Subject: Re: [PATCH 2/2] drm/amdkfd: Slighly optimize 'init_doorbell_bitmap()'
To:     Christophe JAILLET <christophe.jaillet@wanadoo.fr>,
        alexander.deucher@amd.com, christian.koenig@amd.com,
        Xinhui.Pan@amd.com, airlied@linux.ie, daniel@ffwll.ch
Cc:     amd-gfx@lists.freedesktop.org, dri-devel@lists.freedesktop.org,
        linux-kernel@vger.kernel.org, kernel-janitors@vger.kernel.org
References: <2343a4e6547a8436419308744ba8c433088922a5.1637516393.git.christophe.jaillet@wanadoo.fr>
 <3e54737649cf94daabaa5b51db9f4c21d43124fe.1637516393.git.christophe.jaillet@wanadoo.fr>
From:   Felix Kuehling <felix.kuehling@amd.com>
Message-ID: <283c0b53-ff4e-85f8-4738-2d477365f458@amd.com>
Date:   Mon, 22 Nov 2021 16:44:20 -0500
User-Agent: Mozilla/5.0 (X11; Linux x86_64; rv:78.0) Gecko/20100101
 Thunderbird/78.14.0
In-Reply-To: <3e54737649cf94daabaa5b51db9f4c21d43124fe.1637516393.git.christophe.jaillet@wanadoo.fr>
Content-Type: text/plain; charset=utf-8
Content-Transfer-Encoding: 7bit
Content-Language: en-US
MIME-Version: 1.0
X-MS-Exchange-AntiSpam-MessageData-ChunkCount: 1
X-MS-Exchange-AntiSpam-MessageData-0: =?utf-8?B?YWZyVXRwZThJa2xCZDBORmh1SFBtckZ5bW9rZ3VieVBkcFExbnhuZmh0SEJX?=
 =?utf-8?B?M1Q4VnFwTUp3VTB2a3BBVHYrQUU3RjBFU0JVMmV0c0FPdm5ONTlWa3JiOHZL?=
 =?utf-8?B?TnNJdElUQmU2YVJDcmJTUEdBYUZzc09jNWV5NE4xMlZYc3hocE5YbWRISVI1?=
 =?utf-8?B?eTdlVXRNWW9vTlpyNWlyU0hJTVYyUDk2M0ZhUWZrcGkyUzdlL3lQMWJjaHRz?=
 =?utf-8?B?OGd2L0NQUTJkZlAwckRXR1N2N0JFdjNoTk1jYWp1T1dZL0xrMFQ1cjdqd3RE?=
 =?utf-8?B?VEt1by82UDd3MjNlM2pVQnRCV210aUFwQ2VpTEppTFRwM1E1bm95YjhkaHU0?=
 =?utf-8?B?OWYvUWxkcWplQlVSOWJtN1VvOHgxTnhzdkthYXdhRGFic0N3OFhoSC9mZUdi?=
 =?utf-8?B?SEl1cjltSllxY0NLNm9yT3JUbVZVaGZPRWZFc25HN2lvbDJKemVzWFFQYkVw?=
 =?utf-8?B?bXBOWER1bGxaYlBqSm1lNys3N1JmY0ZTZzg3bVFKY0V3by92bHR3UlU1WFpq?=
 =?utf-8?B?SGx3MXpUeUxJTzBwMk9nVDFBYklzRFFhZ3NUajVmMDJmUTNPTWdMYlBVOHp3?=
 =?utf-8?B?MSsrZldvQjZ1SVpRbFZqdlRVQ2R6b2YvZmtrVE9oVzIwcU5rRVdPYmw1RFh3?=
 =?utf-8?B?N1RITUJocVA5S0szVDNaNHBvL2kwaktMK2VUNGxHcUNxcGpPRXlWRGo2ejk4?=
 =?utf-8?B?MWtQdTBCRnF2TkJrTFlCbXdnUkYyMDlOd2ppMldIYWpQSlc1ZTU3dHZ3RkNH?=
 =?utf-8?B?SkZVQy96Q3VTT0M3Yit1NHBVSzcvZ0xqOVBaNWZ3ckZZU0lzYTR0Z2cxdFBN?=
 =?utf-8?B?SER5UDI4eUYveGtUc2ZTVHMrM0ViT08rdUVtdGoyM3JJRUFncVRnMHhpQ1FN?=
 =?utf-8?B?ZEp0VDR1VUVJTTBaQnVzUzREd0dKQjF6Q3k2VXVqamZFYjFIODBzaEZGMEty?=
 =?utf-8?B?YUQ4azVWOGs4RjFjZWNyaENONkhMbFVMdjEwcUkydXNROHg5cFZpMmU4VElY?=
 =?utf-8?B?NWU5YTlRTmt5TWFDc0svdUo1dDhJRGE4bW50ckJkZXRBWERDNWFlN04zdXNu?=
 =?utf-8?B?RVNCWTVqNzdPeVhCZWdQbDRDZmNmSldleE5icVlLbksyN01IKzRYd2VBNks2?=
 =?utf-8?B?TFd0M09xRUNlTDMzZThrbkdpdXBjdzlJQlc4S1p5c3BQOWhWNHpOY1hFN096?=
 =?utf-8?B?N1dpVDdTRm5CTlRRTUQ0OHpLU2hFaDJmcHFVTkkwQnJMWHYwQjE3WE4zWnVj?=
 =?utf-8?B?OUlKRlJjMEE0NWhvNDdUNzhwK2R1RkJmMkJ2U2FkN2tqZmNWSXN1NWVEcEhq?=
 =?utf-8?B?N1V4Mld2TFJFSVZMUHQ5TC9xWlpXaDR4NDhkTnArNGNyTURkUG9wM0U4UTEy?=
 =?utf-8?B?OFRpMDRaVmJVSml0eTg4UzZKSk8wWUtnNGlaNllXRU11TEdzUjhnNUUyNGJv?=
 =?utf-8?B?bDlVSnZNK0JaTkVEaEFZZUp6K1FzZjRVeWVkc3AvVWdRa3IwZlhUZmtxL2lP?=
 =?utf-8?B?a2M3ekRDWHUzMXAxM2dwaU02Y1VmcTlQS3BpekIram9JYWt1QldFZjVrSHds?=
 =?utf-8?B?LzIzT0loQnJteitZVVRvaHJyczVUa2RMVDQ2ZUdkTE1oaWk3bWROSndsendB?=
 =?utf-8?B?bjB3WC9zek8yM1JxRnU4NnBmZnF3RkVrRnlKMG1GTU1uUWp1VklZYXA1OWNH?=
 =?utf-8?B?ckNhSm8wRHNkQ1ZoMHJVeHlhWUNnUE1Zbzc2OEF6UDN4OUkxdy9rYXZEWUxz?=
 =?utf-8?B?K3pxQnlYa1AzaHVoVVBYQUFlS0FnN1hRcWltK1JrckQvazZVRjNwYThWSUh6?=
 =?utf-8?B?V1BUaTZ2NlVackZ5VnZDTGMra1d3SE52NXJJVElDZEhvWXZtNVVKeVpxUnkv?=
 =?utf-8?B?TzE2RnNqblU3aEZubkpGeUdPRnZqU1ArdDE4L0FRTEJFOWNIZXFXc2p2UTZY?=
 =?utf-8?B?cXMxaWJJOXlPMmFzTnNORXo1dHhUS05zSFUyRlV0aDFCRnJZdjhlOVBvVUow?=
 =?utf-8?B?eWdxR1FjZG1yT1Y4aEFGenVrYzgveTVSOU9GS0gwM1RVdHUreTRGWUwvUXpl?=
 =?utf-8?B?ZWVvNU8xN2NoWUlkSHYzVXVlSjVxRmNac1VUbFBaZm4xMUlldnFNVDZlWTN5?=
 =?utf-8?B?azBuYnZuQmtTVjRHTWZaaE14UkpBNzlZV3BabW1IUEVCZHhITkN5djZiMVhI?=
 =?utf-8?Q?Lbd6SsxslBpParJuAQIW9Ls=3D?=
X-OriginatorOrg: amd.com
X-MS-Exchange-CrossTenant-Network-Message-Id: 0e38f3c7-884f-4020-8f24-08d9ae013e9d
X-MS-Exchange-CrossTenant-AuthSource: BN9PR12MB5115.namprd12.prod.outlook.com
X-MS-Exchange-CrossTenant-AuthAs: Internal
X-MS-Exchange-CrossTenant-OriginalArrivalTime: 22 Nov 2021 21:44:22.2565
 (UTC)
X-MS-Exchange-CrossTenant-FromEntityHeader: Hosted
X-MS-Exchange-CrossTenant-Id: 3dd8961f-e488-4e60-8e11-a82d994e183d
X-MS-Exchange-CrossTenant-MailboxType: HOSTED
X-MS-Exchange-CrossTenant-UserPrincipalName: /QcsIOpxbHp55LNYOJkfeodnncxXnL0fkbH9y89sQzOyfcHxB4qLNdX6NVkR3i8/HNmJG25rTBrShgeSPYcMXA==
X-MS-Exchange-Transport-CrossTenantHeadersStamped: BN9PR12MB5036
Precedence: bulk
List-ID: <linux-kernel.vger.kernel.org>
X-Mailing-List: linux-kernel@vger.kernel.org

Am 2021-11-21 um 12:41 p.m. schrieb Christophe JAILLET:
> The 'doorbell_bitmap' bitmap has just been allocated. So we can use the
> non-atomic '__set_bit()' function to save a few cycles as no concurrent
> access can happen.
>
> Signed-off-by: Christophe JAILLET <christophe.jaillet@wanadoo.fr>

Thank you for the patches. I think the same sort of change (at least the
allocation/freeing part) could be applied to the queue_slot_bitmap in
kfd_process_queue_manager.c. Would you like to submit another revision
of this patch series that handles that as well?

Either way, this series is

Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>


> ---
> bitmap_set() could certainly also be use, but range checking would be
> tricky.
> ---
>  drivers/gpu/drm/amd/amdkfd/kfd_process.c | 6 +++---
>  1 file changed, 3 insertions(+), 3 deletions(-)
>
> diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process.c b/drivers/gpu/drm/amd/amdkfd/kfd_process.c
> index 172ee8763523..2e9d341062c4 100644
> --- a/drivers/gpu/drm/amd/amdkfd/kfd_process.c
> +++ b/drivers/gpu/drm/amd/amdkfd/kfd_process.c
> @@ -1447,9 +1447,9 @@ static int init_doorbell_bitmap(struct qcm_process_device *qpd,
>  
>  	for (i = 0; i < KFD_MAX_NUM_OF_QUEUES_PER_PROCESS / 2; i++) {
>  		if (i >= range_start && i <= range_end) {
> -			set_bit(i, qpd->doorbell_bitmap);
> -			set_bit(i + KFD_QUEUE_DOORBELL_MIRROR_OFFSET,
> -				qpd->doorbell_bitmap);
> +			__set_bit(i, qpd->doorbell_bitmap);
> +			__set_bit(i + KFD_QUEUE_DOORBELL_MIRROR_OFFSET,
> +				  qpd->doorbell_bitmap);
>  		}
>  	}
>