diff options
author | Jens Axboe <axboe@kernel.dk> | 2018-10-01 08:58:57 -0600 |
---|---|---|
committer | Jens Axboe <axboe@kernel.dk> | 2018-10-01 08:58:57 -0600 |
commit | c0aac682fa6590cb660cb083dbc09f55e799d2d2 (patch) | |
tree | 28ded5b660c42661c29e1d4abdeb1a5e92a258ed /drivers/block | |
parent | 451bb7c3319739997d2e5a2527aef62d1f9200ac (diff) | |
parent | 17b57b1883c1285f3d0dc2266e8f79286a7bef38 (diff) |
Merge tag 'v4.19-rc6' into for-4.20/block
Merge -rc6 in, for two reasons:
1) Resolve a trivial conflict in the blk-mq-tag.c documentation
2) A few important regression fixes went into upstream directly, so
they aren't in the 4.20 branch.
Signed-off-by: Jens Axboe <axboe@kernel.dk>
* tag 'v4.19-rc6': (780 commits)
Linux 4.19-rc6
MAINTAINERS: fix reference to moved drivers/{misc => auxdisplay}/panel.c
cpufreq: qcom-kryo: Fix section annotations
perf/core: Add sanity check to deal with pinned event failure
xen/blkfront: correct purging of persistent grants
Revert "xen/blkfront: When purging persistent grants, keep them in the buffer"
selftests/powerpc: Fix Makefiles for headers_install change
blk-mq: I/O and timer unplugs are inverted in blktrace
dax: Fix deadlock in dax_lock_mapping_entry()
x86/boot: Fix kexec booting failure in the SEV bit detection code
bcache: add separate workqueue for journal_write to avoid deadlock
drm/amd/display: Fix Edid emulation for linux
drm/amd/display: Fix Vega10 lightup on S3 resume
drm/amdgpu: Fix vce work queue was not cancelled when suspend
Revert "drm/panel: Add device_link from panel device to DRM device"
xen/blkfront: When purging persistent grants, keep them in the buffer
clocksource/drivers/timer-atmel-pit: Properly handle error cases
block: fix deadline elevator drain for zoned block devices
ACPI / hotplug / PCI: Don't scan for non-hotplug bridges if slot is not bridge
drm/syncobj: Don't leak fences when WAIT_FOR_SUBMIT is set
...
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Diffstat (limited to 'drivers/block')
-rw-r--r-- | drivers/block/floppy.c | 3 | ||||
-rw-r--r-- | drivers/block/null_blk.h | 17 | ||||
-rw-r--r-- | drivers/block/null_blk_main.c | 45 | ||||
-rw-r--r-- | drivers/block/null_blk_zoned.c | 34 | ||||
-rw-r--r-- | drivers/block/rbd.c | 235 | ||||
-rw-r--r-- | drivers/block/xen-blkfront.c | 4 |
6 files changed, 245 insertions, 93 deletions
diff --git a/drivers/block/floppy.c b/drivers/block/floppy.c index 1bc99e9dfaee..c494a771c06f 100644 --- a/drivers/block/floppy.c +++ b/drivers/block/floppy.c @@ -3467,6 +3467,9 @@ static int fd_locked_ioctl(struct block_device *bdev, fmode_t mode, unsigned int (struct floppy_struct **)&outparam); if (ret) return ret; + memcpy(&inparam.g, outparam, + offsetof(struct floppy_struct, name)); + outparam = &inparam.g; break; case FDMSGON: UDP->flags |= FTD_MSG; diff --git a/drivers/block/null_blk.h b/drivers/block/null_blk.h index d81781f22dba..34e0030f0592 100644 --- a/drivers/block/null_blk.h +++ b/drivers/block/null_blk.h @@ -87,10 +87,10 @@ struct nullb { #ifdef CONFIG_BLK_DEV_ZONED int null_zone_init(struct nullb_device *dev); void null_zone_exit(struct nullb_device *dev); -blk_status_t null_zone_report(struct nullb *nullb, - struct nullb_cmd *cmd); -void null_zone_write(struct nullb_cmd *cmd); -void null_zone_reset(struct nullb_cmd *cmd); +blk_status_t null_zone_report(struct nullb *nullb, struct bio *bio); +void null_zone_write(struct nullb_cmd *cmd, sector_t sector, + unsigned int nr_sectors); +void null_zone_reset(struct nullb_cmd *cmd, sector_t sector); #else static inline int null_zone_init(struct nullb_device *dev) { @@ -98,11 +98,14 @@ static inline int null_zone_init(struct nullb_device *dev) } static inline void null_zone_exit(struct nullb_device *dev) {} static inline blk_status_t null_zone_report(struct nullb *nullb, - struct nullb_cmd *cmd) + struct bio *bio) { return BLK_STS_NOTSUPP; } -static inline void null_zone_write(struct nullb_cmd *cmd) {} -static inline void null_zone_reset(struct nullb_cmd *cmd) {} +static inline void null_zone_write(struct nullb_cmd *cmd, sector_t sector, + unsigned int nr_sectors) +{ +} +static inline void null_zone_reset(struct nullb_cmd *cmd, sector_t sector) {} #endif /* CONFIG_BLK_DEV_ZONED */ #endif /* __NULL_BLK_H */ diff --git a/drivers/block/null_blk_main.c b/drivers/block/null_blk_main.c index 6127e3ff7b4b..093b614d6524 100644 --- a/drivers/block/null_blk_main.c +++ b/drivers/block/null_blk_main.c @@ -1157,16 +1157,33 @@ static void null_restart_queue_async(struct nullb *nullb) } } +static bool cmd_report_zone(struct nullb *nullb, struct nullb_cmd *cmd) +{ + struct nullb_device *dev = cmd->nq->dev; + + if (dev->queue_mode == NULL_Q_BIO) { + if (bio_op(cmd->bio) == REQ_OP_ZONE_REPORT) { + cmd->error = null_zone_report(nullb, cmd->bio); + return true; + } + } else { + if (req_op(cmd->rq) == REQ_OP_ZONE_REPORT) { + cmd->error = null_zone_report(nullb, cmd->rq->bio); + return true; + } + } + + return false; +} + static blk_status_t null_handle_cmd(struct nullb_cmd *cmd) { struct nullb_device *dev = cmd->nq->dev; struct nullb *nullb = dev->nullb; int err = 0; - if (req_op(cmd->rq) == REQ_OP_ZONE_REPORT) { - cmd->error = null_zone_report(nullb, cmd); + if (cmd_report_zone(nullb, cmd)) goto out; - } if (test_bit(NULLB_DEV_FL_THROTTLED, &dev->flags)) { struct request *rq = cmd->rq; @@ -1234,10 +1251,24 @@ static blk_status_t null_handle_cmd(struct nullb_cmd *cmd) cmd->error = errno_to_blk_status(err); if (!cmd->error && dev->zoned) { - if (req_op(cmd->rq) == REQ_OP_WRITE) - null_zone_write(cmd); - else if (req_op(cmd->rq) == REQ_OP_ZONE_RESET) - null_zone_reset(cmd); + sector_t sector; + unsigned int nr_sectors; + int op; + + if (dev->queue_mode == NULL_Q_BIO) { + op = bio_op(cmd->bio); + sector = cmd->bio->bi_iter.bi_sector; + nr_sectors = cmd->bio->bi_iter.bi_size >> 9; + } else { + op = req_op(cmd->rq); + sector = blk_rq_pos(cmd->rq); + nr_sectors = blk_rq_sectors(cmd->rq); + } + + if (op == REQ_OP_WRITE) + null_zone_write(cmd, sector, nr_sectors); + else if (op == REQ_OP_ZONE_RESET) + null_zone_reset(cmd, sector); } out: /* Complete IO by inline, softirq or timer */ diff --git a/drivers/block/null_blk_zoned.c b/drivers/block/null_blk_zoned.c index a979ca00d7be..7c6b86d98700 100644 --- a/drivers/block/null_blk_zoned.c +++ b/drivers/block/null_blk_zoned.c @@ -48,8 +48,8 @@ void null_zone_exit(struct nullb_device *dev) kvfree(dev->zones); } -static void null_zone_fill_rq(struct nullb_device *dev, struct request *rq, - unsigned int zno, unsigned int nr_zones) +static void null_zone_fill_bio(struct nullb_device *dev, struct bio *bio, + unsigned int zno, unsigned int nr_zones) { struct blk_zone_report_hdr *hdr = NULL; struct bio_vec bvec; @@ -57,7 +57,7 @@ static void null_zone_fill_rq(struct nullb_device *dev, struct request *rq, void *addr; unsigned int zones_to_cpy; - bio_for_each_segment(bvec, rq->bio, iter) { + bio_for_each_segment(bvec, bio, iter) { addr = kmap_atomic(bvec.bv_page); zones_to_cpy = bvec.bv_len / sizeof(struct blk_zone); @@ -84,29 +84,24 @@ static void null_zone_fill_rq(struct nullb_device *dev, struct request *rq, } } -blk_status_t null_zone_report(struct nullb *nullb, - struct nullb_cmd *cmd) +blk_status_t null_zone_report(struct nullb *nullb, struct bio *bio) { struct nullb_device *dev = nullb->dev; - struct request *rq = cmd->rq; - unsigned int zno = null_zone_no(dev, blk_rq_pos(rq)); + unsigned int zno = null_zone_no(dev, bio->bi_iter.bi_sector); unsigned int nr_zones = dev->nr_zones - zno; - unsigned int max_zones = (blk_rq_bytes(rq) / - sizeof(struct blk_zone)) - 1; + unsigned int max_zones; + max_zones = (bio->bi_iter.bi_size / sizeof(struct blk_zone)) - 1; nr_zones = min_t(unsigned int, nr_zones, max_zones); - - null_zone_fill_rq(nullb->dev, rq, zno, nr_zones); + null_zone_fill_bio(nullb->dev, bio, zno, nr_zones); return BLK_STS_OK; } -void null_zone_write(struct nullb_cmd *cmd) +void null_zone_write(struct nullb_cmd *cmd, sector_t sector, + unsigned int nr_sectors) { struct nullb_device *dev = cmd->nq->dev; - struct request *rq = cmd->rq; - sector_t sector = blk_rq_pos(rq); - unsigned int rq_sectors = blk_rq_sectors(rq); unsigned int zno = null_zone_no(dev, sector); struct blk_zone *zone = &dev->zones[zno]; @@ -118,7 +113,7 @@ void null_zone_write(struct nullb_cmd *cmd) case BLK_ZONE_COND_EMPTY: case BLK_ZONE_COND_IMP_OPEN: /* Writes must be at the write pointer position */ - if (blk_rq_pos(rq) != zone->wp) { + if (sector != zone->wp) { cmd->error = BLK_STS_IOERR; break; } @@ -126,7 +121,7 @@ void null_zone_write(struct nullb_cmd *cmd) if (zone->cond == BLK_ZONE_COND_EMPTY) zone->cond = BLK_ZONE_COND_IMP_OPEN; - zone->wp += rq_sectors; + zone->wp += nr_sectors; if (zone->wp == zone->start + zone->len) zone->cond = BLK_ZONE_COND_FULL; break; @@ -137,11 +132,10 @@ void null_zone_write(struct nullb_cmd *cmd) } } -void null_zone_reset(struct nullb_cmd *cmd) +void null_zone_reset(struct nullb_cmd *cmd, sector_t sector) { struct nullb_device *dev = cmd->nq->dev; - struct request *rq = cmd->rq; - unsigned int zno = null_zone_no(dev, blk_rq_pos(rq)); + unsigned int zno = null_zone_no(dev, sector); struct blk_zone *zone = &dev->zones[zno]; zone->cond = BLK_ZONE_COND_EMPTY; diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c index 7915f3b03736..73ed5f3a862d 100644 --- a/drivers/block/rbd.c +++ b/drivers/block/rbd.c @@ -4207,11 +4207,13 @@ static ssize_t rbd_parent_show(struct device *dev, count += sprintf(&buf[count], "%s" "pool_id %llu\npool_name %s\n" + "pool_ns %s\n" "image_id %s\nimage_name %s\n" "snap_id %llu\nsnap_name %s\n" "overlap %llu\n", !count ? "" : "\n", /* first? */ spec->pool_id, spec->pool_name, + spec->pool_ns ?: "", spec->image_id, spec->image_name ?: "(unknown)", spec->snap_id, spec->snap_name, rbd_dev->parent_overlap); @@ -4584,47 +4586,177 @@ static int rbd_dev_v2_features(struct rbd_device *rbd_dev) &rbd_dev->header.features); } +struct parent_image_info { + u64 pool_id; + const char *pool_ns; + const char *image_id; + u64 snap_id; + + bool has_overlap; + u64 overlap; +}; + +/* + * The caller is responsible for @pii. + */ +static int decode_parent_image_spec(void **p, void *end, + struct parent_image_info *pii) +{ + u8 struct_v; + u32 struct_len; + int ret; + + ret = ceph_start_decoding(p, end, 1, "ParentImageSpec", + &struct_v, &struct_len); + if (ret) + return ret; + + ceph_decode_64_safe(p, end, pii->pool_id, e_inval); + pii->pool_ns = ceph_extract_encoded_string(p, end, NULL, GFP_KERNEL); + if (IS_ERR(pii->pool_ns)) { + ret = PTR_ERR(pii->pool_ns); + pii->pool_ns = NULL; + return ret; + } + pii->image_id = ceph_extract_encoded_string(p, end, NULL, GFP_KERNEL); + if (IS_ERR(pii->image_id)) { + ret = PTR_ERR(pii->image_id); + pii->image_id = NULL; + return ret; + } + ceph_decode_64_safe(p, end, pii->snap_id, e_inval); + return 0; + +e_inval: + return -EINVAL; +} + +static int __get_parent_info(struct rbd_device *rbd_dev, + struct page *req_page, + struct page *reply_page, + struct parent_image_info *pii) +{ + struct ceph_osd_client *osdc = &rbd_dev->rbd_client->client->osdc; + size_t reply_len = PAGE_SIZE; + void *p, *end; + int ret; + + ret = ceph_osdc_call(osdc, &rbd_dev->header_oid, &rbd_dev->header_oloc, + "rbd", "parent_get", CEPH_OSD_FLAG_READ, + req_page, sizeof(u64), reply_page, &reply_len); + if (ret) + return ret == -EOPNOTSUPP ? 1 : ret; + + p = page_address(reply_page); + end = p + reply_len; + ret = decode_parent_image_spec(&p, end, pii); + if (ret) + return ret; + + ret = ceph_osdc_call(osdc, &rbd_dev->header_oid, &rbd_dev->header_oloc, + "rbd", "parent_overlap_get", CEPH_OSD_FLAG_READ, + req_page, sizeof(u64), reply_page, &reply_len); + if (ret) + return ret; + + p = page_address(reply_page); + end = p + reply_len; + ceph_decode_8_safe(&p, end, pii->has_overlap, e_inval); + if (pii->has_overlap) + ceph_decode_64_safe(&p, end, pii->overlap, e_inval); + + return 0; + +e_inval: + return -EINVAL; +} + +/* + * The caller is responsible for @pii. + */ +static int __get_parent_info_legacy(struct rbd_device *rbd_dev, + struct page *req_page, + struct page *reply_page, + struct parent_image_info *pii) +{ + struct ceph_osd_client *osdc = &rbd_dev->rbd_client->client->osdc; + size_t reply_len = PAGE_SIZE; + void *p, *end; + int ret; + + ret = ceph_osdc_call(osdc, &rbd_dev->header_oid, &rbd_dev->header_oloc, + "rbd", "get_parent", CEPH_OSD_FLAG_READ, + req_page, sizeof(u64), reply_page, &reply_len); + if (ret) + return ret; + + p = page_address(reply_page); + end = p + reply_len; + ceph_decode_64_safe(&p, end, pii->pool_id, e_inval); + pii->image_id = ceph_extract_encoded_string(&p, end, NULL, GFP_KERNEL); + if (IS_ERR(pii->image_id)) { + ret = PTR_ERR(pii->image_id); + pii->image_id = NULL; + return ret; + } + ceph_decode_64_safe(&p, end, pii->snap_id, e_inval); + pii->has_overlap = true; + ceph_decode_64_safe(&p, end, pii->overlap, e_inval); + + return 0; + +e_inval: + return -EINVAL; +} + +static int get_parent_info(struct rbd_device *rbd_dev, + struct parent_image_info *pii) +{ + struct page *req_page, *reply_page; + void *p; + int ret; + + req_page = alloc_page(GFP_KERNEL); + if (!req_page) + return -ENOMEM; + + reply_page = alloc_page(GFP_KERNEL); + if (!reply_page) { + __free_page(req_page); + return -ENOMEM; + } + + p = page_address(req_page); + ceph_encode_64(&p, rbd_dev->spec->snap_id); + ret = __get_parent_info(rbd_dev, req_page, reply_page, pii); + if (ret > 0) + ret = __get_parent_info_legacy(rbd_dev, req_page, reply_page, + pii); + + __free_page(req_page); + __free_page(reply_page); + return ret; +} + static int rbd_dev_v2_parent_info(struct rbd_device *rbd_dev) { struct rbd_spec *parent_spec; - size_t size; - void *reply_buf = NULL; - __le64 snapid; - void *p; - void *end; - u64 pool_id; - char *image_id; - u64 snap_id; - u64 overlap; + struct parent_image_info pii = { 0 }; int ret; parent_spec = rbd_spec_alloc(); if (!parent_spec) return -ENOMEM; - size = sizeof (__le64) + /* pool_id */ - sizeof (__le32) + RBD_IMAGE_ID_LEN_MAX + /* image_id */ - sizeof (__le64) + /* snap_id */ - sizeof (__le64); /* overlap */ - reply_buf = kmalloc(size, GFP_KERNEL); - if (!reply_buf) { - ret = -ENOMEM; + ret = get_parent_info(rbd_dev, &pii); + if (ret) goto out_err; - } - snapid = cpu_to_le64(rbd_dev->spec->snap_id); - ret = rbd_obj_method_sync(rbd_dev, &rbd_dev->header_oid, - &rbd_dev->header_oloc, "get_parent", - &snapid, sizeof(snapid), reply_buf, size); - dout("%s: rbd_obj_method_sync returned %d\n", __func__, ret); - if (ret < 0) - goto out_err; + dout("%s pool_id %llu pool_ns %s image_id %s snap_id %llu has_overlap %d overlap %llu\n", + __func__, pii.pool_id, pii.pool_ns, pii.image_id, pii.snap_id, + pii.has_overlap, pii.overlap); - p = reply_buf; - end = reply_buf + ret; - ret = -ERANGE; - ceph_decode_64_safe(&p, end, pool_id, out_err); - if (pool_id == CEPH_NOPOOL) { + if (pii.pool_id == CEPH_NOPOOL || !pii.has_overlap) { /* * Either the parent never existed, or we have * record of it but the image got flattened so it no @@ -4633,6 +4765,10 @@ static int rbd_dev_v2_parent_info(struct rbd_device *rbd_dev) * overlap to 0. The effect of this is that all new * requests will be treated as if the image had no * parent. + * + * If !pii.has_overlap, the parent image spec is not + * applicable. It's there to avoid duplication in each + * snapshot record. */ if (rbd_dev->parent_overlap) { rbd_dev->parent_overlap = 0; @@ -4647,51 +4783,36 @@ static int rbd_dev_v2_parent_info(struct rbd_device *rbd_dev) /* The ceph file layout needs to fit pool id in 32 bits */ ret = -EIO; - if (pool_id > (u64)U32_MAX) { + if (pii.pool_id > (u64)U32_MAX) { rbd_warn(NULL, "parent pool id too large (%llu > %u)", - (unsigned long long)pool_id, U32_MAX); + (unsigned long long)pii.pool_id, U32_MAX); goto out_err; } - image_id = ceph_extract_encoded_string(&p, end, NULL, GFP_KERNEL); - if (IS_ERR(image_id)) { - ret = PTR_ERR(image_id); - goto out_err; - } - ceph_decode_64_safe(&p, end, snap_id, out_err); - ceph_decode_64_safe(&p, end, overlap, out_err); - /* * The parent won't change (except when the clone is * flattened, already handled that). So we only need to * record the parent spec we have not already done so. */ if (!rbd_dev->parent_spec) { - parent_spec->pool_id = pool_id; - parent_spec->image_id = image_id; - parent_spec->snap_id = snap_id; - - /* TODO: support cloning across namespaces */ - if (rbd_dev->spec->pool_ns) { - parent_spec->pool_ns = kstrdup(rbd_dev->spec->pool_ns, - GFP_KERNEL); - if (!parent_spec->pool_ns) { - ret = -ENOMEM; - goto out_err; - } + parent_spec->pool_id = pii.pool_id; + if (pii.pool_ns && *pii.pool_ns) { + parent_spec->pool_ns = pii.pool_ns; + pii.pool_ns = NULL; } + parent_spec->image_id = pii.image_id; + pii.image_id = NULL; + parent_spec->snap_id = pii.snap_id; rbd_dev->parent_spec = parent_spec; parent_spec = NULL; /* rbd_dev now owns this */ - } else { - kfree(image_id); } /* * We always update the parent overlap. If it's zero we issue * a warning, as we will proceed as if there was no parent. */ - if (!overlap) { + if (!pii.overlap) { if (parent_spec) { /* refresh, careful to warn just once */ if (rbd_dev->parent_overlap) @@ -4702,14 +4823,14 @@ static int rbd_dev_v2_parent_info(struct rbd_device *rbd_dev) rbd_warn(rbd_dev, "clone is standalone (overlap 0)"); } } - rbd_dev->parent_overlap = overlap; + rbd_dev->parent_overlap = pii.overlap; out: ret = 0; out_err: - kfree(reply_buf); + kfree(pii.pool_ns); + kfree(pii.image_id); rbd_spec_put(parent_spec); - return ret; } diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c index e5e40272d233..9eea83ae01c6 100644 --- a/drivers/block/xen-blkfront.c +++ b/drivers/block/xen-blkfront.c @@ -2670,8 +2670,8 @@ static void purge_persistent_grants(struct blkfront_info *info) list_del(&gnt_list_entry->node); gnttab_end_foreign_access(gnt_list_entry->gref, 0, 0UL); rinfo->persistent_gnts_c--; - __free_page(gnt_list_entry->page); - kfree(gnt_list_entry); + gnt_list_entry->gref = GRANT_INVALID_REF; + list_add_tail(&gnt_list_entry->node, &rinfo->grants); } spin_unlock_irqrestore(&rinfo->ring_lock, flags); |