diff --git a/Documentation/block/queue-sysfs.rst b/Documentation/block/queue-sysfs.rst index 4dc7f0d499a8..e8c74306f70a 100644 --- a/Documentation/block/queue-sysfs.rst +++ b/Documentation/block/queue-sysfs.rst @@ -4,7 +4,7 @@ Queue sysfs files This text file will detail the queue files that are located in the sysfs tree for each block device. Note that stacked devices typically do not export -any settings, since their queue merely functions are a remapping target. +any settings, since their queue merely functions as a remapping target. These files are the ones found in the /sys/block/xxx/queue/ directory. Files denoted with a RO postfix are readonly and the RW postfix means @@ -286,4 +286,35 @@ sequential zones of zoned block devices (devices with a zoned attributed that reports "host-managed" or "host-aware"). This value is always 0 for regular block devices. +independent_access_ranges (RO) +------------------------------ + +The presence of this sub-directory of the /sys/block/xxx/queue/ directory +indicates that the device is capable of executing requests targeting +different sector ranges in parallel. For instance, single LUN multi-actuator +hard-disks will have an independent_access_ranges directory if the device +correctly advertizes the sector ranges of its actuators. + +The independent_access_ranges directory contains one directory per access +range, with each range described using the sector (RO) attribute file to +indicate the first sector of the range and the nr_sectors (RO) attribute file +to indicate the total number of sectors in the range starting from the first +sector of the range. For example, a dual-actuator hard-disk will have the +following independent_access_ranges entries.:: + + $ tree /sys/block//queue/independent_access_ranges/ + /sys/block//queue/independent_access_ranges/ + |-- 0 + | |-- nr_sectors + | `-- sector + `-- 1 + |-- nr_sectors + `-- sector + +The sector and nr_sectors attributes use 512B sector unit, regardless of +the actual block size of the device. Independent access ranges do not +overlap and include all sectors within the device capacity. The access +ranges are numbered in increasing order of the range start sector, +that is, the sector attribute of range 0 always has the value 0. + Jens Axboe , February 2009 diff --git a/Documentation/cdrom/cdrom-standard.rst b/Documentation/cdrom/cdrom-standard.rst index 5845960ca382..52ea7b6b2fe8 100644 --- a/Documentation/cdrom/cdrom-standard.rst +++ b/Documentation/cdrom/cdrom-standard.rst @@ -907,6 +907,17 @@ commands can be identified by the underscores in their names. specifies the slot for which the information is given. The special value *CDSL_CURRENT* requests that information about the currently selected slot be returned. +`CDROM_TIMED_MEDIA_CHANGE` + Checks whether the disc has been changed since a user supplied time + and returns the time of the last disc change. + + *arg* is a pointer to a *cdrom_timed_media_change_info* struct. + *arg->last_media_change* may be set by calling code to signal + the timestamp of the last known media change (by the caller). + Upon successful return, this ioctl call will set + *arg->last_media_change* to the latest media change timestamp (in ms) + known by the kernel/driver and set *arg->has_changed* to 1 if + that timestamp is more recent than the timestamp set by the caller. `CDROM_DRIVE_STATUS` Returns the status of the drive by a call to *drive_status()*. Return values are defined in cdrom_drive_status_. diff --git a/Documentation/userspace-api/ioctl/cdrom.rst b/Documentation/userspace-api/ioctl/cdrom.rst index 3b4c0506de46..682948fc88a3 100644 --- a/Documentation/userspace-api/ioctl/cdrom.rst +++ b/Documentation/userspace-api/ioctl/cdrom.rst @@ -13,61 +13,64 @@ in drivers/cdrom/cdrom.c and drivers/block/scsi_ioctl.c ioctl values are listed in . As of this writing, they are as follows: - ====================== =============================================== - CDROMPAUSE Pause Audio Operation - CDROMRESUME Resume paused Audio Operation - CDROMPLAYMSF Play Audio MSF (struct cdrom_msf) - CDROMPLAYTRKIND Play Audio Track/index (struct cdrom_ti) - CDROMREADTOCHDR Read TOC header (struct cdrom_tochdr) - CDROMREADTOCENTRY Read TOC entry (struct cdrom_tocentry) - CDROMSTOP Stop the cdrom drive - CDROMSTART Start the cdrom drive - CDROMEJECT Ejects the cdrom media - CDROMVOLCTRL Control output volume (struct cdrom_volctrl) - CDROMSUBCHNL Read subchannel data (struct cdrom_subchnl) - CDROMREADMODE2 Read CDROM mode 2 data (2336 Bytes) - (struct cdrom_read) - CDROMREADMODE1 Read CDROM mode 1 data (2048 Bytes) - (struct cdrom_read) - CDROMREADAUDIO (struct cdrom_read_audio) - CDROMEJECT_SW enable(1)/disable(0) auto-ejecting - CDROMMULTISESSION Obtain the start-of-last-session - address of multi session disks - (struct cdrom_multisession) - CDROM_GET_MCN Obtain the "Universal Product Code" - if available (struct cdrom_mcn) - CDROM_GET_UPC Deprecated, use CDROM_GET_MCN instead. - CDROMRESET hard-reset the drive - CDROMVOLREAD Get the drive's volume setting - (struct cdrom_volctrl) - CDROMREADRAW read data in raw mode (2352 Bytes) - (struct cdrom_read) - CDROMREADCOOKED read data in cooked mode - CDROMSEEK seek msf address - CDROMPLAYBLK scsi-cd only, (struct cdrom_blk) - CDROMREADALL read all 2646 bytes - CDROMGETSPINDOWN return 4-bit spindown value - CDROMSETSPINDOWN set 4-bit spindown value - CDROMCLOSETRAY pendant of CDROMEJECT - CDROM_SET_OPTIONS Set behavior options - CDROM_CLEAR_OPTIONS Clear behavior options - CDROM_SELECT_SPEED Set the CD-ROM speed - CDROM_SELECT_DISC Select disc (for juke-boxes) - CDROM_MEDIA_CHANGED Check is media changed - CDROM_DRIVE_STATUS Get tray position, etc. - CDROM_DISC_STATUS Get disc type, etc. - CDROM_CHANGER_NSLOTS Get number of slots - CDROM_LOCKDOOR lock or unlock door - CDROM_DEBUG Turn debug messages on/off - CDROM_GET_CAPABILITY get capabilities - CDROMAUDIOBUFSIZ set the audio buffer size - DVD_READ_STRUCT Read structure - DVD_WRITE_STRUCT Write structure - DVD_AUTH Authentication - CDROM_SEND_PACKET send a packet to the drive - CDROM_NEXT_WRITABLE get next writable block - CDROM_LAST_WRITTEN get last block written on disc - ====================== =============================================== + ======================== =============================================== + CDROMPAUSE Pause Audio Operation + CDROMRESUME Resume paused Audio Operation + CDROMPLAYMSF Play Audio MSF (struct cdrom_msf) + CDROMPLAYTRKIND Play Audio Track/index (struct cdrom_ti) + CDROMREADTOCHDR Read TOC header (struct cdrom_tochdr) + CDROMREADTOCENTRY Read TOC entry (struct cdrom_tocentry) + CDROMSTOP Stop the cdrom drive + CDROMSTART Start the cdrom drive + CDROMEJECT Ejects the cdrom media + CDROMVOLCTRL Control output volume (struct cdrom_volctrl) + CDROMSUBCHNL Read subchannel data (struct cdrom_subchnl) + CDROMREADMODE2 Read CDROM mode 2 data (2336 Bytes) + (struct cdrom_read) + CDROMREADMODE1 Read CDROM mode 1 data (2048 Bytes) + (struct cdrom_read) + CDROMREADAUDIO (struct cdrom_read_audio) + CDROMEJECT_SW enable(1)/disable(0) auto-ejecting + CDROMMULTISESSION Obtain the start-of-last-session + address of multi session disks + (struct cdrom_multisession) + CDROM_GET_MCN Obtain the "Universal Product Code" + if available (struct cdrom_mcn) + CDROM_GET_UPC Deprecated, use CDROM_GET_MCN instead. + CDROMRESET hard-reset the drive + CDROMVOLREAD Get the drive's volume setting + (struct cdrom_volctrl) + CDROMREADRAW read data in raw mode (2352 Bytes) + (struct cdrom_read) + CDROMREADCOOKED read data in cooked mode + CDROMSEEK seek msf address + CDROMPLAYBLK scsi-cd only, (struct cdrom_blk) + CDROMREADALL read all 2646 bytes + CDROMGETSPINDOWN return 4-bit spindown value + CDROMSETSPINDOWN set 4-bit spindown value + CDROMCLOSETRAY pendant of CDROMEJECT + CDROM_SET_OPTIONS Set behavior options + CDROM_CLEAR_OPTIONS Clear behavior options + CDROM_SELECT_SPEED Set the CD-ROM speed + CDROM_SELECT_DISC Select disc (for juke-boxes) + CDROM_MEDIA_CHANGED Check is media changed + CDROM_TIMED_MEDIA_CHANGE Check if media changed + since given time + (struct cdrom_timed_media_change_info) + CDROM_DRIVE_STATUS Get tray position, etc. + CDROM_DISC_STATUS Get disc type, etc. + CDROM_CHANGER_NSLOTS Get number of slots + CDROM_LOCKDOOR lock or unlock door + CDROM_DEBUG Turn debug messages on/off + CDROM_GET_CAPABILITY get capabilities + CDROMAUDIOBUFSIZ set the audio buffer size + DVD_READ_STRUCT Read structure + DVD_WRITE_STRUCT Write structure + DVD_AUTH Authentication + CDROM_SEND_PACKET send a packet to the drive + CDROM_NEXT_WRITABLE get next writable block + CDROM_LAST_WRITTEN get last block written on disc + ======================== =============================================== The information that follows was determined from reading kernel source diff --git a/arch/m68k/emu/nfblock.c b/arch/m68k/emu/nfblock.c index 4ef457ba5220..9c57b245dc12 100644 --- a/arch/m68k/emu/nfblock.c +++ b/arch/m68k/emu/nfblock.c @@ -99,6 +99,7 @@ static int __init nfhd_init_one(int id, u32 blocks, u32 bsize) { struct nfhd_device *dev; int dev_id = id - NFHD_DEV_OFFSET; + int err = -ENOMEM; pr_info("nfhd%u: found device with %u blocks (%u bytes)\n", dev_id, blocks, bsize); @@ -129,16 +130,20 @@ static int __init nfhd_init_one(int id, u32 blocks, u32 bsize) sprintf(dev->disk->disk_name, "nfhd%u", dev_id); set_capacity(dev->disk, (sector_t)blocks * (bsize / 512)); blk_queue_logical_block_size(dev->disk->queue, bsize); - add_disk(dev->disk); + err = add_disk(dev->disk); + if (err) + goto out_cleanup_disk; list_add_tail(&dev->list, &nfhd_list); return 0; +out_cleanup_disk: + blk_cleanup_disk(dev->disk); free_dev: kfree(dev); out: - return -ENOMEM; + return err; } static int __init nfhd_init(void) diff --git a/arch/um/drivers/ubd_kern.c b/arch/um/drivers/ubd_kern.c index fefd343412c7..69d2d0049a61 100644 --- a/arch/um/drivers/ubd_kern.c +++ b/arch/um/drivers/ubd_kern.c @@ -855,8 +855,8 @@ static const struct attribute_group *ubd_attr_groups[] = { NULL, }; -static void ubd_disk_register(int major, u64 size, int unit, - struct gendisk *disk) +static int ubd_disk_register(int major, u64 size, int unit, + struct gendisk *disk) { disk->major = major; disk->first_minor = unit << UBD_SHIFT; @@ -873,7 +873,7 @@ static void ubd_disk_register(int major, u64 size, int unit, disk->private_data = &ubd_devs[unit]; disk->queue = ubd_devs[unit].queue; - device_add_disk(&ubd_devs[unit].pdev.dev, disk, ubd_attr_groups); + return device_add_disk(&ubd_devs[unit].pdev.dev, disk, ubd_attr_groups); } #define ROUND_BLOCK(n) ((n + (SECTOR_SIZE - 1)) & (-SECTOR_SIZE)) @@ -920,10 +920,15 @@ static int ubd_add(int n, char **error_out) blk_queue_write_cache(ubd_dev->queue, true, false); blk_queue_max_segments(ubd_dev->queue, MAX_SG); blk_queue_segment_boundary(ubd_dev->queue, PAGE_SIZE - 1); - ubd_disk_register(UBD_MAJOR, ubd_dev->size, n, disk); + err = ubd_disk_register(UBD_MAJOR, ubd_dev->size, n, disk); + if (err) + goto out_cleanup_disk; + ubd_gendisk[n] = disk; return 0; +out_cleanup_disk: + blk_cleanup_disk(disk); out_cleanup_tags: blk_mq_free_tag_set(&ubd_dev->tag_set); out: diff --git a/arch/xtensa/platforms/iss/simdisk.c b/arch/xtensa/platforms/iss/simdisk.c index ddd1fe3db474..07b642c1916a 100644 --- a/arch/xtensa/platforms/iss/simdisk.c +++ b/arch/xtensa/platforms/iss/simdisk.c @@ -258,6 +258,7 @@ static int __init simdisk_setup(struct simdisk *dev, int which, struct proc_dir_entry *procdir) { char tmp[2] = { '0' + which, 0 }; + int err = -ENOMEM; dev->fd = -1; dev->filename = NULL; @@ -266,7 +267,7 @@ static int __init simdisk_setup(struct simdisk *dev, int which, dev->gd = blk_alloc_disk(NUMA_NO_NODE); if (!dev->gd) - return -ENOMEM; + goto out; dev->gd->major = simdisk_major; dev->gd->first_minor = which; dev->gd->minors = SIMDISK_MINORS; @@ -274,10 +275,18 @@ static int __init simdisk_setup(struct simdisk *dev, int which, dev->gd->private_data = dev; snprintf(dev->gd->disk_name, 32, "simdisk%d", which); set_capacity(dev->gd, 0); - add_disk(dev->gd); + err = add_disk(dev->gd); + if (err) + goto out_cleanup_disk; dev->procfile = proc_create_data(tmp, 0644, procdir, &simdisk_proc_ops, dev); + return 0; + +out_cleanup_disk: + blk_cleanup_disk(dev->gd); +out: + return err; } static int __init simdisk_init(void) diff --git a/block/fops.c b/block/fops.c index a2f492e50782..3777c7b76eae 100644 --- a/block/fops.c +++ b/block/fops.c @@ -605,7 +605,7 @@ static long blkdev_fallocate(struct file *file, int mode, loff_t start, return -EOPNOTSUPP; /* Don't go off the end of the device. */ - isize = i_size_read(bdev->bd_inode); + isize = bdev_nr_bytes(bdev); if (start >= isize) return -EINVAL; if (end >= isize) { diff --git a/block/genhd.c b/block/genhd.c index 2052aeffa39b..febaaa55125a 100644 --- a/block/genhd.c +++ b/block/genhd.c @@ -58,6 +58,7 @@ void set_capacity(struct gendisk *disk, sector_t sectors) spin_lock(&bdev->bd_size_lock); i_size_write(bdev->bd_inode, (loff_t)sectors << SECTOR_SHIFT); + bdev->bd_nr_sectors = sectors; spin_unlock(&bdev->bd_size_lock); } EXPORT_SYMBOL(set_capacity); diff --git a/block/ioctl.c b/block/ioctl.c index 77b1b2453f39..d6af0ac97e57 100644 --- a/block/ioctl.c +++ b/block/ioctl.c @@ -132,7 +132,7 @@ static int blk_ioctl_discard(struct block_device *bdev, fmode_t mode, if (len & 511) return -EINVAL; - if (start + len > i_size_read(bdev->bd_inode)) + if (start + len > bdev_nr_bytes(bdev)) return -EINVAL; err = truncate_bdev_range(bdev, mode, start, start + len - 1); @@ -164,7 +164,7 @@ static int blk_ioctl_zeroout(struct block_device *bdev, fmode_t mode, return -EINVAL; if (len & 511) return -EINVAL; - if (end >= (uint64_t)i_size_read(bdev->bd_inode)) + if (end >= (uint64_t)bdev_nr_bytes(bdev)) return -EINVAL; if (end < start) return -EINVAL; @@ -543,7 +543,6 @@ long blkdev_ioctl(struct file *file, unsigned cmd, unsigned long arg) struct block_device *bdev = I_BDEV(file->f_mapping->host); void __user *argp = (void __user *)arg; fmode_t mode = file->f_mode; - loff_t size; int ret; /* @@ -570,10 +569,9 @@ long blkdev_ioctl(struct file *file, unsigned cmd, unsigned long arg) return put_long(argp, (bdev->bd_disk->bdi->ra_pages * PAGE_SIZE) / 512); case BLKGETSIZE: - size = i_size_read(bdev->bd_inode); - if ((size >> 9) > ~0UL) + if (bdev_nr_sectors(bdev) > ~0UL) return -EFBIG; - return put_ulong(argp, size >> 9); + return put_ulong(argp, bdev_nr_sectors(bdev)); /* The data is compatible, but the command number is different */ case BLKBSZGET: /* get block device soft block size (cf. BLKSSZGET) */ @@ -581,7 +579,7 @@ long blkdev_ioctl(struct file *file, unsigned cmd, unsigned long arg) case BLKBSZSET: return blkdev_bszset(bdev, mode, argp); case BLKGETSIZE64: - return put_u64(argp, i_size_read(bdev->bd_inode)); + return put_u64(argp, bdev_nr_bytes(bdev)); /* Incompatible alignment on i386 */ case BLKTRACESETUP: @@ -615,7 +613,6 @@ long compat_blkdev_ioctl(struct file *file, unsigned cmd, unsigned long arg) struct block_device *bdev = I_BDEV(file->f_mapping->host); struct gendisk *disk = bdev->bd_disk; fmode_t mode = file->f_mode; - loff_t size; /* * O_NDELAY can be altered using fcntl(.., F_SETFL, ..), so we have @@ -641,10 +638,9 @@ long compat_blkdev_ioctl(struct file *file, unsigned cmd, unsigned long arg) return compat_put_long(argp, (bdev->bd_disk->bdi->ra_pages * PAGE_SIZE) / 512); case BLKGETSIZE: - size = i_size_read(bdev->bd_inode); - if ((size >> 9) > ~0UL) + if (bdev_nr_sectors(bdev) > ~0UL) return -EFBIG; - return compat_put_ulong(argp, size >> 9); + return compat_put_ulong(argp, bdev_nr_sectors(bdev)); /* The data is compatible, but the command number is different */ case BLKBSZGET_32: /* get the logical block size (cf. BLKSSZGET) */ @@ -652,7 +648,7 @@ long compat_blkdev_ioctl(struct file *file, unsigned cmd, unsigned long arg) case BLKBSZSET_32: return blkdev_bszset(bdev, mode, argp); case BLKGETSIZE64_32: - return put_u64(argp, i_size_read(bdev->bd_inode)); + return put_u64(argp, bdev_nr_bytes(bdev)); /* Incompatible alignment on i386 */ case BLKTRACESETUP32: diff --git a/block/partitions/core.c b/block/partitions/core.c index ed5deef1d7e1..334b72ef1d73 100644 --- a/block/partitions/core.c +++ b/block/partitions/core.c @@ -91,6 +91,7 @@ static void bdev_set_nr_sectors(struct block_device *bdev, sector_t sectors) { spin_lock(&bdev->bd_size_lock); i_size_write(bdev->bd_inode, (loff_t)sectors << SECTOR_SHIFT); + bdev->bd_nr_sectors = sectors; spin_unlock(&bdev->bd_size_lock); } diff --git a/block/partitions/efi.c b/block/partitions/efi.c index 7ca5c4c374d4..5e9be13a56a8 100644 --- a/block/partitions/efi.c +++ b/block/partitions/efi.c @@ -133,7 +133,7 @@ efi_crc32(const void *buf, unsigned long len) */ static u64 last_lba(struct gendisk *disk) { - return div_u64(disk->part0->bd_inode->i_size, + return div_u64(bdev_nr_bytes(disk->part0), queue_logical_block_size(disk->queue)) - 1ULL; } diff --git a/block/partitions/ibm.c b/block/partitions/ibm.c index 9bca396aef4a..403756dbd50d 100644 --- a/block/partitions/ibm.c +++ b/block/partitions/ibm.c @@ -198,7 +198,7 @@ static int find_lnx1_partitions(struct parsed_partitions *state, char name[], union label_t *label, sector_t labelsect, - loff_t i_size, + sector_t nr_sectors, dasd_information2_t *info) { loff_t offset, geo_size, size; @@ -213,14 +213,14 @@ static int find_lnx1_partitions(struct parsed_partitions *state, } else { /* * Formated w/o large volume support. If the sanity check - * 'size based on geo == size based on i_size' is true, then + * 'size based on geo == size based on nr_sectors' is true, then * we can safely assume that we know the formatted size of * the disk, otherwise we need additional information * that we can only get from a real DASD device. */ geo_size = geo->cylinders * geo->heads * geo->sectors * secperblk; - size = i_size >> 9; + size = nr_sectors; if (size != geo_size) { if (!info) { strlcat(state->pp_buf, "\n", PAGE_SIZE); @@ -229,7 +229,7 @@ static int find_lnx1_partitions(struct parsed_partitions *state, if (!strcmp(info->type, "ECKD")) if (geo_size < size) size = geo_size; - /* else keep size based on i_size */ + /* else keep size based on nr_sectors */ } } /* first and only partition starts in the first block after the label */ @@ -293,7 +293,8 @@ int ibm_partition(struct parsed_partitions *state) struct gendisk *disk = state->disk; struct block_device *bdev = disk->part0; int blocksize, res; - loff_t i_size, offset, size; + loff_t offset, size; + sector_t nr_sectors; dasd_information2_t *info; struct hd_geometry *geo; char type[5] = {0,}; @@ -308,8 +309,8 @@ int ibm_partition(struct parsed_partitions *state) blocksize = bdev_logical_block_size(bdev); if (blocksize <= 0) goto out_symbol; - i_size = i_size_read(bdev->bd_inode); - if (i_size == 0) + nr_sectors = bdev_nr_sectors(bdev); + if (nr_sectors == 0) goto out_symbol; info = kmalloc(sizeof(dasd_information2_t), GFP_KERNEL); if (info == NULL) @@ -336,7 +337,7 @@ int ibm_partition(struct parsed_partitions *state) label); } else if (!strncmp(type, "LNX1", 4)) { res = find_lnx1_partitions(state, geo, blocksize, name, - label, labelsect, i_size, + label, labelsect, nr_sectors, info); } else if (!strncmp(type, "CMS1", 4)) { res = find_cms1_partitions(state, geo, blocksize, name, @@ -353,7 +354,7 @@ int ibm_partition(struct parsed_partitions *state) res = 1; if (info->format == DASD_FORMAT_LDL) { strlcat(state->pp_buf, "(nonl)", PAGE_SIZE); - size = i_size >> 9; + size = nr_sectors; offset = (info->label_block + 1) * (blocksize >> 9); put_partition(state, 1, offset, size-offset); strlcat(state->pp_buf, "\n", PAGE_SIZE); diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c index eed65311b5d1..75f1a6cd6621 100644 --- a/drivers/ata/libata-core.c +++ b/drivers/ata/libata-core.c @@ -2459,18 +2459,70 @@ static void ata_dev_config_devslp(struct ata_device *dev) } } +static void ata_dev_config_cpr(struct ata_device *dev) +{ + unsigned int err_mask; + size_t buf_len; + int i, nr_cpr = 0; + struct ata_cpr_log *cpr_log = NULL; + u8 *desc, *buf = NULL; + + if (!ata_identify_page_supported(dev, + ATA_LOG_CONCURRENT_POSITIONING_RANGES)) + goto out; + + /* + * Read IDENTIFY DEVICE data log, page 0x47 + * (concurrent positioning ranges). We can have at most 255 32B range + * descriptors plus a 64B header. + */ + buf_len = (64 + 255 * 32 + 511) & ~511; + buf = kzalloc(buf_len, GFP_KERNEL); + if (!buf) + goto out; + + err_mask = ata_read_log_page(dev, ATA_LOG_IDENTIFY_DEVICE, + ATA_LOG_CONCURRENT_POSITIONING_RANGES, + buf, buf_len >> 9); + if (err_mask) + goto out; + + nr_cpr = buf[0]; + if (!nr_cpr) + goto out; + + cpr_log = kzalloc(struct_size(cpr_log, cpr, nr_cpr), GFP_KERNEL); + if (!cpr_log) + goto out; + + cpr_log->nr_cpr = nr_cpr; + desc = &buf[64]; + for (i = 0; i < nr_cpr; i++, desc += 32) { + cpr_log->cpr[i].num = desc[0]; + cpr_log->cpr[i].num_storage_elements = desc[1]; + cpr_log->cpr[i].start_lba = get_unaligned_le64(&desc[8]); + cpr_log->cpr[i].num_lbas = get_unaligned_le64(&desc[16]); + } + +out: + swap(dev->cpr_log, cpr_log); + kfree(cpr_log); + kfree(buf); +} + static void ata_dev_print_features(struct ata_device *dev) { if (!(dev->flags & ATA_DFLAG_FEATURES_MASK)) return; ata_dev_info(dev, - "Features:%s%s%s%s%s\n", + "Features:%s%s%s%s%s%s\n", dev->flags & ATA_DFLAG_TRUSTED ? " Trust" : "", dev->flags & ATA_DFLAG_DA ? " Dev-Attention" : "", dev->flags & ATA_DFLAG_DEVSLP ? " Dev-Sleep" : "", dev->flags & ATA_DFLAG_NCQ_SEND_RECV ? " NCQ-sndrcv" : "", - dev->flags & ATA_DFLAG_NCQ_PRIO ? " NCQ-prio" : ""); + dev->flags & ATA_DFLAG_NCQ_PRIO ? " NCQ-prio" : "", + dev->cpr_log ? " CPR" : ""); } /** @@ -2634,6 +2686,7 @@ int ata_dev_configure(struct ata_device *dev) ata_dev_config_sense_reporting(dev); ata_dev_config_zac(dev); ata_dev_config_trusted(dev); + ata_dev_config_cpr(dev); dev->cdb_len = 32; if (ata_msg_drv(ap) && print_info) diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c index 1fb4611f7eeb..15a279f773c7 100644 --- a/drivers/ata/libata-scsi.c +++ b/drivers/ata/libata-scsi.c @@ -1895,7 +1895,7 @@ static unsigned int ata_scsiop_inq_std(struct ata_scsi_args *args, u8 *rbuf) */ static unsigned int ata_scsiop_inq_00(struct ata_scsi_args *args, u8 *rbuf) { - int num_pages; + int i, num_pages = 0; static const u8 pages[] = { 0x00, /* page 0x00, this page */ 0x80, /* page 0x80, unit serial no page */ @@ -1905,13 +1905,17 @@ static unsigned int ata_scsiop_inq_00(struct ata_scsi_args *args, u8 *rbuf) 0xb1, /* page 0xb1, block device characteristics page */ 0xb2, /* page 0xb2, thin provisioning page */ 0xb6, /* page 0xb6, zoned block device characteristics */ + 0xb9, /* page 0xb9, concurrent positioning ranges */ }; - num_pages = sizeof(pages); - if (!(args->dev->flags & ATA_DFLAG_ZAC)) - num_pages--; + for (i = 0; i < sizeof(pages); i++) { + if (pages[i] == 0xb6 && + !(args->dev->flags & ATA_DFLAG_ZAC)) + continue; + rbuf[num_pages + 4] = pages[i]; + num_pages++; + } rbuf[3] = num_pages; /* number of supported VPD pages */ - memcpy(rbuf + 4, pages, num_pages); return 0; } @@ -2121,6 +2125,26 @@ static unsigned int ata_scsiop_inq_b6(struct ata_scsi_args *args, u8 *rbuf) return 0; } +static unsigned int ata_scsiop_inq_b9(struct ata_scsi_args *args, u8 *rbuf) +{ + struct ata_cpr_log *cpr_log = args->dev->cpr_log; + u8 *desc = &rbuf[64]; + int i; + + /* SCSI Concurrent Positioning Ranges VPD page: SBC-5 rev 1 or later */ + rbuf[1] = 0xb9; + put_unaligned_be16(64 + (int)cpr_log->nr_cpr * 32 - 4, &rbuf[3]); + + for (i = 0; i < cpr_log->nr_cpr; i++, desc += 32) { + desc[0] = cpr_log->cpr[i].num; + desc[1] = cpr_log->cpr[i].num_storage_elements; + put_unaligned_be64(cpr_log->cpr[i].start_lba, &desc[8]); + put_unaligned_be64(cpr_log->cpr[i].num_lbas, &desc[16]); + } + + return 0; +} + /** * modecpy - Prepare response for MODE SENSE * @dest: output buffer @@ -4120,11 +4144,17 @@ void ata_scsi_simulate(struct ata_device *dev, struct scsi_cmnd *cmd) ata_scsi_rbuf_fill(&args, ata_scsiop_inq_b2); break; case 0xb6: - if (dev->flags & ATA_DFLAG_ZAC) { + if (dev->flags & ATA_DFLAG_ZAC) ata_scsi_rbuf_fill(&args, ata_scsiop_inq_b6); - break; - } - fallthrough; + else + ata_scsi_set_invalid_field(dev, cmd, 2, 0xff); + break; + case 0xb9: + if (dev->cpr_log) + ata_scsi_rbuf_fill(&args, ata_scsiop_inq_b9); + else + ata_scsi_set_invalid_field(dev, cmd, 2, 0xff); + break; default: ata_scsi_set_invalid_field(dev, cmd, 2, 0xff); break; diff --git a/drivers/block/Kconfig b/drivers/block/Kconfig index ab3e37aa1830..f7f32eeaee63 100644 --- a/drivers/block/Kconfig +++ b/drivers/block/Kconfig @@ -180,14 +180,6 @@ config BLK_DEV_LOOP bits of, say, a sound file). This is also safe if the file resides on a remote file server. - There are several ways of encrypting disks. Some of these require - kernel patches. The vanilla kernel offers the cryptoloop option - and a Device Mapper target (which is superior, as it supports all - file systems). If you want to use the cryptoloop, say Y to both - LOOP and CRYPTOLOOP, and make sure you have a recent (version 2.12 - or later) version of util-linux. Additionally, be aware that - the cryptoloop is not safe for storing journaled filesystems. - Note that this loop device has nothing to do with the loopback device used for network connections from the machine to itself. @@ -211,21 +203,6 @@ config BLK_DEV_LOOP_MIN_COUNT is used, it can be set to 0, since needed loop devices can be dynamically allocated with the /dev/loop-control interface. -config BLK_DEV_CRYPTOLOOP - tristate "Cryptoloop Support (DEPRECATED)" - select CRYPTO - select CRYPTO_CBC - depends on BLK_DEV_LOOP - help - Say Y here if you want to be able to use the ciphers that are - provided by the CryptoAPI as loop transformation. This might be - used as hard disk encryption. - - WARNING: This device is not safe for journaled file systems like - ext3 or Reiserfs. Please use the Device Mapper crypto module - instead, which can be configured to be on-disk compatible with the - cryptoloop device. cryptoloop support will be removed in Linux 5.16. - source "drivers/block/drbd/Kconfig" config BLK_DEV_NBD diff --git a/drivers/block/Makefile b/drivers/block/Makefile index bc68817ef496..11a74f17c9ad 100644 --- a/drivers/block/Makefile +++ b/drivers/block/Makefile @@ -24,7 +24,6 @@ obj-$(CONFIG_CDROM_PKTCDVD) += pktcdvd.o obj-$(CONFIG_SUNVDC) += sunvdc.o obj-$(CONFIG_BLK_DEV_NBD) += nbd.o -obj-$(CONFIG_BLK_DEV_CRYPTOLOOP) += cryptoloop.o obj-$(CONFIG_VIRTIO_BLK) += virtio_blk.o obj-$(CONFIG_BLK_DEV_SX8) += sx8.o diff --git a/drivers/block/amiflop.c b/drivers/block/amiflop.c index 2909fd9e72fb..bf5c124c5452 100644 --- a/drivers/block/amiflop.c +++ b/drivers/block/amiflop.c @@ -1780,6 +1780,7 @@ static const struct blk_mq_ops amiflop_mq_ops = { static int fd_alloc_disk(int drive, int system) { struct gendisk *disk; + int err; disk = blk_mq_alloc_disk(&unit[drive].tag_set, NULL); if (IS_ERR(disk)) @@ -1798,8 +1799,10 @@ static int fd_alloc_disk(int drive, int system) set_capacity(disk, 880 * 2); unit[drive].gendisk[system] = disk; - add_disk(disk); - return 0; + err = add_disk(disk); + if (err) + blk_cleanup_disk(disk); + return err; } static int fd_alloc_drive(int drive) diff --git a/drivers/block/aoe/aoeblk.c b/drivers/block/aoe/aoeblk.c index 06b360f7123a..52484bcdedb9 100644 --- a/drivers/block/aoe/aoeblk.c +++ b/drivers/block/aoe/aoeblk.c @@ -37,8 +37,7 @@ static ssize_t aoedisk_show_state(struct device *dev, struct gendisk *disk = dev_to_disk(dev); struct aoedev *d = disk->private_data; - return snprintf(page, PAGE_SIZE, - "%s%s\n", + return sysfs_emit(page, "%s%s\n", (d->flags & DEVFL_UP) ? "up" : "down", (d->flags & DEVFL_KICKME) ? ",kickme" : (d->nopen && !(d->flags & DEVFL_UP)) ? ",closewait" : ""); @@ -52,8 +51,8 @@ static ssize_t aoedisk_show_mac(struct device *dev, struct aoetgt *t = d->targets[0]; if (t == NULL) - return snprintf(page, PAGE_SIZE, "none\n"); - return snprintf(page, PAGE_SIZE, "%pm\n", t->addr); + return sysfs_emit(page, "none\n"); + return sysfs_emit(page, "%pm\n", t->addr); } static ssize_t aoedisk_show_netif(struct device *dev, struct device_attribute *attr, char *page) @@ -85,7 +84,7 @@ static ssize_t aoedisk_show_netif(struct device *dev, ne = nd; nd = nds; if (*nd == NULL) - return snprintf(page, PAGE_SIZE, "none\n"); + return sysfs_emit(page, "none\n"); for (p = page; nd < ne; nd++) p += scnprintf(p, PAGE_SIZE - (p-page), "%s%s", p == page ? "" : ",", (*nd)->name); @@ -99,7 +98,7 @@ static ssize_t aoedisk_show_fwver(struct device *dev, struct gendisk *disk = dev_to_disk(dev); struct aoedev *d = disk->private_data; - return snprintf(page, PAGE_SIZE, "0x%04x\n", (unsigned int) d->fw_ver); + return sysfs_emit(page, "0x%04x\n", (unsigned int) d->fw_ver); } static ssize_t aoedisk_show_payload(struct device *dev, struct device_attribute *attr, char *page) @@ -107,7 +106,7 @@ static ssize_t aoedisk_show_payload(struct device *dev, struct gendisk *disk = dev_to_disk(dev); struct aoedev *d = disk->private_data; - return snprintf(page, PAGE_SIZE, "%lu\n", d->maxbcnt); + return sysfs_emit(page, "%lu\n", d->maxbcnt); } static int aoedisk_debugfs_show(struct seq_file *s, void *ignored) @@ -417,7 +416,9 @@ aoeblk_gdalloc(void *vp) spin_unlock_irqrestore(&d->lock, flags); - device_add_disk(NULL, gd, aoe_attr_groups); + err = device_add_disk(NULL, gd, aoe_attr_groups); + if (err) + goto out_disk_cleanup; aoedisk_add_debugfs(d); spin_lock_irqsave(&d->lock, flags); @@ -426,6 +427,8 @@ aoeblk_gdalloc(void *vp) spin_unlock_irqrestore(&d->lock, flags); return; +out_disk_cleanup: + blk_cleanup_disk(gd); err_tagset: blk_mq_free_tag_set(set); err_mempool: diff --git a/drivers/block/ataflop.c b/drivers/block/ataflop.c index 58e921ab5729..d14bdc3589b2 100644 --- a/drivers/block/ataflop.c +++ b/drivers/block/ataflop.c @@ -299,6 +299,7 @@ static struct atari_floppy_struct { disk change detection) */ int flags; /* flags */ struct gendisk *disk[NUM_DISK_MINORS]; + bool registered[NUM_DISK_MINORS]; int ref; int type; struct blk_mq_tag_set tag_set; @@ -457,10 +458,20 @@ static DEFINE_TIMER(fd_timer, check_change); static void fd_end_request_cur(blk_status_t err) { + DPRINT(("fd_end_request_cur(), bytes %d of %d\n", + blk_rq_cur_bytes(fd_request), + blk_rq_bytes(fd_request))); + if (!blk_update_request(fd_request, err, blk_rq_cur_bytes(fd_request))) { + DPRINT(("calling __blk_mq_end_request()\n")); __blk_mq_end_request(fd_request, err); fd_request = NULL; + } else { + /* requeue rest of request */ + DPRINT(("calling blk_mq_requeue_request()\n")); + blk_mq_requeue_request(fd_request, true); + fd_request = NULL; } } @@ -654,9 +665,6 @@ static inline void copy_buffer(void *from, void *to) *p2++ = *p1++; } - - - /* General Interrupt Handling */ static void (*FloppyIRQHandler)( int status ) = NULL; @@ -701,12 +709,21 @@ static void fd_error( void ) if (fd_request->error_count >= MAX_ERRORS) { printk(KERN_ERR "fd%d: too many errors.\n", SelectedDrive ); fd_end_request_cur(BLK_STS_IOERR); + finish_fdc(); + return; } else if (fd_request->error_count == RECALIBRATE_ERRORS) { printk(KERN_WARNING "fd%d: recalibrating\n", SelectedDrive ); if (SelectedDrive != -1) SUD.track = -1; } + /* need to re-run request to recalibrate */ + atari_disable_irq( IRQ_MFP_FDC ); + + setup_req_params( SelectedDrive ); + do_fd_action( SelectedDrive ); + + atari_enable_irq( IRQ_MFP_FDC ); } @@ -733,8 +750,10 @@ static int do_format(int drive, int type, struct atari_format_descr *desc) if (type) { type--; if (type >= NUM_DISK_MINORS || - minor2disktype[type].drive_types > DriveType) + minor2disktype[type].drive_types > DriveType) { + finish_fdc(); return -EINVAL; + } } q = unit[drive].disk[type]->queue; @@ -752,6 +771,7 @@ static int do_format(int drive, int type, struct atari_format_descr *desc) } if (!UDT || desc->track >= UDT->blocks/UDT->spt/2 || desc->head >= 2) { + finish_fdc(); ret = -EINVAL; goto out; } @@ -792,6 +812,7 @@ static int do_format(int drive, int type, struct atari_format_descr *desc) wait_for_completion(&format_wait); + finish_fdc(); ret = FormatError ? -EIO : 0; out: blk_mq_unquiesce_queue(q); @@ -826,6 +847,7 @@ static void do_fd_action( int drive ) else { /* all sectors finished */ fd_end_request_cur(BLK_STS_OK); + finish_fdc(); return; } } @@ -1230,6 +1252,7 @@ static void fd_rwsec_done1(int status) else { /* all sectors finished */ fd_end_request_cur(BLK_STS_OK); + finish_fdc(); } return; @@ -1351,7 +1374,7 @@ static void fd_times_out(struct timer_list *unused) static void finish_fdc( void ) { - if (!NeedSeek) { + if (!NeedSeek || !stdma_is_locked_by(floppy_irq)) { finish_fdc_done( 0 ); } else { @@ -1386,7 +1409,8 @@ static void finish_fdc_done( int dummy ) start_motor_off_timer(); local_irq_save(flags); - stdma_release(); + if (stdma_is_locked_by(floppy_irq)) + stdma_release(); local_irq_restore(flags); DPRINT(("finish_fdc() finished\n")); @@ -1436,8 +1460,7 @@ static int floppy_revalidate(struct gendisk *disk) unsigned int drive = p - unit; if (test_bit(drive, &changed_floppies) || - test_bit(drive, &fake_change) || - p->disktype == 0) { + test_bit(drive, &fake_change) || !p->disktype) { if (UD.flags & FTD_MSG) printk(KERN_ERR "floppy: clear format %p!\n", UDT); BufferDrive = -1; @@ -1476,15 +1499,6 @@ static void setup_req_params( int drive ) ReqTrack, ReqSector, (unsigned long)ReqData )); } -static void ataflop_commit_rqs(struct blk_mq_hw_ctx *hctx) -{ - spin_lock_irq(&ataflop_lock); - atari_disable_irq(IRQ_MFP_FDC); - finish_fdc(); - atari_enable_irq(IRQ_MFP_FDC); - spin_unlock_irq(&ataflop_lock); -} - static blk_status_t ataflop_queue_rq(struct blk_mq_hw_ctx *hctx, const struct blk_mq_queue_data *bd) { @@ -1492,6 +1506,10 @@ static blk_status_t ataflop_queue_rq(struct blk_mq_hw_ctx *hctx, int drive = floppy - unit; int type = floppy->type; + DPRINT(("Queue request: drive %d type %d sectors %d of %d last %d\n", + drive, type, blk_rq_cur_sectors(bd->rq), + blk_rq_sectors(bd->rq), bd->last)); + spin_lock_irq(&ataflop_lock); if (fd_request) { spin_unlock_irq(&ataflop_lock); @@ -1512,6 +1530,7 @@ static blk_status_t ataflop_queue_rq(struct blk_mq_hw_ctx *hctx, /* drive not connected */ printk(KERN_ERR "Unknown Device: fd%d\n", drive ); fd_end_request_cur(BLK_STS_IOERR); + stdma_release(); goto out; } @@ -1528,11 +1547,13 @@ static blk_status_t ataflop_queue_rq(struct blk_mq_hw_ctx *hctx, if (--type >= NUM_DISK_MINORS) { printk(KERN_WARNING "fd%d: invalid disk format", drive ); fd_end_request_cur(BLK_STS_IOERR); + stdma_release(); goto out; } if (minor2disktype[type].drive_types > DriveType) { printk(KERN_WARNING "fd%d: unsupported disk format", drive ); fd_end_request_cur(BLK_STS_IOERR); + stdma_release(); goto out; } type = minor2disktype[type].index; @@ -1551,8 +1572,6 @@ static blk_status_t ataflop_queue_rq(struct blk_mq_hw_ctx *hctx, setup_req_params( drive ); do_fd_action( drive ); - if (bd->last) - finish_fdc(); atari_enable_irq( IRQ_MFP_FDC ); out: @@ -1635,6 +1654,7 @@ static int fd_locked_ioctl(struct block_device *bdev, fmode_t mode, /* what if type > 0 here? Overwrite specified entry ? */ if (type) { /* refuse to re-set a predefined type for now */ + finish_fdc(); return -EINVAL; } @@ -1702,8 +1722,10 @@ static int fd_locked_ioctl(struct block_device *bdev, fmode_t mode, /* sanity check */ if (setprm.track != dtp->blocks/dtp->spt/2 || - setprm.head != 2) + setprm.head != 2) { + finish_fdc(); return -EINVAL; + } UDT = dtp; set_capacity(disk, UDT->blocks); @@ -1963,7 +1985,6 @@ static const struct block_device_operations floppy_fops = { static const struct blk_mq_ops ataflop_mq_ops = { .queue_rq = ataflop_queue_rq, - .commit_rqs = ataflop_commit_rqs, }; static int ataflop_alloc_disk(unsigned int drive, unsigned int type) @@ -2001,12 +2022,28 @@ static void ataflop_probe(dev_t dev) return; mutex_lock(&ataflop_probe_lock); if (!unit[drive].disk[type]) { - if (ataflop_alloc_disk(drive, type) == 0) + if (ataflop_alloc_disk(drive, type) == 0) { add_disk(unit[drive].disk[type]); + unit[drive].registered[type] = true; + } } mutex_unlock(&ataflop_probe_lock); } +static void atari_cleanup_floppy_disk(struct atari_floppy_struct *fs) +{ + int type; + + for (type = 0; type < NUM_DISK_MINORS; type++) { + if (!fs->disk[type]) + continue; + if (fs->registered[type]) + del_gendisk(fs->disk[type]); + blk_cleanup_disk(fs->disk[type]); + } + blk_mq_free_tag_set(&fs->tag_set); +} + static int __init atari_floppy_init (void) { int i; @@ -2065,7 +2102,10 @@ static int __init atari_floppy_init (void) for (i = 0; i < FD_MAX_UNITS; i++) { unit[i].track = -1; unit[i].flags = 0; - add_disk(unit[i].disk[0]); + ret = add_disk(unit[i].disk[0]); + if (ret) + goto err_out_dma; + unit[i].registered[0] = true; } printk(KERN_INFO "Atari floppy driver: max. %cD, %strack buffering\n", @@ -2075,12 +2115,11 @@ static int __init atari_floppy_init (void) return 0; +err_out_dma: + atari_stram_free(DMABuffer); err: - while (--i >= 0) { - blk_cleanup_queue(unit[i].disk[0]->queue); - put_disk(unit[i].disk[0]); - blk_mq_free_tag_set(&unit[i].tag_set); - } + while (--i >= 0) + atari_cleanup_floppy_disk(&unit[i]); unregister_blkdev(FLOPPY_MAJOR, "fd"); out_unlock: @@ -2129,18 +2168,10 @@ __setup("floppy=", atari_floppy_setup); static void __exit atari_floppy_exit(void) { - int i, type; + int i; - for (i = 0; i < FD_MAX_UNITS; i++) { - for (type = 0; type < NUM_DISK_MINORS; type++) { - if (!unit[i].disk[type]) - continue; - del_gendisk(unit[i].disk[type]); - blk_cleanup_queue(unit[i].disk[type]->queue); - put_disk(unit[i].disk[type]); - } - blk_mq_free_tag_set(&unit[i].tag_set); - } + for (i = 0; i < FD_MAX_UNITS; i++) + atari_cleanup_floppy_disk(&unit[i]); unregister_blkdev(FLOPPY_MAJOR, "fd"); del_timer_sync(&fd_timer); diff --git a/drivers/block/cryptoloop.c b/drivers/block/cryptoloop.c deleted file mode 100644 index f0a91faa43a8..000000000000 --- a/drivers/block/cryptoloop.c +++ /dev/null @@ -1,206 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-or-later -/* - Linux loop encryption enabling module - - Copyright (C) 2002 Herbert Valerio Riedel - Copyright (C) 2003 Fruhwirth Clemens - - */ - -#include - -#include -#include -#include -#include -#include -#include -#include "loop.h" - -MODULE_LICENSE("GPL"); -MODULE_DESCRIPTION("loop blockdevice transferfunction adaptor / CryptoAPI"); -MODULE_AUTHOR("Herbert Valerio Riedel "); - -#define LOOP_IV_SECTOR_BITS 9 -#define LOOP_IV_SECTOR_SIZE (1 << LOOP_IV_SECTOR_BITS) - -static int -cryptoloop_init(struct loop_device *lo, const struct loop_info64 *info) -{ - int err = -EINVAL; - int cipher_len; - int mode_len; - char cms[LO_NAME_SIZE]; /* cipher-mode string */ - char *mode; - char *cmsp = cms; /* c-m string pointer */ - struct crypto_sync_skcipher *tfm; - - /* encryption breaks for non sector aligned offsets */ - - if (info->lo_offset % LOOP_IV_SECTOR_SIZE) - goto out; - - strncpy(cms, info->lo_crypt_name, LO_NAME_SIZE); - cms[LO_NAME_SIZE - 1] = 0; - - cipher_len = strcspn(cmsp, "-"); - - mode = cmsp + cipher_len; - mode_len = 0; - if (*mode) { - mode++; - mode_len = strcspn(mode, "-"); - } - - if (!mode_len) { - mode = "cbc"; - mode_len = 3; - } - - if (cipher_len + mode_len + 3 > LO_NAME_SIZE) - return -EINVAL; - - memmove(cms, mode, mode_len); - cmsp = cms + mode_len; - *cmsp++ = '('; - memcpy(cmsp, info->lo_crypt_name, cipher_len); - cmsp += cipher_len; - *cmsp++ = ')'; - *cmsp = 0; - - tfm = crypto_alloc_sync_skcipher(cms, 0, 0); - if (IS_ERR(tfm)) - return PTR_ERR(tfm); - - err = crypto_sync_skcipher_setkey(tfm, info->lo_encrypt_key, - info->lo_encrypt_key_size); - - if (err != 0) - goto out_free_tfm; - - lo->key_data = tfm; - return 0; - - out_free_tfm: - crypto_free_sync_skcipher(tfm); - - out: - return err; -} - - -typedef int (*encdec_cbc_t)(struct skcipher_request *req); - -static int -cryptoloop_transfer(struct loop_device *lo, int cmd, - struct page *raw_page, unsigned raw_off, - struct page *loop_page, unsigned loop_off, - int size, sector_t IV) -{ - struct crypto_sync_skcipher *tfm = lo->key_data; - SYNC_SKCIPHER_REQUEST_ON_STACK(req, tfm); - struct scatterlist sg_out; - struct scatterlist sg_in; - - encdec_cbc_t encdecfunc; - struct page *in_page, *out_page; - unsigned in_offs, out_offs; - int err; - - skcipher_request_set_sync_tfm(req, tfm); - skcipher_request_set_callback(req, CRYPTO_TFM_REQ_MAY_SLEEP, - NULL, NULL); - - sg_init_table(&sg_out, 1); - sg_init_table(&sg_in, 1); - - if (cmd == READ) { - in_page = raw_page; - in_offs = raw_off; - out_page = loop_page; - out_offs = loop_off; - encdecfunc = crypto_skcipher_decrypt; - } else { - in_page = loop_page; - in_offs = loop_off; - out_page = raw_page; - out_offs = raw_off; - encdecfunc = crypto_skcipher_encrypt; - } - - while (size > 0) { - const int sz = min(size, LOOP_IV_SECTOR_SIZE); - u32 iv[4] = { 0, }; - iv[0] = cpu_to_le32(IV & 0xffffffff); - - sg_set_page(&sg_in, in_page, sz, in_offs); - sg_set_page(&sg_out, out_page, sz, out_offs); - - skcipher_request_set_crypt(req, &sg_in, &sg_out, sz, iv); - err = encdecfunc(req); - if (err) - goto out; - - IV++; - size -= sz; - in_offs += sz; - out_offs += sz; - } - - err = 0; - -out: - skcipher_request_zero(req); - return err; -} - -static int -cryptoloop_ioctl(struct loop_device *lo, int cmd, unsigned long arg) -{ - return -EINVAL; -} - -static int -cryptoloop_release(struct loop_device *lo) -{ - struct crypto_sync_skcipher *tfm = lo->key_data; - if (tfm != NULL) { - crypto_free_sync_skcipher(tfm); - lo->key_data = NULL; - return 0; - } - printk(KERN_ERR "cryptoloop_release(): tfm == NULL?\n"); - return -EINVAL; -} - -static struct loop_func_table cryptoloop_funcs = { - .number = LO_CRYPT_CRYPTOAPI, - .init = cryptoloop_init, - .ioctl = cryptoloop_ioctl, - .transfer = cryptoloop_transfer, - .release = cryptoloop_release, - .owner = THIS_MODULE -}; - -static int __init -init_cryptoloop(void) -{ - int rc = loop_register_transfer(&cryptoloop_funcs); - - if (rc) - printk(KERN_ERR "cryptoloop: loop_register_transfer failed\n"); - else - pr_warn("the cryptoloop driver has been deprecated and will be removed in in Linux 5.16\n"); - return rc; -} - -static void __exit -cleanup_cryptoloop(void) -{ - if (loop_unregister_transfer(LO_CRYPT_CRYPTOAPI)) - printk(KERN_ERR - "cryptoloop: loop_unregister_transfer failed\n"); -} - -module_init(init_cryptoloop); -module_exit(cleanup_cryptoloop); diff --git a/drivers/block/drbd/drbd_int.h b/drivers/block/drbd/drbd_int.h index 6674a0b88341..f27d5b0f9a0b 100644 --- a/drivers/block/drbd/drbd_int.h +++ b/drivers/block/drbd/drbd_int.h @@ -1826,8 +1826,7 @@ static inline sector_t drbd_md_last_sector(struct drbd_backing_dev *bdev) /* Returns the number of 512 byte sectors of the device */ static inline sector_t drbd_get_capacity(struct block_device *bdev) { - /* return bdev ? get_capacity(bdev->bd_disk) : 0; */ - return bdev ? i_size_read(bdev->bd_inode) >> 9 : 0; + return bdev ? bdev_nr_sectors(bdev) : 0; } /** diff --git a/drivers/block/drbd/drbd_main.c b/drivers/block/drbd/drbd_main.c index 55234a558e98..19db80a1e409 100644 --- a/drivers/block/drbd/drbd_main.c +++ b/drivers/block/drbd/drbd_main.c @@ -2794,7 +2794,9 @@ enum drbd_ret_code drbd_create_device(struct drbd_config_context *adm_ctx, unsig goto out_idr_remove_vol; } - add_disk(disk); + err = add_disk(disk); + if (err) + goto out_cleanup_disk; /* inherit the connection state */ device->state.conn = first_connection(resource)->cstate; @@ -2808,6 +2810,8 @@ enum drbd_ret_code drbd_create_device(struct drbd_config_context *adm_ctx, unsig drbd_debugfs_device_add(device); return NO_ERROR; +out_cleanup_disk: + blk_cleanup_disk(disk); out_idr_remove_vol: idr_remove(&connection->peer_devices, vnr); out_idr_remove_from_resource: diff --git a/drivers/block/floppy.c b/drivers/block/floppy.c index 6288ce888414..3873e789478e 100644 --- a/drivers/block/floppy.c +++ b/drivers/block/floppy.c @@ -4479,6 +4479,7 @@ static const struct blk_mq_ops floppy_mq_ops = { }; static struct platform_device floppy_device[N_DRIVE]; +static bool registered[N_DRIVE]; static bool floppy_available(int drive) { @@ -4694,8 +4695,12 @@ static int __init do_floppy_init(void) if (err) goto out_remove_drives; - device_add_disk(&floppy_device[drive].dev, disks[drive][0], - NULL); + registered[drive] = true; + + err = device_add_disk(&floppy_device[drive].dev, + disks[drive][0], NULL); + if (err) + goto out_remove_drives; } return 0; @@ -4704,7 +4709,8 @@ out_remove_drives: while (drive--) { if (floppy_available(drive)) { del_gendisk(disks[drive][0]); - platform_device_unregister(&floppy_device[drive]); + if (registered[drive]) + platform_device_unregister(&floppy_device[drive]); } } out_release_dma: @@ -4947,30 +4953,14 @@ static void __exit floppy_module_exit(void) if (disks[drive][i]) del_gendisk(disks[drive][i]); } - platform_device_unregister(&floppy_device[drive]); + if (registered[drive]) + platform_device_unregister(&floppy_device[drive]); } for (i = 0; i < ARRAY_SIZE(floppy_type); i++) { if (disks[drive][i]) - blk_cleanup_queue(disks[drive][i]->queue); + blk_cleanup_disk(disks[drive][i]); } blk_mq_free_tag_set(&tag_sets[drive]); - - /* - * These disks have not called add_disk(). Don't put down - * queue reference in put_disk(). - */ - if (!(allowed_drive_mask & (1 << drive)) || - fdc_state[FDC(drive)].version == FDC_NONE) { - for (i = 0; i < ARRAY_SIZE(floppy_type); i++) { - if (disks[drive][i]) - disks[drive][i]->queue = NULL; - } - } - - for (i = 0; i < ARRAY_SIZE(floppy_type); i++) { - if (disks[drive][i]) - put_disk(disks[drive][i]); - } } cancel_delayed_work_sync(&fd_timeout); diff --git a/drivers/block/loop.c b/drivers/block/loop.c index ab23bbc467e7..f094de5f0056 100644 --- a/drivers/block/loop.c +++ b/drivers/block/loop.c @@ -133,58 +133,6 @@ static void loop_global_unlock(struct loop_device *lo, bool global) static int max_part; static int part_shift; -static int transfer_xor(struct loop_device *lo, int cmd, - struct page *raw_page, unsigned raw_off, - struct page *loop_page, unsigned loop_off, - int size, sector_t real_block) -{ - char *raw_buf = kmap_atomic(raw_page) + raw_off; - char *loop_buf = kmap_atomic(loop_page) + loop_off; - char *in, *out, *key; - int i, keysize; - - if (cmd == READ) { - in = raw_buf; - out = loop_buf; - } else { - in = loop_buf; - out = raw_buf; - } - - key = lo->lo_encrypt_key; - keysize = lo->lo_encrypt_key_size; - for (i = 0; i < size; i++) - *out++ = *in++ ^ key[(i & 511) % keysize]; - - kunmap_atomic(loop_buf); - kunmap_atomic(raw_buf); - cond_resched(); - return 0; -} - -static int xor_init(struct loop_device *lo, const struct loop_info64 *info) -{ - if (unlikely(info->lo_encrypt_key_size <= 0)) - return -EINVAL; - return 0; -} - -static struct loop_func_table none_funcs = { - .number = LO_CRYPT_NONE, -}; - -static struct loop_func_table xor_funcs = { - .number = LO_CRYPT_XOR, - .transfer = transfer_xor, - .init = xor_init -}; - -/* xfer_funcs[0] is special - its release function is never called */ -static struct loop_func_table *xfer_funcs[MAX_LO_CRYPT] = { - &none_funcs, - &xor_funcs -}; - static loff_t get_size(loff_t offset, loff_t sizelimit, struct file *file) { loff_t loopsize; @@ -228,8 +176,7 @@ static void __loop_update_dio(struct loop_device *lo, bool dio) /* * We support direct I/O only if lo_offset is aligned with the * logical I/O size of backing device, and the logical block - * size of loop is bigger than the backing device's and the loop - * needn't transform transfer. + * size of loop is bigger than the backing device's. * * TODO: the above condition may be loosed in the future, and * direct I/O may be switched runtime at that time because most @@ -238,8 +185,7 @@ static void __loop_update_dio(struct loop_device *lo, bool dio) if (dio) { if (queue_logical_block_size(lo->lo_queue) >= sb_bsize && !(lo->lo_offset & dio_align) && - mapping->a_ops->direct_IO && - !lo->transfer) + mapping->a_ops->direct_IO) use_dio = true; else use_dio = false; @@ -286,24 +232,6 @@ static void loop_set_size(struct loop_device *lo, loff_t size) kobject_uevent(&disk_to_dev(lo->lo_disk)->kobj, KOBJ_CHANGE); } -static inline int -lo_do_transfer(struct loop_device *lo, int cmd, - struct page *rpage, unsigned roffs, - struct page *lpage, unsigned loffs, - int size, sector_t rblock) -{ - int ret; - - ret = lo->transfer(lo, cmd, rpage, roffs, lpage, loffs, size, rblock); - if (likely(!ret)) - return 0; - - printk_ratelimited(KERN_ERR - "loop: Transfer error at byte offset %llu, length %i.\n", - (unsigned long long)rblock << 9, size); - return ret; -} - static int lo_write_bvec(struct file *file, struct bio_vec *bvec, loff_t *ppos) { struct iov_iter i; @@ -343,41 +271,6 @@ static int lo_write_simple(struct loop_device *lo, struct request *rq, return ret; } -/* - * This is the slow, transforming version that needs to double buffer the - * data as it cannot do the transformations in place without having direct - * access to the destination pages of the backing file. - */ -static int lo_write_transfer(struct loop_device *lo, struct request *rq, - loff_t pos) -{ - struct bio_vec bvec, b; - struct req_iterator iter; - struct page *page; - int ret = 0; - - page = alloc_page(GFP_NOIO); - if (unlikely(!page)) - return -ENOMEM; - - rq_for_each_segment(bvec, rq, iter) { - ret = lo_do_transfer(lo, WRITE, page, 0, bvec.bv_page, - bvec.bv_offset, bvec.bv_len, pos >> 9); - if (unlikely(ret)) - break; - - b.bv_page = page; - b.bv_offset = 0; - b.bv_len = bvec.bv_len; - ret = lo_write_bvec(lo->lo_backing_file, &b, &pos); - if (ret < 0) - break; - } - - __free_page(page); - return ret; -} - static int lo_read_simple(struct loop_device *lo, struct request *rq, loff_t pos) { @@ -407,64 +300,12 @@ static int lo_read_simple(struct loop_device *lo, struct request *rq, return 0; } -static int lo_read_transfer(struct loop_device *lo, struct request *rq, - loff_t pos) -{ - struct bio_vec bvec, b; - struct req_iterator iter; - struct iov_iter i; - struct page *page; - ssize_t len; - int ret = 0; - - page = alloc_page(GFP_NOIO); - if (unlikely(!page)) - return -ENOMEM; - - rq_for_each_segment(bvec, rq, iter) { - loff_t offset = pos; - - b.bv_page = page; - b.bv_offset = 0; - b.bv_len = bvec.bv_len; - - iov_iter_bvec(&i, READ, &b, 1, b.bv_len); - len = vfs_iter_read(lo->lo_backing_file, &i, &pos, 0); - if (len < 0) { - ret = len; - goto out_free_page; - } - - ret = lo_do_transfer(lo, READ, page, 0, bvec.bv_page, - bvec.bv_offset, len, offset >> 9); - if (ret) - goto out_free_page; - - flush_dcache_page(bvec.bv_page); - - if (len != bvec.bv_len) { - struct bio *bio; - - __rq_for_each_bio(bio, rq) - zero_fill_bio(bio); - break; - } - } - - ret = 0; -out_free_page: - __free_page(page); - return ret; -} - static int lo_fallocate(struct loop_device *lo, struct request *rq, loff_t pos, int mode) { /* * We use fallocate to manipulate the space mappings used by the image - * a.k.a. discard/zerorange. However we do not support this if - * encryption is enabled, because it may give an attacker useful - * information. + * a.k.a. discard/zerorange. */ struct file *file = lo->lo_backing_file; struct request_queue *q = lo->lo_queue; @@ -647,16 +488,12 @@ static int do_req_filebacked(struct loop_device *lo, struct request *rq) case REQ_OP_DISCARD: return lo_fallocate(lo, rq, pos, FALLOC_FL_PUNCH_HOLE); case REQ_OP_WRITE: - if (lo->transfer) - return lo_write_transfer(lo, rq, pos); - else if (cmd->use_aio) + if (cmd->use_aio) return lo_rw_aio(lo, cmd, pos, WRITE); else return lo_write_simple(lo, rq, pos); case REQ_OP_READ: - if (lo->transfer) - return lo_read_transfer(lo, rq, pos); - else if (cmd->use_aio) + if (cmd->use_aio) return lo_rw_aio(lo, cmd, pos, READ); else return lo_read_simple(lo, rq, pos); @@ -921,7 +758,7 @@ static void loop_config_discard(struct loop_device *lo) * not blkdev_issue_discard(). This maintains consistent behavior with * file-backed loop devices: discarded regions read back as zero. */ - if (S_ISBLK(inode->i_mode) && !lo->lo_encrypt_key_size) { + if (S_ISBLK(inode->i_mode)) { struct request_queue *backingq = bdev_get_queue(I_BDEV(inode)); max_discard_sectors = backingq->limits.max_write_zeroes_sectors; @@ -930,11 +767,9 @@ static void loop_config_discard(struct loop_device *lo) /* * We use punch hole to reclaim the free space used by the - * image a.k.a. discard. However we do not support discard if - * encryption is enabled, because it may give an attacker - * useful information. + * image a.k.a. discard. */ - } else if (!file->f_op->fallocate || lo->lo_encrypt_key_size) { + } else if (!file->f_op->fallocate) { max_discard_sectors = 0; granularity = 0; @@ -1071,43 +906,6 @@ static void loop_update_rotational(struct loop_device *lo) blk_queue_flag_clear(QUEUE_FLAG_NONROT, q); } -static int -loop_release_xfer(struct loop_device *lo) -{ - int err = 0; - struct loop_func_table *xfer = lo->lo_encryption; - - if (xfer) { - if (xfer->release) - err = xfer->release(lo); - lo->transfer = NULL; - lo->lo_encryption = NULL; - module_put(xfer->owner); - } - return err; -} - -static int -loop_init_xfer(struct loop_device *lo, struct loop_func_table *xfer, - const struct loop_info64 *i) -{ - int err = 0; - - if (xfer) { - struct module *owner = xfer->owner; - - if (!try_module_get(owner)) - return -EINVAL; - if (xfer->init) - err = xfer->init(lo, i); - if (err) - module_put(owner); - else - lo->lo_encryption = xfer; - } - return err; -} - /** * loop_set_status_from_info - configure device from loop_info * @lo: struct loop_device to configure @@ -1120,55 +918,27 @@ static int loop_set_status_from_info(struct loop_device *lo, const struct loop_info64 *info) { - int err; - struct loop_func_table *xfer; - kuid_t uid = current_uid(); - if ((unsigned int) info->lo_encrypt_key_size > LO_KEY_SIZE) return -EINVAL; - err = loop_release_xfer(lo); - if (err) - return err; - - if (info->lo_encrypt_type) { - unsigned int type = info->lo_encrypt_type; - - if (type >= MAX_LO_CRYPT) - return -EINVAL; - xfer = xfer_funcs[type]; - if (xfer == NULL) - return -EINVAL; - } else - xfer = NULL; - - err = loop_init_xfer(lo, xfer, info); - if (err) - return err; + switch (info->lo_encrypt_type) { + case LO_CRYPT_NONE: + break; + case LO_CRYPT_XOR: + pr_warn("support for the xor transformation has been removed.\n"); + return -EINVAL; + case LO_CRYPT_CRYPTOAPI: + pr_warn("support for cryptoloop has been removed. Use dm-crypt instead.\n"); + return -EINVAL; + default: + return -EINVAL; + } lo->lo_offset = info->lo_offset; lo->lo_sizelimit = info->lo_sizelimit; memcpy(lo->lo_file_name, info->lo_file_name, LO_NAME_SIZE); - memcpy(lo->lo_crypt_name, info->lo_crypt_name, LO_NAME_SIZE); lo->lo_file_name[LO_NAME_SIZE-1] = 0; - lo->lo_crypt_name[LO_NAME_SIZE-1] = 0; - - if (!xfer) - xfer = &none_funcs; - lo->transfer = xfer->transfer; - lo->ioctl = xfer->ioctl; - lo->lo_flags = info->lo_flags; - - lo->lo_encrypt_key_size = info->lo_encrypt_key_size; - lo->lo_init[0] = info->lo_init[0]; - lo->lo_init[1] = info->lo_init[1]; - if (info->lo_encrypt_key_size) { - memcpy(lo->lo_encrypt_key, info->lo_encrypt_key, - info->lo_encrypt_key_size); - lo->lo_key_owner = uid; - } - return 0; } @@ -1367,16 +1137,9 @@ static int __loop_clr_fd(struct loop_device *lo, bool release) lo->lo_backing_file = NULL; spin_unlock_irq(&lo->lo_lock); - loop_release_xfer(lo); - lo->transfer = NULL; - lo->ioctl = NULL; lo->lo_device = NULL; - lo->lo_encryption = NULL; lo->lo_offset = 0; lo->lo_sizelimit = 0; - lo->lo_encrypt_key_size = 0; - memset(lo->lo_encrypt_key, 0, LO_KEY_SIZE); - memset(lo->lo_crypt_name, 0, LO_NAME_SIZE); memset(lo->lo_file_name, 0, LO_NAME_SIZE); blk_queue_logical_block_size(lo->lo_queue, 512); blk_queue_physical_block_size(lo->lo_queue, 512); @@ -1478,7 +1241,6 @@ static int loop_set_status(struct loop_device *lo, const struct loop_info64 *info) { int err; - kuid_t uid = current_uid(); int prev_lo_flags; bool partscan = false; bool size_changed = false; @@ -1486,12 +1248,6 @@ loop_set_status(struct loop_device *lo, const struct loop_info64 *info) err = mutex_lock_killable(&lo->lo_mutex); if (err) return err; - if (lo->lo_encrypt_key_size && - !uid_eq(lo->lo_key_owner, uid) && - !capable(CAP_SYS_ADMIN)) { - err = -EPERM; - goto out_unlock; - } if (lo->lo_state != Lo_bound) { err = -ENXIO; goto out_unlock; @@ -1577,14 +1333,6 @@ loop_get_status(struct loop_device *lo, struct loop_info64 *info) info->lo_sizelimit = lo->lo_sizelimit; info->lo_flags = lo->lo_flags; memcpy(info->lo_file_name, lo->lo_file_name, LO_NAME_SIZE); - memcpy(info->lo_crypt_name, lo->lo_crypt_name, LO_NAME_SIZE); - info->lo_encrypt_type = - lo->lo_encryption ? lo->lo_encryption->number : 0; - if (lo->lo_encrypt_key_size && capable(CAP_SYS_ADMIN)) { - info->lo_encrypt_key_size = lo->lo_encrypt_key_size; - memcpy(info->lo_encrypt_key, lo->lo_encrypt_key, - lo->lo_encrypt_key_size); - } /* Drop lo_mutex while we call into the filesystem. */ path = lo->lo_backing_file->f_path; @@ -1610,16 +1358,8 @@ loop_info64_from_old(const struct loop_info *info, struct loop_info64 *info64) info64->lo_rdevice = info->lo_rdevice; info64->lo_offset = info->lo_offset; info64->lo_sizelimit = 0; - info64->lo_encrypt_type = info->lo_encrypt_type; - info64->lo_encrypt_key_size = info->lo_encrypt_key_size; info64->lo_flags = info->lo_flags; - info64->lo_init[0] = info->lo_init[0]; - info64->lo_init[1] = info->lo_init[1]; - if (info->lo_encrypt_type == LO_CRYPT_CRYPTOAPI) - memcpy(info64->lo_crypt_name, info->lo_name, LO_NAME_SIZE); - else - memcpy(info64->lo_file_name, info->lo_name, LO_NAME_SIZE); - memcpy(info64->lo_encrypt_key, info->lo_encrypt_key, LO_KEY_SIZE); + memcpy(info64->lo_file_name, info->lo_name, LO_NAME_SIZE); } static int @@ -1631,16 +1371,8 @@ loop_info64_to_old(const struct loop_info64 *info64, struct loop_info *info) info->lo_inode = info64->lo_inode; info->lo_rdevice = info64->lo_rdevice; info->lo_offset = info64->lo_offset; - info->lo_encrypt_type = info64->lo_encrypt_type; - info->lo_encrypt_key_size = info64->lo_encrypt_key_size; info->lo_flags = info64->lo_flags; - info->lo_init[0] = info64->lo_init[0]; - info->lo_init[1] = info64->lo_init[1]; - if (info->lo_encrypt_type == LO_CRYPT_CRYPTOAPI) - memcpy(info->lo_name, info64->lo_crypt_name, LO_NAME_SIZE); - else - memcpy(info->lo_name, info64->lo_file_name, LO_NAME_SIZE); - memcpy(info->lo_encrypt_key, info64->lo_encrypt_key, LO_KEY_SIZE); + memcpy(info->lo_name, info64->lo_file_name, LO_NAME_SIZE); /* error in case values were truncated */ if (info->lo_device != info64->lo_device || @@ -1789,7 +1521,7 @@ static int lo_simple_ioctl(struct loop_device *lo, unsigned int cmd, err = loop_set_block_size(lo, arg); break; default: - err = lo->ioctl ? lo->ioctl(lo, cmd, arg) : -EINVAL; + err = -EINVAL; } mutex_unlock(&lo->lo_mutex); return err; @@ -1865,7 +1597,6 @@ struct compat_loop_info { compat_ulong_t lo_inode; /* ioctl r/o */ compat_dev_t lo_rdevice; /* ioctl r/o */ compat_int_t lo_offset; - compat_int_t lo_encrypt_type; compat_int_t lo_encrypt_key_size; /* ioctl w/o */ compat_int_t lo_flags; /* ioctl r/o */ char lo_name[LO_NAME_SIZE]; @@ -1894,16 +1625,8 @@ loop_info64_from_compat(const struct compat_loop_info __user *arg, info64->lo_rdevice = info.lo_rdevice; info64->lo_offset = info.lo_offset; info64->lo_sizelimit = 0; - info64->lo_encrypt_type = info.lo_encrypt_type; - info64->lo_encrypt_key_size = info.lo_encrypt_key_size; info64->lo_flags = info.lo_flags; - info64->lo_init[0] = info.lo_init[0]; - info64->lo_init[1] = info.lo_init[1]; - if (info.lo_encrypt_type == LO_CRYPT_CRYPTOAPI) - memcpy(info64->lo_crypt_name, info.lo_name, LO_NAME_SIZE); - else - memcpy(info64->lo_file_name, info.lo_name, LO_NAME_SIZE); - memcpy(info64->lo_encrypt_key, info.lo_encrypt_key, LO_KEY_SIZE); + memcpy(info64->lo_file_name, info.lo_name, LO_NAME_SIZE); return 0; } @@ -1923,24 +1646,14 @@ loop_info64_to_compat(const struct loop_info64 *info64, info.lo_inode = info64->lo_inode; info.lo_rdevice = info64->lo_rdevice; info.lo_offset = info64->lo_offset; - info.lo_encrypt_type = info64->lo_encrypt_type; - info.lo_encrypt_key_size = info64->lo_encrypt_key_size; info.lo_flags = info64->lo_flags; - info.lo_init[0] = info64->lo_init[0]; - info.lo_init[1] = info64->lo_init[1]; - if (info.lo_encrypt_type == LO_CRYPT_CRYPTOAPI) - memcpy(info.lo_name, info64->lo_crypt_name, LO_NAME_SIZE); - else - memcpy(info.lo_name, info64->lo_file_name, LO_NAME_SIZE); - memcpy(info.lo_encrypt_key, info64->lo_encrypt_key, LO_KEY_SIZE); + memcpy(info.lo_name, info64->lo_file_name, LO_NAME_SIZE); /* error in case values were truncated */ if (info.lo_device != info64->lo_device || info.lo_rdevice != info64->lo_rdevice || info.lo_inode != info64->lo_inode || - info.lo_offset != info64->lo_offset || - info.lo_init[0] != info64->lo_init[0] || - info.lo_init[1] != info64->lo_init[1]) + info.lo_offset != info64->lo_offset) return -EOVERFLOW; if (copy_to_user(arg, &info, sizeof(info))) @@ -2081,43 +1794,6 @@ MODULE_PARM_DESC(max_part, "Maximum number of partitions per loop device"); MODULE_LICENSE("GPL"); MODULE_ALIAS_BLOCKDEV_MAJOR(LOOP_MAJOR); -int loop_register_transfer(struct loop_func_table *funcs) -{ - unsigned int n = funcs->number; - - if (n >= MAX_LO_CRYPT || xfer_funcs[n]) - return -EINVAL; - xfer_funcs[n] = funcs; - return 0; -} - -int loop_unregister_transfer(int number) -{ - unsigned int n = number; - struct loop_func_table *xfer; - - if (n == 0 || n >= MAX_LO_CRYPT || (xfer = xfer_funcs[n]) == NULL) - return -EINVAL; - /* - * This function is called from only cleanup_cryptoloop(). - * Given that each loop device that has a transfer enabled holds a - * reference to the module implementing it we should never get here - * with a transfer that is set (unless forced module unloading is - * requested). Thus, check module's refcount and warn if this is - * not a clean unloading. - */ -#ifdef CONFIG_MODULE_UNLOAD - if (xfer->owner && module_refcount(xfer->owner) != -1) - pr_err("Danger! Unregistering an in use transfer function.\n"); -#endif - - xfer_funcs[n] = NULL; - return 0; -} - -EXPORT_SYMBOL(loop_register_transfer); -EXPORT_SYMBOL(loop_unregister_transfer); - static blk_status_t loop_queue_rq(struct blk_mq_hw_ctx *hctx, const struct blk_mq_queue_data *bd) { @@ -2374,13 +2050,19 @@ static int loop_add(int i) disk->event_flags = DISK_EVENT_FLAG_UEVENT; sprintf(disk->disk_name, "loop%d", i); /* Make this loop device reachable from pathname. */ - add_disk(disk); + err = add_disk(disk); + if (err) + goto out_cleanup_disk; + /* Show this loop device. */ mutex_lock(&loop_ctl_mutex); lo->idr_visible = true; mutex_unlock(&loop_ctl_mutex); + return i; +out_cleanup_disk: + blk_cleanup_disk(disk); out_cleanup_tags: blk_mq_free_tag_set(&lo->tag_set); out_free_idr: diff --git a/drivers/block/loop.h b/drivers/block/loop.h index 04c88dd6eabd..082d4b6bfc6a 100644 --- a/drivers/block/loop.h +++ b/drivers/block/loop.h @@ -32,23 +32,10 @@ struct loop_device { loff_t lo_offset; loff_t lo_sizelimit; int lo_flags; - int (*transfer)(struct loop_device *, int cmd, - struct page *raw_page, unsigned raw_off, - struct page *loop_page, unsigned loop_off, - int size, sector_t real_block); char lo_file_name[LO_NAME_SIZE]; - char lo_crypt_name[LO_NAME_SIZE]; - char lo_encrypt_key[LO_KEY_SIZE]; - int lo_encrypt_key_size; - struct loop_func_table *lo_encryption; - __u32 lo_init[2]; - kuid_t lo_key_owner; /* Who set the key */ - int (*ioctl)(struct loop_device *, int cmd, - unsigned long arg); struct file * lo_backing_file; struct block_device *lo_device; - void *key_data; gfp_t old_gfp_mask; @@ -82,21 +69,4 @@ struct loop_cmd { struct cgroup_subsys_state *memcg_css; }; -/* Support for loadable transfer modules */ -struct loop_func_table { - int number; /* filter type */ - int (*transfer)(struct loop_device *lo, int cmd, - struct page *raw_page, unsigned raw_off, - struct page *loop_page, unsigned loop_off, - int size, sector_t real_block); - int (*init)(struct loop_device *, const struct loop_info64 *); - /* release is called from loop_unregister_transfer or clr_fd */ - int (*release)(struct loop_device *); - int (*ioctl)(struct loop_device *, int cmd, unsigned long arg); - struct module *owner; -}; - -int loop_register_transfer(struct loop_func_table *funcs); -int loop_unregister_transfer(int number); - #endif diff --git a/drivers/block/mtip32xx/mtip32xx.c b/drivers/block/mtip32xx/mtip32xx.c index 901855717cb5..c91b9010c1a6 100644 --- a/drivers/block/mtip32xx/mtip32xx.c +++ b/drivers/block/mtip32xx/mtip32xx.c @@ -3633,7 +3633,9 @@ skip_create_disk: set_capacity(dd->disk, capacity); /* Enable the block device and add it to /dev */ - device_add_disk(&dd->pdev->dev, dd->disk, mtip_disk_attr_groups); + rv = device_add_disk(&dd->pdev->dev, dd->disk, mtip_disk_attr_groups); + if (rv) + goto read_capacity_error; if (dd->mtip_svc_handler) { set_bit(MTIP_DDF_INIT_DONE_BIT, &dd->dd_flag); @@ -4061,7 +4063,6 @@ block_initialize_err: msi_initialize_err: if (dd->isr_workq) { - flush_workqueue(dd->isr_workq); destroy_workqueue(dd->isr_workq); drop_cpu(dd->work[0].cpu_binding); drop_cpu(dd->work[1].cpu_binding); @@ -4119,7 +4120,6 @@ static void mtip_pci_remove(struct pci_dev *pdev) mtip_block_remove(dd); if (dd->isr_workq) { - flush_workqueue(dd->isr_workq); destroy_workqueue(dd->isr_workq); drop_cpu(dd->work[0].cpu_binding); drop_cpu(dd->work[1].cpu_binding); diff --git a/drivers/block/n64cart.c b/drivers/block/n64cart.c index b168ca25b6c9..78282f01f581 100644 --- a/drivers/block/n64cart.c +++ b/drivers/block/n64cart.c @@ -115,6 +115,7 @@ static const struct block_device_operations n64cart_fops = { static int __init n64cart_probe(struct platform_device *pdev) { struct gendisk *disk; + int err = -ENOMEM; if (!start || !size) { pr_err("start or size not specified\n"); @@ -132,7 +133,7 @@ static int __init n64cart_probe(struct platform_device *pdev) disk = blk_alloc_disk(NUMA_NO_NODE); if (!disk) - return -ENOMEM; + goto out; disk->first_minor = 0; disk->flags = GENHD_FL_NO_PART_SCAN; @@ -147,11 +148,18 @@ static int __init n64cart_probe(struct platform_device *pdev) blk_queue_physical_block_size(disk->queue, 4096); blk_queue_logical_block_size(disk->queue, 4096); - add_disk(disk); + err = add_disk(disk); + if (err) + goto out_cleanup_disk; pr_info("n64cart: %u kb disk\n", size / 1024); return 0; + +out_cleanup_disk: + blk_cleanup_disk(disk); +out: + return err; } static struct platform_driver n64cart_driver = { diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c index 504c20a2f33e..b47b2a87ae8f 100644 --- a/drivers/block/nbd.c +++ b/drivers/block/nbd.c @@ -122,15 +122,21 @@ struct nbd_device { struct work_struct remove_work; struct list_head list; - struct task_struct *task_recv; struct task_struct *task_setup; unsigned long flags; + pid_t pid; /* pid of nbd-client, if attached */ char *backend; }; #define NBD_CMD_REQUEUED 1 +/* + * This flag will be set if nbd_queue_rq() succeed, and will be checked and + * cleared in completion. Both setting and clearing of the flag are protected + * by cmd->lock. + */ +#define NBD_CMD_INFLIGHT 2 struct nbd_cmd { struct nbd_device *nbd; @@ -217,7 +223,7 @@ static ssize_t pid_show(struct device *dev, struct gendisk *disk = dev_to_disk(dev); struct nbd_device *nbd = (struct nbd_device *)disk->private_data; - return sprintf(buf, "%d\n", task_pid_nr(nbd->task_recv)); + return sprintf(buf, "%d\n", nbd->pid); } static const struct device_attribute pid_attr = { @@ -322,7 +328,7 @@ static int nbd_set_size(struct nbd_device *nbd, loff_t bytesize, nbd->config->bytesize = bytesize; nbd->config->blksize_bits = __ffs(blksize); - if (!nbd->task_recv) + if (!nbd->pid) return 0; if (nbd->config->flags & NBD_FLAG_SEND_TRIM) { @@ -398,6 +404,11 @@ static enum blk_eh_timer_return nbd_xmit_timeout(struct request *req, if (!mutex_trylock(&cmd->lock)) return BLK_EH_RESET_TIMER; + if (!__test_and_clear_bit(NBD_CMD_INFLIGHT, &cmd->flags)) { + mutex_unlock(&cmd->lock); + return BLK_EH_DONE; + } + if (!refcount_inc_not_zero(&nbd->config_refs)) { cmd->status = BLK_STS_TIMEOUT; mutex_unlock(&cmd->lock); @@ -477,7 +488,8 @@ done: } /* - * Send or receive packet. + * Send or receive packet. Return a positive value on success and + * negtive value on failue, and never return 0. */ static int sock_xmit(struct nbd_device *nbd, int index, int send, struct iov_iter *iter, int msg_flags, int *sent) @@ -603,7 +615,7 @@ static int nbd_send_cmd(struct nbd_device *nbd, struct nbd_cmd *cmd, int index) result = sock_xmit(nbd, index, 1, &from, (type == NBD_CMD_WRITE) ? MSG_MORE : 0, &sent); trace_nbd_header_sent(req, handle); - if (result <= 0) { + if (result < 0) { if (was_interrupted(result)) { /* If we havne't sent anything we can just return BUSY, * however if we have sent something we need to make @@ -647,7 +659,7 @@ send_pages: skip = 0; } result = sock_xmit(nbd, index, 1, &from, flags, &sent); - if (result <= 0) { + if (result < 0) { if (was_interrupted(result)) { /* We've already sent the header, we * have no choice but to set pending and @@ -681,38 +693,45 @@ out: return 0; } -/* NULL returned = something went wrong, inform userspace */ -static struct nbd_cmd *nbd_read_stat(struct nbd_device *nbd, int index) +static int nbd_read_reply(struct nbd_device *nbd, int index, + struct nbd_reply *reply) +{ + struct kvec iov = {.iov_base = reply, .iov_len = sizeof(*reply)}; + struct iov_iter to; + int result; + + reply->magic = 0; + iov_iter_kvec(&to, READ, &iov, 1, sizeof(*reply)); + result = sock_xmit(nbd, index, 0, &to, MSG_WAITALL, NULL); + if (result < 0) { + if (!nbd_disconnected(nbd->config)) + dev_err(disk_to_dev(nbd->disk), + "Receive control failed (result %d)\n", result); + return result; + } + + if (ntohl(reply->magic) != NBD_REPLY_MAGIC) { + dev_err(disk_to_dev(nbd->disk), "Wrong magic (0x%lx)\n", + (unsigned long)ntohl(reply->magic)); + return -EPROTO; + } + + return 0; +} + +/* NULL returned = something went wrong, inform userspace */ +static struct nbd_cmd *nbd_handle_reply(struct nbd_device *nbd, int index, + struct nbd_reply *reply) { - struct nbd_config *config = nbd->config; int result; - struct nbd_reply reply; struct nbd_cmd *cmd; struct request *req = NULL; u64 handle; u16 hwq; u32 tag; - struct kvec iov = {.iov_base = &reply, .iov_len = sizeof(reply)}; - struct iov_iter to; int ret = 0; - reply.magic = 0; - iov_iter_kvec(&to, READ, &iov, 1, sizeof(reply)); - result = sock_xmit(nbd, index, 0, &to, MSG_WAITALL, NULL); - if (result <= 0) { - if (!nbd_disconnected(config)) - dev_err(disk_to_dev(nbd->disk), - "Receive control failed (result %d)\n", result); - return ERR_PTR(result); - } - - if (ntohl(reply.magic) != NBD_REPLY_MAGIC) { - dev_err(disk_to_dev(nbd->disk), "Wrong magic (0x%lx)\n", - (unsigned long)ntohl(reply.magic)); - return ERR_PTR(-EPROTO); - } - - memcpy(&handle, reply.handle, sizeof(handle)); + memcpy(&handle, reply->handle, sizeof(handle)); tag = nbd_handle_to_tag(handle); hwq = blk_mq_unique_tag_to_hwq(tag); if (hwq < nbd->tag_set.nr_hw_queues) @@ -727,6 +746,16 @@ static struct nbd_cmd *nbd_read_stat(struct nbd_device *nbd, int index) cmd = blk_mq_rq_to_pdu(req); mutex_lock(&cmd->lock); + if (!__test_and_clear_bit(NBD_CMD_INFLIGHT, &cmd->flags)) { + dev_err(disk_to_dev(nbd->disk), "Suspicious reply %d (status %u flags %lu)", + tag, cmd->status, cmd->flags); + ret = -ENOENT; + goto out; + } + if (cmd->index != index) { + dev_err(disk_to_dev(nbd->disk), "Unexpected reply %d from different sock %d (expected %d)", + tag, index, cmd->index); + } if (cmd->cmd_cookie != nbd_handle_to_cookie(handle)) { dev_err(disk_to_dev(nbd->disk), "Double reply on req %p, cmd_cookie %u, handle cookie %u\n", req, cmd->cmd_cookie, nbd_handle_to_cookie(handle)); @@ -745,9 +774,9 @@ static struct nbd_cmd *nbd_read_stat(struct nbd_device *nbd, int index) ret = -ENOENT; goto out; } - if (ntohl(reply.error)) { + if (ntohl(reply->error)) { dev_err(disk_to_dev(nbd->disk), "Other side returned error (%d)\n", - ntohl(reply.error)); + ntohl(reply->error)); cmd->status = BLK_STS_IOERR; goto out; } @@ -756,11 +785,12 @@ static struct nbd_cmd *nbd_read_stat(struct nbd_device *nbd, int index) if (rq_data_dir(req) != WRITE) { struct req_iterator iter; struct bio_vec bvec; + struct iov_iter to; rq_for_each_segment(bvec, req, iter) { iov_iter_bvec(&to, READ, &bvec, 1, bvec.bv_len); result = sock_xmit(nbd, index, 0, &to, MSG_WAITALL, NULL); - if (result <= 0) { + if (result < 0) { dev_err(disk_to_dev(nbd->disk), "Receive data failed (result %d)\n", result); /* @@ -769,7 +799,7 @@ static struct nbd_cmd *nbd_read_stat(struct nbd_device *nbd, int index) * and let the timeout stuff handle resubmitting * this request onto another connection. */ - if (nbd_disconnected(config)) { + if (nbd_disconnected(nbd->config)) { cmd->status = BLK_STS_IOERR; goto out; } @@ -793,24 +823,46 @@ static void recv_work(struct work_struct *work) work); struct nbd_device *nbd = args->nbd; struct nbd_config *config = nbd->config; + struct request_queue *q = nbd->disk->queue; + struct nbd_sock *nsock; struct nbd_cmd *cmd; struct request *rq; while (1) { - cmd = nbd_read_stat(nbd, args->index); - if (IS_ERR(cmd)) { - struct nbd_sock *nsock = config->socks[args->index]; + struct nbd_reply reply; - mutex_lock(&nsock->tx_lock); - nbd_mark_nsock_dead(nbd, nsock, 1); - mutex_unlock(&nsock->tx_lock); + if (nbd_read_reply(nbd, args->index, &reply)) + break; + + /* + * Grab .q_usage_counter so request pool won't go away, then no + * request use-after-free is possible during nbd_handle_reply(). + * If queue is frozen, there won't be any inflight requests, we + * needn't to handle the incoming garbage message. + */ + if (!percpu_ref_tryget(&q->q_usage_counter)) { + dev_err(disk_to_dev(nbd->disk), "%s: no io inflight\n", + __func__); + break; + } + + cmd = nbd_handle_reply(nbd, args->index, &reply); + if (IS_ERR(cmd)) { + percpu_ref_put(&q->q_usage_counter); break; } rq = blk_mq_rq_from_pdu(cmd); if (likely(!blk_should_fake_timeout(rq->q))) blk_mq_complete_request(rq); + percpu_ref_put(&q->q_usage_counter); } + + nsock = config->socks[args->index]; + mutex_lock(&nsock->tx_lock); + nbd_mark_nsock_dead(nbd, nsock, 1); + mutex_unlock(&nsock->tx_lock); + nbd_config_put(nbd); atomic_dec(&config->recv_threads); wake_up(&config->recv_wq); @@ -826,6 +878,10 @@ static bool nbd_clear_req(struct request *req, void *data, bool reserved) return true; mutex_lock(&cmd->lock); + if (!__test_and_clear_bit(NBD_CMD_INFLIGHT, &cmd->flags)) { + mutex_unlock(&cmd->lock); + return true; + } cmd->status = BLK_STS_IOERR; mutex_unlock(&cmd->lock); @@ -907,7 +963,6 @@ static int nbd_handle_cmd(struct nbd_cmd *cmd, int index) if (!refcount_inc_not_zero(&nbd->config_refs)) { dev_err_ratelimited(disk_to_dev(nbd->disk), "Socks array is empty\n"); - blk_mq_start_request(req); return -EINVAL; } config = nbd->config; @@ -916,7 +971,6 @@ static int nbd_handle_cmd(struct nbd_cmd *cmd, int index) dev_err_ratelimited(disk_to_dev(nbd->disk), "Attempted send on invalid socket\n"); nbd_config_put(nbd); - blk_mq_start_request(req); return -EINVAL; } cmd->status = BLK_STS_OK; @@ -940,7 +994,6 @@ again: */ sock_shutdown(nbd); nbd_config_put(nbd); - blk_mq_start_request(req); return -EIO; } goto again; @@ -962,7 +1015,13 @@ again: * returns EAGAIN can be retried on a different socket. */ ret = nbd_send_cmd(nbd, cmd, index); - if (ret == -EAGAIN) { + /* + * Access to this flag is protected by cmd->lock, thus it's safe to set + * the flag after nbd_send_cmd() succeed to send request to server. + */ + if (!ret) + __set_bit(NBD_CMD_INFLIGHT, &cmd->flags); + else if (ret == -EAGAIN) { dev_err_ratelimited(disk_to_dev(nbd->disk), "Request send failed, requeueing\n"); nbd_mark_nsock_dead(nbd, nsock, 1); @@ -1199,7 +1258,7 @@ static void send_disconnects(struct nbd_device *nbd) iov_iter_kvec(&from, WRITE, &iov, 1, sizeof(request)); mutex_lock(&nsock->tx_lock); ret = sock_xmit(nbd, i, 1, &from, 0, NULL); - if (ret <= 0) + if (ret < 0) dev_err(disk_to_dev(nbd->disk), "Send disconnect failed %d\n", ret); mutex_unlock(&nsock->tx_lock); @@ -1236,7 +1295,7 @@ static void nbd_config_put(struct nbd_device *nbd) if (test_and_clear_bit(NBD_RT_HAS_PID_FILE, &config->runtime_flags)) device_remove_file(disk_to_dev(nbd->disk), &pid_attr); - nbd->task_recv = NULL; + nbd->pid = 0; if (test_and_clear_bit(NBD_RT_HAS_BACKEND_FILE, &config->runtime_flags)) { device_remove_file(disk_to_dev(nbd->disk), &backend_attr); @@ -1277,7 +1336,7 @@ static int nbd_start_device(struct nbd_device *nbd) int num_connections = config->num_connections; int error = 0, i; - if (nbd->task_recv) + if (nbd->pid) return -EBUSY; if (!config->socks) return -EINVAL; @@ -1296,7 +1355,7 @@ static int nbd_start_device(struct nbd_device *nbd) } blk_mq_update_nr_hw_queues(&nbd->tag_set, config->num_connections); - nbd->task_recv = current; + nbd->pid = task_pid_nr(current); nbd_parse_flags(nbd); @@ -1552,8 +1611,8 @@ static int nbd_dbg_tasks_show(struct seq_file *s, void *unused) { struct nbd_device *nbd = s->private; - if (nbd->task_recv) - seq_printf(s, "recv: %d\n", task_pid_nr(nbd->task_recv)); + if (nbd->pid) + seq_printf(s, "recv: %d\n", nbd->pid); return 0; } @@ -1757,7 +1816,9 @@ static struct nbd_device *nbd_dev_add(int index, unsigned int refs) disk->fops = &nbd_fops; disk->private_data = nbd; sprintf(disk->disk_name, "nbd%d", index); - add_disk(disk); + err = add_disk(disk); + if (err) + goto out_err_disk; /* * Now publish the device. @@ -1766,6 +1827,8 @@ static struct nbd_device *nbd_dev_add(int index, unsigned int refs) nbd_total_devices++; return nbd; +out_err_disk: + blk_cleanup_disk(disk); out_free_idr: mutex_lock(&nbd_index_mutex); idr_remove(&nbd_index_idr, index); @@ -2130,7 +2193,7 @@ static int nbd_genl_reconfigure(struct sk_buff *skb, struct genl_info *info) mutex_lock(&nbd->config_lock); config = nbd->config; if (!test_bit(NBD_RT_BOUND, &config->runtime_flags) || - !nbd->task_recv) { + !nbd->pid) { dev_err(nbd_to_dev(nbd), "not configured, cannot reconfigure\n"); ret = -EINVAL; diff --git a/drivers/block/null_blk/main.c b/drivers/block/null_blk/main.c index e5cbcf582233..323af5c9c802 100644 --- a/drivers/block/null_blk/main.c +++ b/drivers/block/null_blk/main.c @@ -92,6 +92,10 @@ static int g_submit_queues = 1; module_param_named(submit_queues, g_submit_queues, int, 0444); MODULE_PARM_DESC(submit_queues, "Number of submission queues"); +static int g_poll_queues = 1; +module_param_named(poll_queues, g_poll_queues, int, 0444); +MODULE_PARM_DESC(poll_queues, "Number of IOPOLL submission queues"); + static int g_home_node = NUMA_NO_NODE; module_param_named(home_node, g_home_node, int, 0444); MODULE_PARM_DESC(home_node, "Home node for the device"); @@ -324,29 +328,69 @@ nullb_device_##NAME##_store(struct config_item *item, const char *page, \ } \ CONFIGFS_ATTR(nullb_device_, NAME); -static int nullb_apply_submit_queues(struct nullb_device *dev, - unsigned int submit_queues) -{ - struct nullb *nullb = dev->nullb; - struct blk_mq_tag_set *set; +static int nullb_update_nr_hw_queues(struct nullb_device *dev, + unsigned int submit_queues, + unsigned int poll_queues) - if (!nullb) +{ + struct blk_mq_tag_set *set; + int ret, nr_hw_queues; + + if (!dev->nullb) return 0; + /* + * Make sure at least one queue exists for each of submit and poll. + */ + if (!submit_queues || !poll_queues) + return -EINVAL; + /* * Make sure that null_init_hctx() does not access nullb->queues[] past * the end of that array. */ - if (submit_queues > nr_cpu_ids) + if (submit_queues > nr_cpu_ids || poll_queues > g_poll_queues) return -EINVAL; - set = nullb->tag_set; - blk_mq_update_nr_hw_queues(set, submit_queues); - return set->nr_hw_queues == submit_queues ? 0 : -ENOMEM; + + /* + * Keep previous and new queue numbers in nullb_device for reference in + * the call back function null_map_queues(). + */ + dev->prev_submit_queues = dev->submit_queues; + dev->prev_poll_queues = dev->poll_queues; + dev->submit_queues = submit_queues; + dev->poll_queues = poll_queues; + + set = dev->nullb->tag_set; + nr_hw_queues = submit_queues + poll_queues; + blk_mq_update_nr_hw_queues(set, nr_hw_queues); + ret = set->nr_hw_queues == nr_hw_queues ? 0 : -ENOMEM; + + if (ret) { + /* on error, revert the queue numbers */ + dev->submit_queues = dev->prev_submit_queues; + dev->poll_queues = dev->prev_poll_queues; + } + + return ret; +} + +static int nullb_apply_submit_queues(struct nullb_device *dev, + unsigned int submit_queues) +{ + return nullb_update_nr_hw_queues(dev, submit_queues, dev->poll_queues); +} + +static int nullb_apply_poll_queues(struct nullb_device *dev, + unsigned int poll_queues) +{ + return nullb_update_nr_hw_queues(dev, dev->submit_queues, poll_queues); } NULLB_DEVICE_ATTR(size, ulong, NULL); NULLB_DEVICE_ATTR(completion_nsec, ulong, NULL); NULLB_DEVICE_ATTR(submit_queues, uint, nullb_apply_submit_queues); +NULLB_DEVICE_ATTR(poll_queues, uint, nullb_apply_poll_queues); NULLB_DEVICE_ATTR(home_node, uint, NULL); NULLB_DEVICE_ATTR(queue_mode, uint, NULL); NULLB_DEVICE_ATTR(blocksize, uint, NULL); @@ -466,6 +510,7 @@ static struct configfs_attribute *nullb_device_attrs[] = { &nullb_device_attr_size, &nullb_device_attr_completion_nsec, &nullb_device_attr_submit_queues, + &nullb_device_attr_poll_queues, &nullb_device_attr_home_node, &nullb_device_attr_queue_mode, &nullb_device_attr_blocksize, @@ -593,6 +638,9 @@ static struct nullb_device *null_alloc_dev(void) dev->size = g_gb * 1024; dev->completion_nsec = g_completion_nsec; dev->submit_queues = g_submit_queues; + dev->prev_submit_queues = g_submit_queues; + dev->poll_queues = g_poll_queues; + dev->prev_poll_queues = g_poll_queues; dev->home_node = g_home_node; dev->queue_mode = g_queue_mode; dev->blocksize = g_bs; @@ -1454,12 +1502,100 @@ static bool should_requeue_request(struct request *rq) return false; } +static int null_map_queues(struct blk_mq_tag_set *set) +{ + struct nullb *nullb = set->driver_data; + int i, qoff; + unsigned int submit_queues = g_submit_queues; + unsigned int poll_queues = g_poll_queues; + + if (nullb) { + struct nullb_device *dev = nullb->dev; + + /* + * Refer nr_hw_queues of the tag set to check if the expected + * number of hardware queues are prepared. If block layer failed + * to prepare them, use previous numbers of submit queues and + * poll queues to map queues. + */ + if (set->nr_hw_queues == + dev->submit_queues + dev->poll_queues) { + submit_queues = dev->submit_queues; + poll_queues = dev->poll_queues; + } else if (set->nr_hw_queues == + dev->prev_submit_queues + dev->prev_poll_queues) { + submit_queues = dev->prev_submit_queues; + poll_queues = dev->prev_poll_queues; + } else { + pr_warn("tag set has unexpected nr_hw_queues: %d\n", + set->nr_hw_queues); + return -EINVAL; + } + } + + for (i = 0, qoff = 0; i < set->nr_maps; i++) { + struct blk_mq_queue_map *map = &set->map[i]; + + switch (i) { + case HCTX_TYPE_DEFAULT: + map->nr_queues = submit_queues; + break; + case HCTX_TYPE_READ: + map->nr_queues = 0; + continue; + case HCTX_TYPE_POLL: + map->nr_queues = poll_queues; + break; + } + map->queue_offset = qoff; + qoff += map->nr_queues; + blk_mq_map_queues(map); + } + + return 0; +} + +static int null_poll(struct blk_mq_hw_ctx *hctx, struct io_comp_batch *iob) +{ + struct nullb_queue *nq = hctx->driver_data; + LIST_HEAD(list); + int nr = 0; + + spin_lock(&nq->poll_lock); + list_splice_init(&nq->poll_list, &list); + spin_unlock(&nq->poll_lock); + + while (!list_empty(&list)) { + struct nullb_cmd *cmd; + struct request *req; + + req = list_first_entry(&list, struct request, queuelist); + list_del_init(&req->queuelist); + cmd = blk_mq_rq_to_pdu(req); + cmd->error = null_process_cmd(cmd, req_op(req), blk_rq_pos(req), + blk_rq_sectors(req)); + end_cmd(cmd); + nr++; + } + + return nr; +} + static enum blk_eh_timer_return null_timeout_rq(struct request *rq, bool res) { + struct blk_mq_hw_ctx *hctx = rq->mq_hctx; struct nullb_cmd *cmd = blk_mq_rq_to_pdu(rq); pr_info("rq %p timed out\n", rq); + if (hctx->type == HCTX_TYPE_POLL) { + struct nullb_queue *nq = hctx->driver_data; + + spin_lock(&nq->poll_lock); + list_del_init(&rq->queuelist); + spin_unlock(&nq->poll_lock); + } + /* * If the device is marked as blocking (i.e. memory backed or zoned * device), the submission path may be blocked waiting for resources @@ -1480,10 +1616,11 @@ static blk_status_t null_queue_rq(struct blk_mq_hw_ctx *hctx, struct nullb_queue *nq = hctx->driver_data; sector_t nr_sectors = blk_rq_sectors(bd->rq); sector_t sector = blk_rq_pos(bd->rq); + const bool is_poll = hctx->type == HCTX_TYPE_POLL; might_sleep_if(hctx->flags & BLK_MQ_F_BLOCKING); - if (nq->dev->irqmode == NULL_IRQ_TIMER) { + if (!is_poll && nq->dev->irqmode == NULL_IRQ_TIMER) { hrtimer_init(&cmd->timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); cmd->timer.function = null_cmd_timer_expired; } @@ -1507,6 +1644,13 @@ static blk_status_t null_queue_rq(struct blk_mq_hw_ctx *hctx, return BLK_STS_OK; } } + + if (is_poll) { + spin_lock(&nq->poll_lock); + list_add_tail(&bd->rq->queuelist, &nq->poll_list); + spin_unlock(&nq->poll_lock); + return BLK_STS_OK; + } if (cmd->fake_timeout) return BLK_STS_OK; @@ -1542,6 +1686,8 @@ static void null_init_queue(struct nullb *nullb, struct nullb_queue *nq) init_waitqueue_head(&nq->wait); nq->queue_depth = nullb->queue_depth; nq->dev = nullb->dev; + INIT_LIST_HEAD(&nq->poll_list); + spin_lock_init(&nq->poll_lock); } static int null_init_hctx(struct blk_mq_hw_ctx *hctx, void *driver_data, @@ -1567,6 +1713,8 @@ static const struct blk_mq_ops null_mq_ops = { .queue_rq = null_queue_rq, .complete = null_complete_rq, .timeout = null_timeout_rq, + .poll = null_poll, + .map_queues = null_map_queues, .init_hctx = null_init_hctx, .exit_hctx = null_exit_hctx, }; @@ -1663,13 +1811,17 @@ static int setup_commands(struct nullb_queue *nq) static int setup_queues(struct nullb *nullb) { - nullb->queues = kcalloc(nr_cpu_ids, sizeof(struct nullb_queue), + int nqueues = nr_cpu_ids; + + if (g_poll_queues) + nqueues += g_poll_queues; + + nullb->queues = kcalloc(nqueues, sizeof(struct nullb_queue), GFP_KERNEL); if (!nullb->queues) return -ENOMEM; nullb->queue_depth = nullb->dev->hw_queue_depth; - return 0; } @@ -1721,9 +1873,14 @@ static int null_gendisk_register(struct nullb *nullb) static int null_init_tag_set(struct nullb *nullb, struct blk_mq_tag_set *set) { + int poll_queues; + set->ops = &null_mq_ops; set->nr_hw_queues = nullb ? nullb->dev->submit_queues : g_submit_queues; + poll_queues = nullb ? nullb->dev->poll_queues : g_poll_queues; + if (poll_queues) + set->nr_hw_queues += poll_queues; set->queue_depth = nullb ? nullb->dev->hw_queue_depth : g_hw_queue_depth; set->numa_node = nullb ? nullb->dev->home_node : g_home_node; @@ -1733,7 +1890,11 @@ static int null_init_tag_set(struct nullb *nullb, struct blk_mq_tag_set *set) set->flags |= BLK_MQ_F_NO_SCHED; if (g_shared_tag_bitmap) set->flags |= BLK_MQ_F_TAG_HCTX_SHARED; - set->driver_data = NULL; + set->driver_data = nullb; + if (g_poll_queues) + set->nr_maps = 3; + else + set->nr_maps = 1; if ((nullb && nullb->dev->blocking) || g_blocking) set->flags |= BLK_MQ_F_BLOCKING; @@ -1753,6 +1914,13 @@ static int null_validate_conf(struct nullb_device *dev) dev->submit_queues = nr_cpu_ids; else if (dev->submit_queues == 0) dev->submit_queues = 1; + dev->prev_submit_queues = dev->submit_queues; + + if (dev->poll_queues > g_poll_queues) + dev->poll_queues = g_poll_queues; + else if (dev->poll_queues == 0) + dev->poll_queues = 1; + dev->prev_poll_queues = dev->poll_queues; dev->queue_mode = min_t(unsigned int, dev->queue_mode, NULL_Q_MQ); dev->irqmode = min_t(unsigned int, dev->irqmode, NULL_IRQ_TIMER); diff --git a/drivers/block/null_blk/null_blk.h b/drivers/block/null_blk/null_blk.h index 64bef125d1df..78eb56b0ca55 100644 --- a/drivers/block/null_blk/null_blk.h +++ b/drivers/block/null_blk/null_blk.h @@ -32,6 +32,9 @@ struct nullb_queue { struct nullb_device *dev; unsigned int requeue_selection; + struct list_head poll_list; + spinlock_t poll_lock; + struct nullb_cmd *cmds; }; @@ -83,6 +86,9 @@ struct nullb_device { unsigned int zone_max_open; /* max number of open zones */ unsigned int zone_max_active; /* max number of active zones */ unsigned int submit_queues; /* number of submission queues */ + unsigned int prev_submit_queues; /* number of submission queues before change */ + unsigned int poll_queues; /* number of IOPOLL submission queues */ + unsigned int prev_poll_queues; /* number of IOPOLL submission queues before change */ unsigned int home_node; /* home node for the device */ unsigned int queue_mode; /* block interface */ unsigned int blocksize; /* block size */ diff --git a/drivers/block/paride/pcd.c b/drivers/block/paride/pcd.c index f9cdd11f02f5..f6b1d63e96e1 100644 --- a/drivers/block/paride/pcd.c +++ b/drivers/block/paride/pcd.c @@ -183,8 +183,6 @@ static int pcd_audio_ioctl(struct cdrom_device_info *cdi, static int pcd_packet(struct cdrom_device_info *cdi, struct packet_command *cgc); -static int pcd_detect(void); -static void pcd_probe_capabilities(void); static void do_pcd_read_drq(void); static blk_status_t pcd_queue_rq(struct blk_mq_hw_ctx *hctx, const struct blk_mq_queue_data *bd); @@ -302,53 +300,6 @@ static const struct blk_mq_ops pcd_mq_ops = { .queue_rq = pcd_queue_rq, }; -static void pcd_init_units(void) -{ - struct pcd_unit *cd; - int unit; - - pcd_drive_count = 0; - for (unit = 0, cd = pcd; unit < PCD_UNITS; unit++, cd++) { - struct gendisk *disk; - - if (blk_mq_alloc_sq_tag_set(&cd->tag_set, &pcd_mq_ops, 1, - BLK_MQ_F_SHOULD_MERGE)) - continue; - - disk = blk_mq_alloc_disk(&cd->tag_set, cd); - if (IS_ERR(disk)) { - blk_mq_free_tag_set(&cd->tag_set); - continue; - } - - INIT_LIST_HEAD(&cd->rq_list); - blk_queue_bounce_limit(disk->queue, BLK_BOUNCE_HIGH); - cd->disk = disk; - cd->pi = &cd->pia; - cd->present = 0; - cd->last_sense = 0; - cd->changed = 1; - cd->drive = (*drives[unit])[D_SLV]; - if ((*drives[unit])[D_PRT]) - pcd_drive_count++; - - cd->name = &cd->info.name[0]; - snprintf(cd->name, sizeof(cd->info.name), "%s%d", name, unit); - cd->info.ops = &pcd_dops; - cd->info.handle = cd; - cd->info.speed = 0; - cd->info.capacity = 1; - cd->info.mask = 0; - disk->major = major; - disk->first_minor = unit; - disk->minors = 1; - strcpy(disk->disk_name, cd->name); /* umm... */ - disk->fops = &pcd_bdops; - disk->flags = GENHD_FL_BLOCK_EVENTS_ON_EXCL_WRITE; - disk->events = DISK_EVENT_MEDIA_CHANGE; - } -} - static int pcd_open(struct cdrom_device_info *cdi, int purpose) { struct pcd_unit *cd = cdi->handle; @@ -630,10 +581,11 @@ static int pcd_drive_status(struct cdrom_device_info *cdi, int slot_nr) return CDS_DISC_OK; } -static int pcd_identify(struct pcd_unit *cd, char *id) +static int pcd_identify(struct pcd_unit *cd) { - int k, s; char id_cmd[12] = { 0x12, 0, 0, 0, 36, 0, 0, 0, 0, 0, 0, 0 }; + char id[18]; + int k, s; pcd_bufblk = -1; @@ -661,108 +613,47 @@ static int pcd_identify(struct pcd_unit *cd, char *id) } /* - * returns 0, with id set if drive is detected - * -1, if drive detection failed + * returns 0, with id set if drive is detected, otherwise an error code. */ -static int pcd_probe(struct pcd_unit *cd, int ms, char *id) +static int pcd_probe(struct pcd_unit *cd, int ms) { if (ms == -1) { for (cd->drive = 0; cd->drive <= 1; cd->drive++) - if (!pcd_reset(cd) && !pcd_identify(cd, id)) + if (!pcd_reset(cd) && !pcd_identify(cd)) return 0; } else { cd->drive = ms; - if (!pcd_reset(cd) && !pcd_identify(cd, id)) + if (!pcd_reset(cd) && !pcd_identify(cd)) return 0; } - return -1; + return -ENODEV; } -static void pcd_probe_capabilities(void) +static int pcd_probe_capabilities(struct pcd_unit *cd) { - int unit, r; - char buffer[32]; char cmd[12] = { 0x5a, 1 << 3, 0x2a, 0, 0, 0, 0, 18, 0, 0, 0, 0 }; - struct pcd_unit *cd; + char buffer[32]; + int ret; - for (unit = 0, cd = pcd; unit < PCD_UNITS; unit++, cd++) { - if (!cd->present) - continue; - r = pcd_atapi(cd, cmd, 18, buffer, "mode sense capabilities"); - if (r) - continue; - /* we should now have the cap page */ - if ((buffer[11] & 1) == 0) - cd->info.mask |= CDC_CD_R; - if ((buffer[11] & 2) == 0) - cd->info.mask |= CDC_CD_RW; - if ((buffer[12] & 1) == 0) - cd->info.mask |= CDC_PLAY_AUDIO; - if ((buffer[14] & 1) == 0) - cd->info.mask |= CDC_LOCK; - if ((buffer[14] & 8) == 0) - cd->info.mask |= CDC_OPEN_TRAY; - if ((buffer[14] >> 6) == 0) - cd->info.mask |= CDC_CLOSE_TRAY; - } -} + ret = pcd_atapi(cd, cmd, 18, buffer, "mode sense capabilities"); + if (ret) + return ret; -static int pcd_detect(void) -{ - char id[18]; - int k, unit; - struct pcd_unit *cd; + /* we should now have the cap page */ + if ((buffer[11] & 1) == 0) + cd->info.mask |= CDC_CD_R; + if ((buffer[11] & 2) == 0) + cd->info.mask |= CDC_CD_RW; + if ((buffer[12] & 1) == 0) + cd->info.mask |= CDC_PLAY_AUDIO; + if ((buffer[14] & 1) == 0) + cd->info.mask |= CDC_LOCK; + if ((buffer[14] & 8) == 0) + cd->info.mask |= CDC_OPEN_TRAY; + if ((buffer[14] >> 6) == 0) + cd->info.mask |= CDC_CLOSE_TRAY; - printk("%s: %s version %s, major %d, nice %d\n", - name, name, PCD_VERSION, major, nice); - - par_drv = pi_register_driver(name); - if (!par_drv) { - pr_err("failed to register %s driver\n", name); - return -1; - } - - k = 0; - if (pcd_drive_count == 0) { /* nothing spec'd - so autoprobe for 1 */ - cd = pcd; - if (cd->disk && pi_init(cd->pi, 1, -1, -1, -1, -1, -1, - pcd_buffer, PI_PCD, verbose, cd->name)) { - if (!pcd_probe(cd, -1, id)) { - cd->present = 1; - k++; - } else - pi_release(cd->pi); - } - } else { - for (unit = 0, cd = pcd; unit < PCD_UNITS; unit++, cd++) { - int *conf = *drives[unit]; - if (!conf[D_PRT]) - continue; - if (!cd->disk) - continue; - if (!pi_init(cd->pi, 0, conf[D_PRT], conf[D_MOD], - conf[D_UNI], conf[D_PRO], conf[D_DLY], - pcd_buffer, PI_PCD, verbose, cd->name)) - continue; - if (!pcd_probe(cd, conf[D_SLV], id)) { - cd->present = 1; - k++; - } else - pi_release(cd->pi); - } - } - if (k) - return 0; - - printk("%s: No CD-ROM drive found\n", name); - for (unit = 0, cd = pcd; unit < PCD_UNITS; unit++, cd++) { - if (!cd->disk) - continue; - blk_cleanup_disk(cd->disk); - blk_mq_free_tag_set(&cd->tag_set); - } - pi_unregister_driver(par_drv); - return -1; + return 0; } /* I/O request processing */ @@ -999,43 +890,130 @@ static int pcd_get_mcn(struct cdrom_device_info *cdi, struct cdrom_mcn *mcn) return 0; } +static int pcd_init_unit(struct pcd_unit *cd, bool autoprobe, int port, + int mode, int unit, int protocol, int delay, int ms) +{ + struct gendisk *disk; + int ret; + + ret = blk_mq_alloc_sq_tag_set(&cd->tag_set, &pcd_mq_ops, 1, + BLK_MQ_F_SHOULD_MERGE); + if (ret) + return ret; + + disk = blk_mq_alloc_disk(&cd->tag_set, cd); + if (IS_ERR(disk)) { + ret = PTR_ERR(disk); + goto out_free_tag_set; + } + + INIT_LIST_HEAD(&cd->rq_list); + blk_queue_bounce_limit(disk->queue, BLK_BOUNCE_HIGH); + cd->disk = disk; + cd->pi = &cd->pia; + cd->present = 0; + cd->last_sense = 0; + cd->changed = 1; + cd->drive = (*drives[cd - pcd])[D_SLV]; + + cd->name = &cd->info.name[0]; + snprintf(cd->name, sizeof(cd->info.name), "%s%d", name, unit); + cd->info.ops = &pcd_dops; + cd->info.handle = cd; + cd->info.speed = 0; + cd->info.capacity = 1; + cd->info.mask = 0; + disk->major = major; + disk->first_minor = unit; + disk->minors = 1; + strcpy(disk->disk_name, cd->name); /* umm... */ + disk->fops = &pcd_bdops; + disk->flags = GENHD_FL_BLOCK_EVENTS_ON_EXCL_WRITE; + disk->events = DISK_EVENT_MEDIA_CHANGE; + + if (!pi_init(cd->pi, autoprobe, port, mode, unit, protocol, delay, + pcd_buffer, PI_PCD, verbose, cd->name)) { + ret = -ENODEV; + goto out_free_disk; + } + ret = pcd_probe(cd, ms); + if (ret) + goto out_pi_release; + + cd->present = 1; + pcd_probe_capabilities(cd); + ret = register_cdrom(cd->disk, &cd->info); + if (ret) + goto out_pi_release; + ret = add_disk(cd->disk); + if (ret) + goto out_unreg_cdrom; + return 0; + +out_unreg_cdrom: + unregister_cdrom(&cd->info); +out_pi_release: + pi_release(cd->pi); +out_free_disk: + blk_cleanup_disk(cd->disk); +out_free_tag_set: + blk_mq_free_tag_set(&cd->tag_set); + return ret; +} + static int __init pcd_init(void) { - struct pcd_unit *cd; - int unit; + int found = 0, unit; if (disable) return -EINVAL; - pcd_init_units(); - - if (pcd_detect()) - return -ENODEV; - - /* get the atapi capabilities page */ - pcd_probe_capabilities(); - - if (register_blkdev(major, name)) { - for (unit = 0, cd = pcd; unit < PCD_UNITS; unit++, cd++) { - if (!cd->disk) - continue; - - blk_cleanup_queue(cd->disk->queue); - blk_mq_free_tag_set(&cd->tag_set); - put_disk(cd->disk); - } + if (register_blkdev(major, name)) return -EBUSY; + + pr_info("%s: %s version %s, major %d, nice %d\n", + name, name, PCD_VERSION, major, nice); + + par_drv = pi_register_driver(name); + if (!par_drv) { + pr_err("failed to register %s driver\n", name); + goto out_unregister_blkdev; } - for (unit = 0, cd = pcd; unit < PCD_UNITS; unit++, cd++) { - if (cd->present) { - register_cdrom(cd->disk, &cd->info); - cd->disk->private_data = cd; - add_disk(cd->disk); + for (unit = 0; unit < PCD_UNITS; unit++) { + if ((*drives[unit])[D_PRT]) + pcd_drive_count++; + } + + if (pcd_drive_count == 0) { /* nothing spec'd - so autoprobe for 1 */ + if (!pcd_init_unit(pcd, 1, -1, -1, -1, -1, -1, -1)) + found++; + } else { + for (unit = 0; unit < PCD_UNITS; unit++) { + struct pcd_unit *cd = &pcd[unit]; + int *conf = *drives[unit]; + + if (!conf[D_PRT]) + continue; + if (!pcd_init_unit(cd, 0, conf[D_PRT], conf[D_MOD], + conf[D_UNI], conf[D_PRO], conf[D_DLY], + conf[D_SLV])) + found++; } } + if (!found) { + pr_info("%s: No CD-ROM drive found\n", name); + goto out_unregister_pi_driver; + } + return 0; + +out_unregister_pi_driver: + pi_unregister_driver(par_drv); +out_unregister_blkdev: + unregister_blkdev(major, name); + return -ENODEV; } static void __exit pcd_exit(void) @@ -1044,20 +1022,18 @@ static void __exit pcd_exit(void) int unit; for (unit = 0, cd = pcd; unit < PCD_UNITS; unit++, cd++) { - if (!cd->disk) + if (!cd->present) continue; - if (cd->present) { - del_gendisk(cd->disk); - pi_release(cd->pi); - unregister_cdrom(&cd->info); - } - blk_cleanup_queue(cd->disk->queue); + unregister_cdrom(&cd->info); + del_gendisk(cd->disk); + pi_release(cd->pi); + blk_cleanup_disk(cd->disk); + blk_mq_free_tag_set(&cd->tag_set); - put_disk(cd->disk); } - unregister_blkdev(major, name); pi_unregister_driver(par_drv); + unregister_blkdev(major, name); } MODULE_LICENSE("GPL"); diff --git a/drivers/block/paride/pd.c b/drivers/block/paride/pd.c index 675327df6aff..e59759bcf416 100644 --- a/drivers/block/paride/pd.c +++ b/drivers/block/paride/pd.c @@ -875,9 +875,27 @@ static const struct blk_mq_ops pd_mq_ops = { .queue_rq = pd_queue_rq, }; -static void pd_probe_drive(struct pd_unit *disk) +static int pd_probe_drive(struct pd_unit *disk, int autoprobe, int port, + int mode, int unit, int protocol, int delay) { + int index = disk - pd; + int *parm = *drives[index]; struct gendisk *p; + int ret; + + disk->pi = &disk->pia; + disk->access = 0; + disk->changed = 1; + disk->capacity = 0; + disk->drive = parm[D_SLV]; + snprintf(disk->name, PD_NAMELEN, "%s%c", name, 'a' + index); + disk->alt_geom = parm[D_GEO]; + disk->standby = parm[D_SBY]; + INIT_LIST_HEAD(&disk->rq_list); + + if (!pi_init(disk->pi, autoprobe, port, mode, unit, protocol, delay, + pd_scratch, PI_PD, verbose, disk->name)) + return -ENXIO; memset(&disk->tag_set, 0, sizeof(disk->tag_set)); disk->tag_set.ops = &pd_mq_ops; @@ -887,14 +905,14 @@ static void pd_probe_drive(struct pd_unit *disk) disk->tag_set.queue_depth = 2; disk->tag_set.numa_node = NUMA_NO_NODE; disk->tag_set.flags = BLK_MQ_F_SHOULD_MERGE | BLK_MQ_F_BLOCKING; - - if (blk_mq_alloc_tag_set(&disk->tag_set)) - return; + ret = blk_mq_alloc_tag_set(&disk->tag_set); + if (ret) + goto pi_release; p = blk_mq_alloc_disk(&disk->tag_set, disk); if (IS_ERR(p)) { - blk_mq_free_tag_set(&disk->tag_set); - return; + ret = PTR_ERR(p); + goto free_tag_set; } disk->gd = p; @@ -905,102 +923,88 @@ static void pd_probe_drive(struct pd_unit *disk) p->minors = 1 << PD_BITS; p->events = DISK_EVENT_MEDIA_CHANGE; p->private_data = disk; - blk_queue_max_hw_sectors(p->queue, cluster); blk_queue_bounce_limit(p->queue, BLK_BOUNCE_HIGH); if (disk->drive == -1) { - for (disk->drive = 0; disk->drive <= 1; disk->drive++) - if (pd_special_command(disk, pd_identify) == 0) - return; - } else if (pd_special_command(disk, pd_identify) == 0) - return; - disk->gd = NULL; + for (disk->drive = 0; disk->drive <= 1; disk->drive++) { + ret = pd_special_command(disk, pd_identify); + if (ret == 0) + break; + } + } else { + ret = pd_special_command(disk, pd_identify); + } + if (ret) + goto put_disk; + set_capacity(disk->gd, disk->capacity); + ret = add_disk(disk->gd); + if (ret) + goto cleanup_disk; + return 0; +cleanup_disk: + blk_cleanup_disk(disk->gd); +put_disk: put_disk(p); + disk->gd = NULL; +free_tag_set: + blk_mq_free_tag_set(&disk->tag_set); +pi_release: + pi_release(disk->pi); + return ret; } -static int pd_detect(void) +static int __init pd_init(void) { int found = 0, unit, pd_drive_count = 0; struct pd_unit *disk; - for (unit = 0; unit < PD_UNITS; unit++) { - int *parm = *drives[unit]; - struct pd_unit *disk = pd + unit; - disk->pi = &disk->pia; - disk->access = 0; - disk->changed = 1; - disk->capacity = 0; - disk->drive = parm[D_SLV]; - snprintf(disk->name, PD_NAMELEN, "%s%c", name, 'a'+unit); - disk->alt_geom = parm[D_GEO]; - disk->standby = parm[D_SBY]; - if (parm[D_PRT]) - pd_drive_count++; - INIT_LIST_HEAD(&disk->rq_list); - } + if (disable) + return -ENODEV; + + if (register_blkdev(major, name)) + return -ENODEV; + + printk("%s: %s version %s, major %d, cluster %d, nice %d\n", + name, name, PD_VERSION, major, cluster, nice); par_drv = pi_register_driver(name); if (!par_drv) { pr_err("failed to register %s driver\n", name); - return -1; + goto out_unregister_blkdev; + } + + for (unit = 0; unit < PD_UNITS; unit++) { + int *parm = *drives[unit]; + + if (parm[D_PRT]) + pd_drive_count++; } if (pd_drive_count == 0) { /* nothing spec'd - so autoprobe for 1 */ - disk = pd; - if (pi_init(disk->pi, 1, -1, -1, -1, -1, -1, pd_scratch, - PI_PD, verbose, disk->name)) { - pd_probe_drive(disk); - if (!disk->gd) - pi_release(disk->pi); - } - + if (!pd_probe_drive(pd, 1, -1, -1, -1, -1, -1)) + found++; } else { for (unit = 0, disk = pd; unit < PD_UNITS; unit++, disk++) { int *parm = *drives[unit]; if (!parm[D_PRT]) continue; - if (pi_init(disk->pi, 0, parm[D_PRT], parm[D_MOD], - parm[D_UNI], parm[D_PRO], parm[D_DLY], - pd_scratch, PI_PD, verbose, disk->name)) { - pd_probe_drive(disk); - if (!disk->gd) - pi_release(disk->pi); - } - } - } - for (unit = 0, disk = pd; unit < PD_UNITS; unit++, disk++) { - if (disk->gd) { - set_capacity(disk->gd, disk->capacity); - add_disk(disk->gd); - found = 1; + if (!pd_probe_drive(disk, 0, parm[D_PRT], parm[D_MOD], + parm[D_UNI], parm[D_PRO], parm[D_DLY])) + found++; } } if (!found) { printk("%s: no valid drive found\n", name); - pi_unregister_driver(par_drv); + goto out_pi_unregister_driver; } - return found; -} - -static int __init pd_init(void) -{ - if (disable) - goto out1; - - if (register_blkdev(major, name)) - goto out1; - - printk("%s: %s version %s, major %d, cluster %d, nice %d\n", - name, name, PD_VERSION, major, cluster, nice); - if (!pd_detect()) - goto out2; return 0; -out2: +out_pi_unregister_driver: + pi_unregister_driver(par_drv); +out_unregister_blkdev: unregister_blkdev(major, name); -out1: return -ENODEV; } diff --git a/drivers/block/paride/pf.c b/drivers/block/paride/pf.c index d5b9c88ba76f..bf8d0ef41a0a 100644 --- a/drivers/block/paride/pf.c +++ b/drivers/block/paride/pf.c @@ -214,7 +214,6 @@ static int pf_getgeo(struct block_device *bdev, struct hd_geometry *geo); static void pf_release(struct gendisk *disk, fmode_t mode); -static int pf_detect(void); static void do_pf_read(void); static void do_pf_read_start(void); static void do_pf_write(void); @@ -285,45 +284,6 @@ static const struct blk_mq_ops pf_mq_ops = { .queue_rq = pf_queue_rq, }; -static void __init pf_init_units(void) -{ - struct pf_unit *pf; - int unit; - - pf_drive_count = 0; - for (unit = 0, pf = units; unit < PF_UNITS; unit++, pf++) { - struct gendisk *disk; - - if (blk_mq_alloc_sq_tag_set(&pf->tag_set, &pf_mq_ops, 1, - BLK_MQ_F_SHOULD_MERGE)) - continue; - - disk = blk_mq_alloc_disk(&pf->tag_set, pf); - if (IS_ERR(disk)) { - blk_mq_free_tag_set(&pf->tag_set); - continue; - } - - INIT_LIST_HEAD(&pf->rq_list); - blk_queue_max_segments(disk->queue, cluster); - blk_queue_bounce_limit(disk->queue, BLK_BOUNCE_HIGH); - pf->disk = disk; - pf->pi = &pf->pia; - pf->media_status = PF_NM; - pf->drive = (*drives[unit])[D_SLV]; - pf->lun = (*drives[unit])[D_LUN]; - snprintf(pf->name, PF_NAMELEN, "%s%d", name, unit); - disk->major = major; - disk->first_minor = unit; - disk->minors = 1; - strcpy(disk->disk_name, pf->name); - disk->fops = &pf_fops; - disk->events = DISK_EVENT_MEDIA_CHANGE; - if (!(*drives[unit])[D_PRT]) - pf_drive_count++; - } -} - static int pf_open(struct block_device *bdev, fmode_t mode) { struct pf_unit *pf = bdev->bd_disk->private_data; @@ -691,9 +651,9 @@ static int pf_identify(struct pf_unit *pf) return 0; } -/* returns 0, with id set if drive is detected - -1, if drive detection failed -*/ +/* + * returns 0, with id set if drive is detected, otherwise an error code. + */ static int pf_probe(struct pf_unit *pf) { if (pf->drive == -1) { @@ -715,60 +675,7 @@ static int pf_probe(struct pf_unit *pf) if (!pf_identify(pf)) return 0; } - return -1; -} - -static int pf_detect(void) -{ - struct pf_unit *pf = units; - int k, unit; - - printk("%s: %s version %s, major %d, cluster %d, nice %d\n", - name, name, PF_VERSION, major, cluster, nice); - - par_drv = pi_register_driver(name); - if (!par_drv) { - pr_err("failed to register %s driver\n", name); - return -1; - } - k = 0; - if (pf_drive_count == 0) { - if (pi_init(pf->pi, 1, -1, -1, -1, -1, -1, pf_scratch, PI_PF, - verbose, pf->name)) { - if (!pf_probe(pf) && pf->disk) { - pf->present = 1; - k++; - } else - pi_release(pf->pi); - } - - } else - for (unit = 0; unit < PF_UNITS; unit++, pf++) { - int *conf = *drives[unit]; - if (!conf[D_PRT]) - continue; - if (pi_init(pf->pi, 0, conf[D_PRT], conf[D_MOD], - conf[D_UNI], conf[D_PRO], conf[D_DLY], - pf_scratch, PI_PF, verbose, pf->name)) { - if (pf->disk && !pf_probe(pf)) { - pf->present = 1; - k++; - } else - pi_release(pf->pi); - } - } - if (k) - return 0; - - printk("%s: No ATAPI disk detected\n", name); - for (pf = units, unit = 0; unit < PF_UNITS; pf++, unit++) { - if (!pf->disk) - continue; - blk_cleanup_disk(pf->disk); - blk_mq_free_tag_set(&pf->tag_set); - } - pi_unregister_driver(par_drv); - return -1; + return -ENODEV; } /* The i/o request engine */ @@ -1014,61 +921,134 @@ static void do_pf_write_done(void) next_request(0); } +static int __init pf_init_unit(struct pf_unit *pf, bool autoprobe, int port, + int mode, int unit, int protocol, int delay, int ms) +{ + struct gendisk *disk; + int ret; + + ret = blk_mq_alloc_sq_tag_set(&pf->tag_set, &pf_mq_ops, 1, + BLK_MQ_F_SHOULD_MERGE); + if (ret) + return ret; + + disk = blk_mq_alloc_disk(&pf->tag_set, pf); + if (IS_ERR(disk)) { + ret = PTR_ERR(disk); + goto out_free_tag_set; + } + disk->major = major; + disk->first_minor = pf - units; + disk->minors = 1; + strcpy(disk->disk_name, pf->name); + disk->fops = &pf_fops; + disk->events = DISK_EVENT_MEDIA_CHANGE; + disk->private_data = pf; + + blk_queue_max_segments(disk->queue, cluster); + blk_queue_bounce_limit(disk->queue, BLK_BOUNCE_HIGH); + + INIT_LIST_HEAD(&pf->rq_list); + pf->disk = disk; + pf->pi = &pf->pia; + pf->media_status = PF_NM; + pf->drive = (*drives[disk->first_minor])[D_SLV]; + pf->lun = (*drives[disk->first_minor])[D_LUN]; + snprintf(pf->name, PF_NAMELEN, "%s%d", name, disk->first_minor); + + if (!pi_init(pf->pi, autoprobe, port, mode, unit, protocol, delay, + pf_scratch, PI_PF, verbose, pf->name)) { + ret = -ENODEV; + goto out_free_disk; + } + ret = pf_probe(pf); + if (ret) + goto out_pi_release; + + ret = add_disk(disk); + if (ret) + goto out_pi_release; + pf->present = 1; + return 0; + +out_pi_release: + pi_release(pf->pi); +out_free_disk: + blk_cleanup_disk(pf->disk); +out_free_tag_set: + blk_mq_free_tag_set(&pf->tag_set); + return ret; +} + static int __init pf_init(void) { /* preliminary initialisation */ struct pf_unit *pf; - int unit; + int found = 0, unit; if (disable) return -EINVAL; - pf_init_units(); - - if (pf_detect()) - return -ENODEV; - pf_busy = 0; - - if (register_blkdev(major, name)) { - for (pf = units, unit = 0; unit < PF_UNITS; pf++, unit++) { - if (!pf->disk) - continue; - blk_cleanup_queue(pf->disk->queue); - blk_mq_free_tag_set(&pf->tag_set); - put_disk(pf->disk); - } + if (register_blkdev(major, name)) return -EBUSY; + + printk("%s: %s version %s, major %d, cluster %d, nice %d\n", + name, name, PF_VERSION, major, cluster, nice); + + par_drv = pi_register_driver(name); + if (!par_drv) { + pr_err("failed to register %s driver\n", name); + goto out_unregister_blkdev; } - for (pf = units, unit = 0; unit < PF_UNITS; pf++, unit++) { - struct gendisk *disk = pf->disk; - - if (!pf->present) - continue; - disk->private_data = pf; - add_disk(disk); + for (unit = 0; unit < PF_UNITS; unit++) { + if (!(*drives[unit])[D_PRT]) + pf_drive_count++; } + + pf = units; + if (pf_drive_count == 0) { + if (pf_init_unit(pf, 1, -1, -1, -1, -1, -1, verbose)) + found++; + } else { + for (unit = 0; unit < PF_UNITS; unit++, pf++) { + int *conf = *drives[unit]; + if (!conf[D_PRT]) + continue; + if (pf_init_unit(pf, 0, conf[D_PRT], conf[D_MOD], + conf[D_UNI], conf[D_PRO], conf[D_DLY], + verbose)) + found++; + } + } + if (!found) { + printk("%s: No ATAPI disk detected\n", name); + goto out_unregister_pi_driver; + } + pf_busy = 0; return 0; + +out_unregister_pi_driver: + pi_unregister_driver(par_drv); +out_unregister_blkdev: + unregister_blkdev(major, name); + return -ENODEV; } static void __exit pf_exit(void) { struct pf_unit *pf; int unit; - unregister_blkdev(major, name); + for (pf = units, unit = 0; unit < PF_UNITS; pf++, unit++) { - if (!pf->disk) + if (!pf->present) continue; - - if (pf->present) - del_gendisk(pf->disk); - - blk_cleanup_queue(pf->disk->queue); + del_gendisk(pf->disk); + blk_cleanup_disk(pf->disk); blk_mq_free_tag_set(&pf->tag_set); - put_disk(pf->disk); - - if (pf->present) - pi_release(pf->pi); + pi_release(pf->pi); } + + unregister_blkdev(major, name); } MODULE_LICENSE("GPL"); diff --git a/drivers/block/pktcdvd.c b/drivers/block/pktcdvd.c index cb52cce6fb03..e48d4771d4c1 100644 --- a/drivers/block/pktcdvd.c +++ b/drivers/block/pktcdvd.c @@ -2728,7 +2728,9 @@ static int pkt_setup_dev(dev_t dev, dev_t* pkt_dev) /* inherit events of the host device */ disk->events = pd->bdev->bd_disk->events; - add_disk(disk); + ret = add_disk(disk); + if (ret) + goto out_mem2; pkt_sysfs_dev_new(pd); pkt_debugfs_dev_new(pd); diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c index bf60aebd0cfb..953fa134cd3d 100644 --- a/drivers/block/rbd.c +++ b/drivers/block/rbd.c @@ -7054,7 +7054,9 @@ static ssize_t do_rbd_add(struct bus_type *bus, if (rc) goto err_out_image_lock; - device_add_disk(&rbd_dev->dev, rbd_dev->disk, NULL); + rc = device_add_disk(&rbd_dev->dev, rbd_dev->disk, NULL); + if (rc) + goto err_out_cleanup_disk; spin_lock(&rbd_dev_list_lock); list_add_tail(&rbd_dev->node, &rbd_dev_list); @@ -7068,6 +7070,8 @@ out: module_put(THIS_MODULE); return rc; +err_out_cleanup_disk: + rbd_free_disk(rbd_dev); err_out_image_lock: rbd_dev_image_unlock(rbd_dev); rbd_dev_device_release(rbd_dev); diff --git a/drivers/block/rnbd/rnbd-clt.c b/drivers/block/rnbd/rnbd-clt.c index 0ec0191d4196..2df0657cdf00 100644 --- a/drivers/block/rnbd/rnbd-clt.c +++ b/drivers/block/rnbd/rnbd-clt.c @@ -1384,8 +1384,10 @@ static void setup_request_queue(struct rnbd_clt_dev *dev) blk_queue_write_cache(dev->queue, dev->wc, dev->fua); } -static void rnbd_clt_setup_gen_disk(struct rnbd_clt_dev *dev, int idx) +static int rnbd_clt_setup_gen_disk(struct rnbd_clt_dev *dev, int idx) { + int err; + dev->gd->major = rnbd_client_major; dev->gd->first_minor = idx << RNBD_PART_BITS; dev->gd->minors = 1 << RNBD_PART_BITS; @@ -1410,7 +1412,11 @@ static void rnbd_clt_setup_gen_disk(struct rnbd_clt_dev *dev, int idx) if (!dev->rotational) blk_queue_flag_set(QUEUE_FLAG_NONROT, dev->queue); - add_disk(dev->gd); + err = add_disk(dev->gd); + if (err) + blk_cleanup_disk(dev->gd); + + return err; } static int rnbd_client_setup_device(struct rnbd_clt_dev *dev) @@ -1426,8 +1432,7 @@ static int rnbd_client_setup_device(struct rnbd_clt_dev *dev) rnbd_init_mq_hw_queues(dev); setup_request_queue(dev); - rnbd_clt_setup_gen_disk(dev, idx); - return 0; + return rnbd_clt_setup_gen_disk(dev, idx); } static struct rnbd_clt_dev *init_dev(struct rnbd_clt_session *sess, diff --git a/drivers/block/rsxx/core.c b/drivers/block/rsxx/core.c index 83636714b8d7..8d9d69f5dfbc 100644 --- a/drivers/block/rsxx/core.c +++ b/drivers/block/rsxx/core.c @@ -935,7 +935,9 @@ static int rsxx_pci_probe(struct pci_dev *dev, card->size8 = 0; } - rsxx_attach_dev(card); + st = rsxx_attach_dev(card); + if (st) + goto failed_create_dev; /************* Setup Debugfs *************/ rsxx_debugfs_dev_new(card); diff --git a/drivers/block/rsxx/dev.c b/drivers/block/rsxx/dev.c index 268252380e88..dd33f1bdf3b8 100644 --- a/drivers/block/rsxx/dev.c +++ b/drivers/block/rsxx/dev.c @@ -191,6 +191,8 @@ static bool rsxx_discard_supported(struct rsxx_cardinfo *card) int rsxx_attach_dev(struct rsxx_cardinfo *card) { + int err = 0; + mutex_lock(&card->dev_lock); /* The block device requires the stripe size from the config. */ @@ -199,13 +201,17 @@ int rsxx_attach_dev(struct rsxx_cardinfo *card) set_capacity(card->gendisk, card->size8 >> 9); else set_capacity(card->gendisk, 0); - device_add_disk(CARD_TO_DEV(card), card->gendisk, NULL); - card->bdev_attached = 1; + err = device_add_disk(CARD_TO_DEV(card), card->gendisk, NULL); + if (err == 0) + card->bdev_attached = 1; } mutex_unlock(&card->dev_lock); - return 0; + if (err) + blk_cleanup_disk(card->gendisk); + + return err; } void rsxx_detach_dev(struct rsxx_cardinfo *card) diff --git a/drivers/block/swim.c b/drivers/block/swim.c index 3911d0833e1b..821594cd1315 100644 --- a/drivers/block/swim.c +++ b/drivers/block/swim.c @@ -185,6 +185,7 @@ struct floppy_state { int track; int ref_count; + bool registered; struct gendisk *disk; struct blk_mq_tag_set tag_set; @@ -772,6 +773,20 @@ static const struct blk_mq_ops swim_mq_ops = { .queue_rq = swim_queue_rq, }; +static void swim_cleanup_floppy_disk(struct floppy_state *fs) +{ + struct gendisk *disk = fs->disk; + + if (!disk) + return; + + if (fs->registered) + del_gendisk(fs->disk); + + blk_cleanup_disk(disk); + blk_mq_free_tag_set(&fs->tag_set); +} + static int swim_floppy_init(struct swim_priv *swd) { int err; @@ -828,7 +843,10 @@ static int swim_floppy_init(struct swim_priv *swd) swd->unit[drive].disk->events = DISK_EVENT_MEDIA_CHANGE; swd->unit[drive].disk->private_data = &swd->unit[drive]; set_capacity(swd->unit[drive].disk, 2880); - add_disk(swd->unit[drive].disk); + err = add_disk(swd->unit[drive].disk); + if (err) + goto exit_put_disks; + swd->unit[drive].registered = true; } return 0; @@ -836,12 +854,7 @@ static int swim_floppy_init(struct swim_priv *swd) exit_put_disks: unregister_blkdev(FLOPPY_MAJOR, "fd"); do { - struct gendisk *disk = swd->unit[drive].disk; - - if (!disk) - continue; - blk_cleanup_disk(disk); - blk_mq_free_tag_set(&swd->unit[drive].tag_set); + swim_cleanup_floppy_disk(&swd->unit[drive]); } while (drive--); return err; } @@ -910,12 +923,8 @@ static int swim_remove(struct platform_device *dev) int drive; struct resource *res; - for (drive = 0; drive < swd->floppy_count; drive++) { - del_gendisk(swd->unit[drive].disk); - blk_cleanup_queue(swd->unit[drive].disk->queue); - blk_mq_free_tag_set(&swd->unit[drive].tag_set); - put_disk(swd->unit[drive].disk); - } + for (drive = 0; drive < swd->floppy_count; drive++) + swim_cleanup_floppy_disk(&swd->unit[drive]); unregister_blkdev(FLOPPY_MAJOR, "fd"); diff --git a/drivers/block/swim3.c b/drivers/block/swim3.c index 965af0a3e95b..4b91c9aa5892 100644 --- a/drivers/block/swim3.c +++ b/drivers/block/swim3.c @@ -27,6 +27,7 @@ #include #include #include +#include #include #include #include @@ -1229,7 +1230,9 @@ static int swim3_attach(struct macio_dev *mdev, disk->flags |= GENHD_FL_REMOVABLE; sprintf(disk->disk_name, "fd%d", floppy_count); set_capacity(disk, 2880); - add_disk(disk); + rc = add_disk(disk); + if (rc) + goto out_cleanup_disk; disks[floppy_count++] = disk; return 0; diff --git a/drivers/block/sx8.c b/drivers/block/sx8.c index 420cd952ddc4..d1676fe0da1a 100644 --- a/drivers/block/sx8.c +++ b/drivers/block/sx8.c @@ -297,6 +297,7 @@ struct carm_host { struct work_struct fsm_task; + int probe_err; struct completion probe_comp; }; @@ -1181,8 +1182,11 @@ static void carm_fsm_task (struct work_struct *work) struct gendisk *disk = port->disk; set_capacity(disk, port->capacity); - add_disk(disk); - activated++; + host->probe_err = add_disk(disk); + if (!host->probe_err) + activated++; + else + break; } printk(KERN_INFO DRV_NAME "(%s): %d ports activated\n", @@ -1192,11 +1196,9 @@ static void carm_fsm_task (struct work_struct *work) reschedule = 1; break; } - case HST_PROBE_FINISHED: complete(&host->probe_comp); break; - case HST_ERROR: /* FIXME: TODO */ break; @@ -1507,7 +1509,12 @@ static int carm_init_one (struct pci_dev *pdev, const struct pci_device_id *ent) goto err_out_free_irq; DPRINTK("waiting for probe_comp\n"); + host->probe_err = -ENODEV; wait_for_completion(&host->probe_comp); + if (host->probe_err) { + rc = host->probe_err; + goto err_out_free_irq; + } printk(KERN_INFO "%s: pci %s, ports %d, io %llx, irq %u, major %d\n", host->name, pci_name(pdev), (int) CARM_MAX_PORTS, diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c index df0deb927760..8e3983e456f3 100644 --- a/drivers/block/xen-blkfront.c +++ b/drivers/block/xen-blkfront.c @@ -2386,7 +2386,13 @@ static void blkfront_connect(struct blkfront_info *info) for_each_rinfo(info, rinfo, i) kick_pending_request_queues(rinfo); - device_add_disk(&info->xbdev->dev, info->gd, NULL); + err = device_add_disk(&info->xbdev->dev, info->gd, NULL); + if (err) { + blk_cleanup_disk(info->gd); + blk_mq_free_tag_set(&info->tag_set); + info->rq = NULL; + goto fail; + } info->is_ready = 1; return; diff --git a/drivers/cdrom/cdrom.c b/drivers/cdrom/cdrom.c index bd2e5b1560f5..9877e413fce3 100644 --- a/drivers/cdrom/cdrom.c +++ b/drivers/cdrom/cdrom.c @@ -344,6 +344,12 @@ static void cdrom_sysctl_register(void); static LIST_HEAD(cdrom_list); +static void signal_media_change(struct cdrom_device_info *cdi) +{ + cdi->mc_flags = 0x3; /* set media changed bits, on both queues */ + cdi->last_media_change_ms = ktime_to_ms(ktime_get()); +} + int cdrom_dummy_generic_packet(struct cdrom_device_info *cdi, struct packet_command *cgc) { @@ -616,6 +622,7 @@ int register_cdrom(struct gendisk *disk, struct cdrom_device_info *cdi) ENSURE(cdo, generic_packet, CDC_GENERIC_PACKET); cdi->mc_flags = 0; cdi->options = CDO_USE_FFLAGS; + cdi->last_media_change_ms = ktime_to_ms(ktime_get()); if (autoclose == 1 && CDROM_CAN(CDC_CLOSE_TRAY)) cdi->options |= (int) CDO_AUTO_CLOSE; @@ -864,7 +871,7 @@ static void cdrom_mmc3_profile(struct cdrom_device_info *cdi) { struct packet_command cgc; char buffer[32]; - int ret, mmc3_profile; + int mmc3_profile; init_cdrom_command(&cgc, buffer, sizeof(buffer), CGC_DATA_READ); @@ -874,7 +881,7 @@ static void cdrom_mmc3_profile(struct cdrom_device_info *cdi) cgc.cmd[8] = sizeof(buffer); /* Allocation Length */ cgc.quiet = 1; - if ((ret = cdi->ops->generic_packet(cdi, &cgc))) + if (cdi->ops->generic_packet(cdi, &cgc)) mmc3_profile = 0xffff; else mmc3_profile = (buffer[6] << 8) | buffer[7]; @@ -1421,8 +1428,7 @@ static int cdrom_select_disc(struct cdrom_device_info *cdi, int slot) cdi->ops->check_events(cdi, 0, slot); if (slot == CDSL_NONE) { - /* set media changed bits, on both queues */ - cdi->mc_flags = 0x3; + signal_media_change(cdi); return cdrom_load_unload(cdi, -1); } @@ -1455,7 +1461,7 @@ static int cdrom_select_disc(struct cdrom_device_info *cdi, int slot) slot = curslot; /* set media changed bits on both queues */ - cdi->mc_flags = 0x3; + signal_media_change(cdi); if ((ret = cdrom_load_unload(cdi, slot))) return ret; @@ -1521,7 +1527,7 @@ int media_changed(struct cdrom_device_info *cdi, int queue) cdi->ioctl_events = 0; if (changed) { - cdi->mc_flags = 0x3; /* set bit on both queues */ + signal_media_change(cdi); ret |= 1; cdi->media_written = 0; } @@ -2336,6 +2342,49 @@ static int cdrom_ioctl_media_changed(struct cdrom_device_info *cdi, return ret; } +/* + * Media change detection with timing information. + * + * arg is a pointer to a cdrom_timed_media_change_info struct. + * arg->last_media_change may be set by calling code to signal + * the timestamp (in ms) of the last known media change (by the caller). + * Upon successful return, ioctl call will set arg->last_media_change + * to the latest media change timestamp known by the kernel/driver + * and set arg->has_changed to 1 if that timestamp is more recent + * than the timestamp set by the caller. + */ +static int cdrom_ioctl_timed_media_change(struct cdrom_device_info *cdi, + unsigned long arg) +{ + int ret; + struct cdrom_timed_media_change_info __user *info; + struct cdrom_timed_media_change_info tmp_info; + + if (!CDROM_CAN(CDC_MEDIA_CHANGED)) + return -ENOSYS; + + info = (struct cdrom_timed_media_change_info __user *)arg; + cd_dbg(CD_DO_IOCTL, "entering CDROM_TIMED_MEDIA_CHANGE\n"); + + ret = cdrom_ioctl_media_changed(cdi, CDSL_CURRENT); + if (ret < 0) + return ret; + + if (copy_from_user(&tmp_info, info, sizeof(tmp_info)) != 0) + return -EFAULT; + + tmp_info.media_flags = 0; + if (tmp_info.last_media_change - cdi->last_media_change_ms < 0) + tmp_info.media_flags |= MEDIA_CHANGED_FLAG; + + tmp_info.last_media_change = cdi->last_media_change_ms; + + if (copy_to_user(info, &tmp_info, sizeof(*info)) != 0) + return -EFAULT; + + return 0; +} + static int cdrom_ioctl_set_options(struct cdrom_device_info *cdi, unsigned long arg) { @@ -3313,6 +3362,8 @@ int cdrom_ioctl(struct cdrom_device_info *cdi, struct block_device *bdev, return cdrom_ioctl_eject_sw(cdi, arg); case CDROM_MEDIA_CHANGED: return cdrom_ioctl_media_changed(cdi, arg); + case CDROM_TIMED_MEDIA_CHANGE: + return cdrom_ioctl_timed_media_change(cdi, arg); case CDROM_SET_OPTIONS: return cdrom_ioctl_set_options(cdi, arg); case CDROM_CLEAR_OPTIONS: diff --git a/drivers/cdrom/gdrom.c b/drivers/cdrom/gdrom.c index 8e1fe75af93f..d50cc1fd34d5 100644 --- a/drivers/cdrom/gdrom.c +++ b/drivers/cdrom/gdrom.c @@ -805,9 +805,14 @@ static int probe_gdrom(struct platform_device *devptr) err = -ENOMEM; goto probe_fail_free_irqs; } - add_disk(gd.disk); + err = add_disk(gd.disk); + if (err) + goto probe_fail_add_disk; + return 0; +probe_fail_add_disk: + kfree(gd.toc); probe_fail_free_irqs: free_irq(HW_EVENT_GDROM_DMA, &gd); free_irq(HW_EVENT_GDROM_CMD, &gd); diff --git a/drivers/md/bcache/bcache.h b/drivers/md/bcache/bcache.h index 5fc989a6d452..9ed9c955add7 100644 --- a/drivers/md/bcache/bcache.h +++ b/drivers/md/bcache/bcache.h @@ -178,7 +178,6 @@ #define pr_fmt(fmt) "bcache: %s() " fmt, __func__ -#include #include #include #include @@ -190,6 +189,7 @@ #include #include +#include "bcache_ondisk.h" #include "bset.h" #include "util.h" #include "closure.h" @@ -395,8 +395,6 @@ struct cached_dev { atomic_t io_errors; unsigned int error_limit; unsigned int offline_seconds; - - char backing_dev_name[BDEVNAME_SIZE]; }; enum alloc_reserve { @@ -470,8 +468,6 @@ struct cache { atomic_long_t meta_sectors_written; atomic_long_t btree_sectors_written; atomic_long_t sectors_written; - - char cache_dev_name[BDEVNAME_SIZE]; }; struct gc_stat { diff --git a/include/uapi/linux/bcache.h b/drivers/md/bcache/bcache_ondisk.h similarity index 99% rename from include/uapi/linux/bcache.h rename to drivers/md/bcache/bcache_ondisk.h index cf7399f03b71..97413586195b 100644 --- a/include/uapi/linux/bcache.h +++ b/drivers/md/bcache/bcache_ondisk.h @@ -43,9 +43,9 @@ static inline void SET_##name(struct bkey *k, unsigned int i, __u64 v) \ #define KEY_MAX_U64S 8 KEY_FIELD(KEY_PTRS, high, 60, 3) -KEY_FIELD(HEADER_SIZE, high, 58, 2) +KEY_FIELD(__PAD0, high, 58, 2) KEY_FIELD(KEY_CSUM, high, 56, 2) -KEY_FIELD(KEY_PINNED, high, 55, 1) +KEY_FIELD(__PAD1, high, 55, 1) KEY_FIELD(KEY_DIRTY, high, 36, 1) KEY_FIELD(KEY_SIZE, high, 20, KEY_SIZE_BITS) diff --git a/drivers/md/bcache/bset.h b/drivers/md/bcache/bset.h index a50dcfda656f..d795c84246b0 100644 --- a/drivers/md/bcache/bset.h +++ b/drivers/md/bcache/bset.h @@ -2,10 +2,10 @@ #ifndef _BCACHE_BSET_H #define _BCACHE_BSET_H -#include #include #include +#include "bcache_ondisk.h" #include "util.h" /* for time_stats */ /* diff --git a/drivers/md/bcache/btree.c b/drivers/md/bcache/btree.c index 0595559de174..93b67b8d31c3 100644 --- a/drivers/md/bcache/btree.c +++ b/drivers/md/bcache/btree.c @@ -141,7 +141,7 @@ static uint64_t btree_csum_set(struct btree *b, struct bset *i) uint64_t crc = b->key.ptr[0]; void *data = (void *) i + 8, *end = bset_bkey_last(i); - crc = bch_crc64_update(crc, data, end - data); + crc = crc64_be(crc, data, end - data); return crc ^ 0xffffffffffffffffULL; } diff --git a/drivers/md/bcache/debug.c b/drivers/md/bcache/debug.c index 116edda845c3..6230dfdd9286 100644 --- a/drivers/md/bcache/debug.c +++ b/drivers/md/bcache/debug.c @@ -127,21 +127,20 @@ void bch_data_verify(struct cached_dev *dc, struct bio *bio) citer.bi_size = UINT_MAX; bio_for_each_segment(bv, bio, iter) { - void *p1 = kmap_atomic(bv.bv_page); + void *p1 = bvec_kmap_local(&bv); void *p2; cbv = bio_iter_iovec(check, citer); - p2 = page_address(cbv.bv_page); + p2 = bvec_kmap_local(&cbv); - cache_set_err_on(memcmp(p1 + bv.bv_offset, - p2 + bv.bv_offset, - bv.bv_len), + cache_set_err_on(memcmp(p1, p2, bv.bv_len), dc->disk.c, - "verify failed at dev %s sector %llu", - dc->backing_dev_name, + "verify failed at dev %pg sector %llu", + dc->bdev, (uint64_t) bio->bi_iter.bi_sector); - kunmap_atomic(p1); + kunmap_local(p2); + kunmap_local(p1); bio_advance_iter(check, &citer, bv.bv_len); } diff --git a/drivers/md/bcache/features.c b/drivers/md/bcache/features.c index 6d2b7b84a7b7..634922c5601d 100644 --- a/drivers/md/bcache/features.c +++ b/drivers/md/bcache/features.c @@ -6,7 +6,7 @@ * Copyright 2020 Coly Li * */ -#include +#include "bcache_ondisk.h" #include "bcache.h" #include "features.h" diff --git a/drivers/md/bcache/features.h b/drivers/md/bcache/features.h index d1c8fd3977fc..09161b89c63e 100644 --- a/drivers/md/bcache/features.h +++ b/drivers/md/bcache/features.h @@ -2,10 +2,11 @@ #ifndef _BCACHE_FEATURES_H #define _BCACHE_FEATURES_H -#include #include #include +#include "bcache_ondisk.h" + #define BCH_FEATURE_COMPAT 0 #define BCH_FEATURE_RO_COMPAT 1 #define BCH_FEATURE_INCOMPAT 2 diff --git a/drivers/md/bcache/io.c b/drivers/md/bcache/io.c index e4388fe3ab7e..9c6f9ec55b72 100644 --- a/drivers/md/bcache/io.c +++ b/drivers/md/bcache/io.c @@ -65,15 +65,15 @@ void bch_count_backing_io_errors(struct cached_dev *dc, struct bio *bio) * we shouldn't count failed REQ_RAHEAD bio to dc->io_errors. */ if (bio->bi_opf & REQ_RAHEAD) { - pr_warn_ratelimited("%s: Read-ahead I/O failed on backing device, ignore\n", - dc->backing_dev_name); + pr_warn_ratelimited("%pg: Read-ahead I/O failed on backing device, ignore\n", + dc->bdev); return; } errors = atomic_add_return(1, &dc->io_errors); if (errors < dc->error_limit) - pr_err("%s: IO error on backing device, unrecoverable\n", - dc->backing_dev_name); + pr_err("%pg: IO error on backing device, unrecoverable\n", + dc->bdev); else bch_cached_dev_error(dc); } @@ -123,13 +123,13 @@ void bch_count_io_errors(struct cache *ca, errors >>= IO_ERROR_SHIFT; if (errors < ca->set->error_limit) - pr_err("%s: IO error on %s%s\n", - ca->cache_dev_name, m, + pr_err("%pg: IO error on %s%s\n", + ca->bdev, m, is_read ? ", recovering." : "."); else bch_cache_set_error(ca->set, - "%s: too many IO errors %s\n", - ca->cache_dev_name, m); + "%pg: too many IO errors %s\n", + ca->bdev, m); } } diff --git a/drivers/md/bcache/request.c b/drivers/md/bcache/request.c index 23b28edae90f..d15aae6c51c1 100644 --- a/drivers/md/bcache/request.c +++ b/drivers/md/bcache/request.c @@ -46,7 +46,7 @@ static void bio_csum(struct bio *bio, struct bkey *k) bio_for_each_segment(bv, bio, iter) { void *d = kmap(bv.bv_page) + bv.bv_offset; - csum = bch_crc64_update(csum, d, bv.bv_len); + csum = crc64_be(csum, d, bv.bv_len); kunmap(bv.bv_page); } @@ -651,8 +651,8 @@ static void backing_request_endio(struct bio *bio) */ if (unlikely(s->iop.writeback && bio->bi_opf & REQ_PREFLUSH)) { - pr_err("Can't flush %s: returned bi_status %i\n", - dc->backing_dev_name, bio->bi_status); + pr_err("Can't flush %pg: returned bi_status %i\n", + dc->bdev, bio->bi_status); } else { /* set to orig_bio->bi_status in bio_complete() */ s->iop.status = bio->bi_status; diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c index f2874c77ff79..4a9a65dff95e 100644 --- a/drivers/md/bcache/super.c +++ b/drivers/md/bcache/super.c @@ -1002,7 +1002,7 @@ static void calc_cached_dev_sectors(struct cache_set *c) struct cached_dev *dc; list_for_each_entry(dc, &c->cached_devs, list) - sectors += bdev_sectors(dc->bdev); + sectors += bdev_nr_sectors(dc->bdev); c->cached_dev_sectors = sectors; } @@ -1026,8 +1026,8 @@ static int cached_dev_status_update(void *arg) dc->offline_seconds = 0; if (dc->offline_seconds >= BACKING_DEV_OFFLINE_TIMEOUT) { - pr_err("%s: device offline for %d seconds\n", - dc->backing_dev_name, + pr_err("%pg: device offline for %d seconds\n", + dc->bdev, BACKING_DEV_OFFLINE_TIMEOUT); pr_err("%s: disable I/O request due to backing device offline\n", dc->disk.name); @@ -1058,15 +1058,13 @@ int bch_cached_dev_run(struct cached_dev *dc) }; if (dc->io_disable) { - pr_err("I/O disabled on cached dev %s\n", - dc->backing_dev_name); + pr_err("I/O disabled on cached dev %pg\n", dc->bdev); ret = -EIO; goto out; } if (atomic_xchg(&dc->running, 1)) { - pr_info("cached dev %s is running already\n", - dc->backing_dev_name); + pr_info("cached dev %pg is running already\n", dc->bdev); ret = -EBUSY; goto out; } @@ -1082,7 +1080,9 @@ int bch_cached_dev_run(struct cached_dev *dc) closure_sync(&cl); } - add_disk(d->disk); + ret = add_disk(d->disk); + if (ret) + goto out; bd_link_disk_holder(dc->bdev, dc->disk.disk); /* * won't show up in the uevent file, use udevadm monitor -e instead @@ -1154,16 +1154,16 @@ static void cached_dev_detach_finish(struct work_struct *w) mutex_lock(&bch_register_lock); - calc_cached_dev_sectors(dc->disk.c); bcache_device_detach(&dc->disk); list_move(&dc->list, &uncached_devices); + calc_cached_dev_sectors(dc->disk.c); clear_bit(BCACHE_DEV_DETACHING, &dc->disk.flags); clear_bit(BCACHE_DEV_UNLINK_DONE, &dc->disk.flags); mutex_unlock(&bch_register_lock); - pr_info("Caching disabled for %s\n", dc->backing_dev_name); + pr_info("Caching disabled for %pg\n", dc->bdev); /* Drop ref we took in cached_dev_detach() */ closure_put(&dc->disk.cl); @@ -1203,29 +1203,27 @@ int bch_cached_dev_attach(struct cached_dev *dc, struct cache_set *c, return -ENOENT; if (dc->disk.c) { - pr_err("Can't attach %s: already attached\n", - dc->backing_dev_name); + pr_err("Can't attach %pg: already attached\n", dc->bdev); return -EINVAL; } if (test_bit(CACHE_SET_STOPPING, &c->flags)) { - pr_err("Can't attach %s: shutting down\n", - dc->backing_dev_name); + pr_err("Can't attach %pg: shutting down\n", dc->bdev); return -EINVAL; } if (dc->sb.block_size < c->cache->sb.block_size) { /* Will die */ - pr_err("Couldn't attach %s: block size less than set's block size\n", - dc->backing_dev_name); + pr_err("Couldn't attach %pg: block size less than set's block size\n", + dc->bdev); return -EINVAL; } /* Check whether already attached */ list_for_each_entry_safe(exist_dc, t, &c->cached_devs, list) { if (!memcmp(dc->sb.uuid, exist_dc->sb.uuid, 16)) { - pr_err("Tried to attach %s but duplicate UUID already attached\n", - dc->backing_dev_name); + pr_err("Tried to attach %pg but duplicate UUID already attached\n", + dc->bdev); return -EINVAL; } @@ -1243,15 +1241,13 @@ int bch_cached_dev_attach(struct cached_dev *dc, struct cache_set *c, if (!u) { if (BDEV_STATE(&dc->sb) == BDEV_STATE_DIRTY) { - pr_err("Couldn't find uuid for %s in set\n", - dc->backing_dev_name); + pr_err("Couldn't find uuid for %pg in set\n", dc->bdev); return -ENOENT; } u = uuid_find_empty(c); if (!u) { - pr_err("Not caching %s, no room for UUID\n", - dc->backing_dev_name); + pr_err("Not caching %pg, no room for UUID\n", dc->bdev); return -EINVAL; } } @@ -1319,8 +1315,7 @@ int bch_cached_dev_attach(struct cached_dev *dc, struct cache_set *c, */ kthread_stop(dc->writeback_thread); cancel_writeback_rate_update_dwork(dc); - pr_err("Couldn't run cached device %s\n", - dc->backing_dev_name); + pr_err("Couldn't run cached device %pg\n", dc->bdev); return ret; } @@ -1336,8 +1331,8 @@ int bch_cached_dev_attach(struct cached_dev *dc, struct cache_set *c, /* Allow the writeback thread to proceed */ up_write(&dc->writeback_lock); - pr_info("Caching %s as %s on set %pU\n", - dc->backing_dev_name, + pr_info("Caching %pg as %s on set %pU\n", + dc->bdev, dc->disk.disk->disk_name, dc->disk.c->set_uuid); return 0; @@ -1461,7 +1456,6 @@ static int register_bdev(struct cache_sb *sb, struct cache_sb_disk *sb_disk, struct cache_set *c; int ret = -ENOMEM; - bdevname(bdev, dc->backing_dev_name); memcpy(&dc->sb, sb, sizeof(struct cache_sb)); dc->bdev = bdev; dc->bdev->bd_holder = dc; @@ -1476,7 +1470,7 @@ static int register_bdev(struct cache_sb *sb, struct cache_sb_disk *sb_disk, if (bch_cache_accounting_add_kobjs(&dc->accounting, &dc->disk.kobj)) goto err; - pr_info("registered backing device %s\n", dc->backing_dev_name); + pr_info("registered backing device %pg\n", dc->bdev); list_add(&dc->list, &uncached_devices); /* attach to a matched cache set if it exists */ @@ -1493,7 +1487,7 @@ static int register_bdev(struct cache_sb *sb, struct cache_sb_disk *sb_disk, return 0; err: - pr_notice("error %s: %s\n", dc->backing_dev_name, err); + pr_notice("error %pg: %s\n", dc->bdev, err); bcache_device_stop(&dc->disk); return ret; } @@ -1534,10 +1528,11 @@ static void flash_dev_flush(struct closure *cl) static int flash_dev_run(struct cache_set *c, struct uuid_entry *u) { + int err = -ENOMEM; struct bcache_device *d = kzalloc(sizeof(struct bcache_device), GFP_KERNEL); if (!d) - return -ENOMEM; + goto err_ret; closure_init(&d->cl, NULL); set_closure_fn(&d->cl, flash_dev_flush, system_wq); @@ -1551,9 +1546,12 @@ static int flash_dev_run(struct cache_set *c, struct uuid_entry *u) bcache_device_attach(d, c, u - c->uuids); bch_sectors_dirty_init(d); bch_flash_dev_request_init(d); - add_disk(d->disk); + err = add_disk(d->disk); + if (err) + goto err; - if (kobject_add(&d->kobj, &disk_to_dev(d->disk)->kobj, "bcache")) + err = kobject_add(&d->kobj, &disk_to_dev(d->disk)->kobj, "bcache"); + if (err) goto err; bcache_device_link(d, c, "volume"); @@ -1567,7 +1565,8 @@ static int flash_dev_run(struct cache_set *c, struct uuid_entry *u) return 0; err: kobject_put(&d->kobj); - return -ENOMEM; +err_ret: + return err; } static int flash_devs_run(struct cache_set *c) @@ -1621,8 +1620,8 @@ bool bch_cached_dev_error(struct cached_dev *dc) /* make others know io_disable is true earlier */ smp_mb(); - pr_err("stop %s: too many IO errors on backing device %s\n", - dc->disk.disk->disk_name, dc->backing_dev_name); + pr_err("stop %s: too many IO errors on backing device %pg\n", + dc->disk.disk->disk_name, dc->bdev); bcache_device_stop(&dc->disk); return true; @@ -2338,7 +2337,7 @@ err_btree_alloc: err_free: module_put(THIS_MODULE); if (err) - pr_notice("error %s: %s\n", ca->cache_dev_name, err); + pr_notice("error %pg: %s\n", ca->bdev, err); return ret; } @@ -2348,7 +2347,6 @@ static int register_cache(struct cache_sb *sb, struct cache_sb_disk *sb_disk, const char *err = NULL; /* must be set for any error case */ int ret = 0; - bdevname(bdev, ca->cache_dev_name); memcpy(&ca->sb, sb, sizeof(struct cache_sb)); ca->bdev = bdev; ca->bdev->bd_holder = ca; @@ -2390,14 +2388,14 @@ static int register_cache(struct cache_sb *sb, struct cache_sb_disk *sb_disk, goto out; } - pr_info("registered cache device %s\n", ca->cache_dev_name); + pr_info("registered cache device %pg\n", ca->bdev); out: kobject_put(&ca->kobj); err: if (err) - pr_notice("error %s: %s\n", ca->cache_dev_name, err); + pr_notice("error %pg: %s\n", ca->bdev, err); return ret; } @@ -2617,8 +2615,11 @@ static ssize_t register_bcache(struct kobject *k, struct kobj_attribute *attr, if (SB_IS_BDEV(sb)) { struct cached_dev *dc = kzalloc(sizeof(*dc), GFP_KERNEL); - if (!dc) + if (!dc) { + ret = -ENOMEM; + err = "cannot allocate memory"; goto out_put_sb_page; + } mutex_lock(&bch_register_lock); ret = register_bdev(sb, sb_disk, bdev, dc); @@ -2629,11 +2630,15 @@ static ssize_t register_bcache(struct kobject *k, struct kobj_attribute *attr, } else { struct cache *ca = kzalloc(sizeof(*ca), GFP_KERNEL); - if (!ca) + if (!ca) { + ret = -ENOMEM; + err = "cannot allocate memory"; goto out_put_sb_page; + } /* blkdev_put() will be called in bch_cache_release() */ - if (register_cache(sb, sb_disk, bdev, ca) != 0) + ret = register_cache(sb, sb_disk, bdev, ca); + if (ret) goto out_free_sb; } @@ -2750,7 +2755,7 @@ static int bcache_reboot(struct notifier_block *n, unsigned long code, void *x) * The reason bch_register_lock is not held to call * bch_cache_set_stop() and bcache_device_stop() is to * avoid potential deadlock during reboot, because cache - * set or bcache device stopping process will acqurie + * set or bcache device stopping process will acquire * bch_register_lock too. * * We are safe here because bcache_is_reboot sets to diff --git a/drivers/md/bcache/sysfs.c b/drivers/md/bcache/sysfs.c index 05ac1d6fbbf3..1f0dce30fa75 100644 --- a/drivers/md/bcache/sysfs.c +++ b/drivers/md/bcache/sysfs.c @@ -271,7 +271,7 @@ SHOW(__bch_cached_dev) } if (attr == &sysfs_backing_dev_name) { - snprintf(buf, BDEVNAME_SIZE + 1, "%s", dc->backing_dev_name); + snprintf(buf, BDEVNAME_SIZE + 1, "%pg", dc->bdev); strcat(buf, "\n"); return strlen(buf); } diff --git a/drivers/md/bcache/sysfs.h b/drivers/md/bcache/sysfs.h index 215df32f567b..c1752ba2e05b 100644 --- a/drivers/md/bcache/sysfs.h +++ b/drivers/md/bcache/sysfs.h @@ -51,13 +51,27 @@ STORE(fn) \ #define sysfs_printf(file, fmt, ...) \ do { \ if (attr == &sysfs_ ## file) \ - return snprintf(buf, PAGE_SIZE, fmt "\n", __VA_ARGS__); \ + return sysfs_emit(buf, fmt "\n", __VA_ARGS__); \ } while (0) #define sysfs_print(file, var) \ do { \ if (attr == &sysfs_ ## file) \ - return snprint(buf, PAGE_SIZE, var); \ + return sysfs_emit(buf, \ + __builtin_types_compatible_p(typeof(var), int) \ + ? "%i\n" : \ + __builtin_types_compatible_p(typeof(var), unsigned int) \ + ? "%u\n" : \ + __builtin_types_compatible_p(typeof(var), long) \ + ? "%li\n" : \ + __builtin_types_compatible_p(typeof(var), unsigned long)\ + ? "%lu\n" : \ + __builtin_types_compatible_p(typeof(var), int64_t) \ + ? "%lli\n" : \ + __builtin_types_compatible_p(typeof(var), uint64_t) \ + ? "%llu\n" : \ + __builtin_types_compatible_p(typeof(var), const char *) \ + ? "%s\n" : "%i\n", var); \ } while (0) #define sysfs_hprint(file, val) \ diff --git a/drivers/md/bcache/util.h b/drivers/md/bcache/util.h index b64460a76267..6f3cb7c92130 100644 --- a/drivers/md/bcache/util.h +++ b/drivers/md/bcache/util.h @@ -340,23 +340,6 @@ static inline int bch_strtoul_h(const char *cp, long *res) _r; \ }) -#define snprint(buf, size, var) \ - snprintf(buf, size, \ - __builtin_types_compatible_p(typeof(var), int) \ - ? "%i\n" : \ - __builtin_types_compatible_p(typeof(var), unsigned int) \ - ? "%u\n" : \ - __builtin_types_compatible_p(typeof(var), long) \ - ? "%li\n" : \ - __builtin_types_compatible_p(typeof(var), unsigned long)\ - ? "%lu\n" : \ - __builtin_types_compatible_p(typeof(var), int64_t) \ - ? "%lli\n" : \ - __builtin_types_compatible_p(typeof(var), uint64_t) \ - ? "%llu\n" : \ - __builtin_types_compatible_p(typeof(var), const char *) \ - ? "%s\n" : "%i\n", var) - ssize_t bch_hprint(char *buf, int64_t v); bool bch_is_zero(const char *p, size_t n); @@ -548,14 +531,6 @@ static inline uint64_t bch_crc64(const void *p, size_t len) return crc ^ 0xffffffffffffffffULL; } -static inline uint64_t bch_crc64_update(uint64_t crc, - const void *p, - size_t len) -{ - crc = crc64_be(crc, p, len); - return crc; -} - /* * A stepwise-linear pseudo-exponential. This returns 1 << (x >> * frac_bits), with the less-significant bits filled in by linear @@ -584,8 +559,4 @@ static inline unsigned int fract_exp_two(unsigned int x, void bch_bio_map(struct bio *bio, void *base); int bch_bio_alloc_pages(struct bio *bio, gfp_t gfp_mask); -static inline sector_t bdev_sectors(struct block_device *bdev) -{ - return bdev->bd_inode->i_size >> 9; -} #endif /* _BCACHE_UTIL_H */ diff --git a/drivers/md/bcache/writeback.c b/drivers/md/bcache/writeback.c index 8120da278161..c7560f66dca8 100644 --- a/drivers/md/bcache/writeback.c +++ b/drivers/md/bcache/writeback.c @@ -45,7 +45,7 @@ static uint64_t __calc_target_rate(struct cached_dev *dc) * backing volume uses about 2% of the cache for dirty data. */ uint32_t bdev_share = - div64_u64(bdev_sectors(dc->bdev) << WRITEBACK_SHARE_SHIFT, + div64_u64(bdev_nr_sectors(dc->bdev) << WRITEBACK_SHARE_SHIFT, c->cached_dev_sectors); uint64_t cache_dirty_target = diff --git a/drivers/md/dm-bufio.c b/drivers/md/dm-bufio.c index 50f3e673729c..104ebc1f08dc 100644 --- a/drivers/md/dm-bufio.c +++ b/drivers/md/dm-bufio.c @@ -1525,7 +1525,7 @@ EXPORT_SYMBOL_GPL(dm_bufio_get_block_size); sector_t dm_bufio_get_device_size(struct dm_bufio_client *c) { - sector_t s = i_size_read(c->bdev->bd_inode) >> SECTOR_SHIFT; + sector_t s = bdev_nr_sectors(c->bdev); if (s >= c->start) s -= c->start; else diff --git a/drivers/md/dm-cache-metadata.c b/drivers/md/dm-cache-metadata.c index 89a73204dbf4..2874f222c313 100644 --- a/drivers/md/dm-cache-metadata.c +++ b/drivers/md/dm-cache-metadata.c @@ -334,7 +334,7 @@ static int __write_initial_superblock(struct dm_cache_metadata *cmd) int r; struct dm_block *sblock; struct cache_disk_superblock *disk_super; - sector_t bdev_size = i_size_read(cmd->bdev->bd_inode) >> SECTOR_SHIFT; + sector_t bdev_size = bdev_nr_sectors(cmd->bdev); /* FIXME: see if we can lose the max sectors limit */ if (bdev_size > DM_CACHE_METADATA_MAX_SECTORS) diff --git a/drivers/md/dm-cache-target.c b/drivers/md/dm-cache-target.c index bdd500447dea..447d030036d1 100644 --- a/drivers/md/dm-cache-target.c +++ b/drivers/md/dm-cache-target.c @@ -1940,7 +1940,7 @@ static void cache_dtr(struct dm_target *ti) static sector_t get_dev_size(struct dm_dev *dev) { - return i_size_read(dev->bdev->bd_inode) >> SECTOR_SHIFT; + return bdev_nr_sectors(dev->bdev); } /*----------------------------------------------------------------*/ diff --git a/drivers/md/dm-clone-target.c b/drivers/md/dm-clone-target.c index edd22e4d65df..4599632d7a84 100644 --- a/drivers/md/dm-clone-target.c +++ b/drivers/md/dm-clone-target.c @@ -1514,7 +1514,7 @@ error: static sector_t get_dev_size(struct dm_dev *dev) { - return i_size_read(dev->bdev->bd_inode) >> SECTOR_SHIFT; + return bdev_nr_sectors(dev->bdev); } /*---------------------------------------------------------------------------*/ diff --git a/drivers/md/dm-dust.c b/drivers/md/dm-dust.c index 3163e2b1418e..03672204b0e3 100644 --- a/drivers/md/dm-dust.c +++ b/drivers/md/dm-dust.c @@ -415,7 +415,7 @@ static int dust_message(struct dm_target *ti, unsigned int argc, char **argv, char *result, unsigned int maxlen) { struct dust_device *dd = ti->private; - sector_t size = i_size_read(dd->dev->bdev->bd_inode) >> SECTOR_SHIFT; + sector_t size = bdev_nr_sectors(dd->dev->bdev); bool invalid_msg = false; int r = -EINVAL; unsigned long long tmp, block; @@ -544,8 +544,7 @@ static int dust_prepare_ioctl(struct dm_target *ti, struct block_device **bdev) /* * Only pass ioctls through if the device sizes match exactly. */ - if (dd->start || - ti->len != i_size_read(dev->bdev->bd_inode) >> SECTOR_SHIFT) + if (dd->start || ti->len != bdev_nr_sectors(dev->bdev)) return 1; return 0; diff --git a/drivers/md/dm-ebs-target.c b/drivers/md/dm-ebs-target.c index d25989660a76..7ce5d509b940 100644 --- a/drivers/md/dm-ebs-target.c +++ b/drivers/md/dm-ebs-target.c @@ -416,7 +416,7 @@ static int ebs_prepare_ioctl(struct dm_target *ti, struct block_device **bdev) * Only pass ioctls through if the device sizes match exactly. */ *bdev = dev->bdev; - return !!(ec->start || ti->len != i_size_read(dev->bdev->bd_inode) >> SECTOR_SHIFT); + return !!(ec->start || ti->len != bdev_nr_sectors(dev->bdev)); } static void ebs_io_hints(struct dm_target *ti, struct queue_limits *limits) diff --git a/drivers/md/dm-era-target.c b/drivers/md/dm-era-target.c index 2a78f6874143..1f6bf152b3c7 100644 --- a/drivers/md/dm-era-target.c +++ b/drivers/md/dm-era-target.c @@ -1681,7 +1681,7 @@ static int era_message(struct dm_target *ti, unsigned argc, char **argv, static sector_t get_dev_size(struct dm_dev *dev) { - return i_size_read(dev->bdev->bd_inode) >> SECTOR_SHIFT; + return bdev_nr_sectors(dev->bdev); } static int era_iterate_devices(struct dm_target *ti, diff --git a/drivers/md/dm-exception-store.h b/drivers/md/dm-exception-store.h index 3f4139ac1f60..b5f20eba3641 100644 --- a/drivers/md/dm-exception-store.h +++ b/drivers/md/dm-exception-store.h @@ -168,7 +168,7 @@ static inline void dm_consecutive_chunk_count_dec(struct dm_exception *e) */ static inline sector_t get_dev_size(struct block_device *bdev) { - return i_size_read(bdev->bd_inode) >> SECTOR_SHIFT; + return bdev_nr_sectors(bdev); } static inline chunk_t sector_to_chunk(struct dm_exception_store *store, diff --git a/drivers/md/dm-flakey.c b/drivers/md/dm-flakey.c index 4b94ffe6f2d4..345229d7e59c 100644 --- a/drivers/md/dm-flakey.c +++ b/drivers/md/dm-flakey.c @@ -456,8 +456,7 @@ static int flakey_prepare_ioctl(struct dm_target *ti, struct block_device **bdev /* * Only pass ioctls through if the device sizes match exactly. */ - if (fc->start || - ti->len != i_size_read((*bdev)->bd_inode) >> SECTOR_SHIFT) + if (fc->start || ti->len != bdev_nr_sectors((*bdev))) return 1; return 0; } diff --git a/drivers/md/dm-integrity.c b/drivers/md/dm-integrity.c index dc03b70f6e65..d0f788e72abf 100644 --- a/drivers/md/dm-integrity.c +++ b/drivers/md/dm-integrity.c @@ -4113,11 +4113,11 @@ static int dm_integrity_ctr(struct dm_target *ti, unsigned argc, char **argv) } } - ic->data_device_sectors = i_size_read(ic->dev->bdev->bd_inode) >> SECTOR_SHIFT; + ic->data_device_sectors = bdev_nr_sectors(ic->dev->bdev); if (!ic->meta_dev) ic->meta_device_sectors = ic->data_device_sectors; else - ic->meta_device_sectors = i_size_read(ic->meta_dev->bdev->bd_inode) >> SECTOR_SHIFT; + ic->meta_device_sectors = bdev_nr_sectors(ic->meta_dev->bdev); if (!journal_sectors) { journal_sectors = min((sector_t)DEFAULT_MAX_JOURNAL_SECTORS, @@ -4367,7 +4367,7 @@ try_smaller_buffer: DEBUG_print(" journal_sections %u\n", (unsigned)le32_to_cpu(ic->sb->journal_sections)); DEBUG_print(" journal_entries %u\n", ic->journal_entries); DEBUG_print(" log2_interleave_sectors %d\n", ic->sb->log2_interleave_sectors); - DEBUG_print(" data_device_sectors 0x%llx\n", i_size_read(ic->dev->bdev->bd_inode) >> SECTOR_SHIFT); + DEBUG_print(" data_device_sectors 0x%llx\n", bdev_nr_sectors(ic->dev->bdev)); DEBUG_print(" initial_sectors 0x%x\n", ic->initial_sectors); DEBUG_print(" metadata_run 0x%x\n", ic->metadata_run); DEBUG_print(" log2_metadata_run %d\n", ic->log2_metadata_run); diff --git a/drivers/md/dm-linear.c b/drivers/md/dm-linear.c index 679b4c0a2eea..66ba16713f69 100644 --- a/drivers/md/dm-linear.c +++ b/drivers/md/dm-linear.c @@ -135,8 +135,7 @@ static int linear_prepare_ioctl(struct dm_target *ti, struct block_device **bdev /* * Only pass ioctls through if the device sizes match exactly. */ - if (lc->start || - ti->len != i_size_read(dev->bdev->bd_inode) >> SECTOR_SHIFT) + if (lc->start || ti->len != bdev_nr_sectors(dev->bdev)) return 1; return 0; } diff --git a/drivers/md/dm-log-writes.c b/drivers/md/dm-log-writes.c index d93a4db23512..46de085a9670 100644 --- a/drivers/md/dm-log-writes.c +++ b/drivers/md/dm-log-writes.c @@ -446,7 +446,7 @@ static int log_super(struct log_writes_c *lc) static inline sector_t logdev_last_sector(struct log_writes_c *lc) { - return i_size_read(lc->logdev->bdev->bd_inode) >> SECTOR_SHIFT; + return bdev_nr_sectors(lc->logdev->bdev); } static int log_writes_kthread(void *arg) @@ -851,7 +851,7 @@ static int log_writes_prepare_ioctl(struct dm_target *ti, /* * Only pass ioctls through if the device sizes match exactly. */ - if (ti->len != i_size_read(dev->bdev->bd_inode) >> SECTOR_SHIFT) + if (ti->len != bdev_nr_sectors(dev->bdev)) return 1; return 0; } diff --git a/drivers/md/dm-log.c b/drivers/md/dm-log.c index 1ecf75ef276a..06f328928a7f 100644 --- a/drivers/md/dm-log.c +++ b/drivers/md/dm-log.c @@ -447,7 +447,7 @@ static int create_log_context(struct dm_dirty_log *log, struct dm_target *ti, bdev_logical_block_size(lc->header_location. bdev)); - if (buf_size > i_size_read(dev->bdev->bd_inode)) { + if (buf_size > bdev_nr_bytes(dev->bdev)) { DMWARN("log device %s too small: need %llu bytes", dev->name, (unsigned long long)buf_size); kfree(lc); diff --git a/drivers/md/dm-mpath.c b/drivers/md/dm-mpath.c index 694aaca4eea2..5794f5415155 100644 --- a/drivers/md/dm-mpath.c +++ b/drivers/md/dm-mpath.c @@ -2061,7 +2061,7 @@ static int multipath_prepare_ioctl(struct dm_target *ti, /* * Only pass ioctls through if the device sizes match exactly. */ - if (!r && ti->len != i_size_read((*bdev)->bd_inode) >> SECTOR_SHIFT) + if (!r && ti->len != bdev_nr_sectors((*bdev))) return 1; return r; } diff --git a/drivers/md/dm-raid.c b/drivers/md/dm-raid.c index d9ef52159a22..2b26435a6946 100644 --- a/drivers/md/dm-raid.c +++ b/drivers/md/dm-raid.c @@ -1261,7 +1261,7 @@ static int parse_raid_params(struct raid_set *rs, struct dm_arg_set *as, md_rdev_init(jdev); jdev->mddev = &rs->md; jdev->bdev = rs->journal_dev.dev->bdev; - jdev->sectors = to_sector(i_size_read(jdev->bdev->bd_inode)); + jdev->sectors = bdev_nr_sectors(jdev->bdev); if (jdev->sectors < MIN_RAID456_JOURNAL_SPACE) { rs->ti->error = "No space for raid4/5/6 journal"; return -ENOSPC; @@ -1607,7 +1607,7 @@ static int _check_data_dev_sectors(struct raid_set *rs) rdev_for_each(rdev, &rs->md) if (!test_bit(Journal, &rdev->flags) && rdev->bdev) { - ds = min(ds, to_sector(i_size_read(rdev->bdev->bd_inode))); + ds = min(ds, bdev_nr_sectors(rdev->bdev)); if (ds < rs->md.dev_sectors) { rs->ti->error = "Component device(s) too small"; return -EINVAL; @@ -2662,7 +2662,7 @@ static int rs_adjust_data_offsets(struct raid_set *rs) * Make sure we got a minimum amount of free sectors per device */ if (rs->data_offset && - to_sector(i_size_read(rdev->bdev->bd_inode)) - rs->md.dev_sectors < MIN_FREE_RESHAPE_SPACE) { + bdev_nr_sectors(rdev->bdev) - rs->md.dev_sectors < MIN_FREE_RESHAPE_SPACE) { rs->ti->error = data_offset ? "No space for forward reshape" : "No space for backward reshape"; return -ENOSPC; diff --git a/drivers/md/dm-switch.c b/drivers/md/dm-switch.c index 028a92ff6d57..534dc2ca8bb0 100644 --- a/drivers/md/dm-switch.c +++ b/drivers/md/dm-switch.c @@ -529,7 +529,7 @@ static int switch_prepare_ioctl(struct dm_target *ti, struct block_device **bdev * Only pass ioctls through if the device sizes match exactly. */ if (ti->len + sctx->path_list[path_nr].start != - i_size_read((*bdev)->bd_inode) >> SECTOR_SHIFT) + bdev_nr_sectors((*bdev))) return 1; return 0; } diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c index 8b0f27a745d9..bcddc5effd15 100644 --- a/drivers/md/dm-table.c +++ b/drivers/md/dm-table.c @@ -227,8 +227,7 @@ static int device_area_is_invalid(struct dm_target *ti, struct dm_dev *dev, { struct queue_limits *limits = data; struct block_device *bdev = dev->bdev; - sector_t dev_size = - i_size_read(bdev->bd_inode) >> SECTOR_SHIFT; + sector_t dev_size = bdev_nr_sectors(bdev); unsigned short logical_block_size_sectors = limits->logical_block_size >> SECTOR_SHIFT; char b[BDEVNAME_SIZE]; diff --git a/drivers/md/dm-thin-metadata.c b/drivers/md/dm-thin-metadata.c index c88ed14d49e6..1a96a07cbf44 100644 --- a/drivers/md/dm-thin-metadata.c +++ b/drivers/md/dm-thin-metadata.c @@ -549,7 +549,7 @@ static int __write_initial_superblock(struct dm_pool_metadata *pmd) int r; struct dm_block *sblock; struct thin_disk_superblock *disk_super; - sector_t bdev_size = i_size_read(pmd->bdev->bd_inode) >> SECTOR_SHIFT; + sector_t bdev_size = bdev_nr_sectors(pmd->bdev); if (bdev_size > THIN_METADATA_MAX_SECTORS) bdev_size = THIN_METADATA_MAX_SECTORS; diff --git a/drivers/md/dm-thin.c b/drivers/md/dm-thin.c index 4c67b77c23c1..ec119d2422d5 100644 --- a/drivers/md/dm-thin.c +++ b/drivers/md/dm-thin.c @@ -3212,7 +3212,7 @@ static int metadata_pre_commit_callback(void *context) static sector_t get_dev_size(struct block_device *bdev) { - return i_size_read(bdev->bd_inode) >> SECTOR_SHIFT; + return bdev_nr_sectors(bdev); } static void warn_if_metadata_device_too_big(struct block_device *bdev) diff --git a/drivers/md/dm-verity-target.c b/drivers/md/dm-verity-target.c index aae48a8b1a04..a7efe83aad29 100644 --- a/drivers/md/dm-verity-target.c +++ b/drivers/md/dm-verity-target.c @@ -834,8 +834,7 @@ static int verity_prepare_ioctl(struct dm_target *ti, struct block_device **bdev *bdev = v->data_dev->bdev; - if (v->data_start || - ti->len != i_size_read(v->data_dev->bdev->bd_inode) >> SECTOR_SHIFT) + if (v->data_start || ti->len != bdev_nr_sectors(v->data_dev->bdev)) return 1; return 0; } diff --git a/drivers/md/dm-writecache.c b/drivers/md/dm-writecache.c index 18320444fb0a..017806096b91 100644 --- a/drivers/md/dm-writecache.c +++ b/drivers/md/dm-writecache.c @@ -2341,7 +2341,7 @@ static int writecache_ctr(struct dm_target *ti, unsigned argc, char **argv) ti->error = "Cache data device lookup failed"; goto bad; } - wc->memory_map_size = i_size_read(wc->ssd_dev->bdev->bd_inode); + wc->memory_map_size = bdev_nr_bytes(wc->ssd_dev->bdev); /* * Parse the cache block size diff --git a/drivers/md/dm-zoned-target.c b/drivers/md/dm-zoned-target.c index ae1bc48c0043..8dc21c09329f 100644 --- a/drivers/md/dm-zoned-target.c +++ b/drivers/md/dm-zoned-target.c @@ -733,7 +733,7 @@ static int dmz_get_zoned_device(struct dm_target *ti, char *path, dev->dev_idx = idx; (void)bdevname(dev->bdev, dev->name); - dev->capacity = i_size_read(bdev->bd_inode) >> SECTOR_SHIFT; + dev->capacity = bdev_nr_sectors(bdev); if (ti->begin) { ti->error = "Partial mapping is not supported"; goto err; diff --git a/drivers/md/dm.c b/drivers/md/dm.c index 8b91f4f0e053..63aa52263658 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -2078,7 +2078,9 @@ int dm_setup_md_queue(struct mapped_device *md, struct dm_table *t) if (r) return r; - add_disk(md->disk); + r = add_disk(md->disk); + if (r) + return r; r = dm_sysfs_init(md); if (r) { diff --git a/drivers/md/md.c b/drivers/md/md.c index 22310d5d8d41..5111ed966947 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -354,7 +354,7 @@ static bool create_on_open = true; */ static DECLARE_WAIT_QUEUE_HEAD(md_event_waiters); static atomic_t md_event_count; -void md_new_event(struct mddev *mddev) +void md_new_event(void) { atomic_inc(&md_event_count); wake_up(&md_event_waiters); @@ -888,8 +888,7 @@ static struct md_personality *find_pers(int level, char *clevel) /* return the offset of the super block in 512byte sectors */ static inline sector_t calc_dev_sboffset(struct md_rdev *rdev) { - sector_t num_sectors = i_size_read(rdev->bdev->bd_inode) / 512; - return MD_NEW_SIZE_SECTORS(num_sectors); + return MD_NEW_SIZE_SECTORS(bdev_nr_sectors(rdev->bdev)); } static int alloc_disk_sb(struct md_rdev *rdev) @@ -1631,8 +1630,7 @@ static int super_1_load(struct md_rdev *rdev, struct md_rdev *refdev, int minor_ */ switch(minor_version) { case 0: - sb_start = i_size_read(rdev->bdev->bd_inode) >> 9; - sb_start -= 8*2; + sb_start = bdev_nr_sectors(rdev->bdev) - 8 * 2; sb_start &= ~(sector_t)(4*2-1); break; case 1: @@ -1787,10 +1785,9 @@ static int super_1_load(struct md_rdev *rdev, struct md_rdev *refdev, int minor_ else ret = 0; } - if (minor_version) { - sectors = (i_size_read(rdev->bdev->bd_inode) >> 9); - sectors -= rdev->data_offset; - } else + if (minor_version) + sectors = bdev_nr_sectors(rdev->bdev) - rdev->data_offset; + else sectors = rdev->sb_start; if (sectors < le64_to_cpu(sb->data_size)) return -EINVAL; @@ -2168,8 +2165,7 @@ super_1_rdev_size_change(struct md_rdev *rdev, sector_t num_sectors) return 0; /* too confusing */ if (rdev->sb_start < rdev->data_offset) { /* minor versions 1 and 2; superblock before data */ - max_sectors = i_size_read(rdev->bdev->bd_inode) >> 9; - max_sectors -= rdev->data_offset; + max_sectors = bdev_nr_sectors(rdev->bdev) - rdev->data_offset; if (!num_sectors || num_sectors > max_sectors) num_sectors = max_sectors; } else if (rdev->mddev->bitmap_info.offset) { @@ -2178,7 +2174,7 @@ super_1_rdev_size_change(struct md_rdev *rdev, sector_t num_sectors) } else { /* minor version 0; superblock after data */ sector_t sb_start, bm_space; - sector_t dev_size = i_size_read(rdev->bdev->bd_inode) >> 9; + sector_t dev_size = bdev_nr_sectors(rdev->bdev); /* 8K is for superblock */ sb_start = dev_size - 8*2; @@ -2886,7 +2882,7 @@ static int add_bound_rdev(struct md_rdev *rdev) if (mddev->degraded) set_bit(MD_RECOVERY_RECOVER, &mddev->recovery); set_bit(MD_RECOVERY_NEEDED, &mddev->recovery); - md_new_event(mddev); + md_new_event(); md_wakeup_thread(mddev->thread); return 0; } @@ -2976,7 +2972,11 @@ state_store(struct md_rdev *rdev, const char *buf, size_t len) * -write_error - clears WriteErrorSeen * {,-}failfast - set/clear FailFast */ + + struct mddev *mddev = rdev->mddev; int err = -EINVAL; + bool need_update_sb = false; + if (cmd_match(buf, "faulty") && rdev->mddev->pers) { md_error(rdev->mddev, rdev); if (test_bit(Faulty, &rdev->flags)) @@ -2991,7 +2991,6 @@ state_store(struct md_rdev *rdev, const char *buf, size_t len) if (rdev->raid_disk >= 0) err = -EBUSY; else { - struct mddev *mddev = rdev->mddev; err = 0; if (mddev_is_clustered(mddev)) err = md_cluster_ops->remove_disk(mddev, rdev); @@ -3002,16 +3001,18 @@ state_store(struct md_rdev *rdev, const char *buf, size_t len) set_bit(MD_SB_CHANGE_DEVS, &mddev->sb_flags); md_wakeup_thread(mddev->thread); } - md_new_event(mddev); + md_new_event(); } } } else if (cmd_match(buf, "writemostly")) { set_bit(WriteMostly, &rdev->flags); mddev_create_serial_pool(rdev->mddev, rdev, false); + need_update_sb = true; err = 0; } else if (cmd_match(buf, "-writemostly")) { mddev_destroy_serial_pool(rdev->mddev, rdev, false); clear_bit(WriteMostly, &rdev->flags); + need_update_sb = true; err = 0; } else if (cmd_match(buf, "blocked")) { set_bit(Blocked, &rdev->flags); @@ -3037,9 +3038,11 @@ state_store(struct md_rdev *rdev, const char *buf, size_t len) err = 0; } else if (cmd_match(buf, "failfast")) { set_bit(FailFast, &rdev->flags); + need_update_sb = true; err = 0; } else if (cmd_match(buf, "-failfast")) { clear_bit(FailFast, &rdev->flags); + need_update_sb = true; err = 0; } else if (cmd_match(buf, "-insync") && rdev->raid_disk >= 0 && !test_bit(Journal, &rdev->flags)) { @@ -3118,6 +3121,8 @@ state_store(struct md_rdev *rdev, const char *buf, size_t len) clear_bit(ExternalBbl, &rdev->flags); err = 0; } + if (need_update_sb) + md_update_sb(mddev, 1); if (!err) sysfs_notify_dirent_safe(rdev->sysfs_state); return err ? err : len; @@ -3382,7 +3387,7 @@ rdev_size_store(struct md_rdev *rdev, const char *buf, size_t len) if (!sectors) return -EBUSY; } else if (!sectors) - sectors = (i_size_read(rdev->bdev->bd_inode) >> 9) - + sectors = bdev_nr_sectors(rdev->bdev) - rdev->data_offset; if (!my_mddev->pers->resize) /* Cannot change size for RAID0 or Linear etc */ @@ -3709,7 +3714,7 @@ static struct md_rdev *md_import_device(dev_t newdev, int super_format, int supe kobject_init(&rdev->kobj, &rdev_ktype); - size = i_size_read(rdev->bdev->bd_inode) >> BLOCK_SIZE_BITS; + size = bdev_nr_bytes(rdev->bdev) >> BLOCK_SIZE_BITS; if (!size) { pr_warn("md: %s has zero or unknown size, marking faulty!\n", bdevname(rdev->bdev,b)); @@ -4099,7 +4104,7 @@ level_store(struct mddev *mddev, const char *buf, size_t len) if (!mddev->thread) md_update_sb(mddev, 1); sysfs_notify_dirent_safe(mddev->sysfs_level); - md_new_event(mddev); + md_new_event(); rv = len; out_unlock: mddev_unlock(mddev); @@ -4620,7 +4625,7 @@ new_dev_store(struct mddev *mddev, const char *buf, size_t len) export_rdev(rdev); mddev_unlock(mddev); if (!err) - md_new_event(mddev); + md_new_event(); return err ? err : len; } @@ -5490,6 +5495,10 @@ static struct attribute *md_default_attrs[] = { NULL, }; +static const struct attribute_group md_default_group = { + .attrs = md_default_attrs, +}; + static struct attribute *md_redundancy_attrs[] = { &md_scan_mode.attr, &md_last_scan_mode.attr, @@ -5512,6 +5521,12 @@ static const struct attribute_group md_redundancy_group = { .attrs = md_redundancy_attrs, }; +static const struct attribute_group *md_attr_groups[] = { + &md_default_group, + &md_bitmap_group, + NULL, +}; + static ssize_t md_attr_show(struct kobject *kobj, struct attribute *attr, char *page) { @@ -5587,7 +5602,7 @@ static const struct sysfs_ops md_sysfs_ops = { static struct kobj_type md_ktype = { .release = md_free, .sysfs_ops = &md_sysfs_ops, - .default_attrs = md_default_attrs, + .default_groups = md_attr_groups, }; int mdp_major = 0; @@ -5596,7 +5611,6 @@ static void mddev_delayed_delete(struct work_struct *ws) { struct mddev *mddev = container_of(ws, struct mddev, del_work); - sysfs_remove_group(&mddev->kobj, &md_bitmap_group); kobject_del(&mddev->kobj); kobject_put(&mddev->kobj); } @@ -5663,7 +5677,7 @@ static int md_alloc(dev_t dev, char *name) strcmp(mddev2->gendisk->disk_name, name) == 0) { spin_unlock(&all_mddevs_lock); error = -EEXIST; - goto abort; + goto out_unlock_disks_mutex; } spin_unlock(&all_mddevs_lock); } @@ -5676,7 +5690,7 @@ static int md_alloc(dev_t dev, char *name) error = -ENOMEM; disk = blk_alloc_disk(NUMA_NO_NODE); if (!disk) - goto abort; + goto out_unlock_disks_mutex; disk->major = MAJOR(mddev->unit); disk->first_minor = unit << shift; @@ -5700,27 +5714,25 @@ static int md_alloc(dev_t dev, char *name) disk->flags |= GENHD_FL_EXT_DEVT; disk->events |= DISK_EVENT_MEDIA_CHANGE; mddev->gendisk = disk; - add_disk(disk); + error = add_disk(disk); + if (error) + goto out_cleanup_disk; error = kobject_add(&mddev->kobj, &disk_to_dev(disk)->kobj, "%s", "md"); - if (error) { - /* This isn't possible, but as kobject_init_and_add is marked - * __must_check, we must do something with the result - */ - pr_debug("md: cannot register %s/md - name in use\n", - disk->disk_name); - error = 0; - } - if (mddev->kobj.sd && - sysfs_create_group(&mddev->kobj, &md_bitmap_group)) - pr_debug("pointless warning\n"); - abort: + if (error) + goto out_del_gendisk; + + kobject_uevent(&mddev->kobj, KOBJ_ADD); + mddev->sysfs_state = sysfs_get_dirent_safe(mddev->kobj.sd, "array_state"); + mddev->sysfs_level = sysfs_get_dirent_safe(mddev->kobj.sd, "level"); + goto out_unlock_disks_mutex; + +out_del_gendisk: + del_gendisk(disk); +out_cleanup_disk: + blk_cleanup_disk(disk); +out_unlock_disks_mutex: mutex_unlock(&disks_mutex); - if (!error && mddev->kobj.sd) { - kobject_uevent(&mddev->kobj, KOBJ_ADD); - mddev->sysfs_state = sysfs_get_dirent_safe(mddev->kobj.sd, "array_state"); - mddev->sysfs_level = sysfs_get_dirent_safe(mddev->kobj.sd, "level"); - } mddev_put(mddev); return error; } @@ -6034,7 +6046,7 @@ int md_run(struct mddev *mddev) if (mddev->sb_flags) md_update_sb(mddev, 0); - md_new_event(mddev); + md_new_event(); return 0; bitmap_abort: @@ -6424,7 +6436,7 @@ static int do_md_stop(struct mddev *mddev, int mode, if (mddev->hold_active == UNTIL_STOP) mddev->hold_active = 0; } - md_new_event(mddev); + md_new_event(); sysfs_notify_dirent_safe(mddev->sysfs_state); return 0; } @@ -6880,7 +6892,7 @@ int md_add_new_disk(struct mddev *mddev, struct mdu_disk_info_s *info) if (!mddev->persistent) { pr_debug("md: nonpersistent superblock ...\n"); - rdev->sb_start = i_size_read(rdev->bdev->bd_inode) / 512; + rdev->sb_start = bdev_nr_sectors(rdev->bdev); } else rdev->sb_start = calc_dev_sboffset(rdev); rdev->sectors = rdev->sb_start; @@ -6928,7 +6940,7 @@ kick_rdev: md_wakeup_thread(mddev->thread); else md_update_sb(mddev, 1); - md_new_event(mddev); + md_new_event(); return 0; busy: @@ -6967,7 +6979,7 @@ static int hot_add_disk(struct mddev *mddev, dev_t dev) if (mddev->persistent) rdev->sb_start = calc_dev_sboffset(rdev); else - rdev->sb_start = i_size_read(rdev->bdev->bd_inode) / 512; + rdev->sb_start = bdev_nr_sectors(rdev->bdev); rdev->sectors = rdev->sb_start; @@ -7001,7 +7013,7 @@ static int hot_add_disk(struct mddev *mddev, dev_t dev) */ set_bit(MD_RECOVERY_NEEDED, &mddev->recovery); md_wakeup_thread(mddev->thread); - md_new_event(mddev); + md_new_event(); return 0; abort_export: @@ -7975,7 +7987,7 @@ void md_error(struct mddev *mddev, struct md_rdev *rdev) md_wakeup_thread(mddev->thread); if (mddev->event_work.func) queue_work(md_misc_wq, &mddev->event_work); - md_new_event(mddev); + md_new_event(); } EXPORT_SYMBOL(md_error); @@ -8859,7 +8871,7 @@ void md_do_sync(struct md_thread *thread) mddev->curr_resync = 3; /* no longer delayed */ mddev->curr_resync_completed = j; sysfs_notify_dirent_safe(mddev->sysfs_completed); - md_new_event(mddev); + md_new_event(); update_time = jiffies; blk_start_plug(&plug); @@ -8930,7 +8942,7 @@ void md_do_sync(struct md_thread *thread) /* this is the earliest that rebuild will be * visible in /proc/mdstat */ - md_new_event(mddev); + md_new_event(); if (last_check + window > io_sectors || j == max_sectors) continue; @@ -9154,7 +9166,7 @@ static int remove_and_add_spares(struct mddev *mddev, sysfs_link_rdev(mddev, rdev); if (!test_bit(Journal, &rdev->flags)) spares++; - md_new_event(mddev); + md_new_event(); set_bit(MD_SB_CHANGE_DEVS, &mddev->sb_flags); } } @@ -9188,7 +9200,7 @@ static void md_start_sync(struct work_struct *ws) } else md_wakeup_thread(mddev->sync_thread); sysfs_notify_dirent_safe(mddev->sysfs_action); - md_new_event(mddev); + md_new_event(); } /* @@ -9447,7 +9459,7 @@ void md_reap_sync_thread(struct mddev *mddev) /* flag recovery needed just to double check */ set_bit(MD_RECOVERY_NEEDED, &mddev->recovery); sysfs_notify_dirent_safe(mddev->sysfs_action); - md_new_event(mddev); + md_new_event(); if (mddev->event_work.func) queue_work(md_misc_wq, &mddev->event_work); } diff --git a/drivers/md/md.h b/drivers/md/md.h index 4c96c36bd01a..53ea7a6961de 100644 --- a/drivers/md/md.h +++ b/drivers/md/md.h @@ -731,7 +731,7 @@ extern int sync_page_io(struct md_rdev *rdev, sector_t sector, int size, struct page *page, int op, int op_flags, bool metadata_op); extern void md_do_sync(struct md_thread *thread); -extern void md_new_event(struct mddev *mddev); +extern void md_new_event(void); extern void md_allow_write(struct mddev *mddev); extern void md_wait_for_blocked_rdev(struct md_rdev *rdev, struct mddev *mddev); extern void md_set_array_sectors(struct mddev *mddev, sector_t array_sectors); diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c index 19598bd38939..7dc8026cf6ee 100644 --- a/drivers/md/raid1.c +++ b/drivers/md/raid1.c @@ -1496,7 +1496,7 @@ static void raid1_write_request(struct mddev *mddev, struct bio *bio, if (!r1_bio->bios[i]) continue; - if (first_clone) { + if (first_clone && test_bit(WriteMostly, &rdev->flags)) { /* do behind I/O ? * Not if there are too many, or cannot * allocate memory, or a reader on WriteMostly @@ -1529,13 +1529,12 @@ static void raid1_write_request(struct mddev *mddev, struct bio *bio, r1_bio->bios[i] = mbio; - mbio->bi_iter.bi_sector = (r1_bio->sector + - conf->mirrors[i].rdev->data_offset); - bio_set_dev(mbio, conf->mirrors[i].rdev->bdev); + mbio->bi_iter.bi_sector = (r1_bio->sector + rdev->data_offset); + bio_set_dev(mbio, rdev->bdev); mbio->bi_end_io = raid1_end_write_request; mbio->bi_opf = bio_op(bio) | (bio->bi_opf & (REQ_SYNC | REQ_FUA)); - if (test_bit(FailFast, &conf->mirrors[i].rdev->flags) && - !test_bit(WriteMostly, &conf->mirrors[i].rdev->flags) && + if (test_bit(FailFast, &rdev->flags) && + !test_bit(WriteMostly, &rdev->flags) && conf->raid_disks - mddev->degraded > 1) mbio->bi_opf |= MD_FAILFAST; mbio->bi_private = r1_bio; @@ -1546,7 +1545,7 @@ static void raid1_write_request(struct mddev *mddev, struct bio *bio, trace_block_bio_remap(mbio, disk_devt(mddev->gendisk), r1_bio->sector); /* flush_pending_writes() needs access to the rdev so...*/ - mbio->bi_bdev = (void *)conf->mirrors[i].rdev; + mbio->bi_bdev = (void *)rdev; cb = blk_check_plugged(raid1_unplug, mddev, sizeof(*plug)); if (cb) diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c index aa2636582841..dde98f65bd04 100644 --- a/drivers/md/raid10.c +++ b/drivers/md/raid10.c @@ -4647,7 +4647,7 @@ out: } conf->reshape_checkpoint = jiffies; md_wakeup_thread(mddev->sync_thread); - md_new_event(mddev); + md_new_event(); return 0; abort: diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index 02ed53b20654..9c1a5877cf9f 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -7732,10 +7732,7 @@ static int raid5_run(struct mddev *mddev) * discard data disk but write parity disk */ stripe = stripe * PAGE_SIZE; - /* Round up to power of 2, as discard handling - * currently assumes that */ - while ((stripe-1) & stripe) - stripe = (stripe | (stripe-1)) + 1; + stripe = roundup_pow_of_two(stripe); mddev->queue->limits.discard_alignment = stripe; mddev->queue->limits.discard_granularity = stripe; @@ -8282,7 +8279,7 @@ static int raid5_start_reshape(struct mddev *mddev) } conf->reshape_checkpoint = jiffies; md_wakeup_thread(mddev->sync_thread); - md_new_event(mddev); + md_new_event(); return 0; } diff --git a/drivers/mtd/mtd_blkdevs.c b/drivers/mtd/mtd_blkdevs.c index b8ae1ec14e17..4eaba6f4ec68 100644 --- a/drivers/mtd/mtd_blkdevs.c +++ b/drivers/mtd/mtd_blkdevs.c @@ -384,7 +384,9 @@ int add_mtd_blktrans_dev(struct mtd_blktrans_dev *new) if (new->readonly) set_disk_ro(gd, 1); - device_add_disk(&new->mtd->dev, gd, NULL); + ret = device_add_disk(&new->mtd->dev, gd, NULL); + if (ret) + goto out_cleanup_disk; if (new->disk_attributes) { ret = sysfs_create_group(&disk_to_dev(gd)->kobj, @@ -393,6 +395,8 @@ int add_mtd_blktrans_dev(struct mtd_blktrans_dev *new) } return 0; +out_cleanup_disk: + blk_cleanup_disk(new->disk); out_free_tag_set: blk_mq_free_tag_set(new->tag_set); out_kfree_tag_set: diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index eb284f45fc44..838b5e2058be 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -203,7 +203,7 @@ int nvme_reset_ctrl_sync(struct nvme_ctrl *ctrl) static void nvme_do_delete_ctrl(struct nvme_ctrl *ctrl) { dev_info(ctrl->device, - "Removing ctrl: NQN \"%s\"\n", ctrl->opts->subsysnqn); + "Removing ctrl: NQN \"%s\"\n", nvmf_ctrl_subsysnqn(ctrl)); flush_work(&ctrl->reset_work); nvme_stop_ctrl(ctrl); @@ -815,6 +815,7 @@ static void nvme_assign_write_stream(struct nvme_ctrl *ctrl, static inline void nvme_setup_flush(struct nvme_ns *ns, struct nvme_command *cmnd) { + memset(cmnd, 0, sizeof(*cmnd)); cmnd->common.opcode = nvme_cmd_flush; cmnd->common.nsid = cpu_to_le32(ns->head->ns_id); } @@ -866,6 +867,7 @@ static blk_status_t nvme_setup_discard(struct nvme_ns *ns, struct request *req, return BLK_STS_IOERR; } + memset(cmnd, 0, sizeof(*cmnd)); cmnd->dsm.opcode = nvme_cmd_dsm; cmnd->dsm.nsid = cpu_to_le32(ns->head->ns_id); cmnd->dsm.nr = cpu_to_le32(segments - 1); @@ -882,6 +884,8 @@ static blk_status_t nvme_setup_discard(struct nvme_ns *ns, struct request *req, static inline blk_status_t nvme_setup_write_zeroes(struct nvme_ns *ns, struct request *req, struct nvme_command *cmnd) { + memset(cmnd, 0, sizeof(*cmnd)); + if (ns->ctrl->quirks & NVME_QUIRK_DEALLOCATE_ZEROES) return nvme_setup_discard(ns, req, cmnd); @@ -915,9 +919,15 @@ static inline blk_status_t nvme_setup_rw(struct nvme_ns *ns, dsmgmt |= NVME_RW_DSM_FREQ_PREFETCH; cmnd->rw.opcode = op; + cmnd->rw.flags = 0; cmnd->rw.nsid = cpu_to_le32(ns->head->ns_id); + cmnd->rw.rsvd2 = 0; + cmnd->rw.metadata = 0; cmnd->rw.slba = cpu_to_le64(nvme_sect_to_lba(ns, blk_rq_pos(req))); cmnd->rw.length = cpu_to_le16((blk_rq_bytes(req) >> ns->lba_shift) - 1); + cmnd->rw.reftag = 0; + cmnd->rw.apptag = 0; + cmnd->rw.appmask = 0; if (req_op(req) == REQ_OP_WRITE && ctrl->nr_streams) nvme_assign_write_stream(ctrl, req, &control, &dsmgmt); @@ -974,10 +984,8 @@ blk_status_t nvme_setup_cmd(struct nvme_ns *ns, struct request *req) struct nvme_ctrl *ctrl = nvme_req(req)->ctrl; blk_status_t ret = BLK_STS_OK; - if (!(req->rq_flags & RQF_DONTPREP)) { + if (!(req->rq_flags & RQF_DONTPREP)) nvme_clear_nvme_request(req); - memset(cmd, 0, sizeof(*cmd)); - } switch (req_op(req)) { case REQ_OP_DRV_IN: @@ -2593,6 +2601,24 @@ static ssize_t nvme_subsys_show_nqn(struct device *dev, } static SUBSYS_ATTR_RO(subsysnqn, S_IRUGO, nvme_subsys_show_nqn); +static ssize_t nvme_subsys_show_type(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + struct nvme_subsystem *subsys = + container_of(dev, struct nvme_subsystem, dev); + + switch (subsys->subtype) { + case NVME_NQN_DISC: + return sysfs_emit(buf, "discovery\n"); + case NVME_NQN_NVME: + return sysfs_emit(buf, "nvm\n"); + default: + return sysfs_emit(buf, "reserved\n"); + } +} +static SUBSYS_ATTR_RO(subsystype, S_IRUGO, nvme_subsys_show_type); + #define nvme_subsys_show_str_function(field) \ static ssize_t subsys_##field##_show(struct device *dev, \ struct device_attribute *attr, char *buf) \ @@ -2613,6 +2639,7 @@ static struct attribute *nvme_subsys_attrs[] = { &subsys_attr_serial.attr, &subsys_attr_firmware_rev.attr, &subsys_attr_subsysnqn.attr, + &subsys_attr_subsystype.attr, #ifdef CONFIG_NVME_MULTIPATH &subsys_attr_iopolicy.attr, #endif @@ -2683,6 +2710,21 @@ static int nvme_init_subsystem(struct nvme_ctrl *ctrl, struct nvme_id_ctrl *id) memcpy(subsys->firmware_rev, id->fr, sizeof(subsys->firmware_rev)); subsys->vendor_id = le16_to_cpu(id->vid); subsys->cmic = id->cmic; + + /* Versions prior to 1.4 don't necessarily report a valid type */ + if (id->cntrltype == NVME_CTRL_DISC || + !strcmp(subsys->subnqn, NVME_DISC_SUBSYS_NAME)) + subsys->subtype = NVME_NQN_DISC; + else + subsys->subtype = NVME_NQN_NVME; + + if (nvme_discovery_ctrl(ctrl) && subsys->subtype != NVME_NQN_DISC) { + dev_err(ctrl->device, + "Subsystem %s is not a discovery controller", + subsys->subnqn); + kfree(subsys); + return -EINVAL; + } subsys->awupf = le16_to_cpu(id->awupf); #ifdef CONFIG_NVME_MULTIPATH subsys->iopolicy = NVME_IOPOLICY_NUMA; diff --git a/drivers/nvme/host/fabrics.c b/drivers/nvme/host/fabrics.c index 668c6bb7a567..c5a2b71c5268 100644 --- a/drivers/nvme/host/fabrics.c +++ b/drivers/nvme/host/fabrics.c @@ -548,6 +548,7 @@ static const match_table_t opt_tokens = { { NVMF_OPT_NR_POLL_QUEUES, "nr_poll_queues=%d" }, { NVMF_OPT_TOS, "tos=%d" }, { NVMF_OPT_FAIL_FAST_TMO, "fast_io_fail_tmo=%d" }, + { NVMF_OPT_DISCOVERY, "discovery" }, { NVMF_OPT_ERR, NULL } }; @@ -823,6 +824,9 @@ static int nvmf_parse_options(struct nvmf_ctrl_options *opts, } opts->tos = token; break; + case NVMF_OPT_DISCOVERY: + opts->discovery_nqn = true; + break; default: pr_warn("unknown parameter or missing value '%s' in ctrl creation request\n", p); @@ -949,7 +953,7 @@ EXPORT_SYMBOL_GPL(nvmf_free_options); #define NVMF_ALLOWED_OPTS (NVMF_OPT_QUEUE_SIZE | NVMF_OPT_NR_IO_QUEUES | \ NVMF_OPT_KATO | NVMF_OPT_HOSTNQN | \ NVMF_OPT_HOST_ID | NVMF_OPT_DUP_CONNECT |\ - NVMF_OPT_DISABLE_SQFLOW |\ + NVMF_OPT_DISABLE_SQFLOW | NVMF_OPT_DISCOVERY |\ NVMF_OPT_FAIL_FAST_TMO) static struct nvme_ctrl * diff --git a/drivers/nvme/host/fabrics.h b/drivers/nvme/host/fabrics.h index a146cb903869..c3203ff1c654 100644 --- a/drivers/nvme/host/fabrics.h +++ b/drivers/nvme/host/fabrics.h @@ -67,6 +67,7 @@ enum { NVMF_OPT_TOS = 1 << 19, NVMF_OPT_FAIL_FAST_TMO = 1 << 20, NVMF_OPT_HOST_IFACE = 1 << 21, + NVMF_OPT_DISCOVERY = 1 << 22, }; /** @@ -178,6 +179,13 @@ nvmf_ctlr_matches_baseopts(struct nvme_ctrl *ctrl, return true; } +static inline char *nvmf_ctrl_subsysnqn(struct nvme_ctrl *ctrl) +{ + if (!ctrl->subsys) + return ctrl->opts->subsysnqn; + return ctrl->subsys->subnqn; +} + int nvmf_reg_read32(struct nvme_ctrl *ctrl, u32 off, u32 *val); int nvmf_reg_read64(struct nvme_ctrl *ctrl, u32 off, u64 *val); int nvmf_reg_write32(struct nvme_ctrl *ctrl, u32 off, u32 val); diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c index 580a216da619..71b3108c22f0 100644 --- a/drivers/nvme/host/fc.c +++ b/drivers/nvme/host/fc.c @@ -16,6 +16,7 @@ #include #include "fc.h" #include +#include /* *************************** Data Structures/Defines ****************** */ @@ -2841,6 +2842,28 @@ nvme_fc_complete_rq(struct request *rq) nvme_fc_ctrl_put(ctrl); } +static int nvme_fc_map_queues(struct blk_mq_tag_set *set) +{ + struct nvme_fc_ctrl *ctrl = set->driver_data; + int i; + + for (i = 0; i < set->nr_maps; i++) { + struct blk_mq_queue_map *map = &set->map[i]; + + if (!map->nr_queues) { + WARN_ON(i == HCTX_TYPE_DEFAULT); + continue; + } + + /* Call LLDD map queue functionality if defined */ + if (ctrl->lport->ops->map_queues) + ctrl->lport->ops->map_queues(&ctrl->lport->localport, + map); + else + blk_mq_map_queues(map); + } + return 0; +} static const struct blk_mq_ops nvme_fc_mq_ops = { .queue_rq = nvme_fc_queue_rq, @@ -2849,6 +2872,7 @@ static const struct blk_mq_ops nvme_fc_mq_ops = { .exit_request = nvme_fc_exit_request, .init_hctx = nvme_fc_init_hctx, .timeout = nvme_fc_timeout, + .map_queues = nvme_fc_map_queues, }; static int @@ -3572,7 +3596,7 @@ nvme_fc_init_ctrl(struct device *dev, struct nvmf_ctrl_options *opts, dev_info(ctrl->ctrl.device, "NVME-FC{%d}: new ctrl: NQN \"%s\"\n", - ctrl->cnum, ctrl->ctrl.opts->subsysnqn); + ctrl->cnum, nvmf_ctrl_subsysnqn(&ctrl->ctrl)); return &ctrl->ctrl; diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c index 11440c86881e..7f2071f2460c 100644 --- a/drivers/nvme/host/multipath.c +++ b/drivers/nvme/host/multipath.c @@ -105,8 +105,11 @@ void nvme_kick_requeue_lists(struct nvme_ctrl *ctrl) down_read(&ctrl->namespaces_rwsem); list_for_each_entry(ns, &ctrl->namespaces, list) { - if (ns->head->disk) - kblockd_schedule_work(&ns->head->requeue_work); + if (!ns->head->disk) + continue; + kblockd_schedule_work(&ns->head->requeue_work); + if (ctrl->state == NVME_CTRL_LIVE) + disk_uevent(ns->head->disk, KOBJ_CHANGE); } up_read(&ctrl->namespaces_rwsem); } @@ -143,13 +146,12 @@ void nvme_mpath_clear_ctrl_paths(struct nvme_ctrl *ctrl) { struct nvme_ns *ns; - mutex_lock(&ctrl->scan_lock); down_read(&ctrl->namespaces_rwsem); - list_for_each_entry(ns, &ctrl->namespaces, list) - if (nvme_mpath_clear_current_path(ns)) - kblockd_schedule_work(&ns->head->requeue_work); + list_for_each_entry(ns, &ctrl->namespaces, list) { + nvme_mpath_clear_current_path(ns); + kblockd_schedule_work(&ns->head->requeue_work); + } up_read(&ctrl->namespaces_rwsem); - mutex_unlock(&ctrl->scan_lock); } void nvme_mpath_revalidate_paths(struct nvme_ns *ns) @@ -506,13 +508,23 @@ int nvme_mpath_alloc_disk(struct nvme_ctrl *ctrl, struct nvme_ns_head *head) static void nvme_mpath_set_live(struct nvme_ns *ns) { struct nvme_ns_head *head = ns->head; + int rc; if (!head->disk) return; + /* + * test_and_set_bit() is used because it is protecting against two nvme + * paths simultaneously calling device_add_disk() on the same namespace + * head. + */ if (!test_and_set_bit(NVME_NSHEAD_DISK_LIVE, &head->flags)) { - device_add_disk(&head->subsys->dev, head->disk, - nvme_ns_id_attr_groups); + rc = device_add_disk(&head->subsys->dev, head->disk, + nvme_ns_id_attr_groups); + if (rc) { + clear_bit(NVME_NSHEAD_DISK_LIVE, &ns->flags); + return; + } nvme_add_ns_head_cdev(head); } @@ -550,7 +562,7 @@ static int nvme_parse_ana_log(struct nvme_ctrl *ctrl, void *data, return -EINVAL; nr_nsids = le32_to_cpu(desc->nnsids); - nsid_buf_size = nr_nsids * sizeof(__le32); + nsid_buf_size = flex_array_size(desc, nsids, nr_nsids); if (WARN_ON_ONCE(desc->grpid == 0)) return -EINVAL; diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h index 3652439a7458..b334af8aa264 100644 --- a/drivers/nvme/host/nvme.h +++ b/drivers/nvme/host/nvme.h @@ -373,6 +373,7 @@ struct nvme_subsystem { char model[40]; char firmware_rev[8]; u8 cmic; + enum nvme_subsys_type subtype; u16 vendor_id; u16 awupf; /* 0's based awupf value. */ struct ida ns_ida; diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index fde36c137900..ca2ee806d74b 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -245,8 +245,15 @@ static int nvme_dbbuf_dma_alloc(struct nvme_dev *dev) { unsigned int mem_size = nvme_dbbuf_size(dev); - if (dev->dbbuf_dbs) + if (dev->dbbuf_dbs) { + /* + * Clear the dbbuf memory so the driver doesn't observe stale + * values from the previous instantiation. + */ + memset(dev->dbbuf_dbs, 0, mem_size); + memset(dev->dbbuf_eis, 0, mem_size); return 0; + } dev->dbbuf_dbs = dma_alloc_coherent(dev->dev, mem_size, &dev->dbbuf_dbs_dma_addr, diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c index 7d9ac544db37..850f84d204d0 100644 --- a/drivers/nvme/host/rdma.c +++ b/drivers/nvme/host/rdma.c @@ -1096,11 +1096,13 @@ static int nvme_rdma_setup_ctrl(struct nvme_rdma_ctrl *ctrl, bool new) return ret; if (ctrl->ctrl.icdoff) { + ret = -EOPNOTSUPP; dev_err(ctrl->ctrl.device, "icdoff is not supported!\n"); goto destroy_admin; } if (!(ctrl->ctrl.sgls & (1 << 2))) { + ret = -EOPNOTSUPP; dev_err(ctrl->ctrl.device, "Mandatory keyed sgls are not supported!\n"); goto destroy_admin; @@ -1112,6 +1114,13 @@ static int nvme_rdma_setup_ctrl(struct nvme_rdma_ctrl *ctrl, bool new) ctrl->ctrl.opts->queue_size, ctrl->ctrl.sqsize + 1); } + if (ctrl->ctrl.sqsize + 1 > NVME_RDMA_MAX_QUEUE_SIZE) { + dev_warn(ctrl->ctrl.device, + "ctrl sqsize %u > max queue size %u, clamping down\n", + ctrl->ctrl.sqsize + 1, NVME_RDMA_MAX_QUEUE_SIZE); + ctrl->ctrl.sqsize = NVME_RDMA_MAX_QUEUE_SIZE - 1; + } + if (ctrl->ctrl.sqsize + 1 > ctrl->ctrl.maxcmd) { dev_warn(ctrl->ctrl.device, "sqsize %u > ctrl maxcmd %u, clamping down\n", @@ -2386,7 +2395,7 @@ static struct nvme_ctrl *nvme_rdma_create_ctrl(struct device *dev, goto out_uninit_ctrl; dev_info(ctrl->ctrl.device, "new ctrl: NQN \"%s\", addr %pISpcs\n", - ctrl->ctrl.opts->subsysnqn, &ctrl->addr); + nvmf_ctrl_subsysnqn(&ctrl->ctrl), &ctrl->addr); mutex_lock(&nvme_rdma_ctrl_mutex); list_add_tail(&ctrl->list, &nvme_rdma_ctrl_list); diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c index 19dcb9279a24..33bc83d8d992 100644 --- a/drivers/nvme/host/tcp.c +++ b/drivers/nvme/host/tcp.c @@ -2585,7 +2585,7 @@ static struct nvme_ctrl *nvme_tcp_create_ctrl(struct device *dev, goto out_uninit_ctrl; dev_info(ctrl->ctrl.device, "new ctrl: NQN \"%s\", addr %pISp\n", - ctrl->ctrl.opts->subsysnqn, &ctrl->addr); + nvmf_ctrl_subsysnqn(&ctrl->ctrl), &ctrl->addr); mutex_lock(&nvme_tcp_ctrl_mutex); list_add_tail(&ctrl->list, &nvme_tcp_ctrl_list); diff --git a/drivers/nvme/host/zns.c b/drivers/nvme/host/zns.c index d95010481fce..bfc259e0d7b8 100644 --- a/drivers/nvme/host/zns.c +++ b/drivers/nvme/host/zns.c @@ -233,6 +233,8 @@ out_free: blk_status_t nvme_setup_zone_mgmt_send(struct nvme_ns *ns, struct request *req, struct nvme_command *c, enum nvme_zone_mgmt_action action) { + memset(c, 0, sizeof(*c)); + c->zms.opcode = nvme_cmd_zone_mgmt_send; c->zms.nsid = cpu_to_le32(ns->head->ns_id); c->zms.slba = cpu_to_le64(nvme_sect_to_lba(ns, blk_rq_pos(req))); diff --git a/drivers/nvme/target/admin-cmd.c b/drivers/nvme/target/admin-cmd.c index aa6d84d8848e..6fb24746de06 100644 --- a/drivers/nvme/target/admin-cmd.c +++ b/drivers/nvme/target/admin-cmd.c @@ -264,7 +264,7 @@ static u32 nvmet_format_ana_group(struct nvmet_req *req, u32 grpid, desc->chgcnt = cpu_to_le64(nvmet_ana_chgcnt); desc->state = req->port->ana_state[grpid]; memset(desc->rsvd17, 0, sizeof(desc->rsvd17)); - return sizeof(struct nvme_ana_group_desc) + count * sizeof(__le32); + return struct_size(desc, nsids, count); } static void nvmet_execute_get_log_page_ana(struct nvmet_req *req) @@ -278,8 +278,8 @@ static void nvmet_execute_get_log_page_ana(struct nvmet_req *req) u16 status; status = NVME_SC_INTERNAL; - desc = kmalloc(sizeof(struct nvme_ana_group_desc) + - NVMET_MAX_NAMESPACES * sizeof(__le32), GFP_KERNEL); + desc = kmalloc(struct_size(desc, nsids, NVMET_MAX_NAMESPACES), + GFP_KERNEL); if (!desc) goto out; @@ -374,13 +374,19 @@ static void nvmet_execute_identify_ctrl(struct nvmet_req *req) id->rab = 6; + if (nvmet_is_disc_subsys(ctrl->subsys)) + id->cntrltype = NVME_CTRL_DISC; + else + id->cntrltype = NVME_CTRL_IO; + /* * XXX: figure out how we can assign a IEEE OUI, but until then * the safest is to leave it as zeroes. */ /* we support multiple ports, multiples hosts and ANA: */ - id->cmic = (1 << 0) | (1 << 1) | (1 << 3); + id->cmic = NVME_CTRL_CMIC_MULTI_PORT | NVME_CTRL_CMIC_MULTI_CTRL | + NVME_CTRL_CMIC_ANA; /* Limit MDTS according to transport capability */ if (ctrl->ops->get_mdts) @@ -536,7 +542,7 @@ static void nvmet_execute_identify_ns(struct nvmet_req *req) * Our namespace might always be shared. Not just with other * controllers, but also with any other user of the block device. */ - id->nmic = (1 << 0); + id->nmic = NVME_NS_NMIC_SHARED; id->anagrpid = cpu_to_le32(req->ns->anagrpid); memcpy(&id->nguid, &req->ns->nguid, sizeof(id->nguid)); @@ -1008,7 +1014,7 @@ u16 nvmet_parse_admin_cmd(struct nvmet_req *req) if (nvme_is_fabrics(cmd)) return nvmet_parse_fabrics_cmd(req); - if (nvmet_req_subsys(req)->type == NVME_NQN_DISC) + if (nvmet_is_disc_subsys(nvmet_req_subsys(req))) return nvmet_parse_discovery_cmd(req); ret = nvmet_check_ctrl_status(req); diff --git a/drivers/nvme/target/configfs.c b/drivers/nvme/target/configfs.c index be5d82421e3a..091a0ca16361 100644 --- a/drivers/nvme/target/configfs.c +++ b/drivers/nvme/target/configfs.c @@ -1233,6 +1233,44 @@ static ssize_t nvmet_subsys_attr_model_store(struct config_item *item, } CONFIGFS_ATTR(nvmet_subsys_, attr_model); +static ssize_t nvmet_subsys_attr_discovery_nqn_show(struct config_item *item, + char *page) +{ + return snprintf(page, PAGE_SIZE, "%s\n", + nvmet_disc_subsys->subsysnqn); +} + +static ssize_t nvmet_subsys_attr_discovery_nqn_store(struct config_item *item, + const char *page, size_t count) +{ + struct nvmet_subsys *subsys = to_subsys(item); + char *subsysnqn; + int len; + + len = strcspn(page, "\n"); + if (!len) + return -EINVAL; + + subsysnqn = kmemdup_nul(page, len, GFP_KERNEL); + if (!subsysnqn) + return -ENOMEM; + + /* + * The discovery NQN must be different from subsystem NQN. + */ + if (!strcmp(subsysnqn, subsys->subsysnqn)) { + kfree(subsysnqn); + return -EBUSY; + } + down_write(&nvmet_config_sem); + kfree(nvmet_disc_subsys->subsysnqn); + nvmet_disc_subsys->subsysnqn = subsysnqn; + up_write(&nvmet_config_sem); + + return count; +} +CONFIGFS_ATTR(nvmet_subsys_, attr_discovery_nqn); + #ifdef CONFIG_BLK_DEV_INTEGRITY static ssize_t nvmet_subsys_attr_pi_enable_show(struct config_item *item, char *page) @@ -1262,6 +1300,7 @@ static struct configfs_attribute *nvmet_subsys_attrs[] = { &nvmet_subsys_attr_attr_cntlid_min, &nvmet_subsys_attr_attr_cntlid_max, &nvmet_subsys_attr_attr_model, + &nvmet_subsys_attr_attr_discovery_nqn, #ifdef CONFIG_BLK_DEV_INTEGRITY &nvmet_subsys_attr_attr_pi_enable, #endif @@ -1553,6 +1592,8 @@ static void nvmet_port_release(struct config_item *item) { struct nvmet_port *port = to_nvmet_port(item); + /* Let inflight controllers teardown complete */ + flush_scheduled_work(); list_del(&port->global_entry); kfree(port->ana_state); diff --git a/drivers/nvme/target/core.c b/drivers/nvme/target/core.c index b8425fa34300..5119c687de68 100644 --- a/drivers/nvme/target/core.c +++ b/drivers/nvme/target/core.c @@ -1140,7 +1140,7 @@ static void nvmet_start_ctrl(struct nvmet_ctrl *ctrl) * should verify iosqes,iocqes are zeroed, however that * would break backwards compatibility, so don't enforce it. */ - if (ctrl->subsys->type != NVME_NQN_DISC && + if (!nvmet_is_disc_subsys(ctrl->subsys) && (nvmet_cc_iosqes(ctrl->cc) != NVME_NVM_IOSQES || nvmet_cc_iocqes(ctrl->cc) != NVME_NVM_IOCQES)) { ctrl->csts = NVME_CSTS_CFS; @@ -1205,7 +1205,10 @@ static void nvmet_init_cap(struct nvmet_ctrl *ctrl) /* CC.EN timeout in 500msec units: */ ctrl->cap |= (15ULL << 24); /* maximum queue entries supported: */ - ctrl->cap |= NVMET_QUEUE_SIZE - 1; + if (ctrl->ops->get_max_queue_size) + ctrl->cap |= ctrl->ops->get_max_queue_size(ctrl) - 1; + else + ctrl->cap |= NVMET_QUEUE_SIZE - 1; if (nvmet_is_passthru_subsys(ctrl->subsys)) nvmet_passthrough_override_cap(ctrl); @@ -1278,7 +1281,7 @@ bool nvmet_host_allowed(struct nvmet_subsys *subsys, const char *hostnqn) if (subsys->allow_any_host) return true; - if (subsys->type == NVME_NQN_DISC) /* allow all access to disc subsys */ + if (nvmet_is_disc_subsys(subsys)) /* allow all access to disc subsys */ return true; list_for_each_entry(p, &subsys->hosts, entry) { @@ -1367,6 +1370,7 @@ u16 nvmet_alloc_ctrl(const char *subsysnqn, const char *hostnqn, mutex_init(&ctrl->lock); ctrl->port = req->port; + ctrl->ops = req->ops; INIT_WORK(&ctrl->async_event_work, nvmet_async_event_work); INIT_LIST_HEAD(&ctrl->async_events); @@ -1405,13 +1409,11 @@ u16 nvmet_alloc_ctrl(const char *subsysnqn, const char *hostnqn, } ctrl->cntlid = ret; - ctrl->ops = req->ops; - /* * Discovery controllers may use some arbitrary high value * in order to cleanup stale discovery sessions */ - if ((ctrl->subsys->type == NVME_NQN_DISC) && !kato) + if (nvmet_is_disc_subsys(ctrl->subsys) && !kato) kato = NVMET_DISC_KATO_MS; /* keep-alive timeout in seconds */ @@ -1491,7 +1493,8 @@ static struct nvmet_subsys *nvmet_find_get_subsys(struct nvmet_port *port, if (!port) return NULL; - if (!strcmp(NVME_DISC_SUBSYS_NAME, subsysnqn)) { + if (!strcmp(NVME_DISC_SUBSYS_NAME, subsysnqn) || + !strcmp(nvmet_disc_subsys->subsysnqn, subsysnqn)) { if (!kref_get_unless_zero(&nvmet_disc_subsys->ref)) return NULL; return nvmet_disc_subsys; @@ -1538,6 +1541,7 @@ struct nvmet_subsys *nvmet_subsys_alloc(const char *subsysnqn, subsys->max_qid = NVMET_NR_QUEUES; break; case NVME_NQN_DISC: + case NVME_NQN_CURR: subsys->max_qid = 0; break; default: diff --git a/drivers/nvme/target/discovery.c b/drivers/nvme/target/discovery.c index 7aa62bc6ae84..c2162eef8ce1 100644 --- a/drivers/nvme/target/discovery.c +++ b/drivers/nvme/target/discovery.c @@ -146,7 +146,7 @@ static size_t discovery_log_entries(struct nvmet_req *req) struct nvmet_ctrl *ctrl = req->sq->ctrl; struct nvmet_subsys_link *p; struct nvmet_port *r; - size_t entries = 0; + size_t entries = 1; list_for_each_entry(p, &req->port->subsystems, entry) { if (!nvmet_host_allowed(p->subsys, ctrl->hostnqn)) @@ -171,6 +171,7 @@ static void nvmet_execute_disc_get_log_page(struct nvmet_req *req) u32 numrec = 0; u16 status = 0; void *buffer; + char traddr[NVMF_TRADDR_SIZE]; if (!nvmet_check_transfer_len(req, data_len)) return; @@ -203,15 +204,19 @@ static void nvmet_execute_disc_get_log_page(struct nvmet_req *req) status = NVME_SC_INTERNAL; goto out; } - hdr = buffer; - list_for_each_entry(p, &req->port->subsystems, entry) { - char traddr[NVMF_TRADDR_SIZE]; + nvmet_set_disc_traddr(req, req->port, traddr); + + nvmet_format_discovery_entry(hdr, req->port, + nvmet_disc_subsys->subsysnqn, + traddr, NVME_NQN_CURR, numrec); + numrec++; + + list_for_each_entry(p, &req->port->subsystems, entry) { if (!nvmet_host_allowed(p->subsys, ctrl->hostnqn)) continue; - nvmet_set_disc_traddr(req, req->port, traddr); nvmet_format_discovery_entry(hdr, req->port, p->subsys->subsysnqn, traddr, NVME_NQN_NVME, numrec); @@ -268,6 +273,8 @@ static void nvmet_execute_disc_identify(struct nvmet_req *req) memcpy_and_pad(id->fr, sizeof(id->fr), UTS_RELEASE, strlen(UTS_RELEASE), ' '); + id->cntrltype = NVME_CTRL_DISC; + /* no limit on data transfer sizes for now */ id->mdts = 0; id->cntlid = cpu_to_le16(ctrl->cntlid); @@ -387,7 +394,7 @@ u16 nvmet_parse_discovery_cmd(struct nvmet_req *req) int __init nvmet_init_discovery(void) { nvmet_disc_subsys = - nvmet_subsys_alloc(NVME_DISC_SUBSYS_NAME, NVME_NQN_DISC); + nvmet_subsys_alloc(NVME_DISC_SUBSYS_NAME, NVME_NQN_CURR); return PTR_ERR_OR_ZERO(nvmet_disc_subsys); } diff --git a/drivers/nvme/target/fabrics-cmd.c b/drivers/nvme/target/fabrics-cmd.c index 7d0454cee920..70fb587e9413 100644 --- a/drivers/nvme/target/fabrics-cmd.c +++ b/drivers/nvme/target/fabrics-cmd.c @@ -221,7 +221,8 @@ static void nvmet_execute_admin_connect(struct nvmet_req *req) goto out; } - pr_info("creating controller %d for subsystem %s for NQN %s%s.\n", + pr_info("creating %s controller %d for subsystem %s for NQN %s%s.\n", + nvmet_is_disc_subsys(ctrl->subsys) ? "discovery" : "nvm", ctrl->cntlid, ctrl->subsys->subsysnqn, ctrl->hostnqn, ctrl->pi_support ? " T10-PI is enabled" : ""); req->cqe->result.u16 = cpu_to_le16(ctrl->cntlid); diff --git a/drivers/nvme/target/io-cmd-bdev.c b/drivers/nvme/target/io-cmd-bdev.c index 6139e1de50a6..70ca9dfc1771 100644 --- a/drivers/nvme/target/io-cmd-bdev.c +++ b/drivers/nvme/target/io-cmd-bdev.c @@ -87,7 +87,7 @@ int nvmet_bdev_ns_enable(struct nvmet_ns *ns) ns->bdev = NULL; return ret; } - ns->size = i_size_read(ns->bdev->bd_inode); + ns->size = bdev_nr_bytes(ns->bdev); ns->blksize_shift = blksize_bits(bdev_logical_block_size(ns->bdev)); ns->pi_type = 0; @@ -108,7 +108,7 @@ int nvmet_bdev_ns_enable(struct nvmet_ns *ns) void nvmet_bdev_ns_revalidate(struct nvmet_ns *ns) { - ns->size = i_size_read(ns->bdev->bd_inode); + ns->size = bdev_nr_bytes(ns->bdev); } u16 blk_to_nvme_status(struct nvmet_req *req, blk_status_t blk_sts) diff --git a/drivers/nvme/target/nvmet.h b/drivers/nvme/target/nvmet.h index 7143c7fa7464..af193423c10b 100644 --- a/drivers/nvme/target/nvmet.h +++ b/drivers/nvme/target/nvmet.h @@ -309,6 +309,7 @@ struct nvmet_fabrics_ops { u16 (*install_queue)(struct nvmet_sq *nvme_sq); void (*discovery_chg)(struct nvmet_port *port); u8 (*get_mdts)(const struct nvmet_ctrl *ctrl); + u16 (*get_max_queue_size)(const struct nvmet_ctrl *ctrl); }; #define NVMET_MAX_INLINE_BIOVEC 8 @@ -576,6 +577,11 @@ static inline struct nvmet_subsys *nvmet_req_subsys(struct nvmet_req *req) return req->sq->ctrl->subsys; } +static inline bool nvmet_is_disc_subsys(struct nvmet_subsys *subsys) +{ + return subsys->type != NVME_NQN_NVME; +} + #ifdef CONFIG_NVME_TARGET_PASSTHRU void nvmet_passthru_subsys_free(struct nvmet_subsys *subsys); int nvmet_passthru_ctrl_enable(struct nvmet_subsys *subsys); diff --git a/drivers/nvme/target/rdma.c b/drivers/nvme/target/rdma.c index 38d1f292ecc2..1deb4043e242 100644 --- a/drivers/nvme/target/rdma.c +++ b/drivers/nvme/target/rdma.c @@ -1819,12 +1819,36 @@ restart: mutex_unlock(&nvmet_rdma_queue_mutex); } +static void nvmet_rdma_destroy_port_queues(struct nvmet_rdma_port *port) +{ + struct nvmet_rdma_queue *queue, *tmp; + struct nvmet_port *nport = port->nport; + + mutex_lock(&nvmet_rdma_queue_mutex); + list_for_each_entry_safe(queue, tmp, &nvmet_rdma_queue_list, + queue_list) { + if (queue->port != nport) + continue; + + list_del_init(&queue->queue_list); + __nvmet_rdma_queue_disconnect(queue); + } + mutex_unlock(&nvmet_rdma_queue_mutex); +} + static void nvmet_rdma_disable_port(struct nvmet_rdma_port *port) { struct rdma_cm_id *cm_id = xchg(&port->cm_id, NULL); if (cm_id) rdma_destroy_id(cm_id); + + /* + * Destroy the remaining queues, which are not belong to any + * controller yet. Do it here after the RDMA-CM was destroyed + * guarantees that no new queue will be created. + */ + nvmet_rdma_destroy_port_queues(port); } static int nvmet_rdma_enable_port(struct nvmet_rdma_port *port) @@ -1976,6 +2000,11 @@ static u8 nvmet_rdma_get_mdts(const struct nvmet_ctrl *ctrl) return NVMET_RDMA_MAX_MDTS; } +static u16 nvmet_rdma_get_max_queue_size(const struct nvmet_ctrl *ctrl) +{ + return NVME_RDMA_MAX_QUEUE_SIZE; +} + static const struct nvmet_fabrics_ops nvmet_rdma_ops = { .owner = THIS_MODULE, .type = NVMF_TRTYPE_RDMA, @@ -1987,6 +2016,7 @@ static const struct nvmet_fabrics_ops nvmet_rdma_ops = { .delete_ctrl = nvmet_rdma_delete_ctrl, .disc_traddr = nvmet_rdma_disc_port_addr, .get_mdts = nvmet_rdma_get_mdts, + .get_max_queue_size = nvmet_rdma_get_max_queue_size, }; static void nvmet_rdma_remove_one(struct ib_device *ib_device, void *client_data) diff --git a/drivers/nvme/target/tcp.c b/drivers/nvme/target/tcp.c index 46c3b3be7e03..84c387e4bf43 100644 --- a/drivers/nvme/target/tcp.c +++ b/drivers/nvme/target/tcp.c @@ -1740,6 +1740,17 @@ err_port: return ret; } +static void nvmet_tcp_destroy_port_queues(struct nvmet_tcp_port *port) +{ + struct nvmet_tcp_queue *queue; + + mutex_lock(&nvmet_tcp_queue_mutex); + list_for_each_entry(queue, &nvmet_tcp_queue_list, queue_list) + if (queue->port == port) + kernel_sock_shutdown(queue->sock, SHUT_RDWR); + mutex_unlock(&nvmet_tcp_queue_mutex); +} + static void nvmet_tcp_remove_port(struct nvmet_port *nport) { struct nvmet_tcp_port *port = nport->priv; @@ -1749,6 +1760,11 @@ static void nvmet_tcp_remove_port(struct nvmet_port *nport) port->sock->sk->sk_user_data = NULL; write_unlock_bh(&port->sock->sk->sk_callback_lock); cancel_work_sync(&port->accept_work); + /* + * Destroy the remaining queues, which are not belong to any + * controller yet. + */ + nvmet_tcp_destroy_port_queues(port); sock_release(port->sock); kfree(port); diff --git a/drivers/s390/block/dasd.c b/drivers/s390/block/dasd.c index e34c6cc61983..8e87a31e329d 100644 --- a/drivers/s390/block/dasd.c +++ b/drivers/s390/block/dasd.c @@ -2077,12 +2077,15 @@ static void __dasd_device_check_path_events(struct dasd_device *device) if (device->stopped & ~(DASD_STOPPED_DC_WAIT)) return; + + dasd_path_clear_all_verify(device); + dasd_path_clear_all_fcsec(device); + rc = device->discipline->pe_handler(device, tbvpm, fcsecpm); if (rc) { + dasd_path_add_tbvpm(device, tbvpm); + dasd_path_add_fcsecpm(device, fcsecpm); dasd_device_set_timer(device, 50); - } else { - dasd_path_clear_all_verify(device); - dasd_path_clear_all_fcsec(device); } }; diff --git a/drivers/s390/block/dasd_3990_erp.c b/drivers/s390/block/dasd_3990_erp.c index 4691a3c35d72..299001ad9a32 100644 --- a/drivers/s390/block/dasd_3990_erp.c +++ b/drivers/s390/block/dasd_3990_erp.c @@ -201,7 +201,7 @@ dasd_3990_erp_DCTL(struct dasd_ccw_req * erp, char modifier) struct ccw1 *ccw; struct dasd_ccw_req *dctl_cqr; - dctl_cqr = dasd_alloc_erp_request((char *) &erp->magic, 1, + dctl_cqr = dasd_alloc_erp_request(erp->magic, 1, sizeof(struct DCTL_data), device); if (IS_ERR(dctl_cqr)) { @@ -1652,7 +1652,7 @@ dasd_3990_erp_action_1B_32(struct dasd_ccw_req * default_erp, char *sense) } /* Build new ERP request including DE/LO */ - erp = dasd_alloc_erp_request((char *) &cqr->magic, + erp = dasd_alloc_erp_request(cqr->magic, 2 + 1,/* DE/LO + TIC */ sizeof(struct DE_eckd_data) + sizeof(struct LO_eckd_data), device); @@ -2388,7 +2388,7 @@ static struct dasd_ccw_req *dasd_3990_erp_add_erp(struct dasd_ccw_req *cqr) } /* allocate additional request block */ - erp = dasd_alloc_erp_request((char *) &cqr->magic, + erp = dasd_alloc_erp_request(cqr->magic, cplength, datasize, device); if (IS_ERR(erp)) { if (cqr->retries <= 0) { diff --git a/drivers/s390/block/dasd_eckd.c b/drivers/s390/block/dasd_eckd.c index 460e0f1cca53..8410a25a65c1 100644 --- a/drivers/s390/block/dasd_eckd.c +++ b/drivers/s390/block/dasd_eckd.c @@ -560,8 +560,8 @@ static int prefix_LRE(struct ccw1 *ccw, struct PFX_eckd_data *pfxdata, return -EINVAL; } pfxdata->format = format; - pfxdata->base_address = basepriv->ned->unit_addr; - pfxdata->base_lss = basepriv->ned->ID; + pfxdata->base_address = basepriv->conf.ned->unit_addr; + pfxdata->base_lss = basepriv->conf.ned->ID; pfxdata->validity.define_extent = 1; /* private uid is kept up to date, conf_data may be outdated */ @@ -736,32 +736,30 @@ dasd_eckd_cdl_reclen(int recid) return LABEL_SIZE; } /* create unique id from private structure. */ -static void create_uid(struct dasd_eckd_private *private) +static void create_uid(struct dasd_conf *conf, struct dasd_uid *uid) { int count; - struct dasd_uid *uid; - uid = &private->uid; memset(uid, 0, sizeof(struct dasd_uid)); - memcpy(uid->vendor, private->ned->HDA_manufacturer, + memcpy(uid->vendor, conf->ned->HDA_manufacturer, sizeof(uid->vendor) - 1); EBCASC(uid->vendor, sizeof(uid->vendor) - 1); - memcpy(uid->serial, &private->ned->serial, + memcpy(uid->serial, &conf->ned->serial, sizeof(uid->serial) - 1); EBCASC(uid->serial, sizeof(uid->serial) - 1); - uid->ssid = private->gneq->subsystemID; - uid->real_unit_addr = private->ned->unit_addr; - if (private->sneq) { - uid->type = private->sneq->sua_flags; + uid->ssid = conf->gneq->subsystemID; + uid->real_unit_addr = conf->ned->unit_addr; + if (conf->sneq) { + uid->type = conf->sneq->sua_flags; if (uid->type == UA_BASE_PAV_ALIAS) - uid->base_unit_addr = private->sneq->base_unit_addr; + uid->base_unit_addr = conf->sneq->base_unit_addr; } else { uid->type = UA_BASE_DEVICE; } - if (private->vdsneq) { + if (conf->vdsneq) { for (count = 0; count < 16; count++) { sprintf(uid->vduit+2*count, "%02x", - private->vdsneq->uit[count]); + conf->vdsneq->uit[count]); } } } @@ -776,10 +774,10 @@ static int dasd_eckd_generate_uid(struct dasd_device *device) if (!private) return -ENODEV; - if (!private->ned || !private->gneq) + if (!private->conf.ned || !private->conf.gneq) return -ENODEV; spin_lock_irqsave(get_ccwdev_lock(device->cdev), flags); - create_uid(private); + create_uid(&private->conf, &private->uid); spin_unlock_irqrestore(get_ccwdev_lock(device->cdev), flags); return 0; } @@ -803,14 +801,15 @@ static int dasd_eckd_get_uid(struct dasd_device *device, struct dasd_uid *uid) * return 0 for match */ static int dasd_eckd_compare_path_uid(struct dasd_device *device, - struct dasd_eckd_private *private) + struct dasd_conf *path_conf) { struct dasd_uid device_uid; + struct dasd_uid path_uid; - create_uid(private); + create_uid(path_conf, &path_uid); dasd_eckd_get_uid(device, &device_uid); - return memcmp(&device_uid, &private->uid, sizeof(struct dasd_uid)); + return memcmp(&device_uid, &path_uid, sizeof(struct dasd_uid)); } static void dasd_eckd_fill_rcd_cqr(struct dasd_device *device, @@ -946,34 +945,34 @@ out_error: return ret; } -static int dasd_eckd_identify_conf_parts(struct dasd_eckd_private *private) +static int dasd_eckd_identify_conf_parts(struct dasd_conf *conf) { struct dasd_sneq *sneq; int i, count; - private->ned = NULL; - private->sneq = NULL; - private->vdsneq = NULL; - private->gneq = NULL; - count = private->conf_len / sizeof(struct dasd_sneq); - sneq = (struct dasd_sneq *)private->conf_data; + conf->ned = NULL; + conf->sneq = NULL; + conf->vdsneq = NULL; + conf->gneq = NULL; + count = conf->len / sizeof(struct dasd_sneq); + sneq = (struct dasd_sneq *)conf->data; for (i = 0; i < count; ++i) { if (sneq->flags.identifier == 1 && sneq->format == 1) - private->sneq = sneq; + conf->sneq = sneq; else if (sneq->flags.identifier == 1 && sneq->format == 4) - private->vdsneq = (struct vd_sneq *)sneq; + conf->vdsneq = (struct vd_sneq *)sneq; else if (sneq->flags.identifier == 2) - private->gneq = (struct dasd_gneq *)sneq; + conf->gneq = (struct dasd_gneq *)sneq; else if (sneq->flags.identifier == 3 && sneq->res1 == 1) - private->ned = (struct dasd_ned *)sneq; + conf->ned = (struct dasd_ned *)sneq; sneq++; } - if (!private->ned || !private->gneq) { - private->ned = NULL; - private->sneq = NULL; - private->vdsneq = NULL; - private->gneq = NULL; + if (!conf->ned || !conf->gneq) { + conf->ned = NULL; + conf->sneq = NULL; + conf->vdsneq = NULL; + conf->gneq = NULL; return -EINVAL; } return 0; @@ -1016,9 +1015,9 @@ static void dasd_eckd_store_conf_data(struct dasd_device *device, * with the new one if this points to the same data */ cdp = device->path[chp].conf_data; - if (private->conf_data == cdp) { - private->conf_data = (void *)conf_data; - dasd_eckd_identify_conf_parts(private); + if (private->conf.data == cdp) { + private->conf.data = (void *)conf_data; + dasd_eckd_identify_conf_parts(&private->conf); } ccw_device_get_schid(device->cdev, &sch_id); device->path[chp].conf_data = conf_data; @@ -1036,8 +1035,8 @@ static void dasd_eckd_clear_conf_data(struct dasd_device *device) struct dasd_eckd_private *private = device->private; int i; - private->conf_data = NULL; - private->conf_len = 0; + private->conf.data = NULL; + private->conf.len = 0; for (i = 0; i < 8; i++) { kfree(device->path[i].conf_data); device->path[i].conf_data = NULL; @@ -1071,15 +1070,55 @@ static void dasd_eckd_read_fc_security(struct dasd_device *device) } } +static void dasd_eckd_get_uid_string(struct dasd_conf *conf, + char *print_uid) +{ + struct dasd_uid uid; + + create_uid(conf, &uid); + if (strlen(uid.vduit) > 0) + snprintf(print_uid, sizeof(*print_uid), + "%s.%s.%04x.%02x.%s", + uid.vendor, uid.serial, uid.ssid, + uid.real_unit_addr, uid.vduit); + else + snprintf(print_uid, sizeof(*print_uid), + "%s.%s.%04x.%02x", + uid.vendor, uid.serial, uid.ssid, + uid.real_unit_addr); +} + +static int dasd_eckd_check_cabling(struct dasd_device *device, + void *conf_data, __u8 lpm) +{ + struct dasd_eckd_private *private = device->private; + char print_path_uid[60], print_device_uid[60]; + struct dasd_conf path_conf; + + path_conf.data = conf_data; + path_conf.len = DASD_ECKD_RCD_DATA_SIZE; + if (dasd_eckd_identify_conf_parts(&path_conf)) + return 1; + + if (dasd_eckd_compare_path_uid(device, &path_conf)) { + dasd_eckd_get_uid_string(&path_conf, print_path_uid); + dasd_eckd_get_uid_string(&private->conf, print_device_uid); + dev_err(&device->cdev->dev, + "Not all channel paths lead to the same device, path %02X leads to device %s instead of %s\n", + lpm, print_path_uid, print_device_uid); + return 1; + } + + return 0; +} + static int dasd_eckd_read_conf(struct dasd_device *device) { void *conf_data; int conf_len, conf_data_saved; int rc, path_err, pos; __u8 lpm, opm; - struct dasd_eckd_private *private, path_private; - struct dasd_uid *uid; - char print_path_uid[60], print_device_uid[60]; + struct dasd_eckd_private *private; private = device->private; opm = ccw_device_get_path_mask(device->cdev); @@ -1109,11 +1148,11 @@ static int dasd_eckd_read_conf(struct dasd_device *device) if (!conf_data_saved) { /* initially clear previously stored conf_data */ dasd_eckd_clear_conf_data(device); - private->conf_data = conf_data; - private->conf_len = conf_len; - if (dasd_eckd_identify_conf_parts(private)) { - private->conf_data = NULL; - private->conf_len = 0; + private->conf.data = conf_data; + private->conf.len = conf_len; + if (dasd_eckd_identify_conf_parts(&private->conf)) { + private->conf.data = NULL; + private->conf.len = 0; kfree(conf_data); continue; } @@ -1123,59 +1162,11 @@ static int dasd_eckd_read_conf(struct dasd_device *device) */ dasd_eckd_generate_uid(device); conf_data_saved++; - } else { - path_private.conf_data = conf_data; - path_private.conf_len = DASD_ECKD_RCD_DATA_SIZE; - if (dasd_eckd_identify_conf_parts( - &path_private)) { - path_private.conf_data = NULL; - path_private.conf_len = 0; - kfree(conf_data); - continue; - } - if (dasd_eckd_compare_path_uid( - device, &path_private)) { - uid = &path_private.uid; - if (strlen(uid->vduit) > 0) - snprintf(print_path_uid, - sizeof(print_path_uid), - "%s.%s.%04x.%02x.%s", - uid->vendor, uid->serial, - uid->ssid, uid->real_unit_addr, - uid->vduit); - else - snprintf(print_path_uid, - sizeof(print_path_uid), - "%s.%s.%04x.%02x", - uid->vendor, uid->serial, - uid->ssid, - uid->real_unit_addr); - uid = &private->uid; - if (strlen(uid->vduit) > 0) - snprintf(print_device_uid, - sizeof(print_device_uid), - "%s.%s.%04x.%02x.%s", - uid->vendor, uid->serial, - uid->ssid, uid->real_unit_addr, - uid->vduit); - else - snprintf(print_device_uid, - sizeof(print_device_uid), - "%s.%s.%04x.%02x", - uid->vendor, uid->serial, - uid->ssid, - uid->real_unit_addr); - dev_err(&device->cdev->dev, - "Not all channel paths lead to " - "the same device, path %02X leads to " - "device %s instead of %s\n", lpm, - print_path_uid, print_device_uid); - path_err = -EINVAL; - dasd_path_add_cablepm(device, lpm); - continue; - } - path_private.conf_data = NULL; - path_private.conf_len = 0; + } else if (dasd_eckd_check_cabling(device, conf_data, lpm)) { + dasd_path_add_cablepm(device, lpm); + path_err = -EINVAL; + kfree(conf_data); + continue; } pos = pathmask_to_pos(lpm); @@ -1197,8 +1188,6 @@ static int dasd_eckd_read_conf(struct dasd_device *device) } } - dasd_eckd_read_fc_security(device); - return path_err; } @@ -1213,7 +1202,7 @@ static u32 get_fcx_max_data(struct dasd_device *device) return 0; /* is transport mode supported? */ fcx_in_css = css_general_characteristics.fcx; - fcx_in_gneq = private->gneq->reserved2[7] & 0x04; + fcx_in_gneq = private->conf.gneq->reserved2[7] & 0x04; fcx_in_features = private->features.feature[40] & 0x80; tpm = fcx_in_css && fcx_in_gneq && fcx_in_features; @@ -1282,9 +1271,9 @@ static int rebuild_device_uid(struct dasd_device *device, "returned error %d", rc); break; } - memcpy(private->conf_data, data->rcd_buffer, + memcpy(private->conf.data, data->rcd_buffer, DASD_ECKD_RCD_DATA_SIZE); - if (dasd_eckd_identify_conf_parts(private)) { + if (dasd_eckd_identify_conf_parts(&private->conf)) { rc = -ENODEV; } else /* first valid path is enough */ break; @@ -1299,11 +1288,10 @@ static int rebuild_device_uid(struct dasd_device *device, static void dasd_eckd_path_available_action(struct dasd_device *device, struct pe_handler_work_data *data) { - struct dasd_eckd_private path_private; - struct dasd_uid *uid; __u8 path_rcd_buf[DASD_ECKD_RCD_DATA_SIZE]; __u8 lpm, opm, npm, ppm, epm, hpfpm, cablepm; struct dasd_conf_data *conf_data; + struct dasd_conf path_conf; unsigned long flags; char print_uid[60]; int rc, pos; @@ -1367,11 +1355,11 @@ static void dasd_eckd_path_available_action(struct dasd_device *device, */ memcpy(&path_rcd_buf, data->rcd_buffer, DASD_ECKD_RCD_DATA_SIZE); - path_private.conf_data = (void *) &path_rcd_buf; - path_private.conf_len = DASD_ECKD_RCD_DATA_SIZE; - if (dasd_eckd_identify_conf_parts(&path_private)) { - path_private.conf_data = NULL; - path_private.conf_len = 0; + path_conf.data = (void *)&path_rcd_buf; + path_conf.len = DASD_ECKD_RCD_DATA_SIZE; + if (dasd_eckd_identify_conf_parts(&path_conf)) { + path_conf.data = NULL; + path_conf.len = 0; continue; } @@ -1382,7 +1370,7 @@ static void dasd_eckd_path_available_action(struct dasd_device *device, * the first working path UID will be used as device UID */ if (dasd_path_get_opm(device) && - dasd_eckd_compare_path_uid(device, &path_private)) { + dasd_eckd_compare_path_uid(device, &path_conf)) { /* * the comparison was not successful * rebuild the device UID with at least one @@ -1396,20 +1384,8 @@ static void dasd_eckd_path_available_action(struct dasd_device *device, */ if (rebuild_device_uid(device, data) || dasd_eckd_compare_path_uid( - device, &path_private)) { - uid = &path_private.uid; - if (strlen(uid->vduit) > 0) - snprintf(print_uid, sizeof(print_uid), - "%s.%s.%04x.%02x.%s", - uid->vendor, uid->serial, - uid->ssid, uid->real_unit_addr, - uid->vduit); - else - snprintf(print_uid, sizeof(print_uid), - "%s.%s.%04x.%02x", - uid->vendor, uid->serial, - uid->ssid, - uid->real_unit_addr); + device, &path_conf)) { + dasd_eckd_get_uid_string(&path_conf, print_uid); dev_err(&device->cdev->dev, "The newly added channel path %02X " "will not be used because it leads " @@ -1427,6 +1403,14 @@ static void dasd_eckd_path_available_action(struct dasd_device *device, if (conf_data) { memcpy(conf_data, data->rcd_buffer, DASD_ECKD_RCD_DATA_SIZE); + } else { + /* + * path is operational but path config data could not + * be stored due to low mem condition + * add it to the error path mask and schedule a path + * verification later that this could be added again + */ + epm |= lpm; } pos = pathmask_to_pos(lpm); dasd_eckd_store_conf_data(device, conf_data, pos); @@ -1447,7 +1431,10 @@ static void dasd_eckd_path_available_action(struct dasd_device *device, } dasd_path_add_nppm(device, npm); dasd_path_add_ppm(device, ppm); - dasd_path_add_tbvpm(device, epm); + if (epm) { + dasd_path_add_tbvpm(device, epm); + dasd_device_set_timer(device, 50); + } dasd_path_add_cablepm(device, cablepm); dasd_path_add_nohpfpm(device, hpfpm); spin_unlock_irqrestore(get_ccwdev_lock(device->cdev), flags); @@ -1625,8 +1612,8 @@ static int dasd_eckd_read_vol_info(struct dasd_device *device) prssdp = cqr->data; prssdp->order = PSF_ORDER_PRSSD; prssdp->suborder = PSF_SUBORDER_VSQ; /* Volume Storage Query */ - prssdp->lss = private->ned->ID; - prssdp->volume = private->ned->unit_addr; + prssdp->lss = private->conf.ned->ID; + prssdp->volume = private->conf.ned->unit_addr; ccw = cqr->cpaddr; ccw->cmd_code = DASD_ECKD_CCW_PSF; @@ -2085,11 +2072,11 @@ dasd_eckd_check_characteristics(struct dasd_device *device) device->path_thrhld = DASD_ECKD_PATH_THRHLD; device->path_interval = DASD_ECKD_PATH_INTERVAL; - if (private->gneq) { + if (private->conf.gneq) { value = 1; - for (i = 0; i < private->gneq->timeout.value; i++) + for (i = 0; i < private->conf.gneq->timeout.value; i++) value = 10 * value; - value = value * private->gneq->timeout.number; + value = value * private->conf.gneq->timeout.number; /* do not accept useless values */ if (value != 0 && value <= DASD_EXPIRES_MAX) device->default_expires = value; @@ -2121,6 +2108,7 @@ dasd_eckd_check_characteristics(struct dasd_device *device) if (rc) goto out_err3; + dasd_eckd_read_fc_security(device); dasd_path_create_kobjects(device); /* Read Feature Codes */ @@ -2195,10 +2183,10 @@ static void dasd_eckd_uncheck_device(struct dasd_device *device) return; dasd_alias_disconnect_device_from_lcu(device); - private->ned = NULL; - private->sneq = NULL; - private->vdsneq = NULL; - private->gneq = NULL; + private->conf.ned = NULL; + private->conf.sneq = NULL; + private->conf.vdsneq = NULL; + private->conf.gneq = NULL; dasd_eckd_clear_conf_data(device); dasd_path_remove_kobjects(device); } @@ -3750,8 +3738,8 @@ dasd_eckd_dso_ras(struct dasd_device *device, struct dasd_block *block, * subset. */ ras_data->op_flags.guarantee_init = !!(features->feature[56] & 0x01); - ras_data->lss = private->ned->ID; - ras_data->dev_addr = private->ned->unit_addr; + ras_data->lss = private->conf.ned->ID; + ras_data->dev_addr = private->conf.ned->unit_addr; ras_data->nr_exts = nr_exts; if (by_extent) { @@ -4293,8 +4281,8 @@ static int prepare_itcw(struct itcw *itcw, memset(&pfxdata, 0, sizeof(pfxdata)); pfxdata.format = 1; /* PFX with LRE */ - pfxdata.base_address = basepriv->ned->unit_addr; - pfxdata.base_lss = basepriv->ned->ID; + pfxdata.base_address = basepriv->conf.ned->unit_addr; + pfxdata.base_lss = basepriv->conf.ned->ID; pfxdata.validity.define_extent = 1; /* private uid is kept up to date, conf_data may be outdated */ @@ -4963,9 +4951,9 @@ dasd_eckd_fill_info(struct dasd_device * device, info->characteristics_size = sizeof(private->rdc_data); memcpy(info->characteristics, &private->rdc_data, sizeof(private->rdc_data)); - info->confdata_size = min((unsigned long)private->conf_len, - sizeof(info->configuration_data)); - memcpy(info->configuration_data, private->conf_data, + info->confdata_size = min_t(unsigned long, private->conf.len, + sizeof(info->configuration_data)); + memcpy(info->configuration_data, private->conf.data, info->confdata_size); return 0; } @@ -5808,6 +5796,8 @@ static int dasd_eckd_reload_device(struct dasd_device *device) if (rc) goto out_err; + dasd_eckd_read_fc_security(device); + rc = dasd_eckd_generate_uid(device); if (rc) goto out_err; @@ -5820,15 +5810,7 @@ static int dasd_eckd_reload_device(struct dasd_device *device) dasd_eckd_get_uid(device, &uid); if (old_base != uid.base_unit_addr) { - if (strlen(uid.vduit) > 0) - snprintf(print_uid, sizeof(print_uid), - "%s.%s.%04x.%02x.%s", uid.vendor, uid.serial, - uid.ssid, uid.base_unit_addr, uid.vduit); - else - snprintf(print_uid, sizeof(print_uid), - "%s.%s.%04x.%02x", uid.vendor, uid.serial, - uid.ssid, uid.base_unit_addr); - + dasd_eckd_get_uid_string(&private->conf, print_uid); dev_info(&device->cdev->dev, "An Alias device was reassigned to a new base device " "with UID: %s\n", print_uid); @@ -5966,8 +5948,8 @@ static int dasd_eckd_query_host_access(struct dasd_device *device, prssdp->order = PSF_ORDER_PRSSD; prssdp->suborder = PSF_SUBORDER_QHA; /* query host access */ /* LSS and Volume that will be queried */ - prssdp->lss = private->ned->ID; - prssdp->volume = private->ned->unit_addr; + prssdp->lss = private->conf.ned->ID; + prssdp->volume = private->conf.ned->unit_addr; /* all other bytes of prssdp must be zero */ ccw = cqr->cpaddr; diff --git a/drivers/s390/block/dasd_eckd.h b/drivers/s390/block/dasd_eckd.h index 65e4630ad2ae..a91b265441cc 100644 --- a/drivers/s390/block/dasd_eckd.h +++ b/drivers/s390/block/dasd_eckd.h @@ -658,16 +658,19 @@ struct dasd_conf_data { struct dasd_gneq gneq; } __packed; -struct dasd_eckd_private { - struct dasd_eckd_characteristics rdc_data; - u8 *conf_data; - int conf_len; - +struct dasd_conf { + u8 *data; + int len; /* pointers to specific parts in the conf_data */ struct dasd_ned *ned; struct dasd_sneq *sneq; struct vd_sneq *vdsneq; struct dasd_gneq *gneq; +}; + +struct dasd_eckd_private { + struct dasd_eckd_characteristics rdc_data; + struct dasd_conf conf; struct eckd_count count_area[5]; int init_cqr_status; diff --git a/drivers/s390/block/dasd_erp.c b/drivers/s390/block/dasd_erp.c index ba4fa372d02d..c07e6e713518 100644 --- a/drivers/s390/block/dasd_erp.c +++ b/drivers/s390/block/dasd_erp.c @@ -24,7 +24,7 @@ #include "dasd_int.h" struct dasd_ccw_req * -dasd_alloc_erp_request(char *magic, int cplength, int datasize, +dasd_alloc_erp_request(unsigned int magic, int cplength, int datasize, struct dasd_device * device) { unsigned long flags; @@ -33,8 +33,8 @@ dasd_alloc_erp_request(char *magic, int cplength, int datasize, int size; /* Sanity checks */ - BUG_ON( magic == NULL || datasize > PAGE_SIZE || - (cplength*sizeof(struct ccw1)) > PAGE_SIZE); + BUG_ON(datasize > PAGE_SIZE || + (cplength*sizeof(struct ccw1)) > PAGE_SIZE); size = (sizeof(struct dasd_ccw_req) + 7L) & -8L; if (cplength > 0) @@ -62,7 +62,7 @@ dasd_alloc_erp_request(char *magic, int cplength, int datasize, cqr->data = data; memset(cqr->data, 0, datasize); } - strncpy((char *) &cqr->magic, magic, 4); + cqr->magic = magic; ASCEBC((char *) &cqr->magic, 4); set_bit(DASD_CQR_FLAGS_USE_ERP, &cqr->flags); dasd_get_device(device); diff --git a/drivers/s390/block/dasd_int.h b/drivers/s390/block/dasd_int.h index 155428bfed8a..8b458010f88a 100644 --- a/drivers/s390/block/dasd_int.h +++ b/drivers/s390/block/dasd_int.h @@ -887,7 +887,7 @@ void dasd_proc_exit(void); /* externals in dasd_erp.c */ struct dasd_ccw_req *dasd_default_erp_action(struct dasd_ccw_req *); struct dasd_ccw_req *dasd_default_erp_postaction(struct dasd_ccw_req *); -struct dasd_ccw_req *dasd_alloc_erp_request(char *, int, int, +struct dasd_ccw_req *dasd_alloc_erp_request(unsigned int, int, int, struct dasd_device *); void dasd_free_erp_request(struct dasd_ccw_req *, struct dasd_device *); void dasd_log_sense(struct dasd_ccw_req *, struct irb *); @@ -1305,6 +1305,15 @@ static inline void dasd_path_add_ppm(struct dasd_device *device, __u8 pm) dasd_path_preferred(device, chp); } +static inline void dasd_path_add_fcsecpm(struct dasd_device *device, __u8 pm) +{ + int chp; + + for (chp = 0; chp < 8; chp++) + if (pm & (0x80 >> chp)) + dasd_path_fcsec(device, chp); +} + /* * set functions for path masks * the existing path mask will be replaced by the given path mask diff --git a/drivers/s390/block/dasd_ioctl.c b/drivers/s390/block/dasd_ioctl.c index 468cbeb539ff..95349f95758c 100644 --- a/drivers/s390/block/dasd_ioctl.c +++ b/drivers/s390/block/dasd_ioctl.c @@ -650,8 +650,8 @@ int dasd_ioctl(struct block_device *bdev, fmode_t mode, /** * dasd_biodasdinfo() - fill out the dasd information structure - * @disk [in]: pointer to gendisk structure that references a DASD - * @info [out]: pointer to the dasd_information2_t structure + * @disk: [in] pointer to gendisk structure that references a DASD + * @info: [out] pointer to the dasd_information2_t structure * * Provide access to DASD specific information. * The gendisk structure is checked if it belongs to the DASD driver by diff --git a/drivers/scsi/qla2xxx/qla_nvme.c b/drivers/scsi/qla2xxx/qla_nvme.c index 1c5da2dbd6f9..253055cf9daf 100644 --- a/drivers/scsi/qla2xxx/qla_nvme.c +++ b/drivers/scsi/qla2xxx/qla_nvme.c @@ -8,6 +8,8 @@ #include #include #include +#include +#include static struct nvme_fc_port_template qla_nvme_fc_transport; @@ -642,6 +644,18 @@ static int qla_nvme_post_cmd(struct nvme_fc_local_port *lport, return rval; } +static void qla_nvme_map_queues(struct nvme_fc_local_port *lport, + struct blk_mq_queue_map *map) +{ + struct scsi_qla_host *vha = lport->private; + int rc; + + rc = blk_mq_pci_map_queues(map, vha->hw->pdev, vha->irq_offset); + if (rc) + ql_log(ql_log_warn, vha, 0x21de, + "pci map queue failed 0x%x", rc); +} + static void qla_nvme_localport_delete(struct nvme_fc_local_port *lport) { struct scsi_qla_host *vha = lport->private; @@ -676,6 +690,7 @@ static struct nvme_fc_port_template qla_nvme_fc_transport = { .ls_abort = qla_nvme_ls_abort, .fcp_io = qla_nvme_post_cmd, .fcp_abort = qla_nvme_fcp_abort, + .map_queues = qla_nvme_map_queues, .max_hw_queues = 8, .max_sgl_segments = 1024, .max_dif_sgl_segments = 64, diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c index 9bdee968d3b5..f75cfc97982d 100644 --- a/drivers/scsi/sd.c +++ b/drivers/scsi/sd.c @@ -3088,6 +3088,86 @@ static void sd_read_security(struct scsi_disk *sdkp, unsigned char *buffer) 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]) + 3; + 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); +} + /* * Determine the device's preferred I/O size for reads and writes * unless the reported value is unreasonably small, large, not a @@ -3203,6 +3283,7 @@ static int sd_revalidate_disk(struct gendisk *disk) sd_read_app_tag_own(sdkp, buffer); sd_read_write_same(sdkp, buffer); sd_read_security(sdkp, buffer); + sd_read_cpr(sdkp); } /* diff --git a/drivers/scsi/sd.h b/drivers/scsi/sd.h index b59136c4125b..2e5932bde43d 100644 --- a/drivers/scsi/sd.h +++ b/drivers/scsi/sd.h @@ -106,6 +106,7 @@ struct scsi_disk { u8 protection_type;/* Data Integrity Field */ u8 provisioning_mode; u8 zeroing_mode; + u8 nr_actuators; /* Number of actuators */ unsigned ATO : 1; /* state of disk ATO bit */ unsigned cache_override : 1; /* temp override of WCE,RCD */ unsigned WCE : 1; /* state of disk WCE bit */ diff --git a/drivers/target/target_core_iblock.c b/drivers/target/target_core_iblock.c index 31df20abe141..b1ef041cacd8 100644 --- a/drivers/target/target_core_iblock.c +++ b/drivers/target/target_core_iblock.c @@ -232,9 +232,9 @@ static unsigned long long iblock_emulate_read_cap_with_block_size( struct block_device *bd, struct request_queue *q) { - unsigned long long blocks_long = (div_u64(i_size_read(bd->bd_inode), - bdev_logical_block_size(bd)) - 1); u32 block_size = bdev_logical_block_size(bd); + unsigned long long blocks_long = + div_u64(bdev_nr_bytes(bd), block_size) - 1; if (block_size == dev->dev_attrib.block_size) return blocks_long; diff --git a/fs/affs/super.c b/fs/affs/super.c index c6c2a513ec92..c609005a9eaa 100644 --- a/fs/affs/super.c +++ b/fs/affs/super.c @@ -389,7 +389,7 @@ static int affs_fill_super(struct super_block *sb, void *data, int silent) * blocks, we will have to change it. */ - size = i_size_read(sb->s_bdev->bd_inode) >> 9; + size = bdev_nr_sectors(sb->s_bdev); pr_debug("initial blocksize=%d, #blocks=%d\n", 512, size); affs_set_blocksize(sb, PAGE_SIZE); diff --git a/fs/btrfs/dev-replace.c b/fs/btrfs/dev-replace.c index d029be40ea6f..fbb8b4457a72 100644 --- a/fs/btrfs/dev-replace.c +++ b/fs/btrfs/dev-replace.c @@ -283,8 +283,7 @@ static int btrfs_init_dev_replace_tgtdev(struct btrfs_fs_info *fs_info, } - if (i_size_read(bdev->bd_inode) < - btrfs_device_get_total_bytes(srcdev)) { + if (bdev_nr_bytes(bdev) < btrfs_device_get_total_bytes(srcdev)) { btrfs_err(fs_info, "target device is smaller than source device!"); ret = -EINVAL; diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 355ea88d5c5f..29e7598584c4 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -3740,7 +3740,7 @@ struct btrfs_super_block *btrfs_read_dev_one_super(struct block_device *bdev, else if (ret) return ERR_PTR(ret); - if (bytenr + BTRFS_SUPER_INFO_SIZE >= i_size_read(bdev->bd_inode)) + if (bytenr + BTRFS_SUPER_INFO_SIZE >= bdev_nr_bytes(bdev)) return ERR_PTR(-EINVAL); page = read_cache_page_gfp(mapping, bytenr >> PAGE_SHIFT, GFP_NOFS); diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index cc61813213d8..36ff713da1b1 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -1730,7 +1730,7 @@ static noinline int btrfs_ioctl_resize(struct file *file, } if (!strcmp(sizestr, "max")) - new_size = device->bdev->bd_inode->i_size; + new_size = bdev_nr_bytes(device->bdev); else { if (sizestr[0] == '-') { mod = -1; @@ -1771,7 +1771,7 @@ static noinline int btrfs_ioctl_resize(struct file *file, ret = -EINVAL; goto out_finish; } - if (new_size > device->bdev->bd_inode->i_size) { + if (new_size > bdev_nr_bytes(device->bdev)) { ret = -EFBIG; goto out_finish; } diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index 2ec3b8ac8fa3..676c7c4e6e59 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -1286,7 +1286,7 @@ static struct btrfs_super_block *btrfs_read_disk_super(struct block_device *bdev pgoff_t index; /* make sure our super fits in the device */ - if (bytenr + PAGE_SIZE >= i_size_read(bdev->bd_inode)) + if (bytenr + PAGE_SIZE >= bdev_nr_bytes(bdev)) return ERR_PTR(-EINVAL); /* make sure our super fits in the page */ @@ -2610,8 +2610,8 @@ int btrfs_init_new_device(struct btrfs_fs_info *fs_info, const char *device_path device->io_width = fs_info->sectorsize; device->io_align = fs_info->sectorsize; device->sector_size = fs_info->sectorsize; - device->total_bytes = round_down(i_size_read(bdev->bd_inode), - fs_info->sectorsize); + device->total_bytes = + round_down(bdev_nr_bytes(bdev), fs_info->sectorsize); device->disk_total_bytes = device->total_bytes; device->commit_total_bytes = device->total_bytes; set_bit(BTRFS_DEV_STATE_IN_FS_METADATA, &device->dev_state); @@ -7236,7 +7236,7 @@ static int read_one_dev(struct extent_buffer *leaf, fill_device_from_item(leaf, dev_item, device); if (device->bdev) { - u64 max_total_bytes = i_size_read(device->bdev->bd_inode); + u64 max_total_bytes = bdev_nr_bytes(device->bdev); if (device->total_bytes > max_total_bytes) { btrfs_err(fs_info, diff --git a/fs/buffer.c b/fs/buffer.c index c615387aedca..46bc589b7a03 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -878,7 +878,7 @@ link_dev_buffers(struct page *page, struct buffer_head *head) static sector_t blkdev_max_block(struct block_device *bdev, unsigned int size) { sector_t retval = ~((sector_t)0); - loff_t sz = i_size_read(bdev->bd_inode); + loff_t sz = bdev_nr_bytes(bdev); if (sz) { unsigned int sizebits = blksize_bits(size); @@ -897,7 +897,7 @@ init_page_buffers(struct page *page, struct block_device *bdev, struct buffer_head *head = page_buffers(page); struct buffer_head *bh = head; int uptodate = PageUptodate(page); - sector_t end_block = blkdev_max_block(I_BDEV(bdev->bd_inode), size); + sector_t end_block = blkdev_max_block(bdev, size); do { if (!buffer_mapped(bh)) { diff --git a/fs/cramfs/inode.c b/fs/cramfs/inode.c index 2be65269a987..666aa380011e 100644 --- a/fs/cramfs/inode.c +++ b/fs/cramfs/inode.c @@ -209,7 +209,7 @@ static void *cramfs_blkdev_read(struct super_block *sb, unsigned int offset, return read_buffers[i] + blk_offset; } - devsize = mapping->host->i_size >> PAGE_SHIFT; + devsize = bdev_nr_bytes(sb->s_bdev) >> PAGE_SHIFT; /* Ok, read in BLKS_PER_BUF pages completely first. */ for (i = 0; i < BLKS_PER_BUF; i++) { diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 88d5d274a868..29f38251013e 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -4474,7 +4474,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) goto cantfind_ext4; /* check blocks count against device size */ - blocks_count = sb->s_bdev->bd_inode->i_size >> sb->s_blocksize_bits; + blocks_count = sb_bdev_nr_blocks(sb); if (blocks_count && ext4_blocks_count(es) > blocks_count) { ext4_msg(sb, KERN_WARNING, "bad geometry: block count %llu " "exceeds size of device (%llu blocks)", diff --git a/fs/fat/inode.c b/fs/fat/inode.c index de0c9b013a85..9f3cd03668ad 100644 --- a/fs/fat/inode.c +++ b/fs/fat/inode.c @@ -1536,14 +1536,11 @@ static int fat_read_static_bpb(struct super_block *sb, struct fat_bios_param_block *bpb) { static const char *notdos1x = "This doesn't look like a DOS 1.x volume"; - + sector_t bd_sects = bdev_nr_sectors(sb->s_bdev); struct fat_floppy_defaults *fdefaults = NULL; int error = -EINVAL; - sector_t bd_sects; unsigned i; - bd_sects = i_size_read(sb->s_bdev->bd_inode) / SECTOR_SIZE; - /* 16-bit DOS 1.x reliably wrote bootstrap short-jmp code */ if (b->ignored[0] != 0xeb || b->ignored[2] != 0x90) { if (!silent) diff --git a/fs/hfs/mdb.c b/fs/hfs/mdb.c index cdf0edeeb278..5beb82652435 100644 --- a/fs/hfs/mdb.c +++ b/fs/hfs/mdb.c @@ -36,7 +36,7 @@ static int hfs_get_last_session(struct super_block *sb, /* default values */ *start = 0; - *size = i_size_read(sb->s_bdev->bd_inode) >> 9; + *size = bdev_nr_sectors(sb->s_bdev); if (HFS_SB(sb)->session >= 0) { struct cdrom_tocentry te; diff --git a/fs/hfsplus/wrapper.c b/fs/hfsplus/wrapper.c index 0350dc7821bf..51ae6f1eb4a5 100644 --- a/fs/hfsplus/wrapper.c +++ b/fs/hfsplus/wrapper.c @@ -131,7 +131,7 @@ static int hfsplus_get_last_session(struct super_block *sb, /* default values */ *start = 0; - *size = i_size_read(sb->s_bdev->bd_inode) >> 9; + *size = bdev_nr_sectors(sb->s_bdev); if (HFSPLUS_SB(sb)->session >= 0) { struct cdrom_tocentry te; diff --git a/fs/io-wq.c b/fs/io-wq.c index 422a7ed6a9bd..38b33ad9e8cf 100644 --- a/fs/io-wq.c +++ b/fs/io-wq.c @@ -140,6 +140,7 @@ static void io_wqe_dec_running(struct io_worker *worker); static bool io_acct_cancel_pending_work(struct io_wqe *wqe, struct io_wqe_acct *acct, struct io_cb_cancel_data *match); +static void create_worker_cb(struct callback_head *cb); static bool io_worker_get(struct io_worker *worker) { @@ -174,12 +175,46 @@ static void io_worker_ref_put(struct io_wq *wq) complete(&wq->worker_done); } +static void io_worker_cancel_cb(struct io_worker *worker) +{ + struct io_wqe_acct *acct = io_wqe_get_acct(worker); + struct io_wqe *wqe = worker->wqe; + struct io_wq *wq = wqe->wq; + + atomic_dec(&acct->nr_running); + raw_spin_lock(&worker->wqe->lock); + acct->nr_workers--; + raw_spin_unlock(&worker->wqe->lock); + io_worker_ref_put(wq); + clear_bit_unlock(0, &worker->create_state); + io_worker_release(worker); +} + +static bool io_task_worker_match(struct callback_head *cb, void *data) +{ + struct io_worker *worker; + + if (cb->func != create_worker_cb) + return false; + worker = container_of(cb, struct io_worker, create_work); + return worker == data; +} + static void io_worker_exit(struct io_worker *worker) { struct io_wqe *wqe = worker->wqe; + struct io_wq *wq = wqe->wq; - if (refcount_dec_and_test(&worker->ref)) - complete(&worker->ref_done); + while (1) { + struct callback_head *cb = task_work_cancel_match(wq->task, + io_task_worker_match, worker); + + if (!cb) + break; + io_worker_cancel_cb(worker); + } + + io_worker_release(worker); wait_for_completion(&worker->ref_done); raw_spin_lock(&wqe->lock); @@ -323,8 +358,10 @@ static bool io_queue_worker_create(struct io_worker *worker, init_task_work(&worker->create_work, func); worker->create_index = acct->index; - if (!task_work_add(wq->task, &worker->create_work, TWA_SIGNAL)) + if (!task_work_add(wq->task, &worker->create_work, TWA_SIGNAL)) { + clear_bit_unlock(0, &worker->create_state); return true; + } clear_bit_unlock(0, &worker->create_state); fail_release: io_worker_release(worker); @@ -716,11 +753,8 @@ static void io_workqueue_create(struct work_struct *work) struct io_worker *worker = container_of(work, struct io_worker, work); struct io_wqe_acct *acct = io_wqe_get_acct(worker); - if (!io_queue_worker_create(worker, acct, create_worker_cont)) { - clear_bit_unlock(0, &worker->create_state); - io_worker_release(worker); + if (!io_queue_worker_create(worker, acct, create_worker_cont)) kfree(worker); - } } static bool create_io_worker(struct io_wq *wq, struct io_wqe *wqe, int index) @@ -1150,17 +1184,9 @@ static void io_wq_exit_workers(struct io_wq *wq) while ((cb = task_work_cancel_match(wq->task, io_task_work_match, wq)) != NULL) { struct io_worker *worker; - struct io_wqe_acct *acct; worker = container_of(cb, struct io_worker, create_work); - acct = io_wqe_get_acct(worker); - atomic_dec(&acct->nr_running); - raw_spin_lock(&worker->wqe->lock); - acct->nr_workers--; - raw_spin_unlock(&worker->wqe->lock); - io_worker_ref_put(wq); - clear_bit_unlock(0, &worker->create_state); - io_worker_release(worker); + io_worker_cancel_cb(worker); } rcu_read_lock(); diff --git a/fs/io-wq.h b/fs/io-wq.h index bf5c4c533760..41bf37674a49 100644 --- a/fs/io-wq.h +++ b/fs/io-wq.h @@ -29,6 +29,17 @@ struct io_wq_work_list { struct io_wq_work_node *last; }; +#define wq_list_for_each(pos, prv, head) \ + for (pos = (head)->first, prv = NULL; pos; prv = pos, pos = (pos)->next) + +#define wq_list_for_each_resume(pos, prv) \ + for (; pos; prv = pos, pos = (pos)->next) + +#define wq_list_empty(list) (READ_ONCE((list)->first) == NULL) +#define INIT_WQ_LIST(list) do { \ + (list)->first = NULL; \ +} while (0) + static inline void wq_list_add_after(struct io_wq_work_node *node, struct io_wq_work_node *pos, struct io_wq_work_list *list) @@ -54,6 +65,15 @@ static inline void wq_list_add_tail(struct io_wq_work_node *node, } } +static inline void wq_list_add_head(struct io_wq_work_node *node, + struct io_wq_work_list *list) +{ + node->next = list->first; + if (!node->next) + list->last = node; + WRITE_ONCE(list->first, node); +} + static inline void wq_list_cut(struct io_wq_work_list *list, struct io_wq_work_node *last, struct io_wq_work_node *prev) @@ -69,6 +89,31 @@ static inline void wq_list_cut(struct io_wq_work_list *list, last->next = NULL; } +static inline void __wq_list_splice(struct io_wq_work_list *list, + struct io_wq_work_node *to) +{ + list->last->next = to->next; + to->next = list->first; + INIT_WQ_LIST(list); +} + +static inline bool wq_list_splice(struct io_wq_work_list *list, + struct io_wq_work_node *to) +{ + if (!wq_list_empty(list)) { + __wq_list_splice(list, to); + return true; + } + return false; +} + +static inline void wq_stack_add_head(struct io_wq_work_node *node, + struct io_wq_work_node *stack) +{ + node->next = stack->next; + stack->next = node; +} + static inline void wq_list_del(struct io_wq_work_list *list, struct io_wq_work_node *node, struct io_wq_work_node *prev) @@ -76,14 +121,14 @@ static inline void wq_list_del(struct io_wq_work_list *list, wq_list_cut(list, node, prev); } -#define wq_list_for_each(pos, prv, head) \ - for (pos = (head)->first, prv = NULL; pos; prv = pos, pos = (pos)->next) +static inline +struct io_wq_work_node *wq_stack_extract(struct io_wq_work_node *stack) +{ + struct io_wq_work_node *node = stack->next; -#define wq_list_empty(list) (READ_ONCE((list)->first) == NULL) -#define INIT_WQ_LIST(list) do { \ - (list)->first = NULL; \ - (list)->last = NULL; \ -} while (0) + stack->next = node->next; + return node; +} struct io_wq_work { struct io_wq_work_node list; diff --git a/fs/io_uring.c b/fs/io_uring.c index 057d07cee9f8..ca10dbb01201 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -103,11 +103,14 @@ #define IORING_MAX_REG_BUFFERS (1U << 14) -#define SQE_VALID_FLAGS (IOSQE_FIXED_FILE|IOSQE_IO_DRAIN|IOSQE_IO_LINK| \ - IOSQE_IO_HARDLINK | IOSQE_ASYNC | \ - IOSQE_BUFFER_SELECT) +#define SQE_COMMON_FLAGS (IOSQE_FIXED_FILE | IOSQE_IO_LINK | \ + IOSQE_IO_HARDLINK | IOSQE_ASYNC) + +#define SQE_VALID_FLAGS (SQE_COMMON_FLAGS|IOSQE_BUFFER_SELECT|IOSQE_IO_DRAIN) + #define IO_REQ_CLEAN_FLAGS (REQ_F_BUFFER_SELECTED | REQ_F_NEED_CLEANUP | \ - REQ_F_POLLED | REQ_F_INFLIGHT | REQ_F_CREDS) + REQ_F_POLLED | REQ_F_INFLIGHT | REQ_F_CREDS | \ + REQ_F_ASYNC_DATA) #define IO_TCTX_REFS_CACHE_NR (1U << 10) @@ -195,8 +198,10 @@ struct io_rings { }; enum io_uring_cmd_flags { - IO_URING_F_NONBLOCK = 1, - IO_URING_F_COMPLETE_DEFER = 2, + IO_URING_F_COMPLETE_DEFER = 1, + IO_URING_F_UNLOCKED = 2, + /* int's last bit, sign checks are usually faster than a bit test */ + IO_URING_F_NONBLOCK = INT_MIN, }; struct io_mapped_ubuf { @@ -305,26 +310,16 @@ struct io_submit_link { }; struct io_submit_state { - struct blk_plug plug; + /* inline/task_work completion list, under ->uring_lock */ + struct io_wq_work_node free_list; + /* batch completion logic */ + struct io_wq_work_list compl_reqs; struct io_submit_link link; - /* - * io_kiocb alloc cache - */ - void *reqs[IO_REQ_CACHE_SIZE]; - unsigned int free_reqs; - bool plug_started; - - /* - * Batch completion logic - */ - struct io_kiocb *compl_reqs[IO_COMPL_BATCH]; - unsigned int compl_nr; - /* inline/task_work completion list, under ->uring_lock */ - struct list_head free_list; - - unsigned int ios_left; + bool need_plug; + unsigned short submit_nr; + struct blk_plug plug; }; struct io_ring_ctx { @@ -368,6 +363,7 @@ struct io_ring_ctx { * uring_lock, and updated through io_uring_register(2) */ struct io_rsrc_node *rsrc_node; + int rsrc_cached_refs; struct io_file_table file_table; unsigned nr_user_files; unsigned nr_user_bufs; @@ -384,7 +380,7 @@ struct io_ring_ctx { } ____cacheline_aligned_in_smp; /* IRQ completion list, under ->completion_lock */ - struct list_head locked_free_list; + struct io_wq_work_list locked_free_list; unsigned int locked_free_nr; const struct cred *sq_creds; /* cred used for __io_sq_thread() */ @@ -399,7 +395,6 @@ struct io_ring_ctx { unsigned cached_cq_tail; unsigned cq_entries; struct eventfd_ctx *cq_ev_fd; - struct wait_queue_head poll_wait; struct wait_queue_head cq_wait; unsigned cq_extra; atomic_t cq_timeouts; @@ -417,7 +412,7 @@ struct io_ring_ctx { * For SQPOLL, only the single threaded io_sq_thread() will * manipulate the list, hence no extra locking is needed there. */ - struct list_head iopoll_list; + struct io_wq_work_list iopoll_list; struct hlist_head *cancel_hash; unsigned cancel_hash_bits; bool poll_multi_queue; @@ -580,7 +575,6 @@ struct io_sr_msg { int msg_flags; int bgid; size_t len; - struct io_buffer *kbuf; }; struct io_open { @@ -692,11 +686,6 @@ struct io_hardlink { int flags; }; -struct io_completion { - struct file *file; - u32 cflags; -}; - struct io_async_connect { struct sockaddr_storage address; }; @@ -710,11 +699,15 @@ struct io_async_msghdr { struct sockaddr_storage addr; }; -struct io_async_rw { - struct iovec fast_iov[UIO_FASTIOV]; - const struct iovec *free_iovec; +struct io_rw_state { struct iov_iter iter; struct iov_iter_state iter_state; + struct iovec fast_iov[UIO_FASTIOV]; +}; + +struct io_async_rw { + struct io_rw_state s; + const struct iovec *free_iovec; size_t bytes_done; struct wait_page_queue wpq; }; @@ -741,9 +734,9 @@ enum { REQ_F_CREDS_BIT, REQ_F_REFCOUNT_BIT, REQ_F_ARM_LTIMEOUT_BIT, + REQ_F_ASYNC_DATA_BIT, /* keep async read/write and isreg together and in order */ - REQ_F_NOWAIT_READ_BIT, - REQ_F_NOWAIT_WRITE_BIT, + REQ_F_SUPPORT_NOWAIT_BIT, REQ_F_ISREG_BIT, /* not a real bit, just to check we're not overflowing the space */ @@ -784,10 +777,8 @@ enum { REQ_F_COMPLETE_INLINE = BIT(REQ_F_COMPLETE_INLINE_BIT), /* caller should reissue async */ REQ_F_REISSUE = BIT(REQ_F_REISSUE_BIT), - /* supports async reads */ - REQ_F_NOWAIT_READ = BIT(REQ_F_NOWAIT_READ_BIT), - /* supports async writes */ - REQ_F_NOWAIT_WRITE = BIT(REQ_F_NOWAIT_WRITE_BIT), + /* supports async reads/writes */ + REQ_F_SUPPORT_NOWAIT = BIT(REQ_F_SUPPORT_NOWAIT_BIT), /* regular file */ REQ_F_ISREG = BIT(REQ_F_ISREG_BIT), /* has creds assigned */ @@ -796,6 +787,8 @@ enum { REQ_F_REFCOUNT = BIT(REQ_F_REFCOUNT_BIT), /* there is a linked timeout that has to be armed */ REQ_F_ARM_LTIMEOUT = BIT(REQ_F_ARM_LTIMEOUT_BIT), + /* ->async_data allocated */ + REQ_F_ASYNC_DATA = BIT(REQ_F_ASYNC_DATA_BIT), }; struct async_poll { @@ -852,39 +845,41 @@ struct io_kiocb { struct io_mkdir mkdir; struct io_symlink symlink; struct io_hardlink hardlink; - /* use only after cleaning per-op data, see io_clean_op() */ - struct io_completion compl; }; - /* opcode allocated if it needs to store data for async defer */ - void *async_data; u8 opcode; /* polled IO has completed */ u8 iopoll_completed; - u16 buf_index; + unsigned int flags; + + u64 user_data; u32 result; + u32 cflags; struct io_ring_ctx *ctx; - unsigned int flags; - atomic_t refs; struct task_struct *task; - u64 user_data; - struct io_kiocb *link; struct percpu_ref *fixed_rsrc_refs; + /* store used ubuf, so we can prevent reloading */ + struct io_mapped_ubuf *imu; - /* used with ctx->iopoll_list with reads/writes */ - struct list_head inflight_entry; + /* used by request caches, completion batching and iopoll */ + struct io_wq_work_node comp_list; + atomic_t refs; + struct io_kiocb *link; struct io_task_work io_task_work; /* for polled requests, i.e. IORING_OP_POLL_ADD and async armed poll */ struct hlist_node hash_node; + /* internal polling, see IORING_FEAT_FAST_POLL */ struct async_poll *apoll; + /* opcode allocated if it needs to store data for async defer */ + void *async_data; struct io_wq_work work; + /* custom credentials, valid IFF REQ_F_CREDS is set */ const struct cred *creds; - - /* store used ubuf, so we can prevent reloading */ - struct io_mapped_ubuf *imu; + /* stores selected buf, valid IFF REQ_F_BUFFER_SELECTED is set */ + struct io_buffer *kbuf; }; struct io_tctx_node { @@ -902,12 +897,12 @@ struct io_defer_entry { struct io_op_def { /* needs req->file assigned */ unsigned needs_file : 1; + /* should block plug */ + unsigned plug : 1; /* hash wq insertion if file is a regular file */ unsigned hash_reg_file : 1; /* unbound wq insertion if file is a non-regular file */ unsigned unbound_nonreg_file : 1; - /* opcode is not supported by this kernel */ - unsigned not_supported : 1; /* set if opcode supports polled "wait" */ unsigned pollin : 1; unsigned pollout : 1; @@ -915,8 +910,8 @@ struct io_op_def { unsigned buffer_select : 1; /* do prep async if is going to be punted */ unsigned needs_async_setup : 1; - /* should block plug */ - unsigned plug : 1; + /* opcode is not supported by this kernel */ + unsigned not_supported : 1; /* size of async data needed, if any */ unsigned short async_size; }; @@ -1080,7 +1075,7 @@ static void io_uring_try_cancel_requests(struct io_ring_ctx *ctx, static void io_uring_cancel_generic(bool cancel_all, struct io_sq_data *sqd); static bool io_cqring_fill_event(struct io_ring_ctx *ctx, u64 user_data, - long res, unsigned int cflags); + s32 res, u32 cflags); static void io_put_req(struct io_kiocb *req); static void io_put_req_deferred(struct io_kiocb *req); static void io_dismantle_req(struct io_kiocb *req); @@ -1095,7 +1090,7 @@ static void __io_queue_sqe(struct io_kiocb *req); static void io_rsrc_put_work(struct work_struct *work); static void io_req_task_queue(struct io_kiocb *req); -static void io_submit_flush_completions(struct io_ring_ctx *ctx); +static void __io_submit_flush_completions(struct io_ring_ctx *ctx); static int io_req_prep_async(struct io_kiocb *req); static int io_install_fixed_file(struct io_kiocb *req, struct file *file, @@ -1167,6 +1162,12 @@ static inline void req_ref_get(struct io_kiocb *req) atomic_inc(&req->refs); } +static inline void io_submit_flush_completions(struct io_ring_ctx *ctx) +{ + if (!wq_list_empty(&ctx->submit_state.compl_reqs)) + __io_submit_flush_completions(ctx); +} + static inline void __io_req_set_refcount(struct io_kiocb *req, int nr) { if (!(req->flags & REQ_F_REFCOUNT)) { @@ -1180,13 +1181,52 @@ static inline void io_req_set_refcount(struct io_kiocb *req) __io_req_set_refcount(req, 1); } -static inline void io_req_set_rsrc_node(struct io_kiocb *req) -{ - struct io_ring_ctx *ctx = req->ctx; +#define IO_RSRC_REF_BATCH 100 +static inline void io_req_put_rsrc_locked(struct io_kiocb *req, + struct io_ring_ctx *ctx) + __must_hold(&ctx->uring_lock) +{ + struct percpu_ref *ref = req->fixed_rsrc_refs; + + if (ref) { + if (ref == &ctx->rsrc_node->refs) + ctx->rsrc_cached_refs++; + else + percpu_ref_put(ref); + } +} + +static inline void io_req_put_rsrc(struct io_kiocb *req, struct io_ring_ctx *ctx) +{ + if (req->fixed_rsrc_refs) + percpu_ref_put(req->fixed_rsrc_refs); +} + +static __cold void io_rsrc_refs_drop(struct io_ring_ctx *ctx) + __must_hold(&ctx->uring_lock) +{ + if (ctx->rsrc_cached_refs) { + percpu_ref_put_many(&ctx->rsrc_node->refs, ctx->rsrc_cached_refs); + ctx->rsrc_cached_refs = 0; + } +} + +static void io_rsrc_refs_refill(struct io_ring_ctx *ctx) + __must_hold(&ctx->uring_lock) +{ + ctx->rsrc_cached_refs += IO_RSRC_REF_BATCH; + percpu_ref_get_many(&ctx->rsrc_node->refs, IO_RSRC_REF_BATCH); +} + +static inline void io_req_set_rsrc_node(struct io_kiocb *req, + struct io_ring_ctx *ctx) +{ if (!req->fixed_rsrc_refs) { req->fixed_rsrc_refs = &ctx->rsrc_node->refs; - percpu_ref_get(req->fixed_rsrc_refs); + ctx->rsrc_cached_refs--; + if (unlikely(ctx->rsrc_cached_refs < 0)) + io_rsrc_refs_refill(ctx); } } @@ -1219,6 +1259,11 @@ static bool io_match_task(struct io_kiocb *head, struct task_struct *task, return false; } +static inline bool req_has_async_data(struct io_kiocb *req) +{ + return req->flags & REQ_F_ASYNC_DATA; +} + static inline void req_set_fail(struct io_kiocb *req) { req->flags |= REQ_F_FAIL; @@ -1230,7 +1275,7 @@ static inline void req_fail_link_node(struct io_kiocb *req, int res) req->result = res; } -static void io_ring_ctx_ref_free(struct percpu_ref *ref) +static __cold void io_ring_ctx_ref_free(struct percpu_ref *ref) { struct io_ring_ctx *ctx = container_of(ref, struct io_ring_ctx, refs); @@ -1242,7 +1287,7 @@ static inline bool io_is_timeout_noseq(struct io_kiocb *req) return !req->timeout.off; } -static void io_fallback_req_func(struct work_struct *work) +static __cold void io_fallback_req_func(struct work_struct *work) { struct io_ring_ctx *ctx = container_of(work, struct io_ring_ctx, fallback_work.work); @@ -1255,15 +1300,13 @@ static void io_fallback_req_func(struct work_struct *work) req->io_task_work.func(req, &locked); if (locked) { - if (ctx->submit_state.compl_nr) - io_submit_flush_completions(ctx); + io_submit_flush_completions(ctx); mutex_unlock(&ctx->uring_lock); } percpu_ref_put(&ctx->refs); - } -static struct io_ring_ctx *io_ring_ctx_alloc(struct io_uring_params *p) +static __cold struct io_ring_ctx *io_ring_ctx_alloc(struct io_uring_params *p) { struct io_ring_ctx *ctx; int hash_bits; @@ -1300,7 +1343,6 @@ static struct io_ring_ctx *io_ring_ctx_alloc(struct io_uring_params *p) ctx->flags = p->flags; init_waitqueue_head(&ctx->sqo_sq_wait); INIT_LIST_HEAD(&ctx->sqd_list); - init_waitqueue_head(&ctx->poll_wait); INIT_LIST_HEAD(&ctx->cq_overflow_list); init_completion(&ctx->ref_comp); xa_init_flags(&ctx->io_buffers, XA_FLAGS_ALLOC1); @@ -1309,7 +1351,7 @@ static struct io_ring_ctx *io_ring_ctx_alloc(struct io_uring_params *p) init_waitqueue_head(&ctx->cq_wait); spin_lock_init(&ctx->completion_lock); spin_lock_init(&ctx->timeout_lock); - INIT_LIST_HEAD(&ctx->iopoll_list); + INIT_WQ_LIST(&ctx->iopoll_list); INIT_LIST_HEAD(&ctx->defer_list); INIT_LIST_HEAD(&ctx->timeout_list); INIT_LIST_HEAD(&ctx->ltimeout_list); @@ -1318,9 +1360,10 @@ static struct io_ring_ctx *io_ring_ctx_alloc(struct io_uring_params *p) INIT_DELAYED_WORK(&ctx->rsrc_put_work, io_rsrc_put_work); init_llist_head(&ctx->rsrc_put_llist); INIT_LIST_HEAD(&ctx->tctx_list); - INIT_LIST_HEAD(&ctx->submit_state.free_list); - INIT_LIST_HEAD(&ctx->locked_free_list); + ctx->submit_state.free_list.next = NULL; + INIT_WQ_LIST(&ctx->locked_free_list); INIT_DELAYED_WORK(&ctx->fallback_work, io_fallback_req_func); + INIT_WQ_LIST(&ctx->submit_state.compl_reqs); return ctx; err: kfree(ctx->dummy_ubuf); @@ -1348,21 +1391,16 @@ static bool req_need_defer(struct io_kiocb *req, u32 seq) return false; } -#define FFS_ASYNC_READ 0x1UL -#define FFS_ASYNC_WRITE 0x2UL -#ifdef CONFIG_64BIT -#define FFS_ISREG 0x4UL -#else -#define FFS_ISREG 0x0UL -#endif -#define FFS_MASK ~(FFS_ASYNC_READ|FFS_ASYNC_WRITE|FFS_ISREG) +#define FFS_NOWAIT 0x1UL +#define FFS_ISREG 0x2UL +#define FFS_MASK ~(FFS_NOWAIT|FFS_ISREG) static inline bool io_req_ffs_set(struct io_kiocb *req) { - return IS_ENABLED(CONFIG_64BIT) && (req->flags & REQ_F_FIXED_FILE); + return req->flags & REQ_F_FIXED_FILE; } -static void io_req_track_inflight(struct io_kiocb *req) +static inline void io_req_track_inflight(struct io_kiocb *req) { if (!(req->flags & REQ_F_INFLIGHT)) { req->flags |= REQ_F_INFLIGHT; @@ -1440,15 +1478,19 @@ static void io_prep_async_link(struct io_kiocb *req) } } -static void io_queue_async_work(struct io_kiocb *req, bool *locked) +static inline void io_req_add_compl_list(struct io_kiocb *req) +{ + struct io_submit_state *state = &req->ctx->submit_state; + + wq_list_add_tail(&req->comp_list, &state->compl_reqs); +} + +static void io_queue_async_work(struct io_kiocb *req, bool *dont_use) { struct io_ring_ctx *ctx = req->ctx; struct io_kiocb *link = io_prep_linked_timeout(req); struct io_uring_task *tctx = req->task->io_uring; - /* must not take the lock, NULL it as a precaution */ - locked = NULL; - BUG_ON(!tctx); BUG_ON(!tctx->io_wq); @@ -1489,7 +1531,7 @@ static void io_kill_timeout(struct io_kiocb *req, int status) } } -static void io_queue_deferred(struct io_ring_ctx *ctx) +static __cold void io_queue_deferred(struct io_ring_ctx *ctx) { while (!list_empty(&ctx->defer_list)) { struct io_defer_entry *de = list_first_entry(&ctx->defer_list, @@ -1503,7 +1545,7 @@ static void io_queue_deferred(struct io_ring_ctx *ctx) } } -static void io_flush_timeouts(struct io_ring_ctx *ctx) +static __cold void io_flush_timeouts(struct io_ring_ctx *ctx) __must_hold(&ctx->completion_lock) { u32 seq = ctx->cached_cq_tail - atomic_read(&ctx->cq_timeouts); @@ -1536,7 +1578,7 @@ static void io_flush_timeouts(struct io_ring_ctx *ctx) spin_unlock_irq(&ctx->timeout_lock); } -static void __io_commit_cqring_flush(struct io_ring_ctx *ctx) +static __cold void __io_commit_cqring_flush(struct io_ring_ctx *ctx) { if (ctx->off_timeout_used) io_flush_timeouts(ctx); @@ -1606,12 +1648,8 @@ static void io_cqring_ev_posted(struct io_ring_ctx *ctx) */ if (wq_has_sleeper(&ctx->cq_wait)) wake_up_all(&ctx->cq_wait); - if (ctx->sq_data && waitqueue_active(&ctx->sq_data->wait)) - wake_up(&ctx->sq_data->wait); if (io_should_trigger_evfd(ctx)) eventfd_signal(ctx->cq_ev_fd, 1); - if (waitqueue_active(&ctx->poll_wait)) - wake_up_interruptible(&ctx->poll_wait); } static void io_cqring_ev_posted_iopoll(struct io_ring_ctx *ctx) @@ -1625,8 +1663,6 @@ static void io_cqring_ev_posted_iopoll(struct io_ring_ctx *ctx) } if (io_should_trigger_evfd(ctx)) eventfd_signal(ctx->cq_ev_fd, 1); - if (waitqueue_active(&ctx->poll_wait)) - wake_up_interruptible(&ctx->poll_wait); } /* Returns true if there are no backlogged entries after the flush */ @@ -1722,7 +1758,7 @@ static inline void io_get_task_refs(int nr) } static bool io_cqring_event_overflow(struct io_ring_ctx *ctx, u64 user_data, - long res, unsigned int cflags) + s32 res, u32 cflags) { struct io_overflow_cqe *ocqe; @@ -1750,7 +1786,7 @@ static bool io_cqring_event_overflow(struct io_ring_ctx *ctx, u64 user_data, } static inline bool __io_cqring_fill_event(struct io_ring_ctx *ctx, u64 user_data, - long res, unsigned int cflags) + s32 res, u32 cflags) { struct io_uring_cqe *cqe; @@ -1773,13 +1809,13 @@ static inline bool __io_cqring_fill_event(struct io_ring_ctx *ctx, u64 user_data /* not as hot to bloat with inlining */ static noinline bool io_cqring_fill_event(struct io_ring_ctx *ctx, u64 user_data, - long res, unsigned int cflags) + s32 res, u32 cflags) { return __io_cqring_fill_event(ctx, user_data, res, cflags); } -static void io_req_complete_post(struct io_kiocb *req, long res, - unsigned int cflags) +static void io_req_complete_post(struct io_kiocb *req, s32 res, + u32 cflags) { struct io_ring_ctx *ctx = req->ctx; @@ -1798,40 +1834,27 @@ static void io_req_complete_post(struct io_kiocb *req, long res, req->link = NULL; } } + io_req_put_rsrc(req, ctx); io_dismantle_req(req); io_put_task(req->task, 1); - list_add(&req->inflight_entry, &ctx->locked_free_list); + wq_list_add_head(&req->comp_list, &ctx->locked_free_list); ctx->locked_free_nr++; - } else { - if (!percpu_ref_tryget(&ctx->refs)) - req = NULL; } io_commit_cqring(ctx); spin_unlock(&ctx->completion_lock); - - if (req) { - io_cqring_ev_posted(ctx); - percpu_ref_put(&ctx->refs); - } + io_cqring_ev_posted(ctx); } -static inline bool io_req_needs_clean(struct io_kiocb *req) +static inline void io_req_complete_state(struct io_kiocb *req, s32 res, + u32 cflags) { - return req->flags & IO_REQ_CLEAN_FLAGS; -} - -static void io_req_complete_state(struct io_kiocb *req, long res, - unsigned int cflags) -{ - if (io_req_needs_clean(req)) - io_clean_op(req); req->result = res; - req->compl.cflags = cflags; + req->cflags = cflags; req->flags |= REQ_F_COMPLETE_INLINE; } static inline void __io_req_complete(struct io_kiocb *req, unsigned issue_flags, - long res, unsigned cflags) + s32 res, u32 cflags) { if (issue_flags & IO_URING_F_COMPLETE_DEFER) io_req_complete_state(req, res, cflags); @@ -1839,12 +1862,12 @@ static inline void __io_req_complete(struct io_kiocb *req, unsigned issue_flags, io_req_complete_post(req, res, cflags); } -static inline void io_req_complete(struct io_kiocb *req, long res) +static inline void io_req_complete(struct io_kiocb *req, s32 res) { __io_req_complete(req, 0, res, 0); } -static void io_req_complete_failed(struct io_kiocb *req, long res) +static void io_req_complete_failed(struct io_kiocb *req, s32 res) { req_set_fail(req); io_req_complete_post(req, res, 0); @@ -1878,7 +1901,7 @@ static void io_flush_cached_locked_reqs(struct io_ring_ctx *ctx, struct io_submit_state *state) { spin_lock(&ctx->completion_lock); - list_splice_init(&ctx->locked_free_list, &state->free_list); + wq_list_splice(&ctx->locked_free_list, &state->free_list); ctx->locked_free_nr = 0; spin_unlock(&ctx->completion_lock); } @@ -1887,7 +1910,6 @@ static void io_flush_cached_locked_reqs(struct io_ring_ctx *ctx, static bool io_flush_cached_reqs(struct io_ring_ctx *ctx) { struct io_submit_state *state = &ctx->submit_state; - int nr; /* * If we have more than a batch's worth of requests in our IRQ side @@ -1896,20 +1918,7 @@ static bool io_flush_cached_reqs(struct io_ring_ctx *ctx) */ if (READ_ONCE(ctx->locked_free_nr) > IO_COMPL_BATCH) io_flush_cached_locked_reqs(ctx, state); - - nr = state->free_reqs; - while (!list_empty(&state->free_list)) { - struct io_kiocb *req = list_first_entry(&state->free_list, - struct io_kiocb, inflight_entry); - - list_del(&req->inflight_entry); - state->reqs[nr++] = req; - if (nr == ARRAY_SIZE(state->reqs)) - break; - } - - state->free_reqs = nr; - return nr != 0; + return !!state->free_list.next; } /* @@ -1918,38 +1927,54 @@ static bool io_flush_cached_reqs(struct io_ring_ctx *ctx) * Because of that, io_alloc_req() should be called only under ->uring_lock * and with extra caution to not get a request that is still worked on. */ -static struct io_kiocb *io_alloc_req(struct io_ring_ctx *ctx) +static __cold bool __io_alloc_req_refill(struct io_ring_ctx *ctx) __must_hold(&ctx->uring_lock) { struct io_submit_state *state = &ctx->submit_state; gfp_t gfp = GFP_KERNEL | __GFP_NOWARN; + void *reqs[IO_REQ_ALLOC_BATCH]; + struct io_kiocb *req; int ret, i; - BUILD_BUG_ON(ARRAY_SIZE(state->reqs) < IO_REQ_ALLOC_BATCH); + if (likely(state->free_list.next || io_flush_cached_reqs(ctx))) + return true; - if (likely(state->free_reqs || io_flush_cached_reqs(ctx))) - goto got_req; - - ret = kmem_cache_alloc_bulk(req_cachep, gfp, IO_REQ_ALLOC_BATCH, - state->reqs); + ret = kmem_cache_alloc_bulk(req_cachep, gfp, ARRAY_SIZE(reqs), reqs); /* * Bulk alloc is all-or-nothing. If we fail to get a batch, * retry single alloc to be on the safe side. */ if (unlikely(ret <= 0)) { - state->reqs[0] = kmem_cache_alloc(req_cachep, gfp); - if (!state->reqs[0]) - return NULL; + reqs[0] = kmem_cache_alloc(req_cachep, gfp); + if (!reqs[0]) + return false; ret = 1; } - for (i = 0; i < ret; i++) - io_preinit_req(state->reqs[i], ctx); - state->free_reqs = ret; -got_req: - state->free_reqs--; - return state->reqs[state->free_reqs]; + percpu_ref_get_many(&ctx->refs, ret); + for (i = 0; i < ret; i++) { + req = reqs[i]; + + io_preinit_req(req, ctx); + wq_stack_add_head(&req->comp_list, &state->free_list); + } + return true; +} + +static inline bool io_alloc_req_refill(struct io_ring_ctx *ctx) +{ + if (unlikely(!ctx->submit_state.free_list.next)) + return __io_alloc_req_refill(ctx); + return true; +} + +static inline struct io_kiocb *io_alloc_req(struct io_ring_ctx *ctx) +{ + struct io_wq_work_node *node; + + node = wq_stack_extract(&ctx->submit_state.free_list); + return container_of(node, struct io_kiocb, comp_list); } static inline void io_put_file(struct file *file) @@ -1958,35 +1983,28 @@ static inline void io_put_file(struct file *file) fput(file); } -static void io_dismantle_req(struct io_kiocb *req) +static inline void io_dismantle_req(struct io_kiocb *req) { unsigned int flags = req->flags; - if (io_req_needs_clean(req)) + if (unlikely(flags & IO_REQ_CLEAN_FLAGS)) io_clean_op(req); if (!(flags & REQ_F_FIXED_FILE)) io_put_file(req->file); - if (req->fixed_rsrc_refs) - percpu_ref_put(req->fixed_rsrc_refs); - if (req->async_data) { - kfree(req->async_data); - req->async_data = NULL; - } } -static void __io_free_req(struct io_kiocb *req) +static __cold void __io_free_req(struct io_kiocb *req) { struct io_ring_ctx *ctx = req->ctx; + io_req_put_rsrc(req, ctx); io_dismantle_req(req); io_put_task(req->task, 1); spin_lock(&ctx->completion_lock); - list_add(&req->inflight_entry, &ctx->locked_free_list); + wq_list_add_head(&req->comp_list, &ctx->locked_free_list); ctx->locked_free_nr++; spin_unlock(&ctx->completion_lock); - - percpu_ref_put(&ctx->refs); } static inline void io_remove_next_linked(struct io_kiocb *req) @@ -2072,47 +2090,45 @@ static bool io_disarm_next(struct io_kiocb *req) return posted; } -static struct io_kiocb *__io_req_find_next(struct io_kiocb *req) +static void __io_req_find_next_prep(struct io_kiocb *req) +{ + struct io_ring_ctx *ctx = req->ctx; + bool posted; + + spin_lock(&ctx->completion_lock); + posted = io_disarm_next(req); + if (posted) + io_commit_cqring(req->ctx); + spin_unlock(&ctx->completion_lock); + if (posted) + io_cqring_ev_posted(ctx); +} + +static inline struct io_kiocb *io_req_find_next(struct io_kiocb *req) { struct io_kiocb *nxt; + if (likely(!(req->flags & (REQ_F_LINK|REQ_F_HARDLINK)))) + return NULL; /* * If LINK is set, we have dependent requests in this chain. If we * didn't fail this request, queue the first one up, moving any other * dependencies to the next request. In case of failure, fail the rest * of the chain. */ - if (req->flags & IO_DISARM_MASK) { - struct io_ring_ctx *ctx = req->ctx; - bool posted; - - spin_lock(&ctx->completion_lock); - posted = io_disarm_next(req); - if (posted) - io_commit_cqring(req->ctx); - spin_unlock(&ctx->completion_lock); - if (posted) - io_cqring_ev_posted(ctx); - } + if (unlikely(req->flags & IO_DISARM_MASK)) + __io_req_find_next_prep(req); nxt = req->link; req->link = NULL; return nxt; } -static inline struct io_kiocb *io_req_find_next(struct io_kiocb *req) -{ - if (likely(!(req->flags & (REQ_F_LINK|REQ_F_HARDLINK)))) - return NULL; - return __io_req_find_next(req); -} - static void ctx_flush_and_put(struct io_ring_ctx *ctx, bool *locked) { if (!ctx) return; if (*locked) { - if (ctx->submit_state.compl_nr) - io_submit_flush_completions(ctx); + io_submit_flush_completions(ctx); mutex_unlock(&ctx->uring_lock); *locked = false; } @@ -2129,7 +2145,7 @@ static void tctx_task_work(struct callback_head *cb) while (1) { struct io_wq_work_node *node; - if (!tctx->task_list.first && locked && ctx->submit_state.compl_nr) + if (!tctx->task_list.first && locked) io_submit_flush_completions(ctx); spin_lock_irq(&tctx->task_lock); @@ -2192,8 +2208,9 @@ static void io_req_task_work_add(struct io_kiocb *req) * will do the job. */ notify = (req->ctx->flags & IORING_SETUP_SQPOLL) ? TWA_NONE : TWA_SIGNAL; - if (!task_work_add(tsk, &tctx->task_work, notify)) { - wake_up_process(tsk); + if (likely(!task_work_add(tsk, &tctx->task_work, notify))) { + if (notify == TWA_NONE) + wake_up_process(tsk); return; } @@ -2271,77 +2288,62 @@ static void io_free_req_work(struct io_kiocb *req, bool *locked) io_free_req(req); } -struct req_batch { - struct task_struct *task; - int task_refs; - int ctx_refs; -}; - -static inline void io_init_req_batch(struct req_batch *rb) -{ - rb->task_refs = 0; - rb->ctx_refs = 0; - rb->task = NULL; -} - -static void io_req_free_batch_finish(struct io_ring_ctx *ctx, - struct req_batch *rb) -{ - if (rb->ctx_refs) - percpu_ref_put_many(&ctx->refs, rb->ctx_refs); - if (rb->task) - io_put_task(rb->task, rb->task_refs); -} - -static void io_req_free_batch(struct req_batch *rb, struct io_kiocb *req, - struct io_submit_state *state) -{ - io_queue_next(req); - io_dismantle_req(req); - - if (req->task != rb->task) { - if (rb->task) - io_put_task(rb->task, rb->task_refs); - rb->task = req->task; - rb->task_refs = 0; - } - rb->task_refs++; - rb->ctx_refs++; - - if (state->free_reqs != ARRAY_SIZE(state->reqs)) - state->reqs[state->free_reqs++] = req; - else - list_add(&req->inflight_entry, &state->free_list); -} - -static void io_submit_flush_completions(struct io_ring_ctx *ctx) +static void io_free_batch_list(struct io_ring_ctx *ctx, + struct io_wq_work_node *node) __must_hold(&ctx->uring_lock) { + struct task_struct *task = NULL; + int task_refs = 0; + + do { + struct io_kiocb *req = container_of(node, struct io_kiocb, + comp_list); + + if (unlikely(req->flags & REQ_F_REFCOUNT)) { + node = req->comp_list.next; + if (!req_ref_put_and_test(req)) + continue; + } + + io_req_put_rsrc_locked(req, ctx); + io_queue_next(req); + io_dismantle_req(req); + + if (req->task != task) { + if (task) + io_put_task(task, task_refs); + task = req->task; + task_refs = 0; + } + task_refs++; + node = req->comp_list.next; + wq_stack_add_head(&req->comp_list, &ctx->submit_state.free_list); + } while (node); + + if (task) + io_put_task(task, task_refs); +} + +static void __io_submit_flush_completions(struct io_ring_ctx *ctx) + __must_hold(&ctx->uring_lock) +{ + struct io_wq_work_node *node, *prev; struct io_submit_state *state = &ctx->submit_state; - int i, nr = state->compl_nr; - struct req_batch rb; spin_lock(&ctx->completion_lock); - for (i = 0; i < nr; i++) { - struct io_kiocb *req = state->compl_reqs[i]; + wq_list_for_each(node, prev, &state->compl_reqs) { + struct io_kiocb *req = container_of(node, struct io_kiocb, + comp_list); __io_cqring_fill_event(ctx, req->user_data, req->result, - req->compl.cflags); + req->cflags); } io_commit_cqring(ctx); spin_unlock(&ctx->completion_lock); io_cqring_ev_posted(ctx); - io_init_req_batch(&rb); - for (i = 0; i < nr; i++) { - struct io_kiocb *req = state->compl_reqs[i]; - - if (req_ref_put_and_test(req)) - io_req_free_batch(&rb, req, &ctx->submit_state); - } - - io_req_free_batch_finish(ctx, &rb); - state->compl_nr = 0; + io_free_batch_list(ctx, state->compl_reqs.first); + INIT_WQ_LIST(&state->compl_reqs); } /* @@ -2401,12 +2403,9 @@ static unsigned int io_put_kbuf(struct io_kiocb *req, struct io_buffer *kbuf) static inline unsigned int io_put_rw_kbuf(struct io_kiocb *req) { - struct io_buffer *kbuf; - if (likely(!(req->flags & REQ_F_BUFFER_SELECTED))) return 0; - kbuf = (struct io_buffer *) (unsigned long) req->rw.addr; - return io_put_kbuf(req, kbuf); + return io_put_kbuf(req, req->kbuf); } static inline bool io_run_task_work(void) @@ -2420,52 +2419,22 @@ static inline bool io_run_task_work(void) return false; } -/* - * Find and free completed poll iocbs - */ -static void io_iopoll_complete(struct io_ring_ctx *ctx, unsigned int *nr_events, - struct list_head *done) +static int io_do_iopoll(struct io_ring_ctx *ctx, bool force_nonspin) { - struct req_batch rb; - struct io_kiocb *req; - - /* order with ->result store in io_complete_rw_iopoll() */ - smp_rmb(); - - io_init_req_batch(&rb); - while (!list_empty(done)) { - req = list_first_entry(done, struct io_kiocb, inflight_entry); - list_del(&req->inflight_entry); - - __io_cqring_fill_event(ctx, req->user_data, req->result, - io_put_rw_kbuf(req)); - (*nr_events)++; - - if (req_ref_put_and_test(req)) - io_req_free_batch(&rb, req, &ctx->submit_state); - } - - io_commit_cqring(ctx); - io_cqring_ev_posted_iopoll(ctx); - io_req_free_batch_finish(ctx, &rb); -} - -static int io_do_iopoll(struct io_ring_ctx *ctx, unsigned int *nr_events, - long min) -{ - struct io_kiocb *req, *tmp; + struct io_wq_work_node *pos, *start, *prev; unsigned int poll_flags = BLK_POLL_NOSLEEP; DEFINE_IO_COMP_BATCH(iob); - LIST_HEAD(done); + int nr_events = 0; /* * Only spin for completions if we don't have multiple devices hanging - * off our complete list, and we're under the requested amount. + * off our complete list. */ - if (ctx->poll_multi_queue || *nr_events >= min) + if (ctx->poll_multi_queue || force_nonspin) poll_flags |= BLK_POLL_ONESHOT; - list_for_each_entry_safe(req, tmp, &ctx->iopoll_list, inflight_entry) { + wq_list_for_each(pos, start, &ctx->iopoll_list) { + struct io_kiocb *req = container_of(pos, struct io_kiocb, comp_list); struct kiocb *kiocb = &req->rw.kiocb; int ret; @@ -2474,11 +2443,7 @@ static int io_do_iopoll(struct io_ring_ctx *ctx, unsigned int *nr_events, * If we find a request that requires polling, break out * and complete those lists first, if we have entries there. */ - if (READ_ONCE(req->iopoll_completed)) { - list_move_tail(&req->inflight_entry, &done); - continue; - } - if (!list_empty(&done)) + if (READ_ONCE(req->iopoll_completed)) break; ret = kiocb->ki_filp->f_op->iopoll(kiocb, &iob, poll_flags); @@ -2490,34 +2455,50 @@ static int io_do_iopoll(struct io_ring_ctx *ctx, unsigned int *nr_events, /* iopoll may have completed current req */ if (!rq_list_empty(iob.req_list) || READ_ONCE(req->iopoll_completed)) - list_move_tail(&req->inflight_entry, &done); + break; } if (!rq_list_empty(iob.req_list)) iob.complete(&iob); - if (!list_empty(&done)) - io_iopoll_complete(ctx, nr_events, &done); + else if (!pos) + return 0; - return 0; + prev = start; + wq_list_for_each_resume(pos, prev) { + struct io_kiocb *req = container_of(pos, struct io_kiocb, comp_list); + + /* order with io_complete_rw_iopoll(), e.g. ->result updates */ + if (!smp_load_acquire(&req->iopoll_completed)) + break; + __io_cqring_fill_event(ctx, req->user_data, req->result, + io_put_rw_kbuf(req)); + nr_events++; + } + + if (unlikely(!nr_events)) + return 0; + + io_commit_cqring(ctx); + io_cqring_ev_posted_iopoll(ctx); + pos = start ? start->next : ctx->iopoll_list.first; + wq_list_cut(&ctx->iopoll_list, prev, start); + io_free_batch_list(ctx, pos); + return nr_events; } /* * We can't just wait for polled events to come to us, we have to actively * find and complete them. */ -static void io_iopoll_try_reap_events(struct io_ring_ctx *ctx) +static __cold void io_iopoll_try_reap_events(struct io_ring_ctx *ctx) { if (!(ctx->flags & IORING_SETUP_IOPOLL)) return; mutex_lock(&ctx->uring_lock); - while (!list_empty(&ctx->iopoll_list)) { - unsigned int nr_events = 0; - - io_do_iopoll(ctx, &nr_events, 0); - + while (!wq_list_empty(&ctx->iopoll_list)) { /* let it sleep and repeat later if can't complete a request */ - if (nr_events == 0) + if (io_do_iopoll(ctx, true) == 0) break; /* * Ensure we allow local-to-the-cpu processing to take place, @@ -2564,7 +2545,7 @@ static int io_iopoll_check(struct io_ring_ctx *ctx, long min) * forever, while the workqueue is stuck trying to acquire the * very same mutex. */ - if (list_empty(&ctx->iopoll_list)) { + if (wq_list_empty(&ctx->iopoll_list)) { u32 tail = ctx->cached_cq_tail; mutex_unlock(&ctx->uring_lock); @@ -2573,11 +2554,15 @@ static int io_iopoll_check(struct io_ring_ctx *ctx, long min) /* some requests don't go through iopoll_list */ if (tail != ctx->cached_cq_tail || - list_empty(&ctx->iopoll_list)) + wq_list_empty(&ctx->iopoll_list)) break; } - ret = io_do_iopoll(ctx, &nr_events, min); - } while (!ret && nr_events < min && !need_resched()); + ret = io_do_iopoll(ctx, !min); + if (ret < 0) + break; + nr_events += ret; + ret = 0; + } while (nr_events < min && !need_resched()); out: mutex_unlock(&ctx->uring_lock); return ret; @@ -2602,9 +2587,9 @@ static bool io_resubmit_prep(struct io_kiocb *req) { struct io_async_rw *rw = req->async_data; - if (!rw) + if (!req_has_async_data(req)) return !io_req_prep_async(req); - iov_iter_restore(&rw->iter, &rw->iter_state); + iov_iter_restore(&rw->s.iter, &rw->s.iter_state); return true; } @@ -2648,7 +2633,7 @@ static bool __io_complete_rw_common(struct io_kiocb *req, long res) { if (req->rw.kiocb.ki_flags & IOCB_WRITE) kiocb_end_write(req); - if (res != req->result) { + if (unlikely(res != req->result)) { if ((res == -EAGAIN || res == -EOPNOTSUPP) && io_rw_should_reissue(req)) { req->flags |= REQ_F_REISSUE; @@ -2663,16 +2648,11 @@ static bool __io_complete_rw_common(struct io_kiocb *req, long res) static void io_req_task_complete(struct io_kiocb *req, bool *locked) { unsigned int cflags = io_put_rw_kbuf(req); - long res = req->result; + int res = req->result; if (*locked) { - struct io_ring_ctx *ctx = req->ctx; - struct io_submit_state *state = &ctx->submit_state; - io_req_complete_state(req, res, cflags); - state->compl_reqs[state->compl_nr++] = req; - if (state->compl_nr == ARRAY_SIZE(state->compl_reqs)) - io_submit_flush_completions(ctx); + io_req_add_compl_list(req); } else { io_req_complete_post(req, res, cflags); } @@ -2708,12 +2688,11 @@ static void io_complete_rw_iopoll(struct kiocb *kiocb, long res, long res2) req->flags |= REQ_F_REISSUE; return; } + req->result = res; } - WRITE_ONCE(req->result, res); - /* order with io_iopoll_complete() checking ->result */ - smp_wmb(); - WRITE_ONCE(req->iopoll_completed, 1); + /* order with io_iopoll_complete() checking ->iopoll_completed */ + smp_store_release(&req->iopoll_completed, 1); } /* @@ -2722,13 +2701,13 @@ static void io_complete_rw_iopoll(struct kiocb *kiocb, long res, long res2) * find it from a io_do_iopoll() thread before the issuer is done * accessing the kiocb cookie. */ -static void io_iopoll_req_issued(struct io_kiocb *req) +static void io_iopoll_req_issued(struct io_kiocb *req, unsigned int issue_flags) { struct io_ring_ctx *ctx = req->ctx; - const bool in_async = io_wq_current_is_worker(); + const bool needs_lock = issue_flags & IO_URING_F_UNLOCKED; /* workqueue context doesn't hold uring_lock, grab it now */ - if (unlikely(in_async)) + if (unlikely(needs_lock)) mutex_lock(&ctx->uring_lock); /* @@ -2736,14 +2715,13 @@ static void io_iopoll_req_issued(struct io_kiocb *req) * how we do polling eventually, not spinning if we're on potentially * different devices. */ - if (list_empty(&ctx->iopoll_list)) { + if (wq_list_empty(&ctx->iopoll_list)) { ctx->poll_multi_queue = false; } else if (!ctx->poll_multi_queue) { struct io_kiocb *list_req; - list_req = list_first_entry(&ctx->iopoll_list, struct io_kiocb, - inflight_entry); - + list_req = container_of(ctx->iopoll_list.first, struct io_kiocb, + comp_list); if (list_req->file != req->file) ctx->poll_multi_queue = true; } @@ -2753,11 +2731,11 @@ static void io_iopoll_req_issued(struct io_kiocb *req) * it to the front so we find it first. */ if (READ_ONCE(req->iopoll_completed)) - list_add(&req->inflight_entry, &ctx->iopoll_list); + wq_list_add_head(&req->comp_list, &ctx->iopoll_list); else - list_add_tail(&req->inflight_entry, &ctx->iopoll_list); + wq_list_add_tail(&req->comp_list, &ctx->iopoll_list); - if (unlikely(in_async)) { + if (unlikely(needs_lock)) { /* * If IORING_SETUP_SQPOLL is enabled, sqes are either handle * in sq thread task context or in io worker task context. If @@ -2782,10 +2760,8 @@ static bool io_bdev_nowait(struct block_device *bdev) * any file. For now, just ensure that anything potentially problematic is done * inline. */ -static bool __io_file_supports_nowait(struct file *file, int rw) +static bool __io_file_supports_nowait(struct file *file, umode_t mode) { - umode_t mode = file_inode(file)->i_mode; - if (S_ISBLK(mode)) { if (IS_ENABLED(CONFIG_BLOCK) && io_bdev_nowait(I_BDEV(file->f_mapping->host))) @@ -2805,28 +2781,32 @@ static bool __io_file_supports_nowait(struct file *file, int rw) /* any ->read/write should understand O_NONBLOCK */ if (file->f_flags & O_NONBLOCK) return true; - - if (!(file->f_mode & FMODE_NOWAIT)) - return false; - - if (rw == READ) - return file->f_op->read_iter != NULL; - - return file->f_op->write_iter != NULL; + return file->f_mode & FMODE_NOWAIT; } -static bool io_file_supports_nowait(struct io_kiocb *req, int rw) +/* + * If we tracked the file through the SCM inflight mechanism, we could support + * any file. For now, just ensure that anything potentially problematic is done + * inline. + */ +static unsigned int io_file_get_flags(struct file *file) { - if (rw == READ && (req->flags & REQ_F_NOWAIT_READ)) - return true; - else if (rw == WRITE && (req->flags & REQ_F_NOWAIT_WRITE)) - return true; + umode_t mode = file_inode(file)->i_mode; + unsigned int res = 0; - return __io_file_supports_nowait(req->file, rw); + if (S_ISREG(mode)) + res |= FFS_ISREG; + if (__io_file_supports_nowait(file, mode)) + res |= FFS_NOWAIT; + return res; } -static int io_prep_rw(struct io_kiocb *req, const struct io_uring_sqe *sqe, - int rw) +static inline bool io_file_supports_nowait(struct io_kiocb *req) +{ + return req->flags & REQ_F_SUPPORT_NOWAIT; +} + +static int io_prep_rw(struct io_kiocb *req, const struct io_uring_sqe *sqe) { struct io_ring_ctx *ctx = req->ctx; struct kiocb *kiocb = &req->rw.kiocb; @@ -2834,16 +2814,15 @@ static int io_prep_rw(struct io_kiocb *req, const struct io_uring_sqe *sqe, unsigned ioprio; int ret; - if (!io_req_ffs_set(req) && S_ISREG(file_inode(file)->i_mode)) - req->flags |= REQ_F_ISREG; + if (!io_req_ffs_set(req)) + req->flags |= io_file_get_flags(file) << REQ_F_SUPPORT_NOWAIT_BIT; kiocb->ki_pos = READ_ONCE(sqe->off); if (kiocb->ki_pos == -1 && !(file->f_mode & FMODE_STREAM)) { req->flags |= REQ_F_CUR_POS; kiocb->ki_pos = file->f_pos; } - kiocb->ki_hint = ki_hint_validate(file_write_hint(kiocb->ki_filp)); - kiocb->ki_flags = iocb_flags(kiocb->ki_filp); + kiocb->ki_flags = iocb_flags(file); ret = kiocb_set_rw_flags(kiocb, READ_ONCE(sqe->rw_flags)); if (unlikely(ret)) return ret; @@ -2854,22 +2833,11 @@ static int io_prep_rw(struct io_kiocb *req, const struct io_uring_sqe *sqe, * reliably. If not, or it IOCB_NOWAIT is set, don't retry. */ if ((kiocb->ki_flags & IOCB_NOWAIT) || - ((file->f_flags & O_NONBLOCK) && !io_file_supports_nowait(req, rw))) + ((file->f_flags & O_NONBLOCK) && !io_file_supports_nowait(req))) req->flags |= REQ_F_NOWAIT; - ioprio = READ_ONCE(sqe->ioprio); - if (ioprio) { - ret = ioprio_check_cap(ioprio); - if (ret) - return ret; - - kiocb->ki_ioprio = ioprio; - } else - kiocb->ki_ioprio = get_current_ioprio(); - if (ctx->flags & IORING_SETUP_IOPOLL) { - if (!(kiocb->ki_flags & IOCB_DIRECT) || - !kiocb->ki_filp->f_op->iopoll) + if (!(kiocb->ki_flags & IOCB_DIRECT) || !file->f_op->iopoll) return -EOPNOTSUPP; kiocb->ki_flags |= IOCB_HIPRI | IOCB_ALLOC_CACHE; @@ -2881,12 +2849,18 @@ static int io_prep_rw(struct io_kiocb *req, const struct io_uring_sqe *sqe, kiocb->ki_complete = io_complete_rw; } - if (req->opcode == IORING_OP_READ_FIXED || - req->opcode == IORING_OP_WRITE_FIXED) { - req->imu = NULL; - io_req_set_rsrc_node(req); + ioprio = READ_ONCE(sqe->ioprio); + if (ioprio) { + ret = ioprio_check_cap(ioprio); + if (ret) + return ret; + + kiocb->ki_ioprio = ioprio; + } else { + kiocb->ki_ioprio = get_current_ioprio(); } + req->imu = NULL; req->rw.addr = READ_ONCE(sqe->addr); req->rw.len = READ_ONCE(sqe->len); req->buf_index = READ_ONCE(sqe->buf_index); @@ -2921,7 +2895,7 @@ static void kiocb_done(struct kiocb *kiocb, ssize_t ret, struct io_async_rw *io = req->async_data; /* add previously done IO, if any */ - if (io && io->bytes_done > 0) { + if (req_has_async_data(req) && io->bytes_done > 0) { if (ret < 0) ret = io->bytes_done; else @@ -2944,7 +2918,7 @@ static void kiocb_done(struct kiocb *kiocb, ssize_t ret, struct io_ring_ctx *ctx = req->ctx; req_set_fail(req); - if (!(issue_flags & IO_URING_F_NONBLOCK)) { + if (issue_flags & IO_URING_F_UNLOCKED) { mutex_lock(&ctx->uring_lock); __io_req_complete(req, issue_flags, ret, cflags); mutex_unlock(&ctx->uring_lock); @@ -3015,13 +2989,15 @@ static int __io_import_fixed(struct io_kiocb *req, int rw, struct iov_iter *iter static int io_import_fixed(struct io_kiocb *req, int rw, struct iov_iter *iter) { - struct io_ring_ctx *ctx = req->ctx; struct io_mapped_ubuf *imu = req->imu; u16 index, buf_index = req->buf_index; if (likely(!imu)) { + struct io_ring_ctx *ctx = req->ctx; + if (unlikely(buf_index >= ctx->nr_user_bufs)) return -EFAULT; + io_req_set_rsrc_node(req, ctx); index = array_index_nospec(buf_index, ctx->nr_user_bufs); imu = READ_ONCE(ctx->user_bufs[index]); req->imu = imu; @@ -3048,10 +3024,11 @@ static void io_ring_submit_lock(struct io_ring_ctx *ctx, bool needs_lock) } static struct io_buffer *io_buffer_select(struct io_kiocb *req, size_t *len, - int bgid, struct io_buffer *kbuf, - bool needs_lock) + int bgid, unsigned int issue_flags) { + struct io_buffer *kbuf = req->kbuf; struct io_buffer *head; + bool needs_lock = issue_flags & IO_URING_F_UNLOCKED; if (req->flags & REQ_F_BUFFER_SELECTED) return kbuf; @@ -3072,34 +3049,32 @@ static struct io_buffer *io_buffer_select(struct io_kiocb *req, size_t *len, } if (*len > kbuf->len) *len = kbuf->len; + req->flags |= REQ_F_BUFFER_SELECTED; + req->kbuf = kbuf; } else { kbuf = ERR_PTR(-ENOBUFS); } io_ring_submit_unlock(req->ctx, needs_lock); - return kbuf; } static void __user *io_rw_buffer_select(struct io_kiocb *req, size_t *len, - bool needs_lock) + unsigned int issue_flags) { struct io_buffer *kbuf; u16 bgid; - kbuf = (struct io_buffer *) (unsigned long) req->rw.addr; bgid = req->buf_index; - kbuf = io_buffer_select(req, len, bgid, kbuf, needs_lock); + kbuf = io_buffer_select(req, len, bgid, issue_flags); if (IS_ERR(kbuf)) return kbuf; - req->rw.addr = (u64) (unsigned long) kbuf; - req->flags |= REQ_F_BUFFER_SELECTED; return u64_to_user_ptr(kbuf->addr); } #ifdef CONFIG_COMPAT static ssize_t io_compat_import(struct io_kiocb *req, struct iovec *iov, - bool needs_lock) + unsigned int issue_flags) { struct compat_iovec __user *uiov; compat_ssize_t clen; @@ -3115,7 +3090,7 @@ static ssize_t io_compat_import(struct io_kiocb *req, struct iovec *iov, return -EINVAL; len = clen; - buf = io_rw_buffer_select(req, &len, needs_lock); + buf = io_rw_buffer_select(req, &len, issue_flags); if (IS_ERR(buf)) return PTR_ERR(buf); iov[0].iov_base = buf; @@ -3125,7 +3100,7 @@ static ssize_t io_compat_import(struct io_kiocb *req, struct iovec *iov, #endif static ssize_t __io_iov_buffer_select(struct io_kiocb *req, struct iovec *iov, - bool needs_lock) + unsigned int issue_flags) { struct iovec __user *uiov = u64_to_user_ptr(req->rw.addr); void __user *buf; @@ -3137,7 +3112,7 @@ static ssize_t __io_iov_buffer_select(struct io_kiocb *req, struct iovec *iov, len = iov[0].iov_len; if (len < 0) return -EINVAL; - buf = io_rw_buffer_select(req, &len, needs_lock); + buf = io_rw_buffer_select(req, &len, issue_flags); if (IS_ERR(buf)) return PTR_ERR(buf); iov[0].iov_base = buf; @@ -3146,12 +3121,11 @@ static ssize_t __io_iov_buffer_select(struct io_kiocb *req, struct iovec *iov, } static ssize_t io_iov_buffer_select(struct io_kiocb *req, struct iovec *iov, - bool needs_lock) + unsigned int issue_flags) { if (req->flags & REQ_F_BUFFER_SELECTED) { - struct io_buffer *kbuf; + struct io_buffer *kbuf = req->kbuf; - kbuf = (struct io_buffer *) (unsigned long) req->rw.addr; iov[0].iov_base = u64_to_user_ptr(kbuf->addr); iov[0].iov_len = kbuf->len; return 0; @@ -3161,52 +3135,72 @@ static ssize_t io_iov_buffer_select(struct io_kiocb *req, struct iovec *iov, #ifdef CONFIG_COMPAT if (req->ctx->compat) - return io_compat_import(req, iov, needs_lock); + return io_compat_import(req, iov, issue_flags); #endif - return __io_iov_buffer_select(req, iov, needs_lock); + return __io_iov_buffer_select(req, iov, issue_flags); } -static int io_import_iovec(int rw, struct io_kiocb *req, struct iovec **iovec, - struct iov_iter *iter, bool needs_lock) +static struct iovec *__io_import_iovec(int rw, struct io_kiocb *req, + struct io_rw_state *s, + unsigned int issue_flags) { - void __user *buf = u64_to_user_ptr(req->rw.addr); - size_t sqe_len = req->rw.len; + struct iov_iter *iter = &s->iter; u8 opcode = req->opcode; + struct iovec *iovec; + void __user *buf; + size_t sqe_len; ssize_t ret; - if (opcode == IORING_OP_READ_FIXED || opcode == IORING_OP_WRITE_FIXED) { - *iovec = NULL; - return io_import_fixed(req, rw, iter); - } + BUILD_BUG_ON(ERR_PTR(0) != NULL); + + if (opcode == IORING_OP_READ_FIXED || opcode == IORING_OP_WRITE_FIXED) + return ERR_PTR(io_import_fixed(req, rw, iter)); /* buffer index only valid with fixed read/write, or buffer select */ - if (req->buf_index && !(req->flags & REQ_F_BUFFER_SELECT)) - return -EINVAL; + if (unlikely(req->buf_index && !(req->flags & REQ_F_BUFFER_SELECT))) + return ERR_PTR(-EINVAL); + + buf = u64_to_user_ptr(req->rw.addr); + sqe_len = req->rw.len; if (opcode == IORING_OP_READ || opcode == IORING_OP_WRITE) { if (req->flags & REQ_F_BUFFER_SELECT) { - buf = io_rw_buffer_select(req, &sqe_len, needs_lock); + buf = io_rw_buffer_select(req, &sqe_len, issue_flags); if (IS_ERR(buf)) - return PTR_ERR(buf); + return ERR_CAST(buf); req->rw.len = sqe_len; } - ret = import_single_range(rw, buf, sqe_len, *iovec, iter); - *iovec = NULL; - return ret; + ret = import_single_range(rw, buf, sqe_len, s->fast_iov, iter); + return ERR_PTR(ret); } + iovec = s->fast_iov; if (req->flags & REQ_F_BUFFER_SELECT) { - ret = io_iov_buffer_select(req, *iovec, needs_lock); + ret = io_iov_buffer_select(req, iovec, issue_flags); if (!ret) - iov_iter_init(iter, rw, *iovec, 1, (*iovec)->iov_len); - *iovec = NULL; - return ret; + iov_iter_init(iter, rw, iovec, 1, iovec->iov_len); + return ERR_PTR(ret); } - return __import_iovec(rw, buf, sqe_len, UIO_FASTIOV, iovec, iter, + ret = __import_iovec(rw, buf, sqe_len, UIO_FASTIOV, &iovec, iter, req->ctx->compat); + if (unlikely(ret < 0)) + return ERR_PTR(ret); + return iovec; +} + +static inline int io_import_iovec(int rw, struct io_kiocb *req, + struct iovec **iovec, struct io_rw_state *s, + unsigned int issue_flags) +{ + *iovec = __io_import_iovec(rw, req, s, issue_flags); + if (unlikely(IS_ERR(*iovec))) + return PTR_ERR(*iovec); + + iov_iter_save_state(&s->iter, &s->iter_state); + return 0; } static inline loff_t *io_kiocb_ppos(struct kiocb *kiocb) @@ -3231,7 +3225,8 @@ static ssize_t loop_rw_iter(int rw, struct io_kiocb *req, struct iov_iter *iter) */ if (kiocb->ki_flags & IOCB_HIPRI) return -EOPNOTSUPP; - if (kiocb->ki_flags & IOCB_NOWAIT) + if ((kiocb->ki_flags & IOCB_NOWAIT) && + !(kiocb->ki_filp->f_flags & O_NONBLOCK)) return -EAGAIN; while (iov_iter_count(iter)) { @@ -3277,7 +3272,7 @@ static void io_req_map_rw(struct io_kiocb *req, const struct iovec *iovec, { struct io_async_rw *rw = req->async_data; - memcpy(&rw->iter, iter, sizeof(*iter)); + memcpy(&rw->s.iter, iter, sizeof(*iter)); rw->free_iovec = iovec; rw->bytes_done = 0; /* can only be fixed buffers, no need to do anything */ @@ -3286,33 +3281,36 @@ static void io_req_map_rw(struct io_kiocb *req, const struct iovec *iovec, if (!iovec) { unsigned iov_off = 0; - rw->iter.iov = rw->fast_iov; + rw->s.iter.iov = rw->s.fast_iov; if (iter->iov != fast_iov) { iov_off = iter->iov - fast_iov; - rw->iter.iov += iov_off; + rw->s.iter.iov += iov_off; } - if (rw->fast_iov != fast_iov) - memcpy(rw->fast_iov + iov_off, fast_iov + iov_off, + if (rw->s.fast_iov != fast_iov) + memcpy(rw->s.fast_iov + iov_off, fast_iov + iov_off, sizeof(struct iovec) * iter->nr_segs); } else { req->flags |= REQ_F_NEED_CLEANUP; } } -static inline int io_alloc_async_data(struct io_kiocb *req) +static inline bool io_alloc_async_data(struct io_kiocb *req) { WARN_ON_ONCE(!io_op_defs[req->opcode].async_size); req->async_data = kmalloc(io_op_defs[req->opcode].async_size, GFP_KERNEL); - return req->async_data == NULL; + if (req->async_data) { + req->flags |= REQ_F_ASYNC_DATA; + return false; + } + return true; } static int io_setup_async_rw(struct io_kiocb *req, const struct iovec *iovec, - const struct iovec *fast_iov, - struct iov_iter *iter, bool force) + struct io_rw_state *s, bool force) { if (!force && !io_op_defs[req->opcode].needs_async_setup) return 0; - if (!req->async_data) { + if (!req_has_async_data(req)) { struct io_async_rw *iorw; if (io_alloc_async_data(req)) { @@ -3320,10 +3318,10 @@ static int io_setup_async_rw(struct io_kiocb *req, const struct iovec *iovec, return -ENOMEM; } - io_req_map_rw(req, iovec, fast_iov, iter); + io_req_map_rw(req, iovec, s->fast_iov, &s->iter); iorw = req->async_data; /* we've copied and mapped the iter, ensure state is saved */ - iov_iter_save_state(&iorw->iter, &iorw->iter_state); + iov_iter_save_state(&iorw->s.iter, &iorw->s.iter_state); } return 0; } @@ -3331,10 +3329,11 @@ static int io_setup_async_rw(struct io_kiocb *req, const struct iovec *iovec, static inline int io_rw_prep_async(struct io_kiocb *req, int rw) { struct io_async_rw *iorw = req->async_data; - struct iovec *iov = iorw->fast_iov; + struct iovec *iov; int ret; - ret = io_import_iovec(rw, req, &iov, &iorw->iter, false); + /* submission path, ->uring_lock should already be taken */ + ret = io_import_iovec(rw, req, &iov, &iorw->s, 0); if (unlikely(ret < 0)) return ret; @@ -3342,7 +3341,6 @@ static inline int io_rw_prep_async(struct io_kiocb *req, int rw) iorw->free_iovec = iov; if (iov) req->flags |= REQ_F_NEED_CLEANUP; - iov_iter_save_state(&iorw->iter, &iorw->iter_state); return 0; } @@ -3350,7 +3348,7 @@ static int io_read_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) { if (unlikely(!(req->file->f_mode & FMODE_READ))) return -EBADF; - return io_prep_rw(req, sqe, READ); + return io_prep_rw(req, sqe); } /* @@ -3426,7 +3424,7 @@ static bool io_rw_should_retry(struct io_kiocb *req) static inline int io_iter_do_read(struct io_kiocb *req, struct iov_iter *iter) { - if (req->file->f_op->read_iter) + if (likely(req->file->f_op->read_iter)) return call_read_iter(req->file, &req->rw.kiocb, iter); else if (req->file->f_op->read) return loop_rw_iter(READ, req, iter); @@ -3442,43 +3440,40 @@ static bool need_read_all(struct io_kiocb *req) static int io_read(struct io_kiocb *req, unsigned int issue_flags) { - struct iovec inline_vecs[UIO_FASTIOV], *iovec = inline_vecs; + struct io_rw_state __s, *s = &__s; + struct iovec *iovec; struct kiocb *kiocb = &req->rw.kiocb; - struct iov_iter __iter, *iter = &__iter; - struct io_async_rw *rw = req->async_data; bool force_nonblock = issue_flags & IO_URING_F_NONBLOCK; - struct iov_iter_state __state, *state; + struct io_async_rw *rw; ssize_t ret, ret2; - if (rw) { - iter = &rw->iter; - state = &rw->iter_state; + if (!req_has_async_data(req)) { + ret = io_import_iovec(READ, req, &iovec, s, issue_flags); + if (unlikely(ret < 0)) + return ret; + } else { + rw = req->async_data; + s = &rw->s; /* * We come here from an earlier attempt, restore our state to * match in case it doesn't. It's cheap enough that we don't * need to make this conditional. */ - iov_iter_restore(iter, state); + iov_iter_restore(&s->iter, &s->iter_state); iovec = NULL; - } else { - ret = io_import_iovec(READ, req, &iovec, iter, !force_nonblock); - if (ret < 0) - return ret; - state = &__state; - iov_iter_save_state(iter, state); } - req->result = iov_iter_count(iter); + req->result = iov_iter_count(&s->iter); - /* Ensure we clear previously set non-block flag */ - if (!force_nonblock) - kiocb->ki_flags &= ~IOCB_NOWAIT; - else + if (force_nonblock) { + /* If the file doesn't support async, just async punt */ + if (unlikely(!io_file_supports_nowait(req))) { + ret = io_setup_async_rw(req, iovec, s, true); + return ret ?: -EAGAIN; + } kiocb->ki_flags |= IOCB_NOWAIT; - - /* If the file doesn't support async, just async punt */ - if (force_nonblock && !io_file_supports_nowait(req, READ)) { - ret = io_setup_async_rw(req, iovec, inline_vecs, iter, true); - return ret ?: -EAGAIN; + } else { + /* Ensure we clear previously set non-block flag */ + kiocb->ki_flags &= ~IOCB_NOWAIT; } ret = rw_verify_area(READ, req->file, io_kiocb_ppos(kiocb), req->result); @@ -3487,7 +3482,7 @@ static int io_read(struct io_kiocb *req, unsigned int issue_flags) return ret; } - ret = io_iter_do_read(req, iter); + ret = io_iter_do_read(req, &s->iter); if (ret == -EAGAIN || (req->flags & REQ_F_REISSUE)) { req->flags &= ~REQ_F_REISSUE; @@ -3500,7 +3495,7 @@ static int io_read(struct io_kiocb *req, unsigned int issue_flags) ret = 0; } else if (ret == -EIOCBQUEUED) { goto out_free; - } else if (ret <= 0 || ret == req->result || !force_nonblock || + } else if (ret == req->result || ret <= 0 || !force_nonblock || (req->flags & REQ_F_NOWAIT) || !need_read_all(req)) { /* read all, failed, already did sync or don't want to retry */ goto done; @@ -3511,22 +3506,19 @@ static int io_read(struct io_kiocb *req, unsigned int issue_flags) * untouched in case of error. Restore it and we'll advance it * manually if we need to. */ - iov_iter_restore(iter, state); + iov_iter_restore(&s->iter, &s->iter_state); - ret2 = io_setup_async_rw(req, iovec, inline_vecs, iter, true); + ret2 = io_setup_async_rw(req, iovec, s, true); if (ret2) return ret2; iovec = NULL; rw = req->async_data; + s = &rw->s; /* * Now use our persistent iterator and state, if we aren't already. * We've restored and mapped the iter to match. */ - if (iter != &rw->iter) { - iter = &rw->iter; - state = &rw->iter_state; - } do { /* @@ -3534,11 +3526,11 @@ static int io_read(struct io_kiocb *req, unsigned int issue_flags) * above or inside this loop. Advance the iter by the bytes * that were consumed. */ - iov_iter_advance(iter, ret); - if (!iov_iter_count(iter)) + iov_iter_advance(&s->iter, ret); + if (!iov_iter_count(&s->iter)) break; rw->bytes_done += ret; - iov_iter_save_state(iter, state); + iov_iter_save_state(&s->iter, &s->iter_state); /* if we can retry, do so with the callbacks armed */ if (!io_rw_should_retry(req)) { @@ -3552,12 +3544,12 @@ static int io_read(struct io_kiocb *req, unsigned int issue_flags) * desired page gets unlocked. We can also get a partial read * here, and if we do, then just retry at the new offset. */ - ret = io_iter_do_read(req, iter); + ret = io_iter_do_read(req, &s->iter); if (ret == -EIOCBQUEUED) return 0; /* we got some bytes, but not all. retry. */ kiocb->ki_flags &= ~IOCB_WAITQ; - iov_iter_restore(iter, state); + iov_iter_restore(&s->iter, &s->iter_state); } while (ret > 0); done: kiocb_done(kiocb, ret, issue_flags); @@ -3572,47 +3564,46 @@ static int io_write_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) { if (unlikely(!(req->file->f_mode & FMODE_WRITE))) return -EBADF; - return io_prep_rw(req, sqe, WRITE); + req->rw.kiocb.ki_hint = ki_hint_validate(file_write_hint(req->file)); + return io_prep_rw(req, sqe); } static int io_write(struct io_kiocb *req, unsigned int issue_flags) { - struct iovec inline_vecs[UIO_FASTIOV], *iovec = inline_vecs; + struct io_rw_state __s, *s = &__s; + struct iovec *iovec; struct kiocb *kiocb = &req->rw.kiocb; - struct iov_iter __iter, *iter = &__iter; - struct io_async_rw *rw = req->async_data; bool force_nonblock = issue_flags & IO_URING_F_NONBLOCK; - struct iov_iter_state __state, *state; ssize_t ret, ret2; - if (rw) { - iter = &rw->iter; - state = &rw->iter_state; - iov_iter_restore(iter, state); - iovec = NULL; - } else { - ret = io_import_iovec(WRITE, req, &iovec, iter, !force_nonblock); - if (ret < 0) + if (!req_has_async_data(req)) { + ret = io_import_iovec(WRITE, req, &iovec, s, issue_flags); + if (unlikely(ret < 0)) return ret; - state = &__state; - iov_iter_save_state(iter, state); + } else { + struct io_async_rw *rw = req->async_data; + + s = &rw->s; + iov_iter_restore(&s->iter, &s->iter_state); + iovec = NULL; } - req->result = iov_iter_count(iter); + req->result = iov_iter_count(&s->iter); + + if (force_nonblock) { + /* If the file doesn't support async, just async punt */ + if (unlikely(!io_file_supports_nowait(req))) + goto copy_iov; + + /* file path doesn't support NOWAIT for non-direct_IO */ + if (force_nonblock && !(kiocb->ki_flags & IOCB_DIRECT) && + (req->flags & REQ_F_ISREG)) + goto copy_iov; - /* Ensure we clear previously set non-block flag */ - if (!force_nonblock) - kiocb->ki_flags &= ~IOCB_NOWAIT; - else kiocb->ki_flags |= IOCB_NOWAIT; - - /* If the file doesn't support async, just async punt */ - if (force_nonblock && !io_file_supports_nowait(req, WRITE)) - goto copy_iov; - - /* file path doesn't support NOWAIT for non-direct_IO */ - if (force_nonblock && !(kiocb->ki_flags & IOCB_DIRECT) && - (req->flags & REQ_F_ISREG)) - goto copy_iov; + } else { + /* Ensure we clear previously set non-block flag */ + kiocb->ki_flags &= ~IOCB_NOWAIT; + } ret = rw_verify_area(WRITE, req->file, io_kiocb_ppos(kiocb), req->result); if (unlikely(ret)) @@ -3632,10 +3623,10 @@ static int io_write(struct io_kiocb *req, unsigned int issue_flags) } kiocb->ki_flags |= IOCB_WRITE; - if (req->file->f_op->write_iter) - ret2 = call_write_iter(req->file, kiocb, iter); + if (likely(req->file->f_op->write_iter)) + ret2 = call_write_iter(req->file, kiocb, &s->iter); else if (req->file->f_op->write) - ret2 = loop_rw_iter(WRITE, req, iter); + ret2 = loop_rw_iter(WRITE, req, &s->iter); else ret2 = -EINVAL; @@ -3655,14 +3646,14 @@ static int io_write(struct io_kiocb *req, unsigned int issue_flags) goto done; if (!force_nonblock || ret2 != -EAGAIN) { /* IOPOLL retry should happen for io-wq threads */ - if ((req->ctx->flags & IORING_SETUP_IOPOLL) && ret2 == -EAGAIN) + if (ret2 == -EAGAIN && (req->ctx->flags & IORING_SETUP_IOPOLL)) goto copy_iov; done: kiocb_done(kiocb, ret2, issue_flags); } else { copy_iov: - iov_iter_restore(iter, state); - ret = io_setup_async_rw(req, iovec, inline_vecs, iter, false); + iov_iter_restore(&s->iter, &s->iter_state); + ret = io_setup_async_rw(req, iovec, s, false); return ret ?: -EAGAIN; } out_free: @@ -3798,7 +3789,7 @@ static int io_mkdirat_prep(struct io_kiocb *req, return 0; } -static int io_mkdirat(struct io_kiocb *req, int issue_flags) +static int io_mkdirat(struct io_kiocb *req, unsigned int issue_flags) { struct io_mkdir *mkd = &req->mkdir; int ret; @@ -3847,7 +3838,7 @@ static int io_symlinkat_prep(struct io_kiocb *req, return 0; } -static int io_symlinkat(struct io_kiocb *req, int issue_flags) +static int io_symlinkat(struct io_kiocb *req, unsigned int issue_flags) { struct io_symlink *sl = &req->symlink; int ret; @@ -3897,7 +3888,7 @@ static int io_linkat_prep(struct io_kiocb *req, return 0; } -static int io_linkat(struct io_kiocb *req, int issue_flags) +static int io_linkat(struct io_kiocb *req, unsigned int issue_flags) { struct io_hardlink *lnk = &req->hardlink; int ret; @@ -4316,9 +4307,9 @@ static int io_remove_buffers(struct io_kiocb *req, unsigned int issue_flags) struct io_ring_ctx *ctx = req->ctx; struct io_buffer *head; int ret = 0; - bool force_nonblock = issue_flags & IO_URING_F_NONBLOCK; + bool needs_lock = issue_flags & IO_URING_F_UNLOCKED; - io_ring_submit_lock(ctx, !force_nonblock); + io_ring_submit_lock(ctx, needs_lock); lockdep_assert_held(&ctx->uring_lock); @@ -4331,7 +4322,7 @@ static int io_remove_buffers(struct io_kiocb *req, unsigned int issue_flags) /* complete before unlock, IOPOLL may need the lock */ __io_req_complete(req, issue_flags, ret, 0); - io_ring_submit_unlock(ctx, !force_nonblock); + io_ring_submit_unlock(ctx, needs_lock); return 0; } @@ -4403,9 +4394,9 @@ static int io_provide_buffers(struct io_kiocb *req, unsigned int issue_flags) struct io_ring_ctx *ctx = req->ctx; struct io_buffer *head, *list; int ret = 0; - bool force_nonblock = issue_flags & IO_URING_F_NONBLOCK; + bool needs_lock = issue_flags & IO_URING_F_UNLOCKED; - io_ring_submit_lock(ctx, !force_nonblock); + io_ring_submit_lock(ctx, needs_lock); lockdep_assert_held(&ctx->uring_lock); @@ -4421,7 +4412,7 @@ static int io_provide_buffers(struct io_kiocb *req, unsigned int issue_flags) req_set_fail(req); /* complete before unlock, IOPOLL may need the lock */ __io_req_complete(req, issue_flags, ret, 0); - io_ring_submit_unlock(ctx, !force_nonblock); + io_ring_submit_unlock(ctx, needs_lock); return 0; } @@ -4754,8 +4745,9 @@ static int io_sendmsg(struct io_kiocb *req, unsigned int issue_flags) if (unlikely(!sock)) return -ENOTSOCK; - kmsg = req->async_data; - if (!kmsg) { + if (req_has_async_data(req)) { + kmsg = req->async_data; + } else { ret = io_sendmsg_copy_hdr(req, &iomsg); if (ret) return ret; @@ -4914,23 +4906,16 @@ static int io_recvmsg_copy_hdr(struct io_kiocb *req, } static struct io_buffer *io_recv_buffer_select(struct io_kiocb *req, - bool needs_lock) + unsigned int issue_flags) { struct io_sr_msg *sr = &req->sr_msg; - struct io_buffer *kbuf; - kbuf = io_buffer_select(req, &sr->len, sr->bgid, sr->kbuf, needs_lock); - if (IS_ERR(kbuf)) - return kbuf; - - sr->kbuf = kbuf; - req->flags |= REQ_F_BUFFER_SELECTED; - return kbuf; + return io_buffer_select(req, &sr->len, sr->bgid, issue_flags); } static inline unsigned int io_put_recv_kbuf(struct io_kiocb *req) { - return io_put_kbuf(req, req->sr_msg.kbuf); + return io_put_kbuf(req, req->kbuf); } static int io_recvmsg_prep_async(struct io_kiocb *req) @@ -4978,8 +4963,9 @@ static int io_recvmsg(struct io_kiocb *req, unsigned int issue_flags) if (unlikely(!sock)) return -ENOTSOCK; - kmsg = req->async_data; - if (!kmsg) { + if (req_has_async_data(req)) { + kmsg = req->async_data; + } else { ret = io_recvmsg_copy_hdr(req, &iomsg); if (ret) return ret; @@ -4987,7 +4973,7 @@ static int io_recvmsg(struct io_kiocb *req, unsigned int issue_flags) } if (req->flags & REQ_F_BUFFER_SELECT) { - kbuf = io_recv_buffer_select(req, !force_nonblock); + kbuf = io_recv_buffer_select(req, issue_flags); if (IS_ERR(kbuf)) return PTR_ERR(kbuf); kmsg->fast_iov[0].iov_base = u64_to_user_ptr(kbuf->addr); @@ -5039,7 +5025,7 @@ static int io_recv(struct io_kiocb *req, unsigned int issue_flags) return -ENOTSOCK; if (req->flags & REQ_F_BUFFER_SELECT) { - kbuf = io_recv_buffer_select(req, !force_nonblock); + kbuf = io_recv_buffer_select(req, issue_flags); if (IS_ERR(kbuf)) return PTR_ERR(kbuf); buf = u64_to_user_ptr(kbuf->addr); @@ -5170,7 +5156,7 @@ static int io_connect(struct io_kiocb *req, unsigned int issue_flags) int ret; bool force_nonblock = issue_flags & IO_URING_F_NONBLOCK; - if (req->async_data) { + if (req_has_async_data(req)) { io = req->async_data; } else { ret = move_addr_to_kernel(req->connect.addr, @@ -5186,7 +5172,7 @@ static int io_connect(struct io_kiocb *req, unsigned int issue_flags) ret = __sys_connect_file(req->file, &io->address, req->connect.addr_len, file_flags); if ((ret == -EAGAIN || ret == -EINPROGRESS) && force_nonblock) { - if (req->async_data) + if (req_has_async_data(req)) return -EAGAIN; if (io_alloc_async_data(req)) { ret = -ENOMEM; @@ -5346,16 +5332,6 @@ static bool __io_poll_complete(struct io_kiocb *req, __poll_t mask) return !(flags & IORING_CQE_F_MORE); } -static inline bool io_poll_complete(struct io_kiocb *req, __poll_t mask) - __must_hold(&req->ctx->completion_lock) -{ - bool done; - - done = __io_poll_complete(req, mask); - io_commit_cqring(req->ctx); - return done; -} - static void io_poll_task_func(struct io_kiocb *req, bool *locked) { struct io_ring_ctx *ctx = req->ctx; @@ -5477,7 +5453,10 @@ static void __io_queue_proc(struct io_poll_iocb *poll, struct io_poll_table *pt, io_init_poll_iocb(poll, poll_one->events, io_poll_double_wake); req_ref_get(req); poll->wait.private = req; + *poll_ptr = poll; + if (req->opcode == IORING_OP_POLL_ADD) + req->flags |= REQ_F_ASYNC_DATA; } pt->nr_entries++; @@ -5601,17 +5580,13 @@ static int io_arm_poll_handler(struct io_kiocb *req) struct async_poll *apoll; struct io_poll_table ipt; __poll_t ret, mask = EPOLLONESHOT | POLLERR | POLLPRI; - int rw; - if (!req->file || !file_can_poll(req->file)) - return IO_APOLL_ABORTED; - if (req->flags & REQ_F_POLLED) - return IO_APOLL_ABORTED; if (!def->pollin && !def->pollout) return IO_APOLL_ABORTED; + if (!file_can_poll(req->file) || (req->flags & REQ_F_POLLED)) + return IO_APOLL_ABORTED; if (def->pollin) { - rw = READ; mask |= POLLIN | POLLRDNORM; /* If reading from MSG_ERRQUEUE using recvmsg, ignore POLLIN */ @@ -5619,14 +5594,9 @@ static int io_arm_poll_handler(struct io_kiocb *req) (req->sr_msg.msg_flags & MSG_ERRQUEUE)) mask &= ~POLLIN; } else { - rw = WRITE; mask |= POLLOUT | POLLWRNORM; } - /* if we can't nonblock try, then no point in arming a poll handler */ - if (!io_file_supports_nowait(req, rw)) - return IO_APOLL_ABORTED; - apoll = kmalloc(sizeof(*apoll), GFP_ATOMIC); if (unlikely(!apoll)) return IO_APOLL_ABORTED; @@ -5687,8 +5657,8 @@ static bool io_poll_remove_one(struct io_kiocb *req) /* * Returns true if we found and killed one or more poll requests */ -static bool io_poll_remove_all(struct io_ring_ctx *ctx, struct task_struct *tsk, - bool cancel_all) +static __cold bool io_poll_remove_all(struct io_ring_ctx *ctx, + struct task_struct *tsk, bool cancel_all) { struct hlist_node *tmp; struct io_kiocb *req; @@ -5842,7 +5812,8 @@ static int io_poll_add(struct io_kiocb *req, unsigned int issue_flags) if (mask) { /* no async, we'd stolen it */ ipt.error = 0; - done = io_poll_complete(req, mask); + done = __io_poll_complete(req, mask); + io_commit_cqring(req->ctx); } spin_unlock(&ctx->completion_lock); @@ -5918,7 +5889,10 @@ err: static void io_req_task_timeout(struct io_kiocb *req, bool *locked) { - req_set_fail(req); + struct io_timeout_data *data = req->async_data; + + if (!(data->flags & IORING_TIMEOUT_ETIME_SUCCESS)) + req_set_fail(req); io_req_complete_post(req, -ETIME, 0); } @@ -6124,7 +6098,8 @@ static int io_timeout_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe, if (off && is_timeout_link) return -EINVAL; flags = READ_ONCE(sqe->timeout_flags); - if (flags & ~(IORING_TIMEOUT_ABS | IORING_TIMEOUT_CLOCK_MASK)) + if (flags & ~(IORING_TIMEOUT_ABS | IORING_TIMEOUT_CLOCK_MASK | + IORING_TIMEOUT_ETIME_SUCCESS)) return -EINVAL; /* more than one clock specified is invalid, obviously */ if (hweight32(flags & IORING_TIMEOUT_CLOCK_MASK) > 1) @@ -6135,7 +6110,9 @@ static int io_timeout_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe, if (unlikely(off && !req->ctx->off_timeout_used)) req->ctx->off_timeout_used = true; - if (!req->async_data && io_alloc_async_data(req)) + if (WARN_ON_ONCE(req_has_async_data(req))) + return -EFAULT; + if (io_alloc_async_data(req)) return -ENOMEM; data = req->async_data; @@ -6292,6 +6269,7 @@ static int io_async_cancel(struct io_kiocb *req, unsigned int issue_flags) { struct io_ring_ctx *ctx = req->ctx; u64 sqe_addr = req->cancel.addr; + bool needs_lock = issue_flags & IO_URING_F_UNLOCKED; struct io_tctx_node *node; int ret; @@ -6300,7 +6278,7 @@ static int io_async_cancel(struct io_kiocb *req, unsigned int issue_flags) goto done; /* slow path, try all io-wq's */ - io_ring_submit_lock(ctx, !(issue_flags & IO_URING_F_NONBLOCK)); + io_ring_submit_lock(ctx, needs_lock); ret = -ENOENT; list_for_each_entry(node, &ctx->tctx_list, ctx_node) { struct io_uring_task *tctx = node->task->io_uring; @@ -6309,7 +6287,7 @@ static int io_async_cancel(struct io_kiocb *req, unsigned int issue_flags) if (ret != -ENOENT) break; } - io_ring_submit_unlock(ctx, !(issue_flags & IO_URING_F_NONBLOCK)); + io_ring_submit_unlock(ctx, needs_lock); done: if (ret < 0) req_set_fail(req); @@ -6336,6 +6314,7 @@ static int io_rsrc_update_prep(struct io_kiocb *req, static int io_files_update(struct io_kiocb *req, unsigned int issue_flags) { struct io_ring_ctx *ctx = req->ctx; + bool needs_lock = issue_flags & IO_URING_F_UNLOCKED; struct io_uring_rsrc_update2 up; int ret; @@ -6345,10 +6324,10 @@ static int io_files_update(struct io_kiocb *req, unsigned int issue_flags) up.tags = 0; up.resv = 0; - io_ring_submit_lock(ctx, !(issue_flags & IO_URING_F_NONBLOCK)); + io_ring_submit_lock(ctx, needs_lock); ret = __io_register_rsrc_update(ctx, IORING_RSRC_FILE, &up, req->rsrc_update.nr_args); - io_ring_submit_unlock(ctx, !(issue_flags & IO_URING_F_NONBLOCK)); + io_ring_submit_unlock(ctx, needs_lock); if (ret < 0) req_set_fail(req); @@ -6444,7 +6423,7 @@ static int io_req_prep_async(struct io_kiocb *req) { if (!io_op_defs[req->opcode].needs_async_setup) return 0; - if (WARN_ON_ONCE(req->async_data)) + if (WARN_ON_ONCE(req_has_async_data(req))) return -EFAULT; if (io_alloc_async_data(req)) return -EAGAIN; @@ -6476,68 +6455,39 @@ static u32 io_get_sequence(struct io_kiocb *req) return seq; } -static bool io_drain_req(struct io_kiocb *req) +static __cold void io_drain_req(struct io_kiocb *req) { - struct io_kiocb *pos; struct io_ring_ctx *ctx = req->ctx; struct io_defer_entry *de; int ret; - u32 seq; - - if (req->flags & REQ_F_FAIL) { - io_req_complete_fail_submit(req); - return true; - } - - /* - * If we need to drain a request in the middle of a link, drain the - * head request and the next request/link after the current link. - * Considering sequential execution of links, IOSQE_IO_DRAIN will be - * maintained for every request of our link. - */ - if (ctx->drain_next) { - req->flags |= REQ_F_IO_DRAIN; - ctx->drain_next = false; - } - /* not interested in head, start from the first linked */ - io_for_each_link(pos, req->link) { - if (pos->flags & REQ_F_IO_DRAIN) { - ctx->drain_next = true; - req->flags |= REQ_F_IO_DRAIN; - break; - } - } + u32 seq = io_get_sequence(req); /* Still need defer if there is pending req in defer list. */ - if (likely(list_empty_careful(&ctx->defer_list) && - !(req->flags & REQ_F_IO_DRAIN))) { + if (!req_need_defer(req, seq) && list_empty_careful(&ctx->defer_list)) { +queue: ctx->drain_active = false; - return false; + io_req_task_queue(req); + return; } - seq = io_get_sequence(req); - /* Still a chance to pass the sequence check */ - if (!req_need_defer(req, seq) && list_empty_careful(&ctx->defer_list)) - return false; - ret = io_req_prep_async(req); - if (ret) - goto fail; + if (ret) { +fail: + io_req_complete_failed(req, ret); + return; + } io_prep_async_link(req); de = kmalloc(sizeof(*de), GFP_KERNEL); if (!de) { ret = -ENOMEM; -fail: - io_req_complete_failed(req, ret); - return true; + goto fail; } spin_lock(&ctx->completion_lock); if (!req_need_defer(req, seq) && list_empty(&ctx->defer_list)) { spin_unlock(&ctx->completion_lock); kfree(de); - io_queue_async_work(req, NULL); - return true; + goto queue; } trace_io_uring_defer(ctx, req, req->user_data); @@ -6545,23 +6495,13 @@ fail: de->seq = seq; list_add_tail(&de->list, &ctx->defer_list); spin_unlock(&ctx->completion_lock); - return true; } static void io_clean_op(struct io_kiocb *req) { if (req->flags & REQ_F_BUFFER_SELECTED) { - switch (req->opcode) { - case IORING_OP_READV: - case IORING_OP_READ_FIXED: - case IORING_OP_READ: - kfree((void *)(unsigned long)req->rw.addr); - break; - case IORING_OP_RECVMSG: - case IORING_OP_RECV: - kfree(req->sr_msg.kbuf); - break; - } + kfree(req->kbuf); + req->kbuf = NULL; } if (req->flags & REQ_F_NEED_CLEANUP) { @@ -6626,17 +6566,19 @@ static void io_clean_op(struct io_kiocb *req) } if (req->flags & REQ_F_CREDS) put_cred(req->creds); - + if (req->flags & REQ_F_ASYNC_DATA) { + kfree(req->async_data); + req->async_data = NULL; + } req->flags &= ~IO_REQ_CLEAN_FLAGS; } static int io_issue_sqe(struct io_kiocb *req, unsigned int issue_flags) { - struct io_ring_ctx *ctx = req->ctx; const struct cred *creds = NULL; int ret; - if ((req->flags & REQ_F_CREDS) && req->creds != current_cred()) + if (unlikely((req->flags & REQ_F_CREDS) && req->creds != current_cred())) creds = override_creds(req->creds); switch (req->opcode) { @@ -6759,8 +6701,8 @@ static int io_issue_sqe(struct io_kiocb *req, unsigned int issue_flags) if (ret) return ret; /* If the op doesn't have a file, we're not polling for it */ - if ((ctx->flags & IORING_SETUP_IOPOLL) && req->file) - io_iopoll_req_issued(req); + if ((req->ctx->flags & IORING_SETUP_IOPOLL) && req->file) + io_iopoll_req_issued(req, issue_flags); return 0; } @@ -6776,6 +6718,8 @@ static struct io_wq_work *io_wq_free_work(struct io_wq_work *work) static void io_wq_submit_work(struct io_wq_work *work) { struct io_kiocb *req = container_of(work, struct io_kiocb, work); + unsigned int issue_flags = IO_URING_F_UNLOCKED; + bool needs_poll = false; struct io_kiocb *timeout; int ret = 0; @@ -6790,23 +6734,42 @@ static void io_wq_submit_work(struct io_wq_work *work) io_queue_linked_timeout(timeout); /* either cancelled or io-wq is dying, so don't touch tctx->iowq */ - if (work->flags & IO_WQ_WORK_CANCEL) - ret = -ECANCELED; - - if (!ret) { - do { - ret = io_issue_sqe(req, 0); - /* - * We can get EAGAIN for polled IO even though we're - * forcing a sync submission from here, since we can't - * wait for request slots on the block side. - */ - if (ret != -EAGAIN) - break; - cond_resched(); - } while (1); + if (work->flags & IO_WQ_WORK_CANCEL) { + io_req_task_queue_fail(req, -ECANCELED); + return; } + if (req->flags & REQ_F_FORCE_ASYNC) { + const struct io_op_def *def = &io_op_defs[req->opcode]; + bool opcode_poll = def->pollin || def->pollout; + + if (opcode_poll && file_can_poll(req->file)) { + needs_poll = true; + issue_flags |= IO_URING_F_NONBLOCK; + } + } + + do { + ret = io_issue_sqe(req, issue_flags); + if (ret != -EAGAIN) + break; + /* + * We can get EAGAIN for iopolled IO even though we're + * forcing a sync submission from here, since we can't + * wait for request slots on the block side. + */ + if (!needs_poll) { + cond_resched(); + continue; + } + + if (io_arm_poll_handler(req) == IO_APOLL_OK) + return; + /* aborted or ready, in either case retry blocking */ + needs_poll = false; + issue_flags &= ~IO_URING_F_NONBLOCK; + } while (1); + /* avoid locking problems by failing it from a clean context */ if (ret) io_req_task_queue_fail(req, ret); @@ -6830,12 +6793,7 @@ static void io_fixed_file_set(struct io_fixed_file *file_slot, struct file *file { unsigned long file_ptr = (unsigned long) file; - if (__io_file_supports_nowait(file, READ)) - file_ptr |= FFS_ASYNC_READ; - if (__io_file_supports_nowait(file, WRITE)) - file_ptr |= FFS_ASYNC_WRITE; - if (S_ISREG(file_inode(file)->i_mode)) - file_ptr |= FFS_ISREG; + file_ptr |= io_file_get_flags(file); file_slot->file_ptr = file_ptr; } @@ -6852,8 +6810,8 @@ static inline struct file *io_file_get_fixed(struct io_ring_ctx *ctx, file = (struct file *) (file_ptr & FFS_MASK); file_ptr &= ~FFS_MASK; /* mask in overlapping REQ_F and FFS bits */ - req->flags |= (file_ptr << REQ_F_NOWAIT_READ_BIT); - io_req_set_rsrc_node(req); + req->flags |= (file_ptr << REQ_F_SUPPORT_NOWAIT_BIT); + io_req_set_rsrc_node(req, ctx); return file; } @@ -6945,67 +6903,66 @@ static void io_queue_linked_timeout(struct io_kiocb *req) io_put_req(req); } -static void __io_queue_sqe(struct io_kiocb *req) +static void io_queue_sqe_arm_apoll(struct io_kiocb *req) + __must_hold(&req->ctx->uring_lock) +{ + struct io_kiocb *linked_timeout = io_prep_linked_timeout(req); + + switch (io_arm_poll_handler(req)) { + case IO_APOLL_READY: + if (linked_timeout) { + io_queue_linked_timeout(linked_timeout); + linked_timeout = NULL; + } + io_req_task_queue(req); + break; + case IO_APOLL_ABORTED: + /* + * Queued up for async execution, worker will release + * submit reference when the iocb is actually submitted. + */ + io_queue_async_work(req, NULL); + break; + } + + if (linked_timeout) + io_queue_linked_timeout(linked_timeout); +} + +static inline void __io_queue_sqe(struct io_kiocb *req) __must_hold(&req->ctx->uring_lock) { struct io_kiocb *linked_timeout; int ret; -issue_sqe: ret = io_issue_sqe(req, IO_URING_F_NONBLOCK|IO_URING_F_COMPLETE_DEFER); + if (req->flags & REQ_F_COMPLETE_INLINE) { + io_req_add_compl_list(req); + return; + } /* * We async punt it if the file wasn't marked NOWAIT, or if the file * doesn't support non-blocking read/write attempts */ if (likely(!ret)) { - if (req->flags & REQ_F_COMPLETE_INLINE) { - struct io_ring_ctx *ctx = req->ctx; - struct io_submit_state *state = &ctx->submit_state; - - state->compl_reqs[state->compl_nr++] = req; - if (state->compl_nr == ARRAY_SIZE(state->compl_reqs)) - io_submit_flush_completions(ctx); - return; - } - linked_timeout = io_prep_linked_timeout(req); if (linked_timeout) io_queue_linked_timeout(linked_timeout); } else if (ret == -EAGAIN && !(req->flags & REQ_F_NOWAIT)) { - linked_timeout = io_prep_linked_timeout(req); - - switch (io_arm_poll_handler(req)) { - case IO_APOLL_READY: - if (linked_timeout) - io_queue_linked_timeout(linked_timeout); - goto issue_sqe; - case IO_APOLL_ABORTED: - /* - * Queued up for async execution, worker will release - * submit reference when the iocb is actually submitted. - */ - io_queue_async_work(req, NULL); - break; - } - - if (linked_timeout) - io_queue_linked_timeout(linked_timeout); + io_queue_sqe_arm_apoll(req); } else { io_req_complete_failed(req, ret); } } -static inline void io_queue_sqe(struct io_kiocb *req) +static void io_queue_sqe_fallback(struct io_kiocb *req) __must_hold(&req->ctx->uring_lock) { - if (unlikely(req->ctx->drain_active) && io_drain_req(req)) - return; - - if (likely(!(req->flags & (REQ_F_FORCE_ASYNC | REQ_F_FAIL)))) { - __io_queue_sqe(req); - } else if (req->flags & REQ_F_FAIL) { + if (req->flags & REQ_F_FAIL) { io_req_complete_fail_submit(req); + } else if (unlikely(req->ctx->drain_active)) { + io_drain_req(req); } else { int ret = io_req_prep_async(req); @@ -7016,6 +6973,15 @@ static inline void io_queue_sqe(struct io_kiocb *req) } } +static inline void io_queue_sqe(struct io_kiocb *req) + __must_hold(&req->ctx->uring_lock) +{ + if (likely(!(req->flags & (REQ_F_FORCE_ASYNC | REQ_F_FAIL)))) + __io_queue_sqe(req); + else + io_queue_sqe_fallback(req); +} + /* * Check SQE restrictions (opcode and flags). * @@ -7025,9 +6991,6 @@ static inline bool io_check_restriction(struct io_ring_ctx *ctx, struct io_kiocb *req, unsigned int sqe_flags) { - if (likely(!ctx->restricted)) - return true; - if (!test_bit(req->opcode, ctx->restrictions.sqe_op)) return false; @@ -7042,16 +7005,35 @@ static inline bool io_check_restriction(struct io_ring_ctx *ctx, return true; } +static void io_init_req_drain(struct io_kiocb *req) +{ + struct io_ring_ctx *ctx = req->ctx; + struct io_kiocb *head = ctx->submit_state.link.head; + + ctx->drain_active = true; + if (head) { + /* + * If we need to drain a request in the middle of a link, drain + * the head request and the next request/link after the current + * link. Considering sequential execution of links, + * IOSQE_IO_DRAIN will be maintained for every request of our + * link. + */ + head->flags |= IOSQE_IO_DRAIN | REQ_F_FORCE_ASYNC; + ctx->drain_next = true; + } +} + static int io_init_req(struct io_ring_ctx *ctx, struct io_kiocb *req, const struct io_uring_sqe *sqe) __must_hold(&ctx->uring_lock) { - struct io_submit_state *state; unsigned int sqe_flags; - int personality, ret = 0; + int personality; + u8 opcode; /* req is partially pre-initialised, see io_preinit_req() */ - req->opcode = READ_ONCE(sqe->opcode); + req->opcode = opcode = READ_ONCE(sqe->opcode); /* same numerical values with corresponding REQ_F_*, safe to copy */ req->flags = sqe_flags = READ_ONCE(sqe->flags); req->user_data = READ_ONCE(sqe->user_data); @@ -7059,19 +7041,52 @@ static int io_init_req(struct io_ring_ctx *ctx, struct io_kiocb *req, req->fixed_rsrc_refs = NULL; req->task = current; - /* enforce forwards compatibility on users */ - if (unlikely(sqe_flags & ~SQE_VALID_FLAGS)) + if (unlikely(opcode >= IORING_OP_LAST)) { + req->opcode = 0; return -EINVAL; - if (unlikely(req->opcode >= IORING_OP_LAST)) - return -EINVAL; - if (!io_check_restriction(ctx, req, sqe_flags)) - return -EACCES; + } + if (unlikely(sqe_flags & ~SQE_COMMON_FLAGS)) { + /* enforce forwards compatibility on users */ + if (sqe_flags & ~SQE_VALID_FLAGS) + return -EINVAL; + if ((sqe_flags & IOSQE_BUFFER_SELECT) && + !io_op_defs[opcode].buffer_select) + return -EOPNOTSUPP; + if (sqe_flags & IOSQE_IO_DRAIN) + io_init_req_drain(req); + } + if (unlikely(ctx->restricted || ctx->drain_active || ctx->drain_next)) { + if (ctx->restricted && !io_check_restriction(ctx, req, sqe_flags)) + return -EACCES; + /* knock it to the slow queue path, will be drained there */ + if (ctx->drain_active) + req->flags |= REQ_F_FORCE_ASYNC; + /* if there is no link, we're at "next" request and need to drain */ + if (unlikely(ctx->drain_next) && !ctx->submit_state.link.head) { + ctx->drain_next = false; + ctx->drain_active = true; + req->flags |= IOSQE_IO_DRAIN | REQ_F_FORCE_ASYNC; + } + } - if ((sqe_flags & IOSQE_BUFFER_SELECT) && - !io_op_defs[req->opcode].buffer_select) - return -EOPNOTSUPP; - if (unlikely(sqe_flags & IOSQE_IO_DRAIN)) - ctx->drain_active = true; + if (io_op_defs[opcode].needs_file) { + struct io_submit_state *state = &ctx->submit_state; + + /* + * Plug now if we have more than 2 IO left after this, and the + * target is potentially a read/write to block based storage. + */ + if (state->need_plug && io_op_defs[opcode].plug) { + state->plug_started = true; + state->need_plug = false; + blk_start_plug_nr_ios(&state->plug, state->submit_nr); + } + + req->file = io_file_get(ctx, req, READ_ONCE(sqe->fd), + (sqe_flags & IOSQE_FIXED_FILE)); + if (unlikely(!req->file)) + return -EBADF; + } personality = READ_ONCE(sqe->personality); if (personality) { @@ -7081,27 +7096,8 @@ static int io_init_req(struct io_ring_ctx *ctx, struct io_kiocb *req, get_cred(req->creds); req->flags |= REQ_F_CREDS; } - state = &ctx->submit_state; - /* - * Plug now if we have more than 1 IO left after this, and the target - * is potentially a read/write to block based storage. - */ - if (!state->plug_started && state->ios_left > 1 && - io_op_defs[req->opcode].plug) { - blk_start_plug(&state->plug); - state->plug_started = true; - } - - if (io_op_defs[req->opcode].needs_file) { - req->file = io_file_get(ctx, req, READ_ONCE(sqe->fd), - (sqe_flags & IOSQE_FIXED_FILE)); - if (unlikely(!req->file)) - ret = -EBADF; - } - - state->ios_left--; - return ret; + return io_req_prep(req, sqe); } static int io_submit_sqe(struct io_ring_ctx *ctx, struct io_kiocb *req, @@ -7113,7 +7109,8 @@ static int io_submit_sqe(struct io_ring_ctx *ctx, struct io_kiocb *req, ret = io_init_req(ctx, req, sqe); if (unlikely(ret)) { -fail_req: + trace_io_uring_req_failed(sqe, ret); + /* fail even hard links since we don't submit */ if (link->head) { /* @@ -7136,10 +7133,6 @@ fail_req: return ret; } req_fail_link_node(req, ret); - } else { - ret = io_req_prep(req, sqe); - if (unlikely(ret)) - goto fail_req; } /* don't need @sqe from now on */ @@ -7169,33 +7162,32 @@ fail_req: link->last->link = req; link->last = req; + if (req->flags & (REQ_F_LINK | REQ_F_HARDLINK)) + return 0; /* last request of a link, enqueue the link */ - if (!(req->flags & (REQ_F_LINK | REQ_F_HARDLINK))) { - link->head = NULL; - io_queue_sqe(head); - } - } else { - if (req->flags & (REQ_F_LINK | REQ_F_HARDLINK)) { - link->head = req; - link->last = req; - } else { - io_queue_sqe(req); - } + link->head = NULL; + req = head; + } else if (req->flags & (REQ_F_LINK | REQ_F_HARDLINK)) { + link->head = req; + link->last = req; + return 0; } + io_queue_sqe(req); return 0; } /* * Batched submission is done, ensure local IO is flushed out. */ -static void io_submit_state_end(struct io_submit_state *state, - struct io_ring_ctx *ctx) +static void io_submit_state_end(struct io_ring_ctx *ctx) { + struct io_submit_state *state = &ctx->submit_state; + if (state->link.head) io_queue_sqe(state->link.head); - if (state->compl_nr) - io_submit_flush_completions(ctx); + /* flush only after queuing links as they can generate completions */ + io_submit_flush_completions(ctx); if (state->plug_started) blk_finish_plug(&state->plug); } @@ -7207,7 +7199,8 @@ static void io_submit_state_start(struct io_submit_state *state, unsigned int max_ios) { state->plug_started = false; - state->ios_left = max_ios; + state->need_plug = max_ios > 2; + state->submit_nr = max_ios; /* set only head, no need to init link_last in advance */ state->link.head = NULL; } @@ -7259,45 +7252,45 @@ static const struct io_uring_sqe *io_get_sqe(struct io_ring_ctx *ctx) static int io_submit_sqes(struct io_ring_ctx *ctx, unsigned int nr) __must_hold(&ctx->uring_lock) { + unsigned int entries = io_sqring_entries(ctx); int submitted = 0; + if (unlikely(!entries)) + return 0; /* make sure SQ entry isn't read before tail */ - nr = min3(nr, ctx->sq_entries, io_sqring_entries(ctx)); - if (!percpu_ref_tryget_many(&ctx->refs, nr)) - return -EAGAIN; + nr = min3(nr, ctx->sq_entries, entries); io_get_task_refs(nr); io_submit_state_start(&ctx->submit_state, nr); - while (submitted < nr) { + do { const struct io_uring_sqe *sqe; struct io_kiocb *req; - req = io_alloc_req(ctx); - if (unlikely(!req)) { + if (unlikely(!io_alloc_req_refill(ctx))) { if (!submitted) submitted = -EAGAIN; break; } + req = io_alloc_req(ctx); sqe = io_get_sqe(ctx); if (unlikely(!sqe)) { - list_add(&req->inflight_entry, &ctx->submit_state.free_list); + wq_stack_add_head(&req->comp_list, &ctx->submit_state.free_list); break; } /* will complete beyond this point, count as submitted */ submitted++; if (io_submit_sqe(ctx, req, sqe)) break; - } + } while (submitted < nr); if (unlikely(submitted != nr)) { int ref_used = (submitted == -EAGAIN) ? 0 : submitted; int unused = nr - ref_used; current->io_uring->cached_refs += unused; - percpu_ref_put_many(&ctx->refs, unused); } - io_submit_state_end(&ctx->submit_state, ctx); + io_submit_state_end(ctx); /* Commit SQ ring head once we've consumed and submitted all SQEs */ io_commit_sqring(ctx); @@ -7336,16 +7329,15 @@ static int __io_sq_thread(struct io_ring_ctx *ctx, bool cap_entries) if (cap_entries && to_submit > IORING_SQPOLL_CAP_ENTRIES_VALUE) to_submit = IORING_SQPOLL_CAP_ENTRIES_VALUE; - if (!list_empty(&ctx->iopoll_list) || to_submit) { - unsigned nr_events = 0; + if (!wq_list_empty(&ctx->iopoll_list) || to_submit) { const struct cred *creds = NULL; if (ctx->sq_creds != current_cred()) creds = override_creds(ctx->sq_creds); mutex_lock(&ctx->uring_lock); - if (!list_empty(&ctx->iopoll_list)) - io_do_iopoll(ctx, &nr_events, 0); + if (!wq_list_empty(&ctx->iopoll_list)) + io_do_iopoll(ctx, true); /* * Don't submit if refs are dying, good for io_uring_register(), @@ -7365,7 +7357,7 @@ static int __io_sq_thread(struct io_ring_ctx *ctx, bool cap_entries) return ret; } -static void io_sqd_update_thread_idle(struct io_sq_data *sqd) +static __cold void io_sqd_update_thread_idle(struct io_sq_data *sqd) { struct io_ring_ctx *ctx; unsigned sq_thread_idle = 0; @@ -7422,7 +7414,7 @@ static int io_sq_thread(void *data) list_for_each_entry(ctx, &sqd->ctx_list, sqd_list) { int ret = __io_sq_thread(ctx, cap_entries); - if (!sqt_spin && (ret > 0 || !list_empty(&ctx->iopoll_list))) + if (!sqt_spin && (ret > 0 || !wq_list_empty(&ctx->iopoll_list))) sqt_spin = true; } if (io_run_task_work()) @@ -7443,7 +7435,7 @@ static int io_sq_thread(void *data) io_ring_set_wakeup_flag(ctx); if ((ctx->flags & IORING_SETUP_IOPOLL) && - !list_empty_careful(&ctx->iopoll_list)) { + !wq_list_empty(&ctx->iopoll_list)) { needs_sched = false; break; } @@ -7619,7 +7611,7 @@ static void io_free_page_table(void **table, size_t size) kfree(table); } -static void **io_alloc_page_table(size_t size) +static __cold void **io_alloc_page_table(size_t size) { unsigned i, nr_tables = DIV_ROUND_UP(size, PAGE_SIZE); size_t init_size = size; @@ -7648,7 +7640,7 @@ static void io_rsrc_node_destroy(struct io_rsrc_node *ref_node) kfree(ref_node); } -static void io_rsrc_node_ref_zero(struct percpu_ref *ref) +static __cold void io_rsrc_node_ref_zero(struct percpu_ref *ref) { struct io_rsrc_node *node = container_of(ref, struct io_rsrc_node, refs); struct io_ring_ctx *ctx = node->rsrc_data->ctx; @@ -7694,10 +7686,13 @@ static struct io_rsrc_node *io_rsrc_node_alloc(struct io_ring_ctx *ctx) static void io_rsrc_node_switch(struct io_ring_ctx *ctx, struct io_rsrc_data *data_to_kill) + __must_hold(&ctx->uring_lock) { WARN_ON_ONCE(!ctx->rsrc_backup_node); WARN_ON_ONCE(data_to_kill && !ctx->rsrc_node); + io_rsrc_refs_drop(ctx); + if (data_to_kill) { struct io_rsrc_node *rsrc_node = ctx->rsrc_node; @@ -7725,7 +7720,8 @@ static int io_rsrc_node_switch_start(struct io_ring_ctx *ctx) return ctx->rsrc_backup_node ? 0 : -ENOMEM; } -static int io_rsrc_ref_quiesce(struct io_rsrc_data *data, struct io_ring_ctx *ctx) +static __cold int io_rsrc_ref_quiesce(struct io_rsrc_data *data, + struct io_ring_ctx *ctx) { int ret; @@ -7781,9 +7777,9 @@ static void io_rsrc_data_free(struct io_rsrc_data *data) kfree(data); } -static int io_rsrc_data_alloc(struct io_ring_ctx *ctx, rsrc_put_fn *do_put, - u64 __user *utags, unsigned nr, - struct io_rsrc_data **pdata) +static __cold int io_rsrc_data_alloc(struct io_ring_ctx *ctx, rsrc_put_fn *do_put, + u64 __user *utags, unsigned nr, + struct io_rsrc_data **pdata) { struct io_rsrc_data *data; int ret = -ENOMEM; @@ -8351,12 +8347,12 @@ static int io_install_fixed_file(struct io_kiocb *req, struct file *file, unsigned int issue_flags, u32 slot_index) { struct io_ring_ctx *ctx = req->ctx; - bool force_nonblock = issue_flags & IO_URING_F_NONBLOCK; + bool needs_lock = issue_flags & IO_URING_F_UNLOCKED; bool needs_switch = false; struct io_fixed_file *file_slot; int ret = -EBADF; - io_ring_submit_lock(ctx, !force_nonblock); + io_ring_submit_lock(ctx, needs_lock); if (file->f_op == &io_uring_fops) goto err; ret = -ENXIO; @@ -8397,7 +8393,7 @@ static int io_install_fixed_file(struct io_kiocb *req, struct file *file, err: if (needs_switch) io_rsrc_node_switch(ctx, ctx->file_data); - io_ring_submit_unlock(ctx, !force_nonblock); + io_ring_submit_unlock(ctx, needs_lock); if (ret) fput(file); return ret; @@ -8407,11 +8403,12 @@ static int io_close_fixed(struct io_kiocb *req, unsigned int issue_flags) { unsigned int offset = req->close.file_slot - 1; struct io_ring_ctx *ctx = req->ctx; + bool needs_lock = issue_flags & IO_URING_F_UNLOCKED; struct io_fixed_file *file_slot; struct file *file; int ret, i; - io_ring_submit_lock(ctx, !(issue_flags & IO_URING_F_NONBLOCK)); + io_ring_submit_lock(ctx, needs_lock); ret = -ENXIO; if (unlikely(!ctx->file_data)) goto out; @@ -8437,7 +8434,7 @@ static int io_close_fixed(struct io_kiocb *req, unsigned int issue_flags) io_rsrc_node_switch(ctx, ctx->file_data); ret = 0; out: - io_ring_submit_unlock(ctx, !(issue_flags & IO_URING_F_NONBLOCK)); + io_ring_submit_unlock(ctx, needs_lock); return ret; } @@ -8553,8 +8550,8 @@ static struct io_wq *io_init_wq_offload(struct io_ring_ctx *ctx, return io_wq_create(concurrency, &data); } -static int io_uring_alloc_task_context(struct task_struct *task, - struct io_ring_ctx *ctx) +static __cold int io_uring_alloc_task_context(struct task_struct *task, + struct io_ring_ctx *ctx) { struct io_uring_task *tctx; int ret; @@ -8601,8 +8598,8 @@ void __io_uring_free(struct task_struct *tsk) tsk->io_uring = NULL; } -static int io_sq_offload_create(struct io_ring_ctx *ctx, - struct io_uring_params *p) +static __cold int io_sq_offload_create(struct io_ring_ctx *ctx, + struct io_uring_params *p) { int ret; @@ -9213,29 +9210,25 @@ static void io_destroy_buffers(struct io_ring_ctx *ctx) } } -static void io_req_cache_free(struct list_head *list) -{ - struct io_kiocb *req, *nxt; - - list_for_each_entry_safe(req, nxt, list, inflight_entry) { - list_del(&req->inflight_entry); - kmem_cache_free(req_cachep, req); - } -} - static void io_req_caches_free(struct io_ring_ctx *ctx) { struct io_submit_state *state = &ctx->submit_state; + int nr = 0; mutex_lock(&ctx->uring_lock); - - if (state->free_reqs) { - kmem_cache_free_bulk(req_cachep, state->free_reqs, state->reqs); - state->free_reqs = 0; - } - io_flush_cached_locked_reqs(ctx, state); - io_req_cache_free(&state->free_list); + + while (state->free_list.next) { + struct io_wq_work_node *node; + struct io_kiocb *req; + + node = wq_stack_extract(&state->free_list); + req = container_of(node, struct io_kiocb, comp_list); + kmem_cache_free(req_cachep, req); + nr++; + } + if (nr) + percpu_ref_put_many(&ctx->refs, nr); mutex_unlock(&ctx->uring_lock); } @@ -9245,7 +9238,7 @@ static void io_wait_rsrc_data(struct io_rsrc_data *data) wait_for_completion(&data->done); } -static void io_ring_ctx_free(struct io_ring_ctx *ctx) +static __cold void io_ring_ctx_free(struct io_ring_ctx *ctx) { io_sq_thread_finish(ctx); @@ -9254,6 +9247,7 @@ static void io_ring_ctx_free(struct io_ring_ctx *ctx) ctx->mm_account = NULL; } + io_rsrc_refs_drop(ctx); /* __io_rsrc_put_work() may need uring_lock to progress, wait w/o it */ io_wait_rsrc_data(ctx->buf_data); io_wait_rsrc_data(ctx->file_data); @@ -9277,6 +9271,7 @@ static void io_ring_ctx_free(struct io_ring_ctx *ctx) if (ctx->rsrc_backup_node) io_rsrc_node_destroy(ctx->rsrc_backup_node); flush_delayed_work(&ctx->rsrc_put_work); + flush_delayed_work(&ctx->fallback_work); WARN_ON_ONCE(!list_empty(&ctx->rsrc_ref_list)); WARN_ON_ONCE(!llist_empty(&ctx->rsrc_put_llist)); @@ -9307,7 +9302,7 @@ static __poll_t io_uring_poll(struct file *file, poll_table *wait) struct io_ring_ctx *ctx = file->private_data; __poll_t mask = 0; - poll_wait(file, &ctx->poll_wait, wait); + poll_wait(file, &ctx->cq_wait, wait); /* * synchronizes with barrier from wq_has_sleeper call in * io_commit_cqring @@ -9354,7 +9349,7 @@ struct io_tctx_exit { struct io_ring_ctx *ctx; }; -static void io_tctx_exit_cb(struct callback_head *cb) +static __cold void io_tctx_exit_cb(struct callback_head *cb) { struct io_uring_task *tctx = current->io_uring; struct io_tctx_exit *work; @@ -9369,14 +9364,14 @@ static void io_tctx_exit_cb(struct callback_head *cb) complete(&work->completion); } -static bool io_cancel_ctx_cb(struct io_wq_work *work, void *data) +static __cold bool io_cancel_ctx_cb(struct io_wq_work *work, void *data) { struct io_kiocb *req = container_of(work, struct io_kiocb, work); return req->ctx == data; } -static void io_ring_exit_work(struct work_struct *work) +static __cold void io_ring_exit_work(struct work_struct *work) { struct io_ring_ctx *ctx = container_of(work, struct io_ring_ctx, exit_work); unsigned long timeout = jiffies + HZ * 60 * 5; @@ -9405,6 +9400,8 @@ static void io_ring_exit_work(struct work_struct *work) io_sq_thread_unpark(sqd); } + io_req_caches_free(ctx); + if (WARN_ON_ONCE(time_after(jiffies, timeout))) { /* there is little hope left, don't run it too often */ interval = HZ * 60; @@ -9431,7 +9428,6 @@ static void io_ring_exit_work(struct work_struct *work) ret = task_work_add(node->task, &exit.task_work, TWA_SIGNAL); if (WARN_ON_ONCE(ret)) continue; - wake_up_process(node->task); mutex_unlock(&ctx->uring_lock); wait_for_completion(&exit.completion); @@ -9445,8 +9441,8 @@ static void io_ring_exit_work(struct work_struct *work) } /* Returns true if we found and killed one or more timeouts */ -static bool io_kill_timeouts(struct io_ring_ctx *ctx, struct task_struct *tsk, - bool cancel_all) +static __cold bool io_kill_timeouts(struct io_ring_ctx *ctx, + struct task_struct *tsk, bool cancel_all) { struct io_kiocb *req, *tmp; int canceled = 0; @@ -9468,7 +9464,7 @@ static bool io_kill_timeouts(struct io_ring_ctx *ctx, struct task_struct *tsk, return canceled != 0; } -static void io_ring_ctx_wait_and_kill(struct io_ring_ctx *ctx) +static __cold void io_ring_ctx_wait_and_kill(struct io_ring_ctx *ctx) { unsigned long index; struct creds *creds; @@ -9530,8 +9526,9 @@ static bool io_cancel_task_cb(struct io_wq_work *work, void *data) return ret; } -static bool io_cancel_defer_files(struct io_ring_ctx *ctx, - struct task_struct *task, bool cancel_all) +static __cold bool io_cancel_defer_files(struct io_ring_ctx *ctx, + struct task_struct *task, + bool cancel_all) { struct io_defer_entry *de; LIST_HEAD(list); @@ -9556,7 +9553,7 @@ static bool io_cancel_defer_files(struct io_ring_ctx *ctx, return true; } -static bool io_uring_try_cancel_iowq(struct io_ring_ctx *ctx) +static __cold bool io_uring_try_cancel_iowq(struct io_ring_ctx *ctx) { struct io_tctx_node *node; enum io_wq_cancel cret; @@ -9580,9 +9577,9 @@ static bool io_uring_try_cancel_iowq(struct io_ring_ctx *ctx) return ret; } -static void io_uring_try_cancel_requests(struct io_ring_ctx *ctx, - struct task_struct *task, - bool cancel_all) +static __cold void io_uring_try_cancel_requests(struct io_ring_ctx *ctx, + struct task_struct *task, + bool cancel_all) { struct io_task_cancel cancel = { .task = task, .all = cancel_all, }; struct io_uring_task *tctx = task ? task->io_uring : NULL; @@ -9606,7 +9603,7 @@ static void io_uring_try_cancel_requests(struct io_ring_ctx *ctx, /* SQPOLL thread does its own polling */ if ((!(ctx->flags & IORING_SETUP_SQPOLL) && cancel_all) || (ctx->sq_data && ctx->sq_data->thread == current)) { - while (!list_empty_careful(&ctx->iopoll_list)) { + while (!wq_list_empty(&ctx->iopoll_list)) { io_iopoll_try_reap_events(ctx); ret = true; } @@ -9681,7 +9678,7 @@ static inline int io_uring_add_tctx_node(struct io_ring_ctx *ctx) /* * Remove this io_uring_file -> task mapping. */ -static void io_uring_del_tctx_node(unsigned long index) +static __cold void io_uring_del_tctx_node(unsigned long index) { struct io_uring_task *tctx = current->io_uring; struct io_tctx_node *node; @@ -9704,7 +9701,7 @@ static void io_uring_del_tctx_node(unsigned long index) kfree(node); } -static void io_uring_clean_tctx(struct io_uring_task *tctx) +static __cold void io_uring_clean_tctx(struct io_uring_task *tctx) { struct io_wq *wq = tctx->io_wq; struct io_tctx_node *node; @@ -9731,7 +9728,7 @@ static s64 tctx_inflight(struct io_uring_task *tctx, bool tracked) return percpu_counter_sum(&tctx->inflight); } -static void io_uring_drop_tctx_refs(struct task_struct *task) +static __cold void io_uring_drop_tctx_refs(struct task_struct *task) { struct io_uring_task *tctx = task->io_uring; unsigned int refs = tctx->cached_refs; @@ -9747,7 +9744,8 @@ static void io_uring_drop_tctx_refs(struct task_struct *task) * Find any io_uring ctx that this task has registered or done IO on, and cancel * requests. @sqd should be not-null IIF it's an SQPOLL thread cancellation. */ -static void io_uring_cancel_generic(bool cancel_all, struct io_sq_data *sqd) +static __cold void io_uring_cancel_generic(bool cancel_all, + struct io_sq_data *sqd) { struct io_uring_task *tctx = current->io_uring; struct io_ring_ctx *ctx; @@ -9840,7 +9838,7 @@ static void *io_uring_validate_mmap_request(struct file *file, #ifdef CONFIG_MMU -static int io_uring_mmap(struct file *file, struct vm_area_struct *vma) +static __cold int io_uring_mmap(struct file *file, struct vm_area_struct *vma) { size_t sz = vma->vm_end - vma->vm_start; unsigned long pfn; @@ -10025,7 +10023,7 @@ out_fput: } #ifdef CONFIG_PROC_FS -static int io_uring_show_cred(struct seq_file *m, unsigned int id, +static __cold int io_uring_show_cred(struct seq_file *m, unsigned int id, const struct cred *cred) { struct user_namespace *uns = seq_user_ns(m); @@ -10057,11 +10055,59 @@ static int io_uring_show_cred(struct seq_file *m, unsigned int id, return 0; } -static void __io_uring_show_fdinfo(struct io_ring_ctx *ctx, struct seq_file *m) +static __cold void __io_uring_show_fdinfo(struct io_ring_ctx *ctx, + struct seq_file *m) { struct io_sq_data *sq = NULL; + struct io_overflow_cqe *ocqe; + struct io_rings *r = ctx->rings; + unsigned int sq_mask = ctx->sq_entries - 1, cq_mask = ctx->cq_entries - 1; + unsigned int sq_head = READ_ONCE(r->sq.head); + unsigned int sq_tail = READ_ONCE(r->sq.tail); + unsigned int cq_head = READ_ONCE(r->cq.head); + unsigned int cq_tail = READ_ONCE(r->cq.tail); + unsigned int sq_entries, cq_entries; bool has_lock; - int i; + unsigned int i; + + /* + * we may get imprecise sqe and cqe info if uring is actively running + * since we get cached_sq_head and cached_cq_tail without uring_lock + * and sq_tail and cq_head are changed by userspace. But it's ok since + * we usually use these info when it is stuck. + */ + seq_printf(m, "SqMask:\t\t0x%x\n", sq_mask); + seq_printf(m, "SqHead:\t%u\n", sq_head); + seq_printf(m, "SqTail:\t%u\n", sq_tail); + seq_printf(m, "CachedSqHead:\t%u\n", ctx->cached_sq_head); + seq_printf(m, "CqMask:\t0x%x\n", cq_mask); + seq_printf(m, "CqHead:\t%u\n", cq_head); + seq_printf(m, "CqTail:\t%u\n", cq_tail); + seq_printf(m, "CachedCqTail:\t%u\n", ctx->cached_cq_tail); + seq_printf(m, "SQEs:\t%u\n", sq_tail - ctx->cached_sq_head); + sq_entries = min(sq_tail - sq_head, ctx->sq_entries); + for (i = 0; i < sq_entries; i++) { + unsigned int entry = i + sq_head; + unsigned int sq_idx = READ_ONCE(ctx->sq_array[entry & sq_mask]); + struct io_uring_sqe *sqe = &ctx->sq_sqes[sq_idx]; + + if (sq_idx > sq_mask) + continue; + sqe = &ctx->sq_sqes[sq_idx]; + seq_printf(m, "%5u: opcode:%d, fd:%d, flags:%x, user_data:%llu\n", + sq_idx, sqe->opcode, sqe->fd, sqe->flags, + sqe->user_data); + } + seq_printf(m, "CQEs:\t%u\n", cq_tail - cq_head); + cq_entries = min(cq_tail - cq_head, ctx->cq_entries); + for (i = 0; i < cq_entries; i++) { + unsigned int entry = i + cq_head; + struct io_uring_cqe *cqe = &r->cqes[entry & cq_mask]; + + seq_printf(m, "%5u: user_data:%llu, res:%d, flag:%x\n", + entry & cq_mask, cqe->user_data, cqe->res, + cqe->flags); + } /* * Avoid ABBA deadlock between the seq lock and the io_uring mutex, @@ -10103,7 +10149,10 @@ static void __io_uring_show_fdinfo(struct io_ring_ctx *ctx, struct seq_file *m) xa_for_each(&ctx->personalities, index, cred) io_uring_show_cred(m, index, cred); } - seq_printf(m, "PollList:\n"); + if (has_lock) + mutex_unlock(&ctx->uring_lock); + + seq_puts(m, "PollList:\n"); spin_lock(&ctx->completion_lock); for (i = 0; i < (1U << ctx->cancel_hash_bits); i++) { struct hlist_head *list = &ctx->cancel_hash[i]; @@ -10113,12 +10162,20 @@ static void __io_uring_show_fdinfo(struct io_ring_ctx *ctx, struct seq_file *m) seq_printf(m, " op=%d, task_works=%d\n", req->opcode, req->task->task_works != NULL); } + + seq_puts(m, "CqOverflowList:\n"); + list_for_each_entry(ocqe, &ctx->cq_overflow_list, list) { + struct io_uring_cqe *cqe = &ocqe->cqe; + + seq_printf(m, " user_data=%llu, res=%d, flags=%x\n", + cqe->user_data, cqe->res, cqe->flags); + + } + spin_unlock(&ctx->completion_lock); - if (has_lock) - mutex_unlock(&ctx->uring_lock); } -static void io_uring_show_fdinfo(struct seq_file *m, struct file *f) +static __cold void io_uring_show_fdinfo(struct seq_file *m, struct file *f) { struct io_ring_ctx *ctx = f->private_data; @@ -10142,8 +10199,8 @@ static const struct file_operations io_uring_fops = { #endif }; -static int io_allocate_scq_urings(struct io_ring_ctx *ctx, - struct io_uring_params *p) +static __cold int io_allocate_scq_urings(struct io_ring_ctx *ctx, + struct io_uring_params *p) { struct io_rings *rings; size_t size, sq_array_offset; @@ -10232,8 +10289,8 @@ static struct file *io_uring_get_file(struct io_ring_ctx *ctx) return file; } -static int io_uring_create(unsigned entries, struct io_uring_params *p, - struct io_uring_params __user *params) +static __cold int io_uring_create(unsigned entries, struct io_uring_params *p, + struct io_uring_params __user *params) { struct io_ring_ctx *ctx; struct file *file; @@ -10391,7 +10448,8 @@ SYSCALL_DEFINE2(io_uring_setup, u32, entries, return io_uring_setup(entries, params); } -static int io_probe(struct io_ring_ctx *ctx, void __user *arg, unsigned nr_args) +static __cold int io_probe(struct io_ring_ctx *ctx, void __user *arg, + unsigned nr_args) { struct io_uring_probe *p; size_t size; @@ -10447,8 +10505,8 @@ static int io_register_personality(struct io_ring_ctx *ctx) return id; } -static int io_register_restrictions(struct io_ring_ctx *ctx, void __user *arg, - unsigned int nr_args) +static __cold int io_register_restrictions(struct io_ring_ctx *ctx, + void __user *arg, unsigned int nr_args) { struct io_uring_restriction *res; size_t size; @@ -10582,7 +10640,7 @@ static int io_register_rsrc_update(struct io_ring_ctx *ctx, void __user *arg, return __io_register_rsrc_update(ctx, type, &up, up.nr); } -static int io_register_rsrc(struct io_ring_ctx *ctx, void __user *arg, +static __cold int io_register_rsrc(struct io_ring_ctx *ctx, void __user *arg, unsigned int size, unsigned int type) { struct io_uring_rsrc_register rr; @@ -10608,8 +10666,8 @@ static int io_register_rsrc(struct io_ring_ctx *ctx, void __user *arg, return -EINVAL; } -static int io_register_iowq_aff(struct io_ring_ctx *ctx, void __user *arg, - unsigned len) +static __cold int io_register_iowq_aff(struct io_ring_ctx *ctx, + void __user *arg, unsigned len) { struct io_uring_task *tctx = current->io_uring; cpumask_var_t new_mask; @@ -10635,7 +10693,7 @@ static int io_register_iowq_aff(struct io_ring_ctx *ctx, void __user *arg, return ret; } -static int io_unregister_iowq_aff(struct io_ring_ctx *ctx) +static __cold int io_unregister_iowq_aff(struct io_ring_ctx *ctx) { struct io_uring_task *tctx = current->io_uring; @@ -10645,8 +10703,8 @@ static int io_unregister_iowq_aff(struct io_ring_ctx *ctx) return io_wq_cpu_affinity(tctx->io_wq, NULL); } -static int io_register_iowq_max_workers(struct io_ring_ctx *ctx, - void __user *arg) +static __cold int io_register_iowq_max_workers(struct io_ring_ctx *ctx, + void __user *arg) __must_hold(&ctx->uring_lock) { struct io_tctx_node *node; @@ -10751,7 +10809,7 @@ static bool io_register_op_must_quiesce(int op) } } -static int io_ctx_quiesce(struct io_ring_ctx *ctx) +static __cold int io_ctx_quiesce(struct io_ring_ctx *ctx) { long ret; @@ -10766,10 +10824,14 @@ static int io_ctx_quiesce(struct io_ring_ctx *ctx) */ mutex_unlock(&ctx->uring_lock); do { - ret = wait_for_completion_interruptible(&ctx->ref_comp); - if (!ret) + ret = wait_for_completion_interruptible_timeout(&ctx->ref_comp, HZ); + if (ret) { + ret = min(0L, ret); break; + } + ret = io_run_task_work_sig(); + io_req_caches_free(ctx); } while (ret >= 0); mutex_lock(&ctx->uring_lock); @@ -11000,6 +11062,8 @@ static int __init io_uring_init(void) /* should fit into one byte */ BUILD_BUG_ON(SQE_VALID_FLAGS >= (1 << 8)); + BUILD_BUG_ON(SQE_COMMON_FLAGS >= (1 << 8)); + BUILD_BUG_ON((SQE_VALID_FLAGS | SQE_COMMON_FLAGS) != SQE_VALID_FLAGS); BUILD_BUG_ON(ARRAY_SIZE(io_op_defs) != IORING_OP_LAST); BUILD_BUG_ON(__REQ_F_LAST_BIT > 8 * sizeof(int)); diff --git a/fs/jfs/resize.c b/fs/jfs/resize.c index bde787c354fc..8b9a72ae5efa 100644 --- a/fs/jfs/resize.c +++ b/fs/jfs/resize.c @@ -86,8 +86,7 @@ int jfs_extendfs(struct super_block *sb, s64 newLVSize, int newLogSize) goto out; } - VolumeSize = i_size_read(sb->s_bdev->bd_inode) >> sb->s_blocksize_bits; - + VolumeSize = sb_bdev_nr_blocks(sb); if (VolumeSize) { if (newLVSize > VolumeSize) { printk(KERN_WARNING "jfs_extendfs: invalid size\n"); @@ -199,7 +198,7 @@ int jfs_extendfs(struct super_block *sb, s64 newLVSize, int newLogSize) txQuiesce(sb); /* Reset size of direct inode */ - sbi->direct_inode->i_size = i_size_read(sb->s_bdev->bd_inode); + sbi->direct_inode->i_size = bdev_nr_bytes(sb->s_bdev); if (sbi->mntflag & JFS_INLINELOG) { /* diff --git a/fs/jfs/super.c b/fs/jfs/super.c index 9030aeaf0f88..24cbc9946e01 100644 --- a/fs/jfs/super.c +++ b/fs/jfs/super.c @@ -284,8 +284,7 @@ static int parse_options(char *options, struct super_block *sb, s64 *newLVSize, } case Opt_resize_nosize: { - *newLVSize = i_size_read(sb->s_bdev->bd_inode) >> - sb->s_blocksize_bits; + *newLVSize = sb_bdev_nr_blocks(sb); if (*newLVSize == 0) pr_err("JFS: Cannot determine volume size\n"); break; @@ -551,7 +550,7 @@ static int jfs_fill_super(struct super_block *sb, void *data, int silent) ret = -ENOMEM; goto out_unload; } - inode->i_size = i_size_read(sb->s_bdev->bd_inode); + inode->i_size = bdev_nr_bytes(sb->s_bdev); inode->i_mapping->a_ops = &jfs_metapage_aops; inode_fake_hash(inode); mapping_set_gfp_mask(inode->i_mapping, GFP_NOFS); diff --git a/fs/nfs/blocklayout/dev.c b/fs/nfs/blocklayout/dev.c index acb1d22907da..5e56da748b2a 100644 --- a/fs/nfs/blocklayout/dev.c +++ b/fs/nfs/blocklayout/dev.c @@ -252,7 +252,7 @@ bl_parse_simple(struct nfs_server *server, struct pnfs_block_dev *d, d->bdev = bdev; - d->len = i_size_read(d->bdev->bd_inode); + d->len = bdev_nr_bytes(d->bdev); d->map = bl_map_simple; printk(KERN_INFO "pNFS: using block device %s\n", @@ -367,7 +367,7 @@ bl_parse_scsi(struct nfs_server *server, struct pnfs_block_dev *d, return PTR_ERR(bdev); d->bdev = bdev; - d->len = i_size_read(d->bdev->bd_inode); + d->len = bdev_nr_bytes(d->bdev); d->map = bl_map_simple; d->pr_key = v->scsi.pr_key; diff --git a/fs/nilfs2/ioctl.c b/fs/nilfs2/ioctl.c index 640ac8fe891e..1d0583cfd970 100644 --- a/fs/nilfs2/ioctl.c +++ b/fs/nilfs2/ioctl.c @@ -1107,7 +1107,7 @@ static int nilfs_ioctl_set_alloc_range(struct inode *inode, void __user *argp) goto out; ret = -ERANGE; - if (range[1] > i_size_read(inode->i_sb->s_bdev->bd_inode)) + if (range[1] > bdev_nr_bytes(inode->i_sb->s_bdev)) goto out; segbytes = nilfs->ns_blocks_per_segment * nilfs->ns_blocksize; diff --git a/fs/nilfs2/super.c b/fs/nilfs2/super.c index f6b2d280aab5..3134c0e42fd4 100644 --- a/fs/nilfs2/super.c +++ b/fs/nilfs2/super.c @@ -403,7 +403,7 @@ int nilfs_resize_fs(struct super_block *sb, __u64 newsize) int ret; ret = -ERANGE; - devsize = i_size_read(sb->s_bdev->bd_inode); + devsize = bdev_nr_bytes(sb->s_bdev); if (newsize > devsize) goto out; diff --git a/fs/nilfs2/the_nilfs.c b/fs/nilfs2/the_nilfs.c index c8bfc01da5d7..1bfcb5d3ea48 100644 --- a/fs/nilfs2/the_nilfs.c +++ b/fs/nilfs2/the_nilfs.c @@ -489,7 +489,7 @@ static int nilfs_load_super_block(struct the_nilfs *nilfs, { struct nilfs_super_block **sbp = nilfs->ns_sbp; struct buffer_head **sbh = nilfs->ns_sbh; - u64 sb2off = NILFS_SB2_OFFSET_BYTES(nilfs->ns_bdev->bd_inode->i_size); + u64 sb2off = NILFS_SB2_OFFSET_BYTES(bdev_nr_bytes(nilfs->ns_bdev)); int valid[2], swp = 0; sbp[0] = nilfs_read_super_block(sb, NILFS_SB_OFFSET_BYTES, blocksize, diff --git a/fs/ntfs/super.c b/fs/ntfs/super.c index 0d7e948cb29c..5ae8de09b271 100644 --- a/fs/ntfs/super.c +++ b/fs/ntfs/super.c @@ -2772,13 +2772,12 @@ static int ntfs_fill_super(struct super_block *sb, void *opt, const int silent) ntfs_debug("Set device block size to %i bytes (block size bits %i).", blocksize, sb->s_blocksize_bits); /* Determine the size of the device in units of block_size bytes. */ - if (!i_size_read(sb->s_bdev->bd_inode)) { + vol->nr_blocks = sb_bdev_nr_blocks(sb); + if (!vol->nr_blocks) { if (!silent) ntfs_error(sb, "Unable to determine device size."); goto err_out_now; } - vol->nr_blocks = i_size_read(sb->s_bdev->bd_inode) >> - sb->s_blocksize_bits; /* Read the boot sector and return unlocked buffer head to it. */ if (!(bh = read_ntfs_boot_sector(sb, silent))) { if (!silent) @@ -2816,8 +2815,7 @@ static int ntfs_fill_super(struct super_block *sb, void *opt, const int silent) goto err_out_now; } BUG_ON(blocksize != sb->s_blocksize); - vol->nr_blocks = i_size_read(sb->s_bdev->bd_inode) >> - sb->s_blocksize_bits; + vol->nr_blocks = sb_bdev_nr_blocks(sb); ntfs_debug("Changed device block size to %i bytes (block size " "bits %i) to match volume sector size.", blocksize, sb->s_blocksize_bits); diff --git a/fs/ntfs3/super.c b/fs/ntfs3/super.c index d41d76979e12..29813200c7af 100644 --- a/fs/ntfs3/super.c +++ b/fs/ntfs3/super.c @@ -921,7 +921,7 @@ static int ntfs_fill_super(struct super_block *sb, struct fs_context *fc) /* Parse boot. */ err = ntfs_init_from_boot(sb, rq ? queue_logical_block_size(rq) : 512, - bdev->bd_inode->i_size); + bdev_nr_bytes(bdev)); if (err) goto out; diff --git a/fs/pstore/blk.c b/fs/pstore/blk.c index 04ce58c939a0..5d1fbaffd66a 100644 --- a/fs/pstore/blk.c +++ b/fs/pstore/blk.c @@ -205,7 +205,6 @@ static ssize_t psblk_generic_blk_write(const char *buf, size_t bytes, static int __register_pstore_blk(struct pstore_device_info *dev, const char *devpath) { - struct inode *inode; int ret = -ENODEV; lockdep_assert_held(&pstore_blk_lock); @@ -217,14 +216,13 @@ static int __register_pstore_blk(struct pstore_device_info *dev, goto err; } - inode = file_inode(psblk_file); - if (!S_ISBLK(inode->i_mode)) { + if (!S_ISBLK(file_inode(psblk_file)->i_mode)) { pr_err("'%s' is not block device!\n", devpath); goto err_fput; } - inode = I_BDEV(psblk_file->f_mapping->host)->bd_inode; - dev->zone.total_size = i_size_read(inode); + dev->zone.total_size = + bdev_nr_bytes(I_BDEV(psblk_file->f_mapping->host)); ret = __register_pstore_device(dev); if (ret) diff --git a/fs/reiserfs/super.c b/fs/reiserfs/super.c index 58481f8d63d5..076f9ab94306 100644 --- a/fs/reiserfs/super.c +++ b/fs/reiserfs/super.c @@ -1199,9 +1199,7 @@ static int reiserfs_parse_options(struct super_block *s, if (!strcmp(arg, "auto")) { /* From JFS code, to auto-get the size. */ - *blocks = - i_size_read(s->s_bdev->bd_inode) >> s-> - s_blocksize_bits; + *blocks = sb_bdev_nr_blocks(s); } else { *blocks = simple_strtoul(arg, &p, 0); if (*p != '\0') { @@ -1986,9 +1984,7 @@ static int reiserfs_fill_super(struct super_block *s, void *data, int silent) * smaller than the filesystem. If the check fails then abort and * scream, because bad stuff will happen otherwise. */ - if (s->s_bdev && s->s_bdev->bd_inode - && i_size_read(s->s_bdev->bd_inode) < - sb_block_count(rs) * sb_blocksize(rs)) { + if (bdev_nr_bytes(s->s_bdev) < sb_block_count(rs) * sb_blocksize(rs)) { SWARN(silent, s, "", "Filesystem cannot be " "mounted because it is bigger than the device"); SWARN(silent, s, "", "You may need to run fsck " diff --git a/fs/squashfs/super.c b/fs/squashfs/super.c index 60d6951915f4..bb44ff4c5cc6 100644 --- a/fs/squashfs/super.c +++ b/fs/squashfs/super.c @@ -16,6 +16,7 @@ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt +#include #include #include #include @@ -179,8 +180,8 @@ static int squashfs_fill_super(struct super_block *sb, struct fs_context *fc) /* Check the filesystem does not extend beyond the end of the block device */ msblk->bytes_used = le64_to_cpu(sblk->bytes_used); - if (msblk->bytes_used < 0 || msblk->bytes_used > - i_size_read(sb->s_bdev->bd_inode)) + if (msblk->bytes_used < 0 || + msblk->bytes_used > bdev_nr_bytes(sb->s_bdev)) goto failed_mount; /* Check block size for sanity */ diff --git a/fs/udf/lowlevel.c b/fs/udf/lowlevel.c index f1094cdcd6cd..46d697172197 100644 --- a/fs/udf/lowlevel.c +++ b/fs/udf/lowlevel.c @@ -47,8 +47,7 @@ unsigned int udf_get_last_session(struct super_block *sb) unsigned long udf_get_last_block(struct super_block *sb) { - struct block_device *bdev = sb->s_bdev; - struct cdrom_device_info *cdi = disk_to_cdi(bdev->bd_disk); + struct cdrom_device_info *cdi = disk_to_cdi(sb->s_bdev->bd_disk); unsigned long lblock = 0; /* @@ -56,7 +55,7 @@ unsigned long udf_get_last_block(struct super_block *sb) * Try using the device size... */ if (!cdi || cdrom_get_last_written(cdi, &lblock) || lblock == 0) - lblock = i_size_read(bdev->bd_inode) >> sb->s_blocksize_bits; + lblock = sb_bdev_nr_blocks(sb); if (lblock) return lblock - 1; diff --git a/fs/udf/super.c b/fs/udf/super.c index b2d7c57d0688..34247fba6df9 100644 --- a/fs/udf/super.c +++ b/fs/udf/super.c @@ -1175,8 +1175,7 @@ static int udf_load_vat(struct super_block *sb, int p_index, int type1_index) struct udf_inode_info *vati; uint32_t pos; struct virtualAllocationTable20 *vat20; - sector_t blocks = i_size_read(sb->s_bdev->bd_inode) >> - sb->s_blocksize_bits; + sector_t blocks = sb_bdev_nr_blocks(sb); udf_find_vat_block(sb, p_index, type1_index, sbi->s_last_block); if (!sbi->s_vat_inode && @@ -1838,8 +1837,7 @@ static int udf_check_anchor_block(struct super_block *sb, sector_t block, int ret; if (UDF_QUERY_FLAG(sb, UDF_FLAG_VARCONV) && - udf_fixed_to_variable(block) >= - i_size_read(sb->s_bdev->bd_inode) >> sb->s_blocksize_bits) + udf_fixed_to_variable(block) >= sb_bdev_nr_blocks(sb)) return -EAGAIN; bh = udf_read_tagged(sb, block, block, &ident); @@ -1901,8 +1899,7 @@ static int udf_scan_anchors(struct super_block *sb, sector_t *lastblock, last[last_count++] = *lastblock - 152; for (i = 0; i < last_count; i++) { - if (last[i] >= i_size_read(sb->s_bdev->bd_inode) >> - sb->s_blocksize_bits) + if (last[i] >= sb_bdev_nr_blocks(sb)) continue; ret = udf_check_anchor_block(sb, last[i], fileset); if (ret != -EAGAIN) { diff --git a/include/linux/ata.h b/include/linux/ata.h index 1b44f40c7700..199e47e97d64 100644 --- a/include/linux/ata.h +++ b/include/linux/ata.h @@ -329,6 +329,7 @@ enum { ATA_LOG_SECURITY = 0x06, ATA_LOG_SATA_SETTINGS = 0x08, ATA_LOG_ZONED_INFORMATION = 0x09, + ATA_LOG_CONCURRENT_POSITIONING_RANGES = 0x47, /* Identify device SATA settings log:*/ ATA_LOG_DEVSLP_OFFSET = 0x30, diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index f77a44a324e8..40f0f80a4f20 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -20,8 +20,26 @@ struct cgroup_subsys_state; typedef void (bio_end_io_t) (struct bio *); struct bio_crypt_ctx; +/* + * The basic unit of block I/O is a sector. It is used in a number of contexts + * in Linux (blk, bio, genhd). The size of one sector is 512 = 2**9 + * bytes. Variables of type sector_t represent an offset or size that is a + * multiple of 512 bytes. Hence these two constants. + */ +#ifndef SECTOR_SHIFT +#define SECTOR_SHIFT 9 +#endif +#ifndef SECTOR_SIZE +#define SECTOR_SIZE (1 << SECTOR_SHIFT) +#endif + +#define PAGE_SECTORS_SHIFT (PAGE_SHIFT - SECTOR_SHIFT) +#define PAGE_SECTORS (1 << PAGE_SECTORS_SHIFT) +#define SECTOR_MASK (PAGE_SECTORS - 1) + struct block_device { sector_t bd_start_sect; + sector_t bd_nr_sectors; struct disk_stats __percpu *bd_stats; unsigned long bd_stamp; bool bd_read_only; /* read-only policy */ diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index d2d627e2c782..ed5be661dd0c 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -621,23 +621,6 @@ static inline struct request_queue *bdev_get_queue(struct block_device *bdev) return bdev->bd_queue; /* this is never NULL */ } -/* - * The basic unit of block I/O is a sector. It is used in a number of contexts - * in Linux (blk, bio, genhd). The size of one sector is 512 = 2**9 - * bytes. Variables of type sector_t represent an offset or size that is a - * multiple of 512 bytes. Hence these two constants. - */ -#ifndef SECTOR_SHIFT -#define SECTOR_SHIFT 9 -#endif -#ifndef SECTOR_SIZE -#define SECTOR_SIZE (1 << SECTOR_SHIFT) -#endif - -#define PAGE_SECTORS_SHIFT (PAGE_SHIFT - SECTOR_SHIFT) -#define PAGE_SECTORS (1 << PAGE_SECTORS_SHIFT) -#define SECTOR_MASK (PAGE_SECTORS - 1) - #ifdef CONFIG_BLK_DEV_ZONED /* Helper to convert BLK_ZONE_ZONE_XXX to its string format XXX */ diff --git a/include/linux/cdrom.h b/include/linux/cdrom.h index c4fef00abdf3..0a89f111e00e 100644 --- a/include/linux/cdrom.h +++ b/include/linux/cdrom.h @@ -64,6 +64,7 @@ struct cdrom_device_info { int for_data; int (*exit)(struct cdrom_device_info *); int mrw_mode_page; + __s64 last_media_change_ms; }; struct cdrom_device_ops { diff --git a/include/linux/genhd.h b/include/linux/genhd.h index 13f313ab99e7..59eabbc3a36b 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -245,7 +245,12 @@ static inline sector_t get_start_sect(struct block_device *bdev) static inline sector_t bdev_nr_sectors(struct block_device *bdev) { - return i_size_read(bdev->bd_inode) >> 9; + return bdev->bd_nr_sectors; +} + +static inline loff_t bdev_nr_bytes(struct block_device *bdev) +{ + return bdev_nr_sectors(bdev) << SECTOR_SHIFT; } static inline sector_t get_capacity(struct gendisk *disk) @@ -253,6 +258,12 @@ static inline sector_t get_capacity(struct gendisk *disk) return bdev_nr_sectors(disk->part0); } +static inline u64 sb_bdev_nr_blocks(struct super_block *sb) +{ + return bdev_nr_sectors(sb->s_bdev) >> + (sb->s_blocksize_bits - SECTOR_SHIFT); +} + int bdev_disk_changed(struct gendisk *disk, bool invalidate); void blk_drop_partitions(struct gendisk *disk); diff --git a/include/linux/libata.h b/include/linux/libata.h index c0c64f03e107..236ec689056a 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -676,6 +676,18 @@ struct ata_ering { struct ata_ering_entry ring[ATA_ERING_SIZE]; }; +struct ata_cpr { + u8 num; + u8 num_storage_elements; + u64 start_lba; + u64 num_lbas; +}; + +struct ata_cpr_log { + u8 nr_cpr; + struct ata_cpr cpr[]; +}; + struct ata_device { struct ata_link *link; unsigned int devno; /* 0 or 1 */ @@ -735,6 +747,9 @@ struct ata_device { u32 zac_zones_optimal_nonseq; u32 zac_zones_max_open; + /* Concurrent positioning ranges */ + struct ata_cpr_log *cpr_log; + /* error history */ int spdn_cnt; /* ering is CLEAR_END, read comment above CLEAR_END */ diff --git a/include/linux/nvme-fc-driver.h b/include/linux/nvme-fc-driver.h index 2a38f2b477a5..cb909edb76c4 100644 --- a/include/linux/nvme-fc-driver.h +++ b/include/linux/nvme-fc-driver.h @@ -7,6 +7,7 @@ #define _NVME_FC_DRIVER_H 1 #include +#include /* @@ -497,6 +498,8 @@ struct nvme_fc_port_template { int (*xmt_ls_rsp)(struct nvme_fc_local_port *localport, struct nvme_fc_remote_port *rport, struct nvmefc_ls_rsp *ls_rsp); + void (*map_queues)(struct nvme_fc_local_port *localport, + struct blk_mq_queue_map *map); u32 max_hw_queues; u16 max_sgl_segments; @@ -779,6 +782,10 @@ struct nvmet_fc_target_port { * LS received. * Entrypoint is Mandatory. * + * @map_queues: This functions lets the driver expose the queue mapping + * to the block layer. + * Entrypoint is Optional. + * * @fcp_op: Called to perform a data transfer or transmit a response. * The nvmefc_tgt_fcp_req structure is the same LLDD-supplied * exchange structure specified in the nvmet_fc_rcv_fcp_req() call diff --git a/include/linux/nvme-rdma.h b/include/linux/nvme-rdma.h index 3ec8e50efa16..4dd7e6fe92fb 100644 --- a/include/linux/nvme-rdma.h +++ b/include/linux/nvme-rdma.h @@ -6,6 +6,8 @@ #ifndef _LINUX_NVME_RDMA_H #define _LINUX_NVME_RDMA_H +#define NVME_RDMA_MAX_QUEUE_SIZE 128 + enum nvme_rdma_cm_fmt { NVME_RDMA_CM_FMT_1_0 = 0x0, }; diff --git a/include/linux/nvme.h b/include/linux/nvme.h index b7c4c4130b65..855dd9b3e84b 100644 --- a/include/linux/nvme.h +++ b/include/linux/nvme.h @@ -27,8 +27,20 @@ #define NVME_NSID_ALL 0xffffffff enum nvme_subsys_type { - NVME_NQN_DISC = 1, /* Discovery type target subsystem */ - NVME_NQN_NVME = 2, /* NVME type target subsystem */ + /* Referral to another discovery type target subsystem */ + NVME_NQN_DISC = 1, + + /* NVME type target subsystem */ + NVME_NQN_NVME = 2, + + /* Current discovery type target subsystem */ + NVME_NQN_CURR = 3, +}; + +enum nvme_ctrl_type { + NVME_CTRL_IO = 1, /* I/O controller */ + NVME_CTRL_DISC = 2, /* Discovery controller */ + NVME_CTRL_ADMIN = 3, /* Administrative controller */ }; /* Address Family codes for Discovery Log Page entry ADRFAM field */ @@ -244,7 +256,9 @@ struct nvme_id_ctrl { __le32 rtd3e; __le32 oaes; __le32 ctratt; - __u8 rsvd100[28]; + __u8 rsvd100[11]; + __u8 cntrltype; + __u8 fguid[16]; __le16 crdt1; __le16 crdt2; __le16 crdt3; @@ -312,6 +326,7 @@ struct nvme_id_ctrl { }; enum { + NVME_CTRL_CMIC_MULTI_PORT = 1 << 0, NVME_CTRL_CMIC_MULTI_CTRL = 1 << 1, NVME_CTRL_CMIC_ANA = 1 << 3, NVME_CTRL_ONCS_COMPARE = 1 << 0, @@ -1303,6 +1318,12 @@ struct nvmf_common_command { #define MAX_DISC_LOGS 255 +/* Discovery log page entry flags (EFLAGS): */ +enum { + NVME_DISC_EFLAGS_EPCSD = (1 << 1), + NVME_DISC_EFLAGS_DUPRETINFO = (1 << 0), +}; + /* Discovery log page entry */ struct nvmf_disc_rsp_page_entry { __u8 trtype; @@ -1312,7 +1333,8 @@ struct nvmf_disc_rsp_page_entry { __le16 portid; __le16 cntlid; __le16 asqsz; - __u8 resv8[22]; + __le16 eflags; + __u8 resv10[20]; char trsvcid[NVMF_TRSVCID_SIZE]; __u8 resv64[192]; char subnqn[NVMF_NQN_FIELD_LEN]; diff --git a/include/trace/events/io_uring.h b/include/trace/events/io_uring.h index 0dd30de00e5b..7346f0164cf4 100644 --- a/include/trace/events/io_uring.h +++ b/include/trace/events/io_uring.h @@ -6,6 +6,7 @@ #define _TRACE_IO_URING_H #include +#include struct io_wq_work; @@ -497,6 +498,66 @@ TRACE_EVENT(io_uring_task_run, (unsigned long long) __entry->user_data) ); +/* + * io_uring_req_failed - called when an sqe is errored dring submission + * + * @sqe: pointer to the io_uring_sqe that failed + * @error: error it failed with + * + * Allows easier diagnosing of malformed requests in production systems. + */ +TRACE_EVENT(io_uring_req_failed, + + TP_PROTO(const struct io_uring_sqe *sqe, int error), + + TP_ARGS(sqe, error), + + TP_STRUCT__entry ( + __field( u8, opcode ) + __field( u8, flags ) + __field( u8, ioprio ) + __field( u64, off ) + __field( u64, addr ) + __field( u32, len ) + __field( u32, op_flags ) + __field( u64, user_data ) + __field( u16, buf_index ) + __field( u16, personality ) + __field( u32, file_index ) + __field( u64, pad1 ) + __field( u64, pad2 ) + __field( int, error ) + ), + + TP_fast_assign( + __entry->opcode = sqe->opcode; + __entry->flags = sqe->flags; + __entry->ioprio = sqe->ioprio; + __entry->off = sqe->off; + __entry->addr = sqe->addr; + __entry->len = sqe->len; + __entry->op_flags = sqe->rw_flags; + __entry->user_data = sqe->user_data; + __entry->buf_index = sqe->buf_index; + __entry->personality = sqe->personality; + __entry->file_index = sqe->file_index; + __entry->pad1 = sqe->__pad2[0]; + __entry->pad2 = sqe->__pad2[1]; + __entry->error = error; + ), + + TP_printk("op %d, flags=0x%x, prio=%d, off=%llu, addr=%llu, " + "len=%u, rw_flags=0x%x, user_data=0x%llx, buf_index=%d, " + "personality=%d, file_index=%d, pad=0x%llx/%llx, error=%d", + __entry->opcode, __entry->flags, __entry->ioprio, + (unsigned long long)__entry->off, + (unsigned long long) __entry->addr, __entry->len, + __entry->op_flags, (unsigned long long) __entry->user_data, + __entry->buf_index, __entry->personality, __entry->file_index, + (unsigned long long) __entry->pad1, + (unsigned long long) __entry->pad2, __entry->error) +); + #endif /* _TRACE_IO_URING_H */ /* This part must be outside protection */ diff --git a/include/uapi/linux/cdrom.h b/include/uapi/linux/cdrom.h index 6c34f6e2f1f7..804ff8d98f71 100644 --- a/include/uapi/linux/cdrom.h +++ b/include/uapi/linux/cdrom.h @@ -147,6 +147,8 @@ #define CDROM_NEXT_WRITABLE 0x5394 /* get next writable block */ #define CDROM_LAST_WRITTEN 0x5395 /* get last block written on disc */ +#define CDROM_TIMED_MEDIA_CHANGE 0x5396 /* get the timestamp of the last media change */ + /******************************************************* * CDROM IOCTL structures *******************************************************/ @@ -295,6 +297,23 @@ struct cdrom_generic_command }; }; +/* This struct is used by CDROM_TIMED_MEDIA_CHANGE */ +struct cdrom_timed_media_change_info { + __s64 last_media_change; /* Timestamp of the last detected media + * change in ms. May be set by caller, + * updated upon successful return of + * ioctl. + */ + __u64 media_flags; /* Flags returned by ioctl to indicate + * media status. + */ +}; +#define MEDIA_CHANGED_FLAG 0x1 /* Last detected media change was more + * recent than last_media_change set by + * caller. + */ +/* other bits of media_flags available for future use */ + /* * A CD-ROM physical sector size is 2048, 2052, 2056, 2324, 2332, 2336, * 2340, or 2352 bytes long. diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index b270a07b285e..c45b5e9a9387 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -158,6 +158,7 @@ enum { #define IORING_TIMEOUT_BOOTTIME (1U << 2) #define IORING_TIMEOUT_REALTIME (1U << 3) #define IORING_LINK_TIMEOUT_UPDATE (1U << 4) +#define IORING_TIMEOUT_ETIME_SUCCESS (1U << 5) #define IORING_TIMEOUT_CLOCK_MASK (IORING_TIMEOUT_BOOTTIME | IORING_TIMEOUT_REALTIME) #define IORING_TIMEOUT_UPDATE_MASK (IORING_TIMEOUT_UPDATE | IORING_LINK_TIMEOUT_UPDATE) /*