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, 280 insertions, 0 deletions

diff --git a/fs/xfs/xfs_quotaops.c b/fs/xfs/xfs_quotaops.c
new file mode 100644
index 000000000..9c162e699
--- /dev/null
+++ b/fs/xfs/xfs_quotaops.c
@@ -0,0 +1,280 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2008, Christoph Hellwig
+ * All Rights Reserved.
+ */
+#include "xfs.h"
+#include "xfs_shared.h"
+#include "xfs_format.h"
+#include "xfs_log_format.h"
+#include "xfs_trans_resv.h"
+#include "xfs_mount.h"
+#include "xfs_inode.h"
+#include "xfs_quota.h"
+#include "xfs_trans.h"
+#include "xfs_icache.h"
+#include "xfs_qm.h"
+
+
+static void
+xfs_qm_fill_state(
+	struct qc_type_state	*tstate,
+	struct xfs_mount	*mp,
+	struct xfs_inode	*ip,
+	xfs_ino_t		ino,
+	struct xfs_def_quota	*defq)
+{
+	bool			tempqip = false;
+
+	tstate->ino = ino;
+	if (!ip && ino == NULLFSINO)
+		return;
+	if (!ip) {
+		if (xfs_iget(mp, NULL, ino, 0, 0, &ip))
+			return;
+		tempqip = true;
+	}
+	tstate->flags |= QCI_SYSFILE;
+	tstate->blocks = ip->i_nblocks;
+	tstate->nextents = ip->i_df.if_nextents;
+	tstate->spc_timelimit = (u32)defq->blk.time;
+	tstate->ino_timelimit = (u32)defq->ino.time;
+	tstate->rt_spc_timelimit = (u32)defq->rtb.time;
+	tstate->spc_warnlimit = 0;
+	tstate->ino_warnlimit = 0;
+	tstate->rt_spc_warnlimit = 0;
+	if (tempqip)
+		xfs_irele(ip);
+}
+
+/*
+ * Return quota status information, such as enforcements, quota file inode
+ * numbers etc.
+ */
+static int
+xfs_fs_get_quota_state(
+	struct super_block	*sb,
+	struct qc_state		*state)
+{
+	struct xfs_mount *mp = XFS_M(sb);
+	struct xfs_quotainfo *q = mp->m_quotainfo;
+
+	memset(state, 0, sizeof(*state));
+	if (!XFS_IS_QUOTA_ON(mp))
+		return 0;
+	state->s_incoredqs = q->qi_dquots;
+	if (XFS_IS_UQUOTA_ON(mp))
+		state->s_state[USRQUOTA].flags |= QCI_ACCT_ENABLED;
+	if (XFS_IS_UQUOTA_ENFORCED(mp))
+		state->s_state[USRQUOTA].flags |= QCI_LIMITS_ENFORCED;
+	if (XFS_IS_GQUOTA_ON(mp))
+		state->s_state[GRPQUOTA].flags |= QCI_ACCT_ENABLED;
+	if (XFS_IS_GQUOTA_ENFORCED(mp))
+		state->s_state[GRPQUOTA].flags |= QCI_LIMITS_ENFORCED;
+	if (XFS_IS_PQUOTA_ON(mp))
+		state->s_state[PRJQUOTA].flags |= QCI_ACCT_ENABLED;
+	if (XFS_IS_PQUOTA_ENFORCED(mp))
+		state->s_state[PRJQUOTA].flags |= QCI_LIMITS_ENFORCED;
+
+	xfs_qm_fill_state(&state->s_state[USRQUOTA], mp, q->qi_uquotaip,
+			  mp->m_sb.sb_uquotino, &q->qi_usr_default);
+	xfs_qm_fill_state(&state->s_state[GRPQUOTA], mp, q->qi_gquotaip,
+			  mp->m_sb.sb_gquotino, &q->qi_grp_default);
+	xfs_qm_fill_state(&state->s_state[PRJQUOTA], mp, q->qi_pquotaip,
+			  mp->m_sb.sb_pquotino, &q->qi_prj_default);
+	return 0;
+}
+
+STATIC xfs_dqtype_t
+xfs_quota_type(int type)
+{
+	switch (type) {
+	case USRQUOTA:
+		return XFS_DQTYPE_USER;
+	case GRPQUOTA:
+		return XFS_DQTYPE_GROUP;
+	default:
+		return XFS_DQTYPE_PROJ;
+	}
+}
+
+#define XFS_QC_SETINFO_MASK (QC_TIMER_MASK)
+
+/*
+ * Adjust quota timers & warnings
+ */
+static int
+xfs_fs_set_info(
+	struct super_block	*sb,
+	int			type,
+	struct qc_info		*info)
+{
+	struct xfs_mount	*mp = XFS_M(sb);
+	struct qc_dqblk		newlim;
+
+	if (sb_rdonly(sb))
+		return -EROFS;
+	if (!XFS_IS_QUOTA_ON(mp))
+		return -ENOSYS;
+	if (info->i_fieldmask & ~XFS_QC_SETINFO_MASK)
+		return -EINVAL;
+	if ((info->i_fieldmask & XFS_QC_SETINFO_MASK) == 0)
+		return 0;
+
+	newlim.d_fieldmask = info->i_fieldmask;
+	newlim.d_spc_timer = info->i_spc_timelimit;
+	newlim.d_ino_timer = info->i_ino_timelimit;
+	newlim.d_rt_spc_timer = info->i_rt_spc_timelimit;
+	newlim.d_ino_warns = info->i_ino_warnlimit;
+	newlim.d_spc_warns = info->i_spc_warnlimit;
+	newlim.d_rt_spc_warns = info->i_rt_spc_warnlimit;
+
+	return xfs_qm_scall_setqlim(mp, 0, xfs_quota_type(type), &newlim);
+}
+
+static unsigned int
+xfs_quota_flags(unsigned int uflags)
+{
+	unsigned int flags = 0;
+
+	if (uflags & FS_QUOTA_UDQ_ACCT)
+		flags |= XFS_UQUOTA_ACCT;
+	if (uflags & FS_QUOTA_PDQ_ACCT)
+		flags |= XFS_PQUOTA_ACCT;
+	if (uflags & FS_QUOTA_GDQ_ACCT)
+		flags |= XFS_GQUOTA_ACCT;
+	if (uflags & FS_QUOTA_UDQ_ENFD)
+		flags |= XFS_UQUOTA_ENFD;
+	if (uflags & FS_QUOTA_GDQ_ENFD)
+		flags |= XFS_GQUOTA_ENFD;
+	if (uflags & FS_QUOTA_PDQ_ENFD)
+		flags |= XFS_PQUOTA_ENFD;
+
+	return flags;
+}
+
+STATIC int
+xfs_quota_enable(
+	struct super_block	*sb,
+	unsigned int		uflags)
+{
+	struct xfs_mount	*mp = XFS_M(sb);
+
+	if (sb_rdonly(sb))
+		return -EROFS;
+	if (!XFS_IS_QUOTA_ON(mp))
+		return -ENOSYS;
+
+	return xfs_qm_scall_quotaon(mp, xfs_quota_flags(uflags));
+}
+
+STATIC int
+xfs_quota_disable(
+	struct super_block	*sb,
+	unsigned int		uflags)
+{
+	struct xfs_mount	*mp = XFS_M(sb);
+
+	if (sb_rdonly(sb))
+		return -EROFS;
+	if (!XFS_IS_QUOTA_ON(mp))
+		return -ENOSYS;
+
+	return xfs_qm_scall_quotaoff(mp, xfs_quota_flags(uflags));
+}
+
+STATIC int
+xfs_fs_rm_xquota(
+	struct super_block	*sb,
+	unsigned int		uflags)
+{
+	struct xfs_mount	*mp = XFS_M(sb);
+	unsigned int		flags = 0;
+
+	if (sb_rdonly(sb))
+		return -EROFS;
+
+	if (XFS_IS_QUOTA_ON(mp))
+		return -EINVAL;
+
+	if (uflags & ~(FS_USER_QUOTA | FS_GROUP_QUOTA | FS_PROJ_QUOTA))
+		return -EINVAL;
+
+	if (uflags & FS_USER_QUOTA)
+		flags |= XFS_QMOPT_UQUOTA;
+	if (uflags & FS_GROUP_QUOTA)
+		flags |= XFS_QMOPT_GQUOTA;
+	if (uflags & FS_PROJ_QUOTA)
+		flags |= XFS_QMOPT_PQUOTA;
+
+	return xfs_qm_scall_trunc_qfiles(mp, flags);
+}
+
+STATIC int
+xfs_fs_get_dqblk(
+	struct super_block	*sb,
+	struct kqid		qid,
+	struct qc_dqblk		*qdq)
+{
+	struct xfs_mount	*mp = XFS_M(sb);
+	xfs_dqid_t		id;
+
+	if (!XFS_IS_QUOTA_ON(mp))
+		return -ENOSYS;
+
+	id = from_kqid(&init_user_ns, qid);
+	return xfs_qm_scall_getquota(mp, id, xfs_quota_type(qid.type), qdq);
+}
+
+/* Return quota info for active quota >= this qid */
+STATIC int
+xfs_fs_get_nextdqblk(
+	struct super_block	*sb,
+	struct kqid		*qid,
+	struct qc_dqblk		*qdq)
+{
+	int			ret;
+	struct xfs_mount	*mp = XFS_M(sb);
+	xfs_dqid_t		id;
+
+	if (!XFS_IS_QUOTA_ON(mp))
+		return -ENOSYS;
+
+	id = from_kqid(&init_user_ns, *qid);
+	ret = xfs_qm_scall_getquota_next(mp, &id, xfs_quota_type(qid->type),
+			qdq);
+	if (ret)
+		return ret;
+
+	/* ID may be different, so convert back what we got */
+	*qid = make_kqid(current_user_ns(), qid->type, id);
+	return 0;
+}
+
+STATIC int
+xfs_fs_set_dqblk(
+	struct super_block	*sb,
+	struct kqid		qid,
+	struct qc_dqblk		*qdq)
+{
+	struct xfs_mount	*mp = XFS_M(sb);
+
+	if (sb_rdonly(sb))
+		return -EROFS;
+	if (!XFS_IS_QUOTA_ON(mp))
+		return -ENOSYS;
+
+	return xfs_qm_scall_setqlim(mp, from_kqid(&init_user_ns, qid),
+				     xfs_quota_type(qid.type), qdq);
+}
+
+const struct quotactl_ops xfs_quotactl_operations = {
+	.get_state		= xfs_fs_get_quota_state,
+	.set_info		= xfs_fs_set_info,
+	.quota_enable		= xfs_quota_enable,
+	.quota_disable		= xfs_quota_disable,
+	.rm_xquota		= xfs_fs_rm_xquota,
+	.get_dqblk		= xfs_fs_get_dqblk,
+	.get_nextdqblk		= xfs_fs_get_nextdqblk,
+	.set_dqblk		= xfs_fs_set_dqblk,
+};