Merge branch 'mana-per-vport-eq'

Long Li says:

====================
net: mana: Per-vPort EQ and MSI-X management

This series moves EQ ownership from the shared mana_context to per-vPort
mana_port_context, enabling each vPort to have dedicated MSI-X vectors
when the hardware provides enough vectors. When vectors are limited, the
driver falls back to sharing MSI-X among vPorts.

The series introduces a GDMA IRQ Context (GIC) abstraction with reference
counting to manage interrupt context lifecycle. This allows both Ethernet
and RDMA EQs to dynamically acquire dedicated or shared MSI-X vectors at
vPort creation time rather than pre-allocating all vectors at probe time.
====================

Link: https://patch.msgid.link/20260605005717.2059954-1-longli@microsoft.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

2 files changed, 42 insertions, 6 deletions

diff --git a/include/net/mana/gdma.h b/include/net/mana/gdma.h
index 70d62bc32837..78afd696b08b 100644
--- a/include/net/mana/gdma.h
+++ b/include/net/mana/gdma.h
@@ -342,6 +342,7 @@ struct gdma_queue {
 			void *context;
 
 			unsigned int msix_index;
+			unsigned int irq;
 
 			u32 log2_throttle_limit;
 		} eq;
@@ -388,6 +389,11 @@ struct gdma_irq_context {
 	spinlock_t lock;
 	struct list_head eq_list;
 	char name[MANA_IRQ_NAME_SZ];
+	unsigned int msi;
+	unsigned int irq;
+	refcount_t refcount;
+	unsigned int bitmap_refs;
+	bool dyn_msix;
 };
 
 enum gdma_context_flags {
@@ -399,8 +405,10 @@ struct gdma_context {
 	struct device		*dev;
 	struct dentry		*mana_pci_debugfs;
 
-	/* Per-vPort max number of queues */
+	/* Hardware max number of queues */
 	unsigned int		max_num_queues;
+	/* Per-vPort max number of queues */
+	unsigned int		max_num_queues_vport;
 	unsigned int		max_num_msix;
 	unsigned int		num_msix_usable;
 	struct xarray		irq_contexts;
@@ -447,6 +455,15 @@ struct gdma_context {
 	struct workqueue_struct *service_wq;
 
 	unsigned long		flags;
+
+	/* Protect access to GIC context */
+	struct mutex		gic_mutex;
+
+	/* Indicate if this device is sharing MSI for EQs on MANA */
+	bool msi_sharing;
+
+	/* Bitmap tracks where MSI is allocated when it is not shared for EQs */
+	unsigned long *msi_bitmap;
 };
 
 static inline bool mana_gd_is_mana(struct gdma_dev *gd)
@@ -599,6 +616,7 @@ enum {
 #define GDMA_DRV_CAP_FLAG_1_HWC_TIMEOUT_RECONFIG BIT(3)
 #define GDMA_DRV_CAP_FLAG_1_GDMA_PAGES_4MB_1GB_2GB BIT(4)
 #define GDMA_DRV_CAP_FLAG_1_VARIABLE_INDIRECTION_TABLE_SUPPORT BIT(5)
+#define GDMA_DRV_CAP_FLAG_1_HW_VPORT_LINK_AWARE BIT(6)
 
 /* Driver can handle holes (zeros) in the device list */
 #define GDMA_DRV_CAP_FLAG_1_DEV_LIST_HOLES_SUP BIT(11)
@@ -615,7 +633,8 @@ enum {
 /* Driver detects stalled send queues and recovers them */
 #define GDMA_DRV_CAP_FLAG_1_HANDLE_STALL_SQ_RECOVERY BIT(18)
 
-#define GDMA_DRV_CAP_FLAG_1_HW_VPORT_LINK_AWARE BIT(6)
+/* Driver supports separate EQ/MSIs for each vPort */
+#define GDMA_DRV_CAP_FLAG_1_EQ_MSI_UNSHARE_MULTI_VPORT BIT(19)
 
 /* Driver supports linearizing the skb when num_sge exceeds hardware limit */
 #define GDMA_DRV_CAP_FLAG_1_SKB_LINEARIZE BIT(20)
@@ -643,7 +662,8 @@ enum {
 	 GDMA_DRV_CAP_FLAG_1_SKB_LINEARIZE | \
 	 GDMA_DRV_CAP_FLAG_1_PROBE_RECOVERY | \
 	 GDMA_DRV_CAP_FLAG_1_HANDLE_STALL_SQ_RECOVERY | \
-	 GDMA_DRV_CAP_FLAG_1_HWC_TIMEOUT_RECOVERY)
+	 GDMA_DRV_CAP_FLAG_1_HWC_TIMEOUT_RECOVERY | \
+	 GDMA_DRV_CAP_FLAG_1_EQ_MSI_UNSHARE_MULTI_VPORT)
 
 #define GDMA_DRV_CAP_FLAGS2 0
 
@@ -1019,4 +1039,11 @@ int mana_gd_resume(struct pci_dev *pdev);
 
 bool mana_need_log(struct gdma_context *gc, int err);
 
+struct gdma_irq_context *mana_gd_get_gic(struct gdma_context *gc,
+					 bool use_msi_bitmap,
+					 int *msi_requested);
+void mana_gd_put_gic(struct gdma_context *gc, bool use_msi_bitmap, int msi);
+int mana_gd_query_device_cfg(struct gdma_context *gc, u32 proto_major_ver,
+			     u32 proto_minor_ver, u32 proto_micro_ver,
+			     u16 *max_num_vports, u8 *bm_hostmode);
 #endif /* _GDMA_H */
diff --git a/include/net/mana/mana.h b/include/net/mana/mana.h
index d9c27310fd04..5a9b94e0ef34 100644
--- a/include/net/mana/mana.h
+++ b/include/net/mana/mana.h
@@ -480,8 +480,6 @@ struct mana_context {
 	u8 bm_hostmode;
 
 	struct mana_ethtool_hc_stats hc_stats;
-	struct mana_eq *eqs;
-	struct dentry *mana_eqs_debugfs;
 	struct workqueue_struct *per_port_queue_reset_wq;
 	/* Workqueue for querying hardware stats */
 	struct delayed_work gf_stats_work;
@@ -501,6 +499,9 @@ struct mana_port_context {
 
 	u8 mac_addr[ETH_ALEN];
 
+	struct mana_eq *eqs;
+	struct dentry *mana_eqs_debugfs;
+
 	enum TRI_STATE rss_state;
 
 	mana_handle_t default_rxobj;
@@ -547,6 +548,12 @@ struct mana_port_context {
 	struct mutex vport_mutex;
 	int vport_use_count;
 
+	/* Set by mana_set_channels() under vport_mutex to block RDMA
+	 * from grabbing the vport during the detach/attach window.
+	 * Checked by mana_cfg_vport() when called from the RDMA path.
+	 */
+	bool channel_changing;
+
 	/* Net shaper handle*/
 	struct net_shaper_handle handle;
 
@@ -1040,8 +1047,10 @@ void mana_destroy_wq_obj(struct mana_port_context *apc, u32 wq_type,
 			 mana_handle_t wq_obj);
 
 int mana_cfg_vport(struct mana_port_context *apc, u32 protection_dom_id,
-		   u32 doorbell_pg_id);
+		   u32 doorbell_pg_id, bool check_channel_changing);
 void mana_uncfg_vport(struct mana_port_context *apc);
+int mana_create_eq(struct mana_port_context *apc);
+void mana_destroy_eq(struct mana_port_context *apc);
 
 struct net_device *mana_get_primary_netdev(struct mana_context *ac,
 					   u32 port_index,