Merge branch 'mlx5-next' of git://git.kernel.org/pub/scm/linux/kernel/git/mellanox/linux

This merge commit includes some misc shared code updates from mlx5-next branch needed
for net-next.

1) From Maxim, Remove un-used macros and spinlock from mlx5 code.

2) From Aya, Expose Management PCIE info register layout and add rate limit
print macros.

3) From Tariq, Compilation warning fix in fs_core.c

4) From Vu, Huy and Saeed, Improve mlx5 initialization flow:
The goal is to provide a better logical separation of mlx5 core
device initialization flow and will help to seamlessly support
creating different mlx5 device types such as PF, VF and SF
mlx5 sub-function virtual devices.

Mlx5_core driver needs to separate HCA resources from pci resources.
Its initialize/load/unload will be broken into stages:
1. Initialize common data structures
2. Setup function which initializes pci resources (for PF/VF)
   or some other specific resources for virtual device
3. Initialize software objects according to hardware capabilities
4. Load all mlx5_core components

It is also necessary to detach mlx5_core mdev name/message from pci
device mdev->pdev name/message for a clearer report/debug of
different mlx5 device types.

Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>

4 files changed, 63 insertions, 32 deletions

diff --git a/include/linux/mlx5/cq.h b/include/linux/mlx5/cq.h
index 612c8c2f2466..769326ea1d9b 100644
--- a/include/linux/mlx5/cq.h
+++ b/include/linux/mlx5/cq.h
@@ -170,7 +170,7 @@ static inline void mlx5_cq_arm(struct mlx5_core_cq *cq, u32 cmd,
 	doorbell[0] = cpu_to_be32(sn << 28 | cmd | ci);
 	doorbell[1] = cpu_to_be32(cq->cqn);
 
-	mlx5_write64(doorbell, uar_page + MLX5_CQ_DOORBELL, NULL);
+	mlx5_write64(doorbell, uar_page + MLX5_CQ_DOORBELL);
 }
 
 static inline void mlx5_cq_hold(struct mlx5_core_cq *cq)
diff --git a/include/linux/mlx5/doorbell.h b/include/linux/mlx5/doorbell.h
index 0787de28f2fc..5c267707e1df 100644
--- a/include/linux/mlx5/doorbell.h
+++ b/include/linux/mlx5/doorbell.h
@@ -36,46 +36,25 @@
 #define MLX5_BF_OFFSET	      0x800
 #define MLX5_CQ_DOORBELL      0x20
 
-#if BITS_PER_LONG == 64
 /* Assume that we can just write a 64-bit doorbell atomically.  s390
  * actually doesn't have writeq() but S/390 systems don't even have
  * PCI so we won't worry about it.
+ *
+ * Note that the write is not atomic on 32-bit systems! In contrast to 64-bit
+ * ones, it requires proper locking. mlx5_write64 doesn't do any locking, so use
+ * it at your own discretion, protected by some kind of lock on 32 bits.
+ *
+ * TODO: use write{q,l}_relaxed()
  */
 
-#define MLX5_DECLARE_DOORBELL_LOCK(name)
-#define MLX5_INIT_DOORBELL_LOCK(ptr)    do { } while (0)
-#define MLX5_GET_DOORBELL_LOCK(ptr)      (NULL)
-
-static inline void mlx5_write64(__be32 val[2], void __iomem *dest,
-				spinlock_t *doorbell_lock)
+static inline void mlx5_write64(__be32 val[2], void __iomem *dest)
 {
+#if BITS_PER_LONG == 64
 	__raw_writeq(*(u64 *)val, dest);
-}
-
 #else
-
-/* Just fall back to a spinlock to protect the doorbell if
- * BITS_PER_LONG is 32 -- there's no portable way to do atomic 64-bit
- * MMIO writes.
- */
-
-#define MLX5_DECLARE_DOORBELL_LOCK(name) spinlock_t name;
-#define MLX5_INIT_DOORBELL_LOCK(ptr)     spin_lock_init(ptr)
-#define MLX5_GET_DOORBELL_LOCK(ptr)      (ptr)
-
-static inline void mlx5_write64(__be32 val[2], void __iomem *dest,
-				spinlock_t *doorbell_lock)
-{
-	unsigned long flags;
-
-	if (doorbell_lock)
-		spin_lock_irqsave(doorbell_lock, flags);
 	__raw_writel((__force u32) val[0], dest);
 	__raw_writel((__force u32) val[1], dest + 4);
-	if (doorbell_lock)
-		spin_unlock_irqrestore(doorbell_lock, flags);
-}
-
 #endif
+}
 
 #endif /* MLX5_DOORBELL_H */
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index 022541dc5dbf..6c43191c0186 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -133,6 +133,7 @@ enum {
 	MLX5_REG_MTRC_CONF	 = 0x9041,
 	MLX5_REG_MTRC_STDB	 = 0x9042,
 	MLX5_REG_MTRC_CTRL	 = 0x9043,
+	MLX5_REG_MPEIN		 = 0x9050,
 	MLX5_REG_MPCNT		 = 0x9051,
 	MLX5_REG_MTPPS		 = 0x9053,
 	MLX5_REG_MTPPSE		 = 0x9054,
@@ -660,6 +661,7 @@ struct mlx5_core_dev {
 	u64			sys_image_guid;
 	phys_addr_t		iseg_base;
 	struct mlx5_init_seg __iomem *iseg;
+	phys_addr_t             bar_addr;
 	enum mlx5_device_state	state;
 	/* sync interface state */
 	struct mutex		intf_state_mutex;
@@ -885,6 +887,7 @@ void mlx5_cmd_mbox_status(void *out, u8 *status, u32 *syndrome);
 int mlx5_core_get_caps(struct mlx5_core_dev *dev, enum mlx5_cap_type cap_type);
 int mlx5_cmd_alloc_uar(struct mlx5_core_dev *dev, u32 *uarn);
 int mlx5_cmd_free_uar(struct mlx5_core_dev *dev, u32 uarn);
+void mlx5_health_flush(struct mlx5_core_dev *dev);
 void mlx5_health_cleanup(struct mlx5_core_dev *dev);
 int mlx5_health_init(struct mlx5_core_dev *dev);
 void mlx5_start_health_poll(struct mlx5_core_dev *dev);
diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index b0e17c94566c..0e0e63d4d7aa 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -8027,6 +8027,52 @@ struct mlx5_ifc_ppcnt_reg_bits {
 	union mlx5_ifc_eth_cntrs_grp_data_layout_auto_bits counter_set;
 };
 
+struct mlx5_ifc_mpein_reg_bits {
+	u8         reserved_at_0[0x2];
+	u8         depth[0x6];
+	u8         pcie_index[0x8];
+	u8         node[0x8];
+	u8         reserved_at_18[0x8];
+
+	u8         capability_mask[0x20];
+
+	u8         reserved_at_40[0x8];
+	u8         link_width_enabled[0x8];
+	u8         link_speed_enabled[0x10];
+
+	u8         lane0_physical_position[0x8];
+	u8         link_width_active[0x8];
+	u8         link_speed_active[0x10];
+
+	u8         num_of_pfs[0x10];
+	u8         num_of_vfs[0x10];
+
+	u8         bdf0[0x10];
+	u8         reserved_at_b0[0x10];
+
+	u8         max_read_request_size[0x4];
+	u8         max_payload_size[0x4];
+	u8         reserved_at_c8[0x5];
+	u8         pwr_status[0x3];
+	u8         port_type[0x4];
+	u8         reserved_at_d4[0xb];
+	u8         lane_reversal[0x1];
+
+	u8         reserved_at_e0[0x14];
+	u8         pci_power[0xc];
+
+	u8         reserved_at_100[0x20];
+
+	u8         device_status[0x10];
+	u8         port_state[0x8];
+	u8         reserved_at_138[0x8];
+
+	u8         reserved_at_140[0x10];
+	u8         receiver_detect_result[0x10];
+
+	u8         reserved_at_160[0x20];
+};
+
 struct mlx5_ifc_mpcnt_reg_bits {
 	u8         reserved_at_0[0x8];
 	u8         pcie_index[0x8];
@@ -8346,7 +8392,9 @@ struct mlx5_ifc_pcam_reg_bits {
 };
 
 struct mlx5_ifc_mcam_enhanced_features_bits {
-	u8         reserved_at_0[0x74];
+	u8         reserved_at_0[0x6e];
+	u8         pci_status_and_power[0x1];
+	u8         reserved_at_6f[0x5];
 	u8         mark_tx_action_cnp[0x1];
 	u8         mark_tx_action_cqe[0x1];
 	u8         dynamic_tx_overflow[0x1];
@@ -8954,6 +9002,7 @@ union mlx5_ifc_ports_control_registers_document_bits {
 	struct mlx5_ifc_pmtu_reg_bits pmtu_reg;
 	struct mlx5_ifc_ppad_reg_bits ppad_reg;
 	struct mlx5_ifc_ppcnt_reg_bits ppcnt_reg;
+	struct mlx5_ifc_mpein_reg_bits mpein_reg;
 	struct mlx5_ifc_mpcnt_reg_bits mpcnt_reg;
 	struct mlx5_ifc_pplm_reg_bits pplm_reg;
 	struct mlx5_ifc_pplr_reg_bits pplr_reg;