Fix "verify bad_hdr rand_seed" for requeued I/Os

On configurations that can cause I/Os to be internally requeued from
FIO_Q_BUSY such as '--iodepth_batch_complete_max', and the workload has
verify enabled, the subsequent verification of the data fails with a bad
verify rand_seed because the pattern for the I/O is generated twice for
the same I/O, causing the seed to become out of sync when the verify is
later performed. The seed is generate twice because do_io() handles the
I/O twice, first when it originates the I/O and again when it later gets
the same I/O back from get_io_u() after it's is pulled from the requeue
list, which is where the first submission landed due to the workload
reaching '--iodepth_batch_complete_max'.

The fix is for do_io() to track when it has generated the verify pattern
for an I/O via a new io_u flag 'IO_U_F_PATTERN_DONE', avoiding a second
call to populate_verify_io_u() when that flag is detected.

Link: axboe#1526

Signed-off-by: Adam Horshack (horshack@live.com)

backend.c

@@ -1040,8 +1040,11 @@ static void do_io(struct thread_data *td, uint64_t *bytes_done)
 		}
 
 		if (io_u->ddir == DDIR_WRITE && td->flags & TD_F_DO_VERIFY) {
-			io_u->numberio = td->io_issues[io_u->ddir];
-			populate_verify_io_u(td, io_u);
+			if (!(io_u->flags & IO_U_F_PATTERN_DONE)) {
+				io_u_set(td, io_u, IO_U_F_PATTERN_DONE);
+				io_u->numberio = td->io_issues[io_u->ddir];
+				populate_verify_io_u(td, io_u);
+			}
 		}
 
 		ddir = io_u->ddir;

io_u.c

@@ -2004,7 +2004,7 @@ static void io_completed(struct thread_data *td, struct io_u **io_u_ptr,
 	dprint_io_u(io_u, "complete");
 
 	assert(io_u->flags & IO_U_F_FLIGHT);
-	io_u_clear(td, io_u, IO_U_F_FLIGHT | IO_U_F_BUSY_OK);
+	io_u_clear(td, io_u, IO_U_F_FLIGHT | IO_U_F_BUSY_OK | IO_U_F_PATTERN_DONE);
 
 	/*
 	 * Mark IO ok to verify

io_u.h

@@ -21,6 +21,7 @@ enum {
 	IO_U_F_TRIMMED		= 1 << 5,
 	IO_U_F_BARRIER		= 1 << 6,
 	IO_U_F_VER_LIST		= 1 << 7,
+	IO_U_F_PATTERN_DONE = 1 << 8,
 };
 
 /*