Merge branch 'Add-GVE-Features'

David Awogbemila says:

====================
Add GVE Features.

Note: Patch 4 in v3 was dropped.

Patch 4 (patch 5 in v3): Start/stop timer only when report stats is
				enabled/disabled.
Patch 7 (patch 8 in v3): Use netdev_info, not dev_info, to log
				device link status.
====================
Acked-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>

drivers/net/ethernet/google/gve/gve.h

@@ -27,6 +27,17 @@
 /* 1 for management, 1 for rx, 1 for tx */
 #define GVE_MIN_MSIX 3
 
+/* Numbers of gve tx/rx stats in stats report. */
+#define GVE_TX_STATS_REPORT_NUM	5
+#define GVE_RX_STATS_REPORT_NUM	2
+
+/* Interval to schedule a stats report update, 20000ms. */
+#define GVE_STATS_REPORT_TIMER_PERIOD	20000
+
+/* Numbers of NIC tx/rx stats in stats report. */
+#define NIC_TX_STATS_REPORT_NUM	0
+#define NIC_RX_STATS_REPORT_NUM	4
+
 /* Each slot in the desc ring has a 1:1 mapping to a slot in the data ring */
 struct gve_rx_desc_queue {
 	struct gve_rx_desc *desc_ring; /* the descriptor ring */
@@ -71,6 +82,11 @@ struct gve_rx_ring {
 	u32 cnt; /* free-running total number of completed packets */
 	u32 fill_cnt; /* free-running total number of descs and buffs posted */
 	u32 mask; /* masks the cnt and fill_cnt to the size of the ring */
+	u64 rx_copybreak_pkt; /* free-running count of copybreak packets */
+	u64 rx_copied_pkt; /* free-running total number of copied packets */
+	u64 rx_skb_alloc_fail; /* free-running count of skb alloc fails */
+	u64 rx_buf_alloc_fail; /* free-running count of buffer alloc fails */
+	u64 rx_desc_err_dropped_pkt; /* free-running count of packets dropped by descriptor error */
 	u32 q_num; /* queue index */
 	u32 ntfy_id; /* notification block index */
 	struct gve_queue_resources *q_resources; /* head and tail pointer idx */
@@ -202,24 +218,63 @@ struct gve_priv {
 	dma_addr_t adminq_bus_addr;
 	u32 adminq_mask; /* masks prod_cnt to adminq size */
 	u32 adminq_prod_cnt; /* free-running count of AQ cmds executed */
-
+	u32 adminq_cmd_fail; /* free-running count of AQ cmds failed */
+	u32 adminq_timeouts; /* free-running count of AQ cmds timeouts */
+	/* free-running count of per AQ cmd executed */
+	u32 adminq_describe_device_cnt;
+	u32 adminq_cfg_device_resources_cnt;
+	u32 adminq_register_page_list_cnt;
+	u32 adminq_unregister_page_list_cnt;
+	u32 adminq_create_tx_queue_cnt;
+	u32 adminq_create_rx_queue_cnt;
+	u32 adminq_destroy_tx_queue_cnt;
+	u32 adminq_destroy_rx_queue_cnt;
+	u32 adminq_dcfg_device_resources_cnt;
+	u32 adminq_set_driver_parameter_cnt;
+	u32 adminq_report_stats_cnt;
+	u32 adminq_report_link_speed_cnt;
+
+	/* Global stats */
+	u32 interface_up_cnt; /* count of times interface turned up since last reset */
+	u32 interface_down_cnt; /* count of times interface turned down since last reset */
+	u32 reset_cnt; /* count of reset */
+	u32 page_alloc_fail; /* count of page alloc fails */
+	u32 dma_mapping_error; /* count of dma mapping errors */
+	u32 stats_report_trigger_cnt; /* count of device-requested stats-reports since last reset */
 	struct workqueue_struct *gve_wq;
 	struct work_struct service_task;
+	struct work_struct stats_report_task;
 	unsigned long service_task_flags;
 	unsigned long state_flags;
+
+	struct gve_stats_report *stats_report;
+	u64 stats_report_len;
+	dma_addr_t stats_report_bus; /* dma address for the stats report */
+	unsigned long ethtool_flags;
+
+	unsigned long stats_report_timer_period;
+	struct timer_list stats_report_timer;
+
+	/* Gvnic device link speed from hypervisor. */
+	u64 link_speed;
 };
 
-enum gve_service_task_flags {
-	GVE_PRIV_FLAGS_DO_RESET			= BIT(1),
-	GVE_PRIV_FLAGS_RESET_IN_PROGRESS	= BIT(2),
-	GVE_PRIV_FLAGS_PROBE_IN_PROGRESS	= BIT(3),
+enum gve_service_task_flags_bit {
+	GVE_PRIV_FLAGS_DO_RESET			= 1,
+	GVE_PRIV_FLAGS_RESET_IN_PROGRESS	= 2,
+	GVE_PRIV_FLAGS_PROBE_IN_PROGRESS	= 3,
+	GVE_PRIV_FLAGS_DO_REPORT_STATS = 4,
 };
 
-enum gve_state_flags {
-	GVE_PRIV_FLAGS_ADMIN_QUEUE_OK		= BIT(1),
-	GVE_PRIV_FLAGS_DEVICE_RESOURCES_OK	= BIT(2),
-	GVE_PRIV_FLAGS_DEVICE_RINGS_OK		= BIT(3),
-	GVE_PRIV_FLAGS_NAPI_ENABLED		= BIT(4),
+enum gve_state_flags_bit {
+	GVE_PRIV_FLAGS_ADMIN_QUEUE_OK		= 1,
+	GVE_PRIV_FLAGS_DEVICE_RESOURCES_OK	= 2,
+	GVE_PRIV_FLAGS_DEVICE_RINGS_OK		= 3,
+	GVE_PRIV_FLAGS_NAPI_ENABLED		= 4,
+};
+
+enum gve_ethtool_flags_bit {
+	GVE_PRIV_FLAGS_REPORT_STATS		= 0,
 };
 
 static inline bool gve_get_do_reset(struct gve_priv *priv)
@@ -269,6 +324,22 @@ static inline void gve_clear_probe_in_progress(struct gve_priv *priv)
 	clear_bit(GVE_PRIV_FLAGS_PROBE_IN_PROGRESS, &priv->service_task_flags);
 }
 
+static inline bool gve_get_do_report_stats(struct gve_priv *priv)
+{
+	return test_bit(GVE_PRIV_FLAGS_DO_REPORT_STATS,
+			&priv->service_task_flags);
+}
+
+static inline void gve_set_do_report_stats(struct gve_priv *priv)
+{
+	set_bit(GVE_PRIV_FLAGS_DO_REPORT_STATS, &priv->service_task_flags);
+}
+
+static inline void gve_clear_do_report_stats(struct gve_priv *priv)
+{
+	clear_bit(GVE_PRIV_FLAGS_DO_REPORT_STATS, &priv->service_task_flags);
+}
+
 static inline bool gve_get_admin_queue_ok(struct gve_priv *priv)
 {
 	return test_bit(GVE_PRIV_FLAGS_ADMIN_QUEUE_OK, &priv->state_flags);
@@ -329,6 +400,16 @@ static inline void gve_clear_napi_enabled(struct gve_priv *priv)
 	clear_bit(GVE_PRIV_FLAGS_NAPI_ENABLED, &priv->state_flags);
 }
 
+static inline bool gve_get_report_stats(struct gve_priv *priv)
+{
+	return test_bit(GVE_PRIV_FLAGS_REPORT_STATS, &priv->ethtool_flags);
+}
+
+static inline void gve_clear_report_stats(struct gve_priv *priv)
+{
+	clear_bit(GVE_PRIV_FLAGS_REPORT_STATS, &priv->ethtool_flags);
+}
+
 /* Returns the address of the ntfy_blocks irq doorbell
  */
 static inline __be32 __iomem *gve_irq_doorbell(struct gve_priv *priv,
@@ -426,7 +507,8 @@ static inline bool gve_can_recycle_pages(struct net_device *dev)
 }
 
 /* buffers */
-int gve_alloc_page(struct device *dev, struct page **page, dma_addr_t *dma,
+int gve_alloc_page(struct gve_priv *priv, struct device *dev,
+		   struct page **page, dma_addr_t *dma,
 		   enum dma_data_direction);
 void gve_free_page(struct device *dev, struct page *page, dma_addr_t dma,
 		   enum dma_data_direction);
@@ -450,6 +532,8 @@ int gve_reset(struct gve_priv *priv, bool attempt_teardown);
 int gve_adjust_queues(struct gve_priv *priv,
 		      struct gve_queue_config new_rx_config,
 		      struct gve_queue_config new_tx_config);
+/* report stats handling */
+void gve_handle_report_stats(struct gve_priv *priv);
 /* exported by ethtool.c */
 extern const struct ethtool_ops gve_ethtool_ops;
 /* needed by ethtool */

drivers/net/ethernet/google/gve/gve_adminq.h

@@ -21,6 +21,8 @@ enum gve_adminq_opcodes {
 	GVE_ADMINQ_DESTROY_RX_QUEUE		= 0x8,
 	GVE_ADMINQ_DECONFIGURE_DEVICE_RESOURCES	= 0x9,
 	GVE_ADMINQ_SET_DRIVER_PARAMETER		= 0xB,
+	GVE_ADMINQ_REPORT_STATS			= 0xC,
+	GVE_ADMINQ_REPORT_LINK_SPEED	= 0xD
 };
 
 /* Admin queue status codes */
@@ -172,6 +174,51 @@ struct gve_adminq_set_driver_parameter {
 
 static_assert(sizeof(struct gve_adminq_set_driver_parameter) == 16);
 
+struct gve_adminq_report_stats {
+	__be64 stats_report_len;
+	__be64 stats_report_addr;
+	__be64 interval;
+};
+
+static_assert(sizeof(struct gve_adminq_report_stats) == 24);
+
+struct gve_adminq_report_link_speed {
+	__be64 link_speed_address;
+};
+
+static_assert(sizeof(struct gve_adminq_report_link_speed) == 8);
+
+struct stats {
+	__be32 stat_name;
+	__be32 queue_id;
+	__be64 value;
+};
+
+static_assert(sizeof(struct stats) == 16);
+
+struct gve_stats_report {
+	__be64 written_count;
+	struct stats stats[0];
+};
+
+static_assert(sizeof(struct gve_stats_report) == 8);
+
+enum gve_stat_names {
+	// stats from gve
+	TX_WAKE_CNT			= 1,
+	TX_STOP_CNT			= 2,
+	TX_FRAMES_SENT			= 3,
+	TX_BYTES_SENT			= 4,
+	TX_LAST_COMPLETION_PROCESSED	= 5,
+	RX_NEXT_EXPECTED_SEQUENCE	= 6,
+	RX_BUFFERS_POSTED		= 7,
+	// stats from NIC
+	RX_QUEUE_DROP_CNT		= 65,
+	RX_NO_BUFFERS_POSTED		= 66,
+	RX_DROPS_PACKET_OVER_MRU	= 67,
+	RX_DROPS_INVALID_CHECKSUM	= 68,
+};
+
 union gve_adminq_command {
 	struct {
 		__be32 opcode;
@@ -187,6 +234,8 @@ union gve_adminq_command {
 			struct gve_adminq_register_page_list reg_page_list;
 			struct gve_adminq_unregister_page_list unreg_page_list;
 			struct gve_adminq_set_driver_parameter set_driver_param;
+			struct gve_adminq_report_stats report_stats;
+			struct gve_adminq_report_link_speed report_link_speed;
 		};
 	};
 	u8 reserved[64];
@@ -197,8 +246,6 @@ static_assert(sizeof(union gve_adminq_command) == 64);
 int gve_adminq_alloc(struct device *dev, struct gve_priv *priv);
 void gve_adminq_free(struct device *dev, struct gve_priv *priv);
 void gve_adminq_release(struct gve_priv *priv);
-int gve_adminq_execute_cmd(struct gve_priv *priv,
-			   union gve_adminq_command *cmd_orig);
 int gve_adminq_describe_device(struct gve_priv *priv);
 int gve_adminq_configure_device_resources(struct gve_priv *priv,
 					  dma_addr_t counter_array_bus_addr,
@@ -206,12 +253,15 @@ int gve_adminq_configure_device_resources(struct gve_priv *priv,
 					  dma_addr_t db_array_bus_addr,
 					  u32 num_ntfy_blks);
 int gve_adminq_deconfigure_device_resources(struct gve_priv *priv);
-int gve_adminq_create_tx_queue(struct gve_priv *priv, u32 queue_id);
-int gve_adminq_destroy_tx_queue(struct gve_priv *priv, u32 queue_id);
-int gve_adminq_create_rx_queue(struct gve_priv *priv, u32 queue_id);
-int gve_adminq_destroy_rx_queue(struct gve_priv *priv, u32 queue_id);
+int gve_adminq_create_tx_queues(struct gve_priv *priv, u32 num_queues);
+int gve_adminq_destroy_tx_queues(struct gve_priv *priv, u32 queue_id);
+int gve_adminq_create_rx_queues(struct gve_priv *priv, u32 num_queues);
+int gve_adminq_destroy_rx_queues(struct gve_priv *priv, u32 queue_id);
 int gve_adminq_register_page_list(struct gve_priv *priv,
 				  struct gve_queue_page_list *qpl);
 int gve_adminq_unregister_page_list(struct gve_priv *priv, u32 page_list_id);
 int gve_adminq_set_mtu(struct gve_priv *priv, u64 mtu);
+int gve_adminq_report_stats(struct gve_priv *priv, u64 stats_report_len,
+			    dma_addr_t stats_report_addr, u64 interval);
+int gve_adminq_report_link_speed(struct gve_priv *priv);
 #endif /* _GVE_ADMINQ_H */

drivers/net/ethernet/google/gve/gve_register.h

@@ -23,5 +23,6 @@ struct gve_registers {
 enum gve_device_status_flags {
 	GVE_DEVICE_STATUS_RESET_MASK		= BIT(1),
 	GVE_DEVICE_STATUS_LINK_STATUS_MASK	= BIT(2),
+	GVE_DEVICE_STATUS_REPORT_STATS_MASK	= BIT(3),
 };
 #endif /* _GVE_REGISTER_H_ */

drivers/net/ethernet/google/gve/gve_rx.c

@@ -225,7 +225,8 @@ static enum pkt_hash_types gve_rss_type(__be16 pkt_flags)
 	return PKT_HASH_TYPE_L2;
 }
 
-static struct sk_buff *gve_rx_copy(struct net_device *dev,
+static struct sk_buff *gve_rx_copy(struct gve_rx_ring *rx,
+				   struct net_device *dev,
 				   struct napi_struct *napi,
 				   struct gve_rx_slot_page_info *page_info,
 				   u16 len)
@@ -242,6 +243,11 @@ static struct sk_buff *gve_rx_copy(struct net_device *dev,
 	skb_copy_to_linear_data(skb, va, len);
 
 	skb->protocol = eth_type_trans(skb, dev);
+
+	u64_stats_update_begin(&rx->statss);
+	rx->rx_copied_pkt++;
+	u64_stats_update_end(&rx->statss);
+
 	return skb;
 }
 
@@ -284,8 +290,12 @@ static bool gve_rx(struct gve_rx_ring *rx, struct gve_rx_desc *rx_desc,
 	u16 len;
 
 	/* drop this packet */
-	if (unlikely(rx_desc->flags_seq & GVE_RXF_ERR))
+	if (unlikely(rx_desc->flags_seq & GVE_RXF_ERR)) {
+		u64_stats_update_begin(&rx->statss);
+		rx->rx_desc_err_dropped_pkt++;
+		u64_stats_update_end(&rx->statss);
 		return true;
+	}
 
 	len = be16_to_cpu(rx_desc->len) - GVE_RX_PAD;
 	page_info = &rx->data.page_info[idx];
@@ -300,11 +310,14 @@ static bool gve_rx(struct gve_rx_ring *rx, struct gve_rx_desc *rx_desc,
 	if (PAGE_SIZE == 4096) {
 		if (len <= priv->rx_copybreak) {
 			/* Just copy small packets */
-			skb = gve_rx_copy(dev, napi, page_info, len);
+			skb = gve_rx_copy(rx, dev, napi, page_info, len);
+			u64_stats_update_begin(&rx->statss);
+			rx->rx_copybreak_pkt++;
+			u64_stats_update_end(&rx->statss);
 			goto have_skb;
 		}
 		if (unlikely(!gve_can_recycle_pages(dev))) {
-			skb = gve_rx_copy(dev, napi, page_info, len);
+			skb = gve_rx_copy(rx, dev, napi, page_info, len);
 			goto have_skb;
 		}
 		pagecount = page_count(page_info->page);
@@ -314,8 +327,12 @@ static bool gve_rx(struct gve_rx_ring *rx, struct gve_rx_desc *rx_desc,
 			 * stack.
 			 */
 			skb = gve_rx_add_frags(dev, napi, page_info, len);
-			if (!skb)
+			if (!skb) {
+				u64_stats_update_begin(&rx->statss);
+				rx->rx_skb_alloc_fail++;
+				u64_stats_update_end(&rx->statss);
 				return true;
+			}
 			/* Make sure the kernel stack can't release the page */
 			get_page(page_info->page);
 			/* "flip" to other packet buffer on this page */
@@ -324,21 +341,25 @@ static bool gve_rx(struct gve_rx_ring *rx, struct gve_rx_desc *rx_desc,
 			/* We have previously passed the other half of this
 			 * page up the stack, but it has not yet been freed.
 			 */
-			skb = gve_rx_copy(dev, napi, page_info, len);
+			skb = gve_rx_copy(rx, dev, napi, page_info, len);
 		} else {
 			WARN(pagecount < 1, "Pagecount should never be < 1");
 			return false;
 		}
 	} else {
-		skb = gve_rx_copy(dev, napi, page_info, len);
+		skb = gve_rx_copy(rx, dev, napi, page_info, len);
 	}
 
 have_skb:
 	/* We didn't manage to allocate an skb but we haven't had any
 	 * reset worthy failures.
 	 */
-	if (!skb)
+	if (!skb) {
+		u64_stats_update_begin(&rx->statss);
+		rx->rx_skb_alloc_fail++;
+		u64_stats_update_end(&rx->statss);
 		return true;
+	}
 
 	if (likely(feat & NETIF_F_RXCSUM)) {
 		/* NIC passes up the partial sum */