linux/include/asm-generic/barrier.h

266 lines
6.0 KiB
C
Raw Normal View History

/*
* Generic barrier definitions.
*
* It should be possible to use these on really simple architectures,
* but it serves more as a starting point for new ports.
*
* Copyright (C) 2007 Red Hat, Inc. All Rights Reserved.
* Written by David Howells (dhowells@redhat.com)
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public Licence
* as published by the Free Software Foundation; either version
* 2 of the Licence, or (at your option) any later version.
*/
#ifndef __ASM_GENERIC_BARRIER_H
#define __ASM_GENERIC_BARRIER_H
#ifndef __ASSEMBLY__
#include <linux/compiler.h>
#ifndef nop
#define nop() asm volatile ("nop")
#endif
/*
* Force strict CPU ordering. And yes, this is required on UP too when we're
* talking to devices.
*
* Fall back to compiler barriers if nothing better is provided.
*/
#ifndef mb
#define mb() barrier()
#endif
#ifndef rmb
#define rmb() mb()
#endif
#ifndef wmb
#define wmb() mb()
#endif
arch: Add lightweight memory barriers dma_rmb() and dma_wmb() There are a number of situations where the mandatory barriers rmb() and wmb() are used to order memory/memory operations in the device drivers and those barriers are much heavier than they actually need to be. For example in the case of PowerPC wmb() calls the heavy-weight sync instruction when for coherent memory operations all that is really needed is an lsync or eieio instruction. This commit adds a coherent only version of the mandatory memory barriers rmb() and wmb(). In most cases this should result in the barrier being the same as the SMP barriers for the SMP case, however in some cases we use a barrier that is somewhere in between rmb() and smp_rmb(). For example on ARM the rmb barriers break down as follows: Barrier Call Explanation --------- -------- ---------------------------------- rmb() dsb() Data synchronization barrier - system dma_rmb() dmb(osh) data memory barrier - outer sharable smp_rmb() dmb(ish) data memory barrier - inner sharable These new barriers are not as safe as the standard rmb() and wmb(). Specifically they do not guarantee ordering between coherent and incoherent memories. The primary use case for these would be to enforce ordering of reads and writes when accessing coherent memory that is shared between the CPU and a device. It may also be noted that there is no dma_mb(). Most architectures don't provide a good mechanism for performing a coherent only full barrier without resorting to the same mechanism used in mb(). As such there isn't much to be gained in trying to define such a function. Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca> Cc: Michael Ellerman <michael@ellerman.id.au> Cc: Michael Neuling <mikey@neuling.org> Cc: Russell King <linux@arm.linux.org.uk> Cc: Geert Uytterhoeven <geert@linux-m68k.org> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Tony Luck <tony.luck@intel.com> Cc: Oleg Nesterov <oleg@redhat.com> Cc: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ingo Molnar <mingo@kernel.org> Cc: David Miller <davem@davemloft.net> Acked-by: Benjamin Herrenschmidt <benh@kernel.crashing.org> Acked-by: Will Deacon <will.deacon@arm.com> Signed-off-by: Alexander Duyck <alexander.h.duyck@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-12-12 07:02:06 +08:00
#ifndef dma_rmb
#define dma_rmb() rmb()
#endif
#ifndef dma_wmb
#define dma_wmb() wmb()
#endif
#ifndef read_barrier_depends
#define read_barrier_depends() do { } while (0)
#endif
#ifndef __smp_mb
#define __smp_mb() mb()
#endif
#ifndef __smp_rmb
#define __smp_rmb() rmb()
#endif
#ifndef __smp_wmb
#define __smp_wmb() wmb()
#endif
#ifndef __smp_read_barrier_depends
#define __smp_read_barrier_depends() read_barrier_depends()
#endif
#ifdef CONFIG_SMP
#ifndef smp_mb
#define smp_mb() __smp_mb()
#endif
#ifndef smp_rmb
#define smp_rmb() __smp_rmb()
#endif
#ifndef smp_wmb
#define smp_wmb() __smp_wmb()
#endif
#ifndef smp_read_barrier_depends
#define smp_read_barrier_depends() __smp_read_barrier_depends()
#endif
- Support for HS38 cores based on ARCv2 ISA ARCv2 is the next generation ISA from Synopsys and basis for the HS3{4,6,8} families of processors which retain the traditional ARC mantra of low power and configurability and are now more performant and feature rich. HS38x is a 10 stage pipeline core which supports MMU (with huge pages) and SMP (upto 4 cores) among other features. + www.synopsys.com/dw/ipdir.php?ds=arc-hs38-processor + http://news.synopsys.com/2014-10-14-New-DesignWare-ARC-HS38-Processor-Doubles-Performance-for-Embedded-Linux-Applications + http://www.embedded.com/electronics-news/4435975/Synopsys-ARC-HS38-core-gives-2X-boost-to-Linux-based-apps - Support for ARC SDP (Software Development platform): Main Board + CPU Cards = AXS101: CPU Card with ARC700 in silicon @ 700 MHz = AXS103: CPU Card with HS38x in FPGA - Refactoring of ARCompact port to accomodate new ARCv2 ISA - Miscll updates/cleanups -----BEGIN PGP SIGNATURE----- Version: GnuPG v1 iQIcBAABAgAGBQJVk0g8AAoJEGnX8d3iisJecqsQAI6gvBC4GSNYDrmgGJJK1uLQ uf6ZXQRLBtyxwa6VMvaNFe91i5XV5WvEXDuNBQX4FdYbp7Fs+Jz5VK79xFtbVEdU H6mgKcs9HBwQvrHBxl54XxxXfX7kD1kxrlV7cL4b7bXTEX0XyH5ROUj600/YP+B4 8t+XdYcfgFK0HpeFGXVP+Xmv/e+hBbzCpOjOd2ZFqEwymvSpZDc4KZ2yDvV2+Ybn JNZ421urQOrxR27njvvPvtpeN7uuJKfRYq7IuIR8+Ad72S19EDdw+DZHp2XoUMXA wgydWrrOaX2Dr2CmXHGA1C4nWEG7+Yo9I1WitjJct0tkOQyDR2OIDGmvKGBd1uoS QsihtoKBRvns+2gpXBEOmOHmF6ggpHNN0ppIwCp+AK5kX3fmxBtyUekyYmVpg8oQ xgFIuJgmiAvW7QB7xIO6SFFt18De2ifDRrKWJwVauvfW/PvUIwuUBEcbh0OHAn54 ebUUWu2ZdVNe0XCsZOAQGwYHZRWBk8Bn3bhFpNnOliRiF77e9GsKeGYeIswYFy7I 42Gp35ftEj1pLLFZ1vIsAo72N6ErmHwPOcJkaBYaTbPGPcTEO2aR6b8WOcCjsPxK DUeUV3H2HV+6V4jw/96lnsaRqsaj4TsJxEAFRR3wT1DLoRudCIDubaXTdvvDie77 RgKn4ZdxgmXD97+deBqc =KwNo -----END PGP SIGNATURE----- Merge tag 'arc-4.2-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/vgupta/arc Pull ARC architecture updates from Vineet Gupta: - support for HS38 cores based on ARCv2 ISA ARCv2 is the next generation ISA from Synopsys and basis for the HS3{4,6,8} families of processors which retain the traditional ARC mantra of low power and configurability and are now more performant and feature rich. HS38x is a 10 stage pipeline core which supports MMU (with huge pages) and SMP (upto 4 cores) among other features. + www.synopsys.com/dw/ipdir.php?ds=arc-hs38-processor + http://news.synopsys.com/2014-10-14-New-DesignWare-ARC-HS38-Processor-Doubles-Performance-for-Embedded-Linux-Applications + http://www.embedded.com/electronics-news/4435975/Synopsys-ARC-HS38-core-gives-2X-boost-to-Linux-based-apps - support for ARC SDP (Software Development platform): Main Board + CPU Cards = AXS101: CPU Card with ARC700 in silicon @ 700 MHz = AXS103: CPU Card with HS38x in FPGA - refactoring of ARCompact port to accomodate new ARCv2 ISA - misc updates/cleanups * tag 'arc-4.2-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/vgupta/arc: (72 commits) ARC: Fix build failures for ARCompact in linux-next after ARCv2 support ARCv2: Allow older gcc to cope with new regime of ARCv2/ARCompact support ARCv2: [vdk] dts files and defconfig for HS38 VDK ARCv2: [axs103] Support ARC SDP FPGA platform for HS38x cores ARC: [axs101] Prepare for AXS103 ARCv2: [nsim*hs*] Support simulation platforms for HS38x cores ARCv2: All bits in place, allow ARCv2 builds ARCv2: SLC: Handle explcit flush for DMA ops (w/o IO-coherency) ARCv2: STAR 9000837815 workaround hardware exclusive transactions livelock ARC: Reduce bitops lines of code using macros ARCv2: barriers arch: conditionally define smp_{mb,rmb,wmb} ARC: add smp barriers around atomics per Documentation/atomic_ops.txt ARC: add compiler barrier to LLSC based cmpxchg ARCv2: SMP: intc: IDU 2nd level intc for dynamic IRQ distribution ARCv2: SMP: clocksource: Enable Global Real Time counter ARCv2: SMP: ARConnect debug/robustness ARCv2: SMP: Support ARConnect (MCIP) for Inter-Core-Interrupts et al ARC: make plat_smp_ops weak to allow over-rides ARCv2: clocksource: Introduce 64bit local RTC counter ...
2015-07-02 00:24:26 +08:00
#else /* !CONFIG_SMP */
#ifndef smp_mb
#define smp_mb() barrier()
#endif
#ifndef smp_rmb
#define smp_rmb() barrier()
#endif
#ifndef smp_wmb
#define smp_wmb() barrier()
#endif
#ifndef smp_read_barrier_depends
#define smp_read_barrier_depends() do { } while (0)
#endif
- Support for HS38 cores based on ARCv2 ISA ARCv2 is the next generation ISA from Synopsys and basis for the HS3{4,6,8} families of processors which retain the traditional ARC mantra of low power and configurability and are now more performant and feature rich. HS38x is a 10 stage pipeline core which supports MMU (with huge pages) and SMP (upto 4 cores) among other features. + www.synopsys.com/dw/ipdir.php?ds=arc-hs38-processor + http://news.synopsys.com/2014-10-14-New-DesignWare-ARC-HS38-Processor-Doubles-Performance-for-Embedded-Linux-Applications + http://www.embedded.com/electronics-news/4435975/Synopsys-ARC-HS38-core-gives-2X-boost-to-Linux-based-apps - Support for ARC SDP (Software Development platform): Main Board + CPU Cards = AXS101: CPU Card with ARC700 in silicon @ 700 MHz = AXS103: CPU Card with HS38x in FPGA - Refactoring of ARCompact port to accomodate new ARCv2 ISA - Miscll updates/cleanups -----BEGIN PGP SIGNATURE----- Version: GnuPG v1 iQIcBAABAgAGBQJVk0g8AAoJEGnX8d3iisJecqsQAI6gvBC4GSNYDrmgGJJK1uLQ uf6ZXQRLBtyxwa6VMvaNFe91i5XV5WvEXDuNBQX4FdYbp7Fs+Jz5VK79xFtbVEdU H6mgKcs9HBwQvrHBxl54XxxXfX7kD1kxrlV7cL4b7bXTEX0XyH5ROUj600/YP+B4 8t+XdYcfgFK0HpeFGXVP+Xmv/e+hBbzCpOjOd2ZFqEwymvSpZDc4KZ2yDvV2+Ybn JNZ421urQOrxR27njvvPvtpeN7uuJKfRYq7IuIR8+Ad72S19EDdw+DZHp2XoUMXA wgydWrrOaX2Dr2CmXHGA1C4nWEG7+Yo9I1WitjJct0tkOQyDR2OIDGmvKGBd1uoS QsihtoKBRvns+2gpXBEOmOHmF6ggpHNN0ppIwCp+AK5kX3fmxBtyUekyYmVpg8oQ xgFIuJgmiAvW7QB7xIO6SFFt18De2ifDRrKWJwVauvfW/PvUIwuUBEcbh0OHAn54 ebUUWu2ZdVNe0XCsZOAQGwYHZRWBk8Bn3bhFpNnOliRiF77e9GsKeGYeIswYFy7I 42Gp35ftEj1pLLFZ1vIsAo72N6ErmHwPOcJkaBYaTbPGPcTEO2aR6b8WOcCjsPxK DUeUV3H2HV+6V4jw/96lnsaRqsaj4TsJxEAFRR3wT1DLoRudCIDubaXTdvvDie77 RgKn4ZdxgmXD97+deBqc =KwNo -----END PGP SIGNATURE----- Merge tag 'arc-4.2-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/vgupta/arc Pull ARC architecture updates from Vineet Gupta: - support for HS38 cores based on ARCv2 ISA ARCv2 is the next generation ISA from Synopsys and basis for the HS3{4,6,8} families of processors which retain the traditional ARC mantra of low power and configurability and are now more performant and feature rich. HS38x is a 10 stage pipeline core which supports MMU (with huge pages) and SMP (upto 4 cores) among other features. + www.synopsys.com/dw/ipdir.php?ds=arc-hs38-processor + http://news.synopsys.com/2014-10-14-New-DesignWare-ARC-HS38-Processor-Doubles-Performance-for-Embedded-Linux-Applications + http://www.embedded.com/electronics-news/4435975/Synopsys-ARC-HS38-core-gives-2X-boost-to-Linux-based-apps - support for ARC SDP (Software Development platform): Main Board + CPU Cards = AXS101: CPU Card with ARC700 in silicon @ 700 MHz = AXS103: CPU Card with HS38x in FPGA - refactoring of ARCompact port to accomodate new ARCv2 ISA - misc updates/cleanups * tag 'arc-4.2-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/vgupta/arc: (72 commits) ARC: Fix build failures for ARCompact in linux-next after ARCv2 support ARCv2: Allow older gcc to cope with new regime of ARCv2/ARCompact support ARCv2: [vdk] dts files and defconfig for HS38 VDK ARCv2: [axs103] Support ARC SDP FPGA platform for HS38x cores ARC: [axs101] Prepare for AXS103 ARCv2: [nsim*hs*] Support simulation platforms for HS38x cores ARCv2: All bits in place, allow ARCv2 builds ARCv2: SLC: Handle explcit flush for DMA ops (w/o IO-coherency) ARCv2: STAR 9000837815 workaround hardware exclusive transactions livelock ARC: Reduce bitops lines of code using macros ARCv2: barriers arch: conditionally define smp_{mb,rmb,wmb} ARC: add smp barriers around atomics per Documentation/atomic_ops.txt ARC: add compiler barrier to LLSC based cmpxchg ARCv2: SMP: intc: IDU 2nd level intc for dynamic IRQ distribution ARCv2: SMP: clocksource: Enable Global Real Time counter ARCv2: SMP: ARConnect debug/robustness ARCv2: SMP: Support ARConnect (MCIP) for Inter-Core-Interrupts et al ARC: make plat_smp_ops weak to allow over-rides ARCv2: clocksource: Introduce 64bit local RTC counter ...
2015-07-02 00:24:26 +08:00
#endif /* CONFIG_SMP */
#ifndef __smp_store_mb
#define __smp_store_mb(var, value) do { WRITE_ONCE(var, value); __smp_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
#ifndef __smp_store_release
#define __smp_store_release(p, v) \
do { \
compiletime_assert_atomic_type(*p); \
__smp_mb(); \
WRITE_ONCE(*p, v); \
} while (0)
#endif
#ifndef __smp_load_acquire
#define __smp_load_acquire(p) \
({ \
typeof(*p) ___p1 = READ_ONCE(*p); \
compiletime_assert_atomic_type(*p); \
__smp_mb(); \
___p1; \
})
#endif
#ifdef CONFIG_SMP
#ifndef smp_store_mb
#define smp_store_mb(var, value) __smp_store_mb(var, value)
#endif
#ifndef smp_mb__before_atomic
#define smp_mb__before_atomic() __smp_mb__before_atomic()
#endif
#ifndef smp_mb__after_atomic
#define smp_mb__after_atomic() __smp_mb__after_atomic()
#endif
#ifndef smp_store_release
#define smp_store_release(p, v) __smp_store_release(p, v)
#endif
#ifndef smp_load_acquire
#define smp_load_acquire(p) __smp_load_acquire(p)
#endif
#else /* !CONFIG_SMP */
#ifndef smp_store_mb
#define smp_store_mb(var, value) do { WRITE_ONCE(var, value); barrier(); } while (0)
#endif
#ifndef smp_mb__before_atomic
#define smp_mb__before_atomic() barrier()
#endif
#ifndef smp_mb__after_atomic
#define smp_mb__after_atomic() barrier()
#endif
#ifndef smp_store_release
arch: Introduce smp_load_acquire(), smp_store_release() A number of situations currently require the heavyweight smp_mb(), even though there is no need to order prior stores against later loads. Many architectures have much cheaper ways to handle these situations, but the Linux kernel currently has no portable way to make use of them. This commit therefore supplies smp_load_acquire() and smp_store_release() to remedy this situation. The new smp_load_acquire() primitive orders the specified load against any subsequent reads or writes, while the new smp_store_release() primitive orders the specifed store against any prior reads or writes. These primitives allow array-based circular FIFOs to be implemented without an smp_mb(), and also allow a theoretical hole in rcu_assign_pointer() to be closed at no additional expense on most architectures. In addition, the RCU experience transitioning from explicit smp_read_barrier_depends() and smp_wmb() to rcu_dereference() and rcu_assign_pointer(), respectively resulted in substantial improvements in readability. It therefore seems likely that replacing other explicit barriers with smp_load_acquire() and smp_store_release() will provide similar benefits. It appears that roughly half of the explicit barriers in core kernel code might be so replaced. [Changelog by PaulMck] Reviewed-by: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com> Signed-off-by: Peter Zijlstra <peterz@infradead.org> Acked-by: Will Deacon <will.deacon@arm.com> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca> Cc: Michael Ellerman <michael@ellerman.id.au> Cc: Michael Neuling <mikey@neuling.org> Cc: Russell King <linux@arm.linux.org.uk> Cc: Geert Uytterhoeven <geert@linux-m68k.org> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Victor Kaplansky <VICTORK@il.ibm.com> Cc: Tony Luck <tony.luck@intel.com> Cc: Oleg Nesterov <oleg@redhat.com> Link: http://lkml.kernel.org/r/20131213150640.908486364@infradead.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-06 21:57:36 +08:00
#define smp_store_release(p, v) \
do { \
compiletime_assert_atomic_type(*p); \
barrier(); \
locking, arch: use WRITE_ONCE()/READ_ONCE() in smp_store_release()/smp_load_acquire() Replace ACCESS_ONCE() macro in smp_store_release() and smp_load_acquire() with WRITE_ONCE() and READ_ONCE() on x86, arm, arm64, ia64, metag, mips, powerpc, s390, sparc and asm-generic since ACCESS_ONCE() does not work reliably on non-scalar types. WRITE_ONCE() and READ_ONCE() were introduced in the following commits: 230fa253df63 ("kernel: Provide READ_ONCE and ASSIGN_ONCE") 43239cbe79fc ("kernel: Change ASSIGN_ONCE(val, x) to WRITE_ONCE(x, val)") Signed-off-by: Andrey Konovalov <andreyknvl@google.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Acked-by: Davidlohr Bueso <dbueso@suse.de> Acked-by: Michael Ellerman <mpe@ellerman.id.au> (powerpc) Acked-by: Ralf Baechle <ralf@linux-mips.org> Cc: Alexander Duyck <alexander.h.duyck@redhat.com> Cc: Andre Przywara <andre.przywara@arm.com> Cc: Arnd Bergmann <arnd@arndb.de> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Borislav Petkov <bp@suse.de> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Christian Borntraeger <borntraeger@de.ibm.com> Cc: David S. Miller <davem@davemloft.net> Cc: Davidlohr Bueso <dave@stgolabs.net> Cc: Dmitry Vyukov <dvyukov@google.com> Cc: Fenghua Yu <fenghua.yu@intel.com> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: James Hogan <james.hogan@imgtec.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Russell King <linux@arm.linux.org.uk> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Tony Luck <tony.luck@intel.com> Cc: Will Deacon <will.deacon@arm.com> Cc: linux-arch@vger.kernel.org Link: http://lkml.kernel.org/r/1438528264-714-1-git-send-email-andreyknvl@google.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-08-02 23:11:04 +08:00
WRITE_ONCE(*p, v); \
arch: Introduce smp_load_acquire(), smp_store_release() A number of situations currently require the heavyweight smp_mb(), even though there is no need to order prior stores against later loads. Many architectures have much cheaper ways to handle these situations, but the Linux kernel currently has no portable way to make use of them. This commit therefore supplies smp_load_acquire() and smp_store_release() to remedy this situation. The new smp_load_acquire() primitive orders the specified load against any subsequent reads or writes, while the new smp_store_release() primitive orders the specifed store against any prior reads or writes. These primitives allow array-based circular FIFOs to be implemented without an smp_mb(), and also allow a theoretical hole in rcu_assign_pointer() to be closed at no additional expense on most architectures. In addition, the RCU experience transitioning from explicit smp_read_barrier_depends() and smp_wmb() to rcu_dereference() and rcu_assign_pointer(), respectively resulted in substantial improvements in readability. It therefore seems likely that replacing other explicit barriers with smp_load_acquire() and smp_store_release() will provide similar benefits. It appears that roughly half of the explicit barriers in core kernel code might be so replaced. [Changelog by PaulMck] Reviewed-by: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com> Signed-off-by: Peter Zijlstra <peterz@infradead.org> Acked-by: Will Deacon <will.deacon@arm.com> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca> Cc: Michael Ellerman <michael@ellerman.id.au> Cc: Michael Neuling <mikey@neuling.org> Cc: Russell King <linux@arm.linux.org.uk> Cc: Geert Uytterhoeven <geert@linux-m68k.org> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Victor Kaplansky <VICTORK@il.ibm.com> Cc: Tony Luck <tony.luck@intel.com> Cc: Oleg Nesterov <oleg@redhat.com> Link: http://lkml.kernel.org/r/20131213150640.908486364@infradead.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-06 21:57:36 +08:00
} while (0)
#endif
arch: Introduce smp_load_acquire(), smp_store_release() A number of situations currently require the heavyweight smp_mb(), even though there is no need to order prior stores against later loads. Many architectures have much cheaper ways to handle these situations, but the Linux kernel currently has no portable way to make use of them. This commit therefore supplies smp_load_acquire() and smp_store_release() to remedy this situation. The new smp_load_acquire() primitive orders the specified load against any subsequent reads or writes, while the new smp_store_release() primitive orders the specifed store against any prior reads or writes. These primitives allow array-based circular FIFOs to be implemented without an smp_mb(), and also allow a theoretical hole in rcu_assign_pointer() to be closed at no additional expense on most architectures. In addition, the RCU experience transitioning from explicit smp_read_barrier_depends() and smp_wmb() to rcu_dereference() and rcu_assign_pointer(), respectively resulted in substantial improvements in readability. It therefore seems likely that replacing other explicit barriers with smp_load_acquire() and smp_store_release() will provide similar benefits. It appears that roughly half of the explicit barriers in core kernel code might be so replaced. [Changelog by PaulMck] Reviewed-by: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com> Signed-off-by: Peter Zijlstra <peterz@infradead.org> Acked-by: Will Deacon <will.deacon@arm.com> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca> Cc: Michael Ellerman <michael@ellerman.id.au> Cc: Michael Neuling <mikey@neuling.org> Cc: Russell King <linux@arm.linux.org.uk> Cc: Geert Uytterhoeven <geert@linux-m68k.org> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Victor Kaplansky <VICTORK@il.ibm.com> Cc: Tony Luck <tony.luck@intel.com> Cc: Oleg Nesterov <oleg@redhat.com> Link: http://lkml.kernel.org/r/20131213150640.908486364@infradead.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-06 21:57:36 +08:00
#ifndef smp_load_acquire
arch: Introduce smp_load_acquire(), smp_store_release() A number of situations currently require the heavyweight smp_mb(), even though there is no need to order prior stores against later loads. Many architectures have much cheaper ways to handle these situations, but the Linux kernel currently has no portable way to make use of them. This commit therefore supplies smp_load_acquire() and smp_store_release() to remedy this situation. The new smp_load_acquire() primitive orders the specified load against any subsequent reads or writes, while the new smp_store_release() primitive orders the specifed store against any prior reads or writes. These primitives allow array-based circular FIFOs to be implemented without an smp_mb(), and also allow a theoretical hole in rcu_assign_pointer() to be closed at no additional expense on most architectures. In addition, the RCU experience transitioning from explicit smp_read_barrier_depends() and smp_wmb() to rcu_dereference() and rcu_assign_pointer(), respectively resulted in substantial improvements in readability. It therefore seems likely that replacing other explicit barriers with smp_load_acquire() and smp_store_release() will provide similar benefits. It appears that roughly half of the explicit barriers in core kernel code might be so replaced. [Changelog by PaulMck] Reviewed-by: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com> Signed-off-by: Peter Zijlstra <peterz@infradead.org> Acked-by: Will Deacon <will.deacon@arm.com> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca> Cc: Michael Ellerman <michael@ellerman.id.au> Cc: Michael Neuling <mikey@neuling.org> Cc: Russell King <linux@arm.linux.org.uk> Cc: Geert Uytterhoeven <geert@linux-m68k.org> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Victor Kaplansky <VICTORK@il.ibm.com> Cc: Tony Luck <tony.luck@intel.com> Cc: Oleg Nesterov <oleg@redhat.com> Link: http://lkml.kernel.org/r/20131213150640.908486364@infradead.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-06 21:57:36 +08:00
#define smp_load_acquire(p) \
({ \
locking, arch: use WRITE_ONCE()/READ_ONCE() in smp_store_release()/smp_load_acquire() Replace ACCESS_ONCE() macro in smp_store_release() and smp_load_acquire() with WRITE_ONCE() and READ_ONCE() on x86, arm, arm64, ia64, metag, mips, powerpc, s390, sparc and asm-generic since ACCESS_ONCE() does not work reliably on non-scalar types. WRITE_ONCE() and READ_ONCE() were introduced in the following commits: 230fa253df63 ("kernel: Provide READ_ONCE and ASSIGN_ONCE") 43239cbe79fc ("kernel: Change ASSIGN_ONCE(val, x) to WRITE_ONCE(x, val)") Signed-off-by: Andrey Konovalov <andreyknvl@google.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Acked-by: Davidlohr Bueso <dbueso@suse.de> Acked-by: Michael Ellerman <mpe@ellerman.id.au> (powerpc) Acked-by: Ralf Baechle <ralf@linux-mips.org> Cc: Alexander Duyck <alexander.h.duyck@redhat.com> Cc: Andre Przywara <andre.przywara@arm.com> Cc: Arnd Bergmann <arnd@arndb.de> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Borislav Petkov <bp@suse.de> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Christian Borntraeger <borntraeger@de.ibm.com> Cc: David S. Miller <davem@davemloft.net> Cc: Davidlohr Bueso <dave@stgolabs.net> Cc: Dmitry Vyukov <dvyukov@google.com> Cc: Fenghua Yu <fenghua.yu@intel.com> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: James Hogan <james.hogan@imgtec.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Russell King <linux@arm.linux.org.uk> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Tony Luck <tony.luck@intel.com> Cc: Will Deacon <will.deacon@arm.com> Cc: linux-arch@vger.kernel.org Link: http://lkml.kernel.org/r/1438528264-714-1-git-send-email-andreyknvl@google.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2015-08-02 23:11:04 +08:00
typeof(*p) ___p1 = READ_ONCE(*p); \
arch: Introduce smp_load_acquire(), smp_store_release() A number of situations currently require the heavyweight smp_mb(), even though there is no need to order prior stores against later loads. Many architectures have much cheaper ways to handle these situations, but the Linux kernel currently has no portable way to make use of them. This commit therefore supplies smp_load_acquire() and smp_store_release() to remedy this situation. The new smp_load_acquire() primitive orders the specified load against any subsequent reads or writes, while the new smp_store_release() primitive orders the specifed store against any prior reads or writes. These primitives allow array-based circular FIFOs to be implemented without an smp_mb(), and also allow a theoretical hole in rcu_assign_pointer() to be closed at no additional expense on most architectures. In addition, the RCU experience transitioning from explicit smp_read_barrier_depends() and smp_wmb() to rcu_dereference() and rcu_assign_pointer(), respectively resulted in substantial improvements in readability. It therefore seems likely that replacing other explicit barriers with smp_load_acquire() and smp_store_release() will provide similar benefits. It appears that roughly half of the explicit barriers in core kernel code might be so replaced. [Changelog by PaulMck] Reviewed-by: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com> Signed-off-by: Peter Zijlstra <peterz@infradead.org> Acked-by: Will Deacon <will.deacon@arm.com> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca> Cc: Michael Ellerman <michael@ellerman.id.au> Cc: Michael Neuling <mikey@neuling.org> Cc: Russell King <linux@arm.linux.org.uk> Cc: Geert Uytterhoeven <geert@linux-m68k.org> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Victor Kaplansky <VICTORK@il.ibm.com> Cc: Tony Luck <tony.luck@intel.com> Cc: Oleg Nesterov <oleg@redhat.com> Link: http://lkml.kernel.org/r/20131213150640.908486364@infradead.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-06 21:57:36 +08:00
compiletime_assert_atomic_type(*p); \
barrier(); \
arch: Introduce smp_load_acquire(), smp_store_release() A number of situations currently require the heavyweight smp_mb(), even though there is no need to order prior stores against later loads. Many architectures have much cheaper ways to handle these situations, but the Linux kernel currently has no portable way to make use of them. This commit therefore supplies smp_load_acquire() and smp_store_release() to remedy this situation. The new smp_load_acquire() primitive orders the specified load against any subsequent reads or writes, while the new smp_store_release() primitive orders the specifed store against any prior reads or writes. These primitives allow array-based circular FIFOs to be implemented without an smp_mb(), and also allow a theoretical hole in rcu_assign_pointer() to be closed at no additional expense on most architectures. In addition, the RCU experience transitioning from explicit smp_read_barrier_depends() and smp_wmb() to rcu_dereference() and rcu_assign_pointer(), respectively resulted in substantial improvements in readability. It therefore seems likely that replacing other explicit barriers with smp_load_acquire() and smp_store_release() will provide similar benefits. It appears that roughly half of the explicit barriers in core kernel code might be so replaced. [Changelog by PaulMck] Reviewed-by: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com> Signed-off-by: Peter Zijlstra <peterz@infradead.org> Acked-by: Will Deacon <will.deacon@arm.com> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca> Cc: Michael Ellerman <michael@ellerman.id.au> Cc: Michael Neuling <mikey@neuling.org> Cc: Russell King <linux@arm.linux.org.uk> Cc: Geert Uytterhoeven <geert@linux-m68k.org> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Victor Kaplansky <VICTORK@il.ibm.com> Cc: Tony Luck <tony.luck@intel.com> Cc: Oleg Nesterov <oleg@redhat.com> Link: http://lkml.kernel.org/r/20131213150640.908486364@infradead.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-06 21:57:36 +08:00
___p1; \
})
#endif
arch: Introduce smp_load_acquire(), smp_store_release() A number of situations currently require the heavyweight smp_mb(), even though there is no need to order prior stores against later loads. Many architectures have much cheaper ways to handle these situations, but the Linux kernel currently has no portable way to make use of them. This commit therefore supplies smp_load_acquire() and smp_store_release() to remedy this situation. The new smp_load_acquire() primitive orders the specified load against any subsequent reads or writes, while the new smp_store_release() primitive orders the specifed store against any prior reads or writes. These primitives allow array-based circular FIFOs to be implemented without an smp_mb(), and also allow a theoretical hole in rcu_assign_pointer() to be closed at no additional expense on most architectures. In addition, the RCU experience transitioning from explicit smp_read_barrier_depends() and smp_wmb() to rcu_dereference() and rcu_assign_pointer(), respectively resulted in substantial improvements in readability. It therefore seems likely that replacing other explicit barriers with smp_load_acquire() and smp_store_release() will provide similar benefits. It appears that roughly half of the explicit barriers in core kernel code might be so replaced. [Changelog by PaulMck] Reviewed-by: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com> Signed-off-by: Peter Zijlstra <peterz@infradead.org> Acked-by: Will Deacon <will.deacon@arm.com> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca> Cc: Michael Ellerman <michael@ellerman.id.au> Cc: Michael Neuling <mikey@neuling.org> Cc: Russell King <linux@arm.linux.org.uk> Cc: Geert Uytterhoeven <geert@linux-m68k.org> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Victor Kaplansky <VICTORK@il.ibm.com> Cc: Tony Luck <tony.luck@intel.com> Cc: Oleg Nesterov <oleg@redhat.com> Link: http://lkml.kernel.org/r/20131213150640.908486364@infradead.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-11-06 21:57:36 +08:00
locking/spinlock, arch: Update and fix spin_unlock_wait() implementations This patch updates/fixes all spin_unlock_wait() implementations. The update is in semantics; where it previously was only a control dependency, we now upgrade to a full load-acquire to match the store-release from the spin_unlock() we waited on. This ensures that when spin_unlock_wait() returns, we're guaranteed to observe the full critical section we waited on. This fixes a number of spin_unlock_wait() users that (not unreasonably) rely on this. I also fixed a number of ticket lock versions to only wait on the current lock holder, instead of for a full unlock, as this is sufficient. Furthermore; again for ticket locks; I added an smp_rmb() in between the initial ticket load and the spin loop testing the current value because I could not convince myself the address dependency is sufficient, esp. if the loads are of different sizes. I'm more than happy to remove this smp_rmb() again if people are certain the address dependency does indeed work as expected. Note: PPC32 will be fixed independently Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: chris@zankel.net Cc: cmetcalf@mellanox.com Cc: davem@davemloft.net Cc: dhowells@redhat.com Cc: james.hogan@imgtec.com Cc: jejb@parisc-linux.org Cc: linux@armlinux.org.uk Cc: mpe@ellerman.id.au Cc: ralf@linux-mips.org Cc: realmz6@gmail.com Cc: rkuo@codeaurora.org Cc: rth@twiddle.net Cc: schwidefsky@de.ibm.com Cc: tony.luck@intel.com Cc: vgupta@synopsys.com Cc: ysato@users.sourceforge.jp Cc: linux-kernel@vger.kernel.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2016-05-26 16:35:03 +08:00
#endif /* CONFIG_SMP */
/* Barriers for virtual machine guests when talking to an SMP host */
#define virt_mb() __smp_mb()
#define virt_rmb() __smp_rmb()
#define virt_wmb() __smp_wmb()
#define virt_read_barrier_depends() __smp_read_barrier_depends()
#define virt_store_mb(var, value) __smp_store_mb(var, value)
#define virt_mb__before_atomic() __smp_mb__before_atomic()
#define virt_mb__after_atomic() __smp_mb__after_atomic()
#define virt_store_release(p, v) __smp_store_release(p, v)
#define virt_load_acquire(p) __smp_load_acquire(p)
/**
* smp_acquire__after_ctrl_dep() - Provide ACQUIRE ordering after a control dependency
*
* A control dependency provides a LOAD->STORE order, the additional RMB
* provides LOAD->LOAD order, together they provide LOAD->{LOAD,STORE} order,
* aka. (load)-ACQUIRE.
*
* Architectures that do not do load speculation can have this be barrier().
*/
#ifndef smp_acquire__after_ctrl_dep
#define smp_acquire__after_ctrl_dep() smp_rmb()
#endif
/**
* smp_cond_load_relaxed() - (Spin) wait for cond with no ordering guarantees
* @ptr: pointer to the variable to wait on
* @cond: boolean expression to wait for
*
* Equivalent to using READ_ONCE() on the condition variable.
*
* Due to C lacking lambda expressions we load the value of *ptr into a
* pre-named variable @VAL to be used in @cond.
*/
#ifndef smp_cond_load_relaxed
#define smp_cond_load_relaxed(ptr, cond_expr) ({ \
typeof(ptr) __PTR = (ptr); \
typeof(*ptr) VAL; \
for (;;) { \
VAL = READ_ONCE(*__PTR); \
if (cond_expr) \
break; \
cpu_relax(); \
} \
VAL; \
})
#endif
/**
* smp_cond_load_acquire() - (Spin) wait for cond with ACQUIRE ordering
* @ptr: pointer to the variable to wait on
* @cond: boolean expression to wait for
*
* Equivalent to using smp_load_acquire() on the condition variable but employs
* the control dependency of the wait to reduce the barrier on many platforms.
*/
#ifndef smp_cond_load_acquire
#define smp_cond_load_acquire(ptr, cond_expr) ({ \
typeof(*ptr) _val; \
_val = smp_cond_load_relaxed(ptr, cond_expr); \
smp_acquire__after_ctrl_dep(); \
_val; \
})
#endif
#endif /* !__ASSEMBLY__ */
#endif /* __ASM_GENERIC_BARRIER_H */