From: Tomer Tayar <ttayar@habana.ai>
Date: Wed, 1 Mar 2023 17:45:58 +0200
Subject: [PATCH] accel/habanalabs: postpone mem_mgr IDR destruction to
 hpriv_release()
References: bsc#1012628
Patch-mainline: 6.3.4
Git-commit: 2e8e9a895c4589f124a37fc84d123b5114406e94

[ Upstream commit 2e8e9a895c4589f124a37fc84d123b5114406e94 ]

The memory manager IDR is currently destroyed when user releases the
file descriptor.
However, at this point the user context might be still held, and memory
buffers might be still in use.
Later on, calls to release those buffers will fail due to not finding
their handles in the IDR, leading to a memory leak.
To avoid this leak, split the IDR destruction from the memory manager
fini, and postpone it to hpriv_release() when there is no user context
and no buffers are used.

Signed-off-by: Tomer Tayar <ttayar@habana.ai>
Reviewed-by: Oded Gabbay <ogabbay@kernel.org>
Signed-off-by: Oded Gabbay <ogabbay@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
Signed-off-by: Jiri Slaby <jslaby@suse.cz>
---
 drivers/accel/habanalabs/common/device.c         |  9 +++++++++
 drivers/accel/habanalabs/common/habanalabs.h     |  1 +
 drivers/accel/habanalabs/common/habanalabs_drv.c |  1 +
 drivers/accel/habanalabs/common/memory_mgr.c     | 13 ++++++++++++-
 4 files changed, 23 insertions(+), 1 deletion(-)

diff --git a/drivers/accel/habanalabs/common/device.c b/drivers/accel/habanalabs/common/device.c
index 9933e585..c9143660 100644
--- a/drivers/accel/habanalabs/common/device.c
+++ b/drivers/accel/habanalabs/common/device.c
@@ -423,6 +423,9 @@ static void hpriv_release(struct kref *ref)
 	mutex_destroy(&hpriv->ctx_lock);
 	mutex_destroy(&hpriv->restore_phase_mutex);
 
+	/* There should be no memory buffers at this point and handles IDR can be destroyed */
+	hl_mem_mgr_idr_destroy(&hpriv->mem_mgr);
+
 	/* Device should be reset if reset-upon-device-release is enabled, or if there is a pending
 	 * reset that waits for device release.
 	 */
@@ -514,6 +517,10 @@ static int hl_device_release(struct inode *inode, struct file *filp)
 	}
 
 	hl_ctx_mgr_fini(hdev, &hpriv->ctx_mgr);
+
+	/* Memory buffers might be still in use at this point and thus the handles IDR destruction
+	 * is postponed to hpriv_release().
+	 */
 	hl_mem_mgr_fini(&hpriv->mem_mgr);
 
 	hdev->compute_ctx_in_release = 1;
@@ -887,6 +894,7 @@ static int device_early_init(struct hl_device *hdev)
 
 free_cb_mgr:
 	hl_mem_mgr_fini(&hdev->kernel_mem_mgr);
+	hl_mem_mgr_idr_destroy(&hdev->kernel_mem_mgr);
 free_chip_info:
 	kfree(hdev->hl_chip_info);
 free_prefetch_wq:
@@ -930,6 +938,7 @@ static void device_early_fini(struct hl_device *hdev)
 	mutex_destroy(&hdev->clk_throttling.lock);
 
 	hl_mem_mgr_fini(&hdev->kernel_mem_mgr);
+	hl_mem_mgr_idr_destroy(&hdev->kernel_mem_mgr);
 
 	kfree(hdev->hl_chip_info);
 
diff --git a/drivers/accel/habanalabs/common/habanalabs.h b/drivers/accel/habanalabs/common/habanalabs.h
index fa05e76d..829b30ab 100644
--- a/drivers/accel/habanalabs/common/habanalabs.h
+++ b/drivers/accel/habanalabs/common/habanalabs.h
@@ -3861,6 +3861,7 @@ const char *hl_sync_engine_to_string(enum hl_sync_engine_type engine_type);
 
 void hl_mem_mgr_init(struct device *dev, struct hl_mem_mgr *mmg);
 void hl_mem_mgr_fini(struct hl_mem_mgr *mmg);
+void hl_mem_mgr_idr_destroy(struct hl_mem_mgr *mmg);
 int hl_mem_mgr_mmap(struct hl_mem_mgr *mmg, struct vm_area_struct *vma,
 		    void *args);
 struct hl_mmap_mem_buf *hl_mmap_mem_buf_get(struct hl_mem_mgr *mmg,
diff --git a/drivers/accel/habanalabs/common/habanalabs_drv.c b/drivers/accel/habanalabs/common/habanalabs_drv.c
index 03dae57d..e3781cfe 100644
--- a/drivers/accel/habanalabs/common/habanalabs_drv.c
+++ b/drivers/accel/habanalabs/common/habanalabs_drv.c
@@ -237,6 +237,7 @@ int hl_device_open(struct inode *inode, struct file *filp)
 out_err:
 	mutex_unlock(&hdev->fpriv_list_lock);
 	hl_mem_mgr_fini(&hpriv->mem_mgr);
+	hl_mem_mgr_idr_destroy(&hpriv->mem_mgr);
 	hl_ctx_mgr_fini(hpriv->hdev, &hpriv->ctx_mgr);
 	filp->private_data = NULL;
 	mutex_destroy(&hpriv->ctx_lock);
diff --git a/drivers/accel/habanalabs/common/memory_mgr.c b/drivers/accel/habanalabs/common/memory_mgr.c
index 0f2759e2..f8e8261c 100644
--- a/drivers/accel/habanalabs/common/memory_mgr.c
+++ b/drivers/accel/habanalabs/common/memory_mgr.c
@@ -341,8 +341,19 @@ void hl_mem_mgr_fini(struct hl_mem_mgr *mmg)
 				"%s: Buff handle %u for CTX is still alive\n",
 				topic, id);
 	}
+}
 
-	/* TODO: can it happen that some buffer is still in use at this point? */
+/**
+ * hl_mem_mgr_idr_destroy() - destroy memory manager IDR.
+ * @mmg: parent unified memory manager
+ *
+ * Destroy the memory manager IDR.
+ * Shall be called when IDR is empty and no memory buffers are in use.
+ */
+void hl_mem_mgr_idr_destroy(struct hl_mem_mgr *mmg)
+{
+	if (!idr_is_empty(&mmg->handles))
+		dev_crit(mmg->dev, "memory manager IDR is destroyed while it is not empty!\n");
 
 	idr_destroy(&mmg->handles);
 }
-- 
2.35.3