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, 588 insertions, 0 deletions

diff --git a/drivers/tty/tty_jobctrl.c b/drivers/tty/tty_jobctrl.c
new file mode 100644
index 000000000..0d04287da
--- /dev/null
+++ b/drivers/tty/tty_jobctrl.c
@@ -0,0 +1,588 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ *  Copyright (C) 1991, 1992  Linus Torvalds
+ */
+
+#include <linux/types.h>
+#include <linux/errno.h>
+#include <linux/signal.h>
+#include <linux/sched/signal.h>
+#include <linux/sched/task.h>
+#include <linux/tty.h>
+#include <linux/fcntl.h>
+#include <linux/uaccess.h>
+#include "tty.h"
+
+static int is_ignored(int sig)
+{
+	return (sigismember(&current->blocked, sig) ||
+		current->sighand->action[sig-1].sa.sa_handler == SIG_IGN);
+}
+
+/**
+ *	__tty_check_change	-	check for POSIX terminal changes
+ *	@tty: tty to check
+ *	@sig: signal to send
+ *
+ *	If we try to write to, or set the state of, a terminal and we're
+ *	not in the foreground, send a SIGTTOU.  If the signal is blocked or
+ *	ignored, go ahead and perform the operation.  (POSIX 7.2)
+ *
+ *	Locking: ctrl.lock
+ */
+int __tty_check_change(struct tty_struct *tty, int sig)
+{
+	unsigned long flags;
+	struct pid *pgrp, *tty_pgrp;
+	int ret = 0;
+
+	if (current->signal->tty != tty)
+		return 0;
+
+	rcu_read_lock();
+	pgrp = task_pgrp(current);
+
+	spin_lock_irqsave(&tty->ctrl.lock, flags);
+	tty_pgrp = tty->ctrl.pgrp;
+	spin_unlock_irqrestore(&tty->ctrl.lock, flags);
+
+	if (tty_pgrp && pgrp != tty_pgrp) {
+		if (is_ignored(sig)) {
+			if (sig == SIGTTIN)
+				ret = -EIO;
+		} else if (is_current_pgrp_orphaned())
+			ret = -EIO;
+		else {
+			kill_pgrp(pgrp, sig, 1);
+			set_thread_flag(TIF_SIGPENDING);
+			ret = -ERESTARTSYS;
+		}
+	}
+	rcu_read_unlock();
+
+	if (!tty_pgrp)
+		tty_warn(tty, "sig=%d, tty->pgrp == NULL!\n", sig);
+
+	return ret;
+}
+
+int tty_check_change(struct tty_struct *tty)
+{
+	return __tty_check_change(tty, SIGTTOU);
+}
+EXPORT_SYMBOL(tty_check_change);
+
+void proc_clear_tty(struct task_struct *p)
+{
+	unsigned long flags;
+	struct tty_struct *tty;
+
+	spin_lock_irqsave(&p->sighand->siglock, flags);
+	tty = p->signal->tty;
+	p->signal->tty = NULL;
+	spin_unlock_irqrestore(&p->sighand->siglock, flags);
+	tty_kref_put(tty);
+}
+
+/**
+ * __proc_set_tty -  set the controlling terminal
+ *	@tty: tty structure
+ *
+ * Only callable by the session leader and only if it does not already have
+ * a controlling terminal.
+ *
+ * Caller must hold:  tty_lock()
+ *		      a readlock on tasklist_lock
+ *		      sighand lock
+ */
+static void __proc_set_tty(struct tty_struct *tty)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&tty->ctrl.lock, flags);
+	/*
+	 * The session and fg pgrp references will be non-NULL if
+	 * tiocsctty() is stealing the controlling tty
+	 */
+	put_pid(tty->ctrl.session);
+	put_pid(tty->ctrl.pgrp);
+	tty->ctrl.pgrp = get_pid(task_pgrp(current));
+	tty->ctrl.session = get_pid(task_session(current));
+	spin_unlock_irqrestore(&tty->ctrl.lock, flags);
+	if (current->signal->tty) {
+		tty_debug(tty, "current tty %s not NULL!!\n",
+			  current->signal->tty->name);
+		tty_kref_put(current->signal->tty);
+	}
+	put_pid(current->signal->tty_old_pgrp);
+	current->signal->tty = tty_kref_get(tty);
+	current->signal->tty_old_pgrp = NULL;
+}
+
+static void proc_set_tty(struct tty_struct *tty)
+{
+	spin_lock_irq(&current->sighand->siglock);
+	__proc_set_tty(tty);
+	spin_unlock_irq(&current->sighand->siglock);
+}
+
+/*
+ * Called by tty_open() to set the controlling tty if applicable.
+ */
+void tty_open_proc_set_tty(struct file *filp, struct tty_struct *tty)
+{
+	read_lock(&tasklist_lock);
+	spin_lock_irq(&current->sighand->siglock);
+	if (current->signal->leader &&
+	    !current->signal->tty &&
+	    tty->ctrl.session == NULL) {
+		/*
+		 * Don't let a process that only has write access to the tty
+		 * obtain the privileges associated with having a tty as
+		 * controlling terminal (being able to reopen it with full
+		 * access through /dev/tty, being able to perform pushback).
+		 * Many distributions set the group of all ttys to "tty" and
+		 * grant write-only access to all terminals for setgid tty
+		 * binaries, which should not imply full privileges on all ttys.
+		 *
+		 * This could theoretically break old code that performs open()
+		 * on a write-only file descriptor. In that case, it might be
+		 * necessary to also permit this if
+		 * inode_permission(inode, MAY_READ) == 0.
+		 */
+		if (filp->f_mode & FMODE_READ)
+			__proc_set_tty(tty);
+	}
+	spin_unlock_irq(&current->sighand->siglock);
+	read_unlock(&tasklist_lock);
+}
+
+struct tty_struct *get_current_tty(void)
+{
+	struct tty_struct *tty;
+	unsigned long flags;
+
+	spin_lock_irqsave(&current->sighand->siglock, flags);
+	tty = tty_kref_get(current->signal->tty);
+	spin_unlock_irqrestore(&current->sighand->siglock, flags);
+	return tty;
+}
+EXPORT_SYMBOL_GPL(get_current_tty);
+
+/*
+ * Called from tty_release().
+ */
+void session_clear_tty(struct pid *session)
+{
+	struct task_struct *p;
+
+	do_each_pid_task(session, PIDTYPE_SID, p) {
+		proc_clear_tty(p);
+	} while_each_pid_task(session, PIDTYPE_SID, p);
+}
+
+/**
+ *	tty_signal_session_leader	- sends SIGHUP to session leader
+ *	@tty: controlling tty
+ *	@exit_session: if non-zero, signal all foreground group processes
+ *
+ *	Send SIGHUP and SIGCONT to the session leader and its process group.
+ *	Optionally, signal all processes in the foreground process group.
+ *
+ *	Returns the number of processes in the session with this tty
+ *	as their controlling terminal. This value is used to drop
+ *	tty references for those processes.
+ */
+int tty_signal_session_leader(struct tty_struct *tty, int exit_session)
+{
+	struct task_struct *p;
+	int refs = 0;
+	struct pid *tty_pgrp = NULL;
+
+	read_lock(&tasklist_lock);
+	if (tty->ctrl.session) {
+		do_each_pid_task(tty->ctrl.session, PIDTYPE_SID, p) {
+			spin_lock_irq(&p->sighand->siglock);
+			if (p->signal->tty == tty) {
+				p->signal->tty = NULL;
+				/*
+				 * We defer the dereferences outside of
+				 * the tasklist lock.
+				 */
+				refs++;
+			}
+			if (!p->signal->leader) {
+				spin_unlock_irq(&p->sighand->siglock);
+				continue;
+			}
+			send_signal_locked(SIGHUP, SEND_SIG_PRIV, p, PIDTYPE_TGID);
+			send_signal_locked(SIGCONT, SEND_SIG_PRIV, p, PIDTYPE_TGID);
+			put_pid(p->signal->tty_old_pgrp);  /* A noop */
+			spin_lock(&tty->ctrl.lock);
+			tty_pgrp = get_pid(tty->ctrl.pgrp);
+			if (tty->ctrl.pgrp)
+				p->signal->tty_old_pgrp =
+					get_pid(tty->ctrl.pgrp);
+			spin_unlock(&tty->ctrl.lock);
+			spin_unlock_irq(&p->sighand->siglock);
+		} while_each_pid_task(tty->ctrl.session, PIDTYPE_SID, p);
+	}
+	read_unlock(&tasklist_lock);
+
+	if (tty_pgrp) {
+		if (exit_session)
+			kill_pgrp(tty_pgrp, SIGHUP, exit_session);
+		put_pid(tty_pgrp);
+	}
+
+	return refs;
+}
+
+/**
+ *	disassociate_ctty	-	disconnect controlling tty
+ *	@on_exit: true if exiting so need to "hang up" the session
+ *
+ *	This function is typically called only by the session leader, when
+ *	it wants to disassociate itself from its controlling tty.
+ *
+ *	It performs the following functions:
+ *	(1)  Sends a SIGHUP and SIGCONT to the foreground process group
+ *	(2)  Clears the tty from being controlling the session
+ *	(3)  Clears the controlling tty for all processes in the
+ *		session group.
+ *
+ *	The argument on_exit is set to 1 if called when a process is
+ *	exiting; it is 0 if called by the ioctl TIOCNOTTY.
+ *
+ *	Locking:
+ *		BTM is taken for hysterical raisons, and held when
+ *		  called from no_tty().
+ *		  tty_mutex is taken to protect tty
+ *		  ->siglock is taken to protect ->signal/->sighand
+ *		  tasklist_lock is taken to walk process list for sessions
+ *		    ->siglock is taken to protect ->signal/->sighand
+ */
+void disassociate_ctty(int on_exit)
+{
+	struct tty_struct *tty;
+
+	if (!current->signal->leader)
+		return;
+
+	tty = get_current_tty();
+	if (tty) {
+		if (on_exit && tty->driver->type != TTY_DRIVER_TYPE_PTY) {
+			tty_vhangup_session(tty);
+		} else {
+			struct pid *tty_pgrp = tty_get_pgrp(tty);
+
+			if (tty_pgrp) {
+				kill_pgrp(tty_pgrp, SIGHUP, on_exit);
+				if (!on_exit)
+					kill_pgrp(tty_pgrp, SIGCONT, on_exit);
+				put_pid(tty_pgrp);
+			}
+		}
+		tty_kref_put(tty);
+
+	} else if (on_exit) {
+		struct pid *old_pgrp;
+
+		spin_lock_irq(&current->sighand->siglock);
+		old_pgrp = current->signal->tty_old_pgrp;
+		current->signal->tty_old_pgrp = NULL;
+		spin_unlock_irq(&current->sighand->siglock);
+		if (old_pgrp) {
+			kill_pgrp(old_pgrp, SIGHUP, on_exit);
+			kill_pgrp(old_pgrp, SIGCONT, on_exit);
+			put_pid(old_pgrp);
+		}
+		return;
+	}
+
+	spin_lock_irq(&current->sighand->siglock);
+	put_pid(current->signal->tty_old_pgrp);
+	current->signal->tty_old_pgrp = NULL;
+	tty = tty_kref_get(current->signal->tty);
+	spin_unlock_irq(&current->sighand->siglock);
+
+	if (tty) {
+		unsigned long flags;
+
+		tty_lock(tty);
+		spin_lock_irqsave(&tty->ctrl.lock, flags);
+		put_pid(tty->ctrl.session);
+		put_pid(tty->ctrl.pgrp);
+		tty->ctrl.session = NULL;
+		tty->ctrl.pgrp = NULL;
+		spin_unlock_irqrestore(&tty->ctrl.lock, flags);
+		tty_unlock(tty);
+		tty_kref_put(tty);
+	}
+
+	/* Now clear signal->tty under the lock */
+	read_lock(&tasklist_lock);
+	session_clear_tty(task_session(current));
+	read_unlock(&tasklist_lock);
+}
+
+/*
+ *
+ *	no_tty	- Ensure the current process does not have a controlling tty
+ */
+void no_tty(void)
+{
+	/*
+	 * FIXME: Review locking here. The tty_lock never covered any race
+	 * between a new association and proc_clear_tty but possibly we need
+	 * to protect against this anyway.
+	 */
+	struct task_struct *tsk = current;
+
+	disassociate_ctty(0);
+	proc_clear_tty(tsk);
+}
+
+/**
+ *	tiocsctty	-	set controlling tty
+ *	@tty: tty structure
+ *	@file: file structure used to check permissions
+ *	@arg: user argument
+ *
+ *	This ioctl is used to manage job control. It permits a session
+ *	leader to set this tty as the controlling tty for the session.
+ *
+ *	Locking:
+ *		Takes tty_lock() to serialize proc_set_tty() for this tty
+ *		Takes tasklist_lock internally to walk sessions
+ *		Takes ->siglock() when updating signal->tty
+ */
+static int tiocsctty(struct tty_struct *tty, struct file *file, int arg)
+{
+	int ret = 0;
+
+	tty_lock(tty);
+	read_lock(&tasklist_lock);
+
+	if (current->signal->leader &&
+			task_session(current) == tty->ctrl.session)
+		goto unlock;
+
+	/*
+	 * The process must be a session leader and
+	 * not have a controlling tty already.
+	 */
+	if (!current->signal->leader || current->signal->tty) {
+		ret = -EPERM;
+		goto unlock;
+	}
+
+	if (tty->ctrl.session) {
+		/*
+		 * This tty is already the controlling
+		 * tty for another session group!
+		 */
+		if (arg == 1 && capable(CAP_SYS_ADMIN)) {
+			/*
+			 * Steal it away
+			 */
+			session_clear_tty(tty->ctrl.session);
+		} else {
+			ret = -EPERM;
+			goto unlock;
+		}
+	}
+
+	/* See the comment in tty_open_proc_set_tty(). */
+	if ((file->f_mode & FMODE_READ) == 0 && !capable(CAP_SYS_ADMIN)) {
+		ret = -EPERM;
+		goto unlock;
+	}
+
+	proc_set_tty(tty);
+unlock:
+	read_unlock(&tasklist_lock);
+	tty_unlock(tty);
+	return ret;
+}
+
+/**
+ *	tty_get_pgrp	-	return a ref counted pgrp pid
+ *	@tty: tty to read
+ *
+ *	Returns a refcounted instance of the pid struct for the process
+ *	group controlling the tty.
+ */
+struct pid *tty_get_pgrp(struct tty_struct *tty)
+{
+	unsigned long flags;
+	struct pid *pgrp;
+
+	spin_lock_irqsave(&tty->ctrl.lock, flags);
+	pgrp = get_pid(tty->ctrl.pgrp);
+	spin_unlock_irqrestore(&tty->ctrl.lock, flags);
+
+	return pgrp;
+}
+EXPORT_SYMBOL_GPL(tty_get_pgrp);
+
+/*
+ * This checks not only the pgrp, but falls back on the pid if no
+ * satisfactory pgrp is found. I dunno - gdb doesn't work correctly
+ * without this...
+ *
+ * The caller must hold rcu lock or the tasklist lock.
+ */
+static struct pid *session_of_pgrp(struct pid *pgrp)
+{
+	struct task_struct *p;
+	struct pid *sid = NULL;
+
+	p = pid_task(pgrp, PIDTYPE_PGID);
+	if (p == NULL)
+		p = pid_task(pgrp, PIDTYPE_PID);
+	if (p != NULL)
+		sid = task_session(p);
+
+	return sid;
+}
+
+/**
+ *	tiocgpgrp		-	get process group
+ *	@tty: tty passed by user
+ *	@real_tty: tty side of the tty passed by the user if a pty else the tty
+ *	@p: returned pid
+ *
+ *	Obtain the process group of the tty. If there is no process group
+ *	return an error.
+ *
+ *	Locking: none. Reference to current->signal->tty is safe.
+ */
+static int tiocgpgrp(struct tty_struct *tty, struct tty_struct *real_tty, pid_t __user *p)
+{
+	struct pid *pid;
+	int ret;
+	/*
+	 * (tty == real_tty) is a cheap way of
+	 * testing if the tty is NOT a master pty.
+	 */
+	if (tty == real_tty && current->signal->tty != real_tty)
+		return -ENOTTY;
+	pid = tty_get_pgrp(real_tty);
+	ret =  put_user(pid_vnr(pid), p);
+	put_pid(pid);
+	return ret;
+}
+
+/**
+ *	tiocspgrp		-	attempt to set process group
+ *	@tty: tty passed by user
+ *	@real_tty: tty side device matching tty passed by user
+ *	@p: pid pointer
+ *
+ *	Set the process group of the tty to the session passed. Only
+ *	permitted where the tty session is our session.
+ *
+ *	Locking: RCU, ctrl lock
+ */
+static int tiocspgrp(struct tty_struct *tty, struct tty_struct *real_tty, pid_t __user *p)
+{
+	struct pid *pgrp;
+	pid_t pgrp_nr;
+	int retval = tty_check_change(real_tty);
+
+	if (retval == -EIO)
+		return -ENOTTY;
+	if (retval)
+		return retval;
+
+	if (get_user(pgrp_nr, p))
+		return -EFAULT;
+	if (pgrp_nr < 0)
+		return -EINVAL;
+
+	spin_lock_irq(&real_tty->ctrl.lock);
+	if (!current->signal->tty ||
+	    (current->signal->tty != real_tty) ||
+	    (real_tty->ctrl.session != task_session(current))) {
+		retval = -ENOTTY;
+		goto out_unlock_ctrl;
+	}
+	rcu_read_lock();
+	pgrp = find_vpid(pgrp_nr);
+	retval = -ESRCH;
+	if (!pgrp)
+		goto out_unlock;
+	retval = -EPERM;
+	if (session_of_pgrp(pgrp) != task_session(current))
+		goto out_unlock;
+	retval = 0;
+	put_pid(real_tty->ctrl.pgrp);
+	real_tty->ctrl.pgrp = get_pid(pgrp);
+out_unlock:
+	rcu_read_unlock();
+out_unlock_ctrl:
+	spin_unlock_irq(&real_tty->ctrl.lock);
+	return retval;
+}
+
+/**
+ *	tiocgsid		-	get session id
+ *	@tty: tty passed by user
+ *	@real_tty: tty side of the tty passed by the user if a pty else the tty
+ *	@p: pointer to returned session id
+ *
+ *	Obtain the session id of the tty. If there is no session
+ *	return an error.
+ */
+static int tiocgsid(struct tty_struct *tty, struct tty_struct *real_tty, pid_t __user *p)
+{
+	unsigned long flags;
+	pid_t sid;
+
+	/*
+	 * (tty == real_tty) is a cheap way of
+	 * testing if the tty is NOT a master pty.
+	 */
+	if (tty == real_tty && current->signal->tty != real_tty)
+		return -ENOTTY;
+
+	spin_lock_irqsave(&real_tty->ctrl.lock, flags);
+	if (!real_tty->ctrl.session)
+		goto err;
+	sid = pid_vnr(real_tty->ctrl.session);
+	spin_unlock_irqrestore(&real_tty->ctrl.lock, flags);
+
+	return put_user(sid, p);
+
+err:
+	spin_unlock_irqrestore(&real_tty->ctrl.lock, flags);
+	return -ENOTTY;
+}
+
+/*
+ * Called from tty_ioctl(). If tty is a pty then real_tty is the slave side,
+ * if not then tty == real_tty.
+ */
+long tty_jobctrl_ioctl(struct tty_struct *tty, struct tty_struct *real_tty,
+		       struct file *file, unsigned int cmd, unsigned long arg)
+{
+	void __user *p = (void __user *)arg;
+
+	switch (cmd) {
+	case TIOCNOTTY:
+		if (current->signal->tty != tty)
+			return -ENOTTY;
+		no_tty();
+		return 0;
+	case TIOCSCTTY:
+		return tiocsctty(real_tty, file, arg);
+	case TIOCGPGRP:
+		return tiocgpgrp(tty, real_tty, p);
+	case TIOCSPGRP:
+		return tiocspgrp(tty, real_tty, p);
+	case TIOCGSID:
+		return tiocgsid(tty, real_tty, p);
+	}
+	return -ENOIOCTLCMD;
+}