From eeb1b55b6e25c5f7265ff45cd050f3bc2cc423a4 Mon Sep 17 00:00:00 2001 From: Jaegeuk Kim Date: Thu, 7 Jan 2021 10:53:16 -0800 Subject: [PATCH] scsi: ufs: Fix tm request when non-fatal error happens When non-fatal error like line-reset happens, ufshcd_err_handler() starts to abort tasks by ufshcd_try_to_abort_task(). When it tries to issue a task management request, we hit two warnings: WARNING: CPU: 7 PID: 7 at block/blk-core.c:630 blk_get_request+0x68/0x70 WARNING: CPU: 4 PID: 157 at block/blk-mq-tag.c:82 blk_mq_get_tag+0x438/0x46c After fixing the above warnings we hit another tm_cmd timeout which may be caused by unstable controller state: __ufshcd_issue_tm_cmd: task management cmd 0x80 timed-out Then, ufshcd_err_handler() enters full reset, and kernel gets stuck. It turned out ufshcd_print_trs() printed too many messages on console which requires CPU locks. Likewise hba->silence_err_logs, we need to avoid too verbose messages. This is actually not an error case. Link: https://lore.kernel.org/r/20210107185316.788815-3-jaegeuk@kernel.org Fixes: 69a6c269c097 ("scsi: ufs: Use blk_{get,put}_request() to allocate and free TMFs") Reviewed-by: Can Guo Signed-off-by: Jaegeuk Kim Signed-off-by: Martin K. Petersen --- drivers/scsi/ufs/ufshcd.c | 18 +++++++++++++----- 1 file changed, 13 insertions(+), 5 deletions(-) diff --git a/drivers/scsi/ufs/ufshcd.c b/drivers/scsi/ufs/ufshcd.c index cff4f52..fb32d12 100644 --- a/drivers/scsi/ufs/ufshcd.c +++ b/drivers/scsi/ufs/ufshcd.c @@ -4994,7 +4994,8 @@ ufshcd_transfer_rsp_status(struct ufs_hba *hba, struct ufshcd_lrb *lrbp) break; } /* end of switch */ - if ((host_byte(result) != DID_OK) && !hba->silence_err_logs) + if ((host_byte(result) != DID_OK) && + (host_byte(result) != DID_REQUEUE) && !hba->silence_err_logs) ufshcd_print_trs(hba, 1 << lrbp->task_tag, true); return result; } @@ -6300,9 +6301,13 @@ static irqreturn_t ufshcd_intr(int irq, void *__hba) intr_status = ufshcd_readl(hba, REG_INTERRUPT_STATUS); } - if (enabled_intr_status && retval == IRQ_NONE) { - dev_err(hba->dev, "%s: Unhandled interrupt 0x%08x\n", - __func__, intr_status); + if (enabled_intr_status && retval == IRQ_NONE && + !ufshcd_eh_in_progress(hba)) { + dev_err(hba->dev, "%s: Unhandled interrupt 0x%08x (0x%08x, 0x%08x)\n", + __func__, + intr_status, + hba->ufs_stats.last_intr_status, + enabled_intr_status); ufshcd_dump_regs(hba, 0, UFSHCI_REG_SPACE_SIZE, "host_regs: "); } @@ -6346,7 +6351,10 @@ static int __ufshcd_issue_tm_cmd(struct ufs_hba *hba, * Even though we use wait_event() which sleeps indefinitely, * the maximum wait time is bounded by %TM_CMD_TIMEOUT. */ - req = blk_get_request(q, REQ_OP_DRV_OUT, BLK_MQ_REQ_RESERVED); + req = blk_get_request(q, REQ_OP_DRV_OUT, 0); + if (IS_ERR(req)) + return PTR_ERR(req); + req->end_io_data = &wait; free_slot = req->tag; WARN_ON_ONCE(free_slot < 0 || free_slot >= hba->nutmrs); -- 2.7.4