@@ -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>
@@ -436,6 +437,7 @@ 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);
@@ -1577,7 +1577,7 @@ 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,
@@ -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"
@@ -1273,6 +1274,8 @@ 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);
@@ -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"
@@ -379,6 +380,7 @@ 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);
@@ -123,6 +123,8 @@ 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
@@ -130,6 +132,7 @@ 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)
@@ -177,6 +180,11 @@ long wait_iff_congested(struct pglist_data *pgdat, int sync, long timeout);
int pdflush_proc_obsolete(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp, loff_t *ppos);
+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;
By discussion[1], we will replace rw_page devices with on-stack-bio. For such super-fast devices to be detected, this patch introduces BDI_CAP_SYNC which means synchronous IO would be more efficient for asnychronous IO and uses the flags to brd, zram, btt and pmem. [1] lkml.kernel.org/r/<20170728165604.10455-1-ross.zwisler@linux.intel.com> Signed-off-by: Minchan Kim <minchan@kernel.org> --- 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(-)