percpu_ida: Make percpu_ida_alloc + callers accept task state bitmask

This patch changes percpu_ida_alloc() + callers to accept task state
bitmask for prepare_to_wait() for code like target/iscsi that needs
it for interruptible sleep, that is provided in a subsequent patch.

It now expects TASK_UNINTERRUPTIBLE when the caller is able to sleep
waiting for a new tag, or TASK_RUNNING when the caller cannot sleep,
and is forced to return a negative value when no tags are available.

v2 changes:
  - Include blk-mq + tcm_fc + vhost/scsi + target/iscsi changes
  - Drop signal_pending_state() call
v3 changes:
  - Only call prepare_to_wait() + finish_wait() when != TASK_RUNNING
    (PeterZ)

Reported-by: Linus Torvalds <[email protected]>
Cc: Linus Torvalds <[email protected]>
Cc: Ingo Molnar <[email protected]>
Cc: Peter Zijlstra <[email protected]>
Cc: Jens Axboe <[email protected]>
Signed-off-by: Kent Overstreet <[email protected]>
Cc: <[email protected]> #3.12+
Signed-off-by: Nicholas Bellinger <[email protected]>

Author: Kent Overstreet

block/blk-mq-tag.c

@@ -36,7 +36,8 @@ static unsigned int __blk_mq_get_tag(struct blk_mq_tags *tags, gfp_t gfp)
 {
 	int tag;
 
-	tag = percpu_ida_alloc(&tags->free_tags, gfp);
+	tag = percpu_ida_alloc(&tags->free_tags, (gfp & __GFP_WAIT) ?
+			       TASK_UNINTERRUPTIBLE : TASK_RUNNING);
 	if (tag < 0)
 		return BLK_MQ_TAG_FAIL;
 	return tag + tags->nr_reserved_tags;
@@ -52,7 +53,8 @@ static unsigned int __blk_mq_get_reserved_tag(struct blk_mq_tags *tags,
 		return BLK_MQ_TAG_FAIL;
 	}
 
-	tag = percpu_ida_alloc(&tags->reserved_tags, gfp);
+	tag = percpu_ida_alloc(&tags->reserved_tags, (gfp & __GFP_WAIT) ?
+			       TASK_UNINTERRUPTIBLE : TASK_RUNNING);
 	if (tag < 0)
 		return BLK_MQ_TAG_FAIL;
 	return tag;

drivers/target/iscsi/iscsi_target_util.c

@@ -156,9 +156,13 @@ struct iscsi_cmd *iscsit_allocate_cmd(struct iscsi_conn *conn, gfp_t gfp_mask)
 {
 	struct iscsi_cmd *cmd;
 	struct se_session *se_sess = conn->sess->se_sess;
-	int size, tag;
+	int size, tag, state = (gfp_mask & __GFP_WAIT) ? TASK_UNINTERRUPTIBLE :
+				TASK_RUNNING;
+
+	tag = percpu_ida_alloc(&se_sess->sess_tag_pool, state);
+	if (tag < 0)
+		return NULL;
 
-	tag = percpu_ida_alloc(&se_sess->sess_tag_pool, gfp_mask);
 	size = sizeof(struct iscsi_cmd) + conn->conn_transport->priv_size;
 	cmd = (struct iscsi_cmd *)(se_sess->sess_cmd_map + (tag * size));
 	memset(cmd, 0, size);

drivers/target/tcm_fc/tfc_cmd.c

@@ -438,7 +438,7 @@ static void ft_recv_cmd(struct ft_sess *sess, struct fc_frame *fp)
 	struct se_session *se_sess = sess->se_sess;
 	int tag;
 
-	tag = percpu_ida_alloc(&se_sess->sess_tag_pool, GFP_ATOMIC);
+	tag = percpu_ida_alloc(&se_sess->sess_tag_pool, TASK_RUNNING);
 	if (tag < 0)
 		goto busy;
 

drivers/vhost/scsi.c

@@ -728,7 +728,7 @@ vhost_scsi_get_tag(struct vhost_virtqueue *vq,
 	}
 	se_sess = tv_nexus->tvn_se_sess;
 
-	tag = percpu_ida_alloc(&se_sess->sess_tag_pool, GFP_ATOMIC);
+	tag = percpu_ida_alloc(&se_sess->sess_tag_pool, TASK_RUNNING);
 	if (tag < 0) {
 		pr_err("Unable to obtain tag for tcm_vhost_cmd\n");
 		return ERR_PTR(-ENOMEM);

include/linux/percpu_ida.h

@@ -4,6 +4,7 @@
 #include <linux/types.h>
 #include <linux/bitops.h>
 #include <linux/init.h>
+#include <linux/sched.h>
 #include <linux/spinlock_types.h>
 #include <linux/wait.h>
 #include <linux/cpumask.h>
@@ -61,7 +62,7 @@ struct percpu_ida {
 /* Max size of percpu freelist, */
 #define IDA_DEFAULT_PCPU_SIZE	((IDA_DEFAULT_PCPU_BATCH_MOVE * 3) / 2)
 
-int percpu_ida_alloc(struct percpu_ida *pool, gfp_t gfp);
+int percpu_ida_alloc(struct percpu_ida *pool, int state);
 void percpu_ida_free(struct percpu_ida *pool, unsigned tag);
 
 void percpu_ida_destroy(struct percpu_ida *pool);

lib/percpu_ida.c

@@ -132,22 +132,22 @@ static inline unsigned alloc_local_tag(struct percpu_ida_cpu *tags)
 /**
  * percpu_ida_alloc - allocate a tag
  * @pool: pool to allocate from
- * @gfp: gfp flags
+ * @state: task state for prepare_to_wait
  *
  * Returns a tag - an integer in the range [0..nr_tags) (passed to
  * tag_pool_init()), or otherwise -ENOSPC on allocation failure.
  *
  * Safe to be called from interrupt context (assuming it isn't passed
- * __GFP_WAIT, of course).
+ * TASK_UNINTERRUPTIBLE, of course).
  *
  * @gfp indicates whether or not to wait until a free id is available (it's not
  * used for internal memory allocations); thus if passed __GFP_WAIT we may sleep
  * however long it takes until another thread frees an id (same semantics as a
  * mempool).
  *
- * Will not fail if passed __GFP_WAIT.
+ * Will not fail if passed TASK_UNINTERRUPTIBLE.
  */
-int percpu_ida_alloc(struct percpu_ida *pool, gfp_t gfp)
+int percpu_ida_alloc(struct percpu_ida *pool, int state)
 {
 	DEFINE_WAIT(wait);
 	struct percpu_ida_cpu *tags;
@@ -174,7 +174,8 @@ int percpu_ida_alloc(struct percpu_ida *pool, gfp_t gfp)
 		 *
 		 * global lock held and irqs disabled, don't need percpu lock
 		 */
-		prepare_to_wait(&pool->wait, &wait, TASK_UNINTERRUPTIBLE);
+		if (state != TASK_RUNNING)
+			prepare_to_wait(&pool->wait, &wait, state);
 
 		if (!tags->nr_free)
 			alloc_global_tags(pool, tags);
@@ -191,16 +192,17 @@ int percpu_ida_alloc(struct percpu_ida *pool, gfp_t gfp)
 		spin_unlock(&pool->lock);
 		local_irq_restore(flags);
 
-		if (tag >= 0 || !(gfp & __GFP_WAIT))
+		if (tag >= 0 || state == TASK_RUNNING)
 			break;
 
 		schedule();
 
 		local_irq_save(flags);
 		tags = this_cpu_ptr(pool->tag_cpu);
 	}
+	if (state != TASK_RUNNING)
+		finish_wait(&pool->wait, &wait);
 
-	finish_wait(&pool->wait, &wait);
 	return tag;
 }
 EXPORT_SYMBOL_GPL(percpu_ida_alloc);