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/taskstats.c | 724 +++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 724 insertions(+) create mode 100644 kernel/taskstats.c (limited to 'kernel/taskstats.c') diff --git a/kernel/taskstats.c b/kernel/taskstats.c new file mode 100644 index 000000000..8ce3fa0c1 --- /dev/null +++ b/kernel/taskstats.c @@ -0,0 +1,724 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * taskstats.c - Export per-task statistics to userland + * + * Copyright (C) Shailabh Nagar, IBM Corp. 2006 + * (C) Balbir Singh, IBM Corp. 2006 + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +/* + * Maximum length of a cpumask that can be specified in + * the TASKSTATS_CMD_ATTR_REGISTER/DEREGISTER_CPUMASK attribute + */ +#define TASKSTATS_CPUMASK_MAXLEN (100+6*NR_CPUS) + +static DEFINE_PER_CPU(__u32, taskstats_seqnum); +static int family_registered; +struct kmem_cache *taskstats_cache; + +static struct genl_family family; + +static const struct nla_policy taskstats_cmd_get_policy[] = { + [TASKSTATS_CMD_ATTR_PID] = { .type = NLA_U32 }, + [TASKSTATS_CMD_ATTR_TGID] = { .type = NLA_U32 }, + [TASKSTATS_CMD_ATTR_REGISTER_CPUMASK] = { .type = NLA_STRING }, + [TASKSTATS_CMD_ATTR_DEREGISTER_CPUMASK] = { .type = NLA_STRING },}; + +static const struct nla_policy cgroupstats_cmd_get_policy[] = { + [CGROUPSTATS_CMD_ATTR_FD] = { .type = NLA_U32 }, +}; + +struct listener { + struct list_head list; + pid_t pid; + char valid; +}; + +struct listener_list { + struct rw_semaphore sem; + struct list_head list; +}; +static DEFINE_PER_CPU(struct listener_list, listener_array); + +enum actions { + REGISTER, + DEREGISTER, + CPU_DONT_CARE +}; + +static int prepare_reply(struct genl_info *info, u8 cmd, struct sk_buff **skbp, + size_t size) +{ + struct sk_buff *skb; + void *reply; + + /* + * If new attributes are added, please revisit this allocation + */ + skb = genlmsg_new(size, GFP_KERNEL); + if (!skb) + return -ENOMEM; + + if (!info) { + int seq = this_cpu_inc_return(taskstats_seqnum) - 1; + + reply = genlmsg_put(skb, 0, seq, &family, 0, cmd); + } else + reply = genlmsg_put_reply(skb, info, &family, 0, cmd); + if (reply == NULL) { + nlmsg_free(skb); + return -EINVAL; + } + + *skbp = skb; + return 0; +} + +/* + * Send taskstats data in @skb to listener with nl_pid @pid + */ +static int send_reply(struct sk_buff *skb, struct genl_info *info) +{ + struct genlmsghdr *genlhdr = nlmsg_data(nlmsg_hdr(skb)); + void *reply = genlmsg_data(genlhdr); + + genlmsg_end(skb, reply); + + return genlmsg_reply(skb, info); +} + +/* + * Send taskstats data in @skb to listeners registered for @cpu's exit data + */ +static void send_cpu_listeners(struct sk_buff *skb, + struct listener_list *listeners) +{ + struct genlmsghdr *genlhdr = nlmsg_data(nlmsg_hdr(skb)); + struct listener *s, *tmp; + struct sk_buff *skb_next, *skb_cur = skb; + void *reply = genlmsg_data(genlhdr); + int delcount = 0; + + genlmsg_end(skb, reply); + + down_read(&listeners->sem); + list_for_each_entry(s, &listeners->list, list) { + int rc; + + skb_next = NULL; + if (!list_is_last(&s->list, &listeners->list)) { + skb_next = skb_clone(skb_cur, GFP_KERNEL); + if (!skb_next) + break; + } + rc = genlmsg_unicast(&init_net, skb_cur, s->pid); + if (rc == -ECONNREFUSED) { + s->valid = 0; + delcount++; + } + skb_cur = skb_next; + } + up_read(&listeners->sem); + + if (skb_cur) + nlmsg_free(skb_cur); + + if (!delcount) + return; + + /* Delete invalidated entries */ + down_write(&listeners->sem); + list_for_each_entry_safe(s, tmp, &listeners->list, list) { + if (!s->valid) { + list_del(&s->list); + kfree(s); + } + } + up_write(&listeners->sem); +} + +static void exe_add_tsk(struct taskstats *stats, struct task_struct *tsk) +{ + /* No idea if I'm allowed to access that here, now. */ + struct file *exe_file = get_task_exe_file(tsk); + + if (exe_file) { + /* Following cp_new_stat64() in stat.c . */ + stats->ac_exe_dev = + huge_encode_dev(exe_file->f_inode->i_sb->s_dev); + stats->ac_exe_inode = exe_file->f_inode->i_ino; + fput(exe_file); + } else { + stats->ac_exe_dev = 0; + stats->ac_exe_inode = 0; + } +} + +static void fill_stats(struct user_namespace *user_ns, + struct pid_namespace *pid_ns, + struct task_struct *tsk, struct taskstats *stats) +{ + memset(stats, 0, sizeof(*stats)); + /* + * Each accounting subsystem adds calls to its functions to + * fill in relevant parts of struct taskstsats as follows + * + * per-task-foo(stats, tsk); + */ + + delayacct_add_tsk(stats, tsk); + + /* fill in basic acct fields */ + stats->version = TASKSTATS_VERSION; + stats->nvcsw = tsk->nvcsw; + stats->nivcsw = tsk->nivcsw; + bacct_add_tsk(user_ns, pid_ns, stats, tsk); + + /* fill in extended acct fields */ + xacct_add_tsk(stats, tsk); + + /* add executable info */ + exe_add_tsk(stats, tsk); +} + +static int fill_stats_for_pid(pid_t pid, struct taskstats *stats) +{ + struct task_struct *tsk; + + tsk = find_get_task_by_vpid(pid); + if (!tsk) + return -ESRCH; + fill_stats(current_user_ns(), task_active_pid_ns(current), tsk, stats); + put_task_struct(tsk); + return 0; +} + +static int fill_stats_for_tgid(pid_t tgid, struct taskstats *stats) +{ + struct task_struct *tsk, *first; + unsigned long flags; + int rc = -ESRCH; + u64 delta, utime, stime; + u64 start_time; + + /* + * Add additional stats from live tasks except zombie thread group + * leaders who are already counted with the dead tasks + */ + rcu_read_lock(); + first = find_task_by_vpid(tgid); + + if (!first || !lock_task_sighand(first, &flags)) + goto out; + + if (first->signal->stats) + memcpy(stats, first->signal->stats, sizeof(*stats)); + else + memset(stats, 0, sizeof(*stats)); + + tsk = first; + start_time = ktime_get_ns(); + do { + if (tsk->exit_state) + continue; + /* + * Accounting subsystem can call its functions here to + * fill in relevant parts of struct taskstsats as follows + * + * per-task-foo(stats, tsk); + */ + delayacct_add_tsk(stats, tsk); + + /* calculate task elapsed time in nsec */ + delta = start_time - tsk->start_time; + /* Convert to micro seconds */ + do_div(delta, NSEC_PER_USEC); + stats->ac_etime += delta; + + task_cputime(tsk, &utime, &stime); + stats->ac_utime += div_u64(utime, NSEC_PER_USEC); + stats->ac_stime += div_u64(stime, NSEC_PER_USEC); + + stats->nvcsw += tsk->nvcsw; + stats->nivcsw += tsk->nivcsw; + } while_each_thread(first, tsk); + + unlock_task_sighand(first, &flags); + rc = 0; +out: + rcu_read_unlock(); + + stats->version = TASKSTATS_VERSION; + /* + * Accounting subsystems can also add calls here to modify + * fields of taskstats. + */ + return rc; +} + +static void fill_tgid_exit(struct task_struct *tsk) +{ + unsigned long flags; + + spin_lock_irqsave(&tsk->sighand->siglock, flags); + if (!tsk->signal->stats) + goto ret; + + /* + * Each accounting subsystem calls its functions here to + * accumalate its per-task stats for tsk, into the per-tgid structure + * + * per-task-foo(tsk->signal->stats, tsk); + */ + delayacct_add_tsk(tsk->signal->stats, tsk); +ret: + spin_unlock_irqrestore(&tsk->sighand->siglock, flags); + return; +} + +static int add_del_listener(pid_t pid, const struct cpumask *mask, int isadd) +{ + struct listener_list *listeners; + struct listener *s, *tmp, *s2; + unsigned int cpu; + int ret = 0; + + if (!cpumask_subset(mask, cpu_possible_mask)) + return -EINVAL; + + if (current_user_ns() != &init_user_ns) + return -EINVAL; + + if (task_active_pid_ns(current) != &init_pid_ns) + return -EINVAL; + + if (isadd == REGISTER) { + for_each_cpu(cpu, mask) { + s = kmalloc_node(sizeof(struct listener), + GFP_KERNEL, cpu_to_node(cpu)); + if (!s) { + ret = -ENOMEM; + goto cleanup; + } + s->pid = pid; + s->valid = 1; + + listeners = &per_cpu(listener_array, cpu); + down_write(&listeners->sem); + list_for_each_entry(s2, &listeners->list, list) { + if (s2->pid == pid && s2->valid) + goto exists; + } + list_add(&s->list, &listeners->list); + s = NULL; +exists: + up_write(&listeners->sem); + kfree(s); /* nop if NULL */ + } + return 0; + } + + /* Deregister or cleanup */ +cleanup: + for_each_cpu(cpu, mask) { + listeners = &per_cpu(listener_array, cpu); + down_write(&listeners->sem); + list_for_each_entry_safe(s, tmp, &listeners->list, list) { + if (s->pid == pid) { + list_del(&s->list); + kfree(s); + break; + } + } + up_write(&listeners->sem); + } + return ret; +} + +static int parse(struct nlattr *na, struct cpumask *mask) +{ + char *data; + int len; + int ret; + + if (na == NULL) + return 1; + len = nla_len(na); + if (len > TASKSTATS_CPUMASK_MAXLEN) + return -E2BIG; + if (len < 1) + return -EINVAL; + data = kmalloc(len, GFP_KERNEL); + if (!data) + return -ENOMEM; + nla_strscpy(data, na, len); + ret = cpulist_parse(data, mask); + kfree(data); + return ret; +} + +static struct taskstats *mk_reply(struct sk_buff *skb, int type, u32 pid) +{ + struct nlattr *na, *ret; + int aggr; + + aggr = (type == TASKSTATS_TYPE_PID) + ? TASKSTATS_TYPE_AGGR_PID + : TASKSTATS_TYPE_AGGR_TGID; + + na = nla_nest_start_noflag(skb, aggr); + if (!na) + goto err; + + if (nla_put(skb, type, sizeof(pid), &pid) < 0) { + nla_nest_cancel(skb, na); + goto err; + } + ret = nla_reserve_64bit(skb, TASKSTATS_TYPE_STATS, + sizeof(struct taskstats), TASKSTATS_TYPE_NULL); + if (!ret) { + nla_nest_cancel(skb, na); + goto err; + } + nla_nest_end(skb, na); + + return nla_data(ret); +err: + return NULL; +} + +static int cgroupstats_user_cmd(struct sk_buff *skb, struct genl_info *info) +{ + int rc = 0; + struct sk_buff *rep_skb; + struct cgroupstats *stats; + struct nlattr *na; + size_t size; + u32 fd; + struct fd f; + + na = info->attrs[CGROUPSTATS_CMD_ATTR_FD]; + if (!na) + return -EINVAL; + + fd = nla_get_u32(info->attrs[CGROUPSTATS_CMD_ATTR_FD]); + f = fdget(fd); + if (!f.file) + return 0; + + size = nla_total_size(sizeof(struct cgroupstats)); + + rc = prepare_reply(info, CGROUPSTATS_CMD_NEW, &rep_skb, + size); + if (rc < 0) + goto err; + + na = nla_reserve(rep_skb, CGROUPSTATS_TYPE_CGROUP_STATS, + sizeof(struct cgroupstats)); + if (na == NULL) { + nlmsg_free(rep_skb); + rc = -EMSGSIZE; + goto err; + } + + stats = nla_data(na); + memset(stats, 0, sizeof(*stats)); + + rc = cgroupstats_build(stats, f.file->f_path.dentry); + if (rc < 0) { + nlmsg_free(rep_skb); + goto err; + } + + rc = send_reply(rep_skb, info); + +err: + fdput(f); + return rc; +} + +static int cmd_attr_register_cpumask(struct genl_info *info) +{ + cpumask_var_t mask; + int rc; + + if (!alloc_cpumask_var(&mask, GFP_KERNEL)) + return -ENOMEM; + rc = parse(info->attrs[TASKSTATS_CMD_ATTR_REGISTER_CPUMASK], mask); + if (rc < 0) + goto out; + rc = add_del_listener(info->snd_portid, mask, REGISTER); +out: + free_cpumask_var(mask); + return rc; +} + +static int cmd_attr_deregister_cpumask(struct genl_info *info) +{ + cpumask_var_t mask; + int rc; + + if (!alloc_cpumask_var(&mask, GFP_KERNEL)) + return -ENOMEM; + rc = parse(info->attrs[TASKSTATS_CMD_ATTR_DEREGISTER_CPUMASK], mask); + if (rc < 0) + goto out; + rc = add_del_listener(info->snd_portid, mask, DEREGISTER); +out: + free_cpumask_var(mask); + return rc; +} + +static size_t taskstats_packet_size(void) +{ + size_t size; + + size = nla_total_size(sizeof(u32)) + + nla_total_size_64bit(sizeof(struct taskstats)) + + nla_total_size(0); + + return size; +} + +static int cmd_attr_pid(struct genl_info *info) +{ + struct taskstats *stats; + struct sk_buff *rep_skb; + size_t size; + u32 pid; + int rc; + + size = taskstats_packet_size(); + + rc = prepare_reply(info, TASKSTATS_CMD_NEW, &rep_skb, size); + if (rc < 0) + return rc; + + rc = -EINVAL; + pid = nla_get_u32(info->attrs[TASKSTATS_CMD_ATTR_PID]); + stats = mk_reply(rep_skb, TASKSTATS_TYPE_PID, pid); + if (!stats) + goto err; + + rc = fill_stats_for_pid(pid, stats); + if (rc < 0) + goto err; + return send_reply(rep_skb, info); +err: + nlmsg_free(rep_skb); + return rc; +} + +static int cmd_attr_tgid(struct genl_info *info) +{ + struct taskstats *stats; + struct sk_buff *rep_skb; + size_t size; + u32 tgid; + int rc; + + size = taskstats_packet_size(); + + rc = prepare_reply(info, TASKSTATS_CMD_NEW, &rep_skb, size); + if (rc < 0) + return rc; + + rc = -EINVAL; + tgid = nla_get_u32(info->attrs[TASKSTATS_CMD_ATTR_TGID]); + stats = mk_reply(rep_skb, TASKSTATS_TYPE_TGID, tgid); + if (!stats) + goto err; + + rc = fill_stats_for_tgid(tgid, stats); + if (rc < 0) + goto err; + return send_reply(rep_skb, info); +err: + nlmsg_free(rep_skb); + return rc; +} + +static int taskstats_user_cmd(struct sk_buff *skb, struct genl_info *info) +{ + if (info->attrs[TASKSTATS_CMD_ATTR_REGISTER_CPUMASK]) + return cmd_attr_register_cpumask(info); + else if (info->attrs[TASKSTATS_CMD_ATTR_DEREGISTER_CPUMASK]) + return cmd_attr_deregister_cpumask(info); + else if (info->attrs[TASKSTATS_CMD_ATTR_PID]) + return cmd_attr_pid(info); + else if (info->attrs[TASKSTATS_CMD_ATTR_TGID]) + return cmd_attr_tgid(info); + else + return -EINVAL; +} + +static struct taskstats *taskstats_tgid_alloc(struct task_struct *tsk) +{ + struct signal_struct *sig = tsk->signal; + struct taskstats *stats_new, *stats; + + /* Pairs with smp_store_release() below. */ + stats = smp_load_acquire(&sig->stats); + if (stats || thread_group_empty(tsk)) + return stats; + + /* No problem if kmem_cache_zalloc() fails */ + stats_new = kmem_cache_zalloc(taskstats_cache, GFP_KERNEL); + + spin_lock_irq(&tsk->sighand->siglock); + stats = sig->stats; + if (!stats) { + /* + * Pairs with smp_store_release() above and order the + * kmem_cache_zalloc(). + */ + smp_store_release(&sig->stats, stats_new); + stats = stats_new; + stats_new = NULL; + } + spin_unlock_irq(&tsk->sighand->siglock); + + if (stats_new) + kmem_cache_free(taskstats_cache, stats_new); + + return stats; +} + +/* Send pid data out on exit */ +void taskstats_exit(struct task_struct *tsk, int group_dead) +{ + int rc; + struct listener_list *listeners; + struct taskstats *stats; + struct sk_buff *rep_skb; + size_t size; + int is_thread_group; + + if (!family_registered) + return; + + /* + * Size includes space for nested attributes + */ + size = taskstats_packet_size(); + + is_thread_group = !!taskstats_tgid_alloc(tsk); + if (is_thread_group) { + /* PID + STATS + TGID + STATS */ + size = 2 * size; + /* fill the tsk->signal->stats structure */ + fill_tgid_exit(tsk); + } + + listeners = raw_cpu_ptr(&listener_array); + if (list_empty(&listeners->list)) + return; + + rc = prepare_reply(NULL, TASKSTATS_CMD_NEW, &rep_skb, size); + if (rc < 0) + return; + + stats = mk_reply(rep_skb, TASKSTATS_TYPE_PID, + task_pid_nr_ns(tsk, &init_pid_ns)); + if (!stats) + goto err; + + fill_stats(&init_user_ns, &init_pid_ns, tsk, stats); + if (group_dead) + stats->ac_flag |= AGROUP; + + /* + * Doesn't matter if tsk is the leader or the last group member leaving + */ + if (!is_thread_group || !group_dead) + goto send; + + stats = mk_reply(rep_skb, TASKSTATS_TYPE_TGID, + task_tgid_nr_ns(tsk, &init_pid_ns)); + if (!stats) + goto err; + + memcpy(stats, tsk->signal->stats, sizeof(*stats)); + +send: + send_cpu_listeners(rep_skb, listeners); + return; +err: + nlmsg_free(rep_skb); +} + +static const struct genl_ops taskstats_ops[] = { + { + .cmd = TASKSTATS_CMD_GET, + .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, + .doit = taskstats_user_cmd, + .policy = taskstats_cmd_get_policy, + .maxattr = ARRAY_SIZE(taskstats_cmd_get_policy) - 1, + .flags = GENL_ADMIN_PERM, + }, + { + .cmd = CGROUPSTATS_CMD_GET, + .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, + .doit = cgroupstats_user_cmd, + .policy = cgroupstats_cmd_get_policy, + .maxattr = ARRAY_SIZE(cgroupstats_cmd_get_policy) - 1, + }, +}; + +static struct genl_family family __ro_after_init = { + .name = TASKSTATS_GENL_NAME, + .version = TASKSTATS_GENL_VERSION, + .module = THIS_MODULE, + .ops = taskstats_ops, + .n_ops = ARRAY_SIZE(taskstats_ops), + .resv_start_op = CGROUPSTATS_CMD_GET + 1, + .netnsok = true, +}; + +/* Needed early in initialization */ +void __init taskstats_init_early(void) +{ + unsigned int i; + + taskstats_cache = KMEM_CACHE(taskstats, SLAB_PANIC); + for_each_possible_cpu(i) { + INIT_LIST_HEAD(&(per_cpu(listener_array, i).list)); + init_rwsem(&(per_cpu(listener_array, i).sem)); + } +} + +static int __init taskstats_init(void) +{ + int rc; + + rc = genl_register_family(&family); + if (rc) + return rc; + + family_registered = 1; + pr_info("registered taskstats version %d\n", TASKSTATS_GENL_VERSION); + return 0; +} + +/* + * late initcall ensures initialization of statistics collection + * mechanisms precedes initialization of the taskstats interface + */ +late_initcall(taskstats_init); -- cgit v1.2.3