Merge branch 'core/urgent' into core/futexes

Merge reason: this branch was on an pre -rc1 base, merge it up to -rc6+
              to get the latest upstream fixes.

Conflicts:
	kernel/futex.c

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>

include/linux/Kbuild

@@ -138,6 +138,7 @@ header-y += qnxtypes.h
 header-y += radeonfb.h
 header-y += raw.h
 header-y += resource.h
+header-y += romfs_fs.h
 header-y += rose.h
 header-y += serial_reg.h
 header-y += smbno.h
@@ -314,7 +315,6 @@ unifdef-y += irqnr.h
 unifdef-y += reboot.h
 unifdef-y += reiserfs_fs.h
 unifdef-y += reiserfs_xattr.h
-unifdef-y += romfs_fs.h
 unifdef-y += route.h
 unifdef-y += rtc.h
 unifdef-y += rtnetlink.h

include/linux/acpi.h

@@ -97,6 +97,7 @@ void acpi_table_print_madt_entry (struct acpi_subtable_header *madt);
 /* the following four functions are architecture-dependent */
 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_x2apic_affinity_init(struct acpi_srat_x2apic_cpu_affinity *pa);
 void acpi_numa_memory_affinity_init (struct acpi_srat_mem_affinity *ma);
 void acpi_numa_arch_fixup(void);
 
@@ -110,6 +111,7 @@ int acpi_register_ioapic(acpi_handle handle, u64 phys_addr, u32 gsi_base);
 int acpi_unregister_ioapic(acpi_handle handle, u32 gsi_base);
 void acpi_irq_stats_init(void);
 extern u32 acpi_irq_handled;
+extern u32 acpi_irq_not_handled;
 
 extern struct acpi_mcfg_allocation *pci_mmcfg_config;
 extern int pci_mmcfg_config_num;

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 +730,42 @@ static inline int ata_id_has_unload(const u16 *id)
 	return 0;
 }
 
+static inline int ata_id_form_factor(const u16 *id)
+{
+	u16 val = id[168];
+
+	if (ata_id_major_version(id) < 7 || val == 0 || val == 0xffff)
+		return 0;
+
+	val &= 0xf;
+
+	if (val > 5)
+		return 0;
+
+	return val;
+}
+
+static inline int ata_id_rotation_rate(const u16 *id)
+{
+	u16 val = id[217];
+
+	if (ata_id_major_version(id) < 7 || val == 0 || val == 0xffff)
+		return 0;
+
+	if (val > 1 && val < 0x401)
+		return 0;
+
+	return val;
+}
+
+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 +906,32 @@ 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) ||

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);

include/linux/binfmts.h

@@ -82,7 +82,19 @@ struct linux_binfmt {
 	int hasvdso;
 };
 
-extern int register_binfmt(struct linux_binfmt *);
+extern int __register_binfmt(struct linux_binfmt *fmt, int insert);
+
+/* Registration of default binfmt handlers */
+static inline int register_binfmt(struct linux_binfmt *fmt)
+{
+	return __register_binfmt(fmt, 0);
+}
+/* Same as above, but adds a new binfmt at the top of the list */
+static inline int insert_binfmt(struct linux_binfmt *fmt)
+{
+	return __register_binfmt(fmt, 1);
+}
+
 extern void unregister_binfmt(struct linux_binfmt *);
 
 extern int prepare_binprm(struct linux_binprm *);

include/linux/bio.h

@@ -132,6 +132,7 @@ struct bio {
  * top 4 bits of bio flags indicate the pool this bio came from
  */
 #define BIO_POOL_BITS		(4)
+#define BIO_POOL_NONE		((1UL << BIO_POOL_BITS) - 1)
 #define BIO_POOL_OFFSET		(BITS_PER_LONG - BIO_POOL_BITS)
 #define BIO_POOL_MASK		(1UL << BIO_POOL_OFFSET)
 #define BIO_POOL_IDX(bio)	((bio)->bi_flags >> BIO_POOL_OFFSET)	
@@ -145,20 +146,21 @@ 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 +172,7 @@ 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 +191,7 @@ 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
@@ -501,6 +505,115 @@ static inline int bio_has_data(struct bio *bio)
 	return bio && bio->bi_io_vec != NULL;
 }
 
+/*
+ * BIO list managment for use by remapping drivers (e.g. DM or MD).
+ *
+ * A bio_list anchors a singly-linked list of bios chained through the bi_next
+ * member of the bio.  The bio_list also caches the last list member to allow
+ * fast access to the tail.
+ */
+struct bio_list {
+	struct bio *head;
+	struct bio *tail;
+};
+
+static inline int bio_list_empty(const struct bio_list *bl)
+{
+	return bl->head == NULL;
+}
+
+static inline void bio_list_init(struct bio_list *bl)
+{
+	bl->head = bl->tail = NULL;
+}
+
+#define bio_list_for_each(bio, bl) \
+	for (bio = (bl)->head; bio; bio = bio->bi_next)
+
+static inline unsigned bio_list_size(const struct bio_list *bl)
+{
+	unsigned sz = 0;
+	struct bio *bio;
+
+	bio_list_for_each(bio, bl)
+		sz++;
+
+	return sz;
+}
+
+static inline void bio_list_add(struct bio_list *bl, struct bio *bio)
+{
+	bio->bi_next = NULL;
+
+	if (bl->tail)
+		bl->tail->bi_next = bio;
+	else
+		bl->head = bio;
+
+	bl->tail = bio;
+}
+
+static inline void bio_list_add_head(struct bio_list *bl, struct bio *bio)
+{
+	bio->bi_next = bl->head;
+
+	bl->head = bio;
+
+	if (!bl->tail)
+		bl->tail = bio;
+}
+
+static inline void bio_list_merge(struct bio_list *bl, struct bio_list *bl2)
+{
+	if (!bl2->head)
+		return;
+
+	if (bl->tail)
+		bl->tail->bi_next = bl2->head;
+	else
+		bl->head = bl2->head;
+
+	bl->tail = bl2->tail;
+}
+
+static inline void bio_list_merge_head(struct bio_list *bl,
+				       struct bio_list *bl2)
+{
+	if (!bl2->head)
+		return;
+
+	if (bl->head)
+		bl2->tail->bi_next = bl->head;
+	else
+		bl->tail = bl2->tail;
+
+	bl->head = bl2->head;
+}
+
+static inline struct bio *bio_list_pop(struct bio_list *bl)
+{
+	struct bio *bio = bl->head;
+
+	if (bio) {
+		bl->head = bl->head->bi_next;
+		if (!bl->head)
+			bl->tail = NULL;
+
+		bio->bi_next = NULL;
+	}
+
+	return bio;
+}
+
+static inline struct bio *bio_list_get(struct bio_list *bl)
+{
+	struct bio *bio = bl->head;
+
+	bl->head = bl->tail = NULL;
+
+	return bio;
+}
+
 #if defined(CONFIG_BLK_DEV_INTEGRITY)
 
 #define bip_vec_idx(bip, idx)	(&(bip->bip_vec[(idx)]))

include/linux/bitops.h

@@ -112,6 +112,25 @@ static inline unsigned fls_long(unsigned long l)
 	return fls64(l);
 }
 
+/**
+ * __ffs64 - find first set bit in a 64 bit word
+ * @word: The 64 bit word
+ *
+ * On 64 bit arches this is a synomyn for __ffs
+ * The result is not defined if no bits are set, so check that @word
+ * is non-zero before calling this.
+ */
+static inline unsigned long __ffs64(u64 word)
+{
+#if BITS_PER_LONG == 32
+	if (((u32)word) == 0UL)
+		return __ffs((u32)(word >> 32)) + 32;
+#elif BITS_PER_LONG != 64
+#error BITS_PER_LONG not 32 or 64
+#endif
+	return __ffs((unsigned long)word);
+}
+
 #ifdef __KERNEL__
 #ifdef CONFIG_GENERIC_FIND_FIRST_BIT
 

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 +112,13 @@ 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_IO_STAT,		/* account I/O stat */
 	__REQ_NR_BITS,		/* stops here */
 };
 
@@ -135,7 +145,8 @@ 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 REQ_IO_STAT	(1 << __REQ_IO_STAT)
 
 #define BLK_MAX_CDB	16
 
@@ -438,8 +449,8 @@ 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 */
@@ -589,6 +600,8 @@ enum {
 				 blk_failfast_transport(rq) ||	\
 				 blk_failfast_driver(rq))
 #define blk_rq_started(rq)	((rq)->cmd_flags & REQ_STARTED)
+#define blk_rq_io_stat(rq)	((rq)->cmd_flags & REQ_IO_STAT)
+#define blk_rq_quiet(rq)	((rq)->cmd_flags & REQ_QUIET)
 
 #define blk_account_rq(rq)	(blk_rq_started(rq) && (blk_fs_request(rq) || blk_discard_rq(rq))) 
 
@@ -611,32 +624,42 @@ 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);
 }
 
 

include/linux/blktrace_api.h

@@ -144,6 +144,9 @@ struct blk_user_trace_setup {
 
 #ifdef __KERNEL__
 #if defined(CONFIG_BLK_DEV_IO_TRACE)
+
+#include <linux/sysfs.h>
+
 struct blk_trace {
 	int trace_state;
 	struct rchan *rchan;
@@ -194,6 +197,8 @@ extern int blk_trace_setup(struct request_queue *q, char *name, dev_t dev,
 extern int blk_trace_startstop(struct request_queue *q, int start);
 extern int blk_trace_remove(struct request_queue *q);
 
+extern struct attribute_group blk_trace_attr_group;
+
 #else /* !CONFIG_BLK_DEV_IO_TRACE */
 #define blk_trace_ioctl(bdev, cmd, arg)		(-ENOTTY)
 #define blk_trace_shutdown(q)			do { } while (0)

include/linux/buffer_head.h

@@ -155,6 +155,7 @@ void create_empty_buffers(struct page *, unsigned long,
 			unsigned long b_state);
 void end_buffer_read_sync(struct buffer_head *bh, int uptodate);
 void end_buffer_write_sync(struct buffer_head *bh, int uptodate);
+void end_buffer_async_write(struct buffer_head *bh, int uptodate);
 
 /* Things to do with buffers at mapping->private_list */
 void mark_buffer_dirty_inode(struct buffer_head *bh, struct inode *inode);
@@ -197,6 +198,8 @@ extern int buffer_heads_over_limit;
 void block_invalidatepage(struct page *page, unsigned long offset);
 int block_write_full_page(struct page *page, get_block_t *get_block,
 				struct writeback_control *wbc);
+int block_write_full_page_endio(struct page *page, get_block_t *get_block,
+			struct writeback_control *wbc, bh_end_io_t *handler);
 int block_read_full_page(struct page*, get_block_t*);
 int block_is_partially_uptodate(struct page *page, read_descriptor_t *desc,
 				unsigned long from);

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 */
 

include/linux/clocksource.h

@@ -143,7 +143,9 @@ extern u64 timecounter_cyc2time(struct timecounter *tc,
  *			400-499: Perfect
  *				The ideal clocksource. A must-use where
  *				available.
- * @read:		returns a cycle value
+ * @read:		returns a cycle value, passes clocksource as argument
+ * @enable:		optional function to enable the clocksource
+ * @disable:		optional function to disable the clocksource
  * @mask:		bitmask for two's complement
  *			subtraction of non 64 bit counters
  * @mult:		cycle to nanosecond multiplier (adjusted by NTP)
@@ -162,7 +164,9 @@ struct clocksource {
 	char *name;
 	struct list_head list;
 	int rating;
-	cycle_t (*read)(void);
+	cycle_t (*read)(struct clocksource *cs);
+	int (*enable)(struct clocksource *cs);
+	void (*disable)(struct clocksource *cs);
 	cycle_t mask;
 	u32 mult;
 	u32 mult_orig;
@@ -271,7 +275,34 @@ static inline u32 clocksource_hz2mult(u32 hz, u32 shift_constant)
  */
 static inline cycle_t clocksource_read(struct clocksource *cs)
 {
-	return cs->read();
+	return cs->read(cs);
+}
+
+/**
+ * clocksource_enable: - enable clocksource
+ * @cs:		pointer to clocksource
+ *
+ * Enables the specified clocksource. The clocksource callback
+ * function should start up the hardware and setup mult and field
+ * members of struct clocksource to reflect hardware capabilities.
+ */
+static inline int clocksource_enable(struct clocksource *cs)
+{
+	return cs->enable ? cs->enable(cs) : 0;
+}
+
+/**
+ * clocksource_disable: - disable clocksource
+ * @cs:		pointer to clocksource
+ *
+ * Disables the specified clocksource. The clocksource callback
+ * function should power down the now unused hardware block to
+ * save power.
+ */
+static inline void clocksource_disable(struct clocksource *cs)
+{
+	if (cs->disable)
+		cs->disable(cs);
 }
 
 /**

include/linux/compat.h

@@ -193,10 +193,10 @@ asmlinkage ssize_t compat_sys_writev(unsigned long fd,
 		const struct compat_iovec __user *vec, unsigned long vlen);
 asmlinkage ssize_t compat_sys_preadv(unsigned long fd,
 		const struct compat_iovec __user *vec,
-		unsigned long vlen, u32 pos_high, u32 pos_low);
+		unsigned long vlen, u32 pos_low, u32 pos_high);
 asmlinkage ssize_t compat_sys_pwritev(unsigned long fd,
 		const struct compat_iovec __user *vec,
-		unsigned long vlen, u32 pos_high, u32 pos_low);
+		unsigned long vlen, u32 pos_low, u32 pos_high);
 
 int compat_do_execve(char * filename, compat_uptr_t __user *argv,
 	        compat_uptr_t __user *envp, struct pt_regs * regs);

include/linux/compiler.h

@@ -68,6 +68,7 @@ struct ftrace_branch_data {
 			unsigned long miss;
 			unsigned long hit;
 		};
+		unsigned long miss_hit[2];
 	};
 };
 
@@ -75,7 +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)
@@ -113,7 +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			\
@@ -125,10 +129,7 @@ void ftrace_likely_update(struct ftrace_branch_data *f, int val, int expect);
 				.line = __LINE__,			\
 			};						\
 		______r = !!(cond);					\
-		if (______r)						\
-			______f.hit++;					\
-		else							\
-			______f.miss++;					\
+		______f.miss_hit[______r]++;					\
 		______r;						\
 	}))
 #endif /* CONFIG_PROFILE_ALL_BRANCHES */

include/linux/connector.h

@@ -39,8 +39,10 @@
 #define CN_IDX_V86D			0x4
 #define CN_VAL_V86D_UVESAFB		0x1
 #define CN_IDX_BB			0x5	/* BlackBoard, from the TSP GPL sampling framework */
+#define CN_DST_IDX			0x6
+#define CN_DST_VAL			0x1
 
-#define CN_NETLINK_USERS		6
+#define CN_NETLINK_USERS		7
 
 /*
  * Maximum connector's message size.

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:
  */

include/linux/debugfs.h

@@ -71,6 +71,9 @@ struct dentry *debugfs_create_bool(const char *name, mode_t mode,
 struct dentry *debugfs_create_blob(const char *name, mode_t mode,
 				  struct dentry *parent,
 				  struct debugfs_blob_wrapper *blob);
+
+bool debugfs_initialized(void);
+
 #else
 
 #include <linux/err.h>
@@ -183,6 +186,11 @@ static inline struct dentry *debugfs_create_blob(const char *name, mode_t mode,
 	return ERR_PTR(-ENODEV);
 }
 
+static inline bool debugfs_initialized(void)
+{
+	return false;
+}
+
 #endif
 
 #endif

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;

include/linux/device.h

@@ -384,13 +384,8 @@ struct device {
 	struct device_driver *driver;	/* which driver has allocated this
 					   device */
 	void		*driver_data;	/* data private to the driver */
-
-	void		*platform_data;	/* We will remove platform_data
-					   field if all platform devices
-					   pass its platform specific data
-					   from platform_device->platform_data,
-					   other kind of devices should not
-					   use platform_data. */
+	void		*platform_data;	/* Platform specific data, device
+					   core doesn't touch it */
 	struct dev_pm_info	power;
 
 #ifdef CONFIG_NUMA
@@ -551,6 +546,7 @@ extern int (*platform_notify_remove)(struct device *dev);
 extern struct device *get_device(struct device *dev);
 extern void put_device(struct device *dev);
 
+extern void wait_for_device_probe(void);
 
 /* drivers/base/power/shutdown.c */
 extern void device_shutdown(void);

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);

include/linux/dmaengine.h

@@ -78,12 +78,18 @@ enum dma_transaction_type {
  * 	dependency chains
  * @DMA_COMPL_SKIP_SRC_UNMAP - set to disable dma-unmapping the source buffer(s)
  * @DMA_COMPL_SKIP_DEST_UNMAP - set to disable dma-unmapping the destination(s)
+ * @DMA_COMPL_SRC_UNMAP_SINGLE - set to do the source dma-unmapping as single
+ * 	(if not set, do the source dma-unmapping as page)
+ * @DMA_COMPL_DEST_UNMAP_SINGLE - set to do the destination dma-unmapping as single
+ * 	(if not set, do the destination dma-unmapping as page)
  */
 enum dma_ctrl_flags {
 	DMA_PREP_INTERRUPT = (1 << 0),
 	DMA_CTRL_ACK = (1 << 1),
 	DMA_COMPL_SKIP_SRC_UNMAP = (1 << 2),
 	DMA_COMPL_SKIP_DEST_UNMAP = (1 << 3),
+	DMA_COMPL_SRC_UNMAP_SINGLE = (1 << 4),
+	DMA_COMPL_DEST_UNMAP_SINGLE = (1 << 5),
 };
 
 /**

include/linux/dmar.h

@@ -34,6 +34,7 @@ struct dmar_drhd_unit {
 	u64	reg_base_addr;		/* register base address*/
 	struct	pci_dev **devices; 	/* target device array	*/
 	int	devices_cnt;		/* target device count	*/
+	u16	segment;		/* PCI domain		*/
 	u8	ignored:1; 		/* ignore drhd		*/
 	u8	include_all:1;
 	struct intel_iommu *iommu;
@@ -44,6 +45,14 @@ extern struct list_head dmar_drhd_units;
 #define for_each_drhd_unit(drhd) \
 	list_for_each_entry(drhd, &dmar_drhd_units, list)
 
+#define for_each_active_iommu(i, drhd)					\
+	list_for_each_entry(drhd, &dmar_drhd_units, list)		\
+		if (i=drhd->iommu, drhd->ignored) {} else
+
+#define for_each_iommu(i, drhd)						\
+	list_for_each_entry(drhd, &dmar_drhd_units, list)		\
+		if (i=drhd->iommu, 0) {} else 
+
 extern int dmar_table_init(void);
 extern int dmar_dev_scope_init(void);
 
@@ -100,6 +109,8 @@ struct irte {
 #ifdef CONFIG_INTR_REMAP
 extern int intr_remapping_enabled;
 extern int enable_intr_remapping(int);
+extern void disable_intr_remapping(void);
+extern int reenable_intr_remapping(int);
 
 extern int get_irte(int irq, struct irte *entry);
 extern int modify_irte(int irq, struct irte *irte_modified);

include/linux/ds1wm.h

@@ -1,12 +0,0 @@
-/* platform data for the DS1WM driver */
-
-struct ds1wm_platform_data {
-	int bus_shift;	    /* number of shifts needed to calculate the
-			     * offset between DS1WM registers;
-			     * e.g. on h5xxx and h2200 this is 2
-			     * (registers aligned to 4-byte boundaries),
-			     * while on hx4700 this is 1 */
-	int active_high;
-	void (*enable)(struct platform_device *pdev);
-	void (*disable)(struct platform_device *pdev);
-};

include/linux/dst.h

@@ -0,0 +1,587 @@
+/*
+ * 2007+ Copyright (c) Evgeniy Polyakov <johnpol@2ka.mipt.ru>
+ * All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef __DST_H
+#define __DST_H
+
+#include <linux/types.h>
+#include <linux/connector.h>
+
+#define DST_NAMELEN		32
+#define DST_NAME		"dst"
+
+enum {
+	/* Remove node with given id from storage */
+	DST_DEL_NODE	= 0,
+	/* Add remote node with given id to the storage */
+	DST_ADD_REMOTE,
+	/* Add local node with given id to the storage to be exported and used by remote peers */
+	DST_ADD_EXPORT,
+	/* Crypto initialization command (hash/cipher used to protect the connection) */
+	DST_CRYPTO,
+	/* Security attributes for given connection (permissions for example) */
+	DST_SECURITY,
+	/* Register given node in the block layer subsystem */
+	DST_START,
+	DST_CMD_MAX
+};
+
+struct dst_ctl
+{
+	/* Storage name */
+	char			name[DST_NAMELEN];
+	/* Command flags */
+	__u32			flags;
+	/* Command itself (see above) */
+	__u32			cmd;
+	/* Maximum number of pages per single request in this device */
+	__u32			max_pages;
+	/* Stale/error transaction scanning timeout in milliseconds */
+	__u32			trans_scan_timeout;
+	/* Maximum number of retry sends before completing transaction as broken */
+	__u32			trans_max_retries;
+	/* Storage size */
+	__u64			size;
+};
+
+/* Reply command carries completion status */
+struct dst_ctl_ack
+{
+	struct cn_msg		msg;
+	int			error;
+	int			unused[3];
+};
+
+/*
+ * Unfortunaltely socket address structure is not exported to userspace
+ * and is redefined there.
+ */
+#define SADDR_MAX_DATA	128
+
+struct saddr {
+	/* address family, AF_xxx	*/
+	unsigned short		sa_family;
+	/* 14 bytes of protocol address	*/
+	char			sa_data[SADDR_MAX_DATA];
+	/* Number of bytes used in sa_data */
+	unsigned short		sa_data_len;
+};
+
+/* Address structure */
+struct dst_network_ctl
+{
+	/* Socket type: datagram, stream...*/
+	unsigned int		type;
+	/* Let me guess, is it a Jupiter diameter? */
+	unsigned int		proto;
+	/* Peer's address */
+	struct saddr		addr;
+};
+
+struct dst_crypto_ctl
+{
+	/* Cipher and hash names */
+	char			cipher_algo[DST_NAMELEN];
+	char			hash_algo[DST_NAMELEN];
+
+	/* Key sizes. Can be zero for digest for example */
+	unsigned int		cipher_keysize, hash_keysize;
+	/* Alignment. Calculated by the DST itself. */
+	unsigned int		crypto_attached_size;
+	/* Number of threads to perform crypto operations */
+	int			thread_num;
+};
+
+/* Export security attributes have this bits checked in when client connects */
+#define DST_PERM_READ		(1<<0)
+#define DST_PERM_WRITE		(1<<1)
+
+/*
+ * Right now it is simple model, where each remote address
+ * is assigned to set of permissions it is allowed to perform.
+ * In real world block device does not know anything but
+ * reading and writing, so it should be more than enough.
+ */
+struct dst_secure_user
+{
+	unsigned int		permissions;
+	struct saddr		addr;
+};
+
+/*
+ * Export control command: device to export and network address to accept
+ * clients to work with given device
+ */
+struct dst_export_ctl
+{
+	char			device[DST_NAMELEN];
+	struct dst_network_ctl	ctl;
+};
+
+enum {
+	DST_CFG	= 1, 		/* Request remote configuration */
+	DST_IO,			/* IO command */
+	DST_IO_RESPONSE,	/* IO response */
+	DST_PING,		/* Keepalive message */
+	DST_NCMD_MAX,
+};
+
+struct dst_cmd
+{
+	/* Network command itself, see above */
+	__u32			cmd;
+	/*
+	 * Size of the attached data
+	 * (in most cases, for READ command it means how many bytes were requested)
+	 */
+	__u32			size;
+	/* Crypto size: number of attached bytes with digest/hmac */
+	__u32			csize;
+	/* Here we can carry secret data */
+	__u32			reserved;
+	/* Read/write bits, see how they are encoded in bio structure */
+	__u64			rw;
+	/* BIO flags */
+	__u64			flags;
+	/* Unique command id (like transaction ID) */
+	__u64			id;
+	/* Sector to start IO from */
+	__u64			sector;
+	/* Hash data is placed after this header */
+	__u8			hash[0];
+};
+
+/*
+ * Convert command to/from network byte order.
+ * We do not use hton*() functions, since there is
+ * no 64-bit implementation.
+ */
+static inline void dst_convert_cmd(struct dst_cmd *c)
+{
+	c->cmd = __cpu_to_be32(c->cmd);
+	c->csize = __cpu_to_be32(c->csize);
+	c->size = __cpu_to_be32(c->size);
+	c->sector = __cpu_to_be64(c->sector);
+	c->id = __cpu_to_be64(c->id);
+	c->flags = __cpu_to_be64(c->flags);
+	c->rw = __cpu_to_be64(c->rw);
+}
+
+/* Transaction id */
+typedef __u64 dst_gen_t;
+
+#ifdef __KERNEL__
+
+#include <linux/blkdev.h>
+#include <linux/bio.h>
+#include <linux/device.h>
+#include <linux/mempool.h>
+#include <linux/net.h>
+#include <linux/poll.h>
+#include <linux/rbtree.h>
+
+#ifdef CONFIG_DST_DEBUG
+#define dprintk(f, a...) printk(KERN_NOTICE f, ##a)
+#else
+static inline void __attribute__ ((format (printf, 1, 2)))
+	dprintk(const char *fmt, ...) {}
+#endif
+
+struct dst_node;
+
+struct dst_trans
+{
+	/* DST node we are working with */
+	struct dst_node		*n;
+
+	/* Entry inside transaction tree */
+	struct rb_node		trans_entry;
+
+	/* Merlin kills this transaction when this memory cell equals zero */
+	atomic_t		refcnt;
+
+	/* How this transaction should be processed by crypto engine */
+	short			enc;
+	/* How many times this transaction was resent */
+	short			retries;
+	/* Completion status */
+	int			error;
+
+	/* When did we send it to the remote peer */
+	long			send_time;
+
+	/* My name is...
+	 * Well, computers does not speak, they have unique id instead */
+	dst_gen_t		gen;
+
+	/* Block IO we are working with */
+	struct bio		*bio;
+
+	/* Network command for above block IO request */
+	struct dst_cmd		cmd;
+};
+
+struct dst_crypto_engine
+{
+	/* What should we do with all block requests */
+	struct crypto_hash	*hash;
+	struct crypto_ablkcipher	*cipher;
+
+	/* Pool of pages used to encrypt data into before sending */
+	int			page_num;
+	struct page		**pages;
+
+	/* What to do with current request */
+	int			enc;
+	/* Who we are and where do we go */
+	struct scatterlist	*src, *dst;
+
+	/* Maximum timeout waiting for encryption to be completed */
+	long			timeout;
+	/* IV is a 64-bit sequential counter */
+	u64			iv;
+
+	/* Secret data */
+	void			*private;
+
+	/* Cached temporary data lives here */
+	int			size;
+	void			*data;
+};
+
+struct dst_state
+{
+	/* The main state protection */
+	struct mutex		state_lock;
+
+	/* Polling machinery for sockets */
+	wait_queue_t 		wait;
+	wait_queue_head_t 	*whead;
+	/* Most of events are being waited here */
+	wait_queue_head_t 	thread_wait;
+
+	/* Who owns this? */
+	struct dst_node		*node;
+
+	/* Network address for this state */
+	struct dst_network_ctl	ctl;
+
+	/* Permissions to work with: read-only or rw connection */
+	u32			permissions;
+
+	/* Called when we need to clean private data */
+	void			(* cleanup)(struct dst_state *st);
+
+	/* Used by the server: BIO completion queues BIOs here */
+	struct list_head	request_list;
+	spinlock_t		request_lock;
+
+	/* Guess what? No, it is not number of planets */
+	atomic_t		refcnt;
+
+	/* This flags is set when connection should be dropped */
+	int			need_exit;
+
+	/*
+	 * Socket to work with. Second pointer is used for
+	 * lockless check if socket was changed before performing
+	 * next action (like working with cached polling result)
+	 */
+	struct socket		*socket, *read_socket;
+
+	/* Cached preallocated data */
+	void			*data;
+	unsigned int		size;
+
+	/* Currently processed command */
+	struct dst_cmd		cmd;
+};
+
+struct dst_info
+{
+	/* Device size */
+	u64			size;
+
+	/* Local device name for export devices */
+	char			local[DST_NAMELEN];
+
+	/* Network setup */
+	struct dst_network_ctl	net;
+
+	/* Sysfs bits use this */
+	struct device		device;
+};
+
+struct dst_node
+{
+	struct list_head	node_entry;
+
+	/* Hi, my name is stored here */
+	char			name[DST_NAMELEN];
+	/* My cache name is stored here */
+	char			cache_name[DST_NAMELEN];
+
+	/* Block device attached to given node.
+	 * Only valid for exporting nodes */
+	struct block_device 	*bdev;
+	/* Network state machine for given peer */
+	struct dst_state	*state;
+
+	/* Block IO machinery */
+	struct request_queue	*queue;
+	struct gendisk		*disk;
+
+	/* Number of threads in processing pool */
+	int			thread_num;
+	/* Maximum number of pages in single IO */
+	int			max_pages;
+
+	/* I'm that big in bytes */
+	loff_t			size;
+
+	/* Exported to userspace node information */
+	struct dst_info		*info;
+
+	/*
+	 * Security attribute list.
+	 * Used only by exporting node currently.
+	 */
+	struct list_head	security_list;
+	struct mutex		security_lock;
+
+	/*
+	 * When this unerflows below zero, university collapses.
+	 * But this will not happen, since node will be freed,
+	 * when reference counter reaches zero.
+	 */
+	atomic_t		refcnt;
+
+	/* How precisely should I be started? */
+	int 			(*start)(struct dst_node *);
+
+	/* Crypto capabilities */
+	struct dst_crypto_ctl	crypto;
+	u8			*hash_key;
+	u8			*cipher_key;
+
+	/* Pool of processing thread */
+	struct thread_pool	*pool;
+
+	/* Transaction IDs live here */
+	atomic_long_t		gen;
+
+	/*
+	 * How frequently and how many times transaction
+	 * tree should be scanned to drop stale objects.
+	 */
+	long			trans_scan_timeout;
+	int			trans_max_retries;
+
+	/* Small gnomes live here */
+	struct rb_root		trans_root;
+	struct mutex		trans_lock;
+
+	/*
+	 * Transaction cache/memory pool.
+	 * It is big enough to contain not only transaction
+	 * itself, but additional crypto data (digest/hmac).
+	 */
+	struct kmem_cache	*trans_cache;
+	mempool_t		*trans_pool;
+
+	/* This entity scans transaction tree */
+	struct delayed_work 	trans_work;
+
+	wait_queue_head_t	wait;
+};
+
+/* Kernel representation of the security attribute */
+struct dst_secure
+{
+	struct list_head	sec_entry;
+	struct dst_secure_user	sec;
+};
+
+int dst_process_bio(struct dst_node *n, struct bio *bio);
+
+int dst_node_init_connected(struct dst_node *n, struct dst_network_ctl *r);
+int dst_node_init_listened(struct dst_node *n, struct dst_export_ctl *le);
+
+static inline struct dst_state *dst_state_get(struct dst_state *st)
+{
+	BUG_ON(atomic_read(&st->refcnt) == 0);
+	atomic_inc(&st->refcnt);
+	return st;
+}
+
+void dst_state_put(struct dst_state *st);
+
+struct dst_state *dst_state_alloc(struct dst_node *n);
+int dst_state_socket_create(struct dst_state *st);
+void dst_state_socket_release(struct dst_state *st);
+
+void dst_state_exit_connected(struct dst_state *st);
+
+int dst_state_schedule_receiver(struct dst_state *st);
+
+void dst_dump_addr(struct socket *sk, struct sockaddr *sa, char *str);
+
+static inline void dst_state_lock(struct dst_state *st)
+{
+	mutex_lock(&st->state_lock);
+}
+
+static inline void dst_state_unlock(struct dst_state *st)
+{
+	mutex_unlock(&st->state_lock);
+}
+
+void dst_poll_exit(struct dst_state *st);
+int dst_poll_init(struct dst_state *st);
+
+static inline unsigned int dst_state_poll(struct dst_state *st)
+{
+	unsigned int revents = POLLHUP | POLLERR;
+
+	dst_state_lock(st);
+	if (st->socket)
+		revents = st->socket->ops->poll(NULL, st->socket, NULL);
+	dst_state_unlock(st);
+
+	return revents;
+}
+
+static inline int dst_thread_setup(void *private, void *data)
+{
+	return 0;
+}
+
+void dst_node_put(struct dst_node *n);
+
+static inline struct dst_node *dst_node_get(struct dst_node *n)
+{
+	atomic_inc(&n->refcnt);
+	return n;
+}
+
+int dst_data_recv(struct dst_state *st, void *data, unsigned int size);
+int dst_recv_cdata(struct dst_state *st, void *cdata);
+int dst_data_send_header(struct socket *sock,
+		void *data, unsigned int size, int more);
+
+int dst_send_bio(struct dst_state *st, struct dst_cmd *cmd, struct bio *bio);
+
+int dst_process_io(struct dst_state *st);
+int dst_export_crypto(struct dst_node *n, struct bio *bio);
+int dst_export_send_bio(struct bio *bio);
+int dst_start_export(struct dst_node *n);
+
+int __init dst_export_init(void);
+void dst_export_exit(void);
+
+/* Private structure for export block IO requests */
+struct dst_export_priv
+{
+	struct list_head		request_entry;
+	struct dst_state		*state;
+	struct bio			*bio;
+	struct dst_cmd			cmd;
+};
+
+static inline void dst_trans_get(struct dst_trans *t)
+{
+	atomic_inc(&t->refcnt);
+}
+
+struct dst_trans *dst_trans_search(struct dst_node *node, dst_gen_t gen);
+int dst_trans_remove(struct dst_trans *t);
+int dst_trans_remove_nolock(struct dst_trans *t);
+void dst_trans_put(struct dst_trans *t);
+
+/*
+ * Convert bio into network command.
+ */
+static inline void dst_bio_to_cmd(struct bio *bio, struct dst_cmd *cmd,
+		u32 command, u64 id)
+{
+	cmd->cmd = command;
+	cmd->flags = (bio->bi_flags << BIO_POOL_BITS) >> BIO_POOL_BITS;
+	cmd->rw = bio->bi_rw;
+	cmd->size = bio->bi_size;
+	cmd->csize = 0;
+	cmd->id = id;
+	cmd->sector = bio->bi_sector;
+};
+
+int dst_trans_send(struct dst_trans *t);
+int dst_trans_crypto(struct dst_trans *t);
+
+int dst_node_crypto_init(struct dst_node *n, struct dst_crypto_ctl *ctl);
+void dst_node_crypto_exit(struct dst_node *n);
+
+static inline int dst_need_crypto(struct dst_node *n)
+{
+	struct dst_crypto_ctl *c = &n->crypto;
+	/*
+	 * Logical OR is appropriate here, but boolean one produces
+	 * more optimal code, so it is used instead.
+	 */
+	return (c->hash_algo[0] | c->cipher_algo[0]);
+}
+
+int dst_node_trans_init(struct dst_node *n, unsigned int size);
+void dst_node_trans_exit(struct dst_node *n);
+
+/*
+ * Pool of threads.
+ * Ready list contains threads currently free to be used,
+ * active one contains threads with some work scheduled for them.
+ * Caller can wait in given queue when thread is ready.
+ */
+struct thread_pool
+{
+	int			thread_num;
+	struct mutex		thread_lock;
+	struct list_head	ready_list, active_list;
+
+	wait_queue_head_t	wait;
+};
+
+void thread_pool_del_worker(struct thread_pool *p);
+void thread_pool_del_worker_id(struct thread_pool *p, unsigned int id);
+int thread_pool_add_worker(struct thread_pool *p,
+		char *name,
+		unsigned int id,
+		void *(* init)(void *data),
+		void (* cleanup)(void *data),
+		void *data);
+
+void thread_pool_destroy(struct thread_pool *p);
+struct thread_pool *thread_pool_create(int num, char *name,
+		void *(* init)(void *data),
+		void (* cleanup)(void *data),
+		void *data);
+
+int thread_pool_schedule(struct thread_pool *p,
+		int (* setup)(void *stored_private, void *setup_data),
+		int (* action)(void *stored_private, void *setup_data),
+		void *setup_data, long timeout);
+int thread_pool_schedule_private(struct thread_pool *p,
+		int (* setup)(void *private, void *data),
+		int (* action)(void *private, void *data),
+		void *data, long timeout, void *id);
+
+#endif /* __KERNEL__ */
+#endif /* __DST_H */

include/linux/dynamic_debug.h

@@ -70,7 +70,7 @@ extern int ddebug_remove_module(char *mod_name);
 		DEBUG_HASH2, __LINE__, _DPRINTK_FLAGS_DEFAULT };	\
 	if (__dynamic_dbg_enabled(descriptor))				\
 			dev_printk(KERN_DEBUG, dev,			\
-					KBUILD_MODNAME ": " pr_fmt(fmt),\
+					KBUILD_MODNAME ": " fmt,	\
 					##__VA_ARGS__);			\
 	} while (0)
 

include/linux/elevator.h

@@ -116,6 +116,7 @@ extern void elv_abort_queue(struct request_queue *);
 extern void elv_completed_request(struct request_queue *, struct request *);
 extern int elv_set_request(struct request_queue *, struct request *, gfp_t);
 extern void elv_put_request(struct request_queue *, struct request *);
+extern void elv_drain_elevator(struct request_queue *);
 
 /*
  * io scheduler registration

include/linux/fb.h

@@ -173,8 +173,12 @@ struct fb_fix_screeninfo {
 /* Interpretation of offset for color fields: All offsets are from the right,
  * inside a "pixel" value, which is exactly 'bits_per_pixel' wide (means: you
  * can use the offset as right argument to <<). A pixel afterwards is a bit
- * stream and is written to video memory as that unmodified. This implies
- * big-endian byte order if bits_per_pixel is greater than 8.
+ * stream and is written to video memory as that unmodified.
+ *
+ * For pseudocolor: offset and length should be the same for all color
+ * components. Offset specifies the position of the least significant bit
+ * of the pallette index in a pixel value. Length indicates the number
+ * of available palette entries (i.e. # of entries = 1 << length).
  */
 struct fb_bitfield {
 	__u32 offset;			/* beginning of bitfield	*/

include/linux/fdtable.h

@@ -5,12 +5,14 @@
 #ifndef __LINUX_FDTABLE_H
 #define __LINUX_FDTABLE_H
 
-#include <asm/atomic.h>
 #include <linux/posix_types.h>
 #include <linux/compiler.h>
 #include <linux/spinlock.h>
 #include <linux/rcupdate.h>
 #include <linux/types.h>
+#include <linux/init.h>
+
+#include <asm/atomic.h>
 
 /*
  * The default fd array needs to be at least BITS_PER_LONG,

include/linux/fiemap.h

@@ -11,6 +11,8 @@
 #ifndef _LINUX_FIEMAP_H
 #define _LINUX_FIEMAP_H
 
+#include <linux/types.h>
+
 struct fiemap_extent {
 	__u64 fe_logical;  /* logical offset in bytes for the start of
 			    * the extent from the beginning of the file */

include/linux/fs.h

@@ -87,6 +87,60 @@ struct inodes_stat_t {
  */
 #define FMODE_NOCMTIME		((__force fmode_t)2048)
 
+/*
+ * The below are the various read and write types that we support. Some of
+ * them include behavioral modifiers that send information down to the
+ * block layer and IO scheduler. Terminology:
+ *
+ *	The block layer uses device plugging to defer IO a little bit, in
+ *	the hope that we will see more IO very shortly. This increases
+ *	coalescing of adjacent IO and thus reduces the number of IOs we
+ *	have to send to the device. It also allows for better queuing,
+ *	if the IO isn't mergeable. If the caller is going to be waiting
+ *	for the IO, then he must ensure that the device is unplugged so
+ *	that the IO is dispatched to the driver.
+ *
+ *	All IO is handled async in Linux. This is fine for background
+ *	writes, but for reads or writes that someone waits for completion
+ *	on, we want to notify the block layer and IO scheduler so that they
+ *	know about it. That allows them to make better scheduling
+ *	decisions. So when the below references 'sync' and 'async', it
+ *	is referencing this priority hint.
+ *
+ * With that in mind, the available types are:
+ *
+ * READ			A normal read operation. Device will be plugged.
+ * READ_SYNC		A synchronous read. Device is not plugged, caller can
+ *			immediately wait on this read without caring about
+ *			unplugging.
+ * READA		Used for read-ahead operations. Lower priority, and the
+ *			 block layer could (in theory) choose to ignore this
+ *			request if it runs into resource problems.
+ * WRITE		A normal async write. Device will be plugged.
+ * SWRITE		Like WRITE, but a special case for ll_rw_block() that
+ *			tells it to lock the buffer first. Normally a buffer
+ *			must be locked before doing IO.
+ * WRITE_SYNC_PLUG	Synchronous write. Identical to WRITE, but passes down
+ *			the hint that someone will be waiting on this IO
+ *			shortly. The device must still be unplugged explicitly,
+ *			WRITE_SYNC_PLUG does not do this as we could be
+ *			submitting more writes before we actually wait on any
+ *			of them.
+ * WRITE_SYNC		Like WRITE_SYNC_PLUG, but also unplugs the device
+ *			immediately after submission. The write equivalent
+ *			of READ_SYNC.
+ * WRITE_ODIRECT	Special case write for O_DIRECT only.
+ * SWRITE_SYNC
+ * SWRITE_SYNC_PLUG	Like WRITE_SYNC/WRITE_SYNC_PLUG, but locks the buffer.
+ *			See SWRITE.
+ * WRITE_BARRIER	Like WRITE, but tells the block layer that all
+ *			previously submitted writes must be safely on storage
+ *			before this one is started. Also guarantees that when
+ *			this write is complete, it itself is also safely on
+ *			storage. Prevents reordering of writes on both sides
+ *			of this IO.
+ *
+ */
 #define RW_MASK		1
 #define RWA_MASK	2
 #define READ 0
@@ -95,9 +149,18 @@ struct inodes_stat_t {
 #define SWRITE 3	/* for ll_rw_block() - wait for buffer lock */
 #define READ_SYNC	(READ | (1 << BIO_RW_SYNCIO) | (1 << BIO_RW_UNPLUG))
 #define READ_META	(READ | (1 << BIO_RW_META))
-#define WRITE_SYNC	(WRITE | (1 << BIO_RW_SYNCIO) | (1 << BIO_RW_UNPLUG))
-#define SWRITE_SYNC	(SWRITE | (1 << BIO_RW_SYNCIO) | (1 << BIO_RW_UNPLUG))
+#define WRITE_SYNC_PLUG	(WRITE | (1 << BIO_RW_SYNCIO) | (1 << BIO_RW_NOIDLE))
+#define WRITE_SYNC	(WRITE_SYNC_PLUG | (1 << BIO_RW_UNPLUG))
+#define WRITE_ODIRECT	(WRITE | (1 << BIO_RW_SYNCIO) | (1 << BIO_RW_UNPLUG))
+#define SWRITE_SYNC_PLUG	\
+			(SWRITE | (1 << BIO_RW_SYNCIO) | (1 << BIO_RW_NOIDLE))
+#define SWRITE_SYNC	(SWRITE_SYNC_PLUG | (1 << BIO_RW_UNPLUG))
 #define WRITE_BARRIER	(WRITE | (1 << BIO_RW_BARRIER))
+
+/*
+ * These aren't really reads or writes, they pass down information about
+ * parts of device that are now unused by the file system.
+ */
 #define DISCARD_NOBARRIER (1 << BIO_RW_DISCARD)
 #define DISCARD_BARRIER ((1 << BIO_RW_DISCARD) | (1 << BIO_RW_BARRIER))
 
@@ -734,9 +797,6 @@ enum inode_i_mutex_lock_class
 	I_MUTEX_QUOTA
 };
 
-extern void inode_double_lock(struct inode *inode1, struct inode *inode2);
-extern void inode_double_unlock(struct inode *inode1, struct inode *inode2);
-
 /*
  * NOTE: in a 32bit arch with a preemptable kernel and
  * an UP compile the i_size_read/write must be atomic
@@ -1695,6 +1755,9 @@ struct file_system_type {
 	struct lock_class_key i_alloc_sem_key;
 };
 
+extern int get_sb_ns(struct file_system_type *fs_type, int flags, void *data,
+	int (*fill_super)(struct super_block *, void *, int),
+	struct vfsmount *mnt);
 extern int get_sb_bdev(struct file_system_type *fs_type,
 	int flags, const char *dev_name, void *data,
 	int (*fill_super)(struct super_block *, void *, int),
@@ -1712,6 +1775,7 @@ void kill_block_super(struct super_block *sb);
 void kill_anon_super(struct super_block *sb);
 void kill_litter_super(struct super_block *sb);
 void deactivate_super(struct super_block *sb);
+void deactivate_locked_super(struct super_block *sb);
 int set_anon_super(struct super_block *s, void *data);
 struct super_block *sget(struct file_system_type *type,
 			int (*test)(struct super_block *,void *),
@@ -2054,7 +2118,7 @@ extern struct file *create_write_pipe(int flags);
 extern void free_write_pipe(struct file *);
 
 extern struct file *do_filp_open(int dfd, const char *pathname,
-		int open_flag, int mode);
+		int open_flag, int mode, int acc_mode);
 extern int may_open(struct path *, int, int);
 
 extern int kernel_read(struct file *, unsigned long, char *, unsigned long);
@@ -2143,8 +2207,6 @@ extern ssize_t generic_file_splice_read(struct file *, loff_t *,
 		struct pipe_inode_info *, size_t, unsigned int);
 extern ssize_t generic_file_splice_write(struct pipe_inode_info *,
 		struct file *, loff_t *, size_t, unsigned int);
-extern ssize_t generic_file_splice_write_nolock(struct pipe_inode_info *,
-		struct file *, loff_t *, size_t, unsigned int);
 extern ssize_t generic_splice_sendpage(struct pipe_inode_info *pipe,
 		struct file *out, loff_t *, size_t len, unsigned int flags);
 extern long do_splice_direct(struct file *in, loff_t *ppos, struct file *out,
@@ -2238,9 +2300,8 @@ extern int vfs_readdir(struct file *, filldir_t, void *);
 
 extern int vfs_stat(char __user *, struct kstat *);
 extern int vfs_lstat(char __user *, struct kstat *);
-extern int vfs_stat_fd(int dfd, char __user *, struct kstat *);
-extern int vfs_lstat_fd(int dfd, char __user *, struct kstat *);
 extern int vfs_fstat(unsigned int, struct kstat *);
+extern int vfs_fstatat(int , char __user *, struct kstat *, int);
 
 extern int do_vfs_ioctl(struct file *filp, unsigned int fd, unsigned int cmd,
 		    unsigned long arg);
@@ -2307,6 +2368,7 @@ extern void file_update_time(struct file *file);
 
 extern int generic_show_options(struct seq_file *m, struct vfsmount *mnt);
 extern void save_mount_options(struct super_block *sb, char *options);
+extern void replace_mount_options(struct super_block *sb, char *options);
 
 static inline ino_t parent_ino(struct dentry *dentry)
 {
@@ -2337,19 +2399,7 @@ ssize_t simple_transaction_read(struct file *file, char __user *buf,
 				size_t size, loff_t *pos);
 int simple_transaction_release(struct inode *inode, struct file *file);
 
-static inline void simple_transaction_set(struct file *file, size_t n)
-{
-	struct simple_transaction_argresp *ar = file->private_data;
-
-	BUG_ON(n > SIMPLE_TRANSACTION_LIMIT);
-
-	/*
-	 * The barrier ensures that ar->size will really remain zero until
-	 * ar->data is ready for reading.
-	 */
-	smp_mb();
-	ar->size = n;
-}
+void simple_transaction_set(struct file *file, size_t n);
 
 /*
  * simple attribute files
@@ -2396,32 +2446,11 @@ ssize_t simple_attr_read(struct file *file, char __user *buf,
 ssize_t simple_attr_write(struct file *file, const char __user *buf,
 			  size_t len, loff_t *ppos);
 
-
-#ifdef CONFIG_SECURITY
-static inline char *alloc_secdata(void)
-{
-	return (char *)get_zeroed_page(GFP_KERNEL);
-}
-
-static inline void free_secdata(void *secdata)
-{
-	free_page((unsigned long)secdata);
-}
-#else
-static inline char *alloc_secdata(void)
-{
-	return (char *)1;
-}
-
-static inline void free_secdata(void *secdata)
-{ }
-#endif	/* CONFIG_SECURITY */
-
 struct ctl_table;
 int proc_nr_files(struct ctl_table *table, int write, struct file *filp,
 		  void __user *buffer, size_t *lenp, loff_t *ppos);
 
-int get_filesystem_list(char * buf);
+int __init get_filesystem_list(char *buf);
 
 #endif /* __KERNEL__ */
 #endif /* _LINUX_FS_H */

include/linux/fsl_devices.h

@@ -18,7 +18,6 @@
 #define _FSL_DEVICE_H_
 
 #include <linux/types.h>
-#include <linux/phy.h>
 
 /*
  * Some conventions on how we handle peripherals on Freescale chips
@@ -44,31 +43,6 @@
  *
  */
 
-struct gianfar_platform_data {
-	/* device specific information */
-	u32	device_flags;
-	char	bus_id[BUS_ID_SIZE];
-	phy_interface_t interface;
-};
-
-struct gianfar_mdio_data {
-	/* board specific information */
-	int	irq[32];
-};
-
-/* Flags in gianfar_platform_data */
-#define FSL_GIANFAR_BRD_HAS_PHY_INTR	0x00000001 /* set or use a timer */
-#define FSL_GIANFAR_BRD_IS_REDUCED	0x00000002 /* Set if RGMII, RMII */
-
-struct fsl_i2c_platform_data {
-	/* device specific information */
-	u32	device_flags;
-};
-
-/* Flags related to I2C device features */
-#define FSL_I2C_DEV_SEPARATE_DFSRR	0x00000001
-#define FSL_I2C_DEV_CLOCK_5200		0x00000002
-
 enum fsl_usb2_operating_modes {
 	FSL_USB2_MPH_HOST,
 	FSL_USB2_DR_HOST,
@@ -105,6 +79,10 @@ struct fsl_spi_platform_data {
 	u16	max_chipselect;
 	void	(*cs_control)(struct spi_device *spi, bool on);
 	u32	sysclk;
+
+	/* Legacy hooks, used by mpc52xx_psc_spi driver. */
+	void	(*activate_cs)(u8 cs, u8 polarity);
+	void	(*deactivate_cs)(u8 cs, u8 polarity);
 };
 
 struct mpc8xx_pcmcia_ops {

include/linux/ftrace.h

@@ -1,15 +1,18 @@
 #ifndef _LINUX_FTRACE_H
 #define _LINUX_FTRACE_H
 
-#include <linux/linkage.h>
-#include <linux/fs.h>
-#include <linux/ktime.h>
-#include <linux/init.h>
-#include <linux/types.h>
-#include <linux/module.h>
+#include <linux/trace_clock.h>
 #include <linux/kallsyms.h>
+#include <linux/linkage.h>
 #include <linux/bitops.h>
+#include <linux/module.h>
+#include <linux/ktime.h>
 #include <linux/sched.h>
+#include <linux/types.h>
+#include <linux/init.h>
+#include <linux/fs.h>
+
+#include <asm/ftrace.h>
 
 #ifdef CONFIG_FUNCTION_TRACER
 
@@ -95,9 +98,41 @@ stack_trace_sysctl(struct ctl_table *table, int write,
 		   loff_t *ppos);
 #endif
 
+struct ftrace_func_command {
+	struct list_head	list;
+	char			*name;
+	int			(*func)(char *func, char *cmd,
+					char *params, int enable);
+};
+
 #ifdef CONFIG_DYNAMIC_FTRACE
-/* asm/ftrace.h must be defined for archs supporting dynamic ftrace */
-#include <asm/ftrace.h>
+
+int ftrace_arch_code_modify_prepare(void);
+int ftrace_arch_code_modify_post_process(void);
+
+struct seq_file;
+
+struct ftrace_probe_ops {
+	void			(*func)(unsigned long ip,
+					unsigned long parent_ip,
+					void **data);
+	int			(*callback)(unsigned long ip, void **data);
+	void			(*free)(void **data);
+	int			(*print)(struct seq_file *m,
+					 unsigned long ip,
+					 struct ftrace_probe_ops *ops,
+					 void *data);
+};
+
+extern int
+register_ftrace_function_probe(char *glob, struct ftrace_probe_ops *ops,
+			      void *data);
+extern void
+unregister_ftrace_function_probe(char *glob, struct ftrace_probe_ops *ops,
+				void *data);
+extern void
+unregister_ftrace_function_probe_func(char *glob, struct ftrace_probe_ops *ops);
+extern void unregister_ftrace_function_probe_all(char *glob);
 
 enum {
 	FTRACE_FL_FREE		= (1 << 0),
@@ -110,15 +145,23 @@ enum {
 };
 
 struct dyn_ftrace {
-	struct list_head	list;
-	unsigned long		ip; /* address of mcount call-site */
-	unsigned long		flags;
-	struct dyn_arch_ftrace	arch;
+	union {
+		unsigned long		ip; /* address of mcount call-site */
+		struct dyn_ftrace	*freelist;
+	};
+	union {
+		unsigned long		flags;
+		struct dyn_ftrace	*newlist;
+	};
+	struct dyn_arch_ftrace		arch;
 };
 
 int ftrace_force_update(void);
 void ftrace_set_filter(unsigned char *buf, int len, int reset);
 
+int register_ftrace_command(struct ftrace_func_command *cmd);
+int unregister_ftrace_command(struct ftrace_func_command *cmd);
+
 /* defined in arch */
 extern int ftrace_ip_converted(unsigned long ip);
 extern int ftrace_dyn_arch_init(void *data);
@@ -126,6 +169,10 @@ extern int ftrace_update_ftrace_func(ftrace_func_t func);
 extern void ftrace_caller(void);
 extern void ftrace_call(void);
 extern void mcount_call(void);
+
+#ifndef FTRACE_ADDR
+#define FTRACE_ADDR ((unsigned long)ftrace_caller)
+#endif
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
 extern void ftrace_graph_caller(void);
 extern int ftrace_enable_ftrace_graph_caller(void);
@@ -136,7 +183,7 @@ static inline int ftrace_disable_ftrace_graph_caller(void) { return 0; }
 #endif
 
 /**
- * ftrace_make_nop - convert code into top
+ * ftrace_make_nop - convert code into nop
  * @mod: module structure if called by module load initialization
  * @rec: the mcount call site record
  * @addr: the address that the call site should be calling
@@ -181,7 +228,6 @@ extern int ftrace_make_nop(struct module *mod,
  */
 extern int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr);
 
-
 /* May be defined in arch */
 extern int ftrace_arch_read_dyn_info(char *buf, int size);
 
@@ -198,6 +244,14 @@ extern void ftrace_enable_daemon(void);
 # define ftrace_disable_daemon()		do { } while (0)
 # define ftrace_enable_daemon()			do { } while (0)
 static inline void ftrace_release(void *start, unsigned long size) { }
+static inline int register_ftrace_command(struct ftrace_func_command *cmd)
+{
+	return -EINVAL;
+}
+static inline int unregister_ftrace_command(char *cmd_name)
+{
+	return -EINVAL;
+}
 #endif /* CONFIG_DYNAMIC_FTRACE */
 
 /* totally disable ftrace - can not re-enable after this */
@@ -233,24 +287,25 @@ static inline void __ftrace_enabled_restore(int enabled)
 #endif
 }
 
-#ifdef CONFIG_FRAME_POINTER
-/* TODO: need to fix this for ARM */
-# define CALLER_ADDR0 ((unsigned long)__builtin_return_address(0))
-# define CALLER_ADDR1 ((unsigned long)__builtin_return_address(1))
-# define CALLER_ADDR2 ((unsigned long)__builtin_return_address(2))
-# define CALLER_ADDR3 ((unsigned long)__builtin_return_address(3))
-# define CALLER_ADDR4 ((unsigned long)__builtin_return_address(4))
-# define CALLER_ADDR5 ((unsigned long)__builtin_return_address(5))
-# define CALLER_ADDR6 ((unsigned long)__builtin_return_address(6))
-#else
-# define CALLER_ADDR0 ((unsigned long)__builtin_return_address(0))
-# define CALLER_ADDR1 0UL
-# define CALLER_ADDR2 0UL
-# define CALLER_ADDR3 0UL
-# define CALLER_ADDR4 0UL
-# define CALLER_ADDR5 0UL
-# define CALLER_ADDR6 0UL
-#endif
+#ifndef HAVE_ARCH_CALLER_ADDR
+# ifdef CONFIG_FRAME_POINTER
+#  define CALLER_ADDR0 ((unsigned long)__builtin_return_address(0))
+#  define CALLER_ADDR1 ((unsigned long)__builtin_return_address(1))
+#  define CALLER_ADDR2 ((unsigned long)__builtin_return_address(2))
+#  define CALLER_ADDR3 ((unsigned long)__builtin_return_address(3))
+#  define CALLER_ADDR4 ((unsigned long)__builtin_return_address(4))
+#  define CALLER_ADDR5 ((unsigned long)__builtin_return_address(5))
+#  define CALLER_ADDR6 ((unsigned long)__builtin_return_address(6))
+# else
+#  define CALLER_ADDR0 ((unsigned long)__builtin_return_address(0))
+#  define CALLER_ADDR1 0UL
+#  define CALLER_ADDR2 0UL
+#  define CALLER_ADDR3 0UL
+#  define CALLER_ADDR4 0UL
+#  define CALLER_ADDR5 0UL
+#  define CALLER_ADDR6 0UL
+# endif
+#endif /* ifndef HAVE_ARCH_CALLER_ADDR */
 
 #ifdef CONFIG_IRQSOFF_TRACER
   extern void time_hardirqs_on(unsigned long a0, unsigned long a1);
@@ -268,54 +323,6 @@ static inline void __ftrace_enabled_restore(int enabled)
 # define trace_preempt_off(a0, a1)		do { } while (0)
 #endif
 
-#ifdef CONFIG_TRACING
-extern int ftrace_dump_on_oops;
-
-extern void tracing_start(void);
-extern void tracing_stop(void);
-extern void ftrace_off_permanent(void);
-
-extern void
-ftrace_special(unsigned long arg1, unsigned long arg2, unsigned long arg3);
-
-/**
- * ftrace_printk - printf formatting in the ftrace buffer
- * @fmt: the printf format for printing
- *
- * Note: __ftrace_printk is an internal function for ftrace_printk and
- *       the @ip is passed in via the ftrace_printk macro.
- *
- * This function allows a kernel developer to debug fast path sections
- * that printk is not appropriate for. By scattering in various
- * printk like tracing in the code, a developer can quickly see
- * where problems are occurring.
- *
- * This is intended as a debugging tool for the developer only.
- * Please refrain from leaving ftrace_printks scattered around in
- * your code.
- */
-# define ftrace_printk(fmt...) __ftrace_printk(_THIS_IP_, fmt)
-extern int
-__ftrace_printk(unsigned long ip, const char *fmt, ...)
-	__attribute__ ((format (printf, 2, 3)));
-extern void ftrace_dump(void);
-#else
-static inline void
-ftrace_special(unsigned long arg1, unsigned long arg2, unsigned long arg3) { }
-static inline int
-ftrace_printk(const char *fmt, ...) __attribute__ ((format (printf, 1, 2)));
-
-static inline void tracing_start(void) { }
-static inline void tracing_stop(void) { }
-static inline void ftrace_off_permanent(void) { }
-static inline int
-ftrace_printk(const char *fmt, ...)
-{
-	return 0;
-}
-static inline void ftrace_dump(void) { }
-#endif
-
 #ifdef CONFIG_FTRACE_MCOUNT_RECORD
 extern void ftrace_init(void);
 extern void ftrace_init_module(struct module *mod,
@@ -327,36 +334,6 @@ ftrace_init_module(struct module *mod,
 		   unsigned long *start, unsigned long *end) { }
 #endif
 
-enum {
-	POWER_NONE = 0,
-	POWER_CSTATE = 1,
-	POWER_PSTATE = 2,
-};
-
-struct power_trace {
-#ifdef CONFIG_POWER_TRACER
-	ktime_t			stamp;
-	ktime_t			end;
-	int			type;
-	int			state;
-#endif
-};
-
-#ifdef CONFIG_POWER_TRACER
-extern void trace_power_start(struct power_trace *it, unsigned int type,
-					unsigned int state);
-extern void trace_power_mark(struct power_trace *it, unsigned int type,
-					unsigned int state);
-extern void trace_power_end(struct power_trace *it);
-#else
-static inline void trace_power_start(struct power_trace *it, unsigned int type,
-					unsigned int state) { }
-static inline void trace_power_mark(struct power_trace *it, unsigned int type,
-					unsigned int state) { }
-static inline void trace_power_end(struct power_trace *it) { }
-#endif
-
-
 /*
  * Structure that defines an entry function trace.
  */
@@ -379,6 +356,9 @@ struct ftrace_graph_ret {
 
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
 
+/* for init task */
+#define INIT_FTRACE_GRAPH		.ret_stack = NULL,
+
 /*
  * Stack of return addresses for functions
  * of a thread.
@@ -398,8 +378,7 @@ struct ftrace_ret_stack {
 extern void return_to_handler(void);
 
 extern int
-ftrace_push_return_trace(unsigned long ret, unsigned long long time,
-			 unsigned long func, int *depth);
+ftrace_push_return_trace(unsigned long ret, unsigned long func, int *depth);
 extern void
 ftrace_pop_return_trace(struct ftrace_graph_ret *trace, unsigned long *ret);
 
@@ -454,10 +433,11 @@ static inline void unpause_graph_tracing(void)
 {
 	atomic_dec(&current->tracing_graph_pause);
 }
-#else
+#else /* !CONFIG_FUNCTION_GRAPH_TRACER */
 
 #define __notrace_funcgraph
 #define __irq_entry
+#define INIT_FTRACE_GRAPH
 
 static inline void ftrace_graph_init_task(struct task_struct *t) { }
 static inline void ftrace_graph_exit_task(struct task_struct *t) { }
@@ -469,7 +449,7 @@ static inline int task_curr_ret_stack(struct task_struct *tsk)
 
 static inline void pause_graph_tracing(void) { }
 static inline void unpause_graph_tracing(void) { }
-#endif
+#endif /* CONFIG_FUNCTION_GRAPH_TRACER */
 
 #ifdef CONFIG_TRACING
 #include <linux/sched.h>
@@ -514,6 +494,21 @@ static inline int test_tsk_trace_graph(struct task_struct *tsk)
 	return tsk->trace & TSK_TRACE_FL_GRAPH;
 }
 
+extern int ftrace_dump_on_oops;
+
 #endif /* CONFIG_TRACING */
 
+
+#ifdef CONFIG_HW_BRANCH_TRACER
+
+void trace_hw_branch(u64 from, u64 to);
+void trace_hw_branch_oops(void);
+
+#else /* CONFIG_HW_BRANCH_TRACER */
+
+static inline void trace_hw_branch(u64 from, u64 to) {}
+static inline void trace_hw_branch_oops(void) {}
+
+#endif /* CONFIG_HW_BRANCH_TRACER */
+
 #endif /* _LINUX_FTRACE_H */

include/linux/ftrace_irq.h

@@ -2,7 +2,7 @@
 #define _LINUX_FTRACE_IRQ_H
 
 
-#if defined(CONFIG_DYNAMIC_FTRACE) || defined(CONFIG_FUNCTION_GRAPH_TRACER)
+#ifdef CONFIG_FTRACE_NMI_ENTER
 extern void ftrace_nmi_enter(void);
 extern void ftrace_nmi_exit(void);
 #else

include/linux/genhd.h

@@ -214,6 +214,7 @@ static inline void disk_put_part(struct hd_struct *part)
 #define DISK_PITER_REVERSE	(1 << 0) /* iterate in the reverse direction */
 #define DISK_PITER_INCL_EMPTY	(1 << 1) /* include 0-sized parts */
 #define DISK_PITER_INCL_PART0	(1 << 2) /* include partition 0 */
+#define DISK_PITER_INCL_EMPTY_PART0 (1 << 3) /* include empty partition 0 */
 
 struct disk_part_iter {
 	struct gendisk		*disk;

include/linux/gfp.h

@@ -4,6 +4,7 @@
 #include <linux/mmzone.h>
 #include <linux/stddef.h>
 #include <linux/linkage.h>
+#include <linux/topology.h>
 
 struct vm_area_struct;
 

include/linux/hardirq.h

@@ -15,55 +15,61 @@
  * - bits 0-7 are the preemption count (max preemption depth: 256)
  * - bits 8-15 are the softirq count (max # of softirqs: 256)
  *
- * The hardirq count can be overridden per architecture, the default is:
+ * The hardirq count can in theory reach the same as NR_IRQS.
+ * In reality, the number of nested IRQS is limited to the stack
+ * size as well. For archs with over 1000 IRQS it is not practical
+ * to expect that they will all nest. We give a max of 10 bits for
+ * hardirq nesting. An arch may choose to give less than 10 bits.
+ * m68k expects it to be 8.
  *
- * - bits 16-27 are the hardirq count (max # of hardirqs: 4096)
- * - ( bit 28 is the PREEMPT_ACTIVE flag. )
+ * - bits 16-25 are the hardirq count (max # of nested hardirqs: 1024)
+ * - bit 26 is the NMI_MASK
+ * - bit 28 is the PREEMPT_ACTIVE flag
  *
  * PREEMPT_MASK: 0x000000ff
  * SOFTIRQ_MASK: 0x0000ff00
- * HARDIRQ_MASK: 0x0fff0000
+ * HARDIRQ_MASK: 0x03ff0000
+ *     NMI_MASK: 0x04000000
  */
 #define PREEMPT_BITS	8
 #define SOFTIRQ_BITS	8
+#define NMI_BITS	1
+
+#define MAX_HARDIRQ_BITS 10
 
 #ifndef HARDIRQ_BITS
-#define HARDIRQ_BITS	12
-
-#ifndef MAX_HARDIRQS_PER_CPU
-#define MAX_HARDIRQS_PER_CPU NR_IRQS
+# define HARDIRQ_BITS	MAX_HARDIRQ_BITS
 #endif
 
-/*
- * The hardirq mask has to be large enough to have space for potentially
- * all IRQ sources in the system nesting on a single CPU.
- */
-#if (1 << HARDIRQ_BITS) < MAX_HARDIRQS_PER_CPU
-# error HARDIRQ_BITS is too low!
-#endif
+#if HARDIRQ_BITS > MAX_HARDIRQ_BITS
+#error HARDIRQ_BITS too high!
 #endif
 
 #define PREEMPT_SHIFT	0
 #define SOFTIRQ_SHIFT	(PREEMPT_SHIFT + PREEMPT_BITS)
 #define HARDIRQ_SHIFT	(SOFTIRQ_SHIFT + SOFTIRQ_BITS)
+#define NMI_SHIFT	(HARDIRQ_SHIFT + HARDIRQ_BITS)
 
 #define __IRQ_MASK(x)	((1UL << (x))-1)
 
 #define PREEMPT_MASK	(__IRQ_MASK(PREEMPT_BITS) << PREEMPT_SHIFT)
 #define SOFTIRQ_MASK	(__IRQ_MASK(SOFTIRQ_BITS) << SOFTIRQ_SHIFT)
 #define HARDIRQ_MASK	(__IRQ_MASK(HARDIRQ_BITS) << HARDIRQ_SHIFT)
+#define NMI_MASK	(__IRQ_MASK(NMI_BITS)     << NMI_SHIFT)
 
 #define PREEMPT_OFFSET	(1UL << PREEMPT_SHIFT)
 #define SOFTIRQ_OFFSET	(1UL << SOFTIRQ_SHIFT)
 #define HARDIRQ_OFFSET	(1UL << HARDIRQ_SHIFT)
+#define NMI_OFFSET	(1UL << NMI_SHIFT)
 
-#if PREEMPT_ACTIVE < (1 << (HARDIRQ_SHIFT + HARDIRQ_BITS))
+#if PREEMPT_ACTIVE < (1 << (NMI_SHIFT + NMI_BITS))
 #error PREEMPT_ACTIVE is too low!
 #endif
 
 #define hardirq_count()	(preempt_count() & HARDIRQ_MASK)
 #define softirq_count()	(preempt_count() & SOFTIRQ_MASK)
-#define irq_count()	(preempt_count() & (HARDIRQ_MASK | SOFTIRQ_MASK))
+#define irq_count()	(preempt_count() & (HARDIRQ_MASK | SOFTIRQ_MASK \
+				 | NMI_MASK))
 
 /*
  * Are we doing bottom half or hardware interrupt processing?
@@ -73,6 +79,11 @@
 #define in_softirq()		(softirq_count())
 #define in_interrupt()		(irq_count())
 
+/*
+ * Are we in NMI context?
+ */
+#define in_nmi()	(preempt_count() & NMI_MASK)
+
 #if defined(CONFIG_PREEMPT)
 # define PREEMPT_INATOMIC_BASE kernel_locked()
 # define PREEMPT_CHECK_OFFSET 1
@@ -105,7 +116,7 @@
 # define IRQ_EXIT_OFFSET HARDIRQ_OFFSET
 #endif
 
-#ifdef CONFIG_SMP
+#if defined(CONFIG_SMP) || defined(CONFIG_GENERIC_HARDIRQS)
 extern void synchronize_irq(unsigned int irq);
 #else
 # define synchronize_irq(irq)	barrier()
@@ -164,20 +175,24 @@ extern void irq_enter(void);
  */
 extern void irq_exit(void);
 
-#define nmi_enter()				\
-	do {					\
-		ftrace_nmi_enter();		\
-		lockdep_off();			\
-		rcu_nmi_enter();		\
-		__irq_enter();			\
+#define nmi_enter()						\
+	do {							\
+		ftrace_nmi_enter();				\
+		BUG_ON(in_nmi());				\
+		add_preempt_count(NMI_OFFSET + HARDIRQ_OFFSET);	\
+		lockdep_off();					\
+		rcu_nmi_enter();				\
+		trace_hardirq_enter();				\
 	} while (0)
 
-#define nmi_exit()				\
-	do {					\
-		__irq_exit();			\
-		rcu_nmi_exit();			\
-		lockdep_on();			\
-		ftrace_nmi_exit();		\
+#define nmi_exit()						\
+	do {							\
+		trace_hardirq_exit();				\
+		rcu_nmi_exit();					\
+		lockdep_on();					\
+		BUG_ON(!in_nmi());				\
+		sub_preempt_count(NMI_OFFSET + HARDIRQ_OFFSET);	\
+		ftrace_nmi_exit();				\
 	} while (0)
 
 #endif /* LINUX_HARDIRQ_H */

include/linux/hrtimer.h

@@ -336,6 +336,11 @@ extern int hrtimer_start(struct hrtimer *timer, ktime_t tim,
 			 const enum hrtimer_mode mode);
 extern int hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim,
 			unsigned long range_ns, const enum hrtimer_mode mode);
+extern int
+__hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim,
+			 unsigned long delta_ns,
+			 const enum hrtimer_mode mode, int wakeup);
+
 extern int hrtimer_cancel(struct hrtimer *timer);
 extern int hrtimer_try_to_cancel(struct hrtimer *timer);
 

include/linux/i2c-algo-sgi.h

@@ -1,26 +0,0 @@
-/*
- * This file is subject to the terms and conditions of the GNU General Public
- * License version 2 as published by the Free Software Foundation.
- *
- * Copyright (C) 2003 Ladislav Michl <ladis@linux-mips.org>
- */
-
-#ifndef I2C_ALGO_SGI_H
-#define I2C_ALGO_SGI_H 1
-
-#include <linux/i2c.h>
-
-struct i2c_algo_sgi_data {
-	void *data;	/* private data for lowlevel routines */
-	unsigned (*getctrl)(void *data);
-	void (*setctrl)(void *data, unsigned val);
-	unsigned (*rdata)(void *data);
-	void (*wdata)(void *data, unsigned val);
-
-	int xfer_timeout;
-	int ack_timeout;
-};
-
-int i2c_sgi_add_bus(struct i2c_adapter *);
-
-#endif /* I2C_ALGO_SGI_H */

include/linux/i2c-id.h

@@ -33,47 +33,10 @@
 
 #define I2C_DRIVERID_MSP3400	 1
 #define I2C_DRIVERID_TUNER	 2
-#define I2C_DRIVERID_TEA6420	 5	/* audio matrix switch		*/
-#define I2C_DRIVERID_TEA6415C	 6	/* video matrix switch		*/
-#define I2C_DRIVERID_TDA9840	 7	/* stereo sound processor	*/
-#define I2C_DRIVERID_SAA7111A	 8	/* video input processor	*/
-#define I2C_DRIVERID_SAA7185B	13	/* video encoder		*/
-#define I2C_DRIVERID_SAA7110	22	/* video decoder		*/
-#define I2C_DRIVERID_SAA5249	24	/* SAA5249 and compatibles	*/
 #define I2C_DRIVERID_TDA7432	27	/* Stereo sound processor	*/
 #define I2C_DRIVERID_TVAUDIO    29      /* Generic TV sound driver      */
-#define I2C_DRIVERID_TDA9875    32      /* TV sound decoder chip        */
-#define I2C_DRIVERID_BT819	40     /* video decoder			*/
-#define I2C_DRIVERID_BT856	41     /* video encoder			*/
-#define I2C_DRIVERID_VPX3220	42     /* video decoder+vbi/vtxt	*/
-#define I2C_DRIVERID_ADV7175	48     /* ADV 7175/7176 video encoder	*/
-#define I2C_DRIVERID_SAA7114	49	/* video decoder		*/
-#define I2C_DRIVERID_ADV7170	54	/* video encoder		*/
-#define I2C_DRIVERID_SAA7191	57	/* video decoder		*/
-#define I2C_DRIVERID_INDYCAM	58	/* SGI IndyCam			*/
-#define I2C_DRIVERID_OVCAMCHIP	61	/* OmniVision CMOS image sens.	*/
-#define I2C_DRIVERID_SAA6752HS	67	/* MPEG2 encoder		*/
-#define I2C_DRIVERID_TVEEPROM	68	/* TV EEPROM			*/
-#define I2C_DRIVERID_WM8775	69	/* wm8775 audio processor	*/
-#define I2C_DRIVERID_CS53L32A	70	/* cs53l32a audio processor	*/
-#define I2C_DRIVERID_CX25840	71	/* cx2584x video encoder	*/
-#define I2C_DRIVERID_SAA7127	72	/* saa7127 video encoder	*/
 #define I2C_DRIVERID_SAA711X	73	/* saa711x video encoders	*/
 #define I2C_DRIVERID_INFRARED	75	/* I2C InfraRed on Video boards */
-#define I2C_DRIVERID_TVP5150	76	/* TVP5150 video decoder        */
-#define I2C_DRIVERID_WM8739	77	/* wm8739 audio processor	*/
-#define I2C_DRIVERID_UPD64083	78	/* upd64083 video processor	*/
-#define I2C_DRIVERID_UPD64031A	79	/* upd64031a video processor	*/
-#define I2C_DRIVERID_SAA717X	80	/* saa717x video encoder	*/
-#define I2C_DRIVERID_BT866	85	/* Conexant bt866 video encoder */
-#define I2C_DRIVERID_KS0127	86	/* Samsung ks0127 video decoder */
-#define I2C_DRIVERID_TLV320AIC23B 87	/* TI TLV320AIC23B audio codec  */
-#define I2C_DRIVERID_VP27SMPX	93	/* Panasonic VP27s tuner internal MPX */
-#define I2C_DRIVERID_M52790 	95      /* Mitsubishi M52790SP/FP AV switch */
-#define I2C_DRIVERID_CS5345	96	/* cs5345 audio processor	*/
-#define I2C_DRIVERID_AU8522	97	/* Auvitek au8522       */
-
-#define I2C_DRIVERID_OV7670 1048	/* Omnivision 7670 camera */
 
 /*
  * ---- Adapter types ----------------------------------------------------
@@ -88,6 +51,7 @@
 #define I2C_HW_B_CX2341X	0x010020 /* Conexant CX2341X MPEG encoder cards */
 #define I2C_HW_B_CX23885	0x010022 /* conexant 23885 based tv cards (bus1) */
 #define I2C_HW_B_AU0828		0x010023 /* auvitek au0828 usb bridge */
+#define I2C_HW_B_CX231XX	0x010024 /* Conexant CX231XX USB based cards */
 #define I2C_HW_B_HDPVR		0x010025 /* Hauppauge HD PVR */
 
 /* --- SGI adapters							*/

include/linux/i2c.h

@@ -274,7 +274,7 @@ struct i2c_board_info {
  * are provided using conventional syntax.
  */
 #define I2C_BOARD_INFO(dev_type, dev_addr) \
-	.type = (dev_type), .addr = (dev_addr)
+	.type = dev_type, .addr = (dev_addr)
 
 
 /* Add-on boards should register/unregister their devices; e.g. a board
@@ -353,8 +353,8 @@ struct i2c_adapter {
 	void *algo_data;
 
 	/* --- administration stuff. */
-	int (*client_register)(struct i2c_client *);
-	int (*client_unregister)(struct i2c_client *);
+	int (*client_register)(struct i2c_client *) __deprecated;
+	int (*client_unregister)(struct i2c_client *) __deprecated;
 
 	/* data fields that are valid for all devices	*/
 	u8 level; 			/* nesting level for lockdep */

include/linux/i2c/s6000.h

@@ -0,0 +1,10 @@
+#ifndef __LINUX_I2C_S6000_H
+#define __LINUX_I2C_S6000_H
+
+struct s6_i2c_platform_data {
+	const char *clock; /* the clock to use */
+	int bus_num; /* the bus number to register */
+};
+
+#endif
+

include/linux/ide.h

@@ -239,66 +239,39 @@ typedef enum {
 	ide_started,	/* a drive operation was started, handler was set */
 } ide_startstop_t;
 
+enum {
+	IDE_VALID_ERROR 		= (1 << 1),
+	IDE_VALID_FEATURE		= IDE_VALID_ERROR,
+	IDE_VALID_NSECT 		= (1 << 2),
+	IDE_VALID_LBAL			= (1 << 3),
+	IDE_VALID_LBAM			= (1 << 4),
+	IDE_VALID_LBAH			= (1 << 5),
+	IDE_VALID_DEVICE		= (1 << 6),
+	IDE_VALID_LBA			= IDE_VALID_LBAL |
+					  IDE_VALID_LBAM |
+					  IDE_VALID_LBAH,
+	IDE_VALID_OUT_TF		= IDE_VALID_FEATURE |
+					  IDE_VALID_NSECT |
+					  IDE_VALID_LBA,
+	IDE_VALID_IN_TF 		= IDE_VALID_NSECT |
+					  IDE_VALID_LBA,
+	IDE_VALID_OUT_HOB		= IDE_VALID_OUT_TF,
+	IDE_VALID_IN_HOB		= IDE_VALID_ERROR |
+					  IDE_VALID_NSECT |
+					  IDE_VALID_LBA,
+};
+
 enum {
 	IDE_TFLAG_LBA48			= (1 << 0),
-	IDE_TFLAG_OUT_HOB_FEATURE	= (1 << 1),
-	IDE_TFLAG_OUT_HOB_NSECT		= (1 << 2),
-	IDE_TFLAG_OUT_HOB_LBAL		= (1 << 3),
-	IDE_TFLAG_OUT_HOB_LBAM		= (1 << 4),
-	IDE_TFLAG_OUT_HOB_LBAH		= (1 << 5),
-	IDE_TFLAG_OUT_HOB		= IDE_TFLAG_OUT_HOB_FEATURE |
-					  IDE_TFLAG_OUT_HOB_NSECT |
-					  IDE_TFLAG_OUT_HOB_LBAL |
-					  IDE_TFLAG_OUT_HOB_LBAM |
-					  IDE_TFLAG_OUT_HOB_LBAH,
-	IDE_TFLAG_OUT_FEATURE		= (1 << 6),
-	IDE_TFLAG_OUT_NSECT		= (1 << 7),
-	IDE_TFLAG_OUT_LBAL		= (1 << 8),
-	IDE_TFLAG_OUT_LBAM		= (1 << 9),
-	IDE_TFLAG_OUT_LBAH		= (1 << 10),
-	IDE_TFLAG_OUT_TF		= IDE_TFLAG_OUT_FEATURE |
-					  IDE_TFLAG_OUT_NSECT |
-					  IDE_TFLAG_OUT_LBAL |
-					  IDE_TFLAG_OUT_LBAM |
-					  IDE_TFLAG_OUT_LBAH,
-	IDE_TFLAG_OUT_DEVICE		= (1 << 11),
-	IDE_TFLAG_WRITE			= (1 << 12),
-	IDE_TFLAG_CUSTOM_HANDLER	= (1 << 13),
-	IDE_TFLAG_DMA_PIO_FALLBACK	= (1 << 14),
-	IDE_TFLAG_IN_HOB_ERROR		= (1 << 15),
-	IDE_TFLAG_IN_HOB_NSECT		= (1 << 16),
-	IDE_TFLAG_IN_HOB_LBAL		= (1 << 17),
-	IDE_TFLAG_IN_HOB_LBAM		= (1 << 18),
-	IDE_TFLAG_IN_HOB_LBAH		= (1 << 19),
-	IDE_TFLAG_IN_HOB_LBA		= IDE_TFLAG_IN_HOB_LBAL |
-					  IDE_TFLAG_IN_HOB_LBAM |
-					  IDE_TFLAG_IN_HOB_LBAH,
-	IDE_TFLAG_IN_HOB		= IDE_TFLAG_IN_HOB_ERROR |
-					  IDE_TFLAG_IN_HOB_NSECT |
-					  IDE_TFLAG_IN_HOB_LBA,
-	IDE_TFLAG_IN_ERROR		= (1 << 20),
-	IDE_TFLAG_IN_NSECT		= (1 << 21),
-	IDE_TFLAG_IN_LBAL		= (1 << 22),
-	IDE_TFLAG_IN_LBAM		= (1 << 23),
-	IDE_TFLAG_IN_LBAH		= (1 << 24),
-	IDE_TFLAG_IN_LBA		= IDE_TFLAG_IN_LBAL |
-					  IDE_TFLAG_IN_LBAM |
-					  IDE_TFLAG_IN_LBAH,
-	IDE_TFLAG_IN_TF			= IDE_TFLAG_IN_NSECT |
-					  IDE_TFLAG_IN_LBA,
-	IDE_TFLAG_IN_DEVICE		= (1 << 25),
-	IDE_TFLAG_HOB			= IDE_TFLAG_OUT_HOB |
-					  IDE_TFLAG_IN_HOB,
-	IDE_TFLAG_TF			= IDE_TFLAG_OUT_TF |
-					  IDE_TFLAG_IN_TF,
-	IDE_TFLAG_DEVICE		= IDE_TFLAG_OUT_DEVICE |
-					  IDE_TFLAG_IN_DEVICE,
+	IDE_TFLAG_WRITE			= (1 << 1),
+	IDE_TFLAG_CUSTOM_HANDLER	= (1 << 2),
+	IDE_TFLAG_DMA_PIO_FALLBACK	= (1 << 3),
 	/* force 16-bit I/O operations */
-	IDE_TFLAG_IO_16BIT		= (1 << 26),
+	IDE_TFLAG_IO_16BIT		= (1 << 4),
 	/* struct ide_cmd was allocated using kmalloc() */
-	IDE_TFLAG_DYN			= (1 << 27),
-	IDE_TFLAG_FS			= (1 << 28),
-	IDE_TFLAG_MULTI_PIO		= (1 << 29),
+	IDE_TFLAG_DYN			= (1 << 5),
+	IDE_TFLAG_FS			= (1 << 6),
+	IDE_TFLAG_MULTI_PIO		= (1 << 7),
 };
 
 enum {
@@ -309,45 +282,34 @@ enum {
 };
 
 struct ide_taskfile {
-	u8	hob_data;	/*  0: high data byte (for TASKFILE IOCTL) */
-				/*  1-5: additional data to support LBA48 */
-	union {
-		u8 hob_error;	/*   read: error */
-		u8 hob_feature;	/*  write: feature */
+	u8	data;		/* 0: data byte (for TASKFILE ioctl) */
+	union {			/* 1: */
+		u8 error;	/*  read: error */
+		u8 feature;	/* write: feature */
 	};
-
-	u8	hob_nsect;
-	u8	hob_lbal;
-	u8	hob_lbam;
-	u8	hob_lbah;
-
-	u8	data;		/*  6: low data byte (for TASKFILE IOCTL) */
-
-	union {			/*  7: */
-		u8 error;	/*   read:  error */
-		u8 feature;	/*  write: feature */
-	};
-
-	u8	nsect;		/*  8: number of sectors */
-	u8	lbal;		/*  9: LBA low */
-	u8	lbam;		/* 10: LBA mid */
-	u8	lbah;		/* 11: LBA high */
-
-	u8	device;		/* 12: device select */
-
-	union {			/* 13: */
-		u8 status;	/*  read: status  */
+	u8	nsect;		/* 2: number of sectors */
+	u8	lbal;		/* 3: LBA low */
+	u8	lbam;		/* 4: LBA mid */
+	u8	lbah;		/* 5: LBA high */
+	u8	device;		/* 6: device select */
+	union {			/* 7: */
+		u8 status;	/*  read: status */
 		u8 command;	/* write: command */
 	};
 };
 
 struct ide_cmd {
-	union {
-		struct ide_taskfile	tf;
-		u8			tf_array[14];
-	};
+	struct ide_taskfile	tf;
+	struct ide_taskfile	hob;
+	struct {
+		struct {
+			u8		tf;
+			u8		hob;
+		} out, in;
+	} valid;
+
+	u8			tf_flags;
 	u8			ftf_flags;	/* for TASKFILE ioctl */
-	u32			tf_flags;
 	int			protocol;
 
 	int			sg_nents;	  /* number of sg entries */
@@ -662,8 +624,8 @@ struct ide_tp_ops {
 	void	(*write_devctl)(struct hwif_s *, u8);
 
 	void	(*dev_select)(ide_drive_t *);
-	void	(*tf_load)(ide_drive_t *, struct ide_cmd *);
-	void	(*tf_read)(ide_drive_t *, struct ide_cmd *);
+	void	(*tf_load)(ide_drive_t *, struct ide_taskfile *, u8);
+	void	(*tf_read)(ide_drive_t *, struct ide_taskfile *, u8);
 
 	void	(*input_data)(ide_drive_t *, struct ide_cmd *,
 			      void *, unsigned int);
@@ -1162,7 +1124,8 @@ extern int ide_devset_execute(ide_drive_t *drive,
 void ide_complete_cmd(ide_drive_t *, struct ide_cmd *, u8, u8);
 int ide_complete_rq(ide_drive_t *, int, unsigned int);
 
-void ide_tf_dump(const char *, struct ide_taskfile *);
+void ide_tf_readback(ide_drive_t *drive, struct ide_cmd *cmd);
+void ide_tf_dump(const char *, struct ide_cmd *);
 
 void ide_exec_command(ide_hwif_t *, u8);
 u8 ide_read_status(ide_hwif_t *);
@@ -1170,8 +1133,8 @@ u8 ide_read_altstatus(ide_hwif_t *);
 void ide_write_devctl(ide_hwif_t *, u8);
 
 void ide_dev_select(ide_drive_t *);
-void ide_tf_load(ide_drive_t *, struct ide_cmd *);
-void ide_tf_read(ide_drive_t *, struct ide_cmd *);
+void ide_tf_load(ide_drive_t *, struct ide_taskfile *, u8);
+void ide_tf_read(ide_drive_t *, struct ide_taskfile *, u8);
 
 void ide_input_data(ide_drive_t *, struct ide_cmd *, void *, unsigned int);
 void ide_output_data(ide_drive_t *, struct ide_cmd *, void *, unsigned int);
@@ -1529,7 +1492,7 @@ static inline void ide_set_hwifdata (ide_hwif_t * hwif, void *data)
 
 extern void ide_toggle_bounce(ide_drive_t *drive, int on);
 
-u64 ide_get_lba_addr(struct ide_taskfile *, int);
+u64 ide_get_lba_addr(struct ide_cmd *, int);
 u8 ide_dump_status(ide_drive_t *, const char *, u8);
 
 struct ide_timing {

include/linux/init.h

@@ -2,6 +2,8 @@
 #define _LINUX_INIT_H
 
 #include <linux/compiler.h>
+#include <linux/section-names.h>
+#include <linux/stringify.h>
 
 /* These macros are used to mark some functions or 
  * initialized data (doesn't apply to uninitialized data)
@@ -60,14 +62,6 @@
 #define __refdata        __section(.ref.data)
 #define __refconst       __section(.ref.rodata)
 
-/* backward compatibility note
- *  A few places hardcode the old section names:
- *  .text.init.refok
- *  .data.init.refok
- *  .exit.text.refok
- *  They should be converted to use the defines from this file
- */
-
 /* compatibility defines */
 #define __init_refok     __ref
 #define __initdata_refok __refdata
@@ -107,7 +101,7 @@
 #define __memexitconst   __section(.memexit.rodata)
 
 /* For assembly routines */
-#define __HEAD		.section	".head.text","ax"
+#define __HEAD		.section	__stringify(HEAD_TEXT_SECTION),"ax"
 #define __INIT		.section	".init.text","ax"
 #define __FINIT		.previous
 
@@ -247,6 +241,7 @@ struct obs_kernel_param {
 
 /* Relies on boot_command_line being set */
 void __init parse_early_param(void);
+void __init parse_early_options(char *cmdline);
 #endif /* __ASSEMBLY__ */
 
 /**

include/linux/init_task.h

@@ -5,6 +5,7 @@
 #include <linux/irqflags.h>
 #include <linux/utsname.h>
 #include <linux/lockdep.h>
+#include <linux/ftrace.h>
 #include <linux/ipc.h>
 #include <linux/pid_namespace.h>
 #include <linux/user_namespace.h>
@@ -14,19 +15,6 @@
 extern struct files_struct init_files;
 extern struct fs_struct init_fs;
 
-#define INIT_KIOCTX(name, which_mm) \
-{							\
-	.users		= ATOMIC_INIT(1),		\
-	.dead		= 0,				\
-	.mm		= &which_mm,			\
-	.user_id	= 0,				\
-	.next		= NULL,				\
-	.wait		= __WAIT_QUEUE_HEAD_INITIALIZER(name.wait), \
-	.ctx_lock	= __SPIN_LOCK_UNLOCKED(name.ctx_lock), \
-	.reqs_active	= 0U,				\
-	.max_reqs	= ~0U,				\
-}
-
 #define INIT_MM(name) \
 {			 					\
 	.mm_rb		= RB_ROOT,				\
@@ -185,6 +173,7 @@ extern struct cred init_cred;
 	INIT_IDS							\
 	INIT_TRACE_IRQFLAGS						\
 	INIT_LOCKDEP							\
+	INIT_FTRACE_GRAPH						\
 }
 
 

include/linux/input.h

@@ -106,6 +106,7 @@ struct input_absinfo {
 
 #define SYN_REPORT		0
 #define SYN_CONFIG		1
+#define SYN_MT_REPORT		2
 
 /*
  * Keys and buttons
@@ -445,6 +446,7 @@ struct input_absinfo {
 #define BTN_STYLUS2		0x14c
 #define BTN_TOOL_DOUBLETAP	0x14d
 #define BTN_TOOL_TRIPLETAP	0x14e
+#define BTN_TOOL_QUADTAP	0x14f	/* Four fingers on trackpad */
 
 #define BTN_WHEEL		0x150
 #define BTN_GEAR_DOWN		0x150
@@ -644,6 +646,17 @@ struct input_absinfo {
 #define ABS_TOOL_WIDTH		0x1c
 #define ABS_VOLUME		0x20
 #define ABS_MISC		0x28
+
+#define ABS_MT_TOUCH_MAJOR	0x30	/* Major axis of touching ellipse */
+#define ABS_MT_TOUCH_MINOR	0x31	/* Minor axis (omit if circular) */
+#define ABS_MT_WIDTH_MAJOR	0x32	/* Major axis of approaching ellipse */
+#define ABS_MT_WIDTH_MINOR	0x33	/* Minor axis (omit if circular) */
+#define ABS_MT_ORIENTATION	0x34	/* Ellipse orientation */
+#define ABS_MT_POSITION_X	0x35	/* Center X ellipse position */
+#define ABS_MT_POSITION_Y	0x36	/* Center Y ellipse position */
+#define ABS_MT_TOOL_TYPE	0x37	/* Type of touching device */
+#define ABS_MT_BLOB_ID		0x38	/* Group a set of packets as a blob */
+
 #define ABS_MAX			0x3f
 #define ABS_CNT			(ABS_MAX+1)
 
@@ -742,6 +755,12 @@ struct input_absinfo {
 #define BUS_GSC			0x1A
 #define BUS_ATARI		0x1B
 
+/*
+ * MT_TOOL types
+ */
+#define MT_TOOL_FINGER		0
+#define MT_TOOL_PEN		1
+
 /*
  * Values describing the status of a force-feedback effect
  */
@@ -1311,6 +1330,11 @@ static inline void input_sync(struct input_dev *dev)
 	input_event(dev, EV_SYN, SYN_REPORT, 0);
 }
 
+static inline void input_mt_sync(struct input_dev *dev)
+{
+	input_event(dev, EV_SYN, SYN_MT_REPORT, 0);
+}
+
 void input_set_capability(struct input_dev *dev, unsigned int type, unsigned int code);
 
 static inline void input_set_abs_params(struct input_dev *dev, int axis, int min, int max, int fuzz, int flat)

include/linux/intel-iommu.h

@@ -164,6 +164,7 @@ static inline void dmar_writeq(void __iomem *addr, u64 val)
 #define DMA_GCMD_QIE (((u32)1) << 26)
 #define DMA_GCMD_SIRTP (((u32)1) << 24)
 #define DMA_GCMD_IRE (((u32) 1) << 25)
+#define DMA_GCMD_CFI (((u32) 1) << 23)
 
 /* GSTS_REG */
 #define DMA_GSTS_TES (((u32)1) << 31)
@@ -174,6 +175,7 @@ static inline void dmar_writeq(void __iomem *addr, u64 val)
 #define DMA_GSTS_QIES (((u32)1) << 26)
 #define DMA_GSTS_IRTPS (((u32)1) << 24)
 #define DMA_GSTS_IRES (((u32)1) << 25)
+#define DMA_GSTS_CFIS (((u32)1) << 23)
 
 /* CCMD_REG */
 #define DMA_CCMD_ICC (((u64)1) << 63)
@@ -284,6 +286,14 @@ struct iommu_flush {
 		unsigned int size_order, u64 type, int non_present_entry_flush);
 };
 
+enum {
+	SR_DMAR_FECTL_REG,
+	SR_DMAR_FEDATA_REG,
+	SR_DMAR_FEADDR_REG,
+	SR_DMAR_FEUADDR_REG,
+	MAX_SR_DMAR_REGS
+};
+
 struct intel_iommu {
 	void __iomem	*reg; /* Pointer to hardware regs, virtual addr */
 	u64		cap;
@@ -304,6 +314,8 @@ struct intel_iommu {
 	struct iommu_flush flush;
 #endif
 	struct q_inval  *qi;            /* Queued invalidation info */
+	u32 *iommu_state; /* Store iommu states between suspend and resume.*/
+
 #ifdef CONFIG_INTR_REMAP
 	struct ir_table *ir_table;	/* Interrupt remapping info */
 #endif
@@ -322,6 +334,7 @@ extern int alloc_iommu(struct dmar_drhd_unit *drhd);
 extern void free_iommu(struct intel_iommu *iommu);
 extern int dmar_enable_qi(struct intel_iommu *iommu);
 extern void dmar_disable_qi(struct intel_iommu *iommu);
+extern int dmar_reenable_qi(struct intel_iommu *iommu);
 extern void qi_global_iec(struct intel_iommu *iommu);
 
 extern int qi_flush_context(struct intel_iommu *iommu, u16 did, u16 sid,

include/linux/interrupt.h

@@ -59,6 +59,18 @@
 #define IRQF_NOBALANCING	0x00000800
 #define IRQF_IRQPOLL		0x00001000
 
+/*
+ * Bits used by threaded handlers:
+ * IRQTF_RUNTHREAD - signals that the interrupt handler thread should run
+ * IRQTF_DIED      - handler thread died
+ * IRQTF_WARNED    - warning "IRQ_WAKE_THREAD w/o thread_fn" has been printed
+ */
+enum {
+	IRQTF_RUNTHREAD,
+	IRQTF_DIED,
+	IRQTF_WARNED,
+};
+
 typedef irqreturn_t (*irq_handler_t)(int, void *);
 
 /**
@@ -71,6 +83,9 @@ typedef irqreturn_t (*irq_handler_t)(int, void *);
  * @next:	pointer to the next irqaction for shared interrupts
  * @irq:	interrupt number
  * @dir:	pointer to the proc/irq/NN/name entry
+ * @thread_fn:	interupt handler function for threaded interrupts
+ * @thread:	thread pointer for threaded interrupts
+ * @thread_flags:	flags related to @thread
  */
 struct irqaction {
 	irq_handler_t handler;
@@ -81,18 +96,68 @@ struct irqaction {
 	struct irqaction *next;
 	int irq;
 	struct proc_dir_entry *dir;
+	irq_handler_t thread_fn;
+	struct task_struct *thread;
+	unsigned long thread_flags;
 };
 
 extern irqreturn_t no_action(int cpl, void *dev_id);
-extern int __must_check request_irq(unsigned int, irq_handler_t handler,
-		       unsigned long, const char *, void *);
+
+#ifdef CONFIG_GENERIC_HARDIRQS
+extern int __must_check
+request_threaded_irq(unsigned int irq, irq_handler_t handler,
+		     irq_handler_t thread_fn,
+		     unsigned long flags, const char *name, void *dev);
+
+static inline int __must_check
+request_irq(unsigned int irq, irq_handler_t handler, unsigned long flags,
+	    const char *name, void *dev)
+{
+	return request_threaded_irq(irq, handler, NULL, flags, name, dev);
+}
+
+extern void exit_irq_thread(void);
+#else
+
+extern int __must_check
+request_irq(unsigned int irq, irq_handler_t handler, unsigned long flags,
+	    const char *name, void *dev);
+
+/*
+ * Special function to avoid ifdeffery in kernel/irq/devres.c which
+ * gets magically built by GENERIC_HARDIRQS=n architectures (sparc,
+ * m68k). I really love these $@%#!* obvious Makefile references:
+ * ../../../kernel/irq/devres.o
+ */
+static inline int __must_check
+request_threaded_irq(unsigned int irq, irq_handler_t handler,
+		     irq_handler_t thread_fn,
+		     unsigned long flags, const char *name, void *dev)
+{
+	return request_irq(irq, handler, flags, name, dev);
+}
+
+static inline void exit_irq_thread(void) { }
+#endif
+
 extern void free_irq(unsigned int, void *);
 
 struct device;
 
-extern int __must_check devm_request_irq(struct device *dev, unsigned int irq,
-			    irq_handler_t handler, unsigned long irqflags,
-			    const char *devname, void *dev_id);
+extern int __must_check
+devm_request_threaded_irq(struct device *dev, unsigned int irq,
+			  irq_handler_t handler, irq_handler_t thread_fn,
+			  unsigned long irqflags, const char *devname,
+			  void *dev_id);
+
+static inline int __must_check
+devm_request_irq(struct device *dev, unsigned int irq, irq_handler_t handler,
+		 unsigned long irqflags, const char *devname, void *dev_id)
+{
+	return devm_request_threaded_irq(dev, irq, handler, NULL, irqflags,
+					 devname, dev_id);
+}
+
 extern void devm_free_irq(struct device *dev, unsigned int irq, void *dev_id);
 
 /*
@@ -278,6 +343,11 @@ enum
 	NR_SOFTIRQS
 };
 
+/* map softirq index to softirq name. update 'softirq_to_name' in
+ * kernel/softirq.c when adding a new softirq.
+ */
+extern char *softirq_to_name[NR_SOFTIRQS];
+
 /* softirq mask and active fields moved to irq_cpustat_t in
  * asm/hardirq.h to get better cache usage.  KAO
  */
@@ -294,6 +364,7 @@ extern void softirq_init(void);
 #define __raise_softirq_irqoff(nr) do { or_softirq_pending(1UL << (nr)); } while (0)
 extern void raise_softirq_irqoff(unsigned int nr);
 extern void raise_softirq(unsigned int nr);
+extern void wakeup_softirqd(void);
 
 /* This is the worklist that queues up per-cpu softirq work.
  *

include/linux/ipc_namespace.h

@@ -25,7 +25,7 @@ struct ipc_ids {
 };
 
 struct ipc_namespace {
-	struct kref	kref;
+	atomic_t	count;
 	struct ipc_ids	ids[3];
 
 	int		sem_ctls[4];
@@ -44,25 +44,57 @@ struct ipc_namespace {
 	int		shm_tot;
 
 	struct notifier_block ipcns_nb;
+
+	/* The kern_mount of the mqueuefs sb.  We take a ref on it */
+	struct vfsmount	*mq_mnt;
+
+	/* # queues in this ns, protected by mq_lock */
+	unsigned int    mq_queues_count;
+
+	/* next fields are set through sysctl */
+	unsigned int    mq_queues_max;   /* initialized to DFLT_QUEUESMAX */
+	unsigned int    mq_msg_max;      /* initialized to DFLT_MSGMAX */
+	unsigned int    mq_msgsize_max;  /* initialized to DFLT_MSGSIZEMAX */
+
 };
 
 extern struct ipc_namespace init_ipc_ns;
 extern atomic_t nr_ipc_ns;
 
-#ifdef CONFIG_SYSVIPC
+extern spinlock_t mq_lock;
+#if defined(CONFIG_POSIX_MQUEUE) || defined(CONFIG_SYSVIPC)
 #define INIT_IPC_NS(ns)		.ns		= &init_ipc_ns,
+#else
+#define INIT_IPC_NS(ns)
+#endif
 
+#ifdef CONFIG_SYSVIPC
 extern int register_ipcns_notifier(struct ipc_namespace *);
 extern int cond_register_ipcns_notifier(struct ipc_namespace *);
 extern void unregister_ipcns_notifier(struct ipc_namespace *);
 extern int ipcns_notify(unsigned long);
-
 #else /* CONFIG_SYSVIPC */
-#define INIT_IPC_NS(ns)
+static inline int register_ipcns_notifier(struct ipc_namespace *ns)
+{ return 0; }
+static inline int cond_register_ipcns_notifier(struct ipc_namespace *ns)
+{ return 0; }
+static inline void unregister_ipcns_notifier(struct ipc_namespace *ns) { }
+static inline int ipcns_notify(unsigned long l) { return 0; }
 #endif /* CONFIG_SYSVIPC */
 
-#if defined(CONFIG_SYSVIPC) && defined(CONFIG_IPC_NS)
-extern void free_ipc_ns(struct kref *kref);
+#ifdef CONFIG_POSIX_MQUEUE
+extern int mq_init_ns(struct ipc_namespace *ns);
+/* default values */
+#define DFLT_QUEUESMAX 256     /* max number of message queues */
+#define DFLT_MSGMAX    10      /* max number of messages in each queue */
+#define HARD_MSGMAX    (131072/sizeof(void *))
+#define DFLT_MSGSIZEMAX 8192   /* max message size */
+#else
+static inline int mq_init_ns(struct ipc_namespace *ns) { return 0; }
+#endif
+
+#if defined(CONFIG_IPC_NS)
+extern void free_ipc_ns(struct ipc_namespace *ns);
 extern struct ipc_namespace *copy_ipcs(unsigned long flags,
 				       struct ipc_namespace *ns);
 extern void free_ipcs(struct ipc_namespace *ns, struct ipc_ids *ids,
@@ -72,14 +104,11 @@ extern void free_ipcs(struct ipc_namespace *ns, struct ipc_ids *ids,
 static inline struct ipc_namespace *get_ipc_ns(struct ipc_namespace *ns)
 {
 	if (ns)
-		kref_get(&ns->kref);
+		atomic_inc(&ns->count);
 	return ns;
 }
 
-static inline void put_ipc_ns(struct ipc_namespace *ns)
-{
-	kref_put(&ns->kref, free_ipc_ns);
-}
+extern void put_ipc_ns(struct ipc_namespace *ns);
 #else
 static inline struct ipc_namespace *copy_ipcs(unsigned long flags,
 		struct ipc_namespace *ns)
@@ -99,4 +128,18 @@ static inline void put_ipc_ns(struct ipc_namespace *ns)
 {
 }
 #endif
+
+#ifdef CONFIG_POSIX_MQUEUE_SYSCTL
+
+struct ctl_table_header;
+extern struct ctl_table_header *mq_register_sysctl_table(void);
+
+#else /* CONFIG_POSIX_MQUEUE_SYSCTL */
+
+static inline struct ctl_table_header *mq_register_sysctl_table(void)
+{
+	return NULL;
+}
+
+#endif /* CONFIG_POSIX_MQUEUE_SYSCTL */
 #endif

include/linux/ipmi.h

@@ -198,6 +198,8 @@ struct kernel_ipmi_msg {
 					      response.  When you send a
 					      response message, this will
 					      be returned. */
+#define IPMI_OEM_RECV_TYPE		5 /* The response for OEM Channels */
+
 /* Note that async events and received commands do not have a completion
    code as the first byte of the incoming data, unlike a response. */
 

include/linux/ipmi_msgdefs.h

@@ -58,6 +58,12 @@
 #define IPMI_READ_EVENT_MSG_BUFFER_CMD	0x35
 #define IPMI_GET_CHANNEL_INFO_CMD	0x42
 
+/* Bit for BMC global enables. */
+#define IPMI_BMC_RCV_MSG_INTR     0x01
+#define IPMI_BMC_EVT_MSG_INTR     0x02
+#define IPMI_BMC_EVT_MSG_BUFF     0x04
+#define IPMI_BMC_SYS_LOG          0x08
+
 #define IPMI_NETFN_STORAGE_REQUEST		0x0a
 #define IPMI_NETFN_STORAGE_RESPONSE		0x0b
 #define IPMI_ADD_SEL_ENTRY_CMD		0x44
@@ -109,5 +115,7 @@
 #define IPMI_CHANNEL_MEDIUM_USB1	10
 #define IPMI_CHANNEL_MEDIUM_USB2	11
 #define IPMI_CHANNEL_MEDIUM_SYSINTF	12
+#define IPMI_CHANNEL_MEDIUM_OEM_MIN	0x60
+#define IPMI_CHANNEL_MEDIUM_OEM_MAX	0x7f
 
 #endif /* __LINUX_IPMI_MSGDEFS_H */

include/linux/irq.h

@@ -22,6 +22,7 @@
 #include <linux/irqnr.h>
 #include <linux/errno.h>
 #include <linux/topology.h>
+#include <linux/wait.h>
 
 #include <asm/irq.h>
 #include <asm/ptrace.h>
@@ -158,6 +159,8 @@ struct irq_2_iommu;
  * @affinity:		IRQ affinity on SMP
  * @cpu:		cpu index useful for balancing
  * @pending_mask:	pending rebalanced interrupts
+ * @threads_active:	number of irqaction threads currently running
+ * @wait_for_threads:	wait queue for sync_irq to wait for threaded handlers
  * @dir:		/proc/irq/ procfs entry
  * @name:		flow handler name for /proc/interrupts output
  */
@@ -189,6 +192,8 @@ struct irq_desc {
 	cpumask_var_t		pending_mask;
 #endif
 #endif
+	atomic_t		threads_active;
+	wait_queue_head_t       wait_for_threads;
 #ifdef CONFIG_PROC_FS
 	struct proc_dir_entry	*dir;
 #endif
@@ -482,6 +487,16 @@ static inline void init_copy_desc_masks(struct irq_desc *old_desc,
 #endif
 }
 
+static inline void free_desc_masks(struct irq_desc *old_desc,
+				   struct irq_desc *new_desc)
+{
+	free_cpumask_var(old_desc->affinity);
+
+#ifdef CONFIG_GENERIC_PENDING_IRQ
+	free_cpumask_var(old_desc->pending_mask);
+#endif
+}
+
 #else /* !CONFIG_SMP */
 
 static inline bool init_alloc_desc_masks(struct irq_desc *desc, int cpu,
@@ -495,6 +510,10 @@ static inline void init_copy_desc_masks(struct irq_desc *old_desc,
 {
 }
 
+static inline void free_desc_masks(struct irq_desc *old_desc,
+				   struct irq_desc *new_desc)
+{
+}
 #endif	/* CONFIG_SMP */
 
 #endif /* _LINUX_IRQ_H */

include/linux/irqreturn.h

@@ -5,10 +5,12 @@
  * enum irqreturn
  * @IRQ_NONE		interrupt was not from this device
  * @IRQ_HANDLED		interrupt was handled by this device
+ * @IRQ_WAKE_THREAD	handler requests to wake the handler thread
  */
 enum irqreturn {
 	IRQ_NONE,
 	IRQ_HANDLED,
+	IRQ_WAKE_THREAD,
 };
 
 typedef enum irqreturn irqreturn_t;

include/linux/jbd.h

@@ -978,7 +978,8 @@ extern void	   journal_destroy_revoke(journal_t *);
 extern int	   journal_revoke (handle_t *,
 				unsigned long, struct buffer_head *);
 extern int	   journal_cancel_revoke(handle_t *, struct journal_head *);
-extern void	   journal_write_revoke_records(journal_t *, transaction_t *);
+extern void	   journal_write_revoke_records(journal_t *,
+						transaction_t *, int);
 
 /* Recovery revoke support */
 extern int	journal_set_revoke(journal_t *, unsigned long, tid_t);

include/linux/jbd2.h

@@ -1193,7 +1193,8 @@ extern int	   jbd2_journal_init_revoke_caches(void);
 extern void	   jbd2_journal_destroy_revoke(journal_t *);
 extern int	   jbd2_journal_revoke (handle_t *, unsigned long long, struct buffer_head *);
 extern int	   jbd2_journal_cancel_revoke(handle_t *, struct journal_head *);
-extern void	   jbd2_journal_write_revoke_records(journal_t *, transaction_t *);
+extern void	   jbd2_journal_write_revoke_records(journal_t *,
+						     transaction_t *, int);
 
 /* Recovery revoke support */
 extern int	jbd2_journal_set_revoke(journal_t *, unsigned long long, tid_t);

include/linux/kallsyms.h

@@ -13,10 +13,17 @@
 #define KSYM_SYMBOL_LEN (sizeof("%s+%#lx/%#lx [%s]") + (KSYM_NAME_LEN - 1) + \
 			 2*(BITS_PER_LONG*3/10) + (MODULE_NAME_LEN - 1) + 1)
 
+struct module;
+
 #ifdef CONFIG_KALLSYMS
 /* Lookup the address for a symbol. Returns 0 if not found. */
 unsigned long kallsyms_lookup_name(const char *name);
 
+/* Call a function on each kallsyms symbol in the core kernel */
+int kallsyms_on_each_symbol(int (*fn)(void *, const char *, struct module *,
+				      unsigned long),
+			    void *data);
+
 extern int kallsyms_lookup_size_offset(unsigned long addr,
 				  unsigned long *symbolsize,
 				  unsigned long *offset);
@@ -43,6 +50,14 @@ static inline unsigned long kallsyms_lookup_name(const char *name)
 	return 0;
 }
 
+static inline int kallsyms_on_each_symbol(int (*fn)(void *, const char *,
+						    struct module *,
+						    unsigned long),
+					  void *data)
+{
+	return 0;
+}
+
 static inline int kallsyms_lookup_size_offset(unsigned long addr,
 					      unsigned long *symbolsize,
 					      unsigned long *offset)

include/linux/kernel.h

@@ -242,6 +242,19 @@ extern struct ratelimit_state printk_ratelimit_state;
 extern int printk_ratelimit(void);
 extern bool printk_timed_ratelimit(unsigned long *caller_jiffies,
 				   unsigned int interval_msec);
+
+/*
+ * Print a one-time message (analogous to WARN_ONCE() et al):
+ */
+#define printk_once(x...) ({			\
+	static int __print_once = 1;		\
+						\
+	if (__print_once) {			\
+		__print_once = 0;		\
+		printk(x);			\
+	}					\
+})
+
 void log_buf_kexec_setup(void);
 #else
 static inline int vprintk(const char *s, va_list args)
@@ -254,6 +267,10 @@ static inline int printk_ratelimit(void) { return 0; }
 static inline bool printk_timed_ratelimit(unsigned long *caller_jiffies, \
 					  unsigned int interval_msec)	\
 		{ return false; }
+
+/* No effect, but we still get type checking even in the !PRINTK case: */
+#define printk_once(x...) printk(x)
+
 static inline void log_buf_kexec_setup(void)
 {
 }
@@ -360,6 +377,15 @@ static inline char *pack_hex_byte(char *buf, u8 byte)
 #define pr_cont(fmt, ...) \
 	printk(KERN_CONT fmt, ##__VA_ARGS__)
 
+/* pr_devel() should produce zero code unless DEBUG is defined */
+#ifdef DEBUG
+#define pr_devel(fmt, ...) \
+	printk(KERN_DEBUG pr_fmt(fmt), ##__VA_ARGS__)
+#else
+#define pr_devel(fmt, ...) \
+	({ if (0) printk(KERN_DEBUG pr_fmt(fmt), ##__VA_ARGS__); 0; })
+#endif
+
 /* If you are writing a driver, please use dev_dbg instead */
 #if defined(DEBUG)
 #define pr_debug(fmt, ...) \
@@ -374,6 +400,139 @@ static inline char *pack_hex_byte(char *buf, u8 byte)
 	({ if (0) printk(KERN_DEBUG pr_fmt(fmt), ##__VA_ARGS__); 0; })
 #endif
 
+/*
+ * General tracing related utility functions - trace_printk(),
+ * tracing_on/tracing_off and tracing_start()/tracing_stop
+ *
+ * Use tracing_on/tracing_off when you want to quickly turn on or off
+ * tracing. It simply enables or disables the recording of the trace events.
+ * This also corresponds to the user space debugfs/tracing/tracing_on
+ * file, which gives a means for the kernel and userspace to interact.
+ * Place a tracing_off() in the kernel where you want tracing to end.
+ * From user space, examine the trace, and then echo 1 > tracing_on
+ * to continue tracing.
+ *
+ * tracing_stop/tracing_start has slightly more overhead. It is used
+ * by things like suspend to ram where disabling the recording of the
+ * trace is not enough, but tracing must actually stop because things
+ * like calling smp_processor_id() may crash the system.
+ *
+ * Most likely, you want to use tracing_on/tracing_off.
+ */
+#ifdef CONFIG_RING_BUFFER
+void tracing_on(void);
+void tracing_off(void);
+/* trace_off_permanent stops recording with no way to bring it back */
+void tracing_off_permanent(void);
+int tracing_is_on(void);
+#else
+static inline void tracing_on(void) { }
+static inline void tracing_off(void) { }
+static inline void tracing_off_permanent(void) { }
+static inline int tracing_is_on(void) { return 0; }
+#endif
+#ifdef CONFIG_TRACING
+extern void tracing_start(void);
+extern void tracing_stop(void);
+extern void ftrace_off_permanent(void);
+
+extern void
+ftrace_special(unsigned long arg1, unsigned long arg2, unsigned long arg3);
+
+static inline void __attribute__ ((format (printf, 1, 2)))
+____trace_printk_check_format(const char *fmt, ...)
+{
+}
+#define __trace_printk_check_format(fmt, args...)			\
+do {									\
+	if (0)								\
+		____trace_printk_check_format(fmt, ##args);		\
+} while (0)
+
+/**
+ * trace_printk - printf formatting in the ftrace buffer
+ * @fmt: the printf format for printing
+ *
+ * Note: __trace_printk is an internal function for trace_printk and
+ *       the @ip is passed in via the trace_printk macro.
+ *
+ * This function allows a kernel developer to debug fast path sections
+ * that printk is not appropriate for. By scattering in various
+ * printk like tracing in the code, a developer can quickly see
+ * where problems are occurring.
+ *
+ * This is intended as a debugging tool for the developer only.
+ * Please refrain from leaving trace_printks scattered around in
+ * your code.
+ */
+
+#define trace_printk(fmt, args...)					\
+do {									\
+	__trace_printk_check_format(fmt, ##args);			\
+	if (__builtin_constant_p(fmt)) {				\
+		static const char *trace_printk_fmt			\
+		  __attribute__((section("__trace_printk_fmt"))) =	\
+			__builtin_constant_p(fmt) ? fmt : NULL;		\
+									\
+		__trace_bprintk(_THIS_IP_, trace_printk_fmt, ##args);	\
+	} else								\
+		__trace_printk(_THIS_IP_, fmt, ##args);		\
+} while (0)
+
+extern int
+__trace_bprintk(unsigned long ip, const char *fmt, ...)
+	__attribute__ ((format (printf, 2, 3)));
+
+extern int
+__trace_printk(unsigned long ip, const char *fmt, ...)
+	__attribute__ ((format (printf, 2, 3)));
+
+/*
+ * The double __builtin_constant_p is because gcc will give us an error
+ * if we try to allocate the static variable to fmt if it is not a
+ * constant. Even with the outer if statement.
+ */
+#define ftrace_vprintk(fmt, vargs)					\
+do {									\
+	if (__builtin_constant_p(fmt)) {				\
+		static const char *trace_printk_fmt			\
+		  __attribute__((section("__trace_printk_fmt"))) =	\
+			__builtin_constant_p(fmt) ? fmt : NULL;		\
+									\
+		__ftrace_vbprintk(_THIS_IP_, trace_printk_fmt, vargs);	\
+	} else								\
+		__ftrace_vprintk(_THIS_IP_, fmt, vargs);		\
+} while (0)
+
+extern int
+__ftrace_vbprintk(unsigned long ip, const char *fmt, va_list ap);
+
+extern int
+__ftrace_vprintk(unsigned long ip, const char *fmt, va_list ap);
+
+extern void ftrace_dump(void);
+#else
+static inline void
+ftrace_special(unsigned long arg1, unsigned long arg2, unsigned long arg3) { }
+static inline int
+trace_printk(const char *fmt, ...) __attribute__ ((format (printf, 1, 2)));
+
+static inline void tracing_start(void) { }
+static inline void tracing_stop(void) { }
+static inline void ftrace_off_permanent(void) { }
+static inline int
+trace_printk(const char *fmt, ...)
+{
+	return 0;
+}
+static inline int
+ftrace_vprintk(const char *fmt, va_list ap)
+{
+	return 0;
+}
+static inline void ftrace_dump(void) { }
+#endif /* CONFIG_TRACING */
+
 /*
  *      Display an IP address in readable format.
  */

include/linux/key.h

@@ -20,6 +20,7 @@
 #include <linux/rbtree.h>
 #include <linux/rcupdate.h>
 #include <linux/sysctl.h>
+#include <linux/rwsem.h>
 #include <asm/atomic.h>
 
 #ifdef __KERNEL__

include/linux/kmod.h

@@ -29,10 +29,15 @@
 #ifdef CONFIG_MODULES
 /* modprobe exit status on success, -ve on error.  Return value
  * usually useless though. */
-extern int request_module(const char * name, ...) __attribute__ ((format (printf, 1, 2)));
-#define try_then_request_module(x, mod...) ((x) ?: (request_module(mod), (x)))
+extern int __request_module(bool wait, const char *name, ...) \
+	__attribute__((format(printf, 2, 3)));
+#define request_module(mod...) __request_module(true, mod)
+#define request_module_nowait(mod...) __request_module(false, mod)
+#define try_then_request_module(x, mod...) \
+	((x) ?: (__request_module(true, mod), (x)))
 #else
-static inline int request_module(const char * name, ...) { return -ENOSYS; }
+static inline int request_module(const char *name, ...) { return -ENOSYS; }
+static inline int request_module_nowait(const char *name, ...) { return -ENOSYS; }
 #define try_then_request_module(x, mod...) (x)
 #endif
 

include/linux/kprobes.h

@@ -94,12 +94,16 @@ struct kprobe {
 	/* Called after addr is executed, unless... */
 	kprobe_post_handler_t post_handler;
 
-	/* ... called if executing addr causes a fault (eg. page fault).
-	 * Return 1 if it handled fault, otherwise kernel will see it. */
+	/*
+	 * ... called if executing addr causes a fault (eg. page fault).
+	 * Return 1 if it handled fault, otherwise kernel will see it.
+	 */
 	kprobe_fault_handler_t fault_handler;
 
-	/* ... called if breakpoint trap occurs in probe handler.
-	 * Return 1 if it handled break, otherwise kernel will see it. */
+	/*
+	 * ... called if breakpoint trap occurs in probe handler.
+	 * Return 1 if it handled break, otherwise kernel will see it.
+	 */
 	kprobe_break_handler_t break_handler;
 
 	/* Saved opcode (which has been replaced with breakpoint) */
@@ -108,18 +112,28 @@ struct kprobe {
 	/* copy of the original instruction */
 	struct arch_specific_insn ainsn;
 
-	/* Indicates various status flags.  Protected by kprobe_mutex. */
+	/*
+	 * Indicates various status flags.
+	 * Protected by kprobe_mutex after this kprobe is registered.
+	 */
 	u32 flags;
 };
 
 /* Kprobe status flags */
 #define KPROBE_FLAG_GONE	1 /* breakpoint has already gone */
+#define KPROBE_FLAG_DISABLED	2 /* probe is temporarily disabled */
 
+/* Has this kprobe gone ? */
 static inline int kprobe_gone(struct kprobe *p)
 {
 	return p->flags & KPROBE_FLAG_GONE;
 }
 
+/* Is this kprobe disabled ? */
+static inline int kprobe_disabled(struct kprobe *p)
+{
+	return p->flags & (KPROBE_FLAG_DISABLED | KPROBE_FLAG_GONE);
+}
 /*
  * Special probe type that uses setjmp-longjmp type tricks to resume
  * execution at a specified entry with a matching prototype corresponding
@@ -279,6 +293,9 @@ void unregister_kretprobes(struct kretprobe **rps, int num);
 void kprobe_flush_task(struct task_struct *tk);
 void recycle_rp_inst(struct kretprobe_instance *ri, struct hlist_head *head);
 
+int disable_kprobe(struct kprobe *kp);
+int enable_kprobe(struct kprobe *kp);
+
 #else /* !CONFIG_KPROBES: */
 
 static inline int kprobes_built_in(void)
@@ -345,5 +362,30 @@ static inline void unregister_kretprobes(struct kretprobe **rps, int num)
 static inline void kprobe_flush_task(struct task_struct *tk)
 {
 }
+static inline int disable_kprobe(struct kprobe *kp)
+{
+	return -ENOSYS;
+}
+static inline int enable_kprobe(struct kprobe *kp)
+{
+	return -ENOSYS;
+}
 #endif /* CONFIG_KPROBES */
+static inline int disable_kretprobe(struct kretprobe *rp)
+{
+	return disable_kprobe(&rp->kp);
+}
+static inline int enable_kretprobe(struct kretprobe *rp)
+{
+	return enable_kprobe(&rp->kp);
+}
+static inline int disable_jprobe(struct jprobe *jp)
+{
+	return disable_kprobe(&jp->kp);
+}
+static inline int enable_jprobe(struct jprobe *jp)
+{
+	return enable_kprobe(&jp->kp);
+}
+
 #endif /* _LINUX_KPROBES_H */

include/linux/kvm.h

@@ -409,6 +409,8 @@ struct kvm_trace_rec {
 #ifdef __KVM_HAVE_DEVICE_ASSIGNMENT
 #define KVM_CAP_DEVICE_DEASSIGNMENT 27
 #endif
+/* Another bug in KVM_SET_USER_MEMORY_REGION fixed: */
+#define KVM_CAP_JOIN_MEMORY_REGIONS_WORKS 30
 
 #ifdef KVM_CAP_IRQ_ROUTING
 

include/linux/leds-bd2802.h

@@ -0,0 +1,26 @@
+/*
+ * leds-bd2802.h - RGB LED Driver
+ *
+ * Copyright (C) 2009 Samsung Electronics
+ * Kim Kyuwon <q1.kim@samsung.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * Datasheet: http://www.rohm.com/products/databook/driver/pdf/bd2802gu-e.pdf
+ *
+ */
+#ifndef _LEDS_BD2802_H_
+#define _LEDS_BD2802_H_
+
+struct bd2802_led_platform_data{
+	int	reset_gpio;
+	u8	rgb_time;
+};
+
+#define RGB_TIME(slopedown, slopeup, waveform) \
+	((slopedown) << 6 | (slopeup) << 4 | (waveform))
+
+#endif /* _LEDS_BD2802_H_ */
+

include/linux/leds.h

@@ -30,6 +30,7 @@ enum led_brightness {
 struct led_classdev {
 	const char		*name;
 	int			 brightness;
+	int			 max_brightness;
 	int			 flags;
 
 	/* Lower 16 bits reflect status */
@@ -140,7 +141,8 @@ struct gpio_led {
 	const char *name;
 	const char *default_trigger;
 	unsigned 	gpio;
-	u8 		active_low;
+	u8 		active_low : 1;
+	u8		retain_state_suspended : 1;
 };
 
 struct gpio_led_platform_data {

include/linux/leds_pwm.h

@@ -0,0 +1,21 @@
+/*
+ * PWM LED driver data - see drivers/leds/leds-pwm.c
+ */
+#ifndef __LINUX_LEDS_PWM_H
+#define __LINUX_LEDS_PWM_H
+
+struct led_pwm {
+	const char	*name;
+	const char	*default_trigger;
+	unsigned	pwm_id;
+	u8 		active_low;
+	unsigned 	max_brightness;
+	unsigned	pwm_period_ns;
+};
+
+struct led_pwm_platform_data {
+	int			num_leds;
+	struct led_pwm	*leds;
+};
+
+#endif

include/linux/libata.h

@@ -209,6 +209,7 @@ enum {
 
 	/* bits 24:31 of ap->flags are reserved for LLD specific flags */
 
+
 	/* struct ata_port pflags */
 	ATA_PFLAG_EH_PENDING	= (1 << 0), /* EH pending */
 	ATA_PFLAG_EH_IN_PROGRESS = (1 << 1), /* EH in progress */
@@ -225,6 +226,9 @@ enum {
 	ATA_PFLAG_PM_PENDING	= (1 << 18), /* PM operation pending */
 	ATA_PFLAG_INIT_GTM_VALID = (1 << 19), /* initial gtm data valid */
 
+	ATA_PFLAG_PIO32		= (1 << 20),  /* 32bit PIO */
+	ATA_PFLAG_PIO32CHANGE	= (1 << 21),  /* 32bit PIO can be turned on/off */
+
 	/* struct ata_queued_cmd flags */
 	ATA_QCFLAG_ACTIVE	= (1 << 0), /* cmd not yet ack'd to scsi lyer */
 	ATA_QCFLAG_DMAMAP	= (1 << 1), /* SG table is DMA mapped */
@@ -689,7 +693,10 @@ struct ata_port {
 	struct Scsi_Host	*scsi_host; /* our co-allocated scsi host */
 	struct ata_port_operations *ops;
 	spinlock_t		*lock;
+	/* Flags owned by the EH context. Only EH should touch these once the
+	   port is active */
 	unsigned long		flags;	/* ATA_FLAG_xxx */
+	/* Flags that change dynamically, protected by ap->lock */
 	unsigned int		pflags; /* ATA_PFLAG_xxx */
 	unsigned int		print_id; /* user visible unique port ID */
 	unsigned int		port_no; /* 0 based port no. inside the host */
@@ -1595,6 +1602,7 @@ extern void ata_sff_drain_fifo(struct ata_queued_cmd *qc);
 extern void ata_sff_error_handler(struct ata_port *ap);
 extern void ata_sff_post_internal_cmd(struct ata_queued_cmd *qc);
 extern int ata_sff_port_start(struct ata_port *ap);
+extern int ata_sff_port_start32(struct ata_port *ap);
 extern void ata_sff_std_ports(struct ata_ioports *ioaddr);
 extern unsigned long ata_bmdma_mode_filter(struct ata_device *dev,
 					   unsigned long xfer_mask);

include/linux/lockd/xdr.h

@@ -25,13 +25,13 @@ struct svc_rqst;
 #define NLM_MAXCOOKIELEN    	32
 #define NLM_MAXSTRLEN		1024
 
-#define	nlm_granted		__constant_htonl(NLM_LCK_GRANTED)
-#define	nlm_lck_denied		__constant_htonl(NLM_LCK_DENIED)
-#define	nlm_lck_denied_nolocks	__constant_htonl(NLM_LCK_DENIED_NOLOCKS)
-#define	nlm_lck_blocked		__constant_htonl(NLM_LCK_BLOCKED)
-#define	nlm_lck_denied_grace_period	__constant_htonl(NLM_LCK_DENIED_GRACE_PERIOD)
+#define	nlm_granted		cpu_to_be32(NLM_LCK_GRANTED)
+#define	nlm_lck_denied		cpu_to_be32(NLM_LCK_DENIED)
+#define	nlm_lck_denied_nolocks	cpu_to_be32(NLM_LCK_DENIED_NOLOCKS)
+#define	nlm_lck_blocked		cpu_to_be32(NLM_LCK_BLOCKED)
+#define	nlm_lck_denied_grace_period	cpu_to_be32(NLM_LCK_DENIED_GRACE_PERIOD)
 
-#define nlm_drop_reply		__constant_htonl(30000)
+#define nlm_drop_reply		cpu_to_be32(30000)
 
 /* Lock info passed via NLM */
 struct nlm_lock {

include/linux/lockd/xdr4.h

@@ -15,11 +15,11 @@
 #include <linux/lockd/xdr.h>
 
 /* error codes new to NLMv4 */
-#define	nlm4_deadlock		__constant_htonl(NLM_DEADLCK)
-#define	nlm4_rofs		__constant_htonl(NLM_ROFS)
-#define	nlm4_stale_fh		__constant_htonl(NLM_STALE_FH)
-#define	nlm4_fbig		__constant_htonl(NLM_FBIG)
-#define	nlm4_failed		__constant_htonl(NLM_FAILED)
+#define	nlm4_deadlock		cpu_to_be32(NLM_DEADLCK)
+#define	nlm4_rofs		cpu_to_be32(NLM_ROFS)
+#define	nlm4_stale_fh		cpu_to_be32(NLM_STALE_FH)
+#define	nlm4_fbig		cpu_to_be32(NLM_FBIG)
+#define	nlm4_failed		cpu_to_be32(NLM_FAILED)
 
 
 

include/linux/memcontrol.h

@@ -56,7 +56,7 @@ extern void mem_cgroup_move_lists(struct page *page,
 				  enum lru_list from, enum lru_list to);
 extern void mem_cgroup_uncharge_page(struct page *page);
 extern void mem_cgroup_uncharge_cache_page(struct page *page);
-extern int mem_cgroup_shrink_usage(struct page *page,
+extern int mem_cgroup_shmem_charge_fallback(struct page *page,
 			struct mm_struct *mm, gfp_t gfp_mask);
 
 extern unsigned long mem_cgroup_isolate_pages(unsigned long nr_to_scan,
@@ -75,7 +75,7 @@ int mm_match_cgroup(const struct mm_struct *mm, const struct mem_cgroup *cgroup)
 {
 	struct mem_cgroup *mem;
 	rcu_read_lock();
-	mem = mem_cgroup_from_task((mm)->owner);
+	mem = mem_cgroup_from_task(rcu_dereference((mm)->owner));
 	rcu_read_unlock();
 	return cgroup == mem;
 }
@@ -155,7 +155,7 @@ static inline void mem_cgroup_uncharge_cache_page(struct page *page)
 {
 }
 
-static inline int mem_cgroup_shrink_usage(struct page *page,
+static inline int mem_cgroup_shmem_charge_fallback(struct page *page,
 			struct mm_struct *mm, gfp_t gfp_mask)
 {
 	return 0;

include/linux/memory.h

@@ -110,4 +110,10 @@ struct memory_accessor {
 			 off_t offset, size_t count);
 };
 
+/*
+ * Kernel text modification mutex, used for code patching. Users of this lock
+ * can sleep.
+ */
+extern struct mutex text_mutex;
+
 #endif /* _LINUX_MEMORY_H_ */

include/linux/mfd/ds1wm.h

@@ -0,0 +1,6 @@
+/* MFD cell driver data for the DS1WM driver */
+
+struct ds1wm_driver_data {
+	int active_high;
+	int clock_rate;
+};

include/linux/mfd/htc-pasic3.h

@@ -48,7 +48,6 @@ struct pasic3_leds_machinfo {
 
 struct pasic3_platform_data {
 	struct pasic3_leds_machinfo *led_pdata;
-	unsigned int                 bus_shift;
 	unsigned int                 clock_rate;
 };
 

include/linux/mfd/pcf50633/core.h

@@ -29,6 +29,8 @@ struct pcf50633_platform_data {
 	char **batteries;
 	int num_batteries;
 
+	int charging_restart_interval;
+
 	/* Callbacks */
 	void (*probe_done)(struct pcf50633 *);
 	void (*mbc_event_callback)(struct pcf50633 *, int);

include/linux/mfd/pcf50633/mbc.h

@@ -128,7 +128,6 @@ enum pcf50633_reg_mbcs3 {
 int pcf50633_mbc_usb_curlim_set(struct pcf50633 *pcf, int ma);
 
 int pcf50633_mbc_get_status(struct pcf50633 *);
-void pcf50633_mbc_set_status(struct pcf50633 *, int what, int status);
 
 #endif
 

include/linux/mfd/wm8350/core.h

@@ -640,9 +640,11 @@ struct wm8350 {
  *
  * @init: Function called during driver initialisation.  Should be
  *        used by the platform to configure GPIO functions and similar.
+ * @irq_high: Set if WM8350 IRQ is active high.
  */
 struct wm8350_platform_data {
 	int (*init)(struct wm8350 *wm8350);
+	int irq_high;
 };
 
 

include/linux/mg_disk.h

@@ -0,0 +1,206 @@
+/*
+ *  include/linux/mg_disk.c
+ *
+ *  Support for the mGine m[g]flash IO mode.
+ *  Based on legacy hd.c
+ *
+ * (c) 2008 mGine Co.,LTD
+ * (c) 2008 unsik Kim <donari75@gmail.com>
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of the GNU General Public License version 2 as
+ *  published by the Free Software Foundation.
+ */
+
+#ifndef __MG_DISK_H__
+#define __MG_DISK_H__
+
+#include <linux/blkdev.h>
+#include <linux/ata.h>
+
+/* name for block device */
+#define MG_DISK_NAME "mgd"
+/* name for platform device */
+#define MG_DEV_NAME "mg_disk"
+
+#define MG_DISK_MAJ 0
+#define MG_DISK_MAX_PART 16
+#define MG_SECTOR_SIZE 512
+#define MG_MAX_SECTS 256
+
+/* Register offsets */
+#define MG_BUFF_OFFSET			0x8000
+#define MG_STORAGE_BUFFER_SIZE		0x200
+#define MG_REG_OFFSET			0xC000
+#define MG_REG_FEATURE			(MG_REG_OFFSET + 2)	/* write case */
+#define MG_REG_ERROR			(MG_REG_OFFSET + 2)	/* read case */
+#define MG_REG_SECT_CNT			(MG_REG_OFFSET + 4)
+#define MG_REG_SECT_NUM			(MG_REG_OFFSET + 6)
+#define MG_REG_CYL_LOW			(MG_REG_OFFSET + 8)
+#define MG_REG_CYL_HIGH			(MG_REG_OFFSET + 0xA)
+#define MG_REG_DRV_HEAD			(MG_REG_OFFSET + 0xC)
+#define MG_REG_COMMAND			(MG_REG_OFFSET + 0xE)	/* write case */
+#define MG_REG_STATUS			(MG_REG_OFFSET + 0xE)	/* read  case */
+#define MG_REG_DRV_CTRL			(MG_REG_OFFSET + 0x10)
+#define MG_REG_BURST_CTRL		(MG_REG_OFFSET + 0x12)
+
+/* "Drive Select/Head Register" bit values */
+#define MG_REG_HEAD_MUST_BE_ON		0xA0 /* These 2 bits are always on */
+#define MG_REG_HEAD_DRIVE_MASTER	(0x00 | MG_REG_HEAD_MUST_BE_ON)
+#define MG_REG_HEAD_DRIVE_SLAVE		(0x10 | MG_REG_HEAD_MUST_BE_ON)
+#define MG_REG_HEAD_LBA_MODE		(0x40 | MG_REG_HEAD_MUST_BE_ON)
+
+
+/* "Device Control Register" bit values */
+#define MG_REG_CTRL_INTR_ENABLE			0x0
+#define MG_REG_CTRL_INTR_DISABLE		(0x1<<1)
+#define MG_REG_CTRL_RESET			(0x1<<2)
+#define MG_REG_CTRL_INTR_POLA_ACTIVE_HIGH	0x0
+#define MG_REG_CTRL_INTR_POLA_ACTIVE_LOW	(0x1<<4)
+#define MG_REG_CTRL_DPD_POLA_ACTIVE_LOW		0x0
+#define MG_REG_CTRL_DPD_POLA_ACTIVE_HIGH	(0x1<<5)
+#define MG_REG_CTRL_DPD_DISABLE			0x0
+#define MG_REG_CTRL_DPD_ENABLE			(0x1<<6)
+
+/* Status register bit */
+/* error bit in status register */
+#define MG_REG_STATUS_BIT_ERROR			0x01
+/* corrected error in status register */
+#define MG_REG_STATUS_BIT_CORRECTED_ERROR	0x04
+/* data request bit in status register */
+#define MG_REG_STATUS_BIT_DATA_REQ		0x08
+/* DSC - Drive Seek Complete */
+#define MG_REG_STATUS_BIT_SEEK_DONE		0x10
+/* DWF - Drive Write Fault */
+#define MG_REG_STATUS_BIT_WRITE_FAULT		0x20
+#define MG_REG_STATUS_BIT_READY			0x40
+#define MG_REG_STATUS_BIT_BUSY			0x80
+
+/* handy status */
+#define MG_STAT_READY	(MG_REG_STATUS_BIT_READY | MG_REG_STATUS_BIT_SEEK_DONE)
+#define MG_READY_OK(s)	(((s) & (MG_STAT_READY | \
+				(MG_REG_STATUS_BIT_BUSY | \
+				 MG_REG_STATUS_BIT_WRITE_FAULT | \
+				 MG_REG_STATUS_BIT_ERROR))) == MG_STAT_READY)
+
+/* Error register */
+#define MG_REG_ERR_AMNF		0x01
+#define MG_REG_ERR_ABRT		0x04
+#define MG_REG_ERR_IDNF		0x10
+#define MG_REG_ERR_UNC		0x40
+#define MG_REG_ERR_BBK		0x80
+
+/* error code for others */
+#define MG_ERR_NONE		0
+#define MG_ERR_TIMEOUT		0x100
+#define MG_ERR_INIT_STAT	0x101
+#define MG_ERR_TRANSLATION	0x102
+#define MG_ERR_CTRL_RST		0x103
+#define MG_ERR_INV_STAT		0x104
+#define MG_ERR_RSTOUT		0x105
+
+#define MG_MAX_ERRORS	6	/* Max read/write errors */
+
+/* command */
+#define MG_CMD_RD 0x20
+#define MG_CMD_WR 0x30
+#define MG_CMD_SLEEP 0x99
+#define MG_CMD_WAKEUP 0xC3
+#define MG_CMD_ID 0xEC
+#define MG_CMD_WR_CONF 0x3C
+#define MG_CMD_RD_CONF 0x40
+
+/* operation mode */
+#define MG_OP_CASCADE (1 << 0)
+#define MG_OP_CASCADE_SYNC_RD (1 << 1)
+#define MG_OP_CASCADE_SYNC_WR (1 << 2)
+#define MG_OP_INTERLEAVE (1 << 3)
+
+/* synchronous */
+#define MG_BURST_LAT_4 (3 << 4)
+#define MG_BURST_LAT_5 (4 << 4)
+#define MG_BURST_LAT_6 (5 << 4)
+#define MG_BURST_LAT_7 (6 << 4)
+#define MG_BURST_LAT_8 (7 << 4)
+#define MG_BURST_LEN_4 (1 << 1)
+#define MG_BURST_LEN_8 (2 << 1)
+#define MG_BURST_LEN_16 (3 << 1)
+#define MG_BURST_LEN_32 (4 << 1)
+#define MG_BURST_LEN_CONT (0 << 1)
+
+/* timeout value (unit: ms) */
+#define MG_TMAX_CONF_TO_CMD	1
+#define MG_TMAX_WAIT_RD_DRQ	10
+#define MG_TMAX_WAIT_WR_DRQ	500
+#define MG_TMAX_RST_TO_BUSY	10
+#define MG_TMAX_HDRST_TO_RDY	500
+#define MG_TMAX_SWRST_TO_RDY	500
+#define MG_TMAX_RSTOUT		3000
+
+/* device attribution */
+/* use mflash as boot device */
+#define MG_BOOT_DEV		(1 << 0)
+/* use mflash as storage device */
+#define MG_STORAGE_DEV		(1 << 1)
+/* same as MG_STORAGE_DEV, but bootloader already done reset sequence */
+#define MG_STORAGE_DEV_SKIP_RST	(1 << 2)
+
+#define MG_DEV_MASK (MG_BOOT_DEV | MG_STORAGE_DEV | MG_STORAGE_DEV_SKIP_RST)
+
+/* names of GPIO resource */
+#define MG_RST_PIN	"mg_rst"
+/* except MG_BOOT_DEV, reset-out pin should be assigned */
+#define MG_RSTOUT_PIN	"mg_rstout"
+
+/* private driver data */
+struct mg_drv_data {
+	/* disk resource */
+	u32 use_polling;
+
+	/* device attribution */
+	u32 dev_attr;
+
+	/* internally used */
+	struct mg_host *host;
+};
+
+/* main structure for mflash driver */
+struct mg_host {
+	struct device *dev;
+
+	struct request_queue *breq;
+	spinlock_t lock;
+	struct gendisk *gd;
+
+	struct timer_list timer;
+	void (*mg_do_intr) (struct mg_host *);
+
+	u16 id[ATA_ID_WORDS];
+
+	u16 cyls;
+	u16 heads;
+	u16 sectors;
+	u32 n_sectors;
+	u32 nres_sectors;
+
+	void __iomem *dev_base;
+	unsigned int irq;
+	unsigned int rst;
+	unsigned int rstout;
+
+	u32 major;
+	u32 error;
+};
+
+/*
+ * Debugging macro and defines
+ */
+#undef DO_MG_DEBUG
+#ifdef DO_MG_DEBUG
+#  define MG_DBG(fmt, args...) \
+	printk(KERN_DEBUG "%s:%d "fmt, __func__, __LINE__, ##args)
+#else /* CONFIG_MG_DEBUG */
+#  define MG_DBG(fmt, args...) do { } while (0)
+#endif /* CONFIG_MG_DEBUG */
+
+#endif

include/linux/mman.h

@@ -12,21 +12,18 @@
 
 #ifdef __KERNEL__
 #include <linux/mm.h>
+#include <linux/percpu_counter.h>
 
 #include <asm/atomic.h>
 
 extern int sysctl_overcommit_memory;
 extern int sysctl_overcommit_ratio;
-extern atomic_long_t vm_committed_space;
+extern struct percpu_counter vm_committed_as;
 
-#ifdef CONFIG_SMP
-extern void vm_acct_memory(long pages);
-#else
 static inline void vm_acct_memory(long pages)
 {
-	atomic_long_add(pages, &vm_committed_space);
+	percpu_counter_add(&vm_committed_as, pages);
 }
-#endif
 
 static inline void vm_unacct_memory(long pages)
 {

include/linux/mmzone.h

@@ -764,12 +764,6 @@ extern int numa_zonelist_order_handler(struct ctl_table *, int,
 extern char numa_zonelist_order[];
 #define NUMA_ZONELIST_ORDER_LEN 16	/* string buffer size */
 
-#include <linux/topology.h>
-/* Returns the number of the current Node. */
-#ifndef numa_node_id
-#define numa_node_id()		(cpu_to_node(raw_smp_processor_id()))
-#endif
-
 #ifndef CONFIG_NEED_MULTIPLE_NODES
 
 extern struct pglist_data contig_page_data;

include/linux/module.h

@@ -248,6 +248,10 @@ struct module
 	const unsigned long *crcs;
 	unsigned int num_syms;
 
+	/* Kernel parameters. */
+	struct kernel_param *kp;
+	unsigned int num_kp;
+
 	/* GPL-only exported symbols. */
 	unsigned int num_gpl_syms;
 	const struct kernel_symbol *gpl_syms;
@@ -329,6 +333,11 @@ struct module
 	unsigned int num_tracepoints;
 #endif
 
+#ifdef CONFIG_TRACING
+	const char **trace_bprintk_fmt_start;
+	unsigned int num_trace_bprintk_fmt;
+#endif
+
 #ifdef CONFIG_MODULE_UNLOAD
 	/* What modules depend on me? */
 	struct list_head modules_which_use_me;
@@ -350,6 +359,8 @@ struct module
 #define MODULE_ARCH_INIT {}
 #endif
 
+extern struct mutex module_mutex;
+
 /* FIXME: It'd be nice to isolate modules during init, too, so they
    aren't used before they (may) fail.  But presently too much code
    (IDE & SCSI) require entry into the module during init.*/
@@ -358,10 +369,10 @@ static inline int module_is_live(struct module *mod)
 	return mod->state != MODULE_STATE_GOING;
 }
 
-/* Is this address in a module? (second is with no locks, for oops) */
-struct module *module_text_address(unsigned long addr);
 struct module *__module_text_address(unsigned long addr);
-int is_module_address(unsigned long addr);
+struct module *__module_address(unsigned long addr);
+bool is_module_address(unsigned long addr);
+bool is_module_text_address(unsigned long addr);
 
 static inline int within_module_core(unsigned long addr, struct module *mod)
 {
@@ -375,6 +386,31 @@ static inline int within_module_init(unsigned long addr, struct module *mod)
 	       addr < (unsigned long)mod->module_init + mod->init_size;
 }
 
+/* Search for module by name: must hold module_mutex. */
+struct module *find_module(const char *name);
+
+struct symsearch {
+	const struct kernel_symbol *start, *stop;
+	const unsigned long *crcs;
+	enum {
+		NOT_GPL_ONLY,
+		GPL_ONLY,
+		WILL_BE_GPL_ONLY,
+	} licence;
+	bool unused;
+};
+
+/* Search for an exported symbol by name. */
+const struct kernel_symbol *find_symbol(const char *name,
+					struct module **owner,
+					const unsigned long **crc,
+					bool gplok,
+					bool warn);
+
+/* Walk the exported symbol table */
+bool each_symbol(bool (*fn)(const struct symsearch *arr, struct module *owner,
+			    unsigned int symnum, void *data), void *data);
+
 /* Returns 0 and fills in value, defined and namebuf, or -ERANGE if
    symnum out of range. */
 int module_get_kallsym(unsigned int symnum, unsigned long *value, char *type,
@@ -383,6 +419,10 @@ int module_get_kallsym(unsigned int symnum, unsigned long *value, char *type,
 /* Look for this name: can be of form module:name. */
 unsigned long module_kallsyms_lookup_name(const char *name);
 
+int module_kallsyms_on_each_symbol(int (*fn)(void *, const char *,
+					     struct module *, unsigned long),
+				   void *data);
+
 extern void __module_put_and_exit(struct module *mod, long code)
 	__attribute__((noreturn));
 #define module_put_and_exit(code) __module_put_and_exit(THIS_MODULE, code);
@@ -444,6 +484,7 @@ static inline void __module_get(struct module *module)
 #define symbol_put_addr(p) do { } while(0)
 
 #endif /* CONFIG_MODULE_UNLOAD */
+int use_module(struct module *a, struct module *b);
 
 /* This is a #define so the string doesn't get put in every .o file */
 #define module_name(mod)			\
@@ -490,21 +531,24 @@ search_module_extables(unsigned long addr)
 	return NULL;
 }
 
-/* Is this address in a module? */
-static inline struct module *module_text_address(unsigned long addr)
+static inline struct module *__module_address(unsigned long addr)
 {
 	return NULL;
 }
 
-/* Is this address in a module? (don't take a lock, we're oopsing) */
 static inline struct module *__module_text_address(unsigned long addr)
 {
 	return NULL;
 }
 
-static inline int is_module_address(unsigned long addr)
+static inline bool is_module_address(unsigned long addr)
 {
-	return 0;
+	return false;
+}
+
+static inline bool is_module_text_address(unsigned long addr)
+{
+	return false;
 }
 
 /* Get/put a kernel symbol (calls should be symmetric) */
@@ -559,6 +603,14 @@ static inline unsigned long module_kallsyms_lookup_name(const char *name)
 	return 0;
 }
 
+static inline int module_kallsyms_on_each_symbol(int (*fn)(void *, const char *,
+							   struct module *,
+							   unsigned long),
+						 void *data)
+{
+	return 0;
+}
+
 static inline int register_module_notifier(struct notifier_block * nb)
 {
 	/* no events will happen anyway, so this can always succeed */

include/linux/moduleparam.h

@@ -138,6 +138,16 @@ extern int parse_args(const char *name,
 		      unsigned num,
 		      int (*unknown)(char *param, char *val));
 
+/* Called by module remove. */
+#ifdef CONFIG_SYSFS
+extern void destroy_params(const struct kernel_param *params, unsigned num);
+#else
+static inline void destroy_params(const struct kernel_param *params,
+				  unsigned num)
+{
+}
+#endif /* !CONFIG_SYSFS */
+
 /* All the helper functions */
 /* The macros to do compile-time type checking stolen from Jakub
    Jelinek, who IIRC came up with this idea for the 2.4 module init code. */

include/linux/mtd/mtd.h

@@ -11,6 +11,7 @@
 #include <linux/module.h>
 #include <linux/uio.h>
 #include <linux/notifier.h>
+#include <linux/device.h>
 
 #include <linux/mtd/compatmac.h>
 #include <mtd/mtd-abi.h>
@@ -162,6 +163,20 @@ struct mtd_info {
 	/* We probably shouldn't allow XIP if the unpoint isn't a NULL */
 	void (*unpoint) (struct mtd_info *mtd, loff_t from, size_t len);
 
+	/* Allow NOMMU mmap() to directly map the device (if not NULL)
+	 * - return the address to which the offset maps
+	 * - return -ENOSYS to indicate refusal to do the mapping
+	 */
+	unsigned long (*get_unmapped_area) (struct mtd_info *mtd,
+					    unsigned long len,
+					    unsigned long offset,
+					    unsigned long flags);
+
+	/* Backing device capabilities for this device
+	 * - provides mmap capabilities
+	 */
+	struct backing_dev_info *backing_dev_info;
+
 
 	int (*read) (struct mtd_info *mtd, loff_t from, size_t len, size_t *retlen, u_char *buf);
 	int (*write) (struct mtd_info *mtd, loff_t to, size_t len, size_t *retlen, const u_char *buf);
@@ -223,6 +238,7 @@ struct mtd_info {
 	void *priv;
 
 	struct module *owner;
+	struct device dev;
 	int usecount;
 
 	/* If the driver is something smart, like UBI, it may need to maintain
@@ -233,6 +249,11 @@ struct mtd_info {
 	void (*put_device) (struct mtd_info *mtd);
 };
 
+static inline struct mtd_info *dev_to_mtd(struct device *dev)
+{
+	return dev ? container_of(dev, struct mtd_info, dev) : NULL;
+}
+
 static inline uint32_t mtd_div_by_eb(uint64_t sz, struct mtd_info *mtd)
 {
 	if (mtd->erasesize_shift)

include/linux/mtd/nand.h

@@ -43,8 +43,8 @@ extern void nand_wait_ready(struct mtd_info *mtd);
  * is supported now. If you add a chip with bigger oobsize/page
  * adjust this accordingly.
  */
-#define NAND_MAX_OOBSIZE	64
-#define NAND_MAX_PAGESIZE	2048
+#define NAND_MAX_OOBSIZE	128
+#define NAND_MAX_PAGESIZE	4096
 
 /*
  * Constants for hardware specific CLE/ALE/NCE function

include/linux/mtd/partitions.h

@@ -76,4 +76,16 @@ int __devinit of_mtd_parse_partitions(struct device *dev,
                                       struct device_node *node,
                                       struct mtd_partition **pparts);
 
+#ifdef CONFIG_MTD_PARTITIONS
+static inline int mtd_has_partitions(void) { return 1; }
+#else
+static inline int mtd_has_partitions(void) { return 0; }
+#endif
+
+#ifdef CONFIG_MTD_CMDLINE_PARTS
+static inline int mtd_has_cmdlinepart(void) { return 1; }
+#else
+static inline int mtd_has_cmdlinepart(void) { return 0; }
+#endif
+
 #endif

include/linux/namei.h

@@ -69,7 +69,6 @@ extern int path_lookup(const char *, unsigned, struct nameidata *);
 extern int vfs_path_lookup(struct dentry *, struct vfsmount *,
 			   const char *, unsigned int, struct nameidata *);
 
-extern int path_lookup_open(int dfd, const char *name, unsigned lookup_flags, struct nameidata *, int open_flags);
 extern struct file *lookup_instantiate_filp(struct nameidata *nd, struct dentry *dentry,
 		int (*open)(struct inode *, struct file *));
 extern struct file *nameidata_to_filp(struct nameidata *nd, int flags);

include/linux/netdevice.h

@@ -104,7 +104,7 @@ struct wireless_dev;
 # else
 #  define LL_MAX_HEADER 96
 # endif
-#elif defined(CONFIG_TR)
+#elif defined(CONFIG_TR) || defined(CONFIG_TR_MODULE)
 # define LL_MAX_HEADER 48
 #else
 # define LL_MAX_HEADER 32
@@ -500,7 +500,7 @@ struct netdev_queue {
  *
  * int (*ndo_set_mac_address)(struct net_device *dev, void *addr);
  *	This function  is called when the Media Access Control address
- *	needs to be changed. If not this interface is not defined, the
+ *	needs to be changed. If this interface is not defined, the
  *	mac address can not be changed.
  *
  * int (*ndo_validate_addr)(struct net_device *dev);

include/linux/netfilter/nfnetlink_conntrack.h

@@ -100,6 +100,7 @@ enum ctattr_protoinfo_tcp {
 enum ctattr_protoinfo_dccp {
 	CTA_PROTOINFO_DCCP_UNSPEC,
 	CTA_PROTOINFO_DCCP_STATE,
+	CTA_PROTOINFO_DCCP_ROLE,
 	__CTA_PROTOINFO_DCCP_MAX,
 };
 #define CTA_PROTOINFO_DCCP_MAX (__CTA_PROTOINFO_DCCP_MAX - 1)

include/linux/netfilter/x_tables.h

@@ -354,9 +354,6 @@ struct xt_table
 	/* What hooks you will enter on */
 	unsigned int valid_hooks;
 
-	/* Lock for the curtain */
-	struct mutex lock;
-
 	/* Man behind the curtain... */
 	struct xt_table_info *private;
 
@@ -434,8 +431,74 @@ extern void xt_proto_fini(struct net *net, u_int8_t af);
 
 extern struct xt_table_info *xt_alloc_table_info(unsigned int size);
 extern void xt_free_table_info(struct xt_table_info *info);
-extern void xt_table_entry_swap_rcu(struct xt_table_info *old,
-				    struct xt_table_info *new);
+
+/*
+ * Per-CPU spinlock associated with per-cpu table entries, and
+ * with a counter for the "reading" side that allows a recursive
+ * reader to avoid taking the lock and deadlocking.
+ *
+ * "reading" is used by ip/arp/ip6 tables rule processing which runs per-cpu.
+ * It needs to ensure that the rules are not being changed while the packet
+ * is being processed. In some cases, the read lock will be acquired
+ * twice on the same CPU; this is okay because of the count.
+ *
+ * "writing" is used when reading counters.
+ *  During replace any readers that are using the old tables have to complete
+ *  before freeing the old table. This is handled by the write locking
+ *  necessary for reading the counters.
+ */
+struct xt_info_lock {
+	spinlock_t lock;
+	unsigned char readers;
+};
+DECLARE_PER_CPU(struct xt_info_lock, xt_info_locks);
+
+/*
+ * Note: we need to ensure that preemption is disabled before acquiring
+ * the per-cpu-variable, so we do it as a two step process rather than
+ * using "spin_lock_bh()".
+ *
+ * We _also_ need to disable bottom half processing before updating our
+ * nesting count, to make sure that the only kind of re-entrancy is this
+ * code being called by itself: since the count+lock is not an atomic
+ * operation, we can allow no races.
+ *
+ * _Only_ that special combination of being per-cpu and never getting
+ * re-entered asynchronously means that the count is safe.
+ */
+static inline void xt_info_rdlock_bh(void)
+{
+	struct xt_info_lock *lock;
+
+	local_bh_disable();
+	lock = &__get_cpu_var(xt_info_locks);
+	if (likely(!lock->readers++))
+		spin_lock(&lock->lock);
+}
+
+static inline void xt_info_rdunlock_bh(void)
+{
+	struct xt_info_lock *lock = &__get_cpu_var(xt_info_locks);
+
+	if (likely(!--lock->readers))
+		spin_unlock(&lock->lock);
+	local_bh_enable();
+}
+
+/*
+ * The "writer" side needs to get exclusive access to the lock,
+ * regardless of readers.  This must be called with bottom half
+ * processing (and thus also preemption) disabled.
+ */
+static inline void xt_info_wrlock(unsigned int cpu)
+{
+	spin_lock(&per_cpu(xt_info_locks, cpu).lock);
+}
+
+static inline void xt_info_wrunlock(unsigned int cpu)
+{
+	spin_unlock(&per_cpu(xt_info_locks, cpu).lock);
+}
 
 /*
  * This helper is performance critical and must be inlined

include/linux/netfilter/xt_LED.h

@@ -1,6 +1,8 @@
 #ifndef _XT_LED_H
 #define _XT_LED_H
 
+#include <linux/types.h>
+
 struct xt_led_info {
 	char id[27];        /* Unique ID for this trigger in the LED class */
 	__u8 always_blink;  /* Blink even if the LED is already on */

include/linux/netfilter/xt_cluster.h

@@ -12,4 +12,6 @@ struct xt_cluster_match_info {
 	u_int32_t		flags;
 };
 
+#define XT_CLUSTER_NODES_MAX	32
+
 #endif /* _XT_CLUSTER_MATCH_H */

include/linux/nfs.h

@@ -109,7 +109,6 @@
 	NFSERR_FILE_OPEN = 10046,      /*       v4 */
 	NFSERR_ADMIN_REVOKED = 10047,  /*       v4 */
 	NFSERR_CB_PATH_DOWN = 10048,   /*       v4 */
-	NFSERR_REPLAY_ME = 10049	/*       v4 */
 };
 
 /* NFSv2 file types - beware, these are not the same in NFSv3 */

include/linux/nfs4.h

@@ -21,6 +21,7 @@
 #define NFS4_FHSIZE		128
 #define NFS4_MAXPATHLEN		PATH_MAX
 #define NFS4_MAXNAMLEN		NAME_MAX
+#define NFS4_MAX_SESSIONID_LEN	16
 
 #define NFS4_ACCESS_READ        0x0001
 #define NFS4_ACCESS_LOOKUP      0x0002
@@ -38,6 +39,7 @@
 #define NFS4_OPEN_RESULT_CONFIRM 0x0002
 #define NFS4_OPEN_RESULT_LOCKTYPE_POSIX 0x0004
 
+#define NFS4_SHARE_ACCESS_MASK	0x000F
 #define NFS4_SHARE_ACCESS_READ	0x0001
 #define NFS4_SHARE_ACCESS_WRITE	0x0002
 #define NFS4_SHARE_ACCESS_BOTH	0x0003
@@ -45,6 +47,19 @@
 #define NFS4_SHARE_DENY_WRITE	0x0002
 #define NFS4_SHARE_DENY_BOTH	0x0003
 
+/* nfs41 */
+#define NFS4_SHARE_WANT_MASK		0xFF00
+#define NFS4_SHARE_WANT_NO_PREFERENCE	0x0000
+#define NFS4_SHARE_WANT_READ_DELEG	0x0100
+#define NFS4_SHARE_WANT_WRITE_DELEG	0x0200
+#define NFS4_SHARE_WANT_ANY_DELEG	0x0300
+#define NFS4_SHARE_WANT_NO_DELEG	0x0400
+#define NFS4_SHARE_WANT_CANCEL		0x0500
+
+#define NFS4_SHARE_WHEN_MASK		0xF0000
+#define NFS4_SHARE_SIGNAL_DELEG_WHEN_RESRC_AVAIL	0x10000
+#define NFS4_SHARE_PUSH_DELEG_WHEN_UNCONTENDED		0x20000
+
 #define NFS4_SET_TO_SERVER_TIME	0
 #define NFS4_SET_TO_CLIENT_TIME	1
 
@@ -88,6 +103,31 @@
 #define NFS4_ACE_GENERIC_EXECUTE              0x001200A0
 #define NFS4_ACE_MASK_ALL                     0x001F01FF
 
+#define EXCHGID4_FLAG_SUPP_MOVED_REFER		0x00000001
+#define EXCHGID4_FLAG_SUPP_MOVED_MIGR		0x00000002
+#define EXCHGID4_FLAG_USE_NON_PNFS		0x00010000
+#define EXCHGID4_FLAG_USE_PNFS_MDS		0x00020000
+#define EXCHGID4_FLAG_USE_PNFS_DS		0x00040000
+#define EXCHGID4_FLAG_UPD_CONFIRMED_REC_A	0x40000000
+#define EXCHGID4_FLAG_CONFIRMED_R		0x80000000
+/*
+ * Since the validity of these bits depends on whether
+ * they're set in the argument or response, have separate
+ * invalid flag masks for arg (_A) and resp (_R).
+ */
+#define EXCHGID4_FLAG_MASK_A			0x40070003
+#define EXCHGID4_FLAG_MASK_R			0x80070003
+
+#define SEQ4_STATUS_CB_PATH_DOWN		0x00000001
+#define SEQ4_STATUS_CB_GSS_CONTEXTS_EXPIRING	0x00000002
+#define SEQ4_STATUS_CB_GSS_CONTEXTS_EXPIRED	0x00000004
+#define SEQ4_STATUS_EXPIRED_ALL_STATE_REVOKED	0x00000008
+#define SEQ4_STATUS_EXPIRED_SOME_STATE_REVOKED	0x00000010
+#define SEQ4_STATUS_ADMIN_STATE_REVOKED		0x00000020
+#define SEQ4_STATUS_RECALLABLE_STATE_REVOKED	0x00000040
+#define SEQ4_STATUS_LEASE_MOVED			0x00000080
+#define SEQ4_STATUS_RESTART_RECLAIM_NEEDED	0x00000100
+
 #define NFS4_MAX_UINT64	(~(u64)0)
 
 enum nfs4_acl_whotype {
@@ -154,6 +194,28 @@ enum nfs_opnum4 {
 	OP_VERIFY = 37,
 	OP_WRITE = 38,
 	OP_RELEASE_LOCKOWNER = 39,
+
+	/* nfs41 */
+	OP_BACKCHANNEL_CTL = 40,
+	OP_BIND_CONN_TO_SESSION = 41,
+	OP_EXCHANGE_ID = 42,
+	OP_CREATE_SESSION = 43,
+	OP_DESTROY_SESSION = 44,
+	OP_FREE_STATEID = 45,
+	OP_GET_DIR_DELEGATION = 46,
+	OP_GETDEVICEINFO = 47,
+	OP_GETDEVICELIST = 48,
+	OP_LAYOUTCOMMIT = 49,
+	OP_LAYOUTGET = 50,
+	OP_LAYOUTRETURN = 51,
+	OP_SECINFO_NO_NAME = 52,
+	OP_SEQUENCE = 53,
+	OP_SET_SSV = 54,
+	OP_TEST_STATEID = 55,
+	OP_WANT_DELEGATION = 56,
+	OP_DESTROY_CLIENTID = 57,
+	OP_RECLAIM_COMPLETE = 58,
+
 	OP_ILLEGAL = 10044,
 };
 
@@ -230,7 +292,48 @@ enum nfsstat4 {
 	NFS4ERR_DEADLOCK = 10045,
 	NFS4ERR_FILE_OPEN = 10046,
 	NFS4ERR_ADMIN_REVOKED = 10047,
-	NFS4ERR_CB_PATH_DOWN = 10048
+	NFS4ERR_CB_PATH_DOWN = 10048,
+
+	/* nfs41 */
+	NFS4ERR_BADIOMODE	= 10049,
+	NFS4ERR_BADLAYOUT	= 10050,
+	NFS4ERR_BAD_SESSION_DIGEST = 10051,
+	NFS4ERR_BADSESSION	= 10052,
+	NFS4ERR_BADSLOT		= 10053,
+	NFS4ERR_COMPLETE_ALREADY = 10054,
+	NFS4ERR_CONN_NOT_BOUND_TO_SESSION = 10055,
+	NFS4ERR_DELEG_ALREADY_WANTED = 10056,
+	NFS4ERR_BACK_CHAN_BUSY	= 10057,	/* backchan reqs outstanding */
+	NFS4ERR_LAYOUTTRYLATER	= 10058,
+	NFS4ERR_LAYOUTUNAVAILABLE = 10059,
+	NFS4ERR_NOMATCHING_LAYOUT = 10060,
+	NFS4ERR_RECALLCONFLICT	= 10061,
+	NFS4ERR_UNKNOWN_LAYOUTTYPE = 10062,
+	NFS4ERR_SEQ_MISORDERED = 10063, 	/* unexpected seq.id in req */
+	NFS4ERR_SEQUENCE_POS	= 10064,	/* [CB_]SEQ. op not 1st op */
+	NFS4ERR_REQ_TOO_BIG	= 10065,	/* request too big */
+	NFS4ERR_REP_TOO_BIG	= 10066,	/* reply too big */
+	NFS4ERR_REP_TOO_BIG_TO_CACHE = 10067,	/* rep. not all cached */
+	NFS4ERR_RETRY_UNCACHED_REP = 10068,	/* retry & rep. uncached */
+	NFS4ERR_UNSAFE_COMPOUND = 10069,	/* retry/recovery too hard */
+	NFS4ERR_TOO_MANY_OPS	= 10070,	/* too many ops in [CB_]COMP */
+	NFS4ERR_OP_NOT_IN_SESSION = 10071,	/* op needs [CB_]SEQ. op */
+	NFS4ERR_HASH_ALG_UNSUPP = 10072,	/* hash alg. not supp. */
+						/* Error 10073 is unused. */
+	NFS4ERR_CLIENTID_BUSY	= 10074,	/* clientid has state */
+	NFS4ERR_PNFS_IO_HOLE	= 10075,	/* IO to _SPARSE file hole */
+	NFS4ERR_SEQ_FALSE_RETRY	= 10076,	/* retry not origional */
+	NFS4ERR_BAD_HIGH_SLOT	= 10077,	/* sequence arg bad */
+	NFS4ERR_DEADSESSION	= 10078,	/* persistent session dead */
+	NFS4ERR_ENCR_ALG_UNSUPP = 10079,	/* SSV alg mismatch */
+	NFS4ERR_PNFS_NO_LAYOUT	= 10080,	/* direct I/O with no layout */
+	NFS4ERR_NOT_ONLY_OP	= 10081,	/* bad compound */
+	NFS4ERR_WRONG_CRED	= 10082,	/* permissions:state change */
+	NFS4ERR_WRONG_TYPE	= 10083,	/* current operation mismatch */
+	NFS4ERR_DIRDELEG_UNAVAIL = 10084,	/* no directory delegation */
+	NFS4ERR_REJECT_DELEG	= 10085,	/* on callback */
+	NFS4ERR_RETURNCONFLICT	= 10086,	/* outstanding layoutreturn */
+	NFS4ERR_DELEG_REVOKED	= 10087,	/* deleg./layout revoked */
 };
 
 /*
@@ -265,7 +368,13 @@ enum opentype4 {
 enum createmode4 {
 	NFS4_CREATE_UNCHECKED = 0,
 	NFS4_CREATE_GUARDED = 1,
-	NFS4_CREATE_EXCLUSIVE = 2
+	NFS4_CREATE_EXCLUSIVE = 2,
+	/*
+	 * New to NFSv4.1. If session is persistent,
+	 * GUARDED4 MUST be used. Otherwise, use
+	 * EXCLUSIVE4_1 instead of EXCLUSIVE4.
+	 */
+	NFS4_CREATE_EXCLUSIVE4_1 = 3
 };
 
 enum limit_by4 {
@@ -301,6 +410,8 @@ enum lock_type4 {
 #define FATTR4_WORD0_UNIQUE_HANDLES     (1UL << 9)
 #define FATTR4_WORD0_LEASE_TIME         (1UL << 10)
 #define FATTR4_WORD0_RDATTR_ERROR       (1UL << 11)
+/* Mandatory in NFSv4.1 */
+#define FATTR4_WORD2_SUPPATTR_EXCLCREAT (1UL << 11)
 
 /* Recommended Attributes */
 #define FATTR4_WORD0_ACL                (1UL << 12)
@@ -391,6 +502,29 @@ enum {
 	NFSPROC4_CLNT_GETACL,
 	NFSPROC4_CLNT_SETACL,
 	NFSPROC4_CLNT_FS_LOCATIONS,
+
+	/* nfs41 */
+	NFSPROC4_CLNT_EXCHANGE_ID,
+	NFSPROC4_CLNT_CREATE_SESSION,
+	NFSPROC4_CLNT_DESTROY_SESSION,
+	NFSPROC4_CLNT_SEQUENCE,
+	NFSPROC4_CLNT_GET_LEASE_TIME,
+};
+
+/* nfs41 types */
+struct nfs4_sessionid {
+	unsigned char data[NFS4_MAX_SESSIONID_LEN];
+};
+
+/* Create Session Flags */
+#define SESSION4_PERSIST	 0x001
+#define SESSION4_BACK_CHAN 	 0x002
+#define SESSION4_RDMA		 0x004
+
+enum state_protect_how4 {
+	SP4_NONE	= 0,
+	SP4_MACH_CRED	= 1,
+	SP4_SSV		= 2
 };
 
 #endif

include/linux/nfsd/cache.h

@@ -76,4 +76,12 @@ void	nfsd_reply_cache_shutdown(void);
 int	nfsd_cache_lookup(struct svc_rqst *, int);
 void	nfsd_cache_update(struct svc_rqst *, int, __be32 *);
 
+#ifdef CONFIG_NFSD_V4
+void	nfsd4_set_statp(struct svc_rqst *rqstp, __be32 *statp);
+#else  /* CONFIG_NFSD_V4 */
+static inline void nfsd4_set_statp(struct svc_rqst *rqstp, __be32 *statp)
+{
+}
+#endif /* CONFIG_NFSD_V4 */
+
 #endif /* NFSCACHE_H */

include/linux/nfsd/nfsd.h

@@ -23,7 +23,7 @@
 /*
  * nfsd version
  */
-#define NFSD_SUPPORTED_MINOR_VERSION	0
+#define NFSD_SUPPORTED_MINOR_VERSION	1
 
 /*
  * Flags for nfsd_permission
@@ -53,6 +53,7 @@ typedef int (*nfsd_dirop_t)(struct inode *, struct dentry *, int, int);
 extern struct svc_program	nfsd_program;
 extern struct svc_version	nfsd_version2, nfsd_version3,
 				nfsd_version4;
+extern u32			nfsd_supported_minorversion;
 extern struct mutex		nfsd_mutex;
 extern struct svc_serv		*nfsd_serv;
 
@@ -105,7 +106,7 @@ void		nfsd_close(struct file *);
 __be32 		nfsd_read(struct svc_rqst *, struct svc_fh *, struct file *,
 				loff_t, struct kvec *, int, unsigned long *);
 __be32 		nfsd_write(struct svc_rqst *, struct svc_fh *,struct file *,
-				loff_t, struct kvec *,int, unsigned long, int *);
+				loff_t, struct kvec *,int, unsigned long *, int *);
 __be32		nfsd_readlink(struct svc_rqst *, struct svc_fh *,
 				char *, int *);
 __be32		nfsd_symlink(struct svc_rqst *, struct svc_fh *,
@@ -149,6 +150,7 @@ int nfsd_set_posix_acl(struct svc_fh *, int, struct posix_acl *);
 
 enum vers_op {NFSD_SET, NFSD_CLEAR, NFSD_TEST, NFSD_AVAIL };
 int nfsd_vers(int vers, enum vers_op change);
+int nfsd_minorversion(u32 minorversion, enum vers_op change);
 void nfsd_reset_versions(void);
 int nfsd_create_serv(void);
 
@@ -186,78 +188,119 @@ void		nfsd_lockd_shutdown(void);
 /*
  * These macros provide pre-xdr'ed values for faster operation.
  */
-#define	nfs_ok			__constant_htonl(NFS_OK)
-#define	nfserr_perm		__constant_htonl(NFSERR_PERM)
-#define	nfserr_noent		__constant_htonl(NFSERR_NOENT)
-#define	nfserr_io		__constant_htonl(NFSERR_IO)
-#define	nfserr_nxio		__constant_htonl(NFSERR_NXIO)
-#define	nfserr_eagain		__constant_htonl(NFSERR_EAGAIN)
-#define	nfserr_acces		__constant_htonl(NFSERR_ACCES)
-#define	nfserr_exist		__constant_htonl(NFSERR_EXIST)
-#define	nfserr_xdev		__constant_htonl(NFSERR_XDEV)
-#define	nfserr_nodev		__constant_htonl(NFSERR_NODEV)
-#define	nfserr_notdir		__constant_htonl(NFSERR_NOTDIR)
-#define	nfserr_isdir		__constant_htonl(NFSERR_ISDIR)
-#define	nfserr_inval		__constant_htonl(NFSERR_INVAL)
-#define	nfserr_fbig		__constant_htonl(NFSERR_FBIG)
-#define	nfserr_nospc		__constant_htonl(NFSERR_NOSPC)
-#define	nfserr_rofs		__constant_htonl(NFSERR_ROFS)
-#define	nfserr_mlink		__constant_htonl(NFSERR_MLINK)
-#define	nfserr_opnotsupp	__constant_htonl(NFSERR_OPNOTSUPP)
-#define	nfserr_nametoolong	__constant_htonl(NFSERR_NAMETOOLONG)
-#define	nfserr_notempty		__constant_htonl(NFSERR_NOTEMPTY)
-#define	nfserr_dquot		__constant_htonl(NFSERR_DQUOT)
-#define	nfserr_stale		__constant_htonl(NFSERR_STALE)
-#define	nfserr_remote		__constant_htonl(NFSERR_REMOTE)
-#define	nfserr_wflush		__constant_htonl(NFSERR_WFLUSH)
-#define	nfserr_badhandle	__constant_htonl(NFSERR_BADHANDLE)
-#define	nfserr_notsync		__constant_htonl(NFSERR_NOT_SYNC)
-#define	nfserr_badcookie	__constant_htonl(NFSERR_BAD_COOKIE)
-#define	nfserr_notsupp		__constant_htonl(NFSERR_NOTSUPP)
-#define	nfserr_toosmall		__constant_htonl(NFSERR_TOOSMALL)
-#define	nfserr_serverfault	__constant_htonl(NFSERR_SERVERFAULT)
-#define	nfserr_badtype		__constant_htonl(NFSERR_BADTYPE)
-#define	nfserr_jukebox		__constant_htonl(NFSERR_JUKEBOX)
-#define	nfserr_denied		__constant_htonl(NFSERR_DENIED)
-#define	nfserr_deadlock		__constant_htonl(NFSERR_DEADLOCK)
-#define nfserr_expired          __constant_htonl(NFSERR_EXPIRED)
-#define	nfserr_bad_cookie	__constant_htonl(NFSERR_BAD_COOKIE)
-#define	nfserr_same		__constant_htonl(NFSERR_SAME)
-#define	nfserr_clid_inuse	__constant_htonl(NFSERR_CLID_INUSE)
-#define	nfserr_stale_clientid	__constant_htonl(NFSERR_STALE_CLIENTID)
-#define	nfserr_resource		__constant_htonl(NFSERR_RESOURCE)
-#define	nfserr_moved		__constant_htonl(NFSERR_MOVED)
-#define	nfserr_nofilehandle	__constant_htonl(NFSERR_NOFILEHANDLE)
-#define	nfserr_minor_vers_mismatch	__constant_htonl(NFSERR_MINOR_VERS_MISMATCH)
-#define nfserr_share_denied	__constant_htonl(NFSERR_SHARE_DENIED)
-#define nfserr_stale_stateid	__constant_htonl(NFSERR_STALE_STATEID)
-#define nfserr_old_stateid	__constant_htonl(NFSERR_OLD_STATEID)
-#define nfserr_bad_stateid	__constant_htonl(NFSERR_BAD_STATEID)
-#define nfserr_bad_seqid	__constant_htonl(NFSERR_BAD_SEQID)
-#define	nfserr_symlink		__constant_htonl(NFSERR_SYMLINK)
-#define	nfserr_not_same		__constant_htonl(NFSERR_NOT_SAME)
-#define	nfserr_restorefh	__constant_htonl(NFSERR_RESTOREFH)
-#define	nfserr_attrnotsupp	__constant_htonl(NFSERR_ATTRNOTSUPP)
-#define	nfserr_bad_xdr		__constant_htonl(NFSERR_BAD_XDR)
-#define	nfserr_openmode		__constant_htonl(NFSERR_OPENMODE)
-#define	nfserr_locks_held	__constant_htonl(NFSERR_LOCKS_HELD)
-#define	nfserr_op_illegal	__constant_htonl(NFSERR_OP_ILLEGAL)
-#define	nfserr_grace		__constant_htonl(NFSERR_GRACE)
-#define	nfserr_no_grace		__constant_htonl(NFSERR_NO_GRACE)
-#define	nfserr_reclaim_bad	__constant_htonl(NFSERR_RECLAIM_BAD)
-#define	nfserr_badname		__constant_htonl(NFSERR_BADNAME)
-#define	nfserr_cb_path_down	__constant_htonl(NFSERR_CB_PATH_DOWN)
-#define	nfserr_locked		__constant_htonl(NFSERR_LOCKED)
-#define	nfserr_wrongsec		__constant_htonl(NFSERR_WRONGSEC)
-#define	nfserr_replay_me	__constant_htonl(NFSERR_REPLAY_ME)
+#define	nfs_ok			cpu_to_be32(NFS_OK)
+#define	nfserr_perm		cpu_to_be32(NFSERR_PERM)
+#define	nfserr_noent		cpu_to_be32(NFSERR_NOENT)
+#define	nfserr_io		cpu_to_be32(NFSERR_IO)
+#define	nfserr_nxio		cpu_to_be32(NFSERR_NXIO)
+#define	nfserr_eagain		cpu_to_be32(NFSERR_EAGAIN)
+#define	nfserr_acces		cpu_to_be32(NFSERR_ACCES)
+#define	nfserr_exist		cpu_to_be32(NFSERR_EXIST)
+#define	nfserr_xdev		cpu_to_be32(NFSERR_XDEV)
+#define	nfserr_nodev		cpu_to_be32(NFSERR_NODEV)
+#define	nfserr_notdir		cpu_to_be32(NFSERR_NOTDIR)
+#define	nfserr_isdir		cpu_to_be32(NFSERR_ISDIR)
+#define	nfserr_inval		cpu_to_be32(NFSERR_INVAL)
+#define	nfserr_fbig		cpu_to_be32(NFSERR_FBIG)
+#define	nfserr_nospc		cpu_to_be32(NFSERR_NOSPC)
+#define	nfserr_rofs		cpu_to_be32(NFSERR_ROFS)
+#define	nfserr_mlink		cpu_to_be32(NFSERR_MLINK)
+#define	nfserr_opnotsupp	cpu_to_be32(NFSERR_OPNOTSUPP)
+#define	nfserr_nametoolong	cpu_to_be32(NFSERR_NAMETOOLONG)
+#define	nfserr_notempty		cpu_to_be32(NFSERR_NOTEMPTY)
+#define	nfserr_dquot		cpu_to_be32(NFSERR_DQUOT)
+#define	nfserr_stale		cpu_to_be32(NFSERR_STALE)
+#define	nfserr_remote		cpu_to_be32(NFSERR_REMOTE)
+#define	nfserr_wflush		cpu_to_be32(NFSERR_WFLUSH)
+#define	nfserr_badhandle	cpu_to_be32(NFSERR_BADHANDLE)
+#define	nfserr_notsync		cpu_to_be32(NFSERR_NOT_SYNC)
+#define	nfserr_badcookie	cpu_to_be32(NFSERR_BAD_COOKIE)
+#define	nfserr_notsupp		cpu_to_be32(NFSERR_NOTSUPP)
+#define	nfserr_toosmall		cpu_to_be32(NFSERR_TOOSMALL)
+#define	nfserr_serverfault	cpu_to_be32(NFSERR_SERVERFAULT)
+#define	nfserr_badtype		cpu_to_be32(NFSERR_BADTYPE)
+#define	nfserr_jukebox		cpu_to_be32(NFSERR_JUKEBOX)
+#define	nfserr_denied		cpu_to_be32(NFSERR_DENIED)
+#define	nfserr_deadlock		cpu_to_be32(NFSERR_DEADLOCK)
+#define nfserr_expired          cpu_to_be32(NFSERR_EXPIRED)
+#define	nfserr_bad_cookie	cpu_to_be32(NFSERR_BAD_COOKIE)
+#define	nfserr_same		cpu_to_be32(NFSERR_SAME)
+#define	nfserr_clid_inuse	cpu_to_be32(NFSERR_CLID_INUSE)
+#define	nfserr_stale_clientid	cpu_to_be32(NFSERR_STALE_CLIENTID)
+#define	nfserr_resource		cpu_to_be32(NFSERR_RESOURCE)
+#define	nfserr_moved		cpu_to_be32(NFSERR_MOVED)
+#define	nfserr_nofilehandle	cpu_to_be32(NFSERR_NOFILEHANDLE)
+#define	nfserr_minor_vers_mismatch	cpu_to_be32(NFSERR_MINOR_VERS_MISMATCH)
+#define nfserr_share_denied	cpu_to_be32(NFSERR_SHARE_DENIED)
+#define nfserr_stale_stateid	cpu_to_be32(NFSERR_STALE_STATEID)
+#define nfserr_old_stateid	cpu_to_be32(NFSERR_OLD_STATEID)
+#define nfserr_bad_stateid	cpu_to_be32(NFSERR_BAD_STATEID)
+#define nfserr_bad_seqid	cpu_to_be32(NFSERR_BAD_SEQID)
+#define	nfserr_symlink		cpu_to_be32(NFSERR_SYMLINK)
+#define	nfserr_not_same		cpu_to_be32(NFSERR_NOT_SAME)
+#define	nfserr_restorefh	cpu_to_be32(NFSERR_RESTOREFH)
+#define	nfserr_attrnotsupp	cpu_to_be32(NFSERR_ATTRNOTSUPP)
+#define	nfserr_bad_xdr		cpu_to_be32(NFSERR_BAD_XDR)
+#define	nfserr_openmode		cpu_to_be32(NFSERR_OPENMODE)
+#define	nfserr_locks_held	cpu_to_be32(NFSERR_LOCKS_HELD)
+#define	nfserr_op_illegal	cpu_to_be32(NFSERR_OP_ILLEGAL)
+#define	nfserr_grace		cpu_to_be32(NFSERR_GRACE)
+#define	nfserr_no_grace		cpu_to_be32(NFSERR_NO_GRACE)
+#define	nfserr_reclaim_bad	cpu_to_be32(NFSERR_RECLAIM_BAD)
+#define	nfserr_badname		cpu_to_be32(NFSERR_BADNAME)
+#define	nfserr_cb_path_down	cpu_to_be32(NFSERR_CB_PATH_DOWN)
+#define	nfserr_locked		cpu_to_be32(NFSERR_LOCKED)
+#define	nfserr_wrongsec		cpu_to_be32(NFSERR_WRONGSEC)
+#define nfserr_badiomode		cpu_to_be32(NFS4ERR_BADIOMODE)
+#define nfserr_badlayout		cpu_to_be32(NFS4ERR_BADLAYOUT)
+#define nfserr_bad_session_digest	cpu_to_be32(NFS4ERR_BAD_SESSION_DIGEST)
+#define nfserr_badsession		cpu_to_be32(NFS4ERR_BADSESSION)
+#define nfserr_badslot			cpu_to_be32(NFS4ERR_BADSLOT)
+#define nfserr_complete_already		cpu_to_be32(NFS4ERR_COMPLETE_ALREADY)
+#define nfserr_conn_not_bound_to_session cpu_to_be32(NFS4ERR_CONN_NOT_BOUND_TO_SESSION)
+#define nfserr_deleg_already_wanted	cpu_to_be32(NFS4ERR_DELEG_ALREADY_WANTED)
+#define nfserr_back_chan_busy		cpu_to_be32(NFS4ERR_BACK_CHAN_BUSY)
+#define nfserr_layouttrylater		cpu_to_be32(NFS4ERR_LAYOUTTRYLATER)
+#define nfserr_layoutunavailable	cpu_to_be32(NFS4ERR_LAYOUTUNAVAILABLE)
+#define nfserr_nomatching_layout	cpu_to_be32(NFS4ERR_NOMATCHING_LAYOUT)
+#define nfserr_recallconflict		cpu_to_be32(NFS4ERR_RECALLCONFLICT)
+#define nfserr_unknown_layouttype	cpu_to_be32(NFS4ERR_UNKNOWN_LAYOUTTYPE)
+#define nfserr_seq_misordered		cpu_to_be32(NFS4ERR_SEQ_MISORDERED)
+#define nfserr_sequence_pos		cpu_to_be32(NFS4ERR_SEQUENCE_POS)
+#define nfserr_req_too_big		cpu_to_be32(NFS4ERR_REQ_TOO_BIG)
+#define nfserr_rep_too_big		cpu_to_be32(NFS4ERR_REP_TOO_BIG)
+#define nfserr_rep_too_big_to_cache	cpu_to_be32(NFS4ERR_REP_TOO_BIG_TO_CACHE)
+#define nfserr_retry_uncached_rep	cpu_to_be32(NFS4ERR_RETRY_UNCACHED_REP)
+#define nfserr_unsafe_compound		cpu_to_be32(NFS4ERR_UNSAFE_COMPOUND)
+#define nfserr_too_many_ops		cpu_to_be32(NFS4ERR_TOO_MANY_OPS)
+#define nfserr_op_not_in_session	cpu_to_be32(NFS4ERR_OP_NOT_IN_SESSION)
+#define nfserr_hash_alg_unsupp		cpu_to_be32(NFS4ERR_HASH_ALG_UNSUPP)
+#define nfserr_clientid_busy		cpu_to_be32(NFS4ERR_CLIENTID_BUSY)
+#define nfserr_pnfs_io_hole		cpu_to_be32(NFS4ERR_PNFS_IO_HOLE)
+#define nfserr_seq_false_retry		cpu_to_be32(NFS4ERR_SEQ_FALSE_RETRY)
+#define nfserr_bad_high_slot		cpu_to_be32(NFS4ERR_BAD_HIGH_SLOT)
+#define nfserr_deadsession		cpu_to_be32(NFS4ERR_DEADSESSION)
+#define nfserr_encr_alg_unsupp		cpu_to_be32(NFS4ERR_ENCR_ALG_UNSUPP)
+#define nfserr_pnfs_no_layout		cpu_to_be32(NFS4ERR_PNFS_NO_LAYOUT)
+#define nfserr_not_only_op		cpu_to_be32(NFS4ERR_NOT_ONLY_OP)
+#define nfserr_wrong_cred		cpu_to_be32(NFS4ERR_WRONG_CRED)
+#define nfserr_wrong_type		cpu_to_be32(NFS4ERR_WRONG_TYPE)
+#define nfserr_dirdeleg_unavail		cpu_to_be32(NFS4ERR_DIRDELEG_UNAVAIL)
+#define nfserr_reject_deleg		cpu_to_be32(NFS4ERR_REJECT_DELEG)
+#define nfserr_returnconflict		cpu_to_be32(NFS4ERR_RETURNCONFLICT)
+#define nfserr_deleg_revoked		cpu_to_be32(NFS4ERR_DELEG_REVOKED)
 
 /* error codes for internal use */
 /* if a request fails due to kmalloc failure, it gets dropped.
  *  Client should resend eventually
  */
-#define	nfserr_dropit		__constant_htonl(30000)
+#define	nfserr_dropit		cpu_to_be32(30000)
 /* end-of-file indicator in readdir */
-#define	nfserr_eof		__constant_htonl(30001)
+#define	nfserr_eof		cpu_to_be32(30001)
+/* replay detected */
+#define	nfserr_replay_me	cpu_to_be32(11001)
+/* nfs41 replay detected */
+#define	nfserr_replay_cache	cpu_to_be32(11002)
 
 /* Check for dir entries '.' and '..' */
 #define isdotent(n, l)	(l < 3 && n[0] == '.' && (l == 1 || n[1] == '.'))
@@ -300,7 +343,7 @@ extern struct timeval	nfssvc_boot;
  *    TIME_BACKUP   (unlikely to be supported any time soon)
  *    TIME_CREATE   (unlikely to be supported any time soon)
  */
-#define NFSD_SUPPORTED_ATTRS_WORD0                                                          \
+#define NFSD4_SUPPORTED_ATTRS_WORD0                                                         \
 (FATTR4_WORD0_SUPPORTED_ATTRS   | FATTR4_WORD0_TYPE         | FATTR4_WORD0_FH_EXPIRE_TYPE   \
  | FATTR4_WORD0_CHANGE          | FATTR4_WORD0_SIZE         | FATTR4_WORD0_LINK_SUPPORT     \
  | FATTR4_WORD0_SYMLINK_SUPPORT | FATTR4_WORD0_NAMED_ATTR   | FATTR4_WORD0_FSID             \
@@ -312,7 +355,7 @@ extern struct timeval	nfssvc_boot;
  | FATTR4_WORD0_MAXFILESIZE     | FATTR4_WORD0_MAXLINK      | FATTR4_WORD0_MAXNAME          \
  | FATTR4_WORD0_MAXREAD         | FATTR4_WORD0_MAXWRITE     | FATTR4_WORD0_ACL)
 
-#define NFSD_SUPPORTED_ATTRS_WORD1                                                          \
+#define NFSD4_SUPPORTED_ATTRS_WORD1                                                         \
 (FATTR4_WORD1_MODE              | FATTR4_WORD1_NO_TRUNC     | FATTR4_WORD1_NUMLINKS         \
  | FATTR4_WORD1_OWNER	        | FATTR4_WORD1_OWNER_GROUP  | FATTR4_WORD1_RAWDEV           \
  | FATTR4_WORD1_SPACE_AVAIL     | FATTR4_WORD1_SPACE_FREE   | FATTR4_WORD1_SPACE_TOTAL      \
@@ -320,6 +363,35 @@ extern struct timeval	nfssvc_boot;
  | FATTR4_WORD1_TIME_DELTA   | FATTR4_WORD1_TIME_METADATA    \
  | FATTR4_WORD1_TIME_MODIFY     | FATTR4_WORD1_TIME_MODIFY_SET | FATTR4_WORD1_MOUNTED_ON_FILEID)
 
+#define NFSD4_SUPPORTED_ATTRS_WORD2 0
+
+#define NFSD4_1_SUPPORTED_ATTRS_WORD0 \
+	NFSD4_SUPPORTED_ATTRS_WORD0
+
+#define NFSD4_1_SUPPORTED_ATTRS_WORD1 \
+	NFSD4_SUPPORTED_ATTRS_WORD1
+
+#define NFSD4_1_SUPPORTED_ATTRS_WORD2 \
+	(NFSD4_SUPPORTED_ATTRS_WORD2 | FATTR4_WORD2_SUPPATTR_EXCLCREAT)
+
+static inline u32 nfsd_suppattrs0(u32 minorversion)
+{
+	return minorversion ? NFSD4_1_SUPPORTED_ATTRS_WORD0
+			    : NFSD4_SUPPORTED_ATTRS_WORD0;
+}
+
+static inline u32 nfsd_suppattrs1(u32 minorversion)
+{
+	return minorversion ? NFSD4_1_SUPPORTED_ATTRS_WORD1
+			    : NFSD4_SUPPORTED_ATTRS_WORD1;
+}
+
+static inline u32 nfsd_suppattrs2(u32 minorversion)
+{
+	return minorversion ? NFSD4_1_SUPPORTED_ATTRS_WORD2
+			    : NFSD4_SUPPORTED_ATTRS_WORD2;
+}
+
 /* These will return ERR_INVAL if specified in GETATTR or READDIR. */
 #define NFSD_WRITEONLY_ATTRS_WORD1							    \
 (FATTR4_WORD1_TIME_ACCESS_SET   | FATTR4_WORD1_TIME_MODIFY_SET)
@@ -330,6 +402,19 @@ extern struct timeval	nfssvc_boot;
 #define NFSD_WRITEABLE_ATTRS_WORD1                                                          \
 (FATTR4_WORD1_MODE              | FATTR4_WORD1_OWNER         | FATTR4_WORD1_OWNER_GROUP     \
  | FATTR4_WORD1_TIME_ACCESS_SET | FATTR4_WORD1_TIME_MODIFY_SET)
+#define NFSD_WRITEABLE_ATTRS_WORD2 0
+
+#define NFSD_SUPPATTR_EXCLCREAT_WORD0 \
+	NFSD_WRITEABLE_ATTRS_WORD0
+/*
+ * we currently store the exclusive create verifier in the v_{a,m}time
+ * attributes so the client can't set these at create time using EXCLUSIVE4_1
+ */
+#define NFSD_SUPPATTR_EXCLCREAT_WORD1 \
+	(NFSD_WRITEABLE_ATTRS_WORD1 & \
+	 ~(FATTR4_WORD1_TIME_ACCESS_SET | FATTR4_WORD1_TIME_MODIFY_SET))
+#define NFSD_SUPPATTR_EXCLCREAT_WORD2 \
+	NFSD_WRITEABLE_ATTRS_WORD2
 
 #endif /* CONFIG_NFSD_V4 */
 

include/linux/nfsd/nfsfh.h

@@ -269,6 +269,13 @@ fh_copy(struct svc_fh *dst, struct svc_fh *src)
 	return dst;
 }
 
+static inline void
+fh_copy_shallow(struct knfsd_fh *dst, struct knfsd_fh *src)
+{
+	dst->fh_size = src->fh_size;
+	memcpy(&dst->fh_base, &src->fh_base, src->fh_size);
+}
+
 static __inline__ struct svc_fh *
 fh_init(struct svc_fh *fhp, int maxsize)
 {

include/linux/nfsd/state.h

@@ -66,8 +66,7 @@ struct nfs4_cb_recall {
 	u32			cbr_ident;
 	int			cbr_trunc;
 	stateid_t		cbr_stateid;
-	u32			cbr_fhlen;
-	char			cbr_fhval[NFS4_FHSIZE];
+	struct knfsd_fh		cbr_fh;
 	struct nfs4_delegation	*cbr_dp;
 };
 
@@ -86,8 +85,7 @@ struct nfs4_delegation {
 };
 
 #define dl_stateid      dl_recall.cbr_stateid
-#define dl_fhlen        dl_recall.cbr_fhlen
-#define dl_fhval        dl_recall.cbr_fhval
+#define dl_fh           dl_recall.cbr_fh
 
 /* client delegation callback info */
 struct nfs4_callback {
@@ -101,6 +99,64 @@ struct nfs4_callback {
 	struct rpc_clnt *       cb_client;
 };
 
+/* Maximum number of slots per session. 128 is useful for long haul TCP */
+#define NFSD_MAX_SLOTS_PER_SESSION	128
+/* Maximum number of pages per slot cache entry */
+#define NFSD_PAGES_PER_SLOT	1
+/* Maximum number of operations per session compound */
+#define NFSD_MAX_OPS_PER_COMPOUND	16
+
+struct nfsd4_cache_entry {
+	__be32		ce_status;
+	struct kvec	ce_datav; /* encoded NFSv4.1 data in rq_res.head[0] */
+	struct page	*ce_respages[NFSD_PAGES_PER_SLOT + 1];
+	int		ce_cachethis;
+	short		ce_resused;
+	int		ce_opcnt;
+	int		ce_rpchdrlen;
+};
+
+struct nfsd4_slot {
+	bool				sl_inuse;
+	u32				sl_seqid;
+	struct nfsd4_cache_entry	sl_cache_entry;
+};
+
+struct nfsd4_session {
+	struct kref		se_ref;
+	struct list_head	se_hash;	/* hash by sessionid */
+	struct list_head	se_perclnt;
+	u32			se_flags;
+	struct nfs4_client	*se_client;	/* for expire_client */
+	struct nfs4_sessionid	se_sessionid;
+	u32			se_fmaxreq_sz;
+	u32			se_fmaxresp_sz;
+	u32			se_fmaxresp_cached;
+	u32			se_fmaxops;
+	u32			se_fnumslots;
+	struct nfsd4_slot	se_slots[];	/* forward channel slots */
+};
+
+static inline void
+nfsd4_put_session(struct nfsd4_session *ses)
+{
+	extern void free_session(struct kref *kref);
+	kref_put(&ses->se_ref, free_session);
+}
+
+static inline void
+nfsd4_get_session(struct nfsd4_session *ses)
+{
+	kref_get(&ses->se_ref);
+}
+
+/* formatted contents of nfs4_sessionid */
+struct nfsd4_sessionid {
+	clientid_t	clientid;
+	u32		sequence;
+	u32		reserved;
+};
+
 #define HEXDIR_LEN     33 /* hex version of 16 byte md5 of cl_name plus '\0' */
 
 /*
@@ -132,6 +188,12 @@ struct nfs4_client {
 	struct nfs4_callback	cl_callback;    /* callback info */
 	atomic_t		cl_count;	/* ref count */
 	u32			cl_firststate;	/* recovery dir creation */
+
+	/* for nfs41 */
+	struct list_head	cl_sessions;
+	struct nfsd4_slot	cl_slot;	/* create_session slot */
+	u32			cl_exchange_flags;
+	struct nfs4_sessionid	cl_sessionid;
 };
 
 /* struct nfs4_client_reset
@@ -168,8 +230,7 @@ struct nfs4_replay {
 	unsigned int		rp_buflen;
 	char			*rp_buf;
 	unsigned		intrp_allocated;
-	int			rp_openfh_len;
-	char			rp_openfh[NFS4_FHSIZE];
+	struct knfsd_fh		rp_openfh;
 	char			rp_ibuf[NFSD4_REPLAY_ISIZE];
 };
 
@@ -217,7 +278,7 @@ struct nfs4_stateowner {
 *      share_acces, share_deny on the file.
 */
 struct nfs4_file {
-	struct kref		fi_ref;
+	atomic_t		fi_ref;
 	struct list_head        fi_hash;    /* hash by "struct inode *" */
 	struct list_head        fi_stateids;
 	struct list_head	fi_delegations;
@@ -259,14 +320,13 @@ struct nfs4_stateid {
 };
 
 /* flags for preprocess_seqid_op() */
-#define CHECK_FH                0x00000001
+#define HAS_SESSION             0x00000001
 #define CONFIRM                 0x00000002
 #define OPEN_STATE              0x00000004
 #define LOCK_STATE              0x00000008
 #define RD_STATE	        0x00000010
 #define WR_STATE	        0x00000020
 #define CLOSE_STATE             0x00000040
-#define DELEG_RET               0x00000080
 
 #define seqid_mutating_err(err)                       \
 	(((err) != nfserr_stale_clientid) &&    \
@@ -274,7 +334,9 @@ struct nfs4_stateid {
 	((err) != nfserr_stale_stateid) &&      \
 	((err) != nfserr_bad_stateid))
 
-extern __be32 nfs4_preprocess_stateid_op(struct svc_fh *current_fh,
+struct nfsd4_compound_state;
+
+extern __be32 nfs4_preprocess_stateid_op(struct nfsd4_compound_state *cstate,
 		stateid_t *stateid, int flags, struct file **filp);
 extern void nfs4_lock_state(void);
 extern void nfs4_unlock_state(void);
@@ -290,7 +352,7 @@ extern void nfsd4_init_recdir(char *recdir_name);
 extern int nfsd4_recdir_load(void);
 extern void nfsd4_shutdown_recdir(void);
 extern int nfs4_client_to_reclaim(const char *name);
-extern int nfs4_has_reclaimed_state(const char *name);
+extern int nfs4_has_reclaimed_state(const char *name, bool use_exchange_id);
 extern void nfsd4_recdir_purge_old(void);
 extern int nfsd4_create_clid_dir(struct nfs4_client *clp);
 extern void nfsd4_remove_clid_dir(struct nfs4_client *clp);

include/linux/nfsd/stats.h

@@ -11,6 +11,11 @@
 
 #include <linux/nfs4.h>
 
+/* thread usage wraps very million seconds (approx one fortnight) */
+#define	NFSD_USAGE_WRAP	(HZ*1000000)
+
+#ifdef __KERNEL__
+
 struct nfsd_stats {
 	unsigned int	rchits;		/* repcache hits */
 	unsigned int	rcmisses;	/* repcache hits */
@@ -35,10 +40,6 @@ struct nfsd_stats {
 
 };
 
-/* thread usage wraps very million seconds (approx one fortnight) */
-#define	NFSD_USAGE_WRAP	(HZ*1000000)
-
-#ifdef __KERNEL__
 
 extern struct nfsd_stats	nfsdstats;
 extern struct svc_stat		nfsd_svcstats;

include/linux/nfsd/xdr4.h

@@ -45,11 +45,23 @@
 #define XDR_LEN(n)                     (((n) + 3) & ~3)
 
 struct nfsd4_compound_state {
-	struct svc_fh current_fh;
-	struct svc_fh save_fh;
-	struct nfs4_stateowner *replay_owner;
+	struct svc_fh		current_fh;
+	struct svc_fh		save_fh;
+	struct nfs4_stateowner	*replay_owner;
+	/* For sessions DRC */
+	struct nfsd4_session	*session;
+	struct nfsd4_slot	*slot;
+	__be32			*statp;
+	size_t			iovlen;
+	u32			minorversion;
+	u32			status;
 };
 
+static inline bool nfsd4_has_session(struct nfsd4_compound_state *cs)
+{
+	return cs->slot != NULL;
+}
+
 struct nfsd4_change_info {
 	u32		atomic;
 	u32		before_ctime_sec;
@@ -90,7 +102,7 @@ struct nfsd4_create {
 			u32 specdata2;
 		} dev;    /* NF4BLK, NF4CHR */
 	} u;
-	u32		cr_bmval[2];        /* request */
+	u32		cr_bmval[3];        /* request */
 	struct iattr	cr_iattr;           /* request */
 	struct nfsd4_change_info  cr_cinfo; /* response */
 	struct nfs4_acl *cr_acl;
@@ -105,7 +117,7 @@ struct nfsd4_delegreturn {
 };
 
 struct nfsd4_getattr {
-	u32		ga_bmval[2];        /* request */
+	u32		ga_bmval[3];        /* request */
 	struct svc_fh	*ga_fhp;            /* response */
 };
 
@@ -206,11 +218,9 @@ struct nfsd4_open {
 	stateid_t       op_delegate_stateid; /* request - response */
 	u32		op_create;     	    /* request */
 	u32		op_createmode;      /* request */
-	u32		op_bmval[2];        /* request */
-	union {                             /* request */
-		struct iattr	iattr;                      /* UNCHECKED4,GUARDED4 */
-		nfs4_verifier	verf;                                /* EXCLUSIVE4 */
-	} u;
+	u32		op_bmval[3];        /* request */
+	struct iattr	iattr;              /* UNCHECKED4, GUARDED4, EXCLUSIVE4_1 */
+	nfs4_verifier	verf;               /* EXCLUSIVE4 */
 	clientid_t	op_clientid;        /* request */
 	struct xdr_netobj op_owner;           /* request */
 	u32		op_seqid;           /* request */
@@ -224,8 +234,8 @@ struct nfsd4_open {
 	struct nfs4_stateowner *op_stateowner; /* used during processing */
 	struct nfs4_acl *op_acl;
 };
-#define op_iattr	u.iattr
-#define op_verf		u.verf
+#define op_iattr	iattr
+#define op_verf		verf
 
 struct nfsd4_open_confirm {
 	stateid_t	oc_req_stateid		/* request */;
@@ -259,7 +269,7 @@ struct nfsd4_readdir {
 	nfs4_verifier	rd_verf;            /* request */
 	u32		rd_dircount;        /* request */
 	u32		rd_maxcount;        /* request */
-	u32		rd_bmval[2];        /* request */
+	u32		rd_bmval[3];        /* request */
 	struct svc_rqst *rd_rqstp;          /* response */
 	struct svc_fh * rd_fhp;             /* response */
 
@@ -301,7 +311,7 @@ struct nfsd4_secinfo {
 
 struct nfsd4_setattr {
 	stateid_t	sa_stateid;         /* request */
-	u32		sa_bmval[2];        /* request */
+	u32		sa_bmval[3];        /* request */
 	struct iattr	sa_iattr;           /* request */
 	struct nfs4_acl *sa_acl;
 };
@@ -327,7 +337,7 @@ struct nfsd4_setclientid_confirm {
 
 /* also used for NVERIFY */
 struct nfsd4_verify {
-	u32		ve_bmval[2];        /* request */
+	u32		ve_bmval[3];        /* request */
 	u32		ve_attrlen;         /* request */
 	char *		ve_attrval;         /* request */
 };
@@ -344,6 +354,54 @@ struct nfsd4_write {
 	nfs4_verifier	wr_verifier;        /* response */
 };
 
+struct nfsd4_exchange_id {
+	nfs4_verifier	verifier;
+	struct xdr_netobj clname;
+	u32		flags;
+	clientid_t	clientid;
+	u32		seqid;
+	int		spa_how;
+};
+
+struct nfsd4_channel_attrs {
+	u32		headerpadsz;
+	u32		maxreq_sz;
+	u32		maxresp_sz;
+	u32		maxresp_cached;
+	u32		maxops;
+	u32		maxreqs;
+	u32		nr_rdma_attrs;
+	u32		rdma_attrs;
+};
+
+struct nfsd4_create_session {
+	clientid_t		clientid;
+	struct nfs4_sessionid	sessionid;
+	u32			seqid;
+	u32			flags;
+	struct nfsd4_channel_attrs fore_channel;
+	struct nfsd4_channel_attrs back_channel;
+	u32			callback_prog;
+	u32			uid;
+	u32			gid;
+};
+
+struct nfsd4_sequence {
+	struct nfs4_sessionid	sessionid;		/* request/response */
+	u32			seqid;			/* request/response */
+	u32			slotid;			/* request/response */
+	u32			maxslots;		/* request/response */
+	u32			cachethis;		/* request */
+#if 0
+	u32			target_maxslots;	/* response */
+	u32			status_flags;		/* response */
+#endif /* not yet */
+};
+
+struct nfsd4_destroy_session {
+	struct nfs4_sessionid	sessionid;
+};
+
 struct nfsd4_op {
 	int					opnum;
 	__be32					status;
@@ -378,6 +436,12 @@ struct nfsd4_op {
 		struct nfsd4_verify		verify;
 		struct nfsd4_write		write;
 		struct nfsd4_release_lockowner	release_lockowner;
+
+		/* NFSv4.1 */
+		struct nfsd4_exchange_id	exchange_id;
+		struct nfsd4_create_session	create_session;
+		struct nfsd4_destroy_session	destroy_session;
+		struct nfsd4_sequence		sequence;
 	} u;
 	struct nfs4_replay *			replay;
 };
@@ -416,9 +480,22 @@ struct nfsd4_compoundres {
 	u32				taglen;
 	char *				tag;
 	u32				opcnt;
-	__be32 *			tagp; /* where to encode tag and  opcount */
+	__be32 *			tagp; /* tag, opcount encode location */
+	struct nfsd4_compound_state	cstate;
 };
 
+static inline bool nfsd4_is_solo_sequence(struct nfsd4_compoundres *resp)
+{
+	struct nfsd4_compoundargs *args = resp->rqstp->rq_argp;
+	return args->opcnt == 1;
+}
+
+static inline bool nfsd4_not_cached(struct nfsd4_compoundres *resp)
+{
+	return !resp->cstate.slot->sl_cache_entry.ce_cachethis ||
+			nfsd4_is_solo_sequence(resp);
+}
+
 #define NFS4_SVC_XDRSIZE		sizeof(struct nfsd4_compoundargs)
 
 static inline void
@@ -448,7 +525,23 @@ extern __be32 nfsd4_setclientid(struct svc_rqst *rqstp,
 extern __be32 nfsd4_setclientid_confirm(struct svc_rqst *rqstp,
 		struct nfsd4_compound_state *,
 		struct nfsd4_setclientid_confirm *setclientid_confirm);
-extern __be32 nfsd4_process_open1(struct nfsd4_open *open);
+extern void nfsd4_store_cache_entry(struct nfsd4_compoundres *resp);
+extern __be32 nfsd4_replay_cache_entry(struct nfsd4_compoundres *resp,
+		struct nfsd4_sequence *seq);
+extern __be32 nfsd4_exchange_id(struct svc_rqst *rqstp,
+		struct nfsd4_compound_state *,
+struct nfsd4_exchange_id *);
+		extern __be32 nfsd4_create_session(struct svc_rqst *,
+		struct nfsd4_compound_state *,
+		struct nfsd4_create_session *);
+extern __be32 nfsd4_sequence(struct svc_rqst *,
+		struct nfsd4_compound_state *,
+		struct nfsd4_sequence *);
+extern __be32 nfsd4_destroy_session(struct svc_rqst *,
+		struct nfsd4_compound_state *,
+		struct nfsd4_destroy_session *);
+extern __be32 nfsd4_process_open1(struct nfsd4_compound_state *,
+		struct nfsd4_open *open);
 extern __be32 nfsd4_process_open2(struct svc_rqst *rqstp,
 		struct svc_fh *current_fh, struct nfsd4_open *open);
 extern __be32 nfsd4_open_confirm(struct svc_rqst *rqstp,

include/linux/nilfs2_fs.h

@@ -0,0 +1,801 @@
+/*
+ * nilfs2_fs.h - NILFS2 on-disk structures and common declarations.
+ *
+ * Copyright (C) 2005-2008 Nippon Telegraph and Telephone Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
+ *
+ * Written by Koji Sato <koji@osrg.net>
+ *            Ryusuke Konishi <ryusuke@osrg.net>
+ */
+/*
+ *  linux/include/linux/ext2_fs.h
+ *
+ * Copyright (C) 1992, 1993, 1994, 1995
+ * Remy Card (card@masi.ibp.fr)
+ * Laboratoire MASI - Institut Blaise Pascal
+ * Universite Pierre et Marie Curie (Paris VI)
+ *
+ *  from
+ *
+ *  linux/include/linux/minix_fs.h
+ *
+ *  Copyright (C) 1991, 1992  Linus Torvalds
+ */
+
+#ifndef _LINUX_NILFS_FS_H
+#define _LINUX_NILFS_FS_H
+
+#include <linux/types.h>
+#include <linux/ioctl.h>
+
+/*
+ * Inode flags stored in nilfs_inode and on-memory nilfs inode
+ *
+ * We define these flags based on ext2-fs because of the
+ * compatibility reason; to avoid problems in chattr(1)
+ */
+#define NILFS_SECRM_FL		0x00000001 /* Secure deletion */
+#define NILFS_UNRM_FL		0x00000002 /* Undelete */
+#define NILFS_SYNC_FL		0x00000008 /* Synchronous updates */
+#define NILFS_IMMUTABLE_FL	0x00000010 /* Immutable file */
+#define NILFS_APPEND_FL		0x00000020 /* writes to file may only append */
+#define NILFS_NODUMP_FL		0x00000040 /* do not dump file */
+#define NILFS_NOATIME_FL	0x00000080 /* do not update atime */
+/* Reserved for compression usage... */
+#define NILFS_NOTAIL_FL		0x00008000 /* file tail should not be merged */
+#define NILFS_DIRSYNC_FL	0x00010000 /* dirsync behaviour */
+
+#define NILFS_FL_USER_VISIBLE	0x0003DFFF /* User visible flags */
+#define NILFS_FL_USER_MODIFIABLE	0x000380FF /* User modifiable flags */
+
+
+#define NILFS_INODE_BMAP_SIZE	7
+/**
+ * struct nilfs_inode - structure of an inode on disk
+ * @i_blocks: blocks count
+ * @i_size: size in bytes
+ * @i_ctime: creation time (seconds)
+ * @i_mtime: modification time (seconds)
+ * @i_ctime_nsec: creation time (nano seconds)
+ * @i_mtime_nsec: modification time (nano seconds)
+ * @i_uid: user id
+ * @i_gid: group id
+ * @i_mode: file mode
+ * @i_links_count: links count
+ * @i_flags: file flags
+ * @i_bmap: block mapping
+ * @i_xattr: extended attributes
+ * @i_generation: file generation (for NFS)
+ * @i_pad:	padding
+ */
+struct nilfs_inode {
+	__le64	i_blocks;
+	__le64	i_size;
+	__le64	i_ctime;
+	__le64	i_mtime;
+	__le32	i_ctime_nsec;
+	__le32	i_mtime_nsec;
+	__le32	i_uid;
+	__le32	i_gid;
+	__le16	i_mode;
+	__le16	i_links_count;
+	__le32	i_flags;
+	__le64	i_bmap[NILFS_INODE_BMAP_SIZE];
+#define i_device_code	i_bmap[0]
+	__le64	i_xattr;
+	__le32	i_generation;
+	__le32	i_pad;
+};
+
+/**
+ * struct nilfs_super_root - structure of super root
+ * @sr_sum: check sum
+ * @sr_bytes: byte count of the structure
+ * @sr_flags: flags (reserved)
+ * @sr_nongc_ctime: write time of the last segment not for cleaner operation
+ * @sr_dat: DAT file inode
+ * @sr_cpfile: checkpoint file inode
+ * @sr_sufile: segment usage file inode
+ */
+struct nilfs_super_root {
+	__le32 sr_sum;
+	__le16 sr_bytes;
+	__le16 sr_flags;
+	__le64 sr_nongc_ctime;
+	struct nilfs_inode sr_dat;
+	struct nilfs_inode sr_cpfile;
+	struct nilfs_inode sr_sufile;
+};
+
+#define NILFS_SR_MDT_OFFSET(inode_size, i)  \
+	((unsigned long)&((struct nilfs_super_root *)0)->sr_dat + \
+			(inode_size) * (i))
+#define NILFS_SR_DAT_OFFSET(inode_size)     NILFS_SR_MDT_OFFSET(inode_size, 0)
+#define NILFS_SR_CPFILE_OFFSET(inode_size)  NILFS_SR_MDT_OFFSET(inode_size, 1)
+#define NILFS_SR_SUFILE_OFFSET(inode_size)  NILFS_SR_MDT_OFFSET(inode_size, 2)
+#define NILFS_SR_BYTES                  (sizeof(struct nilfs_super_root))
+
+/*
+ * Maximal mount counts
+ */
+#define NILFS_DFL_MAX_MNT_COUNT		50      /* 50 mounts */
+
+/*
+ * File system states (sbp->s_state, nilfs->ns_mount_state)
+ */
+#define NILFS_VALID_FS			0x0001  /* Unmounted cleanly */
+#define NILFS_ERROR_FS			0x0002  /* Errors detected */
+#define NILFS_RESIZE_FS			0x0004	/* Resize required */
+
+/*
+ * Mount flags (sbi->s_mount_opt)
+ */
+#define NILFS_MOUNT_ERROR_MODE		0x0070  /* Error mode mask */
+#define NILFS_MOUNT_ERRORS_CONT		0x0010  /* Continue on errors */
+#define NILFS_MOUNT_ERRORS_RO		0x0020  /* Remount fs ro on errors */
+#define NILFS_MOUNT_ERRORS_PANIC	0x0040  /* Panic on errors */
+#define NILFS_MOUNT_SNAPSHOT		0x0080  /* Snapshot flag */
+#define NILFS_MOUNT_BARRIER		0x1000  /* Use block barriers */
+#define NILFS_MOUNT_STRICT_ORDER	0x2000  /* Apply strict in-order
+						   semantics also for data */
+
+
+/**
+ * struct nilfs_super_block - structure of super block on disk
+ */
+struct nilfs_super_block {
+	__le32	s_rev_level;		/* Revision level */
+	__le16	s_minor_rev_level;	/* minor revision level */
+	__le16	s_magic;		/* Magic signature */
+
+	__le16  s_bytes;		/* Bytes count of CRC calculation
+					   for this structure. s_reserved
+					   is excluded. */
+	__le16  s_flags;		/* flags */
+	__le32  s_crc_seed;		/* Seed value of CRC calculation */
+	__le32	s_sum;			/* Check sum of super block */
+
+	__le32	s_log_block_size;	/* Block size represented as follows
+					   blocksize =
+					       1 << (s_log_block_size + 10) */
+	__le64  s_nsegments;		/* Number of segments in filesystem */
+	__le64  s_dev_size;		/* block device size in bytes */
+	__le64	s_first_data_block;	/* 1st seg disk block number */
+	__le32  s_blocks_per_segment;   /* number of blocks per full segment */
+	__le32	s_r_segments_percentage; /* Reserved segments percentage */
+
+	__le64  s_last_cno;		/* Last checkpoint number */
+	__le64  s_last_pseg;		/* disk block addr pseg written last */
+	__le64  s_last_seq;             /* seq. number of seg written last */
+	__le64	s_free_blocks_count;	/* Free blocks count */
+
+	__le64	s_ctime;		/* Creation time (execution time of
+					   newfs) */
+	__le64	s_mtime;		/* Mount time */
+	__le64	s_wtime;		/* Write time */
+	__le16	s_mnt_count;		/* Mount count */
+	__le16	s_max_mnt_count;	/* Maximal mount count */
+	__le16	s_state;		/* File system state */
+	__le16	s_errors;		/* Behaviour when detecting errors */
+	__le64	s_lastcheck;		/* time of last check */
+
+	__le32	s_checkinterval;	/* max. time between checks */
+	__le32	s_creator_os;		/* OS */
+	__le16	s_def_resuid;		/* Default uid for reserved blocks */
+	__le16	s_def_resgid;		/* Default gid for reserved blocks */
+	__le32	s_first_ino; 		/* First non-reserved inode */
+
+	__le16  s_inode_size; 		/* Size of an inode */
+	__le16  s_dat_entry_size;       /* Size of a dat entry */
+	__le16  s_checkpoint_size;      /* Size of a checkpoint */
+	__le16	s_segment_usage_size;	/* Size of a segment usage */
+
+	__u8	s_uuid[16];		/* 128-bit uuid for volume */
+	char	s_volume_name[16]; 	/* volume name */
+	char	s_last_mounted[64]; 	/* directory where last mounted */
+
+	__le32  s_c_interval;           /* Commit interval of segment */
+	__le32  s_c_block_max;          /* Threshold of data amount for
+					   the segment construction */
+	__u32	s_reserved[192];	/* padding to the end of the block */
+};
+
+/*
+ * Codes for operating systems
+ */
+#define NILFS_OS_LINUX		0
+/* Codes from 1 to 4 are reserved to keep compatibility with ext2 creator-OS */
+
+/*
+ * Revision levels
+ */
+#define NILFS_CURRENT_REV	2	/* current major revision */
+#define NILFS_MINOR_REV		0	/* minor revision */
+
+/*
+ * Bytes count of super_block for CRC-calculation
+ */
+#define NILFS_SB_BYTES  \
+	((long)&((struct nilfs_super_block *)0)->s_reserved)
+
+/*
+ * Special inode number
+ */
+#define NILFS_ROOT_INO		2	/* Root file inode */
+#define NILFS_DAT_INO		3	/* DAT file */
+#define NILFS_CPFILE_INO	4	/* checkpoint file */
+#define NILFS_SUFILE_INO	5	/* segment usage file */
+#define NILFS_IFILE_INO		6	/* ifile */
+#define NILFS_ATIME_INO		7	/* Atime file (reserved) */
+#define NILFS_XATTR_INO		8	/* Xattribute file (reserved) */
+#define NILFS_SKETCH_INO	10	/* Sketch file */
+#define NILFS_USER_INO		11	/* Fisrt user's file inode number */
+
+#define NILFS_SB_OFFSET_BYTES	1024	/* byte offset of nilfs superblock */
+#define NILFS_SUPER_MAGIC	0x3434	/* NILFS filesystem  magic number */
+
+#define NILFS_SEG_MIN_BLOCKS	16	/* Minimum number of blocks in
+					   a full segment */
+#define NILFS_PSEG_MIN_BLOCKS	2	/* Minimum number of blocks in
+					   a partial segment */
+#define NILFS_MIN_NRSVSEGS	8	/* Minimum number of reserved
+					   segments */
+
+/*
+ * bytes offset of secondary super block
+ */
+#define NILFS_SB2_OFFSET_BYTES(devsize)	((((devsize) >> 12) - 1) << 12)
+
+/*
+ * Maximal count of links to a file
+ */
+#define NILFS_LINK_MAX		32000
+
+/*
+ * Structure of a directory entry
+ *  (Same as ext2)
+ */
+
+#define NILFS_NAME_LEN 255
+
+/*
+ * The new version of the directory entry.  Since V0 structures are
+ * stored in intel byte order, and the name_len field could never be
+ * bigger than 255 chars, it's safe to reclaim the extra byte for the
+ * file_type field.
+ */
+struct nilfs_dir_entry {
+	__le64	inode;			/* Inode number */
+	__le16	rec_len;		/* Directory entry length */
+	__u8	name_len;		/* Name length */
+	__u8	file_type;
+	char	name[NILFS_NAME_LEN];	/* File name */
+	char    pad;
+};
+
+/*
+ * NILFS directory file types.  Only the low 3 bits are used.  The
+ * other bits are reserved for now.
+ */
+enum {
+	NILFS_FT_UNKNOWN,
+	NILFS_FT_REG_FILE,
+	NILFS_FT_DIR,
+	NILFS_FT_CHRDEV,
+	NILFS_FT_BLKDEV,
+	NILFS_FT_FIFO,
+	NILFS_FT_SOCK,
+	NILFS_FT_SYMLINK,
+	NILFS_FT_MAX
+};
+
+/*
+ * NILFS_DIR_PAD defines the directory entries boundaries
+ *
+ * NOTE: It must be a multiple of 8
+ */
+#define NILFS_DIR_PAD			8
+#define NILFS_DIR_ROUND			(NILFS_DIR_PAD - 1)
+#define NILFS_DIR_REC_LEN(name_len)	(((name_len) + 12 + NILFS_DIR_ROUND) & \
+					~NILFS_DIR_ROUND)
+
+
+/**
+ * struct nilfs_finfo - file information
+ * @fi_ino: inode number
+ * @fi_cno: checkpoint number
+ * @fi_nblocks: number of blocks (including intermediate blocks)
+ * @fi_ndatablk: number of file data blocks
+ */
+struct nilfs_finfo {
+	__le64 fi_ino;
+	__le64 fi_cno;
+	__le32 fi_nblocks;
+	__le32 fi_ndatablk;
+	/* array of virtual block numbers */
+};
+
+/**
+ * struct nilfs_binfo_v - information for the block to which a virtual block number is assigned
+ * @bi_vblocknr: virtual block number
+ * @bi_blkoff: block offset
+ */
+struct nilfs_binfo_v {
+	__le64 bi_vblocknr;
+	__le64 bi_blkoff;
+};
+
+/**
+ * struct nilfs_binfo_dat - information for the block which belongs to the DAT file
+ * @bi_blkoff: block offset
+ * @bi_level: level
+ * @bi_pad: padding
+ */
+struct nilfs_binfo_dat {
+	__le64 bi_blkoff;
+	__u8 bi_level;
+	__u8 bi_pad[7];
+};
+
+/**
+ * union nilfs_binfo: block information
+ * @bi_v: nilfs_binfo_v structure
+ * @bi_dat: nilfs_binfo_dat structure
+ */
+union nilfs_binfo {
+	struct nilfs_binfo_v bi_v;
+	struct nilfs_binfo_dat bi_dat;
+};
+
+/**
+ * struct nilfs_segment_summary - segment summary
+ * @ss_datasum: checksum of data
+ * @ss_sumsum: checksum of segment summary
+ * @ss_magic: magic number
+ * @ss_bytes: size of this structure in bytes
+ * @ss_flags: flags
+ * @ss_seq: sequence number
+ * @ss_create: creation timestamp
+ * @ss_next: next segment
+ * @ss_nblocks: number of blocks
+ * @ss_nfinfo: number of finfo structures
+ * @ss_sumbytes: total size of segment summary in bytes
+ * @ss_pad: padding
+ */
+struct nilfs_segment_summary {
+	__le32 ss_datasum;
+	__le32 ss_sumsum;
+	__le32 ss_magic;
+	__le16 ss_bytes;
+	__le16 ss_flags;
+	__le64 ss_seq;
+	__le64 ss_create;
+	__le64 ss_next;
+	__le32 ss_nblocks;
+	__le32 ss_nfinfo;
+	__le32 ss_sumbytes;
+	__le32 ss_pad;
+	/* array of finfo structures */
+};
+
+#define NILFS_SEGSUM_MAGIC	0x1eaffa11  /* segment summary magic number */
+
+/*
+ * Segment summary flags
+ */
+#define NILFS_SS_LOGBGN 0x0001  /* begins a logical segment */
+#define NILFS_SS_LOGEND 0x0002  /* ends a logical segment */
+#define NILFS_SS_SR     0x0004  /* has super root */
+#define NILFS_SS_SYNDT  0x0008  /* includes data only updates */
+#define NILFS_SS_GC     0x0010  /* segment written for cleaner operation */
+
+/**
+ * struct nilfs_palloc_group_desc - block group descriptor
+ * @pg_nfrees: number of free entries in block group
+ */
+struct nilfs_palloc_group_desc {
+	__le32 pg_nfrees;
+};
+
+/**
+ * struct nilfs_dat_entry - disk address translation entry
+ * @dt_blocknr: block number
+ * @dt_start: start checkpoint number
+ * @dt_end: end checkpoint number
+ * @dt_rsv: reserved for future use
+ */
+struct nilfs_dat_entry {
+	__le64 de_blocknr;
+	__le64 de_start;
+	__le64 de_end;
+	__le64 de_rsv;
+};
+
+/**
+ * struct nilfs_dat_group_desc - block group descriptor
+ * @dg_nfrees: number of free virtual block numbers in block group
+ */
+struct nilfs_dat_group_desc {
+	__le32 dg_nfrees;
+};
+
+
+/**
+ * struct nilfs_snapshot_list - snapshot list
+ * @ssl_next: next checkpoint number on snapshot list
+ * @ssl_prev: previous checkpoint number on snapshot list
+ */
+struct nilfs_snapshot_list {
+	__le64 ssl_next;
+	__le64 ssl_prev;
+};
+
+/**
+ * struct nilfs_checkpoint - checkpoint structure
+ * @cp_flags: flags
+ * @cp_checkpoints_count: checkpoints count in a block
+ * @cp_snapshot_list: snapshot list
+ * @cp_cno: checkpoint number
+ * @cp_create: creation timestamp
+ * @cp_nblk_inc: number of blocks incremented by this checkpoint
+ * @cp_inodes_count: inodes count
+ * @cp_blocks_count: blocks count
+ * @cp_ifile_inode: inode of ifile
+ */
+struct nilfs_checkpoint {
+	__le32 cp_flags;
+	__le32 cp_checkpoints_count;
+	struct nilfs_snapshot_list cp_snapshot_list;
+	__le64 cp_cno;
+	__le64 cp_create;
+	__le64 cp_nblk_inc;
+	__le64 cp_inodes_count;
+	__le64 cp_blocks_count;		/* Reserved (might be deleted) */
+
+	/* Do not change the byte offset of ifile inode.
+	   To keep the compatibility of the disk format,
+	   additional fields should be added behind cp_ifile_inode. */
+	struct nilfs_inode cp_ifile_inode;
+};
+
+/* checkpoint flags */
+enum {
+	NILFS_CHECKPOINT_SNAPSHOT,
+	NILFS_CHECKPOINT_INVALID,
+	NILFS_CHECKPOINT_SKETCH,
+	NILFS_CHECKPOINT_MINOR,
+};
+
+#define NILFS_CHECKPOINT_FNS(flag, name)				\
+static inline void							\
+nilfs_checkpoint_set_##name(struct nilfs_checkpoint *cp)		\
+{									\
+	cp->cp_flags = cpu_to_le32(le32_to_cpu(cp->cp_flags) |		\
+				   (1UL << NILFS_CHECKPOINT_##flag));	\
+}									\
+static inline void							\
+nilfs_checkpoint_clear_##name(struct nilfs_checkpoint *cp)		\
+{									\
+	cp->cp_flags = cpu_to_le32(le32_to_cpu(cp->cp_flags) &		\
+				   ~(1UL << NILFS_CHECKPOINT_##flag));	\
+}									\
+static inline int							\
+nilfs_checkpoint_##name(const struct nilfs_checkpoint *cp)		\
+{									\
+	return !!(le32_to_cpu(cp->cp_flags) &				\
+		  (1UL << NILFS_CHECKPOINT_##flag));			\
+}
+
+NILFS_CHECKPOINT_FNS(SNAPSHOT, snapshot)
+NILFS_CHECKPOINT_FNS(INVALID, invalid)
+NILFS_CHECKPOINT_FNS(MINOR, minor)
+
+/**
+ * struct nilfs_cpinfo - checkpoint information
+ * @ci_flags: flags
+ * @ci_pad: padding
+ * @ci_cno: checkpoint number
+ * @ci_create: creation timestamp
+ * @ci_nblk_inc: number of blocks incremented by this checkpoint
+ * @ci_inodes_count: inodes count
+ * @ci_blocks_count: blocks count
+ * @ci_next: next checkpoint number in snapshot list
+ */
+struct nilfs_cpinfo {
+	__u32 ci_flags;
+	__u32 ci_pad;
+	__u64 ci_cno;
+	__u64 ci_create;
+	__u64 ci_nblk_inc;
+	__u64 ci_inodes_count;
+	__u64 ci_blocks_count;
+	__u64 ci_next;
+};
+
+#define NILFS_CPINFO_FNS(flag, name)					\
+static inline int							\
+nilfs_cpinfo_##name(const struct nilfs_cpinfo *cpinfo)			\
+{									\
+	return !!(cpinfo->ci_flags & (1UL << NILFS_CHECKPOINT_##flag));	\
+}
+
+NILFS_CPINFO_FNS(SNAPSHOT, snapshot)
+NILFS_CPINFO_FNS(INVALID, invalid)
+NILFS_CPINFO_FNS(MINOR, minor)
+
+
+/**
+ * struct nilfs_cpfile_header - checkpoint file header
+ * @ch_ncheckpoints: number of checkpoints
+ * @ch_nsnapshots: number of snapshots
+ * @ch_snapshot_list: snapshot list
+ */
+struct nilfs_cpfile_header {
+	__le64 ch_ncheckpoints;
+	__le64 ch_nsnapshots;
+	struct nilfs_snapshot_list ch_snapshot_list;
+};
+
+#define NILFS_CPFILE_FIRST_CHECKPOINT_OFFSET	\
+	((sizeof(struct nilfs_cpfile_header) +				\
+	  sizeof(struct nilfs_checkpoint) - 1) /			\
+			sizeof(struct nilfs_checkpoint))
+
+/**
+ * struct nilfs_segment_usage - segment usage
+ * @su_lastmod: last modified timestamp
+ * @su_nblocks: number of blocks in segment
+ * @su_flags: flags
+ */
+struct nilfs_segment_usage {
+	__le64 su_lastmod;
+	__le32 su_nblocks;
+	__le32 su_flags;
+};
+
+/* segment usage flag */
+enum {
+	NILFS_SEGMENT_USAGE_ACTIVE,
+	NILFS_SEGMENT_USAGE_DIRTY,
+	NILFS_SEGMENT_USAGE_ERROR,
+
+	/* ... */
+};
+
+#define NILFS_SEGMENT_USAGE_FNS(flag, name)				\
+static inline void							\
+nilfs_segment_usage_set_##name(struct nilfs_segment_usage *su)		\
+{									\
+	su->su_flags = cpu_to_le32(le32_to_cpu(su->su_flags) |		\
+				   (1UL << NILFS_SEGMENT_USAGE_##flag));\
+}									\
+static inline void							\
+nilfs_segment_usage_clear_##name(struct nilfs_segment_usage *su)	\
+{									\
+	su->su_flags =							\
+		cpu_to_le32(le32_to_cpu(su->su_flags) &			\
+			    ~(1UL << NILFS_SEGMENT_USAGE_##flag));      \
+}									\
+static inline int							\
+nilfs_segment_usage_##name(const struct nilfs_segment_usage *su)	\
+{									\
+	return !!(le32_to_cpu(su->su_flags) &				\
+		  (1UL << NILFS_SEGMENT_USAGE_##flag));			\
+}
+
+NILFS_SEGMENT_USAGE_FNS(ACTIVE, active)
+NILFS_SEGMENT_USAGE_FNS(DIRTY, dirty)
+NILFS_SEGMENT_USAGE_FNS(ERROR, error)
+
+static inline void
+nilfs_segment_usage_set_clean(struct nilfs_segment_usage *su)
+{
+	su->su_lastmod = cpu_to_le64(0);
+	su->su_nblocks = cpu_to_le32(0);
+	su->su_flags = cpu_to_le32(0);
+}
+
+static inline int
+nilfs_segment_usage_clean(const struct nilfs_segment_usage *su)
+{
+	return !le32_to_cpu(su->su_flags);
+}
+
+/**
+ * struct nilfs_sufile_header - segment usage file header
+ * @sh_ncleansegs: number of clean segments
+ * @sh_ndirtysegs: number of dirty segments
+ * @sh_last_alloc: last allocated segment number
+ */
+struct nilfs_sufile_header {
+	__le64 sh_ncleansegs;
+	__le64 sh_ndirtysegs;
+	__le64 sh_last_alloc;
+	/* ... */
+};
+
+#define NILFS_SUFILE_FIRST_SEGMENT_USAGE_OFFSET	\
+	((sizeof(struct nilfs_sufile_header) +				\
+	  sizeof(struct nilfs_segment_usage) - 1) /			\
+			 sizeof(struct nilfs_segment_usage))
+
+/**
+ * nilfs_suinfo - segment usage information
+ * @sui_lastmod:
+ * @sui_nblocks:
+ * @sui_flags:
+ */
+struct nilfs_suinfo {
+	__u64 sui_lastmod;
+	__u32 sui_nblocks;
+	__u32 sui_flags;
+};
+
+#define NILFS_SUINFO_FNS(flag, name)					\
+static inline int							\
+nilfs_suinfo_##name(const struct nilfs_suinfo *si)			\
+{									\
+	return si->sui_flags & (1UL << NILFS_SEGMENT_USAGE_##flag);	\
+}
+
+NILFS_SUINFO_FNS(ACTIVE, active)
+NILFS_SUINFO_FNS(DIRTY, dirty)
+NILFS_SUINFO_FNS(ERROR, error)
+
+static inline int nilfs_suinfo_clean(const struct nilfs_suinfo *si)
+{
+	return !si->sui_flags;
+}
+
+/* ioctl */
+enum {
+	NILFS_CHECKPOINT,
+	NILFS_SNAPSHOT,
+};
+
+/**
+ * struct nilfs_cpmode -
+ * @cc_cno:
+ * @cc_mode:
+ */
+struct nilfs_cpmode {
+	__u64 cm_cno;
+	__u32 cm_mode;
+	__u32 cm_pad;
+};
+
+/**
+ * struct nilfs_argv - argument vector
+ * @v_base:
+ * @v_nmembs:
+ * @v_size:
+ * @v_flags:
+ * @v_index:
+ */
+struct nilfs_argv {
+	__u64 v_base;
+	__u32 v_nmembs;	/* number of members */
+	__u16 v_size;	/* size of members */
+	__u16 v_flags;
+	__u64 v_index;
+};
+
+/**
+ * struct nilfs_period -
+ * @p_start:
+ * @p_end:
+ */
+struct nilfs_period {
+	__u64 p_start;
+	__u64 p_end;
+};
+
+/**
+ * struct nilfs_cpstat -
+ * @cs_cno: checkpoint number
+ * @cs_ncps: number of checkpoints
+ * @cs_nsss: number of snapshots
+ */
+struct nilfs_cpstat {
+	__u64 cs_cno;
+	__u64 cs_ncps;
+	__u64 cs_nsss;
+};
+
+/**
+ * struct nilfs_sustat -
+ * @ss_nsegs: number of segments
+ * @ss_ncleansegs: number of clean segments
+ * @ss_ndirtysegs: number of dirty segments
+ * @ss_ctime: creation time of the last segment
+ * @ss_nongc_ctime: creation time of the last segment not for GC
+ * @ss_prot_seq: least sequence number of segments which must not be reclaimed
+ */
+struct nilfs_sustat {
+	__u64 ss_nsegs;
+	__u64 ss_ncleansegs;
+	__u64 ss_ndirtysegs;
+	__u64 ss_ctime;
+	__u64 ss_nongc_ctime;
+	__u64 ss_prot_seq;
+};
+
+/**
+ * struct nilfs_vinfo - virtual block number information
+ * @vi_vblocknr:
+ * @vi_start:
+ * @vi_end:
+ * @vi_blocknr:
+ */
+struct nilfs_vinfo {
+	__u64 vi_vblocknr;
+	__u64 vi_start;
+	__u64 vi_end;
+	__u64 vi_blocknr;
+};
+
+/**
+ * struct nilfs_vdesc -
+ */
+struct nilfs_vdesc {
+	__u64 vd_ino;
+	__u64 vd_cno;
+	__u64 vd_vblocknr;
+	struct nilfs_period vd_period;
+	__u64 vd_blocknr;
+	__u64 vd_offset;
+	__u32 vd_flags;
+	__u32 vd_pad;
+};
+
+/**
+ * struct nilfs_bdesc -
+ */
+struct nilfs_bdesc {
+	__u64 bd_ino;
+	__u64 bd_oblocknr;
+	__u64 bd_blocknr;
+	__u64 bd_offset;
+	__u32 bd_level;
+	__u32 bd_pad;
+};
+
+#define NILFS_IOCTL_IDENT		'n'
+
+#define NILFS_IOCTL_CHANGE_CPMODE  \
+	_IOW(NILFS_IOCTL_IDENT, 0x80, struct nilfs_cpmode)
+#define NILFS_IOCTL_DELETE_CHECKPOINT  \
+	_IOW(NILFS_IOCTL_IDENT, 0x81, __u64)
+#define NILFS_IOCTL_GET_CPINFO  \
+	_IOR(NILFS_IOCTL_IDENT, 0x82, struct nilfs_argv)
+#define NILFS_IOCTL_GET_CPSTAT  \
+	_IOR(NILFS_IOCTL_IDENT, 0x83, struct nilfs_cpstat)
+#define NILFS_IOCTL_GET_SUINFO  \
+	_IOR(NILFS_IOCTL_IDENT, 0x84, struct nilfs_argv)
+#define NILFS_IOCTL_GET_SUSTAT  \
+	_IOR(NILFS_IOCTL_IDENT, 0x85, struct nilfs_sustat)
+#define NILFS_IOCTL_GET_VINFO  \
+	_IOWR(NILFS_IOCTL_IDENT, 0x86, struct nilfs_argv)
+#define NILFS_IOCTL_GET_BDESCS  \
+	_IOWR(NILFS_IOCTL_IDENT, 0x87, struct nilfs_argv)
+#define NILFS_IOCTL_CLEAN_SEGMENTS  \
+	_IOW(NILFS_IOCTL_IDENT, 0x88, struct nilfs_argv[5])
+#define NILFS_IOCTL_SYNC  \
+	_IOR(NILFS_IOCTL_IDENT, 0x8A, __u64)
+#define NILFS_IOCTL_RESIZE  \
+	_IOW(NILFS_IOCTL_IDENT, 0x8B, __u64)
+
+#endif	/* _LINUX_NILFS_FS_H */

include/linux/nls.h

@@ -58,6 +58,25 @@ static inline int nls_strnicmp(struct nls_table *t, const unsigned char *s1,
 	return 0;
 }
 
+/*
+ * nls_nullsize - return length of null character for codepage
+ * @codepage - codepage for which to return length of NULL terminator
+ *
+ * Since we can't guarantee that the null terminator will be a particular
+ * length, we have to check against the codepage. If there's a problem
+ * determining it, assume a single-byte NULL terminator.
+ */
+static inline int
+nls_nullsize(const struct nls_table *codepage)
+{
+	int charlen;
+	char tmp[NLS_MAX_CHARSET_SIZE];
+
+	charlen = codepage->uni2char(0, tmp, NLS_MAX_CHARSET_SIZE);
+
+	return charlen > 0 ? charlen : 1;
+}
+
 #define MODULE_ALIAS_NLS(name)	MODULE_ALIAS("nls_" __stringify(name))
 
 #endif /* _LINUX_NLS_H */

include/linux/of_platform.h

@@ -51,6 +51,16 @@ extern int of_register_driver(struct of_platform_driver *drv,
 			      struct bus_type *bus);
 extern void of_unregister_driver(struct of_platform_driver *drv);
 
+/* Platform drivers register/unregister */
+static inline int of_register_platform_driver(struct of_platform_driver *drv)
+{
+	return of_register_driver(drv, &of_platform_bus_type);
+}
+static inline void of_unregister_platform_driver(struct of_platform_driver *drv)
+{
+	of_unregister_driver(drv);
+}
+
 #include <asm/of_platform.h>
 
 extern struct of_device *of_find_device_by_node(struct device_node *np);

include/linux/parport_pc.h

@@ -228,10 +228,11 @@ extern void parport_pc_release_resources(struct parport *p);
 extern int parport_pc_claim_resources(struct parport *p);
 
 /* PCMCIA code will want to get us to look at a port.  Provide a mechanism. */
-extern struct parport *parport_pc_probe_port (unsigned long base,
-					      unsigned long base_hi,
-					      int irq, int dma,
-					      struct device *dev);
-extern void parport_pc_unregister_port (struct parport *p);
+extern struct parport *parport_pc_probe_port(unsigned long base,
+					     unsigned long base_hi,
+					     int irq, int dma,
+					     struct device *dev,
+					     int irqflags);
+extern void parport_pc_unregister_port(struct parport *p);
 
 #endif

include/linux/pci.h

@@ -674,6 +674,11 @@ int __must_check pci_reenable_device(struct pci_dev *);
 int __must_check pcim_enable_device(struct pci_dev *pdev);
 void pcim_pin_device(struct pci_dev *pdev);
 
+static inline int pci_is_enabled(struct pci_dev *pdev)
+{
+	return (atomic_read(&pdev->enable_cnt) > 0);
+}
+
 static inline int pci_is_managed(struct pci_dev *pdev)
 {
 	return pdev->is_managed;