Linux 3.4.81

commit 3dd4765fce upstream.

...and ensure that we tear down the nfs_commit_data cache too when
unloading the module.

Cc: Bryan Schumaker <bjschuma@netapp.com>
Signed-off-by: Jeff Layton <jlayton@redhat.com>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
[bwh: Backported to 3.2: drop the nfs_cdata_cachep cleanup; it doesn't exist]
Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
Cc: Li Zefan <lizefan@huawei.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

Makefile

@@ -1,6 +1,6 @@
 VERSION = 3
 PATCHLEVEL = 4
-SUBLEVEL = 80
+SUBLEVEL = 81
 EXTRAVERSION =
 NAME = Saber-toothed Squirrel
 

drivers/block/virtio_blk.c

@@ -21,8 +21,6 @@ struct workqueue_struct *virtblk_wq;
 
 struct virtio_blk
 {
-	spinlock_t lock;
-
 	struct virtio_device *vdev;
 	struct virtqueue *vq;
 
@@ -69,7 +67,7 @@ static void blk_done(struct virtqueue *vq)
 	unsigned int len;
 	unsigned long flags;
 
-	spin_lock_irqsave(&vblk->lock, flags);
+	spin_lock_irqsave(vblk->disk->queue->queue_lock, flags);
 	while ((vbr = virtqueue_get_buf(vblk->vq, &len)) != NULL) {
 		int error;
 
@@ -104,7 +102,7 @@ static void blk_done(struct virtqueue *vq)
 	}
 	/* In case queue is stopped waiting for more buffers. */
 	blk_start_queue(vblk->disk->queue);
-	spin_unlock_irqrestore(&vblk->lock, flags);
+	spin_unlock_irqrestore(vblk->disk->queue->queue_lock, flags);
 }
 
 static bool do_req(struct request_queue *q, struct virtio_blk *vblk,
@@ -438,7 +436,6 @@ static int __devinit virtblk_probe(struct virtio_device *vdev)
 	}
 
 	INIT_LIST_HEAD(&vblk->reqs);
-	spin_lock_init(&vblk->lock);
 	vblk->vdev = vdev;
 	vblk->sg_elems = sg_elems;
 	sg_init_table(vblk->sg, vblk->sg_elems);
@@ -463,7 +460,7 @@ static int __devinit virtblk_probe(struct virtio_device *vdev)
 		goto out_mempool;
 	}
 
-	q = vblk->disk->queue = blk_init_queue(do_virtblk_request, &vblk->lock);
+	q = vblk->disk->queue = blk_init_queue(do_virtblk_request, NULL);
 	if (!q) {
 		err = -ENOMEM;
 		goto out_put_disk;

drivers/gpu/drm/i915/i915_dma.c

@@ -1934,6 +1934,27 @@ ips_ping_for_i915_load(void)
 	}
 }
 
+static void i915_kick_out_firmware_fb(struct drm_i915_private *dev_priv)
+{
+	struct apertures_struct *ap;
+	struct pci_dev *pdev = dev_priv->dev->pdev;
+	bool primary;
+
+	ap = alloc_apertures(1);
+	if (!ap)
+		return;
+
+	ap->ranges[0].base = dev_priv->dev->agp->base;
+	ap->ranges[0].size =
+		dev_priv->mm.gtt->gtt_mappable_entries << PAGE_SHIFT;
+	primary =
+		pdev->resource[PCI_ROM_RESOURCE].flags & IORESOURCE_ROM_SHADOW;
+
+	remove_conflicting_framebuffers(ap, "inteldrmfb", primary);
+
+	kfree(ap);
+}
+
 /**
  * i915_driver_load - setup chip and create an initial config
  * @dev: DRM device
@@ -1971,6 +1992,15 @@ int i915_driver_load(struct drm_device *dev, unsigned long flags)
 		goto free_priv;
 	}
 
+	dev_priv->mm.gtt = intel_gtt_get();
+	if (!dev_priv->mm.gtt) {
+		DRM_ERROR("Failed to initialize GTT\n");
+		ret = -ENODEV;
+		goto put_bridge;
+	}
+
+	i915_kick_out_firmware_fb(dev_priv);
+
 	pci_set_master(dev->pdev);
 
 	/* overlay on gen2 is broken and can't address above 1G */
@@ -1996,13 +2026,6 @@ int i915_driver_load(struct drm_device *dev, unsigned long flags)
 		goto put_bridge;
 	}
 
-	dev_priv->mm.gtt = intel_gtt_get();
-	if (!dev_priv->mm.gtt) {
-		DRM_ERROR("Failed to initialize GTT\n");
-		ret = -ENODEV;
-		goto out_rmmap;
-	}
-
 	agp_size = dev_priv->mm.gtt->gtt_mappable_entries << PAGE_SHIFT;
 
 	dev_priv->mm.gtt_mapping =

drivers/infiniband/hw/qib/qib_user_sdma.c

@@ -284,8 +284,7 @@ static int qib_user_sdma_pin_pages(const struct qib_devdata *dd,
 	int j;
 	int ret;
 
-	ret = get_user_pages(current, current->mm, addr,
-			     npages, 0, 1, pages, NULL);
+	ret = get_user_pages_fast(addr, npages, 0, pages);
 
 	if (ret != npages) {
 		int i;
@@ -830,10 +829,7 @@ int qib_user_sdma_writev(struct qib_ctxtdata *rcd,
 	while (dim) {
 		const int mxp = 8;
 
-		down_write(&current->mm->mmap_sem);
 		ret = qib_user_sdma_queue_pkts(dd, pq, &list, iov, dim, mxp);
-		up_write(&current->mm->mmap_sem);
-
 		if (ret <= 0)
 			goto done_unlock;
 		else {

drivers/input/mouse/synaptics.c

@@ -40,11 +40,28 @@
  * Note that newer firmware allows querying device for maximum useable
  * coordinates.
  */
+#define XMIN 0
+#define XMAX 6143
+#define YMIN 0
+#define YMAX 6143
 #define XMIN_NOMINAL 1472
 #define XMAX_NOMINAL 5472
 #define YMIN_NOMINAL 1408
 #define YMAX_NOMINAL 4448
 
+/* Size in bits of absolute position values reported by the hardware */
+#define ABS_POS_BITS 13
+
+/*
+ * Any position values from the hardware above the following limits are
+ * treated as "wrapped around negative" values that have been truncated to
+ * the 13-bit reporting range of the hardware. These are just reasonable
+ * guesses and can be adjusted if hardware is found that operates outside
+ * of these parameters.
+ */
+#define X_MAX_POSITIVE (((1 << ABS_POS_BITS) + XMAX) / 2)
+#define Y_MAX_POSITIVE (((1 << ABS_POS_BITS) + YMAX) / 2)
+
 /*
  * Synaptics touchpads report the y coordinate from bottom to top, which is
  * opposite from what userspace expects.
@@ -555,6 +572,12 @@ static int synaptics_parse_hw_state(const unsigned char buf[],
 		hw->right = (buf[0] & 0x02) ? 1 : 0;
 	}
 
+	/* Convert wrap-around values to negative */
+	if (hw->x > X_MAX_POSITIVE)
+		hw->x -= 1 << ABS_POS_BITS;
+	if (hw->y > Y_MAX_POSITIVE)
+		hw->y -= 1 << ABS_POS_BITS;
+
 	return 0;
 }
 

drivers/md/Kconfig

@@ -185,8 +185,12 @@ config MD_FAULTY
 
 	  In unsure, say N.
 
+config BLK_DEV_DM_BUILTIN
+	boolean
+
 config BLK_DEV_DM
 	tristate "Device mapper support"
+	select BLK_DEV_DM_BUILTIN
 	---help---
 	  Device-mapper is a low level volume manager.  It works by allowing
 	  people to specify mappings for ranges of logical sectors.  Various

drivers/md/Makefile

@@ -28,6 +28,7 @@ obj-$(CONFIG_MD_MULTIPATH)	+= multipath.o
 obj-$(CONFIG_MD_FAULTY)		+= faulty.o
 obj-$(CONFIG_BLK_DEV_MD)	+= md-mod.o
 obj-$(CONFIG_BLK_DEV_DM)	+= dm-mod.o
+obj-$(CONFIG_BLK_DEV_DM_BUILTIN) += dm-builtin.o
 obj-$(CONFIG_DM_BUFIO)		+= dm-bufio.o
 obj-$(CONFIG_DM_CRYPT)		+= dm-crypt.o
 obj-$(CONFIG_DM_DELAY)		+= dm-delay.o

drivers/md/dm-builtin.c

@@ -0,0 +1,50 @@
+#include "dm.h"
+
+#include <linux/export.h>
+
+/*
+ * The kobject release method must not be placed in the module itself,
+ * otherwise we are subject to module unload races.
+ *
+ * The release method is called when the last reference to the kobject is
+ * dropped. It may be called by any other kernel code that drops the last
+ * reference.
+ *
+ * The release method suffers from module unload race. We may prevent the
+ * module from being unloaded at the start of the release method (using
+ * increased module reference count or synchronizing against the release
+ * method), however there is no way to prevent the module from being
+ * unloaded at the end of the release method.
+ *
+ * If this code were placed in the dm module, the following race may
+ * happen:
+ *  1. Some other process takes a reference to dm kobject
+ *  2. The user issues ioctl function to unload the dm device
+ *  3. dm_sysfs_exit calls kobject_put, however the object is not released
+ *     because of the other reference taken at step 1
+ *  4. dm_sysfs_exit waits on the completion
+ *  5. The other process that took the reference in step 1 drops it,
+ *     dm_kobject_release is called from this process
+ *  6. dm_kobject_release calls complete()
+ *  7. a reschedule happens before dm_kobject_release returns
+ *  8. dm_sysfs_exit continues, the dm device is unloaded, module reference
+ *     count is decremented
+ *  9. The user unloads the dm module
+ * 10. The other process that was rescheduled in step 7 continues to run,
+ *     it is now executing code in unloaded module, so it crashes
+ *
+ * Note that if the process that takes the foreign reference to dm kobject
+ * has a low priority and the system is sufficiently loaded with
+ * higher-priority processes that prevent the low-priority process from
+ * being scheduled long enough, this bug may really happen.
+ *
+ * In order to fix this module unload race, we place the release method
+ * into a helper code that is compiled directly into the kernel.
+ */
+
+void dm_kobject_release(struct kobject *kobj)
+{
+	complete(dm_get_completion_from_kobject(kobj));
+}
+
+EXPORT_SYMBOL(dm_kobject_release);

drivers/md/dm-sysfs.c

@@ -79,11 +79,6 @@ static const struct sysfs_ops dm_sysfs_ops = {
 	.show	= dm_attr_show,
 };
 
-static void dm_kobject_release(struct kobject *kobj)
-{
-	complete(dm_get_completion_from_kobject(kobj));
-}
-
 /*
  * dm kobject is embedded in mapped_device structure
  * no need to define release function here

drivers/md/dm.c

@@ -191,11 +191,8 @@ struct mapped_device {
 	/* forced geometry settings */
 	struct hd_geometry geometry;
 
-	/* sysfs handle */
-	struct kobject kobj;
-
-	/* wait until the kobject is released */
-	struct completion kobj_completion;
+	/* kobject and completion */
+	struct dm_kobject_holder kobj_holder;
 
 	/* zero-length flush that will be cloned and submitted to targets */
 	struct bio flush_bio;
@@ -1894,7 +1891,7 @@ static struct mapped_device *alloc_dev(int minor)
 	init_waitqueue_head(&md->wait);
 	INIT_WORK(&md->work, dm_wq_work);
 	init_waitqueue_head(&md->eventq);
-	init_completion(&md->kobj_completion);
+	init_completion(&md->kobj_holder.completion);
 
 	md->disk->major = _major;
 	md->disk->first_minor = minor;
@@ -2686,20 +2683,14 @@ struct gendisk *dm_disk(struct mapped_device *md)
 
 struct kobject *dm_kobject(struct mapped_device *md)
 {
-	return &md->kobj;
+	return &md->kobj_holder.kobj;
 }
 
-/*
- * struct mapped_device should not be exported outside of dm.c
- * so use this check to verify that kobj is part of md structure
- */
 struct mapped_device *dm_get_from_kobject(struct kobject *kobj)
 {
 	struct mapped_device *md;
 
-	md = container_of(kobj, struct mapped_device, kobj);
-	if (&md->kobj != kobj)
-		return NULL;
+	md = container_of(kobj, struct mapped_device, kobj_holder.kobj);
 
 	if (test_bit(DMF_FREEING, &md->flags) ||
 	    dm_deleting_md(md))
@@ -2709,13 +2700,6 @@ struct mapped_device *dm_get_from_kobject(struct kobject *kobj)
 	return md;
 }
 
-struct completion *dm_get_completion_from_kobject(struct kobject *kobj)
-{
-	struct mapped_device *md = container_of(kobj, struct mapped_device, kobj);
-
-	return &md->kobj_completion;
-}
-
 int dm_suspended_md(struct mapped_device *md)
 {
 	return test_bit(DMF_SUSPENDED, &md->flags);

drivers/md/dm.h

@@ -16,6 +16,7 @@
 #include <linux/blkdev.h>
 #include <linux/hdreg.h>
 #include <linux/completion.h>
+#include <linux/kobject.h>
 
 /*
  * Suspend feature flags
@@ -120,11 +121,25 @@ void dm_interface_exit(void);
 /*
  * sysfs interface
  */
+struct dm_kobject_holder {
+	struct kobject kobj;
+	struct completion completion;
+};
+
+static inline struct completion *dm_get_completion_from_kobject(struct kobject *kobj)
+{
+	return &container_of(kobj, struct dm_kobject_holder, kobj)->completion;
+}
+
 int dm_sysfs_init(struct mapped_device *md);
 void dm_sysfs_exit(struct mapped_device *md);
 struct kobject *dm_kobject(struct mapped_device *md);
 struct mapped_device *dm_get_from_kobject(struct kobject *kobj);
-struct completion *dm_get_completion_from_kobject(struct kobject *kobj);
+
+/*
+ * The kobject helper
+ */
+void dm_kobject_release(struct kobject *kobj);
 
 /*
  * Targets for linear and striped mappings

drivers/target/target_core_file.c

@@ -133,21 +133,24 @@ static struct se_device *fd_create_virtdevice(
 		ret = PTR_ERR(dev_p);
 		goto fail;
 	}
-#if 0
-	if (di->no_create_file)
-		flags = O_RDWR | O_LARGEFILE;
-	else
-		flags = O_RDWR | O_CREAT | O_LARGEFILE;
-#else
-	flags = O_RDWR | O_CREAT | O_LARGEFILE;
-#endif
-/*	flags |= O_DIRECT; */
 	/*
-	 * If fd_buffered_io=1 has not been set explicitly (the default),
-	 * use O_SYNC to force FILEIO writes to disk.
+	 * Use O_DSYNC by default instead of O_SYNC to forgo syncing
+	 * of pure timestamp updates.
 	 */
-	if (!(fd_dev->fbd_flags & FDBD_USE_BUFFERED_IO))
-		flags |= O_SYNC;
+	flags = O_RDWR | O_CREAT | O_LARGEFILE | O_DSYNC;
+	/*
+	 * Optionally allow fd_buffered_io=1 to be enabled for people
+	 * who want use the fs buffer cache as an WriteCache mechanism.
+	 *
+	 * This means that in event of a hard failure, there is a risk
+	 * of silent data-loss if the SCSI client has *not* performed a
+	 * forced unit access (FUA) write, or issued SYNCHRONIZE_CACHE
+	 * to write-out the entire device cache.
+	 */
+	if (fd_dev->fbd_flags & FDBD_HAS_BUFFERED_IO_WCE) {
+		pr_debug("FILEIO: Disabling O_DSYNC, using buffered FILEIO\n");
+		flags &= ~O_DSYNC;
+	}
 
 	file = filp_open(dev_p, flags, 0600);
 	if (IS_ERR(file)) {
@@ -215,6 +218,12 @@ static struct se_device *fd_create_virtdevice(
 	if (!dev)
 		goto fail;
 
+	if (fd_dev->fbd_flags & FDBD_HAS_BUFFERED_IO_WCE) {
+		pr_debug("FILEIO: Forcing setting of emulate_write_cache=1"
+			" with FDBD_HAS_BUFFERED_IO_WCE\n");
+		dev->se_sub_dev->se_dev_attrib.emulate_write_cache = 1;
+	}
+
 	fd_dev->fd_dev_id = fd_host->fd_host_dev_id_count++;
 	fd_dev->fd_queue_depth = dev->queue_depth;
 
@@ -399,26 +408,6 @@ static void fd_emulate_sync_cache(struct se_task *task)
 		transport_complete_sync_cache(cmd, ret == 0);
 }
 
-/*
- * WRITE Force Unit Access (FUA) emulation on a per struct se_task
- * LBA range basis..
- */
-static void fd_emulate_write_fua(struct se_cmd *cmd, struct se_task *task)
-{
-	struct se_device *dev = cmd->se_dev;
-	struct fd_dev *fd_dev = dev->dev_ptr;
-	loff_t start = task->task_lba * dev->se_sub_dev->se_dev_attrib.block_size;
-	loff_t end = start + task->task_size;
-	int ret;
-
-	pr_debug("FILEIO: FUA WRITE LBA: %llu, bytes: %u\n",
-			task->task_lba, task->task_size);
-
-	ret = vfs_fsync_range(fd_dev->fd_file, start, end, 1);
-	if (ret != 0)
-		pr_err("FILEIO: vfs_fsync_range() failed: %d\n", ret);
-}
-
 static int fd_do_task(struct se_task *task)
 {
 	struct se_cmd *cmd = task->task_se_cmd;
@@ -433,19 +422,21 @@ static int fd_do_task(struct se_task *task)
 		ret = fd_do_readv(task);
 	} else {
 		ret = fd_do_writev(task);
-
+		/*
+		 * Perform implict vfs_fsync_range() for fd_do_writev() ops
+		 * for SCSI WRITEs with Forced Unit Access (FUA) set.
+		 * Allow this to happen independent of WCE=0 setting.
+		 */
 		if (ret > 0 &&
-		    dev->se_sub_dev->se_dev_attrib.emulate_write_cache > 0 &&
 		    dev->se_sub_dev->se_dev_attrib.emulate_fua_write > 0 &&
 		    (cmd->se_cmd_flags & SCF_FUA)) {
-			/*
-			 * We might need to be a bit smarter here
-			 * and return some sense data to let the initiator
-			 * know the FUA WRITE cache sync failed..?
-			 */
-			fd_emulate_write_fua(cmd, task);
-		}
+			struct fd_dev *fd_dev = dev->dev_ptr;
+			loff_t start = task->task_lba *
+				dev->se_sub_dev->se_dev_attrib.block_size;
+			loff_t end = start + task->task_size;
 
+			vfs_fsync_range(fd_dev->fd_file, start, end, 1);
+		}
 	}
 
 	if (ret < 0) {
@@ -544,7 +535,7 @@ static ssize_t fd_set_configfs_dev_params(
 			pr_debug("FILEIO: Using buffered I/O"
 				" operations for struct fd_dev\n");
 
-			fd_dev->fbd_flags |= FDBD_USE_BUFFERED_IO;
+			fd_dev->fbd_flags |= FDBD_HAS_BUFFERED_IO_WCE;
 			break;
 		default:
 			break;
@@ -579,8 +570,8 @@ static ssize_t fd_show_configfs_dev_params(
 	bl = sprintf(b + bl, "TCM FILEIO ID: %u", fd_dev->fd_dev_id);
 	bl += sprintf(b + bl, "        File: %s  Size: %llu  Mode: %s\n",
 		fd_dev->fd_dev_name, fd_dev->fd_dev_size,
-		(fd_dev->fbd_flags & FDBD_USE_BUFFERED_IO) ?
-		"Buffered" : "Synchronous");
+		(fd_dev->fbd_flags & FDBD_HAS_BUFFERED_IO_WCE) ?
+		"Buffered-WCE" : "O_DSYNC");
 	return bl;
 }
 

drivers/target/target_core_file.h

@@ -18,7 +18,7 @@ struct fd_request {
 
 #define FBDF_HAS_PATH		0x01
 #define FBDF_HAS_SIZE		0x02
-#define FDBD_USE_BUFFERED_IO	0x04
+#define FDBD_HAS_BUFFERED_IO_WCE 0x04
 
 struct fd_dev {
 	u32		fbd_flags;

fs/buffer.c

@@ -613,14 +613,16 @@ EXPORT_SYMBOL(mark_buffer_dirty_inode);
 static void __set_page_dirty(struct page *page,
 		struct address_space *mapping, int warn)
 {
-	spin_lock_irq(&mapping->tree_lock);
+	unsigned long flags;
+
+	spin_lock_irqsave(&mapping->tree_lock, flags);
 	if (page->mapping) {	/* Race with truncate? */
 		WARN_ON_ONCE(warn && !PageUptodate(page));
 		account_page_dirtied(page, mapping);
 		radix_tree_tag_set(&mapping->page_tree,
 				page_index(page), PAGECACHE_TAG_DIRTY);
 	}
-	spin_unlock_irq(&mapping->tree_lock);
+	spin_unlock_irqrestore(&mapping->tree_lock, flags);
 	__mark_inode_dirty(mapping->host, I_DIRTY_PAGES);
 }
 

fs/ext4/ialloc.c

@@ -778,6 +778,8 @@ got:
 			ext4_itable_unused_set(sb, gdp,
 					(EXT4_INODES_PER_GROUP(sb) - ino));
 		up_read(&grp->alloc_sem);
+	} else {
+		ext4_lock_group(sb, group);
 	}
 	ext4_free_inodes_set(sb, gdp, ext4_free_inodes_count(sb, gdp) - 1);
 	if (S_ISDIR(mode)) {
@@ -790,8 +792,8 @@ got:
 	}
 	if (EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_GDT_CSUM)) {
 		gdp->bg_checksum = ext4_group_desc_csum(sbi, group, gdp);
-		ext4_unlock_group(sb, group);
 	}
+	ext4_unlock_group(sb, group);
 
 	BUFFER_TRACE(group_desc_bh, "call ext4_handle_dirty_metadata");
 	err = ext4_handle_dirty_metadata(handle, NULL, group_desc_bh);

fs/nfs/write.c

@@ -1751,12 +1751,12 @@ int __init nfs_init_writepagecache(void)
 	nfs_wdata_mempool = mempool_create_slab_pool(MIN_POOL_WRITE,
 						     nfs_wdata_cachep);
 	if (nfs_wdata_mempool == NULL)
-		return -ENOMEM;
+		goto out_destroy_write_cache;
 
 	nfs_commit_mempool = mempool_create_slab_pool(MIN_POOL_COMMIT,
 						      nfs_wdata_cachep);
 	if (nfs_commit_mempool == NULL)
-		return -ENOMEM;
+		goto out_destroy_write_mempool;
 
 	/*
 	 * NFS congestion size, scale with available memory.
@@ -1779,6 +1779,12 @@ int __init nfs_init_writepagecache(void)
 		nfs_congestion_kb = 256*1024;
 
 	return 0;
+
+out_destroy_write_mempool:
+	mempool_destroy(nfs_wdata_mempool);
+out_destroy_write_cache:
+	kmem_cache_destroy(nfs_wdata_cachep);
+	return -ENOMEM;
 }
 
 void nfs_destroy_writepagecache(void)

include/linux/sched.h

@@ -144,6 +144,7 @@ extern unsigned long this_cpu_load(void);
 
 
 extern void calc_global_load(unsigned long ticks);
+extern void update_cpu_load_nohz(void);
 
 extern unsigned long get_parent_ip(unsigned long addr);
 

kernel/power/swap.c

@@ -6,7 +6,7 @@
  *
  * Copyright (C) 1998,2001-2005 Pavel Machek <pavel@ucw.cz>
  * Copyright (C) 2006 Rafael J. Wysocki <rjw@sisk.pl>
- * Copyright (C) 2010 Bojan Smojver <bojan@rexursive.com>
+ * Copyright (C) 2010-2012 Bojan Smojver <bojan@rexursive.com>
  *
  * This file is released under the GPLv2.
  *
@@ -282,14 +282,17 @@ static int write_page(void *buf, sector_t offset, struct bio **bio_chain)
 		return -ENOSPC;
 
 	if (bio_chain) {
-		src = (void *)__get_free_page(__GFP_WAIT | __GFP_HIGH);
+		src = (void *)__get_free_page(__GFP_WAIT | __GFP_NOWARN |
+		                              __GFP_NORETRY);
 		if (src) {
 			copy_page(src, buf);
 		} else {
 			ret = hib_wait_on_bio_chain(bio_chain); /* Free pages */
 			if (ret)
 				return ret;
-			src = (void *)__get_free_page(__GFP_WAIT | __GFP_HIGH);
+			src = (void *)__get_free_page(__GFP_WAIT |
+			                              __GFP_NOWARN |
+			                              __GFP_NORETRY);
 			if (src) {
 				copy_page(src, buf);
 			} else {
@@ -367,12 +370,17 @@ static int swap_write_page(struct swap_map_handle *handle, void *buf,
 		clear_page(handle->cur);
 		handle->cur_swap = offset;
 		handle->k = 0;
-	}
-	if (bio_chain && low_free_pages() <= handle->reqd_free_pages) {
-		error = hib_wait_on_bio_chain(bio_chain);
-		if (error)
-			goto out;
-		handle->reqd_free_pages = reqd_free_pages();
+
+		if (bio_chain && low_free_pages() <= handle->reqd_free_pages) {
+			error = hib_wait_on_bio_chain(bio_chain);
+			if (error)
+				goto out;
+			/*
+			 * Recalculate the number of required free pages, to
+			 * make sure we never take more than half.
+			 */
+			handle->reqd_free_pages = reqd_free_pages();
+		}
 	}
  out:
 	return error;
@@ -419,8 +427,9 @@ static int swap_writer_finish(struct swap_map_handle *handle,
 /* Maximum number of threads for compression/decompression. */
 #define LZO_THREADS	3
 
-/* Maximum number of pages for read buffering. */
-#define LZO_READ_PAGES	(MAP_PAGE_ENTRIES * 8)
+/* Minimum/maximum number of pages for read buffering. */
+#define LZO_MIN_RD_PAGES	1024
+#define LZO_MAX_RD_PAGES	8192
 
 
 /**
@@ -630,12 +639,6 @@ static int save_image_lzo(struct swap_map_handle *handle,
 		}
 	}
 
-	/*
-	 * Adjust number of free pages after all allocations have been done.
-	 * We don't want to run out of pages when writing.
-	 */
-	handle->reqd_free_pages = reqd_free_pages();
-
 	/*
 	 * Start the CRC32 thread.
 	 */
@@ -657,6 +660,12 @@ static int save_image_lzo(struct swap_map_handle *handle,
 		goto out_clean;
 	}
 
+	/*
+	 * Adjust the number of required free pages after all allocations have
+	 * been done. We don't want to run out of pages when writing.
+	 */
+	handle->reqd_free_pages = reqd_free_pages();
+
 	printk(KERN_INFO
 		"PM: Using %u thread(s) for compression.\n"
 		"PM: Compressing and saving image data (%u pages) ...     ",
@@ -1067,7 +1076,7 @@ static int load_image_lzo(struct swap_map_handle *handle,
 	unsigned i, thr, run_threads, nr_threads;
 	unsigned ring = 0, pg = 0, ring_size = 0,
 	         have = 0, want, need, asked = 0;
-	unsigned long read_pages;
+	unsigned long read_pages = 0;
 	unsigned char **page = NULL;
 	struct dec_data *data = NULL;
 	struct crc_data *crc = NULL;
@@ -1079,7 +1088,7 @@ static int load_image_lzo(struct swap_map_handle *handle,
 	nr_threads = num_online_cpus() - 1;
 	nr_threads = clamp_val(nr_threads, 1, LZO_THREADS);
 
-	page = vmalloc(sizeof(*page) * LZO_READ_PAGES);
+	page = vmalloc(sizeof(*page) * LZO_MAX_RD_PAGES);
 	if (!page) {
 		printk(KERN_ERR "PM: Failed to allocate LZO page\n");
 		ret = -ENOMEM;
@@ -1144,15 +1153,22 @@ static int load_image_lzo(struct swap_map_handle *handle,
 	}
 
 	/*
-	 * Adjust number of pages for read buffering, in case we are short.
+	 * Set the number of pages for read buffering.
+	 * This is complete guesswork, because we'll only know the real
+	 * picture once prepare_image() is called, which is much later on
+	 * during the image load phase. We'll assume the worst case and
+	 * say that none of the image pages are from high memory.
 	 */
-	read_pages = (nr_free_pages() - snapshot_get_image_size()) >> 1;
-	read_pages = clamp_val(read_pages, LZO_CMP_PAGES, LZO_READ_PAGES);
+	if (low_free_pages() > snapshot_get_image_size())
+		read_pages = (low_free_pages() - snapshot_get_image_size()) / 2;
+	read_pages = clamp_val(read_pages, LZO_MIN_RD_PAGES, LZO_MAX_RD_PAGES);
 
 	for (i = 0; i < read_pages; i++) {
 		page[i] = (void *)__get_free_page(i < LZO_CMP_PAGES ?
 		                                  __GFP_WAIT | __GFP_HIGH :
-		                                  __GFP_WAIT);
+		                                  __GFP_WAIT | __GFP_NOWARN |
+		                                  __GFP_NORETRY);
+
 		if (!page[i]) {
 			if (i < LZO_CMP_PAGES) {
 				ring_size = i;

kernel/printk.c

@@ -1172,7 +1172,6 @@ static int __cpuinit console_cpu_notify(struct notifier_block *self,
 	switch (action) {
 	case CPU_ONLINE:
 	case CPU_DEAD:
-	case CPU_DYING:
 	case CPU_DOWN_FAILED:
 	case CPU_UP_CANCELED:
 		console_lock();

kernel/sched/core.c

@@ -692,8 +692,6 @@ int tg_nop(struct task_group *tg, void *data)
 }
 #endif
 
-void update_cpu_load(struct rq *this_rq);
-
 static void set_load_weight(struct task_struct *p)
 {
 	int prio = p->static_prio - MAX_RT_PRIO;
@@ -2620,22 +2618,13 @@ decay_load_missed(unsigned long load, unsigned long missed_updates, int idx)
  * scheduler tick (TICK_NSEC). With tickless idle this will not be called
  * every tick. We fix it up based on jiffies.
  */
-void update_cpu_load(struct rq *this_rq)
+static void __update_cpu_load(struct rq *this_rq, unsigned long this_load,
+			      unsigned long pending_updates)
 {
-	unsigned long this_load = this_rq->load.weight;
-	unsigned long curr_jiffies = jiffies;
-	unsigned long pending_updates;
 	int i, scale;
 
 	this_rq->nr_load_updates++;
 
-	/* Avoid repeated calls on same jiffy, when moving in and out of idle */
-	if (curr_jiffies == this_rq->last_load_update_tick)
-		return;
-
-	pending_updates = curr_jiffies - this_rq->last_load_update_tick;
-	this_rq->last_load_update_tick = curr_jiffies;
-
 	/* Update our load: */
 	this_rq->cpu_load[0] = this_load; /* Fasttrack for idx 0 */
 	for (i = 1, scale = 2; i < CPU_LOAD_IDX_MAX; i++, scale += scale) {
@@ -2660,9 +2649,78 @@ void update_cpu_load(struct rq *this_rq)
 	sched_avg_update(this_rq);
 }
 
+#ifdef CONFIG_NO_HZ
+/*
+ * There is no sane way to deal with nohz on smp when using jiffies because the
+ * cpu doing the jiffies update might drift wrt the cpu doing the jiffy reading
+ * causing off-by-one errors in observed deltas; {0,2} instead of {1,1}.
+ *
+ * Therefore we cannot use the delta approach from the regular tick since that
+ * would seriously skew the load calculation. However we'll make do for those
+ * updates happening while idle (nohz_idle_balance) or coming out of idle
+ * (tick_nohz_idle_exit).
+ *
+ * This means we might still be one tick off for nohz periods.
+ */
+
+/*
+ * Called from nohz_idle_balance() to update the load ratings before doing the
+ * idle balance.
+ */
+void update_idle_cpu_load(struct rq *this_rq)
+{
+	unsigned long curr_jiffies = ACCESS_ONCE(jiffies);
+	unsigned long load = this_rq->load.weight;
+	unsigned long pending_updates;
+
+	/*
+	 * bail if there's load or we're actually up-to-date.
+	 */
+	if (load || curr_jiffies == this_rq->last_load_update_tick)
+		return;
+
+	pending_updates = curr_jiffies - this_rq->last_load_update_tick;
+	this_rq->last_load_update_tick = curr_jiffies;
+
+	__update_cpu_load(this_rq, load, pending_updates);
+}
+
+/*
+ * Called from tick_nohz_idle_exit() -- try and fix up the ticks we missed.
+ */
+void update_cpu_load_nohz(void)
+{
+	struct rq *this_rq = this_rq();
+	unsigned long curr_jiffies = ACCESS_ONCE(jiffies);
+	unsigned long pending_updates;
+
+	if (curr_jiffies == this_rq->last_load_update_tick)
+		return;
+
+	raw_spin_lock(&this_rq->lock);
+	pending_updates = curr_jiffies - this_rq->last_load_update_tick;
+	if (pending_updates) {
+		this_rq->last_load_update_tick = curr_jiffies;
+		/*
+		 * We were idle, this means load 0, the current load might be
+		 * !0 due to remote wakeups and the sort.
+		 */
+		__update_cpu_load(this_rq, 0, pending_updates);
+	}
+	raw_spin_unlock(&this_rq->lock);
+}
+#endif /* CONFIG_NO_HZ */
+
+/*
+ * Called from scheduler_tick()
+ */
 static void update_cpu_load_active(struct rq *this_rq)
 {
-	update_cpu_load(this_rq);
+	/*
+	 * See the mess around update_idle_cpu_load() / update_cpu_load_nohz().
+	 */
+	this_rq->last_load_update_tick = jiffies;
+	__update_cpu_load(this_rq, this_rq->load.weight, 1);
 
 	calc_load_account_active(this_rq);
 }

kernel/sched/fair.c

@@ -5042,7 +5042,7 @@ static void nohz_idle_balance(int this_cpu, enum cpu_idle_type idle)
 
 		raw_spin_lock_irq(&this_rq->lock);
 		update_rq_clock(this_rq);
-		update_cpu_load(this_rq);
+		update_idle_cpu_load(this_rq);
 		raw_spin_unlock_irq(&this_rq->lock);
 
 		rebalance_domains(balance_cpu, CPU_IDLE);

kernel/sched/sched.h

@@ -873,7 +873,7 @@ extern void resched_cpu(int cpu);
 extern struct rt_bandwidth def_rt_bandwidth;
 extern void init_rt_bandwidth(struct rt_bandwidth *rt_b, u64 period, u64 runtime);
 
-extern void update_cpu_load(struct rq *this_rq);
+extern void update_idle_cpu_load(struct rq *this_rq);
 
 #ifdef CONFIG_CGROUP_CPUACCT
 #include <linux/cgroup.h>

kernel/time/tick-sched.c

@@ -582,6 +582,7 @@ void tick_nohz_idle_exit(void)
 	/* Update jiffies first */
 	select_nohz_load_balancer(0);
 	tick_do_update_jiffies64(now);
+	update_cpu_load_nohz();
 
 #ifndef CONFIG_VIRT_CPU_ACCOUNTING
 	/*

kernel/trace/ftrace.c

@@ -222,6 +222,29 @@ static void update_global_ops(void)
 	global_ops.func = func;
 }
 
+static void ftrace_sync(struct work_struct *work)
+{
+	/*
+	 * This function is just a stub to implement a hard force
+	 * of synchronize_sched(). This requires synchronizing
+	 * tasks even in userspace and idle.
+	 *
+	 * Yes, function tracing is rude.
+	 */
+}
+
+static void ftrace_sync_ipi(void *data)
+{
+	/* Probably not needed, but do it anyway */
+	smp_rmb();
+}
+
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+static void update_function_graph_func(void);
+#else
+static inline void update_function_graph_func(void) { }
+#endif
+
 static void update_ftrace_function(void)
 {
 	ftrace_func_t func;
@@ -240,6 +263,8 @@ static void update_ftrace_function(void)
 	else
 		func = ftrace_ops_list_func;
 
+	update_function_graph_func();
+
 #ifdef CONFIG_HAVE_FUNCTION_TRACE_MCOUNT_TEST
 	ftrace_trace_function = func;
 #else
@@ -359,16 +384,6 @@ static int __unregister_ftrace_function(struct ftrace_ops *ops)
 	} else if (ops->flags & FTRACE_OPS_FL_CONTROL) {
 		ret = remove_ftrace_list_ops(&ftrace_control_list,
 					     &control_ops, ops);
-		if (!ret) {
-			/*
-			 * The ftrace_ops is now removed from the list,
-			 * so there'll be no new users. We must ensure
-			 * all current users are done before we free
-			 * the control data.
-			 */
-			synchronize_sched();
-			control_ops_free(ops);
-		}
 	} else
 		ret = remove_ftrace_ops(&ftrace_ops_list, ops);
 
@@ -378,13 +393,6 @@ static int __unregister_ftrace_function(struct ftrace_ops *ops)
 	if (ftrace_enabled)
 		update_ftrace_function();
 
-	/*
-	 * Dynamic ops may be freed, we must make sure that all
-	 * callers are done before leaving this function.
-	 */
-	if (ops->flags & FTRACE_OPS_FL_DYNAMIC)
-		synchronize_sched();
-
 	return 0;
 }
 
@@ -2008,10 +2016,41 @@ static int ftrace_shutdown(struct ftrace_ops *ops, int command)
 		command |= FTRACE_UPDATE_TRACE_FUNC;
 	}
 
-	if (!command || !ftrace_enabled)
+	if (!command || !ftrace_enabled) {
+		/*
+		 * If these are control ops, they still need their
+		 * per_cpu field freed. Since, function tracing is
+		 * not currently active, we can just free them
+		 * without synchronizing all CPUs.
+		 */
+		if (ops->flags & FTRACE_OPS_FL_CONTROL)
+			control_ops_free(ops);
 		return 0;
+	}
 
 	ftrace_run_update_code(command);
+
+	/*
+	 * Dynamic ops may be freed, we must make sure that all
+	 * callers are done before leaving this function.
+	 * The same goes for freeing the per_cpu data of the control
+	 * ops.
+	 *
+	 * Again, normal synchronize_sched() is not good enough.
+	 * We need to do a hard force of sched synchronization.
+	 * This is because we use preempt_disable() to do RCU, but
+	 * the function tracers can be called where RCU is not watching
+	 * (like before user_exit()). We can not rely on the RCU
+	 * infrastructure to do the synchronization, thus we must do it
+	 * ourselves.
+	 */
+	if (ops->flags & (FTRACE_OPS_FL_DYNAMIC | FTRACE_OPS_FL_CONTROL)) {
+		schedule_on_each_cpu(ftrace_sync);
+
+		if (ops->flags & FTRACE_OPS_FL_CONTROL)
+			control_ops_free(ops);
+	}
+
 	return 0;
 }
 
@@ -4404,6 +4443,7 @@ int ftrace_graph_entry_stub(struct ftrace_graph_ent *trace)
 trace_func_graph_ret_t ftrace_graph_return =
 			(trace_func_graph_ret_t)ftrace_stub;
 trace_func_graph_ent_t ftrace_graph_entry = ftrace_graph_entry_stub;
+static trace_func_graph_ent_t __ftrace_graph_entry = ftrace_graph_entry_stub;
 
 /* Try to assign a return stack array on FTRACE_RETSTACK_ALLOC_SIZE tasks. */
 static int alloc_retstack_tasklist(struct ftrace_ret_stack **ret_stack_list)
@@ -4544,6 +4584,30 @@ static struct ftrace_ops fgraph_ops __read_mostly = {
 	.flags		= FTRACE_OPS_FL_GLOBAL,
 };
 
+static int ftrace_graph_entry_test(struct ftrace_graph_ent *trace)
+{
+	if (!ftrace_ops_test(&global_ops, trace->func))
+		return 0;
+	return __ftrace_graph_entry(trace);
+}
+
+/*
+ * The function graph tracer should only trace the functions defined
+ * by set_ftrace_filter and set_ftrace_notrace. If another function
+ * tracer ops is registered, the graph tracer requires testing the
+ * function against the global ops, and not just trace any function
+ * that any ftrace_ops registered.
+ */
+static void update_function_graph_func(void)
+{
+	if (ftrace_ops_list == &ftrace_list_end ||
+	    (ftrace_ops_list == &global_ops &&
+	     global_ops.next == &ftrace_list_end))
+		ftrace_graph_entry = __ftrace_graph_entry;
+	else
+		ftrace_graph_entry = ftrace_graph_entry_test;
+}
+
 int register_ftrace_graph(trace_func_graph_ret_t retfunc,
 			trace_func_graph_ent_t entryfunc)
 {
@@ -4568,7 +4632,16 @@ int register_ftrace_graph(trace_func_graph_ret_t retfunc,
 	}
 
 	ftrace_graph_return = retfunc;
-	ftrace_graph_entry = entryfunc;
+
+	/*
+	 * Update the indirect function to the entryfunc, and the
+	 * function that gets called to the entry_test first. Then
+	 * call the update fgraph entry function to determine if
+	 * the entryfunc should be called directly or not.
+	 */
+	__ftrace_graph_entry = entryfunc;
+	ftrace_graph_entry = ftrace_graph_entry_test;
+	update_function_graph_func();
 
 	ret = ftrace_startup(&fgraph_ops, FTRACE_START_FUNC_RET);
 
@@ -4587,6 +4660,7 @@ void unregister_ftrace_graph(void)
 	ftrace_graph_active--;
 	ftrace_graph_return = (trace_func_graph_ret_t)ftrace_stub;
 	ftrace_graph_entry = ftrace_graph_entry_stub;
+	__ftrace_graph_entry = ftrace_graph_entry_stub;
 	ftrace_shutdown(&fgraph_ops, FTRACE_STOP_FUNC_RET);
 	unregister_pm_notifier(&ftrace_suspend_notifier);
 	unregister_trace_sched_switch(ftrace_graph_probe_sched_switch, NULL);

lib/Makefile

@@ -41,6 +41,7 @@ obj-$(CONFIG_DEBUG_SPINLOCK) += spinlock_debug.o
 lib-$(CONFIG_RWSEM_GENERIC_SPINLOCK) += rwsem-spinlock.o
 lib-$(CONFIG_RWSEM_XCHGADD_ALGORITHM) += rwsem.o
 
+GCOV_PROFILE_hweight.o := n
 CFLAGS_hweight.o = $(subst $(quote),,$(CONFIG_ARCH_HWEIGHT_CFLAGS))
 obj-$(CONFIG_GENERIC_HWEIGHT) += hweight.o
 

lib/vsprintf.c

@@ -926,7 +926,8 @@ char *pointer(const char *fmt, char *buf, char *end, void *ptr,
 		 * %pK cannot be used in IRQ context because its test
 		 * for CAP_SYSLOG would be meaningless.
 		 */
-		if (in_irq() || in_serving_softirq() || in_nmi()) {
+		if (kptr_restrict && (in_irq() || in_serving_softirq() ||
+				      in_nmi())) {
 			if (spec.field_width == -1)
 				spec.field_width = 2 * sizeof(void *);
 			return string(buf, end, "pK-error", spec);

mm/internal.h

@@ -309,3 +309,5 @@ extern u64 hwpoison_filter_flags_mask;
 extern u64 hwpoison_filter_flags_value;
 extern u64 hwpoison_filter_memcg;
 extern u32 hwpoison_filter_enable;
+
+extern void set_pageblock_order(void);

mm/page-writeback.c

@@ -1993,11 +1993,12 @@ int __set_page_dirty_nobuffers(struct page *page)
 	if (!TestSetPageDirty(page)) {
 		struct address_space *mapping = page_mapping(page);
 		struct address_space *mapping2;
+		unsigned long flags;
 
 		if (!mapping)
 			return 1;
 
-		spin_lock_irq(&mapping->tree_lock);
+		spin_lock_irqsave(&mapping->tree_lock, flags);
 		mapping2 = page_mapping(page);
 		if (mapping2) { /* Race with truncate? */
 			BUG_ON(mapping2 != mapping);
@@ -2006,7 +2007,7 @@ int __set_page_dirty_nobuffers(struct page *page)
 			radix_tree_tag_set(&mapping->page_tree,
 				page_index(page), PAGECACHE_TAG_DIRTY);
 		}
-		spin_unlock_irq(&mapping->tree_lock);
+		spin_unlock_irqrestore(&mapping->tree_lock, flags);
 		if (mapping->host) {
 			/* !PageAnon && !swapper_space */
 			__mark_inode_dirty(mapping->host, I_DIRTY_PAGES);

mm/page_alloc.c

@@ -4254,25 +4254,24 @@ static inline void setup_usemap(struct pglist_data *pgdat, struct zone *zone,
 
 #ifdef CONFIG_HUGETLB_PAGE_SIZE_VARIABLE
 
-/* Return a sensible default order for the pageblock size. */
-static inline int pageblock_default_order(void)
-{
-	if (HPAGE_SHIFT > PAGE_SHIFT)
-		return HUGETLB_PAGE_ORDER;
-
-	return MAX_ORDER-1;
-}
-
 /* Initialise the number of pages represented by NR_PAGEBLOCK_BITS */
-static inline void __init set_pageblock_order(unsigned int order)
+void __init set_pageblock_order(void)
 {
+	unsigned int order;
+
 	/* Check that pageblock_nr_pages has not already been setup */
 	if (pageblock_order)
 		return;
 
+	if (HPAGE_SHIFT > PAGE_SHIFT)
+		order = HUGETLB_PAGE_ORDER;
+	else
+		order = MAX_ORDER - 1;
+
 	/*
 	 * Assume the largest contiguous order of interest is a huge page.
-	 * This value may be variable depending on boot parameters on IA64
+	 * This value may be variable depending on boot parameters on IA64 and
+	 * powerpc.
 	 */
 	pageblock_order = order;
 }
@@ -4280,15 +4279,13 @@ static inline void __init set_pageblock_order(unsigned int order)
 
 /*
  * When CONFIG_HUGETLB_PAGE_SIZE_VARIABLE is not set, set_pageblock_order()
- * and pageblock_default_order() are unused as pageblock_order is set
- * at compile-time. See include/linux/pageblock-flags.h for the values of
- * pageblock_order based on the kernel config
+ * is unused as pageblock_order is set at compile-time. See
+ * include/linux/pageblock-flags.h for the values of pageblock_order based on
+ * the kernel config
  */
-static inline int pageblock_default_order(unsigned int order)
+void __init set_pageblock_order(void)
 {
-	return MAX_ORDER-1;
 }
-#define set_pageblock_order(x)	do {} while (0)
 
 #endif /* CONFIG_HUGETLB_PAGE_SIZE_VARIABLE */
 
@@ -4376,7 +4373,7 @@ static void __paginginit free_area_init_core(struct pglist_data *pgdat,
 		if (!size)
 			continue;
 
-		set_pageblock_order(pageblock_default_order());
+		set_pageblock_order();
 		setup_usemap(pgdat, zone, zone_start_pfn, size);
 		ret = init_currently_empty_zone(zone, zone_start_pfn,
 						size, MEMMAP_EARLY);

mm/sparse.c

@@ -486,6 +486,9 @@ void __init sparse_init(void)
 	struct page **map_map;
 #endif
 
+	/* Setup pageblock_order for HUGETLB_PAGE_SIZE_VARIABLE */
+	set_pageblock_order();
+
 	/*
 	 * map is using big page (aka 2M in x86 64 bit)
 	 * usemap is less one page (aka 24 bytes)

security/selinux/ss/services.c

@@ -1229,6 +1229,10 @@ static int security_context_to_sid_core(const char *scontext, u32 scontext_len,
 	struct context context;
 	int rc = 0;
 
+	/* An empty security context is never valid. */
+	if (!scontext_len)
+		return -EINVAL;
+
 	if (!ss_initialized) {
 		int i;
 

virt/kvm/irq_comm.c

@@ -318,6 +318,7 @@ static int setup_routing_entry(struct kvm_irq_routing_table *rt,
 	 */
 	hlist_for_each_entry(ei, n, &rt->map[ue->gsi], link)
 		if (ei->type == KVM_IRQ_ROUTING_MSI ||
+		    ue->type == KVM_IRQ_ROUTING_MSI ||
 		    ue->u.irqchip.irqchip == ei->irqchip.irqchip)
 			return r;