[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <ZIlb1vrQVwjOT1QV@infradead.org>
Date: Tue, 13 Jun 2023 23:19:02 -0700
From: Christoph Hellwig <hch@...radead.org>
To: Ed Tsai <ed.tsai@...iatek.com>
Cc: axboe@...nel.dk, matthias.bgg@...il.com,
angelogioacchino.delregno@...labora.com,
linux-block@...r.kernel.org, linux-kernel@...r.kernel.org,
linux-arm-kernel@...ts.infradead.org,
linux-mediatek@...ts.infradead.org, kbusch@...nel.org,
amergnat@...libre.com, liusong@...ux.alibaba.com,
wsd_upstream@...iatek.com, peter.wang@...iatek.com,
stanley.chu@...iatek.com, powen.kao@...iatek.com,
alice.chao@...iatek.com, naomi.chu@...iatek.com,
Chun-Hung.Wu@...iatek.com
Subject: Re: [PATCH v3] blk-mq: check on cpu id when there is only one ctx
mapping
This looks fine to me:
Reviewed-by: Christoph Hellwig <hch@....de>
> - if (rq->mq_hctx->nr_ctx == 1 ||
> + if ((rq->mq_hctx->nr_ctx == 1 &&
> + rq->mq_ctx->cpu == raw_smp_processor_id()) ||
> rq->cmd_flags & REQ_POLLED)
But please fix the incorrct indentation in the existing code here
please while you're at it (maybe Jens can just fold it in):
if ((rq->mq_hctx->nr_ctx == 1 &&
rq->mq_ctx->cpu == raw_smp_processor_id()) ||
(rq->cmd_flags & REQ_POLLED))
Powered by blists - more mailing lists