| Message ID | 4e7adb96a576c6ff12d6cc2a972b2bf44ed2319a.1466036668.git.luto@kernel.org (mailing list archive) |
|---|---|
| State | New, archived |
| Headers | show |
On Wed, Jun 15, 2016 at 05:28:30PM -0700, Andy Lutomirski wrote: > If we call do_exit with a clean stack, we greatly reduce the risk of > recursive oopses due to stack overflow in do_exit, and we allow > do_exit to work even if we OOPS from an IST stack. The latter gives > us a much better chance of surviving long enough after we detect a > stack overflow to write out our logs. > > I intentionally separated this from the preceding patch that > disables do_exit-on-OOPS on IST stacks. This way, if we need to > revert this patch, we still end up in an acceptable state wrt stack > overflow handling. > > Signed-off-by: Andy Lutomirski <luto@kernel.org> > --- > arch/x86/entry/entry_32.S | 11 +++++++++++ > arch/x86/entry/entry_64.S | 11 +++++++++++ > arch/x86/kernel/dumpstack.c | 13 +++++++++---- > 3 files changed, 31 insertions(+), 4 deletions(-) > > diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S > index 983e5d3a0d27..1499db695a88 100644 > --- a/arch/x86/entry/entry_32.S > +++ b/arch/x86/entry/entry_32.S > @@ -1153,3 +1153,14 @@ ENTRY(async_page_fault) > jmp error_code > END(async_page_fault) > #endif > + > +ENTRY(rewind_stack_do_exit) > + /* Prevent any naive code from trying to unwind to our caller. */ > + xorl %ebp, %ebp > + > + movl PER_CPU_VAR(cpu_current_top_of_stack), %esi > + leal -TOP_OF_KERNEL_STACK_PADDING-PT_OLDSS(%esi), %esp > + > + call do_exit > +1: jmp 1b > +END(rewind_stack_do_exit) > diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S > index 9ee0da1807ed..394cad73e890 100644 > --- a/arch/x86/entry/entry_64.S > +++ b/arch/x86/entry/entry_64.S > @@ -1423,3 +1423,14 @@ ENTRY(ignore_sysret) > mov $-ENOSYS, %eax > sysret > END(ignore_sysret) > + > +ENTRY(rewind_stack_do_exit) > + /* Prevent any naive code from trying to unwind to our caller. */ > + xorl %ebp, %ebp > + > + movq PER_CPU_VAR(cpu_current_top_of_stack), %rax > + leaq -TOP_OF_KERNEL_STACK_PADDING-SS(%rax), %rsp I think this should be: leaq -TOP_OF_KERNEL_STACK_PADDING-SIZEOF_PTREGS, %rsp That way when it calls do_exit(), the stack frame will be placed at the conventional spot where a smart unwinder would expect to find it.
On Thu, Jun 16, 2016 at 10:50 AM, Josh Poimboeuf <jpoimboe@redhat.com> wrote: > On Wed, Jun 15, 2016 at 05:28:30PM -0700, Andy Lutomirski wrote: >> If we call do_exit with a clean stack, we greatly reduce the risk of >> recursive oopses due to stack overflow in do_exit, and we allow >> do_exit to work even if we OOPS from an IST stack. The latter gives >> us a much better chance of surviving long enough after we detect a >> stack overflow to write out our logs. >> >> I intentionally separated this from the preceding patch that >> disables do_exit-on-OOPS on IST stacks. This way, if we need to >> revert this patch, we still end up in an acceptable state wrt stack >> overflow handling. >> >> Signed-off-by: Andy Lutomirski <luto@kernel.org> >> --- >> arch/x86/entry/entry_32.S | 11 +++++++++++ >> arch/x86/entry/entry_64.S | 11 +++++++++++ >> arch/x86/kernel/dumpstack.c | 13 +++++++++---- >> 3 files changed, 31 insertions(+), 4 deletions(-) >> >> diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S >> index 983e5d3a0d27..1499db695a88 100644 >> --- a/arch/x86/entry/entry_32.S >> +++ b/arch/x86/entry/entry_32.S >> @@ -1153,3 +1153,14 @@ ENTRY(async_page_fault) >> jmp error_code >> END(async_page_fault) >> #endif >> + >> +ENTRY(rewind_stack_do_exit) >> + /* Prevent any naive code from trying to unwind to our caller. */ >> + xorl %ebp, %ebp >> + >> + movl PER_CPU_VAR(cpu_current_top_of_stack), %esi >> + leal -TOP_OF_KERNEL_STACK_PADDING-PT_OLDSS(%esi), %esp >> + >> + call do_exit >> +1: jmp 1b >> +END(rewind_stack_do_exit) >> diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S >> index 9ee0da1807ed..394cad73e890 100644 >> --- a/arch/x86/entry/entry_64.S >> +++ b/arch/x86/entry/entry_64.S >> @@ -1423,3 +1423,14 @@ ENTRY(ignore_sysret) >> mov $-ENOSYS, %eax >> sysret >> END(ignore_sysret) >> + >> +ENTRY(rewind_stack_do_exit) >> + /* Prevent any naive code from trying to unwind to our caller. */ >> + xorl %ebp, %ebp >> + >> + movq PER_CPU_VAR(cpu_current_top_of_stack), %rax >> + leaq -TOP_OF_KERNEL_STACK_PADDING-SS(%rax), %rsp > > I think this should be: > > leaq -TOP_OF_KERNEL_STACK_PADDING-SIZEOF_PTREGS, %rsp > > That way when it calls do_exit(), the stack frame will be placed at the > conventional spot where a smart unwinder would expect to find it. Whoops! --Andy
diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S index 983e5d3a0d27..1499db695a88 100644 --- a/arch/x86/entry/entry_32.S +++ b/arch/x86/entry/entry_32.S @@ -1153,3 +1153,14 @@ ENTRY(async_page_fault) jmp error_code END(async_page_fault) #endif + +ENTRY(rewind_stack_do_exit) + /* Prevent any naive code from trying to unwind to our caller. */ + xorl %ebp, %ebp + + movl PER_CPU_VAR(cpu_current_top_of_stack), %esi + leal -TOP_OF_KERNEL_STACK_PADDING-PT_OLDSS(%esi), %esp + + call do_exit +1: jmp 1b +END(rewind_stack_do_exit) diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S index 9ee0da1807ed..394cad73e890 100644 --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -1423,3 +1423,14 @@ ENTRY(ignore_sysret) mov $-ENOSYS, %eax sysret END(ignore_sysret) + +ENTRY(rewind_stack_do_exit) + /* Prevent any naive code from trying to unwind to our caller. */ + xorl %ebp, %ebp + + movq PER_CPU_VAR(cpu_current_top_of_stack), %rax + leaq -TOP_OF_KERNEL_STACK_PADDING-SS(%rax), %rsp + + call do_exit +1: jmp 1b +END(rewind_stack_do_exit) diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c index 36effb39c9c9..d4d085e27d04 100644 --- a/arch/x86/kernel/dumpstack.c +++ b/arch/x86/kernel/dumpstack.c @@ -228,6 +228,8 @@ unsigned long oops_begin(void) EXPORT_SYMBOL_GPL(oops_begin); NOKPROBE_SYMBOL(oops_begin); +extern void __noreturn rewind_stack_do_exit(int signr); + void oops_end(unsigned long flags, struct pt_regs *regs, int signr) { if (regs && kexec_should_crash(current)) @@ -247,12 +249,15 @@ void oops_end(unsigned long flags, struct pt_regs *regs, int signr) return; if (in_interrupt()) panic("Fatal exception in interrupt"); - if (((current_stack_pointer() ^ (current_top_of_stack() - 1)) - & ~(THREAD_SIZE - 1)) != 0) - panic("Fatal exception on special stack"); if (panic_on_oops) panic("Fatal exception"); - do_exit(signr); + + /* + * We're not going to return, but we might be on an IST stack or + * have very little stack space left. Rewind the stack and kill + * the task. + */ + rewind_stack_do_exit(signr); } NOKPROBE_SYMBOL(oops_end);
If we call do_exit with a clean stack, we greatly reduce the risk of recursive oopses due to stack overflow in do_exit, and we allow do_exit to work even if we OOPS from an IST stack. The latter gives us a much better chance of surviving long enough after we detect a stack overflow to write out our logs. I intentionally separated this from the preceding patch that disables do_exit-on-OOPS on IST stacks. This way, if we need to revert this patch, we still end up in an acceptable state wrt stack overflow handling. Signed-off-by: Andy Lutomirski <luto@kernel.org> --- arch/x86/entry/entry_32.S | 11 +++++++++++ arch/x86/entry/entry_64.S | 11 +++++++++++ arch/x86/kernel/dumpstack.c | 13 +++++++++---- 3 files changed, 31 insertions(+), 4 deletions(-)