FS-Cache: Permit cache retrieval ops to be interrupted in the initial wait phase

Permit the operations to retrieve data from the cache or to allocate space in
the cache for future writes to be interrupted whilst they're waiting for
permission for the operation to proceed.  Typically this wait occurs whilst the
cache object is being looked up on disk in the background.

If an interruption occurs, and the operation has not yet been given the
go-ahead to run, the operation is dequeued and cancelled, and control returns
to the read operation of the netfs routine with none of the requested pages
having been read or in any way marked as known by the cache.

This means that the initial wait is done interruptibly rather than
uninterruptibly.

In addition, extra stats values are made available to show the number of ops
cancelled and the number of cache space allocations interrupted.

Signed-off-by: David Howells <dhowells@redhat.com>

4 files changed, 113 insertions, 39 deletions

diff --git a/fs/fscache/internal.h b/fs/fscache/internal.h
index b85cc8906818..50324ad2b194 100644
--- a/fs/fscache/internal.h
+++ b/fs/fscache/internal.h
@@ -112,6 +112,7 @@ extern int fscache_submit_exclusive_op(struct fscache_object *,
                                        struct fscache_operation *);
 extern int fscache_submit_op(struct fscache_object *,
                              struct fscache_operation *);
+extern int fscache_cancel_op(struct fscache_operation *);
 extern void fscache_abort_object(struct fscache_object *);
 extern void fscache_start_operations(struct fscache_object *);
 extern void fscache_operation_gc(struct work_struct *);
@@ -140,6 +141,7 @@ extern atomic_t fscache_n_op_enqueue;
 extern atomic_t fscache_n_op_deferred_release;
 extern atomic_t fscache_n_op_release;
 extern atomic_t fscache_n_op_gc;
+extern atomic_t fscache_n_op_cancelled;
 
 extern atomic_t fscache_n_attr_changed;
 extern atomic_t fscache_n_attr_changed_ok;
@@ -151,6 +153,7 @@ extern atomic_t fscache_n_allocs;
 extern atomic_t fscache_n_allocs_ok;
 extern atomic_t fscache_n_allocs_wait;
 extern atomic_t fscache_n_allocs_nobufs;
+extern atomic_t fscache_n_allocs_intr;
 extern atomic_t fscache_n_alloc_ops;
 extern atomic_t fscache_n_alloc_op_waits;
 
diff --git a/fs/fscache/operation.c b/fs/fscache/operation.c
index 09e43b6e822f..296492efb81b 100644
--- a/fs/fscache/operation.c
+++ b/fs/fscache/operation.c
@@ -34,32 +34,31 @@ void fscache_enqueue_operation(struct fscache_operation *op)
 
         fscache_set_op_state(op, "EnQ");
 
+        ASSERT(list_empty(&op->pend_link));
         ASSERT(op->processor != NULL);
         ASSERTCMP(op->object->state, >=, FSCACHE_OBJECT_AVAILABLE);
         ASSERTCMP(atomic_read(&op->usage), >, 0);
 
-        if (list_empty(&op->pend_link)) {
-                switch (op->flags & FSCACHE_OP_TYPE) {
-                case FSCACHE_OP_FAST:
-                        _debug("queue fast");
-                        atomic_inc(&op->usage);
-                        if (!schedule_work(&op->fast_work))
-                                fscache_put_operation(op);
-                        break;
-                case FSCACHE_OP_SLOW:
-                        _debug("queue slow");
-                        slow_work_enqueue(&op->slow_work);
-                        break;
-                case FSCACHE_OP_MYTHREAD:
-                        _debug("queue for caller's attention");
-                        break;
-                default:
-                        printk(KERN_ERR "FS-Cache: Unexpected op type %lx",
-                               op->flags);
-                        BUG();
-                        break;
-                }
-                fscache_stat(&fscache_n_op_enqueue);
+        fscache_stat(&fscache_n_op_enqueue);
+        switch (op->flags & FSCACHE_OP_TYPE) {
+        case FSCACHE_OP_FAST:
+                _debug("queue fast");
+                atomic_inc(&op->usage);
+                if (!schedule_work(&op->fast_work))
+                        fscache_put_operation(op);
+                break;
+        case FSCACHE_OP_SLOW:
+                _debug("queue slow");
+                slow_work_enqueue(&op->slow_work);
+                break;
+        case FSCACHE_OP_MYTHREAD:
+                _debug("queue for caller's attention");
+                break;
+        default:
+                printk(KERN_ERR "FS-Cache: Unexpected op type %lx",
+                       op->flags);
+                BUG();
+                break;
         }
 }
 EXPORT_SYMBOL(fscache_enqueue_operation);
@@ -97,6 +96,7 @@ int fscache_submit_exclusive_op(struct fscache_object *object,
         spin_lock(&object->lock);
         ASSERTCMP(object->n_ops, >=, object->n_in_progress);
         ASSERTCMP(object->n_ops, >=, object->n_exclusive);
+        ASSERT(list_empty(&op->pend_link));
 
         ret = -ENOBUFS;
         if (fscache_object_is_active(object)) {
@@ -202,6 +202,7 @@ int fscache_submit_op(struct fscache_object *object,
         spin_lock(&object->lock);
         ASSERTCMP(object->n_ops, >=, object->n_in_progress);
         ASSERTCMP(object->n_ops, >=, object->n_exclusive);
+        ASSERT(list_empty(&op->pend_link));
 
         ostate = object->state;
         smp_rmb();
@@ -273,12 +274,7 @@ void fscache_start_operations(struct fscache_object *object)
                         stop = true;
                 }
                 list_del_init(&op->pend_link);
-                object->n_in_progress++;
-
-                if (test_and_clear_bit(FSCACHE_OP_WAITING, &op->flags))
-                        wake_up_bit(&op->flags, FSCACHE_OP_WAITING);
-                if (op->processor)
-                        fscache_enqueue_operation(op);
+                fscache_run_op(object, op);
 
                 /* the pending queue was holding a ref on the object */
                 fscache_put_operation(op);
@@ -291,6 +287,36 @@ void fscache_start_operations(struct fscache_object *object)
 }
 
 /*
+ * cancel an operation that's pending on an object
+ */
+int fscache_cancel_op(struct fscache_operation *op)
+{
+        struct fscache_object *object = op->object;
+        int ret;
+
+        _enter("OBJ%x OP%x}", op->object->debug_id, op->debug_id);
+
+        spin_lock(&object->lock);
+
+        ret = -EBUSY;
+        if (!list_empty(&op->pend_link)) {
+                fscache_stat(&fscache_n_op_cancelled);
+                list_del_init(&op->pend_link);
+                object->n_ops--;
+                if (test_bit(FSCACHE_OP_EXCLUSIVE, &op->flags))
+                        object->n_exclusive--;
+                if (test_and_clear_bit(FSCACHE_OP_WAITING, &op->flags))
+                        wake_up_bit(&op->flags, FSCACHE_OP_WAITING);
+                fscache_put_operation(op);
+                ret = 0;
+        }
+
+        spin_unlock(&object->lock);
+        _leave(" = %d", ret);
+        return ret;
+}
+
+/*
  * release an operation
  * - queues pending ops if this is the last in-progress op
  */
diff --git a/fs/fscache/page.c b/fs/fscache/page.c
index 250dfd34c07b..e6f2e61133a1 100644
--- a/fs/fscache/page.c
+++ b/fs/fscache/page.c
@@ -295,8 +295,20 @@ int __fscache_read_or_alloc_page(struct fscache_cookie *cookie,
         if (test_bit(FSCACHE_OP_WAITING, &op->op.flags)) {
                 _debug(">>> WT");
                 fscache_stat(&fscache_n_retrieval_op_waits);
-                wait_on_bit(&op->op.flags, FSCACHE_OP_WAITING,
-                            fscache_wait_bit, TASK_UNINTERRUPTIBLE);
+                if (wait_on_bit(&op->op.flags, FSCACHE_OP_WAITING,
+                                fscache_wait_bit_interruptible,
+                                TASK_INTERRUPTIBLE) < 0) {
+                        ret = fscache_cancel_op(&op->op);
+                        if (ret == 0) {
+                                ret = -ERESTARTSYS;
+                                goto error;
+                        }
+
+                        /* it's been removed from the pending queue by another
+                         * party, so we should get to run shortly */
+                        wait_on_bit(&op->op.flags, FSCACHE_OP_WAITING,
+                                    fscache_wait_bit, TASK_UNINTERRUPTIBLE);
+                }
                 _debug("<<< GO");
         }
 
@@ -313,6 +325,7 @@ int __fscache_read_or_alloc_page(struct fscache_cookie *cookie,
                 fscache_stat_d(&fscache_n_cop_read_or_alloc_page);
         }
 
+error:
         if (ret == -ENOMEM)
                 fscache_stat(&fscache_n_retrievals_nomem);
         else if (ret == -ERESTARTSYS)
@@ -412,8 +425,20 @@ int __fscache_read_or_alloc_pages(struct fscache_cookie *cookie,
         if (test_bit(FSCACHE_OP_WAITING, &op->op.flags)) {
                 _debug(">>> WT");
                 fscache_stat(&fscache_n_retrieval_op_waits);
-                wait_on_bit(&op->op.flags, FSCACHE_OP_WAITING,
-                            fscache_wait_bit, TASK_UNINTERRUPTIBLE);
+                if (wait_on_bit(&op->op.flags, FSCACHE_OP_WAITING,
+                                fscache_wait_bit_interruptible,
+                                TASK_INTERRUPTIBLE) < 0) {
+                        ret = fscache_cancel_op(&op->op);
+                        if (ret == 0) {
+                                ret = -ERESTARTSYS;
+                                goto error;
+                        }
+
+                        /* it's been removed from the pending queue by another
+                         * party, so we should get to run shortly */
+                        wait_on_bit(&op->op.flags, FSCACHE_OP_WAITING,
+                                    fscache_wait_bit, TASK_UNINTERRUPTIBLE);
+                }
                 _debug("<<< GO");
         }
 
@@ -430,6 +455,7 @@ int __fscache_read_or_alloc_pages(struct fscache_cookie *cookie,
                 fscache_stat_d(&fscache_n_cop_read_or_alloc_pages);
         }
 
+error:
         if (ret == -ENOMEM)
                 fscache_stat(&fscache_n_retrievals_nomem);
         else if (ret == -ERESTARTSYS)
@@ -505,8 +531,20 @@ int __fscache_alloc_page(struct fscache_cookie *cookie,
         if (test_bit(FSCACHE_OP_WAITING, &op->op.flags)) {
                 _debug(">>> WT");
                 fscache_stat(&fscache_n_alloc_op_waits);
-                wait_on_bit(&op->op.flags, FSCACHE_OP_WAITING,
-                            fscache_wait_bit, TASK_UNINTERRUPTIBLE);
+                if (wait_on_bit(&op->op.flags, FSCACHE_OP_WAITING,
+                                fscache_wait_bit_interruptible,
+                                TASK_INTERRUPTIBLE) < 0) {
+                        ret = fscache_cancel_op(&op->op);
+                        if (ret == 0) {
+                                ret = -ERESTARTSYS;
+                                goto error;
+                        }
+
+                        /* it's been removed from the pending queue by another
+                         * party, so we should get to run shortly */
+                        wait_on_bit(&op->op.flags, FSCACHE_OP_WAITING,
+                                    fscache_wait_bit, TASK_UNINTERRUPTIBLE);
+                }
                 _debug("<<< GO");
         }
 
@@ -515,7 +553,10 @@ int __fscache_alloc_page(struct fscache_cookie *cookie,
         ret = object->cache->ops->allocate_page(op, page, gfp);
         fscache_stat_d(&fscache_n_cop_allocate_page);
 
-        if (ret < 0)
+error:
+        if (ret == -ERESTARTSYS)
+                fscache_stat(&fscache_n_allocs_intr);
+        else if (ret < 0)
                 fscache_stat(&fscache_n_allocs_nobufs);
         else
                 fscache_stat(&fscache_n_allocs_ok);
diff --git a/fs/fscache/stats.c b/fs/fscache/stats.c
index 20233fb44bfd..4c07439d1307 100644
--- a/fs/fscache/stats.c
+++ b/fs/fscache/stats.c
@@ -25,6 +25,7 @@ atomic_t fscache_n_op_requeue;
 atomic_t fscache_n_op_deferred_release;
 atomic_t fscache_n_op_release;
 atomic_t fscache_n_op_gc;
+atomic_t fscache_n_op_cancelled;
 
 atomic_t fscache_n_attr_changed;
 atomic_t fscache_n_attr_changed_ok;
@@ -36,6 +37,7 @@ atomic_t fscache_n_allocs;
 atomic_t fscache_n_allocs_ok;
 atomic_t fscache_n_allocs_wait;
 atomic_t fscache_n_allocs_nobufs;
+atomic_t fscache_n_allocs_intr;
 atomic_t fscache_n_alloc_ops;
 atomic_t fscache_n_alloc_op_waits;
 
@@ -169,11 +171,12 @@ static int fscache_stats_show(struct seq_file *m, void *v)
                    atomic_read(&fscache_n_attr_changed_nomem),
                    atomic_read(&fscache_n_attr_changed_calls));
 
-        seq_printf(m, "Allocs : n=%u ok=%u wt=%u nbf=%u\n",
+        seq_printf(m, "Allocs : n=%u ok=%u wt=%u nbf=%u int=%u\n",
                    atomic_read(&fscache_n_allocs),
                    atomic_read(&fscache_n_allocs_ok),
                    atomic_read(&fscache_n_allocs_wait),
-                   atomic_read(&fscache_n_allocs_nobufs));
+                   atomic_read(&fscache_n_allocs_nobufs),
+                   atomic_read(&fscache_n_allocs_intr));
         seq_printf(m, "Allocs : ops=%u owt=%u\n",
                    atomic_read(&fscache_n_alloc_ops),
                    atomic_read(&fscache_n_alloc_op_waits));
@@ -201,10 +204,11 @@ static int fscache_stats_show(struct seq_file *m, void *v)
                    atomic_read(&fscache_n_store_ops),
                    atomic_read(&fscache_n_store_calls));
 
-        seq_printf(m, "Ops    : pend=%u run=%u enq=%u\n",
+        seq_printf(m, "Ops    : pend=%u run=%u enq=%u can=%u\n",
                    atomic_read(&fscache_n_op_pend),
                    atomic_read(&fscache_n_op_run),
-                   atomic_read(&fscache_n_op_enqueue));
+                   atomic_read(&fscache_n_op_enqueue),
+                   atomic_read(&fscache_n_op_cancelled));
         seq_printf(m, "Ops    : dfr=%u rel=%u gc=%u\n",
                    atomic_read(&fscache_n_op_deferred_release),
                    atomic_read(&fscache_n_op_release),