Received-SPF: pass (google.com: domain of linux-kernel+bounces-103197-linux.lists.archive=gmail.com@vger.kernel.org designates 2604:1380:45e3:2400::1 as permitted sender) client-ip=2604:1380:45e3:2400::1;
Date: Thu, 14 Mar 2024 12:51:38 +0100
From: Michal Kubiak <michal.kubiak@intel.com>
To: Yewon Choi <woni9911@gmail.com>
CC: Allison Henderson <allison.henderson@oracle.com>, "David S. Miller"
	<davem@davemloft.net>, Eric Dumazet <edumazet@google.com>, Jakub Kicinski
	<kuba@kernel.org>, Paolo Abeni <pabeni@redhat.com>, <netdev@vger.kernel.org>,
	<linux-rdma@vger.kernel.org>, <rds-devel@oss.oracle.com>,
	<linux-kernel@vger.kernel.org>, "Dae R. Jeong" <threeearcat@gmail.com>
Subject: Re: [PATCH net] rds: introduce acquire/release ordering in
 acquire/release_in_xmit()
Message-ID: <ZfLkyiTssYD8wmVl@localhost.localdomain>
References: <ZfLdv5DZvBg0wajJ@libra05>
Content-Type: text/plain; charset="us-ascii"
Content-Disposition: inline
In-Reply-To: <ZfLdv5DZvBg0wajJ@libra05>
Precedence: bulk
MIME-Version: 1.0
X-MS-Exchange-AntiSpam-MessageData-ChunkCount: 1
X-MS-Exchange-AntiSpam-MessageData-0: =?us-ascii?Q?Lr8Zf37Y+GbER6Ko62LkdTSuiJhB+iylRcYPF+iYRA69jIKduD5mrzX+nApY?=
 =?us-ascii?Q?6s/PSt7+KRm2XoC7Q7c4AUU7CYG13xZ8mRtzPYGqUBuAC3e4EXxf975wp9e+?=
 =?us-ascii?Q?ZUgm6NxDhK8e3w7JUHGWwWxaWqxO64v5eTmjwUXmlptD3BsCAOu6aIjpG9Ha?=
 =?us-ascii?Q?CfzNj+Oa9BX/BqXkoFMv7R7Bxf/yLLiw8OKmsNZ8AU19uE1NHeLtkDCXKf38?=
 =?us-ascii?Q?fwjrKYtMEPw+HJ5wfWErNu/CCJASDin1a01X2v4lBZEF/mAr1DUJ90+gZcyy?=
 =?us-ascii?Q?2DNI8tpByS8aGQSXxPIcKnXWCKTF+AVnLfH9zdgy0Oj2+11Bi+PjjjuF9ZSl?=
 =?us-ascii?Q?0Lo6VROgfHxCBWPrqLHzuHgMi3312aA+AgyLKo2FK98HHPG3A727jU70BgUS?=
 =?us-ascii?Q?qBtTfPWHGi/stAbIrXVrfK/gwJExs0SbruZ8Sk4yTDMIsaV0za/HQ70PICog?=
 =?us-ascii?Q?aYApbmWeoaiMPKROTIx9euhktQb8VdOR5JG3ZnWjSxCznepKHdKKFpsdXogV?=
 =?us-ascii?Q?zoIm68jg9i0kJYx6ApZUJ/mfpEAwpLvHr7UT7/5uVj7AyRMPXMFhVZgsDXbg?=
 =?us-ascii?Q?2AUb+VuVft82Vy76F8qM/TPkjVBmuaAx/3d7/1YPkZZVg2qBGLoy2NLtUnWV?=
 =?us-ascii?Q?cc0EjH7e2bsWU6M1RX+gWG2a7CxfGtlF7dyHVMJu8uzB+u0qFvpzgZR73DjK?=
 =?us-ascii?Q?eX70gwuW2wNiSBA+FaIXnfrx3b+LrE+P/DxK1BKoZPYcJDqy1GNuRuuE4Rsg?=
 =?us-ascii?Q?6K/htWk1IsTPbIdrfFXD1askE2wlDbwX3D0G5EmNb1PFj8LZ+prmRPPsrUQW?=
 =?us-ascii?Q?RIF/IYsDT+Th5sTpI62rOXGzB7yLMoqisf4TV15kyjM22jJ4B3GkKIPLL/zt?=
 =?us-ascii?Q?PPCXcVXQDwdo3xqHi+7sxEzHqyVU5mT/KBL4+9AQ4Vw2c4L00myU7tzB/kox?=
 =?us-ascii?Q?BFd8CsQfEO4tX/gEFBTwDPQ7I4MC0fgDh+slD94FE5PY6ZMU3Z+SGFuXCVXV?=
 =?us-ascii?Q?zT6pE/fS41AcV0CJ9Qkzsz6Ln75VoSQslQ+Nglwy2fmTxgF4KDyvt8PSRSzc?=
 =?us-ascii?Q?SkCbmOm+zmP0oOuUlDPlXIkh7MWiUiReWdMQ4TU3GreU9RwEUVe5RF7x+wLu?=
 =?us-ascii?Q?UR8T7Z4EGEUlvUqhXYf9aGL+Vjx+sN72cvpEk/PEVU7E8etHC4BTt5V+Fd6z?=
 =?us-ascii?Q?GZLw6uMCJaU4T6XSrlLbAqa05XLmXjvTbGKOUQZnzwzx5Uj64F+9R+9sbRjF?=
 =?us-ascii?Q?gNQdE+hWbFEnZkzG5cI7fRwAZ8c7WDKP0Ll/4BGXwDRkkaAKxctuWPchinhb?=
 =?us-ascii?Q?ixo8Kal83PNt5qBFHM8uCFRwtGSxOqVwvy42Xi9JSfjXaQIjrx8w+u3oG4uW?=
 =?us-ascii?Q?zczGxDq6U5HiAg7ux1fpTH+byPR2tj2McX1FQS2oM9If8zD38c/clkMOpAO3?=
 =?us-ascii?Q?6dk9D/a6rXB+Rvw4fU7p/HSFZ0345NIGqGOjbwzkI4LOAD7rzBCmYM1reuJR?=
 =?us-ascii?Q?7SjEIFcD6LTIEfis+SlESeP0B0QKcZYk4/C00EWlsxnR+jmll6Bbp8ggdfeD?=
 =?us-ascii?Q?i4O5IjuMLxsCFD14jEa5iduRWFx6KyJII6e3wUhc8Ex7ajzg4C/45jqkRKte?=
 =?us-ascii?Q?cA=3D=3D?=
X-MS-Exchange-CrossTenant-Network-Message-Id: 3d882e83-b62b-4995-a191-08dc441d2045
X-MS-Exchange-CrossTenant-AuthSource: PH0PR11MB5782.namprd11.prod.outlook.com
X-MS-Exchange-CrossTenant-AuthAs: Internal
X-MS-Exchange-CrossTenant-OriginalArrivalTime: 14 Mar 2024 11:51:46.6913
 (UTC)
X-MS-Exchange-CrossTenant-FromEntityHeader: Hosted
X-MS-Exchange-CrossTenant-Id: 46c98d88-e344-4ed4-8496-4ed7712e255d
X-MS-Exchange-CrossTenant-MailboxType: HOSTED
X-MS-Exchange-CrossTenant-UserPrincipalName: ANVjut8oPJoAy6vtJ9k/csV0yC91YF0HVQz26OrK/91l3szgOUgVpaS1T268wmR4++8//U1we4ZE2NdlYVSk4Q==
X-MS-Exchange-Transport-CrossTenantHeadersStamped: PH8PR11MB6831
X-OriginatorOrg: intel.com

On Thu, Mar 14, 2024 at 08:21:35PM +0900, Yewon Choi wrote:
> acquire/release_in_xmit() work as bit lock in rds_send_xmit(), so they
> are expected to ensure acquire/release memory ordering semantics.
> However, test_and_set_bit/clear_bit() don't imply such semantics, on
> top of this, following smp_mb__after_atomic() does not guarantee release
> ordering (memory barrier actually should be placed before clear_bit()).
> 
> Instead, we use clear_bit_unlock/test_and_set_bit_lock() here.
> 
> Signed-off-by: Yewon Choi <woni9911@gmail.com>

Missing "Fixes" tag for the patch addressed to the "net" tree.

Thanks,
Michal