On Fri, Oct 01, 2021 at 06:19:59AM +0200, Christoph Hellwig wrote:
> On Tue, Sep 14, 2021 at 03:45:06PM +0000, Ioana Ciornei wrote:
> > [ 245.927020] fsl_dpaa2_eth dpni.3: scather-gather idx 0 P=20a7320000
> > N=20a7320 D=20a7320000 L=30 DMA_BIDIRECTIONAL dma map error check not
> > applicable·
> > [ 245.927048] fsl_dpaa2_eth dpni.3: scather-gather idx 1 P=20a7320030
> > N=20a7320 D=20a7320030 L=5a8 DMA_BIDIRECTIONAL dma map error check not
> > applicable
> > [ 245.927062] DMA-API: cacheline tracking EEXIST, overlapping mappings
> > aren't supported
> >
> > The first line is the dump of the dma_debug_entry which is already present
> > in the radix tree and the second one is the entry which just triggered
> > the EEXIST.
> >
> > As we can see, they are not actually overlapping, at least from my
> > understanding. The first one starts at 0x20a7320000 with a size 0x30
> > and the second one at 0x20a7320030.
>
> They overlap the cache lines. Which means if you use this driver
> on a system that is not dma coherent you will corrupt data.
This is a driver of an integrated ethernet controller which is DMA
coherent.
I added a print just to make sure of this:
--- a/kernel/dma/debug.c
+++ b/kernel/dma/debug.c
@@ -567,6 +567,7 @@ static void add_dma_entry(struct dma_debug_entry *entry)
pr_err("cacheline tracking ENOMEM, dma-debug disabled\n");
global_disable = true;
} else if (rc == -EEXIST) {
+ pr_err("dev_is_dma_coherent(%s) = %d\n", dev_name(entry->dev),
dev_is_dma_coherent(entry->dev));
err_printk(entry->dev, entry,
"cacheline tracking EEXIST, overlapping mappings aren't
supported\n");
}
[ 85.852218] DMA-API: dev_is_dma_coherent(dpni.3) = 1
[ 85.858891] ------------[ cut here ]------------
[ 85.858893] DMA-API: fsl_dpaa2_eth dpni.3: cacheline tracking EEXIST,
overlapping mappings aren't supported
[ 85.858901] WARNING: CPU: 13 PID: 1046 at kernel/dma/debug.c:571
add_dma_entry+0x330/0x390
[ 85.858911] Modules linked in:
[ 85.858915] CPU: 13 PID: 1046 Comm: iperf3 Not tainted
5.15.0-rc2-00478-g34286ba6a164-dirty #1275
[ 85.858919] Hardware name: NXP Layerscape LX2160ARDB (DT)
Shouldn't this case not generate this kind of warning?
Ioana
_______________________________________________
iommu mailing list
iommu@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/iommu
