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, 715 insertions, 0 deletions

diff --git a/drivers/infiniband/hw/hfi1/pio_copy.c b/drivers/infiniband/hw/hfi1/pio_copy.c
new file mode 100644
index 000000000..7690f996d
--- /dev/null
+++ b/drivers/infiniband/hw/hfi1/pio_copy.c
@@ -0,0 +1,715 @@
+// SPDX-License-Identifier: GPL-2.0 or BSD-3-Clause
+/*
+ * Copyright(c) 2015, 2016 Intel Corporation.
+ */
+
+#include "hfi.h"
+
+/* additive distance between non-SOP and SOP space */
+#define SOP_DISTANCE (TXE_PIO_SIZE / 2)
+#define PIO_BLOCK_MASK (PIO_BLOCK_SIZE - 1)
+/* number of QUADWORDs in a block */
+#define PIO_BLOCK_QWS (PIO_BLOCK_SIZE / sizeof(u64))
+
+/**
+ * pio_copy - copy data block to MMIO space
+ * @dd: hfi1 dev data
+ * @pbuf: a number of blocks allocated within a PIO send context
+ * @pbc: PBC to send
+ * @from: source, must be 8 byte aligned
+ * @count: number of DWORD (32-bit) quantities to copy from source
+ *
+ * Copy data from source to PIO Send Buffer memory, 8 bytes at a time.
+ * Must always write full BLOCK_SIZE bytes blocks.  The first block must
+ * be written to the corresponding SOP=1 address.
+ *
+ * Known:
+ * o pbuf->start always starts on a block boundary
+ * o pbuf can wrap only at a block boundary
+ */
+void pio_copy(struct hfi1_devdata *dd, struct pio_buf *pbuf, u64 pbc,
+	      const void *from, size_t count)
+{
+	void __iomem *dest = pbuf->start + SOP_DISTANCE;
+	void __iomem *send = dest + PIO_BLOCK_SIZE;
+	void __iomem *dend;			/* 8-byte data end */
+
+	/* write the PBC */
+	writeq(pbc, dest);
+	dest += sizeof(u64);
+
+	/* calculate where the QWORD data ends - in SOP=1 space */
+	dend = dest + ((count >> 1) * sizeof(u64));
+
+	if (dend < send) {
+		/*
+		 * all QWORD data is within the SOP block, does *not*
+		 * reach the end of the SOP block
+		 */
+
+		while (dest < dend) {
+			writeq(*(u64 *)from, dest);
+			from += sizeof(u64);
+			dest += sizeof(u64);
+		}
+		/*
+		 * No boundary checks are needed here:
+		 * 0. We're not on the SOP block boundary
+		 * 1. The possible DWORD dangle will still be within
+		 *    the SOP block
+		 * 2. We cannot wrap except on a block boundary.
+		 */
+	} else {
+		/* QWORD data extends _to_ or beyond the SOP block */
+
+		/* write 8-byte SOP chunk data */
+		while (dest < send) {
+			writeq(*(u64 *)from, dest);
+			from += sizeof(u64);
+			dest += sizeof(u64);
+		}
+		/* drop out of the SOP range */
+		dest -= SOP_DISTANCE;
+		dend -= SOP_DISTANCE;
+
+		/*
+		 * If the wrap comes before or matches the data end,
+		 * copy until until the wrap, then wrap.
+		 *
+		 * If the data ends at the end of the SOP above and
+		 * the buffer wraps, then pbuf->end == dend == dest
+		 * and nothing will get written, but we will wrap in
+		 * case there is a dangling DWORD.
+		 */
+		if (pbuf->end <= dend) {
+			while (dest < pbuf->end) {
+				writeq(*(u64 *)from, dest);
+				from += sizeof(u64);
+				dest += sizeof(u64);
+			}
+
+			dest -= pbuf->sc->size;
+			dend -= pbuf->sc->size;
+		}
+
+		/* write 8-byte non-SOP, non-wrap chunk data */
+		while (dest < dend) {
+			writeq(*(u64 *)from, dest);
+			from += sizeof(u64);
+			dest += sizeof(u64);
+		}
+	}
+	/* at this point we have wrapped if we are going to wrap */
+
+	/* write dangling u32, if any */
+	if (count & 1) {
+		union mix val;
+
+		val.val64 = 0;
+		val.val32[0] = *(u32 *)from;
+		writeq(val.val64, dest);
+		dest += sizeof(u64);
+	}
+	/*
+	 * fill in rest of block, no need to check pbuf->end
+	 * as we only wrap on a block boundary
+	 */
+	while (((unsigned long)dest & PIO_BLOCK_MASK) != 0) {
+		writeq(0, dest);
+		dest += sizeof(u64);
+	}
+
+	/* finished with this buffer */
+	this_cpu_dec(*pbuf->sc->buffers_allocated);
+	preempt_enable();
+}
+
+/*
+ * Handle carry bytes using shifts and masks.
+ *
+ * NOTE: the value the unused portion of carry is expected to always be zero.
+ */
+
+/*
+ * "zero" shift - bit shift used to zero out upper bytes.  Input is
+ * the count of LSB bytes to preserve.
+ */
+#define zshift(x) (8 * (8 - (x)))
+
+/*
+ * "merge" shift - bit shift used to merge with carry bytes.  Input is
+ * the LSB byte count to move beyond.
+ */
+#define mshift(x) (8 * (x))
+
+/*
+ * Jump copy - no-loop copy for < 8 bytes.
+ */
+static inline void jcopy(u8 *dest, const u8 *src, u32 n)
+{
+	switch (n) {
+	case 7:
+		*dest++ = *src++;
+		fallthrough;
+	case 6:
+		*dest++ = *src++;
+		fallthrough;
+	case 5:
+		*dest++ = *src++;
+		fallthrough;
+	case 4:
+		*dest++ = *src++;
+		fallthrough;
+	case 3:
+		*dest++ = *src++;
+		fallthrough;
+	case 2:
+		*dest++ = *src++;
+		fallthrough;
+	case 1:
+		*dest++ = *src++;
+	}
+}
+
+/*
+ * Read nbytes from "from" and place them in the low bytes
+ * of pbuf->carry.  Other bytes are left as-is.  Any previous
+ * value in pbuf->carry is lost.
+ *
+ * NOTES:
+ * o do not read from from if nbytes is zero
+ * o from may _not_ be u64 aligned.
+ */
+static inline void read_low_bytes(struct pio_buf *pbuf, const void *from,
+				  unsigned int nbytes)
+{
+	pbuf->carry.val64 = 0;
+	jcopy(&pbuf->carry.val8[0], from, nbytes);
+	pbuf->carry_bytes = nbytes;
+}
+
+/*
+ * Read nbytes bytes from "from" and put them at the end of pbuf->carry.
+ * It is expected that the extra read does not overfill carry.
+ *
+ * NOTES:
+ * o from may _not_ be u64 aligned
+ * o nbytes may span a QW boundary
+ */
+static inline void read_extra_bytes(struct pio_buf *pbuf,
+				    const void *from, unsigned int nbytes)
+{
+	jcopy(&pbuf->carry.val8[pbuf->carry_bytes], from, nbytes);
+	pbuf->carry_bytes += nbytes;
+}
+
+/*
+ * Write a quad word using parts of pbuf->carry and the next 8 bytes of src.
+ * Put the unused part of the next 8 bytes of src into the LSB bytes of
+ * pbuf->carry with the upper bytes zeroed..
+ *
+ * NOTES:
+ * o result must keep unused bytes zeroed
+ * o src must be u64 aligned
+ */
+static inline void merge_write8(
+	struct pio_buf *pbuf,
+	void __iomem *dest,
+	const void *src)
+{
+	u64 new, temp;
+
+	new = *(u64 *)src;
+	temp = pbuf->carry.val64 | (new << mshift(pbuf->carry_bytes));
+	writeq(temp, dest);
+	pbuf->carry.val64 = new >> zshift(pbuf->carry_bytes);
+}
+
+/*
+ * Write a quad word using all bytes of carry.
+ */
+static inline void carry8_write8(union mix carry, void __iomem *dest)
+{
+	writeq(carry.val64, dest);
+}
+
+/*
+ * Write a quad word using all the valid bytes of carry.  If carry
+ * has zero valid bytes, nothing is written.
+ * Returns 0 on nothing written, non-zero on quad word written.
+ */
+static inline int carry_write8(struct pio_buf *pbuf, void __iomem *dest)
+{
+	if (pbuf->carry_bytes) {
+		/* unused bytes are always kept zeroed, so just write */
+		writeq(pbuf->carry.val64, dest);
+		return 1;
+	}
+
+	return 0;
+}
+
+/*
+ * Segmented PIO Copy - start
+ *
+ * Start a PIO copy.
+ *
+ * @pbuf: destination buffer
+ * @pbc: the PBC for the PIO buffer
+ * @from: data source, QWORD aligned
+ * @nbytes: bytes to copy
+ */
+void seg_pio_copy_start(struct pio_buf *pbuf, u64 pbc,
+			const void *from, size_t nbytes)
+{
+	void __iomem *dest = pbuf->start + SOP_DISTANCE;
+	void __iomem *send = dest + PIO_BLOCK_SIZE;
+	void __iomem *dend;			/* 8-byte data end */
+
+	writeq(pbc, dest);
+	dest += sizeof(u64);
+
+	/* calculate where the QWORD data ends - in SOP=1 space */
+	dend = dest + ((nbytes >> 3) * sizeof(u64));
+
+	if (dend < send) {
+		/*
+		 * all QWORD data is within the SOP block, does *not*
+		 * reach the end of the SOP block
+		 */
+
+		while (dest < dend) {
+			writeq(*(u64 *)from, dest);
+			from += sizeof(u64);
+			dest += sizeof(u64);
+		}
+		/*
+		 * No boundary checks are needed here:
+		 * 0. We're not on the SOP block boundary
+		 * 1. The possible DWORD dangle will still be within
+		 *    the SOP block
+		 * 2. We cannot wrap except on a block boundary.
+		 */
+	} else {
+		/* QWORD data extends _to_ or beyond the SOP block */
+
+		/* write 8-byte SOP chunk data */
+		while (dest < send) {
+			writeq(*(u64 *)from, dest);
+			from += sizeof(u64);
+			dest += sizeof(u64);
+		}
+		/* drop out of the SOP range */
+		dest -= SOP_DISTANCE;
+		dend -= SOP_DISTANCE;
+
+		/*
+		 * If the wrap comes before or matches the data end,
+		 * copy until until the wrap, then wrap.
+		 *
+		 * If the data ends at the end of the SOP above and
+		 * the buffer wraps, then pbuf->end == dend == dest
+		 * and nothing will get written, but we will wrap in
+		 * case there is a dangling DWORD.
+		 */
+		if (pbuf->end <= dend) {
+			while (dest < pbuf->end) {
+				writeq(*(u64 *)from, dest);
+				from += sizeof(u64);
+				dest += sizeof(u64);
+			}
+
+			dest -= pbuf->sc->size;
+			dend -= pbuf->sc->size;
+		}
+
+		/* write 8-byte non-SOP, non-wrap chunk data */
+		while (dest < dend) {
+			writeq(*(u64 *)from, dest);
+			from += sizeof(u64);
+			dest += sizeof(u64);
+		}
+	}
+	/* at this point we have wrapped if we are going to wrap */
+
+	/* ...but it doesn't matter as we're done writing */
+
+	/* save dangling bytes, if any */
+	read_low_bytes(pbuf, from, nbytes & 0x7);
+
+	pbuf->qw_written = 1 /*PBC*/ + (nbytes >> 3);
+}
+
+/*
+ * Mid copy helper, "mixed case" - source is 64-bit aligned but carry
+ * bytes are non-zero.
+ *
+ * Whole u64s must be written to the chip, so bytes must be manually merged.
+ *
+ * @pbuf: destination buffer
+ * @from: data source, is QWORD aligned.
+ * @nbytes: bytes to copy
+ *
+ * Must handle nbytes < 8.
+ */
+static void mid_copy_mix(struct pio_buf *pbuf, const void *from, size_t nbytes)
+{
+	void __iomem *dest = pbuf->start + (pbuf->qw_written * sizeof(u64));
+	void __iomem *dend;			/* 8-byte data end */
+	unsigned long qw_to_write = nbytes >> 3;
+	unsigned long bytes_left = nbytes & 0x7;
+
+	/* calculate 8-byte data end */
+	dend = dest + (qw_to_write * sizeof(u64));
+
+	if (pbuf->qw_written < PIO_BLOCK_QWS) {
+		/*
+		 * Still within SOP block.  We don't need to check for
+		 * wrap because we are still in the first block and
+		 * can only wrap on block boundaries.
+		 */
+		void __iomem *send;		/* SOP end */
+		void __iomem *xend;
+
+		/*
+		 * calculate the end of data or end of block, whichever
+		 * comes first
+		 */
+		send = pbuf->start + PIO_BLOCK_SIZE;
+		xend = min(send, dend);
+
+		/* shift up to SOP=1 space */
+		dest += SOP_DISTANCE;
+		xend += SOP_DISTANCE;
+
+		/* write 8-byte chunk data */
+		while (dest < xend) {
+			merge_write8(pbuf, dest, from);
+			from += sizeof(u64);
+			dest += sizeof(u64);
+		}
+
+		/* shift down to SOP=0 space */
+		dest -= SOP_DISTANCE;
+	}
+	/*
+	 * At this point dest could be (either, both, or neither):
+	 * - at dend
+	 * - at the wrap
+	 */
+
+	/*
+	 * If the wrap comes before or matches the data end,
+	 * copy until until the wrap, then wrap.
+	 *
+	 * If dest is at the wrap, we will fall into the if,
+	 * not do the loop, when wrap.
+	 *
+	 * If the data ends at the end of the SOP above and
+	 * the buffer wraps, then pbuf->end == dend == dest
+	 * and nothing will get written.
+	 */
+	if (pbuf->end <= dend) {
+		while (dest < pbuf->end) {
+			merge_write8(pbuf, dest, from);
+			from += sizeof(u64);
+			dest += sizeof(u64);
+		}
+
+		dest -= pbuf->sc->size;
+		dend -= pbuf->sc->size;
+	}
+
+	/* write 8-byte non-SOP, non-wrap chunk data */
+	while (dest < dend) {
+		merge_write8(pbuf, dest, from);
+		from += sizeof(u64);
+		dest += sizeof(u64);
+	}
+
+	pbuf->qw_written += qw_to_write;
+
+	/* handle carry and left-over bytes */
+	if (pbuf->carry_bytes + bytes_left >= 8) {
+		unsigned long nread;
+
+		/* there is enough to fill another qw - fill carry */
+		nread = 8 - pbuf->carry_bytes;
+		read_extra_bytes(pbuf, from, nread);
+
+		/*
+		 * One more write - but need to make sure dest is correct.
+		 * Check for wrap and the possibility the write
+		 * should be in SOP space.
+		 *
+		 * The two checks immediately below cannot both be true, hence
+		 * the else. If we have wrapped, we cannot still be within the
+		 * first block. Conversely, if we are still in the first block,
+		 * we cannot have wrapped. We do the wrap check first as that
+		 * is more likely.
+		 */
+		/* adjust if we have wrapped */
+		if (dest >= pbuf->end)
+			dest -= pbuf->sc->size;
+		/* jump to the SOP range if within the first block */
+		else if (pbuf->qw_written < PIO_BLOCK_QWS)
+			dest += SOP_DISTANCE;
+
+		/* flush out full carry */
+		carry8_write8(pbuf->carry, dest);
+		pbuf->qw_written++;
+
+		/* now adjust and read the rest of the bytes into carry */
+		bytes_left -= nread;
+		from += nread; /* from is now not aligned */
+		read_low_bytes(pbuf, from, bytes_left);
+	} else {
+		/* not enough to fill another qw, append the rest to carry */
+		read_extra_bytes(pbuf, from, bytes_left);
+	}
+}
+
+/*
+ * Mid copy helper, "straight case" - source pointer is 64-bit aligned
+ * with no carry bytes.
+ *
+ * @pbuf: destination buffer
+ * @from: data source, is QWORD aligned
+ * @nbytes: bytes to copy
+ *
+ * Must handle nbytes < 8.
+ */
+static void mid_copy_straight(struct pio_buf *pbuf,
+			      const void *from, size_t nbytes)
+{
+	void __iomem *dest = pbuf->start + (pbuf->qw_written * sizeof(u64));
+	void __iomem *dend;			/* 8-byte data end */
+
+	/* calculate 8-byte data end */
+	dend = dest + ((nbytes >> 3) * sizeof(u64));
+
+	if (pbuf->qw_written < PIO_BLOCK_QWS) {
+		/*
+		 * Still within SOP block.  We don't need to check for
+		 * wrap because we are still in the first block and
+		 * can only wrap on block boundaries.
+		 */
+		void __iomem *send;		/* SOP end */
+		void __iomem *xend;
+
+		/*
+		 * calculate the end of data or end of block, whichever
+		 * comes first
+		 */
+		send = pbuf->start + PIO_BLOCK_SIZE;
+		xend = min(send, dend);
+
+		/* shift up to SOP=1 space */
+		dest += SOP_DISTANCE;
+		xend += SOP_DISTANCE;
+
+		/* write 8-byte chunk data */
+		while (dest < xend) {
+			writeq(*(u64 *)from, dest);
+			from += sizeof(u64);
+			dest += sizeof(u64);
+		}
+
+		/* shift down to SOP=0 space */
+		dest -= SOP_DISTANCE;
+	}
+	/*
+	 * At this point dest could be (either, both, or neither):
+	 * - at dend
+	 * - at the wrap
+	 */
+
+	/*
+	 * If the wrap comes before or matches the data end,
+	 * copy until until the wrap, then wrap.
+	 *
+	 * If dest is at the wrap, we will fall into the if,
+	 * not do the loop, when wrap.
+	 *
+	 * If the data ends at the end of the SOP above and
+	 * the buffer wraps, then pbuf->end == dend == dest
+	 * and nothing will get written.
+	 */
+	if (pbuf->end <= dend) {
+		while (dest < pbuf->end) {
+			writeq(*(u64 *)from, dest);
+			from += sizeof(u64);
+			dest += sizeof(u64);
+		}
+
+		dest -= pbuf->sc->size;
+		dend -= pbuf->sc->size;
+	}
+
+	/* write 8-byte non-SOP, non-wrap chunk data */
+	while (dest < dend) {
+		writeq(*(u64 *)from, dest);
+		from += sizeof(u64);
+		dest += sizeof(u64);
+	}
+
+	/* we know carry_bytes was zero on entry to this routine */
+	read_low_bytes(pbuf, from, nbytes & 0x7);
+
+	pbuf->qw_written += nbytes >> 3;
+}
+
+/*
+ * Segmented PIO Copy - middle
+ *
+ * Must handle any aligned tail and any aligned source with any byte count.
+ *
+ * @pbuf: a number of blocks allocated within a PIO send context
+ * @from: data source
+ * @nbytes: number of bytes to copy
+ */
+void seg_pio_copy_mid(struct pio_buf *pbuf, const void *from, size_t nbytes)
+{
+	unsigned long from_align = (unsigned long)from & 0x7;
+
+	if (pbuf->carry_bytes + nbytes < 8) {
+		/* not enough bytes to fill a QW */
+		read_extra_bytes(pbuf, from, nbytes);
+		return;
+	}
+
+	if (from_align) {
+		/* misaligned source pointer - align it */
+		unsigned long to_align;
+
+		/* bytes to read to align "from" */
+		to_align = 8 - from_align;
+
+		/*
+		 * In the advance-to-alignment logic below, we do not need
+		 * to check if we are using more than nbytes.  This is because
+		 * if we are here, we already know that carry+nbytes will
+		 * fill at least one QW.
+		 */
+		if (pbuf->carry_bytes + to_align < 8) {
+			/* not enough align bytes to fill a QW */
+			read_extra_bytes(pbuf, from, to_align);
+			from += to_align;
+			nbytes -= to_align;
+		} else {
+			/* bytes to fill carry */
+			unsigned long to_fill = 8 - pbuf->carry_bytes;
+			/* bytes left over to be read */
+			unsigned long extra = to_align - to_fill;
+			void __iomem *dest;
+
+			/* fill carry... */
+			read_extra_bytes(pbuf, from, to_fill);
+			from += to_fill;
+			nbytes -= to_fill;
+			/* may not be enough valid bytes left to align */
+			if (extra > nbytes)
+				extra = nbytes;
+
+			/* ...now write carry */
+			dest = pbuf->start + (pbuf->qw_written * sizeof(u64));
+
+			/*
+			 * The two checks immediately below cannot both be
+			 * true, hence the else.  If we have wrapped, we
+			 * cannot still be within the first block.
+			 * Conversely, if we are still in the first block, we
+			 * cannot have wrapped.  We do the wrap check first
+			 * as that is more likely.
+			 */
+			/* adjust if we've wrapped */
+			if (dest >= pbuf->end)
+				dest -= pbuf->sc->size;
+			/* jump to SOP range if within the first block */
+			else if (pbuf->qw_written < PIO_BLOCK_QWS)
+				dest += SOP_DISTANCE;
+
+			carry8_write8(pbuf->carry, dest);
+			pbuf->qw_written++;
+
+			/* read any extra bytes to do final alignment */
+			/* this will overwrite anything in pbuf->carry */
+			read_low_bytes(pbuf, from, extra);
+			from += extra;
+			nbytes -= extra;
+			/*
+			 * If no bytes are left, return early - we are done.
+			 * NOTE: This short-circuit is *required* because
+			 * "extra" may have been reduced in size and "from"
+			 * is not aligned, as required when leaving this
+			 * if block.
+			 */
+			if (nbytes == 0)
+				return;
+		}
+
+		/* at this point, from is QW aligned */
+	}
+
+	if (pbuf->carry_bytes)
+		mid_copy_mix(pbuf, from, nbytes);
+	else
+		mid_copy_straight(pbuf, from, nbytes);
+}
+
+/*
+ * Segmented PIO Copy - end
+ *
+ * Write any remainder (in pbuf->carry) and finish writing the whole block.
+ *
+ * @pbuf: a number of blocks allocated within a PIO send context
+ */
+void seg_pio_copy_end(struct pio_buf *pbuf)
+{
+	void __iomem *dest = pbuf->start + (pbuf->qw_written * sizeof(u64));
+
+	/*
+	 * The two checks immediately below cannot both be true, hence the
+	 * else.  If we have wrapped, we cannot still be within the first
+	 * block.  Conversely, if we are still in the first block, we
+	 * cannot have wrapped.  We do the wrap check first as that is
+	 * more likely.
+	 */
+	/* adjust if we have wrapped */
+	if (dest >= pbuf->end)
+		dest -= pbuf->sc->size;
+	/* jump to the SOP range if within the first block */
+	else if (pbuf->qw_written < PIO_BLOCK_QWS)
+		dest += SOP_DISTANCE;
+
+	/* write final bytes, if any */
+	if (carry_write8(pbuf, dest)) {
+		dest += sizeof(u64);
+		/*
+		 * NOTE: We do not need to recalculate whether dest needs
+		 * SOP_DISTANCE or not.
+		 *
+		 * If we are in the first block and the dangle write
+		 * keeps us in the same block, dest will need
+		 * to retain SOP_DISTANCE in the loop below.
+		 *
+		 * If we are in the first block and the dangle write pushes
+		 * us to the next block, then loop below will not run
+		 * and dest is not used.  Hence we do not need to update
+		 * it.
+		 *
+		 * If we are past the first block, then SOP_DISTANCE
+		 * was never added, so there is nothing to do.
+		 */
+	}
+
+	/* fill in rest of block */
+	while (((unsigned long)dest & PIO_BLOCK_MASK) != 0) {
+		writeq(0, dest);
+		dest += sizeof(u64);
+	}
+
+	/* finished with this buffer */
+	this_cpu_dec(*pbuf->sc->buffers_allocated);
+	preempt_enable();
+}