[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <aRY28IRvBFmTW6cz@kbusch-mbp>
Date: Thu, 13 Nov 2025 14:52:16 -0500
From: Keith Busch <kbusch@...nel.org>
To: Jens Axboe <axboe@...nel.dk>
Cc: Christoph Hellwig <hch@....de>, Sagi Grimberg <sagi@...mberg.me>,
Leon Romanovsky <leon@...nel.org>, linux-block@...r.kernel.org,
linux-kernel@...r.kernel.org, linux-nvme@...ts.infradead.org
Subject: Re: [PATCH v4 0/2] block: Enable proper MMIO memory handling for P2P
DMA
On Thu, Nov 13, 2025 at 10:45:53AM -0700, Jens Axboe wrote:
> I took a look, and what happens here is that iter.p2pdma.map is 0 as it
> never got set to anything. That is the same as PCI_P2PDMA_MAP_UNKNOWN,
> and hence we just end up in a BLK_STS_RESOURCE. First of all, returning
> BLK_STS_RESOURCE for that seems... highly suspicious. That should surely
> be a fatal error. And secondly, this just further backs up that there's
> ZERO testing done on this patchset at all. WTF?
>
> FWIW, the below makes it boot just fine, as expected, as a default zero
> filled iter then matches the UNKNOWN case.
I think this must mean you don't have CONFIG_PCI_P2PDMA enabled. The
state is never set in that case, but I think it should have been.
---
diff --git a/include/linux/pci-p2pdma.h b/include/linux/pci-p2pdma.h
index 951f81a38f3af..1dfcdafebf867 100644
--- a/include/linux/pci-p2pdma.h
+++ b/include/linux/pci-p2pdma.h
@@ -166,6 +166,8 @@ pci_p2pdma_state(struct pci_p2pdma_map_state *state, struct device *dev,
__pci_p2pdma_update_state(state, dev, page);
return state->map;
}
+
+ state->map = PCI_P2PDMA_MAP_NONE;
return PCI_P2PDMA_MAP_NONE;
}
--
Powered by blists - more mailing lists