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, 687 insertions, 0 deletions

diff --git a/fs/nfsd/nfs4idmap.c b/fs/nfsd/nfs4idmap.c
new file mode 100644
index 000000000..5e9809aff
--- /dev/null
+++ b/fs/nfsd/nfs4idmap.c
@@ -0,0 +1,687 @@
+/*
+ *  Mapping of UID/GIDs to name and vice versa.
+ *
+ *  Copyright (c) 2002, 2003 The Regents of the University of
+ *  Michigan.  All rights reserved.
+ *
+ *  Marius Aamodt Eriksen <marius@umich.edu>
+ *
+ *  Redistribution and use in source and binary forms, with or without
+ *  modification, are permitted provided that the following conditions
+ *  are met:
+ *
+ *  1. Redistributions of source code must retain the above copyright
+ *     notice, this list of conditions and the following disclaimer.
+ *  2. Redistributions in binary form must reproduce the above copyright
+ *     notice, this list of conditions and the following disclaimer in the
+ *     documentation and/or other materials provided with the distribution.
+ *  3. Neither the name of the University nor the names of its
+ *     contributors may be used to endorse or promote products derived
+ *     from this software without specific prior written permission.
+ *
+ *  THIS SOFTWARE IS PROVIDED ``AS IS'' AND ANY EXPRESS OR IMPLIED
+ *  WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF
+ *  MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+ *  DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
+ *  FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ *  CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ *  SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR
+ *  BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF
+ *  LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING
+ *  NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
+ *  SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#include <linux/module.h>
+#include <linux/seq_file.h>
+#include <linux/sched.h>
+#include <linux/slab.h>
+#include <linux/sunrpc/svc_xprt.h>
+#include <net/net_namespace.h>
+#include "idmap.h"
+#include "nfsd.h"
+#include "netns.h"
+#include "vfs.h"
+
+/*
+ * Turn off idmapping when using AUTH_SYS.
+ */
+static bool nfs4_disable_idmapping = true;
+module_param(nfs4_disable_idmapping, bool, 0644);
+MODULE_PARM_DESC(nfs4_disable_idmapping,
+		"Turn off server's NFSv4 idmapping when using 'sec=sys'");
+
+/*
+ * Cache entry
+ */
+
+/*
+ * XXX we know that IDMAP_NAMESZ < PAGE_SIZE, but it's ugly to rely on
+ * that.
+ */
+
+struct ent {
+	struct cache_head h;
+	int               type;		       /* User / Group */
+	u32               id;
+	char              name[IDMAP_NAMESZ];
+	char              authname[IDMAP_NAMESZ];
+	struct rcu_head	  rcu_head;
+};
+
+/* Common entry handling */
+
+#define ENT_HASHBITS          8
+#define ENT_HASHMAX           (1 << ENT_HASHBITS)
+
+static void
+ent_init(struct cache_head *cnew, struct cache_head *citm)
+{
+	struct ent *new = container_of(cnew, struct ent, h);
+	struct ent *itm = container_of(citm, struct ent, h);
+
+	new->id = itm->id;
+	new->type = itm->type;
+
+	strscpy(new->name, itm->name, sizeof(new->name));
+	strscpy(new->authname, itm->authname, sizeof(new->authname));
+}
+
+static void
+ent_put(struct kref *ref)
+{
+	struct ent *map = container_of(ref, struct ent, h.ref);
+	kfree_rcu(map, rcu_head);
+}
+
+static struct cache_head *
+ent_alloc(void)
+{
+	struct ent *e = kmalloc(sizeof(*e), GFP_KERNEL);
+	if (e)
+		return &e->h;
+	else
+		return NULL;
+}
+
+/*
+ * ID -> Name cache
+ */
+
+static uint32_t
+idtoname_hash(struct ent *ent)
+{
+	uint32_t hash;
+
+	hash = hash_str(ent->authname, ENT_HASHBITS);
+	hash = hash_long(hash ^ ent->id, ENT_HASHBITS);
+
+	/* Flip LSB for user/group */
+	if (ent->type == IDMAP_TYPE_GROUP)
+		hash ^= 1;
+
+	return hash;
+}
+
+static int
+idtoname_upcall(struct cache_detail *cd, struct cache_head *h)
+{
+	return sunrpc_cache_pipe_upcall_timeout(cd, h);
+}
+
+static void
+idtoname_request(struct cache_detail *cd, struct cache_head *ch, char **bpp,
+    int *blen)
+{
+ 	struct ent *ent = container_of(ch, struct ent, h);
+	char idstr[11];
+
+	qword_add(bpp, blen, ent->authname);
+	snprintf(idstr, sizeof(idstr), "%u", ent->id);
+	qword_add(bpp, blen, ent->type == IDMAP_TYPE_GROUP ? "group" : "user");
+	qword_add(bpp, blen, idstr);
+
+	(*bpp)[-1] = '\n';
+}
+
+static int
+idtoname_match(struct cache_head *ca, struct cache_head *cb)
+{
+	struct ent *a = container_of(ca, struct ent, h);
+	struct ent *b = container_of(cb, struct ent, h);
+
+	return (a->id == b->id && a->type == b->type &&
+	    strcmp(a->authname, b->authname) == 0);
+}
+
+static int
+idtoname_show(struct seq_file *m, struct cache_detail *cd, struct cache_head *h)
+{
+	struct ent *ent;
+
+	if (h == NULL) {
+		seq_puts(m, "#domain type id [name]\n");
+		return 0;
+	}
+	ent = container_of(h, struct ent, h);
+	seq_printf(m, "%s %s %u", ent->authname,
+			ent->type == IDMAP_TYPE_GROUP ? "group" : "user",
+			ent->id);
+	if (test_bit(CACHE_VALID, &h->flags))
+		seq_printf(m, " %s", ent->name);
+	seq_putc(m, '\n');
+	return 0;
+}
+
+static void
+warn_no_idmapd(struct cache_detail *detail, int has_died)
+{
+	printk("nfsd: nfsv4 idmapping failing: has idmapd %s?\n",
+			has_died ? "died" : "not been started");
+}
+
+
+static int         idtoname_parse(struct cache_detail *, char *, int);
+static struct ent *idtoname_lookup(struct cache_detail *, struct ent *);
+static struct ent *idtoname_update(struct cache_detail *, struct ent *,
+				   struct ent *);
+
+static const struct cache_detail idtoname_cache_template = {
+	.owner		= THIS_MODULE,
+	.hash_size	= ENT_HASHMAX,
+	.name		= "nfs4.idtoname",
+	.cache_put	= ent_put,
+	.cache_upcall	= idtoname_upcall,
+	.cache_request	= idtoname_request,
+	.cache_parse	= idtoname_parse,
+	.cache_show	= idtoname_show,
+	.warn_no_listener = warn_no_idmapd,
+	.match		= idtoname_match,
+	.init		= ent_init,
+	.update		= ent_init,
+	.alloc		= ent_alloc,
+};
+
+static int
+idtoname_parse(struct cache_detail *cd, char *buf, int buflen)
+{
+	struct ent ent, *res;
+	char *buf1, *bp;
+	int len;
+	int error = -EINVAL;
+
+	if (buf[buflen - 1] != '\n')
+		return (-EINVAL);
+	buf[buflen - 1]= '\0';
+
+	buf1 = kmalloc(PAGE_SIZE, GFP_KERNEL);
+	if (buf1 == NULL)
+		return (-ENOMEM);
+
+	memset(&ent, 0, sizeof(ent));
+
+	/* Authentication name */
+	len = qword_get(&buf, buf1, PAGE_SIZE);
+	if (len <= 0 || len >= IDMAP_NAMESZ)
+		goto out;
+	memcpy(ent.authname, buf1, sizeof(ent.authname));
+
+	/* Type */
+	if (qword_get(&buf, buf1, PAGE_SIZE) <= 0)
+		goto out;
+	ent.type = strcmp(buf1, "user") == 0 ?
+		IDMAP_TYPE_USER : IDMAP_TYPE_GROUP;
+
+	/* ID */
+	if (qword_get(&buf, buf1, PAGE_SIZE) <= 0)
+		goto out;
+	ent.id = simple_strtoul(buf1, &bp, 10);
+	if (bp == buf1)
+		goto out;
+
+	/* expiry */
+	ent.h.expiry_time = get_expiry(&buf);
+	if (ent.h.expiry_time == 0)
+		goto out;
+
+	error = -ENOMEM;
+	res = idtoname_lookup(cd, &ent);
+	if (!res)
+		goto out;
+
+	/* Name */
+	error = -EINVAL;
+	len = qword_get(&buf, buf1, PAGE_SIZE);
+	if (len < 0 || len >= IDMAP_NAMESZ)
+		goto out;
+	if (len == 0)
+		set_bit(CACHE_NEGATIVE, &ent.h.flags);
+	else
+		memcpy(ent.name, buf1, sizeof(ent.name));
+	error = -ENOMEM;
+	res = idtoname_update(cd, &ent, res);
+	if (res == NULL)
+		goto out;
+
+	cache_put(&res->h, cd);
+	error = 0;
+out:
+	kfree(buf1);
+	return error;
+}
+
+static struct ent *
+idtoname_lookup(struct cache_detail *cd, struct ent *item)
+{
+	struct cache_head *ch = sunrpc_cache_lookup_rcu(cd, &item->h,
+							idtoname_hash(item));
+	if (ch)
+		return container_of(ch, struct ent, h);
+	else
+		return NULL;
+}
+
+static struct ent *
+idtoname_update(struct cache_detail *cd, struct ent *new, struct ent *old)
+{
+	struct cache_head *ch = sunrpc_cache_update(cd, &new->h, &old->h,
+						    idtoname_hash(new));
+	if (ch)
+		return container_of(ch, struct ent, h);
+	else
+		return NULL;
+}
+
+
+/*
+ * Name -> ID cache
+ */
+
+static inline int
+nametoid_hash(struct ent *ent)
+{
+	return hash_str(ent->name, ENT_HASHBITS);
+}
+
+static int
+nametoid_upcall(struct cache_detail *cd, struct cache_head *h)
+{
+	return sunrpc_cache_pipe_upcall_timeout(cd, h);
+}
+
+static void
+nametoid_request(struct cache_detail *cd, struct cache_head *ch, char **bpp,
+    int *blen)
+{
+ 	struct ent *ent = container_of(ch, struct ent, h);
+
+	qword_add(bpp, blen, ent->authname);
+	qword_add(bpp, blen, ent->type == IDMAP_TYPE_GROUP ? "group" : "user");
+	qword_add(bpp, blen, ent->name);
+
+	(*bpp)[-1] = '\n';
+}
+
+static int
+nametoid_match(struct cache_head *ca, struct cache_head *cb)
+{
+	struct ent *a = container_of(ca, struct ent, h);
+	struct ent *b = container_of(cb, struct ent, h);
+
+	return (a->type == b->type && strcmp(a->name, b->name) == 0 &&
+	    strcmp(a->authname, b->authname) == 0);
+}
+
+static int
+nametoid_show(struct seq_file *m, struct cache_detail *cd, struct cache_head *h)
+{
+	struct ent *ent;
+
+	if (h == NULL) {
+		seq_puts(m, "#domain type name [id]\n");
+		return 0;
+	}
+	ent = container_of(h, struct ent, h);
+	seq_printf(m, "%s %s %s", ent->authname,
+			ent->type == IDMAP_TYPE_GROUP ? "group" : "user",
+			ent->name);
+	if (test_bit(CACHE_VALID, &h->flags))
+		seq_printf(m, " %u", ent->id);
+	seq_putc(m, '\n');
+	return 0;
+}
+
+static struct ent *nametoid_lookup(struct cache_detail *, struct ent *);
+static struct ent *nametoid_update(struct cache_detail *, struct ent *,
+				   struct ent *);
+static int         nametoid_parse(struct cache_detail *, char *, int);
+
+static const struct cache_detail nametoid_cache_template = {
+	.owner		= THIS_MODULE,
+	.hash_size	= ENT_HASHMAX,
+	.name		= "nfs4.nametoid",
+	.cache_put	= ent_put,
+	.cache_upcall	= nametoid_upcall,
+	.cache_request	= nametoid_request,
+	.cache_parse	= nametoid_parse,
+	.cache_show	= nametoid_show,
+	.warn_no_listener = warn_no_idmapd,
+	.match		= nametoid_match,
+	.init		= ent_init,
+	.update		= ent_init,
+	.alloc		= ent_alloc,
+};
+
+static int
+nametoid_parse(struct cache_detail *cd, char *buf, int buflen)
+{
+	struct ent ent, *res;
+	char *buf1;
+	int len, error = -EINVAL;
+
+	if (buf[buflen - 1] != '\n')
+		return (-EINVAL);
+	buf[buflen - 1]= '\0';
+
+	buf1 = kmalloc(PAGE_SIZE, GFP_KERNEL);
+	if (buf1 == NULL)
+		return (-ENOMEM);
+
+	memset(&ent, 0, sizeof(ent));
+
+	/* Authentication name */
+	len = qword_get(&buf, buf1, PAGE_SIZE);
+	if (len <= 0 || len >= IDMAP_NAMESZ)
+		goto out;
+	memcpy(ent.authname, buf1, sizeof(ent.authname));
+
+	/* Type */
+	if (qword_get(&buf, buf1, PAGE_SIZE) <= 0)
+		goto out;
+	ent.type = strcmp(buf1, "user") == 0 ?
+		IDMAP_TYPE_USER : IDMAP_TYPE_GROUP;
+
+	/* Name */
+	len = qword_get(&buf, buf1, PAGE_SIZE);
+	if (len <= 0 || len >= IDMAP_NAMESZ)
+		goto out;
+	memcpy(ent.name, buf1, sizeof(ent.name));
+
+	/* expiry */
+	ent.h.expiry_time = get_expiry(&buf);
+	if (ent.h.expiry_time == 0)
+		goto out;
+
+	/* ID */
+	error = get_int(&buf, &ent.id);
+	if (error == -EINVAL)
+		goto out;
+	if (error == -ENOENT)
+		set_bit(CACHE_NEGATIVE, &ent.h.flags);
+
+	error = -ENOMEM;
+	res = nametoid_lookup(cd, &ent);
+	if (res == NULL)
+		goto out;
+	res = nametoid_update(cd, &ent, res);
+	if (res == NULL)
+		goto out;
+
+	cache_put(&res->h, cd);
+	error = 0;
+out:
+	kfree(buf1);
+	return (error);
+}
+
+
+static struct ent *
+nametoid_lookup(struct cache_detail *cd, struct ent *item)
+{
+	struct cache_head *ch = sunrpc_cache_lookup_rcu(cd, &item->h,
+							nametoid_hash(item));
+	if (ch)
+		return container_of(ch, struct ent, h);
+	else
+		return NULL;
+}
+
+static struct ent *
+nametoid_update(struct cache_detail *cd, struct ent *new, struct ent *old)
+{
+	struct cache_head *ch = sunrpc_cache_update(cd, &new->h, &old->h,
+						    nametoid_hash(new));
+	if (ch)
+		return container_of(ch, struct ent, h);
+	else
+		return NULL;
+}
+
+/*
+ * Exported API
+ */
+
+int
+nfsd_idmap_init(struct net *net)
+{
+	int rv;
+	struct nfsd_net *nn = net_generic(net, nfsd_net_id);
+
+	nn->idtoname_cache = cache_create_net(&idtoname_cache_template, net);
+	if (IS_ERR(nn->idtoname_cache))
+		return PTR_ERR(nn->idtoname_cache);
+	rv = cache_register_net(nn->idtoname_cache, net);
+	if (rv)
+		goto destroy_idtoname_cache;
+	nn->nametoid_cache = cache_create_net(&nametoid_cache_template, net);
+	if (IS_ERR(nn->nametoid_cache)) {
+		rv = PTR_ERR(nn->nametoid_cache);
+		goto unregister_idtoname_cache;
+	}
+	rv = cache_register_net(nn->nametoid_cache, net);
+	if (rv)
+		goto destroy_nametoid_cache;
+	return 0;
+
+destroy_nametoid_cache:
+	cache_destroy_net(nn->nametoid_cache, net);
+unregister_idtoname_cache:
+	cache_unregister_net(nn->idtoname_cache, net);
+destroy_idtoname_cache:
+	cache_destroy_net(nn->idtoname_cache, net);
+	return rv;
+}
+
+void
+nfsd_idmap_shutdown(struct net *net)
+{
+	struct nfsd_net *nn = net_generic(net, nfsd_net_id);
+
+	cache_unregister_net(nn->idtoname_cache, net);
+	cache_unregister_net(nn->nametoid_cache, net);
+	cache_destroy_net(nn->idtoname_cache, net);
+	cache_destroy_net(nn->nametoid_cache, net);
+}
+
+static int
+idmap_lookup(struct svc_rqst *rqstp,
+		struct ent *(*lookup_fn)(struct cache_detail *, struct ent *),
+		struct ent *key, struct cache_detail *detail, struct ent **item)
+{
+	int ret;
+
+	*item = lookup_fn(detail, key);
+	if (!*item)
+		return -ENOMEM;
+ retry:
+	ret = cache_check(detail, &(*item)->h, &rqstp->rq_chandle);
+
+	if (ret == -ETIMEDOUT) {
+		struct ent *prev_item = *item;
+		*item = lookup_fn(detail, key);
+		if (*item != prev_item)
+			goto retry;
+		cache_put(&(*item)->h, detail);
+	}
+	return ret;
+}
+
+static char *
+rqst_authname(struct svc_rqst *rqstp)
+{
+	struct auth_domain *clp;
+
+	clp = rqstp->rq_gssclient ? rqstp->rq_gssclient : rqstp->rq_client;
+	return clp->name;
+}
+
+static __be32
+idmap_name_to_id(struct svc_rqst *rqstp, int type, const char *name, u32 namelen,
+		u32 *id)
+{
+	struct ent *item, key = {
+		.type = type,
+	};
+	int ret;
+	struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id);
+
+	if (namelen + 1 > sizeof(key.name))
+		return nfserr_badowner;
+	memcpy(key.name, name, namelen);
+	key.name[namelen] = '\0';
+	strscpy(key.authname, rqst_authname(rqstp), sizeof(key.authname));
+	ret = idmap_lookup(rqstp, nametoid_lookup, &key, nn->nametoid_cache, &item);
+	if (ret == -ENOENT)
+		return nfserr_badowner;
+	if (ret)
+		return nfserrno(ret);
+	*id = item->id;
+	cache_put(&item->h, nn->nametoid_cache);
+	return 0;
+}
+
+static __be32 encode_ascii_id(struct xdr_stream *xdr, u32 id)
+{
+	char buf[11];
+	int len;
+	__be32 *p;
+
+	len = sprintf(buf, "%u", id);
+	p = xdr_reserve_space(xdr, len + 4);
+	if (!p)
+		return nfserr_resource;
+	p = xdr_encode_opaque(p, buf, len);
+	return 0;
+}
+
+static __be32 idmap_id_to_name(struct xdr_stream *xdr,
+			       struct svc_rqst *rqstp, int type, u32 id)
+{
+	struct ent *item, key = {
+		.id = id,
+		.type = type,
+	};
+	__be32 *p;
+	int ret;
+	struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id);
+
+	strscpy(key.authname, rqst_authname(rqstp), sizeof(key.authname));
+	ret = idmap_lookup(rqstp, idtoname_lookup, &key, nn->idtoname_cache, &item);
+	if (ret == -ENOENT)
+		return encode_ascii_id(xdr, id);
+	if (ret)
+		return nfserrno(ret);
+	ret = strlen(item->name);
+	WARN_ON_ONCE(ret > IDMAP_NAMESZ);
+	p = xdr_reserve_space(xdr, ret + 4);
+	if (!p)
+		return nfserr_resource;
+	p = xdr_encode_opaque(p, item->name, ret);
+	cache_put(&item->h, nn->idtoname_cache);
+	return 0;
+}
+
+static bool
+numeric_name_to_id(struct svc_rqst *rqstp, int type, const char *name, u32 namelen, u32 *id)
+{
+	int ret;
+	char buf[11];
+
+	if (namelen + 1 > sizeof(buf))
+		/* too long to represent a 32-bit id: */
+		return false;
+	/* Just to make sure it's null-terminated: */
+	memcpy(buf, name, namelen);
+	buf[namelen] = '\0';
+	ret = kstrtouint(buf, 10, id);
+	return ret == 0;
+}
+
+static __be32
+do_name_to_id(struct svc_rqst *rqstp, int type, const char *name, u32 namelen, u32 *id)
+{
+	if (nfs4_disable_idmapping && rqstp->rq_cred.cr_flavor < RPC_AUTH_GSS)
+		if (numeric_name_to_id(rqstp, type, name, namelen, id))
+			return 0;
+		/*
+		 * otherwise, fall through and try idmapping, for
+		 * backwards compatibility with clients sending names:
+		 */
+	return idmap_name_to_id(rqstp, type, name, namelen, id);
+}
+
+static __be32 encode_name_from_id(struct xdr_stream *xdr,
+				  struct svc_rqst *rqstp, int type, u32 id)
+{
+	if (nfs4_disable_idmapping && rqstp->rq_cred.cr_flavor < RPC_AUTH_GSS)
+		return encode_ascii_id(xdr, id);
+	return idmap_id_to_name(xdr, rqstp, type, id);
+}
+
+__be32
+nfsd_map_name_to_uid(struct svc_rqst *rqstp, const char *name, size_t namelen,
+		kuid_t *uid)
+{
+	__be32 status;
+	u32 id = -1;
+
+	if (name == NULL || namelen == 0)
+		return nfserr_inval;
+
+	status = do_name_to_id(rqstp, IDMAP_TYPE_USER, name, namelen, &id);
+	*uid = make_kuid(nfsd_user_namespace(rqstp), id);
+	if (!uid_valid(*uid))
+		status = nfserr_badowner;
+	return status;
+}
+
+__be32
+nfsd_map_name_to_gid(struct svc_rqst *rqstp, const char *name, size_t namelen,
+		kgid_t *gid)
+{
+	__be32 status;
+	u32 id = -1;
+
+	if (name == NULL || namelen == 0)
+		return nfserr_inval;
+
+	status = do_name_to_id(rqstp, IDMAP_TYPE_GROUP, name, namelen, &id);
+	*gid = make_kgid(nfsd_user_namespace(rqstp), id);
+	if (!gid_valid(*gid))
+		status = nfserr_badowner;
+	return status;
+}
+
+__be32 nfsd4_encode_user(struct xdr_stream *xdr, struct svc_rqst *rqstp,
+			 kuid_t uid)
+{
+	u32 id = from_kuid_munged(nfsd_user_namespace(rqstp), uid);
+	return encode_name_from_id(xdr, rqstp, IDMAP_TYPE_USER, id);
+}
+
+__be32 nfsd4_encode_group(struct xdr_stream *xdr, struct svc_rqst *rqstp,
+			  kgid_t gid)
+{
+	u32 id = from_kgid_munged(nfsd_user_namespace(rqstp), gid);
+	return encode_name_from_id(xdr, rqstp, IDMAP_TYPE_GROUP, id);
+}