From: John Garry <john.garry@huawei.com>
To: <jejb@linux.vnet.ibm.com>, <martin.petersen@oracle.com>
Cc: <john.garry2@mail.dcu.ie>, <linuxarm@huawei.com>,
<linux-scsi@vger.kernel.org>, <linux-kernel@vger.kernel.org>,
<zhangfei.gao@linaro.org>, Xiang Chen <chenxiang66@hisilicon.com>,
John Garry <john.garry@huawei.com>
Subject: [PATCH 6/6] scsi: hisi_sas: controller reset for multi-bits ECC and AXI fatal errors
Date: Mon, 10 Apr 2017 21:22:01 +0800 [thread overview]
Message-ID: <1491830521-21437-7-git-send-email-john.garry@huawei.com> (raw)
In-Reply-To: <1491830521-21437-1-git-send-email-john.garry@huawei.com>
From: Xiang Chen <chenxiang66@hisilicon.com>
For 1 bit ECC errors, those errors can be recovered by hw. But for
multi-bits ECC and AXI errors, there are something wrong with whole
module or system, so try reset the controller to recover those errors
instead of calling panic().
Signed-off-by: Xiang Chen <chenxiang66@hisilicon.com>
Signed-off-by: John Garry <john.garry@huawei.com>
---
drivers/scsi/hisi_sas/hisi_sas_v2_hw.c | 93 ++++++++++++++++++++--------------
1 file changed, 56 insertions(+), 37 deletions(-)
diff --git a/drivers/scsi/hisi_sas/hisi_sas_v2_hw.c b/drivers/scsi/hisi_sas/hisi_sas_v2_hw.c
index cc5675b..89d0959 100644
--- a/drivers/scsi/hisi_sas/hisi_sas_v2_hw.c
+++ b/drivers/scsi/hisi_sas/hisi_sas_v2_hw.c
@@ -2918,94 +2918,105 @@ static void multi_bit_ecc_error_process_v2_hw(struct hisi_hba *hisi_hba,
if (irq_value & BIT(SAS_ECC_INTR_DQE_ECC_MB_OFF)) {
reg_val = hisi_sas_read32(hisi_hba, HGC_DQE_ECC_ADDR);
- panic("%s: hgc_dqe_accbad_intr (0x%x) found: \
+ dev_warn(dev, "hgc_dqe_accbad_intr (0x%x) found: \
Ram address is 0x%08X\n",
- dev_name(dev), irq_value,
+ irq_value,
(reg_val & HGC_DQE_ECC_MB_ADDR_MSK) >>
HGC_DQE_ECC_MB_ADDR_OFF);
+ queue_work(hisi_hba->wq, &hisi_hba->rst_work);
}
if (irq_value & BIT(SAS_ECC_INTR_IOST_ECC_MB_OFF)) {
reg_val = hisi_sas_read32(hisi_hba, HGC_IOST_ECC_ADDR);
- panic("%s: hgc_iost_accbad_intr (0x%x) found: \
+ dev_warn(dev, "hgc_iost_accbad_intr (0x%x) found: \
Ram address is 0x%08X\n",
- dev_name(dev), irq_value,
+ irq_value,
(reg_val & HGC_IOST_ECC_MB_ADDR_MSK) >>
HGC_IOST_ECC_MB_ADDR_OFF);
+ queue_work(hisi_hba->wq, &hisi_hba->rst_work);
}
if (irq_value & BIT(SAS_ECC_INTR_ITCT_ECC_MB_OFF)) {
reg_val = hisi_sas_read32(hisi_hba, HGC_ITCT_ECC_ADDR);
- panic("%s: hgc_itct_accbad_intr (0x%x) found: \
+ dev_warn(dev,"hgc_itct_accbad_intr (0x%x) found: \
Ram address is 0x%08X\n",
- dev_name(dev), irq_value,
+ irq_value,
(reg_val & HGC_ITCT_ECC_MB_ADDR_MSK) >>
HGC_ITCT_ECC_MB_ADDR_OFF);
+ queue_work(hisi_hba->wq, &hisi_hba->rst_work);
}
if (irq_value & BIT(SAS_ECC_INTR_IOSTLIST_ECC_MB_OFF)) {
reg_val = hisi_sas_read32(hisi_hba, HGC_LM_DFX_STATUS2);
- panic("%s: hgc_iostl_accbad_intr (0x%x) found: \
+ dev_warn(dev, "hgc_iostl_accbad_intr (0x%x) found: \
memory address is 0x%08X\n",
- dev_name(dev), irq_value,
+ irq_value,
(reg_val & HGC_LM_DFX_STATUS2_IOSTLIST_MSK) >>
HGC_LM_DFX_STATUS2_IOSTLIST_OFF);
+ queue_work(hisi_hba->wq, &hisi_hba->rst_work);
}
if (irq_value & BIT(SAS_ECC_INTR_ITCTLIST_ECC_MB_OFF)) {
reg_val = hisi_sas_read32(hisi_hba, HGC_LM_DFX_STATUS2);
- panic("%s: hgc_itctl_accbad_intr (0x%x) found: \
+ dev_warn(dev, "hgc_itctl_accbad_intr (0x%x) found: \
memory address is 0x%08X\n",
- dev_name(dev), irq_value,
+ irq_value,
(reg_val & HGC_LM_DFX_STATUS2_ITCTLIST_MSK) >>
HGC_LM_DFX_STATUS2_ITCTLIST_OFF);
+ queue_work(hisi_hba->wq, &hisi_hba->rst_work);
}
if (irq_value & BIT(SAS_ECC_INTR_CQE_ECC_MB_OFF)) {
reg_val = hisi_sas_read32(hisi_hba, HGC_CQE_ECC_ADDR);
- panic("%s: hgc_cqe_accbad_intr (0x%x) found: \
+ dev_warn(dev, "hgc_cqe_accbad_intr (0x%x) found: \
Ram address is 0x%08X\n",
- dev_name(dev), irq_value,
+ irq_value,
(reg_val & HGC_CQE_ECC_MB_ADDR_MSK) >>
HGC_CQE_ECC_MB_ADDR_OFF);
+ queue_work(hisi_hba->wq, &hisi_hba->rst_work);
}
if (irq_value & BIT(SAS_ECC_INTR_NCQ_MEM0_ECC_MB_OFF)) {
reg_val = hisi_sas_read32(hisi_hba, HGC_RXM_DFX_STATUS14);
- panic("%s: rxm_mem0_accbad_intr (0x%x) found: \
+ dev_warn(dev, "rxm_mem0_accbad_intr (0x%x) found: \
memory address is 0x%08X\n",
- dev_name(dev), irq_value,
+ irq_value,
(reg_val & HGC_RXM_DFX_STATUS14_MEM0_MSK) >>
HGC_RXM_DFX_STATUS14_MEM0_OFF);
+ queue_work(hisi_hba->wq, &hisi_hba->rst_work);
}
if (irq_value & BIT(SAS_ECC_INTR_NCQ_MEM1_ECC_MB_OFF)) {
reg_val = hisi_sas_read32(hisi_hba, HGC_RXM_DFX_STATUS14);
- panic("%s: rxm_mem1_accbad_intr (0x%x) found: \
+ dev_warn(dev, "rxm_mem1_accbad_intr (0x%x) found: \
memory address is 0x%08X\n",
- dev_name(dev), irq_value,
+ irq_value,
(reg_val & HGC_RXM_DFX_STATUS14_MEM1_MSK) >>
HGC_RXM_DFX_STATUS14_MEM1_OFF);
+ queue_work(hisi_hba->wq, &hisi_hba->rst_work);
}
if (irq_value & BIT(SAS_ECC_INTR_NCQ_MEM2_ECC_MB_OFF)) {
reg_val = hisi_sas_read32(hisi_hba, HGC_RXM_DFX_STATUS14);
- panic("%s: rxm_mem2_accbad_intr (0x%x) found: \
+ dev_warn(dev, "rxm_mem2_accbad_intr (0x%x) found: \
memory address is 0x%08X\n",
- dev_name(dev), irq_value,
+ irq_value,
(reg_val & HGC_RXM_DFX_STATUS14_MEM2_MSK) >>
HGC_RXM_DFX_STATUS14_MEM2_OFF);
+ queue_work(hisi_hba->wq, &hisi_hba->rst_work);
}
if (irq_value & BIT(SAS_ECC_INTR_NCQ_MEM3_ECC_MB_OFF)) {
reg_val = hisi_sas_read32(hisi_hba, HGC_RXM_DFX_STATUS15);
- panic("%s: rxm_mem3_accbad_intr (0x%x) found: \
+ dev_warn(dev, "rxm_mem3_accbad_intr (0x%x) found: \
memory address is 0x%08X\n",
- dev_name(dev), irq_value,
+ irq_value,
(reg_val & HGC_RXM_DFX_STATUS15_MEM3_MSK) >>
HGC_RXM_DFX_STATUS15_MEM3_OFF);
+ queue_work(hisi_hba->wq, &hisi_hba->rst_work);
}
+ return;
}
static irqreturn_t fatal_ecc_int_v2_hw(int irq_no, void *p)
@@ -3063,23 +3074,27 @@ static irqreturn_t fatal_axi_int_v2_hw(int irq_no, void *p)
if (irq_value & BIT(ENT_INT_SRC3_WP_DEPTH_OFF)) {
hisi_sas_write32(hisi_hba, ENT_INT_SRC3,
1 << ENT_INT_SRC3_WP_DEPTH_OFF);
- panic("%s: write pointer and depth error (0x%x) \
+ dev_warn(dev, "write pointer and depth error (0x%x) \
found!\n",
- dev_name(dev), irq_value);
+ irq_value);
+ queue_work(hisi_hba->wq, &hisi_hba->rst_work);
}
if (irq_value & BIT(ENT_INT_SRC3_IPTT_SLOT_NOMATCH_OFF)) {
hisi_sas_write32(hisi_hba, ENT_INT_SRC3,
1 <<
ENT_INT_SRC3_IPTT_SLOT_NOMATCH_OFF);
- panic("%s: iptt no match slot error (0x%x) found!\n",
- dev_name(dev), irq_value);
+ dev_warn(dev, "iptt no match slot error (0x%x) found!\n",
+ irq_value);
+ queue_work(hisi_hba->wq, &hisi_hba->rst_work);
}
- if (irq_value & BIT(ENT_INT_SRC3_RP_DEPTH_OFF))
- panic("%s: read pointer and depth error (0x%x) \
+ if (irq_value & BIT(ENT_INT_SRC3_RP_DEPTH_OFF)) {
+ dev_warn(dev, "read pointer and depth error (0x%x) \
found!\n",
- dev_name(dev), irq_value);
+ irq_value);
+ queue_work(hisi_hba->wq, &hisi_hba->rst_work);
+ }
if (irq_value & BIT(ENT_INT_SRC3_AXI_OFF)) {
int i;
@@ -3090,10 +3105,11 @@ static irqreturn_t fatal_axi_int_v2_hw(int irq_no, void *p)
HGC_AXI_FIFO_ERR_INFO);
for (i = 0; i < AXI_ERR_NR; i++) {
- if (err_value & BIT(i))
- panic("%s: %s (0x%x) found!\n",
- dev_name(dev),
+ if (err_value & BIT(i)) {
+ dev_warn(dev, "%s (0x%x) found!\n",
axi_err_info[i], irq_value);
+ queue_work(hisi_hba->wq, &hisi_hba->rst_work);
+ }
}
}
@@ -3106,10 +3122,11 @@ static irqreturn_t fatal_axi_int_v2_hw(int irq_no, void *p)
HGC_AXI_FIFO_ERR_INFO);
for (i = 0; i < FIFO_ERR_NR; i++) {
- if (err_value & BIT(AXI_ERR_NR + i))
- panic("%s: %s (0x%x) found!\n",
- dev_name(dev),
+ if (err_value & BIT(AXI_ERR_NR + i)) {
+ dev_warn(dev, "%s (0x%x) found!\n",
fifo_err_info[i], irq_value);
+ queue_work(hisi_hba->wq, &hisi_hba->rst_work);
+ }
}
}
@@ -3117,15 +3134,17 @@ static irqreturn_t fatal_axi_int_v2_hw(int irq_no, void *p)
if (irq_value & BIT(ENT_INT_SRC3_LM_OFF)) {
hisi_sas_write32(hisi_hba, ENT_INT_SRC3,
1 << ENT_INT_SRC3_LM_OFF);
- panic("%s: LM add/fetch list error (0x%x) found!\n",
- dev_name(dev), irq_value);
+ dev_warn(dev, "LM add/fetch list error (0x%x) found!\n",
+ irq_value);
+ queue_work(hisi_hba->wq, &hisi_hba->rst_work);
}
if (irq_value & BIT(ENT_INT_SRC3_ABT_OFF)) {
hisi_sas_write32(hisi_hba, ENT_INT_SRC3,
1 << ENT_INT_SRC3_ABT_OFF);
- panic("%s: SAS_HGC_ABT fetch LM list error (0x%x) found!\n",
- dev_name(dev), irq_value);
+ dev_warn(dev, "SAS_HGC_ABT fetch LM list error (0x%x) found!\n",
+ irq_value);
+ queue_work(hisi_hba->wq, &hisi_hba->rst_work);
}
}
--
1.9.1
next prev parent reply other threads:[~2017-04-10 12:53 UTC|newest]
Thread overview: 10+ messages / expand[flat|nested] mbox.gz Atom feed top
2017-04-10 13:21 [PATCH 0/6] hisi_sas: v2 hw SoC bug workarounds John Garry
2017-04-10 13:21 ` [PATCH 1/6] scsi: hisi_sas: workaround STP link SoC bug John Garry
2017-04-10 13:16 ` Johannes Thumshirn
2017-04-10 13:21 ` [PATCH 2/6] scsi: hisi_sas: workaround a SoC SATA IO processing bug John Garry
2017-04-10 14:07 ` Johannes Thumshirn
2017-04-10 13:21 ` [PATCH 3/6] scsi: hisi_sas: workaround SoC about abort timeout bug John Garry
2017-04-10 13:21 ` [PATCH 4/6] scsi: hisi_sas: add v2 hw internal abort timeout workaround John Garry
2017-04-10 13:22 ` [PATCH 5/6] scsi: hisi_sas: fix NULL deference when TMF timeouts John Garry
2017-04-10 13:22 ` John Garry [this message]
2017-04-12 2:02 ` [PATCH 0/6] hisi_sas: v2 hw SoC bug workarounds Martin K. Petersen
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=1491830521-21437-7-git-send-email-john.garry@huawei.com \
--to=john.garry@huawei.com \
--cc=chenxiang66@hisilicon.com \
--cc=jejb@linux.vnet.ibm.com \
--cc=john.garry2@mail.dcu.ie \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-scsi@vger.kernel.org \
--cc=linuxarm@huawei.com \
--cc=martin.petersen@oracle.com \
--cc=zhangfei.gao@linaro.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox
all inboxes | Powered by JetHome®