From 97eb35f3ad42de1c932ef1f7e2f0044d4fca35f4 Mon Sep 17 00:00:00 2001 From: Kumar Kartikeya Dwivedi Date: Sat, 15 Mar 2025 21:05:38 -0700 Subject: bpf: Introduce rqspinlock kfuncs Introduce four new kfuncs, bpf_res_spin_lock, and bpf_res_spin_unlock, and their irqsave/irqrestore variants, which wrap the rqspinlock APIs. bpf_res_spin_lock returns a conditional result, depending on whether the lock was acquired (NULL is returned when lock acquisition succeeds, non-NULL upon failure). The memory pointed to by the returned pointer upon failure can be dereferenced after the NULL check to obtain the error code. Instead of using the old bpf_spin_lock type, introduce a new type with the same layout, and the same alignment, but a different name to avoid type confusion. Preemption is disabled upon successful lock acquisition, however IRQs are not. Special kfuncs can be introduced later to allow disabling IRQs when taking a spin lock. Resilient locks are safe against AA deadlocks, hence not disabling IRQs currently does not allow violation of kernel safety. __irq_flag annotation is used to accept IRQ flags for the IRQ-variants, with the same semantics as existing bpf_local_irq_{save, restore}. These kfuncs will require additional verifier-side support in subsequent commits, to allow programs to hold multiple locks at the same time. Signed-off-by: Kumar Kartikeya Dwivedi Link: https://lore.kernel.org/r/20250316040541.108729-23-memxor@gmail.com Signed-off-by: Alexei Starovoitov --- kernel/bpf/rqspinlock.c | 74 +++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 74 insertions(+) (limited to 'kernel/bpf') diff --git a/kernel/bpf/rqspinlock.c b/kernel/bpf/rqspinlock.c index ed21ee010063..b896c4a75a5c 100644 --- a/kernel/bpf/rqspinlock.c +++ b/kernel/bpf/rqspinlock.c @@ -15,6 +15,8 @@ #include #include +#include +#include #include #include #include @@ -661,3 +663,75 @@ err_release_entry: EXPORT_SYMBOL_GPL(resilient_queued_spin_lock_slowpath); #endif /* CONFIG_QUEUED_SPINLOCKS */ + +__bpf_kfunc_start_defs(); + +__bpf_kfunc int bpf_res_spin_lock(struct bpf_res_spin_lock *lock) +{ + int ret; + + BUILD_BUG_ON(sizeof(rqspinlock_t) != sizeof(struct bpf_res_spin_lock)); + BUILD_BUG_ON(__alignof__(rqspinlock_t) != __alignof__(struct bpf_res_spin_lock)); + + preempt_disable(); + ret = res_spin_lock((rqspinlock_t *)lock); + if (unlikely(ret)) { + preempt_enable(); + return ret; + } + return 0; +} + +__bpf_kfunc void bpf_res_spin_unlock(struct bpf_res_spin_lock *lock) +{ + res_spin_unlock((rqspinlock_t *)lock); + preempt_enable(); +} + +__bpf_kfunc int bpf_res_spin_lock_irqsave(struct bpf_res_spin_lock *lock, unsigned long *flags__irq_flag) +{ + u64 *ptr = (u64 *)flags__irq_flag; + unsigned long flags; + int ret; + + preempt_disable(); + local_irq_save(flags); + ret = res_spin_lock((rqspinlock_t *)lock); + if (unlikely(ret)) { + local_irq_restore(flags); + preempt_enable(); + return ret; + } + *ptr = flags; + return 0; +} + +__bpf_kfunc void bpf_res_spin_unlock_irqrestore(struct bpf_res_spin_lock *lock, unsigned long *flags__irq_flag) +{ + u64 *ptr = (u64 *)flags__irq_flag; + unsigned long flags = *ptr; + + res_spin_unlock((rqspinlock_t *)lock); + local_irq_restore(flags); + preempt_enable(); +} + +__bpf_kfunc_end_defs(); + +BTF_KFUNCS_START(rqspinlock_kfunc_ids) +BTF_ID_FLAGS(func, bpf_res_spin_lock, KF_RET_NULL) +BTF_ID_FLAGS(func, bpf_res_spin_unlock) +BTF_ID_FLAGS(func, bpf_res_spin_lock_irqsave, KF_RET_NULL) +BTF_ID_FLAGS(func, bpf_res_spin_unlock_irqrestore) +BTF_KFUNCS_END(rqspinlock_kfunc_ids) + +static const struct btf_kfunc_id_set rqspinlock_kfunc_set = { + .owner = THIS_MODULE, + .set = &rqspinlock_kfunc_ids, +}; + +static __init int rqspinlock_register_kfuncs(void) +{ + return register_btf_kfunc_id_set(BPF_PROG_TYPE_UNSPEC, &rqspinlock_kfunc_set); +} +late_initcall(rqspinlock_register_kfuncs); -- cgit