lkml.org 
[lkml]   [2019]   [Dec]   [16]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
Patch in this message
/
From
Subject[PATCH 5.3 135/180] scsi: lpfc: Fix bad ndlp ptr in xri aborted handling
Date
From: James Smart <jsmart2021@gmail.com>

[ Upstream commit 324e1c402069e8d277d2a2b18ce40bde1265b96a ]

In cases where I/O may be aborted, such as driver unload or link bounces,
the system will crash based on a bad ndlp pointer.

Example:
RIP: 0010:lpfc_sli4_abts_err_handler+0x15/0x140 [lpfc]
...
lpfc_sli4_io_xri_aborted+0x20d/0x270 [lpfc]
lpfc_sli4_sp_handle_abort_xri_wcqe.isra.54+0x84/0x170 [lpfc]
lpfc_sli4_fp_handle_cqe+0xc2/0x480 [lpfc]
__lpfc_sli4_process_cq+0xc6/0x230 [lpfc]
__lpfc_sli4_hba_process_cq+0x29/0xc0 [lpfc]
process_one_work+0x14c/0x390

Crash was caused by a bad ndlp address passed to I/O indicated by the XRI
aborted CQE. The address was not NULL so the routine deferenced the ndlp
ptr. The bad ndlp also caused the lpfc_sli4_io_xri_aborted to call an
erroneous io handler. Root cause for the bad ndlp was an lpfc_ncmd that
was aborted, put on the abort_io list, completed, taken off the abort_io
list, sent to lpfc_release_nvme_buf where it was put back on the abort_io
list because the lpfc_ncmd->flags setting LPFC_SBUF_XBUSY was not cleared
on the final completion.

Rework the exchange busy handling to ensure the flags are properly set for
both scsi and nvme.

Fixes: c490850a0947 ("scsi: lpfc: Adapt partitioned XRI lists to efficient sharing")
Cc: <stable@vger.kernel.org> # v5.1+
Link: https://lore.kernel.org/r/20191018211832.7917-6-jsmart2021@gmail.com
Signed-off-by: Dick Kennedy <dick.kennedy@broadcom.com>
Signed-off-by: James Smart <jsmart2021@gmail.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
drivers/scsi/lpfc/lpfc_scsi.c | 11 +++++++----
drivers/scsi/lpfc/lpfc_sli.c | 5 ++++-
drivers/scsi/lpfc/lpfc_sli.h | 3 +--
3 files changed, 12 insertions(+), 7 deletions(-)

diff --git a/drivers/scsi/lpfc/lpfc_scsi.c b/drivers/scsi/lpfc/lpfc_scsi.c
index f9df800e70672..6ba4a741a8053 100644
--- a/drivers/scsi/lpfc/lpfc_scsi.c
+++ b/drivers/scsi/lpfc/lpfc_scsi.c
@@ -583,7 +583,7 @@ lpfc_sli4_fcp_xri_aborted(struct lpfc_hba *phba,
if (psb->cur_iocbq.sli4_xritag == xri) {
list_del(&psb->list);
qp->abts_scsi_io_bufs--;
- psb->exch_busy = 0;
+ psb->flags &= ~LPFC_SBUF_XBUSY;
psb->status = IOSTAT_SUCCESS;
spin_unlock(
&qp->abts_scsi_buf_list_lock);
@@ -615,7 +615,7 @@ lpfc_sli4_fcp_xri_aborted(struct lpfc_hba *phba,
if (iocbq->sli4_xritag != xri)
continue;
psb = container_of(iocbq, struct lpfc_io_buf, cur_iocbq);
- psb->exch_busy = 0;
+ psb->flags &= ~LPFC_SBUF_XBUSY;
spin_unlock_irqrestore(&phba->hbalock, iflag);
if (!list_empty(&pring->txq))
lpfc_worker_wake_up(phba);
@@ -834,7 +834,7 @@ lpfc_release_scsi_buf_s4(struct lpfc_hba *phba, struct lpfc_io_buf *psb)
psb->prot_seg_cnt = 0;

qp = psb->hdwq;
- if (psb->exch_busy) {
+ if (psb->flags & LPFC_SBUF_XBUSY) {
spin_lock_irqsave(&qp->abts_scsi_buf_list_lock, iflag);
psb->pCmd = NULL;
list_add_tail(&psb->list, &qp->lpfc_abts_scsi_buf_list);
@@ -3679,7 +3679,10 @@ lpfc_scsi_cmd_iocb_cmpl(struct lpfc_hba *phba, struct lpfc_iocbq *pIocbIn,
lpfc_cmd->result = (pIocbOut->iocb.un.ulpWord[4] & IOERR_PARAM_MASK);
lpfc_cmd->status = pIocbOut->iocb.ulpStatus;
/* pick up SLI4 exhange busy status from HBA */
- lpfc_cmd->exch_busy = pIocbOut->iocb_flag & LPFC_EXCHANGE_BUSY;
+ if (pIocbOut->iocb_flag & LPFC_EXCHANGE_BUSY)
+ lpfc_cmd->flags |= LPFC_SBUF_XBUSY;
+ else
+ lpfc_cmd->flags &= ~LPFC_SBUF_XBUSY;

#ifdef CONFIG_SCSI_LPFC_DEBUG_FS
if (lpfc_cmd->prot_data_type) {
diff --git a/drivers/scsi/lpfc/lpfc_sli.c b/drivers/scsi/lpfc/lpfc_sli.c
index c7027ecd4d19e..6f6e306ff1e6c 100644
--- a/drivers/scsi/lpfc/lpfc_sli.c
+++ b/drivers/scsi/lpfc/lpfc_sli.c
@@ -11768,7 +11768,10 @@ lpfc_sli_wake_iocb_wait(struct lpfc_hba *phba,
!(cmdiocbq->iocb_flag & LPFC_IO_LIBDFC)) {
lpfc_cmd = container_of(cmdiocbq, struct lpfc_io_buf,
cur_iocbq);
- lpfc_cmd->exch_busy = rspiocbq->iocb_flag & LPFC_EXCHANGE_BUSY;
+ if (rspiocbq && (rspiocbq->iocb_flag & LPFC_EXCHANGE_BUSY))
+ lpfc_cmd->flags |= LPFC_SBUF_XBUSY;
+ else
+ lpfc_cmd->flags &= ~LPFC_SBUF_XBUSY;
}

pdone_q = cmdiocbq->context_un.wait_queue;
diff --git a/drivers/scsi/lpfc/lpfc_sli.h b/drivers/scsi/lpfc/lpfc_sli.h
index 467b8270f7fdd..9449236c231d5 100644
--- a/drivers/scsi/lpfc/lpfc_sli.h
+++ b/drivers/scsi/lpfc/lpfc_sli.h
@@ -375,14 +375,13 @@ struct lpfc_io_buf {

struct lpfc_nodelist *ndlp;
uint32_t timeout;
- uint16_t flags; /* TBD convert exch_busy to flags */
+ uint16_t flags;
#define LPFC_SBUF_XBUSY 0x1 /* SLI4 hba reported XB on WCQE cmpl */
#define LPFC_SBUF_BUMP_QDEPTH 0x2 /* bumped queue depth counter */
/* External DIF device IO conversions */
#define LPFC_SBUF_NORMAL_DIF 0x4 /* normal mode to insert/strip */
#define LPFC_SBUF_PASS_DIF 0x8 /* insert/strip mode to passthru */
#define LPFC_SBUF_NOT_POSTED 0x10 /* SGL failed post to FW. */
- uint16_t exch_busy; /* SLI4 hba reported XB on complete WCQE */
uint16_t status; /* From IOCB Word 7- ulpStatus */
uint32_t result; /* From IOCB Word 4. */

--
2.20.1


\
 
 \ /
  Last update: 2019-12-16 19:13    [W:0.421 / U:1.824 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site