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, 853 insertions, 0 deletions

diff --git a/fs/nfsd/nfs4acl.c b/fs/nfsd/nfs4acl.c
new file mode 100644
index 000000000..518203821
--- /dev/null
+++ b/fs/nfsd/nfs4acl.c
@@ -0,0 +1,853 @@
+/*
+ *  Common NFSv4 ACL handling code.
+ *
+ *  Copyright (c) 2002, 2003 The Regents of the University of Michigan.
+ *  All rights reserved.
+ *
+ *  Marius Aamodt Eriksen <marius@umich.edu>
+ *  Jeff Sedlak <jsedlak@umich.edu>
+ *  J. Bruce Fields <bfields@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/fs.h>
+#include <linux/slab.h>
+#include <linux/posix_acl.h>
+
+#include "nfsfh.h"
+#include "nfsd.h"
+#include "acl.h"
+#include "vfs.h"
+
+#define NFS4_ACL_TYPE_DEFAULT	0x01
+#define NFS4_ACL_DIR		0x02
+#define NFS4_ACL_OWNER		0x04
+
+/* mode bit translations: */
+#define NFS4_READ_MODE (NFS4_ACE_READ_DATA)
+#define NFS4_WRITE_MODE (NFS4_ACE_WRITE_DATA | NFS4_ACE_APPEND_DATA)
+#define NFS4_EXECUTE_MODE NFS4_ACE_EXECUTE
+#define NFS4_ANYONE_MODE (NFS4_ACE_READ_ATTRIBUTES | NFS4_ACE_READ_ACL | NFS4_ACE_SYNCHRONIZE)
+#define NFS4_OWNER_MODE (NFS4_ACE_WRITE_ATTRIBUTES | NFS4_ACE_WRITE_ACL)
+
+/* flags used to simulate posix default ACLs */
+#define NFS4_INHERITANCE_FLAGS (NFS4_ACE_FILE_INHERIT_ACE \
+		| NFS4_ACE_DIRECTORY_INHERIT_ACE)
+
+#define NFS4_SUPPORTED_FLAGS (NFS4_INHERITANCE_FLAGS \
+		| NFS4_ACE_INHERIT_ONLY_ACE \
+		| NFS4_ACE_IDENTIFIER_GROUP)
+
+static u32
+mask_from_posix(unsigned short perm, unsigned int flags)
+{
+	int mask = NFS4_ANYONE_MODE;
+
+	if (flags & NFS4_ACL_OWNER)
+		mask |= NFS4_OWNER_MODE;
+	if (perm & ACL_READ)
+		mask |= NFS4_READ_MODE;
+	if (perm & ACL_WRITE)
+		mask |= NFS4_WRITE_MODE;
+	if ((perm & ACL_WRITE) && (flags & NFS4_ACL_DIR))
+		mask |= NFS4_ACE_DELETE_CHILD;
+	if (perm & ACL_EXECUTE)
+		mask |= NFS4_EXECUTE_MODE;
+	return mask;
+}
+
+static u32
+deny_mask_from_posix(unsigned short perm, u32 flags)
+{
+	u32 mask = 0;
+
+	if (perm & ACL_READ)
+		mask |= NFS4_READ_MODE;
+	if (perm & ACL_WRITE)
+		mask |= NFS4_WRITE_MODE;
+	if ((perm & ACL_WRITE) && (flags & NFS4_ACL_DIR))
+		mask |= NFS4_ACE_DELETE_CHILD;
+	if (perm & ACL_EXECUTE)
+		mask |= NFS4_EXECUTE_MODE;
+	return mask;
+}
+
+/* XXX: modify functions to return NFS errors; they're only ever
+ * used by nfs code, after all.... */
+
+/* We only map from NFSv4 to POSIX ACLs when setting ACLs, when we err on the
+ * side of being more restrictive, so the mode bit mapping below is
+ * pessimistic.  An optimistic version would be needed to handle DENY's,
+ * but we expect to coalesce all ALLOWs and DENYs before mapping to mode
+ * bits. */
+
+static void
+low_mode_from_nfs4(u32 perm, unsigned short *mode, unsigned int flags)
+{
+	u32 write_mode = NFS4_WRITE_MODE;
+
+	if (flags & NFS4_ACL_DIR)
+		write_mode |= NFS4_ACE_DELETE_CHILD;
+	*mode = 0;
+	if ((perm & NFS4_READ_MODE) == NFS4_READ_MODE)
+		*mode |= ACL_READ;
+	if ((perm & write_mode) == write_mode)
+		*mode |= ACL_WRITE;
+	if ((perm & NFS4_EXECUTE_MODE) == NFS4_EXECUTE_MODE)
+		*mode |= ACL_EXECUTE;
+}
+
+static short ace2type(struct nfs4_ace *);
+static void _posix_to_nfsv4_one(struct posix_acl *, struct nfs4_acl *,
+				unsigned int);
+
+int
+nfsd4_get_nfs4_acl(struct svc_rqst *rqstp, struct dentry *dentry,
+		struct nfs4_acl **acl)
+{
+	struct inode *inode = d_inode(dentry);
+	int error = 0;
+	struct posix_acl *pacl = NULL, *dpacl = NULL;
+	unsigned int flags = 0;
+	int size = 0;
+
+	pacl = get_inode_acl(inode, ACL_TYPE_ACCESS);
+	if (!pacl)
+		pacl = posix_acl_from_mode(inode->i_mode, GFP_KERNEL);
+
+	if (IS_ERR(pacl))
+		return PTR_ERR(pacl);
+
+	/* allocate for worst case: one (deny, allow) pair each: */
+	size += 2 * pacl->a_count;
+
+	if (S_ISDIR(inode->i_mode)) {
+		flags = NFS4_ACL_DIR;
+		dpacl = get_inode_acl(inode, ACL_TYPE_DEFAULT);
+		if (IS_ERR(dpacl)) {
+			error = PTR_ERR(dpacl);
+			goto rel_pacl;
+		}
+
+		if (dpacl)
+			size += 2 * dpacl->a_count;
+	}
+
+	*acl = kmalloc(nfs4_acl_bytes(size), GFP_KERNEL);
+	if (*acl == NULL) {
+		error = -ENOMEM;
+		goto out;
+	}
+	(*acl)->naces = 0;
+
+	_posix_to_nfsv4_one(pacl, *acl, flags & ~NFS4_ACL_TYPE_DEFAULT);
+
+	if (dpacl)
+		_posix_to_nfsv4_one(dpacl, *acl, flags | NFS4_ACL_TYPE_DEFAULT);
+
+out:
+	posix_acl_release(dpacl);
+rel_pacl:
+	posix_acl_release(pacl);
+	return error;
+}
+
+struct posix_acl_summary {
+	unsigned short owner;
+	unsigned short users;
+	unsigned short group;
+	unsigned short groups;
+	unsigned short other;
+	unsigned short mask;
+};
+
+static void
+summarize_posix_acl(struct posix_acl *acl, struct posix_acl_summary *pas)
+{
+	struct posix_acl_entry *pa, *pe;
+
+	/*
+	 * Only pas.users and pas.groups need initialization; previous
+	 * posix_acl_valid() calls ensure that the other fields will be
+	 * initialized in the following loop.  But, just to placate gcc:
+	 */
+	memset(pas, 0, sizeof(*pas));
+	pas->mask = 07;
+
+	pe = acl->a_entries + acl->a_count;
+
+	FOREACH_ACL_ENTRY(pa, acl, pe) {
+		switch (pa->e_tag) {
+			case ACL_USER_OBJ:
+				pas->owner = pa->e_perm;
+				break;
+			case ACL_GROUP_OBJ:
+				pas->group = pa->e_perm;
+				break;
+			case ACL_USER:
+				pas->users |= pa->e_perm;
+				break;
+			case ACL_GROUP:
+				pas->groups |= pa->e_perm;
+				break;
+			case ACL_OTHER:
+				pas->other = pa->e_perm;
+				break;
+			case ACL_MASK:
+				pas->mask = pa->e_perm;
+				break;
+		}
+	}
+	/* We'll only care about effective permissions: */
+	pas->users &= pas->mask;
+	pas->group &= pas->mask;
+	pas->groups &= pas->mask;
+}
+
+/* We assume the acl has been verified with posix_acl_valid. */
+static void
+_posix_to_nfsv4_one(struct posix_acl *pacl, struct nfs4_acl *acl,
+						unsigned int flags)
+{
+	struct posix_acl_entry *pa, *group_owner_entry;
+	struct nfs4_ace *ace;
+	struct posix_acl_summary pas;
+	unsigned short deny;
+	int eflag = ((flags & NFS4_ACL_TYPE_DEFAULT) ?
+		NFS4_INHERITANCE_FLAGS | NFS4_ACE_INHERIT_ONLY_ACE : 0);
+
+	BUG_ON(pacl->a_count < 3);
+	summarize_posix_acl(pacl, &pas);
+
+	pa = pacl->a_entries;
+	ace = acl->aces + acl->naces;
+
+	/* We could deny everything not granted by the owner: */
+	deny = ~pas.owner;
+	/*
+	 * but it is equivalent (and simpler) to deny only what is not
+	 * granted by later entries:
+	 */
+	deny &= pas.users | pas.group | pas.groups | pas.other;
+	if (deny) {
+		ace->type = NFS4_ACE_ACCESS_DENIED_ACE_TYPE;
+		ace->flag = eflag;
+		ace->access_mask = deny_mask_from_posix(deny, flags);
+		ace->whotype = NFS4_ACL_WHO_OWNER;
+		ace++;
+		acl->naces++;
+	}
+
+	ace->type = NFS4_ACE_ACCESS_ALLOWED_ACE_TYPE;
+	ace->flag = eflag;
+	ace->access_mask = mask_from_posix(pa->e_perm, flags | NFS4_ACL_OWNER);
+	ace->whotype = NFS4_ACL_WHO_OWNER;
+	ace++;
+	acl->naces++;
+	pa++;
+
+	while (pa->e_tag == ACL_USER) {
+		deny = ~(pa->e_perm & pas.mask);
+		deny &= pas.groups | pas.group | pas.other;
+		if (deny) {
+			ace->type = NFS4_ACE_ACCESS_DENIED_ACE_TYPE;
+			ace->flag = eflag;
+			ace->access_mask = deny_mask_from_posix(deny, flags);
+			ace->whotype = NFS4_ACL_WHO_NAMED;
+			ace->who_uid = pa->e_uid;
+			ace++;
+			acl->naces++;
+		}
+		ace->type = NFS4_ACE_ACCESS_ALLOWED_ACE_TYPE;
+		ace->flag = eflag;
+		ace->access_mask = mask_from_posix(pa->e_perm & pas.mask,
+						   flags);
+		ace->whotype = NFS4_ACL_WHO_NAMED;
+		ace->who_uid = pa->e_uid;
+		ace++;
+		acl->naces++;
+		pa++;
+	}
+
+	/* In the case of groups, we apply allow ACEs first, then deny ACEs,
+	 * since a user can be in more than one group.  */
+
+	/* allow ACEs */
+
+	group_owner_entry = pa;
+
+	ace->type = NFS4_ACE_ACCESS_ALLOWED_ACE_TYPE;
+	ace->flag = eflag;
+	ace->access_mask = mask_from_posix(pas.group, flags);
+	ace->whotype = NFS4_ACL_WHO_GROUP;
+	ace++;
+	acl->naces++;
+	pa++;
+
+	while (pa->e_tag == ACL_GROUP) {
+		ace->type = NFS4_ACE_ACCESS_ALLOWED_ACE_TYPE;
+		ace->flag = eflag | NFS4_ACE_IDENTIFIER_GROUP;
+		ace->access_mask = mask_from_posix(pa->e_perm & pas.mask,
+						   flags);
+		ace->whotype = NFS4_ACL_WHO_NAMED;
+		ace->who_gid = pa->e_gid;
+		ace++;
+		acl->naces++;
+		pa++;
+	}
+
+	/* deny ACEs */
+
+	pa = group_owner_entry;
+
+	deny = ~pas.group & pas.other;
+	if (deny) {
+		ace->type = NFS4_ACE_ACCESS_DENIED_ACE_TYPE;
+		ace->flag = eflag;
+		ace->access_mask = deny_mask_from_posix(deny, flags);
+		ace->whotype = NFS4_ACL_WHO_GROUP;
+		ace++;
+		acl->naces++;
+	}
+	pa++;
+
+	while (pa->e_tag == ACL_GROUP) {
+		deny = ~(pa->e_perm & pas.mask);
+		deny &= pas.other;
+		if (deny) {
+			ace->type = NFS4_ACE_ACCESS_DENIED_ACE_TYPE;
+			ace->flag = eflag | NFS4_ACE_IDENTIFIER_GROUP;
+			ace->access_mask = deny_mask_from_posix(deny, flags);
+			ace->whotype = NFS4_ACL_WHO_NAMED;
+			ace->who_gid = pa->e_gid;
+			ace++;
+			acl->naces++;
+		}
+		pa++;
+	}
+
+	if (pa->e_tag == ACL_MASK)
+		pa++;
+	ace->type = NFS4_ACE_ACCESS_ALLOWED_ACE_TYPE;
+	ace->flag = eflag;
+	ace->access_mask = mask_from_posix(pa->e_perm, flags);
+	ace->whotype = NFS4_ACL_WHO_EVERYONE;
+	acl->naces++;
+}
+
+static bool
+pace_gt(struct posix_acl_entry *pace1, struct posix_acl_entry *pace2)
+{
+	if (pace1->e_tag != pace2->e_tag)
+		return pace1->e_tag > pace2->e_tag;
+	if (pace1->e_tag == ACL_USER)
+		return uid_gt(pace1->e_uid, pace2->e_uid);
+	if (pace1->e_tag == ACL_GROUP)
+		return gid_gt(pace1->e_gid, pace2->e_gid);
+	return false;
+}
+
+static void
+sort_pacl_range(struct posix_acl *pacl, int start, int end) {
+	int sorted = 0, i;
+
+	/* We just do a bubble sort; easy to do in place, and we're not
+	 * expecting acl's to be long enough to justify anything more. */
+	while (!sorted) {
+		sorted = 1;
+		for (i = start; i < end; i++) {
+			if (pace_gt(&pacl->a_entries[i],
+				    &pacl->a_entries[i+1])) {
+				sorted = 0;
+				swap(pacl->a_entries[i],
+				     pacl->a_entries[i + 1]);
+			}
+		}
+	}
+}
+
+static void
+sort_pacl(struct posix_acl *pacl)
+{
+	/* posix_acl_valid requires that users and groups be in order
+	 * by uid/gid. */
+	int i, j;
+
+	/* no users or groups */
+	if (!pacl || pacl->a_count <= 4)
+		return;
+
+	i = 1;
+	while (pacl->a_entries[i].e_tag == ACL_USER)
+		i++;
+	sort_pacl_range(pacl, 1, i-1);
+
+	BUG_ON(pacl->a_entries[i].e_tag != ACL_GROUP_OBJ);
+	j = ++i;
+	while (pacl->a_entries[j].e_tag == ACL_GROUP)
+		j++;
+	sort_pacl_range(pacl, i, j-1);
+	return;
+}
+
+/*
+ * While processing the NFSv4 ACE, this maintains bitmasks representing
+ * which permission bits have been allowed and which denied to a given
+ * entity: */
+struct posix_ace_state {
+	u32 allow;
+	u32 deny;
+};
+
+struct posix_user_ace_state {
+	union {
+		kuid_t uid;
+		kgid_t gid;
+	};
+	struct posix_ace_state perms;
+};
+
+struct posix_ace_state_array {
+	int n;
+	struct posix_user_ace_state aces[];
+};
+
+/*
+ * While processing the NFSv4 ACE, this maintains the partial permissions
+ * calculated so far: */
+
+struct posix_acl_state {
+	int empty;
+	struct posix_ace_state owner;
+	struct posix_ace_state group;
+	struct posix_ace_state other;
+	struct posix_ace_state everyone;
+	struct posix_ace_state mask; /* Deny unused in this case */
+	struct posix_ace_state_array *users;
+	struct posix_ace_state_array *groups;
+};
+
+static int
+init_state(struct posix_acl_state *state, int cnt)
+{
+	int alloc;
+
+	memset(state, 0, sizeof(struct posix_acl_state));
+	state->empty = 1;
+	/*
+	 * In the worst case, each individual acl could be for a distinct
+	 * named user or group, but we don't know which, so we allocate
+	 * enough space for either:
+	 */
+	alloc = sizeof(struct posix_ace_state_array)
+		+ cnt*sizeof(struct posix_user_ace_state);
+	state->users = kzalloc(alloc, GFP_KERNEL);
+	if (!state->users)
+		return -ENOMEM;
+	state->groups = kzalloc(alloc, GFP_KERNEL);
+	if (!state->groups) {
+		kfree(state->users);
+		return -ENOMEM;
+	}
+	return 0;
+}
+
+static void
+free_state(struct posix_acl_state *state) {
+	kfree(state->users);
+	kfree(state->groups);
+}
+
+static inline void add_to_mask(struct posix_acl_state *state, struct posix_ace_state *astate)
+{
+	state->mask.allow |= astate->allow;
+}
+
+static struct posix_acl *
+posix_state_to_acl(struct posix_acl_state *state, unsigned int flags)
+{
+	struct posix_acl_entry *pace;
+	struct posix_acl *pacl;
+	int nace;
+	int i;
+
+	/*
+	 * ACLs with no ACEs are treated differently in the inheritable
+	 * and effective cases: when there are no inheritable ACEs,
+	 * calls ->set_acl with a NULL ACL structure.
+	 */
+	if (state->empty && (flags & NFS4_ACL_TYPE_DEFAULT))
+		return NULL;
+
+	/*
+	 * When there are no effective ACEs, the following will end
+	 * up setting a 3-element effective posix ACL with all
+	 * permissions zero.
+	 */
+	if (!state->users->n && !state->groups->n)
+		nace = 3;
+	else /* Note we also include a MASK ACE in this case: */
+		nace = 4 + state->users->n + state->groups->n;
+	pacl = posix_acl_alloc(nace, GFP_KERNEL);
+	if (!pacl)
+		return ERR_PTR(-ENOMEM);
+
+	pace = pacl->a_entries;
+	pace->e_tag = ACL_USER_OBJ;
+	low_mode_from_nfs4(state->owner.allow, &pace->e_perm, flags);
+
+	for (i=0; i < state->users->n; i++) {
+		pace++;
+		pace->e_tag = ACL_USER;
+		low_mode_from_nfs4(state->users->aces[i].perms.allow,
+					&pace->e_perm, flags);
+		pace->e_uid = state->users->aces[i].uid;
+		add_to_mask(state, &state->users->aces[i].perms);
+	}
+
+	pace++;
+	pace->e_tag = ACL_GROUP_OBJ;
+	low_mode_from_nfs4(state->group.allow, &pace->e_perm, flags);
+	add_to_mask(state, &state->group);
+
+	for (i=0; i < state->groups->n; i++) {
+		pace++;
+		pace->e_tag = ACL_GROUP;
+		low_mode_from_nfs4(state->groups->aces[i].perms.allow,
+					&pace->e_perm, flags);
+		pace->e_gid = state->groups->aces[i].gid;
+		add_to_mask(state, &state->groups->aces[i].perms);
+	}
+
+	if (state->users->n || state->groups->n) {
+		pace++;
+		pace->e_tag = ACL_MASK;
+		low_mode_from_nfs4(state->mask.allow, &pace->e_perm, flags);
+	}
+
+	pace++;
+	pace->e_tag = ACL_OTHER;
+	low_mode_from_nfs4(state->other.allow, &pace->e_perm, flags);
+
+	return pacl;
+}
+
+static inline void allow_bits(struct posix_ace_state *astate, u32 mask)
+{
+	/* Allow all bits in the mask not already denied: */
+	astate->allow |= mask & ~astate->deny;
+}
+
+static inline void deny_bits(struct posix_ace_state *astate, u32 mask)
+{
+	/* Deny all bits in the mask not already allowed: */
+	astate->deny |= mask & ~astate->allow;
+}
+
+static int find_uid(struct posix_acl_state *state, kuid_t uid)
+{
+	struct posix_ace_state_array *a = state->users;
+	int i;
+
+	for (i = 0; i < a->n; i++)
+		if (uid_eq(a->aces[i].uid, uid))
+			return i;
+	/* Not found: */
+	a->n++;
+	a->aces[i].uid = uid;
+	a->aces[i].perms.allow = state->everyone.allow;
+	a->aces[i].perms.deny  = state->everyone.deny;
+
+	return i;
+}
+
+static int find_gid(struct posix_acl_state *state, kgid_t gid)
+{
+	struct posix_ace_state_array *a = state->groups;
+	int i;
+
+	for (i = 0; i < a->n; i++)
+		if (gid_eq(a->aces[i].gid, gid))
+			return i;
+	/* Not found: */
+	a->n++;
+	a->aces[i].gid = gid;
+	a->aces[i].perms.allow = state->everyone.allow;
+	a->aces[i].perms.deny  = state->everyone.deny;
+
+	return i;
+}
+
+static void deny_bits_array(struct posix_ace_state_array *a, u32 mask)
+{
+	int i;
+
+	for (i=0; i < a->n; i++)
+		deny_bits(&a->aces[i].perms, mask);
+}
+
+static void allow_bits_array(struct posix_ace_state_array *a, u32 mask)
+{
+	int i;
+
+	for (i=0; i < a->n; i++)
+		allow_bits(&a->aces[i].perms, mask);
+}
+
+static void process_one_v4_ace(struct posix_acl_state *state,
+				struct nfs4_ace *ace)
+{
+	u32 mask = ace->access_mask;
+	int i;
+
+	state->empty = 0;
+
+	switch (ace2type(ace)) {
+	case ACL_USER_OBJ:
+		if (ace->type == NFS4_ACE_ACCESS_ALLOWED_ACE_TYPE) {
+			allow_bits(&state->owner, mask);
+		} else {
+			deny_bits(&state->owner, mask);
+		}
+		break;
+	case ACL_USER:
+		i = find_uid(state, ace->who_uid);
+		if (ace->type == NFS4_ACE_ACCESS_ALLOWED_ACE_TYPE) {
+			allow_bits(&state->users->aces[i].perms, mask);
+		} else {
+			deny_bits(&state->users->aces[i].perms, mask);
+			mask = state->users->aces[i].perms.deny;
+			deny_bits(&state->owner, mask);
+		}
+		break;
+	case ACL_GROUP_OBJ:
+		if (ace->type == NFS4_ACE_ACCESS_ALLOWED_ACE_TYPE) {
+			allow_bits(&state->group, mask);
+		} else {
+			deny_bits(&state->group, mask);
+			mask = state->group.deny;
+			deny_bits(&state->owner, mask);
+			deny_bits(&state->everyone, mask);
+			deny_bits_array(state->users, mask);
+			deny_bits_array(state->groups, mask);
+		}
+		break;
+	case ACL_GROUP:
+		i = find_gid(state, ace->who_gid);
+		if (ace->type == NFS4_ACE_ACCESS_ALLOWED_ACE_TYPE) {
+			allow_bits(&state->groups->aces[i].perms, mask);
+		} else {
+			deny_bits(&state->groups->aces[i].perms, mask);
+			mask = state->groups->aces[i].perms.deny;
+			deny_bits(&state->owner, mask);
+			deny_bits(&state->group, mask);
+			deny_bits(&state->everyone, mask);
+			deny_bits_array(state->users, mask);
+			deny_bits_array(state->groups, mask);
+		}
+		break;
+	case ACL_OTHER:
+		if (ace->type == NFS4_ACE_ACCESS_ALLOWED_ACE_TYPE) {
+			allow_bits(&state->owner, mask);
+			allow_bits(&state->group, mask);
+			allow_bits(&state->other, mask);
+			allow_bits(&state->everyone, mask);
+			allow_bits_array(state->users, mask);
+			allow_bits_array(state->groups, mask);
+		} else {
+			deny_bits(&state->owner, mask);
+			deny_bits(&state->group, mask);
+			deny_bits(&state->other, mask);
+			deny_bits(&state->everyone, mask);
+			deny_bits_array(state->users, mask);
+			deny_bits_array(state->groups, mask);
+		}
+	}
+}
+
+static int nfs4_acl_nfsv4_to_posix(struct nfs4_acl *acl,
+		struct posix_acl **pacl, struct posix_acl **dpacl,
+		unsigned int flags)
+{
+	struct posix_acl_state effective_acl_state, default_acl_state;
+	struct nfs4_ace *ace;
+	int ret;
+
+	ret = init_state(&effective_acl_state, acl->naces);
+	if (ret)
+		return ret;
+	ret = init_state(&default_acl_state, acl->naces);
+	if (ret)
+		goto out_estate;
+	ret = -EINVAL;
+	for (ace = acl->aces; ace < acl->aces + acl->naces; ace++) {
+		if (ace->type != NFS4_ACE_ACCESS_ALLOWED_ACE_TYPE &&
+		    ace->type != NFS4_ACE_ACCESS_DENIED_ACE_TYPE)
+			goto out_dstate;
+		if (ace->flag & ~NFS4_SUPPORTED_FLAGS)
+			goto out_dstate;
+		if ((ace->flag & NFS4_INHERITANCE_FLAGS) == 0) {
+			process_one_v4_ace(&effective_acl_state, ace);
+			continue;
+		}
+		if (!(flags & NFS4_ACL_DIR))
+			goto out_dstate;
+		/*
+		 * Note that when only one of FILE_INHERIT or DIRECTORY_INHERIT
+		 * is set, we're effectively turning on the other.  That's OK,
+		 * according to rfc 3530.
+		 */
+		process_one_v4_ace(&default_acl_state, ace);
+
+		if (!(ace->flag & NFS4_ACE_INHERIT_ONLY_ACE))
+			process_one_v4_ace(&effective_acl_state, ace);
+	}
+	*pacl = posix_state_to_acl(&effective_acl_state, flags);
+	if (IS_ERR(*pacl)) {
+		ret = PTR_ERR(*pacl);
+		*pacl = NULL;
+		goto out_dstate;
+	}
+	*dpacl = posix_state_to_acl(&default_acl_state,
+						flags | NFS4_ACL_TYPE_DEFAULT);
+	if (IS_ERR(*dpacl)) {
+		ret = PTR_ERR(*dpacl);
+		*dpacl = NULL;
+		posix_acl_release(*pacl);
+		*pacl = NULL;
+		goto out_dstate;
+	}
+	sort_pacl(*pacl);
+	sort_pacl(*dpacl);
+	ret = 0;
+out_dstate:
+	free_state(&default_acl_state);
+out_estate:
+	free_state(&effective_acl_state);
+	return ret;
+}
+
+__be32 nfsd4_acl_to_attr(enum nfs_ftype4 type, struct nfs4_acl *acl,
+			 struct nfsd_attrs *attr)
+{
+	int host_error;
+	unsigned int flags = 0;
+
+	if (!acl)
+		return nfs_ok;
+
+	if (type == NF4DIR)
+		flags = NFS4_ACL_DIR;
+
+	host_error = nfs4_acl_nfsv4_to_posix(acl, &attr->na_pacl,
+					     &attr->na_dpacl, flags);
+	if (host_error == -EINVAL)
+		return nfserr_attrnotsupp;
+	else
+		return nfserrno(host_error);
+}
+
+static short
+ace2type(struct nfs4_ace *ace)
+{
+	switch (ace->whotype) {
+		case NFS4_ACL_WHO_NAMED:
+			return (ace->flag & NFS4_ACE_IDENTIFIER_GROUP ?
+					ACL_GROUP : ACL_USER);
+		case NFS4_ACL_WHO_OWNER:
+			return ACL_USER_OBJ;
+		case NFS4_ACL_WHO_GROUP:
+			return ACL_GROUP_OBJ;
+		case NFS4_ACL_WHO_EVERYONE:
+			return ACL_OTHER;
+	}
+	BUG();
+	return -1;
+}
+
+/*
+ * return the size of the struct nfs4_acl required to represent an acl
+ * with @entries entries.
+ */
+int nfs4_acl_bytes(int entries)
+{
+	return sizeof(struct nfs4_acl) + entries * sizeof(struct nfs4_ace);
+}
+
+static struct {
+	char *string;
+	int   stringlen;
+	int type;
+} s2t_map[] = {
+	{
+		.string    = "OWNER@",
+		.stringlen = sizeof("OWNER@") - 1,
+		.type      = NFS4_ACL_WHO_OWNER,
+	},
+	{
+		.string    = "GROUP@",
+		.stringlen = sizeof("GROUP@") - 1,
+		.type      = NFS4_ACL_WHO_GROUP,
+	},
+	{
+		.string    = "EVERYONE@",
+		.stringlen = sizeof("EVERYONE@") - 1,
+		.type      = NFS4_ACL_WHO_EVERYONE,
+	},
+};
+
+int
+nfs4_acl_get_whotype(char *p, u32 len)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(s2t_map); i++) {
+		if (s2t_map[i].stringlen == len &&
+				0 == memcmp(s2t_map[i].string, p, len))
+			return s2t_map[i].type;
+	}
+	return NFS4_ACL_WHO_NAMED;
+}
+
+__be32 nfs4_acl_write_who(struct xdr_stream *xdr, int who)
+{
+	__be32 *p;
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(s2t_map); i++) {
+		if (s2t_map[i].type != who)
+			continue;
+		p = xdr_reserve_space(xdr, s2t_map[i].stringlen + 4);
+		if (!p)
+			return nfserr_resource;
+		p = xdr_encode_opaque(p, s2t_map[i].string,
+					s2t_map[i].stringlen);
+		return 0;
+	}
+	WARN_ON_ONCE(1);
+	return nfserr_serverfault;
+}