Enable IB out-of-order by default in mlx5

This series from Or changes default of IB out-of-order feature and
allows to the RDMA users to decide if they need to wait for completion
for all segments or it is enough to wait for last segment completion only.

Thanks

Signed-off-by: Leon Romanovsky <[email protected]>

10 files changed, 51 insertions, 18 deletions

diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h
index dd5ce1137f04..de0b0c3e7395 100644
--- a/include/linux/blk-mq.h
+++ b/include/linux/blk-mq.h
@@ -228,6 +228,12 @@ static inline unsigned short req_get_ioprio(struct request *req)
 	*(listptr) = rq;				\
 } while (0)
 
+#define rq_list_add_tail(lastpptr, rq)	do {		\
+	(rq)->rq_next = NULL;				\
+	**(lastpptr) = rq;				\
+	*(lastpptr) = &rq->rq_next;			\
+} while (0)
+
 #define rq_list_pop(listptr)				\
 ({							\
 	struct request *__req = NULL;			\
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index d1aee08f8c18..941304f17492 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -1446,11 +1446,10 @@ static inline void blk_wake_io_task(struct task_struct *waiter)
 		wake_up_process(waiter);
 }
 
-unsigned long bdev_start_io_acct(struct block_device *bdev,
-				 unsigned int sectors, enum req_op op,
+unsigned long bdev_start_io_acct(struct block_device *bdev, enum req_op op,
 				 unsigned long start_time);
 void bdev_end_io_acct(struct block_device *bdev, enum req_op op,
-		unsigned long start_time);
+		      unsigned int sectors, unsigned long start_time);
 
 unsigned long bio_start_io_acct(struct bio *bio);
 void bio_end_io_acct_remapped(struct bio *bio, unsigned long start_time,
diff --git a/include/linux/clk-provider.h b/include/linux/clk-provider.h
index 842e72a5348f..6f3175f0678a 100644
--- a/include/linux/clk-provider.h
+++ b/include/linux/clk-provider.h
@@ -1363,7 +1363,13 @@ struct clk_hw_onecell_data {
 	struct clk_hw *hws[];
 };
 
-#define CLK_OF_DECLARE(name, compat, fn) OF_DECLARE_1(clk, name, compat, fn)
+#define CLK_OF_DECLARE(name, compat, fn) \
+	static void __init __##name##_of_clk_init_declare(struct device_node *np) \
+	{								\
+		fn(np);							\
+		fwnode_dev_initialized(of_fwnode_handle(np), true);	\
+	}								\
+	OF_DECLARE_1(clk, name, compat, __##name##_of_clk_init_declare)
 
 /*
  * Use this macro when you have a driver that requires two initialization
diff --git a/include/linux/fb.h b/include/linux/fb.h
index d8d20514ea05..02d09cb57f6c 100644
--- a/include/linux/fb.h
+++ b/include/linux/fb.h
@@ -212,6 +212,7 @@ struct fb_deferred_io {
 	/* delay between mkwrite and deferred handler */
 	unsigned long delay;
 	bool sort_pagereflist; /* sort pagelist by offset */
+	int open_count; /* number of opened files; protected by fb_info lock */
 	struct mutex lock; /* mutex that protects the pageref list */
 	struct list_head pagereflist; /* list of pagerefs for touched pages */
 	/* callback */
diff --git a/include/linux/interconnect-provider.h b/include/linux/interconnect-provider.h
index cd5c5a27557f..d12cd18aab3f 100644
--- a/include/linux/interconnect-provider.h
+++ b/include/linux/interconnect-provider.h
@@ -122,6 +122,9 @@ int icc_link_destroy(struct icc_node *src, struct icc_node *dst);
 void icc_node_add(struct icc_node *node, struct icc_provider *provider);
 void icc_node_del(struct icc_node *node);
 int icc_nodes_remove(struct icc_provider *provider);
+void icc_provider_init(struct icc_provider *provider);
+int icc_provider_register(struct icc_provider *provider);
+void icc_provider_deregister(struct icc_provider *provider);
 int icc_provider_add(struct icc_provider *provider);
 void icc_provider_del(struct icc_provider *provider);
 struct icc_node_data *of_icc_get_from_provider(struct of_phandle_args *spec);
@@ -167,6 +170,15 @@ static inline int icc_nodes_remove(struct icc_provider *provider)
 	return -ENOTSUPP;
 }
 
+static inline void icc_provider_init(struct icc_provider *provider) { }
+
+static inline int icc_provider_register(struct icc_provider *provider)
+{
+	return -ENOTSUPP;
+}
+
+static inline void icc_provider_deregister(struct icc_provider *provider) { }
+
 static inline int icc_provider_add(struct icc_provider *provider)
 {
 	return -ENOTSUPP;
diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index 66d76e97a087..62039b147432 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -1077,7 +1077,9 @@ struct mlx5_ifc_roce_cap_bits {
 	u8         sw_r_roce_src_udp_port[0x1];
 	u8         fl_rc_qp_when_roce_disabled[0x1];
 	u8         fl_rc_qp_when_roce_enabled[0x1];
-	u8         reserved_at_7[0x17];
+	u8         reserved_at_7[0x1];
+	u8	   qp_ooo_transmit_default[0x1];
+	u8         reserved_at_9[0x15];
 	u8	   qp_ts_format[0x2];
 
 	u8         reserved_at_20[0x60];
@@ -1493,7 +1495,8 @@ struct mlx5_ifc_cmd_hca_cap_bits {
 	u8         reserved_at_b0[0x1];
 	u8         uplink_follow[0x1];
 	u8         ts_cqe_to_dest_cqn[0x1];
-	u8         reserved_at_b3[0x7];
+	u8         reserved_at_b3[0x6];
+	u8         go_back_n[0x1];
 	u8         shampo[0x1];
 	u8         reserved_at_bb[0x5];
 
@@ -3261,7 +3264,8 @@ struct mlx5_ifc_qpc_bits {
 	u8         log_rq_stride[0x3];
 	u8         no_sq[0x1];
 	u8         log_sq_size[0x4];
-	u8         reserved_at_55[0x3];
+	u8         reserved_at_55[0x1];
+	u8	   retry_mode[0x2];
 	u8	   ts_format[0x2];
 	u8         reserved_at_5a[0x1];
 	u8         rlky[0x1];
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 6a14b7b11766..470085b121d3 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -297,9 +297,11 @@ struct hh_cache {
  * relationship HH alignment <= LL alignment.
  */
 #define LL_RESERVED_SPACE(dev) \
-	((((dev)->hard_header_len+(dev)->needed_headroom)&~(HH_DATA_MOD - 1)) + HH_DATA_MOD)
+	((((dev)->hard_header_len + READ_ONCE((dev)->needed_headroom)) \
+	  & ~(HH_DATA_MOD - 1)) + HH_DATA_MOD)
 #define LL_RESERVED_SPACE_EXTRA(dev,extra) \
-	((((dev)->hard_header_len+(dev)->needed_headroom+(extra))&~(HH_DATA_MOD - 1)) + HH_DATA_MOD)
+	((((dev)->hard_header_len + READ_ONCE((dev)->needed_headroom) + (extra)) \
+	  & ~(HH_DATA_MOD - 1)) + HH_DATA_MOD)
 
 struct header_ops {
 	int	(*create) (struct sk_buff *skb, struct net_device *dev,
diff --git a/include/linux/nvme.h b/include/linux/nvme.h
index 4fad4aa245fb..779507ac750b 100644
--- a/include/linux/nvme.h
+++ b/include/linux/nvme.h
@@ -812,6 +812,7 @@ enum nvme_opcode {
 		nvme_opcode_name(nvme_cmd_compare),		\
 		nvme_opcode_name(nvme_cmd_write_zeroes),	\
 		nvme_opcode_name(nvme_cmd_dsm),			\
+		nvme_opcode_name(nvme_cmd_verify),		\
 		nvme_opcode_name(nvme_cmd_resv_register),	\
 		nvme_opcode_name(nvme_cmd_resv_report),		\
 		nvme_opcode_name(nvme_cmd_resv_acquire),	\
@@ -1144,10 +1145,14 @@ enum nvme_admin_opcode {
 		nvme_admin_opcode_name(nvme_admin_ns_mgmt),		\
 		nvme_admin_opcode_name(nvme_admin_activate_fw),		\
 		nvme_admin_opcode_name(nvme_admin_download_fw),		\
+		nvme_admin_opcode_name(nvme_admin_dev_self_test),	\
 		nvme_admin_opcode_name(nvme_admin_ns_attach),		\
 		nvme_admin_opcode_name(nvme_admin_keep_alive),		\
 		nvme_admin_opcode_name(nvme_admin_directive_send),	\
 		nvme_admin_opcode_name(nvme_admin_directive_recv),	\
+		nvme_admin_opcode_name(nvme_admin_virtual_mgmt),	\
+		nvme_admin_opcode_name(nvme_admin_nvme_mi_send),	\
+		nvme_admin_opcode_name(nvme_admin_nvme_mi_recv),	\
 		nvme_admin_opcode_name(nvme_admin_dbbuf),		\
 		nvme_admin_opcode_name(nvme_admin_format_nvm),		\
 		nvme_admin_opcode_name(nvme_admin_security_send),	\
diff --git a/include/linux/pci.h b/include/linux/pci.h
index fafd8020c6d7..b50e5c79f7e3 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -1438,6 +1438,7 @@ void pci_bus_add_resource(struct pci_bus *bus, struct resource *res,
 			  unsigned int flags);
 struct resource *pci_bus_resource_n(const struct pci_bus *bus, int n);
 void pci_bus_remove_resources(struct pci_bus *bus);
+void pci_bus_remove_resource(struct pci_bus *bus, struct resource *res);
 int devm_request_pci_bus_resources(struct device *dev,
 				   struct list_head *resources);
 
diff --git a/include/linux/tracepoint.h b/include/linux/tracepoint.h
index e299f29375bb..6811e43c1b5c 100644
--- a/include/linux/tracepoint.h
+++ b/include/linux/tracepoint.h
@@ -242,12 +242,11 @@ static inline struct tracepoint *tracepoint_ptr_deref(tracepoint_ptr_t *p)
  * not add unwanted padding between the beginning of the section and the
  * structure. Force alignment to the same alignment as the section start.
  *
- * When lockdep is enabled, we make sure to always do the RCU portions of
- * the tracepoint code, regardless of whether tracing is on. However,
- * don't check if the condition is false, due to interaction with idle
- * instrumentation. This lets us find RCU issues triggered with tracepoints
- * even when this tracepoint is off. This code has no purpose other than
- * poking RCU a bit.
+ * When lockdep is enabled, we make sure to always test if RCU is
+ * "watching" regardless if the tracepoint is enabled or not. Tracepoints
+ * require RCU to be active, and it should always warn at the tracepoint
+ * site if it is not watching, as it will need to be active when the
+ * tracepoint is enabled.
  */
 #define __DECLARE_TRACE(name, proto, args, cond, data_proto)		\
 	extern int __traceiter_##name(data_proto);			\
@@ -260,9 +259,7 @@ static inline struct tracepoint *tracepoint_ptr_deref(tracepoint_ptr_t *p)
 				TP_ARGS(args),				\
 				TP_CONDITION(cond), 0);			\
 		if (IS_ENABLED(CONFIG_LOCKDEP) && (cond)) {		\
-			rcu_read_lock_sched_notrace();			\
-			rcu_dereference_sched(__tracepoint_##name.funcs);\
-			rcu_read_unlock_sched_notrace();		\
+			WARN_ON_ONCE(!rcu_is_watching());		\
 		}							\
 	}								\
 	__DECLARE_TRACE_RCU(name, PARAMS(proto), PARAMS(args),		\