X-Git-Url: http://ftp.safe.ca/?a=blobdiff_plain;f=drivers%2Fscsi%2Fsd.c;h=829cc37abc41a57ad45715524a81730b60b7d4ba;hb=95bb335c0ebe96afe926387a1ef3a096bd884a82;hp=56b9501d12f3043c2af7c24b090fa2ea4a9d75bc;hpb=e0597d70012c82e16ee152270a55d89d8bf66693;p=safe%2Fjmp%2Flinux-2.6 diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c index 56b9501..829cc37 100644 --- a/drivers/scsi/sd.c +++ b/drivers/scsi/sd.c @@ -47,7 +47,11 @@ #include #include #include +#include +#include +#include #include +#include #include #include @@ -86,6 +90,12 @@ MODULE_ALIAS_SCSI_DEVICE(TYPE_DISK); MODULE_ALIAS_SCSI_DEVICE(TYPE_MOD); MODULE_ALIAS_SCSI_DEVICE(TYPE_RBC); +#if !defined(CONFIG_DEBUG_BLOCK_EXT_DEVT) +#define SD_MINORS 16 +#else +#define SD_MINORS 0 +#endif + static int sd_revalidate_disk(struct gendisk *); static int sd_probe(struct device *); static int sd_remove(struct device *); @@ -99,6 +109,7 @@ static void scsi_disk_release(struct device *cdev); static void sd_print_sense_hdr(struct scsi_disk *, struct scsi_sense_hdr *); static void sd_print_result(struct scsi_disk *, int); +static DEFINE_SPINLOCK(sd_index_lock); static DEFINE_IDA(sd_index_ida); /* This semaphore is used to mediate the 0->1 reference get in the @@ -106,6 +117,9 @@ static DEFINE_IDA(sd_index_ida); * object after last put) */ static DEFINE_MUTEX(sd_ref_mutex); +struct kmem_cache *sd_cdb_cache; +mempool_t *sd_cdb_pool; + static const char *sd_cache_types[] = { "write through", "none", "write back", "write back, no read (daft)" @@ -159,7 +173,7 @@ sd_store_cache_type(struct device *dev, struct device_attribute *attr, sd_print_sense_hdr(sdkp, &sshdr); return -EINVAL; } - sd_revalidate_disk(sdkp->disk); + revalidate_disk(sdkp->disk); return count; } @@ -251,6 +265,15 @@ sd_show_app_tag_own(struct device *dev, struct device_attribute *attr, return snprintf(buf, 20, "%u\n", sdkp->ATO); } +static ssize_t +sd_show_thin_provisioning(struct device *dev, struct device_attribute *attr, + char *buf) +{ + struct scsi_disk *sdkp = to_scsi_disk(dev); + + return snprintf(buf, 20, "%u\n", sdkp->thin_provisioning); +} + static struct device_attribute sd_disk_attrs[] = { __ATTR(cache_type, S_IRUGO|S_IWUSR, sd_show_cache_type, sd_store_cache_type), @@ -261,6 +284,7 @@ static struct device_attribute sd_disk_attrs[] = { sd_store_manage_start_stop), __ATTR(protection_type, S_IRUGO, sd_show_protection_type, NULL), __ATTR(app_tag_own, S_IRUGO, sd_show_app_tag_own, NULL), + __ATTR(thin_provisioning, S_IRUGO, sd_show_thin_provisioning, NULL), __ATTR_NULL, }; @@ -360,6 +384,82 @@ static void scsi_disk_put(struct scsi_disk *sdkp) mutex_unlock(&sd_ref_mutex); } +static void sd_prot_op(struct scsi_cmnd *scmd, unsigned int dif) +{ + unsigned int prot_op = SCSI_PROT_NORMAL; + unsigned int dix = scsi_prot_sg_count(scmd); + + if (scmd->sc_data_direction == DMA_FROM_DEVICE) { + if (dif && dix) + prot_op = SCSI_PROT_READ_PASS; + else if (dif && !dix) + prot_op = SCSI_PROT_READ_STRIP; + else if (!dif && dix) + prot_op = SCSI_PROT_READ_INSERT; + } else { + if (dif && dix) + prot_op = SCSI_PROT_WRITE_PASS; + else if (dif && !dix) + prot_op = SCSI_PROT_WRITE_INSERT; + else if (!dif && dix) + prot_op = SCSI_PROT_WRITE_STRIP; + } + + scsi_set_prot_op(scmd, prot_op); + scsi_set_prot_type(scmd, dif); +} + +/** + * sd_prepare_discard - unmap blocks on thinly provisioned device + * @rq: Request to prepare + * + * Will issue either UNMAP or WRITE SAME(16) depending on preference + * indicated by target device. + **/ +static int sd_prepare_discard(struct request *rq) +{ + struct scsi_disk *sdkp = scsi_disk(rq->rq_disk); + struct bio *bio = rq->bio; + sector_t sector = bio->bi_sector; + unsigned int num = bio_sectors(bio); + + if (sdkp->device->sector_size == 4096) { + sector >>= 3; + num >>= 3; + } + + rq->cmd_type = REQ_TYPE_BLOCK_PC; + rq->timeout = SD_TIMEOUT; + + memset(rq->cmd, 0, rq->cmd_len); + + if (sdkp->unmap) { + char *buf = kmap_atomic(bio_page(bio), KM_USER0); + + rq->cmd[0] = UNMAP; + rq->cmd[8] = 24; + rq->cmd_len = 10; + + /* Ensure that data length matches payload */ + rq->__data_len = bio->bi_size = bio->bi_io_vec->bv_len = 24; + + put_unaligned_be16(6 + 16, &buf[0]); + put_unaligned_be16(16, &buf[2]); + put_unaligned_be64(sector, &buf[8]); + put_unaligned_be32(num, &buf[16]); + + kunmap_atomic(buf, KM_USER0); + } else { + rq->cmd[0] = WRITE_SAME_16; + rq->cmd[1] = 0x8; /* UNMAP */ + put_unaligned_be64(sector, &rq->cmd[2]); + put_unaligned_be32(num, &rq->cmd[10]); + rq->cmd_len = 16; + } + + return BLKPREP_OK; +} + /** * sd_init_command - build a scsi (read or write) command from * information in the request structure. @@ -373,10 +473,19 @@ static int sd_prep_fn(struct request_queue *q, struct request *rq) struct scsi_cmnd *SCpnt; struct scsi_device *sdp = q->queuedata; struct gendisk *disk = rq->rq_disk; - sector_t block = rq->sector; - unsigned int this_count = rq->nr_sectors; - unsigned int timeout = sdp->timeout; - int ret; + struct scsi_disk *sdkp; + sector_t block = blk_rq_pos(rq); + sector_t threshold; + unsigned int this_count = blk_rq_sectors(rq); + int ret, host_dif; + unsigned char protect; + + /* + * Discard request come in as REQ_TYPE_FS but we turn them into + * block PC requests to make life easier. + */ + if (blk_discard_rq(rq)) + ret = sd_prepare_discard(rq); if (rq->cmd_type == REQ_TYPE_BLOCK_PC) { ret = scsi_setup_blk_pc_cmnd(sdp, rq); @@ -389,6 +498,7 @@ static int sd_prep_fn(struct request_queue *q, struct request *rq) if (ret != BLKPREP_OK) goto out; SCpnt = rq->special; + sdkp = scsi_disk(disk); /* from here on until we're complete, any goto out * is used for a killable error condition */ @@ -401,10 +511,10 @@ static int sd_prep_fn(struct request_queue *q, struct request *rq) this_count)); if (!sdp || !scsi_device_online(sdp) || - block + rq->nr_sectors > get_capacity(disk)) { + block + blk_rq_sectors(rq) > get_capacity(disk)) { SCSI_LOG_HLQUEUE(2, scmd_printk(KERN_INFO, SCpnt, - "Finishing %ld sectors\n", - rq->nr_sectors)); + "Finishing %u sectors\n", + blk_rq_sectors(rq))); SCSI_LOG_HLQUEUE(2, scmd_printk(KERN_INFO, SCpnt, "Retry with 0x%p\n", SCpnt)); goto out; @@ -420,13 +530,21 @@ static int sd_prep_fn(struct request_queue *q, struct request *rq) } /* - * Some devices (some sdcards for one) don't like it if the - * last sector gets read in a larger then 1 sector read. + * Some SD card readers can't handle multi-sector accesses which touch + * the last one or two hardware sectors. Split accesses as needed. */ - if (unlikely(sdp->last_sector_bug && - rq->nr_sectors > sdp->sector_size / 512 && - block + this_count == get_capacity(disk))) - this_count -= sdp->sector_size / 512; + threshold = get_capacity(disk) - SD_LAST_BUGGY_SECTORS * + (sdp->sector_size / 512); + + if (unlikely(sdp->last_sector_bug && block + this_count > threshold)) { + if (block < threshold) { + /* Access up to the threshold but not beyond */ + this_count = threshold - block; + } else { + /* Access only a single hardware sector */ + this_count = sdp->sector_size / 512; + } + } SCSI_LOG_HLQUEUE(2, scmd_printk(KERN_INFO, SCpnt, "block=%llu\n", (unsigned long long)block)); @@ -443,7 +561,7 @@ static int sd_prep_fn(struct request_queue *q, struct request *rq) * for this. */ if (sdp->sector_size == 1024) { - if ((block & 1) || (rq->nr_sectors & 1)) { + if ((block & 1) || (blk_rq_sectors(rq) & 1)) { scmd_printk(KERN_ERR, SCpnt, "Bad block number requested\n"); goto out; @@ -453,7 +571,7 @@ static int sd_prep_fn(struct request_queue *q, struct request *rq) } } if (sdp->sector_size == 2048) { - if ((block & 3) || (rq->nr_sectors & 3)) { + if ((block & 3) || (blk_rq_sectors(rq) & 3)) { scmd_printk(KERN_ERR, SCpnt, "Bad block number requested\n"); goto out; @@ -463,7 +581,7 @@ static int sd_prep_fn(struct request_queue *q, struct request *rq) } } if (sdp->sector_size == 4096) { - if ((block & 7) || (rq->nr_sectors & 7)) { + if ((block & 7) || (blk_rq_sectors(rq) & 7)) { scmd_printk(KERN_ERR, SCpnt, "Bad block number requested\n"); goto out; @@ -478,6 +596,11 @@ static int sd_prep_fn(struct request_queue *q, struct request *rq) } SCpnt->cmnd[0] = WRITE_6; SCpnt->sc_data_direction = DMA_TO_DEVICE; + + if (blk_integrity_rq(rq) && + sd_dif_prepare(rq, block, sdp->sector_size) == -EIO) + goto out; + } else if (rq_data_dir(rq) == READ) { SCpnt->cmnd[0] = READ_6; SCpnt->sc_data_direction = DMA_FROM_DEVICE; @@ -487,16 +610,57 @@ static int sd_prep_fn(struct request_queue *q, struct request *rq) } SCSI_LOG_HLQUEUE(2, scmd_printk(KERN_INFO, SCpnt, - "%s %d/%ld 512 byte blocks.\n", + "%s %d/%u 512 byte blocks.\n", (rq_data_dir(rq) == WRITE) ? "writing" : "reading", this_count, - rq->nr_sectors)); + blk_rq_sectors(rq))); - SCpnt->cmnd[1] = 0; - - if (block > 0xffffffff) { + /* Set RDPROTECT/WRPROTECT if disk is formatted with DIF */ + host_dif = scsi_host_dif_capable(sdp->host, sdkp->protection_type); + if (host_dif) + protect = 1 << 5; + else + protect = 0; + + if (host_dif == SD_DIF_TYPE2_PROTECTION) { + SCpnt->cmnd = mempool_alloc(sd_cdb_pool, GFP_ATOMIC); + + if (unlikely(SCpnt->cmnd == NULL)) { + ret = BLKPREP_DEFER; + goto out; + } + + SCpnt->cmd_len = SD_EXT_CDB_SIZE; + memset(SCpnt->cmnd, 0, SCpnt->cmd_len); + SCpnt->cmnd[0] = VARIABLE_LENGTH_CMD; + SCpnt->cmnd[7] = 0x18; + SCpnt->cmnd[9] = (rq_data_dir(rq) == READ) ? READ_32 : WRITE_32; + SCpnt->cmnd[10] = protect | (blk_fua_rq(rq) ? 0x8 : 0); + + /* LBA */ + SCpnt->cmnd[12] = sizeof(block) > 4 ? (unsigned char) (block >> 56) & 0xff : 0; + SCpnt->cmnd[13] = sizeof(block) > 4 ? (unsigned char) (block >> 48) & 0xff : 0; + SCpnt->cmnd[14] = sizeof(block) > 4 ? (unsigned char) (block >> 40) & 0xff : 0; + SCpnt->cmnd[15] = sizeof(block) > 4 ? (unsigned char) (block >> 32) & 0xff : 0; + SCpnt->cmnd[16] = (unsigned char) (block >> 24) & 0xff; + SCpnt->cmnd[17] = (unsigned char) (block >> 16) & 0xff; + SCpnt->cmnd[18] = (unsigned char) (block >> 8) & 0xff; + SCpnt->cmnd[19] = (unsigned char) block & 0xff; + + /* Expected Indirect LBA */ + SCpnt->cmnd[20] = (unsigned char) (block >> 24) & 0xff; + SCpnt->cmnd[21] = (unsigned char) (block >> 16) & 0xff; + SCpnt->cmnd[22] = (unsigned char) (block >> 8) & 0xff; + SCpnt->cmnd[23] = (unsigned char) block & 0xff; + + /* Transfer length */ + SCpnt->cmnd[28] = (unsigned char) (this_count >> 24) & 0xff; + SCpnt->cmnd[29] = (unsigned char) (this_count >> 16) & 0xff; + SCpnt->cmnd[30] = (unsigned char) (this_count >> 8) & 0xff; + SCpnt->cmnd[31] = (unsigned char) this_count & 0xff; + } else if (block > 0xffffffff) { SCpnt->cmnd[0] += READ_16 - READ_6; - SCpnt->cmnd[1] |= blk_fua_rq(rq) ? 0x8 : 0; + SCpnt->cmnd[1] = protect | (blk_fua_rq(rq) ? 0x8 : 0); SCpnt->cmnd[2] = sizeof(block) > 4 ? (unsigned char) (block >> 56) & 0xff : 0; SCpnt->cmnd[3] = sizeof(block) > 4 ? (unsigned char) (block >> 48) & 0xff : 0; SCpnt->cmnd[4] = sizeof(block) > 4 ? (unsigned char) (block >> 40) & 0xff : 0; @@ -511,12 +675,13 @@ static int sd_prep_fn(struct request_queue *q, struct request *rq) SCpnt->cmnd[13] = (unsigned char) this_count & 0xff; SCpnt->cmnd[14] = SCpnt->cmnd[15] = 0; } else if ((this_count > 0xff) || (block > 0x1fffff) || + scsi_device_protection(SCpnt->device) || SCpnt->device->use_10_for_rw) { if (this_count > 0xffff) this_count = 0xffff; SCpnt->cmnd[0] += READ_10 - READ_6; - SCpnt->cmnd[1] |= blk_fua_rq(rq) ? 0x8 : 0; + SCpnt->cmnd[1] = protect | (blk_fua_rq(rq) ? 0x8 : 0); SCpnt->cmnd[2] = (unsigned char) (block >> 24) & 0xff; SCpnt->cmnd[3] = (unsigned char) (block >> 16) & 0xff; SCpnt->cmnd[4] = (unsigned char) (block >> 8) & 0xff; @@ -545,6 +710,10 @@ static int sd_prep_fn(struct request_queue *q, struct request *rq) } SCpnt->sdb.length = this_count * sdp->sector_size; + /* If DIF or DIX is enabled, tell HBA how to handle request */ + if (host_dif || scsi_prot_sg_count(SCpnt)) + sd_prot_op(SCpnt, host_dif); + /* * We shouldn't disconnect in the middle of a sector, so with a dumb * host adapter, it's safe to assume that we can at least transfer @@ -553,7 +722,6 @@ static int sd_prep_fn(struct request_queue *q, struct request *rq) SCpnt->transfersize = sdp->sector_size; SCpnt->underflow = this_count << 9; SCpnt->allowed = SD_MAX_RETRIES; - SCpnt->timeout_per_command = timeout; /* * This indicates that the command is ready from our end to be @@ -577,17 +745,15 @@ static int sd_prep_fn(struct request_queue *q, struct request *rq) * In the latter case @inode and @filp carry an abridged amount * of information as noted above. **/ -static int sd_open(struct inode *inode, struct file *filp) +static int sd_open(struct block_device *bdev, fmode_t mode) { - struct gendisk *disk = inode->i_bdev->bd_disk; - struct scsi_disk *sdkp; + struct scsi_disk *sdkp = scsi_disk_get(bdev->bd_disk); struct scsi_device *sdev; int retval; - if (!(sdkp = scsi_disk_get(disk))) + if (!sdkp) return -ENXIO; - SCSI_LOG_HLQUEUE(3, sd_printk(KERN_INFO, sdkp, "sd_open\n")); sdev = sdkp->device; @@ -601,14 +767,13 @@ static int sd_open(struct inode *inode, struct file *filp) goto error_out; if (sdev->removable || sdkp->write_prot) - check_disk_change(inode->i_bdev); + check_disk_change(bdev); /* * If the drive is empty, just let the open fail. */ retval = -ENOMEDIUM; - if (sdev->removable && !sdkp->media_present && - !(filp->f_flags & O_NDELAY)) + if (sdev->removable && !sdkp->media_present && !(mode & FMODE_NDELAY)) goto error_out; /* @@ -616,7 +781,7 @@ static int sd_open(struct inode *inode, struct file *filp) * if the user expects to be able to write to the thing. */ retval = -EROFS; - if (sdkp->write_prot && (filp->f_mode & FMODE_WRITE)) + if (sdkp->write_prot && (mode & FMODE_WRITE)) goto error_out; /* @@ -652,9 +817,8 @@ error_out: * Note: may block (uninterruptible) if error recovery is underway * on this disk. **/ -static int sd_release(struct inode *inode, struct file *filp) +static int sd_release(struct gendisk *disk, fmode_t mode) { - struct gendisk *disk = inode->i_bdev->bd_disk; struct scsi_disk *sdkp = scsi_disk(disk); struct scsi_device *sdev = sdkp->device; @@ -711,10 +875,9 @@ static int sd_getgeo(struct block_device *bdev, struct hd_geometry *geo) * Note: most ioctls are forward onto the block subsystem or further * down in the scsi subsystem. **/ -static int sd_ioctl(struct inode * inode, struct file * filp, +static int sd_ioctl(struct block_device *bdev, fmode_t mode, unsigned int cmd, unsigned long arg) { - struct block_device *bdev = inode->i_bdev; struct gendisk *disk = bdev->bd_disk; struct scsi_device *sdp = scsi_disk(disk)->device; void __user *p = (void __user *)arg; @@ -729,7 +892,8 @@ static int sd_ioctl(struct inode * inode, struct file * filp, * may try and take the device offline, in which case all further * access to the device is prohibited. */ - error = scsi_nonblockable_ioctl(sdp, cmd, p, filp); + error = scsi_nonblockable_ioctl(sdp, cmd, p, + (mode & FMODE_NDELAY) != 0); if (!scsi_block_when_processing_errors(sdp) || !error) return error; @@ -743,7 +907,7 @@ static int sd_ioctl(struct inode * inode, struct file * filp, case SCSI_IOCTL_GET_BUS_NUMBER: return scsi_ioctl(sdp, cmd, p); default: - error = scsi_cmd_ioctl(filp, disk->queue, disk, cmd, p); + error = scsi_cmd_ioctl(disk->queue, disk, mode, cmd, p); if (error != -ENOTTY) return error; } @@ -856,7 +1020,7 @@ static int sd_sync_cache(struct scsi_disk *sdkp) * flush everything. */ res = scsi_execute_req(sdp, cmd, DMA_NONE, NULL, 0, &sshdr, - SD_TIMEOUT, SD_MAX_RETRIES); + SD_TIMEOUT, SD_MAX_RETRIES, NULL); if (res == 0) break; } @@ -876,6 +1040,7 @@ static void sd_prepare_flush(struct request_queue *q, struct request *rq) { rq->cmd_type = REQ_TYPE_BLOCK_PC; rq->timeout = SD_TIMEOUT; + rq->retries = SD_MAX_RETRIES; rq->cmd[0] = SYNCHRONIZE_CACHE; rq->cmd_len = 10; } @@ -885,7 +1050,7 @@ static void sd_rescan(struct device *dev) struct scsi_disk *sdkp = scsi_disk_get_from_dev(dev); if (sdkp) { - sd_revalidate_disk(sdkp->disk); + revalidate_disk(sdkp->disk); scsi_disk_put(sdkp); } } @@ -896,11 +1061,10 @@ static void sd_rescan(struct device *dev) * This gets directly called from VFS. When the ioctl * is not recognized we go back to the other translation paths. */ -static long sd_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg) +static int sd_compat_ioctl(struct block_device *bdev, fmode_t mode, + unsigned int cmd, unsigned long arg) { - struct block_device *bdev = file->f_path.dentry->d_inode->i_bdev; - struct gendisk *disk = bdev->bd_disk; - struct scsi_device *sdev = scsi_disk(disk)->device; + struct scsi_device *sdev = scsi_disk(bdev->bd_disk)->device; /* * If we are in the middle of error recovery, don't let anyone @@ -926,11 +1090,11 @@ static long sd_compat_ioctl(struct file *file, unsigned int cmd, unsigned long a } #endif -static struct block_device_operations sd_fops = { +static const struct block_device_operations sd_fops = { .owner = THIS_MODULE, .open = sd_open, .release = sd_release, - .ioctl = sd_ioctl, + .locked_ioctl = sd_ioctl, .getgeo = sd_getgeo, #ifdef CONFIG_COMPAT .compat_ioctl = sd_compat_ioctl, @@ -939,6 +1103,48 @@ static struct block_device_operations sd_fops = { .revalidate_disk = sd_revalidate_disk, }; +static unsigned int sd_completed_bytes(struct scsi_cmnd *scmd) +{ + u64 start_lba = blk_rq_pos(scmd->request); + u64 end_lba = blk_rq_pos(scmd->request) + (scsi_bufflen(scmd) / 512); + u64 bad_lba; + int info_valid; + + if (!blk_fs_request(scmd->request)) + return 0; + + info_valid = scsi_get_sense_info_fld(scmd->sense_buffer, + SCSI_SENSE_BUFFERSIZE, + &bad_lba); + if (!info_valid) + return 0; + + if (scsi_bufflen(scmd) <= scmd->device->sector_size) + return 0; + + if (scmd->device->sector_size < 512) { + /* only legitimate sector_size here is 256 */ + start_lba <<= 1; + end_lba <<= 1; + } else { + /* be careful ... don't want any overflows */ + u64 factor = scmd->device->sector_size / 512; + do_div(start_lba, factor); + do_div(end_lba, factor); + } + + /* The bad lba was reported incorrectly, we have no idea where + * the error is. + */ + if (bad_lba < start_lba || bad_lba >= end_lba) + return 0; + + /* This computation should always be done in terms of + * the resolution of the device's medium. + */ + return (bad_lba - start_lba) * scmd->device->sector_size; +} + /** * sd_done - bottom half handler: called when the lower level * driver has completed (successfully or otherwise) a scsi command. @@ -949,15 +1155,11 @@ static struct block_device_operations sd_fops = { static int sd_done(struct scsi_cmnd *SCpnt) { int result = SCpnt->result; - unsigned int xfer_size = scsi_bufflen(SCpnt); - unsigned int good_bytes = result ? 0 : xfer_size; - u64 start_lba = SCpnt->request->sector; - u64 end_lba = SCpnt->request->sector + (xfer_size / 512); - u64 bad_lba; + unsigned int good_bytes = result ? 0 : scsi_bufflen(SCpnt); struct scsi_sense_hdr sshdr; + struct scsi_disk *sdkp = scsi_disk(SCpnt->request->rq_disk); int sense_valid = 0; int sense_deferred = 0; - int info_valid; if (result) { sense_valid = scsi_command_normalize_sense(SCpnt, &sshdr); @@ -982,61 +1184,47 @@ static int sd_done(struct scsi_cmnd *SCpnt) switch (sshdr.sense_key) { case HARDWARE_ERROR: case MEDIUM_ERROR: - if (!blk_fs_request(SCpnt->request)) - goto out; - info_valid = scsi_get_sense_info_fld(SCpnt->sense_buffer, - SCSI_SENSE_BUFFERSIZE, - &bad_lba); - if (!info_valid) - goto out; - if (xfer_size <= SCpnt->device->sector_size) - goto out; - if (SCpnt->device->sector_size < 512) { - /* only legitimate sector_size here is 256 */ - start_lba <<= 1; - end_lba <<= 1; - } else { - /* be careful ... don't want any overflows */ - u64 factor = SCpnt->device->sector_size / 512; - do_div(start_lba, factor); - do_div(end_lba, factor); - } - - if (bad_lba < start_lba || bad_lba >= end_lba) - /* the bad lba was reported incorrectly, we have - * no idea where the error is - */ - goto out; - - /* This computation should always be done in terms of - * the resolution of the device's medium. - */ - good_bytes = (bad_lba - start_lba)*SCpnt->device->sector_size; + good_bytes = sd_completed_bytes(SCpnt); break; case RECOVERED_ERROR: + good_bytes = scsi_bufflen(SCpnt); + break; case NO_SENSE: - /* Inform the user, but make sure that it's not treated - * as a hard error. + /* This indicates a false check condition, so ignore it. An + * unknown amount of data was transferred so treat it as an + * error. */ scsi_print_sense("sd", SCpnt); SCpnt->result = 0; memset(SCpnt->sense_buffer, 0, SCSI_SENSE_BUFFERSIZE); - good_bytes = xfer_size; break; - case ILLEGAL_REQUEST: - if (SCpnt->device->use_10_for_rw && - (SCpnt->cmnd[0] == READ_10 || - SCpnt->cmnd[0] == WRITE_10)) - SCpnt->device->use_10_for_rw = 0; - if (SCpnt->device->use_10_for_ms && - (SCpnt->cmnd[0] == MODE_SENSE_10 || - SCpnt->cmnd[0] == MODE_SELECT_10)) - SCpnt->device->use_10_for_ms = 0; + case ABORTED_COMMAND: /* DIF: Target detected corruption */ + case ILLEGAL_REQUEST: /* DIX: Host detected corruption */ + if (sshdr.asc == 0x10) + good_bytes = sd_completed_bytes(SCpnt); break; default: break; } out: + if (rq_data_dir(SCpnt->request) == READ && scsi_prot_sg_count(SCpnt)) + sd_dif_complete(SCpnt, good_bytes); + + if (scsi_host_dif_capable(sdkp->device->host, sdkp->protection_type) + == SD_DIF_TYPE2_PROTECTION && SCpnt->cmnd != SCpnt->request->cmd) { + + /* We have to print a failed command here as the + * extended CDB gets freed before scsi_io_completion() + * is called. + */ + if (result) + scsi_print_command(SCpnt); + + mempool_free(SCpnt->cmnd, sd_cdb_pool); + SCpnt->cmnd = NULL; + SCpnt->cmd_len = 0; + } + return good_bytes; } @@ -1084,7 +1272,7 @@ sd_spinup_disk(struct scsi_disk *sdkp) the_result = scsi_execute_req(sdkp->device, cmd, DMA_NONE, NULL, 0, &sshdr, SD_TIMEOUT, - SD_MAX_RETRIES); + SD_MAX_RETRIES, NULL); /* * If the drive has indicated to us that it @@ -1115,23 +1303,19 @@ sd_spinup_disk(struct scsi_disk *sdkp) /* * The device does not want the automatic start to be issued. */ - if (sdkp->device->no_start_on_add) { + if (sdkp->device->no_start_on_add) break; - } - /* - * If manual intervention is required, or this is an - * absent USB storage device, a spinup is meaningless. - */ - if (sense_valid && - sshdr.sense_key == NOT_READY && - sshdr.asc == 4 && sshdr.ascq == 3) { - break; /* manual intervention required */ - - /* - * Issue command to spin up drive when not ready - */ - } else if (sense_valid && sshdr.sense_key == NOT_READY) { + if (sense_valid && sshdr.sense_key == NOT_READY) { + if (sshdr.asc == 4 && sshdr.ascq == 3) + break; /* manual intervention required */ + if (sshdr.asc == 4 && sshdr.ascq == 0xb) + break; /* standby */ + if (sshdr.asc == 4 && sshdr.ascq == 0xc) + break; /* unavailable */ + /* + * Issue command to spin up drive when not ready + */ if (!spintime) { sd_printk(KERN_NOTICE, sdkp, "Spinning up disk..."); cmd[0] = START_STOP; @@ -1142,7 +1326,8 @@ sd_spinup_disk(struct scsi_disk *sdkp) cmd[4] |= 1 << 4; scsi_execute_req(sdkp->device, cmd, DMA_NONE, NULL, 0, &sshdr, - SD_TIMEOUT, SD_MAX_RETRIES); + SD_TIMEOUT, SD_MAX_RETRIES, + NULL); spintime_expire = jiffies + 100 * HZ; spintime = 1; } @@ -1194,161 +1379,285 @@ void sd_read_protection_type(struct scsi_disk *sdkp, unsigned char *buffer) u8 type; if (scsi_device_protection(sdp) == 0 || (buffer[12] & 1) == 0) - type = 0; - else - type = ((buffer[12] >> 1) & 7) + 1; /* P_TYPE 0 = Type 1 */ + return; - switch (type) { - case SD_DIF_TYPE0_PROTECTION: - sdkp->protection_type = 0; - break; + type = ((buffer[12] >> 1) & 7) + 1; /* P_TYPE 0 = Type 1 */ - case SD_DIF_TYPE1_PROTECTION: - case SD_DIF_TYPE3_PROTECTION: - sdkp->protection_type = type; - break; + if (type == sdkp->protection_type || !sdkp->first_scan) + return; - case SD_DIF_TYPE2_PROTECTION: - sd_printk(KERN_ERR, sdkp, "formatted with DIF Type 2 " \ - "protection which is currently unsupported. " \ - "Disabling disk!\n"); - goto disable; + sdkp->protection_type = type; - default: - sd_printk(KERN_ERR, sdkp, "formatted with unknown " \ - "protection type %d. Disabling disk!\n", type); - goto disable; + if (type > SD_DIF_TYPE3_PROTECTION) { + sd_printk(KERN_ERR, sdkp, "formatted with unsupported " \ + "protection type %u. Disabling disk!\n", type); + sdkp->capacity = 0; + return; } - return; + if (scsi_host_dif_capable(sdp->host, type)) + sd_printk(KERN_NOTICE, sdkp, + "Enabling DIF Type %u protection\n", type); + else + sd_printk(KERN_NOTICE, sdkp, + "Disabling DIF Type %u protection\n", type); +} -disable: - sdkp->protection_type = 0; - sdkp->capacity = 0; +static void read_capacity_error(struct scsi_disk *sdkp, struct scsi_device *sdp, + struct scsi_sense_hdr *sshdr, int sense_valid, + int the_result) +{ + sd_print_result(sdkp, the_result); + if (driver_byte(the_result) & DRIVER_SENSE) + sd_print_sense_hdr(sdkp, sshdr); + else + sd_printk(KERN_NOTICE, sdkp, "Sense not available.\n"); + + /* + * Set dirty bit for removable devices if not ready - + * sometimes drives will not report this properly. + */ + if (sdp->removable && + sense_valid && sshdr->sense_key == NOT_READY) + sdp->changed = 1; + + /* + * We used to set media_present to 0 here to indicate no media + * in the drive, but some drives fail read capacity even with + * media present, so we can't do that. + */ + sdkp->capacity = 0; /* unknown mapped to zero - as usual */ } -/* - * read disk capacity - */ -static void -sd_read_capacity(struct scsi_disk *sdkp, unsigned char *buffer) +#define RC16_LEN 32 +#if RC16_LEN > SD_BUF_SIZE +#error RC16_LEN must not be more than SD_BUF_SIZE +#endif + +#define READ_CAPACITY_RETRIES_ON_RESET 10 + +static int read_capacity_16(struct scsi_disk *sdkp, struct scsi_device *sdp, + unsigned char *buffer) { unsigned char cmd[16]; - int the_result, retries; - int sector_size = 0; - /* Force READ CAPACITY(16) when PROTECT=1 */ - int longrc = scsi_device_protection(sdkp->device) ? 1 : 0; struct scsi_sense_hdr sshdr; int sense_valid = 0; - struct scsi_device *sdp = sdkp->device; + int the_result; + int retries = 3, reset_retries = READ_CAPACITY_RETRIES_ON_RESET; + unsigned int alignment; + unsigned long long lba; + unsigned sector_size; -repeat: - retries = 3; do { - if (longrc) { - memset((void *) cmd, 0, 16); - cmd[0] = SERVICE_ACTION_IN; - cmd[1] = SAI_READ_CAPACITY_16; - cmd[13] = 13; - memset((void *) buffer, 0, 13); - } else { - cmd[0] = READ_CAPACITY; - memset((void *) &cmd[1], 0, 9); - memset((void *) buffer, 0, 8); + memset(cmd, 0, 16); + cmd[0] = SERVICE_ACTION_IN; + cmd[1] = SAI_READ_CAPACITY_16; + cmd[13] = RC16_LEN; + memset(buffer, 0, RC16_LEN); + + the_result = scsi_execute_req(sdp, cmd, DMA_FROM_DEVICE, + buffer, RC16_LEN, &sshdr, + SD_TIMEOUT, SD_MAX_RETRIES, NULL); + + if (media_not_present(sdkp, &sshdr)) + return -ENODEV; + + if (the_result) { + sense_valid = scsi_sense_valid(&sshdr); + if (sense_valid && + sshdr.sense_key == ILLEGAL_REQUEST && + (sshdr.asc == 0x20 || sshdr.asc == 0x24) && + sshdr.ascq == 0x00) + /* Invalid Command Operation Code or + * Invalid Field in CDB, just retry + * silently with RC10 */ + return -EINVAL; + if (sense_valid && + sshdr.sense_key == UNIT_ATTENTION && + sshdr.asc == 0x29 && sshdr.ascq == 0x00) + /* Device reset might occur several times, + * give it one more chance */ + if (--reset_retries > 0) + continue; } - + retries--; + + } while (the_result && retries); + + if (the_result) { + sd_printk(KERN_NOTICE, sdkp, "READ CAPACITY(16) failed\n"); + read_capacity_error(sdkp, sdp, &sshdr, sense_valid, the_result); + return -EINVAL; + } + + sector_size = get_unaligned_be32(&buffer[8]); + lba = get_unaligned_be64(&buffer[0]); + + sd_read_protection_type(sdkp, buffer); + + if ((sizeof(sdkp->capacity) == 4) && (lba >= 0xffffffffULL)) { + sd_printk(KERN_ERR, sdkp, "Too big for this kernel. Use a " + "kernel compiled with support for large block " + "devices.\n"); + sdkp->capacity = 0; + return -EOVERFLOW; + } + + /* Logical blocks per physical block exponent */ + sdkp->hw_sector_size = (1 << (buffer[13] & 0xf)) * sector_size; + + /* Lowest aligned logical block */ + alignment = ((buffer[14] & 0x3f) << 8 | buffer[15]) * sector_size; + blk_queue_alignment_offset(sdp->request_queue, alignment); + if (alignment && sdkp->first_scan) + sd_printk(KERN_NOTICE, sdkp, + "physical block alignment offset: %u\n", alignment); + + if (buffer[14] & 0x80) { /* TPE */ + struct request_queue *q = sdp->request_queue; + + sdkp->thin_provisioning = 1; + q->limits.discard_granularity = sdkp->hw_sector_size; + q->limits.max_discard_sectors = 0xffffffff; + + if (buffer[14] & 0x40) /* TPRZ */ + q->limits.discard_zeroes_data = 1; + + queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, q); + } + + sdkp->capacity = lba + 1; + return sector_size; +} + +static int read_capacity_10(struct scsi_disk *sdkp, struct scsi_device *sdp, + unsigned char *buffer) +{ + unsigned char cmd[16]; + struct scsi_sense_hdr sshdr; + int sense_valid = 0; + int the_result; + int retries = 3, reset_retries = READ_CAPACITY_RETRIES_ON_RESET; + sector_t lba; + unsigned sector_size; + + do { + cmd[0] = READ_CAPACITY; + memset(&cmd[1], 0, 9); + memset(buffer, 0, 8); + the_result = scsi_execute_req(sdp, cmd, DMA_FROM_DEVICE, - buffer, longrc ? 13 : 8, &sshdr, - SD_TIMEOUT, SD_MAX_RETRIES); + buffer, 8, &sshdr, + SD_TIMEOUT, SD_MAX_RETRIES, NULL); if (media_not_present(sdkp, &sshdr)) - return; + return -ENODEV; - if (the_result) + if (the_result) { sense_valid = scsi_sense_valid(&sshdr); + if (sense_valid && + sshdr.sense_key == UNIT_ATTENTION && + sshdr.asc == 0x29 && sshdr.ascq == 0x00) + /* Device reset might occur several times, + * give it one more chance */ + if (--reset_retries > 0) + continue; + } retries--; } while (the_result && retries); - if (the_result && !longrc) { + if (the_result) { sd_printk(KERN_NOTICE, sdkp, "READ CAPACITY failed\n"); - sd_print_result(sdkp, the_result); - if (driver_byte(the_result) & DRIVER_SENSE) - sd_print_sense_hdr(sdkp, &sshdr); - else - sd_printk(KERN_NOTICE, sdkp, "Sense not available.\n"); + read_capacity_error(sdkp, sdp, &sshdr, sense_valid, the_result); + return -EINVAL; + } - /* Set dirty bit for removable devices if not ready - - * sometimes drives will not report this properly. */ - if (sdp->removable && - sense_valid && sshdr.sense_key == NOT_READY) - sdp->changed = 1; + sector_size = get_unaligned_be32(&buffer[4]); + lba = get_unaligned_be32(&buffer[0]); - /* Either no media are present but the drive didn't tell us, - or they are present but the read capacity command fails */ - /* sdkp->media_present = 0; -- not always correct */ - sdkp->capacity = 0; /* unknown mapped to zero - as usual */ + if ((sizeof(sdkp->capacity) == 4) && (lba == 0xffffffff)) { + sd_printk(KERN_ERR, sdkp, "Too big for this kernel. Use a " + "kernel compiled with support for large block " + "devices.\n"); + sdkp->capacity = 0; + return -EOVERFLOW; + } - return; - } else if (the_result && longrc) { - /* READ CAPACITY(16) has been failed */ - sd_printk(KERN_NOTICE, sdkp, "READ CAPACITY(16) failed\n"); - sd_print_result(sdkp, the_result); - sd_printk(KERN_NOTICE, sdkp, "Use 0xffffffff as device size\n"); + sdkp->capacity = lba + 1; + sdkp->hw_sector_size = sector_size; + return sector_size; +} - sdkp->capacity = 1 + (sector_t) 0xffffffff; - goto got_data; - } - - if (!longrc) { - sector_size = (buffer[4] << 24) | - (buffer[5] << 16) | (buffer[6] << 8) | buffer[7]; - if (buffer[0] == 0xff && buffer[1] == 0xff && - buffer[2] == 0xff && buffer[3] == 0xff) { - if(sizeof(sdkp->capacity) > 4) { - sd_printk(KERN_NOTICE, sdkp, "Very big device. " - "Trying to use READ CAPACITY(16).\n"); - longrc = 1; - goto repeat; - } - sd_printk(KERN_ERR, sdkp, "Too big for this kernel. Use " - "a kernel compiled with support for large " - "block devices.\n"); - sdkp->capacity = 0; +static int sd_try_rc16_first(struct scsi_device *sdp) +{ + if (sdp->host->max_cmd_len < 16) + return 0; + if (sdp->scsi_level > SCSI_SPC_2) + return 1; + if (scsi_device_protection(sdp)) + return 1; + return 0; +} + +/* + * read disk capacity + */ +static void +sd_read_capacity(struct scsi_disk *sdkp, unsigned char *buffer) +{ + int sector_size; + struct scsi_device *sdp = sdkp->device; + sector_t old_capacity = sdkp->capacity; + + if (sd_try_rc16_first(sdp)) { + sector_size = read_capacity_16(sdkp, sdp, buffer); + if (sector_size == -EOVERFLOW) goto got_data; - } - sdkp->capacity = 1 + (((sector_t)buffer[0] << 24) | - (buffer[1] << 16) | - (buffer[2] << 8) | - buffer[3]); + if (sector_size == -ENODEV) + return; + if (sector_size < 0) + sector_size = read_capacity_10(sdkp, sdp, buffer); + if (sector_size < 0) + return; } else { - sdkp->capacity = 1 + (((u64)buffer[0] << 56) | - ((u64)buffer[1] << 48) | - ((u64)buffer[2] << 40) | - ((u64)buffer[3] << 32) | - ((sector_t)buffer[4] << 24) | - ((sector_t)buffer[5] << 16) | - ((sector_t)buffer[6] << 8) | - (sector_t)buffer[7]); - - sector_size = (buffer[8] << 24) | - (buffer[9] << 16) | (buffer[10] << 8) | buffer[11]; - - sd_read_protection_type(sdkp, buffer); - } - - /* Some devices return the total number of sectors, not the - * highest sector number. Make the necessary adjustment. */ - if (sdp->fix_capacity) { - --sdkp->capacity; + sector_size = read_capacity_10(sdkp, sdp, buffer); + if (sector_size == -EOVERFLOW) + goto got_data; + if (sector_size < 0) + return; + if ((sizeof(sdkp->capacity) > 4) && + (sdkp->capacity > 0xffffffffULL)) { + int old_sector_size = sector_size; + sd_printk(KERN_NOTICE, sdkp, "Very big device. " + "Trying to use READ CAPACITY(16).\n"); + sector_size = read_capacity_16(sdkp, sdp, buffer); + if (sector_size < 0) { + sd_printk(KERN_NOTICE, sdkp, + "Using 0xffffffff as device size\n"); + sdkp->capacity = 1 + (sector_t) 0xffffffff; + sector_size = old_sector_size; + goto got_data; + } + } + } - /* Some devices have version which report the correct sizes - * and others which do not. We guess size according to a heuristic - * and err on the side of lowering the capacity. */ - } else { - if (sdp->guess_capacity) - if (sdkp->capacity & 0x01) /* odd sizes are odd */ - --sdkp->capacity; + /* Some devices are known to return the total number of blocks, + * not the highest block number. Some devices have versions + * which do this and others which do not. Some devices we might + * suspect of doing this but we don't know for certain. + * + * If we know the reported capacity is wrong, decrement it. If + * we can only guess, then assume the number of blocks is even + * (usually true but not always) and err on the side of lowering + * the capacity. + */ + if (sdp->fix_capacity || + (sdp->guess_capacity && (sdkp->capacity & 0x01))) { + sd_printk(KERN_INFO, sdkp, "Adjusting the sector count " + "from its reported value: %llu\n", + (unsigned long long) sdkp->capacity); + --sdkp->capacity; } got_data: @@ -1380,27 +1689,28 @@ got_data: */ sector_size = 512; } + blk_queue_logical_block_size(sdp->request_queue, sector_size); + { - /* - * The msdos fs needs to know the hardware sector size - * So I have created this table. See ll_rw_blk.c - * Jacques Gelinas (Jacques@solucorp.qc.ca) - */ - int hard_sector = sector_size; - sector_t sz = (sdkp->capacity/2) * (hard_sector/256); - struct request_queue *queue = sdp->request_queue; - sector_t mb = sz; + char cap_str_2[10], cap_str_10[10]; + u64 sz = (u64)sdkp->capacity << ilog2(sector_size); - blk_queue_hardsect_size(queue, hard_sector); - /* avoid 64-bit division on 32-bit platforms */ - sector_div(sz, 625); - mb -= sz - 974; - sector_div(mb, 1950); + string_get_size(sz, STRING_UNITS_2, cap_str_2, + sizeof(cap_str_2)); + string_get_size(sz, STRING_UNITS_10, cap_str_10, + sizeof(cap_str_10)); - sd_printk(KERN_NOTICE, sdkp, - "%llu %d-byte hardware sectors (%llu MB)\n", - (unsigned long long)sdkp->capacity, - hard_sector, (unsigned long long)mb); + if (sdkp->first_scan || old_capacity != sdkp->capacity) { + sd_printk(KERN_NOTICE, sdkp, + "%llu %d-byte logical blocks: (%s/%s)\n", + (unsigned long long)sdkp->capacity, + sector_size, cap_str_10, cap_str_2); + + if (sdkp->hw_sector_size != sector_size) + sd_printk(KERN_NOTICE, sdkp, + "%u-byte physical blocks\n", + sdkp->hw_sector_size); + } } /* Rescale capacity to 512-byte units */ @@ -1413,6 +1723,7 @@ got_data: else if (sector_size == 256) sdkp->capacity >>= 1; + blk_queue_physical_block_size(sdp->request_queue, sdkp->hw_sector_size); sdkp->device->sector_size = sector_size; } @@ -1437,6 +1748,7 @@ sd_read_write_protect_flag(struct scsi_disk *sdkp, unsigned char *buffer) int res; struct scsi_device *sdp = sdkp->device; struct scsi_mode_data data; + int old_wp = sdkp->write_prot; set_disk_ro(sdkp->disk, 0); if (sdp->skip_ms_page_3f) { @@ -1477,11 +1789,13 @@ sd_read_write_protect_flag(struct scsi_disk *sdkp, unsigned char *buffer) } else { sdkp->write_prot = ((data.device_specific & 0x80) != 0); set_disk_ro(sdkp->disk, sdkp->write_prot); - sd_printk(KERN_NOTICE, sdkp, "Write Protect is %s\n", - sdkp->write_prot ? "on" : "off"); - sd_printk(KERN_DEBUG, sdkp, - "Mode Sense: %02x %02x %02x %02x\n", - buffer[0], buffer[1], buffer[2], buffer[3]); + if (sdkp->first_scan || old_wp != sdkp->write_prot) { + sd_printk(KERN_NOTICE, sdkp, "Write Protect is %s\n", + sdkp->write_prot ? "on" : "off"); + sd_printk(KERN_DEBUG, sdkp, + "Mode Sense: %02x %02x %02x %02x\n", + buffer[0], buffer[1], buffer[2], buffer[3]); + } } } @@ -1499,6 +1813,9 @@ sd_read_cache_type(struct scsi_disk *sdkp, unsigned char *buffer) int modepage; struct scsi_mode_data data; struct scsi_sense_hdr sshdr; + int old_wce = sdkp->WCE; + int old_rcd = sdkp->RCD; + int old_dpofua = sdkp->DPOFUA; if (sdp->skip_ms_page_8) goto defaults; @@ -1570,12 +1887,14 @@ sd_read_cache_type(struct scsi_disk *sdkp, unsigned char *buffer) sdkp->DPOFUA = 0; } - sd_printk(KERN_NOTICE, sdkp, - "Write cache: %s, read cache: %s, %s\n", - sdkp->WCE ? "enabled" : "disabled", - sdkp->RCD ? "disabled" : "enabled", - sdkp->DPOFUA ? "supports DPO and FUA" - : "doesn't support DPO or FUA"); + if (sdkp->first_scan || old_wce != sdkp->WCE || + old_rcd != sdkp->RCD || old_dpofua != sdkp->DPOFUA) + sd_printk(KERN_NOTICE, sdkp, + "Write cache: %s, read cache: %s, %s\n", + sdkp->WCE ? "enabled" : "disabled", + sdkp->RCD ? "disabled" : "enabled", + sdkp->DPOFUA ? "supports DPO and FUA" + : "doesn't support DPO or FUA"); return; } @@ -1643,6 +1962,94 @@ void sd_read_app_tag_own(struct scsi_disk *sdkp, unsigned char *buffer) } /** + * sd_read_block_limits - Query disk device for preferred I/O sizes. + * @disk: disk to query + */ +static void sd_read_block_limits(struct scsi_disk *sdkp) +{ + struct request_queue *q = sdkp->disk->queue; + unsigned int sector_sz = sdkp->device->sector_size; + const int vpd_len = 64; + unsigned char *buffer = kmalloc(vpd_len, GFP_KERNEL); + + if (!buffer || + /* Block Limits VPD */ + scsi_get_vpd_page(sdkp->device, 0xb0, buffer, vpd_len)) + goto out; + + blk_queue_io_min(sdkp->disk->queue, + get_unaligned_be16(&buffer[6]) * sector_sz); + blk_queue_io_opt(sdkp->disk->queue, + get_unaligned_be32(&buffer[12]) * sector_sz); + + /* Thin provisioning enabled and page length indicates TP support */ + if (sdkp->thin_provisioning && buffer[3] == 0x3c) { + unsigned int lba_count, desc_count, granularity; + + lba_count = get_unaligned_be32(&buffer[20]); + desc_count = get_unaligned_be32(&buffer[24]); + + if (lba_count) { + q->limits.max_discard_sectors = + lba_count * sector_sz >> 9; + + if (desc_count) + sdkp->unmap = 1; + } + + granularity = get_unaligned_be32(&buffer[28]); + + if (granularity) + q->limits.discard_granularity = granularity * sector_sz; + + if (buffer[32] & 0x80) + q->limits.discard_alignment = + get_unaligned_be32(&buffer[32]) & ~(1 << 31); + } + + out: + kfree(buffer); +} + +/** + * sd_read_block_characteristics - Query block dev. characteristics + * @disk: disk to query + */ +static void sd_read_block_characteristics(struct scsi_disk *sdkp) +{ + unsigned char *buffer; + u16 rot; + const int vpd_len = 64; + + buffer = kmalloc(vpd_len, GFP_KERNEL); + + if (!buffer || + /* Block Device Characteristics VPD */ + scsi_get_vpd_page(sdkp->device, 0xb1, buffer, vpd_len)) + goto out; + + rot = get_unaligned_be16(&buffer[4]); + + if (rot == 1) + queue_flag_set_unlocked(QUEUE_FLAG_NONROT, sdkp->disk->queue); + + out: + kfree(buffer); +} + +static int sd_try_extended_inquiry(struct scsi_device *sdp) +{ + /* + * Although VPD inquiries can go to SCSI-2 type devices, + * some USB ones crash on receiving them, and the pages + * we currently ask for are for SPC-3 and beyond + */ + if (sdp->scsi_level > SCSI_SPC_2) + return 1; + return 0; +} + +/** * sd_revalidate_disk - called the first time a new disk is seen, * performs disk spin up, read_capacity, etc. * @disk: struct gendisk we care about @@ -1671,15 +2078,6 @@ static int sd_revalidate_disk(struct gendisk *disk) goto out; } - /* defaults, until the device tells us otherwise */ - sdp->sector_size = 512; - sdkp->capacity = 0; - sdkp->media_present = 1; - sdkp->write_prot = 0; - sdkp->WCE = 0; - sdkp->RCD = 0; - sdkp->ATO = 0; - sd_spinup_disk(sdkp); /* @@ -1688,11 +2086,19 @@ static int sd_revalidate_disk(struct gendisk *disk) */ if (sdkp->media_present) { sd_read_capacity(sdkp, buffer); + + if (sd_try_extended_inquiry(sdp)) { + sd_read_block_limits(sdkp); + sd_read_block_characteristics(sdkp); + } + sd_read_write_protect_flag(sdkp, buffer); sd_read_cache_type(sdkp, buffer); sd_read_app_tag_own(sdkp, buffer); } + sdkp->first_scan = 0; + /* * We now have all cache related info, determine how we deal * with ordered requests. Note that as the current SCSI @@ -1715,6 +2121,107 @@ static int sd_revalidate_disk(struct gendisk *disk) } /** + * sd_format_disk_name - format disk name + * @prefix: name prefix - ie. "sd" for SCSI disks + * @index: index of the disk to format name for + * @buf: output buffer + * @buflen: length of the output buffer + * + * SCSI disk names starts at sda. The 26th device is sdz and the + * 27th is sdaa. The last one for two lettered suffix is sdzz + * which is followed by sdaaa. + * + * This is basically 26 base counting with one extra 'nil' entry + * at the beginning from the second digit on and can be + * determined using similar method as 26 base conversion with the + * index shifted -1 after each digit is computed. + * + * CONTEXT: + * Don't care. + * + * RETURNS: + * 0 on success, -errno on failure. + */ +static int sd_format_disk_name(char *prefix, int index, char *buf, int buflen) +{ + const int base = 'z' - 'a' + 1; + char *begin = buf + strlen(prefix); + char *end = buf + buflen; + char *p; + int unit; + + p = end - 1; + *p = '\0'; + unit = base; + do { + if (p == begin) + return -EINVAL; + *--p = 'a' + (index % unit); + index = (index / unit) - 1; + } while (index >= 0); + + memmove(begin, p, end - p); + memcpy(buf, prefix, strlen(prefix)); + + return 0; +} + +/* + * The asynchronous part of sd_probe + */ +static void sd_probe_async(void *data, async_cookie_t cookie) +{ + struct scsi_disk *sdkp = data; + struct scsi_device *sdp; + struct gendisk *gd; + u32 index; + struct device *dev; + + sdp = sdkp->device; + gd = sdkp->disk; + index = sdkp->index; + dev = &sdp->sdev_gendev; + + if (index < SD_MAX_DISKS) { + gd->major = sd_major((index & 0xf0) >> 4); + gd->first_minor = ((index & 0xf) << 4) | (index & 0xfff00); + gd->minors = SD_MINORS; + } + gd->fops = &sd_fops; + gd->private_data = &sdkp->driver; + gd->queue = sdkp->device->request_queue; + + /* defaults, until the device tells us otherwise */ + sdp->sector_size = 512; + sdkp->capacity = 0; + sdkp->media_present = 1; + sdkp->write_prot = 0; + sdkp->WCE = 0; + sdkp->RCD = 0; + sdkp->ATO = 0; + sdkp->first_scan = 1; + + sd_revalidate_disk(gd); + + blk_queue_prep_rq(sdp->request_queue, sd_prep_fn); + + gd->driverfs_dev = &sdp->sdev_gendev; + gd->flags = GENHD_FL_EXT_DEVT; + if (sdp->removable) + gd->flags |= GENHD_FL_REMOVABLE; + + dev_set_drvdata(dev, sdkp); + add_disk(gd); + sd_dif_config_host(sdkp); + + sd_revalidate_disk(gd); + + sd_printk(KERN_NOTICE, sdkp, "Attached SCSI %sdisk\n", + sdp->removable ? "removable " : ""); + put_device(&sdkp->dev); +} + +/** * sd_probe - called during driver initialization and whenever a * new scsi device is attached to the system. It is called once * for each scsi device (not just disks) present. @@ -1752,7 +2259,7 @@ static int sd_probe(struct device *dev) if (!sdkp) goto out; - gd = alloc_disk(16); + gd = alloc_disk(SD_MINORS); if (!gd) goto out_free; @@ -1760,14 +2267,16 @@ static int sd_probe(struct device *dev) if (!ida_pre_get(&sd_index_ida, GFP_KERNEL)) goto out_put; + spin_lock(&sd_index_lock); error = ida_get_new(&sd_index_ida, &index); + spin_unlock(&sd_index_lock); } while (error == -EAGAIN); if (error) goto out_put; - error = -EBUSY; - if (index >= SD_MAX_DISKS) + error = sd_format_disk_name("sd", index, gd->disk_name, DISK_NAME_LEN); + if (error) goto out_free_index; sdkp->device = sdp; @@ -1777,63 +2286,33 @@ static int sd_probe(struct device *dev) sdkp->openers = 0; sdkp->previous_state = 1; - if (!sdp->timeout) { + if (!sdp->request_queue->rq_timeout) { if (sdp->type != TYPE_MOD) - sdp->timeout = SD_TIMEOUT; + blk_queue_rq_timeout(sdp->request_queue, SD_TIMEOUT); else - sdp->timeout = SD_MOD_TIMEOUT; + blk_queue_rq_timeout(sdp->request_queue, + SD_MOD_TIMEOUT); } device_initialize(&sdkp->dev); sdkp->dev.parent = &sdp->sdev_gendev; sdkp->dev.class = &sd_disk_class; - strncpy(sdkp->dev.bus_id, sdp->sdev_gendev.bus_id, BUS_ID_SIZE); + dev_set_name(&sdkp->dev, dev_name(&sdp->sdev_gendev)); if (device_add(&sdkp->dev)) goto out_free_index; get_device(&sdp->sdev_gendev); - gd->major = sd_major((index & 0xf0) >> 4); - gd->first_minor = ((index & 0xf) << 4) | (index & 0xfff00); - gd->minors = 16; - gd->fops = &sd_fops; - - if (index < 26) { - sprintf(gd->disk_name, "sd%c", 'a' + index % 26); - } else if (index < (26 + 1) * 26) { - sprintf(gd->disk_name, "sd%c%c", - 'a' + index / 26 - 1,'a' + index % 26); - } else { - const unsigned int m1 = (index / 26 - 1) / 26 - 1; - const unsigned int m2 = (index / 26 - 1) % 26; - const unsigned int m3 = index % 26; - sprintf(gd->disk_name, "sd%c%c%c", - 'a' + m1, 'a' + m2, 'a' + m3); - } - - gd->private_data = &sdkp->driver; - gd->queue = sdkp->device->request_queue; - - sd_revalidate_disk(gd); - - blk_queue_prep_rq(sdp->request_queue, sd_prep_fn); - - gd->driverfs_dev = &sdp->sdev_gendev; - gd->flags = GENHD_FL_DRIVERFS; - if (sdp->removable) - gd->flags |= GENHD_FL_REMOVABLE; - - dev_set_drvdata(dev, sdkp); - add_disk(gd); - - sd_printk(KERN_NOTICE, sdkp, "Attached SCSI %sdisk\n", - sdp->removable ? "removable " : ""); + get_device(&sdkp->dev); /* prevent release before async_schedule */ + async_schedule(sd_probe_async, sdkp); return 0; out_free_index: + spin_lock(&sd_index_lock); ida_remove(&sd_index_ida, index); + spin_unlock(&sd_index_lock); out_put: put_disk(gd); out_free: @@ -1855,8 +2334,11 @@ static int sd_probe(struct device *dev) **/ static int sd_remove(struct device *dev) { - struct scsi_disk *sdkp = dev_get_drvdata(dev); + struct scsi_disk *sdkp; + async_synchronize_full(); + sdkp = dev_get_drvdata(dev); + blk_queue_prep_rq(sdkp->device->request_queue, scsi_prep_fn); device_del(&sdkp->dev); del_gendisk(sdkp->disk); sd_shutdown(dev); @@ -1883,7 +2365,9 @@ static void scsi_disk_release(struct device *dev) struct scsi_disk *sdkp = to_scsi_disk(dev); struct gendisk *disk = sdkp->disk; + spin_lock(&sd_index_lock); ida_remove(&sd_index_ida, sdkp->index); + spin_unlock(&sd_index_lock); disk->private_data = NULL; put_disk(disk); @@ -1909,7 +2393,7 @@ static int sd_start_stop_device(struct scsi_disk *sdkp, int start) return -ENODEV; res = scsi_execute_req(sdp, cmd, DMA_NONE, NULL, 0, &sshdr, - SD_TIMEOUT, SD_MAX_RETRIES); + SD_TIMEOUT, SD_MAX_RETRIES, NULL); if (res) { sd_printk(KERN_WARNING, sdkp, "START_STOP FAILED\n"); sd_print_result(sdkp, res); @@ -2013,8 +2497,24 @@ static int __init init_sd(void) if (err) goto err_out_class; + sd_cdb_cache = kmem_cache_create("sd_ext_cdb", SD_EXT_CDB_SIZE, + 0, 0, NULL); + if (!sd_cdb_cache) { + printk(KERN_ERR "sd: can't init extended cdb cache\n"); + goto err_out_class; + } + + sd_cdb_pool = mempool_create_slab_pool(SD_MEMPOOL_SIZE, sd_cdb_cache); + if (!sd_cdb_pool) { + printk(KERN_ERR "sd: can't init extended cdb pool\n"); + goto err_out_cache; + } + return 0; +err_out_cache: + kmem_cache_destroy(sd_cdb_cache); + err_out_class: class_unregister(&sd_disk_class); err_out: @@ -2034,6 +2534,9 @@ static void __exit exit_sd(void) SCSI_LOG_HLQUEUE(3, printk("exit_sd: exiting sd driver\n")); + mempool_destroy(sd_cdb_pool); + kmem_cache_destroy(sd_cdb_cache); + scsi_unregister_driver(&sd_template.gendrv); class_unregister(&sd_disk_class);