[PATCH v2 2/3] job: take each job's lock individually in job_txn_apply

[Stefan Reiter]

All callers of job_txn_apply hold a single job's lock, but different
jobs within a transaction can have different contexts, thus we need to
lock each one individually before applying the callback function.

Similar to job_completed_txn_abort this also requires releasing the
caller's context before and reacquiring it after to avoid recursive
locks which might break AIO_WAIT_WHILE in the callback.

Signed-off-by: Stefan Reiter <address@hidden>
---
 job.c | 32 ++++++++++++++++++++++++--------
 1 file changed, 24 insertions(+), 8 deletions(-)

diff --git a/job.c b/job.c
index 134a07b92e..e0966162fa 100644
--- a/job.c
+++ b/job.c
@@ -136,17 +136,33 @@ static void job_txn_del_job(Job *job)
     }
 }
 
-static int job_txn_apply(JobTxn *txn, int fn(Job *))
+static int job_txn_apply(Job *job, int fn(Job *))
 {
-    Job *job, *next;
+    AioContext *outer_ctx = job->aio_context;
+    AioContext *inner_ctx;
+    Job *other_job, *next;
+    JobTxn *txn = job->txn;
     int rc = 0;
 
-    QLIST_FOREACH_SAFE(job, &txn->jobs, txn_list, next) {
-        rc = fn(job);
+    /*
+     * Similar to job_completed_txn_abort, we take each job's lock before
+     * applying fn, but since we assume that outer_ctx is held by the caller,
+     * we need to release it here to avoid holding the lock twice - which would
+     * break AIO_WAIT_WHILE from within fn.
+     */
+    aio_context_release(outer_ctx);
+
+    QLIST_FOREACH_SAFE(other_job, &txn->jobs, txn_list, next) {
+        inner_ctx = other_job->aio_context;
+        aio_context_acquire(inner_ctx);
+        rc = fn(other_job);
+        aio_context_release(inner_ctx);
         if (rc) {
             break;
         }
     }
+
+    aio_context_acquire(outer_ctx);
     return rc;
 }
 
@@ -774,11 +790,11 @@ static void job_do_finalize(Job *job)
     assert(job && job->txn);
 
     /* prepare the transaction to complete */
-    rc = job_txn_apply(job->txn, job_prepare);
+    rc = job_txn_apply(job, job_prepare);
     if (rc) {
         job_completed_txn_abort(job);
     } else {
-        job_txn_apply(job->txn, job_finalize_single);
+        job_txn_apply(job, job_finalize_single);
     }
 }
 
@@ -824,10 +840,10 @@ static void job_completed_txn_success(Job *job)
         assert(other_job->ret == 0);
     }
 
-    job_txn_apply(txn, job_transition_to_pending);
+    job_txn_apply(job, job_transition_to_pending);
 
     /* If no jobs need manual finalization, automatically do so */
-    if (job_txn_apply(txn, job_needs_finalize) == 0) {
+    if (job_txn_apply(job, job_needs_finalize) == 0) {
         job_do_finalize(job);
     }
 }
-- 
2.26.0