[PATCH 1/4] powerpc: Dynamic DMA zone limits

Michael Ellerman mpe at ellerman.id.au
Mon Oct 13 20:00:49 AEDT 2014

On Mon, 2014-10-13 at 18:14 +1100, Anton Blanchard wrote:
> Hi Scott,
> > Platform code can call limit_zone_pfn() to set appropriate limits
> > for ZONE_DMA and ZONE_DMA32, and dma_direct_alloc_coherent() will
> > select a suitable zone based on a device's mask and the pfn limits
> > that platform code has configured.
> This patch breaks my POWER8 box:
> ipr 0001:08:00.0: Using 64-bit DMA iommu bypass
> ipr 0001:08:00.0: dma_direct_alloc_coherent: No suitable zone for pfn 0x10000
> ipr 0001:08:00.0: Couldn't allocate enough memory for device driver! 
> ipr: probe of 0001:08:00.0 failed with error -12
> ipr isn't setting a coherent mask, but we shouldn't care on these boxes.
> Could we ignore the coherent mask or copy the dma mask to it?

Talking to Ben the answer seems to be "it's complicated".

We shouldn't be ignoring the coherent mask, but we have been, and have been
getting away with it.

The PCI code sets a default 32-bit mask, so we can't even detect when a device
hasn't set it. Though maybe the powernv PCI code could be initialising it to
64-bit ?

For this cycle I'm thinking of the below patch.

Scott & Anton can you test please?

Also the depends on FSL_PCI was totally a guess, so please correct that if it's
wrong Scott.


[PATCH] powerpc: Only do dynamic DMA zone limits on platforms that need it

Scott's patch 1c98025c6c95 "Dynamic DMA zone limits" changed
dma_direct_alloc_coherent() to start using dev->coherent_dma_mask.

That seems fair enough, but it exposes the fact that some of the drivers
we care about on IBM platforms aren't setting the coherent mask.

The proper fix is to have drivers set the coherent mask and also have
the platform code honor it.

For now, just restrict the dynamic DMA zone limits to the platforms that
need it, which is those using FSL_PCI.

Fixes: 1c98025c6c95 ("powerpc: Dynamic DMA zone limits")
Signed-off-by: Michael Ellerman <mpe at ellerman.id.au>
 arch/powerpc/Kconfig      | 2 +-
 arch/powerpc/kernel/dma.c | 4 ++--
 2 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index 88eace4e28c3..9b9044aec217 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -290,7 +290,7 @@ config PPC_EMULATE_SSTEP
 config ZONE_DMA32
-	default y if PPC64
+	default y if PPC64 && FSL_PCI
 source "init/Kconfig"
diff --git a/arch/powerpc/kernel/dma.c b/arch/powerpc/kernel/dma.c
index adac9dc54aee..bd443a2e4426 100644
--- a/arch/powerpc/kernel/dma.c
+++ b/arch/powerpc/kernel/dma.c
@@ -53,6 +53,7 @@ void *dma_direct_alloc_coherent(struct device *dev, size_t size,
 	struct page *page;
 	int node = dev_to_node(dev);
 	u64 pfn = get_pfn_limit(dev);
 	int zone;
@@ -67,12 +68,11 @@ void *dma_direct_alloc_coherent(struct device *dev, size_t size,
 	case ZONE_DMA:
 		flag |= GFP_DMA;
 	case ZONE_DMA32:
 		flag |= GFP_DMA32;
+#endif /* CONFIG_ZONE_DMA32 */
 	/* ignore region specifiers */
 	flag  &= ~(__GFP_HIGHMEM);

More information about the Linuxppc-dev mailing list