diff mbox series

[v3,1/2] ufs: core: fix ufshcd_clear_cmd racing issue

Message ID 20240628070030.30929-2-peter.wang@mediatek.com
State New
Headers show
Series ufs: core: fix ufshcd_abort_all racing issue | expand

Commit Message

Peter Wang (王信友) June 28, 2024, 7 a.m. UTC 
From: Peter Wang <peter.wang@mediatek.com>

When ufshcd_clear_cmd racing with complete ISR,
the completed tag of request's mq_hctx pointer will set NULL by ISR.
And ufshcd_clear_cmd call ufshcd_mcq_req_to_hwq will get NULL pointer KE.
Return success when request is completed by ISR beacuse sq dosen't
need cleanup.

The racing flow is:

Thread A
ufshcd_err_handler					step 1
	ufshcd_try_to_abort_task
		ufshcd_cmd_inflight(true)		step 3
		ufshcd_clear_cmd
			...
			ufshcd_mcq_req_to_hwq
			blk_mq_unique_tag
				rq->mq_hctx->queue_num	step 5

Thread B
ufs_mtk_mcq_intr(cq complete ISR)			step 2
	scsi_done
		...
		__blk_mq_free_request
			rq->mq_hctx = NULL;		step 4

Below is KE back trace:

  ufshcd_try_to_abort_task: cmd pending in the device. tag = 6
  Unable to handle kernel NULL pointer dereference at virtual address 0000000000000194
   pc : [0xffffffd589679bf8] blk_mq_unique_tag+0x8/0x14
   lr : [0xffffffd5862f95b4] ufshcd_mcq_sq_cleanup+0x6c/0x1cc [ufs_mediatek_mod_ise]
   Workqueue: ufs_eh_wq_0 ufshcd_err_handler [ufs_mediatek_mod_ise]
   Call trace:
    dump_backtrace+0xf8/0x148
    show_stack+0x18/0x24
    dump_stack_lvl+0x60/0x7c
    dump_stack+0x18/0x3c
    mrdump_common_die+0x24c/0x398 [mrdump]
    ipanic_die+0x20/0x34 [mrdump]
    notify_die+0x80/0xd8
    die+0x94/0x2b8
    __do_kernel_fault+0x264/0x298
    do_page_fault+0xa4/0x4b8
    do_translation_fault+0x38/0x54
    do_mem_abort+0x58/0x118
    el1_abort+0x3c/0x5c
    el1h_64_sync_handler+0x54/0x90
    el1h_64_sync+0x68/0x6c
    blk_mq_unique_tag+0x8/0x14
    ufshcd_clear_cmd+0x34/0x118 [ufs_mediatek_mod_ise]
    ufshcd_try_to_abort_task+0x2c8/0x5b4 [ufs_mediatek_mod_ise]
    ufshcd_err_handler+0xa7c/0xfa8 [ufs_mediatek_mod_ise]
    process_one_work+0x208/0x4fc
    worker_thread+0x228/0x438
    kthread+0x104/0x1d4
    ret_from_fork+0x10/0x20

Fixes: 8d7290348992 ("scsi: ufs: mcq: Add supporting functions for MCQ abort")
Cc: <stable@vger.kernel.org> 6.6.x
Suggested-by: Bart Van Assche <bvanassche@acm.org>
Signed-off-by: Peter Wang <peter.wang@mediatek.com>
---
 drivers/ufs/core/ufs-mcq.c | 11 ++++++-----
 1 file changed, 6 insertions(+), 5 deletions(-)
diff mbox series

Patch

diff --git a/drivers/ufs/core/ufs-mcq.c b/drivers/ufs/core/ufs-mcq.c
index 8944548c30fa..c532416aec22 100644
--- a/drivers/ufs/core/ufs-mcq.c
+++ b/drivers/ufs/core/ufs-mcq.c
@@ -105,16 +105,15 @@  EXPORT_SYMBOL_GPL(ufshcd_mcq_config_mac);
  * @hba: per adapter instance
  * @req: pointer to the request to be issued
  *
- * Return: the hardware queue instance on which the request would
- * be queued.
+ * Return: the hardware queue instance on which the request will be or has
+ * been queued. %NULL if the request has already been freed.
  */
 struct ufs_hw_queue *ufshcd_mcq_req_to_hwq(struct ufs_hba *hba,
 					 struct request *req)
 {
-	u32 utag = blk_mq_unique_tag(req);
-	u32 hwq = blk_mq_unique_tag_to_hwq(utag);
+	struct blk_mq_hw_ctx *hctx = READ_ONCE(req->mq_hctx);
 
-	return &hba->uhq[hwq];
+	return hctx ? &hba->uhq[hctx->queue_num] : NULL;
 }
 
 /**
@@ -515,6 +514,8 @@  int ufshcd_mcq_sq_cleanup(struct ufs_hba *hba, int task_tag)
 		if (!cmd)
 			return -EINVAL;
 		hwq = ufshcd_mcq_req_to_hwq(hba, scsi_cmd_to_rq(cmd));
+		if (!hwq)
+			return 0;
 	} else {
 		hwq = hba->dev_cmd_queue;
 	}