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, 548 insertions, 0 deletions

diff --git a/drivers/net/wireless/ath/ath6kl/bmi.c b/drivers/net/wireless/ath/ath6kl/bmi.c
new file mode 100644
index 000000000..bde5a10d4
--- /dev/null
+++ b/drivers/net/wireless/ath/ath6kl/bmi.c
@@ -0,0 +1,548 @@
+/*
+ * Copyright (c) 2004-2011 Atheros Communications Inc.
+ * Copyright (c) 2011-2012 Qualcomm Atheros, Inc.
+ *
+ * Permission to use, copy, modify, and/or distribute this software for any
+ * purpose with or without fee is hereby granted, provided that the above
+ * copyright notice and this permission notice appear in all copies.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES
+ * WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF
+ * MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR
+ * ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
+ * WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN
+ * ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF
+ * OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
+ */
+
+#include "core.h"
+#include "hif-ops.h"
+#include "target.h"
+#include "debug.h"
+
+int ath6kl_bmi_done(struct ath6kl *ar)
+{
+	int ret;
+	u32 cid = BMI_DONE;
+
+	if (ar->bmi.done_sent) {
+		ath6kl_dbg(ATH6KL_DBG_BMI, "bmi done skipped\n");
+		return 0;
+	}
+
+	ar->bmi.done_sent = true;
+
+	ret = ath6kl_hif_bmi_write(ar, (u8 *)&cid, sizeof(cid));
+	if (ret) {
+		ath6kl_err("Unable to send bmi done: %d\n", ret);
+		return ret;
+	}
+
+	return 0;
+}
+
+int ath6kl_bmi_get_target_info(struct ath6kl *ar,
+			       struct ath6kl_bmi_target_info *targ_info)
+{
+	int ret;
+	u32 cid = BMI_GET_TARGET_INFO;
+
+	if (ar->bmi.done_sent) {
+		ath6kl_err("bmi done sent already, cmd %d disallowed\n", cid);
+		return -EACCES;
+	}
+
+	ret = ath6kl_hif_bmi_write(ar, (u8 *)&cid, sizeof(cid));
+	if (ret) {
+		ath6kl_err("Unable to send get target info: %d\n", ret);
+		return ret;
+	}
+
+	if (ar->hif_type == ATH6KL_HIF_TYPE_USB) {
+		ret = ath6kl_hif_bmi_read(ar, (u8 *)targ_info,
+					  sizeof(*targ_info));
+	} else {
+		ret = ath6kl_hif_bmi_read(ar, (u8 *)&targ_info->version,
+				sizeof(targ_info->version));
+	}
+
+	if (ret) {
+		ath6kl_err("Unable to recv target info: %d\n", ret);
+		return ret;
+	}
+
+	if (le32_to_cpu(targ_info->version) == TARGET_VERSION_SENTINAL) {
+		/* Determine how many bytes are in the Target's targ_info */
+		ret = ath6kl_hif_bmi_read(ar,
+				   (u8 *)&targ_info->byte_count,
+				   sizeof(targ_info->byte_count));
+		if (ret) {
+			ath6kl_err("unable to read target info byte count: %d\n",
+				   ret);
+			return ret;
+		}
+
+		/*
+		 * The target's targ_info doesn't match the host's targ_info.
+		 * We need to do some backwards compatibility to make this work.
+		 */
+		if (le32_to_cpu(targ_info->byte_count) != sizeof(*targ_info)) {
+			WARN_ON(1);
+			return -EINVAL;
+		}
+
+		/* Read the remainder of the targ_info */
+		ret = ath6kl_hif_bmi_read(ar,
+				   ((u8 *)targ_info) +
+				   sizeof(targ_info->byte_count),
+				   sizeof(*targ_info) -
+				   sizeof(targ_info->byte_count));
+
+		if (ret) {
+			ath6kl_err("Unable to read target info (%d bytes): %d\n",
+				   targ_info->byte_count, ret);
+			return ret;
+		}
+	}
+
+	ath6kl_dbg(ATH6KL_DBG_BMI, "target info (ver: 0x%x type: 0x%x)\n",
+		   targ_info->version, targ_info->type);
+
+	return 0;
+}
+
+int ath6kl_bmi_read(struct ath6kl *ar, u32 addr, u8 *buf, u32 len)
+{
+	u32 cid = BMI_READ_MEMORY;
+	int ret;
+	u32 offset;
+	u32 len_remain, rx_len;
+	u16 size;
+
+	if (ar->bmi.done_sent) {
+		ath6kl_err("bmi done sent already, cmd %d disallowed\n", cid);
+		return -EACCES;
+	}
+
+	size = ar->bmi.max_data_size + sizeof(cid) + sizeof(addr) + sizeof(len);
+	if (size > ar->bmi.max_cmd_size) {
+		WARN_ON(1);
+		return -EINVAL;
+	}
+	memset(ar->bmi.cmd_buf, 0, size);
+
+	ath6kl_dbg(ATH6KL_DBG_BMI,
+		   "bmi read memory: device: addr: 0x%x, len: %d\n",
+		   addr, len);
+
+	len_remain = len;
+
+	while (len_remain) {
+		rx_len = (len_remain < ar->bmi.max_data_size) ?
+					len_remain : ar->bmi.max_data_size;
+		offset = 0;
+		memcpy(&(ar->bmi.cmd_buf[offset]), &cid, sizeof(cid));
+		offset += sizeof(cid);
+		memcpy(&(ar->bmi.cmd_buf[offset]), &addr, sizeof(addr));
+		offset += sizeof(addr);
+		memcpy(&(ar->bmi.cmd_buf[offset]), &rx_len, sizeof(rx_len));
+		offset += sizeof(len);
+
+		ret = ath6kl_hif_bmi_write(ar, ar->bmi.cmd_buf, offset);
+		if (ret) {
+			ath6kl_err("Unable to write to the device: %d\n",
+				   ret);
+			return ret;
+		}
+		ret = ath6kl_hif_bmi_read(ar, ar->bmi.cmd_buf, rx_len);
+		if (ret) {
+			ath6kl_err("Unable to read from the device: %d\n",
+				   ret);
+			return ret;
+		}
+		memcpy(&buf[len - len_remain], ar->bmi.cmd_buf, rx_len);
+		len_remain -= rx_len; addr += rx_len;
+	}
+
+	return 0;
+}
+
+int ath6kl_bmi_write(struct ath6kl *ar, u32 addr, u8 *buf, u32 len)
+{
+	u32 cid = BMI_WRITE_MEMORY;
+	int ret;
+	u32 offset;
+	u32 len_remain, tx_len;
+	const u32 header = sizeof(cid) + sizeof(addr) + sizeof(len);
+	u8 aligned_buf[400];
+	u8 *src;
+
+	if (ar->bmi.done_sent) {
+		ath6kl_err("bmi done sent already, cmd %d disallowed\n", cid);
+		return -EACCES;
+	}
+
+	if ((ar->bmi.max_data_size + header) > ar->bmi.max_cmd_size) {
+		WARN_ON(1);
+		return -EINVAL;
+	}
+
+	if (WARN_ON(ar->bmi.max_data_size > sizeof(aligned_buf)))
+		return -E2BIG;
+
+	memset(ar->bmi.cmd_buf, 0, ar->bmi.max_data_size + header);
+
+	ath6kl_dbg(ATH6KL_DBG_BMI,
+		   "bmi write memory: addr: 0x%x, len: %d\n", addr, len);
+
+	len_remain = len;
+	while (len_remain) {
+		src = &buf[len - len_remain];
+
+		if (len_remain < (ar->bmi.max_data_size - header)) {
+			if (len_remain & 3) {
+				/* align it with 4 bytes */
+				len_remain = len_remain +
+					     (4 - (len_remain & 3));
+				memcpy(aligned_buf, src, len_remain);
+				src = aligned_buf;
+			}
+			tx_len = len_remain;
+		} else {
+			tx_len = (ar->bmi.max_data_size - header);
+		}
+
+		offset = 0;
+		memcpy(&(ar->bmi.cmd_buf[offset]), &cid, sizeof(cid));
+		offset += sizeof(cid);
+		memcpy(&(ar->bmi.cmd_buf[offset]), &addr, sizeof(addr));
+		offset += sizeof(addr);
+		memcpy(&(ar->bmi.cmd_buf[offset]), &tx_len, sizeof(tx_len));
+		offset += sizeof(tx_len);
+		memcpy(&(ar->bmi.cmd_buf[offset]), src, tx_len);
+		offset += tx_len;
+
+		ret = ath6kl_hif_bmi_write(ar, ar->bmi.cmd_buf, offset);
+		if (ret) {
+			ath6kl_err("Unable to write to the device: %d\n",
+				   ret);
+			return ret;
+		}
+		len_remain -= tx_len; addr += tx_len;
+	}
+
+	return 0;
+}
+
+int ath6kl_bmi_execute(struct ath6kl *ar, u32 addr, u32 *param)
+{
+	u32 cid = BMI_EXECUTE;
+	int ret;
+	u32 offset;
+	u16 size;
+
+	if (ar->bmi.done_sent) {
+		ath6kl_err("bmi done sent already, cmd %d disallowed\n", cid);
+		return -EACCES;
+	}
+
+	size = sizeof(cid) + sizeof(addr) + sizeof(param);
+	if (size > ar->bmi.max_cmd_size) {
+		WARN_ON(1);
+		return -EINVAL;
+	}
+	memset(ar->bmi.cmd_buf, 0, size);
+
+	ath6kl_dbg(ATH6KL_DBG_BMI, "bmi execute: addr: 0x%x, param: %d)\n",
+		   addr, *param);
+
+	offset = 0;
+	memcpy(&(ar->bmi.cmd_buf[offset]), &cid, sizeof(cid));
+	offset += sizeof(cid);
+	memcpy(&(ar->bmi.cmd_buf[offset]), &addr, sizeof(addr));
+	offset += sizeof(addr);
+	memcpy(&(ar->bmi.cmd_buf[offset]), param, sizeof(*param));
+	offset += sizeof(*param);
+
+	ret = ath6kl_hif_bmi_write(ar, ar->bmi.cmd_buf, offset);
+	if (ret) {
+		ath6kl_err("Unable to write to the device: %d\n", ret);
+		return ret;
+	}
+
+	ret = ath6kl_hif_bmi_read(ar, ar->bmi.cmd_buf, sizeof(*param));
+	if (ret) {
+		ath6kl_err("Unable to read from the device: %d\n", ret);
+		return ret;
+	}
+
+	memcpy(param, ar->bmi.cmd_buf, sizeof(*param));
+
+	return 0;
+}
+
+int ath6kl_bmi_set_app_start(struct ath6kl *ar, u32 addr)
+{
+	u32 cid = BMI_SET_APP_START;
+	int ret;
+	u32 offset;
+	u16 size;
+
+	if (ar->bmi.done_sent) {
+		ath6kl_err("bmi done sent already, cmd %d disallowed\n", cid);
+		return -EACCES;
+	}
+
+	size = sizeof(cid) + sizeof(addr);
+	if (size > ar->bmi.max_cmd_size) {
+		WARN_ON(1);
+		return -EINVAL;
+	}
+	memset(ar->bmi.cmd_buf, 0, size);
+
+	ath6kl_dbg(ATH6KL_DBG_BMI, "bmi set app start: addr: 0x%x\n", addr);
+
+	offset = 0;
+	memcpy(&(ar->bmi.cmd_buf[offset]), &cid, sizeof(cid));
+	offset += sizeof(cid);
+	memcpy(&(ar->bmi.cmd_buf[offset]), &addr, sizeof(addr));
+	offset += sizeof(addr);
+
+	ret = ath6kl_hif_bmi_write(ar, ar->bmi.cmd_buf, offset);
+	if (ret) {
+		ath6kl_err("Unable to write to the device: %d\n", ret);
+		return ret;
+	}
+
+	return 0;
+}
+
+int ath6kl_bmi_reg_read(struct ath6kl *ar, u32 addr, u32 *param)
+{
+	u32 cid = BMI_READ_SOC_REGISTER;
+	int ret;
+	u32 offset;
+	u16 size;
+
+	if (ar->bmi.done_sent) {
+		ath6kl_err("bmi done sent already, cmd %d disallowed\n", cid);
+		return -EACCES;
+	}
+
+	size = sizeof(cid) + sizeof(addr);
+	if (size > ar->bmi.max_cmd_size) {
+		WARN_ON(1);
+		return -EINVAL;
+	}
+	memset(ar->bmi.cmd_buf, 0, size);
+
+	ath6kl_dbg(ATH6KL_DBG_BMI, "bmi read SOC reg: addr: 0x%x\n", addr);
+
+	offset = 0;
+	memcpy(&(ar->bmi.cmd_buf[offset]), &cid, sizeof(cid));
+	offset += sizeof(cid);
+	memcpy(&(ar->bmi.cmd_buf[offset]), &addr, sizeof(addr));
+	offset += sizeof(addr);
+
+	ret = ath6kl_hif_bmi_write(ar, ar->bmi.cmd_buf, offset);
+	if (ret) {
+		ath6kl_err("Unable to write to the device: %d\n", ret);
+		return ret;
+	}
+
+	ret = ath6kl_hif_bmi_read(ar, ar->bmi.cmd_buf, sizeof(*param));
+	if (ret) {
+		ath6kl_err("Unable to read from the device: %d\n", ret);
+		return ret;
+	}
+	memcpy(param, ar->bmi.cmd_buf, sizeof(*param));
+
+	return 0;
+}
+
+int ath6kl_bmi_reg_write(struct ath6kl *ar, u32 addr, u32 param)
+{
+	u32 cid = BMI_WRITE_SOC_REGISTER;
+	int ret;
+	u32 offset;
+	u16 size;
+
+	if (ar->bmi.done_sent) {
+		ath6kl_err("bmi done sent already, cmd %d disallowed\n", cid);
+		return -EACCES;
+	}
+
+	size = sizeof(cid) + sizeof(addr) + sizeof(param);
+	if (size > ar->bmi.max_cmd_size) {
+		WARN_ON(1);
+		return -EINVAL;
+	}
+	memset(ar->bmi.cmd_buf, 0, size);
+
+	ath6kl_dbg(ATH6KL_DBG_BMI,
+		   "bmi write SOC reg: addr: 0x%x, param: %d\n",
+		    addr, param);
+
+	offset = 0;
+	memcpy(&(ar->bmi.cmd_buf[offset]), &cid, sizeof(cid));
+	offset += sizeof(cid);
+	memcpy(&(ar->bmi.cmd_buf[offset]), &addr, sizeof(addr));
+	offset += sizeof(addr);
+	memcpy(&(ar->bmi.cmd_buf[offset]), &param, sizeof(param));
+	offset += sizeof(param);
+
+	ret = ath6kl_hif_bmi_write(ar, ar->bmi.cmd_buf, offset);
+	if (ret) {
+		ath6kl_err("Unable to write to the device: %d\n", ret);
+		return ret;
+	}
+
+	return 0;
+}
+
+int ath6kl_bmi_lz_data(struct ath6kl *ar, u8 *buf, u32 len)
+{
+	u32 cid = BMI_LZ_DATA;
+	int ret;
+	u32 offset;
+	u32 len_remain, tx_len;
+	const u32 header = sizeof(cid) + sizeof(len);
+	u16 size;
+
+	if (ar->bmi.done_sent) {
+		ath6kl_err("bmi done sent already, cmd %d disallowed\n", cid);
+		return -EACCES;
+	}
+
+	size = ar->bmi.max_data_size + header;
+	if (size > ar->bmi.max_cmd_size) {
+		WARN_ON(1);
+		return -EINVAL;
+	}
+	memset(ar->bmi.cmd_buf, 0, size);
+
+	ath6kl_dbg(ATH6KL_DBG_BMI, "bmi send LZ data: len: %d)\n",
+		   len);
+
+	len_remain = len;
+	while (len_remain) {
+		tx_len = (len_remain < (ar->bmi.max_data_size - header)) ?
+			  len_remain : (ar->bmi.max_data_size - header);
+
+		offset = 0;
+		memcpy(&(ar->bmi.cmd_buf[offset]), &cid, sizeof(cid));
+		offset += sizeof(cid);
+		memcpy(&(ar->bmi.cmd_buf[offset]), &tx_len, sizeof(tx_len));
+		offset += sizeof(tx_len);
+		memcpy(&(ar->bmi.cmd_buf[offset]), &buf[len - len_remain],
+		       tx_len);
+		offset += tx_len;
+
+		ret = ath6kl_hif_bmi_write(ar, ar->bmi.cmd_buf, offset);
+		if (ret) {
+			ath6kl_err("Unable to write to the device: %d\n",
+				   ret);
+			return ret;
+		}
+
+		len_remain -= tx_len;
+	}
+
+	return 0;
+}
+
+int ath6kl_bmi_lz_stream_start(struct ath6kl *ar, u32 addr)
+{
+	u32 cid = BMI_LZ_STREAM_START;
+	int ret;
+	u32 offset;
+	u16 size;
+
+	if (ar->bmi.done_sent) {
+		ath6kl_err("bmi done sent already, cmd %d disallowed\n", cid);
+		return -EACCES;
+	}
+
+	size = sizeof(cid) + sizeof(addr);
+	if (size > ar->bmi.max_cmd_size) {
+		WARN_ON(1);
+		return -EINVAL;
+	}
+	memset(ar->bmi.cmd_buf, 0, size);
+
+	ath6kl_dbg(ATH6KL_DBG_BMI,
+		   "bmi LZ stream start: addr: 0x%x)\n",
+		    addr);
+
+	offset = 0;
+	memcpy(&(ar->bmi.cmd_buf[offset]), &cid, sizeof(cid));
+	offset += sizeof(cid);
+	memcpy(&(ar->bmi.cmd_buf[offset]), &addr, sizeof(addr));
+	offset += sizeof(addr);
+
+	ret = ath6kl_hif_bmi_write(ar, ar->bmi.cmd_buf, offset);
+	if (ret) {
+		ath6kl_err("Unable to start LZ stream to the device: %d\n",
+			   ret);
+		return ret;
+	}
+
+	return 0;
+}
+
+int ath6kl_bmi_fast_download(struct ath6kl *ar, u32 addr, u8 *buf, u32 len)
+{
+	int ret;
+	u32 last_word = 0;
+	u32 last_word_offset = len & ~0x3;
+	u32 unaligned_bytes = len & 0x3;
+
+	ret = ath6kl_bmi_lz_stream_start(ar, addr);
+	if (ret)
+		return ret;
+
+	if (unaligned_bytes) {
+		/* copy the last word into a zero padded buffer */
+		memcpy(&last_word, &buf[last_word_offset], unaligned_bytes);
+	}
+
+	ret = ath6kl_bmi_lz_data(ar, buf, last_word_offset);
+	if (ret)
+		return ret;
+
+	if (unaligned_bytes)
+		ret = ath6kl_bmi_lz_data(ar, (u8 *)&last_word, 4);
+
+	if (!ret) {
+		/* Close compressed stream and open a new (fake) one.
+		 * This serves mainly to flush Target caches. */
+		ret = ath6kl_bmi_lz_stream_start(ar, 0x00);
+	}
+	return ret;
+}
+
+void ath6kl_bmi_reset(struct ath6kl *ar)
+{
+	ar->bmi.done_sent = false;
+}
+
+int ath6kl_bmi_init(struct ath6kl *ar)
+{
+	if (WARN_ON(ar->bmi.max_data_size == 0))
+		return -EINVAL;
+
+	/* cmd + addr + len + data_size */
+	ar->bmi.max_cmd_size = ar->bmi.max_data_size + (sizeof(u32) * 3);
+
+	ar->bmi.cmd_buf = kzalloc(ar->bmi.max_cmd_size, GFP_KERNEL);
+	if (!ar->bmi.cmd_buf)
+		return -ENOMEM;
+
+	return 0;
+}
+
+void ath6kl_bmi_cleanup(struct ath6kl *ar)
+{
+	kfree(ar->bmi.cmd_buf);
+	ar->bmi.cmd_buf = NULL;
+}