diff options
Diffstat (limited to 'drivers/scsi/sd.c')
| -rw-r--r-- | drivers/scsi/sd.c | 3168 |
1 files changed, 1976 insertions, 1192 deletions
diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c index bea36adeee17..f50b92e63201 100644 --- a/drivers/scsi/sd.c +++ b/drivers/scsi/sd.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * sd.c Copyright (C) 1992 Drew Eckhardt * Copyright (C) 1993, 1994, 1995, 1999 Eric Youngdale @@ -32,12 +33,11 @@ * than the level indicated above to trigger output. */ +#include <linux/bio-integrity.h> #include <linux/module.h> #include <linux/fs.h> #include <linux/kernel.h> #include <linux/mm.h> -#include <linux/bio.h> -#include <linux/genhd.h> #include <linux/hdreg.h> #include <linux/errno.h> #include <linux/idr.h> @@ -45,27 +45,31 @@ #include <linux/init.h> #include <linux/blkdev.h> #include <linux/blkpg.h> +#include <linux/blk-pm.h> #include <linux/delay.h> +#include <linux/rw_hint.h> +#include <linux/major.h> #include <linux/mutex.h> #include <linux/string_helpers.h> -#include <linux/async.h> #include <linux/slab.h> #include <linux/sed-opal.h> #include <linux/pm_runtime.h> #include <linux/pr.h> #include <linux/t10-pi.h> #include <linux/uaccess.h> -#include <asm/unaligned.h> +#include <linux/unaligned.h> #include <scsi/scsi.h> #include <scsi/scsi_cmnd.h> #include <scsi/scsi_dbg.h> #include <scsi/scsi_device.h> +#include <scsi/scsi_devinfo.h> #include <scsi/scsi_driver.h> #include <scsi/scsi_eh.h> #include <scsi/scsi_host.h> #include <scsi/scsi_ioctl.h> #include <scsi/scsicam.h> +#include <scsi/scsi_common.h> #include "sd.h" #include "scsi_priv.h" @@ -96,60 +100,39 @@ MODULE_ALIAS_SCSI_DEVICE(TYPE_MOD); MODULE_ALIAS_SCSI_DEVICE(TYPE_RBC); MODULE_ALIAS_SCSI_DEVICE(TYPE_ZBC); -#if !defined(CONFIG_DEBUG_BLOCK_EXT_DEVT) #define SD_MINORS 16 -#else -#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_config_discard(struct scsi_disk *sdkp, struct queue_limits *lim, + unsigned int mode); +static void sd_config_write_same(struct scsi_disk *sdkp, + struct queue_limits *lim); +static void 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 void sd_eh_reset(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(const struct scsi_disk *, const char *, int); -static DEFINE_SPINLOCK(sd_index_lock); static DEFINE_IDA(sd_index_ida); -/* This semaphore is used to mediate the 0->1 reference get in the - * face of object destruction (i.e. we can't allow a get on an - * object after last put) */ -static DEFINE_MUTEX(sd_ref_mutex); - -static struct kmem_cache *sd_cdb_cache; -static mempool_t *sd_cdb_pool; +static mempool_t *sd_page_pool; +static struct lock_class_key sd_bio_compl_lkclass; static const char *sd_cache_types[] = { "write through", "none", "write back", "write back, no read (daft)" }; -static void sd_set_flush_flag(struct scsi_disk *sdkp) +static void sd_set_flush_flag(struct scsi_disk *sdkp, + struct queue_limits *lim) { - bool wc = false, fua = false; - if (sdkp->WCE) { - wc = true; + lim->features |= BLK_FEAT_WRITE_CACHE; if (sdkp->DPOFUA) - fua = true; + lim->features |= BLK_FEAT_FUA; + else + lim->features &= ~BLK_FEAT_FUA; + } else { + lim->features &= ~(BLK_FEAT_WRITE_CACHE | BLK_FEAT_FUA); } - - blk_queue_write_cache(sdkp->disk->queue, wc, fua); } static ssize_t @@ -164,7 +147,7 @@ cache_type_store(struct device *dev, struct device_attribute *attr, struct scsi_mode_data data; struct scsi_sense_hdr sshdr; static const char temp[] = "temporary "; - int len; + int len, ret; if (sdp->type != TYPE_DISK && sdp->type != TYPE_ZBC) /* no cache control on RBC devices; theoretically they @@ -187,14 +170,22 @@ cache_type_store(struct device *dev, struct device_attribute *attr, wce = (ct & 0x02) && !sdkp->write_prot ? 1 : 0; if (sdkp->cache_override) { + struct queue_limits lim; + sdkp->WCE = wce; sdkp->RCD = rcd; - sd_set_flush_flag(sdkp); + + lim = queue_limits_start_update(sdkp->disk->queue); + sd_set_flush_flag(sdkp, &lim); + ret = queue_limits_commit_update_frozen(sdkp->disk->queue, + &lim); + if (ret) + return ret; return count; } - if (scsi_mode_sense(sdp, 0x08, 8, buffer, sizeof(buffer), SD_TIMEOUT, - SD_MAX_RETRIES, &data, NULL)) + if (scsi_mode_sense(sdp, 0x08, 8, 0, buffer, sizeof(buffer), SD_TIMEOUT, + sdkp->max_retries, &data, NULL)) return -EINVAL; len = min_t(size_t, sizeof(buffer), data.length - data.header_length - data.block_descriptor_length); @@ -205,41 +196,156 @@ cache_type_store(struct device *dev, struct device_attribute *attr, sp = buffer_data[0] & 0x80 ? 1 : 0; buffer_data[0] &= ~0x80; - if (scsi_mode_select(sdp, 1, sp, 8, buffer_data, len, SD_TIMEOUT, - SD_MAX_RETRIES, &data, &sshdr)) { - if (scsi_sense_valid(&sshdr)) + /* + * Ensure WP, DPOFUA, and RESERVED fields are cleared in + * received mode parameter buffer before doing MODE SELECT. + */ + data.device_specific = 0; + + ret = scsi_mode_select(sdp, 1, sp, buffer_data, len, SD_TIMEOUT, + sdkp->max_retries, &data, &sshdr); + if (ret) { + if (ret > 0 && scsi_sense_valid(&sshdr)) sd_print_sense_hdr(sdkp, &sshdr); return -EINVAL; } - revalidate_disk(sdkp->disk); + sd_revalidate_disk(sdkp->disk); return count; } static ssize_t -manage_start_stop_show(struct device *dev, struct device_attribute *attr, - char *buf) +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 sprintf(buf, "%u\n", sdp->manage_start_stop); + return sysfs_emit(buf, "%u\n", + sdp->manage_system_start_stop && + sdp->manage_runtime_start_stop && + sdp->manage_shutdown); } +static DEVICE_ATTR_RO(manage_start_stop); static ssize_t -manage_start_stop_store(struct device *dev, struct device_attribute *attr, - const char *buf, size_t count) +manage_system_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 sysfs_emit(buf, "%u\n", sdp->manage_system_start_stop); +} + +static ssize_t +manage_system_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; + bool v; if (!capable(CAP_SYS_ADMIN)) return -EACCES; - sdp->manage_start_stop = simple_strtoul(buf, NULL, 10); + if (kstrtobool(buf, &v)) + return -EINVAL; + + sdp->manage_system_start_stop = v; return count; } -static DEVICE_ATTR_RW(manage_start_stop); +static DEVICE_ATTR_RW(manage_system_start_stop); + +static ssize_t +manage_runtime_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 sysfs_emit(buf, "%u\n", sdp->manage_runtime_start_stop); +} + +static ssize_t +manage_runtime_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; + bool v; + + if (!capable(CAP_SYS_ADMIN)) + return -EACCES; + + if (kstrtobool(buf, &v)) + return -EINVAL; + + sdp->manage_runtime_start_stop = v; + + return count; +} +static DEVICE_ATTR_RW(manage_runtime_start_stop); + +static ssize_t manage_shutdown_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 sysfs_emit(buf, "%u\n", sdp->manage_shutdown); +} + +static ssize_t manage_shutdown_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; + bool v; + + if (!capable(CAP_SYS_ADMIN)) + return -EACCES; + + if (kstrtobool(buf, &v)) + return -EINVAL; + + sdp->manage_shutdown = v; + + return count; +} +static DEVICE_ATTR_RW(manage_shutdown); + +static ssize_t manage_restart_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 sysfs_emit(buf, "%u\n", sdp->manage_restart); +} + +static ssize_t manage_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; + bool v; + + if (!capable(CAP_SYS_ADMIN)) + return -EACCES; + + if (kstrtobool(buf, &v)) + return -EINVAL; + + sdp->manage_restart = v; + + return count; +} +static DEVICE_ATTR_RW(manage_restart); static ssize_t allow_restart_show(struct device *dev, struct device_attribute *attr, char *buf) @@ -253,6 +359,7 @@ static ssize_t allow_restart_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { + bool v; struct scsi_disk *sdkp = to_scsi_disk(dev); struct scsi_device *sdp = sdkp->device; @@ -262,7 +369,10 @@ allow_restart_store(struct device *dev, struct device_attribute *attr, if (sdp->type != TYPE_DISK && sdp->type != TYPE_ZBC) return -EINVAL; - sdp->allow_restart = simple_strtoul(buf, NULL, 10); + if (kstrtobool(buf, &v)) + return -EINVAL; + + sdp->allow_restart = v; return count; } @@ -312,7 +422,7 @@ protection_type_store(struct device *dev, struct device_attribute *attr, if (err) return err; - if (val >= 0 && val <= T10_PI_TYPE3_PROTECTION) + if (val <= T10_PI_TYPE3_PROTECTION) sdkp->protection_type = val; return count; @@ -386,16 +496,12 @@ provisioning_mode_store(struct device *dev, struct device_attribute *attr, { struct scsi_disk *sdkp = to_scsi_disk(dev); struct scsi_device *sdp = sdkp->device; - int mode; + struct queue_limits lim; + int mode, err; if (!capable(CAP_SYS_ADMIN)) return -EACCES; - if (sd_is_zoned(sdkp)) { - sd_config_discard(sdkp, SD_LBP_DISABLE); - return count; - } - if (sdp->type != TYPE_DISK) return -EINVAL; @@ -403,8 +509,11 @@ provisioning_mode_store(struct device *dev, struct device_attribute *attr, if (mode < 0) return -EINVAL; - sd_config_discard(sdkp, mode); - + lim = queue_limits_start_update(sdkp->disk->queue); + sd_config_discard(sdkp, &lim, mode); + err = queue_limits_commit_update_frozen(sdkp->disk->queue, &lim); + if (err) + return err; return count; } static DEVICE_ATTR_RW(provisioning_mode); @@ -487,6 +596,7 @@ max_write_same_blocks_store(struct device *dev, struct device_attribute *attr, { struct scsi_disk *sdkp = to_scsi_disk(dev); struct scsi_device *sdp = sdkp->device; + struct queue_limits lim; unsigned long max; int err; @@ -508,17 +618,72 @@ max_write_same_blocks_store(struct device *dev, struct device_attribute *attr, sdkp->max_ws_blocks = max; } - sd_config_write_same(sdkp); - + lim = queue_limits_start_update(sdkp->disk->queue); + sd_config_write_same(sdkp, &lim); + err = queue_limits_commit_update_frozen(sdkp->disk->queue, &lim); + if (err) + return err; return count; } static DEVICE_ATTR_RW(max_write_same_blocks); +static ssize_t +zoned_cap_show(struct device *dev, struct device_attribute *attr, char *buf) +{ + struct scsi_disk *sdkp = to_scsi_disk(dev); + + if (sdkp->device->type == TYPE_ZBC) + return sprintf(buf, "host-managed\n"); + if (sdkp->zoned == 1) + return sprintf(buf, "host-aware\n"); + if (sdkp->zoned == 2) + return sprintf(buf, "drive-managed\n"); + return sprintf(buf, "none\n"); +} +static DEVICE_ATTR_RO(zoned_cap); + +static ssize_t +max_retries_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 *sdev = sdkp->device; + int retries, err; + + err = kstrtoint(buf, 10, &retries); + if (err) + return err; + + if (retries == SCSI_CMD_RETRIES_NO_LIMIT || retries <= SD_MAX_RETRIES) { + sdkp->max_retries = retries; + return count; + } + + sdev_printk(KERN_ERR, sdev, "max_retries must be between -1 and %d\n", + SD_MAX_RETRIES); + return -EINVAL; +} + +static ssize_t +max_retries_show(struct device *dev, struct device_attribute *attr, + char *buf) +{ + struct scsi_disk *sdkp = to_scsi_disk(dev); + + return sprintf(buf, "%d\n", sdkp->max_retries); +} + +static DEVICE_ATTR_RW(max_retries); + 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_manage_system_start_stop.attr, + &dev_attr_manage_runtime_start_stop.attr, + &dev_attr_manage_shutdown.attr, + &dev_attr_manage_restart.attr, &dev_attr_protection_type.attr, &dev_attr_protection_mode.attr, &dev_attr_app_tag_own.attr, @@ -527,51 +692,24 @@ static struct attribute *sd_disk_attrs[] = { &dev_attr_zeroing_mode.attr, &dev_attr_max_write_same_blocks.attr, &dev_attr_max_medium_access_timeouts.attr, + &dev_attr_zoned_cap.attr, + &dev_attr_max_retries.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 = { - .gendrv = { - .name = "sd", - .owner = THIS_MODULE, - .probe = sd_probe, - .remove = sd_remove, - .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, - .eh_reset = sd_eh_reset, -}; - /* - * Dummy kobj_map->probe function. - * The default ->probe function will call modprobe, which is - * pointless as this module is already loaded. + * Don't request a new module, as that could deadlock in multipath + * environment. */ -static struct kobject *sd_default_probe(dev_t devt, int *partno, void *data) +static void sd_default_probe(dev_t devt) { - return NULL; } /* @@ -603,39 +741,16 @@ static int sd_major(int major_idx) } } -static struct scsi_disk *scsi_disk_get(struct gendisk *disk) -{ - struct scsi_disk *sdkp = NULL; - - mutex_lock(&sd_ref_mutex); - - if (disk->private_data) { - sdkp = scsi_disk(disk); - if (scsi_device_get(sdkp->device) == 0) - get_device(&sdkp->dev); - else - sdkp = NULL; - } - mutex_unlock(&sd_ref_mutex); - return sdkp; -} - -static void scsi_disk_put(struct scsi_disk *sdkp) -{ - struct scsi_device *sdev = sdkp->device; - - mutex_lock(&sd_ref_mutex); - put_device(&sdkp->dev); - scsi_device_put(sdev); - mutex_unlock(&sd_ref_mutex); -} - #ifdef CONFIG_BLK_SED_OPAL static int sd_sec_submit(void *data, u16 spsp, u8 secp, void *buffer, size_t len, bool send) { - struct scsi_device *sdev = data; + struct scsi_disk *sdkp = data; + struct scsi_device *sdev = sdkp->device; u8 cdb[12] = { 0, }; + const struct scsi_exec_args exec_args = { + .req_flags = BLK_MQ_REQ_PM, + }; int ret; cdb[0] = send ? SECURITY_PROTOCOL_OUT : SECURITY_PROTOCOL_IN; @@ -643,32 +758,95 @@ static int sd_sec_submit(void *data, u16 spsp, u8 secp, void *buffer, put_unaligned_be16(spsp, &cdb[2]); put_unaligned_be32(len, &cdb[6]); - ret = scsi_execute_req(sdev, cdb, - send ? DMA_TO_DEVICE : DMA_FROM_DEVICE, - buffer, len, NULL, SD_TIMEOUT, SD_MAX_RETRIES, NULL); + ret = scsi_execute_cmd(sdev, cdb, send ? REQ_OP_DRV_OUT : REQ_OP_DRV_IN, + buffer, len, SD_TIMEOUT, sdkp->max_retries, + &exec_args); return ret <= 0 ? ret : -EIO; } #endif /* CONFIG_BLK_SED_OPAL */ +/* + * Look up the DIX operation based on whether the command is read or + * write and whether dix and dif are enabled. + */ +static unsigned int sd_prot_op(bool write, bool dix, bool dif) +{ + /* Lookup table: bit 2 (write), bit 1 (dix), bit 0 (dif) */ + static const unsigned int ops[] = { /* wrt dix dif */ + SCSI_PROT_NORMAL, /* 0 0 0 */ + SCSI_PROT_READ_STRIP, /* 0 0 1 */ + SCSI_PROT_READ_INSERT, /* 0 1 0 */ + SCSI_PROT_READ_PASS, /* 0 1 1 */ + SCSI_PROT_NORMAL, /* 1 0 0 */ + SCSI_PROT_WRITE_INSERT, /* 1 0 1 */ + SCSI_PROT_WRITE_STRIP, /* 1 1 0 */ + SCSI_PROT_WRITE_PASS, /* 1 1 1 */ + }; + + return ops[write << 2 | dix << 1 | dif]; +} + +/* + * Returns a mask of the protection flags that are valid for a given DIX + * operation. + */ +static unsigned int sd_prot_flag_mask(unsigned int prot_op) +{ + static const unsigned int flag_mask[] = { + [SCSI_PROT_NORMAL] = 0, + + [SCSI_PROT_READ_STRIP] = SCSI_PROT_TRANSFER_PI | + SCSI_PROT_GUARD_CHECK | + SCSI_PROT_REF_CHECK | + SCSI_PROT_REF_INCREMENT, + + [SCSI_PROT_READ_INSERT] = SCSI_PROT_REF_INCREMENT | + SCSI_PROT_IP_CHECKSUM, + + [SCSI_PROT_READ_PASS] = SCSI_PROT_TRANSFER_PI | + SCSI_PROT_GUARD_CHECK | + SCSI_PROT_REF_CHECK | + SCSI_PROT_REF_INCREMENT | + SCSI_PROT_IP_CHECKSUM, + + [SCSI_PROT_WRITE_INSERT] = SCSI_PROT_TRANSFER_PI | + SCSI_PROT_REF_INCREMENT, + + [SCSI_PROT_WRITE_STRIP] = SCSI_PROT_GUARD_CHECK | + SCSI_PROT_REF_CHECK | + SCSI_PROT_REF_INCREMENT | + SCSI_PROT_IP_CHECKSUM, + + [SCSI_PROT_WRITE_PASS] = SCSI_PROT_TRANSFER_PI | + SCSI_PROT_GUARD_CHECK | + SCSI_PROT_REF_CHECK | + SCSI_PROT_REF_INCREMENT | + SCSI_PROT_IP_CHECKSUM, + }; + + return flag_mask[prot_op]; +} + static unsigned char sd_setup_protect_cmnd(struct scsi_cmnd *scmd, unsigned int dix, unsigned int dif) { - struct bio *bio = scmd->request->bio; - unsigned int prot_op = sd_prot_op(rq_data_dir(scmd->request), dix, dif); + struct request *rq = scsi_cmd_to_rq(scmd); + struct bio *bio = rq->bio; + unsigned int prot_op = sd_prot_op(rq_data_dir(rq), dix, dif); unsigned int protect = 0; if (dix) { /* DIX Type 0, 1, 2, 3 */ if (bio_integrity_flagged(bio, BIP_IP_CHECKSUM)) scmd->prot_flags |= SCSI_PROT_IP_CHECKSUM; - if (bio_integrity_flagged(bio, BIP_CTRL_NOCHECK) == false) + if (bio_integrity_flagged(bio, BIP_CHECK_GUARD)) scmd->prot_flags |= SCSI_PROT_GUARD_CHECK; } if (dif != T10_PI_TYPE3_PROTECTION) { /* DIX/DIF Type 0, 1, 2 */ scmd->prot_flags |= SCSI_PROT_REF_INCREMENT; - if (bio_integrity_flagged(bio, BIP_CTRL_NOCHECK) == false) + if (bio_integrity_flagged(bio, BIP_CHECK_REFTAG)) scmd->prot_flags |= SCSI_PROT_REF_CHECK; } @@ -688,26 +866,28 @@ static unsigned char sd_setup_protect_cmnd(struct scsi_cmnd *scmd, return protect; } -static void sd_config_discard(struct scsi_disk *sdkp, unsigned int mode) +static void sd_disable_discard(struct scsi_disk *sdkp) +{ + sdkp->provisioning_mode = SD_LBP_DISABLE; + blk_queue_disable_discard(sdkp->disk->queue); +} + +static void sd_config_discard(struct scsi_disk *sdkp, struct queue_limits *lim, + 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_alignment = - sdkp->unmap_alignment * logical_block_size; - q->limits.discard_granularity = - max(sdkp->physical_block_size, - sdkp->unmap_granularity * logical_block_size); + lim->discard_alignment = sdkp->unmap_alignment * logical_block_size; + lim->discard_granularity = max(sdkp->physical_block_size, + sdkp->unmap_granularity * logical_block_size); sdkp->provisioning_mode = mode; switch (mode) { case SD_LBP_FULL: case SD_LBP_DISABLE: - blk_queue_max_discard_sectors(q, 0); - queue_flag_clear_unlocked(QUEUE_FLAG_DISCARD, q); - return; + break; case SD_LBP_UNMAP: max_blocks = min_not_zero(sdkp->max_unmap_blocks, @@ -715,13 +895,21 @@ static void sd_config_discard(struct scsi_disk *sdkp, unsigned int mode) break; case SD_LBP_WS16: - max_blocks = min_not_zero(sdkp->max_ws_blocks, - (u32)SD_MAX_WS16_BLOCKS); + if (sdkp->device->unmap_limit_for_ws) + max_blocks = sdkp->max_unmap_blocks; + else + max_blocks = sdkp->max_ws_blocks; + + max_blocks = min_not_zero(max_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); + if (sdkp->device->unmap_limit_for_ws) + max_blocks = sdkp->max_unmap_blocks; + else + max_blocks = sdkp->max_ws_blocks; + + max_blocks = min_not_zero(max_blocks, (u32)SD_MAX_WS10_BLOCKS); break; case SD_LBP_ZERO: @@ -730,142 +918,204 @@ static void sd_config_discard(struct scsi_disk *sdkp, unsigned int mode) break; } - blk_queue_max_discard_sectors(q, max_blocks * (logical_block_size >> 9)); - queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, q); + lim->max_hw_discard_sectors = max_blocks * + (logical_block_size >> SECTOR_SHIFT); } -static int sd_setup_unmap_cmnd(struct scsi_cmnd *cmd) +static void *sd_set_special_bvec(struct request *rq, unsigned int data_len) +{ + struct page *page; + + page = mempool_alloc(sd_page_pool, GFP_ATOMIC); + if (!page) + return NULL; + clear_highpage(page); + bvec_set_page(&rq->special_vec, page, data_len, 0); + rq->rq_flags |= RQF_SPECIAL_PAYLOAD; + return bvec_virt(&rq->special_vec); +} + +static blk_status_t sd_setup_unmap_cmnd(struct scsi_cmnd *cmd) { struct scsi_device *sdp = cmd->device; - struct request *rq = cmd->request; - u64 sector = blk_rq_pos(rq) >> (ilog2(sdp->sector_size) - 9); - u32 nr_sectors = blk_rq_sectors(rq) >> (ilog2(sdp->sector_size) - 9); + struct request *rq = scsi_cmd_to_rq(cmd); + struct scsi_disk *sdkp = scsi_disk(rq->q->disk); + u64 lba = sectors_to_logical(sdp, blk_rq_pos(rq)); + u32 nr_blocks = sectors_to_logical(sdp, blk_rq_sectors(rq)); unsigned int data_len = 24; char *buf; - rq->special_vec.bv_page = alloc_page(GFP_ATOMIC | __GFP_ZERO); - if (!rq->special_vec.bv_page) - return BLKPREP_DEFER; - rq->special_vec.bv_offset = 0; - rq->special_vec.bv_len = data_len; - rq->rq_flags |= RQF_SPECIAL_PAYLOAD; + buf = sd_set_special_bvec(rq, data_len); + if (!buf) + return BLK_STS_RESOURCE; cmd->cmd_len = 10; cmd->cmnd[0] = UNMAP; cmd->cmnd[8] = 24; - buf = page_address(rq->special_vec.bv_page); 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]); + put_unaligned_be64(lba, &buf[8]); + put_unaligned_be32(nr_blocks, &buf[16]); - cmd->allowed = SD_MAX_RETRIES; + cmd->allowed = sdkp->max_retries; cmd->transfersize = data_len; rq->timeout = SD_TIMEOUT; - scsi_req(rq)->resid_len = data_len; - return scsi_init_io(cmd); + return scsi_alloc_sgtables(cmd); } -static int sd_setup_write_same16_cmnd(struct scsi_cmnd *cmd, bool unmap) +static void sd_config_atomic(struct scsi_disk *sdkp, struct queue_limits *lim) +{ + unsigned int logical_block_size = sdkp->device->sector_size, + physical_block_size_sectors, max_atomic, unit_min, unit_max; + + if ((!sdkp->max_atomic && !sdkp->max_atomic_with_boundary) || + sdkp->protection_type == T10_PI_TYPE2_PROTECTION) + return; + + physical_block_size_sectors = sdkp->physical_block_size / + sdkp->device->sector_size; + + unit_min = rounddown_pow_of_two(sdkp->atomic_granularity ? + sdkp->atomic_granularity : + physical_block_size_sectors); + + /* + * Only use atomic boundary when we have the odd scenario of + * sdkp->max_atomic == 0, which the spec does permit. + */ + if (sdkp->max_atomic) { + max_atomic = sdkp->max_atomic; + unit_max = rounddown_pow_of_two(sdkp->max_atomic); + sdkp->use_atomic_write_boundary = 0; + } else { + max_atomic = sdkp->max_atomic_with_boundary; + unit_max = rounddown_pow_of_two(sdkp->max_atomic_boundary); + sdkp->use_atomic_write_boundary = 1; + } + + /* + * Ensure compliance with granularity and alignment. For now, keep it + * simple and just don't support atomic writes for values mismatched + * with max_{boundary}atomic, physical block size, and + * atomic_granularity itself. + * + * We're really being distrustful by checking unit_max also... + */ + if (sdkp->atomic_granularity > 1) { + if (unit_min > 1 && unit_min % sdkp->atomic_granularity) + return; + if (unit_max > 1 && unit_max % sdkp->atomic_granularity) + return; + } + + if (sdkp->atomic_alignment > 1) { + if (unit_min > 1 && unit_min % sdkp->atomic_alignment) + return; + if (unit_max > 1 && unit_max % sdkp->atomic_alignment) + return; + } + + lim->atomic_write_hw_max = max_atomic * logical_block_size; + lim->atomic_write_hw_boundary = 0; + lim->atomic_write_hw_unit_min = unit_min * logical_block_size; + lim->atomic_write_hw_unit_max = unit_max * logical_block_size; + lim->features |= BLK_FEAT_ATOMIC_WRITES; +} + +static blk_status_t sd_setup_write_same16_cmnd(struct scsi_cmnd *cmd, + bool unmap) { struct scsi_device *sdp = cmd->device; - struct request *rq = cmd->request; - u64 sector = blk_rq_pos(rq) >> (ilog2(sdp->sector_size) - 9); - u32 nr_sectors = blk_rq_sectors(rq) >> (ilog2(sdp->sector_size) - 9); + struct request *rq = scsi_cmd_to_rq(cmd); + struct scsi_disk *sdkp = scsi_disk(rq->q->disk); + u64 lba = sectors_to_logical(sdp, blk_rq_pos(rq)); + u32 nr_blocks = sectors_to_logical(sdp, blk_rq_sectors(rq)); u32 data_len = sdp->sector_size; - rq->special_vec.bv_page = alloc_page(GFP_ATOMIC | __GFP_ZERO); - if (!rq->special_vec.bv_page) - return BLKPREP_DEFER; - rq->special_vec.bv_offset = 0; - rq->special_vec.bv_len = data_len; - rq->rq_flags |= RQF_SPECIAL_PAYLOAD; + if (!sd_set_special_bvec(rq, data_len)) + return BLK_STS_RESOURCE; cmd->cmd_len = 16; cmd->cmnd[0] = WRITE_SAME_16; if (unmap) cmd->cmnd[1] = 0x8; /* UNMAP */ - put_unaligned_be64(sector, &cmd->cmnd[2]); - put_unaligned_be32(nr_sectors, &cmd->cmnd[10]); + put_unaligned_be64(lba, &cmd->cmnd[2]); + put_unaligned_be32(nr_blocks, &cmd->cmnd[10]); - cmd->allowed = SD_MAX_RETRIES; + cmd->allowed = sdkp->max_retries; cmd->transfersize = data_len; rq->timeout = unmap ? SD_TIMEOUT : SD_WRITE_SAME_TIMEOUT; - scsi_req(rq)->resid_len = data_len; - return scsi_init_io(cmd); + return scsi_alloc_sgtables(cmd); } -static int sd_setup_write_same10_cmnd(struct scsi_cmnd *cmd, bool unmap) +static blk_status_t sd_setup_write_same10_cmnd(struct scsi_cmnd *cmd, + bool unmap) { struct scsi_device *sdp = cmd->device; - struct request *rq = cmd->request; - u64 sector = blk_rq_pos(rq) >> (ilog2(sdp->sector_size) - 9); - u32 nr_sectors = blk_rq_sectors(rq) >> (ilog2(sdp->sector_size) - 9); + struct request *rq = scsi_cmd_to_rq(cmd); + struct scsi_disk *sdkp = scsi_disk(rq->q->disk); + u64 lba = sectors_to_logical(sdp, blk_rq_pos(rq)); + u32 nr_blocks = sectors_to_logical(sdp, blk_rq_sectors(rq)); u32 data_len = sdp->sector_size; - rq->special_vec.bv_page = alloc_page(GFP_ATOMIC | __GFP_ZERO); - if (!rq->special_vec.bv_page) - return BLKPREP_DEFER; - rq->special_vec.bv_offset = 0; - rq->special_vec.bv_len = data_len; - rq->rq_flags |= RQF_SPECIAL_PAYLOAD; + if (!sd_set_special_bvec(rq, data_len)) + return BLK_STS_RESOURCE; cmd->cmd_len = 10; cmd->cmnd[0] = WRITE_SAME; if (unmap) cmd->cmnd[1] = 0x8; /* UNMAP */ - put_unaligned_be32(sector, &cmd->cmnd[2]); - put_unaligned_be16(nr_sectors, &cmd->cmnd[7]); + put_unaligned_be32(lba, &cmd->cmnd[2]); + put_unaligned_be16(nr_blocks, &cmd->cmnd[7]); - cmd->allowed = SD_MAX_RETRIES; + cmd->allowed = sdkp->max_retries; cmd->transfersize = data_len; rq->timeout = unmap ? SD_TIMEOUT : SD_WRITE_SAME_TIMEOUT; - scsi_req(rq)->resid_len = data_len; - return scsi_init_io(cmd); + return scsi_alloc_sgtables(cmd); } -static int sd_setup_write_zeroes_cmnd(struct scsi_cmnd *cmd) +static blk_status_t sd_setup_write_zeroes_cmnd(struct scsi_cmnd *cmd) { - struct request *rq = cmd->request; + struct request *rq = scsi_cmd_to_rq(cmd); struct scsi_device *sdp = cmd->device; - struct scsi_disk *sdkp = scsi_disk(rq->rq_disk); - u64 sector = blk_rq_pos(rq) >> (ilog2(sdp->sector_size) - 9); - u32 nr_sectors = blk_rq_sectors(rq) >> (ilog2(sdp->sector_size) - 9); - int ret; + struct scsi_disk *sdkp = scsi_disk(rq->q->disk); + u64 lba = sectors_to_logical(sdp, blk_rq_pos(rq)); + u32 nr_blocks = sectors_to_logical(sdp, blk_rq_sectors(rq)); if (!(rq->cmd_flags & REQ_NOUNMAP)) { switch (sdkp->zeroing_mode) { case SD_ZERO_WS16_UNMAP: - ret = sd_setup_write_same16_cmnd(cmd, true); - goto out; + return sd_setup_write_same16_cmnd(cmd, true); case SD_ZERO_WS10_UNMAP: - ret = sd_setup_write_same10_cmnd(cmd, true); - goto out; + return sd_setup_write_same10_cmnd(cmd, true); } } - if (sdp->no_write_same) - return BLKPREP_INVALID; + if (sdp->no_write_same) { + rq->rq_flags |= RQF_QUIET; + return BLK_STS_TARGET; + } - if (sdkp->ws16 || sector > 0xffffffff || nr_sectors > 0xffff) - ret = sd_setup_write_same16_cmnd(cmd, false); - else - ret = sd_setup_write_same10_cmnd(cmd, false); + if (sdkp->ws16 || lba > 0xffffffff || nr_blocks > 0xffff) + return sd_setup_write_same16_cmnd(cmd, false); -out: - if (sd_is_zoned(sdkp) && ret == BLKPREP_OK) - return sd_zbc_write_lock_zone(cmd); + return sd_setup_write_same10_cmnd(cmd, false); +} - return ret; +static void sd_disable_write_same(struct scsi_disk *sdkp) +{ + sdkp->device->no_write_same = 1; + sdkp->max_ws_blocks = 0; + blk_queue_disable_write_zeroes(sdkp->disk->queue); } -static void sd_config_write_same(struct scsi_disk *sdkp) +static void sd_config_write_same(struct scsi_disk *sdkp, + struct queue_limits *lim) { - struct request_queue *q = sdkp->disk->queue; unsigned int logical_block_size = sdkp->device->sector_size; if (sdkp->device->no_write_same) { @@ -898,352 +1148,326 @@ static void sd_config_write_same(struct scsi_disk *sdkp) else sdkp->zeroing_mode = SD_ZERO_WRITE; + if (sdkp->max_ws_blocks && + sdkp->physical_block_size > logical_block_size) { + /* + * Reporting a maximum number of blocks that is not aligned + * on the device physical size would cause a large write same + * request to be split into physically unaligned chunks by + * __blkdev_issue_write_zeroes() even if the caller of this + * functions took care to align the large request. So make sure + * the maximum reported is aligned to the device physical block + * size. This is only an optional optimization for regular + * disks, but this is mandatory to avoid failure of large write + * same requests directed at sequential write required zones of + * host-managed ZBC disks. + */ + sdkp->max_ws_blocks = + round_down(sdkp->max_ws_blocks, + bytes_to_logical(sdkp->device, + sdkp->physical_block_size)); + } + out: - blk_queue_max_write_same_sectors(q, sdkp->max_ws_blocks * - (logical_block_size >> 9)); - blk_queue_max_write_zeroes_sectors(q, sdkp->max_ws_blocks * - (logical_block_size >> 9)); + lim->max_write_zeroes_sectors = + sdkp->max_ws_blocks * (logical_block_size >> SECTOR_SHIFT); + + if (sdkp->zeroing_mode == SD_ZERO_WS16_UNMAP || + sdkp->zeroing_mode == SD_ZERO_WS10_UNMAP) + lim->max_hw_wzeroes_unmap_sectors = + lim->max_write_zeroes_sectors; } -/** - * sd_setup_write_same_cmnd - write the same data to multiple blocks - * @cmd: command to prepare - * - * Will set up either WRITE SAME(10) or WRITE SAME(16) depending on - * the preference indicated by the target device. - **/ -static int sd_setup_write_same_cmnd(struct scsi_cmnd *cmd) +static blk_status_t sd_setup_flush_cmnd(struct scsi_cmnd *cmd) { - struct request *rq = cmd->request; - struct scsi_device *sdp = cmd->device; - 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_INVALID; + struct request *rq = scsi_cmd_to_rq(cmd); + struct scsi_disk *sdkp = scsi_disk(rq->q->disk); - BUG_ON(bio_offset(bio) || bio_iovec(bio).bv_len != sdp->sector_size); - - if (sd_is_zoned(sdkp)) { - ret = sd_zbc_write_lock_zone(cmd); - if (ret != BLKPREP_OK) - return ret; - } - - sector >>= ilog2(sdp->sector_size) - 9; - nr_sectors >>= ilog2(sdp->sector_size) - 9; - - rq->timeout = SD_WRITE_SAME_TIMEOUT; + /* flush requests don't perform I/O, zero the S/G table */ + memset(&cmd->sdb, 0, sizeof(cmd->sdb)); - if (sdkp->ws16 || sector > 0xffffffff || nr_sectors > 0xffff) { + if (cmd->device->use_16_for_sync) { + cmd->cmnd[0] = SYNCHRONIZE_CACHE_16; cmd->cmd_len = 16; - cmd->cmnd[0] = WRITE_SAME_16; - put_unaligned_be64(sector, &cmd->cmnd[2]); - put_unaligned_be32(nr_sectors, &cmd->cmnd[10]); } else { + cmd->cmnd[0] = SYNCHRONIZE_CACHE; cmd->cmd_len = 10; - cmd->cmnd[0] = WRITE_SAME; - put_unaligned_be32(sector, &cmd->cmnd[2]); - put_unaligned_be16(nr_sectors, &cmd->cmnd[7]); } + cmd->transfersize = 0; + cmd->allowed = sdkp->max_retries; - cmd->transfersize = sdp->sector_size; - cmd->allowed = SD_MAX_RETRIES; + rq->timeout = rq->q->rq_timeout * SD_FLUSH_TIMEOUT_MULTIPLIER; + return BLK_STS_OK; +} - /* - * For WRITE SAME the data transferred via the DATA OUT buffer is - * different from the amount of data actually written to the target. - * - * We set up __data_len to the amount of data transferred via the - * DATA OUT buffer so that blk_rq_map_sg sets up the proper S/G list - * to transfer a single sector of data first, but then reset it to - * the amount of data to be written right after so that the I/O path - * knows how much to actually write. - */ - rq->__data_len = sdp->sector_size; - ret = scsi_init_io(cmd); - rq->__data_len = nr_bytes; +/** + * sd_group_number() - Compute the GROUP NUMBER field + * @cmd: SCSI command for which to compute the value of the six-bit GROUP NUMBER + * field. + * + * From SBC-5 r05 (https://www.t10.org/cgi-bin/ac.pl?t=f&f=sbc5r05.pdf): + * 0: no relative lifetime. + * 1: shortest relative lifetime. + * 2: second shortest relative lifetime. + * 3 - 0x3d: intermediate relative lifetimes. + * 0x3e: second longest relative lifetime. + * 0x3f: longest relative lifetime. + */ +static u8 sd_group_number(struct scsi_cmnd *cmd) +{ + const struct request *rq = scsi_cmd_to_rq(cmd); + struct scsi_disk *sdkp = scsi_disk(rq->q->disk); - if (sd_is_zoned(sdkp) && ret != BLKPREP_OK) - sd_zbc_write_unlock_zone(cmd); + if (!sdkp->rscs) + return 0; - return ret; + return min3((u32)rq->bio->bi_write_hint, + (u32)sdkp->permanent_stream_count, 0x3fu); } -static int sd_setup_flush_cmnd(struct scsi_cmnd *cmd) +static blk_status_t sd_setup_rw32_cmnd(struct scsi_cmnd *cmd, bool write, + sector_t lba, unsigned int nr_blocks, + unsigned char flags, unsigned int dld) { - struct request *rq = cmd->request; + cmd->cmd_len = SD_EXT_CDB_SIZE; + cmd->cmnd[0] = VARIABLE_LENGTH_CMD; + cmd->cmnd[6] = sd_group_number(cmd); + cmd->cmnd[7] = 0x18; /* Additional CDB len */ + cmd->cmnd[9] = write ? WRITE_32 : READ_32; + cmd->cmnd[10] = flags; + cmd->cmnd[11] = dld & 0x07; + put_unaligned_be64(lba, &cmd->cmnd[12]); + put_unaligned_be32(lba, &cmd->cmnd[20]); /* Expected Indirect LBA */ + put_unaligned_be32(nr_blocks, &cmd->cmnd[28]); + + return BLK_STS_OK; +} - /* flush requests don't perform I/O, zero the S/G table */ - memset(&cmd->sdb, 0, sizeof(cmd->sdb)); +static blk_status_t sd_setup_rw16_cmnd(struct scsi_cmnd *cmd, bool write, + sector_t lba, unsigned int nr_blocks, + unsigned char flags, unsigned int dld) +{ + cmd->cmd_len = 16; + cmd->cmnd[0] = write ? WRITE_16 : READ_16; + cmd->cmnd[1] = flags | ((dld >> 2) & 0x01); + cmd->cmnd[14] = ((dld & 0x03) << 6) | sd_group_number(cmd); + cmd->cmnd[15] = 0; + put_unaligned_be64(lba, &cmd->cmnd[2]); + put_unaligned_be32(nr_blocks, &cmd->cmnd[10]); + + return BLK_STS_OK; +} - cmd->cmnd[0] = SYNCHRONIZE_CACHE; +static blk_status_t sd_setup_rw10_cmnd(struct scsi_cmnd *cmd, bool write, + sector_t lba, unsigned int nr_blocks, + unsigned char flags) +{ cmd->cmd_len = 10; - cmd->transfersize = 0; - cmd->allowed = SD_MAX_RETRIES; - - rq->timeout = rq->q->rq_timeout * SD_FLUSH_TIMEOUT_MULTIPLIER; - return BLKPREP_OK; + cmd->cmnd[0] = write ? WRITE_10 : READ_10; + cmd->cmnd[1] = flags; + cmd->cmnd[6] = sd_group_number(cmd); + cmd->cmnd[9] = 0; + put_unaligned_be32(lba, &cmd->cmnd[2]); + put_unaligned_be16(nr_blocks, &cmd->cmnd[7]); + + return BLK_STS_OK; } -static int sd_setup_read_write_cmnd(struct scsi_cmnd *SCpnt) +static blk_status_t sd_setup_rw6_cmnd(struct scsi_cmnd *cmd, bool write, + sector_t lba, unsigned int nr_blocks, + unsigned char flags) { - struct request *rq = SCpnt->request; - struct scsi_device *sdp = SCpnt->device; - struct gendisk *disk = rq->rq_disk; - struct scsi_disk *sdkp = scsi_disk(disk); - sector_t block = blk_rq_pos(rq); - sector_t threshold; - unsigned int this_count = blk_rq_sectors(rq); - unsigned int dif, dix; - bool zoned_write = sd_is_zoned(sdkp) && rq_data_dir(rq) == WRITE; - int ret; - unsigned char protect; + /* Avoid that 0 blocks gets translated into 256 blocks. */ + if (WARN_ON_ONCE(nr_blocks == 0)) + return BLK_STS_IOERR; - if (zoned_write) { - ret = sd_zbc_write_lock_zone(SCpnt); - if (ret != BLKPREP_OK) - return ret; + if (unlikely(flags & 0x8)) { + /* + * 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, cmd, "FUA write on READ/WRITE(6) drive\n"); + return BLK_STS_IOERR; } - ret = scsi_init_io(SCpnt); - if (ret != BLKPREP_OK) - goto out; - SCpnt = rq->special; + cmd->cmd_len = 6; + cmd->cmnd[0] = write ? WRITE_6 : READ_6; + cmd->cmnd[1] = (lba >> 16) & 0x1f; + cmd->cmnd[2] = (lba >> 8) & 0xff; + cmd->cmnd[3] = lba & 0xff; + cmd->cmnd[4] = nr_blocks; + cmd->cmnd[5] = 0; - /* from here on until we're complete, any goto out - * is used for a killable error condition */ - ret = BLKPREP_KILL; + return BLK_STS_OK; +} - 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)) { - 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; - } +/* + * Check if a command has a duration limit set. If it does, and the target + * device supports CDL and the feature is enabled, return the limit + * descriptor index to use. Return 0 (no limit) otherwise. + */ +static int sd_cdl_dld(struct scsi_disk *sdkp, struct scsi_cmnd *scmd) +{ + struct scsi_device *sdp = sdkp->device; + int hint; - if (sdp->changed) { - /* - * quietly refuse to do anything to a changed disc until - * the changed bit has been reset - */ - /* printk("SCSI disk has been changed or is not present. Prohibiting further I/O.\n"); */ - goto out; - } + if (!sdp->cdl_supported || !sdp->cdl_enable) + return 0; /* - * Some SD card readers can't handle multi-sector accesses which touch - * the last one or two hardware sectors. Split accesses as needed. + * Use "no limit" if the request ioprio does not specify a duration + * limit hint. */ - threshold = get_capacity(disk) - SD_LAST_BUGGY_SECTORS * - (sdp->sector_size / 512); + hint = IOPRIO_PRIO_HINT(req_get_ioprio(scsi_cmd_to_rq(scmd))); + if (hint < IOPRIO_HINT_DEV_DURATION_LIMIT_1 || + hint > IOPRIO_HINT_DEV_DURATION_LIMIT_7) + return 0; - 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; - } - } + return (hint - IOPRIO_HINT_DEV_DURATION_LIMIT_1) + 1; +} - SCSI_LOG_HLQUEUE(2, scmd_printk(KERN_INFO, SCpnt, "block=%llu\n", - (unsigned long long)block)); +static blk_status_t sd_setup_atomic_cmnd(struct scsi_cmnd *cmd, + sector_t lba, unsigned int nr_blocks, + bool boundary, unsigned char flags) +{ + cmd->cmd_len = 16; + cmd->cmnd[0] = WRITE_ATOMIC_16; + cmd->cmnd[1] = flags; + put_unaligned_be64(lba, &cmd->cmnd[2]); + put_unaligned_be16(nr_blocks, &cmd->cmnd[12]); + if (boundary) + put_unaligned_be16(nr_blocks, &cmd->cmnd[10]); + else + put_unaligned_be16(0, &cmd->cmnd[10]); + put_unaligned_be16(nr_blocks, &cmd->cmnd[12]); + cmd->cmnd[14] = 0; + cmd->cmnd[15] = 0; - /* - * If we have a 1K hardware sectorsize, prevent access to single - * 512 byte sectors. In theory we could handle this - in fact - * the scsi cdrom driver must be able to handle this because - * we typically use 1K blocksizes, and cdroms typically have - * 2K hardware sectorsizes. Of course, things are simpler - * with the cdrom, since it is read-only. For performance - * reasons, the filesystems should be able to handle this - * and not force the scsi disk driver to use bounce buffers - * for this. - */ - if (sdp->sector_size == 1024) { - 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; - } + return BLK_STS_OK; +} + +static blk_status_t sd_setup_read_write_cmnd(struct scsi_cmnd *cmd) +{ + struct request *rq = scsi_cmd_to_rq(cmd); + struct scsi_device *sdp = cmd->device; + struct scsi_disk *sdkp = scsi_disk(rq->q->disk); + sector_t lba = sectors_to_logical(sdp, blk_rq_pos(rq)); + sector_t threshold; + unsigned int nr_blocks = sectors_to_logical(sdp, blk_rq_sectors(rq)); + unsigned int mask = logical_to_sectors(sdp, 1) - 1; + bool write = rq_data_dir(rq) == WRITE; + unsigned char protect, fua; + unsigned int dld; + blk_status_t ret; + unsigned int dif; + bool dix; + + ret = scsi_alloc_sgtables(cmd); + if (ret != BLK_STS_OK) + return ret; + + ret = BLK_STS_IOERR; + if (!scsi_device_online(sdp) || sdp->changed) { + scmd_printk(KERN_ERR, cmd, "device offline or changed\n"); + goto fail; } - if (sdp->sector_size == 2048) { - 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 (blk_rq_pos(rq) + blk_rq_sectors(rq) > get_capacity(rq->q->disk)) { + scmd_printk(KERN_ERR, cmd, "access beyond end of device\n"); + goto fail; } - if (sdp->sector_size == 4096) { - 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; - } + + if ((blk_rq_pos(rq) & mask) || (blk_rq_sectors(rq) & mask)) { + scmd_printk(KERN_ERR, cmd, "request not aligned to the logical block size\n"); + goto fail; } - if (rq_data_dir(rq) == WRITE) { - SCpnt->cmnd[0] = WRITE_6; - if (blk_integrity_rq(rq)) - sd_dif_prepare(SCpnt); + /* + * Some SD card readers can't handle accesses which touch the + * last one or two logical blocks. Split accesses as needed. + */ + threshold = sdkp->capacity - SD_LAST_BUGGY_SECTORS; - } else if (rq_data_dir(rq) == READ) { - SCpnt->cmnd[0] = READ_6; - } else { - scmd_printk(KERN_ERR, SCpnt, "Unknown command %d\n", req_op(rq)); - goto out; + if (unlikely(sdp->last_sector_bug && lba + nr_blocks > threshold)) { + if (lba < threshold) { + /* Access up to the threshold but not beyond */ + nr_blocks = threshold - lba; + } else { + /* Access only a single logical block */ + nr_blocks = 1; + } } - 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))); - - dix = scsi_prot_sg_count(SCpnt); - dif = scsi_host_dif_capable(SCpnt->device->host, sdkp->protection_type); + fua = rq->cmd_flags & REQ_FUA ? 0x8 : 0; + dix = scsi_prot_sg_count(cmd); + dif = scsi_host_dif_capable(cmd->device->host, sdkp->protection_type); + dld = sd_cdl_dld(sdkp, cmd); if (dif || dix) - protect = sd_setup_protect_cmnd(SCpnt, dix, dif); + protect = sd_setup_protect_cmnd(cmd, dix, dif); else protect = 0; if (protect && sdkp->protection_type == T10_PI_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 || (this_count > 0xffff)) { - 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; - SCpnt->cmnd[5] = sizeof(block) > 4 ? (unsigned char) (block >> 32) & 0xff : 0; - SCpnt->cmnd[6] = (unsigned char) (block >> 24) & 0xff; - SCpnt->cmnd[7] = (unsigned char) (block >> 16) & 0xff; - SCpnt->cmnd[8] = (unsigned char) (block >> 8) & 0xff; - SCpnt->cmnd[9] = (unsigned char) block & 0xff; - SCpnt->cmnd[10] = (unsigned char) (this_count >> 24) & 0xff; - SCpnt->cmnd[11] = (unsigned char) (this_count >> 16) & 0xff; - SCpnt->cmnd[12] = (unsigned char) (this_count >> 8) & 0xff; - 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) { - 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; - SCpnt->cmnd[5] = (unsigned char) block & 0xff; - SCpnt->cmnd[6] = SCpnt->cmnd[9] = 0; - SCpnt->cmnd[7] = (unsigned char) (this_count >> 8) & 0xff; - SCpnt->cmnd[8] = (unsigned char) this_count & 0xff; + ret = sd_setup_rw32_cmnd(cmd, write, lba, nr_blocks, + protect | fua, dld); + } else if (rq->cmd_flags & REQ_ATOMIC) { + ret = sd_setup_atomic_cmnd(cmd, lba, nr_blocks, + sdkp->use_atomic_write_boundary, + protect | fua); + } else if (sdp->use_16_for_rw || (nr_blocks > 0xffff)) { + ret = sd_setup_rw16_cmnd(cmd, write, lba, nr_blocks, + protect | fua, dld); + } else if ((nr_blocks > 0xff) || (lba > 0x1fffff) || + sdp->use_10_for_rw || protect || rq->bio->bi_write_hint) { + ret = sd_setup_rw10_cmnd(cmd, write, lba, nr_blocks, + protect | fua); } 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; + ret = sd_setup_rw6_cmnd(cmd, write, lba, nr_blocks, + protect | fua); } - SCpnt->sdb.length = this_count * sdp->sector_size; + + if (unlikely(ret != BLK_STS_OK)) + goto fail; /* * We shouldn't disconnect in the middle of a sector, so with a dumb * host adapter, it's safe to assume that we can at least transfer * this many bytes between each connect / disconnect. */ - SCpnt->transfersize = sdp->sector_size; - SCpnt->underflow = this_count << 9; - SCpnt->allowed = SD_MAX_RETRIES; + cmd->transfersize = sdp->sector_size; + cmd->underflow = nr_blocks << 9; + cmd->allowed = sdkp->max_retries; + cmd->sdb.length = nr_blocks * sdp->sector_size; + + SCSI_LOG_HLQUEUE(1, + scmd_printk(KERN_INFO, cmd, + "%s: block=%llu, count=%d\n", __func__, + (unsigned long long)blk_rq_pos(rq), + blk_rq_sectors(rq))); + SCSI_LOG_HLQUEUE(2, + scmd_printk(KERN_INFO, cmd, + "%s %d/%u 512 byte blocks.\n", + write ? "writing" : "reading", nr_blocks, + blk_rq_sectors(rq))); /* - * This indicates that the command is ready from our end to be - * queued. + * This indicates that the command is ready from our end to be queued. */ - ret = BLKPREP_OK; - out: - if (zoned_write && ret != BLKPREP_OK) - sd_zbc_write_unlock_zone(SCpnt); - + return BLK_STS_OK; +fail: + scsi_free_sgtables(cmd); return ret; } -static int sd_init_command(struct scsi_cmnd *cmd) +static blk_status_t sd_init_command(struct scsi_cmnd *cmd) { - struct request *rq = cmd->request; + struct request *rq = scsi_cmd_to_rq(cmd); switch (req_op(rq)) { case REQ_OP_DISCARD: - switch (scsi_disk(rq->rq_disk)->provisioning_mode) { + switch (scsi_disk(rq->q->disk)->provisioning_mode) { case SD_LBP_UNMAP: return sd_setup_unmap_cmnd(cmd); case SD_LBP_WS16: @@ -1253,44 +1477,60 @@ static int sd_init_command(struct scsi_cmnd *cmd) case SD_LBP_ZERO: return sd_setup_write_same10_cmnd(cmd, false); default: - return BLKPREP_INVALID; + return BLK_STS_TARGET; } case REQ_OP_WRITE_ZEROES: return sd_setup_write_zeroes_cmnd(cmd); - case REQ_OP_WRITE_SAME: - return sd_setup_write_same_cmnd(cmd); case REQ_OP_FLUSH: return sd_setup_flush_cmnd(cmd); case REQ_OP_READ: case REQ_OP_WRITE: return sd_setup_read_write_cmnd(cmd); - case REQ_OP_ZONE_REPORT: - return sd_zbc_setup_report_cmnd(cmd); case REQ_OP_ZONE_RESET: - return sd_zbc_setup_reset_cmnd(cmd); + return sd_zbc_setup_zone_mgmt_cmnd(cmd, ZO_RESET_WRITE_POINTER, + false); + case REQ_OP_ZONE_RESET_ALL: + return sd_zbc_setup_zone_mgmt_cmnd(cmd, ZO_RESET_WRITE_POINTER, + true); + case REQ_OP_ZONE_OPEN: + return sd_zbc_setup_zone_mgmt_cmnd(cmd, ZO_OPEN_ZONE, false); + case REQ_OP_ZONE_CLOSE: + return sd_zbc_setup_zone_mgmt_cmnd(cmd, ZO_CLOSE_ZONE, false); + case REQ_OP_ZONE_FINISH: + return sd_zbc_setup_zone_mgmt_cmnd(cmd, ZO_FINISH_ZONE, false); default: - BUG(); + WARN_ON_ONCE(1); + return BLK_STS_NOTSUPP; } } static void sd_uninit_command(struct scsi_cmnd *SCpnt) { - struct request *rq = SCpnt->request; + struct request *rq = scsi_cmd_to_rq(SCpnt); if (rq->rq_flags & RQF_SPECIAL_PAYLOAD) - __free_page(rq->special_vec.bv_page); + mempool_free(rq->special_vec.bv_page, sd_page_pool); +} - if (SCpnt->cmnd != scsi_req(rq)->cmd) { - mempool_free(SCpnt->cmnd, sd_cdb_pool); - SCpnt->cmnd = NULL; - SCpnt->cmd_len = 0; +static bool sd_need_revalidate(struct gendisk *disk, struct scsi_disk *sdkp) +{ + if (sdkp->device->removable || sdkp->write_prot) { + if (disk_check_media_change(disk)) + return true; } + + /* + * Force a full rescan after ioctl(BLKRRPART). While the disk state has + * nothing to do with partitions, BLKRRPART is used to force a full + * revalidate after things like a format for historical reasons. + */ + return test_bit(GD_NEED_PART_SCAN, &disk->state); } /** * sd_open - open a scsi disk device - * @bdev: Block device of the scsi disk to open - * @mode: FMODE_* mask + * @disk: disk to open + * @mode: open mode * * Returns 0 if successful. Returns a negated errno value in case * of error. @@ -1300,21 +1540,19 @@ static void sd_uninit_command(struct scsi_cmnd *SCpnt) * In the latter case @inode and @filp carry an abridged amount * of information as noted above. * - * Locking: called with bdev->bd_mutex held. + * Locking: called with disk->open_mutex held. **/ -static int sd_open(struct block_device *bdev, fmode_t mode) +static int sd_open(struct gendisk *disk, blk_mode_t mode) { - struct scsi_disk *sdkp = scsi_disk_get(bdev->bd_disk); - struct scsi_device *sdev; + struct scsi_disk *sdkp = scsi_disk(disk); + struct scsi_device *sdev = sdkp->device; int retval; - if (!sdkp) + if (scsi_device_get(sdev)) return -ENXIO; SCSI_LOG_HLQUEUE(3, sd_printk(KERN_INFO, sdkp, "sd_open\n")); - sdev = sdkp->device; - /* * If the device is in error recovery, wait until it is done. * If the device is offline, then disallow any access to it. @@ -1323,14 +1561,15 @@ static int sd_open(struct block_device *bdev, fmode_t mode) if (!scsi_block_when_processing_errors(sdev)) goto error_out; - if (sdev->removable || sdkp->write_prot) - check_disk_change(bdev); + if (sd_need_revalidate(disk, sdkp)) + sd_revalidate_disk(disk); /* * If the drive is empty, just let the open fail. */ retval = -ENOMEDIUM; - if (sdev->removable && !sdkp->media_present && !(mode & FMODE_NDELAY)) + if (sdev->removable && !sdkp->media_present && + !(mode & BLK_OPEN_NDELAY)) goto error_out; /* @@ -1338,7 +1577,7 @@ static int sd_open(struct block_device *bdev, fmode_t mode) * if the user expects to be able to write to the thing. */ retval = -EROFS; - if (sdkp->write_prot && (mode & FMODE_WRITE)) + if (sdkp->write_prot && (mode & BLK_OPEN_WRITE)) goto error_out; /* @@ -1359,7 +1598,7 @@ static int sd_open(struct block_device *bdev, fmode_t mode) return 0; error_out: - scsi_disk_put(sdkp); + scsi_device_put(sdev); return retval; } @@ -1367,16 +1606,15 @@ error_out: * sd_release - invoked when the (last) close(2) is called on this * scsi disk. * @disk: disk to release - * @mode: FMODE_* mask * * Returns 0. * * Note: may block (uninterruptible) if error recovery is underway * on this disk. * - * Locking: called with bdev->bd_mutex held. + * Locking: called with disk->open_mutex held. **/ -static void sd_release(struct gendisk *disk, fmode_t mode) +static void sd_release(struct gendisk *disk) { struct scsi_disk *sdkp = scsi_disk(disk); struct scsi_device *sdev = sdkp->device; @@ -1388,17 +1626,12 @@ static void sd_release(struct gendisk *disk, fmode_t mode) scsi_set_medium_removal(sdev, SCSI_REMOVAL_ALLOW); } - /* - * XXX and what if there are packets in flight and this close() - * XXX is followed by a "rmmod sd_mod"? - */ - - scsi_disk_put(sdkp); + scsi_device_put(sdev); } -static int sd_getgeo(struct block_device *bdev, struct hd_geometry *geo) +static int sd_getgeo(struct gendisk *disk, struct hd_geometry *geo) { - struct scsi_disk *sdkp = scsi_disk(bdev->bd_disk); + struct scsi_disk *sdkp = scsi_disk(disk); struct scsi_device *sdp = sdkp->device; struct Scsi_Host *host = sdp->host; sector_t capacity = logical_to_sectors(sdp, sdkp->capacity); @@ -1411,9 +1644,9 @@ static int sd_getgeo(struct block_device *bdev, struct hd_geometry *geo) /* override with calculated, extended default, or driver values */ if (host->hostt->bios_param) - host->hostt->bios_param(sdp, bdev, capacity, diskinfo); + host->hostt->bios_param(sdp, disk, capacity, diskinfo); else - scsicam_bios_param(bdev, capacity, diskinfo); + scsicam_bios_param(disk, capacity, diskinfo); geo->heads = diskinfo[0]; geo->sectors = diskinfo[1]; @@ -1424,7 +1657,7 @@ static int sd_getgeo(struct block_device *bdev, struct hd_geometry *geo) /** * sd_ioctl - process an ioctl * @bdev: target block device - * @mode: FMODE_* mask + * @mode: open mode * @cmd: ioctl command number * @arg: this is third argument given to ioctl(2) system call. * Often contains a pointer. @@ -1435,7 +1668,7 @@ static int sd_getgeo(struct block_device *bdev, struct hd_geometry *geo) * Note: most ioctls are forward onto the block subsystem or further * down in the scsi subsystem. **/ -static int sd_ioctl(struct block_device *bdev, fmode_t mode, +static int sd_ioctl(struct block_device *bdev, blk_mode_t mode, unsigned int cmd, unsigned long arg) { struct gendisk *disk = bdev->bd_disk; @@ -1447,9 +1680,8 @@ static int sd_ioctl(struct block_device *bdev, fmode_t mode, 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 (bdev_is_partition(bdev) && !capable(CAP_SYS_RAWIO)) + return -ENOIOCTLCMD; /* * If we are in the middle of error recovery, don't let anyone @@ -1458,32 +1690,13 @@ static int sd_ioctl(struct block_device *bdev, fmode_t mode, * access to the device is prohibited. */ error = scsi_ioctl_block_when_processing_errors(sdp, cmd, - (mode & FMODE_NDELAY) != 0); + (mode & BLK_OPEN_NDELAY)); if (error) - goto out; + return error; if (is_sed_ioctl(cmd)) return sed_ioctl(sdkp->opal_dev, cmd, p); - - /* - * Send SCSI addressing ioctls directly to mid level, send other - * ioctls to block level and then onto mid level if they can't be - * resolved. - */ - switch (cmd) { - case SCSI_IOCTL_GET_IDLUN: - case SCSI_IOCTL_GET_BUS_NUMBER: - error = scsi_ioctl(sdp, cmd, p); - break; - default: - error = scsi_cmd_blk_ioctl(bdev, mode, cmd, p); - if (error != -ENOTTY) - break; - error = scsi_ioctl(sdp, cmd, p); - break; - } -out: - return error; + return scsi_ioctl(sdp, mode & BLK_OPEN_WRITE, cmd, p); } static void set_media_not_present(struct scsi_disk *sdkp) @@ -1527,9 +1740,10 @@ static int media_not_present(struct scsi_disk *sdkp, **/ static unsigned int sd_check_events(struct gendisk *disk, unsigned int clearing) { - struct scsi_disk *sdkp = scsi_disk_get(disk); + struct scsi_disk *sdkp = disk->private_data; struct scsi_device *sdp; int retval; + bool disk_changed; if (!sdkp) return 0; @@ -1560,11 +1774,11 @@ static unsigned int sd_check_events(struct gendisk *disk, unsigned int clearing) if (scsi_block_when_processing_errors(sdp)) { struct scsi_sense_hdr sshdr = { 0, }; - retval = scsi_test_unit_ready(sdp, SD_TIMEOUT, SD_MAX_RETRIES, + retval = scsi_test_unit_ready(sdp, SD_TIMEOUT, sdkp->max_retries, &sshdr); /* failed to execute TUR, assume media not present */ - if (host_byte(retval)) { + if (retval < 0 || host_byte(retval)) { set_media_not_present(sdkp); goto out; } @@ -1587,54 +1801,70 @@ out: * Medium present state has changed in either direction. * Device has indicated UNIT_ATTENTION. */ - retval = sdp->changed ? DISK_EVENT_MEDIA_CHANGE : 0; + disk_changed = sdp->changed; sdp->changed = 0; - scsi_disk_put(sdkp); - return retval; + return disk_changed ? DISK_EVENT_MEDIA_CHANGE : 0; } -static int sd_sync_cache(struct scsi_disk *sdkp, struct scsi_sense_hdr *sshdr) +static int sd_sync_cache(struct scsi_disk *sdkp) { - int retries, res; + int res; struct scsi_device *sdp = sdkp->device; const int timeout = sdp->request_queue->rq_timeout * SD_FLUSH_TIMEOUT_MULTIPLIER; - struct scsi_sense_hdr my_sshdr; + /* Leave the rest of the command zero to indicate flush everything. */ + const unsigned char cmd[16] = { sdp->use_16_for_sync ? + SYNCHRONIZE_CACHE_16 : SYNCHRONIZE_CACHE }; + struct scsi_sense_hdr sshdr; + struct scsi_failure failure_defs[] = { + { + .allowed = 3, + .result = SCMD_FAILURE_RESULT_ANY, + }, + {} + }; + struct scsi_failures failures = { + .failure_definitions = failure_defs, + }; + const struct scsi_exec_args exec_args = { + .req_flags = BLK_MQ_REQ_PM, + .sshdr = &sshdr, + .failures = &failures, + }; if (!scsi_device_online(sdp)) return -ENODEV; - /* caller might not be interested in sense, but we need it */ - if (!sshdr) - sshdr = &my_sshdr; - - for (retries = 3; retries > 0; --retries) { - unsigned char cmd[10] = { 0 }; - - cmd[0] = SYNCHRONIZE_CACHE; - /* - * Leave the rest of the command zero to indicate - * flush everything. - */ - res = scsi_execute(sdp, cmd, DMA_NONE, NULL, 0, NULL, sshdr, - timeout, SD_MAX_RETRIES, 0, RQF_PM, NULL); - if (res == 0) - break; - } - + res = scsi_execute_cmd(sdp, cmd, REQ_OP_DRV_IN, NULL, 0, timeout, + sdkp->max_retries, &exec_args); if (res) { sd_print_result(sdkp, "Synchronize Cache(10) failed", res); - if (driver_byte(res) & DRIVER_SENSE) - sd_print_sense_hdr(sdkp, sshdr); + if (res < 0) + return res; + + if (scsi_status_is_check_condition(res) && + scsi_sense_valid(&sshdr)) { + 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 */ + /* we need to evaluate the error return */ + if (sshdr.asc == 0x3a || /* medium not present */ + sshdr.asc == 0x20 || /* invalid command */ + (sshdr.asc == 0x74 && sshdr.ascq == 0x71)) /* drive is password locked */ /* this is no error here */ return 0; + /* + * If a format is in progress or if the drive does not + * support sync, there is not much we can do because + * this is called during shutdown or suspend so just + * return success so those operations can proceed. + */ + if ((sshdr.asc == 0x04 && sshdr.ascq == 0x04) || + sshdr.sense_key == ILLEGAL_REQUEST) + return 0; + } + switch (host_byte(res)) { /* ignore errors due to racing a disconnection */ case DID_BAD_TARGET: @@ -1657,60 +1887,213 @@ static void sd_rescan(struct device *dev) { struct scsi_disk *sdkp = dev_get_drvdata(dev); - revalidate_disk(sdkp->disk); + sd_revalidate_disk(sdkp->disk); } +static int sd_get_unique_id(struct gendisk *disk, u8 id[16], + enum blk_unique_id type) +{ + struct scsi_device *sdev = scsi_disk(disk)->device; + const struct scsi_vpd *vpd; + const unsigned char *d; + int ret = -ENXIO, len; + + rcu_read_lock(); + vpd = rcu_dereference(sdev->vpd_pg83); + if (!vpd) + goto out_unlock; + + ret = -EINVAL; + for (d = vpd->data + 4; d < vpd->data + vpd->len; d += d[3] + 4) { + /* we only care about designators with LU association */ + if (((d[1] >> 4) & 0x3) != 0x00) + continue; + if ((d[1] & 0xf) != type) + continue; -#ifdef CONFIG_COMPAT -/* - * This gets directly called from VFS. When the ioctl - * is not recognized we go back to the other translation paths. - */ -static int sd_compat_ioctl(struct block_device *bdev, fmode_t mode, - unsigned int cmd, unsigned long arg) + /* + * Only exit early if a 16-byte descriptor was found. Otherwise + * keep looking as one with more entropy might still show up. + */ + len = d[3]; + if (len != 8 && len != 12 && len != 16) + continue; + ret = len; + memcpy(id, d + 4, len); + if (len == 16) + break; + } +out_unlock: + rcu_read_unlock(); + return ret; +} + +static int sd_scsi_to_pr_err(struct scsi_sense_hdr *sshdr, int result) { - struct scsi_device *sdev = scsi_disk(bdev->bd_disk)->device; - int error; + switch (host_byte(result)) { + case DID_TRANSPORT_MARGINAL: + case DID_TRANSPORT_DISRUPTED: + case DID_BUS_BUSY: + return PR_STS_RETRY_PATH_FAILURE; + case DID_NO_CONNECT: + return PR_STS_PATH_FAILED; + case DID_TRANSPORT_FAILFAST: + return PR_STS_PATH_FAST_FAILED; + } - error = scsi_ioctl_block_when_processing_errors(sdev, cmd, - (mode & FMODE_NDELAY) != 0); - if (error) - return error; - - /* - * Let the static ioctl translation table take care of it. + switch (status_byte(result)) { + case SAM_STAT_RESERVATION_CONFLICT: + return PR_STS_RESERVATION_CONFLICT; + case SAM_STAT_CHECK_CONDITION: + if (!scsi_sense_valid(sshdr)) + return PR_STS_IOERR; + + if (sshdr->sense_key == ILLEGAL_REQUEST && + (sshdr->asc == 0x26 || sshdr->asc == 0x24)) + return -EINVAL; + + fallthrough; + default: + return PR_STS_IOERR; + } +} + +static int sd_pr_in_command(struct block_device *bdev, u8 sa, + unsigned char *data, int data_len) +{ + struct scsi_disk *sdkp = scsi_disk(bdev->bd_disk); + struct scsi_device *sdev = sdkp->device; + struct scsi_sense_hdr sshdr; + u8 cmd[10] = { PERSISTENT_RESERVE_IN, sa }; + struct scsi_failure failure_defs[] = { + { + .sense = UNIT_ATTENTION, + .asc = SCMD_FAILURE_ASC_ANY, + .ascq = SCMD_FAILURE_ASCQ_ANY, + .allowed = 5, + .result = SAM_STAT_CHECK_CONDITION, + }, + {} + }; + struct scsi_failures failures = { + .failure_definitions = failure_defs, + }; + const struct scsi_exec_args exec_args = { + .sshdr = &sshdr, + .failures = &failures, + }; + int result; + + put_unaligned_be16(data_len, &cmd[7]); + + result = scsi_execute_cmd(sdev, cmd, REQ_OP_DRV_IN, data, data_len, + SD_TIMEOUT, sdkp->max_retries, &exec_args); + if (scsi_status_is_check_condition(result) && + scsi_sense_valid(&sshdr)) { + sdev_printk(KERN_INFO, sdev, "PR command failed: %d\n", result); + scsi_print_sense_hdr(sdev, NULL, &sshdr); + } + + if (result <= 0) + return result; + + return sd_scsi_to_pr_err(&sshdr, result); +} + +static int sd_pr_read_keys(struct block_device *bdev, struct pr_keys *keys_info) +{ + int result, i, data_offset, num_copy_keys; + u32 num_keys = keys_info->num_keys; + int data_len; + u8 *data; + + /* + * Each reservation key takes 8 bytes and there is an 8-byte header + * before the reservation key list. The total size must fit into the + * 16-bit ALLOCATION LENGTH field. */ - if (!sdev->host->hostt->compat_ioctl) - return -ENOIOCTLCMD; - return sdev->host->hostt->compat_ioctl(sdev, cmd, (void __user *)arg); + if (check_mul_overflow(num_keys, 8, &data_len) || + check_add_overflow(data_len, 8, &data_len) || + data_len > USHRT_MAX) + return -EINVAL; + + data = kzalloc(data_len, GFP_KERNEL); + if (!data) + return -ENOMEM; + + result = sd_pr_in_command(bdev, READ_KEYS, data, data_len); + if (result) + goto free_data; + + keys_info->generation = get_unaligned_be32(&data[0]); + keys_info->num_keys = get_unaligned_be32(&data[4]) / 8; + + data_offset = 8; + num_copy_keys = min(num_keys, keys_info->num_keys); + + for (i = 0; i < num_copy_keys; i++) { + keys_info->keys[i] = get_unaligned_be64(&data[data_offset]); + data_offset += 8; + } + +free_data: + kfree(data); + return result; } -#endif -static char sd_pr_type(enum pr_type type) -{ - switch (type) { - case PR_WRITE_EXCLUSIVE: - return 0x01; - case PR_EXCLUSIVE_ACCESS: - return 0x03; - case PR_WRITE_EXCLUSIVE_REG_ONLY: - return 0x05; - case PR_EXCLUSIVE_ACCESS_REG_ONLY: - return 0x06; - case PR_WRITE_EXCLUSIVE_ALL_REGS: - return 0x07; - case PR_EXCLUSIVE_ACCESS_ALL_REGS: - return 0x08; - default: +static int sd_pr_read_reservation(struct block_device *bdev, + struct pr_held_reservation *rsv) +{ + struct scsi_disk *sdkp = scsi_disk(bdev->bd_disk); + struct scsi_device *sdev = sdkp->device; + u8 data[24] = { }; + int result, len; + + result = sd_pr_in_command(bdev, READ_RESERVATION, data, sizeof(data)); + if (result) + return result; + + len = get_unaligned_be32(&data[4]); + if (!len) return 0; + + /* Make sure we have at least the key and type */ + if (len < 14) { + sdev_printk(KERN_INFO, sdev, + "READ RESERVATION failed due to short return buffer of %d bytes\n", + len); + return -EINVAL; } -}; -static int sd_pr_command(struct block_device *bdev, u8 sa, - u64 key, u64 sa_key, u8 type, u8 flags) + rsv->generation = get_unaligned_be32(&data[0]); + rsv->key = get_unaligned_be64(&data[8]); + rsv->type = scsi_pr_type_to_block(data[21] & 0x0f); + return 0; +} + +static int sd_pr_out_command(struct block_device *bdev, u8 sa, u64 key, + u64 sa_key, enum scsi_pr_type type, u8 flags) { - struct scsi_device *sdev = scsi_disk(bdev->bd_disk)->device; + struct scsi_disk *sdkp = scsi_disk(bdev->bd_disk); + struct scsi_device *sdev = sdkp->device; struct scsi_sense_hdr sshdr; + struct scsi_failure failure_defs[] = { + { + .sense = UNIT_ATTENTION, + .asc = SCMD_FAILURE_ASC_ANY, + .ascq = SCMD_FAILURE_ASCQ_ANY, + .allowed = 5, + .result = SAM_STAT_CHECK_CONDITION, + }, + {} + }; + struct scsi_failures failures = { + .failure_definitions = failure_defs, + }; + const struct scsi_exec_args exec_args = { + .sshdr = &sshdr, + .failures = &failures, + }; int result; u8 cmd[16] = { 0, }; u8 data[24] = { 0, }; @@ -1724,16 +2107,20 @@ static int sd_pr_command(struct block_device *bdev, u8 sa, put_unaligned_be64(sa_key, &data[8]); data[20] = flags; - result = scsi_execute_req(sdev, cmd, DMA_TO_DEVICE, &data, sizeof(data), - &sshdr, SD_TIMEOUT, SD_MAX_RETRIES, NULL); + result = scsi_execute_cmd(sdev, cmd, REQ_OP_DRV_OUT, &data, + sizeof(data), SD_TIMEOUT, sdkp->max_retries, + &exec_args); - if ((driver_byte(result) & DRIVER_SENSE) && - (scsi_sense_valid(&sshdr))) { + if (scsi_status_is_check_condition(result) && + scsi_sense_valid(&sshdr)) { sdev_printk(KERN_INFO, sdev, "PR command failed: %d\n", result); scsi_print_sense_hdr(sdev, NULL, &sshdr); } - return result; + if (result <= 0) + return result; + + return sd_scsi_to_pr_err(&sshdr, result); } static int sd_pr_register(struct block_device *bdev, u64 old_key, u64 new_key, @@ -1741,7 +2128,7 @@ static int sd_pr_register(struct block_device *bdev, u64 old_key, u64 new_key, { if (flags & ~PR_FL_IGNORE_KEY) return -EOPNOTSUPP; - return sd_pr_command(bdev, (flags & PR_FL_IGNORE_KEY) ? 0x06 : 0x00, + return sd_pr_out_command(bdev, (flags & PR_FL_IGNORE_KEY) ? 0x06 : 0x00, old_key, new_key, 0, (1 << 0) /* APTPL */); } @@ -1751,24 +2138,26 @@ static int sd_pr_reserve(struct block_device *bdev, u64 key, enum pr_type type, { if (flags) return -EOPNOTSUPP; - return sd_pr_command(bdev, 0x01, key, 0, sd_pr_type(type), 0); + return sd_pr_out_command(bdev, 0x01, key, 0, + block_pr_type_to_scsi(type), 0); } static int sd_pr_release(struct block_device *bdev, u64 key, enum pr_type type) { - return sd_pr_command(bdev, 0x02, key, 0, sd_pr_type(type), 0); + return sd_pr_out_command(bdev, 0x02, key, 0, + block_pr_type_to_scsi(type), 0); } static int sd_pr_preempt(struct block_device *bdev, u64 old_key, u64 new_key, enum pr_type type, bool abort) { - return sd_pr_command(bdev, abort ? 0x05 : 0x04, old_key, new_key, - sd_pr_type(type), 0); + return sd_pr_out_command(bdev, abort ? 0x05 : 0x04, old_key, new_key, + block_pr_type_to_scsi(type), 0); } static int sd_pr_clear(struct block_device *bdev, u64 key) { - return sd_pr_command(bdev, 0x03, key, 0, 0, 0); + return sd_pr_out_command(bdev, 0x03, key, 0, 0, 0); } static const struct pr_ops sd_pr_ops = { @@ -1777,20 +2166,29 @@ static const struct pr_ops sd_pr_ops = { .pr_release = sd_pr_release, .pr_preempt = sd_pr_preempt, .pr_clear = sd_pr_clear, + .pr_read_keys = sd_pr_read_keys, + .pr_read_reservation = sd_pr_read_reservation, }; +static void scsi_disk_free_disk(struct gendisk *disk) +{ + struct scsi_disk *sdkp = scsi_disk(disk); + + put_device(&sdkp->disk_dev); +} + 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 + .compat_ioctl = blkdev_compat_ptr_ioctl, .check_events = sd_check_events, - .revalidate_disk = sd_revalidate_disk, .unlock_native_capacity = sd_unlock_native_capacity, + .report_zones = sd_zbc_report_zones, + .get_unique_id = sd_get_unique_id, + .free_disk = scsi_disk_free_disk, .pr_ops = &sd_pr_ops, }; @@ -1808,7 +2206,7 @@ static const struct block_device_operations sd_fops = { **/ static void sd_eh_reset(struct scsi_cmnd *scmd) { - struct scsi_disk *sdkp = scsi_disk(scmd->request->rq_disk); + struct scsi_disk *sdkp = scsi_disk(scsi_cmd_to_rq(scmd)->q->disk); /* New SCSI EH run, reset gate variable */ sdkp->ignore_medium_access_errors = false; @@ -1828,7 +2226,7 @@ static void sd_eh_reset(struct scsi_cmnd *scmd) **/ static int sd_eh_action(struct scsi_cmnd *scmd, int eh_disp) { - struct scsi_disk *sdkp = scsi_disk(scmd->request->rq_disk); + struct scsi_disk *sdkp = scsi_disk(scsi_cmd_to_rq(scmd)->q->disk); struct scsi_device *sdev = scmd->device; if (!scsi_device_online(sdev) || @@ -1869,7 +2267,7 @@ static int sd_eh_action(struct scsi_cmnd *scmd, int eh_disp) static unsigned int sd_completed_bytes(struct scsi_cmnd *scmd) { - struct request *req = scmd->request; + struct request *req = scsi_cmd_to_rq(scmd); struct scsi_device *sdev = scmd->device; unsigned int transferred, good_bytes; u64 start_lba, end_lba, bad_lba; @@ -1924,16 +2322,19 @@ static int sd_done(struct scsi_cmnd *SCpnt) unsigned int sector_size = SCpnt->device->sector_size; unsigned int resid; struct scsi_sense_hdr sshdr; - struct scsi_disk *sdkp = scsi_disk(SCpnt->request->rq_disk); - struct request *req = SCpnt->request; + struct request *req = scsi_cmd_to_rq(SCpnt); + struct scsi_disk *sdkp = scsi_disk(req->q->disk); int sense_valid = 0; int sense_deferred = 0; switch (req_op(req)) { case REQ_OP_DISCARD: case REQ_OP_WRITE_ZEROES: - case REQ_OP_WRITE_SAME: case REQ_OP_ZONE_RESET: + case REQ_OP_ZONE_RESET_ALL: + case REQ_OP_ZONE_OPEN: + case REQ_OP_ZONE_CLOSE: + case REQ_OP_ZONE_FINISH: if (!result) { good_bytes = blk_rq_bytes(req); scsi_set_resid(SCpnt, 0); @@ -1942,16 +2343,6 @@ static int sd_done(struct scsi_cmnd *SCpnt) scsi_set_resid(SCpnt, blk_rq_bytes(req)); } break; - case REQ_OP_ZONE_REPORT: - if (!result) { - good_bytes = scsi_bufflen(SCpnt) - - scsi_get_resid(SCpnt); - scsi_set_resid(SCpnt, 0); - } else { - good_bytes = 0; - scsi_set_resid(SCpnt, blk_rq_bytes(req)); - } - break; default: /* * In case of bogus fw or device, we could end up having @@ -1963,6 +2354,7 @@ static int sd_done(struct scsi_cmnd *SCpnt) sd_printk(KERN_INFO, sdkp, "Unaligned partial completion (resid=%u, sector_sz=%u)\n", resid, sector_size); + scsi_print_command(SCpnt); resid = min(scsi_bufflen(SCpnt), round_up(resid, sector_size)); scsi_set_resid(SCpnt, resid); @@ -1976,7 +2368,7 @@ static int sd_done(struct scsi_cmnd *SCpnt) } sdkp->medium_access_timed_out = 0; - if (driver_byte(result) != DRIVER_SENSE && + if (!scsi_status_is_check_condition(result) && (!sense_valid || sense_deferred)) goto out; @@ -2009,16 +2401,14 @@ static int sd_done(struct scsi_cmnd *SCpnt) case 0x24: /* INVALID FIELD IN CDB */ switch (SCpnt->cmnd[0]) { case UNMAP: - sd_config_discard(sdkp, SD_LBP_DISABLE); + sd_disable_discard(sdkp); break; case WRITE_SAME_16: case WRITE_SAME: if (SCpnt->cmnd[1] & 8) { /* UNMAP */ - sd_config_discard(sdkp, SD_LBP_DISABLE); + sd_disable_discard(sdkp); } else { - sdkp->device->no_write_same = 1; - sd_config_write_same(sdkp); - req->__data_len = blk_rq_bytes(req); + sd_disable_write_same(sdkp); req->rq_flags |= RQF_QUIET; } break; @@ -2030,16 +2420,13 @@ static int sd_done(struct scsi_cmnd *SCpnt) } out: - if (sd_is_zoned(sdkp)) - sd_zbc_complete(SCpnt, good_bytes, &sshdr); + if (sdkp->device->type == TYPE_ZBC) + good_bytes = sd_zbc_complete(SCpnt, good_bytes, &sshdr); SCSI_LOG_HLCOMPLETE(1, scmd_printk(KERN_INFO, SCpnt, "sd_done: completed %d of %d bytes\n", good_bytes, scsi_bufflen(SCpnt))); - if (rq_data_dir(SCpnt->request) == READ && scsi_prot_sg_count(SCpnt)) - sd_dif_complete(SCpnt, good_bytes); - return good_bytes; } @@ -2049,46 +2436,70 @@ static int sd_done(struct scsi_cmnd *SCpnt) static void sd_spinup_disk(struct scsi_disk *sdkp) { - unsigned char cmd[10]; + static const u8 cmd[10] = { TEST_UNIT_READY }; unsigned long spintime_expire = 0; - int retries, spintime; + int spintime, sense_valid = 0; unsigned int the_result; struct scsi_sense_hdr sshdr; - int sense_valid = 0; + struct scsi_failure failure_defs[] = { + /* Do not retry Medium Not Present */ + { + .sense = UNIT_ATTENTION, + .asc = 0x3A, + .ascq = SCMD_FAILURE_ASCQ_ANY, + .result = SAM_STAT_CHECK_CONDITION, + }, + { + .sense = NOT_READY, + .asc = 0x3A, + .ascq = SCMD_FAILURE_ASCQ_ANY, + .result = SAM_STAT_CHECK_CONDITION, + }, + /* Retry when scsi_status_is_good would return false 3 times */ + { + .result = SCMD_FAILURE_STAT_ANY, + .allowed = 3, + }, + {} + }; + struct scsi_failures failures = { + .failure_definitions = failure_defs, + }; + const struct scsi_exec_args exec_args = { + .sshdr = &sshdr, + .failures = &failures, + }; spintime = 0; /* Spin up drives, as required. Only do this at boot time */ /* Spinup needs to be done for module loads too. */ do { - retries = 0; + bool media_was_present = sdkp->media_present; + + scsi_failures_reset_retries(&failures); - do { - cmd[0] = TEST_UNIT_READY; - memset((void *) &cmd[1], 0, 9); + the_result = scsi_execute_cmd(sdkp->device, cmd, REQ_OP_DRV_IN, + NULL, 0, SD_TIMEOUT, + sdkp->max_retries, &exec_args); - the_result = scsi_execute_req(sdkp->device, cmd, - DMA_NONE, NULL, 0, - &sshdr, SD_TIMEOUT, - SD_MAX_RETRIES, NULL); + if (the_result > 0) { /* - * If the drive has indicated to us that it - * doesn't have any media in it, don't bother - * with any more polling. + * 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)) + if (media_not_present(sdkp, &sshdr)) { + if (media_was_present) + sd_printk(KERN_NOTICE, sdkp, + "Media removed, stopped polling\n"); return; + } + sense_valid = scsi_sense_valid(&sshdr); + } - if (the_result) - sense_valid = scsi_sense_valid(&sshdr); - retries++; - } while (retries < 3 && - (!scsi_status_is_good(the_result) || - ((driver_byte(the_result) & DRIVER_SENSE) && - sense_valid && sshdr.sense_key == UNIT_ATTENTION))); - - if ((driver_byte(the_result) & DRIVER_SENSE) == 0) { + if (!scsi_status_is_check_condition(the_result)) { /* no sense, TUR either succeeded or failed * with a status error */ if(!spintime && !scsi_status_is_good(the_result)) { @@ -2111,27 +2522,35 @@ sd_spinup_disk(struct scsi_disk *sdkp) break; /* standby */ if (sshdr.asc == 4 && sshdr.ascq == 0xc) break; /* unavailable */ + if (sshdr.asc == 4 && sshdr.ascq == 0x1b) + break; /* sanitize in progress */ + if (sshdr.asc == 4 && sshdr.ascq == 0x24) + break; /* depopulation in progress */ + if (sshdr.asc == 4 && sshdr.ascq == 0x25) + break; /* depopulation restoration in progress */ /* * Issue command to spin up drive when not ready */ if (!spintime) { + /* Return immediately and start spin cycle */ + const u8 start_cmd[10] = { + [0] = START_STOP, + [1] = 1, + [4] = sdkp->device->start_stop_pwr_cond ? + 0x11 : 1, + }; + 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, - NULL); + scsi_execute_cmd(sdkp->device, start_cmd, + REQ_OP_DRV_IN, NULL, 0, + SD_TIMEOUT, sdkp->max_retries, + &exec_args); spintime_expire = jiffies + 100 * HZ; spintime = 1; } /* Wait 1 second for next try */ msleep(1000); - printk("."); + printk(KERN_CONT "."); /* * Wait for USB flash devices with slow firmware. @@ -2161,9 +2580,9 @@ sd_spinup_disk(struct scsi_disk *sdkp) if (spintime) { if (scsi_status_is_good(the_result)) - printk("ready\n"); + printk(KERN_CONT "ready\n"); else - printk("not responding...\n"); + printk(KERN_CONT "not responding...\n"); } } @@ -2174,45 +2593,54 @@ 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; + if (scsi_device_protection(sdp) == 0 || (buffer[12] & 1) == 0) { + sdkp->protection_type = 0; + return 0; + } type = ((buffer[12] >> 1) & 7) + 1; /* P_TYPE 0 = Type 1 */ - if (type > T10_PI_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; - } + if (type > T10_PI_TYPE3_PROTECTION) { + sd_printk(KERN_ERR, sdkp, "formatted with unsupported" \ + " protection type %u. Disabling disk!\n", + type); + sdkp->protection_type = 0; + return -ENODEV; + } sdkp->protection_type = type; - return ret; + return 0; +} + +static void sd_config_protection(struct scsi_disk *sdkp, + struct queue_limits *lim) +{ + struct scsi_device *sdp = sdkp->device; + + if (IS_ENABLED(CONFIG_BLK_DEV_INTEGRITY)) + sd_dif_config_host(sdkp, lim); + + if (!sdkp->protection_type) + return; + + if (!scsi_host_dif_capable(sdp->host, sdkp->protection_type)) { + sd_first_printk(KERN_NOTICE, sdkp, + "Disabling DIF Type %u protection\n", + sdkp->protection_type); + sdkp->protection_type = 0; + } + + sd_first_printk(KERN_NOTICE, sdkp, "Enabling DIF Type %u protection\n", + sdkp->protection_type); } static void read_capacity_error(struct scsi_disk *sdkp, struct scsi_device *sdp, struct scsi_sense_hdr *sshdr, int sense_valid, int the_result) { - if (driver_byte(the_result) & DRIVER_SENSE) + if (sense_valid) sd_print_sense_hdr(sdkp, sshdr); else sd_printk(KERN_NOTICE, sdkp, "Sense not available.\n"); @@ -2240,27 +2668,14 @@ static void read_capacity_error(struct scsi_disk *sdkp, struct scsi_device *sdp, #define READ_CAPACITY_RETRIES_ON_RESET 10 -/* - * Ensure that we don't overflow sector_t when CONFIG_LBDAF is not set - * and the reported logical block size is bigger than 512 bytes. Note - * that last_sector is a u64 and therefore logical_to_sectors() is not - * applicable. - */ -static bool sd_addressable_capacity(u64 lba, unsigned int sector_size) -{ - u64 last_sector = (lba + 1ULL) << (ilog2(sector_size) - 9); - - if (sizeof(sector_t) == 4 && last_sector > U32_MAX) - return false; - - return true; -} - static int read_capacity_16(struct scsi_disk *sdkp, struct scsi_device *sdp, - unsigned char *buffer) + struct queue_limits *lim, unsigned char *buffer) { unsigned char cmd[16]; struct scsi_sense_hdr sshdr; + const struct scsi_exec_args exec_args = { + .sshdr = &sshdr, + }; int sense_valid = 0; int the_result; int retries = 3, reset_retries = READ_CAPACITY_RETRIES_ON_RESET; @@ -2278,14 +2693,13 @@ static int read_capacity_16(struct scsi_disk *sdkp, struct scsi_device *sdp, 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; + the_result = scsi_execute_cmd(sdp, cmd, REQ_OP_DRV_IN, + buffer, RC16_LEN, SD_TIMEOUT, + sdkp->max_retries, &exec_args); + if (the_result > 0) { + 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 && @@ -2321,14 +2735,6 @@ static int read_capacity_16(struct scsi_disk *sdkp, struct scsi_device *sdp, return -ENODEV; } - if (!sd_addressable_capacity(lba, sector_size)) { - 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; @@ -2337,7 +2743,7 @@ static int read_capacity_16(struct scsi_disk *sdkp, struct scsi_device *sdp, /* Lowest aligned logical block */ alignment = ((buffer[14] & 0x3f) << 8 | buffer[15]) * sector_size; - blk_queue_alignment_offset(sdp->request_queue, alignment); + lim->alignment_offset = alignment; if (alignment && sdkp->first_scan) sd_printk(KERN_NOTICE, sdkp, "physical block alignment offset: %u\n", alignment); @@ -2347,8 +2753,6 @@ static int read_capacity_16(struct scsi_disk *sdkp, struct scsi_device *sdp, if (buffer[14] & 0x40) /* LBPRZ */ sdkp->lbprz = 1; - - sd_config_discard(sdkp, SD_LBP_WS16); } sdkp->capacity = lba + 1; @@ -2358,39 +2762,58 @@ static int read_capacity_16(struct scsi_disk *sdkp, struct scsi_device *sdp, static int read_capacity_10(struct scsi_disk *sdkp, struct scsi_device *sdp, unsigned char *buffer) { - unsigned char cmd[16]; + static const u8 cmd[10] = { READ_CAPACITY }; struct scsi_sense_hdr sshdr; + struct scsi_failure failure_defs[] = { + /* Do not retry Medium Not Present */ + { + .sense = UNIT_ATTENTION, + .asc = 0x3A, + .result = SAM_STAT_CHECK_CONDITION, + }, + { + .sense = NOT_READY, + .asc = 0x3A, + .result = SAM_STAT_CHECK_CONDITION, + }, + /* Device reset might occur several times so retry a lot */ + { + .sense = UNIT_ATTENTION, + .asc = 0x29, + .allowed = READ_CAPACITY_RETRIES_ON_RESET, + .result = SAM_STAT_CHECK_CONDITION, + }, + /* Any other error not listed above retry 3 times */ + { + .result = SCMD_FAILURE_RESULT_ANY, + .allowed = 3, + }, + {} + }; + struct scsi_failures failures = { + .failure_definitions = failure_defs, + }; + const struct scsi_exec_args exec_args = { + .sshdr = &sshdr, + .failures = &failures, + }; 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); + memset(buffer, 0, 8); - the_result = scsi_execute_req(sdp, cmd, DMA_FROM_DEVICE, - buffer, 8, &sshdr, - SD_TIMEOUT, SD_MAX_RETRIES, NULL); + the_result = scsi_execute_cmd(sdp, cmd, REQ_OP_DRV_IN, buffer, + 8, SD_TIMEOUT, sdkp->max_retries, + &exec_args); + + if (the_result > 0) { + sense_valid = scsi_sense_valid(&sshdr); if (media_not_present(sdkp, &sshdr)) return -ENODEV; - - 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) { sd_print_result(sdkp, "Read Capacity(10) failed", the_result); @@ -2410,14 +2833,6 @@ static int read_capacity_10(struct scsi_disk *sdkp, struct scsi_device *sdp, return sector_size; } - if (!sd_addressable_capacity(lba, sector_size)) { - 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; @@ -2440,13 +2855,14 @@ static int sd_try_rc16_first(struct scsi_device *sdp) * read disk capacity */ static void -sd_read_capacity(struct scsi_disk *sdkp, unsigned char *buffer) +sd_read_capacity(struct scsi_disk *sdkp, struct queue_limits *lim, + unsigned char *buffer) { int sector_size; struct scsi_device *sdp = sdkp->device; if (sd_try_rc16_first(sdp)) { - sector_size = read_capacity_16(sdkp, sdp, buffer); + sector_size = read_capacity_16(sdkp, sdp, lim, buffer); if (sector_size == -EOVERFLOW) goto got_data; if (sector_size == -ENODEV) @@ -2466,7 +2882,7 @@ sd_read_capacity(struct scsi_disk *sdkp, unsigned char *buffer) 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); + sector_size = read_capacity_16(sdkp, sdp, lim, buffer); if (sector_size < 0) { sd_printk(KERN_NOTICE, sdkp, "Using 0xffffffff as device size\n"); @@ -2474,6 +2890,8 @@ sd_read_capacity(struct scsi_disk *sdkp, unsigned char *buffer) sector_size = old_sector_size; goto got_data; } + /* Remember that READ CAPACITY(16) succeeded */ + sdp->try_rc_10_first = 0; } } @@ -2523,9 +2941,8 @@ got_data: */ sector_size = 512; } - blk_queue_logical_block_size(sdp->request_queue, sector_size); - blk_queue_physical_block_size(sdp->request_queue, - sdkp->physical_block_size); + lim->logical_block_size = sector_size; + lim->physical_block_size = sdkp->physical_block_size; sdkp->device->sector_size = sector_size; if (sdkp->capacity > 0xffffffff) @@ -2543,36 +2960,40 @@ sd_print_capacity(struct scsi_disk *sdkp, int sector_size = sdkp->device->sector_size; char cap_str_2[10], cap_str_10[10]; + if (!sdkp->first_scan && old_capacity == sdkp->capacity) + return; + string_get_size(sdkp->capacity, sector_size, STRING_UNITS_2, cap_str_2, sizeof(cap_str_2)); string_get_size(sdkp->capacity, sector_size, - 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); + STRING_UNITS_10, cap_str_10, sizeof(cap_str_10)); - if (sdkp->physical_block_size != sector_size) - sd_printk(KERN_NOTICE, sdkp, - "%u-byte physical blocks\n", - sdkp->physical_block_size); + 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); - sd_zbc_print_zones(sdkp); - } + if (sdkp->physical_block_size != sector_size) + sd_printk(KERN_NOTICE, sdkp, + "%u-byte physical blocks\n", + sdkp->physical_block_size); } /* called with buffer of length 512 */ static inline int -sd_do_mode_sense(struct scsi_device *sdp, int dbd, int modepage, +sd_do_mode_sense(struct scsi_disk *sdkp, int dbd, int modepage, unsigned char *buffer, int len, struct scsi_mode_data *data, struct scsi_sense_hdr *sshdr) { - return scsi_mode_sense(sdp, dbd, modepage, buffer, len, - SD_TIMEOUT, SD_MAX_RETRIES, data, - sshdr); + /* + * If we must use MODE SENSE(10), make sure that the buffer length + * is at least 8 bytes so that the mode sense header fits. + */ + if (sdkp->device->use_10_for_ms && len < 8) + len = 8; + + return scsi_mode_sense(sdkp->device, dbd, modepage, 0, buffer, len, + SD_TIMEOUT, sdkp->max_retries, data, sshdr); } /* @@ -2594,14 +3015,14 @@ sd_read_write_protect_flag(struct scsi_disk *sdkp, unsigned char *buffer) } if (sdp->use_192_bytes_for_3f) { - res = sd_do_mode_sense(sdp, 0, 0x3F, buffer, 192, &data, NULL); + res = sd_do_mode_sense(sdkp, 0, 0x3F, buffer, 192, &data, NULL); } else { /* * First attempt: ask for all pages (0x3F), but only 4 bytes. * We have to start carefully: some devices hang if we ask * for more than is available. */ - res = sd_do_mode_sense(sdp, 0, 0x3F, buffer, 4, &data, NULL); + res = sd_do_mode_sense(sdkp, 0, 0x3F, buffer, 4, &data, NULL); /* * Second attempt: ask for page 0 When only page 0 is @@ -2609,18 +3030,18 @@ sd_read_write_protect_flag(struct scsi_disk *sdkp, unsigned char *buffer) * 5: Illegal Request, Sense Code 24: Invalid field in * CDB. */ - if (!scsi_status_is_good(res)) - res = sd_do_mode_sense(sdp, 0, 0, buffer, 4, &data, NULL); + if (res < 0) + res = sd_do_mode_sense(sdkp, 0, 0, buffer, 4, &data, NULL); /* * Third attempt: ask 255 bytes, as we did earlier. */ - if (!scsi_status_is_good(res)) - res = sd_do_mode_sense(sdp, 0, 0x3F, buffer, 255, + if (res < 0) + res = sd_do_mode_sense(sdkp, 0, 0x3F, buffer, 255, &data, NULL); } - if (!scsi_status_is_good(res)) { + if (res < 0) { sd_first_printk(KERN_WARNING, sdkp, "Test WP failed, assume Write Enabled\n"); } else { @@ -2678,10 +3099,10 @@ sd_read_cache_type(struct scsi_disk *sdkp, unsigned char *buffer) } /* cautiously ask */ - res = sd_do_mode_sense(sdp, dbd, modepage, buffer, first_len, + res = sd_do_mode_sense(sdkp, dbd, modepage, buffer, first_len, &data, &sshdr); - if (!scsi_status_is_good(res)) + if (res < 0) goto bad_sense; if (!data.header_length) { @@ -2710,10 +3131,10 @@ sd_read_cache_type(struct scsi_disk *sdkp, unsigned char *buffer) /* Get the data */ if (len > first_len) - res = sd_do_mode_sense(sdp, dbd, modepage, buffer, len, + res = sd_do_mode_sense(sdkp, dbd, modepage, buffer, len, &data, &sshdr); - if (scsi_status_is_good(res)) { + if (!res) { int offset = data.header_length + data.block_descriptor_length; while (offset < len) { @@ -2748,7 +3169,8 @@ sd_read_cache_type(struct scsi_disk *sdkp, unsigned char *buffer) } } - sd_first_printk(KERN_ERR, sdkp, "No Caching mode page found\n"); + sd_first_printk(KERN_WARNING, sdkp, + "No Caching mode page found\n"); goto defaults; Page_found: @@ -2788,7 +3210,7 @@ sd_read_cache_type(struct scsi_disk *sdkp, unsigned char *buffer) } bad_sense: - if (scsi_sense_valid(&sshdr) && + if (res == -EIO && scsi_sense_valid(&sshdr) && sshdr.sense_key == ILLEGAL_REQUEST && sshdr.asc == 0x24 && sshdr.ascq == 0x0) /* Invalid field in CDB */ @@ -2803,7 +3225,7 @@ defaults: "Assuming drive cache: write back\n"); sdkp->WCE = 1; } else { - sd_first_printk(KERN_ERR, sdkp, + sd_first_printk(KERN_WARNING, sdkp, "Assuming drive cache: write through\n"); sdkp->WCE = 0; } @@ -2811,6 +3233,75 @@ defaults: sdkp->DPOFUA = 0; } +static bool sd_is_perm_stream(struct scsi_disk *sdkp, unsigned int stream_id) +{ + u8 cdb[16] = { SERVICE_ACTION_IN_16, SAI_GET_STREAM_STATUS }; + struct { + struct scsi_stream_status_header h; + struct scsi_stream_status s; + } buf; + struct scsi_device *sdev = sdkp->device; + struct scsi_sense_hdr sshdr; + const struct scsi_exec_args exec_args = { + .sshdr = &sshdr, + }; + int res; + + put_unaligned_be16(stream_id, &cdb[4]); + put_unaligned_be32(sizeof(buf), &cdb[10]); + + res = scsi_execute_cmd(sdev, cdb, REQ_OP_DRV_IN, &buf, sizeof(buf), + SD_TIMEOUT, sdkp->max_retries, &exec_args); + if (res < 0) + return false; + if (scsi_status_is_check_condition(res) && scsi_sense_valid(&sshdr)) + sd_print_sense_hdr(sdkp, &sshdr); + if (res) + return false; + if (get_unaligned_be32(&buf.h.len) < sizeof(struct scsi_stream_status)) + return false; + return buf.s.perm; +} + +static void sd_read_io_hints(struct scsi_disk *sdkp, unsigned char *buffer) +{ + struct scsi_device *sdp = sdkp->device; + const struct scsi_io_group_descriptor *desc, *start, *end; + u16 permanent_stream_count_old; + struct scsi_sense_hdr sshdr; + struct scsi_mode_data data; + int res; + + if (sdp->sdev_bflags & BLIST_SKIP_IO_HINTS) + return; + + res = scsi_mode_sense(sdp, /*dbd=*/0x8, /*modepage=*/0x0a, + /*subpage=*/0x05, buffer, SD_BUF_SIZE, SD_TIMEOUT, + sdkp->max_retries, &data, &sshdr); + if (res < 0) + return; + start = (void *)buffer + data.header_length + 16; + end = (void *)buffer + ALIGN_DOWN(data.header_length + data.length, + sizeof(*end)); + /* + * From "SBC-5 Constrained Streams with Data Lifetimes": Device severs + * should assign the lowest numbered stream identifiers to permanent + * streams. + */ + for (desc = start; desc < end; desc++) + if (!desc->st_enble || !sd_is_perm_stream(sdkp, desc - start)) + break; + permanent_stream_count_old = sdkp->permanent_stream_count; + sdkp->permanent_stream_count = desc - start; + if (sdkp->rscs && sdkp->permanent_stream_count < 2) + sd_printk(KERN_INFO, sdkp, + "Unexpected: RSCS has been set and the permanent stream count is %u\n", + sdkp->permanent_stream_count); + else if (sdkp->permanent_stream_count != permanent_stream_count_old) + sd_printk(KERN_INFO, sdkp, "permanent stream count = %d\n", + sdkp->permanent_stream_count); +} + /* * The ATO bit indicates whether the DIF application tag is available * for use by the operating system. @@ -2828,15 +3319,15 @@ static void sd_read_app_tag_own(struct scsi_disk *sdkp, unsigned char *buffer) if (sdkp->protection_type == 0) return; - res = scsi_mode_sense(sdp, 1, 0x0a, buffer, 36, SD_TIMEOUT, - SD_MAX_RETRIES, &data, &sshdr); + res = scsi_mode_sense(sdp, 1, 0x0a, 0, buffer, 36, SD_TIMEOUT, + sdkp->max_retries, &data, &sshdr); - if (!scsi_status_is_good(res) || !data.header_length || + if (res < 0 || !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)) + if (res == -EIO && scsi_sense_valid(&sshdr)) sd_print_sense_hdr(sdkp, &sshdr); return; @@ -2857,118 +3348,123 @@ static void sd_read_app_tag_own(struct scsi_disk *sdkp, unsigned char *buffer) return; } -/** - * sd_read_block_limits - Query disk device for preferred I/O sizes. - * @sdkp: disk to query +static unsigned int sd_discard_mode(struct scsi_disk *sdkp) +{ + if (!sdkp->lbpme) + return SD_LBP_FULL; + + if (!sdkp->lbpvpd) { + /* LBP VPD page not provided */ + if (sdkp->max_unmap_blocks) + return SD_LBP_UNMAP; + return SD_LBP_WS16; + } + + /* LBP VPD page tells us what to use */ + if (sdkp->lbpu && sdkp->max_unmap_blocks) + return SD_LBP_UNMAP; + if (sdkp->lbpws) + return SD_LBP_WS16; + if (sdkp->lbpws10) + return SD_LBP_WS10; + return SD_LBP_DISABLE; +} + +/* + * Query disk device for preferred I/O sizes. */ -static void sd_read_block_limits(struct scsi_disk *sdkp) +static void sd_read_block_limits(struct scsi_disk *sdkp, + struct queue_limits *lim) { - unsigned int sector_sz = sdkp->device->sector_size; - const int vpd_len = 64; - unsigned char *buffer = kmalloc(vpd_len, GFP_KERNEL); + struct scsi_vpd *vpd; - if (!buffer || - /* Block Limits VPD */ - scsi_get_vpd_page(sdkp->device, 0xb0, buffer, vpd_len)) - goto out; + rcu_read_lock(); - blk_queue_io_min(sdkp->disk->queue, - get_unaligned_be16(&buffer[6]) * sector_sz); + vpd = rcu_dereference(sdkp->device->vpd_pgb0); + if (!vpd || vpd->len < 16) + goto out; - sdkp->max_xfer_blocks = get_unaligned_be32(&buffer[8]); - sdkp->opt_xfer_blocks = get_unaligned_be32(&buffer[12]); + sdkp->min_xfer_blocks = get_unaligned_be16(&vpd->data[6]); + sdkp->max_xfer_blocks = get_unaligned_be32(&vpd->data[8]); + sdkp->opt_xfer_blocks = get_unaligned_be32(&vpd->data[12]); - if (buffer[3] == 0x3c) { + if (vpd->len >= 64) { unsigned int lba_count, desc_count; - sdkp->max_ws_blocks = (u32)get_unaligned_be64(&buffer[36]); + sdkp->max_ws_blocks = (u32)get_unaligned_be64(&vpd->data[36]); if (!sdkp->lbpme) - goto out; + goto config_atomic; - lba_count = get_unaligned_be32(&buffer[20]); - desc_count = get_unaligned_be32(&buffer[24]); + lba_count = get_unaligned_be32(&vpd->data[20]); + desc_count = get_unaligned_be32(&vpd->data[24]); if (lba_count && desc_count) sdkp->max_unmap_blocks = lba_count; - sdkp->unmap_granularity = get_unaligned_be32(&buffer[28]); + sdkp->unmap_granularity = get_unaligned_be32(&vpd->data[28]); - if (buffer[32] & 0x80) + if (vpd->data[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 if (sdkp->lbpu && sdkp->max_unmap_blocks) - sd_config_discard(sdkp, SD_LBP_UNMAP); - else - sd_config_discard(sdkp, SD_LBP_DISABLE); - } + get_unaligned_be32(&vpd->data[32]) & ~(1 << 31); + +config_atomic: + sdkp->max_atomic = get_unaligned_be32(&vpd->data[44]); + sdkp->atomic_alignment = get_unaligned_be32(&vpd->data[48]); + sdkp->atomic_granularity = get_unaligned_be32(&vpd->data[52]); + sdkp->max_atomic_with_boundary = get_unaligned_be32(&vpd->data[56]); + sdkp->max_atomic_boundary = get_unaligned_be32(&vpd->data[60]); + + sd_config_atomic(sdkp, lim); } out: - kfree(buffer); + rcu_read_unlock(); } -/** - * sd_read_block_characteristics - Query block dev. characteristics - * @sdkp: disk to query - */ -static void sd_read_block_characteristics(struct scsi_disk *sdkp) +/* Parse the Block Limits Extension VPD page (0xb7) */ +static void sd_read_block_limits_ext(struct scsi_disk *sdkp) { - struct request_queue *q = sdkp->disk->queue; - unsigned char *buffer; - u16 rot; - const int vpd_len = 64; + struct scsi_vpd *vpd; - buffer = kmalloc(vpd_len, GFP_KERNEL); + rcu_read_lock(); + vpd = rcu_dereference(sdkp->device->vpd_pgb7); + if (vpd && vpd->len >= 6) + sdkp->rscs = vpd->data[5] & 1; + rcu_read_unlock(); +} - if (!buffer || - /* Block Device Characteristics VPD */ - scsi_get_vpd_page(sdkp->device, 0xb1, buffer, vpd_len)) - goto out; +/* Query block device characteristics */ +static void sd_read_block_characteristics(struct scsi_disk *sdkp, + struct queue_limits *lim) +{ + struct scsi_vpd *vpd; + u16 rot; - rot = get_unaligned_be16(&buffer[4]); + rcu_read_lock(); + vpd = rcu_dereference(sdkp->device->vpd_pgb1); - if (rot == 1) { - queue_flag_set_unlocked(QUEUE_FLAG_NONROT, q); - queue_flag_clear_unlocked(QUEUE_FLAG_ADD_RANDOM, q); + if (!vpd || vpd->len <= 8) { + rcu_read_unlock(); + return; } - if (sdkp->device->type == TYPE_ZBC) { - /* Host-managed */ - q->limits.zoned = BLK_ZONED_HM; - } else { - sdkp->zoned = (buffer[8] >> 4) & 3; - if (sdkp->zoned == 1) - /* Host-aware */ - q->limits.zoned = BLK_ZONED_HA; - else - /* - * Treat drive-managed devices as - * regular block devices. - */ - q->limits.zoned = BLK_ZONED_NONE; - } - if (blk_queue_is_zoned(q) && sdkp->first_scan) - sd_printk(KERN_NOTICE, sdkp, "Host-%s zoned block device\n", - q->limits.zoned == BLK_ZONED_HM ? "managed" : "aware"); + rot = get_unaligned_be16(&vpd->data[4]); + sdkp->zoned = (vpd->data[8] >> 4) & 3; + rcu_read_unlock(); - out: - kfree(buffer); + if (rot == 1) + lim->features &= ~(BLK_FEAT_ROTATIONAL | BLK_FEAT_ADD_RANDOM); + + if (!sdkp->first_scan) + return; + + if (sdkp->device->type == TYPE_ZBC) + sd_printk(KERN_NOTICE, sdkp, "Host-managed zoned block device\n"); + else if (sdkp->zoned == 1) + sd_printk(KERN_NOTICE, sdkp, "Host-aware SMR disk used as regular disk\n"); + else if (sdkp->zoned == 2) + sd_printk(KERN_NOTICE, sdkp, "Drive-managed SMR disk\n"); } /** @@ -2977,24 +3473,24 @@ static void sd_read_block_characteristics(struct scsi_disk *sdkp) */ static void sd_read_block_provisioning(struct scsi_disk *sdkp) { - unsigned char *buffer; - const int vpd_len = 8; + struct scsi_vpd *vpd; if (sdkp->lbpme == 0) return; - buffer = kmalloc(vpd_len, GFP_KERNEL); + rcu_read_lock(); + vpd = rcu_dereference(sdkp->device->vpd_pgb2); - if (!buffer || scsi_get_vpd_page(sdkp->device, 0xb2, buffer, vpd_len)) - goto out; + if (!vpd || vpd->len < 8) { + rcu_read_unlock(); + return; + } 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); + sdkp->lbpu = (vpd->data[5] >> 7) & 1; /* UNMAP */ + sdkp->lbpws = (vpd->data[5] >> 6) & 1; /* WRITE SAME(16) w/ UNMAP */ + sdkp->lbpws10 = (vpd->data[5] >> 5) & 1; /* WRITE SAME(10) w/ UNMAP */ + rcu_read_unlock(); } static void sd_read_write_same(struct scsi_disk *sdkp, unsigned char *buffer) @@ -3007,24 +3503,21 @@ static void sd_read_write_same(struct scsi_disk *sdkp, unsigned char *buffer) 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; - + if (scsi_report_opcode(sdev, buffer, SD_BUF_SIZE, INQUIRY, 0) < 0) { 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). + /* + * Disable WRITE SAME if REPORT SUPPORTED OPERATION CODES is + * unsupported and this is an ATA device. */ - if (!scsi_get_vpd_page(sdev, 0x89, buffer, vpd_buf_len)) + if (sdev->is_ata) sdev->no_write_same = 1; } - if (scsi_report_opcode(sdev, buffer, SD_BUF_SIZE, WRITE_SAME_16) == 1) + if (scsi_report_opcode(sdev, buffer, SD_BUF_SIZE, WRITE_SAME_16, 0) == 1) sdkp->ws16 = 1; - if (scsi_report_opcode(sdev, buffer, SD_BUF_SIZE, WRITE_SAME) == 1) + if (scsi_report_opcode(sdev, buffer, SD_BUF_SIZE, WRITE_SAME, 0) == 1) sdkp->ws10 = 1; } @@ -3036,25 +3529,217 @@ static void sd_read_security(struct scsi_disk *sdkp, unsigned char *buffer) return; if (scsi_report_opcode(sdev, buffer, SD_BUF_SIZE, - SECURITY_PROTOCOL_IN) == 1 && + SECURITY_PROTOCOL_IN, 0) == 1 && scsi_report_opcode(sdev, buffer, SD_BUF_SIZE, - SECURITY_PROTOCOL_OUT) == 1) + SECURITY_PROTOCOL_OUT, 0) == 1) sdkp->security = 1; } +static inline sector_t sd64_to_sectors(struct scsi_disk *sdkp, u8 *buf) +{ + return logical_to_sectors(sdkp->device, get_unaligned_be64(buf)); +} + +/** + * sd_read_cpr - Query concurrent positioning ranges + * @sdkp: disk to query + */ +static void sd_read_cpr(struct scsi_disk *sdkp) +{ + struct blk_independent_access_ranges *iars = NULL; + unsigned char *buffer = NULL; + unsigned int nr_cpr = 0; + int i, vpd_len, buf_len = SD_BUF_SIZE; + u8 *desc; + + /* + * We need to have the capacity set first for the block layer to be + * able to check the ranges. + */ + if (sdkp->first_scan) + return; + + if (!sdkp->capacity) + goto out; + + /* + * Concurrent Positioning Ranges VPD: there can be at most 256 ranges, + * leading to a maximum page size of 64 + 256*32 bytes. + */ + buf_len = 64 + 256*32; + buffer = kmalloc(buf_len, GFP_KERNEL); + if (!buffer || scsi_get_vpd_page(sdkp->device, 0xb9, buffer, buf_len)) + goto out; + + /* We must have at least a 64B header and one 32B range descriptor */ + vpd_len = get_unaligned_be16(&buffer[2]) + 4; + if (vpd_len > buf_len || vpd_len < 64 + 32 || (vpd_len & 31)) { + sd_printk(KERN_ERR, sdkp, + "Invalid Concurrent Positioning Ranges VPD page\n"); + goto out; + } + + nr_cpr = (vpd_len - 64) / 32; + if (nr_cpr == 1) { + nr_cpr = 0; + goto out; + } + + iars = disk_alloc_independent_access_ranges(sdkp->disk, nr_cpr); + if (!iars) { + nr_cpr = 0; + goto out; + } + + desc = &buffer[64]; + for (i = 0; i < nr_cpr; i++, desc += 32) { + if (desc[0] != i) { + sd_printk(KERN_ERR, sdkp, + "Invalid Concurrent Positioning Range number\n"); + nr_cpr = 0; + break; + } + + iars->ia_range[i].sector = sd64_to_sectors(sdkp, desc + 8); + iars->ia_range[i].nr_sectors = sd64_to_sectors(sdkp, desc + 16); + } + +out: + disk_set_independent_access_ranges(sdkp->disk, iars); + if (nr_cpr && sdkp->nr_actuators != nr_cpr) { + sd_printk(KERN_NOTICE, sdkp, + "%u concurrent positioning ranges\n", nr_cpr); + sdkp->nr_actuators = nr_cpr; + } + + kfree(buffer); +} + +static bool sd_validate_min_xfer_size(struct scsi_disk *sdkp) +{ + struct scsi_device *sdp = sdkp->device; + unsigned int min_xfer_bytes = + logical_to_bytes(sdp, sdkp->min_xfer_blocks); + + if (sdkp->min_xfer_blocks == 0) + return false; + + if (min_xfer_bytes & (sdkp->physical_block_size - 1)) { + sd_first_printk(KERN_WARNING, sdkp, + "Preferred minimum I/O size %u bytes not a " \ + "multiple of physical block size (%u bytes)\n", + min_xfer_bytes, sdkp->physical_block_size); + sdkp->min_xfer_blocks = 0; + return false; + } + + sd_first_printk(KERN_INFO, sdkp, "Preferred minimum I/O size %u bytes\n", + min_xfer_bytes); + return true; +} + +/* + * Determine the device's preferred I/O size for reads and writes + * unless the reported value is unreasonably small, large, not a + * multiple of the physical block size, or simply garbage. + */ +static bool sd_validate_opt_xfer_size(struct scsi_disk *sdkp, + unsigned int dev_max) +{ + struct scsi_device *sdp = sdkp->device; + unsigned int opt_xfer_bytes = + logical_to_bytes(sdp, sdkp->opt_xfer_blocks); + unsigned int min_xfer_bytes = + logical_to_bytes(sdp, sdkp->min_xfer_blocks); + + if (sdkp->opt_xfer_blocks == 0) + return false; + + if (sdkp->opt_xfer_blocks > dev_max) { + sd_first_printk(KERN_WARNING, sdkp, + "Optimal transfer size %u logical blocks " \ + "> dev_max (%u logical blocks)\n", + sdkp->opt_xfer_blocks, dev_max); + return false; + } + + if (sdkp->opt_xfer_blocks > SD_DEF_XFER_BLOCKS) { + sd_first_printk(KERN_WARNING, sdkp, + "Optimal transfer size %u logical blocks " \ + "> sd driver limit (%u logical blocks)\n", + sdkp->opt_xfer_blocks, SD_DEF_XFER_BLOCKS); + return false; + } + + if (opt_xfer_bytes < PAGE_SIZE) { + sd_first_printk(KERN_WARNING, sdkp, + "Optimal transfer size %u bytes < " \ + "PAGE_SIZE (%u bytes)\n", + opt_xfer_bytes, (unsigned int)PAGE_SIZE); + return false; + } + + if (min_xfer_bytes && opt_xfer_bytes % min_xfer_bytes) { + sd_first_printk(KERN_WARNING, sdkp, + "Optimal transfer size %u bytes not a " \ + "multiple of preferred minimum block " \ + "size (%u bytes)\n", + opt_xfer_bytes, min_xfer_bytes); + return false; + } + + if (opt_xfer_bytes & (sdkp->physical_block_size - 1)) { + sd_first_printk(KERN_WARNING, sdkp, + "Optimal transfer size %u bytes not a " \ + "multiple of physical block size (%u bytes)\n", + opt_xfer_bytes, sdkp->physical_block_size); + return false; + } + + sd_first_printk(KERN_INFO, sdkp, "Optimal transfer size %u bytes\n", + opt_xfer_bytes); + return true; +} + +static void sd_read_block_zero(struct scsi_disk *sdkp) +{ + struct scsi_device *sdev = sdkp->device; + unsigned int buf_len = sdev->sector_size; + u8 *buffer, cmd[16] = { }; + + buffer = kmalloc(buf_len, GFP_KERNEL); + if (!buffer) + return; + + if (sdev->use_16_for_rw) { + cmd[0] = READ_16; + put_unaligned_be64(0, &cmd[2]); /* Logical block address 0 */ + put_unaligned_be32(1, &cmd[10]);/* Transfer 1 logical block */ + } else { + cmd[0] = READ_10; + put_unaligned_be32(0, &cmd[2]); /* Logical block address 0 */ + put_unaligned_be16(1, &cmd[7]); /* Transfer 1 logical block */ + } + + scsi_execute_cmd(sdkp->device, cmd, REQ_OP_DRV_IN, buffer, buf_len, + SD_TIMEOUT, sdkp->max_retries, NULL); + kfree(buffer); +} + /** * sd_revalidate_disk - called the first time a new disk is seen, * performs disk spin up, read_capacity, etc. * @disk: struct gendisk we care about **/ -static int sd_revalidate_disk(struct gendisk *disk) +static void sd_revalidate_disk(struct gendisk *disk) { struct scsi_disk *sdkp = scsi_disk(disk); struct scsi_device *sdp = sdkp->device; - struct request_queue *q = sdkp->disk->queue; sector_t old_capacity = sdkp->capacity; - unsigned char *buffer; - unsigned int dev_max, rw_max; + struct queue_limits *lim = NULL; + unsigned char *buffer = NULL; + unsigned int dev_max; + int err; SCSI_LOG_HLQUEUE(3, sd_printk(KERN_INFO, sdkp, "sd_revalidate_disk\n")); @@ -3064,79 +3749,120 @@ static int sd_revalidate_disk(struct gendisk *disk) * of the other niceties. */ if (!scsi_device_online(sdp)) - goto out; + return; + + lim = kmalloc(sizeof(*lim), GFP_KERNEL); + if (!lim) + return; buffer = kmalloc(SD_BUF_SIZE, GFP_KERNEL); - if (!buffer) { - sd_printk(KERN_WARNING, sdkp, "sd_revalidate_disk: Memory " - "allocation failure.\n"); + if (!buffer) goto out; - } sd_spinup_disk(sdkp); + *lim = queue_limits_start_update(sdkp->disk->queue); + /* * Without media there is no reason to ask; moreover, some devices * react badly if we do. */ if (sdkp->media_present) { - sd_read_capacity(sdkp, buffer); + sd_read_capacity(sdkp, lim, buffer); + /* + * Some USB/UAS devices return generic values for mode pages + * until the media has been accessed. Trigger a READ operation + * to force the device to populate mode pages. + */ + if (sdp->read_before_ms) + sd_read_block_zero(sdkp); + /* + * set the default to rotational. All non-rotational devices + * support the block characteristics VPD page, which will + * cause this to be updated correctly and any device which + * doesn't support it should be treated as rotational. + */ + lim->features |= (BLK_FEAT_ROTATIONAL | BLK_FEAT_ADD_RANDOM); if (scsi_device_supports_vpd(sdp)) { sd_read_block_provisioning(sdkp); - sd_read_block_limits(sdkp); - sd_read_block_characteristics(sdkp); - sd_zbc_read_zones(sdkp, buffer); + sd_read_block_limits(sdkp, lim); + sd_read_block_limits_ext(sdkp); + sd_read_block_characteristics(sdkp, lim); + sd_zbc_read_zones(sdkp, lim, buffer); } + sd_config_discard(sdkp, lim, sd_discard_mode(sdkp)); + sd_print_capacity(sdkp, old_capacity); sd_read_write_protect_flag(sdkp, buffer); sd_read_cache_type(sdkp, buffer); + sd_read_io_hints(sdkp, buffer); sd_read_app_tag_own(sdkp, buffer); sd_read_write_same(sdkp, buffer); sd_read_security(sdkp, buffer); + sd_config_protection(sdkp, lim); } - sdkp->first_scan = 0; - /* * We now have all cache related info, determine how we deal * with flush requests. */ - sd_set_flush_flag(sdkp); + sd_set_flush_flag(sdkp, lim); /* Initial block count limit based on CDB TRANSFER LENGTH field size. */ dev_max = sdp->use_16_for_rw ? SD_MAX_XFER_BLOCKS : SD_DEF_XFER_BLOCKS; /* Some devices report a maximum block count for READ/WRITE requests. */ dev_max = min_not_zero(dev_max, sdkp->max_xfer_blocks); - q->limits.max_dev_sectors = logical_to_sectors(sdp, dev_max); + lim->max_dev_sectors = logical_to_sectors(sdp, dev_max); + + if (sd_validate_min_xfer_size(sdkp)) + lim->io_min = logical_to_bytes(sdp, sdkp->min_xfer_blocks); + else + lim->io_min = 0; /* - * Use the device's preferred I/O size for reads and writes - * unless the reported value is unreasonably small, large, or - * garbage. + * Limit default to SCSI host optimal sector limit if set. There may be + * an impact on performance for when the size of a request exceeds this + * host limit. */ - if (sdkp->opt_xfer_blocks && - sdkp->opt_xfer_blocks <= dev_max && - sdkp->opt_xfer_blocks <= SD_DEF_XFER_BLOCKS && - logical_to_bytes(sdp, sdkp->opt_xfer_blocks) >= PAGE_SIZE) { - q->limits.io_opt = logical_to_bytes(sdp, sdkp->opt_xfer_blocks); - rw_max = logical_to_sectors(sdp, sdkp->opt_xfer_blocks); - } else - rw_max = min_not_zero(logical_to_sectors(sdp, dev_max), - (sector_t)BLK_DEF_MAX_SECTORS); - - /* Combine with controller limits */ - q->limits.max_sectors = min(rw_max, queue_max_hw_sectors(q)); - - set_capacity(disk, logical_to_sectors(sdp, sdkp->capacity)); - sd_config_write_same(sdkp); - kfree(buffer); + lim->io_opt = sdp->host->opt_sectors << SECTOR_SHIFT; + if (sd_validate_opt_xfer_size(sdkp, dev_max)) { + lim->io_opt = min_not_zero(lim->io_opt, + logical_to_bytes(sdp, sdkp->opt_xfer_blocks)); + } + + sdkp->first_scan = 0; + + set_capacity_and_notify(disk, logical_to_sectors(sdp, sdkp->capacity)); + sd_config_write_same(sdkp, lim); + + err = queue_limits_commit_update_frozen(sdkp->disk->queue, lim); + if (err) + goto out; + + /* + * Query concurrent positioning ranges after + * queue_limits_commit_update() unlocked q->limits_lock to avoid + * deadlock with q->sysfs_dir_lock and q->sysfs_lock. + */ + if (sdkp->media_present && scsi_device_supports_vpd(sdp)) + sd_read_cpr(sdkp); + + /* + * For a zoned drive, revalidating the zones can be done only once + * the gendisk capacity is set. So if this fails, set back the gendisk + * capacity to 0. + */ + if (sd_zbc_revalidate_zones(sdkp)) + set_capacity_and_notify(disk, 0); out: - return 0; + kfree(buffer); + kfree(lim); + } /** @@ -3205,69 +3931,6 @@ static int sd_format_disk_name(char *prefix, int index, char *buf, int buflen) 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->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); - device_add_disk(dev, gd); - if (sdkp->capacity) - sd_dif_config_host(sdkp); - - sd_revalidate_disk(gd); - - if (sdkp->security) { - sdkp->opal_dev = init_opal_dev(sdp, &sd_sec_submit); - if (sdkp->opal_dev) - sd_printk(KERN_NOTICE, sdkp, "supports TCG Opal\n"); - } - - 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 @@ -3302,10 +3965,12 @@ static int sd_probe(struct device *dev) sdp->type != TYPE_RBC) goto out; -#ifndef CONFIG_BLK_DEV_ZONED - if (sdp->type == TYPE_ZBC) + if (!IS_ENABLED(CONFIG_BLK_DEV_ZONED) && sdp->type == TYPE_ZBC) { + sdev_printk(KERN_WARNING, sdp, + "Unsupported ZBC host-managed device.\n"); goto out; -#endif + } + SCSI_LOG_HLQUEUE(3, sdev_printk(KERN_INFO, sdp, "sd_probe\n")); @@ -3314,20 +3979,13 @@ static int sd_probe(struct device *dev) if (!sdkp) goto out; - gd = alloc_disk(SD_MINORS); + gd = blk_mq_alloc_disk_for_queue(sdp->request_queue, + &sd_bio_compl_lkclass); if (!gd) goto out_free; - do { - if (!ida_pre_get(&sd_index_ida, GFP_KERNEL)) - goto out_put; - - spin_lock(&sd_index_lock); - error = ida_get_new(&sd_index_ida, &index); - spin_unlock(&sd_index_lock); - } while (error == -EAGAIN); - - if (error) { + index = ida_alloc(&sd_index_ida, GFP_KERNEL); + if (index < 0) { sdev_printk(KERN_WARNING, sdp, "sd_probe: memory exhausted.\n"); goto out_put; } @@ -3339,9 +3997,9 @@ static int sd_probe(struct device *dev) } sdkp->device = sdp; - sdkp->driver = &sd_template; sdkp->disk = gd; sdkp->index = index; + sdkp->max_retries = SD_MAX_RETRIES; atomic_set(&sdkp->openers, 0); atomic_set(&sdkp->device->ioerr_cnt, 0); @@ -3353,27 +4011,73 @@ static int sd_probe(struct device *dev) SD_MOD_TIMEOUT); } - device_initialize(&sdkp->dev); - sdkp->dev.parent = dev; - sdkp->dev.class = &sd_disk_class; - dev_set_name(&sdkp->dev, "%s", dev_name(dev)); + device_initialize(&sdkp->disk_dev); + sdkp->disk_dev.parent = get_device(dev); + sdkp->disk_dev.class = &sd_disk_class; + dev_set_name(&sdkp->disk_dev, "%s", dev_name(dev)); - error = device_add(&sdkp->dev); - if (error) - goto out_free_index; + error = device_add(&sdkp->disk_dev); + if (error) { + put_device(&sdkp->disk_dev); + goto out; + } - get_device(dev); dev_set_drvdata(dev, sdkp); - get_device(&sdkp->dev); /* prevent release before async_schedule */ - async_schedule_domain(sd_probe_async, sdkp, &scsi_sd_probe_domain); + 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; + + /* 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); + + if (sdp->removable) { + gd->flags |= GENHD_FL_REMOVABLE; + gd->events |= DISK_EVENT_MEDIA_CHANGE; + gd->event_flags = DISK_EVENT_FLAG_POLL | DISK_EVENT_FLAG_UEVENT; + } + + blk_pm_runtime_init(sdp->request_queue, dev); + if (sdp->rpm_autosuspend) { + pm_runtime_set_autosuspend_delay(dev, + sdp->host->rpm_autosuspend_delay); + } + + error = device_add_disk(dev, gd, NULL); + if (error) { + device_unregister(&sdkp->disk_dev); + put_disk(gd); + goto out; + } + + if (sdkp->security) { + sdkp->opal_dev = init_opal_dev(sdkp, &sd_sec_submit); + if (sdkp->opal_dev) + sd_printk(KERN_NOTICE, sdkp, "supports TCG Opal\n"); + } + + sd_printk(KERN_NOTICE, sdkp, "Attached SCSI %sdisk\n", + sdp->removable ? "removable " : ""); + scsi_autopm_put_device(sdp); return 0; out_free_index: - spin_lock(&sd_index_lock); - ida_remove(&sd_index_ida, index); - spin_unlock(&sd_index_lock); + ida_free(&sd_index_ida, index); out_put: put_disk(gd); out_free: @@ -3396,55 +4100,26 @@ static int sd_probe(struct device *dev) **/ static int sd_remove(struct device *dev) { - struct scsi_disk *sdkp; - dev_t devt; + struct scsi_disk *sdkp = dev_get_drvdata(dev); - 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); + device_del(&sdkp->disk_dev); del_gendisk(sdkp->disk); - sd_shutdown(dev); - - sd_zbc_remove(sdkp); - - free_opal_dev(sdkp->opal_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); - mutex_unlock(&sd_ref_mutex); + if (!sdkp->suspended) + sd_shutdown(dev); + put_disk(sdkp->disk); return 0; } -/** - * scsi_disk_release - Called to free the scsi_disk structure - * @dev: pointer to embedded class device - * - * 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 put_device. - **/ static void scsi_disk_release(struct device *dev) { struct scsi_disk *sdkp = to_scsi_disk(dev); - struct gendisk *disk = sdkp->disk; - - spin_lock(&sd_index_lock); - ida_remove(&sd_index_ida, sdkp->index); - spin_unlock(&sd_index_lock); - - disk->private_data = NULL; - put_disk(disk); + + ida_free(&sd_index_ida, sdkp->index); put_device(&sdkp->device->sdev_gendev); + free_opal_dev(sdkp->opal_dev); kfree(sdkp); } @@ -3453,6 +4128,39 @@ 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_failure failure_defs[] = { + { + /* Power on, reset, or bus device reset occurred */ + .sense = UNIT_ATTENTION, + .asc = 0x29, + .ascq = 0, + .result = SAM_STAT_CHECK_CONDITION, + }, + { + /* Power on occurred */ + .sense = UNIT_ATTENTION, + .asc = 0x29, + .ascq = 1, + .result = SAM_STAT_CHECK_CONDITION, + }, + { + /* SCSI bus reset */ + .sense = UNIT_ATTENTION, + .asc = 0x29, + .ascq = 2, + .result = SAM_STAT_CHECK_CONDITION, + }, + {} + }; + struct scsi_failures failures = { + .total_allowed = 3, + .failure_definitions = failure_defs, + }; + const struct scsi_exec_args exec_args = { + .sshdr = &sshdr, + .req_flags = BLK_MQ_REQ_PM, + .failures = &failures, + }; struct scsi_device *sdp = sdkp->device; int res; @@ -3465,16 +4173,16 @@ static int sd_start_stop_device(struct scsi_disk *sdkp, int start) if (!scsi_device_online(sdp)) return -ENODEV; - res = scsi_execute(sdp, cmd, DMA_NONE, NULL, 0, NULL, &sshdr, - SD_TIMEOUT, SD_MAX_RETRIES, 0, RQF_PM, NULL); + res = scsi_execute_cmd(sdp, cmd, REQ_OP_DRV_IN, NULL, 0, SD_TIMEOUT, + sdkp->max_retries, &exec_args); if (res) { sd_print_result(sdkp, "Start/Stop Unit failed", res); - if (driver_byte(res) & DRIVER_SENSE) + if (res > 0 && scsi_sense_valid(&sshdr)) { sd_print_sense_hdr(sdkp, &sshdr); - if (scsi_sense_valid(&sshdr) && /* 0x3a is medium not present */ - sshdr.asc == 0x3a) - res = 0; + if (sshdr.asc == 0x3a) + res = 0; + } } /* SCSI error codes must not go to the generic layer */ @@ -3501,85 +4209,182 @@ static void sd_shutdown(struct device *dev) if (sdkp->WCE && sdkp->media_present) { sd_printk(KERN_NOTICE, sdkp, "Synchronizing SCSI cache\n"); - sd_sync_cache(sdkp, NULL); + sd_sync_cache(sdkp); } - if (system_state != SYSTEM_RESTART && sdkp->device->manage_start_stop) { + if ((system_state != SYSTEM_RESTART && + sdkp->device->manage_system_start_stop) || + (system_state == SYSTEM_POWER_OFF && + sdkp->device->manage_shutdown) || + (system_state == SYSTEM_RUNNING && + sdkp->device->manage_runtime_start_stop) || + (system_state == SYSTEM_RESTART && + sdkp->device->manage_restart)) { sd_printk(KERN_NOTICE, sdkp, "Stopping disk\n"); sd_start_stop_device(sdkp, 0); } } -static int sd_suspend_common(struct device *dev, bool ignore_stop_errors) +static inline bool sd_do_start_stop(struct scsi_device *sdev, bool runtime) +{ + return (sdev->manage_system_start_stop && !runtime) || + (sdev->manage_runtime_start_stop && runtime); +} + +static int sd_suspend_common(struct device *dev, bool runtime) { struct scsi_disk *sdkp = dev_get_drvdata(dev); - struct scsi_sense_hdr sshdr; int ret = 0; if (!sdkp) /* E.g.: runtime suspend following sd_remove() */ return 0; if (sdkp->WCE && sdkp->media_present) { - sd_printk(KERN_NOTICE, sdkp, "Synchronizing SCSI cache\n"); - ret = sd_sync_cache(sdkp, &sshdr); - - if (ret) { - /* ignore OFFLINE device */ - if (ret == -ENODEV) - return 0; - - if (!scsi_sense_valid(&sshdr) || - sshdr.sense_key != ILLEGAL_REQUEST) - return ret; + if (!sdkp->device->silence_suspend) + sd_printk(KERN_NOTICE, sdkp, "Synchronizing SCSI cache\n"); + ret = sd_sync_cache(sdkp); + /* ignore OFFLINE device */ + if (ret == -ENODEV) + return 0; - /* - * sshdr.sense_key == ILLEGAL_REQUEST means this drive - * doesn't support sync. There's not much to do and - * suspend shouldn't fail. - */ - ret = 0; - } + if (ret) + return ret; } - if (sdkp->device->manage_start_stop) { - sd_printk(KERN_NOTICE, sdkp, "Stopping disk\n"); + if (sd_do_start_stop(sdkp->device, runtime)) { + if (!sdkp->device->silence_suspend) + 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) + if (!runtime) ret = 0; } + if (!ret) + sdkp->suspended = true; + return ret; } static int sd_suspend_system(struct device *dev) { - return sd_suspend_common(dev, true); + if (pm_runtime_suspended(dev)) + return 0; + + return sd_suspend_common(dev, false); } static int sd_suspend_runtime(struct device *dev) { - return sd_suspend_common(dev, false); + return sd_suspend_common(dev, true); } static int sd_resume(struct device *dev) { struct scsi_disk *sdkp = dev_get_drvdata(dev); + + sd_printk(KERN_NOTICE, sdkp, "Starting disk\n"); + + if (opal_unlock_from_suspend(sdkp->opal_dev)) { + sd_printk(KERN_NOTICE, sdkp, "OPAL unlock failed\n"); + return -EIO; + } + + return 0; +} + +static int sd_resume_common(struct device *dev, bool runtime) +{ + struct scsi_disk *sdkp = dev_get_drvdata(dev); int ret; if (!sdkp) /* E.g.: runtime resume at the start of sd_probe() */ return 0; - if (!sdkp->device->manage_start_stop) + if (!sd_do_start_stop(sdkp->device, runtime)) { + sdkp->suspended = false; return 0; + } sd_printk(KERN_NOTICE, sdkp, "Starting disk\n"); ret = sd_start_stop_device(sdkp, 1); - if (!ret) - opal_unlock_from_suspend(sdkp->opal_dev); + if (!ret) { + sd_resume(dev); + sdkp->suspended = false; + } + return ret; } +static int sd_resume_system(struct device *dev) +{ + if (pm_runtime_suspended(dev)) { + struct scsi_disk *sdkp = dev_get_drvdata(dev); + struct scsi_device *sdp = sdkp ? sdkp->device : NULL; + + if (sdp && sdp->force_runtime_start_on_system_start) + pm_request_resume(dev); + + return 0; + } + + return sd_resume_common(dev, false); +} + +static int sd_resume_runtime(struct device *dev) +{ + struct scsi_disk *sdkp = dev_get_drvdata(dev); + struct scsi_device *sdp; + + if (!sdkp) /* E.g.: runtime resume at the start of sd_probe() */ + return 0; + + sdp = sdkp->device; + + if (sdp->ignore_media_change) { + /* clear the device's sense data */ + static const u8 cmd[10] = { REQUEST_SENSE }; + const struct scsi_exec_args exec_args = { + .req_flags = BLK_MQ_REQ_PM, + }; + + if (scsi_execute_cmd(sdp, cmd, REQ_OP_DRV_IN, NULL, 0, + sdp->request_queue->rq_timeout, 1, + &exec_args)) + sd_printk(KERN_NOTICE, sdkp, + "Failed to clear sense data\n"); + } + + return sd_resume_common(dev, true); +} + +static const struct dev_pm_ops sd_pm_ops = { + .suspend = sd_suspend_system, + .resume = sd_resume_system, + .poweroff = sd_suspend_system, + .restore = sd_resume_system, + .runtime_suspend = sd_suspend_runtime, + .runtime_resume = sd_resume_runtime, +}; + +static struct scsi_driver sd_template = { + .gendrv = { + .name = "sd", + .probe = sd_probe, + .probe_type = PROBE_PREFER_ASYNCHRONOUS, + .remove = sd_remove, + .shutdown = sd_shutdown, + .pm = &sd_pm_ops, + }, + .rescan = sd_rescan, + .resume = sd_resume, + .init_command = sd_init_command, + .uninit_command = sd_uninit_command, + .done = sd_done, + .eh_action = sd_eh_action, + .eh_reset = sd_eh_reset, +}; + /** * init_sd - entry point for this driver (both when built in or when * a module). @@ -3593,11 +4398,9 @@ 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) + if (__register_blkdev(sd_major(i), "sd", sd_default_probe)) continue; majors++; - blk_register_region(sd_major(i), SD_MINORS, NULL, - sd_default_probe, NULL, NULL); } if (!majors) @@ -3607,21 +4410,13 @@ static int __init init_sd(void) 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"); + sd_page_pool = mempool_create_page_pool(SD_MEMPOOL_SIZE, 0); + if (!sd_page_pool) { + printk(KERN_ERR "sd: can't init discard page pool\n"); err = -ENOMEM; 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"); - err = -ENOMEM; - goto err_out_cache; - } - err = scsi_register_driver(&sd_template.gendrv); if (err) goto err_out_driver; @@ -3629,11 +4424,7 @@ static int __init init_sd(void) return 0; err_out_driver: - mempool_destroy(sd_cdb_pool); - -err_out_cache: - kmem_cache_destroy(sd_cdb_cache); - + mempool_destroy(sd_page_pool); err_out_class: class_unregister(&sd_disk_class); err_out: @@ -3654,41 +4445,34 @@ 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); + mempool_destroy(sd_page_pool); class_unregister(&sd_disk_class); - for (i = 0; i < SD_MAJORS; i++) { - blk_unregister_region(sd_major(i), SD_MINORS); + for (i = 0; i < SD_MAJORS; i++) unregister_blkdev(sd_major(i), "sd"); - } } module_init(init_sd); module_exit(exit_sd); -static void sd_print_sense_hdr(struct scsi_disk *sdkp, - struct scsi_sense_hdr *sshdr) +void sd_print_sense_hdr(struct scsi_disk *sdkp, struct scsi_sense_hdr *sshdr) { scsi_print_sense_hdr(sdkp->device, sdkp->disk ? sdkp->disk->disk_name : NULL, sshdr); } -static void sd_print_result(const struct scsi_disk *sdkp, const char *msg, - int result) +void sd_print_result(const struct scsi_disk *sdkp, const char *msg, int result) { const char *hb_string = scsi_hostbyte_string(result); - const char *db_string = scsi_driverbyte_string(result); - if (hb_string || db_string) + if (hb_string) sd_printk(KERN_INFO, sdkp, "%s: Result: hostbyte=%s driverbyte=%s\n", msg, hb_string ? hb_string : "invalid", - db_string ? db_string : "invalid"); + "DRIVER_OK"); else sd_printk(KERN_INFO, sdkp, - "%s: Result: hostbyte=0x%02x driverbyte=0x%02x\n", - msg, host_byte(result), driver_byte(result)); + "%s: Result: hostbyte=0x%02x driverbyte=%s\n", + msg, host_byte(result), "DRIVER_OK"); } - |