If we cannot setup a cmd because we run out of ring space
or global pages release the blocks before sleeping. This
prevents a deadlock where dev0 has waiting_blocks set and
needs N blocks, but dev1 to devX have each allocated N / X blocks
and also hit the global block limit so they went to sleep.
find_free_blocks is not able to take the sleeping dev's
blocks becaause their waiting_blocks is set and even
if it was not the block returned by find_last_bit could equal
dbi_max. The latter will probably never happen because
DATA_BLOCK_BITS is so high but in the next patches
DATA_BLOCK_BITS and TCMU_GLOBAL_MAX_BLOCKS will be settable so
it might be lower and could happen.
Signed-off-by: Mike Christie <mchristi@xxxxxxxxxx>
---
drivers/target/target_core_user.c | 7 +++++++
1 file changed, 7 insertions(+)
diff --git a/drivers/target/target_core_user.c b/drivers/target/target_core_user.c
index 5226b82..612ac65 100644
--- a/drivers/target/target_core_user.c
+++ b/drivers/target/target_core_user.c
@@ -806,6 +806,13 @@ static int tcmu_setup_cmd_timer(struct tcmu_cmd *tcmu_cmd)
int ret;
DEFINE_WAIT(__wait);
+ /*
+ * Don't leave commands partially setup because the unmap
+ * thread might need the blocks to make forward progress.
+ */
+ tcmu_cmd_free_data(tcmu_cmd, tcmu_cmd->dbi_cur);
+ tcmu_cmd_reset_dbi_cur(tcmu_cmd);
+
prepare_to_wait(&udev->wait_cmdr, &__wait, TASK_INTERRUPTIBLE);
pr_debug("sleeping for ring space\n");
--
1.8.3.1
