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, 549 insertions, 0 deletions

diff --git a/drivers/infiniband/hw/qib/qib_qsfp.c b/drivers/infiniband/hw/qib/qib_qsfp.c
new file mode 100644
index 000000000..295d40a83
--- /dev/null
+++ b/drivers/infiniband/hw/qib/qib_qsfp.c
@@ -0,0 +1,549 @@
+/*
+ * Copyright (c) 2006, 2007, 2008, 2009 QLogic Corporation. All rights reserved.
+ * Copyright (c) 2003, 2004, 2005, 2006 PathScale, 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/delay.h>
+#include <linux/pci.h>
+#include <linux/vmalloc.h>
+
+#include "qib.h"
+#include "qib_qsfp.h"
+
+/*
+ * QSFP support for ib_qib driver, using "Two Wire Serial Interface" driver
+ * in qib_twsi.c
+ */
+#define QSFP_MAX_RETRY 4
+
+static int qsfp_read(struct qib_pportdata *ppd, int addr, void *bp, int len)
+{
+	struct qib_devdata *dd = ppd->dd;
+	u32 out, mask;
+	int ret, cnt, pass = 0;
+	int stuck = 0;
+	u8 *buff = bp;
+
+	ret = mutex_lock_interruptible(&dd->eep_lock);
+	if (ret)
+		goto no_unlock;
+
+	if (dd->twsi_eeprom_dev == QIB_TWSI_NO_DEV) {
+		ret = -ENXIO;
+		goto bail;
+	}
+
+	/*
+	 * We presume, if we are called at all, that this board has
+	 * QSFP. This is on the same i2c chain as the legacy parts,
+	 * but only responds if the module is selected via GPIO pins.
+	 * Further, there are very long setup and hold requirements
+	 * on MODSEL.
+	 */
+	mask = QSFP_GPIO_MOD_SEL_N | QSFP_GPIO_MOD_RST_N | QSFP_GPIO_LP_MODE;
+	out = QSFP_GPIO_MOD_RST_N | QSFP_GPIO_LP_MODE;
+	if (ppd->hw_pidx) {
+		mask <<= QSFP_GPIO_PORT2_SHIFT;
+		out <<= QSFP_GPIO_PORT2_SHIFT;
+	}
+
+	dd->f_gpio_mod(dd, out, mask, mask);
+
+	/*
+	 * Module could take up to 2 Msec to respond to MOD_SEL, and there
+	 * is no way to tell if it is ready, so we must wait.
+	 */
+	msleep(20);
+
+	/* Make sure TWSI bus is in sane state. */
+	ret = qib_twsi_reset(dd);
+	if (ret) {
+		qib_dev_porterr(dd, ppd->port,
+				"QSFP interface Reset for read failed\n");
+		ret = -EIO;
+		stuck = 1;
+		goto deselect;
+	}
+
+	/* All QSFP modules are at A0 */
+
+	cnt = 0;
+	while (cnt < len) {
+		unsigned in_page;
+		int wlen = len - cnt;
+
+		in_page = addr % QSFP_PAGESIZE;
+		if ((in_page + wlen) > QSFP_PAGESIZE)
+			wlen = QSFP_PAGESIZE - in_page;
+		ret = qib_twsi_blk_rd(dd, QSFP_DEV, addr, buff + cnt, wlen);
+		/* Some QSFP's fail first try. Retry as experiment */
+		if (ret && cnt == 0 && ++pass < QSFP_MAX_RETRY)
+			continue;
+		if (ret) {
+			/* qib_twsi_blk_rd() 1 for error, else 0 */
+			ret = -EIO;
+			goto deselect;
+		}
+		addr += wlen;
+		cnt += wlen;
+	}
+	ret = cnt;
+
+deselect:
+	/*
+	 * Module could take up to 10 uSec after transfer before
+	 * ready to respond to MOD_SEL negation, and there is no way
+	 * to tell if it is ready, so we must wait.
+	 */
+	udelay(10);
+	/* set QSFP MODSEL, RST. LP all high */
+	dd->f_gpio_mod(dd, mask, mask, mask);
+
+	/*
+	 * Module could take up to 2 Msec to respond to MOD_SEL
+	 * going away, and there is no way to tell if it is ready.
+	 * so we must wait.
+	 */
+	if (stuck)
+		qib_dev_err(dd, "QSFP interface bus stuck non-idle\n");
+
+	if (pass >= QSFP_MAX_RETRY && ret)
+		qib_dev_porterr(dd, ppd->port, "QSFP failed even retrying\n");
+	else if (pass)
+		qib_dev_porterr(dd, ppd->port, "QSFP retries: %d\n", pass);
+
+	msleep(20);
+
+bail:
+	mutex_unlock(&dd->eep_lock);
+
+no_unlock:
+	return ret;
+}
+
+/*
+ * qsfp_write
+ * We do not ordinarily write the QSFP, but this is needed to select
+ * the page on non-flat QSFPs, and possibly later unusual cases
+ */
+static int qib_qsfp_write(struct qib_pportdata *ppd, int addr, void *bp,
+			  int len)
+{
+	struct qib_devdata *dd = ppd->dd;
+	u32 out, mask;
+	int ret, cnt;
+	u8 *buff = bp;
+
+	ret = mutex_lock_interruptible(&dd->eep_lock);
+	if (ret)
+		goto no_unlock;
+
+	if (dd->twsi_eeprom_dev == QIB_TWSI_NO_DEV) {
+		ret = -ENXIO;
+		goto bail;
+	}
+
+	/*
+	 * We presume, if we are called at all, that this board has
+	 * QSFP. This is on the same i2c chain as the legacy parts,
+	 * but only responds if the module is selected via GPIO pins.
+	 * Further, there are very long setup and hold requirements
+	 * on MODSEL.
+	 */
+	mask = QSFP_GPIO_MOD_SEL_N | QSFP_GPIO_MOD_RST_N | QSFP_GPIO_LP_MODE;
+	out = QSFP_GPIO_MOD_RST_N | QSFP_GPIO_LP_MODE;
+	if (ppd->hw_pidx) {
+		mask <<= QSFP_GPIO_PORT2_SHIFT;
+		out <<= QSFP_GPIO_PORT2_SHIFT;
+	}
+	dd->f_gpio_mod(dd, out, mask, mask);
+
+	/*
+	 * Module could take up to 2 Msec to respond to MOD_SEL,
+	 * and there is no way to tell if it is ready, so we must wait.
+	 */
+	msleep(20);
+
+	/* Make sure TWSI bus is in sane state. */
+	ret = qib_twsi_reset(dd);
+	if (ret) {
+		qib_dev_porterr(dd, ppd->port,
+				"QSFP interface Reset for write failed\n");
+		ret = -EIO;
+		goto deselect;
+	}
+
+	/* All QSFP modules are at A0 */
+
+	cnt = 0;
+	while (cnt < len) {
+		unsigned in_page;
+		int wlen = len - cnt;
+
+		in_page = addr % QSFP_PAGESIZE;
+		if ((in_page + wlen) > QSFP_PAGESIZE)
+			wlen = QSFP_PAGESIZE - in_page;
+		ret = qib_twsi_blk_wr(dd, QSFP_DEV, addr, buff + cnt, wlen);
+		if (ret) {
+			/* qib_twsi_blk_wr() 1 for error, else 0 */
+			ret = -EIO;
+			goto deselect;
+		}
+		addr += wlen;
+		cnt += wlen;
+	}
+	ret = cnt;
+
+deselect:
+	/*
+	 * Module could take up to 10 uSec after transfer before
+	 * ready to respond to MOD_SEL negation, and there is no way
+	 * to tell if it is ready, so we must wait.
+	 */
+	udelay(10);
+	/* set QSFP MODSEL, RST, LP high */
+	dd->f_gpio_mod(dd, mask, mask, mask);
+	/*
+	 * Module could take up to 2 Msec to respond to MOD_SEL
+	 * going away, and there is no way to tell if it is ready.
+	 * so we must wait.
+	 */
+	msleep(20);
+
+bail:
+	mutex_unlock(&dd->eep_lock);
+
+no_unlock:
+	return ret;
+}
+
+/*
+ * For validation, we want to check the checksums, even of the
+ * fields we do not otherwise use. This function reads the bytes from
+ * <first> to <next-1> and returns the 8lsbs of the sum, or <0 for errors
+ */
+static int qsfp_cks(struct qib_pportdata *ppd, int first, int next)
+{
+	int ret;
+	u16 cks;
+	u8 bval;
+
+	cks = 0;
+	while (first < next) {
+		ret = qsfp_read(ppd, first, &bval, 1);
+		if (ret < 0)
+			goto bail;
+		cks += bval;
+		++first;
+	}
+	ret = cks & 0xFF;
+bail:
+	return ret;
+
+}
+
+int qib_refresh_qsfp_cache(struct qib_pportdata *ppd, struct qib_qsfp_cache *cp)
+{
+	int ret;
+	int idx;
+	u16 cks;
+	u8 peek[4];
+
+	/* ensure sane contents on invalid reads, for cable swaps */
+	memset(cp, 0, sizeof(*cp));
+
+	if (!qib_qsfp_mod_present(ppd)) {
+		ret = -ENODEV;
+		goto bail;
+	}
+
+	ret = qsfp_read(ppd, 0, peek, 3);
+	if (ret < 0)
+		goto bail;
+	if ((peek[0] & 0xFE) != 0x0C)
+		qib_dev_porterr(ppd->dd, ppd->port,
+				"QSFP byte0 is 0x%02X, S/B 0x0C/D\n", peek[0]);
+
+	if ((peek[2] & 4) == 0) {
+		/*
+		 * If cable is paged, rather than "flat memory", we need to
+		 * set the page to zero, Even if it already appears to be zero.
+		 */
+		u8 poke = 0;
+
+		ret = qib_qsfp_write(ppd, 127, &poke, 1);
+		udelay(50);
+		if (ret != 1) {
+			qib_dev_porterr(ppd->dd, ppd->port,
+					"Failed QSFP Page set\n");
+			goto bail;
+		}
+	}
+
+	ret = qsfp_read(ppd, QSFP_MOD_ID_OFFS, &cp->id, 1);
+	if (ret < 0)
+		goto bail;
+	if ((cp->id & 0xFE) != 0x0C)
+		qib_dev_porterr(ppd->dd, ppd->port,
+				"QSFP ID byte is 0x%02X, S/B 0x0C/D\n", cp->id);
+	cks = cp->id;
+
+	ret = qsfp_read(ppd, QSFP_MOD_PWR_OFFS, &cp->pwr, 1);
+	if (ret < 0)
+		goto bail;
+	cks += cp->pwr;
+
+	ret = qsfp_cks(ppd, QSFP_MOD_PWR_OFFS + 1, QSFP_MOD_LEN_OFFS);
+	if (ret < 0)
+		goto bail;
+	cks += ret;
+
+	ret = qsfp_read(ppd, QSFP_MOD_LEN_OFFS, &cp->len, 1);
+	if (ret < 0)
+		goto bail;
+	cks += cp->len;
+
+	ret = qsfp_read(ppd, QSFP_MOD_TECH_OFFS, &cp->tech, 1);
+	if (ret < 0)
+		goto bail;
+	cks += cp->tech;
+
+	ret = qsfp_read(ppd, QSFP_VEND_OFFS, &cp->vendor, QSFP_VEND_LEN);
+	if (ret < 0)
+		goto bail;
+	for (idx = 0; idx < QSFP_VEND_LEN; ++idx)
+		cks += cp->vendor[idx];
+
+	ret = qsfp_read(ppd, QSFP_IBXCV_OFFS, &cp->xt_xcv, 1);
+	if (ret < 0)
+		goto bail;
+	cks += cp->xt_xcv;
+
+	ret = qsfp_read(ppd, QSFP_VOUI_OFFS, &cp->oui, QSFP_VOUI_LEN);
+	if (ret < 0)
+		goto bail;
+	for (idx = 0; idx < QSFP_VOUI_LEN; ++idx)
+		cks += cp->oui[idx];
+
+	ret = qsfp_read(ppd, QSFP_PN_OFFS, &cp->partnum, QSFP_PN_LEN);
+	if (ret < 0)
+		goto bail;
+	for (idx = 0; idx < QSFP_PN_LEN; ++idx)
+		cks += cp->partnum[idx];
+
+	ret = qsfp_read(ppd, QSFP_REV_OFFS, &cp->rev, QSFP_REV_LEN);
+	if (ret < 0)
+		goto bail;
+	for (idx = 0; idx < QSFP_REV_LEN; ++idx)
+		cks += cp->rev[idx];
+
+	ret = qsfp_read(ppd, QSFP_ATTEN_OFFS, &cp->atten, QSFP_ATTEN_LEN);
+	if (ret < 0)
+		goto bail;
+	for (idx = 0; idx < QSFP_ATTEN_LEN; ++idx)
+		cks += cp->atten[idx];
+
+	ret = qsfp_cks(ppd, QSFP_ATTEN_OFFS + QSFP_ATTEN_LEN, QSFP_CC_OFFS);
+	if (ret < 0)
+		goto bail;
+	cks += ret;
+
+	cks &= 0xFF;
+	ret = qsfp_read(ppd, QSFP_CC_OFFS, &cp->cks1, 1);
+	if (ret < 0)
+		goto bail;
+	if (cks != cp->cks1)
+		qib_dev_porterr(ppd->dd, ppd->port,
+				"QSFP cks1 is %02X, computed %02X\n", cp->cks1,
+				cks);
+
+	/* Second checksum covers 192 to (serial, date, lot) */
+	ret = qsfp_cks(ppd, QSFP_CC_OFFS + 1, QSFP_SN_OFFS);
+	if (ret < 0)
+		goto bail;
+	cks = ret;
+
+	ret = qsfp_read(ppd, QSFP_SN_OFFS, &cp->serial, QSFP_SN_LEN);
+	if (ret < 0)
+		goto bail;
+	for (idx = 0; idx < QSFP_SN_LEN; ++idx)
+		cks += cp->serial[idx];
+
+	ret = qsfp_read(ppd, QSFP_DATE_OFFS, &cp->date, QSFP_DATE_LEN);
+	if (ret < 0)
+		goto bail;
+	for (idx = 0; idx < QSFP_DATE_LEN; ++idx)
+		cks += cp->date[idx];
+
+	ret = qsfp_read(ppd, QSFP_LOT_OFFS, &cp->lot, QSFP_LOT_LEN);
+	if (ret < 0)
+		goto bail;
+	for (idx = 0; idx < QSFP_LOT_LEN; ++idx)
+		cks += cp->lot[idx];
+
+	ret = qsfp_cks(ppd, QSFP_LOT_OFFS + QSFP_LOT_LEN, QSFP_CC_EXT_OFFS);
+	if (ret < 0)
+		goto bail;
+	cks += ret;
+
+	ret = qsfp_read(ppd, QSFP_CC_EXT_OFFS, &cp->cks2, 1);
+	if (ret < 0)
+		goto bail;
+	cks &= 0xFF;
+	if (cks != cp->cks2)
+		qib_dev_porterr(ppd->dd, ppd->port,
+				"QSFP cks2 is %02X, computed %02X\n", cp->cks2,
+				cks);
+	return 0;
+
+bail:
+	cp->id = 0;
+	return ret;
+}
+
+const char * const qib_qsfp_devtech[16] = {
+	"850nm VCSEL", "1310nm VCSEL", "1550nm VCSEL", "1310nm FP",
+	"1310nm DFB", "1550nm DFB", "1310nm EML", "1550nm EML",
+	"Cu Misc", "1490nm DFB", "Cu NoEq", "Cu Eq",
+	"Undef", "Cu Active BothEq", "Cu FarEq", "Cu NearEq"
+};
+
+#define QSFP_DUMP_CHUNK 16 /* Holds longest string */
+#define QSFP_DEFAULT_HDR_CNT 224
+
+static const char *pwr_codes = "1.5W2.0W2.5W3.5W";
+
+int qib_qsfp_mod_present(struct qib_pportdata *ppd)
+{
+	u32 mask;
+	int ret;
+
+	mask = QSFP_GPIO_MOD_PRS_N <<
+		(ppd->hw_pidx * QSFP_GPIO_PORT2_SHIFT);
+	ret = ppd->dd->f_gpio_mod(ppd->dd, 0, 0, 0);
+
+	return !((ret & mask) >>
+		 ((ppd->hw_pidx * QSFP_GPIO_PORT2_SHIFT) + 3));
+}
+
+/*
+ * Initialize structures that control access to QSFP. Called once per port
+ * on cards that support QSFP.
+ */
+void qib_qsfp_init(struct qib_qsfp_data *qd,
+		   void (*fevent)(struct work_struct *))
+{
+	u32 mask, highs;
+
+	struct qib_devdata *dd = qd->ppd->dd;
+
+	/* Initialize work struct for later QSFP events */
+	INIT_WORK(&qd->work, fevent);
+
+	/*
+	 * Later, we may want more validation. For now, just set up pins and
+	 * blip reset. If module is present, call qib_refresh_qsfp_cache(),
+	 * to do further init.
+	 */
+	mask = QSFP_GPIO_MOD_SEL_N | QSFP_GPIO_MOD_RST_N | QSFP_GPIO_LP_MODE;
+	highs = mask - QSFP_GPIO_MOD_RST_N;
+	if (qd->ppd->hw_pidx) {
+		mask <<= QSFP_GPIO_PORT2_SHIFT;
+		highs <<= QSFP_GPIO_PORT2_SHIFT;
+	}
+	dd->f_gpio_mod(dd, highs, mask, mask);
+	udelay(20); /* Generous RST dwell */
+
+	dd->f_gpio_mod(dd, mask, mask, mask);
+}
+
+int qib_qsfp_dump(struct qib_pportdata *ppd, char *buf, int len)
+{
+	struct qib_qsfp_cache cd;
+	u8 bin_buff[QSFP_DUMP_CHUNK];
+	char lenstr[6];
+	int sofar, ret;
+	int bidx = 0;
+
+	sofar = 0;
+	ret = qib_refresh_qsfp_cache(ppd, &cd);
+	if (ret < 0)
+		goto bail;
+
+	lenstr[0] = ' ';
+	lenstr[1] = '\0';
+	if (QSFP_IS_CU(cd.tech))
+		sprintf(lenstr, "%dM ", cd.len);
+
+	sofar += scnprintf(buf + sofar, len - sofar, "PWR:%.3sW\n", pwr_codes +
+			   (QSFP_PWR(cd.pwr) * 4));
+
+	sofar += scnprintf(buf + sofar, len - sofar, "TECH:%s%s\n", lenstr,
+			   qib_qsfp_devtech[cd.tech >> 4]);
+
+	sofar += scnprintf(buf + sofar, len - sofar, "Vendor:%.*s\n",
+			   QSFP_VEND_LEN, cd.vendor);
+
+	sofar += scnprintf(buf + sofar, len - sofar, "OUI:%06X\n",
+			   QSFP_OUI(cd.oui));
+
+	sofar += scnprintf(buf + sofar, len - sofar, "Part#:%.*s\n",
+			   QSFP_PN_LEN, cd.partnum);
+	sofar += scnprintf(buf + sofar, len - sofar, "Rev:%.*s\n",
+			   QSFP_REV_LEN, cd.rev);
+	if (QSFP_IS_CU(cd.tech))
+		sofar += scnprintf(buf + sofar, len - sofar, "Atten:%d, %d\n",
+				   QSFP_ATTEN_SDR(cd.atten),
+				   QSFP_ATTEN_DDR(cd.atten));
+	sofar += scnprintf(buf + sofar, len - sofar, "Serial:%.*s\n",
+			   QSFP_SN_LEN, cd.serial);
+	sofar += scnprintf(buf + sofar, len - sofar, "Date:%.*s\n",
+			   QSFP_DATE_LEN, cd.date);
+	sofar += scnprintf(buf + sofar, len - sofar, "Lot:%.*s\n",
+			   QSFP_LOT_LEN, cd.lot);
+
+	while (bidx < QSFP_DEFAULT_HDR_CNT) {
+		int iidx;
+
+		ret = qsfp_read(ppd, bidx, bin_buff, QSFP_DUMP_CHUNK);
+		if (ret < 0)
+			goto bail;
+		for (iidx = 0; iidx < ret; ++iidx) {
+			sofar += scnprintf(buf + sofar, len-sofar, " %02X",
+				bin_buff[iidx]);
+		}
+		sofar += scnprintf(buf + sofar, len - sofar, "\n");
+		bidx += QSFP_DUMP_CHUNK;
+	}
+	ret = sofar;
+bail:
+	return ret;
+}