seqlock: PREEMPT_RT: Do not starve seqlock_t writers

On PREEMPT_RT, seqlock_t is transformed to a sleeping lock that do not
disable preemption. A seqlock_t reader can thus preempt its write side
section and spin for the enter scheduler tick. If that reader belongs to
a real-time scheduling class, it can spin forever and the kernel will
livelock.

To break this livelock possibility on PREEMPT_RT, implement seqlock_t in
terms of "seqcount_spinlock_t" instead of plain "seqcount_t".

Beside its pure annotational value, this will leverage the existing
seqcount_LOCKNAME_T PREEMPT_RT anti-livelock mechanisms, without adding
any extra code.

Signed-off-by: Ahmed S. Darwish <a.darwish@linutronix.de>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20200904153231.11994-6-a.darwish@linutronix.de
This commit is contained in:
Ahmed S. Darwish 2020-09-04 17:32:31 +02:00 committed by Peter Zijlstra
parent 8117ab508f
commit 1909760f5f
1 changed files with 21 additions and 11 deletions

View File

@ -790,13 +790,17 @@ static inline void raw_write_seqcount_latch(seqcount_latch_t *s)
* - Documentation/locking/seqlock.rst
*/
typedef struct {
struct seqcount seqcount;
/*
* Make sure that readers don't starve writers on PREEMPT_RT: use
* seqcount_spinlock_t instead of seqcount_t. Check __SEQ_LOCK().
*/
seqcount_spinlock_t seqcount;
spinlock_t lock;
} seqlock_t;
#define __SEQLOCK_UNLOCKED(lockname) \
{ \
.seqcount = SEQCNT_ZERO(lockname), \
.seqcount = SEQCNT_SPINLOCK_ZERO(lockname, &(lockname).lock), \
.lock = __SPIN_LOCK_UNLOCKED(lockname) \
}
@ -806,8 +810,8 @@ typedef struct {
*/
#define seqlock_init(sl) \
do { \
seqcount_init(&(sl)->seqcount); \
spin_lock_init(&(sl)->lock); \
seqcount_spinlock_init(&(sl)->seqcount, &(sl)->lock); \
} while (0)
/**
@ -854,6 +858,12 @@ static inline unsigned read_seqretry(const seqlock_t *sl, unsigned start)
return read_seqcount_retry(&sl->seqcount, start);
}
/*
* For all seqlock_t write side functions, use write_seqcount_*t*_begin()
* instead of the generic write_seqcount_begin(). This way, no redundant
* lockdep_assert_held() checks are added.
*/
/**
* write_seqlock() - start a seqlock_t write side critical section
* @sl: Pointer to seqlock_t
@ -870,7 +880,7 @@ static inline unsigned read_seqretry(const seqlock_t *sl, unsigned start)
static inline void write_seqlock(seqlock_t *sl)
{
spin_lock(&sl->lock);
write_seqcount_t_begin(&sl->seqcount);
write_seqcount_t_begin(&sl->seqcount.seqcount);
}
/**
@ -882,7 +892,7 @@ static inline void write_seqlock(seqlock_t *sl)
*/
static inline void write_sequnlock(seqlock_t *sl)
{
write_seqcount_t_end(&sl->seqcount);
write_seqcount_t_end(&sl->seqcount.seqcount);
spin_unlock(&sl->lock);
}
@ -896,7 +906,7 @@ static inline void write_sequnlock(seqlock_t *sl)
static inline void write_seqlock_bh(seqlock_t *sl)
{
spin_lock_bh(&sl->lock);
write_seqcount_t_begin(&sl->seqcount);
write_seqcount_t_begin(&sl->seqcount.seqcount);
}
/**
@ -909,7 +919,7 @@ static inline void write_seqlock_bh(seqlock_t *sl)
*/
static inline void write_sequnlock_bh(seqlock_t *sl)
{
write_seqcount_t_end(&sl->seqcount);
write_seqcount_t_end(&sl->seqcount.seqcount);
spin_unlock_bh(&sl->lock);
}
@ -923,7 +933,7 @@ static inline void write_sequnlock_bh(seqlock_t *sl)
static inline void write_seqlock_irq(seqlock_t *sl)
{
spin_lock_irq(&sl->lock);
write_seqcount_t_begin(&sl->seqcount);
write_seqcount_t_begin(&sl->seqcount.seqcount);
}
/**
@ -935,7 +945,7 @@ static inline void write_seqlock_irq(seqlock_t *sl)
*/
static inline void write_sequnlock_irq(seqlock_t *sl)
{
write_seqcount_t_end(&sl->seqcount);
write_seqcount_t_end(&sl->seqcount.seqcount);
spin_unlock_irq(&sl->lock);
}
@ -944,7 +954,7 @@ static inline unsigned long __write_seqlock_irqsave(seqlock_t *sl)
unsigned long flags;
spin_lock_irqsave(&sl->lock, flags);
write_seqcount_t_begin(&sl->seqcount);
write_seqcount_t_begin(&sl->seqcount.seqcount);
return flags;
}
@ -973,7 +983,7 @@ static inline unsigned long __write_seqlock_irqsave(seqlock_t *sl)
static inline void
write_sequnlock_irqrestore(seqlock_t *sl, unsigned long flags)
{
write_seqcount_t_end(&sl->seqcount);
write_seqcount_t_end(&sl->seqcount.seqcount);
spin_unlock_irqrestore(&sl->lock, flags);
}