Hi Dan,

Thanks for the review,


On Tue, May 17, 2016 at 12:34:57PM -0700, Dan Williams wrote:

On Tue, May 17, 2016 at 11:29 AM, Jon Derrick
[off-list ref] wrote:

quoted

This patch fixes S_DAX bd_inode i_flag locking to conform to suggested

A "fix" implies that its currently broken.  I don't see how it is, not
until we add an ioctl method or other path that also tries to update
the flags outside of blkdev_get() context.  So, I don't think this
patch stands on its own if you were intending it to be merged
separately.

Are there no other paths that can set/clear a bd_inode->i_flags?
If not, that's fine and I'll pack this into the next HIPRI set

quoted

locking rules. It is presumed that S_DAX is the only valid inode flag
for a block device which subscribes to direct-access, and will restore
any previously set flags if direct-access initialization fails.

This reverts to i_flags behavior prior to
bbab37ddc20bae4709bca8745c128c4f46fe63c5
by allowing other bd_inode flags when DAX is disabled

Signed-off-by: Jon Derrick <redacted>
---
 fs/block_dev.c | 31 ++++++++++++++++++++++++++-----
 1 file changed, 26 insertions(+), 5 deletions(-)

diff --git a/fs/block_dev.c b/fs/block_dev.c
index 20a2c02..d41e37f 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c

@@ -1159,6 +1159,20 @@ void bd_set_size(struct block_device *bdev, loff_t size)
 }
 EXPORT_SYMBOL(bd_set_size);

+static void bd_add_dax(struct inode *inode)
+{
+       inode_lock(inode);
+       inode->i_flags |= S_DAX;
+       inode_unlock(inode);
+}
+
+static void bd_clear_dax(struct inode *inode)
+{
+       inode_lock(inode);
+       inode->i_flags &= ~S_DAX;
+       inode_unlock(inode);
+}

Since this is inode generic should these helpers be prefixed "i_"
rather than "bd_"?

That's fine. bd_acquire/forget also use the inode in its parameter list, but its simple enough to use the bdev instead for these functions or i_ as you suggest

quoted

+
 static void __blkdev_put(struct block_device *bdev, fmode_t mode, int for_part);

 /*

@@ -1172,6 +1186,7 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part)
 {
        struct gendisk *disk;
        struct module *owner;
+       struct inode *inode;
        int ret;
        int partno;
        int perm = 0;

@@ -1198,6 +1213,7 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part)
        if (!disk)
                goto out;
        owner = disk->fops->owner;
+       inode = bdev->bd_inode;

        disk_block_events(disk);
        mutex_lock_nested(&bdev->bd_mutex, for_part);

@@ -1206,9 +1222,7 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part)
                bdev->bd_queue = disk->queue;
                bdev->bd_contains = bdev;
                if (IS_ENABLED(CONFIG_BLK_DEV_DAX) && disk->fops->direct_access)
-                       bdev->bd_inode->i_flags = S_DAX;
-               else
-                       bdev->bd_inode->i_flags = 0;
+                       bd_add_dax(inode);

                if (!partno) {
                        ret = -ENXIO;

@@ -1228,6 +1242,7 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part)
                                        bdev->bd_part = NULL;
                                        bdev->bd_disk = NULL;
                                        bdev->bd_queue = NULL;
+                                       bd_clear_dax(inode);
                                        mutex_unlock(&bdev->bd_mutex);
                                        disk_unblock_events(disk);
                                        put_disk(disk);

@@ -1239,7 +1254,7 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part)
                        if (!ret) {
                                bd_set_size(bdev,(loff_t)get_capacity(disk)<<9);
                                if (!blkdev_dax_capable(bdev))
-                                       bdev->bd_inode->i_flags &= ~S_DAX;
+                                       bd_clear_dax(inode);
                        }

                        /*

@@ -1276,7 +1291,7 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part)
                        }
                        bd_set_size(bdev, (loff_t)bdev->bd_part->nr_sects << 9);
                        if (!blkdev_dax_capable(bdev))
-                               bdev->bd_inode->i_flags &= ~S_DAX;
+                               bd_clear_dax(inode);
                }
        } else {
                if (bdev->bd_contains == bdev) {

@@ -1297,6 +1312,11 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part)
                put_disk(disk);
                module_put(owner);
        }
+       inode_lock(inode);
+       if (inode->i_flags & S_DAX)
+               inode->i_flags = S_DAX;
+       inode_unlock(inode);
+

Clear all other flags if S_DAX is set? Why?

Code today sets i_flags = S_DAX, clearing all other flags, so I figured that's how it's supposed to be. Though I can't see any reason it has to be that way.

quoted

        bdev->bd_openers++;
        if (for_part)
                bdev->bd_part_count++;

@@ -1309,6 +1329,7 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part)
        bdev->bd_disk = NULL;
        bdev->bd_part = NULL;
        bdev->bd_queue = NULL;
+       bd_clear_dax(inode);

Why?

As far as I can tell, this path is only for cleanup when a whole block device or partition block device fails to get. Your question makes me think I don't understand this part of the code correctly, and admittedly I don't understand it all that well.

All callers of out_clear set an error code on ret, so I assumed all instances of out_clear are errors. There's no reason to keep the S_DAX flag on the bdev this time around. If it resolves itself (for example, GENHD_FL_UP gets set), it can be set again on the next __blkdev_get pass.