diff options
Diffstat (limited to 'drivers/block')
-rw-r--r-- | drivers/block/drbd/drbd_receiver.c | 4 | ||||
-rw-r--r-- | drivers/block/virtio_blk.c | 110 | ||||
-rw-r--r-- | drivers/block/zram/zram_drv.c | 64 | ||||
-rw-r--r-- | drivers/block/zram/zram_drv.h | 15 |
4 files changed, 128 insertions, 65 deletions
diff --git a/drivers/block/drbd/drbd_receiver.c b/drivers/block/drbd/drbd_receiver.c index c897c4572036..ee69d50ba4fd 100644 --- a/drivers/block/drbd/drbd_receiver.c +++ b/drivers/block/drbd/drbd_receiver.c @@ -781,7 +781,7 @@ static struct socket *drbd_wait_for_connect(struct drbd_connection *connection, timeo = connect_int * HZ; /* 28.5% random jitter */ - timeo += (prandom_u32() & 1) ? timeo / 7 : -timeo / 7; + timeo += prandom_u32_max(2) ? timeo / 7 : -timeo / 7; err = wait_for_completion_interruptible_timeout(&ad->door_bell, timeo); if (err <= 0) @@ -1004,7 +1004,7 @@ retry: drbd_warn(connection, "Error receiving initial packet\n"); sock_release(s); randomize: - if (prandom_u32() & 1) + if (prandom_u32_max(2)) goto retry; } } diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c index 3f4739d52268..19da5defd734 100644 --- a/drivers/block/virtio_blk.c +++ b/drivers/block/virtio_blk.c @@ -130,7 +130,7 @@ static int virtblk_add_req(struct virtqueue *vq, struct virtblk_req *vbr) return virtqueue_add_sgs(vq, sgs, num_out, num_in, vbr, GFP_ATOMIC); } -static int virtblk_setup_discard_write_zeroes(struct request *req, bool unmap) +static int virtblk_setup_discard_write_zeroes_erase(struct request *req, bool unmap) { unsigned short segments = blk_rq_nr_discard_segments(req); unsigned short n = 0; @@ -240,6 +240,9 @@ static blk_status_t virtblk_setup_cmd(struct virtio_device *vdev, type = VIRTIO_BLK_T_WRITE_ZEROES; unmap = !(req->cmd_flags & REQ_NOUNMAP); break; + case REQ_OP_SECURE_ERASE: + type = VIRTIO_BLK_T_SECURE_ERASE; + break; case REQ_OP_DRV_IN: type = VIRTIO_BLK_T_GET_ID; break; @@ -251,8 +254,9 @@ static blk_status_t virtblk_setup_cmd(struct virtio_device *vdev, vbr->out_hdr.type = cpu_to_virtio32(vdev, type); vbr->out_hdr.ioprio = cpu_to_virtio32(vdev, req_get_ioprio(req)); - if (type == VIRTIO_BLK_T_DISCARD || type == VIRTIO_BLK_T_WRITE_ZEROES) { - if (virtblk_setup_discard_write_zeroes(req, unmap)) + if (type == VIRTIO_BLK_T_DISCARD || type == VIRTIO_BLK_T_WRITE_ZEROES || + type == VIRTIO_BLK_T_SECURE_ERASE) { + if (virtblk_setup_discard_write_zeroes_erase(req, unmap)) return BLK_STS_RESOURCE; } @@ -886,6 +890,8 @@ static int virtblk_probe(struct virtio_device *vdev) int err, index; u32 v, blk_size, max_size, sg_elems, opt_io_size; + u32 max_discard_segs = 0; + u32 discard_granularity = 0; u16 min_io_size; u8 physical_block_exp, alignment_offset; unsigned int queue_depth; @@ -1043,27 +1049,14 @@ static int virtblk_probe(struct virtio_device *vdev) if (virtio_has_feature(vdev, VIRTIO_BLK_F_DISCARD)) { virtio_cread(vdev, struct virtio_blk_config, - discard_sector_alignment, &v); - if (v) - q->limits.discard_granularity = v << SECTOR_SHIFT; - else - q->limits.discard_granularity = blk_size; + discard_sector_alignment, &discard_granularity); virtio_cread(vdev, struct virtio_blk_config, max_discard_sectors, &v); blk_queue_max_discard_sectors(q, v ? v : UINT_MAX); virtio_cread(vdev, struct virtio_blk_config, max_discard_seg, - &v); - - /* - * max_discard_seg == 0 is out of spec but we always - * handled it. - */ - if (!v) - v = sg_elems; - blk_queue_max_discard_segments(q, - min(v, MAX_DISCARD_SEGMENTS)); + &max_discard_segs); } if (virtio_has_feature(vdev, VIRTIO_BLK_F_WRITE_ZEROES)) { @@ -1072,6 +1065,85 @@ static int virtblk_probe(struct virtio_device *vdev) blk_queue_max_write_zeroes_sectors(q, v ? v : UINT_MAX); } + /* The discard and secure erase limits are combined since the Linux + * block layer uses the same limit for both commands. + * + * If both VIRTIO_BLK_F_SECURE_ERASE and VIRTIO_BLK_F_DISCARD features + * are negotiated, we will use the minimum between the limits. + * + * discard sector alignment is set to the minimum between discard_sector_alignment + * and secure_erase_sector_alignment. + * + * max discard sectors is set to the minimum between max_discard_seg and + * max_secure_erase_seg. + */ + if (virtio_has_feature(vdev, VIRTIO_BLK_F_SECURE_ERASE)) { + + virtio_cread(vdev, struct virtio_blk_config, + secure_erase_sector_alignment, &v); + + /* secure_erase_sector_alignment should not be zero, the device should set a + * valid number of sectors. + */ + if (!v) { + dev_err(&vdev->dev, + "virtio_blk: secure_erase_sector_alignment can't be 0\n"); + err = -EINVAL; + goto out_cleanup_disk; + } + + discard_granularity = min_not_zero(discard_granularity, v); + + virtio_cread(vdev, struct virtio_blk_config, + max_secure_erase_sectors, &v); + + /* max_secure_erase_sectors should not be zero, the device should set a + * valid number of sectors. + */ + if (!v) { + dev_err(&vdev->dev, + "virtio_blk: max_secure_erase_sectors can't be 0\n"); + err = -EINVAL; + goto out_cleanup_disk; + } + + blk_queue_max_secure_erase_sectors(q, v); + + virtio_cread(vdev, struct virtio_blk_config, + max_secure_erase_seg, &v); + + /* max_secure_erase_seg should not be zero, the device should set a + * valid number of segments + */ + if (!v) { + dev_err(&vdev->dev, + "virtio_blk: max_secure_erase_seg can't be 0\n"); + err = -EINVAL; + goto out_cleanup_disk; + } + + max_discard_segs = min_not_zero(max_discard_segs, v); + } + + if (virtio_has_feature(vdev, VIRTIO_BLK_F_DISCARD) || + virtio_has_feature(vdev, VIRTIO_BLK_F_SECURE_ERASE)) { + /* max_discard_seg and discard_granularity will be 0 only + * if max_discard_seg and discard_sector_alignment fields in the virtio + * config are 0 and VIRTIO_BLK_F_SECURE_ERASE feature is not negotiated. + * In this case, we use default values. + */ + if (!max_discard_segs) + max_discard_segs = sg_elems; + + blk_queue_max_discard_segments(q, + min(max_discard_segs, MAX_DISCARD_SEGMENTS)); + + if (discard_granularity) + q->limits.discard_granularity = discard_granularity << SECTOR_SHIFT; + else + q->limits.discard_granularity = blk_size; + } + virtblk_update_capacity(vblk, false); virtio_device_ready(vdev); @@ -1167,6 +1239,7 @@ static unsigned int features_legacy[] = { VIRTIO_BLK_F_RO, VIRTIO_BLK_F_BLK_SIZE, VIRTIO_BLK_F_FLUSH, VIRTIO_BLK_F_TOPOLOGY, VIRTIO_BLK_F_CONFIG_WCE, VIRTIO_BLK_F_MQ, VIRTIO_BLK_F_DISCARD, VIRTIO_BLK_F_WRITE_ZEROES, + VIRTIO_BLK_F_SECURE_ERASE, } ; static unsigned int features[] = { @@ -1174,6 +1247,7 @@ static unsigned int features[] = { VIRTIO_BLK_F_RO, VIRTIO_BLK_F_BLK_SIZE, VIRTIO_BLK_F_FLUSH, VIRTIO_BLK_F_TOPOLOGY, VIRTIO_BLK_F_CONFIG_WCE, VIRTIO_BLK_F_MQ, VIRTIO_BLK_F_DISCARD, VIRTIO_BLK_F_WRITE_ZEROES, + VIRTIO_BLK_F_SECURE_ERASE, }; static struct virtio_driver virtio_blk = { diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c index e551433cd107..966aab902d19 100644 --- a/drivers/block/zram/zram_drv.c +++ b/drivers/block/zram/zram_drv.c @@ -52,9 +52,6 @@ static unsigned int num_devices = 1; static size_t huge_class_size; static const struct block_device_operations zram_devops; -#ifdef CONFIG_ZRAM_WRITEBACK -static const struct block_device_operations zram_wb_devops; -#endif static void zram_free_page(struct zram *zram, size_t index); static int zram_bvec_read(struct zram *zram, struct bio_vec *bvec, @@ -329,8 +326,8 @@ static ssize_t idle_store(struct device *dev, if (!sysfs_streq(buf, "all")) { /* - * If it did not parse as 'all' try to treat it as an integer when - * we have memory tracking enabled. + * If it did not parse as 'all' try to treat it as an integer + * when we have memory tracking enabled. */ u64 age_sec; @@ -345,7 +342,10 @@ static ssize_t idle_store(struct device *dev, if (!init_done(zram)) goto out_unlock; - /* A cutoff_time of 0 marks everything as idle, this is the "all" behavior */ + /* + * A cutoff_time of 0 marks everything as idle, this is the + * "all" behavior. + */ mark_idle(zram, cutoff_time); rv = len; @@ -543,17 +543,6 @@ static ssize_t backing_dev_store(struct device *dev, zram->backing_dev = backing_dev; zram->bitmap = bitmap; zram->nr_pages = nr_pages; - /* - * With writeback feature, zram does asynchronous IO so it's no longer - * synchronous device so let's remove synchronous io flag. Othewise, - * upper layer(e.g., swap) could wait IO completion rather than - * (submit and return), which will cause system sluggish. - * Furthermore, when the IO function returns(e.g., swap_readpage), - * upper layer expects IO was done so it could deallocate the page - * freely but in fact, IO is going on so finally could cause - * use-after-free when the IO is really done. - */ - zram->disk->fops = &zram_wb_devops; up_write(&zram->init_lock); pr_info("setup backing device %s\n", file_name); @@ -1267,6 +1256,9 @@ static int __zram_bvec_read(struct zram *zram, struct page *page, u32 index, struct bio_vec bvec; zram_slot_unlock(zram, index); + /* A null bio means rw_page was used, we must fallback to bio */ + if (!bio) + return -EOPNOTSUPP; bvec.bv_page = page; bvec.bv_len = PAGE_SIZE; @@ -1410,9 +1402,19 @@ compress_again: handle = zs_malloc(zram->mem_pool, comp_len, GFP_NOIO | __GFP_HIGHMEM | __GFP_MOVABLE); - if (!IS_ERR((void *)handle)) + if (IS_ERR((void *)handle)) + return PTR_ERR((void *)handle); + + if (comp_len != PAGE_SIZE) goto compress_again; - return PTR_ERR((void *)handle); + /* + * If the page is not compressible, you need to acquire the + * lock and execute the code below. The zcomp_stream_get() + * call is needed to disable the cpu hotplug and grab the + * zstrm buffer back. It is necessary that the dereferencing + * of the zstrm variable below occurs correctly. + */ + zstrm = zcomp_stream_get(zram->comp); } alloced_pages = zs_get_total_pages(zram->mem_pool); @@ -1710,9 +1712,6 @@ out: static void zram_reset_device(struct zram *zram) { - struct zcomp *comp; - u64 disksize; - down_write(&zram->init_lock); zram->limit_pages = 0; @@ -1722,17 +1721,15 @@ static void zram_reset_device(struct zram *zram) return; } - comp = zram->comp; - disksize = zram->disksize; - zram->disksize = 0; - set_capacity_and_notify(zram->disk, 0); part_stat_set_all(zram->disk->part0, 0); /* I/O operation under all of CPU are done so let's free */ - zram_meta_free(zram, disksize); + zram_meta_free(zram, zram->disksize); + zram->disksize = 0; memset(&zram->stats, 0, sizeof(zram->stats)); - zcomp_destroy(comp); + zcomp_destroy(zram->comp); + zram->comp = NULL; reset_bdev(zram); up_write(&zram->init_lock); @@ -1848,15 +1845,6 @@ static const struct block_device_operations zram_devops = { .owner = THIS_MODULE }; -#ifdef CONFIG_ZRAM_WRITEBACK -static const struct block_device_operations zram_wb_devops = { - .open = zram_open, - .submit_bio = zram_submit_bio, - .swap_slot_free_notify = zram_slot_free_notify, - .owner = THIS_MODULE -}; -#endif - static DEVICE_ATTR_WO(compact); static DEVICE_ATTR_RW(disksize); static DEVICE_ATTR_RO(initstate); @@ -2126,6 +2114,8 @@ static int __init zram_init(void) { int ret; + BUILD_BUG_ON(__NR_ZRAM_PAGEFLAGS > BITS_PER_LONG); + ret = cpuhp_setup_state_multi(CPUHP_ZCOMP_PREPARE, "block/zram:prepare", zcomp_cpu_up_prepare, zcomp_cpu_dead); if (ret < 0) diff --git a/drivers/block/zram/zram_drv.h b/drivers/block/zram/zram_drv.h index 80c3b43b4828..a2bda53020fd 100644 --- a/drivers/block/zram/zram_drv.h +++ b/drivers/block/zram/zram_drv.h @@ -30,16 +30,15 @@ /* - * The lower ZRAM_FLAG_SHIFT bits of table.flags is for - * object size (excluding header), the higher bits is for - * zram_pageflags. + * ZRAM is mainly used for memory efficiency so we want to keep memory + * footprint small and thus squeeze size and zram pageflags into a flags + * member. The lower ZRAM_FLAG_SHIFT bits is for object size (excluding + * header), which cannot be larger than PAGE_SIZE (requiring PAGE_SHIFT + * bits), the higher bits are for zram_pageflags. * - * zram is mainly used for memory efficiency so we want to keep memory - * footprint small so we can squeeze size and flags into a field. - * The lower ZRAM_FLAG_SHIFT bits is for object size (excluding header), - * the higher bits is for zram_pageflags. + * We use BUILD_BUG_ON() to make sure that zram pageflags don't overflow. */ -#define ZRAM_FLAG_SHIFT 24 +#define ZRAM_FLAG_SHIFT (PAGE_SHIFT + 1) /* Flags for zram pages (table[page_no].flags) */ enum zram_pageflags { |