Re: [PATCH v3 2/2] x86/refcount: Implement fast refcount overflow protection
diff mbox

Message ID 20170509170812.uyfkvblwofhxpk4e@treble
State New
Headers show

Commit Message

Josh Poimboeuf May 9, 2017, 5:08 p.m. UTC
On Mon, May 08, 2017 at 08:58:29PM -0500, Josh Poimboeuf wrote:
> On Mon, May 08, 2017 at 04:31:11PM -0700, Kees Cook wrote:
> > On Mon, May 8, 2017 at 3:53 PM, Josh Poimboeuf <jpoimboe@redhat.com> wrote:
> > > On Mon, May 08, 2017 at 12:32:52PM -0700, Kees Cook wrote:
> > >> +#define REFCOUNT_EXCEPTION                           \
> > >> +     "movl $0x7fffffff, %[counter]\n\t"              \
> > >> +     "int $"__stringify(X86_REFCOUNT_VECTOR)"\n"     \
> > >> +     "0:\n\t"                                        \
> > >> +     _ASM_EXTABLE(0b, 0b)
> > >
> > > Despite the objtool warnings going away, this still uses the exception
> > > table in a new way, which will confuse objtool.  I need to do some more
> > > thinking about the best way to fix it, either as a change to your patch
> > > or a change to objtool.
> > 
> > In that it's not a "true" exception?
> 
> Right.  And also that it doesn't need the "fixup" since it would return
> to the same address anyway.

How about the following on top of your patch?  It uses #UD (invalid
opcode).  Notice it's mostly code deletions :-)

Comments

Kees Cook May 9, 2017, 5:29 p.m. UTC | #1
On Tue, May 9, 2017 at 10:08 AM, Josh Poimboeuf <jpoimboe@redhat.com> wrote:
> On Mon, May 08, 2017 at 08:58:29PM -0500, Josh Poimboeuf wrote:
>> On Mon, May 08, 2017 at 04:31:11PM -0700, Kees Cook wrote:
>> > On Mon, May 8, 2017 at 3:53 PM, Josh Poimboeuf <jpoimboe@redhat.com> wrote:
>> > > On Mon, May 08, 2017 at 12:32:52PM -0700, Kees Cook wrote:
>> > >> +#define REFCOUNT_EXCEPTION                           \
>> > >> +     "movl $0x7fffffff, %[counter]\n\t"              \
>> > >> +     "int $"__stringify(X86_REFCOUNT_VECTOR)"\n"     \
>> > >> +     "0:\n\t"                                        \
>> > >> +     _ASM_EXTABLE(0b, 0b)
>> > >
>> > > Despite the objtool warnings going away, this still uses the exception
>> > > table in a new way, which will confuse objtool.  I need to do some more
>> > > thinking about the best way to fix it, either as a change to your patch
>> > > or a change to objtool.
>> >
>> > In that it's not a "true" exception?
>>
>> Right.  And also that it doesn't need the "fixup" since it would return
>> to the same address anyway.
>
> How about the following on top of your patch?  It uses #UD (invalid
> opcode).  Notice it's mostly code deletions :-)

Hah, I wrote this patch almost exactly last night, but hadn't had a
chance to send it out. :)

I ended up defining a new exception handler, which means nothing
special in the generic trap code. I didn't send it out because it was
still using a jns instead of js, and I was pondering if I wanted to
reintroduce the text section jump just to gain the initial benefit of
forward-branch-not-taken optimization...

> diff --git a/arch/x86/include/asm/refcount.h b/arch/x86/include/asm/refcount.h
> index 6e8bbd7..653a985 100644
> --- a/arch/x86/include/asm/refcount.h
> +++ b/arch/x86/include/asm/refcount.h
> @@ -8,15 +8,16 @@
>   */
>  #include <linux/refcount.h>
>  #include <asm/irq_vectors.h>
> +#include <asm/bug.h>
>
>  #define REFCOUNT_EXCEPTION                             \
>         "movl $0x7fffffff, %[counter]\n\t"              \
> -       "int $"__stringify(X86_REFCOUNT_VECTOR)"\n"     \
> -       "0:\n\t"                                        \
> -       _ASM_EXTABLE(0b, 0b)
> +       "1:\t" ASM_UD0 "\n"                             \
> +       "2:\n\t"                                        \
> +       _ASM_EXTABLE(1b, 2b)

I used _ASM_EXTABLE_REFCOUNT(1b, 2b) here, with
arch/x86/include/asm/asm.h adding:

+# define _ASM_EXTABLE_REFCOUNT(from, to)                       \
+       _ASM_EXTABLE_HANDLE(from, to, ex_handler_refcount)

> diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
> index 0b2dbcc..7de95b7 100644
> --- a/arch/x86/kernel/traps.c
> +++ b/arch/x86/kernel/traps.c
> @@ -220,8 +220,8 @@ do_trap_no_signal(struct task_struct *tsk, int trapnr, char *str,
>         if (!user_mode(regs)) {
>                 if (fixup_exception(regs, trapnr)) {
>                         if (IS_ENABLED(CONFIG_FAST_REFCOUNT) &&
> -                           trapnr == X86_REFCOUNT_VECTOR)
> -                               refcount_error_report(regs, str);
> +                           trapnr == X86_TRAP_UD)
> +                               refcount_error_report(regs);
>
>                         return 0;
>                 }

And then I could leave out this hunk, instead adding this to
arch/x86/mm/extable.c:

+bool ex_handler_refcount(const struct exception_table_entry *fixup,
+                        struct pt_regs *regs, int trapnr)
+{
+       regs->ip = ex_fixup_addr(fixup);
+       refcount_error_report(regs, "overflow");
+       return true;
+}
+EXPORT_SYMBOL_GPL(ex_handler_refcount);

After looking at the assembly output, the "movl" instructions can be
various sizes, depending on where %[counter] lives, so I'm also
considering returning to using PaX's "lea", but I'm not sure the
benefit would be very large.

-Kees
Josh Poimboeuf May 9, 2017, 5:44 p.m. UTC | #2
On Tue, May 09, 2017 at 10:29:16AM -0700, Kees Cook wrote:
> On Tue, May 9, 2017 at 10:08 AM, Josh Poimboeuf <jpoimboe@redhat.com> wrote:
> > On Mon, May 08, 2017 at 08:58:29PM -0500, Josh Poimboeuf wrote:
> >> On Mon, May 08, 2017 at 04:31:11PM -0700, Kees Cook wrote:
> >> > On Mon, May 8, 2017 at 3:53 PM, Josh Poimboeuf <jpoimboe@redhat.com> wrote:
> >> > > On Mon, May 08, 2017 at 12:32:52PM -0700, Kees Cook wrote:
> >> > >> +#define REFCOUNT_EXCEPTION                           \
> >> > >> +     "movl $0x7fffffff, %[counter]\n\t"              \
> >> > >> +     "int $"__stringify(X86_REFCOUNT_VECTOR)"\n"     \
> >> > >> +     "0:\n\t"                                        \
> >> > >> +     _ASM_EXTABLE(0b, 0b)
> >> > >
> >> > > Despite the objtool warnings going away, this still uses the exception
> >> > > table in a new way, which will confuse objtool.  I need to do some more
> >> > > thinking about the best way to fix it, either as a change to your patch
> >> > > or a change to objtool.
> >> >
> >> > In that it's not a "true" exception?
> >>
> >> Right.  And also that it doesn't need the "fixup" since it would return
> >> to the same address anyway.
> >
> > How about the following on top of your patch?  It uses #UD (invalid
> > opcode).  Notice it's mostly code deletions :-)
> 
> Hah, I wrote this patch almost exactly last night, but hadn't had a
> chance to send it out. :)
> 
> I ended up defining a new exception handler, which means nothing
> special in the generic trap code. I didn't send it out because it was
> still using a jns instead of js, and I was pondering if I wanted to
> reintroduce the text section jump just to gain the initial benefit of
> forward-branch-not-taken optimization...
> 
> > diff --git a/arch/x86/include/asm/refcount.h b/arch/x86/include/asm/refcount.h
> > index 6e8bbd7..653a985 100644
> > --- a/arch/x86/include/asm/refcount.h
> > +++ b/arch/x86/include/asm/refcount.h
> > @@ -8,15 +8,16 @@
> >   */
> >  #include <linux/refcount.h>
> >  #include <asm/irq_vectors.h>
> > +#include <asm/bug.h>
> >
> >  #define REFCOUNT_EXCEPTION                             \
> >         "movl $0x7fffffff, %[counter]\n\t"              \
> > -       "int $"__stringify(X86_REFCOUNT_VECTOR)"\n"     \
> > -       "0:\n\t"                                        \
> > -       _ASM_EXTABLE(0b, 0b)
> > +       "1:\t" ASM_UD0 "\n"                             \
> > +       "2:\n\t"                                        \
> > +       _ASM_EXTABLE(1b, 2b)
> 
> I used _ASM_EXTABLE_REFCOUNT(1b, 2b) here, with
> arch/x86/include/asm/asm.h adding:
> 
> +# define _ASM_EXTABLE_REFCOUNT(from, to)                       \
> +       _ASM_EXTABLE_HANDLE(from, to, ex_handler_refcount)
> 
> > diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
> > index 0b2dbcc..7de95b7 100644
> > --- a/arch/x86/kernel/traps.c
> > +++ b/arch/x86/kernel/traps.c
> > @@ -220,8 +220,8 @@ do_trap_no_signal(struct task_struct *tsk, int trapnr, char *str,
> >         if (!user_mode(regs)) {
> >                 if (fixup_exception(regs, trapnr)) {
> >                         if (IS_ENABLED(CONFIG_FAST_REFCOUNT) &&
> > -                           trapnr == X86_REFCOUNT_VECTOR)
> > -                               refcount_error_report(regs, str);
> > +                           trapnr == X86_TRAP_UD)
> > +                               refcount_error_report(regs);
> >
> >                         return 0;
> >                 }
> 
> And then I could leave out this hunk, instead adding this to
> arch/x86/mm/extable.c:
> 
> +bool ex_handler_refcount(const struct exception_table_entry *fixup,
> +                        struct pt_regs *regs, int trapnr)
> +{
> +       regs->ip = ex_fixup_addr(fixup);
> +       refcount_error_report(regs, "overflow");
> +       return true;
> +}
> +EXPORT_SYMBOL_GPL(ex_handler_refcount);
> 
> After looking at the assembly output, the "movl" instructions can be
> various sizes, depending on where %[counter] lives, so I'm also
> considering returning to using PaX's "lea", but I'm not sure the
> benefit would be very large.

Good, your patch sounds better than mine :-)

Patch
diff mbox

diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S
index bba6976..50bc269 100644
--- a/arch/x86/entry/entry_32.S
+++ b/arch/x86/entry/entry_32.S
@@ -789,15 +789,6 @@  ENTRY(spurious_interrupt_bug)
 	jmp	common_exception
 END(spurious_interrupt_bug)
 
-#ifdef CONFIG_FAST_REFCOUNT
-ENTRY(refcount_error)
-	ASM_CLAC
-	pushl   $0
-	pushl   $do_refcount_error
-	jmp     common_exception
-ENDPROC(refcount_error)
-#endif
-
 #ifdef CONFIG_XEN
 ENTRY(xen_hypervisor_callback)
 	pushl	$-1				/* orig_ax = -1 => not a system call */
diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S
index 783045d..607d72c 100644
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -855,9 +855,6 @@  idtentry coprocessor_error		do_coprocessor_error		has_error_code=0
 idtentry alignment_check		do_alignment_check		has_error_code=1
 idtentry simd_coprocessor_error		do_simd_coprocessor_error	has_error_code=0
 
-#ifdef CONFIG_FAST_REFCOUNT
-idtentry refcount_error			do_refcount_error		has_error_code=0
-#endif
 
 	/*
 	 * Reload gs selector with exception handling
diff --git a/arch/x86/include/asm/irq_vectors.h b/arch/x86/include/asm/irq_vectors.h
index d117776..6ca9fd6 100644
--- a/arch/x86/include/asm/irq_vectors.h
+++ b/arch/x86/include/asm/irq_vectors.h
@@ -48,9 +48,6 @@ 
 
 #define IA32_SYSCALL_VECTOR		0x80
 
-/* Refcount overflow reporting exception. */
-#define X86_REFCOUNT_VECTOR		0x81
-
 /*
  * Vectors 0x30-0x3f are used for ISA interrupts.
  *   round up to the next 16-vector boundary
diff --git a/arch/x86/include/asm/refcount.h b/arch/x86/include/asm/refcount.h
index 6e8bbd7..653a985 100644
--- a/arch/x86/include/asm/refcount.h
+++ b/arch/x86/include/asm/refcount.h
@@ -8,15 +8,16 @@ 
  */
 #include <linux/refcount.h>
 #include <asm/irq_vectors.h>
+#include <asm/bug.h>
 
 #define REFCOUNT_EXCEPTION				\
 	"movl $0x7fffffff, %[counter]\n\t"		\
-	"int $"__stringify(X86_REFCOUNT_VECTOR)"\n"	\
-	"0:\n\t"					\
-	_ASM_EXTABLE(0b, 0b)
+	"1:\t" ASM_UD0 "\n"				\
+	"2:\n\t"					\
+	_ASM_EXTABLE(1b, 2b)
 
 #define REFCOUNT_CHECK					\
-	"jns 0f\n\t"					\
+	"jns 2f\n\t"					\
 	REFCOUNT_EXCEPTION
 
 static __always_inline void refcount_add(unsigned int i, refcount_t *r)
diff --git a/arch/x86/include/asm/traps.h b/arch/x86/include/asm/traps.h
index e4d8db7..01fd0a7 100644
--- a/arch/x86/include/asm/traps.h
+++ b/arch/x86/include/asm/traps.h
@@ -38,10 +38,6 @@  asmlinkage void machine_check(void);
 #endif /* CONFIG_X86_MCE */
 asmlinkage void simd_coprocessor_error(void);
 
-#ifdef CONFIG_FAST_REFCOUNT
-asmlinkage void refcount_error(void);
-#endif
-
 #ifdef CONFIG_TRACING
 asmlinkage void trace_page_fault(void);
 #define trace_stack_segment stack_segment
@@ -58,7 +54,6 @@  asmlinkage void trace_page_fault(void);
 #define trace_alignment_check alignment_check
 #define trace_simd_coprocessor_error simd_coprocessor_error
 #define trace_async_page_fault async_page_fault
-#define trace_refcount_error refcount_error
 #endif
 
 dotraplinkage void do_divide_error(struct pt_regs *, long);
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index 0b2dbcc..7de95b7 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -220,8 +220,8 @@  do_trap_no_signal(struct task_struct *tsk, int trapnr, char *str,
 	if (!user_mode(regs)) {
 		if (fixup_exception(regs, trapnr)) {
 			if (IS_ENABLED(CONFIG_FAST_REFCOUNT) &&
-			    trapnr == X86_REFCOUNT_VECTOR)
-				refcount_error_report(regs, str);
+			    trapnr == X86_TRAP_UD)
+				refcount_error_report(regs);
 
 			return 0;
 		}
@@ -332,10 +332,6 @@  DO_ERROR(X86_TRAP_NP,     SIGBUS,  "segment not present",	segment_not_present)
 DO_ERROR(X86_TRAP_SS,     SIGBUS,  "stack segment",		stack_segment)
 DO_ERROR(X86_TRAP_AC,     SIGBUS,  "alignment check",		alignment_check)
 
-#ifdef CONFIG_FAST_REFCOUNT
-DO_ERROR(X86_REFCOUNT_VECTOR, SIGILL, "refcount overflow",	refcount_error)
-#endif
-
 #ifdef CONFIG_VMAP_STACK
 __visible void __noreturn handle_stack_overflow(const char *message,
 						struct pt_regs *regs,
@@ -1026,11 +1022,6 @@  void __init trap_init(void)
 	set_bit(IA32_SYSCALL_VECTOR, used_vectors);
 #endif
 
-#ifdef CONFIG_FAST_REFCOUNT
-	set_intr_gate(X86_REFCOUNT_VECTOR, refcount_error);
-	set_bit(X86_REFCOUNT_VECTOR, used_vectors);
-#endif
-
 	/*
 	 * Set the IDT descriptor to a fixed read-only location, so that the
 	 * "sidt" instruction will not leak the location of the kernel, and
diff --git a/include/linux/kernel.h b/include/linux/kernel.h
index 94f87d5..53c9326 100644
--- a/include/linux/kernel.h
+++ b/include/linux/kernel.h
@@ -276,7 +276,7 @@  extern int oops_may_print(void);
 void do_exit(long error_code) __noreturn;
 void complete_and_exit(struct completion *, long) __noreturn;
 
-void refcount_error_report(struct pt_regs *regs, const char *kind);
+void refcount_error_report(struct pt_regs *regs);
 
 /* Internal, do not use. */
 int __must_check _kstrtoul(const char *s, unsigned int base, unsigned long *res);
diff --git a/kernel/panic.c b/kernel/panic.c
index c95b919..2c4ce79 100644
--- a/kernel/panic.c
+++ b/kernel/panic.c
@@ -605,7 +605,7 @@  EXPORT_SYMBOL(__stack_chk_fail);
 #ifdef CONFIG_FAST_REFCOUNT
 static DEFINE_RATELIMIT_STATE(refcount_ratelimit, 15 * HZ, 3);
 
-void refcount_error_report(struct pt_regs *regs, const char *kind)
+void refcount_error_report(struct pt_regs *regs)
 {
 	/* Always make sure triggering process will be terminated. */
 	do_send_sig_info(SIGKILL, SEND_SIG_FORCED, current, true);
@@ -613,8 +613,7 @@  void refcount_error_report(struct pt_regs *regs, const char *kind)
 	if (!__ratelimit(&refcount_ratelimit))
 		return;
 
-	pr_emerg("%s detected in: %s:%d, uid/euid: %u/%u\n",
-		kind ? kind : "refcount error",
+	pr_emerg("refcount error detected in: %s:%d, uid/euid: %u/%u\n",
 		current->comm, task_pid_nr(current),
 		from_kuid_munged(&init_user_ns, current_uid()),
 		from_kuid_munged(&init_user_ns, current_euid()));