liquidio: improve soft command handling

1. Set LIO_SC_MAX_TMO_MS as the maximum timeout value for a soft command
   (sc).  All sc's use this value as a hard timeout value. Add expiry_time
   in struct octeon_soft_command to keep the hard timeout value. The field
   wait_time and timeout in struct octeon_soft_command will be obsoleted in
   the last patch of this patch series.
2. Add processing a synchronous sc in sc response thread
   lio_process_ordered_list. The memory allocated for a synchronous sc will
   be freed by lio_process_ordered_list() to the sc pool.
3. Add two response lists for lio_process_ordered_list to process the
   storage allocated for sc's:
   OCTEON_DONE_SC_LIST response list keeps all sc's which will be freed to
   the pool after their requestors have finished processing the responses.
   OCTEON_ZOMBIE_SC_LIST response list keeps all sc's which have got
   LIO_SC_MAX_TMO_MS timeout.
   When an sc gets a hard timeout, lio_process_order_list() will recheck
   its status 1 ms later. If the status has not updated by the firmware at
   that time, the sc will be removed from OCTEON_DONE_SC_LIST response list
   to OCTEON_ZOMBIE_SC_LIST response list. The sc's in the
   OCTEON_ZOMBIE_SC_LIST response list will be freed when the driver is
   unloaded.

Signed-off-by: Weilin Chang <weilin.chang@cavium.com>
Signed-off-by: Felix Manlunas <felix.manlunas@cavium.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

drivers/net/ethernet/cavium/liquidio/lio_main.c

@@ -1037,12 +1037,12 @@ static void octeon_destroy_resources(struct octeon_device *oct)
 
 		/* fallthrough */
 	case OCT_DEV_IO_QUEUES_DONE:
-		if (wait_for_pending_requests(oct))
-			dev_err(&oct->pci_dev->dev, "There were pending requests\n");
-
 		if (lio_wait_for_instr_fetch(oct))
 			dev_err(&oct->pci_dev->dev, "IQ had pending instructions\n");
 
+		if (wait_for_pending_requests(oct))
+			dev_err(&oct->pci_dev->dev, "There were pending requests\n");
+
 		/* Disable the input and output queues now. No more packets will
 		 * arrive from Octeon, but we should wait for all packet
 		 * processing to finish.
@@ -1052,6 +1052,31 @@ static void octeon_destroy_resources(struct octeon_device *oct)
 		if (lio_wait_for_oq_pkts(oct))
 			dev_err(&oct->pci_dev->dev, "OQ had pending packets\n");
 
+		/* Force all requests waiting to be fetched by OCTEON to
+		 * complete.
+		 */
+		for (i = 0; i < MAX_OCTEON_INSTR_QUEUES(oct); i++) {
+			struct octeon_instr_queue *iq;
+
+			if (!(oct->io_qmask.iq & BIT_ULL(i)))
+				continue;
+			iq = oct->instr_queue[i];
+
+			if (atomic_read(&iq->instr_pending)) {
+				spin_lock_bh(&iq->lock);
+				iq->fill_cnt = 0;
+				iq->octeon_read_index = iq->host_write_index;
+				iq->stats.instr_processed +=
+					atomic_read(&iq->instr_pending);
+				lio_process_iq_request_list(oct, iq, 0);
+				spin_unlock_bh(&iq->lock);
+			}
+		}
+
+		lio_process_ordered_list(oct, 1);
+		octeon_free_sc_done_list(oct);
+		octeon_free_sc_zombie_list(oct);
+
 	/* fallthrough */
 	case OCT_DEV_INTR_SET_DONE:
 		/* Disable interrupts  */

drivers/net/ethernet/cavium/liquidio/lio_vf_main.c

@@ -471,12 +471,12 @@ static void octeon_destroy_resources(struct octeon_device *oct)
 	case OCT_DEV_HOST_OK:
 		/* fallthrough */
 	case OCT_DEV_IO_QUEUES_DONE:
-		if (wait_for_pending_requests(oct))
-			dev_err(&oct->pci_dev->dev, "There were pending requests\n");
-
 		if (lio_wait_for_instr_fetch(oct))
 			dev_err(&oct->pci_dev->dev, "IQ had pending instructions\n");
 
+		if (wait_for_pending_requests(oct))
+			dev_err(&oct->pci_dev->dev, "There were pending requests\n");
+
 		/* Disable the input and output queues now. No more packets will
 		 * arrive from Octeon, but we should wait for all packet
 		 * processing to finish.
@@ -485,6 +485,32 @@ static void octeon_destroy_resources(struct octeon_device *oct)
 
 		if (lio_wait_for_oq_pkts(oct))
 			dev_err(&oct->pci_dev->dev, "OQ had pending packets\n");
+
+		/* Force all requests waiting to be fetched by OCTEON to
+		 * complete.
+		 */
+		for (i = 0; i < MAX_OCTEON_INSTR_QUEUES(oct); i++) {
+			struct octeon_instr_queue *iq;
+
+			if (!(oct->io_qmask.iq & BIT_ULL(i)))
+				continue;
+			iq = oct->instr_queue[i];
+
+			if (atomic_read(&iq->instr_pending)) {
+				spin_lock_bh(&iq->lock);
+				iq->fill_cnt = 0;
+				iq->octeon_read_index = iq->host_write_index;
+				iq->stats.instr_processed +=
+					atomic_read(&iq->instr_pending);
+				lio_process_iq_request_list(oct, iq, 0);
+				spin_unlock_bh(&iq->lock);
+			}
+		}
+
+		lio_process_ordered_list(oct, 1);
+		octeon_free_sc_done_list(oct);
+		octeon_free_sc_zombie_list(oct);
+
 	/* fall through */
 	case OCT_DEV_INTR_SET_DONE:
 		/* Disable interrupts  */

drivers/net/ethernet/cavium/liquidio/octeon_config.h

@@ -440,7 +440,7 @@ struct octeon_config {
 /* Response lists - 1 ordered, 1 unordered-blocking, 1 unordered-nonblocking
  * NoResponse Lists are now maintained with each IQ. (Dec' 2007).
  */
-#define MAX_RESPONSE_LISTS           4
+#define MAX_RESPONSE_LISTS           6
 
 /* Opcode hash bits. The opcode is hashed on the lower 6-bits to lookup the
  * dispatch table.

drivers/net/ethernet/cavium/liquidio/octeon_iq.h

@@ -294,11 +294,20 @@ struct octeon_soft_command {
 	/** Time out and callback */
 	size_t wait_time;
 	size_t timeout;
+	size_t expiry_time;
+
 	u32 iq_no;
 	void (*callback)(struct octeon_device *, u32, void *);
 	void *callback_arg;
+
+	int caller_is_done;
+	u32 sc_status;
+	struct completion complete;
 };
 
+/* max timeout (in milli sec) for soft request */
+#define LIO_SC_MAX_TMO_MS       60000
+
 /** Maximum number of buffers to allocate into soft command buffer pool
  */
 #define  MAX_SOFT_COMMAND_BUFFERS	256
@@ -319,6 +328,8 @@ struct octeon_sc_buffer_pool {
 		(((octeon_dev_ptr)->instr_queue[iq_no]->stats.field) += count)
 
 int octeon_setup_sc_buffer_pool(struct octeon_device *oct);
+int octeon_free_sc_done_list(struct octeon_device *oct);
+int octeon_free_sc_zombie_list(struct octeon_device *oct);
 int octeon_free_sc_buffer_pool(struct octeon_device *oct);
 struct octeon_soft_command *
 	octeon_alloc_soft_command(struct octeon_device *oct,

drivers/net/ethernet/cavium/liquidio/octeon_nic.c

@@ -75,8 +75,7 @@ octeon_alloc_soft_command_resp(struct octeon_device    *oct,
 	else
 		sc->cmd.cmd2.rptr =  sc->dmarptr;
 
-	sc->wait_time = 1000;
+	sc->expiry_time = jiffies + msecs_to_jiffies(LIO_SC_MAX_TMO_MS);
-	sc->timeout = jiffies + sc->wait_time;
 
 	return sc;
 }

drivers/net/ethernet/cavium/liquidio/request_manager.c

@@ -409,33 +409,22 @@ lio_process_iq_request_list(struct octeon_device *oct,
 			else
 				irh = (struct octeon_instr_irh *)
 					&sc->cmd.cmd2.irh;
-			if (irh->rflag) {
+
 			/* We're expecting a response from Octeon.
 			 * It's up to lio_process_ordered_list() to
 			 * process  sc. Add sc to the ordered soft
 			 * command response list because we expect
 			 * a response from Octeon.
 			 */
-				spin_lock_irqsave
+			spin_lock_irqsave(&oct->response_list
-					(&oct->response_list
+					  [OCTEON_ORDERED_SC_LIST].lock, flags);
-					 [OCTEON_ORDERED_SC_LIST].lock,
-					 flags);
 			atomic_inc(&oct->response_list
-					[OCTEON_ORDERED_SC_LIST].
+				   [OCTEON_ORDERED_SC_LIST].pending_req_count);
-					pending_req_count);
 			list_add_tail(&sc->node, &oct->response_list
 				[OCTEON_ORDERED_SC_LIST].head);
-				spin_unlock_irqrestore
+			spin_unlock_irqrestore(&oct->response_list
-					(&oct->response_list
 					       [OCTEON_ORDERED_SC_LIST].lock,
 					       flags);
-			} else {
-				if (sc->callback) {
-					/* This callback must not sleep */
-					sc->callback(oct, OCTEON_REQUEST_DONE,
-						     sc->callback_arg);
-				}
-			}
 			break;
 		default:
 			dev_err(&oct->pci_dev->dev,
@@ -755,8 +744,7 @@ int octeon_send_soft_command(struct octeon_device *oct,
 		len = (u32)ih2->dlengsz;
 	}
 
-	if (sc->wait_time)
+	sc->expiry_time = jiffies + msecs_to_jiffies(LIO_SC_MAX_TMO_MS);
-		sc->timeout = jiffies + sc->wait_time;
 
 	return (octeon_send_command(oct, sc->iq_no, 1, &sc->cmd, sc,
 				    len, REQTYPE_SOFT_COMMAND));
@@ -791,11 +779,76 @@ int octeon_setup_sc_buffer_pool(struct octeon_device *oct)
 	return 0;
 }
 
+int octeon_free_sc_done_list(struct octeon_device *oct)
+{
+	struct octeon_response_list *done_sc_list, *zombie_sc_list;
+	struct octeon_soft_command *sc;
+	struct list_head *tmp, *tmp2;
+	spinlock_t *sc_lists_lock; /* lock for response_list */
+
+	done_sc_list = &oct->response_list[OCTEON_DONE_SC_LIST];
+	zombie_sc_list = &oct->response_list[OCTEON_ZOMBIE_SC_LIST];
+
+	if (!atomic_read(&done_sc_list->pending_req_count))
+		return 0;
+
+	sc_lists_lock = &oct->response_list[OCTEON_ORDERED_SC_LIST].lock;
+
+	spin_lock_bh(sc_lists_lock);
+
+	list_for_each_safe(tmp, tmp2, &done_sc_list->head) {
+		sc = list_entry(tmp, struct octeon_soft_command, node);
+
+		if (READ_ONCE(sc->caller_is_done)) {
+			list_del(&sc->node);
+			atomic_dec(&done_sc_list->pending_req_count);
+
+			if (*sc->status_word == COMPLETION_WORD_INIT) {
+				/* timeout; move sc to zombie list */
+				list_add_tail(&sc->node, &zombie_sc_list->head);
+				atomic_inc(&zombie_sc_list->pending_req_count);
+			} else {
+				octeon_free_soft_command(oct, sc);
+			}
+		}
+	}
+
+	spin_unlock_bh(sc_lists_lock);
+
+	return 0;
+}
+
+int octeon_free_sc_zombie_list(struct octeon_device *oct)
+{
+	struct octeon_response_list *zombie_sc_list;
+	struct octeon_soft_command *sc;
+	struct list_head *tmp, *tmp2;
+	spinlock_t *sc_lists_lock; /* lock for response_list */
+
+	zombie_sc_list = &oct->response_list[OCTEON_ZOMBIE_SC_LIST];
+	sc_lists_lock = &oct->response_list[OCTEON_ORDERED_SC_LIST].lock;
+
+	spin_lock_bh(sc_lists_lock);
+
+	list_for_each_safe(tmp, tmp2, &zombie_sc_list->head) {
+		list_del(tmp);
+		atomic_dec(&zombie_sc_list->pending_req_count);
+		sc = list_entry(tmp, struct octeon_soft_command, node);
+		octeon_free_soft_command(oct, sc);
+	}
+
+	spin_unlock_bh(sc_lists_lock);
+
+	return 0;
+}
+
 int octeon_free_sc_buffer_pool(struct octeon_device *oct)
 {
 	struct list_head *tmp, *tmp2;
 	struct octeon_soft_command *sc;
 
+	octeon_free_sc_zombie_list(oct);
+
 	spin_lock_bh(&oct->sc_buf_pool.lock);
 
 	list_for_each_safe(tmp, tmp2, &oct->sc_buf_pool.head) {
@@ -824,6 +877,9 @@ struct octeon_soft_command *octeon_alloc_soft_command(struct octeon_device *oct,
 	struct octeon_soft_command *sc = NULL;
 	struct list_head *tmp;
 
+	if (!rdatasize)
+		rdatasize = 16;
+
 	WARN_ON((offset + datasize + rdatasize + ctxsize) >
 	       SOFT_COMMAND_BUFFER_SIZE);
 

drivers/net/ethernet/cavium/liquidio/response_manager.c

@@ -69,6 +69,8 @@ int lio_process_ordered_list(struct octeon_device *octeon_dev,
 	u32 status;
 	u64 status64;
 
+	octeon_free_sc_done_list(octeon_dev);
+
 	ordered_sc_list = &octeon_dev->response_list[OCTEON_ORDERED_SC_LIST];
 
 	do {
@@ -111,26 +113,88 @@ int lio_process_ordered_list(struct octeon_device *octeon_dev,
 					}
 				}
 			}
-		} else if (force_quit || (sc->timeout &&
+		} else if (unlikely(force_quit) || (sc->expiry_time &&
-			time_after(jiffies, (unsigned long)sc->timeout))) {
+			time_after(jiffies, (unsigned long)sc->expiry_time))) {
-			dev_err(&octeon_dev->pci_dev->dev, "%s: cmd failed, timeout (%ld, %ld)\n",
+			struct octeon_instr_irh *irh =
-				__func__, (long)jiffies, (long)sc->timeout);
+				(struct octeon_instr_irh *)&sc->cmd.cmd3.irh;
+
+			dev_err(&octeon_dev->pci_dev->dev, "%s: ", __func__);
+			dev_err(&octeon_dev->pci_dev->dev,
+				"cmd %x/%x/%llx/%llx failed, ",
+				irh->opcode, irh->subcode,
+				sc->cmd.cmd3.ossp[0], sc->cmd.cmd3.ossp[1]);
+			dev_err(&octeon_dev->pci_dev->dev,
+				"timeout (%ld, %ld)\n",
+				(long)jiffies, (long)sc->expiry_time);
 			status = OCTEON_REQUEST_TIMEOUT;
 		}
 
 		if (status != OCTEON_REQUEST_PENDING) {
+			sc->sc_status = status;
+
 			/* we have received a response or we have timed out */
 			/* remove node from linked list */
 			list_del(&sc->node);
 			atomic_dec(&octeon_dev->response_list
 				   [OCTEON_ORDERED_SC_LIST].
 				   pending_req_count);
-			spin_unlock_bh
-			    (&ordered_sc_list->lock);
 
-			if (sc->callback)
+			if (!sc->callback) {
+				atomic_inc(&octeon_dev->response_list
+					   [OCTEON_DONE_SC_LIST].
+					   pending_req_count);
+				list_add_tail(&sc->node,
+					      &octeon_dev->response_list
+					      [OCTEON_DONE_SC_LIST].head);
+
+				if (unlikely(READ_ONCE(sc->caller_is_done))) {
+					/* caller does not wait for response
+					 * from firmware
+					 */
+					if (status != OCTEON_REQUEST_DONE) {
+						struct octeon_instr_irh *irh;
+
+						irh =
+						    (struct octeon_instr_irh *)
+						    &sc->cmd.cmd3.irh;
+						dev_dbg
+						    (&octeon_dev->pci_dev->dev,
+						    "%s: sc failed: opcode=%x, ",
+						    __func__, irh->opcode);
+						dev_dbg
+						    (&octeon_dev->pci_dev->dev,
+						    "subcode=%x, ossp[0]=%llx, ",
+						    irh->subcode,
+						    sc->cmd.cmd3.ossp[0]);
+						dev_dbg
+						    (&octeon_dev->pci_dev->dev,
+						    "ossp[1]=%llx, status=%d\n",
+						    sc->cmd.cmd3.ossp[1],
+						    status);
+					}
+				} else {
+					complete(&sc->complete);
+				}
+
+				spin_unlock_bh(&ordered_sc_list->lock);
+			} else {
+				/* sc with callback function */
+				if (status == OCTEON_REQUEST_TIMEOUT) {
+					atomic_inc(&octeon_dev->response_list
+						   [OCTEON_ZOMBIE_SC_LIST].
+						   pending_req_count);
+					list_add_tail(&sc->node,
+						      &octeon_dev->response_list
+						      [OCTEON_ZOMBIE_SC_LIST].
+						      head);
+				}
+
+				spin_unlock_bh(&ordered_sc_list->lock);
+
 				sc->callback(octeon_dev, status,
 					     sc->callback_arg);
+				/* sc is freed by caller */
+			}
 
 			request_complete++;
 

drivers/net/ethernet/cavium/liquidio/response_manager.h

@@ -53,7 +53,9 @@ enum {
 	OCTEON_ORDERED_LIST = 0,
 	OCTEON_UNORDERED_NONBLOCKING_LIST = 1,
 	OCTEON_UNORDERED_BLOCKING_LIST = 2,
-	OCTEON_ORDERED_SC_LIST = 3
+	OCTEON_ORDERED_SC_LIST = 3,
+	OCTEON_DONE_SC_LIST = 4,
+	OCTEON_ZOMBIE_SC_LIST = 5
 };
 
 /** Response Order values for a Octeon Request. */