Yes, the iommu is an interesting case, and the current code is
wrong for that. Can you try the patch below? It contains a modified
version of Nicolas' patch to try CMA again for the expansion and a new
(for now hackish) way to not apply the addressability check for dma-iommu
allocations.
diff --git a/kernel/dma/pool.c b/kernel/dma/pool.c
index 6bc74a2d51273e..ec5e525d2b9309 100644
--- a/kernel/dma/pool.c
+++ b/kernel/dma/pool.c
@@ -3,7 +3,9 @@
* Copyright (C) 2012 ARM Ltd.
* Copyright (C) 2020 Google LLC
*/
+#include <linux/cma.h>
#include <linux/debugfs.h>
+#include <linux/dma-contiguous.h>
#include <linux/dma-direct.h>
#include <linux/dma-noncoherent.h>
#include <linux/init.h>
@@ -55,6 +57,31 @@ static void dma_atomic_pool_size_add(gfp_t gfp, size_t size)
pool_size_kernel += size;
}
+static bool cma_in_zone(gfp_t gfp)
+{
+ phys_addr_t end;
+ unsigned long size;
+ struct cma *cma;
+
+ cma = dev_get_cma_area(NULL);
+ if (!cma)
+ return false;
+
+ size = cma_get_size(cma);
+ if (!size)
+ return false;
+ end = cma_get_base(cma) - memblock_start_of_DRAM() + size - 1;
+
+ /* CMA can't cross zone boundaries, see cma_activate_area() */
+ if (IS_ENABLED(CONFIG_ZONE_DMA) && (gfp & GFP_DMA) &&
+ end <= DMA_BIT_MASK(zone_dma_bits))
+ return true;
+ if (IS_ENABLED(CONFIG_ZONE_DMA32) && (gfp & GFP_DMA32) &&
+ end <= DMA_BIT_MASK(32))
+ return true;
+ return true;
+}
+
static int atomic_pool_expand(struct gen_pool *pool, size_t pool_size,
gfp_t gfp)
{
@@ -68,7 +95,11 @@ static int atomic_pool_expand(struct gen_pool *pool, size_t
pool_size,
do {
pool_size = 1 << (PAGE_SHIFT + order);
- page = alloc_pages(gfp, order);
+ if (cma_in_zone(gfp))
+ page = dma_alloc_from_contiguous(NULL, 1 << order,
+ order, false);
+ if (!page)
+ page = alloc_pages(gfp, order);
} while (!page && order-- > 0);
if (!page)
goto out;
@@ -251,7 +282,11 @@ void *dma_alloc_from_pool(struct device *dev, size_t size,
continue;
phys = gen_pool_virt_to_phys(pool, val);
- if (dma_coherent_ok(dev, phys, size))
+ /*
+ * Only apply the addressability check for dma-direct.
+ * This is a nasty hack and won't work e.g. for arm.
+ */
+ if (get_dma_ops(dev) || dma_coherent_ok(dev, phys, size))
break;
gen_pool_free(pool, val, size);
