Since the kretprobe replaces the function return address with
the kretprobe_trampoline on the stack, x86 unwinders can not
continue the stack unwinding at that point, or record
kretprobe_trampoline instead of correct return address.
To fix this issue, find the correct return address from task's
kretprobe_instances as like as function-graph tracer does.
With this fix, the unwinder can correctly unwind the stack
from kretprobe event on x86, as below.
<...>-135 [003] ...1 6.722338: r_full_proxy_read_0: (vfs_read+0xab/0x1a0 <- full_proxy_read)
<...>-135 [003] ...1 6.722377: <stack trace>
=> kretprobe_trace_func+0x209/0x2f0
=> kretprobe_dispatcher+0x4a/0x70
=> __kretprobe_trampoline_handler+0xca/0x150
=> trampoline_handler+0x44/0x70
=> kretprobe_trampoline+0x2a/0x50
=> vfs_read+0xab/0x1a0
=> ksys_read+0x5f/0xe0
=> do_syscall_64+0x33/0x40
=> entry_SYSCALL_64_after_hwframe+0x44/0xae
Reported-by: Daniel Xu <dxu@xxxxxxxxx>
Signed-off-by: Masami Hiramatsu <mhiramat@xxxxxxxxxx>
Suggested-by: Josh Poimboeuf <jpoimboe@xxxxxxxxxx>
---
Changes in v3:
- Split out the kretprobe side patch
- Fix build error when CONFIG_KRETPROBES=n.
Changes in v2:
- Remove kretprobe wrapper functions from unwind_orc.c
- Do not fixup state->ip when unwinding with regs because
kretprobe fixup instruction pointer before calling handler.
---
arch/x86/include/asm/unwind.h | 17 +++++++++++++++++
arch/x86/kernel/unwind_frame.c | 4 ++--
arch/x86/kernel/unwind_guess.c | 3 +--
arch/x86/kernel/unwind_orc.c | 6 +++---
4 files changed, 23 insertions(+), 7 deletions(-)
diff --git a/arch/x86/include/asm/unwind.h b/arch/x86/include/asm/unwind.h
index 70fc159ebe69..332aa6174b10 100644
--- a/arch/x86/include/asm/unwind.h
+++ b/arch/x86/include/asm/unwind.h
@@ -4,6 +4,7 @@
#include <linux/sched.h>
#include <linux/ftrace.h>
+#include <linux/kprobes.h>
#include <asm/ptrace.h>
#include <asm/stacktrace.h>
@@ -15,6 +16,7 @@ struct unwind_state {
unsigned long stack_mask;
struct task_struct *task;
int graph_idx;
+ struct llist_node *kr_cur;
bool error;
#if defined(CONFIG_UNWINDER_ORC)
bool signal, full_regs;
@@ -99,6 +101,21 @@ void unwind_module_init(struct module *mod, void *orc_ip, size_t orc_ip_size,
void *orc, size_t orc_size) {}
#endif
+/* Recover the return address modified by instrumentation (e.g. kretprobe) */
+static inline
+unsigned long unwind_recover_ret_addr(struct unwind_state *state,
+ unsigned long addr, unsigned long *addr_p)
+{
+ unsigned long ret;
+
+ ret = ftrace_graph_ret_addr(state->task, &state->graph_idx,
+ addr, addr_p);
+ if (is_kretprobe_trampoline(ret))
+ ret = kretprobe_find_ret_addr(state->task, addr_p,
+ &state->kr_cur);
+ return ret;
+}
+
/*
* 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
diff --git a/arch/x86/kernel/unwind_frame.c b/arch/x86/kernel/unwind_frame.c
index d7c44b257f7f..24e33b44b2be 100644
--- a/arch/x86/kernel/unwind_frame.c
+++ b/arch/x86/kernel/unwind_frame.c
@@ -3,6 +3,7 @@
#include <linux/sched/task.h>
#include <linux/sched/task_stack.h>
#include <linux/interrupt.h>
+#include <linux/kprobes.h>
#include <asm/sections.h>
#include <asm/ptrace.h>
#include <asm/bitops.h>
@@ -240,8 +241,7 @@ static bool update_stack_state(struct unwind_state *state,
else {
addr_p = unwind_get_return_address_ptr(state);
addr = READ_ONCE_TASK_STACK(state->task, *addr_p);
- state->ip = ftrace_graph_ret_addr(state->task, &state->graph_idx,
- addr, addr_p);
+ state->ip = unwind_recover_ret_addr(state, addr, addr_p);
}
/* Save the original stack pointer for unwind_dump(): */
diff --git a/arch/x86/kernel/unwind_guess.c b/arch/x86/kernel/unwind_guess.c
index c49f10ffd8cd..884d68a6e714 100644
--- a/arch/x86/kernel/unwind_guess.c
+++ b/arch/x86/kernel/unwind_guess.c
@@ -15,8 +15,7 @@ unsigned long unwind_get_return_address(struct unwind_state *state)
addr = READ_ONCE_NOCHECK(*state->sp);
- return ftrace_graph_ret_addr(state->task, &state->graph_idx,
- addr, state->sp);
+ return unwind_recover_ret_addr(state, addr, state->sp);
}
EXPORT_SYMBOL_GPL(unwind_get_return_address);
diff --git a/arch/x86/kernel/unwind_orc.c b/arch/x86/kernel/unwind_orc.c
index a1202536fc57..839a0698342a 100644
--- a/arch/x86/kernel/unwind_orc.c
+++ b/arch/x86/kernel/unwind_orc.c
@@ -2,6 +2,7 @@
#include <linux/objtool.h>
#include <linux/module.h>
#include <linux/sort.h>
+#include <linux/kprobes.h>
#include <asm/ptrace.h>
#include <asm/stacktrace.h>
#include <asm/unwind.h>
@@ -534,9 +535,8 @@ bool unwind_next_frame(struct unwind_state *state)
if (!deref_stack_reg(state, ip_p, &state->ip))
goto err;
- state->ip = ftrace_graph_ret_addr(state->task, &state->graph_idx,
- state->ip, (void *)ip_p);
-
+ state->ip = unwind_recover_ret_addr(state, state->ip,
+ (unsigned long *)ip_p);
state->sp = sp;
state->regs = NULL;
state->prev_regs = NULL;
