Merge tag 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mst/vhost

Pull virtio barrier rework+fixes from Michael Tsirkin:
 "This adds a new kind of barrier, and reworks virtio and xen to use it.

  Plus some fixes here and there"

* tag 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mst/vhost: (44 commits)
  checkpatch: add virt barriers
  checkpatch: check for __smp outside barrier.h
  checkpatch.pl: add missing memory barriers
  virtio: make find_vqs() checkpatch.pl-friendly
  virtio_balloon: fix race between migration and ballooning
  virtio_balloon: fix race by fill and leak
  s390: more efficient smp barriers
  s390: use generic memory barriers
  xen/events: use virt_xxx barriers
  xen/io: use virt_xxx barriers
  xenbus: use virt_xxx barriers
  virtio_ring: use virt_store_mb
  sh: move xchg_cmpxchg to a header by itself
  sh: support 1 and 2 byte xchg
  virtio_ring: update weak barriers to use virt_xxx
  Revert "virtio_ring: Update weak barriers to use dma_wmb/rmb"
  asm-generic: implement virt_xxx memory barriers
  x86: define __smp_xxx
  xtensa: define __smp_xxx
  tile: define __smp_xxx
  ...

6 files changed, 92 insertions, 23 deletions

diff --git a/arch/sh/include/asm/barrier.h b/arch/sh/include/asm/barrier.h
index bf91037db4e0..f887c6465a82 100644
--- a/arch/sh/include/asm/barrier.h
+++ b/arch/sh/include/asm/barrier.h
@@ -32,7 +32,8 @@
 #define ctrl_barrier()	__asm__ __volatile__ ("nop;nop;nop;nop;nop;nop;nop;nop")
 #endif
 
-#define smp_store_mb(var, value) do { (void)xchg(&var, value); } while (0)
+#define __smp_store_mb(var, value) do { (void)xchg(&var, value); } while (0)
+#define smp_store_mb(var, value) __smp_store_mb(var, value)
 
 #include <asm-generic/barrier.h>
 
diff --git a/arch/sh/include/asm/cmpxchg-grb.h b/arch/sh/include/asm/cmpxchg-grb.h
index f848dec9e483..2ed557b31bd9 100644
--- a/arch/sh/include/asm/cmpxchg-grb.h
+++ b/arch/sh/include/asm/cmpxchg-grb.h
@@ -23,6 +23,28 @@ static inline unsigned long xchg_u32(volatile u32 *m, unsigned long val)
 	return retval;
 }
 
+static inline unsigned long xchg_u16(volatile u16 *m, unsigned long val)
+{
+	unsigned long retval;
+
+	__asm__ __volatile__ (
+		"   .align  2             \n\t"
+		"   mova    1f,   r0      \n\t" /* r0 = end point */
+		"   mov    r15,   r1      \n\t" /* r1 = saved sp */
+		"   mov    #-6,   r15     \n\t" /* LOGIN */
+		"   mov.w  @%1,   %0      \n\t" /* load  old value */
+		"   extu.w  %0,   %0      \n\t" /* extend as unsigned */
+		"   mov.w   %2,   @%1     \n\t" /* store new value */
+		"1: mov     r1,   r15     \n\t" /* LOGOUT */
+		: "=&r" (retval),
+		  "+r"  (m),
+		  "+r"  (val)		/* inhibit r15 overloading */
+		:
+		: "memory" , "r0", "r1");
+
+	return retval;
+}
+
 static inline unsigned long xchg_u8(volatile u8 *m, unsigned long val)
 {
 	unsigned long retval;
diff --git a/arch/sh/include/asm/cmpxchg-irq.h b/arch/sh/include/asm/cmpxchg-irq.h
index bd11f630414a..f88877257171 100644
--- a/arch/sh/include/asm/cmpxchg-irq.h
+++ b/arch/sh/include/asm/cmpxchg-irq.h
@@ -14,6 +14,17 @@ static inline unsigned long xchg_u32(volatile u32 *m, unsigned long val)
 	return retval;
 }
 
+static inline unsigned long xchg_u16(volatile u16 *m, unsigned long val)
+{
+	unsigned long flags, retval;
+
+	local_irq_save(flags);
+	retval = *m;
+	*m = val;
+	local_irq_restore(flags);
+	return retval;
+}
+
 static inline unsigned long xchg_u8(volatile u8 *m, unsigned long val)
 {
 	unsigned long flags, retval;
diff --git a/arch/sh/include/asm/cmpxchg-llsc.h b/arch/sh/include/asm/cmpxchg-llsc.h
index 47136661a203..fcfd32271bff 100644
--- a/arch/sh/include/asm/cmpxchg-llsc.h
+++ b/arch/sh/include/asm/cmpxchg-llsc.h
@@ -22,29 +22,8 @@ static inline unsigned long xchg_u32(volatile u32 *m, unsigned long val)
 	return retval;
 }
 
-static inline unsigned long xchg_u8(volatile u8 *m, unsigned long val)
-{
-	unsigned long retval;
-	unsigned long tmp;
-
-	__asm__ __volatile__ (
-		"1:					\n\t"
-		"movli.l	@%2, %0	! xchg_u8	\n\t"
-		"mov		%0, %1			\n\t"
-		"mov		%3, %0			\n\t"
-		"movco.l	%0, @%2			\n\t"
-		"bf		1b			\n\t"
-		"synco					\n\t"
-		: "=&z"(tmp), "=&r" (retval)
-		: "r" (m), "r" (val & 0xff)
-		: "t", "memory"
-	);
-
-	return retval;
-}
-
 static inline unsigned long
-__cmpxchg_u32(volatile int *m, unsigned long old, unsigned long new)
+__cmpxchg_u32(volatile u32 *m, unsigned long old, unsigned long new)
 {
 	unsigned long retval;
 	unsigned long tmp;
@@ -68,4 +47,6 @@ __cmpxchg_u32(volatile int *m, unsigned long old, unsigned long new)
 	return retval;
 }
 
+#include <asm/cmpxchg-xchg.h>
+
 #endif /* __ASM_SH_CMPXCHG_LLSC_H */
diff --git a/arch/sh/include/asm/cmpxchg-xchg.h b/arch/sh/include/asm/cmpxchg-xchg.h
new file mode 100644
index 000000000000..7219719c23a3
--- /dev/null
+++ b/arch/sh/include/asm/cmpxchg-xchg.h
@@ -0,0 +1,51 @@
+#ifndef __ASM_SH_CMPXCHG_XCHG_H
+#define __ASM_SH_CMPXCHG_XCHG_H
+
+/*
+ * Copyright (C) 2016 Red Hat, Inc.
+ * Author: Michael S. Tsirkin <mst@redhat.com>
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2.  See the
+ * file "COPYING" in the main directory of this archive for more details.
+ */
+#include <linux/bitops.h>
+#include <asm/byteorder.h>
+
+/*
+ * Portable implementations of 1 and 2 byte xchg using a 4 byte cmpxchg.
+ * Note: this header isn't self-contained: before including it, __cmpxchg_u32
+ * must be defined first.
+ */
+static inline u32 __xchg_cmpxchg(volatile void *ptr, u32 x, int size)
+{
+	int off = (unsigned long)ptr % sizeof(u32);
+	volatile u32 *p = ptr - off;
+#ifdef __BIG_ENDIAN
+	int bitoff = (sizeof(u32) - 1 - off) * BITS_PER_BYTE;
+#else
+	int bitoff = off * BITS_PER_BYTE;
+#endif
+	u32 bitmask = ((0x1 << size * BITS_PER_BYTE) - 1) << bitoff;
+	u32 oldv, newv;
+	u32 ret;
+
+	do {
+		oldv = READ_ONCE(*p);
+		ret = (oldv & bitmask) >> bitoff;
+		newv = (oldv & ~bitmask) | (x << bitoff);
+	} while (__cmpxchg_u32(p, oldv, newv) != oldv);
+
+	return ret;
+}
+
+static inline unsigned long xchg_u16(volatile u16 *m, unsigned long val)
+{
+	return __xchg_cmpxchg(m, val, sizeof *m);
+}
+
+static inline unsigned long xchg_u8(volatile u8 *m, unsigned long val)
+{
+	return __xchg_cmpxchg(m, val, sizeof *m);
+}
+
+#endif /* __ASM_SH_CMPXCHG_XCHG_H */
diff --git a/arch/sh/include/asm/cmpxchg.h b/arch/sh/include/asm/cmpxchg.h
index 85c97b188d71..5225916c1057 100644
--- a/arch/sh/include/asm/cmpxchg.h
+++ b/arch/sh/include/asm/cmpxchg.h
@@ -27,6 +27,9 @@ extern void __xchg_called_with_bad_pointer(void);
 	case 4:						\
 		__xchg__res = xchg_u32(__xchg_ptr, x);	\
 		break;					\
+	case 2:						\
+		__xchg__res = xchg_u16(__xchg_ptr, x);	\
+		break;					\
 	case 1:						\
 		__xchg__res = xchg_u8(__xchg_ptr, x);	\
 		break;					\