[PATCH 17/19] x86/entry/dumpstack: encode pt_regs pointer in frame pointer
From: Josh Poimboeuf
Date: Thu Jul 21 2016 - 17:22:37 EST
With frame pointers, when a task is interrupted, its stack is no longer
completely reliable because the function could have been interrupted
before it had a chance to save the previous frame pointer on the stack.
So the caller of the interrupted function could get skipped by a stack
trace.
This is problematic for live patching, which needs to know whether a
stack trace of a sleeping task can be relied upon. There's currently no
way to detect if a sleeping task was interrupted by a page fault
exception or preemption before it went to sleep.
Another issue is that when dumping the stack of an interrupted task, the
unwinder has no way of knowing where the saved pt_regs registers are, so
it can't print them.
This solves those issues by encoding the pt_regs pointer in the frame
pointer on entry from an interrupt or an exception. The frame pointer
unwinder is also updated to decode it.
Suggested-by: Andy Lutomirski <luto@xxxxxxxxxxxxxx>
Signed-off-by: Josh Poimboeuf <jpoimboe@xxxxxxxxxx>
---
arch/x86/entry/calling.h | 21 ++++++++++++++++++++
arch/x86/entry/entry_64.S | 7 ++++++-
arch/x86/include/asm/unwind.h | 11 +++++++++++
arch/x86/kernel/unwind_frame.c | 44 ++++++++++++++++++++++++++++++++++++++++++
4 files changed, 82 insertions(+), 1 deletion(-)
diff --git a/arch/x86/entry/calling.h b/arch/x86/entry/calling.h
index 9a9e588..ff5a5a3 100644
--- a/arch/x86/entry/calling.h
+++ b/arch/x86/entry/calling.h
@@ -201,6 +201,27 @@ For 32-bit we have the following conventions - kernel is built with
.byte 0xf1
.endm
+ /*
+ * This is a sneaky trick to help the unwinder find pt_regs on the
+ * stack. The frame pointer is replaced with an encoded pointer to
+ * pt_regs. The encoding is just a clearing of the highest-order bit,
+ * which makes it an invalid address and is also a signal to the
+ * unwinder that it's a pt_regs pointer in disguise.
+ *
+ * NOTE: This must be called *after* SAVE_EXTRA_REGS because it
+ * corrupts rbp.
+ */
+.macro ENCODE_FRAME_POINTER ptregs_offset=0
+#ifdef CONFIG_FRAME_POINTER
+ .if \ptregs_offset
+ leaq \ptregs_offset(%rsp), %rbp
+ .else
+ mov %rsp, %rbp
+ .endif
+ btr $63, %rbp
+#endif
+.endm
+
#endif /* CONFIG_X86_64 */
/*
diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S
index b846875..7f492e2 100644
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -431,6 +431,7 @@ END(irq_entries_start)
ALLOC_PT_GPREGS_ON_STACK
SAVE_C_REGS
SAVE_EXTRA_REGS
+ ENCODE_FRAME_POINTER
testb $3, CS(%rsp)
jz 1f
@@ -893,6 +894,7 @@ ENTRY(xen_failsafe_callback)
ALLOC_PT_GPREGS_ON_STACK
SAVE_C_REGS
SAVE_EXTRA_REGS
+ ENCODE_FRAME_POINTER
jmp error_exit
END(xen_failsafe_callback)
@@ -936,6 +938,7 @@ ENTRY(paranoid_entry)
cld
SAVE_C_REGS 8
SAVE_EXTRA_REGS 8
+ ENCODE_FRAME_POINTER 8
movl $1, %ebx
movl $MSR_GS_BASE, %ecx
rdmsr
@@ -983,6 +986,7 @@ ENTRY(error_entry)
cld
SAVE_C_REGS 8
SAVE_EXTRA_REGS 8
+ ENCODE_FRAME_POINTER 8
xorl %ebx, %ebx
testb $3, CS+8(%rsp)
jz .Lerror_kernelspace
@@ -1165,6 +1169,7 @@ ENTRY(nmi)
pushq %r13 /* pt_regs->r13 */
pushq %r14 /* pt_regs->r14 */
pushq %r15 /* pt_regs->r15 */
+ ENCODE_FRAME_POINTER
/*
* At this point we no longer need to worry about stack damage
@@ -1182,7 +1187,7 @@ ENTRY(nmi)
* do_nmi doesn't modify pt_regs.
*/
SWAPGS
- jmp restore_c_regs_and_iret
+ jmp restore_regs_and_iret
.Lnmi_from_kernel:
/*
diff --git a/arch/x86/include/asm/unwind.h b/arch/x86/include/asm/unwind.h
index 61c6e95..6d461ee 100644
--- a/arch/x86/include/asm/unwind.h
+++ b/arch/x86/include/asm/unwind.h
@@ -14,6 +14,7 @@ struct unwind_state {
int graph_idx;
#ifdef CONFIG_FRAME_POINTER
unsigned long *bp;
+ struct pt_regs *regs;
#endif
};
@@ -35,6 +36,11 @@ static inline unsigned long *unwind_get_return_address_ptr(struct unwind_state *
unsigned long unwind_get_return_address(struct unwind_state *state);
+static inline struct pt_regs *unwind_get_entry_regs(struct unwind_state *state)
+{
+ return state->regs;
+}
+
#else /* !CONFIG_FRAME_POINTER */
static inline unsigned long *unwind_get_return_address_ptr(struct unwind_state *state)
@@ -50,6 +56,11 @@ static inline unsigned long unwind_get_return_address(struct unwind_state *state
return *state->sp;
}
+static inline struct pt_regs *unwind_get_entry_regs(struct unwind_state *state)
+{
+ return NULL;
+}
+
#endif /* CONFIG_FRAME_POINTER */
static inline unsigned long *unwind_get_stack_ptr(struct unwind_state *state)
diff --git a/arch/x86/kernel/unwind_frame.c b/arch/x86/kernel/unwind_frame.c
index 1234480..2536353 100644
--- a/arch/x86/kernel/unwind_frame.c
+++ b/arch/x86/kernel/unwind_frame.c
@@ -18,6 +18,31 @@ unsigned long unwind_get_return_address(struct unwind_state *state)
}
EXPORT_SYMBOL_GPL(unwind_get_return_address);
+/*
+ * This determines if the frame pointer actually contains an encoded pointer to
+ * pt_regs on the stack. See ENCODE_FRAME_POINTER.
+ */
+static struct pt_regs *decode_frame_pointer(struct unwind_state *state,
+ unsigned long *bp)
+{
+ struct pt_regs *regs = (struct pt_regs *)bp;
+ unsigned long *task_begin = task_stack_page(state->task);
+ unsigned long *task_end = task_stack_page(state->task) + THREAD_SIZE;
+
+ if (test_and_set_bit(BITS_PER_LONG - 1, (unsigned long *)®s))
+ return NULL;
+
+ if (on_stack(&state->stack_info, regs, sizeof(*regs)))
+ return regs;
+
+ if ((unsigned long *)regs >= task_begin &&
+ (unsigned long *)regs < task_end &&
+ (unsigned long *)(regs + 1) <= task_end)
+ return regs;
+
+ return NULL;
+}
+
static unsigned long *update_stack_state(struct unwind_state *state, void *addr,
size_t len)
{
@@ -58,14 +83,32 @@ static bool unwind_next_frame_bp(struct unwind_state *state, unsigned long *bp)
return true;
}
+static bool unwind_next_frame_regs(struct unwind_state *state,
+ struct pt_regs *regs)
+{
+ update_stack_state(state, regs, sizeof(*regs));
+ if (state->stack_info.type == STACK_TYPE_UNKNOWN)
+ return false;
+
+ state->regs = regs;
+
+ return unwind_next_frame_bp(state, (unsigned long *)regs->bp);
+}
+
bool unwind_next_frame(struct unwind_state *state)
{
+ struct pt_regs *regs;
unsigned long *bp;
+ state->regs = NULL;
+
if (unwind_done(state))
return false;
bp = (unsigned long *)*state->bp;
+ regs = decode_frame_pointer(state, bp);
+ if (regs)
+ return unwind_next_frame_regs(state, regs);
return unwind_next_frame_bp(state, bp);
}
@@ -79,6 +122,7 @@ void __unwind_start(struct unwind_state *state, struct task_struct *task,
state->task = task;
state->sp = sp;
state->bp = get_frame_pointer(task, regs);
+ state->regs = NULL;
get_stack_info(sp, state->task, &state->stack_info, &state->stack_mask);
--
2.7.4