Merge branch 'merge' of git://git.kernel.org/pub/scm/linux/kernel/git/benh/powerpc

* 'merge' of git://git.kernel.org/pub/scm/linux/kernel/git/benh/powerpc:
  powerpc/mm: Fix broken MMU PID stealing on !SMP
diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
index e87bdbf..fd5cac0 100644
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -1535,6 +1535,10 @@
 			register save and restore. The kernel will only save
 			legacy floating-point registers on task switch.
 
+	noxsave		[BUGS=X86] Disables x86 extended register state save
+			and restore using xsave. The kernel will fallback to
+			enabling legacy floating-point and sse state.
+
 	nohlt		[BUGS=ARM,SH] Tells the kernel that the sleep(SH) or
 			wfi(ARM) instruction doesn't work correctly and not to
 			use it. This is also useful when using JTAG debugger.
diff --git a/arch/x86/boot/memory.c b/arch/x86/boot/memory.c
index 5054c2d..74b3d2b 100644
--- a/arch/x86/boot/memory.c
+++ b/arch/x86/boot/memory.c
@@ -17,11 +17,6 @@
 
 #define SMAP	0x534d4150	/* ASCII "SMAP" */
 
-struct e820_ext_entry {
-	struct e820entry std;
-	u32 ext_flags;
-} __attribute__((packed));
-
 static int detect_memory_e820(void)
 {
 	int count = 0;
@@ -29,13 +24,21 @@
 	u32 size, id, edi;
 	u8 err;
 	struct e820entry *desc = boot_params.e820_map;
-	static struct e820_ext_entry buf; /* static so it is zeroed */
+	static struct e820entry buf; /* static so it is zeroed */
 
 	/*
-	 * Set this here so that if the BIOS doesn't change this field
-	 * but still doesn't change %ecx, we're still okay...
+	 * Note: at least one BIOS is known which assumes that the
+	 * buffer pointed to by one e820 call is the same one as
+	 * the previous call, and only changes modified fields.  Therefore,
+	 * we use a temporary buffer and copy the results entry by entry.
+	 *
+	 * This routine deliberately does not try to account for
+	 * ACPI 3+ extended attributes.  This is because there are
+	 * BIOSes in the field which report zero for the valid bit for
+	 * all ranges, and we don't currently make any use of the
+	 * other attribute bits.  Revisit this if we see the extended
+	 * attribute bits deployed in a meaningful way in the future.
 	 */
-	buf.ext_flags = 1;
 
 	do {
 		size = sizeof buf;
@@ -66,13 +69,7 @@
 			break;
 		}
 
-		/* ACPI 3.0 added the extended flags support.  If bit 0
-		   in the extended flags is zero, we're supposed to simply
-		   ignore the entry -- a backwards incompatible change! */
-		if (size > 20 && !(buf.ext_flags & 1))
-			continue;
-
-		*desc++ = buf.std;
+		*desc++ = buf;
 		count++;
 	} while (next && count < ARRAY_SIZE(boot_params.e820_map));
 
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index c1caefc..77848d9 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -114,6 +114,13 @@
 } };
 EXPORT_PER_CPU_SYMBOL_GPL(gdt_page);
 
+static int __init x86_xsave_setup(char *s)
+{
+	setup_clear_cpu_cap(X86_FEATURE_XSAVE);
+	return 1;
+}
+__setup("noxsave", x86_xsave_setup);
+
 #ifdef CONFIG_X86_32
 static int cachesize_override __cpuinitdata = -1;
 static int disable_x86_serial_nr __cpuinitdata = 1;
diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c
index 1340dad..667188e 100644
--- a/arch/x86/kernel/reboot.c
+++ b/arch/x86/kernel/reboot.c
@@ -232,6 +232,14 @@
 			DMI_MATCH(DMI_PRODUCT_NAME, "Dell DXP061"),
 		},
 	},
+	{	/* Handle problems with rebooting on Sony VGN-Z540N */
+		.callback = set_bios_reboot,
+		.ident = "Sony VGN-Z540N",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Sony Corporation"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "VGN-Z540N"),
+		},
+	},
 	{ }
 };
 
diff --git a/arch/x86/kernel/setup_percpu.c b/arch/x86/kernel/setup_percpu.c
index 3a97a4c..8f0e13b 100644
--- a/arch/x86/kernel/setup_percpu.c
+++ b/arch/x86/kernel/setup_percpu.c
@@ -160,8 +160,10 @@
 	/*
 	 * If large page isn't supported, there's no benefit in doing
 	 * this.  Also, on non-NUMA, embedding is better.
+	 *
+	 * NOTE: disabled for now.
 	 */
-	if (!cpu_has_pse || !pcpu_need_numa())
+	if (true || !cpu_has_pse || !pcpu_need_numa())
 		return -EINVAL;
 
 	/*
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index b6caf13..32cf11e 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -2897,8 +2897,7 @@
 
 static int kvm_pv_mmu_flush_tlb(struct kvm_vcpu *vcpu)
 {
-	kvm_x86_ops->tlb_flush(vcpu);
-	set_bit(KVM_REQ_MMU_SYNC, &vcpu->requests);
+	kvm_set_cr3(vcpu, vcpu->arch.cr3);
 	return 1;
 }
 
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 49079a4..3944e91 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -338,6 +338,9 @@
 
 void kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
 {
+	unsigned long old_cr4 = vcpu->arch.cr4;
+	unsigned long pdptr_bits = X86_CR4_PGE | X86_CR4_PSE | X86_CR4_PAE;
+
 	if (cr4 & CR4_RESERVED_BITS) {
 		printk(KERN_DEBUG "set_cr4: #GP, reserved bits\n");
 		kvm_inject_gp(vcpu, 0);
@@ -351,7 +354,8 @@
 			kvm_inject_gp(vcpu, 0);
 			return;
 		}
-	} else if (is_paging(vcpu) && !is_pae(vcpu) && (cr4 & X86_CR4_PAE)
+	} else if (is_paging(vcpu) && (cr4 & X86_CR4_PAE)
+		   && ((cr4 ^ old_cr4) & pdptr_bits)
 		   && !load_pdptrs(vcpu, vcpu->arch.cr3)) {
 		printk(KERN_DEBUG "set_cr4: #GP, pdptrs reserved bits\n");
 		kvm_inject_gp(vcpu, 0);
diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c
index 797f9f1..0f9052b 100644
--- a/arch/x86/mm/pageattr.c
+++ b/arch/x86/mm/pageattr.c
@@ -153,7 +153,7 @@
 	 */
 	__flush_tlb_all();
 
-	if (cache && boot_cpu_data.x86_model >= 4)
+	if (cache && boot_cpu_data.x86 >= 4)
 		wbinvd();
 }
 
@@ -204,6 +204,11 @@
 	}
 }
 
+static void wbinvd_local(void *unused)
+{
+	wbinvd();
+}
+
 static void cpa_flush_array(unsigned long *start, int numpages, int cache,
 			    int in_flags, struct page **pages)
 {
@@ -218,8 +223,9 @@
 
 	/* 4M threshold */
 	if (numpages >= 1024) {
-		if (boot_cpu_data.x86_model >= 4)
-			wbinvd();
+		if (boot_cpu_data.x86 >= 4)
+			on_each_cpu(wbinvd_local, NULL, 1);
+
 		return;
 	}
 	/*
diff --git a/drivers/base/power/main.c b/drivers/base/power/main.c
index 69b4ddb..3e4bc69 100644
--- a/drivers/base/power/main.c
+++ b/drivers/base/power/main.c
@@ -357,6 +357,7 @@
 {
 	struct device *dev;
 
+	mutex_lock(&dpm_list_mtx);
 	list_for_each_entry(dev, &dpm_list, power.entry)
 		if (dev->power.status > DPM_OFF) {
 			int error;
@@ -366,6 +367,7 @@
 			if (error)
 				pm_dev_err(dev, state, " early", error);
 		}
+	mutex_unlock(&dpm_list_mtx);
 }
 
 /**
@@ -614,6 +616,7 @@
 	int error = 0;
 
 	suspend_device_irqs();
+	mutex_lock(&dpm_list_mtx);
 	list_for_each_entry_reverse(dev, &dpm_list, power.entry) {
 		error = suspend_device_noirq(dev, state);
 		if (error) {
@@ -622,6 +625,7 @@
 		}
 		dev->power.status = DPM_OFF_IRQ;
 	}
+	mutex_unlock(&dpm_list_mtx);
 	if (error)
 		device_power_up(resume_event(state));
 	return error;
diff --git a/drivers/md/bitmap.c b/drivers/md/bitmap.c
index 47c68bc..56df1ce 100644
--- a/drivers/md/bitmap.c
+++ b/drivers/md/bitmap.c
@@ -1097,14 +1097,12 @@
 	}
 	bitmap->allclean = 1;
 
+	spin_lock_irqsave(&bitmap->lock, flags);
 	for (j = 0; j < bitmap->chunks; j++) {
 		bitmap_counter_t *bmc;
-		spin_lock_irqsave(&bitmap->lock, flags);
-		if (!bitmap->filemap) {
+		if (!bitmap->filemap)
 			/* error or shutdown */
-			spin_unlock_irqrestore(&bitmap->lock, flags);
 			break;
-		}
 
 		page = filemap_get_page(bitmap, j);
 
@@ -1121,6 +1119,8 @@
 					write_page(bitmap, page, 0);
 					bitmap->allclean = 0;
 				}
+				spin_lock_irqsave(&bitmap->lock, flags);
+				j |= (PAGE_BITS - 1);
 				continue;
 			}
 
@@ -1181,9 +1181,10 @@
 					ext2_clear_bit(file_page_offset(j), paddr);
 				kunmap_atomic(paddr, KM_USER0);
 			}
-		}
-		spin_unlock_irqrestore(&bitmap->lock, flags);
+		} else
+			j |= PAGE_COUNTER_MASK;
 	}
+	spin_unlock_irqrestore(&bitmap->lock, flags);
 
 	/* now sync the final page */
 	if (lastpage != NULL) {
diff --git a/drivers/md/md.c b/drivers/md/md.c
index fccc834..641b211 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -1375,6 +1375,9 @@
 
 	sb->raid_disks = cpu_to_le32(mddev->raid_disks);
 	sb->size = cpu_to_le64(mddev->dev_sectors);
+	sb->chunksize = cpu_to_le32(mddev->chunk_size >> 9);
+	sb->level = cpu_to_le32(mddev->level);
+	sb->layout = cpu_to_le32(mddev->layout);
 
 	if (mddev->bitmap && mddev->bitmap_file == NULL) {
 		sb->bitmap_offset = cpu_to_le32((__u32)mddev->bitmap_offset);
@@ -3303,7 +3306,9 @@
 action_show(mddev_t *mddev, char *page)
 {
 	char *type = "idle";
-	if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery) ||
+	if (test_bit(MD_RECOVERY_FROZEN, &mddev->recovery))
+		type = "frozen";
+	else if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery) ||
 	    (!mddev->ro && test_bit(MD_RECOVERY_NEEDED, &mddev->recovery))) {
 		if (test_bit(MD_RECOVERY_RESHAPE, &mddev->recovery))
 			type = "reshape";
@@ -3326,7 +3331,12 @@
 	if (!mddev->pers || !mddev->pers->sync_request)
 		return -EINVAL;
 
-	if (cmd_match(page, "idle")) {
+	if (cmd_match(page, "frozen"))
+		set_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
+	else
+		clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
+
+	if (cmd_match(page, "idle") || cmd_match(page, "frozen")) {
 		if (mddev->sync_thread) {
 			set_bit(MD_RECOVERY_INTR, &mddev->recovery);
 			md_unregister_thread(mddev->sync_thread);
@@ -3680,7 +3690,7 @@
 		if (strict_blocks_to_sectors(buf, &sectors) < 0)
 			return -EINVAL;
 		if (mddev->pers && mddev->pers->size(mddev, 0, 0) < sectors)
-			return -EINVAL;
+			return -E2BIG;
 
 		mddev->external_size = 1;
 	}
@@ -5557,7 +5567,7 @@
 	.owner		= THIS_MODULE,
 	.open		= md_open,
 	.release	= md_release,
-	.locked_ioctl	= md_ioctl,
+	.ioctl		= md_ioctl,
 	.getgeo		= md_getgeo,
 	.media_changed	= md_media_changed,
 	.revalidate_disk= md_revalidate,
@@ -6352,12 +6362,13 @@
 
 		skipped = 0;
 
-		if ((mddev->curr_resync > mddev->curr_resync_completed &&
-		     (mddev->curr_resync - mddev->curr_resync_completed)
-		    > (max_sectors >> 4)) ||
-		    (j - mddev->curr_resync_completed)*2
-		    >= mddev->resync_max - mddev->curr_resync_completed
-			) {
+		if (!test_bit(MD_RECOVERY_RESHAPE, &mddev->recovery) &&
+		    ((mddev->curr_resync > mddev->curr_resync_completed &&
+		      (mddev->curr_resync - mddev->curr_resync_completed)
+		      > (max_sectors >> 4)) ||
+		     (j - mddev->curr_resync_completed)*2
+		     >= mddev->resync_max - mddev->curr_resync_completed
+			    )) {
 			/* time to update curr_resync_completed */
 			blk_unplug(mddev->queue);
 			wait_event(mddev->recovery_wait,
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index 4616bc3..3c3626d 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -3811,13 +3811,13 @@
 	safepos = conf->reshape_safe;
 	sector_div(safepos, data_disks);
 	if (mddev->delta_disks < 0) {
-		writepos -= reshape_sectors;
+		writepos -= min(reshape_sectors, writepos);
 		readpos += reshape_sectors;
 		safepos += reshape_sectors;
 	} else {
 		writepos += reshape_sectors;
-		readpos -= reshape_sectors;
-		safepos -= reshape_sectors;
+		readpos -= min(reshape_sectors, readpos);
+		safepos -= min(reshape_sectors, safepos);
 	}
 
 	/* 'writepos' is the most advanced device address we might write.
diff --git a/init/main.c b/init/main.c
index 3bbf93b..d721dad 100644
--- a/init/main.c
+++ b/init/main.c
@@ -566,8 +566,7 @@
 	tick_init();
 	boot_cpu_init();
 	page_address_init();
-	printk(KERN_NOTICE);
-	printk(linux_banner);
+	printk(KERN_NOTICE "%s", linux_banner);
 	setup_arch(&command_line);
 	mm_init_owner(&init_mm, &init_task);
 	setup_command_line(command_line);
diff --git a/kernel/async.c b/kernel/async.c
index 968ef94..5054030 100644
--- a/kernel/async.c
+++ b/kernel/async.c
@@ -92,19 +92,23 @@
 static async_cookie_t  __lowest_in_progress(struct list_head *running)
 {
 	struct async_entry *entry;
+	async_cookie_t ret = next_cookie; /* begin with "infinity" value */
+
 	if (!list_empty(running)) {
 		entry = list_first_entry(running,
 			struct async_entry, list);
-		return entry->cookie;
-	} else if (!list_empty(&async_pending)) {
-		entry = list_first_entry(&async_pending,
-			struct async_entry, list);
-		return entry->cookie;
-	} else {
-		/* nothing in progress... next_cookie is "infinity" */
-		return next_cookie;
+		ret = entry->cookie;
 	}
 
+	if (!list_empty(&async_pending)) {
+		list_for_each_entry(entry, &async_pending, list)
+			if (entry->running == running) {
+				ret = entry->cookie;
+				break;
+			}
+	}
+
+	return ret;
 }
 
 static async_cookie_t  lowest_in_progress(struct list_head *running)
diff --git a/kernel/kexec.c b/kernel/kexec.c
index 5a758c6e..e498377 100644
--- a/kernel/kexec.c
+++ b/kernel/kexec.c
@@ -1451,7 +1451,6 @@
 		error = device_suspend(PMSG_FREEZE);
 		if (error)
 			goto Resume_console;
-		device_pm_lock();
 		/* At this point, device_suspend() has been called,
 		 * but *not* device_power_down(). We *must*
 		 * device_power_down() now.  Otherwise, drivers for
@@ -1489,7 +1488,6 @@
 		enable_nonboot_cpus();
 		device_power_up(PMSG_RESTORE);
  Resume_devices:
-		device_pm_unlock();
 		device_resume(PMSG_RESTORE);
  Resume_console:
 		resume_console();
diff --git a/kernel/power/disk.c b/kernel/power/disk.c
index b0dc9e7..5cb080e 100644
--- a/kernel/power/disk.c
+++ b/kernel/power/disk.c
@@ -215,8 +215,6 @@
 	if (error)
 		return error;
 
-	device_pm_lock();
-
 	/* At this point, device_suspend() has been called, but *not*
 	 * device_power_down(). We *must* call device_power_down() now.
 	 * Otherwise, drivers for some devices (e.g. interrupt controllers)
@@ -227,7 +225,7 @@
 	if (error) {
 		printk(KERN_ERR "PM: Some devices failed to power down, "
 			"aborting hibernation\n");
-		goto Unlock;
+		return error;
 	}
 
 	error = platform_pre_snapshot(platform_mode);
@@ -280,9 +278,6 @@
 	device_power_up(in_suspend ?
 		(error ? PMSG_RECOVER : PMSG_THAW) : PMSG_RESTORE);
 
- Unlock:
-	device_pm_unlock();
-
 	return error;
 }
 
@@ -344,13 +339,11 @@
 {
 	int error;
 
-	device_pm_lock();
-
 	error = device_power_down(PMSG_QUIESCE);
 	if (error) {
 		printk(KERN_ERR "PM: Some devices failed to power down, "
 			"aborting resume\n");
-		goto Unlock;
+		return error;
 	}
 
 	error = platform_pre_restore(platform_mode);
@@ -403,9 +396,6 @@
 
 	device_power_up(PMSG_RECOVER);
 
- Unlock:
-	device_pm_unlock();
-
 	return error;
 }
 
@@ -464,11 +454,9 @@
 		goto Resume_devices;
 	}
 
-	device_pm_lock();
-
 	error = device_power_down(PMSG_HIBERNATE);
 	if (error)
-		goto Unlock;
+		goto Resume_devices;
 
 	error = hibernation_ops->prepare();
 	if (error)
@@ -493,9 +481,6 @@
 
 	device_power_up(PMSG_RESTORE);
 
- Unlock:
-	device_pm_unlock();
-
  Resume_devices:
 	entering_platform_hibernation = false;
 	device_resume(PMSG_RESTORE);
diff --git a/kernel/power/main.c b/kernel/power/main.c
index f99ed6a..8680282 100644
--- a/kernel/power/main.c
+++ b/kernel/power/main.c
@@ -289,12 +289,10 @@
 {
 	int error;
 
-	device_pm_lock();
-
 	if (suspend_ops->prepare) {
 		error = suspend_ops->prepare();
 		if (error)
-			goto Done;
+			return error;
 	}
 
 	error = device_power_down(PMSG_SUSPEND);
@@ -343,9 +341,6 @@
 	if (suspend_ops->finish)
 		suspend_ops->finish();
 
- Done:
-	device_pm_unlock();
-
 	return error;
 }