slub tracing: move trace calls out of always inlined functions to reduce kernel code size

Having the trace calls defined in the always inlined kmalloc functions
in include/linux/slub_def.h causes a lot of code duplication as the
trace functions get instantiated for each kamalloc call site. This can
simply be removed by pushing the trace calls down into the functions in
slub.c.

On my x86_64 built this patch shrinks the code size of the kernel by
approx 36K and also shrinks the code size of many modules -- too many to
list here ;)

size vmlinux (2.6.36) reports
       text        data     bss     dec     hex filename
    5410611	 743172	 828928	6982711	 6a8c37	vmlinux
    5373738	 744244	 828928	6946910	 6a005e	vmlinux + patch

The resulting kernel has had some testing & kmalloc trace still seems to
work.

This patch
- moves trace_kmalloc out of the inlined kmalloc() and pushes it down
into kmem_cache_alloc_trace() so this it only get instantiated once.

- rename kmem_cache_alloc_notrace()  to kmem_cache_alloc_trace() to
indicate that now is does have tracing. (maybe this would better being
called something like kmalloc_kmem_cache ?)

- adds a new function kmalloc_order() to handle allocation and tracing
of large allocations of page order.

- removes tracing from the inlined kmalloc_large() replacing them with a
call to kmalloc_order();

- move tracing out of inlined kmalloc_node() and pushing it down into
kmem_cache_alloc_node_trace

- rename kmem_cache_alloc_node_notrace() to
kmem_cache_alloc_node_trace()

- removes the include of trace/events/kmem.h from slub_def.h.

v2
- keep kmalloc_order_trace inline when !CONFIG_TRACE

Signed-off-by: Richard Kennedy <richard@rsk.demon.co.uk>
Signed-off-by: Pekka Enberg <penberg@kernel.org>

1 files changed, 23 insertions, 7 deletions

diff --git a/mm/slub.c b/mm/slub.c
index 8fd5401bb07..7e657aa1947 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -28,6 +28,8 @@
 #include <linux/math64.h>
 #include <linux/fault-inject.h>
 
+#include <trace/events/kmem.h>
+
 /*
  * Lock order:
  *   1. slab_lock(page)
@@ -1774,11 +1776,21 @@ void *kmem_cache_alloc(struct kmem_cache *s, gfp_t gfpflags)
 EXPORT_SYMBOL(kmem_cache_alloc);
 
 #ifdef CONFIG_TRACING
-void *kmem_cache_alloc_notrace(struct kmem_cache *s, gfp_t gfpflags)
+void *kmem_cache_alloc_trace(struct kmem_cache *s, gfp_t gfpflags, size_t size)
+{
+	void *ret = slab_alloc(s, gfpflags, NUMA_NO_NODE, _RET_IP_);
+	trace_kmalloc(_RET_IP_, ret, size, s->size, gfpflags);
+	return ret;
+}
+EXPORT_SYMBOL(kmem_cache_alloc_trace);
+
+void *kmalloc_order_trace(size_t size, gfp_t flags, unsigned int order)
 {
-	return slab_alloc(s, gfpflags, NUMA_NO_NODE, _RET_IP_);
+	void *ret = kmalloc_order(size, flags, order);
+	trace_kmalloc(_RET_IP_, ret, size, PAGE_SIZE << order, flags);
+	return ret;
 }
-EXPORT_SYMBOL(kmem_cache_alloc_notrace);
+EXPORT_SYMBOL(kmalloc_order_trace);
 #endif
 
 #ifdef CONFIG_NUMA
@@ -1794,13 +1806,17 @@ void *kmem_cache_alloc_node(struct kmem_cache *s, gfp_t gfpflags, int node)
 EXPORT_SYMBOL(kmem_cache_alloc_node);
 
 #ifdef CONFIG_TRACING
-void *kmem_cache_alloc_node_notrace(struct kmem_cache *s,
+void *kmem_cache_alloc_node_trace(struct kmem_cache *s,
 				    gfp_t gfpflags,
-				    int node)
+				    int node, size_t size)
 {
-	return slab_alloc(s, gfpflags, node, _RET_IP_);
+	void *ret = slab_alloc(s, gfpflags, node, _RET_IP_);
+
+	trace_kmalloc_node(_RET_IP_, ret,
+			   size, s->size, gfpflags, node);
+	return ret;
 }
-EXPORT_SYMBOL(kmem_cache_alloc_node_notrace);
+EXPORT_SYMBOL(kmem_cache_alloc_node_trace);
 #endif
 #endif