[PATCH v4 01/23] Fix "x86/alternatives: Lockdep-enforce text_mutex in text_poke*()"

From: Rick Edgecombe
Date: Mon Apr 22 2019 - 15:00:59 EST


From: Nadav Amit <namit@xxxxxxxxxx>

text_mutex is currently expected to be held before text_poke() is
called, but kgdb does not take the mutex, and instead *supposedly*
ensures the lock is not taken and will not be acquired by any other core
while text_poke() is running.

The reason for the "supposedly" comment is that it is not entirely clear
that this would be the case if gdb_do_roundup is zero.

Create two wrapper functions, text_poke() and text_poke_kgdb(), which do
or do not run the lockdep assertion respectively.

While we are at it, change the return code of text_poke() to something
meaningful. One day, callers might actually respect it and the existing
BUG_ON() when patching fails could be removed. For kgdb, the return
value can actually be used.

Cc: Andy Lutomirski <luto@xxxxxxxxxx>
Cc: Kees Cook <keescook@xxxxxxxxxxxx>
Cc: Dave Hansen <dave.hansen@xxxxxxxxx>
Cc: Masami Hiramatsu <mhiramat@xxxxxxxxxx>
Fixes: 9222f606506c ("x86/alternatives: Lockdep-enforce text_mutex in text_poke*()")
Suggested-by: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
Acked-by: Jiri Kosina <jkosina@xxxxxxx>
Acked-by: Peter Zijlstra (Intel) <peterz@xxxxxxxxxxxxx>
Reviewed-by: Masami Hiramatsu <mhiramat@xxxxxxxxxx>
Signed-off-by: Nadav Amit <namit@xxxxxxxxxx>
Signed-off-by: Rick Edgecombe <rick.p.edgecombe@xxxxxxxxx>
---
arch/x86/include/asm/text-patching.h | 1 +
arch/x86/kernel/alternative.c | 52 ++++++++++++++++++++--------
arch/x86/kernel/kgdb.c | 11 +++---
3 files changed, 45 insertions(+), 19 deletions(-)

diff --git a/arch/x86/include/asm/text-patching.h b/arch/x86/include/asm/text-patching.h
index e85ff65c43c3..f8fc8e86cf01 100644
--- a/arch/x86/include/asm/text-patching.h
+++ b/arch/x86/include/asm/text-patching.h
@@ -35,6 +35,7 @@ extern void *text_poke_early(void *addr, const void *opcode, size_t len);
* inconsistent instruction while you patch.
*/
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 int after_bootmem;
diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
index 9a79c7808f9c..0a814d73547a 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -679,18 +679,7 @@ void *__init_or_module text_poke_early(void *addr, const void *opcode,
return addr;
}

-/**
- * text_poke - Update instructions on a live kernel
- * @addr: address to modify
- * @opcode: source of the copy
- * @len: length to copy
- *
- * Only atomic text poke/set should be allowed when not doing early patching.
- * It means the size must be writable atomically and the address must be aligned
- * in a way that permits an atomic write. It also makes sure we fit on a single
- * page.
- */
-void *text_poke(void *addr, const void *opcode, size_t len)
+static void *__text_poke(void *addr, const void *opcode, size_t len)
{
unsigned long flags;
char *vaddr;
@@ -703,8 +692,6 @@ void *text_poke(void *addr, const void *opcode, size_t len)
*/
BUG_ON(!after_bootmem);

- lockdep_assert_held(&text_mutex);
-
if (!core_kernel_text((unsigned long)addr)) {
pages[0] = vmalloc_to_page(addr);
pages[1] = vmalloc_to_page(addr + PAGE_SIZE);
@@ -733,6 +720,43 @@ void *text_poke(void *addr, const void *opcode, size_t len)
return addr;
}

+/**
+ * text_poke - Update instructions on a live kernel
+ * @addr: address to modify
+ * @opcode: source of the copy
+ * @len: length to copy
+ *
+ * Only atomic text poke/set should be allowed when not doing early patching.
+ * It means the size must be writable atomically and the address must be aligned
+ * in a way that permits an atomic write. It also makes sure we fit on a single
+ * page.
+ */
+void *text_poke(void *addr, const void *opcode, size_t len)
+{
+ lockdep_assert_held(&text_mutex);
+
+ return __text_poke(addr, opcode, len);
+}
+
+/**
+ * text_poke_kgdb - Update instructions on a live kernel by kgdb
+ * @addr: address to modify
+ * @opcode: source of the copy
+ * @len: length to copy
+ *
+ * Only atomic text poke/set should be allowed when not doing early patching.
+ * It means the size must be writable atomically and the address must be aligned
+ * in a way that permits an atomic write. It also makes sure we fit on a single
+ * page.
+ *
+ * Context: should only be used by kgdb, which ensures no other core is running,
+ * despite the fact it does not hold the text_mutex.
+ */
+void *text_poke_kgdb(void *addr, const void *opcode, size_t len)
+{
+ return __text_poke(addr, opcode, len);
+}
+
static void do_sync_core(void *info)
{
sync_core();
diff --git a/arch/x86/kernel/kgdb.c b/arch/x86/kernel/kgdb.c
index 4ff6b4cdb941..2b203ee5b879 100644
--- a/arch/x86/kernel/kgdb.c
+++ b/arch/x86/kernel/kgdb.c
@@ -759,13 +759,13 @@ int kgdb_arch_set_breakpoint(struct kgdb_bkpt *bpt)
if (!err)
return err;
/*
- * It is safe to call text_poke() because normal kernel execution
+ * It is safe to call text_poke_kgdb() because normal kernel execution
* is stopped on all cores, so long as the text_mutex is not locked.
*/
if (mutex_is_locked(&text_mutex))
return -EBUSY;
- text_poke((void *)bpt->bpt_addr, arch_kgdb_ops.gdb_bpt_instr,
- BREAK_INSTR_SIZE);
+ text_poke_kgdb((void *)bpt->bpt_addr, arch_kgdb_ops.gdb_bpt_instr,
+ BREAK_INSTR_SIZE);
err = probe_kernel_read(opc, (char *)bpt->bpt_addr, BREAK_INSTR_SIZE);
if (err)
return err;
@@ -784,12 +784,13 @@ int kgdb_arch_remove_breakpoint(struct kgdb_bkpt *bpt)
if (bpt->type != BP_POKE_BREAKPOINT)
goto knl_write;
/*
- * It is safe to call text_poke() because normal kernel execution
+ * It is safe to call text_poke_kgdb() because normal kernel execution
* is stopped on all cores, so long as the text_mutex is not locked.
*/
if (mutex_is_locked(&text_mutex))
goto knl_write;
- text_poke((void *)bpt->bpt_addr, bpt->saved_instr, BREAK_INSTR_SIZE);
+ text_poke_kgdb((void *)bpt->bpt_addr, bpt->saved_instr,
+ BREAK_INSTR_SIZE);
err = probe_kernel_read(opc, (char *)bpt->bpt_addr, BREAK_INSTR_SIZE);
if (err || memcmp(opc, bpt->saved_instr, BREAK_INSTR_SIZE))
goto knl_write;
--
2.17.1