Merge branch 'core-locking-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull core locking updates from Ingo Molnar:
"The biggest change is the MCS spinlock generalization changes from Tim
Chen, Peter Zijlstra, Jason Low et al. There's also lockdep
fixes/enhancements from Oleg Nesterov, in particular a false negative
fix related to lockdep_set_novalidate_class() usage"
* 'core-locking-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (22 commits)
locking/mutex: Fix debug checks
locking/mutexes: Add extra reschedule point
locking/mutexes: Introduce cancelable MCS lock for adaptive spinning
locking/mutexes: Unlock the mutex without the wait_lock
locking/mutexes: Modify the way optimistic spinners are queued
locking/mutexes: Return false if task need_resched() in mutex_can_spin_on_owner()
locking: Move mcs_spinlock.h into kernel/locking/
m68k: Skip futex_atomic_cmpxchg_inatomic() test
futex: Allow architectures to skip futex_atomic_cmpxchg_inatomic() test
Revert "sched/wait: Suppress Sparse 'variable shadowing' warning"
lockdep: Change lockdep_set_novalidate_class() to use _and_name
lockdep: Change mark_held_locks() to check hlock->check instead of lockdep_no_validate
lockdep: Don't create the wrong dependency on hlock->check == 0
lockdep: Make held_lock->check and "int check" argument bool
locking/mcs: Allow architecture specific asm files to be used for contended case
locking/mcs: Order the header files in Kbuild of each architecture in alphabetical order
sched/wait: Suppress Sparse 'variable shadowing' warning
hung_task/Documentation: Fix hung_task_warnings description
locking/mcs: Allow architectures to hook in to contended paths
locking/mcs: Micro-optimize the MCS code, add extra comments
...
diff --git a/Documentation/sysctl/kernel.txt b/Documentation/sysctl/kernel.txt
index e55124e..e1d28fb 100644
--- a/Documentation/sysctl/kernel.txt
+++ b/Documentation/sysctl/kernel.txt
@@ -320,10 +320,11 @@
==============================================================
-hung_task_warning:
+hung_task_warnings:
The maximum number of warnings to report. During a check interval
-When this value is reached, no more the warnings will be reported.
+if a hung task is detected, this value is decreased by 1.
+When this value reaches 0, no more warnings will be reported.
This file shows up if CONFIG_DETECT_HUNG_TASK is enabled.
-1: report an infinite number of warnings.
diff --git a/arch/alpha/include/asm/Kbuild b/arch/alpha/include/asm/Kbuild
index a73a8e2..7736f42 100644
--- a/arch/alpha/include/asm/Kbuild
+++ b/arch/alpha/include/asm/Kbuild
@@ -1,7 +1,8 @@
-generic-y += clkdev.h
+generic-y += clkdev.h
generic-y += exec.h
-generic-y += trace_clock.h
-generic-y += preempt.h
generic-y += hash.h
+generic-y += mcs_spinlock.h
+generic-y += preempt.h
+generic-y += trace_clock.h
diff --git a/arch/arc/include/asm/Kbuild b/arch/arc/include/asm/Kbuild
index 0d33629..e76fd79 100644
--- a/arch/arc/include/asm/Kbuild
+++ b/arch/arc/include/asm/Kbuild
@@ -1,15 +1,15 @@
generic-y += auxvec.h
generic-y += barrier.h
-generic-y += bugs.h
generic-y += bitsperlong.h
+generic-y += bugs.h
generic-y += clkdev.h
generic-y += cputime.h
generic-y += device.h
generic-y += div64.h
generic-y += emergency-restart.h
generic-y += errno.h
-generic-y += fcntl.h
generic-y += fb.h
+generic-y += fcntl.h
generic-y += ftrace.h
generic-y += hardirq.h
generic-y += hash.h
@@ -22,6 +22,7 @@
generic-y += kvm_para.h
generic-y += local.h
generic-y += local64.h
+generic-y += mcs_spinlock.h
generic-y += mman.h
generic-y += msgbuf.h
generic-y += param.h
@@ -30,6 +31,7 @@
generic-y += percpu.h
generic-y += poll.h
generic-y += posix_types.h
+generic-y += preempt.h
generic-y += resource.h
generic-y += scatterlist.h
generic-y += sembuf.h
@@ -48,4 +50,3 @@
generic-y += user.h
generic-y += vga.h
generic-y += xor.h
-generic-y += preempt.h
diff --git a/arch/arm/include/asm/Kbuild b/arch/arm/include/asm/Kbuild
index 3278afe..23e728e 100644
--- a/arch/arm/include/asm/Kbuild
+++ b/arch/arm/include/asm/Kbuild
@@ -7,16 +7,19 @@
generic-y += emergency-restart.h
generic-y += errno.h
generic-y += exec.h
+generic-y += hash.h
generic-y += ioctl.h
generic-y += ipcbuf.h
generic-y += irq_regs.h
generic-y += kdebug.h
generic-y += local.h
generic-y += local64.h
+generic-y += mcs_spinlock.h
generic-y += msgbuf.h
generic-y += param.h
generic-y += parport.h
generic-y += poll.h
+generic-y += preempt.h
generic-y += resource.h
generic-y += sections.h
generic-y += segment.h
@@ -33,5 +36,3 @@
generic-y += timex.h
generic-y += trace_clock.h
generic-y += unaligned.h
-generic-y += preempt.h
-generic-y += hash.h
diff --git a/arch/arm64/include/asm/Kbuild b/arch/arm64/include/asm/Kbuild
index 71c53ec..3bdfdda 100644
--- a/arch/arm64/include/asm/Kbuild
+++ b/arch/arm64/include/asm/Kbuild
@@ -12,6 +12,7 @@
generic-y += emergency-restart.h
generic-y += errno.h
generic-y += ftrace.h
+generic-y += hash.h
generic-y += hw_irq.h
generic-y += ioctl.h
generic-y += ioctls.h
@@ -22,12 +23,14 @@
generic-y += kvm_para.h
generic-y += local.h
generic-y += local64.h
+generic-y += mcs_spinlock.h
generic-y += mman.h
generic-y += msgbuf.h
generic-y += mutex.h
generic-y += pci.h
generic-y += poll.h
generic-y += posix_types.h
+generic-y += preempt.h
generic-y += resource.h
generic-y += scatterlist.h
generic-y += sections.h
@@ -38,8 +41,8 @@
generic-y += sizes.h
generic-y += socket.h
generic-y += sockios.h
-generic-y += switch_to.h
generic-y += swab.h
+generic-y += switch_to.h
generic-y += termbits.h
generic-y += termios.h
generic-y += topology.h
@@ -49,5 +52,3 @@
generic-y += user.h
generic-y += vga.h
generic-y += xor.h
-generic-y += preempt.h
-generic-y += hash.h
diff --git a/arch/avr32/include/asm/Kbuild b/arch/avr32/include/asm/Kbuild
index c7c64a6..00a0f3c 100644
--- a/arch/avr32/include/asm/Kbuild
+++ b/arch/avr32/include/asm/Kbuild
@@ -1,22 +1,23 @@
-generic-y += clkdev.h
-generic-y += cputime.h
-generic-y += delay.h
-generic-y += device.h
-generic-y += div64.h
-generic-y += emergency-restart.h
-generic-y += exec.h
-generic-y += futex.h
-generic-y += preempt.h
-generic-y += irq_regs.h
-generic-y += param.h
-generic-y += local.h
-generic-y += local64.h
-generic-y += percpu.h
-generic-y += scatterlist.h
-generic-y += sections.h
-generic-y += topology.h
-generic-y += trace_clock.h
+generic-y += clkdev.h
+generic-y += cputime.h
+generic-y += delay.h
+generic-y += device.h
+generic-y += div64.h
+generic-y += emergency-restart.h
+generic-y += exec.h
+generic-y += futex.h
+generic-y += hash.h
+generic-y += irq_regs.h
+generic-y += local.h
+generic-y += local64.h
+generic-y += mcs_spinlock.h
+generic-y += param.h
+generic-y += percpu.h
+generic-y += preempt.h
+generic-y += scatterlist.h
+generic-y += sections.h
+generic-y += topology.h
+generic-y += trace_clock.h
generic-y += vga.h
-generic-y += xor.h
-generic-y += hash.h
+generic-y += xor.h
diff --git a/arch/blackfin/include/asm/Kbuild b/arch/blackfin/include/asm/Kbuild
index 359d36f..0d93b9a 100644
--- a/arch/blackfin/include/asm/Kbuild
+++ b/arch/blackfin/include/asm/Kbuild
@@ -10,6 +10,7 @@
generic-y += errno.h
generic-y += fb.h
generic-y += futex.h
+generic-y += hash.h
generic-y += hw_irq.h
generic-y += ioctl.h
generic-y += ipcbuf.h
@@ -17,14 +18,16 @@
generic-y += kdebug.h
generic-y += kmap_types.h
generic-y += kvm_para.h
-generic-y += local64.h
generic-y += local.h
+generic-y += local64.h
+generic-y += mcs_spinlock.h
generic-y += mman.h
generic-y += msgbuf.h
generic-y += mutex.h
generic-y += param.h
generic-y += percpu.h
generic-y += pgalloc.h
+generic-y += preempt.h
generic-y += resource.h
generic-y += scatterlist.h
generic-y += sembuf.h
@@ -44,5 +47,3 @@
generic-y += unaligned.h
generic-y += user.h
generic-y += xor.h
-generic-y += preempt.h
-generic-y += hash.h
diff --git a/arch/c6x/include/asm/Kbuild b/arch/c6x/include/asm/Kbuild
index d73bb85..8dbdce8 100644
--- a/arch/c6x/include/asm/Kbuild
+++ b/arch/c6x/include/asm/Kbuild
@@ -15,6 +15,7 @@
generic-y += fb.h
generic-y += fcntl.h
generic-y += futex.h
+generic-y += hash.h
generic-y += hw_irq.h
generic-y += io.h
generic-y += ioctl.h
@@ -24,6 +25,7 @@
generic-y += kdebug.h
generic-y += kmap_types.h
generic-y += local.h
+generic-y += mcs_spinlock.h
generic-y += mman.h
generic-y += mmu.h
generic-y += mmu_context.h
@@ -34,6 +36,7 @@
generic-y += pgalloc.h
generic-y += poll.h
generic-y += posix_types.h
+generic-y += preempt.h
generic-y += resource.h
generic-y += scatterlist.h
generic-y += segment.h
@@ -56,5 +59,3 @@
generic-y += user.h
generic-y += vga.h
generic-y += xor.h
-generic-y += preempt.h
-generic-y += hash.h
diff --git a/arch/cris/include/asm/Kbuild b/arch/cris/include/asm/Kbuild
index f3fd876..056027f 100644
--- a/arch/cris/include/asm/Kbuild
+++ b/arch/cris/include/asm/Kbuild
@@ -9,8 +9,9 @@
generic-y += hash.h
generic-y += kvm_para.h
generic-y += linkage.h
+generic-y += mcs_spinlock.h
generic-y += module.h
+generic-y += preempt.h
generic-y += trace_clock.h
generic-y += vga.h
generic-y += xor.h
-generic-y += preempt.h
diff --git a/arch/frv/include/asm/Kbuild b/arch/frv/include/asm/Kbuild
index bc42f14..babb933 100644
--- a/arch/frv/include/asm/Kbuild
+++ b/arch/frv/include/asm/Kbuild
@@ -1,6 +1,7 @@
generic-y += clkdev.h
generic-y += exec.h
-generic-y += trace_clock.h
-generic-y += preempt.h
generic-y += hash.h
+generic-y += mcs_spinlock.h
+generic-y += preempt.h
+generic-y += trace_clock.h
diff --git a/arch/hexagon/include/asm/Kbuild b/arch/hexagon/include/asm/Kbuild
index 38ca45d..eadcc11 100644
--- a/arch/hexagon/include/asm/Kbuild
+++ b/arch/hexagon/include/asm/Kbuild
@@ -25,14 +25,16 @@
generic-y += irq_regs.h
generic-y += kdebug.h
generic-y += kmap_types.h
-generic-y += local64.h
generic-y += local.h
+generic-y += local64.h
+generic-y += mcs_spinlock.h
generic-y += mman.h
generic-y += msgbuf.h
generic-y += pci.h
generic-y += percpu.h
generic-y += poll.h
generic-y += posix_types.h
+generic-y += preempt.h
generic-y += resource.h
generic-y += rwsem.h
generic-y += scatterlist.h
@@ -45,8 +47,8 @@
generic-y += sizes.h
generic-y += socket.h
generic-y += sockios.h
-generic-y += statfs.h
generic-y += stat.h
+generic-y += statfs.h
generic-y += termbits.h
generic-y += termios.h
generic-y += topology.h
@@ -55,4 +57,3 @@
generic-y += ucontext.h
generic-y += unaligned.h
generic-y += xor.h
-generic-y += preempt.h
diff --git a/arch/ia64/include/asm/Kbuild b/arch/ia64/include/asm/Kbuild
index 283a831..0da4aa2 100644
--- a/arch/ia64/include/asm/Kbuild
+++ b/arch/ia64/include/asm/Kbuild
@@ -1,8 +1,9 @@
generic-y += clkdev.h
generic-y += exec.h
-generic-y += kvm_para.h
-generic-y += trace_clock.h
-generic-y += preempt.h
-generic-y += vtime.h
generic-y += hash.h
+generic-y += kvm_para.h
+generic-y += mcs_spinlock.h
+generic-y += preempt.h
+generic-y += trace_clock.h
+generic-y += vtime.h
diff --git a/arch/m32r/include/asm/Kbuild b/arch/m32r/include/asm/Kbuild
index 932435a..5825a35 100644
--- a/arch/m32r/include/asm/Kbuild
+++ b/arch/m32r/include/asm/Kbuild
@@ -1,7 +1,8 @@
generic-y += clkdev.h
generic-y += exec.h
-generic-y += module.h
-generic-y += trace_clock.h
-generic-y += preempt.h
generic-y += hash.h
+generic-y += mcs_spinlock.h
+generic-y += module.h
+generic-y += preempt.h
+generic-y += trace_clock.h
diff --git a/arch/m68k/Kconfig b/arch/m68k/Kconfig
index dbdd223..b2e3229 100644
--- a/arch/m68k/Kconfig
+++ b/arch/m68k/Kconfig
@@ -17,6 +17,7 @@
select FPU if MMU
select ARCH_WANT_IPC_PARSE_VERSION
select ARCH_USES_GETTIMEOFFSET if MMU && !COLDFIRE
+ select HAVE_FUTEX_CMPXCHG if MMU && FUTEX
select HAVE_MOD_ARCH_SPECIFIC
select MODULES_USE_ELF_REL
select MODULES_USE_ELF_RELA
diff --git a/arch/m68k/include/asm/Kbuild b/arch/m68k/include/asm/Kbuild
index 6fb9e81..c67c94a 100644
--- a/arch/m68k/include/asm/Kbuild
+++ b/arch/m68k/include/asm/Kbuild
@@ -14,8 +14,9 @@
generic-y += kdebug.h
generic-y += kmap_types.h
generic-y += kvm_para.h
-generic-y += local64.h
generic-y += local.h
+generic-y += local64.h
+generic-y += mcs_spinlock.h
generic-y += mman.h
generic-y += mutex.h
generic-y += percpu.h
diff --git a/arch/metag/include/asm/Kbuild b/arch/metag/include/asm/Kbuild
index b716d80..c29ead8 100644
--- a/arch/metag/include/asm/Kbuild
+++ b/arch/metag/include/asm/Kbuild
@@ -13,6 +13,7 @@
generic-y += fcntl.h
generic-y += futex.h
generic-y += hardirq.h
+generic-y += hash.h
generic-y += hw_irq.h
generic-y += ioctl.h
generic-y += ioctls.h
@@ -23,6 +24,7 @@
generic-y += kvm_para.h
generic-y += local.h
generic-y += local64.h
+generic-y += mcs_spinlock.h
generic-y += msgbuf.h
generic-y += mutex.h
generic-y += param.h
@@ -30,6 +32,7 @@
generic-y += percpu.h
generic-y += poll.h
generic-y += posix_types.h
+generic-y += preempt.h
generic-y += scatterlist.h
generic-y += sections.h
generic-y += sembuf.h
@@ -52,5 +55,3 @@
generic-y += user.h
generic-y += vga.h
generic-y += xor.h
-generic-y += preempt.h
-generic-y += hash.h
diff --git a/arch/microblaze/include/asm/Kbuild b/arch/microblaze/include/asm/Kbuild
index 2b98bc7..1f590ab 100644
--- a/arch/microblaze/include/asm/Kbuild
+++ b/arch/microblaze/include/asm/Kbuild
@@ -3,6 +3,7 @@
generic-y += clkdev.h
generic-y += exec.h
generic-y += hash.h
-generic-y += trace_clock.h
-generic-y += syscalls.h
+generic-y += mcs_spinlock.h
generic-y += preempt.h
+generic-y += syscalls.h
+generic-y += trace_clock.h
diff --git a/arch/mips/include/asm/Kbuild b/arch/mips/include/asm/Kbuild
index 2d7f650..0543918 100644
--- a/arch/mips/include/asm/Kbuild
+++ b/arch/mips/include/asm/Kbuild
@@ -2,16 +2,17 @@
generic-y += cputime.h
generic-y += current.h
generic-y += emergency-restart.h
+generic-y += hash.h
generic-y += local64.h
+generic-y += mcs_spinlock.h
generic-y += mutex.h
generic-y += parport.h
generic-y += percpu.h
+generic-y += preempt.h
generic-y += scatterlist.h
generic-y += sections.h
generic-y += segment.h
generic-y += serial.h
generic-y += trace_clock.h
-generic-y += preempt.h
generic-y += ucontext.h
generic-y += xor.h
-generic-y += hash.h
diff --git a/arch/mn10300/include/asm/Kbuild b/arch/mn10300/include/asm/Kbuild
index 992e989..cbc6b9b 100644
--- a/arch/mn10300/include/asm/Kbuild
+++ b/arch/mn10300/include/asm/Kbuild
@@ -3,5 +3,6 @@
generic-y += clkdev.h
generic-y += exec.h
generic-y += hash.h
-generic-y += trace_clock.h
+generic-y += mcs_spinlock.h
generic-y += preempt.h
+generic-y += trace_clock.h
diff --git a/arch/openrisc/include/asm/Kbuild b/arch/openrisc/include/asm/Kbuild
index 2e40f1c..480af0d 100644
--- a/arch/openrisc/include/asm/Kbuild
+++ b/arch/openrisc/include/asm/Kbuild
@@ -10,8 +10,8 @@
generic-y += cacheflush.h
generic-y += checksum.h
generic-y += clkdev.h
-generic-y += cmpxchg.h
generic-y += cmpxchg-local.h
+generic-y += cmpxchg.h
generic-y += cputime.h
generic-y += current.h
generic-y += device.h
@@ -25,6 +25,7 @@
generic-y += ftrace.h
generic-y += futex.h
generic-y += hardirq.h
+generic-y += hash.h
generic-y += hw_irq.h
generic-y += ioctl.h
generic-y += ioctls.h
@@ -34,6 +35,7 @@
generic-y += kmap_types.h
generic-y += kvm_para.h
generic-y += local.h
+generic-y += mcs_spinlock.h
generic-y += mman.h
generic-y += module.h
generic-y += msgbuf.h
@@ -41,6 +43,7 @@
generic-y += percpu.h
generic-y += poll.h
generic-y += posix_types.h
+generic-y += preempt.h
generic-y += resource.h
generic-y += scatterlist.h
generic-y += sections.h
@@ -53,11 +56,11 @@
generic-y += signal.h
generic-y += socket.h
generic-y += sockios.h
-generic-y += statfs.h
generic-y += stat.h
+generic-y += statfs.h
generic-y += string.h
-generic-y += switch_to.h
generic-y += swab.h
+generic-y += switch_to.h
generic-y += termbits.h
generic-y += termios.h
generic-y += topology.h
@@ -68,5 +71,3 @@
generic-y += vga.h
generic-y += word-at-a-time.h
generic-y += xor.h
-generic-y += preempt.h
-generic-y += hash.h
diff --git a/arch/parisc/include/asm/Kbuild b/arch/parisc/include/asm/Kbuild
index 752c981..ecf25e6 100644
--- a/arch/parisc/include/asm/Kbuild
+++ b/arch/parisc/include/asm/Kbuild
@@ -1,9 +1,29 @@
+generic-y += auxvec.h
generic-y += barrier.h
-generic-y += word-at-a-time.h auxvec.h user.h cputime.h emergency-restart.h \
- segment.h topology.h vga.h device.h percpu.h hw_irq.h mutex.h \
- div64.h irq_regs.h kdebug.h kvm_para.h local64.h local.h param.h \
- poll.h xor.h clkdev.h exec.h
-generic-y += trace_clock.h
-generic-y += preempt.h
+generic-y += clkdev.h
+generic-y += cputime.h
+generic-y += device.h
+generic-y += div64.h
+generic-y += emergency-restart.h
+generic-y += exec.h
generic-y += hash.h
+generic-y += hw_irq.h
+generic-y += irq_regs.h
+generic-y += kdebug.h
+generic-y += kvm_para.h
+generic-y += local.h
+generic-y += local64.h
+generic-y += mcs_spinlock.h
+generic-y += mutex.h
+generic-y += param.h
+generic-y += percpu.h
+generic-y += poll.h
+generic-y += preempt.h
+generic-y += segment.h
+generic-y += topology.h
+generic-y += trace_clock.h
+generic-y += user.h
+generic-y += vga.h
+generic-y += word-at-a-time.h
+generic-y += xor.h
diff --git a/arch/powerpc/include/asm/Kbuild b/arch/powerpc/include/asm/Kbuild
index 6c0a955..3fb1bc4 100644
--- a/arch/powerpc/include/asm/Kbuild
+++ b/arch/powerpc/include/asm/Kbuild
@@ -1,7 +1,8 @@
generic-y += clkdev.h
+generic-y += hash.h
+generic-y += mcs_spinlock.h
+generic-y += preempt.h
generic-y += rwsem.h
generic-y += trace_clock.h
-generic-y += preempt.h
generic-y += vtime.h
-generic-y += hash.h
diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig
index 65a0775..bb74b21 100644
--- a/arch/s390/Kconfig
+++ b/arch/s390/Kconfig
@@ -117,6 +117,7 @@
select HAVE_FUNCTION_GRAPH_TRACER
select HAVE_FUNCTION_TRACER
select HAVE_FUNCTION_TRACE_MCOUNT_TEST
+ select HAVE_FUTEX_CMPXCHG if FUTEX
select HAVE_KERNEL_BZIP2
select HAVE_KERNEL_GZIP
select HAVE_KERNEL_LZ4
diff --git a/arch/s390/include/asm/Kbuild b/arch/s390/include/asm/Kbuild
index 8386a4a..57892a8 100644
--- a/arch/s390/include/asm/Kbuild
+++ b/arch/s390/include/asm/Kbuild
@@ -1,6 +1,7 @@
generic-y += clkdev.h
-generic-y += trace_clock.h
-generic-y += preempt.h
generic-y += hash.h
+generic-y += mcs_spinlock.h
+generic-y += preempt.h
+generic-y += trace_clock.h
diff --git a/arch/score/include/asm/Kbuild b/arch/score/include/asm/Kbuild
index 146b9d5..4630cf2 100644
--- a/arch/score/include/asm/Kbuild
+++ b/arch/score/include/asm/Kbuild
@@ -1,10 +1,11 @@
header-y +=
+
generic-y += barrier.h
generic-y += clkdev.h
generic-y += hash.h
+generic-y += mcs_spinlock.h
+generic-y += preempt.h
generic-y += trace_clock.h
generic-y += xor.h
-generic-y += preempt.h
-
diff --git a/arch/sh/include/asm/Kbuild b/arch/sh/include/asm/Kbuild
index 0cd7198..c19e47d 100644
--- a/arch/sh/include/asm/Kbuild
+++ b/arch/sh/include/asm/Kbuild
@@ -8,18 +8,21 @@
generic-y += errno.h
generic-y += exec.h
generic-y += fcntl.h
+generic-y += hash.h
generic-y += ioctl.h
generic-y += ipcbuf.h
generic-y += irq_regs.h
generic-y += kvm_para.h
generic-y += local.h
generic-y += local64.h
+generic-y += mcs_spinlock.h
+generic-y += mman.h
+generic-y += msgbuf.h
generic-y += param.h
generic-y += parport.h
generic-y += percpu.h
generic-y += poll.h
-generic-y += mman.h
-generic-y += msgbuf.h
+generic-y += preempt.h
generic-y += resource.h
generic-y += scatterlist.h
generic-y += sembuf.h
@@ -34,5 +37,3 @@
generic-y += trace_clock.h
generic-y += ucontext.h
generic-y += xor.h
-generic-y += preempt.h
-generic-y += hash.h
diff --git a/arch/sparc/include/asm/Kbuild b/arch/sparc/include/asm/Kbuild
index 4b60a0c..a458218 100644
--- a/arch/sparc/include/asm/Kbuild
+++ b/arch/sparc/include/asm/Kbuild
@@ -6,15 +6,16 @@
generic-y += div64.h
generic-y += emergency-restart.h
generic-y += exec.h
-generic-y += linkage.h
-generic-y += local64.h
-generic-y += mutex.h
+generic-y += hash.h
generic-y += irq_regs.h
+generic-y += linkage.h
generic-y += local.h
+generic-y += local64.h
+generic-y += mcs_spinlock.h
generic-y += module.h
+generic-y += mutex.h
+generic-y += preempt.h
generic-y += serial.h
generic-y += trace_clock.h
generic-y += types.h
generic-y += word-at-a-time.h
-generic-y += preempt.h
-generic-y += hash.h
diff --git a/arch/tile/include/asm/Kbuild b/arch/tile/include/asm/Kbuild
index 3793c75..0aa5675 100644
--- a/arch/tile/include/asm/Kbuild
+++ b/arch/tile/include/asm/Kbuild
@@ -11,6 +11,7 @@
generic-y += exec.h
generic-y += fb.h
generic-y += fcntl.h
+generic-y += hash.h
generic-y += hw_irq.h
generic-y += ioctl.h
generic-y += ioctls.h
@@ -18,12 +19,14 @@
generic-y += irq_regs.h
generic-y += local.h
generic-y += local64.h
+generic-y += mcs_spinlock.h
generic-y += msgbuf.h
generic-y += mutex.h
generic-y += param.h
generic-y += parport.h
generic-y += poll.h
generic-y += posix_types.h
+generic-y += preempt.h
generic-y += resource.h
generic-y += scatterlist.h
generic-y += sembuf.h
@@ -38,5 +41,3 @@
generic-y += trace_clock.h
generic-y += types.h
generic-y += xor.h
-generic-y += preempt.h
-generic-y += hash.h
diff --git a/arch/um/include/asm/Kbuild b/arch/um/include/asm/Kbuild
index 88a330d..a5e4b60 100644
--- a/arch/um/include/asm/Kbuild
+++ b/arch/um/include/asm/Kbuild
@@ -1,8 +1,28 @@
-generic-y += bug.h cputime.h device.h emergency-restart.h futex.h hardirq.h
-generic-y += hw_irq.h irq_regs.h kdebug.h percpu.h sections.h topology.h xor.h
-generic-y += ftrace.h pci.h io.h param.h delay.h mutex.h current.h exec.h
-generic-y += switch_to.h clkdev.h
-generic-y += trace_clock.h
-generic-y += preempt.h
-generic-y += hash.h
generic-y += barrier.h
+generic-y += bug.h
+generic-y += clkdev.h
+generic-y += cputime.h
+generic-y += current.h
+generic-y += delay.h
+generic-y += device.h
+generic-y += emergency-restart.h
+generic-y += exec.h
+generic-y += ftrace.h
+generic-y += futex.h
+generic-y += hardirq.h
+generic-y += hash.h
+generic-y += hw_irq.h
+generic-y += io.h
+generic-y += irq_regs.h
+generic-y += kdebug.h
+generic-y += mcs_spinlock.h
+generic-y += mutex.h
+generic-y += param.h
+generic-y += pci.h
+generic-y += percpu.h
+generic-y += preempt.h
+generic-y += sections.h
+generic-y += switch_to.h
+generic-y += topology.h
+generic-y += trace_clock.h
+generic-y += xor.h
diff --git a/arch/unicore32/include/asm/Kbuild b/arch/unicore32/include/asm/Kbuild
index 3ef4f9d..1e5fb87 100644
--- a/arch/unicore32/include/asm/Kbuild
+++ b/arch/unicore32/include/asm/Kbuild
@@ -16,6 +16,7 @@
generic-y += ftrace.h
generic-y += futex.h
generic-y += hardirq.h
+generic-y += hash.h
generic-y += hw_irq.h
generic-y += ioctl.h
generic-y += ioctls.h
@@ -24,6 +25,7 @@
generic-y += kdebug.h
generic-y += kmap_types.h
generic-y += local.h
+generic-y += mcs_spinlock.h
generic-y += mman.h
generic-y += module.h
generic-y += msgbuf.h
@@ -32,6 +34,7 @@
generic-y += percpu.h
generic-y += poll.h
generic-y += posix_types.h
+generic-y += preempt.h
generic-y += resource.h
generic-y += scatterlist.h
generic-y += sections.h
@@ -60,5 +63,3 @@
generic-y += user.h
generic-y += vga.h
generic-y += xor.h
-generic-y += preempt.h
-generic-y += hash.h
diff --git a/arch/x86/include/asm/Kbuild b/arch/x86/include/asm/Kbuild
index 7f66985..a8fee07 100644
--- a/arch/x86/include/asm/Kbuild
+++ b/arch/x86/include/asm/Kbuild
@@ -5,3 +5,4 @@
genhdr-y += unistd_x32.h
generic-y += clkdev.h
+generic-y += mcs_spinlock.h
diff --git a/arch/xtensa/include/asm/Kbuild b/arch/xtensa/include/asm/Kbuild
index 0a337e4..c3d20ba 100644
--- a/arch/xtensa/include/asm/Kbuild
+++ b/arch/xtensa/include/asm/Kbuild
@@ -9,6 +9,7 @@
generic-y += exec.h
generic-y += fcntl.h
generic-y += hardirq.h
+generic-y += hash.h
generic-y += ioctl.h
generic-y += irq_regs.h
generic-y += kdebug.h
@@ -17,7 +18,9 @@
generic-y += linkage.h
generic-y += local.h
generic-y += local64.h
+generic-y += mcs_spinlock.h
generic-y += percpu.h
+generic-y += preempt.h
generic-y += resource.h
generic-y += scatterlist.h
generic-y += sections.h
@@ -27,5 +30,3 @@
generic-y += topology.h
generic-y += trace_clock.h
generic-y += xor.h
-generic-y += preempt.h
-generic-y += hash.h
diff --git a/drivers/tty/tty_ldsem.c b/drivers/tty/tty_ldsem.c
index d8a55e8..0ffb0cb 100644
--- a/drivers/tty/tty_ldsem.c
+++ b/drivers/tty/tty_ldsem.c
@@ -39,17 +39,10 @@
lock_acquire(&(l)->dep_map, s, t, r, c, n, i)
# define __rel(l, n, i) \
lock_release(&(l)->dep_map, n, i)
-# ifdef CONFIG_PROVE_LOCKING
-# define lockdep_acquire(l, s, t, i) __acq(l, s, t, 0, 2, NULL, i)
-# define lockdep_acquire_nest(l, s, t, n, i) __acq(l, s, t, 0, 2, n, i)
-# define lockdep_acquire_read(l, s, t, i) __acq(l, s, t, 1, 2, NULL, i)
-# define lockdep_release(l, n, i) __rel(l, n, i)
-# else
-# define lockdep_acquire(l, s, t, i) __acq(l, s, t, 0, 1, NULL, i)
-# define lockdep_acquire_nest(l, s, t, n, i) __acq(l, s, t, 0, 1, n, i)
-# define lockdep_acquire_read(l, s, t, i) __acq(l, s, t, 1, 1, NULL, i)
-# define lockdep_release(l, n, i) __rel(l, n, i)
-# endif
+#define lockdep_acquire(l, s, t, i) __acq(l, s, t, 0, 1, NULL, i)
+#define lockdep_acquire_nest(l, s, t, n, i) __acq(l, s, t, 0, 1, n, i)
+#define lockdep_acquire_read(l, s, t, i) __acq(l, s, t, 1, 1, NULL, i)
+#define lockdep_release(l, n, i) __rel(l, n, i)
#else
# define lockdep_acquire(l, s, t, i) do { } while (0)
# define lockdep_acquire_nest(l, s, t, n, i) do { } while (0)
diff --git a/include/asm-generic/mcs_spinlock.h b/include/asm-generic/mcs_spinlock.h
new file mode 100644
index 0000000..10cd4ff
--- /dev/null
+++ b/include/asm-generic/mcs_spinlock.h
@@ -0,0 +1,13 @@
+#ifndef __ASM_MCS_SPINLOCK_H
+#define __ASM_MCS_SPINLOCK_H
+
+/*
+ * Architectures can define their own:
+ *
+ * arch_mcs_spin_lock_contended(l)
+ * arch_mcs_spin_unlock_contended(l)
+ *
+ * See kernel/locking/mcs_spinlock.c.
+ */
+
+#endif /* __ASM_MCS_SPINLOCK_H */
diff --git a/include/linux/futex.h b/include/linux/futex.h
index b0d95ca..6435f46 100644
--- a/include/linux/futex.h
+++ b/include/linux/futex.h
@@ -55,7 +55,11 @@
#ifdef CONFIG_FUTEX
extern void exit_robust_list(struct task_struct *curr);
extern void exit_pi_state_list(struct task_struct *curr);
+#ifdef CONFIG_HAVE_FUTEX_CMPXCHG
+#define futex_cmpxchg_enabled 1
+#else
extern int futex_cmpxchg_enabled;
+#endif
#else
static inline void exit_robust_list(struct task_struct *curr)
{
diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h
index 92b1bfc..060e513 100644
--- a/include/linux/lockdep.h
+++ b/include/linux/lockdep.h
@@ -252,9 +252,9 @@
unsigned int trylock:1; /* 16 bits */
unsigned int read:2; /* see lock_acquire() comment */
- unsigned int check:2; /* see lock_acquire() comment */
+ unsigned int check:1; /* see lock_acquire() comment */
unsigned int hardirqs_off:1;
- unsigned int references:11; /* 32 bits */
+ unsigned int references:12; /* 32 bits */
};
/*
@@ -303,7 +303,7 @@
(lock)->dep_map.key, sub)
#define lockdep_set_novalidate_class(lock) \
- lockdep_set_class(lock, &__lockdep_no_validate__)
+ lockdep_set_class_and_name(lock, &__lockdep_no_validate__, #lock)
/*
* Compare locking classes
*/
@@ -326,9 +326,8 @@
*
* Values for check:
*
- * 0: disabled
- * 1: simple checks (freeing, held-at-exit-time, etc.)
- * 2: full validation
+ * 0: simple checks (freeing, held-at-exit-time, etc.)
+ * 1: full validation
*/
extern void lock_acquire(struct lockdep_map *lock, unsigned int subclass,
int trylock, int read, int check,
@@ -479,15 +478,9 @@
* on the per lock-class debug mode:
*/
-#ifdef CONFIG_PROVE_LOCKING
- #define lock_acquire_exclusive(l, s, t, n, i) lock_acquire(l, s, t, 0, 2, n, i)
- #define lock_acquire_shared(l, s, t, n, i) lock_acquire(l, s, t, 1, 2, n, i)
- #define lock_acquire_shared_recursive(l, s, t, n, i) lock_acquire(l, s, t, 2, 2, n, i)
-#else
- #define lock_acquire_exclusive(l, s, t, n, i) lock_acquire(l, s, t, 0, 1, n, i)
- #define lock_acquire_shared(l, s, t, n, i) lock_acquire(l, s, t, 1, 1, n, i)
- #define lock_acquire_shared_recursive(l, s, t, n, i) lock_acquire(l, s, t, 2, 1, n, i)
-#endif
+#define lock_acquire_exclusive(l, s, t, n, i) lock_acquire(l, s, t, 0, 1, n, i)
+#define lock_acquire_shared(l, s, t, n, i) lock_acquire(l, s, t, 1, 1, n, i)
+#define lock_acquire_shared_recursive(l, s, t, n, i) lock_acquire(l, s, t, 2, 1, n, i)
#define spin_acquire(l, s, t, i) lock_acquire_exclusive(l, s, t, NULL, i)
#define spin_acquire_nest(l, s, t, n, i) lock_acquire_exclusive(l, s, t, n, i)
@@ -518,13 +511,13 @@
# define might_lock(lock) \
do { \
typecheck(struct lockdep_map *, &(lock)->dep_map); \
- lock_acquire(&(lock)->dep_map, 0, 0, 0, 2, NULL, _THIS_IP_); \
+ lock_acquire(&(lock)->dep_map, 0, 0, 0, 1, NULL, _THIS_IP_); \
lock_release(&(lock)->dep_map, 0, _THIS_IP_); \
} while (0)
# define might_lock_read(lock) \
do { \
typecheck(struct lockdep_map *, &(lock)->dep_map); \
- lock_acquire(&(lock)->dep_map, 0, 0, 1, 2, NULL, _THIS_IP_); \
+ lock_acquire(&(lock)->dep_map, 0, 0, 1, 1, NULL, _THIS_IP_); \
lock_release(&(lock)->dep_map, 0, _THIS_IP_); \
} while (0)
#else
diff --git a/include/linux/mutex.h b/include/linux/mutex.h
index d318193..11692de 100644
--- a/include/linux/mutex.h
+++ b/include/linux/mutex.h
@@ -46,6 +46,7 @@
* - detects multi-task circular deadlocks and prints out all affected
* locks and tasks (and only those tasks)
*/
+struct optimistic_spin_queue;
struct mutex {
/* 1: unlocked, 0: locked, negative: locked, possible waiters */
atomic_t count;
@@ -55,7 +56,7 @@
struct task_struct *owner;
#endif
#ifdef CONFIG_MUTEX_SPIN_ON_OWNER
- void *spin_mlock; /* Spinner MCS lock */
+ struct optimistic_spin_queue *osq; /* Spinner MCS lock */
#endif
#ifdef CONFIG_DEBUG_MUTEXES
const char *name;
@@ -179,4 +180,4 @@
# define arch_mutex_cpu_relax() cpu_relax()
#endif
-#endif
+#endif /* __LINUX_MUTEX_H */
diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h
index 72bf3a0..adff3c9 100644
--- a/include/linux/rcupdate.h
+++ b/include/linux/rcupdate.h
@@ -314,7 +314,7 @@
static inline void rcu_lock_acquire(struct lockdep_map *map)
{
- lock_acquire(map, 0, 0, 2, 1, NULL, _THIS_IP_);
+ lock_acquire(map, 0, 0, 2, 0, NULL, _THIS_IP_);
}
static inline void rcu_lock_release(struct lockdep_map *map)
diff --git a/init/Kconfig b/init/Kconfig
index 009a797..d56cb03 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -1387,6 +1387,13 @@
support for "fast userspace mutexes". The resulting kernel may not
run glibc-based applications correctly.
+config HAVE_FUTEX_CMPXCHG
+ bool
+ help
+ Architectures should select this if futex_atomic_cmpxchg_inatomic()
+ is implemented and always working. This removes a couple of runtime
+ checks.
+
config EPOLL
bool "Enable eventpoll support" if EXPERT
default y
diff --git a/kernel/futex.c b/kernel/futex.c
index 08ec814..67dacaf 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -157,7 +157,9 @@
* enqueue.
*/
+#ifndef CONFIG_HAVE_FUTEX_CMPXCHG
int __read_mostly futex_cmpxchg_enabled;
+#endif
/*
* Futex flags used to encode options to functions and preserve them across
@@ -2875,9 +2877,28 @@
return do_futex(uaddr, op, val, tp, uaddr2, val2, val3);
}
+static void __init futex_detect_cmpxchg(void)
+{
+#ifndef CONFIG_HAVE_FUTEX_CMPXCHG
+ u32 curval;
+
+ /*
+ * This will fail and we want it. Some arch implementations do
+ * runtime detection of the futex_atomic_cmpxchg_inatomic()
+ * functionality. We want to know that before we call in any
+ * of the complex code paths. Also we want to prevent
+ * registration of robust lists in that case. NULL is
+ * guaranteed to fault and we get -EFAULT on functional
+ * implementation, the non-functional ones will return
+ * -ENOSYS.
+ */
+ if (cmpxchg_futex_value_locked(&curval, NULL, 0, 0) == -EFAULT)
+ futex_cmpxchg_enabled = 1;
+#endif
+}
+
static int __init futex_init(void)
{
- u32 curval;
unsigned int futex_shift;
unsigned long i;
@@ -2893,18 +2914,8 @@
&futex_shift, NULL,
futex_hashsize, futex_hashsize);
futex_hashsize = 1UL << futex_shift;
- /*
- * This will fail and we want it. Some arch implementations do
- * runtime detection of the futex_atomic_cmpxchg_inatomic()
- * functionality. We want to know that before we call in any
- * of the complex code paths. Also we want to prevent
- * registration of robust lists in that case. NULL is
- * guaranteed to fault and we get -EFAULT on functional
- * implementation, the non-functional ones will return
- * -ENOSYS.
- */
- if (cmpxchg_futex_value_locked(&curval, NULL, 0, 0) == -EFAULT)
- futex_cmpxchg_enabled = 1;
+
+ futex_detect_cmpxchg();
for (i = 0; i < futex_hashsize; i++) {
atomic_set(&futex_queues[i].waiters, 0);
diff --git a/kernel/locking/Makefile b/kernel/locking/Makefile
index baab8e5..2a9ee96 100644
--- a/kernel/locking/Makefile
+++ b/kernel/locking/Makefile
@@ -1,5 +1,5 @@
-obj-y += mutex.o semaphore.o rwsem.o lglock.o
+obj-y += mutex.o semaphore.o rwsem.o lglock.o mcs_spinlock.o
ifdef CONFIG_FUNCTION_TRACER
CFLAGS_REMOVE_lockdep.o = -pg
diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c
index eb8a547..bf0c6b0 100644
--- a/kernel/locking/lockdep.c
+++ b/kernel/locking/lockdep.c
@@ -1936,12 +1936,12 @@
for (;;) {
int distance = curr->lockdep_depth - depth + 1;
- hlock = curr->held_locks + depth-1;
+ hlock = curr->held_locks + depth - 1;
/*
* Only non-recursive-read entries get new dependencies
* added:
*/
- if (hlock->read != 2) {
+ if (hlock->read != 2 && hlock->check) {
if (!check_prev_add(curr, hlock, next,
distance, trylock_loop))
return 0;
@@ -2098,7 +2098,7 @@
* (If lookup_chain_cache() returns with 1 it acquires
* graph_lock for us)
*/
- if (!hlock->trylock && (hlock->check == 2) &&
+ if (!hlock->trylock && hlock->check &&
lookup_chain_cache(curr, hlock, chain_key)) {
/*
* Check whether last held lock:
@@ -2517,7 +2517,7 @@
BUG_ON(usage_bit >= LOCK_USAGE_STATES);
- if (hlock_class(hlock)->key == __lockdep_no_validate__.subkeys)
+ if (!hlock->check)
continue;
if (!mark_lock(curr, hlock, usage_bit))
@@ -3055,9 +3055,6 @@
int class_idx;
u64 chain_key;
- if (!prove_locking)
- check = 1;
-
if (unlikely(!debug_locks))
return 0;
@@ -3069,8 +3066,8 @@
if (DEBUG_LOCKS_WARN_ON(!irqs_disabled()))
return 0;
- if (lock->key == &__lockdep_no_validate__)
- check = 1;
+ if (!prove_locking || lock->key == &__lockdep_no_validate__)
+ check = 0;
if (subclass < NR_LOCKDEP_CACHING_CLASSES)
class = lock->class_cache[subclass];
@@ -3138,7 +3135,7 @@
hlock->holdtime_stamp = lockstat_clock();
#endif
- if (check == 2 && !mark_irqflags(curr, hlock))
+ if (check && !mark_irqflags(curr, hlock))
return 0;
/* mark it as used: */
diff --git a/kernel/locking/mcs_spinlock.c b/kernel/locking/mcs_spinlock.c
new file mode 100644
index 0000000..838dc9e
--- /dev/null
+++ b/kernel/locking/mcs_spinlock.c
@@ -0,0 +1,178 @@
+
+#include <linux/percpu.h>
+#include <linux/mutex.h>
+#include <linux/sched.h>
+#include "mcs_spinlock.h"
+
+#ifdef CONFIG_SMP
+
+/*
+ * An MCS like lock especially tailored for optimistic spinning for sleeping
+ * lock implementations (mutex, rwsem, etc).
+ *
+ * Using a single mcs node per CPU is safe because sleeping locks should not be
+ * called from interrupt context and we have preemption disabled while
+ * spinning.
+ */
+static DEFINE_PER_CPU_SHARED_ALIGNED(struct optimistic_spin_queue, osq_node);
+
+/*
+ * Get a stable @node->next pointer, either for unlock() or unqueue() purposes.
+ * Can return NULL in case we were the last queued and we updated @lock instead.
+ */
+static inline struct optimistic_spin_queue *
+osq_wait_next(struct optimistic_spin_queue **lock,
+ struct optimistic_spin_queue *node,
+ struct optimistic_spin_queue *prev)
+{
+ struct optimistic_spin_queue *next = NULL;
+
+ for (;;) {
+ if (*lock == node && cmpxchg(lock, node, prev) == node) {
+ /*
+ * We were the last queued, we moved @lock back. @prev
+ * will now observe @lock and will complete its
+ * unlock()/unqueue().
+ */
+ break;
+ }
+
+ /*
+ * We must xchg() the @node->next value, because if we were to
+ * leave it in, a concurrent unlock()/unqueue() from
+ * @node->next might complete Step-A and think its @prev is
+ * still valid.
+ *
+ * If the concurrent unlock()/unqueue() wins the race, we'll
+ * wait for either @lock to point to us, through its Step-B, or
+ * wait for a new @node->next from its Step-C.
+ */
+ if (node->next) {
+ next = xchg(&node->next, NULL);
+ if (next)
+ break;
+ }
+
+ arch_mutex_cpu_relax();
+ }
+
+ return next;
+}
+
+bool osq_lock(struct optimistic_spin_queue **lock)
+{
+ struct optimistic_spin_queue *node = this_cpu_ptr(&osq_node);
+ struct optimistic_spin_queue *prev, *next;
+
+ node->locked = 0;
+ node->next = NULL;
+
+ node->prev = prev = xchg(lock, node);
+ if (likely(prev == NULL))
+ return true;
+
+ ACCESS_ONCE(prev->next) = node;
+
+ /*
+ * Normally @prev is untouchable after the above store; because at that
+ * moment unlock can proceed and wipe the node element from stack.
+ *
+ * However, since our nodes are static per-cpu storage, we're
+ * guaranteed their existence -- this allows us to apply
+ * cmpxchg in an attempt to undo our queueing.
+ */
+
+ while (!smp_load_acquire(&node->locked)) {
+ /*
+ * If we need to reschedule bail... so we can block.
+ */
+ if (need_resched())
+ goto unqueue;
+
+ arch_mutex_cpu_relax();
+ }
+ return true;
+
+unqueue:
+ /*
+ * Step - A -- stabilize @prev
+ *
+ * Undo our @prev->next assignment; this will make @prev's
+ * unlock()/unqueue() wait for a next pointer since @lock points to us
+ * (or later).
+ */
+
+ for (;;) {
+ if (prev->next == node &&
+ cmpxchg(&prev->next, node, NULL) == node)
+ break;
+
+ /*
+ * We can only fail the cmpxchg() racing against an unlock(),
+ * in which case we should observe @node->locked becomming
+ * true.
+ */
+ if (smp_load_acquire(&node->locked))
+ return true;
+
+ arch_mutex_cpu_relax();
+
+ /*
+ * Or we race against a concurrent unqueue()'s step-B, in which
+ * case its step-C will write us a new @node->prev pointer.
+ */
+ prev = ACCESS_ONCE(node->prev);
+ }
+
+ /*
+ * Step - B -- stabilize @next
+ *
+ * Similar to unlock(), wait for @node->next or move @lock from @node
+ * back to @prev.
+ */
+
+ next = osq_wait_next(lock, node, prev);
+ if (!next)
+ return false;
+
+ /*
+ * Step - C -- unlink
+ *
+ * @prev is stable because its still waiting for a new @prev->next
+ * pointer, @next is stable because our @node->next pointer is NULL and
+ * it will wait in Step-A.
+ */
+
+ ACCESS_ONCE(next->prev) = prev;
+ ACCESS_ONCE(prev->next) = next;
+
+ return false;
+}
+
+void osq_unlock(struct optimistic_spin_queue **lock)
+{
+ struct optimistic_spin_queue *node = this_cpu_ptr(&osq_node);
+ struct optimistic_spin_queue *next;
+
+ /*
+ * Fast path for the uncontended case.
+ */
+ if (likely(cmpxchg(lock, node, NULL) == node))
+ return;
+
+ /*
+ * Second most likely case.
+ */
+ next = xchg(&node->next, NULL);
+ if (next) {
+ ACCESS_ONCE(next->locked) = 1;
+ return;
+ }
+
+ next = osq_wait_next(lock, node, NULL);
+ if (next)
+ ACCESS_ONCE(next->locked) = 1;
+}
+
+#endif
+
diff --git a/kernel/locking/mcs_spinlock.h b/kernel/locking/mcs_spinlock.h
new file mode 100644
index 0000000..a2dbac4
--- /dev/null
+++ b/kernel/locking/mcs_spinlock.h
@@ -0,0 +1,129 @@
+/*
+ * MCS lock defines
+ *
+ * This file contains the main data structure and API definitions of MCS lock.
+ *
+ * The MCS lock (proposed by Mellor-Crummey and Scott) is a simple spin-lock
+ * with the desirable properties of being fair, and with each cpu trying
+ * to acquire the lock spinning on a local variable.
+ * It avoids expensive cache bouncings that common test-and-set spin-lock
+ * implementations incur.
+ */
+#ifndef __LINUX_MCS_SPINLOCK_H
+#define __LINUX_MCS_SPINLOCK_H
+
+#include <asm/mcs_spinlock.h>
+
+struct mcs_spinlock {
+ struct mcs_spinlock *next;
+ int locked; /* 1 if lock acquired */
+};
+
+#ifndef arch_mcs_spin_lock_contended
+/*
+ * Using smp_load_acquire() provides a memory barrier that ensures
+ * subsequent operations happen after the lock is acquired.
+ */
+#define arch_mcs_spin_lock_contended(l) \
+do { \
+ while (!(smp_load_acquire(l))) \
+ arch_mutex_cpu_relax(); \
+} while (0)
+#endif
+
+#ifndef arch_mcs_spin_unlock_contended
+/*
+ * smp_store_release() provides a memory barrier to ensure all
+ * operations in the critical section has been completed before
+ * unlocking.
+ */
+#define arch_mcs_spin_unlock_contended(l) \
+ smp_store_release((l), 1)
+#endif
+
+/*
+ * Note: the smp_load_acquire/smp_store_release pair is not
+ * sufficient to form a full memory barrier across
+ * cpus for many architectures (except x86) for mcs_unlock and mcs_lock.
+ * For applications that need a full barrier across multiple cpus
+ * with mcs_unlock and mcs_lock pair, smp_mb__after_unlock_lock() should be
+ * used after mcs_lock.
+ */
+
+/*
+ * In order to acquire the lock, the caller should declare a local node and
+ * pass a reference of the node to this function in addition to the lock.
+ * If the lock has already been acquired, then this will proceed to spin
+ * on this node->locked until the previous lock holder sets the node->locked
+ * in mcs_spin_unlock().
+ *
+ * We don't inline mcs_spin_lock() so that perf can correctly account for the
+ * time spent in this lock function.
+ */
+static inline
+void mcs_spin_lock(struct mcs_spinlock **lock, struct mcs_spinlock *node)
+{
+ struct mcs_spinlock *prev;
+
+ /* Init node */
+ node->locked = 0;
+ node->next = NULL;
+
+ prev = xchg(lock, node);
+ if (likely(prev == NULL)) {
+ /*
+ * Lock acquired, don't need to set node->locked to 1. Threads
+ * only spin on its own node->locked value for lock acquisition.
+ * However, since this thread can immediately acquire the lock
+ * and does not proceed to spin on its own node->locked, this
+ * value won't be used. If a debug mode is needed to
+ * audit lock status, then set node->locked value here.
+ */
+ return;
+ }
+ ACCESS_ONCE(prev->next) = node;
+
+ /* Wait until the lock holder passes the lock down. */
+ arch_mcs_spin_lock_contended(&node->locked);
+}
+
+/*
+ * Releases the lock. The caller should pass in the corresponding node that
+ * was used to acquire the lock.
+ */
+static inline
+void mcs_spin_unlock(struct mcs_spinlock **lock, struct mcs_spinlock *node)
+{
+ struct mcs_spinlock *next = ACCESS_ONCE(node->next);
+
+ if (likely(!next)) {
+ /*
+ * Release the lock by setting it to NULL
+ */
+ if (likely(cmpxchg(lock, node, NULL) == node))
+ return;
+ /* Wait until the next pointer is set */
+ while (!(next = ACCESS_ONCE(node->next)))
+ arch_mutex_cpu_relax();
+ }
+
+ /* Pass lock to next waiter. */
+ arch_mcs_spin_unlock_contended(&next->locked);
+}
+
+/*
+ * Cancellable version of the MCS lock above.
+ *
+ * Intended for adaptive spinning of sleeping locks:
+ * mutex_lock()/rwsem_down_{read,write}() etc.
+ */
+
+struct optimistic_spin_queue {
+ struct optimistic_spin_queue *next, *prev;
+ int locked; /* 1 if lock acquired */
+};
+
+extern bool osq_lock(struct optimistic_spin_queue **lock);
+extern void osq_unlock(struct optimistic_spin_queue **lock);
+
+#endif /* __LINUX_MCS_SPINLOCK_H */
diff --git a/kernel/locking/mutex-debug.c b/kernel/locking/mutex-debug.c
index faf6f5b..e1191c9 100644
--- a/kernel/locking/mutex-debug.c
+++ b/kernel/locking/mutex-debug.c
@@ -83,6 +83,12 @@
DEBUG_LOCKS_WARN_ON(!lock->wait_list.prev && !lock->wait_list.next);
mutex_clear_owner(lock);
+
+ /*
+ * __mutex_slowpath_needs_to_unlock() is explicitly 0 for debug
+ * mutexes so that we can do it here after we've verified state.
+ */
+ atomic_set(&lock->count, 1);
}
void debug_mutex_init(struct mutex *lock, const char *name,
diff --git a/kernel/locking/mutex.c b/kernel/locking/mutex.c
index 4dd6e4c..14fe72c 100644
--- a/kernel/locking/mutex.c
+++ b/kernel/locking/mutex.c
@@ -25,6 +25,7 @@
#include <linux/spinlock.h>
#include <linux/interrupt.h>
#include <linux/debug_locks.h>
+#include "mcs_spinlock.h"
/*
* In the DEBUG case we are using the "NULL fastpath" for mutexes,
@@ -33,6 +34,13 @@
#ifdef CONFIG_DEBUG_MUTEXES
# include "mutex-debug.h"
# include <asm-generic/mutex-null.h>
+/*
+ * Must be 0 for the debug case so we do not do the unlock outside of the
+ * wait_lock region. debug_mutex_unlock() will do the actual unlock in this
+ * case.
+ */
+# undef __mutex_slowpath_needs_to_unlock
+# define __mutex_slowpath_needs_to_unlock() 0
#else
# include "mutex.h"
# include <asm/mutex.h>
@@ -52,7 +60,7 @@
INIT_LIST_HEAD(&lock->wait_list);
mutex_clear_owner(lock);
#ifdef CONFIG_MUTEX_SPIN_ON_OWNER
- lock->spin_mlock = NULL;
+ lock->osq = NULL;
#endif
debug_mutex_init(lock, name, key);
@@ -111,54 +119,7 @@
* more or less simultaneously, the spinners need to acquire a MCS lock
* first before spinning on the owner field.
*
- * We don't inline mspin_lock() so that perf can correctly account for the
- * time spent in this lock function.
*/
-struct mspin_node {
- struct mspin_node *next ;
- int locked; /* 1 if lock acquired */
-};
-#define MLOCK(mutex) ((struct mspin_node **)&((mutex)->spin_mlock))
-
-static noinline
-void mspin_lock(struct mspin_node **lock, struct mspin_node *node)
-{
- struct mspin_node *prev;
-
- /* Init node */
- node->locked = 0;
- node->next = NULL;
-
- prev = xchg(lock, node);
- if (likely(prev == NULL)) {
- /* Lock acquired */
- node->locked = 1;
- return;
- }
- ACCESS_ONCE(prev->next) = node;
- smp_wmb();
- /* Wait until the lock holder passes the lock down */
- while (!ACCESS_ONCE(node->locked))
- arch_mutex_cpu_relax();
-}
-
-static void mspin_unlock(struct mspin_node **lock, struct mspin_node *node)
-{
- struct mspin_node *next = ACCESS_ONCE(node->next);
-
- if (likely(!next)) {
- /*
- * Release the lock by setting it to NULL
- */
- if (cmpxchg(lock, node, NULL) == node)
- return;
- /* Wait until the next pointer is set */
- while (!(next = ACCESS_ONCE(node->next)))
- arch_mutex_cpu_relax();
- }
- ACCESS_ONCE(next->locked) = 1;
- smp_wmb();
-}
/*
* Mutex spinning code migrated from kernel/sched/core.c
@@ -212,6 +173,9 @@
struct task_struct *owner;
int retval = 1;
+ if (need_resched())
+ return 0;
+
rcu_read_lock();
owner = ACCESS_ONCE(lock->owner);
if (owner)
@@ -446,9 +410,11 @@
if (!mutex_can_spin_on_owner(lock))
goto slowpath;
+ if (!osq_lock(&lock->osq))
+ goto slowpath;
+
for (;;) {
struct task_struct *owner;
- struct mspin_node node;
if (use_ww_ctx && ww_ctx->acquired > 0) {
struct ww_mutex *ww;
@@ -463,19 +429,16 @@
* performed the optimistic spinning cannot be done.
*/
if (ACCESS_ONCE(ww->ctx))
- goto slowpath;
+ break;
}
/*
* If there's an owner, wait for it to either
* release the lock or go to sleep.
*/
- mspin_lock(MLOCK(lock), &node);
owner = ACCESS_ONCE(lock->owner);
- if (owner && !mutex_spin_on_owner(lock, owner)) {
- mspin_unlock(MLOCK(lock), &node);
- goto slowpath;
- }
+ if (owner && !mutex_spin_on_owner(lock, owner))
+ break;
if ((atomic_read(&lock->count) == 1) &&
(atomic_cmpxchg(&lock->count, 1, 0) == 1)) {
@@ -488,11 +451,10 @@
}
mutex_set_owner(lock);
- mspin_unlock(MLOCK(lock), &node);
+ osq_unlock(&lock->osq);
preempt_enable();
return 0;
}
- mspin_unlock(MLOCK(lock), &node);
/*
* When there's no owner, we might have preempted between the
@@ -501,7 +463,7 @@
* the owner complete.
*/
if (!owner && (need_resched() || rt_task(task)))
- goto slowpath;
+ break;
/*
* The cpu_relax() call is a compiler barrier which forces
@@ -511,7 +473,15 @@
*/
arch_mutex_cpu_relax();
}
+ osq_unlock(&lock->osq);
slowpath:
+ /*
+ * If we fell out of the spin path because of need_resched(),
+ * reschedule now, before we try-lock the mutex. This avoids getting
+ * scheduled out right after we obtained the mutex.
+ */
+ if (need_resched())
+ schedule_preempt_disabled();
#endif
spin_lock_mutex(&lock->wait_lock, flags);
@@ -717,10 +687,6 @@
struct mutex *lock = container_of(lock_count, struct mutex, count);
unsigned long flags;
- spin_lock_mutex(&lock->wait_lock, flags);
- mutex_release(&lock->dep_map, nested, _RET_IP_);
- debug_mutex_unlock(lock);
-
/*
* some architectures leave the lock unlocked in the fastpath failure
* case, others need to leave it locked. In the later case we have to
@@ -729,6 +695,10 @@
if (__mutex_slowpath_needs_to_unlock())
atomic_set(&lock->count, 1);
+ spin_lock_mutex(&lock->wait_lock, flags);
+ mutex_release(&lock->dep_map, nested, _RET_IP_);
+ debug_mutex_unlock(lock);
+
if (!list_empty(&lock->wait_list)) {
/* get the first entry from the wait-list: */
struct mutex_waiter *waiter =