Merge branch 'merge' of git://git.secretlab.ca/git/linux-2.6 into merge

80 files changed, 2404 insertions, 566 deletions

diff --git a/include/linux/ata.h b/include/linux/ata.h
index 6617c9f8f2ca..cb79b7a208e1 100644
--- a/include/linux/ata.h
+++ b/include/linux/ata.h
@@ -29,6 +29,8 @@
 #ifndef __LINUX_ATA_H__
 #define __LINUX_ATA_H__
 
+#include <linux/kernel.h>
+#include <linux/string.h>
 #include <linux/types.h>
 #include <asm/byteorder.h>
 
@@ -91,6 +93,7 @@ enum {
 	ATA_ID_CFA_POWER	= 160,
 	ATA_ID_CFA_KEY_MGMT	= 162,
 	ATA_ID_CFA_MODES	= 163,
+	ATA_ID_DATA_SET_MGMT	= 169,
 	ATA_ID_ROT_SPEED	= 217,
 	ATA_ID_PIO4		= (1 << 1),
 
@@ -248,6 +251,7 @@ enum {
 	ATA_CMD_SMART		= 0xB0,
 	ATA_CMD_MEDIA_LOCK	= 0xDE,
 	ATA_CMD_MEDIA_UNLOCK	= 0xDF,
+	ATA_CMD_DSM		= 0x06,
 	/* marked obsolete in the ATA/ATAPI-7 spec */
 	ATA_CMD_RESTORE		= 0x10,
 
@@ -321,6 +325,9 @@ enum {
 	ATA_SMART_READ_VALUES	= 0xD0,
 	ATA_SMART_READ_THRESHOLDS = 0xD1,
 
+	/* feature values for Data Set Management */
+	ATA_DSM_TRIM		= 0x01,
+
 	/* password used in LBA Mid / LBA High for executing SMART commands */
 	ATA_SMART_LBAM_PASS	= 0x4F,
 	ATA_SMART_LBAH_PASS	= 0xC2,
@@ -723,6 +730,14 @@ static inline int ata_id_has_unload(const u16 *id)
 	return 0;
 }
 
+static inline int ata_id_has_trim(const u16 *id)
+{
+	if (ata_id_major_version(id) >= 7 &&
+	    (id[ATA_ID_DATA_SET_MGMT] & 1))
+		return 1;
+	return 0;
+}
+
 static inline int ata_id_current_chs_valid(const u16 *id)
 {
 	/* For ATA-1 devices, if the INITIALIZE DEVICE PARAMETERS command
@@ -863,6 +878,32 @@ static inline void ata_id_to_hd_driveid(u16 *id)
 #endif
 }
 
+/*
+ * Write up to 'max' LBA Range Entries to the buffer that will cover the
+ * extent from sector to sector + count.  This is used for TRIM and for
+ * ADD LBA(S) TO NV CACHE PINNED SET.
+ */
+static inline unsigned ata_set_lba_range_entries(void *_buffer, unsigned max,
+						u64 sector, unsigned long count)
+{
+	__le64 *buffer = _buffer;
+	unsigned i = 0;
+
+	while (i < max) {
+		u64 entry = sector |
+			((u64)(count > 0xffff ? 0xffff : count) << 48);
+		buffer[i++] = __cpu_to_le64(entry);
+		if (count <= 0xffff)
+			break;
+		count -= 0xffff;
+		sector += 0xffff;
+	}
+
+	max = ALIGN(i * 8, 512);
+	memset(buffer + i, 0, max - i * 8);
+	return max;
+}
+
 static inline int is_multi_taskfile(struct ata_taskfile *tf)
 {
 	return (tf->command == ATA_CMD_READ_MULTI) ||
diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h
index bee52abb8a4d..0ec2c594868e 100644
--- a/include/linux/backing-dev.h
+++ b/include/linux/backing-dev.h
@@ -24,8 +24,8 @@ struct dentry;
  */
 enum bdi_state {
 	BDI_pdflush,		/* A pdflush thread is working this device */
-	BDI_write_congested,	/* The write queue is getting full */
-	BDI_read_congested,	/* The read queue is getting full */
+	BDI_async_congested,	/* The async (write) queue is getting full */
+	BDI_sync_congested,	/* The sync queue is getting full */
 	BDI_unused,		/* Available bits start here */
 };
 
@@ -215,18 +215,18 @@ static inline int bdi_congested(struct backing_dev_info *bdi, int bdi_bits)
 
 static inline int bdi_read_congested(struct backing_dev_info *bdi)
 {
-	return bdi_congested(bdi, 1 << BDI_read_congested);
+	return bdi_congested(bdi, 1 << BDI_sync_congested);
 }
 
 static inline int bdi_write_congested(struct backing_dev_info *bdi)
 {
-	return bdi_congested(bdi, 1 << BDI_write_congested);
+	return bdi_congested(bdi, 1 << BDI_async_congested);
 }
 
 static inline int bdi_rw_congested(struct backing_dev_info *bdi)
 {
-	return bdi_congested(bdi, (1 << BDI_read_congested)|
-				  (1 << BDI_write_congested));
+	return bdi_congested(bdi, (1 << BDI_sync_congested) |
+				  (1 << BDI_async_congested));
 }
 
 void clear_bdi_congested(struct backing_dev_info *bdi, int rw);
diff --git a/include/linux/bio.h b/include/linux/bio.h
index b05b1d4d17d2..b900d2c67d29 100644
--- a/include/linux/bio.h
+++ b/include/linux/bio.h
@@ -145,20 +145,21 @@ struct bio {
  * bit 2 -- barrier
  *	Insert a serialization point in the IO queue, forcing previously
  *	submitted IO to be completed before this one is issued.
- * bit 3 -- synchronous I/O hint: the block layer will unplug immediately
- *	Note that this does NOT indicate that the IO itself is sync, just
- *	that the block layer will not postpone issue of this IO by plugging.
- * bit 4 -- metadata request
+ * bit 3 -- synchronous I/O hint.
+ * bit 4 -- Unplug the device immediately after submitting this bio.
+ * bit 5 -- metadata request
  *	Used for tracing to differentiate metadata and data IO. May also
  *	get some preferential treatment in the IO scheduler
- * bit 5 -- discard sectors
+ * bit 6 -- discard sectors
  *	Informs the lower level device that this range of sectors is no longer
  *	used by the file system and may thus be freed by the device. Used
  *	for flash based storage.
- * bit 6 -- fail fast device errors
- * bit 7 -- fail fast transport errors
- * bit 8 -- fail fast driver errors
+ * bit 7 -- fail fast device errors
+ * bit 8 -- fail fast transport errors
+ * bit 9 -- fail fast driver errors
  *	Don't want driver retries for any fast fail whatever the reason.
+ * bit 10 -- Tell the IO scheduler not to wait for more requests after this
+	one has been submitted, even if it is a SYNC request.
  */
 #define BIO_RW		0	/* Must match RW in req flags (blkdev.h) */
 #define BIO_RW_AHEAD	1	/* Must match FAILFAST in req flags */
@@ -170,6 +171,7 @@ struct bio {
 #define BIO_RW_FAILFAST_DEV		7
 #define BIO_RW_FAILFAST_TRANSPORT	8
 #define BIO_RW_FAILFAST_DRIVER		9
+#define BIO_RW_NOIDLE	10
 
 #define bio_rw_flagged(bio, flag)	((bio)->bi_rw & (1 << (flag)))
 
@@ -188,6 +190,7 @@ struct bio {
 #define bio_rw_ahead(bio)	bio_rw_flagged(bio, BIO_RW_AHEAD)
 #define bio_rw_meta(bio)	bio_rw_flagged(bio, BIO_RW_META)
 #define bio_discard(bio)	bio_rw_flagged(bio, BIO_RW_DISCARD)
+#define bio_noidle(bio)		bio_rw_flagged(bio, BIO_RW_NOIDLE)
 
 /*
  * upper 16 bits of bi_rw define the io priority of this bio
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 465d6babc847..ba54c834a590 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -38,6 +38,10 @@ struct request;
 typedef void (rq_end_io_fn)(struct request *, int);
 
 struct request_list {
+	/*
+	 * count[], starved[], and wait[] are indexed by
+	 * BLK_RW_SYNC/BLK_RW_ASYNC
+	 */
 	int count[2];
 	int starved[2];
 	int elvpriv;
@@ -66,6 +70,11 @@ enum rq_cmd_type_bits {
 	REQ_TYPE_ATA_PC,
 };
 
+enum {
+	BLK_RW_ASYNC	= 0,
+	BLK_RW_SYNC	= 1,
+};
+
 /*
  * For request of type REQ_TYPE_LINUX_BLOCK, rq->cmd[0] is the opcode being
  * sent down (similar to how REQ_TYPE_BLOCK_PC means that ->cmd[] holds a
@@ -103,12 +112,12 @@ enum rq_flag_bits {
 	__REQ_QUIET,		/* don't worry about errors */
 	__REQ_PREEMPT,		/* set for "ide_preempt" requests */
 	__REQ_ORDERED_COLOR,	/* is before or after barrier */
-	__REQ_RW_SYNC,		/* request is sync (O_DIRECT) */
+	__REQ_RW_SYNC,		/* request is sync (sync write or read) */
 	__REQ_ALLOCED,		/* request came from our alloc pool */
 	__REQ_RW_META,		/* metadata io request */
 	__REQ_COPY_USER,	/* contains copies of user pages */
 	__REQ_INTEGRITY,	/* integrity metadata has been remapped */
-	__REQ_UNPLUG,		/* unplug queue on submission */
+	__REQ_NOIDLE,		/* Don't anticipate more IO after this one */
 	__REQ_NR_BITS,		/* stops here */
 };
 
@@ -135,7 +144,7 @@ enum rq_flag_bits {
 #define REQ_RW_META	(1 << __REQ_RW_META)
 #define REQ_COPY_USER	(1 << __REQ_COPY_USER)
 #define REQ_INTEGRITY	(1 << __REQ_INTEGRITY)
-#define REQ_UNPLUG	(1 << __REQ_UNPLUG)
+#define REQ_NOIDLE	(1 << __REQ_NOIDLE)
 
 #define BLK_MAX_CDB	16
 
@@ -438,8 +447,8 @@ struct request_queue
 #define QUEUE_FLAG_CLUSTER	0	/* cluster several segments into 1 */
 #define QUEUE_FLAG_QUEUED	1	/* uses generic tag queueing */
 #define QUEUE_FLAG_STOPPED	2	/* queue is stopped */
-#define	QUEUE_FLAG_READFULL	3	/* read queue has been filled */
-#define QUEUE_FLAG_WRITEFULL	4	/* write queue has been filled */
+#define	QUEUE_FLAG_SYNCFULL	3	/* read queue has been filled */
+#define QUEUE_FLAG_ASYNCFULL	4	/* write queue has been filled */
 #define QUEUE_FLAG_DEAD		5	/* queue being torn down */
 #define QUEUE_FLAG_REENTER	6	/* Re-entrancy avoidance */
 #define QUEUE_FLAG_PLUGGED	7	/* queue is plugged */
@@ -611,32 +620,42 @@ enum {
 #define rq_data_dir(rq)		((rq)->cmd_flags & 1)
 
 /*
- * We regard a request as sync, if it's a READ or a SYNC write.
+ * We regard a request as sync, if either a read or a sync write
  */
-#define rq_is_sync(rq)		(rq_data_dir((rq)) == READ || (rq)->cmd_flags & REQ_RW_SYNC)
+static inline bool rw_is_sync(unsigned int rw_flags)
+{
+	return !(rw_flags & REQ_RW) || (rw_flags & REQ_RW_SYNC);
+}
+
+static inline bool rq_is_sync(struct request *rq)
+{
+	return rw_is_sync(rq->cmd_flags);
+}
+
 #define rq_is_meta(rq)		((rq)->cmd_flags & REQ_RW_META)
+#define rq_noidle(rq)		((rq)->cmd_flags & REQ_NOIDLE)
 
-static inline int blk_queue_full(struct request_queue *q, int rw)
+static inline int blk_queue_full(struct request_queue *q, int sync)
 {
-	if (rw == READ)
-		return test_bit(QUEUE_FLAG_READFULL, &q->queue_flags);
-	return test_bit(QUEUE_FLAG_WRITEFULL, &q->queue_flags);
+	if (sync)
+		return test_bit(QUEUE_FLAG_SYNCFULL, &q->queue_flags);
+	return test_bit(QUEUE_FLAG_ASYNCFULL, &q->queue_flags);
 }
 
-static inline void blk_set_queue_full(struct request_queue *q, int rw)
+static inline void blk_set_queue_full(struct request_queue *q, int sync)
 {
-	if (rw == READ)
-		queue_flag_set(QUEUE_FLAG_READFULL, q);
+	if (sync)
+		queue_flag_set(QUEUE_FLAG_SYNCFULL, q);
 	else
-		queue_flag_set(QUEUE_FLAG_WRITEFULL, q);
+		queue_flag_set(QUEUE_FLAG_ASYNCFULL, q);
 }
 
-static inline void blk_clear_queue_full(struct request_queue *q, int rw)
+static inline void blk_clear_queue_full(struct request_queue *q, int sync)
 {
-	if (rw == READ)
-		queue_flag_clear(QUEUE_FLAG_READFULL, q);
+	if (sync)
+		queue_flag_clear(QUEUE_FLAG_SYNCFULL, q);
 	else
-		queue_flag_clear(QUEUE_FLAG_WRITEFULL, q);
+		queue_flag_clear(QUEUE_FLAG_ASYNCFULL, q);
 }
 
 
diff --git a/include/linux/capability.h b/include/linux/capability.h
index 4864a43b2b45..c3021105edc0 100644
--- a/include/linux/capability.h
+++ b/include/linux/capability.h
@@ -377,7 +377,21 @@ struct cpu_vfs_cap_data {
 #define CAP_FOR_EACH_U32(__capi)  \
 	for (__capi = 0; __capi < _KERNEL_CAPABILITY_U32S; ++__capi)
 
+/*
+ * CAP_FS_MASK and CAP_NFSD_MASKS:
+ *
+ * The fs mask is all the privileges that fsuid==0 historically meant.
+ * At one time in the past, that included CAP_MKNOD and CAP_LINUX_IMMUTABLE.
+ *
+ * It has never meant setting security.* and trusted.* xattrs.
+ *
+ * We could also define fsmask as follows:
+ *   1. CAP_FS_MASK is the privilege to bypass all fs-related DAC permissions
+ *   2. The security.* and trusted.* xattrs are fs-related MAC permissions
+ */
+
 # define CAP_FS_MASK_B0     (CAP_TO_MASK(CAP_CHOWN)		\
+			    | CAP_TO_MASK(CAP_MKNOD)		\
 			    | CAP_TO_MASK(CAP_DAC_OVERRIDE)	\
 			    | CAP_TO_MASK(CAP_DAC_READ_SEARCH)	\
 			    | CAP_TO_MASK(CAP_FOWNER)		\
@@ -392,11 +406,12 @@ struct cpu_vfs_cap_data {
 # define CAP_EMPTY_SET    ((kernel_cap_t){{ 0, 0 }})
 # define CAP_FULL_SET     ((kernel_cap_t){{ ~0, ~0 }})
 # define CAP_INIT_EFF_SET ((kernel_cap_t){{ ~CAP_TO_MASK(CAP_SETPCAP), ~0 }})
-# define CAP_FS_SET       ((kernel_cap_t){{ CAP_FS_MASK_B0, CAP_FS_MASK_B1 } })
+# define CAP_FS_SET       ((kernel_cap_t){{ CAP_FS_MASK_B0 \
+				    | CAP_TO_MASK(CAP_LINUX_IMMUTABLE), \
+				    CAP_FS_MASK_B1 } })
 # define CAP_NFSD_SET     ((kernel_cap_t){{ CAP_FS_MASK_B0 \
-					    | CAP_TO_MASK(CAP_SYS_RESOURCE) \
-					    | CAP_TO_MASK(CAP_MKNOD), \
-					    CAP_FS_MASK_B1 } })
+				    | CAP_TO_MASK(CAP_SYS_RESOURCE), \
+				    CAP_FS_MASK_B1 } })
 
 #endif /* _KERNEL_CAPABILITY_U32S != 2 */
 
diff --git a/include/linux/compiler.h b/include/linux/compiler.h
index 6faa7e549de4..37bcb50a4d7c 100644
--- a/include/linux/compiler.h
+++ b/include/linux/compiler.h
@@ -76,7 +76,8 @@ struct ftrace_branch_data {
  * Note: DISABLE_BRANCH_PROFILING can be used by special lowlevel code
  * to disable branch tracing on a per file basis.
  */
-#if defined(CONFIG_TRACE_BRANCH_PROFILING) && !defined(DISABLE_BRANCH_PROFILING)
+#if defined(CONFIG_TRACE_BRANCH_PROFILING) \
+    && !defined(DISABLE_BRANCH_PROFILING) && !defined(__CHECKER__)
 void ftrace_likely_update(struct ftrace_branch_data *f, int val, int expect);
 
 #define likely_notrace(x)	__builtin_expect(!!(x), 1)
@@ -114,7 +115,9 @@ void ftrace_likely_update(struct ftrace_branch_data *f, int val, int expect);
  * "Define 'is'", Bill Clinton
  * "Define 'if'", Steven Rostedt
  */
-#define if(cond) if (__builtin_constant_p((cond)) ? !!(cond) :		\
+#define if(cond, ...) __trace_if( (cond , ## __VA_ARGS__) )
+#define __trace_if(cond) \
+	if (__builtin_constant_p((cond)) ? !!(cond) :			\
 	({								\
 		int ______r;						\
 		static struct ftrace_branch_data			\
diff --git a/include/linux/debug_locks.h b/include/linux/debug_locks.h
index 096476f1fb35..29b3ce3f2a1d 100644
--- a/include/linux/debug_locks.h
+++ b/include/linux/debug_locks.h
@@ -2,12 +2,20 @@
 #define __LINUX_DEBUG_LOCKING_H
 
 #include <linux/kernel.h>
+#include <asm/atomic.h>
+#include <asm/system.h>
 
 struct task_struct;
 
 extern int debug_locks;
 extern int debug_locks_silent;
 
+
+static inline int __debug_locks_off(void)
+{
+	return xchg(&debug_locks, 0);
+}
+
 /*
  * Generic 'turn off all lock debugging' function:
  */
diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h
index 66ec05a57955..ded2d7c42668 100644
--- a/include/linux/device-mapper.h
+++ b/include/linux/device-mapper.h
@@ -116,7 +116,6 @@ void dm_put_device(struct dm_target *ti, struct dm_dev *d);
 /*
  * Target features
  */
-#define DM_TARGET_SUPPORTS_BARRIERS 0x00000001
 
 struct target_type {
 	uint64_t features;
diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h
index d7d090d21031..8083b6a36a38 100644
--- a/include/linux/dma-mapping.h
+++ b/include/linux/dma-mapping.h
@@ -115,7 +115,7 @@ static inline u64 dma_get_mask(struct device *dev)
 {
 	if (dev && dev->dma_mask && *dev->dma_mask)
 		return *dev->dma_mask;
-	return DMA_32BIT_MASK;
+	return DMA_BIT_MASK(32);
 }
 
 extern u64 dma_get_required_mask(struct device *dev);
diff --git a/include/linux/dmar.h b/include/linux/dmar.h
index 2f3427468956..e397dc342cda 100644
--- a/