Merge tag 'net-next-6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-nextgrafted

Pull networking updates from Jakub Kicinski:
 "Core:

   - Add dedicated kmem_cache for typical/small skb->head, avoid having
     to access struct page at kfree time, and improve memory use.

   - Introduce sysctl to set default RPS configuration for new netdevs.

   - Define Netlink protocol specification format which can be used to
     describe messages used by each family and auto-generate parsers.
     Add tools for generating kernel data structures and uAPI headers.

   - Expose all net/core sysctls inside netns.

   - Remove 4s sleep in netpoll if carrier is instantly detected on
     boot.

   - Add configurable limit of MDB entries per port, and port-vlan.

   - Continue populating drop reasons throughout the stack.

   - Retire a handful of legacy Qdiscs and classifiers.

  Protocols:

   - Support IPv4 big TCP (TSO frames larger than 64kB).

   - Add IP_LOCAL_PORT_RANGE socket option, to control local port range
     on socket by socket basis.

   - Track and report in procfs number of MPTCP sockets used.

   - Support mixing IPv4 and IPv6 flows in the in-kernel MPTCP path
     manager.

   - IPv6: don't check net.ipv6.route.max_size and rely on garbage
     collection to free memory (similarly to IPv4).

   - Support Penultimate Segment Pop (PSP) flavor in SRv6 (RFC8986).

   - ICMP: add per-rate limit counters.

   - Add support for user scanning requests in ieee802154.

   - Remove static WEP support.

   - Support minimal Wi-Fi 7 Extremely High Throughput (EHT) rate
     reporting.

   - WiFi 7 EHT channel puncturing support (client & AP).

  BPF:

   - Add a rbtree data structure following the "next-gen data structure"
     precedent set by recently added linked list, that is, by using
     kfunc + kptr instead of adding a new BPF map type.

   - Expose XDP hints via kfuncs with initial support for RX hash and
     timestamp metadata.

   - Add BPF_F_NO_TUNNEL_KEY extension to bpf_skb_set_tunnel_key to
     better support decap on GRE tunnel devices not operating in collect
     metadata.

   - Improve x86 JIT's codegen for PROBE_MEM runtime error checks.

   - Remove the need for trace_printk_lock for bpf_trace_printk and
     bpf_trace_vprintk helpers.

   - Extend libbpf's bpf_tracing.h support for tracing arguments of
     kprobes/uprobes and syscall as a special case.

   - Significantly reduce the search time for module symbols by
     livepatch and BPF.

   - Enable cpumasks to be used as kptrs, which is useful for tracing
     programs tracking which tasks end up running on which CPUs in
     different time intervals.

   - Add support for BPF trampoline on s390x and riscv64.

   - Add capability to export the XDP features supported by the NIC.

   - Add __bpf_kfunc tag for marking kernel functions as kfuncs.

   - Add cgroup.memory=nobpf kernel parameter option to disable BPF
     memory accounting for container environments.

  Netfilter:

   - Remove the CLUSTERIP target. It has been marked as obsolete for
     years, and we still have WARN splats wrt races of the out-of-band
     /proc interface installed by this target.

   - Add 'destroy' commands to nf_tables. They are identical to the
     existing 'delete' commands, but do not return an error if the
     referenced object (set, chain, rule...) did not exist.

  Driver API:

   - Improve cpumask_local_spread() locality to help NICs set the right
     IRQ affinity on AMD platforms.

   - Separate C22 and C45 MDIO bus transactions more clearly.

   - Introduce new DCB table to control DSCP rewrite on egress.

   - Support configuration of Physical Layer Collision Avoidance (PLCA)
     Reconciliation Sublayer (RS) (802.3cg-2019). Modern version of
     shared medium Ethernet.

   - Support for MAC Merge layer (IEEE 802.3-2018 clause 99). Allowing
     preemption of low priority frames by high priority frames.

   - Add support for controlling MACSec offload using netlink SET.

   - Rework devlink instance refcounts to allow registration and
     de-registration under the instance lock. Split the code into
     multiple files, drop some of the unnecessarily granular locks and
     factor out common parts of netlink operation handling.

   - Add TX frame aggregation parameters (for USB drivers).

   - Add a new attr TCA_EXT_WARN_MSG to report TC (offload) warning
     messages with notifications for debug.

   - Allow offloading of UDP NEW connections via act_ct.

   - Add support for per action HW stats in TC.

   - Support hardware miss to TC action (continue processing in SW from
     a specific point in the action chain).

   - Warn if old Wireless Extension user space interface is used with
     modern cfg80211/mac80211 drivers. Do not support Wireless
     Extensions for Wi-Fi 7 devices at all. Everyone should switch to
     using nl80211 interface instead.

   - Improve the CAN bit timing configuration. Use extack to return
     error messages directly to user space, update the SJW handling,
     including the definition of a new default value that will benefit
     CAN-FD controllers, by increasing their oscillator tolerance.

  New hardware / drivers:

   - Ethernet:
      - nVidia BlueField-3 support (control traffic driver)
      - Ethernet support for imx93 SoCs
      - Motorcomm yt8531 gigabit Ethernet PHY
      - onsemi NCN26000 10BASE-T1S PHY (with support for PLCA)
      - Microchip LAN8841 PHY (incl. cable diagnostics and PTP)
      - Amlogic gxl MDIO mux

   - WiFi:
      - RealTek RTL8188EU (rtl8xxxu)
      - Qualcomm Wi-Fi 7 devices (ath12k)

   - CAN:
      - Renesas R-Car V4H

  Drivers:

   - Bluetooth:
      - Set Per Platform Antenna Gain (PPAG) for Intel controllers.

   - Ethernet NICs:
      - Intel (1G, igc):
         - support TSN / Qbv / packet scheduling features of i226 model
      - Intel (100G, ice):
         - use GNSS subsystem instead of TTY
         - multi-buffer XDP support
         - extend support for GPIO pins to E823 devices
      - nVidia/Mellanox:
         - update the shared buffer configuration on PFC commands
         - implement PTP adjphase function for HW offset control
         - TC support for Geneve and GRE with VF tunnel offload
         - more efficient crypto key management method
         - multi-port eswitch support
      - Netronome/Corigine:
         - add DCB IEEE support
         - support IPsec offloading for NFP3800
      - Freescale/NXP (enetc):
         - support XDP_REDIRECT for XDP non-linear buffers
         - improve reconfig, avoid link flap and waiting for idle
         - support MAC Merge layer
      - Other NICs:
         - sfc/ef100: add basic devlink support for ef100
         - ionic: rx_push mode operation (writing descriptors via MMIO)
         - bnxt: use the auxiliary bus abstraction for RDMA
         - r8169: disable ASPM and reset bus in case of tx timeout
         - cpsw: support QSGMII mode for J721e CPSW9G
         - cpts: support pulse-per-second output
         - ngbe: add an mdio bus driver
         - usbnet: optimize usbnet_bh() by avoiding unnecessary queuing
         - r8152: handle devices with FW with NCM support
         - amd-xgbe: support 10Mbps, 2.5GbE speeds and rx-adaptation
         - virtio-net: support multi buffer XDP
         - virtio/vsock: replace virtio_vsock_pkt with sk_buff
         - tsnep: XDP support

   - Ethernet high-speed switches:
      - nVidia/Mellanox (mlxsw):
         - add support for latency TLV (in FW control messages)
      - Microchip (sparx5):
         - separate explicit and implicit traffic forwarding rules, make
           the implicit rules always active
         - add support for egress DSCP rewrite
         - IS0 VCAP support (Ingress Classification)
         - IS2 VCAP filters (protos, L3 addrs, L4 ports, flags, ToS
           etc.)
         - ES2 VCAP support (Egress Access Control)
         - support for Per-Stream Filtering and Policing (802.1Q,
           8.6.5.1)

   - Ethernet embedded switches:
      - Marvell (mv88e6xxx):
         - add MAB (port auth) offload support
         - enable PTP receive for mv88e6390
      - NXP (ocelot):
         - support MAC Merge layer
         - support for the the vsc7512 internal copper phys
      - Microchip:
         - lan9303: convert to PHYLINK
         - lan966x: support TC flower filter statistics
         - lan937x: PTP support for KSZ9563/KSZ8563 and LAN937x
         - lan937x: support Credit Based Shaper configuration
         - ksz9477: support Energy Efficient Ethernet
      - other:
         - qca8k: convert to regmap read/write API, use bulk operations
         - rswitch: Improve TX timestamp accuracy

   - Intel WiFi (iwlwifi):
      - EHT (Wi-Fi 7) rate reporting
      - STEP equalizer support: transfer some STEP (connection to radio
        on platforms with integrated wifi) related parameters from the
        BIOS to the firmware.

   - Qualcomm 802.11ax WiFi (ath11k):
      - IPQ5018 support
      - Fine Timing Measurement (FTM) responder role support
      - channel 177 support

   - MediaTek WiFi (mt76):
      - per-PHY LED support
      - mt7996: EHT (Wi-Fi 7) support
      - Wireless Ethernet Dispatch (WED) reset support
      - switch to using page pool allocator

   - RealTek WiFi (rtw89):
      - support new version of Bluetooth co-existance

   - Mobile:
      - rmnet: support TX aggregation"

* tag 'net-next-6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (1872 commits)
  page_pool: add a comment explaining the fragment counter usage
  net: ethtool: fix __ethtool_dev_mm_supported() implementation
  ethtool: pse-pd: Fix double word in comments
  xsk: add linux/vmalloc.h to xsk.c
  sefltests: netdevsim: wait for devlink instance after netns removal
  selftest: fib_tests: Always cleanup before exit
  net/mlx5e: Align IPsec ASO result memory to be as required by hardware
  net/mlx5e: TC, Set CT miss to the specific ct action instance
  net/mlx5e: Rename CHAIN_TO_REG to MAPPED_OBJ_TO_REG
  net/mlx5: Refactor tc miss handling to a single function
  net/mlx5: Kconfig: Make tc offload depend on tc skb extension
  net/sched: flower: Support hardware miss to tc action
  net/sched: flower: Move filter handle initialization earlier
  net/sched: cls_api: Support hardware miss to tc action
  net/sched: Rename user cookie and act cookie
  sfc: fix builds without CONFIG_RTC_LIB
  sfc: clean up some inconsistent indentings
  net/mlx4_en: Introduce flexible array to silence overflow warning
  net: lan966x: Fix possible deadlock inside PTP
  net/ulp: Remove redundant ->clone() test in inet_clone_ulp().
  ...

1 files changed, 463 insertions, 0 deletions

diff --git a/drivers/infiniband/hw/mlx5/cong.c b/drivers/infiniband/hw/mlx5/cong.c
new file mode 100644
index 000000000..290ea8ac3
--- /dev/null
+++ b/drivers/infiniband/hw/mlx5/cong.c
@@ -0,0 +1,463 @@
+/*
+ * Copyright (c) 2013-2017, Mellanox Technologies. All rights reserved.
+ *
+ * This software is available to you under a choice of one of two
+ * licenses.  You may choose to be licensed under the terms of the GNU
+ * General Public License (GPL) Version 2, available from the file
+ * COPYING in the main directory of this source tree, or the
+ * OpenIB.org BSD license below:
+ *
+ *     Redistribution and use in source and binary forms, with or
+ *     without modification, are permitted provided that the following
+ *     conditions are met:
+ *
+ *      - Redistributions of source code must retain the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer.
+ *
+ *      - Redistributions in binary form must reproduce the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer in the documentation and/or other materials
+ *        provided with the distribution.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+
+#include <linux/debugfs.h>
+
+#include "mlx5_ib.h"
+#include "cmd.h"
+
+enum mlx5_ib_cong_node_type {
+	MLX5_IB_RROCE_ECN_RP = 1,
+	MLX5_IB_RROCE_ECN_NP = 2,
+};
+
+static const char * const mlx5_ib_dbg_cc_name[] = {
+	"rp_clamp_tgt_rate",
+	"rp_clamp_tgt_rate_ati",
+	"rp_time_reset",
+	"rp_byte_reset",
+	"rp_threshold",
+	"rp_ai_rate",
+	"rp_max_rate",
+	"rp_hai_rate",
+	"rp_min_dec_fac",
+	"rp_min_rate",
+	"rp_rate_to_set_on_first_cnp",
+	"rp_dce_tcp_g",
+	"rp_dce_tcp_rtt",
+	"rp_rate_reduce_monitor_period",
+	"rp_initial_alpha_value",
+	"rp_gd",
+	"np_min_time_between_cnps",
+	"np_cnp_dscp",
+	"np_cnp_prio_mode",
+	"np_cnp_prio",
+};
+
+#define MLX5_IB_RP_CLAMP_TGT_RATE_ATTR			BIT(1)
+#define MLX5_IB_RP_CLAMP_TGT_RATE_ATI_ATTR		BIT(2)
+#define MLX5_IB_RP_TIME_RESET_ATTR			BIT(3)
+#define MLX5_IB_RP_BYTE_RESET_ATTR			BIT(4)
+#define MLX5_IB_RP_THRESHOLD_ATTR			BIT(5)
+#define MLX5_IB_RP_MAX_RATE_ATTR			BIT(6)
+#define MLX5_IB_RP_AI_RATE_ATTR				BIT(7)
+#define MLX5_IB_RP_HAI_RATE_ATTR			BIT(8)
+#define MLX5_IB_RP_MIN_DEC_FAC_ATTR			BIT(9)
+#define MLX5_IB_RP_MIN_RATE_ATTR			BIT(10)
+#define MLX5_IB_RP_RATE_TO_SET_ON_FIRST_CNP_ATTR	BIT(11)
+#define MLX5_IB_RP_DCE_TCP_G_ATTR			BIT(12)
+#define MLX5_IB_RP_DCE_TCP_RTT_ATTR			BIT(13)
+#define MLX5_IB_RP_RATE_REDUCE_MONITOR_PERIOD_ATTR	BIT(14)
+#define MLX5_IB_RP_INITIAL_ALPHA_VALUE_ATTR		BIT(15)
+#define MLX5_IB_RP_GD_ATTR				BIT(16)
+
+#define MLX5_IB_NP_MIN_TIME_BETWEEN_CNPS_ATTR		BIT(2)
+#define MLX5_IB_NP_CNP_DSCP_ATTR			BIT(3)
+#define MLX5_IB_NP_CNP_PRIO_MODE_ATTR			BIT(4)
+
+static enum mlx5_ib_cong_node_type
+mlx5_ib_param_to_node(enum mlx5_ib_dbg_cc_types param_offset)
+{
+	if (param_offset >= MLX5_IB_DBG_CC_RP_CLAMP_TGT_RATE &&
+	    param_offset <= MLX5_IB_DBG_CC_RP_GD)
+		return MLX5_IB_RROCE_ECN_RP;
+	else
+		return MLX5_IB_RROCE_ECN_NP;
+}
+
+static u32 mlx5_get_cc_param_val(void *field, int offset)
+{
+	switch (offset) {
+	case MLX5_IB_DBG_CC_RP_CLAMP_TGT_RATE:
+		return MLX5_GET(cong_control_r_roce_ecn_rp, field,
+				clamp_tgt_rate);
+	case MLX5_IB_DBG_CC_RP_CLAMP_TGT_RATE_ATI:
+		return MLX5_GET(cong_control_r_roce_ecn_rp, field,
+				clamp_tgt_rate_after_time_inc);
+	case MLX5_IB_DBG_CC_RP_TIME_RESET:
+		return MLX5_GET(cong_control_r_roce_ecn_rp, field,
+				rpg_time_reset);
+	case MLX5_IB_DBG_CC_RP_BYTE_RESET:
+		return MLX5_GET(cong_control_r_roce_ecn_rp, field,
+				rpg_byte_reset);
+	case MLX5_IB_DBG_CC_RP_THRESHOLD:
+		return MLX5_GET(cong_control_r_roce_ecn_rp, field,
+				rpg_threshold);
+	case MLX5_IB_DBG_CC_RP_AI_RATE:
+		return MLX5_GET(cong_control_r_roce_ecn_rp, field,
+				rpg_ai_rate);
+	case MLX5_IB_DBG_CC_RP_MAX_RATE:
+		return MLX5_GET(cong_control_r_roce_ecn_rp, field,
+				rpg_max_rate);
+	case MLX5_IB_DBG_CC_RP_HAI_RATE:
+		return MLX5_GET(cong_control_r_roce_ecn_rp, field,
+				rpg_hai_rate);
+	case MLX5_IB_DBG_CC_RP_MIN_DEC_FAC:
+		return MLX5_GET(cong_control_r_roce_ecn_rp, field,
+				rpg_min_dec_fac);
+	case MLX5_IB_DBG_CC_RP_MIN_RATE:
+		return MLX5_GET(cong_control_r_roce_ecn_rp, field,
+				rpg_min_rate);
+	case MLX5_IB_DBG_CC_RP_RATE_TO_SET_ON_FIRST_CNP:
+		return MLX5_GET(cong_control_r_roce_ecn_rp, field,
+				rate_to_set_on_first_cnp);
+	case MLX5_IB_DBG_CC_RP_DCE_TCP_G:
+		return MLX5_GET(cong_control_r_roce_ecn_rp, field,
+				dce_tcp_g);
+	case MLX5_IB_DBG_CC_RP_DCE_TCP_RTT:
+		return MLX5_GET(cong_control_r_roce_ecn_rp, field,
+				dce_tcp_rtt);
+	case MLX5_IB_DBG_CC_RP_RATE_REDUCE_MONITOR_PERIOD:
+		return MLX5_GET(cong_control_r_roce_ecn_rp, field,
+				rate_reduce_monitor_period);
+	case MLX5_IB_DBG_CC_RP_INITIAL_ALPHA_VALUE:
+		return MLX5_GET(cong_control_r_roce_ecn_rp, field,
+				initial_alpha_value);
+	case MLX5_IB_DBG_CC_RP_GD:
+		return MLX5_GET(cong_control_r_roce_ecn_rp, field,
+				rpg_gd);
+	case MLX5_IB_DBG_CC_NP_MIN_TIME_BETWEEN_CNPS:
+		return MLX5_GET(cong_control_r_roce_ecn_np, field,
+				min_time_between_cnps);
+	case MLX5_IB_DBG_CC_NP_CNP_DSCP:
+		return MLX5_GET(cong_control_r_roce_ecn_np, field,
+				cnp_dscp);
+	case MLX5_IB_DBG_CC_NP_CNP_PRIO_MODE:
+		return MLX5_GET(cong_control_r_roce_ecn_np, field,
+				cnp_prio_mode);
+	case MLX5_IB_DBG_CC_NP_CNP_PRIO:
+		return MLX5_GET(cong_control_r_roce_ecn_np, field,
+				cnp_802p_prio);
+	default:
+		return 0;
+	}
+}
+
+static void mlx5_ib_set_cc_param_mask_val(void *field, int offset,
+					  u32 var, u32 *attr_mask)
+{
+	switch (offset) {
+	case MLX5_IB_DBG_CC_RP_CLAMP_TGT_RATE:
+		*attr_mask |= MLX5_IB_RP_CLAMP_TGT_RATE_ATTR;
+		MLX5_SET(cong_control_r_roce_ecn_rp, field,
+			 clamp_tgt_rate, var);
+		break;
+	case MLX5_IB_DBG_CC_RP_CLAMP_TGT_RATE_ATI:
+		*attr_mask |= MLX5_IB_RP_CLAMP_TGT_RATE_ATI_ATTR;
+		MLX5_SET(cong_control_r_roce_ecn_rp, field,
+			 clamp_tgt_rate_after_time_inc, var);
+		break;
+	case MLX5_IB_DBG_CC_RP_TIME_RESET:
+		*attr_mask |= MLX5_IB_RP_TIME_RESET_ATTR;
+		MLX5_SET(cong_control_r_roce_ecn_rp, field,
+			 rpg_time_reset, var);
+		break;
+	case MLX5_IB_DBG_CC_RP_BYTE_RESET:
+		*attr_mask |= MLX5_IB_RP_BYTE_RESET_ATTR;
+		MLX5_SET(cong_control_r_roce_ecn_rp, field,
+			 rpg_byte_reset, var);
+		break;
+	case MLX5_IB_DBG_CC_RP_THRESHOLD:
+		*attr_mask |= MLX5_IB_RP_THRESHOLD_ATTR;
+		MLX5_SET(cong_control_r_roce_ecn_rp, field,
+			 rpg_threshold, var);
+		break;
+	case MLX5_IB_DBG_CC_RP_AI_RATE:
+		*attr_mask |= MLX5_IB_RP_AI_RATE_ATTR;
+		MLX5_SET(cong_control_r_roce_ecn_rp, field,
+			 rpg_ai_rate, var);
+		break;
+	case MLX5_IB_DBG_CC_RP_MAX_RATE:
+		*attr_mask |= MLX5_IB_RP_MAX_RATE_ATTR;
+		MLX5_SET(cong_control_r_roce_ecn_rp, field,
+			 rpg_max_rate, var);
+		break;
+	case MLX5_IB_DBG_CC_RP_HAI_RATE:
+		*attr_mask |= MLX5_IB_RP_HAI_RATE_ATTR;
+		MLX5_SET(cong_control_r_roce_ecn_rp, field,
+			 rpg_hai_rate, var);
+		break;
+	case MLX5_IB_DBG_CC_RP_MIN_DEC_FAC:
+		*attr_mask |= MLX5_IB_RP_MIN_DEC_FAC_ATTR;
+		MLX5_SET(cong_control_r_roce_ecn_rp, field,
+			 rpg_min_dec_fac, var);
+		break;
+	case MLX5_IB_DBG_CC_RP_MIN_RATE:
+		*attr_mask |= MLX5_IB_RP_MIN_RATE_ATTR;
+		MLX5_SET(cong_control_r_roce_ecn_rp, field,
+			 rpg_min_rate, var);
+		break;
+	case MLX5_IB_DBG_CC_RP_RATE_TO_SET_ON_FIRST_CNP:
+		*attr_mask |= MLX5_IB_RP_RATE_TO_SET_ON_FIRST_CNP_ATTR;
+		MLX5_SET(cong_control_r_roce_ecn_rp, field,
+			 rate_to_set_on_first_cnp, var);
+		break;
+	case MLX5_IB_DBG_CC_RP_DCE_TCP_G:
+		*attr_mask |= MLX5_IB_RP_DCE_TCP_G_ATTR;
+		MLX5_SET(cong_control_r_roce_ecn_rp, field,
+			 dce_tcp_g, var);
+		break;
+	case MLX5_IB_DBG_CC_RP_DCE_TCP_RTT:
+		*attr_mask |= MLX5_IB_RP_DCE_TCP_RTT_ATTR;
+		MLX5_SET(cong_control_r_roce_ecn_rp, field,
+			 dce_tcp_rtt, var);
+		break;
+	case MLX5_IB_DBG_CC_RP_RATE_REDUCE_MONITOR_PERIOD:
+		*attr_mask |= MLX5_IB_RP_RATE_REDUCE_MONITOR_PERIOD_ATTR;
+		MLX5_SET(cong_control_r_roce_ecn_rp, field,
+			 rate_reduce_monitor_period, var);
+		break;
+	case MLX5_IB_DBG_CC_RP_INITIAL_ALPHA_VALUE:
+		*attr_mask |= MLX5_IB_RP_INITIAL_ALPHA_VALUE_ATTR;
+		MLX5_SET(cong_control_r_roce_ecn_rp, field,
+			 initial_alpha_value, var);
+		break;
+	case MLX5_IB_DBG_CC_RP_GD:
+		*attr_mask |= MLX5_IB_RP_GD_ATTR;
+		MLX5_SET(cong_control_r_roce_ecn_rp, field,
+			 rpg_gd, var);
+		break;
+	case MLX5_IB_DBG_CC_NP_MIN_TIME_BETWEEN_CNPS:
+		*attr_mask |= MLX5_IB_NP_MIN_TIME_BETWEEN_CNPS_ATTR;
+		MLX5_SET(cong_control_r_roce_ecn_np, field,
+			 min_time_between_cnps, var);
+		break;
+	case MLX5_IB_DBG_CC_NP_CNP_DSCP:
+		*attr_mask |= MLX5_IB_NP_CNP_DSCP_ATTR;
+		MLX5_SET(cong_control_r_roce_ecn_np, field, cnp_dscp, var);
+		break;
+	case MLX5_IB_DBG_CC_NP_CNP_PRIO_MODE:
+		*attr_mask |= MLX5_IB_NP_CNP_PRIO_MODE_ATTR;
+		MLX5_SET(cong_control_r_roce_ecn_np, field, cnp_prio_mode, var);
+		break;
+	case MLX5_IB_DBG_CC_NP_CNP_PRIO:
+		*attr_mask |= MLX5_IB_NP_CNP_PRIO_MODE_ATTR;
+		MLX5_SET(cong_control_r_roce_ecn_np, field, cnp_prio_mode, 0);
+		MLX5_SET(cong_control_r_roce_ecn_np, field, cnp_802p_prio, var);
+		break;
+	}
+}
+
+static int mlx5_ib_get_cc_params(struct mlx5_ib_dev *dev, u32 port_num,
+				 int offset, u32 *var)
+{
+	int outlen = MLX5_ST_SZ_BYTES(query_cong_params_out);
+	void *out;
+	void *field;
+	int err;
+	enum mlx5_ib_cong_node_type node;
+	struct mlx5_core_dev *mdev;
+
+	/* Takes a 1-based port number */
+	mdev = mlx5_ib_get_native_port_mdev(dev, port_num + 1, NULL);
+	if (!mdev)
+		return -ENODEV;
+
+	out = kvzalloc(outlen, GFP_KERNEL);
+	if (!out) {
+		err = -ENOMEM;
+		goto alloc_err;
+	}
+
+	node = mlx5_ib_param_to_node(offset);
+
+	err = mlx5_cmd_query_cong_params(mdev, node, out);
+	if (err)
+		goto free;
+
+	field = MLX5_ADDR_OF(query_cong_params_out, out, congestion_parameters);
+	*var = mlx5_get_cc_param_val(field, offset);
+
+free:
+	kvfree(out);
+alloc_err:
+	mlx5_ib_put_native_port_mdev(dev, port_num + 1);
+	return err;
+}
+
+static int mlx5_ib_set_cc_params(struct mlx5_ib_dev *dev, u32 port_num,
+				 int offset, u32 var)
+{
+	int inlen = MLX5_ST_SZ_BYTES(modify_cong_params_in);
+	void *in;
+	void *field;
+	enum mlx5_ib_cong_node_type node;
+	struct mlx5_core_dev *mdev;
+	u32 attr_mask = 0;
+	int err;
+
+	/* Takes a 1-based port number */
+	mdev = mlx5_ib_get_native_port_mdev(dev, port_num + 1, NULL);
+	if (!mdev)
+		return -ENODEV;
+
+	in = kvzalloc(inlen, GFP_KERNEL);
+	if (!in) {
+		err = -ENOMEM;
+		goto alloc_err;
+	}
+
+	MLX5_SET(modify_cong_params_in, in, opcode,
+		 MLX5_CMD_OP_MODIFY_CONG_PARAMS);
+
+	node = mlx5_ib_param_to_node(offset);
+	MLX5_SET(modify_cong_params_in, in, cong_protocol, node);
+
+	field = MLX5_ADDR_OF(modify_cong_params_in, in, congestion_parameters);
+	mlx5_ib_set_cc_param_mask_val(field, offset, var, &attr_mask);
+
+	field = MLX5_ADDR_OF(modify_cong_params_in, in, field_select);
+	MLX5_SET(field_select_r_roce_rp, field, field_select_r_roce_rp,
+		 attr_mask);
+
+	err = mlx5_cmd_exec_in(dev->mdev, modify_cong_params, in);
+	kvfree(in);
+alloc_err:
+	mlx5_ib_put_native_port_mdev(dev, port_num + 1);
+	return err;
+}
+
+static ssize_t set_param(struct file *filp, const char __user *buf,
+			 size_t count, loff_t *pos)
+{
+	struct mlx5_ib_dbg_param *param = filp->private_data;
+	int offset = param->offset;
+	char lbuf[11] = { };
+	u32 var;
+	int ret;
+
+	if (count > sizeof(lbuf))
+		return -EINVAL;
+
+	if (copy_from_user(lbuf, buf, count))
+		return -EFAULT;
+
+	lbuf[sizeof(lbuf) - 1] = '\0';
+
+	if (kstrtou32(lbuf, 0, &var))
+		return -EINVAL;
+
+	ret = mlx5_ib_set_cc_params(param->dev, param->port_num, offset, var);
+	return ret ? ret : count;
+}
+
+static ssize_t get_param(struct file *filp, char __user *buf, size_t count,
+			 loff_t *pos)
+{
+	struct mlx5_ib_dbg_param *param = filp->private_data;
+	int offset = param->offset;
+	u32 var = 0;
+	int ret;
+	char lbuf[11];
+
+	ret = mlx5_ib_get_cc_params(param->dev, param->port_num, offset, &var);
+	if (ret)
+		return ret;
+
+	ret = snprintf(lbuf, sizeof(lbuf), "%d\n", var);
+	if (ret < 0)
+		return ret;
+
+	return simple_read_from_buffer(buf, count, pos, lbuf, ret);
+}
+
+static const struct file_operations dbg_cc_fops = {
+	.owner	= THIS_MODULE,
+	.open	= simple_open,
+	.write	= set_param,
+	.read	= get_param,
+};
+
+void mlx5_ib_cleanup_cong_debugfs(struct mlx5_ib_dev *dev, u32 port_num)
+{
+	if (!mlx5_debugfs_root ||
+	    !dev->port[port_num].dbg_cc_params ||
+	    !dev->port[port_num].dbg_cc_params->root)
+		return;
+
+	debugfs_remove_recursive(dev->port[port_num].dbg_cc_params->root);
+	kfree(dev->port[port_num].dbg_cc_params);
+	dev->port[port_num].dbg_cc_params = NULL;
+}
+
+void mlx5_ib_init_cong_debugfs(struct mlx5_ib_dev *dev, u32 port_num)
+{
+	struct mlx5_ib_dbg_cc_params *dbg_cc_params;
+	struct mlx5_core_dev *mdev;
+	int i;
+
+	if (!mlx5_debugfs_root)
+		return;
+
+	/* Takes a 1-based port number */
+	mdev = mlx5_ib_get_native_port_mdev(dev, port_num + 1, NULL);
+	if (!mdev)
+		return;
+
+	if (!MLX5_CAP_GEN(mdev, cc_query_allowed) ||
+	    !MLX5_CAP_GEN(mdev, cc_modify_allowed))
+		goto put_mdev;
+
+	dbg_cc_params = kzalloc(sizeof(*dbg_cc_params), GFP_KERNEL);
+	if (!dbg_cc_params)
+		goto err;
+
+	dev->port[port_num].dbg_cc_params = dbg_cc_params;
+
+	dbg_cc_params->root = debugfs_create_dir("cc_params", mlx5_debugfs_get_dev_root(mdev));
+
+	for (i = 0; i < MLX5_IB_DBG_CC_MAX; i++) {
+		dbg_cc_params->params[i].offset = i;
+		dbg_cc_params->params[i].dev = dev;
+		dbg_cc_params->params[i].port_num = port_num;
+		dbg_cc_params->params[i].dentry =
+			debugfs_create_file(mlx5_ib_dbg_cc_name[i],
+					    0600, dbg_cc_params->root,
+					    &dbg_cc_params->params[i],
+					    &dbg_cc_fops);
+	}
+
+put_mdev:
+	mlx5_ib_put_native_port_mdev(dev, port_num + 1);
+	return;
+
+err:
+	mlx5_ib_warn(dev, "cong debugfs failure\n");
+	mlx5_ib_cleanup_cong_debugfs(dev, port_num);
+	mlx5_ib_put_native_port_mdev(dev, port_num + 1);
+
+	/*
+	 * We don't want to fail driver if debugfs failed to initialize,
+	 * so we are not forwarding error to the user.
+	 */
+	return;
+}