When reset is caused by hbm protocol mismatch or timeout
we might end up in an endless reset loop and hbm protocol
will never sync
Cc: <sta...@vger.kernel.org>
Signed-off-by: Tomas Winkler <tomas.wink...@intel.com>
Signed-off-by: Alexander Usyskin <alexander.usys...@intel.com>
---
drivers/misc/mei/hbm.c | 19 +++++++++++++++++++
drivers/misc/mei/hbm.h | 1 +
drivers/misc/mei/init.c | 12 ++++++++----
drivers/misc/mei/interrupt.c | 25 +++++++++++++++----------
4 files changed, 43 insertions(+), 14 deletions(-)
diff --git a/drivers/misc/mei/hbm.c b/drivers/misc/mei/hbm.c
index 8109b9a..836f92d 100644
--- a/drivers/misc/mei/hbm.c
+++ b/drivers/misc/mei/hbm.c
@@ -126,6 +126,17 @@ static bool is_treat_specially_client(struct mei_cl *cl,
return false;
}
+/**
+ * mei_hbm_idle - set hbm to idle state
+ *
+ * @dev: the device structure
+ */
+void mei_hbm_idle(struct mei_device *dev)
+{
+ dev->init_clients_timer = 0;
+ dev->hbm_state = MEI_HBM_IDLE;
+}
+
int mei_hbm_start_wait(struct mei_device *dev)
{
int ret;
@@ -583,6 +594,14 @@ int mei_hbm_dispatch(struct mei_device *dev, struct
mei_msg_hdr *hdr)
mei_read_slots(dev, dev->rd_msg_buf, hdr->length);
mei_msg = (struct mei_bus_message *)dev->rd_msg_buf;
+ /* ignore spurious message and prevent reset nesting
+ * hbm is put to idle during system reset
+ */
+ if (dev->hbm_state == MEI_HBM_IDLE) {
+ dev_dbg(&dev->pdev->dev, "hbm: state is idle ignore spurious
messages\n");
+ return 0;
+ }
+
switch (mei_msg->hbm_cmd) {
case HOST_START_RES_CMD:
dev_dbg(&dev->pdev->dev, "hbm: start: response message
received.\n");
diff --git a/drivers/misc/mei/hbm.h b/drivers/misc/mei/hbm.h
index f2540ff..5f92188 100644
--- a/drivers/misc/mei/hbm.h
+++ b/drivers/misc/mei/hbm.h
@@ -49,6 +49,7 @@ static inline void mei_hbm_hdr(struct mei_msg_hdr *hdr,
size_t length)
hdr->reserved = 0;
}
+void mei_hbm_idle(struct mei_device *dev);
int mei_hbm_start_req(struct mei_device *dev);
int mei_hbm_start_wait(struct mei_device *dev);
int mei_hbm_cl_flow_control_req(struct mei_device *dev, struct mei_cl *cl);
diff --git a/drivers/misc/mei/init.c b/drivers/misc/mei/init.c
index 71cd209..2af08bf 100644
--- a/drivers/misc/mei/init.c
+++ b/drivers/misc/mei/init.c
@@ -129,14 +129,19 @@ void mei_reset(struct mei_device *dev, int
interrupts_enabled)
dev_warn(&dev->pdev->dev, "unexpected reset: dev_state = %s\n",
mei_dev_state_str(dev->dev_state));
+ /* we're already in reset, cancel the init timer
+ * if the reset was called due the hbm protocol error
+ * we need to call it before hw start
+ * so the hbm watchdog won't kick in
+ */
+ mei_hbm_idle(dev);
+
ret = mei_hw_reset(dev, interrupts_enabled);
if (ret) {
dev_err(&dev->pdev->dev, "hw reset failed disabling the
device\n");
interrupts_enabled = false;
- dev->dev_state = MEI_DEV_DISABLED;
}
- dev->hbm_state = MEI_HBM_IDLE;
if (dev->dev_state != MEI_DEV_INITIALIZING &&
dev->dev_state != MEI_DEV_POWER_UP) {
@@ -161,8 +166,6 @@ void mei_reset(struct mei_device *dev, int
interrupts_enabled)
memset(&dev->wr_ext_msg, 0, sizeof(dev->wr_ext_msg));
}
- /* we're already in reset, cancel the init timer */
- dev->init_clients_timer = 0;
dev->me_clients_num = 0;
dev->rd_msg_hdr = 0;
@@ -170,6 +173,7 @@ void mei_reset(struct mei_device *dev, int
interrupts_enabled)
if (!interrupts_enabled) {
dev_dbg(&dev->pdev->dev, "intr not enabled end of reset\n");
+ dev->dev_state = MEI_DEV_DISABLED;
return;
}
diff --git a/drivers/misc/mei/interrupt.c b/drivers/misc/mei/interrupt.c
index bbb61be..206dbe9 100644
--- a/drivers/misc/mei/interrupt.c
+++ b/drivers/misc/mei/interrupt.c
@@ -537,7 +537,6 @@ EXPORT_SYMBOL_GPL(mei_irq_write_handler);
*
* @work: pointer to the work_struct structure
*
- * NOTE: This function is called by timer interrupt work
*/
void mei_timer(struct work_struct *work)
{
@@ -552,18 +551,24 @@ void mei_timer(struct work_struct *work)
mutex_lock(&dev->device_lock);
- if (dev->dev_state != MEI_DEV_ENABLED) {
- if (dev->dev_state == MEI_DEV_INIT_CLIENTS) {
- if (dev->init_clients_timer) {
- if (--dev->init_clients_timer == 0) {
- dev_err(&dev->pdev->dev, "reset: init
clients timeout hbm_state = %d.\n",
- dev->hbm_state);
- mei_reset(dev, 1);
- }
+
+ /* Catch interrupt stalls during HBM init handshake */
+ if (dev->dev_state == MEI_DEV_INIT_CLIENTS &&
+ dev->hbm_state != MEI_HBM_IDLE) {
+
+ if (dev->init_clients_timer) {
+ if (--dev->init_clients_timer == 0) {
+ dev_err(&dev->pdev->dev, "timer: init clients
timeout hbm_state = %d.\n",
+ dev->hbm_state);
+ mei_reset(dev, 1);
+ goto out;
}
}
- goto out;
}
+
+ if (dev->dev_state != MEI_DEV_ENABLED)
+ goto out;
+
/*** connect/disconnect timeouts ***/
list_for_each_entry_safe(cl_pos, cl_next, &dev->file_list, link) {
if (cl_pos->timer_count) {
--
1.8.4.2
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majord...@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
