summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
-rw-r--r--kernel/locking/qspinlock.c57
1 files changed, 57 insertions, 0 deletions
diff --git a/kernel/locking/qspinlock.c b/kernel/locking/qspinlock.c
index ee7deb08d43d..2f9153b183c9 100644
--- a/kernel/locking/qspinlock.c
+++ b/kernel/locking/qspinlock.c
@@ -268,6 +268,63 @@ static __always_inline u32 __pv_wait_head_or_lock(struct qspinlock *lock,
#endif
/*
+ * Various notes on spin_is_locked() and spin_unlock_wait(), which are
+ * 'interesting' functions:
+ *
+ * PROBLEM: some architectures have an interesting issue with atomic ACQUIRE
+ * operations in that the ACQUIRE applies to the LOAD _not_ the STORE (ARM64,
+ * PPC). Also qspinlock has a similar issue per construction, the setting of
+ * the locked byte can be unordered acquiring the lock proper.
+ *
+ * This gets to be 'interesting' in the following cases, where the /should/s
+ * end up false because of this issue.
+ *
+ *
+ * CASE 1:
+ *
+ * So the spin_is_locked() correctness issue comes from something like:
+ *
+ * CPU0 CPU1
+ *
+ * global_lock(); local_lock(i)
+ * spin_lock(&G) spin_lock(&L[i])
+ * for (i) if (!spin_is_locked(&G)) {
+ * spin_unlock_wait(&L[i]); smp_acquire__after_ctrl_dep();
+ * return;
+ * }
+ * // deal with fail
+ *
+ * Where it is important CPU1 sees G locked or CPU0 sees L[i] locked such
+ * that there is exclusion between the two critical sections.
+ *
+ * The load from spin_is_locked(&G) /should/ be constrained by the ACQUIRE from
+ * spin_lock(&L[i]), and similarly the load(s) from spin_unlock_wait(&L[i])
+ * /should/ be constrained by the ACQUIRE from spin_lock(&G).
+ *
+ * Similarly, later stuff is constrained by the ACQUIRE from CTRL+RMB.
+ *
+ *
+ * CASE 2:
+ *
+ * For spin_unlock_wait() there is a second correctness issue, namely:
+ *
+ * CPU0 CPU1
+ *
+ * flag = set;
+ * smp_mb(); spin_lock(&l)
+ * spin_unlock_wait(&l); if (!flag)
+ * // add to lockless list
+ * spin_unlock(&l);
+ * // iterate lockless list
+ *
+ * Which wants to ensure that CPU1 will stop adding bits to the list and CPU0
+ * will observe the last entry on the list (if spin_unlock_wait() had ACQUIRE
+ * semantics etc..)
+ *
+ * Where flag /should/ be ordered against the locked store of l.
+ */
+
+/*
* queued_spin_lock_slowpath() can (load-)ACQUIRE the lock before
* issuing an _unordered_ store to set _Q_LOCKED_VAL.
*