icp: properly fix all RETs in x86_64 Asm code

Commit 43569ee374 ("Fix objtool: missing int3 after ret warning")
addressed replacing all `ret`s in x86 asm code to a macro in the
Linux kernel in order to enable SLS. That was done by copying the
upstream macro definitions and fixed objtool complaints.
Since then, several more mitigations were introduced, including
Rethunk. It requires to have a jump to one of the thunks in order
to work, so the RET macro was changed again. And, as ZFS code
didn't use the mainline defition, but copied it, this is currently
missing.

Objtool reminds about it time to time (Clang 16, CONFIG_RETHUNK=y):

fs/zfs/lua/zlua.o: warning: objtool: setjmp+0x25: 'naked' return
 found in RETHUNK build
fs/zfs/lua/zlua.o: warning: objtool: longjmp+0x27: 'naked' return
 found in RETHUNK build

Do it the following way:
* if we're building under Linux, unconditionally include
  <linux/linkage.h> in the related files. It is available in x86
  sources since even pre-2.6 times, so doesn't need any conftests;
* then, if RET macro is available, it will be used directly, so that
  we will always have the version actual to the kernel we build;
* if there's no such macro, we define it as a simple `ret`, as it
  was on pre-SLS times.

This ensures we always have the up-to-date definition with no need
to update it manually, and at the same time is safe for the whole
variety of kernels ZFS module supports.
Then, there's a couple more "naked" rets left in the code, they're
just defined as:

	.byte 0xf3,0xc3

In fact, this is just:

	rep ret

`rep ret` instead of just `ret` seems to mitigate performance issues
on some old AMD processors and most likely makes no sense as of
today.
Anyways, address those rets, so that they will be protected with
Rethunk and SLS. Include <sys/asm_linkage.h> here which now always
has RET definition and replace those constructs with just RET.
This wipes the last couple of places with unpatched rets objtool's
been complaining about.

Reviewed-by: Attila Fülöp <attila@fueloep.org>
Reviewed-by: Tino Reichardt <milky-zfs@mcmilk.de>
Reviewed-by: Richard Yao <richard.yao@alumni.stonybrook.edu>
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Signed-off-by: Alexander Lobakin <alobakin@pm.me>
Closes #14035

module/icp/asm-x86_64/modes/aesni-gcm-x86_64.S

@@ -47,6 +47,9 @@
 #if defined(__x86_64__) && defined(HAVE_AVX) && \
     defined(HAVE_AES) && defined(HAVE_PCLMULQDQ)
 
+#define _ASM
+#include <sys/asm_linkage.h>
+
 .extern gcm_avx_can_use_movbe
 
 .text
@@ -363,7 +366,7 @@ _aesni_ctr32_ghash_6x:
 	vpxor	16+8(%rsp),%xmm8,%xmm8
 	vpxor	%xmm4,%xmm8,%xmm8
 
-	.byte	0xf3,0xc3
+	RET
 .cfi_endproc
 .size	_aesni_ctr32_ghash_6x,.-_aesni_ctr32_ghash_6x
 #endif /* ifdef HAVE_MOVBE */
@@ -691,7 +694,7 @@ _aesni_ctr32_ghash_no_movbe_6x:
 	vpxor	16+8(%rsp),%xmm8,%xmm8
 	vpxor	%xmm4,%xmm8,%xmm8
 
-	.byte	0xf3,0xc3
+	RET
 .cfi_endproc
 .size	_aesni_ctr32_ghash_no_movbe_6x,.-_aesni_ctr32_ghash_no_movbe_6x
 
@@ -810,7 +813,7 @@ aesni_gcm_decrypt:
 .cfi_def_cfa_register	%rsp
 .Lgcm_dec_abort:
 	movq	%r10,%rax
-	.byte	0xf3,0xc3
+	RET
 .cfi_endproc
 .size	aesni_gcm_decrypt,.-aesni_gcm_decrypt
 .type	_aesni_ctr32_6x,@function
@@ -880,7 +883,7 @@ _aesni_ctr32_6x:
 	vmovups	%xmm14,80(%rsi)
 	leaq	96(%rsi),%rsi
 
-	.byte	0xf3,0xc3
+	RET
 .align	32
 .Lhandle_ctr32_2:
 	vpshufb	%xmm0,%xmm1,%xmm6
@@ -1186,7 +1189,7 @@ aesni_gcm_encrypt:
 .cfi_def_cfa_register	%rsp
 .Lgcm_enc_abort:
 	movq	%r10,%rax
-	.byte	0xf3,0xc3
+	RET
 .cfi_endproc
 .size	aesni_gcm_encrypt,.-aesni_gcm_encrypt
 

module/icp/asm-x86_64/modes/ghash-x86_64.S

@@ -97,6 +97,9 @@
 #if defined(__x86_64__) && defined(HAVE_AVX) && \
     defined(HAVE_AES) && defined(HAVE_PCLMULQDQ)
 
+#define _ASM
+#include <sys/asm_linkage.h>
+
 .text
 
 .globl	gcm_gmult_clmul
@@ -149,7 +152,7 @@ gcm_gmult_clmul:
 	pxor	%xmm1,%xmm0
 .byte	102,15,56,0,197
 	movdqu	%xmm0,(%rdi)
-	.byte	0xf3,0xc3
+	RET
 .cfi_endproc
 .size	gcm_gmult_clmul,.-gcm_gmult_clmul
 
@@ -262,7 +265,7 @@ gcm_init_htab_avx:
 	vmovdqu	%xmm5,-16(%rdi)
 
 	vzeroupper
-	.byte	0xf3,0xc3
+	RET
 .cfi_endproc
 .size	gcm_init_htab_avx,.-gcm_init_htab_avx
 
@@ -649,7 +652,7 @@ gcm_ghash_avx:
 	vpshufb	%xmm13,%xmm10,%xmm10
 	vmovdqu	%xmm10,(%rdi)
 	vzeroupper
-	.byte	0xf3,0xc3
+	RET
 .cfi_endproc
 .size	gcm_ghash_avx,.-gcm_ghash_avx
 .align	64

module/icp/include/sys/ia32/asm_linkage.h

@@ -30,9 +30,11 @@
 #include <sys/stack.h>
 #include <sys/trap.h>
 
-#if defined(__linux__) && defined(CONFIG_SLS)
-#define	RET	ret; int3
-#else
+#if defined(_KERNEL) && defined(__linux__)
+#include <linux/linkage.h>
+#endif
+
+#ifndef RET
 #define	RET	ret
 #endif
 
@@ -204,6 +206,7 @@ sym1	= sym2
  * insert the calls to mcount for profiling. ENTRY_NP is identical, but
  * never calls mcount.
  */
+#undef ENTRY
 #define	ENTRY(x) \
 	.text; \
 	.align	ASM_ENTRY_ALIGN; \

module/lua/setjmp/setjmp_x86_64.S

@@ -23,7 +23,15 @@
  * Copyright (c) 1992, 2010, Oracle and/or its affiliates. All rights reserved.
  */
 
+#if defined(_KERNEL) && defined(__linux__)
+#include <linux/linkage.h>
+#endif
 
+#ifndef RET
+#define	RET	ret
+#endif
+
+#undef ENTRY
 #define	ENTRY(x) \
 	.text; \
 	.align	8; \
@@ -34,13 +42,6 @@ x:
 #define	SET_SIZE(x) \
 	.size	x, [.-x]
 
-
-#if defined(__linux__) && defined(CONFIG_SLS)
-#define	RET	ret; int3
-#else
-#define	RET	ret
-#endif
-
 /*
  * Setjmp and longjmp implement non-local gotos using state vectors
  * type label_t.