Merge tag 'nfs-rdma-for-4.1-1' of git://git.linux-nfs.org/projects/anna/nfs-rdma

NFS: NFSoRDMA Client Changes

This patch series creates an operation vector for each of the different
memory registration modes.  This should make it easier to one day increase
credit limit, rsize, and wsize.

Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>

25 files changed, 124 insertions, 121 deletions

diff --git a/arch/x86/boot/compressed/aslr.c b/arch/x86/boot/compressed/aslr.c
index 7083c16..bb13763 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 5903089..a950864 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 ee3576b..04477d6 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 947c6bf..54f60ab 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 0dbc082..72ba21a 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 95e11f7..f97fbe3 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 fa1195d..164e3f8 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/uapi/asm/bootparam.h b/arch/x86/include/uapi/asm/bootparam.h
index 44e6dd7..225b098 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 3d525c6..803b684 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 c2fd21f..017149c 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 1d74d16..2babb39 100644
--- a/arch/x86/kernel/entry_64.S
+++ b/arch/x86/kernel/entry_64.S
@@ -364,12 +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:
@@ -386,7 +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:
@@ -432,6 +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 9bbb9b3..d1ac80b 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 98dc931..0a2421c 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 9d2073e..4ff5d16 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 34f66e5..cdc6cf9 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/i8259.c b/arch/x86/kvm/i8259.c
index cc31f7c..9541ba3 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 b1947e0..46d4449 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 bd4e34d..4ee827d 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;
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index f7b20b4..ae4f6d3 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,
@@ -9218,9 +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 bd7a70b..32bf19e 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/common.c b/arch/x86/pci/common.c
index 3d2612b..2fb3847 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 efb8493..852aa4c 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 e71b3db..5dc6ca5 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 31776d0..d7ec4e2 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 740ae30..9f93af5 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);