[PATCH v8 1/2] drm/amdgpu: add debugfs for reset registers list

[Christian König]

Am 21.02.22 um 08:15 schrieb Somalapuram Amaranath:
> List of register populated for dump collection during the GPU reset.
>
> Signed-off-by: Somalapuram Amaranath <Amaranath.Somalapuram at amd.com>
> ---
>   drivers/gpu/drm/amd/amdgpu/amdgpu.h         |   4 +
>   drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c | 114 ++++++++++++++++++++
>   2 files changed, 118 insertions(+)
>
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
> index b85b67a88a3d..6e35f2c4c869 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
> @@ -1097,6 +1097,10 @@ struct amdgpu_device {
>   
>   	struct amdgpu_reset_control     *reset_cntl;
>   	uint32_t                        ip_versions[HW_ID_MAX][HWIP_MAX_INSTANCE];
> +
> +	/* reset dump register */
> +	uint32_t			*reset_dump_reg_list;
> +	int                             num_regs;
>   };
>   
>   static inline struct amdgpu_device *drm_to_adev(struct drm_device *ddev)
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c
> index 164d6a9e9fbb..14ad9610f805 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c
> @@ -1609,6 +1609,118 @@ DEFINE_DEBUGFS_ATTRIBUTE(fops_ib_preempt, NULL,
>   DEFINE_DEBUGFS_ATTRIBUTE(fops_sclk_set, NULL,
>   			amdgpu_debugfs_sclk_set, "%llu\n");
>   
> +static ssize_t amdgpu_reset_dump_register_list_read(struct file *f,
> +				char __user *buf, size_t size, loff_t *pos)
> +{
> +	struct amdgpu_device *adev = (struct amdgpu_device *)file_inode(f)->i_private;
> +	char reg_offset[11];
> +	uint32_t num_regs;
> +	int i, ret, len = 0;
> +
> +	if (*pos)
> +		return 0;
> +
> +	ret = down_read_killable(&adev->reset_sem);
> +
> +	if (ret)
> +		return ret;
> +
> +	num_regs = adev->num_regs;
> +
> +	up_read(&adev->reset_sem);
> +
> +	if (num_regs == 0)
> +		return 0;

I think we should drop that cause it just avoids the final \n.

> +
> +	for (i = 0; i < num_regs; i++) {

That's pretty close, but one problem is still that it is possible that 
the number of register becomes much smaller while this loop runs.

Try it like this instead:

down_read_killable(...)
for (i = 0; i < adev->num_regs; ++i) {
     sprintf(...)
     up_read(...);

     copy_to_user(

     down_read_killable(...)
}
up_read().

> +
> +		ret = down_read_killable(&adev->reset_sem);
> +
> +		if (ret)
> +			return ret;
> +
> +		sprintf(reg_offset, "0x%x ", adev->reset_dump_reg_list[i]);
> +
> +		up_read(&adev->reset_sem);
> +
> +		ret = copy_to_user(buf + len, reg_offset, strlen(reg_offset));
> +
> +		if (ret)
> +			return -EFAULT;
> +
> +		len += strlen(reg_offset);
> +	}
> +
> +	ret = copy_to_user(buf + len, "\n", 1);
> +
> +	if (ret)
> +		return -EFAULT;
> +
> +	len++;
> +	*pos += len;
> +
> +	return len;
> +}
> +
> +static ssize_t amdgpu_reset_dump_register_list_write(struct file *f,
> +			const char __user *buf, size_t size, loff_t *pos)
> +{
> +	struct amdgpu_device *adev = (struct amdgpu_device *)file_inode(f)->i_private;
> +	char *reg_offset, *reg, reg_temp[11];
> +	uint32_t *tmp_list;
> +	int ret, i = 0, len = 0;
> +
> +	do {
> +		reg_offset = reg_temp;
> +		memset(reg_offset, 0, 11);
> +		ret = copy_from_user(reg_offset, buf + len, min(11, ((int)size-len)));
> +
> +		if (ret) {
> +			kfree(tmp_list);
> +			return -EFAULT;
> +		}
> +
> +		reg = strsep(&reg_offset, " ");
> +		tmp_list = krealloc_array(tmp_list,
> +					1, sizeof(uint32_t), GFP_KERNEL);
> +		ret = kstrtouint(reg, 16, &tmp_list[i]);
> +
> +		if (ret) {
> +			kfree(tmp_list);
> +			return -EFAULT;
> +		}
> +
> +		len += strlen(reg) + 1;
> +		i++;
> +
> +	} while (len < size);
> +
> +	ret = down_read_killable(&adev->reset_sem);
> +
> +	if (ret) {
> +		kfree(tmp_list);
> +		return ret;
> +	}
> +
> +	kfree(adev->reset_dump_reg_list);
> +
> +	swap(adev->reset_dump_reg_list, tmp_list);

Just an assignment is sufficient here if you do the kfree before since 
tmp_list isn't used after that.

> +	adev->num_regs = i;
> +
> +	up_read(&adev->reset_sem);

This should be a down_write_killable() and up_write() to avoid 
concurrent reads.

Apart from that the write function now looks clean.

Regards,
Christian.

> +
> +	return size;
> +}
> +
> +
> +
> +static const struct file_operations amdgpu_reset_dump_register_list = {
> +	.owner = THIS_MODULE,
> +	.read = amdgpu_reset_dump_register_list_read,
> +	.write = amdgpu_reset_dump_register_list_write,
> +	.llseek = default_llseek
> +};
> +
>   int amdgpu_debugfs_init(struct amdgpu_device *adev)
>   {
>   	struct dentry *root = adev_to_drm(adev)->primary->debugfs_root;
> @@ -1672,6 +1784,8 @@ int amdgpu_debugfs_init(struct amdgpu_device *adev)
>   			    &amdgpu_debugfs_test_ib_fops);
>   	debugfs_create_file("amdgpu_vm_info", 0444, root, adev,
>   			    &amdgpu_debugfs_vm_info_fops);
> +	debugfs_create_file("amdgpu_reset_dump_register_list", 0644, root, adev,
> +			    &amdgpu_reset_dump_register_list);
>   
>   	adev->debugfs_vbios_blob.data = adev->bios;
>   	adev->debugfs_vbios_blob.size = adev->bios_size;