bdi: introduce BDI_CAP_SYNCHRONOUS_IO

As discussed at

  https://lkml.kernel.org/r/<20170728165604.10455-1-ross.zwisler@linux.intel.com>

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@kernel.org
Signed-off-by: Minchan Kim <minchan@kernel.org>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: Ross Zwisler <ross.zwisler@linux.intel.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Ilya Dryomov <idryomov@gmail.com>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Sergey Senozhatsky <sergey.senozhatsky@gmail.com>
Cc: Huang Ying <ying.huang@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/drivers/block/brd.c b/drivers/block/brd.c
index c1cf877..588360d 100644 (file)
--- a/drivers/block/brd.c
+++ b/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 i)
        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 --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c
index d95bb8c..8856422 100644 (file)
--- a/drivers/block/zram/zram_drv.c
+++ b/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 --git a/drivers/nvdimm/btt.c b/drivers/nvdimm/btt.c
index d5612bd..e949e33 100644 (file)
--- a/drivers/nvdimm/btt.c
+++ b/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 --git a/drivers/nvdimm/pmem.c b/drivers/nvdimm/pmem.c
index 39dfd7a..7fbc5c5 100644 (file)
--- a/drivers/nvdimm/pmem.c
+++ b/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 device *dev,
        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 --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h
index f41ca84..7360e79 100644 (file)
--- a/include/linux/backing-dev.h
+++ b/include/linux/backing-dev.h
@@ -122,6 +122,8 @@ int bdi_set_max_ratio(struct backing_dev_info *bdi, unsigned int max_ratio);
  * 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_info *bdi, unsigned int max_ratio);
 #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 bdi_writeback *wb, int cong_bits)
 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;