Merge branch 'for-5.20/io_uring' into for-5.20/io_uring-zerocopy-send

* for-5.20/io_uring: (716 commits)
  io_uring: ensure REQ_F_ISREG is set async offload
  net: fix compat pointer in get_compat_msghdr()
  io_uring: Don't require reinitable percpu_ref
  io_uring: fix types in io_recvmsg_multishot_overflow
  io_uring: Use atomic_long_try_cmpxchg in __io_account_mem
  io_uring: support multishot in recvmsg
  net: copy from user before calling __get_compat_msghdr
  net: copy from user before calling __copy_msghdr
  io_uring: support 0 length iov in buffer select in compat
  io_uring: fix multishot ending when not polled
  io_uring: add netmsg cache
  io_uring: impose max limit on apoll cache
  io_uring: add abstraction around apoll cache
  io_uring: move apoll cache to poll.c
  io_uring: consolidate hash_locked io-wq handling
  io_uring: clear REQ_F_HASH_LOCKED on hash removal
  io_uring: don't race double poll setting REQ_F_ASYNC_DATA
  io_uring: don't miss setting REQ_F_DOUBLE_POLL
  io_uring: disable multishot recvmsg
  io_uring: only trace one of complete or overflow
  ...

Signed-off-by: Jens Axboe <axboe@kernel.dk>

1 files changed, 45 insertions, 6 deletions

diff --git a/arch/x86/kernel/static_call.c b/arch/x86/kernel/static_call.c
index aa72cefdd5be..aaaba85d6d7f 100644
--- a/arch/x86/kernel/static_call.c
+++ b/arch/x86/kernel/static_call.c
@@ -12,13 +12,21 @@ enum insn_type {
 };
 
 /*
+ * ud1 %esp, %ecx - a 3 byte #UD that is unique to trampolines, chosen such
+ * that there is no false-positive trampoline identification while also being a
+ * speculation stop.
+ */
+static const u8 tramp_ud[] = { 0x0f, 0xb9, 0xcc };
+
+/*
  * cs cs cs xorl %eax, %eax - a single 5 byte instruction that clears %[er]ax
  */
 static const u8 xor5rax[] = { 0x2e, 0x2e, 0x2e, 0x31, 0xc0 };
 
 static const u8 retinsn[] = { RET_INSN_OPCODE, 0xcc, 0xcc, 0xcc, 0xcc };
 
-static void __ref __static_call_transform(void *insn, enum insn_type type, void *func)
+static void __ref __static_call_transform(void *insn, enum insn_type type,
+					  void *func, bool modinit)
 {
 	const void *emulate = NULL;
 	int size = CALL_INSN_SIZE;
@@ -43,14 +51,17 @@ static void __ref __static_call_transform(void *insn, enum insn_type type, void
 		break;
 
 	case RET:
-		code = &retinsn;
+		if (cpu_feature_enabled(X86_FEATURE_RETHUNK))
+			code = text_gen_insn(JMP32_INSN_OPCODE, insn, &__x86_return_thunk);
+		else
+			code = &retinsn;
 		break;
 	}
 
 	if (memcmp(insn, code, size) == 0)
 		return;
 
-	if (unlikely(system_state == SYSTEM_BOOTING))
+	if (system_state == SYSTEM_BOOTING || modinit)
 		return text_poke_early(insn, code, size);
 
 	text_poke_bp(insn, code, size, emulate);
@@ -60,7 +71,7 @@ static void __static_call_validate(void *insn, bool tail, bool tramp)
 {
 	u8 opcode = *(u8 *)insn;
 
-	if (tramp && memcmp(insn+5, "SCT", 3)) {
+	if (tramp && memcmp(insn+5, tramp_ud, 3)) {
 		pr_err("trampoline signature fail");
 		BUG();
 	}
@@ -104,14 +115,42 @@ void arch_static_call_transform(void *site, void *tramp, void *func, bool tail)
 
 	if (tramp) {
 		__static_call_validate(tramp, true, true);
-		__static_call_transform(tramp, __sc_insn(!func, true), func);
+		__static_call_transform(tramp, __sc_insn(!func, true), func, false);
 	}
 
 	if (IS_ENABLED(CONFIG_HAVE_STATIC_CALL_INLINE) && site) {
 		__static_call_validate(site, tail, false);
-		__static_call_transform(site, __sc_insn(!func, tail), func);
+		__static_call_transform(site, __sc_insn(!func, tail), func, false);
 	}
 
 	mutex_unlock(&text_mutex);
 }
 EXPORT_SYMBOL_GPL(arch_static_call_transform);
+
+#ifdef CONFIG_RETHUNK
+/*
+ * This is called by apply_returns() to fix up static call trampolines,
+ * specifically ARCH_DEFINE_STATIC_CALL_NULL_TRAMP which is recorded as
+ * having a return trampoline.
+ *
+ * The problem is that static_call() is available before determining
+ * X86_FEATURE_RETHUNK and, by implication, running alternatives.
+ *
+ * This means that __static_call_transform() above can have overwritten the
+ * return trampoline and we now need to fix things up to be consistent.
+ */
+bool __static_call_fixup(void *tramp, u8 op, void *dest)
+{
+	if (memcmp(tramp+5, tramp_ud, 3)) {
+		/* Not a trampoline site, not our problem. */
+		return false;
+	}
+
+	mutex_lock(&text_mutex);
+	if (op == RET_INSN_OPCODE || dest == &__x86_return_thunk)
+		__static_call_transform(tramp, RET, NULL, true);
+	mutex_unlock(&text_mutex);
+
+	return true;
+}
+#endif