Thread (20 messages) flat view 20 messages, 4 authors, 7d ago
COOLING7d

[PATCH RFC 09/13] arm64: ftrace: Maintain Tasks RCU trampoline nesting in ftrace_caller

From: Josef Bacik <josef@toxicpanda.com>
Date: 2026-09-10 18:51:18
Also in: bpf, linux-arm-kernel, lkml, rcu, xen-devel
Subsystem: arm64 port (aarch64 architecture), function hooks (ftrace), the rest · Maintainers: Catalin Marinas, Will Deacon, Steven Rostedt, Masami Hiramatsu, Linus Torvalds

Bracket the call out to the ftrace_ops callback in ftrace_caller with an
increment/decrement of current->rcu_tramp_nesting, using x12/w13 which
are scratch there.  The read-modify-write is not atomic, but only current
modifies the count and every interrupting user is balanced, so nothing is
lost.

ftrace_caller itself, including the early CALL_OPS direct path and the
late direct tail that carry a BPF trampoline address in x17 with the
count at zero, is static kernel text: add an ftrace_static_tramp_end
marker after ftrace_stub_direct_tramp and provide
arch_rcu_tasks_ip_in_trampoline() covering
[ftrace_caller, ftrace_static_tramp_end) so the irq-exit check treats a
task interrupted anywhere in it as inside a trampoline.

The hook is built only under CONFIG_RCU_TASKS_PREEMPT_QS, which arm64
does not select until a later patch.

Assisted-by: LLM
Signed-off-by: Josef Bacik <josef@toxicpanda.com>
---
 arch/arm64/kernel/asm-offsets.c  |  3 +++
 arch/arm64/kernel/entry-ftrace.S | 35 +++++++++++++++++++++++++++++++++++
 arch/arm64/kernel/ftrace.c       | 16 ++++++++++++++++
 3 files changed, 54 insertions(+)
diff --git a/arch/arm64/kernel/asm-offsets.c b/arch/arm64/kernel/asm-offsets.c
index 9c853ed3ceab..f6655a284f18 100644
--- a/arch/arm64/kernel/asm-offsets.c
+++ b/arch/arm64/kernel/asm-offsets.c
@@ -39,6 +39,9 @@ int main(void)
   DEFINE(TSK_STACK,		offsetof(struct task_struct, stack));
 #ifdef CONFIG_STACKPROTECTOR
   DEFINE(TSK_STACK_CANARY,	offsetof(struct task_struct, stack_canary));
+#endif
+#ifdef CONFIG_TASKS_RCU
+  DEFINE(TSK_RCU_TRAMP_NESTING,	offsetof(struct task_struct, rcu_tramp_nesting));
 #endif
   BLANK();
   DEFINE(THREAD_CPU_CONTEXT,	offsetof(struct task_struct, thread.cpu_context));
diff --git a/arch/arm64/kernel/entry-ftrace.S b/arch/arm64/kernel/entry-ftrace.S
index 025140caafe7..46a102e7199a 100644
--- a/arch/arm64/kernel/entry-ftrace.S
+++ b/arch/arm64/kernel/entry-ftrace.S
@@ -14,6 +14,33 @@
 #include <asm/insn.h>
 
 #ifdef CONFIG_DYNAMIC_FTRACE_WITH_ARGS
+/*
+ * Tasks RCU trampoline nesting, see rcu_tasks_trampoline_enter().  The whole
+ * of ftrace_caller is treated as trampoline text by the irq-exit IP check (see
+ * arch_rcu_tasks_ip_in_trampoline()), so these only need to bracket the call
+ * out to ops->func; everything before the increment and after the decrement,
+ * including the direct-call tails that carry a BPF trampoline address in x17,
+ * is covered by that.  The count is only modified by current and every nested
+ * user (interrupts) is balanced, so a plain ldr/add/str is sufficient.
+ */
+	.macro rcu_tasks_tramp_enter, tsk:req, tmp:req
+#ifdef CONFIG_TASKS_RCU
+	mrs	\tsk, sp_el0
+	ldr	\tmp, [\tsk, #TSK_RCU_TRAMP_NESTING]
+	add	\tmp, \tmp, #1
+	str	\tmp, [\tsk, #TSK_RCU_TRAMP_NESTING]
+#endif
+	.endm
+
+	.macro rcu_tasks_tramp_exit, tsk:req, tmp:req
+#ifdef CONFIG_TASKS_RCU
+	mrs	\tsk, sp_el0
+	ldr	\tmp, [\tsk, #TSK_RCU_TRAMP_NESTING]
+	sub	\tmp, \tmp, #1
+	str	\tmp, [\tsk, #TSK_RCU_TRAMP_NESTING]
+#endif
+	.endm
+
 /*
  * Due to -fpatchable-function-entry=2, the compiler has placed two NOPs before
  * the regular function prologue. For an enabled callsite, ftrace_init_nop() and
@@ -94,6 +121,8 @@ SYM_CODE_START(ftrace_caller)
 	stp	x29, x30, [sp, #FREGS_SIZE]
 	add	x29, sp, #FREGS_SIZE
 
+	rcu_tasks_tramp_enter x12, w13
+
 	/* Prepare arguments for the tracer func */
 	sub	x0, x30, #AARCH64_INSN_SIZE		// ip (callsite's BL insn)
 	mov	x1, x9					// parent_ip (callsite's LR)
@@ -111,6 +140,8 @@ SYM_INNER_LABEL(ftrace_call, SYM_L_GLOBAL)
 	bl      ftrace_stub				// func(ip, parent_ip, op, regs)
 #endif
 
+	rcu_tasks_tramp_exit x12, w13
+
 /*
  * At the callsite x0-x8 and x19-x30 were live. Any C code will have preserved
  * x19-x29 per the AAPCS, and we created frame records upon entry, so we need
@@ -178,6 +209,10 @@ SYM_CODE_START(ftrace_stub_direct_tramp)
 SYM_CODE_END(ftrace_stub_direct_tramp)
 #endif /* CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS */
 
+/* End of [ftrace_caller, ...) for arch_rcu_tasks_ip_in_trampoline(). */
+SYM_CODE_START(ftrace_static_tramp_end)
+SYM_CODE_END(ftrace_static_tramp_end)
+
 #else /* CONFIG_DYNAMIC_FTRACE_WITH_ARGS */
 
 /*
diff --git a/arch/arm64/kernel/ftrace.c b/arch/arm64/kernel/ftrace.c
index e1a3c0b3a051..1b7ac2afed0d 100644
--- a/arch/arm64/kernel/ftrace.c
+++ b/arch/arm64/kernel/ftrace.c
@@ -17,6 +17,22 @@
 #include <asm/insn.h>
 #include <asm/text-patching.h>
 
+#ifdef CONFIG_RCU_TASKS_PREEMPT_QS
+extern void ftrace_static_tramp_end(void);
+
+/*
+ * See rcu_tasks_ip_in_trampoline().  ftrace_caller and ftrace_stub_direct_tramp
+ * are core kernel text but must be treated as trampolines: a task preempted in
+ * them may be carrying an ops pointer (x11) or a direct-call BPF trampoline
+ * address (x17) whose lifetime is guarded only by Tasks RCU.
+ */
+bool arch_rcu_tasks_ip_in_trampoline(unsigned long ip)
+{
+	return ip >= (unsigned long)ftrace_caller &&
+	       ip <  (unsigned long)ftrace_static_tramp_end;
+}
+#endif
+
 #ifdef CONFIG_DYNAMIC_FTRACE_WITH_ARGS
 struct fregs_offset {
 	const char *name;
-- 
2.55.0
Keyboard shortcuts
hback out one level
jnext message in thread
kprevious message in thread
ldrill in
Escclose help / fold thread tree
?toggle this help