From c8365dbda056578eebe164bf110816b1a39b4b7f Mon Sep 17 00:00:00 2001

From: =?UTF-8?q?Christian=20K=C3=B6nig?= <christian.koenig@amd.com>

Date: Thu, 30 Sep 2021 11:22:51 +0200

Subject: drm/amdgpu: revert "Add autodump debugfs node for gpu reset v8"

MIME-Version: 1.0

Content-Type: text/plain; charset=UTF-8

Content-Transfer-Encoding: 8bit

Git-commit: c8365dbda056578eebe164bf110816b1a39b4b7f

Patch-mainline: v5.16-rc1

References: git-fixes

This reverts commit 728e7e0cd61899208e924472b9e641dbeb0775c4.

Further discussion reveals that this feature is severely broken

and needs to be reverted ASAP.

GPU reset can never be delayed by userspace even for debugging or

otherwise we can run into in kernel deadlocks.

Signed-off-by: Christian König <christian.koenig@amd.com>

Acked-by: Alex Deucher <alexander.deucher@amd.com>

Acked-by: Nirmoy Das <nirmoy.das@amd.com>

Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

Signed-off-by: Patrik Jakobsson <pjakobsson@suse.de>

---

 drivers/gpu/drm/amd/amdgpu/amdgpu.h         |    2 

 drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c |   76 ----------------------------

 drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.h |    6 --

 drivers/gpu/drm/amd/amdgpu/amdgpu_device.c  |    2 

 4 files changed, 86 deletions(-)

--- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h

+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h

@@ -992,8 +992,6 @@ struct amdgpu_device {

 	char				product_name[32];

 	char				serial[20];

-	struct amdgpu_autodump		autodump;

-

 	atomic_t			throttling_logging_enabled;

 	struct ratelimit_state		throttling_logging_rs;

 };

--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c

+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c

@@ -74,82 +74,8 @@ int amdgpu_debugfs_add_files(struct amdg

 	return 0;

 }

-int amdgpu_debugfs_wait_dump(struct amdgpu_device *adev)

-{

-#if defined(CONFIG_DEBUG_FS)

-	unsigned long timeout = 600 * HZ;

-	int ret;

-

-	wake_up_interruptible(&adev->autodump.gpu_hang);

-

-	ret = wait_for_completion_interruptible_timeout(&adev->autodump.dumping, timeout);

-	if (ret == 0) {

-		pr_err("autodump: timeout, move on to gpu recovery\n");

-		return -ETIMEDOUT;

-	}

-#endif

-	return 0;

-}

-

 #if defined(CONFIG_DEBUG_FS)

-static int amdgpu_debugfs_autodump_open(struct inode *inode, struct file *file)

-{

-	struct amdgpu_device *adev = inode->i_private;

-	int ret;

-

-	file->private_data = adev;

-

-	mutex_lock(&adev->lock_reset);

-	if (adev->autodump.dumping.done) {

-		reinit_completion(&adev->autodump.dumping);

-		ret = 0;

-	} else {

-		ret = -EBUSY;

-	}

-	mutex_unlock(&adev->lock_reset);

-

-	return ret;

-}

-

-static int amdgpu_debugfs_autodump_release(struct inode *inode, struct file *file)

-{

-	struct amdgpu_device *adev = file->private_data;

-

-	complete_all(&adev->autodump.dumping);

-	return 0;

-}

-

-static unsigned int amdgpu_debugfs_autodump_poll(struct file *file, struct poll_table_struct *poll_table)

-{

-	struct amdgpu_device *adev = file->private_data;

-

-	poll_wait(file, &adev->autodump.gpu_hang, poll_table);

-

-	if (adev->in_gpu_reset)

-		return POLLIN | POLLRDNORM | POLLWRNORM;

-

-	return 0;

-}

-

-static const struct file_operations autodump_debug_fops = {

-	.owner = THIS_MODULE,

-	.open = amdgpu_debugfs_autodump_open,

-	.poll = amdgpu_debugfs_autodump_poll,

-	.release = amdgpu_debugfs_autodump_release,

-};

-

-static void amdgpu_debugfs_autodump_init(struct amdgpu_device *adev)

-{

-	init_completion(&adev->autodump.dumping);

-	complete_all(&adev->autodump.dumping);

-	init_waitqueue_head(&adev->autodump.gpu_hang);

-

-	debugfs_create_file("amdgpu_autodump", 0600,

-		adev->ddev->primary->debugfs_root,

-		adev, &autodump_debug_fops);

-}

-

 /**

  * amdgpu_debugfs_process_reg_op - Handle MMIO register reads/writes

  *

@@ -1621,8 +1547,6 @@ int amdgpu_debugfs_init(struct amdgpu_de

 	amdgpu_ras_debugfs_create_all(adev);

-	amdgpu_debugfs_autodump_init(adev);

-

 	return amdgpu_debugfs_add_files(adev, amdgpu_debugfs_list,

 					ARRAY_SIZE(amdgpu_debugfs_list));

 }

--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.h

+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.h

@@ -31,11 +31,6 @@ struct amdgpu_debugfs {

 	unsigned		num_files;

 };

-struct amdgpu_autodump {

-	struct completion		dumping;

-	struct wait_queue_head		gpu_hang;

-};

-

 int amdgpu_debugfs_regs_init(struct amdgpu_device *adev);

 int amdgpu_debugfs_init(struct amdgpu_device *adev);

 void amdgpu_debugfs_fini(struct amdgpu_device *adev);

@@ -45,4 +40,3 @@ int amdgpu_debugfs_add_files(struct amdg

 int amdgpu_debugfs_fence_init(struct amdgpu_device *adev);

 int amdgpu_debugfs_firmware_init(struct amdgpu_device *adev);

 int amdgpu_debugfs_gem_init(struct amdgpu_device *adev);

-int amdgpu_debugfs_wait_dump(struct amdgpu_device *adev);

--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c

+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c

@@ -3963,8 +3963,6 @@ static int amdgpu_device_pre_asic_reset(

 	int i, r = 0;

 	bool need_full_reset  = *need_full_reset_arg;

-	amdgpu_debugfs_wait_dump(adev);

-

 	/* block all schedulers and reset given job's ring */

 	for (i = 0; i < AMDGPU_MAX_RINGS; ++i) {

 		struct amdgpu_ring *ring = adev->rings[i];