Merge commit 'v2.6.28-rc2' into tracing/urgent

64 files changed, 4014 insertions, 273 deletions

diff --git a/include/linux/acpi.h b/include/linux/acpi.h
index 702f79dad16a..fd6a452b0ceb 100644
--- a/include/linux/acpi.h
+++ b/include/linux/acpi.h
@@ -94,18 +94,10 @@ int acpi_parse_mcfg (struct acpi_table_header *header);
 void acpi_table_print_madt_entry (struct acpi_subtable_header *madt);
 
 /* the following four functions are architecture-dependent */
-#ifdef CONFIG_HAVE_ARCH_PARSE_SRAT
-#define NR_NODE_MEMBLKS MAX_NUMNODES
-#define acpi_numa_slit_init(slit) do {} while (0)
-#define acpi_numa_processor_affinity_init(pa) do {} while (0)
-#define acpi_numa_memory_affinity_init(ma) do {} while (0)
-#define acpi_numa_arch_fixup() do {} while (0)
-#else
 void acpi_numa_slit_init (struct acpi_table_slit *slit);
 void acpi_numa_processor_affinity_init (struct acpi_srat_cpu_affinity *pa);
 void acpi_numa_memory_affinity_init (struct acpi_srat_mem_affinity *ma);
 void acpi_numa_arch_fixup(void);
-#endif
 
 #ifdef CONFIG_ACPI_HOTPLUG_CPU
 /* Arch dependent functions for cpu hotplug support */
diff --git a/include/linux/bitmap.h b/include/linux/bitmap.h
index 1abfe664c444..a08c33a26ca9 100644
--- a/include/linux/bitmap.h
+++ b/include/linux/bitmap.h
@@ -129,6 +129,7 @@ extern void bitmap_fold(unsigned long *dst, const unsigned long *orig,
 extern int bitmap_find_free_region(unsigned long *bitmap, int bits, int order);
 extern void bitmap_release_region(unsigned long *bitmap, int pos, int order);
 extern int bitmap_allocate_region(unsigned long *bitmap, int pos, int order);
+extern void bitmap_copy_le(void *dst, const unsigned long *src, int nbits);
 
 #define BITMAP_LAST_WORD_MASK(nbits)					\
 (									\
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index b4fe68fe3a57..a135256b272c 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -717,10 +717,10 @@ extern void blk_plug_device(struct request_queue *);
 extern void blk_plug_device_unlocked(struct request_queue *);
 extern int blk_remove_plug(struct request_queue *);
 extern void blk_recount_segments(struct request_queue *, struct bio *);
-extern int scsi_cmd_ioctl(struct file *, struct request_queue *,
-			  struct gendisk *, unsigned int, void __user *);
-extern int sg_scsi_ioctl(struct file *, struct request_queue *,
-		struct gendisk *, struct scsi_ioctl_command __user *);
+extern int scsi_cmd_ioctl(struct request_queue *, struct gendisk *, fmode_t,
+			  unsigned int, void __user *);
+extern int sg_scsi_ioctl(struct request_queue *, struct gendisk *, fmode_t,
+			 struct scsi_ioctl_command __user *);
 
 /*
  * Temporary export, until SCSI gets fixed up.
@@ -910,7 +910,8 @@ static inline int sb_issue_discard(struct super_block *sb,
 * command filter functions
 */
 extern int blk_verify_command(struct blk_cmd_filter *filter,
-			      unsigned char *cmd, int has_write_perm);
+			      unsigned char *cmd, fmode_t has_write_perm);
+extern void blk_unregister_filter(struct gendisk *disk);
 extern void blk_set_cmd_filter_defaults(struct blk_cmd_filter *filter);
 
 #define MAX_PHYS_SEGMENTS 128
@@ -1056,6 +1057,22 @@ static inline int blk_integrity_rq(struct request *rq)
 
 #endif /* CONFIG_BLK_DEV_INTEGRITY */
 
+struct block_device_operations {
+	int (*open) (struct block_device *, fmode_t);
+	int (*release) (struct gendisk *, fmode_t);
+	int (*locked_ioctl) (struct block_device *, fmode_t, unsigned, unsigned long);
+	int (*ioctl) (struct block_device *, fmode_t, unsigned, unsigned long);
+	int (*compat_ioctl) (struct block_device *, fmode_t, unsigned, unsigned long);
+	int (*direct_access) (struct block_device *, sector_t,
+						void **, unsigned long *);
+	int (*media_changed) (struct gendisk *);
+	int (*revalidate_disk) (struct gendisk *);
+	int (*getgeo)(struct block_device *, struct hd_geometry *);
+	struct module *owner;
+};
+
+extern int __blkdev_driver_ioctl(struct block_device *, fmode_t, unsigned int,
+				 unsigned long);
 #else /* CONFIG_BLOCK */
 /*
  * stubs for when the block layer is configured out
diff --git a/include/linux/cdrom.h b/include/linux/cdrom.h
index 5db265ea60f6..0b49e08d3cb0 100644
--- a/include/linux/cdrom.h
+++ b/include/linux/cdrom.h
@@ -987,11 +987,11 @@ struct cdrom_device_ops {
 };
 
 /* the general block_device operations structure: */
-extern int cdrom_open(struct cdrom_device_info *cdi, struct inode *ip,
-			struct file *fp);
-extern int cdrom_release(struct cdrom_device_info *cdi, struct file *fp);
-extern int cdrom_ioctl(struct file *file, struct cdrom_device_info *cdi,
-		struct inode *ip, unsigned int cmd, unsigned long arg);
+extern int cdrom_open(struct cdrom_device_info *cdi, struct block_device *bdev,
+			fmode_t mode);
+extern void cdrom_release(struct cdrom_device_info *cdi, fmode_t mode);
+extern int cdrom_ioctl(struct cdrom_device_info *cdi, struct block_device *bdev,
+		       fmode_t mode, unsigned int cmd, unsigned long arg);
 extern int cdrom_media_changed(struct cdrom_device_info *);
 
 extern int register_cdrom(struct cdrom_device_info *cdi);
diff --git a/include/linux/crash_dump.h b/include/linux/crash_dump.h
index 0acf3b737e2e..2dac064d8359 100644
--- a/include/linux/crash_dump.h
+++ b/include/linux/crash_dump.h
@@ -14,8 +14,6 @@ extern unsigned long long elfcorehdr_addr;
 
 extern ssize_t copy_oldmem_page(unsigned long, char *, size_t,
 						unsigned long, int);
-extern const struct file_operations proc_vmcore_operations;
-extern struct proc_dir_entry *proc_vmcore;
 
 /* Architecture code defines this if there are other possible ELF
  * machine types, e.g. on bi-arch capable hardware. */
diff --git a/include/linux/dcache.h b/include/linux/dcache.h
index efba1de629ac..a37359d0bad1 100644
--- a/include/linux/dcache.h
+++ b/include/linux/dcache.h
@@ -228,9 +228,9 @@ extern void d_delete(struct dentry *);
 
 /* allocate/de-allocate */
 extern struct dentry * d_alloc(struct dentry *, const struct qstr *);
-extern struct dentry * d_alloc_anon(struct inode *);
 extern struct dentry * d_splice_alias(struct inode *, struct dentry *);
 extern struct dentry * d_add_ci(struct dentry *, struct inode *, struct qstr *);
+extern struct dentry * d_obtain_alias(struct inode *);
 extern void shrink_dcache_sb(struct super_block *);
 extern void shrink_dcache_parent(struct dentry *);
 extern void shrink_dcache_for_umount(struct super_block *);
@@ -287,6 +287,7 @@ static inline struct dentry *d_add_unique(struct dentry *entry, struct inode *in
 
 /* used for rename() and baskets */
 extern void d_move(struct dentry *, struct dentry *);
+extern struct dentry *d_ancestor(struct dentry *, struct dentry *);
 
 /* appendix may either be NULL or be used for transname suffixes */
 extern struct dentry * d_lookup(struct dentry *, struct qstr *);
diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h
index 08d783592b73..c17fd334e574 100644
--- a/include/linux/device-mapper.h
+++ b/include/linux/device-mapper.h
@@ -69,8 +69,7 @@ typedef int (*dm_status_fn) (struct dm_target *ti, status_type_t status_type,
 
 typedef int (*dm_message_fn) (struct dm_target *ti, unsigned argc, char **argv);
 
-typedef int (*dm_ioctl_fn) (struct dm_target *ti, struct inode *inode,
-			    struct file *filp, unsigned int cmd,
+typedef int (*dm_ioctl_fn) (struct dm_target *ti, unsigned int cmd,
 			    unsigned long arg);
 
 typedef int (*dm_merge_fn) (struct dm_target *ti, struct bvec_merge_data *bvm,
@@ -85,7 +84,7 @@ void dm_set_device_limits(struct dm_target *ti, struct block_device *bdev);
 
 struct dm_dev {
 	struct block_device *bdev;
-	int mode;
+	fmode_t mode;
 	char name[16];
 };
 
@@ -95,7 +94,7 @@ struct dm_dev {
  * FIXME: too many arguments.
  */
 int dm_get_device(struct dm_target *ti, const char *path, sector_t start,
-		  sector_t len, int mode, struct dm_dev **result);
+		  sector_t len, fmode_t mode, struct dm_dev **result);
 void dm_put_device(struct dm_target *ti, struct dm_dev *d);
 
 /*
@@ -223,7 +222,7 @@ int dm_set_geometry(struct mapped_device *md, struct hd_geometry *geo);
 /*
  * First create an empty table.
  */
-int dm_table_create(struct dm_table **result, int mode,
+int dm_table_create(struct dm_table **result, fmode_t mode,
 		    unsigned num_targets, struct mapped_device *md);
 
 /*
@@ -254,7 +253,7 @@ void dm_table_put(struct dm_table *t);
  */
 sector_t dm_table_get_size(struct dm_table *t);
 unsigned int dm_table_get_num_targets(struct dm_table *t);
-int dm_table_get_mode(struct dm_table *t);
+fmode_t dm_table_get_mode(struct dm_table *t);
 struct mapped_device *dm_table_get_md(struct dm_table *t);
 
 /*
@@ -354,6 +353,9 @@ void *dm_vcalloc(unsigned long nmemb, unsigned long elem_size);
  */
 #define dm_round_up(n, sz) (dm_div_up((n), (sz)) * (sz))
 
+#define dm_array_too_big(fixed, obj, num) \
+	((num) > (UINT_MAX - (fixed)) / (obj))
+
 static inline sector_t to_sector(unsigned long n)
 {
 	return (n >> SECTOR_SHIFT);
diff --git a/include/linux/device.h b/include/linux/device.h
index 987f5912720a..1a3686d15f98 100644
--- a/include/linux/device.h
+++ b/include/linux/device.h
@@ -450,7 +450,7 @@ static inline void set_dev_node(struct device *dev, int node)
 }
 #endif
 
-static inline void *dev_get_drvdata(struct device *dev)
+static inline void *dev_get_drvdata(const struct device *dev)
 {
 	return dev->driver_data;
 }
diff --git a/include/linux/dm-region-hash.h b/include/linux/dm-region-hash.h
new file mode 100644
index 000000000000..a9e652a41373
--- /dev/null
+++ b/include/linux/dm-region-hash.h
@@ -0,0 +1,104 @@
+/*
+ * Copyright (C) 2003 Sistina Software Limited.
+ * Copyright (C) 2004-2008 Red Hat, Inc. All rights reserved.
+ *
+ * Device-Mapper dirty region hash interface.
+ *
+ * This file is released under the GPL.
+ */
+
+#ifndef DM_REGION_HASH_H
+#define DM_REGION_HASH_H
+
+#include <linux/dm-dirty-log.h>
+
+/*-----------------------------------------------------------------
+ * Region hash
+ *----------------------------------------------------------------*/
+struct dm_region_hash;
+struct dm_region;
+
+/*
+ * States a region can have.
+ */
+enum dm_rh_region_states {
+	DM_RH_CLEAN	 = 0x01,	/* No writes in flight. */
+	DM_RH_DIRTY	 = 0x02,	/* Writes in flight. */
+	DM_RH_NOSYNC	 = 0x04,	/* Out of sync. */
+	DM_RH_RECOVERING = 0x08,	/* Under resynchronization. */
+};
+
+/*
+ * Region hash create/destroy.
+ */
+struct bio_list;
+struct dm_region_hash *dm_region_hash_create(
+		void *context, void (*dispatch_bios)(void *context,
+						     struct bio_list *bios),
+		void (*wakeup_workers)(void *context),
+		void (*wakeup_all_recovery_waiters)(void *context),
+		sector_t target_begin, unsigned max_recovery,
+		struct dm_dirty_log *log, uint32_t region_size,
+		region_t nr_regions);
+void dm_region_hash_destroy(struct dm_region_hash *rh);
+
+struct dm_dirty_log *dm_rh_dirty_log(struct dm_region_hash *rh);
+
+/*
+ * Conversion functions.
+ */
+region_t dm_rh_bio_to_region(struct dm_region_hash *rh, struct bio *bio);
+sector_t dm_rh_region_to_sector(struct dm_region_hash *rh, region_t region);
+void *dm_rh_region_context(struct dm_region *reg);
+
+/*
+ * Get region size and key (ie. number of the region).
+ */
+sector_t dm_rh_get_region_size(struct dm_region_hash *rh);
+region_t dm_rh_get_region_key(struct dm_region *reg);
+
+/*
+ * Get/set/update region state (and dirty log).
+ *
+ */
+int dm_rh_get_state(struct dm_region_hash *rh, region_t region, int may_block);
+void dm_rh_set_state(struct dm_region_hash *rh, region_t region,
+		     enum dm_rh_region_states state, int may_block);
+
+/* Non-zero errors_handled leaves the state of the region NOSYNC */
+void dm_rh_update_states(struct dm_region_hash *rh, int errors_handled);
+
+/* Flush the region hash and dirty log. */
+int dm_rh_flush(struct dm_region_hash *rh);
+
+/* Inc/dec pending count on regions. */
+void dm_rh_inc_pending(struct dm_region_hash *rh, struct bio_list *bios);
+void dm_rh_dec(struct dm_region_hash *rh, region_t region);
+
+/* Delay bios on regions. */
+void dm_rh_delay(struct dm_region_hash *rh, struct bio *bio);
+
+void dm_rh_mark_nosync(struct dm_region_hash *rh,
+		       struct bio *bio, unsigned done, int error);
+
+/*
+ * Region recovery control.
+ */
+
+/* Prepare some regions for recovery by starting to quiesce them. */
+void dm_rh_recovery_prepare(struct dm_region_hash *rh);
+
+/* Try fetching a quiesced region for recovery. */
+struct dm_region *dm_rh_recovery_start(struct dm_region_hash *rh);
+
+/* Report recovery end on a region. */
+void dm_rh_recovery_end(struct dm_region *reg, int error);
+
+/* Returns number of regions with recovery work outstanding. */
+int dm_rh_recovery_in_flight(struct dm_region_hash *rh);
+
+/* Start/stop recovery. */
+void dm_rh_start_recovery(struct dm_region_hash *rh);
+void dm_rh_stop_recovery(struct dm_region_hash *rh);
+
+#endif /* DM_REGION_HASH_H */
diff --git a/include/linux/dma_remapping.h b/include/linux/dma_remapping.h
index bff5c65f81dc..952df39c989d 100644
--- a/include/linux/dma_remapping.h
+++ b/include/linux/dma_remapping.h
@@ -2,15 +2,14 @@
 #define _DMA_REMAPPING_H
 
 /*
- * We need a fixed PAGE_SIZE of 4K irrespective of
- * arch PAGE_SIZE for IOMMU page tables.
+ * VT-d hardware uses 4KiB page size regardless of host page size.
  */
-#define PAGE_SHIFT_4K		(12)
-#define PAGE_SIZE_4K		(1UL << PAGE_SHIFT_4K)
-#define PAGE_MASK_4K		(((u64)-1) << PAGE_SHIFT_4K)
-#define PAGE_ALIGN_4K(addr)	(((addr) + PAGE_SIZE_4K - 1) & PAGE_MASK_4K)
+#define VTD_PAGE_SHIFT		(12)
+#define VTD_PAGE_SIZE		(1UL << VTD_PAGE_SHIFT)
+#define VTD_PAGE_MASK		(((u64)-1) << VTD_PAGE_SHIFT)
+#define VTD_PAGE_ALIGN(addr)	(((addr) + VTD_PAGE_SIZE - 1) & VTD_PAGE_MASK)
 
-#define IOVA_PFN(addr)		((addr) >> PAGE_SHIFT_4K)
+#define IOVA_PFN(addr)		((addr) >> PAGE_SHIFT)
 #define DMA_32BIT_PFN		IOVA_PFN(DMA_32BIT_MASK)
 #define DMA_64BIT_PFN		IOVA_PFN(DMA_64BIT_MASK)
 
@@ -25,7 +24,7 @@ struct root_entry {
 	u64	val;
 	u64	rsvd1;
 };
-#define ROOT_ENTRY_NR (PAGE_SIZE_4K/sizeof(struct root_entry))
+#define ROOT_ENTRY_NR (VTD_PAGE_SIZE/sizeof(struct root_entry))
 static inline bool root_present(struct root_entry *root)
 {
 	return (root->val & 1);
@@ -36,7 +35,7 @@ static inline void set_root_present(struct root_entry *root)
 }
 static inline void set_root_value(struct root_entry *root, unsigned long value)
 {
-	root->val |= value & PAGE_MASK_4K;
+	root->val |= value & VTD_PAGE_MASK;
 }
 
 struct context_entry;
@@ -45,7 +44,7 @@ get_context_addr_from_root(struct root_entry *root)
 {
 	return (struct context_entry *)
 		(root_present(root)?phys_to_virt(
-		root->val & PAGE_MASK_4K):
+		root->val & VTD_PAGE_MASK) :
 		NULL);
 }
 
@@ -67,7 +66,7 @@ struct context_entry {
 #define context_present(c) ((c).lo & 1)
 #define context_fault_disable(c) (((c).lo >> 1) & 1)
 #define context_translation_type(c) (((c).lo >> 2) & 3)
-#define context_address_root(c) ((c).lo & PAGE_MASK_4K)
+#define context_address_root(c) ((c).lo & VTD_PAGE_MASK)
 #define context_address_width(c) ((c).hi &  7)
 #define context_domain_id(c) (((c).hi >> 8) & ((1 << 16) - 1))
 
@@ -81,7 +80,7 @@ struct context_entry {
 	} while (0)
 #define CONTEXT_TT_MULTI_LEVEL 0
 #define context_set_address_root(c, val) \
-	do {(c).lo |= (val) & PAGE_MASK_4K;} while (0)
+	do {(c).lo |= (val) & VTD_PAGE_MASK; } while (0)
 #define context_set_address_width(c, val) do {(c).hi |= (val) & 7;} while (0)
 #define context_set_domain_id(c, val) \
 	do {(c).hi |= ((val) & ((1 << 16) - 1)) << 8;} while (0)
@@ -107,9 +106,9 @@ struct dma_pte {
 #define dma_set_pte_writable(p) do {(p).val |= DMA_PTE_WRITE;} while (0)
 #define dma_set_pte_prot(p, prot) \
 		do {(p).val = ((p).val & ~3) | ((prot) & 3); } while (0)
-#define dma_pte_addr(p) ((p).val & PAGE_MASK_4K)
+#define dma_pte_addr(p) ((p).val & VTD_PAGE_MASK)
 #define dma_set_pte_addr(p, addr) do {\
-		(p).val |= ((addr) & PAGE_MASK_4K); } while (0)
+		(p).val |= ((addr) & VTD_PAGE_MASK); } while (0)
 #define dma_pte_present(p) (((p).val & 3) != 0)
 
 struct intel_iommu;
diff --git a/include/linux/file.h b/include/linux/file.h
index a20259e248a5..335a0a5c316e 100644
--- a/include/linux/file.h
+++ b/include/linux/file.h
@@ -19,10 +19,10 @@ struct file_operations;
 struct vfsmount;
 struct dentry;
 extern int init_file(struct file *, struct vfsmount *mnt,
-		struct dentry *dentry, mode_t mode,
+		struct dentry *dentry, fmode_t mode,
 		const struct file_operations *fop);
 extern struct file *alloc_file(struct vfsmount *, struct dentry *dentry,
-		mode_t mode, const struct file_operations *fop);
+		fmode_t mode, const struct file_operations *fop);
 
 static inline void fput_light(struct file *file, int fput_needed)
 {
diff --git a/include/linux/fs.h b/include/linux/fs.h
index a6a625be13fc..5b248d61430c 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -63,18 +63,23 @@ extern int dir_notify_enable;
 #define MAY_ACCESS 16
 #define MAY_OPEN 32
 
-#define FMODE_READ 1
-#define FMODE_WRITE 2
+#define FMODE_READ ((__force fmode_t)1)
+#define FMODE_WRITE ((__force fmode_t)2)
 
 /* Internal kernel extensions */
-#define FMODE_LSEEK	4
-#define FMODE_PREAD	8
+#define FMODE_LSEEK	((__force fmode_t)4)
+#define FMODE_PREAD	((__force fmode_t)8)
 #define FMODE_PWRITE	FMODE_PREAD	/* These go hand in hand */
 
 /* File is being opened for execution. Primary users of this flag are
    distributed filesystems that can use it to achieve correct ETXTBUSY
    behavior for cross-node execution/opening_for_writing of files */
-#define FMODE_EXEC	16
+#define FMODE_EXEC	((__force fmode_t)16)
+
+#define FMODE_NDELAY	((__force fmode_t)32)
+#define FMODE_EXCL	((__force fmode_t)64)
+#define FMODE_WRITE_IOCTL	((__force fmode_t)128)
+#define FMODE_NDELAY_NOW	((__force fmode_t)256)
 
 #define RW_MASK		1
 #define RWA_MASK	2
@@ -136,7 +141,7 @@ extern int dir_notify_enable;
 /*
  * Superblock flags that can be altered by MS_REMOUNT
  */
-#define MS_RMT_MASK	(MS_RDONLY|MS_SYNCHRONOUS|MS_MANDLOCK)
+#define MS_RMT_MASK	(MS_RDONLY|MS_SYNCHRONOUS|MS_MANDLOCK|MS_I_VERSION)
 
 /*
  * Old magic mount flag and mask
@@ -825,7 +830,7 @@ struct file {
 	const struct file_operations	*f_op;
 	atomic_long_t		f_count;
 	unsigned int 		f_flags;
-	mode_t			f_mode;
+	fmode_t			f_mode;
 	loff_t			f_pos;
 	struct fown_struct	f_owner;
 	unsigned int		f_uid, f_gid;
@@ -1037,7 +1042,6 @@ extern int vfs_setlease(struct file *, long, struct file_lock **);
 extern int lease_modify(struct file_lock **, int);
 extern int lock_may_read(struct inode *, loff_t start, unsigned long count);
 extern int lock_may_write(struct inode *, loff_t start, unsigned long count);
-extern struct seq_operations locks_seq_operations;
 #else /* !CONFIG_FILE_LOCKING */
 #define fcntl_getlk(a, b) ({ -EINVAL; })
 #define fcntl_setlk(a, b, c, d) ({ -EACCES; })
@@ -1152,6 +1156,7 @@ struct super_block {
 	char s_id[32];				/* Informational name */
 
 	void 			*s_fs_info;	/* Filesystem private info */
+	fmode_t			s_mode;
 
 	/*
 	 * The next field is for VFS *only*. No filesystems have any business
@@ -1266,20 +1271,7 @@ int generic_osync_inode(struct inode *, struct address_space *, int);
  * to have different dirent layouts depending on the binary type