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, 283 insertions, 0 deletions

diff --git a/tools/io_uring/io_uring-cp.c b/tools/io_uring/io_uring-cp.c
new file mode 100644
index 000000000..d9bd6f5f8
--- /dev/null
+++ b/tools/io_uring/io_uring-cp.c
@@ -0,0 +1,283 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Simple test program that demonstrates a file copy through io_uring. This
+ * uses the API exposed by liburing.
+ *
+ * Copyright (C) 2018-2019 Jens Axboe
+ */
+#include <stdio.h>
+#include <fcntl.h>
+#include <string.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <assert.h>
+#include <errno.h>
+#include <inttypes.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <sys/ioctl.h>
+
+#include "liburing.h"
+
+#define QD	64
+#define BS	(32*1024)
+
+static int infd, outfd;
+
+struct io_data {
+	int read;
+	off_t first_offset, offset;
+	size_t first_len;
+	struct iovec iov;
+};
+
+static int setup_context(unsigned entries, struct io_uring *ring)
+{
+	int ret;
+
+	ret = io_uring_queue_init(entries, ring, 0);
+	if (ret < 0) {
+		fprintf(stderr, "queue_init: %s\n", strerror(-ret));
+		return -1;
+	}
+
+	return 0;
+}
+
+static int get_file_size(int fd, off_t *size)
+{
+	struct stat st;
+
+	if (fstat(fd, &st) < 0)
+		return -1;
+	if (S_ISREG(st.st_mode)) {
+		*size = st.st_size;
+		return 0;
+	} else if (S_ISBLK(st.st_mode)) {
+		unsigned long long bytes;
+
+		if (ioctl(fd, BLKGETSIZE64, &bytes) != 0)
+			return -1;
+
+		*size = bytes;
+		return 0;
+	}
+
+	return -1;
+}
+
+static void queue_prepped(struct io_uring *ring, struct io_data *data)
+{
+	struct io_uring_sqe *sqe;
+
+	sqe = io_uring_get_sqe(ring);
+	assert(sqe);
+
+	if (data->read)
+		io_uring_prep_readv(sqe, infd, &data->iov, 1, data->offset);
+	else
+		io_uring_prep_writev(sqe, outfd, &data->iov, 1, data->offset);
+
+	io_uring_sqe_set_data(sqe, data);
+}
+
+static int queue_read(struct io_uring *ring, off_t size, off_t offset)
+{
+	struct io_uring_sqe *sqe;
+	struct io_data *data;
+
+	data = malloc(size + sizeof(*data));
+	if (!data)
+		return 1;
+
+	sqe = io_uring_get_sqe(ring);
+	if (!sqe) {
+		free(data);
+		return 1;
+	}
+
+	data->read = 1;
+	data->offset = data->first_offset = offset;
+
+	data->iov.iov_base = data + 1;
+	data->iov.iov_len = size;
+	data->first_len = size;
+
+	io_uring_prep_readv(sqe, infd, &data->iov, 1, offset);
+	io_uring_sqe_set_data(sqe, data);
+	return 0;
+}
+
+static void queue_write(struct io_uring *ring, struct io_data *data)
+{
+	data->read = 0;
+	data->offset = data->first_offset;
+
+	data->iov.iov_base = data + 1;
+	data->iov.iov_len = data->first_len;
+
+	queue_prepped(ring, data);
+	io_uring_submit(ring);
+}
+
+static int copy_file(struct io_uring *ring, off_t insize)
+{
+	unsigned long reads, writes;
+	struct io_uring_cqe *cqe;
+	off_t write_left, offset;
+	int ret;
+
+	write_left = insize;
+	writes = reads = offset = 0;
+
+	while (insize || write_left) {
+		int had_reads, got_comp;
+
+		/*
+		 * Queue up as many reads as we can
+		 */
+		had_reads = reads;
+		while (insize) {
+			off_t this_size = insize;
+
+			if (reads + writes >= QD)
+				break;
+			if (this_size > BS)
+				this_size = BS;
+			else if (!this_size)
+				break;
+
+			if (queue_read(ring, this_size, offset))
+				break;
+
+			insize -= this_size;
+			offset += this_size;
+			reads++;
+		}
+
+		if (had_reads != reads) {
+			ret = io_uring_submit(ring);
+			if (ret < 0) {
+				fprintf(stderr, "io_uring_submit: %s\n", strerror(-ret));
+				break;
+			}
+		}
+
+		/*
+		 * Queue is full at this point. Find at least one completion.
+		 */
+		got_comp = 0;
+		while (write_left) {
+			struct io_data *data;
+
+			if (!got_comp) {
+				ret = io_uring_wait_cqe(ring, &cqe);
+				got_comp = 1;
+			} else {
+				ret = io_uring_peek_cqe(ring, &cqe);
+				if (ret == -EAGAIN) {
+					cqe = NULL;
+					ret = 0;
+				}
+			}
+			if (ret < 0) {
+				fprintf(stderr, "io_uring_peek_cqe: %s\n",
+							strerror(-ret));
+				return 1;
+			}
+			if (!cqe)
+				break;
+
+			data = io_uring_cqe_get_data(cqe);
+			if (cqe->res < 0) {
+				if (cqe->res == -EAGAIN) {
+					queue_prepped(ring, data);
+					io_uring_cqe_seen(ring, cqe);
+					continue;
+				}
+				fprintf(stderr, "cqe failed: %s\n",
+						strerror(-cqe->res));
+				return 1;
+			} else if (cqe->res != data->iov.iov_len) {
+				/* Short read/write, adjust and requeue */
+				data->iov.iov_base += cqe->res;
+				data->iov.iov_len -= cqe->res;
+				data->offset += cqe->res;
+				queue_prepped(ring, data);
+				io_uring_cqe_seen(ring, cqe);
+				continue;
+			}
+
+			/*
+			 * All done. if write, nothing else to do. if read,
+			 * queue up corresponding write.
+			 */
+			if (data->read) {
+				queue_write(ring, data);
+				write_left -= data->first_len;
+				reads--;
+				writes++;
+			} else {
+				free(data);
+				writes--;
+			}
+			io_uring_cqe_seen(ring, cqe);
+		}
+	}
+
+	/* wait out pending writes */
+	while (writes) {
+		struct io_data *data;
+
+		ret = io_uring_wait_cqe(ring, &cqe);
+		if (ret) {
+			fprintf(stderr, "wait_cqe=%d\n", ret);
+			return 1;
+		}
+		if (cqe->res < 0) {
+			fprintf(stderr, "write res=%d\n", cqe->res);
+			return 1;
+		}
+		data = io_uring_cqe_get_data(cqe);
+		free(data);
+		writes--;
+		io_uring_cqe_seen(ring, cqe);
+	}
+
+	return 0;
+}
+
+int main(int argc, char *argv[])
+{
+	struct io_uring ring;
+	off_t insize;
+	int ret;
+
+	if (argc < 3) {
+		printf("%s: infile outfile\n", argv[0]);
+		return 1;
+	}
+
+	infd = open(argv[1], O_RDONLY);
+	if (infd < 0) {
+		perror("open infile");
+		return 1;
+	}
+	outfd = open(argv[2], O_WRONLY | O_CREAT | O_TRUNC, 0644);
+	if (outfd < 0) {
+		perror("open outfile");
+		return 1;
+	}
+
+	if (setup_context(QD, &ring))
+		return 1;
+	if (get_file_size(infd, &insize))
+		return 1;
+
+	ret = copy_file(&ring, insize);
+
+	close(infd);
+	close(outfd);
+	io_uring_queue_exit(&ring);
+	return ret;
+}