From: James Smart <jsmart2021@gmail.com>
Date: Fri, 15 Nov 2019 16:38:47 -0800
Subject: [PATCH] scsi: lpfc: use hdwq assigned cpu for allocation
Git-commit: 4583a4f66b323c6e4d774be2649e83a4e7c7b78c
Patch-Mainline: v5.5-rc1
References: bsc#1157160
Looking at the recent conversion from smp_processor_id() to
raw_smp_processor_id(), realized that the allocation should be based on the
cpu the hdwq is bound to, not the executing cpu.
Revise to pull cpu number from the hdwq
Fixes: 765ab6cdac3b ("scsi: lpfc: Fix a kernel warning triggered by lpfc_get_sgl_per_hdwq()")
Link: https://lore.kernel.org/r/20191116003847.6141-1-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>
Acked-by: Hannes Reinecke <hare@suse.de>
---
drivers/scsi/lpfc/lpfc_sli.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/drivers/scsi/lpfc/lpfc_sli.c b/drivers/scsi/lpfc/lpfc_sli.c
index 5286c78645ac..7c8527bd1677 100644
--- a/drivers/scsi/lpfc/lpfc_sli.c
+++ b/drivers/scsi/lpfc/lpfc_sli.c
@@ -20668,7 +20668,7 @@ lpfc_get_sgl_per_hdwq(struct lpfc_hba *phba, struct lpfc_io_buf *lpfc_buf)
/* allocate more */
spin_unlock_irqrestore(&hdwq->hdwq_lock, iflags);
tmp = kmalloc_node(sizeof(*tmp), GFP_ATOMIC,
- cpu_to_node(raw_smp_processor_id()));
+ cpu_to_node(hdwq->io_wq->chann));
if (!tmp) {
lpfc_printf_log(phba, KERN_INFO, LOG_SLI,
"8353 error kmalloc memory for HDWQ "
@@ -20811,7 +20811,7 @@ lpfc_get_cmd_rsp_buf_per_hdwq(struct lpfc_hba *phba,
/* allocate more */
spin_unlock_irqrestore(&hdwq->hdwq_lock, iflags);
tmp = kmalloc_node(sizeof(*tmp), GFP_ATOMIC,
- cpu_to_node(raw_smp_processor_id()));
+ cpu_to_node(hdwq->io_wq->chann));
if (!tmp) {
lpfc_printf_log(phba, KERN_INFO, LOG_SLI,
"8355 error kmalloc memory for HDWQ "
--
2.16.4