linux-kernel - [PATCH bpf-next v1 20/22] bpf: Introduce rqspinlock kfuncs

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives
Hash Suite: Windows password security audit tool. GUI, reports in PDF.
[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20250107140004.2732830-21-memxor@gmail.com>
Date: Tue,  7 Jan 2025 06:00:02 -0800
From: Kumar Kartikeya Dwivedi <memxor@...il.com>
To: bpf@...r.kernel.org,
	linux-kernel@...r.kernel.org
Cc: Linus Torvalds <torvalds@...ux-foundation.org>,
	Peter Zijlstra <peterz@...radead.org>,
	Waiman Long <llong@...hat.com>,
	Alexei Starovoitov <ast@...nel.org>,
	Andrii Nakryiko <andrii@...nel.org>,
	Daniel Borkmann <daniel@...earbox.net>,
	Martin KaFai Lau <martin.lau@...nel.org>,
	Eduard Zingerman <eddyz87@...il.com>,
	"Paul E. McKenney" <paulmck@...nel.org>,
	Tejun Heo <tj@...nel.org>,
	Barret Rhoden <brho@...gle.com>,
	Josh Don <joshdon@...gle.com>,
	Dohyun Kim <dohyunkim@...gle.com>,
	kernel-team@...a.com
Subject: [PATCH bpf-next v1 20/22] 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 <memxor@...il.com>
---
 include/asm-generic/rqspinlock.h |  4 ++
 include/linux/bpf.h              |  1 +
 kernel/locking/rqspinlock.c      | 78 ++++++++++++++++++++++++++++++++
 3 files changed, 83 insertions(+)

diff --git a/include/asm-generic/rqspinlock.h b/include/asm-generic/rqspinlock.h
index 53be8426373c..22f8770f033b 100644
--- a/include/asm-generic/rqspinlock.h
+++ b/include/asm-generic/rqspinlock.h
@@ -14,6 +14,10 @@
 #include <linux/percpu.h>
 #include <asm/qspinlock.h>
 
+struct bpf_res_spin_lock {
+	u32 val;
+};
+
 struct qspinlock;
 typedef struct qspinlock rqspinlock_t;
 
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index feda0ce90f5a..f93a4f40aaaf 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -30,6 +30,7 @@
 #include <linux/static_call.h>
 #include <linux/memcontrol.h>
 #include <linux/cfi.h>
+#include <asm/rqspinlock.h>
 
 struct bpf_verifier_env;
 struct bpf_verifier_log;
diff --git a/kernel/locking/rqspinlock.c b/kernel/locking/rqspinlock.c
index 9d3036f5e613..2c6293d1298c 100644
--- a/kernel/locking/rqspinlock.c
+++ b/kernel/locking/rqspinlock.c
@@ -15,6 +15,8 @@
 
 #include <linux/smp.h>
 #include <linux/bug.h>
+#include <linux/bpf.h>
+#include <linux/err.h>
 #include <linux/cpumask.h>
 #include <linux/percpu.h>
 #include <linux/hardirq.h>
@@ -644,3 +646,79 @@ int __lockfunc resilient_queued_spin_lock_slowpath(struct qspinlock *lock, u32 v
 	return ret;
 }
 EXPORT_SYMBOL(resilient_queued_spin_lock_slowpath);
+
+__bpf_kfunc_start_defs();
+
+#define REPORT_STR(ret) ({ ret == -ETIMEDOUT ? "Timeout detected" : "AA or ABBA deadlock detected"; })
+
+__bpf_kfunc int bpf_res_spin_lock(struct bpf_res_spin_lock *lock)
+{
+	int ret;
+
+	BUILD_BUG_ON(sizeof(struct qspinlock) != sizeof(struct bpf_res_spin_lock));
+	BUILD_BUG_ON(__alignof__(struct qspinlock) != __alignof__(struct bpf_res_spin_lock));
+
+	preempt_disable();
+	ret = res_spin_lock((struct qspinlock *)lock);
+	if (unlikely(ret)) {
+		preempt_enable();
+		rqspinlock_report_violation(REPORT_STR(ret), lock);
+		return ret;
+	}
+	return 0;
+}
+
+__bpf_kfunc void bpf_res_spin_unlock(struct bpf_res_spin_lock *lock)
+{
+	res_spin_unlock((struct qspinlock *)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((struct qspinlock *)lock);
+	if (unlikely(ret)) {
+		local_irq_restore(flags);
+		preempt_enable();
+		rqspinlock_report_violation(REPORT_STR(ret), lock);
+		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((struct qspinlock *)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);
-- 
2.43.5