Thanks to the nested inlining, all drivers correctly calling
dma_mapping_error() after a mapping a page or single buffer generate two
calls to get_arch_dma_ops() per callsite, which all adds up to a fair
old chunk of useless code, e.g. ~3KB for an arm64 defconfig plus extras:
text data bss dec hex filename
13051391 1503898 327768 14883057 e318f1 vmlinux.o.old
13050751 1503898 327768 14882417 e31671 vmlinux.o.new
Give the compiler a hand by making it clear we want the same ops.
Signed-off-by: Robin Murphy <robin.murphy@xxxxxxx>
---
include/linux/dma-mapping.h | 7 ++++---
1 file changed, 4 insertions(+), 3 deletions(-)
diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h
index 843ab866e0f4..239e53d12ee8 100644
--- a/include/linux/dma-mapping.h
+++ b/include/linux/dma-mapping.h
@@ -541,10 +541,11 @@ static inline void dma_free_noncoherent(struct device *dev, size_t size,
static inline int dma_mapping_error(struct device *dev, dma_addr_t dma_addr)
{
- debug_dma_mapping_error(dev, dma_addr);
+ const struct dma_map_ops *ops = get_dma_ops(dev);
- if (get_dma_ops(dev)->mapping_error)
- return get_dma_ops(dev)->mapping_error(dev, dma_addr);
+ debug_dma_mapping_error(dev, dma_addr);
+ if (ops->mapping_error)
+ return ops->mapping_error(dev, dma_addr);
return 0;
}