Merge tag 'arm64-mmiowb' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux

Pull mmiowb removal from Will Deacon:
 "Remove Mysterious Macro Intended to Obscure Weird Behaviours (mmiowb())

  Remove mmiowb() from the kernel memory barrier API and instead, for
  architectures that need it, hide the barrier inside spin_unlock() when
  MMIO has been performed inside the critical section.

  The only relatively recent changes have been addressing review
  comments on the documentation, which is in a much better shape thanks
  to the efforts of Ben and Ingo.

  I was initially planning to split this into two pull requests so that
  you could run the coccinelle script yourself, however it's been plain
  sailing in linux-next so I've just included the whole lot here to keep
  things simple"

* tag 'arm64-mmiowb' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux: (23 commits)
  docs/memory-barriers.txt: Update I/O section to be clearer about CPU vs thread
  docs/memory-barriers.txt: Fix style, spacing and grammar in I/O section
  arch: Remove dummy mmiowb() definitions from arch code
  net/ethernet/silan/sc92031: Remove stale comment about mmiowb()
  i40iw: Redefine i40iw_mmiowb() to do nothing
  scsi/qla1280: Remove stale comment about mmiowb()
  drivers: Remove explicit invocations of mmiowb()
  drivers: Remove useless trailing comments from mmiowb() invocations
  Documentation: Kill all references to mmiowb()
  riscv/mmiowb: Hook up mmwiob() implementation to asm-generic code
  powerpc/mmiowb: Hook up mmwiob() implementation to asm-generic code
  ia64/mmiowb: Add unconditional mmiowb() to arch_spin_unlock()
  mips/mmiowb: Add unconditional mmiowb() to arch_spin_unlock()
  sh/mmiowb: Add unconditional mmiowb() to arch_spin_unlock()
  m68k/io: Remove useless definition of mmiowb()
  nds32/io: Remove useless definition of mmiowb()
  x86/io: Remove useless definition of mmiowb()
  arm64/io: Remove useless definition of mmiowb()
  ARM/io: Remove useless definition of mmiowb()
  mmiowb: Hook up mmiowb helpers to spinlocks and generic I/O accessors
  ...

3 files changed, 19 insertions, 1 deletions

diff --git a/kernel/Kconfig.locks b/kernel/Kconfig.locks
index e335953fa704..bf770d7556f7 100644
--- a/kernel/Kconfig.locks
+++ b/kernel/Kconfig.locks
@@ -251,3 +251,10 @@ config ARCH_USE_QUEUED_RWLOCKS
 config QUEUED_RWLOCKS
 	def_bool y if ARCH_USE_QUEUED_RWLOCKS
 	depends on SMP
+
+config ARCH_HAS_MMIOWB
+	bool
+
+config MMIOWB
+	def_bool y if ARCH_HAS_MMIOWB
+	depends on SMP
diff --git a/kernel/locking/spinlock.c b/kernel/locking/spinlock.c
index 936f3d14dd6b..0ff08380f531 100644
--- a/kernel/locking/spinlock.c
+++ b/kernel/locking/spinlock.c
@@ -22,6 +22,13 @@
 #include <linux/debug_locks.h>
 #include <linux/export.h>
 
+#ifdef CONFIG_MMIOWB
+#ifndef arch_mmiowb_state
+DEFINE_PER_CPU(struct mmiowb_state, __mmiowb_state);
+EXPORT_PER_CPU_SYMBOL(__mmiowb_state);
+#endif
+#endif
+
 /*
  * If lockdep is enabled then we use the non-preemption spin-ops
  * even on CONFIG_PREEMPT, because lockdep assumes that interrupts are
diff --git a/kernel/locking/spinlock_debug.c b/kernel/locking/spinlock_debug.c
index 9aa0fccd5d43..399669f7eba8 100644
--- a/kernel/locking/spinlock_debug.c
+++ b/kernel/locking/spinlock_debug.c
@@ -111,6 +111,7 @@ void do_raw_spin_lock(raw_spinlock_t *lock)
 {
 	debug_spin_lock_before(lock);
 	arch_spin_lock(&lock->raw_lock);
+	mmiowb_spin_lock();
 	debug_spin_lock_after(lock);
 }
 
@@ -118,8 +119,10 @@ int do_raw_spin_trylock(raw_spinlock_t *lock)
 {
 	int ret = arch_spin_trylock(&lock->raw_lock);
 
-	if (ret)
+	if (ret) {
+		mmiowb_spin_lock();
 		debug_spin_lock_after(lock);
+	}
 #ifndef CONFIG_SMP
 	/*
 	 * Must not happen on UP:
@@ -131,6 +134,7 @@ int do_raw_spin_trylock(raw_spinlock_t *lock)
 
 void do_raw_spin_unlock(raw_spinlock_t *lock)
 {
+	mmiowb_spin_unlock();
 	debug_spin_unlock(lock);
 	arch_spin_unlock(&lock->raw_lock);
 }