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, 398 insertions, 0 deletions

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/rl.c b/drivers/net/ethernet/mellanox/mlx5/core/rl.c
new file mode 100644
index 000000000..9f8b4005f
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/rl.c
@@ -0,0 +1,398 @@
+/*
+ * Copyright (c) 2013-2016, 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/kernel.h>
+#include <linux/mlx5/driver.h>
+#include "mlx5_core.h"
+
+/* Scheduling element fw management */
+int mlx5_create_scheduling_element_cmd(struct mlx5_core_dev *dev, u8 hierarchy,
+				       void *ctx, u32 *element_id)
+{
+	u32 out[MLX5_ST_SZ_DW(create_scheduling_element_in)] = {};
+	u32 in[MLX5_ST_SZ_DW(create_scheduling_element_in)] = {};
+	void *schedc;
+	int err;
+
+	schedc = MLX5_ADDR_OF(create_scheduling_element_in, in,
+			      scheduling_context);
+	MLX5_SET(create_scheduling_element_in, in, opcode,
+		 MLX5_CMD_OP_CREATE_SCHEDULING_ELEMENT);
+	MLX5_SET(create_scheduling_element_in, in, scheduling_hierarchy,
+		 hierarchy);
+	memcpy(schedc, ctx, MLX5_ST_SZ_BYTES(scheduling_context));
+
+	err = mlx5_cmd_exec_inout(dev, create_scheduling_element, in, out);
+	if (err)
+		return err;
+
+	*element_id = MLX5_GET(create_scheduling_element_out, out,
+			       scheduling_element_id);
+	return 0;
+}
+
+int mlx5_modify_scheduling_element_cmd(struct mlx5_core_dev *dev, u8 hierarchy,
+				       void *ctx, u32 element_id,
+				       u32 modify_bitmask)
+{
+	u32 in[MLX5_ST_SZ_DW(modify_scheduling_element_in)] = {};
+	void *schedc;
+
+	schedc = MLX5_ADDR_OF(modify_scheduling_element_in, in,
+			      scheduling_context);
+	MLX5_SET(modify_scheduling_element_in, in, opcode,
+		 MLX5_CMD_OP_MODIFY_SCHEDULING_ELEMENT);
+	MLX5_SET(modify_scheduling_element_in, in, scheduling_element_id,
+		 element_id);
+	MLX5_SET(modify_scheduling_element_in, in, modify_bitmask,
+		 modify_bitmask);
+	MLX5_SET(modify_scheduling_element_in, in, scheduling_hierarchy,
+		 hierarchy);
+	memcpy(schedc, ctx, MLX5_ST_SZ_BYTES(scheduling_context));
+
+	return mlx5_cmd_exec_in(dev, modify_scheduling_element, in);
+}
+
+int mlx5_destroy_scheduling_element_cmd(struct mlx5_core_dev *dev, u8 hierarchy,
+					u32 element_id)
+{
+	u32 in[MLX5_ST_SZ_DW(destroy_scheduling_element_in)] = {};
+
+	MLX5_SET(destroy_scheduling_element_in, in, opcode,
+		 MLX5_CMD_OP_DESTROY_SCHEDULING_ELEMENT);
+	MLX5_SET(destroy_scheduling_element_in, in, scheduling_element_id,
+		 element_id);
+	MLX5_SET(destroy_scheduling_element_in, in, scheduling_hierarchy,
+		 hierarchy);
+
+	return mlx5_cmd_exec_in(dev, destroy_scheduling_element, in);
+}
+
+static bool mlx5_rl_are_equal_raw(struct mlx5_rl_entry *entry, void *rl_in,
+				  u16 uid)
+{
+	return (!memcmp(entry->rl_raw, rl_in, sizeof(entry->rl_raw)) &&
+		entry->uid == uid);
+}
+
+/* Finds an entry where we can register the given rate
+ * If the rate already exists, return the entry where it is registered,
+ * otherwise return the first available entry.
+ * If the table is full, return NULL
+ */
+static struct mlx5_rl_entry *find_rl_entry(struct mlx5_rl_table *table,
+					   void *rl_in, u16 uid, bool dedicated)
+{
+	struct mlx5_rl_entry *ret_entry = NULL;
+	bool empty_found = false;
+	int i;
+
+	lockdep_assert_held(&table->rl_lock);
+	WARN_ON(!table->rl_entry);
+
+	for (i = 0; i < table->max_size; i++) {
+		if (dedicated) {
+			if (!table->rl_entry[i].refcount)
+				return &table->rl_entry[i];
+			continue;
+		}
+
+		if (table->rl_entry[i].refcount) {
+			if (table->rl_entry[i].dedicated)
+				continue;
+			if (mlx5_rl_are_equal_raw(&table->rl_entry[i], rl_in,
+						  uid))
+				return &table->rl_entry[i];
+		} else if (!empty_found) {
+			empty_found = true;
+			ret_entry = &table->rl_entry[i];
+		}
+	}
+
+	return ret_entry;
+}
+
+static int mlx5_set_pp_rate_limit_cmd(struct mlx5_core_dev *dev,
+				      struct mlx5_rl_entry *entry, bool set)
+{
+	u32 in[MLX5_ST_SZ_DW(set_pp_rate_limit_in)] = {};
+	void *pp_context;
+
+	pp_context = MLX5_ADDR_OF(set_pp_rate_limit_in, in, ctx);
+	MLX5_SET(set_pp_rate_limit_in, in, opcode,
+		 MLX5_CMD_OP_SET_PP_RATE_LIMIT);
+	MLX5_SET(set_pp_rate_limit_in, in, uid, entry->uid);
+	MLX5_SET(set_pp_rate_limit_in, in, rate_limit_index, entry->index);
+	if (set)
+		memcpy(pp_context, entry->rl_raw, sizeof(entry->rl_raw));
+	return mlx5_cmd_exec_in(dev, set_pp_rate_limit, in);
+}
+
+bool mlx5_rl_is_in_range(struct mlx5_core_dev *dev, u32 rate)
+{
+	struct mlx5_rl_table *table = &dev->priv.rl_table;
+
+	return (rate <= table->max_rate && rate >= table->min_rate);
+}
+EXPORT_SYMBOL(mlx5_rl_is_in_range);
+
+bool mlx5_rl_are_equal(struct mlx5_rate_limit *rl_0,
+		       struct mlx5_rate_limit *rl_1)
+{
+	return ((rl_0->rate == rl_1->rate) &&
+		(rl_0->max_burst_sz == rl_1->max_burst_sz) &&
+		(rl_0->typical_pkt_sz == rl_1->typical_pkt_sz));
+}
+EXPORT_SYMBOL(mlx5_rl_are_equal);
+
+static int mlx5_rl_table_get(struct mlx5_rl_table *table)
+{
+	int i;
+
+	lockdep_assert_held(&table->rl_lock);
+
+	if (table->rl_entry) {
+		table->refcount++;
+		return 0;
+	}
+
+	table->rl_entry = kcalloc(table->max_size, sizeof(struct mlx5_rl_entry),
+				  GFP_KERNEL);
+	if (!table->rl_entry)
+		return -ENOMEM;
+
+	/* The index represents the index in HW rate limit table
+	 * Index 0 is reserved for unlimited rate
+	 */
+	for (i = 0; i < table->max_size; i++)
+		table->rl_entry[i].index = i + 1;
+
+	table->refcount++;
+	return 0;
+}
+
+static void mlx5_rl_table_put(struct mlx5_rl_table *table)
+{
+	lockdep_assert_held(&table->rl_lock);
+	if (--table->refcount)
+		return;
+
+	kfree(table->rl_entry);
+	table->rl_entry = NULL;
+}
+
+static void mlx5_rl_table_free(struct mlx5_core_dev *dev, struct mlx5_rl_table *table)
+{
+	int i;
+
+	if (!table->rl_entry)
+		return;
+
+	/* Clear all configured rates */
+	for (i = 0; i < table->max_size; i++)
+		if (table->rl_entry[i].refcount)
+			mlx5_set_pp_rate_limit_cmd(dev, &table->rl_entry[i], false);
+	kfree(table->rl_entry);
+}
+
+static void mlx5_rl_entry_get(struct mlx5_rl_entry *entry)
+{
+	entry->refcount++;
+}
+
+static void
+mlx5_rl_entry_put(struct mlx5_core_dev *dev, struct mlx5_rl_entry *entry)
+{
+	entry->refcount--;
+	if (!entry->refcount)
+		mlx5_set_pp_rate_limit_cmd(dev, entry, false);
+}
+
+int mlx5_rl_add_rate_raw(struct mlx5_core_dev *dev, void *rl_in, u16 uid,
+			 bool dedicated_entry, u16 *index)
+{
+	struct mlx5_rl_table *table = &dev->priv.rl_table;
+	struct mlx5_rl_entry *entry;
+	u32 rate;
+	int err;
+
+	if (!table->max_size)
+		return -EOPNOTSUPP;
+
+	rate = MLX5_GET(set_pp_rate_limit_context, rl_in, rate_limit);
+	if (!rate || !mlx5_rl_is_in_range(dev, rate)) {
+		mlx5_core_err(dev, "Invalid rate: %u, should be %u to %u\n",
+			      rate, table->min_rate, table->max_rate);
+		return -EINVAL;
+	}
+
+	mutex_lock(&table->rl_lock);
+	err = mlx5_rl_table_get(table);
+	if (err)
+		goto out;
+
+	entry = find_rl_entry(table, rl_in, uid, dedicated_entry);
+	if (!entry) {
+		mlx5_core_err(dev, "Max number of %u rates reached\n",
+			      table->max_size);
+		err = -ENOSPC;
+		goto rl_err;
+	}
+	if (!entry->refcount) {
+		/* new rate limit */
+		memcpy(entry->rl_raw, rl_in, sizeof(entry->rl_raw));
+		entry->uid = uid;
+		err = mlx5_set_pp_rate_limit_cmd(dev, entry, true);
+		if (err) {
+			mlx5_core_err(
+				dev,
+				"Failed configuring rate limit(err %d): rate %u, max_burst_sz %u, typical_pkt_sz %u\n",
+				err, rate,
+				MLX5_GET(set_pp_rate_limit_context, rl_in,
+					 burst_upper_bound),
+				MLX5_GET(set_pp_rate_limit_context, rl_in,
+					 typical_packet_size));
+			goto rl_err;
+		}
+
+		entry->dedicated = dedicated_entry;
+	}
+	mlx5_rl_entry_get(entry);
+	*index = entry->index;
+	mutex_unlock(&table->rl_lock);
+	return 0;
+
+rl_err:
+	mlx5_rl_table_put(table);
+out:
+	mutex_unlock(&table->rl_lock);
+	return err;
+}
+EXPORT_SYMBOL(mlx5_rl_add_rate_raw);
+
+void mlx5_rl_remove_rate_raw(struct mlx5_core_dev *dev, u16 index)
+{
+	struct mlx5_rl_table *table = &dev->priv.rl_table;
+	struct mlx5_rl_entry *entry;
+
+	mutex_lock(&table->rl_lock);
+	entry = &table->rl_entry[index - 1];
+	mlx5_rl_entry_put(dev, entry);
+	mlx5_rl_table_put(table);
+	mutex_unlock(&table->rl_lock);
+}
+EXPORT_SYMBOL(mlx5_rl_remove_rate_raw);
+
+int mlx5_rl_add_rate(struct mlx5_core_dev *dev, u16 *index,
+		     struct mlx5_rate_limit *rl)
+{
+	u8 rl_raw[MLX5_ST_SZ_BYTES(set_pp_rate_limit_context)] = {};
+
+	MLX5_SET(set_pp_rate_limit_context, rl_raw, rate_limit, rl->rate);
+	MLX5_SET(set_pp_rate_limit_context, rl_raw, burst_upper_bound,
+		 rl->max_burst_sz);
+	MLX5_SET(set_pp_rate_limit_context, rl_raw, typical_packet_size,
+		 rl->typical_pkt_sz);
+
+	return mlx5_rl_add_rate_raw(dev, rl_raw,
+				    MLX5_CAP_QOS(dev, packet_pacing_uid) ?
+					MLX5_SHARED_RESOURCE_UID : 0,
+				    false, index);
+}
+EXPORT_SYMBOL(mlx5_rl_add_rate);
+
+void mlx5_rl_remove_rate(struct mlx5_core_dev *dev, struct mlx5_rate_limit *rl)
+{
+	u8 rl_raw[MLX5_ST_SZ_BYTES(set_pp_rate_limit_context)] = {};
+	struct mlx5_rl_table *table = &dev->priv.rl_table;
+	struct mlx5_rl_entry *entry = NULL;
+
+	/* 0 is a reserved value for unlimited rate */
+	if (rl->rate == 0)
+		return;
+
+	MLX5_SET(set_pp_rate_limit_context, rl_raw, rate_limit, rl->rate);
+	MLX5_SET(set_pp_rate_limit_context, rl_raw, burst_upper_bound,
+		 rl->max_burst_sz);
+	MLX5_SET(set_pp_rate_limit_context, rl_raw, typical_packet_size,
+		 rl->typical_pkt_sz);
+
+	mutex_lock(&table->rl_lock);
+	entry = find_rl_entry(table, rl_raw,
+			      MLX5_CAP_QOS(dev, packet_pacing_uid) ?
+				MLX5_SHARED_RESOURCE_UID : 0, false);
+	if (!entry || !entry->refcount) {
+		mlx5_core_warn(dev, "Rate %u, max_burst_sz %u typical_pkt_sz %u are not configured\n",
+			       rl->rate, rl->max_burst_sz, rl->typical_pkt_sz);
+		goto out;
+	}
+	mlx5_rl_entry_put(dev, entry);
+	mlx5_rl_table_put(table);
+out:
+	mutex_unlock(&table->rl_lock);
+}
+EXPORT_SYMBOL(mlx5_rl_remove_rate);
+
+int mlx5_init_rl_table(struct mlx5_core_dev *dev)
+{
+	struct mlx5_rl_table *table = &dev->priv.rl_table;
+
+	if (!MLX5_CAP_GEN(dev, qos) || !MLX5_CAP_QOS(dev, packet_pacing)) {
+		table->max_size = 0;
+		return 0;
+	}
+
+	mutex_init(&table->rl_lock);
+
+	/* First entry is reserved for unlimited rate */
+	table->max_size = MLX5_CAP_QOS(dev, packet_pacing_rate_table_size) - 1;
+	table->max_rate = MLX5_CAP_QOS(dev, packet_pacing_max_rate);
+	table->min_rate = MLX5_CAP_QOS(dev, packet_pacing_min_rate);
+
+	mlx5_core_info(dev, "Rate limit: %u rates are supported, range: %uMbps to %uMbps\n",
+		       table->max_size,
+		       table->min_rate >> 10,
+		       table->max_rate >> 10);
+
+	return 0;
+}
+
+void mlx5_cleanup_rl_table(struct mlx5_core_dev *dev)
+{
+	struct mlx5_rl_table *table = &dev->priv.rl_table;
+
+	if (!MLX5_CAP_GEN(dev, qos) || !MLX5_CAP_QOS(dev, packet_pacing))
+		return;
+
+	mlx5_rl_table_free(dev, table);
+	mutex_destroy(&table->rl_lock);
+}