habanalabs: add page fault info uapi

Only the first page fault will be saved.
Besides the address which caused the page fault, the driver captures
all of the mmu user mappings.
User can retrieve this data via the new uapi (new opcode in INFO ioctl).

Signed-off-by: Dani Liberman <dliberman@habana.ai>
Reviewed-by: Oded Gabbay <ogabbay@kernel.org>
Signed-off-by: Oded Gabbay <ogabbay@kernel.org>

1 files changed, 42 insertions, 0 deletions

diff --git a/drivers/misc/habanalabs/common/habanalabs_ioctl.c b/drivers/misc/habanalabs/common/habanalabs_ioctl.c
index 6aef4e24d122..cac2c7fb14f1 100644
--- a/drivers/misc/habanalabs/common/habanalabs_ioctl.c
+++ b/drivers/misc/habanalabs/common/habanalabs_ioctl.c
@@ -778,6 +778,42 @@ static int engine_status_info(struct hl_fpriv *hpriv, struct hl_info_args *args)
 	return rc;
 }
 
+static int page_fault_info(struct hl_fpriv *hpriv, struct hl_info_args *args)
+{
+	struct hl_device *hdev = hpriv->hdev;
+	u32 max_size = args->return_size;
+	struct hl_page_fault_info *info = &hdev->captured_err_info.pgf_info.pgf;
+	void __user *out = (void __user *) (uintptr_t) args->return_pointer;
+
+	if ((!max_size) || (!out))
+		return -EINVAL;
+
+	return copy_to_user(out, info, min_t(size_t, max_size, sizeof(struct hl_page_fault_info)))
+				? -EFAULT : 0;
+}
+
+static int user_mappings_info(struct hl_fpriv *hpriv, struct hl_info_args *args)
+{
+	void __user *out = (void __user *) (uintptr_t) args->return_pointer;
+	u32 user_buf_size = args->return_size;
+	struct hl_device *hdev = hpriv->hdev;
+	struct page_fault_info *pgf_info;
+	u64 actual_size;
+
+	pgf_info = &hdev->captured_err_info.pgf_info;
+	args->array_size = pgf_info->num_of_user_mappings;
+
+	if (!out)
+		return -EINVAL;
+
+	actual_size = pgf_info->num_of_user_mappings * sizeof(struct hl_user_mapping);
+	if (user_buf_size < actual_size)
+		return -ENOMEM;
+
+	return copy_to_user(out, pgf_info->user_mappings, min_t(size_t, user_buf_size, actual_size))
+				? -EFAULT : 0;
+}
+
 static int _hl_info_ioctl(struct hl_fpriv *hpriv, void *data,
 				struct device *dev)
 {
@@ -837,6 +873,12 @@ static int _hl_info_ioctl(struct hl_fpriv *hpriv, void *data,
 	case HL_INFO_GET_EVENTS:
 		return events_info(hpriv, args);
 
+	case HL_INFO_PAGE_FAULT_EVENT:
+		return page_fault_info(hpriv, args);
+
+	case HL_INFO_USER_MAPPINGS:
+		return user_mappings_info(hpriv, args);
+
 	default:
 		break;
 	}