* [GIT PULL] locking tree updates for v3.17
@ 2014-08-04 9:43 Ingo Molnar
0 siblings, 0 replies; only message in thread
From: Ingo Molnar @ 2014-08-04 9:43 UTC (permalink / raw)
To: Linus Torvalds
Cc: linux-kernel, Peter Zijlstra, Thomas Gleixner, Andrew Morton
Linus,
Please pull the latest locking-core-for-linus git tree from:
git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git locking-core-for-linus
# HEAD: 3a6bfbc91df04b081a44d419e0260bad54abddf7 arch, locking: Ciao arch_mutex_cpu_relax()
The main changes in this cycle are:
- big rtmutex and futex cleanup and robustification from Thomas Gleixner
- mutex optimizations and refinements from Jason Low
- arch_mutex_cpu_relax() removal and related cleanups
- smaller lockdep tweaks
Thanks,
Ingo
------------------>
Andreas Gruenbacher (1):
locking/lockdep: Only ask for /proc/lock_stat output when available
Davidlohr Bueso (1):
arch, locking: Ciao arch_mutex_cpu_relax()
Jason Low (4):
locking/mutexes: Correct documentation on mutex optimistic spinning
locking/mutexes: Delete the MUTEX_SHOW_NO_WAITER macro
locking/mutexes: Try to acquire mutex only if it is unlocked
locking/mutexes: Optimize mutex trylock slowpath
Peter Zijlstra (1):
x86, locking: Use no more OOSTORE nonsense
Thomas Gleixner (15):
rtmutex: Simplify rtmutex_slowtrylock()
rtmutex: Simplify and document try_to_take_rtmutex()
rtmutex: No need to keep task ref for lock owner check
rtmutex: Clarify the boost/deboost part
rtmutex: Document pi chain walk
rtmutex: Simplify remove_waiter()
rtmutex: Confine deadlock logic to futex
rtmutex: Cleanup deadlock detector debug logic
rtmutex: Avoid pointless requeueing in the deadlock detection chain walk
futex: Make unlock_pi more robust
futex: Use futex_top_waiter() in lookup_pi_state()
futex: Split out the waiter check from lookup_pi_state()
futex: Split out the first waiter attachment from lookup_pi_state()
futex: Simplify futex_lock_pi_atomic() and make it more robust
rtmutex: Make the rtmutex tester depend on BROKEN
Trond Myklebust (1):
lockdep: Revert lockdep check in raw_seqcount_begin()
arch/alpha/include/asm/processor.h | 1 +
arch/arc/include/asm/processor.h | 2 +
arch/arm/include/asm/processor.h | 2 +
arch/arm64/include/asm/processor.h | 1 +
arch/avr32/include/asm/processor.h | 1 +
arch/blackfin/include/asm/processor.h | 2 +-
arch/c6x/include/asm/processor.h | 1 +
arch/cris/include/asm/processor.h | 1 +
arch/hexagon/include/asm/processor.h | 1 +
arch/ia64/include/asm/processor.h | 1 +
arch/m32r/include/asm/processor.h | 1 +
arch/m68k/include/asm/processor.h | 1 +
arch/metag/include/asm/processor.h | 1 +
arch/microblaze/include/asm/processor.h | 1 +
arch/mips/include/asm/processor.h | 1 +
arch/mn10300/include/asm/processor.h | 2 +
arch/openrisc/include/asm/processor.h | 1 +
arch/parisc/include/asm/processor.h | 1 +
arch/powerpc/include/asm/processor.h | 2 +
arch/s390/include/asm/processor.h | 2 +-
arch/score/include/asm/processor.h | 1 +
arch/sh/include/asm/processor.h | 1 +
arch/sparc/include/asm/processor_32.h | 2 +
arch/sparc/include/asm/processor_64.h | 1 +
arch/tile/include/asm/processor.h | 2 +
arch/unicore32/include/asm/processor.h | 1 +
arch/x86/include/asm/barrier.h | 2 +-
arch/x86/include/asm/processor.h | 2 +
arch/x86/include/asm/qrwlock.h | 2 +-
arch/x86/um/asm/processor.h | 3 +-
arch/xtensa/include/asm/processor.h | 1 +
include/linux/mutex.h | 4 -
include/linux/rtmutex.h | 6 +-
include/linux/seqlock.h | 2 -
kernel/futex.c | 402 +++++++++++------------
kernel/locking/lockdep.c | 2 +
kernel/locking/mcs_spinlock.c | 8 +-
kernel/locking/mcs_spinlock.h | 4 +-
kernel/locking/mutex.c | 39 +--
kernel/locking/qrwlock.c | 9 +-
kernel/locking/rtmutex-debug.c | 5 +-
kernel/locking/rtmutex-debug.h | 7 +-
kernel/locking/rtmutex.c | 562 ++++++++++++++++++++++++--------
kernel/locking/rtmutex.h | 7 +-
kernel/locking/rtmutex_common.h | 22 +-
kernel/locking/rwsem-xadd.c | 4 +-
lib/Kconfig.debug | 2 +-
lib/lockref.c | 3 +-
48 files changed, 707 insertions(+), 425 deletions(-)
diff --git a/arch/alpha/include/asm/processor.h b/arch/alpha/include/asm/processor.h
index 6cb7fe8..b4cf036 100644
--- a/arch/alpha/include/asm/processor.h
+++ b/arch/alpha/include/asm/processor.h
@@ -57,6 +57,7 @@ unsigned long get_wchan(struct task_struct *p);
((tsk) == current ? rdusp() : task_thread_info(tsk)->pcb.usp)
#define cpu_relax() barrier()
+#define cpu_relax_lowlatency() cpu_relax()
#define ARCH_HAS_PREFETCH
#define ARCH_HAS_PREFETCHW
diff --git a/arch/arc/include/asm/processor.h b/arch/arc/include/asm/processor.h
index d99f9b3..82588f3 100644
--- a/arch/arc/include/asm/processor.h
+++ b/arch/arc/include/asm/processor.h
@@ -62,6 +62,8 @@ unsigned long thread_saved_pc(struct task_struct *t);
#define cpu_relax() do { } while (0)
#endif
+#define cpu_relax_lowlatency() cpu_relax()
+
#define copy_segments(tsk, mm) do { } while (0)
#define release_segments(mm) do { } while (0)
diff --git a/arch/arm/include/asm/processor.h b/arch/arm/include/asm/processor.h
index c3d5fc1..8a1e8e9 100644
--- a/arch/arm/include/asm/processor.h
+++ b/arch/arm/include/asm/processor.h
@@ -82,6 +82,8 @@ unsigned long get_wchan(struct task_struct *p);
#define cpu_relax() barrier()
#endif
+#define cpu_relax_lowlatency() cpu_relax()
+
#define task_pt_regs(p) \
((struct pt_regs *)(THREAD_START_SP + task_stack_page(p)) - 1)
diff --git a/arch/arm64/include/asm/processor.h b/arch/arm64/include/asm/processor.h
index 34de2a8..4610b0d 100644
--- a/arch/arm64/include/asm/processor.h
+++ b/arch/arm64/include/asm/processor.h
@@ -129,6 +129,7 @@ extern void release_thread(struct task_struct *);
unsigned long get_wchan(struct task_struct *p);
#define cpu_relax() barrier()
+#define cpu_relax_lowlatency() cpu_relax()
/* Thread switching */
extern struct task_struct *cpu_switch_to(struct task_struct *prev,
diff --git a/arch/avr32/include/asm/processor.h b/arch/avr32/include/asm/processor.h
index 972adcc..941593c 100644
--- a/arch/avr32/include/asm/processor.h
+++ b/arch/avr32/include/asm/processor.h
@@ -92,6 +92,7 @@ extern struct avr32_cpuinfo boot_cpu_data;
#define TASK_UNMAPPED_BASE (PAGE_ALIGN(TASK_SIZE / 3))
#define cpu_relax() barrier()
+#define cpu_relax_lowlatency() cpu_relax()
#define cpu_sync_pipeline() asm volatile("sub pc, -2" : : : "memory")
struct cpu_context {
diff --git a/arch/blackfin/include/asm/processor.h b/arch/blackfin/include/asm/processor.h
index d0e72e9..7acd466 100644
--- a/arch/blackfin/include/asm/processor.h
+++ b/arch/blackfin/include/asm/processor.h
@@ -99,7 +99,7 @@ unsigned long get_wchan(struct task_struct *p);
#define KSTK_ESP(tsk) ((tsk) == current ? rdusp() : (tsk)->thread.usp)
#define cpu_relax() smp_mb()
-
+#define cpu_relax_lowlatency() cpu_relax()
/* Get the Silicon Revision of the chip */
static inline uint32_t __pure bfin_revid(void)
diff --git a/arch/c6x/include/asm/processor.h b/arch/c6x/include/asm/processor.h
index b9eb3da..f2ef31b 100644
--- a/arch/c6x/include/asm/processor.h
+++ b/arch/c6x/include/asm/processor.h
@@ -121,6 +121,7 @@ extern unsigned long get_wchan(struct task_struct *p);
#define KSTK_ESP(task) (task_pt_regs(task)->sp)
#define cpu_relax() do { } while (0)
+#define cpu_relax_lowlatency() cpu_relax()
extern const struct seq_operations cpuinfo_op;
diff --git a/arch/cris/include/asm/processor.h b/arch/cris/include/asm/processor.h
index 15b815d..862126b 100644
--- a/arch/cris/include/asm/processor.h
+++ b/arch/cris/include/asm/processor.h
@@ -63,6 +63,7 @@ static inline void release_thread(struct task_struct *dead_task)
#define init_stack (init_thread_union.stack)
#define cpu_relax() barrier()
+#define cpu_relax_lowlatency() cpu_relax()
void default_idle(void);
diff --git a/arch/hexagon/include/asm/processor.h b/arch/hexagon/include/asm/processor.h
index 45a8254..d850113 100644
--- a/arch/hexagon/include/asm/processor.h
+++ b/arch/hexagon/include/asm/processor.h
@@ -56,6 +56,7 @@ struct thread_struct {
}
#define cpu_relax() __vmyield()
+#define cpu_relax_lowlatency() cpu_relax()
/*
* Decides where the kernel will search for a free chunk of vm space during
diff --git a/arch/ia64/include/asm/processor.h b/arch/ia64/include/asm/processor.h
index efd1b92..c736713 100644
--- a/arch/ia64/include/asm/processor.h
+++ b/arch/ia64/include/asm/processor.h
@@ -548,6 +548,7 @@ ia64_eoi (void)
}
#define cpu_relax() ia64_hint(ia64_hint_pause)
+#define cpu_relax_lowlatency() cpu_relax()
static inline int
ia64_get_irr(unsigned int vector)
diff --git a/arch/m32r/include/asm/processor.h b/arch/m32r/include/asm/processor.h
index 5767367..9f8fd9b 100644
--- a/arch/m32r/include/asm/processor.h
+++ b/arch/m32r/include/asm/processor.h
@@ -133,5 +133,6 @@ unsigned long get_wchan(struct task_struct *p);
#define KSTK_ESP(tsk) ((tsk)->thread.sp)
#define cpu_relax() barrier()
+#define cpu_relax_lowlatency() cpu_relax()
#endif /* _ASM_M32R_PROCESSOR_H */
diff --git a/arch/m68k/include/asm/processor.h b/arch/m68k/include/asm/processor.h
index b0768a6..20dda1d 100644
--- a/arch/m68k/include/asm/processor.h
+++ b/arch/m68k/include/asm/processor.h
@@ -176,5 +176,6 @@ unsigned long get_wchan(struct task_struct *p);
#define task_pt_regs(tsk) ((struct pt_regs *) ((tsk)->thread.esp0))
#define cpu_relax() barrier()
+#define cpu_relax_lowlatency() cpu_relax()
#endif
diff --git a/arch/metag/include/asm/processor.h b/arch/metag/include/asm/processor.h
index a8a3747..881071c 100644
--- a/arch/metag/include/asm/processor.h
+++ b/arch/metag/include/asm/processor.h
@@ -155,6 +155,7 @@ unsigned long get_wchan(struct task_struct *p);
#define user_stack_pointer(regs) ((regs)->ctx.AX[0].U0)
#define cpu_relax() barrier()
+#define cpu_relax_lowlatency() cpu_relax()
extern void setup_priv(void);
diff --git a/arch/microblaze/include/asm/processor.h b/arch/microblaze/include/asm/processor.h
index 9d31b05..497a988 100644
--- a/arch/microblaze/include/asm/processor.h
+++ b/arch/microblaze/include/asm/processor.h
@@ -22,6 +22,7 @@
extern const struct seq_operations cpuinfo_op;
# define cpu_relax() barrier()
+# define cpu_relax_lowlatency() cpu_relax()
#define task_pt_regs(tsk) \
(((struct pt_regs *)(THREAD_SIZE + task_stack_page(tsk))) - 1)
diff --git a/arch/mips/include/asm/processor.h b/arch/mips/include/asm/processor.h
index ad70cba..d5098bc 100644
--- a/arch/mips/include/asm/processor.h
+++ b/arch/mips/include/asm/processor.h
@@ -367,6 +367,7 @@ unsigned long get_wchan(struct task_struct *p);
#define KSTK_STATUS(tsk) (task_pt_regs(tsk)->cp0_status)
#define cpu_relax() barrier()
+#define cpu_relax_lowlatency() cpu_relax()
/*
* Return_address is a replacement for __builtin_return_address(count)
diff --git a/arch/mn10300/include/asm/processor.h b/arch/mn10300/include/asm/processor.h
index 8b80b19..769d5ed 100644
--- a/arch/mn10300/include/asm/processor.h
+++ b/arch/mn10300/include/asm/processor.h
@@ -68,7 +68,9 @@ extern struct mn10300_cpuinfo cpu_data[];
extern void identify_cpu(struct mn10300_cpuinfo *);
extern void print_cpu_info(struct mn10300_cpuinfo *);
extern void dodgy_tsc(void);
+
#define cpu_relax() barrier()
+#define cpu_relax_lowlatency() cpu_relax()
/*
* User space process size: 1.75GB (default).
diff --git a/arch/openrisc/include/asm/processor.h b/arch/openrisc/include/asm/processor.h
index cab746f..4d235e3 100644
--- a/arch/openrisc/include/asm/processor.h
+++ b/arch/openrisc/include/asm/processor.h
@@ -101,6 +101,7 @@ extern unsigned long thread_saved_pc(struct task_struct *t);
#define init_stack (init_thread_union.stack)
#define cpu_relax() barrier()
+#define cpu_relax_lowlatency() cpu_relax()
#endif /* __ASSEMBLY__ */
#endif /* __ASM_OPENRISC_PROCESSOR_H */
diff --git a/arch/parisc/include/asm/processor.h b/arch/parisc/include/asm/processor.h
index d951c96..689a8ad 100644
--- a/arch/parisc/include/asm/processor.h
+++ b/arch/parisc/include/asm/processor.h
@@ -338,6 +338,7 @@ extern unsigned long get_wchan(struct task_struct *p);
#define KSTK_ESP(tsk) ((tsk)->thread.regs.gr[30])
#define cpu_relax() barrier()
+#define cpu_relax_lowlatency() cpu_relax()
/* Used as a macro to identify the combined VIPT/PIPT cached
* CPUs which require a guarantee of coherency (no inequivalent
diff --git a/arch/powerpc/include/asm/processor.h b/arch/powerpc/include/asm/processor.h
index 6d59072..dda7ac4 100644
--- a/arch/powerpc/include/asm/processor.h
+++ b/arch/powerpc/include/asm/processor.h
@@ -400,6 +400,8 @@ static inline unsigned long __pack_fe01(unsigned int fpmode)
#define cpu_relax() barrier()
#endif
+#define cpu_relax_lowlatency() cpu_relax()
+
/* Check that a certain kernel stack pointer is valid in task_struct p */
int validate_sp(unsigned long sp, struct task_struct *p,
unsigned long nbytes);
diff --git a/arch/s390/include/asm/processor.h b/arch/s390/include/asm/processor.h
index 6f02d45..e568fc8 100644
--- a/arch/s390/include/asm/processor.h
+++ b/arch/s390/include/asm/processor.h
@@ -217,7 +217,7 @@ static inline void cpu_relax(void)
barrier();
}
-#define arch_mutex_cpu_relax() barrier()
+#define cpu_relax_lowlatency() barrier()
static inline void psw_set_key(unsigned int key)
{
diff --git a/arch/score/include/asm/processor.h b/arch/score/include/asm/processor.h
index d9a922d..851f441 100644
--- a/arch/score/include/asm/processor.h
+++ b/arch/score/include/asm/processor.h
@@ -24,6 +24,7 @@ extern unsigned long get_wchan(struct task_struct *p);
#define current_text_addr() ({ __label__ _l; _l: &&_l; })
#define cpu_relax() barrier()
+#define cpu_relax_lowlatency() cpu_relax()
#define release_thread(thread) do {} while (0)
/*
diff --git a/arch/sh/include/asm/processor.h b/arch/sh/include/asm/processor.h
index 5448f9b..1506897 100644
--- a/arch/sh/include/asm/processor.h
+++ b/arch/sh/include/asm/processor.h
@@ -97,6 +97,7 @@ extern struct sh_cpuinfo cpu_data[];
#define cpu_sleep() __asm__ __volatile__ ("sleep" : : : "memory")
#define cpu_relax() barrier()
+#define cpu_relax_lowlatency() cpu_relax()
void default_idle(void);
void stop_this_cpu(void *);
diff --git a/arch/sparc/include/asm/processor_32.h b/arch/sparc/include/asm/processor_32.h
index a564817..812fd08 100644
--- a/arch/sparc/include/asm/processor_32.h
+++ b/arch/sparc/include/asm/processor_32.h
@@ -119,6 +119,8 @@ extern struct task_struct *last_task_used_math;
int do_mathemu(struct pt_regs *regs, struct task_struct *fpt);
#define cpu_relax() barrier()
+#define cpu_relax_lowlatency() cpu_relax()
+
extern void (*sparc_idle)(void);
#endif
diff --git a/arch/sparc/include/asm/processor_64.h b/arch/sparc/include/asm/processor_64.h
index 7028fe1..6924bde 100644
--- a/arch/sparc/include/asm/processor_64.h
+++ b/arch/sparc/include/asm/processor_64.h
@@ -216,6 +216,7 @@ unsigned long get_wchan(struct task_struct *task);
"nop\n\t" \
".previous" \
::: "memory")
+#define cpu_relax_lowlatency() cpu_relax()
/* Prefetch support. This is tuned for UltraSPARC-III and later.
* UltraSPARC-I will treat these as nops, and UltraSPARC-II has
diff --git a/arch/tile/include/asm/processor.h b/arch/tile/include/asm/processor.h
index 4232363..dd4f9f1 100644
--- a/arch/tile/include/asm/processor.h
+++ b/arch/tile/include/asm/processor.h
@@ -266,6 +266,8 @@ static inline void cpu_relax(void)
barrier();
}
+#define cpu_relax_lowlatency() cpu_relax()
+
/* Info on this processor (see fs/proc/cpuinfo.c) */
struct seq_operations;
extern const struct seq_operations cpuinfo_op;
diff --git a/arch/unicore32/include/asm/processor.h b/arch/unicore32/include/asm/processor.h
index 4eaa421..8d21b7a 100644
--- a/arch/unicore32/include/asm/processor.h
+++ b/arch/unicore32/include/asm/processor.h
@@ -71,6 +71,7 @@ extern void release_thread(struct task_struct *);
unsigned long get_wchan(struct task_struct *p);
#define cpu_relax() barrier()
+#define cpu_relax_lowlatency() cpu_relax()
#define task_pt_regs(p) \
((struct pt_regs *)(THREAD_START_SP + task_stack_page(p)) - 1)
diff --git a/arch/x86/include/asm/barrier.h b/arch/x86/include/asm/barrier.h
index 5c7198c..0f4460b 100644
--- a/arch/x86/include/asm/barrier.h
+++ b/arch/x86/include/asm/barrier.h
@@ -99,7 +99,7 @@
#if defined(CONFIG_X86_PPRO_FENCE)
/*
- * For either of these options x86 doesn't have a strong TSO memory
+ * For this option x86 doesn't have a strong TSO memory
* model and we should fall back to full barriers.
*/
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index a4ea023..32cc237 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -696,6 +696,8 @@ static inline void cpu_relax(void)
rep_nop();
}
+#define cpu_relax_lowlatency() cpu_relax()
+
/* Stop speculative execution and prefetching of modified code. */
static inline void sync_core(void)
{
diff --git a/arch/x86/include/asm/qrwlock.h b/arch/x86/include/asm/qrwlock.h
index 70f46f0..ae0e241 100644
--- a/arch/x86/include/asm/qrwlock.h
+++ b/arch/x86/include/asm/qrwlock.h
@@ -3,7 +3,7 @@
#include <asm-generic/qrwlock_types.h>
-#if !defined(CONFIG_X86_OOSTORE) && !defined(CONFIG_X86_PPRO_FENCE)
+#ifndef CONFIG_X86_PPRO_FENCE
#define queue_write_unlock queue_write_unlock
static inline void queue_write_unlock(struct qrwlock *lock)
{
diff --git a/arch/x86/um/asm/processor.h b/arch/x86/um/asm/processor.h
index 04f82e0..2a206d2 100644
--- a/arch/x86/um/asm/processor.h
+++ b/arch/x86/um/asm/processor.h
@@ -25,7 +25,8 @@ static inline void rep_nop(void)
__asm__ __volatile__("rep;nop": : :"memory");
}
-#define cpu_relax() rep_nop()
+#define cpu_relax() rep_nop()
+#define cpu_relax_lowlatency() cpu_relax()
#include <asm/processor-generic.h>
diff --git a/arch/xtensa/include/asm/processor.h b/arch/xtensa/include/asm/processor.h
index abb5970..b61bdf0 100644
--- a/arch/xtensa/include/asm/processor.h
+++ b/arch/xtensa/include/asm/processor.h
@@ -182,6 +182,7 @@ extern unsigned long get_wchan(struct task_struct *p);
#define KSTK_ESP(tsk) (task_pt_regs(tsk)->areg[1])
#define cpu_relax() barrier()
+#define cpu_relax_lowlatency() cpu_relax()
/* Special register access. */
diff --git a/include/linux/mutex.h b/include/linux/mutex.h
index 42aa9b9..8d5535c 100644
--- a/include/linux/mutex.h
+++ b/include/linux/mutex.h
@@ -176,8 +176,4 @@ extern void mutex_unlock(struct mutex *lock);
extern int atomic_dec_and_mutex_lock(atomic_t *cnt, struct mutex *lock);
-#ifndef arch_mutex_cpu_relax
-# define arch_mutex_cpu_relax() cpu_relax()
-#endif
-
#endif /* __LINUX_MUTEX_H */
diff --git a/include/linux/rtmutex.h b/include/linux/rtmutex.h
index 3aed8d7..1abba5c 100644
--- a/include/linux/rtmutex.h
+++ b/include/linux/rtmutex.h
@@ -90,11 +90,9 @@ extern void __rt_mutex_init(struct rt_mutex *lock, const char *name);
extern void rt_mutex_destroy(struct rt_mutex *lock);
extern void rt_mutex_lock(struct rt_mutex *lock);
-extern int rt_mutex_lock_interruptible(struct rt_mutex *lock,
- int detect_deadlock);
+extern int rt_mutex_lock_interruptible(struct rt_mutex *lock);
extern int rt_mutex_timed_lock(struct rt_mutex *lock,
- struct hrtimer_sleeper *timeout,
- int detect_deadlock);
+ struct hrtimer_sleeper *timeout);
extern int rt_mutex_trylock(struct rt_mutex *lock);
diff --git a/include/linux/seqlock.h b/include/linux/seqlock.h
index 535f158..8cf3503 100644
--- a/include/linux/seqlock.h
+++ b/include/linux/seqlock.h
@@ -164,8 +164,6 @@ static inline unsigned read_seqcount_begin(const seqcount_t *s)
static inline unsigned raw_seqcount_begin(const seqcount_t *s)
{
unsigned ret = ACCESS_ONCE(s->sequence);
-
- seqcount_lockdep_reader_access(s);
smp_rmb();
return ret & ~1;
}
diff --git a/kernel/futex.c b/kernel/futex.c
index b632b5f..d3a9d94 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -792,94 +792,91 @@ void exit_pi_state_list(struct task_struct *curr)
* [10] There is no transient state which leaves owner and user space
* TID out of sync.
*/
-static int
-lookup_pi_state(u32 uval, struct futex_hash_bucket *hb,
- union futex_key *key, struct futex_pi_state **ps)
+
+/*
+ * Validate that the existing waiter has a pi_state and sanity check
+ * the pi_state against the user space value. If correct, attach to
+ * it.
+ */
+static int attach_to_pi_state(u32 uval, struct futex_pi_state *pi_state,
+ struct futex_pi_state **ps)
{
- struct futex_pi_state *pi_state = NULL;
- struct futex_q *this, *next;
- struct task_struct *p;
pid_t pid = uval & FUTEX_TID_MASK;
- plist_for_each_entry_safe(this, next, &hb->chain, list) {
- if (match_futex(&this->key, key)) {
- /*
- * Sanity check the waiter before increasing
- * the refcount and attaching to it.
- */
- pi_state = this->pi_state;
- /*
- * Userspace might have messed up non-PI and
- * PI futexes [3]
- */
- if (unlikely(!pi_state))
- return -EINVAL;
+ /*
+ * Userspace might have messed up non-PI and PI futexes [3]
+ */
+ if (unlikely(!pi_state))
+ return -EINVAL;
- WARN_ON(!atomic_read(&pi_state->refcount));
+ WARN_ON(!atomic_read(&pi_state->refcount));
+ /*
+ * Handle the owner died case:
+ */
+ if (uval & FUTEX_OWNER_DIED) {
+ /*
+ * exit_pi_state_list sets owner to NULL and wakes the
+ * topmost waiter. The task which acquires the
+ * pi_state->rt_mutex will fixup owner.
+ */
+ if (!pi_state->owner) {
/*
- * Handle the owner died case:
+ * No pi state owner, but the user space TID
+ * is not 0. Inconsistent state. [5]
*/
- if (uval & FUTEX_OWNER_DIED) {
- /*
- * exit_pi_state_list sets owner to NULL and
- * wakes the topmost waiter. The task which
- * acquires the pi_state->rt_mutex will fixup
- * owner.
- */
- if (!pi_state->owner) {
- /*
- * No pi state owner, but the user
- * space TID is not 0. Inconsistent
- * state. [5]
- */
- if (pid)
- return -EINVAL;
- /*
- * Take a ref on the state and
- * return. [4]
- */
- goto out_state;
- }
-
- /*
- * If TID is 0, then either the dying owner
- * has not yet executed exit_pi_state_list()
- * or some waiter acquired the rtmutex in the
- * pi state, but did not yet fixup the TID in
- * user space.
- *
- * Take a ref on the state and return. [6]
- */
- if (!pid)
- goto out_state;
- } else {
- /*
- * If the owner died bit is not set,
- * then the pi_state must have an
- * owner. [7]
- */
- if (!pi_state->owner)
- return -EINVAL;
- }
-
+ if (pid)
+ return -EINVAL;
/*
- * Bail out if user space manipulated the
- * futex value. If pi state exists then the
- * owner TID must be the same as the user
- * space TID. [9/10]
+ * Take a ref on the state and return success. [4]
*/
- if (pid != task_pid_vnr(pi_state->owner))
- return -EINVAL;
-
- out_state:
- atomic_inc(&pi_state->refcount);
- *ps = pi_state;
- return 0;
+ goto out_state;
}
+
+ /*
+ * If TID is 0, then either the dying owner has not
+ * yet executed exit_pi_state_list() or some waiter
+ * acquired the rtmutex in the pi state, but did not
+ * yet fixup the TID in user space.
+ *
+ * Take a ref on the state and return success. [6]
+ */
+ if (!pid)
+ goto out_state;
+ } else {
+ /*
+ * If the owner died bit is not set, then the pi_state
+ * must have an owner. [7]
+ */
+ if (!pi_state->owner)
+ return -EINVAL;
}
/*
+ * Bail out if user space manipulated the futex value. If pi
+ * state exists then the owner TID must be the same as the
+ * user space TID. [9/10]
+ */
+ if (pid != task_pid_vnr(pi_state->owner))
+ return -EINVAL;
+out_state:
+ atomic_inc(&pi_state->refcount);
+ *ps = pi_state;
+ return 0;
+}
+
+/*
+ * Lookup the task for the TID provided from user space and attach to
+ * it after doing proper sanity checks.
+ */
+static int attach_to_pi_owner(u32 uval, union futex_key *key,
+ struct futex_pi_state **ps)
+{
+ pid_t pid = uval & FUTEX_TID_MASK;
+ struct futex_pi_state *pi_state;
+ struct task_struct *p;
+
+ /*
* We are the first waiter - try to look up the real owner and attach
* the new pi_state to it, but bail out when TID = 0 [1]
*/
@@ -920,7 +917,7 @@ lookup_pi_state(u32 uval, struct futex_hash_bucket *hb,
pi_state = alloc_pi_state();
/*
- * Initialize the pi_mutex in locked state and make 'p'
+ * Initialize the pi_mutex in locked state and make @p
* the owner of it:
*/
rt_mutex_init_proxy_locked(&pi_state->pi_mutex, p);
@@ -940,6 +937,36 @@ lookup_pi_state(u32 uval, struct futex_hash_bucket *hb,
return 0;
}
+static int lookup_pi_state(u32 uval, struct futex_hash_bucket *hb,
+ union futex_key *key, struct futex_pi_state **ps)
+{
+ struct futex_q *match = futex_top_waiter(hb, key);
+
+ /*
+ * If there is a waiter on that futex, validate it and
+ * attach to the pi_state when the validation succeeds.
+ */
+ if (match)
+ return attach_to_pi_state(uval, match->pi_state, ps);
+
+ /*
+ * We are the first waiter - try to look up the owner based on
+ * @uval and attach to it.
+ */
+ return attach_to_pi_owner(uval, key, ps);
+}
+
+static int lock_pi_update_atomic(u32 __user *uaddr, u32 uval, u32 newval)
+{
+ u32 uninitialized_var(curval);
+
+ if (unlikely(cmpxchg_futex_value_locked(&curval, uaddr, uval, newval)))
+ return -EFAULT;
+
+ /*If user space value changed, let the caller retry */
+ return curval != uval ? -EAGAIN : 0;
+}
+
/**
* futex_lock_pi_atomic() - Atomic work required to acquire a pi aware futex
* @uaddr: the pi futex user address
@@ -963,113 +990,69 @@ static int futex_lock_pi_atomic(u32 __user *uaddr, struct futex_hash_bucket *hb,
struct futex_pi_state **ps,
struct task_struct *task, int set_waiters)
{
- int lock_taken, ret, force_take = 0;
- u32 uval, newval, curval, vpid = task_pid_vnr(task);
-
-retry:
- ret = lock_taken = 0;
+ u32 uval, newval, vpid = task_pid_vnr(task);
+ struct futex_q *match;
+ int ret;
/*
- * To avoid races, we attempt to take the lock here again
- * (by doing a 0 -> TID atomic cmpxchg), while holding all
- * the locks. It will most likely not succeed.
+ * Read the user space value first so we can validate a few
+ * things before proceeding further.
*/
- newval = vpid;
- if (set_waiters)
- newval |= FUTEX_WAITERS;
-
- if (unlikely(cmpxchg_futex_value_locked(&curval, uaddr, 0, newval)))
+ if (get_futex_value_locked(&uval, uaddr))
return -EFAULT;
/*
* Detect deadlocks.
*/
- if ((unlikely((curval & FUTEX_TID_MASK) == vpid)))
+ if ((unlikely((uval & FUTEX_TID_MASK) == vpid)))
return -EDEADLK;
/*
- * Surprise - we got the lock, but we do not trust user space at all.
- */
- if (unlikely(!curval)) {
- /*
- * We verify whether there is kernel state for this
- * futex. If not, we can safely assume, that the 0 ->
- * TID transition is correct. If state exists, we do
- * not bother to fixup the user space state as it was
- * corrupted already.
- */
- return futex_top_waiter(hb, key) ? -EINVAL : 1;
- }
-
- uval = curval;
-
- /*
- * Set the FUTEX_WAITERS flag, so the owner will know it has someone
- * to wake at the next unlock.
+ * Lookup existing state first. If it exists, try to attach to
+ * its pi_state.
*/
- newval = curval | FUTEX_WAITERS;
+ match = futex_top_waiter(hb, key);
+ if (match)
+ return attach_to_pi_state(uval, match->pi_state, ps);
/*
- * Should we force take the futex? See below.
+ * No waiter and user TID is 0. We are here because the
+ * waiters or the owner died bit is set or called from
+ * requeue_cmp_pi or for whatever reason something took the
+ * syscall.
*/
- if (unlikely(force_take)) {
+ if (!(uval & FUTEX_TID_MASK)) {
/*
- * Keep the OWNER_DIED and the WAITERS bit and set the
- * new TID value.
+ * We take over the futex. No other waiters and the user space
+ * TID is 0. We preserve the owner died bit.
*/
- newval = (curval & ~FUTEX_TID_MASK) | vpid;
- force_take = 0;
- lock_taken = 1;
- }
+ newval = uval & FUTEX_OWNER_DIED;
+ newval |= vpid;
- if (unlikely(cmpxchg_futex_value_locked(&curval, uaddr, uval, newval)))
- return -EFAULT;
- if (unlikely(curval != uval))
- goto retry;
+ /* The futex requeue_pi code can enforce the waiters bit */
+ if (set_waiters)
+ newval |= FUTEX_WAITERS;
+
+ ret = lock_pi_update_atomic(uaddr, uval, newval);
+ /* If the take over worked, return 1 */
+ return ret < 0 ? ret : 1;
+ }
/*
- * We took the lock due to forced take over.
+ * First waiter. Set the waiters bit before attaching ourself to
+ * the owner. If owner tries to unlock, it will be forced into
+ * the kernel and blocked on hb->lock.
*/
- if (unlikely(lock_taken))
- return 1;
-
+ newval = uval | FUTEX_WAITERS;
+ ret = lock_pi_update_atomic(uaddr, uval, newval);
+ if (ret)
+ return ret;
/*
- * We dont have the lock. Look up the PI state (or create it if
- * we are the first waiter):
+ * If the update of the user space value succeeded, we try to
+ * attach to the owner. If that fails, no harm done, we only
+ * set the FUTEX_WAITERS bit in the user space variable.
*/
- ret = lookup_pi_state(uval, hb, key, ps);
-
- if (unlikely(ret)) {
- switch (ret) {
- case -ESRCH:
- /*
- * We failed to find an owner for this
- * futex. So we have no pi_state to block
- * on. This can happen in two cases:
- *
- * 1) The owner died
- * 2) A stale FUTEX_WAITERS bit
- *
- * Re-read the futex value.
- */
- if (get_futex_value_locked(&curval, uaddr))
- return -EFAULT;
-
- /*
- * If the owner died or we have a stale
- * WAITERS bit the owner TID in the user space
- * futex is 0.
- */
- if (!(curval & FUTEX_TID_MASK)) {
- force_take = 1;
- goto retry;
- }
- default:
- break;
- }
- }
-
- return ret;
+ return attach_to_pi_owner(uval, key, ps);
}
/**
@@ -1186,22 +1169,6 @@ static int wake_futex_pi(u32 __user *uaddr, u32 uval, struct futex_q *this)
return 0;
}
-static int unlock_futex_pi(u32 __user *uaddr, u32 uval)
-{
- u32 uninitialized_var(oldval);
-
- /*
- * There is no waiter, so we unlock the futex. The owner died
- * bit has not to be preserved here. We are the owner:
- */
- if (cmpxchg_futex_value_locked(&oldval, uaddr, uval, 0))
- return -EFAULT;
- if (oldval != uval)
- return -EAGAIN;
-
- return 0;
-}
-
/*
* Express the locking dependencies for lockdep:
*/
@@ -1659,7 +1626,12 @@ retry_private:
goto retry;
goto out;
case -EAGAIN:
- /* The owner was exiting, try again. */
+ /*
+ * Two reasons for this:
+ * - Owner is exiting and we just wait for the
+ * exit to complete.
+ * - The user space value changed.
+ */
double_unlock_hb(hb1, hb2);
hb_waiters_dec(hb2);
put_futex_key(&key2);
@@ -1718,7 +1690,7 @@ retry_private:
this->pi_state = pi_state;
ret = rt_mutex_start_proxy_lock(&pi_state->pi_mutex,
this->rt_waiter,
- this->task, 1);
+ this->task);
if (ret == 1) {
/* We got the lock. */
requeue_pi_wake_futex(this, &key2, hb2);
@@ -2316,8 +2288,10 @@ retry_private:
goto uaddr_faulted;
case -EAGAIN:
/*
- * Task is exiting and we just wait for the
- * exit to complete.
+ * Two reasons for this:
+ * - Task is exiting and we just wait for the
+ * exit to complete.
+ * - The user space value changed.
*/
queue_unlock(hb);
put_futex_key(&q.key);
@@ -2337,9 +2311,9 @@ retry_private:
/*
* Block on the PI mutex:
*/
- if (!trylock)
- ret = rt_mutex_timed_lock(&q.pi_state->pi_mutex, to, 1);
- else {
+ if (!trylock) {
+ ret = rt_mutex_timed_futex_lock(&q.pi_state->pi_mutex, to);
+ } else {
ret = rt_mutex_trylock(&q.pi_state->pi_mutex);
/* Fixup the trylock return value: */
ret = ret ? 0 : -EWOULDBLOCK;
@@ -2401,10 +2375,10 @@ uaddr_faulted:
*/
static int futex_unlock_pi(u32 __user *uaddr, unsigned int flags)
{
- struct futex_hash_bucket *hb;
- struct futex_q *this, *next;
+ u32 uninitialized_var(curval), uval, vpid = task_pid_vnr(current);
union futex_key key = FUTEX_KEY_INIT;
- u32 uval, vpid = task_pid_vnr(current);
+ struct futex_hash_bucket *hb;
+ struct futex_q *match;
int ret;
retry:
@@ -2417,57 +2391,47 @@ retry:
return -EPERM;
ret = get_futex_key(uaddr, flags & FLAGS_SHARED, &key, VERIFY_WRITE);
- if (unlikely(ret != 0))
- goto out;
+ if (ret)
+ return ret;
hb = hash_futex(&key);
spin_lock(&hb->lock);
/*
- * To avoid races, try to do the TID -> 0 atomic transition
- * again. If it succeeds then we can return without waking
- * anyone else up. We only try this if neither the waiters nor
- * the owner died bit are set.
- */
- if (!(uval & ~FUTEX_TID_MASK) &&
- cmpxchg_futex_value_locked(&uval, uaddr, vpid, 0))
- goto pi_faulted;
- /*
- * Rare case: we managed to release the lock atomically,
- * no need to wake anyone else up:
- */
- if (unlikely(uval == vpid))
- goto out_unlock;
-
- /*
- * Ok, other tasks may need to be woken up - check waiters
- * and do the wakeup if necessary:
+ * Check waiters first. We do not trust user space values at
+ * all and we at least want to know if user space fiddled
+ * with the futex value instead of blindly unlocking.
*/
- plist_for_each_entry_safe(this, next, &hb->chain, list) {
- if (!match_futex (&this->key, &key))
- continue;
- ret = wake_futex_pi(uaddr, uval, this);
+ match = futex_top_waiter(hb, &key);
+ if (match) {
+ ret = wake_futex_pi(uaddr, uval, match);
/*
- * The atomic access to the futex value
- * generated a pagefault, so retry the
- * user-access and the wakeup:
+ * The atomic access to the futex value generated a
+ * pagefault, so retry the user-access and the wakeup:
*/
if (ret == -EFAULT)
goto pi_faulted;
goto out_unlock;
}
+
/*
- * No waiters - kernel unlocks the futex:
+ * We have no kernel internal state, i.e. no waiters in the
+ * kernel. Waiters which are about to queue themselves are stuck
+ * on hb->lock. So we can safely ignore them. We do neither
+ * preserve the WAITERS bit not the OWNER_DIED one. We are the
+ * owner.
*/
- ret = unlock_futex_pi(uaddr, uval);
- if (ret == -EFAULT)
+ if (cmpxchg_futex_value_locked(&curval, uaddr, uval, 0))
goto pi_faulted;
+ /*
+ * If uval has changed, let user space handle it.
+ */
+ ret = (curval == uval) ? 0 : -EAGAIN;
+
out_unlock:
spin_unlock(&hb->lock);
put_futex_key(&key);
-
-out:
return ret;
pi_faulted:
@@ -2669,7 +2633,7 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags,
*/
WARN_ON(!q.pi_state);
pi_mutex = &q.pi_state->pi_mutex;
- ret = rt_mutex_finish_proxy_lock(pi_mutex, to, &rt_waiter, 1);
+ ret = rt_mutex_finish_proxy_lock(pi_mutex, to, &rt_waiter);
debug_rt_mutex_free_waiter(&rt_waiter);
spin_lock(q.lock_ptr);
diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c
index d24e433..88d0d44 100644
--- a/kernel/locking/lockdep.c
+++ b/kernel/locking/lockdep.c
@@ -384,7 +384,9 @@ static void print_lockdep_off(const char *bug_msg)
{
printk(KERN_DEBUG "%s\n", bug_msg);
printk(KERN_DEBUG "turning off the locking correctness validator.\n");
+#ifdef CONFIG_LOCK_STAT
printk(KERN_DEBUG "Please attach the output of /proc/lock_stat to the bug report\n");
+#endif
}
static int save_trace(struct stack_trace *trace)
diff --git a/kernel/locking/mcs_spinlock.c b/kernel/locking/mcs_spinlock.c
index be9ee15..9887a90 100644
--- a/kernel/locking/mcs_spinlock.c
+++ b/kernel/locking/mcs_spinlock.c
@@ -1,6 +1,4 @@
-
#include <linux/percpu.h>
-#include <linux/mutex.h>
#include <linux/sched.h>
#include "mcs_spinlock.h"
@@ -79,7 +77,7 @@ osq_wait_next(struct optimistic_spin_queue *lock,
break;
}
- arch_mutex_cpu_relax();
+ cpu_relax_lowlatency();
}
return next;
@@ -120,7 +118,7 @@ bool osq_lock(struct optimistic_spin_queue *lock)
if (need_resched())
goto unqueue;
- arch_mutex_cpu_relax();
+ cpu_relax_lowlatency();
}
return true;
@@ -146,7 +144,7 @@ unqueue:
if (smp_load_acquire(&node->locked))
return true;
- arch_mutex_cpu_relax();
+ cpu_relax_lowlatency();
/*
* Or we race against a concurrent unqueue()'s step-B, in which
diff --git a/kernel/locking/mcs_spinlock.h b/kernel/locking/mcs_spinlock.h
index 74356dc..23e89c5 100644
--- a/kernel/locking/mcs_spinlock.h
+++ b/kernel/locking/mcs_spinlock.h
@@ -27,7 +27,7 @@ struct mcs_spinlock {
#define arch_mcs_spin_lock_contended(l) \
do { \
while (!(smp_load_acquire(l))) \
- arch_mutex_cpu_relax(); \
+ cpu_relax_lowlatency(); \
} while (0)
#endif
@@ -104,7 +104,7 @@ void mcs_spin_unlock(struct mcs_spinlock **lock, struct mcs_spinlock *node)
return;
/* Wait until the next pointer is set */
while (!(next = ACCESS_ONCE(node->next)))
- arch_mutex_cpu_relax();
+ cpu_relax_lowlatency();
}
/* Pass lock to next waiter. */
diff --git a/kernel/locking/mutex.c b/kernel/locking/mutex.c
index acca2c1..ae712b2 100644
--- a/kernel/locking/mutex.c
+++ b/kernel/locking/mutex.c
@@ -46,12 +46,6 @@
# include <asm/mutex.h>
#endif
-/*
- * A negative mutex count indicates that waiters are sleeping waiting for the
- * mutex.
- */
-#define MUTEX_SHOW_NO_WAITER(mutex) (atomic_read(&(mutex)->count) >= 0)
-
void
__mutex_init(struct mutex *lock, const char *name, struct lock_class_key *key)
{
@@ -152,7 +146,7 @@ int mutex_spin_on_owner(struct mutex *lock, struct task_struct *owner)
if (need_resched())
break;
- arch_mutex_cpu_relax();
+ cpu_relax_lowlatency();
}
rcu_read_unlock();
@@ -388,12 +382,10 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass,
/*
* Optimistic spinning.
*
- * We try to spin for acquisition when we find that there are no
- * pending waiters and the lock owner is currently running on a
- * (different) CPU.
- *
- * The rationale is that if the lock owner is running, it is likely to
- * release the lock soon.
+ * We try to spin for acquisition when we find that the lock owner
+ * is currently running on a (different) CPU and while we don't
+ * need to reschedule. The rationale is that if the lock owner is
+ * running, it is likely to release the lock soon.
*
* Since this needs the lock owner, and this mutex implementation
* doesn't track the owner atomically in the lock field, we need to
@@ -440,7 +432,8 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass,
if (owner && !mutex_spin_on_owner(lock, owner))
break;
- if ((atomic_read(&lock->count) == 1) &&
+ /* Try to acquire the mutex if it is unlocked. */
+ if (!mutex_is_locked(lock) &&
(atomic_cmpxchg(&lock->count, 1, 0) == 1)) {
lock_acquired(&lock->dep_map, ip);
if (use_ww_ctx) {
@@ -471,7 +464,7 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass,
* memory barriers as we'll eventually observe the right
* values at the cost of a few extra spins.
*/
- arch_mutex_cpu_relax();
+ cpu_relax_lowlatency();
}
osq_unlock(&lock->osq);
slowpath:
@@ -485,8 +478,11 @@ slowpath:
#endif
spin_lock_mutex(&lock->wait_lock, flags);
- /* once more, can we acquire the lock? */
- if (MUTEX_SHOW_NO_WAITER(lock) && (atomic_xchg(&lock->count, 0) == 1))
+ /*
+ * Once more, try to acquire the lock. Only try-lock the mutex if
+ * it is unlocked to reduce unnecessary xchg() operations.
+ */
+ if (!mutex_is_locked(lock) && (atomic_xchg(&lock->count, 0) == 1))
goto skip_wait;
debug_mutex_lock_common(lock, &waiter);
@@ -506,9 +502,10 @@ slowpath:
* it's unlocked. Later on, if we sleep, this is the
* operation that gives us the lock. We xchg it to -1, so
* that when we release the lock, we properly wake up the
- * other waiters:
+ * other waiters. We only attempt the xchg if the count is
+ * non-negative in order to avoid unnecessary xchg operations:
*/
- if (MUTEX_SHOW_NO_WAITER(lock) &&
+ if (atomic_read(&lock->count) >= 0 &&
(atomic_xchg(&lock->count, -1) == 1))
break;
@@ -823,6 +820,10 @@ static inline int __mutex_trylock_slowpath(atomic_t *lock_count)
unsigned long flags;
int prev;
+ /* No need to trylock if the mutex is locked. */
+ if (mutex_is_locked(lock))
+ return 0;
+
spin_lock_mutex(&lock->wait_lock, flags);
prev = atomic_xchg(&lock->count, -1);
diff --git a/kernel/locking/qrwlock.c b/kernel/locking/qrwlock.c
index fb5b8ac..f956ede 100644
--- a/kernel/locking/qrwlock.c
+++ b/kernel/locking/qrwlock.c
@@ -20,7 +20,6 @@
#include <linux/cpumask.h>
#include <linux/percpu.h>
#include <linux/hardirq.h>
-#include <linux/mutex.h>
#include <asm/qrwlock.h>
/**
@@ -35,7 +34,7 @@ static __always_inline void
rspin_until_writer_unlock(struct qrwlock *lock, u32 cnts)
{
while ((cnts & _QW_WMASK) == _QW_LOCKED) {
- arch_mutex_cpu_relax();
+ cpu_relax_lowlatency();
cnts = smp_load_acquire((u32 *)&lock->cnts);
}
}
@@ -75,7 +74,7 @@ void queue_read_lock_slowpath(struct qrwlock *lock)
* to make sure that the write lock isn't taken.
*/
while (atomic_read(&lock->cnts) & _QW_WMASK)
- arch_mutex_cpu_relax();
+ cpu_relax_lowlatency();
cnts = atomic_add_return(_QR_BIAS, &lock->cnts) - _QR_BIAS;
rspin_until_writer_unlock(lock, cnts);
@@ -114,7 +113,7 @@ void queue_write_lock_slowpath(struct qrwlock *lock)
cnts | _QW_WAITING) == cnts))
break;
- arch_mutex_cpu_relax();
+ cpu_relax_lowlatency();
}
/* When no more readers, set the locked flag */
@@ -125,7 +124,7 @@ void queue_write_lock_slowpath(struct qrwlock *lock)
_QW_LOCKED) == _QW_WAITING))
break;
- arch_mutex_cpu_relax();
+ cpu_relax_lowlatency();
}
unlock:
arch_spin_unlock(&lock->lock);
diff --git a/kernel/locking/rtmutex-debug.c b/kernel/locking/rtmutex-debug.c
index 49b2ed3..62b6cee 100644
--- a/kernel/locking/rtmutex-debug.c
+++ b/kernel/locking/rtmutex-debug.c
@@ -66,12 +66,13 @@ void rt_mutex_debug_task_free(struct task_struct *task)
* the deadlock. We print when we return. act_waiter can be NULL in
* case of a remove waiter operation.
*/
-void debug_rt_mutex_deadlock(int detect, struct rt_mutex_waiter *act_waiter,
+void debug_rt_mutex_deadlock(enum rtmutex_chainwalk chwalk,
+ struct rt_mutex_waiter *act_waiter,
struct rt_mutex *lock)
{
struct task_struct *task;
- if (!debug_locks || detect || !act_waiter)
+ if (!debug_locks || chwalk == RT_MUTEX_FULL_CHAINWALK || !act_waiter)
return;
task = rt_mutex_owner(act_waiter->lock);
diff --git a/kernel/locking/rtmutex-debug.h b/kernel/locking/rtmutex-debug.h
index ab29b6a..d0519c3 100644
--- a/kernel/locking/rtmutex-debug.h
+++ b/kernel/locking/rtmutex-debug.h
@@ -20,14 +20,15 @@ extern void debug_rt_mutex_unlock(struct rt_mutex *lock);
extern void debug_rt_mutex_proxy_lock(struct rt_mutex *lock,
struct task_struct *powner);
extern void debug_rt_mutex_proxy_unlock(struct rt_mutex *lock);
-extern void debug_rt_mutex_deadlock(int detect, struct rt_mutex_waiter *waiter,
+extern void debug_rt_mutex_deadlock(enum rtmutex_chainwalk chwalk,
+ struct rt_mutex_waiter *waiter,
struct rt_mutex *lock);
extern void debug_rt_mutex_print_deadlock(struct rt_mutex_waiter *waiter);
# define debug_rt_mutex_reset_waiter(w) \
do { (w)->deadlock_lock = NULL; } while (0)
-static inline int debug_rt_mutex_detect_deadlock(struct rt_mutex_waiter *waiter,
- int detect)
+static inline bool debug_rt_mutex_detect_deadlock(struct rt_mutex_waiter *waiter,
+ enum rtmutex_chainwalk walk)
{
return (waiter != NULL);
}
diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c
index fc60594..a0ea2a1 100644
--- a/kernel/locking/rtmutex.c
+++ b/kernel/locking/rtmutex.c
@@ -308,6 +308,32 @@ static void rt_mutex_adjust_prio(struct task_struct *task)
}
/*
+ * Deadlock detection is conditional:
+ *
+ * If CONFIG_DEBUG_RT_MUTEXES=n, deadlock detection is only conducted
+ * if the detect argument is == RT_MUTEX_FULL_CHAINWALK.
+ *
+ * If CONFIG_DEBUG_RT_MUTEXES=y, deadlock detection is always
+ * conducted independent of the detect argument.
+ *
+ * If the waiter argument is NULL this indicates the deboost path and
+ * deadlock detection is disabled independent of the detect argument
+ * and the config settings.
+ */
+static bool rt_mutex_cond_detect_deadlock(struct rt_mutex_waiter *waiter,
+ enum rtmutex_chainwalk chwalk)
+{
+ /*
+ * This is just a wrapper function for the following call,
+ * because debug_rt_mutex_detect_deadlock() smells like a magic
+ * debug feature and I wanted to keep the cond function in the
+ * main source file along with the comments instead of having
+ * two of the same in the headers.
+ */
+ return debug_rt_mutex_detect_deadlock(waiter, chwalk);
+}
+
+/*
* Max number of times we'll walk the boosting chain:
*/
int max_lock_depth = 1024;
@@ -337,21 +363,65 @@ static inline struct rt_mutex *task_blocked_on_lock(struct task_struct *p)
* @top_task: the current top waiter
*
* Returns 0 or -EDEADLK.
+ *
+ * Chain walk basics and protection scope
+ *
+ * [R] refcount on task
+ * [P] task->pi_lock held
+ * [L] rtmutex->wait_lock held
+ *
+ * Step Description Protected by
+ * function arguments:
+ * @task [R]
+ * @orig_lock if != NULL @top_task is blocked on it
+ * @next_lock Unprotected. Cannot be
+ * dereferenced. Only used for
+ * comparison.
+ * @orig_waiter if != NULL @top_task is blocked on it
+ * @top_task current, or in case of proxy
+ * locking protected by calling
+ * code
+ * again:
+ * loop_sanity_check();
+ * retry:
+ * [1] lock(task->pi_lock); [R] acquire [P]
+ * [2] waiter = task->pi_blocked_on; [P]
+ * [3] check_exit_conditions_1(); [P]
+ * [4] lock = waiter->lock; [P]
+ * [5] if (!try_lock(lock->wait_lock)) { [P] try to acquire [L]
+ * unlock(task->pi_lock); release [P]
+ * goto retry;
+ * }
+ * [6] check_exit_conditions_2(); [P] + [L]
+ * [7] requeue_lock_waiter(lock, waiter); [P] + [L]
+ * [8] unlock(task->pi_lock); release [P]
+ * put_task_struct(task); release [R]
+ * [9] check_exit_conditions_3(); [L]
+ * [10] task = owner(lock); [L]
+ * get_task_struct(task); [L] acquire [R]
+ * lock(task->pi_lock); [L] acquire [P]
+ * [11] requeue_pi_waiter(tsk, waiters(lock));[P] + [L]
+ * [12] check_exit_conditions_4(); [P] + [L]
+ * [13] unlock(task->pi_lock); release [P]
+ * unlock(lock->wait_lock); release [L]
+ * goto again;
*/
static int rt_mutex_adjust_prio_chain(struct task_struct *task,
- int deadlock_detect,
+ enum rtmutex_chainwalk chwalk,
struct rt_mutex *orig_lock,
struct rt_mutex *next_lock,
struct rt_mutex_waiter *orig_waiter,
struct task_struct *top_task)
{
- struct rt_mutex *lock;
struct rt_mutex_waiter *waiter, *top_waiter = orig_waiter;
- int detect_deadlock, ret = 0, depth = 0;
+ struct rt_mutex_waiter *prerequeue_top_waiter;
+ int ret = 0, depth = 0;
+ struct rt_mutex *lock;
+ bool detect_deadlock;
unsigned long flags;
+ bool requeue = true;
- detect_deadlock = debug_rt_mutex_detect_deadlock(orig_waiter,
- deadlock_detect);
+ detect_deadlock = rt_mutex_cond_detect_deadlock(orig_waiter, chwalk);
/*
* The (de)boosting is a step by step approach with a lot of
@@ -360,6 +430,9 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task,
* carefully whether things change under us.
*/
again:
+ /*
+ * We limit the lock chain length for each invocation.
+ */
if (++depth > max_lock_depth) {
static int prev_max;
@@ -377,13 +450,28 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task,
return -EDEADLK;
}
+
+ /*
+ * We are fully preemptible here and only hold the refcount on
+ * @task. So everything can have changed under us since the
+ * caller or our own code below (goto retry/again) dropped all
+ * locks.
+ */
retry:
/*
- * Task can not go away as we did a get_task() before !
+ * [1] Task cannot go away as we did a get_task() before !
*/
raw_spin_lock_irqsave(&task->pi_lock, flags);
+ /*
+ * [2] Get the waiter on which @task is blocked on.
+ */
waiter = task->pi_blocked_on;
+
+ /*
+ * [3] check_exit_conditions_1() protected by task->pi_lock.
+ */
+
/*
* Check whether the end of the boosting chain has been
* reached or the state of the chain has changed while we
@@ -421,20 +509,41 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task,
goto out_unlock_pi;
/*
* If deadlock detection is off, we stop here if we
- * are not the top pi waiter of the task.
+ * are not the top pi waiter of the task. If deadlock
+ * detection is enabled we continue, but stop the
+ * requeueing in the chain walk.
*/
- if (!detect_deadlock && top_waiter != task_top_pi_waiter(task))
- goto out_unlock_pi;
+ if (top_waiter != task_top_pi_waiter(task)) {
+ if (!detect_deadlock)
+ goto out_unlock_pi;
+ else
+ requeue = false;
+ }
}
/*
- * When deadlock detection is off then we check, if further
- * priority adjustment is necessary.
+ * If the waiter priority is the same as the task priority
+ * then there is no further priority adjustment necessary. If
+ * deadlock detection is off, we stop the chain walk. If its
+ * enabled we continue, but stop the requeueing in the chain
+ * walk.
*/
- if (!detect_deadlock && waiter->prio == task->prio)
- goto out_unlock_pi;
+ if (waiter->prio == task->prio) {
+ if (!detect_deadlock)
+ goto out_unlock_pi;
+ else
+ requeue = false;
+ }
+ /*
+ * [4] Get the next lock
+ */
lock = waiter->lock;
+ /*
+ * [5] We need to trylock here as we are holding task->pi_lock,
+ * which is the reverse lock order versus the other rtmutex
+ * operations.
+ */
if (!raw_spin_trylock(&lock->wait_lock)) {
raw_spin_unlock_irqrestore(&task->pi_lock, flags);
cpu_relax();
@@ -442,79 +551,180 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task,
}
/*
+ * [6] check_exit_conditions_2() protected by task->pi_lock and
+ * lock->wait_lock.
+ *
* Deadlock detection. If the lock is the same as the original
* lock which caused us to walk the lock chain or if the
* current lock is owned by the task which initiated the chain
* walk, we detected a deadlock.
*/
if (lock == orig_lock || rt_mutex_owner(lock) == top_task) {
- debug_rt_mutex_deadlock(deadlock_detect, orig_waiter, lock);
+ debug_rt_mutex_deadlock(chwalk, orig_waiter, lock);
raw_spin_unlock(&lock->wait_lock);
ret = -EDEADLK;
goto out_unlock_pi;
}
- top_waiter = rt_mutex_top_waiter(lock);
+ /*
+ * If we just follow the lock chain for deadlock detection, no
+ * need to do all the requeue operations. To avoid a truckload
+ * of conditionals around the various places below, just do the
+ * minimum chain walk checks.
+ */
+ if (!requeue) {
+ /*
+ * No requeue[7] here. Just release @task [8]
+ */
+ raw_spin_unlock_irqrestore(&task->pi_lock, flags);
+ put_task_struct(task);
+
+ /*
+ * [9] check_exit_conditions_3 protected by lock->wait_lock.
+ * If there is no owner of the lock, end of chain.
+ */
+ if (!rt_mutex_owner(lock)) {
+ raw_spin_unlock(&lock->wait_lock);
+ return 0;
+ }
+
+ /* [10] Grab the next task, i.e. owner of @lock */
+ task = rt_mutex_owner(lock);
+ get_task_struct(task);
+ raw_spin_lock_irqsave(&task->pi_lock, flags);
+
+ /*
+ * No requeue [11] here. We just do deadlock detection.
+ *
+ * [12] Store whether owner is blocked
+ * itself. Decision is made after dropping the locks
+ */
+ next_lock = task_blocked_on_lock(task);
+ /*
+ * Get the top waiter for the next iteration
+ */
+ top_waiter = rt_mutex_top_waiter(lock);
+
+ /* [13] Drop locks */
+ raw_spin_unlock_irqrestore(&task->pi_lock, flags);
+ raw_spin_unlock(&lock->wait_lock);
+
+ /* If owner is not blocked, end of chain. */
+ if (!next_lock)
+ goto out_put_task;
+ goto again;
+ }
- /* Requeue the waiter */
+ /*
+ * Store the current top waiter before doing the requeue
+ * operation on @lock. We need it for the boost/deboost
+ * decision below.
+ */
+ prerequeue_top_waiter = rt_mutex_top_waiter(lock);
+
+ /* [7] Requeue the waiter in the lock waiter list. */
rt_mutex_dequeue(lock, waiter);
waiter->prio = task->prio;
rt_mutex_enqueue(lock, waiter);
- /* Release the task */
+ /* [8] Release the task */
raw_spin_unlock_irqrestore(&task->pi_lock, flags);
+ put_task_struct(task);
+
+ /*
+ * [9] check_exit_conditions_3 protected by lock->wait_lock.
+ *
+ * We must abort the chain walk if there is no lock owner even
+ * in the dead lock detection case, as we have nothing to
+ * follow here. This is the end of the chain we are walking.
+ */
if (!rt_mutex_owner(lock)) {
/*
- * If the requeue above changed the top waiter, then we need
- * to wake the new top waiter up to try to get the lock.
+ * If the requeue [7] above changed the top waiter,
+ * then we need to wake the new top waiter up to try
+ * to get the lock.
*/
-
- if (top_waiter != rt_mutex_top_waiter(lock))
+ if (prerequeue_top_waiter != rt_mutex_top_waiter(lock))
wake_up_process(rt_mutex_top_waiter(lock)->task);
raw_spin_unlock(&lock->wait_lock);
- goto out_put_task;
+ return 0;
}
- put_task_struct(task);
- /* Grab the next task */
+ /* [10] Grab the next task, i.e. the owner of @lock */
task = rt_mutex_owner(lock);
get_task_struct(task);
raw_spin_lock_irqsave(&task->pi_lock, flags);
+ /* [11] requeue the pi waiters if necessary */
if (waiter == rt_mutex_top_waiter(lock)) {
- /* Boost the owner */
- rt_mutex_dequeue_pi(task, top_waiter);
+ /*
+ * The waiter became the new top (highest priority)
+ * waiter on the lock. Replace the previous top waiter
+ * in the owner tasks pi waiters list with this waiter
+ * and adjust the priority of the owner.
+ */
+ rt_mutex_dequeue_pi(task, prerequeue_top_waiter);
rt_mutex_enqueue_pi(task, waiter);
__rt_mutex_adjust_prio(task);
- } else if (top_waiter == waiter) {
- /* Deboost the owner */
+ } else if (prerequeue_top_waiter == waiter) {
+ /*
+ * The waiter was the top waiter on the lock, but is
+ * no longer the top prority waiter. Replace waiter in
+ * the owner tasks pi waiters list with the new top
+ * (highest priority) waiter and adjust the priority
+ * of the owner.
+ * The new top waiter is stored in @waiter so that
+ * @waiter == @top_waiter evaluates to true below and
+ * we continue to deboost the rest of the chain.
+ */
rt_mutex_dequeue_pi(task, waiter);
waiter = rt_mutex_top_waiter(lock);
rt_mutex_enqueue_pi(task, waiter);
__rt_mutex_adjust_prio(task);
+ } else {
+ /*
+ * Nothing changed. No need to do any priority
+ * adjustment.
+ */
}
/*
+ * [12] check_exit_conditions_4() protected by task->pi_lock
+ * and lock->wait_lock. The actual decisions are made after we
+ * dropped the locks.
+ *
* Check whether the task which owns the current lock is pi
* blocked itself. If yes we store a pointer to the lock for
* the lock chain change detection above. After we dropped
* task->pi_lock next_lock cannot be dereferenced anymore.
*/
next_lock = task_blocked_on_lock(task);
+ /*
+ * Store the top waiter of @lock for the end of chain walk
+ * decision below.
+ */
+ top_waiter = rt_mutex_top_waiter(lock);
+ /* [13] Drop the locks */
raw_spin_unlock_irqrestore(&task->pi_lock, flags);
-
- top_waiter = rt_mutex_top_waiter(lock);
raw_spin_unlock(&lock->wait_lock);
/*
+ * Make the actual exit decisions [12], based on the stored
+ * values.
+ *
* We reached the end of the lock chain. Stop right here. No
* point to go back just to figure that out.
*/
if (!next_lock)
goto out_put_task;
+ /*
+ * If the current waiter is not the top waiter on the lock,
+ * then we can stop the chain walk here if we are not in full
+ * deadlock detection mode.
+ */
if (!detect_deadlock && waiter != top_waiter)
goto out_put_task;
@@ -533,76 +743,119 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task,
*
* Must be called with lock->wait_lock held.
*
- * @lock: the lock to be acquired.
- * @task: the task which wants to acquire the lock
- * @waiter: the waiter that is queued to the lock's wait list. (could be NULL)
+ * @lock: The lock to be acquired.
+ * @task: The task which wants to acquire the lock
+ * @waiter: The waiter that is queued to the lock's wait list if the
+ * callsite called task_blocked_on_lock(), otherwise NULL
*/
static int try_to_take_rt_mutex(struct rt_mutex *lock, struct task_struct *task,
- struct rt_mutex_waiter *waiter)
+ struct rt_mutex_waiter *waiter)
{
+ unsigned long flags;
+
/*
- * We have to be careful here if the atomic speedups are
- * enabled, such that, when
- * - no other waiter is on the lock
- * - the lock has been released since we did the cmpxchg
- * the lock can be released or taken while we are doing the
- * checks and marking the lock with RT_MUTEX_HAS_WAITERS.
+ * Before testing whether we can acquire @lock, we set the
+ * RT_MUTEX_HAS_WAITERS bit in @lock->owner. This forces all
+ * other tasks which try to modify @lock into the slow path
+ * and they serialize on @lock->wait_lock.
+ *
+ * The RT_MUTEX_HAS_WAITERS bit can have a transitional state
+ * as explained at the top of this file if and only if:
*
- * The atomic acquire/release aware variant of
- * mark_rt_mutex_waiters uses a cmpxchg loop. After setting
- * the WAITERS bit, the atomic release / acquire can not
- * happen anymore and lock->wait_lock protects us from the
- * non-atomic case.
+ * - There is a lock owner. The caller must fixup the
+ * transient state if it does a trylock or leaves the lock
+ * function due to a signal or timeout.
*
- * Note, that this might set lock->owner =
- * RT_MUTEX_HAS_WAITERS in the case the lock is not contended
- * any more. This is fixed up when we take the ownership.
- * This is the transitional state explained at the top of this file.
+ * - @task acquires the lock and there are no other
+ * waiters. This is undone in rt_mutex_set_owner(@task) at
+ * the end of this function.
*/
mark_rt_mutex_waiters(lock);
+ /*
+ * If @lock has an owner, give up.
+ */
if (rt_mutex_owner(lock))
return 0;
/*
- * It will get the lock because of one of these conditions:
- * 1) there is no waiter
- * 2) higher priority than waiters
- * 3) it is top waiter
+ * If @waiter != NULL, @task has already enqueued the waiter
+ * into @lock waiter list. If @waiter == NULL then this is a
+ * trylock attempt.
*/
- if (rt_mutex_has_waiters(lock)) {
- if (task->prio >= rt_mutex_top_waiter(lock)->prio) {
- if (!waiter || waiter != rt_mutex_top_waiter(lock))
- return 0;
- }
- }
-
- if (waiter || rt_mutex_has_waiters(lock)) {
- unsigned long flags;
- struct rt_mutex_waiter *top;
-
- raw_spin_lock_irqsave(&task->pi_lock, flags);
+ if (waiter) {
+ /*
+ * If waiter is not the highest priority waiter of
+ * @lock, give up.
+ */
+ if (waiter != rt_mutex_top_waiter(lock))
+ return 0;
- /* remove the queued waiter. */
- if (waiter) {
- rt_mutex_dequeue(lock, waiter);
- task->pi_blocked_on = NULL;
- }
+ /*
+ * We can acquire the lock. Remove the waiter from the
+ * lock waiters list.
+ */
+ rt_mutex_dequeue(lock, waiter);
+ } else {
/*
- * We have to enqueue the top waiter(if it exists) into
- * task->pi_waiters list.
+ * If the lock has waiters already we check whether @task is
+ * eligible to take over the lock.
+ *
+ * If there are no other waiters, @task can acquire
+ * the lock. @task->pi_blocked_on is NULL, so it does
+ * not need to be dequeued.
*/
if (rt_mutex_has_waiters(lock)) {
- top = rt_mutex_top_waiter(lock);
- rt_mutex_enqueue_pi(task, top);
+ /*
+ * If @task->prio is greater than or equal to
+ * the top waiter priority (kernel view),
+ * @task lost.
+ */
+ if (task->prio >= rt_mutex_top_waiter(lock)->prio)
+ return 0;
+
+ /*
+ * The current top waiter stays enqueued. We
+ * don't have to change anything in the lock
+ * waiters order.
+ */
+ } else {
+ /*
+ * No waiters. Take the lock without the
+ * pi_lock dance.@task->pi_blocked_on is NULL
+ * and we have no waiters to enqueue in @task
+ * pi waiters list.
+ */
+ goto takeit;
}
- raw_spin_unlock_irqrestore(&task->pi_lock, flags);
}
+ /*
+ * Clear @task->pi_blocked_on. Requires protection by
+ * @task->pi_lock. Redundant operation for the @waiter == NULL
+ * case, but conditionals are more expensive than a redundant
+ * store.
+ */
+ raw_spin_lock_irqsave(&task->pi_lock, flags);
+ task->pi_blocked_on = NULL;
+ /*
+ * Finish the lock acquisition. @task is the new owner. If
+ * other waiters exist we have to insert the highest priority
+ * waiter into @task->pi_waiters list.
+ */
+ if (rt_mutex_has_waiters(lock))
+ rt_mutex_enqueue_pi(task, rt_mutex_top_waiter(lock));
+ raw_spin_unlock_irqrestore(&task->pi_lock, flags);
+
+takeit:
/* We got the lock. */
debug_rt_mutex_lock(lock);
+ /*
+ * This either preserves the RT_MUTEX_HAS_WAITERS bit if there
+ * are still waiters or clears it.
+ */
rt_mutex_set_owner(lock, task);
rt_mutex_deadlock_account_lock(lock, task);
@@ -620,7 +873,7 @@ static int try_to_take_rt_mutex(struct rt_mutex *lock, struct task_struct *task,
static int task_blocks_on_rt_mutex(struct rt_mutex *lock,
struct rt_mutex_waiter *waiter,
struct task_struct *task,
- int detect_deadlock)
+ enum rtmutex_chainwalk chwalk)
{
struct task_struct *owner = rt_mutex_owner(lock);
struct rt_mutex_waiter *top_waiter = waiter;
@@ -666,7 +919,7 @@ static int task_blocks_on_rt_mutex(struct rt_mutex *lock,
__rt_mutex_adjust_prio(owner);
if (owner->pi_blocked_on)
chain_walk = 1;
- } else if (debug_rt_mutex_detect_deadlock(waiter, detect_deadlock)) {
+ } else if (rt_mutex_cond_detect_deadlock(waiter, chwalk)) {
chain_walk = 1;
}
@@ -691,7 +944,7 @@ static int task_blocks_on_rt_mutex(struct rt_mutex *lock,
raw_spin_unlock(&lock->wait_lock);
- res = rt_mutex_adjust_prio_chain(owner, detect_deadlock, lock,
+ res = rt_mutex_adjust_prio_chain(owner, chwalk, lock,
next_lock, waiter, task);
raw_spin_lock(&lock->wait_lock);
@@ -753,9 +1006,9 @@ static void wakeup_next_waiter(struct rt_mutex *lock)
static void remove_waiter(struct rt_mutex *lock,
struct rt_mutex_waiter *waiter)
{
- int first = (waiter == rt_mutex_top_waiter(lock));
+ bool is_top_waiter = (waiter == rt_mutex_top_waiter(lock));
struct task_struct *owner = rt_mutex_owner(lock);
- struct rt_mutex *next_lock = NULL;
+ struct rt_mutex *next_lock;
unsigned long flags;
raw_spin_lock_irqsave(¤t->pi_lock, flags);
@@ -763,29 +1016,31 @@ static void remove_waiter(struct rt_mutex *lock,
current->pi_blocked_on = NULL;
raw_spin_unlock_irqrestore(¤t->pi_lock, flags);
- if (!owner)
+ /*
+ * Only update priority if the waiter was the highest priority
+ * waiter of the lock and there is an owner to update.
+ */
+ if (!owner || !is_top_waiter)
return;
- if (first) {
-
- raw_spin_lock_irqsave(&owner->pi_lock, flags);
+ raw_spin_lock_irqsave(&owner->pi_lock, flags);
- rt_mutex_dequeue_pi(owner, waiter);
+ rt_mutex_dequeue_pi(owner, waiter);
- if (rt_mutex_has_waiters(lock)) {
- struct rt_mutex_waiter *next;
+ if (rt_mutex_has_waiters(lock))
+ rt_mutex_enqueue_pi(owner, rt_mutex_top_waiter(lock));
- next = rt_mutex_top_waiter(lock);
- rt_mutex_enqueue_pi(owner, next);
- }
- __rt_mutex_adjust_prio(owner);
+ __rt_mutex_adjust_prio(owner);
- /* Store the lock on which owner is blocked or NULL */
- next_lock = task_blocked_on_lock(owner);
+ /* Store the lock on which owner is blocked or NULL */
+ next_lock = task_blocked_on_lock(owner);
- raw_spin_unlock_irqrestore(&owner->pi_lock, flags);
- }
+ raw_spin_unlock_irqrestore(&owner->pi_lock, flags);
+ /*
+ * Don't walk the chain, if the owner task is not blocked
+ * itself.
+ */
if (!next_lock)
return;
@@ -794,7 +1049,8 @@ static void remove_waiter(struct rt_mutex *lock,
raw_spin_unlock(&lock->wait_lock);
- rt_mutex_adjust_prio_chain(owner, 0, lock, next_lock, NULL, current);
+ rt_mutex_adjust_prio_chain(owner, RT_MUTEX_MIN_CHAINWALK, lock,
+ next_lock, NULL, current);
raw_spin_lock(&lock->wait_lock);
}
@@ -824,7 +1080,8 @@ void rt_mutex_adjust_pi(struct task_struct *task)
/* gets dropped in rt_mutex_adjust_prio_chain()! */
get_task_struct(task);
- rt_mutex_adjust_prio_chain(task, 0, NULL, next_lock, NULL, task);
+ rt_mutex_adjust_prio_chain(task, RT_MUTEX_MIN_CHAINWALK, NULL,
+ next_lock, NULL, task);
}
/**
@@ -902,7 +1159,7 @@ static void rt_mutex_handle_deadlock(int res, int detect_deadlock,
static int __sched
rt_mutex_slowlock(struct rt_mutex *lock, int state,
struct hrtimer_sleeper *timeout,
- int detect_deadlock)
+ enum rtmutex_chainwalk chwalk)
{
struct rt_mutex_waiter waiter;
int ret = 0;
@@ -928,7 +1185,7 @@ rt_mutex_slowlock(struct rt_mutex *lock, int state,
timeout->task = NULL;
}
- ret = task_blocks_on_rt_mutex(lock, &waiter, current, detect_deadlock);
+ ret = task_blocks_on_rt_mutex(lock, &waiter, current, chwalk);
if (likely(!ret))
ret = __rt_mutex_slowlock(lock, state, timeout, &waiter);
@@ -937,7 +1194,7 @@ rt_mutex_slowlock(struct rt_mutex *lock, int state,
if (unlikely(ret)) {
remove_waiter(lock, &waiter);
- rt_mutex_handle_deadlock(ret, detect_deadlock, &waiter);
+ rt_mutex_handle_deadlock(ret, chwalk, &waiter);
}
/*
@@ -960,22 +1217,31 @@ rt_mutex_slowlock(struct rt_mutex *lock, int state,
/*
* Slow path try-lock function:
*/
-static inline int
-rt_mutex_slowtrylock(struct rt_mutex *lock)
+static inline int rt_mutex_slowtrylock(struct rt_mutex *lock)
{
- int ret = 0;
+ int ret;
+
+ /*
+ * If the lock already has an owner we fail to get the lock.
+ * This can be done without taking the @lock->wait_lock as
+ * it is only being read, and this is a trylock anyway.
+ */
+ if (rt_mutex_owner(lock))
+ return 0;
+ /*
+ * The mutex has currently no owner. Lock the wait lock and
+ * try to acquire the lock.
+ */
raw_spin_lock(&lock->wait_lock);
- if (likely(rt_mutex_owner(lock) != current)) {
+ ret = try_to_take_rt_mutex(lock, current, NULL);
- ret = try_to_take_rt_mutex(lock, current, NULL);
- /*
- * try_to_take_rt_mutex() sets the lock waiters
- * bit unconditionally. Clean this up.
- */
- fixup_rt_mutex_waiters(lock);
- }
+ /*
+ * try_to_take_rt_mutex() sets the lock waiters bit
+ * unconditionally. Clean this up.
+ */
+ fixup_rt_mutex_waiters(lock);
raw_spin_unlock(&lock->wait_lock);
@@ -1053,30 +1319,31 @@ rt_mutex_slowunlock(struct rt_mutex *lock)
*/
static inline int
rt_mutex_fastlock(struct rt_mutex *lock, int state,
- int detect_deadlock,
int (*slowfn)(struct rt_mutex *lock, int state,
struct hrtimer_sleeper *timeout,
- int detect_deadlock))
+ enum rtmutex_chainwalk chwalk))
{
- if (!detect_deadlock && likely(rt_mutex_cmpxchg(lock, NULL, current))) {
+ if (likely(rt_mutex_cmpxchg(lock, NULL, current))) {
rt_mutex_deadlock_account_lock(lock, current);
return 0;
} else
- return slowfn(lock, state, NULL, detect_deadlock);
+ return slowfn(lock, state, NULL, RT_MUTEX_MIN_CHAINWALK);
}
static inline int
rt_mutex_timed_fastlock(struct rt_mutex *lock, int state,
- struct hrtimer_sleeper *timeout, int detect_deadlock,
+ struct hrtimer_sleeper *timeout,
+ enum rtmutex_chainwalk chwalk,
int (*slowfn)(struct rt_mutex *lock, int state,
struct hrtimer_sleeper *timeout,
- int detect_deadlock))
+ enum rtmutex_chainwalk chwalk))
{
- if (!detect_deadlock && likely(rt_mutex_cmpxchg(lock, NULL, current))) {
+ if (chwalk == RT_MUTEX_MIN_CHAINWALK &&
+ likely(rt_mutex_cmpxchg(lock, NULL, current))) {
rt_mutex_deadlock_account_lock(lock, current);
return 0;
} else
- return slowfn(lock, state, timeout, detect_deadlock);
+ return slowfn(lock, state, timeout, chwalk);
}
static inline int
@@ -1109,54 +1376,61 @@ void __sched rt_mutex_lock(struct rt_mutex *lock)
{
might_sleep();
- rt_mutex_fastlock(lock, TASK_UNINTERRUPTIBLE, 0, rt_mutex_slowlock);
+ rt_mutex_fastlock(lock, TASK_UNINTERRUPTIBLE, rt_mutex_slowlock);
}
EXPORT_SYMBOL_GPL(rt_mutex_lock);
/**
* rt_mutex_lock_interruptible - lock a rt_mutex interruptible
*
- * @lock: the rt_mutex to be locked
- * @detect_deadlock: deadlock detection on/off
+ * @lock: the rt_mutex to be locked
*
* Returns:
- * 0 on success
- * -EINTR when interrupted by a signal
- * -EDEADLK when the lock would deadlock (when deadlock detection is on)
+ * 0 on success
+ * -EINTR when interrupted by a signal
*/
-int __sched rt_mutex_lock_interruptible(struct rt_mutex *lock,
- int detect_deadlock)
+int __sched rt_mutex_lock_interruptible(struct rt_mutex *lock)
{
might_sleep();
- return rt_mutex_fastlock(lock, TASK_INTERRUPTIBLE,
- detect_deadlock, rt_mutex_slowlock);
+ return rt_mutex_fastlock(lock, TASK_INTERRUPTIBLE, rt_mutex_slowlock);
}
EXPORT_SYMBOL_GPL(rt_mutex_lock_interruptible);
+/*
+ * Futex variant with full deadlock detection.
+ */
+int rt_mutex_timed_futex_lock(struct rt_mutex *lock,
+ struct hrtimer_sleeper *timeout)
+{
+ might_sleep();
+
+ return rt_mutex_timed_fastlock(lock, TASK_INTERRUPTIBLE, timeout,
+ RT_MUTEX_FULL_CHAINWALK,
+ rt_mutex_slowlock);
+}
+
/**
* rt_mutex_timed_lock - lock a rt_mutex interruptible
* the timeout structure is provided
* by the caller
*
- * @lock: the rt_mutex to be locked
+ * @lock: the rt_mutex to be locked
* @timeout: timeout structure or NULL (no timeout)
- * @detect_deadlock: deadlock detection on/off
*
* Returns:
- * 0 on success
- * -EINTR when interrupted by a signal
+ * 0 on success
+ * -EINTR when interrupted by a signal
* -ETIMEDOUT when the timeout expired
- * -EDEADLK when the lock would deadlock (when deadlock detection is on)
*/
int
-rt_mutex_timed_lock(struct rt_mutex *lock, struct hrtimer_sleeper *timeout,
- int detect_deadlock)
+rt_mutex_timed_lock(struct rt_mutex *lock, struct hrtimer_sleeper *timeout)
{
might_sleep();
return rt_mutex_timed_fastlock(lock, TASK_INTERRUPTIBLE, timeout,
- detect_deadlock, rt_mutex_slowlock);
+ RT_MUTEX_MIN_CHAINWALK,
+ rt_mutex_slowlock);
}
EXPORT_SYMBOL_GPL(rt_mutex_timed_lock);
@@ -1262,7 +1536,6 @@ void rt_mutex_proxy_unlock(struct rt_mutex *lock,
* @lock: the rt_mutex to take
* @waiter: the pre-initialized rt_mutex_waiter
* @task: the task to prepare
- * @detect_deadlock: perform deadlock detection (1) or not (0)
*
* Returns:
* 0 - task blocked on lock
@@ -1273,7 +1546,7 @@ void rt_mutex_proxy_unlock(struct rt_mutex *lock,
*/
int rt_mutex_start_proxy_lock(struct rt_mutex *lock,
struct rt_mutex_waiter *waiter,
- struct task_struct *task, int detect_deadlock)
+ struct task_struct *task)
{
int ret;
@@ -1285,7 +1558,8 @@ int rt_mutex_start_proxy_lock(struct rt_mutex *lock,
}
/* We enforce deadlock detection for futexes */
- ret = task_blocks_on_rt_mutex(lock, waiter, task, 1);
+ ret = task_blocks_on_rt_mutex(lock, waiter, task,
+ RT_MUTEX_FULL_CHAINWALK);
if (ret && !rt_mutex_owner(lock)) {
/*
@@ -1331,22 +1605,20 @@ struct task_struct *rt_mutex_next_owner(struct rt_mutex *lock)
* rt_mutex_finish_proxy_lock() - Complete lock acquisition
* @lock: the rt_mutex we were woken on
* @to: the timeout, null if none. hrtimer should already have
- * been started.
+ * been started.
* @waiter: the pre-initialized rt_mutex_waiter
- * @detect_deadlock: perform deadlock detection (1) or not (0)
*
* Complete the lock acquisition started our behalf by another thread.
*
* Returns:
* 0 - success
- * <0 - error, one of -EINTR, -ETIMEDOUT, or -EDEADLK
+ * <0 - error, one of -EINTR, -ETIMEDOUT
*
* Special API call for PI-futex requeue support
*/
int rt_mutex_finish_proxy_lock(struct rt_mutex *lock,
struct hrtimer_sleeper *to,
- struct rt_mutex_waiter *waiter,
- int detect_deadlock)
+ struct rt_mutex_waiter *waiter)
{
int ret;
diff --git a/kernel/locking/rtmutex.h b/kernel/locking/rtmutex.h
index f6a1f3c..c406058 100644
--- a/kernel/locking/rtmutex.h
+++ b/kernel/locking/rtmutex.h
@@ -22,10 +22,15 @@
#define debug_rt_mutex_init(m, n) do { } while (0)
#define debug_rt_mutex_deadlock(d, a ,l) do { } while (0)
#define debug_rt_mutex_print_deadlock(w) do { } while (0)
-#define debug_rt_mutex_detect_deadlock(w,d) (d)
#define debug_rt_mutex_reset_waiter(w) do { } while (0)
static inline void rt_mutex_print_deadlock(struct rt_mutex_waiter *w)
{
WARN(1, "rtmutex deadlock detected\n");
}
+
+static inline bool debug_rt_mutex_detect_deadlock(struct rt_mutex_waiter *w,
+ enum rtmutex_chainwalk walk)
+{
+ return walk == RT_MUTEX_FULL_CHAINWALK;
+}
diff --git a/kernel/locking/rtmutex_common.h b/kernel/locking/rtmutex_common.h
index 7431a9c..8552125 100644
--- a/kernel/locking/rtmutex_common.h
+++ b/kernel/locking/rtmutex_common.h
@@ -102,6 +102,21 @@ static inline struct task_struct *rt_mutex_owner(struct rt_mutex *lock)
}
/*
+ * Constants for rt mutex functions which have a selectable deadlock
+ * detection.
+ *
+ * RT_MUTEX_MIN_CHAINWALK: Stops the lock chain walk when there are
+ * no further PI adjustments to be made.
+ *
+ * RT_MUTEX_FULL_CHAINWALK: Invoke deadlock detection with a full
+ * walk of the lock chain.
+ */
+enum rtmutex_chainwalk {
+ RT_MUTEX_MIN_CHAINWALK,
+ RT_MUTEX_FULL_CHAINWALK,
+};
+
+/*
* PI-futex support (proxy locking functions, etc.):
*/
extern struct task_struct *rt_mutex_next_owner(struct rt_mutex *lock);
@@ -111,12 +126,11 @@ extern void rt_mutex_proxy_unlock(struct rt_mutex *lock,
struct task_struct *proxy_owner);
extern int rt_mutex_start_proxy_lock(struct rt_mutex *lock,
struct rt_mutex_waiter *waiter,
- struct task_struct *task,
- int detect_deadlock);
+ struct task_struct *task);
extern int rt_mutex_finish_proxy_lock(struct rt_mutex *lock,
struct hrtimer_sleeper *to,
- struct rt_mutex_waiter *waiter,
- int detect_deadlock);
+ struct rt_mutex_waiter *waiter);
+extern int rt_mutex_timed_futex_lock(struct rt_mutex *l, struct hrtimer_sleeper *to);
#ifdef CONFIG_DEBUG_RT_MUTEXES
# include "rtmutex-debug.h"
diff --git a/kernel/locking/rwsem-xadd.c b/kernel/locking/rwsem-xadd.c
index a2391ac..d6203fa 100644
--- a/kernel/locking/rwsem-xadd.c
+++ b/kernel/locking/rwsem-xadd.c
@@ -329,7 +329,7 @@ bool rwsem_spin_on_owner(struct rw_semaphore *sem, struct task_struct *owner)
if (need_resched())
break;
- arch_mutex_cpu_relax();
+ cpu_relax_lowlatency();
}
rcu_read_unlock();
@@ -381,7 +381,7 @@ static bool rwsem_optimistic_spin(struct rw_semaphore *sem)
* memory barriers as we'll eventually observe the right
* values at the cost of a few extra spins.
*/
- arch_mutex_cpu_relax();
+ cpu_relax_lowlatency();
}
osq_unlock(&sem->osq);
done:
diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index 7a638aa..f488bef 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -835,7 +835,7 @@ config DEBUG_RT_MUTEXES
config RT_MUTEX_TESTER
bool "Built-in scriptable tester for rt-mutexes"
- depends on DEBUG_KERNEL && RT_MUTEXES
+ depends on DEBUG_KERNEL && RT_MUTEXES && BROKEN
help
This option enables a rt-mutex tester.
diff --git a/lib/lockref.c b/lib/lockref.c
index f07a40d..d2233de 100644
--- a/lib/lockref.c
+++ b/lib/lockref.c
@@ -1,6 +1,5 @@
#include <linux/export.h>
#include <linux/lockref.h>
-#include <linux/mutex.h>
#if USE_CMPXCHG_LOCKREF
@@ -29,7 +28,7 @@
if (likely(old.lock_count == prev.lock_count)) { \
SUCCESS; \
} \
- arch_mutex_cpu_relax(); \
+ cpu_relax_lowlatency(); \
} \
} while (0)
^ permalink raw reply related [flat|nested] only message in thread
only message in thread, other threads:[~2014-08-04 9:43 UTC | newest]
Thread overview: (only message) (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2014-08-04 9:43 [GIT PULL] locking tree updates for v3.17 Ingo Molnar
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.