFFSET)(%rsp)	/* R11 == RFLAGS */
 	jne opportunistic_sysret_failed
 
-	testq $X86_EFLAGS_RF,%r11		/* sysret can't restore RF */
+	/*
+	 * SYSRET can't restore RF.  SYSRET can restore TF, but unlike IRET,
+	 * restoring TF results in a trap from userspace immediately after
+	 * SYSRET.  This would cause an infinite loop whenever #DB happens
+	 * with register state that satisfies the opportunistic SYSRET
+	 * conditions.  For example, single-stepping this user code:
+	 *
+	 *           movq $stuck_here,%rcx
+	 *           pushfq
+	 *           popq %r11
+	 *   stuck_here:
+	 *
+	 * would never get past 'stuck_here'.
+	 */
+	testq $(X86_EFLAGS_RF|X86_EFLAGS_TF), %r11
 	jnz opportunistic_sysret_failed
 
 	/* nothing to check for RSP */
@@ -1208,6 +1235,9 @@ ENTRY(xen_do_hypervisor_callback)   # do_hypervisor_callback(struct *pt_regs)
 	popq %rsp
 	CFI_DEF_CFA_REGISTER rsp
 	decl PER_CPU_VAR(irq_count)
+#ifndef CONFIG_PREEMPT
+	call xen_maybe_preempt_hcall
+#endif
 	jmp  error_exit
 	CFI_ENDPROC
 END(xen_do_hypervisor_callback)
diff --git a/arch/x86/kernel/kgdb.c b/arch/x86/kernel/kgdb.c
index 7ec1d5f8d283..25ecd56cefa8 100644
--- a/arch/x86/kernel/kgdb.c
+++ b/arch/x86/kernel/kgdb.c
@@ -72,7 +72,7 @@ struct dbg_reg_def_t dbg_reg_def[DBG_MAX_REG_NUM] =
 	{ "bx", 8, offsetof(struct pt_regs, bx) },
 	{ "cx", 8, offsetof(struct pt_regs, cx) },
 	{ "dx", 8, offsetof(struct pt_regs, dx) },
-	{ "si", 8, offsetof(struct pt_regs, dx) },
+	{ "si", 8, offsetof(struct pt_regs, si) },
 	{ "di", 8, offsetof(struct pt_regs, di) },
 	{ "bp", 8, offsetof(struct pt_regs, bp) },
 	{ "sp", 8, offsetof(struct pt_regs, sp) },
diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c
index 6a1146ea4d4d..4e3d5a9621fe 100644
--- a/arch/x86/kernel/kprobes/core.c
+++ b/arch/x86/kernel/kprobes/core.c
@@ -223,27 +223,48 @@ static unsigned long
 __recover_probed_insn(kprobe_opcode_t *buf, unsigned long addr)
 {
 	struct kprobe *kp;
+	unsigned long faddr;
 
 	kp = get_kprobe((void *)addr);
-	/* There is no probe, return original address */
-	if (!kp)
+	faddr = ftrace_location(addr);
+	/*
+	 * Addresses inside the ftrace location are refused by
+	 * arch_check_ftrace_location(). Something went terribly wrong
+	 * if such an address is checked here.
+	 */
+	if (WARN_ON(faddr && faddr != addr))
+		return 0UL;
+	/*
+	 * Use the current code if it is not modified by Kprobe
+	 * and it cannot be modified by ftrace.
+	 */
+	if (!kp && !faddr)
 		return addr;
 
 	/*
-	 *  Basically, kp->ainsn.insn has an original instruction.
-	 *  However, RIP-relative instruction can not do single-stepping
-	 *  at different place, __copy_instruction() tweaks the displacement of
-	 *  that instruction. In that case, we can't recover the instruction
-	 *  from the kp->ainsn.insn.
+	 * Basically, kp->ainsn.insn has an original instruction.
+	 * However, RIP-relative instruction can not do single-stepping
+	 * at different place, __copy_instruction() tweaks the displacement of
+	 * that instruction. In that case, we can't recover the instruction
+	 * from the kp->ainsn.insn.
 	 *
-	 *  On the other hand, kp->opcode has a copy of the first byte of
-	 *  the probed instruction, which is overwritten by int3. And
-	 *  the instruction at kp->addr is not modified by kprobes except
-	 *  for the first byte, we can recover the original instruction
-	 *  from it and kp->opcode.
+	 * On the other hand, in case on normal Kprobe, kp->opcode has a copy
+	 * of the first byte of the probed instruction, which is overwritten
+	 * by int3. And the instruction at kp->addr is not modified by kprobes
+	 * except for the first byte, we can recover the original instruction
+	 * from it and kp->opcode.
+	 *
+	 * In case of Kprobes using ftrace, we do not have a copy of
+	 * the original instruction. In fact, the ftrace location might
+	 * be modified at anytime and even could be in an inconsistent state.
+	 * Fortunately, we know that the original code is the ideal 5-byte
+	 * long NOP.
 	 */
-	memcpy(buf, kp->addr, MAX_INSN_SIZE * sizeof(kprobe_opcode_t));
-	buf[0] = kp->opcode;
+	memcpy(buf, (void *)addr, MAX_INSN_SIZE * sizeof(kprobe_opcode_t));
+	if (faddr)
+		memcpy(buf, ideal_nops[NOP_ATOMIC5], 5);
+	else
+		buf[0] = kp->opcode;
 	return (unsigned long)buf;
 }
 
@@ -251,6 +272,7 @@ __recover_probed_insn(kprobe_opcode_t *buf, unsigned long addr)
  * Recover the probed instruction at addr for further analysis.
  * Caller must lock kprobes by kprobe_mutex, or disable preemption
  * for preventing to release referencing kprobes.
+ * Returns zero if the instruction can not get recovered.
  */
 unsigned long recover_probed_instruction(kprobe_opcode_t *buf, unsigned long addr)
 {
@@ -285,6 +307,8 @@ static int can_probe(unsigned long paddr)
 		 * normally used, we just go through if there is no kprobe.
 		 */
 		__addr = recover_probed_instruction(buf, addr);
+		if (!__addr)
+			return 0;
 		kernel_insn_init(&insn, (void *)__addr, MAX_INSN_SIZE);
 		insn_get_length(&insn);
 
@@ -333,6 +357,8 @@ int __copy_instruction(u8 *dest, u8 *src)
 	unsigned long recovered_insn =
 		recover_probed_instruction(buf, (unsigned long)src);
 
+	if (!recovered_insn)
+		return 0;
 	kernel_insn_init(&insn, (void *)recovered_insn, MAX_INSN_SIZE);
 	insn_get_length(&insn);
 	/* Another subsystem puts a breakpoint, failed to recover */
diff --git a/arch/x86/kernel/kprobes/opt.c b/arch/x86/kernel/kprobes/opt.c
index 0dd8d089c315..7b3b9d15c47a 100644
--- a/arch/x86/kernel/kprobes/opt.c
+++ b/arch/x86/kernel/kprobes/opt.c
@@ -259,6 +259,8 @@ static int can_optimize(unsigned long paddr)
 			 */
 			return 0;
 		recovered_insn = recover_probed_instruction(buf, addr);
+		if (!recovered_insn)
+			return 0;
 		kernel_insn_init(&insn, (void *)recovered_insn, MAX_INSN_SIZE);
 		insn_get_length(&insn);
 		/* Another subsystem puts a breakpoint */
diff --git a/arch/x86/kernel/module.c b/arch/x86/kernel/module.c
index 9bbb9b35c144..d1ac80b72c72 100644
--- a/arch/x86/kernel/module.c
+++ b/arch/x86/kernel/module.c
@@ -47,13 +47,21 @@ do {							\
 
 #ifdef CONFIG_RANDOMIZE_BASE
 static unsigned long module_load_offset;
+static int randomize_modules = 1;
 
 /* Mutex protects the module_load_offset. */
 static DEFINE_MUTEX(module_kaslr_mutex);
 
+static int __init parse_nokaslr(char *p)
+{
+	randomize_modules = 0;
+	return 0;
+}
+early_param("nokaslr", parse_nokaslr);
+
 static unsigned long int get_module_load_offset(void)
 {
-	if (kaslr_enabled) {
+	if (randomize_modules) {
 		mutex_lock(&module_kaslr_mutex);
 		/*
 		 * Calculate the module_load_offset the first time this
diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c
index bae6c609888e..86db4bcd7ce5 100644
--- a/arch/x86/kernel/reboot.c
+++ b/arch/x86/kernel/reboot.c
@@ -183,6 +183,16 @@ static struct dmi_system_id __initdata reboot_dmi_table[] = {
 		},
 	},
 
+	/* ASRock */
+	{	/* Handle problems with rebooting on ASRock Q1900DC-ITX */
+		.callback = set_pci_reboot,
+		.ident = "ASRock Q1900DC-ITX",
+		.matches = {
+			DMI_MATCH(DMI_BOARD_VENDOR, "ASRock"),
+			DMI_MATCH(DMI_BOARD_NAME, "Q1900DC-ITX"),
+		},
+	},
+
 	/* ASUS */
 	{	/* Handle problems with rebooting on ASUS P4S800 */
 		.callback = set_bios_reboot,
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 98dc9317286e..0a2421cca01f 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -122,8 +122,6 @@
 unsigned long max_low_pfn_mapped;
 unsigned long max_pfn_mapped;
 
-bool __read_mostly kaslr_enabled = false;
-
 #ifdef CONFIG_DMI
 RESERVE_BRK(dmi_alloc, 65536);
 #endif
@@ -427,11 +425,6 @@ static void __init reserve_initrd(void)
 }
 #endif /* CONFIG_BLK_DEV_INITRD */
 
-static void __init parse_kaslr_setup(u64 pa_data, u32 data_len)
-{
-	kaslr_enabled = (bool)(pa_data + sizeof(struct setup_data));
-}
-
 static void __init parse_setup_data(void)
 {
 	struct setup_data *data;
@@ -457,9 +450,6 @@ static void __init parse_setup_data(void)
 		case SETUP_EFI:
 			parse_efi_setup(pa_data, data_len);
 			break;
-		case SETUP_KASLR:
-			parse_kaslr_setup(pa_data, data_len);
-			break;
 		default:
 			break;
 		}
@@ -842,14 +832,10 @@ static void __init trim_low_memory_range(void)
 static int
 dump_kernel_offset(struct notifier_block *self, unsigned long v, void *p)
 {
-	if (kaslr_enabled)
-		pr_emerg("Kernel Offset: 0x%lx from 0x%lx (relocation range: 0x%lx-0x%lx)\n",
-			 (unsigned long)&_text - __START_KERNEL,
-			 __START_KERNEL,
-			 __START_KERNEL_map,
-			 MODULES_VADDR-1);
-	else
-		pr_emerg("Kernel Offset: disabled\n");
+	pr_emerg("Kernel Offset: 0x%lx from 0x%lx "
+		 "(relocation range: 0x%lx-0x%lx)\n",
+		 (unsigned long)&_text - __START_KERNEL, __START_KERNEL,
+		 __START_KERNEL_map, MODULES_VADDR-1);
 
 	return 0;
 }
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index 9d2073e2ecc9..4ff5d162ff9f 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -384,7 +384,7 @@ dotraplinkage void do_bounds(struct pt_regs *regs, long error_code)
 		goto exit;
 	conditional_sti(regs);
 
-	if (!user_mode(regs))
+	if (!user_mode_vm(regs))
 		die("bounds", regs, error_code);
 
 	if (!cpu_feature_enabled(X86_FEATURE_MPX)) {
@@ -637,7 +637,7 @@ dotraplinkage void do_debug(struct pt_regs *regs, long error_code)
 	 * then it's very likely the result of an icebp/int01 trap.
 	 * User wants a sigtrap for that.
 	 */
-	if (!dr6 && user_mode(regs))
+	if (!dr6 && user_mode_vm(regs))
 		user_icebp = 1;
 
 	/* Catch kmemcheck conditions first of all! */
diff --git a/arch/x86/kernel/xsave.c b/arch/x86/kernel/xsave.c
index 34f66e58a896..cdc6cf903078 100644
--- a/arch/x86/kernel/xsave.c
+++ b/arch/x86/kernel/xsave.c
@@ -379,7 +379,7 @@ int __restore_xstate_sig(void __user *buf, void __user *buf_fx, int size)
 		 * thread's fpu state, reconstruct fxstate from the fsave
 		 * header. Sanitize the copied state etc.
 		 */
-		struct xsave_struct *xsave = &tsk->thread.fpu.state->xsave;
+		struct fpu *fpu = &tsk->thread.fpu;
 		struct user_i387_ia32_struct env;
 		int err = 0;
 
@@ -393,14 +393,15 @@ int __restore_xstate_sig(void __user *buf, void __user *buf_fx, int size)
 		 */
 		drop_fpu(tsk);
 
-		if (__copy_from_user(xsave, buf_fx, state_size) ||
+		if (__copy_from_user(&fpu->state->xsave, buf_fx, state_size) ||
 		    __copy_from_user(&env, buf, sizeof(env))) {
+			fpu_finit(fpu);
 			err = -1;
 		} else {
 			sanitize_restored_xstate(tsk, &env, xstate_bv, fx_only);
-			set_used_math();
 		}
 
+		set_used_math();
 		if (use_eager_fpu()) {
 			preempt_disable();
 			math_state_restore();