x86: Support __attribute__((__cold__)) in gcc 4.3

gcc 4.3 supports a new __attribute__((__cold__)) to mark functions cold. Any
path directly leading to a call of this function will be unlikely. And gcc
will try to generate smaller code for the function itself.

Please use with care. The code generation advantage isn't large and in most
cases it is not worth uglifying code with this.

This patch marks some common error functions like panic(), printk()
as cold.  This will longer term make many unlikely()s unnecessary, although
we can keep them for now for older compilers.

BUG is not marked cold because there is currently no way to tell
gcc to mark a inline function told.

Also all __init and __exit functions are marked cold. With a non -Os
build this will tell the compiler to generate slightly smaller code
for them. I think it currently only uses less alignments for labels,
but that might change in the future.

One disadvantage over *likely() is that they cannot be easily instrumented
to verify them.

Another drawback is that only the latest gcc 4.3 snapshots support this.
Unfortunately we cannot detect this using the preprocessor. This means older
snapshots will fail now. I don't think that's a problem because they are
unreleased compilers that nobody should be using.

gcc also has a __hot__ attribute, but I don't see any sense in using
this in the kernel right now. But someday I hope gcc will be able
to use more aggressive optimizing for hot functions even in -Os,
if that happens it should be added.

Includes compile fix from Thomas Gleixner.

Cc: Jan Hubicka <jh@suse.cz>
Signed-off-by: Andi Kleen <ak@suse.de>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/include/linux/compiler-gcc4.h b/include/linux/compiler-gcc4.h
index a03e939..14f7494 100644 (file)
--- a/include/linux/compiler-gcc4.h
+++ b/include/linux/compiler-gcc4.h
@@ -23,3 +23,21 @@
  * code
  */
 #define uninitialized_var(x) x = x
+
+#if !(__GNUC__ == 4 && __GNUC_MINOR__ < 3)
+/* Mark functions as cold. gcc will assume any path leading to a call
+   to them will be unlikely.  This means a lot of manual unlikely()s
+   are unnecessary now for any paths leading to the usual suspects
+   like BUG(), printk(), panic() etc. [but let's keep them for now for
+   older compilers]
+
+   Early snapshots of gcc 4.3 don't support this and we can't detect this
+   in the preprocessor, but we can live with this because they're unreleased.
+   Maketime probing would be overkill here.
+
+   gcc also has a __attribute__((__hot__)) to move hot functions into
+   a special section, but I don't see any sense in this right now in
+   the kernel context */
+#define __cold                 __attribute__((__cold__))
+
+#endif

diff --git a/include/linux/compiler.h b/include/linux/compiler.h
index 8287a72..12a1291 100644 (file)
--- a/include/linux/compiler.h
+++ b/include/linux/compiler.h
@@ -174,4 +174,13 @@ extern void __chk_io_ptr(const void __iomem *);
 # define __attribute_const__   /* unimplemented */
 #endif
 
+/*
+ * Tell gcc if a function is cold. The compiler will assume any path
+ * directly leading to the call is unlikely.
+ */
+
+#ifndef __cold
+#define __cold
+#endif
+
 #endif /* __LINUX_COMPILER_H */

diff --git a/include/linux/init.h b/include/linux/init.h
index 5b52853..f0d0e32 100644 (file)
--- a/include/linux/init.h
+++ b/include/linux/init.h
@@ -40,10 +40,10 @@
 
 /* These are for everybody (although not all archs will actually
    discard it in modules) */
-#define __init         __attribute__ ((__section__ (".init.text")))
+#define __init         __attribute__ ((__section__ (".init.text"))) __cold
 #define __initdata     __attribute__ ((__section__ (".init.data")))
 #define __exitdata     __attribute__ ((__section__(".exit.data")))
-#define __exit_call    __attribute_used__ __attribute__ ((__section__ (".exitcall.exit")))
+#define __exit_call    __attribute_used__ __attribute__ ((__section__ (".exitcall.exit"))) __cold
 
 /* modpost check for section mismatches during the kernel build.
  * A section mismatch happens when there are references from a
@@ -59,9 +59,9 @@
 #define __initdata_refok          __attribute__ ((__section__ (".data.init.refok")))
 
 #ifdef MODULE
-#define __exit         __attribute__ ((__section__(".exit.text")))
+#define __exit         __attribute__ ((__section__(".exit.text"))) __cold
 #else
-#define __exit         __attribute_used__ __attribute__ ((__section__(".exit.text")))
+#define __exit         __attribute_used__ __attribute__ ((__section__(".exit.text"))) __cold
 #endif
 
 /* For assembly routines */

diff --git a/include/linux/kernel.h b/include/linux/kernel.h
index 1eb9cde..4300bb4 100644 (file)
--- a/include/linux/kernel.h
+++ b/include/linux/kernel.h
@@ -106,7 +106,7 @@ extern int cond_resched(void);
 extern struct atomic_notifier_head panic_notifier_list;
 extern long (*panic_blink)(long time);
 NORET_TYPE void panic(const char * fmt, ...)
-       __attribute__ ((NORET_AND format (printf, 1, 2)));
+       __attribute__ ((NORET_AND format (printf, 1, 2))) __cold;
 extern void oops_enter(void);
 extern void oops_exit(void);
 extern int oops_may_print(void);
@@ -155,14 +155,14 @@ extern void dump_thread(struct pt_regs *regs, struct user *dump);
 asmlinkage int vprintk(const char *fmt, va_list args)
        __attribute__ ((format (printf, 1, 0)));
 asmlinkage int printk(const char * fmt, ...)
-       __attribute__ ((format (printf, 1, 2)));
+       __attribute__ ((format (printf, 1, 2))) __cold;
 #else
 static inline int vprintk(const char *s, va_list args)
        __attribute__ ((format (printf, 1, 0)));
 static inline int vprintk(const char *s, va_list args) { return 0; }
 static inline int printk(const char *s, ...)
        __attribute__ ((format (printf, 1, 2)));
-static inline int printk(const char *s, ...) { return 0; }
+static inline int __cold printk(const char *s, ...) { return 0; }
 #endif
 
 unsigned long int_sqrt(unsigned long);
@@ -212,7 +212,7 @@ extern enum system_states {
 #define TAINT_USER                     (1<<6)
 #define TAINT_DIE                      (1<<7)
 
-extern void dump_stack(void);
+extern void dump_stack(void) __cold;
 
 enum {
        DUMP_PREFIX_NONE,