mm, vmalloc: properly track vmalloc users

__vmalloc_node_flags used to be static inline but this has changed by
"mm: introduce kv[mz]alloc helpers" because kvmalloc_node needs to use
it as well and the code is outside of the vmalloc proper.  I haven't
realized that changing this will lead to a subtle bug though.  The
function is responsible to track the caller as well.  This caller is
then printed by /proc/vmallocinfo.  If __vmalloc_node_flags is not
inline then we would get only direct users of __vmalloc_node_flags as
callers (e.g.  v[mz]alloc) which reduces usefulness of this debugging
feature considerably.  It simply doesn't help to see that the given
range belongs to vmalloc as a caller:

  0xffffc90002c79000-0xffffc90002c7d000   16384 vmalloc+0x16/0x18 pages=3 vmalloc N0=3
  0xffffc90002c81000-0xffffc90002c85000   16384 vmalloc+0x16/0x18 pages=3 vmalloc N1=3
  0xffffc90002c8d000-0xffffc90002c91000   16384 vmalloc+0x16/0x18 pages=3 vmalloc N1=3
  0xffffc90002c95000-0xffffc90002c99000   16384 vmalloc+0x16/0x18 pages=3 vmalloc N1=3

We really want to catch the _caller_ of the vmalloc function.  Fix this
issue by making __vmalloc_node_flags static inline again.

Link: http://lkml.kernel.org/r/20170502134657.12381-1-mhocko@kernel.org
Signed-off-by: Michal Hocko <mhocko@suse.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

include/linux/vmalloc.h

@@ -6,6 +6,7 @@
 #include <linux/list.h>
 #include <linux/llist.h>
 #include <asm/page.h>		/* pgprot_t */
+#include <asm/pgtable.h>	/* PAGE_KERNEL */
 #include <linux/rbtree.h>
 
 struct vm_area_struct;		/* vma defining user mapping in mm_types.h */
@@ -80,7 +81,25 @@ extern void *__vmalloc_node_range(unsigned long size, unsigned long align,
 			unsigned long start, unsigned long end, gfp_t gfp_mask,
 			pgprot_t prot, unsigned long vm_flags, int node,
 			const void *caller);
+#ifndef CONFIG_MMU
 extern void *__vmalloc_node_flags(unsigned long size, int node, gfp_t flags);
+#else
+extern void *__vmalloc_node(unsigned long size, unsigned long align,
+			    gfp_t gfp_mask, pgprot_t prot,
+			    int node, const void *caller);
+
+/*
+ * We really want to have this inlined due to caller tracking. This
+ * function is used by the highlevel vmalloc apis and so we want to track
+ * their callers and inlining will achieve that.
+ */
+static inline void *__vmalloc_node_flags(unsigned long size,
+					int node, gfp_t flags)
+{
+	return __vmalloc_node(size, 1, flags, PAGE_KERNEL,
+					node, __builtin_return_address(0));
+}
+#endif
 
 extern void vfree(const void *addr);
 extern void vfree_atomic(const void *addr);

mm/vmalloc.c

@@ -1649,9 +1649,6 @@ void *vmap(struct page **pages, unsigned int count,
 }
 EXPORT_SYMBOL(vmap);
 
-static void *__vmalloc_node(unsigned long size, unsigned long align,
-			    gfp_t gfp_mask, pgprot_t prot,
-			    int node, const void *caller);
 static void *__vmalloc_area_node(struct vm_struct *area, gfp_t gfp_mask,
 				 pgprot_t prot, int node)
 {
@@ -1794,7 +1791,7 @@ fail:
  *	with mm people.
  *
  */
-static void *__vmalloc_node(unsigned long size, unsigned long align,
+void *__vmalloc_node(unsigned long size, unsigned long align,
 			    gfp_t gfp_mask, pgprot_t prot,
 			    int node, const void *caller)
 {
@@ -1809,13 +1806,6 @@ void *__vmalloc(unsigned long size, gfp_t gfp_mask, pgprot_t prot)
 }
 EXPORT_SYMBOL(__vmalloc);
 
-void *__vmalloc_node_flags(unsigned long size,
-					int node, gfp_t flags)
-{
-	return __vmalloc_node(size, 1, flags, PAGE_KERNEL,
-					node, __builtin_return_address(0));
-}
-
 /**
  *	vmalloc  -  allocate virtually contiguous memory
  *	@size:		allocation size