[PATCH v7 4/5] btrfs: introduce new device-state read_preferred

[Anand Jain <anand.jain@oracle.com>]

This is a preparatory patch and introduces a new device flag
'read_preferred', and is a generic flag which along with the read_policy
'device' in the following patch the user can route the read IO to the
device of choice.

This also provides a sysfs interface to set the device state as
read_preferred.

Signed-off-by: Anand Jain <anand.jain@oracle.com>
---
v7: Change log updated.
v6: If there is no change in device's read prefer then don't log. 
    Add pid to the logs.
v5: born

 fs/btrfs/sysfs.c   | 55 ++++++++++++++++++++++++++++++++++++++++++++++
 fs/btrfs/volumes.h |  1 +
 2 files changed, 56 insertions(+)

diff --git a/fs/btrfs/sysfs.c b/fs/btrfs/sysfs.c
index c9a8850b186a..72daaedb7b04 100644
--- a/fs/btrfs/sysfs.c
+++ b/fs/btrfs/sysfs.c
@@ -1317,11 +1317,66 @@ static ssize_t btrfs_devinfo_writeable_show(struct kobject *kobj,
 }
 BTRFS_ATTR(devid, writeable, btrfs_devinfo_writeable_show);
 
+static ssize_t btrfs_devinfo_read_pref_show(struct kobject *kobj,
+					    struct kobj_attribute *a, char *buf)
+{
+	int val;
+	struct btrfs_device *device = container_of(kobj, struct btrfs_device,
+						   devid_kobj);
+
+	val = !!test_bit(BTRFS_DEV_STATE_READ_PREFERRED, &device->dev_state);
+
+	return snprintf(buf, PAGE_SIZE, "%d\n", val);
+}
+
+static ssize_t btrfs_devinfo_read_pref_store(struct kobject *kobj,
+					     struct kobj_attribute *a,
+					     const char *buf, size_t len)
+{
+	int ret;
+	unsigned long val;
+	struct btrfs_device *device;
+
+	ret = kstrtoul(skip_spaces(buf), 0, &val);
+	if (ret)
+		return ret;
+
+	if (val != 0 && val != 1)
+		return -EINVAL;
+
+	/*
+	 * lock is not required, the btrfs_device struct can't be freed while
+	 * its kobject btrfs_device::devid_kobj is still open.
+	 */
+	device = container_of(kobj, struct btrfs_device, devid_kobj);
+
+	if (val &&
+	    ! test_bit(BTRFS_DEV_STATE_READ_PREFERRED, &device->dev_state)) {
+
+		set_bit(BTRFS_DEV_STATE_READ_PREFERRED, &device->dev_state);
+		btrfs_info(device->fs_devices->fs_info,
+			   "set read preferred on devid %llu (%d)",
+			   device->devid, task_pid_nr(current));
+	} else if (!val &&
+		   test_bit(BTRFS_DEV_STATE_READ_PREFERRED, &device->dev_state)) {
+
+		clear_bit(BTRFS_DEV_STATE_READ_PREFERRED, &device->dev_state);
+		btrfs_info(device->fs_devices->fs_info,
+			   "reset read preferred on devid %llu (%d)",
+			   device->devid, task_pid_nr(current));
+	}
+
+	return len;
+}
+BTRFS_ATTR_RW(devid, read_preferred, btrfs_devinfo_read_pref_show,
+	      btrfs_devinfo_read_pref_store);
+
 static struct attribute *devid_attrs[] = {
 	BTRFS_ATTR_PTR(devid, in_fs_metadata),
 	BTRFS_ATTR_PTR(devid, missing),
 	BTRFS_ATTR_PTR(devid, replace_target),
 	BTRFS_ATTR_PTR(devid, writeable),
+	BTRFS_ATTR_PTR(devid, read_preferred),
 	NULL
 };
 ATTRIBUTE_GROUPS(devid);
diff --git a/fs/btrfs/volumes.h b/fs/btrfs/volumes.h
index 1775d35706ab..487a54c3140e 100644
--- a/fs/btrfs/volumes.h
+++ b/fs/btrfs/volumes.h
@@ -50,6 +50,7 @@ struct btrfs_io_geometry {
 #define BTRFS_DEV_STATE_MISSING		(2)
 #define BTRFS_DEV_STATE_REPLACE_TGT	(3)
 #define BTRFS_DEV_STATE_FLUSH_SENT	(4)
+#define BTRFS_DEV_STATE_READ_PREFERRED	(5)
 
 struct btrfs_device {
 	struct list_head dev_list; /* device_list_mutex */
-- 
2.23.0