From: Minchan Kim <minchan@xxxxxxxxxx> Subject: bdi: introduce BDI_CAP_SYNCHRONOUS_IO As discussed at lkml.kernel.org/r/<20170728165604.10455-1-ross.zwisler@xxxxxxxxxxxxxxx>, someday we will remove rw_page(). If so, we need something to detect such super-fast storage on which synchronous IO operations like the current rw_page are always a win. Introduces BDI_CAP_SYNCHRONOUS_IO to indicate such devices. With it, we could use various optimization techniques. Link: http://lkml.kernel.org/r/1505886205-9671-3-git-send-email-minchan@xxxxxxxxxx Signed-off-by: Minchan Kim <minchan@xxxxxxxxxx> Cc: Christoph Hellwig <hch@xxxxxx> Cc: Dan Williams <dan.j.williams@xxxxxxxxx> Cc: Ross Zwisler <ross.zwisler@xxxxxxxxxxxxxxx> Cc: Hugh Dickins <hughd@xxxxxxxxxx> Cc: Ilya Dryomov <idryomov@xxxxxxxxx> Cc: Jens Axboe <axboe@xxxxxxxxx> Cc: Sergey Senozhatsky <sergey.senozhatsky@xxxxxxxxx> Cc: Huang Ying <ying.huang@xxxxxxxxx> Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx> --- drivers/block/brd.c | 2 ++ drivers/block/zram/zram_drv.c | 2 +- drivers/nvdimm/btt.c | 3 +++ drivers/nvdimm/pmem.c | 2 ++ include/linux/backing-dev.h | 8 ++++++++ 5 files changed, 16 insertions(+), 1 deletion(-) diff -puN drivers/block/brd.c~bdi-introduce-bdi_cap_synchronous_io drivers/block/brd.c --- a/drivers/block/brd.c~bdi-introduce-bdi_cap_synchronous_io +++ a/drivers/block/brd.c @@ -20,6 +20,7 @@ #include <linux/radix-tree.h> #include <linux/fs.h> #include <linux/slab.h> +#include <linux/backing-dev.h> #ifdef CONFIG_BLK_DEV_RAM_DAX #include <linux/pfn_t.h> #include <linux/dax.h> @@ -448,6 +449,7 @@ static struct brd_device *brd_alloc(int disk->flags = GENHD_FL_EXT_DEVT; sprintf(disk->disk_name, "ram%d", i); set_capacity(disk, rd_size * 2); + disk->queue->backing_dev_info->capabilities |= BDI_CAP_SYNCHRONOUS_IO; #ifdef CONFIG_BLK_DEV_RAM_DAX queue_flag_set_unlocked(QUEUE_FLAG_DAX, brd->brd_queue); diff -puN drivers/block/zram/zram_drv.c~bdi-introduce-bdi_cap_synchronous_io drivers/block/zram/zram_drv.c --- a/drivers/block/zram/zram_drv.c~bdi-introduce-bdi_cap_synchronous_io +++ a/drivers/block/zram/zram_drv.c @@ -1558,7 +1558,7 @@ static int zram_add(void) blk_queue_max_write_zeroes_sectors(zram->disk->queue, UINT_MAX); zram->disk->queue->backing_dev_info->capabilities |= - BDI_CAP_STABLE_WRITES; + (BDI_CAP_STABLE_WRITES | BDI_CAP_SYNCHRONOUS_IO); add_disk(zram->disk); ret = sysfs_create_group(&disk_to_dev(zram->disk)->kobj, diff -puN drivers/nvdimm/btt.c~bdi-introduce-bdi_cap_synchronous_io drivers/nvdimm/btt.c --- a/drivers/nvdimm/btt.c~bdi-introduce-bdi_cap_synchronous_io +++ a/drivers/nvdimm/btt.c @@ -23,6 +23,7 @@ #include <linux/ndctl.h> #include <linux/fs.h> #include <linux/nd.h> +#include <linux/backing-dev.h> #include "btt.h" #include "nd.h" @@ -1402,6 +1403,8 @@ static int btt_blk_init(struct btt *btt) btt->btt_disk->private_data = btt; btt->btt_disk->queue = btt->btt_queue; btt->btt_disk->flags = GENHD_FL_EXT_DEVT; + btt->btt_disk->queue->backing_dev_info->capabilities |= + BDI_CAP_SYNCHRONOUS_IO; blk_queue_make_request(btt->btt_queue, btt_make_request); blk_queue_logical_block_size(btt->btt_queue, btt->sector_size); diff -puN drivers/nvdimm/pmem.c~bdi-introduce-bdi_cap_synchronous_io drivers/nvdimm/pmem.c --- a/drivers/nvdimm/pmem.c~bdi-introduce-bdi_cap_synchronous_io +++ a/drivers/nvdimm/pmem.c @@ -31,6 +31,7 @@ #include <linux/uio.h> #include <linux/dax.h> #include <linux/nd.h> +#include <linux/backing-dev.h> #include "pmem.h" #include "pfn.h" #include "nd.h" @@ -394,6 +395,7 @@ static int pmem_attach_disk(struct devic disk->fops = &pmem_fops; disk->queue = q; disk->flags = GENHD_FL_EXT_DEVT; + disk->queue->backing_dev_info->capabilities |= BDI_CAP_SYNCHRONOUS_IO; nvdimm_namespace_disk_name(ndns, disk->disk_name); set_capacity(disk, (pmem->size - pmem->pfn_pad - pmem->data_offset) / 512); diff -puN include/linux/backing-dev.h~bdi-introduce-bdi_cap_synchronous_io include/linux/backing-dev.h --- a/include/linux/backing-dev.h~bdi-introduce-bdi_cap_synchronous_io +++ a/include/linux/backing-dev.h @@ -122,6 +122,8 @@ int bdi_set_max_ratio(struct backing_dev * BDI_CAP_STRICTLIMIT: Keep number of dirty pages below bdi threshold. * * BDI_CAP_CGROUP_WRITEBACK: Supports cgroup-aware writeback. + * BDI_CAP_SYNCHRONOUS_IO: Device is so fast that asynchronous IO would be + * inefficient. */ #define BDI_CAP_NO_ACCT_DIRTY 0x00000001 #define BDI_CAP_NO_WRITEBACK 0x00000002 @@ -129,6 +131,7 @@ int bdi_set_max_ratio(struct backing_dev #define BDI_CAP_STABLE_WRITES 0x00000008 #define BDI_CAP_STRICTLIMIT 0x00000010 #define BDI_CAP_CGROUP_WRITEBACK 0x00000020 +#define BDI_CAP_SYNCHRONOUS_IO 0x00000040 #define BDI_CAP_NO_ACCT_AND_WRITEBACK \ (BDI_CAP_NO_WRITEBACK | BDI_CAP_NO_ACCT_DIRTY | BDI_CAP_NO_ACCT_WB) @@ -174,6 +177,11 @@ static inline int wb_congested(struct bd long congestion_wait(int sync, long timeout); long wait_iff_congested(struct pglist_data *pgdat, int sync, long timeout); +static inline bool bdi_cap_synchronous_io(struct backing_dev_info *bdi) +{ + return bdi->capabilities & BDI_CAP_SYNCHRONOUS_IO; +} + static inline bool bdi_cap_stable_pages_required(struct backing_dev_info *bdi) { return bdi->capabilities & BDI_CAP_STABLE_WRITES; _ -- To unsubscribe from this list: send the line "unsubscribe mm-commits" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html
