[PATCHSET,0/6] Enable NO_OFFLOAD support

Message ID	20230419160759.568904-1-axboe@kernel.dk (mailing list archive)
Headers	show Return-Path: <linux-block-owner@vger.kernel.org> From: Jens Axboe <axboe@kernel.dk> To: linux-block@vger.kernel.org Cc: luhongfei@vivo.com Subject: [PATCHSET 0/6] Enable NO_OFFLOAD support Date: Wed, 19 Apr 2023 10:07:53 -0600 Message-Id: <20230419160759.568904-1-axboe@kernel.dk> MIME-Version: 1.0 Content-Transfer-Encoding: 8bit Precedence: bulk
Series	Enable NO_OFFLOAD support \| expand [PATCHSET,0/6] Enable NO_OFFLOAD support [1/6] io_uring: grow struct io_kiocb 'flags' to a 64-bit value [2/6] io_uring: move poll_refs up a cacheline to fill a hole [3/6] io_uring: add support for NO_OFFLOAD [4/6] Revert "io_uring: always go async for unsupported fadvise flags" [5/6] Revert "io_uring: for requests that require async, force it" [6/6] io_uring: mark opcodes that always need io-wq punt

Message ID

20230419160759.568904-1-axboe@kernel.dk (mailing list archive)

Headers

From: Jens Axboe <axboe@kernel.dk>
To: linux-block@vger.kernel.org
Cc: luhongfei@vivo.com
Subject: [PATCHSET 0/6] Enable NO_OFFLOAD support
Date: Wed, 19 Apr 2023 10:07:53 -0600
Message-Id: <20230419160759.568904-1-axboe@kernel.dk>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Precedence: bulk

Series

Enable NO_OFFLOAD support | expand

Message

Jens Axboe April 19, 2023, 4:07 p.m. UTC

Hi,

This series enables support for forcing no-offload for requests that
otherwise would have been punted to io-wq. In essence, it bypasses
the normal non-blocking issue in favor of just letting the issue block.
This is only done for requests that would've otherwise hit io-wq in
the offload path, anything pollable will still be doing non-blocking
issue. See patch 3 for details.

Patches 1-2 are just prep patches, and patch 4-5 are reverts of async
cleanups, and patch 6 enables this for requests that don't support
nonblocking issue at all.

Comments

Jens Axboe April 19, 2023, 4:26 p.m. UTC | #1

On 4/19/23 10:07 AM, Jens Axboe wrote:
> Hi,
> 
> This series enables support for forcing no-offload for requests that
> otherwise would have been punted to io-wq. In essence, it bypasses
> the normal non-blocking issue in favor of just letting the issue block.
> This is only done for requests that would've otherwise hit io-wq in
> the offload path, anything pollable will still be doing non-blocking
> issue. See patch 3 for details.
> 
> Patches 1-2 are just prep patches, and patch 4-5 are reverts of async
> cleanups, and patch 6 enables this for requests that don't support
> nonblocking issue at all.

Wrong list... Just disregard this patchset.