block: add a bi_error field to struct bio

Currently we have two different ways to signal an I/O error on a BIO:

 (1) by clearing the BIO_UPTODATE flag
 (2) by returning a Linux errno value to the bi_end_io callback

The first one has the drawback of only communicating a single possible
error (-EIO), and the second one has the drawback of not beeing persistent
when bios are queued up, and are not passed along from child to parent
bio in the ever more popular chaining scenario.  Having both mechanisms
available has the additional drawback of utterly confusing driver authors
and introducing bugs where various I/O submitters only deal with one of
them, and the others have to add boilerplate code to deal with both kinds
of error returns.

So add a new bi_error field to store an errno value directly in struct
bio and remove the existing mechanisms to clean all this up.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Reviewed-by: NeilBrown <neilb@suse.com>
Signed-off-by: Jens Axboe <axboe@fb.com>

5 files changed, 30 insertions, 58 deletions

diff --git a/drivers/block/drbd/drbd_actlog.c b/drivers/block/drbd/drbd_actlog.c
index 1318e3217cb0..b3868e7a1ffd 100644
--- a/drivers/block/drbd/drbd_actlog.c
+++ b/drivers/block/drbd/drbd_actlog.c
@@ -175,11 +175,11 @@ static int _drbd_md_sync_page_io(struct drbd_device *device,
 	atomic_inc(&device->md_io.in_use); /* drbd_md_put_buffer() is in the completion handler */
 	device->md_io.submit_jif = jiffies;
 	if (drbd_insert_fault(device, (rw & WRITE) ? DRBD_FAULT_MD_WR : DRBD_FAULT_MD_RD))
-		bio_endio(bio, -EIO);
+		bio_io_error(bio);
 	else
 		submit_bio(rw, bio);
 	wait_until_done_or_force_detached(device, bdev, &device->md_io.done);
-	if (bio_flagged(bio, BIO_UPTODATE))
+	if (!bio->bi_error)
 		err = device->md_io.error;
 
  out:
diff --git a/drivers/block/drbd/drbd_bitmap.c b/drivers/block/drbd/drbd_bitmap.c
index 434c77dcc99e..e5e0f19ceda0 100644
--- a/drivers/block/drbd/drbd_bitmap.c
+++ b/drivers/block/drbd/drbd_bitmap.c
@@ -941,36 +941,27 @@ static void drbd_bm_aio_ctx_destroy(struct kref *kref)
 }
 
 /* bv_page may be a copy, or may be the original */
-static void drbd_bm_endio(struct bio *bio, int error)
+static void drbd_bm_endio(struct bio *bio)
 {
 	struct drbd_bm_aio_ctx *ctx = bio->bi_private;
 	struct drbd_device *device = ctx->device;
 	struct drbd_bitmap *b = device->bitmap;
 	unsigned int idx = bm_page_to_idx(bio->bi_io_vec[0].bv_page);
-	int uptodate = bio_flagged(bio, BIO_UPTODATE);
-
-
-	/* strange behavior of some lower level drivers...
-	 * fail the request by clearing the uptodate flag,
-	 * but do not return any error?!
-	 * do we want to WARN() on this? */
-	if (!error && !uptodate)
-		error = -EIO;
 
 	if ((ctx->flags & BM_AIO_COPY_PAGES) == 0 &&
 	    !bm_test_page_unchanged(b->bm_pages[idx]))
 		drbd_warn(device, "bitmap page idx %u changed during IO!\n", idx);
 
-	if (error) {
+	if (bio->bi_error) {
 		/* ctx error will hold the completed-last non-zero error code,
 		 * in case error codes differ. */
-		ctx->error = error;
+		ctx->error = bio->bi_error;
 		bm_set_page_io_err(b->bm_pages[idx]);
 		/* Not identical to on disk version of it.
 		 * Is BM_PAGE_IO_ERROR enough? */
 		if (__ratelimit(&drbd_ratelimit_state))
 			drbd_err(device, "IO ERROR %d on bitmap page idx %u\n",
-					error, idx);
+					bio->bi_error, idx);
 	} else {
 		bm_clear_page_io_err(b->bm_pages[idx]);
 		dynamic_drbd_dbg(device, "bitmap page idx %u completed\n", idx);
@@ -1031,7 +1022,7 @@ static void bm_page_io_async(struct drbd_bm_aio_ctx *ctx, int page_nr) __must_ho
 
 	if (drbd_insert_fault(device, (rw & WRITE) ? DRBD_FAULT_MD_WR : DRBD_FAULT_MD_RD)) {
 		bio->bi_rw |= rw;
-		bio_endio(bio, -EIO);
+		bio_io_error(bio);
 	} else {
 		submit_bio(rw, bio);
 		/* this should not count as user activity and cause the
diff --git a/drivers/block/drbd/drbd_int.h b/drivers/block/drbd/drbd_int.h
index efd19c2da9c2..a08c4a9179f1 100644
--- a/drivers/block/drbd/drbd_int.h
+++ b/drivers/block/drbd/drbd_int.h
@@ -1481,9 +1481,9 @@ extern int drbd_khelper(struct drbd_device *device, char *cmd);
 
 /* drbd_worker.c */
 /* bi_end_io handlers */
-extern void drbd_md_endio(struct bio *bio, int error);
-extern void drbd_peer_request_endio(struct bio *bio, int error);
-extern void drbd_request_endio(struct bio *bio, int error);
+extern void drbd_md_endio(struct bio *bio);
+extern void drbd_peer_request_endio(struct bio *bio);
+extern void drbd_request_endio(struct bio *bio);
 extern int drbd_worker(struct drbd_thread *thi);
 enum drbd_ret_code drbd_resync_after_valid(struct drbd_device *device, int o_minor);
 void drbd_resync_after_changed(struct drbd_device *device);
@@ -1604,12 +1604,13 @@ static inline void drbd_generic_make_request(struct drbd_device *device,
 	__release(local);
 	if (!bio->bi_bdev) {
 		drbd_err(device, "drbd_generic_make_request: bio->bi_bdev == NULL\n");
-		bio_endio(bio, -ENODEV);
+		bio->bi_error = -ENODEV;
+		bio_endio(bio);
 		return;
 	}
 
 	if (drbd_insert_fault(device, fault_type))
-		bio_endio(bio, -EIO);
+		bio_io_error(bio);
 	else
 		generic_make_request(bio);
 }
diff --git a/drivers/block/drbd/drbd_req.c b/drivers/block/drbd/drbd_req.c
index 3907202fb9d9..9cb41166366e 100644
--- a/drivers/block/drbd/drbd_req.c
+++ b/drivers/block/drbd/drbd_req.c
@@ -201,7 +201,8 @@ void start_new_tl_epoch(struct drbd_connection *connection)
 void complete_master_bio(struct drbd_device *device,
 		struct bio_and_error *m)
 {
-	bio_endio(m->bio, m->error);
+	m->bio->bi_error = m->error;
+	bio_endio(m->bio);
 	dec_ap_bio(device);
 }
 
@@ -1153,12 +1154,12 @@ drbd_submit_req_private_bio(struct drbd_request *req)
 				      rw == WRITE ? DRBD_FAULT_DT_WR
 				    : rw == READ  ? DRBD_FAULT_DT_RD
 				    :               DRBD_FAULT_DT_RA))
-			bio_endio(bio, -EIO);
+			bio_io_error(bio);
 		else
 			generic_make_request(bio);
 		put_ldev(device);
 	} else
-		bio_endio(bio, -EIO);
+		bio_io_error(bio);
 }
 
 static void drbd_queue_write(struct drbd_device *device, struct drbd_request *req)
@@ -1191,7 +1192,8 @@ drbd_request_prepare(struct drbd_device *device, struct bio *bio, unsigned long
 		/* only pass the error to the upper layers.
 		 * if user cannot handle io errors, that's not our business. */
 		drbd_err(device, "could not kmalloc() req\n");
-		bio_endio(bio, -ENOMEM);
+		bio->bi_error = -ENOMEM;
+		bio_endio(bio);
 		return ERR_PTR(-ENOMEM);
 	}
 	req->start_jif = start_jif;
diff --git a/drivers/block/drbd/drbd_worker.c b/drivers/block/drbd/drbd_worker.c
index d0fae55d871d..5578c1477ba6 100644
--- a/drivers/block/drbd/drbd_worker.c
+++ b/drivers/block/drbd/drbd_worker.c
@@ -65,12 +65,12 @@ rwlock_t global_state_lock;
 /* used for synchronous meta data and bitmap IO
  * submitted by drbd_md_sync_page_io()
  */
-void drbd_md_endio(struct bio *bio, int error)
+void drbd_md_endio(struct bio *bio)
 {
 	struct drbd_device *device;
 
 	device = bio->bi_private;
-	device->md_io.error = error;
+	device->md_io.error = bio->bi_error;
 
 	/* We grabbed an extra reference in _drbd_md_sync_page_io() to be able
 	 * to timeout on the lower level device, and eventually detach from it.
@@ -170,31 +170,20 @@ void drbd_endio_write_sec_final(struct drbd_peer_request *peer_req) __releases(l
 /* writes on behalf of the partner, or resync writes,
  * "submitted" by the receiver.
  */
-void drbd_peer_request_endio(struct bio *bio, int error)
+void drbd_peer_request_endio(struct bio *bio)
 {
 	struct drbd_peer_request *peer_req = bio->bi_private;
 	struct drbd_device *device = peer_req->peer_device->device;
-	int uptodate = bio_flagged(bio, BIO_UPTODATE);
 	int is_write = bio_data_dir(bio) == WRITE;
 	int is_discard = !!(bio->bi_rw & REQ_DISCARD);
 
-	if (error && __ratelimit(&drbd_ratelimit_state))
+	if (bio->bi_error && __ratelimit(&drbd_ratelimit_state))
 		drbd_warn(device, "%s: error=%d s=%llus\n",
 				is_write ? (is_discard ? "discard" : "write")
-					: "read", error,
+					: "read", bio->bi_error,
 				(unsigned long long)peer_req->i.sector);
-	if (!error && !uptodate) {
-		if (__ratelimit(&drbd_ratelimit_state))
-			drbd_warn(device, "%s: setting error to -EIO s=%llus\n",
-					is_write ? "write" : "read",
-					(unsigned long long)peer_req->i.sector);
-		/* strange behavior of some lower level drivers...
-		 * fail the request by clearing the uptodate flag,
-		 * but do not return any error?! */
-		error = -EIO;
-	}
 
-	if (error)
+	if (bio->bi_error)
 		set_bit(__EE_WAS_ERROR, &peer_req->flags);
 
 	bio_put(bio); /* no need for the bio anymore */
@@ -208,24 +197,13 @@ void drbd_peer_request_endio(struct bio *bio, int error)
 
 /* read, readA or write requests on R_PRIMARY coming from drbd_make_request
  */
-void drbd_request_endio(struct bio *bio, int error)
+void drbd_request_endio(struct bio *bio)
 {
 	unsigned long flags;
 	struct drbd_request *req = bio->bi_private;
 	struct drbd_device *device = req->device;
 	struct bio_and_error m;
 	enum drbd_req_event what;
-	int uptodate = bio_flagged(bio, BIO_UPTODATE);
-
-	if (!error && !uptodate) {
-		drbd_warn(device, "p %s: setting error to -EIO\n",
-			 bio_data_dir(bio) == WRITE ? "write" : "read");
-		/* strange behavior of some lower level drivers...
-		 * fail the request by clearing the uptodate flag,
-		 * but do not return any error?! */
-		error = -EIO;
-	}
-
 
 	/* If this request was aborted locally before,
 	 * but now was completed "successfully",
@@ -259,14 +237,14 @@ void drbd_request_endio(struct bio *bio, int error)
 		if (__ratelimit(&drbd_ratelimit_state))
 			drbd_emerg(device, "delayed completion of aborted local request; disk-timeout may be too aggressive\n");
 
-		if (!error)
+		if (!bio->bi_error)
 			panic("possible random memory corruption caused by delayed completion of aborted local request\n");
 	}
 
 	/* to avoid recursion in __req_mod */
-	if (unlikely(error)) {
+	if (unlikely(bio->bi_error)) {
 		if (bio->bi_rw & REQ_DISCARD)
-			what = (error == -EOPNOTSUPP)
+			what = (bio->bi_error == -EOPNOTSUPP)
 				? DISCARD_COMPLETED_NOTSUPP
 				: DISCARD_COMPLETED_WITH_ERROR;
 		else
@@ -279,7 +257,7 @@ void drbd_request_endio(struct bio *bio, int error)
 		what = COMPLETED_OK;
 
 	bio_put(req->private_bio);
-	req->private_bio = ERR_PTR(error);
+	req->private_bio = ERR_PTR(bio->bi_error);
 
 	/* not req_mod(), we need irqsave here! */
 	spin_lock_irqsave(&device->resource->req_lock, flags);