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, 610 insertions, 0 deletions

diff --git a/drivers/scsi/csiostor/csio_isr.c b/drivers/scsi/csiostor/csio_isr.c
new file mode 100644
index 000000000..b2540402f
--- /dev/null
+++ b/drivers/scsi/csiostor/csio_isr.c
@@ -0,0 +1,610 @@
+/*
+ * This file is part of the Chelsio FCoE driver for Linux.
+ *
+ * Copyright (c) 2008-2012 Chelsio Communications, 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/kernel.h>
+#include <linux/pci.h>
+#include <linux/interrupt.h>
+#include <linux/cpumask.h>
+#include <linux/string.h>
+
+#include "csio_init.h"
+#include "csio_hw.h"
+
+static irqreturn_t
+csio_nondata_isr(int irq, void *dev_id)
+{
+	struct csio_hw *hw = (struct csio_hw *) dev_id;
+	int rv;
+	unsigned long flags;
+
+	if (unlikely(!hw))
+		return IRQ_NONE;
+
+	if (unlikely(pci_channel_offline(hw->pdev))) {
+		CSIO_INC_STATS(hw, n_pcich_offline);
+		return IRQ_NONE;
+	}
+
+	spin_lock_irqsave(&hw->lock, flags);
+	csio_hw_slow_intr_handler(hw);
+	rv = csio_mb_isr_handler(hw);
+
+	if (rv == 0 && !(hw->flags & CSIO_HWF_FWEVT_PENDING)) {
+		hw->flags |= CSIO_HWF_FWEVT_PENDING;
+		spin_unlock_irqrestore(&hw->lock, flags);
+		schedule_work(&hw->evtq_work);
+		return IRQ_HANDLED;
+	}
+	spin_unlock_irqrestore(&hw->lock, flags);
+	return IRQ_HANDLED;
+}
+
+/*
+ * csio_fwevt_handler - Common FW event handler routine.
+ * @hw: HW module.
+ *
+ * This is the ISR for FW events. It is shared b/w MSIX
+ * and INTx handlers.
+ */
+static void
+csio_fwevt_handler(struct csio_hw *hw)
+{
+	int rv;
+	unsigned long flags;
+
+	rv = csio_fwevtq_handler(hw);
+
+	spin_lock_irqsave(&hw->lock, flags);
+	if (rv == 0 && !(hw->flags & CSIO_HWF_FWEVT_PENDING)) {
+		hw->flags |= CSIO_HWF_FWEVT_PENDING;
+		spin_unlock_irqrestore(&hw->lock, flags);
+		schedule_work(&hw->evtq_work);
+		return;
+	}
+	spin_unlock_irqrestore(&hw->lock, flags);
+
+} /* csio_fwevt_handler */
+
+/*
+ * csio_fwevt_isr() - FW events MSIX ISR
+ * @irq:
+ * @dev_id:
+ *
+ * Process WRs on the FW event queue.
+ *
+ */
+static irqreturn_t
+csio_fwevt_isr(int irq, void *dev_id)
+{
+	struct csio_hw *hw = (struct csio_hw *) dev_id;
+
+	if (unlikely(!hw))
+		return IRQ_NONE;
+
+	if (unlikely(pci_channel_offline(hw->pdev))) {
+		CSIO_INC_STATS(hw, n_pcich_offline);
+		return IRQ_NONE;
+	}
+
+	csio_fwevt_handler(hw);
+
+	return IRQ_HANDLED;
+}
+
+/*
+ * csio_fwevt_isr() - INTx wrapper for handling FW events.
+ * @irq:
+ * @dev_id:
+ */
+void
+csio_fwevt_intx_handler(struct csio_hw *hw, void *wr, uint32_t len,
+			   struct csio_fl_dma_buf *flb, void *priv)
+{
+	csio_fwevt_handler(hw);
+} /* csio_fwevt_intx_handler */
+
+/*
+ * csio_process_scsi_cmpl - Process a SCSI WR completion.
+ * @hw: HW module.
+ * @wr: The completed WR from the ingress queue.
+ * @len: Length of the WR.
+ * @flb: Freelist buffer array.
+ *
+ */
+static void
+csio_process_scsi_cmpl(struct csio_hw *hw, void *wr, uint32_t len,
+			struct csio_fl_dma_buf *flb, void *cbfn_q)
+{
+	struct csio_ioreq *ioreq;
+	uint8_t *scsiwr;
+	uint8_t subop;
+	void *cmnd;
+	unsigned long flags;
+
+	ioreq = csio_scsi_cmpl_handler(hw, wr, len, flb, NULL, &scsiwr);
+	if (likely(ioreq)) {
+		if (unlikely(*scsiwr == FW_SCSI_ABRT_CLS_WR)) {
+			subop = FW_SCSI_ABRT_CLS_WR_SUB_OPCODE_GET(
+					((struct fw_scsi_abrt_cls_wr *)
+					    scsiwr)->sub_opcode_to_chk_all_io);
+
+			csio_dbg(hw, "%s cmpl recvd ioreq:%p status:%d\n",
+				    subop ? "Close" : "Abort",
+				    ioreq, ioreq->wr_status);
+
+			spin_lock_irqsave(&hw->lock, flags);
+			if (subop)
+				csio_scsi_closed(ioreq,
+						 (struct list_head *)cbfn_q);
+			else
+				csio_scsi_aborted(ioreq,
+						  (struct list_head *)cbfn_q);
+			/*
+			 * We call scsi_done for I/Os that driver thinks aborts
+			 * have timed out. If there is a race caused by FW
+			 * completing abort at the exact same time that the
+			 * driver has deteced the abort timeout, the following
+			 * check prevents calling of scsi_done twice for the
+			 * same command: once from the eh_abort_handler, another
+			 * from csio_scsi_isr_handler(). This also avoids the
+			 * need to check if csio_scsi_cmnd(req) is NULL in the
+			 * fast path.
+			 */
+			cmnd = csio_scsi_cmnd(ioreq);
+			if (unlikely(cmnd == NULL))
+				list_del_init(&ioreq->sm.sm_list);
+
+			spin_unlock_irqrestore(&hw->lock, flags);
+
+			if (unlikely(cmnd == NULL))
+				csio_put_scsi_ioreq_lock(hw,
+						csio_hw_to_scsim(hw), ioreq);
+		} else {
+			spin_lock_irqsave(&hw->lock, flags);
+			csio_scsi_completed(ioreq, (struct list_head *)cbfn_q);
+			spin_unlock_irqrestore(&hw->lock, flags);
+		}
+	}
+}
+
+/*
+ * csio_scsi_isr_handler() - Common SCSI ISR handler.
+ * @iq: Ingress queue pointer.
+ *
+ * Processes SCSI completions on the SCSI IQ indicated by scm->iq_idx
+ * by calling csio_wr_process_iq_idx. If there are completions on the
+ * isr_cbfn_q, yank them out into a local queue and call their io_cbfns.
+ * Once done, add these completions onto the freelist.
+ * This routine is shared b/w MSIX and INTx.
+ */
+static inline irqreturn_t
+csio_scsi_isr_handler(struct csio_q *iq)
+{
+	struct csio_hw *hw = (struct csio_hw *)iq->owner;
+	LIST_HEAD(cbfn_q);
+	struct list_head *tmp;
+	struct csio_scsim *scm;
+	struct csio_ioreq *ioreq;
+	int isr_completions = 0;
+
+	scm = csio_hw_to_scsim(hw);
+
+	if (unlikely(csio_wr_process_iq(hw, iq, csio_process_scsi_cmpl,
+					&cbfn_q) != 0))
+		return IRQ_NONE;
+
+	/* Call back the completion routines */
+	list_for_each(tmp, &cbfn_q) {
+		ioreq = (struct csio_ioreq *)tmp;
+		isr_completions++;
+		ioreq->io_cbfn(hw, ioreq);
+		/* Release ddp buffer if used for this req */
+		if (unlikely(ioreq->dcopy))
+			csio_put_scsi_ddp_list_lock(hw, scm, &ioreq->gen_list,
+						    ioreq->nsge);
+	}
+
+	if (isr_completions) {
+		/* Return the ioreqs back to ioreq->freelist */
+		csio_put_scsi_ioreq_list_lock(hw, scm, &cbfn_q,
+					      isr_completions);
+	}
+
+	return IRQ_HANDLED;
+}
+
+/*
+ * csio_scsi_isr() - SCSI MSIX handler
+ * @irq:
+ * @dev_id:
+ *
+ * This is the top level SCSI MSIX handler. Calls csio_scsi_isr_handler()
+ * for handling SCSI completions.
+ */
+static irqreturn_t
+csio_scsi_isr(int irq, void *dev_id)
+{
+	struct csio_q *iq = (struct csio_q *) dev_id;
+	struct csio_hw *hw;
+
+	if (unlikely(!iq))
+		return IRQ_NONE;
+
+	hw = (struct csio_hw *)iq->owner;
+
+	if (unlikely(pci_channel_offline(hw->pdev))) {
+		CSIO_INC_STATS(hw, n_pcich_offline);
+		return IRQ_NONE;
+	}
+
+	csio_scsi_isr_handler(iq);
+
+	return IRQ_HANDLED;
+}
+
+/*
+ * csio_scsi_intx_handler() - SCSI INTx handler
+ * @irq:
+ * @dev_id:
+ *
+ * This is the top level SCSI INTx handler. Calls csio_scsi_isr_handler()
+ * for handling SCSI completions.
+ */
+void
+csio_scsi_intx_handler(struct csio_hw *hw, void *wr, uint32_t len,
+			struct csio_fl_dma_buf *flb, void *priv)
+{
+	struct csio_q *iq = priv;
+
+	csio_scsi_isr_handler(iq);
+
+} /* csio_scsi_intx_handler */
+
+/*
+ * csio_fcoe_isr() - INTx/MSI interrupt service routine for FCoE.
+ * @irq:
+ * @dev_id:
+ *
+ *
+ */
+static irqreturn_t
+csio_fcoe_isr(int irq, void *dev_id)
+{
+	struct csio_hw *hw = (struct csio_hw *) dev_id;
+	struct csio_q *intx_q = NULL;
+	int rv;
+	irqreturn_t ret = IRQ_NONE;
+	unsigned long flags;
+
+	if (unlikely(!hw))
+		return IRQ_NONE;
+
+	if (unlikely(pci_channel_offline(hw->pdev))) {
+		CSIO_INC_STATS(hw, n_pcich_offline);
+		return IRQ_NONE;
+	}
+
+	/* Disable the interrupt for this PCI function. */
+	if (hw->intr_mode == CSIO_IM_INTX)
+		csio_wr_reg32(hw, 0, MYPF_REG(PCIE_PF_CLI_A));
+
+	/*
+	 * The read in the following function will flush the
+	 * above write.
+	 */
+	if (csio_hw_slow_intr_handler(hw))
+		ret = IRQ_HANDLED;
+
+	/* Get the INTx Forward interrupt IQ. */
+	intx_q = csio_get_q(hw, hw->intr_iq_idx);
+
+	CSIO_DB_ASSERT(intx_q);
+
+	/* IQ handler is not possible for intx_q, hence pass in NULL */
+	if (likely(csio_wr_process_iq(hw, intx_q, NULL, NULL) == 0))
+		ret = IRQ_HANDLED;
+
+	spin_lock_irqsave(&hw->lock, flags);
+	rv = csio_mb_isr_handler(hw);
+	if (rv == 0 && !(hw->flags & CSIO_HWF_FWEVT_PENDING)) {
+		hw->flags |= CSIO_HWF_FWEVT_PENDING;
+		spin_unlock_irqrestore(&hw->lock, flags);
+		schedule_work(&hw->evtq_work);
+		return IRQ_HANDLED;
+	}
+	spin_unlock_irqrestore(&hw->lock, flags);
+
+	return ret;
+}
+
+static void
+csio_add_msix_desc(struct csio_hw *hw)
+{
+	int i;
+	struct csio_msix_entries *entryp = &hw->msix_entries[0];
+	int k = CSIO_EXTRA_VECS;
+	int len = sizeof(entryp->desc) - 1;
+	int cnt = hw->num_sqsets + k;
+
+	/* Non-data vector */
+	memset(entryp->desc, 0, len + 1);
+	snprintf(entryp->desc, len, "csio-%02x:%02x:%x-nondata",
+		 CSIO_PCI_BUS(hw), CSIO_PCI_DEV(hw), CSIO_PCI_FUNC(hw));
+
+	entryp++;
+	memset(entryp->desc, 0, len + 1);
+	snprintf(entryp->desc, len, "csio-%02x:%02x:%x-fwevt",
+		 CSIO_PCI_BUS(hw), CSIO_PCI_DEV(hw), CSIO_PCI_FUNC(hw));
+	entryp++;
+
+	/* Name SCSI vecs */
+	for (i = k; i < cnt; i++, entryp++) {
+		memset(entryp->desc, 0, len + 1);
+		snprintf(entryp->desc, len, "csio-%02x:%02x:%x-scsi%d",
+			 CSIO_PCI_BUS(hw), CSIO_PCI_DEV(hw),
+			 CSIO_PCI_FUNC(hw), i - CSIO_EXTRA_VECS);
+	}
+}
+
+int
+csio_request_irqs(struct csio_hw *hw)
+{
+	int rv, i, j, k = 0;
+	struct csio_msix_entries *entryp = &hw->msix_entries[0];
+	struct csio_scsi_cpu_info *info;
+	struct pci_dev *pdev = hw->pdev;
+
+	if (hw->intr_mode != CSIO_IM_MSIX) {
+		rv = request_irq(pci_irq_vector(pdev, 0), csio_fcoe_isr,
+				hw->intr_mode == CSIO_IM_MSI ? 0 : IRQF_SHARED,
+				KBUILD_MODNAME, hw);
+		if (rv) {
+			csio_err(hw, "Failed to allocate interrupt line.\n");
+			goto out_free_irqs;
+		}
+
+		goto out;
+	}
+
+	/* Add the MSIX vector descriptions */
+	csio_add_msix_desc(hw);
+
+	rv = request_irq(pci_irq_vector(pdev, k), csio_nondata_isr, 0,
+			 entryp[k].desc, hw);
+	if (rv) {
+		csio_err(hw, "IRQ request failed for vec %d err:%d\n",
+			 pci_irq_vector(pdev, k), rv);
+		goto out_free_irqs;
+	}
+
+	entryp[k++].dev_id = hw;
+
+	rv = request_irq(pci_irq_vector(pdev, k), csio_fwevt_isr, 0,
+			 entryp[k].desc, hw);
+	if (rv) {
+		csio_err(hw, "IRQ request failed for vec %d err:%d\n",
+			 pci_irq_vector(pdev, k), rv);
+		goto out_free_irqs;
+	}
+
+	entryp[k++].dev_id = (void *)hw;
+
+	/* Allocate IRQs for SCSI */
+	for (i = 0; i < hw->num_pports; i++) {
+		info = &hw->scsi_cpu_info[i];
+		for (j = 0; j < info->max_cpus; j++, k++) {
+			struct csio_scsi_qset *sqset = &hw->sqset[i][j];
+			struct csio_q *q = hw->wrm.q_arr[sqset->iq_idx];
+
+			rv = request_irq(pci_irq_vector(pdev, k), csio_scsi_isr, 0,
+					 entryp[k].desc, q);
+			if (rv) {
+				csio_err(hw,
+				       "IRQ request failed for vec %d err:%d\n",
+				       pci_irq_vector(pdev, k), rv);
+				goto out_free_irqs;
+			}
+
+			entryp[k].dev_id = q;
+
+		} /* for all scsi cpus */
+	} /* for all ports */
+
+out:
+	hw->flags |= CSIO_HWF_HOST_INTR_ENABLED;
+	return 0;
+
+out_free_irqs:
+	for (i = 0; i < k; i++)
+		free_irq(pci_irq_vector(pdev, i), hw->msix_entries[i].dev_id);
+	pci_free_irq_vectors(hw->pdev);
+	return -EINVAL;
+}
+
+/* Reduce per-port max possible CPUs */
+static void
+csio_reduce_sqsets(struct csio_hw *hw, int cnt)
+{
+	int i;
+	struct csio_scsi_cpu_info *info;
+
+	while (cnt < hw->num_sqsets) {
+		for (i = 0; i < hw->num_pports; i++) {
+			info = &hw->scsi_cpu_info[i];
+			if (info->max_cpus > 1) {
+				info->max_cpus--;
+				hw->num_sqsets--;
+				if (hw->num_sqsets <= cnt)
+					break;
+			}
+		}
+	}
+
+	csio_dbg(hw, "Reduced sqsets to %d\n", hw->num_sqsets);
+}
+
+static void csio_calc_sets(struct irq_affinity *affd, unsigned int nvecs)
+{
+	struct csio_hw *hw = affd->priv;
+	u8 i;
+
+	if (!nvecs)
+		return;
+
+	if (nvecs < hw->num_pports) {
+		affd->nr_sets = 1;
+		affd->set_size[0] = nvecs;
+		return;
+	}
+
+	affd->nr_sets = hw->num_pports;
+	for (i = 0; i < hw->num_pports; i++)
+		affd->set_size[i] = nvecs / hw->num_pports;
+}
+
+static int
+csio_enable_msix(struct csio_hw *hw)
+{
+	int i, j, k, n, min, cnt;
+	int extra = CSIO_EXTRA_VECS;
+	struct csio_scsi_cpu_info *info;
+	struct irq_affinity desc = {
+		.pre_vectors = CSIO_EXTRA_VECS,
+		.calc_sets = csio_calc_sets,
+		.priv = hw,
+	};
+
+	if (hw->num_pports > IRQ_AFFINITY_MAX_SETS)
+		return -ENOSPC;
+
+	min = hw->num_pports + extra;
+	cnt = hw->num_sqsets + extra;
+
+	/* Max vectors required based on #niqs configured in fw */
+	if (hw->flags & CSIO_HWF_USING_SOFT_PARAMS || !csio_is_hw_master(hw))
+		cnt = min_t(uint8_t, hw->cfg_niq, cnt);
+
+	csio_dbg(hw, "FW supp #niq:%d, trying %d msix's\n", hw->cfg_niq, cnt);
+
+	cnt = pci_alloc_irq_vectors_affinity(hw->pdev, min, cnt,
+			PCI_IRQ_MSIX | PCI_IRQ_AFFINITY, &desc);
+	if (cnt < 0)
+		return cnt;
+
+	if (cnt < (hw->num_sqsets + extra)) {
+		csio_dbg(hw, "Reducing sqsets to %d\n", cnt - extra);
+		csio_reduce_sqsets(hw, cnt - extra);
+	}
+
+	/* Distribute vectors */
+	k = 0;
+	csio_set_nondata_intr_idx(hw, k);
+	csio_set_mb_intr_idx(csio_hw_to_mbm(hw), k++);
+	csio_set_fwevt_intr_idx(hw, k++);
+
+	for (i = 0; i < hw->num_pports; i++) {
+		info = &hw->scsi_cpu_info[i];
+
+		for (j = 0; j < hw->num_scsi_msix_cpus; j++) {
+			n = (j % info->max_cpus) +  k;
+			hw->sqset[i][j].intr_idx = n;
+		}
+
+		k += info->max_cpus;
+	}
+
+	return 0;
+}
+
+void
+csio_intr_enable(struct csio_hw *hw)
+{
+	hw->intr_mode = CSIO_IM_NONE;
+	hw->flags &= ~CSIO_HWF_HOST_INTR_ENABLED;
+
+	/* Try MSIX, then MSI or fall back to INTx */
+	if ((csio_msi == 2) && !csio_enable_msix(hw))
+		hw->intr_mode = CSIO_IM_MSIX;
+	else {
+		/* Max iqs required based on #niqs configured in fw */
+		if (hw->flags & CSIO_HWF_USING_SOFT_PARAMS ||
+			!csio_is_hw_master(hw)) {
+			int extra = CSIO_EXTRA_MSI_IQS;
+
+			if (hw->cfg_niq < (hw->num_sqsets + extra)) {
+				csio_dbg(hw, "Reducing sqsets to %d\n",
+					 hw->cfg_niq - extra);
+				csio_reduce_sqsets(hw, hw->cfg_niq - extra);
+			}
+		}
+
+		if ((csio_msi == 1) && !pci_enable_msi(hw->pdev))
+			hw->intr_mode = CSIO_IM_MSI;
+		else
+			hw->intr_mode = CSIO_IM_INTX;
+	}
+
+	csio_dbg(hw, "Using %s interrupt mode.\n",
+		(hw->intr_mode == CSIO_IM_MSIX) ? "MSIX" :
+		((hw->intr_mode == CSIO_IM_MSI) ? "MSI" : "INTx"));
+}
+
+void
+csio_intr_disable(struct csio_hw *hw, bool free)
+{
+	csio_hw_intr_disable(hw);
+
+	if (free) {
+		int i;
+
+		switch (hw->intr_mode) {
+		case CSIO_IM_MSIX:
+			for (i = 0; i < hw->num_sqsets + CSIO_EXTRA_VECS; i++) {
+				free_irq(pci_irq_vector(hw->pdev, i),
+					 hw->msix_entries[i].dev_id);
+			}
+			break;
+		case CSIO_IM_MSI:
+		case CSIO_IM_INTX:
+			free_irq(pci_irq_vector(hw->pdev, 0), hw);
+			break;
+		default:
+			break;
+		}
+	}
+
+	pci_free_irq_vectors(hw->pdev);
+	hw->intr_mode = CSIO_IM_NONE;
+	hw->flags &= ~CSIO_HWF_HOST_INTR_ENABLED;
+}