Merge branch 'block' of git://brick.kernel.dk/data/git/linux-2.6-block

* 'block' of git://brick.kernel.dk/data/git/linux-2.6-block: (67 commits)
  [PATCH] blk_queue_start_tag() shared map race fix
  [PATCH] Update axboe@suse.de email address
  [PATCH] fix creating zero sized bio mempools in low memory system
  [PATCH] CONFIG_BLOCK: blk_congestion_wait() fix
  [PATCH] CONFIG_BLOCK internal.h cleanups
  [PATCH] BLOCK: Make USB storage depend on SCSI rather than selecting it [try #6]
  [PATCH] BLOCK: Make it possible to disable the block layer [try #6]
  [PATCH] BLOCK: Remove no-longer necessary linux/buffer_head.h inclusions [try #6]
  [PATCH] BLOCK: Remove no-longer necessary linux/mpage.h inclusions [try #6]
  [PATCH] BLOCK: Move the msdos device ioctl compat stuff to the msdos driver [try #6]
  [PATCH] BLOCK: Move the Ext3 device ioctl compat stuff to the Ext3 driver [try #6]
  [PATCH] BLOCK: Move the Ext2 device ioctl compat stuff to the Ext2 driver [try #6]
  [PATCH] BLOCK: Move the ReiserFS device ioctl compat stuff to the ReiserFS driver [try #6]
  [PATCH] BLOCK: Move common FS-specific ioctls to linux/fs.h [try #6]
  [PATCH] BLOCK: Move the loop device ioctl compat stuff to the loop driver [try #6]
  [PATCH] BLOCK: Move __invalidate_device() to block_dev.c [try #6]
  [PATCH] BLOCK: Dissociate generic_writepages() from mpage stuff [try #6]
  [PATCH] BLOCK: Remove dependence on existence of blockdev_superblock [try #6]
  [PATCH] BLOCK: Move extern declarations out of fs/*.c into header files [try #6]
  [PATCH] BLOCK: Don't call block_sync_page() from AFS [try #6]
  ...

MAINTAINERS

@@ -501,7 +501,7 @@ S:	Maintained
 
 BLOCK LAYER
 P:	Jens Axboe
-M:	axboe@suse.de
+M:	axboe@kernel.dk
 L:	linux-kernel@vger.kernel.org
 T:	git kernel.org:/pub/scm/linux/kernel/git/axboe/linux-2.6-block.git
 S:	Maintained
@@ -1380,7 +1380,7 @@ S:	Maintained
 
 IDE/ATAPI CDROM DRIVER
 P:	Jens Axboe
-M:	axboe@suse.de
+M:	axboe@kernel.dk
 L:	linux-kernel@vger.kernel.org
 W:	http://www.kernel.dk
 S:	Maintained
@@ -2531,7 +2531,7 @@ S:	Maintained
 
 SCSI CDROM DRIVER
 P:	Jens Axboe
-M:	axboe@suse.de
+M:	axboe@kernel.dk
 L:	linux-scsi@vger.kernel.org
 W:	http://www.kernel.dk
 S:	Maintained
@@ -2976,7 +2976,7 @@ S:	Maintained
 
 UNIFORM CDROM DRIVER
 P:	Jens Axboe
-M:	axboe@suse.de
+M:	axboe@kernel.dk
 L:	linux-kernel@vger.kernel.org
 W:	http://www.kernel.dk
 S:	Maintained

arch/mips/kernel/signal_n32.c

@@ -42,6 +42,8 @@
 
 #include "signal-common.h"
 
+extern void sigset_from_compat(sigset_t *set, compat_sigset_t *compat);
+
 /*
  * Including <asm/unistd.h> would give use the 64-bit syscall numbers ...
  */
@@ -81,8 +83,6 @@ struct rt_sigframe_n32 {
 #endif
 };
 
-extern void sigset_from_compat (sigset_t *set, compat_sigset_t *compat);
-
 save_static_function(sysn32_rt_sigsuspend);
 __attribute_used__ noinline static int
 _sysn32_rt_sigsuspend(nabi_no_regargs struct pt_regs regs)

arch/um/drivers/ubd_kern.c

@@ -981,8 +981,6 @@ static int prepare_request(struct request *req, struct io_thread_req *io_req)
 	__u64 offset;
 	int len;
 
-	if(req->rq_status == RQ_INACTIVE) return(1);
-
 	/* This should be impossible now */
 	if((rq_data_dir(req) == WRITE) && !dev->openflags.w){
 		printk("Write attempted on readonly ubd device %s\n",

block/Kconfig

 #
 # Block layer core configuration
 #
+config BLOCK
+       bool "Enable the block layer"
+       default y
+       help
+	 This permits the block layer to be removed from the kernel if it's not
+	 needed (on some embedded devices for example).  If this option is
+	 disabled, then blockdev files will become unusable and some
+	 filesystems (such as ext3) will become unavailable.
+
+	 This option will also disable SCSI character devices and USB storage
+	 since they make use of various block layer definitions and
+	 facilities.
+
+	 Say Y here unless you know you really don't want to mount disks and
+	 suchlike.
+
+if BLOCK
+
 #XXX - it makes sense to enable this only for 32-bit subarch's, not for x86_64
 #for instance.
 config LBD
@@ -33,4 +51,6 @@ config LSF
 
 	  If unsure, say Y.
 
+endif
+
 source block/Kconfig.iosched

block/Kconfig.iosched

+if BLOCK
 
 menu "IO Schedulers"
 
@@ -67,3 +68,5 @@ config DEFAULT_IOSCHED
 	default "noop" if DEFAULT_NOOP
 
 endmenu
+
+endif

block/Makefile

@@ -2,7 +2,7 @@
 # Makefile for the kernel block layer
 #
 
-obj-y	:= elevator.o ll_rw_blk.o ioctl.o genhd.o scsi_ioctl.o
+obj-$(CONFIG_BLOCK) := elevator.o ll_rw_blk.o ioctl.o genhd.o scsi_ioctl.o
 
 obj-$(CONFIG_IOSCHED_NOOP)	+= noop-iosched.o
 obj-$(CONFIG_IOSCHED_AS)	+= as-iosched.o

block/blktrace.c

 /*
- * Copyright (C) 2006 Jens Axboe <axboe@suse.de>
+ * Copyright (C) 2006 Jens Axboe <axboe@kernel.dk>
  *
  * 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
@@ -69,7 +69,7 @@ static u32 ddir_act[2] __read_mostly = { BLK_TC_ACT(BLK_TC_READ), BLK_TC_ACT(BLK
 /*
  * Bio action bits of interest
  */
-static u32 bio_act[5] __read_mostly = { 0, BLK_TC_ACT(BLK_TC_BARRIER), BLK_TC_ACT(BLK_TC_SYNC), 0, BLK_TC_ACT(BLK_TC_AHEAD) };
+static u32 bio_act[9] __read_mostly = { 0, BLK_TC_ACT(BLK_TC_BARRIER), BLK_TC_ACT(BLK_TC_SYNC), 0, BLK_TC_ACT(BLK_TC_AHEAD), 0, 0, 0, BLK_TC_ACT(BLK_TC_META) };
 
 /*
  * More could be added as needed, taking care to increment the decrementer
@@ -81,6 +81,8 @@ static u32 bio_act[5] __read_mostly = { 0, BLK_TC_ACT(BLK_TC_BARRIER), BLK_TC_AC
 	(((rw) & (1 << BIO_RW_SYNC)) >> (BIO_RW_SYNC - 1))
 #define trace_ahead_bit(rw)	\
 	(((rw) & (1 << BIO_RW_AHEAD)) << (2 - BIO_RW_AHEAD))
+#define trace_meta_bit(rw)	\
+	(((rw) & (1 << BIO_RW_META)) >> (BIO_RW_META - 3))
 
 /*
  * The worker for the various blk_add_trace*() types. Fills out a
@@ -103,6 +105,7 @@ void __blk_add_trace(struct blk_trace *bt, sector_t sector, int bytes,
 	what |= bio_act[trace_barrier_bit(rw)];
 	what |= bio_act[trace_sync_bit(rw)];
 	what |= bio_act[trace_ahead_bit(rw)];
+	what |= bio_act[trace_meta_bit(rw)];
 
 	pid = tsk->pid;
 	if (unlikely(act_log_check(bt, what, sector, pid)))
@@ -473,6 +476,9 @@ static void blk_check_time(unsigned long long *t)
 	*t -= (a + b) / 2;
 }
 
+/*
+ * calibrate our inter-CPU timings
+ */
 static void blk_trace_check_cpu_time(void *data)
 {
 	unsigned long long *t;
@@ -490,20 +496,6 @@ static void blk_trace_check_cpu_time(void *data)
 	put_cpu();
 }
 
-/*
- * Call blk_trace_check_cpu_time() on each CPU to calibrate our inter-CPU
- * timings
- */
-static void blk_trace_calibrate_offsets(void)
-{
-	unsigned long flags;
-
-	smp_call_function(blk_trace_check_cpu_time, NULL, 1, 1);
-	local_irq_save(flags);
-	blk_trace_check_cpu_time(NULL);
-	local_irq_restore(flags);
-}
-
 static void blk_trace_set_ht_offsets(void)
 {
 #if defined(CONFIG_SCHED_SMT)
@@ -532,7 +524,7 @@ static void blk_trace_set_ht_offsets(void)
 static __init int blk_trace_init(void)
 {
 	mutex_init(&blk_tree_mutex);
-	blk_trace_calibrate_offsets();
+	on_each_cpu(blk_trace_check_cpu_time, NULL, 1, 1);
 	blk_trace_set_ht_offsets();
 
 	return 0;

block/noop-iosched.c

@@ -69,7 +69,7 @@ static void *noop_init_queue(request_queue_t *q, elevator_t *e)
 {
 	struct noop_data *nd;
 
-	nd = kmalloc(sizeof(*nd), GFP_KERNEL);
+	nd = kmalloc_node(sizeof(*nd), GFP_KERNEL, q->node);
 	if (!nd)
 		return NULL;
 	INIT_LIST_HEAD(&nd->queue);

block/scsi_ioctl.c

@@ -294,7 +294,7 @@ static int sg_io(struct file *file, request_queue_t *q,
 	rq->sense = sense;
 	rq->sense_len = 0;
 
-	rq->flags |= REQ_BLOCK_PC;
+	rq->cmd_type = REQ_TYPE_BLOCK_PC;
 	bio = rq->bio;
 
 	/*
@@ -470,7 +470,7 @@ int sg_scsi_ioctl(struct file *file, struct request_queue *q,
 	memset(sense, 0, sizeof(sense));
 	rq->sense = sense;
 	rq->sense_len = 0;
-	rq->flags |= REQ_BLOCK_PC;
+	rq->cmd_type = REQ_TYPE_BLOCK_PC;
 
 	blk_execute_rq(q, disk, rq, 0);
 
@@ -502,7 +502,7 @@ static int __blk_send_generic(request_queue_t *q, struct gendisk *bd_disk, int c
 	int err;
 
 	rq = blk_get_request(q, WRITE, __GFP_WAIT);
-	rq->flags |= REQ_BLOCK_PC;
+	rq->cmd_type = REQ_TYPE_BLOCK_PC;
 	rq->data = NULL;
 	rq->data_len = 0;
 	rq->timeout = BLK_DEFAULT_TIMEOUT;

drivers/block/DAC960.c

@@ -3331,7 +3331,7 @@ static int DAC960_process_queue(DAC960_Controller_T *Controller, struct request_
 		Command->DmaDirection = PCI_DMA_TODEVICE;
 		Command->CommandType = DAC960_WriteCommand;
 	}
-	Command->Completion = Request->waiting;
+	Command->Completion = Request->end_io_data;
 	Command->LogicalDriveNumber = (long)Request->rq_disk->private_data;
 	Command->BlockNumber = Request->sector;
 	Command->BlockCount = Request->nr_sectors;

drivers/block/Kconfig

@@ -2,6 +2,8 @@
 # Block device driver configuration
 #
 
+if BLOCK
+
 menu "Block devices"
 
 config BLK_DEV_FD
@@ -468,3 +470,5 @@ config ATA_OVER_ETH
 	devices like the Coraid EtherDrive (R) Storage Blade.
 
 endmenu
+
+endif

drivers/block/cciss.c

@@ -1229,7 +1229,6 @@ static inline void complete_buffers(struct bio *bio, int status)
 		int nr_sectors = bio_sectors(bio);
 
 		bio->bi_next = NULL;
-		blk_finished_io(len);
 		bio_endio(bio, nr_sectors << 9, status ? 0 : -EIO);
 		bio = xbh;
 	}

drivers/block/cpqarray.c

@@ -989,7 +989,6 @@ static inline void complete_buffers(struct bio *bio, int ok)
 		xbh = bio->bi_next;
 		bio->bi_next = NULL;
 		
-		blk_finished_io(nr_sectors);
 		bio_endio(bio, nr_sectors << 9, ok ? 0 : -EIO);
 
 		bio = xbh;

drivers/block/floppy.c

@@ -2991,8 +2991,8 @@ static void do_fd_request(request_queue_t * q)
 	if (usage_count == 0) {
 		printk("warning: usage count=0, current_req=%p exiting\n",
 		       current_req);
-		printk("sect=%ld flags=%lx\n", (long)current_req->sector,
-		       current_req->flags);
+		printk("sect=%ld type=%x flags=%x\n", (long)current_req->sector,
+		       current_req->cmd_type, current_req->cmd_flags);
 		return;
 	}
 	if (test_bit(0, &fdc_busy)) {

drivers/block/loop.c

@@ -66,6 +66,7 @@
 #include <linux/swap.h>
 #include <linux/slab.h>
 #include <linux/loop.h>
+#include <linux/compat.h>
 #include <linux/suspend.h>
 #include <linux/writeback.h>
 #include <linux/buffer_head.h>		/* for invalidate_bdev() */
@@ -1165,6 +1166,162 @@ static int lo_ioctl(struct inode * inode, struct file * file,
 	return err;
 }
 
+#ifdef CONFIG_COMPAT
+struct compat_loop_info {
+	compat_int_t	lo_number;      /* ioctl r/o */
+	compat_dev_t	lo_device;      /* ioctl r/o */
+	compat_ulong_t	lo_inode;       /* ioctl r/o */
+	compat_dev_t	lo_rdevice;     /* ioctl r/o */
+	compat_int_t	lo_offset;
+	compat_int_t	lo_encrypt_type;
+	compat_int_t	lo_encrypt_key_size;    /* ioctl w/o */
+	compat_int_t	lo_flags;       /* ioctl r/o */
+	char		lo_name[LO_NAME_SIZE];
+	unsigned char	lo_encrypt_key[LO_KEY_SIZE]; /* ioctl w/o */
+	compat_ulong_t	lo_init[2];
+	char		reserved[4];
+};
+
+/*
+ * Transfer 32-bit compatibility structure in userspace to 64-bit loop info
+ * - noinlined to reduce stack space usage in main part of driver
+ */
+static noinline int
+loop_info64_from_compat(const struct compat_loop_info *arg,
+			struct loop_info64 *info64)
+{
+	struct compat_loop_info info;
+
+	if (copy_from_user(&info, arg, sizeof(info)))
+		return -EFAULT;
+
+	memset(info64, 0, sizeof(*info64));
+	info64->lo_number = info.lo_number;
+	info64->lo_device = info.lo_device;
+	info64->lo_inode = info.lo_inode;
+	info64->lo_rdevice = info.lo_rdevice;
+	info64->lo_offset = info.lo_offset;
+	info64->lo_sizelimit = 0;
+	info64->lo_encrypt_type = info.lo_encrypt_type;
+	info64->lo_encrypt_key_size = info.lo_encrypt_key_size;
+	info64->lo_flags = info.lo_flags;
+	info64->lo_init[0] = info.lo_init[0];
+	info64->lo_init[1] = info.lo_init[1];
+	if (info.lo_encrypt_type == LO_CRYPT_CRYPTOAPI)
+		memcpy(info64->lo_crypt_name, info.lo_name, LO_NAME_SIZE);
+	else
+		memcpy(info64->lo_file_name, info.lo_name, LO_NAME_SIZE);
+	memcpy(info64->lo_encrypt_key, info.lo_encrypt_key, LO_KEY_SIZE);
+	return 0;
+}
+
+/*
+ * Transfer 64-bit loop info to 32-bit compatibility structure in userspace
+ * - noinlined to reduce stack space usage in main part of driver
+ */
+static noinline int
+loop_info64_to_compat(const struct loop_info64 *info64,
+		      struct compat_loop_info __user *arg)
+{
+	struct compat_loop_info info;
+
+	memset(&info, 0, sizeof(info));
+	info.lo_number = info64->lo_number;
+	info.lo_device = info64->lo_device;
+	info.lo_inode = info64->lo_inode;
+	info.lo_rdevice = info64->lo_rdevice;
+	info.lo_offset = info64->lo_offset;
+	info.lo_encrypt_type = info64->lo_encrypt_type;
+	info.lo_encrypt_key_size = info64->lo_encrypt_key_size;
+	info.lo_flags = info64->lo_flags;
+	info.lo_init[0] = info64->lo_init[0];
+	info.lo_init[1] = info64->lo_init[1];
+	if (info.lo_encrypt_type == LO_CRYPT_CRYPTOAPI)
+		memcpy(info.lo_name, info64->lo_crypt_name, LO_NAME_SIZE);
+	else
+		memcpy(info.lo_name, info64->lo_file_name, LO_NAME_SIZE);
+	memcpy(info.lo_encrypt_key, info64->lo_encrypt_key, LO_KEY_SIZE);
+
+	/* error in case values were truncated */
+	if (info.lo_device != info64->lo_device ||
+	    info.lo_rdevice != info64->lo_rdevice ||
+	    info.lo_inode != info64->lo_inode ||
+	    info.lo_offset != info64->lo_offset ||
+	    info.lo_init[0] != info64->lo_init[0] ||
+	    info.lo_init[1] != info64->lo_init[1])
+		return -EOVERFLOW;
+
+	if (copy_to_user(arg, &info, sizeof(info)))
+		return -EFAULT;
+	return 0;
+}
+
+static int
+loop_set_status_compat(struct loop_device *lo,
+		       const struct compat_loop_info __user *arg)
+{
+	struct loop_info64 info64;
+	int ret;
+
+	ret = loop_info64_from_compat(arg, &info64);
+	if (ret < 0)
+		return ret;
+	return loop_set_status(lo, &info64);
+}
+
+static int
+loop_get_status_compat(struct loop_device *lo,
+		       struct compat_loop_info __user *arg)
+{
+	struct loop_info64 info64;
+	int err = 0;
+
+	if (!arg)
+		err = -EINVAL;
+	if (!err)
+		err = loop_get_status(lo, &info64);
+	if (!err)
+		err = loop_info64_to_compat(&info64, arg);
+	return err;
+}
+
+static long lo_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
+{
+	struct inode *inode = file->f_dentry->d_inode;
+	struct loop_device *lo = inode->i_bdev->bd_disk->private_data;
+	int err;
+
+	lock_kernel();
+	switch(cmd) {
+	case LOOP_SET_STATUS:
+		mutex_lock(&lo->lo_ctl_mutex);
+		err = loop_set_status_compat(
+			lo, (const struct compat_loop_info __user *) arg);
+		mutex_unlock(&lo->lo_ctl_mutex);
+		break;
+	case LOOP_GET_STATUS:
+		mutex_lock(&lo->lo_ctl_mutex);
+		err = loop_get_status_compat(
+			lo, (struct compat_loop_info __user *) arg);
+		mutex_unlock(&lo->lo_ctl_mutex);
+		break;
+	case LOOP_CLR_FD:
+	case LOOP_GET_STATUS64:
+	case LOOP_SET_STATUS64:
+		arg = (unsigned long) compat_ptr(arg);
+	case LOOP_SET_FD:
+	case LOOP_CHANGE_FD:
+		err = lo_ioctl(inode, file, cmd, arg);
+		break;
+	default:
+		err = -ENOIOCTLCMD;
+		break;
+	}
+	unlock_kernel();
+	return err;
+}
+#endif
+
 static int lo_open(struct inode *inode, struct file *file)
 {
 	struct loop_device *lo = inode->i_bdev->bd_disk->private_data;
@@ -1192,6 +1349,9 @@ static struct block_device_operations lo_fops = {
 	.open =		lo_open,
 	.release =	lo_release,
 	.ioctl =	lo_ioctl,
+#ifdef CONFIG_COMPAT
+	.compat_ioctl =	lo_compat_ioctl,
+#endif
 };
 
 /*

drivers/block/nbd.c

@@ -407,10 +407,10 @@ static void do_nbd_request(request_queue_t * q)
 		struct nbd_device *lo;
 
 		blkdev_dequeue_request(req);
-		dprintk(DBG_BLKDEV, "%s: request %p: dequeued (flags=%lx)\n",
-				req->rq_disk->disk_name, req, req->flags);
+		dprintk(DBG_BLKDEV, "%s: request %p: dequeued (flags=%x)\n",
+				req->rq_disk->disk_name, req, req->cmd_type);
 
-		if (!(req->flags & REQ_CMD))
+		if (!blk_fs_request(req))
 			goto error_out;
 
 		lo = req->rq_disk->private_data;
@@ -489,7 +489,7 @@ static int nbd_ioctl(struct inode *inode, struct file *file,
 	switch (cmd) {
 	case NBD_DISCONNECT:
 	        printk(KERN_INFO "%s: NBD_DISCONNECT\n", lo->disk->disk_name);
-		sreq.flags = REQ_SPECIAL;
+		sreq.cmd_type = REQ_TYPE_SPECIAL;
 		nbd_cmd(&sreq) = NBD_CMD_DISC;
 		/*
 		 * Set these to sane values in case server implementation