@@ -203,28 +203,42 @@ static void bsg_request_fn(struct request_queue *q)
spin_lock_irq(q->queue_lock);
}
-static int bsg_init_rq(struct request_queue *q, struct request *req, gfp_t gfp)
+static int bsg_init_job(struct request_queue *q, struct request *req, gfp_t gfp)
{
struct bsg_job *job = blk_mq_rq_to_pdu(req);
struct scsi_request *sreq = &job->sreq;
- memset(job, 0, sizeof(*job));
+ /* called right after the request is allocated for the request_queue */
- scsi_req_init(sreq);
- sreq->sense_len = SCSI_SENSE_BUFFERSIZE;
- sreq->sense = kzalloc(sreq->sense_len, gfp);
+ sreq->sense = kzalloc(SCSI_SENSE_BUFFERSIZE, gfp);
if (!sreq->sense)
return -ENOMEM;
- job->req = req;
- job->reply = sreq->sense;
- job->reply_len = sreq->sense_len;
- job->dd_data = job + 1;
-
return 0;
}
-static void bsg_exit_rq(struct request_queue *q, struct request *req)
+static void bsg_init_rq(struct request *req)
+{
+ struct bsg_job *job = blk_mq_rq_to_pdu(req);
+ struct scsi_request *sreq = &job->sreq;
+ void *sense = sreq->sense;
+
+ /* called right before the request is given to the request_queue user */
+
+ memset(job, 0, sizeof(*job));
+
+ scsi_req_init(sreq);
+
+ sreq->sense = sense;
+ sreq->sense_len = SCSI_SENSE_BUFFERSIZE;
+
+ job->req = req;
+ job->reply = sense;
+ job->reply_len = sreq->sense_len;
+ job->dd_data = job + 1;
+}
+
+static void bsg_exit_job(struct request_queue *q, struct request *req)
{
struct bsg_job *job = blk_mq_rq_to_pdu(req);
struct scsi_request *sreq = &job->sreq;
@@ -250,8 +264,9 @@ struct request_queue *bsg_setup_queue(struct device *dev, const char *name,
if (!q)
return ERR_PTR(-ENOMEM);
q->cmd_size = sizeof(struct bsg_job) + dd_job_size;
- q->init_rq_fn = bsg_init_rq;
- q->exit_rq_fn = bsg_exit_rq;
+ q->init_rq_fn = bsg_init_job;
+ q->exit_rq_fn = bsg_exit_job;
+ q->initialize_rq_fn = bsg_init_rq;
q->request_fn = bsg_request_fn;
ret = blk_init_allocated_queue(q);
When under memory-pressure it is possible that the mempool which backs the 'struct request_queue' will make use of up to BLKDEV_MIN_RQ count emergency buffers - in case it can't get a regular allocation. These buffers are preallocated and once they are also used, they are re-supplied with old finished requests from the same request_queue (see mempool_free()). The bug is, when re-supplying the emergency pool, the old requests are not again ran through the callback mempool_t->alloc(), and thus also not through the callback bsg_init_rq(). Thus we skip initialization, and while the sense-buffer still should be good, scsi_request->cmd might have become to be an invalid pointer in the meantime. When the request is initialized in bsg.c, and the user's CDB is larger than BLK_MAX_CDB, bsg will replace it with a custom allocated buffer, which is freed when the user's command is finished, thus it dangles afterwards. When next a command is sent by the user that has a smaller/similar CDB as BLK_MAX_CDB, bsg will assume that scsi_request->cmd is backed by scsi_request->__cmd, will not make a custom allocation, and write into undefined memory. Fix this by splitting bsg_init_rq() into two functions: - bsg_init_job() directly replace bsg_init_rq() and only does the allocation of the sense-buffer, which is used to back the bsg job's reply buffer. This pointer should never change during the lifetime of a scsi_request, so it doesn't need re-initialization. - bsg_init_rq() is a new function that make use of 'struct request_queue's initialize_rq_fn callback (which was introduced in v4.12). This is always called before the request is given out via blk_get_request(). This function does the remaining initialization that was previously done in bsg_init_rq(), and will also do it when the request is taken from the emergency-pool of the backing mempool. Also rename bsg_exit_rq() into bsg_exit_job(), to make it fit the name-scheme. Fixes: 50b4d485528d ("bsg-lib: fix kernel panic resulting from missing allocation of reply-buffer") Cc: <stable@vger.kernel.org> # 4.11+ Signed-off-by: Benjamin Block <bblock@linux.vnet.ibm.com> --- Notes: I did test this on zFCP with FC CT commands send via the ioctl() and write() system-call. That did work fine. But I would very much appreciate if anyone could run this against an other HBA or even an other implementer of bsg-lib, such as now SAS, because I have no access to such hardware here. This should make no difference to the normal cases - where each request is allocated via slab - with- or without this patch; if I didn't miss anything. Only the order is a bit mixed up - the memset is done after the sense-allocation, so I have to buffer the sense-pointer for that. But otherwise there is no difference I am aware of, so it should behave the same (does for me). I could not reproduce the memory-pressure case here in the lab.. I don't see any reason why it should work now, but I am open to suggestions :) Beste Grüße / Best regards, - Benjamin Block block/bsg-lib.c | 41 ++++++++++++++++++++++++++++------------- 1 file changed, 28 insertions(+), 13 deletions(-)