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(). ... --- lib/test_lockup.c | 620 ++++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 620 insertions(+) create mode 100644 lib/test_lockup.c (limited to 'lib/test_lockup.c') diff --git a/lib/test_lockup.c b/lib/test_lockup.c new file mode 100644 index 000000000..c3fd87d6c --- /dev/null +++ b/lib/test_lockup.c @@ -0,0 +1,620 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Test module to generate lockups + */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +static unsigned int time_secs; +module_param(time_secs, uint, 0600); +MODULE_PARM_DESC(time_secs, "lockup time in seconds, default 0"); + +static unsigned int time_nsecs; +module_param(time_nsecs, uint, 0600); +MODULE_PARM_DESC(time_nsecs, "nanoseconds part of lockup time, default 0"); + +static unsigned int cooldown_secs; +module_param(cooldown_secs, uint, 0600); +MODULE_PARM_DESC(cooldown_secs, "cooldown time between iterations in seconds, default 0"); + +static unsigned int cooldown_nsecs; +module_param(cooldown_nsecs, uint, 0600); +MODULE_PARM_DESC(cooldown_nsecs, "nanoseconds part of cooldown, default 0"); + +static unsigned int iterations = 1; +module_param(iterations, uint, 0600); +MODULE_PARM_DESC(iterations, "lockup iterations, default 1"); + +static bool all_cpus; +module_param(all_cpus, bool, 0400); +MODULE_PARM_DESC(all_cpus, "trigger lockup at all cpus at once"); + +static int wait_state; +static char *state = "R"; +module_param(state, charp, 0400); +MODULE_PARM_DESC(state, "wait in 'R' running (default), 'D' uninterruptible, 'K' killable, 'S' interruptible state"); + +static bool use_hrtimer; +module_param(use_hrtimer, bool, 0400); +MODULE_PARM_DESC(use_hrtimer, "use high-resolution timer for sleeping"); + +static bool iowait; +module_param(iowait, bool, 0400); +MODULE_PARM_DESC(iowait, "account sleep time as iowait"); + +static bool lock_read; +module_param(lock_read, bool, 0400); +MODULE_PARM_DESC(lock_read, "lock read-write locks for read"); + +static bool lock_single; +module_param(lock_single, bool, 0400); +MODULE_PARM_DESC(lock_single, "acquire locks only at one cpu"); + +static bool reacquire_locks; +module_param(reacquire_locks, bool, 0400); +MODULE_PARM_DESC(reacquire_locks, "release and reacquire locks/irq/preempt between iterations"); + +static bool touch_softlockup; +module_param(touch_softlockup, bool, 0600); +MODULE_PARM_DESC(touch_softlockup, "touch soft-lockup watchdog between iterations"); + +static bool touch_hardlockup; +module_param(touch_hardlockup, bool, 0600); +MODULE_PARM_DESC(touch_hardlockup, "touch hard-lockup watchdog between iterations"); + +static bool call_cond_resched; +module_param(call_cond_resched, bool, 0600); +MODULE_PARM_DESC(call_cond_resched, "call cond_resched() between iterations"); + +static bool measure_lock_wait; +module_param(measure_lock_wait, bool, 0400); +MODULE_PARM_DESC(measure_lock_wait, "measure lock wait time"); + +static unsigned long lock_wait_threshold = ULONG_MAX; +module_param(lock_wait_threshold, ulong, 0400); +MODULE_PARM_DESC(lock_wait_threshold, "print lock wait time longer than this in nanoseconds, default off"); + +static bool test_disable_irq; +module_param_named(disable_irq, test_disable_irq, bool, 0400); +MODULE_PARM_DESC(disable_irq, "disable interrupts: generate hard-lockups"); + +static bool disable_softirq; +module_param(disable_softirq, bool, 0400); +MODULE_PARM_DESC(disable_softirq, "disable bottom-half irq handlers"); + +static bool disable_preempt; +module_param(disable_preempt, bool, 0400); +MODULE_PARM_DESC(disable_preempt, "disable preemption: generate soft-lockups"); + +static bool lock_rcu; +module_param(lock_rcu, bool, 0400); +MODULE_PARM_DESC(lock_rcu, "grab rcu_read_lock: generate rcu stalls"); + +static bool lock_mmap_sem; +module_param(lock_mmap_sem, bool, 0400); +MODULE_PARM_DESC(lock_mmap_sem, "lock mm->mmap_lock: block procfs interfaces"); + +static unsigned long lock_rwsem_ptr; +module_param_unsafe(lock_rwsem_ptr, ulong, 0400); +MODULE_PARM_DESC(lock_rwsem_ptr, "lock rw_semaphore at address"); + +static unsigned long lock_mutex_ptr; +module_param_unsafe(lock_mutex_ptr, ulong, 0400); +MODULE_PARM_DESC(lock_mutex_ptr, "lock mutex at address"); + +static unsigned long lock_spinlock_ptr; +module_param_unsafe(lock_spinlock_ptr, ulong, 0400); +MODULE_PARM_DESC(lock_spinlock_ptr, "lock spinlock at address"); + +static unsigned long lock_rwlock_ptr; +module_param_unsafe(lock_rwlock_ptr, ulong, 0400); +MODULE_PARM_DESC(lock_rwlock_ptr, "lock rwlock at address"); + +static unsigned int alloc_pages_nr; +module_param_unsafe(alloc_pages_nr, uint, 0600); +MODULE_PARM_DESC(alloc_pages_nr, "allocate and free pages under locks"); + +static unsigned int alloc_pages_order; +module_param(alloc_pages_order, uint, 0400); +MODULE_PARM_DESC(alloc_pages_order, "page order to allocate"); + +static gfp_t alloc_pages_gfp = GFP_KERNEL; +module_param_unsafe(alloc_pages_gfp, uint, 0400); +MODULE_PARM_DESC(alloc_pages_gfp, "allocate pages with this gfp_mask, default GFP_KERNEL"); + +static bool alloc_pages_atomic; +module_param(alloc_pages_atomic, bool, 0400); +MODULE_PARM_DESC(alloc_pages_atomic, "allocate pages with GFP_ATOMIC"); + +static bool reallocate_pages; +module_param(reallocate_pages, bool, 0400); +MODULE_PARM_DESC(reallocate_pages, "free and allocate pages between iterations"); + +struct file *test_file; +static struct inode *test_inode; +static char test_file_path[256]; +module_param_string(file_path, test_file_path, sizeof(test_file_path), 0400); +MODULE_PARM_DESC(file_path, "file path to test"); + +static bool test_lock_inode; +module_param_named(lock_inode, test_lock_inode, bool, 0400); +MODULE_PARM_DESC(lock_inode, "lock file -> inode -> i_rwsem"); + +static bool test_lock_mapping; +module_param_named(lock_mapping, test_lock_mapping, bool, 0400); +MODULE_PARM_DESC(lock_mapping, "lock file -> mapping -> i_mmap_rwsem"); + +static bool test_lock_sb_umount; +module_param_named(lock_sb_umount, test_lock_sb_umount, bool, 0400); +MODULE_PARM_DESC(lock_sb_umount, "lock file -> sb -> s_umount"); + +static atomic_t alloc_pages_failed = ATOMIC_INIT(0); + +static atomic64_t max_lock_wait = ATOMIC64_INIT(0); + +static struct task_struct *main_task; +static int master_cpu; + +static void test_lock(bool master, bool verbose) +{ + u64 wait_start; + + if (measure_lock_wait) + wait_start = local_clock(); + + if (lock_mutex_ptr && master) { + if (verbose) + pr_notice("lock mutex %ps\n", (void *)lock_mutex_ptr); + mutex_lock((struct mutex *)lock_mutex_ptr); + } + + if (lock_rwsem_ptr && master) { + if (verbose) + pr_notice("lock rw_semaphore %ps\n", + (void *)lock_rwsem_ptr); + if (lock_read) + down_read((struct rw_semaphore *)lock_rwsem_ptr); + else + down_write((struct rw_semaphore *)lock_rwsem_ptr); + } + + if (lock_mmap_sem && master) { + if (verbose) + pr_notice("lock mmap_lock pid=%d\n", main_task->pid); + if (lock_read) + mmap_read_lock(main_task->mm); + else + mmap_write_lock(main_task->mm); + } + + if (test_disable_irq) + local_irq_disable(); + + if (disable_softirq) + local_bh_disable(); + + if (disable_preempt) + preempt_disable(); + + if (lock_rcu) + rcu_read_lock(); + + if (lock_spinlock_ptr && master) { + if (verbose) + pr_notice("lock spinlock %ps\n", + (void *)lock_spinlock_ptr); + spin_lock((spinlock_t *)lock_spinlock_ptr); + } + + if (lock_rwlock_ptr && master) { + if (verbose) + pr_notice("lock rwlock %ps\n", + (void *)lock_rwlock_ptr); + if (lock_read) + read_lock((rwlock_t *)lock_rwlock_ptr); + else + write_lock((rwlock_t *)lock_rwlock_ptr); + } + + if (measure_lock_wait) { + s64 cur_wait = local_clock() - wait_start; + s64 max_wait = atomic64_read(&max_lock_wait); + + do { + if (cur_wait < max_wait) + break; + max_wait = atomic64_cmpxchg(&max_lock_wait, + max_wait, cur_wait); + } while (max_wait != cur_wait); + + if (cur_wait > lock_wait_threshold) + pr_notice_ratelimited("lock wait %lld ns\n", cur_wait); + } +} + +static void test_unlock(bool master, bool verbose) +{ + if (lock_rwlock_ptr && master) { + if (lock_read) + read_unlock((rwlock_t *)lock_rwlock_ptr); + else + write_unlock((rwlock_t *)lock_rwlock_ptr); + if (verbose) + pr_notice("unlock rwlock %ps\n", + (void *)lock_rwlock_ptr); + } + + if (lock_spinlock_ptr && master) { + spin_unlock((spinlock_t *)lock_spinlock_ptr); + if (verbose) + pr_notice("unlock spinlock %ps\n", + (void *)lock_spinlock_ptr); + } + + if (lock_rcu) + rcu_read_unlock(); + + if (disable_preempt) + preempt_enable(); + + if (disable_softirq) + local_bh_enable(); + + if (test_disable_irq) + local_irq_enable(); + + if (lock_mmap_sem && master) { + if (lock_read) + mmap_read_unlock(main_task->mm); + else + mmap_write_unlock(main_task->mm); + if (verbose) + pr_notice("unlock mmap_lock pid=%d\n", main_task->pid); + } + + if (lock_rwsem_ptr && master) { + if (lock_read) + up_read((struct rw_semaphore *)lock_rwsem_ptr); + else + up_write((struct rw_semaphore *)lock_rwsem_ptr); + if (verbose) + pr_notice("unlock rw_semaphore %ps\n", + (void *)lock_rwsem_ptr); + } + + if (lock_mutex_ptr && master) { + mutex_unlock((struct mutex *)lock_mutex_ptr); + if (verbose) + pr_notice("unlock mutex %ps\n", + (void *)lock_mutex_ptr); + } +} + +static void test_alloc_pages(struct list_head *pages) +{ + struct page *page; + unsigned int i; + + for (i = 0; i < alloc_pages_nr; i++) { + page = alloc_pages(alloc_pages_gfp, alloc_pages_order); + if (!page) { + atomic_inc(&alloc_pages_failed); + break; + } + list_add(&page->lru, pages); + } +} + +static void test_free_pages(struct list_head *pages) +{ + struct page *page, *next; + + list_for_each_entry_safe(page, next, pages, lru) + __free_pages(page, alloc_pages_order); + INIT_LIST_HEAD(pages); +} + +static void test_wait(unsigned int secs, unsigned int nsecs) +{ + if (wait_state == TASK_RUNNING) { + if (secs) + mdelay(secs * MSEC_PER_SEC); + if (nsecs) + ndelay(nsecs); + return; + } + + __set_current_state(wait_state); + if (use_hrtimer) { + ktime_t time; + + time = ns_to_ktime((u64)secs * NSEC_PER_SEC + nsecs); + schedule_hrtimeout(&time, HRTIMER_MODE_REL); + } else { + schedule_timeout(secs * HZ + nsecs_to_jiffies(nsecs)); + } +} + +static void test_lockup(bool master) +{ + u64 lockup_start = local_clock(); + unsigned int iter = 0; + LIST_HEAD(pages); + + pr_notice("Start on CPU%d\n", raw_smp_processor_id()); + + test_lock(master, true); + + test_alloc_pages(&pages); + + while (iter++ < iterations && !signal_pending(main_task)) { + + if (iowait) + current->in_iowait = 1; + + test_wait(time_secs, time_nsecs); + + if (iowait) + current->in_iowait = 0; + + if (reallocate_pages) + test_free_pages(&pages); + + if (reacquire_locks) + test_unlock(master, false); + + if (touch_softlockup) + touch_softlockup_watchdog(); + + if (touch_hardlockup) + touch_nmi_watchdog(); + + if (call_cond_resched) + cond_resched(); + + test_wait(cooldown_secs, cooldown_nsecs); + + if (reacquire_locks) + test_lock(master, false); + + if (reallocate_pages) + test_alloc_pages(&pages); + } + + pr_notice("Finish on CPU%d in %lld ns\n", raw_smp_processor_id(), + local_clock() - lockup_start); + + test_free_pages(&pages); + + test_unlock(master, true); +} + +static DEFINE_PER_CPU(struct work_struct, test_works); + +static void test_work_fn(struct work_struct *work) +{ + test_lockup(!lock_single || + work == per_cpu_ptr(&test_works, master_cpu)); +} + +static bool test_kernel_ptr(unsigned long addr, int size) +{ + void *ptr = (void *)addr; + char buf; + + if (!addr) + return false; + + /* should be at least readable kernel address */ + if (!IS_ENABLED(CONFIG_ALTERNATE_USER_ADDRESS_SPACE) && + (access_ok((void __user *)ptr, 1) || + access_ok((void __user *)ptr + size - 1, 1))) { + pr_err("user space ptr invalid in kernel: %#lx\n", addr); + return true; + } + + if (get_kernel_nofault(buf, ptr) || + get_kernel_nofault(buf, ptr + size - 1)) { + pr_err("invalid kernel ptr: %#lx\n", addr); + return true; + } + + return false; +} + +static bool __maybe_unused test_magic(unsigned long addr, int offset, + unsigned int expected) +{ + void *ptr = (void *)addr + offset; + unsigned int magic = 0; + + if (!addr) + return false; + + if (get_kernel_nofault(magic, ptr) || magic != expected) { + pr_err("invalid magic at %#lx + %#x = %#x, expected %#x\n", + addr, offset, magic, expected); + return true; + } + + return false; +} + +static int __init test_lockup_init(void) +{ + u64 test_start = local_clock(); + + main_task = current; + + switch (state[0]) { + case 'S': + wait_state = TASK_INTERRUPTIBLE; + break; + case 'D': + wait_state = TASK_UNINTERRUPTIBLE; + break; + case 'K': + wait_state = TASK_KILLABLE; + break; + case 'R': + wait_state = TASK_RUNNING; + break; + default: + pr_err("unknown state=%s\n", state); + return -EINVAL; + } + + if (alloc_pages_atomic) + alloc_pages_gfp = GFP_ATOMIC; + + if (test_kernel_ptr(lock_spinlock_ptr, sizeof(spinlock_t)) || + test_kernel_ptr(lock_rwlock_ptr, sizeof(rwlock_t)) || + test_kernel_ptr(lock_mutex_ptr, sizeof(struct mutex)) || + test_kernel_ptr(lock_rwsem_ptr, sizeof(struct rw_semaphore))) + return -EINVAL; + +#ifdef CONFIG_DEBUG_SPINLOCK +#ifdef CONFIG_PREEMPT_RT + if (test_magic(lock_spinlock_ptr, + offsetof(spinlock_t, lock.wait_lock.magic), + SPINLOCK_MAGIC) || + test_magic(lock_rwlock_ptr, + offsetof(rwlock_t, rwbase.rtmutex.wait_lock.magic), + SPINLOCK_MAGIC) || + test_magic(lock_mutex_ptr, + offsetof(struct mutex, rtmutex.wait_lock.magic), + SPINLOCK_MAGIC) || + test_magic(lock_rwsem_ptr, + offsetof(struct rw_semaphore, rwbase.rtmutex.wait_lock.magic), + SPINLOCK_MAGIC)) + return -EINVAL; +#else + if (test_magic(lock_spinlock_ptr, + offsetof(spinlock_t, rlock.magic), + SPINLOCK_MAGIC) || + test_magic(lock_rwlock_ptr, + offsetof(rwlock_t, magic), + RWLOCK_MAGIC) || + test_magic(lock_mutex_ptr, + offsetof(struct mutex, wait_lock.magic), + SPINLOCK_MAGIC) || + test_magic(lock_rwsem_ptr, + offsetof(struct rw_semaphore, wait_lock.magic), + SPINLOCK_MAGIC)) + return -EINVAL; +#endif +#endif + + if ((wait_state != TASK_RUNNING || + (call_cond_resched && !reacquire_locks) || + (alloc_pages_nr && gfpflags_allow_blocking(alloc_pages_gfp))) && + (test_disable_irq || disable_softirq || disable_preempt || + lock_rcu || lock_spinlock_ptr || lock_rwlock_ptr)) { + pr_err("refuse to sleep in atomic context\n"); + return -EINVAL; + } + + if (lock_mmap_sem && !main_task->mm) { + pr_err("no mm to lock mmap_lock\n"); + return -EINVAL; + } + + if (test_file_path[0]) { + test_file = filp_open(test_file_path, O_RDONLY, 0); + if (IS_ERR(test_file)) { + pr_err("failed to open %s: %ld\n", test_file_path, PTR_ERR(test_file)); + return PTR_ERR(test_file); + } + test_inode = file_inode(test_file); + } else if (test_lock_inode || + test_lock_mapping || + test_lock_sb_umount) { + pr_err("no file to lock\n"); + return -EINVAL; + } + + if (test_lock_inode && test_inode) + lock_rwsem_ptr = (unsigned long)&test_inode->i_rwsem; + + if (test_lock_mapping && test_file && test_file->f_mapping) + lock_rwsem_ptr = (unsigned long)&test_file->f_mapping->i_mmap_rwsem; + + if (test_lock_sb_umount && test_inode) + lock_rwsem_ptr = (unsigned long)&test_inode->i_sb->s_umount; + + pr_notice("START pid=%d time=%u +%u ns cooldown=%u +%u ns iterations=%u state=%s %s%s%s%s%s%s%s%s%s%s%s\n", + main_task->pid, time_secs, time_nsecs, + cooldown_secs, cooldown_nsecs, iterations, state, + all_cpus ? "all_cpus " : "", + iowait ? "iowait " : "", + test_disable_irq ? "disable_irq " : "", + disable_softirq ? "disable_softirq " : "", + disable_preempt ? "disable_preempt " : "", + lock_rcu ? "lock_rcu " : "", + lock_read ? "lock_read " : "", + touch_softlockup ? "touch_softlockup " : "", + touch_hardlockup ? "touch_hardlockup " : "", + call_cond_resched ? "call_cond_resched " : "", + reacquire_locks ? "reacquire_locks " : ""); + + if (alloc_pages_nr) + pr_notice("ALLOCATE PAGES nr=%u order=%u gfp=%pGg %s\n", + alloc_pages_nr, alloc_pages_order, &alloc_pages_gfp, + reallocate_pages ? "reallocate_pages " : ""); + + if (all_cpus) { + unsigned int cpu; + + cpus_read_lock(); + + preempt_disable(); + master_cpu = smp_processor_id(); + for_each_online_cpu(cpu) { + INIT_WORK(per_cpu_ptr(&test_works, cpu), test_work_fn); + queue_work_on(cpu, system_highpri_wq, + per_cpu_ptr(&test_works, cpu)); + } + preempt_enable(); + + for_each_online_cpu(cpu) + flush_work(per_cpu_ptr(&test_works, cpu)); + + cpus_read_unlock(); + } else { + test_lockup(true); + } + + if (measure_lock_wait) + pr_notice("Maximum lock wait: %lld ns\n", + atomic64_read(&max_lock_wait)); + + if (alloc_pages_nr) + pr_notice("Page allocation failed %u times\n", + atomic_read(&alloc_pages_failed)); + + pr_notice("FINISH in %llu ns\n", local_clock() - test_start); + + if (test_file) + fput(test_file); + + if (signal_pending(main_task)) + return -EINTR; + + return -EAGAIN; +} +module_init(test_lockup_init); + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Konstantin Khlebnikov "); +MODULE_DESCRIPTION("Test module to generate lockups"); -- cgit v1.2.3