bsg: support for full generic block layer SG v3

Signed-off-by: NJens Axboe <jens.axboe@oracle.com>

block/Kconfig

@@ -51,4 +51,11 @@ config LSF
 
 endif # BLOCK
 
+config BLK_DEV_BSG
+	bool "Block layer SG support"
+	default y
+	---help---
+	Saying Y here will enable generic SG (SCSI generic) v3
+	support for any block device.
+
 source block/Kconfig.iosched

block/Makefile

@@ -4,6 +4,7 @@
 
 obj-$(CONFIG_BLOCK) := elevator.o ll_rw_blk.o ioctl.o genhd.o scsi_ioctl.o
 
+obj-$(CONFIG_BLK_DEV_BSG)	+= bsg.o
 obj-$(CONFIG_IOSCHED_NOOP)	+= noop-iosched.o
 obj-$(CONFIG_IOSCHED_AS)	+= as-iosched.o
 obj-$(CONFIG_IOSCHED_DEADLINE)	+= deadline-iosched.o

block/ll_rw_blk.c

@@ -4091,6 +4091,13 @@ int blk_register_queue(struct gendisk *disk)
 		return ret;
 	}
 
+	ret = bsg_register_disk(disk);
+	if (ret) {
+		elv_unregister_queue(q);
+		kobject_unregister(&q->kobj);
+		return ret;
+	}
+
 	return 0;
 }
 
@@ -4099,6 +4106,7 @@ void blk_unregister_queue(struct gendisk *disk)
 	request_queue_t *q = disk->queue;
 
 	if (q && q->request_fn) {
+		bsg_unregister_disk(disk);
 		elv_unregister_queue(q);
 
 		kobject_uevent(&q->kobj, KOBJ_REMOVE);

block/scsi_ioctl.c

@@ -41,8 +41,6 @@ const unsigned char scsi_command_size[8] =
 
 EXPORT_SYMBOL(scsi_command_size);
 
-#define BLK_DEFAULT_TIMEOUT	(60 * HZ)
-
 #include <scsi/sg.h>
 
 static int sg_get_version(int __user *p)
@@ -114,7 +112,7 @@ static int sg_emulated_host(request_queue_t *q, int __user *p)
 #define safe_for_read(cmd)	[cmd] = CMD_READ_SAFE
 #define safe_for_write(cmd)	[cmd] = CMD_WRITE_SAFE
 
-static int verify_command(struct file *file, unsigned char *cmd)
+static int verify_command(unsigned char *cmd, int has_write_perm)
 {
 	static unsigned char cmd_type[256] = {
 
@@ -193,18 +191,11 @@ static int verify_command(struct file *file, unsigned char *cmd)
 		safe_for_write(GPCMD_SET_STREAMING),
 	};
 	unsigned char type = cmd_type[cmd[0]];
-	int has_write_perm = 0;
 
 	/* Anybody who can open the device can do a read-safe command */
 	if (type & CMD_READ_SAFE)
 		return 0;
 
-	/*
-	 * file can be NULL from ioctl_by_bdev()...
-	 */
-	if (file)
-		has_write_perm = file->f_mode & FMODE_WRITE;
-
 	/* Write-safe commands just require a writable open.. */
 	if ((type & CMD_WRITE_SAFE) && has_write_perm)
 		return 0;
@@ -222,24 +213,104 @@ static int verify_command(struct file *file, unsigned char *cmd)
 	return -EPERM;
 }
 
+int blk_fill_sghdr_rq(request_queue_t *q, struct request *rq,
+		      struct sg_io_hdr *hdr, int has_write_perm)
+{
+	memset(rq->cmd, 0, BLK_MAX_CDB); /* ATAPI hates garbage after CDB */
+
+	if (copy_from_user(rq->cmd, hdr->cmdp, hdr->cmd_len))
+		return -EFAULT;
+	if (verify_command(rq->cmd, has_write_perm))
+		return -EPERM;
+
+	/*
+	 * fill in request structure
+	 */
+	rq->cmd_len = hdr->cmd_len;
+	rq->cmd_type = REQ_TYPE_BLOCK_PC;
+
+	rq->timeout = (hdr->timeout * HZ) / 1000;
+	if (!rq->timeout)
+		rq->timeout = q->sg_timeout;
+	if (!rq->timeout)
+		rq->timeout = BLK_DEFAULT_SG_TIMEOUT;
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(blk_fill_sghdr_rq);
+
+/*
+ * unmap a request that was previously mapped to this sg_io_hdr. handles
+ * both sg and non-sg sg_io_hdr.
+ */
+int blk_unmap_sghdr_rq(struct request *rq, struct sg_io_hdr *hdr)
+{
+	struct bio *bio = rq->bio;
+
+	/*
+	 * also releases request
+	 */
+	if (!hdr->iovec_count)
+		return blk_rq_unmap_user(bio, hdr->dxfer_len);
+
+	rq_for_each_bio(bio, rq)
+		bio_unmap_user(bio);
+
+	blk_put_request(rq);
+	return 0;
+}
+EXPORT_SYMBOL_GPL(blk_unmap_sghdr_rq);
+
+int blk_complete_sghdr_rq(struct request *rq, struct sg_io_hdr *hdr,
+			  struct bio *bio)
+{
+	int r, ret = 0;
+
+	/*
+	 * fill in all the output members
+	 */
+	hdr->status = rq->errors & 0xff;
+	hdr->masked_status = status_byte(rq->errors);
+	hdr->msg_status = msg_byte(rq->errors);
+	hdr->host_status = host_byte(rq->errors);
+	hdr->driver_status = driver_byte(rq->errors);
+	hdr->info = 0;
+	if (hdr->masked_status || hdr->host_status || hdr->driver_status)
+		hdr->info |= SG_INFO_CHECK;
+	hdr->resid = rq->data_len;
+	hdr->sb_len_wr = 0;
+
+	if (rq->sense_len && hdr->sbp) {
+		int len = min((unsigned int) hdr->mx_sb_len, rq->sense_len);
+
+		if (!copy_to_user(hdr->sbp, rq->sense, len))
+			hdr->sb_len_wr = len;
+		else
+			ret = -EFAULT;
+	}
+
+	rq->bio = bio;
+	r = blk_unmap_sghdr_rq(rq, hdr);
+	if (ret)
+		r = ret;
+
+	return r;
+}
+EXPORT_SYMBOL_GPL(blk_complete_sghdr_rq);
+
 static int sg_io(struct file *file, request_queue_t *q,
 		struct gendisk *bd_disk, struct sg_io_hdr *hdr)
 {
-	unsigned long start_time, timeout;
-	int writing = 0, ret = 0;
+	unsigned long start_time;
+	int writing = 0, ret = 0, has_write_perm = 0;
 	struct request *rq;
 	char sense[SCSI_SENSE_BUFFERSIZE];
-	unsigned char cmd[BLK_MAX_CDB];
 	struct bio *bio;
 
 	if (hdr->interface_id != 'S')
 		return -EINVAL;
 	if (hdr->cmd_len > BLK_MAX_CDB)
 		return -EINVAL;
-	if (copy_from_user(cmd, hdr->cmdp, hdr->cmd_len))
-		return -EFAULT;
-	if (verify_command(file, cmd))
-		return -EPERM;
 
 	if (hdr->dxfer_len > (q->max_hw_sectors << 9))
 		return -EIO;
@@ -260,25 +331,14 @@ static int sg_io(struct file *file, request_queue_t *q,
 	if (!rq)
 		return -ENOMEM;
 
-	/*
-	 * fill in request structure
-	 */
-	rq->cmd_len = hdr->cmd_len;
-	memset(rq->cmd, 0, BLK_MAX_CDB); /* ATAPI hates garbage after CDB */
-	memcpy(rq->cmd, cmd, hdr->cmd_len);
-
-	memset(sense, 0, sizeof(sense));
-	rq->sense = sense;
-	rq->sense_len = 0;
-
-	rq->cmd_type = REQ_TYPE_BLOCK_PC;
+	if (file)
+		has_write_perm = file->f_mode & FMODE_WRITE;
 
-	timeout = msecs_to_jiffies(hdr->timeout);
-	rq->timeout = (timeout < INT_MAX) ? timeout : INT_MAX;
-	if (!rq->timeout)
-		rq->timeout = q->sg_timeout;
-	if (!rq->timeout)
-		rq->timeout = BLK_DEFAULT_TIMEOUT;
+	if (blk_fill_sghdr_rq(q, rq, hdr, has_write_perm)) {
+		blk_rq_unmap_user(bio, hdr->dxfer_len);
+		blk_put_request(rq);
+		return -EFAULT;
+	}
 
 	if (hdr->iovec_count) {
 		const int size = sizeof(struct sg_iovec) * hdr->iovec_count;
@@ -306,6 +366,9 @@ static int sg_io(struct file *file, request_queue_t *q,
 		goto out;
 
 	bio = rq->bio;
+	memset(sense, 0, sizeof(sense));
+	rq->sense = sense;
+	rq->sense_len = 0;
 	rq->retries = 0;
 
 	start_time = jiffies;
@@ -316,31 +379,9 @@ static int sg_io(struct file *file, request_queue_t *q,
 	 */
 	blk_execute_rq(q, bd_disk, rq, 0);
 
-	/* write to all output members */
-	hdr->status = 0xff & rq->errors;
-	hdr->masked_status = status_byte(rq->errors);
-	hdr->msg_status = msg_byte(rq->errors);
-	hdr->host_status = host_byte(rq->errors);
-	hdr->driver_status = driver_byte(rq->errors);
-	hdr->info = 0;
-	if (hdr->masked_status || hdr->host_status || hdr->driver_status)
-		hdr->info |= SG_INFO_CHECK;
-	hdr->resid = rq->data_len;
 	hdr->duration = ((jiffies - start_time) * 1000) / HZ;
-	hdr->sb_len_wr = 0;
-
-	if (rq->sense_len && hdr->sbp) {
-		int len = min((unsigned int) hdr->mx_sb_len, rq->sense_len);
-
-		if (!copy_to_user(hdr->sbp, rq->sense, len))
-			hdr->sb_len_wr = len;
-	}
-
-	if (blk_rq_unmap_user(bio))
-		ret = -EFAULT;
 
-	/* may not have succeeded, but output values written to control
-	 * structure (struct sg_io_hdr).  */
+	return blk_complete_sghdr_rq(rq, hdr, bio);
 out:
 	blk_put_request(rq);
 	return ret;
@@ -427,7 +468,7 @@ int sg_scsi_ioctl(struct file *file, struct request_queue *q,
 	if (in_len && copy_from_user(buffer, sic->data + cmdlen, in_len))
 		goto error;
 
-	err = verify_command(file, rq->cmd);
+	err = verify_command(rq->cmd, file->f_mode & FMODE_WRITE);
 	if (err)
 		goto error;
 
@@ -454,7 +495,7 @@ int sg_scsi_ioctl(struct file *file, struct request_queue *q,
 		rq->retries = 1;
 		break;
 	default:
-		rq->timeout = BLK_DEFAULT_TIMEOUT;
+		rq->timeout = BLK_DEFAULT_SG_TIMEOUT;
 		break;
 	}
 
@@ -501,7 +542,7 @@ static int __blk_send_generic(request_queue_t *q, struct gendisk *bd_disk, int c
 	rq->cmd_type = REQ_TYPE_BLOCK_PC;
 	rq->data = NULL;
 	rq->data_len = 0;
-	rq->timeout = BLK_DEFAULT_TIMEOUT;
+	rq->timeout = BLK_DEFAULT_SG_TIMEOUT;
 	memset(rq->cmd, 0, sizeof(rq->cmd));
 	rq->cmd[0] = cmd;
 	rq->cmd[4] = data;

drivers/ide/ide-floppy.c

@@ -1258,19 +1258,25 @@ static void idefloppy_create_rw_cmd (idefloppy_floppy_t *floppy, idefloppy_pc_t
 	set_bit(PC_DMA_RECOMMENDED, &pc->flags);
 }
 
-static int
+static void
 idefloppy_blockpc_cmd(idefloppy_floppy_t *floppy, idefloppy_pc_t *pc, struct request *rq)
 {
-	/*
-	 * just support eject for now, it would not be hard to make the
-	 * REQ_BLOCK_PC support fully-featured
-	 */
-	if (rq->cmd[0] != IDEFLOPPY_START_STOP_CMD)
-		return 1;
-
 	idefloppy_init_pc(pc);
+	pc->callback = &idefloppy_rw_callback;
 	memcpy(pc->c, rq->cmd, sizeof(pc->c));
-	return 0;
+	pc->rq = rq;
+	pc->b_count = rq->data_len;
+	if (rq->data_len && rq_data_dir(rq) == WRITE)
+		set_bit(PC_WRITING, &pc->flags);
+	pc->buffer = rq->data;
+	if (rq->bio)
+		set_bit(PC_DMA_RECOMMENDED, &pc->flags);
+		
+	/*
+	 * possibly problematic, doesn't look like ide-floppy correctly
+	 * handled scattered requests if dma fails...
+	 */
+	pc->request_transfer = pc->buffer_size = rq->data_len;
 }
 
 /*
@@ -1317,10 +1323,7 @@ static ide_startstop_t idefloppy_do_request (ide_drive_t *drive, struct request
 		pc = (idefloppy_pc_t *) rq->buffer;
 	} else if (blk_pc_request(rq)) {
 		pc = idefloppy_next_pc_storage(drive);
-		if (idefloppy_blockpc_cmd(floppy, pc, rq)) {
-			idefloppy_do_end_request(drive, 0, 0);
-			return ide_stopped;
-		}
+		idefloppy_blockpc_cmd(floppy, pc, rq);
 	} else {
 		blk_dump_rq_flags(rq,
 			"ide-floppy: unsupported command in queue");

drivers/ide/ide.c

@@ -1049,9 +1049,13 @@ int generic_ide_ioctl(ide_drive_t *drive, struct file *file, struct block_device
 	unsigned long flags;
 	ide_driver_t *drv;
 	void __user *p = (void __user *)arg;
-	int err = 0, (*setfunc)(ide_drive_t *, int);
+	int err, (*setfunc)(ide_drive_t *, int);
 	u8 *val;
 
+	err = scsi_cmd_ioctl(file, bdev->bd_disk, cmd, p);
+	if (err != -ENOTTY)
+		return err;
+
 	switch (cmd) {
 	case HDIO_GET_32BIT:	    val = &drive->io_32bit;	 goto read_val;
 	case HDIO_GET_KEEPSETTINGS: val = &drive->keep_settings; goto read_val;
@@ -1171,10 +1175,6 @@ int generic_ide_ioctl(ide_drive_t *drive, struct file *file, struct block_device
 			return 0;
 		}
 
-		case CDROMEJECT:
-		case CDROMCLOSETRAY:
-			return scsi_cmd_ioctl(file, bdev->bd_disk, cmd, p);
-
 		case HDIO_GET_BUSSTATE:
 			if (!capable(CAP_SYS_ADMIN))
 				return -EACCES;

include/linux/blkdev.h

@@ -41,6 +41,8 @@ struct elevator_queue;
 typedef struct elevator_queue elevator_t;
 struct request_pm_state;
 struct blk_trace;
+struct request;
+struct sg_io_hdr;
 
 #define BLKDEV_MIN_RQ	4
 #define BLKDEV_MAX_RQ	128	/* Default maximum */
@@ -607,6 +609,11 @@ extern unsigned long blk_max_low_pfn, blk_max_pfn;
 #define BLK_BOUNCE_ANY		((u64)blk_max_pfn << PAGE_SHIFT)
 #define BLK_BOUNCE_ISA		(ISA_DMA_THRESHOLD)
 
+/*
+ * default timeout for SG_IO if none specified
+ */
+#define BLK_DEFAULT_SG_TIMEOUT	(60 * HZ)
+
 #ifdef CONFIG_MMU
 extern int init_emergency_isa_pool(void);
 extern void blk_queue_bounce(request_queue_t *q, struct bio **bio);
@@ -680,6 +687,11 @@ extern int blk_execute_rq(request_queue_t *, struct gendisk *,
 			  struct request *, int);
 extern void blk_execute_rq_nowait(request_queue_t *, struct gendisk *,
 				  struct request *, int, rq_end_io_fn *);
+extern int blk_fill_sghdr_rq(request_queue_t *, struct request *,
+		      struct sg_io_hdr *, int);
+extern int blk_unmap_sghdr_rq(struct request *, struct sg_io_hdr *);
+extern int blk_complete_sghdr_rq(struct request *, struct sg_io_hdr *,
+			  struct bio *);
 
 static inline request_queue_t *bdev_get_queue(struct block_device *bdev)
 {

include/linux/bsg.h

+#ifndef BSG_H
+#define BSG_H
+
+#if defined(CONFIG_BLK_DEV_BSG)
+struct bsg_class_device {
+	struct class_device *class_dev;
+	struct device *dev;
+	int minor;
+	struct gendisk *disk;
+	struct list_head list;
+};
+
+extern int bsg_register_disk(struct gendisk *);
+extern void bsg_unregister_disk(struct gendisk *);
+#else
+struct bsg_class_device { };
+#define bsg_register_disk(disk)		(0)
+#define bsg_unregister_disk(disk)	do { } while (0)
+#endif
+
+#endif

include/linux/genhd.h

@@ -67,6 +67,7 @@ struct partition {
 #include <linux/string.h>
 #include <linux/fs.h>
 #include <linux/workqueue.h>
+#include <linux/bsg.h>
 
 struct partition {
 	unsigned char boot_ind;		/* 0x80 - active */
@@ -91,6 +92,7 @@ struct hd_struct {
 #ifdef CONFIG_FAIL_MAKE_REQUEST
 	int make_it_fail;
 #endif
+	struct bsg_class_device bsg_dev;
 };
 
 #define GENHD_FL_REMOVABLE			1