Support effective VF bandwidth query in LAG mode

Currently, mlx5 driver exposes only the parent function's speed to VFs,
providing no way to query the actual effective bandwidth in LAG and
MPESW configurations. This limitation prevents userspace and
upper-layer software from obtaining accurate bandwidth information,
which impacts traffic scheduling decisions.

This series addresses this by:

1. Adding mlx5 internal logic to calculate and propagate the effective
   aggregated LAG speed to all attached vports. The vport speeds are
   dynamically updated when LAG member link states change.

2. Extending RDMA core with a new ib_query_port_speed() verb and an
   IB_EVENT_DEVICE_SPEED_CHANGE async event. These interfaces expose
   the effective port speed to userspace, supporting speeds that are
   not expressible as IB speed * width (where width is 2^n).

This series enables userspace applications to query the effective
port speed and receive notifications on speed changes in real-time.
In LAG configurations, each mlx5 port reports the aggregated bandwidth
of all active LAG members.

Signed-off-by: Leon Romanovsky <leon@kernel.org>

13 files changed, 44 insertions, 21 deletions

diff --git a/include/linux/bio.h b/include/linux/bio.h
index ad2d57908c1c..c75a9b3672aa 100644
--- a/include/linux/bio.h
+++ b/include/linux/bio.h
@@ -46,6 +46,21 @@ static inline unsigned int bio_max_segs(unsigned int nr_segs)
 #define bio_data_dir(bio) \
 	(op_is_write(bio_op(bio)) ? WRITE : READ)
 
+static inline bool bio_flagged(const struct bio *bio, unsigned int bit)
+{
+	return bio->bi_flags & (1U << bit);
+}
+
+static inline void bio_set_flag(struct bio *bio, unsigned int bit)
+{
+	bio->bi_flags |= (1U << bit);
+}
+
+static inline void bio_clear_flag(struct bio *bio, unsigned int bit)
+{
+	bio->bi_flags &= ~(1U << bit);
+}
+
 /*
  * Check whether this bio carries any data or not. A NULL bio is allowed.
  */
@@ -225,21 +240,6 @@ static inline void bio_cnt_set(struct bio *bio, unsigned int count)
 	atomic_set(&bio->__bi_cnt, count);
 }
 
-static inline bool bio_flagged(struct bio *bio, unsigned int bit)
-{
-	return bio->bi_flags & (1U << bit);
-}
-
-static inline void bio_set_flag(struct bio *bio, unsigned int bit)
-{
-	bio->bi_flags |= (1U << bit);
-}
-
-static inline void bio_clear_flag(struct bio *bio, unsigned int bit)
-{
-	bio->bi_flags &= ~(1U << bit);
-}
-
 static inline struct bio_vec *bio_first_bvec_all(struct bio *bio)
 {
 	WARN_ON_ONCE(bio_flagged(bio, BIO_CLONED));
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 6498be4c44f8..e5be698256d1 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -1283,6 +1283,8 @@ struct bpf_ksym {
 	struct list_head	 lnode;
 	struct latch_tree_node	 tnode;
 	bool			 prog;
+	u32			 fp_start;
+	u32			 fp_end;
 };
 
 enum bpf_tramp_prog_type {
@@ -1511,6 +1513,7 @@ void bpf_image_ksym_add(struct bpf_ksym *ksym);
 void bpf_image_ksym_del(struct bpf_ksym *ksym);
 void bpf_ksym_add(struct bpf_ksym *ksym);
 void bpf_ksym_del(struct bpf_ksym *ksym);
+bool bpf_has_frame_pointer(unsigned long ip);
 int bpf_jit_charge_modmem(u32 size);
 void bpf_jit_uncharge_modmem(u32 size);
 bool bpf_prog_has_trampoline(const struct bpf_prog *prog);
diff --git a/include/linux/compiler-clang.h b/include/linux/compiler-clang.h
index 107ce05bd16e..7edf1a07b535 100644
--- a/include/linux/compiler-clang.h
+++ b/include/linux/compiler-clang.h
@@ -145,6 +145,7 @@
  */
 #define ASM_INPUT_G "ir"
 #define ASM_INPUT_RM "r"
+#define ASM_OUTPUT_RM "=r"
 
 /*
  * Declare compiler support for __typeof_unqual__() operator.
diff --git a/include/linux/compiler_types.h b/include/linux/compiler_types.h
index 1280693766b9..d3318a3c2577 100644
--- a/include/linux/compiler_types.h
+++ b/include/linux/compiler_types.h
@@ -548,11 +548,12 @@ struct ftrace_likely_data {
 
 /*
  * Clang has trouble with constraints with multiple
- * alternative behaviors (mainly "g" and "rm").
+ * alternative behaviors ("g" , "rm" and "=rm").
  */
 #ifndef ASM_INPUT_G
   #define ASM_INPUT_G "g"
   #define ASM_INPUT_RM "rm"
+  #define ASM_OUTPUT_RM "=rm"
 #endif
 
 #ifdef CONFIG_CC_HAS_ASM_INLINE
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 04ceeca12a0d..f5c9cf28c4dc 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -3247,7 +3247,7 @@ struct offset_ctx {
 void simple_offset_init(struct offset_ctx *octx);
 int simple_offset_add(struct offset_ctx *octx, struct dentry *dentry);
 void simple_offset_remove(struct offset_ctx *octx, struct dentry *dentry);
-int simple_offset_rename(struct inode *old_dir, struct dentry *old_dentry,
+void simple_offset_rename(struct inode *old_dir, struct dentry *old_dentry,
 			 struct inode *new_dir, struct dentry *new_dentry);
 int simple_offset_rename_exchange(struct inode *old_dir,
 				  struct dentry *old_dentry,
diff --git a/include/linux/intel_rapl.h b/include/linux/intel_rapl.h
index e9ade2ff4af6..f479ef5b3341 100644
--- a/include/linux/intel_rapl.h
+++ b/include/linux/intel_rapl.h
@@ -214,10 +214,14 @@ void rapl_remove_package(struct rapl_package *rp);
 
 #ifdef CONFIG_PERF_EVENTS
 int rapl_package_add_pmu(struct rapl_package *rp);
+int rapl_package_add_pmu_locked(struct rapl_package *rp);
 void rapl_package_remove_pmu(struct rapl_package *rp);
+void rapl_package_remove_pmu_locked(struct rapl_package *rp);
 #else
 static inline int rapl_package_add_pmu(struct rapl_package *rp) { return 0; }
+static inline int rapl_package_add_pmu_locked(struct rapl_package *rp) { return 0; }
 static inline void rapl_package_remove_pmu(struct rapl_package *rp) { }
+static inline void rapl_package_remove_pmu_locked(struct rapl_package *rp) { }
 #endif
 
 #endif /* __INTEL_RAPL_H__ */
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index 1c54aa6f74fb..e2d067b1e67b 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -1149,6 +1149,7 @@ int mlx5_cmd_destroy_vport_lag(struct mlx5_core_dev *dev);
 bool mlx5_lag_is_roce(struct mlx5_core_dev *dev);
 bool mlx5_lag_is_sriov(struct mlx5_core_dev *dev);
 bool mlx5_lag_is_active(struct mlx5_core_dev *dev);
+int mlx5_lag_query_bond_speed(struct mlx5_core_dev *dev, u32 *speed);
 bool mlx5_lag_mode_is_hash(struct mlx5_core_dev *dev);
 bool mlx5_lag_is_master(struct mlx5_core_dev *dev);
 bool mlx5_lag_is_shared_fdb(struct mlx5_core_dev *dev);
diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index e9dcd4bf355d..e844cfa4fe0a 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -1071,7 +1071,9 @@ struct mlx5_ifc_e_switch_cap_bits {
 	u8         esw_shared_ingress_acl[0x1];
 	u8         esw_uplink_ingress_acl[0x1];
 	u8         root_ft_on_other_esw[0x1];
-	u8         reserved_at_a[0xf];
+	u8         reserved_at_a[0x1];
+	u8         esw_vport_state_max_tx_speed[0x1];
+	u8         reserved_at_c[0xd];
 	u8         esw_functions_changed[0x1];
 	u8         reserved_at_1a[0x1];
 	u8         ecpf_vport_exists[0x1];
@@ -5445,7 +5447,8 @@ struct mlx5_ifc_query_vport_state_out_bits {
 
 	u8         reserved_at_40[0x20];
 
-	u8         reserved_at_60[0x18];
+	u8         max_tx_speed[0x10];
+	u8         reserved_at_70[0x8];
 	u8         admin_state[0x4];
 	u8         state[0x4];
 };
@@ -7778,7 +7781,7 @@ struct mlx5_ifc_modify_vport_state_in_bits {
 	u8         reserved_at_41[0xf];
 	u8         vport_number[0x10];
 
-	u8         reserved_at_60[0x10];
+	u8         max_tx_speed[0x10];
 	u8         ingress_connect[0x1];
 	u8         egress_connect[0x1];
 	u8         ingress_connect_valid[0x1];
diff --git a/include/linux/mlx5/vport.h b/include/linux/mlx5/vport.h
index f876bfc0669c..dfa2fe32217a 100644
--- a/include/linux/mlx5/vport.h
+++ b/include/linux/mlx5/vport.h
@@ -41,6 +41,8 @@
 	 (MLX5_CAP_GEN(mdev, port_type) == MLX5_CAP_PORT_TYPE_ETH) &&	\
 	 mlx5_core_is_pf(mdev))
 
+#define MLX5_MAX_TX_SPEED_UNIT 100
+
 enum {
 	MLX5_CAP_INLINE_MODE_L2,
 	MLX5_CAP_INLINE_MODE_VPORT_CONTEXT,
@@ -58,6 +60,10 @@ enum {
 u8 mlx5_query_vport_state(struct mlx5_core_dev *mdev, u8 opmod, u16 vport);
 int mlx5_modify_vport_admin_state(struct mlx5_core_dev *mdev, u8 opmod,
 				  u16 vport, u8 other_vport, u8 state);
+int mlx5_query_vport_max_tx_speed(struct mlx5_core_dev *mdev, u8 op_mod,
+				  u16 vport, u8 other_vport, u32 *max_tx_speed);
+int mlx5_modify_vport_max_tx_speed(struct mlx5_core_dev *mdev, u8 opmod,
+				   u16 vport, u8 other_vport, u16 max_tx_speed);
 int mlx5_query_nic_vport_mac_address(struct mlx5_core_dev *mdev,
 				     u16 vport, bool other, u8 *addr);
 int mlx5_query_mac_address(struct mlx5_core_dev *mdev, u8 *addr);
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 9f6de068295d..42af2292951d 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -1631,7 +1631,6 @@ enum tlb_flush_reason {
 	TLB_LOCAL_MM_SHOOTDOWN,
 	TLB_REMOTE_SEND_IPI,
 	TLB_REMOTE_WRONG_CPU,
-	NR_TLB_FLUSH_REASONS,
 };
 
 /**
diff --git a/include/linux/property.h b/include/linux/property.h
index 272bfbdea7bf..e30ef23a9af3 100644
--- a/include/linux/property.h
+++ b/include/linux/property.h
@@ -371,6 +371,7 @@ struct software_node_ref_args {
 (const struct software_node_ref_args) {				\
 	.swnode = _Generic(_ref_,				\
 			   const struct software_node *: _ref_,	\
+			   struct software_node *: _ref_,	\
 			   default: NULL),			\
 	.fwnode = _Generic(_ref_,				\
 			   struct fwnode_handle *: _ref_,	\
diff --git a/include/linux/virtio.h b/include/linux/virtio.h
index 132a474e5914..3626eb694728 100644
--- a/include/linux/virtio.h
+++ b/include/linux/virtio.h
@@ -13,6 +13,8 @@
 #include <linux/completion.h>
 #include <linux/virtio_features.h>
 
+struct module;
+
 /**
  * struct virtqueue - a queue to register buffers for sending or receiving.
  * @list: the chain of virtqueues for this device
diff --git a/include/linux/virtio_features.h b/include/linux/virtio_features.h
index ea2ad8717882..ce59ea91f474 100644
--- a/include/linux/virtio_features.h
+++ b/include/linux/virtio_features.h
@@ -3,6 +3,8 @@
 #define _LINUX_VIRTIO_FEATURES_H
 
 #include <linux/bits.h>
+#include <linux/bug.h>
+#include <linux/string.h>
 
 #define VIRTIO_FEATURES_U64S	2
 #define VIRTIO_FEATURES_BITS	(VIRTIO_FEATURES_U64S * 64)