[tip: core/kprobes] x86/alternatives: Teach text_poke_bp() to emulate instructions
From: tip-bot2 for Peter Zijlstra
Date: Fri Nov 15 2019 - 04:43:38 EST
The following commit has been merged into the core/kprobes branch of tip:
Commit-ID: 8c7eebc10687af45ac8e40ad1bac0cf7893dba9f
Gitweb: https://git.kernel.org/tip/8c7eebc10687af45ac8e40ad1bac0cf7893dba9f
Author: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
AuthorDate: Wed, 05 Jun 2019 10:48:37 +02:00
Committer: Ingo Molnar <mingo@xxxxxxxxxx>
CommitterDate: Fri, 15 Nov 2019 09:07:41 +01:00
x86/alternatives: Teach text_poke_bp() to emulate instructions
In preparation for static_call and variable size jump_label support,
teach text_poke_bp() to emulate instructions, namely:
JMP32, JMP8, CALL, NOP2, NOP_ATOMIC5, INT3
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.
Tested-by: Alexei Starovoitov <ast@xxxxxxxxxx>
Tested-by: Steven Rostedt (VMware) <rostedt@xxxxxxxxxxx>
Signed-off-by: Peter Zijlstra (Intel) <peterz@xxxxxxxxxxxxx>
Reviewed-by: Masami Hiramatsu <mhiramat@xxxxxxxxxx>
Reviewed-by: Daniel Bristot de Oliveira <bristot@xxxxxxxxxx>
Acked-by: Alexei Starovoitov <ast@xxxxxxxxxx>
Cc: Andy Lutomirski <luto@xxxxxxxxxx>
Cc: Borislav Petkov <bp@xxxxxxxxx>
Cc: H. Peter Anvin <hpa@xxxxxxxxx>
Cc: Josh Poimboeuf <jpoimboe@xxxxxxxxxx>
Cc: Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx>
Cc: Steven Rostedt <rostedt@xxxxxxxxxxx>
Cc: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
Link: https://lkml.kernel.org/r/20191111132457.529086974@xxxxxxxxxxxxx
Signed-off-by: Ingo Molnar <mingo@xxxxxxxxxx>
---
arch/x86/include/asm/text-patching.h | 24 +++--
arch/x86/kernel/alternative.c | 132 +++++++++++++++++++-------
arch/x86/kernel/jump_label.c | 9 +--
arch/x86/kernel/kprobes/opt.c | 11 +-
4 files changed, 130 insertions(+), 46 deletions(-)
diff --git a/arch/x86/include/asm/text-patching.h b/arch/x86/include/asm/text-patching.h
index 5e8319b..23c626a 100644
--- a/arch/x86/include/asm/text-patching.h
+++ b/arch/x86/include/asm/text-patching.h
@@ -26,10 +26,11 @@ static inline void apply_paravirt(struct paravirt_patch_site *start,
#define POKE_MAX_OPCODE_SIZE 5
struct text_poke_loc {
- void *detour;
void *addr;
- size_t len;
- const char opcode[POKE_MAX_OPCODE_SIZE];
+ int len;
+ s32 rel32;
+ u8 opcode;
+ const u8 text[POKE_MAX_OPCODE_SIZE];
};
extern void text_poke_early(void *addr, const void *opcode, size_t len);
@@ -51,8 +52,10 @@ 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 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 void text_poke_bp_batch(struct text_poke_loc *tp, unsigned int nr_entries);
+extern void text_poke_loc_init(struct text_poke_loc *tp, 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;
@@ -63,8 +66,17 @@ static inline void int3_emulate_jmp(struct pt_regs *regs, unsigned long ip)
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 JMP32_INSN_SIZE 5
+#define JMP32_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)
{
diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
index 9d3a971..9ec463f 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -956,16 +956,15 @@ NOKPROBE_SYMBOL(patch_cmp);
int poke_int3_handler(struct pt_regs *regs)
{
struct text_poke_loc *tp;
- unsigned char int3 = 0xcc;
void *ip;
/*
* Having observed our INT3 instruction, we now must observe
* bp_patching.nr_entries.
*
- * nr_entries != 0 INT3
- * WMB RMB
- * write INT3 if (nr_entries)
+ * nr_entries != 0 INT3
+ * WMB RMB
+ * write INT3 if (nr_entries)
*
* Idem for other elements in bp_patching.
*/
@@ -978,9 +977,9 @@ int poke_int3_handler(struct pt_regs *regs)
return 0;
/*
- * Discount the sizeof(int3). See text_poke_bp_batch().
+ * Discount the INT3. See text_poke_bp_batch().
*/
- ip = (void *) regs->ip - sizeof(int3);
+ ip = (void *) regs->ip - INT3_INSN_SIZE;
/*
* Skip the binary search if there is a single member in the vector.
@@ -997,8 +996,28 @@ int poke_int3_handler(struct pt_regs *regs)
return 0;
}
- /* set up the specified breakpoint detour */
- regs->ip = (unsigned long) tp->detour;
+ ip += tp->len;
+
+ switch (tp->opcode) {
+ case INT3_INSN_OPCODE:
+ /*
+ * Someone poked an explicit INT3, they'll want to handle it,
+ * do not consume.
+ */
+ return 0;
+
+ case CALL_INSN_OPCODE:
+ int3_emulate_call(regs, (long)ip + tp->rel32);
+ break;
+
+ case JMP32_INSN_OPCODE:
+ case JMP8_INSN_OPCODE:
+ int3_emulate_jmp(regs, (long)ip + tp->rel32);
+ break;
+
+ default:
+ BUG();
+ }
return 1;
}
@@ -1014,7 +1033,7 @@ NOKPROBE_SYMBOL(poke_int3_handler);
* synchronization using int3 breakpoint.
*
* The way it is done:
- * - For each entry in the vector:
+ * - For each entry in the vector:
* - add a int3 trap to the address that will be patched
* - sync cores
* - For each entry in the vector:
@@ -1027,9 +1046,9 @@ NOKPROBE_SYMBOL(poke_int3_handler);
*/
void text_poke_bp_batch(struct text_poke_loc *tp, unsigned int nr_entries)
{
- int patched_all_but_first = 0;
- unsigned char int3 = 0xcc;
+ unsigned char int3 = INT3_INSN_OPCODE;
unsigned int i;
+ int do_sync;
lockdep_assert_held(&text_mutex);
@@ -1053,16 +1072,16 @@ void text_poke_bp_batch(struct text_poke_loc *tp, unsigned int nr_entries)
/*
* Second step: update all but the first byte of the patched range.
*/
- for (i = 0; i < nr_entries; i++) {
+ for (do_sync = 0, i = 0; i < nr_entries; i++) {
if (tp[i].len - sizeof(int3) > 0) {
text_poke((char *)tp[i].addr + sizeof(int3),
- (const char *)tp[i].opcode + sizeof(int3),
+ (const char *)tp[i].text + sizeof(int3),
tp[i].len - sizeof(int3));
- patched_all_but_first++;
+ do_sync++;
}
}
- if (patched_all_but_first) {
+ if (do_sync) {
/*
* According to Intel, this core syncing is very likely
* not necessary and we'd be safe even without it. But
@@ -1075,10 +1094,17 @@ void text_poke_bp_batch(struct text_poke_loc *tp, unsigned int nr_entries)
* Third step: replace the first byte (int3) by the first byte of
* replacing opcode.
*/
- for (i = 0; i < nr_entries; i++)
- text_poke(tp[i].addr, tp[i].opcode, sizeof(int3));
+ for (do_sync = 0, i = 0; i < nr_entries; i++) {
+ if (tp[i].text[0] == INT3_INSN_OPCODE)
+ continue;
+
+ text_poke(tp[i].addr, tp[i].text, sizeof(int3));
+ do_sync++;
+ }
+
+ if (do_sync)
+ on_each_cpu(do_sync_core, NULL, 1);
- on_each_cpu(do_sync_core, NULL, 1);
/*
* sync_core() implies an smp_mb() and orders this store against
* the writing of the new instruction.
@@ -1087,6 +1113,60 @@ void text_poke_bp_batch(struct text_poke_loc *tp, unsigned int nr_entries)
bp_patching.nr_entries = 0;
}
+void text_poke_loc_init(struct text_poke_loc *tp, void *addr,
+ const void *opcode, size_t len, const void *emulate)
+{
+ struct insn insn;
+
+ if (!opcode)
+ opcode = (void *)tp->text;
+ else
+ memcpy((void *)tp->text, opcode, len);
+
+ if (!emulate)
+ emulate = opcode;
+
+ kernel_insn_init(&insn, emulate, MAX_INSN_SIZE);
+ insn_get_length(&insn);
+
+ BUG_ON(!insn_complete(&insn));
+ BUG_ON(len != insn.length);
+
+ tp->addr = addr;
+ tp->len = len;
+ tp->opcode = insn.opcode.bytes[0];
+
+ switch (tp->opcode) {
+ case INT3_INSN_OPCODE:
+ break;
+
+ case CALL_INSN_OPCODE:
+ case JMP32_INSN_OPCODE:
+ case JMP8_INSN_OPCODE:
+ tp->rel32 = insn.immediate.value;
+ break;
+
+ default: /* assume NOP */
+ switch (len) {
+ case 2: /* NOP2 -- emulate as JMP8+0 */
+ BUG_ON(memcmp(emulate, ideal_nops[len], len));
+ tp->opcode = JMP8_INSN_OPCODE;
+ tp->rel32 = 0;
+ break;
+
+ case 5: /* NOP5 -- emulate as JMP32+0 */
+ BUG_ON(memcmp(emulate, ideal_nops[NOP_ATOMIC5], len));
+ tp->opcode = JMP32_INSN_OPCODE;
+ tp->rel32 = 0;
+ break;
+
+ default: /* unknown instruction */
+ BUG();
+ }
+ break;
+ }
+}
+
/**
* text_poke_bp() -- update instructions on live kernel on SMP
* @addr: address to patch
@@ -1098,20 +1178,10 @@ void text_poke_bp_batch(struct text_poke_loc *tp, unsigned int nr_entries)
* dynamically allocated memory. This function should be used when it is
* not possible to allocate memory.
*/
-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)
{
- struct text_poke_loc tp = {
- .detour = handler,
- .addr = addr,
- .len = len,
- };
-
- if (len > POKE_MAX_OPCODE_SIZE) {
- WARN_ONCE(1, "len is larger than %d\n", POKE_MAX_OPCODE_SIZE);
- return;
- }
-
- memcpy((void *)tp.opcode, opcode, len);
+ struct text_poke_loc tp;
+ text_poke_loc_init(&tp, addr, opcode, len, emulate);
text_poke_bp_batch(&tp, 1);
}
diff --git a/arch/x86/kernel/jump_label.c b/arch/x86/kernel/jump_label.c
index 0440532..c1a8b9e 100644
--- a/arch/x86/kernel/jump_label.c
+++ b/arch/x86/kernel/jump_label.c
@@ -89,8 +89,7 @@ static void __ref __jump_label_transform(struct jump_entry *entry,
return;
}
- text_poke_bp((void *)jump_entry_code(entry), &code, JUMP_LABEL_NOP_SIZE,
- (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,
@@ -147,11 +146,9 @@ bool arch_jump_label_transform_queue(struct jump_entry *entry,
}
__jump_label_set_jump_code(entry, type,
- (union jump_code_union *) &tp->opcode, 0);
+ (union jump_code_union *)&tp->text, 0);
- tp->addr = entry_code;
- tp->detour = entry_code + JUMP_LABEL_NOP_SIZE;
- tp->len = JUMP_LABEL_NOP_SIZE;
+ text_poke_loc_init(tp, entry_code, NULL, JUMP_LABEL_NOP_SIZE, NULL);
tp_vec_nr++;
diff --git a/arch/x86/kernel/kprobes/opt.c b/arch/x86/kernel/kprobes/opt.c
index b348dd5..8900329 100644
--- a/arch/x86/kernel/kprobes/opt.c
+++ b/arch/x86/kernel/kprobes/opt.c
@@ -437,8 +437,7 @@ void arch_optimize_kprobes(struct list_head *oplist)
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_head *oplist)
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);
}
/*