diff options
Diffstat (limited to 'drivers/scsi/sd.c')
| -rw-r--r-- | drivers/scsi/sd.c | 1429 |
1 files changed, 1086 insertions, 343 deletions
diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c index 255da53e5a0..6825eda1114 100644 --- a/drivers/scsi/sd.c +++ b/drivers/scsi/sd.c @@ -49,6 +49,8 @@ #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> @@ -63,6 +65,7 @@ #include <scsi/scsicam.h> #include "sd.h" +#include "scsi_priv.h" #include "scsi_logging.h" MODULE_AUTHOR("Eric Youngdale"); @@ -95,14 +98,21 @@ MODULE_ALIAS_SCSI_DEVICE(TYPE_RBC); #define SD_MINORS 0 #endif +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(struct device *, pm_message_t state); +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 *); @@ -116,8 +126,8 @@ static DEFINE_IDA(sd_index_ida); * object after last put) */ static DEFINE_MUTEX(sd_ref_mutex); -struct kmem_cache *sd_cdb_cache; -mempool_t *sd_cdb_pool; +static struct kmem_cache *sd_cdb_cache; +static mempool_t *sd_cdb_pool; static const char *sd_cache_types[] = { "write through", "none", "write back", @@ -125,8 +135,8 @@ static const char *sd_cache_types[] = { }; static ssize_t -sd_store_cache_type(struct device *dev, struct device_attribute *attr, - const char *buf, size_t count) +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); @@ -135,6 +145,7 @@ sd_store_cache_type(struct device *dev, struct device_attribute *attr, 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) @@ -143,8 +154,15 @@ sd_store_cache_type(struct device *dev, struct device_attribute *attr, * 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++) { - const int len = strlen(sd_cache_types[i]); + len = strlen(sd_cache_types[i]); if (strncmp(sd_cache_types[i], buf, len) == 0 && buf[len] == '\n') { ct = i; @@ -155,6 +173,13 @@ sd_store_cache_type(struct device *dev, struct device_attribute *attr, 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; @@ -177,8 +202,18 @@ sd_store_cache_type(struct device *dev, struct device_attribute *attr, } static ssize_t -sd_store_manage_start_stop(struct device *dev, struct device_attribute *attr, - const char *buf, size_t count) +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; @@ -190,10 +225,19 @@ sd_store_manage_start_stop(struct device *dev, struct device_attribute *attr, return count; } +static DEVICE_ATTR_RW(manage_start_stop); static ssize_t -sd_store_allow_restart(struct device *dev, struct device_attribute *attr, - const char *buf, size_t count) +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; @@ -208,90 +252,247 @@ sd_store_allow_restart(struct device *dev, struct device_attribute *attr, return count; } +static DEVICE_ATTR_RW(allow_restart); static ssize_t -sd_show_cache_type(struct device *dev, struct device_attribute *attr, - char *buf) +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 -sd_show_fua(struct device *dev, struct device_attribute *attr, char *buf) +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 -sd_show_manage_start_stop(struct device *dev, struct device_attribute *attr, - char *buf) +protection_type_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); + return snprintf(buf, 20, "%u\n", sdkp->protection_type); } static ssize_t -sd_show_allow_restart(struct device *dev, struct device_attribute *attr, - char *buf) +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; - return snprintf(buf, 40, "%d\n", sdkp->device->allow_restart); + 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 -sd_show_protection_type(struct device *dev, struct device_attribute *attr, - char *buf) +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; - return snprintf(buf, 20, "%u\n", sdkp->protection_type); + 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 -sd_show_app_tag_own(struct device *dev, struct device_attribute *attr, - char *buf) +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 -sd_show_thin_provisioning(struct device *dev, struct device_attribute *attr, - char *buf) +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); +} - return snprintf(buf, 20, "%u\n", sdkp->thin_provisioning); -} - -static struct device_attribute sd_disk_attrs[] = { - __ATTR(cache_type, S_IRUGO|S_IWUSR, sd_show_cache_type, - sd_store_cache_type), - __ATTR(FUA, S_IRUGO, sd_show_fua, NULL), - __ATTR(allow_restart, S_IRUGO|S_IWUSR, sd_show_allow_restart, - sd_store_allow_restart), - __ATTR(manage_start_stop, S_IRUGO|S_IWUSR, sd_show_manage_start_stop, - sd_store_manage_start_stop), - __ATTR(protection_type, S_IRUGO, sd_show_protection_type, NULL), - __ATTR(app_tag_own, S_IRUGO, sd_show_app_tag_own, NULL), - __ATTR(thin_provisioning, S_IRUGO, sd_show_thin_provisioning, NULL), - __ATTR_NULL, +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_attrs = sd_disk_attrs, + .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 = { @@ -300,15 +501,27 @@ static struct scsi_driver sd_template = { .name = "sd", .probe = sd_probe, .remove = sd_remove, - .suspend = sd_suspend, - .resume = sd_resume, .shutdown = sd_shutdown, + .pm = &sd_pm_ops, }, .rescan = sd_rescan, + .init_command = sd_init_command, + .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 @@ -408,69 +621,243 @@ static void sd_prot_op(struct scsi_cmnd *scmd, unsigned int dif) 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_prepare_discard - unmap blocks on thinly provisioned device + * sd_setup_discard_cmnd - unmap blocks on thinly provisioned device + * @sdp: scsi device to operate one * @rq: Request to prepare * * Will issue either UNMAP or WRITE SAME(16) depending on preference * indicated by target device. **/ -static int sd_prepare_discard(struct request *rq) +static int sd_setup_discard_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 = bio->bi_sector; - unsigned int num = bio_sectors(bio); - - if (sdkp->device->sector_size == 4096) { - sector >>= 3; - num >>= 3; - } - - rq->cmd_type = REQ_TYPE_BLOCK_PC; + 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); - if (sdkp->unmap) { - char *buf = kmap_atomic(bio_page(bio), KM_USER0); + 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; - rq->cmd_len = 10; - - /* Ensure that data length matches payload */ - rq->__data_len = bio->bi_size = bio->bi_io_vec->bv_len = 24; put_unaligned_be16(6 + 16, &buf[0]); put_unaligned_be16(16, &buf[2]); put_unaligned_be64(sector, &buf[8]); - put_unaligned_be32(num, &buf[16]); + put_unaligned_be32(nr_sectors, &buf[16]); - kunmap_atomic(buf, KM_USER0); - } else { + 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(num, &rq->cmd[10]); - rq->cmd_len = 16; + 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; + + default: + ret = BLKPREP_KILL; + goto out; } - return BLKPREP_OK; + 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 (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; + } + +out: + blk_queue_max_write_same_sectors(q, sdkp->max_ws_blocks * + (logical_block_size >> 9)); } /** - * 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_write_same_cmnd - write the same data to multiple blocks + * @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 WRITE SAME(10) or WRITE SAME(16) depending on + * preference indicated by target device. **/ -static int sd_prep_fn(struct request_queue *q, struct request *rq) +static int sd_setup_write_same_cmnd(struct scsi_device *sdp, struct request *rq) { - struct scsi_cmnd *SCpnt; - struct scsi_device *sdp = q->queuedata; + 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; + + 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; + + 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); @@ -483,14 +870,14 @@ static int sd_prep_fn(struct request_queue *q, struct request *rq) * Discard request come in as REQ_TYPE_FS but we turn them into * block PC requests to make life easier. */ - if (blk_discard_rq(rq)) - ret = sd_prepare_discard(rq); - - if (rq->cmd_type == REQ_TYPE_BLOCK_PC) { - ret = scsi_setup_blk_pc_cmnd(sdp, rq); + if (rq->cmd_flags & REQ_DISCARD) { + ret = sd_setup_discard_cmnd(sdp, rq); goto out; - } else if (rq->cmd_type != REQ_TYPE_FS) { - ret = BLKPREP_KILL; + } 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); @@ -503,11 +890,10 @@ static int sd_prep_fn(struct request_queue *q, struct request *rq) * is used for a killable error condition */ ret = BLKPREP_KILL; - SCSI_LOG_HLQUEUE(1, scmd_printk(KERN_INFO, SCpnt, - "sd_init_command: block=%llu, " - "count=%d\n", - (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 + blk_rq_sectors(rq) > get_capacity(disk)) { @@ -524,7 +910,7 @@ static int sd_prep_fn(struct request_queue *q, struct request *rq) * 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"); */ + /* printk("SCSI disk has been changed or is not present. Prohibiting further I/O.\n"); */ goto out; } @@ -596,15 +982,14 @@ static int sd_prep_fn(struct request_queue *q, struct request *rq) SCpnt->cmnd[0] = WRITE_6; SCpnt->sc_data_direction = DMA_TO_DEVICE; - if (blk_integrity_rq(rq) && - sd_dif_prepare(rq, block, sdp->sector_size) == -EIO) - goto out; + 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 { - scmd_printk(KERN_ERR, SCpnt, "Unknown command %x\n", rq->cmd_flags); + scmd_printk(KERN_ERR, SCpnt, "Unknown command %llx\n", (unsigned long long) rq->cmd_flags); goto out; } @@ -634,7 +1019,7 @@ static int sd_prep_fn(struct request_queue *q, struct request *rq) SCpnt->cmnd[0] = VARIABLE_LENGTH_CMD; SCpnt->cmnd[7] = 0x18; SCpnt->cmnd[9] = (rq_data_dir(rq) == READ) ? READ_32 : WRITE_32; - SCpnt->cmnd[10] = protect | (blk_fua_rq(rq) ? 0x8 : 0); + SCpnt->cmnd[10] = protect | ((rq->cmd_flags & REQ_FUA) ? 0x8 : 0); /* LBA */ SCpnt->cmnd[12] = sizeof(block) > 4 ? (unsigned char) (block >> 56) & 0xff : 0; @@ -657,9 +1042,9 @@ static int sd_prep_fn(struct request_queue *q, struct request *rq) SCpnt->cmnd[29] = (unsigned char) (this_count >> 16) & 0xff; SCpnt->cmnd[30] = (unsigned char) (this_count >> 8) & 0xff; SCpnt->cmnd[31] = (unsigned char) this_count & 0xff; - } else if (block > 0xffffffff) { + } else if (sdp->use_16_for_rw) { SCpnt->cmnd[0] += READ_16 - READ_6; - SCpnt->cmnd[1] = protect | (blk_fua_rq(rq) ? 0x8 : 0); + 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; @@ -680,7 +1065,7 @@ static int sd_prep_fn(struct request_queue *q, struct request *rq) this_count = 0xffff; SCpnt->cmnd[0] += READ_10 - READ_6; - SCpnt->cmnd[1] = protect | (blk_fua_rq(rq) ? 0x8 : 0); + 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; @@ -689,7 +1074,7 @@ static int sd_prep_fn(struct request_queue *q, struct request *rq) SCpnt->cmnd[7] = (unsigned char) (this_count >> 8) & 0xff; SCpnt->cmnd[8] = (unsigned char) this_count & 0xff; } else { - if (unlikely(blk_fua_rq(rq))) { + if (unlikely(rq->cmd_flags & REQ_FUA)) { /* * This happens only if this drive failed * 10byte rw command with ILLEGAL_REQUEST @@ -728,7 +1113,7 @@ static int sd_prep_fn(struct request_queue *q, struct request *rq) */ ret = BLKPREP_OK; out: - return scsi_prep_return(q, rq, ret); + return ret; } /** @@ -743,6 +1128,8 @@ static int sd_prep_fn(struct request_queue *q, struct request *rq) * 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 block_device *bdev, fmode_t mode) { @@ -793,7 +1180,7 @@ static int sd_open(struct block_device *bdev, fmode_t mode) 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); } @@ -815,15 +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 gendisk *disk, fmode_t mode) +static void sd_release(struct gendisk *disk, fmode_t mode) { struct scsi_disk *sdkp = scsi_disk(disk); struct scsi_device *sdev = sdkp->device; 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); } @@ -832,8 +1221,8 @@ static int sd_release(struct gendisk *disk, fmode_t mode) * 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_getgeo(struct block_device *bdev, struct hd_geometry *geo) @@ -868,7 +1257,7 @@ static int sd_getgeo(struct block_device *bdev, struct hd_geometry *geo) * @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 @@ -878,12 +1267,17 @@ static int sd_ioctl(struct block_device *bdev, fmode_t mode, unsigned int cmd, unsigned long arg) { 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 @@ -894,7 +1288,7 @@ static int sd_ioctl(struct block_device *bdev, fmode_t mode, error = scsi_nonblockable_ioctl(sdp, cmd, p, (mode & FMODE_NDELAY) != 0); if (!scsi_block_when_processing_errors(sdp) || !error) - return error; + goto out; /* * Send SCSI addressing ioctls directly to mid level, send other @@ -904,41 +1298,66 @@ static int sd_ioctl(struct block_device *bdev, fmode_t mode, 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(disk->queue, disk, mode, 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, sd_printk(KERN_INFO, sdkp, "sd_media_changed\n")); - - 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 @@ -948,7 +1367,6 @@ static int sd_media_changed(struct gendisk *disk) */ if (!scsi_device_online(sdp)) { set_media_not_present(sdkp); - retval = 1; goto out; } @@ -969,34 +1387,32 @@ static int sd_media_changed(struct gendisk *disk) sshdr); } - /* - * 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 || (scsi_sense_valid(sshdr) && - /* 0x3a is medium not present */ - sshdr->asc == 0x3a)) { + /* failed to execute TUR, assume media not present */ + if (host_byte(retval)) { set_media_not_present(sdkp); - retval = 1; 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; - sdp->changed = 0; out: - if (retval != sdkp->previous_state) - sdev_evt_send_simple(sdp, SDEV_EVT_MEDIA_CHANGE, GFP_KERNEL); - sdkp->previous_state = retval; + /* + * 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; } @@ -1004,12 +1420,13 @@ 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 }; @@ -1018,31 +1435,43 @@ static int sd_sync_cache(struct scsi_disk *sdkp) * 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, NULL); + 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) { 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; + } } - - if (res) - return -EIO; return 0; } -static void sd_prepare_flush(struct request_queue *q, struct request *rq) -{ - rq->cmd_type = REQ_TYPE_BLOCK_PC; - rq->timeout = SD_TIMEOUT; - rq->cmd[0] = SYNCHRONIZE_CACHE; - rq->cmd_len = 10; -} - static void sd_rescan(struct device *dev) { struct scsi_disk *sdkp = scsi_disk_get_from_dev(dev); @@ -1063,6 +1492,11 @@ static int sd_compat_ioctl(struct block_device *bdev, fmode_t mode, unsigned int cmd, unsigned long arg) { 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 @@ -1074,8 +1508,6 @@ static int sd_compat_ioctl(struct block_device *bdev, fmode_t mode, return -ENODEV; if (sdev->host->hostt->compat_ioctl) { - int ret; - ret = sdev->host->hostt->compat_ioctl(sdev, cmd, (void __user *)arg); return ret; @@ -1092,23 +1524,77 @@ static const struct block_device_operations sd_fops = { .owner = THIS_MODULE, .open = sd_open, .release = sd_release, - .locked_ioctl = sd_ioctl, + .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_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 (!blk_fs_request(scmd->request)) + if (scmd->request->cmd_type != REQ_TYPE_FS) return 0; info_valid = scsi_get_sense_info_fld(scmd->sense_buffer, @@ -1126,7 +1612,7 @@ static unsigned int sd_completed_bytes(struct scsi_cmnd *scmd) end_lba <<= 1; } else { /* be careful ... don't want any overflows */ - u64 factor = scmd->device->sector_size / 512; + unsigned int factor = scmd->device->sector_size / 512; do_div(start_lba, factor); do_div(end_lba, factor); } @@ -1140,7 +1626,8 @@ static unsigned int sd_completed_bytes(struct scsi_cmnd *scmd) /* This computation should always be done in terms of * the resolution of the device's medium. */ - return (bad_lba - start_lba) * scmd->device->sector_size; + good_bytes = (bad_lba - start_lba) * scmd->device->sector_size; + return min(good_bytes, transferred); } /** @@ -1156,8 +1643,21 @@ static int sd_done(struct scsi_cmnd *SCpnt) 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; + 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); @@ -1175,6 +1675,8 @@ static int sd_done(struct scsi_cmnd *SCpnt) sshdr.ascq)); } #endif + sdkp->medium_access_timed_out = 0; + if (driver_byte(result) != DRIVER_SENSE && (!sense_valid || sense_deferred)) goto out; @@ -1197,17 +1699,31 @@ static int sd_done(struct scsi_cmnd *SCpnt) memset(SCpnt->sense_buffer, 0, SCSI_SENSE_BUFFERSIZE); break; case ABORTED_COMMAND: - if (sshdr.asc == 0x10) { /* DIF: Disk detected corruption */ - scsi_print_result(SCpnt); - scsi_print_sense("sd", SCpnt); + if (sshdr.asc == 0x10) /* DIF: Target detected corruption */ good_bytes = sd_completed_bytes(SCpnt); - } break; case ILLEGAL_REQUEST: - if (sshdr.asc == 0x10) { /* DIX: HBA detected corruption */ - scsi_print_result(SCpnt); - scsi_print_sense("sd", SCpnt); + 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; + } + } } break; default: @@ -1217,30 +1733,9 @@ static int sd_done(struct scsi_cmnd *SCpnt) if (rq_data_dir(SCpnt->request) == READ && scsi_prot_sg_count(SCpnt)) sd_dif_complete(SCpnt, good_bytes); - if (scsi_host_dif_capable(sdkp->device->host, sdkp->protection_type) - == SD_DIF_TYPE2_PROTECTION && SCpnt->cmnd != SCpnt->request->cmd) - mempool_free(SCpnt->cmnd, sd_cdb_pool); - return good_bytes; } -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; - - set_media_not_present(sdkp); - return 1; -} - /* * spinup disk - called only in sd_revalidate_disk() */ @@ -1369,34 +1864,42 @@ sd_spinup_disk(struct scsi_disk *sdkp) /* * Determine whether disk supports Data Integrity Field. */ -void sd_read_protection_type(struct scsi_disk *sdkp, 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; + return ret; type = ((buffer[12] >> 1) & 7) + 1; /* P_TYPE 0 = Type 1 */ - if (type == sdkp->protection_type || !sdkp->first_scan) - return; + 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; - if (type > SD_DIF_TYPE3_PROTECTION) { - sd_printk(KERN_ERR, sdkp, "formatted with unsupported " \ - "protection type %u. Disabling disk!\n", type); - sdkp->capacity = 0; - return; - } - - if (scsi_host_dif_capable(sdp->host, type)) - sd_printk(KERN_NOTICE, sdkp, - "Enabling DIF Type %u protection\n", type); - else - sd_printk(KERN_NOTICE, sdkp, - "Disabling DIF Type %u protection\n", type); + return ret; } static void read_capacity_error(struct scsi_disk *sdkp, struct scsi_device *sdp, @@ -1415,7 +1918,7 @@ static void read_capacity_error(struct scsi_disk *sdkp, struct scsi_device *sdp, */ if (sdp->removable && sense_valid && sshdr->sense_key == NOT_READY) - sdp->changed = 1; + set_media_not_present(sdkp); /* * We used to set media_present to 0 here to indicate no media @@ -1430,6 +1933,8 @@ static void read_capacity_error(struct scsi_disk *sdkp, struct scsi_device *sdp, #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) { @@ -1437,11 +1942,14 @@ static int read_capacity_16(struct scsi_disk *sdkp, struct scsi_device *sdp, struct scsi_sense_hdr sshdr; int sense_valid = 0; int the_result; - int retries = 3; + 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; + do { memset(cmd, 0, 16); cmd[0] = SERVICE_ACTION_IN; @@ -1466,6 +1974,13 @@ static int read_capacity_16(struct scsi_disk *sdkp, struct scsi_device *sdp, * 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--; @@ -1480,7 +1995,10 @@ static int read_capacity_16(struct scsi_disk *sdkp, struct scsi_device *sdp, sector_size = get_unaligned_be32(&buffer[8]); lba = get_unaligned_be64(&buffer[0]); - sd_read_protection_type(sdkp, buffer); + 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 " @@ -1491,7 +2009,7 @@ static int read_capacity_16(struct scsi_disk *sdkp, struct scsi_device *sdp, } /* Logical blocks per physical block exponent */ - sdkp->hw_sector_size = (1 << (buffer[13] & 0xf)) * sector_size; + sdkp->physical_block_size = (1 << (buffer[13] & 0xf)) * sector_size; /* Lowest aligned logical block */ alignment = ((buffer[14] & 0x3f) << 8 | buffer[15]) * sector_size; @@ -1500,17 +2018,13 @@ static int read_capacity_16(struct scsi_disk *sdkp, struct scsi_device *sdp, sd_printk(KERN_NOTICE, sdkp, "physical block alignment offset: %u\n", alignment); - if (buffer[14] & 0x80) { /* TPE */ - struct request_queue *q = sdp->request_queue; - - sdkp->thin_provisioning = 1; - q->limits.discard_granularity = sdkp->hw_sector_size; - q->limits.max_discard_sectors = 0xffffffff; + if (buffer[14] & 0x80) { /* LBPME */ + sdkp->lbpme = 1; - if (buffer[14] & 0x40) /* TPRZ */ - q->limits.discard_zeroes_data = 1; + if (buffer[14] & 0x40) /* LBPRZ */ + sdkp->lbprz = 1; - queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, q); + sd_config_discard(sdkp, SD_LBP_WS16); } sdkp->capacity = lba + 1; @@ -1524,7 +2038,7 @@ static int read_capacity_10(struct scsi_disk *sdkp, struct scsi_device *sdp, struct scsi_sense_hdr sshdr; int sense_valid = 0; int the_result; - int retries = 3; + int retries = 3, reset_retries = READ_CAPACITY_RETRIES_ON_RESET; sector_t lba; unsigned sector_size; @@ -1540,8 +2054,16 @@ static int read_capacity_10(struct scsi_disk *sdkp, struct scsi_device *sdp, if (media_not_present(sdkp, &sshdr)) 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); @@ -1555,6 +2077,15 @@ static int read_capacity_10(struct scsi_disk *sdkp, struct scsi_device *sdp, sector_size = get_unaligned_be32(&buffer[4]); lba = get_unaligned_be32(&buffer[0]); + 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; + } + 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 " @@ -1564,12 +2095,16 @@ static int read_capacity_10(struct scsi_disk *sdkp, struct scsi_device *sdp, } sdkp->capacity = lba + 1; - sdkp->hw_sector_size = sector_size; + 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)) @@ -1683,13 +2218,15 @@ got_data: (unsigned long long)sdkp->capacity, sector_size, cap_str_10, cap_str_2); - if (sdkp->hw_sector_size != sector_size) + if (sdkp->physical_block_size != sector_size) sd_printk(KERN_NOTICE, sdkp, "%u-byte physical blocks\n", - sdkp->hw_sector_size); + 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; @@ -1700,7 +2237,8 @@ got_data: else if (sector_size == 256) sdkp->capacity >>= 1; - blk_queue_physical_block_size(sdp->request_queue, sdkp->hw_sector_size); + blk_queue_physical_block_size(sdp->request_queue, + sdkp->physical_block_size); sdkp->device->sector_size = sector_size; } @@ -1729,7 +2267,7 @@ sd_read_write_protect_flag(struct scsi_disk *sdkp, unsigned char *buffer) set_disk_ro(sdkp->disk, 0); if (sdp->skip_ms_page_3f) { - sd_printk(KERN_NOTICE, sdkp, "Assuming Write Enabled\n"); + sd_first_printk(KERN_NOTICE, sdkp, "Assuming Write Enabled\n"); return; } @@ -1761,7 +2299,7 @@ sd_read_write_protect_flag(struct scsi_disk *sdkp, unsigned char *buffer) } if (!scsi_status_is_good(res)) { - sd_printk(KERN_WARNING, sdkp, + sd_first_printk(KERN_WARNING, sdkp, "Test WP failed, assume Write Enabled\n"); } else { sdkp->write_prot = ((data.device_specific & 0x80) != 0); @@ -1788,16 +2326,30 @@ sd_read_cache_type(struct scsi_disk *sdkp, unsigned char *buffer) 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 { @@ -1806,14 +2358,17 @@ sd_read_cache_type(struct scsi_disk *sdkp, unsigned char *buffer) } /* 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; - sd_printk(KERN_ERR, sdkp, "Missing header in MODE_SENSE response\n"); + 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 */ @@ -1825,30 +2380,58 @@ sd_read_cache_type(struct scsi_disk *sdkp, unsigned char *buffer) */ 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; - if (len > SD_BUF_SIZE) - goto bad_sense; + 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)) { int offset = data.header_length + data.block_descriptor_length; - if (offset >= SD_BUF_SIZE - 2) { - sd_printk(KERN_ERR, sdkp, "Malformed MODE SENSE response\n"); - 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; + } + } } - if ((buffer[offset] & 0x3f) != modepage) { - sd_printk(KERN_ERR, sdkp, "Got wrong page\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); @@ -1858,8 +2441,11 @@ sd_read_cache_type(struct scsi_disk *sdkp, unsigned char *buffer) } sdkp->DPOFUA = (data.device_specific & 0x10) != 0; - if (sdkp->DPOFUA && !sdkp->device->use_10_for_rw) { - sd_printk(KERN_NOTICE, sdkp, + 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; } @@ -1881,13 +2467,21 @@ bad_sense: sshdr.sense_key == ILLEGAL_REQUEST && sshdr.asc == 0x24 && sshdr.ascq == 0x0) /* Invalid field in CDB */ - sd_printk(KERN_NOTICE, sdkp, "Cache data unavailable\n"); + sd_first_printk(KERN_NOTICE, sdkp, "Cache data unavailable\n"); else - sd_printk(KERN_ERR, sdkp, "Asking for cache data failed\n"); + sd_first_printk(KERN_ERR, sdkp, + "Asking for cache data failed\n"); defaults: - sd_printk(KERN_ERR, sdkp, "Assuming drive cache: write through\n"); - 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; } @@ -1896,7 +2490,7 @@ defaults: * The ATO bit indicates whether the DIF application tag is available * for use by the operating system. */ -void sd_read_app_tag_own(struct scsi_disk *sdkp, unsigned char *buffer) +static void sd_read_app_tag_own(struct scsi_disk *sdkp, unsigned char *buffer) { int res, offset; struct scsi_device *sdp = sdkp->device; @@ -1914,7 +2508,7 @@ void sd_read_app_tag_own(struct scsi_disk *sdkp, unsigned char *buffer) if (!scsi_status_is_good(res) || !data.header_length || data.length < 6) { - sd_printk(KERN_WARNING, sdkp, + sd_first_printk(KERN_WARNING, sdkp, "getting Control mode page failed, assume no ATO\n"); if (scsi_sense_valid(&sshdr)) @@ -1926,7 +2520,7 @@ void sd_read_app_tag_own(struct scsi_disk *sdkp, unsigned char *buffer) offset = data.header_length + data.block_descriptor_length; if ((buffer[offset] & 0x3f) != 0x0a) { - sd_printk(KERN_ERR, sdkp, "ATO Got wrong page\n"); + sd_first_printk(KERN_ERR, sdkp, "ATO Got wrong page\n"); return; } @@ -1944,46 +2538,61 @@ void sd_read_app_tag_own(struct scsi_disk *sdkp, unsigned char *buffer) */ static void sd_read_block_limits(struct scsi_disk *sdkp) { - struct request_queue *q = sdkp->disk->queue; unsigned int sector_sz = sdkp->device->sector_size; - char *buffer; - - /* Block Limits VPD */ - buffer = scsi_get_vpd_page(sdkp->device, 0xb0); + const int vpd_len = 64; + unsigned char *buffer = kmalloc(vpd_len, GFP_KERNEL); - if (buffer == NULL) - return; + if (!buffer || + /* Block Limits VPD */ + scsi_get_vpd_page(sdkp->device, 0xb0, buffer, vpd_len)) + goto out; blk_queue_io_min(sdkp->disk->queue, get_unaligned_be16(&buffer[6]) * sector_sz); blk_queue_io_opt(sdkp->disk->queue, get_unaligned_be32(&buffer[12]) * sector_sz); - /* Thin provisioning enabled and page length indicates TP support */ - if (sdkp->thin_provisioning && buffer[3] == 0x3c) { - unsigned int lba_count, desc_count, granularity; + if (buffer[3] == 0x3c) { + unsigned int lba_count, desc_count; - lba_count = get_unaligned_be32(&buffer[20]); - desc_count = get_unaligned_be32(&buffer[24]); + sdkp->max_ws_blocks = (u32)get_unaligned_be64(&buffer[36]); - if (lba_count) { - q->limits.max_discard_sectors = - lba_count * sector_sz >> 9; + if (!sdkp->lbpme) + goto out; - if (desc_count) - sdkp->unmap = 1; - } + lba_count = get_unaligned_be32(&buffer[20]); + desc_count = get_unaligned_be32(&buffer[24]); - granularity = get_unaligned_be32(&buffer[28]); + if (lba_count && desc_count) + sdkp->max_unmap_blocks = lba_count; - if (granularity) - q->limits.discard_granularity = granularity * sector_sz; + sdkp->unmap_granularity = get_unaligned_be32(&buffer[28]); if (buffer[32] & 0x80) - q->limits.discard_alignment = + 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); } @@ -1993,23 +2602,83 @@ static void sd_read_block_limits(struct scsi_disk *sdkp) */ static void sd_read_block_characteristics(struct scsi_disk *sdkp) { - char *buffer; + unsigned char *buffer; u16 rot; + const int vpd_len = 64; - /* Block Device Characteristics VPD */ - buffer = scsi_get_vpd_page(sdkp->device, 0xb1); + buffer = kmalloc(vpd_len, GFP_KERNEL); - if (buffer == NULL) - return; + 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) { /* @@ -2017,7 +2686,7 @@ static int sd_try_extended_inquiry(struct scsi_device *sdp) * 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) + if (sdp->scsi_level > SCSI_SPC_2 && !sdp->skip_vpd_pages) return 1; return 0; } @@ -2032,7 +2701,7 @@ 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 ordered; + unsigned flush = 0; SCSI_LOG_HLQUEUE(3, sd_printk(KERN_INFO, sdkp, "sd_revalidate_disk\n")); @@ -2061,6 +2730,7 @@ static int sd_revalidate_disk(struct gendisk *disk) 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); } @@ -2068,25 +2738,25 @@ static int sd_revalidate_disk(struct gendisk *disk) 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 ordered requests. Note that as the current SCSI - * dispatch function can alter request order, we cannot use - * QUEUE_ORDERED_TAG_* even when ordered tag is supported. + * with flush requests. */ - if (sdkp->WCE) - ordered = sdkp->DPOFUA - ? QUEUE_ORDERED_DRAIN_FUA : QUEUE_ORDERED_DRAIN_FLUSH; - else - ordered = QUEUE_ORDERED_DRAIN; + if (sdkp->WCE) { + flush |= REQ_FLUSH; + if (sdkp->DPOFUA) + flush |= REQ_FUA; + } - blk_queue_ordered(sdkp->disk->queue, ordered, sd_prepare_flush); + blk_queue_flush(sdkp->disk->queue, flush); set_capacity(disk, sdkp->capacity); + sd_config_write_same(sdkp); kfree(buffer); out: @@ -2094,6 +2764,26 @@ 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 @@ -2105,7 +2795,7 @@ static int sd_revalidate_disk(struct gendisk *disk) * which is followed by sdaaa. * * This is basically 26 base counting with one extra 'nil' entry - * at the beggining from the second digit on and can be + * 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. * @@ -2155,11 +2845,10 @@ static void sd_probe_async(void *data, async_cookie_t cookie) index = sdkp->index; dev = &sdp->sdev_gendev; - if (index < SD_MAX_DISKS) { - gd->major = sd_major((index & 0xf0) >> 4); - gd->first_minor = ((index & 0xf) << 4) | (index & 0xfff00); - gd->minors = SD_MINORS; - } + gd->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; @@ -2169,28 +2858,32 @@ static void sd_probe_async(void *data, async_cookie_t cookie) 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); - blk_queue_prep_rq(sdp->request_queue, sd_prep_fn); - gd->driverfs_dev = &sdp->sdev_gendev; - gd->flags = GENHD_FL_EXT_DEVT | GENHD_FL_DRIVERFS; - if (sdp->removable) + gd->flags = GENHD_FL_EXT_DEVT; + if (sdp->removable) { gd->flags |= GENHD_FL_REMOVABLE; + gd->events |= DISK_EVENT_MEDIA_CHANGE; + } - dev_set_drvdata(dev, sdkp); + blk_pm_runtime_init(sdp->request_queue, dev); add_disk(gd); - sd_dif_config_host(sdkp); + 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); } @@ -2209,15 +2902,15 @@ static void sd_probe_async(void *data, async_cookie_t cookie) * (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; @@ -2225,7 +2918,7 @@ 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 = kzalloc(sizeof(*sdkp), GFP_KERNEL); @@ -2245,19 +2938,23 @@ static int sd_probe(struct device *dev) spin_unlock(&sd_index_lock); } while (error == -EAGAIN); - 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) + if (error) { + sdev_printk(KERN_WARNING, sdp, "SCSI disk (sd) name length exceeded.\n"); goto out_free_index; + } sdkp->device = sdp; sdkp->driver = &sd_template; sdkp->disk = gd; sdkp->index = index; - sdkp->openers = 0; - sdkp->previous_state = 1; + atomic_set(&sdkp->openers, 0); + atomic_set(&sdkp->device->ioerr_cnt, 0); if (!sdp->request_queue->rq_timeout) { if (sdp->type != TYPE_MOD) @@ -2268,17 +2965,18 @@ static int sd_probe(struct device *dev) } device_initialize(&sdkp->dev); - sdkp->dev.parent = &sdp->sdev_gendev; + sdkp->dev.parent = dev; sdkp->dev.class = &sd_disk_class; - dev_set_name(&sdkp->dev, dev_name(&sdp->sdev_gendev)); + dev_set_name(&sdkp->dev, "%s", dev_name(dev)); if (device_add(&sdkp->dev)) goto out_free_index; - get_device(&sdp->sdev_gendev); + get_device(dev); + dev_set_drvdata(dev, sdkp); get_device(&sdkp->dev); /* prevent release before async_schedule */ - async_schedule(sd_probe_async, sdkp); + async_schedule_domain(sd_probe_async, sdkp, &scsi_sd_probe_domain); return 0; @@ -2308,14 +3006,21 @@ static int sd_probe(struct device *dev) static int sd_remove(struct device *dev) { struct scsi_disk *sdkp; + dev_t devt; - async_synchronize_full(); sdkp = dev_get_drvdata(dev); - blk_queue_prep_rq(sdkp->device->request_queue, scsi_prep_fn); + 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); + blk_register_region(devt, SD_MINORS, NULL, + sd_default_probe, NULL, NULL); + mutex_lock(&sd_ref_mutex); dev_set_drvdata(dev, NULL); put_device(&sdkp->dev); @@ -2365,16 +3070,24 @@ static int sd_start_stop_device(struct scsi_disk *sdkp, int start) if (!scsi_device_online(sdp)) return -ENODEV; - res = scsi_execute_req(sdp, cmd, DMA_NONE, NULL, 0, &sshdr, - SD_TIMEOUT, SD_MAX_RETRIES, NULL); + 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; } - return res; + /* SCSI error codes must not go to the generic layer */ + if (res) + return -EIO; + + return 0; } /* @@ -2389,7 +3102,10 @@ static void sd_shutdown(struct device *dev) if (!sdkp) return; /* this can happen */ - if (sdkp->WCE) { + 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); } @@ -2399,10 +3115,11 @@ static void sd_shutdown(struct device *dev) sd_start_stop_device(sdkp, 0); } +exit: scsi_disk_put(sdkp); } -static int sd_suspend(struct device *dev, pm_message_t mesg) +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; @@ -2410,16 +3127,23 @@ static int sd_suspend(struct device *dev, pm_message_t mesg) if (!sdkp) return 0; /* this can happen */ - if (sdkp->WCE) { + if (sdkp->WCE && sdkp->media_present) { sd_printk(KERN_NOTICE, sdkp, "Synchronizing SCSI cache\n"); ret = sd_sync_cache(sdkp); - if (ret) + if (ret) { + /* ignore OFFLINE device */ + if (ret == -ENODEV) + ret = 0; goto done; + } } - if ((mesg.event & PM_EVENT_SLEEP) && sdkp->device->manage_start_stop) { + 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: @@ -2427,6 +3151,16 @@ done: 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); @@ -2455,9 +3189,13 @@ static int __init init_sd(void) 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; @@ -2466,10 +3204,6 @@ static int __init init_sd(void) if (err) goto err_out; - err = scsi_register_driver(&sd_template.gendrv); - if (err) - goto err_out_class; - sd_cdb_cache = kmem_cache_create("sd_ext_cdb", SD_EXT_CDB_SIZE, 0, 0, NULL); if (!sd_cdb_cache) { @@ -2483,8 +3217,15 @@ static int __init init_sd(void) 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); @@ -2507,14 +3248,16 @@ static void __exit exit_sd(void) SCSI_LOG_HLQUEUE(3, printk("exit_sd: exiting sd driver\n")); + scsi_unregister_driver(&sd_template.gendrv); mempool_destroy(sd_cdb_pool); kmem_cache_destroy(sd_cdb_cache); - scsi_unregister_driver(&sd_template.gendrv); class_unregister(&sd_disk_class); - for (i = 0; i < SD_MAJORS; i++) + for (i = 0; i < SD_MAJORS; i++) { + blk_unregister_region(sd_major(i), SD_MINORS); unregister_blkdev(sd_major(i), "sd"); + } } module_init(init_sd); @@ -2523,15 +3266,15 @@ module_exit(exit_sd); static void sd_print_sense_hdr(struct scsi_disk *sdkp, struct scsi_sense_hdr *sshdr) { - sd_printk(KERN_INFO, sdkp, ""); + sd_printk(KERN_INFO, sdkp, " "); scsi_show_sense_hdr(sshdr); - sd_printk(KERN_INFO, sdkp, ""); + 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, ""); + sd_printk(KERN_INFO, sdkp, " "); scsi_show_result(result); } |