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, 645 insertions, 0 deletions

diff --git a/tools/testing/selftests/bpf/xsk.c b/tools/testing/selftests/bpf/xsk.c
new file mode 100644
index 000000000..687d83e70
--- /dev/null
+++ b/tools/testing/selftests/bpf/xsk.c
@@ -0,0 +1,645 @@
+// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause)
+
+/*
+ * AF_XDP user-space access library.
+ *
+ * Copyright(c) 2018 - 2019 Intel Corporation.
+ *
+ * Author(s): Magnus Karlsson <magnus.karlsson@intel.com>
+ */
+
+#include <errno.h>
+#include <stdlib.h>
+#include <string.h>
+#include <unistd.h>
+#include <arpa/inet.h>
+#include <asm/barrier.h>
+#include <linux/compiler.h>
+#include <linux/ethtool.h>
+#include <linux/filter.h>
+#include <linux/if_ether.h>
+#include <linux/if_packet.h>
+#include <linux/if_xdp.h>
+#include <linux/kernel.h>
+#include <linux/list.h>
+#include <linux/sockios.h>
+#include <net/if.h>
+#include <sys/ioctl.h>
+#include <sys/mman.h>
+#include <sys/socket.h>
+#include <sys/types.h>
+#include <linux/if_link.h>
+
+#include <bpf/bpf.h>
+#include <bpf/libbpf.h>
+#include "xsk.h"
+#include "bpf_util.h"
+
+#ifndef SOL_XDP
+ #define SOL_XDP 283
+#endif
+
+#ifndef AF_XDP
+ #define AF_XDP 44
+#endif
+
+#ifndef PF_XDP
+ #define PF_XDP AF_XDP
+#endif
+
+#define pr_warn(fmt, ...) fprintf(stderr, fmt, ##__VA_ARGS__)
+
+#define XSKMAP_SIZE 1
+
+struct xsk_umem {
+	struct xsk_ring_prod *fill_save;
+	struct xsk_ring_cons *comp_save;
+	char *umem_area;
+	struct xsk_umem_config config;
+	int fd;
+	int refcount;
+	struct list_head ctx_list;
+	bool rx_ring_setup_done;
+	bool tx_ring_setup_done;
+};
+
+struct xsk_ctx {
+	struct xsk_ring_prod *fill;
+	struct xsk_ring_cons *comp;
+	__u32 queue_id;
+	struct xsk_umem *umem;
+	int refcount;
+	int ifindex;
+	struct list_head list;
+};
+
+struct xsk_socket {
+	struct xsk_ring_cons *rx;
+	struct xsk_ring_prod *tx;
+	struct xsk_ctx *ctx;
+	struct xsk_socket_config config;
+	int fd;
+};
+
+int xsk_umem__fd(const struct xsk_umem *umem)
+{
+	return umem ? umem->fd : -EINVAL;
+}
+
+int xsk_socket__fd(const struct xsk_socket *xsk)
+{
+	return xsk ? xsk->fd : -EINVAL;
+}
+
+static bool xsk_page_aligned(void *buffer)
+{
+	unsigned long addr = (unsigned long)buffer;
+
+	return !(addr & (getpagesize() - 1));
+}
+
+static void xsk_set_umem_config(struct xsk_umem_config *cfg,
+				const struct xsk_umem_config *usr_cfg)
+{
+	if (!usr_cfg) {
+		cfg->fill_size = XSK_RING_PROD__DEFAULT_NUM_DESCS;
+		cfg->comp_size = XSK_RING_CONS__DEFAULT_NUM_DESCS;
+		cfg->frame_size = XSK_UMEM__DEFAULT_FRAME_SIZE;
+		cfg->frame_headroom = XSK_UMEM__DEFAULT_FRAME_HEADROOM;
+		cfg->flags = XSK_UMEM__DEFAULT_FLAGS;
+		return;
+	}
+
+	cfg->fill_size = usr_cfg->fill_size;
+	cfg->comp_size = usr_cfg->comp_size;
+	cfg->frame_size = usr_cfg->frame_size;
+	cfg->frame_headroom = usr_cfg->frame_headroom;
+	cfg->flags = usr_cfg->flags;
+}
+
+static int xsk_set_xdp_socket_config(struct xsk_socket_config *cfg,
+				     const struct xsk_socket_config *usr_cfg)
+{
+	if (!usr_cfg) {
+		cfg->rx_size = XSK_RING_CONS__DEFAULT_NUM_DESCS;
+		cfg->tx_size = XSK_RING_PROD__DEFAULT_NUM_DESCS;
+		cfg->bind_flags = 0;
+		return 0;
+	}
+
+	cfg->rx_size = usr_cfg->rx_size;
+	cfg->tx_size = usr_cfg->tx_size;
+	cfg->bind_flags = usr_cfg->bind_flags;
+
+	return 0;
+}
+
+static int xsk_get_mmap_offsets(int fd, struct xdp_mmap_offsets *off)
+{
+	socklen_t optlen;
+	int err;
+
+	optlen = sizeof(*off);
+	err = getsockopt(fd, SOL_XDP, XDP_MMAP_OFFSETS, off, &optlen);
+	if (err)
+		return err;
+
+	if (optlen == sizeof(*off))
+		return 0;
+
+	return -EINVAL;
+}
+
+static int xsk_create_umem_rings(struct xsk_umem *umem, int fd,
+				 struct xsk_ring_prod *fill,
+				 struct xsk_ring_cons *comp)
+{
+	struct xdp_mmap_offsets off;
+	void *map;
+	int err;
+
+	err = setsockopt(fd, SOL_XDP, XDP_UMEM_FILL_RING,
+			 &umem->config.fill_size,
+			 sizeof(umem->config.fill_size));
+	if (err)
+		return -errno;
+
+	err = setsockopt(fd, SOL_XDP, XDP_UMEM_COMPLETION_RING,
+			 &umem->config.comp_size,
+			 sizeof(umem->config.comp_size));
+	if (err)
+		return -errno;
+
+	err = xsk_get_mmap_offsets(fd, &off);
+	if (err)
+		return -errno;
+
+	map = mmap(NULL, off.fr.desc + umem->config.fill_size * sizeof(__u64),
+		   PROT_READ | PROT_WRITE, MAP_SHARED | MAP_POPULATE, fd,
+		   XDP_UMEM_PGOFF_FILL_RING);
+	if (map == MAP_FAILED)
+		return -errno;
+
+	fill->mask = umem->config.fill_size - 1;
+	fill->size = umem->config.fill_size;
+	fill->producer = map + off.fr.producer;
+	fill->consumer = map + off.fr.consumer;
+	fill->flags = map + off.fr.flags;
+	fill->ring = map + off.fr.desc;
+	fill->cached_cons = umem->config.fill_size;
+
+	map = mmap(NULL, off.cr.desc + umem->config.comp_size * sizeof(__u64),
+		   PROT_READ | PROT_WRITE, MAP_SHARED | MAP_POPULATE, fd,
+		   XDP_UMEM_PGOFF_COMPLETION_RING);
+	if (map == MAP_FAILED) {
+		err = -errno;
+		goto out_mmap;
+	}
+
+	comp->mask = umem->config.comp_size - 1;
+	comp->size = umem->config.comp_size;
+	comp->producer = map + off.cr.producer;
+	comp->consumer = map + off.cr.consumer;
+	comp->flags = map + off.cr.flags;
+	comp->ring = map + off.cr.desc;
+
+	return 0;
+
+out_mmap:
+	munmap(map, off.fr.desc + umem->config.fill_size * sizeof(__u64));
+	return err;
+}
+
+int xsk_umem__create(struct xsk_umem **umem_ptr, void *umem_area,
+		     __u64 size, struct xsk_ring_prod *fill,
+		     struct xsk_ring_cons *comp,
+		     const struct xsk_umem_config *usr_config)
+{
+	struct xdp_umem_reg mr;
+	struct xsk_umem *umem;
+	int err;
+
+	if (!umem_area || !umem_ptr || !fill || !comp)
+		return -EFAULT;
+	if (!size && !xsk_page_aligned(umem_area))
+		return -EINVAL;
+
+	umem = calloc(1, sizeof(*umem));
+	if (!umem)
+		return -ENOMEM;
+
+	umem->fd = socket(AF_XDP, SOCK_RAW | SOCK_CLOEXEC, 0);
+	if (umem->fd < 0) {
+		err = -errno;
+		goto out_umem_alloc;
+	}
+
+	umem->umem_area = umem_area;
+	INIT_LIST_HEAD(&umem->ctx_list);
+	xsk_set_umem_config(&umem->config, usr_config);
+
+	memset(&mr, 0, sizeof(mr));
+	mr.addr = (uintptr_t)umem_area;
+	mr.len = size;
+	mr.chunk_size = umem->config.frame_size;
+	mr.headroom = umem->config.frame_headroom;
+	mr.flags = umem->config.flags;
+
+	err = setsockopt(umem->fd, SOL_XDP, XDP_UMEM_REG, &mr, sizeof(mr));
+	if (err) {
+		err = -errno;
+		goto out_socket;
+	}
+
+	err = xsk_create_umem_rings(umem, umem->fd, fill, comp);
+	if (err)
+		goto out_socket;
+
+	umem->fill_save = fill;
+	umem->comp_save = comp;
+	*umem_ptr = umem;
+	return 0;
+
+out_socket:
+	close(umem->fd);
+out_umem_alloc:
+	free(umem);
+	return err;
+}
+
+bool xsk_is_in_mode(u32 ifindex, int mode)
+{
+	LIBBPF_OPTS(bpf_xdp_query_opts, opts);
+	int ret;
+
+	ret = bpf_xdp_query(ifindex, mode, &opts);
+	if (ret) {
+		printf("XDP mode query returned error %s\n", strerror(errno));
+		return false;
+	}
+
+	if (mode == XDP_FLAGS_DRV_MODE)
+		return opts.attach_mode == XDP_ATTACHED_DRV;
+	else if (mode == XDP_FLAGS_SKB_MODE)
+		return opts.attach_mode == XDP_ATTACHED_SKB;
+
+	return false;
+}
+
+int xsk_attach_xdp_program(struct bpf_program *prog, int ifindex, u32 xdp_flags)
+{
+	int prog_fd;
+
+	prog_fd = bpf_program__fd(prog);
+	return bpf_xdp_attach(ifindex, prog_fd, xdp_flags, NULL);
+}
+
+void xsk_detach_xdp_program(int ifindex, u32 xdp_flags)
+{
+	bpf_xdp_detach(ifindex, xdp_flags, NULL);
+}
+
+void xsk_clear_xskmap(struct bpf_map *map)
+{
+	u32 index = 0;
+	int map_fd;
+
+	map_fd = bpf_map__fd(map);
+	bpf_map_delete_elem(map_fd, &index);
+}
+
+int xsk_update_xskmap(struct bpf_map *map, struct xsk_socket *xsk)
+{
+	int map_fd, sock_fd;
+	u32 index = 0;
+
+	map_fd = bpf_map__fd(map);
+	sock_fd = xsk_socket__fd(xsk);
+
+	return bpf_map_update_elem(map_fd, &index, &sock_fd, 0);
+}
+
+static struct xsk_ctx *xsk_get_ctx(struct xsk_umem *umem, int ifindex,
+				   __u32 queue_id)
+{
+	struct xsk_ctx *ctx;
+
+	if (list_empty(&umem->ctx_list))
+		return NULL;
+
+	list_for_each_entry(ctx, &umem->ctx_list, list) {
+		if (ctx->ifindex == ifindex && ctx->queue_id == queue_id) {
+			ctx->refcount++;
+			return ctx;
+		}
+	}
+
+	return NULL;
+}
+
+static void xsk_put_ctx(struct xsk_ctx *ctx, bool unmap)
+{
+	struct xsk_umem *umem = ctx->umem;
+	struct xdp_mmap_offsets off;
+	int err;
+
+	if (--ctx->refcount)
+		return;
+
+	if (!unmap)
+		goto out_free;
+
+	err = xsk_get_mmap_offsets(umem->fd, &off);
+	if (err)
+		goto out_free;
+
+	munmap(ctx->fill->ring - off.fr.desc, off.fr.desc + umem->config.fill_size *
+	       sizeof(__u64));
+	munmap(ctx->comp->ring - off.cr.desc, off.cr.desc + umem->config.comp_size *
+	       sizeof(__u64));
+
+out_free:
+	list_del(&ctx->list);
+	free(ctx);
+}
+
+static struct xsk_ctx *xsk_create_ctx(struct xsk_socket *xsk,
+				      struct xsk_umem *umem, int ifindex,
+				      __u32 queue_id,
+				      struct xsk_ring_prod *fill,
+				      struct xsk_ring_cons *comp)
+{
+	struct xsk_ctx *ctx;
+	int err;
+
+	ctx = calloc(1, sizeof(*ctx));
+	if (!ctx)
+		return NULL;
+
+	if (!umem->fill_save) {
+		err = xsk_create_umem_rings(umem, xsk->fd, fill, comp);
+		if (err) {
+			free(ctx);
+			return NULL;
+		}
+	} else if (umem->fill_save != fill || umem->comp_save != comp) {
+		/* Copy over rings to new structs. */
+		memcpy(fill, umem->fill_save, sizeof(*fill));
+		memcpy(comp, umem->comp_save, sizeof(*comp));
+	}
+
+	ctx->ifindex = ifindex;
+	ctx->refcount = 1;
+	ctx->umem = umem;
+	ctx->queue_id = queue_id;
+
+	ctx->fill = fill;
+	ctx->comp = comp;
+	list_add(&ctx->list, &umem->ctx_list);
+	return ctx;
+}
+
+int xsk_socket__create_shared(struct xsk_socket **xsk_ptr,
+			      int ifindex,
+			      __u32 queue_id, struct xsk_umem *umem,
+			      struct xsk_ring_cons *rx,
+			      struct xsk_ring_prod *tx,
+			      struct xsk_ring_prod *fill,
+			      struct xsk_ring_cons *comp,
+			      const struct xsk_socket_config *usr_config)
+{
+	bool unmap, rx_setup_done = false, tx_setup_done = false;
+	void *rx_map = NULL, *tx_map = NULL;
+	struct sockaddr_xdp sxdp = {};
+	struct xdp_mmap_offsets off;
+	struct xsk_socket *xsk;
+	struct xsk_ctx *ctx;
+	int err;
+
+	if (!umem || !xsk_ptr || !(rx || tx))
+		return -EFAULT;
+
+	unmap = umem->fill_save != fill;
+
+	xsk = calloc(1, sizeof(*xsk));
+	if (!xsk)
+		return -ENOMEM;
+
+	err = xsk_set_xdp_socket_config(&xsk->config, usr_config);
+	if (err)
+		goto out_xsk_alloc;
+
+	if (umem->refcount++ > 0) {
+		xsk->fd = socket(AF_XDP, SOCK_RAW | SOCK_CLOEXEC, 0);
+		if (xsk->fd < 0) {
+			err = -errno;
+			goto out_xsk_alloc;
+		}
+	} else {
+		xsk->fd = umem->fd;
+		rx_setup_done = umem->rx_ring_setup_done;
+		tx_setup_done = umem->tx_ring_setup_done;
+	}
+
+	ctx = xsk_get_ctx(umem, ifindex, queue_id);
+	if (!ctx) {
+		if (!fill || !comp) {
+			err = -EFAULT;
+			goto out_socket;
+		}
+
+		ctx = xsk_create_ctx(xsk, umem, ifindex, queue_id, fill, comp);
+		if (!ctx) {
+			err = -ENOMEM;
+			goto out_socket;
+		}
+	}
+	xsk->ctx = ctx;
+
+	if (rx && !rx_setup_done) {
+		err = setsockopt(xsk->fd, SOL_XDP, XDP_RX_RING,
+				 &xsk->config.rx_size,
+				 sizeof(xsk->config.rx_size));
+		if (err) {
+			err = -errno;
+			goto out_put_ctx;
+		}
+		if (xsk->fd == umem->fd)
+			umem->rx_ring_setup_done = true;
+	}
+	if (tx && !tx_setup_done) {
+		err = setsockopt(xsk->fd, SOL_XDP, XDP_TX_RING,
+				 &xsk->config.tx_size,
+				 sizeof(xsk->config.tx_size));
+		if (err) {
+			err = -errno;
+			goto out_put_ctx;
+		}
+		if (xsk->fd == umem->fd)
+			umem->tx_ring_setup_done = true;
+	}
+
+	err = xsk_get_mmap_offsets(xsk->fd, &off);
+	if (err) {
+		err = -errno;
+		goto out_put_ctx;
+	}
+
+	if (rx) {
+		rx_map = mmap(NULL, off.rx.desc +
+			      xsk->config.rx_size * sizeof(struct xdp_desc),
+			      PROT_READ | PROT_WRITE, MAP_SHARED | MAP_POPULATE,
+			      xsk->fd, XDP_PGOFF_RX_RING);
+		if (rx_map == MAP_FAILED) {
+			err = -errno;
+			goto out_put_ctx;
+		}
+
+		rx->mask = xsk->config.rx_size - 1;
+		rx->size = xsk->config.rx_size;
+		rx->producer = rx_map + off.rx.producer;
+		rx->consumer = rx_map + off.rx.consumer;
+		rx->flags = rx_map + off.rx.flags;
+		rx->ring = rx_map + off.rx.desc;
+		rx->cached_prod = *rx->producer;
+		rx->cached_cons = *rx->consumer;
+	}
+	xsk->rx = rx;
+
+	if (tx) {
+		tx_map = mmap(NULL, off.tx.desc +
+			      xsk->config.tx_size * sizeof(struct xdp_desc),
+			      PROT_READ | PROT_WRITE, MAP_SHARED | MAP_POPULATE,
+			      xsk->fd, XDP_PGOFF_TX_RING);
+		if (tx_map == MAP_FAILED) {
+			err = -errno;
+			goto out_mmap_rx;
+		}
+
+		tx->mask = xsk->config.tx_size - 1;
+		tx->size = xsk->config.tx_size;
+		tx->producer = tx_map + off.tx.producer;
+		tx->consumer = tx_map + off.tx.consumer;
+		tx->flags = tx_map + off.tx.flags;
+		tx->ring = tx_map + off.tx.desc;
+		tx->cached_prod = *tx->producer;
+		/* cached_cons is r->size bigger than the real consumer pointer
+		 * See xsk_prod_nb_free
+		 */
+		tx->cached_cons = *tx->consumer + xsk->config.tx_size;
+	}
+	xsk->tx = tx;
+
+	sxdp.sxdp_family = PF_XDP;
+	sxdp.sxdp_ifindex = ctx->ifindex;
+	sxdp.sxdp_queue_id = ctx->queue_id;
+	if (umem->refcount > 1) {
+		sxdp.sxdp_flags |= XDP_SHARED_UMEM;
+		sxdp.sxdp_shared_umem_fd = umem->fd;
+	} else {
+		sxdp.sxdp_flags = xsk->config.bind_flags;
+	}
+
+	err = bind(xsk->fd, (struct sockaddr *)&sxdp, sizeof(sxdp));
+	if (err) {
+		err = -errno;
+		goto out_mmap_tx;
+	}
+
+	*xsk_ptr = xsk;
+	umem->fill_save = NULL;
+	umem->comp_save = NULL;
+	return 0;
+
+out_mmap_tx:
+	if (tx)
+		munmap(tx_map, off.tx.desc +
+		       xsk->config.tx_size * sizeof(struct xdp_desc));
+out_mmap_rx:
+	if (rx)
+		munmap(rx_map, off.rx.desc +
+		       xsk->config.rx_size * sizeof(struct xdp_desc));
+out_put_ctx:
+	xsk_put_ctx(ctx, unmap);
+out_socket:
+	if (--umem->refcount)
+		close(xsk->fd);
+out_xsk_alloc:
+	free(xsk);
+	return err;
+}
+
+int xsk_socket__create(struct xsk_socket **xsk_ptr, int ifindex,
+		       __u32 queue_id, struct xsk_umem *umem,
+		       struct xsk_ring_cons *rx, struct xsk_ring_prod *tx,
+		       const struct xsk_socket_config *usr_config)
+{
+	if (!umem)
+		return -EFAULT;
+
+	return xsk_socket__create_shared(xsk_ptr, ifindex, queue_id, umem,
+					 rx, tx, umem->fill_save,
+					 umem->comp_save, usr_config);
+}
+
+int xsk_umem__delete(struct xsk_umem *umem)
+{
+	struct xdp_mmap_offsets off;
+	int err;
+
+	if (!umem)
+		return 0;
+
+	if (umem->refcount)
+		return -EBUSY;
+
+	err = xsk_get_mmap_offsets(umem->fd, &off);
+	if (!err && umem->fill_save && umem->comp_save) {
+		munmap(umem->fill_save->ring - off.fr.desc,
+		       off.fr.desc + umem->config.fill_size * sizeof(__u64));
+		munmap(umem->comp_save->ring - off.cr.desc,
+		       off.cr.desc + umem->config.comp_size * sizeof(__u64));
+	}
+
+	close(umem->fd);
+	free(umem);
+
+	return 0;
+}
+
+void xsk_socket__delete(struct xsk_socket *xsk)
+{
+	size_t desc_sz = sizeof(struct xdp_desc);
+	struct xdp_mmap_offsets off;
+	struct xsk_umem *umem;
+	struct xsk_ctx *ctx;
+	int err;
+
+	if (!xsk)
+		return;
+
+	ctx = xsk->ctx;
+	umem = ctx->umem;
+
+	xsk_put_ctx(ctx, true);
+
+	err = xsk_get_mmap_offsets(xsk->fd, &off);
+	if (!err) {
+		if (xsk->rx) {
+			munmap(xsk->rx->ring - off.rx.desc,
+			       off.rx.desc + xsk->config.rx_size * desc_sz);
+		}
+		if (xsk->tx) {
+			munmap(xsk->tx->ring - off.tx.desc,
+			       off.tx.desc + xsk->config.tx_size * desc_sz);
+		}
+	}
+
+	umem->refcount--;
+	/* Do not close an fd that also has an associated umem connected
+	 * to it.
+	 */
+	if (xsk->fd != umem->fd)
+		close(xsk->fd);
+	free(xsk);
+}