habanalabs: clear non-released encapsulated signals

Reserved encapsulated signals which were not released hold the context
refcount, leading to a failure when killing the user process on device
reset or device fini.
Add the release of these left signals in the CS roll-back process.

Signed-off-by: Tomer Tayar <ttayar@habana.ai>
Reviewed-by: Oded Gabbay <ogabbay@kernel.org>
Signed-off-by: Oded Gabbay <ogabbay@kernel.org>

3 files changed, 71 insertions, 31 deletions

diff --git a/drivers/misc/habanalabs/common/command_submission.c b/drivers/misc/habanalabs/common/command_submission.c
index f1c69c8ed74a..ea0e5101c10e 100644
--- a/drivers/misc/habanalabs/common/command_submission.c
+++ b/drivers/misc/habanalabs/common/command_submission.c
@@ -742,13 +742,11 @@ static void cs_do_release(struct kref *ref)
 		 */
 		if (hl_cs_cmpl->encaps_signals)
 			kref_put(&hl_cs_cmpl->encaps_sig_hdl->refcount,
-						hl_encaps_handle_do_release);
+					hl_encaps_release_handle_and_put_ctx);
 	}
 
-	if ((cs->type == CS_TYPE_WAIT || cs->type == CS_TYPE_COLLECTIVE_WAIT)
-			&& cs->encaps_signals)
-		kref_put(&cs->encaps_sig_hdl->refcount,
-					hl_encaps_handle_do_release);
+	if ((cs->type == CS_TYPE_WAIT || cs->type == CS_TYPE_COLLECTIVE_WAIT) && cs->encaps_signals)
+		kref_put(&cs->encaps_sig_hdl->refcount, hl_encaps_release_handle_and_put_ctx);
 
 out:
 	/* Must be called before hl_ctx_put because inside we use ctx to get
@@ -1011,6 +1009,34 @@ static void cs_rollback(struct hl_device *hdev, struct hl_cs *cs)
 		hl_complete_job(hdev, job);
 }
 
+/*
+ * release_reserved_encaps_signals() - release reserved encapsulated signals.
+ * @hdev: pointer to habanalabs device structure
+ *
+ * Release reserved encapsulated signals which weren't un-reserved, or for which a CS with
+ * encapsulated signals wasn't submitted and thus weren't released as part of CS roll-back.
+ * For these signals need also to put the refcount of the H/W SOB which was taken at the
+ * reservation.
+ */
+static void release_reserved_encaps_signals(struct hl_device *hdev)
+{
+	struct hl_ctx *ctx = hl_get_compute_ctx(hdev);
+	struct hl_cs_encaps_sig_handle *handle;
+	struct hl_encaps_signals_mgr *mgr;
+	u32 id;
+
+	if (!ctx)
+		return;
+
+	mgr = &ctx->sig_mgr;
+
+	idr_for_each_entry(&mgr->handles, handle, id)
+		if (handle->cs_seq == ULLONG_MAX)
+			kref_put(&handle->refcount, hl_encaps_release_handle_and_put_sob_ctx);
+
+	hl_ctx_put(ctx);
+}
+
 void hl_cs_rollback_all(struct hl_device *hdev, bool skip_wq_flush)
 {
 	int i;
@@ -1039,6 +1065,8 @@ void hl_cs_rollback_all(struct hl_device *hdev, bool skip_wq_flush)
 	}
 
 	force_complete_multi_cs(hdev);
+
+	release_reserved_encaps_signals(hdev);
 }
 
 static void
@@ -2001,6 +2029,8 @@ static int cs_ioctl_reserve_signals(struct hl_fpriv *hpriv,
 	 */
 	handle->pre_sob_val = prop->next_sob_val - handle->count;
 
+	handle->cs_seq = ULLONG_MAX;
+
 	*signals_count = prop->next_sob_val;
 	hdev->asic_funcs->hw_queues_unlock(hdev);
 
@@ -2350,10 +2380,8 @@ put_cs:
 	/* We finished with the CS in this function, so put the ref */
 	cs_put(cs);
 free_cs_chunk_array:
-	if (!wait_cs_submitted && cs_encaps_signals && handle_found &&
-							is_wait_cs)
-		kref_put(&encaps_sig_hdl->refcount,
-				hl_encaps_handle_do_release);
+	if (!wait_cs_submitted && cs_encaps_signals && handle_found && is_wait_cs)
+		kref_put(&encaps_sig_hdl->refcount, hl_encaps_release_handle_and_put_ctx);
 	kfree(cs_chunk_array);
 out:
 	return rc;
diff --git a/drivers/misc/habanalabs/common/context.c b/drivers/misc/habanalabs/common/context.c
index ba6675960203..9c8b1b37b510 100644
--- a/drivers/misc/habanalabs/common/context.c
+++ b/drivers/misc/habanalabs/common/context.c
@@ -9,37 +9,46 @@
 
 #include <linux/slab.h>
 
-void hl_encaps_handle_do_release(struct kref *ref)
+static void encaps_handle_do_release(struct hl_cs_encaps_sig_handle *handle, bool put_hw_sob,
+					bool put_ctx)
 {
-	struct hl_cs_encaps_sig_handle *handle =
-		container_of(ref, struct hl_cs_encaps_sig_handle, refcount);
 	struct hl_encaps_signals_mgr *mgr = &handle->ctx->sig_mgr;
 
+	if (put_hw_sob)
+		hw_sob_put(handle->hw_sob);
+
 	spin_lock(&mgr->lock);
 	idr_remove(&mgr->handles, handle->id);
 	spin_unlock(&mgr->lock);
 
-	hl_ctx_put(handle->ctx);
+	if (put_ctx)
+		hl_ctx_put(handle->ctx);
+
 	kfree(handle);
 }
 
-static void hl_encaps_handle_do_release_sob(struct kref *ref)
+void hl_encaps_release_handle_and_put_ctx(struct kref *ref)
 {
 	struct hl_cs_encaps_sig_handle *handle =
-		container_of(ref, struct hl_cs_encaps_sig_handle, refcount);
-	struct hl_encaps_signals_mgr *mgr = &handle->ctx->sig_mgr;
+			container_of(ref, struct hl_cs_encaps_sig_handle, refcount);
 
-	/* if we're here, then there was a signals reservation but cs with
-	 * encaps signals wasn't submitted, so need to put refcount
-	 * to hw_sob taken at the reservation.
-	 */
-	hw_sob_put(handle->hw_sob);
+	encaps_handle_do_release(handle, false, true);
+}
 
-	spin_lock(&mgr->lock);
-	idr_remove(&mgr->handles, handle->id);
-	spin_unlock(&mgr->lock);
+static void hl_encaps_release_handle_and_put_sob(struct kref *ref)
+{
+	struct hl_cs_encaps_sig_handle *handle =
+			container_of(ref, struct hl_cs_encaps_sig_handle, refcount);
 
-	kfree(handle);
+	encaps_handle_do_release(handle, true, false);
+}
+
+void hl_encaps_release_handle_and_put_sob_ctx(struct kref *ref)
+{
+	struct hl_cs_encaps_sig_handle *handle =
+			container_of(ref, struct hl_cs_encaps_sig_handle, refcount);
+
+	encaps_handle_do_release(handle, true, true);
 }
 
 static void hl_encaps_sig_mgr_init(struct hl_encaps_signals_mgr *mgr)
@@ -48,8 +57,7 @@ static void hl_encaps_sig_mgr_init(struct hl_encaps_signals_mgr *mgr)
 	idr_init(&mgr->handles);
 }
 
-static void hl_encaps_sig_mgr_fini(struct hl_device *hdev,
-			struct hl_encaps_signals_mgr *mgr)
+static void hl_encaps_sig_mgr_fini(struct hl_device *hdev, struct hl_encaps_signals_mgr *mgr)
 {
 	struct hl_cs_encaps_sig_handle *handle;
 	struct idr *idp;
@@ -57,11 +65,14 @@ static void hl_encaps_sig_mgr_fini(struct hl_device *hdev,
 
 	idp = &mgr->handles;
 
+	/* The IDR is expected to be empty at this stage, because any left signal should have been
+	 * released as part of CS roll-back.
+	 */
 	if (!idr_is_empty(idp)) {
-		dev_warn(hdev->dev, "device released while some encaps signals handles are still allocated\n");
+		dev_warn(hdev->dev,
+			"device released while some encaps signals handles are still allocated\n");
 		idr_for_each_entry(idp, handle, id)
-			kref_put(&handle->refcount,
-					hl_encaps_handle_do_release_sob);
+			kref_put(&handle->refcount, hl_encaps_release_handle_and_put_sob);
 	}
 
 	idr_destroy(&mgr->handles);
diff --git a/drivers/misc/habanalabs/common/habanalabs.h b/drivers/misc/habanalabs/common/habanalabs.h
index 0329a0980bb7..e2527d976ee0 100644
--- a/drivers/misc/habanalabs/common/habanalabs.h
+++ b/drivers/misc/habanalabs/common/habanalabs.h
@@ -3775,7 +3775,8 @@ void hl_sysfs_add_dev_vrm_attr(struct hl_device *hdev, struct attribute_group *d
 
 void hw_sob_get(struct hl_hw_sob *hw_sob);
 void hw_sob_put(struct hl_hw_sob *hw_sob);
-void hl_encaps_handle_do_release(struct kref *ref);
+void hl_encaps_release_handle_and_put_ctx(struct kref *ref);
+void hl_encaps_release_handle_and_put_sob_ctx(struct kref *ref);
 void hl_hw_queue_encaps_sig_set_sob_info(struct hl_device *hdev,
 			struct hl_cs *cs, struct hl_cs_job *job,
 			struct hl_cs_compl *cs_cmpl);