diff options
| author | Linus Torvalds <torvalds@linux-foundation.org> | 2019-05-07 18:14:36 -0700 |
|---|---|---|
| committer | Linus Torvalds <torvalds@linux-foundation.org> | 2019-05-07 18:14:36 -0700 |
| commit | 67a242223958d628f0ba33283668e3ddd192d057 (patch) | |
| tree | a39e7039e9a2ef9ab46f8ba561175dbdc6101d11 /drivers | |
| parent | 8b35ad6232c462b02e397e87ce702bcddd4ba543 (diff) | |
| parent | b8753433fc611e23e31300e1d099001a08955c88 (diff) | |
Merge tag 'for-5.2/block-20190507' of git://git.kernel.dk/linux-block
Pull block updates from Jens Axboe:
"Nothing major in this series, just fixes and improvements all over the
map. This contains:
- Series of fixes for sed-opal (David, Jonas)
- Fixes and performance tweaks for BFQ (via Paolo)
- Set of fixes for bcache (via Coly)
- Set of fixes for md (via Song)
- Enabling multi-page for passthrough requests (Ming)
- Queue release fix series (Ming)
- Device notification improvements (Martin)
- Propagate underlying device rotational status in loop (Holger)
- Removal of mtip32xx trim support, which has been disabled for years
(Christoph)
- Improvement and cleanup of nvme command handling (Christoph)
- Add block SPDX tags (Christoph)
- Cleanup/hardening of bio/bvec iteration (Christoph)
- A few NVMe pull requests (Christoph)
- Removal of CONFIG_LBDAF (Christoph)
- Various little fixes here and there"
* tag 'for-5.2/block-20190507' of git://git.kernel.dk/linux-block: (164 commits)
block: fix mismerge in bvec_advance
block: don't drain in-progress dispatch in blk_cleanup_queue()
blk-mq: move cancel of hctx->run_work into blk_mq_hw_sysfs_release
blk-mq: always free hctx after request queue is freed
blk-mq: split blk_mq_alloc_and_init_hctx into two parts
blk-mq: free hw queue's resource in hctx's release handler
blk-mq: move cancel of requeue_work into blk_mq_release
blk-mq: grab .q_usage_counter when queuing request from plug code path
block: fix function name in comment
nvmet: protect discovery change log event list iteration
nvme: mark nvme_core_init and nvme_core_exit static
nvme: move command size checks to the core
nvme-fabrics: check more command sizes
nvme-pci: check more command sizes
nvme-pci: remove an unneeded variable initialization
nvme-pci: unquiesce admin queue on shutdown
nvme-pci: shutdown on timeout during deletion
nvme-pci: fix psdt field for single segment sgls
nvme-multipath: don't print ANA group state by default
nvme-multipath: split bios with the ns_head bio_set before submitting
...
Diffstat (limited to 'drivers')
62 files changed, 636 insertions, 667 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/brd.c b/drivers/block/brd.c index c18586fccb6f..17defbf4f332 100644 --- a/drivers/block/brd.c +++ b/drivers/block/brd.c @@ -96,13 +96,8 @@ static struct page *brd_insert_page(struct brd_device *brd, sector_t sector) /* * Must use NOIO because we don't want to recurse back into the * block or filesystem layers from page reclaim. - * - * Cannot support DAX and highmem, because our ->direct_access - * routine for DAX must return memory that is always addressable. - * If DAX was reworked to use pfns and kmap throughout, this - * restriction might be able to be lifted. */ - gfp_flags = GFP_NOIO | __GFP_ZERO; + gfp_flags = GFP_NOIO | __GFP_ZERO | __GFP_HIGHMEM; page = alloc_page(gfp_flags); if (!page) return NULL; diff --git a/drivers/block/drbd/drbd_int.h b/drivers/block/drbd/drbd_int.h index f070f7200fc0..549c64df9708 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 49f89db0766f..b8998abd86a5 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/mtip32xx/mtip32xx.c b/drivers/block/mtip32xx/mtip32xx.c index 83302ecdc8db..f0105d118056 100644 --- a/drivers/block/mtip32xx/mtip32xx.c +++ b/drivers/block/mtip32xx/mtip32xx.c @@ -1192,14 +1192,6 @@ static int mtip_get_identify(struct mtip_port *port, void __user *user_buffer) else clear_bit(MTIP_DDF_SEC_LOCK_BIT, &port->dd->dd_flag); -#ifdef MTIP_TRIM /* Disabling TRIM support temporarily */ - /* Demux ID.DRAT & ID.RZAT to determine trim support */ - if (port->identify[69] & (1 << 14) && port->identify[69] & (1 << 5)) - port->dd->trim_supp = true; - else -#endif - port->dd->trim_supp = false; - /* Set the identify buffer as valid. */ port->identify_valid = 1; @@ -1387,77 +1379,6 @@ static int mtip_get_smart_attr(struct mtip_port *port, unsigned int id, } /* - * Trim unused sectors - * - * @dd pointer to driver_data structure - * @lba starting lba - * @len # of 512b sectors to trim - */ -static blk_status_t mtip_send_trim(struct driver_data *dd, unsigned int lba, - unsigned int len) -{ - u64 tlba, tlen, sect_left; - struct mtip_trim_entry *buf; - dma_addr_t dma_addr; - struct host_to_dev_fis fis; - blk_status_t ret = BLK_STS_OK; - int i; - - if (!len || dd->trim_supp == false) - return BLK_STS_IOERR; - - /* Trim request too big */ - WARN_ON(len > (MTIP_MAX_TRIM_ENTRY_LEN * MTIP_MAX_TRIM_ENTRIES)); - - /* Trim request not aligned on 4k boundary */ - WARN_ON(len % 8 != 0); - - /* Warn if vu_trim structure is too big */ - WARN_ON(sizeof(struct mtip_trim) > ATA_SECT_SIZE); - - /* Allocate a DMA buffer for the trim structure */ - buf = dma_alloc_coherent(&dd->pdev->dev, ATA_SECT_SIZE, &dma_addr, - GFP_KERNEL); - if (!buf) - return BLK_STS_RESOURCE; - memset(buf, 0, ATA_SECT_SIZE); - - for (i = 0, sect_left = len, tlba = lba; - i < MTIP_MAX_TRIM_ENTRIES && sect_left; - i++) { - tlen = (sect_left >= MTIP_MAX_TRIM_ENTRY_LEN ? - MTIP_MAX_TRIM_ENTRY_LEN : - sect_left); - buf[i].lba = cpu_to_le32(tlba); - buf[i].range = cpu_to_le16(tlen); - tlba += tlen; - sect_left -= tlen; - } - WARN_ON(sect_left != 0); - - /* Build the fis */ - memset(&fis, 0, sizeof(struct host_to_dev_fis)); - fis.type = 0x27; - fis.opts = 1 << 7; - fis.command = 0xfb; - fis.features = 0x60; - fis.sect_count = 1; - fis.device = ATA_DEVICE_OBS; - - if (mtip_exec_internal_command(dd->port, - &fis, - 5, - dma_addr, - ATA_SECT_SIZE, - 0, - MTIP_TRIM_TIMEOUT_MS) < 0) - ret = BLK_STS_IOERR; - - dma_free_coherent(&dd->pdev->dev, ATA_SECT_SIZE, buf, dma_addr); - return ret; -} - -/* * Get the drive capacity. * * @dd Pointer to the device data structure. @@ -3590,8 +3511,6 @@ static blk_status_t mtip_queue_rq(struct blk_mq_hw_ctx *hctx, blk_mq_start_request(rq); - if (req_op(rq) == REQ_OP_DISCARD) - return mtip_send_trim(dd, blk_rq_pos(rq), blk_rq_sectors(rq)); mtip_hw_submit_io(dd, rq, cmd, hctx); return BLK_STS_OK; } @@ -3769,14 +3688,6 @@ skip_create_disk: blk_queue_max_segment_size(dd->queue, 0x400000); blk_queue_io_min(dd->queue, 4096); - /* Signal trim support */ - if (dd->trim_supp == true) { - blk_queue_flag_set(QUEUE_FLAG_DISCARD, dd->queue); - dd->queue->limits.discard_granularity = 4096; - blk_queue_max_discard_sectors(dd->queue, - MTIP_MAX_TRIM_ENTRY_LEN * MTIP_MAX_TRIM_ENTRIES); - } - /* Set the capacity of the device in 512 byte sectors. */ if (!(mtip_hw_get_capacity(dd, &capacity))) { dev_warn(&dd->pdev->dev, diff --git a/drivers/block/mtip32xx/mtip32xx.h b/drivers/block/mtip32xx/mtip32xx.h index abce25f27f57..91c1cb5b1532 100644 --- a/drivers/block/mtip32xx/mtip32xx.h +++ b/drivers/block/mtip32xx/mtip32xx.h @@ -193,21 +193,6 @@ struct mtip_work { mtip_workq_sdbfx(w->port, group, w->completed); \ } -#define MTIP_TRIM_TIMEOUT_MS 240000 -#define MTIP_MAX_TRIM_ENTRIES 8 -#define MTIP_MAX_TRIM_ENTRY_LEN 0xfff8 - -struct mtip_trim_entry { - __le32 lba; /* starting lba of region */ - __le16 rsvd; /* unused */ - __le16 range; /* # of 512b blocks to trim */ -} __packed; - -struct mtip_trim { - /* Array of regions to trim */ - struct mtip_trim_entry entry[MTIP_MAX_TRIM_ENTRIES]; -} __packed; - /* Register Frame Information Structure (FIS), host to device. */ struct host_to_dev_fis { /* @@ -474,8 +459,6 @@ struct driver_data { struct dentry *dfs_node; - bool trim_supp; /* flag indicating trim support */ - bool sr; int numa_node; /* NUMA support */ 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/bcache/alloc.c b/drivers/md/bcache/alloc.c index 5002838ea476..f8986effcb50 100644 --- a/drivers/md/bcache/alloc.c +++ b/drivers/md/bcache/alloc.c @@ -327,10 +327,11 @@ static int bch_allocator_thread(void *arg) * possibly issue discards to them, then we add the bucket to * the free list: */ - while (!fifo_empty(&ca->free_inc)) { + while (1) { long bucket; - fifo_pop(&ca->free_inc, bucket); + if (!fifo_pop(&ca->free_inc, bucket)) + break; if (ca->discard) { mutex_unlock(&ca->set->bucket_lock); diff --git a/drivers/md/bcache/btree.c b/drivers/md/bcache/btree.c index 64def336f053..773f5fdad25f 100644 --- a/drivers/md/bcache/btree.c +++ b/drivers/md/bcache/btree.c @@ -429,14 +429,14 @@ static void do_btree_node_write(struct btree *b) bset_sector_offset(&b->keys, i)); if (!bch_bio_alloc_pages(b->bio, __GFP_NOWARN|GFP_NOWAIT)) { - int j; struct bio_vec *bv; - void *base = (void *) ((unsigned long) i & ~(PAGE_SIZE - 1)); + void *addr = (void *) ((unsigned long) i & ~(PAGE_SIZE - 1)); struct bvec_iter_all iter_all; - bio_for_each_segment_all(bv, b->bio, j, iter_all) - memcpy(page_address(bv->bv_page), - base + j * PAGE_SIZE, PAGE_SIZE); + bio_for_each_segment_all(bv, b->bio, iter_all) { + memcpy(page_address(bv->bv_page), addr, PAGE_SIZE); + addr += PAGE_SIZE; + } bch_submit_bbio(b->bio, b->c, &k.key, 0); @@ -1476,11 +1476,11 @@ static int btree_gc_coalesce(struct btree *b, struct btree_op *op, out_nocoalesce: closure_sync(&cl); - bch_keylist_free(&keylist); while ((k = bch_keylist_pop(&keylist))) if (!bkey_cmp(k, &ZERO_KEY)) atomic_dec(&b->c->prio_blocked); + bch_keylist_free(&keylist); for (i = 0; i < nodes; i++) if (!IS_ERR_OR_NULL(new_nodes[i])) { diff --git a/drivers/md/bcache/journal.c b/drivers/md/bcache/journal.c index b2fd412715b1..12dae9348147 100644 --- a/drivers/md/bcache/journal.c +++ b/drivers/md/bcache/journal.c @@ -147,7 +147,7 @@ int bch_journal_read(struct cache_set *c, struct list_head *list) { #define read_bucket(b) \ ({ \ - int ret = journal_read_bucket(ca, list, b); \ + ret = journal_read_bucket(ca, list, b); \ __set_bit(b, bitmap); \ if (ret < 0) \ return ret; \ @@ -156,6 +156,7 @@ int bch_journal_read(struct cache_set *c, struct list_head *list) struct cache *ca; unsigned int iter; + int ret = 0; for_each_cache(ca, c, iter) { struct journal_device *ja = &ca->journal; @@ -267,7 +268,7 @@ bsearch: struct journal_replay, list)->j.seq; - return 0; + return ret; #undef read_bucket } @@ -317,6 +318,18 @@ void bch_journal_mark(struct cache_set *c, struct list_head *list) } } +static bool is_discard_enabled(struct cache_set *s) +{ + struct cache *ca; + unsigned int i; + + for_each_cache(ca, s, i) + if (ca->discard) + return true; + + return false; +} + int bch_journal_replay(struct cache_set *s, struct list_head *list) { int ret = 0, keys = 0, entries = 0; @@ -330,9 +343,17 @@ int bch_journal_replay(struct cache_set *s, struct list_head *list) list_for_each_entry(i, list, list) { BUG_ON(i->pin && atomic_read(i->pin) != 1); - cache_set_err_on(n != i->j.seq, s, -"bcache: journal entries %llu-%llu missing! (replaying %llu-%llu)", - n, i->j.seq - 1, start, end); + if (n != i->j.seq) { + if (n == start && is_discard_enabled(s)) + pr_info("bcache: journal entries %llu-%llu may be discarded! (replaying %llu-%llu)", + n, i->j.seq - 1, start, end); + else { + pr_err("bcache: journal entries %llu-%llu missing! (replaying %llu-%llu)", + n, i->j.seq - 1, start, end); + ret = -EIO; + goto err; + } + } for (k = i->j.start; k < bset_bkey_last(&i->j); @@ -540,11 +561,11 @@ static void journal_reclaim(struct cache_set *c) ca->sb.nr_this_dev); } - bkey_init(k); - SET_KEY_PTRS(k, n); - - if (n) + if (n) { + bkey_init(k); + SET_KEY_PTRS(k, n); c->journal.blocks_free = c->sb.bucket_size >> c->block_bits; + } out: if (!journal_full(&c->journal)) __closure_wake_up(&c->journal.wait); @@ -671,6 +692,9 @@ static void journal_write_unlocked(struct closure *cl) ca->journal.seq[ca->journal.cur_idx] = w->data->seq; } + /* If KEY_PTRS(k) == 0, this jset gets lost in air */ + BUG_ON(i == 0); + atomic_dec_bug(&fifo_back(&c->journal.pin)); bch_journal_next(&c->journal); journal_reclaim(c); diff --git a/drivers/md/bcache/request.c b/drivers/md/bcache/request.c index f101bfe8657a..41adcd1546f1 100644 --- a/drivers/md/bcache/request.c +++ b/drivers/md/bcache/request.c @@ -329,12 +329,13 @@ void bch_data_insert(struct closure *cl) bch_data_insert_start(cl); } -/* Congested? */ - -unsigned int bch_get_congested(struct cache_set *c) +/* + * Congested? Return 0 (not congested) or the limit (in sectors) + * beyond which we should bypass the cache due to congestion. + */ +unsigned int bch_get_congested(const struct cache_set *c) { int i; - long rand; if (!c->congested_read_threshold_us && !c->congested_write_threshold_us) @@ -353,8 +354,7 @@ unsigned int bch_get_congested(struct cache_set *c) if (i > 0) i = fract_exp_two(i, 6); - rand = get_random_int(); - i -= bitmap_weight(&rand, BITS_PER_LONG); + i -= hweight32(get_random_u32()); return i > 0 ? i : 1; } @@ -376,7 +376,7 @@ static bool check_should_bypass(struct cached_dev *dc, struct bio *bio) { struct cache_set *c = dc->disk.c; unsigned int mode = cache_mode(dc); - unsigned int sectors, congested = bch_get_congested(c); + unsigned int sectors, congested; struct task_struct *task = current; struct io *i; @@ -412,6 +412,7 @@ static bool check_should_bypass(struct cached_dev *dc, struct bio *bio) goto rescale; } + congested = bch_get_congested(c); if (!congested && !dc->sequential_cutoff) goto rescale; @@ -706,14 +707,14 @@ static void search_free(struct closure *cl) { struct search *s = container_of(cl, struct search, cl); - atomic_dec(&s->d->c->search_inflight); + atomic_dec(&s->iop.c->search_inflight); if (s->iop.bio) bio_put(s->iop.bio); bio_complete(s); closure_debug_destroy(cl); - mempool_free(s, &s->d->c->search); + mempool_free(s, &s->iop.c->search); } static inline struct search *search_alloc(struct bio *bio, @@ -756,13 +757,13 @@ static void cached_dev_bio_complete(struct closure *cl) struct search *s = container_of(cl, struct search, cl); struct cached_dev *dc = container_of(s->d, struct cached_dev, disk); - search_free(cl); cached_dev_put(dc); + search_free(cl); } /* Process reads */ -static void cached_dev_cache_miss_done(struct closure *cl) +static void cached_dev_read_error_done(struct closure *cl) { struct search *s = container_of(cl, struct search, cl); @@ -800,7 +801,22 @@ static void cached_dev_read_error(struct closure *cl) closure_bio_submit(s->iop.c, bio, cl); } - continue_at(cl, cached_dev_cache_miss_done, NULL); + continue_at(cl, cached_dev_read_error_done, NULL); +} + +static void cached_dev_cache_miss_done(struct closure *cl) +{ + struct search *s = container_of(cl, struct search, cl); + struct bcache_device *d = s->d; + + if (s->iop.replace_collision) + bch_mark_cache_miss_collision(s->iop.c, s->d); + + if (s->iop.bio) + bio_free_pages(s->iop.bio); + + cached_dev_bio_complete(cl); + closure_put(&d->cl); } static void cached_dev_read_done(struct closure *cl) @@ -833,6 +849,7 @@ static void cached_dev_read_done(struct closure *cl) if (verify(dc) && s->recoverable && !s->read_dirty_data) bch_data_verify(dc, s->orig_bio); + closure_get(&dc->disk.cl); bio_complete(s); if (s->iop.bio && diff --git a/drivers/md/bcache/request.h b/drivers/md/bcache/request.h index 721bf336ed1a..c64dbd7a91aa 100644 --- a/drivers/md/bcache/request.h +++ b/drivers/md/bcache/request.h @@ -33,7 +33,7 @@ struct data_insert_op { BKEY_PADDED(replace_key); }; -unsigned int bch_get_congested(struct cache_set *c); +unsigned int bch_get_congested(const struct cache_set *c); void bch_data_insert(struct closure *cl); void bch_cached_dev_request_init(struct cached_dev *dc); diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c index a697a3a923cd..1b63ac876169 100644 --- a/drivers/md/bcache/super.c +++ b/drivers/md/bcache/super.c @@ -662,6 +662,11 @@ static const struct block_device_operations bcache_ops = { void bcache_device_stop(struct bcache_device *d) { if (!test_and_set_bit(BCACHE_DEV_CLOSING, &d->flags)) + /* + * closure_fn set to + * - cached device: cached_dev_flush() + * - flash dev: flash_dev_flush() + */ closure_queue(&d->cl); } @@ -906,21 +911,18 @@ static int cached_dev_status_update(void *arg) void bch_cached_dev_run(struct cached_dev *dc) { struct bcache_device *d = &dc->disk; - char buf[SB_LABEL_SIZE + 1]; + char *buf = kmemdup_nul(dc->sb.label, SB_LABEL_SIZE, GFP_KERNEL); char *env[] = { "DRIVER=bcache", kasprintf(GFP_KERNEL, "CACHED_UUID=%pU", dc->sb.uuid), - NULL, + kasprintf(GFP_KERNEL, "CACHED_LABEL=%s", buf ? : ""), NULL, }; - memcpy(buf, dc->sb.label, SB_LABEL_SIZE); - buf[SB_LABEL_SIZE] = '\0'; - env[2] = kasprintf(GFP_KERNEL, "CACHED_LABEL=%s", buf); - if (atomic_xchg(&dc->running, 1)) { kfree(env[1]); kfree(env[2]); + kfree(buf); return; } @@ -944,6 +946,7 @@ void bch_cached_dev_run(struct cached_dev *dc) kobject_uevent_env(&disk_to_dev(d->disk)->kobj, KOBJ_CHANGE, env); kfree(env[1]); kfree(env[2]); + kfree(buf); if (sysfs_create_link(&d->kobj, &disk_to_dev(d->disk)->kobj, "dev") || sysfs_create_link(&disk_to_dev(d->disk)->kobj, &d->kobj, "bcache")) @@ -1174,6 +1177,7 @@ int bch_cached_dev_attach(struct cached_dev *dc, struct cache_set *c, return 0; } +/* when dc->disk.kobj released */ void bch_cached_dev_release(struct kobject *kobj) { struct cached_dev *dc = container_of(kobj, struct cached_dev, @@ -1280,7 +1284,7 @@ static int cached_dev_init(struct cached_dev *dc, unsigned int block_size) /* Cached device - bcache superblock */ -static void register_bdev(struct cache_sb *sb, struct page *sb_page, +static int register_bdev(struct cache_sb *sb, struct page *sb_page, struct block_device *bdev, struct cached_dev *dc) { @@ -1318,14 +1322,16 @@ static void register_bdev(struct cache_sb *sb, struct page *sb_page, BDEV_STATE(&dc->sb) == BDEV_STATE_STALE) bch_cached_dev_run(dc); - return; + return 0; err: pr_notice("error %s: %s", dc->backing_dev_name, err); bcache_device_stop(&dc->disk); + return -EIO; } /* Flash only volumes */ +/* When d->kobj released */ void bch_flash_dev_release(struct kobject *kobj) { struct bcache_device *d = container_of(kobj, struct bcache_device, @@ -1496,6 +1502,7 @@ bool bch_cache_set_error(struct cache_set *c, const char *fmt, ...) return true; } +/* When c->kobj released */ void bch_cache_set_release(struct kobject *kobj) { struct cache_set *c = container_of(kobj, struct cache_set, kobj); @@ -1516,6 +1523,7 @@ static void cache_set_free(struct closure *cl) bch_btree_cache_free(c); bch_journal_free(c); + mutex_lock(&bch_register_lock); for_each_cache(ca, c, i) if (ca) { ca->set = NULL; @@ -1534,7 +1542,6 @@ static void cache_set_free(struct closure *cl) mempool_exit(&c->search); kfree(c->devices); - mutex_lock(&bch_register_lock); list_del(&c->list); mutex_unlock(&bch_register_lock); @@ -1673,6 +1680,7 @@ static void __cache_set_unregister(struct closure *cl) void bch_cache_set_stop(struct cache_set *c) { if (!test_and_set_bit(CACHE_SET_STOPPING, &c->flags)) + /* closure_fn set to __cache_set_unregister() */ closure_queue(&c->caching); } @@ -1775,13 +1783,15 @@ err: return NULL; } -static void run_cache_set(struct cache_set *c) +static int run_cache_set(struct cache_set *c) { const char *err = "cannot allocate memory"; struct cached_dev *dc, *t; struct cache *ca; struct closure cl; unsigned int i; + LIST_HEAD(journal); + struct journal_replay *l; closure_init_stack(&cl); @@ -1790,7 +1800,6 @@ static void run_cache_set(struct cache_set *c) set_gc_sectors(c); if (CACHE_SYNC(&c->sb)) { - LIST_HEAD(journal); struct bkey *k; struct jset *j; @@ -1869,7 +1878,9 @@ static void run_cache_set(struct cache_set *c) if (j->version < BCACHE_JSET_VERSION_UUID) __uuid_write(c); - bch_journal_replay(c, &journal); + err = "bcache: replay journal failed"; + if (bch_journal_replay(c, &journal)) + goto err; } else { pr_notice("invalidating existing data"); @@ -1937,11 +1948,19 @@ static void run_cache_set(struct cache_set *c) flash_devs_run(c); set_bit(CACHE_SET_RUNNING, &c->flags); - return; + return 0; err: + while (!list_empty(&journal)) { + l = list_first_entry(&journal, struct journal_replay, list); + list_del(&l->list); + kfree(l); + } + closure_sync(&cl); /* XXX: test this, it's broken */ bch_cache_set_error(c, "%s", err); + + return -EIO; } static bool can_attach_cache(struct cache *ca, struct cache_set *c) @@ -2005,8 +2024,11 @@ found: ca->set->cache[ca->sb.nr_this_dev] = ca; c->cache_by_alloc[c->caches_loaded++] = ca; - if (c->caches_loaded == c->sb.nr_in_set) - run_cache_set(c); + if (c->caches_loaded == c->sb.nr_in_set) { + err = "failed to run cache set"; + if (run_cache_set(c) < 0) + goto err; + } return NULL; err: @@ -2016,6 +2038,7 @@ err: /* Cache device */ +/* When ca->kobj released */ void bch_cache_release(struct kobject *kobj) { struct cache *ca = container_of(kobj, struct cache, kobj); @@ -2179,6 +2202,12 @@ static int register_cache(struct cache_sb *sb, struct page *sb_page, ret = cache_alloc(ca); if (ret != 0) { + /* + * If we failed here, it means ca->kobj is not initialized yet, + * kobject_put() won't be called and there is no chance to + * call blkdev_put() to bdev in bch_cache_release(). So we + * explicitly call blkdev_put() here. + */ blkdev_put(bdev, FMODE_READ|FMODE_WRITE|FMODE_EXCL); if (ret == -ENOMEM) err = "cache_alloc(): -ENOMEM"; @@ -2262,7 +2291,7 @@ static bool bch_is_open(struct block_device *bdev) static ssize_t register_bcache(struct kobject *k, struct kobj_attribute *attr, const char *buffer, size_t size) { - ssize_t ret = size; + ssize_t ret = -EINVAL; const char *err = "cannot allocate memory"; char *path = NULL; struct cache_sb *sb = NULL; @@ -2296,7 +2325,7 @@ static ssize_t register_bcache(struct kobject *k, struct kobj_attribute *attr, if (!IS_ERR(bdev)) bdput(bdev); if (attr == &ksysfs_register_quiet) - goto out; + goto quiet_out; } goto err; } @@ -2317,17 +2346,23 @@ static ssize_t register_bcache(struct kobject *k, struct kobj_attribute *attr, goto err_close; mutex_lock(&bch_register_lock); - register_bdev(sb, sb_page, bdev, dc); + ret = register_bdev(sb, sb_page, bdev, dc); mutex_unlock(&bch_register_lock); + /* blkdev_put() will be called in cached_dev_free() */ + if (ret < 0) + goto err; } else { struct cache *ca = kzalloc(sizeof(*ca), GFP_KERNEL); if (!ca) goto err_close; + /* blkdev_put() will be called in bch_cache_release() */ if (register_cache(sb, sb_page, bdev, ca) != 0) goto err; } +quiet_out: + ret = size; out: if (sb_page) put_page(sb_page); @@ -2340,7 +2375,6 @@ err_close: blkdev_put(bdev, FMODE_READ|FMODE_WRITE|FMODE_EXCL); err: pr_info("error %s: %s", path, err); - ret = -EINVAL; goto out; } @@ -2370,10 +2404,19 @@ static int bcache_reboot(struct notifier_block *n, unsigned long code, void *x) list_for_each_entry_safe(dc, tdc, &uncached_devices, list) bcache_device_stop(&dc->disk); + mutex_unlock(&bch_register_lock); + + /* + * Give an early chance for other kthreads and + * kworkers to stop themselves + */ + schedule(); + /* What's a condition variable? */ while (1) { - long timeout = start + 2 * HZ - jiffies; + long timeout = start + 10 * HZ - jiffies; + mutex_lock(&bch_register_lock); stopped = list_empty(&bch_cache_sets) && list_empty(&uncached_devices); @@ -2385,7 +2428,6 @@ static int bcache_reboot(struct notifier_block *n, unsigned long code, void *x) mutex_unlock(&bch_register_lock); schedule_timeout(timeout); - mutex_lock(&bch_register_lock); } finish_wait(&unregister_wait, &wait); diff --git a/drivers/md/bcache/sysfs.c b/drivers/md/bcache/sysfs.c index 17bae9c14ca0..6cd44d3cf906 100644 --- a/drivers/md/bcache/sysfs.c +++ b/drivers/md/bcache/sysfs.c @@ -996,8 +996,6 @@ SHOW(__bch_cache) !cached[n - 1]) --n; - unused = ca->sb.nbuckets - n; - while (cached < p + n && *cached == BTREE_PRIO) cached++, n--; diff --git a/drivers/md/bcache/util.h b/drivers/md/bcache/util.h index 00aab6abcfe4..1fbced94e4cc 100644 --- a/drivers/md/bcache/util.h +++ b/drivers/md/bcache/util.h @@ -560,17 +560,29 @@ static inline uint64_t bch_crc64_update(uint64_t crc, return crc; } -/* Does linear interpolation between powers of two */ +/* + * A stepwise-linear pseudo-exponential. This returns 1 << (x >> + * frac_bits), with the less-significant bits filled in by linear + * interpolation. + * + * This can also be interpreted as a floating-point number format, + * where the low frac_bits are the mantissa (with implicit leading + * 1 bit), and the more significant bits are the exponent. + * The return value is 1.mantissa * 2^exponent. + * + * The way this is used, fract_bits is 6 and the largest possible + * input is CONGESTED_MAX-1 = 1023 (exponent 16, mantissa 0x1.fc), + * so the maximum output is 0x1fc00. + */ static inline unsigned int fract_exp_two(unsigned int x, unsigned int fract_bits) { - unsigned int fract = x & ~(~0 << fract_bits); - - x >>= fract_bits; - x = 1 << x; - x += (x * fract) >> fract_bits; + unsigned int mantissa = 1 << fract_bits; /* Implicit bit */ - return x; + mantissa += x & (mantissa - 1); + x >>= fract_bits; /* The exponent */ + /* Largest intermediate value 0x7f0000 */ + return mantissa << x >> fract_bits; } void bch_bio_map(struct bio *bio, void *base); diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c index 9faed1c92b52..7f6462f74ac8 100644 --- a/drivers/md/dm-crypt.c +++ b/drivers/md/dm-crypt.c @@ -1442,11 +1442,10 @@ out: static void crypt_free_buffer_pages(struct crypt_config *cc, struct bio *clone) { - unsigned int i; struct bio_vec *bv; struct bvec_iter_all iter_all; - bio_for_each_segment_all(bv, clone, i, iter_all) { + bio_for_each_segment_all(bv, clone, iter_all) { BUG_ON(!bv->bv_page); mempool_free(bv->bv_page, &cc->page_pool); } 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 95ae4bf34203..c27c32cf4a30 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..45ffa23fa85d 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 @@ -3384,10 +3380,10 @@ rdev_attr_store(struct kobject *kobj, struct attribute *attr, return -EIO; if (!capable(CAP_SYS_ADMIN)) return -EACCES; - rv = mddev ? mddev_lock(mddev): -EBUSY; + rv = mddev ? mddev_lock(mddev) : -ENODEV; if (!rv) { if (rdev->mddev == NULL) - rv = -EBUSY; + rv = -ENODEV; else rv = entry->store(rdev, page, length); mddev_unlock(mddev); @@ -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/raid1.c b/drivers/md/raid1.c index fdf451aac369..0c8a098d220e 100644 --- a/drivers/md/raid1.c +++ b/drivers/md/raid1.c @@ -2110,7 +2110,7 @@ static void process_checks(struct r1bio *r1_bio) } r1_bio->read_disk = primary; for (i = 0; i < conf->raid_disks * 2; i++) { - int j; + int j = 0; struct bio *pbio = r1_bio->bios[primary]; struct bio *sbio = r1_bio->bios[i]; blk_status_t status = sbio->bi_status; @@ -2125,8 +2125,8 @@ static void process_checks(struct r1bio *r1_bio) /* Now we can 'fixup' the error value */ sbio->bi_status = 0; - bio_for_each_segment_all(bi, sbio, j, iter_all) - page_len[j] = bi->bv_len; + bio_for_each_segment_all(bi, sbio, iter_all) + page_len[j++] = bi->bv_len; if (!status) { for (j = vcnt; j-- ; ) { diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index c033bfcb209e..7fde645d2e90 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); @@ -4187,7 +4191,7 @@ static void handle_parity_checks6(struct r5conf *conf, struct stripe_head *sh, /* now write out any block on a failed drive, * or P or Q if they were recomputed */ - BUG_ON(s->uptodate < disks - 1); /* We don't need Q to recover */ + dev = NULL; if (s->failed == 2) { dev = &sh->dev[s->failed_num[1]]; s->locked++; @@ -4212,6 +4216,14 @@ static void handle_parity_checks6(struct r5conf *conf, struct stripe_head *sh, set_bit(R5_LOCKED, &dev->flags); set_bit(R5_Wantwrite, &dev->flags); } + if (WARN_ONCE(dev && !test_bit(R5_UPTODATE, &dev->flags), + "%s: disk%td not up to date\n", + mdname(conf->mddev), + dev - (struct r5dev *) &sh->dev)) { + clear_bit(R5_LOCKED, &dev->flags); + clear_bit(R5_Wantwrite, &dev->flags); + s->locked--; + } clear_bit(STRIPE_DEGRADED, &sh->state); set_bit(STRIPE_INSYNC, &sh->state); @@ -6166,6 +6178,8 @@ 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 6265d9225ec8..a6644a2c3ef7 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; } @@ -1588,9 +1588,13 @@ 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; + if (ns->lba_shift > PAGE_SHIFT) { + /* unsupported block size, set capacity to 0 later */ + bs = (1 << 9); + } blk_mq_freeze_queue(disk->queue); blk_integrity_unregister(disk); @@ -1601,7 +1605,8 @@ static void nvme_update_disk_info(struct gendisk *disk, if (ns->ms && !ns->ext && (ns->ctrl->ops->flags & NVME_F_METADATA_SUPPORTED)) nvme_init_integrity(disk, ns->ms, ns->pi_type); - if (ns->ms && !nvme_ns_has_pi(ns) && !blk_get_integrity(disk)) + if ((ns->ms && !nvme_ns_has_pi(ns) && !blk_get_integrity(disk)) || + ns->lba_shift > PAGE_SHIFT) capacity = 0; set_capacity(disk, capacity); @@ -2549,7 +2554,7 @@ 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; @@ -3874,10 +3879,37 @@ void nvme_start_queues(struct nvme_ctrl *ctrl) } EXPORT_SYMBOL_GPL(nvme_start_queues); -int __init nvme_core_init(void) +/* + * Check we didn't inadvertently grow the command structure sizes: + */ +static inline void _nvme_check_size(void) +{ + BUILD_BUG_ON(sizeof(struct nvme_common_command) != 64); + BUILD_BUG_ON(sizeof(struct nvme_rw_command) != 64); + BUILD_BUG_ON(sizeof(struct nvme_identify) != 64); + BUILD_BUG_ON(sizeof(struct nvme_features) != 64); + BUILD_BUG_ON(sizeof(struct nvme_download_firmware) != 64); + BUILD_BUG_ON(sizeof(struct nvme_format_cmd) != 64); + BUILD_BUG_ON(sizeof(struct nvme_dsm_cmd) != 64); + BUILD_BUG_ON(sizeof(struct nvme_write_zeroes_cmd) != 64); + BUILD_BUG_ON(sizeof(struct nvme_abort_cmd) != 64); + BUILD_BUG_ON(sizeof(struct nvme_get_log_page_command) != 64); + BUILD_BUG_ON(sizeof(struct nvme_command) != 64); + BUILD_BUG_ON(sizeof(struct nvme_id_ctrl) != NVME_IDENTIFY_DATA_SIZE); + BUILD_BUG_ON(sizeof(struct nvme_id_ns) != NVME_IDENTIFY_DATA_SIZE); + BUILD_BUG_ON(sizeof(struct nvme_lba_range_type) != 64); + BUILD_BUG_ON(sizeof(struct nvme_smart_log) != 512); + BUILD_BUG_ON(sizeof(struct nvme_dbbuf) != 64); + BUILD_BUG_ON(sizeof(struct nvme_directive_cmd) != 64); +} + + +static int __init nvme_core_init(void) { int result = -ENOMEM; + _nvme_check_size(); + nvme_wq = alloc_workqueue("nvme-wq", WQ_UNBOUND | WQ_MEM_RECLAIM | WQ_SYSFS, 0); if (!nvme_wq) @@ -3924,7 +3956,7 @@ out: return result; } -void __exit nvme_core_exit(void) +static void __exit nvme_core_exit(void) { ida_destroy(&nvme_subsystems_ida); class_destroy(nvme_subsys_class); diff --git a/drivers/nvme/host/fabrics.c b/drivers/nvme/host/fabrics.c index d4cb826f58ff..592d1e61ef7e 100644 --- a/drivers/nvme/host/fabrics.c +++ b/drivers/nvme/host/fabrics.c @@ -1188,6 +1188,7 @@ static void __exit nvmf_exit(void) class_destroy(nvmf_class); nvmf_host_put(nvmf_default_host); + BUILD_BUG_ON(sizeof(struct nvmf_common_command) != 64); BUILD_BUG_ON(sizeof(struct nvmf_connect_command) != 64); BUILD_BUG_ON(sizeof(struct nvmf_property_get_command) != 64); BUILD_BUG_ON(sizeof(struct nvmf_property_set_command) != 64); diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c index f0716f6ce41f..5c9429d41120 100644 --- a/drivers/nvme/host/multipath.c +++ b/drivers/nvme/host/multipath.c @@ -232,6 +232,14 @@ static blk_qc_t nvme_ns_head_make_request(struct request_queue *q, blk_qc_t ret = BLK_QC_T_NONE; int srcu_idx; + /* + * The namespace might be going away and the bio might + * be moved to a different queue via blk_steal_bios(), + * so we need to use the bio_split pool from the original + * queue to allocate the bvecs from. + */ + blk_queue_split(q, &bio); + srcu_idx = srcu_read_lock(&head->srcu); ns = nvme_find_path(head); if (likely(ns)) { @@ -421,7 +429,7 @@ static int nvme_update_ana_state(struct nvme_ctrl *ctrl, unsigned *nr_change_groups = data; struct nvme_ns *ns; - dev_info(ctrl->device, "ANA group %d: %s.\n", + dev_dbg(ctrl->device, "ANA group %d: %s.\n", le32_to_cpu(desc->grpid), nvme_ana_state_names[desc->state]); diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h index 527d64545023..5ee75b5ff83f 100644 --- a/drivers/nvme/host/nvme.h +++ b/drivers/nvme/host/nvme.h @@ -577,7 +577,4 @@ static inline struct nvme_ns *nvme_get_ns_from_dev(struct device *dev) return dev_to_disk(dev)->private_data; } -int __init nvme_core_init(void); -void __exit nvme_core_exit(void); - #endif /* _NVME_H */ diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index a90cf5d63aac..3e4fb891a95a 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -146,7 +146,7 @@ static int io_queue_depth_set(const char *val, const struct kernel_param *kp) static int queue_count_set(const char *val, const struct kernel_param *kp) { - int n = 0, ret; + int n, ret; ret = kstrtoint(val, 10, &n); if (ret) @@ -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; @@ -220,33 +220,12 @@ 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]; }; -/* - * Check we didin't inadvertently grow the command struct - */ -static inline void _nvme_check_size(void) -{ - BUILD_BUG_ON(sizeof(struct nvme_rw_command) != 64); - BUILD_BUG_ON(sizeof(struct nvme_create_cq) != 64); - BUILD_BUG_ON(sizeof(struct nvme_create_sq) != 64); - BUILD_BUG_ON(sizeof(struct nvme_delete_queue) != 64); - BUILD_BUG_ON(sizeof(struct nvme_features) != 64); - BUILD_BUG_ON(sizeof(struct nvme_format_cmd) != 64); - BUILD_BUG_ON(sizeof(struct nvme_abort_cmd) != 64); - BUILD_BUG_ON(sizeof(struct nvme_command) != 64); - BUILD_BUG_ON(sizeof(struct nvme_id_ctrl) != NVME_IDENTIFY_DATA_SIZE); - BUILD_BUG_ON(sizeof(struct nvme_id_ns) != NVME_IDENTIFY_DATA_SIZE); - BUILD_BUG_ON(sizeof(struct nvme_lba_range_type) != 64); - BUILD_BUG_ON(sizeof(struct nvme_smart_log) != 512); - BUILD_BUG_ON(sizeof(struct nvme_dbbuf) != 64); -} - static unsigned int max_io_queues(void) { return num_possible_cpus() + write_queues + poll_queues; @@ -372,12 +351,6 @@ 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 +384,6 @@ 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 +548,26 @@ 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; - - return BLK_STS_OK; -} + WARN_ON_ONCE(!iod->nents); -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; + /* 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)); - int i; if (iod->npages == 0) dma_pool_free(dev->prp_small_pool, nvme_pci_iod_list(req)[0], @@ -638,8 +591,7 @@ 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 +781,104 @@ 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->flags = NVME_CMD_SGL_METABUF; + 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 +891,14 @@ 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 +910,23 @@ 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 +935,14 @@ 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 +1077,7 @@ 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 +1137,7 @@ 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 +1150,7 @@ 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); } @@ -1271,6 +1257,7 @@ static enum blk_eh_timer_return nvme_timeout(struct request *req, bool reserved) struct nvme_dev *dev = nvmeq->dev; struct request *abort_req; struct nvme_command cmd; + bool shutdown = false; u32 csts = readl(dev->bar + NVME_REG_CSTS); /* If PCI error recovery process is happening, we cannot reset or @@ -1307,12 +1294,14 @@ static enum blk_eh_timer_return nvme_timeout(struct request *req, bool reserved) * shutdown, so we return BLK_EH_DONE. */ switch (dev->ctrl.state) { + case NVME_CTRL_DELETING: + shutdown = true; case NVME_CTRL_CONNECTING: case NVME_CTRL_RESETTING: dev_warn_ratelimited(dev->ctrl.device, "I/O %d QID %d timeout, disable controller\n", req->tag, nvmeq->qid); - nvme_dev_disable(dev, false); + nvme_dev_disable(dev, shutdown); nvme_req(req)->flags |= NVME_REQ_CANCELLED; return BLK_EH_DONE; default: @@ -1371,16 +1360,16 @@ 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 +1399,8 @@ 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 +1485,6 @@ 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 +1493,6 @@ 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 +1537,7 @@ 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 +1548,7 @@ 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 +1563,8 @@ 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 +1574,6 @@ 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 +1624,7 @@ 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 +1715,7 @@ 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 +2156,8 @@ 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 +2269,7 @@ 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; @@ -2438,8 +2417,11 @@ static void nvme_dev_disable(struct nvme_dev *dev, bool shutdown) * must flush all entered requests to their failed completion to avoid * deadlocking blk-mq hot-cpu notifier. */ - if (shutdown) + if (shutdown) { nvme_start_queues(&dev->ctrl); + if (dev->ctrl.admin_q && !blk_queue_dying(dev->ctrl.admin_q)) + blk_mq_unquiesce_queue(dev->ctrl.admin_q); + } mutex_unlock(&dev->shutdown_lock); } @@ -2979,6 +2961,9 @@ static struct pci_driver nvme_driver = { static int __init nvme_init(void) { + BUILD_BUG_ON(sizeof(struct nvme_create_cq) != 64); + BUILD_BUG_ON(sizeof(struct nvme_create_sq) != 64); + BUILD_BUG_ON(sizeof(struct nvme_delete_queue) != 64); BUILD_BUG_ON(IRQ_AFFINITY_MAX_SETS < 2); return pci_register_driver(&nvme_driver); } @@ -2987,7 +2972,6 @@ static void __exit nvme_exit(void) { pci_unregister_driver(&nvme_driver); flush_workqueue(nvme_wq); - _nvme_check_size(); } MODULE_AUTHOR("Matthew Wilcox <willy@linux.intel.com>"); diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c index 11a5ecae78c8..e1824c2e0a1c 100644 --- a/drivers/nvme/host/rdma.c +++ b/drivers/nvme/host/rdma.c @@ -914,8 +914,9 @@ static void nvme_rdma_teardown_admin_queue(struct nvme_rdma_ctrl *ctrl, { blk_mq_quiesce_queue(ctrl->ctrl.admin_q); nvme_rdma_stop_queue(&ctrl->queues[0]); - blk_mq_tagset_busy_iter(&ctrl->admin_tag_set, nvme_cancel_request, - &ctrl->ctrl); + if (ctrl->ctrl.admin_tagset) + blk_mq_tagset_busy_iter(ctrl->ctrl.admin_tagset, + nvme_cancel_request, &ctrl->ctrl); blk_mq_unquiesce_queue(ctrl->ctrl.admin_q); nvme_rdma_destroy_admin_queue(ctrl, remove); } @@ -926,8 +927,9 @@ static void nvme_rdma_teardown_io_queues(struct nvme_rdma_ctrl *ctrl, if (ctrl->ctrl.queue_count > 1) { nvme_stop_queues(&ctrl->ctrl); nvme_rdma_stop_io_queues(ctrl); - blk_mq_tagset_busy_iter(&ctrl->tag_set, nvme_cancel_request, - &ctrl->ctrl); + if (ctrl->ctrl.tagset) + blk_mq_tagset_busy_iter(ctrl->ctrl.tagset, + nvme_cancel_request, &ctrl->ctrl); if (remove) nvme_start_queues(&ctrl->ctrl); nvme_rdma_destroy_io_queues(ctrl, remove); diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c index 68c49dd67210..2b107a1d152b 100644 --- a/drivers/nvme/host/tcp.c +++ b/drivers/nvme/host/tcp.c @@ -473,7 +473,6 @@ static int nvme_tcp_handle_c2h_data(struct nvme_tcp_queue *queue, } return 0; - } static int nvme_tcp_handle_comp(struct nvme_tcp_queue *queue, @@ -634,7 +633,6 @@ static inline void nvme_tcp_end_request(struct request *rq, u16 status) nvme_end_request(rq, cpu_to_le16(status << 1), res); } - static int nvme_tcp_recv_data(struct nvme_tcp_queue *queue, struct sk_buff *skb, unsigned int *offset, size_t *len) { @@ -1425,7 +1423,8 @@ static int nvme_tcp_start_queue(struct nvme_ctrl *nctrl, int idx) if (!ret) { set_bit(NVME_TCP_Q_LIVE, &ctrl->queues[idx].flags); } else { - __nvme_tcp_stop_queue(&ctrl->queues[idx]); + if (test_bit(NVME_TCP_Q_ALLOCATED, &ctrl->queues[idx].flags)) + __nvme_tcp_stop_queue(&ctrl->queues[idx]); dev_err(nctrl->device, "failed to connect queue: %d ret=%d\n", idx, ret); } @@ -1535,7 +1534,7 @@ out_free_queue: return ret; } -static int nvme_tcp_alloc_io_queues(struct nvme_ctrl *ctrl) +static int __nvme_tcp_alloc_io_queues(struct nvme_ctrl *ctrl) { int i, ret; @@ -1565,7 +1564,7 @@ static unsigned int nvme_tcp_nr_io_queues(struct nvme_ctrl *ctrl) return nr_io_queues; } -static int nvme_alloc_io_queues(struct nvme_ctrl *ctrl) +static int nvme_tcp_alloc_io_queues(struct nvme_ctrl *ctrl) { unsigned int nr_io_queues; int ret; @@ -1582,7 +1581,7 @@ static int nvme_alloc_io_queues(struct nvme_ctrl *ctrl) dev_info(ctrl->device, "creating %d I/O queues.\n", nr_io_queues); - return nvme_tcp_alloc_io_queues(ctrl); + return __nvme_tcp_alloc_io_queues(ctrl); } static void nvme_tcp_destroy_io_queues(struct nvme_ctrl *ctrl, bool remove) @@ -1599,7 +1598,7 @@ static int nvme_tcp_configure_io_queues(struct nvme_ctrl *ctrl, bool new) { int ret; - ret = nvme_alloc_io_queues(ctrl); + ret = nvme_tcp_alloc_io_queues(ctrl); if (ret) return ret; @@ -1710,7 +1709,9 @@ static void nvme_tcp_teardown_admin_queue(struct nvme_ctrl *ctrl, { blk_mq_quiesce_queue(ctrl->admin_q); nvme_tcp_stop_queue(ctrl, 0); - blk_mq_tagset_busy_iter(ctrl->admin_tagset, nvme_cancel_request, ctrl); + if (ctrl->admin_tagset) + blk_mq_tagset_busy_iter(ctrl->admin_tagset, + nvme_cancel_request, ctrl); blk_mq_unquiesce_queue(ctrl->admin_q); nvme_tcp_destroy_admin_queue(ctrl, remove); } @@ -1722,7 +1723,9 @@ static void nvme_tcp_teardown_io_queues(struct nvme_ctrl *ctrl, return; nvme_stop_queues(ctrl); nvme_tcp_stop_io_queues(ctrl); - blk_mq_tagset_busy_iter(ctrl->tagset, nvme_cancel_request, ctrl); + if (ctrl->tagset) + blk_mq_tagset_busy_iter(ctrl->tagset, + nvme_cancel_request, ctrl); if (remove) nvme_start_queues(ctrl); nvme_tcp_destroy_io_queues(ctrl, remove); diff --git a/drivers/nvme/target/Kconfig b/drivers/nvme/target/Kconfig index d94f25cde019..3ef0a4e5eed6 100644 --- a/drivers/nvme/target/Kconfig +++ b/drivers/nvme/target/Kconfig @@ -3,6 +3,7 @@ config NVME_TARGET tristate "NVMe Target support" depends on BLOCK depends on CONFIGFS_FS + select SGL_ALLOC help This enabled target side support for the NVMe protocol, that is it allows the Linux kernel to implement NVMe subsystems and diff --git a/drivers/nvme/target/configfs.c b/drivers/nvme/target/configfs.c index adb79545cdd7..08dd5af357f7 100644 --- a/drivers/nvme/target/configfs.c +++ b/drivers/nvme/target/configfs.c @@ -898,8 +898,8 @@ static struct config_group *nvmet_subsys_make(struct config_group *group, } subsys = nvmet_subsys_alloc(name, NVME_NQN_NVME); - if (!subsys) - return ERR_PTR(-ENOMEM); + if (IS_ERR(subsys)) + return ERR_CAST(subsys); config_group_init_type_name(&subsys->group, name, &nvmet_subsys_type); diff --git a/drivers/nvme/target/core.c b/drivers/nvme/target/core.c index b3e765a95af8..7734a6acff85 100644 --- a/drivers/nvme/target/core.c +++ b/drivers/nvme/target/core.c @@ -8,6 +8,7 @@ #include <linux/random.h> #include <linux/rculist.h> #include <linux/pci-p2pdma.h> +#include <linux/scatterlist.h> #include "nvmet.h" @@ -214,6 +215,8 @@ 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 +497,14 @@ 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); @@ -644,7 +648,7 @@ static void nvmet_update_sq_head(struct nvmet_req *req) } while (cmpxchg(&req->sq->sqhd, old_sqhd, new_sqhd) != old_sqhd); } - req->rsp->sq_head = cpu_to_le16(req->sq->sqhd & 0x0000FFFF); + req->cqe->sq_head = cpu_to_le16(req->sq->sqhd & 0x0000FFFF); } static void nvmet_set_error(struct nvmet_req *req, u16 status) @@ -653,7 +657,7 @@ static void nvmet_set_error(struct nvmet_req *req, u16 status) struct nvme_error_slot *new_error_slot; unsigned long flags; - req->rsp->status = cpu_to_le16(status << 1); + req->cqe->status = cpu_to_le16(status << 1); if (!ctrl || req->error_loc == NVMET_NO_ERROR_LOC) return; @@ -673,15 +677,15 @@ static void nvmet_set_error(struct nvmet_req *req, u16 status) spin_unlock_irqrestore(&ctrl->error_lock, flags); /* set the more bit for this request */ - req->rsp->status |= cpu_to_le16(1 << 14); + req->cqe->status |= cpu_to_le16(1 << 14); } static void __nvmet_req_complete(struct nvmet_req *req, u16 status) { if (!req->sq->sqhd_disabled) nvmet_update_sq_head(req); - req->rsp->sq_id = cpu_to_le16(req->sq->qid); - req->rsp->command_id = req->cmd->common.command_id; + req->cqe->sq_id = cpu_to_le16(req->sq->qid); + req->cqe->command_id = req->cmd->common.command_id; if (unlikely(status)) nvmet_set_error(req, status); @@ -838,8 +842,8 @@ bool nvmet_req_init(struct nvmet_req *req, struct nvmet_cq *cq, req->sg = NULL; req->sg_cnt = 0; req->transfer_len = 0; - req->rsp->status = 0; - req->rsp->sq_head = 0; + req->cqe->status = 0; + req->cqe->sq_head = 0; req->ns = NULL; req->error_loc = NVMET_NO_ERROR_LOC; req->error_slba = 0; @@ -1066,7 +1070,7 @@ u16 nvmet_ctrl_find_get(const char *subsysnqn, const char *hostnqn, u16 cntlid, if (!subsys) { pr_warn("connect request for invalid subsystem %s!\n", subsysnqn); - req->rsp->result.u32 = IPO_IATTR_CONNECT_DATA(subsysnqn); + req->cqe->result.u32 = IPO_IATTR_CONNECT_DATA(subsysnqn); return NVME_SC_CONNECT_INVALID_PARAM | NVME_SC_DNR; } @@ -1087,7 +1091,7 @@ u16 nvmet_ctrl_find_get(const char *subsysnqn, const char *hostnqn, u16 cntlid, pr_warn("could not find controller %d for subsys %s / host %s\n", cntlid, subsysnqn, hostnqn); - req->rsp->result.u32 = IPO_IATTR_CONNECT_DATA(cntlid); + req->cqe->result.u32 = IPO_IATTR_CONNECT_DATA(cntlid); status = NVME_SC_CONNECT_INVALID_PARAM | NVME_SC_DNR; out: @@ -1185,7 +1189,7 @@ u16 nvmet_alloc_ctrl(const char *subsysnqn, const char *hostnqn, if (!subsys) { pr_warn("connect request for invalid subsystem %s!\n", subsysnqn); - req->rsp->result.u32 = IPO_IATTR_CONNECT_DATA(subsysnqn); + req->cqe->result.u32 = IPO_IATTR_CONNECT_DATA(subsysnqn); goto out; } @@ -1194,7 +1198,7 @@ u16 nvmet_alloc_ctrl(const char *subsysnqn, const char *hostnqn, if (!nvmet_host_allowed(subsys, hostnqn)) { pr_info("connect by host %s for subsystem %s not allowed\n", hostnqn, subsysnqn); - req->rsp->result.u32 = IPO_IATTR_CONNECT_DATA(hostnqn); + req->cqe->result.u32 = IPO_IATTR_CONNECT_DATA(hostnqn); up_read(&nvmet_config_sem); status = NVME_SC_CONNECT_INVALID_HOST | NVME_SC_DNR; goto out_put_subsystem; @@ -1364,7 +1368,7 @@ struct nvmet_subsys *nvmet_subsys_alloc(const char *subsysnqn, subsys = kzalloc(sizeof(*subsys), GFP_KERNEL); if (!subsys) - return NULL; + return ERR_PTR(-ENOMEM); subsys->ver = NVME_VS(1, 3, 0); /* NVMe 1.3.0 */ /* generate a random serial number as our controllers are ephemeral: */ @@ -1380,14 +1384,14 @@ struct nvmet_subsys *nvmet_subsys_alloc(const char *subsysnqn, default: pr_err("%s: Unknown Subsystem type - %d\n", __func__, type); kfree(subsys); - return NULL; + return ERR_PTR(-EINVAL); } subsys->type = type; subsys->subsysnqn = kstrndup(subsysnqn, NVMF_NQN_SIZE, GFP_KERNEL); if (!subsys->subsysnqn) { kfree(subsys); - return NULL; + return ERR_PTR(-ENOMEM); } kref_init(&subsys->ref); diff --git a/drivers/nvme/target/discovery.c b/drivers/nvme/target/discovery.c index 33ed95e72d6b..5baf269f3f8a 100644 --- a/drivers/nvme/target/discovery.c +++ b/drivers/nvme/target/discovery.c @@ -30,14 +30,17 @@ void nvmet_port_disc_changed(struct nvmet_port *port, { struct nvmet_ctrl *ctrl; + lockdep_assert_held(&nvmet_config_sem); nvmet_genctr++; + mutex_lock(&nvmet_disc_subsys->lock); list_for_each_entry(ctrl, &nvmet_disc_subsys->ctrls, subsys_entry) { if (subsys && !nvmet_host_allowed(subsys, ctrl->hostnqn)) continue; __nvmet_disc_changed(port, ctrl); } + mutex_unlock(&nvmet_disc_subsys->lock); } static void __nvmet_subsys_disc_changed(struct nvmet_port *port, @@ -46,12 +49,14 @@ static void __nvmet_subsys_disc_changed(struct nvmet_port *port, { struct nvmet_ctrl *ctrl; + mutex_lock(&nvmet_disc_subsys->lock); list_for_each_entry(ctrl, &nvmet_disc_subsys->ctrls, subsys_entry) { if (host && strcmp(nvmet_host_name(host), ctrl->hostnqn)) continue; __nvmet_disc_changed(port, ctrl); } + mutex_unlock(&nvmet_disc_subsys->lock); } void nvmet_subsys_disc_changed(struct nvmet_subsys *subsys, @@ -372,8 +377,8 @@ int __init nvmet_init_discovery(void) { nvmet_disc_subsys = nvmet_subsys_alloc(NVME_DISC_SUBSYS_NAME, NVME_NQN_DISC); - if (!nvmet_disc_subsys) - return -ENOMEM; + if (IS_ERR(nvmet_disc_subsys)) + return PTR_ERR(nvmet_disc_subsys); return 0; } diff --git a/drivers/nvme/target/fabrics-cmd.c b/drivers/nvme/target/fabrics-cmd.c index 3a76ebc3d155..3b9f79aba98f 100644 --- a/drivers/nvme/target/fabrics-cmd.c +++ b/drivers/nvme/target/fabrics-cmd.c @@ -72,7 +72,7 @@ static void nvmet_execute_prop_get(struct nvmet_req *req) offsetof(struct nvmf_property_get_command, attrib); } - req->rsp->result.u64 = cpu_to_le64(val); + req->cqe->result.u64 = cpu_to_le64(val); nvmet_req_complete(req, status); } @@ -124,7 +124,7 @@ static u16 nvmet_install_queue(struct nvmet_ctrl *ctrl, struct nvmet_req *req) if (c->cattr & NVME_CONNECT_DISABLE_SQFLOW) { req->sq->sqhd_disabled = true; - req->rsp->sq_head = cpu_to_le16(0xffff); + req->cqe->sq_head = cpu_to_le16(0xffff); } if (ctrl->ops->install_queue) { @@ -158,7 +158,7 @@ static void nvmet_execute_admin_connect(struct nvmet_req *req) goto out; /* zero out initial completion result, assign values as needed */ - req->rsp->result.u32 = 0; + req->cqe->result.u32 = 0; if (c->recfmt != 0) { pr_warn("invalid connect version (%d).\n", @@ -172,7 +172,7 @@ static void nvmet_execute_admin_connect(struct nvmet_req *req) pr_warn("connect attempt for invalid controller ID %#x\n", d->cntlid); status = NVME_SC_CONNECT_INVALID_PARAM | NVME_SC_DNR; - req->rsp->result.u32 = IPO_IATTR_CONNECT_DATA(cntlid); + req->cqe->result.u32 = IPO_IATTR_CONNECT_DATA(cntlid); goto out; } @@ -195,7 +195,7 @@ static void nvmet_execute_admin_connect(struct nvmet_req *req) pr_info("creating controller %d for subsystem %s for NQN %s.\n", ctrl->cntlid, ctrl->subsys->subsysnqn, ctrl->hostnqn); - req->rsp->result.u16 = cpu_to_le16(ctrl->cntlid); + req->cqe->result.u16 = cpu_to_le16(ctrl->cntlid); out: kfree(d); @@ -222,7 +222,7 @@ static void nvmet_execute_io_connect(struct nvmet_req *req) goto out; /* zero out initial completion result, assign values as needed */ - req->rsp->result.u32 = 0; + req->cqe->result.u32 = 0; if (c->recfmt != 0) { pr_warn("invalid connect version (%d).\n", @@ -240,14 +240,14 @@ static void nvmet_execute_io_connect(struct nvmet_req *req) if (unlikely(qid > ctrl->subsys->max_qid)) { pr_warn("invalid queue id (%d)\n", qid); status = NVME_SC_CONNECT_INVALID_PARAM | NVME_SC_DNR; - req->rsp->result.u32 = IPO_IATTR_CONNECT_SQE(qid); + req->cqe->result.u32 = IPO_IATTR_CONNECT_SQE(qid); goto out_ctrl_put; } status = nvmet_install_queue(ctrl, req); if (status) { /* pass back cntlid that had the issue of installing queue */ - req->rsp->result.u16 = cpu_to_le16(ctrl->cntlid); + req->cqe->result.u16 = cpu_to_le16(ctrl->cntlid); goto out_ctrl_put; } diff --git a/drivers/nvme/target/fc.c b/drivers/nvme/target/fc.c index 98b7b1f4ee96..508661af0f50 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; @@ -2187,7 +2184,7 @@ nvmet_fc_handle_fcp_rqst(struct nvmet_fc_tgtport *tgtport, } fod->req.cmd = &fod->cmdiubuf.sqe; - fod->req.rsp = &fod->rspiubuf.cqe; + fod->req.cqe = &fod->rspiubuf.cqe; fod->req.port = tgtport->pe->port; /* clear any response payload */ 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/io-cmd-file.c b/drivers/nvme/target/io-cmd-file.c index bc6ebb51b0bf..05453f5d1448 100644 --- a/drivers/nvme/target/io-cmd-file.c +++ b/drivers/nvme/target/io-cmd-file.c @@ -49,7 +49,12 @@ int nvmet_file_ns_enable(struct nvmet_ns *ns) goto err; ns->size = stat.size; - ns->blksize_shift = file_inode(ns->file)->i_blkbits; + /* + * i_blkbits can be greater than the universally accepted upper bound, + * so make sure we export a sane namespace lba_shift. + */ + ns->blksize_shift = min_t(u8, + file_inode(ns->file)->i_blkbits, 12); ns->bvec_cache = kmem_cache_create("nvmet-bvec", NVMET_MAX_MPOOL_BVEC * sizeof(struct bio_vec), diff --git a/drivers/nvme/target/loop.c b/drivers/nvme/target/loop.c index b9f623ab01f3..9e211ad6bdd3 100644 --- a/drivers/nvme/target/loop.c +++ b/drivers/nvme/target/loop.c @@ -18,7 +18,7 @@ struct nvme_loop_iod { struct nvme_request nvme_req; struct nvme_command cmd; - struct nvme_completion rsp; + struct nvme_completion cqe; struct nvmet_req req; struct nvme_loop_queue *queue; struct work_struct work; @@ -94,7 +94,7 @@ static void nvme_loop_queue_response(struct nvmet_req *req) { struct nvme_loop_queue *queue = container_of(req->sq, struct nvme_loop_queue, nvme_sq); - struct nvme_completion *cqe = req->rsp; + struct nvme_completion *cqe = req->cqe; /* * AEN requests are special as they don't time out and can @@ -129,20 +129,6 @@ static void nvme_loop_execute_work(struct work_struct *work) nvmet_req_execute(&iod->req); } -static enum blk_eh_timer_return -nvme_loop_timeout(struct request *rq, bool reserved) -{ - struct nvme_loop_iod *iod = blk_mq_rq_to_pdu(rq); - - /* queue error recovery */ - nvme_reset_ctrl(&iod->queue->ctrl->ctrl); - - /* fail with DNR on admin cmd timeout */ - nvme_req(rq)->status = NVME_SC_ABORT_REQ | NVME_SC_DNR; - - return BLK_EH_DONE; -} - static blk_status_t nvme_loop_queue_rq(struct blk_mq_hw_ctx *hctx, const struct blk_mq_queue_data *bd) { @@ -207,7 +193,7 @@ static int nvme_loop_init_iod(struct nvme_loop_ctrl *ctrl, struct nvme_loop_iod *iod, unsigned int queue_idx) { iod->req.cmd = &iod->cmd; - iod->req.rsp = &iod->rsp; + iod->req.cqe = &iod->cqe; iod->queue = &ctrl->queues[queue_idx]; INIT_WORK(&iod->work, nvme_loop_execute_work); return 0; @@ -253,7 +239,6 @@ static const struct blk_mq_ops nvme_loop_mq_ops = { .complete = nvme_loop_complete_rq, .init_request = nvme_loop_init_request, .init_hctx = nvme_loop_init_hctx, - .timeout = nvme_loop_timeout, }; static const struct blk_mq_ops nvme_loop_admin_mq_ops = { @@ -261,7 +246,6 @@ static const struct blk_mq_ops nvme_loop_admin_mq_ops = { .complete = nvme_loop_complete_rq, .init_request = nvme_loop_init_request, .init_hctx = nvme_loop_init_admin_hctx, - .timeout = nvme_loop_timeout, }; static void nvme_loop_destroy_admin_queue(struct nvme_loop_ctrl *ctrl) diff --git a/drivers/nvme/target/nvmet.h b/drivers/nvme/target/nvmet.h index 1653d19b187f..c25d88fc9dec 100644 --- a/drivers/nvme/target/nvmet.h +++ b/drivers/nvme/target/nvmet.h @@ -284,7 +284,7 @@ struct nvmet_fabrics_ops { struct nvmet_req { struct nvme_command *cmd; - struct nvme_completion *rsp; + struct nvme_completion *cqe; struct nvmet_sq *sq; struct nvmet_cq *cq; struct nvmet_ns *ns; @@ -322,7 +322,7 @@ extern struct workqueue_struct *buffered_io_wq; static inline void nvmet_set_result(struct nvmet_req *req, u32 result) { - req->rsp->result.u32 = cpu_to_le32(result); + req->cqe->result.u32 = cpu_to_le32(result); } /* diff --git a/drivers/nvme/target/rdma.c b/drivers/nvme/target/rdma.c index ef893addf341..36d906a7f70d 100644 --- a/drivers/nvme/target/rdma.c +++ b/drivers/nvme/target/rdma.c @@ -160,7 +160,7 @@ static inline bool nvmet_rdma_need_data_out(struct nvmet_rdma_rsp *rsp) { return !nvme_is_write(rsp->req.cmd) && rsp->req.transfer_len && - !rsp->req.rsp->status && + !rsp->req.cqe->status && !(rsp->flags & NVMET_RDMA_REQ_INLINE_DATA); } @@ -364,16 +364,17 @@ static int nvmet_rdma_alloc_rsp(struct nvmet_rdma_device *ndev, struct nvmet_rdma_rsp *r) { /* NVMe CQE / RDMA SEND */ - r->req.rsp = kmalloc(sizeof(*r->req.rsp), GFP_KERNEL); - if (!r->req.rsp) + r->req.cqe = kmalloc(sizeof(*r->req.cqe), GFP_KERNEL); + if (!r->req.cqe) goto out; - r->send_sge.addr = ib_dma_map_single(ndev->device, r->req.rsp, - sizeof(*r->req.rsp), DMA_TO_DEVICE); + r->send_sge.addr = ib_dma_map_single(ndev->device, r->req.cqe, + sizeof(*r->req.cqe), DMA_TO_DEVICE); if (ib_dma_mapping_error(ndev->device, r->send_sge.addr)) goto out_free_rsp; - r->send_sge.length = sizeof(*r->req.rsp); + r->req.p2p_client = &ndev->device->dev; + r->send_sge.length = sizeof(*r->req.cqe); r->send_sge.lkey = ndev->pd->local_dma_lkey; r->send_cqe.done = nvmet_rdma_send_done; @@ -388,7 +389,7 @@ static int nvmet_rdma_alloc_rsp(struct nvmet_rdma_device *ndev, return 0; out_free_rsp: - kfree(r->req.rsp); + kfree(r->req.cqe); out: return -ENOMEM; } @@ -397,8 +398,8 @@ static void nvmet_rdma_free_rsp(struct nvmet_rdma_device *ndev, struct nvmet_rdma_rsp *r) { ib_dma_unmap_single(ndev->device, r->send_sge.addr, - sizeof(*r->req.rsp), DMA_TO_DEVICE); - kfree(r->req.rsp); + sizeof(*r->req.cqe), DMA_TO_DEVICE); + kfree(r->req.cqe); } static int @@ -763,8 +764,6 @@ static void nvmet_rdma_handle_command(struct nvmet_rdma_queue *queue, cmd->send_sge.addr, cmd->send_sge.length, DMA_TO_DEVICE); - cmd->req.p2p_client = &queue->dev->device->dev; - if (!nvmet_req_init(&cmd->req, &queue->nvme_cq, &queue->nvme_sq, &nvmet_rdma_ops)) return; diff --git a/drivers/nvme/target/tcp.c b/drivers/nvme/target/tcp.c index ad0df786fe93..69b83fa0c76c 100644 --- a/drivers/nvme/target/tcp.c +++ b/drivers/nvme/target/tcp.c @@ -161,14 +161,14 @@ static inline bool nvmet_tcp_has_data_in(struct nvmet_tcp_cmd *cmd) static inline bool nvmet_tcp_need_data_in(struct nvmet_tcp_cmd *cmd) { - return nvmet_tcp_has_data_in(cmd) && !cmd->req.rsp->status; + return nvmet_tcp_has_data_in(cmd) && !cmd->req.cqe->status; } static inline bool nvmet_tcp_need_data_out(struct nvmet_tcp_cmd *cmd) { return !nvme_is_write(cmd->req.cmd) && cmd->req.transfer_len > 0 && - !cmd->req.rsp->status; + !cmd->req.cqe->status; } static inline bool nvmet_tcp_has_inline_data(struct nvmet_tcp_cmd *cmd) @@ -371,13 +371,14 @@ 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 = cpu_to_le32(pdu->hdr.hlen + hdgst + cmd->req.transfer_len + ddgst); - pdu->command_id = cmd->req.rsp->command_id; + pdu->command_id = cmd->req.cqe->command_id; pdu->data_length = cpu_to_le32(cmd->req.transfer_len); pdu->data_offset = cpu_to_le32(cmd->wbytes_done); @@ -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; } @@ -756,12 +774,6 @@ static int nvmet_tcp_handle_icreq(struct nvmet_tcp_queue *queue) return -EPROTO; } - if (icreq->maxr2t != 0) { - pr_err("queue %d: unsupported maxr2t %d\n", queue->idx, - le32_to_cpu(icreq->maxr2t) + 1); - return -EPROTO; - } - queue->hdr_digest = !!(icreq->digest & NVME_TCP_HDR_DIGEST_ENABLE); queue->data_digest = !!(icreq->digest & NVME_TCP_DATA_DIGEST_ENABLE); if (queue->hdr_digest || queue->data_digest) { @@ -1206,7 +1218,7 @@ static int nvmet_tcp_alloc_cmd(struct nvmet_tcp_queue *queue, sizeof(*c->rsp_pdu) + hdgst, GFP_KERNEL | __GFP_ZERO); if (!c->rsp_pdu) goto out_free_cmd; - c->req.rsp = &c->rsp_pdu->cqe; + c->req.cqe = &c->rsp_pdu->cqe; c->data_pdu = page_frag_alloc(&queue->pf_cache, sizeof(*c->data_pdu) + hdgst, GFP_KERNEL | __GFP_ZERO); 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/staging/erofs/data.c b/drivers/staging/erofs/data.c index c64ec76643d4..746685f90564 100644 --- a/drivers/staging/erofs/data.c +++ b/drivers/staging/erofs/data.c @@ -18,7 +18,6 @@ static inline void read_endio(struct bio *bio) { struct super_block *const sb = bio->bi_private; - int i; struct bio_vec *bvec; blk_status_t err = bio->bi_status; struct bvec_iter_all iter_all; @@ -28,7 +27,7 @@ static inline void read_endio(struct bio *bio) err = BLK_STS_IOERR; } - bio_for_each_segment_all(bvec, bio, i, iter_all) { + bio_for_each_segment_all(bvec, bio, iter_all) { struct page *page = bvec->bv_page; /* page is already locked */ diff --git a/drivers/staging/erofs/unzip_vle.c b/drivers/staging/erofs/unzip_vle.c index a2e03c932102..9ecaa872bae8 100644 --- a/drivers/staging/erofs/unzip_vle.c +++ b/drivers/staging/erofs/unzip_vle.c @@ -846,11 +846,10 @@ static inline void z_erofs_vle_read_endio(struct bio *bio) { struct erofs_sb_info *sbi = NULL; blk_status_t err = bio->bi_status; - unsigned int i; struct bio_vec *bvec; struct bvec_iter_all iter_all; - bio_for_each_segment_all(bvec, bio, i, iter_all) { + bio_for_each_segment_all(bvec, bio, iter_all) { struct page *page = bvec->bv_page; bool cachemngd = false; 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 |