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, 339 insertions, 0 deletions

diff --git a/arch/mips/include/asm/octeon/cvmx-ipd.h b/arch/mips/include/asm/octeon/cvmx-ipd.h
new file mode 100644
index 000000000..adab7b54c
--- /dev/null
+++ b/arch/mips/include/asm/octeon/cvmx-ipd.h
@@ -0,0 +1,339 @@
+/***********************license start***************
+ * Author: Cavium Networks
+ *
+ * Contact: support@caviumnetworks.com
+ * This file is part of the OCTEON SDK
+ *
+ * Copyright (c) 2003-2008 Cavium Networks
+ *
+ * This file is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License, Version 2, as
+ * published by the Free Software Foundation.
+ *
+ * This file is distributed in the hope that it will be useful, but
+ * AS-IS and WITHOUT ANY WARRANTY; without even the implied warranty
+ * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE, TITLE, or
+ * NONINFRINGEMENT.  See the GNU General Public License for more
+ * details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this file; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
+ * or visit http://www.gnu.org/licenses/.
+ *
+ * This file may also be available under a different license from Cavium.
+ * Contact Cavium Networks for more information
+ ***********************license end**************************************/
+
+/**
+ *
+ * Interface to the hardware Input Packet Data unit.
+ */
+
+#ifndef __CVMX_IPD_H__
+#define __CVMX_IPD_H__
+
+#include <asm/octeon/octeon-feature.h>
+
+#include <asm/octeon/cvmx-ipd-defs.h>
+#include <asm/octeon/cvmx-pip-defs.h>
+
+enum cvmx_ipd_mode {
+   CVMX_IPD_OPC_MODE_STT = 0LL,	  /* All blocks DRAM, not cached in L2 */
+   CVMX_IPD_OPC_MODE_STF = 1LL,	  /* All blocks into  L2 */
+   CVMX_IPD_OPC_MODE_STF1_STT = 2LL,   /* 1st block L2, rest DRAM */
+   CVMX_IPD_OPC_MODE_STF2_STT = 3LL    /* 1st, 2nd blocks L2, rest DRAM */
+};
+
+#ifndef CVMX_ENABLE_LEN_M8_FIX
+#define CVMX_ENABLE_LEN_M8_FIX 0
+#endif
+
+/* CSR typedefs have been moved to cvmx-csr-*.h */
+typedef union cvmx_ipd_1st_mbuff_skip cvmx_ipd_mbuff_first_skip_t;
+typedef union cvmx_ipd_1st_next_ptr_back cvmx_ipd_first_next_ptr_back_t;
+
+typedef cvmx_ipd_mbuff_first_skip_t cvmx_ipd_mbuff_not_first_skip_t;
+typedef cvmx_ipd_first_next_ptr_back_t cvmx_ipd_second_next_ptr_back_t;
+
+/**
+ * Configure IPD
+ *
+ * @mbuff_size: Packets buffer size in 8 byte words
+ * @first_mbuff_skip:
+ *		     Number of 8 byte words to skip in the first buffer
+ * @not_first_mbuff_skip:
+ *		     Number of 8 byte words to skip in each following buffer
+ * @first_back: Must be same as first_mbuff_skip / 128
+ * @second_back:
+ *		     Must be same as not_first_mbuff_skip / 128
+ * @wqe_fpa_pool:
+ *		     FPA pool to get work entries from
+ * @cache_mode:
+ * @back_pres_enable_flag:
+ *		     Enable or disable port back pressure
+ */
+static inline void cvmx_ipd_config(uint64_t mbuff_size,
+				   uint64_t first_mbuff_skip,
+				   uint64_t not_first_mbuff_skip,
+				   uint64_t first_back,
+				   uint64_t second_back,
+				   uint64_t wqe_fpa_pool,
+				   enum cvmx_ipd_mode cache_mode,
+				   uint64_t back_pres_enable_flag)
+{
+	cvmx_ipd_mbuff_first_skip_t first_skip;
+	cvmx_ipd_mbuff_not_first_skip_t not_first_skip;
+	union cvmx_ipd_packet_mbuff_size size;
+	cvmx_ipd_first_next_ptr_back_t first_back_struct;
+	cvmx_ipd_second_next_ptr_back_t second_back_struct;
+	union cvmx_ipd_wqe_fpa_queue wqe_pool;
+	union cvmx_ipd_ctl_status ipd_ctl_reg;
+
+	first_skip.u64 = 0;
+	first_skip.s.skip_sz = first_mbuff_skip;
+	cvmx_write_csr(CVMX_IPD_1ST_MBUFF_SKIP, first_skip.u64);
+
+	not_first_skip.u64 = 0;
+	not_first_skip.s.skip_sz = not_first_mbuff_skip;
+	cvmx_write_csr(CVMX_IPD_NOT_1ST_MBUFF_SKIP, not_first_skip.u64);
+
+	size.u64 = 0;
+	size.s.mb_size = mbuff_size;
+	cvmx_write_csr(CVMX_IPD_PACKET_MBUFF_SIZE, size.u64);
+
+	first_back_struct.u64 = 0;
+	first_back_struct.s.back = first_back;
+	cvmx_write_csr(CVMX_IPD_1st_NEXT_PTR_BACK, first_back_struct.u64);
+
+	second_back_struct.u64 = 0;
+	second_back_struct.s.back = second_back;
+	cvmx_write_csr(CVMX_IPD_2nd_NEXT_PTR_BACK, second_back_struct.u64);
+
+	wqe_pool.u64 = 0;
+	wqe_pool.s.wqe_pool = wqe_fpa_pool;
+	cvmx_write_csr(CVMX_IPD_WQE_FPA_QUEUE, wqe_pool.u64);
+
+	ipd_ctl_reg.u64 = cvmx_read_csr(CVMX_IPD_CTL_STATUS);
+	ipd_ctl_reg.s.opc_mode = cache_mode;
+	ipd_ctl_reg.s.pbp_en = back_pres_enable_flag;
+	cvmx_write_csr(CVMX_IPD_CTL_STATUS, ipd_ctl_reg.u64);
+
+	/* Note: the example RED code that used to be here has been moved to
+	   cvmx_helper_setup_red */
+}
+
+/**
+ * Enable IPD
+ */
+static inline void cvmx_ipd_enable(void)
+{
+	union cvmx_ipd_ctl_status ipd_reg;
+	ipd_reg.u64 = cvmx_read_csr(CVMX_IPD_CTL_STATUS);
+	if (ipd_reg.s.ipd_en) {
+		cvmx_dprintf
+		    ("Warning: Enabling IPD when IPD already enabled.\n");
+	}
+	ipd_reg.s.ipd_en = 1;
+#if  CVMX_ENABLE_LEN_M8_FIX
+	if (!OCTEON_IS_MODEL(OCTEON_CN38XX_PASS2))
+		ipd_reg.s.len_m8 = TRUE;
+#endif
+	cvmx_write_csr(CVMX_IPD_CTL_STATUS, ipd_reg.u64);
+}
+
+/**
+ * Disable IPD
+ */
+static inline void cvmx_ipd_disable(void)
+{
+	union cvmx_ipd_ctl_status ipd_reg;
+	ipd_reg.u64 = cvmx_read_csr(CVMX_IPD_CTL_STATUS);
+	ipd_reg.s.ipd_en = 0;
+	cvmx_write_csr(CVMX_IPD_CTL_STATUS, ipd_reg.u64);
+}
+
+/**
+ * Supportive function for cvmx_fpa_shutdown_pool.
+ */
+static inline void cvmx_ipd_free_ptr(void)
+{
+	/* Only CN38XXp{1,2} cannot read pointer out of the IPD */
+	if (!OCTEON_IS_MODEL(OCTEON_CN38XX_PASS1)
+	    && !OCTEON_IS_MODEL(OCTEON_CN38XX_PASS2)) {
+		int no_wptr = 0;
+		union cvmx_ipd_ptr_count ipd_ptr_count;
+		ipd_ptr_count.u64 = cvmx_read_csr(CVMX_IPD_PTR_COUNT);
+
+		/* Handle Work Queue Entry in cn56xx and cn52xx */
+		if (octeon_has_feature(OCTEON_FEATURE_NO_WPTR)) {
+			union cvmx_ipd_ctl_status ipd_ctl_status;
+			ipd_ctl_status.u64 = cvmx_read_csr(CVMX_IPD_CTL_STATUS);
+			if (ipd_ctl_status.s.no_wptr)
+				no_wptr = 1;
+		}
+
+		/* Free the prefetched WQE */
+		if (ipd_ptr_count.s.wqev_cnt) {
+			union cvmx_ipd_wqe_ptr_valid ipd_wqe_ptr_valid;
+			ipd_wqe_ptr_valid.u64 =
+			    cvmx_read_csr(CVMX_IPD_WQE_PTR_VALID);
+			if (no_wptr)
+				cvmx_fpa_free(cvmx_phys_to_ptr
+					      ((uint64_t) ipd_wqe_ptr_valid.s.
+					       ptr << 7), CVMX_FPA_PACKET_POOL,
+					      0);
+			else
+				cvmx_fpa_free(cvmx_phys_to_ptr
+					      ((uint64_t) ipd_wqe_ptr_valid.s.
+					       ptr << 7), CVMX_FPA_WQE_POOL, 0);
+		}
+
+		/* Free all WQE in the fifo */
+		if (ipd_ptr_count.s.wqe_pcnt) {
+			int i;
+			union cvmx_ipd_pwp_ptr_fifo_ctl ipd_pwp_ptr_fifo_ctl;
+			ipd_pwp_ptr_fifo_ctl.u64 =
+			    cvmx_read_csr(CVMX_IPD_PWP_PTR_FIFO_CTL);
+			for (i = 0; i < ipd_ptr_count.s.wqe_pcnt; i++) {
+				ipd_pwp_ptr_fifo_ctl.s.cena = 0;
+				ipd_pwp_ptr_fifo_ctl.s.raddr =
+				    ipd_pwp_ptr_fifo_ctl.s.max_cnts +
+				    (ipd_pwp_ptr_fifo_ctl.s.wraddr +
+				     i) % ipd_pwp_ptr_fifo_ctl.s.max_cnts;
+				cvmx_write_csr(CVMX_IPD_PWP_PTR_FIFO_CTL,
+					       ipd_pwp_ptr_fifo_ctl.u64);
+				ipd_pwp_ptr_fifo_ctl.u64 =
+				    cvmx_read_csr(CVMX_IPD_PWP_PTR_FIFO_CTL);
+				if (no_wptr)
+					cvmx_fpa_free(cvmx_phys_to_ptr
+						      ((uint64_t)
+						       ipd_pwp_ptr_fifo_ctl.s.
+						       ptr << 7),
+						      CVMX_FPA_PACKET_POOL, 0);
+				else
+					cvmx_fpa_free(cvmx_phys_to_ptr
+						      ((uint64_t)
+						       ipd_pwp_ptr_fifo_ctl.s.
+						       ptr << 7),
+						      CVMX_FPA_WQE_POOL, 0);
+			}
+			ipd_pwp_ptr_fifo_ctl.s.cena = 1;
+			cvmx_write_csr(CVMX_IPD_PWP_PTR_FIFO_CTL,
+				       ipd_pwp_ptr_fifo_ctl.u64);
+		}
+
+		/* Free the prefetched packet */
+		if (ipd_ptr_count.s.pktv_cnt) {
+			union cvmx_ipd_pkt_ptr_valid ipd_pkt_ptr_valid;
+			ipd_pkt_ptr_valid.u64 =
+			    cvmx_read_csr(CVMX_IPD_PKT_PTR_VALID);
+			cvmx_fpa_free(cvmx_phys_to_ptr
+				      (ipd_pkt_ptr_valid.s.ptr << 7),
+				      CVMX_FPA_PACKET_POOL, 0);
+		}
+
+		/* Free the per port prefetched packets */
+		if (1) {
+			int i;
+			union cvmx_ipd_prc_port_ptr_fifo_ctl
+			    ipd_prc_port_ptr_fifo_ctl;
+			ipd_prc_port_ptr_fifo_ctl.u64 =
+			    cvmx_read_csr(CVMX_IPD_PRC_PORT_PTR_FIFO_CTL);
+
+			for (i = 0; i < ipd_prc_port_ptr_fifo_ctl.s.max_pkt;
+			     i++) {
+				ipd_prc_port_ptr_fifo_ctl.s.cena = 0;
+				ipd_prc_port_ptr_fifo_ctl.s.raddr =
+				    i % ipd_prc_port_ptr_fifo_ctl.s.max_pkt;
+				cvmx_write_csr(CVMX_IPD_PRC_PORT_PTR_FIFO_CTL,
+					       ipd_prc_port_ptr_fifo_ctl.u64);
+				ipd_prc_port_ptr_fifo_ctl.u64 =
+				    cvmx_read_csr
+				    (CVMX_IPD_PRC_PORT_PTR_FIFO_CTL);
+				cvmx_fpa_free(cvmx_phys_to_ptr
+					      ((uint64_t)
+					       ipd_prc_port_ptr_fifo_ctl.s.
+					       ptr << 7), CVMX_FPA_PACKET_POOL,
+					      0);
+			}
+			ipd_prc_port_ptr_fifo_ctl.s.cena = 1;
+			cvmx_write_csr(CVMX_IPD_PRC_PORT_PTR_FIFO_CTL,
+				       ipd_prc_port_ptr_fifo_ctl.u64);
+		}
+
+		/* Free all packets in the holding fifo */
+		if (ipd_ptr_count.s.pfif_cnt) {
+			int i;
+			union cvmx_ipd_prc_hold_ptr_fifo_ctl
+			    ipd_prc_hold_ptr_fifo_ctl;
+
+			ipd_prc_hold_ptr_fifo_ctl.u64 =
+			    cvmx_read_csr(CVMX_IPD_PRC_HOLD_PTR_FIFO_CTL);
+
+			for (i = 0; i < ipd_ptr_count.s.pfif_cnt; i++) {
+				ipd_prc_hold_ptr_fifo_ctl.s.cena = 0;
+				ipd_prc_hold_ptr_fifo_ctl.s.raddr =
+				    (ipd_prc_hold_ptr_fifo_ctl.s.praddr +
+				     i) % ipd_prc_hold_ptr_fifo_ctl.s.max_pkt;
+				cvmx_write_csr(CVMX_IPD_PRC_HOLD_PTR_FIFO_CTL,
+					       ipd_prc_hold_ptr_fifo_ctl.u64);
+				ipd_prc_hold_ptr_fifo_ctl.u64 =
+				    cvmx_read_csr
+				    (CVMX_IPD_PRC_HOLD_PTR_FIFO_CTL);
+				cvmx_fpa_free(cvmx_phys_to_ptr
+					      ((uint64_t)
+					       ipd_prc_hold_ptr_fifo_ctl.s.
+					       ptr << 7), CVMX_FPA_PACKET_POOL,
+					      0);
+			}
+			ipd_prc_hold_ptr_fifo_ctl.s.cena = 1;
+			cvmx_write_csr(CVMX_IPD_PRC_HOLD_PTR_FIFO_CTL,
+				       ipd_prc_hold_ptr_fifo_ctl.u64);
+		}
+
+		/* Free all packets in the fifo */
+		if (ipd_ptr_count.s.pkt_pcnt) {
+			int i;
+			union cvmx_ipd_pwp_ptr_fifo_ctl ipd_pwp_ptr_fifo_ctl;
+			ipd_pwp_ptr_fifo_ctl.u64 =
+			    cvmx_read_csr(CVMX_IPD_PWP_PTR_FIFO_CTL);
+
+			for (i = 0; i < ipd_ptr_count.s.pkt_pcnt; i++) {
+				ipd_pwp_ptr_fifo_ctl.s.cena = 0;
+				ipd_pwp_ptr_fifo_ctl.s.raddr =
+				    (ipd_pwp_ptr_fifo_ctl.s.praddr +
+				     i) % ipd_pwp_ptr_fifo_ctl.s.max_cnts;
+				cvmx_write_csr(CVMX_IPD_PWP_PTR_FIFO_CTL,
+					       ipd_pwp_ptr_fifo_ctl.u64);
+				ipd_pwp_ptr_fifo_ctl.u64 =
+				    cvmx_read_csr(CVMX_IPD_PWP_PTR_FIFO_CTL);
+				cvmx_fpa_free(cvmx_phys_to_ptr
+					      ((uint64_t) ipd_pwp_ptr_fifo_ctl.
+					       s.ptr << 7),
+					      CVMX_FPA_PACKET_POOL, 0);
+			}
+			ipd_pwp_ptr_fifo_ctl.s.cena = 1;
+			cvmx_write_csr(CVMX_IPD_PWP_PTR_FIFO_CTL,
+				       ipd_pwp_ptr_fifo_ctl.u64);
+		}
+
+		/* Reset the IPD to get all buffers out of it */
+		{
+			union cvmx_ipd_ctl_status ipd_ctl_status;
+			ipd_ctl_status.u64 = cvmx_read_csr(CVMX_IPD_CTL_STATUS);
+			ipd_ctl_status.s.reset = 1;
+			cvmx_write_csr(CVMX_IPD_CTL_STATUS, ipd_ctl_status.u64);
+		}
+
+		/* Reset the PIP */
+		{
+			union cvmx_pip_sft_rst pip_sft_rst;
+			pip_sft_rst.u64 = cvmx_read_csr(CVMX_PIP_SFT_RST);
+			pip_sft_rst.s.rst = 1;
+			cvmx_write_csr(CVMX_PIP_SFT_RST, pip_sft_rst.u64);
+		}
+	}
+}
+
+#endif /*  __CVMX_IPD_H__ */