On Tue, Jun 11, 2019 at 06:21:28PM +0200, Peter Zijlstra wrote:
> although at this point I'm
> thinking we should just used the instruction decode we have instead of
> playing iffy games with packed structures.

How's something like this? It accepts jmp/32 jmp/8 call and nop5_atomic.

---
Subject: x86/alternatives: Teach text_poke_bp() to emulate instructions
From: Peter Zijlstra <pet...@infradead.org>
Date: Wed Jun 5 10:48:37 CEST 2019

In preparation for static_call support, teach text_poke_bp() to
emulate instructions, including CALL.

The current text_poke_bp() takes a @handler argument which is used as
a jump target when the temporary INT3 is hit by a different CPU.

When patching CALL instructions, this doesn't work because we'd miss
the PUSH of the return address. Instead, teach poke_int3_handler() to
emulate an instruction, typically the instruction we're patching in.

This fits almost all text_poke_bp() users, except
arch_unoptimize_kprobe() which restores random text, and for that site
we have to build an explicit emulate instruction.

Signed-off-by: Peter Zijlstra (Intel) <pet...@infradead.org>
---
 arch/x86/include/asm/text-patching.h |   15 +++++--
 arch/x86/kernel/alternative.c        |   73 +++++++++++++++++++++++++----------
 arch/x86/kernel/jump_label.c         |    3 -
 arch/x86/kernel/kprobes/opt.c        |   11 +++--
 4 files changed, 75 insertions(+), 27 deletions(-)

--- a/arch/x86/include/asm/text-patching.h
+++ b/arch/x86/include/asm/text-patching.h
@@ -37,7 +37,7 @@ extern void text_poke_early(void *addr,
 extern void *text_poke(void *addr, const void *opcode, size_t len);
 extern void *text_poke_kgdb(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, const 
void *emulate);
 extern int after_bootmem;
 extern __ro_after_init struct mm_struct *poking_mm;
 extern __ro_after_init unsigned long poking_addr;
@@ -48,8 +48,17 @@ static inline void int3_emulate_jmp(stru
        regs->ip = ip;
 }
 
-#define INT3_INSN_SIZE 1
-#define CALL_INSN_SIZE 5
+#define INT3_INSN_SIZE         1
+#define INT3_INSN_OPCODE       0xCC
+
+#define CALL_INSN_SIZE         5
+#define CALL_INSN_OPCODE       0xE8
+
+#define JMP_INSN_SIZE          5
+#define JMP_INSN_OPCODE                0xE9
+
+#define JMP8_INSN_SIZE         2
+#define JMP8_INSN_OPCODE       0xEB
 
 static inline void int3_emulate_push(struct pt_regs *regs, unsigned long val)
 {
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -920,31 +920,45 @@ static void do_sync_core(void *info)
        sync_core();
 }
 
-static bool bp_patching_in_progress;
-static void *bp_int3_handler, *bp_int3_addr;
+static const void *bp_int3_addr;
+static const struct insn *bp_int3_insn;
 
 int poke_int3_handler(struct pt_regs *regs)
 {
+       long ip;
+
        /*
         * Having observed our INT3 instruction, we now must observe
-        * bp_patching_in_progress.
-        *
-        *      in_progress = TRUE              INT3
-        *      WMB                             RMB
-        *      write INT3                      if (in_progress)
+        * bp_int3_addr and bp_int3_insn:
         *
-        * Idem for bp_int3_handler.
+        *      bp_int3_{addr,insn) = ..        INT3
+        *      WMB                             RMB
+        *      write INT3                      if (insn)
         */
        smp_rmb();
 
-       if (likely(!bp_patching_in_progress))
+       if (likely(!bp_int3_insn))
                return 0;
 
        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;
+       ip = regs->ip - INT3_INSN_SIZE + bp_int3_insn->length;
+
+       switch (bp_int3_insn->opcode.bytes[0]) {
+       case CALL_INSN_OPCODE:
+               int3_emulate_call(regs, ip + bp_int3_insn->immediate.value);
+               break;
+
+       case JMP_INSN_OPCODE:
+       case JMP8_INSN_OPCODE:
+               int3_emulate_jmp(regs, ip + bp_int3_insn->immediate.value);
+               break;
+
+       default: /* assume NOP */
+               int3_emulate_jmp(regs, ip);
+               break;
+       }
 
        return 1;
 }
@@ -955,7 +969,7 @@ NOKPROBE_SYMBOL(poke_int3_handler);
  * @addr:      address to patch
  * @opcode:    opcode of new instruction
  * @len:       length to copy
- * @handler:   address to jump to when the temporary breakpoint is hit
+ * @emulate:   opcode to emulate, when NULL use @opcode
  *
  * Modify multi-byte instruction by using int3 breakpoint on SMP.
  * We completely avoid stop_machine() here, and achieve the
@@ -970,19 +984,40 @@ NOKPROBE_SYMBOL(poke_int3_handler);
  *       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, const void 
*emulate)
 {
-       unsigned char int3 = 0xcc;
+       unsigned char int3 = INT3_INSN_OPCODE;
+       struct insn insn;
 
-       bp_int3_handler = handler;
-       bp_int3_addr = (u8 *)addr + sizeof(int3);
-       bp_patching_in_progress = true;
+       bp_int3_addr = addr + INT3_INSN_SIZE;
 
        lockdep_assert_held(&text_mutex);
 
+       if (!emulate)
+               emulate = opcode;
+
+       kernel_insn_init(&insn, emulate, MAX_INSN_SIZE);
+       insn_get_length(&insn);
+
+       BUG_ON(!insn_complete(&insn));
+       BUG_ON(insn.length != len);
+
+       switch (insn.opcode.bytes[0]) {
+       case CALL_INSN_OPCODE:
+       case JMP_INSN_OPCODE:
+       case JMP8_INSN_OPCODE:
+               break;
+
+       default:
+               BUG_ON(len != 5);
+               BUG_ON(memcmp(emulate, ideal_nops[NOP_ATOMIC5], 5));
+       }
+
+       bp_int3_insn = &insn;
+
        /*
         * Corresponding read barrier in int3 notifier for making sure the
-        * in_progress and handler are correctly ordered wrt. patching.
+        * in_progress and opcode are correctly ordered wrt. patching.
         */
        smp_wmb();
 
@@ -1011,6 +1046,6 @@ void text_poke_bp(void *addr, const void
         * sync_core() implies an smp_mb() and orders this store against
         * the writing of the new instruction.
         */
-       bp_patching_in_progress = false;
+       bp_int3_insn = NULL;
 }
 
--- a/arch/x86/kernel/jump_label.c
+++ b/arch/x86/kernel/jump_label.c
@@ -87,8 +87,7 @@ static void __ref __jump_label_transform
                return;
        }
 
-       text_poke_bp((void *)jump_entry_code(entry), code, JUMP_LABEL_NOP_SIZE,
-                    (void *)jump_entry_code(entry) + JUMP_LABEL_NOP_SIZE);
+       text_poke_bp((void *)jump_entry_code(entry), code, JUMP_LABEL_NOP_SIZE, 
NULL);
 }
 
 void arch_jump_label_transform(struct jump_entry *entry,
--- a/arch/x86/kernel/kprobes/opt.c
+++ b/arch/x86/kernel/kprobes/opt.c
@@ -437,8 +437,7 @@ void arch_optimize_kprobes(struct list_h
                insn_buff[0] = RELATIVEJUMP_OPCODE;
                *(s32 *)(&insn_buff[1]) = rel;
 
-               text_poke_bp(op->kp.addr, insn_buff, RELATIVEJUMP_SIZE,
-                            op->optinsn.insn);
+               text_poke_bp(op->kp.addr, insn_buff, RELATIVEJUMP_SIZE, NULL);
 
                list_del_init(&op->list);
        }
@@ -448,12 +447,18 @@ void arch_optimize_kprobes(struct list_h
 void arch_unoptimize_kprobe(struct optimized_kprobe *op)
 {
        u8 insn_buff[RELATIVEJUMP_SIZE];
+       u8 emulate_buff[RELATIVEJUMP_SIZE];
 
        /* Set int3 to first byte for kprobes */
        insn_buff[0] = BREAKPOINT_INSTRUCTION;
        memcpy(insn_buff + 1, op->optinsn.copied_insn, RELATIVE_ADDR_SIZE);
+
+       emulate_buff[0] = RELATIVEJUMP_OPCODE;
+       *(s32 *)(&emulate_buff[1]) = (s32)((long)op->optinsn.insn -
+                       ((long)op->kp.addr + RELATIVEJUMP_SIZE));
+
        text_poke_bp(op->kp.addr, insn_buff, RELATIVEJUMP_SIZE,
-                    op->optinsn.insn);
+                    emulate_buff);
 }
 
 /*

Reply via email to