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, 482 insertions, 0 deletions

diff --git a/drivers/net/ethernet/mellanox/mlx4/cq.c b/drivers/net/ethernet/mellanox/mlx4/cq.c
new file mode 100644
index 000000000..4d4f9cf9f
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx4/cq.c
@@ -0,0 +1,482 @@
+/*
+ * Copyright (c) 2004, 2005 Topspin Communications.  All rights reserved.
+ * Copyright (c) 2005 Sun Microsystems, Inc. All rights reserved.
+ * Copyright (c) 2005, 2006, 2007 Cisco Systems, Inc. All rights reserved.
+ * Copyright (c) 2005, 2006, 2007, 2008 Mellanox Technologies. All rights reserved.
+ * Copyright (c) 2004 Voltaire, Inc. 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/hardirq.h>
+#include <linux/export.h>
+
+#include <linux/mlx4/cmd.h>
+#include <linux/mlx4/cq.h>
+
+#include "mlx4.h"
+#include "icm.h"
+
+#define MLX4_CQ_STATUS_OK		( 0 << 28)
+#define MLX4_CQ_STATUS_OVERFLOW		( 9 << 28)
+#define MLX4_CQ_STATUS_WRITE_FAIL	(10 << 28)
+#define MLX4_CQ_FLAG_CC			( 1 << 18)
+#define MLX4_CQ_FLAG_OI			( 1 << 17)
+#define MLX4_CQ_STATE_ARMED		( 9 <<  8)
+#define MLX4_CQ_STATE_ARMED_SOL		( 6 <<  8)
+#define MLX4_EQ_STATE_FIRED		(10 <<  8)
+
+#define TASKLET_MAX_TIME 2
+#define TASKLET_MAX_TIME_JIFFIES msecs_to_jiffies(TASKLET_MAX_TIME)
+
+void mlx4_cq_tasklet_cb(struct tasklet_struct *t)
+{
+	unsigned long flags;
+	unsigned long end = jiffies + TASKLET_MAX_TIME_JIFFIES;
+	struct mlx4_eq_tasklet *ctx = from_tasklet(ctx, t, task);
+	struct mlx4_cq *mcq, *temp;
+
+	spin_lock_irqsave(&ctx->lock, flags);
+	list_splice_tail_init(&ctx->list, &ctx->process_list);
+	spin_unlock_irqrestore(&ctx->lock, flags);
+
+	list_for_each_entry_safe(mcq, temp, &ctx->process_list, tasklet_ctx.list) {
+		list_del_init(&mcq->tasklet_ctx.list);
+		mcq->tasklet_ctx.comp(mcq);
+		if (refcount_dec_and_test(&mcq->refcount))
+			complete(&mcq->free);
+		if (time_after(jiffies, end))
+			break;
+	}
+
+	if (!list_empty(&ctx->process_list))
+		tasklet_schedule(&ctx->task);
+}
+
+static void mlx4_add_cq_to_tasklet(struct mlx4_cq *cq)
+{
+	struct mlx4_eq_tasklet *tasklet_ctx = cq->tasklet_ctx.priv;
+	unsigned long flags;
+	bool kick;
+
+	spin_lock_irqsave(&tasklet_ctx->lock, flags);
+	/* When migrating CQs between EQs will be implemented, please note
+	 * that you need to sync this point. It is possible that
+	 * while migrating a CQ, completions on the old EQs could
+	 * still arrive.
+	 */
+	if (list_empty_careful(&cq->tasklet_ctx.list)) {
+		refcount_inc(&cq->refcount);
+		kick = list_empty(&tasklet_ctx->list);
+		list_add_tail(&cq->tasklet_ctx.list, &tasklet_ctx->list);
+		if (kick)
+			tasklet_schedule(&tasklet_ctx->task);
+	}
+	spin_unlock_irqrestore(&tasklet_ctx->lock, flags);
+}
+
+void mlx4_cq_completion(struct mlx4_dev *dev, u32 cqn)
+{
+	struct mlx4_cq *cq;
+
+	rcu_read_lock();
+	cq = radix_tree_lookup(&mlx4_priv(dev)->cq_table.tree,
+			       cqn & (dev->caps.num_cqs - 1));
+	rcu_read_unlock();
+
+	if (!cq) {
+		mlx4_dbg(dev, "Completion event for bogus CQ %08x\n", cqn);
+		return;
+	}
+
+	/* Acessing the CQ outside of rcu_read_lock is safe, because
+	 * the CQ is freed only after interrupt handling is completed.
+	 */
+	++cq->arm_sn;
+
+	cq->comp(cq);
+}
+
+void mlx4_cq_event(struct mlx4_dev *dev, u32 cqn, int event_type)
+{
+	struct mlx4_cq_table *cq_table = &mlx4_priv(dev)->cq_table;
+	struct mlx4_cq *cq;
+
+	rcu_read_lock();
+	cq = radix_tree_lookup(&cq_table->tree, cqn & (dev->caps.num_cqs - 1));
+	rcu_read_unlock();
+
+	if (!cq) {
+		mlx4_dbg(dev, "Async event for bogus CQ %08x\n", cqn);
+		return;
+	}
+
+	/* Acessing the CQ outside of rcu_read_lock is safe, because
+	 * the CQ is freed only after interrupt handling is completed.
+	 */
+	cq->event(cq, event_type);
+}
+
+static int mlx4_SW2HW_CQ(struct mlx4_dev *dev, struct mlx4_cmd_mailbox *mailbox,
+			 int cq_num, u8 opmod)
+{
+	return mlx4_cmd(dev, mailbox->dma, cq_num, opmod,
+			MLX4_CMD_SW2HW_CQ, MLX4_CMD_TIME_CLASS_A,
+			MLX4_CMD_WRAPPED);
+}
+
+static int mlx4_MODIFY_CQ(struct mlx4_dev *dev, struct mlx4_cmd_mailbox *mailbox,
+			 int cq_num, u32 opmod)
+{
+	return mlx4_cmd(dev, mailbox->dma, cq_num, opmod, MLX4_CMD_MODIFY_CQ,
+			MLX4_CMD_TIME_CLASS_A, MLX4_CMD_WRAPPED);
+}
+
+static int mlx4_HW2SW_CQ(struct mlx4_dev *dev, struct mlx4_cmd_mailbox *mailbox,
+			 int cq_num)
+{
+	return mlx4_cmd_box(dev, 0, mailbox ? mailbox->dma : 0,
+			    cq_num, mailbox ? 0 : 1, MLX4_CMD_HW2SW_CQ,
+			    MLX4_CMD_TIME_CLASS_A, MLX4_CMD_WRAPPED);
+}
+
+int mlx4_cq_modify(struct mlx4_dev *dev, struct mlx4_cq *cq,
+		   u16 count, u16 period)
+{
+	struct mlx4_cmd_mailbox *mailbox;
+	struct mlx4_cq_context *cq_context;
+	int err;
+
+	mailbox = mlx4_alloc_cmd_mailbox(dev);
+	if (IS_ERR(mailbox))
+		return PTR_ERR(mailbox);
+
+	cq_context = mailbox->buf;
+	cq_context->cq_max_count = cpu_to_be16(count);
+	cq_context->cq_period    = cpu_to_be16(period);
+
+	err = mlx4_MODIFY_CQ(dev, mailbox, cq->cqn, 1);
+
+	mlx4_free_cmd_mailbox(dev, mailbox);
+	return err;
+}
+EXPORT_SYMBOL_GPL(mlx4_cq_modify);
+
+int mlx4_cq_resize(struct mlx4_dev *dev, struct mlx4_cq *cq,
+		   int entries, struct mlx4_mtt *mtt)
+{
+	struct mlx4_cmd_mailbox *mailbox;
+	struct mlx4_cq_context *cq_context;
+	u64 mtt_addr;
+	int err;
+
+	mailbox = mlx4_alloc_cmd_mailbox(dev);
+	if (IS_ERR(mailbox))
+		return PTR_ERR(mailbox);
+
+	cq_context = mailbox->buf;
+	cq_context->logsize_usrpage = cpu_to_be32(ilog2(entries) << 24);
+	cq_context->log_page_size   = mtt->page_shift - 12;
+	mtt_addr = mlx4_mtt_addr(dev, mtt);
+	cq_context->mtt_base_addr_h = mtt_addr >> 32;
+	cq_context->mtt_base_addr_l = cpu_to_be32(mtt_addr & 0xffffffff);
+
+	err = mlx4_MODIFY_CQ(dev, mailbox, cq->cqn, 0);
+
+	mlx4_free_cmd_mailbox(dev, mailbox);
+	return err;
+}
+EXPORT_SYMBOL_GPL(mlx4_cq_resize);
+
+int __mlx4_cq_alloc_icm(struct mlx4_dev *dev, int *cqn)
+{
+	struct mlx4_priv *priv = mlx4_priv(dev);
+	struct mlx4_cq_table *cq_table = &priv->cq_table;
+	int err;
+
+	*cqn = mlx4_bitmap_alloc(&cq_table->bitmap);
+	if (*cqn == -1)
+		return -ENOMEM;
+
+	err = mlx4_table_get(dev, &cq_table->table, *cqn);
+	if (err)
+		goto err_out;
+
+	err = mlx4_table_get(dev, &cq_table->cmpt_table, *cqn);
+	if (err)
+		goto err_put;
+	return 0;
+
+err_put:
+	mlx4_table_put(dev, &cq_table->table, *cqn);
+
+err_out:
+	mlx4_bitmap_free(&cq_table->bitmap, *cqn, MLX4_NO_RR);
+	return err;
+}
+
+static int mlx4_cq_alloc_icm(struct mlx4_dev *dev, int *cqn, u8 usage)
+{
+	u32 in_modifier = RES_CQ | (((u32)usage & 3) << 30);
+	u64 out_param;
+	int err;
+
+	if (mlx4_is_mfunc(dev)) {
+		err = mlx4_cmd_imm(dev, 0, &out_param, in_modifier,
+				   RES_OP_RESERVE_AND_MAP, MLX4_CMD_ALLOC_RES,
+				   MLX4_CMD_TIME_CLASS_A, MLX4_CMD_WRAPPED);
+		if (err)
+			return err;
+		else {
+			*cqn = get_param_l(&out_param);
+			return 0;
+		}
+	}
+	return __mlx4_cq_alloc_icm(dev, cqn);
+}
+
+void __mlx4_cq_free_icm(struct mlx4_dev *dev, int cqn)
+{
+	struct mlx4_priv *priv = mlx4_priv(dev);
+	struct mlx4_cq_table *cq_table = &priv->cq_table;
+
+	mlx4_table_put(dev, &cq_table->cmpt_table, cqn);
+	mlx4_table_put(dev, &cq_table->table, cqn);
+	mlx4_bitmap_free(&cq_table->bitmap, cqn, MLX4_NO_RR);
+}
+
+static void mlx4_cq_free_icm(struct mlx4_dev *dev, int cqn)
+{
+	u64 in_param = 0;
+	int err;
+
+	if (mlx4_is_mfunc(dev)) {
+		set_param_l(&in_param, cqn);
+		err = mlx4_cmd(dev, in_param, RES_CQ, RES_OP_RESERVE_AND_MAP,
+			       MLX4_CMD_FREE_RES,
+			       MLX4_CMD_TIME_CLASS_A, MLX4_CMD_WRAPPED);
+		if (err)
+			mlx4_warn(dev, "Failed freeing cq:%d\n", cqn);
+	} else
+		__mlx4_cq_free_icm(dev, cqn);
+}
+
+static int mlx4_init_user_cqes(void *buf, int entries, int cqe_size)
+{
+	int entries_per_copy = PAGE_SIZE / cqe_size;
+	void *init_ents;
+	int err = 0;
+	int i;
+
+	init_ents = kmalloc(PAGE_SIZE, GFP_KERNEL);
+	if (!init_ents)
+		return -ENOMEM;
+
+	/* Populate a list of CQ entries to reduce the number of
+	 * copy_to_user calls. 0xcc is the initialization value
+	 * required by the FW.
+	 */
+	memset(init_ents, 0xcc, PAGE_SIZE);
+
+	if (entries_per_copy < entries) {
+		for (i = 0; i < entries / entries_per_copy; i++) {
+			err = copy_to_user((void __user *)buf, init_ents, PAGE_SIZE) ?
+				-EFAULT : 0;
+			if (err)
+				goto out;
+
+			buf += PAGE_SIZE;
+		}
+	} else {
+		err = copy_to_user((void __user *)buf, init_ents,
+				   array_size(entries, cqe_size)) ?
+			-EFAULT : 0;
+	}
+
+out:
+	kfree(init_ents);
+
+	return err;
+}
+
+static void mlx4_init_kernel_cqes(struct mlx4_buf *buf,
+				  int entries,
+				  int cqe_size)
+{
+	int i;
+
+	if (buf->nbufs == 1)
+		memset(buf->direct.buf, 0xcc, entries * cqe_size);
+	else
+		for (i = 0; i < buf->npages; i++)
+			memset(buf->page_list[i].buf, 0xcc,
+			       1UL << buf->page_shift);
+}
+
+int mlx4_cq_alloc(struct mlx4_dev *dev, int nent,
+		  struct mlx4_mtt *mtt, struct mlx4_uar *uar, u64 db_rec,
+		  struct mlx4_cq *cq, unsigned vector, int collapsed,
+		  int timestamp_en, void *buf_addr, bool user_cq)
+{
+	bool sw_cq_init = dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_SW_CQ_INIT;
+	struct mlx4_priv *priv = mlx4_priv(dev);
+	struct mlx4_cq_table *cq_table = &priv->cq_table;
+	struct mlx4_cmd_mailbox *mailbox;
+	struct mlx4_cq_context *cq_context;
+	u64 mtt_addr;
+	int err;
+
+	if (vector >= dev->caps.num_comp_vectors)
+		return -EINVAL;
+
+	cq->vector = vector;
+
+	err = mlx4_cq_alloc_icm(dev, &cq->cqn, cq->usage);
+	if (err)
+		return err;
+
+	spin_lock(&cq_table->lock);
+	err = radix_tree_insert(&cq_table->tree, cq->cqn, cq);
+	spin_unlock(&cq_table->lock);
+	if (err)
+		goto err_icm;
+
+	mailbox = mlx4_alloc_cmd_mailbox(dev);
+	if (IS_ERR(mailbox)) {
+		err = PTR_ERR(mailbox);
+		goto err_radix;
+	}
+
+	cq_context = mailbox->buf;
+	cq_context->flags	    = cpu_to_be32(!!collapsed << 18);
+	if (timestamp_en)
+		cq_context->flags  |= cpu_to_be32(1 << 19);
+
+	cq_context->logsize_usrpage =
+		cpu_to_be32((ilog2(nent) << 24) |
+			    mlx4_to_hw_uar_index(dev, uar->index));
+	cq_context->comp_eqn	    = priv->eq_table.eq[MLX4_CQ_TO_EQ_VECTOR(vector)].eqn;
+	cq_context->log_page_size   = mtt->page_shift - MLX4_ICM_PAGE_SHIFT;
+
+	mtt_addr = mlx4_mtt_addr(dev, mtt);
+	cq_context->mtt_base_addr_h = mtt_addr >> 32;
+	cq_context->mtt_base_addr_l = cpu_to_be32(mtt_addr & 0xffffffff);
+	cq_context->db_rec_addr     = cpu_to_be64(db_rec);
+
+	if (sw_cq_init) {
+		if (user_cq) {
+			err = mlx4_init_user_cqes(buf_addr, nent,
+						  dev->caps.cqe_size);
+			if (err)
+				sw_cq_init = false;
+		} else {
+			mlx4_init_kernel_cqes(buf_addr, nent,
+					      dev->caps.cqe_size);
+		}
+	}
+
+	err = mlx4_SW2HW_CQ(dev, mailbox, cq->cqn, sw_cq_init);
+
+	mlx4_free_cmd_mailbox(dev, mailbox);
+	if (err)
+		goto err_radix;
+
+	cq->cons_index = 0;
+	cq->arm_sn     = 1;
+	cq->uar        = uar;
+	refcount_set(&cq->refcount, 1);
+	init_completion(&cq->free);
+	cq->comp = mlx4_add_cq_to_tasklet;
+	cq->tasklet_ctx.priv =
+		&priv->eq_table.eq[MLX4_CQ_TO_EQ_VECTOR(vector)].tasklet_ctx;
+	INIT_LIST_HEAD(&cq->tasklet_ctx.list);
+
+
+	cq->irq = priv->eq_table.eq[MLX4_CQ_TO_EQ_VECTOR(vector)].irq;
+	return 0;
+
+err_radix:
+	spin_lock(&cq_table->lock);
+	radix_tree_delete(&cq_table->tree, cq->cqn);
+	spin_unlock(&cq_table->lock);
+
+err_icm:
+	mlx4_cq_free_icm(dev, cq->cqn);
+
+	return err;
+}
+EXPORT_SYMBOL_GPL(mlx4_cq_alloc);
+
+void mlx4_cq_free(struct mlx4_dev *dev, struct mlx4_cq *cq)
+{
+	struct mlx4_priv *priv = mlx4_priv(dev);
+	struct mlx4_cq_table *cq_table = &priv->cq_table;
+	int err;
+
+	err = mlx4_HW2SW_CQ(dev, NULL, cq->cqn);
+	if (err)
+		mlx4_warn(dev, "HW2SW_CQ failed (%d) for CQN %06x\n", err, cq->cqn);
+
+	spin_lock(&cq_table->lock);
+	radix_tree_delete(&cq_table->tree, cq->cqn);
+	spin_unlock(&cq_table->lock);
+
+	synchronize_irq(priv->eq_table.eq[MLX4_CQ_TO_EQ_VECTOR(cq->vector)].irq);
+	if (priv->eq_table.eq[MLX4_CQ_TO_EQ_VECTOR(cq->vector)].irq !=
+	    priv->eq_table.eq[MLX4_EQ_ASYNC].irq)
+		synchronize_irq(priv->eq_table.eq[MLX4_EQ_ASYNC].irq);
+
+	if (refcount_dec_and_test(&cq->refcount))
+		complete(&cq->free);
+	wait_for_completion(&cq->free);
+
+	mlx4_cq_free_icm(dev, cq->cqn);
+}
+EXPORT_SYMBOL_GPL(mlx4_cq_free);
+
+int mlx4_init_cq_table(struct mlx4_dev *dev)
+{
+	struct mlx4_cq_table *cq_table = &mlx4_priv(dev)->cq_table;
+
+	spin_lock_init(&cq_table->lock);
+	INIT_RADIX_TREE(&cq_table->tree, GFP_ATOMIC);
+	if (mlx4_is_slave(dev))
+		return 0;
+
+	return mlx4_bitmap_init(&cq_table->bitmap, dev->caps.num_cqs,
+				dev->caps.num_cqs - 1, dev->caps.reserved_cqs, 0);
+}
+
+void mlx4_cleanup_cq_table(struct mlx4_dev *dev)
+{
+	if (mlx4_is_slave(dev))
+		return;
+	/* Nothing to do to clean up radix_tree */
+	mlx4_bitmap_cleanup(&mlx4_priv(dev)->cq_table.bitmap);
+}