diff options
Diffstat (limited to 'drivers/scsi/sd.c')
| -rw-r--r-- | drivers/scsi/sd.c | 2965 |
1 files changed, 2242 insertions, 723 deletions
diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c index bb5b242ac6b..6825eda1114 100644 --- a/drivers/scsi/sd.c +++ b/drivers/scsi/sd.c @@ -32,11 +32,9 @@ * than the level indicated above to trigger output. */ -#include <linux/config.h> #include <linux/module.h> #include <linux/fs.h> #include <linux/kernel.h> -#include <linux/sched.h> #include <linux/mm.h> #include <linux/bio.h> #include <linux/genhd.h> @@ -47,9 +45,14 @@ #include <linux/init.h> #include <linux/blkdev.h> #include <linux/blkpg.h> -#include <linux/kref.h> #include <linux/delay.h> +#include <linux/mutex.h> +#include <linux/string_helpers.h> +#include <linux/async.h> +#include <linux/slab.h> +#include <linux/pm_runtime.h> #include <asm/uaccess.h> +#include <asm/unaligned.h> #include <scsi/scsi.h> #include <scsi/scsi_cmnd.h> @@ -61,70 +64,436 @@ #include <scsi/scsi_ioctl.h> #include <scsi/scsicam.h> +#include "sd.h" +#include "scsi_priv.h" #include "scsi_logging.h" -/* - * More than enough for everybody ;) The huge number of majors - * is a leftover from 16bit dev_t days, we don't really need that - * much numberspace. - */ -#define SD_MAJORS 16 - -/* - * This is limited by the naming scheme enforced in sd_probe, - * add another character to it if you really need more disks. - */ -#define SD_MAX_DISKS (((26 * 26) + 26 + 1) * 26) +MODULE_AUTHOR("Eric Youngdale"); +MODULE_DESCRIPTION("SCSI disk (sd) driver"); +MODULE_LICENSE("GPL"); -/* - * Time out in seconds for disks and Magneto-opticals (which are slower). - */ -#define SD_TIMEOUT (30 * HZ) -#define SD_MOD_TIMEOUT (75 * HZ) +MODULE_ALIAS_BLOCKDEV_MAJOR(SCSI_DISK0_MAJOR); +MODULE_ALIAS_BLOCKDEV_MAJOR(SCSI_DISK1_MAJOR); +MODULE_ALIAS_BLOCKDEV_MAJOR(SCSI_DISK2_MAJOR); +MODULE_ALIAS_BLOCKDEV_MAJOR(SCSI_DISK3_MAJOR); +MODULE_ALIAS_BLOCKDEV_MAJOR(SCSI_DISK4_MAJOR); +MODULE_ALIAS_BLOCKDEV_MAJOR(SCSI_DISK5_MAJOR); +MODULE_ALIAS_BLOCKDEV_MAJOR(SCSI_DISK6_MAJOR); +MODULE_ALIAS_BLOCKDEV_MAJOR(SCSI_DISK7_MAJOR); +MODULE_ALIAS_BLOCKDEV_MAJOR(SCSI_DISK8_MAJOR); +MODULE_ALIAS_BLOCKDEV_MAJOR(SCSI_DISK9_MAJOR); +MODULE_ALIAS_BLOCKDEV_MAJOR(SCSI_DISK10_MAJOR); +MODULE_ALIAS_BLOCKDEV_MAJOR(SCSI_DISK11_MAJOR); +MODULE_ALIAS_BLOCKDEV_MAJOR(SCSI_DISK12_MAJOR); +MODULE_ALIAS_BLOCKDEV_MAJOR(SCSI_DISK13_MAJOR); +MODULE_ALIAS_BLOCKDEV_MAJOR(SCSI_DISK14_MAJOR); +MODULE_ALIAS_BLOCKDEV_MAJOR(SCSI_DISK15_MAJOR); +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 -/* - * Number of allowed retries - */ -#define SD_MAX_RETRIES 5 -#define SD_PASSTHROUGH_RETRIES 1 - -static void scsi_disk_release(struct kref *kref); - -struct scsi_disk { - struct scsi_driver *driver; /* always &sd_template */ - struct scsi_device *device; - struct kref kref; - struct gendisk *disk; - unsigned int openers; /* protected by BKL for now, yuck */ - sector_t capacity; /* size in 512-byte sectors */ - u32 index; - u8 media_present; - u8 write_prot; - unsigned WCE : 1; /* state of disk WCE bit */ - unsigned RCD : 1; /* state of disk RCD bit, unused */ -}; +static void sd_config_discard(struct scsi_disk *, unsigned int); +static void sd_config_write_same(struct scsi_disk *); +static int sd_revalidate_disk(struct gendisk *); +static void sd_unlock_native_capacity(struct gendisk *disk); +static int sd_probe(struct device *); +static int sd_remove(struct device *); +static void sd_shutdown(struct device *); +static int sd_suspend_system(struct device *); +static int sd_suspend_runtime(struct device *); +static int sd_resume(struct device *); +static void sd_rescan(struct device *); +static int sd_init_command(struct scsi_cmnd *SCpnt); +static void sd_uninit_command(struct scsi_cmnd *SCpnt); +static int sd_done(struct scsi_cmnd *); +static int sd_eh_action(struct scsi_cmnd *, int); +static void sd_read_capacity(struct scsi_disk *sdkp, unsigned char *buffer); +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_IDR(sd_index_idr); 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 * face of object destruction (i.e. we can't allow a get on an * object after last put) */ -static DECLARE_MUTEX(sd_ref_sem); +static DEFINE_MUTEX(sd_ref_mutex); -static int sd_revalidate_disk(struct gendisk *disk); -static void sd_rw_intr(struct scsi_cmnd * SCpnt); +static struct kmem_cache *sd_cdb_cache; +static mempool_t *sd_cdb_pool; -static int sd_probe(struct device *); -static int sd_remove(struct device *); -static void sd_shutdown(struct device *dev); -static void sd_rescan(struct device *); -static int sd_init_command(struct scsi_cmnd *); -static int sd_issue_flush(struct device *, sector_t *); -static void sd_end_flush(request_queue_t *, struct request *); -static int sd_prepare_flush(request_queue_t *, struct request *); -static void sd_read_capacity(struct scsi_disk *sdkp, char *diskname, - unsigned char *buffer); +static const char *sd_cache_types[] = { + "write through", "none", "write back", + "write back, no read (daft)" +}; + +static ssize_t +cache_type_store(struct device *dev, struct device_attribute *attr, + const char *buf, size_t count) +{ + int i, ct = -1, rcd, wce, sp; + struct scsi_disk *sdkp = to_scsi_disk(dev); + struct scsi_device *sdp = sdkp->device; + char buffer[64]; + char *buffer_data; + struct scsi_mode_data data; + struct scsi_sense_hdr sshdr; + static const char temp[] = "temporary "; + int len; + + if (sdp->type != TYPE_DISK) + /* no cache control on RBC devices; theoretically they + * can do it, but there's probably so many exceptions + * it's not worth the risk */ + return -EINVAL; + + if (strncmp(buf, temp, sizeof(temp) - 1) == 0) { + buf += sizeof(temp) - 1; + sdkp->cache_override = 1; + } else { + sdkp->cache_override = 0; + } + + for (i = 0; i < ARRAY_SIZE(sd_cache_types); i++) { + len = strlen(sd_cache_types[i]); + if (strncmp(sd_cache_types[i], buf, len) == 0 && + buf[len] == '\n') { + ct = i; + break; + } + } + if (ct < 0) + return -EINVAL; + rcd = ct & 0x01 ? 1 : 0; + wce = ct & 0x02 ? 1 : 0; + + if (sdkp->cache_override) { + sdkp->WCE = wce; + sdkp->RCD = rcd; + return count; + } + + if (scsi_mode_sense(sdp, 0x08, 8, buffer, sizeof(buffer), SD_TIMEOUT, + SD_MAX_RETRIES, &data, NULL)) + return -EINVAL; + len = min_t(size_t, sizeof(buffer), data.length - data.header_length - + data.block_descriptor_length); + buffer_data = buffer + data.header_length + + data.block_descriptor_length; + buffer_data[2] &= ~0x05; + buffer_data[2] |= wce << 2 | rcd; + sp = buffer_data[0] & 0x80 ? 1 : 0; + + if (scsi_mode_select(sdp, 1, sp, 8, buffer_data, len, SD_TIMEOUT, + SD_MAX_RETRIES, &data, &sshdr)) { + if (scsi_sense_valid(&sshdr)) + sd_print_sense_hdr(sdkp, &sshdr); + return -EINVAL; + } + revalidate_disk(sdkp->disk); + return count; +} + +static ssize_t +manage_start_stop_show(struct device *dev, struct device_attribute *attr, + char *buf) +{ + struct scsi_disk *sdkp = to_scsi_disk(dev); + struct scsi_device *sdp = sdkp->device; + + return snprintf(buf, 20, "%u\n", sdp->manage_start_stop); +} + +static ssize_t +manage_start_stop_store(struct device *dev, struct device_attribute *attr, + const char *buf, size_t count) +{ + struct scsi_disk *sdkp = to_scsi_disk(dev); + struct scsi_device *sdp = sdkp->device; + + if (!capable(CAP_SYS_ADMIN)) + return -EACCES; + + sdp->manage_start_stop = simple_strtoul(buf, NULL, 10); + + return count; +} +static DEVICE_ATTR_RW(manage_start_stop); + +static ssize_t +allow_restart_show(struct device *dev, struct device_attribute *attr, char *buf) +{ + struct scsi_disk *sdkp = to_scsi_disk(dev); + + return snprintf(buf, 40, "%d\n", sdkp->device->allow_restart); +} + +static ssize_t +allow_restart_store(struct device *dev, struct device_attribute *attr, + const char *buf, size_t count) +{ + struct scsi_disk *sdkp = to_scsi_disk(dev); + struct scsi_device *sdp = sdkp->device; + + if (!capable(CAP_SYS_ADMIN)) + return -EACCES; + + if (sdp->type != TYPE_DISK) + return -EINVAL; + + sdp->allow_restart = simple_strtoul(buf, NULL, 10); + + return count; +} +static DEVICE_ATTR_RW(allow_restart); + +static ssize_t +cache_type_show(struct device *dev, struct device_attribute *attr, char *buf) +{ + struct scsi_disk *sdkp = to_scsi_disk(dev); + int ct = sdkp->RCD + 2*sdkp->WCE; + + return snprintf(buf, 40, "%s\n", sd_cache_types[ct]); +} +static DEVICE_ATTR_RW(cache_type); + +static ssize_t +FUA_show(struct device *dev, struct device_attribute *attr, char *buf) +{ + struct scsi_disk *sdkp = to_scsi_disk(dev); + + return snprintf(buf, 20, "%u\n", sdkp->DPOFUA); +} +static DEVICE_ATTR_RO(FUA); + +static ssize_t +protection_type_show(struct device *dev, struct device_attribute *attr, + char *buf) +{ + struct scsi_disk *sdkp = to_scsi_disk(dev); + + return snprintf(buf, 20, "%u\n", sdkp->protection_type); +} + +static ssize_t +protection_type_store(struct device *dev, struct device_attribute *attr, + const char *buf, size_t count) +{ + struct scsi_disk *sdkp = to_scsi_disk(dev); + unsigned int val; + int err; + + if (!capable(CAP_SYS_ADMIN)) + return -EACCES; + + err = kstrtouint(buf, 10, &val); + + if (err) + return err; + + if (val >= 0 && val <= SD_DIF_TYPE3_PROTECTION) + sdkp->protection_type = val; + + return count; +} +static DEVICE_ATTR_RW(protection_type); + +static ssize_t +protection_mode_show(struct device *dev, struct device_attribute *attr, + char *buf) +{ + struct scsi_disk *sdkp = to_scsi_disk(dev); + struct scsi_device *sdp = sdkp->device; + unsigned int dif, dix; + + dif = scsi_host_dif_capable(sdp->host, sdkp->protection_type); + dix = scsi_host_dix_capable(sdp->host, sdkp->protection_type); + + if (!dix && scsi_host_dix_capable(sdp->host, SD_DIF_TYPE0_PROTECTION)) { + dif = 0; + dix = 1; + } + + if (!dif && !dix) + return snprintf(buf, 20, "none\n"); + + return snprintf(buf, 20, "%s%u\n", dix ? "dix" : "dif", dif); +} +static DEVICE_ATTR_RO(protection_mode); + +static ssize_t +app_tag_own_show(struct device *dev, struct device_attribute *attr, char *buf) +{ + struct scsi_disk *sdkp = to_scsi_disk(dev); + + return snprintf(buf, 20, "%u\n", sdkp->ATO); +} +static DEVICE_ATTR_RO(app_tag_own); + +static ssize_t +thin_provisioning_show(struct device *dev, struct device_attribute *attr, + char *buf) +{ + struct scsi_disk *sdkp = to_scsi_disk(dev); + + return snprintf(buf, 20, "%u\n", sdkp->lbpme); +} +static DEVICE_ATTR_RO(thin_provisioning); + +static const char *lbp_mode[] = { + [SD_LBP_FULL] = "full", + [SD_LBP_UNMAP] = "unmap", + [SD_LBP_WS16] = "writesame_16", + [SD_LBP_WS10] = "writesame_10", + [SD_LBP_ZERO] = "writesame_zero", + [SD_LBP_DISABLE] = "disabled", +}; + +static ssize_t +provisioning_mode_show(struct device *dev, struct device_attribute *attr, + char *buf) +{ + struct scsi_disk *sdkp = to_scsi_disk(dev); + + return snprintf(buf, 20, "%s\n", lbp_mode[sdkp->provisioning_mode]); +} + +static ssize_t +provisioning_mode_store(struct device *dev, struct device_attribute *attr, + const char *buf, size_t count) +{ + struct scsi_disk *sdkp = to_scsi_disk(dev); + struct scsi_device *sdp = sdkp->device; + + if (!capable(CAP_SYS_ADMIN)) + return -EACCES; + + if (sdp->type != TYPE_DISK) + return -EINVAL; + + if (!strncmp(buf, lbp_mode[SD_LBP_UNMAP], 20)) + sd_config_discard(sdkp, SD_LBP_UNMAP); + else if (!strncmp(buf, lbp_mode[SD_LBP_WS16], 20)) + sd_config_discard(sdkp, SD_LBP_WS16); + else if (!strncmp(buf, lbp_mode[SD_LBP_WS10], 20)) + sd_config_discard(sdkp, SD_LBP_WS10); + else if (!strncmp(buf, lbp_mode[SD_LBP_ZERO], 20)) + sd_config_discard(sdkp, SD_LBP_ZERO); + else if (!strncmp(buf, lbp_mode[SD_LBP_DISABLE], 20)) + sd_config_discard(sdkp, SD_LBP_DISABLE); + else + return -EINVAL; + + return count; +} +static DEVICE_ATTR_RW(provisioning_mode); + +static ssize_t +max_medium_access_timeouts_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct scsi_disk *sdkp = to_scsi_disk(dev); + + return snprintf(buf, 20, "%u\n", sdkp->max_medium_access_timeouts); +} + +static ssize_t +max_medium_access_timeouts_store(struct device *dev, + struct device_attribute *attr, const char *buf, + size_t count) +{ + struct scsi_disk *sdkp = to_scsi_disk(dev); + int err; + + if (!capable(CAP_SYS_ADMIN)) + return -EACCES; + + err = kstrtouint(buf, 10, &sdkp->max_medium_access_timeouts); + + return err ? err : count; +} +static DEVICE_ATTR_RW(max_medium_access_timeouts); + +static ssize_t +max_write_same_blocks_show(struct device *dev, struct device_attribute *attr, + char *buf) +{ + struct scsi_disk *sdkp = to_scsi_disk(dev); + + return snprintf(buf, 20, "%u\n", sdkp->max_ws_blocks); +} + +static ssize_t +max_write_same_blocks_store(struct device *dev, struct device_attribute *attr, + const char *buf, size_t count) +{ + struct scsi_disk *sdkp = to_scsi_disk(dev); + struct scsi_device *sdp = sdkp->device; + unsigned long max; + int err; + + if (!capable(CAP_SYS_ADMIN)) + return -EACCES; + + if (sdp->type != TYPE_DISK) + return -EINVAL; + + err = kstrtoul(buf, 10, &max); + + if (err) + return err; + + if (max == 0) + sdp->no_write_same = 1; + else if (max <= SD_MAX_WS16_BLOCKS) { + sdp->no_write_same = 0; + sdkp->max_ws_blocks = max; + } + + sd_config_write_same(sdkp); + + return count; +} +static DEVICE_ATTR_RW(max_write_same_blocks); + +static struct attribute *sd_disk_attrs[] = { + &dev_attr_cache_type.attr, + &dev_attr_FUA.attr, + &dev_attr_allow_restart.attr, + &dev_attr_manage_start_stop.attr, + &dev_attr_protection_type.attr, + &dev_attr_protection_mode.attr, + &dev_attr_app_tag_own.attr, + &dev_attr_thin_provisioning.attr, + &dev_attr_provisioning_mode.attr, + &dev_attr_max_write_same_blocks.attr, + &dev_attr_max_medium_access_timeouts.attr, + NULL, +}; +ATTRIBUTE_GROUPS(sd_disk); + +static struct class sd_disk_class = { + .name = "scsi_disk", + .owner = THIS_MODULE, + .dev_release = scsi_disk_release, + .dev_groups = sd_disk_groups, +}; + +static const struct dev_pm_ops sd_pm_ops = { + .suspend = sd_suspend_system, + .resume = sd_resume, + .poweroff = sd_suspend_system, + .restore = sd_resume, + .runtime_suspend = sd_suspend_runtime, + .runtime_resume = sd_resume, +}; static struct scsi_driver sd_template = { .owner = THIS_MODULE, @@ -133,15 +502,26 @@ static struct scsi_driver sd_template = { .probe = sd_probe, .remove = sd_remove, .shutdown = sd_shutdown, + .pm = &sd_pm_ops, }, .rescan = sd_rescan, .init_command = sd_init_command, - .issue_flush = sd_issue_flush, - .prepare_flush = sd_prepare_flush, - .end_flush = sd_end_flush, + .uninit_command = sd_uninit_command, + .done = sd_done, + .eh_action = sd_eh_action, }; /* + * Dummy kobj_map->probe function. + * The default ->probe function will call modprobe, which is + * pointless as this module is already loaded. + */ +static struct kobject *sd_default_probe(dev_t devt, int *partno, void *data) +{ + return NULL; +} + +/* * Device no to disk mapping: * * major disc2 disc p1 @@ -170,13 +550,6 @@ static int sd_major(int major_idx) } } -#define to_scsi_disk(obj) container_of(obj,struct scsi_disk,kref) - -static inline struct scsi_disk *scsi_disk(struct gendisk *disk) -{ - return container_of(disk->private_data, struct scsi_disk, driver); -} - static struct scsi_disk *__scsi_disk_get(struct gendisk *disk) { struct scsi_disk *sdkp = NULL; @@ -184,7 +557,7 @@ static struct scsi_disk *__scsi_disk_get(struct gendisk *disk) if (disk->private_data) { sdkp = scsi_disk(disk); if (scsi_device_get(sdkp->device) == 0) - kref_get(&sdkp->kref); + get_device(&sdkp->dev); else sdkp = NULL; } @@ -195,9 +568,9 @@ static struct scsi_disk *scsi_disk_get(struct gendisk *disk) { struct scsi_disk *sdkp; - down(&sd_ref_sem); + mutex_lock(&sd_ref_mutex); sdkp = __scsi_disk_get(disk); - up(&sd_ref_sem); + mutex_unlock(&sd_ref_mutex); return sdkp; } @@ -205,11 +578,11 @@ static struct scsi_disk *scsi_disk_get_from_dev(struct device *dev) { struct scsi_disk *sdkp; - down(&sd_ref_sem); + mutex_lock(&sd_ref_mutex); sdkp = dev_get_drvdata(dev); if (sdkp) sdkp = __scsi_disk_get(sdkp->disk); - up(&sd_ref_sem); + mutex_unlock(&sd_ref_mutex); return sdkp; } @@ -217,75 +590,319 @@ static void scsi_disk_put(struct scsi_disk *sdkp) { struct scsi_device *sdev = sdkp->device; - down(&sd_ref_sem); - kref_put(&sdkp->kref, scsi_disk_release); + mutex_lock(&sd_ref_mutex); + put_device(&sdkp->dev); scsi_device_put(sdev); - up(&sd_ref_sem); + 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); +} + +static void sd_config_discard(struct scsi_disk *sdkp, unsigned int mode) +{ + struct request_queue *q = sdkp->disk->queue; + unsigned int logical_block_size = sdkp->device->sector_size; + unsigned int max_blocks = 0; + + q->limits.discard_zeroes_data = sdkp->lbprz; + q->limits.discard_alignment = sdkp->unmap_alignment * + logical_block_size; + q->limits.discard_granularity = + max(sdkp->physical_block_size, + sdkp->unmap_granularity * logical_block_size); + + sdkp->provisioning_mode = mode; + + switch (mode) { + + case SD_LBP_DISABLE: + q->limits.max_discard_sectors = 0; + queue_flag_clear_unlocked(QUEUE_FLAG_DISCARD, q); + return; + + case SD_LBP_UNMAP: + max_blocks = min_not_zero(sdkp->max_unmap_blocks, + (u32)SD_MAX_WS16_BLOCKS); + break; + + case SD_LBP_WS16: + max_blocks = min_not_zero(sdkp->max_ws_blocks, + (u32)SD_MAX_WS16_BLOCKS); + break; + + case SD_LBP_WS10: + max_blocks = min_not_zero(sdkp->max_ws_blocks, + (u32)SD_MAX_WS10_BLOCKS); + break; + + case SD_LBP_ZERO: + max_blocks = min_not_zero(sdkp->max_ws_blocks, + (u32)SD_MAX_WS10_BLOCKS); + q->limits.discard_zeroes_data = 1; + break; + } + + q->limits.max_discard_sectors = max_blocks * (logical_block_size >> 9); + queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, q); } /** - * sd_init_command - build a scsi (read or write) command from - * information in the request structure. - * @SCpnt: pointer to mid-level's per scsi command structure that - * contains request and into which the scsi command is written + * sd_setup_discard_cmnd - unmap blocks on thinly provisioned device + * @sdp: scsi device to operate one + * @rq: Request to prepare * - * Returns 1 if successful and 0 if error (or cannot be done now). + * Will issue either UNMAP or WRITE SAME(16) depending on preference + * indicated by target device. **/ -static int sd_init_command(struct scsi_cmnd * SCpnt) +static int sd_setup_discard_cmnd(struct scsi_device *sdp, struct request *rq) { - unsigned int this_count, timeout; - struct gendisk *disk; - sector_t block; - struct scsi_device *sdp = SCpnt->device; - struct request *rq = SCpnt->request; + struct scsi_disk *sdkp = scsi_disk(rq->rq_disk); + sector_t sector = blk_rq_pos(rq); + unsigned int nr_sectors = blk_rq_sectors(rq); + unsigned int nr_bytes = blk_rq_bytes(rq); + unsigned int len; + int ret; + char *buf; + struct page *page; + + sector >>= ilog2(sdp->sector_size) - 9; + nr_sectors >>= ilog2(sdp->sector_size) - 9; + rq->timeout = SD_TIMEOUT; + + memset(rq->cmd, 0, rq->cmd_len); + + page = alloc_page(GFP_ATOMIC | __GFP_ZERO); + if (!page) + return BLKPREP_DEFER; + + switch (sdkp->provisioning_mode) { + case SD_LBP_UNMAP: + buf = page_address(page); + + rq->cmd_len = 10; + rq->cmd[0] = UNMAP; + rq->cmd[8] = 24; + + put_unaligned_be16(6 + 16, &buf[0]); + put_unaligned_be16(16, &buf[2]); + put_unaligned_be64(sector, &buf[8]); + put_unaligned_be32(nr_sectors, &buf[16]); + + len = 24; + break; + + case SD_LBP_WS16: + rq->cmd_len = 16; + rq->cmd[0] = WRITE_SAME_16; + rq->cmd[1] = 0x8; /* UNMAP */ + put_unaligned_be64(sector, &rq->cmd[2]); + put_unaligned_be32(nr_sectors, &rq->cmd[10]); + + len = sdkp->device->sector_size; + break; + + case SD_LBP_WS10: + case SD_LBP_ZERO: + rq->cmd_len = 10; + rq->cmd[0] = WRITE_SAME; + if (sdkp->provisioning_mode == SD_LBP_WS10) + rq->cmd[1] = 0x8; /* UNMAP */ + put_unaligned_be32(sector, &rq->cmd[2]); + put_unaligned_be16(nr_sectors, &rq->cmd[7]); + + len = sdkp->device->sector_size; + break; - timeout = sdp->timeout; + default: + ret = BLKPREP_KILL; + goto out; + } - /* - * SG_IO from block layer already setup, just copy cdb basically + rq->completion_data = page; + blk_add_request_payload(rq, page, len); + ret = scsi_setup_blk_pc_cmnd(sdp, rq); + rq->__data_len = nr_bytes; + +out: + if (ret != BLKPREP_OK) + __free_page(page); + return ret; +} + +static void sd_config_write_same(struct scsi_disk *sdkp) +{ + struct request_queue *q = sdkp->disk->queue; + unsigned int logical_block_size = sdkp->device->sector_size; + + if (sdkp->device->no_write_same) { + sdkp->max_ws_blocks = 0; + goto out; + } + + /* Some devices can not handle block counts above 0xffff despite + * supporting WRITE SAME(16). Consequently we default to 64k + * blocks per I/O unless the device explicitly advertises a + * bigger limit. */ - if (blk_pc_request(rq)) { - if (sizeof(rq->cmd) > sizeof(SCpnt->cmnd)) - return 0; + if (sdkp->max_ws_blocks > SD_MAX_WS10_BLOCKS) + sdkp->max_ws_blocks = min_not_zero(sdkp->max_ws_blocks, + (u32)SD_MAX_WS16_BLOCKS); + else if (sdkp->ws16 || sdkp->ws10 || sdkp->device->no_report_opcodes) + sdkp->max_ws_blocks = min_not_zero(sdkp->max_ws_blocks, + (u32)SD_MAX_WS10_BLOCKS); + else { + sdkp->device->no_write_same = 1; + sdkp->max_ws_blocks = 0; + } - memcpy(SCpnt->cmnd, rq->cmd, sizeof(SCpnt->cmnd)); - SCpnt->cmd_len = rq->cmd_len; - if (rq_data_dir(rq) == WRITE) - SCpnt->sc_data_direction = DMA_TO_DEVICE; - else if (rq->data_len) - SCpnt->sc_data_direction = DMA_FROM_DEVICE; - else - SCpnt->sc_data_direction = DMA_NONE; +out: + blk_queue_max_write_same_sectors(q, sdkp->max_ws_blocks * + (logical_block_size >> 9)); +} + +/** + * sd_setup_write_same_cmnd - write the same data to multiple blocks + * @sdp: scsi device to operate one + * @rq: Request to prepare + * + * Will issue either WRITE SAME(10) or WRITE SAME(16) depending on + * preference indicated by target device. + **/ +static int sd_setup_write_same_cmnd(struct scsi_device *sdp, struct request *rq) +{ + struct scsi_disk *sdkp = scsi_disk(rq->rq_disk); + struct bio *bio = rq->bio; + sector_t sector = blk_rq_pos(rq); + unsigned int nr_sectors = blk_rq_sectors(rq); + unsigned int nr_bytes = blk_rq_bytes(rq); + int ret; + + if (sdkp->device->no_write_same) + return BLKPREP_KILL; + + BUG_ON(bio_offset(bio) || bio_iovec(bio).bv_len != sdp->sector_size); + + sector >>= ilog2(sdp->sector_size) - 9; + nr_sectors >>= ilog2(sdp->sector_size) - 9; + + rq->__data_len = sdp->sector_size; + rq->timeout = SD_WRITE_SAME_TIMEOUT; + memset(rq->cmd, 0, rq->cmd_len); + + if (sdkp->ws16 || sector > 0xffffffff || nr_sectors > 0xffff) { + rq->cmd_len = 16; + rq->cmd[0] = WRITE_SAME_16; + put_unaligned_be64(sector, &rq->cmd[2]); + put_unaligned_be32(nr_sectors, &rq->cmd[10]); + } else { + rq->cmd_len = 10; + rq->cmd[0] = WRITE_SAME; + put_unaligned_be32(sector, &rq->cmd[2]); + put_unaligned_be16(nr_sectors, &rq->cmd[7]); + } + + ret = scsi_setup_blk_pc_cmnd(sdp, rq); + rq->__data_len = nr_bytes; - this_count = rq->data_len; - if (rq->timeout) - timeout = rq->timeout; + return ret; +} + +static int scsi_setup_flush_cmnd(struct scsi_device *sdp, struct request *rq) +{ + rq->timeout *= SD_FLUSH_TIMEOUT_MULTIPLIER; + rq->retries = SD_MAX_RETRIES; + rq->cmd[0] = SYNCHRONIZE_CACHE; + rq->cmd_len = 10; + + return scsi_setup_blk_pc_cmnd(sdp, rq); +} + +static void sd_uninit_command(struct scsi_cmnd *SCpnt) +{ + struct request *rq = SCpnt->request; - SCpnt->transfersize = rq->data_len; - SCpnt->allowed = SD_PASSTHROUGH_RETRIES; - goto queue; + if (rq->cmd_flags & REQ_DISCARD) + __free_page(rq->completion_data); + + if (SCpnt->cmnd != rq->cmd) { + mempool_free(SCpnt->cmnd, sd_cdb_pool); + SCpnt->cmnd = NULL; + SCpnt->cmd_len = 0; } +} + +static int sd_init_command(struct scsi_cmnd *SCpnt) +{ + struct request *rq = SCpnt->request; + struct scsi_device *sdp = SCpnt->device; + struct gendisk *disk = rq->rq_disk; + 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; /* - * we only do REQ_CMD and REQ_BLOCK_PC + * Discard request come in as REQ_TYPE_FS but we turn them into + * block PC requests to make life easier. */ - if (!blk_fs_request(rq)) - return 0; + if (rq->cmd_flags & REQ_DISCARD) { + ret = sd_setup_discard_cmnd(sdp, rq); + goto out; + } else if (rq->cmd_flags & REQ_WRITE_SAME) { + ret = sd_setup_write_same_cmnd(sdp, rq); + goto out; + } else if (rq->cmd_flags & REQ_FLUSH) { + ret = scsi_setup_flush_cmnd(sdp, rq); + goto out; + } + ret = scsi_setup_fs_cmnd(sdp, rq); + if (ret != BLKPREP_OK) + goto out; + SCpnt = rq->special; + sdkp = scsi_disk(disk); - disk = rq->rq_disk; - block = rq->sector; - this_count = SCpnt->request_bufflen >> 9; + /* from here on until we're complete, any goto out + * is used for a killable error condition */ + ret = BLKPREP_KILL; - SCSI_LOG_HLQUEUE(1, printk("sd_init_command: disk=%s, block=%llu, " - "count=%d\n", disk->disk_name, - (unsigned long long)block, this_count)); + SCSI_LOG_HLQUEUE(1, + scmd_printk(KERN_INFO, SCpnt, + "%s: block=%llu, count=%d\n", + __func__, (unsigned long long)block, this_count)); if (!sdp || !scsi_device_online(sdp) || - block + rq->nr_sectors > get_capacity(disk)) { - SCSI_LOG_HLQUEUE(2, printk("Finishing %ld sectors\n", - rq->nr_sectors)); - SCSI_LOG_HLQUEUE(2, printk("Retry with 0x%p\n", SCpnt)); - return 0; + block + blk_rq_sectors(rq) > get_capacity(disk)) { + SCSI_LOG_HLQUEUE(2, scmd_printk(KERN_INFO, SCpnt, + "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; } if (sdp->changed) { @@ -293,11 +910,29 @@ static int sd_init_command(struct scsi_cmnd * SCpnt) * quietly refuse to do anything to a changed disc until * the changed bit has been reset */ - /* printk("SCSI disk has been changed. Prohibiting further I/O.\n"); */ - return 0; + /* printk("SCSI disk has been changed or is not present. Prohibiting further I/O.\n"); */ + goto out; + } + + /* + * Some SD card readers can't handle multi-sector accesses which touch + * the last one or two hardware sectors. Split accesses as needed. + */ + 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, printk("%s : block=%llu\n", - disk->disk_name, (unsigned long long)block)); + + SCSI_LOG_HLQUEUE(2, scmd_printk(KERN_INFO, SCpnt, "block=%llu\n", + (unsigned long long)block)); /* * If we have a 1K hardware sectorsize, prevent access to single @@ -311,27 +946,30 @@ static int sd_init_command(struct scsi_cmnd * SCpnt) * for this. */ if (sdp->sector_size == 1024) { - if ((block & 1) || (rq->nr_sectors & 1)) { - printk(KERN_ERR "sd: Bad block number requested"); - return 0; + if ((block & 1) || (blk_rq_sectors(rq) & 1)) { + scmd_printk(KERN_ERR, SCpnt, + "Bad block number requested\n"); + goto out; } else { block = block >> 1; this_count = this_count >> 1; } } if (sdp->sector_size == 2048) { - if ((block & 3) || (rq->nr_sectors & 3)) { - printk(KERN_ERR "sd: Bad block number requested"); - return 0; + if ((block & 3) || (blk_rq_sectors(rq) & 3)) { + scmd_printk(KERN_ERR, SCpnt, + "Bad block number requested\n"); + goto out; } else { block = block >> 2; this_count = this_count >> 2; } } if (sdp->sector_size == 4096) { - if ((block & 7) || (rq->nr_sectors & 7)) { - printk(KERN_ERR "sd: Bad block number requested"); - return 0; + if ((block & 7) || (blk_rq_sectors(rq) & 7)) { + scmd_printk(KERN_ERR, SCpnt, + "Bad block number requested\n"); + goto out; } else { block = block >> 3; this_count = this_count >> 3; @@ -339,27 +977,74 @@ static int sd_init_command(struct scsi_cmnd * SCpnt) } if (rq_data_dir(rq) == WRITE) { if (!sdp->writeable) { - return 0; + goto out; } 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); + } else if (rq_data_dir(rq) == READ) { SCpnt->cmnd[0] = READ_6; SCpnt->sc_data_direction = DMA_FROM_DEVICE; } else { - printk(KERN_ERR "sd: Unknown command %lx\n", rq->flags); -/* overkill panic("Unknown sd command %lx\n", rq->flags); */ - return 0; + scmd_printk(KERN_ERR, SCpnt, "Unknown command %llx\n", (unsigned long long) rq->cmd_flags); + goto out; } - SCSI_LOG_HLQUEUE(2, printk("%s : %s %d/%ld 512 byte blocks.\n", - disk->disk_name, (rq_data_dir(rq) == WRITE) ? - "writing" : "reading", this_count, rq->nr_sectors)); + SCSI_LOG_HLQUEUE(2, scmd_printk(KERN_INFO, SCpnt, + "%s %d/%u 512 byte blocks.\n", + (rq_data_dir(rq) == WRITE) ? + "writing" : "reading", this_count, + 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 | ((rq->cmd_flags & REQ_FUA) ? 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 (sdp->use_16_for_rw) { SCpnt->cmnd[0] += READ_16 - READ_6; + SCpnt->cmnd[1] = protect | ((rq->cmd_flags & REQ_FUA) ? 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; @@ -374,11 +1059,13 @@ static int sd_init_command(struct scsi_cmnd * SCpnt) 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] = protect | ((rq->cmd_flags & REQ_FUA) ? 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; @@ -387,14 +1074,29 @@ static int sd_init_command(struct scsi_cmnd * SCpnt) SCpnt->cmnd[7] = (unsigned char) (this_count >> 8) & 0xff; SCpnt->cmnd[8] = (unsigned char) this_count & 0xff; } else { + if (unlikely(rq->cmd_flags & REQ_FUA)) { + /* + * This happens only if this drive failed + * 10byte rw command with ILLEGAL_REQUEST + * during operation and thus turned off + * use_10_for_rw. + */ + scmd_printk(KERN_ERR, SCpnt, + "FUA write on READ/WRITE(6) drive\n"); + goto out; + } + SCpnt->cmnd[1] |= (unsigned char) ((block >> 16) & 0x1f); SCpnt->cmnd[2] = (unsigned char) ((block >> 8) & 0xff); SCpnt->cmnd[3] = (unsigned char) block & 0xff; SCpnt->cmnd[4] = (unsigned char) this_count; SCpnt->cmnd[5] = 0; } - SCpnt->request_bufflen = SCpnt->bufflen = - this_count * sdp->sector_size; + 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 @@ -405,20 +1107,13 @@ static int sd_init_command(struct scsi_cmnd * SCpnt) SCpnt->underflow = this_count << 9; SCpnt->allowed = SD_MAX_RETRIES; -queue: - SCpnt->timeout_per_command = timeout; - - /* - * This is the completion routine we use. This is matched in terms - * of capability to this function. - */ - SCpnt->done = sd_rw_intr; - /* * This indicates that the command is ready from our end to be * queued. */ - return 1; + ret = BLKPREP_OK; + out: + return ret; } /** @@ -433,19 +1128,19 @@ queue: * or from within the kernel (e.g. as a result of a mount(1) ). * In the latter case @inode and @filp carry an abridged amount * of information as noted above. + * + * Locking: called with bdev->bd_mutex held. **/ -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, printk("sd_open: disk=%s\n", disk->disk_name)); + SCSI_LOG_HLQUEUE(3, sd_printk(KERN_INFO, sdkp, "sd_open\n")); sdev = sdkp->device; @@ -458,14 +1153,13 @@ 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; /* @@ -473,7 +1167,7 @@ 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; /* @@ -486,7 +1180,7 @@ static int sd_open(struct inode *inode, struct file *filp) if (!scsi_device_online(sdev)) goto error_out; - if (!sdkp->openers++ && sdev->removable) { + if ((atomic_inc_return(&sdkp->openers) == 1) && sdev->removable) { if (scsi_block_when_processing_errors(sdev)) scsi_set_medium_removal(sdev, SCSI_REMOVAL_PREVENT); } @@ -508,16 +1202,17 @@ error_out: * * Note: may block (uninterruptible) if error recovery is underway * on this disk. + * + * Locking: called with bdev->bd_mutex held. **/ -static int sd_release(struct inode *inode, struct file *filp) +static void 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; - SCSI_LOG_HLQUEUE(3, printk("sd_release: disk=%s\n", disk->disk_name)); + SCSI_LOG_HLQUEUE(3, sd_printk(KERN_INFO, sdkp, "sd_release\n")); - if (!--sdkp->openers && sdev->removable) { + if (atomic_dec_return(&sdkp->openers) == 0 && sdev->removable) { if (scsi_block_when_processing_errors(sdev)) scsi_set_medium_removal(sdev, SCSI_REMOVAL_ALLOW); } @@ -526,11 +1221,11 @@ static int sd_release(struct inode *inode, struct file *filp) * XXX and what if there are packets in flight and this close() * XXX is followed by a "rmmod sd_mod"? */ + scsi_disk_put(sdkp); - return 0; } -static int sd_hdio_getgeo(struct block_device *bdev, struct hd_geometry __user *loc) +static int sd_getgeo(struct block_device *bdev, struct hd_geometry *geo) { struct scsi_disk *sdkp = scsi_disk(bdev->bd_disk); struct scsi_device *sdp = sdkp->device; @@ -548,15 +1243,9 @@ static int sd_hdio_getgeo(struct block_device *bdev, struct hd_geometry __user * else scsicam_bios_param(bdev, sdkp->capacity, diskinfo); - if (put_user(diskinfo[0], &loc->heads)) - return -EFAULT; - if (put_user(diskinfo[1], &loc->sectors)) - return -EFAULT; - if (put_user(diskinfo[2], &loc->cylinders)) - return -EFAULT; - if (put_user((unsigned)get_start_sect(bdev), - (unsigned long __user *)&loc->start)) - return -EFAULT; + geo->heads = diskinfo[0]; + geo->sectors = diskinfo[1]; + geo->cylinders = diskinfo[2]; return 0; } @@ -568,23 +1257,27 @@ static int sd_hdio_getgeo(struct block_device *bdev, struct hd_geometry __user * * @arg: this is third argument given to ioctl(2) system call. * Often contains a pointer. * - * Returns 0 if successful (some ioctls return postive numbers on + * Returns 0 if successful (some ioctls return positive numbers on * success as well). Returns a negated errno value in case of error. * * Note: most ioctls are forward onto the block subsystem or further - * down in the scsi subsytem. + * 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; + struct scsi_disk *sdkp = scsi_disk(disk); + struct scsi_device *sdp = sdkp->device; void __user *p = (void __user *)arg; int error; - SCSI_LOG_IOCTL(1, printk("sd_ioctl: disk=%s, cmd=0x%x\n", - disk->disk_name, cmd)); + SCSI_LOG_IOCTL(1, sd_printk(KERN_INFO, sdkp, "sd_ioctl: disk=%s, " + "cmd=0x%x\n", disk->disk_name, cmd)); + + error = scsi_verify_blk_ioctl(bdev, cmd); + if (error < 0) + return error; /* * If we are in the middle of error recovery, don't let anyone @@ -592,15 +1285,10 @@ 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; - - if (cmd == HDIO_GETGEO) { - if (!arg) - return -EINVAL; - return sd_hdio_getgeo(bdev, p); - } + goto out; /* * Send SCSI addressing ioctls directly to mid level, send other @@ -610,41 +1298,66 @@ static int sd_ioctl(struct inode * inode, struct file * filp, switch (cmd) { case SCSI_IOCTL_GET_IDLUN: case SCSI_IOCTL_GET_BUS_NUMBER: - return scsi_ioctl(sdp, cmd, p); + error = scsi_ioctl(sdp, cmd, p); + break; default: - error = scsi_cmd_ioctl(filp, disk, cmd, p); + error = scsi_cmd_blk_ioctl(bdev, mode, cmd, p); if (error != -ENOTTY) - return error; + break; + error = scsi_ioctl(sdp, cmd, p); + break; } - return scsi_ioctl(sdp, cmd, p); +out: + return error; } static void set_media_not_present(struct scsi_disk *sdkp) { - sdkp->media_present = 0; - sdkp->capacity = 0; - sdkp->device->changed = 1; + if (sdkp->media_present) + sdkp->device->changed = 1; + + if (sdkp->device->removable) { + sdkp->media_present = 0; + sdkp->capacity = 0; + } +} + +static int media_not_present(struct scsi_disk *sdkp, + struct scsi_sense_hdr *sshdr) +{ + if (!scsi_sense_valid(sshdr)) + return 0; + + /* not invoked for commands that could return deferred errors */ + switch (sshdr->sense_key) { + case UNIT_ATTENTION: + case NOT_READY: + /* medium not present */ + if (sshdr->asc == 0x3A) { + set_media_not_present(sdkp); + return 1; + } + } + return 0; } /** - * sd_media_changed - check if our medium changed - * @disk: kernel device descriptor + * sd_check_events - check media events + * @disk: kernel device descriptor + * @clearing: disk events currently being cleared * - * Returns 0 if not applicable or no change; 1 if change + * Returns mask of DISK_EVENT_*. * * Note: this function is invoked from the block subsystem. **/ -static int sd_media_changed(struct gendisk *disk) +static unsigned int sd_check_events(struct gendisk *disk, unsigned int clearing) { struct scsi_disk *sdkp = scsi_disk(disk); struct scsi_device *sdp = sdkp->device; + struct scsi_sense_hdr *sshdr = NULL; int retval; - SCSI_LOG_HLQUEUE(3, printk("sd_media_changed: disk=%s\n", - disk->disk_name)); - - if (!sdp->removable) - return 0; + SCSI_LOG_HLQUEUE(3, sd_printk(KERN_INFO, sdkp, "sd_check_events\n")); /* * If the device is offline, don't send any commands - just pretend as @@ -652,8 +1365,10 @@ static int sd_media_changed(struct gendisk *disk) * can deal with it then. It is only because of unrecoverable errors * that we would ever take a device offline in the first place. */ - if (!scsi_device_online(sdp)) - goto not_present; + if (!scsi_device_online(sdp)) { + set_media_not_present(sdkp); + goto out; + } /* * Using TEST_UNIT_READY enables differentiation between drive with @@ -665,44 +1380,53 @@ static int sd_media_changed(struct gendisk *disk) * sd_revalidate() is called. */ retval = -ENODEV; - if (scsi_block_when_processing_errors(sdp)) - retval = scsi_test_unit_ready(sdp, SD_TIMEOUT, SD_MAX_RETRIES); - /* - * Unable to test, unit probably not ready. This usually - * means there is no disc in the drive. Mark as changed, - * and we will figure it out later once the drive is - * available again. - */ - if (retval) - goto not_present; + if (scsi_block_when_processing_errors(sdp)) { + sshdr = kzalloc(sizeof(*sshdr), GFP_KERNEL); + retval = scsi_test_unit_ready(sdp, SD_TIMEOUT, SD_MAX_RETRIES, + sshdr); + } + + /* failed to execute TUR, assume media not present */ + if (host_byte(retval)) { + set_media_not_present(sdkp); + goto out; + } + + if (media_not_present(sdkp, sshdr)) + goto out; /* * For removable scsi disk we have to recognise the presence - * of a disk in the drive. This is kept in the struct scsi_disk - * struct and tested at open ! Daniel Roche (dan@lectra.fr) + * of a disk in the drive. */ + if (!sdkp->media_present) + sdp->changed = 1; sdkp->media_present = 1; - - retval = sdp->changed; +out: + /* + * sdp->changed is set under the following conditions: + * + * Medium present state has changed in either direction. + * Device has indicated UNIT_ATTENTION. + */ + kfree(sshdr); + retval = sdp->changed ? DISK_EVENT_MEDIA_CHANGE : 0; sdp->changed = 0; - return retval; - -not_present: - set_media_not_present(sdkp); - return 1; } -static int sd_sync_cache(struct scsi_device *sdp) +static int sd_sync_cache(struct scsi_disk *sdkp) { int retries, res; + struct scsi_device *sdp = sdkp->device; + const int timeout = sdp->request_queue->rq_timeout + * SD_FLUSH_TIMEOUT_MULTIPLIER; struct scsi_sense_hdr sshdr; if (!scsi_device_online(sdp)) return -ENODEV; - for (retries = 3; retries > 0; --retries) { unsigned char cmd[10] = { 0 }; @@ -711,78 +1435,41 @@ static int sd_sync_cache(struct scsi_device *sdp) * Leave the rest of the command zero to indicate * flush everything. */ - res = scsi_execute_req(sdp, cmd, DMA_NONE, NULL, 0, &sshdr, - SD_TIMEOUT, SD_MAX_RETRIES); + res = scsi_execute_req_flags(sdp, cmd, DMA_NONE, NULL, 0, + &sshdr, timeout, SD_MAX_RETRIES, + NULL, REQ_PM); if (res == 0) break; } - if (res) { printk(KERN_WARNING "FAILED\n status = %x, message = %02x, " - "host = %d, driver = %02x\n ", - status_byte(res), msg_byte(res), - host_byte(res), driver_byte(res)); - if (driver_byte(res) & DRIVER_SENSE) - scsi_print_sense_hdr("sd", &sshdr); - } - - return res; -} - -static int sd_issue_flush(struct device *dev, sector_t *error_sector) -{ - int ret = 0; - struct scsi_device *sdp = to_scsi_device(dev); - struct scsi_disk *sdkp = scsi_disk_get_from_dev(dev); - - if (!sdkp) - return -ENODEV; - - if (sdkp->WCE) - ret = sd_sync_cache(sdp); - scsi_disk_put(sdkp); - return ret; -} - -static void sd_end_flush(request_queue_t *q, struct request *flush_rq) -{ - struct request *rq = flush_rq->end_io_data; - struct scsi_cmnd *cmd = rq->special; - unsigned int bytes = rq->hard_nr_sectors << 9; - - if (!flush_rq->errors) { - spin_unlock(q->queue_lock); - scsi_io_completion(cmd, bytes, 0); - spin_lock(q->queue_lock); - } else if (blk_barrier_postflush(rq)) { - spin_unlock(q->queue_lock); - scsi_io_completion(cmd, 0, bytes); - spin_lock(q->queue_lock); - } else { - /* - * force journal abort of barriers - */ - end_that_request_first(rq, -EOPNOTSUPP, rq->hard_nr_sectors); - end_that_request_last(rq); - } -} - -static int sd_prepare_flush(request_queue_t *q, struct request *rq) -{ - struct scsi_device *sdev = q->queuedata; - struct scsi_disk *sdkp = scsi_disk_get_from_dev(&sdev->sdev_gendev); - int ret = 0; - - if (sdkp) { - if (sdkp->WCE) { - memset(rq->cmd, 0, sizeof(rq->cmd)); - rq->flags |= REQ_BLOCK_PC | REQ_SOFTBARRIER; - rq->timeout = SD_TIMEOUT; - rq->cmd[0] = SYNCHRONIZE_CACHE; - ret = 1; + if (res) { + sd_print_result(sdkp, res); + + if (driver_byte(res) & DRIVER_SENSE) + sd_print_sense_hdr(sdkp, &sshdr); + /* we need to evaluate the error return */ + if (scsi_sense_valid(&sshdr) && + (sshdr.asc == 0x3a || /* medium not present */ + sshdr.asc == 0x20)) /* invalid command */ + /* this is no error here */ + return 0; + + switch (host_byte(res)) { + /* ignore errors due to racing a disconnection */ + case DID_BAD_TARGET: + case DID_NO_CONNECT: + return 0; + /* signal the upper layer it might try again */ + case DID_BUS_BUSY: + case DID_IMM_RETRY: + case DID_REQUEUE: + case DID_SOFT_ERROR: + return -EBUSY; + default: + return -EIO; } - scsi_disk_put(sdkp); } - return ret; + return 0; } static void sd_rescan(struct device *dev) @@ -790,7 +1477,7 @@ 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); } } @@ -801,11 +1488,15 @@ 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_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; + int ret; + + ret = scsi_verify_blk_ioctl(bdev, cmd); + if (ret < 0) + return ret; /* * If we are in the middle of error recovery, don't let anyone @@ -817,8 +1508,6 @@ static long sd_compat_ioctl(struct file *file, unsigned int cmd, unsigned long a return -ENODEV; if (sdev->host->hostt->compat_ioctl) { - int ret; - ret = sdev->host->hostt->compat_ioctl(sdev, cmd, (void __user *)arg); return ret; @@ -831,168 +1520,227 @@ 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, + .getgeo = sd_getgeo, #ifdef CONFIG_COMPAT .compat_ioctl = sd_compat_ioctl, #endif - .media_changed = sd_media_changed, + .check_events = sd_check_events, .revalidate_disk = sd_revalidate_disk, + .unlock_native_capacity = sd_unlock_native_capacity, }; /** - * sd_rw_intr - bottom half handler: called when the lower level + * sd_eh_action - error handling callback + * @scmd: sd-issued command that has failed + * @eh_disp: The recovery disposition suggested by the midlayer + * + * This function is called by the SCSI midlayer upon completion of an + * error test command (currently TEST UNIT READY). The result of sending + * the eh command is passed in eh_disp. We're looking for devices that + * fail medium access commands but are OK with non access commands like + * test unit ready (so wrongly see the device as having a successful + * recovery) + **/ +static int sd_eh_action(struct scsi_cmnd *scmd, int eh_disp) +{ + struct scsi_disk *sdkp = scsi_disk(scmd->request->rq_disk); + + if (!scsi_device_online(scmd->device) || + !scsi_medium_access_command(scmd) || + host_byte(scmd->result) != DID_TIME_OUT || + eh_disp != SUCCESS) + return eh_disp; + + /* + * The device has timed out executing a medium access command. + * However, the TEST UNIT READY command sent during error + * handling completed successfully. Either the device is in the + * process of recovering or has it suffered an internal failure + * that prevents access to the storage medium. + */ + sdkp->medium_access_timed_out++; + + /* + * If the device keeps failing read/write commands but TEST UNIT + * READY always completes successfully we assume that medium + * access is no longer possible and take the device offline. + */ + if (sdkp->medium_access_timed_out >= sdkp->max_medium_access_timeouts) { + scmd_printk(KERN_ERR, scmd, + "Medium access timeout failure. Offlining disk!\n"); + scsi_device_set_state(scmd->device, SDEV_OFFLINE); + + return FAILED; + } + + return eh_disp; +} + +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; + /* + * resid is optional but mostly filled in. When it's unused, + * its value is zero, so we assume the whole buffer transferred + */ + unsigned int transferred = scsi_bufflen(scmd) - scsi_get_resid(scmd); + unsigned int good_bytes; + + if (scmd->request->cmd_type != REQ_TYPE_FS) + 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 */ + unsigned int 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. + */ + good_bytes = (bad_lba - start_lba) * scmd->device->sector_size; + return min(good_bytes, transferred); +} + +/** + * sd_done - bottom half handler: called when the lower level * driver has completed (successfully or otherwise) a scsi command. * @SCpnt: mid-level's per command structure. * * Note: potentially run from within an ISR. Must not block. **/ -static void sd_rw_intr(struct scsi_cmnd * SCpnt) +static int sd_done(struct scsi_cmnd *SCpnt) { int result = SCpnt->result; - int this_count = SCpnt->bufflen; - int good_bytes = (result == 0 ? this_count : 0); - sector_t block_sectors = 1; - u64 first_err_block; - sector_t error_sector; + unsigned int good_bytes = result ? 0 : scsi_bufflen(SCpnt); struct scsi_sense_hdr sshdr; + struct scsi_disk *sdkp = scsi_disk(SCpnt->request->rq_disk); + struct request *req = SCpnt->request; int sense_valid = 0; int sense_deferred = 0; - int info_valid; + unsigned char op = SCpnt->cmnd[0]; + unsigned char unmap = SCpnt->cmnd[1] & 8; + + if (req->cmd_flags & REQ_DISCARD || req->cmd_flags & REQ_WRITE_SAME) { + if (!result) { + good_bytes = blk_rq_bytes(req); + scsi_set_resid(SCpnt, 0); + } else { + good_bytes = 0; + scsi_set_resid(SCpnt, blk_rq_bytes(req)); + } + } if (result) { sense_valid = scsi_command_normalize_sense(SCpnt, &sshdr); if (sense_valid) sense_deferred = scsi_sense_is_deferred(&sshdr); } - #ifdef CONFIG_SCSI_LOGGING - SCSI_LOG_HLCOMPLETE(1, printk("sd_rw_intr: %s: res=0x%x\n", - SCpnt->request->rq_disk->disk_name, result)); + SCSI_LOG_HLCOMPLETE(1, scsi_print_result(SCpnt)); if (sense_valid) { - SCSI_LOG_HLCOMPLETE(1, printk("sd_rw_intr: sb[respc,sk,asc," - "ascq]=%x,%x,%x,%x\n", sshdr.response_code, - sshdr.sense_key, sshdr.asc, sshdr.ascq)); + SCSI_LOG_HLCOMPLETE(1, scmd_printk(KERN_INFO, SCpnt, + "sd_done: sb[respc,sk,asc," + "ascq]=%x,%x,%x,%x\n", + sshdr.response_code, + sshdr.sense_key, sshdr.asc, + sshdr.ascq)); } #endif - /* - Handle MEDIUM ERRORs that indicate partial success. Since this is a - relatively rare error condition, no care is taken to avoid - unnecessary additional work such as memcpy's that could be avoided. - */ + sdkp->medium_access_timed_out = 0; - /* - * If SG_IO from block layer then set good_bytes to stop retries; - * else if errors, check them, and if necessary prepare for - * (partial) retries. - */ - if (blk_pc_request(SCpnt->request)) - good_bytes = this_count; - else if (driver_byte(result) != 0 && - sense_valid && !sense_deferred) { - switch (sshdr.sense_key) { - case MEDIUM_ERROR: - if (!blk_fs_request(SCpnt->request)) - break; - info_valid = scsi_get_sense_info_fld( - SCpnt->sense_buffer, SCSI_SENSE_BUFFERSIZE, - &first_err_block); - /* - * May want to warn and skip if following cast results - * in actual truncation (if sector_t < 64 bits) - */ - error_sector = (sector_t)first_err_block; - if (SCpnt->request->bio != NULL) - block_sectors = bio_sectors(SCpnt->request->bio); - switch (SCpnt->device->sector_size) { - case 1024: - error_sector <<= 1; - if (block_sectors < 2) - block_sectors = 2; - break; - case 2048: - error_sector <<= 2; - if (block_sectors < 4) - block_sectors = 4; - break; - case 4096: - error_sector <<=3; - if (block_sectors < 8) - block_sectors = 8; - break; - case 256: - error_sector >>= 1; - break; - default: + if (driver_byte(result) != DRIVER_SENSE && + (!sense_valid || sense_deferred)) + goto out; + + switch (sshdr.sense_key) { + case HARDWARE_ERROR: + case MEDIUM_ERROR: + good_bytes = sd_completed_bytes(SCpnt); + break; + case RECOVERED_ERROR: + good_bytes = scsi_bufflen(SCpnt); + break; + case NO_SENSE: + /* 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); + break; + case ABORTED_COMMAND: + if (sshdr.asc == 0x10) /* DIF: Target detected corruption */ + good_bytes = sd_completed_bytes(SCpnt); + break; + case ILLEGAL_REQUEST: + if (sshdr.asc == 0x10) /* DIX: Host detected corruption */ + good_bytes = sd_completed_bytes(SCpnt); + /* INVALID COMMAND OPCODE or INVALID FIELD IN CDB */ + if (sshdr.asc == 0x20 || sshdr.asc == 0x24) { + switch (op) { + case UNMAP: + sd_config_discard(sdkp, SD_LBP_DISABLE); break; + case WRITE_SAME_16: + case WRITE_SAME: + if (unmap) + sd_config_discard(sdkp, SD_LBP_DISABLE); + else { + sdkp->device->no_write_same = 1; + sd_config_write_same(sdkp); + + good_bytes = 0; + req->__data_len = blk_rq_bytes(req); + req->cmd_flags |= REQ_QUIET; + } } - - error_sector &= ~(block_sectors - 1); - good_bytes = (error_sector - SCpnt->request->sector) << 9; - if (good_bytes < 0 || good_bytes >= this_count) - good_bytes = 0; - break; - - case RECOVERED_ERROR: /* an error occurred, but it recovered */ - case NO_SENSE: /* LLDD got sense data */ - /* - * Inform the user, but make sure that it's not treated - * as a hard error. - */ - scsi_print_sense("sd", SCpnt); - SCpnt->result = 0; - memset(SCpnt->sense_buffer, 0, SCSI_SENSE_BUFFERSIZE); - good_bytes = this_count; - 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; - break; - - default: - break; } + break; + default: + break; } - /* - * This calls the generic completion function, now that we know - * how many actual sectors finished, and how many sectors we need - * to say have failed. - */ - scsi_io_completion(SCpnt, good_bytes, block_sectors << 9); -} - -static int media_not_present(struct scsi_disk *sdkp, - struct scsi_sense_hdr *sshdr) -{ - - if (!scsi_sense_valid(sshdr)) - return 0; - /* not invoked for commands that could return deferred errors */ - if (sshdr->sense_key != NOT_READY && - sshdr->sense_key != UNIT_ATTENTION) - return 0; - if (sshdr->asc != 0x3A) /* medium not present */ - return 0; + out: + if (rq_data_dir(SCpnt->request) == READ && scsi_prot_sg_count(SCpnt)) + sd_dif_complete(SCpnt, good_bytes); - set_media_not_present(sdkp); - return 1; + return good_bytes; } /* * spinup disk - called only in sd_revalidate_disk() */ static void -sd_spinup_disk(struct scsi_disk *sdkp, char *diskname) +sd_spinup_disk(struct scsi_disk *sdkp) { unsigned char cmd[10]; unsigned long spintime_expire = 0; @@ -1015,7 +1763,15 @@ sd_spinup_disk(struct scsi_disk *sdkp, char *diskname) 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 + * doesn't have any media in it, don't bother + * with any more polling. + */ + if (media_not_present(sdkp, &sshdr)) + return; if (the_result) sense_valid = scsi_sense_valid(&sshdr); @@ -1025,53 +1781,44 @@ sd_spinup_disk(struct scsi_disk *sdkp, char *diskname) ((driver_byte(the_result) & DRIVER_SENSE) && sense_valid && sshdr.sense_key == UNIT_ATTENTION))); - /* - * If the drive has indicated to us that it doesn't have - * any media in it, don't bother with any of the rest of - * this crap. - */ - if (media_not_present(sdkp, &sshdr)) - return; - if ((driver_byte(the_result) & DRIVER_SENSE) == 0) { /* no sense, TUR either succeeded or failed * with a status error */ - if(!spintime && !scsi_status_is_good(the_result)) - printk(KERN_NOTICE "%s: Unit Not Ready, " - "error = 0x%x\n", diskname, the_result); + if(!spintime && !scsi_status_is_good(the_result)) { + sd_printk(KERN_NOTICE, sdkp, "Unit Not Ready\n"); + sd_print_result(sdkp, the_result); + } break; } /* * 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) { - printk(KERN_NOTICE "%s: Spinning up disk...", - diskname); + sd_printk(KERN_NOTICE, sdkp, "Spinning up disk..."); cmd[0] = START_STOP; cmd[1] = 1; /* Return immediately */ memset((void *) &cmd[2], 0, 8); cmd[4] = 1; /* Start spin cycle */ + if (sdkp->device->start_stop_pwr_cond) + 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; } @@ -1097,9 +1844,8 @@ sd_spinup_disk(struct scsi_disk *sdkp, char *diskname) /* we don't understand the sense code, so it's * probably pointless to loop */ if(!spintime) { - printk(KERN_NOTICE "%s: Unit Not Ready, " - "sense:\n", diskname); - scsi_print_sense_hdr("", &sshdr); + sd_printk(KERN_NOTICE, sdkp, "Unit Not Ready\n"); + sd_print_sense_hdr(sdkp, &sshdr); } break; } @@ -1114,136 +1860,323 @@ sd_spinup_disk(struct scsi_disk *sdkp, char *diskname) } } + /* - * read disk capacity + * Determine whether disk supports Data Integrity Field. */ -static void -sd_read_capacity(struct scsi_disk *sdkp, char *diskname, - unsigned char *buffer) +static int sd_read_protection_type(struct scsi_disk *sdkp, unsigned char *buffer) +{ + struct scsi_device *sdp = sdkp->device; + u8 type; + int ret = 0; + + if (scsi_device_protection(sdp) == 0 || (buffer[12] & 1) == 0) + return ret; + + type = ((buffer[12] >> 1) & 7) + 1; /* P_TYPE 0 = Type 1 */ + + if (type > SD_DIF_TYPE3_PROTECTION) + ret = -ENODEV; + else if (scsi_host_dif_capable(sdp->host, type)) + ret = 1; + + if (sdkp->first_scan || type != sdkp->protection_type) + switch (ret) { + case -ENODEV: + sd_printk(KERN_ERR, sdkp, "formatted with unsupported" \ + " protection type %u. Disabling disk!\n", + type); + break; + case 1: + sd_printk(KERN_NOTICE, sdkp, + "Enabling DIF Type %u protection\n", type); + break; + case 0: + sd_printk(KERN_NOTICE, sdkp, + "Disabling DIF Type %u protection\n", type); + break; + } + + sdkp->protection_type = type; + + return ret; +} + +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) + set_media_not_present(sdkp); + + /* + * 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 */ +} + +#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; - int longrc = 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; + + if (sdp->no_read_capacity_16) + return -EINVAL; -repeat: - retries = 3; do { - if (longrc) { - memset((void *) cmd, 0, 16); - cmd[0] = SERVICE_ACTION_IN; - cmd[1] = SAI_READ_CAPACITY_16; - cmd[13] = 12; - memset((void *) buffer, 0, 12); - } 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]); + + if (sd_read_protection_type(sdkp, buffer) < 0) { + sdkp->capacity = 0; + return -ENODEV; + } + + 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->physical_block_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) { /* LBPME */ + sdkp->lbpme = 1; + + if (buffer[14] & 0x40) /* LBPRZ */ + sdkp->lbprz = 1; + + sd_config_discard(sdkp, SD_LBP_WS16); + } + + 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 ? 12 : 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) { - printk(KERN_NOTICE "%s : READ CAPACITY failed.\n" - "%s : status=%x, message=%02x, host=%d, driver=%02x \n", - diskname, diskname, - status_byte(the_result), - msg_byte(the_result), - host_byte(the_result), - driver_byte(the_result)); - - if (driver_byte(the_result) & DRIVER_SENSE) - scsi_print_sense_hdr("sd", &sshdr); - else - printk("%s : sense not available. \n", diskname); + if (the_result) { + sd_printk(KERN_NOTICE, sdkp, "READ CAPACITY failed\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 = 0x200000; /* 1 GB - random */ + if (sdp->no_read_capacity_16 && (lba == 0xffffffff)) { + /* Some buggy (usb cardreader) devices return an lba of + 0xffffffff when the want to report a size of 0 (with + which they really mean no media is present) */ + sdkp->capacity = 0; + sdkp->physical_block_size = sector_size; + return sector_size; + } - return; - } else if (the_result && longrc) { - /* READ CAPACITY(16) has been failed */ - printk(KERN_NOTICE "%s : READ CAPACITY(16) failed.\n" - "%s : status=%x, message=%02x, host=%d, driver=%02x \n", - diskname, diskname, - status_byte(the_result), - msg_byte(the_result), - host_byte(the_result), - driver_byte(the_result)); - printk(KERN_NOTICE "%s : use 0xffffffff as device size\n", - diskname); - - 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) { - printk(KERN_NOTICE "%s : very big device. try to use" - " READ CAPACITY(16).\n", diskname); - longrc = 1; - goto repeat; - } - printk(KERN_ERR "%s: too big for this kernel. Use a " - "kernel compiled with support for large block " - "devices.\n", diskname); - sdkp->capacity = 0; + 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; + } + + sdkp->capacity = lba + 1; + sdkp->physical_block_size = sector_size; + return sector_size; +} + +static int sd_try_rc16_first(struct scsi_device *sdp) +{ + if (sdp->host->max_cmd_len < 16) + return 0; + if (sdp->try_rc_10_first) + 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]; - } - - /* Some devices return the total number of sectors, not the - * highest sector number. Make the necessary adjustment. */ - if (sdp->fix_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 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: if (sector_size == 0) { sector_size = 512; - printk(KERN_NOTICE "%s : sector size 0 reported, " - "assuming 512.\n", diskname); + sd_printk(KERN_NOTICE, sdkp, "Sector size 0 reported, " + "assuming 512.\n"); } if (sector_size != 512 && @@ -1251,8 +2184,8 @@ got_data: sector_size != 2048 && sector_size != 4096 && sector_size != 256) { - printk(KERN_NOTICE "%s : unsupported sector size " - "%d.\n", diskname, sector_size); + sd_printk(KERN_NOTICE, sdkp, "Unsupported sector size %d.\n", + sector_size); /* * The user might want to re-format the drive with * a supported sectorsize. Once this happens, it @@ -1268,29 +2201,32 @@ got_data: */ sector_size = 512; } - { - /* - * 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); - request_queue_t *queue = sdp->request_queue; - sector_t mb = sz; + blk_queue_logical_block_size(sdp->request_queue, 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); - - printk(KERN_NOTICE "SCSI device %s: " - "%llu %d-byte hdwr sectors (%llu MB)\n", - diskname, (unsigned long long)sdkp->capacity, - hard_sector, (unsigned long long)mb); + { + char cap_str_2[10], cap_str_10[10]; + u64 sz = (u64)sdkp->capacity << ilog2(sector_size); + + 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)); + + 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->physical_block_size != sector_size) + sd_printk(KERN_NOTICE, sdkp, + "%u-byte physical blocks\n", + sdkp->physical_block_size); + } } + sdp->use_16_for_rw = (sdkp->capacity > 0xffffffff); + /* Rescale capacity to 512-byte units */ if (sector_size == 4096) sdkp->capacity <<= 3; @@ -1301,6 +2237,8 @@ got_data: else if (sector_size == 256) sdkp->capacity >>= 1; + blk_queue_physical_block_size(sdp->request_queue, + sdkp->physical_block_size); sdkp->device->sector_size = sector_size; } @@ -1317,19 +2255,19 @@ sd_do_mode_sense(struct scsi_device *sdp, int dbd, int modepage, /* * read write protect setting, if possible - called only in sd_revalidate_disk() - * called with buffer of length 512 + * called with buffer of length SD_BUF_SIZE */ static void -sd_read_write_protect_flag(struct scsi_disk *sdkp, char *diskname, - unsigned char *buffer) +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) { - printk(KERN_NOTICE "%s: assuming Write Enabled\n", diskname); + sd_first_printk(KERN_NOTICE, sdkp, "Assuming Write Enabled\n"); return; } @@ -1361,38 +2299,57 @@ sd_read_write_protect_flag(struct scsi_disk *sdkp, char *diskname, } if (!scsi_status_is_good(res)) { - printk(KERN_WARNING - "%s: test WP failed, assume Write Enabled\n", diskname); + sd_first_printk(KERN_WARNING, sdkp, + "Test WP failed, assume Write Enabled\n"); } else { sdkp->write_prot = ((data.device_specific & 0x80) != 0); set_disk_ro(sdkp->disk, sdkp->write_prot); - printk(KERN_NOTICE "%s: Write Protect is %s\n", diskname, - sdkp->write_prot ? "on" : "off"); - printk(KERN_DEBUG "%s: Mode Sense: %02x %02x %02x %02x\n", - diskname, 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]); + } } } /* * sd_read_cache_type - called only from sd_revalidate_disk() - * called with buffer of length 512 + * called with buffer of length SD_BUF_SIZE */ static void -sd_read_cache_type(struct scsi_disk *sdkp, char *diskname, - unsigned char *buffer) +sd_read_cache_type(struct scsi_disk *sdkp, unsigned char *buffer) { int len = 0, res; struct scsi_device *sdp = sdkp->device; int dbd; int modepage; + int first_len; 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; - if (sdp->type == TYPE_RBC) { + if (sdkp->cache_override) + return; + + first_len = 4; + if (sdp->skip_ms_page_8) { + if (sdp->type == TYPE_RBC) + goto defaults; + else { + if (sdp->skip_ms_page_3f) + goto defaults; + modepage = 0x3F; + if (sdp->use_192_bytes_for_3f) + first_len = 192; + dbd = 0; + } + } else if (sdp->type == TYPE_RBC) { modepage = 6; dbd = 8; } else { @@ -1401,11 +2358,19 @@ sd_read_cache_type(struct scsi_disk *sdkp, char *diskname, } /* cautiously ask */ - res = sd_do_mode_sense(sdp, dbd, modepage, buffer, 4, &data, &sshdr); + res = sd_do_mode_sense(sdp, dbd, modepage, buffer, first_len, + &data, &sshdr); if (!scsi_status_is_good(res)) goto bad_sense; + if (!data.header_length) { + modepage = 6; + first_len = 0; + sd_first_printk(KERN_ERR, sdkp, + "Missing header in MODE_SENSE response\n"); + } + /* that went OK, now ask for the proper length */ len = data.length; @@ -1415,28 +2380,58 @@ sd_read_cache_type(struct scsi_disk *sdkp, char *diskname, */ if (len < 3) goto bad_sense; - if (len > 20) - len = 20; - - /* Take headers and block descriptors into account */ - len += data.header_length + data.block_descriptor_length; + else if (len > SD_BUF_SIZE) { + sd_first_printk(KERN_NOTICE, sdkp, "Truncating mode parameter " + "data from %d to %d bytes\n", len, SD_BUF_SIZE); + len = SD_BUF_SIZE; + } + if (modepage == 0x3F && sdp->use_192_bytes_for_3f) + len = 192; /* Get the data */ - res = sd_do_mode_sense(sdp, dbd, modepage, buffer, len, &data, &sshdr); + if (len > first_len) + res = sd_do_mode_sense(sdp, dbd, modepage, buffer, len, + &data, &sshdr); if (scsi_status_is_good(res)) { - const char *types[] = { - "write through", "none", "write back", - "write back, no read (daft)" - }; - int ct = 0; int offset = data.header_length + data.block_descriptor_length; - if ((buffer[offset] & 0x3f) != modepage) { - printk(KERN_ERR "%s: got wrong page\n", diskname); - goto defaults; + while (offset < len) { + u8 page_code = buffer[offset] & 0x3F; + u8 spf = buffer[offset] & 0x40; + + if (page_code == 8 || page_code == 6) { + /* We're interested only in the first 3 bytes. + */ + if (len - offset <= 2) { + sd_first_printk(KERN_ERR, sdkp, + "Incomplete mode parameter " + "data\n"); + goto defaults; + } else { + modepage = page_code; + goto Page_found; + } + } else { + /* Go to the next page */ + if (spf && len - offset > 3) + offset += 4 + (buffer[offset+2] << 8) + + buffer[offset+3]; + else if (!spf && len - offset > 1) + offset += 2 + buffer[offset+1]; + else { + sd_first_printk(KERN_ERR, sdkp, + "Incomplete mode " + "parameter data\n"); + goto defaults; + } + } } + sd_first_printk(KERN_ERR, sdkp, "No Caching mode page found\n"); + goto defaults; + + Page_found: if (modepage == 8) { sdkp->WCE = ((buffer[offset + 2] & 0x04) != 0); sdkp->RCD = ((buffer[offset + 2] & 0x01) != 0); @@ -1445,10 +2440,24 @@ sd_read_cache_type(struct scsi_disk *sdkp, char *diskname, sdkp->RCD = 0; } - ct = sdkp->RCD + 2*sdkp->WCE; + sdkp->DPOFUA = (data.device_specific & 0x10) != 0; + if (sdp->broken_fua) { + sd_first_printk(KERN_NOTICE, sdkp, "Disabling FUA\n"); + sdkp->DPOFUA = 0; + } else if (sdkp->DPOFUA && !sdkp->device->use_10_for_rw) { + sd_first_printk(KERN_NOTICE, sdkp, + "Uses READ/WRITE(6), disabling FUA\n"); + sdkp->DPOFUA = 0; + } - printk(KERN_NOTICE "SCSI device %s: drive cache: %s\n", - diskname, types[ct]); + 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; } @@ -1457,17 +2466,229 @@ bad_sense: if (scsi_sense_valid(&sshdr) && sshdr.sense_key == ILLEGAL_REQUEST && sshdr.asc == 0x24 && sshdr.ascq == 0x0) - printk(KERN_NOTICE "%s: cache data unavailable\n", - diskname); /* Invalid field in CDB */ + /* Invalid field in CDB */ + sd_first_printk(KERN_NOTICE, sdkp, "Cache data unavailable\n"); else - printk(KERN_ERR "%s: asking for cache data failed\n", - diskname); + sd_first_printk(KERN_ERR, sdkp, + "Asking for cache data failed\n"); defaults: - printk(KERN_ERR "%s: assuming drive cache: write through\n", - diskname); - sdkp->WCE = 0; + if (sdp->wce_default_on) { + sd_first_printk(KERN_NOTICE, sdkp, + "Assuming drive cache: write back\n"); + sdkp->WCE = 1; + } else { + sd_first_printk(KERN_ERR, sdkp, + "Assuming drive cache: write through\n"); + sdkp->WCE = 0; + } sdkp->RCD = 0; + sdkp->DPOFUA = 0; +} + +/* + * The ATO bit indicates whether the DIF application tag is available + * for use by the operating system. + */ +static void sd_read_app_tag_own(struct scsi_disk *sdkp, unsigned char *buffer) +{ + int res, offset; + struct scsi_device *sdp = sdkp->device; + struct scsi_mode_data data; + struct scsi_sense_hdr sshdr; + + if (sdp->type != TYPE_DISK) + return; + + if (sdkp->protection_type == 0) + return; + + res = scsi_mode_sense(sdp, 1, 0x0a, buffer, 36, SD_TIMEOUT, + SD_MAX_RETRIES, &data, &sshdr); + + if (!scsi_status_is_good(res) || !data.header_length || + data.length < 6) { + sd_first_printk(KERN_WARNING, sdkp, + "getting Control mode page failed, assume no ATO\n"); + + if (scsi_sense_valid(&sshdr)) + sd_print_sense_hdr(sdkp, &sshdr); + + return; + } + + offset = data.header_length + data.block_descriptor_length; + + if ((buffer[offset] & 0x3f) != 0x0a) { + sd_first_printk(KERN_ERR, sdkp, "ATO Got wrong page\n"); + return; + } + + if ((buffer[offset + 5] & 0x80) == 0) + return; + + sdkp->ATO = 1; + + return; +} + +/** + * 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) +{ + 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); + + if (buffer[3] == 0x3c) { + unsigned int lba_count, desc_count; + + sdkp->max_ws_blocks = (u32)get_unaligned_be64(&buffer[36]); + + if (!sdkp->lbpme) + goto out; + + lba_count = get_unaligned_be32(&buffer[20]); + desc_count = get_unaligned_be32(&buffer[24]); + + if (lba_count && desc_count) + sdkp->max_unmap_blocks = lba_count; + + sdkp->unmap_granularity = get_unaligned_be32(&buffer[28]); + + if (buffer[32] & 0x80) + sdkp->unmap_alignment = + get_unaligned_be32(&buffer[32]) & ~(1 << 31); + + if (!sdkp->lbpvpd) { /* LBP VPD page not provided */ + + if (sdkp->max_unmap_blocks) + sd_config_discard(sdkp, SD_LBP_UNMAP); + else + sd_config_discard(sdkp, SD_LBP_WS16); + + } else { /* LBP VPD page tells us what to use */ + + if (sdkp->lbpu && sdkp->max_unmap_blocks) + sd_config_discard(sdkp, SD_LBP_UNMAP); + else if (sdkp->lbpws) + sd_config_discard(sdkp, SD_LBP_WS16); + else if (sdkp->lbpws10) + sd_config_discard(sdkp, SD_LBP_WS10); + else + sd_config_discard(sdkp, SD_LBP_DISABLE); + } + } + + 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); +} + +/** + * sd_read_block_provisioning - Query provisioning VPD page + * @disk: disk to query + */ +static void sd_read_block_provisioning(struct scsi_disk *sdkp) +{ + unsigned char *buffer; + const int vpd_len = 8; + + if (sdkp->lbpme == 0) + return; + + buffer = kmalloc(vpd_len, GFP_KERNEL); + + if (!buffer || scsi_get_vpd_page(sdkp->device, 0xb2, buffer, vpd_len)) + goto out; + + sdkp->lbpvpd = 1; + sdkp->lbpu = (buffer[5] >> 7) & 1; /* UNMAP */ + sdkp->lbpws = (buffer[5] >> 6) & 1; /* WRITE SAME(16) with UNMAP */ + sdkp->lbpws10 = (buffer[5] >> 5) & 1; /* WRITE SAME(10) with UNMAP */ + + out: + kfree(buffer); +} + +static void sd_read_write_same(struct scsi_disk *sdkp, unsigned char *buffer) +{ + struct scsi_device *sdev = sdkp->device; + + if (sdev->host->no_write_same) { + sdev->no_write_same = 1; + + return; + } + + if (scsi_report_opcode(sdev, buffer, SD_BUF_SIZE, INQUIRY) < 0) { + /* too large values might cause issues with arcmsr */ + int vpd_buf_len = 64; + + sdev->no_report_opcodes = 1; + + /* Disable WRITE SAME if REPORT SUPPORTED OPERATION + * CODES is unsupported and the device has an ATA + * Information VPD page (SAT). + */ + if (!scsi_get_vpd_page(sdev, 0x89, buffer, vpd_buf_len)) + sdev->no_write_same = 1; + } + + if (scsi_report_opcode(sdev, buffer, SD_BUF_SIZE, WRITE_SAME_16) == 1) + sdkp->ws16 = 1; + + if (scsi_report_opcode(sdev, buffer, SD_BUF_SIZE, WRITE_SAME) == 1) + sdkp->ws10 = 1; +} + +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 && !sdp->skip_vpd_pages) + return 1; + return 0; } /** @@ -1480,8 +2701,10 @@ static int sd_revalidate_disk(struct gendisk *disk) struct scsi_disk *sdkp = scsi_disk(disk); struct scsi_device *sdp = sdkp->device; unsigned char *buffer; + unsigned flush = 0; - SCSI_LOG_HLQUEUE(3, printk("sd_revalidate_disk: disk=%s\n", disk->disk_name)); + SCSI_LOG_HLQUEUE(3, sd_printk(KERN_INFO, sdkp, + "sd_revalidate_disk\n")); /* * If the device is offline, don't try and read capacity or any @@ -1490,36 +2713,50 @@ static int sd_revalidate_disk(struct gendisk *disk) if (!scsi_device_online(sdp)) goto out; - buffer = kmalloc(512, GFP_KERNEL | __GFP_DMA); + buffer = kmalloc(SD_BUF_SIZE, GFP_KERNEL); if (!buffer) { - printk(KERN_WARNING "(sd_revalidate_disk:) Memory allocation " - "failure.\n"); + sd_printk(KERN_WARNING, sdkp, "sd_revalidate_disk: Memory " + "allocation failure.\n"); 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; - - sd_spinup_disk(sdkp, disk->disk_name); + sd_spinup_disk(sdkp); /* * Without media there is no reason to ask; moreover, some devices * react badly if we do. */ if (sdkp->media_present) { - sd_read_capacity(sdkp, disk->disk_name, buffer); - if (sdp->removable) - sd_read_write_protect_flag(sdkp, disk->disk_name, - buffer); - sd_read_cache_type(sdkp, disk->disk_name, buffer); + sd_read_capacity(sdkp, buffer); + + if (sd_try_extended_inquiry(sdp)) { + sd_read_block_provisioning(sdkp); + 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); + sd_read_write_same(sdkp, buffer); } - + + sdkp->first_scan = 0; + + /* + * We now have all cache related info, determine how we deal + * with flush requests. + */ + if (sdkp->WCE) { + flush |= REQ_FLUSH; + if (sdkp->DPOFUA) + flush |= REQ_FUA; + } + + blk_queue_flush(sdkp->disk->queue, flush); + set_capacity(disk, sdkp->capacity); + sd_config_write_same(sdkp); kfree(buffer); out: @@ -1527,6 +2764,130 @@ static int sd_revalidate_disk(struct gendisk *disk) } /** + * sd_unlock_native_capacity - unlock native capacity + * @disk: struct gendisk to set capacity for + * + * Block layer calls this function if it detects that partitions + * on @disk reach beyond the end of the device. If the SCSI host + * implements ->unlock_native_capacity() method, it's invoked to + * give it a chance to adjust the device capacity. + * + * CONTEXT: + * Defined by block layer. Might sleep. + */ +static void sd_unlock_native_capacity(struct gendisk *disk) +{ + struct scsi_device *sdev = scsi_disk(disk)->device; + + if (sdev->host->hostt->unlock_native_capacity) + sdev->host->hostt->unlock_native_capacity(sdev); +} + +/** + * 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; + + 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->cache_override = 0; + sdkp->WCE = 0; + sdkp->RCD = 0; + sdkp->ATO = 0; + sdkp->first_scan = 1; + sdkp->max_medium_access_timeouts = SD_MAX_MEDIUM_TIMEOUTS; + + sd_revalidate_disk(gd); + + gd->driverfs_dev = &sdp->sdev_gendev; + gd->flags = GENHD_FL_EXT_DEVT; + if (sdp->removable) { + gd->flags |= GENHD_FL_REMOVABLE; + gd->events |= DISK_EVENT_MEDIA_CHANGE; + } + + blk_pm_runtime_init(sdp->request_queue, dev); + add_disk(gd); + if (sdkp->capacity) + sd_dif_config_host(sdkp); + + sd_revalidate_disk(gd); + + sd_printk(KERN_NOTICE, sdkp, "Attached SCSI %sdisk\n", + sdp->removable ? "removable " : ""); + scsi_autopm_put_device(sdp); + 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. @@ -1541,15 +2902,15 @@ static int sd_revalidate_disk(struct gendisk *disk) * (e.g. /dev/sda). More precisely it is the block device major * and minor number that is chosen here. * - * Assume sd_attach is not re-entrant (for time being) - * Also think about sd_attach() and sd_remove() running coincidentally. + * Assume sd_probe is not re-entrant (for time being) + * Also think about sd_probe() and sd_remove() running coincidentally. **/ static int sd_probe(struct device *dev) { struct scsi_device *sdp = to_scsi_device(dev); struct scsi_disk *sdkp; struct gendisk *gd; - u32 index; + int index; int error; error = -ENODEV; @@ -1557,89 +2918,77 @@ static int sd_probe(struct device *dev) goto out; SCSI_LOG_HLQUEUE(3, sdev_printk(KERN_INFO, sdp, - "sd_attach\n")); + "sd_probe\n")); error = -ENOMEM; - sdkp = kmalloc(sizeof(*sdkp), GFP_KERNEL); + sdkp = kzalloc(sizeof(*sdkp), GFP_KERNEL); if (!sdkp) goto out; - memset (sdkp, 0, sizeof(*sdkp)); - kref_init(&sdkp->kref); - - gd = alloc_disk(16); + gd = alloc_disk(SD_MINORS); if (!gd) goto out_free; - if (!idr_pre_get(&sd_index_idr, GFP_KERNEL)) - goto out_put; + do { + if (!ida_pre_get(&sd_index_ida, GFP_KERNEL)) + goto out_put; - spin_lock(&sd_index_lock); - error = idr_get_new(&sd_index_idr, NULL, &index); - spin_unlock(&sd_index_lock); + spin_lock(&sd_index_lock); + error = ida_get_new(&sd_index_ida, &index); + spin_unlock(&sd_index_lock); + } while (error == -EAGAIN); - if (index >= SD_MAX_DISKS) - error = -EBUSY; - if (error) + if (error) { + sdev_printk(KERN_WARNING, sdp, "sd_probe: memory exhausted.\n"); goto out_put; + } + + error = sd_format_disk_name("sd", index, gd->disk_name, DISK_NAME_LEN); + if (error) { + sdev_printk(KERN_WARNING, sdp, "SCSI disk (sd) name length exceeded.\n"); + goto out_free_index; + } - get_device(&sdp->sdev_gendev); sdkp->device = sdp; sdkp->driver = &sd_template; sdkp->disk = gd; sdkp->index = index; - sdkp->openers = 0; + atomic_set(&sdkp->openers, 0); + atomic_set(&sdkp->device->ioerr_cnt, 0); - 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; - } - - 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); + blk_queue_rq_timeout(sdp->request_queue, + SD_MOD_TIMEOUT); } - strcpy(gd->devfs_name, sdp->devfs_name); + device_initialize(&sdkp->dev); + sdkp->dev.parent = dev; + sdkp->dev.class = &sd_disk_class; + dev_set_name(&sdkp->dev, "%s", dev_name(dev)); - gd->private_data = &sdkp->driver; - - sd_revalidate_disk(gd); - - gd->driverfs_dev = &sdp->sdev_gendev; - gd->flags = GENHD_FL_DRIVERFS; - if (sdp->removable) - gd->flags |= GENHD_FL_REMOVABLE; - gd->queue = sdkp->device->request_queue; + if (device_add(&sdkp->dev)) + goto out_free_index; + get_device(dev); dev_set_drvdata(dev, sdkp); - add_disk(gd); - sdev_printk(KERN_NOTICE, sdp, "Attached scsi %sdisk %s\n", - sdp->removable ? "removable " : "", gd->disk_name); + get_device(&sdkp->dev); /* prevent release before async_schedule */ + async_schedule_domain(sd_probe_async, sdkp, &scsi_sd_probe_domain); return 0; -out_put: + 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: + out_free: kfree(sdkp); -out: + out: return error; } @@ -1656,35 +3005,46 @@ out: **/ static int sd_remove(struct device *dev) { - struct scsi_disk *sdkp = dev_get_drvdata(dev); + struct scsi_disk *sdkp; + dev_t devt; + sdkp = dev_get_drvdata(dev); + devt = disk_devt(sdkp->disk); + scsi_autopm_get_device(sdkp->device); + + async_synchronize_full_domain(&scsi_sd_pm_domain); + async_synchronize_full_domain(&scsi_sd_probe_domain); + device_del(&sdkp->dev); del_gendisk(sdkp->disk); sd_shutdown(dev); - down(&sd_ref_sem); + blk_register_region(devt, SD_MINORS, NULL, + sd_default_probe, NULL, NULL); + + mutex_lock(&sd_ref_mutex); dev_set_drvdata(dev, NULL); - kref_put(&sdkp->kref, scsi_disk_release); - up(&sd_ref_sem); + put_device(&sdkp->dev); + mutex_unlock(&sd_ref_mutex); return 0; } /** * scsi_disk_release - Called to free the scsi_disk structure - * @kref: pointer to embedded kref + * @dev: pointer to embedded class device * - * sd_ref_sem must be held entering this routine. Because it is + * sd_ref_mutex must be held entering this routine. Because it is * called on last put, you should always use the scsi_disk_get() * scsi_disk_put() helpers which manipulate the semaphore directly - * and never do a direct kref_put(). + * and never do a direct put_device. **/ -static void scsi_disk_release(struct kref *kref) +static void scsi_disk_release(struct device *dev) { - struct scsi_disk *sdkp = to_scsi_disk(kref); + struct scsi_disk *sdkp = to_scsi_disk(dev); struct gendisk *disk = sdkp->disk; spin_lock(&sd_index_lock); - idr_remove(&sd_index_idr, sdkp->index); + ida_remove(&sd_index_ida, sdkp->index); spin_unlock(&sd_index_lock); disk->private_data = NULL; @@ -1694,6 +3054,42 @@ static void scsi_disk_release(struct kref *kref) kfree(sdkp); } +static int sd_start_stop_device(struct scsi_disk *sdkp, int start) +{ + unsigned char cmd[6] = { START_STOP }; /* START_VALID */ + struct scsi_sense_hdr sshdr; + struct scsi_device *sdp = sdkp->device; + int res; + + if (start) + cmd[4] |= 1; /* START */ + + if (sdp->start_stop_pwr_cond) + cmd[4] |= start ? 1 << 4 : 3 << 4; /* Active or Standby */ + + if (!scsi_device_online(sdp)) + return -ENODEV; + + res = scsi_execute_req_flags(sdp, cmd, DMA_NONE, NULL, 0, &sshdr, + SD_TIMEOUT, SD_MAX_RETRIES, NULL, REQ_PM); + if (res) { + sd_printk(KERN_WARNING, sdkp, "START_STOP FAILED\n"); + sd_print_result(sdkp, res); + if (driver_byte(res) & DRIVER_SENSE) + sd_print_sense_hdr(sdkp, &sshdr); + if (scsi_sense_valid(&sshdr) && + /* 0x3a is medium not present */ + sshdr.asc == 0x3a) + res = 0; + } + + /* SCSI error codes must not go to the generic layer */ + if (res) + return -EIO; + + return 0; +} + /* * Send a SYNCHRONIZE CACHE instruction down to the device through * the normal SCSI command structure. Wait for the command to @@ -1701,18 +3097,84 @@ static void scsi_disk_release(struct kref *kref) */ static void sd_shutdown(struct device *dev) { - struct scsi_device *sdp = to_scsi_device(dev); struct scsi_disk *sdkp = scsi_disk_get_from_dev(dev); if (!sdkp) return; /* this can happen */ - if (sdkp->WCE) { - printk(KERN_NOTICE "Synchronizing SCSI cache for disk %s: \n", - sdkp->disk->disk_name); - sd_sync_cache(sdp); + if (pm_runtime_suspended(dev)) + goto exit; + + if (sdkp->WCE && sdkp->media_present) { + sd_printk(KERN_NOTICE, sdkp, "Synchronizing SCSI cache\n"); + sd_sync_cache(sdkp); + } + + if (system_state != SYSTEM_RESTART && sdkp->device->manage_start_stop) { + sd_printk(KERN_NOTICE, sdkp, "Stopping disk\n"); + sd_start_stop_device(sdkp, 0); + } + +exit: + scsi_disk_put(sdkp); +} + +static int sd_suspend_common(struct device *dev, bool ignore_stop_errors) +{ + struct scsi_disk *sdkp = scsi_disk_get_from_dev(dev); + int ret = 0; + + if (!sdkp) + return 0; /* this can happen */ + + if (sdkp->WCE && sdkp->media_present) { + sd_printk(KERN_NOTICE, sdkp, "Synchronizing SCSI cache\n"); + ret = sd_sync_cache(sdkp); + if (ret) { + /* ignore OFFLINE device */ + if (ret == -ENODEV) + ret = 0; + goto done; + } + } + + if (sdkp->device->manage_start_stop) { + sd_printk(KERN_NOTICE, sdkp, "Stopping disk\n"); + /* an error is not worth aborting a system sleep */ + ret = sd_start_stop_device(sdkp, 0); + if (ignore_stop_errors) + ret = 0; } + +done: scsi_disk_put(sdkp); + return ret; +} + +static int sd_suspend_system(struct device *dev) +{ + return sd_suspend_common(dev, true); +} + +static int sd_suspend_runtime(struct device *dev) +{ + return sd_suspend_common(dev, false); +} + +static int sd_resume(struct device *dev) +{ + struct scsi_disk *sdkp = scsi_disk_get_from_dev(dev); + int ret = 0; + + if (!sdkp->device->manage_start_stop) + goto done; + + sd_printk(KERN_NOTICE, sdkp, "Starting disk\n"); + ret = sd_start_stop_device(sdkp, 1); + +done: + scsi_disk_put(sdkp); + return ret; } /** @@ -1723,18 +3185,56 @@ static void sd_shutdown(struct device *dev) **/ static int __init init_sd(void) { - int majors = 0, i; + int majors = 0, i, err; SCSI_LOG_HLQUEUE(3, printk("init_sd: sd driver entry point\n")); - for (i = 0; i < SD_MAJORS; i++) - if (register_blkdev(sd_major(i), "sd") == 0) - majors++; + for (i = 0; i < SD_MAJORS; i++) { + if (register_blkdev(sd_major(i), "sd") != 0) + continue; + majors++; + blk_register_region(sd_major(i), SD_MINORS, NULL, + sd_default_probe, NULL, NULL); + } if (!majors) return -ENODEV; - return scsi_register_driver(&sd_template.gendrv); + err = class_register(&sd_disk_class); + if (err) + goto err_out; + + 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; + } + + err = scsi_register_driver(&sd_template.gendrv); + if (err) + goto err_out_driver; + + return 0; + +err_out_driver: + mempool_destroy(sd_cdb_pool); + +err_out_cache: + kmem_cache_destroy(sd_cdb_cache); + +err_out_class: + class_unregister(&sd_disk_class); +err_out: + for (i = 0; i < SD_MAJORS; i++) + unregister_blkdev(sd_major(i), "sd"); + return err; } /** @@ -1749,13 +3249,32 @@ static void __exit exit_sd(void) SCSI_LOG_HLQUEUE(3, printk("exit_sd: exiting sd driver\n")); scsi_unregister_driver(&sd_template.gendrv); - for (i = 0; i < SD_MAJORS; i++) + mempool_destroy(sd_cdb_pool); + kmem_cache_destroy(sd_cdb_cache); + + class_unregister(&sd_disk_class); + + for (i = 0; i < SD_MAJORS; i++) { + blk_unregister_region(sd_major(i), SD_MINORS); unregister_blkdev(sd_major(i), "sd"); + } } -MODULE_LICENSE("GPL"); -MODULE_AUTHOR("Eric Youngdale"); -MODULE_DESCRIPTION("SCSI disk (sd) driver"); - module_init(init_sd); module_exit(exit_sd); + +static void sd_print_sense_hdr(struct scsi_disk *sdkp, + struct scsi_sense_hdr *sshdr) +{ + sd_printk(KERN_INFO, sdkp, " "); + scsi_show_sense_hdr(sshdr); + sd_printk(KERN_INFO, sdkp, " "); + scsi_show_extd_sense(sshdr->asc, sshdr->ascq); +} + +static void sd_print_result(struct scsi_disk *sdkp, int result) +{ + sd_printk(KERN_INFO, sdkp, " "); + scsi_show_result(result); +} + |