Merge tag 'v4.0-rc6' into timers/core, before applying new patches

Signed-off-by: Ingo Molnar <mingo@kernel.org>

30 files changed, 170 insertions, 164 deletions

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index c2fb8a87dccb..b7d31ca55187 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -499,6 +499,7 @@ config X86_INTEL_QUARK
 	depends on X86_IO_APIC
 	select IOSF_MBI
 	select INTEL_IMR
+	select COMMON_CLK
 	---help---
 	  Select to include support for Quark X1000 SoC.
 	  Say Y here if you have a Quark based system such as the Arduino
diff --git a/arch/x86/boot/compressed/aslr.c b/arch/x86/boot/compressed/aslr.c
index 7083c16cccba..bb1376381985 100644
--- a/arch/x86/boot/compressed/aslr.c
+++ b/arch/x86/boot/compressed/aslr.c
@@ -14,13 +14,6 @@
 static const char build_str[] = UTS_RELEASE " (" LINUX_COMPILE_BY "@"
 		LINUX_COMPILE_HOST ") (" LINUX_COMPILER ") " UTS_VERSION;
 
-struct kaslr_setup_data {
-	__u64 next;
-	__u32 type;
-	__u32 len;
-	__u8 data[1];
-} kaslr_setup_data;
-
 #define I8254_PORT_CONTROL	0x43
 #define I8254_PORT_COUNTER0	0x40
 #define I8254_CMD_READBACK	0xC0
@@ -302,29 +295,7 @@ static unsigned long find_random_addr(unsigned long minimum,
 	return slots_fetch_random();
 }
 
-static void add_kaslr_setup_data(struct boot_params *params, __u8 enabled)
-{
-	struct setup_data *data;
-
-	kaslr_setup_data.type = SETUP_KASLR;
-	kaslr_setup_data.len = 1;
-	kaslr_setup_data.next = 0;
-	kaslr_setup_data.data[0] = enabled;
-
-	data = (struct setup_data *)(unsigned long)params->hdr.setup_data;
-
-	while (data && data->next)
-		data = (struct setup_data *)(unsigned long)data->next;
-
-	if (data)
-		data->next = (unsigned long)&kaslr_setup_data;
-	else
-		params->hdr.setup_data = (unsigned long)&kaslr_setup_data;
-
-}
-
-unsigned char *choose_kernel_location(struct boot_params *params,
-				      unsigned char *input,
+unsigned char *choose_kernel_location(unsigned char *input,
 				      unsigned long input_size,
 				      unsigned char *output,
 				      unsigned long output_size)
@@ -335,17 +306,14 @@ unsigned char *choose_kernel_location(struct boot_params *params,
 #ifdef CONFIG_HIBERNATION
 	if (!cmdline_find_option_bool("kaslr")) {
 		debug_putstr("KASLR disabled by default...\n");
-		add_kaslr_setup_data(params, 0);
 		goto out;
 	}
 #else
 	if (cmdline_find_option_bool("nokaslr")) {
 		debug_putstr("KASLR disabled by cmdline...\n");
-		add_kaslr_setup_data(params, 0);
 		goto out;
 	}
 #endif
-	add_kaslr_setup_data(params, 1);
 
 	/* Record the various known unsafe memory ranges. */
 	mem_avoid_init((unsigned long)input, input_size,
diff --git a/arch/x86/boot/compressed/misc.c b/arch/x86/boot/compressed/misc.c
index 5903089c818f..a950864a64da 100644
--- a/arch/x86/boot/compressed/misc.c
+++ b/arch/x86/boot/compressed/misc.c
@@ -401,8 +401,7 @@ asmlinkage __visible void *decompress_kernel(void *rmode, memptr heap,
 	 * the entire decompressed kernel plus relocation table, or the
 	 * entire decompressed kernel plus .bss and .brk sections.
 	 */
-	output = choose_kernel_location(real_mode, input_data, input_len,
-					output,
+	output = choose_kernel_location(input_data, input_len, output,
 					output_len > run_size ? output_len
 							      : run_size);
 
diff --git a/arch/x86/boot/compressed/misc.h b/arch/x86/boot/compressed/misc.h
index ee3576b2666b..04477d68403f 100644
--- a/arch/x86/boot/compressed/misc.h
+++ b/arch/x86/boot/compressed/misc.h
@@ -57,8 +57,7 @@ int cmdline_find_option_bool(const char *option);
 
 #if CONFIG_RANDOMIZE_BASE
 /* aslr.c */
-unsigned char *choose_kernel_location(struct boot_params *params,
-				      unsigned char *input,
+unsigned char *choose_kernel_location(unsigned char *input,
 				      unsigned long input_size,
 				      unsigned char *output,
 				      unsigned long output_size);
@@ -66,8 +65,7 @@ unsigned char *choose_kernel_location(struct boot_params *params,
 bool has_cpuflag(int flag);
 #else
 static inline
-unsigned char *choose_kernel_location(struct boot_params *params,
-				      unsigned char *input,
+unsigned char *choose_kernel_location(unsigned char *input,
 				      unsigned long input_size,
 				      unsigned char *output,
 				      unsigned long output_size)
diff --git a/arch/x86/crypto/aesni-intel_glue.c b/arch/x86/crypto/aesni-intel_glue.c
index 947c6bf52c33..54f60ab41c63 100644
--- a/arch/x86/crypto/aesni-intel_glue.c
+++ b/arch/x86/crypto/aesni-intel_glue.c
@@ -1155,7 +1155,7 @@ static int __driver_rfc4106_decrypt(struct aead_request *req)
 		src = kmalloc(req->cryptlen + req->assoclen, GFP_ATOMIC);
 		if (!src)
 			return -ENOMEM;
-		assoc = (src + req->cryptlen + auth_tag_len);
+		assoc = (src + req->cryptlen);
 		scatterwalk_map_and_copy(src, req->src, 0, req->cryptlen, 0);
 		scatterwalk_map_and_copy(assoc, req->assoc, 0,
 			req->assoclen, 0);
@@ -1180,7 +1180,7 @@ static int __driver_rfc4106_decrypt(struct aead_request *req)
 		scatterwalk_done(&src_sg_walk, 0, 0);
 		scatterwalk_done(&assoc_sg_walk, 0, 0);
 	} else {
-		scatterwalk_map_and_copy(dst, req->dst, 0, req->cryptlen, 1);
+		scatterwalk_map_and_copy(dst, req->dst, 0, tempCipherLen, 1);
 		kfree(src);
 	}
 	return retval;
diff --git a/arch/x86/include/asm/fpu-internal.h b/arch/x86/include/asm/fpu-internal.h
index 0dbc08282291..72ba21a8b5fc 100644
--- a/arch/x86/include/asm/fpu-internal.h
+++ b/arch/x86/include/asm/fpu-internal.h
@@ -370,7 +370,7 @@ static inline void drop_fpu(struct task_struct *tsk)
 	preempt_disable();
 	tsk->thread.fpu_counter = 0;
 	__drop_fpu(tsk);
-	clear_used_math();
+	clear_stopped_child_used_math(tsk);
 	preempt_enable();
 }
 
diff --git a/arch/x86/include/asm/page_types.h b/arch/x86/include/asm/page_types.h
index 95e11f79f123..f97fbe3abb67 100644
--- a/arch/x86/include/asm/page_types.h
+++ b/arch/x86/include/asm/page_types.h
@@ -51,8 +51,6 @@ extern int devmem_is_allowed(unsigned long pagenr);
 extern unsigned long max_low_pfn_mapped;
 extern unsigned long max_pfn_mapped;
 
-extern bool kaslr_enabled;
-
 static inline phys_addr_t get_max_mapped(void)
 {
 	return (phys_addr_t)max_pfn_mapped << PAGE_SHIFT;
diff --git a/arch/x86/include/asm/pci_x86.h b/arch/x86/include/asm/pci_x86.h
index fa1195dae425..164e3f8d3c3d 100644
--- a/arch/x86/include/asm/pci_x86.h
+++ b/arch/x86/include/asm/pci_x86.h
@@ -93,6 +93,8 @@ extern raw_spinlock_t pci_config_lock;
 extern int (*pcibios_enable_irq)(struct pci_dev *dev);
 extern void (*pcibios_disable_irq)(struct pci_dev *dev);
 
+extern bool mp_should_keep_irq(struct device *dev);
+
 struct pci_raw_ops {
 	int (*read)(unsigned int domain, unsigned int bus, unsigned int devfn,
 						int reg, int len, u32 *val);
diff --git a/arch/x86/include/asm/xsave.h b/arch/x86/include/asm/xsave.h
index 5fa9770035dc..c9a6d68b8d62 100644
--- a/arch/x86/include/asm/xsave.h
+++ b/arch/x86/include/asm/xsave.h
@@ -82,18 +82,15 @@ static inline int xsave_state_booting(struct xsave_struct *fx, u64 mask)
 	if (boot_cpu_has(X86_FEATURE_XSAVES))
 		asm volatile("1:"XSAVES"\n\t"
 			"2:\n\t"
-			: : "D" (fx), "m" (*fx), "a" (lmask), "d" (hmask)
+			     xstate_fault
+			: "D" (fx), "m" (*fx), "a" (lmask), "d" (hmask)
 			:   "memory");
 	else
 		asm volatile("1:"XSAVE"\n\t"
 			"2:\n\t"
-			: : "D" (fx), "m" (*fx), "a" (lmask), "d" (hmask)
+			     xstate_fault
+			: "D" (fx), "m" (*fx), "a" (lmask), "d" (hmask)
 			:   "memory");
-
-	asm volatile(xstate_fault
-		     : "0" (0)
-		     : "memory");
-
 	return err;
 }
 
@@ -112,18 +109,15 @@ static inline int xrstor_state_booting(struct xsave_struct *fx, u64 mask)
 	if (boot_cpu_has(X86_FEATURE_XSAVES))
 		asm volatile("1:"XRSTORS"\n\t"
 			"2:\n\t"
-			: : "D" (fx), "m" (*fx), "a" (lmask), "d" (hmask)
+			     xstate_fault
+			: "D" (fx), "m" (*fx), "a" (lmask), "d" (hmask)
 			:   "memory");
 	else
 		asm volatile("1:"XRSTOR"\n\t"
 			"2:\n\t"
-			: : "D" (fx), "m" (*fx), "a" (lmask), "d" (hmask)
+			     xstate_fault
+			: "D" (fx), "m" (*fx), "a" (lmask), "d" (hmask)
 			:   "memory");
-
-	asm volatile(xstate_fault
-		     : "0" (0)
-		     : "memory");
-
 	return err;
 }
 
@@ -149,9 +143,9 @@ static inline int xsave_state(struct xsave_struct *fx, u64 mask)
 	 */
 	alternative_input_2(
 		"1:"XSAVE,
-		"1:"XSAVEOPT,
+		XSAVEOPT,
 		X86_FEATURE_XSAVEOPT,
-		"1:"XSAVES,
+		XSAVES,
 		X86_FEATURE_XSAVES,
 		[fx] "D" (fx), "a" (lmask), "d" (hmask) :
 		"memory");
@@ -178,7 +172,7 @@ static inline int xrstor_state(struct xsave_struct *fx, u64 mask)
 	 */
 	alternative_input(
 		"1: " XRSTOR,
-		"1: " XRSTORS,
+		XRSTORS,
 		X86_FEATURE_XSAVES,
 		"D" (fx), "m" (*fx), "a" (lmask), "d" (hmask)
 		: "memory");
diff --git a/arch/x86/include/uapi/asm/bootparam.h b/arch/x86/include/uapi/asm/bootparam.h
index 44e6dd7e36a2..225b0988043a 100644
--- a/arch/x86/include/uapi/asm/bootparam.h
+++ b/arch/x86/include/uapi/asm/bootparam.h
@@ -7,7 +7,6 @@
 #define SETUP_DTB			2
 #define SETUP_PCI			3
 #define SETUP_EFI			4
-#define SETUP_KASLR			5
 
 /* ram_size flags */
 #define RAMDISK_IMAGE_START_MASK	0x07FF
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/entry_64.S b/arch/x86/kernel/entry_64.S
index 10074ad9ebf8..2babb393915e 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)
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/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();
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index e0b794a84c35..106c01557f2b 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -4950,7 +4950,8 @@ int x86_emulate_insn(struct x86_emulate_ctxt *ctxt)
 			goto done;
 		}
 	}
-	ctxt->dst.orig_val = ctxt->dst.val;
+	/* Copy full 64-bit value for CMPXCHG8B.  */
+	ctxt->dst.orig_val64 = ctxt->dst.val64;
 
 special_insn:
 
diff --git a/arch/x86/kvm/i8259.c b/arch/x86/kvm/i8259.c
index cc31f7c06d3d..9541ba34126b 100644
--- a/arch/x86/kvm/i8259.c
+++ b/arch/x86/kvm/i8259.c
@@ -507,6 +507,7 @@ static int picdev_read(struct kvm_pic *s,
 		return -EOPNOTSUPP;
 
 	if (len != 1) {
+		memset(val, 0, len);
 		pr_pic_unimpl("non byte read\n");
 		return 0;
 	}
diff --git a/arch/x86/kvm/ioapic.c b/arch/x86/kvm/ioapic.c
index b1947e0f3e10..46d4449772bc 100644
--- a/arch/x86/kvm/ioapic.c
+++ b/arch/x86/kvm/ioapic.c
@@ -422,6 +422,7 @@ static void __kvm_ioapic_update_eoi(struct kvm_vcpu *vcpu,
 			struct kvm_ioapic *ioapic, int vector, int trigger_mode)
 {
 	int i;
+	struct kvm_lapic *apic = vcpu->arch.apic;
 
 	for (i = 0; i < IOAPIC_NUM_PINS; i++) {
 		union kvm_ioapic_redirect_entry *ent = &ioapic->redirtbl[i];
@@ -443,7 +444,8 @@ static void __kvm_ioapic_update_eoi(struct kvm_vcpu *vcpu,
 		kvm_notify_acked_irq(ioapic->kvm, KVM_IRQCHIP_IOAPIC, i);
 		spin_lock(&ioapic->lock);
 
-		if (trigger_mode != IOAPIC_LEVEL_TRIG)
+		if (trigger_mode != IOAPIC_LEVEL_TRIG ||
+		    kvm_apic_get_reg(apic, APIC_SPIV) & APIC_SPIV_DIRECTED_EOI)
 			continue;
 
 		ASSERT(ent->fields.trig_mode == IOAPIC_LEVEL_TRIG);
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index e55b5fc344eb..4ee827d7bf36 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -833,8 +833,7 @@ int kvm_apic_compare_prio(struct kvm_vcpu *vcpu1, struct kvm_vcpu *vcpu2)
 
 static void kvm_ioapic_send_eoi(struct kvm_lapic *apic, int vector)
 {
-	if (!(kvm_apic_get_reg(apic, APIC_SPIV) & APIC_SPIV_DIRECTED_EOI) &&
-	    kvm_ioapic_handles_vector(apic->vcpu->kvm, vector)) {
+	if (kvm_ioapic_handles_vector(apic->vcpu->kvm, vector)) {
 		int trigger_mode;
 		if (apic_test_vector(vector, apic->regs + APIC_TMR))
 			trigger_mode = IOAPIC_LEVEL_TRIG;
@@ -1572,7 +1571,7 @@ void kvm_lapic_reset(struct kvm_vcpu *vcpu)
 		apic_set_reg(apic, APIC_TMR + 0x10 * i, 0);
 	}
 	apic->irr_pending = kvm_apic_vid_enabled(vcpu->kvm);
-	apic->isr_count = kvm_apic_vid_enabled(vcpu->kvm);
+	apic->isr_count = kvm_x86_ops->hwapic_isr_update ? 1 : 0;
 	apic->highest_isr_cache = -1;
 	update_divide_count(apic);
 	atomic_set(&apic->lapic_timer.pending, 0);
@@ -1782,7 +1781,7 @@ void kvm_apic_post_state_restore(struct kvm_vcpu *vcpu,
 	update_divide_count(apic);
 	start_apic_timer(apic);
 	apic->irr_pending = true;
-	apic->isr_count = kvm_apic_vid_enabled(vcpu->kvm) ?
+	apic->isr_count = kvm_x86_ops->hwapic_isr_update ?
 				1 : count_vectors(apic->regs + APIC_ISR);
 	apic->highest_isr_cache = -1;
 	if (kvm_x86_ops->hwapic_irr_update)
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index d319e0c24758..cc618c882f90 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -3649,11 +3649,6 @@ static void svm_load_eoi_exitmap(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap)
 	return;
 }
 
-static void svm_hwapic_isr_update(struct kvm *kvm, int isr)
-{
-	return;
-}
-
 static void svm_sync_pir_to_irr(struct kvm_vcpu *vcpu)
 {
 	return;
@@ -4403,7 +4398,6 @@ static struct kvm_x86_ops svm_x86_ops = {
 	.set_virtual_x2apic_mode = svm_set_virtual_x2apic_mode,
 	.vm_has_apicv = svm_vm_has_apicv,
 	.load_eoi_exitmap = svm_load_eoi_exitmap,
-	.hwapic_isr_update = svm_hwapic_isr_update,
 	.sync_pir_to_irr = svm_sync_pir_to_irr,
 
 	.set_tss_addr = svm_set_tss_addr,
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 14c1a18d206a..ae4f6d35d19c 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -2168,7 +2168,10 @@ static void vmx_set_msr_bitmap(struct kvm_vcpu *vcpu)
 {
 	unsigned long *msr_bitmap;
 
-	if (irqchip_in_kernel(vcpu->kvm) && apic_x2apic_mode(vcpu->arch.apic)) {
+	if (is_guest_mode(vcpu))
+		msr_bitmap = vmx_msr_bitmap_nested;
+	else if (irqchip_in_kernel(vcpu->kvm) &&
+		apic_x2apic_mode(vcpu->arch.apic)) {
 		if (is_long_mode(vcpu))
 			msr_bitmap = vmx_msr_bitmap_longmode_x2apic;
 		else
@@ -2476,8 +2479,7 @@ static void nested_vmx_setup_ctls_msrs(struct vcpu_vmx *vmx)
 	if (enable_ept) {
 		/* nested EPT: emulate EPT also to L1 */
 		vmx->nested.nested_vmx_secondary_ctls_high |=
-			SECONDARY_EXEC_ENABLE_EPT |
-			SECONDARY_EXEC_UNRESTRICTED_GUEST;
+			SECONDARY_EXEC_ENABLE_EPT;
 		vmx->nested.nested_vmx_ept_caps = VMX_EPT_PAGE_WALK_4_BIT |
 			 VMX_EPTP_WB_BIT | VMX_EPT_2MB_PAGE_BIT |
 			 VMX_EPT_INVEPT_BIT;
@@ -2491,6 +2493,10 @@ static void nested_vmx_setup_ctls_msrs(struct vcpu_vmx *vmx)
 	} else
 		vmx->nested.nested_vmx_ept_caps = 0;
 
+	if (enable_unrestricted_guest)
+		vmx->nested.nested_vmx_secondary_ctls_high |=
+			SECONDARY_EXEC_UNRESTRICTED_GUEST;
+
 	/* miscellaneous data */
 	rdmsr(MSR_IA32_VMX_MISC,
 		vmx->nested.nested_vmx_misc_low,
@@ -4367,6 +4373,18 @@ static int vmx_complete_nested_posted_interrupt(struct kvm_vcpu *vcpu)
 	return 0;
 }
 
+static inline bool kvm_vcpu_trigger_posted_interrupt(struct kvm_vcpu *vcpu)
+{
+#ifdef CONFIG_SMP
+	if (vcpu->mode == IN_GUEST_MODE) {
+		apic->send_IPI_mask(get_cpu_mask(vcpu->cpu),
+				POSTED_INTR_VECTOR);
+		return true;
+	}
+#endif
+	return false;
+}
+
 static int vmx_deliver_nested_posted_interrupt(struct kvm_vcpu *vcpu,
 						int vector)
 {
@@ -4375,9 +4393,7 @@ static int vmx_deliver_nested_posted_interrupt(struct kvm_vcpu *vcpu,
 	if (is_guest_mode(vcpu) &&
 	    vector == vmx->nested.posted_intr_nv) {
 		/* the PIR and ON have been set by L1. */
-		if (vcpu->mode == IN_GUEST_MODE)
-			apic->send_IPI_mask(get_cpu_mask(vcpu->cpu),
-				POSTED_INTR_VECTOR);
+		kvm_vcpu_trigger_posted_interrupt(vcpu);
 		/*
 		 * If a posted intr is not recognized by hardware,
 		 * we will accomplish it in the next vmentry.
@@ -4409,12 +4425,7 @@ static void vmx_deliver_posted_interrupt(struct kvm_vcpu *vcpu, int vector)
 
 	r = pi_test_and_set_on(&vmx->pi_desc);
 	kvm_make_request(KVM_REQ_EVENT, vcpu);
-#ifdef CONFIG_SMP
-	if (!r && (vcpu->mode == IN_GUEST_MODE))
-		apic->send_IPI_mask(get_cpu_mask(vcpu->cpu),
-				POSTED_INTR_VECTOR);
-	else
-#endif
+	if (r || !kvm_vcpu_trigger_posted_interrupt(vcpu))
 		kvm_vcpu_kick(vcpu);
 }
 
@@ -9213,9 +9224,9 @@ static void prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12)
 	}
 
 	if (cpu_has_vmx_msr_bitmap() &&
-	    exec_control & CPU_BASED_USE_MSR_BITMAPS &&
-	    nested_vmx_merge_msr_bitmap(vcpu, vmcs12)) {
-		vmcs_write64(MSR_BITMAP, __pa(vmx_msr_bitmap_nested));
+	    exec_control & CPU_BASED_USE_MSR_BITMAPS) {
+		nested_vmx_merge_msr_bitmap(vcpu, vmcs12);
+		/* MSR_BITMAP will be set by following vmx_set_efer. */
 	} else
 		exec_control &= ~CPU_BASED_USE_MSR_BITMAPS;
 
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index d7a300e0147f..0ee725f1896d 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -2744,7 +2744,6 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 	case KVM_CAP_USER_NMI:
 	case KVM_CAP_REINJECT_CONTROL:
 	case KVM_CAP_IRQ_INJECT_STATUS:
-	case KVM_CAP_IRQFD:
 	case KVM_CAP_IOEVENTFD:
 	case KVM_CAP_IOEVENTFD_NO_LENGTH:
 	case KVM_CAP_PIT2:
diff --git a/arch/x86/pci/acpi.c b/arch/x86/pci/acpi.c
index 6ac273832f28..e4695985f9de 100644
--- a/arch/x86/pci/acpi.c
+++ b/arch/x86/pci/acpi.c
@@ -331,7 +331,7 @@ static void probe_pci_root_info(struct pci_root_info *info,
 				struct list_head *list)
 {
 	int ret;
-	struct resource_entry *entry;
+	struct resource_entry *entry, *tmp;
 
 	sprintf(info->name, "PCI Bus %04x:%02x", domain, busnum);
 	info->bridge = device;
@@ -345,8 +345,13 @@ static void probe_pci_root_info(struct pci_root_info *info,
 		dev_dbg(&device->dev,
 			"no IO and memory resources present in _CRS\n");
 	else
-		resource_list_for_each_entry(entry, list)
-			entry->res->name = info->name;
+		resource_list_for_each_entry_safe(entry, tmp, list) {
+			if ((entry->res->flags & IORESOURCE_WINDOW) == 0 ||
+			    (entry->res->flags & IORESOURCE_DISABLED))
+				resource_list_destroy_entry(entry);
+			else
+				entry->res->name = info->name;
+		}
 }
 
 struct pci_bus *pci_acpi_scan_root(struct acpi_pci_root *root)
diff --git a/arch/x86/pci/common.c b/arch/x86/pci/common.c
index 3d2612b68694..2fb384724ebb 100644
--- a/arch/x86/pci/common.c
+++ b/arch/x86/pci/common.c
@@ -513,31 +513,6 @@ void __init pcibios_set_cache_line_size(void)
 	}
 }
 
-/*
- * Some device drivers assume dev->irq won't change after calling
- * pci_disable_device(). So delay releasing of IRQ resource to driver
- * unbinding time. Otherwise it will break PM subsystem and drivers
- * like xen-pciback etc.
- */
-static int pci_irq_notifier(struct notifier_block *nb, unsigned long action,
-			    void *data)
-{
-	struct pci_dev *dev = to_pci_dev(data);
-
-	if (action != BUS_NOTIFY_UNBOUND_DRIVER)
-		return NOTIFY_DONE;
-
-	if (pcibios_disable_irq)
-		pcibios_disable_irq(dev);
-
-	return NOTIFY_OK;
-}
-
-static struct notifier_block pci_irq_nb = {
-	.notifier_call = pci_irq_notifier,
-	.priority = INT_MIN,
-};
-
 int __init pcibios_init(void)
 {
 	if (!raw_pci_ops) {
@@ -550,9 +525,6 @@ int __init pcibios_init(void)
 
 	if (pci_bf_sort >= pci_force_bf)
 		pci_sort_breadthfirst();
-
-	bus_register_notifier(&pci_bus_type, &pci_irq_nb);
-
 	return 0;
 }
 
@@ -711,6 +683,12 @@ int pcibios_enable_device(struct pci_dev *dev, int mask)
 	return 0;
 }
 
+void pcibios_disable_device (struct pci_dev *dev)
+{
+	if (!pci_dev_msi_enabled(dev) && pcibios_disable_irq)
+		pcibios_disable_irq(dev);
+}
+
 int pci_ext_cfg_avail(void)
 {
 	if (raw_pci_ext_ops)
diff --git a/arch/x86/pci/intel_mid_pci.c b/arch/x86/pci/intel_mid_pci.c
index efb849323c74..852aa4c92da0 100644
--- a/arch/x86/pci/intel_mid_pci.c
+++ b/arch/x86/pci/intel_mid_pci.c
@@ -234,10 +234,10 @@ static int intel_mid_pci_irq_enable(struct pci_dev *dev)
 
 static void intel_mid_pci_irq_disable(struct pci_dev *dev)
 {
-	if (dev->irq_managed && dev->irq > 0) {
+	if (!mp_should_keep_irq(&dev->dev) && dev->irq_managed &&
+	    dev->irq > 0) {
 		mp_unmap_irq(dev->irq);
 		dev->irq_managed = 0;
-		dev->irq = 0;
 	}
 }
 
diff --git a/arch/x86/pci/irq.c b/arch/x86/pci/irq.c
index e71b3dbd87b8..5dc6ca5e1741 100644
--- a/arch/x86/pci/irq.c
+++ b/arch/x86/pci/irq.c
@@ -1256,9 +1256,22 @@ static int pirq_enable_irq(struct pci_dev *dev)
 	return 0;
 }
 
+bool mp_should_keep_irq(struct device *dev)
+{
+	if (dev->power.is_prepared)
+		return true;
+#ifdef CONFIG_PM
+	if (dev->power.runtime_status == RPM_SUSPENDING)
+		return true;
+#endif
+
+	return false;
+}
+
 static void pirq_disable_irq(struct pci_dev *dev)
 {
-	if (io_apic_assign_pci_irqs && dev->irq_managed && dev->irq) {
+	if (io_apic_assign_pci_irqs && !mp_should_keep_irq(&dev->dev) &&
+	    dev->irq_managed && dev->irq) {
 		mp_unmap_irq(dev->irq);
 		dev->irq = 0;
 		dev->irq_managed = 0;
diff --git a/arch/x86/vdso/vdso32/sigreturn.S b/arch/x86/vdso/vdso32/sigreturn.S
index 31776d0efc8c..d7ec4e251c0a 100644
--- a/arch/x86/vdso/vdso32/sigreturn.S
+++ b/arch/x86/vdso/vdso32/sigreturn.S
@@ -17,6 +17,7 @@
 	.text
 	.globl __kernel_sigreturn
 	.type __kernel_sigreturn,@function
+	nop /* this guy is needed for .LSTARTFDEDLSI1 below (watch for HACK) */
 	ALIGN
 __kernel_sigreturn:
 .LSTART_sigreturn:
diff --git a/arch/x86/xen/p2m.c b/arch/x86/xen/p2m.c
index 740ae3026a14..9f93af56a5fc 100644
--- a/arch/x86/xen/p2m.c
+++ b/arch/x86/xen/p2m.c
@@ -563,7 +563,7 @@ static bool alloc_p2m(unsigned long pfn)
 		if (p2m_pfn == PFN_DOWN(__pa(p2m_missing)))
 			p2m_init(p2m);
 		else
-			p2m_init_identity(p2m, pfn);
+			p2m_init_identity(p2m, pfn & ~(P2M_PER_PAGE - 1));
 
 		spin_lock_irqsave(&p2m_update_lock, flags);