diff options
Diffstat (limited to 'drivers/block')
-rw-r--r-- | drivers/block/Kconfig | 2 | ||||
-rw-r--r-- | drivers/block/brd.c | 6 | ||||
-rw-r--r-- | drivers/block/loop.c | 42 | ||||
-rw-r--r-- | drivers/block/loop.h | 1 | ||||
-rw-r--r-- | drivers/block/nbd.c | 18 | ||||
-rw-r--r-- | drivers/block/null_blk.c | 2 | ||||
-rw-r--r-- | drivers/block/sunvdc.c | 61 | ||||
-rw-r--r-- | drivers/block/virtio_blk.c | 23 | ||||
-rw-r--r-- | drivers/block/xen-blkback/xenbus.c | 10 | ||||
-rw-r--r-- | drivers/block/xen-blkfront.c | 31 | ||||
-rw-r--r-- | drivers/block/zram/Kconfig | 12 | ||||
-rw-r--r-- | drivers/block/zram/zram_drv.c | 544 | ||||
-rw-r--r-- | drivers/block/zram/zram_drv.h | 11 |
13 files changed, 607 insertions, 156 deletions
diff --git a/drivers/block/Kconfig b/drivers/block/Kconfig index 8ddc98279c8f..80aaf3420e12 100644 --- a/drivers/block/Kconfig +++ b/drivers/block/Kconfig @@ -470,7 +470,7 @@ config VIRTIO_BLK depends on VIRTIO ---help--- This is the virtual block driver for virtio. It can be used with - lguest or QEMU based VMMs (like KVM or Xen). Say Y or M. + QEMU based VMMs (like KVM or Xen). Say Y or M. config VIRTIO_BLK_SCSI bool "SCSI passthrough request for the Virtio block driver" diff --git a/drivers/block/brd.c b/drivers/block/brd.c index 104b71c0490d..5d9ed0616413 100644 --- a/drivers/block/brd.c +++ b/drivers/block/brd.c @@ -326,7 +326,11 @@ static int brd_rw_page(struct block_device *bdev, sector_t sector, struct page *page, bool is_write) { struct brd_device *brd = bdev->bd_disk->private_data; - int err = brd_do_bvec(brd, page, PAGE_SIZE, 0, is_write, sector); + int err; + + if (PageTransHuge(page)) + return -ENOTSUPP; + err = brd_do_bvec(brd, page, PAGE_SIZE, 0, is_write, sector); page_endio(page, is_write, err); return err; } diff --git a/drivers/block/loop.c b/drivers/block/loop.c index ef8334949b42..f321b96405f5 100644 --- a/drivers/block/loop.c +++ b/drivers/block/loop.c @@ -221,8 +221,7 @@ static void __loop_update_dio(struct loop_device *lo, bool dio) } static int -figure_loop_size(struct loop_device *lo, loff_t offset, loff_t sizelimit, - loff_t logical_blocksize) +figure_loop_size(struct loop_device *lo, loff_t offset, loff_t sizelimit) { loff_t size = get_size(offset, sizelimit, lo->lo_backing_file); sector_t x = (sector_t)size; @@ -234,12 +233,6 @@ figure_loop_size(struct loop_device *lo, loff_t offset, loff_t sizelimit, lo->lo_offset = offset; if (lo->lo_sizelimit != sizelimit) lo->lo_sizelimit = sizelimit; - if (lo->lo_flags & LO_FLAGS_BLOCKSIZE) { - lo->lo_logical_blocksize = logical_blocksize; - blk_queue_physical_block_size(lo->lo_queue, lo->lo_blocksize); - blk_queue_logical_block_size(lo->lo_queue, - lo->lo_logical_blocksize); - } set_capacity(lo->lo_disk, x); bd_set_size(bdev, (loff_t)get_capacity(bdev->bd_disk) << 9); /* let user-space know about the new size */ @@ -820,7 +813,6 @@ static void loop_config_discard(struct loop_device *lo) struct file *file = lo->lo_backing_file; struct inode *inode = file->f_mapping->host; struct request_queue *q = lo->lo_queue; - int lo_bits = 9; /* * We use punch hole to reclaim the free space used by the @@ -840,11 +832,9 @@ static void loop_config_discard(struct loop_device *lo) q->limits.discard_granularity = inode->i_sb->s_blocksize; q->limits.discard_alignment = 0; - if (lo->lo_flags & LO_FLAGS_BLOCKSIZE) - lo_bits = blksize_bits(lo->lo_logical_blocksize); - blk_queue_max_discard_sectors(q, UINT_MAX >> lo_bits); - blk_queue_max_write_zeroes_sectors(q, UINT_MAX >> lo_bits); + blk_queue_max_discard_sectors(q, UINT_MAX >> 9); + blk_queue_max_write_zeroes_sectors(q, UINT_MAX >> 9); queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, q); } @@ -938,7 +928,6 @@ static int loop_set_fd(struct loop_device *lo, fmode_t mode, lo->use_dio = false; lo->lo_blocksize = lo_blocksize; - lo->lo_logical_blocksize = 512; lo->lo_device = bdev; lo->lo_flags = lo_flags; lo->lo_backing_file = file; @@ -1104,7 +1093,6 @@ loop_set_status(struct loop_device *lo, const struct loop_info64 *info) int err; struct loop_func_table *xfer; kuid_t uid = current_uid(); - int lo_flags = lo->lo_flags; if (lo->lo_encrypt_key_size && !uid_eq(lo->lo_key_owner, uid) && @@ -1137,26 +1125,9 @@ loop_set_status(struct loop_device *lo, const struct loop_info64 *info) if (err) goto exit; - if (info->lo_flags & LO_FLAGS_BLOCKSIZE) { - if (!(lo->lo_flags & LO_FLAGS_BLOCKSIZE)) - lo->lo_logical_blocksize = 512; - lo->lo_flags |= LO_FLAGS_BLOCKSIZE; - if (LO_INFO_BLOCKSIZE(info) != 512 && - LO_INFO_BLOCKSIZE(info) != 1024 && - LO_INFO_BLOCKSIZE(info) != 2048 && - LO_INFO_BLOCKSIZE(info) != 4096) - return -EINVAL; - if (LO_INFO_BLOCKSIZE(info) > lo->lo_blocksize) - return -EINVAL; - } - if (lo->lo_offset != info->lo_offset || - lo->lo_sizelimit != info->lo_sizelimit || - lo->lo_flags != lo_flags || - ((lo->lo_flags & LO_FLAGS_BLOCKSIZE) && - lo->lo_logical_blocksize != LO_INFO_BLOCKSIZE(info))) { - if (figure_loop_size(lo, info->lo_offset, info->lo_sizelimit, - LO_INFO_BLOCKSIZE(info))) { + lo->lo_sizelimit != info->lo_sizelimit) { + if (figure_loop_size(lo, info->lo_offset, info->lo_sizelimit)) { err = -EFBIG; goto exit; } @@ -1348,8 +1319,7 @@ static int loop_set_capacity(struct loop_device *lo) if (unlikely(lo->lo_state != Lo_bound)) return -ENXIO; - return figure_loop_size(lo, lo->lo_offset, lo->lo_sizelimit, - lo->lo_logical_blocksize); + return figure_loop_size(lo, lo->lo_offset, lo->lo_sizelimit); } static int loop_set_dio(struct loop_device *lo, unsigned long arg) diff --git a/drivers/block/loop.h b/drivers/block/loop.h index 2c096b9a17b8..fecd3f97ef8c 100644 --- a/drivers/block/loop.h +++ b/drivers/block/loop.h @@ -49,7 +49,6 @@ struct loop_device { struct file * lo_backing_file; struct block_device *lo_device; unsigned lo_blocksize; - unsigned lo_logical_blocksize; void *key_data; gfp_t old_gfp_mask; diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c index 87a0a29f6e7e..5bdf923294a5 100644 --- a/drivers/block/nbd.c +++ b/drivers/block/nbd.c @@ -908,7 +908,8 @@ static int nbd_reconnect_socket(struct nbd_device *nbd, unsigned long arg) continue; } sk_set_memalloc(sock->sk); - sock->sk->sk_sndtimeo = nbd->tag_set.timeout; + if (nbd->tag_set.timeout) + sock->sk->sk_sndtimeo = nbd->tag_set.timeout; atomic_inc(&config->recv_threads); refcount_inc(&nbd->config_refs); old = nsock->sock; @@ -922,6 +923,8 @@ static int nbd_reconnect_socket(struct nbd_device *nbd, unsigned long arg) mutex_unlock(&nsock->tx_lock); sockfd_put(old); + clear_bit(NBD_DISCONNECTED, &config->runtime_flags); + /* We take the tx_mutex in an error path in the recv_work, so we * need to queue_work outside of the tx_mutex. */ @@ -978,11 +981,15 @@ static void send_disconnects(struct nbd_device *nbd) int i, ret; for (i = 0; i < config->num_connections; i++) { + struct nbd_sock *nsock = config->socks[i]; + iov_iter_kvec(&from, WRITE | ITER_KVEC, &iov, 1, sizeof(request)); + mutex_lock(&nsock->tx_lock); ret = sock_xmit(nbd, i, 1, &from, 0, NULL); if (ret <= 0) dev_err(disk_to_dev(nbd->disk), "Send disconnect failed %d\n", ret); + mutex_unlock(&nsock->tx_lock); } } @@ -991,9 +998,8 @@ static int nbd_disconnect(struct nbd_device *nbd) struct nbd_config *config = nbd->config; dev_info(disk_to_dev(nbd->disk), "NBD_DISCONNECT\n"); - if (!test_and_set_bit(NBD_DISCONNECT_REQUESTED, - &config->runtime_flags)) - send_disconnects(nbd); + set_bit(NBD_DISCONNECT_REQUESTED, &config->runtime_flags); + send_disconnects(nbd); return 0; } @@ -1074,7 +1080,9 @@ static int nbd_start_device(struct nbd_device *nbd) return -ENOMEM; } sk_set_memalloc(config->socks[i]->sock->sk); - config->socks[i]->sock->sk->sk_sndtimeo = nbd->tag_set.timeout; + if (nbd->tag_set.timeout) + config->socks[i]->sock->sk->sk_sndtimeo = + nbd->tag_set.timeout; atomic_inc(&config->recv_threads); refcount_inc(&nbd->config_refs); INIT_WORK(&args->work, recv_work); diff --git a/drivers/block/null_blk.c b/drivers/block/null_blk.c index 85c24cace973..81142ce781da 100644 --- a/drivers/block/null_blk.c +++ b/drivers/block/null_blk.c @@ -13,7 +13,7 @@ struct nullb_cmd { struct list_head list; struct llist_node ll_list; - struct call_single_data csd; + call_single_data_t csd; struct request *rq; struct bio *bio; unsigned int tag; diff --git a/drivers/block/sunvdc.c b/drivers/block/sunvdc.c index 6b16ead1da58..ad9749463d4f 100644 --- a/drivers/block/sunvdc.c +++ b/drivers/block/sunvdc.c @@ -875,6 +875,56 @@ static void print_version(void) printk(KERN_INFO "%s", version); } +struct vdc_check_port_data { + int dev_no; + char *type; +}; + +static int vdc_device_probed(struct device *dev, void *arg) +{ + struct vio_dev *vdev = to_vio_dev(dev); + struct vdc_check_port_data *port_data; + + port_data = (struct vdc_check_port_data *)arg; + + if ((vdev->dev_no == port_data->dev_no) && + (!(strcmp((char *)&vdev->type, port_data->type))) && + dev_get_drvdata(dev)) { + /* This device has already been configured + * by vdc_port_probe() + */ + return 1; + } else { + return 0; + } +} + +/* Determine whether the VIO device is part of an mpgroup + * by locating all the virtual-device-port nodes associated + * with the parent virtual-device node for the VIO device + * and checking whether any of these nodes are vdc-ports + * which have already been configured. + * + * Returns true if this device is part of an mpgroup and has + * already been probed. + */ +static bool vdc_port_mpgroup_check(struct vio_dev *vdev) +{ + struct vdc_check_port_data port_data; + struct device *dev; + + port_data.dev_no = vdev->dev_no; + port_data.type = (char *)&vdev->type; + + dev = device_find_child(vdev->dev.parent, &port_data, + vdc_device_probed); + + if (dev) + return true; + + return false; +} + static int vdc_port_probe(struct vio_dev *vdev, const struct vio_device_id *id) { struct mdesc_handle *hp; @@ -893,6 +943,14 @@ static int vdc_port_probe(struct vio_dev *vdev, const struct vio_device_id *id) goto err_out_release_mdesc; } + /* Check if this device is part of an mpgroup */ + if (vdc_port_mpgroup_check(vdev)) { + printk(KERN_WARNING + "VIO: Ignoring extra vdisk port %s", + dev_name(&vdev->dev)); + goto err_out_release_mdesc; + } + port = kzalloc(sizeof(*port), GFP_KERNEL); err = -ENOMEM; if (!port) { @@ -943,6 +1001,9 @@ static int vdc_port_probe(struct vio_dev *vdev, const struct vio_device_id *id) if (err) goto err_out_free_tx_ring; + /* Note that the device driver_data is used to determine + * whether the port has been probed. + */ dev_set_drvdata(&vdev->dev, port); mdesc_release(hp); diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c index 4e02aa5fdac0..d3d5523862c2 100644 --- a/drivers/block/virtio_blk.c +++ b/drivers/block/virtio_blk.c @@ -381,6 +381,7 @@ static void virtblk_config_changed_work(struct work_struct *work) struct request_queue *q = vblk->disk->queue; char cap_str_2[10], cap_str_10[10]; char *envp[] = { "RESIZE=1", NULL }; + unsigned long long nblocks; u64 capacity; /* Host must always specify the capacity. */ @@ -393,16 +394,19 @@ static void virtblk_config_changed_work(struct work_struct *work) capacity = (sector_t)-1; } - string_get_size(capacity, queue_logical_block_size(q), + nblocks = DIV_ROUND_UP_ULL(capacity, queue_logical_block_size(q) >> 9); + + string_get_size(nblocks, queue_logical_block_size(q), STRING_UNITS_2, cap_str_2, sizeof(cap_str_2)); - string_get_size(capacity, queue_logical_block_size(q), + string_get_size(nblocks, queue_logical_block_size(q), STRING_UNITS_10, cap_str_10, sizeof(cap_str_10)); dev_notice(&vdev->dev, - "new size: %llu %d-byte logical blocks (%s/%s)\n", - (unsigned long long)capacity, - queue_logical_block_size(q), - cap_str_10, cap_str_2); + "new size: %llu %d-byte logical blocks (%s/%s)\n", + nblocks, + queue_logical_block_size(q), + cap_str_10, + cap_str_2); set_capacity(vblk->disk, capacity); revalidate_disk(vblk->disk); @@ -541,12 +545,9 @@ virtblk_cache_type_store(struct device *dev, struct device_attribute *attr, int i; BUG_ON(!virtio_has_feature(vblk->vdev, VIRTIO_BLK_F_CONFIG_WCE)); - for (i = ARRAY_SIZE(virtblk_cache_types); --i >= 0; ) - if (sysfs_streq(buf, virtblk_cache_types[i])) - break; - + i = sysfs_match_string(virtblk_cache_types, buf); if (i < 0) - return -EINVAL; + return i; virtio_cwrite8(vdev, offsetof(struct virtio_blk_config, wce), i); virtblk_update_cache_mode(vdev); diff --git a/drivers/block/xen-blkback/xenbus.c b/drivers/block/xen-blkback/xenbus.c index 792da683e70d..2adb8599be93 100644 --- a/drivers/block/xen-blkback/xenbus.c +++ b/drivers/block/xen-blkback/xenbus.c @@ -244,6 +244,7 @@ static int xen_blkif_disconnect(struct xen_blkif *blkif) { struct pending_req *req, *n; unsigned int j, r; + bool busy = false; for (r = 0; r < blkif->nr_rings; r++) { struct xen_blkif_ring *ring = &blkif->rings[r]; @@ -261,8 +262,10 @@ static int xen_blkif_disconnect(struct xen_blkif *blkif) * don't have any discard_io or other_io requests. So, checking * for inflight IO is enough. */ - if (atomic_read(&ring->inflight) > 0) - return -EBUSY; + if (atomic_read(&ring->inflight) > 0) { + busy = true; + continue; + } if (ring->irq) { unbind_from_irqhandler(ring->irq, ring); @@ -300,6 +303,9 @@ static int xen_blkif_disconnect(struct xen_blkif *blkif) WARN_ON(i != (XEN_BLKIF_REQS_PER_PAGE * blkif->nr_ring_pages)); ring->active = false; } + if (busy) + return -EBUSY; + blkif->nr_ring_pages = 0; /* * blkif->rings was allocated in connect_ring, so we should free it in diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c index c852ed3c01d5..2468c28d4771 100644 --- a/drivers/block/xen-blkfront.c +++ b/drivers/block/xen-blkfront.c @@ -111,7 +111,7 @@ struct blk_shadow { }; struct blkif_req { - int error; + blk_status_t error; }; static inline struct blkif_req *blkif_req(struct request *rq) @@ -708,6 +708,7 @@ static int blkif_queue_rw_req(struct request *req, struct blkfront_ring_info *ri * existing persistent grants, or if we have to get new grants, * as there are not sufficiently many free. */ + bool new_persistent_gnts = false; struct scatterlist *sg; int num_sg, max_grefs, num_grant; @@ -719,19 +720,21 @@ static int blkif_queue_rw_req(struct request *req, struct blkfront_ring_info *ri */ max_grefs += INDIRECT_GREFS(max_grefs); - /* - * We have to reserve 'max_grefs' grants because persistent - * grants are shared by all rings. - */ - if (max_grefs > 0) - if (gnttab_alloc_grant_references(max_grefs, &setup.gref_head) < 0) { + /* Check if we have enough persistent grants to allocate a requests */ + if (rinfo->persistent_gnts_c < max_grefs) { + new_persistent_gnts = true; + + if (gnttab_alloc_grant_references( + max_grefs - rinfo->persistent_gnts_c, + &setup.gref_head) < 0) { gnttab_request_free_callback( &rinfo->callback, blkif_restart_queue_callback, rinfo, - max_grefs); + max_grefs - rinfo->persistent_gnts_c); return 1; } + } /* Fill out a communications ring structure. */ id = blkif_ring_get_request(rinfo, req, &ring_req); @@ -832,7 +835,7 @@ static int blkif_queue_rw_req(struct request *req, struct blkfront_ring_info *ri if (unlikely(require_extra_req)) rinfo->shadow[extra_id].req = *extra_ring_req; - if (max_grefs > 0) + if (new_persistent_gnts) gnttab_free_grant_references(setup.gref_head); return 0; @@ -906,8 +909,8 @@ out_err: return BLK_STS_IOERR; out_busy: - spin_unlock_irqrestore(&rinfo->ring_lock, flags); blk_mq_stop_hw_queue(hctx); + spin_unlock_irqrestore(&rinfo->ring_lock, flags); return BLK_STS_RESOURCE; } @@ -1616,7 +1619,7 @@ static irqreturn_t blkif_interrupt(int irq, void *dev_id) if (unlikely(bret->status == BLKIF_RSP_EOPNOTSUPP)) { printk(KERN_WARNING "blkfront: %s: %s op failed\n", info->gd->disk_name, op_name(bret->operation)); - blkif_req(req)->error = -EOPNOTSUPP; + blkif_req(req)->error = BLK_STS_NOTSUPP; } if (unlikely(bret->status == BLKIF_RSP_ERROR && rinfo->shadow[id].req.u.rw.nr_segments == 0)) { @@ -2072,9 +2075,9 @@ static int blkfront_resume(struct xenbus_device *dev) /* * Get the bios in the request so we can re-queue them. */ - if (req_op(shadow[i].request) == REQ_OP_FLUSH || - req_op(shadow[i].request) == REQ_OP_DISCARD || - req_op(shadow[i].request) == REQ_OP_SECURE_ERASE || + if (req_op(shadow[j].request) == REQ_OP_FLUSH || + req_op(shadow[j].request) == REQ_OP_DISCARD || + req_op(shadow[j].request) == REQ_OP_SECURE_ERASE || shadow[j].request->cmd_flags & REQ_FUA) { /* * Flush operations don't contain bios, so diff --git a/drivers/block/zram/Kconfig b/drivers/block/zram/Kconfig index b8ecba6dcd3b..7cd4a8ec3c8f 100644 --- a/drivers/block/zram/Kconfig +++ b/drivers/block/zram/Kconfig @@ -13,3 +13,15 @@ config ZRAM disks and maybe many more. See zram.txt for more information. + +config ZRAM_WRITEBACK + bool "Write back incompressible page to backing device" + depends on ZRAM + default n + help + With incompressible page, there is no memory saving to keep it + in memory. Instead, write it out to backing device. + For this feature, admin should set up backing device via + /sys/block/zramX/backing_dev. + + See zram.txt for more infomration. diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c index 856d5dc02451..4a0438c4ef2a 100644 --- a/drivers/block/zram/zram_drv.c +++ b/drivers/block/zram/zram_drv.c @@ -270,6 +270,349 @@ static ssize_t mem_used_max_store(struct device *dev, return len; } +#ifdef CONFIG_ZRAM_WRITEBACK +static bool zram_wb_enabled(struct zram *zram) +{ + return zram->backing_dev; +} + +static void reset_bdev(struct zram *zram) +{ + struct block_device *bdev; + + if (!zram_wb_enabled(zram)) + return; + + bdev = zram->bdev; + if (zram->old_block_size) + set_blocksize(bdev, zram->old_block_size); + blkdev_put(bdev, FMODE_READ|FMODE_WRITE|FMODE_EXCL); + /* hope filp_close flush all of IO */ + filp_close(zram->backing_dev, NULL); + zram->backing_dev = NULL; + zram->old_block_size = 0; + zram->bdev = NULL; + + kvfree(zram->bitmap); + zram->bitmap = NULL; +} + +static ssize_t backing_dev_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct zram *zram = dev_to_zram(dev); + struct file *file = zram->backing_dev; + char *p; + ssize_t ret; + + down_read(&zram->init_lock); + if (!zram_wb_enabled(zram)) { + memcpy(buf, "none\n", 5); + up_read(&zram->init_lock); + return 5; + } + + p = file_path(file, buf, PAGE_SIZE - 1); + if (IS_ERR(p)) { + ret = PTR_ERR(p); + goto out; + } + + ret = strlen(p); + memmove(buf, p, ret); + buf[ret++] = '\n'; +out: + up_read(&zram->init_lock); + return ret; +} + +static ssize_t backing_dev_store(struct device *dev, + struct device_attribute *attr, const char *buf, size_t len) +{ + char *file_name; + struct file *backing_dev = NULL; + struct inode *inode; + struct address_space *mapping; + unsigned int bitmap_sz, old_block_size = 0; + unsigned long nr_pages, *bitmap = NULL; + struct block_device *bdev = NULL; + int err; + struct zram *zram = dev_to_zram(dev); + + file_name = kmalloc(PATH_MAX, GFP_KERNEL); + if (!file_name) + return -ENOMEM; + + down_write(&zram->init_lock); + if (init_done(zram)) { + pr_info("Can't setup backing device for initialized device\n"); + err = -EBUSY; + goto out; + } + + strlcpy(file_name, buf, len); + + backing_dev = filp_open(file_name, O_RDWR|O_LARGEFILE, 0); + if (IS_ERR(backing_dev)) { + err = PTR_ERR(backing_dev); + backing_dev = NULL; + goto out; + } + + mapping = backing_dev->f_mapping; + inode = mapping->host; + + /* Support only block device in this moment */ + if (!S_ISBLK(inode->i_mode)) { + err = -ENOTBLK; + goto out; + } + + bdev = bdgrab(I_BDEV(inode)); + err = blkdev_get(bdev, FMODE_READ | FMODE_WRITE | FMODE_EXCL, zram); + if (err < 0) + goto out; + + nr_pages = i_size_read(inode) >> PAGE_SHIFT; + bitmap_sz = BITS_TO_LONGS(nr_pages) * sizeof(long); + bitmap = kvzalloc(bitmap_sz, GFP_KERNEL); + if (!bitmap) { + err = -ENOMEM; + goto out; + } + + old_block_size = block_size(bdev); + err = set_blocksize(bdev, PAGE_SIZE); + if (err) + goto out; + + reset_bdev(zram); + spin_lock_init(&zram->bitmap_lock); + + zram->old_block_size = old_block_size; + zram->bdev = bdev; + zram->backing_dev = backing_dev; + zram->bitmap = bitmap; + zram->nr_pages = nr_pages; + up_write(&zram->init_lock); + + pr_info("setup backing device %s\n", file_name); + kfree(file_name); + + return len; +out: + if (bitmap) + kvfree(bitmap); + + if (bdev) + blkdev_put(bdev, FMODE_READ | FMODE_WRITE | FMODE_EXCL); + + if (backing_dev) + filp_close(backing_dev, NULL); + + up_write(&zram->init_lock); + + kfree(file_name); + + return err; +} + +static unsigned long get_entry_bdev(struct zram *zram) +{ + unsigned long entry; + + spin_lock(&zram->bitmap_lock); + /* skip 0 bit to confuse zram.handle = 0 */ + entry = find_next_zero_bit(zram->bitmap, zram->nr_pages, 1); + if (entry == zram->nr_pages) { + spin_unlock(&zram->bitmap_lock); + return 0; + } + + set_bit(entry, zram->bitmap); + spin_unlock(&zram->bitmap_lock); + + return entry; +} + +static void put_entry_bdev(struct zram *zram, unsigned long entry) +{ + int was_set; + + spin_lock(&zram->bitmap_lock); + was_set = test_and_clear_bit(entry, zram->bitmap); + spin_unlock(&zram->bitmap_lock); + WARN_ON_ONCE(!was_set); +} + +void zram_page_end_io(struct bio *bio) +{ + struct page *page = bio->bi_io_vec[0].bv_page; + + page_endio(page, op_is_write(bio_op(bio)), + blk_status_to_errno(bio->bi_status)); + bio_put(bio); +} + +/* + * Returns 1 if the submission is successful. + */ +static int read_from_bdev_async(struct zram *zram, struct bio_vec *bvec, + unsigned long entry, struct bio *parent) +{ + struct bio *bio; + + bio = bio_alloc(GFP_ATOMIC, 1); + if (!bio) + return -ENOMEM; + + bio->bi_iter.bi_sector = entry * (PAGE_SIZE >> 9); + bio->bi_bdev = zram->bdev; + if (!bio_add_page(bio, bvec->bv_page, bvec->bv_len, bvec->bv_offset)) { + bio_put(bio); + return -EIO; + } + + if (!parent) { + bio->bi_opf = REQ_OP_READ; + bio->bi_end_io = zram_page_end_io; + } else { + bio->bi_opf = parent->bi_opf; + bio_chain(bio, parent); + } + + submit_bio(bio); + return 1; +} + +struct zram_work { + struct work_struct work; + struct zram *zram; + unsigned long entry; + struct bio *bio; +}; + +#if PAGE_SIZE != 4096 +static void zram_sync_read(struct work_struct *work) +{ + struct bio_vec bvec; + struct zram_work *zw = container_of(work, struct zram_work, work); + struct zram *zram = zw->zram; + unsigned long entry = zw->entry; + struct bio *bio = zw->bio; + + read_from_bdev_async(zram, &bvec, entry, bio); +} + +/* + * Block layer want one ->make_request_fn to be active at a time + * so if we use chained IO with parent IO in same context, + * it's a deadlock. To avoid, it, it uses worker thread context. + */ +static int read_from_bdev_sync(struct zram *zram, struct bio_vec *bvec, + unsigned long entry, struct bio *bio) +{ + struct zram_work work; + + work.zram = zram; + work.entry = entry; + work.bio = bio; + + INIT_WORK_ONSTACK(&work.work, zram_sync_read); + queue_work(system_unbound_wq, &work.work); + flush_work(&work.work); + destroy_work_on_stack(&work.work); + + return 1; +} +#else +static int read_from_bdev_sync(struct zram *zram, struct bio_vec *bvec, + unsigned long entry, struct bio *bio) +{ + WARN_ON(1); + return -EIO; +} +#endif + +static int read_from_bdev(struct zram *zram, struct bio_vec *bvec, + unsigned long entry, struct bio *parent, bool sync) +{ + if (sync) + return read_from_bdev_sync(zram, bvec, entry, parent); + else + return read_from_bdev_async(zram, bvec, entry, parent); +} + +static int write_to_bdev(struct zram *zram, struct bio_vec *bvec, + u32 index, struct bio *parent, + unsigned long *pentry) +{ + struct bio *bio; + unsigned long entry; + + bio = bio_alloc(GFP_ATOMIC, 1); + if (!bio) + return -ENOMEM; + + entry = get_entry_bdev(zram); + if (!entry) { + bio_put(bio); + return -ENOSPC; + } + + bio->bi_iter.bi_sector = entry * (PAGE_SIZE >> 9); + bio->bi_bdev = zram->bdev; + if (!bio_add_page(bio, bvec->bv_page, bvec->bv_len, + bvec->bv_offset)) { + bio_put(bio); + put_entry_bdev(zram, entry); + return -EIO; + } + + if (!parent) { + bio->bi_opf = REQ_OP_WRITE | REQ_SYNC; + bio->bi_end_io = zram_page_end_io; + } else { + bio->bi_opf = parent->bi_opf; + bio_chain(bio, parent); + } + + submit_bio(bio); + *pentry = entry; + + return 0; +} + +static void zram_wb_clear(struct zram *zram, u32 index) +{ + unsigned long entry; + + zram_clear_flag(zram, index, ZRAM_WB); + entry = zram_get_element(zram, index); + zram_set_element(zram, index, 0); + put_entry_bdev(zram, entry); +} + +#else +static bool zram_wb_enabled(struct zram *zram) { return false; } +static inline void reset_bdev(struct zram *zram) {}; +static int write_to_bdev(struct zram *zram, struct bio_vec *bvec, + u32 index, struct bio *parent, + unsigned long *pentry) + +{ + return -EIO; +} + +static int read_from_bdev(struct zram *zram, struct bio_vec *bvec, + unsigned long entry, struct bio *parent, bool sync) +{ + return -EIO; +} +static void zram_wb_clear(struct zram *zram, u32 index) {} +#endif + + /* * We switched to per-cpu streams and this attr is not needed anymore. * However, we will keep it around for some time, because: @@ -308,7 +651,7 @@ static ssize_t comp_algorithm_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t len) { struct zram *zram = dev_to_zram(dev); - char compressor[CRYPTO_MAX_ALG_NAME]; + char compressor[ARRAY_SIZE(zram->compressor)]; size_t sz; strlcpy(compressor, buf, sizeof(compressor)); @@ -327,7 +670,7 @@ static ssize_t comp_algorithm_store(struct device *dev, return -EBUSY; } - strlcpy(zram->compressor, compressor, sizeof(compressor)); + strcpy(zram->compressor, compressor); up_write(&zram->init_lock); return len; } @@ -453,30 +796,6 @@ static bool zram_same_page_read(struct zram *zram, u32 index, return false; } -static bool zram_same_page_write(struct zram *zram, u32 index, - struct page *page) -{ - unsigned long element; - void *mem = kmap_atomic(page); - - if (page_same_filled(mem, &element)) { - kunmap_atomic(mem); - /* Free memory associated with this sector now. */ - zram_slot_lock(zram, index); - zram_free_page(zram, index); - zram_set_flag(zram, index, ZRAM_SAME); - zram_set_element(zram, index, element); - zram_slot_unlock(zram, index); - - atomic64_inc(&zram->stats.same_pages); - atomic64_inc(&zram->stats.pages_stored); - return true; - } - kunmap_atomic(mem); - - return false; -} - static void zram_meta_free(struct zram *zram, u64 disksize) { size_t num_pages = disksize >> PAGE_SHIFT; @@ -515,7 +834,13 @@ static bool zram_meta_alloc(struct zram *zram, u64 disksize) */ static void zram_free_page(struct zram *zram, size_t index) { - unsigned long handle = zram_get_handle(zram, index); + unsigned long handle; + + if (zram_wb_enabled(zram) && zram_test_flag(zram, index, ZRAM_WB)) { + zram_wb_clear(zram, index); + atomic64_dec(&zram->stats.pages_stored); + return; + } /* * No memory is allocated for same element filled pages. @@ -529,6 +854,7 @@ static void zram_free_page(struct zram *zram, size_t index) return; } + handle = zram_get_handle(zram, index); if (!handle) return; @@ -542,13 +868,31 @@ static void zram_free_page(struct zram *zram, size_t index) zram_set_obj_size(zram, index, 0); } -static int zram_decompress_page(struct zram *zram, struct page *page, u32 index) +static int __zram_bvec_read(struct zram *zram, struct page *page, u32 index, + struct bio *bio, bool partial_io) { int ret; unsigned long handle; unsigned int size; void *src, *dst; + if (zram_wb_enabled(zram)) { + zram_slot_lock(zram, index); + if (zram_test_flag(zram, index, ZRAM_WB)) { + struct bio_vec bvec; + + zram_slot_unlock(zram, index); + + bvec.bv_page = page; + bvec.bv_len = PAGE_SIZE; + bvec.bv_offset = 0; + return read_from_bdev(zram, &bvec, + zram_get_element(zram, index), + bio, partial_io); + } + zram_slot_unlock(zram, index); + } + if (zram_same_page_read(zram, index, page, 0, PAGE_SIZE)) return 0; @@ -581,7 +925,7 @@ static int zram_decompress_page(struct zram *zram, struct page *page, u32 index) } static int zram_bvec_read(struct zram *zram, struct bio_vec *bvec, - u32 index, int offset) + u32 index, int offset, struct bio *bio) { int ret; struct page *page; @@ -594,7 +938,7 @@ static int zram_bvec_read(struct zram *zram, struct bio_vec *bvec, return -ENOMEM; } - ret = zram_decompress_page(zram, page, index); + ret = __zram_bvec_read(zram, page, index, bio, is_partial_io(bvec)); if (unlikely(ret)) goto out; @@ -613,30 +957,57 @@ out: return ret; } -static int zram_compress(struct zram *zram, struct zcomp_strm **zstrm, - struct page *page, - unsigned long *out_handle, unsigned int *out_comp_len) +static int __zram_bvec_write(struct zram *zram, struct bio_vec *bvec, + u32 index, struct bio *bio) { - int ret; - unsigned int comp_len; - void *src; + int ret = 0; unsigned long alloced_pages; unsigned long handle = 0; + unsigned int comp_len = 0; + void *src, *dst, *mem; + struct zcomp_strm *zstrm; + struct page *page = bvec->bv_page; + unsigned long element = 0; + enum zram_pageflags flags = 0; + bool allow_wb = true; + + mem = kmap_atomic(page); + if (page_same_filled(mem, &element)) { + kunmap_atomic(mem); + /* Free memory associated with this sector now. */ |