[PATCH rdma-rc 1/3] RDMA/hns: Fix the Oops during rmmod or insmod ko when reset occurs

From: Wei Hu (Xavier)
Date: Thu Jan 10 2019 - 08:42:37 EST


In the reset process, the hns3 NIC driver notifies the RoCE driver
to perform reset related processing by calling the .reset_notify()
interface registered by the RoCE driver in hip08 SoC.

In the current version, if a reset occurs simultaneously during
the execution of rmmod or insmod ko, there may be Oops error as below:

[ 650.375307] Internal error: Oops: 86000007 [#1] PREEMPT SMP
[ 650.381223] Modules linked in: hns_roce(O) hns3(O) hclge(O) hnae3(O) [last unloaded: hns_roce_hw_v2]
[ 650.391279] CPU: 0 PID: 14 Comm: kworker/0:1 Tainted: G O 4.19.0-ge00d540 #1
[ 650.399875] Hardware name: Huawei Technologies Co., Ltd.
[ 650.411393] Workqueue: events hclge_reset_service_task [hclge]
[ 650.417576] pstate: 60c00009 (nZCv daif +PAN +UAO)
[ 650.422618] pc : 0xffff00000100b0b8
[ 650.426282] lr : 0xffff00000100aea0
[ 650.429914] sp : ffff000009afbab0
[ 650.433388] x29: ffff000009afbab0 x28: 0000000000000800
[ 650.439012] x27: 0000000000007ff0 x26: ffff80002f90c004
[ 650.444599] x25: 00000000000007ff x24: ffff000008f97000
[ 650.450165] x23: ffff80003efee0a8 x22: 0000000000001000
[ 650.455730] x21: ffff80002f917ff0 x20: ffff8000286ea070
[ 650.461289] x19: 0000000000000800 x18: 0000000000000400
[ 650.466868] x17: 00000000c4d3225d x16: 00000000000021b8
[ 650.472423] x15: 0000000000000400 x14: 0000000000000400
[ 650.477990] x13: 0000000000000000 x12: ffff80003fac6e30
[ 650.483552] x11: 0000800036303000 x10: 0000000000000001
[ 650.489103] x9 : 0000000000000000 x8 : ffff80003016d000
[ 650.494662] x7 : 0000000000000000 x6 : 000000000000003f
[ 650.500218] x5 : 0000000000000040 x4 : 0000000000000000
[ 650.505783] x3 : 0000000000000004 x2 : 00000000000007ff
[ 650.511349] x1 : 0000000000000000 x0 : 0000000000000000
[ 650.517002] Process kworker/0:1 (pid: 14, stack limit = 0x00000000af8f0ad9)
[ 650.524164] Call trace:
[ 650.526814] 0xffff00000100b0b8
[ 650.530108] 0xffff00000100b3a0
[ 650.534336] hns_roce_init+0x624/0xc88 [hns_roce]
[ 650.539196] 0xffff000001002df8
[ 650.542488] 0xffff000001006960
[ 650.546032] hclge_notify_roce_client+0x74/0xe0 [hclge]
[ 650.551637] hclge_reset_service_task+0xa58/0xbc0 [hclge]
[ 650.557479] process_one_work+0x1e4/0x458
[ 650.561738] worker_thread+0x40/0x450
[ 650.565662] kthread+0x12c/0x130
[ 650.569247] ret_from_fork+0x10/0x18
[ 650.573235] Code: bad PC value
[ 650.576663] ---[ end trace 97e6a2fe783337a8 ]---

In the reset process, we will release the resources firstly,
and after the hardware reset is completed, we will reapply
resources and reconfigure the hardware. We can solve this
bug by avoiding simultaneous installation or uninstallation
and reset process.

Fixes: cb7a94c9c808 ("RDMA/hns: Add reset process for RoCE in hip08")
Signed-off-by: Wei Hu (Xavier) <xavier.huwei@xxxxxxxxxx>
---
drivers/infiniband/hw/hns/hns_roce_device.h | 21 +++++
drivers/infiniband/hw/hns/hns_roce_hw_v2.c | 136 +++++++++++++++++++++++++---
drivers/infiniband/hw/hns/hns_roce_hw_v2.h | 7 ++
3 files changed, 151 insertions(+), 13 deletions(-)

diff --git a/drivers/infiniband/hw/hns/hns_roce_device.h b/drivers/infiniband/hw/hns/hns_roce_device.h
index 509e467..f4cac63 100644
--- a/drivers/infiniband/hw/hns/hns_roce_device.h
+++ b/drivers/infiniband/hw/hns/hns_roce_device.h
@@ -216,6 +216,26 @@ enum {
HNS_ROCE_DB_PER_PAGE = PAGE_SIZE / 4
};

+enum hns_roce_reset_stage {
+ HNS_ROCE_STATE_NON_RST,
+ HNS_ROCE_STATE_RST_BEF_DOWN,
+ HNS_ROCE_STATE_RST_DOWN,
+ HNS_ROCE_STATE_RST_UNINIT,
+ HNS_ROCE_STATE_RST_INIT,
+ HNS_ROCE_STATE_RST_INITED,
+};
+
+enum hns_roce_instance_state {
+ HNS_ROCE_STATE_NON_INIT,
+ HNS_ROCE_STATE_INIT,
+ HNS_ROCE_STATE_INITED,
+ HNS_ROCE_STATE_UNINIT,
+};
+
+enum {
+ HNS_ROCE_RST_DIRECT_RETURN = 0,
+};
+
#define HNS_ROCE_CMD_SUCCESS 1

#define HNS_ROCE_PORT_DOWN 0
@@ -898,6 +918,7 @@ struct hns_roce_dev {
spinlock_t bt_cmd_lock;
bool active;
bool is_reset;
+ unsigned long reset_cnt;
struct hns_roce_ib_iboe iboe;

struct list_head pgdir_list;
diff --git a/drivers/infiniband/hw/hns/hns_roce_hw_v2.c b/drivers/infiniband/hw/hns/hns_roce_hw_v2.c
index 3a66945..dadb685 100644
--- a/drivers/infiniband/hw/hns/hns_roce_hw_v2.c
+++ b/drivers/infiniband/hw/hns/hns_roce_hw_v2.c
@@ -5800,6 +5800,7 @@ static int hns_roce_v2_post_srq_recv(struct ib_srq *ibsrq,
static int hns_roce_hw_v2_get_cfg(struct hns_roce_dev *hr_dev,
struct hnae3_handle *handle)
{
+ struct hns_roce_v2_priv *priv = hr_dev->priv;
const struct pci_device_id *id;
int i;

@@ -5830,10 +5831,13 @@ static int hns_roce_hw_v2_get_cfg(struct hns_roce_dev *hr_dev,
hr_dev->cmd_mod = 1;
hr_dev->loop_idc = 0;

+ hr_dev->reset_cnt = handle->ae_algo->ops->ae_dev_reset_cnt(handle);
+ priv->handle = handle;
+
return 0;
}

-static int hns_roce_hw_v2_init_instance(struct hnae3_handle *handle)
+static int __hns_roce_hw_v2_init_instance(struct hnae3_handle *handle)
{
struct hns_roce_dev *hr_dev;
int ret;
@@ -5850,7 +5854,6 @@ static int hns_roce_hw_v2_init_instance(struct hnae3_handle *handle)

hr_dev->pci_dev = handle->pdev;
hr_dev->dev = &handle->pdev->dev;
- handle->priv = hr_dev;

ret = hns_roce_hw_v2_get_cfg(hr_dev, handle);
if (ret) {
@@ -5864,6 +5867,8 @@ static int hns_roce_hw_v2_init_instance(struct hnae3_handle *handle)
goto error_failed_get_cfg;
}

+ handle->priv = hr_dev;
+
return 0;

error_failed_get_cfg:
@@ -5875,7 +5880,7 @@ static int hns_roce_hw_v2_init_instance(struct hnae3_handle *handle)
return ret;
}

-static void hns_roce_hw_v2_uninit_instance(struct hnae3_handle *handle,
+static void __hns_roce_hw_v2_uninit_instance(struct hnae3_handle *handle,
bool reset)
{
struct hns_roce_dev *hr_dev = (struct hns_roce_dev *)handle->priv;
@@ -5883,24 +5888,111 @@ static void hns_roce_hw_v2_uninit_instance(struct hnae3_handle *handle,
if (!hr_dev)
return;

+ handle->priv = NULL;
hns_roce_exit(hr_dev);
kfree(hr_dev->priv);
ib_dealloc_device(&hr_dev->ib_dev);
}

+static int hns_roce_hw_v2_init_instance(struct hnae3_handle *handle)
+{
+ const struct hnae3_ae_ops *ops = handle->ae_algo->ops;
+ struct device *dev = &handle->pdev->dev;
+ int ret;
+
+ handle->rinfo.instance_state = HNS_ROCE_STATE_INIT;
+
+ if (ops->ae_dev_resetting(handle) || ops->get_hw_reset_stat(handle)) {
+ handle->rinfo.instance_state = HNS_ROCE_STATE_NON_INIT;
+ goto reset_chk_err;
+ }
+
+ ret = __hns_roce_hw_v2_init_instance(handle);
+ if (ret) {
+ handle->rinfo.instance_state = HNS_ROCE_STATE_NON_INIT;
+ dev_err(dev, "RoCE instance init failed! ret = %d\n", ret);
+ if (ops->ae_dev_resetting(handle) ||
+ ops->get_hw_reset_stat(handle))
+ goto reset_chk_err;
+ else
+ return ret;
+ }
+
+ handle->rinfo.instance_state = HNS_ROCE_STATE_INITED;
+
+
+ return 0;
+
+reset_chk_err:
+ dev_err(dev, "Device is busy in resetting state.\n"
+ "please retry later.\n");
+
+ return -EBUSY;
+}
+
+static void hns_roce_hw_v2_uninit_instance(struct hnae3_handle *handle,
+ bool reset)
+{
+ const struct hnae3_ae_ops *ops = handle->ae_algo->ops;
+ struct device *dev = &handle->pdev->dev;
+ struct hns_roce_dev *hr_dev;
+ unsigned long end;
+
+ if (handle->rinfo.instance_state != HNS_ROCE_STATE_INITED)
+ return;
+
+ handle->rinfo.instance_state = HNS_ROCE_STATE_UNINIT;
+ hr_dev = (struct hns_roce_dev *)handle->priv;
+ if (!hr_dev)
+ return;
+
+ /* Check the status of the current software reset process, if in
+ * software reset process, wait until software reset process finished,
+ * in order to ensure that reset process and this function will not call
+ * __hns_roce_hw_v2_uninit_instance at the same time.
+ * If a timeout occurs, it indicates that the network subsystem has
+ * encountered a serious error and cannot be recovered from the reset
+ * processing.
+ */
+ if (ops->ae_dev_resetting(handle)) {
+ dev_warn(dev, "Device is busy in resetting state. waiting.\n");
+ end = msecs_to_jiffies(HNS_ROCE_V2_RST_PRC_MAX_TIME) + jiffies;
+ while (ops->ae_dev_resetting(handle) &&
+ time_before(jiffies, end))
+ msleep(20);
+
+ if (!ops->ae_dev_resetting(handle) ||
+ ops->ae_dev_reset_cnt(handle) != hr_dev->reset_cnt)
+ dev_warn(dev, "Device completed reset.\n");
+ else {
+ dev_warn(dev, "Device is still resetting! timeout!\n"
+ "Unrecoverable failure!\n");
+ return;
+ }
+ }
+
+ __hns_roce_hw_v2_uninit_instance(handle, reset);
+
+ handle->rinfo.instance_state = HNS_ROCE_STATE_NON_INIT;
+}
static int hns_roce_hw_v2_reset_notify_down(struct hnae3_handle *handle)
{
- struct hns_roce_dev *hr_dev = (struct hns_roce_dev *)handle->priv;
+ struct hns_roce_dev *hr_dev;
struct ib_event event;

- if (!hr_dev) {
- dev_err(&handle->pdev->dev,
- "Input parameter handle->priv is NULL!\n");
- return -EINVAL;
+ if (handle->rinfo.instance_state != HNS_ROCE_STATE_INITED) {
+ set_bit(HNS_ROCE_RST_DIRECT_RETURN, &handle->rinfo.state);
+ return 0;
}

+ handle->rinfo.reset_state = HNS_ROCE_STATE_RST_DOWN;
+ clear_bit(HNS_ROCE_RST_DIRECT_RETURN, &handle->rinfo.state);
+
+ hr_dev = (struct hns_roce_dev *)handle->priv;
+ if (!hr_dev)
+ return 0;
+
hr_dev->active = false;
- hr_dev->is_reset = true;

event.event = IB_EVENT_DEVICE_FATAL;
event.device = &hr_dev->ib_dev;
@@ -5912,17 +6004,29 @@ static int hns_roce_hw_v2_reset_notify_down(struct hnae3_handle *handle)

static int hns_roce_hw_v2_reset_notify_init(struct hnae3_handle *handle)
{
+ struct device *dev = &handle->pdev->dev;
int ret;

- ret = hns_roce_hw_v2_init_instance(handle);
+ if (test_and_clear_bit(HNS_ROCE_RST_DIRECT_RETURN,
+ &handle->rinfo.state)) {
+ handle->rinfo.reset_state = HNS_ROCE_STATE_RST_INITED;
+ return 0;
+ }
+
+ handle->rinfo.reset_state = HNS_ROCE_STATE_RST_INIT;
+
+ dev_info(&handle->pdev->dev, "In reset process RoCE client reinit.\n");
+ ret = __hns_roce_hw_v2_init_instance(handle);
if (ret) {
/* when reset notify type is HNAE3_INIT_CLIENT In reset notify
* callback function, RoCE Engine reinitialize. If RoCE reinit
* failed, we should inform NIC driver.
*/
handle->priv = NULL;
- dev_err(&handle->pdev->dev,
- "In reset process RoCE reinit failed %d.\n", ret);
+ dev_err(dev, "In reset process RoCE reinit failed %d.\n", ret);
+ } else {
+ handle->rinfo.reset_state = HNS_ROCE_STATE_RST_INITED;
+ dev_info(dev, "Reset done, RoCE client reinit finished.\n");
}

return ret;
@@ -5930,8 +6034,14 @@ static int hns_roce_hw_v2_reset_notify_init(struct hnae3_handle *handle)

static int hns_roce_hw_v2_reset_notify_uninit(struct hnae3_handle *handle)
{
+ if (test_bit(HNS_ROCE_RST_DIRECT_RETURN, &handle->rinfo.state))
+ return 0;
+
+ handle->rinfo.reset_state = HNS_ROCE_STATE_RST_UNINIT;
+ dev_info(&handle->pdev->dev, "In reset process RoCE client uninit.\n");
msleep(100);
- hns_roce_hw_v2_uninit_instance(handle, false);
+ __hns_roce_hw_v2_uninit_instance(handle, false);
+
return 0;
}

diff --git a/drivers/infiniband/hw/hns/hns_roce_hw_v2.h b/drivers/infiniband/hw/hns/hns_roce_hw_v2.h
index b72d044..8def828 100644
--- a/drivers/infiniband/hw/hns/hns_roce_hw_v2.h
+++ b/drivers/infiniband/hw/hns/hns_roce_hw_v2.h
@@ -90,6 +90,12 @@
#define HNS_ROCE_V2_UC_RC_SGE_NUM_IN_WQE 2
#define HNS_ROCE_V2_RSV_QPS 8

+/* The longest time for software reset process in NIC subsystem, if a timeout
+ * occurs, it indicates that the network subsystem has encountered a serious
+ * error and cannot be recovered from the reset processing.
+ */
+#define HNS_ROCE_V2_RST_PRC_MAX_TIME 300000
+
#define HNS_ROCE_CONTEXT_HOP_NUM 1
#define HNS_ROCE_MTT_HOP_NUM 1
#define HNS_ROCE_CQE_HOP_NUM 1
@@ -1546,6 +1552,7 @@ struct hns_roce_link_table_entry {
#define HNS_ROCE_LINK_TABLE_NXT_PTR_M GENMASK(31, 20)

struct hns_roce_v2_priv {
+ struct hnae3_handle *handle;
struct hns_roce_v2_cmq cmq;
struct hns_roce_link_table tsq;
struct hns_roce_link_table tpq;
--
1.9.1