On 2017年03月08日 16:45, lixiubo@xxxxxxxxxxxxxxxxxxxx wrote:
From: Xiubo Li <lixiubo@xxxxxxxxxxxxxxxxxxxx>
The t_data_nents and t_bidi_data_nents are all the numbers of the
segments, and we couldn't be sure the size of the data area block
will equal to size of the segment.
Use the actually block number needed intead of the sum of segments.
Signed-off-by: Xiubo Li <lixiubo@xxxxxxxxxxxxxxxxxxxx>
---
drivers/target/target_core_user.c | 3 +--
1 file changed, 1 insertion(+), 2 deletions(-)
diff --git a/drivers/target/target_core_user.c b/drivers/target/target_core_user.c
index 99cd239..117be07 100644
--- a/drivers/target/target_core_user.c
+++ b/drivers/target/target_core_user.c
@@ -650,8 +650,7 @@ static bool is_ring_space_avail(struct tcmu_dev *udev, struct tcmu_cmd *cmd,
* expensive to tell how many regions are freed in the bitmap
*/
base_command_size = max(offsetof(struct tcmu_cmd_entry,
- req.iov[se_cmd->t_bidi_data_nents +
- se_cmd->t_data_nents]),
+ req.iov[tcmu_cmd->dbi_len]),
For the old code:
If the segment size is larger than the DATA_BLOCK_SIZE, and at the same
time all the
data blocks won't be continues between each other(that to say each block
will use
one iov: iov_cnt == block cnt > nents), the entry's cdb data will
overlap with entry's
iov[] data.
Thanks,
BRs
Xiubo
sizeof(struct tcmu_cmd_entry));
command_size = base_command_size
+ round_up(scsi_command_size(se_cmd->t_task_cdb), TCMU_OP_ALIGN_SIZE);
