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/bpf/task_iter.c | 864 +++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 864 insertions(+) create mode 100644 kernel/bpf/task_iter.c (limited to 'kernel/bpf/task_iter.c') diff --git a/kernel/bpf/task_iter.c b/kernel/bpf/task_iter.c new file mode 100644 index 000000000..c4ab9d6cd --- /dev/null +++ b/kernel/bpf/task_iter.c @@ -0,0 +1,864 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Copyright (c) 2020 Facebook */ + +#include +#include +#include +#include +#include +#include +#include +#include "mmap_unlock_work.h" + +static const char * const iter_task_type_names[] = { + "ALL", + "TID", + "PID", +}; + +struct bpf_iter_seq_task_common { + struct pid_namespace *ns; + enum bpf_iter_task_type type; + u32 pid; + u32 pid_visiting; +}; + +struct bpf_iter_seq_task_info { + /* The first field must be struct bpf_iter_seq_task_common. + * this is assumed by {init, fini}_seq_pidns() callback functions. + */ + struct bpf_iter_seq_task_common common; + u32 tid; +}; + +static struct task_struct *task_group_seq_get_next(struct bpf_iter_seq_task_common *common, + u32 *tid, + bool skip_if_dup_files) +{ + struct task_struct *task, *next_task; + struct pid *pid; + u32 saved_tid; + + if (!*tid) { + /* The first time, the iterator calls this function. */ + pid = find_pid_ns(common->pid, common->ns); + if (!pid) + return NULL; + + task = get_pid_task(pid, PIDTYPE_TGID); + if (!task) + return NULL; + + *tid = common->pid; + common->pid_visiting = common->pid; + + return task; + } + + /* If the control returns to user space and comes back to the + * kernel again, *tid and common->pid_visiting should be the + * same for task_seq_start() to pick up the correct task. + */ + if (*tid == common->pid_visiting) { + pid = find_pid_ns(common->pid_visiting, common->ns); + task = get_pid_task(pid, PIDTYPE_PID); + + return task; + } + + pid = find_pid_ns(common->pid_visiting, common->ns); + if (!pid) + return NULL; + + task = get_pid_task(pid, PIDTYPE_PID); + if (!task) + return NULL; + +retry: + if (!pid_alive(task)) { + put_task_struct(task); + return NULL; + } + + next_task = next_thread(task); + put_task_struct(task); + if (!next_task) + return NULL; + + saved_tid = *tid; + *tid = __task_pid_nr_ns(next_task, PIDTYPE_PID, common->ns); + if (!*tid || *tid == common->pid) { + /* Run out of tasks of a process. The tasks of a + * thread_group are linked as circular linked list. + */ + *tid = saved_tid; + return NULL; + } + + get_task_struct(next_task); + common->pid_visiting = *tid; + + if (skip_if_dup_files && task->files == task->group_leader->files) { + task = next_task; + goto retry; + } + + return next_task; +} + +static struct task_struct *task_seq_get_next(struct bpf_iter_seq_task_common *common, + u32 *tid, + bool skip_if_dup_files) +{ + struct task_struct *task = NULL; + struct pid *pid; + + if (common->type == BPF_TASK_ITER_TID) { + if (*tid && *tid != common->pid) + return NULL; + rcu_read_lock(); + pid = find_pid_ns(common->pid, common->ns); + if (pid) { + task = get_pid_task(pid, PIDTYPE_TGID); + *tid = common->pid; + } + rcu_read_unlock(); + + return task; + } + + if (common->type == BPF_TASK_ITER_TGID) { + rcu_read_lock(); + task = task_group_seq_get_next(common, tid, skip_if_dup_files); + rcu_read_unlock(); + + return task; + } + + rcu_read_lock(); +retry: + pid = find_ge_pid(*tid, common->ns); + if (pid) { + *tid = pid_nr_ns(pid, common->ns); + task = get_pid_task(pid, PIDTYPE_PID); + if (!task) { + ++*tid; + goto retry; + } else if (skip_if_dup_files && !thread_group_leader(task) && + task->files == task->group_leader->files) { + put_task_struct(task); + task = NULL; + ++*tid; + goto retry; + } + } + rcu_read_unlock(); + + return task; +} + +static void *task_seq_start(struct seq_file *seq, loff_t *pos) +{ + struct bpf_iter_seq_task_info *info = seq->private; + struct task_struct *task; + + task = task_seq_get_next(&info->common, &info->tid, false); + if (!task) + return NULL; + + if (*pos == 0) + ++*pos; + return task; +} + +static void *task_seq_next(struct seq_file *seq, void *v, loff_t *pos) +{ + struct bpf_iter_seq_task_info *info = seq->private; + struct task_struct *task; + + ++*pos; + ++info->tid; + put_task_struct((struct task_struct *)v); + task = task_seq_get_next(&info->common, &info->tid, false); + if (!task) + return NULL; + + return task; +} + +struct bpf_iter__task { + __bpf_md_ptr(struct bpf_iter_meta *, meta); + __bpf_md_ptr(struct task_struct *, task); +}; + +DEFINE_BPF_ITER_FUNC(task, struct bpf_iter_meta *meta, struct task_struct *task) + +static int __task_seq_show(struct seq_file *seq, struct task_struct *task, + bool in_stop) +{ + struct bpf_iter_meta meta; + struct bpf_iter__task ctx; + struct bpf_prog *prog; + + meta.seq = seq; + prog = bpf_iter_get_info(&meta, in_stop); + if (!prog) + return 0; + + ctx.meta = &meta; + ctx.task = task; + return bpf_iter_run_prog(prog, &ctx); +} + +static int task_seq_show(struct seq_file *seq, void *v) +{ + return __task_seq_show(seq, v, false); +} + +static void task_seq_stop(struct seq_file *seq, void *v) +{ + if (!v) + (void)__task_seq_show(seq, v, true); + else + put_task_struct((struct task_struct *)v); +} + +static int bpf_iter_attach_task(struct bpf_prog *prog, + union bpf_iter_link_info *linfo, + struct bpf_iter_aux_info *aux) +{ + unsigned int flags; + struct pid *pid; + pid_t tgid; + + if ((!!linfo->task.tid + !!linfo->task.pid + !!linfo->task.pid_fd) > 1) + return -EINVAL; + + aux->task.type = BPF_TASK_ITER_ALL; + if (linfo->task.tid != 0) { + aux->task.type = BPF_TASK_ITER_TID; + aux->task.pid = linfo->task.tid; + } + if (linfo->task.pid != 0) { + aux->task.type = BPF_TASK_ITER_TGID; + aux->task.pid = linfo->task.pid; + } + if (linfo->task.pid_fd != 0) { + aux->task.type = BPF_TASK_ITER_TGID; + + pid = pidfd_get_pid(linfo->task.pid_fd, &flags); + if (IS_ERR(pid)) + return PTR_ERR(pid); + + tgid = pid_nr_ns(pid, task_active_pid_ns(current)); + aux->task.pid = tgid; + put_pid(pid); + } + + return 0; +} + +static const struct seq_operations task_seq_ops = { + .start = task_seq_start, + .next = task_seq_next, + .stop = task_seq_stop, + .show = task_seq_show, +}; + +struct bpf_iter_seq_task_file_info { + /* The first field must be struct bpf_iter_seq_task_common. + * this is assumed by {init, fini}_seq_pidns() callback functions. + */ + struct bpf_iter_seq_task_common common; + struct task_struct *task; + u32 tid; + u32 fd; +}; + +static struct file * +task_file_seq_get_next(struct bpf_iter_seq_task_file_info *info) +{ + u32 saved_tid = info->tid; + struct task_struct *curr_task; + unsigned int curr_fd = info->fd; + + /* If this function returns a non-NULL file object, + * it held a reference to the task/file. + * Otherwise, it does not hold any reference. + */ +again: + if (info->task) { + curr_task = info->task; + curr_fd = info->fd; + } else { + curr_task = task_seq_get_next(&info->common, &info->tid, true); + if (!curr_task) { + info->task = NULL; + return NULL; + } + + /* set info->task */ + info->task = curr_task; + if (saved_tid == info->tid) + curr_fd = info->fd; + else + curr_fd = 0; + } + + rcu_read_lock(); + for (;; curr_fd++) { + struct file *f; + f = task_lookup_next_fd_rcu(curr_task, &curr_fd); + if (!f) + break; + if (!get_file_rcu(f)) + continue; + + /* set info->fd */ + info->fd = curr_fd; + rcu_read_unlock(); + return f; + } + + /* the current task is done, go to the next task */ + rcu_read_unlock(); + put_task_struct(curr_task); + + if (info->common.type == BPF_TASK_ITER_TID) { + info->task = NULL; + return NULL; + } + + info->task = NULL; + info->fd = 0; + saved_tid = ++(info->tid); + goto again; +} + +static void *task_file_seq_start(struct seq_file *seq, loff_t *pos) +{ + struct bpf_iter_seq_task_file_info *info = seq->private; + struct file *file; + + info->task = NULL; + file = task_file_seq_get_next(info); + if (file && *pos == 0) + ++*pos; + + return file; +} + +static void *task_file_seq_next(struct seq_file *seq, void *v, loff_t *pos) +{ + struct bpf_iter_seq_task_file_info *info = seq->private; + + ++*pos; + ++info->fd; + fput((struct file *)v); + return task_file_seq_get_next(info); +} + +struct bpf_iter__task_file { + __bpf_md_ptr(struct bpf_iter_meta *, meta); + __bpf_md_ptr(struct task_struct *, task); + u32 fd __aligned(8); + __bpf_md_ptr(struct file *, file); +}; + +DEFINE_BPF_ITER_FUNC(task_file, struct bpf_iter_meta *meta, + struct task_struct *task, u32 fd, + struct file *file) + +static int __task_file_seq_show(struct seq_file *seq, struct file *file, + bool in_stop) +{ + struct bpf_iter_seq_task_file_info *info = seq->private; + struct bpf_iter__task_file ctx; + struct bpf_iter_meta meta; + struct bpf_prog *prog; + + meta.seq = seq; + prog = bpf_iter_get_info(&meta, in_stop); + if (!prog) + return 0; + + ctx.meta = &meta; + ctx.task = info->task; + ctx.fd = info->fd; + ctx.file = file; + return bpf_iter_run_prog(prog, &ctx); +} + +static int task_file_seq_show(struct seq_file *seq, void *v) +{ + return __task_file_seq_show(seq, v, false); +} + +static void task_file_seq_stop(struct seq_file *seq, void *v) +{ + struct bpf_iter_seq_task_file_info *info = seq->private; + + if (!v) { + (void)__task_file_seq_show(seq, v, true); + } else { + fput((struct file *)v); + put_task_struct(info->task); + info->task = NULL; + } +} + +static int init_seq_pidns(void *priv_data, struct bpf_iter_aux_info *aux) +{ + struct bpf_iter_seq_task_common *common = priv_data; + + common->ns = get_pid_ns(task_active_pid_ns(current)); + common->type = aux->task.type; + common->pid = aux->task.pid; + + return 0; +} + +static void fini_seq_pidns(void *priv_data) +{ + struct bpf_iter_seq_task_common *common = priv_data; + + put_pid_ns(common->ns); +} + +static const struct seq_operations task_file_seq_ops = { + .start = task_file_seq_start, + .next = task_file_seq_next, + .stop = task_file_seq_stop, + .show = task_file_seq_show, +}; + +struct bpf_iter_seq_task_vma_info { + /* The first field must be struct bpf_iter_seq_task_common. + * this is assumed by {init, fini}_seq_pidns() callback functions. + */ + struct bpf_iter_seq_task_common common; + struct task_struct *task; + struct mm_struct *mm; + struct vm_area_struct *vma; + u32 tid; + unsigned long prev_vm_start; + unsigned long prev_vm_end; +}; + +enum bpf_task_vma_iter_find_op { + task_vma_iter_first_vma, /* use find_vma() with addr 0 */ + task_vma_iter_next_vma, /* use vma_next() with curr_vma */ + task_vma_iter_find_vma, /* use find_vma() to find next vma */ +}; + +static struct vm_area_struct * +task_vma_seq_get_next(struct bpf_iter_seq_task_vma_info *info) +{ + enum bpf_task_vma_iter_find_op op; + struct vm_area_struct *curr_vma; + struct task_struct *curr_task; + struct mm_struct *curr_mm; + u32 saved_tid = info->tid; + + /* If this function returns a non-NULL vma, it holds a reference to + * the task_struct, holds a refcount on mm->mm_users, and holds + * read lock on vma->mm->mmap_lock. + * If this function returns NULL, it does not hold any reference or + * lock. + */ + if (info->task) { + curr_task = info->task; + curr_vma = info->vma; + curr_mm = info->mm; + /* In case of lock contention, drop mmap_lock to unblock + * the writer. + * + * After relock, call find(mm, prev_vm_end - 1) to find + * new vma to process. + * + * +------+------+-----------+ + * | VMA1 | VMA2 | VMA3 | + * +------+------+-----------+ + * | | | | + * 4k 8k 16k 400k + * + * For example, curr_vma == VMA2. Before unlock, we set + * + * prev_vm_start = 8k + * prev_vm_end = 16k + * + * There are a few cases: + * + * 1) VMA2 is freed, but VMA3 exists. + * + * find_vma() will return VMA3, just process VMA3. + * + * 2) VMA2 still exists. + * + * find_vma() will return VMA2, process VMA2->next. + * + * 3) no more vma in this mm. + * + * Process the next task. + * + * 4) find_vma() returns a different vma, VMA2'. + * + * 4.1) If VMA2 covers same range as VMA2', skip VMA2', + * because we already covered the range; + * 4.2) VMA2 and VMA2' covers different ranges, process + * VMA2'. + */ + if (mmap_lock_is_contended(curr_mm)) { + info->prev_vm_start = curr_vma->vm_start; + info->prev_vm_end = curr_vma->vm_end; + op = task_vma_iter_find_vma; + mmap_read_unlock(curr_mm); + if (mmap_read_lock_killable(curr_mm)) { + mmput(curr_mm); + goto finish; + } + } else { + op = task_vma_iter_next_vma; + } + } else { +again: + curr_task = task_seq_get_next(&info->common, &info->tid, true); + if (!curr_task) { + info->tid++; + goto finish; + } + + if (saved_tid != info->tid) { + /* new task, process the first vma */ + op = task_vma_iter_first_vma; + } else { + /* Found the same tid, which means the user space + * finished data in previous buffer and read more. + * We dropped mmap_lock before returning to user + * space, so it is necessary to use find_vma() to + * find the next vma to process. + */ + op = task_vma_iter_find_vma; + } + + curr_mm = get_task_mm(curr_task); + if (!curr_mm) + goto next_task; + + if (mmap_read_lock_killable(curr_mm)) { + mmput(curr_mm); + goto finish; + } + } + + switch (op) { + case task_vma_iter_first_vma: + curr_vma = find_vma(curr_mm, 0); + break; + case task_vma_iter_next_vma: + curr_vma = find_vma(curr_mm, curr_vma->vm_end); + break; + case task_vma_iter_find_vma: + /* We dropped mmap_lock so it is necessary to use find_vma + * to find the next vma. This is similar to the mechanism + * in show_smaps_rollup(). + */ + curr_vma = find_vma(curr_mm, info->prev_vm_end - 1); + /* case 1) and 4.2) above just use curr_vma */ + + /* check for case 2) or case 4.1) above */ + if (curr_vma && + curr_vma->vm_start == info->prev_vm_start && + curr_vma->vm_end == info->prev_vm_end) + curr_vma = find_vma(curr_mm, curr_vma->vm_end); + break; + } + if (!curr_vma) { + /* case 3) above, or case 2) 4.1) with vma->next == NULL */ + mmap_read_unlock(curr_mm); + mmput(curr_mm); + goto next_task; + } + info->task = curr_task; + info->vma = curr_vma; + info->mm = curr_mm; + return curr_vma; + +next_task: + if (info->common.type == BPF_TASK_ITER_TID) + goto finish; + + put_task_struct(curr_task); + info->task = NULL; + info->mm = NULL; + info->tid++; + goto again; + +finish: + if (curr_task) + put_task_struct(curr_task); + info->task = NULL; + info->vma = NULL; + info->mm = NULL; + return NULL; +} + +static void *task_vma_seq_start(struct seq_file *seq, loff_t *pos) +{ + struct bpf_iter_seq_task_vma_info *info = seq->private; + struct vm_area_struct *vma; + + vma = task_vma_seq_get_next(info); + if (vma && *pos == 0) + ++*pos; + + return vma; +} + +static void *task_vma_seq_next(struct seq_file *seq, void *v, loff_t *pos) +{ + struct bpf_iter_seq_task_vma_info *info = seq->private; + + ++*pos; + return task_vma_seq_get_next(info); +} + +struct bpf_iter__task_vma { + __bpf_md_ptr(struct bpf_iter_meta *, meta); + __bpf_md_ptr(struct task_struct *, task); + __bpf_md_ptr(struct vm_area_struct *, vma); +}; + +DEFINE_BPF_ITER_FUNC(task_vma, struct bpf_iter_meta *meta, + struct task_struct *task, struct vm_area_struct *vma) + +static int __task_vma_seq_show(struct seq_file *seq, bool in_stop) +{ + struct bpf_iter_seq_task_vma_info *info = seq->private; + struct bpf_iter__task_vma ctx; + struct bpf_iter_meta meta; + struct bpf_prog *prog; + + meta.seq = seq; + prog = bpf_iter_get_info(&meta, in_stop); + if (!prog) + return 0; + + ctx.meta = &meta; + ctx.task = info->task; + ctx.vma = info->vma; + return bpf_iter_run_prog(prog, &ctx); +} + +static int task_vma_seq_show(struct seq_file *seq, void *v) +{ + return __task_vma_seq_show(seq, false); +} + +static void task_vma_seq_stop(struct seq_file *seq, void *v) +{ + struct bpf_iter_seq_task_vma_info *info = seq->private; + + if (!v) { + (void)__task_vma_seq_show(seq, true); + } else { + /* info->vma has not been seen by the BPF program. If the + * user space reads more, task_vma_seq_get_next should + * return this vma again. Set prev_vm_start to ~0UL, + * so that we don't skip the vma returned by the next + * find_vma() (case task_vma_iter_find_vma in + * task_vma_seq_get_next()). + */ + info->prev_vm_start = ~0UL; + info->prev_vm_end = info->vma->vm_end; + mmap_read_unlock(info->mm); + mmput(info->mm); + info->mm = NULL; + put_task_struct(info->task); + info->task = NULL; + } +} + +static const struct seq_operations task_vma_seq_ops = { + .start = task_vma_seq_start, + .next = task_vma_seq_next, + .stop = task_vma_seq_stop, + .show = task_vma_seq_show, +}; + +static const struct bpf_iter_seq_info task_seq_info = { + .seq_ops = &task_seq_ops, + .init_seq_private = init_seq_pidns, + .fini_seq_private = fini_seq_pidns, + .seq_priv_size = sizeof(struct bpf_iter_seq_task_info), +}; + +static int bpf_iter_fill_link_info(const struct bpf_iter_aux_info *aux, struct bpf_link_info *info) +{ + switch (aux->task.type) { + case BPF_TASK_ITER_TID: + info->iter.task.tid = aux->task.pid; + break; + case BPF_TASK_ITER_TGID: + info->iter.task.pid = aux->task.pid; + break; + default: + break; + } + return 0; +} + +static void bpf_iter_task_show_fdinfo(const struct bpf_iter_aux_info *aux, struct seq_file *seq) +{ + seq_printf(seq, "task_type:\t%s\n", iter_task_type_names[aux->task.type]); + if (aux->task.type == BPF_TASK_ITER_TID) + seq_printf(seq, "tid:\t%u\n", aux->task.pid); + else if (aux->task.type == BPF_TASK_ITER_TGID) + seq_printf(seq, "pid:\t%u\n", aux->task.pid); +} + +static struct bpf_iter_reg task_reg_info = { + .target = "task", + .attach_target = bpf_iter_attach_task, + .feature = BPF_ITER_RESCHED, + .ctx_arg_info_size = 1, + .ctx_arg_info = { + { offsetof(struct bpf_iter__task, task), + PTR_TO_BTF_ID_OR_NULL }, + }, + .seq_info = &task_seq_info, + .fill_link_info = bpf_iter_fill_link_info, + .show_fdinfo = bpf_iter_task_show_fdinfo, +}; + +static const struct bpf_iter_seq_info task_file_seq_info = { + .seq_ops = &task_file_seq_ops, + .init_seq_private = init_seq_pidns, + .fini_seq_private = fini_seq_pidns, + .seq_priv_size = sizeof(struct bpf_iter_seq_task_file_info), +}; + +static struct bpf_iter_reg task_file_reg_info = { + .target = "task_file", + .attach_target = bpf_iter_attach_task, + .feature = BPF_ITER_RESCHED, + .ctx_arg_info_size = 2, + .ctx_arg_info = { + { offsetof(struct bpf_iter__task_file, task), + PTR_TO_BTF_ID_OR_NULL }, + { offsetof(struct bpf_iter__task_file, file), + PTR_TO_BTF_ID_OR_NULL }, + }, + .seq_info = &task_file_seq_info, + .fill_link_info = bpf_iter_fill_link_info, + .show_fdinfo = bpf_iter_task_show_fdinfo, +}; + +static const struct bpf_iter_seq_info task_vma_seq_info = { + .seq_ops = &task_vma_seq_ops, + .init_seq_private = init_seq_pidns, + .fini_seq_private = fini_seq_pidns, + .seq_priv_size = sizeof(struct bpf_iter_seq_task_vma_info), +}; + +static struct bpf_iter_reg task_vma_reg_info = { + .target = "task_vma", + .attach_target = bpf_iter_attach_task, + .feature = BPF_ITER_RESCHED, + .ctx_arg_info_size = 2, + .ctx_arg_info = { + { offsetof(struct bpf_iter__task_vma, task), + PTR_TO_BTF_ID_OR_NULL }, + { offsetof(struct bpf_iter__task_vma, vma), + PTR_TO_BTF_ID_OR_NULL }, + }, + .seq_info = &task_vma_seq_info, + .fill_link_info = bpf_iter_fill_link_info, + .show_fdinfo = bpf_iter_task_show_fdinfo, +}; + +BPF_CALL_5(bpf_find_vma, struct task_struct *, task, u64, start, + bpf_callback_t, callback_fn, void *, callback_ctx, u64, flags) +{ + struct mmap_unlock_irq_work *work = NULL; + struct vm_area_struct *vma; + bool irq_work_busy = false; + struct mm_struct *mm; + int ret = -ENOENT; + + if (flags) + return -EINVAL; + + if (!task) + return -ENOENT; + + mm = task->mm; + if (!mm) + return -ENOENT; + + irq_work_busy = bpf_mmap_unlock_get_irq_work(&work); + + if (irq_work_busy || !mmap_read_trylock(mm)) + return -EBUSY; + + vma = find_vma(mm, start); + + if (vma && vma->vm_start <= start && vma->vm_end > start) { + callback_fn((u64)(long)task, (u64)(long)vma, + (u64)(long)callback_ctx, 0, 0); + ret = 0; + } + bpf_mmap_unlock_mm(work, mm); + return ret; +} + +const struct bpf_func_proto bpf_find_vma_proto = { + .func = bpf_find_vma, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_BTF_ID, + .arg1_btf_id = &btf_tracing_ids[BTF_TRACING_TYPE_TASK], + .arg2_type = ARG_ANYTHING, + .arg3_type = ARG_PTR_TO_FUNC, + .arg4_type = ARG_PTR_TO_STACK_OR_NULL, + .arg5_type = ARG_ANYTHING, +}; + +DEFINE_PER_CPU(struct mmap_unlock_irq_work, mmap_unlock_work); + +static void do_mmap_read_unlock(struct irq_work *entry) +{ + struct mmap_unlock_irq_work *work; + + if (WARN_ON_ONCE(IS_ENABLED(CONFIG_PREEMPT_RT))) + return; + + work = container_of(entry, struct mmap_unlock_irq_work, irq_work); + mmap_read_unlock_non_owner(work->mm); +} + +static int __init task_iter_init(void) +{ + struct mmap_unlock_irq_work *work; + int ret, cpu; + + for_each_possible_cpu(cpu) { + work = per_cpu_ptr(&mmap_unlock_work, cpu); + init_irq_work(&work->irq_work, do_mmap_read_unlock); + } + + task_reg_info.ctx_arg_info[0].btf_id = btf_tracing_ids[BTF_TRACING_TYPE_TASK]; + ret = bpf_iter_reg_target(&task_reg_info); + if (ret) + return ret; + + task_file_reg_info.ctx_arg_info[0].btf_id = btf_tracing_ids[BTF_TRACING_TYPE_TASK]; + task_file_reg_info.ctx_arg_info[1].btf_id = btf_tracing_ids[BTF_TRACING_TYPE_FILE]; + ret = bpf_iter_reg_target(&task_file_reg_info); + if (ret) + return ret; + + task_vma_reg_info.ctx_arg_info[0].btf_id = btf_tracing_ids[BTF_TRACING_TYPE_TASK]; + task_vma_reg_info.ctx_arg_info[1].btf_id = btf_tracing_ids[BTF_TRACING_TYPE_VMA]; + return bpf_iter_reg_target(&task_vma_reg_info); +} +late_initcall(task_iter_init); -- cgit v1.2.3