Merge branch 'x86-asmlinkage-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 LTO changes from Peter Anvin:
 "More infrastructure work in preparation for link-time optimization
  (LTO).  Most of these changes is to make sure symbols accessed from
  assembly code are properly marked as visible so the linker doesn't
  remove them.

  My understanding is that the changes to support LTO are still not
  upstream in binutils, but are on the way there.  This patchset should
  conclude the x86-specific changes, and remaining patches to actually
  enable LTO will be fed through the Kbuild tree (other than keeping up
  with changes to the x86 code base, of course), although not
  necessarily in this merge window"

* 'x86-asmlinkage-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (25 commits)
  Kbuild, lto: Handle basic LTO in modpost
  Kbuild, lto: Disable LTO for asm-offsets.c
  Kbuild, lto: Add a gcc-ld script to let run gcc as ld
  Kbuild, lto: add ld-version and ld-ifversion macros
  Kbuild, lto: Drop .number postfixes in modpost
  Kbuild, lto, workaround: Don't warn for initcall_reference in modpost
  lto: Disable LTO for sys_ni
  lto: Handle LTO common symbols in module loader
  lto, workaround: Add workaround for initcall reordering
  lto: Make asmlinkage __visible
  x86, lto: Disable LTO for the x86 VDSO
  initconst, x86: Fix initconst mistake in ts5500 code
  initconst: Fix initconst mistake in dcdbas
  asmlinkage: Make trace_hardirqs_on/off_caller visible
  asmlinkage, x86: Fix 32bit memcpy for LTO
  asmlinkage Make __stack_chk_failed and memcmp visible
  asmlinkage: Mark rwsem functions that can be called from assembler asmlinkage
  asmlinkage: Make main_extable_sort_needed visible
  asmlinkage, mutex: Mark __visible
  asmlinkage: Make trace_hardirq visible
  ...

9 files changed, 24 insertions, 13 deletions

diff --git a/kernel/Makefile b/kernel/Makefile
index 4fd8474..f2a8b62 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -18,6 +18,9 @@ CFLAGS_REMOVE_cgroup-debug.o = -pg
 CFLAGS_REMOVE_irq_work.o = -pg
 endif
 
+# cond_syscall is currently not LTO compatible
+CFLAGS_sys_ni.o = $(DISABLE_LTO)
+
 obj-y += sched/
 obj-y += locking/
 obj-y += power/
diff --git a/kernel/extable.c b/kernel/extable.c
index 763faf0..d8a6446 100644
--- a/kernel/extable.c
+++ b/kernel/extable.c
@@ -36,7 +36,7 @@ extern struct exception_table_entry __start___ex_table[];
 extern struct exception_table_entry __stop___ex_table[];
 
 /* Cleared by build time tools if the table is already sorted. */
-u32 __initdata main_extable_sort_needed = 1;
+u32 __initdata __visible main_extable_sort_needed = 1;
 
 /* Sort the kernel's built-in exception table */
 void __init sort_main_extable(void)
diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c
index bf0c6b0..b0e9467 100644
--- a/kernel/locking/lockdep.c
+++ b/kernel/locking/lockdep.c
@@ -2557,7 +2557,7 @@ static void __trace_hardirqs_on_caller(unsigned long ip)
 	debug_atomic_inc(hardirqs_on_events);
 }
 
-void trace_hardirqs_on_caller(unsigned long ip)
+__visible void trace_hardirqs_on_caller(unsigned long ip)
 {
 	time_hardirqs_on(CALLER_ADDR0, ip);
 
@@ -2610,7 +2610,7 @@ EXPORT_SYMBOL(trace_hardirqs_on);
 /*
  * Hardirqs were disabled:
  */
-void trace_hardirqs_off_caller(unsigned long ip)
+__visible void trace_hardirqs_off_caller(unsigned long ip)
 {
 	struct task_struct *curr = current;
 
@@ -4188,7 +4188,7 @@ void debug_show_held_locks(struct task_struct *task)
 }
 EXPORT_SYMBOL_GPL(debug_show_held_locks);
 
-void lockdep_sys_exit(void)
+asmlinkage void lockdep_sys_exit(void)
 {
 	struct task_struct *curr = current;
 
diff --git a/kernel/locking/mutex.c b/kernel/locking/mutex.c
index 14fe72c..bc73d33 100644
--- a/kernel/locking/mutex.c
+++ b/kernel/locking/mutex.c
@@ -75,8 +75,7 @@ EXPORT_SYMBOL(__mutex_init);
  * We also put the fastpath first in the kernel image, to make sure the
  * branch is predicted by the CPU as default-untaken.
  */
-static __used noinline void __sched
-__mutex_lock_slowpath(atomic_t *lock_count);
+__visible void __sched __mutex_lock_slowpath(atomic_t *lock_count);
 
 /**
  * mutex_lock - acquire the mutex
@@ -189,7 +188,8 @@ static inline int mutex_can_spin_on_owner(struct mutex *lock)
 }
 #endif
 
-static __used noinline void __sched __mutex_unlock_slowpath(atomic_t *lock_count);
+__visible __used noinline
+void __sched __mutex_unlock_slowpath(atomic_t *lock_count);
 
 /**
  * mutex_unlock - release the mutex
@@ -716,7 +716,7 @@ __mutex_unlock_common_slowpath(atomic_t *lock_count, int nested)
 /*
  * Release the lock, slowpath:
  */
-static __used noinline void
+__visible void
 __mutex_unlock_slowpath(atomic_t *lock_count)
 {
 	__mutex_unlock_common_slowpath(lock_count, 1);
@@ -773,7 +773,7 @@ int __sched mutex_lock_killable(struct mutex *lock)
 }
 EXPORT_SYMBOL(mutex_lock_killable);
 
-static __used noinline void __sched
+__visible void __sched
 __mutex_lock_slowpath(atomic_t *lock_count)
 {
 	struct mutex *lock = container_of(lock_count, struct mutex, count);
diff --git a/kernel/locking/rwsem-xadd.c b/kernel/locking/rwsem-xadd.c
index 19c5fa9..1d66e08 100644
--- a/kernel/locking/rwsem-xadd.c
+++ b/kernel/locking/rwsem-xadd.c
@@ -143,6 +143,7 @@ __rwsem_do_wake(struct rw_semaphore *sem, enum rwsem_wake_type wake_type)
 /*
  * wait for the read lock to be granted
  */
+__visible
 struct rw_semaphore __sched *rwsem_down_read_failed(struct rw_semaphore *sem)
 {
 	long count, adjustment = -RWSEM_ACTIVE_READ_BIAS;
@@ -190,6 +191,7 @@ struct rw_semaphore __sched *rwsem_down_read_failed(struct rw_semaphore *sem)
 /*
  * wait until we successfully acquire the write lock
  */
+__visible
 struct rw_semaphore __sched *rwsem_down_write_failed(struct rw_semaphore *sem)
 {
 	long count, adjustment = -RWSEM_ACTIVE_WRITE_BIAS;
@@ -252,6 +254,7 @@ struct rw_semaphore __sched *rwsem_down_write_failed(struct rw_semaphore *sem)
  * handle waking up a waiter on the semaphore
  * - up_read/up_write has decremented the active part of count if we come here
  */
+__visible
 struct rw_semaphore *rwsem_wake(struct rw_semaphore *sem)
 {
 	unsigned long flags;
@@ -272,6 +275,7 @@ struct rw_semaphore *rwsem_wake(struct rw_semaphore *sem)
  * - caller incremented waiting part of count and discovered it still negative
  * - just wake up any readers at the front of the queue
  */
+__visible
 struct rw_semaphore *rwsem_downgrade_wake(struct rw_semaphore *sem)
 {
 	unsigned long flags;
diff --git a/kernel/module.c b/kernel/module.c
index ca2c1ad..8dc7f5e 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -1948,6 +1948,10 @@ static int simplify_symbols(struct module *mod, const struct load_info *info)
 
 		switch (sym[i].st_shndx) {
 		case SHN_COMMON:
+			/* Ignore common symbols */
+			if (!strncmp(name, "__gnu_lto", 9))
+				break;
+
 			/* We compiled with -fno-common.  These are not
 			   supposed to happen.  */
 			pr_debug("Common symbol: %s\n", name);
diff --git a/kernel/panic.c b/kernel/panic.c
index 2270cfd..cca8a91 100644
--- a/kernel/panic.c
+++ b/kernel/panic.c
@@ -459,7 +459,7 @@ EXPORT_SYMBOL(warn_slowpath_null);
  * Called when gcc's -fstack-protector feature is used, and
  * gcc detects corruption of the on-stack canary value
  */
-void __stack_chk_fail(void)
+__visible void __stack_chk_fail(void)
 {
 	panic("stack-protector: Kernel stack is corrupted in: %p\n",
 		__builtin_return_address(0));
diff --git a/kernel/timer.c b/kernel/timer.c
index accfd24..d78de04 100644
--- a/kernel/timer.c
+++ b/kernel/timer.c
@@ -52,7 +52,7 @@
 #define CREATE_TRACE_POINTS
 #include <trace/events/timer.h>
 
-u64 jiffies_64 __cacheline_aligned_in_smp = INITIAL_JIFFIES;
+__visible u64 jiffies_64 __cacheline_aligned_in_smp = INITIAL_JIFFIES;
 
 EXPORT_SYMBOL(jiffies_64);
 
diff --git a/kernel/trace/trace_irqsoff.c b/kernel/trace/trace_irqsoff.c
index 2aefbee..887ef88 100644
--- a/kernel/trace/trace_irqsoff.c
+++ b/kernel/trace/trace_irqsoff.c
@@ -498,14 +498,14 @@ void trace_hardirqs_off(void)
 }
 EXPORT_SYMBOL(trace_hardirqs_off);
 
-void trace_hardirqs_on_caller(unsigned long caller_addr)
+__visible void trace_hardirqs_on_caller(unsigned long caller_addr)
 {
 	if (!preempt_trace() && irq_trace())
 		stop_critical_timing(CALLER_ADDR0, caller_addr);
 }
 EXPORT_SYMBOL(trace_hardirqs_on_caller);
 
-void trace_hardirqs_off_caller(unsigned long caller_addr)
+__visible void trace_hardirqs_off_caller(unsigned long caller_addr)
 {
 	if (!preempt_trace() && irq_trace())
 		start_critical_timing(CALLER_ADDR0, caller_addr);