[PATCH 5/7] Out of line dma_alloc/free_attrs

[Andi Kleen]

From: Andi Kleen <ak@xxxxxxxxxxxxxxx>

These functions are very big and frequently used. I don't see any
sense in inlining them because they do slow operations.

Out of lining them saves ~19k text in my kernel.

   text    data     bss     dec     hex filename
9047801 5367568 11116544        25531913        1859609 vmlinux-after-dma
9067798 5367600 11116544        25551942        185e446 vmlinux-before-dma

Cc: akpm@xxxxxxxxxxxxxxxxxxxx
Signed-off-by: Andi Kleen <ak@xxxxxxxxxxxxxxx>
---
 include/linux/dma-mapping.h | 45 ++++++-------------------------------------
 lib/Makefile                |  2 +-
 lib/dma-mapping.c           | 47 +++++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 54 insertions(+), 40 deletions(-)
 create mode 100644 lib/dma-mapping.c

diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h
index 0977317c6835..1a357a65f4cc 100644
--- a/include/linux/dma-mapping.h
+++ b/include/linux/dma-mapping.h
@@ -473,46 +473,13 @@ dma_get_sgtable_attrs(struct device *dev, struct sg_table *sgt, void *cpu_addr,
 #define arch_dma_alloc_attrs(dev, flag)	(true)
 #endif
 
-static inline void *dma_alloc_attrs(struct device *dev, size_t size,
-				       dma_addr_t *dma_handle, gfp_t flag,
-				       unsigned long attrs)
-{
-	const struct dma_map_ops *ops = get_dma_ops(dev);
-	void *cpu_addr;
-
-	BUG_ON(!ops);
-
-	if (dma_alloc_from_coherent(dev, size, dma_handle, &cpu_addr))
-		return cpu_addr;
-
-	if (!arch_dma_alloc_attrs(&dev, &flag))
-		return NULL;
-	if (!ops->alloc)
-		return NULL;
-
-	cpu_addr = ops->alloc(dev, size, dma_handle, flag, attrs);
-	debug_dma_alloc_coherent(dev, size, *dma_handle, cpu_addr);
-	return cpu_addr;
-}
-
-static inline void dma_free_attrs(struct device *dev, size_t size,
-				     void *cpu_addr, dma_addr_t dma_handle,
-				     unsigned long attrs)
-{
-	const struct dma_map_ops *ops = get_dma_ops(dev);
-
-	BUG_ON(!ops);
-	WARN_ON(irqs_disabled());
-
-	if (dma_release_from_coherent(dev, get_order(size), cpu_addr))
-		return;
-
-	if (!ops->free || !cpu_addr)
-		return;
+void *dma_alloc_attrs(struct device *dev, size_t size,
+		      dma_addr_t *dma_handle, gfp_t flag,
+		      unsigned long attrs);
 
-	debug_dma_free_coherent(dev, size, cpu_addr, dma_handle);
-	ops->free(dev, size, cpu_addr, dma_handle, attrs);
-}
+void dma_free_attrs(struct device *dev, size_t size,
+		    void *cpu_addr, dma_addr_t dma_handle,
+		    unsigned long attrs);
 
 static inline void *dma_alloc_coherent(struct device *dev, size_t size,
 		dma_addr_t *dma_handle, gfp_t flag)
diff --git a/lib/Makefile b/lib/Makefile
index 320ac46a8725..7fcfe102d244 100644
--- a/lib/Makefile
+++ b/lib/Makefile
@@ -23,7 +23,7 @@ lib-y := ctype.o string.o vsprintf.o cmdline.o \
 	 flex_proportions.o ratelimit.o show_mem.o \
 	 is_single_threaded.o plist.o decompress.o kobject_uevent.o \
 	 earlycpio.o seq_buf.o siphash.o \
-	 nmi_backtrace.o nodemask.o win_minmax.o
+	 nmi_backtrace.o nodemask.o win_minmax.o dma-mapping.o
 
 CFLAGS_radix-tree.o += -DCONFIG_SPARSE_RCU_POINTER
 CFLAGS_idr.o += -DCONFIG_SPARSE_RCU_POINTER
diff --git a/lib/dma-mapping.c b/lib/dma-mapping.c
new file mode 100644
index 000000000000..3f221652c7e1
--- /dev/null
+++ b/lib/dma-mapping.c
@@ -0,0 +1,47 @@
+#include <linux/dma-mapping.h>
+#include <linux/module.h>
+
+void *dma_alloc_attrs(struct device *dev, size_t size,
+		      dma_addr_t *dma_handle, gfp_t flag,
+		      unsigned long attrs)
+{
+	const struct dma_map_ops *ops = get_dma_ops(dev);
+	void *cpu_addr;
+
+	BUG_ON(!ops);
+
+	if (dma_alloc_from_coherent(dev, size, dma_handle, &cpu_addr))
+		return cpu_addr;
+
+	if (!arch_dma_alloc_attrs(&dev, &flag))
+		return NULL;
+	if (!ops->alloc)
+		return NULL;
+
+	cpu_addr = ops->alloc(dev, size, dma_handle, flag, attrs);
+	debug_dma_alloc_coherent(dev, size, *dma_handle, cpu_addr);
+	return cpu_addr;
+}
+
+EXPORT_SYMBOL(dma_alloc_attrs);
+
+void dma_free_attrs(struct device *dev, size_t size,
+		    void *cpu_addr, dma_addr_t dma_handle,
+		    unsigned long attrs)
+{
+	const struct dma_map_ops *ops = get_dma_ops(dev);
+
+	BUG_ON(!ops);
+	WARN_ON(irqs_disabled());
+
+	if (dma_release_from_coherent(dev, get_order(size), cpu_addr))
+		return;
+
+	if (!ops->free || !cpu_addr)
+		return;
+
+	debug_dma_free_coherent(dev, size, cpu_addr, dma_handle);
+	ops->free(dev, size, cpu_addr, dma_handle, attrs);
+}
+
+EXPORT_SYMBOL(dma_free_attrs);
-- 
2.9.3