drm/nouveau: expose GSP-RM logging buffers via debugfs

The LOGINIT, LOGINTR, LOGRM, and LOGPMU buffers are circular buffers
that have printf-like logs from GSP-RM and PMU encoded in them.

LOGINIT, LOGINTR, and LOGRM are allocated by Nouveau and their DMA
addresses are passed to GSP-RM during initialization. The buffers are
required for GSP-RM to initialize properly.

LOGPMU is also allocated by Nouveau, but its contents are updated
when Nouveau receives an NV_VGPU_MSG_EVENT_UCODE_LIBOS_PRINT RPC from
GSP-RM. Nouveau then copies the RPC to the buffer.

The messages are encoded as an array of variable-length structures that
contain the parameters to an NV_PRINTF call. The format string and
parameter count are stored in a special ELF image that contains only
logging strings. This image is not currently shipped with the Nvidia
driver.

There are two methods to extract the logs.

OpenRM tries to load the logging ELF, and if present, parses the log
buffers in real time and outputs the strings to the kernel console.

Alternatively, and this is the method used by this patch, the buffers
can be exposed to user space, and a user-space tool (along with the
logging ELF image) can parse the buffer and dump the logs.

This method has the advantage that it allows the buffers to be parsed
even when the logging ELF file is not available to the user. However,
it has the disadvantage the debugfs entries need to remain until the
driver is unloaded.

The buffers are exposed via debugfs. If GSP-RM fails to initialize, then
Nouveau immediately shuts down the GSP interface. This would normally
also deallocate the logging buffers, thereby preventing the user from
capturing the debug logs.

To avoid this, introduce the keep-gsp-logging command line parameter. If
specified, and if at least one logging buffer has content, then Nouveau
will migrate these buffers into new debugfs entries that are retained
until the driver unloads.

An end-user can capture the logs using the following commands:

    cp /sys/kernel/debug/nouveau/<path>/loginit loginit
    cp /sys/kernel/debug/nouveau/<path>/logrm logrm
    cp /sys/kernel/debug/nouveau/<path>/logintr logintr
    cp /sys/kernel/debug/nouveau/<path>/logpmu logpmu

where (for a PCI device) <path> is the PCI ID of the GPU (e.g.
0000:65:00.0).

Since LOGPMU is not needed for normal GSP-RM operation, it is only
created if debugfs is available. Otherwise, the
NV_VGPU_MSG_EVENT_UCODE_LIBOS_PRINT RPCs are ignored.

A simple way to test the buffer migration feature is to have
nvkm_gsp_init() return an error code.

Tested-by: Ben Skeggs <[email protected]>
Signed-off-by: Timur Tabi <[email protected]>
Signed-off-by: Danilo Krummrich <[email protected]>
Link: https://patchwork.freedesktop.org/patch/msgid/[email protected]

Author: ttabi

drivers/gpu/drm/nouveau/include/nvif/log.h

@@ -0,0 +1,51 @@
+/* SPDX-License-Identifier: MIT */
+/* SPDX-FileCopyrightText: Copyright (c) 2024 NVIDIA CORPORATION & AFFILIATES. */
+
+#ifndef __NVIF_LOG_H__
+#define __NVIF_LOG_H__
+
+#ifdef CONFIG_DEBUG_FS
+
+/**
+ * nvif_log - structure for tracking logging buffers
+ * @entry: an entry in a list of struct nvif_logs
+ * @shutdown: pointer to function to call to clean up
+ *
+ * Structure used to track logging buffers so that they can be cleaned up
+ * when the module exits.
+ *
+ * The @shutdown function is called when the module exits. It should free all
+ * backing resources, such as logging buffers.
+ */
+struct nvif_log {
+	struct list_head entry;
+	void (*shutdown)(struct nvif_log *log);
+};
+
+/**
+ * nvif_logs - linked list of nvif_log objects
+ */
+struct nvif_logs {
+	struct list_head head;
+};
+
+#define NVIF_LOGS_DECLARE(logs) \
+	struct nvif_logs logs = { LIST_HEAD_INIT(logs.head) }
+
+static inline void nvif_log_shutdown(struct nvif_logs *logs)
+{
+	if (!list_empty(&logs->head)) {
+		struct nvif_log *log, *n;
+
+		list_for_each_entry_safe(log, n, &logs->head, entry) {
+			/* shutdown() should also delete the log entry */
+			log->shutdown(log);
+		}
+	}
+}
+
+extern struct nvif_logs gsp_logs;
+
+#endif
+
+#endif

drivers/gpu/drm/nouveau/include/nvkm/subdev/gsp.h

@@ -5,6 +5,8 @@
 #include <core/falcon.h>
 #include <core/firmware.h>
 
+#include <linux/debugfs.h>
+
 #define GSP_PAGE_SHIFT 12
 #define GSP_PAGE_SIZE  BIT(GSP_PAGE_SHIFT)
 
@@ -220,6 +222,24 @@ struct nvkm_gsp {
 
 	/* The size of the registry RPC */
 	size_t registry_rpc_size;
+
+#ifdef CONFIG_DEBUG_FS
+	/*
+	 * Logging buffers in debugfs. The wrapper objects need to remain
+	 * in memory until the dentry is deleted.
+	 */
+	struct {
+		struct dentry *parent;
+		struct dentry *init;
+		struct dentry *rm;
+		struct dentry *intr;
+		struct dentry *pmu;
+	} debugfs;
+	struct debugfs_blob_wrapper blob_init;
+	struct debugfs_blob_wrapper blob_intr;
+	struct debugfs_blob_wrapper blob_rm;
+	struct debugfs_blob_wrapper blob_pmu;
+#endif
 };
 
 static inline bool

drivers/gpu/drm/nouveau/nouveau_drm.c

@@ -30,6 +30,7 @@
 #include <linux/vga_switcheroo.h>
 #include <linux/mmu_notifier.h>
 #include <linux/dynamic_debug.h>
+#include <linux/debugfs.h>
 
 #include <drm/clients/drm_client_setup.h>
 #include <drm/drm_drv.h>
@@ -47,6 +48,7 @@
 #include <nvif/fifo.h>
 #include <nvif/push006c.h>
 #include <nvif/user.h>
+#include <nvif/log.h>
 
 #include <nvif/class.h>
 #include <nvif/cl0002.h>
@@ -115,6 +117,16 @@ static struct drm_driver driver_platform;
 
 #ifdef CONFIG_DEBUG_FS
 struct dentry *nouveau_debugfs_root;
+
+/**
+ * gsp_logs - list of nvif_log GSP-RM logging buffers
+ *
+ * Head pointer to a a list of nvif_log buffers that is created for each GPU
+ * upon GSP shutdown if the "keep_gsp_logging" command-line parameter is
+ * specified. This is used to track the alternative debugfs entries for the
+ * GSP-RM logs.
+ */
+NVIF_LOGS_DECLARE(gsp_logs);
 #endif
 
 static u64
@@ -1482,6 +1494,10 @@ nouveau_drm_exit(void)
 	if (IS_ENABLED(CONFIG_DRM_NOUVEAU_SVM))
 		mmu_notifier_synchronize();
 
+#ifdef CONFIG_DEBUG_FS
+	nvif_log_shutdown(&gsp_logs);
+#endif
+
 	nouveau_module_debugfs_fini();
 }