Merge tag 'mlx5-updates-2017-11-04' of git://git.kernel.org/pub/scm/linux/kernel/git/saeed/linux

Saeed Mahameed says:

====================
mlx5-updates-2017-11-04

This series includes:

From Huy: dscp to priority mapping for Ethernet packet.

===================================================
First six patches enable differentiated services code point (dscp) to
priority mapping for Ethernet packet. Once this feature is
enabled, the packet is routed to the corresponding priority based on its
dscp. User can combine this feature with priority flow control (pfc)
feature to have priority flow control based on the dscp.

Firmware interface:
Mellanox firmware provides two control knobs for this feature:
  QPTS register allow changing the trust state between dscp and
  pcp mode. The default is pcp mode. Once in dscp mode, firmware will
  route the packet based on its dscp value if the dscp field exists.

  QPDPM register allow mapping a specific dscp (0 to 63) to a
  specific priority (0 to 7). By default, all the dscps are mapped to
  priority zero.

Software interface:
This feature is controlled via application priority TLV. IEEE
specification P802.1Qcd/D2.1 defines priority selector id 5 for
application priority TLV. This APP TLV selector defines DSCP to priority
map. This APP TLV can be sent by the switch or can be set locally using
software such as lldptool. In mlx5 drivers, we add the support for net
dcb's getapp and setapp call back. Mlx5 driver only handles the selector
id 5 application entry (dscp application priority application entry).
If user sends multiple dscp to priority APP TLV entries on the same
dscp, the last sent one will take effect. All the previous sent will be
deleted.

The firmware trust state (in QPTS register) is changed based on the
number of dscp to priority application entries. When the first dscp to
priority application entry is added by the user, the trust state is
changed to dscp. When the last dscp to priority application entry is
deleted by the user, the trust state is changed to pcp.

When the port is in DSCP trust state, the transmit queue is selected
based on the dscp of the skb.

When the port is in DSCP trust state and vport inline mode is not NONE,
firmware requires mlx5 driver to copy the IP header to the
wqe ethernet segment inline header if the skb has it.
This is done by changing the transmit queue sq's min inline mode to L3.
Note that the min inline mode of sqs that belong to other features
such as xdpsq, icosq are not modified.
===================================================

Plus to the dscp series, some small misc changes are include as well:

From Inbar, Ethtool msglvl support and some debug prints in DCBNL logic
From Or Gerlitz, Enlarge the NIC TC offload table size
From Rabie, Initialize destination_flow struct to 0
From Feras, Add inner TTC table to IPoIB flow steering
From Tal, Enable CQE based moderation on TX CQ
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

5 files changed, 105 insertions, 1 deletions

diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h
index e32dbc4934db..409ffb14298a 100644
--- a/include/linux/mlx5/device.h
+++ b/include/linux/mlx5/device.h
@@ -49,11 +49,15 @@
 #define __mlx5_nullp(typ) ((struct mlx5_ifc_##typ##_bits *)0)
 #define __mlx5_bit_sz(typ, fld) sizeof(__mlx5_nullp(typ)->fld)
 #define __mlx5_bit_off(typ, fld) (offsetof(struct mlx5_ifc_##typ##_bits, fld))
+#define __mlx5_16_off(typ, fld) (__mlx5_bit_off(typ, fld) / 16)
 #define __mlx5_dw_off(typ, fld) (__mlx5_bit_off(typ, fld) / 32)
 #define __mlx5_64_off(typ, fld) (__mlx5_bit_off(typ, fld) / 64)
+#define __mlx5_16_bit_off(typ, fld) (16 - __mlx5_bit_sz(typ, fld) - (__mlx5_bit_off(typ, fld) & 0xf))
 #define __mlx5_dw_bit_off(typ, fld) (32 - __mlx5_bit_sz(typ, fld) - (__mlx5_bit_off(typ, fld) & 0x1f))
 #define __mlx5_mask(typ, fld) ((u32)((1ull << __mlx5_bit_sz(typ, fld)) - 1))
 #define __mlx5_dw_mask(typ, fld) (__mlx5_mask(typ, fld) << __mlx5_dw_bit_off(typ, fld))
+#define __mlx5_mask16(typ, fld) ((u16)((1ull << __mlx5_bit_sz(typ, fld)) - 1))
+#define __mlx5_16_mask(typ, fld) (__mlx5_mask16(typ, fld) << __mlx5_16_bit_off(typ, fld))
 #define __mlx5_st_sz_bits(typ) sizeof(struct mlx5_ifc_##typ##_bits)
 
 #define MLX5_FLD_SZ_BYTES(typ, fld) (__mlx5_bit_sz(typ, fld) / 8)
@@ -116,6 +120,19 @@ __mlx5_mask(typ, fld))
 	___t; \
 })
 
+#define MLX5_GET16(typ, p, fld) ((be16_to_cpu(*((__be16 *)(p) +\
+__mlx5_16_off(typ, fld))) >> __mlx5_16_bit_off(typ, fld)) & \
+__mlx5_mask16(typ, fld))
+
+#define MLX5_SET16(typ, p, fld, v) do { \
+	u16 _v = v; \
+	BUILD_BUG_ON(__mlx5_st_sz_bits(typ) % 16);             \
+	*((__be16 *)(p) + __mlx5_16_off(typ, fld)) = \
+	cpu_to_be16((be16_to_cpu(*((__be16 *)(p) + __mlx5_16_off(typ, fld))) & \
+		     (~__mlx5_16_mask(typ, fld))) | (((_v) & __mlx5_mask16(typ, fld)) \
+		     << __mlx5_16_bit_off(typ, fld))); \
+} while (0)
+
 /* Big endian getters */
 #define MLX5_GET64_BE(typ, p, fld) (*((__be64 *)(p) +\
 	__mlx5_64_off(typ, fld)))
@@ -1000,6 +1017,14 @@ enum mlx5_mcam_feature_groups {
 	MLX5_MCAM_FEATURE_ENHANCED_FEATURES         = 0x0,
 };
 
+enum mlx5_qcam_reg_groups {
+	MLX5_QCAM_REGS_FIRST_128                    = 0x0,
+};
+
+enum mlx5_qcam_feature_groups {
+	MLX5_QCAM_FEATURE_ENHANCED_FEATURES         = 0x0,
+};
+
 /* GET Dev Caps macros */
 #define MLX5_CAP_GEN(mdev, cap) \
 	MLX5_GET(cmd_hca_cap, mdev->caps.hca_cur[MLX5_CAP_GENERAL], cap)
@@ -1108,6 +1133,12 @@ enum mlx5_mcam_feature_groups {
 #define MLX5_CAP_MCAM_FEATURE(mdev, fld) \
 	MLX5_GET(mcam_reg, (mdev)->caps.mcam, mng_feature_cap_mask.enhanced_features.fld)
 
+#define MLX5_CAP_QCAM_REG(mdev, fld) \
+	MLX5_GET(qcam_reg, (mdev)->caps.qcam, qos_access_reg_cap_mask.reg_cap.fld)
+
+#define MLX5_CAP_QCAM_FEATURE(mdev, fld) \
+	MLX5_GET(qcam_reg, (mdev)->caps.qcam, qos_feature_cap_mask.feature_cap.fld)
+
 #define MLX5_CAP_FPGA(mdev, cap) \
 	MLX5_GET(fpga_cap, (mdev)->caps.fpga, cap)
 
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index 08c77b7e59cb..a886b51511ab 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -107,8 +107,11 @@ enum {
 };
 
 enum {
+	MLX5_REG_QPTS            = 0x4002,
 	MLX5_REG_QETCR		 = 0x4005,
 	MLX5_REG_QTCT		 = 0x400a,
+	MLX5_REG_QPDPM           = 0x4013,
+	MLX5_REG_QCAM            = 0x4019,
 	MLX5_REG_DCBX_PARAM      = 0x4020,
 	MLX5_REG_DCBX_APP        = 0x4021,
 	MLX5_REG_FPGA_CAP	 = 0x4022,
@@ -141,6 +144,11 @@ enum {
 	MLX5_REG_MCAM		 = 0x907f,
 };
 
+enum mlx5_qpts_trust_state {
+	MLX5_QPTS_TRUST_PCP  = 1,
+	MLX5_QPTS_TRUST_DSCP = 2,
+};
+
 enum mlx5_dcbx_oper_mode {
 	MLX5E_DCBX_PARAM_VER_OPER_HOST  = 0x0,
 	MLX5E_DCBX_PARAM_VER_OPER_AUTO  = 0x3,
@@ -798,6 +806,7 @@ struct mlx5_core_dev {
 		u32 pcam[MLX5_ST_SZ_DW(pcam_reg)];
 		u32 mcam[MLX5_ST_SZ_DW(mcam_reg)];
 		u32 fpga[MLX5_ST_SZ_DW(fpga_cap)];
+		u32 qcam[MLX5_ST_SZ_DW(qcam_reg)];
 	} caps;
 	phys_addr_t		iseg_base;
 	struct mlx5_init_seg __iomem *iseg;
diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index 69772347f866..3e5363f760dd 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -838,7 +838,8 @@ struct mlx5_ifc_cmd_hca_cap_bits {
 	u8         cc_modify_allowed[0x1];
 	u8         start_pad[0x1];
 	u8         cache_line_128byte[0x1];
-	u8         reserved_at_165[0xb];
+	u8         reserved_at_165[0xa];
+	u8         qcam_reg[0x1];
 	u8         gid_table_size[0x10];
 
 	u8         out_of_seq_cnt[0x1];
@@ -7890,6 +7891,43 @@ struct mlx5_ifc_mcam_reg_bits {
 	u8         reserved_at_1c0[0x80];
 };
 
+struct mlx5_ifc_qcam_access_reg_cap_mask {
+	u8         qcam_access_reg_cap_mask_127_to_20[0x6C];
+	u8         qpdpm[0x1];
+	u8         qcam_access_reg_cap_mask_18_to_4[0x0F];
+	u8         qdpm[0x1];
+	u8         qpts[0x1];
+	u8         qcap[0x1];
+	u8         qcam_access_reg_cap_mask_0[0x1];
+};
+
+struct mlx5_ifc_qcam_qos_feature_cap_mask {
+	u8         qcam_qos_feature_cap_mask_127_to_1[0x7F];
+	u8         qpts_trust_both[0x1];
+};
+
+struct mlx5_ifc_qcam_reg_bits {
+	u8         reserved_at_0[0x8];
+	u8         feature_group[0x8];
+	u8         reserved_at_10[0x8];
+	u8         access_reg_group[0x8];
+	u8         reserved_at_20[0x20];
+
+	union {
+		struct mlx5_ifc_qcam_access_reg_cap_mask reg_cap;
+		u8  reserved_at_0[0x80];
+	} qos_access_reg_cap_mask;
+
+	u8         reserved_at_c0[0x80];
+
+	union {
+		struct mlx5_ifc_qcam_qos_feature_cap_mask feature_cap;
+		u8  reserved_at_0[0x80];
+	} qos_feature_cap_mask;
+
+	u8         reserved_at_1c0[0x80];
+};
+
 struct mlx5_ifc_pcap_reg_bits {
 	u8         reserved_at_0[0x8];
 	u8         local_port[0x8];
@@ -8540,6 +8578,26 @@ struct mlx5_ifc_qetc_reg_bits {
 	struct mlx5_ifc_ets_global_config_reg_bits global_configuration;
 };
 
+struct mlx5_ifc_qpdpm_dscp_reg_bits {
+	u8         e[0x1];
+	u8         reserved_at_01[0x0b];
+	u8         prio[0x04];
+};
+
+struct mlx5_ifc_qpdpm_reg_bits {
+	u8                                     reserved_at_0[0x8];
+	u8                                     local_port[0x8];
+	u8                                     reserved_at_10[0x10];
+	struct mlx5_ifc_qpdpm_dscp_reg_bits    dscp[64];
+};
+
+struct mlx5_ifc_qpts_reg_bits {
+	u8         reserved_at_0[0x8];
+	u8         local_port[0x8];
+	u8         reserved_at_10[0x2d];
+	u8         trust_state[0x3];
+};
+
 struct mlx5_ifc_qtct_reg_bits {
 	u8         reserved_at_0[0x8];
 	u8         port_number[0x8];
diff --git a/include/linux/mlx5/port.h b/include/linux/mlx5/port.h
index c59af8ab753a..035f0d4dc9fe 100644
--- a/include/linux/mlx5/port.h
+++ b/include/linux/mlx5/port.h
@@ -179,4 +179,9 @@ int mlx5_query_module_eeprom(struct mlx5_core_dev *dev,
 
 int mlx5_query_port_dcbx_param(struct mlx5_core_dev *mdev, u32 *out);
 int mlx5_set_port_dcbx_param(struct mlx5_core_dev *mdev, u32 *in);
+
+int mlx5_set_trust_state(struct mlx5_core_dev *mdev, u8 trust_state);
+int mlx5_query_trust_state(struct mlx5_core_dev *mdev, u8 *trust_state);
+int mlx5_set_dscp2prio(struct mlx5_core_dev *mdev, u8 dscp, u8 prio);
+int mlx5_query_dscp2prio(struct mlx5_core_dev *mdev, u8 *dscp2prio);
 #endif /* __MLX5_PORT_H__ */
diff --git a/include/uapi/linux/dcbnl.h b/include/uapi/linux/dcbnl.h
index b6170a6af7c2..2c0c6453c3f4 100644
--- a/include/uapi/linux/dcbnl.h
+++ b/include/uapi/linux/dcbnl.h
@@ -206,6 +206,7 @@ struct cee_pfc {
 #define IEEE_8021QAZ_APP_SEL_STREAM	2
 #define IEEE_8021QAZ_APP_SEL_DGRAM	3
 #define IEEE_8021QAZ_APP_SEL_ANY	4
+#define IEEE_8021QAZ_APP_SEL_DSCP       5
 
 /* This structure contains the IEEE 802.1Qaz APP managed object. This
  * object is also used for the CEE std as well.