linux-kernel - [tip: locking/core] seqlock: PREEMPT_RT: Do not starve seqlock

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives
Hash Suite: Windows password security audit tool. GUI, reports in PDF.
[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Date:   Thu, 10 Sep 2020 15:08:23 -0000
From:   "tip-bot2 for Ahmed S. Darwish" <tip-bot2@...utronix.de>
To:     linux-tip-commits@...r.kernel.org
Cc:     "Ahmed S. Darwish" <a.darwish@...utronix.de>,
        "Peter Zijlstra (Intel)" <peterz@...radead.org>,
        x86 <x86@...nel.org>, LKML <linux-kernel@...r.kernel.org>
Subject: [tip: locking/core] seqlock: PREEMPT_RT: Do not starve seqlock_t writers

The following commit has been merged into the locking/core branch of tip:

Commit-ID:     1909760f5fc3f123e47b4e24e0ccdc0fc8f3f106
Gitweb:        https://git.kernel.org/tip/1909760f5fc3f123e47b4e24e0ccdc0fc8f3f106
Author:        Ahmed S. Darwish <a.darwish@...utronix.de>
AuthorDate:    Fri, 04 Sep 2020 17:32:31 +02:00
Committer:     Peter Zijlstra <peterz@...radead.org>
CommitterDate: Thu, 10 Sep 2020 11:19:31 +02:00

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@...utronix.de>
Signed-off-by: Peter Zijlstra (Intel) <peterz@...radead.org>
Link: https://lkml.kernel.org/r/20200904153231.11994-6-a.darwish@linutronix.de
---
 include/linux/seqlock.h | 32 +++++++++++++++++++++-----------
 1 file changed, 21 insertions(+), 11 deletions(-)

diff --git a/include/linux/seqlock.h b/include/linux/seqlock.h
index 2bc9510..f73c7eb 100644
--- a/include/linux/seqlock.h
+++ b/include/linux/seqlock.h
@@ -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);
 }