From 436eef23c41fe10dc34ed19a00caf9f1290a8689 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Thu, 13 May 2021 14:54:58 -0700 Subject: tools/memory-model: Add example for heuristic lockless reads This commit adds example code for heuristic lockless reads, based loosely on the sem_lock() and sem_unlock() functions. [ paulmck: Apply Alan Stern and Manfred Spraul feedback. ] Reported-by: Manfred Spraul [ paulmck: Update per Manfred Spraul and Hillf Danton feedback. ] Signed-off-by: Paul E. McKenney --- .../memory-model/Documentation/access-marking.txt | 93 ++++++++++++++++++++++ 1 file changed, 93 insertions(+) (limited to 'tools/memory-model') diff --git a/tools/memory-model/Documentation/access-marking.txt b/tools/memory-model/Documentation/access-marking.txt index 58bff2619876..d96fe20ed582 100644 --- a/tools/memory-model/Documentation/access-marking.txt +++ b/tools/memory-model/Documentation/access-marking.txt @@ -319,6 +319,99 @@ of the ASSERT_EXCLUSIVE_WRITER() is to allow KCSAN to check for a buggy concurrent lockless write. +Lock-Protected Writes With Heuristic Lockless Reads +--------------------------------------------------- + +For another example, suppose that the code can normally make use of +a per-data-structure lock, but there are times when a global lock +is required. These times are indicated via a global flag. The code +might look as follows, and is based loosely on nf_conntrack_lock(), +nf_conntrack_all_lock(), and nf_conntrack_all_unlock(): + + bool global_flag; + DEFINE_SPINLOCK(global_lock); + struct foo { + spinlock_t f_lock; + int f_data; + }; + + /* All foo structures are in the following array. */ + int nfoo; + struct foo *foo_array; + + void do_something_locked(struct foo *fp) + { + /* This works even if data_race() returns nonsense. */ + if (!data_race(global_flag)) { + spin_lock(&fp->f_lock); + if (!smp_load_acquire(&global_flag)) { + do_something(fp); + spin_unlock(&fp->f_lock); + return; + } + spin_unlock(&fp->f_lock); + } + spin_lock(&global_lock); + /* global_lock held, thus global flag cannot be set. */ + spin_lock(&fp->f_lock); + spin_unlock(&global_lock); + /* + * global_flag might be set here, but begin_global() + * will wait for ->f_lock to be released. + */ + do_something(fp); + spin_unlock(&fp->f_lock); + } + + void begin_global(void) + { + int i; + + spin_lock(&global_lock); + WRITE_ONCE(global_flag, true); + for (i = 0; i < nfoo; i++) { + /* + * Wait for pre-existing local locks. One at + * a time to avoid lockdep limitations. + */ + spin_lock(&fp->f_lock); + spin_unlock(&fp->f_lock); + } + } + + void end_global(void) + { + smp_store_release(&global_flag, false); + spin_unlock(&global_lock); + } + +All code paths leading from the do_something_locked() function's first +read from global_flag acquire a lock, so endless load fusing cannot +happen. + +If the value read from global_flag is true, then global_flag is +rechecked while holding ->f_lock, which, if global_flag is now false, +prevents begin_global() from completing. It is therefore safe to invoke +do_something(). + +Otherwise, if either value read from global_flag is true, then after +global_lock is acquired global_flag must be false. The acquisition of +->f_lock will prevent any call to begin_global() from returning, which +means that it is safe to release global_lock and invoke do_something(). + +For this to work, only those foo structures in foo_array[] may be passed +to do_something_locked(). The reason for this is that the synchronization +with begin_global() relies on momentarily holding the lock of each and +every foo structure. + +The smp_load_acquire() and smp_store_release() are required because +changes to a foo structure between calls to begin_global() and +end_global() are carried out without holding that structure's ->f_lock. +The smp_load_acquire() and smp_store_release() ensure that the next +invocation of do_something() from do_something_locked() will see those +changes. + + Lockless Reads and Writes ------------------------- -- cgit v1.2.3