habanalabs: remove stop-on-error flag from DMA

Stop-on-error mode in DMA is useful as it stops the transaction
immediately upon error e.g. page fault.
But it may cause the next command submission to fail as is leaves the DMA
in unstable state.
Therefore we remove the stop-on-error configuration from the DMA.
Stop-on-err is still available for debug.

Signed-off-by: Omer Shpigelman <oshpigelman@habana.ai>
Reviewed-by: Oded Gabbay <oded.gabbay@gmail.com>
Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>

1 files changed, 55 insertions, 0 deletions

diff --git a/drivers/misc/habanalabs/debugfs.c b/drivers/misc/habanalabs/debugfs.c
index 756d36ed5d95..37beff3096f8 100644
--- a/drivers/misc/habanalabs/debugfs.c
+++ b/drivers/misc/habanalabs/debugfs.c
@@ -970,6 +970,49 @@ static ssize_t hl_device_write(struct file *f, const char __user *buf,
 	return count;
 }
 
+static ssize_t hl_stop_on_err_read(struct file *f, char __user *buf,
+					size_t count, loff_t *ppos)
+{
+	struct hl_dbg_device_entry *entry = file_inode(f)->i_private;
+	struct hl_device *hdev = entry->hdev;
+	char tmp_buf[200];
+	ssize_t rc;
+
+	if (*ppos)
+		return 0;
+
+	sprintf(tmp_buf, "%d\n", hdev->stop_on_err);
+	rc = simple_read_from_buffer(buf, strlen(tmp_buf) + 1, ppos, tmp_buf,
+			strlen(tmp_buf) + 1);
+
+	return rc;
+}
+
+static ssize_t hl_stop_on_err_write(struct file *f, const char __user *buf,
+				     size_t count, loff_t *ppos)
+{
+	struct hl_dbg_device_entry *entry = file_inode(f)->i_private;
+	struct hl_device *hdev = entry->hdev;
+	u32 value;
+	ssize_t rc;
+
+	if (atomic_read(&hdev->in_reset)) {
+		dev_warn_ratelimited(hdev->dev,
+				"Can't change stop on error during reset\n");
+		return 0;
+	}
+
+	rc = kstrtouint_from_user(buf, count, 10, &value);
+	if (rc)
+		return rc;
+
+	hdev->stop_on_err = value ? 1 : 0;
+
+	hl_device_reset(hdev, false, false);
+
+	return count;
+}
+
 static const struct file_operations hl_data32b_fops = {
 	.owner = THIS_MODULE,
 	.read = hl_data_read32,
@@ -1015,6 +1058,12 @@ static const struct file_operations hl_device_fops = {
 	.write = hl_device_write
 };
 
+static const struct file_operations hl_stop_on_err_fops = {
+	.owner = THIS_MODULE,
+	.read = hl_stop_on_err_read,
+	.write = hl_stop_on_err_write
+};
+
 static const struct hl_info_list hl_debugfs_list[] = {
 	{"command_buffers", command_buffers_show, NULL},
 	{"command_submission", command_submission_show, NULL},
@@ -1152,6 +1201,12 @@ void hl_debugfs_add_device(struct hl_device *hdev)
 				dev_entry,
 				&hl_device_fops);
 
+	debugfs_create_file("stop_on_err",
+				0644,
+				dev_entry->root,
+				dev_entry,
+				&hl_stop_on_err_fops);
+
 	for (i = 0, entry = dev_entry->entry_arr ; i < count ; i++, entry++) {
 
 		ent = debugfs_create_file(hl_debugfs_list[i].name,