Merge remote-tracking branch 'linus' into linaro-3.0

24 files changed, 452 insertions, 229 deletions

diff --git a/Documentation/x86/boot.txt b/Documentation/x86/boot.txt
index 9b7221a86df..7c3a8801b7c 100644
--- a/Documentation/x86/boot.txt
+++ b/Documentation/x86/boot.txt
@@ -674,7 +674,7 @@ Protocol:	2.10+
 
 Field name:	init_size
 Type:		read
-Offset/size:	0x25c/4
+Offset/size:	0x260/4
 
   This field indicates the amount of linear contiguous memory starting
   at the kernel runtime start address that the kernel needs before it
diff --git a/arch/arm/mach-davinci/board-dm365-evm.c b/arch/arm/mach-davinci/board-dm365-evm.c
index 9844fa4cadc..9818f214d4f 100644
--- a/arch/arm/mach-davinci/board-dm365-evm.c
+++ b/arch/arm/mach-davinci/board-dm365-evm.c
@@ -520,7 +520,7 @@ fail:
 	 */
 	if (have_imager()) {
 		label = "HD imager";
-		mux |= 1;
+		mux |= 2;
 
 		/* externally mux MMC1/ENET/AIC33 to imager */
 		mux |= BIT(6) | BIT(5) | BIT(3);
@@ -540,7 +540,7 @@ fail:
 		resets &= ~BIT(1);
 
 		if (have_tvp7002()) {
-			mux |= 2;
+			mux |= 1;
 			resets &= ~BIT(2);
 			label = "tvp7002 HD";
 		} else {
diff --git a/arch/arm/mach-davinci/gpio.c b/arch/arm/mach-davinci/gpio.c
index e7221398e5a..cafbe13a82a 100644
--- a/arch/arm/mach-davinci/gpio.c
+++ b/arch/arm/mach-davinci/gpio.c
@@ -254,8 +254,10 @@ gpio_irq_handler(unsigned irq, struct irq_desc *desc)
 {
 	struct davinci_gpio_regs __iomem *g;
 	u32 mask = 0xffff;
+	struct davinci_gpio_controller *d;
 
-	g = (__force struct davinci_gpio_regs __iomem *) irq_desc_get_handler_data(desc);
+	d = (struct davinci_gpio_controller *)irq_desc_get_handler_data(desc);
+	g = (struct davinci_gpio_regs __iomem *)d->regs;
 
 	/* we only care about one bank */
 	if (irq & 1)
@@ -274,11 +276,14 @@ gpio_irq_handler(unsigned irq, struct irq_desc *desc)
 		if (!status)
 			break;
 		__raw_writel(status, &g->intstat);
-		if (irq & 1)
-			status >>= 16;
 
 		/* now demux them to the right lowlevel handler */
-		n = (int)irq_get_handler_data(irq);
+		n = d->irq_base;
+		if (irq & 1) {
+			n += 16;
+			status >>= 16;
+		}
+
 		while (status) {
 			res = ffs(status);
 			n += res;
@@ -424,7 +429,13 @@ static int __init davinci_gpio_irq_setup(void)
 
 		/* set up all irqs in this bank */
 		irq_set_chained_handler(bank_irq, gpio_irq_handler);
-		irq_set_handler_data(bank_irq, (__force void *)g);
+
+		/*
+		 * Each chip handles 32 gpios, and each irq bank consists of 16
+		 * gpio irqs. Pass the irq bank's corresponding controller to
+		 * the chained irq handler.
+		 */
+		irq_set_handler_data(bank_irq, &chips[gpio / 32]);
 
 		for (i = 0; i < 16 && gpio < ngpio; i++, irq++, gpio++) {
 			irq_set_chip(irq, &gpio_irqchip);
diff --git a/arch/arm/mach-davinci/irq.c b/arch/arm/mach-davinci/irq.c
index d8c1af02593..952dc126c39 100644
--- a/arch/arm/mach-davinci/irq.c
+++ b/arch/arm/mach-davinci/irq.c
@@ -52,6 +52,12 @@ davinci_alloc_gc(void __iomem *base, unsigned int irq_start, unsigned int num)
 	struct irq_chip_type *ct;
 
 	gc = irq_alloc_generic_chip("AINTC", 1, irq_start, base, handle_edge_irq);
+	if (!gc) {
+		pr_err("%s: irq_alloc_generic_chip for IRQ %u failed\n",
+		       __func__, irq_start);
+		return;
+	}
+
 	ct = gc->chip_types;
 	ct->chip.irq_ack = irq_gc_ack_set_bit;
 	ct->chip.irq_mask = irq_gc_mask_clr_bit;
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index da349723d41..37357a599dc 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -1170,7 +1170,7 @@ comment "NUMA (Summit) requires SMP, 64GB highmem support, ACPI"
 config AMD_NUMA
 	def_bool y
 	prompt "Old style AMD Opteron NUMA detection"
-	depends on NUMA && PCI
+	depends on X86_64 && NUMA && PCI
 	---help---
 	  Enable AMD NUMA node topology detection.  You should say Y here if
 	  you have a multi processor AMD system. This uses an old method to
diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c
index 4f0d46fefa7..9242436e993 100644
--- a/arch/x86/kernel/reboot.c
+++ b/arch/x86/kernel/reboot.c
@@ -419,6 +419,30 @@ static struct dmi_system_id __initdata pci_reboot_dmi_table[] = {
 			DMI_MATCH(DMI_PRODUCT_NAME, "iMac9,1"),
 		},
 	},
+	{	/* Handle problems with rebooting on the Latitude E6320. */
+		.callback = set_pci_reboot,
+		.ident = "Dell Latitude E6320",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
+			DMI_MATCH(DMI_PRODUCT_NAME, "Latitude E6320"),
+		},
+	},
+	{	/* Handle problems with rebooting on the Latitude E5420. */
+		.callback = set_pci_reboot,
+		.ident = "Dell Latitude E5420",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
+			DMI_MATCH(DMI_PRODUCT_NAME, "Latitude E5420"),
+		},
+	},
+	{	/* Handle problems with rebooting on the Latitude E6420. */
+		.callback = set_pci_reboot,
+		.ident = "Dell Latitude E6420",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
+			DMI_MATCH(DMI_PRODUCT_NAME, "Latitude E6420"),
+		},
+	},
 	{ }
 };
 
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index f245c588ae9..ce7914c4c04 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -262,6 +262,7 @@ enum intel_pch {
 };
 
 #define QUIRK_PIPEA_FORCE (1<<0)
+#define QUIRK_LVDS_SSC_DISABLE (1<<1)
 
 struct intel_fbdev;
 
@@ -1194,7 +1195,9 @@ void i915_gem_free_all_phys_object(struct drm_device *dev);
 void i915_gem_release(struct drm_device *dev, struct drm_file *file);
 
 uint32_t
-i915_gem_get_unfenced_gtt_alignment(struct drm_i915_gem_object *obj);
+i915_gem_get_unfenced_gtt_alignment(struct drm_device *dev,
+				    uint32_t size,
+				    int tiling_mode);
 
 /* i915_gem_gtt.c */
 void i915_gem_restore_gtt_mappings(struct drm_device *dev);
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 5c0d1247f45..a087e1bf0c2 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -1374,25 +1374,24 @@ i915_gem_free_mmap_offset(struct drm_i915_gem_object *obj)
 }
 
 static uint32_t
-i915_gem_get_gtt_size(struct drm_i915_gem_object *obj)
+i915_gem_get_gtt_size(struct drm_device *dev, uint32_t size, int tiling_mode)
 {
-	struct drm_device *dev = obj->base.dev;
-	uint32_t size;
+	uint32_t gtt_size;
 
 	if (INTEL_INFO(dev)->gen >= 4 ||
-	    obj->tiling_mode == I915_TILING_NONE)
-		return obj->base.size;
+	    tiling_mode == I915_TILING_NONE)
+		return size;
 
 	/* Previous chips need a power-of-two fence region when tiling */
 	if (INTEL_INFO(dev)->gen == 3)
-		size = 1024*1024;
+		gtt_size = 1024*1024;
 	else
-		size = 512*1024;
+		gtt_size = 512*1024;
 
-	while (size < obj->base.size)
-		size <<= 1;
+	while (gtt_size < size)
+		gtt_size <<= 1;
 
-	return size;
+	return gtt_size;
 }
 
 /**
@@ -1403,59 +1402,52 @@ i915_gem_get_gtt_size(struct drm_i915_gem_object *obj)
  * potential fence register mapping.
  */
 static uint32_t
-i915_gem_get_gtt_alignment(struct drm_i915_gem_object *obj)
+i915_gem_get_gtt_alignment(struct drm_device *dev,
+			   uint32_t size,
+			   int tiling_mode)
 {
-	struct drm_device *dev = obj->base.dev;
-
 	/*
 	 * Minimum alignment is 4k (GTT page size), but might be greater
 	 * if a fence register is needed for the object.
 	 */
 	if (INTEL_INFO(dev)->gen >= 4 ||
-	    obj->tiling_mode == I915_TILING_NONE)
+	    tiling_mode == I915_TILING_NONE)
 		return 4096;
 
 	/*
 	 * Previous chips need to be aligned to the size of the smallest
 	 * fence register that can contain the object.
 	 */
-	return i915_gem_get_gtt_size(obj);
+	return i915_gem_get_gtt_size(dev, size, tiling_mode);
 }
 
 /**
  * i915_gem_get_unfenced_gtt_alignment - return required GTT alignment for an
  *					 unfenced object
- * @obj: object to check
+ * @dev: the device
+ * @size: size of the object
+ * @tiling_mode: tiling mode of the object
  *
  * Return the required GTT alignment for an object, only taking into account
  * unfenced tiled surface requirements.
  */
 uint32_t
-i915_gem_get_unfenced_gtt_alignment(struct drm_i915_gem_object *obj)
+i915_gem_get_unfenced_gtt_alignment(struct drm_device *dev,
+				    uint32_t size,
+				    int tiling_mode)
 {
-	struct drm_device *dev = obj->base.dev;
-	int tile_height;
-
 	/*
 	 * Minimum alignment is 4k (GTT page size) for sane hw.
 	 */
 	if (INTEL_INFO(dev)->gen >= 4 || IS_G33(dev) ||
-	    obj->tiling_mode == I915_TILING_NONE)
+	    tiling_mode == I915_TILING_NONE)
 		return 4096;
 
-	/*
-	 * Older chips need unfenced tiled buffers to be aligned to the left
-	 * edge of an even tile row (where tile rows are counted as if the bo is
-	 * placed in a fenced gtt region).
+	/* Previous hardware however needs to be aligned to a power-of-two
+	 * tile height. The simplest method for determining this is to reuse
+	 * the power-of-tile object size.
 	 */
-	if (IS_GEN2(dev))
-		tile_height = 16;
-	else if (obj->tiling_mode == I915_TILING_Y && HAS_128_BYTE_Y_TILING(dev))
-		tile_height = 32;
-	else
-		tile_height = 8;
-
-	return tile_height * obj->stride * 2;
+	return i915_gem_get_gtt_size(dev, size, tiling_mode);
 }
 
 int
@@ -2744,9 +2736,16 @@ i915_gem_object_bind_to_gtt(struct drm_i915_gem_object *obj,
 		return -EINVAL;
 	}
 
-	fence_size = i915_gem_get_gtt_size(obj);
-	fence_alignment = i915_gem_get_gtt_alignment(obj);
-	unfenced_alignment = i915_gem_get_unfenced_gtt_alignment(obj);
+	fence_size = i915_gem_get_gtt_size(dev,
+					   obj->base.size,
+					   obj->tiling_mode);
+	fence_alignment = i915_gem_get_gtt_alignment(dev,
+						     obj->base.size,
+						     obj->tiling_mode);
+	unfenced_alignment =
+		i915_gem_get_unfenced_gtt_alignment(dev,
+						    obj->base.size,
+						    obj->tiling_mode);
 
 	if (alignment == 0)
 		alignment = map_and_fenceable ? fence_alignment :
diff --git a/drivers/gpu/drm/i915/i915_gem_tiling.c b/drivers/gpu/drm/i915/i915_gem_tiling.c
index 82d70fd9e93..99c4faa59d8 100644
--- a/drivers/gpu/drm/i915/i915_gem_tiling.c
+++ b/drivers/gpu/drm/i915/i915_gem_tiling.c
@@ -348,7 +348,9 @@ i915_gem_set_tiling(struct drm_device *dev, void *data,
 		/* Rebind if we need a change of alignment */
 		if (!obj->map_and_fenceable) {
 			u32 unfenced_alignment =
-				i915_gem_get_unfenced_gtt_alignment(obj);
+				i915_gem_get_unfenced_gtt_alignment(dev,
+								    obj->base.size,
+								    args->tiling_mode);
 			if (obj->gtt_offset & (unfenced_alignment - 1))
 				ret = i915_gem_object_unbind(obj);
 		}
diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index 21b6f93fe91..0f1c799afea 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -4305,7 +4305,8 @@ static void intel_update_watermarks(struct drm_device *dev)
 
 static inline bool intel_panel_use_ssc(struct drm_i915_private *dev_priv)
 {
-	return dev_priv->lvds_use_ssc && i915_panel_use_ssc;
+	return dev_priv->lvds_use_ssc && i915_panel_use_ssc
+		&& !(dev_priv->quirks & QUIRK_LVDS_SSC_DISABLE);
 }
 
 static int i9xx_crtc_mode_set(struct drm_crtc *crtc,
@@ -7810,6 +7811,15 @@ static void quirk_pipea_force (struct drm_device *dev)
 	DRM_DEBUG_DRIVER("applying pipe a force quirk\n");
 }
 
+/*
+ * Some machines (Lenovo U160) do not work with SSC on LVDS for some reason
+ */
+static void quirk_ssc_force_disable(struct drm_device *dev)
+{
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	dev_priv->quirks |= QUIRK_LVDS_SSC_DISABLE;
+}
+
 struct intel_quirk {
 	int device;
 	int subsystem_vendor;
@@ -7838,6 +7848,9 @@ struct intel_quirk intel_quirks[] = {
 	/* 855 & before need to leave pipe A & dpll A up */
 	{ 0x3582, PCI_ANY_ID, PCI_ANY_ID, quirk_pipea_force },
 	{ 0x2562, PCI_ANY_ID, PCI_ANY_ID, quirk_pipea_force },
+
+	/* Lenovo U160 cannot use SSC on LVDS */
+	{ 0x0046, 0x17aa, 0x3920, quirk_ssc_force_disable },
 };
 
 static void intel_init_quirks(struct drm_device *dev)
diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c
index 3e298997629..bc4b12ca537 100644
--- a/fs/cifs/cifsfs.c
+++ b/fs/cifs/cifsfs.c
@@ -35,6 +35,7 @@
 #include <linux/delay.h>
 #include <linux/kthread.h>
 #include <linux/freezer.h>
+#include <linux/namei.h>
 #include <net/ipv6.h>
 #include "cifsfs.h"
 #include "cifspdu.h"
@@ -542,14 +543,12 @@ static const struct super_operations cifs_super_ops = {
 static struct dentry *
 cifs_get_root(struct smb_vol *vol, struct super_block *sb)
 {
-	int xid, rc;
-	struct inode *inode;
-	struct qstr name;
-	struct dentry *dparent = NULL, *dchild = NULL, *alias;
+	struct dentry *dentry;
 	struct cifs_sb_info *cifs_sb = CIFS_SB(sb);
-	unsigned int i, full_len, len;
-	char *full_path = NULL, *pstart;
+	char *full_path = NULL;
+	char *s, *p;
 	char sep;
+	int xid;
 
 	full_path = cifs_build_path_to_root(vol, cifs_sb,
 					    cifs_sb_master_tcon(cifs_sb));
@@ -560,73 +559,32 @@ cifs_get_root(struct smb_vol *vol, struct super_block *sb)
 
 	xid = GetXid();
 	sep = CIFS_DIR_SEP(cifs_sb);
-	dparent = dget(sb->s_root);
-	full_len = strlen(full_path);
-	full_path[full_len] = sep;
-	pstart = full_path + 1;
-
-	for (i = 1, len = 0; i <= full_len; i++) {
-		if (full_path[i] != sep || !len) {
-			len++;
-			continue;
-		}
-
-		full_path[i] = 0;
-		cFYI(1, "get dentry for %s", pstart);
-
-		name.name = pstart;
-		name.len = len;
-		name.hash = full_name_hash(pstart, len);
-		dchild = d_lookup(dparent, &name);
-		if (dchild == NULL) {
-			cFYI(1, "not exists");
-			dchild = d_alloc(dparent, &name);
-			if (dchild == NULL) {
-				dput(dparent);
-				dparent = ERR_PTR(-ENOMEM);
-				goto out;
-			}
-		}
-
-		cFYI(1, "get inode");
-		if (dchild->d_inode == NULL) {
-			cFYI(1, "not exists");
-			inode = NULL;
-			if (cifs_sb_master_tcon(CIFS_SB(sb))->unix_ext)
-				rc = cifs_get_inode_info_unix(&inode, full_path,
-							      sb, xid);
-			else
-				rc = cifs_get_inode_info(&inode, full_path,
-							 NULL, sb, xid, NULL);
-			if (rc) {
-				dput(dchild);
-				dput(dparent);
-				dparent = ERR_PTR(rc);
-				goto out;
-			}
-			alias = d_materialise_unique(dchild, inode);
-			if (alias != NULL) {
-				dput(dchild);
-				if (IS_ERR(alias)) {
-					dput(dparent);
-					dparent = ERR_PTR(-EINVAL); /* XXX */
-					goto out;
-				}
-				dchild = alias;
-			}
-		}
-		cFYI(1, "parent %p, child %p", dparent, dchild);
-
-		dput(dparent);
-		dparent = dchild;
-		len = 0;
-		pstart = full_path + i + 1;
-		full_path[i] = sep;
-	}
-out:
+	dentry = dget(sb->s_root);
+	p = s = full_path;
+
+	do {
+		struct inode *dir = dentry->d_inode;
+		struct dentry *child;
+
+		/* skip separators */
+		while (*s == sep)
+			s++;
+		if (!*s)
+			break;
+		p = s++;
+		/* next separator */
+		while (*s && *s != sep)
+			s++;
+
+		mutex_lock(&dir->i_mutex);
+		child = lookup_one_len(p, dentry, s - p);
+		mutex_unlock(&dir->i_mutex);
+		dput(dentry);
+		dentry = child;
+	} while (!IS_ERR(dentry));
 	_FreeXid(xid);
 	kfree(full_path);
-	return dparent;
+	return dentry;
 }
 
 static int cifs_set_super(struct super_block *sb, void *data)
diff --git a/fs/dcache.c b/fs/dcache.c
index 6e4ea6d8777..fbdcbca4072 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -1813,8 +1813,6 @@ seqretry:
 		tname = dentry->d_name.name;
 		i = dentry->d_inode;
 		prefetch(tname);
-		if (i)
-			prefetch(i);
 		/*
 		 * This seqcount check is required to ensure name and
 		 * len are loaded atomically, so as not to walk off the
diff --git a/fs/fscache/page.c b/fs/fscache/page.c
index 2f343b4d7a7..3f7a59bfa7a 100644
--- a/fs/fscache/page.c
+++ b/fs/fscache/page.c
@@ -976,16 +976,12 @@ void __fscache_uncache_all_inode_pages(struct fscache_cookie *cookie,
 
 	pagevec_init(&pvec, 0);
 	next = 0;
-	while (next <= (loff_t)-1 &&
-	       pagevec_lookup(&pvec, mapping, next, PAGEVEC_SIZE)
-	       ) {
+	do {
+		if (!pagevec_lookup(&pvec, mapping, next, PAGEVEC_SIZE))
+			break;
 		for (i = 0; i < pagevec_count(&pvec); i++) {
 			struct page *page = pvec.pages[i];
-			pgoff_t page_index = page->index;
-
-			ASSERTCMP(page_index, >=, next);
-			next = page_index + 1;
-
+			next = page->index;
 			if (PageFsCache(page)) {
 				__fscache_wait_on_page_write(cookie, page);
 				__fscache_uncache_page(cookie, page);
@@ -993,7 +989,7 @@ void __fscache_uncache_all_inode_pages(struct fscache_cookie *cookie,
 		}
 		pagevec_release(&pvec);
 		cond_resched();
-	}
+	} while (++next);
 
 	_leave("");
 }
diff --git a/fs/libfs.c b/fs/libfs.c
index c88eab55aec..275ca4749a2 100644
--- a/fs/libfs.c
+++ b/fs/libfs.c
@@ -822,7 +822,7 @@ ssize_t simple_attr_write(struct file *file, const char __user *buf,
 		goto out;
 
 	attr->set_buf[size] = '\0';
-	val = simple_strtol(attr->set_buf, NULL, 0);
+	val = simple_strtoll(attr->set_buf, NULL, 0);
 	ret = attr->set(attr->data, val);
 	if (ret == 0)
 		ret = len; /* on success, claim we got the whole input */
diff --git a/fs/namei.c b/fs/namei.c
index 5c867dd1c0b..14ab8d3f2f0 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -942,7 +942,6 @@ static bool __follow_mount_rcu(struct nameidata *nd, struct path *path,
 		 * Don't forget we might have a non-mountpoint managed dentry
 		 * that wants to block transit.
 		 */
-		*inode = path->dentry->d_inode;
 		if (unlikely(managed_dentry_might_block(path->dentry)))
 			return false;
 
@@ -955,6 +954,12 @@ static bool __follow_mount_rcu(struct nameidata *nd, struct path *path,
 		path->mnt = mounted;
 		path->dentry = mounted->mnt_root;
 		nd->seq = read_seqcount_begin(&path->dentry->d_seq);
+		/*
+		 * Update the inode too. We don't need to re-check the
+		 * dentry sequence number here after this d_inode read,
+		 * because a mount-point is always pinned.
+		 */
+		*inode = path->dentry->d_inode;
 	}
 	return true;
 }
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 496770a9648..14a6c7b545d 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -844,6 +844,7 @@ enum cpu_idle_type {
 #define SD_SERIALIZE		0x0400	/* Only a single load balancing instance */
 #define SD_ASYM_PACKING		0x0800  /* Place busy groups earlier in the domain */
 #define SD_PREFER_SIBLING	0x1000	/* Prefer to place tasks in a sibling domain */
+#define SD_OVERLAP		0x2000	/* sched_domains of this level overlap */
 
 enum powersavings_balance_level {
 	POWERSAVINGS_BALANCE_NONE = 0,  /* No power saving load balance */
@@ -893,16 +894,21 @@ static inline int sd_power_saving_flags(void)
 	return 0;
 }
 
-struct sched_group {
-	struct sched_group *next;	/* Must be a circular list */
+struct sched_group_power {
 	atomic_t ref;
-
 	/*
 	 * CPU power of this group, SCHED_LOAD_SCALE being max power for a
 	 * single CPU.
 	 */
-	unsigned int cpu_power, cpu_power_orig;
+	unsigned int power, power_orig;
+};
+
+struct sched_group {
+	struct sched_group *next;	/* Must be a circular list */
+	atomic_t ref;
+
 	unsigned int group_weight;
+	struct sched_group_power *sgp;
 
 	/*
 	 * The CPUs this group covers.
@@ -1254,6 +1260,9 @@ struct task_struct {
 #ifdef CONFIG_PREEMPT_RCU
 	int rcu_read_lock_nesting;
 	char rcu_read_unlock_special;
+#if defined(CONFIG_RCU_BOOST) && defined(CONFIG_TREE_PREEMPT_RCU)
+	int rcu_boosted;
+#endif /* #if defined(CONFIG_RCU_BOOST) && defined(CONFIG_TREE_PREEMPT_RCU) */
 	struct list_head rcu_node_entry;
 #endif /* #ifdef CONFIG_PREEMPT_RCU */
 #ifdef CONFIG_TREE_PREEMPT_RCU
diff --git a/kernel/rcutree_plugin.h b/kernel/rcutree_plugin.h
index 75113cb7c4f..8aafbb80b8b 100644
--- a/kernel/rcutree_plugin.h
+++ b/kernel/rcutree_plugin.h
@@ -68,6 +68,7 @@ struct rcu_state rcu_preempt_state = RCU_STATE_INITIALIZER(rcu_preempt_state);
 DEFINE_PER_CPU(struct rcu_data, rcu_preempt_data);
 static struct rcu_state *rcu_state = &rcu_preempt_state;
 
+static void rcu_read_unlock_special(struct task_struct *t);
 static int rcu_preempted_readers_exp(struct rcu_node *rnp);
 
 /*
@@ -147,7 +148,7 @@ static void rcu_preempt_note_context_switch(int cpu)
 	struct rcu_data *rdp;
 	struct rcu_node *rnp;
 
-	if (t->rcu_read_lock_nesting &&
+	if (t->rcu_read_lock_nesting > 0 &&
 	    (t->rcu_read_unlock_special & RCU_READ_UNLOCK_BLOCKED) == 0) {
 
 		/* Possibly blocking in an RCU read-side critical section. */
@@ -190,6 +191,14 @@ static void rcu_preempt_note_context_switch(int cpu)
 				rnp->gp_tasks = &t->rcu_node_entry;
 		}
 		raw_spin_unlock_irqrestore(&rnp->lock, flags);
+	} else if (t->rcu_read_lock_nesting < 0 &&
+		   t->rcu_read_unlock_special) {
+
+		/*
+		 * Complete exit from RCU read-side critical section on
+		 * behalf of preempted instance of __rcu_read_unlock().
+		 */
+		rcu_read_unlock_special(t);
 	}
 
 	/*
@@ -284,7 +293,7 @@ static struct list_head *rcu_next_node_entry(struct task_struct *t,
  * notify RCU core processing or task having blocked during the RCU
  * read-side critical section.
  */
-static void rcu_read_unlock_special(struct task_struct *t)
+static noinline void rcu_read_unlock_special(struct task_struct *t)
 {
 	int empty;
 	int empty_exp;
@@ -309,7 +318,7 @@ static void rcu_read_unlock_special(struct task_struct *t)
 	}
 
 	/* Hardware IRQ handlers cannot block. */
-	if (in_irq()) {
+	if (in_irq() || in_serving_softirq()) {
 		local_irq_restore(flags);
 		return;
 	}
@@ -342,6 +351,11 @@ static void rcu_read_unlock_special(struct task_struct *t)
 #ifdef CONFIG_RCU_BOOST
 		if (&t->rcu_node_entry == rnp->boost_tasks)
 			rnp->boost_tasks = np;
+		/* Snapshot and clear ->rcu_boosted with rcu_node lock held. */
+		if (t->rcu_boosted) {
+			special |= RCU_READ_UNLOCK_BOOSTED;
+			t->rcu_boosted = 0;
+		}
 #endif /* #ifdef CONFIG_RCU_BOOST */
 		t->rcu_blocked_node = NULL;
 
@@ -358,7 +372,6 @@ static void rcu_read_unlock_special(struct task_struct *t)
 #ifdef CONFIG_RCU_BOOST
 		/* Unboost if we were boosted. */
 		if (special & RCU_READ_UNLOCK_BOOSTED) {
-			t->rcu_read_unlock_special &= ~RCU_READ_UNLOCK_BOOSTED;
 			rt_mutex_unlock(t->rcu_boost_mutex);
 			t->rcu_boost_mutex = NULL;
 		}
@@ -387,13 +400,22 @@ void __rcu_read_unlock(void)
 	struct task_struct *t = current;
 
 	barrier();  /* needed if we ever invoke rcu_read_unlock in rcutree.c */
-	--t->rcu_read_lock_nesting;
-	barrier();  /* decrement before load of ->rcu_read_unlock_special */
-	if (t->rcu_read_lock_nesting == 0 &&
-	    unlikely(ACCESS_ONCE(t->rcu_read_unlock_special)))
-		rcu_read_unlock_special(t);
+	if (t->rcu_read_lock_nesting != 1)
+		--t->rcu_read_lock_nesting;
+	else {
+		t->rcu_read_lock_nesting = INT_MIN;
+		barrier();  /* assign before ->rcu_read_unlock_special load */
+		if (unlikely(ACCESS_ONCE(t->rcu_read_unlock_special)))
+			rcu_read_unlock_special(t);
+		barrier();  /* ->rcu_read_unlock_special load before assign */
+		t->rcu_read_lock_nesting = 0;
+	}
 #ifdef CONFIG_PROVE_LOCKING
-	WARN_ON_ONCE(ACCESS_ONCE(t->rcu_read_lock_nesting) < 0);
+	{
+		int rrln = ACCESS_ONCE(t->rcu_read_lock_nesting);
+
+		WARN_ON_ONCE(rrln < 0 && rrln > INT_MIN / 2);
+	}
 #endif /* #ifdef CONFIG_PROVE_LOCKING */
 }
 EXPORT_SYMBOL_GPL(__rcu_read_unlock);
@@ -589,7 +611,8 @@ static void rcu_preempt_check_callbacks(int cpu)
 		rcu_preempt_qs(cpu);
 		return;
 	}
-	if (per_cpu(rcu_preempt_data, cpu).qs_pending)
+	if (t->rcu_read_lock_nesting > 0 &&
+	    per_cpu(rcu_preempt_data, cpu).qs_pending)
 		t->rcu_read_unlock_special |= RCU_READ_UNLOCK_NEED_QS;
 }
 
@@ -695,9 +718,12 @@ static void rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp)
 
 	raw_spin_lock_irqsave(&rnp->lock, flags);
 	for (;;) {
-		if (!sync_rcu_preempt_exp_done(rnp))
+		if (!sync_rcu_preempt_exp_done(rnp)) {
+			raw_spin_unlock_irqrestore(&rnp->lock, flags);
 			break;
+		}
 		if (rnp->parent == NULL) {
+			raw_spin_unlock_irqrestore(&rnp->lock, flags);
 			wake_up(&sync_rcu_preempt_exp_wq);
 			break;
 		}
@@ -707,7 +733,6 @@ static void rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp)
 		raw_spin_lock(&rnp->lock); /* irqs already disabled */
 		rnp->expmask &= ~mask;
 	}
-	raw_spin_unlock_irqrestore(&rnp->lock, flags);
 }
 
 /*
@@ -1174,7 +1199,7 @@ static int rcu_boost(struct rcu_node *rnp)
 	t = container_of(tb, struct task_struct, rcu_node_entry);
 	rt_mutex_init_proxy_locked(&mtx, t);
 	t->rcu_boost_mutex = &mtx;
-	t->rcu_read_unlock_special |= RCU_READ_UNLOCK_BOOSTED;
+	t->rcu_boosted = 1;
 	raw_spin_unlock_irqrestore(&rnp->lock, flags);
 	rt_mutex_lock(&mtx);  /* Side effect: boosts task t's priority. */
 	rt_mutex_unlock(&mtx);  /* Keep lockdep happy. */
diff --git a/kernel/sched.c b/kernel/sched.c
index 3dc716f6d8a..fde6ff90352 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -2544,13 +2544,9 @@ static int ttwu_remote(struct task_struct *p, int wake_flags)
 }
 
 #ifdef CONFIG_SMP
-static void sched_ttwu_pending(void)
+static void sched_ttwu_do_pending(struct task_struct *list)
 {
 	struct rq *rq = this_rq();
-	struct task_struct *list = xchg(&rq->wake_list, NULL);
-
-	if (!list)
-		return;
 
 	raw_spin_lock(&rq->lock);
 
@@ -2563,9 +2559,45 @@ static void sched_ttwu_pending(void)
 	raw_spin_unlock(&rq->lock);
 }
 
+#ifdef CONFIG_HOTPLUG_CPU
+
+static void sched_ttwu_pending(void)
+{
+	struct rq *rq = this_rq();
+	struct task_struct *list = xchg(&rq->wake_list, NULL);
+
+	if (!list)
+		return;
+
+	sched_ttwu_do_pending(list);
+}
+
+#endif /* CONFIG_HOTPLUG_CPU */
+
 void scheduler_ipi(void)
 {
-	sched_ttwu_pending();
+	struct rq *rq = this_rq();
+	struct task_struct *list = xchg(&rq->wake_list, NULL);
+
+	if (!list)
+		return;
+
+	/*
+	 * Not all reschedule IPI handlers call irq_enter/irq_exit, since
+	 * traditionally all their work was done from the interrupt return
+	 * path. Now that we actually do some work, we need to make sure
+	 * we do call them.
+	 *
+	 * Some archs already do call them, luckily irq_enter/exit nest
+	 * properly.
+	 *
+	 * Arguably we should visit all archs and update all handlers,
+	 * however a fair share of IPIs are still resched only so this would
+	 * somewhat pessimize the simple resched case.
+	 */
+	irq_enter();
+	sched_ttwu_do_pending(list);
+	irq_exit();
 }
 
 static void ttwu_queue_remote(struct task_struct *p, int cpu)
@@ -6557,7 +6589,7 @@ static int sched_domain_debug_one(struct sched_domain *sd, int cpu, int level,
 			break;
 		}
 
-		if (!group->cpu_power) {
+		if (!group->sgp->power) {
 			printk(KERN_CONT "\n");
 			printk(KERN_ERR "ERROR: domain->cpu_power not "
 					"set\n");
@@ -6581,9 +6613,9 @@ static int sched_domain_debug_one(struct sched_domain *sd, int cpu, int level,
 		cpulist_scnprintf(str, sizeof(str), sched_group_cpus(group));
 
 		printk(KERN_CONT " %s", str);
-		if (group->cpu_power != SCHED_POWER_SCALE) {
+		if (group->sgp->power != SCHED_POWER_SCALE) {
 			printk(KERN_CONT " (cpu_power = %d)",
-				group->cpu_power);
+				group->sgp->power);
 		}
 
 		group = group->next;
@@ -6774,11 +6806,39 @@ static struct root_domain *alloc_rootdomain(void)
 	return rd;
 }
 
+static void free_sched_groups(struct sched_group *sg, int free_sgp)
+{
+	struct sched_group *tmp, *first;
+
+	if (!sg)
+		return;
+
+	first = sg;
+	do {
+		tmp = sg->next;
+
+		if (free_sgp && atomic_dec_and_test(&sg->sgp->ref))
+			kfree(sg->sgp);
+
+		kfree(sg);
+		sg = tmp;
+	} while (sg != first);
+}
+
 static void free_sched_domain(struct rcu_head *rcu)
 {
 	struct sched_domain *sd = container_of(rcu, struct sched_domain, rcu);
-	if (atomic_dec_and_test(&sd->groups->ref))
+
+	/*
+	 * If its an overlapping domain it has private groups, iterate and
+	 * nuke them all.
+	 */
+	if (sd->flags & SD_OVERLAP) {
+		free_sched_groups(sd->groups, 1);
+	} else if (atomic_dec_and_test(&sd->groups->ref)) {
+		kfree(sd->groups->sgp);
 		kfree(sd->groups);
+	}
 	kfree(sd);
 }
 
@@ -6945,6 +7005,7 @@ int sched_smt_power_savings = 0, sched_mc_power_savings = 0;
 struct sd_data {
 	struct sched_domain **__percpu sd;
 	struct sched_group **__percpu sg;
+	struct sched_group_power **__percpu sgp;
 };
 
 struct s_data {
@@ -6964,15 +7025,73 @@ struct sched_domain_topology_level;
 typedef struct sched_domain *(*sched_domain_init_f)(struct sched_domain_topology_level *tl, int cpu);
 typedef const struct cpumask *(*sched_domain_mask_f)(int cpu);
 
+#define SDTL_OVERLAP	0x01
+
 struct sched_domain_topology_level {
 	sched_domain_init_f init;
 	sched_domain_mask_f mask;
+	int		    flags;
 	struct sd_data      data;
 };
 
-/*
- * Assumes the sched_domain tree is fully constructed
- */
+static int
+build_overlap_sched_groups(struct sched_domain *sd, int cpu)
+{
+	struct sched_group *first = NULL, *last = NULL, *groups = NULL, *sg;
+	const struct cpumask *span = sched_domain_span(sd);
+	struct cpumask *covered = sched_domains_tmpmask;
+	struct sd_data *sdd = sd->private;
+	struct sched_domain *child;
+	int i;
+
+	cpumask_clear(covered);
+
+	for_each_cpu(i, span) {
+		struct cpumask *sg_span;
+
+		if (cpumask_test_cpu(i, covered))
+			continue;
+
+		sg = kzalloc_node(sizeof(struct sched_group) + cpumask_size(),
+				GFP_KERNEL, cpu_to_node(i));
+
+		if (!sg)
+			goto fail;
+
+		sg_span = sched_group_cpus(sg);
+
+		child = *per_cpu_ptr(sdd->sd, i);
+		if (child->child) {
+			child = child->child;
+			cpumask_copy(sg_span, sched_domain_span(child));
+		} else
+			cpumask_set_cpu(i, sg_span);
+
+		cpumask_or(covered, covered, sg_span);
+
+		sg->sgp = *per_cpu_ptr(sdd->sgp, cpumask_first(sg_span));
+		atomic_inc(&sg->sgp->ref);
+
+		if (cpumask_test_cpu(cpu, sg_span))
+			groups = sg;
+
+		if (!first)
+			first = sg;
+		if (last)
+			last->next = sg;
+		last = sg;
+		last->next = first;
+	}
+	sd->groups = groups;
+
+	return 0;
+
+fail:
+	free_sched_groups(first, 0);
+
+	return -ENOMEM;
+}
+
 static int get_group(int cpu, struct sd_data *sdd, struct sched_group **sg)
 {
 	struct sched_domain *sd = *per_cpu_ptr(sdd->sd, cpu);
@@ -6981,24 +7100,24 @@ static int get_group(int cpu, struct sd_data *sdd, struct sched_group **sg)
 	if (child)
 		cpu = cpumask_first(sched_domain_span(child));
 
-	if (sg)
+	if (sg) {
 		*sg = *per_cpu_ptr(sdd->sg, cpu);
+		(*sg)->sgp = *per_cpu_ptr(sdd->sgp, cpu);
+		atomic_set(&(*sg)->sgp->ref, 1); /* for claim_allocations */
+	}
 
 	return cpu;
 }
 
 /*
- * build_sched_groups takes the cpumask we wish to span, and a pointer
- * to a function which identifies what group(along with sched group) a CPU
- * belongs to. The return value of group_fn must be a >= 0 and < nr_cpu_ids
- * (due to the fact that we keep track of groups covered with a struct cpumask).
- *
  * build_sched_groups will build a circular linked list of the groups
  * covered by the given span, and will set each group's ->cpumask correctly,
  * and ->cpu_power to 0.
+ *
+ * Assumes the sched_domain tree is fully constructed
  */
-static void
-build_sched_groups(struct sched_domain *sd)
+static int
+build_sched_groups(struct sched_domain *sd, int cpu)
 {
 	struct sched_group *first = NULL, *last = NULL;
 	struct sd_data *sdd = sd->private;
@@ -7006,6 +7125,12 @@ build_sched_groups(struct sched_domain *sd)
 	struct cpumask *covered;
 	int i;
 
+	get_group(cpu, sdd, &sd->groups);
+	atomic_inc(&sd->groups->ref);
+
+	if (cpu != cpumask_first(sched_domain_span(sd)))
+		return 0;
+
 	lockdep_assert_held(&sched_domains_mutex);
 	covered = sched_domains_tmpmask;
 
@@ -7020,7 +7145,7 @@ build_sched_groups(struct sched_domain *sd)
 			continue;
 
 		cpumask_clear(sched_group_cpus(sg));
-		sg->cpu_power = 0;
+		sg->sgp->power = 0;
 
 		for_each_cpu(j, span) {
 			if (get_group(j, sdd, NULL) != group)
@@ -7037,6 +7162,8 @@ build_sched_groups(struct sched_domain *sd)
 		last = sg;
 	}
 	last->next = first;
+
+	return 0;
 }
 
 /*
@@ -7051,12 +7178,17 @@ build_sched_groups(struct sched_domain *sd)
  */
 static void init_sched_groups_power(int cpu, struct sched_domain *sd)
 {
-	WARN_ON(!sd || !sd->groups);
+	struct sched_group *sg = sd->groups;
 
-	if (cpu != group_first_cpu(sd->groups))
-		return;
+	WARN_ON(!sd || !sg);
 
-	sd->groups->group_weight = cpumask_weight(sched_group_cpus(sd->groups));
+	do {
+		sg->group_weight = cpumask_weight(sched_group_cpus(sg));
+		sg = sg->next;
+	} while (sg != sd->groups);
+
+	if (cpu != group_first_cpu(sg))
+		return;
 
 	update_group_power(sd, cpu);
 }
@@ -7177,15 +7309,15 @@ static enum s_alloc __visit_domain_allocation_hell(struct s_data *d,
 static void claim_allocations(int cpu, struct sched_domain *sd)
 {
 	struct sd_data *sdd = sd->private;
-	struct sched_group *sg = sd->groups;
 
 	WARN_ON_ONCE(*per_cpu_ptr(sdd->sd, cpu) != sd);
 	*per_cpu_ptr(sdd->sd, cpu) = NULL;
 
-	if (cpu == cpumask_first(sched_group_cpus(sg))) {
-		WARN_ON_ONCE(*per_cpu_ptr(sdd->sg, cpu) != sg);
+	if (atomic_read(&(*per_cpu_ptr(sdd->sg, cpu))->ref))
 		*per_cpu_ptr(sdd->sg, cpu) = NULL;
-	}
+
+	if (atomic_read(&(*per_cpu_ptr(sdd->sgp, cpu))->ref))
+		*per_cpu_ptr(sdd->sgp, cpu) = NULL;
 }
 
 #ifdef CONFIG_SCHED_SMT
@@ -7210,7 +7342,7 @@ static struct sched_domain_topology_level default_topology[] = {
 #endif
 	{ sd_init_CPU, cpu_cpu_mask, },
 #ifdef CONFIG_NUMA
-	{ sd_init_NODE, cpu_node_mask, },
+	{ sd_init_NODE, cpu_node_mask, SDTL_OVERLAP, },
 	{ sd_init_ALLNODES, cpu_allnodes_mask, },
 #endif
 	{ NULL, },
@@ -7234,9 +7366,14 @@ static int __sdt_alloc(const struct cpumask *cpu_map)
 		if (!sdd->sg)
 			return -ENOMEM;
 
+		sdd->sgp = alloc_percpu(struct sched_group_power *);
+		if (!sdd->sgp)
+			return -ENOMEM;
+
 		for_each_cpu(j, cpu_map) {
 			struct sched_domain *sd;
 			struct sched_group *sg;
+			struct sched_group_power *sgp;
 
 		       	sd = kzalloc_node(sizeof(struct sched_domain) + cpumask_size(),
 					GFP_KERNEL, cpu_to_node(j));
@@ -7251,6 +7388,13 @@ static int __sdt_alloc(const struct cpumask *cpu_map)
 				return -ENOMEM;
 
 			*per_cpu_ptr(sdd->sg, j) = sg;
+
+			sgp = kzalloc_node(sizeof(struct sched_group_power),
+					GFP_KERNEL, cpu_to_node(j));
+			if (!sgp)
+				return -ENOMEM;
+
+			*per_cpu_ptr(sdd->sgp, j) = sgp;
 		}
 	}
 
@@ -7266,11 +7410,15 @@ static void __sdt_free(const struct cpumask *cpu_map)
 		struct sd_data *sdd = &tl->data;
 
 		for_each_cpu(j, cpu_map) {
-			kfree(*per_cpu_ptr(sdd->sd, j));
+			struct sched_domain *sd = *per_cpu_ptr(sdd->sd, j);
+			if (sd && (sd->flags & SD_OVERLAP))
+				free_sched_groups(sd->groups, 0);
 			kfree(*per_cpu_ptr(sdd->sg, j));
+			kfree(*per_cpu_ptr(sdd->sgp, j));
 		}
 		free_percpu(sdd->sd);
 		free_percpu(sdd->sg);
+		free_percpu(sdd->sgp);
 	}
 }
 
@@ -7316,8 +7464,13 @@ static int build_sched_domains(const struct cpumask *cpu_map,
 		struct sched_domain_topology_level *tl;
 
 		sd = NULL;
-		for (tl = sched_domain_topology; tl->init; tl++)
+		for (tl = sched_domain_topology; tl->init; tl++) {
 			sd = build_sched_domain(tl, &d, cpu_map, attr, sd, i);
+			if (tl->flags & SDTL_OVERLAP || sched_feat(FORCE_SD_OVERLAP))
+				sd->flags |= SD_OVERLAP;
+			if (cpumask_equal(cpu_map, sched_domain_span(sd)))
+				break;
+		}
 
 		while (sd->child)
 			sd = sd->child;
@@ -7329,13 +7482,13 @@ static int build_sched_domains(const struct cpumask *cpu_map,
 	for_each_cpu(i, cpu_map) {
 		for (sd = *per_cpu_ptr(d.sd, i); sd; sd = sd->parent) {
 			sd->span_weight = cpumask_weight(sched_domain_span(sd));
-			get_group(i, sd->private, &sd->groups);
-			atomic_inc(&sd->groups->ref);
-
-			if (i != cpumask_first(sched_domain_span(sd)))
-				continue;
-
-			build_sched_groups(sd);
+			if (sd->flags & SD_OVERLAP) {
+				if (build_overlap_sched_groups(sd, i))
+					goto error;
+			} else {
+				if (build_sched_groups(sd, i))
+					goto error;
+			}
 		}
 	}
 
diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c
index 433491c2dc8..c768588e180 100644
--- a/kernel/sched_fair.c
+++ b/kernel/sched_fair.c
@@ -1585,7 +1585,7 @@ find_idlest_group(struct sched_domain *sd, struct task_struct *p,
 		}
 
 		/* Adjust by relative CPU power of the group */
-		avg_load = (avg_load * SCHED_POWER_SCALE) / group->cpu_power;
+		avg_load = (avg_load * SCHED_POWER_SCALE) / group->sgp->power;
 
 		if (local_group) {
 			this_load = avg_load;
@@ -2631,7 +2631,7 @@ static void update_cpu_power(struct sched_domain *sd, int cpu)
 		power >>= SCHED_POWER_SHIFT;
 	}
 
-	sdg->cpu_power_orig = power;
+	sdg->sgp->power_orig = power;
 
 	if (sched_feat(ARCH_POWER))
 		power *= arch_scale_freq_power(sd, cpu);
@@ -2647,7 +2647,7 @@ static void update_cpu_power(struct sched_domain *sd, int cpu)
 		power = 1;
 
 	cpu_rq(cpu)->cpu_power = power;
-	sdg->cpu_power = power;
+	sdg->sgp->power = power;
 }
 
 static void update_group_power(struct sched_domain *sd, int cpu)
@@ -2665,11 +2665,11 @@ static void update_group_power(struct sched_domain *sd, int cpu)
 
 	group = child->groups;
 	do {
-		power += group->cpu_power;
+		power += group->sgp->power;
 		group = group->next;
 	} while (group != child->groups);
 
-	sdg->cpu_power = power;
+	sdg->sgp->power = power;
 }
 
 /*
@@ -2691,7 +2691,7 @@ fix_small_capacity(struct sched_domain *sd, struct sched_group *group)
 	/*
 	 * If ~90% of the cpu_power is still there, we're good.
 	 */
-	if (group->cpu_power * 32 > group->cpu_power_orig * 29)
+	if (group->sgp->power * 32 > group->sgp->power_orig * 29)
 		return 1;
 
 	return 0;
@@ -2771,7 +2771,7 @@ static inline void update_sg_lb_stats(struct sched_domain *sd,
 	}
 
 	/* Adjust by relative CPU power of the group */
-	sgs->avg_load = (sgs->group_load*SCHED_POWER_SCALE) / group->cpu_power;
+	sgs->avg_load = (sgs->group_load*SCHED_POWER_SCALE) / group->sgp->power;
 
 	/*
 	 * Consider the group unbalanced when the imbalance is larger
@@ -2788,7 +2788,7 @@ static inline void update_sg_lb_stats(struct sched_domain *sd,
 	if ((max_cpu_load - min_cpu_load) >= avg_load_per_task && max_nr_running > 1)
 		sgs->group_imb = 1;
 
-	sgs->group_capacity = DIV_ROUND_CLOSEST(group->cpu_power,
+	sgs->group_capacity = DIV_ROUND_CLOSEST(group->sgp->power,
 						SCHED_POWER_SCALE);
 	if (!sgs->group_capacity)
 		sgs->group_capacity = fix_small_capacity(sd, group);
@@ -2877,7 +2877,7 @@ static inline void update_sd_lb_stats(struct sched_domain *sd, int this_cpu,
 			return;
 
 		sds->total_load += sgs.group_load;
-		sds->total_pwr += sg->cpu_power;
+		sds->total_pwr += sg->sgp->power;
 
 		/*
 		 * In case the child domain prefers tasks go to siblings
@@ -2962,7 +2962,7 @@ static int check_asym_packing(struct sched_domain *sd,
 	if (this_cpu > busiest_cpu)
 		return 0;
 
-	*imbalance = DIV_ROUND_CLOSEST(sds->max_load * sds->busiest->cpu_power,
+	*imbalance = DIV_ROUND_CLOSEST(sds->max_load * sds->busiest->sgp->power,
 				       SCHED_POWER_SCALE);
 	return 1;
 }
@@ -2993,7 +2993,7 @@ static inline void fix_small_imbalance(struct sd_lb_stats *sds,
 
 	scaled_busy_load_per_task = sds->busiest_load_per_task
 					 * SCHED_POWER_SCALE;
-	scaled_busy_load_per_task /= sds->busiest->cpu_power;
+	scaled_busy_load_per_task /= sds->busiest->sgp->power;
 
 	if (sds->max_load - sds->this_load + scaled_busy_load_per_task >=
 			(scaled_busy_load_per_task * imbn)) {
@@ -3007,28 +3007,28 @@ static inline void fix_small_imbalance(struct sd_lb_stats *sds,
 	 * moving them.
 	 */
 
-	pwr_now += sds->busiest->cpu_power *
+	pwr_now += sds->busiest->sgp->power *
 			min(sds->busiest_load_per_task, sds->max_load);
-	pwr_now += sds->this->cpu_power *
+	pwr_now += sds->this->sgp->power *
 			min(sds->this_load_per_task, sds->this_load);
 	pwr_now /= SCHED_POWER_SCALE;
 
 	/* Amount of load we'd subtract */
 	tmp = (sds->busiest_load_per_task * SCHED_POWER_SCALE) /
-		sds->busiest->cpu_power;
+		sds->busiest->sgp->power;
 	if (sds->max_load > tmp)
-		pwr_move += sds->busiest->cpu_power *
+		pwr_move += sds->busiest->sgp->power *
 			min(sds->busiest_load_per_task, sds->max_load - tmp);
 
 	/* Amount of load we'd add */
-	if (sds->max_load * sds->busiest->cpu_power <
+	if (sds->max_load * sds->busiest->sgp->power <
 		sds->busiest_load_per_task * SCHED_POWER_SCALE)
-		tmp = (sds->max_load * sds->busiest->cpu_power) /
-			sds->this->cpu_power;
+		tmp = (sds->max_load * sds->busiest->sgp->power) /
+			sds->this->sgp->power;
 	else
 		tmp = (sds->busiest_load_per_task * SCHED_POWER_SCALE) /
-			sds->this->cpu_power;
-	pwr_move += sds->this->cpu_power *
+			sds->this->sgp->power;
+	pwr_move += sds->this->sgp->power *
 			min(sds->this_load_per_task, sds->this_load + tmp);
 	pwr_move /= SCHED_POWER_SCALE;
 
@@ -3074,7 +3074,7 @@ static inline void calculate_imbalance(struct sd_lb_stats *sds, int this_cpu,
 
 		load_above_capacity *= (SCHED_LOAD_SCALE * SCHED_POWER_SCALE);
 
-		load_above_capacity /= sds->busiest->cpu_power;
+		load_above_capacity /= sds->busiest->sgp->power;
 	}
 
 	/*
@@ -3090,8 +3090,8 @@ static inline void calculate_imbalance(struct sd_lb_stats *sds, int this_cpu,
 	max_pull = min(sds->max_load - sds->avg_load, load_above_capacity);
 
 	/* How much load to actually move to equalise the imbalance */
-	*imbalance = min(max_pull * sds->busiest->cpu_power,
-		(sds->avg_load - sds->this_load) * sds->this->cpu_power)
+	*imbalance = min(max_pull * sds->busiest->sgp->power,
+		(sds->avg_load - sds->this_load) * sds->this->sgp->power)
 			/ SCHED_POWER_SCALE;
 
 	/*
diff --git a/kernel/sched_features.h b/kernel/sched_features.h
index be40f7371ee..1e7066d76c2 100644
--- a/kernel/sched_features.h
+++ b/kernel/sched_features.h
@@ -70,3 +70,5 @@ SCHED_FEAT(NONIRQ_POWER, 1)
  * using the scheduler IPI. Reduces rq->lock contention/bounces.
  */
 SCHED_FEAT(TTWU_QUEUE, 1)
+
+SCHED_FEAT(FORCE_SD_OVERLAP, 0)
diff --git a/kernel/signal.c b/kernel/signal.c
index ff767860332..415d85d6f6c 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -1178,18 +1178,25 @@ struct sighand_struct *__lock_task_sighand(struct task_struct *tsk,
 {
 	struct sighand_struct *sighand;
 
-	rcu_read_lock();
 	for (;;) {
+		local_irq_save(*flags);
+		rcu_read_lock();
 		sighand = rcu_dereference(tsk->sighand);
-		if (unlikely(sighand == NULL))
+		if (unlikely(sighand == NULL)) {
+			rcu_read_unlock();
+			local_irq_restore(*flags);
 			break;
+		}
 
-		spin_lock_irqsave(&sighand->siglock, *flags);
-		if (likely(sighand == tsk->sighand))
+		spin_lock(&sighand->siglock);
+		if (likely(sighand == tsk->sighand)) {
+			rcu_read_unlock();
 			break;
-		spin_unlock_irqrestore(&sighand->siglock, *flags);
+		}
+		spin_unlock(&sighand->siglock);
+		rcu_read_unlock();
+		local_irq_restore(*flags);
 	}
-	rcu_read_unlock();
 
 	return sighand;
 }
diff --git a/kernel/softirq.c b/kernel/softirq.c
index 40cf63ddd4b..fca82c32042 100644
--- a/kernel/softirq.c
+++ b/kernel/softirq.c
@@ -315,16 +315,24 @@ static inline void invoke_softirq(void)
 {
 	if (!force_irqthreads)
 		__do_softirq();
-	else
+	else {
+		__local_bh_disable((unsigned long)__builtin_return_address(0),
+				SOFTIRQ_OFFSET);
 		wakeup_softirqd();
+		__local_bh_enable(SOFTIRQ_OFFSET);
+	}
 }
 #else
 static inline void invoke_softirq(void)
 {
 	if (!force_irqthreads)
 		do_softirq();
-	else
+	else {
+		__local_bh_disable((unsigned long)__builtin_return_address(0),
+				SOFTIRQ_OFFSET);
 		wakeup_softirqd();
+		__local_bh_enable(SOFTIRQ_OFFSET);
+	}
 }
 #endif
 
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 5ed24b94c5e..d036e59d302 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -2310,7 +2310,8 @@ static bool pgdat_balanced(pg_data_t *pgdat, unsigned long balanced_pages,
 	for (i = 0; i <= classzone_idx; i++)
 		present_pages += pgdat->node_zones[i].present_pages;
 
-	return balanced_pages > (present_pages >> 2);
+	/* A special case here: if zone has no page, we think it's balanced */
+	return balanced_pages >= (present_pages >> 2);
 }
 
 /* is kswapd sleeping prematurely? */
diff --git a/net/ceph/ceph_fs.c b/net/ceph/ceph_fs.c
index a3a3a31d3c3..41466ccb972 100644
--- a/net/ceph/ceph_fs.c
+++ b/net/ceph/ceph_fs.c
@@ -36,16 +36,19 @@ int ceph_flags_to_mode(int flags)
 	if ((flags & O_DIRECTORY) == O_DIRECTORY)
 		return CEPH_FILE_MODE_PIN;
 #endif
-	if ((flags & O_APPEND) == O_APPEND)
-		flags |= O_WRONLY;
 
-	if ((flags & O_ACCMODE) == O_RDWR)
-		mode = CEPH_FILE_MODE_RDWR;
-	else if ((flags & O_ACCMODE) == O_WRONLY)
+	switch (flags & O_ACCMODE) {
+	case O_WRONLY:
 		mode = CEPH_FILE_MODE_WR;
-	else
+		break;
+	case O_RDONLY:
 		mode = CEPH_FILE_MODE_RD;
-
+		break;
+	case O_RDWR:
+	case O_ACCMODE: /* this is what the VFS does */
+		mode = CEPH_FILE_MODE_RDWR;
+		break;
+	}
 #ifdef O_LAZY
 	if (flags & O_LAZY)
 		mode |= CEPH_FILE_MODE_LAZY;