From 36822124f9de200cedc2f42516301b50d386a6cd Mon Sep 17 00:00:00 2001 From: Mason Zhang Date: Fri, 16 Dec 2022 11:25:33 +0800 Subject: [PATCH] scsi: ufs: core: Fix device management cmd timeout flow In the UFS error handling flow, the host will send a device management cmd (NOP OUT) to the device for link recovery. If this cmd times out and clearing the doorbell fails, ufshcd_wait_for_dev_cmd() will do nothing and return. hba->dev_cmd.complete struct is not set to NULL. When this happens, if cmd has been completed by device, then we will call complete() in __ufshcd_transfer_req_compl(). Because the complete struct is allocated on the stack, the following crash will occur: ipanic_die+0x24/0x38 [mrdump] die+0x344/0x748 arm64_notify_die+0x44/0x104 do_debug_exception+0x104/0x1e0 el1_dbg+0x38/0x54 el1_sync_handler+0x40/0x88 el1_sync+0x8c/0x140 queued_spin_lock_slowpath+0x2e4/0x3c0 __ufshcd_transfer_req_compl+0x3b0/0x1164 ufshcd_trc_handler+0x15c/0x308 ufshcd_host_reset_and_restore+0x54/0x260 ufshcd_reset_and_restore+0x28c/0x57c ufshcd_err_handler+0xeb8/0x1b6c process_one_work+0x288/0x964 worker_thread+0x4bc/0xc7c kthread+0x15c/0x264 ret_from_fork+0x10/0x30 Link: https://lore.kernel.org/r/20221216032532.1280-1-mason.zhang@mediatek.com Signed-off-by: Mason Zhang Reviewed-by: Bart Van Assche Signed-off-by: Martin K. Petersen --- drivers/ufs/core/ufshcd.c | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) diff --git a/drivers/ufs/core/ufshcd.c b/drivers/ufs/core/ufshcd.c index 0ba2754..625cacc 100644 --- a/drivers/ufs/core/ufshcd.c +++ b/drivers/ufs/core/ufshcd.c @@ -3109,6 +3109,22 @@ retry: } else { dev_err(hba->dev, "%s: failed to clear tag %d\n", __func__, lrbp->task_tag); + + spin_lock_irqsave(&hba->outstanding_lock, flags); + pending = test_bit(lrbp->task_tag, + &hba->outstanding_reqs); + if (pending) + hba->dev_cmd.complete = NULL; + spin_unlock_irqrestore(&hba->outstanding_lock, flags); + + if (!pending) { + /* + * The completion handler ran while we tried to + * clear the command. + */ + time_left = 1; + goto retry; + } } } -- 2.7.4