[<prev] [next>] [<thread-prev] [day] [month] [year] [list]
Message-ID: <CADUfDZpDS6GUOhhM=je1hiKd-iAQLR6c6pWCyS-qTuutKNWzuw@mail.gmail.com>
Date: Mon, 21 Apr 2025 07:50:19 -0700
From: Caleb Sander Mateos <csander@...estorage.com>
To: Kanchan Joshi <joshi.k@...sung.com>
Cc: Keith Busch <kbusch@...nel.org>, Jens Axboe <axboe@...nel.dk>, Christoph Hellwig <hch@....de>,
Sagi Grimberg <sagi@...mberg.me>, linux-nvme@...ts.infradead.org,
linux-kernel@...r.kernel.org
Subject: Re: [PATCH] nvme/pci: make PRP list DMA pools per-NUMA-node
On Mon, Apr 21, 2025 at 12:09 AM Kanchan Joshi <joshi.k@...sung.com> wrote:
>
> On 4/20/2025 10:14 PM, Caleb Sander Mateos wrote:
> > static int nvme_init_hctx(struct blk_mq_hw_ctx *hctx, void *data,
> > unsigned int hctx_idx)
>
> Missing this handling for admin queue.
>
> We may go to that case (i.e., admin command with data payload > 1
> segment) less often. But when we do, this code will give
> null-pointer-deference.
Good catch, will fix in v2. I'll also adopt your suggestion of
dynamically allocating the per-NUMA-node pool list.
Thanks,
Caleb
Powered by blists - more mailing lists