habanalabs: rename user_ctx as compute_ctx

This patch renames the "user_ctx" field in the device structure to
"compute_ctx". This better reflects the meaning of this context.

In addition, we also check in the ctx_fini() that the debug mode should be
disabled only if the context being destroyed is the compute context. This
has no effect right now as we only have a single process and a single
context, but this makes the code more ready for multiple process support.
Signed-off-by: NOded Gabbay <oded.gabbay@gmail.com>
Reviewed-by: NGreg Kroah-Hartman <gregkh@linuxfoundation.org>

drivers/misc/habanalabs/context.c

@@ -26,12 +26,13 @@ static void hl_ctx_fini(struct hl_ctx *ctx)
 		dma_fence_put(ctx->cs_pending[i]);
 
 	if (ctx->asid != HL_KERNEL_ASID_ID) {
-		/*
-		 * The engines are stopped as there is no executing CS, but the
+		/* The engines are stopped as there is no executing CS, but the
 		 * Coresight might be still working by accessing addresses
 		 * related to the stopped engines. Hence stop it explicitly.
+		 * Stop only if this is the compute context, as there can be
+		 * only one compute context
 		 */
-		if (hdev->in_debug)
+		if ((hdev->in_debug) && (hdev->compute_ctx == ctx))
 			hl_device_set_debug_mode(hdev, false);
 
 		hl_vm_ctx_fini(ctx);
@@ -85,9 +86,11 @@ int hl_ctx_create(struct hl_device *hdev, struct hl_fpriv *hpriv)
 	hl_hpriv_get(hpriv);
 	ctx->hpriv = hpriv;
 
-	/* TODO: remove for multiple contexts */
+	/* TODO: remove for multiple contexts per process */
 	hpriv->ctx = ctx;
-	hdev->user_ctx = ctx;
+
+	/* TODO: remove the following line for multiple process support */
+	hdev->compute_ctx = ctx;
 
 	return 0;
 

drivers/misc/habanalabs/debugfs.c

@@ -370,7 +370,7 @@ static int mmu_show(struct seq_file *s, void *data)
 	if (dev_entry->mmu_asid == HL_KERNEL_ASID_ID)
 		ctx = hdev->kernel_ctx;
 	else
-		ctx = hdev->user_ctx;
+		ctx = hdev->compute_ctx;
 
 	if (!ctx) {
 		dev_err(hdev->dev, "no ctx available\n");
@@ -533,7 +533,7 @@ static bool hl_is_device_va(struct hl_device *hdev, u64 addr)
 static int device_va_to_pa(struct hl_device *hdev, u64 virt_addr,
 				u64 *phys_addr)
 {
-	struct hl_ctx *ctx = hdev->user_ctx;
+	struct hl_ctx *ctx = hdev->compute_ctx;
 	u64 hop_addr, hop_pte_addr, hop_pte;
 	u64 offset_mask = HOP4_MASK | OFFSET_MASK;
 	int rc = 0;

drivers/misc/habanalabs/device.c

@@ -59,7 +59,7 @@ static void hpriv_release(struct kref *ref)
 	atomic_dec(&hdev->fd_open_cnt);
 
 	/* This allows a new user context to open the device */
-	hdev->user_ctx = NULL;
+	hdev->compute_ctx = NULL;
 }
 
 void hl_hpriv_get(struct hl_fpriv *hpriv)
@@ -590,7 +590,7 @@ static void device_kill_open_processes(struct hl_device *hdev)
 	}
 
 	if (atomic_read(&hdev->fd_open_cnt)) {
-		task = get_pid_task(hdev->user_ctx->hpriv->taskpid,
+		task = get_pid_task(hdev->compute_ctx->hpriv->taskpid,
 					PIDTYPE_PID);
 		if (task) {
 			dev_info(hdev->dev, "Killing user processes\n");
@@ -760,9 +760,9 @@ int hl_device_reset(struct hl_device *hdev, bool hard_reset,
 		hl_cq_reset(hdev, &hdev->completion_queue[i]);
 
 	/* Make sure the context switch phase will run again */
-	if (hdev->user_ctx) {
-		atomic_set(&hdev->user_ctx->thread_ctx_switch_token, 1);
-		hdev->user_ctx->thread_ctx_switch_wait_token = 0;
+	if (hdev->compute_ctx) {
+		atomic_set(&hdev->compute_ctx->thread_ctx_switch_token, 1);
+		hdev->compute_ctx->thread_ctx_switch_wait_token = 0;
 	}
 
 	/* Finished tear-down, starting to re-initialize */
@@ -793,7 +793,7 @@ int hl_device_reset(struct hl_device *hdev, bool hard_reset,
 			goto out_err;
 		}
 
-		hdev->user_ctx = NULL;
+		hdev->compute_ctx = NULL;
 
 		rc = hl_ctx_init(hdev, hdev->kernel_ctx, true);
 		if (rc) {
@@ -970,7 +970,7 @@ int hl_device_init(struct hl_device *hdev, struct class *hclass)
 		goto mmu_fini;
 	}
 
-	hdev->user_ctx = NULL;
+	hdev->compute_ctx = NULL;
 
 	rc = hl_ctx_init(hdev, hdev->kernel_ctx, true);
 	if (rc) {

drivers/misc/habanalabs/habanalabs.h

@@ -910,7 +910,7 @@ struct hl_debug_params {
  * @hdev: habanalabs device structure.
  * @filp: pointer to the given file structure.
  * @taskpid: current process ID.
- * @ctx: current executing context.
+ * @ctx: current executing context. TODO: remove for multiple ctx per process
  * @ctx_mgr: context manager to handle multiple context for this FD.
  * @cb_mgr: command buffer manager to handle multiple buffers for this FD.
  * @debugfs_list: list of relevant ASIC debugfs.
@@ -921,7 +921,7 @@ struct hl_fpriv {
 	struct hl_device	*hdev;
 	struct file		*filp;
 	struct pid		*taskpid;
-	struct hl_ctx		*ctx; /* TODO: remove for multiple ctx */
+	struct hl_ctx		*ctx;
 	struct hl_ctx_mgr	ctx_mgr;
 	struct hl_cb_mgr	cb_mgr;
 	struct list_head	debugfs_list;
@@ -1199,7 +1199,7 @@ struct hl_device_reset_work {
  * @hl_debugfs: device's debugfs manager.
  * @cb_pool: list of preallocated CBs.
  * @cb_pool_lock: protects the CB pool.
- * @user_ctx: current user context executing.
+ * @compute_ctx: current compute context executing.
  * @dram_used_mem: current DRAM memory consumption.
  * @timeout_jiffies: device CS timeout value.
  * @max_power: the max power of the device, as configured by the sysadmin. This
@@ -1276,8 +1276,7 @@ struct hl_device {
 	struct list_head		cb_pool;
 	spinlock_t			cb_pool_lock;
 
-	/* TODO: remove user_ctx for multiple process support */
-	struct hl_ctx			*user_ctx;
+	struct hl_ctx			*compute_ctx;
 
 	atomic64_t			dram_used_mem;
 	u64				timeout_jiffies;