* [PATCH v4 5/7] riscv: stacktrace: switch to frame-pointer based unwinder
From: Wang Han @ 2026-06-29 6:42 UTC (permalink / raw)
To: Paul Walmsley, Palmer Dabbelt, Albert Ou
Cc: Alexandre Ghiti, linux-riscv, Oleg Nesterov, Steven Rostedt,
Masami Hiramatsu, Mark Rutland, Peter Zijlstra, Ingo Molnar,
Arnaldo Carvalho de Melo, Namhyung Kim, Alexander Shishkin,
Jiri Olsa, Ian Rogers, Adrian Hunter, James Clark, Josh Poimboeuf,
Jiri Kosina, Miroslav Benes, Petr Mladek, Joe Lawrence,
Shuah Khan, oliver.yang, xueshuai, zhuo.song, jkchen,
Marcos Paulo de Souza, linux-kernel, linux-trace-kernel,
linux-perf-users, live-patching, linux-kselftest
Replace the open-coded frame-pointer walker in arch_stack_walk() with a
robust kunwind state machine, modelled on arch/arm64/kernel/stacktrace.c
and retargeted to the RISC-V {fp, ra} frame record convention. The new
walker tracks stack bounds, consumes frame records monotonically,
understands the metadata pt_regs records added in the previous frame
record metadata patch, and recovers return addresses replaced by
function graph tracing and kretprobes.
This commit introduces arch_stack_walk_reliable() but does not yet
select HAVE_RELIABLE_STACKTRACE; that is done in a follow-up Kconfig
patch so this commit can be reviewed and bisected as a pure unwinder
replacement. Until that Kconfig change lands, livepatch is not yet
enabled and arch_stack_walk_reliable() has no in-tree caller.
Three related callers are updated to keep the same frame-record
assumptions everywhere:
* Function graph tracing: the old RISC-V unwinder matched function
graph return-stack entries by the saved return-address slot. That
was consistent with the static mcount path, but not with the dynamic
ftrace path where the parent slot is ftrace_regs::ra. Use the
architectural frame pointer as the function graph return-address
cookie, matching the kunwind walker.
* Perf callchains: route kernel callchain collection through
arch_stack_walk() so perf sees the same frame-pointer unwind
behaviour as dump_stack() and the upcoming livepatch path.
* dump_backtrace() / __get_wchan() / show_stack(): these now go
through arch_stack_walk(); the explicit "Call Trace:" header is
moved into dump_backtrace() to preserve the original output.
The non-frame-pointer fallback walker is kept untouched for
!CONFIG_FRAME_POINTER builds.
Signed-off-by: Wang Han <wanghan@linux.alibaba.com>
---
arch/riscv/kernel/ftrace.c | 6 +-
arch/riscv/kernel/perf_callchain.c | 2 +-
arch/riscv/kernel/stacktrace.c | 559 ++++++++++++++++++++++++-----
3 files changed, 471 insertions(+), 96 deletions(-)
diff --git a/arch/riscv/kernel/ftrace.c b/arch/riscv/kernel/ftrace.c
index b430edfb83f4..5d55199a9230 100644
--- a/arch/riscv/kernel/ftrace.c
+++ b/arch/riscv/kernel/ftrace.c
@@ -242,7 +242,8 @@ void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr,
*/
old = *parent;
- if (!function_graph_enter(old, self_addr, frame_pointer, parent))
+ if (!function_graph_enter(old, self_addr, frame_pointer,
+ (void *)frame_pointer))
*parent = return_hooker;
}
@@ -264,7 +265,8 @@ void ftrace_graph_func(unsigned long ip, unsigned long parent_ip,
*/
old = *parent;
- if (!function_graph_enter_regs(old, ip, frame_pointer, parent, fregs))
+ if (!function_graph_enter_regs(old, ip, frame_pointer,
+ (void *)frame_pointer, fregs))
*parent = return_hooker;
}
#endif /* CONFIG_DYNAMIC_FTRACE */
diff --git a/arch/riscv/kernel/perf_callchain.c b/arch/riscv/kernel/perf_callchain.c
index b465bc9eb870..436af96ea59c 100644
--- a/arch/riscv/kernel/perf_callchain.c
+++ b/arch/riscv/kernel/perf_callchain.c
@@ -44,5 +44,5 @@ void perf_callchain_kernel(struct perf_callchain_entry_ctx *entry,
return;
}
- walk_stackframe(NULL, regs, fill_callchain, entry);
+ arch_stack_walk(fill_callchain, entry, NULL, regs);
}
diff --git a/arch/riscv/kernel/stacktrace.c b/arch/riscv/kernel/stacktrace.c
index c7555447149b..c43bf9a84207 100644
--- a/arch/riscv/kernel/stacktrace.c
+++ b/arch/riscv/kernel/stacktrace.c
@@ -11,98 +11,16 @@
#include <linux/sched/task_stack.h>
#include <linux/stacktrace.h>
#include <linux/ftrace.h>
+#include <linux/kprobes.h>
+#include <linux/llist.h>
#include <asm/stacktrace.h>
-#ifdef CONFIG_FRAME_POINTER
-
/*
- * This disables KASAN checking when reading a value from another task's stack,
- * since the other task could be running on another CPU and could have poisoned
- * the stack in the meantime.
+ * Non-frame-pointer fallback unwinder.
+ * Only compiled when CONFIG_FRAME_POINTER is not enabled.
*/
-#define READ_ONCE_TASK_STACK(task, x) \
-({ \
- unsigned long val; \
- unsigned long addr = x; \
- if ((task) == current) \
- val = READ_ONCE(addr); \
- else \
- val = READ_ONCE_NOCHECK(addr); \
- val; \
-})
-
-extern asmlinkage void handle_exception(void);
-extern unsigned long ret_from_exception_end;
-
-static inline int fp_is_valid(unsigned long fp, unsigned long sp)
-{
- unsigned long low, high;
-
- low = sp + sizeof(struct stackframe);
- high = ALIGN(sp, THREAD_SIZE);
-
- return !(fp < low || fp > high || fp & 0x07);
-}
-
-void notrace walk_stackframe(struct task_struct *task, struct pt_regs *regs,
- bool (*fn)(void *, unsigned long), void *arg)
-{
- unsigned long fp, sp, pc;
- int graph_idx = 0;
- int level = 0;
-
- if (regs) {
- fp = frame_pointer(regs);
- sp = user_stack_pointer(regs);
- pc = instruction_pointer(regs);
- } else if (task == NULL || task == current) {
- fp = (unsigned long)__builtin_frame_address(0);
- sp = current_stack_pointer;
- pc = (unsigned long)walk_stackframe;
- level = -1;
- } else {
- /* task blocked in __switch_to */
- fp = task->thread.s[0];
- sp = task->thread.sp;
- pc = task->thread.ra;
- }
-
- for (;;) {
- struct stackframe *frame;
-
- if (unlikely(!__kernel_text_address(pc) || (level++ >= 0 && !fn(arg, pc))))
- break;
-
- if (unlikely(!fp_is_valid(fp, sp)))
- break;
-
- /* Unwind stack frame */
- frame = (struct stackframe *)fp - 1;
- sp = fp;
- if (regs && (regs->epc == pc) && fp_is_valid(frame->ra, sp)) {
- /* We hit function where ra is not saved on the stack */
- fp = frame->ra;
- pc = regs->ra;
- } else {
- fp = READ_ONCE_TASK_STACK(task, frame->fp);
- pc = READ_ONCE_TASK_STACK(task, frame->ra);
- pc = ftrace_graph_ret_addr(task, &graph_idx, pc,
- &frame->ra);
- if (pc >= (unsigned long)handle_exception &&
- pc < (unsigned long)&ret_from_exception_end) {
- if (unlikely(!fn(arg, pc)))
- break;
-
- pc = ((struct pt_regs *)sp)->epc;
- fp = ((struct pt_regs *)sp)->s0;
- }
- }
-
- }
-}
-
-#else /* !CONFIG_FRAME_POINTER */
+#ifndef CONFIG_FRAME_POINTER
void notrace walk_stackframe(struct task_struct *task,
struct pt_regs *regs, bool (*fn)(void *, unsigned long), void *arg)
@@ -133,7 +51,12 @@ void notrace walk_stackframe(struct task_struct *task,
}
}
-#endif /* CONFIG_FRAME_POINTER */
+#endif /* !CONFIG_FRAME_POINTER */
+
+/*
+ * Common trace helpers.
+ * These are used by both the FP (kunwind) and non-FP (walk_stackframe) paths.
+ */
static bool print_trace_address(void *arg, unsigned long pc)
{
@@ -146,12 +69,12 @@ static bool print_trace_address(void *arg, unsigned long pc)
noinline void dump_backtrace(struct pt_regs *regs, struct task_struct *task,
const char *loglvl)
{
- walk_stackframe(task, regs, print_trace_address, (void *)loglvl);
+ printk("%sCall Trace:\n", loglvl);
+ arch_stack_walk(print_trace_address, (void *)loglvl, task, regs);
}
void show_stack(struct task_struct *task, unsigned long *sp, const char *loglvl)
{
- pr_cont("%sCall Trace:\n", loglvl);
dump_backtrace(NULL, task, loglvl);
}
@@ -171,17 +94,467 @@ unsigned long __get_wchan(struct task_struct *task)
if (!try_get_task_stack(task))
return 0;
- walk_stackframe(task, NULL, save_wchan, &pc);
+ arch_stack_walk(save_wchan, &pc, task, NULL);
put_task_stack(task);
return pc;
}
-noinline noinstr void arch_stack_walk(stack_trace_consume_fn consume_entry, void *cookie,
- struct task_struct *task, struct pt_regs *regs)
+/*
+ * Frame-pointer-based kernel unwind infrastructure.
+ * Only compiled when CONFIG_FRAME_POINTER is enabled.
+ *
+ * See: arch/arm64/kernel/stacktrace.c for the reference implementation.
+ */
+#ifdef CONFIG_FRAME_POINTER
+
+/*
+ * Per-cpu stacks are only accessible when unwinding the current task in a
+ * non-preemptible context.
+ */
+#define STACKINFO_CPU(task, name) \
+ ({ \
+ (((task) == current) && !preemptible()) \
+ ? stackinfo_get_##name() \
+ : stackinfo_get_unknown(); \
+ })
+
+enum kunwind_source {
+ KUNWIND_SOURCE_UNKNOWN,
+ KUNWIND_SOURCE_FRAME,
+ KUNWIND_SOURCE_CALLER,
+ KUNWIND_SOURCE_TASK,
+ KUNWIND_SOURCE_REGS_PC,
+};
+
+union unwind_flags {
+ unsigned long all;
+ struct {
+ unsigned long fgraph : 1,
+ kretprobe : 1;
+ };
+};
+
+/*
+ * Kernel unwind state
+ *
+ * @common: Common unwind state.
+ * @task: The task being unwound.
+ * @graph_idx: Used by ftrace_graph_ret_addr() for optimized stack unwinding.
+ * @kr_cur: When KRETPROBES is selected, holds the kretprobe instance
+ * associated with the most recently encountered replacement ra
+ * value.
+ */
+struct kunwind_state {
+ struct unwind_state common;
+ struct task_struct *task;
+ int graph_idx;
+#ifdef CONFIG_KRETPROBES
+ struct llist_node *kr_cur;
+#endif
+ enum kunwind_source source;
+ union unwind_flags flags;
+ struct pt_regs *regs;
+};
+
+static __always_inline void
+kunwind_init(struct kunwind_state *state,
+ struct task_struct *task)
+{
+ unwind_init_common(&state->common);
+ state->task = task;
+ state->source = KUNWIND_SOURCE_UNKNOWN;
+ state->flags.all = 0;
+ state->regs = NULL;
+}
+
+/*
+ * Start an unwind from a pt_regs.
+ *
+ * The unwind will begin at the PC within the regs.
+ *
+ * The regs must be on a stack currently owned by the calling task.
+ */
+static __always_inline void
+kunwind_init_from_regs(struct kunwind_state *state,
+ struct pt_regs *regs)
+{
+ kunwind_init(state, current);
+
+ state->regs = regs;
+ state->common.fp = frame_pointer(regs);
+ state->common.pc = instruction_pointer(regs);
+ state->source = KUNWIND_SOURCE_REGS_PC;
+}
+
+/*
+ * Start an unwind from a caller.
+ *
+ * The unwind will begin at the caller of whichever function this is inlined
+ * into.
+ *
+ * The function which invokes this must be noinline.
+ */
+static __always_inline void
+kunwind_init_from_caller(struct kunwind_state *state)
+{
+ unsigned long fp = (unsigned long)__builtin_frame_address(0);
+ struct frame_record *record = (struct frame_record *)fp - 1;
+
+ kunwind_init(state, current);
+
+ state->common.fp = READ_ONCE(record->fp);
+ state->common.pc = READ_ONCE(record->ra);
+ state->source = KUNWIND_SOURCE_CALLER;
+}
+
+/*
+ * Start an unwind from a blocked task.
+ *
+ * The unwind will begin at the blocked task's saved PC (i.e. the caller of
+ * __switch_to).
+ *
+ * The caller should ensure the task is blocked in __switch_to for the
+ * duration of the unwind, or the unwind will be bogus. It is never valid to
+ * call this for the current task.
+ */
+static __always_inline void
+kunwind_init_from_task(struct kunwind_state *state,
+ struct task_struct *task)
+{
+ kunwind_init(state, task);
+
+ state->common.fp = task->thread.s[0];
+ state->common.pc = task->thread.ra;
+ state->source = KUNWIND_SOURCE_TASK;
+}
+
+static __always_inline int
+kunwind_recover_return_address(struct kunwind_state *state)
+{
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+ if (state->task->ret_stack &&
+ state->common.pc == (unsigned long)return_to_handler) {
+ unsigned long orig_pc;
+
+ orig_pc = ftrace_graph_ret_addr(state->task, &state->graph_idx,
+ state->common.pc,
+ (void *)state->common.fp);
+ if (state->common.pc == orig_pc) {
+ WARN_ON_ONCE(state->task == current);
+ return -EINVAL;
+ }
+ state->common.pc = orig_pc;
+ state->flags.fgraph = 1;
+ }
+#endif /* CONFIG_FUNCTION_GRAPH_TRACER */
+
+#ifdef CONFIG_KRETPROBES
+ if (is_kretprobe_trampoline(state->common.pc)) {
+ unsigned long orig_pc;
+
+ orig_pc = kretprobe_find_ret_addr(state->task,
+ (void *)state->common.fp,
+ &state->kr_cur);
+ if (!orig_pc)
+ return -EINVAL;
+ state->common.pc = orig_pc;
+ state->flags.kretprobe = 1;
+ }
+#endif /* CONFIG_KRETPROBES */
+
+ return 0;
+}
+
+/*
+ * When we reach an exception boundary marked by a metadata frame record,
+ * extract pt_regs from the stack and continue unwinding from the saved
+ * context (epc and s0/fp).
+ *
+ * On RISC-V, fp points above the metadata record, so the record's
+ * frame_record portion is at fp - sizeof(struct frame_record).
+ */
+static __always_inline int
+kunwind_next_regs_pc(struct kunwind_state *state)
+{
+ struct stack_info *info;
+ unsigned long fp = state->common.fp;
+ struct pt_regs *regs;
+
+ regs = container_of((unsigned long *)(fp - sizeof(struct frame_record)),
+ struct pt_regs, stackframe.record.fp);
+
+ info = unwind_find_stack(&state->common, (unsigned long)regs,
+ sizeof(*regs));
+ if (!info)
+ return -EINVAL;
+
+ unwind_consume_stack(&state->common, info, (unsigned long)regs,
+ sizeof(*regs));
+
+ state->regs = regs;
+ state->common.pc = regs->epc;
+ state->common.fp = frame_pointer(regs);
+ state->source = KUNWIND_SOURCE_REGS_PC;
+ return 0;
+}
+
+/*
+ * Handle a metadata frame record embedded in pt_regs.
+ *
+ * On RISC-V, fp points above the record (fp = metadata + 16), so the
+ * frame_record_meta starts at fp - sizeof(struct frame_record).
+ *
+ * FRAME_META_TYPE_FINAL: This is the outermost exception entry
+ * (user -> kernel). Unwinding terminates successfully.
+ * FRAME_META_TYPE_PT_REGS: This is a nested exception entry
+ * (kernel -> kernel). Continue unwinding from the saved context.
+ */
+static __always_inline int
+kunwind_next_frame_record_meta(struct kunwind_state *state)
+{
+ struct task_struct *tsk = state->task;
+ unsigned long fp = state->common.fp;
+ unsigned long meta_base = fp - sizeof(struct frame_record);
+ struct frame_record_meta *meta;
+ struct stack_info *info;
+
+ info = unwind_find_stack(&state->common, meta_base, sizeof(*meta));
+ if (!info)
+ return -EINVAL;
+
+ meta = (struct frame_record_meta *)meta_base;
+ switch (READ_ONCE(meta->type)) {
+ case FRAME_META_TYPE_FINAL:
+ if (meta == &task_pt_regs(tsk)->stackframe)
+ return -ENOENT;
+ WARN_ON_ONCE(tsk == current);
+ return -EINVAL;
+ case FRAME_META_TYPE_PT_REGS:
+ return kunwind_next_regs_pc(state);
+ default:
+ WARN_ON_ONCE(tsk == current);
+ return -EINVAL;
+ }
+}
+
+/*
+ * Unwind from one frame record to the next.
+ *
+ * On RISC-V, the frame record sits at fp - sizeof(struct frame_record),
+ * immediately below the address pointed to by fp/s0. This applies to both
+ * normal frame records and metadata frame records (embedded in pt_regs).
+ *
+ * A metadata record is identified by both fp and ra being zero in the
+ * frame_record portion, with a type value following at fp + 16.
+ */
+static __always_inline int
+kunwind_next_frame_record(struct kunwind_state *state)
+{
+ unsigned long fp = state->common.fp;
+ struct frame_record *record;
+ struct stack_info *info;
+ unsigned long new_fp, new_pc;
+ unsigned long record_base;
+
+ if (fp & 0x7)
+ return -EINVAL;
+
+ record_base = fp - sizeof(*record);
+
+ info = unwind_find_stack(&state->common, record_base, sizeof(*record));
+ if (!info)
+ return -EINVAL;
+
+ record = (struct frame_record *)record_base;
+ new_fp = READ_ONCE(record->fp);
+ new_pc = READ_ONCE(record->ra);
+
+ if (!new_fp && !new_pc)
+ return kunwind_next_frame_record_meta(state);
+
+ unwind_consume_stack(&state->common, info, record_base,
+ sizeof(*record));
+
+ state->common.fp = new_fp;
+ state->common.pc = new_pc;
+ state->source = KUNWIND_SOURCE_FRAME;
+
+ return 0;
+}
+
+/*
+ * Unwind from one frame record (A) to the next frame record (B).
+ *
+ * We terminate early if the location of B indicates a malformed chain of frame
+ * records (e.g. a cycle), determined based on the location and fp value of A
+ * and the location (but not the fp value) of B.
+ */
+static __always_inline int
+kunwind_next(struct kunwind_state *state)
+{
+ int err;
+
+ state->flags.all = 0;
+
+ switch (state->source) {
+ case KUNWIND_SOURCE_FRAME:
+ case KUNWIND_SOURCE_CALLER:
+ case KUNWIND_SOURCE_TASK:
+ case KUNWIND_SOURCE_REGS_PC:
+ err = kunwind_next_frame_record(state);
+ break;
+ default:
+ err = -EINVAL;
+ }
+
+ if (err)
+ return err;
+
+ return kunwind_recover_return_address(state);
+}
+
+typedef bool (*kunwind_consume_fn)(const struct kunwind_state *state, void *cookie);
+
+static __always_inline int
+do_kunwind(struct kunwind_state *state, kunwind_consume_fn consume_state,
+ void *cookie)
+{
+ int ret;
+
+ ret = kunwind_recover_return_address(state);
+ if (ret)
+ return ret;
+
+ while (1) {
+ if (!consume_state(state, cookie))
+ return -EINVAL;
+ ret = kunwind_next(state);
+ if (ret == -ENOENT)
+ return 0;
+ if (ret < 0)
+ return ret;
+ }
+}
+
+static __always_inline int
+kunwind_stack_walk(kunwind_consume_fn consume_state,
+ void *cookie, struct task_struct *task,
+ struct pt_regs *regs)
+{
+ struct task_struct *tsk = task ?: current;
+ struct stack_info stacks[] = {
+ stackinfo_get_task(tsk),
+ STACKINFO_CPU(tsk, irq),
+#ifdef CONFIG_VMAP_STACK
+ STACKINFO_CPU(tsk, overflow),
+#endif
+ };
+ struct kunwind_state state = {
+ .common = {
+ .stacks = stacks,
+ .nr_stacks = ARRAY_SIZE(stacks),
+ },
+ };
+
+ if (regs) {
+ if (tsk != current)
+ return -EINVAL;
+ kunwind_init_from_regs(&state, regs);
+ } else if (tsk == current) {
+ kunwind_init_from_caller(&state);
+ } else {
+ kunwind_init_from_task(&state, tsk);
+ }
+
+ return do_kunwind(&state, consume_state, cookie);
+}
+
+struct kunwind_consume_entry_data {
+ stack_trace_consume_fn consume_entry;
+ void *cookie;
+};
+
+static __always_inline bool
+arch_kunwind_consume_entry(const struct kunwind_state *state, void *cookie)
+{
+ struct kunwind_consume_entry_data *data = cookie;
+
+ return data->consume_entry(data->cookie, state->common.pc);
+}
+
+static __always_inline bool
+arch_reliable_kunwind_consume_entry(const struct kunwind_state *state, void *cookie)
+{
+ /*
+ * At an exception boundary we can reliably consume the saved PC. We do
+ * not know whether ra was live when the exception was taken, and
+ * so we cannot perform the next unwind step reliably.
+ *
+ * All that matters is whether the *entire* unwind is reliable, so give
+ * up as soon as we hit an exception boundary.
+ */
+ if (state->source == KUNWIND_SOURCE_REGS_PC)
+ return false;
+
+ return arch_kunwind_consume_entry(state, cookie);
+}
+
+#endif /* CONFIG_FRAME_POINTER */
+
+/*
+ * arch_stack_walk - dual implementation.
+ *
+ * When CONFIG_FRAME_POINTER is enabled, uses the kunwind infrastructure for
+ * robust frame-pointer-based unwinding, consistent with arch_stack_walk_reliable.
+ *
+ * When CONFIG_FRAME_POINTER is disabled, falls back to the simple stack scan
+ * in walk_stackframe().
+ */
+#ifdef CONFIG_FRAME_POINTER
+
+noinline noinstr void arch_stack_walk(stack_trace_consume_fn consume_entry,
+ void *cookie, struct task_struct *task,
+ struct pt_regs *regs)
+{
+ struct kunwind_consume_entry_data data = {
+ .consume_entry = consume_entry,
+ .cookie = cookie,
+ };
+
+ kunwind_stack_walk(arch_kunwind_consume_entry, &data, task, regs);
+}
+
+#else
+
+noinline noinstr void arch_stack_walk(stack_trace_consume_fn consume_entry,
+ void *cookie, struct task_struct *task,
+ struct pt_regs *regs)
{
walk_stackframe(task, regs, consume_entry, cookie);
}
+#endif /* CONFIG_FRAME_POINTER */
+
+/*
+ * Reliable stack walk for livepatch (CONFIG_FRAME_POINTER only).
+ */
+#ifdef CONFIG_FRAME_POINTER
+
+noinline noinstr int arch_stack_walk_reliable(stack_trace_consume_fn consume_entry,
+ void *cookie,
+ struct task_struct *task)
+{
+ struct kunwind_consume_entry_data data = {
+ .consume_entry = consume_entry,
+ .cookie = cookie,
+ };
+
+ return kunwind_stack_walk(arch_reliable_kunwind_consume_entry, &data,
+ task, NULL);
+}
+
+#endif /* CONFIG_FRAME_POINTER */
+
/*
* Get the return address for a single stackframe and return a pointer to the
* next frame tail.
--
2.43.0
^ permalink raw reply related
* [PATCH v4 1/7] riscv: stacktrace: Add frame record metadata
From: Wang Han @ 2026-06-29 6:42 UTC (permalink / raw)
To: Paul Walmsley, Palmer Dabbelt, Albert Ou
Cc: Alexandre Ghiti, linux-riscv, Oleg Nesterov, Steven Rostedt,
Masami Hiramatsu, Mark Rutland, Peter Zijlstra, Ingo Molnar,
Arnaldo Carvalho de Melo, Namhyung Kim, Alexander Shishkin,
Jiri Olsa, Ian Rogers, Adrian Hunter, James Clark, Josh Poimboeuf,
Jiri Kosina, Miroslav Benes, Petr Mladek, Joe Lawrence,
Shuah Khan, oliver.yang, xueshuai, zhuo.song, jkchen,
Marcos Paulo de Souza, linux-kernel, linux-trace-kernel,
linux-perf-users, live-patching, linux-kselftest
Reliable frame-pointer unwinding needs an explicit way to identify
exception boundaries and the final entry frame. The existing unwinder
infers those boundaries from return addresses, which is too loose for a
future reliable unwinder.
Add a small metadata frame record to pt_regs and initialize it on
exception entry, kernel stack overflow, kernel thread fork, user fork,
and early idle task setup. The record uses a zero {fp, ra} sentinel plus
a type field so a later unwinder can distinguish a final user-to-kernel
boundary from a nested kernel pt_regs boundary.
This follows the arm64 metadata frame-record model, adapted to the
RISC-V {fp, ra} frame record convention.
The metadata is established at the RISC-V entry boundaries that need an
explicit unwind marker:
* exception entry clears the metadata {fp, ra} pair and uses SPP
(or MPP in M-mode) to record whether the pt_regs frame is the final
user-to-kernel boundary or a nested kernel boundary;
* the kernel stack overflow path builds a nested pt_regs metadata
record on the overflow stack so an unwinder can resume from the
pre-overflow s0 saved in PT_S0;
* _start_kernel builds the init task's final metadata record, while
the secondary CPU path sets up s0 before smp_callin() so idle-task
unwinding does not inherit an undefined caller frame;
* copy_thread creates matching final metadata records for new kernel
and user tasks, and keeps s0 available for the frame-pointer chain.
Keep the embedded metadata-record field offsets distinct from the
s0-relative STACKFRAME_* offsets used by call_on_irq_stack(), because
the latter describe a frame record relative to s0 rather than to the
record base.
These changes keep s0 reserved for the frame-pointer chain at task and
exception boundaries.
Signed-off-by: Wang Han <wanghan@linux.alibaba.com>
---
arch/riscv/include/asm/ptrace.h | 9 ++++
arch/riscv/include/asm/stacktrace/frame.h | 53 +++++++++++++++++++++++
arch/riscv/kernel/asm-offsets.c | 6 +++
arch/riscv/kernel/entry.S | 39 ++++++++++++++++-
arch/riscv/kernel/head.S | 23 ++++++++++
arch/riscv/kernel/process.c | 33 +++++++++++++-
6 files changed, 159 insertions(+), 4 deletions(-)
create mode 100644 arch/riscv/include/asm/stacktrace/frame.h
diff --git a/arch/riscv/include/asm/ptrace.h b/arch/riscv/include/asm/ptrace.h
index addc8188152f..4b9b0f279214 100644
--- a/arch/riscv/include/asm/ptrace.h
+++ b/arch/riscv/include/asm/ptrace.h
@@ -8,6 +8,7 @@
#include <uapi/asm/ptrace.h>
#include <asm/csr.h>
+#include <asm/stacktrace/frame.h>
#include <linux/compiler.h>
#ifndef __ASSEMBLER__
@@ -53,6 +54,14 @@ struct pt_regs {
unsigned long cause;
/* a0 value before the syscall */
unsigned long orig_a0;
+
+ /*
+ * This frame record is entirely zeroed on exception entry, allowing the
+ * unwinder to identify exception boundaries. The type field encodes
+ * whether the exception was taken from user (FINAL) or kernel (PT_REGS)
+ * mode.
+ */
+ struct frame_record_meta stackframe;
};
#define PTRACE_SYSEMU 0x1f
diff --git a/arch/riscv/include/asm/stacktrace/frame.h b/arch/riscv/include/asm/stacktrace/frame.h
new file mode 100644
index 000000000000..5720a6c65fe8
--- /dev/null
+++ b/arch/riscv/include/asm/stacktrace/frame.h
@@ -0,0 +1,53 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+#ifndef __ASM_RISCV_STACKTRACE_FRAME_H
+#define __ASM_RISCV_STACKTRACE_FRAME_H
+
+/*
+ * See: arch/arm64/include/asm/stacktrace/frame.h for the reference
+ * implementation.
+ */
+
+/*
+ * - FRAME_META_TYPE_NONE
+ *
+ * This value is reserved.
+ *
+ * - FRAME_META_TYPE_FINAL
+ *
+ * The record is the last entry on the stack.
+ * Unwinding should terminate successfully.
+ *
+ * - FRAME_META_TYPE_PT_REGS
+ *
+ * The record is embedded within a struct pt_regs, recording the registers at
+ * an arbitrary point in time.
+ * Unwinding should consume pt_regs::epc, followed by pt_regs::ra.
+ *
+ * Note: all other values are reserved and should result in unwinding
+ * terminating with an error.
+ */
+#define FRAME_META_TYPE_NONE 0
+#define FRAME_META_TYPE_FINAL 1
+#define FRAME_META_TYPE_PT_REGS 2
+
+#ifndef __ASSEMBLER__
+/*
+ * A standard RISC-V frame record.
+ */
+struct frame_record {
+ unsigned long fp;
+ unsigned long ra;
+};
+
+/*
+ * A metadata frame record indicating a special unwind.
+ * The record::{fp,ra} fields must be zero to indicate the presence of
+ * metadata.
+ */
+struct frame_record_meta {
+ struct frame_record record;
+ unsigned long type;
+};
+#endif /* __ASSEMBLER__ */
+
+#endif /* __ASM_RISCV_STACKTRACE_FRAME_H */
diff --git a/arch/riscv/kernel/asm-offsets.c b/arch/riscv/kernel/asm-offsets.c
index a75f0cfea1e9..bc8e8cd7130a 100644
--- a/arch/riscv/kernel/asm-offsets.c
+++ b/arch/riscv/kernel/asm-offsets.c
@@ -131,6 +131,9 @@ void asm_offsets(void)
OFFSET(PT_BADADDR, pt_regs, badaddr);
OFFSET(PT_CAUSE, pt_regs, cause);
+ DEFINE(S_STACKFRAME, offsetof(struct pt_regs, stackframe));
+ DEFINE(S_STACKFRAME_TYPE, offsetof(struct pt_regs, stackframe.type));
+
OFFSET(SUSPEND_CONTEXT_REGS, suspend_context, regs);
OFFSET(HIBERN_PBE_ADDR, pbe, address);
@@ -503,6 +506,9 @@ void asm_offsets(void)
DEFINE(STACKFRAME_SIZE_ON_STACK, ALIGN(sizeof(struct stackframe), STACK_ALIGN));
DEFINE(STACKFRAME_FP, offsetof(struct stackframe, fp) - sizeof(struct stackframe));
DEFINE(STACKFRAME_RA, offsetof(struct stackframe, ra) - sizeof(struct stackframe));
+ DEFINE(STACKFRAME_RECORD_SIZE, sizeof(struct stackframe));
+ OFFSET(FRAME_RECORD_FP, frame_record, fp);
+ OFFSET(FRAME_RECORD_RA, frame_record, ra);
#ifdef CONFIG_FUNCTION_TRACER
DEFINE(FTRACE_OPS_FUNC, offsetof(struct ftrace_ops, func));
#ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS
diff --git a/arch/riscv/kernel/entry.S b/arch/riscv/kernel/entry.S
index 08df724e13b9..d1cfb28f9180 100644
--- a/arch/riscv/kernel/entry.S
+++ b/arch/riscv/kernel/entry.S
@@ -11,6 +11,7 @@
#include <asm/asm.h>
#include <asm/csr.h>
#include <asm/scs.h>
+#include <asm/stacktrace/frame.h>
#include <asm/unistd.h>
#include <asm/page.h>
#include <asm/thread_info.h>
@@ -198,6 +199,27 @@ SYM_CODE_START(handle_exception)
REG_S s4, PT_CAUSE(sp)
REG_S s5, PT_TP(sp)
+ /*
+ * Create a metadata frame record. The unwinder will use this to
+ * identify and unwind exception boundaries.
+ */
+ REG_S zero, (S_STACKFRAME + FRAME_RECORD_FP)(sp) /* stackframe.record.fp = 0 */
+ REG_S zero, (S_STACKFRAME + FRAME_RECORD_RA)(sp) /* stackframe.record.ra = 0 */
+#ifdef CONFIG_RISCV_M_MODE
+ li t0, SR_MPP
+ and t0, s1, t0
+#else
+ andi t0, s1, SR_SPP
+#endif
+ bnez t0, 1f
+ li t0, FRAME_META_TYPE_FINAL
+ j 2f
+1:
+ li t0, FRAME_META_TYPE_PT_REGS
+2:
+ REG_S t0, S_STACKFRAME_TYPE(sp)
+ addi s0, sp, S_STACKFRAME + STACKFRAME_RECORD_SIZE
+
/*
* Set the scratch register to 0, so that if a recursive exception
* occurs, the exception vector knows it came from the kernel
@@ -354,6 +376,19 @@ SYM_CODE_START_LOCAL(handle_kernel_stack_overflow)
REG_S s3, PT_BADADDR(sp)
REG_S s4, PT_CAUSE(sp)
REG_S s5, PT_TP(sp)
+
+ /*
+ * Create a metadata frame record for the overflow pt_regs. The
+ * overflow path is entered from kernel context, so this is a nested
+ * pt_regs boundary and the unwinder can resume from the pre-overflow
+ * frame pointer saved in PT_S0.
+ */
+ REG_S zero, (S_STACKFRAME + FRAME_RECORD_FP)(sp)
+ REG_S zero, (S_STACKFRAME + FRAME_RECORD_RA)(sp)
+ li t0, FRAME_META_TYPE_PT_REGS
+ REG_S t0, S_STACKFRAME_TYPE(sp)
+ addi s0, sp, S_STACKFRAME + STACKFRAME_RECORD_SIZE
+
move a0, sp
tail handle_bad_stack
SYM_CODE_END(handle_kernel_stack_overflow)
@@ -362,8 +397,8 @@ ASM_NOKPROBE(handle_kernel_stack_overflow)
SYM_CODE_START(ret_from_fork_kernel_asm)
call schedule_tail
- move a0, s1 /* fn_arg */
- move a1, s0 /* fn */
+ move a0, s3 /* fn_arg */
+ move a1, s2 /* fn */
move a2, sp /* pt_regs */
call ret_from_fork_kernel
j ret_from_exception
diff --git a/arch/riscv/kernel/head.S b/arch/riscv/kernel/head.S
index f6a8ca49e627..341b2d3facbc 100644
--- a/arch/riscv/kernel/head.S
+++ b/arch/riscv/kernel/head.S
@@ -14,6 +14,7 @@
#include <asm/hwcap.h>
#include <asm/image.h>
#include <asm/scs.h>
+#include <asm/stacktrace/frame.h>
#include <asm/usercfi.h>
#include "efi-header.S"
@@ -177,6 +178,14 @@ secondary_start_sbi:
REG_S a0, (a1)
1:
#endif
+
+ /*
+ * Set up the frame pointer for the secondary idle task so reliable
+ * stack unwinding terminates at the metadata frame in task_pt_regs().
+ * Without this, the first frame records can inherit an undefined caller
+ * fp and unwind past smp_callin() into .Lsecondary_park.
+ */
+ addi s0, sp, S_STACKFRAME + STACKFRAME_RECORD_SIZE
scs_load_current
call smp_callin
#endif /* CONFIG_SMP */
@@ -305,6 +314,20 @@ SYM_CODE_START(_start_kernel)
la tp, init_task
la sp, init_thread_union + THREAD_SIZE
addi sp, sp, -PT_SIZE_ON_STACK
+
+ /*
+ * Set up a metadata frame record for the init task so that
+ * the unwinder can identify the outermost frame by its
+ * {fp, ra} = {0, 0} sentinel at the bottom of pt_regs.
+ * fp/s0 points above the metadata record (RISC-V
+ * convention).
+ */
+ REG_S zero, (S_STACKFRAME + FRAME_RECORD_FP)(sp)
+ REG_S zero, (S_STACKFRAME + FRAME_RECORD_RA)(sp)
+ li t0, FRAME_META_TYPE_FINAL
+ REG_S t0, S_STACKFRAME_TYPE(sp)
+ addi s0, sp, S_STACKFRAME + STACKFRAME_RECORD_SIZE
+
#if defined(CONFIG_RISCV_SBI) && defined(CONFIG_RISCV_USER_CFI)
li a7, SBI_EXT_FWFT
li a6, SBI_EXT_FWFT_SET
diff --git a/arch/riscv/kernel/process.c b/arch/riscv/kernel/process.c
index b2df7f72241a..0dc90bf7a652 100644
--- a/arch/riscv/kernel/process.c
+++ b/arch/riscv/kernel/process.c
@@ -258,8 +258,23 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args)
/* Supervisor/Machine, irqs on: */
childregs->status = SR_PP | SR_PIE;
- p->thread.s[0] = (unsigned long)args->fn;
- p->thread.s[1] = (unsigned long)args->fn_arg;
+ /*
+ * Set up a metadata frame record at the bottom of the
+ * stack for the unwinder. Use FRAME_META_TYPE_FINAL
+ * since this is the outermost kernel entry for the new
+ * task. The frame_record::{fp,ra} are already zero from
+ * memset().
+ *
+ * fp/s0 points above the metadata record (RISC-V
+ * convention). fn and fn_arg are passed via s2/s3,
+ * keeping s0 available for the frame pointer chain.
+ */
+ childregs->stackframe.type = FRAME_META_TYPE_FINAL;
+
+ p->thread.s[0] = (unsigned long)(&childregs->stackframe)
+ + sizeof(struct frame_record);
+ p->thread.s[2] = (unsigned long)args->fn;
+ p->thread.s[3] = (unsigned long)args->fn_arg;
p->thread.ra = (unsigned long)ret_from_fork_kernel_asm;
} else {
/* allocate new shadow stack if needed. In case of CLONE_VM we have to */
@@ -278,6 +293,20 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args)
if (clone_flags & CLONE_SETTLS)
childregs->tp = tls;
childregs->a0 = 0; /* Return value of fork() */
+
+ /*
+ * Set up the unwind boundary: ensure the metadata
+ * frame record has its {fp,ra} sentinel zeroed and
+ * point fp/s0 above the metadata record. Mark it as
+ * FINAL since this is the outermost kernel entry for
+ * the new task.
+ */
+ childregs->stackframe.record.fp = 0;
+ childregs->stackframe.record.ra = 0;
+ childregs->stackframe.type = FRAME_META_TYPE_FINAL;
+ p->thread.s[0] = (unsigned long)(&childregs->stackframe)
+ + sizeof(struct frame_record);
+
p->thread.ra = (unsigned long)ret_from_fork_user_asm;
}
p->thread.riscv_v_flags = 0;
--
2.43.0
^ permalink raw reply related
* [PATCH v4 0/7] riscv: Add reliable stack unwinding for livepatch
From: Wang Han @ 2026-06-29 6:42 UTC (permalink / raw)
To: Paul Walmsley, Palmer Dabbelt, Albert Ou
Cc: Alexandre Ghiti, linux-riscv, Oleg Nesterov, Steven Rostedt,
Masami Hiramatsu, Mark Rutland, Peter Zijlstra, Ingo Molnar,
Arnaldo Carvalho de Melo, Namhyung Kim, Alexander Shishkin,
Jiri Olsa, Ian Rogers, Adrian Hunter, James Clark, Josh Poimboeuf,
Jiri Kosina, Miroslav Benes, Petr Mladek, Joe Lawrence,
Shuah Khan, oliver.yang, xueshuai, zhuo.song, jkchen,
Marcos Paulo de Souza, linux-kernel, linux-trace-kernel,
linux-perf-users, live-patching, linux-kselftest
Hi,
This series adds the RISC-V architecture pieces needed by livepatch:
dynamic ftrace must preserve the frame pointer context that livepatch
uses for redirection, and the stack unwinder must be reliable enough for
the livepatch consistency model.
The reliable unwinder is based on frame records and explicit metadata at
task and exception boundaries. It is intentionally conservative: it
rejects ambiguous states instead of trying to unwind through them. The
series then enables HAVE_RELIABLE_STACKTRACE and HAVE_LIVEPATCH for
64-bit RISC-V with dynamic ftrace.
The first patch from v3, "scripts/sorttable: Handle RISC-V patchable
ftrace entries", has been picked up by Paul and is already present in
riscv/for-next as commit 57ad674d032b. It is therefore dropped from this
v4. The remaining patches are rebased on the latest riscv/for-next.
Base:
riscv/for-next 798246e5edfb ("riscv: acpi: Enable ARCH_HAS_ACPI_TABLE_UPGRADE")
Previous versions:
v3: https://lore.kernel.org/r/cover.194d76e3a15b.v3.riscv-livepatch.wanghan@linux.alibaba.com
v2: https://lore.kernel.org/r/20260528082310.1994388-1-wanghan@linux.alibaba.com
v1: https://lore.kernel.org/r/20260527123530.2593918-1-wanghan@linux.alibaba.com
Changes since v3:
* Drop the accepted sorttable fix, now commit 57ad674d032b in
riscv/for-next.
* Rebase the remaining 7 patches on the latest riscv/for-next.
* Adapt the frame metadata patch to the existing call_on_irq_stack()
RV32 frame-pointer ABI fix by keeping metadata frame-record offsets
distinct from the s0-relative STACKFRAME_* offsets.
* Adapt the livepatch syscall selftest prefix change to the current
CONFIG_ARCH_HAS_SYSCALL_WRAPPER wrapper logic.
Validation:
* Built with riscv64-unknown-linux-gnu-gcc 15.2.0 and the existing
configs/riscv_livepatch_config, including RISCV_ISA_C=y, EFI=y and
ACPI=y.
* make -C linux O=$PWD/build/linux/riscv ARCH=riscv \
CROSS_COMPILE=riscv64-unknown-linux-gnu- -j$(nproc) Image modules
passed.
* make kernel-debug ARCH=riscv GDB=riscv64-unknown-linux-gnu-gdb
passed.
* livepatch selftest modules built successfully via ./test-livepatch.sh
riscv.
* QEMU RISC-V livepatch selftests passed with PASS: 7, SKIP: 1,
FAIL: 0. The only skip is test-kprobe.sh because this config does
not enable CONFIG_KPROBES_ON_FTRACE.
* The ftrace function graph subset passed with 3 passed, 0 failed and
3 unsupported tests.
Wang Han (7):
riscv: stacktrace: Add frame record metadata
riscv: stacktrace: disable KASAN and KCOV instrumentation for
stacktrace.o
riscv: ftrace: always preserve s0 in dynamic ftrace register frame
riscv: stacktrace: introduce stack-bound tracking helpers
riscv: stacktrace: switch to frame-pointer based unwinder
riscv: Kconfig: enable HAVE_RELIABLE_STACKTRACE and HAVE_LIVEPATCH
selftests/livepatch: Add RISC-V syscall wrapper prefix
arch/riscv/Kconfig | 4 +
arch/riscv/include/asm/ptrace.h | 9 +
arch/riscv/include/asm/stacktrace.h | 65 +-
arch/riscv/include/asm/stacktrace/common.h | 159 +++++
arch/riscv/include/asm/stacktrace/frame.h | 53 ++
arch/riscv/kernel/Makefile | 6 +
arch/riscv/kernel/asm-offsets.c | 6 +
arch/riscv/kernel/entry.S | 39 +-
arch/riscv/kernel/ftrace.c | 6 +-
arch/riscv/kernel/head.S | 23 +
arch/riscv/kernel/mcount-dyn.S | 4 -
arch/riscv/kernel/perf_callchain.c | 2 +-
arch/riscv/kernel/process.c | 33 +-
arch/riscv/kernel/stacktrace.c | 559 +++++++++++++++---
.../livepatch/test_modules/test_klp_syscall.c | 2 +
15 files changed, 864 insertions(+), 106 deletions(-)
create mode 100644 arch/riscv/include/asm/stacktrace/common.h
create mode 100644 arch/riscv/include/asm/stacktrace/frame.h
Range-diff against v3:
1: 8cef363cfed7 ! 1: efd99ce56c1e riscv: stacktrace: Add frame record metadata
@@ Commit message
the secondary CPU path sets up s0 before smp_callin() so idle-task
unwinding does not inherit an undefined caller frame;
* copy_thread creates matching final metadata records for new kernel
- and user tasks, and keeps s0 available for the frame-pointer chain;
- * call_on_irq_stack still reserves an aligned stack slot, but links the
- saved {fp, ra} with the raw frame-record size so s0 points at the
- RISC-V frame record rather than past the alignment padding.
+ and user tasks, and keeps s0 available for the frame-pointer chain.
- The call_on_irq_stack adjustment fixes a latent RV32 issue. On RV64,
- sizeof(struct stackframe) is equal to the stack alignment, so the old
- s0 value happened to point just above the saved {fp, ra}. On RV32, the
- raw frame record is 8 bytes while the reserved stack slot is 16-byte
- aligned, so the old s0 value pointed into the padding. Using the raw
- record size makes s0 point above the saved frame record on both RV32
- and RV64 while still reserving the aligned slot.
+ Keep the embedded metadata-record field offsets distinct from the
+ s0-relative STACKFRAME_* offsets used by call_on_irq_stack(), because
+ the latter describe a frame record relative to s0 rather than to the
+ record base.
These changes keep s0 reserved for the frame-pointer chain at task and
- stack-switch boundaries.
+ exception boundaries.
Signed-off-by: Wang Han <wanghan@linux.alibaba.com>
@@ arch/riscv/kernel/asm-offsets.c: void asm_offsets(void)
OFFSET(HIBERN_PBE_ADDR, pbe, address);
@@ arch/riscv/kernel/asm-offsets.c: void asm_offsets(void)
- OFFSET(SBI_HART_BOOT_STACK_PTR_OFFSET, sbi_hart_boot_data, stack_ptr);
-
DEFINE(STACKFRAME_SIZE_ON_STACK, ALIGN(sizeof(struct stackframe), STACK_ALIGN));
+ DEFINE(STACKFRAME_FP, offsetof(struct stackframe, fp) - sizeof(struct stackframe));
+ DEFINE(STACKFRAME_RA, offsetof(struct stackframe, ra) - sizeof(struct stackframe));
+ DEFINE(STACKFRAME_RECORD_SIZE, sizeof(struct stackframe));
- OFFSET(STACKFRAME_FP, stackframe, fp);
- OFFSET(STACKFRAME_RA, stackframe, ra);
++ OFFSET(FRAME_RECORD_FP, frame_record, fp);
++ OFFSET(FRAME_RECORD_RA, frame_record, ra);
#ifdef CONFIG_FUNCTION_TRACER
+ DEFINE(FTRACE_OPS_FUNC, offsetof(struct ftrace_ops, func));
+ #ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS
## arch/riscv/kernel/entry.S ##
@@
@@ arch/riscv/kernel/entry.S: SYM_CODE_START(handle_exception)
+ * Create a metadata frame record. The unwinder will use this to
+ * identify and unwind exception boundaries.
+ */
-+ REG_S zero, (S_STACKFRAME + STACKFRAME_FP)(sp) /* stackframe.record.fp = 0 */
-+ REG_S zero, (S_STACKFRAME + STACKFRAME_RA)(sp) /* stackframe.record.ra = 0 */
++ REG_S zero, (S_STACKFRAME + FRAME_RECORD_FP)(sp) /* stackframe.record.fp = 0 */
++ REG_S zero, (S_STACKFRAME + FRAME_RECORD_RA)(sp) /* stackframe.record.ra = 0 */
+#ifdef CONFIG_RISCV_M_MODE
+ li t0, SR_MPP
+ and t0, s1, t0
@@ arch/riscv/kernel/entry.S: SYM_CODE_START_LOCAL(handle_kernel_stack_overflow)
+ * pt_regs boundary and the unwinder can resume from the pre-overflow
+ * frame pointer saved in PT_S0.
+ */
-+ REG_S zero, (S_STACKFRAME + STACKFRAME_FP)(sp)
-+ REG_S zero, (S_STACKFRAME + STACKFRAME_RA)(sp)
++ REG_S zero, (S_STACKFRAME + FRAME_RECORD_FP)(sp)
++ REG_S zero, (S_STACKFRAME + FRAME_RECORD_RA)(sp)
+ li t0, FRAME_META_TYPE_PT_REGS
+ REG_S t0, S_STACKFRAME_TYPE(sp)
+ addi s0, sp, S_STACKFRAME + STACKFRAME_RECORD_SIZE
@@ arch/riscv/kernel/entry.S: ASM_NOKPROBE(handle_kernel_stack_overflow)
move a2, sp /* pt_regs */
call ret_from_fork_kernel
j ret_from_exception
-@@ arch/riscv/kernel/entry.S: SYM_FUNC_START(call_on_irq_stack)
- addi sp, sp, -STACKFRAME_SIZE_ON_STACK
- REG_S ra, STACKFRAME_RA(sp)
- REG_S s0, STACKFRAME_FP(sp)
-- addi s0, sp, STACKFRAME_SIZE_ON_STACK
-+ addi s0, sp, STACKFRAME_RECORD_SIZE
-
- /* Switch to the per-CPU shadow call stack */
- scs_save_current
-@@ arch/riscv/kernel/entry.S: SYM_FUNC_START(call_on_irq_stack)
- scs_load_current
-
- /* Switch back to the thread stack and restore ra and s0 */
-- addi sp, s0, -STACKFRAME_SIZE_ON_STACK
-+ addi sp, s0, -STACKFRAME_RECORD_SIZE
- REG_L ra, STACKFRAME_RA(sp)
- REG_L s0, STACKFRAME_FP(sp)
- addi sp, sp, STACKFRAME_SIZE_ON_STACK
## arch/riscv/kernel/head.S ##
@@
@@ arch/riscv/kernel/head.S: SYM_CODE_START(_start_kernel)
+ * fp/s0 points above the metadata record (RISC-V
+ * convention).
+ */
-+ REG_S zero, (S_STACKFRAME + STACKFRAME_FP)(sp)
-+ REG_S zero, (S_STACKFRAME + STACKFRAME_RA)(sp)
++ REG_S zero, (S_STACKFRAME + FRAME_RECORD_FP)(sp)
++ REG_S zero, (S_STACKFRAME + FRAME_RECORD_RA)(sp)
+ li t0, FRAME_META_TYPE_FINAL
+ REG_S t0, S_STACKFRAME_TYPE(sp)
+ addi s0, sp, S_STACKFRAME + STACKFRAME_RECORD_SIZE
2: 237864b66d78 = 2: bc0af8ec1976 riscv: stacktrace: disable KASAN and KCOV instrumentation for stacktrace.o
3: e6035966a35a = 3: ab3fbed66fff riscv: ftrace: always preserve s0 in dynamic ftrace register frame
4: d132087ea01e = 4: 856d1e31408a riscv: stacktrace: introduce stack-bound tracking helpers
5: 02adea3ece82 = 5: 58aa4435e2ee riscv: stacktrace: switch to frame-pointer based unwinder
6: c7d7dbe7a8a1 = 6: 500f9d9eeac0 riscv: Kconfig: enable HAVE_RELIABLE_STACKTRACE and HAVE_LIVEPATCH
7: ae94a234b34a < -: ------------ selftests/livepatch: Add RISC-V syscall wrapper prefix
-: ------------ > 7: 3dcfa694c207 selftests/livepatch: Add RISC-V syscall wrapper prefix
base-commit: 798246e5edfb3aa0b2d6dca46f41014d0b99b209
--
2.43.0
^ permalink raw reply
* [PATCH v4 6/7] riscv: Kconfig: enable HAVE_RELIABLE_STACKTRACE and HAVE_LIVEPATCH
From: Wang Han @ 2026-06-29 6:42 UTC (permalink / raw)
To: Paul Walmsley, Palmer Dabbelt, Albert Ou
Cc: Alexandre Ghiti, linux-riscv, Oleg Nesterov, Steven Rostedt,
Masami Hiramatsu, Mark Rutland, Peter Zijlstra, Ingo Molnar,
Arnaldo Carvalho de Melo, Namhyung Kim, Alexander Shishkin,
Jiri Olsa, Ian Rogers, Adrian Hunter, James Clark, Josh Poimboeuf,
Jiri Kosina, Miroslav Benes, Petr Mladek, Joe Lawrence,
Shuah Khan, oliver.yang, xueshuai, zhuo.song, jkchen,
Marcos Paulo de Souza, linux-kernel, linux-trace-kernel,
linux-perf-users, live-patching, linux-kselftest
Now that the metadata frame records, the kunwind state machine and
arch_stack_walk_reliable() are all in place, advertise the capability
to the rest of the kernel:
* select HAVE_RELIABLE_STACKTRACE under FRAME_POINTER && 64BIT, so
only the configurations with the tested metadata records and
FP-based reliable walker enable it.
* select HAVE_LIVEPATCH under the same condition and source
kernel/livepatch/Kconfig so the livepatch menu is reachable from
the RISC-V configuration.
The 64BIT dependency is conservative scoping rather than a hard
technical requirement: the metadata frame record, kunwind state machine
and arch_stack_walk_reliable() also build on RV32, and the IRQ-stack
frame-record adjustment fixes a latent RV32 issue. However, the syscall
livepatch selftest and module relocation path have only been exercised
on RV64 QEMU virt so far. The 64BIT gate can be relaxed in a follow-up
once RV32 has equivalent coverage.
This is split out from the unwinder change so the policy decision and
the implementation can be reviewed and reverted independently.
Reviewed-by: Shuai Xue <xueshuai@linux.alibaba.com>
Signed-off-by: Wang Han <wanghan@linux.alibaba.com>
---
arch/riscv/Kconfig | 4 ++++
1 file changed, 4 insertions(+)
diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig
index cb3d85abf595..4d09fab682ac 100644
--- a/arch/riscv/Kconfig
+++ b/arch/riscv/Kconfig
@@ -186,6 +186,7 @@ config RISCV
select HAVE_KRETPROBES
# https://github.com/ClangBuiltLinux/linux/issues/1881
select HAVE_LD_DEAD_CODE_DATA_ELIMINATION if !LD_IS_LLD
+ select HAVE_LIVEPATCH if FRAME_POINTER && 64BIT
select HAVE_MOVE_PMD
select HAVE_MOVE_PUD
select HAVE_PAGE_SIZE_4KB
@@ -196,6 +197,7 @@ config RISCV
select HAVE_POSIX_CPU_TIMERS_TASK_WORK
select HAVE_PREEMPT_DYNAMIC_KEY
select HAVE_REGS_AND_STACK_ACCESS_API
+ select HAVE_RELIABLE_STACKTRACE if FRAME_POINTER && 64BIT
select HAVE_RETHOOK
select HAVE_RSEQ
select HAVE_RUST if RUSTC_SUPPORTS_RISCV && CC_IS_CLANG
@@ -1392,3 +1394,5 @@ endmenu # "CPU Power Management"
source "arch/riscv/kvm/Kconfig"
source "drivers/acpi/Kconfig"
+
+source "kernel/livepatch/Kconfig"
--
2.43.0
^ permalink raw reply related
* [PATCH v4 7/7] selftests/livepatch: Add RISC-V syscall wrapper prefix
From: Wang Han @ 2026-06-29 6:42 UTC (permalink / raw)
To: Paul Walmsley, Palmer Dabbelt, Albert Ou
Cc: Alexandre Ghiti, linux-riscv, Oleg Nesterov, Steven Rostedt,
Masami Hiramatsu, Mark Rutland, Peter Zijlstra, Ingo Molnar,
Arnaldo Carvalho de Melo, Namhyung Kim, Alexander Shishkin,
Jiri Olsa, Ian Rogers, Adrian Hunter, James Clark, Josh Poimboeuf,
Jiri Kosina, Miroslav Benes, Petr Mladek, Joe Lawrence,
Shuah Khan, oliver.yang, xueshuai, zhuo.song, jkchen,
Marcos Paulo de Souza, linux-kernel, linux-trace-kernel,
linux-perf-users, live-patching, linux-kselftest
The syscall livepatch selftest resolves and patches a syscall wrapper
symbol. To use that test for RISC-V livepatch validation, add the
RISC-V FN_PREFIX definition for ARCH_HAS_SYSCALL_WRAPPER.
Without this macro, the syscall livepatch selftest cannot resolve the
RISC-V target symbol, and the syscall-related livepatch test fails on
RISC-V.
Reviewed-by: Marcos Paulo de Souza <mpdesouza@suse.com>
Reviewed-by: Shuai Xue <xueshuai@linux.alibaba.com>
Signed-off-by: Wang Han <wanghan@linux.alibaba.com>
---
.../testing/selftests/livepatch/test_modules/test_klp_syscall.c | 2 ++
1 file changed, 2 insertions(+)
diff --git a/tools/testing/selftests/livepatch/test_modules/test_klp_syscall.c b/tools/testing/selftests/livepatch/test_modules/test_klp_syscall.c
index 08aacc0e14de..9baa2a5f84c9 100644
--- a/tools/testing/selftests/livepatch/test_modules/test_klp_syscall.c
+++ b/tools/testing/selftests/livepatch/test_modules/test_klp_syscall.c
@@ -24,6 +24,8 @@
#define FN_PREFIX __s390x_
#elif defined(__aarch64__)
#define FN_PREFIX __arm64_
+ #elif defined(__riscv)
+ #define FN_PREFIX __riscv_
#elif defined(__powerpc__)
#define FN_PREFIX
#else
--
2.43.0
^ permalink raw reply related
* [PATCH v4 4/7] riscv: stacktrace: introduce stack-bound tracking helpers
From: Wang Han @ 2026-06-29 6:42 UTC (permalink / raw)
To: Paul Walmsley, Palmer Dabbelt, Albert Ou
Cc: Alexandre Ghiti, linux-riscv, Oleg Nesterov, Steven Rostedt,
Masami Hiramatsu, Mark Rutland, Peter Zijlstra, Ingo Molnar,
Arnaldo Carvalho de Melo, Namhyung Kim, Alexander Shishkin,
Jiri Olsa, Ian Rogers, Adrian Hunter, James Clark, Josh Poimboeuf,
Jiri Kosina, Miroslav Benes, Petr Mladek, Joe Lawrence,
Shuah Khan, oliver.yang, xueshuai, zhuo.song, jkchen,
Marcos Paulo de Souza, linux-kernel, linux-trace-kernel,
linux-perf-users, live-patching, linux-kselftest
A reliable unwinder needs to validate that every frame record it reads
is fully contained in a known kernel stack, and it needs to refuse to
walk back into a stack it has already left. Add the building blocks
for that:
* struct stack_info / struct unwind_state in a new
asm/stacktrace/common.h, modelled on the arm64 reference
implementation.
* stackinfo_get_irq() / stackinfo_get_task() / stackinfo_get_overflow()
plus the corresponding on_*_stack() predicates in asm/stacktrace.h,
so callers can ask "is this object on stack X?" by stack kind
rather than open-coded address arithmetic.
* unwind_init_common(), unwind_find_stack() and
unwind_consume_stack() helpers that enforce the
forward-progress-only invariant required for reliability.
No existing user is wired up to these helpers in this commit; the
unwinder switch comes in a follow-up. The header changes leave
on_thread_stack() with the same semantics as before, just expressed in
terms of the new helpers.
Reviewed-by: Shuai Xue <xueshuai@linux.alibaba.com>
Signed-off-by: Wang Han <wanghan@linux.alibaba.com>
---
arch/riscv/include/asm/stacktrace.h | 65 ++++++++-
arch/riscv/include/asm/stacktrace/common.h | 159 +++++++++++++++++++++
2 files changed, 222 insertions(+), 2 deletions(-)
create mode 100644 arch/riscv/include/asm/stacktrace/common.h
diff --git a/arch/riscv/include/asm/stacktrace.h b/arch/riscv/include/asm/stacktrace.h
index b1495a7e06ce..bc87c4940379 100644
--- a/arch/riscv/include/asm/stacktrace.h
+++ b/arch/riscv/include/asm/stacktrace.h
@@ -3,8 +3,13 @@
#ifndef _ASM_RISCV_STACKTRACE_H
#define _ASM_RISCV_STACKTRACE_H
+#include <linux/percpu.h>
#include <linux/sched.h>
+#include <linux/sched/task_stack.h>
+
+#include <asm/irq_stack.h>
#include <asm/ptrace.h>
+#include <asm/stacktrace/common.h>
struct stackframe {
unsigned long fp;
@@ -16,14 +21,70 @@ extern void notrace walk_stackframe(struct task_struct *task, struct pt_regs *re
extern void dump_backtrace(struct pt_regs *regs, struct task_struct *task,
const char *loglvl);
-static inline bool on_thread_stack(void)
+/*
+ * IRQ stack accessors
+ */
+static inline struct stack_info stackinfo_get_irq(void)
+{
+ unsigned long low = (unsigned long)raw_cpu_read(irq_stack_ptr);
+ unsigned long high = low + IRQ_STACK_SIZE;
+
+ return (struct stack_info) {
+ .low = low,
+ .high = high,
+ };
+}
+
+static inline bool on_irq_stack(unsigned long sp, unsigned long size)
+{
+ struct stack_info info = stackinfo_get_irq();
+
+ return stackinfo_on_stack(&info, sp, size);
+}
+
+/*
+ * Task stack accessors
+ */
+static inline struct stack_info stackinfo_get_task(const struct task_struct *tsk)
{
- return !(((unsigned long)(current->stack) ^ current_stack_pointer) & ~(THREAD_SIZE - 1));
+ unsigned long low = (unsigned long)task_stack_page(tsk);
+ unsigned long high = low + THREAD_SIZE;
+
+ return (struct stack_info) {
+ .low = low,
+ .high = high,
+ };
+}
+
+static inline bool on_task_stack(const struct task_struct *tsk,
+ unsigned long sp, unsigned long size)
+{
+ struct stack_info info = stackinfo_get_task(tsk);
+
+ return stackinfo_on_stack(&info, sp, size);
}
+/*
+ * Cast is necessary since current->stack is an opaque ptr.
+ */
+#define on_thread_stack() (on_task_stack(current, current_stack_pointer, 1))
+/*
+ * Overflow stack accessors
+ */
#ifdef CONFIG_VMAP_STACK
DECLARE_PER_CPU(unsigned long [OVERFLOW_STACK_SIZE/sizeof(long)], overflow_stack);
+
+static inline struct stack_info stackinfo_get_overflow(void)
+{
+ unsigned long low = (unsigned long)raw_cpu_ptr(overflow_stack);
+ unsigned long high = low + OVERFLOW_STACK_SIZE;
+
+ return (struct stack_info) {
+ .low = low,
+ .high = high,
+ };
+}
#endif /* CONFIG_VMAP_STACK */
#endif /* _ASM_RISCV_STACKTRACE_H */
diff --git a/arch/riscv/include/asm/stacktrace/common.h b/arch/riscv/include/asm/stacktrace/common.h
new file mode 100644
index 000000000000..360a26e34349
--- /dev/null
+++ b/arch/riscv/include/asm/stacktrace/common.h
@@ -0,0 +1,159 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * RISC-V common stack unwinder types and helpers.
+ *
+ * See: arch/arm64/include/asm/stacktrace/common.h for the reference
+ * implementation.
+ *
+ * Copyright (C) 2026
+ */
+#ifndef __ASM_RISCV_STACKTRACE_COMMON_H
+#define __ASM_RISCV_STACKTRACE_COMMON_H
+
+#include <linux/compiler.h>
+#include <linux/errno.h>
+#include <linux/types.h>
+
+#include <asm/stacktrace/frame.h>
+
+/**
+ * struct stack_info - describes the bounds of a stack.
+ *
+ * @low: The lowest valid address on the stack.
+ * @high: The highest valid address on the stack.
+ */
+struct stack_info {
+ unsigned long low;
+ unsigned long high;
+};
+
+/**
+ * struct unwind_state - state used for robust unwinding.
+ *
+ * @fp: The fp value in the frame record (or the real fp).
+ * @pc: The ra value in the frame record (or the real ra).
+ *
+ * @stack: The stack currently being unwound.
+ * @stacks: An array of stacks which can be unwound.
+ * @nr_stacks: The number of stacks in @stacks.
+ */
+struct unwind_state {
+ unsigned long fp;
+ unsigned long pc;
+
+ struct stack_info stack;
+ struct stack_info *stacks;
+ int nr_stacks;
+};
+
+/**
+ * stackinfo_get_unknown() - Get an unknown stack_info.
+ *
+ * Return: a stack_info with low and high set to 0.
+ */
+static inline struct stack_info stackinfo_get_unknown(void)
+{
+ return (struct stack_info) {
+ .low = 0,
+ .high = 0,
+ };
+}
+
+/**
+ * stackinfo_on_stack() - Check whether an object is fully within a stack.
+ *
+ * @info: The stack to check against.
+ * @sp: The base address of the object.
+ * @size: The size of the object.
+ *
+ * Return: true if the object is fully contained within the stack.
+ */
+static inline bool stackinfo_on_stack(const struct stack_info *info,
+ unsigned long sp, unsigned long size)
+{
+ if (!info->low)
+ return false;
+
+ if (sp < info->low || sp + size < sp || sp + size > info->high)
+ return false;
+
+ return true;
+}
+
+/**
+ * unwind_init_common() - Initialize the common parts of the unwind state.
+ *
+ * @state: the unwind state to initialize.
+ */
+static inline void unwind_init_common(struct unwind_state *state)
+{
+ state->stack = stackinfo_get_unknown();
+}
+
+/**
+ * unwind_find_stack() - Find the accessible stack which entirely contains an
+ * object.
+ *
+ * @state: the current unwind state.
+ * @sp: the base address of the object.
+ * @size: the size of the object.
+ *
+ * Return: a pointer to the relevant stack_info if found; NULL otherwise.
+ */
+static inline struct stack_info *unwind_find_stack(struct unwind_state *state,
+ unsigned long sp,
+ unsigned long size)
+{
+ struct stack_info *info = &state->stack;
+
+ if (stackinfo_on_stack(info, sp, size))
+ return info;
+
+ for (int i = 0; i < state->nr_stacks; i++) {
+ info = &state->stacks[i];
+ if (stackinfo_on_stack(info, sp, size))
+ return info;
+ }
+
+ return NULL;
+}
+
+/**
+ * unwind_consume_stack() - Update stack boundaries so that future unwind steps
+ * cannot consume this object again.
+ *
+ * @state: the current unwind state.
+ * @info: the stack_info of the stack containing the object.
+ * @sp: the base address of the object.
+ * @size: the size of the object.
+ *
+ * Stack transitions are strictly one-way, and once we've
+ * transitioned from one stack to another, it's never valid to
+ * unwind back to the old stack.
+ *
+ * Note that stacks can nest in several valid orders, e.g.
+ *
+ * TASK -> IRQ -> OVERFLOW
+ *
+ * ... so we do not check the specific order of stack
+ * transitions.
+ */
+static inline void unwind_consume_stack(struct unwind_state *state,
+ struct stack_info *info,
+ unsigned long sp,
+ unsigned long size)
+{
+ struct stack_info tmp;
+
+ tmp = *info;
+ *info = stackinfo_get_unknown();
+ state->stack = tmp;
+
+ /*
+ * Future unwind steps can only consume stack above this frame record.
+ * Update the current stack to start immediately above it.
+ */
+ state->stack.low = sp + size;
+}
+
+#endif /* __ASM_RISCV_STACKTRACE_COMMON_H */
--
2.43.0
^ permalink raw reply related
* [PATCH v4 2/7] riscv: stacktrace: disable KASAN and KCOV instrumentation for stacktrace.o
From: Wang Han @ 2026-06-29 6:42 UTC (permalink / raw)
To: Paul Walmsley, Palmer Dabbelt, Albert Ou
Cc: Alexandre Ghiti, linux-riscv, Oleg Nesterov, Steven Rostedt,
Masami Hiramatsu, Mark Rutland, Peter Zijlstra, Ingo Molnar,
Arnaldo Carvalho de Melo, Namhyung Kim, Alexander Shishkin,
Jiri Olsa, Ian Rogers, Adrian Hunter, James Clark, Josh Poimboeuf,
Jiri Kosina, Miroslav Benes, Petr Mladek, Joe Lawrence,
Shuah Khan, oliver.yang, xueshuai, zhuo.song, jkchen,
Marcos Paulo de Souza, linux-kernel, linux-trace-kernel,
linux-perf-users, live-patching, linux-kselftest
KASAN records stack traces for every alloc/free, which means it walks
the unwinder very frequently. Instrumenting the stack trace collection
code itself adds substantial overhead and makes the traces themselves
noisier.
KCOV instruments every basic-block edge. The unwinder is a hot path,
especially with KASAN enabled, so KCOV instrumentation has the same kind
of cost and noise problem here.
Mark stacktrace.o as not KASAN- or KCOV-instrumented, matching the x86
treatment of its stack unwinding code. RISC-V keeps the relevant unwinder
code in stacktrace.o, so a single translation-unit annotation covers the
equivalent scope. This is a prerequisite preference for the upcoming
reliable unwinder, but the change is valid on its own.
Signed-off-by: Wang Han <wanghan@linux.alibaba.com>
---
arch/riscv/kernel/Makefile | 6 ++++++
1 file changed, 6 insertions(+)
diff --git a/arch/riscv/kernel/Makefile b/arch/riscv/kernel/Makefile
index cabb99cadfb6..c565a72a36f3 100644
--- a/arch/riscv/kernel/Makefile
+++ b/arch/riscv/kernel/Makefile
@@ -44,6 +44,12 @@ CFLAGS_REMOVE_return_address.o = $(CC_FLAGS_FTRACE)
CFLAGS_REMOVE_sbi_ecall.o = $(CC_FLAGS_FTRACE)
endif
+# When KASAN is enabled, a stack trace is recorded for every alloc/free, which
+# can significantly impact performance. Avoid instrumenting the stack trace
+# collection code to minimize this impact.
+KASAN_SANITIZE_stacktrace.o := n
+KCOV_INSTRUMENT_stacktrace.o := n
+
always-$(KBUILD_BUILTIN) += vmlinux.lds
obj-y += head.o
--
2.43.0
^ permalink raw reply related
* [PATCH v13 11/11] tracing/probes: Add a new testcase for BTF typecasts
From: Masami Hiramatsu (Google) @ 2026-06-29 6:14 UTC (permalink / raw)
To: Steven Rostedt, Mathieu Desnoyers
Cc: Jonathan Corbet, Shuah Khan, Masami Hiramatsu, linux-kernel,
linux-trace-kernel, linux-doc, linux-kselftest
In-Reply-To: <178271357142.1176915.7193483024740701480.stgit@devnote2>
From: Masami Hiramatsu (Google) <mhiramat@kernel.org>
With the introduction of container_of-style BTF typecasting and
per-CPU variable access support in trace probes, we need a way to
verify their functionality and prevent regressions.
Add a new ftrace kselftest and update the trace event sample module
to test and validate these features.
Specifically, update the trace-events-sample module to set up a
periodic timer whose callback accesses a per-CPU counter. Introduce
a new sample trace event, foo_timer_fn, to trace this callback
and log the current counter value.
Then, add a new test case, btf_probe_event.tc, which defines a
dynamic probe on the timer callback. The probe uses BTF typecasting
to recover the parent structure from the timer argument and
this_cpu_read() to fetch the per-CPU counter. The test verifies
the integrity of the implementation by ensuring the values
recorded by the dynamic probe match those from the static tracepoint.
Assisted-by: Antigravity:gemini-3.5-flash
Signed-off-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
---
Changes in v12:
- Fix current support check in eprobe testcase.
- Fix to return UNRESOLVED error if sample module is not found.
- Always check this_cpu_* in btf_typecast_accepted.tc.
Changes in v11:
- nit: fix the error code in comment.
Changes in v10:
- Add a check for $current and this_cpu_* for eprobe
Changes in v9:
- Add a testcase for checking new syntax.
Changes in v8:
- Add more test cases.
Changes in v6:
- Update testcase according to changes.
Changes in v5:
- Add more syntax test cases.
Changes in v4:
- Fix uprobe $current test.
Changes in v3:
- Add syntax test case.
- Update testcase to use this_cpu_read()
Changes in v2:
- Use timer_shutdown_sync() instead of timer_delete_sync() for teardown.
---
samples/trace_events/trace-events-sample.c | 40 +++++++-
samples/trace_events/trace-events-sample.h | 34 ++++++-
.../ftrace/test.d/dynevent/btf_probe_event.tc | 51 ++++++++++
.../test.d/dynevent/btf_typecast_accepted.tc | 103 ++++++++++++++++++++
.../test.d/dynevent/eprobes_syntax_errors.tc | 9 ++
.../ftrace/test.d/dynevent/fprobe_syntax_errors.tc | 12 ++
.../ftrace/test.d/kprobe/kprobe_syntax_errors.tc | 12 ++
.../ftrace/test.d/kprobe/uprobe_syntax_errors.tc | 5 +
8 files changed, 261 insertions(+), 5 deletions(-)
create mode 100644 tools/testing/selftests/ftrace/test.d/dynevent/btf_probe_event.tc
create mode 100644 tools/testing/selftests/ftrace/test.d/dynevent/btf_typecast_accepted.tc
diff --git a/samples/trace_events/trace-events-sample.c b/samples/trace_events/trace-events-sample.c
index 0b7a6efdb247..ca5d98c360cb 100644
--- a/samples/trace_events/trace-events-sample.c
+++ b/samples/trace_events/trace-events-sample.c
@@ -94,6 +94,20 @@ static int simple_thread_fn(void *arg)
static DEFINE_MUTEX(thread_mutex);
static int simple_thread_cnt;
+static struct foo_timer_data *foo_timer_data;
+
+static void sample_timer_cb(struct timer_list *t)
+{
+ struct foo_timer_data *data = container_of(t, struct foo_timer_data, timer);
+
+ get_cpu();
+ trace_foo_timer_fn(data);
+ (*this_cpu_ptr(data->counter))++;
+ put_cpu();
+
+ mod_timer(t, jiffies + HZ);
+}
+
int foo_bar_reg(void)
{
mutex_lock(&thread_mutex);
@@ -132,9 +146,27 @@ void foo_bar_unreg(void)
static int __init trace_event_init(void)
{
+ foo_timer_data = kzalloc_obj(*foo_timer_data, GFP_KERNEL);
+ if (!foo_timer_data)
+ return -ENOMEM;
+
+ foo_timer_data->name = "sample_timer_counter";
+ foo_timer_data->counter = alloc_percpu(int);
+ if (!foo_timer_data->counter) {
+ kfree(foo_timer_data);
+ return -ENOMEM;
+ }
+
+ timer_setup(&foo_timer_data->timer, sample_timer_cb, 0);
+ mod_timer(&foo_timer_data->timer, jiffies + HZ);
+
simple_tsk = kthread_run(simple_thread, NULL, "event-sample");
- if (IS_ERR(simple_tsk))
- return -1;
+ if (IS_ERR(simple_tsk)) {
+ timer_shutdown_sync(&foo_timer_data->timer);
+ free_percpu(foo_timer_data->counter);
+ kfree(foo_timer_data);
+ return PTR_ERR(simple_tsk);
+ }
return 0;
}
@@ -147,6 +179,10 @@ static void __exit trace_event_exit(void)
kthread_stop(simple_tsk_fn);
simple_tsk_fn = NULL;
mutex_unlock(&thread_mutex);
+
+ timer_shutdown_sync(&foo_timer_data->timer);
+ free_percpu(foo_timer_data->counter);
+ kfree(foo_timer_data);
}
module_init(trace_event_init);
diff --git a/samples/trace_events/trace-events-sample.h b/samples/trace_events/trace-events-sample.h
index 1a05fc153353..816848a456a2 100644
--- a/samples/trace_events/trace-events-sample.h
+++ b/samples/trace_events/trace-events-sample.h
@@ -247,12 +247,14 @@
*/
/*
- * It is OK to have helper functions in the file, but they need to be protected
- * from being defined more than once. Remember, this file gets included more
- * than once.
+ * It is OK to have helper functions and data structures in the file, but they
+ * need to be protected from being defined more than once. Remember, this file
+ * gets included more than once.
*/
#ifndef __TRACE_EVENT_SAMPLE_HELPER_FUNCTIONS
#define __TRACE_EVENT_SAMPLE_HELPER_FUNCTIONS
+#include <linux/timer.h>
+
static inline int __length_of(const int *list)
{
int i;
@@ -270,6 +272,13 @@ enum {
TRACE_SAMPLE_BAR = 4,
TRACE_SAMPLE_ZOO = 8,
};
+
+struct foo_timer_data {
+ const char *name;
+ struct timer_list timer;
+ int __percpu *counter;
+};
+
#endif
/*
@@ -595,6 +604,25 @@ TRACE_EVENT(foo_rel_loc,
__get_rel_bitmask(bitmask),
__get_rel_cpumask(cpumask))
);
+
+TRACE_EVENT(foo_timer_fn,
+
+ TP_PROTO(struct foo_timer_data *data),
+
+ TP_ARGS(data),
+
+ TP_STRUCT__entry(
+ __string( name, data->name )
+ __field( int, count )
+ ),
+
+ TP_fast_assign(
+ __assign_str(name);
+ __entry->count = *this_cpu_ptr(data->counter);
+ ),
+
+ TP_printk("name=%s count=%d", __get_str(name), __entry->count)
+);
#endif
/***** NOTICE! The #if protection ends here. *****/
diff --git a/tools/testing/selftests/ftrace/test.d/dynevent/btf_probe_event.tc b/tools/testing/selftests/ftrace/test.d/dynevent/btf_probe_event.tc
new file mode 100644
index 000000000000..bf71368c31a4
--- /dev/null
+++ b/tools/testing/selftests/ftrace/test.d/dynevent/btf_probe_event.tc
@@ -0,0 +1,51 @@
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
+# description: BTF event with typecast and percpu access
+# requires: dynamic_events "this_cpu_read(<fetcharg>)":README "[(structname[,field])]<argname>[->field[->field|.field...]]":README
+
+# Check if the sample module is loaded
+if ! lsmod | grep -q trace_events_sample; then
+ modprobe trace-events-sample || exit_unresolved
+fi
+
+echo 0 > events/enable
+echo > dynamic_events
+
+# The sample_timer_cb(struct timer_list *t) is called.
+# We want to check (STRUCT,FIELD)VAR typecast and this_cpu_read() access.
+# (foo_timer_data,timer)t converts t to struct foo_timer_data * using container_of.
+# data->counter is a per-cpu pointer to int.
+# this_cpu_read(data->counter) should give the value of the counter.
+
+echo 'f:mysample/myevent sample_timer_cb name=(foo_timer_data,timer)t->name:string count=this_cpu_read((foo_timer_data,timer)t->counter)' >> dynamic_events
+
+echo 1 > events/mysample/myevent/enable
+echo 1 > events/sample-trace/foo_timer_fn/enable
+
+sleep 2
+
+echo 0 > events/mysample/myevent/enable
+echo 0 > events/sample-trace/foo_timer_fn/enable
+
+# Compare the values.
+MATCH=0
+while read line; do
+ if echo $line | grep -q "foo_timer_fn:"; then
+ NAME=`echo $line | sed 's/.*name=\([^ ]*\) .*/\1/'`
+ COUNT=`echo $line | sed 's/.*count=\([^ ]*\).*/\1/'`
+ if grep -q "myevent:.*name=\"${NAME}\" count=$COUNT" trace; then
+ MATCH=$((MATCH+1))
+ fi
+ fi
+done < trace
+
+if [ $MATCH -eq 0 ]; then
+ echo "No matching events found"
+ exit_fail
+fi
+
+# Clean up
+echo 0 > events/mysample/myevent/enable
+echo 0 > events/sample-trace/foo_timer_fn/enable
+echo > dynamic_events
+clear_trace
diff --git a/tools/testing/selftests/ftrace/test.d/dynevent/btf_typecast_accepted.tc b/tools/testing/selftests/ftrace/test.d/dynevent/btf_typecast_accepted.tc
new file mode 100644
index 000000000000..dd5552727054
--- /dev/null
+++ b/tools/testing/selftests/ftrace/test.d/dynevent/btf_typecast_accepted.tc
@@ -0,0 +1,103 @@
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
+# description: BTF typecast and percpu access syntax validation
+# requires: dynamic_events "this_cpu_read(<fetcharg>)":README "[(structname[,field])]<argname>[->field[->field|.field...]]":README
+
+KPROBES=
+FPROBES=
+
+if grep -qF "p[:[<group>/][<event>]] <place> [<args>]" README ; then
+ KPROBES=yes
+fi
+if grep -qF "f[:[<group>/][<event>]] <func-name>[%return] [<args>]" README ; then
+ FPROBES=yes
+fi
+
+if [ -z "$KPROBES" -a -z "$FPROBES" ] ; then
+ exit_unsupported
+fi
+
+echo 0 > events/enable
+echo > dynamic_events
+
+# Load trace-events-sample module if available to have per-CPU counter structure defined
+if ! lsmod | grep -q trace_events_sample; then
+ modprobe trace-events-sample || exit_unresolved
+fi
+
+if [ "$FPROBES" ] ; then
+ # 1. Test basic typecast on fprobe
+ echo 'f:fpevent1 vfs_read name=(file)file->f_path.dentry->d_name.name:string' >> dynamic_events
+ # 2. Test parenthesized typecast target on fprobe
+ echo 'f:fpevent2 vfs_read name=(file)(file)->f_path.dentry->d_name.name:string' >> dynamic_events
+ # 3. Test nested typecasts on fprobe
+ echo 'f:fpevent3 vfs_read name=(dentry)((file)file->f_path.dentry)->d_name.name:string' >> dynamic_events
+ # 4. Test container_of-style typecast with field option on fprobe
+ echo 'f:fpevent4 vfs_read name=(file,f_path)file->f_mode' >> dynamic_events
+ # 5. Test typecast on return value on fprobe
+ echo 'f:fpevent5 vfs_read%return name=(file)$retval->f_path.dentry->d_name.name:string' >> dynamic_events
+ # 6. Test $current variable support on fprobe
+ echo 'f:fpevent6 vfs_read pid=$current->pid' >> dynamic_events
+ echo 'f:fpevent7 vfs_read pid=(task_struct)$current->pid' >> dynamic_events
+ echo 'f:fpevent8 vfs_read pid=(task_struct,group_leader)$current->pid' >> dynamic_events
+
+ # Test this_cpu_read and this_cpu_ptr on fprobe
+ echo 'f:fpevent9 sample_timer_cb name=(foo_timer_data,timer)t->name:string count=this_cpu_read((foo_timer_data,timer)t->counter)' >> dynamic_events
+ echo 'f:fpevent10 sample_timer_cb ptr=this_cpu_ptr((foo_timer_data,timer)t->counter)' >> dynamic_events
+fi
+
+if [ "$KPROBES" ] ; then
+ # 7. Test basic typecast on kprobe
+ echo 'p:kpevent1 vfs_read name=(file)file->f_path.dentry->d_name.name:string' >> dynamic_events
+ # 8. Test parenthesized typecast target on kprobe
+ echo 'p:kpevent2 vfs_read name=(file)(file)->f_path.dentry->d_name.name:string' >> dynamic_events
+ # 9. Test nested typecasts on kprobe
+ echo 'p:kpevent3 vfs_read name=(dentry)((file)file->f_path.dentry)->d_name.name:string' >> dynamic_events
+ # 10. Test container_of-style typecast with field option on kprobe
+ echo 'p:kpevent4 vfs_read name=(file,f_path)file->f_mode' >> dynamic_events
+ # 11. Test typecast on return value on kretprobe
+ echo 'r:kpevent5 vfs_read name=(file)$retval->f_path.dentry->d_name.name:string' >> dynamic_events
+ # 12. Test $current variable support on kprobe
+ echo 'p:kpevent6 vfs_read pid=$current->pid' >> dynamic_events
+ echo 'p:kpevent7 vfs_read pid=(task_struct)$current->pid' >> dynamic_events
+ echo 'p:kpevent8 vfs_read pid=(task_struct,group_leader)$current->pid' >> dynamic_events
+
+ # Test this_cpu_read and this_cpu_ptr on kprobe
+ echo 'p:kpevent9 sample_timer_cb name=(foo_timer_data,timer)t->name:string count=this_cpu_read((foo_timer_data,timer)t->counter)' >> dynamic_events
+ echo 'p:kpevent10 sample_timer_cb ptr=this_cpu_ptr((foo_timer_data,timer)t->counter)' >> dynamic_events
+fi
+
+# Verify the events exist in dynamic_events
+if [ "$FPROBES" ] ; then
+ grep -q "fpevent1 " dynamic_events
+ grep -q "fpevent2 " dynamic_events
+ grep -q "fpevent3 " dynamic_events
+ grep -q "fpevent4 " dynamic_events
+ grep -q "fpevent5 " dynamic_events
+ grep -q "fpevent6 " dynamic_events
+ grep -q "fpevent7 " dynamic_events
+ grep -q "fpevent8 " dynamic_events
+ if lsmod | grep -q trace_events_sample; then
+ grep -q "fpevent9 " dynamic_events
+ grep -q "fpevent10 " dynamic_events
+ fi
+fi
+
+if [ "$KPROBES" ] ; then
+ grep -q "kpevent1 " dynamic_events
+ grep -q "kpevent2 " dynamic_events
+ grep -q "kpevent3 " dynamic_events
+ grep -q "kpevent4 " dynamic_events
+ grep -q "kpevent5 " dynamic_events
+ grep -q "kpevent6 " dynamic_events
+ grep -q "kpevent7 " dynamic_events
+ grep -q "kpevent8 " dynamic_events
+ if lsmod | grep -q trace_events_sample; then
+ grep -q "kpevent9 " dynamic_events
+ grep -q "kpevent10 " dynamic_events
+ fi
+fi
+
+# Clean up
+echo > dynamic_events
+clear_trace
diff --git a/tools/testing/selftests/ftrace/test.d/dynevent/eprobes_syntax_errors.tc b/tools/testing/selftests/ftrace/test.d/dynevent/eprobes_syntax_errors.tc
index 0e65e787e426..c2e3f9d19f13 100644
--- a/tools/testing/selftests/ftrace/test.d/dynevent/eprobes_syntax_errors.tc
+++ b/tools/testing/selftests/ftrace/test.d/dynevent/eprobes_syntax_errors.tc
@@ -21,8 +21,17 @@ check_error 'e:foo/^bar.1 syscalls/sys_enter_openat' # BAD_EVENT_NAME
check_error 'e:foo/bar syscalls/sys_enter_openat arg=^$foo' # BAD_ATTACH_ARG
+check_error 'e:foo/bar syscalls/sys_enter_openat arg=^COMM' # NO_EVENT_FIELD
+if grep -q "\$current.*" README; then
+ check_error 'e:foo/bar syscalls/sys_enter_openat arg=^current' # NO_EVENT_FIELD
+fi
+
if grep -q '<attached-group>\.<attached-event>.*\[if <filter>\]' README; then
check_error 'e:foo/bar syscalls/sys_enter_openat if ^' # NO_EP_FILTER
fi
+if grep -q 'this_cpu_read(<fetcharg>)' README; then
+ check_error 'e:foo/bar syscalls/sys_enter_openat arg=^this_cpu_read(file)' # NOSUP_PERCPU
+fi
+
exit 0
diff --git a/tools/testing/selftests/ftrace/test.d/dynevent/fprobe_syntax_errors.tc b/tools/testing/selftests/ftrace/test.d/dynevent/fprobe_syntax_errors.tc
index fee479295e2f..e9d7e6919c7f 100644
--- a/tools/testing/selftests/ftrace/test.d/dynevent/fprobe_syntax_errors.tc
+++ b/tools/testing/selftests/ftrace/test.d/dynevent/fprobe_syntax_errors.tc
@@ -112,6 +112,18 @@ check_error 'f vfs_read%return $retval->^foo' # NO_PTR_STRCT
check_error 'f vfs_read file->^foo' # NO_BTF_FIELD
check_error 'f vfs_read file^-.foo' # BAD_HYPHEN
check_error 'f vfs_read ^file:string' # BAD_TYPE4STR
+if grep -qF "[(structname" README ; then
+check_error 'f vfs_read arg1=(task_struct)file^' # TYPECAST_REQ_FIELD
+check_error 'f vfs_read arg1=(a)((b)((c)(^(d)file->d)->c)->b)->a' # TOO_MANY_NESTED
+check_error 'f vfs_read arg1=(task_struct,^in_execve)file->comm' # TYPECAST_NOT_ALIGNED
+check_error 'f vfs_read arg1=(task_struct,^foo_bar)file->pid' # NO_BTF_FIELD
+check_error 'f vfs_read arg1=(^task_struct1234)file->pid' # NO_PTR_STRCT
+check_error 'f vfs_read arg1=(task_struct,se^->group_node)file->comm' # TYPECAST_BAD_ARROW
+check_error 'f vfs_read arg1=(task_struct,^->pid)file->comm' # NO_BTF_FIELD
+check_error 'f vfs_read arg1=(task_struct,^.pid)file->comm' # NO_BTF_FIELD
+check_error 'f vfs_read arg1=(task_struct,^.)file->comm' # NO_BTF_FIELD
+check_error 'f vfs_read arg1=(task_struct)^@symbol+10->comm' # TYPECAST_SYM_OFFSET
+fi
fi
else
diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_syntax_errors.tc b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_syntax_errors.tc
index 8f1c58f0c239..21ce8414459f 100644
--- a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_syntax_errors.tc
+++ b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_syntax_errors.tc
@@ -115,6 +115,18 @@ check_error 'p vfs_read+20 ^$arg*' # NOFENTRY_ARGS
check_error 'p vfs_read ^hoge' # NO_BTFARG
check_error 'p kfree ^$arg10' # NO_BTFARG (exceed the number of parameters)
check_error 'r kfree ^$retval' # NO_RETVAL
+if grep -qF "[(structname" README ; then
+check_error 'p vfs_read arg1=(task_struct)file^' # TYPECAST_REQ_FIELD
+check_error 'p vfs_read arg1=(a)((b)((c)(^(d)file->d)->c)->b)->a' # TOO_MANY_NESTED
+check_error 'p vfs_read arg1=(task_struct,^in_execve)file->comm' # TYPECAST_NOT_ALIGNED
+check_error 'p vfs_read arg1=(task_struct,^foo_bar)file->pid' # NO_BTF_FIELD
+check_error 'p vfs_read arg1=(^task_struct1234)file->pid' # NO_PTR_STRCT
+check_error 'p vfs_read arg1=(task_struct,se^->group_node)file->comm' # TYPECAST_BAD_ARROW
+check_error 'p vfs_read arg1=(task_struct,^->pid)file->comm' # NO_BTF_FIELD
+check_error 'p vfs_read arg1=(task_struct,^.pid)file->comm' # NO_BTF_FIELD
+check_error 'p vfs_read arg1=(task_struct,^.)file->comm' # NO_BTF_FIELD
+check_error 'p vfs_read arg1=(task_struct)^@symbol+10->comm' # TYPECAST_SYM_OFFSET
+fi
else
check_error 'p vfs_read ^$arg*' # NOSUP_BTFARG
fi
diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/uprobe_syntax_errors.tc b/tools/testing/selftests/ftrace/test.d/kprobe/uprobe_syntax_errors.tc
index c817158b99db..e12dc967ec76 100644
--- a/tools/testing/selftests/ftrace/test.d/kprobe/uprobe_syntax_errors.tc
+++ b/tools/testing/selftests/ftrace/test.d/kprobe/uprobe_syntax_errors.tc
@@ -28,4 +28,9 @@ if grep -q ".*symstr.*" README; then
check_error 'p /bin/sh:10 $stack0:^symstr' # BAD_TYPE
fi
+# $current is not supported by uprobe
+if grep -q "\$current.*" README; then
+check_error 'p /bin/sh:10 ^$current:u8' # BAD_VAR
+fi
+
exit 0
^ permalink raw reply related
* [PATCH v13 10/11] tracing/probes: Add this_cpu_read() and this_cpu_ptr() dereference method to fetcharg
From: Masami Hiramatsu (Google) @ 2026-06-29 6:14 UTC (permalink / raw)
To: Steven Rostedt, Mathieu Desnoyers
Cc: Jonathan Corbet, Shuah Khan, Masami Hiramatsu, linux-kernel,
linux-trace-kernel, linux-doc, linux-kselftest
In-Reply-To: <178271357142.1176915.7193483024740701480.stgit@devnote2>
From: Masami Hiramatsu (Google) <mhiramat@kernel.org>
When tracing the kernel local variables, sometimes we need to get the
CPU local variables. To access it, current simple dereference is not
enough.
Thus, introduce a special this_cpu_read() dereference to access per-cpu
variable for the current CPU (accessing other CPU variable may race with
updates on other CPUs). Also this_cpu_ptr() is for accessing per-cpu
pointer.
Those are working as same as the kernel percpu macro.
Signed-off-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
---
Changes in v13:
- Remove missed comma fix from this patch.
Changes in v11:
- Remove this_cpu_*() from eprobetrace.rst.
Changes in v10:
- Prohibit this_cpu_*() for eprobe events.
Changes in v9:
- Prohibit this_cpu_*() for non kernel probes.
Changes in v6:
- Rebased on dump fetcharg patch.
- Fix to fetch static percpu variable with @SYM correctly.
Changes in v5:
- Simplify this_cpu_read() into +0(this_cpu_ptr()).
Changes in v3:
- Remove NULL check for percpu var because it is just an offset, could be 0.
- Simplify process_fetch_insn_bottom() code.
- If the last operation is this_cpu_read(), read only memory of the specific
size (of type).
Changes in v2:
- Drop +CPU/+PCPU and introduce this_cpu_read() and this_cpu_ptr().
- Support these method with BTF typecast.
- Just check the base address is NOT NULL instead of is_kernel_percpu_address().
---
Documentation/trace/fprobetrace.rst | 2
Documentation/trace/kprobetrace.rst | 2
kernel/trace/trace.c | 1
kernel/trace/trace_probe.c | 152 ++++++++++++++++++++++++++---------
kernel/trace/trace_probe.h | 4 +
kernel/trace/trace_probe_tmpl.h | 22 ++++-
6 files changed, 138 insertions(+), 45 deletions(-)
diff --git a/Documentation/trace/fprobetrace.rst b/Documentation/trace/fprobetrace.rst
index 3392cab016b3..3439bc9bd351 100644
--- a/Documentation/trace/fprobetrace.rst
+++ b/Documentation/trace/fprobetrace.rst
@@ -52,6 +52,8 @@ Synopsis of fprobe-events
$comm : Fetch current task comm.
$current : Fetch the address of the current task_struct.
+|-[u]OFFS(FETCHARG) : Fetch memory at FETCHARG +|- OFFS address.(\*4)(\*5)
+ this_cpu_read(FETCHARG) : Read the value of the per-CPU variable FETCHARG on the current CPU.
+ this_cpu_ptr(FETCHARG) : Get the address of the per-CPU variable FETCHARG on the current CPU.
\IMM : Store an immediate value to the argument.
NAME=FETCHARG : Set NAME as the argument name of FETCHARG.
FETCHARG:TYPE : Set TYPE as the type of FETCHARG. Currently, basic types
diff --git a/Documentation/trace/kprobetrace.rst b/Documentation/trace/kprobetrace.rst
index 81e4fe38791d..9ae330eb0a52 100644
--- a/Documentation/trace/kprobetrace.rst
+++ b/Documentation/trace/kprobetrace.rst
@@ -55,6 +55,8 @@ Synopsis of kprobe_events
$comm : Fetch current task comm.
$current : Fetch the address of the current task_struct.
+|-[u]OFFS(FETCHARG) : Fetch memory at FETCHARG +|- OFFS address.(\*3)(\*4)
+ this_cpu_read(FETCHARG) : Read the value of the per-CPU variable FETCHARG on the current CPU.
+ this_cpu_ptr(FETCHARG) : Get the address of the per-CPU variable FETCHARG on the current CPU.
\IMM : Store an immediate value to the argument.
NAME=FETCHARG : Set NAME as the argument name of FETCHARG.
FETCHARG:TYPE : Set TYPE as the type of FETCHARG. Currently, basic types
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 2b0b4f9acb2e..c9e182d40059 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -4329,6 +4329,7 @@ static const char readme_msg[] =
"\t $stack<index>, $stack, $retval, $comm, $current\n"
#endif
"\t +|-[u]<offset>(<fetcharg>), \\imm-value, \\\"imm-string\"\n"
+ "\t this_cpu_read(<fetcharg>), this_cpu_ptr(<fetcharg>)\n"
"\t kernel return probes support: $retval, $arg<N>, $comm\n"
"\t type: s8/16/32/64, u8/16/32/64, x8/16/32/64, char, string, symbol,\n"
"\t b<bit-width>@<bit-offset>/<container-size>, ustring,\n"
diff --git a/kernel/trace/trace_probe.c b/kernel/trace/trace_probe.c
index 999dec84275d..18c212122344 100644
--- a/kernel/trace/trace_probe.c
+++ b/kernel/trace/trace_probe.c
@@ -345,6 +345,109 @@ static int parse_trace_event(char *arg, struct fetch_insn *code,
return -EINVAL;
}
+/* this_cpu_* parser */
+#define THIS_CPU_PTR_PREFIX "this_cpu_ptr("
+#define THIS_CPU_READ_PREFIX "this_cpu_read("
+#define THIS_CPU_PTR_LEN (sizeof(THIS_CPU_PTR_PREFIX) - 1)
+#define THIS_CPU_READ_LEN (sizeof(THIS_CPU_READ_PREFIX) - 1)
+
+static int
+parse_probe_arg(char *arg, const struct fetch_type *type,
+ struct fetch_insn **pcode, struct fetch_insn *end,
+ struct traceprobe_parse_context *ctx);
+
+/* handle dereference nested call */
+static inline int handle_dereference(char *arg, struct fetch_insn **pcode,
+ struct fetch_insn *end, struct traceprobe_parse_context *ctx,
+ int deref, long offset)
+{
+ const struct fetch_type *type = find_fetch_type(NULL, ctx->flags);
+ struct fetch_insn *code = *pcode;
+ int cur_offs = ctx->offset;
+ char *tmp;
+ int ret;
+
+ tmp = strrchr(arg, ')');
+ if (!tmp) {
+ trace_probe_log_err(ctx->offset + strlen(arg),
+ DEREF_OPEN_BRACE);
+ return -EINVAL;
+ }
+
+ *tmp = '\0';
+ ret = parse_probe_arg(arg, type, &code, end, ctx);
+ if (ret)
+ return ret;
+ ctx->offset = cur_offs;
+ if (code->op == FETCH_OP_COMM || code->op == FETCH_OP_IMMSTR) {
+ trace_probe_log_err(ctx->offset, COMM_CANT_DEREF);
+ return -EINVAL;
+ }
+
+ /*
+ * this_cpu_ptr(@SYM) does not use SYM value, but use SYM address.
+ * So we overwrite the last FETCH_OP_DEREF with FETCH_OP_CPU_PTR.
+ */
+ if (!(deref == FETCH_OP_CPU_PTR && *arg == '@')) {
+ code++;
+ if (code == end) {
+ trace_probe_log_err(ctx->offset, TOO_MANY_OPS);
+ return -EINVAL;
+ }
+ }
+ *pcode = code;
+
+ code->op = deref;
+ code->offset = offset;
+ /* Reset the last type if used */
+ ctx->last_type = NULL;
+ return 0;
+}
+
+static int parse_this_cpu(char *arg, struct fetch_insn **pcode,
+ struct fetch_insn *end,
+ struct traceprobe_parse_context *ctx)
+{
+ struct fetch_insn *code;
+ bool is_ptr = false;
+ int ret;
+
+ /*
+ * This is only for kernel probes, excluding eprobe, because per-cpu
+ * pointer should not be recorded by events.
+ */
+ if (!(ctx->flags & TPARG_FL_KERNEL) ||
+ (ctx->flags & TPARG_FL_TEVENT)) {
+ trace_probe_log_err(ctx->offset, NOSUP_PERCPU);
+ return -EINVAL;
+ }
+ if (str_has_prefix(arg, THIS_CPU_PTR_PREFIX)) {
+ arg += THIS_CPU_PTR_LEN;
+ ctx->offset += THIS_CPU_PTR_LEN;
+ is_ptr = true;
+ } else if (str_has_prefix(arg, THIS_CPU_READ_PREFIX)) {
+ arg += THIS_CPU_READ_LEN;
+ ctx->offset += THIS_CPU_READ_LEN;
+ } else
+ return -EINVAL;
+
+ ret = handle_dereference(arg, pcode, end, ctx, FETCH_OP_CPU_PTR, 0);
+ if (ret || is_ptr)
+ return ret;
+
+ /* this_cpu_read(VAR) -> +0(this_cpu_ptr(VAR)) */
+ code = *pcode;
+ code++;
+ if (code == end) {
+ trace_probe_log_err(ctx->offset, TOO_MANY_OPS);
+ return -EINVAL;
+ }
+ code->op = FETCH_OP_DEREF;
+ code->offset = 0;
+ *pcode = code;
+ return 0;
+}
+
#ifdef CONFIG_PROBE_EVENTS_BTF_ARGS
static u32 btf_type_int(const struct btf_type *t)
@@ -904,11 +1007,6 @@ static char *find_matched_close_paren(char *s)
return NULL;
}
-static int
-parse_probe_arg(char *arg, const struct fetch_type *type,
- struct fetch_insn **pcode, struct fetch_insn *end,
- struct traceprobe_parse_context *ctx);
-
static int handle_typecast(char *arg, struct fetch_insn **pcode,
struct fetch_insn *end,
struct traceprobe_parse_context *ctx)
@@ -961,7 +1059,9 @@ static int handle_typecast(char *arg, struct fetch_insn **pcode,
/* Skip '(' */
ctx->offset += 1;
tmp++;
- } else if (*tmp == '+' || *tmp == '-') {
+ } else if (*tmp == '+' || *tmp == '-' ||
+ str_has_prefix(tmp, THIS_CPU_PTR_PREFIX) ||
+ str_has_prefix(tmp, THIS_CPU_READ_PREFIX)) {
/* Dereference can have another field access inside it. */
char *open = strchr(tmp + 1, '(');
@@ -1481,36 +1581,9 @@ parse_probe_arg(char *arg, const struct fetch_type *type,
}
ctx->offset += (tmp + 1 - arg) + (arg[0] != '-' ? 1 : 0);
arg = tmp + 1;
- tmp = strrchr(arg, ')');
- if (!tmp) {
- trace_probe_log_err(ctx->offset + strlen(arg),
- DEREF_OPEN_BRACE);
- return -EINVAL;
- } else {
- const struct fetch_type *t2 = find_fetch_type(NULL, ctx->flags);
- int cur_offs = ctx->offset;
-
- *tmp = '\0';
- ret = parse_probe_arg(arg, t2, &code, end, ctx);
- if (ret)
- break;
- ctx->offset = cur_offs;
- if (code->op == FETCH_OP_COMM ||
- code->op == FETCH_OP_IMMSTR) {
- trace_probe_log_err(ctx->offset, COMM_CANT_DEREF);
- return -EINVAL;
- }
- if (++code == end) {
- trace_probe_log_err(ctx->offset, TOO_MANY_OPS);
- return -EINVAL;
- }
- *pcode = code;
-
- code->op = deref;
- code->offset = offset;
- /* Reset the last type if used */
- ctx->last_type = NULL;
- }
+ ret = handle_dereference(arg, pcode, end, ctx, deref, offset);
+ if (ret < 0)
+ return ret;
break;
case '\\': /* Immediate value */
if (arg[1] == '"') { /* Immediate string */
@@ -1531,7 +1604,10 @@ parse_probe_arg(char *arg, const struct fetch_type *type,
ret = handle_typecast(arg, pcode, end, ctx);
break;
default:
- if (isalpha(arg[0]) || arg[0] == '_') {
+ if (str_has_prefix(arg, THIS_CPU_PTR_PREFIX) ||
+ str_has_prefix(arg, THIS_CPU_READ_PREFIX)) {
+ ret = parse_this_cpu(arg, pcode, end, ctx);
+ } else if (isalpha(arg[0]) || arg[0] == '_') {
/* BTF variable or event field*/
if (ctx->flags & TPARG_FL_TEVENT) {
ret = parse_trace_event(arg, *pcode, ctx);
@@ -1548,8 +1624,8 @@ parse_probe_arg(char *arg, const struct fetch_type *type,
return -EINVAL;
}
ret = parse_btf_arg(arg, pcode, end, ctx);
- break;
}
+ break;
}
if (!ret && code->op == FETCH_OP_NOP) {
/* Parsed, but do not find fetch method */
diff --git a/kernel/trace/trace_probe.h b/kernel/trace/trace_probe.h
index 195096f5b8b1..e6268a8dc378 100644
--- a/kernel/trace/trace_probe.h
+++ b/kernel/trace/trace_probe.h
@@ -101,6 +101,7 @@ typedef int (*print_type_func_t)(struct trace_seq *, void *, void *);
/* Stage 2 (dereference) ops */ \
FETCH_OP(DEREF, offset), /* Dereference: .offset */ \
FETCH_OP(UDEREF, offset), /* User-space dereference: .offset */\
+ FETCH_OP(CPU_PTR, none), /* Per-CPU pointer: .offset */ \
/* Stage 3 (store) ops */ \
FETCH_OP(ST_RAW, store), /* Raw value: .size */ \
FETCH_OP(ST_MEM, store), /* Memory: .offset, .size */ \
@@ -598,7 +599,8 @@ extern int traceprobe_define_arg_fields(struct trace_event_call *event_call,
C(TOO_MANY_NESTED, "Too many nested typecasts/dereferences"), \
C(TYPECAST_SYM_OFFSET, "@SYM+/-OFFSET with typecast needs parentheses"), \
C(TYPECAST_NOT_ALIGNED, "Typecast field option is not byte-aligned"), \
- C(TYPECAST_BAD_ARROW, "Typecast field option does not support -> operator"),
+ C(TYPECAST_BAD_ARROW, "Typecast field option does not support -> operator"), \
+ C(NOSUP_PERCPU, "Per-cpu variable access is only for kernel probes"),
#undef C
#define C(a, b) TP_ERR_##a
diff --git a/kernel/trace/trace_probe_tmpl.h b/kernel/trace/trace_probe_tmpl.h
index d0e9662cde00..8db12f758fda 100644
--- a/kernel/trace/trace_probe_tmpl.h
+++ b/kernel/trace/trace_probe_tmpl.h
@@ -129,25 +129,35 @@ process_fetch_insn_bottom(struct fetch_insn *code, unsigned long val,
struct fetch_insn *s3 = NULL;
int total = 0, ret = 0, i = 0;
u32 loc = 0;
- unsigned long lval = val;
+ unsigned long lval, llval = val;
stage2:
/* 2nd stage: dereference memory if needed */
do {
- if (code->op == FETCH_OP_DEREF) {
- lval = val;
+ lval = val;
+ switch (code->op) {
+ case FETCH_OP_DEREF:
ret = probe_mem_read(&val, (void *)val + code->offset,
sizeof(val));
- } else if (code->op == FETCH_OP_UDEREF) {
- lval = val;
+ break;
+ case FETCH_OP_UDEREF:
ret = probe_mem_read_user(&val,
(void *)val + code->offset, sizeof(val));
- } else
break;
+ case FETCH_OP_CPU_PTR:
+ val = (unsigned long)this_cpu_ptr((void __percpu *)val);
+ ret = 0;
+ break;
+ default:
+ lval = llval;
+ goto out;
+ }
if (ret)
return ret;
+ llval = lval;
code++;
} while (1);
+out:
s3 = code;
stage3:
^ permalink raw reply related
* [PATCH v13 09/11] tracing/probes: Add $current variable support
From: Masami Hiramatsu (Google) @ 2026-06-29 6:14 UTC (permalink / raw)
To: Steven Rostedt, Mathieu Desnoyers
Cc: Jonathan Corbet, Shuah Khan, Masami Hiramatsu, linux-kernel,
linux-trace-kernel, linux-doc, linux-kselftest
In-Reply-To: <178271357142.1176915.7193483024740701480.stgit@devnote2>
From: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Since we can use the BTF to cast value to a structure pointer type,
it is useful to introduce "$current" special variable support to
fetcharg.
User can define a fetcharg to access current task_struct properties
using BTF info. e.g.
$current->cpus_ptr
Signed-off-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
---
Changes in v8:
- Avoid uninitialized ctx->btf issue on $current without typecast.
Changes in v7:
- Fix to use force-typecast for task_struct implicitly.
Changes in v6:
- Rebased on dump fetcharg patch.
- Remove function name/eprobe requirement for $current.
Changes in v5:
- Use s32 for bof_find_btf_id().
Changes in v4:
- Add $current in README when CONFIG_HAVE_FUNCTION_ARG_ACCESS_API=y case.
- Fix to prohibit using $current in eprobes and address based kprobes.
Changes in v3:
- Remove $current support from eprobes (because eprobes is only for event)
- Prohibit uprobes to use $current.
Changes in v2:
- Support to parse $current in parse_btf_arg().
- If no typecast on $current, it automatically casted to task_struct.
- Check error case if $current follows something except for "-".
---
Documentation/trace/fprobetrace.rst | 1 +
Documentation/trace/kprobetrace.rst | 1 +
kernel/trace/trace.c | 4 ++--
kernel/trace/trace_probe.c | 37 ++++++++++++++++++++++++++++++++++-
kernel/trace/trace_probe.h | 1 +
kernel/trace/trace_probe_tmpl.h | 3 +++
6 files changed, 44 insertions(+), 3 deletions(-)
diff --git a/Documentation/trace/fprobetrace.rst b/Documentation/trace/fprobetrace.rst
index 290a9e6f7491..3392cab016b3 100644
--- a/Documentation/trace/fprobetrace.rst
+++ b/Documentation/trace/fprobetrace.rst
@@ -50,6 +50,7 @@ Synopsis of fprobe-events
$argN : Fetch the Nth function argument. (N >= 1) (\*2)
$retval : Fetch return value.(\*3)
$comm : Fetch current task comm.
+ $current : Fetch the address of the current task_struct.
+|-[u]OFFS(FETCHARG) : Fetch memory at FETCHARG +|- OFFS address.(\*4)(\*5)
\IMM : Store an immediate value to the argument.
NAME=FETCHARG : Set NAME as the argument name of FETCHARG.
diff --git a/Documentation/trace/kprobetrace.rst b/Documentation/trace/kprobetrace.rst
index a62707e6a9f2..81e4fe38791d 100644
--- a/Documentation/trace/kprobetrace.rst
+++ b/Documentation/trace/kprobetrace.rst
@@ -53,6 +53,7 @@ Synopsis of kprobe_events
$argN : Fetch the Nth function argument. (N >= 1) (\*1)
$retval : Fetch return value.(\*2)
$comm : Fetch current task comm.
+ $current : Fetch the address of the current task_struct.
+|-[u]OFFS(FETCHARG) : Fetch memory at FETCHARG +|- OFFS address.(\*3)(\*4)
\IMM : Store an immediate value to the argument.
NAME=FETCHARG : Set NAME as the argument name of FETCHARG.
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 5670c4b91dc0..2b0b4f9acb2e 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -4320,13 +4320,13 @@ static const char readme_msg[] =
"\t args: <name>=fetcharg[:type]\n"
"\t fetcharg: (%<register>|$<efield>), @<address>, @<symbol>[+|-<offset>],\n"
#ifdef CONFIG_HAVE_FUNCTION_ARG_ACCESS_API
- "\t $stack<index>, $stack, $retval, $comm, $arg<N>,\n"
+ "\t $stack<index>, $stack, $retval, $comm, $arg<N>, $current\n"
#ifdef CONFIG_PROBE_EVENTS_BTF_ARGS
"\t [(structname[,field])]<argname>[->field[->field|.field...]],\n"
"\t [(structname[,field])](fetcharg)->field[->field|.field...],\n"
#endif
#else
- "\t $stack<index>, $stack, $retval, $comm,\n"
+ "\t $stack<index>, $stack, $retval, $comm, $current\n"
#endif
"\t +|-[u]<offset>(<fetcharg>), \\imm-value, \\\"imm-string\"\n"
"\t kernel return probes support: $retval, $arg<N>, $comm\n"
diff --git a/kernel/trace/trace_probe.c b/kernel/trace/trace_probe.c
index fd006b415c68..999dec84275d 100644
--- a/kernel/trace/trace_probe.c
+++ b/kernel/trace/trace_probe.c
@@ -692,7 +692,9 @@ static int parse_btf_arg(char *varname,
int i, is_ptr, ret;
u32 tid;
- if (!ctx->funcname && !(ctx->flags & TPARG_FL_TEVENT))
+ /* Note: field is not separated at this point, so check prefix. */
+ if (!str_has_prefix(varname, "$current") &&
+ !ctx->funcname && !(ctx->flags & TPARG_FL_TEVENT))
return -EINVAL;
is_ptr = split_next_field(varname, &field, ctx);
@@ -705,6 +707,20 @@ static int parse_btf_arg(char *varname,
return -EOPNOTSUPP;
}
+ if (!strcmp(varname, "$current")) {
+ code->op = FETCH_OP_CURRENT;
+ /* If no typecast is specified for $current, use task_struct by default */
+ ret = bpf_find_btf_id("task_struct", BTF_KIND_STRUCT, &ctx->struct_btf);
+ if (ret < 0) {
+ trace_probe_log_err(ctx->offset, NO_BTF_ENTRY);
+ return -ENOENT;
+ }
+ tid = (u32)ret;
+ type = ctx->last_struct =
+ btf_type_skip_modifiers(ctx->struct_btf, tid, NULL);
+ goto found_type;
+ }
+
if (ctx->flags & TPARG_FL_RETURN && !strcmp(varname, "$retval")) {
code->op = FETCH_OP_RETVAL;
/* Check whether the function return type is not void, even with typecast. */
@@ -761,6 +777,7 @@ static int parse_btf_arg(char *varname,
found:
type = btf_type_skip_modifiers(ctx->btf, tid, NULL);
+found_type:
if (!type) {
trace_probe_log_err(ctx->offset, BAD_BTF_TID);
return -EINVAL;
@@ -1270,6 +1287,24 @@ static int parse_probe_vars(char *orig_arg, const struct fetch_type *t,
return 0;
}
+ /* $current returns the address of the current task_struct. */
+ if (str_has_prefix(arg, "current")) {
+ /* $current is only supported by kernel probe. */
+ if (!(ctx->flags & TPARG_FL_KERNEL)) {
+ err = TP_ERR_BAD_VAR;
+ goto inval;
+ }
+ arg += strlen("current");
+ if (*arg == '-' && IS_ENABLED(CONFIG_PROBE_EVENTS_BTF_ARGS))
+ return parse_btf_arg(orig_arg, pcode, end, ctx);
+
+ if (*arg != '\0')
+ goto inval;
+
+ code->op = FETCH_OP_CURRENT;
+ return 0;
+ }
+
#ifdef CONFIG_HAVE_FUNCTION_ARG_ACCESS_API
len = str_has_prefix(arg, "arg");
if (len) {
diff --git a/kernel/trace/trace_probe.h b/kernel/trace/trace_probe.h
index 6a0859e00bf4..195096f5b8b1 100644
--- a/kernel/trace/trace_probe.h
+++ b/kernel/trace/trace_probe.h
@@ -92,6 +92,7 @@ typedef int (*print_type_func_t)(struct trace_seq *, void *, void *);
FETCH_OP(RETVAL, none), /* Return value */ \
FETCH_OP(IMM, imm), /* Immediate: .immediate */ \
FETCH_OP(COMM, none), /* Current comm */ \
+ FETCH_OP(CURRENT, none), /* Current task_struct address */\
FETCH_OP(ARG, param), /* Argument: .param = index */ \
FETCH_OP(FOFFS, imm), /* File offset: .immediate */ \
FETCH_OP(IMMSTR, string), /* Allocated string: .data */ \
diff --git a/kernel/trace/trace_probe_tmpl.h b/kernel/trace/trace_probe_tmpl.h
index 51436f19083b..d0e9662cde00 100644
--- a/kernel/trace/trace_probe_tmpl.h
+++ b/kernel/trace/trace_probe_tmpl.h
@@ -112,6 +112,9 @@ process_common_fetch_insn(struct fetch_insn *code, unsigned long *val)
case FETCH_OP_IMMSTR:
*val = (unsigned long)code->data;
break;
+ case FETCH_OP_CURRENT:
+ *val = (unsigned long)current;
+ break;
default:
return -EILSEQ;
}
^ permalink raw reply related
* [PATCH v13 08/11] tracing/probes: Support field specifier option for typecast
From: Masami Hiramatsu (Google) @ 2026-06-29 6:14 UTC (permalink / raw)
To: Steven Rostedt, Mathieu Desnoyers
Cc: Jonathan Corbet, Shuah Khan, Masami Hiramatsu, linux-kernel,
linux-trace-kernel, linux-doc, linux-kselftest
In-Reply-To: <178271357142.1176915.7193483024740701480.stgit@devnote2>
From: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Add a field specifier option for the typecast. This works like
container_of() macro.
(STRUCT[,FIELD[.FIELD2...]])VAR
This is equivalent to :
container_of(VAR, struct STRUCT, FIELD[.FIELD2...])
For example:
echo "f tick_nohz_handler next_tick=(tick_sched,sched_timer)timer->next_tick" >> dynamic_events
This will trace tick_nohz_handler() with its tick_sched::next_tick which
is converted from @timer by contianer_of(tick, struct tick_sched, sched_timer).
So, if you enabkle both fprobes:tick_nohz_handler__entry and
timer:hrtimer_expire_entry events, we will see something like:
<idle>-0 [002] d.h1. 3778.087272: hrtimer_expire_entry: hrtimer=00000000d63db328 f
unction=tick_nohz_handler now=3777450051040
<idle>-0 [002] d.h1. 3778.087281: tick_nohz_handler__entry: (tick_nohz_handler+0x4
/0x140) next_tick=3777450000000
Signed-off-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
---
Changes in v13:
- Fix missed comma after TYPECAST_SYM_OFFSET error.
Changes in v6:
- Update according to the allways nested patch.
Changes in v3:
- Fix error caret position.
Changes in v2:
- Use byteoffset for typecast field offset instead of bitoffset. This fixes negative modulo calculation.
- Check whether a field is specified after typecast.
- Reject if typecast field option has arrow operator.
---
Documentation/trace/eprobetrace.rst | 5 +
Documentation/trace/fprobetrace.rst | 8 +-
Documentation/trace/kprobetrace.rst | 8 +-
kernel/trace/trace.c | 4 -
kernel/trace/trace_probe.c | 169 ++++++++++++++++++++++++-----------
kernel/trace/trace_probe.h | 5 +
6 files changed, 135 insertions(+), 64 deletions(-)
diff --git a/Documentation/trace/eprobetrace.rst b/Documentation/trace/eprobetrace.rst
index cd0b4aa7f896..680e0af43d5d 100644
--- a/Documentation/trace/eprobetrace.rst
+++ b/Documentation/trace/eprobetrace.rst
@@ -49,7 +49,10 @@ Synopsis of eprobe_events
(STRUCT)FIELD->MEMBER[->MEMBER] : If BTF is supported, typecast FIELD to
a pointer to STRUCT and then derference the pointer defined by
->MEMBER. Note that when this is used, the FIELD name does not
- need to be prefixed with a '$'.
+ need to be prefixed with a '$'. ASGN can be specified optionally.
+ If ASGN is specified, FIELD will be cast to the same offset
+ position as the ASGN member, rather than to the beginning of
+ the STRUCT.
(STRUCT)(FETCHARG)->MEMBER[->MEMBER] : typecast can nest, so the above can
also be used with another FETCHARG instead of FIELD.
diff --git a/Documentation/trace/fprobetrace.rst b/Documentation/trace/fprobetrace.rst
index 6b8bb27bb62d..290a9e6f7491 100644
--- a/Documentation/trace/fprobetrace.rst
+++ b/Documentation/trace/fprobetrace.rst
@@ -57,10 +57,12 @@ Synopsis of fprobe-events
(u8/u16/u32/u64/s8/s16/s32/s64), hexadecimal types
(x8/x16/x32/x64), "char", "string", "ustring", "symbol", "symstr"
and bitfield are supported.
- (STRUCT)FIELD->MEMBER[->MEMBER] : If BTF is supported, typecast FIELD to
+ (STRUCT[,ASGN])FIELD->MEMBER[->MEMBER] : If BTF is supported, typecast FIELD to
a pointer to STRUCT and then derference the pointer defined by
- ->MEMBER.
- (STRUCT)(FETCHARG)->MEMBER[->MEMBER] : typecast can nest, so the above can
+ ->MEMBER. ASGN can be specified optionally. If ASGN is specified,
+ FIELD will be cast to the same offset position as the ASGN member,
+ rather than to the beginning of the STRUCT.
+ (STRUCT[,ASGN])(FETCHARG)->MEMBER[->MEMBER] : typecast can nest, so the above can
also be used with another FETCHARG instead of FIELD.
(\*1) This is available only when BTF is enabled.
diff --git a/Documentation/trace/kprobetrace.rst b/Documentation/trace/kprobetrace.rst
index c4382765d5b2..a62707e6a9f2 100644
--- a/Documentation/trace/kprobetrace.rst
+++ b/Documentation/trace/kprobetrace.rst
@@ -61,11 +61,13 @@ Synopsis of kprobe_events
(x8/x16/x32/x64), VFS layer common type(%pd/%pD), "char",
"string", "ustring", "symbol", "symstr" and bitfield are
supported.
- (STRUCT)FIELD->MEMBER[->MEMBER] : If BTF is supported, typecast FIELD to
+ (STRUCT[,ASGN])FIELD->MEMBER[->MEMBER] : If BTF is supported, typecast FIELD to
a pointer to STRUCT and then derference the pointer defined by
->MEMBER. Note that this is available only when the probe is
- on function entry.
- (STRUCT)(FETCHARG)->MEMBER[->MEMBER] : typecast can nest, so the above can
+ on function entry. ASGN can be specified optionally. If ASGN
+ is specified, FIELD will be cast to the same offset position
+ as the ASGN member, rather than to the beginning of the STRUCT.
+ (STRUCT[,ASGN])(FETCHARG)->MEMBER[->MEMBER] : typecast can nest, so the above can
also be used with another FETCHARG instead of FIELD.
(\*1) only for the probe on function entry (offs == 0). Note, this argument access
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index e56ee034c486..5670c4b91dc0 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -4322,8 +4322,8 @@ static const char readme_msg[] =
#ifdef CONFIG_HAVE_FUNCTION_ARG_ACCESS_API
"\t $stack<index>, $stack, $retval, $comm, $arg<N>,\n"
#ifdef CONFIG_PROBE_EVENTS_BTF_ARGS
- "\t [(structname)]<argname>[->field[->field|.field...]],\n"
- "\t [(structname)](fetcharg)->field[->field|.field...],\n"
+ "\t [(structname[,field])]<argname>[->field[->field|.field...]],\n"
+ "\t [(structname[,field])](fetcharg)->field[->field|.field...],\n"
#endif
#else
"\t $stack<index>, $stack, $retval, $comm,\n"
diff --git a/kernel/trace/trace_probe.c b/kernel/trace/trace_probe.c
index 1b97b125e9cb..fd006b415c68 100644
--- a/kernel/trace/trace_probe.c
+++ b/kernel/trace/trace_probe.c
@@ -568,6 +568,64 @@ static int split_next_field(char *varname, char **next_field,
return ret;
}
+/* Inner loop for solving dot operator ('.'). Return bit-offset of the given field */
+static int get_bitoffset_of_field(char **pfieldname, const struct btf_type **ptype,
+ struct traceprobe_parse_context *ctx)
+{
+ const struct btf_type *type = *ptype;
+ const struct btf_member *field;
+ struct btf *btf = ctx_btf(ctx);
+ char *fieldname = *pfieldname;
+ int bitoffs = 0;
+ u32 anon_offs;
+ char *next;
+ int is_ptr;
+
+ do {
+ next = NULL;
+ is_ptr = split_next_field(fieldname, &next, ctx);
+ if (is_ptr < 0)
+ return is_ptr;
+
+ anon_offs = 0;
+ field = btf_find_struct_member(btf, type, fieldname,
+ &anon_offs);
+ if (IS_ERR(field)) {
+ trace_probe_log_err(ctx->offset, BAD_BTF_TID);
+ return PTR_ERR(field);
+ }
+ if (!field) {
+ trace_probe_log_err(ctx->offset, NO_BTF_FIELD);
+ return -ENOENT;
+ }
+ /* Add anonymous structure/union offset */
+ bitoffs += anon_offs;
+
+ /* Accumulate the bit-offsets of the dot-connected fields */
+ if (btf_type_kflag(type)) {
+ bitoffs += BTF_MEMBER_BIT_OFFSET(field->offset);
+ ctx->last_bitsize = BTF_MEMBER_BITFIELD_SIZE(field->offset);
+ } else {
+ bitoffs += field->offset;
+ ctx->last_bitsize = 0;
+ }
+
+ type = btf_type_skip_modifiers(btf, field->type, NULL);
+ if (!type) {
+ trace_probe_log_err(ctx->offset, BAD_BTF_TID);
+ return -EINVAL;
+ }
+
+ if (next)
+ ctx->offset += next - fieldname;
+ fieldname = next;
+ } while (!is_ptr && fieldname);
+
+ *pfieldname = fieldname;
+ *ptype = type;
+
+ return bitoffs;
+}
/*
* Parse the field of data structure. The @type must be a pointer type
* pointing the target data structure type.
@@ -577,15 +635,13 @@ static int parse_btf_field(char *fieldname, const struct btf_type *type,
struct traceprobe_parse_context *ctx)
{
struct fetch_insn *code = *pcode;
- const struct btf_member *field;
- u32 bitoffs, anon_offs;
- bool is_struct = ctx->struct_btf != NULL;
struct btf *btf = ctx_btf(ctx);
- char *next;
- int is_ptr;
+ bool is_first_field = true;
+ int bitoffs;
do {
- if (!is_struct) {
+ /* For the first field of typecast, @type will be the target structure type. */
+ if (!(is_first_field && ctx->struct_btf)) {
/* Outer loop for solving arrow operator ('->') */
if (BTF_INFO_KIND(type->info) != BTF_KIND_PTR) {
trace_probe_log_err(ctx->offset, NO_PTR_STRCT);
@@ -599,60 +655,25 @@ static int parse_btf_field(char *fieldname, const struct btf_type *type,
return -EINVAL;
}
}
- /* Only the first type can skip being a pointer */
- is_struct = false;
-
- bitoffs = 0;
- do {
- /* Inner loop for solving dot operator ('.') */
- next = NULL;
- is_ptr = split_next_field(fieldname, &next, ctx);
- if (is_ptr < 0)
- return is_ptr;
-
- anon_offs = 0;
- field = btf_find_struct_member(btf, type, fieldname,
- &anon_offs);
- if (IS_ERR(field)) {
- trace_probe_log_err(ctx->offset, BAD_BTF_TID);
- return PTR_ERR(field);
- }
- if (!field) {
- trace_probe_log_err(ctx->offset, NO_BTF_FIELD);
- return -ENOENT;
- }
- /* Add anonymous structure/union offset */
- bitoffs += anon_offs;
-
- /* Accumulate the bit-offsets of the dot-connected fields */
- if (btf_type_kflag(type)) {
- bitoffs += BTF_MEMBER_BIT_OFFSET(field->offset);
- ctx->last_bitsize = BTF_MEMBER_BITFIELD_SIZE(field->offset);
- } else {
- bitoffs += field->offset;
- ctx->last_bitsize = 0;
- }
-
- type = btf_type_skip_modifiers(btf, field->type, NULL);
- if (!type) {
- trace_probe_log_err(ctx->offset, BAD_BTF_TID);
- return -EINVAL;
- }
-
- ctx->offset += next - fieldname;
- fieldname = next;
- } while (!is_ptr && fieldname);
+ bitoffs = get_bitoffset_of_field(&fieldname, &type, ctx);
+ if (bitoffs < 0)
+ return bitoffs;
if (++code == end) {
trace_probe_log_err(ctx->offset, TOO_MANY_OPS);
return -EINVAL;
}
code->op = FETCH_OP_DEREF; /* TODO: user deref support */
code->offset = bitoffs / 8;
+ if (is_first_field && ctx->struct_btf) {
+ /* The first field can be typecasted with field option. */
+ code->offset -= ctx->prefix_byteoffs;
+ }
*pcode = code;
ctx->last_bitoffs = bitoffs % 8;
ctx->last_type = type;
+ is_first_field = false;
} while (fieldname);
return 0;
@@ -808,6 +829,46 @@ static int query_btf_struct(const char *sname, struct traceprobe_parse_context *
return 0;
}
+static int parse_btf_casttype(char *casttype, struct traceprobe_parse_context *ctx)
+{
+ char *field;
+ int ret;
+
+ /* Field option - evaluated later. */
+ field = strchr(casttype, ',');
+ if (field)
+ *field++ = '\0';
+
+ ret = query_btf_struct(casttype, ctx);
+ if (ret < 0) {
+ trace_probe_log_err(ctx->offset, NO_PTR_STRCT);
+ return -EINVAL;
+ }
+
+ if (field) {
+ struct btf_type *type = (struct btf_type *)ctx->last_struct;
+
+ ctx->offset += field - casttype;
+ ret = get_bitoffset_of_field(&field, &ctx->last_struct, ctx);
+ if (ret < 0)
+ return ret;
+ if (ret % 8) {
+ trace_probe_log_err(ctx->offset, TYPECAST_NOT_ALIGNED);
+ return -EINVAL;
+ }
+ if (field != NULL) {
+ /* this means @field skips an arrow operator ("->"). */
+ trace_probe_log_err(ctx->offset - 2, TYPECAST_BAD_ARROW);
+ return -EINVAL;
+ }
+ ctx->prefix_byteoffs = ret / 8;
+ /* Restore the original struct type (overwritten by get_bitoffset_of_field) */
+ ctx->last_struct = type;
+ }
+
+ return ret;
+}
+
/* Find the matching closing parenthesis for a given opening parenthesis. */
static char *find_matched_close_paren(char *s)
{
@@ -940,14 +1001,14 @@ static int handle_typecast(char *arg, struct fetch_insn **pcode,
tmp = close + 2; /* Skip ">" after inner variable name */
/* resolve the typecast struct name */
- ret = query_btf_struct(arg + 1, ctx);
- if (ret < 0) {
- trace_probe_log_err(orig_offset + 1, NO_PTR_STRCT);
- return -EINVAL;
- }
+ ctx->offset = orig_offset + 1; /* for the '(' */
+ ret = parse_btf_casttype(arg + 1, ctx);
+ if (ret < 0)
+ return ret;
ctx->offset = orig_offset + tmp - arg;
ret = parse_btf_field(tmp, ctx->last_struct, pcode, end, ctx);
+ ctx->prefix_byteoffs = 0;
return ret;
}
diff --git a/kernel/trace/trace_probe.h b/kernel/trace/trace_probe.h
index f4fbe3010978..6a0859e00bf4 100644
--- a/kernel/trace/trace_probe.h
+++ b/kernel/trace/trace_probe.h
@@ -451,6 +451,7 @@ struct traceprobe_parse_context {
unsigned int flags;
int offset;
int nested_level;
+ int prefix_byteoffs; /* The byte offset of the prefix field of typecast */
};
/* Each typecast consumes nested level. So the max number of typecast is 3. */
@@ -594,7 +595,9 @@ extern int traceprobe_define_arg_fields(struct trace_event_call *event_call,
C(TYPECAST_NOT_EVENT, "Typecasts are only for eprobe fields"), \
C(TYPECAST_REQ_FIELD, "Typecast requires a field access"), \
C(TOO_MANY_NESTED, "Too many nested typecasts/dereferences"), \
- C(TYPECAST_SYM_OFFSET, "@SYM+/-OFFSET with typecast needs parentheses")
+ C(TYPECAST_SYM_OFFSET, "@SYM+/-OFFSET with typecast needs parentheses"), \
+ C(TYPECAST_NOT_ALIGNED, "Typecast field option is not byte-aligned"), \
+ C(TYPECAST_BAD_ARROW, "Typecast field option does not support -> operator"),
#undef C
#define C(a, b) TP_ERR_##a
^ permalink raw reply related
* [PATCH v13 07/11] tracing/probes: Type casting always involves nested calls
From: Masami Hiramatsu (Google) @ 2026-06-29 6:14 UTC (permalink / raw)
To: Steven Rostedt, Mathieu Desnoyers
Cc: Jonathan Corbet, Shuah Khan, Masami Hiramatsu, linux-kernel,
linux-trace-kernel, linux-doc, linux-kselftest
In-Reply-To: <178271357142.1176915.7193483024740701480.stgit@devnote2>
From: Masami Hiramatsu (Google) <mhiramat@kernel.org>
This allows type casting to various fetchargs without parentheses
by recursively calling parse_probe_arg on the target when type
casting is used.
For example, this allows the following expressions:
- (STRUCT)%REG->FIELD
- (STRUCT)$stackN->FIELD
- (STRUCT)@SYM->FIELD
Note that @SYM+/-OFFSET with typecast needs parentheses like:
- (STRUCT)(@SYM-8)->FIELD
Signed-off-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
---
Changes in v8:
- Fix caret position in error case.
- Add a comment about @SYM+/-OFFSET without parentheses.
Changes in v7:
- Prohibit using @SYM+/-OFFSET without parentheses.
- Cleanup parse_btf_arg() since ctx->struct_btf is always NULL now.
Changes in v6:
- Newly added.
---
kernel/trace/trace_probe.c | 123 ++++++++++++++++++++++++++------------------
kernel/trace/trace_probe.h | 4 +
2 files changed, 75 insertions(+), 52 deletions(-)
diff --git a/kernel/trace/trace_probe.c b/kernel/trace/trace_probe.c
index 827ae04f6351..1b97b125e9cb 100644
--- a/kernel/trace/trace_probe.c
+++ b/kernel/trace/trace_probe.c
@@ -684,19 +684,6 @@ static int parse_btf_arg(char *varname,
return -EOPNOTSUPP;
}
- if (ctx->flags & TPARG_FL_TEVENT) {
- ret = parse_trace_event(varname, code, ctx);
- if (ret < 0) {
- trace_probe_log_err(ctx->offset, BAD_ATTACH_ARG);
- return ret;
- }
- /* TEVENT is only here via a typecast */
- if (WARN_ON_ONCE(ctx->struct_btf == NULL))
- return -EINVAL;
- type = ctx->last_struct;
- goto found_type;
- }
-
if (ctx->flags & TPARG_FL_RETURN && !strcmp(varname, "$retval")) {
code->op = FETCH_OP_RETVAL;
/* Check whether the function return type is not void, even with typecast. */
@@ -708,13 +695,6 @@ static int parse_btf_arg(char *varname,
tid = ctx->proto->type;
goto found;
}
- /*
- * Even if we can not find appropriate BTF info, we can still access
- * the field via typecast.
- */
- if (ctx->struct_btf)
- goto found;
-
if (field) {
trace_probe_log_err(ctx->offset + field - varname,
NO_BTF_ENTRY);
@@ -759,11 +739,7 @@ static int parse_btf_arg(char *varname,
return -ENOENT;
found:
- if (ctx->struct_btf)
- type = ctx->last_struct;
- else
- type = btf_type_skip_modifiers(ctx->btf, tid, NULL);
-found_type:
+ type = btf_type_skip_modifiers(ctx->btf, tid, NULL);
if (!type) {
trace_probe_log_err(ctx->offset, BAD_BTF_TID);
return -EINVAL;
@@ -860,7 +836,7 @@ static int handle_typecast(char *arg, struct fetch_insn **pcode,
struct traceprobe_parse_context *ctx)
{
int orig_offset = ctx->offset;
- bool nested = false;
+ char *close;
char *tmp;
int ret;
@@ -871,6 +847,17 @@ static int handle_typecast(char *arg, struct fetch_insn **pcode,
return -EOPNOTSUPP;
}
+ /*
+ * Always consider the token after typecast as a nested call
+ * For example: (STRUCT)VAR->FIELD and (STRUCT)(VAR)->FIELD are same.
+ * VAR is solved in the nested call.
+ */
+ ctx->nested_level++;
+ if (ctx->nested_level > TRACEPROBE_MAX_NESTED_LEVEL) {
+ trace_probe_log_err(ctx->offset, TOO_MANY_NESTED);
+ return -E2BIG;
+ }
+
tmp = strchr(arg, ')');
if (!tmp) {
trace_probe_log_err(ctx->offset + strlen(arg),
@@ -879,11 +866,10 @@ static int handle_typecast(char *arg, struct fetch_insn **pcode,
}
*tmp++ = '\0';
- /* Handle the nested structure like (STRUCT)(VAR->FIELD)->... */
+ ctx->offset += tmp - arg;
if (*tmp == '(') {
- char *close = find_matched_close_paren(tmp);
+ close = find_matched_close_paren(tmp);
- ctx->offset += tmp - arg;
if (!close) {
trace_probe_log_err(ctx->offset, DEREF_OPEN_BRACE);
return -EINVAL;
@@ -894,27 +880,66 @@ static int handle_typecast(char *arg, struct fetch_insn **pcode,
TYPECAST_REQ_FIELD);
return -EINVAL;
}
-
- ctx->nested_level++;
- if (ctx->nested_level > TRACEPROBE_MAX_NESTED_LEVEL) {
- trace_probe_log_err(ctx->offset, TOO_MANY_NESTED);
- return -E2BIG;
+ /* Skip '(' */
+ ctx->offset += 1;
+ tmp++;
+ } else if (*tmp == '+' || *tmp == '-') {
+ /* Dereference can have another field access inside it. */
+ char *open = strchr(tmp + 1, '(');
+
+ if (!open) {
+ trace_probe_log_err(ctx->offset,
+ DEREF_NEED_BRACE);
+ return -EINVAL;
+ }
+ close = find_matched_close_paren(open);
+ if (!close) {
+ trace_probe_log_err(ctx->offset + strlen(tmp),
+ DEREF_OPEN_BRACE);
+ return -EINVAL;
+ }
+ close++;
+ /* We expect a field access for typecast */
+ if (close[0] != '-' || close[1] != '>') {
+ trace_probe_log_err(ctx->offset + close - tmp,
+ TYPECAST_REQ_FIELD);
+ return -EINVAL;
+ }
+ } else {
+ if (tmp[0] == '@') {
+ /* @sym+offset is not allowed without parenthesized */
+ close = strpbrk(tmp, "+-");
+ if (close && isdigit(close[1])) {
+ trace_probe_log_err(ctx->offset,
+ TYPECAST_SYM_OFFSET);
+ return -EINVAL;
+ }
}
- *close = '\0';
+ /* Inner variable name */
+ close = strchr(tmp, '-');
+ if (!close || close[1] != '>') {
+ trace_probe_log_err(ctx->offset + strlen(tmp),
+ TYPECAST_REQ_FIELD);
+ return -EINVAL;
+ }
+ }
+ *close = '\0';
- ctx->offset += 1; /* for the '(' */
- /* We need to parse the nested one */
- ret = parse_probe_arg(tmp + 1, find_fetch_type(NULL, ctx->flags),
- pcode, end, ctx);
- if (ret < 0)
- return ret;
- ctx->nested_level--;
- clear_struct_btf(ctx);
+ /* We need to parse the nested one */
+ ret = parse_probe_arg(tmp, find_fetch_type(NULL, ctx->flags),
+ pcode, end, ctx);
+ if (ret < 0)
+ return ret;
+ ctx->nested_level--;
+ clear_struct_btf(ctx);
- tmp = close + 3;/* Skip "->" after closing parenthesis */
- nested = true;
- }
+ /* Let tmp point the field name. */
+ if (close[1] == '-')
+ tmp = close + 3; /* Skip "->" after closing parenthesis */
+ else
+ tmp = close + 2; /* Skip ">" after inner variable name */
+ /* resolve the typecast struct name */
ret = query_btf_struct(arg + 1, ctx);
if (ret < 0) {
trace_probe_log_err(orig_offset + 1, NO_PTR_STRCT);
@@ -922,11 +947,7 @@ static int handle_typecast(char *arg, struct fetch_insn **pcode,
}
ctx->offset = orig_offset + tmp - arg;
- /* If it is nested, tmp points to the field name. */
- if (nested)
- ret = parse_btf_field(tmp, ctx->last_struct, pcode, end, ctx);
- else
- ret = parse_btf_arg(tmp, pcode, end, ctx);
+ ret = parse_btf_field(tmp, ctx->last_struct, pcode, end, ctx);
return ret;
}
diff --git a/kernel/trace/trace_probe.h b/kernel/trace/trace_probe.h
index 7d71925244e8..f4fbe3010978 100644
--- a/kernel/trace/trace_probe.h
+++ b/kernel/trace/trace_probe.h
@@ -453,6 +453,7 @@ struct traceprobe_parse_context {
int nested_level;
};
+/* Each typecast consumes nested level. So the max number of typecast is 3. */
#define TRACEPROBE_MAX_NESTED_LEVEL 3
extern int traceprobe_parse_probe_arg(struct trace_probe *tp, int i,
@@ -592,7 +593,8 @@ extern int traceprobe_define_arg_fields(struct trace_event_call *event_call,
C(EVENT_TOO_BIG, "Event too big (too many fields?)"), \
C(TYPECAST_NOT_EVENT, "Typecasts are only for eprobe fields"), \
C(TYPECAST_REQ_FIELD, "Typecast requires a field access"), \
- C(TOO_MANY_NESTED, "Too many nested typecasts/dereferences"),
+ C(TOO_MANY_NESTED, "Too many nested typecasts/dereferences"), \
+ C(TYPECAST_SYM_OFFSET, "@SYM+/-OFFSET with typecast needs parentheses")
#undef C
#define C(a, b) TP_ERR_##a
^ permalink raw reply related
* [PATCH v13 06/11] tracing/probes: Support nested typecast
From: Masami Hiramatsu (Google) @ 2026-06-29 6:13 UTC (permalink / raw)
To: Steven Rostedt, Mathieu Desnoyers
Cc: Jonathan Corbet, Shuah Khan, Masami Hiramatsu, linux-kernel,
linux-trace-kernel, linux-doc, linux-kselftest
In-Reply-To: <178271357142.1176915.7193483024740701480.stgit@devnote2>
From: Masami Hiramatsu (Google) <mhiramat@kernel.org>
When we hit an open parenthesis right after typecast closing
parenthesis, it means we have nested typecast. This allows us to
typecast a generic data member in a structure to a pointer to
another structure.
For example, to cast a DATA_MEMBER of VAR structure to STRUCT pointer
and get MEMBER value.
(STRUCT)(VAR->DATA_MEMBER)->MEMBER
Also, we can nest typecast.
(STRUCT1)((STRUCT2)$ARG->FIELD2)->FIELD1
Currently the max nest level is limited to 3.
This also allows user to use typecasting for registers or stacks on
kprobe events. e.g.
(STRUCT)(%ax)->MEMBER
(STRUCT)($stack0)->MEMBER
Signed-off-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
---
Changes in v11:
- Fix to return -EINVAL if WARN_ON_ONCE() is hit.
Changes in v6:
- Add a WARN_ON_ONCE check for leaking nested_level (it must not happen.)
Changes in v4:
- Use orig_offset for reporting NO_PTR_STRCT error.
Changes in v2:
- Fix to skip "->" after closing parenthetsis.
---
Documentation/trace/eprobetrace.rst | 2 +
Documentation/trace/fprobetrace.rst | 2 +
Documentation/trace/kprobetrace.rst | 2 +
kernel/trace/trace.c | 1
kernel/trace/trace_probe.c | 83 ++++++++++++++++++++++++++++++++---
kernel/trace/trace_probe.h | 7 +++
6 files changed, 88 insertions(+), 9 deletions(-)
diff --git a/Documentation/trace/eprobetrace.rst b/Documentation/trace/eprobetrace.rst
index fe3602540569..cd0b4aa7f896 100644
--- a/Documentation/trace/eprobetrace.rst
+++ b/Documentation/trace/eprobetrace.rst
@@ -50,6 +50,8 @@ Synopsis of eprobe_events
a pointer to STRUCT and then derference the pointer defined by
->MEMBER. Note that when this is used, the FIELD name does not
need to be prefixed with a '$'.
+ (STRUCT)(FETCHARG)->MEMBER[->MEMBER] : typecast can nest, so the above can
+ also be used with another FETCHARG instead of FIELD.
Types
-----
diff --git a/Documentation/trace/fprobetrace.rst b/Documentation/trace/fprobetrace.rst
index 7435ded2d66d..6b8bb27bb62d 100644
--- a/Documentation/trace/fprobetrace.rst
+++ b/Documentation/trace/fprobetrace.rst
@@ -60,6 +60,8 @@ Synopsis of fprobe-events
(STRUCT)FIELD->MEMBER[->MEMBER] : If BTF is supported, typecast FIELD to
a pointer to STRUCT and then derference the pointer defined by
->MEMBER.
+ (STRUCT)(FETCHARG)->MEMBER[->MEMBER] : typecast can nest, so the above can
+ also be used with another FETCHARG instead of FIELD.
(\*1) This is available only when BTF is enabled.
(\*2) only for the probe on function entry (offs == 0). Note, this argument access
diff --git a/Documentation/trace/kprobetrace.rst b/Documentation/trace/kprobetrace.rst
index f73614997d52..c4382765d5b2 100644
--- a/Documentation/trace/kprobetrace.rst
+++ b/Documentation/trace/kprobetrace.rst
@@ -65,6 +65,8 @@ Synopsis of kprobe_events
a pointer to STRUCT and then derference the pointer defined by
->MEMBER. Note that this is available only when the probe is
on function entry.
+ (STRUCT)(FETCHARG)->MEMBER[->MEMBER] : typecast can nest, so the above can
+ also be used with another FETCHARG instead of FIELD.
(\*1) only for the probe on function entry (offs == 0). Note, this argument access
is best effort, because depending on the argument type, it may be passed on
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 280a3dccd13f..e56ee034c486 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -4323,6 +4323,7 @@ static const char readme_msg[] =
"\t $stack<index>, $stack, $retval, $comm, $arg<N>,\n"
#ifdef CONFIG_PROBE_EVENTS_BTF_ARGS
"\t [(structname)]<argname>[->field[->field|.field...]],\n"
+ "\t [(structname)](fetcharg)->field[->field|.field...],\n"
#endif
#else
"\t $stack<index>, $stack, $retval, $comm,\n"
diff --git a/kernel/trace/trace_probe.c b/kernel/trace/trace_probe.c
index e6cc9f3d6c8b..827ae04f6351 100644
--- a/kernel/trace/trace_probe.c
+++ b/kernel/trace/trace_probe.c
@@ -832,10 +832,35 @@ static int query_btf_struct(const char *sname, struct traceprobe_parse_context *
return 0;
}
+/* Find the matching closing parenthesis for a given opening parenthesis. */
+static char *find_matched_close_paren(char *s)
+{
+ char *p = s;
+ int count = 0;
+
+ while (*p) {
+ if (*p == '(')
+ count++;
+ else if (*p == ')') {
+ if (--count == 0)
+ return p;
+ }
+ p++;
+ }
+ return NULL;
+}
+
+static int
+parse_probe_arg(char *arg, const struct fetch_type *type,
+ struct fetch_insn **pcode, struct fetch_insn *end,
+ struct traceprobe_parse_context *ctx);
+
static int handle_typecast(char *arg, struct fetch_insn **pcode,
struct fetch_insn *end,
struct traceprobe_parse_context *ctx)
{
+ int orig_offset = ctx->offset;
+ bool nested = false;
char *tmp;
int ret;
@@ -852,19 +877,56 @@ static int handle_typecast(char *arg, struct fetch_insn **pcode,
DEREF_OPEN_BRACE);
return -EINVAL;
}
- *tmp = '\0';
- ret = query_btf_struct(arg + 1, ctx);
- *tmp = ')';
+ *tmp++ = '\0';
+ /* Handle the nested structure like (STRUCT)(VAR->FIELD)->... */
+ if (*tmp == '(') {
+ char *close = find_matched_close_paren(tmp);
+
+ ctx->offset += tmp - arg;
+ if (!close) {
+ trace_probe_log_err(ctx->offset, DEREF_OPEN_BRACE);
+ return -EINVAL;
+ }
+ /* We expect a field access for typecast */
+ if (close[1] != '-' || close[2] != '>') {
+ trace_probe_log_err(ctx->offset + close - tmp + 1,
+ TYPECAST_REQ_FIELD);
+ return -EINVAL;
+ }
+
+ ctx->nested_level++;
+ if (ctx->nested_level > TRACEPROBE_MAX_NESTED_LEVEL) {
+ trace_probe_log_err(ctx->offset, TOO_MANY_NESTED);
+ return -E2BIG;
+ }
+ *close = '\0';
+
+ ctx->offset += 1; /* for the '(' */
+ /* We need to parse the nested one */
+ ret = parse_probe_arg(tmp + 1, find_fetch_type(NULL, ctx->flags),
+ pcode, end, ctx);
+ if (ret < 0)
+ return ret;
+ ctx->nested_level--;
+ clear_struct_btf(ctx);
+
+ tmp = close + 3;/* Skip "->" after closing parenthesis */
+ nested = true;
+ }
+
+ ret = query_btf_struct(arg + 1, ctx);
if (ret < 0) {
- trace_probe_log_err(ctx->offset + 1, NO_PTR_STRCT);
+ trace_probe_log_err(orig_offset + 1, NO_PTR_STRCT);
return -EINVAL;
}
- tmp++;
-
- ctx->offset += tmp - arg;
- ret = parse_btf_arg(tmp, pcode, end, ctx);
+ ctx->offset = orig_offset + tmp - arg;
+ /* If it is nested, tmp points to the field name. */
+ if (nested)
+ ret = parse_btf_field(tmp, ctx->last_struct, pcode, end, ctx);
+ else
+ ret = parse_btf_arg(tmp, pcode, end, ctx);
return ret;
}
@@ -1638,6 +1700,11 @@ static int traceprobe_parse_probe_arg_body(const char *argv, ssize_t *size,
ctx);
if (ret < 0)
goto fail;
+ /* nested_level must be 0 here, otherwise there is a bug. */
+ if (WARN_ON_ONCE(ctx->nested_level)) {
+ ret = -EINVAL;
+ goto fail;
+ }
/* Update storing type if BTF is available */
if (IS_ENABLED(CONFIG_PROBE_EVENTS_BTF_ARGS) &&
diff --git a/kernel/trace/trace_probe.h b/kernel/trace/trace_probe.h
index aa72e2ffdd93..7d71925244e8 100644
--- a/kernel/trace/trace_probe.h
+++ b/kernel/trace/trace_probe.h
@@ -450,8 +450,11 @@ struct traceprobe_parse_context {
struct trace_probe *tp;
unsigned int flags;
int offset;
+ int nested_level;
};
+#define TRACEPROBE_MAX_NESTED_LEVEL 3
+
extern int traceprobe_parse_probe_arg(struct trace_probe *tp, int i,
const char *argv,
struct traceprobe_parse_context *ctx);
@@ -587,7 +590,9 @@ extern int traceprobe_define_arg_fields(struct trace_event_call *event_call,
C(TOO_MANY_ARGS, "Too many arguments are specified"), \
C(TOO_MANY_EARGS, "Too many entry arguments specified"), \
C(EVENT_TOO_BIG, "Event too big (too many fields?)"), \
- C(TYPECAST_NOT_EVENT, "Typecasts are only for eprobe fields"),
+ C(TYPECAST_NOT_EVENT, "Typecasts are only for eprobe fields"), \
+ C(TYPECAST_REQ_FIELD, "Typecast requires a field access"), \
+ C(TOO_MANY_NESTED, "Too many nested typecasts/dereferences"),
#undef C
#define C(a, b) TP_ERR_##a
^ permalink raw reply related
* [PATCH v13 05/11] tracing/probes: Support typecast for various probe events
From: Masami Hiramatsu (Google) @ 2026-06-29 6:13 UTC (permalink / raw)
To: Steven Rostedt, Mathieu Desnoyers
Cc: Jonathan Corbet, Shuah Khan, Masami Hiramatsu, linux-kernel,
linux-trace-kernel, linux-doc, linux-kselftest
In-Reply-To: <178271357142.1176915.7193483024740701480.stgit@devnote2>
From: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Support BTF typecast feature on other probe events, but only if it is
kernel function entry or return, and must use function parameter name
or $retval. This means you can do:
(STRUCT)PARAM->MEMBER
Note: you can not use other variables like $stackN, %reg etc. That
needs nesting support.
To support other probe events, we just need to use last_struct type
when we find a function parameter in parse_btf_arg().
This also updates <tracefs>/README file to show struct typecast.
Signed-off-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
---
Changes in v5:
- Add comments about $retval with typecast.
- Even if the type of retvalue is not known, if user specifies typecast,
use it for its type.
Changes in v3:
- Clarify the limitation.
Changes in v2:
- Fix to re-enable typecast on eprobe.
---
Documentation/trace/fprobetrace.rst | 3 +++
Documentation/trace/kprobetrace.rst | 4 ++++
kernel/trace/trace.c | 2 +-
kernel/trace/trace_probe.c | 23 +++++++++++++++++------
kernel/trace/trace_probe.h | 5 +++++
5 files changed, 30 insertions(+), 7 deletions(-)
diff --git a/Documentation/trace/fprobetrace.rst b/Documentation/trace/fprobetrace.rst
index b4c2ca3d02c1..7435ded2d66d 100644
--- a/Documentation/trace/fprobetrace.rst
+++ b/Documentation/trace/fprobetrace.rst
@@ -57,6 +57,9 @@ Synopsis of fprobe-events
(u8/u16/u32/u64/s8/s16/s32/s64), hexadecimal types
(x8/x16/x32/x64), "char", "string", "ustring", "symbol", "symstr"
and bitfield are supported.
+ (STRUCT)FIELD->MEMBER[->MEMBER] : If BTF is supported, typecast FIELD to
+ a pointer to STRUCT and then derference the pointer defined by
+ ->MEMBER.
(\*1) This is available only when BTF is enabled.
(\*2) only for the probe on function entry (offs == 0). Note, this argument access
diff --git a/Documentation/trace/kprobetrace.rst b/Documentation/trace/kprobetrace.rst
index 3b6791c17e9b..f73614997d52 100644
--- a/Documentation/trace/kprobetrace.rst
+++ b/Documentation/trace/kprobetrace.rst
@@ -61,6 +61,10 @@ Synopsis of kprobe_events
(x8/x16/x32/x64), VFS layer common type(%pd/%pD), "char",
"string", "ustring", "symbol", "symstr" and bitfield are
supported.
+ (STRUCT)FIELD->MEMBER[->MEMBER] : If BTF is supported, typecast FIELD to
+ a pointer to STRUCT and then derference the pointer defined by
+ ->MEMBER. Note that this is available only when the probe is
+ on function entry.
(\*1) only for the probe on function entry (offs == 0). Note, this argument access
is best effort, because depending on the argument type, it may be passed on
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 1146b83b711a..280a3dccd13f 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -4322,7 +4322,7 @@ static const char readme_msg[] =
#ifdef CONFIG_HAVE_FUNCTION_ARG_ACCESS_API
"\t $stack<index>, $stack, $retval, $comm, $arg<N>,\n"
#ifdef CONFIG_PROBE_EVENTS_BTF_ARGS
- "\t <argname>[->field[->field|.field...]],\n"
+ "\t [(structname)]<argname>[->field[->field|.field...]],\n"
#endif
#else
"\t $stack<index>, $stack, $retval, $comm,\n"
diff --git a/kernel/trace/trace_probe.c b/kernel/trace/trace_probe.c
index 0908019aea12..e6cc9f3d6c8b 100644
--- a/kernel/trace/trace_probe.c
+++ b/kernel/trace/trace_probe.c
@@ -699,7 +699,7 @@ static int parse_btf_arg(char *varname,
if (ctx->flags & TPARG_FL_RETURN && !strcmp(varname, "$retval")) {
code->op = FETCH_OP_RETVAL;
- /* Check whether the function return type is not void */
+ /* Check whether the function return type is not void, even with typecast. */
if (query_btf_context(ctx) == 0) {
if (ctx->proto->type == 0) {
trace_probe_log_err(ctx->offset, NO_RETVAL);
@@ -708,6 +708,13 @@ static int parse_btf_arg(char *varname,
tid = ctx->proto->type;
goto found;
}
+ /*
+ * Even if we can not find appropriate BTF info, we can still access
+ * the field via typecast.
+ */
+ if (ctx->struct_btf)
+ goto found;
+
if (field) {
trace_probe_log_err(ctx->offset + field - varname,
NO_BTF_ENTRY);
@@ -752,7 +759,10 @@ static int parse_btf_arg(char *varname,
return -ENOENT;
found:
- type = btf_type_skip_modifiers(ctx->btf, tid, NULL);
+ if (ctx->struct_btf)
+ type = ctx->last_struct;
+ else
+ type = btf_type_skip_modifiers(ctx->btf, tid, NULL);
found_type:
if (!type) {
trace_probe_log_err(ctx->offset, BAD_BTF_TID);
@@ -829,10 +839,11 @@ static int handle_typecast(char *arg, struct fetch_insn **pcode,
char *tmp;
int ret;
- /* Currently this only works for eprobes */
- if (!(ctx->flags & TPARG_FL_TEVENT)) {
- trace_probe_log_err(ctx->offset, TYPECAST_NOT_EVENT);
- return -EINVAL;
+ if (!(tparg_is_event_probe(ctx->flags) ||
+ tparg_is_function_entry(ctx->flags) ||
+ tparg_is_function_return(ctx->flags))) {
+ trace_probe_log_err(ctx->offset, NOSUP_BTFARG);
+ return -EOPNOTSUPP;
}
tmp = strchr(arg, ')');
diff --git a/kernel/trace/trace_probe.h b/kernel/trace/trace_probe.h
index e36cfe39e9a8..aa72e2ffdd93 100644
--- a/kernel/trace/trace_probe.h
+++ b/kernel/trace/trace_probe.h
@@ -429,6 +429,11 @@ static inline bool tparg_is_function_return(unsigned int flags)
return (flags & TPARG_FL_LOC_MASK) == (TPARG_FL_KERNEL | TPARG_FL_RETURN);
}
+static inline bool tparg_is_event_probe(unsigned int flags)
+{
+ return !!(flags & TPARG_FL_TEVENT);
+}
+
struct traceprobe_parse_context {
struct trace_event_call *event;
/* BTF related parameters */
^ permalink raw reply related
* [PATCH v13 04/11] perf/probe: Ignore comment lines in dynamic_events/kprobe_events file
From: Masami Hiramatsu (Google) @ 2026-06-29 6:13 UTC (permalink / raw)
To: Steven Rostedt, Mathieu Desnoyers
Cc: Jonathan Corbet, Shuah Khan, Masami Hiramatsu, linux-kernel,
linux-trace-kernel, linux-doc, linux-kselftest
In-Reply-To: <178271357142.1176915.7193483024740701480.stgit@devnote2>
From: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Since dynamic_events/kprobe_events files show the fetcharg debug
information as comment lines, its reader needs to ignore it.
Signed-off-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
---
tools/perf/util/probe-file.c | 2 ++
1 file changed, 2 insertions(+)
diff --git a/tools/perf/util/probe-file.c b/tools/perf/util/probe-file.c
index 4032572cbf55..4d12693a83b3 100644
--- a/tools/perf/util/probe-file.c
+++ b/tools/perf/util/probe-file.c
@@ -197,6 +197,8 @@ struct strlist *probe_file__get_rawlist(int fd)
idx = strlen(p) - 1;
if (p[idx] == '\n')
p[idx] = '\0';
+ if (buf[0] == '#')
+ continue;
ret = strlist__add(sl, buf);
if (ret < 0) {
pr_debug("strlist__add failed (%d)\n", ret);
^ permalink raw reply related
* [PATCH v13 03/11] tools/bootconfig: Ignore comment lines in dynamic_events/kprobe_events file
From: Masami Hiramatsu (Google) @ 2026-06-29 6:13 UTC (permalink / raw)
To: Steven Rostedt, Mathieu Desnoyers
Cc: Jonathan Corbet, Shuah Khan, Masami Hiramatsu, linux-kernel,
linux-trace-kernel, linux-doc, linux-kselftest
In-Reply-To: <178271357142.1176915.7193483024740701480.stgit@devnote2>
From: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Since dynamic_events/kprobe_events files show the fetcharg debug
information as comment lines, its reader needs to ignore it.
Signed-off-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
---
tools/bootconfig/scripts/ftrace2bconf.sh | 2 ++
1 file changed, 2 insertions(+)
diff --git a/tools/bootconfig/scripts/ftrace2bconf.sh b/tools/bootconfig/scripts/ftrace2bconf.sh
index 1603801cf126..8eed445c295e 100755
--- a/tools/bootconfig/scripts/ftrace2bconf.sh
+++ b/tools/bootconfig/scripts/ftrace2bconf.sh
@@ -57,6 +57,8 @@ EOF
kprobe_event_options() {
cat $TRACEFS/kprobe_events | while read p args; do
case $p in
+ \#*)
+ continue;;
r*)
cat 1>&2 << EOF
# WARN: A return probe found but it is not supported by bootconfig. Skip it.
^ permalink raw reply related
* [PATCH v13 02/11] tracing/probes: Support dumping fetcharg program for debugging dynamic events
From: Masami Hiramatsu (Google) @ 2026-06-29 6:13 UTC (permalink / raw)
To: Steven Rostedt, Mathieu Desnoyers
Cc: Jonathan Corbet, Shuah Khan, Masami Hiramatsu, linux-kernel,
linux-trace-kernel, linux-doc, linux-kselftest
In-Reply-To: <178271357142.1176915.7193483024740701480.stgit@devnote2>
From: Masami Hiramatsu (Google) <mhiramat@kernel.org>
For debugging probe events, it is helpful to verify the compiled
fetch instructions for each probe argument. This introduces a new
kernel config CONFIG_PROBE_EVENTS_DUMP_FETCHARG to decode the
instruction sequence of each argument and display it under a
commented line starting with '#' immediately following the dynamic
event definition (such as in dynamic_events, kprobe_events,
uprobe_events, etc.).
For example:
/sys/kernel/tracing # cat dynamic_events
p:kprobes/p_vfs_read_0 vfs_read arg1=+0(file):ustring arg2=%ax:x16
# arg1: ARG(0) -> ST_USTRING(offset=0,size=4) -> END
# arg2: REG(80) -> ST_RAW(size=2) -> END
Assisted-by: Antigravity:gemini-3.5-flash
Signed-off-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
---
Changes in v8:
- State this feature is only for debugging probe events.
- Fix dependency list after description in Kconfig.
Changes in v7:
- Show trace event field name for FETCH_OP_TP_ARG.
- Show immediate string value for FETCH_OP_IMMSTR.
- Fix style issues warned by checkpatch.pl.
Changes in v6:
- Newly added.
---
kernel/trace/Kconfig | 12 +++++
kernel/trace/trace_eprobe.c | 2 +
kernel/trace/trace_fprobe.c | 2 +
kernel/trace/trace_kprobe.c | 2 +
kernel/trace/trace_probe.c | 96 +++++++++++++++++++++++++++++++++++++++++++
kernel/trace/trace_probe.h | 79 +++++++++++++++++++++--------------
kernel/trace/trace_uprobe.c | 3 +
7 files changed, 164 insertions(+), 32 deletions(-)
diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig
index 084f34dc6c9f..0ab5916575a9 100644
--- a/kernel/trace/Kconfig
+++ b/kernel/trace/Kconfig
@@ -779,6 +779,18 @@ config PROBE_EVENTS_BTF_ARGS
kernel function entry or a tracepoint.
This is available only if BTF (BPF Type Format) support is enabled.
+config PROBE_EVENTS_DUMP_FETCHARG
+ bool "Dump of dynamic probe event fetch-arguments"
+ depends on PROBE_EVENTS
+ default n
+ help
+ This shows the dump of fetch-arguments of dynamic probe events
+ alongside their event definitions in the dynamic_events file
+ as comment lines. This is useful to debug the probe events.
+ Since this exposes the raw values in the dynamic_events file,
+ it might be a security risk. Only enable it if you need to debug
+ probe events themselves.
+
config KPROBE_EVENTS
depends on KPROBES
depends on HAVE_REGS_AND_STACK_ACCESS_API
diff --git a/kernel/trace/trace_eprobe.c b/kernel/trace/trace_eprobe.c
index 50518b071414..462c31145733 100644
--- a/kernel/trace/trace_eprobe.c
+++ b/kernel/trace/trace_eprobe.c
@@ -87,6 +87,8 @@ static int eprobe_dyn_event_show(struct seq_file *m, struct dyn_event *ev)
seq_printf(m, " %s=%s", ep->tp.args[i].name, ep->tp.args[i].comm);
seq_putc(m, '\n');
+ trace_probe_dump_args(m, &ep->tp);
+
return 0;
}
diff --git a/kernel/trace/trace_fprobe.c b/kernel/trace/trace_fprobe.c
index 4d1abbf66229..536781cd4c47 100644
--- a/kernel/trace/trace_fprobe.c
+++ b/kernel/trace/trace_fprobe.c
@@ -1449,6 +1449,8 @@ static int trace_fprobe_show(struct seq_file *m, struct dyn_event *ev)
seq_printf(m, " %s=%s", tf->tp.args[i].name, tf->tp.args[i].comm);
seq_putc(m, '\n');
+ trace_probe_dump_args(m, &tf->tp);
+
return 0;
}
diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
index a8420e6abb56..cfa807d8e760 100644
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -1320,6 +1320,8 @@ static int trace_kprobe_show(struct seq_file *m, struct dyn_event *ev)
seq_printf(m, " %s=%s", tk->tp.args[i].name, tk->tp.args[i].comm);
seq_putc(m, '\n');
+ trace_probe_dump_args(m, &tk->tp);
+
return 0;
}
diff --git a/kernel/trace/trace_probe.c b/kernel/trace/trace_probe.c
index 2ce7d62471cb..0908019aea12 100644
--- a/kernel/trace/trace_probe.c
+++ b/kernel/trace/trace_probe.c
@@ -2403,3 +2403,99 @@ int trace_probe_print_args(struct trace_seq *s, struct probe_arg *args, int nr_a
}
return 0;
}
+
+#ifdef CONFIG_PROBE_EVENTS_DUMP_FETCHARG
+
+struct fetch_op_decode {
+ const char *name;
+ void (*decode)(struct seq_file *m, struct fetch_insn *insn);
+};
+
+static const struct fetch_op_decode fetch_op_decode[];
+
+static void fetcharg_decode_none(struct seq_file *m, struct fetch_insn *insn)
+{
+ seq_puts(m, fetch_op_decode[insn->op].name);
+}
+
+static void fetcharg_decode_param(struct seq_file *m, struct fetch_insn *insn)
+{
+ seq_printf(m, "%s(%u)", fetch_op_decode[insn->op].name, insn->param);
+}
+
+static void fetcharg_decode_imm(struct seq_file *m, struct fetch_insn *insn)
+{
+ seq_printf(m, "%s(0x%lx)", fetch_op_decode[insn->op].name, insn->immediate);
+}
+
+static void fetcharg_decode_string(struct seq_file *m, struct fetch_insn *insn)
+{
+ seq_printf(m, "%s(%s)", fetch_op_decode[insn->op].name, (char *)insn->data);
+}
+
+static void fetcharg_decode_symbol(struct seq_file *m, struct fetch_insn *insn)
+{
+ seq_printf(m, "%s(%s)", fetch_op_decode[insn->op].name, (char *)insn->data);
+}
+
+static void fetcharg_decode_offset(struct seq_file *m, struct fetch_insn *insn)
+{
+ seq_printf(m, "%s(offset=%d)", fetch_op_decode[insn->op].name, insn->offset);
+}
+
+static void fetcharg_decode_store(struct seq_file *m, struct fetch_insn *insn)
+{
+ if (insn->op == FETCH_OP_ST_RAW)
+ seq_printf(m, "%s(size=%u)", fetch_op_decode[insn->op].name, insn->size);
+ else
+ seq_printf(m, "%s(offset=%d,size=%u)", fetch_op_decode[insn->op].name,
+ insn->offset, insn->size);
+}
+
+static void fetcharg_decode_bf(struct seq_file *m, struct fetch_insn *insn)
+{
+ seq_printf(m, "%s(basesize=%u,lshift=%u,rshift=%u)",
+ fetch_op_decode[insn->op].name, insn->basesize, insn->lshift, insn->rshift);
+}
+
+static void fetcharg_decode_tp_arg(struct seq_file *m, struct fetch_insn *insn)
+{
+ struct ftrace_event_field *field = insn->data;
+
+ seq_printf(m, "%s(%s)", fetch_op_decode[insn->op].name, field->name);
+}
+
+#define FETCH_OP(opname, decode_fn) \
+ [FETCH_OP_##opname] = { .name = #opname, .decode = fetcharg_decode_##decode_fn }
+
+static const struct fetch_op_decode fetch_op_decode[] = FETCH_OP_LIST;
+#undef FETCH_OP
+
+static void trace_probe_dump_arg(struct seq_file *m, struct probe_arg *parg)
+{
+ int i;
+
+ seq_printf(m, "# %s: ", parg->name);
+ for (i = 0; i < FETCH_INSN_MAX; i++) {
+ struct fetch_insn *insn = parg->code + i;
+
+ if (insn->op >= ARRAY_SIZE(fetch_op_decode) || !fetch_op_decode[insn->op].decode)
+ seq_printf(m, "unknown(%d)", insn->op);
+ else
+ fetch_op_decode[insn->op].decode(m, insn);
+
+ if (insn->op == FETCH_OP_END)
+ break;
+ seq_puts(m, " -> ");
+ }
+ seq_putc(m, '\n');
+}
+
+void trace_probe_dump_args(struct seq_file *m, struct trace_probe *tp)
+{
+ int i;
+
+ for (i = 0; i < tp->nr_args; i++)
+ trace_probe_dump_arg(m, &tp->args[i]);
+}
+#endif /* CONFIG_PROBE_EVENTS_DUMP_FETCHARG */
diff --git a/kernel/trace/trace_probe.h b/kernel/trace/trace_probe.h
index 2e0d8384ee5c..e36cfe39e9a8 100644
--- a/kernel/trace/trace_probe.h
+++ b/kernel/trace/trace_probe.h
@@ -83,38 +83,46 @@ static nokprobe_inline u32 update_data_loc(u32 loc, int consumed)
/* Printing function type */
typedef int (*print_type_func_t)(struct trace_seq *, void *, void *);
-enum fetch_op {
- FETCH_OP_NOP = 0,
- // Stage 1 (load) ops
- FETCH_OP_REG, /* Register : .param = offset */
- FETCH_OP_STACK, /* Stack : .param = index */
- FETCH_OP_STACKP, /* Stack pointer */
- FETCH_OP_RETVAL, /* Return value */
- FETCH_OP_IMM, /* Immediate : .immediate */
- FETCH_OP_COMM, /* Current comm */
- FETCH_OP_ARG, /* Function argument : .param */
- FETCH_OP_FOFFS, /* File offset: .immediate */
- FETCH_OP_IMMSTR, /* Allocated string: .data */
- FETCH_OP_EDATA, /* Entry data: .offset */
- // Stage 2 (dereference) op
- FETCH_OP_DEREF, /* Dereference: .offset */
- FETCH_OP_UDEREF, /* User-space Dereference: .offset */
- // Stage 3 (store) ops
- FETCH_OP_ST_RAW, /* Raw: .size */
- FETCH_OP_ST_MEM, /* Mem: .offset, .size */
- FETCH_OP_ST_UMEM, /* Mem: .offset, .size */
- FETCH_OP_ST_STRING, /* String: .offset, .size */
- FETCH_OP_ST_USTRING, /* User String: .offset, .size */
- FETCH_OP_ST_SYMSTR, /* Kernel Symbol String: .offset, .size */
- FETCH_OP_ST_EDATA, /* Store Entry Data: .offset */
- // Stage 4 (modify) op
- FETCH_OP_MOD_BF, /* Bitfield: .basesize, .lshift, .rshift */
- // Stage 5 (loop) op
- FETCH_OP_LP_ARRAY, /* Array: .param = loop count */
- FETCH_OP_TP_ARG, /* Trace Point argument */
- FETCH_OP_END,
- FETCH_NOP_SYMBOL, /* Unresolved Symbol holder */
-};
+#define FETCH_OP_LIST { \
+ /* Stage 1 (load) ops */ \
+ FETCH_OP(NOP, none), /* NOP */ \
+ FETCH_OP(REG, param), /* Register: .param = offset */ \
+ FETCH_OP(STACK, param), /* Stack: .param = index */ \
+ FETCH_OP(STACKP, none), /* Stack pointer */ \
+ FETCH_OP(RETVAL, none), /* Return value */ \
+ FETCH_OP(IMM, imm), /* Immediate: .immediate */ \
+ FETCH_OP(COMM, none), /* Current comm */ \
+ FETCH_OP(ARG, param), /* Argument: .param = index */ \
+ FETCH_OP(FOFFS, imm), /* File offset: .immediate */ \
+ FETCH_OP(IMMSTR, string), /* Allocated string: .data */ \
+ FETCH_OP(EDATA, offset), /* Entry data: .offset */ \
+ FETCH_OP(TP_ARG, tp_arg), /* Tracepoint argument: .data */\
+ /* Stage 2 (dereference) ops */ \
+ FETCH_OP(DEREF, offset), /* Dereference: .offset */ \
+ FETCH_OP(UDEREF, offset), /* User-space dereference: .offset */\
+ /* Stage 3 (store) ops */ \
+ FETCH_OP(ST_RAW, store), /* Raw value: .size */ \
+ FETCH_OP(ST_MEM, store), /* Memory: .offset, .size */ \
+ FETCH_OP(ST_UMEM, store), /* User memory: .offset, .size */\
+ FETCH_OP(ST_STRING, store), /* String: .offset, .size */ \
+ FETCH_OP(ST_USTRING, store), /* User string: .offset, .size */\
+ FETCH_OP(ST_SYMSTR, store), /* Symbol name: .offset, .size */\
+ FETCH_OP(ST_EDATA, offset), /* Entry data: .offset */ \
+ /* Stage 4 (modify) op */ \
+ FETCH_OP(MOD_BF, bf), /* Bitfield: .basesize, .lshift, .rshift*/\
+ /* Stage 5 (loop) op */ \
+ FETCH_OP(LP_ARRAY, param), /* Loop array: .param = count */\
+ /* End */ \
+ FETCH_OP(END, none), \
+ /* Unresolved Symbol holder */ \
+ FETCH_OP(NOP_SYMBOL, symbol), /* Non loaded symbol: .data = symbol name */\
+}
+
+#define FETCH_OP(opname, decode_fn) FETCH_OP_##opname
+enum fetch_op FETCH_OP_LIST;
+#undef FETCH_OP
+
+#define FETCH_NOP_SYMBOL FETCH_OP_NOP_SYMBOL
struct fetch_insn {
enum fetch_op op;
@@ -370,6 +378,13 @@ bool trace_probe_match_command_args(struct trace_probe *tp,
int trace_probe_create(const char *raw_command, int (*createfn)(int, const char **));
int trace_probe_print_args(struct trace_seq *s, struct probe_arg *args, int nr_args,
u8 *data, void *field);
+#ifdef CONFIG_PROBE_EVENTS_DUMP_FETCHARG
+void trace_probe_dump_args(struct seq_file *m, struct trace_probe *tp);
+#else
+static inline void trace_probe_dump_args(struct seq_file *m, struct trace_probe *tp)
+{
+}
+#endif
#ifdef CONFIG_HAVE_FUNCTION_ARG_ACCESS_API
int traceprobe_get_entry_data_size(struct trace_probe *tp);
diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c
index c274346853d1..b2e264a4b96c 100644
--- a/kernel/trace/trace_uprobe.c
+++ b/kernel/trace/trace_uprobe.c
@@ -765,6 +765,9 @@ static int trace_uprobe_show(struct seq_file *m, struct dyn_event *ev)
seq_printf(m, " %s=%s", tu->tp.args[i].name, tu->tp.args[i].comm);
seq_putc(m, '\n');
+
+ trace_probe_dump_args(m, &tu->tp);
+
return 0;
}
^ permalink raw reply related
* [PATCH v13 01/11] tracing/probes: Allow eprobe to use variable without $ prefix
From: Masami Hiramatsu (Google) @ 2026-06-29 6:13 UTC (permalink / raw)
To: Steven Rostedt, Mathieu Desnoyers
Cc: Jonathan Corbet, Shuah Khan, Masami Hiramatsu, linux-kernel,
linux-trace-kernel, linux-doc, linux-kselftest
In-Reply-To: <178271357142.1176915.7193483024740701480.stgit@devnote2>
From: Masami Hiramatsu (Google) <mhiramat@kernel.org>
The commit 69efd863a785 ("tracing/eprobes: Allow use of BTF names
to dereference pointers") allows eprobe to use event field without
"$" prefix when it is used with typecast, it is natual to allow it
without typecast.
Signed-off-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
---
Changes in v8:
- Newly added.
---
kernel/trace/trace_probe.c | 12 +++++++++++-
kernel/trace/trace_probe.h | 1 +
.../test.d/dynevent/eprobes_syntax_errors.tc | 3 +--
3 files changed, 13 insertions(+), 3 deletions(-)
diff --git a/kernel/trace/trace_probe.c b/kernel/trace/trace_probe.c
index 0da7c0b53ba7..2ce7d62471cb 100644
--- a/kernel/trace/trace_probe.c
+++ b/kernel/trace/trace_probe.c
@@ -1341,7 +1341,17 @@ parse_probe_arg(char *arg, const struct fetch_type *type,
ret = handle_typecast(arg, pcode, end, ctx);
break;
default:
- if (isalpha(arg[0]) || arg[0] == '_') { /* BTF variable */
+ if (isalpha(arg[0]) || arg[0] == '_') {
+ /* BTF variable or event field*/
+ if (ctx->flags & TPARG_FL_TEVENT) {
+ ret = parse_trace_event(arg, *pcode, ctx);
+ if (ret < 0) {
+ trace_probe_log_err(ctx->offset,
+ NO_EVENT_FIELD);
+ return -EINVAL;
+ }
+ break;
+ }
if (!tparg_is_function_entry(ctx->flags) &&
!tparg_is_function_return(ctx->flags)) {
trace_probe_log_err(ctx->offset, NOSUP_BTFARG);
diff --git a/kernel/trace/trace_probe.h b/kernel/trace/trace_probe.h
index 40b53b5b58a9..2e0d8384ee5c 100644
--- a/kernel/trace/trace_probe.h
+++ b/kernel/trace/trace_probe.h
@@ -559,6 +559,7 @@ extern int traceprobe_define_arg_fields(struct trace_event_call *event_call,
C(NO_PTR_STRCT, "This is not a pointer to union/structure."), \
C(NOSUP_DAT_ARG, "Non pointer structure/union argument is not supported."),\
C(BAD_HYPHEN, "Failed to parse single hyphen. Forgot '>'?"), \
+ C(NO_EVENT_FIELD, "This event field is not found."), \
C(NO_BTF_FIELD, "This field is not found."), \
C(BAD_BTF_TID, "Failed to get BTF type info."),\
C(BAD_TYPE4STR, "This type does not fit for string."),\
diff --git a/tools/testing/selftests/ftrace/test.d/dynevent/eprobes_syntax_errors.tc b/tools/testing/selftests/ftrace/test.d/dynevent/eprobes_syntax_errors.tc
index 2a680c086047..0e65e787e426 100644
--- a/tools/testing/selftests/ftrace/test.d/dynevent/eprobes_syntax_errors.tc
+++ b/tools/testing/selftests/ftrace/test.d/dynevent/eprobes_syntax_errors.tc
@@ -10,7 +10,7 @@ check_error() { # command-with-error-pos-by-^
check_error 'e ^a.' # NO_EVENT_INFO
check_error 'e ^.b' # NO_EVENT_INFO
check_error 'e ^a.b' # BAD_ATTACH_EVENT
-check_error 'e syscalls/sys_enter_openat ^foo' # BAD_ATTACH_ARG
+check_error 'e syscalls/sys_enter_openat ^foo' # NO_EVENT_FIELD
check_error 'e:^/bar syscalls/sys_enter_openat' # NO_GROUP_NAME
check_error 'e:^12345678901234567890123456789012345678901234567890123456789012345/bar syscalls/sys_enter_openat' # GROUP_TOO_LONG
@@ -19,7 +19,6 @@ check_error 'e:^ syscalls/sys_enter_openat' # NO_EVENT_NAME
check_error 'e:foo/^12345678901234567890123456789012345678901234567890123456789012345 syscalls/sys_enter_openat' # EVENT_TOO_LONG
check_error 'e:foo/^bar.1 syscalls/sys_enter_openat' # BAD_EVENT_NAME
-check_error 'e:foo/bar syscalls/sys_enter_openat arg=^dfd' # BAD_FETCH_ARG
check_error 'e:foo/bar syscalls/sys_enter_openat arg=^$foo' # BAD_ATTACH_ARG
if grep -q '<attached-group>\.<attached-event>.*\[if <filter>\]' README; then
^ permalink raw reply related
* [PATCH v13 00/11] tracing/probes: Add more typecast features
From: Masami Hiramatsu (Google) @ 2026-06-29 6:12 UTC (permalink / raw)
To: Steven Rostedt, Mathieu Desnoyers
Cc: Jonathan Corbet, Shuah Khan, Masami Hiramatsu, linux-kernel,
linux-trace-kernel, linux-doc, linux-kselftest
Hi,
Here is the 13th version of series to introduce more typecast features
to probe events. The previous version is here:
https://lore.kernel.org/all/178269068329.1161310.17763177188897860801.stgit@devnote2/
This version fixes a missed comma issue [8/11][10/11] pointed
by Sashiko.
This series extends BTF typecast feature and add more options:
1. Expanding BTF typecast to kprobe and fprobe.
(currently only function entry/exit)
2. Introduce container_of like typecast. This adds a "assigned
member" option to the typecast.
(STRUCT,MEMBER)VAR->ANOTHER_MEMBER
This casts VAR to STRUCT type but the VAR is as the address
of STRUCT.MEMBER. In C, it is:
container_of(VAR, STRUCT, MEMBER)->ANOTHER_MEMBER
3. Support nested typecast, e.g.
(STRUCT)((STRUCT2)VAR->MEMBER2)->MEMBER
the nest level must be smaller than 3.
4. Add $current variable to point "current" task_struct.
This is useful with typecast, e.g.
(task_struct)$current->pid
5. per-cpu dereference support.
Intrdouce this_cpu_read(VAR) and this_cpu_ptr(VAR) to
access per-cpu data on the current CPU (accessing other CPU
data is not stable, because it can be changed.)
You can access the member of per-cpu data structure using
typecast like:
(STRUCT)this_cpu_ptr(VAR)->MEMBER
6. Support event fields without $ prefix on eprobes.
Now eprobe events can access its event fields.
And added fetcharg dump feature (for debug) and updated test scripts
to test part of them.
Thanks,
---
base-commit: c69b5f959286395e94c237ce6d7d4970bad7f6e3
Masami Hiramatsu (Google) (11):
tracing/probes: Allow eprobe to use variable without $ prefix
tracing/probes: Support dumping fetcharg program for debugging dynamic events
tools/bootconfig: Ignore comment lines in dynamic_events/kprobe_events file
perf/probe: Ignore comment lines in dynamic_events/kprobe_events file
tracing/probes: Support typecast for various probe events
tracing/probes: Support nested typecast
tracing/probes: Type casting always involves nested calls
tracing/probes: Support field specifier option for typecast
tracing/probes: Add $current variable support
tracing/probes: Add this_cpu_read() and this_cpu_ptr() dereference method to fetcharg
tracing/probes: Add a new testcase for BTF typecasts
Documentation/trace/eprobetrace.rst | 7
Documentation/trace/fprobetrace.rst | 10
Documentation/trace/kprobetrace.rst | 11
kernel/trace/Kconfig | 12
kernel/trace/trace.c | 8
kernel/trace/trace_eprobe.c | 2
kernel/trace/trace_fprobe.c | 2
kernel/trace/trace_kprobe.c | 2
kernel/trace/trace_probe.c | 585 ++++++++++++++++----
kernel/trace/trace_probe.h | 100 ++-
kernel/trace/trace_probe_tmpl.h | 25 +
kernel/trace/trace_uprobe.c | 3
samples/trace_events/trace-events-sample.c | 40 +
samples/trace_events/trace-events-sample.h | 34 +
tools/bootconfig/scripts/ftrace2bconf.sh | 2
tools/perf/util/probe-file.c | 2
.../ftrace/test.d/dynevent/btf_probe_event.tc | 51 ++
.../test.d/dynevent/btf_typecast_accepted.tc | 103 ++++
.../test.d/dynevent/eprobes_syntax_errors.tc | 12
.../ftrace/test.d/dynevent/fprobe_syntax_errors.tc | 12
.../ftrace/test.d/kprobe/kprobe_syntax_errors.tc | 12
.../ftrace/test.d/kprobe/uprobe_syntax_errors.tc | 5
22 files changed, 886 insertions(+), 154 deletions(-)
create mode 100644 tools/testing/selftests/ftrace/test.d/dynevent/btf_probe_event.tc
create mode 100644 tools/testing/selftests/ftrace/test.d/dynevent/btf_typecast_accepted.tc
--
Masami Hiramatsu (Google) <mhiramat@kernel.org>
^ permalink raw reply
* [PATCH v12 11/11] tracing/probes: Add a new testcase for BTF typecasts
From: Masami Hiramatsu (Google) @ 2026-06-28 23:53 UTC (permalink / raw)
To: Steven Rostedt, Mathieu Desnoyers
Cc: Jonathan Corbet, Shuah Khan, Masami Hiramatsu, linux-kernel,
linux-trace-kernel, linux-doc, linux-kselftest
In-Reply-To: <178269068329.1161310.17763177188897860801.stgit@devnote2>
From: Masami Hiramatsu (Google) <mhiramat@kernel.org>
With the introduction of container_of-style BTF typecasting and
per-CPU variable access support in trace probes, we need a way to
verify their functionality and prevent regressions.
Add a new ftrace kselftest and update the trace event sample module
to test and validate these features.
Specifically, update the trace-events-sample module to set up a
periodic timer whose callback accesses a per-CPU counter. Introduce
a new sample trace event, foo_timer_fn, to trace this callback
and log the current counter value.
Then, add a new test case, btf_probe_event.tc, which defines a
dynamic probe on the timer callback. The probe uses BTF typecasting
to recover the parent structure from the timer argument and
this_cpu_read() to fetch the per-CPU counter. The test verifies
the integrity of the implementation by ensuring the values
recorded by the dynamic probe match those from the static tracepoint.
Assisted-by: Antigravity:gemini-3.5-flash
Signed-off-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
---
Changes in v12:
- Fix current support check in eprobe testcase.
- Fix to return UNRESOLVED error if sample module is not found.
- Always check this_cpu_* in btf_typecast_accepted.tc.
Changes in v11:
- nit: fix the error code in comment.
Changes in v10:
- Add a check for $current and this_cpu_* for eprobe
Changes in v9:
- Add a testcase for checking new syntax.
Changes in v8:
- Add more test cases.
Changes in v6:
- Update testcase according to changes.
Changes in v5:
- Add more syntax test cases.
Changes in v4:
- Fix uprobe $current test.
Changes in v3:
- Add syntax test case.
- Update testcase to use this_cpu_read()
Changes in v2:
- Use timer_shutdown_sync() instead of timer_delete_sync() for teardown.
---
samples/trace_events/trace-events-sample.c | 40 +++++++-
samples/trace_events/trace-events-sample.h | 34 ++++++-
.../ftrace/test.d/dynevent/btf_probe_event.tc | 51 ++++++++++
.../test.d/dynevent/btf_typecast_accepted.tc | 103 ++++++++++++++++++++
.../test.d/dynevent/eprobes_syntax_errors.tc | 9 ++
.../ftrace/test.d/dynevent/fprobe_syntax_errors.tc | 12 ++
.../ftrace/test.d/kprobe/kprobe_syntax_errors.tc | 12 ++
.../ftrace/test.d/kprobe/uprobe_syntax_errors.tc | 5 +
8 files changed, 261 insertions(+), 5 deletions(-)
create mode 100644 tools/testing/selftests/ftrace/test.d/dynevent/btf_probe_event.tc
create mode 100644 tools/testing/selftests/ftrace/test.d/dynevent/btf_typecast_accepted.tc
diff --git a/samples/trace_events/trace-events-sample.c b/samples/trace_events/trace-events-sample.c
index 0b7a6efdb247..ca5d98c360cb 100644
--- a/samples/trace_events/trace-events-sample.c
+++ b/samples/trace_events/trace-events-sample.c
@@ -94,6 +94,20 @@ static int simple_thread_fn(void *arg)
static DEFINE_MUTEX(thread_mutex);
static int simple_thread_cnt;
+static struct foo_timer_data *foo_timer_data;
+
+static void sample_timer_cb(struct timer_list *t)
+{
+ struct foo_timer_data *data = container_of(t, struct foo_timer_data, timer);
+
+ get_cpu();
+ trace_foo_timer_fn(data);
+ (*this_cpu_ptr(data->counter))++;
+ put_cpu();
+
+ mod_timer(t, jiffies + HZ);
+}
+
int foo_bar_reg(void)
{
mutex_lock(&thread_mutex);
@@ -132,9 +146,27 @@ void foo_bar_unreg(void)
static int __init trace_event_init(void)
{
+ foo_timer_data = kzalloc_obj(*foo_timer_data, GFP_KERNEL);
+ if (!foo_timer_data)
+ return -ENOMEM;
+
+ foo_timer_data->name = "sample_timer_counter";
+ foo_timer_data->counter = alloc_percpu(int);
+ if (!foo_timer_data->counter) {
+ kfree(foo_timer_data);
+ return -ENOMEM;
+ }
+
+ timer_setup(&foo_timer_data->timer, sample_timer_cb, 0);
+ mod_timer(&foo_timer_data->timer, jiffies + HZ);
+
simple_tsk = kthread_run(simple_thread, NULL, "event-sample");
- if (IS_ERR(simple_tsk))
- return -1;
+ if (IS_ERR(simple_tsk)) {
+ timer_shutdown_sync(&foo_timer_data->timer);
+ free_percpu(foo_timer_data->counter);
+ kfree(foo_timer_data);
+ return PTR_ERR(simple_tsk);
+ }
return 0;
}
@@ -147,6 +179,10 @@ static void __exit trace_event_exit(void)
kthread_stop(simple_tsk_fn);
simple_tsk_fn = NULL;
mutex_unlock(&thread_mutex);
+
+ timer_shutdown_sync(&foo_timer_data->timer);
+ free_percpu(foo_timer_data->counter);
+ kfree(foo_timer_data);
}
module_init(trace_event_init);
diff --git a/samples/trace_events/trace-events-sample.h b/samples/trace_events/trace-events-sample.h
index 1a05fc153353..816848a456a2 100644
--- a/samples/trace_events/trace-events-sample.h
+++ b/samples/trace_events/trace-events-sample.h
@@ -247,12 +247,14 @@
*/
/*
- * It is OK to have helper functions in the file, but they need to be protected
- * from being defined more than once. Remember, this file gets included more
- * than once.
+ * It is OK to have helper functions and data structures in the file, but they
+ * need to be protected from being defined more than once. Remember, this file
+ * gets included more than once.
*/
#ifndef __TRACE_EVENT_SAMPLE_HELPER_FUNCTIONS
#define __TRACE_EVENT_SAMPLE_HELPER_FUNCTIONS
+#include <linux/timer.h>
+
static inline int __length_of(const int *list)
{
int i;
@@ -270,6 +272,13 @@ enum {
TRACE_SAMPLE_BAR = 4,
TRACE_SAMPLE_ZOO = 8,
};
+
+struct foo_timer_data {
+ const char *name;
+ struct timer_list timer;
+ int __percpu *counter;
+};
+
#endif
/*
@@ -595,6 +604,25 @@ TRACE_EVENT(foo_rel_loc,
__get_rel_bitmask(bitmask),
__get_rel_cpumask(cpumask))
);
+
+TRACE_EVENT(foo_timer_fn,
+
+ TP_PROTO(struct foo_timer_data *data),
+
+ TP_ARGS(data),
+
+ TP_STRUCT__entry(
+ __string( name, data->name )
+ __field( int, count )
+ ),
+
+ TP_fast_assign(
+ __assign_str(name);
+ __entry->count = *this_cpu_ptr(data->counter);
+ ),
+
+ TP_printk("name=%s count=%d", __get_str(name), __entry->count)
+);
#endif
/***** NOTICE! The #if protection ends here. *****/
diff --git a/tools/testing/selftests/ftrace/test.d/dynevent/btf_probe_event.tc b/tools/testing/selftests/ftrace/test.d/dynevent/btf_probe_event.tc
new file mode 100644
index 000000000000..bf71368c31a4
--- /dev/null
+++ b/tools/testing/selftests/ftrace/test.d/dynevent/btf_probe_event.tc
@@ -0,0 +1,51 @@
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
+# description: BTF event with typecast and percpu access
+# requires: dynamic_events "this_cpu_read(<fetcharg>)":README "[(structname[,field])]<argname>[->field[->field|.field...]]":README
+
+# Check if the sample module is loaded
+if ! lsmod | grep -q trace_events_sample; then
+ modprobe trace-events-sample || exit_unresolved
+fi
+
+echo 0 > events/enable
+echo > dynamic_events
+
+# The sample_timer_cb(struct timer_list *t) is called.
+# We want to check (STRUCT,FIELD)VAR typecast and this_cpu_read() access.
+# (foo_timer_data,timer)t converts t to struct foo_timer_data * using container_of.
+# data->counter is a per-cpu pointer to int.
+# this_cpu_read(data->counter) should give the value of the counter.
+
+echo 'f:mysample/myevent sample_timer_cb name=(foo_timer_data,timer)t->name:string count=this_cpu_read((foo_timer_data,timer)t->counter)' >> dynamic_events
+
+echo 1 > events/mysample/myevent/enable
+echo 1 > events/sample-trace/foo_timer_fn/enable
+
+sleep 2
+
+echo 0 > events/mysample/myevent/enable
+echo 0 > events/sample-trace/foo_timer_fn/enable
+
+# Compare the values.
+MATCH=0
+while read line; do
+ if echo $line | grep -q "foo_timer_fn:"; then
+ NAME=`echo $line | sed 's/.*name=\([^ ]*\) .*/\1/'`
+ COUNT=`echo $line | sed 's/.*count=\([^ ]*\).*/\1/'`
+ if grep -q "myevent:.*name=\"${NAME}\" count=$COUNT" trace; then
+ MATCH=$((MATCH+1))
+ fi
+ fi
+done < trace
+
+if [ $MATCH -eq 0 ]; then
+ echo "No matching events found"
+ exit_fail
+fi
+
+# Clean up
+echo 0 > events/mysample/myevent/enable
+echo 0 > events/sample-trace/foo_timer_fn/enable
+echo > dynamic_events
+clear_trace
diff --git a/tools/testing/selftests/ftrace/test.d/dynevent/btf_typecast_accepted.tc b/tools/testing/selftests/ftrace/test.d/dynevent/btf_typecast_accepted.tc
new file mode 100644
index 000000000000..dd5552727054
--- /dev/null
+++ b/tools/testing/selftests/ftrace/test.d/dynevent/btf_typecast_accepted.tc
@@ -0,0 +1,103 @@
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
+# description: BTF typecast and percpu access syntax validation
+# requires: dynamic_events "this_cpu_read(<fetcharg>)":README "[(structname[,field])]<argname>[->field[->field|.field...]]":README
+
+KPROBES=
+FPROBES=
+
+if grep -qF "p[:[<group>/][<event>]] <place> [<args>]" README ; then
+ KPROBES=yes
+fi
+if grep -qF "f[:[<group>/][<event>]] <func-name>[%return] [<args>]" README ; then
+ FPROBES=yes
+fi
+
+if [ -z "$KPROBES" -a -z "$FPROBES" ] ; then
+ exit_unsupported
+fi
+
+echo 0 > events/enable
+echo > dynamic_events
+
+# Load trace-events-sample module if available to have per-CPU counter structure defined
+if ! lsmod | grep -q trace_events_sample; then
+ modprobe trace-events-sample || exit_unresolved
+fi
+
+if [ "$FPROBES" ] ; then
+ # 1. Test basic typecast on fprobe
+ echo 'f:fpevent1 vfs_read name=(file)file->f_path.dentry->d_name.name:string' >> dynamic_events
+ # 2. Test parenthesized typecast target on fprobe
+ echo 'f:fpevent2 vfs_read name=(file)(file)->f_path.dentry->d_name.name:string' >> dynamic_events
+ # 3. Test nested typecasts on fprobe
+ echo 'f:fpevent3 vfs_read name=(dentry)((file)file->f_path.dentry)->d_name.name:string' >> dynamic_events
+ # 4. Test container_of-style typecast with field option on fprobe
+ echo 'f:fpevent4 vfs_read name=(file,f_path)file->f_mode' >> dynamic_events
+ # 5. Test typecast on return value on fprobe
+ echo 'f:fpevent5 vfs_read%return name=(file)$retval->f_path.dentry->d_name.name:string' >> dynamic_events
+ # 6. Test $current variable support on fprobe
+ echo 'f:fpevent6 vfs_read pid=$current->pid' >> dynamic_events
+ echo 'f:fpevent7 vfs_read pid=(task_struct)$current->pid' >> dynamic_events
+ echo 'f:fpevent8 vfs_read pid=(task_struct,group_leader)$current->pid' >> dynamic_events
+
+ # Test this_cpu_read and this_cpu_ptr on fprobe
+ echo 'f:fpevent9 sample_timer_cb name=(foo_timer_data,timer)t->name:string count=this_cpu_read((foo_timer_data,timer)t->counter)' >> dynamic_events
+ echo 'f:fpevent10 sample_timer_cb ptr=this_cpu_ptr((foo_timer_data,timer)t->counter)' >> dynamic_events
+fi
+
+if [ "$KPROBES" ] ; then
+ # 7. Test basic typecast on kprobe
+ echo 'p:kpevent1 vfs_read name=(file)file->f_path.dentry->d_name.name:string' >> dynamic_events
+ # 8. Test parenthesized typecast target on kprobe
+ echo 'p:kpevent2 vfs_read name=(file)(file)->f_path.dentry->d_name.name:string' >> dynamic_events
+ # 9. Test nested typecasts on kprobe
+ echo 'p:kpevent3 vfs_read name=(dentry)((file)file->f_path.dentry)->d_name.name:string' >> dynamic_events
+ # 10. Test container_of-style typecast with field option on kprobe
+ echo 'p:kpevent4 vfs_read name=(file,f_path)file->f_mode' >> dynamic_events
+ # 11. Test typecast on return value on kretprobe
+ echo 'r:kpevent5 vfs_read name=(file)$retval->f_path.dentry->d_name.name:string' >> dynamic_events
+ # 12. Test $current variable support on kprobe
+ echo 'p:kpevent6 vfs_read pid=$current->pid' >> dynamic_events
+ echo 'p:kpevent7 vfs_read pid=(task_struct)$current->pid' >> dynamic_events
+ echo 'p:kpevent8 vfs_read pid=(task_struct,group_leader)$current->pid' >> dynamic_events
+
+ # Test this_cpu_read and this_cpu_ptr on kprobe
+ echo 'p:kpevent9 sample_timer_cb name=(foo_timer_data,timer)t->name:string count=this_cpu_read((foo_timer_data,timer)t->counter)' >> dynamic_events
+ echo 'p:kpevent10 sample_timer_cb ptr=this_cpu_ptr((foo_timer_data,timer)t->counter)' >> dynamic_events
+fi
+
+# Verify the events exist in dynamic_events
+if [ "$FPROBES" ] ; then
+ grep -q "fpevent1 " dynamic_events
+ grep -q "fpevent2 " dynamic_events
+ grep -q "fpevent3 " dynamic_events
+ grep -q "fpevent4 " dynamic_events
+ grep -q "fpevent5 " dynamic_events
+ grep -q "fpevent6 " dynamic_events
+ grep -q "fpevent7 " dynamic_events
+ grep -q "fpevent8 " dynamic_events
+ if lsmod | grep -q trace_events_sample; then
+ grep -q "fpevent9 " dynamic_events
+ grep -q "fpevent10 " dynamic_events
+ fi
+fi
+
+if [ "$KPROBES" ] ; then
+ grep -q "kpevent1 " dynamic_events
+ grep -q "kpevent2 " dynamic_events
+ grep -q "kpevent3 " dynamic_events
+ grep -q "kpevent4 " dynamic_events
+ grep -q "kpevent5 " dynamic_events
+ grep -q "kpevent6 " dynamic_events
+ grep -q "kpevent7 " dynamic_events
+ grep -q "kpevent8 " dynamic_events
+ if lsmod | grep -q trace_events_sample; then
+ grep -q "kpevent9 " dynamic_events
+ grep -q "kpevent10 " dynamic_events
+ fi
+fi
+
+# Clean up
+echo > dynamic_events
+clear_trace
diff --git a/tools/testing/selftests/ftrace/test.d/dynevent/eprobes_syntax_errors.tc b/tools/testing/selftests/ftrace/test.d/dynevent/eprobes_syntax_errors.tc
index 0e65e787e426..c2e3f9d19f13 100644
--- a/tools/testing/selftests/ftrace/test.d/dynevent/eprobes_syntax_errors.tc
+++ b/tools/testing/selftests/ftrace/test.d/dynevent/eprobes_syntax_errors.tc
@@ -21,8 +21,17 @@ check_error 'e:foo/^bar.1 syscalls/sys_enter_openat' # BAD_EVENT_NAME
check_error 'e:foo/bar syscalls/sys_enter_openat arg=^$foo' # BAD_ATTACH_ARG
+check_error 'e:foo/bar syscalls/sys_enter_openat arg=^COMM' # NO_EVENT_FIELD
+if grep -q "\$current.*" README; then
+ check_error 'e:foo/bar syscalls/sys_enter_openat arg=^current' # NO_EVENT_FIELD
+fi
+
if grep -q '<attached-group>\.<attached-event>.*\[if <filter>\]' README; then
check_error 'e:foo/bar syscalls/sys_enter_openat if ^' # NO_EP_FILTER
fi
+if grep -q 'this_cpu_read(<fetcharg>)' README; then
+ check_error 'e:foo/bar syscalls/sys_enter_openat arg=^this_cpu_read(file)' # NOSUP_PERCPU
+fi
+
exit 0
diff --git a/tools/testing/selftests/ftrace/test.d/dynevent/fprobe_syntax_errors.tc b/tools/testing/selftests/ftrace/test.d/dynevent/fprobe_syntax_errors.tc
index fee479295e2f..e9d7e6919c7f 100644
--- a/tools/testing/selftests/ftrace/test.d/dynevent/fprobe_syntax_errors.tc
+++ b/tools/testing/selftests/ftrace/test.d/dynevent/fprobe_syntax_errors.tc
@@ -112,6 +112,18 @@ check_error 'f vfs_read%return $retval->^foo' # NO_PTR_STRCT
check_error 'f vfs_read file->^foo' # NO_BTF_FIELD
check_error 'f vfs_read file^-.foo' # BAD_HYPHEN
check_error 'f vfs_read ^file:string' # BAD_TYPE4STR
+if grep -qF "[(structname" README ; then
+check_error 'f vfs_read arg1=(task_struct)file^' # TYPECAST_REQ_FIELD
+check_error 'f vfs_read arg1=(a)((b)((c)(^(d)file->d)->c)->b)->a' # TOO_MANY_NESTED
+check_error 'f vfs_read arg1=(task_struct,^in_execve)file->comm' # TYPECAST_NOT_ALIGNED
+check_error 'f vfs_read arg1=(task_struct,^foo_bar)file->pid' # NO_BTF_FIELD
+check_error 'f vfs_read arg1=(^task_struct1234)file->pid' # NO_PTR_STRCT
+check_error 'f vfs_read arg1=(task_struct,se^->group_node)file->comm' # TYPECAST_BAD_ARROW
+check_error 'f vfs_read arg1=(task_struct,^->pid)file->comm' # NO_BTF_FIELD
+check_error 'f vfs_read arg1=(task_struct,^.pid)file->comm' # NO_BTF_FIELD
+check_error 'f vfs_read arg1=(task_struct,^.)file->comm' # NO_BTF_FIELD
+check_error 'f vfs_read arg1=(task_struct)^@symbol+10->comm' # TYPECAST_SYM_OFFSET
+fi
fi
else
diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_syntax_errors.tc b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_syntax_errors.tc
index 8f1c58f0c239..21ce8414459f 100644
--- a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_syntax_errors.tc
+++ b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_syntax_errors.tc
@@ -115,6 +115,18 @@ check_error 'p vfs_read+20 ^$arg*' # NOFENTRY_ARGS
check_error 'p vfs_read ^hoge' # NO_BTFARG
check_error 'p kfree ^$arg10' # NO_BTFARG (exceed the number of parameters)
check_error 'r kfree ^$retval' # NO_RETVAL
+if grep -qF "[(structname" README ; then
+check_error 'p vfs_read arg1=(task_struct)file^' # TYPECAST_REQ_FIELD
+check_error 'p vfs_read arg1=(a)((b)((c)(^(d)file->d)->c)->b)->a' # TOO_MANY_NESTED
+check_error 'p vfs_read arg1=(task_struct,^in_execve)file->comm' # TYPECAST_NOT_ALIGNED
+check_error 'p vfs_read arg1=(task_struct,^foo_bar)file->pid' # NO_BTF_FIELD
+check_error 'p vfs_read arg1=(^task_struct1234)file->pid' # NO_PTR_STRCT
+check_error 'p vfs_read arg1=(task_struct,se^->group_node)file->comm' # TYPECAST_BAD_ARROW
+check_error 'p vfs_read arg1=(task_struct,^->pid)file->comm' # NO_BTF_FIELD
+check_error 'p vfs_read arg1=(task_struct,^.pid)file->comm' # NO_BTF_FIELD
+check_error 'p vfs_read arg1=(task_struct,^.)file->comm' # NO_BTF_FIELD
+check_error 'p vfs_read arg1=(task_struct)^@symbol+10->comm' # TYPECAST_SYM_OFFSET
+fi
else
check_error 'p vfs_read ^$arg*' # NOSUP_BTFARG
fi
diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/uprobe_syntax_errors.tc b/tools/testing/selftests/ftrace/test.d/kprobe/uprobe_syntax_errors.tc
index c817158b99db..e12dc967ec76 100644
--- a/tools/testing/selftests/ftrace/test.d/kprobe/uprobe_syntax_errors.tc
+++ b/tools/testing/selftests/ftrace/test.d/kprobe/uprobe_syntax_errors.tc
@@ -28,4 +28,9 @@ if grep -q ".*symstr.*" README; then
check_error 'p /bin/sh:10 $stack0:^symstr' # BAD_TYPE
fi
+# $current is not supported by uprobe
+if grep -q "\$current.*" README; then
+check_error 'p /bin/sh:10 ^$current:u8' # BAD_VAR
+fi
+
exit 0
^ permalink raw reply related
* [PATCH v12 10/11] tracing/probes: Add this_cpu_read() and this_cpu_ptr() dereference method to fetcharg
From: Masami Hiramatsu (Google) @ 2026-06-28 23:53 UTC (permalink / raw)
To: Steven Rostedt, Mathieu Desnoyers
Cc: Jonathan Corbet, Shuah Khan, Masami Hiramatsu, linux-kernel,
linux-trace-kernel, linux-doc, linux-kselftest
In-Reply-To: <178269068329.1161310.17763177188897860801.stgit@devnote2>
From: Masami Hiramatsu (Google) <mhiramat@kernel.org>
When tracing the kernel local variables, sometimes we need to get the
CPU local variables. To access it, current simple dereference is not
enough.
Thus, introduce a special this_cpu_read() dereference to access per-cpu
variable for the current CPU (accessing other CPU variable may race with
updates on other CPUs). Also this_cpu_ptr() is for accessing per-cpu
pointer.
Those are working as same as the kernel percpu macro.
Signed-off-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
---
Changes in v11:
- Remove this_cpu_*() from eprobetrace.rst.
Changes in v10:
- Prohibit this_cpu_*() for eprobe events.
Changes in v9:
- Prohibit this_cpu_*() for non kernel probes.
Changes in v6:
- Rebased on dump fetcharg patch.
- Fix to fetch static percpu variable with @SYM correctly.
Changes in v5:
- Simplify this_cpu_read() into +0(this_cpu_ptr()).
Changes in v3:
- Remove NULL check for percpu var because it is just an offset, could be 0.
- Simplify process_fetch_insn_bottom() code.
- If the last operation is this_cpu_read(), read only memory of the specific
size (of type).
Changes in v2:
- Drop +CPU/+PCPU and introduce this_cpu_read() and this_cpu_ptr().
- Support these method with BTF typecast.
- Just check the base address is NOT NULL instead of is_kernel_percpu_address().
---
Documentation/trace/fprobetrace.rst | 2
Documentation/trace/kprobetrace.rst | 2
kernel/trace/trace.c | 1
kernel/trace/trace_probe.c | 152 ++++++++++++++++++++++++++---------
kernel/trace/trace_probe.h | 6 +
kernel/trace/trace_probe_tmpl.h | 22 ++++-
6 files changed, 139 insertions(+), 46 deletions(-)
diff --git a/Documentation/trace/fprobetrace.rst b/Documentation/trace/fprobetrace.rst
index 3392cab016b3..3439bc9bd351 100644
--- a/Documentation/trace/fprobetrace.rst
+++ b/Documentation/trace/fprobetrace.rst
@@ -52,6 +52,8 @@ Synopsis of fprobe-events
$comm : Fetch current task comm.
$current : Fetch the address of the current task_struct.
+|-[u]OFFS(FETCHARG) : Fetch memory at FETCHARG +|- OFFS address.(\*4)(\*5)
+ this_cpu_read(FETCHARG) : Read the value of the per-CPU variable FETCHARG on the current CPU.
+ this_cpu_ptr(FETCHARG) : Get the address of the per-CPU variable FETCHARG on the current CPU.
\IMM : Store an immediate value to the argument.
NAME=FETCHARG : Set NAME as the argument name of FETCHARG.
FETCHARG:TYPE : Set TYPE as the type of FETCHARG. Currently, basic types
diff --git a/Documentation/trace/kprobetrace.rst b/Documentation/trace/kprobetrace.rst
index 81e4fe38791d..9ae330eb0a52 100644
--- a/Documentation/trace/kprobetrace.rst
+++ b/Documentation/trace/kprobetrace.rst
@@ -55,6 +55,8 @@ Synopsis of kprobe_events
$comm : Fetch current task comm.
$current : Fetch the address of the current task_struct.
+|-[u]OFFS(FETCHARG) : Fetch memory at FETCHARG +|- OFFS address.(\*3)(\*4)
+ this_cpu_read(FETCHARG) : Read the value of the per-CPU variable FETCHARG on the current CPU.
+ this_cpu_ptr(FETCHARG) : Get the address of the per-CPU variable FETCHARG on the current CPU.
\IMM : Store an immediate value to the argument.
NAME=FETCHARG : Set NAME as the argument name of FETCHARG.
FETCHARG:TYPE : Set TYPE as the type of FETCHARG. Currently, basic types
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 2b0b4f9acb2e..c9e182d40059 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -4329,6 +4329,7 @@ static const char readme_msg[] =
"\t $stack<index>, $stack, $retval, $comm, $current\n"
#endif
"\t +|-[u]<offset>(<fetcharg>), \\imm-value, \\\"imm-string\"\n"
+ "\t this_cpu_read(<fetcharg>), this_cpu_ptr(<fetcharg>)\n"
"\t kernel return probes support: $retval, $arg<N>, $comm\n"
"\t type: s8/16/32/64, u8/16/32/64, x8/16/32/64, char, string, symbol,\n"
"\t b<bit-width>@<bit-offset>/<container-size>, ustring,\n"
diff --git a/kernel/trace/trace_probe.c b/kernel/trace/trace_probe.c
index 999dec84275d..18c212122344 100644
--- a/kernel/trace/trace_probe.c
+++ b/kernel/trace/trace_probe.c
@@ -345,6 +345,109 @@ static int parse_trace_event(char *arg, struct fetch_insn *code,
return -EINVAL;
}
+/* this_cpu_* parser */
+#define THIS_CPU_PTR_PREFIX "this_cpu_ptr("
+#define THIS_CPU_READ_PREFIX "this_cpu_read("
+#define THIS_CPU_PTR_LEN (sizeof(THIS_CPU_PTR_PREFIX) - 1)
+#define THIS_CPU_READ_LEN (sizeof(THIS_CPU_READ_PREFIX) - 1)
+
+static int
+parse_probe_arg(char *arg, const struct fetch_type *type,
+ struct fetch_insn **pcode, struct fetch_insn *end,
+ struct traceprobe_parse_context *ctx);
+
+/* handle dereference nested call */
+static inline int handle_dereference(char *arg, struct fetch_insn **pcode,
+ struct fetch_insn *end, struct traceprobe_parse_context *ctx,
+ int deref, long offset)
+{
+ const struct fetch_type *type = find_fetch_type(NULL, ctx->flags);
+ struct fetch_insn *code = *pcode;
+ int cur_offs = ctx->offset;
+ char *tmp;
+ int ret;
+
+ tmp = strrchr(arg, ')');
+ if (!tmp) {
+ trace_probe_log_err(ctx->offset + strlen(arg),
+ DEREF_OPEN_BRACE);
+ return -EINVAL;
+ }
+
+ *tmp = '\0';
+ ret = parse_probe_arg(arg, type, &code, end, ctx);
+ if (ret)
+ return ret;
+ ctx->offset = cur_offs;
+ if (code->op == FETCH_OP_COMM || code->op == FETCH_OP_IMMSTR) {
+ trace_probe_log_err(ctx->offset, COMM_CANT_DEREF);
+ return -EINVAL;
+ }
+
+ /*
+ * this_cpu_ptr(@SYM) does not use SYM value, but use SYM address.
+ * So we overwrite the last FETCH_OP_DEREF with FETCH_OP_CPU_PTR.
+ */
+ if (!(deref == FETCH_OP_CPU_PTR && *arg == '@')) {
+ code++;
+ if (code == end) {
+ trace_probe_log_err(ctx->offset, TOO_MANY_OPS);
+ return -EINVAL;
+ }
+ }
+ *pcode = code;
+
+ code->op = deref;
+ code->offset = offset;
+ /* Reset the last type if used */
+ ctx->last_type = NULL;
+ return 0;
+}
+
+static int parse_this_cpu(char *arg, struct fetch_insn **pcode,
+ struct fetch_insn *end,
+ struct traceprobe_parse_context *ctx)
+{
+ struct fetch_insn *code;
+ bool is_ptr = false;
+ int ret;
+
+ /*
+ * This is only for kernel probes, excluding eprobe, because per-cpu
+ * pointer should not be recorded by events.
+ */
+ if (!(ctx->flags & TPARG_FL_KERNEL) ||
+ (ctx->flags & TPARG_FL_TEVENT)) {
+ trace_probe_log_err(ctx->offset, NOSUP_PERCPU);
+ return -EINVAL;
+ }
+ if (str_has_prefix(arg, THIS_CPU_PTR_PREFIX)) {
+ arg += THIS_CPU_PTR_LEN;
+ ctx->offset += THIS_CPU_PTR_LEN;
+ is_ptr = true;
+ } else if (str_has_prefix(arg, THIS_CPU_READ_PREFIX)) {
+ arg += THIS_CPU_READ_LEN;
+ ctx->offset += THIS_CPU_READ_LEN;
+ } else
+ return -EINVAL;
+
+ ret = handle_dereference(arg, pcode, end, ctx, FETCH_OP_CPU_PTR, 0);
+ if (ret || is_ptr)
+ return ret;
+
+ /* this_cpu_read(VAR) -> +0(this_cpu_ptr(VAR)) */
+ code = *pcode;
+ code++;
+ if (code == end) {
+ trace_probe_log_err(ctx->offset, TOO_MANY_OPS);
+ return -EINVAL;
+ }
+ code->op = FETCH_OP_DEREF;
+ code->offset = 0;
+ *pcode = code;
+ return 0;
+}
+
#ifdef CONFIG_PROBE_EVENTS_BTF_ARGS
static u32 btf_type_int(const struct btf_type *t)
@@ -904,11 +1007,6 @@ static char *find_matched_close_paren(char *s)
return NULL;
}
-static int
-parse_probe_arg(char *arg, const struct fetch_type *type,
- struct fetch_insn **pcode, struct fetch_insn *end,
- struct traceprobe_parse_context *ctx);
-
static int handle_typecast(char *arg, struct fetch_insn **pcode,
struct fetch_insn *end,
struct traceprobe_parse_context *ctx)
@@ -961,7 +1059,9 @@ static int handle_typecast(char *arg, struct fetch_insn **pcode,
/* Skip '(' */
ctx->offset += 1;
tmp++;
- } else if (*tmp == '+' || *tmp == '-') {
+ } else if (*tmp == '+' || *tmp == '-' ||
+ str_has_prefix(tmp, THIS_CPU_PTR_PREFIX) ||
+ str_has_prefix(tmp, THIS_CPU_READ_PREFIX)) {
/* Dereference can have another field access inside it. */
char *open = strchr(tmp + 1, '(');
@@ -1481,36 +1581,9 @@ parse_probe_arg(char *arg, const struct fetch_type *type,
}
ctx->offset += (tmp + 1 - arg) + (arg[0] != '-' ? 1 : 0);
arg = tmp + 1;
- tmp = strrchr(arg, ')');
- if (!tmp) {
- trace_probe_log_err(ctx->offset + strlen(arg),
- DEREF_OPEN_BRACE);
- return -EINVAL;
- } else {
- const struct fetch_type *t2 = find_fetch_type(NULL, ctx->flags);
- int cur_offs = ctx->offset;
-
- *tmp = '\0';
- ret = parse_probe_arg(arg, t2, &code, end, ctx);
- if (ret)
- break;
- ctx->offset = cur_offs;
- if (code->op == FETCH_OP_COMM ||
- code->op == FETCH_OP_IMMSTR) {
- trace_probe_log_err(ctx->offset, COMM_CANT_DEREF);
- return -EINVAL;
- }
- if (++code == end) {
- trace_probe_log_err(ctx->offset, TOO_MANY_OPS);
- return -EINVAL;
- }
- *pcode = code;
-
- code->op = deref;
- code->offset = offset;
- /* Reset the last type if used */
- ctx->last_type = NULL;
- }
+ ret = handle_dereference(arg, pcode, end, ctx, deref, offset);
+ if (ret < 0)
+ return ret;
break;
case '\\': /* Immediate value */
if (arg[1] == '"') { /* Immediate string */
@@ -1531,7 +1604,10 @@ parse_probe_arg(char *arg, const struct fetch_type *type,
ret = handle_typecast(arg, pcode, end, ctx);
break;
default:
- if (isalpha(arg[0]) || arg[0] == '_') {
+ if (str_has_prefix(arg, THIS_CPU_PTR_PREFIX) ||
+ str_has_prefix(arg, THIS_CPU_READ_PREFIX)) {
+ ret = parse_this_cpu(arg, pcode, end, ctx);
+ } else if (isalpha(arg[0]) || arg[0] == '_') {
/* BTF variable or event field*/
if (ctx->flags & TPARG_FL_TEVENT) {
ret = parse_trace_event(arg, *pcode, ctx);
@@ -1548,8 +1624,8 @@ parse_probe_arg(char *arg, const struct fetch_type *type,
return -EINVAL;
}
ret = parse_btf_arg(arg, pcode, end, ctx);
- break;
}
+ break;
}
if (!ret && code->op == FETCH_OP_NOP) {
/* Parsed, but do not find fetch method */
diff --git a/kernel/trace/trace_probe.h b/kernel/trace/trace_probe.h
index 053f72fdaece..e6268a8dc378 100644
--- a/kernel/trace/trace_probe.h
+++ b/kernel/trace/trace_probe.h
@@ -101,6 +101,7 @@ typedef int (*print_type_func_t)(struct trace_seq *, void *, void *);
/* Stage 2 (dereference) ops */ \
FETCH_OP(DEREF, offset), /* Dereference: .offset */ \
FETCH_OP(UDEREF, offset), /* User-space dereference: .offset */\
+ FETCH_OP(CPU_PTR, none), /* Per-CPU pointer: .offset */ \
/* Stage 3 (store) ops */ \
FETCH_OP(ST_RAW, store), /* Raw value: .size */ \
FETCH_OP(ST_MEM, store), /* Memory: .offset, .size */ \
@@ -596,9 +597,10 @@ extern int traceprobe_define_arg_fields(struct trace_event_call *event_call,
C(TYPECAST_NOT_EVENT, "Typecasts are only for eprobe fields"), \
C(TYPECAST_REQ_FIELD, "Typecast requires a field access"), \
C(TOO_MANY_NESTED, "Too many nested typecasts/dereferences"), \
- C(TYPECAST_SYM_OFFSET, "@SYM+/-OFFSET with typecast needs parentheses") \
+ C(TYPECAST_SYM_OFFSET, "@SYM+/-OFFSET with typecast needs parentheses"), \
C(TYPECAST_NOT_ALIGNED, "Typecast field option is not byte-aligned"), \
- C(TYPECAST_BAD_ARROW, "Typecast field option does not support -> operator"),
+ C(TYPECAST_BAD_ARROW, "Typecast field option does not support -> operator"), \
+ C(NOSUP_PERCPU, "Per-cpu variable access is only for kernel probes"),
#undef C
#define C(a, b) TP_ERR_##a
diff --git a/kernel/trace/trace_probe_tmpl.h b/kernel/trace/trace_probe_tmpl.h
index d0e9662cde00..8db12f758fda 100644
--- a/kernel/trace/trace_probe_tmpl.h
+++ b/kernel/trace/trace_probe_tmpl.h
@@ -129,25 +129,35 @@ process_fetch_insn_bottom(struct fetch_insn *code, unsigned long val,
struct fetch_insn *s3 = NULL;
int total = 0, ret = 0, i = 0;
u32 loc = 0;
- unsigned long lval = val;
+ unsigned long lval, llval = val;
stage2:
/* 2nd stage: dereference memory if needed */
do {
- if (code->op == FETCH_OP_DEREF) {
- lval = val;
+ lval = val;
+ switch (code->op) {
+ case FETCH_OP_DEREF:
ret = probe_mem_read(&val, (void *)val + code->offset,
sizeof(val));
- } else if (code->op == FETCH_OP_UDEREF) {
- lval = val;
+ break;
+ case FETCH_OP_UDEREF:
ret = probe_mem_read_user(&val,
(void *)val + code->offset, sizeof(val));
- } else
break;
+ case FETCH_OP_CPU_PTR:
+ val = (unsigned long)this_cpu_ptr((void __percpu *)val);
+ ret = 0;
+ break;
+ default:
+ lval = llval;
+ goto out;
+ }
if (ret)
return ret;
+ llval = lval;
code++;
} while (1);
+out:
s3 = code;
stage3:
^ permalink raw reply related
* [PATCH v12 09/11] tracing/probes: Add $current variable support
From: Masami Hiramatsu (Google) @ 2026-06-28 23:52 UTC (permalink / raw)
To: Steven Rostedt, Mathieu Desnoyers
Cc: Jonathan Corbet, Shuah Khan, Masami Hiramatsu, linux-kernel,
linux-trace-kernel, linux-doc, linux-kselftest
In-Reply-To: <178269068329.1161310.17763177188897860801.stgit@devnote2>
From: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Since we can use the BTF to cast value to a structure pointer type,
it is useful to introduce "$current" special variable support to
fetcharg.
User can define a fetcharg to access current task_struct properties
using BTF info. e.g.
$current->cpus_ptr
Signed-off-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
---
Changes in v8:
- Avoid uninitialized ctx->btf issue on $current without typecast.
Changes in v7:
- Fix to use force-typecast for task_struct implicitly.
Changes in v6:
- Rebased on dump fetcharg patch.
- Remove function name/eprobe requirement for $current.
Changes in v5:
- Use s32 for bof_find_btf_id().
Changes in v4:
- Add $current in README when CONFIG_HAVE_FUNCTION_ARG_ACCESS_API=y case.
- Fix to prohibit using $current in eprobes and address based kprobes.
Changes in v3:
- Remove $current support from eprobes (because eprobes is only for event)
- Prohibit uprobes to use $current.
Changes in v2:
- Support to parse $current in parse_btf_arg().
- If no typecast on $current, it automatically casted to task_struct.
- Check error case if $current follows something except for "-".
---
Documentation/trace/fprobetrace.rst | 1 +
Documentation/trace/kprobetrace.rst | 1 +
kernel/trace/trace.c | 4 ++--
kernel/trace/trace_probe.c | 37 ++++++++++++++++++++++++++++++++++-
kernel/trace/trace_probe.h | 1 +
kernel/trace/trace_probe_tmpl.h | 3 +++
6 files changed, 44 insertions(+), 3 deletions(-)
diff --git a/Documentation/trace/fprobetrace.rst b/Documentation/trace/fprobetrace.rst
index 290a9e6f7491..3392cab016b3 100644
--- a/Documentation/trace/fprobetrace.rst
+++ b/Documentation/trace/fprobetrace.rst
@@ -50,6 +50,7 @@ Synopsis of fprobe-events
$argN : Fetch the Nth function argument. (N >= 1) (\*2)
$retval : Fetch return value.(\*3)
$comm : Fetch current task comm.
+ $current : Fetch the address of the current task_struct.
+|-[u]OFFS(FETCHARG) : Fetch memory at FETCHARG +|- OFFS address.(\*4)(\*5)
\IMM : Store an immediate value to the argument.
NAME=FETCHARG : Set NAME as the argument name of FETCHARG.
diff --git a/Documentation/trace/kprobetrace.rst b/Documentation/trace/kprobetrace.rst
index a62707e6a9f2..81e4fe38791d 100644
--- a/Documentation/trace/kprobetrace.rst
+++ b/Documentation/trace/kprobetrace.rst
@@ -53,6 +53,7 @@ Synopsis of kprobe_events
$argN : Fetch the Nth function argument. (N >= 1) (\*1)
$retval : Fetch return value.(\*2)
$comm : Fetch current task comm.
+ $current : Fetch the address of the current task_struct.
+|-[u]OFFS(FETCHARG) : Fetch memory at FETCHARG +|- OFFS address.(\*3)(\*4)
\IMM : Store an immediate value to the argument.
NAME=FETCHARG : Set NAME as the argument name of FETCHARG.
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 5670c4b91dc0..2b0b4f9acb2e 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -4320,13 +4320,13 @@ static const char readme_msg[] =
"\t args: <name>=fetcharg[:type]\n"
"\t fetcharg: (%<register>|$<efield>), @<address>, @<symbol>[+|-<offset>],\n"
#ifdef CONFIG_HAVE_FUNCTION_ARG_ACCESS_API
- "\t $stack<index>, $stack, $retval, $comm, $arg<N>,\n"
+ "\t $stack<index>, $stack, $retval, $comm, $arg<N>, $current\n"
#ifdef CONFIG_PROBE_EVENTS_BTF_ARGS
"\t [(structname[,field])]<argname>[->field[->field|.field...]],\n"
"\t [(structname[,field])](fetcharg)->field[->field|.field...],\n"
#endif
#else
- "\t $stack<index>, $stack, $retval, $comm,\n"
+ "\t $stack<index>, $stack, $retval, $comm, $current\n"
#endif
"\t +|-[u]<offset>(<fetcharg>), \\imm-value, \\\"imm-string\"\n"
"\t kernel return probes support: $retval, $arg<N>, $comm\n"
diff --git a/kernel/trace/trace_probe.c b/kernel/trace/trace_probe.c
index fd006b415c68..999dec84275d 100644
--- a/kernel/trace/trace_probe.c
+++ b/kernel/trace/trace_probe.c
@@ -692,7 +692,9 @@ static int parse_btf_arg(char *varname,
int i, is_ptr, ret;
u32 tid;
- if (!ctx->funcname && !(ctx->flags & TPARG_FL_TEVENT))
+ /* Note: field is not separated at this point, so check prefix. */
+ if (!str_has_prefix(varname, "$current") &&
+ !ctx->funcname && !(ctx->flags & TPARG_FL_TEVENT))
return -EINVAL;
is_ptr = split_next_field(varname, &field, ctx);
@@ -705,6 +707,20 @@ static int parse_btf_arg(char *varname,
return -EOPNOTSUPP;
}
+ if (!strcmp(varname, "$current")) {
+ code->op = FETCH_OP_CURRENT;
+ /* If no typecast is specified for $current, use task_struct by default */
+ ret = bpf_find_btf_id("task_struct", BTF_KIND_STRUCT, &ctx->struct_btf);
+ if (ret < 0) {
+ trace_probe_log_err(ctx->offset, NO_BTF_ENTRY);
+ return -ENOENT;
+ }
+ tid = (u32)ret;
+ type = ctx->last_struct =
+ btf_type_skip_modifiers(ctx->struct_btf, tid, NULL);
+ goto found_type;
+ }
+
if (ctx->flags & TPARG_FL_RETURN && !strcmp(varname, "$retval")) {
code->op = FETCH_OP_RETVAL;
/* Check whether the function return type is not void, even with typecast. */
@@ -761,6 +777,7 @@ static int parse_btf_arg(char *varname,
found:
type = btf_type_skip_modifiers(ctx->btf, tid, NULL);
+found_type:
if (!type) {
trace_probe_log_err(ctx->offset, BAD_BTF_TID);
return -EINVAL;
@@ -1270,6 +1287,24 @@ static int parse_probe_vars(char *orig_arg, const struct fetch_type *t,
return 0;
}
+ /* $current returns the address of the current task_struct. */
+ if (str_has_prefix(arg, "current")) {
+ /* $current is only supported by kernel probe. */
+ if (!(ctx->flags & TPARG_FL_KERNEL)) {
+ err = TP_ERR_BAD_VAR;
+ goto inval;
+ }
+ arg += strlen("current");
+ if (*arg == '-' && IS_ENABLED(CONFIG_PROBE_EVENTS_BTF_ARGS))
+ return parse_btf_arg(orig_arg, pcode, end, ctx);
+
+ if (*arg != '\0')
+ goto inval;
+
+ code->op = FETCH_OP_CURRENT;
+ return 0;
+ }
+
#ifdef CONFIG_HAVE_FUNCTION_ARG_ACCESS_API
len = str_has_prefix(arg, "arg");
if (len) {
diff --git a/kernel/trace/trace_probe.h b/kernel/trace/trace_probe.h
index e7fcc77f51fc..053f72fdaece 100644
--- a/kernel/trace/trace_probe.h
+++ b/kernel/trace/trace_probe.h
@@ -92,6 +92,7 @@ typedef int (*print_type_func_t)(struct trace_seq *, void *, void *);
FETCH_OP(RETVAL, none), /* Return value */ \
FETCH_OP(IMM, imm), /* Immediate: .immediate */ \
FETCH_OP(COMM, none), /* Current comm */ \
+ FETCH_OP(CURRENT, none), /* Current task_struct address */\
FETCH_OP(ARG, param), /* Argument: .param = index */ \
FETCH_OP(FOFFS, imm), /* File offset: .immediate */ \
FETCH_OP(IMMSTR, string), /* Allocated string: .data */ \
diff --git a/kernel/trace/trace_probe_tmpl.h b/kernel/trace/trace_probe_tmpl.h
index 51436f19083b..d0e9662cde00 100644
--- a/kernel/trace/trace_probe_tmpl.h
+++ b/kernel/trace/trace_probe_tmpl.h
@@ -112,6 +112,9 @@ process_common_fetch_insn(struct fetch_insn *code, unsigned long *val)
case FETCH_OP_IMMSTR:
*val = (unsigned long)code->data;
break;
+ case FETCH_OP_CURRENT:
+ *val = (unsigned long)current;
+ break;
default:
return -EILSEQ;
}
^ permalink raw reply related
* [PATCH v12 08/11] tracing/probes: Support field specifier option for typecast
From: Masami Hiramatsu (Google) @ 2026-06-28 23:52 UTC (permalink / raw)
To: Steven Rostedt, Mathieu Desnoyers
Cc: Jonathan Corbet, Shuah Khan, Masami Hiramatsu, linux-kernel,
linux-trace-kernel, linux-doc, linux-kselftest
In-Reply-To: <178269068329.1161310.17763177188897860801.stgit@devnote2>
From: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Add a field specifier option for the typecast. This works like
container_of() macro.
(STRUCT[,FIELD[.FIELD2...]])VAR
This is equivalent to :
container_of(VAR, struct STRUCT, FIELD[.FIELD2...])
For example:
echo "f tick_nohz_handler next_tick=(tick_sched,sched_timer)timer->next_tick" >> dynamic_events
This will trace tick_nohz_handler() with its tick_sched::next_tick which
is converted from @timer by contianer_of(tick, struct tick_sched, sched_timer).
So, if you enabkle both fprobes:tick_nohz_handler__entry and
timer:hrtimer_expire_entry events, we will see something like:
<idle>-0 [002] d.h1. 3778.087272: hrtimer_expire_entry: hrtimer=00000000d63db328 f
unction=tick_nohz_handler now=3777450051040
<idle>-0 [002] d.h1. 3778.087281: tick_nohz_handler__entry: (tick_nohz_handler+0x4
/0x140) next_tick=3777450000000
Signed-off-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
---
Changes in v6:
- Update according to the allways nested patch.
Changes in v3:
- Fix error caret position.
Changes in v2:
- Use byteoffset for typecast field offset instead of bitoffset. This fixes negative modulo calculation.
- Check whether a field is specified after typecast.
- Reject if typecast field option has arrow operator.
---
Documentation/trace/eprobetrace.rst | 5 +
Documentation/trace/fprobetrace.rst | 8 +-
Documentation/trace/kprobetrace.rst | 8 +-
kernel/trace/trace.c | 4 -
kernel/trace/trace_probe.c | 169 ++++++++++++++++++++++++-----------
kernel/trace/trace_probe.h | 5 +
6 files changed, 135 insertions(+), 64 deletions(-)
diff --git a/Documentation/trace/eprobetrace.rst b/Documentation/trace/eprobetrace.rst
index cd0b4aa7f896..680e0af43d5d 100644
--- a/Documentation/trace/eprobetrace.rst
+++ b/Documentation/trace/eprobetrace.rst
@@ -49,7 +49,10 @@ Synopsis of eprobe_events
(STRUCT)FIELD->MEMBER[->MEMBER] : If BTF is supported, typecast FIELD to
a pointer to STRUCT and then derference the pointer defined by
->MEMBER. Note that when this is used, the FIELD name does not
- need to be prefixed with a '$'.
+ need to be prefixed with a '$'. ASGN can be specified optionally.
+ If ASGN is specified, FIELD will be cast to the same offset
+ position as the ASGN member, rather than to the beginning of
+ the STRUCT.
(STRUCT)(FETCHARG)->MEMBER[->MEMBER] : typecast can nest, so the above can
also be used with another FETCHARG instead of FIELD.
diff --git a/Documentation/trace/fprobetrace.rst b/Documentation/trace/fprobetrace.rst
index 6b8bb27bb62d..290a9e6f7491 100644
--- a/Documentation/trace/fprobetrace.rst
+++ b/Documentation/trace/fprobetrace.rst
@@ -57,10 +57,12 @@ Synopsis of fprobe-events
(u8/u16/u32/u64/s8/s16/s32/s64), hexadecimal types
(x8/x16/x32/x64), "char", "string", "ustring", "symbol", "symstr"
and bitfield are supported.
- (STRUCT)FIELD->MEMBER[->MEMBER] : If BTF is supported, typecast FIELD to
+ (STRUCT[,ASGN])FIELD->MEMBER[->MEMBER] : If BTF is supported, typecast FIELD to
a pointer to STRUCT and then derference the pointer defined by
- ->MEMBER.
- (STRUCT)(FETCHARG)->MEMBER[->MEMBER] : typecast can nest, so the above can
+ ->MEMBER. ASGN can be specified optionally. If ASGN is specified,
+ FIELD will be cast to the same offset position as the ASGN member,
+ rather than to the beginning of the STRUCT.
+ (STRUCT[,ASGN])(FETCHARG)->MEMBER[->MEMBER] : typecast can nest, so the above can
also be used with another FETCHARG instead of FIELD.
(\*1) This is available only when BTF is enabled.
diff --git a/Documentation/trace/kprobetrace.rst b/Documentation/trace/kprobetrace.rst
index c4382765d5b2..a62707e6a9f2 100644
--- a/Documentation/trace/kprobetrace.rst
+++ b/Documentation/trace/kprobetrace.rst
@@ -61,11 +61,13 @@ Synopsis of kprobe_events
(x8/x16/x32/x64), VFS layer common type(%pd/%pD), "char",
"string", "ustring", "symbol", "symstr" and bitfield are
supported.
- (STRUCT)FIELD->MEMBER[->MEMBER] : If BTF is supported, typecast FIELD to
+ (STRUCT[,ASGN])FIELD->MEMBER[->MEMBER] : If BTF is supported, typecast FIELD to
a pointer to STRUCT and then derference the pointer defined by
->MEMBER. Note that this is available only when the probe is
- on function entry.
- (STRUCT)(FETCHARG)->MEMBER[->MEMBER] : typecast can nest, so the above can
+ on function entry. ASGN can be specified optionally. If ASGN
+ is specified, FIELD will be cast to the same offset position
+ as the ASGN member, rather than to the beginning of the STRUCT.
+ (STRUCT[,ASGN])(FETCHARG)->MEMBER[->MEMBER] : typecast can nest, so the above can
also be used with another FETCHARG instead of FIELD.
(\*1) only for the probe on function entry (offs == 0). Note, this argument access
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index e56ee034c486..5670c4b91dc0 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -4322,8 +4322,8 @@ static const char readme_msg[] =
#ifdef CONFIG_HAVE_FUNCTION_ARG_ACCESS_API
"\t $stack<index>, $stack, $retval, $comm, $arg<N>,\n"
#ifdef CONFIG_PROBE_EVENTS_BTF_ARGS
- "\t [(structname)]<argname>[->field[->field|.field...]],\n"
- "\t [(structname)](fetcharg)->field[->field|.field...],\n"
+ "\t [(structname[,field])]<argname>[->field[->field|.field...]],\n"
+ "\t [(structname[,field])](fetcharg)->field[->field|.field...],\n"
#endif
#else
"\t $stack<index>, $stack, $retval, $comm,\n"
diff --git a/kernel/trace/trace_probe.c b/kernel/trace/trace_probe.c
index 1b97b125e9cb..fd006b415c68 100644
--- a/kernel/trace/trace_probe.c
+++ b/kernel/trace/trace_probe.c
@@ -568,6 +568,64 @@ static int split_next_field(char *varname, char **next_field,
return ret;
}
+/* Inner loop for solving dot operator ('.'). Return bit-offset of the given field */
+static int get_bitoffset_of_field(char **pfieldname, const struct btf_type **ptype,
+ struct traceprobe_parse_context *ctx)
+{
+ const struct btf_type *type = *ptype;
+ const struct btf_member *field;
+ struct btf *btf = ctx_btf(ctx);
+ char *fieldname = *pfieldname;
+ int bitoffs = 0;
+ u32 anon_offs;
+ char *next;
+ int is_ptr;
+
+ do {
+ next = NULL;
+ is_ptr = split_next_field(fieldname, &next, ctx);
+ if (is_ptr < 0)
+ return is_ptr;
+
+ anon_offs = 0;
+ field = btf_find_struct_member(btf, type, fieldname,
+ &anon_offs);
+ if (IS_ERR(field)) {
+ trace_probe_log_err(ctx->offset, BAD_BTF_TID);
+ return PTR_ERR(field);
+ }
+ if (!field) {
+ trace_probe_log_err(ctx->offset, NO_BTF_FIELD);
+ return -ENOENT;
+ }
+ /* Add anonymous structure/union offset */
+ bitoffs += anon_offs;
+
+ /* Accumulate the bit-offsets of the dot-connected fields */
+ if (btf_type_kflag(type)) {
+ bitoffs += BTF_MEMBER_BIT_OFFSET(field->offset);
+ ctx->last_bitsize = BTF_MEMBER_BITFIELD_SIZE(field->offset);
+ } else {
+ bitoffs += field->offset;
+ ctx->last_bitsize = 0;
+ }
+
+ type = btf_type_skip_modifiers(btf, field->type, NULL);
+ if (!type) {
+ trace_probe_log_err(ctx->offset, BAD_BTF_TID);
+ return -EINVAL;
+ }
+
+ if (next)
+ ctx->offset += next - fieldname;
+ fieldname = next;
+ } while (!is_ptr && fieldname);
+
+ *pfieldname = fieldname;
+ *ptype = type;
+
+ return bitoffs;
+}
/*
* Parse the field of data structure. The @type must be a pointer type
* pointing the target data structure type.
@@ -577,15 +635,13 @@ static int parse_btf_field(char *fieldname, const struct btf_type *type,
struct traceprobe_parse_context *ctx)
{
struct fetch_insn *code = *pcode;
- const struct btf_member *field;
- u32 bitoffs, anon_offs;
- bool is_struct = ctx->struct_btf != NULL;
struct btf *btf = ctx_btf(ctx);
- char *next;
- int is_ptr;
+ bool is_first_field = true;
+ int bitoffs;
do {
- if (!is_struct) {
+ /* For the first field of typecast, @type will be the target structure type. */
+ if (!(is_first_field && ctx->struct_btf)) {
/* Outer loop for solving arrow operator ('->') */
if (BTF_INFO_KIND(type->info) != BTF_KIND_PTR) {
trace_probe_log_err(ctx->offset, NO_PTR_STRCT);
@@ -599,60 +655,25 @@ static int parse_btf_field(char *fieldname, const struct btf_type *type,
return -EINVAL;
}
}
- /* Only the first type can skip being a pointer */
- is_struct = false;
-
- bitoffs = 0;
- do {
- /* Inner loop for solving dot operator ('.') */
- next = NULL;
- is_ptr = split_next_field(fieldname, &next, ctx);
- if (is_ptr < 0)
- return is_ptr;
-
- anon_offs = 0;
- field = btf_find_struct_member(btf, type, fieldname,
- &anon_offs);
- if (IS_ERR(field)) {
- trace_probe_log_err(ctx->offset, BAD_BTF_TID);
- return PTR_ERR(field);
- }
- if (!field) {
- trace_probe_log_err(ctx->offset, NO_BTF_FIELD);
- return -ENOENT;
- }
- /* Add anonymous structure/union offset */
- bitoffs += anon_offs;
-
- /* Accumulate the bit-offsets of the dot-connected fields */
- if (btf_type_kflag(type)) {
- bitoffs += BTF_MEMBER_BIT_OFFSET(field->offset);
- ctx->last_bitsize = BTF_MEMBER_BITFIELD_SIZE(field->offset);
- } else {
- bitoffs += field->offset;
- ctx->last_bitsize = 0;
- }
-
- type = btf_type_skip_modifiers(btf, field->type, NULL);
- if (!type) {
- trace_probe_log_err(ctx->offset, BAD_BTF_TID);
- return -EINVAL;
- }
-
- ctx->offset += next - fieldname;
- fieldname = next;
- } while (!is_ptr && fieldname);
+ bitoffs = get_bitoffset_of_field(&fieldname, &type, ctx);
+ if (bitoffs < 0)
+ return bitoffs;
if (++code == end) {
trace_probe_log_err(ctx->offset, TOO_MANY_OPS);
return -EINVAL;
}
code->op = FETCH_OP_DEREF; /* TODO: user deref support */
code->offset = bitoffs / 8;
+ if (is_first_field && ctx->struct_btf) {
+ /* The first field can be typecasted with field option. */
+ code->offset -= ctx->prefix_byteoffs;
+ }
*pcode = code;
ctx->last_bitoffs = bitoffs % 8;
ctx->last_type = type;
+ is_first_field = false;
} while (fieldname);
return 0;
@@ -808,6 +829,46 @@ static int query_btf_struct(const char *sname, struct traceprobe_parse_context *
return 0;
}
+static int parse_btf_casttype(char *casttype, struct traceprobe_parse_context *ctx)
+{
+ char *field;
+ int ret;
+
+ /* Field option - evaluated later. */
+ field = strchr(casttype, ',');
+ if (field)
+ *field++ = '\0';
+
+ ret = query_btf_struct(casttype, ctx);
+ if (ret < 0) {
+ trace_probe_log_err(ctx->offset, NO_PTR_STRCT);
+ return -EINVAL;
+ }
+
+ if (field) {
+ struct btf_type *type = (struct btf_type *)ctx->last_struct;
+
+ ctx->offset += field - casttype;
+ ret = get_bitoffset_of_field(&field, &ctx->last_struct, ctx);
+ if (ret < 0)
+ return ret;
+ if (ret % 8) {
+ trace_probe_log_err(ctx->offset, TYPECAST_NOT_ALIGNED);
+ return -EINVAL;
+ }
+ if (field != NULL) {
+ /* this means @field skips an arrow operator ("->"). */
+ trace_probe_log_err(ctx->offset - 2, TYPECAST_BAD_ARROW);
+ return -EINVAL;
+ }
+ ctx->prefix_byteoffs = ret / 8;
+ /* Restore the original struct type (overwritten by get_bitoffset_of_field) */
+ ctx->last_struct = type;
+ }
+
+ return ret;
+}
+
/* Find the matching closing parenthesis for a given opening parenthesis. */
static char *find_matched_close_paren(char *s)
{
@@ -940,14 +1001,14 @@ static int handle_typecast(char *arg, struct fetch_insn **pcode,
tmp = close + 2; /* Skip ">" after inner variable name */
/* resolve the typecast struct name */
- ret = query_btf_struct(arg + 1, ctx);
- if (ret < 0) {
- trace_probe_log_err(orig_offset + 1, NO_PTR_STRCT);
- return -EINVAL;
- }
+ ctx->offset = orig_offset + 1; /* for the '(' */
+ ret = parse_btf_casttype(arg + 1, ctx);
+ if (ret < 0)
+ return ret;
ctx->offset = orig_offset + tmp - arg;
ret = parse_btf_field(tmp, ctx->last_struct, pcode, end, ctx);
+ ctx->prefix_byteoffs = 0;
return ret;
}
diff --git a/kernel/trace/trace_probe.h b/kernel/trace/trace_probe.h
index f4fbe3010978..e7fcc77f51fc 100644
--- a/kernel/trace/trace_probe.h
+++ b/kernel/trace/trace_probe.h
@@ -451,6 +451,7 @@ struct traceprobe_parse_context {
unsigned int flags;
int offset;
int nested_level;
+ int prefix_byteoffs; /* The byte offset of the prefix field of typecast */
};
/* Each typecast consumes nested level. So the max number of typecast is 3. */
@@ -594,7 +595,9 @@ extern int traceprobe_define_arg_fields(struct trace_event_call *event_call,
C(TYPECAST_NOT_EVENT, "Typecasts are only for eprobe fields"), \
C(TYPECAST_REQ_FIELD, "Typecast requires a field access"), \
C(TOO_MANY_NESTED, "Too many nested typecasts/dereferences"), \
- C(TYPECAST_SYM_OFFSET, "@SYM+/-OFFSET with typecast needs parentheses")
+ C(TYPECAST_SYM_OFFSET, "@SYM+/-OFFSET with typecast needs parentheses") \
+ C(TYPECAST_NOT_ALIGNED, "Typecast field option is not byte-aligned"), \
+ C(TYPECAST_BAD_ARROW, "Typecast field option does not support -> operator"),
#undef C
#define C(a, b) TP_ERR_##a
^ permalink raw reply related
* [PATCH v12 07/11] tracing/probes: Type casting always involves nested calls
From: Masami Hiramatsu (Google) @ 2026-06-28 23:52 UTC (permalink / raw)
To: Steven Rostedt, Mathieu Desnoyers
Cc: Jonathan Corbet, Shuah Khan, Masami Hiramatsu, linux-kernel,
linux-trace-kernel, linux-doc, linux-kselftest
In-Reply-To: <178269068329.1161310.17763177188897860801.stgit@devnote2>
From: Masami Hiramatsu (Google) <mhiramat@kernel.org>
This allows type casting to various fetchargs without parentheses
by recursively calling parse_probe_arg on the target when type
casting is used.
For example, this allows the following expressions:
- (STRUCT)%REG->FIELD
- (STRUCT)$stackN->FIELD
- (STRUCT)@SYM->FIELD
Note that @SYM+/-OFFSET with typecast needs parentheses like:
- (STRUCT)(@SYM-8)->FIELD
Signed-off-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
---
Changes in v8:
- Fix caret position in error case.
- Add a comment about @SYM+/-OFFSET without parentheses.
Changes in v7:
- Prohibit using @SYM+/-OFFSET without parentheses.
- Cleanup parse_btf_arg() since ctx->struct_btf is always NULL now.
Changes in v6:
- Newly added.
---
kernel/trace/trace_probe.c | 123 ++++++++++++++++++++++++++------------------
kernel/trace/trace_probe.h | 4 +
2 files changed, 75 insertions(+), 52 deletions(-)
diff --git a/kernel/trace/trace_probe.c b/kernel/trace/trace_probe.c
index 827ae04f6351..1b97b125e9cb 100644
--- a/kernel/trace/trace_probe.c
+++ b/kernel/trace/trace_probe.c
@@ -684,19 +684,6 @@ static int parse_btf_arg(char *varname,
return -EOPNOTSUPP;
}
- if (ctx->flags & TPARG_FL_TEVENT) {
- ret = parse_trace_event(varname, code, ctx);
- if (ret < 0) {
- trace_probe_log_err(ctx->offset, BAD_ATTACH_ARG);
- return ret;
- }
- /* TEVENT is only here via a typecast */
- if (WARN_ON_ONCE(ctx->struct_btf == NULL))
- return -EINVAL;
- type = ctx->last_struct;
- goto found_type;
- }
-
if (ctx->flags & TPARG_FL_RETURN && !strcmp(varname, "$retval")) {
code->op = FETCH_OP_RETVAL;
/* Check whether the function return type is not void, even with typecast. */
@@ -708,13 +695,6 @@ static int parse_btf_arg(char *varname,
tid = ctx->proto->type;
goto found;
}
- /*
- * Even if we can not find appropriate BTF info, we can still access
- * the field via typecast.
- */
- if (ctx->struct_btf)
- goto found;
-
if (field) {
trace_probe_log_err(ctx->offset + field - varname,
NO_BTF_ENTRY);
@@ -759,11 +739,7 @@ static int parse_btf_arg(char *varname,
return -ENOENT;
found:
- if (ctx->struct_btf)
- type = ctx->last_struct;
- else
- type = btf_type_skip_modifiers(ctx->btf, tid, NULL);
-found_type:
+ type = btf_type_skip_modifiers(ctx->btf, tid, NULL);
if (!type) {
trace_probe_log_err(ctx->offset, BAD_BTF_TID);
return -EINVAL;
@@ -860,7 +836,7 @@ static int handle_typecast(char *arg, struct fetch_insn **pcode,
struct traceprobe_parse_context *ctx)
{
int orig_offset = ctx->offset;
- bool nested = false;
+ char *close;
char *tmp;
int ret;
@@ -871,6 +847,17 @@ static int handle_typecast(char *arg, struct fetch_insn **pcode,
return -EOPNOTSUPP;
}
+ /*
+ * Always consider the token after typecast as a nested call
+ * For example: (STRUCT)VAR->FIELD and (STRUCT)(VAR)->FIELD are same.
+ * VAR is solved in the nested call.
+ */
+ ctx->nested_level++;
+ if (ctx->nested_level > TRACEPROBE_MAX_NESTED_LEVEL) {
+ trace_probe_log_err(ctx->offset, TOO_MANY_NESTED);
+ return -E2BIG;
+ }
+
tmp = strchr(arg, ')');
if (!tmp) {
trace_probe_log_err(ctx->offset + strlen(arg),
@@ -879,11 +866,10 @@ static int handle_typecast(char *arg, struct fetch_insn **pcode,
}
*tmp++ = '\0';
- /* Handle the nested structure like (STRUCT)(VAR->FIELD)->... */
+ ctx->offset += tmp - arg;
if (*tmp == '(') {
- char *close = find_matched_close_paren(tmp);
+ close = find_matched_close_paren(tmp);
- ctx->offset += tmp - arg;
if (!close) {
trace_probe_log_err(ctx->offset, DEREF_OPEN_BRACE);
return -EINVAL;
@@ -894,27 +880,66 @@ static int handle_typecast(char *arg, struct fetch_insn **pcode,
TYPECAST_REQ_FIELD);
return -EINVAL;
}
-
- ctx->nested_level++;
- if (ctx->nested_level > TRACEPROBE_MAX_NESTED_LEVEL) {
- trace_probe_log_err(ctx->offset, TOO_MANY_NESTED);
- return -E2BIG;
+ /* Skip '(' */
+ ctx->offset += 1;
+ tmp++;
+ } else if (*tmp == '+' || *tmp == '-') {
+ /* Dereference can have another field access inside it. */
+ char *open = strchr(tmp + 1, '(');
+
+ if (!open) {
+ trace_probe_log_err(ctx->offset,
+ DEREF_NEED_BRACE);
+ return -EINVAL;
+ }
+ close = find_matched_close_paren(open);
+ if (!close) {
+ trace_probe_log_err(ctx->offset + strlen(tmp),
+ DEREF_OPEN_BRACE);
+ return -EINVAL;
+ }
+ close++;
+ /* We expect a field access for typecast */
+ if (close[0] != '-' || close[1] != '>') {
+ trace_probe_log_err(ctx->offset + close - tmp,
+ TYPECAST_REQ_FIELD);
+ return -EINVAL;
+ }
+ } else {
+ if (tmp[0] == '@') {
+ /* @sym+offset is not allowed without parenthesized */
+ close = strpbrk(tmp, "+-");
+ if (close && isdigit(close[1])) {
+ trace_probe_log_err(ctx->offset,
+ TYPECAST_SYM_OFFSET);
+ return -EINVAL;
+ }
}
- *close = '\0';
+ /* Inner variable name */
+ close = strchr(tmp, '-');
+ if (!close || close[1] != '>') {
+ trace_probe_log_err(ctx->offset + strlen(tmp),
+ TYPECAST_REQ_FIELD);
+ return -EINVAL;
+ }
+ }
+ *close = '\0';
- ctx->offset += 1; /* for the '(' */
- /* We need to parse the nested one */
- ret = parse_probe_arg(tmp + 1, find_fetch_type(NULL, ctx->flags),
- pcode, end, ctx);
- if (ret < 0)
- return ret;
- ctx->nested_level--;
- clear_struct_btf(ctx);
+ /* We need to parse the nested one */
+ ret = parse_probe_arg(tmp, find_fetch_type(NULL, ctx->flags),
+ pcode, end, ctx);
+ if (ret < 0)
+ return ret;
+ ctx->nested_level--;
+ clear_struct_btf(ctx);
- tmp = close + 3;/* Skip "->" after closing parenthesis */
- nested = true;
- }
+ /* Let tmp point the field name. */
+ if (close[1] == '-')
+ tmp = close + 3; /* Skip "->" after closing parenthesis */
+ else
+ tmp = close + 2; /* Skip ">" after inner variable name */
+ /* resolve the typecast struct name */
ret = query_btf_struct(arg + 1, ctx);
if (ret < 0) {
trace_probe_log_err(orig_offset + 1, NO_PTR_STRCT);
@@ -922,11 +947,7 @@ static int handle_typecast(char *arg, struct fetch_insn **pcode,
}
ctx->offset = orig_offset + tmp - arg;
- /* If it is nested, tmp points to the field name. */
- if (nested)
- ret = parse_btf_field(tmp, ctx->last_struct, pcode, end, ctx);
- else
- ret = parse_btf_arg(tmp, pcode, end, ctx);
+ ret = parse_btf_field(tmp, ctx->last_struct, pcode, end, ctx);
return ret;
}
diff --git a/kernel/trace/trace_probe.h b/kernel/trace/trace_probe.h
index 7d71925244e8..f4fbe3010978 100644
--- a/kernel/trace/trace_probe.h
+++ b/kernel/trace/trace_probe.h
@@ -453,6 +453,7 @@ struct traceprobe_parse_context {
int nested_level;
};
+/* Each typecast consumes nested level. So the max number of typecast is 3. */
#define TRACEPROBE_MAX_NESTED_LEVEL 3
extern int traceprobe_parse_probe_arg(struct trace_probe *tp, int i,
@@ -592,7 +593,8 @@ extern int traceprobe_define_arg_fields(struct trace_event_call *event_call,
C(EVENT_TOO_BIG, "Event too big (too many fields?)"), \
C(TYPECAST_NOT_EVENT, "Typecasts are only for eprobe fields"), \
C(TYPECAST_REQ_FIELD, "Typecast requires a field access"), \
- C(TOO_MANY_NESTED, "Too many nested typecasts/dereferences"),
+ C(TOO_MANY_NESTED, "Too many nested typecasts/dereferences"), \
+ C(TYPECAST_SYM_OFFSET, "@SYM+/-OFFSET with typecast needs parentheses")
#undef C
#define C(a, b) TP_ERR_##a
^ permalink raw reply related
* [PATCH v12 06/11] tracing/probes: Support nested typecast
From: Masami Hiramatsu (Google) @ 2026-06-28 23:52 UTC (permalink / raw)
To: Steven Rostedt, Mathieu Desnoyers
Cc: Jonathan Corbet, Shuah Khan, Masami Hiramatsu, linux-kernel,
linux-trace-kernel, linux-doc, linux-kselftest
In-Reply-To: <178269068329.1161310.17763177188897860801.stgit@devnote2>
From: Masami Hiramatsu (Google) <mhiramat@kernel.org>
When we hit an open parenthesis right after typecast closing
parenthesis, it means we have nested typecast. This allows us to
typecast a generic data member in a structure to a pointer to
another structure.
For example, to cast a DATA_MEMBER of VAR structure to STRUCT pointer
and get MEMBER value.
(STRUCT)(VAR->DATA_MEMBER)->MEMBER
Also, we can nest typecast.
(STRUCT1)((STRUCT2)$ARG->FIELD2)->FIELD1
Currently the max nest level is limited to 3.
This also allows user to use typecasting for registers or stacks on
kprobe events. e.g.
(STRUCT)(%ax)->MEMBER
(STRUCT)($stack0)->MEMBER
Signed-off-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
---
Changes in v11:
- Fix to return -EINVAL if WARN_ON_ONCE() is hit.
Changes in v6:
- Add a WARN_ON_ONCE check for leaking nested_level (it must not happen.)
Changes in v4:
- Use orig_offset for reporting NO_PTR_STRCT error.
Changes in v2:
- Fix to skip "->" after closing parenthetsis.
---
Documentation/trace/eprobetrace.rst | 2 +
Documentation/trace/fprobetrace.rst | 2 +
Documentation/trace/kprobetrace.rst | 2 +
kernel/trace/trace.c | 1
kernel/trace/trace_probe.c | 83 ++++++++++++++++++++++++++++++++---
kernel/trace/trace_probe.h | 7 +++
6 files changed, 88 insertions(+), 9 deletions(-)
diff --git a/Documentation/trace/eprobetrace.rst b/Documentation/trace/eprobetrace.rst
index fe3602540569..cd0b4aa7f896 100644
--- a/Documentation/trace/eprobetrace.rst
+++ b/Documentation/trace/eprobetrace.rst
@@ -50,6 +50,8 @@ Synopsis of eprobe_events
a pointer to STRUCT and then derference the pointer defined by
->MEMBER. Note that when this is used, the FIELD name does not
need to be prefixed with a '$'.
+ (STRUCT)(FETCHARG)->MEMBER[->MEMBER] : typecast can nest, so the above can
+ also be used with another FETCHARG instead of FIELD.
Types
-----
diff --git a/Documentation/trace/fprobetrace.rst b/Documentation/trace/fprobetrace.rst
index 7435ded2d66d..6b8bb27bb62d 100644
--- a/Documentation/trace/fprobetrace.rst
+++ b/Documentation/trace/fprobetrace.rst
@@ -60,6 +60,8 @@ Synopsis of fprobe-events
(STRUCT)FIELD->MEMBER[->MEMBER] : If BTF is supported, typecast FIELD to
a pointer to STRUCT and then derference the pointer defined by
->MEMBER.
+ (STRUCT)(FETCHARG)->MEMBER[->MEMBER] : typecast can nest, so the above can
+ also be used with another FETCHARG instead of FIELD.
(\*1) This is available only when BTF is enabled.
(\*2) only for the probe on function entry (offs == 0). Note, this argument access
diff --git a/Documentation/trace/kprobetrace.rst b/Documentation/trace/kprobetrace.rst
index f73614997d52..c4382765d5b2 100644
--- a/Documentation/trace/kprobetrace.rst
+++ b/Documentation/trace/kprobetrace.rst
@@ -65,6 +65,8 @@ Synopsis of kprobe_events
a pointer to STRUCT and then derference the pointer defined by
->MEMBER. Note that this is available only when the probe is
on function entry.
+ (STRUCT)(FETCHARG)->MEMBER[->MEMBER] : typecast can nest, so the above can
+ also be used with another FETCHARG instead of FIELD.
(\*1) only for the probe on function entry (offs == 0). Note, this argument access
is best effort, because depending on the argument type, it may be passed on
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 280a3dccd13f..e56ee034c486 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -4323,6 +4323,7 @@ static const char readme_msg[] =
"\t $stack<index>, $stack, $retval, $comm, $arg<N>,\n"
#ifdef CONFIG_PROBE_EVENTS_BTF_ARGS
"\t [(structname)]<argname>[->field[->field|.field...]],\n"
+ "\t [(structname)](fetcharg)->field[->field|.field...],\n"
#endif
#else
"\t $stack<index>, $stack, $retval, $comm,\n"
diff --git a/kernel/trace/trace_probe.c b/kernel/trace/trace_probe.c
index e6cc9f3d6c8b..827ae04f6351 100644
--- a/kernel/trace/trace_probe.c
+++ b/kernel/trace/trace_probe.c
@@ -832,10 +832,35 @@ static int query_btf_struct(const char *sname, struct traceprobe_parse_context *
return 0;
}
+/* Find the matching closing parenthesis for a given opening parenthesis. */
+static char *find_matched_close_paren(char *s)
+{
+ char *p = s;
+ int count = 0;
+
+ while (*p) {
+ if (*p == '(')
+ count++;
+ else if (*p == ')') {
+ if (--count == 0)
+ return p;
+ }
+ p++;
+ }
+ return NULL;
+}
+
+static int
+parse_probe_arg(char *arg, const struct fetch_type *type,
+ struct fetch_insn **pcode, struct fetch_insn *end,
+ struct traceprobe_parse_context *ctx);
+
static int handle_typecast(char *arg, struct fetch_insn **pcode,
struct fetch_insn *end,
struct traceprobe_parse_context *ctx)
{
+ int orig_offset = ctx->offset;
+ bool nested = false;
char *tmp;
int ret;
@@ -852,19 +877,56 @@ static int handle_typecast(char *arg, struct fetch_insn **pcode,
DEREF_OPEN_BRACE);
return -EINVAL;
}
- *tmp = '\0';
- ret = query_btf_struct(arg + 1, ctx);
- *tmp = ')';
+ *tmp++ = '\0';
+ /* Handle the nested structure like (STRUCT)(VAR->FIELD)->... */
+ if (*tmp == '(') {
+ char *close = find_matched_close_paren(tmp);
+
+ ctx->offset += tmp - arg;
+ if (!close) {
+ trace_probe_log_err(ctx->offset, DEREF_OPEN_BRACE);
+ return -EINVAL;
+ }
+ /* We expect a field access for typecast */
+ if (close[1] != '-' || close[2] != '>') {
+ trace_probe_log_err(ctx->offset + close - tmp + 1,
+ TYPECAST_REQ_FIELD);
+ return -EINVAL;
+ }
+
+ ctx->nested_level++;
+ if (ctx->nested_level > TRACEPROBE_MAX_NESTED_LEVEL) {
+ trace_probe_log_err(ctx->offset, TOO_MANY_NESTED);
+ return -E2BIG;
+ }
+ *close = '\0';
+
+ ctx->offset += 1; /* for the '(' */
+ /* We need to parse the nested one */
+ ret = parse_probe_arg(tmp + 1, find_fetch_type(NULL, ctx->flags),
+ pcode, end, ctx);
+ if (ret < 0)
+ return ret;
+ ctx->nested_level--;
+ clear_struct_btf(ctx);
+
+ tmp = close + 3;/* Skip "->" after closing parenthesis */
+ nested = true;
+ }
+
+ ret = query_btf_struct(arg + 1, ctx);
if (ret < 0) {
- trace_probe_log_err(ctx->offset + 1, NO_PTR_STRCT);
+ trace_probe_log_err(orig_offset + 1, NO_PTR_STRCT);
return -EINVAL;
}
- tmp++;
-
- ctx->offset += tmp - arg;
- ret = parse_btf_arg(tmp, pcode, end, ctx);
+ ctx->offset = orig_offset + tmp - arg;
+ /* If it is nested, tmp points to the field name. */
+ if (nested)
+ ret = parse_btf_field(tmp, ctx->last_struct, pcode, end, ctx);
+ else
+ ret = parse_btf_arg(tmp, pcode, end, ctx);
return ret;
}
@@ -1638,6 +1700,11 @@ static int traceprobe_parse_probe_arg_body(const char *argv, ssize_t *size,
ctx);
if (ret < 0)
goto fail;
+ /* nested_level must be 0 here, otherwise there is a bug. */
+ if (WARN_ON_ONCE(ctx->nested_level)) {
+ ret = -EINVAL;
+ goto fail;
+ }
/* Update storing type if BTF is available */
if (IS_ENABLED(CONFIG_PROBE_EVENTS_BTF_ARGS) &&
diff --git a/kernel/trace/trace_probe.h b/kernel/trace/trace_probe.h
index aa72e2ffdd93..7d71925244e8 100644
--- a/kernel/trace/trace_probe.h
+++ b/kernel/trace/trace_probe.h
@@ -450,8 +450,11 @@ struct traceprobe_parse_context {
struct trace_probe *tp;
unsigned int flags;
int offset;
+ int nested_level;
};
+#define TRACEPROBE_MAX_NESTED_LEVEL 3
+
extern int traceprobe_parse_probe_arg(struct trace_probe *tp, int i,
const char *argv,
struct traceprobe_parse_context *ctx);
@@ -587,7 +590,9 @@ extern int traceprobe_define_arg_fields(struct trace_event_call *event_call,
C(TOO_MANY_ARGS, "Too many arguments are specified"), \
C(TOO_MANY_EARGS, "Too many entry arguments specified"), \
C(EVENT_TOO_BIG, "Event too big (too many fields?)"), \
- C(TYPECAST_NOT_EVENT, "Typecasts are only for eprobe fields"),
+ C(TYPECAST_NOT_EVENT, "Typecasts are only for eprobe fields"), \
+ C(TYPECAST_REQ_FIELD, "Typecast requires a field access"), \
+ C(TOO_MANY_NESTED, "Too many nested typecasts/dereferences"),
#undef C
#define C(a, b) TP_ERR_##a
^ permalink raw reply related
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox