[PATCH AUTOSEL 4.14 09/11] arm64: alternatives: mark patch_alternative() as `noinstr`

[Sasha Levin]

From: Joey Gouly <joey.gouly@xxxxxxx>

[ Upstream commit a2c0b0fbe01419f8f5d1c0b9c581631f34ffce8b ]

The alternatives code must be `noinstr` such that it does not patch itself,
as the cache invalidation is only performed after all the alternatives have
been applied.

Mark patch_alternative() as `noinstr`. Mark branch_insn_requires_update()
and get_alt_insn() with `__always_inline` since they are both only called
through patch_alternative().

Booting a kernel in QEMU TCG with KCSAN=y and ARM64_USE_LSE_ATOMICS=y caused
a boot hang:
[    0.241121] CPU: All CPU(s) started at EL2

The alternatives code was patching the atomics in __tsan_read4() from LL/SC
atomics to LSE atomics.

The following fragment is using LL/SC atomics in the .text section:
  | <__tsan_unaligned_read4+304>:     ldxr    x6, [x2]
  | <__tsan_unaligned_read4+308>:     add     x6, x6, x5
  | <__tsan_unaligned_read4+312>:     stxr    w7, x6, [x2]
  | <__tsan_unaligned_read4+316>:     cbnz    w7, <__tsan_unaligned_read4+304>

This LL/SC atomic sequence was to be replaced with LSE atomics. However since
the alternatives code was instrumentable, __tsan_read4() was being called after
only the first instruction was replaced, which led to the following code in memory:
  | <__tsan_unaligned_read4+304>:     ldadd   x5, x6, [x2]
  | <__tsan_unaligned_read4+308>:     add     x6, x6, x5
  | <__tsan_unaligned_read4+312>:     stxr    w7, x6, [x2]
  | <__tsan_unaligned_read4+316>:     cbnz    w7, <__tsan_unaligned_read4+304>

This caused an infinite loop as the `stxr` instruction never completed successfully,
so `w7` was always 0.

Signed-off-by: Joey Gouly <joey.gouly@xxxxxxx>
Cc: Mark Rutland <mark.rutland@xxxxxxx>
Cc: Catalin Marinas <catalin.marinas@xxxxxxx>
Cc: Will Deacon <will@xxxxxxxxxx>
Link: https://lore.kernel.org/r/20220405104733.11476-1-joey.gouly@xxxxxxx
Signed-off-by: Will Deacon <will@xxxxxxxxxx>
Signed-off-by: Sasha Levin <sashal@xxxxxxxxxx>
---
 arch/arm64/kernel/alternative.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/arch/arm64/kernel/alternative.c b/arch/arm64/kernel/alternative.c
index 4c385763c361..1398fd816068 100644
--- a/arch/arm64/kernel/alternative.c
+++ b/arch/arm64/kernel/alternative.c
@@ -42,7 +42,7 @@ struct alt_region {
 /*
  * Check if the target PC is within an alternative block.
  */
-static bool branch_insn_requires_update(struct alt_instr *alt, unsigned long pc)
+static __always_inline bool branch_insn_requires_update(struct alt_instr *alt, unsigned long pc)
 {
 	unsigned long replptr = (unsigned long)ALT_REPL_PTR(alt);
 	return !(pc >= replptr && pc <= (replptr + alt->alt_len));
@@ -50,7 +50,7 @@ static bool branch_insn_requires_update(struct alt_instr *alt, unsigned long pc)
 
 #define align_down(x, a)	((unsigned long)(x) & ~(((unsigned long)(a)) - 1))
 
-static u32 get_alt_insn(struct alt_instr *alt, __le32 *insnptr, __le32 *altinsnptr)
+static __always_inline u32 get_alt_insn(struct alt_instr *alt, __le32 *insnptr, __le32 *altinsnptr)
 {
 	u32 insn;
 
@@ -95,7 +95,7 @@ static u32 get_alt_insn(struct alt_instr *alt, __le32 *insnptr, __le32 *altinsnp
 	return insn;
 }
 
-static void patch_alternative(struct alt_instr *alt,
+static noinstr void patch_alternative(struct alt_instr *alt,
 			      __le32 *origptr, __le32 *updptr, int nr_inst)
 {
 	__le32 *replptr;
-- 
2.35.1