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, 704 insertions, 0 deletions

diff --git a/fs/proc/inode.c b/fs/proc/inode.c
new file mode 100644
index 000000000..f495fdb39
--- /dev/null
+++ b/fs/proc/inode.c
@@ -0,0 +1,704 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ *  linux/fs/proc/inode.c
+ *
+ *  Copyright (C) 1991, 1992  Linus Torvalds
+ */
+
+#include <linux/cache.h>
+#include <linux/time.h>
+#include <linux/proc_fs.h>
+#include <linux/kernel.h>
+#include <linux/pid_namespace.h>
+#include <linux/mm.h>
+#include <linux/string.h>
+#include <linux/stat.h>
+#include <linux/completion.h>
+#include <linux/poll.h>
+#include <linux/printk.h>
+#include <linux/file.h>
+#include <linux/limits.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/sysctl.h>
+#include <linux/seq_file.h>
+#include <linux/slab.h>
+#include <linux/mount.h>
+#include <linux/bug.h>
+
+#include "internal.h"
+
+static void proc_evict_inode(struct inode *inode)
+{
+	struct proc_dir_entry *de;
+	struct ctl_table_header *head;
+	struct proc_inode *ei = PROC_I(inode);
+
+	truncate_inode_pages_final(&inode->i_data);
+	clear_inode(inode);
+
+	/* Stop tracking associated processes */
+	if (ei->pid) {
+		proc_pid_evict_inode(ei);
+		ei->pid = NULL;
+	}
+
+	/* Let go of any associated proc directory entry */
+	de = ei->pde;
+	if (de) {
+		pde_put(de);
+		ei->pde = NULL;
+	}
+
+	head = ei->sysctl;
+	if (head) {
+		RCU_INIT_POINTER(ei->sysctl, NULL);
+		proc_sys_evict_inode(inode, head);
+	}
+}
+
+static struct kmem_cache *proc_inode_cachep __ro_after_init;
+static struct kmem_cache *pde_opener_cache __ro_after_init;
+
+static struct inode *proc_alloc_inode(struct super_block *sb)
+{
+	struct proc_inode *ei;
+
+	ei = alloc_inode_sb(sb, proc_inode_cachep, GFP_KERNEL);
+	if (!ei)
+		return NULL;
+	ei->pid = NULL;
+	ei->fd = 0;
+	ei->op.proc_get_link = NULL;
+	ei->pde = NULL;
+	ei->sysctl = NULL;
+	ei->sysctl_entry = NULL;
+	INIT_HLIST_NODE(&ei->sibling_inodes);
+	ei->ns_ops = NULL;
+	return &ei->vfs_inode;
+}
+
+static void proc_free_inode(struct inode *inode)
+{
+	kmem_cache_free(proc_inode_cachep, PROC_I(inode));
+}
+
+static void init_once(void *foo)
+{
+	struct proc_inode *ei = (struct proc_inode *) foo;
+
+	inode_init_once(&ei->vfs_inode);
+}
+
+void __init proc_init_kmemcache(void)
+{
+	proc_inode_cachep = kmem_cache_create("proc_inode_cache",
+					     sizeof(struct proc_inode),
+					     0, (SLAB_RECLAIM_ACCOUNT|
+						SLAB_MEM_SPREAD|SLAB_ACCOUNT|
+						SLAB_PANIC),
+					     init_once);
+	pde_opener_cache =
+		kmem_cache_create("pde_opener", sizeof(struct pde_opener), 0,
+				  SLAB_ACCOUNT|SLAB_PANIC, NULL);
+	proc_dir_entry_cache = kmem_cache_create_usercopy(
+		"proc_dir_entry", SIZEOF_PDE, 0, SLAB_PANIC,
+		offsetof(struct proc_dir_entry, inline_name),
+		SIZEOF_PDE_INLINE_NAME, NULL);
+	BUILD_BUG_ON(sizeof(struct proc_dir_entry) >= SIZEOF_PDE);
+}
+
+void proc_invalidate_siblings_dcache(struct hlist_head *inodes, spinlock_t *lock)
+{
+	struct inode *inode;
+	struct proc_inode *ei;
+	struct hlist_node *node;
+	struct super_block *old_sb = NULL;
+
+	rcu_read_lock();
+	for (;;) {
+		struct super_block *sb;
+		node = hlist_first_rcu(inodes);
+		if (!node)
+			break;
+		ei = hlist_entry(node, struct proc_inode, sibling_inodes);
+		spin_lock(lock);
+		hlist_del_init_rcu(&ei->sibling_inodes);
+		spin_unlock(lock);
+
+		inode = &ei->vfs_inode;
+		sb = inode->i_sb;
+		if ((sb != old_sb) && !atomic_inc_not_zero(&sb->s_active))
+			continue;
+		inode = igrab(inode);
+		rcu_read_unlock();
+		if (sb != old_sb) {
+			if (old_sb)
+				deactivate_super(old_sb);
+			old_sb = sb;
+		}
+		if (unlikely(!inode)) {
+			rcu_read_lock();
+			continue;
+		}
+
+		if (S_ISDIR(inode->i_mode)) {
+			struct dentry *dir = d_find_any_alias(inode);
+			if (dir) {
+				d_invalidate(dir);
+				dput(dir);
+			}
+		} else {
+			struct dentry *dentry;
+			while ((dentry = d_find_alias(inode))) {
+				d_invalidate(dentry);
+				dput(dentry);
+			}
+		}
+		iput(inode);
+
+		rcu_read_lock();
+	}
+	rcu_read_unlock();
+	if (old_sb)
+		deactivate_super(old_sb);
+}
+
+static inline const char *hidepid2str(enum proc_hidepid v)
+{
+	switch (v) {
+		case HIDEPID_OFF: return "off";
+		case HIDEPID_NO_ACCESS: return "noaccess";
+		case HIDEPID_INVISIBLE: return "invisible";
+		case HIDEPID_NOT_PTRACEABLE: return "ptraceable";
+	}
+	WARN_ONCE(1, "bad hide_pid value: %d\n", v);
+	return "unknown";
+}
+
+static int proc_show_options(struct seq_file *seq, struct dentry *root)
+{
+	struct proc_fs_info *fs_info = proc_sb_info(root->d_sb);
+
+	if (!gid_eq(fs_info->pid_gid, GLOBAL_ROOT_GID))
+		seq_printf(seq, ",gid=%u", from_kgid_munged(&init_user_ns, fs_info->pid_gid));
+	if (fs_info->hide_pid != HIDEPID_OFF)
+		seq_printf(seq, ",hidepid=%s", hidepid2str(fs_info->hide_pid));
+	if (fs_info->pidonly != PROC_PIDONLY_OFF)
+		seq_printf(seq, ",subset=pid");
+
+	return 0;
+}
+
+const struct super_operations proc_sops = {
+	.alloc_inode	= proc_alloc_inode,
+	.free_inode	= proc_free_inode,
+	.drop_inode	= generic_delete_inode,
+	.evict_inode	= proc_evict_inode,
+	.statfs		= simple_statfs,
+	.show_options	= proc_show_options,
+};
+
+enum {BIAS = -1U<<31};
+
+static inline int use_pde(struct proc_dir_entry *pde)
+{
+	return likely(atomic_inc_unless_negative(&pde->in_use));
+}
+
+static void unuse_pde(struct proc_dir_entry *pde)
+{
+	if (unlikely(atomic_dec_return(&pde->in_use) == BIAS))
+		complete(pde->pde_unload_completion);
+}
+
+/*
+ * At most 2 contexts can enter this function: the one doing the last
+ * close on the descriptor and whoever is deleting PDE itself.
+ *
+ * First to enter calls ->proc_release hook and signals its completion
+ * to the second one which waits and then does nothing.
+ *
+ * PDE is locked on entry, unlocked on exit.
+ */
+static void close_pdeo(struct proc_dir_entry *pde, struct pde_opener *pdeo)
+	__releases(&pde->pde_unload_lock)
+{
+	/*
+	 * close() (proc_reg_release()) can't delete an entry and proceed:
+	 * ->release hook needs to be available at the right moment.
+	 *
+	 * rmmod (remove_proc_entry() et al) can't delete an entry and proceed:
+	 * "struct file" needs to be available at the right moment.
+	 */
+	if (pdeo->closing) {
+		/* somebody else is doing that, just wait */
+		DECLARE_COMPLETION_ONSTACK(c);
+		pdeo->c = &c;
+		spin_unlock(&pde->pde_unload_lock);
+		wait_for_completion(&c);
+	} else {
+		struct file *file;
+		struct completion *c;
+
+		pdeo->closing = true;
+		spin_unlock(&pde->pde_unload_lock);
+
+		file = pdeo->file;
+		pde->proc_ops->proc_release(file_inode(file), file);
+
+		spin_lock(&pde->pde_unload_lock);
+		/* Strictly after ->proc_release, see above. */
+		list_del(&pdeo->lh);
+		c = pdeo->c;
+		spin_unlock(&pde->pde_unload_lock);
+		if (unlikely(c))
+			complete(c);
+		kmem_cache_free(pde_opener_cache, pdeo);
+	}
+}
+
+void proc_entry_rundown(struct proc_dir_entry *de)
+{
+	DECLARE_COMPLETION_ONSTACK(c);
+	/* Wait until all existing callers into module are done. */
+	de->pde_unload_completion = &c;
+	if (atomic_add_return(BIAS, &de->in_use) != BIAS)
+		wait_for_completion(&c);
+
+	/* ->pde_openers list can't grow from now on. */
+
+	spin_lock(&de->pde_unload_lock);
+	while (!list_empty(&de->pde_openers)) {
+		struct pde_opener *pdeo;
+		pdeo = list_first_entry(&de->pde_openers, struct pde_opener, lh);
+		close_pdeo(de, pdeo);
+		spin_lock(&de->pde_unload_lock);
+	}
+	spin_unlock(&de->pde_unload_lock);
+}
+
+static loff_t proc_reg_llseek(struct file *file, loff_t offset, int whence)
+{
+	struct proc_dir_entry *pde = PDE(file_inode(file));
+	loff_t rv = -EINVAL;
+
+	if (pde_is_permanent(pde)) {
+		return pde->proc_ops->proc_lseek(file, offset, whence);
+	} else if (use_pde(pde)) {
+		rv = pde->proc_ops->proc_lseek(file, offset, whence);
+		unuse_pde(pde);
+	}
+	return rv;
+}
+
+static ssize_t proc_reg_read_iter(struct kiocb *iocb, struct iov_iter *iter)
+{
+	struct proc_dir_entry *pde = PDE(file_inode(iocb->ki_filp));
+	ssize_t ret;
+
+	if (pde_is_permanent(pde))
+		return pde->proc_ops->proc_read_iter(iocb, iter);
+
+	if (!use_pde(pde))
+		return -EIO;
+	ret = pde->proc_ops->proc_read_iter(iocb, iter);
+	unuse_pde(pde);
+	return ret;
+}
+
+static ssize_t pde_read(struct proc_dir_entry *pde, struct file *file, char __user *buf, size_t count, loff_t *ppos)
+{
+	typeof_member(struct proc_ops, proc_read) read;
+
+	read = pde->proc_ops->proc_read;
+	if (read)
+		return read(file, buf, count, ppos);
+	return -EIO;
+}
+
+static ssize_t proc_reg_read(struct file *file, char __user *buf, size_t count, loff_t *ppos)
+{
+	struct proc_dir_entry *pde = PDE(file_inode(file));
+	ssize_t rv = -EIO;
+
+	if (pde_is_permanent(pde)) {
+		return pde_read(pde, file, buf, count, ppos);
+	} else if (use_pde(pde)) {
+		rv = pde_read(pde, file, buf, count, ppos);
+		unuse_pde(pde);
+	}
+	return rv;
+}
+
+static ssize_t pde_write(struct proc_dir_entry *pde, struct file *file, const char __user *buf, size_t count, loff_t *ppos)
+{
+	typeof_member(struct proc_ops, proc_write) write;
+
+	write = pde->proc_ops->proc_write;
+	if (write)
+		return write(file, buf, count, ppos);
+	return -EIO;
+}
+
+static ssize_t proc_reg_write(struct file *file, const char __user *buf, size_t count, loff_t *ppos)
+{
+	struct proc_dir_entry *pde = PDE(file_inode(file));
+	ssize_t rv = -EIO;
+
+	if (pde_is_permanent(pde)) {
+		return pde_write(pde, file, buf, count, ppos);
+	} else if (use_pde(pde)) {
+		rv = pde_write(pde, file, buf, count, ppos);
+		unuse_pde(pde);
+	}
+	return rv;
+}
+
+static __poll_t pde_poll(struct proc_dir_entry *pde, struct file *file, struct poll_table_struct *pts)
+{
+	typeof_member(struct proc_ops, proc_poll) poll;
+
+	poll = pde->proc_ops->proc_poll;
+	if (poll)
+		return poll(file, pts);
+	return DEFAULT_POLLMASK;
+}
+
+static __poll_t proc_reg_poll(struct file *file, struct poll_table_struct *pts)
+{
+	struct proc_dir_entry *pde = PDE(file_inode(file));
+	__poll_t rv = DEFAULT_POLLMASK;
+
+	if (pde_is_permanent(pde)) {
+		return pde_poll(pde, file, pts);
+	} else if (use_pde(pde)) {
+		rv = pde_poll(pde, file, pts);
+		unuse_pde(pde);
+	}
+	return rv;
+}
+
+static long pde_ioctl(struct proc_dir_entry *pde, struct file *file, unsigned int cmd, unsigned long arg)
+{
+	typeof_member(struct proc_ops, proc_ioctl) ioctl;
+
+	ioctl = pde->proc_ops->proc_ioctl;
+	if (ioctl)
+		return ioctl(file, cmd, arg);
+	return -ENOTTY;
+}
+
+static long proc_reg_unlocked_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
+{
+	struct proc_dir_entry *pde = PDE(file_inode(file));
+	long rv = -ENOTTY;
+
+	if (pde_is_permanent(pde)) {
+		return pde_ioctl(pde, file, cmd, arg);
+	} else if (use_pde(pde)) {
+		rv = pde_ioctl(pde, file, cmd, arg);
+		unuse_pde(pde);
+	}
+	return rv;
+}
+
+#ifdef CONFIG_COMPAT
+static long pde_compat_ioctl(struct proc_dir_entry *pde, struct file *file, unsigned int cmd, unsigned long arg)
+{
+	typeof_member(struct proc_ops, proc_compat_ioctl) compat_ioctl;
+
+	compat_ioctl = pde->proc_ops->proc_compat_ioctl;
+	if (compat_ioctl)
+		return compat_ioctl(file, cmd, arg);
+	return -ENOTTY;
+}
+
+static long proc_reg_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
+{
+	struct proc_dir_entry *pde = PDE(file_inode(file));
+	long rv = -ENOTTY;
+	if (pde_is_permanent(pde)) {
+		return pde_compat_ioctl(pde, file, cmd, arg);
+	} else if (use_pde(pde)) {
+		rv = pde_compat_ioctl(pde, file, cmd, arg);
+		unuse_pde(pde);
+	}
+	return rv;
+}
+#endif
+
+static int pde_mmap(struct proc_dir_entry *pde, struct file *file, struct vm_area_struct *vma)
+{
+	typeof_member(struct proc_ops, proc_mmap) mmap;
+
+	mmap = pde->proc_ops->proc_mmap;
+	if (mmap)
+		return mmap(file, vma);
+	return -EIO;
+}
+
+static int proc_reg_mmap(struct file *file, struct vm_area_struct *vma)
+{
+	struct proc_dir_entry *pde = PDE(file_inode(file));
+	int rv = -EIO;
+
+	if (pde_is_permanent(pde)) {
+		return pde_mmap(pde, file, vma);
+	} else if (use_pde(pde)) {
+		rv = pde_mmap(pde, file, vma);
+		unuse_pde(pde);
+	}
+	return rv;
+}
+
+static unsigned long
+pde_get_unmapped_area(struct proc_dir_entry *pde, struct file *file, unsigned long orig_addr,
+			   unsigned long len, unsigned long pgoff,
+			   unsigned long flags)
+{
+	typeof_member(struct proc_ops, proc_get_unmapped_area) get_area;
+
+	get_area = pde->proc_ops->proc_get_unmapped_area;
+#ifdef CONFIG_MMU
+	if (!get_area)
+		get_area = current->mm->get_unmapped_area;
+#endif
+	if (get_area)
+		return get_area(file, orig_addr, len, pgoff, flags);
+	return orig_addr;
+}
+
+static unsigned long
+proc_reg_get_unmapped_area(struct file *file, unsigned long orig_addr,
+			   unsigned long len, unsigned long pgoff,
+			   unsigned long flags)
+{
+	struct proc_dir_entry *pde = PDE(file_inode(file));
+	unsigned long rv = -EIO;
+
+	if (pde_is_permanent(pde)) {
+		return pde_get_unmapped_area(pde, file, orig_addr, len, pgoff, flags);
+	} else if (use_pde(pde)) {
+		rv = pde_get_unmapped_area(pde, file, orig_addr, len, pgoff, flags);
+		unuse_pde(pde);
+	}
+	return rv;
+}
+
+static int proc_reg_open(struct inode *inode, struct file *file)
+{
+	struct proc_dir_entry *pde = PDE(inode);
+	int rv = 0;
+	typeof_member(struct proc_ops, proc_open) open;
+	typeof_member(struct proc_ops, proc_release) release;
+	struct pde_opener *pdeo;
+
+	if (!pde->proc_ops->proc_lseek)
+		file->f_mode &= ~FMODE_LSEEK;
+
+	if (pde_is_permanent(pde)) {
+		open = pde->proc_ops->proc_open;
+		if (open)
+			rv = open(inode, file);
+		return rv;
+	}
+
+	/*
+	 * Ensure that
+	 * 1) PDE's ->release hook will be called no matter what
+	 *    either normally by close()/->release, or forcefully by
+	 *    rmmod/remove_proc_entry.
+	 *
+	 * 2) rmmod isn't blocked by opening file in /proc and sitting on
+	 *    the descriptor (including "rmmod foo </proc/foo" scenario).
+	 *
+	 * Save every "struct file" with custom ->release hook.
+	 */
+	if (!use_pde(pde))
+		return -ENOENT;
+
+	release = pde->proc_ops->proc_release;
+	if (release) {
+		pdeo = kmem_cache_alloc(pde_opener_cache, GFP_KERNEL);
+		if (!pdeo) {
+			rv = -ENOMEM;
+			goto out_unuse;
+		}
+	}
+
+	open = pde->proc_ops->proc_open;
+	if (open)
+		rv = open(inode, file);
+
+	if (release) {
+		if (rv == 0) {
+			/* To know what to release. */
+			pdeo->file = file;
+			pdeo->closing = false;
+			pdeo->c = NULL;
+			spin_lock(&pde->pde_unload_lock);
+			list_add(&pdeo->lh, &pde->pde_openers);
+			spin_unlock(&pde->pde_unload_lock);
+		} else
+			kmem_cache_free(pde_opener_cache, pdeo);
+	}
+
+out_unuse:
+	unuse_pde(pde);
+	return rv;
+}
+
+static int proc_reg_release(struct inode *inode, struct file *file)
+{
+	struct proc_dir_entry *pde = PDE(inode);
+	struct pde_opener *pdeo;
+
+	if (pde_is_permanent(pde)) {
+		typeof_member(struct proc_ops, proc_release) release;
+
+		release = pde->proc_ops->proc_release;
+		if (release) {
+			return release(inode, file);
+		}
+		return 0;
+	}
+
+	spin_lock(&pde->pde_unload_lock);
+	list_for_each_entry(pdeo, &pde->pde_openers, lh) {
+		if (pdeo->file == file) {
+			close_pdeo(pde, pdeo);
+			return 0;
+		}
+	}
+	spin_unlock(&pde->pde_unload_lock);
+	return 0;
+}
+
+static const struct file_operations proc_reg_file_ops = {
+	.llseek		= proc_reg_llseek,
+	.read		= proc_reg_read,
+	.write		= proc_reg_write,
+	.poll		= proc_reg_poll,
+	.unlocked_ioctl	= proc_reg_unlocked_ioctl,
+	.mmap		= proc_reg_mmap,
+	.get_unmapped_area = proc_reg_get_unmapped_area,
+	.open		= proc_reg_open,
+	.release	= proc_reg_release,
+};
+
+static const struct file_operations proc_iter_file_ops = {
+	.llseek		= proc_reg_llseek,
+	.read_iter	= proc_reg_read_iter,
+	.write		= proc_reg_write,
+	.splice_read	= generic_file_splice_read,
+	.poll		= proc_reg_poll,
+	.unlocked_ioctl	= proc_reg_unlocked_ioctl,
+	.mmap		= proc_reg_mmap,
+	.get_unmapped_area = proc_reg_get_unmapped_area,
+	.open		= proc_reg_open,
+	.release	= proc_reg_release,
+};
+
+#ifdef CONFIG_COMPAT
+static const struct file_operations proc_reg_file_ops_compat = {
+	.llseek		= proc_reg_llseek,
+	.read		= proc_reg_read,
+	.write		= proc_reg_write,
+	.poll		= proc_reg_poll,
+	.unlocked_ioctl	= proc_reg_unlocked_ioctl,
+	.compat_ioctl	= proc_reg_compat_ioctl,
+	.mmap		= proc_reg_mmap,
+	.get_unmapped_area = proc_reg_get_unmapped_area,
+	.open		= proc_reg_open,
+	.release	= proc_reg_release,
+};
+
+static const struct file_operations proc_iter_file_ops_compat = {
+	.llseek		= proc_reg_llseek,
+	.read_iter	= proc_reg_read_iter,
+	.splice_read	= generic_file_splice_read,
+	.write		= proc_reg_write,
+	.poll		= proc_reg_poll,
+	.unlocked_ioctl	= proc_reg_unlocked_ioctl,
+	.compat_ioctl	= proc_reg_compat_ioctl,
+	.mmap		= proc_reg_mmap,
+	.get_unmapped_area = proc_reg_get_unmapped_area,
+	.open		= proc_reg_open,
+	.release	= proc_reg_release,
+};
+#endif
+
+static void proc_put_link(void *p)
+{
+	unuse_pde(p);
+}
+
+static const char *proc_get_link(struct dentry *dentry,
+				 struct inode *inode,
+				 struct delayed_call *done)
+{
+	struct proc_dir_entry *pde = PDE(inode);
+	if (!use_pde(pde))
+		return ERR_PTR(-EINVAL);
+	set_delayed_call(done, proc_put_link, pde);
+	return pde->data;
+}
+
+const struct inode_operations proc_link_inode_operations = {
+	.get_link	= proc_get_link,
+};
+
+struct inode *proc_get_inode(struct super_block *sb, struct proc_dir_entry *de)
+{
+	struct inode *inode = new_inode(sb);
+
+	if (!inode) {
+		pde_put(de);
+		return NULL;
+	}
+
+	inode->i_private = de->data;
+	inode->i_ino = de->low_ino;
+	inode->i_mtime = inode->i_atime = inode->i_ctime = current_time(inode);
+	PROC_I(inode)->pde = de;
+	if (is_empty_pde(de)) {
+		make_empty_dir_inode(inode);
+		return inode;
+	}
+
+	if (de->mode) {
+		inode->i_mode = de->mode;
+		inode->i_uid = de->uid;
+		inode->i_gid = de->gid;
+	}
+	if (de->size)
+		inode->i_size = de->size;
+	if (de->nlink)
+		set_nlink(inode, de->nlink);
+
+	if (S_ISREG(inode->i_mode)) {
+		inode->i_op = de->proc_iops;
+		if (de->proc_ops->proc_read_iter)
+			inode->i_fop = &proc_iter_file_ops;
+		else
+			inode->i_fop = &proc_reg_file_ops;
+#ifdef CONFIG_COMPAT
+		if (de->proc_ops->proc_compat_ioctl) {
+			if (de->proc_ops->proc_read_iter)
+				inode->i_fop = &proc_iter_file_ops_compat;
+			else
+				inode->i_fop = &proc_reg_file_ops_compat;
+		}
+#endif
+	} else if (S_ISDIR(inode->i_mode)) {
+		inode->i_op = de->proc_iops;
+		inode->i_fop = de->proc_dir_ops;
+	} else if (S_ISLNK(inode->i_mode)) {
+		inode->i_op = de->proc_iops;
+		inode->i_fop = NULL;
+	} else {
+		BUG();
+	}
+	return inode;
+}