diff options
| author | Linus Torvalds <torvalds@linux-foundation.org> | 2019-03-09 01:12:17 +0300 |
|---|---|---|
| committer | Linus Torvalds <torvalds@linux-foundation.org> | 2019-03-09 01:12:17 +0300 |
| commit | 80201fe175cbf7f3e372f53eba0a881a702ad926 (patch) | |
| tree | 8026c68d52763614268a9c3c80759ad386bd5967 /drivers | |
| parent | 4221b807d1f73c03d22543416d303b60a5d1ef31 (diff) | |
| parent | aaeee62c841cc1e48231e1d60c304d2da9c4e41c (diff) | |
| download | linux-80201fe175cbf7f3e372f53eba0a881a702ad926.tar.xz | |
Merge tag 'for-5.1/block-20190302' of git://git.kernel.dk/linux-block
Pull block layer updates from Jens Axboe:
"Not a huge amount of changes in this round, the biggest one is that we
finally have Mings multi-page bvec support merged. Apart from that,
this pull request contains:
- Small series that avoids quiescing the queue for sysfs changes that
match what we currently have (Aleksei)
- Series of bcache fixes (via Coly)
- Series of lightnvm fixes (via Mathias)
- NVMe pull request from Christoph. Nothing major, just SPDX/license
cleanups, RR mp policy (Hannes), and little fixes (Bart,
Chaitanya).
- BFQ series (Paolo)
- Save blk-mq cpu -> hw queue mapping, removing a pointer indirection
for the fast path (Jianchao)
- fops->iopoll() added for async IO polling, this is a feature that
the upcoming io_uring interface will use (Christoph, me)
- Partition scan loop fixes (Dongli)
- mtip32xx conversion from managed resource API (Christoph)
- cdrom registration race fix (Guenter)
- MD pull from Song, two minor fixes.
- Various documentation fixes (Marcos)
- Multi-page bvec feature. This brings a lot of nice improvements
with it, like more efficient splitting, larger IOs can be supported
without growing the bvec table size, and so on. (Ming)
- Various little fixes to core and drivers"
* tag 'for-5.1/block-20190302' of git://git.kernel.dk/linux-block: (117 commits)
block: fix updating bio's front segment size
block: Replace function name in string with __func__
nbd: propagate genlmsg_reply return code
floppy: remove set but not used variable 'q'
null_blk: fix checking for REQ_FUA
block: fix NULL pointer dereference in register_disk
fs: fix guard_bio_eod to check for real EOD errors
blk-mq: use HCTX_TYPE_DEFAULT but not 0 to index blk_mq_tag_set->map
block: optimize bvec iteration in bvec_iter_advance
block: introduce mp_bvec_for_each_page() for iterating over page
block: optimize blk_bio_segment_split for single-page bvec
block: optimize __blk_segment_map_sg() for single-page bvec
block: introduce bvec_nth_page()
iomap: wire up the iopoll method
block: add bio_set_polled() helper
block: wire up block device iopoll method
fs: add an iopoll method to struct file_operations
loop: set GENHD_FL_NO_PART_SCAN after blkdev_reread_part()
loop: do not print warn message if partition scan is successful
block: bounce: make sure that bvec table is updated
...
Diffstat (limited to 'drivers')
62 files changed, 496 insertions, 450 deletions
diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c index c2adfd8486c4..21d1ce20e1a9 100644 --- a/drivers/ata/libata-scsi.c +++ b/drivers/ata/libata-scsi.c @@ -1318,8 +1318,6 @@ static int ata_scsi_dev_config(struct scsi_device *sdev, scsi_change_queue_depth(sdev, depth); } - blk_queue_flush_queueable(q, false); - if (dev->flags & ATA_DFLAG_TRUSTED) sdev->security_supported = 1; diff --git a/drivers/block/floppy.c b/drivers/block/floppy.c index 55481b40df9a..95f608d1a098 100644 --- a/drivers/block/floppy.c +++ b/drivers/block/floppy.c @@ -2230,7 +2230,6 @@ static void floppy_end_request(struct request *req, blk_status_t error) static void request_done(int uptodate) { struct request *req = current_req; - struct request_queue *q; int block; char msg[sizeof("request done ") + sizeof(int) * 3]; @@ -2243,8 +2242,6 @@ static void request_done(int uptodate) return; } - q = req->q; - if (uptodate) { /* maintain values for invalidation on geometry * change */ diff --git a/drivers/block/loop.c b/drivers/block/loop.c index cf5538942834..1e6edd568214 100644 --- a/drivers/block/loop.c +++ b/drivers/block/loop.c @@ -511,21 +511,22 @@ static int lo_rw_aio(struct loop_device *lo, struct loop_cmd *cmd, loff_t pos, bool rw) { struct iov_iter iter; + struct req_iterator rq_iter; struct bio_vec *bvec; struct request *rq = blk_mq_rq_from_pdu(cmd); struct bio *bio = rq->bio; struct file *file = lo->lo_backing_file; + struct bio_vec tmp; unsigned int offset; - int segments = 0; + int nr_bvec = 0; int ret; + rq_for_each_bvec(tmp, rq, rq_iter) + nr_bvec++; + if (rq->bio != rq->biotail) { - struct req_iterator iter; - struct bio_vec tmp; - __rq_for_each_bio(bio, rq) - segments += bio_segments(bio); - bvec = kmalloc_array(segments, sizeof(struct bio_vec), + bvec = kmalloc_array(nr_bvec, sizeof(struct bio_vec), GFP_NOIO); if (!bvec) return -EIO; @@ -534,10 +535,10 @@ static int lo_rw_aio(struct loop_device *lo, struct loop_cmd *cmd, /* * The bios of the request may be started from the middle of * the 'bvec' because of bio splitting, so we can't directly - * copy bio->bi_iov_vec to new bvec. The rq_for_each_segment + * copy bio->bi_iov_vec to new bvec. The rq_for_each_bvec * API will take care of all details for us. */ - rq_for_each_segment(tmp, rq, iter) { + rq_for_each_bvec(tmp, rq, rq_iter) { *bvec = tmp; bvec++; } @@ -551,11 +552,10 @@ static int lo_rw_aio(struct loop_device *lo, struct loop_cmd *cmd, */ offset = bio->bi_iter.bi_bvec_done; bvec = __bvec_iter_bvec(bio->bi_io_vec, bio->bi_iter); - segments = bio_segments(bio); } atomic_set(&cmd->ref, 2); - iov_iter_bvec(&iter, rw, bvec, segments, blk_rq_bytes(rq)); + iov_iter_bvec(&iter, rw, bvec, nr_bvec, blk_rq_bytes(rq)); iter.iov_offset = offset; cmd->iocb.ki_pos = pos; @@ -1089,16 +1089,12 @@ static int __loop_clr_fd(struct loop_device *lo, bool release) kobject_uevent(&disk_to_dev(bdev->bd_disk)->kobj, KOBJ_CHANGE); } mapping_set_gfp_mask(filp->f_mapping, gfp); - lo->lo_state = Lo_unbound; /* This is safe: open() is still holding a reference. */ module_put(THIS_MODULE); blk_mq_unfreeze_queue(lo->lo_queue); partscan = lo->lo_flags & LO_FLAGS_PARTSCAN && bdev; lo_number = lo->lo_number; - lo->lo_flags = 0; - if (!part_shift) - lo->lo_disk->flags |= GENHD_FL_NO_PART_SCAN; loop_unprepare_queue(lo); out_unlock: mutex_unlock(&loop_ctl_mutex); @@ -1115,11 +1111,29 @@ out_unlock: err = __blkdev_reread_part(bdev); else err = blkdev_reread_part(bdev); - pr_warn("%s: partition scan of loop%d failed (rc=%d)\n", - __func__, lo_number, err); + if (err) + pr_warn("%s: partition scan of loop%d failed (rc=%d)\n", + __func__, lo_number, err); /* Device is gone, no point in returning error */ err = 0; } + + /* + * lo->lo_state is set to Lo_unbound here after above partscan has + * finished. + * + * There cannot be anybody else entering __loop_clr_fd() as + * lo->lo_backing_file is already cleared and Lo_rundown state + * protects us from all the other places trying to change the 'lo' + * device. + */ + mutex_lock(&loop_ctl_mutex); + lo->lo_flags = 0; + if (!part_shift) + lo->lo_disk->flags |= GENHD_FL_NO_PART_SCAN; + lo->lo_state = Lo_unbound; + mutex_unlock(&loop_ctl_mutex); + /* * Need not hold loop_ctl_mutex to fput backing file. * Calling fput holding loop_ctl_mutex triggers a circular @@ -1937,7 +1951,7 @@ static int loop_add(struct loop_device **l, int i) lo->tag_set.queue_depth = 128; lo->tag_set.numa_node = NUMA_NO_NODE; lo->tag_set.cmd_size = sizeof(struct loop_cmd); - lo->tag_set.flags = BLK_MQ_F_SHOULD_MERGE | BLK_MQ_F_SG_MERGE; + lo->tag_set.flags = BLK_MQ_F_SHOULD_MERGE; lo->tag_set.driver_data = lo; err = blk_mq_alloc_tag_set(&lo->tag_set); diff --git a/drivers/block/mtip32xx/mtip32xx.c b/drivers/block/mtip32xx/mtip32xx.c index 2f3ee4d6af82..83302ecdc8db 100644 --- a/drivers/block/mtip32xx/mtip32xx.c +++ b/drivers/block/mtip32xx/mtip32xx.c @@ -1416,7 +1416,7 @@ static blk_status_t mtip_send_trim(struct driver_data *dd, unsigned int lba, WARN_ON(sizeof(struct mtip_trim) > ATA_SECT_SIZE); /* Allocate a DMA buffer for the trim structure */ - buf = dmam_alloc_coherent(&dd->pdev->dev, ATA_SECT_SIZE, &dma_addr, + buf = dma_alloc_coherent(&dd->pdev->dev, ATA_SECT_SIZE, &dma_addr, GFP_KERNEL); if (!buf) return BLK_STS_RESOURCE; @@ -1453,7 +1453,7 @@ static blk_status_t mtip_send_trim(struct driver_data *dd, unsigned int lba, MTIP_TRIM_TIMEOUT_MS) < 0) ret = BLK_STS_IOERR; - dmam_free_coherent(&dd->pdev->dev, ATA_SECT_SIZE, buf, dma_addr); + dma_free_coherent(&dd->pdev->dev, ATA_SECT_SIZE, buf, dma_addr); return ret; } @@ -1656,7 +1656,7 @@ static int exec_drive_command(struct mtip_port *port, u8 *command, if (!user_buffer) return -EFAULT; - buf = dmam_alloc_coherent(&port->dd->pdev->dev, + buf = dma_alloc_coherent(&port->dd->pdev->dev, ATA_SECT_SIZE * xfer_sz, &dma_addr, GFP_KERNEL); @@ -1734,7 +1734,7 @@ static int exec_drive_command(struct mtip_port *port, u8 *command, } exit_drive_command: if (buf) - dmam_free_coherent(&port->dd->pdev->dev, + dma_free_coherent(&port->dd->pdev->dev, ATA_SECT_SIZE * xfer_sz, buf, dma_addr); return rv; } @@ -2838,11 +2838,11 @@ static void mtip_dma_free(struct driver_data *dd) struct mtip_port *port = dd->port; if (port->block1) - dmam_free_coherent(&dd->pdev->dev, BLOCK_DMA_ALLOC_SZ, + dma_free_coherent(&dd->pdev->dev, BLOCK_DMA_ALLOC_SZ, port->block1, port->block1_dma); if (port->command_list) { - dmam_free_coherent(&dd->pdev->dev, AHCI_CMD_TBL_SZ, + dma_free_coherent(&dd->pdev->dev, AHCI_CMD_TBL_SZ, port->command_list, port->command_list_dma); } } @@ -2861,7 +2861,7 @@ static int mtip_dma_alloc(struct driver_data *dd) /* Allocate dma memory for RX Fis, Identify, and Sector Bufffer */ port->block1 = - dmam_alloc_coherent(&dd->pdev->dev, BLOCK_DMA_ALLOC_SZ, + dma_alloc_coherent(&dd->pdev->dev, BLOCK_DMA_ALLOC_SZ, &port->block1_dma, GFP_KERNEL); if (!port->block1) return -ENOMEM; @@ -2869,10 +2869,10 @@ static int mtip_dma_alloc(struct driver_data *dd) /* Allocate dma memory for command list */ port->command_list = - dmam_alloc_coherent(&dd->pdev->dev, AHCI_CMD_TBL_SZ, + dma_alloc_coherent(&dd->pdev->dev, AHCI_CMD_TBL_SZ, &port->command_list_dma, GFP_KERNEL); if (!port->command_list) { - dmam_free_coherent(&dd->pdev->dev, BLOCK_DMA_ALLOC_SZ, + dma_free_coherent(&dd->pdev->dev, BLOCK_DMA_ALLOC_SZ, port->block1, port->block1_dma); port->block1 = NULL; port->block1_dma = 0; @@ -3057,13 +3057,8 @@ static int mtip_hw_init(struct driver_data *dd) mtip_start_port(dd->port); /* Setup the ISR and enable interrupts. */ - rv = devm_request_irq(&dd->pdev->dev, - dd->pdev->irq, - mtip_irq_handler, - IRQF_SHARED, - dev_driver_string(&dd->pdev->dev), - dd); - + rv = request_irq(dd->pdev->irq, mtip_irq_handler, IRQF_SHARED, + dev_driver_string(&dd->pdev->dev), dd); if (rv) { dev_err(&dd->pdev->dev, "Unable to allocate IRQ %d\n", dd->pdev->irq); @@ -3091,7 +3086,7 @@ out3: /* Release the IRQ. */ irq_set_affinity_hint(dd->pdev->irq, NULL); - devm_free_irq(&dd->pdev->dev, dd->pdev->irq, dd); + free_irq(dd->pdev->irq, dd); out2: mtip_deinit_port(dd->port); @@ -3146,7 +3141,7 @@ static int mtip_hw_exit(struct driver_data *dd) /* Release the IRQ. */ irq_set_affinity_hint(dd->pdev->irq, NULL); - devm_free_irq(&dd->pdev->dev, dd->pdev->irq, dd); + free_irq(dd->pdev->irq, dd); msleep(1000); /* Free dma regions */ @@ -3610,8 +3605,8 @@ static void mtip_free_cmd(struct blk_mq_tag_set *set, struct request *rq, if (!cmd->command) return; - dmam_free_coherent(&dd->pdev->dev, CMD_DMA_ALLOC_SZ, - cmd->command, cmd->command_dma); + dma_free_coherent(&dd->pdev->dev, CMD_DMA_ALLOC_SZ, cmd->command, + cmd->command_dma); } static int mtip_init_cmd(struct blk_mq_tag_set *set, struct request *rq, @@ -3620,7 +3615,7 @@ static int mtip_init_cmd(struct blk_mq_tag_set *set, struct request *rq, struct driver_data *dd = set->driver_data; struct mtip_cmd *cmd = blk_mq_rq_to_pdu(rq); - cmd->command = dmam_alloc_coherent(&dd->pdev->dev, CMD_DMA_ALLOC_SZ, + cmd->command = dma_alloc_coherent(&dd->pdev->dev, CMD_DMA_ALLOC_SZ, &cmd->command_dma, GFP_KERNEL); if (!cmd->command) return -ENOMEM; diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c index 7c9a949e876b..90ba9f4c03f3 100644 --- a/drivers/block/nbd.c +++ b/drivers/block/nbd.c @@ -1571,7 +1571,7 @@ static int nbd_dev_add(int index) nbd->tag_set.numa_node = NUMA_NO_NODE; nbd->tag_set.cmd_size = sizeof(struct nbd_cmd); nbd->tag_set.flags = BLK_MQ_F_SHOULD_MERGE | - BLK_MQ_F_SG_MERGE | BLK_MQ_F_BLOCKING; + BLK_MQ_F_BLOCKING; nbd->tag_set.driver_data = nbd; err = blk_mq_alloc_tag_set(&nbd->tag_set); @@ -2118,8 +2118,7 @@ static int nbd_genl_status(struct sk_buff *skb, struct genl_info *info) } nla_nest_end(reply, dev_list); genlmsg_end(reply, reply_head); - genlmsg_reply(reply, info); - ret = 0; + ret = genlmsg_reply(reply, info); out: mutex_unlock(&nbd_index_mutex); return ret; diff --git a/drivers/block/null_blk_main.c b/drivers/block/null_blk_main.c index 62c9654b9ce8..417a9f15c116 100644 --- a/drivers/block/null_blk_main.c +++ b/drivers/block/null_blk_main.c @@ -1104,7 +1104,7 @@ static int null_handle_bio(struct nullb_cmd *cmd) len = bvec.bv_len; err = null_transfer(nullb, bvec.bv_page, len, bvec.bv_offset, op_is_write(bio_op(bio)), sector, - bio_op(bio) & REQ_FUA); + bio->bi_opf & REQ_FUA); if (err) { spin_unlock_irq(&nullb->lock); return err; @@ -1678,7 +1678,6 @@ static int null_add_dev(struct nullb_device *dev) if (dev->cache_size > 0) { set_bit(NULLB_DEV_FL_CACHE, &nullb->dev->flags); blk_queue_write_cache(nullb->q, true, true); - blk_queue_flush_queueable(nullb->q, true); } if (dev->zoned) { diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c index 282e2e82d849..74088d8dbaf3 100644 --- a/drivers/block/rbd.c +++ b/drivers/block/rbd.c @@ -3987,7 +3987,7 @@ static int rbd_init_disk(struct rbd_device *rbd_dev) rbd_dev->tag_set.ops = &rbd_mq_ops; rbd_dev->tag_set.queue_depth = rbd_dev->opts->queue_depth; rbd_dev->tag_set.numa_node = NUMA_NO_NODE; - rbd_dev->tag_set.flags = BLK_MQ_F_SHOULD_MERGE | BLK_MQ_F_SG_MERGE; + rbd_dev->tag_set.flags = BLK_MQ_F_SHOULD_MERGE; rbd_dev->tag_set.nr_hw_queues = 1; rbd_dev->tag_set.cmd_size = sizeof(struct work_struct); diff --git a/drivers/block/skd_main.c b/drivers/block/skd_main.c index ab893a7571a2..7d3ad6c22ee5 100644 --- a/drivers/block/skd_main.c +++ b/drivers/block/skd_main.c @@ -2843,7 +2843,6 @@ static int skd_cons_disk(struct skd_device *skdev) skdev->sgs_per_request * sizeof(struct scatterlist); skdev->tag_set.numa_node = NUMA_NO_NODE; skdev->tag_set.flags = BLK_MQ_F_SHOULD_MERGE | - BLK_MQ_F_SG_MERGE | BLK_ALLOC_POLICY_TO_MQ_FLAG(BLK_TAG_ALLOC_FIFO); skdev->tag_set.driver_data = skdev; rc = blk_mq_alloc_tag_set(&skdev->tag_set); diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c index 0ed4b200fa58..d43a5677ccbc 100644 --- a/drivers/block/xen-blkfront.c +++ b/drivers/block/xen-blkfront.c @@ -977,7 +977,7 @@ static int xlvbd_init_blk_queue(struct gendisk *gd, u16 sector_size, } else info->tag_set.queue_depth = BLK_RING_SIZE(info); info->tag_set.numa_node = NUMA_NO_NODE; - info->tag_set.flags = BLK_MQ_F_SHOULD_MERGE | BLK_MQ_F_SG_MERGE; + info->tag_set.flags = BLK_MQ_F_SHOULD_MERGE; info->tag_set.cmd_size = sizeof(struct blkif_req); info->tag_set.driver_data = info; diff --git a/drivers/cdrom/cdrom.c b/drivers/cdrom/cdrom.c index 614ecdbb4ab7..933268b8d6a5 100644 --- a/drivers/cdrom/cdrom.c +++ b/drivers/cdrom/cdrom.c @@ -265,6 +265,7 @@ /* #define ERRLOGMASK (CD_WARNING|CD_OPEN|CD_COUNT_TRACKS|CD_CLOSE) */ /* #define ERRLOGMASK (CD_WARNING|CD_REG_UNREG|CD_DO_IOCTL|CD_OPEN|CD_CLOSE|CD_COUNT_TRACKS) */ +#include <linux/atomic.h> #include <linux/module.h> #include <linux/fs.h> #include <linux/major.h> @@ -3692,9 +3693,9 @@ static struct ctl_table_header *cdrom_sysctl_header; static void cdrom_sysctl_register(void) { - static int initialized; + static atomic_t initialized = ATOMIC_INIT(0); - if (initialized == 1) + if (!atomic_add_unless(&initialized, 1, 1)) return; cdrom_sysctl_header = register_sysctl_table(cdrom_root_table); @@ -3705,8 +3706,6 @@ static void cdrom_sysctl_register(void) cdrom_sysctl_settings.debug = debug; cdrom_sysctl_settings.lock = lockdoor; cdrom_sysctl_settings.check = check_media_type; - - initialized = 1; } static void cdrom_sysctl_unregister(void) diff --git a/drivers/lightnvm/pblk-core.c b/drivers/lightnvm/pblk-core.c index 1ff165351180..6ca868868fee 100644 --- a/drivers/lightnvm/pblk-core.c +++ b/drivers/lightnvm/pblk-core.c @@ -141,7 +141,7 @@ struct nvm_chk_meta *pblk_get_chunk_meta(struct pblk *pblk) ret = nvm_get_chunk_meta(dev, ppa, geo->all_chunks, meta); if (ret) { - kfree(meta); + vfree(meta); return ERR_PTR(-EIO); } @@ -1065,7 +1065,7 @@ static int pblk_line_init_metadata(struct pblk *pblk, struct pblk_line *line, bitmap_set(line->lun_bitmap, 0, lm->lun_bitmap_len); smeta_buf->header.identifier = cpu_to_le32(PBLK_MAGIC); - memcpy(smeta_buf->header.uuid, pblk->instance_uuid, 16); + guid_copy((guid_t *)&smeta_buf->header.uuid, &pblk->instance_uuid); smeta_buf->header.id = cpu_to_le32(line->id); smeta_buf->header.type = cpu_to_le16(line->type); smeta_buf->header.version_major = SMETA_VERSION_MAJOR; @@ -1278,6 +1278,7 @@ static int pblk_line_prepare(struct pblk *pblk, struct pblk_line *line) spin_unlock(&line->lock); kref_init(&line->ref); + atomic_set(&line->sec_to_update, 0); return 0; } @@ -1874,7 +1875,8 @@ void pblk_line_close_meta(struct pblk *pblk, struct pblk_line *line) if (le32_to_cpu(emeta_buf->header.identifier) != PBLK_MAGIC) { emeta_buf->header.identifier = cpu_to_le32(PBLK_MAGIC); - memcpy(emeta_buf->header.uuid, pblk->instance_uuid, 16); + guid_copy((guid_t *)&emeta_buf->header.uuid, + &pblk->instance_uuid); emeta_buf->header.id = cpu_to_le32(line->id); emeta_buf->header.type = cpu_to_le16(line->type); emeta_buf->header.version_major = EMETA_VERSION_MAJOR; diff --git a/drivers/lightnvm/pblk-gc.c b/drivers/lightnvm/pblk-gc.c index 2fa118c8eb71..26a52ea7ec45 100644 --- a/drivers/lightnvm/pblk-gc.c +++ b/drivers/lightnvm/pblk-gc.c @@ -365,16 +365,22 @@ static struct pblk_line *pblk_gc_get_victim_line(struct pblk *pblk, struct list_head *group_list) { struct pblk_line *line, *victim; - int line_vsc, victim_vsc; + unsigned int line_vsc = ~0x0L, victim_vsc = ~0x0L; victim = list_first_entry(group_list, struct pblk_line, list); + list_for_each_entry(line, group_list, list) { - line_vsc = le32_to_cpu(*line->vsc); - victim_vsc = le32_to_cpu(*victim->vsc); - if (line_vsc < victim_vsc) + if (!atomic_read(&line->sec_to_update)) + line_vsc = le32_to_cpu(*line->vsc); + if (line_vsc < victim_vsc) { victim = line; + victim_vsc = le32_to_cpu(*victim->vsc); + } } + if (victim_vsc == ~0x0) + return NULL; + return victim; } @@ -448,13 +454,13 @@ next_gc_group: do { spin_lock(&l_mg->gc_lock); - if (list_empty(group_list)) { + + line = pblk_gc_get_victim_line(pblk, group_list); + if (!line) { spin_unlock(&l_mg->gc_lock); break; } - line = pblk_gc_get_victim_line(pblk, group_list); - spin_lock(&line->lock); WARN_ON(line->state != PBLK_LINESTATE_CLOSED); line->state = PBLK_LINESTATE_GC; diff --git a/drivers/lightnvm/pblk-init.c b/drivers/lightnvm/pblk-init.c index f9a3e47b6a93..8b643d0bffae 100644 --- a/drivers/lightnvm/pblk-init.c +++ b/drivers/lightnvm/pblk-init.c @@ -130,7 +130,7 @@ static int pblk_l2p_recover(struct pblk *pblk, bool factory_init) struct pblk_line *line = NULL; if (factory_init) { - pblk_setup_uuid(pblk); + guid_gen(&pblk->instance_uuid); } else { line = pblk_recov_l2p(pblk); if (IS_ERR(line)) { @@ -584,14 +584,12 @@ static void pblk_lines_free(struct pblk *pblk) struct pblk_line *line; int i; - spin_lock(&l_mg->free_lock); for (i = 0; i < l_mg->nr_lines; i++) { line = &pblk->lines[i]; pblk_line_free(line); pblk_line_meta_free(l_mg, line); } - spin_unlock(&l_mg->free_lock); pblk_line_mg_free(pblk); diff --git a/drivers/lightnvm/pblk-map.c b/drivers/lightnvm/pblk-map.c index 79df583ea709..7fbc99b60cac 100644 --- a/drivers/lightnvm/pblk-map.c +++ b/drivers/lightnvm/pblk-map.c @@ -73,6 +73,7 @@ static int pblk_map_page_data(struct pblk *pblk, unsigned int sentry, */ if (i < valid_secs) { kref_get(&line->ref); + atomic_inc(&line->sec_to_update); w_ctx = pblk_rb_w_ctx(&pblk->rwb, sentry + i); w_ctx->ppa = ppa_list[i]; meta->lba = cpu_to_le64(w_ctx->lba); diff --git a/drivers/lightnvm/pblk-rb.c b/drivers/lightnvm/pblk-rb.c index d4ca8c64ee0f..03c241b340ea 100644 --- a/drivers/lightnvm/pblk-rb.c +++ b/drivers/lightnvm/pblk-rb.c @@ -45,10 +45,23 @@ void pblk_rb_free(struct pblk_rb *rb) /* * pblk_rb_calculate_size -- calculate the size of the write buffer */ -static unsigned int pblk_rb_calculate_size(unsigned int nr_entries) +static unsigned int pblk_rb_calculate_size(unsigned int nr_entries, + unsigned int threshold) { - /* Alloc a write buffer that can at least fit 128 entries */ - return (1 << max(get_count_order(nr_entries), 7)); + unsigned int thr_sz = 1 << (get_count_order(threshold + NVM_MAX_VLBA)); + unsigned int max_sz = max(thr_sz, nr_entries); + unsigned int max_io; + + /* Alloc a write buffer that can (i) fit at least two split bios + * (considering max I/O size NVM_MAX_VLBA, and (ii) guarantee that the + * threshold will be respected + */ + max_io = (1 << max((int)(get_count_order(max_sz)), + (int)(get_count_order(NVM_MAX_VLBA << 1)))); + if ((threshold + NVM_MAX_VLBA) >= max_io) + max_io <<= 1; + + return max_io; } /* @@ -67,12 +80,12 @@ int pblk_rb_init(struct pblk_rb *rb, unsigned int size, unsigned int threshold, unsigned int alloc_order, order, iter; unsigned int nr_entries; - nr_entries = pblk_rb_calculate_size(size); + nr_entries = pblk_rb_calculate_size(size, threshold); entries = vzalloc(array_size(nr_entries, sizeof(struct pblk_rb_entry))); if (!entries) return -ENOMEM; - power_size = get_count_order(size); + power_size = get_count_order(nr_entries); power_seg_sz = get_count_order(seg_size); down_write(&pblk_rb_lock); @@ -149,7 +162,7 @@ int pblk_rb_init(struct pblk_rb *rb, unsigned int size, unsigned int threshold, * Initialize rate-limiter, which controls access to the write buffer * by user and GC I/O */ - pblk_rl_init(&pblk->rl, rb->nr_entries); + pblk_rl_init(&pblk->rl, rb->nr_entries, threshold); return 0; } @@ -247,6 +260,7 @@ static int __pblk_rb_update_l2p(struct pblk_rb *rb, unsigned int to_update) entry->cacheline); line = pblk_ppa_to_line(pblk, w_ctx->ppa); + atomic_dec(&line->sec_to_update); kref_put(&line->ref, pblk_line_put); clean_wctx(w_ctx); rb->l2p_update = pblk_rb_ptr_wrap(rb, rb->l2p_update, 1); diff --git a/drivers/lightnvm/pblk-recovery.c b/drivers/lightnvm/pblk-recovery.c index 5ee20da7bdb3..d86f580036d3 100644 --- a/drivers/lightnvm/pblk-recovery.c +++ b/drivers/lightnvm/pblk-recovery.c @@ -302,35 +302,55 @@ static int pblk_pad_distance(struct pblk *pblk, struct pblk_line *line) return (distance > line->left_msecs) ? line->left_msecs : distance; } -static int pblk_line_wp_is_unbalanced(struct pblk *pblk, - struct pblk_line *line) +/* Return a chunk belonging to a line by stripe(write order) index */ +static struct nvm_chk_meta *pblk_get_stripe_chunk(struct pblk *pblk, + struct pblk_line *line, + int index) { struct nvm_tgt_dev *dev = pblk->dev; struct nvm_geo *geo = &dev->geo; - struct pblk_line_meta *lm = &pblk->lm; struct pblk_lun *rlun; - struct nvm_chk_meta *chunk; struct ppa_addr ppa; - u64 line_wp; - int pos, i; + int pos; - rlun = &pblk->luns[0]; + rlun = &pblk->luns[index]; ppa = rlun->bppa; pos = pblk_ppa_to_pos(geo, ppa); - chunk = &line->chks[pos]; - line_wp = chunk->wp; + return &line->chks[pos]; +} - for (i = 1; i < lm->blk_per_line; i++) { - rlun = &pblk->luns[i]; - ppa = rlun->bppa; - pos = pblk_ppa_to_pos(geo, ppa); - chunk = &line->chks[pos]; +static int pblk_line_wps_are_unbalanced(struct pblk *pblk, + struct pblk_line *line) +{ + struct pblk_line_meta *lm = &pblk->lm; + int blk_in_line = lm->blk_per_line; + struct nvm_chk_meta *chunk; + u64 max_wp, min_wp; + int i; + + i = find_first_zero_bit(line->blk_bitmap, blk_in_line); - if (chunk->wp > line_wp) + /* If there is one or zero good chunks in the line, + * the write pointers can't be unbalanced. + */ + if (i >= (blk_in_line - 1)) + return 0; + + chunk = pblk_get_stripe_chunk(pblk, line, i); + max_wp = chunk->wp; + if (max_wp > pblk->max_write_pgs) + min_wp = max_wp - pblk->max_write_pgs; + else + min_wp = 0; + + i = find_next_zero_bit(line->blk_bitmap, blk_in_line, i + 1); + while (i < blk_in_line) { + chunk = pblk_get_stripe_chunk(pblk, line, i); + if (chunk->wp > max_wp || chunk->wp < min_wp) return 1; - else if (chunk->wp < line_wp) - line_wp = chunk->wp; + + i = find_next_zero_bit(line->blk_bitmap, blk_in_line, i + 1); } return 0; @@ -356,7 +376,7 @@ static int pblk_recov_scan_oob(struct pblk *pblk, struct pblk_line *line, int ret; u64 left_ppas = pblk_sec_in_open_line(pblk, line) - lm->smeta_sec; - if (pblk_line_wp_is_unbalanced(pblk, line)) + if (pblk_line_wps_are_unbalanced(pblk, line)) pblk_warn(pblk, "recovering unbalanced line (%d)\n", line->id); ppa_list = p.ppa_list; @@ -703,11 +723,13 @@ struct pblk_line *pblk_recov_l2p(struct pblk *pblk) /* The first valid instance uuid is used for initialization */ if (!valid_uuid) { - memcpy(pblk->instance_uuid, smeta_buf->header.uuid, 16); + guid_copy(&pblk->instance_uuid, + (guid_t *)&smeta_buf->header.uuid); valid_uuid = 1; } - if (memcmp(pblk->instance_uuid, smeta_buf->header.uuid, 16)) { + if (!guid_equal(&pblk->instance_uuid, + (guid_t *)&smeta_buf->header.uuid)) { pblk_debug(pblk, "ignore line %u due to uuid mismatch\n", i); continue; @@ -737,7 +759,7 @@ struct pblk_line *pblk_recov_l2p(struct pblk *pblk) } if (!found_lines) { - pblk_setup_uuid(pblk); + guid_gen(&pblk->instance_uuid); spin_lock(&l_mg->free_lock); WARN_ON_ONCE(!test_and_clear_bit(meta_line, diff --git a/drivers/lightnvm/pblk-rl.c b/drivers/lightnvm/pblk-rl.c index 76116d5f78e4..b014957dde0b 100644 --- a/drivers/lightnvm/pblk-rl.c +++ b/drivers/lightnvm/pblk-rl.c @@ -207,7 +207,7 @@ void pblk_rl_free(struct pblk_rl *rl) del_timer(&rl->u_timer); } -void pblk_rl_init(struct pblk_rl *rl, int budget) +void pblk_rl_init(struct pblk_rl *rl, int budget, int threshold) { struct pblk *pblk = container_of(rl, struct pblk, rl); struct nvm_tgt_dev *dev = pblk->dev; @@ -217,7 +217,6 @@ void pblk_rl_init(struct pblk_rl *rl, int budget) int sec_meta, blk_meta; unsigned int rb_windows; - /* Consider sectors used for metadata */ sec_meta = (lm->smeta_sec + lm->emeta_sec[0]) * l_mg->nr_free_lines; blk_meta = DIV_ROUND_UP(sec_meta, geo->clba); @@ -234,7 +233,7 @@ void pblk_rl_init(struct pblk_rl *rl, int budget) /* To start with, all buffer is available to user I/O writers */ rl->rb_budget = budget; rl->rb_user_max = budget; - rl->rb_max_io = budget >> 1; + rl->rb_max_io = threshold ? (budget - threshold) : (budget - 1); rl->rb_gc_max = 0; rl->rb_state = PBLK_RL_HIGH; diff --git a/drivers/lightnvm/pblk-trace.h b/drivers/lightnvm/pblk-trace.h index 679e5c458ca6..9534503b69d9 100644 --- a/drivers/lightnvm/pblk-trace.h +++ b/drivers/lightnvm/pblk-trace.h @@ -139,7 +139,7 @@ TRACE_EVENT(pblk_state, /* This part must be outside protection */ #undef TRACE_INCLUDE_PATH -#define TRACE_INCLUDE_PATH ../../../drivers/lightnvm +#define TRACE_INCLUDE_PATH ../../drivers/lightnvm #undef TRACE_INCLUDE_FILE #define TRACE_INCLUDE_FILE pblk-trace #include <trace/define_trace.h> diff --git a/drivers/lightnvm/pblk-write.c b/drivers/lightnvm/pblk-write.c index 06d56deb645d..6593deab52da 100644 --- a/drivers/lightnvm/pblk-write.c +++ b/drivers/lightnvm/pblk-write.c @@ -177,6 +177,7 @@ static void pblk_prepare_resubmit(struct pblk *pblk, unsigned int sentry, * re-map these entries */ line = pblk_ppa_to_line(pblk, w_ctx->ppa); + atomic_dec(&line->sec_to_update); kref_put(&line->ref, pblk_line_put); } spin_unlock(&pblk->trans_lock); diff --git a/drivers/lightnvm/pblk.h b/drivers/lightnvm/pblk.h index 85e38ed62f85..ac3ab778e976 100644 --- a/drivers/lightnvm/pblk.h +++ b/drivers/lightnvm/pblk.h @@ -131,8 +131,8 @@ struct pblk_pr_ctx { unsigned int bio_init_idx; void *ppa_ptr; dma_addr_t dma_ppa_list; - __le64 lba_list_mem[NVM_MAX_VLBA]; - __le64 lba_list_media[NVM_MAX_VLBA]; + u64 lba_list_mem[NVM_MAX_VLBA]; + u64 lba_list_media[NVM_MAX_VLBA]; }; /* Pad context */ @@ -487,6 +487,7 @@ struct pblk_line { __le32 *vsc; /* Valid sector count in line */ struct kref ref; /* Write buffer L2P references */ + atomic_t sec_to_update; /* Outstanding L2P updates to ppa */ struct pblk_w_err_gc *w_err_gc; /* Write error gc recovery metadata */ @@ -646,7 +647,7 @@ struct pblk { int sec_per_write; - unsigned char instance_uuid[16]; + guid_t instance_uuid; /* Persistent write amplification counters, 4kb sector I/Os */ atomic64_t user_wa; /* Sectors written by user */ @@ -924,7 +925,7 @@ int pblk_gc_sysfs_force(struct pblk *pblk, int force); /* * pblk rate limiter */ -void pblk_rl_init(struct pblk_rl *rl, int budget); +void pblk_rl_init(struct pblk_rl *rl, int budget, int threshold); void pblk_rl_free(struct pblk_rl *rl); void pblk_rl_update_rates(struct pblk_rl *rl); int pblk_rl_high_thrs(struct pblk_rl *rl); @@ -1360,14 +1361,6 @@ static inline unsigned int pblk_get_secs(struct bio *bio) return bio->bi_iter.bi_size / PBLK_EXPOSED_PAGE_SIZE; } -static inline void pblk_setup_uuid(struct pblk *pblk) -{ - uuid_le uuid; - - uuid_le_gen(&uuid); - memcpy(pblk->instance_uuid, uuid.b, 16); -} - static inline char *pblk_disk_name(struct pblk *pblk) { struct gendisk *disk = pblk->disk; diff --git a/drivers/md/bcache/btree.c b/drivers/md/bcache/btree.c index 23cb1dc7296b..64def336f053 100644 --- a/drivers/md/bcache/btree.c +++ b/drivers/md/bcache/btree.c @@ -432,8 +432,9 @@ static void do_btree_node_write(struct btree *b) int j; struct bio_vec *bv; void *base = (void *) ((unsigned long) i & ~(PAGE_SIZE - 1)); + struct bvec_iter_all iter_all; - bio_for_each_segment_all(bv, b->bio, j) + bio_for_each_segment_all(bv, b->bio, j, iter_all) memcpy(page_address(bv->bv_page), base + j * PAGE_SIZE, PAGE_SIZE); diff --git a/drivers/md/bcache/extents.c b/drivers/md/bcache/extents.c index 956004366699..886710043025 100644 --- a/drivers/md/bcache/extents.c +++ b/drivers/md/bcache/extents.c @@ -538,6 +538,7 @@ static bool bch_extent_bad(struct btree_keys *bk, const struct bkey *k) { struct btree *b = container_of(bk, struct btree, keys); unsigned int i, stale; + char buf[80]; if (!KEY_PTRS(k) || bch_extent_invalid(bk, k)) @@ -547,19 +548,19 @@ static bool bch_extent_bad(struct btree_keys *bk, const struct bkey *k) if (!ptr_available(b->c, k, i)) return true; - if (!expensive_debug_checks(b->c) && KEY_DIRTY(k)) - return false; - for (i = 0; i < KEY_PTRS(k); i++) { stale = ptr_stale(b->c, k, i); + if (stale && KEY_DIRTY(k)) { + bch_extent_to_text(buf, sizeof(buf), k); + pr_info("stale dirty pointer, stale %u, key: %s", + stale, buf); + } + btree_bug_on(stale > BUCKET_GC_GEN_MAX, b, "key too stale: %i, need_gc %u", stale, b->c->need_gc); - btree_bug_on(stale && KEY_DIRTY(k) && KEY_SIZE(k), - b, "stale dirty pointer"); - if (stale) return true; diff --git a/drivers/md/bcache/request.c b/drivers/md/bcache/request.c index 15070412a32e..f101bfe8657a 100644 --- a/drivers/md/bcache/request.c +++ b/drivers/md/bcache/request.c @@ -392,10 +392,11 @@ static bool check_should_bypass(struct cached_dev *dc, struct bio *bio) /* * Flag for bypass if the IO is for read-ahead or background, - * unless the read-ahead request is for metadata (eg, for gfs2). + * unless the read-ahead request is for metadata + * (eg, for gfs2 or xfs). */ if (bio->bi_opf & (REQ_RAHEAD|REQ_BACKGROUND) && - !(bio->bi_opf & REQ_PRIO)) + !(bio->bi_opf & (REQ_META|REQ_PRIO))) goto skip; if (bio->bi_iter.bi_sector & (c->sb.block_size - 1) || @@ -877,7 +878,7 @@ static int cached_dev_cache_miss(struct btree *b, struct search *s, } if (!(bio->bi_opf & REQ_RAHEAD) && - !(bio->bi_opf & REQ_PRIO) && + !(bio->bi_opf & (REQ_META|REQ_PRIO)) && s->iop.c->gc_stats.in_use < CUTOFF_CACHE_READA) reada = min_t(sector_t, dc->readahead >> 9, get_capacity(bio->bi_disk) - bio_end_sector(bio)); diff --git a/drivers/md/bcache/stats.c b/drivers/md/bcache/stats.c index 894410f3f829..ba1c93791d8d 100644 --- a/drivers/md/bcache/stats.c +++ b/drivers/md/bcache/stats.c @@ -111,7 +111,7 @@ void bch_cache_accounting_clear(struct cache_accounting *acc) { memset(&acc->total.cache_hits, 0, - sizeof(unsigned long) * 7); + sizeof(struct cache_stats)); } void bch_cache_accounting_destroy(struct cache_accounting *acc) diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c index 4dee119c3664..a697a3a923cd 100644 --- a/drivers/md/bcache/super.c +++ b/drivers/md/bcache/super.c @@ -1615,21 +1615,21 @@ static void conditional_stop_bcache_device(struct cache_set *c, */ pr_warn("stop_when_cache_set_failed of %s is \"auto\" and cache is dirty, stop it to avoid potential data corruption.", d->disk->disk_name); - /* - * There might be a small time gap that cache set is - * released but bcache device is not. Inside this time - * gap, regular I/O requests will directly go into - * backing device as no cache set attached to. This - * behavior may also introduce potential inconsistence - * data in writeback mode while cache is dirty. - * Therefore before calling bcache_device_stop() due - * to a broken cache device, dc->io_disable should be - * explicitly set to true. - */ - dc->io_disable = true; - /* make others know io_disable is true earlier */ - smp_mb(); - bcache_device_stop(d); + /* + * There might be a small time gap that cache set is + * released but bcache device is not. Inside this time + * gap, regular I/O requests will directly go into + * backing device as no cache set attached to. This + * behavior may also introduce potential inconsistence + * data in writeback mode while cache is dirty. + * Therefore before calling bcache_device_stop() due + * to a broken cache device, dc->io_disable should be + * explicitly set to true. + */ + dc->io_disable = true; + /* make others know io_disable is true earlier */ + smp_mb(); + bcache_device_stop(d); } else { /* * dc->stop_when_cache_set_failed == BCH_CACHED_STOP_AUTO diff --git a/drivers/md/bcache/sysfs.c b/drivers/md/bcache/sysfs.c index 557a8a3270a1..17bae9c14ca0 100644 --- a/drivers/md/bcache/sysfs.c +++ b/drivers/md/bcache/sysfs.c @@ -67,6 +67,8 @@ read_attribute(written); read_attribute(btree_written); read_attribute(metadata_written); read_attribute(active_journal_entries); +read_attribute(backing_dev_name); +read_attribute(backing_dev_uuid); sysfs_time_stats_attribute(btree_gc, sec, ms); sysfs_time_stats_attribute(btree_split, sec, us); @@ -243,6 +245,19 @@ SHOW(__bch_cached_dev) return strlen(buf); } + if (attr == &sysfs_backing_dev_name) { + snprintf(buf, BDEVNAME_SIZE + 1, "%s", dc->backing_dev_name); + strcat(buf, "\n"); + return strlen(buf); + } + + if (attr == &sysfs_backing_dev_uuid) { + /* convert binary uuid into 36-byte string plus '\0' */ + snprintf(buf, 36+1, "%pU", dc->sb.uuid); + strcat(buf, "\n"); + return strlen(buf); + } + #undef var return 0; } @@ -262,10 +277,10 @@ STORE(__cached_dev) sysfs_strtoul(data_csum, dc->disk.data_csum); d_strtoul(verify); - d_strtoul(bypass_torture_test); - d_strtoul(writeback_metadata); - d_strtoul(writeback_running); - d_strtoul(writeback_delay); + sysfs_strtoul_bool(bypass_torture_test, dc->bypass_torture_test); + sysfs_strtoul_bool(writeback_metadata, dc->writeback_metadata); + sysfs_strtoul_bool(writeback_running, dc->writeback_running); + sysfs_strtoul_clamp(writeback_delay, dc->writeback_delay, 0, UINT_MAX); sysfs_strtoul_clamp(writeback_percent, dc->writeback_percent, 0, bch_cutoff_writeback); @@ -287,9 +302,15 @@ STORE(__cached_dev) sysfs_strtoul_clamp(writeback_rate_update_seconds, dc->writeback_rate_update_seconds, 1, WRITEBACK_RATE_UPDATE_SECS_MAX); - d_strtoul(writeback_rate_i_term_inverse); - d_strtoul_nonzero(writeback_rate_p_term_inverse); - d_strtoul_nonzero(writeback_rate_minimum); + sysfs_strtoul_clamp(writeback_rate_i_term_inverse, + dc->writeback_rate_i_term_inverse, + 1, UINT_MAX); + sysfs_strtoul_clamp(writeback_rate_p_term_inverse, + dc->writeback_rate_p_term_inverse, + 1, UINT_MAX); + sysfs_strtoul_clamp(writeback_rate_minimum, + dc->writeback_rate_minimum, + 1, UINT_MAX); sysfs_strtoul_clamp(io_error_limit, dc->error_limit, 0, INT_MAX); @@ -299,7 +320,9 @@ STORE(__cached_dev) dc->io_disable = v ? 1 : 0; } - d_strtoi_h(sequential_cutoff); + sysfs_strtoul_clamp(sequential_cutoff, + dc->sequential_cutoff, + 0, UINT_MAX); d_strtoi_h(readahead); if (attr == &sysfs_clear_stats) @@ -452,6 +475,8 @@ static struct attribute *bch_cached_dev_files[] = { &sysfs_verify, &sysfs_bypass_torture_test, #endif + &sysfs_backing_dev_name, + &sysfs_backing_dev_uuid, NULL }; KTYPE(bch_cached_dev); @@ -761,10 +786,12 @@ STORE(__bch_cache_set) c->shrink.scan_objects(&c->shrink, &sc); } - sysfs_strtoul(congested_read_threshold_us, - c->congested_read_threshold_us); - sysfs_strtoul(congested_write_threshold_us, - c->congested_write_threshold_us); + sysfs_strtoul_clamp(congested_read_threshold_us, + c->congested_read_threshold_us, + 0, UINT_MAX); + sysfs_strtoul_clamp(congested_write_threshold_us, + c->congested_write_threshold_us, + 0, UINT_MAX); if (attr == &sysfs_errors) { v = __sysfs_match_string(error_actions, -1, buf); @@ -774,12 +801,20 @@ STORE(__bch_cache_set) c->on_error = v; } - if (attr == &sysfs_io_error_limit) - c->error_limit = strtoul_or_return(buf); + sysfs_strtoul_clamp(io_error_limit, c->error_limit, 0, UINT_MAX); /* See count_io_errors() for why 88 */ - if (attr == &sysfs_io_error_halflife) - c->error_decay = strtoul_or_return(buf) / 88; + if (attr == &sysfs_io_error_halflife) { + unsigned long v = 0; + ssize_t ret; + + ret = strtoul_safe_clamp(buf, v, 0, UINT_MAX); + if (!ret) { + c->error_decay = v / 88; + return size; + } + return ret; + } if (attr == &sysfs_io_disable) { v = strtoul_or_return(buf); @@ -794,13 +829,15 @@ STORE(__bch_cache_set) } } - sysfs_strtoul(journal_delay_ms, c->journal_delay_ms); - sysfs_strtoul(verify, c->verify); - sysfs_strtoul(key_merging_disabled, c->key_merging_disabled); + sysfs_strtoul_clamp(journal_delay_ms, + c->journal_delay_ms, + 0, USHRT_MAX); + sysfs_strtoul_bool(verify, c->verify); + sysfs_strtoul_bool(key_merging_disabled, c->key_merging_disabled); sysfs_strtoul(expensive_debug_checks, c->expensive_debug_checks); - sysfs_strtoul(gc_always_rewrite, c->gc_always_rewrite); - sysfs_strtoul(btree_shrinker_disabled, c->shrinker_disabled); - sysfs_strtoul(copy_gc_enabled, c->copy_gc_enabled); + sysfs_strtoul_bool(gc_always_rewrite, c->gc_always_rewrite); + sysfs_strtoul_bool(btree_shrinker_disabled, c->shrinker_disabled); + sysfs_strtoul_bool(copy_gc_enabled, c->copy_gc_enabled); /* * write gc_after_writeback here may overwrite an already set * BCH_DO_AUTO_GC, it doesn't matter because this flag will be diff --git a/drivers/md/bcache/sysfs.h b/drivers/md/bcache/sysfs.h index 3fe82425859c..215df32f567b 100644 --- a/drivers/md/bcache/sysfs.h +++ b/drivers/md/bcache/sysfs.h @@ -79,11 +79,28 @@ do { \ return strtoul_safe(buf, var) ?: (ssize_t) size; \ } while (0) +#define sysfs_strtoul_bool(file, var) \ +do { \ + if (attr == &sysfs_ ## file) { \ + unsigned long v = strtoul_or_return(buf); \ + \ + var = v ? 1 : 0; \ + return size; \ + } \ +} while (0) + #define sysfs_strtoul_clamp(file, var, min, max) \ do { \ - if (attr == &sysfs_ ## file) \ - return strtoul_safe_clamp(buf, var, min, max) \ - ?: (ssize_t) size; \ + if (attr == &sysfs_ ## file) { \ + unsigned long v = 0; \ + ssize_t ret; \ + ret = strtoul_safe_clamp(buf, v, min, max); \ + if (!ret) { \ + var = v; \ + return size; \ + } \ + return ret; \ + } \ } while (0) #define strtoul_or_return(cp) \ diff --git a/drivers/md/bcache/util.c b/drivers/md/bcache/util.c index 20eddeac1531..62fb917f7a4f 100644 --- a/drivers/md/bcache/util.c +++ b/drivers/md/bcache/util.c @@ -270,7 +270,11 @@ int bch_bio_alloc_pages(struct bio *bio, gfp_t gfp_mask) int i; struct bio_vec *bv; - bio_for_each_segment_all(bv, bio, i) { + /* + * This is called on freshly new bio, so it is safe to access the + * bvec table directly. + */ + for (i = 0, bv = bio->bi_io_vec; i < bio->bi_vcnt; bv++, i++) { bv->bv_page = alloc_page(gfp_mask); if (!bv->bv_page) { while (--bv >= bio->bi_io_vec) diff --git a/drivers/md/bcache/writeback.h b/drivers/md/bcache/writeback.h index 6a743d3bb338..4e4c6810dc3c 100644 --- a/drivers/md/bcache/writeback.h +++ b/drivers/md/bcache/writeback.h @@ -71,6 +71,9 @@ static inline bool should_writeback(struct cached_dev *dc, struct bio *bio, in_use > bch_cutoff_writeback_sync) return false; + if (bio_op(bio) == REQ_OP_DISCARD) + return false; + if (dc->partial_stripes_expensive && bcache_dev_stripe_dirty(dc, bio->bi_iter.bi_sector, bio_sectors(bio))) diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c index dd538e6b2748..dd6565798778 100644 --- a/drivers/md/dm-crypt.c +++ b/drivers/md/dm-crypt.c @@ -1447,8 +1447,9 @@ 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) { + bio_for_each_segment_all(bv, clone, i, iter_all) { BUG_ON(!bv->bv_page); mempool_free(bv->bv_page, &cc->page_pool); } diff --git a/drivers/md/dm-rq.c b/drivers/md/dm-rq.c index a20531e5f3b4..b2c03c079a8d 100644 --- a/drivers/md/dm-rq.c +++ b/drivers/md/dm-rq.c @@ -527,7 +527,7 @@ int dm_mq_init_request_queue(struct mapped_device *md, struct dm_table *t) md->tag_set->ops = &dm_mq_ops; md->tag_set->queue_depth = dm_get_blk_mq_queue_depth(); md->tag_set->numa_node = md->numa_node_id; - md->tag_set->flags = BLK_MQ_F_SHOULD_MERGE | BLK_MQ_F_SG_MERGE; + md->tag_set->flags = BLK_MQ_F_SHOULD_MERGE; md->tag_set->nr_hw_queues = dm_get_blk_mq_nr_hw_queues(); md->tag_set->driver_data = md; diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c index 4b1be754cc41..ba9481f1bf3c 100644 --- a/drivers/md/dm-table.c +++ b/drivers/md/dm-table.c @@ -1698,14 +1698,6 @@ static int device_is_not_random(struct dm_target *ti, struct dm_dev *dev, return q && !blk_queue_add_random(q); } -static int queue_supports_sg_merge(struct dm_target *ti, struct dm_dev *dev, - sector_t start, sector_t len, void *data) -{ - struct request_queue *q = bdev_get_queue(dev->bdev); - - return q && !test_bit(QUEUE_FLAG_NO_SG_MERGE, &q->queue_flags); -} - static bool dm_table_all_devices_attribute(struct dm_table *t, iterate_devices_callout_fn func) { @@ -1902,11 +1894,6 @@ void dm_table_set_restrictions(struct dm_table *t, struct request_queue *q, if (!dm_table_supports_write_zeroes(t)) q->limits.max_write_zeroes_sectors = 0; - if (dm_table_all_devices_attribute(t, queue_supports_sg_merge)) - blk_queue_flag_clear(QUEUE_FLAG_NO_SG_MERGE, q); - else - blk_queue_flag_set(QUEUE_FLAG_NO_SG_MERGE, q); - dm_table_verify_integrity(t); /* diff --git a/drivers/md/md-linear.c b/drivers/md/md-linear.c index d45c697c0ebe..5998d78aa189 100644 --- a/drivers/md/md-linear.c +++ b/drivers/md/md-linear.c @@ -96,8 +96,7 @@ static struct linear_conf *linear_conf(struct mddev *mddev, int raid_disks) int i, cnt; bool discard_supported = false; - conf = kzalloc (sizeof (*conf) + raid_disks*sizeof(struct dev_info), - GFP_KERNEL); + conf = kzalloc(struct_size(conf, disks, raid_disks), GFP_KERNEL); if (!conf) return NULL; diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c index fa47249fa3e4..fdf451aac369 100644 --- a/drivers/md/raid1.c +++ b/drivers/md/raid1.c @@ -1603,11 +1603,9 @@ static void raid1_error(struct mddev *mddev, struct md_rdev *rdev) return; } set_bit(Blocked, &rdev->flags); - if (test_and_clear_bit(In_sync, &rdev->flags)) { + if (test_and_clear_bit(In_sync, &rdev->flags)) mddev->degraded++; - set_bit(Faulty, &rdev->flags); - } else - set_bit(Faulty, &rdev->flags); + set_bit(Faulty, &rdev->flags); spin_unlock_irqrestore(&conf->device_lock, flags); /* * if recovery is running, make sure it aborts. @@ -2120,13 +2118,14 @@ static void process_checks(struct r1bio *r1_bio) struct page **spages = get_resync_pages(sbio)->pages; struct bio_vec *bi; int page_len[RESYNC_PAGES] = { 0 }; + struct bvec_iter_all iter_all; if (sbio->bi_end_io != end_sync_read) continue; /* Now we can 'fixup' the error value */ sbio->bi_status = 0; - bio_for_each_segment_all(bi, sbio, j) + bio_for_each_segment_all(bi, sbio, j, iter_all) page_len[j] = bi->bv_len; if (!status) { diff --git a/drivers/mmc/core/queue.c b/drivers/mmc/core/queue.c index 15a45ec6518d..7c364a9c4eeb 100644 --- a/drivers/mmc/core/queue.c +++ b/drivers/mmc/core/queue.c @@ -417,8 +417,7 @@ int mmc_init_queue(struct mmc_queue *mq, struct mmc_card *card) else mq->tag_set.queue_depth = MMC_QUEUE_DEPTH; mq->tag_set.numa_node = NUMA_NO_NODE; - mq->tag_set.flags = BLK_MQ_F_SHOULD_MERGE | BLK_MQ_F_SG_MERGE | - BLK_MQ_F_BLOCKING; + mq->tag_set.flags = BLK_MQ_F_SHOULD_MERGE | BLK_MQ_F_BLOCKING; mq->tag_set.nr_hw_queues = 1; mq->tag_set.cmd_size = sizeof(struct mmc_queue_req); mq->tag_set.driver_data = mq; diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index 6a9dd68c0f4f..07bf2bff3a76 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -1,15 +1,7 @@ +// SPDX-License-Identifier: GPL-2.0 /* * NVM Express device driver * Copyright (c) 2011-2014, Intel Corporation. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. */ #include <linux/blkdev.h> @@ -151,11 +143,8 @@ int nvme_reset_ctrl_sync(struct nvme_ctrl *ctrl) } EXPORT_SYMBOL_GPL(nvme_reset_ctrl_sync); -static void nvme_delete_ctrl_work(struct work_struct *work) +static void nvme_do_delete_ctrl(struct nvme_ctrl *ctrl) { - struct nvme_ctrl *ctrl = - container_of(work, struct nvme_ctrl, delete_work); - dev_info(ctrl->device, "Removing ctrl: NQN \"%s\"\n", ctrl->opts->subsysnqn); @@ -167,6 +156,14 @@ static void nvme_delete_ctrl_work(struct work_struct *work) nvme_put_ctrl(ctrl); } +static void nvme_delete_ctrl_work(struct work_struct *work) +{ + struct nvme_ctrl *ctrl = + container_of(work, struct nvme_ctrl, delete_work); + + nvme_do_delete_ctrl(ctrl); +} + int nvme_delete_ctrl(struct nvme_ctrl *ctrl) { if (!nvme_change_ctrl_state(ctrl, NVME_CTRL_DELETING)) @@ -177,7 +174,7 @@ int nvme_delete_ctrl(struct nvme_ctrl *ctrl) } EXPORT_SYMBOL_GPL(nvme_delete_ctrl); -int nvme_delete_ctrl_sync(struct nvme_ctrl *ctrl) +static int nvme_delete_ctrl_sync(struct nvme_ctrl *ctrl) { int ret = 0; @@ -186,13 +183,13 @@ int nvme_delete_ctrl_sync(struct nvme_ctrl *ctrl) * can free the controller. */ nvme_get_ctrl(ctrl); - ret = nvme_delete_ctrl(ctrl); + if (!nvme_change_ctrl_state(ctrl, NVME_CTRL_DELETING)) + ret = -EBUSY; if (!ret) - flush_work(&ctrl->delete_work); + nvme_do_delete_ctrl(ctrl); nvme_put_ctrl(ctrl); return ret; } -EXPORT_SYMBOL_GPL(nvme_delete_ctrl_sync); static inline bool nvme_ns_has_pi(struct nvme_ns *ns) { @@ -611,6 +608,22 @@ static blk_status_t nvme_setup_discard(struct nvme_ns *ns, struct request *req, return BLK_STS_OK; } +static inline blk_status_t nvme_setup_write_zeroes(struct nvme_ns *ns, + struct request *req, struct nvme_command *cmnd) +{ + if (ns->ctrl->quirks & NVME_QUIRK_DEALLOCATE_ZEROES) + return nvme_setup_discard(ns, req, cmnd); + + cmnd->write_zeroes.opcode = nvme_cmd_write_zeroes; + cmnd->write_zeroes.nsid = cpu_to_le32(ns->head->ns_id); + cmnd->write_zeroes.slba = + cpu_to_le64(nvme_block_nr(ns, blk_rq_pos(req))); + cmnd->write_zeroes.length = + cpu_to_le16((blk_rq_bytes(req) >> ns->lba_shift) - 1); + cmnd->write_zeroes.control = 0; + return BLK_STS_OK; +} + static inline blk_status_t nvme_setup_rw(struct nvme_ns *ns, struct request *req, struct nvme_command *cmnd) { @@ -705,7 +718,8 @@ blk_status_t nvme_setup_cmd(struct nvme_ns *ns, struct request *req, nvme_setup_flush(ns, cmd); break; case REQ_OP_WRITE_ZEROES: - /* currently only aliased to deallocate for a few ctrls: */ + ret = nvme_setup_write_zeroes(ns, req, cmd); + break; case REQ_OP_DISCARD: ret = nvme_setup_discard(ns, req, cmd); break; @@ -1512,6 +1526,37 @@ static void nvme_config_discard(struct nvme_ns *ns) blk_queue_max_write_zeroes_sectors(queue, UINT_MAX); } +static inline void nvme_config_write_zeroes(struct nvme_ns *ns) +{ + u32 max_sectors; + unsigned short bs = 1 << ns->lba_shift; + + if (!(ns->ctrl->oncs & NVME_CTRL_ONCS_WRITE_ZEROES)) + return; + /* + * Even though NVMe spec explicitly states that MDTS is not + * applicable to the write-zeroes:- "The restriction does not apply to + * commands that do not transfer data between the host and the + * controller (e.g., Write Uncorrectable ro Write Zeroes command).". + * In order to be more cautious use controller's max_hw_sectors value + * to configure the maximum sectors for the write-zeroes which is + * configured based on the controller's MDTS field in the + * nvme_init_identify() if available. + */ + if (ns->ctrl->max_hw_sectors == UINT_MAX) + max_sectors = ((u32)(USHRT_MAX + 1) * bs) >> 9; + else + max_sectors = ((u32)(ns->ctrl->max_hw_sectors + 1) * bs) >> 9; + + blk_queue_max_write_zeroes_sectors(ns->queue, max_sectors); +} + +static inline void nvme_ns_config_oncs(struct nvme_ns *ns) +{ + nvme_config_discard(ns); + nvme_config_write_zeroes(ns); +} + static void nvme_report_ns_ids(struct nvme_ctrl *ctrl, unsigned int nsid, struct nvme_id_ns *id, struct nvme_ns_ids *ids) { @@ -1565,7 +1610,7 @@ static void nvme_update_disk_info(struct gendisk *disk, capacity = 0; set_capacity(disk, capacity); - nvme_config_discard(ns); + nvme_ns_config_oncs(ns); if (id->nsattr & (1 << 0)) set_disk_ro(disk, true); @@ -2280,6 +2325,9 @@ static struct attribute *nvme_subsys_attrs[] = { &subsys_attr_serial.attr, &subsys_attr_firmware_rev.attr, &subsys_attr_subsysnqn.attr, +#ifdef CONFIG_NVME_MULTIPATH + &subsys_attr_iopolicy.attr, +#endif NULL, }; @@ -2332,6 +2380,9 @@ static int nvme_init_subsystem(struct nvme_ctrl *ctrl, struct nvme_id_ctrl *id) memcpy(subsys->firmware_rev, id->fr, sizeof(subsys->firmware_rev)); subsys->vendor_id = le16_to_cpu(id->vid); subsys->cmic = id->cmic; +#ifdef CONFIG_NVME_MULTIPATH + subsys->iopolicy = NVME_IOPOLICY_NUMA; +#endif subsys->dev.class = nvme_subsys_class; subsys->dev.release = nvme_release_subsystem; @@ -3163,21 +3214,23 @@ static int nvme_setup_streams_ns(struct nvme_ctrl *ctrl, struct nvme_ns *ns) return 0; } -static void nvme_alloc_ns(struct nvme_ctrl *ctrl, unsigned nsid) +static int nvme_alloc_ns(struct nvme_ctrl *ctrl, unsigned nsid) { struct nvme_ns *ns; struct gendisk *disk; struct nvme_id_ns *id; char disk_name[DISK_NAME_LEN]; - int node = ctrl->numa_node, flags = GENHD_FL_EXT_DEVT; + int node = ctrl->numa_node, flags = GENHD_FL_EXT_DEVT, ret; ns = kzalloc_node(sizeof(*ns), GFP_KERNEL, node); if (!ns) - return; + return -ENOMEM; ns->queue = blk_mq_init_queue(ctrl->tagset); - if (IS_ERR(ns->queue)) + if (IS_ERR(ns->queue)) { + ret = PTR_ERR(ns->queue); goto out_free_ns; + } blk_queue_flag_set(QUEUE_FLAG_NONROT, ns->queue); if (ctrl->ops->flags & NVME_F_PCI_P2PDMA) @@ -3193,20 +3246,27 @@ static void nvme_alloc_ns(struct nvme_ctrl *ctrl, unsigned nsid) nvme_set_queue_limits(ctrl, ns->queue); id = nvme_identify_ns(ctrl, nsid); - if (!id) + if (!id) { + ret = -EIO; goto out_free_queue; + } - if (id->ncap == 0) + if (id->ncap == 0) { + ret = -EINVAL; goto out_free_id; + } - if (nvme_init_ns_head(ns, nsid, id)) + ret = nvme_init_ns_head(ns, nsid, id); + if (ret) goto out_free_id; nvme_setup_streams_ns(ctrl, ns); nvme_set_disk_name(disk_name, ns, ctrl, &flags); disk = alloc_disk_node(0, node); - if (!disk) + if (!disk) { + ret = -ENOMEM; goto out_unlink_ns; + } disk->fops = &nvme_fops; disk->private_data = ns; @@ -3218,7 +3278,8 @@ static void nvme_alloc_ns(struct nvme_ctrl *ctrl, unsigned nsid) __nvme_revalidate_disk(disk, id); if ((ctrl->quirks & NVME_QUIRK_LIGHTNVM) && id->vs[0] == 0x1) { - if (nvme_nvm_register(ns, disk_name, node)) { + ret = nvme_nvm_register(ns, disk_name, node); + if (ret) { dev_warn(ctrl->device, "LightNVM init failure\n"); goto out_put_disk; } @@ -3236,7 +3297,7 @@ static void nvme_alloc_ns(struct nvme_ctrl *ctrl, unsigned nsid) nvme_fault_inject_init(ns); kfree(id); - return; + return 0; out_put_disk: put_disk(ns->disk); out_unlink_ns: @@ -3249,6 +3310,7 @@ static void nvme_alloc_ns(struct nvme_ctrl *ctrl, unsigned nsid) blk_cleanup_queue(ns->queue); out_free_ns: kfree(ns); + return ret; } static void nvme_ns_remove(struct nvme_ns *ns) @@ -3596,8 +3658,6 @@ void nvme_stop_ctrl(struct nvme_ctrl *ctrl) nvme_stop_keep_alive(ctrl); flush_work(&ctrl->async_event_work); cancel_work_sync(&ctrl->fw_act_work); - if (ctrl->ops->stop_ctrl) - ctrl->ops->stop_ctrl(ctrl); } EXPORT_SYMBOL_GPL(nvme_stop_ctrl); diff --git a/drivers/nvme/host/fabrics.c b/drivers/nvme/host/fabrics.c index 3eb908c50e1a..d4cb826f58ff 100644 --- a/drivers/nvme/host/fabrics.c +++ b/drivers/nvme/host/fabrics.c @@ -1,15 +1,7 @@ +// SPDX-License-Identifier: GPL-2.0 /* * NVMe over Fabrics common host code. * Copyright (c) 2015-2016 HGST, a Western Digital Company. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/init.h> @@ -430,6 +422,7 @@ EXPORT_SYMBOL_GPL(nvmf_connect_admin_queue); * @qid: NVMe I/O queue number for the new I/O connection between * host and target (note qid == 0 is illegal as this is * the Admin queue, per NVMe standard). + * @poll: Whether or not to poll for the completion of the connect cmd. * * This function issues a fabrics-protocol connection * of a NVMe I/O queue (via NVMe Fabrics "Connect" command) diff --git a/drivers/nvme/host/fabrics.h b/drivers/nvme/host/fabrics.h index 478343b73e38..3044d8b99a24 100644 --- a/drivers/nvme/host/fabrics.h +++ b/drivers/nvme/host/fabrics.h @@ -1,15 +1,7 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* * NVMe over Fabrics common host code. * Copyright (c) 2015-2016 HGST, a Western Digital Company. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. */ #ifndef _NVME_FABRICS_H #define _NVME_FABRICS_H 1 diff --git a/drivers/nvme/host/fault_inject.c b/drivers/nvme/host/fault_inject.c index 02632266ac06..4cfd2c9222d4 100644 --- a/drivers/nvme/host/fault_inject.c +++ b/drivers/nvme/host/fault_inject.c @@ -1,8 +1,8 @@ +// SPDX-License-Identifier: GPL-2.0 /* * fault injection support for nvme. * * Copyright (c) 2018, Oracle and/or its affiliates - * */ #include <linux/moduleparam.h> diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c index 89accc76d71c..b29b12498a1a 100644 --- a/drivers/nvme/host/fc.c +++ b/drivers/nvme/host/fc.c @@ -1,18 +1,6 @@ +// SPDX-License-Identifier: GPL-2.0 /* * Copyright (c) 2016 Avago Technologies. All rights reserved. - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of version 2 of the GNU General Public License as - * published by the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful. - * ALL EXPRESS OR IMPLIED CONDITIONS, REPRESENTATIONS AND WARRANTIES, - * INCLUDING ANY IMPLIED WARRANTY OF MERCHANTABILITY, FITNESS FOR A - * PARTICULAR PURPOSE, OR NON-INFRINGEMENT, ARE DISCLAIMED, EXCEPT TO - * THE EXTENT THAT SUCH DISCLAIMERS ARE HELD TO BE LEGALLY INVALID. - * See the GNU General Public License for more details, a copy of which - * can be found in the file COPYING included with this package - * */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/module.h> diff --git a/drivers/nvme/host/lightnvm.c b/drivers/nvme/host/lightnvm.c index b759c25c89c8..949e29e1d782 100644 --- a/drivers/nvme/host/lightnvm.c +++ b/drivers/nvme/host/lightnvm.c @@ -1,23 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0 /* * nvme-lightnvm.c - LightNVM NVMe device * * Copyright (C) 2014-2015 IT University of Copenhagen * Initial release: Matias Bjorling <mb@lightnvm.io> - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License version - * 2 as published by the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, but - * WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; see the file COPYING. If not, write to - * the Free Software Foundation, 675 Mass Ave, Cambridge, MA 02139, - * USA. - * */ #include "nvme.h" diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c index b9fff3b8ed1b..2839bb70badf 100644 --- a/drivers/nvme/host/multipath.c +++ b/drivers/nvme/host/multipath.c @@ -1,14 +1,6 @@ +// SPDX-License-Identifier: GPL-2.0 /* * Copyright (c) 2017-2018 Christoph Hellwig. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. */ #include <linux/moduleparam.h> @@ -141,7 +133,10 @@ static struct nvme_ns *__nvme_find_path(struct nvme_ns_head *head, int node) test_bit(NVME_NS_ANA_PENDING, &ns->flags)) continue; - distance = node_distance(node, ns->ctrl->numa_node); + if (READ_ONCE(head->subsys->iopolicy) == NVME_IOPOLICY_NUMA) + distance = node_distance(node, ns->ctrl->numa_node); + else + distance = LOCAL_DISTANCE; switch (ns->ana_state) { case NVME_ANA_OPTIMIZED: @@ -168,6 +163,47 @@ static struct nvme_ns *__nvme_find_path(struct nvme_ns_head *head, int node) return found; } +static struct nvme_ns *nvme_next_ns(struct nvme_ns_head *head, + struct nvme_ns *ns) +{ + ns = list_next_or_null_rcu(&head->list, &ns->siblings, struct nvme_ns, + siblings); + if (ns) + return ns; + return list_first_or_null_rcu(&head->list, struct nvme_ns, siblings); +} + +static struct nvme_ns *nvme_round_robin_path(struct nvme_ns_head *head, + int node, struct nvme_ns *old) +{ + struct nvme_ns *ns, *found, *fallback = NULL; + + if (list_is_singular(&head->list)) + return old; + + for (ns = nvme_next_ns(head, old); + ns != old; + ns = nvme_next_ns(head, ns)) { + if (ns->ctrl->state != NVME_CTRL_LIVE || + test_bit(NVME_NS_ANA_PENDING, &ns->flags)) + continue; + + if (ns->ana_state == NVME_ANA_OPTIMIZED) { + found = ns; + goto out; + } + if (ns->ana_state == NVME_ANA_NONOPTIMIZED) + fallback = ns; + } + + if (!fallback) + return NULL; + found = fallback; +out: + rcu_assign_pointer(head->current_path[node], found); + return found; +} + static inline bool nvme_path_is_optimized(struct nvme_ns *ns) { return ns->ctrl->state == NVME_CTRL_LIVE && @@ -180,6 +216,8 @@ inline struct nvme_ns *nvme_find_path(struct nvme_ns_head *head) struct nvme_ns *ns; ns = srcu_dereference(head->current_path[node], &head->srcu); + if (READ_ONCE(head->subsys->iopolicy) == NVME_IOPOLICY_RR && ns) + ns = nvme_round_robin_path(head, node, ns); if (unlikely(!ns || !nvme_path_is_optimized(ns))) ns = __nvme_find_path(head, node); return ns; @@ -471,6 +509,44 @@ void nvme_mpath_stop(struct nvme_ctrl *ctrl) cancel_work_sync(&ctrl->ana_work); } +#define SUBSYS_ATTR_RW(_name, _mode, _show, _store) \ + struct device_attribute subsys_attr_##_name = \ + __ATTR(_name, _mode, _show, _store) + +static const char *nvme_iopolicy_names[] = { + [NVME_IOPOLICY_NUMA] = "numa", + [NVME_IOPOLICY_RR] = "round-robin", +}; + +static ssize_t nvme_subsys_iopolicy_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct nvme_subsystem *subsys = + container_of(dev, struct nvme_subsystem, dev); + + return sprintf(buf, "%s\n", + nvme_iopolicy_names[READ_ONCE(subsys->iopolicy)]); +} + +static ssize_t nvme_subsys_iopolicy_store(struct device *dev, + struct device_attribute *attr, const char *buf, size_t count) +{ + struct nvme_subsystem *subsys = + container_of(dev, struct nvme_subsystem, dev); + int i; + + for (i = 0; i < ARRAY_SIZE(nvme_iopolicy_names); i++) { + if (sysfs_streq(buf, nvme_iopolicy_names[i])) { + WRITE_ONCE(subsys->iopolicy, i); + return count; + } + } + + return -EINVAL; +} +SUBSYS_ATTR_RW(iopolicy, S_IRUGO | S_IWUSR, + nvme_subsys_iopolicy_show, nvme_subsys_iopolicy_store); + static ssize_t ana_grpid_show(struct device *dev, struct device_attribute *attr, char *buf) { diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h index c4a1bb41abf0..b91f1838bbd5 100644 --- a/drivers/nvme/host/nvme.h +++ b/drivers/nvme/host/nvme.h @@ -1,14 +1,6 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* * Copyright (c) 2011-2014, Intel Corporation. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. */ #ifndef _NVME_H @@ -252,6 +244,11 @@ struct nvme_ctrl { unsigned long discard_page_busy; }; +enum nvme_iopolicy { + NVME_IOPOLICY_NUMA, + NVME_IOPOLICY_RR, +}; + struct nvme_subsystem { int instance; struct device dev; @@ -271,6 +268,9 @@ struct nvme_subsystem { u8 cmic; u16 vendor_id; struct ida ns_ida; +#ifdef CONFIG_NVME_MULTIPATH + enum nvme_iopolicy iopolicy; +#endif }; /* @@ -364,7 +364,6 @@ struct nvme_ctrl_ops { void (*submit_async_event)(struct nvme_ctrl *ctrl); void (*delete_ctrl)(struct nvme_ctrl *ctrl); int (*get_address)(struct nvme_ctrl *ctrl, char *buf, int size); - void (*stop_ctrl)(struct nvme_ctrl *ctrl); }; #ifdef CONFIG_FAULT_INJECTION_DEBUG_FS @@ -459,7 +458,6 @@ void nvme_stop_keep_alive(struct nvme_ctrl *ctrl); int nvme_reset_ctrl(struct nvme_ctrl *ctrl); int nvme_reset_ctrl_sync(struct nvme_ctrl *ctrl); int nvme_delete_ctrl(struct nvme_ctrl *ctrl); -int nvme_delete_ctrl_sync(struct nvme_ctrl *ctrl); int nvme_get_log(struct nvme_ctrl *ctrl, u32 nsid, u8 log_page, u8 lsp, void *log, size_t size, u64 offset); @@ -492,6 +490,7 @@ static inline void nvme_mpath_check_last_path(struct nvme_ns *ns) extern struct device_attribute dev_attr_ana_grpid; extern struct device_attribute dev_attr_ana_state; +extern struct device_attribute subsys_attr_iopolicy; #else static inline bool nvme_ctrl_use_ana(struct nvme_ctrl *ctrl) diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index e905861186e3..92bad1c810ac 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -1,15 +1,7 @@ +// SPDX-License-Identifier: GPL-2.0 /* * NVM Express device driver * Copyright (c) 2011-2014, Intel Corporation. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. */ #include <linux/aer.h> @@ -157,6 +149,8 @@ static int queue_count_set(const char *val, const struct kernel_param *kp) int n = 0, ret; ret = kstrtoint(val, 10, &n); + if (ret) + return ret; if (n > num_possible_cpus()) n = num_possible_cpus(); diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c index 52abc3a6de12..11a5ecae78c8 100644 --- a/drivers/nvme/host/rdma.c +++ b/drivers/nvme/host/rdma.c @@ -1,15 +1,7 @@ +// SPDX-License-Identifier: GPL-2.0 /* * NVMe over Fabrics RDMA host code. * Copyright (c) 2015-2016 HGST, a Western Digital Company. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/module.h> @@ -942,14 +934,6 @@ static void nvme_rdma_teardown_io_queues(struct nvme_rdma_ctrl *ctrl, } } -static void nvme_rdma_stop_ctrl(struct nvme_ctrl *nctrl) -{ - struct nvme_rdma_ctrl *ctrl = to_rdma_ctrl(nctrl); - - cancel_work_sync(&ctrl->err_work); - cancel_delayed_work_sync(&ctrl->reconnect_work); -} - static void nvme_rdma_free_ctrl(struct nvme_ctrl *nctrl) { struct nvme_rdma_ctrl *ctrl = to_rdma_ctrl(nctrl); @@ -1158,7 +1142,7 @@ static void nvme_rdma_unmap_data(struct nvme_rdma_queue *queue, struct nvme_rdma_device *dev = queue->device; struct ib_device *ibdev = dev->dev; - if (!blk_rq_payload_bytes(rq)) + if (!blk_rq_nr_phys_segments(rq)) return; if (req->mr) { @@ -1281,7 +1265,7 @@ static int nvme_rdma_map_data(struct nvme_rdma_queue *queue, c->common.flags |= NVME_CMD_SGL_METABUF; - if (!blk_rq_payload_bytes(rq)) + if (!blk_rq_nr_phys_segments(rq)) return nvme_rdma_set_sg_null(c); req->sg_table.sgl = req->first_sgl; @@ -1854,6 +1838,9 @@ static const struct blk_mq_ops nvme_rdma_admin_mq_ops = { static void nvme_rdma_shutdown_ctrl(struct nvme_rdma_ctrl *ctrl, bool shutdown) { + cancel_work_sync(&ctrl->err_work); + cancel_delayed_work_sync(&ctrl->reconnect_work); + nvme_rdma_teardown_io_queues(ctrl, shutdown); if (shutdown) nvme_shutdown_ctrl(&ctrl->ctrl); @@ -1902,7 +1889,6 @@ static const struct nvme_ctrl_ops nvme_rdma_ctrl_ops = { .submit_async_event = nvme_rdma_submit_async_event, .delete_ctrl = nvme_rdma_delete_ctrl, .get_address = nvmf_get_address, - .stop_ctrl = nvme_rdma_stop_ctrl, }; /* diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c index 5f0a00425242..208ee518af65 100644 --- a/drivers/nvme/host/tcp.c +++ b/drivers/nvme/host/tcp.c @@ -1822,6 +1822,9 @@ static void nvme_tcp_error_recovery_work(struct work_struct *work) static void nvme_tcp_teardown_ctrl(struct nvme_ctrl *ctrl, bool shutdown) { + cancel_work_sync(&to_tcp_ctrl(ctrl)->err_work); + cancel_delayed_work_sync(&to_tcp_ctrl(ctrl)->connect_work); + nvme_tcp_teardown_io_queues(ctrl, shutdown); if (shutdown) nvme_shutdown_ctrl(ctrl); @@ -1859,12 +1862,6 @@ out_fail: nvme_tcp_reconnect_or_remove(ctrl); } -static void nvme_tcp_stop_ctrl(struct nvme_ctrl *ctrl) -{ - cancel_work_sync(&to_tcp_ctrl(ctrl)->err_work); - cancel_delayed_work_sync(&to_tcp_ctrl(ctrl)->connect_work); -} - static void nvme_tcp_free_ctrl(struct nvme_ctrl *nctrl) { struct nvme_tcp_ctrl *ctrl = to_tcp_ctrl(nctrl); @@ -2115,7 +2112,6 @@ static const struct nvme_ctrl_ops nvme_tcp_ctrl_ops = { .submit_async_event = nvme_tcp_submit_async_event, .delete_ctrl = nvme_tcp_delete_ctrl, .get_address = nvmf_get_address, - .stop_ctrl = nvme_tcp_stop_ctrl, }; static bool diff --git a/drivers/nvme/host/trace.c b/drivers/nvme/host/trace.c index 5566dda3237a..58456de78bb2 100644 --- a/drivers/nvme/host/trace.c +++ b/drivers/nvme/host/trace.c @@ -1,15 +1,7 @@ +// SPDX-License-Identifier: GPL-2.0 /* * NVM Express device driver tracepoints * Copyright (c) 2018 Johannes Thumshirn, SUSE Linux GmbH - * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. */ #include <asm/unaligned.h> diff --git a/drivers/nvme/host/trace.h b/drivers/nvme/host/trace.h index 3564120aa7b3..244d7c177e5a 100644 --- a/drivers/nvme/host/trace.h +++ b/drivers/nvme/host/trace.h @@ -1,15 +1,7 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* * NVM Express device driver tracepoints * Copyright (c) 2018 Johannes Thumshirn, SUSE Linux GmbH - * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. */ #undef TRACE_SYSTEM diff --git a/drivers/nvme/target/admin-cmd.c b/drivers/nvme/target/admin-cmd.c index 11baeb14c388..76250181fee0 100644 --- a/drivers/nvme/target/admin-cmd.c +++ b/drivers/nvme/target/admin-cmd.c @@ -1,15 +1,7 @@ +// SPDX-License-Identifier: GPL-2.0 /* * NVMe admin command implementation. * Copyright (c) 2015-2016 HGST, a Western Digital Company. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/module.h> diff --git a/drivers/nvme/target/configfs.c b/drivers/nvme/target/configfs.c index 618bbd006544..adb79545cdd7 100644 --- a/drivers/nvme/target/configfs.c +++ b/drivers/nvme/target/configfs.c @@ -1,15 +1,7 @@ +// SPDX-License-Identifier: GPL-2.0 /* * Configfs interface for the NVMe target. * Copyright (c) 2015-2016 HGST, a Western Digital Company. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/kernel.h> diff --git a/drivers/nvme/target/core.c b/drivers/nvme/target/core.c index 88d260f31835..d44ede147263 100644 --- a/drivers/nvme/target/core.c +++ b/drivers/nvme/target/core.c @@ -1,15 +1,7 @@ +// SPDX-License-Identifier: GPL-2.0 /* * Common code for the NVMe target. * Copyright (c) 2015-2016 HGST, a Western Digital Company. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/module.h> diff --git a/drivers/nvme/target/discovery.c b/drivers/nvme/target/discovery.c index d2cb71a0b419..c872b47a88f3 100644 --- a/drivers/nvme/target/discovery.c +++ b/drivers/nvme/target/discovery.c @@ -1,15 +1,7 @@ +// SPDX-License-Identifier: GPL-2.0 /* * Discovery service for the NVMe over Fabrics target. * Copyright (C) 2016 Intel Corporation. All rights reserved. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License version - * 2 as published by the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/slab.h> @@ -331,7 +323,7 @@ u16 nvmet_parse_discovery_cmd(struct nvmet_req *req) cmd->get_log_page.lid); req->error_loc = offsetof(struct nvme_get_log_page_command, lid); - return NVME_SC_INVALID_OPCODE | NVME_SC_DNR; + return NVME_SC_INVALID_OPCODE | NVME_SC_DNR; } case nvme_admin_identify: req->data_len = NVME_IDENTIFY_DATA_SIZE; diff --git a/drivers/nvme/target/fabrics-cmd.c b/drivers/nvme/target/fabrics-cmd.c index 6cf1fd9eb32e..3a76ebc3d155 100644 --- a/drivers/nvme/target/fabrics-cmd.c +++ b/drivers/nvme/target/fabrics-cmd.c @@ -1,15 +1,7 @@ +// SPDX-License-Identifier: GPL-2.0 /* * NVMe Fabrics command implementation. * Copyright (c) 2015-2016 HGST, a Western Digital Company. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/blkdev.h> diff --git a/drivers/nvme/target/fc.c b/drivers/nvme/target/fc.c index f98f5c5bea26..1e9654f04c60 100644 --- a/drivers/nvme/target/fc.c +++ b/drivers/nvme/target/fc.c @@ -1,18 +1,6 @@ +// SPDX-License-Identifier: GPL-2.0 /* * Copyright (c) 2016 Avago Technologies. All rights reserved. - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of version 2 of the GNU General Public License as - * published by the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful. - * ALL EXPRESS OR IMPLIED CONDITIONS, REPRESENTATIONS AND WARRANTIES, - * INCLUDING ANY IMPLIED WARRANTY OF MERCHANTABILITY, FITNESS FOR A - * PARTICULAR PURPOSE, OR NON-INFRINGEMENT, ARE DISCLAIMED, EXCEPT TO - * THE EXTENT THAT SUCH DISCLAIMERS ARE HELD TO BE LEGALLY INVALID. - * See the GNU General Public License for more details, a copy of which - * can be found in the file COPYING included with this package - * */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/module.h> diff --git a/drivers/nvme/target/fcloop.c b/drivers/nvme/target/fcloop.c index 291f4121f516..381b5a90c48b 100644 --- a/drivers/nvme/target/fcloop.c +++ b/drivers/nvme/target/fcloop.c @@ -1,17 +1,6 @@ +// SPDX-License-Identifier: GPL-2.0 /* * Copyright (c) 2016 Avago Technologies. All rights reserved. - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of version 2 of the GNU General Public License as - * published by the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful. - * ALL EXPRESS OR IMPLIED CONDITIONS, REPRESENTATIONS AND WARRANTIES, - * INCLUDING ANY IMPLIED WARRANTY OF MERCHANTABILITY, FITNESS FOR A - * PARTICULAR PURPOSE, OR NON-INFRINGEMENT, ARE DISCLAIMED, EXCEPT TO - * THE EXTENT THAT SUCH DISCLAIMERS ARE HELD TO BE LEGALLY INVALID. - * See the GNU General Public License for more details, a copy of which - * can be found in the file COPYING included with this package */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/module.h> diff --git a/drivers/nvme/target/io-cmd-bdev.c b/drivers/nvme/target/io-cmd-bdev.c index b6d030d3259f..71dfedbadc26 100644 --- a/drivers/nvme/target/io-cmd-bdev.c +++ b/drivers/nvme/target/io-cmd-bdev.c @@ -1,15 +1,7 @@ +// SPDX-License-Identifier: GPL-2.0 /* * NVMe I/O command implementation. * Copyright (c) 2015-2016 HGST, a Western Digital Company. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/blkdev.h> diff --git a/drivers/nvme/target/loop.c b/drivers/nvme/target/loop.c index 4aac1b4a8112..b9f623ab01f3 100644 --- a/drivers/nvme/target/loop.c +++ b/drivers/nvme/target/loop.c @@ -1,15 +1,7 @@ +// SPDX-License-Identifier: GPL-2.0 /* * NVMe over Fabrics loopback device. * Copyright (c) 2015-2016 HGST, a Western Digital Company. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/scatterlist.h> diff --git a/drivers/nvme/target/nvmet.h b/drivers/nvme/target/nvmet.h index 3e4719fdba85..51e49efd7849 100644 --- a/drivers/nvme/target/nvmet.h +++ b/drivers/nvme/target/nvmet.h @@ -1,14 +1,6 @@ +/* SPDX-License-Identifier: GPL-2.0 */ /* * Copyright (c) 2015-2016 HGST, a Western Digital Company. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. */ #ifndef _NVMET_H diff --git a/drivers/nvme/target/rdma.c b/drivers/nvme/target/rdma.c index a884e3a0e8af..ef893addf341 100644 --- a/drivers/nvme/target/rdma.c +++ b/drivers/nvme/target/rdma.c @@ -1,15 +1,7 @@ +// SPDX-License-Identifier: GPL-2.0 /* * NVMe over Fabrics RDMA target. * Copyright (c) 2015-2016 HGST, a Western Digital Company. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/atomic.h> diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c index a6828391d6b3..ca5fd3ae81f8 100644 --- a/drivers/scsi/scsi_lib.c +++ b/drivers/scsi/scsi_lib.c @@ -1900,7 +1900,7 @@ int scsi_mq_setup_tags(struct Scsi_Host *shost) shost->tag_set.queue_depth = shost->can_queue; shost->tag_set.cmd_size = cmd_size; shost->tag_set.numa_node = NUMA_NO_NODE; - shost->tag_set.flags = BLK_MQ_F_SHOULD_MERGE | BLK_MQ_F_SG_MERGE; + shost->tag_set.flags = BLK_MQ_F_SHOULD_MERGE; shost->tag_set.flags |= BLK_ALLOC_POLICY_TO_MQ_FLAG(shost->hostt->tag_alloc_policy); shost->tag_set.driver_data = shost; diff --git a/drivers/staging/erofs/data.c b/drivers/staging/erofs/data.c index 9c471f08ffd4..526e0dbea5b5 100644 --- a/drivers/staging/erofs/data.c +++ b/drivers/staging/erofs/data.c @@ -20,8 +20,9 @@ static inline void read_endio(struct bio *bio) int i; struct bio_vec *bvec; const blk_status_t err = bio->bi_status; + struct bvec_iter_all iter_all; - bio_for_each_segment_all(bvec, bio, i) { + bio_for_each_segment_all(bvec, bio, i, 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 02f34a83147d..8715bc50e09c 100644 --- a/drivers/staging/erofs/unzip_vle.c +++ b/drivers/staging/erofs/unzip_vle.c @@ -849,8 +849,9 @@ static inline void z_erofs_vle_read_endio(struct bio *bio) #ifdef EROFS_FS_HAS_MANAGED_CACHE struct address_space *mc = NULL; #endif + struct bvec_iter_all iter_all; - bio_for_each_segment_all(bvec, bio, i) { + bio_for_each_segment_all(bvec, bio, i, iter_all) { struct page *page = bvec->bv_page; bool cachemngd = false; |