| Age | Commit message (Collapse) | Author |
|---|
|
There are currently several problems in -rt w.r.t. seqlock objects. RT
moves mainline seqlock_t to "raw_seqlock_t", and creates a new seqlock_t
object that is fully preemptible. Being preemptible is a great step
towards deterministic behavior, but there are a few areas that need
additional measures to protect new vulnerabilities created by the
preemptible code. For the purposes of demonstration, consider three tasks
of different priority: A, B, and C. A is the logically highest, and C is
the lowest. A is trying to acquire a seqlock read critical section, while
C is involved in write locks.
Problem 1) If A spins in seqbegin due to writer contention retries, it may
prevent C from running even if C currently holds the write lock. This
is a deadlock.
Problem 2) B may preempt C, preventing it from releasing the write
critical section. In this case, A becomes inverted behind B.
Problem 3) Lower priority tasks such as C may continually acquire the write
section which subsequently causes A to continually retry and thus fail to
make forward progress. Since C is lower priority it ideally should not
cause delays in A. E.g. C should block if A is in a read-lock and C is <= A.
This patch addresses Problems 1 & 2, and leaves 3 for a later time.
This patch changes the internal seqlock_t implementation to substitute
a rwlock for the basic spinlock previously used, and forces the readers
to serialize with the writers under contention. Blocking on the read_lock
simultaneously sleeps A (preventing problem 1), while boosting C to A's
priority (preventing problem 2). Non reader-to-writer contended
acquisitions, which are the predominant mode, remain free of atomic
operations. Therefore the fast path should not be perturbed by this
change.
This fixes a real-world deadlock discovered under testing where all
high priority readers were hogging the cpus and preventing a writer
from releasing the lock (i.e. problem 1).
Signed-off-by: Gregory Haskins <ghaskins@novell.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
|
|
atomic_seqlock_t will be used to annotate seqlocks which can not be
converted to sleeping locks in preempt-rt
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
|
|
Thomas Gleixner debugged a particularly ugly seqlock related livelock:
do not process the seq-read section if we know it beforehand that the
test at the end of the section will fail ...
Signed-off-by: Ingo Molnar <mingo@elte.hu>
|
|
Signed-off-by: Daniel Walker <dwalker@mvista.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
|
|
Correct mis-spellings of "algorithm", "appear", "consistent" and
(shame, shame) "kernel".
Signed-off-by: Robert P. J. Day <rpjday@mindspring.com>
Signed-off-by: Adrian Bunk <bunk@stusta.de>
|
|
seqlock_init() needs to use spin_lock_init() for dynamic locks, so that
lockdep is notified about the presence of a new lock.
(this is a fallout of the recent networking merge, which started using
the so-far unused seqlock_init() API.)
This fix solves the following lockdep-internal warning on current -git:
INFO: trying to register non-static key.
the code is fine but needs lockdep annotation.
turning off the locking correctness validator.
__lock_acquire+0x10c/0x9f9
lock_acquire+0x56/0x72
_spin_lock+0x35/0x42
neigh_destroy+0x9d/0x12e
neigh_periodic_timer+0x10a/0x15c
run_timer_softirq+0x126/0x18e
__do_softirq+0x6b/0xe6
do_softirq+0x64/0xd2
ksoftirqd+0x82/0x138
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
|
|
Locking init improvement:
- introduce and use __SPIN_LOCK_UNLOCKED for array initializations,
to pass in the name string of locks, used by debugging
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Arjan van de Ven <arjan@linux.intel.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
|
|
Signed-off-by: David Woodhouse <dwmw2@infradead.org>
|
|
In vsyscall function do_vgettimeofday(), some functions are declared as
inlined, which is a hint for gcc to compile the function inlined but it
not forced. Sometimes compiler does not compile the function as
inlined, so here inline is replaced by __always_inline prefix.
It does not happen in gcc compiler actually, but it possibly happens.
Signed-off-by: bibo mao <bibo.mao@intel.com>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
|
|
Initial git repository build. I'm not bothering with the full history,
even though we have it. We can create a separate "historical" git
archive of that later if we want to, and in the meantime it's about
3.2GB when imported into git - space that would just make the early
git days unnecessarily complicated, when we don't have a lot of good
infrastructure for it.
Let it rip!
|
