From 5b7c4cabbb65f5c469464da6c5f614cbd7f730f2 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Tue, 21 Feb 2023 18:24:12 -0800 Subject: Merge tag 'net-next-6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next 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(). ... --- kernel/nsproxy.c | 592 +++++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 592 insertions(+) create mode 100644 kernel/nsproxy.c (limited to 'kernel/nsproxy.c') diff --git a/kernel/nsproxy.c b/kernel/nsproxy.c new file mode 100644 index 000000000..a487ff241 --- /dev/null +++ b/kernel/nsproxy.c @@ -0,0 +1,592 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2006 IBM Corporation + * + * Author: Serge Hallyn + * + * Jun 2006 - namespaces support + * OpenVZ, SWsoft Inc. + * Pavel Emelianov + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +static struct kmem_cache *nsproxy_cachep; + +struct nsproxy init_nsproxy = { + .count = ATOMIC_INIT(1), + .uts_ns = &init_uts_ns, +#if defined(CONFIG_POSIX_MQUEUE) || defined(CONFIG_SYSVIPC) + .ipc_ns = &init_ipc_ns, +#endif + .mnt_ns = NULL, + .pid_ns_for_children = &init_pid_ns, +#ifdef CONFIG_NET + .net_ns = &init_net, +#endif +#ifdef CONFIG_CGROUPS + .cgroup_ns = &init_cgroup_ns, +#endif +#ifdef CONFIG_TIME_NS + .time_ns = &init_time_ns, + .time_ns_for_children = &init_time_ns, +#endif +}; + +static inline struct nsproxy *create_nsproxy(void) +{ + struct nsproxy *nsproxy; + + nsproxy = kmem_cache_alloc(nsproxy_cachep, GFP_KERNEL); + if (nsproxy) + atomic_set(&nsproxy->count, 1); + return nsproxy; +} + +/* + * Create new nsproxy and all of its the associated namespaces. + * Return the newly created nsproxy. Do not attach this to the task, + * leave it to the caller to do proper locking and attach it to task. + */ +static struct nsproxy *create_new_namespaces(unsigned long flags, + struct task_struct *tsk, struct user_namespace *user_ns, + struct fs_struct *new_fs) +{ + struct nsproxy *new_nsp; + int err; + + new_nsp = create_nsproxy(); + if (!new_nsp) + return ERR_PTR(-ENOMEM); + + new_nsp->mnt_ns = copy_mnt_ns(flags, tsk->nsproxy->mnt_ns, user_ns, new_fs); + if (IS_ERR(new_nsp->mnt_ns)) { + err = PTR_ERR(new_nsp->mnt_ns); + goto out_ns; + } + + new_nsp->uts_ns = copy_utsname(flags, user_ns, tsk->nsproxy->uts_ns); + if (IS_ERR(new_nsp->uts_ns)) { + err = PTR_ERR(new_nsp->uts_ns); + goto out_uts; + } + + new_nsp->ipc_ns = copy_ipcs(flags, user_ns, tsk->nsproxy->ipc_ns); + if (IS_ERR(new_nsp->ipc_ns)) { + err = PTR_ERR(new_nsp->ipc_ns); + goto out_ipc; + } + + new_nsp->pid_ns_for_children = + copy_pid_ns(flags, user_ns, tsk->nsproxy->pid_ns_for_children); + if (IS_ERR(new_nsp->pid_ns_for_children)) { + err = PTR_ERR(new_nsp->pid_ns_for_children); + goto out_pid; + } + + new_nsp->cgroup_ns = copy_cgroup_ns(flags, user_ns, + tsk->nsproxy->cgroup_ns); + if (IS_ERR(new_nsp->cgroup_ns)) { + err = PTR_ERR(new_nsp->cgroup_ns); + goto out_cgroup; + } + + new_nsp->net_ns = copy_net_ns(flags, user_ns, tsk->nsproxy->net_ns); + if (IS_ERR(new_nsp->net_ns)) { + err = PTR_ERR(new_nsp->net_ns); + goto out_net; + } + + new_nsp->time_ns_for_children = copy_time_ns(flags, user_ns, + tsk->nsproxy->time_ns_for_children); + if (IS_ERR(new_nsp->time_ns_for_children)) { + err = PTR_ERR(new_nsp->time_ns_for_children); + goto out_time; + } + new_nsp->time_ns = get_time_ns(tsk->nsproxy->time_ns); + + return new_nsp; + +out_time: + put_net(new_nsp->net_ns); +out_net: + put_cgroup_ns(new_nsp->cgroup_ns); +out_cgroup: + if (new_nsp->pid_ns_for_children) + put_pid_ns(new_nsp->pid_ns_for_children); +out_pid: + if (new_nsp->ipc_ns) + put_ipc_ns(new_nsp->ipc_ns); +out_ipc: + if (new_nsp->uts_ns) + put_uts_ns(new_nsp->uts_ns); +out_uts: + if (new_nsp->mnt_ns) + put_mnt_ns(new_nsp->mnt_ns); +out_ns: + kmem_cache_free(nsproxy_cachep, new_nsp); + return ERR_PTR(err); +} + +/* + * called from clone. This now handles copy for nsproxy and all + * namespaces therein. + */ +int copy_namespaces(unsigned long flags, struct task_struct *tsk) +{ + struct nsproxy *old_ns = tsk->nsproxy; + struct user_namespace *user_ns = task_cred_xxx(tsk, user_ns); + struct nsproxy *new_ns; + + if (likely(!(flags & (CLONE_NEWNS | CLONE_NEWUTS | CLONE_NEWIPC | + CLONE_NEWPID | CLONE_NEWNET | + CLONE_NEWCGROUP | CLONE_NEWTIME)))) { + if ((flags & CLONE_VM) || + likely(old_ns->time_ns_for_children == old_ns->time_ns)) { + get_nsproxy(old_ns); + return 0; + } + } else if (!ns_capable(user_ns, CAP_SYS_ADMIN)) + return -EPERM; + + /* + * CLONE_NEWIPC must detach from the undolist: after switching + * to a new ipc namespace, the semaphore arrays from the old + * namespace are unreachable. In clone parlance, CLONE_SYSVSEM + * means share undolist with parent, so we must forbid using + * it along with CLONE_NEWIPC. + */ + if ((flags & (CLONE_NEWIPC | CLONE_SYSVSEM)) == + (CLONE_NEWIPC | CLONE_SYSVSEM)) + return -EINVAL; + + new_ns = create_new_namespaces(flags, tsk, user_ns, tsk->fs); + if (IS_ERR(new_ns)) + return PTR_ERR(new_ns); + + if ((flags & CLONE_VM) == 0) + timens_on_fork(new_ns, tsk); + + tsk->nsproxy = new_ns; + return 0; +} + +void free_nsproxy(struct nsproxy *ns) +{ + if (ns->mnt_ns) + put_mnt_ns(ns->mnt_ns); + if (ns->uts_ns) + put_uts_ns(ns->uts_ns); + if (ns->ipc_ns) + put_ipc_ns(ns->ipc_ns); + if (ns->pid_ns_for_children) + put_pid_ns(ns->pid_ns_for_children); + if (ns->time_ns) + put_time_ns(ns->time_ns); + if (ns->time_ns_for_children) + put_time_ns(ns->time_ns_for_children); + put_cgroup_ns(ns->cgroup_ns); + put_net(ns->net_ns); + kmem_cache_free(nsproxy_cachep, ns); +} + +/* + * Called from unshare. Unshare all the namespaces part of nsproxy. + * On success, returns the new nsproxy. + */ +int unshare_nsproxy_namespaces(unsigned long unshare_flags, + struct nsproxy **new_nsp, struct cred *new_cred, struct fs_struct *new_fs) +{ + struct user_namespace *user_ns; + int err = 0; + + if (!(unshare_flags & (CLONE_NEWNS | CLONE_NEWUTS | CLONE_NEWIPC | + CLONE_NEWNET | CLONE_NEWPID | CLONE_NEWCGROUP | + CLONE_NEWTIME))) + return 0; + + user_ns = new_cred ? new_cred->user_ns : current_user_ns(); + if (!ns_capable(user_ns, CAP_SYS_ADMIN)) + return -EPERM; + + *new_nsp = create_new_namespaces(unshare_flags, current, user_ns, + new_fs ? new_fs : current->fs); + if (IS_ERR(*new_nsp)) { + err = PTR_ERR(*new_nsp); + goto out; + } + +out: + return err; +} + +void switch_task_namespaces(struct task_struct *p, struct nsproxy *new) +{ + struct nsproxy *ns; + + might_sleep(); + + task_lock(p); + ns = p->nsproxy; + p->nsproxy = new; + task_unlock(p); + + if (ns) + put_nsproxy(ns); +} + +void exit_task_namespaces(struct task_struct *p) +{ + switch_task_namespaces(p, NULL); +} + +int exec_task_namespaces(void) +{ + struct task_struct *tsk = current; + struct nsproxy *new; + + if (tsk->nsproxy->time_ns_for_children == tsk->nsproxy->time_ns) + return 0; + + new = create_new_namespaces(0, tsk, current_user_ns(), tsk->fs); + if (IS_ERR(new)) + return PTR_ERR(new); + + timens_on_fork(new, tsk); + switch_task_namespaces(tsk, new); + return 0; +} + +static int check_setns_flags(unsigned long flags) +{ + if (!flags || (flags & ~(CLONE_NEWNS | CLONE_NEWUTS | CLONE_NEWIPC | + CLONE_NEWNET | CLONE_NEWTIME | CLONE_NEWUSER | + CLONE_NEWPID | CLONE_NEWCGROUP))) + return -EINVAL; + +#ifndef CONFIG_USER_NS + if (flags & CLONE_NEWUSER) + return -EINVAL; +#endif +#ifndef CONFIG_PID_NS + if (flags & CLONE_NEWPID) + return -EINVAL; +#endif +#ifndef CONFIG_UTS_NS + if (flags & CLONE_NEWUTS) + return -EINVAL; +#endif +#ifndef CONFIG_IPC_NS + if (flags & CLONE_NEWIPC) + return -EINVAL; +#endif +#ifndef CONFIG_CGROUPS + if (flags & CLONE_NEWCGROUP) + return -EINVAL; +#endif +#ifndef CONFIG_NET_NS + if (flags & CLONE_NEWNET) + return -EINVAL; +#endif +#ifndef CONFIG_TIME_NS + if (flags & CLONE_NEWTIME) + return -EINVAL; +#endif + + return 0; +} + +static void put_nsset(struct nsset *nsset) +{ + unsigned flags = nsset->flags; + + if (flags & CLONE_NEWUSER) + put_cred(nsset_cred(nsset)); + /* + * We only created a temporary copy if we attached to more than just + * the mount namespace. + */ + if (nsset->fs && (flags & CLONE_NEWNS) && (flags & ~CLONE_NEWNS)) + free_fs_struct(nsset->fs); + if (nsset->nsproxy) + free_nsproxy(nsset->nsproxy); +} + +static int prepare_nsset(unsigned flags, struct nsset *nsset) +{ + struct task_struct *me = current; + + nsset->nsproxy = create_new_namespaces(0, me, current_user_ns(), me->fs); + if (IS_ERR(nsset->nsproxy)) + return PTR_ERR(nsset->nsproxy); + + if (flags & CLONE_NEWUSER) + nsset->cred = prepare_creds(); + else + nsset->cred = current_cred(); + if (!nsset->cred) + goto out; + + /* Only create a temporary copy of fs_struct if we really need to. */ + if (flags == CLONE_NEWNS) { + nsset->fs = me->fs; + } else if (flags & CLONE_NEWNS) { + nsset->fs = copy_fs_struct(me->fs); + if (!nsset->fs) + goto out; + } + + nsset->flags = flags; + return 0; + +out: + put_nsset(nsset); + return -ENOMEM; +} + +static inline int validate_ns(struct nsset *nsset, struct ns_common *ns) +{ + return ns->ops->install(nsset, ns); +} + +/* + * This is the inverse operation to unshare(). + * Ordering is equivalent to the standard ordering used everywhere else + * during unshare and process creation. The switch to the new set of + * namespaces occurs at the point of no return after installation of + * all requested namespaces was successful in commit_nsset(). + */ +static int validate_nsset(struct nsset *nsset, struct pid *pid) +{ + int ret = 0; + unsigned flags = nsset->flags; + struct user_namespace *user_ns = NULL; + struct pid_namespace *pid_ns = NULL; + struct nsproxy *nsp; + struct task_struct *tsk; + + /* Take a "snapshot" of the target task's namespaces. */ + rcu_read_lock(); + tsk = pid_task(pid, PIDTYPE_PID); + if (!tsk) { + rcu_read_unlock(); + return -ESRCH; + } + + if (!ptrace_may_access(tsk, PTRACE_MODE_READ_REALCREDS)) { + rcu_read_unlock(); + return -EPERM; + } + + task_lock(tsk); + nsp = tsk->nsproxy; + if (nsp) + get_nsproxy(nsp); + task_unlock(tsk); + if (!nsp) { + rcu_read_unlock(); + return -ESRCH; + } + +#ifdef CONFIG_PID_NS + if (flags & CLONE_NEWPID) { + pid_ns = task_active_pid_ns(tsk); + if (unlikely(!pid_ns)) { + rcu_read_unlock(); + ret = -ESRCH; + goto out; + } + get_pid_ns(pid_ns); + } +#endif + +#ifdef CONFIG_USER_NS + if (flags & CLONE_NEWUSER) + user_ns = get_user_ns(__task_cred(tsk)->user_ns); +#endif + rcu_read_unlock(); + + /* + * Install requested namespaces. The caller will have + * verified earlier that the requested namespaces are + * supported on this kernel. We don't report errors here + * if a namespace is requested that isn't supported. + */ +#ifdef CONFIG_USER_NS + if (flags & CLONE_NEWUSER) { + ret = validate_ns(nsset, &user_ns->ns); + if (ret) + goto out; + } +#endif + + if (flags & CLONE_NEWNS) { + ret = validate_ns(nsset, from_mnt_ns(nsp->mnt_ns)); + if (ret) + goto out; + } + +#ifdef CONFIG_UTS_NS + if (flags & CLONE_NEWUTS) { + ret = validate_ns(nsset, &nsp->uts_ns->ns); + if (ret) + goto out; + } +#endif + +#ifdef CONFIG_IPC_NS + if (flags & CLONE_NEWIPC) { + ret = validate_ns(nsset, &nsp->ipc_ns->ns); + if (ret) + goto out; + } +#endif + +#ifdef CONFIG_PID_NS + if (flags & CLONE_NEWPID) { + ret = validate_ns(nsset, &pid_ns->ns); + if (ret) + goto out; + } +#endif + +#ifdef CONFIG_CGROUPS + if (flags & CLONE_NEWCGROUP) { + ret = validate_ns(nsset, &nsp->cgroup_ns->ns); + if (ret) + goto out; + } +#endif + +#ifdef CONFIG_NET_NS + if (flags & CLONE_NEWNET) { + ret = validate_ns(nsset, &nsp->net_ns->ns); + if (ret) + goto out; + } +#endif + +#ifdef CONFIG_TIME_NS + if (flags & CLONE_NEWTIME) { + ret = validate_ns(nsset, &nsp->time_ns->ns); + if (ret) + goto out; + } +#endif + +out: + if (pid_ns) + put_pid_ns(pid_ns); + if (nsp) + put_nsproxy(nsp); + put_user_ns(user_ns); + + return ret; +} + +/* + * This is the point of no return. There are just a few namespaces + * that do some actual work here and it's sufficiently minimal that + * a separate ns_common operation seems unnecessary for now. + * Unshare is doing the same thing. If we'll end up needing to do + * more in a given namespace or a helper here is ultimately not + * exported anymore a simple commit handler for each namespace + * should be added to ns_common. + */ +static void commit_nsset(struct nsset *nsset) +{ + unsigned flags = nsset->flags; + struct task_struct *me = current; + +#ifdef CONFIG_USER_NS + if (flags & CLONE_NEWUSER) { + /* transfer ownership */ + commit_creds(nsset_cred(nsset)); + nsset->cred = NULL; + } +#endif + + /* We only need to commit if we have used a temporary fs_struct. */ + if ((flags & CLONE_NEWNS) && (flags & ~CLONE_NEWNS)) { + set_fs_root(me->fs, &nsset->fs->root); + set_fs_pwd(me->fs, &nsset->fs->pwd); + } + +#ifdef CONFIG_IPC_NS + if (flags & CLONE_NEWIPC) + exit_sem(me); +#endif + +#ifdef CONFIG_TIME_NS + if (flags & CLONE_NEWTIME) + timens_commit(me, nsset->nsproxy->time_ns); +#endif + + /* transfer ownership */ + switch_task_namespaces(me, nsset->nsproxy); + nsset->nsproxy = NULL; +} + +SYSCALL_DEFINE2(setns, int, fd, int, flags) +{ + struct file *file; + struct ns_common *ns = NULL; + struct nsset nsset = {}; + int err = 0; + + file = fget(fd); + if (!file) + return -EBADF; + + if (proc_ns_file(file)) { + ns = get_proc_ns(file_inode(file)); + if (flags && (ns->ops->type != flags)) + err = -EINVAL; + flags = ns->ops->type; + } else if (!IS_ERR(pidfd_pid(file))) { + err = check_setns_flags(flags); + } else { + err = -EINVAL; + } + if (err) + goto out; + + err = prepare_nsset(flags, &nsset); + if (err) + goto out; + + if (proc_ns_file(file)) + err = validate_ns(&nsset, ns); + else + err = validate_nsset(&nsset, file->private_data); + if (!err) { + commit_nsset(&nsset); + perf_event_namespaces(current); + } + put_nsset(&nsset); +out: + fput(file); + return err; +} + +int __init nsproxy_cache_init(void) +{ + nsproxy_cachep = KMEM_CACHE(nsproxy, SLAB_PANIC|SLAB_ACCOUNT); + return 0; +} -- cgit v1.2.3