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, 17 insertions, 13 deletions

diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig
index 0582260fb6c2..e66745decea1 100644
--- a/arch/riscv/Kconfig
+++ b/arch/riscv/Kconfig
@@ -48,6 +48,7 @@ config RISCV
 	select RISCV_TIMER
 	select GENERIC_IRQ_MULTI_HANDLER
 	select ARCH_HAS_PTE_SPECIAL
+	select ARCH_HAS_MMIOWB
 	select HAVE_EBPF_JIT if 64BIT
 
 config MMU
diff --git a/arch/riscv/include/asm/io.h b/arch/riscv/include/asm/io.h
index 1d9c1376dc64..744fd92e77bc 100644
--- a/arch/riscv/include/asm/io.h
+++ b/arch/riscv/include/asm/io.h
@@ -20,6 +20,7 @@
 #define _ASM_RISCV_IO_H
 
 #include <linux/types.h>
+#include <asm/mmiowb.h>
 
 extern void __iomem *ioremap(phys_addr_t offset, unsigned long size);
 
@@ -100,18 +101,6 @@ static inline u64 __raw_readq(const volatile void __iomem *addr)
 #endif
 
 /*
- * FIXME: I'm flip-flopping on whether or not we should keep this or enforce
- * the ordering with I/O on spinlocks like PowerPC does.  The worry is that
- * drivers won't get this correct, but I also don't want to introduce a fence
- * into the lock code that otherwise only uses AMOs (and is essentially defined
- * by the ISA to be correct).   For now I'm leaving this here: "o,w" is
- * sufficient to ensure that all writes to the device have completed before the
- * write to the spinlock is allowed to commit.  I surmised this from reading
- * "ACQUIRES VS I/O ACCESSES" in memory-barriers.txt.
- */
-#define mmiowb()	__asm__ __volatile__ ("fence o,w" : : : "memory");
-
-/*
  * Unordered I/O memory access primitives.  These are even more relaxed than
  * the relaxed versions, as they don't even order accesses between successive
  * operations to the I/O regions.
@@ -165,7 +154,7 @@ static inline u64 __raw_readq(const volatile void __iomem *addr)
 #define __io_br()	do {} while (0)
 #define __io_ar(v)	__asm__ __volatile__ ("fence i,r" : : : "memory");
 #define __io_bw()	__asm__ __volatile__ ("fence w,o" : : : "memory");
-#define __io_aw()	do {} while (0)
+#define __io_aw()	mmiowb_set_pending()
 
 #define readb(c)	({ u8  __v; __io_br(); __v = readb_cpu(c); __io_ar(__v); __v; })
 #define readw(c)	({ u16 __v; __io_br(); __v = readw_cpu(c); __io_ar(__v); __v; })
diff --git a/arch/riscv/include/asm/mmiowb.h b/arch/riscv/include/asm/mmiowb.h
new file mode 100644
index 000000000000..5d7e3a2b4e3b
--- /dev/null
+++ b/arch/riscv/include/asm/mmiowb.h
@@ -0,0 +1,14 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef _ASM_RISCV_MMIOWB_H
+#define _ASM_RISCV_MMIOWB_H
+
+/*
+ * "o,w" is sufficient to ensure that all writes to the device have completed
+ * before the write to the spinlock is allowed to commit.
+ */
+#define mmiowb()	__asm__ __volatile__ ("fence o,w" : : : "memory");
+
+#include <asm-generic/mmiowb.h>
+
+#endif	/* ASM_RISCV_MMIOWB_H */