Re: [PATCH 02/21] x86/unwinder: Handle stack overflows more gracefully
From: Borislav Petkov
Date: Mon Nov 27 2017 - 12:36:21 EST
On Mon, Nov 27, 2017 at 11:45:10AM +0100, Ingo Molnar wrote:
> From: Josh Poimboeuf <jpoimboe@xxxxxxxxxx>
>
> There are at least two unwinder bugs hindering the debugging of
> stack-overflow crashes:
>
> - It doesn't deal gracefully with the case where the stack overflows and
> the stack pointer itself isn't on a valid stack but the
> to-be-dereferenced data *is*.
>
> - The ORC oops dump code doesn't know how to print partial pt_regs, for the
> case where if we get an interrupt/exception in *early* entry code
> before the full pt_regs have been saved.
>
> Fix both issues.
>
> Signed-off-by: Josh Poimboeuf <jpoimboe@xxxxxxxxxx>
> Cc: Andy Lutomirski <luto@xxxxxxxxxx>
> Cc: Borislav Petkov <bpetkov@xxxxxxx>
> Cc: Brian Gerst <brgerst@xxxxxxxxx>
> Cc: Dave Hansen <dave.hansen@xxxxxxxxx>
> Cc: Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx>
> Cc: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
> Cc: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
> Link: 20171126024031.uxi4numpbjm5rlbr@treble">http://lkml.kernel.org/r/20171126024031.uxi4numpbjm5rlbr@treble
> Signed-off-by: Ingo Molnar <mingo@xxxxxxxxxx>
> ---
> arch/x86/include/asm/kdebug.h | 1 +
> arch/x86/include/asm/unwind.h | 7 ++++
> arch/x86/kernel/dumpstack.c | 32 ++++++++++++++++---
> arch/x86/kernel/process_64.c | 11 +++----
> arch/x86/kernel/stacktrace.c | 2 +-
> arch/x86/kernel/unwind_orc.c | 74 +++++++++++++++----------------------------
> 6 files changed, 66 insertions(+), 61 deletions(-)
>
> diff --git a/arch/x86/include/asm/kdebug.h b/arch/x86/include/asm/kdebug.h
> index f86a8caa561e..395c9631e000 100644
> --- a/arch/x86/include/asm/kdebug.h
> +++ b/arch/x86/include/asm/kdebug.h
> @@ -26,6 +26,7 @@ extern void die(const char *, struct pt_regs *,long);
> extern int __must_check __die(const char *, struct pt_regs *, long);
> extern void show_stack_regs(struct pt_regs *regs);
> extern void __show_regs(struct pt_regs *regs, int all);
> +extern void show_iret_regs(struct pt_regs *regs);
> extern unsigned long oops_begin(void);
> extern void oops_end(unsigned long, struct pt_regs *, int signr);
>
> diff --git a/arch/x86/include/asm/unwind.h b/arch/x86/include/asm/unwind.h
> index e9cc6fe1fc6f..5be2fb23825a 100644
> --- a/arch/x86/include/asm/unwind.h
> +++ b/arch/x86/include/asm/unwind.h
> @@ -7,6 +7,9 @@
> #include <asm/ptrace.h>
> #include <asm/stacktrace.h>
>
> +#define IRET_FRAME_OFFSET (offsetof(struct pt_regs, ip))
> +#define IRET_FRAME_SIZE (sizeof(struct pt_regs) - IRET_FRAME_OFFSET)
> +
> struct unwind_state {
> struct stack_info stack_info;
> unsigned long stack_mask;
> @@ -52,6 +55,10 @@ void unwind_start(struct unwind_state *state, struct task_struct *task,
> }
>
> #if defined(CONFIG_UNWINDER_ORC) || defined(CONFIG_UNWINDER_FRAME_POINTER)
> +/*
> + * WARNING: The entire pt_regs may not be safe to dereference. In some cases,
> + * only the iret registers are accessible. Use with caution!
^^^^^^^^^^^^^^^^^^
You mean the interrupt stack frame here, right?
> + */
> static inline struct pt_regs *unwind_get_entry_regs(struct unwind_state *state)
> {
> if (unwind_done(state))
> diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c
> index f13b4c00a5de..fc918744ad7d 100644
> --- a/arch/x86/kernel/dumpstack.c
> +++ b/arch/x86/kernel/dumpstack.c
> @@ -50,6 +50,28 @@ static void printk_stack_address(unsigned long address, int reliable,
> printk("%s %s%pB\n", log_lvl, reliable ? "" : "? ", (void *)address);
> }
>
> +void show_iret_regs(struct pt_regs *regs)
> +{
> + printk(KERN_DEFAULT "RIP: %04x:%pS\n", (int)regs->cs, (void *)regs->ip);
> + printk(KERN_DEFAULT "RSP: %04x:%016lx EFLAGS: %08lx", (int)regs->ss,
> + regs->sp, regs->flags);
> +}
> +
> +static void show_regs_safe(struct stack_info *info, struct pt_regs *regs)
> +{
> + if (on_stack(info, regs, sizeof(*regs)))
> + __show_regs(regs, 0);
> + else if (on_stack(info, (void *)regs + IRET_FRAME_OFFSET,
> + IRET_FRAME_SIZE)) {
> + /*
> + * When an interrupt or exception occurs in entry code, the
> + * full pt_regs might not have been saved yet. In that case
> + * just print the iret return frame.
Right, it is the interrupt stack frame. But "iret frame" is shorter so
let's stick to that :)
...
> @@ -283,42 +276,32 @@ static bool deref_stack_reg(struct unwind_state *state, unsigned long addr,
> return true;
> }
>
> -#define REGS_SIZE (sizeof(struct pt_regs))
> -#define SP_OFFSET (offsetof(struct pt_regs, sp))
> -#define IRET_REGS_SIZE (REGS_SIZE - offsetof(struct pt_regs, ip))
> -#define IRET_SP_OFFSET (SP_OFFSET - offsetof(struct pt_regs, ip))
> -
> static bool deref_stack_regs(struct unwind_state *state, unsigned long addr,
> - unsigned long *ip, unsigned long *sp, bool full)
> + unsigned long *ip, unsigned long *sp)
> {
> - size_t regs_size = full ? REGS_SIZE : IRET_REGS_SIZE;
> - size_t sp_offset = full ? SP_OFFSET : IRET_SP_OFFSET;
> - struct pt_regs *regs = (struct pt_regs *)(addr + regs_size - REGS_SIZE);
> -
> - if (IS_ENABLED(CONFIG_X86_64)) {
> - if (!stack_access_ok(state, addr, regs_size))
> - return false;
> -
> - *ip = regs->ip;
> - *sp = regs->sp;
> + struct pt_regs *regs = (struct pt_regs *)addr;
>
> - return true;
> - }
> + /* x86-32 support will be more complicated due to the ®s->sp hack */
> + BUILD_BUG_ON(IS_ENABLED(CONFIG_X86_32));
>
> - if (!stack_access_ok(state, addr, sp_offset))
> + if (!stack_access_ok(state, addr, sizeof(struct pt_regs)))
> return false;
>
> *ip = regs->ip;
> + *sp = regs->sp;
> + return true;
> +}
>
> - if (user_mode(regs)) {
> - if (!stack_access_ok(state, addr + sp_offset,
> - REGS_SIZE - SP_OFFSET))
> - return false;
> +static bool deref_stack_iret_regs(struct unwind_state *state, unsigned long addr,
> + unsigned long *ip, unsigned long *sp)
> +{
> + struct pt_regs *regs = (void *)addr - IRET_FRAME_OFFSET;
I guess those are traditionally done with container_of()...
But yeah, FWIW, looks ok to me:
Reviewed-by: Borislav Petkov <bp@xxxxxxx>
--
Regards/Gruss,
Boris.
Good mailing practices for 400: avoid top-posting and trim the reply.