[RFC][PATCH 3/5] arch: s/smp_mb__(before|after)_(atomic|clear)_(dec,inc,bit)/smp_mb__\1/g

From: Peter Zijlstra
Date: Thu Feb 06 2014 - 08:53:37 EST

Next message: Peter Zijlstra: "[RFC][PATCH 4/5] arch: Generic atomic.h cleanup"
Previous message: Peter Zijlstra: "[RFC][PATCH 5/5] arch: Sanitize atomic_t bitwise ops"
In reply to: Peter Zijlstra: "Re: [RFC][PATCH 5/5] arch: Sanitize atomic_t bitwise ops"
Next in thread: Paul E. McKenney: "Re: [RFC][PATCH 3/5] arch:s/smp_mb__(before|after)_(atomic|clear)_(dec,inc,bit)/smp_mb__\1/g"
Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]

Because atomic ops are implemented the same across an architecture,
the current incomplete set of extra barriers:

smp_mb__before_atomic_inc()
smp_mb__after_atomic_inc()
smp_mb__before_atomic_dec()
smp_mb__after_atomic_dec()
smp_mb__before_clear_bit()
smp_mb__after_clear_bit()

is both incomplete and superfluous.

It is incomplete because there are far more atomic operations that do
not return values -- such as atomic_add(), set_bit() etc. And it is
superfluous because they're all the same anyway.

Simplify things by reducing the triplicate set into a single set of
barriers that is valid for all void atomic ops:

smp_mb__before_atomic()
smp_mb__after_atomic()

Signed-off-by: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
---
Documentation/atomic_ops.txt | 31 ++++--------
Documentation/memory-barriers.txt | 44 ++++-------------
arch/alpha/include/asm/atomic.h | 5 -
arch/alpha/include/asm/bitops.h | 3 -
arch/arc/include/asm/atomic.h | 5 -
arch/arc/include/asm/bitops.h | 5 -
arch/arm/include/asm/atomic.h | 5 -
arch/arm/include/asm/barrier.h | 3 +
arch/arm/include/asm/bitops.h | 4 -
arch/arm64/include/asm/atomic.h | 5 -
arch/arm64/include/asm/barrier.h | 3 +
arch/arm64/include/asm/bitops.h | 9 ---
arch/avr32/include/asm/atomic.h | 5 -
arch/avr32/include/asm/bitops.h | 9 ---
arch/blackfin/include/asm/barrier.h | 3 +
arch/blackfin/include/asm/bitops.h | 14 -----
arch/c6x/include/asm/bitops.h | 8 ---
arch/cris/include/asm/atomic.h | 7 --
arch/cris/include/asm/bitops.h | 9 ---
arch/frv/include/asm/atomic.h | 7 --
arch/frv/include/asm/bitops.h | 6 --
arch/hexagon/include/asm/atomic.h | 6 --
arch/hexagon/include/asm/bitops.h | 4 -
arch/ia64/include/asm/atomic.h | 6 --
arch/ia64/include/asm/barrier.h | 3 +
arch/ia64/include/asm/bitops.h | 6 --
arch/m32r/include/asm/atomic.h | 7 --
arch/m32r/include/asm/bitops.h | 6 --
arch/m68k/include/asm/atomic.h | 8 ---
arch/m68k/include/asm/bitops.h | 7 --
arch/metag/include/asm/atomic.h | 6 --
arch/metag/include/asm/barrier.h | 3 +
arch/metag/include/asm/bitops.h | 6 --
arch/mips/include/asm/atomic.h | 9 ---
arch/mips/include/asm/barrier.h | 3 +
arch/mips/include/asm/bitops.h | 11 ----
arch/mips/kernel/irq.c | 4 -
arch/mn10300/include/asm/atomic.h | 7 --
arch/mn10300/include/asm/bitops.h | 4 -
arch/mn10300/mm/tlb-smp.c | 4 -
arch/openrisc/include/asm/bitops.h | 9 ---
arch/parisc/include/asm/atomic.h | 6 --
arch/parisc/include/asm/bitops.h | 4 -
arch/powerpc/include/asm/atomic.h | 6 --
arch/powerpc/include/asm/barrier.h | 3 +
arch/powerpc/include/asm/bitops.h | 6 --
arch/powerpc/kernel/crash.c | 2
arch/s390/include/asm/atomic.h | 6 --
arch/s390/include/asm/barrier.h | 5 +
arch/s390/include/asm/bitops.h | 1
arch/score/include/asm/bitops.h | 7 --
arch/sh/include/asm/atomic.h | 6 --
arch/sh/include/asm/bitops.h | 7 --
arch/sparc/include/asm/atomic_32.h | 7 --
arch/sparc/include/asm/atomic_64.h | 7 --
arch/sparc/include/asm/barrier_64.h | 3 +
arch/sparc/include/asm/bitops_32.h | 4 -
arch/sparc/include/asm/bitops_64.h | 4 -
arch/tile/include/asm/atomic_32.h | 10 ---
arch/tile/include/asm/atomic_64.h | 6 --
arch/tile/include/asm/barrier.h | 14 +++++
arch/tile/include/asm/bitops.h | 1
arch/tile/include/asm/bitops_32.h | 8 ---
arch/tile/include/asm/bitops_64.h | 4 -
arch/x86/include/asm/atomic.h | 7 --
arch/x86/include/asm/barrier.h | 4 +
arch/x86/include/asm/bitops.h | 6 --
arch/x86/include/asm/sync_bitops.h | 2
arch/x86/kernel/apic/hw_nmi.c | 2
arch/xtensa/include/asm/atomic.h | 7 --
arch/xtensa/include/asm/bitops.h | 4 -
block/blk-iopoll.c | 4 -
crypto/chainiv.c | 2
drivers/base/power/domain.c | 2
drivers/block/mtip32xx/mtip32xx.c | 4 -
drivers/cpuidle/coupled.c | 2
drivers/firewire/ohci.c | 2
drivers/gpu/drm/drm_irq.c | 10 +--
drivers/gpu/drm/i915/i915_irq.c | 2
drivers/md/bcache/bcache.h | 2
drivers/md/bcache/closure.h | 2
drivers/md/dm-bufio.c | 8 +--
drivers/md/dm-snap.c | 4 -
drivers/md/dm.c | 2
drivers/md/raid5.c | 2
drivers/media/usb/dvb-usb-v2/dvb_usb_core.c | 6 +-
drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c | 6 +-
drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c | 34 ++++++-------
drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.c | 26 +++++-----
drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c | 12 ++--
drivers/net/ethernet/broadcom/cnic.c | 8 +--
drivers/net/ethernet/brocade/bna/bnad.c | 6 +-
drivers/net/ethernet/chelsio/cxgb/cxgb2.c | 2
drivers/net/ethernet/chelsio/cxgb3/sge.c | 6 +-
drivers/net/ethernet/chelsio/cxgb4/sge.c | 2
drivers/net/ethernet/chelsio/cxgb4vf/sge.c | 2
drivers/net/ethernet/intel/i40e/i40e_main.c | 2
drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 4 -
drivers/net/wireless/ti/wlcore/main.c | 2
drivers/pci/xen-pcifront.c | 4 -
drivers/scsi/isci/remote_device.c | 2
drivers/target/loopback/tcm_loop.c | 4 -
drivers/target/target_core_alua.c | 26 +++++-----
drivers/target/target_core_device.c | 6 +-
drivers/target/target_core_iblock.c | 2
drivers/target/target_core_pr.c | 56 +++++++++++-----------
drivers/target/target_core_transport.c | 16 +++---
drivers/target/target_core_ua.c | 10 +--
drivers/tty/n_tty.c | 2
drivers/tty/serial/mxs-auart.c | 4 -
drivers/usb/gadget/tcm_usb_gadget.c | 4 -
drivers/usb/serial/usb_wwan.c | 2
drivers/vhost/scsi.c | 2
drivers/w1/w1_family.c | 4 -
drivers/xen/xen-pciback/pciback_ops.c | 4 -
fs/btrfs/btrfs_inode.h | 2
fs/btrfs/extent_io.c | 2
fs/btrfs/inode.c | 6 +-
fs/buffer.c | 2
fs/ext4/resize.c | 2
fs/gfs2/glock.c | 8 +--
fs/gfs2/glops.c | 2
fs/gfs2/lock_dlm.c | 4 -
fs/gfs2/recovery.c | 2
fs/gfs2/sys.c | 4 -
fs/jbd2/commit.c | 6 +-
fs/nfs/dir.c | 12 ++--
fs/nfs/inode.c | 2
fs/nfs/nfs4filelayoutdev.c | 4 -
fs/nfs/nfs4state.c | 4 -
fs/nfs/pagelist.c | 6 +-
fs/nfs/pnfs.c | 2
fs/nfs/pnfs.h | 2
fs/nfs/write.c | 4 -
fs/ubifs/lpt_commit.c | 4 -
fs/ubifs/tnc_commit.c | 4 -
include/asm-generic/atomic.h | 7 --
include/asm-generic/barrier.h | 8 +++
include/asm-generic/bitops.h | 8 ---
include/asm-generic/bitops/atomic.h | 2
include/asm-generic/bitops/lock.h | 2
include/linux/buffer_head.h | 2
include/linux/genhd.h | 2
include/linux/interrupt.h | 8 +--
include/linux/netdevice.h | 2
include/linux/sched.h | 6 --
include/linux/sunrpc/sched.h | 8 +--
include/linux/sunrpc/xprt.h | 8 +--
include/linux/tracehook.h | 2
include/net/ip_vs.h | 4 -
kernel/debug/debug_core.c | 4 -
kernel/futex.c | 2
kernel/kmod.c | 2
kernel/rcu/tree.c | 22 ++++----
kernel/rcu/tree_plugin.h | 8 +--
kernel/sched/cpupri.c | 6 +-
kernel/sched/wait.c | 2
mm/backing-dev.c | 2
mm/filemap.c | 4 -
net/atm/pppoatm.c | 2
net/bluetooth/hci_event.c | 4 -
net/core/dev.c | 8 +--
net/core/link_watch.c | 2
net/ipv4/inetpeer.c | 2
net/netfilter/nf_conntrack_core.c | 2
net/rds/ib_recv.c | 4 -
net/rds/iw_recv.c | 4 -
net/rds/send.c | 6 +-
net/rds/tcp_send.c | 2
net/sunrpc/auth.c | 2
net/sunrpc/auth_gss/auth_gss.c | 2
net/sunrpc/backchannel_rqst.c | 4 -
net/sunrpc/xprt.c | 4 -
net/sunrpc/xprtsock.c | 16 +++---
net/unix/af_unix.c | 2
sound/pci/bt87x.c | 4 -
176 files changed, 415 insertions(+), 642 deletions(-)

--- a/Documentation/atomic_ops.txt
+++ b/Documentation/atomic_ops.txt
@@ -285,15 +285,13 @@ If a caller requires memory barrier sema
operation which does not return a value, a set of interfaces are
defined which accomplish this:

- void smp_mb__before_atomic_dec(void);
- void smp_mb__after_atomic_dec(void);
- void smp_mb__before_atomic_inc(void);
- void smp_mb__after_atomic_inc(void);
+ void smp_mb__before_atomic(void);
+ void smp_mb__after_atomic(void);

-For example, smp_mb__before_atomic_dec() can be used like so:
+For example, smp_mb__before_atomic() can be used like so:

obj->dead = 1;
- smp_mb__before_atomic_dec();
+ smp_mb__before_atomic();
atomic_dec(&obj->ref_count);

It makes sure that all memory operations preceding the atomic_dec()
@@ -302,15 +300,10 @@ operation. In the above example, it gua
"1" to obj->dead will be globally visible to other cpus before the
atomic counter decrement.

-Without the explicit smp_mb__before_atomic_dec() call, the
+Without the explicit smp_mb__before_atomic() call, the
implementation could legally allow the atomic counter update visible
to other cpus before the "obj->dead = 1;" assignment.

-The other three interfaces listed are used to provide explicit
-ordering with respect to memory operations after an atomic_dec() call
-(smp_mb__after_atomic_dec()) and around atomic_inc() calls
-(smp_mb__{before,after}_atomic_inc()).
-
A missing memory barrier in the cases where they are required by the
atomic_t implementation above can have disastrous results. Here is
an example, which follows a pattern occurring frequently in the Linux
@@ -487,12 +480,12 @@ memory operation done by test_and_set_bi
Which returns a boolean indicating if bit "nr" is set in the bitmask
pointed to by "addr".

-If explicit memory barriers are required around clear_bit() (which
-does not return a value, and thus does not need to provide memory
-barrier semantics), two interfaces are provided:
+If explicit memory barriers are required around {set,clear}_bit() (which do
+not return a value, and thus does not need to provide memory barrier
+semantics), two interfaces are provided:

- void smp_mb__before_clear_bit(void);
- void smp_mb__after_clear_bit(void);
+ void smp_mb__before_atomic(void);
+ void smp_mb__after_atomic(void);

They are used as follows, and are akin to their atomic_t operation
brothers:
@@ -500,13 +493,13 @@ They are used as follows, and are akin t
/* All memory operations before this call will
* be globally visible before the clear_bit().
*/
- smp_mb__before_clear_bit();
+ smp_mb__before_atomic();
clear_bit( ... );

/* The clear_bit() will be visible before all
* subsequent memory operations.
*/
- smp_mb__after_clear_bit();
+ smp_mb__after_atomic();

There are two special bitops with lock barrier semantics (acquire/release,
same as spinlocks). These operate in the same way as their non-_lock/unlock
--- a/Documentation/memory-barriers.txt
+++ b/Documentation/memory-barriers.txt
@@ -1553,20 +1553,21 @@ CPU from reordering them.
insert anything more than a compiler barrier in a UP compilation.

- (*) smp_mb__before_atomic_dec();
- (*) smp_mb__after_atomic_dec();
- (*) smp_mb__before_atomic_inc();
- (*) smp_mb__after_atomic_inc();
-
- These are for use with atomic add, subtract, increment and decrement
- functions that don't return a value, especially when used for reference
- counting. These functions do not imply memory barriers.
+ (*) smp_mb__before_atomic();
+ (*) smp_mb__after_atomic();
+
+ These are for use with atomic (such as add, subtract, increment and
+ decrement) functions that don't return a value, especially when used for
+ reference counting. These functions do not imply memory barriers.
+
+ These are also used for atomic bitop functions that do not return a
+ value (such as set_bit and clear_bit).

As an example, consider a piece of code that marks an object as being dead
and then decrements the object's reference count:

obj->dead = 1;
- smp_mb__before_atomic_dec();
+ smp_mb__before_atomic();
atomic_dec(&obj->ref_count);

This makes sure that the death mark on the object is perceived to be set
@@ -1576,27 +1577,6 @@ CPU from reordering them.
operations" subsection for information on where to use these.

- (*) smp_mb__before_clear_bit(void);
- (*) smp_mb__after_clear_bit(void);
-
- These are for use similar to the atomic inc/dec barriers. These are
- typically used for bitwise unlocking operations, so care must be taken as
- there are no implicit memory barriers here either.
-
- Consider implementing an unlock operation of some nature by clearing a
- locking bit. The clear_bit() would then need to be barriered like this:
-
- smp_mb__before_clear_bit();
- clear_bit( ... );
-
- This prevents memory operations before the clear leaking to after it. See
- the subsection on "Locking Functions" with reference to RELEASE operation
- implications.
-
- See Documentation/atomic_ops.txt for more information. See the "Atomic
- operations" subsection for information on where to use these.
-
-
MMIO WRITE BARRIER
------------------

@@ -2222,11 +2202,11 @@ barriers, but might be used for implemen
change_bit();

With these the appropriate explicit memory barrier should be used if necessary
-(smp_mb__before_clear_bit() for instance).
+(smp_mb__before_atomic() for instance).

The following also do _not_ imply memory barriers, and so may require explicit
-memory barriers under some circumstances (smp_mb__before_atomic_dec() for
+memory barriers under some circumstances (smp_mb__before_atomic() for
instance):

atomic_add();
--- a/arch/alpha/include/asm/atomic.h
+++ b/arch/alpha/include/asm/atomic.h
@@ -292,9 +292,4 @@ static inline long atomic64_dec_if_posit
#define atomic_dec(v) atomic_sub(1,(v))
#define atomic64_dec(v) atomic64_sub(1,(v))

-#define smp_mb__before_atomic_dec() smp_mb()
-#define smp_mb__after_atomic_dec() smp_mb()
-#define smp_mb__before_atomic_inc() smp_mb()
-#define smp_mb__after_atomic_inc() smp_mb()
-
#endif /* _ALPHA_ATOMIC_H */
--- a/arch/alpha/include/asm/bitops.h
+++ b/arch/alpha/include/asm/bitops.h
@@ -53,9 +53,6 @@ __set_bit(unsigned long nr, volatile voi
*m |= 1 << (nr & 31);
}

-#define smp_mb__before_clear_bit() smp_mb()
-#define smp_mb__after_clear_bit() smp_mb()
-
static inline void
clear_bit(unsigned long nr, volatile void * addr)
{
--- a/arch/arc/include/asm/atomic.h
+++ b/arch/arc/include/asm/atomic.h
@@ -190,11 +190,6 @@ static inline void atomic_clear_mask(uns

#endif /* !CONFIG_ARC_HAS_LLSC */

-#define smp_mb__before_atomic_dec() barrier()
-#define smp_mb__after_atomic_dec() barrier()
-#define smp_mb__before_atomic_inc() barrier()
-#define smp_mb__after_atomic_inc() barrier()
-
/**
* __atomic_add_unless - add unless the number is a given value
* @v: pointer of type atomic_t
--- a/arch/arc/include/asm/bitops.h
+++ b/arch/arc/include/asm/bitops.h
@@ -19,6 +19,7 @@

#include <linux/types.h>
#include <linux/compiler.h>
+#include <asm/barrier.h>

/*
* Hardware assisted read-modify-write using ARC700 LLOCK/SCOND insns.
@@ -496,10 +497,6 @@ static inline __attribute__ ((const)) in
*/
#define ffz(x) __ffs(~(x))

-/* TODO does this affect uni-processor code */
-#define smp_mb__before_clear_bit() barrier()
-#define smp_mb__after_clear_bit() barrier()
-
#include <asm-generic/bitops/hweight.h>
#include <asm-generic/bitops/fls64.h>
#include <asm-generic/bitops/sched.h>
--- a/arch/arm/include/asm/atomic.h
+++ b/arch/arm/include/asm/atomic.h
@@ -211,11 +211,6 @@ static inline int __atomic_add_unless(at

#define atomic_add_negative(i,v) (atomic_add_return(i, v) < 0)

-#define smp_mb__before_atomic_dec() smp_mb()
-#define smp_mb__after_atomic_dec() smp_mb()
-#define smp_mb__before_atomic_inc() smp_mb()
-#define smp_mb__after_atomic_inc() smp_mb()
-
#ifndef CONFIG_GENERIC_ATOMIC64
typedef struct {
long long counter;
--- a/arch/arm/include/asm/barrier.h
+++ b/arch/arm/include/asm/barrier.h
@@ -79,5 +79,8 @@ do { \

#define set_mb(var, value) do { var = value; smp_mb(); } while (0)

+#define smp_mb__before_atomic() smp_mb()
+#define smp_mb__after_atomic() smp_mb()
+
#endif /* !__ASSEMBLY__ */
#endif /* __ASM_BARRIER_H */
--- a/arch/arm/include/asm/bitops.h
+++ b/arch/arm/include/asm/bitops.h
@@ -25,9 +25,7 @@

#include <linux/compiler.h>
#include <linux/irqflags.h>
-
-#define smp_mb__before_clear_bit() smp_mb()
-#define smp_mb__after_clear_bit() smp_mb()
+#include <asm/barrier.h>

/*
* These functions are the basis of our bit ops.
--- a/arch/arm64/include/asm/atomic.h
+++ b/arch/arm64/include/asm/atomic.h
@@ -154,11 +154,6 @@ static inline int __atomic_add_unless(at

#define atomic_add_negative(i,v) (atomic_add_return(i, v) < 0)

-#define smp_mb__before_atomic_dec() smp_mb()
-#define smp_mb__after_atomic_dec() smp_mb()
-#define smp_mb__before_atomic_inc() smp_mb()
-#define smp_mb__after_atomic_inc() smp_mb()
-
/*
* 64-bit atomic operations.
*/
--- a/arch/arm64/include/asm/barrier.h
+++ b/arch/arm64/include/asm/barrier.h
@@ -97,6 +97,9 @@ do { \
#define set_mb(var, value) do { var = value; smp_mb(); } while (0)
#define nop() asm volatile("nop");

+#define smp_mb__before_atomic() smp_mb()
+#define smp_mb__after_atomic() smp_mb()
+
#endif /* __ASSEMBLY__ */

#endif /* __ASM_BARRIER_H */
--- a/arch/arm64/include/asm/bitops.h
+++ b/arch/arm64/include/asm/bitops.h
@@ -17,17 +17,8 @@
#define __ASM_BITOPS_H

#include <linux/compiler.h>
-
#include <asm/barrier.h>

-/*
- * clear_bit may not imply a memory barrier
- */
-#ifndef smp_mb__before_clear_bit
-#define smp_mb__before_clear_bit() smp_mb()
-#define smp_mb__after_clear_bit() smp_mb()
-#endif
-
#ifndef _LINUX_BITOPS_H
#error only <linux/bitops.h> can be included directly
#endif
--- a/arch/avr32/include/asm/atomic.h
+++ b/arch/avr32/include/asm/atomic.h
@@ -183,9 +183,4 @@ static inline int atomic_sub_if_positive

#define atomic_dec_if_positive(v) atomic_sub_if_positive(1, v)

-#define smp_mb__before_atomic_dec() barrier()
-#define smp_mb__after_atomic_dec() barrier()
-#define smp_mb__before_atomic_inc() barrier()
-#define smp_mb__after_atomic_inc() barrier()
-
#endif /* __ASM_AVR32_ATOMIC_H */
--- a/arch/avr32/include/asm/bitops.h
+++ b/arch/avr32/include/asm/bitops.h
@@ -13,12 +13,7 @@
#endif

#include <asm/byteorder.h>
-
-/*
- * clear_bit() doesn't provide any barrier for the compiler
- */
-#define smp_mb__before_clear_bit() barrier()
-#define smp_mb__after_clear_bit() barrier()
+#include <asm/barrier.h>

/*
* set_bit - Atomically set a bit in memory
@@ -67,7 +62,7 @@ static inline void set_bit(int nr, volat
*
* clear_bit() is atomic and may not be reordered. However, it does
* not contain a memory barrier, so if it is used for locking purposes,
- * you should call smp_mb__before_clear_bit() and/or smp_mb__after_clear_bit()
+ * you should call smp_mb__before_atomic() and/or smp_mb__after_atomic()
* in order to ensure changes are visible on other processors.
*/
static inline void clear_bit(int nr, volatile void * addr)
--- a/arch/blackfin/include/asm/barrier.h
+++ b/arch/blackfin/include/asm/barrier.h
@@ -27,6 +27,9 @@

#endif /* !CONFIG_SMP */

+#define smp_mb__before_atomic() barrier()
+#define smp_mb__after_atomic() barrier()
+
#include <asm-generic/barrier.h>

#endif /* _BLACKFIN_BARRIER_H */
--- a/arch/blackfin/include/asm/bitops.h
+++ b/arch/blackfin/include/asm/bitops.h
@@ -27,21 +27,17 @@

#include <asm-generic/bitops/ext2-atomic.h>

+#include <asm/barrier.h>
+
#ifndef CONFIG_SMP
#include <linux/irqflags.h>
-
/*
* clear_bit may not imply a memory barrier
*/
-#ifndef smp_mb__before_clear_bit
-#define smp_mb__before_clear_bit() smp_mb()
-#define smp_mb__after_clear_bit() smp_mb()
-#endif
#include <asm-generic/bitops/atomic.h>
#include <asm-generic/bitops/non-atomic.h>
#else

-#include <asm/barrier.h>
#include <asm/byteorder.h> /* swab32 */
#include <linux/linkage.h>

@@ -101,12 +97,6 @@ static inline int test_and_change_bit(in
return __raw_bit_test_toggle_asm(a, nr & 0x1f);
}

-/*
- * clear_bit() doesn't provide any barrier for the compiler.
- */
-#define smp_mb__before_clear_bit() barrier()
-#define smp_mb__after_clear_bit() barrier()
-
#define test_bit __skip_test_bit
#include <asm-generic/bitops/non-atomic.h>
#undef test_bit
--- a/arch/c6x/include/asm/bitops.h
+++ b/arch/c6x/include/asm/bitops.h
@@ -14,14 +14,8 @@
#ifdef __KERNEL__

#include <linux/bitops.h>
-
#include <asm/byteorder.h>
-
-/*
- * clear_bit() doesn't provide any barrier for the compiler.
- */
-#define smp_mb__before_clear_bit() barrier()
-#define smp_mb__after_clear_bit() barrier()
+#include <asm/barrier.h>

/*
* We are lucky, DSP is perfect for bitops: do it in 3 cycles
--- a/arch/cris/include/asm/atomic.h
+++ b/arch/cris/include/asm/atomic.h
@@ -6,6 +6,7 @@
#include <linux/compiler.h>
#include <linux/types.h>
#include <asm/cmpxchg.h>
+#include <asm/barrier.h>
#include <arch/atomic.h>

/*
@@ -151,10 +152,4 @@ static inline int __atomic_add_unless(at
return ret;
}

-/* Atomic operations are already serializing */
-#define smp_mb__before_atomic_dec() barrier()
-#define smp_mb__after_atomic_dec() barrier()
-#define smp_mb__before_atomic_inc() barrier()
-#define smp_mb__after_atomic_inc() barrier()
-
#endif
--- a/arch/cris/include/asm/bitops.h
+++ b/arch/cris/include/asm/bitops.h
@@ -21,6 +21,7 @@
#include <arch/bitops.h>
#include <linux/atomic.h>
#include <linux/compiler.h>
+#include <asm/barrier.h>

/*
* set_bit - Atomically set a bit in memory
@@ -42,7 +43,7 @@
*
* clear_bit() is atomic and may not be reordered. However, it does
* not contain a memory barrier, so if it is used for locking purposes,
- * you should call smp_mb__before_clear_bit() and/or smp_mb__after_clear_bit()
+ * you should call smp_mb__before_atomic() and/or smp_mb__after_atomic()
* in order to ensure changes are visible on other processors.
*/

@@ -84,12 +85,6 @@ static inline int test_and_set_bit(int n
return retval;
}

-/*
- * clear_bit() doesn't provide any barrier for the compiler.
- */
-#define smp_mb__before_clear_bit() barrier()
-#define smp_mb__after_clear_bit() barrier()
-
/**
* test_and_clear_bit - Clear a bit and return its old value
* @nr: Bit to clear
--- a/arch/frv/include/asm/atomic.h
+++ b/arch/frv/include/asm/atomic.h
@@ -17,6 +17,7 @@
#include <linux/types.h>
#include <asm/spr-regs.h>
#include <asm/cmpxchg.h>
+#include <asm/barrier.h>

#ifdef CONFIG_SMP
#error not SMP safe
@@ -29,12 +30,6 @@
* We do not have SMP systems, so we don't have to deal with that.
*/

-/* Atomic operations are already serializing */
-#define smp_mb__before_atomic_dec() barrier()
-#define smp_mb__after_atomic_dec() barrier()
-#define smp_mb__before_atomic_inc() barrier()
-#define smp_mb__after_atomic_inc() barrier()
-
#define ATOMIC_INIT(i) { (i) }
#define atomic_read(v) (*(volatile int *)&(v)->counter)
#define atomic_set(v, i) (((v)->counter) = (i))
--- a/arch/frv/include/asm/bitops.h
+++ b/arch/frv/include/asm/bitops.h
@@ -25,12 +25,6 @@

#include <asm-generic/bitops/ffz.h>

-/*
- * clear_bit() doesn't provide any barrier for the compiler.
- */
-#define smp_mb__before_clear_bit() barrier()
-#define smp_mb__after_clear_bit() barrier()
-
#ifndef CONFIG_FRV_OUTOFLINE_ATOMIC_OPS
static inline
unsigned long atomic_test_and_ANDNOT_mask(unsigned long mask, volatile unsigned long *v)
--- a/arch/hexagon/include/asm/atomic.h
+++ b/arch/hexagon/include/asm/atomic.h
@@ -24,6 +24,7 @@

#include <linux/types.h>
#include <asm/cmpxchg.h>
+#include <asm/barrier.h>

#define ATOMIC_INIT(i) { (i) }
#define atomic_set(v, i) ((v)->counter = (i))
@@ -163,9 +164,4 @@ static inline int __atomic_add_unless(at
#define atomic_inc_return(v) (atomic_add_return(1, v))
#define atomic_dec_return(v) (atomic_sub_return(1, v))

-#define smp_mb__before_atomic_dec() barrier()
-#define smp_mb__after_atomic_dec() barrier()
-#define smp_mb__before_atomic_inc() barrier()
-#define smp_mb__after_atomic_inc() barrier()
-
#endif
--- a/arch/hexagon/include/asm/bitops.h
+++ b/arch/hexagon/include/asm/bitops.h
@@ -25,12 +25,10 @@
#include <linux/compiler.h>
#include <asm/byteorder.h>
#include <asm/atomic.h>
+#include <asm/barrier.h>

#ifdef __KERNEL__

-#define smp_mb__before_clear_bit() barrier()
-#define smp_mb__after_clear_bit() barrier()
-
/*
* The offset calculations for these are based on BITS_PER_LONG == 32
* (i.e. I get to shift by #5-2 (32 bits per long, 4 bytes per access),
--- a/arch/ia64/include/asm/atomic.h
+++ b/arch/ia64/include/asm/atomic.h
@@ -208,10 +208,4 @@ atomic64_add_negative (__s64 i, atomic64
#define atomic64_inc(v) atomic64_add(1, (v))
#define atomic64_dec(v) atomic64_sub(1, (v))

-/* Atomic operations are already serializing */
-#define smp_mb__before_atomic_dec() barrier()
-#define smp_mb__after_atomic_dec() barrier()
-#define smp_mb__before_atomic_inc() barrier()
-#define smp_mb__after_atomic_inc() barrier()
-
#endif /* _ASM_IA64_ATOMIC_H */
--- a/arch/ia64/include/asm/barrier.h
+++ b/arch/ia64/include/asm/barrier.h
@@ -55,6 +55,9 @@

#endif

+#define smp_mb__before_atomic() barrier()
+#define smp_mb__after_atomic() barrier()
+
/*
* IA64 GCC turns volatile stores into st.rel and volatile loads into ld.acq no
* need for asm trickery!
--- a/arch/ia64/include/asm/bitops.h
+++ b/arch/ia64/include/asm/bitops.h
@@ -16,6 +16,7 @@
#include <linux/compiler.h>
#include <linux/types.h>
#include <asm/intrinsics.h>
+#include <asm/barrier.h>

/**
* set_bit - Atomically set a bit in memory
@@ -65,9 +66,6 @@ __set_bit (int nr, volatile void *addr)
*((__u32 *) addr + (nr >> 5)) |= (1 << (nr & 31));
}

-#define smp_mb__before_clear_bit() barrier();
-#define smp_mb__after_clear_bit() barrier();
-
/**
* clear_bit - Clears a bit in memory
* @nr: Bit to clear
@@ -75,7 +73,7 @@ __set_bit (int nr, volatile void *addr)
*
* clear_bit() is atomic and may not be reordered. However, it does
* not contain a memory barrier, so if it is used for locking purposes,
- * you should call smp_mb__before_clear_bit() and/or smp_mb__after_clear_bit()
+ * you should call smp_mb__before_atomic() and/or smp_mb__after_atomic()
* in order to ensure changes are visible on other processors.
*/
static __inline__ void
--- a/arch/m32r/include/asm/atomic.h
+++ b/arch/m32r/include/asm/atomic.h
@@ -13,6 +13,7 @@
#include <asm/assembler.h>
#include <asm/cmpxchg.h>
#include <asm/dcache_clear.h>
+#include <asm/barrier.h>

/*
* Atomic operations that C can't guarantee us. Useful for
@@ -308,10 +309,4 @@ static __inline__ void atomic_set_mask(u
local_irq_restore(flags);
}

-/* Atomic operations are already serializing on m32r */
-#define smp_mb__before_atomic_dec() barrier()
-#define smp_mb__after_atomic_dec() barrier()
-#define smp_mb__before_atomic_inc() barrier()
-#define smp_mb__after_atomic_inc() barrier()
-
#endif /* _ASM_M32R_ATOMIC_H */
--- a/arch/m32r/include/asm/bitops.h
+++ b/arch/m32r/include/asm/bitops.h
@@ -21,6 +21,7 @@
#include <asm/byteorder.h>
#include <asm/dcache_clear.h>
#include <asm/types.h>
+#include <asm/barrier.h>

/*
* These have to be done with inline assembly: that way the bit-setting
@@ -73,7 +74,7 @@ static __inline__ void set_bit(int nr, v
*
* clear_bit() is atomic and may not be reordered. However, it does
* not contain a memory barrier, so if it is used for locking purposes,
- * you should call smp_mb__before_clear_bit() and/or smp_mb__after_clear_bit()
+ * you should call smp_mb__before_atomic() and/or smp_mb__after_atomic()
* in order to ensure changes are visible on other processors.
*/
static __inline__ void clear_bit(int nr, volatile void * addr)
@@ -103,9 +104,6 @@ static __inline__ void clear_bit(int nr,
local_irq_restore(flags);
}

-#define smp_mb__before_clear_bit() barrier()
-#define smp_mb__after_clear_bit() barrier()
-
/**
* change_bit - Toggle a bit in memory
* @nr: Bit to clear
--- a/arch/m68k/include/asm/atomic.h
+++ b/arch/m68k/include/asm/atomic.h
@@ -4,6 +4,7 @@
#include <linux/types.h>
#include <linux/irqflags.h>
#include <asm/cmpxchg.h>
+#include <asm/barrier.h>

/*
* Atomic operations that C can't guarantee us. Useful for
@@ -209,11 +210,4 @@ static __inline__ int __atomic_add_unles
return c;
}

-
-/* Atomic operations are already serializing */
-#define smp_mb__before_atomic_dec() barrier()
-#define smp_mb__after_atomic_dec() barrier()
-#define smp_mb__before_atomic_inc() barrier()
-#define smp_mb__after_atomic_inc() barrier()
-
#endif /* __ARCH_M68K_ATOMIC __ */
--- a/arch/m68k/include/asm/bitops.h
+++ b/arch/m68k/include/asm/bitops.h
@@ -13,6 +13,7 @@
#endif

#include <linux/compiler.h>
+#include <asm/barrier.h>

/*
* Bit access functions vary across the ColdFire and 68k families.
@@ -67,12 +68,6 @@ static inline void bfset_mem_set_bit(int
#define __set_bit(nr, vaddr) set_bit(nr, vaddr)

-/*
- * clear_bit() doesn't provide any barrier for the compiler.
- */
-#define smp_mb__before_clear_bit() barrier()
-#define smp_mb__after_clear_bit() barrier()
-
static inline void bclr_reg_clear_bit(int nr, volatile unsigned long *vaddr)
{
char *p = (char *)vaddr + (nr ^ 31) / 8;
--- a/arch/metag/include/asm/atomic.h
+++ b/arch/metag/include/asm/atomic.h
@@ -4,6 +4,7 @@
#include <linux/compiler.h>
#include <linux/types.h>
#include <asm/cmpxchg.h>
+#include <asm/barrier.h>

#if defined(CONFIG_METAG_ATOMICITY_IRQSOFF)
/* The simple UP case. */
@@ -39,11 +40,6 @@

#define atomic_inc_not_zero(v) atomic_add_unless((v), 1, 0)

-#define smp_mb__before_atomic_dec() barrier()
-#define smp_mb__after_atomic_dec() barrier()
-#define smp_mb__before_atomic_inc() barrier()
-#define smp_mb__after_atomic_inc() barrier()
-
#endif

#define atomic_dec_if_positive(v) atomic_sub_if_positive(1, v)
--- a/arch/metag/include/asm/barrier.h
+++ b/arch/metag/include/asm/barrier.h
@@ -97,4 +97,7 @@ do { \
___p1; \
})

+#define smp_mb__before_atomic() barrier()
+#define smp_mb__after_atomic() barrier()
+
#endif /* _ASM_METAG_BARRIER_H */
--- a/arch/metag/include/asm/bitops.h
+++ b/arch/metag/include/asm/bitops.h
@@ -5,12 +5,6 @@
#include <asm/barrier.h>
#include <asm/global_lock.h>

-/*
- * clear_bit() doesn't provide any barrier for the compiler.
- */
-#define smp_mb__before_clear_bit() barrier()
-#define smp_mb__after_clear_bit() barrier()
-
#ifdef CONFIG_SMP
/*
* These functions are the basis of our bit ops.
--- a/arch/mips/include/asm/atomic.h
+++ b/arch/mips/include/asm/atomic.h
@@ -761,13 +761,4 @@ static __inline__ int atomic64_add_unles

#endif /* CONFIG_64BIT */

-/*
- * atomic*_return operations are serializing but not the non-*_return
- * versions.
- */
-#define smp_mb__before_atomic_dec() smp_mb__before_llsc()
-#define smp_mb__after_atomic_dec() smp_llsc_mb()
-#define smp_mb__before_atomic_inc() smp_mb__before_llsc()
-#define smp_mb__after_atomic_inc() smp_llsc_mb()
-
#endif /* _ASM_ATOMIC_H */
--- a/arch/mips/include/asm/barrier.h
+++ b/arch/mips/include/asm/barrier.h
@@ -195,4 +195,7 @@ do { \
___p1; \
})

+#define smp_mb__before_atomic() smp_mb__before_llsc()
+#define smp_mb__after_atomic() smp_llsc_mb()
+
#endif /* __ASM_BARRIER_H */
--- a/arch/mips/include/asm/bitops.h
+++ b/arch/mips/include/asm/bitops.h
@@ -38,13 +38,6 @@
#endif

/*
- * clear_bit() doesn't provide any barrier for the compiler.
- */
-#define smp_mb__before_clear_bit() smp_mb__before_llsc()
-#define smp_mb__after_clear_bit() smp_llsc_mb()
-
-
-/*
* These are the "slower" versions of the functions and are in bitops.c.
* These functions call raw_local_irq_{save,restore}().
*/
@@ -120,7 +113,7 @@ static inline void set_bit(unsigned long
*
* clear_bit() is atomic and may not be reordered. However, it does
* not contain a memory barrier, so if it is used for locking purposes,
- * you should call smp_mb__before_clear_bit() and/or smp_mb__after_clear_bit()
+ * you should call smp_mb__before_atomic() and/or smp_mb__after_atomic()
* in order to ensure changes are visible on other processors.
*/
static inline void clear_bit(unsigned long nr, volatile unsigned long *addr)
@@ -175,7 +168,7 @@ static inline void clear_bit(unsigned lo
*/
static inline void clear_bit_unlock(unsigned long nr, volatile unsigned long *addr)
{
- smp_mb__before_clear_bit();
+ smp_mb__before_atomic();
clear_bit(nr, addr);
}

--- a/arch/mips/kernel/irq.c
+++ b/arch/mips/kernel/irq.c
@@ -62,9 +62,9 @@ void __init alloc_legacy_irqno(void)

void free_irqno(unsigned int irq)
{
- smp_mb__before_clear_bit();
+ smp_mb__before_atomic();
clear_bit(irq, irq_map);
- smp_mb__after_clear_bit();
+ smp_mb__after_atomic();
}

/*
--- a/arch/mn10300/include/asm/atomic.h
+++ b/arch/mn10300/include/asm/atomic.h
@@ -13,6 +13,7 @@

#include <asm/irqflags.h>
#include <asm/cmpxchg.h>
+#include <asm/barrier.h>

#ifndef CONFIG_SMP
#include <asm-generic/atomic.h>
@@ -234,12 +235,6 @@ static inline void atomic_set_mask(unsig
#endif
}

-/* Atomic operations are already serializing on MN10300??? */
-#define smp_mb__before_atomic_dec() barrier()
-#define smp_mb__after_atomic_dec() barrier()
-#define smp_mb__before_atomic_inc() barrier()
-#define smp_mb__after_atomic_inc() barrier()
-
#endif /* __KERNEL__ */
#endif /* CONFIG_SMP */
#endif /* _ASM_ATOMIC_H */
--- a/arch/mn10300/include/asm/bitops.h
+++ b/arch/mn10300/include/asm/bitops.h
@@ -18,9 +18,7 @@
#define __ASM_BITOPS_H

#include <asm/cpu-regs.h>
-
-#define smp_mb__before_clear_bit() barrier()
-#define smp_mb__after_clear_bit() barrier()
+#include <asm/barrier.h>

/*
* set bit
--- a/arch/mn10300/mm/tlb-smp.c
+++ b/arch/mn10300/mm/tlb-smp.c
@@ -78,9 +78,9 @@ void smp_flush_tlb(void *unused)
else
local_flush_tlb_page(flush_mm, flush_va);

- smp_mb__before_clear_bit();
+ smp_mb__before_atomic();
cpumask_clear_cpu(cpu_id, &flush_cpumask);
- smp_mb__after_clear_bit();
+ smp_mb__after_atomic();
out:
put_cpu();
}
--- a/arch/openrisc/include/asm/bitops.h
+++ b/arch/openrisc/include/asm/bitops.h
@@ -27,14 +27,7 @@

#include <linux/irqflags.h>
#include <linux/compiler.h>
-
-/*
- * clear_bit may not imply a memory barrier
- */
-#ifndef smp_mb__before_clear_bit
-#define smp_mb__before_clear_bit() smp_mb()
-#define smp_mb__after_clear_bit() smp_mb()
-#endif
+#include <asm/barrier.h>

#include <asm/bitops/__ffs.h>
#include <asm-generic/bitops/ffz.h>
--- a/arch/parisc/include/asm/atomic.h
+++ b/arch/parisc/include/asm/atomic.h
@@ -7,6 +7,7 @@

#include <linux/types.h>
#include <asm/cmpxchg.h>
+#include <asm/barrier.h>

/*
* Atomic operations that C can't guarantee us. Useful for
@@ -143,11 +144,6 @@ static __inline__ int __atomic_add_unles

#define ATOMIC_INIT(i) { (i) }

-#define smp_mb__before_atomic_dec() smp_mb()
-#define smp_mb__after_atomic_dec() smp_mb()
-#define smp_mb__before_atomic_inc() smp_mb()
-#define smp_mb__after_atomic_inc() smp_mb()
-
#ifdef CONFIG_64BIT

#define ATOMIC64_INIT(i) { (i) }
--- a/arch/parisc/include/asm/bitops.h
+++ b/arch/parisc/include/asm/bitops.h
@@ -8,6 +8,7 @@
#include <linux/compiler.h>
#include <asm/types.h> /* for BITS_PER_LONG/SHIFT_PER_LONG */
#include <asm/byteorder.h>
+#include <asm/barrier.h>
#include <linux/atomic.h>

/*
@@ -19,9 +20,6 @@
#define CHOP_SHIFTCOUNT(x) (((unsigned long) (x)) & (BITS_PER_LONG - 1))

-#define smp_mb__before_clear_bit() smp_mb()
-#define smp_mb__after_clear_bit() smp_mb()
-
/* See http://marc.theaimsgroup.com/?t=108826637900003 for discussion
* on use of volatile and __*_bit() (set/clear/change):
* *_bit() want use of volatile.
--- a/arch/powerpc/include/asm/atomic.h
+++ b/arch/powerpc/include/asm/atomic.h
@@ -8,6 +8,7 @@
#ifdef __KERNEL__
#include <linux/types.h>
#include <asm/cmpxchg.h>
+#include <asm/barrier.h>

#define ATOMIC_INIT(i) { (i) }

@@ -270,11 +271,6 @@ static __inline__ int atomic_dec_if_posi
}
#define atomic_dec_if_positive atomic_dec_if_positive

-#define smp_mb__before_atomic_dec() smp_mb()
-#define smp_mb__after_atomic_dec() smp_mb()
-#define smp_mb__before_atomic_inc() smp_mb()
-#define smp_mb__after_atomic_inc() smp_mb()
-
#ifdef __powerpc64__

#define ATOMIC64_INIT(i) { (i) }
--- a/arch/powerpc/include/asm/barrier.h
+++ b/arch/powerpc/include/asm/barrier.h
@@ -84,4 +84,7 @@ do { \
___p1; \
})

+#define smp_mb__before_atomic() smp_mb()
+#define smp_mb__after_atomic() smp_mb()
+
#endif /* _ASM_POWERPC_BARRIER_H */
--- a/arch/powerpc/include/asm/bitops.h
+++ b/arch/powerpc/include/asm/bitops.h
@@ -51,11 +51,7 @@
#define PPC_BIT(bit) (1UL << PPC_BITLSHIFT(bit))
#define PPC_BITMASK(bs, be) ((PPC_BIT(bs) - PPC_BIT(be)) | PPC_BIT(bs))

-/*
- * clear_bit doesn't imply a memory barrier
- */
-#define smp_mb__before_clear_bit() smp_mb()
-#define smp_mb__after_clear_bit() smp_mb()
+#include <asm/barrier.h>

/* Macro for generating the ***_bits() functions */
#define DEFINE_BITOP(fn, op, prefix) \
--- a/arch/powerpc/kernel/crash.c
+++ b/arch/powerpc/kernel/crash.c
@@ -81,7 +81,7 @@ void crash_ipi_callback(struct pt_regs *
}

atomic_inc(&cpus_in_crash);
- smp_mb__after_atomic_inc();
+ smp_mb__after_atomic();

/*
* Starting the kdump boot.
--- a/arch/s390/include/asm/atomic.h
+++ b/arch/s390/include/asm/atomic.h
@@ -16,6 +16,7 @@
#include <linux/compiler.h>
#include <linux/types.h>
#include <asm/cmpxchg.h>
+#include <asm/barrier.h>

#define ATOMIC_INIT(i) { (i) }

@@ -398,9 +399,4 @@ static inline long long atomic64_dec_if_
#define atomic64_dec_and_test(_v) (atomic64_sub_return(1, _v) == 0)
#define atomic64_inc_not_zero(v) atomic64_add_unless((v), 1, 0)

-#define smp_mb__before_atomic_dec() smp_mb()
-#define smp_mb__after_atomic_dec() smp_mb()
-#define smp_mb__before_atomic_inc() smp_mb()
-#define smp_mb__after_atomic_inc() smp_mb()
-
#endif /* __ARCH_S390_ATOMIC__ */
--- a/arch/s390/include/asm/barrier.h
+++ b/arch/s390/include/asm/barrier.h
@@ -27,8 +27,9 @@
#define smp_rmb() rmb()
#define smp_wmb() wmb()
#define smp_read_barrier_depends() read_barrier_depends()
-#define smp_mb__before_clear_bit() smp_mb()
-#define smp_mb__after_clear_bit() smp_mb()
+
+#define smp_mb__before_atomic() smp_mb()
+#define smp_mb__after_atomic() smp_mb()

#define set_mb(var, value) do { var = value; mb(); } while (0)

--- a/arch/s390/include/asm/bitops.h
+++ b/arch/s390/include/asm/bitops.h
@@ -47,6 +47,7 @@

#include <linux/typecheck.h>
#include <linux/compiler.h>
+#include <asm/barrier.h>

#ifndef CONFIG_64BIT

--- a/arch/score/include/asm/bitops.h
+++ b/arch/score/include/asm/bitops.h
@@ -2,12 +2,7 @@
#define _ASM_SCORE_BITOPS_H

#include <asm/byteorder.h> /* swab32 */
-
-/*
- * clear_bit() doesn't provide any barrier for the compiler.
- */
-#define smp_mb__before_clear_bit() barrier()
-#define smp_mb__after_clear_bit() barrier()
+#include <asm/barrier.h>

#include <asm-generic/bitops.h>
#include <asm-generic/bitops/__fls.h>
--- a/arch/sh/include/asm/atomic.h
+++ b/arch/sh/include/asm/atomic.h
@@ -10,6 +10,7 @@
#include <linux/compiler.h>
#include <linux/types.h>
#include <asm/cmpxchg.h>
+#include <asm/barrier.h>

#define ATOMIC_INIT(i) { (i) }

@@ -62,9 +63,4 @@ static inline int __atomic_add_unless(at
return c;
}

-#define smp_mb__before_atomic_dec() smp_mb()
-#define smp_mb__after_atomic_dec() smp_mb()
-#define smp_mb__before_atomic_inc() smp_mb()
-#define smp_mb__after_atomic_inc() smp_mb()
-
#endif /* __ASM_SH_ATOMIC_H */
--- a/arch/sh/include/asm/bitops.h
+++ b/arch/sh/include/asm/bitops.h
@@ -9,6 +9,7 @@

/* For __swab32 */
#include <asm/byteorder.h>
+#include <asm/barrier.h>

#ifdef CONFIG_GUSA_RB
#include <asm/bitops-grb.h>
@@ -22,12 +23,6 @@
#include <asm-generic/bitops/non-atomic.h>
#endif

-/*
- * clear_bit() doesn't provide any barrier for the compiler.
- */
-#define smp_mb__before_clear_bit() smp_mb()
-#define smp_mb__after_clear_bit() smp_mb()
-
#ifdef CONFIG_SUPERH32
static inline unsigned long ffz(unsigned long word)
{
--- a/arch/sparc/include/asm/atomic_32.h
+++ b/arch/sparc/include/asm/atomic_32.h
@@ -14,6 +14,7 @@
#include <linux/types.h>

#include <asm/cmpxchg.h>
+#include <asm/barrier.h>
#include <asm-generic/atomic64.h>

@@ -52,10 +53,4 @@ extern void atomic_set(atomic_t *, int);
#define atomic_dec_and_test(v) (atomic_dec_return(v) == 0)
#define atomic_sub_and_test(i, v) (atomic_sub_return(i, v) == 0)

-/* Atomic operations are already serializing */
-#define smp_mb__before_atomic_dec() barrier()
-#define smp_mb__after_atomic_dec() barrier()
-#define smp_mb__before_atomic_inc() barrier()
-#define smp_mb__after_atomic_inc() barrier()
-
#endif /* !(__ARCH_SPARC_ATOMIC__) */
--- a/arch/sparc/include/asm/atomic_64.h
+++ b/arch/sparc/include/asm/atomic_64.h
@@ -9,6 +9,7 @@

#include <linux/types.h>
#include <asm/cmpxchg.h>
+#include <asm/barrier.h>

#define ATOMIC_INIT(i) { (i) }
#define ATOMIC64_INIT(i) { (i) }
@@ -108,10 +109,4 @@ static inline long atomic64_add_unless(a

extern long atomic64_dec_if_positive(atomic64_t *v);

-/* Atomic operations are already serializing */
-#define smp_mb__before_atomic_dec() barrier()
-#define smp_mb__after_atomic_dec() barrier()
-#define smp_mb__before_atomic_inc() barrier()
-#define smp_mb__after_atomic_inc() barrier()
-
#endif /* !(__ARCH_SPARC64_ATOMIC__) */
--- a/arch/sparc/include/asm/barrier_64.h
+++ b/arch/sparc/include/asm/barrier_64.h
@@ -68,4 +68,7 @@ do { \
___p1; \
})

+#define smp_mb__before_atomic() barrier()
+#define smp_mb__after_atomic() barrier()
+
#endif /* !(__SPARC64_BARRIER_H) */
--- a/arch/sparc/include/asm/bitops_32.h
+++ b/arch/sparc/include/asm/bitops_32.h
@@ -11,6 +11,7 @@

#include <linux/compiler.h>
#include <asm/byteorder.h>
+#include <asm/barrier.h>

#ifdef __KERNEL__

@@ -90,9 +91,6 @@ static inline void change_bit(unsigned l

#include <asm-generic/bitops/non-atomic.h>

-#define smp_mb__before_clear_bit() do { } while(0)
-#define smp_mb__after_clear_bit() do { } while(0)
-
#include <asm-generic/bitops/ffz.h>
#include <asm-generic/bitops/__ffs.h>
#include <asm-generic/bitops/sched.h>
--- a/arch/sparc/include/asm/bitops_64.h
+++ b/arch/sparc/include/asm/bitops_64.h
@@ -13,6 +13,7 @@

#include <linux/compiler.h>
#include <asm/byteorder.h>
+#include <asm/barrier.h>

extern int test_and_set_bit(unsigned long nr, volatile unsigned long *addr);
extern int test_and_clear_bit(unsigned long nr, volatile unsigned long *addr);
@@ -23,9 +24,6 @@ extern void change_bit(unsigned long nr,

#include <asm-generic/bitops/non-atomic.h>

-#define smp_mb__before_clear_bit() barrier()
-#define smp_mb__after_clear_bit() barrier()
-
#include <asm-generic/bitops/fls.h>
#include <asm-generic/bitops/__fls.h>
#include <asm-generic/bitops/fls64.h>
--- a/arch/tile/include/asm/atomic_32.h
+++ b/arch/tile/include/asm/atomic_32.h
@@ -169,16 +169,6 @@ static inline void atomic64_set(atomic64
#define atomic64_dec_and_test(v) (atomic64_dec_return((v)) == 0)
#define atomic64_inc_not_zero(v) atomic64_add_unless((v), 1LL, 0LL)

-/*
- * We need to barrier before modifying the word, since the _atomic_xxx()
- * routines just tns the lock and then read/modify/write of the word.
- * But after the word is updated, the routine issues an "mf" before returning,
- * and since it's a function call, we don't even need a compiler barrier.
- */
-#define smp_mb__before_atomic_dec() smp_mb()
-#define smp_mb__before_atomic_inc() smp_mb()
-#define smp_mb__after_atomic_dec() do { } while (0)
-#define smp_mb__after_atomic_inc() do { } while (0)

#endif /* !__ASSEMBLY__ */

--- a/arch/tile/include/asm/atomic_64.h
+++ b/arch/tile/include/asm/atomic_64.h
@@ -105,12 +105,6 @@ static inline long atomic64_add_unless(a

#define atomic64_inc_not_zero(v) atomic64_add_unless((v), 1, 0)

-/* Atomic dec and inc don't implement barrier, so provide them if needed. */
-#define smp_mb__before_atomic_dec() smp_mb()
-#define smp_mb__after_atomic_dec() smp_mb()
-#define smp_mb__before_atomic_inc() smp_mb()
-#define smp_mb__after_atomic_inc() smp_mb()
-
/* Define this to indicate that cmpxchg is an efficient operation. */
#define __HAVE_ARCH_CMPXCHG

--- a/arch/tile/include/asm/barrier.h
+++ b/arch/tile/include/asm/barrier.h
@@ -72,6 +72,20 @@ mb_incoherent(void)
#define mb() fast_mb()
#define iob() fast_iob()

+#ifndef __tilegx__ /* 32 bit */
+/*
+ * We need to barrier before modifying the word, since the _atomic_xxx()
+ * routines just tns the lock and then read/modify/write of the word.
+ * But after the word is updated, the routine issues an "mf" before returning,
+ * and since it's a function call, we don't even need a compiler barrier.
+ */
+#define smp_mb__before_atomic() smp_mb()
+#define smp_mb__after_atomic() do { } while (0)
+#else /* 64 bit */
+#define smp_mb__before_atomic() smp_mb()
+#define smp_mb__after_atomic() smp_mb()
+#endif
+
#include <asm-generic/barrier.h>

#endif /* !__ASSEMBLY__ */
--- a/arch/tile/include/asm/bitops.h
+++ b/arch/tile/include/asm/bitops.h
@@ -17,6 +17,7 @@
#define _ASM_TILE_BITOPS_H

#include <linux/types.h>
+#include <asm/barrier.h>

#ifndef _LINUX_BITOPS_H
#error only <linux/bitops.h> can be included directly
--- a/arch/tile/include/asm/bitops_32.h
+++ b/arch/tile/include/asm/bitops_32.h
@@ -49,8 +49,8 @@ static inline void set_bit(unsigned nr,
* restricted to acting on a single-word quantity.
*
* clear_bit() may not contain a memory barrier, so if it is used for
- * locking purposes, you should call smp_mb__before_clear_bit() and/or
- * smp_mb__after_clear_bit() to ensure changes are visible on other cpus.
+ * locking purposes, you should call smp_mb__before_atomic() and/or
+ * smp_mb__after_atomic() to ensure changes are visible on other cpus.
*/
static inline void clear_bit(unsigned nr, volatile unsigned long *addr)
{
@@ -121,10 +121,6 @@ static inline int test_and_change_bit(un
return (_atomic_xor(addr, mask) & mask) != 0;
}

-/* See discussion at smp_mb__before_atomic_dec() in <asm/atomic_32.h>. */
-#define smp_mb__before_clear_bit() smp_mb()
-#define smp_mb__after_clear_bit() do {} while (0)
-
#include <asm-generic/bitops/ext2-atomic.h>

#endif /* _ASM_TILE_BITOPS_32_H */
--- a/arch/tile/include/asm/bitops_64.h
+++ b/arch/tile/include/asm/bitops_64.h
@@ -32,10 +32,6 @@ static inline void clear_bit(unsigned nr
__insn_fetchand((void *)(addr + nr / BITS_PER_LONG), ~mask);
}

-#define smp_mb__before_clear_bit() smp_mb()
-#define smp_mb__after_clear_bit() smp_mb()
-
-
static inline void change_bit(unsigned nr, volatile unsigned long *addr)
{
unsigned long mask = (1UL << (nr % BITS_PER_LONG));
--- a/arch/x86/include/asm/atomic.h
+++ b/arch/x86/include/asm/atomic.h
@@ -7,6 +7,7 @@
#include <asm/alternative.h>
#include <asm/cmpxchg.h>
#include <asm/rmwcc.h>
+#include <asm/barrier.h>

/*
* Atomic operations that C can't guarantee us. Useful for
@@ -243,12 +244,6 @@ static inline void atomic_or_long(unsign
: : "r" ((unsigned)(mask)), "m" (*(addr)) \
: "memory")

-/* Atomic operations are already serializing on x86 */
-#define smp_mb__before_atomic_dec() barrier()
-#define smp_mb__after_atomic_dec() barrier()
-#define smp_mb__before_atomic_inc() barrier()
-#define smp_mb__after_atomic_inc() barrier()
-
#ifdef CONFIG_X86_32
# include <asm/atomic64_32.h>
#else
--- a/arch/x86/include/asm/barrier.h
+++ b/arch/x86/include/asm/barrier.h
@@ -141,6 +141,10 @@ do { \

#endif

+/* Atomic operations are already serializing on x86 */
+#define smp_mb__before_atomic() barrier()
+#define smp_mb__after_atomic() barrier()
+
/*
* Stop RDTSC speculation. This is needed when you need to use RDTSC
* (or get_cycles or vread that possibly accesses the TSC) in a defined
--- a/arch/x86/include/asm/bitops.h
+++ b/arch/x86/include/asm/bitops.h
@@ -15,6 +15,7 @@
#include <linux/compiler.h>
#include <asm/alternative.h>
#include <asm/rmwcc.h>
+#include <asm/barrier.h>

#if BITS_PER_LONG == 32
# define _BITOPS_LONG_SHIFT 5
@@ -102,7 +103,7 @@ static inline void __set_bit(long nr, vo
*
* clear_bit() is atomic and may not be reordered. However, it does
* not contain a memory barrier, so if it is used for locking purposes,
- * you should call smp_mb__before_clear_bit() and/or smp_mb__after_clear_bit()
+ * you should call smp_mb__before_atomic() and/or smp_mb__after_atomic()
* in order to ensure changes are visible on other processors.
*/
static __always_inline void
@@ -156,9 +157,6 @@ static inline void __clear_bit_unlock(lo
__clear_bit(nr, addr);
}

-#define smp_mb__before_clear_bit() barrier()
-#define smp_mb__after_clear_bit() barrier()
-
/**
* __change_bit - Toggle a bit in memory
* @nr: the bit to change
--- a/arch/x86/include/asm/sync_bitops.h
+++ b/arch/x86/include/asm/sync_bitops.h
@@ -41,7 +41,7 @@ static inline void sync_set_bit(long nr,
*
* sync_clear_bit() is atomic and may not be reordered. However, it does
* not contain a memory barrier, so if it is used for locking purposes,
- * you should call smp_mb__before_clear_bit() and/or smp_mb__after_clear_bit()
+ * you should call smp_mb__before_atomic() and/or smp_mb__after_atomic()
* in order to ensure changes are visible on other processors.
*/
static inline void sync_clear_bit(long nr, volatile unsigned long *addr)
--- a/arch/x86/kernel/apic/hw_nmi.c
+++ b/arch/x86/kernel/apic/hw_nmi.c
@@ -57,7 +57,7 @@ void arch_trigger_all_cpu_backtrace(void
}

clear_bit(0, &backtrace_flag);
- smp_mb__after_clear_bit();
+ smp_mb__after_atomic();
}

static int __kprobes
--- a/arch/xtensa/include/asm/atomic.h
+++ b/arch/xtensa/include/asm/atomic.h
@@ -19,6 +19,7 @@
#ifdef __KERNEL__
#include <asm/processor.h>
#include <asm/cmpxchg.h>
+#include <asm/barrier.h>

#define ATOMIC_INIT(i) { (i) }

@@ -387,12 +388,6 @@ static inline void atomic_set_mask(unsig
#endif
}

-/* Atomic operations are already serializing */
-#define smp_mb__before_atomic_dec() barrier()
-#define smp_mb__after_atomic_dec() barrier()
-#define smp_mb__before_atomic_inc() barrier()
-#define smp_mb__after_atomic_inc() barrier()
-
#endif /* __KERNEL__ */

#endif /* _XTENSA_ATOMIC_H */
--- a/arch/xtensa/include/asm/bitops.h
+++ b/arch/xtensa/include/asm/bitops.h
@@ -21,9 +21,7 @@

#include <asm/processor.h>
#include <asm/byteorder.h>
-
-#define smp_mb__before_clear_bit() smp_mb()
-#define smp_mb__after_clear_bit() smp_mb()
+#include <asm/barrier.h>

#include <asm-generic/bitops/non-atomic.h>

--- a/block/blk-iopoll.c
+++ b/block/blk-iopoll.c
@@ -52,7 +52,7 @@ EXPORT_SYMBOL(blk_iopoll_sched);
void __blk_iopoll_complete(struct blk_iopoll *iop)
{
list_del(&iop->list);
- smp_mb__before_clear_bit();
+ smp_mb__before_atomic();
clear_bit_unlock(IOPOLL_F_SCHED, &iop->state);
}
EXPORT_SYMBOL(__blk_iopoll_complete);
@@ -164,7 +164,7 @@ EXPORT_SYMBOL(blk_iopoll_disable);
void blk_iopoll_enable(struct blk_iopoll *iop)
{
BUG_ON(!test_bit(IOPOLL_F_SCHED, &iop->state));
- smp_mb__before_clear_bit();
+ smp_mb__before_atomic();
clear_bit_unlock(IOPOLL_F_SCHED, &iop->state);
}
EXPORT_SYMBOL(blk_iopoll_enable);
--- a/crypto/chainiv.c
+++ b/crypto/chainiv.c
@@ -126,7 +126,7 @@ static int async_chainiv_schedule_work(s
int err = ctx->err;

if (!ctx->queue.qlen) {
- smp_mb__before_clear_bit();
+ smp_mb__before_atomic();
clear_bit(CHAINIV_STATE_INUSE, &ctx->state);

if (!ctx->queue.qlen ||
--- a/drivers/base/power/domain.c
+++ b/drivers/base/power/domain.c
@@ -106,7 +106,7 @@ static bool genpd_sd_counter_dec(struct
static void genpd_sd_counter_inc(struct generic_pm_domain *genpd)
{
atomic_inc(&genpd->sd_count);
- smp_mb__after_atomic_inc();
+ smp_mb__after_atomic();
}

static void genpd_acquire_lock(struct generic_pm_domain *genpd)
--- a/drivers/block/mtip32xx/mtip32xx.c
+++ b/drivers/block/mtip32xx/mtip32xx.c
@@ -224,9 +224,9 @@ static int get_slot(struct mtip_port *po
*/
static inline void release_slot(struct mtip_port *port, int tag)
{
- smp_mb__before_clear_bit();
+ smp_mb__before_atomic();
clear_bit(tag, port->allocated);
- smp_mb__after_clear_bit();
+ smp_mb__after_atomic();
}

/*
--- a/drivers/cpuidle/coupled.c
+++ b/drivers/cpuidle/coupled.c
@@ -159,7 +159,7 @@ void cpuidle_coupled_parallel_barrier(st
{
int n = dev->coupled->online_count;

- smp_mb__before_atomic_inc();
+ smp_mb__before_atomic();
atomic_inc(a);

while (atomic_read(a) < n)
--- a/drivers/firewire/ohci.c
+++ b/drivers/firewire/ohci.c
@@ -3509,7 +3509,7 @@ static int ohci_flush_iso_completions(st
}

clear_bit_unlock(0, &ctx->flushing_completions);
- smp_mb__after_clear_bit();
+ smp_mb__after_atomic();
}

tasklet_enable(&ctx->context.tasklet);
--- a/drivers/gpu/drm/drm_irq.c
+++ b/drivers/gpu/drm/drm_irq.c
@@ -156,7 +156,7 @@ static void vblank_disable_and_save(stru
*/
if ((vblrc > 0) && (abs64(diff_ns) > 1000000)) {
atomic_inc(&dev->vblank[crtc].count);
- smp_mb__after_atomic_inc();
+ smp_mb__after_atomic();
}

/* Invalidate all timestamps while vblank irq's are off. */
@@ -864,9 +864,9 @@ static void drm_update_vblank_count(stru
vblanktimestamp(dev, crtc, tslot) = t_vblank;
}

- smp_mb__before_atomic_inc();
+ smp_mb__before_atomic();
atomic_add(diff, &dev->vblank[crtc].count);
- smp_mb__after_atomic_inc();
+ smp_mb__after_atomic();
}

/**
@@ -1330,9 +1330,9 @@ bool drm_handle_vblank(struct drm_device
/* Increment cooked vblank count. This also atomically commits
* the timestamp computed above.
*/
- smp_mb__before_atomic_inc();
+ smp_mb__before_atomic();
atomic_inc(&dev->vblank[crtc].count);
- smp_mb__after_atomic_inc();
+ smp_mb__after_atomic();
} else {
DRM_DEBUG("crtc %d: Redundant vblirq ignored. diff_ns = %d\n",
crtc, (int) diff_ns);
--- a/drivers/gpu/drm/i915/i915_irq.c
+++ b/drivers/gpu/drm/i915/i915_irq.c
@@ -1996,7 +1996,7 @@ static void i915_error_work_func(struct
* updates before
* the counter increment.
*/
- smp_mb__before_atomic_inc();
+ smp_mb__before_atomic();
atomic_inc(&dev_priv->gpu_error.reset_counter);

kobject_uevent_env(&dev->primary->kdev->kobj,
--- a/drivers/md/bcache/bcache.h
+++ b/drivers/md/bcache/bcache.h
@@ -841,7 +841,7 @@ static inline bool cached_dev_get(struct
return false;

/* Paired with the mb in cached_dev_attach */
- smp_mb__after_atomic_inc();
+ smp_mb__after_atomic();
return true;
}

--- a/drivers/md/bcache/closure.h
+++ b/drivers/md/bcache/closure.h
@@ -243,7 +243,7 @@ static inline void set_closure_fn(struct
cl->fn = fn;
cl->wq = wq;
/* between atomic_dec() in closure_put() */
- smp_mb__before_atomic_dec();
+ smp_mb__before_atomic();
}

static inline void closure_queue(struct closure *cl)
--- a/drivers/md/dm-bufio.c
+++ b/drivers/md/dm-bufio.c
@@ -607,9 +607,9 @@ static void write_endio(struct bio *bio,

BUG_ON(!test_bit(B_WRITING, &b->state));

- smp_mb__before_clear_bit();
+ smp_mb__before_atomic();
clear_bit(B_WRITING, &b->state);
- smp_mb__after_clear_bit();
+ smp_mb__after_atomic();

wake_up_bit(&b->state, B_WRITING);
}
@@ -997,9 +997,9 @@ static void read_endio(struct bio *bio,

BUG_ON(!test_bit(B_READING, &b->state));

- smp_mb__before_clear_bit();
+ smp_mb__before_atomic();
clear_bit(B_READING, &b->state);
- smp_mb__after_clear_bit();
+ smp_mb__after_atomic();

wake_up_bit(&b->state, B_READING);
}
--- a/drivers/md/dm-snap.c
+++ b/drivers/md/dm-snap.c
@@ -642,7 +642,7 @@ static void free_pending_exception(struc
struct dm_snapshot *s = pe->snap;

mempool_free(pe, s->pending_pool);
- smp_mb__before_atomic_dec();
+ smp_mb__before_atomic();
atomic_dec(&s->pending_exceptions_count);
}

@@ -783,7 +783,7 @@ static int init_hash_tables(struct dm_sn
static void merge_shutdown(struct dm_snapshot *s)
{
clear_bit_unlock(RUNNING_MERGE, &s->state_bits);
- smp_mb__after_clear_bit();
+ smp_mb__after_atomic();
wake_up_bit(&s->state_bits, RUNNING_MERGE);
}

--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -2451,7 +2451,7 @@ static void dm_wq_work(struct work_struc
static void dm_queue_flush(struct mapped_device *md)
{
clear_bit(DMF_BLOCK_IO_FOR_SUSPEND, &md->flags);
- smp_mb__after_clear_bit();
+ smp_mb__after_atomic();
queue_work(md->wq, &md->work);
}

--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -4406,7 +4406,7 @@ static void raid5_unplug(struct blk_plug
* STRIPE_ON_UNPLUG_LIST clear but the stripe
* is still in our list
*/
- smp_mb__before_clear_bit();
+ smp_mb__before_atomic();
clear_bit(STRIPE_ON_UNPLUG_LIST, &sh->state);
/*
* STRIPE_ON_RELEASE_LIST could be set here. In that
--- a/drivers/media/usb/dvb-usb-v2/dvb_usb_core.c
+++ b/drivers/media/usb/dvb-usb-v2/dvb_usb_core.c
@@ -399,7 +399,7 @@ static int dvb_usb_stop_feed(struct dvb_

/* clear 'streaming' status bit */
clear_bit(ADAP_STREAMING, &adap->state_bits);
- smp_mb__after_clear_bit();
+ smp_mb__after_atomic();
wake_up_bit(&adap->state_bits, ADAP_STREAMING);
skip_feed_stop:

@@ -550,7 +550,7 @@ static int dvb_usb_fe_init(struct dvb_fr
err:
if (!adap->suspend_resume_active) {
clear_bit(ADAP_INIT, &adap->state_bits);
- smp_mb__after_clear_bit();
+ smp_mb__after_atomic();
wake_up_bit(&adap->state_bits, ADAP_INIT);
}

@@ -591,7 +591,7 @@ static int dvb_usb_fe_sleep(struct dvb_f
if (!adap->suspend_resume_active) {
adap->active_fe = -1;
clear_bit(ADAP_SLEEP, &adap->state_bits);
- smp_mb__after_clear_bit();
+ smp_mb__after_atomic();
wake_up_bit(&adap->state_bits, ADAP_SLEEP);
}

--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
@@ -2779,7 +2779,7 @@ int bnx2x_nic_load(struct bnx2x *bp, int

case LOAD_OPEN:
netif_tx_start_all_queues(bp->dev);
- smp_mb__after_clear_bit();
+ smp_mb__after_atomic();
break;

case LOAD_DIAG:
@@ -4773,9 +4773,9 @@ void bnx2x_tx_timeout(struct net_device
bnx2x_panic();
#endif

- smp_mb__before_clear_bit();
+ smp_mb__before_atomic();
set_bit(BNX2X_SP_RTNL_TX_TIMEOUT, &bp->sp_rtnl_state);
- smp_mb__after_clear_bit();
+ smp_mb__after_atomic();

/* This allows the netif to be shutdown gracefully before resetting */
schedule_delayed_work(&bp->sp_rtnl_task, 0);
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
@@ -1837,10 +1837,10 @@ void bnx2x_sp_event(struct bnx2x_fastpat
/* SRIOV: reschedule any 'in_progress' operations */
bnx2x_iov_sp_event(bp, cid, true);

- smp_mb__before_atomic_inc();
+ smp_mb__before_atomic();
atomic_inc(&bp->cq_spq_left);
/* push the change in bp->spq_left and towards the memory */
- smp_mb__after_atomic_inc();
+ smp_mb__after_atomic();

DP(BNX2X_MSG_SP, "bp->cq_spq_left %x\n", atomic_read(&bp->cq_spq_left));

@@ -1855,11 +1855,11 @@ void bnx2x_sp_event(struct bnx2x_fastpat
* sp_state is cleared, and this order prevents
* races
*/
- smp_mb__before_clear_bit();
+ smp_mb__before_atomic();
set_bit(BNX2X_AFEX_PENDING_VIFSET_MCP_ACK, &bp->sp_state);
wmb();
clear_bit(BNX2X_AFEX_FCOE_Q_UPDATE_PENDING, &bp->sp_state);
- smp_mb__after_clear_bit();
+ smp_mb__after_atomic();

/* schedule the sp task as mcp ack is required */
bnx2x_schedule_sp_task(bp);
@@ -3878,9 +3878,9 @@ static void bnx2x_fan_failure(struct bnx
* This is due to some boards consuming sufficient power when driver is
* up to overheat if fan fails.
*/
- smp_mb__before_clear_bit();
+ smp_mb__before_atomic();
set_bit(BNX2X_SP_RTNL_FAN_FAILURE, &bp->sp_rtnl_state);
- smp_mb__after_clear_bit();
+ smp_mb__after_atomic();
schedule_delayed_work(&bp->sp_rtnl_task, 0);
}

@@ -5137,9 +5137,9 @@ static void bnx2x_after_function_update(
__clear_bit(RAMROD_COMP_WAIT, &queue_params.ramrod_flags);

/* mark latest Q bit */
- smp_mb__before_clear_bit();
+ smp_mb__before_atomic();
set_bit(BNX2X_AFEX_FCOE_Q_UPDATE_PENDING, &bp->sp_state);
- smp_mb__after_clear_bit();
+ smp_mb__after_atomic();

/* send Q update ramrod for FCoE Q */
rc = bnx2x_queue_state_change(bp, &queue_params);
@@ -5282,10 +5282,10 @@ static void bnx2x_eq_int(struct bnx2x *b
* sp_rtnl task as all Queue SP operations
* should run under rtnl_lock.
*/
- smp_mb__before_clear_bit();
+ smp_mb__before_atomic();
set_bit(BNX2X_SP_RTNL_AFEX_F_UPDATE,
&bp->sp_rtnl_state);
- smp_mb__after_clear_bit();
+ smp_mb__after_atomic();

schedule_delayed_work(&bp->sp_rtnl_task, 0);
}
@@ -5368,7 +5368,7 @@ static void bnx2x_eq_int(struct bnx2x *b
spqe_cnt++;
} /* for */

- smp_mb__before_atomic_inc();
+ smp_mb__before_atomic();
atomic_add(spqe_cnt, &bp->eq_spq_left);

bp->eq_cons = sw_cons;
@@ -12065,9 +12065,9 @@ static void bnx2x_set_rx_mode(struct net
} else {
/* Schedule an SP task to handle rest of change */
DP(NETIF_MSG_IFUP, "Scheduling an Rx mode change\n");
- smp_mb__before_clear_bit();
+ smp_mb__before_atomic();
set_bit(BNX2X_SP_RTNL_RX_MODE, &bp->sp_rtnl_state);
- smp_mb__after_clear_bit();
+ smp_mb__after_atomic();
schedule_delayed_work(&bp->sp_rtnl_task, 0);
}
}
@@ -12101,10 +12101,10 @@ void bnx2x_set_rx_mode_inner(struct bnx2
/* configuring mcast to a vf involves sleeping (when we
* wait for the pf's response).
*/
- smp_mb__before_clear_bit();
+ smp_mb__before_atomic();
set_bit(BNX2X_SP_RTNL_VFPF_MCAST,
&bp->sp_rtnl_state);
- smp_mb__after_clear_bit();
+ smp_mb__after_atomic();
schedule_delayed_work(&bp->sp_rtnl_task, 0);
}
}
@@ -13723,9 +13723,9 @@ static int bnx2x_drv_ctl(struct net_devi
case DRV_CTL_RET_L2_SPQ_CREDIT_CMD: {
int count = ctl->data.credit.credit_count;

- smp_mb__before_atomic_inc();
+ smp_mb__before_atomic();
atomic_add(count, &bp->cq_spq_left);
- smp_mb__after_atomic_inc();
+ smp_mb__after_atomic();
break;
}
case DRV_CTL_ULP_REGISTER_CMD: {
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.c
@@ -258,16 +258,16 @@ static bool bnx2x_raw_check_pending(stru

static void bnx2x_raw_clear_pending(struct bnx2x_raw_obj *o)
{
- smp_mb__before_clear_bit();
+ smp_mb__before_atomic();
clear_bit(o->state, o->pstate);
- smp_mb__after_clear_bit();
+ smp_mb__after_atomic();
}

static void bnx2x_raw_set_pending(struct bnx2x_raw_obj *o)
{
- smp_mb__before_clear_bit();
+ smp_mb__before_atomic();
set_bit(o->state, o->pstate);
- smp_mb__after_clear_bit();
+ smp_mb__after_atomic();
}

/**
@@ -2131,7 +2131,7 @@ static int bnx2x_set_rx_mode_e1x(struct

/* The operation is completed */
clear_bit(p->state, p->pstate);
- smp_mb__after_clear_bit();
+ smp_mb__after_atomic();

return 0;
}
@@ -3576,16 +3576,16 @@ int bnx2x_config_mcast(struct bnx2x *bp,

static void bnx2x_mcast_clear_sched(struct bnx2x_mcast_obj *o)
{
- smp_mb__before_clear_bit();
+ smp_mb__before_atomic();
clear_bit(o->sched_state, o->raw.pstate);
- smp_mb__after_clear_bit();
+ smp_mb__after_atomic();
}

static void bnx2x_mcast_set_sched(struct bnx2x_mcast_obj *o)
{
- smp_mb__before_clear_bit();
+ smp_mb__before_atomic();
set_bit(o->sched_state, o->raw.pstate);
- smp_mb__after_clear_bit();
+ smp_mb__after_atomic();
}

static bool bnx2x_mcast_check_sched(struct bnx2x_mcast_obj *o)
@@ -4210,7 +4210,7 @@ int bnx2x_queue_state_change(struct bnx2
if (rc) {
o->next_state = BNX2X_Q_STATE_MAX;
clear_bit(pending_bit, pending);
- smp_mb__after_clear_bit();
+ smp_mb__after_atomic();
return rc;
}

@@ -4298,7 +4298,7 @@ static int bnx2x_queue_comp_cmd(struct b
wmb();

clear_bit(cmd, &o->pending);
- smp_mb__after_clear_bit();
+ smp_mb__after_atomic();

return 0;
}
@@ -5242,7 +5242,7 @@ static inline int bnx2x_func_state_chang
wmb();

clear_bit(cmd, &o->pending);
- smp_mb__after_clear_bit();
+ smp_mb__after_atomic();

return 0;
}
@@ -5877,7 +5877,7 @@ int bnx2x_func_state_change(struct bnx2x
if (rc) {
o->next_state = BNX2X_F_STATE_MAX;
clear_bit(cmd, pending);
- smp_mb__after_clear_bit();
+ smp_mb__after_atomic();
return rc;
}

--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c
@@ -971,10 +971,10 @@ static void bnx2x_vfop_qsetup(struct bnx
op_done:
case BNX2X_VFOP_QSETUP_DONE:
vf->cfg_flags |= VF_CFG_VLAN;
- smp_mb__before_clear_bit();
+ smp_mb__before_atomic();
set_bit(BNX2X_SP_RTNL_HYPERVISOR_VLAN,
&bp->sp_rtnl_state);
- smp_mb__after_clear_bit();
+ smp_mb__after_atomic();
schedule_delayed_work(&bp->sp_rtnl_task, 0);
bnx2x_vfop_end(bp, vf, vfop);
return;
@@ -2354,9 +2354,9 @@ static
void bnx2x_vf_handle_filters_eqe(struct bnx2x *bp,
struct bnx2x_virtf *vf)
{
- smp_mb__before_clear_bit();
+ smp_mb__before_atomic();
clear_bit(BNX2X_FILTER_RX_MODE_PENDING, &vf->filter_state);
- smp_mb__after_clear_bit();
+ smp_mb__after_atomic();
}

int bnx2x_iov_eq_sp_event(struct bnx2x *bp, union event_ring_elem *elem)
@@ -3737,10 +3737,10 @@ void bnx2x_timer_sriov(struct bnx2x *bp)

/* if channel is down we need to self destruct */
if (bp->old_bulletin.valid_bitmap & 1 << CHANNEL_DOWN) {
- smp_mb__before_clear_bit();
+ smp_mb__before_atomic();
set_bit(BNX2X_SP_RTNL_VFPF_CHANNEL_DOWN,
&bp->sp_rtnl_state);
- smp_mb__after_clear_bit();
+ smp_mb__after_atomic();
schedule_delayed_work(&bp->sp_rtnl_task, 0);
}
}
--- a/drivers/net/ethernet/broadcom/cnic.c
+++ b/drivers/net/ethernet/broadcom/cnic.c
@@ -436,7 +436,7 @@ static int cnic_offld_prep(struct cnic_s
static int cnic_close_prep(struct cnic_sock *csk)
{
clear_bit(SK_F_CONNECT_START, &csk->flags);
- smp_mb__after_clear_bit();
+ smp_mb__after_atomic();

if (test_and_clear_bit(SK_F_OFFLD_COMPLETE, &csk->flags)) {
while (test_and_set_bit(SK_F_OFFLD_SCHED, &csk->flags))
@@ -450,7 +450,7 @@ static int cnic_close_prep(struct cnic_s
static int cnic_abort_prep(struct cnic_sock *csk)
{
clear_bit(SK_F_CONNECT_START, &csk->flags);
- smp_mb__after_clear_bit();
+ smp_mb__after_atomic();

while (test_and_set_bit(SK_F_OFFLD_SCHED, &csk->flags))
msleep(1);
@@ -3645,7 +3645,7 @@ static int cnic_cm_destroy(struct cnic_s

csk_hold(csk);
clear_bit(SK_F_INUSE, &csk->flags);
- smp_mb__after_clear_bit();
+ smp_mb__after_atomic();
while (atomic_read(&csk->ref_count) != 1)
msleep(1);
cnic_cm_cleanup(csk);
@@ -4025,7 +4025,7 @@ static void cnic_cm_process_kcqe(struct
L4_KCQE_COMPLETION_STATUS_PARITY_ERROR)
set_bit(SK_F_HW_ERR, &csk->flags);

- smp_mb__before_clear_bit();
+ smp_mb__before_atomic();
clear_bit(SK_F_OFFLD_SCHED, &csk->flags);
cnic_cm_upcall(cp, csk, opcode);
break;
--- a/drivers/net/ethernet/brocade/bna/bnad.c
+++ b/drivers/net/ethernet/brocade/bna/bnad.c
@@ -249,7 +249,7 @@ bnad_tx_complete(struct bnad *bnad, stru
if (likely(test_bit(BNAD_TXQ_TX_STARTED, &tcb->flags)))
bna_ib_ack(tcb->i_dbell, sent);

- smp_mb__before_clear_bit();
+ smp_mb__before_atomic();
clear_bit(BNAD_TXQ_FREE_SENT, &tcb->flags);

return sent;
@@ -1125,7 +1125,7 @@ bnad_tx_cleanup(struct delayed_work *wor

bnad_txq_cleanup(bnad, tcb);

- smp_mb__before_clear_bit();
+ smp_mb__before_atomic();
clear_bit(BNAD_TXQ_FREE_SENT, &tcb->flags);
}

@@ -2999,7 +2999,7 @@ bnad_start_xmit(struct sk_buff *skb, str
sent = bnad_txcmpl_process(bnad, tcb);
if (likely(test_bit(BNAD_TXQ_TX_STARTED, &tcb->flags)))
bna_ib_ack(tcb->i_dbell, sent);
- smp_mb__before_clear_bit();
+ smp_mb__before_atomic();
clear_bit(BNAD_TXQ_FREE_SENT, &tcb->flags);
} else {
netif_stop_queue(netdev);
--- a/drivers/net/ethernet/chelsio/cxgb/cxgb2.c
+++ b/drivers/net/ethernet/chelsio/cxgb/cxgb2.c
@@ -281,7 +281,7 @@ static int cxgb_close(struct net_device
if (adapter->params.stats_update_period &&
!(adapter->open_device_map & PORT_MASK)) {
/* Stop statistics accumulation. */
- smp_mb__after_clear_bit();
+ smp_mb__after_atomic();
spin_lock(&adapter->work_lock); /* sync with update task */
spin_unlock(&adapter->work_lock);
cancel_mac_stats_update(adapter);
--- a/drivers/net/ethernet/chelsio/cxgb3/sge.c
+++ b/drivers/net/ethernet/chelsio/cxgb3/sge.c
@@ -1379,7 +1379,7 @@ static inline int check_desc_avail(struc
struct sge_qset *qs = txq_to_qset(q, qid);

set_bit(qid, &qs->txq_stopped);
- smp_mb__after_clear_bit();
+ smp_mb__after_atomic();

if (should_restart_tx(q) &&
test_and_clear_bit(qid, &qs->txq_stopped))
@@ -1492,7 +1492,7 @@ static void restart_ctrlq(unsigned long

if (!skb_queue_empty(&q->sendq)) {
set_bit(TXQ_CTRL, &qs->txq_stopped);
- smp_mb__after_clear_bit();
+ smp_mb__after_atomic();

if (should_restart_tx(q) &&
test_and_clear_bit(TXQ_CTRL, &qs->txq_stopped))
@@ -1697,7 +1697,7 @@ again: reclaim_completed_tx(adap, q, TX_

if (unlikely(q->size - q->in_use < ndesc)) {
set_bit(TXQ_OFLD, &qs->txq_stopped);
- smp_mb__after_clear_bit();
+ smp_mb__after_atomic();

if (should_restart_tx(q) &&
test_and_clear_bit(TXQ_OFLD, &qs->txq_stopped))
--- a/drivers/net/ethernet/chelsio/cxgb4/sge.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/sge.c
@@ -2003,7 +2003,7 @@ static void sge_rx_timer_cb(unsigned lon
struct sge_fl *fl = s->egr_map[id];

clear_bit(id, s->starving_fl);
- smp_mb__after_clear_bit();
+ smp_mb__after_atomic();

if (fl_starving(fl)) {
rxq = container_of(fl, struct sge_eth_rxq, fl);
--- a/drivers/net/ethernet/chelsio/cxgb4vf/sge.c
+++ b/drivers/net/ethernet/chelsio/cxgb4vf/sge.c
@@ -1951,7 +1951,7 @@ static void sge_rx_timer_cb(unsigned lon
struct sge_fl *fl = s->egr_map[id];

clear_bit(id, s->starving_fl);
- smp_mb__after_clear_bit();
+ smp_mb__after_atomic();

/*
* Since we are accessing fl without a lock there's a
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -4576,7 +4576,7 @@ static void i40e_service_event_complete(
BUG_ON(!test_bit(__I40E_SERVICE_SCHED, &pf->state));

/* flush memory to make sure state is correct before next watchog */
- smp_mb__before_clear_bit();
+ smp_mb__before_atomic();
clear_bit(__I40E_SERVICE_SCHED, &pf->state);
}

--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -318,7 +318,7 @@ static void ixgbe_service_event_complete
BUG_ON(!test_bit(__IXGBE_SERVICE_SCHED, &adapter->state));

/* flush memory to make sure state is correct before next watchdog */
- smp_mb__before_clear_bit();
+ smp_mb__before_atomic();
clear_bit(__IXGBE_SERVICE_SCHED, &adapter->state);
}

@@ -4607,7 +4607,7 @@ static void ixgbe_up_complete(struct ixg
if (hw->mac.ops.enable_tx_laser)
hw->mac.ops.enable_tx_laser(hw);

- smp_mb__before_clear_bit();
+ smp_mb__before_atomic();
clear_bit(__IXGBE_DOWN, &adapter->state);
ixgbe_napi_enable_all(adapter);

--- a/drivers/net/wireless/ti/wlcore/main.c
+++ b/drivers/net/wireless/ti/wlcore/main.c
@@ -547,7 +547,7 @@ static int wlcore_irq_locked(struct wl12
* wl1271_ps_elp_wakeup cannot be called concurrently.
*/
clear_bit(WL1271_FLAG_IRQ_RUNNING, &wl->flags);
- smp_mb__after_clear_bit();
+ smp_mb__after_atomic();

ret = wlcore_fw_status(wl, wl->fw_status_1, wl->fw_status_2);
if (ret < 0)
--- a/drivers/pci/xen-pcifront.c
+++ b/drivers/pci/xen-pcifront.c
@@ -662,9 +662,9 @@ static void pcifront_do_aer(struct work_
notify_remote_via_evtchn(pdev->evtchn);

/*in case of we lost an aer request in four lines time_window*/
- smp_mb__before_clear_bit();
+ smp_mb__before_atomic();
clear_bit(_PDEVB_op_active, &pdev->flags);
- smp_mb__after_clear_bit();
+ smp_mb__after_atomic();

schedule_pcifront_aer_op(pdev);

--- a/drivers/scsi/isci/remote_device.c
+++ b/drivers/scsi/isci/remote_device.c
@@ -1541,7 +1541,7 @@ void isci_remote_device_release(struct k
clear_bit(IDEV_STOP_PENDING, &idev->flags);
clear_bit(IDEV_IO_READY, &idev->flags);
clear_bit(IDEV_GONE, &idev->flags);
- smp_mb__before_clear_bit();
+ smp_mb__before_atomic();
clear_bit(IDEV_ALLOCATED, &idev->flags);
wake_up(&ihost->eventq);
}
--- a/drivers/target/loopback/tcm_loop.c
+++ b/drivers/target/loopback/tcm_loop.c
@@ -942,7 +942,7 @@ static int tcm_loop_port_link(
struct tcm_loop_hba *tl_hba = tl_tpg->tl_hba;

atomic_inc(&tl_tpg->tl_tpg_port_count);
- smp_mb__after_atomic_inc();
+ smp_mb__after_atomic();
/*
* Add Linux/SCSI struct scsi_device by HCTL
*/
@@ -977,7 +977,7 @@ static void tcm_loop_port_unlink(
scsi_device_put(sd);

atomic_dec(&tl_tpg->tl_tpg_port_count);
- smp_mb__after_atomic_dec();
+ smp_mb__after_atomic();

pr_debug("TCM_Loop_ConfigFS: Port Unlink Successful\n");
}
--- a/drivers/target/target_core_alua.c
+++ b/drivers/target/target_core_alua.c
@@ -393,7 +393,7 @@ target_emulate_set_target_port_groups(st
continue;

atomic_inc(&tg_pt_gp->tg_pt_gp_ref_cnt);
- smp_mb__after_atomic_inc();
+ smp_mb__after_atomic();

spin_unlock(&dev->t10_alua.tg_pt_gps_lock);

@@ -404,7 +404,7 @@ target_emulate_set_target_port_groups(st

spin_lock(&dev->t10_alua.tg_pt_gps_lock);
atomic_dec(&tg_pt_gp->tg_pt_gp_ref_cnt);
- smp_mb__after_atomic_dec();
+ smp_mb__after_atomic();
break;
}
spin_unlock(&dev->t10_alua.tg_pt_gps_lock);
@@ -997,7 +997,7 @@ static void core_alua_do_transition_tg_p
* TARGET PORT GROUPS command
*/
atomic_inc(&mem->tg_pt_gp_mem_ref_cnt);
- smp_mb__after_atomic_inc();
+ smp_mb__after_atomic();
spin_unlock(&tg_pt_gp->tg_pt_gp_lock);

spin_lock_bh(&port->sep_alua_lock);
@@ -1027,7 +1027,7 @@ static void core_alua_do_transition_tg_p

spin_lock(&tg_pt_gp->tg_pt_gp_lock);
atomic_dec(&mem->tg_pt_gp_mem_ref_cnt);
- smp_mb__after_atomic_dec();
+ smp_mb__after_atomic();
}
spin_unlock(&tg_pt_gp->tg_pt_gp_lock);
/*
@@ -1061,7 +1061,7 @@ static void core_alua_do_transition_tg_p
core_alua_dump_state(tg_pt_gp->tg_pt_gp_alua_pending_state));
spin_lock(&dev->t10_alua.tg_pt_gps_lock);
atomic_dec(&tg_pt_gp->tg_pt_gp_ref_cnt);
- smp_mb__after_atomic_dec();
+ smp_mb__after_atomic();
spin_unlock(&dev->t10_alua.tg_pt_gps_lock);

if (tg_pt_gp->tg_pt_gp_transition_complete)
@@ -1123,7 +1123,7 @@ static int core_alua_do_transition_tg_pt
*/
spin_lock(&dev->t10_alua.tg_pt_gps_lock);
atomic_inc(&tg_pt_gp->tg_pt_gp_ref_cnt);
- smp_mb__after_atomic_inc();
+ smp_mb__after_atomic();
spin_unlock(&dev->t10_alua.tg_pt_gps_lock);

if (!explicit && tg_pt_gp->tg_pt_gp_implicit_trans_secs) {
@@ -1166,7 +1166,7 @@ int core_alua_do_port_transition(
spin_lock(&local_lu_gp_mem->lu_gp_mem_lock);
lu_gp = local_lu_gp_mem->lu_gp;
atomic_inc(&lu_gp->lu_gp_ref_cnt);
- smp_mb__after_atomic_inc();
+ smp_mb__after_atomic();
spin_unlock(&local_lu_gp_mem->lu_gp_mem_lock);
/*
* For storage objects that are members of the 'default_lu_gp',
@@ -1183,7 +1183,7 @@ int core_alua_do_port_transition(
rc = core_alua_do_transition_tg_pt(l_tg_pt_gp,
new_state, explicit);
atomic_dec(&lu_gp->lu_gp_ref_cnt);
- smp_mb__after_atomic_dec();
+ smp_mb__after_atomic();
return rc;
}
/*
@@ -1197,7 +1197,7 @@ int core_alua_do_port_transition(

dev = lu_gp_mem->lu_gp_mem_dev;
atomic_inc(&lu_gp_mem->lu_gp_mem_ref_cnt);
- smp_mb__after_atomic_inc();
+ smp_mb__after_atomic();
spin_unlock(&lu_gp->lu_gp_lock);

spin_lock(&dev->t10_alua.tg_pt_gps_lock);
@@ -1226,7 +1226,7 @@ int core_alua_do_port_transition(
tg_pt_gp->tg_pt_gp_alua_nacl = NULL;
}
atomic_inc(&tg_pt_gp->tg_pt_gp_ref_cnt);
- smp_mb__after_atomic_inc();
+ smp_mb__after_atomic();
spin_unlock(&dev->t10_alua.tg_pt_gps_lock);
/*
* core_alua_do_transition_tg_pt() will always return
@@ -1237,7 +1237,7 @@ int core_alua_do_port_transition(

spin_lock(&dev->t10_alua.tg_pt_gps_lock);
atomic_dec(&tg_pt_gp->tg_pt_gp_ref_cnt);
- smp_mb__after_atomic_dec();
+ smp_mb__after_atomic();
if (rc)
break;
}
@@ -1245,7 +1245,7 @@ int core_alua_do_port_transition(

spin_lock(&lu_gp->lu_gp_lock);
atomic_dec(&lu_gp_mem->lu_gp_mem_ref_cnt);
- smp_mb__after_atomic_dec();
+ smp_mb__after_atomic();
}
spin_unlock(&lu_gp->lu_gp_lock);

@@ -1259,7 +1259,7 @@ int core_alua_do_port_transition(
}

atomic_dec(&lu_gp->lu_gp_ref_cnt);
- smp_mb__after_atomic_dec();
+ smp_mb__after_atomic();
return rc;
}

--- a/drivers/target/target_core_device.c
+++ b/drivers/target/target_core_device.c
@@ -225,7 +225,7 @@ struct se_dev_entry *core_get_se_deve_fr
continue;

atomic_inc(&deve->pr_ref_count);
- smp_mb__after_atomic_inc();
+ smp_mb__after_atomic();
spin_unlock_irq(&nacl->device_list_lock);

return deve;
@@ -1392,7 +1392,7 @@ int core_dev_add_initiator_node_lun_acl(
spin_lock(&lun->lun_acl_lock);
list_add_tail(&lacl->lacl_list, &lun->lun_acl_list);
atomic_inc(&lun->lun_acl_count);
- smp_mb__after_atomic_inc();
+ smp_mb__after_atomic();
spin_unlock(&lun->lun_acl_lock);

pr_debug("%s_TPG[%hu]_LUN[%u->%u] - Added %s ACL for "
@@ -1426,7 +1426,7 @@ int core_dev_del_initiator_node_lun_acl(
spin_lock(&lun->lun_acl_lock);
list_del(&lacl->lacl_list);
atomic_dec(&lun->lun_acl_count);
- smp_mb__after_atomic_dec();
+ smp_mb__after_atomic();
spin_unlock(&lun->lun_acl_lock);

core_disable_device_list_for_node(lun, NULL, lacl->mapped_lun,
--- a/drivers/target/target_core_iblock.c
+++ b/drivers/target/target_core_iblock.c
@@ -324,7 +324,7 @@ static void iblock_bio_done(struct bio *
* Bump the ib_bio_err_cnt and release bio.
*/
atomic_inc(&ibr->ib_bio_err_cnt);
- smp_mb__after_atomic_inc();
+ smp_mb__after_atomic();
}

bio_put(bio);
--- a/drivers/target/target_core_pr.c
+++ b/drivers/target/target_core_pr.c
@@ -675,7 +675,7 @@ static struct t10_pr_registration *__cor
spin_lock(&dev->se_port_lock);
list_for_each_entry_safe(port, port_tmp, &dev->dev_sep_list, sep_list) {
atomic_inc(&port->sep_tg_pt_ref_cnt);
- smp_mb__after_atomic_inc();
+ smp_mb__after_atomic();
spin_unlock(&dev->se_port_lock);

spin_lock_bh(&port->sep_alua_lock);
@@ -710,7 +710,7 @@ static struct t10_pr_registration *__cor
continue;

atomic_inc(&deve_tmp->pr_ref_count);
- smp_mb__after_atomic_inc();
+ smp_mb__after_atomic();
spin_unlock_bh(&port->sep_alua_lock);
/*
* Grab a configfs group dependency that is released
@@ -723,9 +723,9 @@ static struct t10_pr_registration *__cor
pr_err("core_scsi3_lunacl_depend"
"_item() failed\n");
atomic_dec(&port->sep_tg_pt_ref_cnt);
- smp_mb__after_atomic_dec();
+ smp_mb__after_atomic();
atomic_dec(&deve_tmp->pr_ref_count);
- smp_mb__after_atomic_dec();
+ smp_mb__after_atomic();
goto out;
}
/*
@@ -740,9 +740,9 @@ static struct t10_pr_registration *__cor
sa_res_key, all_tg_pt, aptpl);
if (!pr_reg_atp) {
atomic_dec(&port->sep_tg_pt_ref_cnt);
- smp_mb__after_atomic_dec();
+ smp_mb__after_atomic();
atomic_dec(&deve_tmp->pr_ref_count);
- smp_mb__after_atomic_dec();
+ smp_mb__after_atomic();
core_scsi3_lunacl_undepend_item(deve_tmp);
goto out;
}
@@ -755,7 +755,7 @@ static struct t10_pr_registration *__cor

spin_lock(&dev->se_port_lock);
atomic_dec(&port->sep_tg_pt_ref_cnt);
- smp_mb__after_atomic_dec();
+ smp_mb__after_atomic();
}
spin_unlock(&dev->se_port_lock);

@@ -1110,7 +1110,7 @@ static struct t10_pr_registration *__cor
continue;
}
atomic_inc(&pr_reg->pr_res_holders);
- smp_mb__after_atomic_inc();
+ smp_mb__after_atomic();
spin_unlock(&pr_tmpl->registration_lock);
return pr_reg;
}
@@ -1125,7 +1125,7 @@ static struct t10_pr_registration *__cor
continue;

atomic_inc(&pr_reg->pr_res_holders);
- smp_mb__after_atomic_inc();
+ smp_mb__after_atomic();
spin_unlock(&pr_tmpl->registration_lock);
return pr_reg;
}
@@ -1155,7 +1155,7 @@ static struct t10_pr_registration *core_
static void core_scsi3_put_pr_reg(struct t10_pr_registration *pr_reg)
{
atomic_dec(&pr_reg->pr_res_holders);
- smp_mb__after_atomic_dec();
+ smp_mb__after_atomic();
}

static int core_scsi3_check_implicit_release(
@@ -1349,7 +1349,7 @@ static void core_scsi3_tpg_undepend_item
&tpg->tpg_group.cg_item);

atomic_dec(&tpg->tpg_pr_ref_count);
- smp_mb__after_atomic_dec();
+ smp_mb__after_atomic();
}

static int core_scsi3_nodeacl_depend_item(struct se_node_acl *nacl)
@@ -1369,7 +1369,7 @@ static void core_scsi3_nodeacl_undepend_

if (nacl->dynamic_node_acl) {
atomic_dec(&nacl->acl_pr_ref_count);
- smp_mb__after_atomic_dec();
+ smp_mb__after_atomic();
return;
}

@@ -1377,7 +1377,7 @@ static void core_scsi3_nodeacl_undepend_
&nacl->acl_group.cg_item);

atomic_dec(&nacl->acl_pr_ref_count);
- smp_mb__after_atomic_dec();
+ smp_mb__after_atomic();
}

static int core_scsi3_lunacl_depend_item(struct se_dev_entry *se_deve)
@@ -1408,7 +1408,7 @@ static void core_scsi3_lunacl_undepend_i
*/
if (!lun_acl) {
atomic_dec(&se_deve->pr_ref_count);
- smp_mb__after_atomic_dec();
+ smp_mb__after_atomic();
return;
}
nacl = lun_acl->se_lun_nacl;
@@ -1418,7 +1418,7 @@ static void core_scsi3_lunacl_undepend_i
&lun_acl->se_lun_group.cg_item);

atomic_dec(&se_deve->pr_ref_count);
- smp_mb__after_atomic_dec();
+ smp_mb__after_atomic();
}

static sense_reason_t
@@ -1552,14 +1552,14 @@ core_scsi3_decode_spec_i_port(
continue;

atomic_inc(&tmp_tpg->tpg_pr_ref_count);
- smp_mb__after_atomic_inc();
+ smp_mb__after_atomic();
spin_unlock(&dev->se_port_lock);

if (core_scsi3_tpg_depend_item(tmp_tpg)) {
pr_err(" core_scsi3_tpg_depend_item()"
" for tmp_tpg\n");
atomic_dec(&tmp_tpg->tpg_pr_ref_count);
- smp_mb__after_atomic_dec();
+ smp_mb__after_atomic();
ret = TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
goto out_unmap;
}
@@ -1573,7 +1573,7 @@ core_scsi3_decode_spec_i_port(
tmp_tpg, i_str);
if (dest_node_acl) {
atomic_inc(&dest_node_acl->acl_pr_ref_count);
- smp_mb__after_atomic_inc();
+ smp_mb__after_atomic();
}
spin_unlock_irq(&tmp_tpg->acl_node_lock);

@@ -1587,7 +1587,7 @@ core_scsi3_decode_spec_i_port(
pr_err("configfs_depend_item() failed"
" for dest_node_acl->acl_group\n");
atomic_dec(&dest_node_acl->acl_pr_ref_count);
- smp_mb__after_atomic_dec();
+ smp_mb__after_atomic();
core_scsi3_tpg_undepend_item(tmp_tpg);
ret = TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
goto out_unmap;
@@ -1647,7 +1647,7 @@ core_scsi3_decode_spec_i_port(
pr_err("core_scsi3_lunacl_depend_item()"
" failed\n");
atomic_dec(&dest_se_deve->pr_ref_count);
- smp_mb__after_atomic_dec();
+ smp_mb__after_atomic();
core_scsi3_nodeacl_undepend_item(dest_node_acl);
core_scsi3_tpg_undepend_item(dest_tpg);
ret = TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
@@ -3165,14 +3165,14 @@ core_scsi3_emulate_pro_register_and_move
continue;

atomic_inc(&dest_se_tpg->tpg_pr_ref_count);
- smp_mb__after_atomic_inc();
+ smp_mb__after_atomic();
spin_unlock(&dev->se_port_lock);

if (core_scsi3_tpg_depend_item(dest_se_tpg)) {
pr_err("core_scsi3_tpg_depend_item() failed"
" for dest_se_tpg\n");
atomic_dec(&dest_se_tpg->tpg_pr_ref_count);
- smp_mb__after_atomic_dec();
+ smp_mb__after_atomic();
ret = TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
goto out_put_pr_reg;
}
@@ -3270,7 +3270,7 @@ core_scsi3_emulate_pro_register_and_move
initiator_str);
if (dest_node_acl) {
atomic_inc(&dest_node_acl->acl_pr_ref_count);
- smp_mb__after_atomic_inc();
+ smp_mb__after_atomic();
}
spin_unlock_irq(&dest_se_tpg->acl_node_lock);

@@ -3286,7 +3286,7 @@ core_scsi3_emulate_pro_register_and_move
pr_err("core_scsi3_nodeacl_depend_item() for"
" dest_node_acl\n");
atomic_dec(&dest_node_acl->acl_pr_ref_count);
- smp_mb__after_atomic_dec();
+ smp_mb__after_atomic();
dest_node_acl = NULL;
ret = TCM_INVALID_PARAMETER_LIST;
goto out;
@@ -3311,7 +3311,7 @@ core_scsi3_emulate_pro_register_and_move
if (core_scsi3_lunacl_depend_item(dest_se_deve)) {
pr_err("core_scsi3_lunacl_depend_item() failed\n");
atomic_dec(&dest_se_deve->pr_ref_count);
- smp_mb__after_atomic_dec();
+ smp_mb__after_atomic();
dest_se_deve = NULL;
ret = TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
goto out;
@@ -3877,7 +3877,7 @@ core_scsi3_pri_read_full_status(struct s
add_desc_len = 0;

atomic_inc(&pr_reg->pr_res_holders);
- smp_mb__after_atomic_inc();
+ smp_mb__after_atomic();
spin_unlock(&pr_tmpl->registration_lock);
/*
* Determine expected length of $FABRIC_MOD specific
@@ -3891,7 +3891,7 @@ core_scsi3_pri_read_full_status(struct s
" out of buffer: %d\n", cmd->data_length);
spin_lock(&pr_tmpl->registration_lock);
atomic_dec(&pr_reg->pr_res_holders);
- smp_mb__after_atomic_dec();
+ smp_mb__after_atomic();
break;
}
/*
@@ -3953,7 +3953,7 @@ core_scsi3_pri_read_full_status(struct s

spin_lock(&pr_tmpl->registration_lock);
atomic_dec(&pr_reg->pr_res_holders);
- smp_mb__after_atomic_dec();
+ smp_mb__after_atomic();
/*
* Set the ADDITIONAL DESCRIPTOR LENGTH
*/
--- a/drivers/target/target_core_transport.c
+++ b/drivers/target/target_core_transport.c
@@ -728,7 +728,7 @@ void target_qf_do_work(struct work_struc
list_for_each_entry_safe(cmd, cmd_tmp, &qf_cmd_list, se_qf_node) {
list_del(&cmd->se_qf_node);
atomic_dec(&dev->dev_qf_count);
- smp_mb__after_atomic_dec();
+ smp_mb__after_atomic();

pr_debug("Processing %s cmd: %p QUEUE_FULL in work queue"
" context: %s\n", cmd->se_tfo->get_fabric_name(), cmd,
@@ -1140,7 +1140,7 @@ transport_check_alloc_task_attr(struct s
* Dormant to Active status.
*/
cmd->se_ordered_id = atomic_inc_return(&dev->dev_ordered_id);
- smp_mb__after_atomic_inc();
+ smp_mb__after_atomic();
pr_debug("Allocated se_ordered_id: %u for Task Attr: 0x%02x on %s\n",
cmd->se_ordered_id, cmd->sam_task_attr,
dev->transport->name);
@@ -1692,7 +1692,7 @@ static bool target_handle_task_attr(stru
return false;
case MSG_ORDERED_TAG:
atomic_inc(&dev->dev_ordered_sync);
- smp_mb__after_atomic_inc();
+ smp_mb__after_atomic();

pr_debug("Added ORDERED for CDB: 0x%02x to ordered list, "
" se_ordered_id: %u\n",
@@ -1710,7 +1710,7 @@ static bool target_handle_task_attr(stru
* For SIMPLE and UNTAGGED Task Attribute commands
*/
atomic_inc(&dev->simple_cmds);
- smp_mb__after_atomic_inc();
+ smp_mb__after_atomic();
break;
}

@@ -1806,7 +1806,7 @@ static void transport_complete_task_attr

if (cmd->sam_task_attr == MSG_SIMPLE_TAG) {
atomic_dec(&dev->simple_cmds);
- smp_mb__after_atomic_dec();
+ smp_mb__after_atomic();
dev->dev_cur_ordered_id++;
pr_debug("Incremented dev->dev_cur_ordered_id: %u for"
" SIMPLE: %u\n", dev->dev_cur_ordered_id,
@@ -1818,7 +1818,7 @@ static void transport_complete_task_attr
cmd->se_ordered_id);
} else if (cmd->sam_task_attr == MSG_ORDERED_TAG) {
atomic_dec(&dev->dev_ordered_sync);
- smp_mb__after_atomic_dec();
+ smp_mb__after_atomic();

dev->dev_cur_ordered_id++;
pr_debug("Incremented dev_cur_ordered_id: %u for ORDERED:"
@@ -1877,7 +1877,7 @@ static void transport_handle_queue_full(
spin_lock_irq(&dev->qf_cmd_lock);
list_add_tail(&cmd->se_qf_node, &cmd->se_dev->qf_cmd_list);
atomic_inc(&dev->dev_qf_count);
- smp_mb__after_atomic_inc();
+ smp_mb__after_atomic();
spin_unlock_irq(&cmd->se_dev->qf_cmd_lock);

schedule_work(&cmd->se_dev->qf_work_queue);
@@ -2805,7 +2805,7 @@ void transport_send_task_abort(struct se
if (cmd->data_direction == DMA_TO_DEVICE) {
if (cmd->se_tfo->write_pending_status(cmd) != 0) {
cmd->transport_state |= CMD_T_ABORTED;
- smp_mb__after_atomic_inc();
+ smp_mb__after_atomic();
return;
}
}
--- a/drivers/target/target_core_ua.c
+++ b/drivers/target/target_core_ua.c
@@ -162,7 +162,7 @@ int core_scsi3_ua_allocate(
spin_unlock_irq(&nacl->device_list_lock);

atomic_inc(&deve->ua_count);
- smp_mb__after_atomic_inc();
+ smp_mb__after_atomic();
return 0;
}
list_add_tail(&ua->ua_nacl_list, &deve->ua_list);
@@ -175,7 +175,7 @@ int core_scsi3_ua_allocate(
asc, ascq);

atomic_inc(&deve->ua_count);
- smp_mb__after_atomic_inc();
+ smp_mb__after_atomic();
return 0;
}

@@ -190,7 +190,7 @@ void core_scsi3_ua_release_all(
kmem_cache_free(se_ua_cache, ua);

atomic_dec(&deve->ua_count);
- smp_mb__after_atomic_dec();
+ smp_mb__after_atomic();
}
spin_unlock(&deve->ua_lock);
}
@@ -251,7 +251,7 @@ void core_scsi3_ua_for_check_condition(
kmem_cache_free(se_ua_cache, ua);

atomic_dec(&deve->ua_count);
- smp_mb__after_atomic_dec();
+ smp_mb__after_atomic();
}
spin_unlock(&deve->ua_lock);
spin_unlock_irq(&nacl->device_list_lock);
@@ -310,7 +310,7 @@ int core_scsi3_ua_clear_for_request_sens
kmem_cache_free(se_ua_cache, ua);

atomic_dec(&deve->ua_count);
- smp_mb__after_atomic_dec();
+ smp_mb__after_atomic();
}
spin_unlock(&deve->ua_lock);
spin_unlock_irq(&nacl->device_list_lock);
--- a/drivers/tty/n_tty.c
+++ b/drivers/tty/n_tty.c
@@ -2042,7 +2042,7 @@ static int canon_copy_from_read_buf(stru

if (found)
clear_bit(eol, ldata->read_flags);
- smp_mb__after_clear_bit();
+ smp_mb__after_atomic();
ldata->read_tail += c;

if (found) {
--- a/drivers/tty/serial/mxs-auart.c
+++ b/drivers/tty/serial/mxs-auart.c
@@ -200,7 +200,7 @@ static void dma_tx_callback(void *param)

/* clear the bit used to serialize the DMA tx. */
clear_bit(MXS_AUART_DMA_TX_SYNC, &s->flags);
- smp_mb__after_clear_bit();
+ smp_mb__after_atomic();

/* wake up the possible processes. */
if (uart_circ_chars_pending(xmit) < WAKEUP_CHARS)
@@ -275,7 +275,7 @@ static void mxs_auart_tx_chars(struct mx
mxs_auart_dma_tx(s, i);
} else {
clear_bit(MXS_AUART_DMA_TX_SYNC, &s->flags);
- smp_mb__after_clear_bit();
+ smp_mb__after_atomic();
}
return;
}
--- a/drivers/usb/gadget/tcm_usb_gadget.c
+++ b/drivers/usb/gadget/tcm_usb_gadget.c
@@ -1846,7 +1846,7 @@ static int usbg_port_link(struct se_port
struct usbg_tpg *tpg = container_of(se_tpg, struct usbg_tpg, se_tpg);

atomic_inc(&tpg->tpg_port_count);
- smp_mb__after_atomic_inc();
+ smp_mb__after_atomic();
return 0;
}

@@ -1856,7 +1856,7 @@ static void usbg_port_unlink(struct se_p
struct usbg_tpg *tpg = container_of(se_tpg, struct usbg_tpg, se_tpg);

atomic_dec(&tpg->tpg_port_count);
- smp_mb__after_atomic_dec();
+ smp_mb__after_atomic();
}

static int usbg_check_stop_free(struct se_cmd *se_cmd)
--- a/drivers/usb/serial/usb_wwan.c
+++ b/drivers/usb/serial/usb_wwan.c
@@ -325,7 +325,7 @@ static void usb_wwan_outdat_callback(str

for (i = 0; i < N_OUT_URB; ++i) {
if (portdata->out_urbs[i] == urb) {
- smp_mb__before_clear_bit();
+ smp_mb__before_atomic();
clear_bit(i, &portdata->out_busy);
break;
}
--- a/drivers/vhost/scsi.c
+++ b/drivers/vhost/scsi.c
@@ -1244,7 +1244,7 @@ vhost_scsi_set_endpoint(struct vhost_scs
tpg->tv_tpg_vhost_count++;
tpg->vhost_scsi = vs;
vs_tpg[tpg->tport_tpgt] = tpg;
- smp_mb__after_atomic_inc();
+ smp_mb__after_atomic();
match = true;
}
mutex_unlock(&tpg->tv_tpg_mutex);
--- a/drivers/w1/w1_family.c
+++ b/drivers/w1/w1_family.c
@@ -131,9 +131,9 @@ void w1_family_get(struct w1_family *f)

void __w1_family_get(struct w1_family *f)
{
- smp_mb__before_atomic_inc();
+ smp_mb__before_atomic();
atomic_inc(&f->refcnt);
- smp_mb__after_atomic_inc();
+ smp_mb__after_atomic();
}

EXPORT_SYMBOL(w1_unregister_family);
--- a/drivers/xen/xen-pciback/pciback_ops.c
+++ b/drivers/xen/xen-pciback/pciback_ops.c
@@ -348,9 +348,9 @@ void xen_pcibk_do_op(struct work_struct
notify_remote_via_irq(pdev->evtchn_irq);

/* Mark that we're done. */
- smp_mb__before_clear_bit(); /* /after/ clearing PCIF_active */
+ smp_mb__before_atomic(); /* /after/ clearing PCIF_active */
clear_bit(_PDEVF_op_active, &pdev->flags);
- smp_mb__after_clear_bit(); /* /before/ final check for work */
+ smp_mb__after_atomic(); /* /before/ final check for work */

/* Check to see if the driver domain tried to start another request in
* between clearing _XEN_PCIF_active and clearing _PDEVF_op_active.
--- a/fs/btrfs/btrfs_inode.h
+++ b/fs/btrfs/btrfs_inode.h
@@ -279,7 +279,7 @@ static inline void btrfs_inode_block_unl

static inline void btrfs_inode_resume_unlocked_dio(struct inode *inode)
{
- smp_mb__before_clear_bit();
+ smp_mb__before_atomic();
clear_bit(BTRFS_INODE_READDIO_NEED_LOCK,
&BTRFS_I(inode)->runtime_flags);
}
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -3451,7 +3451,7 @@ static int lock_extent_buffer_for_io(str
static void end_extent_buffer_writeback(struct extent_buffer *eb)
{
clear_bit(EXTENT_BUFFER_WRITEBACK, &eb->bflags);
- smp_mb__after_clear_bit();
+ smp_mb__after_atomic();
wake_up_bit(&eb->bflags, EXTENT_BUFFER_WRITEBACK);
}

--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -7078,7 +7078,7 @@ static void btrfs_end_dio_bio(struct bio
* before atomic variable goto zero, we must make sure
* dip->errors is perceived to be set.
*/
- smp_mb__before_atomic_dec();
+ smp_mb__before_atomic();
}

/* if there are more bios still pending for this dio, just exit */
@@ -7258,7 +7258,7 @@ static int btrfs_submit_direct_hook(int
* before atomic variable goto zero, we must
* make sure dip->errors is perceived to be set.
*/
- smp_mb__before_atomic_dec();
+ smp_mb__before_atomic();
if (atomic_dec_and_test(&dip->pending_bios))
bio_io_error(dip->orig_bio);

@@ -7401,7 +7401,7 @@ static ssize_t btrfs_direct_IO(int rw, s
return 0;

atomic_inc(&inode->i_dio_count);
- smp_mb__after_atomic_inc();
+ smp_mb__after_atomic();

/*
* The generic stuff only does filemap_write_and_wait_range, which isn't
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -77,7 +77,7 @@ EXPORT_SYMBOL(__lock_buffer);
void unlock_buffer(struct buffer_head *bh)
{
clear_bit_unlock(BH_Lock, &bh->b_state);
- smp_mb__after_clear_bit();
+ smp_mb__after_atomic();
wake_up_bit(&bh->b_state, BH_Lock);
}
EXPORT_SYMBOL(unlock_buffer);
--- a/fs/ext4/resize.c
+++ b/fs/ext4/resize.c
@@ -42,7 +42,7 @@ int ext4_resize_begin(struct super_block
void ext4_resize_end(struct super_block *sb)
{
clear_bit_unlock(EXT4_RESIZING, &EXT4_SB(sb)->s_resize_flags);
- smp_mb__after_clear_bit();
+ smp_mb__after_atomic();
}

static ext4_group_t ext4_meta_bg_first_group(struct super_block *sb,
--- a/fs/gfs2/glock.c
+++ b/fs/gfs2/glock.c
@@ -275,7 +275,7 @@ static inline int may_grant(const struct
static void gfs2_holder_wake(struct gfs2_holder *gh)
{
clear_bit(HIF_WAIT, &gh->gh_iflags);
- smp_mb__after_clear_bit();
+ smp_mb__after_atomic();
wake_up_bit(&gh->gh_iflags, HIF_WAIT);
}

@@ -409,7 +409,7 @@ static void gfs2_demote_wake(struct gfs2
{
gl->gl_demote_state = LM_ST_EXCLUSIVE;
clear_bit(GLF_DEMOTE, &gl->gl_flags);
- smp_mb__after_clear_bit();
+ smp_mb__after_atomic();
wake_up_bit(&gl->gl_flags, GLF_DEMOTE);
}

@@ -618,7 +618,7 @@ __acquires(&gl->gl_spin)

out_sched:
clear_bit(GLF_LOCK, &gl->gl_flags);
- smp_mb__after_clear_bit();
+ smp_mb__after_atomic();
gl->gl_lockref.count++;
if (queue_delayed_work(glock_workqueue, &gl->gl_work, 0) == 0)
gl->gl_lockref.count--;
@@ -626,7 +626,7 @@ __acquires(&gl->gl_spin)

out_unlock:
clear_bit(GLF_LOCK, &gl->gl_flags);
- smp_mb__after_clear_bit();
+ smp_mb__after_atomic();
return;
}

--- a/fs/gfs2/glops.c
+++ b/fs/gfs2/glops.c
@@ -219,7 +219,7 @@ static void inode_go_sync(struct gfs2_gl
* Writeback of the data mapping may cause the dirty flag to be set
* so we have to clear it again here.
*/
- smp_mb__before_clear_bit();
+ smp_mb__before_atomic();
clear_bit(GLF_DIRTY, &gl->gl_flags);
}

--- a/fs/gfs2/lock_dlm.c
+++ b/fs/gfs2/lock_dlm.c
@@ -1132,7 +1132,7 @@ static void gdlm_recover_done(void *arg,
queue_delayed_work(gfs2_control_wq, &sdp->sd_control_work, 0);

clear_bit(DFL_DLM_RECOVERY, &ls->ls_recover_flags);
- smp_mb__after_clear_bit();
+ smp_mb__after_atomic();
wake_up_bit(&ls->ls_recover_flags, DFL_DLM_RECOVERY);
spin_unlock(&ls->ls_recover_spin);
}
@@ -1269,7 +1269,7 @@ static int gdlm_mount(struct gfs2_sbd *s

ls->ls_first = !!test_bit(DFL_FIRST_MOUNT, &ls->ls_recover_flags);
clear_bit(SDF_NOJOURNALID, &sdp->sd_flags);
- smp_mb__after_clear_bit();
+ smp_mb__after_atomic();
wake_up_bit(&sdp->sd_flags, SDF_NOJOURNALID);
return 0;

--- a/fs/gfs2/recovery.c
+++ b/fs/gfs2/recovery.c
@@ -587,7 +587,7 @@ void gfs2_recover_func(struct work_struc
gfs2_recovery_done(sdp, jd->jd_jid, LM_RD_GAVEUP);
done:
clear_bit(JDF_RECOVERY, &jd->jd_flags);
- smp_mb__after_clear_bit();
+ smp_mb__after_atomic();
wake_up_bit(&jd->jd_flags, JDF_RECOVERY);
}

--- a/fs/gfs2/sys.c
+++ b/fs/gfs2/sys.c
@@ -332,7 +332,7 @@ static ssize_t block_store(struct gfs2_s
set_bit(DFL_BLOCK_LOCKS, &ls->ls_recover_flags);
else if (val == 0) {
clear_bit(DFL_BLOCK_LOCKS, &ls->ls_recover_flags);
- smp_mb__after_clear_bit();
+ smp_mb__after_atomic();
gfs2_glock_thaw(sdp);
} else {
ret = -EINVAL;
@@ -481,7 +481,7 @@ static ssize_t jid_store(struct gfs2_sbd
rv = jid = -EINVAL;
sdp->sd_lockstruct.ls_jid = jid;
clear_bit(SDF_NOJOURNALID, &sdp->sd_flags);
- smp_mb__after_clear_bit();
+ smp_mb__after_atomic();
wake_up_bit(&sdp->sd_flags, SDF_NOJOURNALID);
out:
spin_unlock(&sdp->sd_jindex_spin);
--- a/fs/jbd2/commit.c
+++ b/fs/jbd2/commit.c
@@ -43,7 +43,7 @@ static void journal_end_buffer_io_sync(s
clear_buffer_uptodate(bh);
if (orig_bh) {
clear_bit_unlock(BH_Shadow, &orig_bh->b_state);
- smp_mb__after_clear_bit();
+ smp_mb__after_atomic();
wake_up_bit(&orig_bh->b_state, BH_Shadow);
}
unlock_buffer(bh);
@@ -239,7 +239,7 @@ static int journal_submit_data_buffers(j
spin_lock(&journal->j_list_lock);
J_ASSERT(jinode->i_transaction == commit_transaction);
clear_bit(__JI_COMMIT_RUNNING, &jinode->i_flags);
- smp_mb__after_clear_bit();
+ smp_mb__after_atomic();
wake_up_bit(&jinode->i_flags, __JI_COMMIT_RUNNING);
}
spin_unlock(&journal->j_list_lock);
@@ -277,7 +277,7 @@ static int journal_finish_inode_data_buf
}
spin_lock(&journal->j_list_lock);
clear_bit(__JI_COMMIT_RUNNING, &jinode->i_flags);
- smp_mb__after_clear_bit();
+ smp_mb__after_atomic();
wake_up_bit(&jinode->i_flags, __JI_COMMIT_RUNNING);
}

--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -1985,9 +1985,9 @@ static void nfs_access_free_entry(struct
{
put_rpccred(entry->cred);
kfree(entry);
- smp_mb__before_atomic_dec();
+ smp_mb__before_atomic();
atomic_long_dec(&nfs_access_nr_entries);
- smp_mb__after_atomic_dec();
+ smp_mb__after_atomic();
}

static void nfs_access_free_list(struct list_head *head)
@@ -2035,9 +2035,9 @@ nfs_access_cache_scan(struct shrinker *s
else {
remove_lru_entry:
list_del_init(&nfsi->access_cache_inode_lru);
- smp_mb__before_clear_bit();
+ smp_mb__before_atomic();
clear_bit(NFS_INO_ACL_LRU_SET, &nfsi->flags);
- smp_mb__after_clear_bit();
+ smp_mb__after_atomic();
}
spin_unlock(&inode->i_lock);
}
@@ -2185,9 +2185,9 @@ void nfs_access_add_cache(struct inode *
nfs_access_add_rbtree(inode, cache);

/* Update accounting */
- smp_mb__before_atomic_inc();
+ smp_mb__before_atomic();
atomic_long_inc(&nfs_access_nr_entries);
- smp_mb__after_atomic_inc();
+ smp_mb__after_atomic();

/* Add inode to global LRU list */
if (!test_bit(NFS_INO_ACL_LRU_SET, &NFS_I(inode)->flags)) {
--- a/fs/nfs/inode.c
+++ b/fs/nfs/inode.c
@@ -1058,7 +1058,7 @@ int nfs_revalidate_mapping(struct inode
trace_nfs_invalidate_mapping_exit(inode, ret);

clear_bit_unlock(NFS_INO_INVALIDATING, bitlock);
- smp_mb__after_clear_bit();
+ smp_mb__after_atomic();
wake_up_bit(bitlock, NFS_INO_INVALIDATING);
out:
return ret;
--- a/fs/nfs/nfs4filelayoutdev.c
+++ b/fs/nfs/nfs4filelayoutdev.c
@@ -789,9 +789,9 @@ static void nfs4_wait_ds_connect(struct

static void nfs4_clear_ds_conn_bit(struct nfs4_pnfs_ds *ds)
{
- smp_mb__before_clear_bit();
+ smp_mb__before_atomic();
clear_bit(NFS4DS_CONNECTING, &ds->ds_state);
- smp_mb__after_clear_bit();
+ smp_mb__after_atomic();
wake_up_bit(&ds->ds_state, NFS4DS_CONNECTING);
}

--- a/fs/nfs/nfs4state.c
+++ b/fs/nfs/nfs4state.c
@@ -1145,9 +1145,9 @@ static int nfs4_run_state_manager(void *

static void nfs4_clear_state_manager_bit(struct nfs_client *clp)
{
- smp_mb__before_clear_bit();
+ smp_mb__before_atomic();
clear_bit(NFS4CLNT_MANAGER_RUNNING, &clp->cl_state);
- smp_mb__after_clear_bit();
+ smp_mb__after_atomic();
wake_up_bit(&clp->cl_state, NFS4CLNT_MANAGER_RUNNING);
rpc_wake_up(&clp->cl_rpcwaitq);
}
--- a/fs/nfs/pagelist.c
+++ b/fs/nfs/pagelist.c
@@ -95,7 +95,7 @@ nfs_iocounter_dec(struct nfs_io_counter
{
if (atomic_dec_and_test(&c->io_count)) {
clear_bit(NFS_IO_INPROGRESS, &c->flags);
- smp_mb__after_clear_bit();
+ smp_mb__after_atomic();
wake_up_bit(&c->flags, NFS_IO_INPROGRESS);
}
}
@@ -193,9 +193,9 @@ void nfs_unlock_request(struct nfs_page
printk(KERN_ERR "NFS: Invalid unlock attempted\n");
BUG();
}
- smp_mb__before_clear_bit();
+ smp_mb__before_atomic();
clear_bit(PG_BUSY, &req->wb_flags);
- smp_mb__after_clear_bit();
+ smp_mb__after_atomic();
wake_up_bit(&req->wb_flags, PG_BUSY);
}

--- a/fs/nfs/pnfs.c
+++ b/fs/nfs/pnfs.c
@@ -1795,7 +1795,7 @@ static void pnfs_clear_layoutcommitting(
unsigned long *bitlock = &NFS_I(inode)->flags;

clear_bit_unlock(NFS_INO_LAYOUTCOMMITTING, bitlock);
- smp_mb__after_clear_bit();
+ smp_mb__after_atomic();
wake_up_bit(bitlock, NFS_INO_LAYOUTCOMMITTING);
}

--- a/fs/nfs/pnfs.h
+++ b/fs/nfs/pnfs.h
@@ -275,7 +275,7 @@ pnfs_get_lseg(struct pnfs_layout_segment
{
if (lseg) {
atomic_inc(&lseg->pls_refcount);
- smp_mb__after_atomic_inc();
+ smp_mb__after_atomic();
}
return lseg;
}
--- a/fs/nfs/write.c
+++ b/fs/nfs/write.c
@@ -405,7 +405,7 @@ int nfs_writepages(struct address_space
nfs_pageio_complete(&pgio);

clear_bit_unlock(NFS_INO_FLUSHING, bitlock);
- smp_mb__after_clear_bit();
+ smp_mb__after_atomic();
wake_up_bit(bitlock, NFS_INO_FLUSHING);

if (err < 0)
@@ -1458,7 +1458,7 @@ static int nfs_commit_set_lock(struct nf
static void nfs_commit_clear_lock(struct nfs_inode *nfsi)
{
clear_bit(NFS_INO_COMMIT, &nfsi->flags);
- smp_mb__after_clear_bit();
+ smp_mb__after_atomic();
wake_up_bit(&nfsi->flags, NFS_INO_COMMIT);
}

--- a/fs/ubifs/lpt_commit.c
+++ b/fs/ubifs/lpt_commit.c
@@ -460,9 +460,9 @@ static int write_cnodes(struct ubifs_inf
* important.
*/
clear_bit(DIRTY_CNODE, &cnode->flags);
- smp_mb__before_clear_bit();
+ smp_mb__before_atomic();
clear_bit(COW_CNODE, &cnode->flags);
- smp_mb__after_clear_bit();
+ smp_mb__after_atomic();
offs += len;
dbg_chk_lpt_sz(c, 1, len);
cnode = cnode->cnext;
--- a/fs/ubifs/tnc_commit.c
+++ b/fs/ubifs/tnc_commit.c
@@ -895,9 +895,9 @@ static int write_index(struct ubifs_info
* the reason for the second barrier.
*/
clear_bit(DIRTY_ZNODE, &znode->flags);
- smp_mb__before_clear_bit();
+ smp_mb__before_atomic();
clear_bit(COW_ZNODE, &znode->flags);
- smp_mb__after_clear_bit();
+ smp_mb__after_atomic();

/*
* We have marked the znode as clean but have not updated the
--- a/include/asm-generic/atomic.h
+++ b/include/asm-generic/atomic.h
@@ -16,6 +16,7 @@
#define __ASM_GENERIC_ATOMIC_H

#include <asm/cmpxchg.h>
+#include <asm/barrier.h>

#ifdef CONFIG_SMP
/* Force people to define core atomics */
@@ -182,11 +183,5 @@ static inline void atomic_set_mask(unsig
}
#endif

-/* Assume that atomic operations are already serializing */
-#define smp_mb__before_atomic_dec() barrier()
-#define smp_mb__after_atomic_dec() barrier()
-#define smp_mb__before_atomic_inc() barrier()
-#define smp_mb__after_atomic_inc() barrier()
-
#endif /* __KERNEL__ */
#endif /* __ASM_GENERIC_ATOMIC_H */
--- a/include/asm-generic/barrier.h
+++ b/include/asm-generic/barrier.h
@@ -62,6 +62,14 @@
#define set_mb(var, value) do { (var) = (value); mb(); } while (0)
#endif

+#ifndef smp_mb__before_atomic
+#define smp_mb__before_atomic() smp_mb()
+#endif
+
+#ifndef smp_mb__after_atomic
+#define smp_mb__after_atomic() smp_mb()
+#endif
+
#define smp_store_release(p, v) \
do { \
compiletime_assert_atomic_type(*p); \
--- a/include/asm-generic/bitops.h
+++ b/include/asm-generic/bitops.h
@@ -11,14 +11,8 @@

#include <linux/irqflags.h>
#include <linux/compiler.h>
+#include <asm/barrier.h>

-/*
- * clear_bit may not imply a memory barrier
- */
-#ifndef smp_mb__before_clear_bit
-#define smp_mb__before_clear_bit() smp_mb()
-#define smp_mb__after_clear_bit() smp_mb()
-#endif

#include <asm-generic/bitops/__ffs.h>
#include <asm-generic/bitops/ffz.h>
--- a/include/asm-generic/bitops/atomic.h
+++ b/include/asm-generic/bitops/atomic.h
@@ -80,7 +80,7 @@ static inline void set_bit(int nr, volat
*
* clear_bit() is atomic and may not be reordered. However, it does
* not contain a memory barrier, so if it is used for locking purposes,
- * you should call smp_mb__before_clear_bit() and/or smp_mb__after_clear_bit()
+ * you should call smp_mb__before_atomic() and/or smp_mb__after_atomic()
* in order to ensure changes are visible on other processors.
*/
static inline void clear_bit(int nr, volatile unsigned long *addr)
--- a/include/asm-generic/bitops/lock.h
+++ b/include/asm-generic/bitops/lock.h
@@ -20,7 +20,7 @@
*/
#define clear_bit_unlock(nr, addr) \
do { \
- smp_mb__before_clear_bit(); \
+ smp_mb__before_atomic(); \
clear_bit(nr, addr); \
} while (0)

--- a/include/linux/buffer_head.h
+++ b/include/linux/buffer_head.h
@@ -278,7 +278,7 @@ static inline void get_bh(struct buffer_

static inline void put_bh(struct buffer_head *bh)
{
- smp_mb__before_atomic_dec();
+ smp_mb__before_atomic();
atomic_dec(&bh->b_count);
}

--- a/include/linux/genhd.h
+++ b/include/linux/genhd.h
@@ -649,7 +649,7 @@ static inline void hd_ref_init(struct hd
static inline void hd_struct_get(struct hd_struct *part)
{
atomic_inc(&part->ref);
- smp_mb__after_atomic_inc();
+ smp_mb__after_atomic();
}

static inline int hd_struct_try_get(struct hd_struct *part)
--- a/include/linux/interrupt.h
+++ b/include/linux/interrupt.h
@@ -447,7 +447,7 @@ static inline int tasklet_trylock(struct

static inline void tasklet_unlock(struct tasklet_struct *t)
{
- smp_mb__before_clear_bit();
+ smp_mb__before_atomic();
clear_bit(TASKLET_STATE_RUN, &(t)->state);
}

@@ -495,7 +495,7 @@ static inline void tasklet_hi_schedule_f
static inline void tasklet_disable_nosync(struct tasklet_struct *t)
{
atomic_inc(&t->count);
- smp_mb__after_atomic_inc();
+ smp_mb__after_atomic();
}

static inline void tasklet_disable(struct tasklet_struct *t)
@@ -507,13 +507,13 @@ static inline void tasklet_disable(struc

static inline void tasklet_enable(struct tasklet_struct *t)
{
- smp_mb__before_atomic_dec();
+ smp_mb__before_atomic();
atomic_dec(&t->count);
}

static inline void tasklet_hi_enable(struct tasklet_struct *t)
{
- smp_mb__before_atomic_dec();
+ smp_mb__before_atomic();
atomic_dec(&t->count);
}

--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -500,7 +500,7 @@ static inline void napi_disable(struct n
static inline void napi_enable(struct napi_struct *n)
{
BUG_ON(!test_bit(NAPI_STATE_SCHED, &n->state));
- smp_mb__before_clear_bit();
+ smp_mb__before_atomic();
clear_bit(NAPI_STATE_SCHED, &n->state);
}

--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -2737,10 +2737,8 @@ static inline bool __must_check current_
/*
* Polling state must be visible before we test NEED_RESCHED,
* paired by resched_task()
- *
- * XXX: assumes set/clear bit are identical barrier wise.
*/
- smp_mb__after_clear_bit();
+ smp_mb__after_atomic();

return unlikely(tif_need_resched());
}
@@ -2758,7 +2756,7 @@ static inline bool __must_check current_
* Polling state must be visible before we test NEED_RESCHED,
* paired by resched_task()
*/
- smp_mb__after_clear_bit();
+ smp_mb__after_atomic();

return unlikely(tif_need_resched());
}
--- a/include/linux/sunrpc/sched.h
+++ b/include/linux/sunrpc/sched.h
@@ -142,18 +142,18 @@ struct rpc_task_setup {
test_and_set_bit(RPC_TASK_RUNNING, &(t)->tk_runstate)
#define rpc_clear_running(t) \
do { \
- smp_mb__before_clear_bit(); \
+ smp_mb__before_atomic(); \
clear_bit(RPC_TASK_RUNNING, &(t)->tk_runstate); \
- smp_mb__after_clear_bit(); \
+ smp_mb__after_atomic(); \
} while (0)

#define RPC_IS_QUEUED(t) test_bit(RPC_TASK_QUEUED, &(t)->tk_runstate)
#define rpc_set_queued(t) set_bit(RPC_TASK_QUEUED, &(t)->tk_runstate)
#define rpc_clear_queued(t) \
do { \
- smp_mb__before_clear_bit(); \
+ smp_mb__before_atomic(); \
clear_bit(RPC_TASK_QUEUED, &(t)->tk_runstate); \
- smp_mb__after_clear_bit(); \
+ smp_mb__after_atomic(); \
} while (0)

#define RPC_IS_ACTIVATED(t) test_bit(RPC_TASK_ACTIVE, &(t)->tk_runstate)
--- a/include/linux/sunrpc/xprt.h
+++ b/include/linux/sunrpc/xprt.h
@@ -368,9 +368,9 @@ static inline int xprt_test_and_clear_co

static inline void xprt_clear_connecting(struct rpc_xprt *xprt)
{
- smp_mb__before_clear_bit();
+ smp_mb__before_atomic();
clear_bit(XPRT_CONNECTING, &xprt->state);
- smp_mb__after_clear_bit();
+ smp_mb__after_atomic();
}

static inline int xprt_connecting(struct rpc_xprt *xprt)
@@ -400,9 +400,9 @@ static inline void xprt_clear_bound(stru

static inline void xprt_clear_binding(struct rpc_xprt *xprt)
{
- smp_mb__before_clear_bit();
+ smp_mb__before_atomic();
clear_bit(XPRT_BINDING, &xprt->state);
- smp_mb__after_clear_bit();
+ smp_mb__after_atomic();
}

static inline int xprt_test_and_set_binding(struct rpc_xprt *xprt)
--- a/include/linux/tracehook.h
+++ b/include/linux/tracehook.h
@@ -191,7 +191,7 @@ static inline void tracehook_notify_resu
* pairs with task_work_add()->set_notify_resume() after
* hlist_add_head(task->task_works);
*/
- smp_mb__after_clear_bit();
+ smp_mb__after_atomic();
if (unlikely(current->task_works))
task_work_run();
}
--- a/include/net/ip_vs.h
+++ b/include/net/ip_vs.h
@@ -1204,7 +1204,7 @@ static inline bool __ip_vs_conn_get(stru
/* put back the conn without restarting its timer */
static inline void __ip_vs_conn_put(struct ip_vs_conn *cp)
{
- smp_mb__before_atomic_dec();
+ smp_mb__before_atomic();
atomic_dec(&cp->refcnt);
}
void ip_vs_conn_put(struct ip_vs_conn *cp);
@@ -1408,7 +1408,7 @@ static inline void ip_vs_dest_hold(struc

static inline void ip_vs_dest_put(struct ip_vs_dest *dest)
{
- smp_mb__before_atomic_dec();
+ smp_mb__before_atomic();
atomic_dec(&dest->refcnt);
}

--- a/kernel/debug/debug_core.c
+++ b/kernel/debug/debug_core.c
@@ -526,7 +526,7 @@ static int kgdb_cpu_enter(struct kgdb_st
kgdb_info[cpu].exception_state &=
~(DCPU_WANT_MASTER | DCPU_IS_SLAVE);
kgdb_info[cpu].enter_kgdb--;
- smp_mb__before_atomic_dec();
+ smp_mb__before_atomic();
atomic_dec(&slaves_in_kgdb);
dbg_touch_watchdogs();
local_irq_restore(flags);
@@ -654,7 +654,7 @@ static int kgdb_cpu_enter(struct kgdb_st
kgdb_info[cpu].exception_state &=
~(DCPU_WANT_MASTER | DCPU_IS_SLAVE);
kgdb_info[cpu].enter_kgdb--;
- smp_mb__before_atomic_dec();
+ smp_mb__before_atomic();
atomic_dec(&masters_in_kgdb);
/* Free kgdb_active */
atomic_set(&kgdb_active, -1);
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -250,7 +250,7 @@ static inline void futex_get_mm(union fu
* get_futex_key() implies a full barrier. This is relied upon
* as full barrier (B), see the ordering comment above.
*/
- smp_mb__after_atomic_inc();
+ smp_mb__after_atomic();
}

static inline bool hb_waiters_pending(struct futex_hash_bucket *hb)
--- a/kernel/kmod.c
+++ b/kernel/kmod.c
@@ -498,7 +498,7 @@ int __usermodehelper_disable(enum umh_di
static void helper_lock(void)
{
atomic_inc(&running_helpers);
- smp_mb__after_atomic_inc();
+ smp_mb__after_atomic();
}

static void helper_unlock(void)
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -389,9 +389,9 @@ static void rcu_eqs_enter_common(struct
}
rcu_prepare_for_idle(smp_processor_id());
/* CPUs seeing atomic_inc() must see prior RCU read-side crit sects */
- smp_mb__before_atomic_inc(); /* See above. */
+ smp_mb__before_atomic(); /* See above. */
atomic_inc(&rdtp->dynticks);
- smp_mb__after_atomic_inc(); /* Force ordering with next sojourn. */
+ smp_mb__after_atomic(); /* Force ordering with next sojourn. */
WARN_ON_ONCE(atomic_read(&rdtp->dynticks) & 0x1);

/*
@@ -509,10 +509,10 @@ void rcu_irq_exit(void)
static void rcu_eqs_exit_common(struct rcu_dynticks *rdtp, long long oldval,
int user)
{
- smp_mb__before_atomic_inc(); /* Force ordering w/previous sojourn. */
+ smp_mb__before_atomic(); /* Force ordering w/previous sojourn. */
atomic_inc(&rdtp->dynticks);
/* CPUs seeing atomic_inc() must see later RCU read-side crit sects */
- smp_mb__after_atomic_inc(); /* See above. */
+ smp_mb__after_atomic(); /* See above. */
WARN_ON_ONCE(!(atomic_read(&rdtp->dynticks) & 0x1));
rcu_cleanup_after_idle(smp_processor_id());
trace_rcu_dyntick(TPS("End"), oldval, rdtp->dynticks_nesting);
@@ -637,10 +637,10 @@ void rcu_nmi_enter(void)
(atomic_read(&rdtp->dynticks) & 0x1))
return;
rdtp->dynticks_nmi_nesting++;
- smp_mb__before_atomic_inc(); /* Force delay from prior write. */
+ smp_mb__before_atomic(); /* Force delay from prior write. */
atomic_inc(&rdtp->dynticks);
/* CPUs seeing atomic_inc() must see later RCU read-side crit sects */
- smp_mb__after_atomic_inc(); /* See above. */
+ smp_mb__after_atomic(); /* See above. */
WARN_ON_ONCE(!(atomic_read(&rdtp->dynticks) & 0x1));
}

@@ -659,9 +659,9 @@ void rcu_nmi_exit(void)
--rdtp->dynticks_nmi_nesting != 0)
return;
/* CPUs seeing atomic_inc() must see prior RCU read-side crit sects */
- smp_mb__before_atomic_inc(); /* See above. */
+ smp_mb__before_atomic(); /* See above. */
atomic_inc(&rdtp->dynticks);
- smp_mb__after_atomic_inc(); /* Force delay to next write. */
+ smp_mb__after_atomic(); /* Force delay to next write. */
WARN_ON_ONCE(atomic_read(&rdtp->dynticks) & 0x1);
}

@@ -2738,7 +2738,7 @@ void synchronize_sched_expedited(void)
s = atomic_long_read(&rsp->expedited_done);
if (ULONG_CMP_GE((ulong)s, (ulong)firstsnap)) {
/* ensure test happens before caller kfree */
- smp_mb__before_atomic_inc(); /* ^^^ */
+ smp_mb__before_atomic(); /* ^^^ */
atomic_long_inc(&rsp->expedited_workdone1);
return;
}
@@ -2756,7 +2756,7 @@ void synchronize_sched_expedited(void)
s = atomic_long_read(&rsp->expedited_done);
if (ULONG_CMP_GE((ulong)s, (ulong)firstsnap)) {
/* ensure test happens before caller kfree */
- smp_mb__before_atomic_inc(); /* ^^^ */
+ smp_mb__before_atomic(); /* ^^^ */
atomic_long_inc(&rsp->expedited_workdone2);
return;
}
@@ -2785,7 +2785,7 @@ void synchronize_sched_expedited(void)
s = atomic_long_read(&rsp->expedited_done);
if (ULONG_CMP_GE((ulong)s, (ulong)snap)) {
/* ensure test happens before caller kfree */
- smp_mb__before_atomic_inc(); /* ^^^ */
+ smp_mb__before_atomic(); /* ^^^ */
atomic_long_inc(&rsp->expedited_done_lost);
break;
}
--- a/kernel/rcu/tree_plugin.h
+++ b/kernel/rcu/tree_plugin.h
@@ -2514,9 +2514,9 @@ static void rcu_sysidle_enter(struct rcu
/* Record start of fully idle period. */
j = jiffies;
ACCESS_ONCE(rdtp->dynticks_idle_jiffies) = j;
- smp_mb__before_atomic_inc();
+ smp_mb__before_atomic();
atomic_inc(&rdtp->dynticks_idle);
- smp_mb__after_atomic_inc();
+ smp_mb__after_atomic();
WARN_ON_ONCE(atomic_read(&rdtp->dynticks_idle) & 0x1);
}

@@ -2581,9 +2581,9 @@ static void rcu_sysidle_exit(struct rcu_
}

/* Record end of idle period. */
- smp_mb__before_atomic_inc();
+ smp_mb__before_atomic();
atomic_inc(&rdtp->dynticks_idle);
- smp_mb__after_atomic_inc();
+ smp_mb__after_atomic();
WARN_ON_ONCE(!(atomic_read(&rdtp->dynticks_idle) & 0x1));

/*
--- a/kernel/sched/cpupri.c
+++ b/kernel/sched/cpupri.c
@@ -165,7 +165,7 @@ void cpupri_set(struct cpupri *cp, int c
* do a write memory barrier, and then update the count, to
* make sure the vector is visible when count is set.
*/
- smp_mb__before_atomic_inc();
+ smp_mb__before_atomic();
atomic_inc(&(vec)->count);
do_mb = 1;
}
@@ -185,14 +185,14 @@ void cpupri_set(struct cpupri *cp, int c
* the new priority vec.
*/
if (do_mb)
- smp_mb__after_atomic_inc();
+ smp_mb__after_atomic();

/*
* When removing from the vector, we decrement the counter first
* do a memory barrier and then clear the mask.
*/
atomic_dec(&(vec)->count);
- smp_mb__after_atomic_inc();
+ smp_mb__after_atomic();
cpumask_clear_cpu(cpu, vec->mask);
}

--- a/kernel/sched/wait.c
+++ b/kernel/sched/wait.c
@@ -394,7 +394,7 @@ EXPORT_SYMBOL(__wake_up_bit);
*
* In order for this to function properly, as it uses waitqueue_active()
* internally, some kind of memory barrier must be done prior to calling
- * this. Typically, this will be smp_mb__after_clear_bit(), but in some
+ * this. Typically, this will be smp_mb__after_atomic(), but in some
* cases where bitflags are manipulated non-atomically under a lock, one
* may need to use a less regular barrier, such fs/inode.c's smp_mb(),
* because spin_unlock() does not guarantee a memory barrier.
--- a/mm/backing-dev.c
+++ b/mm/backing-dev.c
@@ -549,7 +549,7 @@ void clear_bdi_congested(struct backing_
bit = sync ? BDI_sync_congested : BDI_async_congested;
if (test_and_clear_bit(bit, &bdi->state))
atomic_dec(&nr_bdi_congested[sync]);
- smp_mb__after_clear_bit();
+ smp_mb__after_atomic();
if (waitqueue_active(wqh))
wake_up(wqh);
}
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -609,7 +609,7 @@ void unlock_page(struct page *page)
{
VM_BUG_ON_PAGE(!PageLocked(page), page);
clear_bit_unlock(PG_locked, &page->flags);
- smp_mb__after_clear_bit();
+ smp_mb__after_atomic();
wake_up_page(page, PG_locked);
}
EXPORT_SYMBOL(unlock_page);
@@ -626,7 +626,7 @@ void end_page_writeback(struct page *pag
if (!test_clear_page_writeback(page))
BUG();

- smp_mb__after_clear_bit();
+ smp_mb__after_atomic();
wake_up_page(page, PG_writeback);
}
EXPORT_SYMBOL(end_page_writeback);
--- a/net/atm/pppoatm.c
+++ b/net/atm/pppoatm.c
@@ -252,7 +252,7 @@ static int pppoatm_may_send(struct pppoa
* we need to ensure there's a memory barrier after it. The bit
* *must* be set before we do the atomic_inc() on pvcc->inflight.
* There's no smp_mb__after_set_bit(), so it's this or abuse
- * smp_mb__after_clear_bit().
+ * smp_mb__after_atomic().
*/
test_and_set_bit(BLOCKED, &pvcc->blocked);

--- a/net/bluetooth/hci_event.c
+++ b/net/bluetooth/hci_event.c
@@ -45,7 +45,7 @@ static void hci_cc_inquiry_cancel(struct
return;

clear_bit(HCI_INQUIRY, &hdev->flags);
- smp_mb__after_clear_bit(); /* wake_up_bit advises about this barrier */
+ smp_mb__after_atomic(); /* wake_up_bit advises about this barrier */
wake_up_bit(&hdev->flags, HCI_INQUIRY);

hci_conn_check_pending(hdev);
@@ -1531,7 +1531,7 @@ static void hci_inquiry_complete_evt(str
if (!test_and_clear_bit(HCI_INQUIRY, &hdev->flags))
return;

- smp_mb__after_clear_bit(); /* wake_up_bit advises about this barrier */
+ smp_mb__after_atomic(); /* wake_up_bit advises about this barrier */
wake_up_bit(&hdev->flags, HCI_INQUIRY);

if (!test_bit(HCI_MGMT, &hdev->dev_flags))
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -1323,7 +1323,7 @@ static int __dev_close_many(struct list_
* dev->stop() will invoke napi_disable() on all of it's
* napi_struct instances on this device.
*/
- smp_mb__after_clear_bit(); /* Commit netif_running(). */
+ smp_mb__after_atomic(); /* Commit netif_running(). */
}

dev_deactivate_many(head);
@@ -3343,7 +3343,7 @@ static void net_tx_action(struct softirq

root_lock = qdisc_lock(q);
if (spin_trylock(root_lock)) {
- smp_mb__before_clear_bit();
+ smp_mb__before_atomic();
clear_bit(__QDISC_STATE_SCHED,
&q->state);
qdisc_run(q);
@@ -3353,7 +3353,7 @@ static void net_tx_action(struct softirq
&q->state)) {
__netif_reschedule(q);
} else {
- smp_mb__before_clear_bit();
+ smp_mb__before_atomic();
clear_bit(__QDISC_STATE_SCHED,
&q->state);
}
@@ -4216,7 +4216,7 @@ void __napi_complete(struct napi_struct
BUG_ON(n->gro_list);

list_del(&n->poll_list);
- smp_mb__before_clear_bit();
+ smp_mb__before_atomic();
clear_bit(NAPI_STATE_SCHED, &n->state);
}
EXPORT_SYMBOL(__napi_complete);
--- a/net/core/link_watch.c
+++ b/net/core/link_watch.c
@@ -147,7 +147,7 @@ static void linkwatch_do_dev(struct net_
* Make sure the above read is complete since it can be
* rewritten as soon as we clear the bit below.
*/
- smp_mb__before_clear_bit();
+ smp_mb__before_atomic();

/* We are about to handle this device,
* so new events can be accepted
--- a/net/ipv4/inetpeer.c
+++ b/net/ipv4/inetpeer.c
@@ -522,7 +522,7 @@ EXPORT_SYMBOL_GPL(inet_getpeer);
void inet_putpeer(struct inet_peer *p)
{
p->dtime = (__u32)jiffies;
- smp_mb__before_atomic_dec();
+ smp_mb__before_atomic();
atomic_dec(&p->refcnt);
}
EXPORT_SYMBOL_GPL(inet_putpeer);
--- a/net/netfilter/nf_conntrack_core.c
+++ b/net/netfilter/nf_conntrack_core.c
@@ -751,7 +751,7 @@ void nf_conntrack_free(struct nf_conn *c
nf_ct_ext_destroy(ct);
nf_ct_ext_free(ct);
kmem_cache_free(net->ct.nf_conntrack_cachep, ct);
- smp_mb__before_atomic_dec();
+ smp_mb__before_atomic();
atomic_dec(&net->ct.count);
}
EXPORT_SYMBOL_GPL(nf_conntrack_free);
--- a/net/rds/ib_recv.c
+++ b/net/rds/ib_recv.c
@@ -598,7 +598,7 @@ static void rds_ib_set_ack(struct rds_ib
{
atomic64_set(&ic->i_ack_next, seq);
if (ack_required) {
- smp_mb__before_clear_bit();
+ smp_mb__before_atomic();
set_bit(IB_ACK_REQUESTED, &ic->i_ack_flags);
}
}
@@ -606,7 +606,7 @@ static void rds_ib_set_ack(struct rds_ib
static u64 rds_ib_get_ack(struct rds_ib_connection *ic)
{
clear_bit(IB_ACK_REQUESTED, &ic->i_ack_flags);
- smp_mb__after_clear_bit();
+ smp_mb__after_atomic();

return atomic64_read(&ic->i_ack_next);
}
--- a/net/rds/iw_recv.c
+++ b/net/rds/iw_recv.c
@@ -429,7 +429,7 @@ static void rds_iw_set_ack(struct rds_iw
{
atomic64_set(&ic->i_ack_next, seq);
if (ack_required) {
- smp_mb__before_clear_bit();
+ smp_mb__before_atomic();
set_bit(IB_ACK_REQUESTED, &ic->i_ack_flags);
}
}
@@ -437,7 +437,7 @@ static void rds_iw_set_ack(struct rds_iw
static u64 rds_iw_get_ack(struct rds_iw_connection *ic)
{
clear_bit(IB_ACK_REQUESTED, &ic->i_ack_flags);
- smp_mb__after_clear_bit();
+ smp_mb__after_atomic();

return atomic64_read(&ic->i_ack_next);
}
--- a/net/rds/send.c
+++ b/net/rds/send.c
@@ -107,7 +107,7 @@ static int acquire_in_xmit(struct rds_co
static void release_in_xmit(struct rds_connection *conn)
{
clear_bit(RDS_IN_XMIT, &conn->c_flags);
- smp_mb__after_clear_bit();
+ smp_mb__after_atomic();
/*
* We don't use wait_on_bit()/wake_up_bit() because our waking is in a
* hot path and finding waiters is very rare. We don't want to walk
@@ -661,7 +661,7 @@ void rds_send_drop_acked(struct rds_conn

/* order flag updates with spin locks */
if (!list_empty(&list))
- smp_mb__after_clear_bit();
+ smp_mb__after_atomic();

spin_unlock_irqrestore(&conn->c_lock, flags);

@@ -691,7 +691,7 @@ void rds_send_drop_to(struct rds_sock *r
}

/* order flag updates with the rs lock */
- smp_mb__after_clear_bit();
+ smp_mb__after_atomic();

spin_unlock_irqrestore(&rs->rs_lock, flags);

--- a/net/rds/tcp_send.c
+++ b/net/rds/tcp_send.c
@@ -93,7 +93,7 @@ int rds_tcp_xmit(struct rds_connection *
rm->m_ack_seq = tc->t_last_sent_nxt +
sizeof(struct rds_header) +
be32_to_cpu(rm->m_inc.i_hdr.h_len) - 1;
- smp_mb__before_clear_bit();
+ smp_mb__before_atomic();
set_bit(RDS_MSG_HAS_ACK_SEQ, &rm->m_flags);
tc->t_last_expected_una = rm->m_ack_seq + 1;

--- a/net/sunrpc/auth.c
+++ b/net/sunrpc/auth.c
@@ -296,7 +296,7 @@ static void
rpcauth_unhash_cred_locked(struct rpc_cred *cred)
{
hlist_del_rcu(&cred->cr_hash);
- smp_mb__before_clear_bit();
+ smp_mb__before_atomic();
clear_bit(RPCAUTH_CRED_HASHED, &cred->cr_flags);
}

--- a/net/sunrpc/auth_gss/auth_gss.c
+++ b/net/sunrpc/auth_gss/auth_gss.c
@@ -142,7 +142,7 @@ gss_cred_set_ctx(struct rpc_cred *cred,
gss_get_ctx(ctx);
rcu_assign_pointer(gss_cred->gc_ctx, ctx);
set_bit(RPCAUTH_CRED_UPTODATE, &cred->cr_flags);
- smp_mb__before_clear_bit();
+ smp_mb__before_atomic();
clear_bit(RPCAUTH_CRED_NEW, &cred->cr_flags);
}

--- a/net/sunrpc/backchannel_rqst.c
+++ b/net/sunrpc/backchannel_rqst.c
@@ -257,10 +257,10 @@ void xprt_free_bc_request(struct rpc_rqs

dprintk("RPC: free backchannel req=%p\n", req);

- smp_mb__before_clear_bit();
+ smp_mb__before_atomic();
WARN_ON_ONCE(!test_bit(RPC_BC_PA_IN_USE, &req->rq_bc_pa_state));
clear_bit(RPC_BC_PA_IN_USE, &req->rq_bc_pa_state);
- smp_mb__after_clear_bit();
+ smp_mb__after_atomic();

if (!xprt_need_to_requeue(xprt)) {
/*
--- a/net/sunrpc/xprt.c
+++ b/net/sunrpc/xprt.c
@@ -230,9 +230,9 @@ static void xprt_clear_locked(struct rpc
{
xprt->snd_task = NULL;
if (!test_bit(XPRT_CLOSE_WAIT, &xprt->state)) {
- smp_mb__before_clear_bit();
+ smp_mb__before_atomic();
clear_bit(XPRT_LOCKED, &xprt->state);
- smp_mb__after_clear_bit();
+ smp_mb__after_atomic();
} else
queue_work(rpciod_workqueue, &xprt->task_cleanup);
}
--- a/net/sunrpc/xprtsock.c
+++ b/net/sunrpc/xprtsock.c
@@ -889,11 +889,11 @@ static void xs_close(struct rpc_xprt *xp
xs_reset_transport(transport);
xprt->reestablish_timeout = 0;

- smp_mb__before_clear_bit();
+ smp_mb__before_atomic();
clear_bit(XPRT_CONNECTION_ABORT, &xprt->state);
clear_bit(XPRT_CLOSE_WAIT, &xprt->state);
clear_bit(XPRT_CLOSING, &xprt->state);
- smp_mb__after_clear_bit();
+ smp_mb__after_atomic();
xprt_disconnect_done(xprt);
}

@@ -1500,12 +1500,12 @@ static void xs_tcp_cancel_linger_timeout

static void xs_sock_reset_connection_flags(struct rpc_xprt *xprt)
{
- smp_mb__before_clear_bit();
+ smp_mb__before_atomic();
clear_bit(XPRT_CONNECTION_ABORT, &xprt->state);
clear_bit(XPRT_CONNECTION_CLOSE, &xprt->state);
clear_bit(XPRT_CLOSE_WAIT, &xprt->state);
clear_bit(XPRT_CLOSING, &xprt->state);
- smp_mb__after_clear_bit();
+ smp_mb__after_atomic();
}

static void xs_sock_mark_closed(struct rpc_xprt *xprt)
@@ -1559,10 +1559,10 @@ static void xs_tcp_state_change(struct s
xprt->connect_cookie++;
xprt->reestablish_timeout = 0;
set_bit(XPRT_CLOSING, &xprt->state);
- smp_mb__before_clear_bit();
+ smp_mb__before_atomic();
clear_bit(XPRT_CONNECTED, &xprt->state);
clear_bit(XPRT_CLOSE_WAIT, &xprt->state);
- smp_mb__after_clear_bit();
+ smp_mb__after_atomic();
xs_tcp_schedule_linger_timeout(xprt, xs_tcp_fin_timeout);
break;
case TCP_CLOSE_WAIT:
@@ -1581,9 +1581,9 @@ static void xs_tcp_state_change(struct s
case TCP_LAST_ACK:
set_bit(XPRT_CLOSING, &xprt->state);
xs_tcp_schedule_linger_timeout(xprt, xs_tcp_fin_timeout);
- smp_mb__before_clear_bit();
+ smp_mb__before_atomic();
clear_bit(XPRT_CONNECTED, &xprt->state);
- smp_mb__after_clear_bit();
+ smp_mb__after_atomic();
break;
case TCP_CLOSE:
xs_tcp_cancel_linger_timeout(xprt);
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -1208,7 +1208,7 @@ static int unix_stream_connect(struct so
sk->sk_state = TCP_ESTABLISHED;
sock_hold(newsk);

- smp_mb__after_atomic_inc(); /* sock_hold() does an atomic_inc() */
+ smp_mb__after_atomic(); /* sock_hold() does an atomic_inc() */
unix_peer(sk) = newsk;

unix_state_unlock(sk);
--- a/sound/pci/bt87x.c
+++ b/sound/pci/bt87x.c
@@ -435,7 +435,7 @@ static int snd_bt87x_pcm_open(struct snd

_error:
clear_bit(0, &chip->opened);
- smp_mb__after_clear_bit();
+ smp_mb__after_atomic();
return err;
}

@@ -450,7 +450,7 @@ static int snd_bt87x_close(struct snd_pc

chip->substream = NULL;
clear_bit(0, &chip->opened);
- smp_mb__after_clear_bit();
+ smp_mb__after_atomic();
return 0;
}

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/

Next message: Peter Zijlstra: "[RFC][PATCH 4/5] arch: Generic atomic.h cleanup"
Previous message: Peter Zijlstra: "[RFC][PATCH 5/5] arch: Sanitize atomic_t bitwise ops"
In reply to: Peter Zijlstra: "Re: [RFC][PATCH 5/5] arch: Sanitize atomic_t bitwise ops"
Next in thread: Paul E. McKenney: "Re: [RFC][PATCH 3/5] arch:s/smp_mb__(before|after)_(atomic|clear)_(dec,inc,bit)/smp_mb__\1/g"
Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]