diff options
Diffstat (limited to 'drivers')
34 files changed, 333 insertions, 384 deletions
diff --git a/drivers/block/amiflop.c b/drivers/block/amiflop.c index 0903e0803ec8..92b930cb3b72 100644 --- a/drivers/block/amiflop.c +++ b/drivers/block/amiflop.c @@ -1829,6 +1829,7 @@ static int __init fd_probe_drives(void) disk->major = FLOPPY_MAJOR; disk->first_minor = drive; disk->fops = &floppy_fops; + disk->events = DISK_EVENT_MEDIA_CHANGE; sprintf(disk->disk_name, "fd%d", drive); disk->private_data = &unit[drive]; set_capacity(disk, 880*2); diff --git a/drivers/block/ataflop.c b/drivers/block/ataflop.c index b0dbbdfeb33e..c7b5c4671f05 100644 --- a/drivers/block/ataflop.c +++ b/drivers/block/ataflop.c @@ -2028,6 +2028,7 @@ static int __init atari_floppy_init (void) unit[i].disk->first_minor = i; sprintf(unit[i].disk->disk_name, "fd%d", i); unit[i].disk->fops = &floppy_fops; + unit[i].disk->events = DISK_EVENT_MEDIA_CHANGE; unit[i].disk->private_data = &unit[i]; set_capacity(unit[i].disk, MAX_DISK_SIZE * 2); add_disk(unit[i].disk); diff --git a/drivers/block/drbd/drbd_int.h b/drivers/block/drbd/drbd_int.h index 000a2f4c0e92..acd7af3630e9 100644 --- a/drivers/block/drbd/drbd_int.h +++ b/drivers/block/drbd/drbd_int.h @@ -1317,10 +1317,6 @@ struct bm_extent { #define DRBD_MAX_SECTORS_FIXED_BM \ ((MD_128MB_SECT - MD_32kB_SECT - MD_4kB_SECT) * (1LL<<(BM_EXT_SHIFT-9))) -#if !defined(CONFIG_LBDAF) && BITS_PER_LONG == 32 -#define DRBD_MAX_SECTORS DRBD_MAX_SECTORS_32 -#define DRBD_MAX_SECTORS_FLEX DRBD_MAX_SECTORS_32 -#else #define DRBD_MAX_SECTORS DRBD_MAX_SECTORS_FIXED_BM /* 16 TB in units of sectors */ #if BITS_PER_LONG == 32 @@ -1333,7 +1329,6 @@ struct bm_extent { #define DRBD_MAX_SECTORS_FLEX (1UL << 51) /* corresponds to (1UL << 38) bits right now. */ #endif -#endif /* Estimate max bio size as 256 * PAGE_SIZE, * so for typical PAGE_SIZE of 4k, that is (1<<20) Byte. diff --git a/drivers/block/floppy.c b/drivers/block/floppy.c index 95f608d1a098..8072bd9881e6 100644 --- a/drivers/block/floppy.c +++ b/drivers/block/floppy.c @@ -4540,6 +4540,7 @@ static int __init do_floppy_init(void) disks[drive]->major = FLOPPY_MAJOR; disks[drive]->first_minor = TOMINOR(drive); disks[drive]->fops = &floppy_fops; + disks[drive]->events = DISK_EVENT_MEDIA_CHANGE; sprintf(disks[drive]->disk_name, "fd%d", drive); timer_setup(&motor_off_timer[drive], motor_off_callback, 0); diff --git a/drivers/block/loop.c b/drivers/block/loop.c index bf1c61cab8eb..102d79575895 100644 --- a/drivers/block/loop.c +++ b/drivers/block/loop.c @@ -264,12 +264,20 @@ lo_do_transfer(struct loop_device *lo, int cmd, return ret; } +static inline void loop_iov_iter_bvec(struct iov_iter *i, + unsigned int direction, const struct bio_vec *bvec, + unsigned long nr_segs, size_t count) +{ + iov_iter_bvec(i, direction, bvec, nr_segs, count); + i->type |= ITER_BVEC_FLAG_NO_REF; +} + static int lo_write_bvec(struct file *file, struct bio_vec *bvec, loff_t *ppos) { struct iov_iter i; ssize_t bw; - iov_iter_bvec(&i, WRITE, bvec, 1, bvec->bv_len); + loop_iov_iter_bvec(&i, WRITE, bvec, 1, bvec->bv_len); file_start_write(file); bw = vfs_iter_write(file, &i, ppos, 0); @@ -347,7 +355,7 @@ static int lo_read_simple(struct loop_device *lo, struct request *rq, ssize_t len; rq_for_each_segment(bvec, rq, iter) { - iov_iter_bvec(&i, READ, &bvec, 1, bvec.bv_len); + loop_iov_iter_bvec(&i, READ, &bvec, 1, bvec.bv_len); len = vfs_iter_read(lo->lo_backing_file, &i, &pos, 0); if (len < 0) return len; @@ -388,7 +396,7 @@ static int lo_read_transfer(struct loop_device *lo, struct request *rq, b.bv_offset = 0; b.bv_len = bvec.bv_len; - iov_iter_bvec(&i, READ, &b, 1, b.bv_len); + loop_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; @@ -555,7 +563,7 @@ static int lo_rw_aio(struct loop_device *lo, struct loop_cmd *cmd, } atomic_set(&cmd->ref, 2); - iov_iter_bvec(&iter, rw, bvec, nr_bvec, blk_rq_bytes(rq)); + loop_iov_iter_bvec(&iter, rw, bvec, nr_bvec, blk_rq_bytes(rq)); iter.iov_offset = offset; cmd->iocb.ki_pos = pos; @@ -900,6 +908,24 @@ static int loop_prepare_queue(struct loop_device *lo) return 0; } +static void loop_update_rotational(struct loop_device *lo) +{ + struct file *file = lo->lo_backing_file; + struct inode *file_inode = file->f_mapping->host; + struct block_device *file_bdev = file_inode->i_sb->s_bdev; + struct request_queue *q = lo->lo_queue; + bool nonrot = true; + + /* not all filesystems (e.g. tmpfs) have a sb->s_bdev */ + if (file_bdev) + nonrot = blk_queue_nonrot(bdev_get_queue(file_bdev)); + + if (nonrot) + blk_queue_flag_set(QUEUE_FLAG_NONROT, q); + else + blk_queue_flag_clear(QUEUE_FLAG_NONROT, q); +} + static int loop_set_fd(struct loop_device *lo, fmode_t mode, struct block_device *bdev, unsigned int arg) { @@ -963,6 +989,7 @@ static int loop_set_fd(struct loop_device *lo, fmode_t mode, if (!(lo_flags & LO_FLAGS_READ_ONLY) && file->f_op->fsync) blk_queue_write_cache(lo->lo_queue, true, false); + loop_update_rotational(lo); loop_update_dio(lo); set_capacity(lo->lo_disk, size); bd_set_size(bdev, size << 9); diff --git a/drivers/block/paride/pcd.c b/drivers/block/paride/pcd.c index 6d415b20fb70..001dbdcbf355 100644 --- a/drivers/block/paride/pcd.c +++ b/drivers/block/paride/pcd.c @@ -343,6 +343,7 @@ static void pcd_init_units(void) 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; } } diff --git a/drivers/block/paride/pd.c b/drivers/block/paride/pd.c index 0ff9b12d0e35..6f9ad3fc716f 100644 --- a/drivers/block/paride/pd.c +++ b/drivers/block/paride/pd.c @@ -897,6 +897,7 @@ static void pd_probe_drive(struct pd_unit *disk) p->fops = &pd_fops; p->major = major; p->first_minor = (disk - pd) << PD_BITS; + p->events = DISK_EVENT_MEDIA_CHANGE; disk->gd = p; p->private_data = disk; diff --git a/drivers/block/paride/pf.c b/drivers/block/paride/pf.c index 35e6e271b219..1e9c50a7256c 100644 --- a/drivers/block/paride/pf.c +++ b/drivers/block/paride/pf.c @@ -319,6 +319,7 @@ static void __init pf_init_units(void) disk->first_minor = unit; strcpy(disk->disk_name, pf->name); disk->fops = &pf_fops; + disk->events = DISK_EVENT_MEDIA_CHANGE; if (!(*drives[unit])[D_PRT]) pf_drive_count++; } diff --git a/drivers/block/pktcdvd.c b/drivers/block/pktcdvd.c index f5a71023f76c..024060165afa 100644 --- a/drivers/block/pktcdvd.c +++ b/drivers/block/pktcdvd.c @@ -2761,7 +2761,6 @@ 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; - disk->async_events = pd->bdev->bd_disk->async_events; add_disk(disk); diff --git a/drivers/block/ps3disk.c b/drivers/block/ps3disk.c index 4e1d9b31f60c..cc61c5ce3ad5 100644 --- a/drivers/block/ps3disk.c +++ b/drivers/block/ps3disk.c @@ -102,7 +102,7 @@ static void ps3disk_scatter_gather(struct ps3_storage_device *dev, rq_for_each_segment(bvec, req, iter) { unsigned long flags; - dev_dbg(&dev->sbd.core, "%s:%u: bio %u: %u sectors from %lu\n", + dev_dbg(&dev->sbd.core, "%s:%u: bio %u: %u sectors from %llu\n", __func__, __LINE__, i, bio_sectors(iter.bio), iter.bio->bi_iter.bi_sector); @@ -496,7 +496,7 @@ static int ps3disk_probe(struct ps3_system_bus_device *_dev) dev->regions[dev->region_idx].size*priv->blocking_factor); dev_info(&dev->sbd.core, - "%s is a %s (%llu MiB total, %lu MiB for OtherOS)\n", + "%s is a %s (%llu MiB total, %llu MiB for OtherOS)\n", gendisk->disk_name, priv->model, priv->raw_capacity >> 11, get_capacity(gendisk) >> 11); diff --git a/drivers/block/swim.c b/drivers/block/swim.c index 3fa6fcc34790..67b5ec281c6d 100644 --- a/drivers/block/swim.c +++ b/drivers/block/swim.c @@ -862,6 +862,7 @@ static int swim_floppy_init(struct swim_priv *swd) swd->unit[drive].disk->first_minor = drive; sprintf(swd->unit[drive].disk->disk_name, "fd%d", drive); swd->unit[drive].disk->fops = &floppy_fops; + 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); diff --git a/drivers/block/swim3.c b/drivers/block/swim3.c index 1e2ae90d7715..cf42729c788e 100644 --- a/drivers/block/swim3.c +++ b/drivers/block/swim3.c @@ -1216,6 +1216,7 @@ static int swim3_attach(struct macio_dev *mdev, disk->first_minor = floppy_count; disk->fops = &floppy_fops; disk->private_data = fs; + disk->events = DISK_EVENT_MEDIA_CHANGE; disk->flags |= GENHD_FL_REMOVABLE; sprintf(disk->disk_name, "fd%d", floppy_count); set_capacity(disk, 2880); diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c index 2a7ca4a1e6f7..f1d90cd3dc47 100644 --- a/drivers/block/virtio_blk.c +++ b/drivers/block/virtio_blk.c @@ -693,7 +693,8 @@ static int virtblk_map_queues(struct blk_mq_tag_set *set) { struct virtio_blk *vblk = set->driver_data; - return blk_mq_virtio_map_queues(&set->map[0], vblk->vdev, 0); + return blk_mq_virtio_map_queues(&set->map[HCTX_TYPE_DEFAULT], + vblk->vdev, 0); } #ifdef CONFIG_VIRTIO_BLK_SCSI diff --git a/drivers/block/xsysace.c b/drivers/block/xsysace.c index 32a21b8d1d85..464c9092bc8b 100644 --- a/drivers/block/xsysace.c +++ b/drivers/block/xsysace.c @@ -1032,6 +1032,7 @@ static int ace_setup(struct ace_device *ace) ace->gd->major = ace_major; ace->gd->first_minor = ace->id * ACE_NUM_MINORS; ace->gd->fops = &ace_fops; + ace->gd->events = DISK_EVENT_MEDIA_CHANGE; ace->gd->queue = ace->queue; ace->gd->private_data = ace; snprintf(ace->gd->disk_name, 32, "xs%c", ace->id + 'a'); diff --git a/drivers/cdrom/gdrom.c b/drivers/cdrom/gdrom.c index f8b7345fe1cb..5cf3bade0d57 100644 --- a/drivers/cdrom/gdrom.c +++ b/drivers/cdrom/gdrom.c @@ -786,6 +786,7 @@ static int probe_gdrom(struct platform_device *devptr) goto probe_fail_cdrom_register; } gd.disk->fops = &gdrom_bdops; + gd.disk->events = DISK_EVENT_MEDIA_CHANGE; /* latch on to the interrupt */ err = gdrom_set_interrupt_handlers(); if (err) diff --git a/drivers/ide/ide-cd.c b/drivers/ide/ide-cd.c index 1f03884a6808..3b15adc6ce98 100644 --- a/drivers/ide/ide-cd.c +++ b/drivers/ide/ide-cd.c @@ -1797,6 +1797,7 @@ static int ide_cd_probe(ide_drive_t *drive) ide_cd_read_toc(drive); g->fops = &idecd_ops; g->flags |= GENHD_FL_REMOVABLE | GENHD_FL_BLOCK_EVENTS_ON_EXCL_WRITE; + g->events = DISK_EVENT_MEDIA_CHANGE; device_add_disk(&drive->gendev, g, NULL); return 0; diff --git a/drivers/ide/ide-cd_ioctl.c b/drivers/ide/ide-cd_ioctl.c index 4a6e1a413ead..46f2df288c6a 100644 --- a/drivers/ide/ide-cd_ioctl.c +++ b/drivers/ide/ide-cd_ioctl.c @@ -82,8 +82,9 @@ int ide_cdrom_drive_status(struct cdrom_device_info *cdi, int slot_nr) /* * ide-cd always generates media changed event if media is missing, which - * makes it impossible to use for proper event reporting, so disk->events - * is cleared to 0 and the following function is used only to trigger + * makes it impossible to use for proper event reporting, so + * DISK_EVENT_FLAG_UEVENT is cleared in disk->event_flags + * and the following function is used only to trigger * revalidation and never propagated to userland. */ unsigned int ide_cdrom_check_events_real(struct cdrom_device_info *cdi, diff --git a/drivers/ide/ide-gd.c b/drivers/ide/ide-gd.c index 04e008e8f6f9..f233b34ea0c0 100644 --- a/drivers/ide/ide-gd.c +++ b/drivers/ide/ide-gd.c @@ -299,8 +299,9 @@ static unsigned int ide_gd_check_events(struct gendisk *disk, /* * The following is used to force revalidation on the first open on * removeable devices, and never gets reported to userland as - * genhd->events is 0. This is intended as removeable ide disk - * can't really detect MEDIA_CHANGE events. + * DISK_EVENT_FLAG_UEVENT isn't set in genhd->event_flags. + * This is intended as removable ide disk can't really detect + * MEDIA_CHANGE events. */ ret = drive->dev_flags & IDE_DFLAG_MEDIA_CHANGED; drive->dev_flags &= ~IDE_DFLAG_MEDIA_CHANGED; @@ -416,6 +417,7 @@ static int ide_gd_probe(ide_drive_t *drive) if (drive->dev_flags & IDE_DFLAG_REMOVABLE) g->flags = GENHD_FL_REMOVABLE; g->fops = &ide_gd_ops; + g->events = DISK_EVENT_MEDIA_CHANGE; device_add_disk(&drive->gendev, g, NULL); return 0; diff --git a/drivers/md/dm-exception-store.h b/drivers/md/dm-exception-store.h index 12b5216c2cfe..721efc493942 100644 --- a/drivers/md/dm-exception-store.h +++ b/drivers/md/dm-exception-store.h @@ -135,9 +135,8 @@ struct dm_dev *dm_snap_cow(struct dm_snapshot *snap); /* * Funtions to manipulate consecutive chunks */ -# if defined(CONFIG_LBDAF) || (BITS_PER_LONG == 64) -# define DM_CHUNK_CONSECUTIVE_BITS 8 -# define DM_CHUNK_NUMBER_BITS 56 +#define DM_CHUNK_CONSECUTIVE_BITS 8 +#define DM_CHUNK_NUMBER_BITS 56 static inline chunk_t dm_chunk_number(chunk_t chunk) { @@ -163,29 +162,6 @@ static inline void dm_consecutive_chunk_count_dec(struct dm_exception *e) e->new_chunk -= (1ULL << DM_CHUNK_NUMBER_BITS); } -# else -# define DM_CHUNK_CONSECUTIVE_BITS 0 - -static inline chunk_t dm_chunk_number(chunk_t chunk) -{ - return chunk; -} - -static inline unsigned dm_consecutive_chunk_count(struct dm_exception *e) -{ - return 0; -} - -static inline void dm_consecutive_chunk_count_inc(struct dm_exception *e) -{ -} - -static inline void dm_consecutive_chunk_count_dec(struct dm_exception *e) -{ -} - -# endif - /* * Return the number of sectors in the device. */ diff --git a/drivers/md/dm-integrity.c b/drivers/md/dm-integrity.c index 7c678f50aaa3..05075613af93 100644 --- a/drivers/md/dm-integrity.c +++ b/drivers/md/dm-integrity.c @@ -88,14 +88,10 @@ struct journal_entry { #if BITS_PER_LONG == 64 #define journal_entry_set_sector(je, x) do { smp_wmb(); WRITE_ONCE((je)->u.sector, cpu_to_le64(x)); } while (0) -#define journal_entry_get_sector(je) le64_to_cpu((je)->u.sector) -#elif defined(CONFIG_LBDAF) -#define journal_entry_set_sector(je, x) do { (je)->u.s.sector_lo = cpu_to_le32(x); smp_wmb(); WRITE_ONCE((je)->u.s.sector_hi, cpu_to_le32((x) >> 32)); } while (0) -#define journal_entry_get_sector(je) le64_to_cpu((je)->u.sector) #else -#define journal_entry_set_sector(je, x) do { (je)->u.s.sector_lo = cpu_to_le32(x); smp_wmb(); WRITE_ONCE((je)->u.s.sector_hi, cpu_to_le32(0)); } while (0) -#define journal_entry_get_sector(je) le32_to_cpu((je)->u.s.sector_lo) +#define journal_entry_set_sector(je, x) do { (je)->u.s.sector_lo = cpu_to_le32(x); smp_wmb(); WRITE_ONCE((je)->u.s.sector_hi, cpu_to_le32((x) >> 32)); } while (0) #endif +#define journal_entry_get_sector(je) le64_to_cpu((je)->u.sector) #define journal_entry_is_unused(je) ((je)->u.s.sector_hi == cpu_to_le32(-1)) #define journal_entry_set_unused(je) do { ((je)->u.s.sector_hi = cpu_to_le32(-1)); } while (0) #define journal_entry_is_inprogress(je) ((je)->u.s.sector_hi == cpu_to_le32(-2)) diff --git a/drivers/md/md-bitmap.c b/drivers/md/md-bitmap.c index 1cd4f991792c..3a62a46b75c7 100644 --- a/drivers/md/md-bitmap.c +++ b/drivers/md/md-bitmap.c @@ -490,10 +490,10 @@ void md_bitmap_print_sb(struct bitmap *bitmap) pr_debug(" magic: %08x\n", le32_to_cpu(sb->magic)); pr_debug(" version: %d\n", le32_to_cpu(sb->version)); pr_debug(" uuid: %08x.%08x.%08x.%08x\n", - le32_to_cpu(*(__u32 *)(sb->uuid+0)), - le32_to_cpu(*(__u32 *)(sb->uuid+4)), - le32_to_cpu(*(__u32 *)(sb->uuid+8)), - le32_to_cpu(*(__u32 *)(sb->uuid+12))); + le32_to_cpu(*(__le32 *)(sb->uuid+0)), + le32_to_cpu(*(__le32 *)(sb->uuid+4)), + le32_to_cpu(*(__le32 *)(sb->uuid+8)), + le32_to_cpu(*(__le32 *)(sb->uuid+12))); pr_debug(" events: %llu\n", (unsigned long long) le64_to_cpu(sb->events)); pr_debug("events cleared: %llu\n", diff --git a/drivers/md/md.c b/drivers/md/md.c index 05ffffb8b769..541015373f6a 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -88,8 +88,7 @@ static struct kobj_type md_ktype; struct md_cluster_operations *md_cluster_ops; EXPORT_SYMBOL(md_cluster_ops); -struct module *md_cluster_mod; -EXPORT_SYMBOL(md_cluster_mod); +static struct module *md_cluster_mod; static DECLARE_WAIT_QUEUE_HEAD(resync_wait); static struct workqueue_struct *md_wq; @@ -132,24 +131,6 @@ static inline int speed_max(struct mddev *mddev) mddev->sync_speed_max : sysctl_speed_limit_max; } -static void * flush_info_alloc(gfp_t gfp_flags, void *data) -{ - return kzalloc(sizeof(struct flush_info), gfp_flags); -} -static void flush_info_free(void *flush_info, void *data) -{ - kfree(flush_info); -} - -static void * flush_bio_alloc(gfp_t gfp_flags, void *data) -{ - return kzalloc(sizeof(struct flush_bio), gfp_flags); -} -static void flush_bio_free(void *flush_bio, void *data) -{ - kfree(flush_bio); -} - static struct ctl_table_header *raid_table_header; static struct ctl_table raid_table[] = { @@ -423,54 +404,31 @@ static int md_congested(void *data, int bits) /* * Generic flush handling for md */ -static void submit_flushes(struct work_struct *ws) -{ - struct flush_info *fi = container_of(ws, struct flush_info, flush_work); - struct mddev *mddev = fi->mddev; - struct bio *bio = fi->bio; - - bio->bi_opf &= ~REQ_PREFLUSH; - md_handle_request(mddev, bio); - - mempool_free(fi, mddev->flush_pool); -} -static void md_end_flush(struct bio *fbio) +static void md_end_flush(struct bio *bio) { - struct flush_bio *fb = fbio->bi_private; - struct md_rdev *rdev = fb->rdev; - struct flush_info *fi = fb->fi; - struct bio *bio = fi->bio; - struct mddev *mddev = fi->mddev; + struct md_rdev *rdev = bio->bi_private; + struct mddev *mddev = rdev->mddev; rdev_dec_pending(rdev, mddev); - if (atomic_dec_and_test(&fi->flush_pending)) { - if (bio->bi_iter.bi_size == 0) { - /* an empty barrier - all done */ - bio_endio(bio); - mempool_free(fi, mddev->flush_pool); - } else { - INIT_WORK(&fi->flush_work, submit_flushes); - queue_work(md_wq, &fi->flush_work); - } + if (atomic_dec_and_test(&mddev->flush_pending)) { + /* The pre-request flush has finished */ + queue_work(md_wq, &mddev->flush_work); } - - mempool_free(fb, mddev->flush_bio_pool); - bio_put(fbio); + bio_put(bio); } -void md_flush_request(struct mddev *mddev, struct bio *bio) +static void md_submit_flush_data(struct work_struct *ws); + +static void submit_flushes(struct work_struct *ws) { + struct mddev *mddev = container_of(ws, struct mddev, flush_work); struct md_rdev *rdev; - struct flush_info *fi; - - fi = mempool_alloc(mddev->flush_pool, GFP_NOIO); - - fi->bio = bio; - fi->mddev = mddev; - atomic_set(&fi->flush_pending, 1); + mddev->start_flush = ktime_get_boottime(); + INIT_WORK(&mddev->flush_work, md_submit_flush_data); + atomic_set(&mddev->flush_pending, 1); rcu_read_lock(); rdev_for_each_rcu(rdev, mddev) if (rdev->raid_disk >= 0 && @@ -480,37 +438,74 @@ void md_flush_request(struct mddev *mddev, struct bio *bio) * we reclaim rcu_read_lock */ struct bio *bi; - struct flush_bio *fb; atomic_inc(&rdev->nr_pending); atomic_inc(&rdev->nr_pending); rcu_read_unlock(); - - fb = mempool_alloc(mddev->flush_bio_pool, GFP_NOIO); - fb->fi = fi; - fb->rdev = rdev; - bi = bio_alloc_mddev(GFP_NOIO, 0, mddev); - bio_set_dev(bi, rdev->bdev); bi->bi_end_io = md_end_flush; - bi->bi_private = fb; + bi->bi_private = rdev; + bio_set_dev(bi, rdev->bdev); bi->bi_opf = REQ_OP_WRITE | REQ_PREFLUSH; - - atomic_inc(&fi->flush_pending); + atomic_inc(&mddev->flush_pending); submit_bio(bi); - rcu_read_lock(); rdev_dec_pending(rdev, mddev); } rcu_read_unlock(); + if (atomic_dec_and_test(&mddev->flush_pending)) + queue_work(md_wq, &mddev->flush_work); +} + +static void md_submit_flush_data(struct work_struct *ws) +{ + struct mddev *mddev = container_of(ws, struct mddev, flush_work); + struct bio *bio = mddev->flush_bio; + + /* + * must reset flush_bio before calling into md_handle_request to avoid a + * deadlock, because other bios passed md_handle_request suspend check + * could wait for this and below md_handle_request could wait for those + * bios because of suspend check + */ + mddev->last_flush = mddev->start_flush; + mddev->flush_bio = NULL; + wake_up(&mddev->sb_wait); + + if (bio->bi_iter.bi_size == 0) { + /* an empty barrier - all done */ + bio_endio(bio); + } else { + bio->bi_opf &= ~REQ_PREFLUSH; + md_handle_request(mddev, bio); + } +} - if (atomic_dec_and_test(&fi->flush_pending)) { - if (bio->bi_iter.bi_size == 0) { +void md_flush_request(struct mddev *mddev, struct bio *bio) +{ + ktime_t start = ktime_get_boottime(); + spin_lock_irq(&mddev->lock); + wait_event_lock_irq(mddev->sb_wait, + !mddev->flush_bio || + ktime_after(mddev->last_flush, start), + mddev->lock); + if (!ktime_after(mddev->last_flush, start)) { + WARN_ON(mddev->flush_bio); + mddev->flush_bio = bio; + bio = NULL; + } + spin_unlock_irq(&mddev->lock); + + if (!bio) { + INIT_WORK(&mddev->flush_work, submit_flushes); + queue_work(md_wq, &mddev->flush_work); + } else { + /* flush was performed for some other bio while we waited. */ + if (bio->bi_iter.bi_size == 0) /* an empty barrier - all done */ bio_endio(bio); - mempool_free(fi, mddev->flush_pool); - } else { - INIT_WORK(&fi->flush_work, submit_flushes); - queue_work(md_wq, &fi->flush_work); + else { + bio->bi_opf &= ~REQ_PREFLUSH; + mddev->pers->make_request(mddev, bio); } } } @@ -560,6 +555,7 @@ void mddev_init(struct mddev *mddev) atomic_set(&mddev->openers, 0); atomic_set(&mddev->active_io, 0); spin_lock_init(&mddev->lock); + atomic_set(&mddev->flush_pending, 0); init_waitqueue_head(&mddev->sb_wait); init_waitqueue_head(&mddev->recovery_wait); mddev->reshape_position = MaxSector; @@ -1109,8 +1105,7 @@ static int super_90_load(struct md_rdev *rdev, struct md_rdev *refdev, int minor * (not needed for Linear and RAID0 as metadata doesn't * record this size) */ - if (IS_ENABLED(CONFIG_LBDAF) && (u64)rdev->sectors >= (2ULL << 32) && - sb->level >= 1) + if ((u64)rdev->sectors >= (2ULL << 32) && sb->level >= 1) rdev->sectors = (sector_t)(2ULL << 32) - 2; if (rdev->sectors < ((sector_t)sb->size) * 2 && sb->level >= 1) @@ -1408,8 +1403,7 @@ super_90_rdev_size_change(struct md_rdev *rdev, sector_t num_sectors) /* Limit to 4TB as metadata cannot record more than that. * 4TB == 2^32 KB, or 2*2^32 sectors. */ - if (IS_ENABLED(CONFIG_LBDAF) && (u64)num_sectors >= (2ULL << 32) && - rdev->mddev->level >= 1) + if ((u64)num_sectors >= (2ULL << 32) && rdev->mddev->level >= 1) num_sectors = (sector_t)(2ULL << 32) - 2; do { md_super_write(rdev->mddev, rdev, rdev->sb_start, rdev->sb_size, @@ -1553,7 +1547,7 @@ static int super_1_load(struct md_rdev *rdev, struct md_rdev *refdev, int minor_ */ s32 offset; sector_t bb_sector; - u64 *bbp; + __le64 *bbp; int i; int sectors = le16_to_cpu(sb->bblog_size); if (sectors > (PAGE_SIZE / 512)) @@ -1565,7 +1559,7 @@ static int super_1_load(struct md_rdev *rdev, struct md_rdev *refdev, int minor_ if (!sync_page_io(rdev, bb_sector, sectors << 9, rdev->bb_page, REQ_OP_READ, 0, true)) return -EIO; - bbp = (u64 *)page_address(rdev->bb_page); + bbp = (__le64 *)page_address(rdev->bb_page); rdev->badblocks.shift = sb->bblog_shift; for (i = 0 ; i < (sectors << (9-3)) ; i++, bbp++) { u64 bb = le64_to_cpu(*bbp); @@ -1877,7 +1871,7 @@ static void super_1_sync(struct mddev *mddev, struct md_rdev *rdev) md_error(mddev, rdev); else { struct badblocks *bb = &rdev->badblocks; - u64 *bbp = (u64 *)page_address(rdev->bb_page); + __le64 *bbp = (__le64 *)page_address(rdev->bb_page); u64 *p = bb->page; sb->feature_map |= cpu_to_le32(MD_FEATURE_BAD_BLOCKS); if (bb->changed) { @@ -2855,8 +2849,10 @@ state_store(struct md_rdev *rdev, const char *buf, size_t len) err = 0; } } else if (cmd_match(buf, "re-add")) { - if (test_bit(Faulty, &rdev->flags) && (rdev->raid_disk == -1) && - rdev->saved_raid_disk >= 0) { + if (!rdev->mddev->pers) + err = -EINVAL; + else if (test_bit(Faulty, &rdev->flags) && (rdev->raid_disk == -1) && + rdev->saved_raid_disk >= 0) { /* clear_bit is performed _after_ all the devices * have their local Faulty bit cleared. If any writes * happen in the meantime in the local node, they @@ -5511,22 +5507,6 @@ int md_run(struct mddev *mddev) if (err) return err; } - if (mddev->flush_pool == NULL) { - mddev->flush_pool = mempool_create(NR_FLUSH_INFOS, flush_info_alloc, - flush_info_free, mddev); - if (!mddev->flush_pool) { - err = -ENOMEM; - goto abort; - } - } - if (mddev->flush_bio_pool == NULL) { - mddev->flush_bio_pool = mempool_create(NR_FLUSH_BIOS, flush_bio_alloc, - flush_bio_free, mddev); - if (!mddev->flush_bio_pool) { - err = -ENOMEM; - goto abort; - } - } spin_lock(&pers_lock); pers = find_pers(mddev->level, mddev->clevel); @@ -5686,11 +5666,8 @@ int md_run(struct mddev *mddev) return 0; abort: - mempool_destroy(mddev->flush_bio_pool); - mddev->flush_bio_pool = NULL; - mempool_destroy(mddev->flush_pool); - mddev->flush_pool = NULL; - + bioset_exit(&mddev->bio_set); + bioset_exit(&mddev->sync_set); return err; } EXPORT_SYMBOL_GPL(md_run); @@ -5894,14 +5871,6 @@ static void __md_stop(struct mddev *mddev) mddev->to_remove = &md_redundancy_group; module_put(pers->owner); clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery); - if (mddev->flush_bio_pool) { - mempool_destroy(mddev->flush_bio_pool); - mddev->flush_bio_pool = NULL; - } - if (mddev->flush_pool) { - mempool_destroy(mddev->flush_pool); - mddev->flush_pool = NULL; - } } void md_stop(struct mddev *mddev) @@ -9257,7 +9226,7 @@ static void check_sb_changes(struct mddev *mddev, struct md_rdev *rdev) * reshape is happening in the remote node, we need to * update reshape_position and call start_reshape. */ - mddev->reshape_position = sb->reshape_position; + mddev->reshape_position = le64_to_cpu(sb->reshape_position); if (mddev->pers->update_reshape_pos) mddev->pers->update_reshape_pos(mddev); if (mddev->pers->start_reshape) diff --git a/drivers/md/md.h b/drivers/md/md.h index c52afb52c776..257cb4c9e22b 100644 --- a/drivers/md/md.h +++ b/drivers/md/md.h @@ -252,19 +252,6 @@ enum mddev_sb_flags { MD_SB_NEED_REWRITE, /* metadata write needs to be repeated */ }; -#define NR_FLUSH_INFOS 8 -#define NR_FLUSH_BIOS 64 -struct flush_info { - struct bio *bio; - struct mddev *mddev; - struct work_struct flush_work; - atomic_t flush_pending; -}; -struct flush_bio { - struct flush_info *fi; - struct md_rdev *rdev; -}; - struct mddev { void *private; struct md_personality *pers; @@ -470,8 +457,16 @@ struct mddev { * metadata and bitmap writes */ - mempool_t *flush_pool; - mempool_t *flush_bio_pool; + /* Generic flush handling. + * The last to finish preflush schedules a worker to submit + * the rest of the request (without the REQ_PREFLUSH flag). + */ + struct bio *flush_bio; + atomic_t flush_pending; + ktime_t start_flush, last_flush; /* last_flush is when the last completed + * flush was started. + */ + struct work_struct flush_work; struct work_struct event_work; /* used by dm to report failure event */ void (*sync_super)(struct mddev *mddev, struct md_rdev *rdev); struct md_cluster_info *cluster_info; diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index c033bfcb209e..2b0a715e70c9 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -711,6 +711,8 @@ static bool is_full_stripe_write(struct stripe_head *sh) } static void lock_two_stripes(struct stripe_head *sh1, struct stripe_head *sh2) + __acquires(&sh1->stripe_lock) + __acquires(&sh2->stripe_lock) { if (sh1 > sh2) { spin_lock_irq(&sh2->stripe_lock); @@ -722,6 +724,8 @@ static void lock_two_stripes(struct stripe_head *sh1, struct stripe_head *sh2) } static void unlock_two_stripes(struct stripe_head *sh1, struct stripe_head *sh2) + __releases(&sh1->stripe_lock) + __releases(&sh2->stripe_lock) { spin_unlock(&sh1->stripe_lock); spin_unlock_irq(&sh2->stripe_lock); @@ -4223,26 +4227,15 @@ static void handle_parity_checks6(struct r5conf *conf, struct stripe_head *sh, case check_state_check_result: sh->check_state = check_state_idle; + if (s->failed > 1) + break; /* handle a successful check operation, if parity is correct * we are done. Otherwise update the mismatch count and repair * parity if !MD_RECOVERY_CHECK */ if (sh->ops.zero_sum_result == 0) { - /* both parities are correct */ - if (!s->failed) - set_bit(STRIPE_INSYNC, &sh->state); - else { - /* in contrast to the raid5 case we can validate - * parity, but still have a failure to write - * back - */ - sh->check_state = check_state_compute_result; - /* Returning at this point means that we may go - * off and bring p and/or q uptodate again so - * we make sure to check zero_sum_result again - * to verify if p or q need writeback - */ - } + /* Any parity checked was correct */ + set_bit(STRIPE_INSYNC, &sh->state); } else { atomic64_add(STRIPE_SECTORS, &conf->mddev->resync_mismatches); if (test_bit(MD_RECOVERY_CHECK, &conf->mddev->recovery)) { @@ -6166,6 +6159,8 @@ static int retry_aligned_read(struct r5conf *conf, struct bio *raid_bio, static int handle_active_stripes(struct r5conf *conf, int group, struct r5worker *worker, struct list_head *temp_inactive_list) + __releases(&conf->device_lock) + __acquires(&conf->device_lock) { struct stripe_head *batch[MAX_STRIPE_BATCH], *sh; int i, batch_size = 0, hash; diff --git a/drivers/nvdimm/pfn_devs.c b/drivers/nvdimm/pfn_devs.c index d271bd731af7..01f40672507f 100644 --- a/drivers/nvdimm/pfn_devs.c +++ b/drivers/nvdimm/pfn_devs.c @@ -391,7 +391,7 @@ static int nd_pfn_clear_memmap_errors(struct nd_pfn *nd_pfn) bb_present = badblocks_check(&nd_region->bb, meta_start, meta_num, &first_bad, &num_bad); if (bb_present) { - dev_dbg(&nd_pfn->dev, "meta: %x badblocks at %lx\n", + dev_dbg(&nd_pfn->dev, "meta: %x badblocks at %llx\n", num_bad, first_bad); nsoff = ALIGN_DOWN((nd_region->ndr_start + (first_bad << 9)) - nsio->res.start, @@ -410,7 +410,7 @@ static int nd_pfn_clear_memmap_errors(struct nd_pfn *nd_pfn) } if (rc) { dev_err(&nd_pfn->dev, - "error clearing %x badblocks at %lx\n", + "error clearing %x badblocks at %llx\n", num_bad, first_bad); return rc; } diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index 2c43e12b70af..248ff3b48041 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -1105,7 +1105,7 @@ static struct nvme_id_ns *nvme_identify_ns(struct nvme_ctrl *ctrl, error = nvme_submit_sync_cmd(ctrl->admin_q, &c, id, sizeof(*id)); if (error) { - dev_warn(ctrl->device, "Identify namespace failed\n"); + dev_warn(ctrl->device, "Identify namespace failed (%d)\n", error); kfree(id); return NULL; } @@ -1588,7 +1588,7 @@ static bool nvme_ns_ids_equal(struct nvme_ns_ids *a, struct nvme_ns_ids *b) static void nvme_update_disk_info(struct gendisk *disk, struct nvme_ns *ns, struct nvme_id_ns *id) { - sector_t capacity = le64_to_cpup(&id->nsze) << (ns->lba_shift - 9); + sector_t capacity = le64_to_cpu(id->nsze) << (ns->lba_shift - 9); unsigned short bs = 1 << ns->lba_shift; blk_mq_freeze_queue(disk->queue); @@ -2549,7 +2549,7 @@ int nvme_init_identify(struct nvme_ctrl *ctrl) ctrl->crdt[2] = le16_to_cpu(id->crdt3); ctrl->oacs = le16_to_cpu(id->oacs); - ctrl->oncs = le16_to_cpup(&id->oncs); + ctrl->oncs = le16_to_cpu(id->oncs); ctrl->oaes = le32_to_cpu(id->oaes); atomic_set(&ctrl->abort_limit, id->acl + 1); ctrl->vwc = id->vwc; diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index a90cf5d63aac..c1eecde6b853 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -177,7 +177,6 @@ static inline struct nvme_dev *to_nvme_dev(struct nvme_ctrl *ctrl) * commands and one for I/O commands). */ struct nvme_queue { - struct device *q_dmadev; struct nvme_dev *dev; spinlock_t sq_lock; struct nvme_command *sq_cmds; @@ -189,7 +188,7 @@ struct nvme_queue { dma_addr_t cq_dma_addr; u32 __iomem *q_db; u16 q_depth; - s16 cq_vector; + u16 cq_vector; u16 sq_tail; u16 last_sq_tail; u16 cq_head; @@ -200,6 +199,7 @@ struct nvme_queue { #define NVMEQ_ENABLED 0 #define NVMEQ_SQ_CMB 1 #define NVMEQ_DELETE_ERROR 2 +#define NVMEQ_POLLED 3 u32 *dbbuf_sq_db; u32 *dbbuf_cq_db; u32 *dbbuf_sq_ei; @@ -208,10 +208,10 @@ struct nvme_queue { }; /* - * The nvme_iod describes the data in an I/O, including the list of PRP - * entries. You can't see it in this data structure because C doesn't let - * me express that. Use nvme_init_iod to ensure there's enough space - * allocated to store the PRP list. + * The nvme_iod describes the data in an I/O. + * + * The sg pointer contains the list of PRP/SGL chunk allocations in addition + * to the actual struct scatterlist. */ struct nvme_iod { struct nvme_request req; @@ -220,11 +220,10 @@ struct nvme_iod { int aborted; int npages; /* In the PRP list. 0 means small pool in use */ int nents; /* Used in scatterlist */ - int length; /* Of data, in bytes */ dma_addr_t first_dma; - struct scatterlist meta_sg; /* metadata requires single contiguous buffer */ + unsigned int dma_len; /* length of single DMA segment mapping */ + dma_addr_t meta_dma; struct scatterlist *sg; - struct scatterlist inline_sg[0]; }; /* @@ -372,12 +371,6 @@ static bool nvme_dbbuf_update_and_check_event(u16 value, u32 *dbbuf_db, } /* - * Max size of iod being embedded in the request payload - */ -#define NVME_INT_PAGES 2 -#define NVME_INT_BYTES(dev) (NVME_INT_PAGES * (dev)->ctrl.page_size) - -/* * Will slightly overestimate the number of pages needed. This is OK * as it only leads to a small amount of wasted memory for the lifetime of * the I/O. @@ -411,15 +404,6 @@ static unsigned int nvme_pci_iod_alloc_size(struct nvme_dev *dev, return alloc_size + sizeof(struct scatterlist) * nseg; } -static unsigned int nvme_pci_cmd_size(struct nvme_dev *dev, bool use_sgl) -{ - unsigned int alloc_size = nvme_pci_iod_alloc_size(dev, - NVME_INT_BYTES(dev), NVME_INT_PAGES, - use_sgl); - - return sizeof(struct nvme_iod) + alloc_size; -} - static int nvme_admin_init_hctx(struct blk_mq_hw_ctx *hctx, void *data, unsigned int hctx_idx) { @@ -584,37 +568,26 @@ static inline bool nvme_pci_use_sgls(struct nvme_dev *dev, struct request *req) return true; } -static blk_status_t nvme_init_iod(struct request *rq, struct nvme_dev *dev) +static void nvme_unmap_data(struct nvme_dev *dev, struct request *req) { - struct nvme_iod *iod = blk_mq_rq_to_pdu(rq); - int nseg = blk_rq_nr_phys_segments(rq); - unsigned int size = blk_rq_payload_bytes(rq); - - iod->use_sgl = nvme_pci_use_sgls(dev, rq); + struct nvme_iod *iod = blk_mq_rq_to_pdu(req); + enum dma_data_direction dma_dir = rq_data_dir(req) ? + DMA_TO_DEVICE : DMA_FROM_DEVICE; + const int last_prp = dev->ctrl.page_size / sizeof(__le64) - 1; + dma_addr_t dma_addr = iod->first_dma, next_dma_addr; + int i; - if (nseg > NVME_INT_PAGES || size > NVME_INT_BYTES(dev)) { - iod->sg = mempool_alloc(dev->iod_mempool, GFP_ATOMIC); - if (!iod->sg) - return BLK_STS_RESOURCE; - } else { - iod->sg = iod->inline_sg; + if (iod->dma_len) { + dma_unmap_page(dev->dev, dma_addr, iod->dma_len, dma_dir); + return; } - iod->aborted = 0; - iod->npages = -1; - iod->nents = 0; - iod->length = size; + WARN_ON_ONCE(!iod->nents); - return BLK_STS_OK; -} + /* P2PDMA requests do not need to be unmapped */ + if (!is_pci_p2pdma_page(sg_page(iod->sg))) + dma_unmap_sg(dev->dev, iod->sg, iod->nents, rq_dma_dir(req)); -static void nvme_free_iod(struct nvme_dev *dev, struct request *req) -{ - struct nvme_iod *iod = blk_mq_rq_to_pdu(req); - const int last_prp = dev->ctrl.page_size / sizeof(__le64) - 1; - dma_addr_t dma_addr = iod->first_dma, next_dma_addr; - - int i; if (iod->npages == 0) dma_pool_free(dev->prp_small_pool, nvme_pci_iod_list(req)[0], @@ -638,8 +611,7 @@ static void nvme_free_iod(struct nvme_dev *dev, struct request *req) dma_addr = next_dma_addr; } - if (iod->sg != iod->inline_sg) - mempool_free(iod->sg, dev->iod_mempool); + mempool_free(iod->sg, dev->iod_mempool); } static void nvme_print_sgl(struct scatterlist *sgl, int nents) @@ -829,80 +801,103 @@ static blk_status_t nvme_pci_setup_sgls(struct nvme_dev *dev, return BLK_STS_OK; } +static blk_status_t nvme_setup_prp_simple(struct nvme_dev *dev, + struct request *req, struct nvme_rw_command *cmnd, + struct bio_vec *bv) +{ + struct nvme_iod *iod = blk_mq_rq_to_pdu(req); + unsigned int first_prp_len = dev->ctrl.page_size - bv->bv_offset; + + iod->first_dma = dma_map_bvec(dev->dev, bv, rq_dma_dir(req), 0); + if (dma_mapping_error(dev->dev, iod->first_dma)) + return BLK_STS_RESOURCE; + iod->dma_len = bv->bv_len; + + cmnd->dptr.prp1 = cpu_to_le64(iod->first_dma); + if (bv->bv_len > first_prp_len) + cmnd->dptr.prp2 = cpu_to_le64(iod->first_dma + first_prp_len); + return 0; +} + +static blk_status_t nvme_setup_sgl_simple(struct nvme_dev *dev, + struct request *req, struct nvme_rw_command *cmnd, + struct bio_vec *bv) +{ + struct nvme_iod *iod = blk_mq_rq_to_pdu(req); + + iod->first_dma = dma_map_bvec(dev->dev, bv, rq_dma_dir(req), 0); + if (dma_mapping_error(dev->dev, iod->first_dma)) + return BLK_STS_RESOURCE; + iod->dma_len = bv->bv_len; + + cmnd->dptr.sgl.addr = cpu_to_le64(iod->first_dma); + cmnd->dptr.sgl.length = cpu_to_le32(iod->dma_len); + cmnd->dptr.sgl.type = NVME_SGL_FMT_DATA_DESC << 4; + return 0; +} + static blk_status_t nvme_map_data(struct nvme_dev *dev, struct request *req, struct nvme_command *cmnd) { struct nvme_iod *iod = blk_mq_rq_to_pdu(req); - struct request_queue *q = req->q; - enum dma_data_direction dma_dir = rq_data_dir(req) ? - DMA_TO_DEVICE : DMA_FROM_DEVICE; - blk_status_t ret = BLK_STS_IOERR; + blk_status_t ret = BLK_STS_RESOURCE; int nr_mapped; + if (blk_rq_nr_phys_segments(req) == 1) { + struct bio_vec bv = req_bvec(req); + + if (!is_pci_p2pdma_page(bv.bv_page)) { + if (bv.bv_offset + bv.bv_len <= dev->ctrl.page_size * 2) + return nvme_setup_prp_simple(dev, req, + &cmnd->rw, &bv); + + if (iod->nvmeq->qid && + dev->ctrl.sgls & ((1 << 0) | (1 << 1))) + return nvme_setup_sgl_simple(dev, req, + &cmnd->rw, &bv); + } + } + + iod->dma_len = 0; + iod->sg = mempool_alloc(dev->iod_mempool, GFP_ATOMIC); + if (!iod->sg) + return BLK_STS_RESOURCE; sg_init_table(iod->sg, blk_rq_nr_phys_segments(req)); - iod->nents = blk_rq_map_sg(q, req, iod->sg); + iod->nents = blk_rq_map_sg(req->q, req, iod->sg); if (!iod->nents) goto out; - ret = BLK_STS_RESOURCE; - if (is_pci_p2pdma_page(sg_page(iod->sg))) nr_mapped = pci_p2pdma_map_sg(dev->dev, iod->sg, iod->nents, - dma_dir); + rq_dma_dir(req)); else nr_mapped = dma_map_sg_attrs(dev->dev, iod->sg, iod->nents, - dma_dir, DMA_ATTR_NO_WARN); + rq_dma_dir(req), DMA_ATTR_NO_WARN); if (!nr_mapped) goto out; + iod->use_sgl = nvme_pci_use_sgls(dev, req); if (iod->use_sgl) ret = nvme_pci_setup_sgls(dev, req, &cmnd->rw, nr_mapped); else ret = nvme_pci_setup_prps(dev, req, &cmnd->rw); - - if (ret != BLK_STS_OK) - goto out_unmap; - - ret = BLK_STS_IOERR; - if (blk_integrity_rq(req)) { - if (blk_rq_count_integrity_sg(q, req->bio) != 1) - goto out_unmap; - - sg_init_table(&iod->meta_sg, 1); - if (blk_rq_map_integrity_sg(q, req->bio, &iod->meta_sg) != 1) - goto out_unmap; - - if (!dma_map_sg(dev->dev, &iod->meta_sg, 1, dma_dir)) - goto out_unmap; - - cmnd->rw.metadata = cpu_to_le64(sg_dma_address(&iod->meta_sg)); - } - - return BLK_STS_OK; - -out_unmap: - dma_unmap_sg(dev->dev, iod->sg, iod->nents, dma_dir); out: + if (ret != BLK_STS_OK) + nvme_unmap_data(dev, req); return ret; } -static void nvme_unmap_data(struct nvme_dev *dev, struct request *req) +static blk_status_t nvme_map_metadata(struct nvme_dev *dev, struct request *req, + struct nvme_command *cmnd) { struct nvme_iod *iod = blk_mq_rq_to_pdu(req); - enum dma_data_direction dma_dir = rq_data_dir(req) ? - DMA_TO_DEVICE : DMA_FROM_DEVICE; - - if (iod->nents) { - /* P2PDMA requests do not need to be unmapped */ - if (!is_pci_p2pdma_page(sg_page(iod->sg))) - dma_unmap_sg(dev->dev, iod->sg, iod->nents, dma_dir); - if (blk_integrity_rq(req)) - dma_unmap_sg(dev->dev, &iod->meta_sg, 1, dma_dir); - } - - nvme_cleanup_cmd(req); - nvme_free_iod(dev, req); + iod->meta_dma = dma_map_bvec(dev->dev, rq_integrity_vec(req), + rq_dma_dir(req), 0); + if (dma_mapping_error(dev->dev, iod->meta_dma)) + return BLK_STS_IOERR; + cmnd->rw.metadata = cpu_to_le64(iod->meta_dma); + return 0; } /* @@ -915,9 +910,14 @@ static blk_status_t nvme_queue_rq(struct blk_mq_hw_ctx *hctx, struct nvme_queue *nvmeq = hctx->driver_data; struct nvme_dev *dev = nvmeq->dev; struct request *req = bd->rq; + struct nvme_iod *iod = blk_mq_rq_to_pdu(req); struct nvme_command cmnd; blk_status_t ret; + iod->aborted = 0; + iod->npages = -1; + iod->nents = 0; + /* * We should not need to do this, but we're still using this to * ensure we can drain requests on a dying queue. @@ -929,21 +929,23 @@ static blk_status_t nvme_queue_rq(struct blk_mq_hw_ctx *hctx, if (ret) return ret; - ret = nvme_init_iod(req, dev); - if (ret) - goto out_free_cmd; - if (blk_rq_nr_phys_segments(req)) { ret = nvme_map_data(dev, req, &cmnd); if (ret) - goto out_cleanup_iod; + goto out_free_cmd; + } + + if (blk_integrity_rq(req)) { + ret = nvme_map_metadata(dev, req, &cmnd); + if (ret) + goto out_unmap_data; } blk_mq_start_request(req); nvme_submit_cmd(nvmeq, &cmnd, bd->last); return BLK_STS_OK; -out_cleanup_iod: - nvme_free_iod(dev, req); +out_unmap_data: + nvme_unmap_data(dev, req); out_free_cmd: nvme_cleanup_cmd(req); return ret; @@ -952,8 +954,14 @@ out_free_cmd: static void nvme_pci_complete_rq(struct request *req) { struct nvme_iod *iod = blk_mq_rq_to_pdu(req); + struct nvme_dev *dev = iod->nvmeq->dev; - nvme_unmap_data(iod->nvmeq->dev, req); + nvme_cleanup_cmd(req); + if (blk_integrity_rq(req)) + dma_unmap_page(dev->dev, iod->meta_dma, + rq_integrity_vec(req)->bv_len, rq_data_dir(req)); + if (blk_rq_nr_phys_segments(req)) + nvme_unmap_data(dev, req); nvme_complete_rq(req); } @@ -1088,7 +1096,7 @@ static int nvme_poll_irqdisable(struct nvme_queue *nvmeq, unsigned int tag) * using the CQ lock. For normal interrupt driven threads we have * to disable the interrupt to avoid racing with it. */ - if (nvmeq->cq_vector == -1) { + if (test_bit(NVMEQ_POLLED, &nvmeq->flags)) { spin_lock(&nvmeq->cq_poll_lock); found = nvme_process_cq(nvmeq, &start, &end, tag); spin_unlock(&nvmeq->cq_poll_lock); @@ -1148,7 +1156,7 @@ static int adapter_alloc_cq(struct nvme_dev *dev, u16 qid, struct nvme_command c; int flags = NVME_QUEUE_PHYS_CONTIG; - if (vector != -1) + if (!test_bit(NVMEQ_POLLED, &nvmeq->flags)) flags |= NVME_CQ_IRQ_ENABLED; /* @@ -1161,10 +1169,7 @@ static int adapter_alloc_cq(struct nvme_dev *dev, u16 qid, c.create_cq.cqid = cpu_to_le16(qid); c.create_cq.qsize = cpu_to_le16(nvmeq->q_depth - 1); c.create_cq.cq_flags = cpu_to_le16(flags); - if (vector != -1) - c.create_cq.irq_vector = cpu_to_le16(vector); - else - c.create_cq.irq_vector = 0; + c.create_cq.irq_vector = cpu_to_le16(vector); return nvme_submit_sync_cmd(dev->ctrl.admin_q, &c, NULL, 0); } @@ -1371,16 +1376,16 @@ static enum blk_eh_timer_return nvme_timeout(struct request *req, bool reserved) static void nvme_free_queue(struct nvme_queue *nvmeq) { - dma_free_coherent(nvmeq->q_dmadev, CQ_SIZE(nvmeq->q_depth), + dma_free_coherent(nvmeq->dev->dev, CQ_SIZE(nvmeq->q_depth), (void *)nvmeq->cqes, nvmeq->cq_dma_addr); if (!nvmeq->sq_cmds) return; if (test_and_clear_bit(NVMEQ_SQ_CMB, &nvmeq->flags)) { - pci_free_p2pmem(to_pci_dev(nvmeq->q_dmadev), + pci_free_p2pmem(to_pci_dev(nvmeq->dev->dev), nvmeq->sq_cmds, SQ_SIZE(nvmeq->q_depth)); } else { - dma_free_coherent(nvmeq->q_dmadev, SQ_SIZE(nvmeq->q_depth), + dma_free_coherent(nvmeq->dev->dev, SQ_SIZE(nvmeq->q_depth), nvmeq->sq_cmds, nvmeq->sq_dma_addr); } } @@ -1410,10 +1415,8 @@ static int nvme_suspend_queue(struct nvme_queue *nvmeq) nvmeq->dev->online_queues--; if (!nvmeq->qid && nvmeq->dev->ctrl.admin_q) blk_mq_quiesce_queue(nvmeq->dev->ctrl.admin_q); - if (nvmeq->cq_vector == -1) - return 0; - pci_free_irq(to_pci_dev(nvmeq->dev->dev), nvmeq->cq_vector, nvmeq); - nvmeq->cq_vector = -1; + if (!test_and_clear_bit(NVMEQ_POLLED, &nvmeq->flags)) + pci_free_irq(to_pci_dev(nvmeq->dev->dev), nvmeq->cq_vector, nvmeq); return 0; } @@ -1498,7 +1501,6 @@ static int nvme_alloc_queue(struct nvme_dev *dev, int qid, int depth) if (nvme_alloc_sq_cmds(dev, nvmeq, qid, depth)) goto free_cqdma; - nvmeq->q_dmadev = dev->dev; nvmeq->dev = dev; spin_lock_init(&nvmeq->sq_lock); spin_lock_init(&nvmeq->cq_poll_lock); @@ -1507,7 +1509,6 @@ static int nvme_alloc_queue(struct nvme_dev *dev, int qid, int depth) nvmeq->q_db = &dev->dbs[qid * 2 * dev->db_stride]; nvmeq->q_depth = depth; nvmeq->qid = qid; - nvmeq->cq_vector = -1; dev->ctrl.queue_count++; return 0; @@ -1552,7 +1553,7 @@ static int nvme_create_queue(struct nvme_queue *nvmeq, int qid, bool polled) { struct nvme_dev *dev = nvmeq->dev; int result; - s16 vector; + u16 vector = 0; clear_bit(NVMEQ_DELETE_ERROR, &nvmeq->flags); @@ -1563,7 +1564,7 @@ static int nvme_create_queue(struct nvme_queue *nvmeq, int qid, bool polled) if (!polled) vector = dev->num_vecs == 1 ? 0 : qid; else - vector = -1; + set_bit(NVMEQ_POLLED, &nvmeq->flags); result = adapter_alloc_cq(dev, qid, nvmeq, vector); if (result) @@ -1578,7 +1579,8 @@ static int nvme_create_queue(struct nvme_queue *nvmeq, int qid, bool polled) nvmeq->cq_vector = vector; nvme_init_queue(nvmeq, qid); - if (vector != -1) { + if (!polled) { + nvmeq->cq_vector = vector; result = queue_request_irq(nvmeq); if (result < 0) goto release_sq; @@ -1588,7 +1590,6 @@ static int nvme_create_queue(struct nvme_queue *nvmeq, int qid, bool polled) return result; release_sq: - nvmeq->cq_vector = -1; dev->online_queues--; adapter_delete_sq(dev, qid); release_cq: @@ -1639,7 +1640,7 @@ static int nvme_alloc_admin_tags(struct nvme_dev *dev) dev->admin_tagset.queue_depth = NVME_AQ_MQ_TAG_DEPTH; dev->admin_tagset.timeout = ADMIN_TIMEOUT; dev->admin_tagset.numa_node = dev_to_node(dev->dev); - dev->admin_tagset.cmd_size = nvme_pci_cmd_size(dev, false); + dev->admin_tagset.cmd_size = sizeof(struct nvme_iod); dev->admin_tagset.flags = BLK_MQ_F_NO_SCHED; dev->admin_tagset.driver_data = dev; @@ -1730,7 +1731,7 @@ static int nvme_pci_configure_admin_queue(struct nvme_dev *dev) nvme_init_queue(nvmeq, 0); result = queue_request_irq(nvmeq); if (result) { - nvmeq->cq_vector = -1; + dev->online_queues--; return result; } @@ -2171,10 +2172,8 @@ static int nvme_setup_io_queues(struct nvme_dev *dev) * number of interrupts. */ result = queue_request_irq(adminq); - if (result) { - adminq->cq_vector = -1; + if (result) return result; - } set_bit(NVMEQ_ENABLED, &adminq->flags); result = nvme_create_io_queues(dev); @@ -2286,11 +2285,7 @@ static int nvme_dev_add(struct nvme_dev *dev) dev->tagset.numa_node = dev_to_node(dev->dev); dev->tagset.queue_depth = min_t(int, dev->q_depth, BLK_MQ_MAX_DEPTH) - 1; - dev->tagset.cmd_size = nvme_pci_cmd_size(dev, false); - if ((dev->ctrl.sgls & ((1 << 0) | (1 << 1))) && sgl_threshold) { - dev->tagset.cmd_size = max(dev->tagset.cmd_size, - nvme_pci_cmd_size(dev, true)); - } + dev->tagset.cmd_size = sizeof(struct nvme_iod); dev->tagset.flags = BLK_MQ_F_SHOULD_MERGE; dev->tagset.driver_data = dev; diff --git a/drivers/nvme/target/core.c b/drivers/nvme/target/core.c index b3e765a95af8..4d8dd29479c0 100644 --- a/drivers/nvme/target/core.c +++ b/drivers/nvme/target/core.c @@ -214,6 +214,8 @@ void nvmet_ns_changed(struct nvmet_subsys *subsys, u32 nsid) { struct nvmet_ctrl *ctrl; + lockdep_assert_held(&subsys->lock); + list_for_each_entry(ctrl, &subsys->ctrls, subsys_entry) { nvmet_add_to_changed_ns_log(ctrl, cpu_to_le32(nsid)); if (nvmet_aen_bit_disabled(ctrl, NVME_AEN_BIT_NS_ATTR)) @@ -494,13 +496,14 @@ int nvmet_ns_enable(struct nvmet_ns *ns) int ret; mutex_lock(&subsys->lock); - ret = -EMFILE; - if (subsys->nr_namespaces == NVMET_MAX_NAMESPACES) - goto out_unlock; ret = 0; if (ns->enabled) goto out_unlock; + ret = -EMFILE; + if (subsys->nr_namespaces == NVMET_MAX_NAMESPACES) + goto out_unlock; + ret = nvmet_bdev_ns_enable(ns); if (ret == -ENOTBLK) ret = nvmet_file_ns_enable(ns); diff --git a/drivers/nvme/target/fc.c b/drivers/nvme/target/fc.c index 98b7b1f4ee96..9369a11fe7a9 100644 --- a/drivers/nvme/target/fc.c +++ b/drivers/nvme/target/fc.c @@ -128,12 +128,12 @@ struct nvmet_fc_tgt_queue { struct nvmet_cq nvme_cq; struct nvmet_sq nvme_sq; struct nvmet_fc_tgt_assoc *assoc; - struct nvmet_fc_fcp_iod *fod; /* array of fcp_iods */ struct list_head fod_list; struct list_head pending_cmd_list; struct list_head avail_defer_list; struct workqueue_struct *work_q; struct kref ref; + struct nvmet_fc_fcp_iod fod[]; /* array of fcp_iods */ } __aligned(sizeof(unsigned long long)); struct nvmet_fc_tgt_assoc { @@ -588,9 +588,7 @@ nvmet_fc_alloc_target_queue(struct nvmet_fc_tgt_assoc *assoc, if (qid > NVMET_NR_QUEUES) return NULL; - queue = kzalloc((sizeof(*queue) + - (sizeof(struct nvmet_fc_fcp_iod) * sqsize)), - GFP_KERNEL); + queue = kzalloc(struct_size(queue, fod, sqsize), GFP_KERNEL); if (!queue) return NULL; @@ -603,7 +601,6 @@ nvmet_fc_alloc_target_queue(struct nvmet_fc_tgt_assoc *assoc, if (!queue->work_q) goto out_a_put; - queue->fod = (struct nvmet_fc_fcp_iod *)&queue[1]; queue->qid = qid; queue->sqsize = sqsize; queue->assoc = assoc; diff --git a/drivers/nvme/target/io-cmd-bdev.c b/drivers/nvme/target/io-cmd-bdev.c index a065dbfc43b1..3efc52f9c309 100644 --- a/drivers/nvme/target/io-cmd-bdev.c +++ b/drivers/nvme/target/io-cmd-bdev.c @@ -196,7 +196,7 @@ static u16 nvmet_bdev_discard_range(struct nvmet_req *req, GFP_KERNEL, 0, bio); if (ret && ret != -EOPNOTSUPP) { req->error_slba = le64_to_cpu(range->slba); - return blk_to_nvme_status(req, errno_to_blk_status(ret)); + return errno_to_nvme_status(req, ret); } return NVME_SC_SUCCESS; } @@ -252,7 +252,6 @@ static void nvmet_bdev_execute_write_zeroes(struct nvmet_req *req) { struct nvme_write_zeroes_cmd *write_zeroes = &req->cmd->write_zeroes; struct bio *bio = NULL; - u16 status = NVME_SC_SUCCESS; sector_t sector; sector_t nr_sector; int ret; @@ -264,13 +263,12 @@ static void nvmet_bdev_execute_write_zeroes(struct nvmet_req *req) ret = __blkdev_issue_zeroout(req->ns->bdev, sector, nr_sector, GFP_KERNEL, &bio, 0); - status = blk_to_nvme_status(req, errno_to_blk_status(ret)); if (bio) { bio->bi_private = req; bio->bi_end_io = nvmet_bio_done; submit_bio(bio); } else { - nvmet_req_complete(req, status); + nvmet_req_complete(req, errno_to_nvme_status(req, ret)); } } diff --git a/drivers/nvme/target/tcp.c b/drivers/nvme/target/tcp.c index ad0df786fe93..0a941abf56ec 100644 --- a/drivers/nvme/target/tcp.c +++ b/drivers/nvme/target/tcp.c @@ -371,7 +371,8 @@ static void nvmet_setup_c2h_data_pdu(struct nvmet_tcp_cmd *cmd) cmd->state = NVMET_TCP_SEND_DATA_PDU; pdu->hdr.type = nvme_tcp_c2h_data; - pdu->hdr.flags = NVME_TCP_F_DATA_LAST; + pdu->hdr.flags = NVME_TCP_F_DATA_LAST | (queue->nvme_sq.sqhd_disabled ? + NVME_TCP_F_DATA_SUCCESS : 0); pdu->hdr.hlen = sizeof(*pdu); pdu->hdr.pdo = pdu->hdr.hlen + hdgst; pdu->hdr.plen = @@ -542,8 +543,19 @@ static int nvmet_try_send_data(struct nvmet_tcp_cmd *cmd) cmd->state = NVMET_TCP_SEND_DDGST; cmd->offset = 0; } else { - nvmet_setup_response_pdu(cmd); + if (queue->nvme_sq.sqhd_disabled) { + cmd->queue->snd_cmd = NULL; + nvmet_tcp_put_cmd(cmd); + } else { + nvmet_setup_response_pdu(cmd); + } } + + if (queue->nvme_sq.sqhd_disabled) { + kfree(cmd->iov); + sgl_free(cmd->req.sg); + } + return 1; } @@ -619,7 +631,13 @@ static int nvmet_try_send_ddgst(struct nvmet_tcp_cmd *cmd) return ret; cmd->offset += ret; - nvmet_setup_response_pdu(cmd); + + if (queue->nvme_sq.sqhd_disabled) { + cmd->queue->snd_cmd = NULL; + nvmet_tcp_put_cmd(cmd); + } else { + nvmet_setup_response_pdu(cmd); + } return 1; } diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c index 2b2bc4b49d78..ebc80354714c 100644 --- a/drivers/scsi/sd.c +++ b/drivers/scsi/sd.c @@ -2256,22 +2256,6 @@ static void read_capacity_error(struct scsi_disk *sdkp, struct scsi_device *sdp, #define READ_CAPACITY_RETRIES_ON_RESET 10 -/* - * Ensure that we don't overflow sector_t when CONFIG_LBDAF is not set - * and the reported logical block size is bigger than 512 bytes. Note - * that last_sector is a u64 and therefore logical_to_sectors() is not - * applicable. - */ -static bool sd_addressable_capacity(u64 lba, unsigned int sector_size) -{ - u64 last_sector = (lba + 1ULL) << (ilog2(sector_size) - 9); - - if (sizeof(sector_t) == 4 && last_sector > U32_MAX) - return false; - - return true; -} - static int read_capacity_16(struct scsi_disk *sdkp, struct scsi_device *sdp, unsigned char *buffer) { @@ -2337,14 +2321,6 @@ static int read_capacity_16(struct scsi_disk *sdkp, struct scsi_device *sdp, return -ENODEV; } - if (!sd_addressable_capacity(lba, sector_size)) { - sd_printk(KERN_ERR, sdkp, "Too big for this kernel. Use a " - "kernel compiled with support for large block " - "devices.\n"); - sdkp->capacity = 0; - return -EOVERFLOW; - } - /* Logical blocks per physical block exponent */ sdkp->physical_block_size = (1 << (buffer[13] & 0xf)) * sector_size; @@ -2426,14 +2402,6 @@ static int read_capacity_10(struct scsi_disk *sdkp, struct scsi_device *sdp, return sector_size; } - if (!sd_addressable_capacity(lba, sector_size)) { - sd_printk(KERN_ERR, sdkp, "Too big for this kernel. Use a " - "kernel compiled with support for large block " - "devices.\n"); - sdkp->capacity = 0; - return -EOVERFLOW; - } - sdkp->capacity = lba + 1; sdkp->physical_block_size = sector_size; return sector_size; @@ -3325,6 +3293,7 @@ static void sd_probe_async(void *data, async_cookie_t cookie) if (sdp->removable) { gd->flags |= GENHD_FL_REMOVABLE; gd->events |= DISK_EVENT_MEDIA_CHANGE; + gd->event_flags = DISK_EVENT_FLAG_POLL | DISK_EVENT_FLAG_UEVENT; } blk_pm_runtime_init(sdp->request_queue, dev); diff --git a/drivers/scsi/sr.c b/drivers/scsi/sr.c index 039c27c2d7b3..c3f443d5aea8 100644 --- a/drivers/scsi/sr.c +++ b/drivers/scsi/sr.c @@ -716,6 +716,7 @@ static int sr_probe(struct device *dev) disk->fops = &sr_bdops; disk->flags = GENHD_FL_CD | GENHD_FL_BLOCK_EVENTS_ON_EXCL_WRITE; disk->events = DISK_EVENT_MEDIA_CHANGE | DISK_EVENT_EJECT_REQUEST; + disk->event_flags = DISK_EVENT_FLAG_POLL | DISK_EVENT_FLAG_UEVENT; blk_queue_rq_timeout(sdev->request_queue, SR_TIMEOUT); diff --git a/drivers/xen/biomerge.c b/drivers/xen/biomerge.c index f3fbb700f569..05a286d24f14 100644 --- a/drivers/xen/biomerge.c +++ b/drivers/xen/biomerge.c @@ -4,12 +4,13 @@ #include <xen/xen.h> #include <xen/page.h> +/* check if @page can be merged with 'vec1' */ bool xen_biovec_phys_mergeable(const struct bio_vec *vec1, - const struct bio_vec *vec2) + const struct page *page) { #if XEN_PAGE_SIZE == PAGE_SIZE unsigned long bfn1 = pfn_to_bfn(page_to_pfn(vec1->bv_page)); - unsigned long bfn2 = pfn_to_bfn(page_to_pfn(vec2->bv_page)); + unsigned long bfn2 = pfn_to_bfn(page_to_pfn(page)); return bfn1 + PFN_DOWN(vec1->bv_offset + vec1->bv_len) == bfn2; #else |