drm/i915/guc: Add stall timer to non blocking CTB send function

Implement a stall timer which fails H2G CTBs once a period of time
with no forward progress is reached to prevent deadlock.

v2:
 (Michal)
  - Improve error message in ct_deadlock()
  - Set broken when ct_deadlock() returns true
  - Return -EPIPE on ct_deadlock()
v3:
 (Michal)
  - Add ms to stall timer comment
 (Matthew)
  - Move broken check to intel_guc_ct_send()

Signed-off-by: John Harrison <[email protected]>
Signed-off-by: Daniele Ceraolo Spurio <[email protected]>
Signed-off-by: Matthew Brost <[email protected]>
Reviewed-by: John Harrison <[email protected]>
Signed-off-by: John Harrison <[email protected]>
Link: https://patchwork.freedesktop.org/patch/msgid/[email protected]

Author: mbrost05

drivers/gpu/drm/i915/gt/uc/intel_guc_ct.c

@@ -4,6 +4,9 @@
  */
 
 #include <linux/circ_buf.h>
+#include <linux/ktime.h>
+#include <linux/time64.h>
+#include <linux/timekeeping.h>
 
 #include "i915_drv.h"
 #include "intel_guc_ct.h"
@@ -316,6 +319,7 @@ int intel_guc_ct_enable(struct intel_guc_ct *ct)
 		goto err_deregister;
 
 	ct->enabled = true;
+	ct->stall_time = KTIME_MAX;
 
 	return 0;
 
@@ -389,9 +393,6 @@ static int ct_write(struct intel_guc_ct *ct,
 	u32 *cmds = ctb->cmds;
 	unsigned int i;
 
-	if (unlikely(ctb->broken))
-		return -EPIPE;
-
 	if (unlikely(desc->status))
 		goto corrupted;
 
@@ -505,6 +506,25 @@ static int wait_for_ct_request_update(struct ct_request *req, u32 *status)
 	return err;
 }
 
+#define GUC_CTB_TIMEOUT_MS	1500
+static inline bool ct_deadlocked(struct intel_guc_ct *ct)
+{
+	long timeout = GUC_CTB_TIMEOUT_MS;
+	bool ret = ktime_ms_delta(ktime_get(), ct->stall_time) > timeout;
+
+	if (unlikely(ret)) {
+		struct guc_ct_buffer_desc *send = ct->ctbs.send.desc;
+		struct guc_ct_buffer_desc *recv = ct->ctbs.send.desc;
+
+		CT_ERROR(ct, "Communication stalled for %lld ms, desc status=%#x,%#x\n",
+			 ktime_ms_delta(ktime_get(), ct->stall_time),
+			 send->status, recv->status);
+		ct->ctbs.send.broken = true;
+	}
+
+	return ret;
+}
+
 static inline bool h2g_has_room(struct intel_guc_ct_buffer *ctb, u32 len_dw)
 {
 	struct guc_ct_buffer_desc *desc = ctb->desc;
@@ -516,6 +536,26 @@ static inline bool h2g_has_room(struct intel_guc_ct_buffer *ctb, u32 len_dw)
 	return space >= len_dw;
 }
 
+static int has_room_nb(struct intel_guc_ct *ct, u32 len_dw)
+{
+	struct intel_guc_ct_buffer *ctb = &ct->ctbs.send;
+
+	lockdep_assert_held(&ct->ctbs.send.lock);
+
+	if (unlikely(!h2g_has_room(ctb, len_dw))) {
+		if (ct->stall_time == KTIME_MAX)
+			ct->stall_time = ktime_get();
+
+		if (unlikely(ct_deadlocked(ct)))
+			return -EPIPE;
+		else
+			return -EBUSY;
+	}
+
+	ct->stall_time = KTIME_MAX;
+	return 0;
+}
+
 static int ct_send_nb(struct intel_guc_ct *ct,
 		      const u32 *action,
 		      u32 len,
@@ -528,11 +568,9 @@ static int ct_send_nb(struct intel_guc_ct *ct,
 
 	spin_lock_irqsave(&ctb->lock, spin_flags);
 
-	ret = h2g_has_room(ctb, len + GUC_CTB_HDR_LEN);
-	if (unlikely(!ret)) {
-		ret = -EBUSY;
+	ret = has_room_nb(ct, len + GUC_CTB_HDR_LEN);
+	if (unlikely(ret))
 		goto out;
-	}
 
 	fence = ct_get_next_fence(ct);
 	ret = ct_write(ct, action, len, fence, flags);
@@ -575,15 +613,22 @@ static int ct_send(struct intel_guc_ct *ct,
 retry:
 	spin_lock_irqsave(&ctb->lock, flags);
 	if (unlikely(!h2g_has_room(ctb, len + GUC_CTB_HDR_LEN))) {
+		if (ct->stall_time == KTIME_MAX)
+			ct->stall_time = ktime_get();
 		spin_unlock_irqrestore(&ctb->lock, flags);
 
+		if (unlikely(ct_deadlocked(ct)))
+			return -EPIPE;
+
 		if (msleep_interruptible(sleep_period_ms))
 			return -EINTR;
 		sleep_period_ms = sleep_period_ms << 1;
 
 		goto retry;
 	}
 
+	ct->stall_time = KTIME_MAX;
+
 	fence = ct_get_next_fence(ct);
 	request.fence = fence;
 	request.status = 0;
@@ -646,6 +691,9 @@ int intel_guc_ct_send(struct intel_guc_ct *ct, const u32 *action, u32 len,
 		return -ENODEV;
 	}
 
+	if (unlikely(ct->ctbs.send.broken))
+		return -EPIPE;
+
 	if (flags & INTEL_GUC_CT_SEND_NB)
 		return ct_send_nb(ct, action, len, flags);
 

drivers/gpu/drm/i915/gt/uc/intel_guc_ct.h

@@ -9,6 +9,7 @@
 #include <linux/interrupt.h>
 #include <linux/spinlock.h>
 #include <linux/workqueue.h>
+#include <linux/ktime.h>
 
 #include "intel_guc_fwif.h"
 
@@ -68,6 +69,9 @@ struct intel_guc_ct {
 		struct list_head incoming; /* incoming requests */
 		struct work_struct worker; /* handler for incoming requests */
 	} requests;
+
+	/** @stall_time: time of first time a CTB submission is stalled */
+	ktime_t stall_time;
 };
 
 void intel_guc_ct_init_early(struct intel_guc_ct *ct);