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, 789 insertions, 0 deletions

diff --git a/fs/quota/quota_tree.c b/fs/quota/quota_tree.c
new file mode 100644
index 000000000..0f1493e0f
--- /dev/null
+++ b/fs/quota/quota_tree.c
@@ -0,0 +1,789 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ *	vfsv0 quota IO operations on file
+ */
+
+#include <linux/errno.h>
+#include <linux/fs.h>
+#include <linux/mount.h>
+#include <linux/dqblk_v2.h>
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <linux/quotaops.h>
+
+#include <asm/byteorder.h>
+
+#include "quota_tree.h"
+
+MODULE_AUTHOR("Jan Kara");
+MODULE_DESCRIPTION("Quota trie support");
+MODULE_LICENSE("GPL");
+
+#define __QUOTA_QT_PARANOIA
+
+static int __get_index(struct qtree_mem_dqinfo *info, qid_t id, int depth)
+{
+	unsigned int epb = info->dqi_usable_bs >> 2;
+
+	depth = info->dqi_qtree_depth - depth - 1;
+	while (depth--)
+		id /= epb;
+	return id % epb;
+}
+
+static int get_index(struct qtree_mem_dqinfo *info, struct kqid qid, int depth)
+{
+	qid_t id = from_kqid(&init_user_ns, qid);
+
+	return __get_index(info, id, depth);
+}
+
+/* Number of entries in one blocks */
+static int qtree_dqstr_in_blk(struct qtree_mem_dqinfo *info)
+{
+	return (info->dqi_usable_bs - sizeof(struct qt_disk_dqdbheader))
+	       / info->dqi_entry_size;
+}
+
+static ssize_t read_blk(struct qtree_mem_dqinfo *info, uint blk, char *buf)
+{
+	struct super_block *sb = info->dqi_sb;
+
+	memset(buf, 0, info->dqi_usable_bs);
+	return sb->s_op->quota_read(sb, info->dqi_type, buf,
+	       info->dqi_usable_bs, (loff_t)blk << info->dqi_blocksize_bits);
+}
+
+static ssize_t write_blk(struct qtree_mem_dqinfo *info, uint blk, char *buf)
+{
+	struct super_block *sb = info->dqi_sb;
+	ssize_t ret;
+
+	ret = sb->s_op->quota_write(sb, info->dqi_type, buf,
+	       info->dqi_usable_bs, (loff_t)blk << info->dqi_blocksize_bits);
+	if (ret != info->dqi_usable_bs) {
+		quota_error(sb, "dquota write failed");
+		if (ret >= 0)
+			ret = -EIO;
+	}
+	return ret;
+}
+
+static inline int do_check_range(struct super_block *sb, const char *val_name,
+				 uint val, uint min_val, uint max_val)
+{
+	if (val < min_val || val > max_val) {
+		quota_error(sb, "Getting %s %u out of range %u-%u",
+			    val_name, val, min_val, max_val);
+		return -EUCLEAN;
+	}
+
+	return 0;
+}
+
+static int check_dquot_block_header(struct qtree_mem_dqinfo *info,
+				    struct qt_disk_dqdbheader *dh)
+{
+	int err = 0;
+
+	err = do_check_range(info->dqi_sb, "dqdh_next_free",
+			     le32_to_cpu(dh->dqdh_next_free), 0,
+			     info->dqi_blocks - 1);
+	if (err)
+		return err;
+	err = do_check_range(info->dqi_sb, "dqdh_prev_free",
+			     le32_to_cpu(dh->dqdh_prev_free), 0,
+			     info->dqi_blocks - 1);
+	if (err)
+		return err;
+	err = do_check_range(info->dqi_sb, "dqdh_entries",
+			     le16_to_cpu(dh->dqdh_entries), 0,
+			     qtree_dqstr_in_blk(info));
+
+	return err;
+}
+
+/* Remove empty block from list and return it */
+static int get_free_dqblk(struct qtree_mem_dqinfo *info)
+{
+	char *buf = kmalloc(info->dqi_usable_bs, GFP_NOFS);
+	struct qt_disk_dqdbheader *dh = (struct qt_disk_dqdbheader *)buf;
+	int ret, blk;
+
+	if (!buf)
+		return -ENOMEM;
+	if (info->dqi_free_blk) {
+		blk = info->dqi_free_blk;
+		ret = read_blk(info, blk, buf);
+		if (ret < 0)
+			goto out_buf;
+		ret = check_dquot_block_header(info, dh);
+		if (ret)
+			goto out_buf;
+		info->dqi_free_blk = le32_to_cpu(dh->dqdh_next_free);
+	}
+	else {
+		memset(buf, 0, info->dqi_usable_bs);
+		/* Assure block allocation... */
+		ret = write_blk(info, info->dqi_blocks, buf);
+		if (ret < 0)
+			goto out_buf;
+		blk = info->dqi_blocks++;
+	}
+	mark_info_dirty(info->dqi_sb, info->dqi_type);
+	ret = blk;
+out_buf:
+	kfree(buf);
+	return ret;
+}
+
+/* Insert empty block to the list */
+static int put_free_dqblk(struct qtree_mem_dqinfo *info, char *buf, uint blk)
+{
+	struct qt_disk_dqdbheader *dh = (struct qt_disk_dqdbheader *)buf;
+	int err;
+
+	dh->dqdh_next_free = cpu_to_le32(info->dqi_free_blk);
+	dh->dqdh_prev_free = cpu_to_le32(0);
+	dh->dqdh_entries = cpu_to_le16(0);
+	err = write_blk(info, blk, buf);
+	if (err < 0)
+		return err;
+	info->dqi_free_blk = blk;
+	mark_info_dirty(info->dqi_sb, info->dqi_type);
+	return 0;
+}
+
+/* Remove given block from the list of blocks with free entries */
+static int remove_free_dqentry(struct qtree_mem_dqinfo *info, char *buf,
+			       uint blk)
+{
+	char *tmpbuf = kmalloc(info->dqi_usable_bs, GFP_NOFS);
+	struct qt_disk_dqdbheader *dh = (struct qt_disk_dqdbheader *)buf;
+	uint nextblk = le32_to_cpu(dh->dqdh_next_free);
+	uint prevblk = le32_to_cpu(dh->dqdh_prev_free);
+	int err;
+
+	if (!tmpbuf)
+		return -ENOMEM;
+	if (nextblk) {
+		err = read_blk(info, nextblk, tmpbuf);
+		if (err < 0)
+			goto out_buf;
+		((struct qt_disk_dqdbheader *)tmpbuf)->dqdh_prev_free =
+							dh->dqdh_prev_free;
+		err = write_blk(info, nextblk, tmpbuf);
+		if (err < 0)
+			goto out_buf;
+	}
+	if (prevblk) {
+		err = read_blk(info, prevblk, tmpbuf);
+		if (err < 0)
+			goto out_buf;
+		((struct qt_disk_dqdbheader *)tmpbuf)->dqdh_next_free =
+							dh->dqdh_next_free;
+		err = write_blk(info, prevblk, tmpbuf);
+		if (err < 0)
+			goto out_buf;
+	} else {
+		info->dqi_free_entry = nextblk;
+		mark_info_dirty(info->dqi_sb, info->dqi_type);
+	}
+	kfree(tmpbuf);
+	dh->dqdh_next_free = dh->dqdh_prev_free = cpu_to_le32(0);
+	/* No matter whether write succeeds block is out of list */
+	if (write_blk(info, blk, buf) < 0)
+		quota_error(info->dqi_sb, "Can't write block (%u) "
+			    "with free entries", blk);
+	return 0;
+out_buf:
+	kfree(tmpbuf);
+	return err;
+}
+
+/* Insert given block to the beginning of list with free entries */
+static int insert_free_dqentry(struct qtree_mem_dqinfo *info, char *buf,
+			       uint blk)
+{
+	char *tmpbuf = kmalloc(info->dqi_usable_bs, GFP_NOFS);
+	struct qt_disk_dqdbheader *dh = (struct qt_disk_dqdbheader *)buf;
+	int err;
+
+	if (!tmpbuf)
+		return -ENOMEM;
+	dh->dqdh_next_free = cpu_to_le32(info->dqi_free_entry);
+	dh->dqdh_prev_free = cpu_to_le32(0);
+	err = write_blk(info, blk, buf);
+	if (err < 0)
+		goto out_buf;
+	if (info->dqi_free_entry) {
+		err = read_blk(info, info->dqi_free_entry, tmpbuf);
+		if (err < 0)
+			goto out_buf;
+		((struct qt_disk_dqdbheader *)tmpbuf)->dqdh_prev_free =
+							cpu_to_le32(blk);
+		err = write_blk(info, info->dqi_free_entry, tmpbuf);
+		if (err < 0)
+			goto out_buf;
+	}
+	kfree(tmpbuf);
+	info->dqi_free_entry = blk;
+	mark_info_dirty(info->dqi_sb, info->dqi_type);
+	return 0;
+out_buf:
+	kfree(tmpbuf);
+	return err;
+}
+
+/* Is the entry in the block free? */
+int qtree_entry_unused(struct qtree_mem_dqinfo *info, char *disk)
+{
+	int i;
+
+	for (i = 0; i < info->dqi_entry_size; i++)
+		if (disk[i])
+			return 0;
+	return 1;
+}
+EXPORT_SYMBOL(qtree_entry_unused);
+
+/* Find space for dquot */
+static uint find_free_dqentry(struct qtree_mem_dqinfo *info,
+			      struct dquot *dquot, int *err)
+{
+	uint blk, i;
+	struct qt_disk_dqdbheader *dh;
+	char *buf = kmalloc(info->dqi_usable_bs, GFP_NOFS);
+	char *ddquot;
+
+	*err = 0;
+	if (!buf) {
+		*err = -ENOMEM;
+		return 0;
+	}
+	dh = (struct qt_disk_dqdbheader *)buf;
+	if (info->dqi_free_entry) {
+		blk = info->dqi_free_entry;
+		*err = read_blk(info, blk, buf);
+		if (*err < 0)
+			goto out_buf;
+		*err = check_dquot_block_header(info, dh);
+		if (*err)
+			goto out_buf;
+	} else {
+		blk = get_free_dqblk(info);
+		if ((int)blk < 0) {
+			*err = blk;
+			kfree(buf);
+			return 0;
+		}
+		memset(buf, 0, info->dqi_usable_bs);
+		/* This is enough as the block is already zeroed and the entry
+		 * list is empty... */
+		info->dqi_free_entry = blk;
+		mark_info_dirty(dquot->dq_sb, dquot->dq_id.type);
+	}
+	/* Block will be full? */
+	if (le16_to_cpu(dh->dqdh_entries) + 1 >= qtree_dqstr_in_blk(info)) {
+		*err = remove_free_dqentry(info, buf, blk);
+		if (*err < 0) {
+			quota_error(dquot->dq_sb, "Can't remove block (%u) "
+				    "from entry free list", blk);
+			goto out_buf;
+		}
+	}
+	le16_add_cpu(&dh->dqdh_entries, 1);
+	/* Find free structure in block */
+	ddquot = buf + sizeof(struct qt_disk_dqdbheader);
+	for (i = 0; i < qtree_dqstr_in_blk(info); i++) {
+		if (qtree_entry_unused(info, ddquot))
+			break;
+		ddquot += info->dqi_entry_size;
+	}
+#ifdef __QUOTA_QT_PARANOIA
+	if (i == qtree_dqstr_in_blk(info)) {
+		quota_error(dquot->dq_sb, "Data block full but it shouldn't");
+		*err = -EIO;
+		goto out_buf;
+	}
+#endif
+	*err = write_blk(info, blk, buf);
+	if (*err < 0) {
+		quota_error(dquot->dq_sb, "Can't write quota data block %u",
+			    blk);
+		goto out_buf;
+	}
+	dquot->dq_off = ((loff_t)blk << info->dqi_blocksize_bits) +
+			sizeof(struct qt_disk_dqdbheader) +
+			i * info->dqi_entry_size;
+	kfree(buf);
+	return blk;
+out_buf:
+	kfree(buf);
+	return 0;
+}
+
+/* Insert reference to structure into the trie */
+static int do_insert_tree(struct qtree_mem_dqinfo *info, struct dquot *dquot,
+			  uint *treeblk, int depth)
+{
+	char *buf = kmalloc(info->dqi_usable_bs, GFP_NOFS);
+	int ret = 0, newson = 0, newact = 0;
+	__le32 *ref;
+	uint newblk;
+
+	if (!buf)
+		return -ENOMEM;
+	if (!*treeblk) {
+		ret = get_free_dqblk(info);
+		if (ret < 0)
+			goto out_buf;
+		*treeblk = ret;
+		memset(buf, 0, info->dqi_usable_bs);
+		newact = 1;
+	} else {
+		ret = read_blk(info, *treeblk, buf);
+		if (ret < 0) {
+			quota_error(dquot->dq_sb, "Can't read tree quota "
+				    "block %u", *treeblk);
+			goto out_buf;
+		}
+	}
+	ref = (__le32 *)buf;
+	newblk = le32_to_cpu(ref[get_index(info, dquot->dq_id, depth)]);
+	ret = do_check_range(dquot->dq_sb, "block", newblk, 0,
+			     info->dqi_blocks - 1);
+	if (ret)
+		goto out_buf;
+	if (!newblk)
+		newson = 1;
+	if (depth == info->dqi_qtree_depth - 1) {
+#ifdef __QUOTA_QT_PARANOIA
+		if (newblk) {
+			quota_error(dquot->dq_sb, "Inserting already present "
+				    "quota entry (block %u)",
+				    le32_to_cpu(ref[get_index(info,
+						dquot->dq_id, depth)]));
+			ret = -EIO;
+			goto out_buf;
+		}
+#endif
+		newblk = find_free_dqentry(info, dquot, &ret);
+	} else {
+		ret = do_insert_tree(info, dquot, &newblk, depth+1);
+	}
+	if (newson && ret >= 0) {
+		ref[get_index(info, dquot->dq_id, depth)] =
+							cpu_to_le32(newblk);
+		ret = write_blk(info, *treeblk, buf);
+	} else if (newact && ret < 0) {
+		put_free_dqblk(info, buf, *treeblk);
+	}
+out_buf:
+	kfree(buf);
+	return ret;
+}
+
+/* Wrapper for inserting quota structure into tree */
+static inline int dq_insert_tree(struct qtree_mem_dqinfo *info,
+				 struct dquot *dquot)
+{
+	int tmp = QT_TREEOFF;
+
+#ifdef __QUOTA_QT_PARANOIA
+	if (info->dqi_blocks <= QT_TREEOFF) {
+		quota_error(dquot->dq_sb, "Quota tree root isn't allocated!");
+		return -EIO;
+	}
+#endif
+	return do_insert_tree(info, dquot, &tmp, 0);
+}
+
+/*
+ * We don't have to be afraid of deadlocks as we never have quotas on quota
+ * files...
+ */
+int qtree_write_dquot(struct qtree_mem_dqinfo *info, struct dquot *dquot)
+{
+	int type = dquot->dq_id.type;
+	struct super_block *sb = dquot->dq_sb;
+	ssize_t ret;
+	char *ddquot = kmalloc(info->dqi_entry_size, GFP_NOFS);
+
+	if (!ddquot)
+		return -ENOMEM;
+
+	/* dq_off is guarded by dqio_sem */
+	if (!dquot->dq_off) {
+		ret = dq_insert_tree(info, dquot);
+		if (ret < 0) {
+			quota_error(sb, "Error %zd occurred while creating "
+				    "quota", ret);
+			kfree(ddquot);
+			return ret;
+		}
+	}
+	spin_lock(&dquot->dq_dqb_lock);
+	info->dqi_ops->mem2disk_dqblk(ddquot, dquot);
+	spin_unlock(&dquot->dq_dqb_lock);
+	ret = sb->s_op->quota_write(sb, type, ddquot, info->dqi_entry_size,
+				    dquot->dq_off);
+	if (ret != info->dqi_entry_size) {
+		quota_error(sb, "dquota write failed");
+		if (ret >= 0)
+			ret = -ENOSPC;
+	} else {
+		ret = 0;
+	}
+	dqstats_inc(DQST_WRITES);
+	kfree(ddquot);
+
+	return ret;
+}
+EXPORT_SYMBOL(qtree_write_dquot);
+
+/* Free dquot entry in data block */
+static int free_dqentry(struct qtree_mem_dqinfo *info, struct dquot *dquot,
+			uint blk)
+{
+	struct qt_disk_dqdbheader *dh;
+	char *buf = kmalloc(info->dqi_usable_bs, GFP_NOFS);
+	int ret = 0;
+
+	if (!buf)
+		return -ENOMEM;
+	if (dquot->dq_off >> info->dqi_blocksize_bits != blk) {
+		quota_error(dquot->dq_sb, "Quota structure has offset to "
+			"other block (%u) than it should (%u)", blk,
+			(uint)(dquot->dq_off >> info->dqi_blocksize_bits));
+		ret = -EIO;
+		goto out_buf;
+	}
+	ret = read_blk(info, blk, buf);
+	if (ret < 0) {
+		quota_error(dquot->dq_sb, "Can't read quota data block %u",
+			    blk);
+		goto out_buf;
+	}
+	dh = (struct qt_disk_dqdbheader *)buf;
+	ret = check_dquot_block_header(info, dh);
+	if (ret)
+		goto out_buf;
+	le16_add_cpu(&dh->dqdh_entries, -1);
+	if (!le16_to_cpu(dh->dqdh_entries)) {	/* Block got free? */
+		ret = remove_free_dqentry(info, buf, blk);
+		if (ret >= 0)
+			ret = put_free_dqblk(info, buf, blk);
+		if (ret < 0) {
+			quota_error(dquot->dq_sb, "Can't move quota data block "
+				    "(%u) to free list", blk);
+			goto out_buf;
+		}
+	} else {
+		memset(buf +
+		       (dquot->dq_off & ((1 << info->dqi_blocksize_bits) - 1)),
+		       0, info->dqi_entry_size);
+		if (le16_to_cpu(dh->dqdh_entries) ==
+		    qtree_dqstr_in_blk(info) - 1) {
+			/* Insert will write block itself */
+			ret = insert_free_dqentry(info, buf, blk);
+			if (ret < 0) {
+				quota_error(dquot->dq_sb, "Can't insert quota "
+				    "data block (%u) to free entry list", blk);
+				goto out_buf;
+			}
+		} else {
+			ret = write_blk(info, blk, buf);
+			if (ret < 0) {
+				quota_error(dquot->dq_sb, "Can't write quota "
+					    "data block %u", blk);
+				goto out_buf;
+			}
+		}
+	}
+	dquot->dq_off = 0;	/* Quota is now unattached */
+out_buf:
+	kfree(buf);
+	return ret;
+}
+
+/* Remove reference to dquot from tree */
+static int remove_tree(struct qtree_mem_dqinfo *info, struct dquot *dquot,
+		       uint *blk, int depth)
+{
+	char *buf = kmalloc(info->dqi_usable_bs, GFP_NOFS);
+	int ret = 0;
+	uint newblk;
+	__le32 *ref = (__le32 *)buf;
+
+	if (!buf)
+		return -ENOMEM;
+	ret = read_blk(info, *blk, buf);
+	if (ret < 0) {
+		quota_error(dquot->dq_sb, "Can't read quota data block %u",
+			    *blk);
+		goto out_buf;
+	}
+	newblk = le32_to_cpu(ref[get_index(info, dquot->dq_id, depth)]);
+	ret = do_check_range(dquot->dq_sb, "block", newblk, QT_TREEOFF,
+			     info->dqi_blocks - 1);
+	if (ret)
+		goto out_buf;
+
+	if (depth == info->dqi_qtree_depth - 1) {
+		ret = free_dqentry(info, dquot, newblk);
+		newblk = 0;
+	} else {
+		ret = remove_tree(info, dquot, &newblk, depth+1);
+	}
+	if (ret >= 0 && !newblk) {
+		int i;
+		ref[get_index(info, dquot->dq_id, depth)] = cpu_to_le32(0);
+		/* Block got empty? */
+		for (i = 0; i < (info->dqi_usable_bs >> 2) && !ref[i]; i++)
+			;
+		/* Don't put the root block into the free block list */
+		if (i == (info->dqi_usable_bs >> 2)
+		    && *blk != QT_TREEOFF) {
+			put_free_dqblk(info, buf, *blk);
+			*blk = 0;
+		} else {
+			ret = write_blk(info, *blk, buf);
+			if (ret < 0)
+				quota_error(dquot->dq_sb,
+					    "Can't write quota tree block %u",
+					    *blk);
+		}
+	}
+out_buf:
+	kfree(buf);
+	return ret;
+}
+
+/* Delete dquot from tree */
+int qtree_delete_dquot(struct qtree_mem_dqinfo *info, struct dquot *dquot)
+{
+	uint tmp = QT_TREEOFF;
+
+	if (!dquot->dq_off)	/* Even not allocated? */
+		return 0;
+	return remove_tree(info, dquot, &tmp, 0);
+}
+EXPORT_SYMBOL(qtree_delete_dquot);
+
+/* Find entry in block */
+static loff_t find_block_dqentry(struct qtree_mem_dqinfo *info,
+				 struct dquot *dquot, uint blk)
+{
+	char *buf = kmalloc(info->dqi_usable_bs, GFP_NOFS);
+	loff_t ret = 0;
+	int i;
+	char *ddquot;
+
+	if (!buf)
+		return -ENOMEM;
+	ret = read_blk(info, blk, buf);
+	if (ret < 0) {
+		quota_error(dquot->dq_sb, "Can't read quota tree "
+			    "block %u", blk);
+		goto out_buf;
+	}
+	ddquot = buf + sizeof(struct qt_disk_dqdbheader);
+	for (i = 0; i < qtree_dqstr_in_blk(info); i++) {
+		if (info->dqi_ops->is_id(ddquot, dquot))
+			break;
+		ddquot += info->dqi_entry_size;
+	}
+	if (i == qtree_dqstr_in_blk(info)) {
+		quota_error(dquot->dq_sb,
+			    "Quota for id %u referenced but not present",
+			    from_kqid(&init_user_ns, dquot->dq_id));
+		ret = -EIO;
+		goto out_buf;
+	} else {
+		ret = ((loff_t)blk << info->dqi_blocksize_bits) + sizeof(struct
+		  qt_disk_dqdbheader) + i * info->dqi_entry_size;
+	}
+out_buf:
+	kfree(buf);
+	return ret;
+}
+
+/* Find entry for given id in the tree */
+static loff_t find_tree_dqentry(struct qtree_mem_dqinfo *info,
+				struct dquot *dquot, uint blk, int depth)
+{
+	char *buf = kmalloc(info->dqi_usable_bs, GFP_NOFS);
+	loff_t ret = 0;
+	__le32 *ref = (__le32 *)buf;
+
+	if (!buf)
+		return -ENOMEM;
+	ret = read_blk(info, blk, buf);
+	if (ret < 0) {
+		quota_error(dquot->dq_sb, "Can't read quota tree block %u",
+			    blk);
+		goto out_buf;
+	}
+	ret = 0;
+	blk = le32_to_cpu(ref[get_index(info, dquot->dq_id, depth)]);
+	if (!blk)	/* No reference? */
+		goto out_buf;
+	ret = do_check_range(dquot->dq_sb, "block", blk, QT_TREEOFF,
+			     info->dqi_blocks - 1);
+	if (ret)
+		goto out_buf;
+
+	if (depth < info->dqi_qtree_depth - 1)
+		ret = find_tree_dqentry(info, dquot, blk, depth+1);
+	else
+		ret = find_block_dqentry(info, dquot, blk);
+out_buf:
+	kfree(buf);
+	return ret;
+}
+
+/* Find entry for given id in the tree - wrapper function */
+static inline loff_t find_dqentry(struct qtree_mem_dqinfo *info,
+				  struct dquot *dquot)
+{
+	return find_tree_dqentry(info, dquot, QT_TREEOFF, 0);
+}
+
+int qtree_read_dquot(struct qtree_mem_dqinfo *info, struct dquot *dquot)
+{
+	int type = dquot->dq_id.type;
+	struct super_block *sb = dquot->dq_sb;
+	loff_t offset;
+	char *ddquot;
+	int ret = 0;
+
+#ifdef __QUOTA_QT_PARANOIA
+	/* Invalidated quota? */
+	if (!sb_dqopt(dquot->dq_sb)->files[type]) {
+		quota_error(sb, "Quota invalidated while reading!");
+		return -EIO;
+	}
+#endif
+	/* Do we know offset of the dquot entry in the quota file? */
+	if (!dquot->dq_off) {
+		offset = find_dqentry(info, dquot);
+		if (offset <= 0) {	/* Entry not present? */
+			if (offset < 0)
+				quota_error(sb,"Can't read quota structure "
+					    "for id %u",
+					    from_kqid(&init_user_ns,
+						      dquot->dq_id));
+			dquot->dq_off = 0;
+			set_bit(DQ_FAKE_B, &dquot->dq_flags);
+			memset(&dquot->dq_dqb, 0, sizeof(struct mem_dqblk));
+			ret = offset;
+			goto out;
+		}
+		dquot->dq_off = offset;
+	}
+	ddquot = kmalloc(info->dqi_entry_size, GFP_NOFS);
+	if (!ddquot)
+		return -ENOMEM;
+	ret = sb->s_op->quota_read(sb, type, ddquot, info->dqi_entry_size,
+				   dquot->dq_off);
+	if (ret != info->dqi_entry_size) {
+		if (ret >= 0)
+			ret = -EIO;
+		quota_error(sb, "Error while reading quota structure for id %u",
+			    from_kqid(&init_user_ns, dquot->dq_id));
+		set_bit(DQ_FAKE_B, &dquot->dq_flags);
+		memset(&dquot->dq_dqb, 0, sizeof(struct mem_dqblk));
+		kfree(ddquot);
+		goto out;
+	}
+	spin_lock(&dquot->dq_dqb_lock);
+	info->dqi_ops->disk2mem_dqblk(dquot, ddquot);
+	if (!dquot->dq_dqb.dqb_bhardlimit &&
+	    !dquot->dq_dqb.dqb_bsoftlimit &&
+	    !dquot->dq_dqb.dqb_ihardlimit &&
+	    !dquot->dq_dqb.dqb_isoftlimit)
+		set_bit(DQ_FAKE_B, &dquot->dq_flags);
+	spin_unlock(&dquot->dq_dqb_lock);
+	kfree(ddquot);
+out:
+	dqstats_inc(DQST_READS);
+	return ret;
+}
+EXPORT_SYMBOL(qtree_read_dquot);
+
+/* Check whether dquot should not be deleted. We know we are
+ * the only one operating on dquot (thanks to dq_lock) */
+int qtree_release_dquot(struct qtree_mem_dqinfo *info, struct dquot *dquot)
+{
+	if (test_bit(DQ_FAKE_B, &dquot->dq_flags) &&
+	    !(dquot->dq_dqb.dqb_curinodes | dquot->dq_dqb.dqb_curspace))
+		return qtree_delete_dquot(info, dquot);
+	return 0;
+}
+EXPORT_SYMBOL(qtree_release_dquot);
+
+static int find_next_id(struct qtree_mem_dqinfo *info, qid_t *id,
+			unsigned int blk, int depth)
+{
+	char *buf = kmalloc(info->dqi_usable_bs, GFP_NOFS);
+	__le32 *ref = (__le32 *)buf;
+	ssize_t ret;
+	unsigned int epb = info->dqi_usable_bs >> 2;
+	unsigned int level_inc = 1;
+	int i;
+
+	if (!buf)
+		return -ENOMEM;
+
+	for (i = depth; i < info->dqi_qtree_depth - 1; i++)
+		level_inc *= epb;
+
+	ret = read_blk(info, blk, buf);
+	if (ret < 0) {
+		quota_error(info->dqi_sb,
+			    "Can't read quota tree block %u", blk);
+		goto out_buf;
+	}
+	for (i = __get_index(info, *id, depth); i < epb; i++) {
+		uint blk_no = le32_to_cpu(ref[i]);
+
+		if (blk_no == 0) {
+			*id += level_inc;
+			continue;
+		}
+		ret = do_check_range(info->dqi_sb, "block", blk_no, 0,
+				     info->dqi_blocks - 1);
+		if (ret)
+			goto out_buf;
+		if (depth == info->dqi_qtree_depth - 1) {
+			ret = 0;
+			goto out_buf;
+		}
+		ret = find_next_id(info, id, blk_no, depth + 1);
+		if (ret != -ENOENT)
+			break;
+	}
+	if (i == epb) {
+		ret = -ENOENT;
+		goto out_buf;
+	}
+out_buf:
+	kfree(buf);
+	return ret;
+}
+
+int qtree_get_next_id(struct qtree_mem_dqinfo *info, struct kqid *qid)
+{
+	qid_t id = from_kqid(&init_user_ns, *qid);
+	int ret;
+
+	ret = find_next_id(info, &id, QT_TREEOFF, 0);
+	if (ret < 0)
+		return ret;
+	*qid = make_kqid(&init_user_ns, qid->type, id);
+	return 0;
+}
+EXPORT_SYMBOL(qtree_get_next_id);