On Mon, Nov 26, 2018 at 11:10:36AM -0600, Josh Poimboeuf wrote:
> On Mon, Nov 26, 2018 at 05:02:17PM +0100, Peter Zijlstra wrote:
> > On Mon, Nov 26, 2018 at 07:55:00AM -0600, Josh Poimboeuf wrote:
> > > diff --git a/arch/x86/kernel/static_call.c b/arch/x86/kernel/static_call.c
> > > index 8026d176f25c..d3869295b88d 100644
> > > --- a/arch/x86/kernel/static_call.c
> > > +++ b/arch/x86/kernel/static_call.c
> > > @@ -9,13 +9,21 @@
> > >
> > > void static_call_bp_handler(void);
> > > void *bp_handler_dest;
> > > +void *bp_handler_continue;
> > >
> > > asm(".pushsection .text, \"ax\"
> > > \n"
> > > ".globl static_call_bp_handler
> > > \n"
> > > ".type static_call_bp_handler, @function
> > > \n"
> > > "static_call_bp_handler:
> > > \n"
> > > - "ANNOTATE_RETPOLINE_SAFE
> > > \n"
> > > +#ifdef CONFIG_HAVE_STATIC_CALL_INLINE
> > > + ANNOTATE_RETPOLINE_SAFE
> > > + "call *bp_handler_dest
> > > \n"
> > > + ANNOTATE_RETPOLINE_SAFE
> > > + "jmp *bp_handler_continue
> > > \n"
> > > +#else /* !CONFIG_HAVE_STATIC_CALL_INLINE */
> > > + ANNOTATE_RETPOLINE_SAFE
> > > "jmp *bp_handler_dest
> > > \n"
> > > +#endif
> > > ".popsection \n");
> > >
> > > void arch_static_call_transform(void *site, void *tramp, void *func)
> > > @@ -25,7 +33,10 @@ void arch_static_call_transform(void *site, void
> > > *tramp, void *func)
> > > unsigned char insn_opcode;
> > > unsigned char opcodes[CALL_INSN_SIZE];
> > >
> > > - insn = (unsigned long)tramp;
> > > + if (IS_ENABLED(CONFIG_HAVE_STATIC_CALL_INLINE))
> > > + insn = (unsigned long)site;
> > > + else
> > > + insn = (unsigned long)tramp;
> > >
> > > mutex_lock(&text_mutex);
> > >
> > > @@ -41,8 +52,10 @@ void arch_static_call_transform(void *site, void
> > > *tramp, void *func)
> > > opcodes[0] = insn_opcode;
> > > memcpy(&opcodes[1], &dest_relative, CALL_INSN_SIZE - 1);
> > >
> > > - /* Set up the variable for the breakpoint handler: */
> > > + /* Set up the variables for the breakpoint handler: */
> > > bp_handler_dest = func;
> > > + if (IS_ENABLED(CONFIG_HAVE_STATIC_CALL_INLINE))
> > > + bp_handler_continue = (void *)(insn + CALL_INSN_SIZE);
> > >
> > > /* Patch the call site: */
> > > text_poke_bp((void *)insn, opcodes, CALL_INSN_SIZE,
> >
> > OK, so this is where that static_call_bp_handler comes from; you need
> > that CALL to frob the stack.
> >
> > But I still think it is broken; consider:
> >
> > CPU0 CPU1
> >
> > bp_handler = ponies;
> >
> > text_poke_bp(, &static_call_bp_handler)
> > text_poke(&int3);
> > on_each_cpu(sync)
> > <IPI>
> > ...
> > </IPI>
> >
> > text_poke(/* all but first bytes */)
> > on_each_cpu(sync)
> > <IPI>
> > ...
> > </IPI>
> >
> > <int3>
> > pt_regs->ip = &static_call_bp_handler
> > </int3>
> >
> > // VCPU takes a nap...
> > text_poke(/* first byte */)
> > on_each_cpu(sync)
> > <IPI>
> > ...
> > </IPI>
> >
> > // VCPU sleeps more
> > bp_handler = unicorn;
> >
> > CALL unicorn
> >
> > *whoops*
> >
> > Now, granted, that is all rather 'unlikely', but that never stopped
> > Murphy.
>
> Good find, thanks Peter.
>
> As we discussed on IRC, we'll need to fix this from within the int3
> exception handler by faking the call: putting a fake return address on
> the stack (pointing to right after the call) and setting regs->ip to the
> called function.
>
> And for the out-of-line case we can just jump straight to the function,
> so the function itself will be the text_poke_bp() "handler".
>
> So the static_call_bp_handler() trampoline will go away.
Peter suggested updating the text_poke_bp() interface to add a handler
which is called from int3 context. This seems to work.
diff --git a/arch/x86/include/asm/text-patching.h
b/arch/x86/include/asm/text-patching.h
index e85ff65c43c3..7fcaa37c1876 100644
--- a/arch/x86/include/asm/text-patching.h
+++ b/arch/x86/include/asm/text-patching.h
@@ -20,6 +20,8 @@ static inline void apply_paravirt(struct paravirt_patch_site
*start,
extern void *text_poke_early(void *addr, const void *opcode, size_t len);
+typedef void (*bp_handler_t)(struct pt_regs *regs);
+
/*
* Clear and restore the kernel write-protection flag on the local CPU.
* Allows the kernel to edit read-only pages.
@@ -36,7 +38,8 @@ extern void *text_poke_early(void *addr, const void *opcode,
size_t len);
*/
extern void *text_poke(void *addr, const void *opcode, size_t len);
extern int poke_int3_handler(struct pt_regs *regs);
-extern void *text_poke_bp(void *addr, const void *opcode, size_t len, void
*handler);
+extern void *text_poke_bp(void *addr, const void *opcode, size_t len,
+ bp_handler_t handler, void *resume);
extern int after_bootmem;
#endif /* _ASM_X86_TEXT_PATCHING_H */
diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
index ebeac487a20c..b6fb645488be 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -738,7 +738,8 @@ static void do_sync_core(void *info)
}
static bool bp_patching_in_progress;
-static void *bp_int3_handler, *bp_int3_addr;
+static void *bp_int3_resume, *bp_int3_addr;
+static bp_handler_t bp_int3_handler;
int poke_int3_handler(struct pt_regs *regs)
{
@@ -746,11 +747,11 @@ int poke_int3_handler(struct pt_regs *regs)
* Having observed our INT3 instruction, we now must observe
* bp_patching_in_progress.
*
- * in_progress = TRUE INT3
- * WMB RMB
- * write INT3 if (in_progress)
+ * in_progress = TRUE INT3
+ * WMB RMB
+ * write INT3 if (in_progress)
*
- * Idem for bp_int3_handler.
+ * Idem for bp_int3_resume.
*/
smp_rmb();
@@ -760,8 +761,10 @@ int poke_int3_handler(struct pt_regs *regs)
if (user_mode(regs) || regs->ip != (unsigned long)bp_int3_addr)
return 0;
- /* set up the specified breakpoint handler */
- regs->ip = (unsigned long) bp_int3_handler;
+ if (bp_int3_handler)
+ bp_int3_handler(regs);
+
+ regs->ip = (unsigned long)bp_int3_resume;
return 1;
@@ -772,7 +775,8 @@ int poke_int3_handler(struct pt_regs *regs)
* @addr: address to patch
* @opcode: opcode of new instruction
* @len: length to copy
- * @handler: address to jump to when the temporary breakpoint is hit
+ * @handler: handler to call from int3 context (optional)
+ * @resume: address to jump to when returning from int3 context
*
* Modify multi-byte instruction by using int3 breakpoint on SMP.
* We completely avoid stop_machine() here, and achieve the
@@ -787,11 +791,13 @@ int poke_int3_handler(struct pt_regs *regs)
* replacing opcode
* - sync cores
*/
-void *text_poke_bp(void *addr, const void *opcode, size_t len, void *handler)
+void *text_poke_bp(void *addr, const void *opcode, size_t len,
+ bp_handler_t handler, void *resume)
{
unsigned char int3 = 0xcc;
bp_int3_handler = handler;
+ bp_int3_resume = resume;
bp_int3_addr = (u8 *)addr + sizeof(int3);
bp_patching_in_progress = true;
diff --git a/arch/x86/kernel/jump_label.c b/arch/x86/kernel/jump_label.c
index aac0c1f7e354..1a54c5c6d9f3 100644
--- a/arch/x86/kernel/jump_label.c
+++ b/arch/x86/kernel/jump_label.c
@@ -90,7 +90,7 @@ static void __ref __jump_label_transform(struct jump_entry
*entry,
return;
}
- text_poke_bp((void *)jump_entry_code(entry), code, JUMP_LABEL_NOP_SIZE,
+ text_poke_bp((void *)jump_entry_code(entry), code, JUMP_LABEL_NOP_SIZE,
NULL,
(void *)jump_entry_code(entry) + JUMP_LABEL_NOP_SIZE);
}
diff --git a/arch/x86/kernel/kprobes/opt.c b/arch/x86/kernel/kprobes/opt.c
index 40b16b270656..5787f48be243 100644
--- a/arch/x86/kernel/kprobes/opt.c
+++ b/arch/x86/kernel/kprobes/opt.c
@@ -446,7 +446,7 @@ void arch_optimize_kprobes(struct list_head *oplist)
insn_buf[0] = RELATIVEJUMP_OPCODE;
*(s32 *)(&insn_buf[1]) = rel;
- text_poke_bp(op->kp.addr, insn_buf, RELATIVEJUMP_SIZE,
+ text_poke_bp(op->kp.addr, insn_buf, RELATIVEJUMP_SIZE, NULL,
op->optinsn.insn);
list_del_init(&op->list);
@@ -461,7 +461,7 @@ void arch_unoptimize_kprobe(struct optimized_kprobe *op)
/* Set int3 to first byte for kprobes */
insn_buf[0] = BREAKPOINT_INSTRUCTION;
memcpy(insn_buf + 1, op->optinsn.copied_insn, RELATIVE_ADDR_SIZE);
- text_poke_bp(op->kp.addr, insn_buf, RELATIVEJUMP_SIZE,
+ text_poke_bp(op->kp.addr, insn_buf, RELATIVEJUMP_SIZE, NULL,
op->optinsn.insn);
}
diff --git a/arch/x86/kernel/static_call.c b/arch/x86/kernel/static_call.c
index d3869295b88d..8fd6c8556750 100644
--- a/arch/x86/kernel/static_call.c
+++ b/arch/x86/kernel/static_call.c
@@ -7,24 +7,19 @@
#define CALL_INSN_SIZE 5
-void static_call_bp_handler(void);
-void *bp_handler_dest;
-void *bp_handler_continue;
+unsigned long bp_handler_call_return_addr;
-asm(".pushsection .text, \"ax\"
\n"
- ".globl static_call_bp_handler \n"
- ".type static_call_bp_handler, @function \n"
- "static_call_bp_handler: \n"
+static void static_call_bp_handler(struct pt_regs *regs)
+{
#ifdef CONFIG_HAVE_STATIC_CALL_INLINE
- ANNOTATE_RETPOLINE_SAFE
- "call *bp_handler_dest \n"
- ANNOTATE_RETPOLINE_SAFE
- "jmp *bp_handler_continue \n"
-#else /* !CONFIG_HAVE_STATIC_CALL_INLINE */
- ANNOTATE_RETPOLINE_SAFE
- "jmp *bp_handler_dest \n"
+ /*
+ * Push the return address on the stack so the "called" function will
+ * return to immediately after the call site.
+ */
+ regs->sp -= sizeof(long);
+ *(unsigned long *)regs->sp = bp_handler_call_return_addr;
#endif
- ".popsection \n");
+}
void arch_static_call_transform(void *site, void *tramp, void *func)
{
@@ -52,14 +47,12 @@ void arch_static_call_transform(void *site, void *tramp,
void *func)
opcodes[0] = insn_opcode;
memcpy(&opcodes[1], &dest_relative, CALL_INSN_SIZE - 1);
- /* Set up the variables for the breakpoint handler: */
- bp_handler_dest = func;
if (IS_ENABLED(CONFIG_HAVE_STATIC_CALL_INLINE))
- bp_handler_continue = (void *)(insn + CALL_INSN_SIZE);
+ bp_handler_call_return_addr = insn + CALL_INSN_SIZE;
/* Patch the call site: */
text_poke_bp((void *)insn, opcodes, CALL_INSN_SIZE,
- static_call_bp_handler);
+ static_call_bp_handler, func);
done:
mutex_unlock(&text_mutex);
