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, 397 insertions, 0 deletions

diff --git a/drivers/md/dm-delay.c b/drivers/md/dm-delay.c
new file mode 100644
index 000000000..869afef56
--- /dev/null
+++ b/drivers/md/dm-delay.c
@@ -0,0 +1,397 @@
+/*
+ * Copyright (C) 2005-2007 Red Hat GmbH
+ *
+ * A target that delays reads and/or writes and can send
+ * them to different devices.
+ *
+ * This file is released under the GPL.
+ */
+
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/blkdev.h>
+#include <linux/bio.h>
+#include <linux/slab.h>
+
+#include <linux/device-mapper.h>
+
+#define DM_MSG_PREFIX "delay"
+
+struct delay_class {
+	struct dm_dev *dev;
+	sector_t start;
+	unsigned delay;
+	unsigned ops;
+};
+
+struct delay_c {
+	struct timer_list delay_timer;
+	struct mutex timer_lock;
+	struct workqueue_struct *kdelayd_wq;
+	struct work_struct flush_expired_bios;
+	struct list_head delayed_bios;
+	atomic_t may_delay;
+
+	struct delay_class read;
+	struct delay_class write;
+	struct delay_class flush;
+
+	int argc;
+};
+
+struct dm_delay_info {
+	struct delay_c *context;
+	struct delay_class *class;
+	struct list_head list;
+	unsigned long expires;
+};
+
+static DEFINE_MUTEX(delayed_bios_lock);
+
+static void handle_delayed_timer(struct timer_list *t)
+{
+	struct delay_c *dc = from_timer(dc, t, delay_timer);
+
+	queue_work(dc->kdelayd_wq, &dc->flush_expired_bios);
+}
+
+static void queue_timeout(struct delay_c *dc, unsigned long expires)
+{
+	mutex_lock(&dc->timer_lock);
+
+	if (!timer_pending(&dc->delay_timer) || expires < dc->delay_timer.expires)
+		mod_timer(&dc->delay_timer, expires);
+
+	mutex_unlock(&dc->timer_lock);
+}
+
+static void flush_bios(struct bio *bio)
+{
+	struct bio *n;
+
+	while (bio) {
+		n = bio->bi_next;
+		bio->bi_next = NULL;
+		dm_submit_bio_remap(bio, NULL);
+		bio = n;
+	}
+}
+
+static struct bio *flush_delayed_bios(struct delay_c *dc, int flush_all)
+{
+	struct dm_delay_info *delayed, *next;
+	unsigned long next_expires = 0;
+	unsigned long start_timer = 0;
+	struct bio_list flush_bios = { };
+
+	mutex_lock(&delayed_bios_lock);
+	list_for_each_entry_safe(delayed, next, &dc->delayed_bios, list) {
+		if (flush_all || time_after_eq(jiffies, delayed->expires)) {
+			struct bio *bio = dm_bio_from_per_bio_data(delayed,
+						sizeof(struct dm_delay_info));
+			list_del(&delayed->list);
+			bio_list_add(&flush_bios, bio);
+			delayed->class->ops--;
+			continue;
+		}
+
+		if (!start_timer) {
+			start_timer = 1;
+			next_expires = delayed->expires;
+		} else
+			next_expires = min(next_expires, delayed->expires);
+	}
+	mutex_unlock(&delayed_bios_lock);
+
+	if (start_timer)
+		queue_timeout(dc, next_expires);
+
+	return bio_list_get(&flush_bios);
+}
+
+static void flush_expired_bios(struct work_struct *work)
+{
+	struct delay_c *dc;
+
+	dc = container_of(work, struct delay_c, flush_expired_bios);
+	flush_bios(flush_delayed_bios(dc, 0));
+}
+
+static void delay_dtr(struct dm_target *ti)
+{
+	struct delay_c *dc = ti->private;
+
+	if (dc->kdelayd_wq)
+		destroy_workqueue(dc->kdelayd_wq);
+
+	if (dc->read.dev)
+		dm_put_device(ti, dc->read.dev);
+	if (dc->write.dev)
+		dm_put_device(ti, dc->write.dev);
+	if (dc->flush.dev)
+		dm_put_device(ti, dc->flush.dev);
+
+	mutex_destroy(&dc->timer_lock);
+
+	kfree(dc);
+}
+
+static int delay_class_ctr(struct dm_target *ti, struct delay_class *c, char **argv)
+{
+	int ret;
+	unsigned long long tmpll;
+	char dummy;
+
+	if (sscanf(argv[1], "%llu%c", &tmpll, &dummy) != 1 || tmpll != (sector_t)tmpll) {
+		ti->error = "Invalid device sector";
+		return -EINVAL;
+	}
+	c->start = tmpll;
+
+	if (sscanf(argv[2], "%u%c", &c->delay, &dummy) != 1) {
+		ti->error = "Invalid delay";
+		return -EINVAL;
+	}
+
+	ret = dm_get_device(ti, argv[0], dm_table_get_mode(ti->table), &c->dev);
+	if (ret) {
+		ti->error = "Device lookup failed";
+		return ret;
+	}
+
+	return 0;
+}
+
+/*
+ * Mapping parameters:
+ *    <device> <offset> <delay> [<write_device> <write_offset> <write_delay>]
+ *
+ * With separate write parameters, the first set is only used for reads.
+ * Offsets are specified in sectors.
+ * Delays are specified in milliseconds.
+ */
+static int delay_ctr(struct dm_target *ti, unsigned int argc, char **argv)
+{
+	struct delay_c *dc;
+	int ret;
+
+	if (argc != 3 && argc != 6 && argc != 9) {
+		ti->error = "Requires exactly 3, 6 or 9 arguments";
+		return -EINVAL;
+	}
+
+	dc = kzalloc(sizeof(*dc), GFP_KERNEL);
+	if (!dc) {
+		ti->error = "Cannot allocate context";
+		return -ENOMEM;
+	}
+
+	ti->private = dc;
+	timer_setup(&dc->delay_timer, handle_delayed_timer, 0);
+	INIT_WORK(&dc->flush_expired_bios, flush_expired_bios);
+	INIT_LIST_HEAD(&dc->delayed_bios);
+	mutex_init(&dc->timer_lock);
+	atomic_set(&dc->may_delay, 1);
+	dc->argc = argc;
+
+	ret = delay_class_ctr(ti, &dc->read, argv);
+	if (ret)
+		goto bad;
+
+	if (argc == 3) {
+		ret = delay_class_ctr(ti, &dc->write, argv);
+		if (ret)
+			goto bad;
+		ret = delay_class_ctr(ti, &dc->flush, argv);
+		if (ret)
+			goto bad;
+		goto out;
+	}
+
+	ret = delay_class_ctr(ti, &dc->write, argv + 3);
+	if (ret)
+		goto bad;
+	if (argc == 6) {
+		ret = delay_class_ctr(ti, &dc->flush, argv + 3);
+		if (ret)
+			goto bad;
+		goto out;
+	}
+
+	ret = delay_class_ctr(ti, &dc->flush, argv + 6);
+	if (ret)
+		goto bad;
+
+out:
+	dc->kdelayd_wq = alloc_workqueue("kdelayd", WQ_MEM_RECLAIM, 0);
+	if (!dc->kdelayd_wq) {
+		ret = -EINVAL;
+		DMERR("Couldn't start kdelayd");
+		goto bad;
+	}
+
+	ti->num_flush_bios = 1;
+	ti->num_discard_bios = 1;
+	ti->accounts_remapped_io = true;
+	ti->per_io_data_size = sizeof(struct dm_delay_info);
+	return 0;
+
+bad:
+	delay_dtr(ti);
+	return ret;
+}
+
+static int delay_bio(struct delay_c *dc, struct delay_class *c, struct bio *bio)
+{
+	struct dm_delay_info *delayed;
+	unsigned long expires = 0;
+
+	if (!c->delay || !atomic_read(&dc->may_delay))
+		return DM_MAPIO_REMAPPED;
+
+	delayed = dm_per_bio_data(bio, sizeof(struct dm_delay_info));
+
+	delayed->context = dc;
+	delayed->expires = expires = jiffies + msecs_to_jiffies(c->delay);
+
+	mutex_lock(&delayed_bios_lock);
+	c->ops++;
+	list_add_tail(&delayed->list, &dc->delayed_bios);
+	mutex_unlock(&delayed_bios_lock);
+
+	queue_timeout(dc, expires);
+
+	return DM_MAPIO_SUBMITTED;
+}
+
+static void delay_presuspend(struct dm_target *ti)
+{
+	struct delay_c *dc = ti->private;
+
+	atomic_set(&dc->may_delay, 0);
+	del_timer_sync(&dc->delay_timer);
+	flush_bios(flush_delayed_bios(dc, 1));
+}
+
+static void delay_resume(struct dm_target *ti)
+{
+	struct delay_c *dc = ti->private;
+
+	atomic_set(&dc->may_delay, 1);
+}
+
+static int delay_map(struct dm_target *ti, struct bio *bio)
+{
+	struct delay_c *dc = ti->private;
+	struct delay_class *c;
+	struct dm_delay_info *delayed = dm_per_bio_data(bio, sizeof(struct dm_delay_info));
+
+	if (bio_data_dir(bio) == WRITE) {
+		if (unlikely(bio->bi_opf & REQ_PREFLUSH))
+			c = &dc->flush;
+		else
+			c = &dc->write;
+	} else {
+		c = &dc->read;
+	}
+	delayed->class = c;
+	bio_set_dev(bio, c->dev->bdev);
+	bio->bi_iter.bi_sector = c->start + dm_target_offset(ti, bio->bi_iter.bi_sector);
+
+	return delay_bio(dc, c, bio);
+}
+
+#define DMEMIT_DELAY_CLASS(c) \
+	DMEMIT("%s %llu %u", (c)->dev->name, (unsigned long long)(c)->start, (c)->delay)
+
+static void delay_status(struct dm_target *ti, status_type_t type,
+			 unsigned status_flags, char *result, unsigned maxlen)
+{
+	struct delay_c *dc = ti->private;
+	int sz = 0;
+
+	switch (type) {
+	case STATUSTYPE_INFO:
+		DMEMIT("%u %u %u", dc->read.ops, dc->write.ops, dc->flush.ops);
+		break;
+
+	case STATUSTYPE_TABLE:
+		DMEMIT_DELAY_CLASS(&dc->read);
+		if (dc->argc >= 6) {
+			DMEMIT(" ");
+			DMEMIT_DELAY_CLASS(&dc->write);
+		}
+		if (dc->argc >= 9) {
+			DMEMIT(" ");
+			DMEMIT_DELAY_CLASS(&dc->flush);
+		}
+		break;
+
+	case STATUSTYPE_IMA:
+		*result = '\0';
+		break;
+	}
+}
+
+static int delay_iterate_devices(struct dm_target *ti,
+				 iterate_devices_callout_fn fn, void *data)
+{
+	struct delay_c *dc = ti->private;
+	int ret = 0;
+
+	ret = fn(ti, dc->read.dev, dc->read.start, ti->len, data);
+	if (ret)
+		goto out;
+	ret = fn(ti, dc->write.dev, dc->write.start, ti->len, data);
+	if (ret)
+		goto out;
+	ret = fn(ti, dc->flush.dev, dc->flush.start, ti->len, data);
+	if (ret)
+		goto out;
+
+out:
+	return ret;
+}
+
+static struct target_type delay_target = {
+	.name	     = "delay",
+	.version     = {1, 3, 0},
+	.features    = DM_TARGET_PASSES_INTEGRITY,
+	.module      = THIS_MODULE,
+	.ctr	     = delay_ctr,
+	.dtr	     = delay_dtr,
+	.map	     = delay_map,
+	.presuspend  = delay_presuspend,
+	.resume	     = delay_resume,
+	.status	     = delay_status,
+	.iterate_devices = delay_iterate_devices,
+};
+
+static int __init dm_delay_init(void)
+{
+	int r;
+
+	r = dm_register_target(&delay_target);
+	if (r < 0) {
+		DMERR("register failed %d", r);
+		goto bad_register;
+	}
+
+	return 0;
+
+bad_register:
+	return r;
+}
+
+static void __exit dm_delay_exit(void)
+{
+	dm_unregister_target(&delay_target);
+}
+
+/* Module hooks */
+module_init(dm_delay_init);
+module_exit(dm_delay_exit);
+
+MODULE_DESCRIPTION(DM_NAME " delay target");
+MODULE_AUTHOR("Heinz Mauelshagen <mauelshagen@redhat.com>");
+MODULE_LICENSE("GPL");