Merge tag 'v6.8-rc4' into x86/percpu, to resolve conflicts and refresh the branch

Conflicts:
	arch/x86/include/asm/percpu.h
	arch/x86/include/asm/text-patching.h

Signed-off-by: Ingo Molnar <mingo@kernel.org>

19 files changed, 188 insertions, 199 deletions

diff --git a/arch/x86/lib/cache-smp.c b/arch/x86/lib/cache-smp.c
index 7c48ff4ae8d1..7af743bd3b13 100644
--- a/arch/x86/lib/cache-smp.c
+++ b/arch/x86/lib/cache-smp.c
@@ -1,4 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0
+#include <asm/paravirt.h>
 #include <linux/smp.h>
 #include <linux/export.h>
 
diff --git a/arch/x86/lib/checksum_32.S b/arch/x86/lib/checksum_32.S
index 23318c338db0..68f7fa3e1322 100644
--- a/arch/x86/lib/checksum_32.S
+++ b/arch/x86/lib/checksum_32.S
@@ -21,10 +21,10 @@
  *                   converted to pure assembler
  */
 
+#include <linux/export.h>
 #include <linux/linkage.h>
 #include <asm/errno.h>
 #include <asm/asm.h>
-#include <asm/export.h>
 #include <asm/nospec-branch.h>
 
 /*
diff --git a/arch/x86/lib/clear_page_64.S b/arch/x86/lib/clear_page_64.S
index f74a3e704a1c..2760a15fbc00 100644
--- a/arch/x86/lib/clear_page_64.S
+++ b/arch/x86/lib/clear_page_64.S
@@ -1,7 +1,7 @@
 /* SPDX-License-Identifier: GPL-2.0-only */
+#include <linux/export.h>
 #include <linux/linkage.h>
 #include <asm/asm.h>
-#include <asm/export.h>
 
 /*
  * Most CPUs support enhanced REP MOVSB/STOSB instructions. It is
diff --git a/arch/x86/lib/cmpxchg8b_emu.S b/arch/x86/lib/cmpxchg8b_emu.S
index 8632d7dd1f00..1c96be769adc 100644
--- a/arch/x86/lib/cmpxchg8b_emu.S
+++ b/arch/x86/lib/cmpxchg8b_emu.S
@@ -1,7 +1,7 @@
 /* SPDX-License-Identifier: GPL-2.0-only */
 
+#include <linux/export.h>
 #include <linux/linkage.h>
-#include <asm/export.h>
 #include <asm/percpu.h>
 #include <asm/processor-flags.h>
 
diff --git a/arch/x86/lib/copy_mc.c b/arch/x86/lib/copy_mc.c
index 80efd45a7761..6e8b7e600def 100644
--- a/arch/x86/lib/copy_mc.c
+++ b/arch/x86/lib/copy_mc.c
@@ -70,23 +70,23 @@ unsigned long __must_check copy_mc_to_kernel(void *dst, const void *src, unsigne
 }
 EXPORT_SYMBOL_GPL(copy_mc_to_kernel);
 
-unsigned long __must_check copy_mc_to_user(void *dst, const void *src, unsigned len)
+unsigned long __must_check copy_mc_to_user(void __user *dst, const void *src, unsigned len)
 {
 	unsigned long ret;
 
 	if (copy_mc_fragile_enabled) {
 		__uaccess_begin();
-		ret = copy_mc_fragile(dst, src, len);
+		ret = copy_mc_fragile((__force void *)dst, src, len);
 		__uaccess_end();
 		return ret;
 	}
 
 	if (static_cpu_has(X86_FEATURE_ERMS)) {
 		__uaccess_begin();
-		ret = copy_mc_enhanced_fast_string(dst, src, len);
+		ret = copy_mc_enhanced_fast_string((__force void *)dst, src, len);
 		__uaccess_end();
 		return ret;
 	}
 
-	return copy_user_generic(dst, src, len);
+	return copy_user_generic((__force void *)dst, src, len);
 }
diff --git a/arch/x86/lib/copy_page_64.S b/arch/x86/lib/copy_page_64.S
index 30ea644bf446..d6ae793d08fa 100644
--- a/arch/x86/lib/copy_page_64.S
+++ b/arch/x86/lib/copy_page_64.S
@@ -1,10 +1,10 @@
 /* SPDX-License-Identifier: GPL-2.0 */
 /* Written 2003 by Andi Kleen, based on a kernel by Evandro Menezes */
 
+#include <linux/export.h>
 #include <linux/linkage.h>
 #include <asm/cpufeatures.h>
 #include <asm/alternative.h>
-#include <asm/export.h>
 
 /*
  * Some CPUs run faster using the string copy instructions (sane microcode).
diff --git a/arch/x86/lib/copy_user_64.S b/arch/x86/lib/copy_user_64.S
index 0a81aafed7f8..fc9fb5d06174 100644
--- a/arch/x86/lib/copy_user_64.S
+++ b/arch/x86/lib/copy_user_64.S
@@ -6,11 +6,11 @@
  * Functions to copy from and to user space.
  */
 
+#include <linux/export.h>
 #include <linux/linkage.h>
 #include <asm/cpufeatures.h>
 #include <asm/alternative.h>
 #include <asm/asm.h>
-#include <asm/export.h>
 
 /*
  * rep_movs_alternative - memory copy with exception handling.
diff --git a/arch/x86/lib/copy_user_uncached_64.S b/arch/x86/lib/copy_user_uncached_64.S
index 5c5f38d32672..2918e36eece2 100644
--- a/arch/x86/lib/copy_user_uncached_64.S
+++ b/arch/x86/lib/copy_user_uncached_64.S
@@ -3,9 +3,9 @@
  * Copyright 2023 Linus Torvalds <torvalds@linux-foundation.org>
  */
 
+#include <linux/export.h>
 #include <linux/linkage.h>
 #include <asm/asm.h>
-#include <asm/export.h>
 
 /*
  * copy_user_nocache - Uncached memory copy with exception handling
diff --git a/arch/x86/lib/csum-partial_64.c b/arch/x86/lib/csum-partial_64.c
index cea25ca8b8cf..c9dae65ac01b 100644
--- a/arch/x86/lib/csum-partial_64.c
+++ b/arch/x86/lib/csum-partial_64.c
@@ -11,26 +11,23 @@
 #include <asm/checksum.h>
 #include <asm/word-at-a-time.h>
 
-static inline unsigned short from32to16(unsigned a)
+static inline __wsum csum_finalize_sum(u64 temp64)
 {
-	unsigned short b = a >> 16;
-	asm("addw %w2,%w0\n\t"
-	    "adcw $0,%w0\n"
-	    : "=r" (b)
-	    : "0" (b), "r" (a));
-	return b;
+	return (__force __wsum)((temp64 + ror64(temp64, 32)) >> 32);
 }
 
-static inline __wsum csum_tail(u64 temp64, int odd)
+static inline unsigned long update_csum_40b(unsigned long sum, const unsigned long m[5])
 {
-	unsigned int result;
-
-	result = add32_with_carry(temp64 >> 32, temp64 & 0xffffffff);
-	if (unlikely(odd)) {
-		result = from32to16(result);
-		result = ((result >> 8) & 0xff) | ((result & 0xff) << 8);
-	}
-	return (__force __wsum)result;
+	asm("addq %1,%0\n\t"
+	     "adcq %2,%0\n\t"
+	     "adcq %3,%0\n\t"
+	     "adcq %4,%0\n\t"
+	     "adcq %5,%0\n\t"
+	     "adcq $0,%0"
+		:"+r" (sum)
+		:"m" (m[0]), "m" (m[1]), "m" (m[2]),
+		 "m" (m[3]), "m" (m[4]));
+	return sum;
 }
 
 /*
@@ -47,64 +44,32 @@ static inline __wsum csum_tail(u64 temp64, int odd)
 __wsum csum_partial(const void *buff, int len, __wsum sum)
 {
 	u64 temp64 = (__force u64)sum;
-	unsigned odd;
 
-	odd = 1 & (unsigned long) buff;
-	if (unlikely(odd)) {
-		if (unlikely(len == 0))
-			return sum;
-		temp64 = ror32((__force u32)sum, 8);
-		temp64 += (*(unsigned char *)buff << 8);
-		len--;
-		buff++;
+	/* Do two 40-byte chunks in parallel to get better ILP */
+	if (likely(len >= 80)) {
+		u64 temp64_2 = 0;
+		do {
+			temp64 = update_csum_40b(temp64, buff);
+			temp64_2 = update_csum_40b(temp64_2, buff + 40);
+			buff += 80;
+			len -= 80;
+		} while (len >= 80);
+
+		asm("addq %1,%0\n\t"
+		    "adcq $0,%0"
+		    :"+r" (temp64): "r" (temp64_2));
 	}
 
 	/*
-	 * len == 40 is the hot case due to IPv6 headers, but annotating it likely()
-	 * has noticeable negative affect on codegen for all other cases with
-	 * minimal performance benefit here.
+	 * len == 40 is the hot case due to IPv6 headers, so return
+	 * early for that exact case without checking the tail bytes.
 	 */
-	if (len == 40) {
-		asm("addq 0*8(%[src]),%[res]\n\t"
-		    "adcq 1*8(%[src]),%[res]\n\t"
-		    "adcq 2*8(%[src]),%[res]\n\t"
-		    "adcq 3*8(%[src]),%[res]\n\t"
-		    "adcq 4*8(%[src]),%[res]\n\t"
-		    "adcq $0,%[res]"
-		    : [res] "+r"(temp64)
-		    : [src] "r"(buff), "m"(*(const char(*)[40])buff));
-		return csum_tail(temp64, odd);
-	}
-	if (unlikely(len >= 64)) {
-		/*
-		 * Extra accumulators for better ILP in the loop.
-		 */
-		u64 tmp_accum, tmp_carries;
-
-		asm("xorl %k[tmp_accum],%k[tmp_accum]\n\t"
-		    "xorl %k[tmp_carries],%k[tmp_carries]\n\t"
-		    "subl $64, %[len]\n\t"
-		    "1:\n\t"
-		    "addq 0*8(%[src]),%[res]\n\t"
-		    "adcq 1*8(%[src]),%[res]\n\t"
-		    "adcq 2*8(%[src]),%[res]\n\t"
-		    "adcq 3*8(%[src]),%[res]\n\t"
-		    "adcl $0,%k[tmp_carries]\n\t"
-		    "addq 4*8(%[src]),%[tmp_accum]\n\t"
-		    "adcq 5*8(%[src]),%[tmp_accum]\n\t"
-		    "adcq 6*8(%[src]),%[tmp_accum]\n\t"
-		    "adcq 7*8(%[src]),%[tmp_accum]\n\t"
-		    "adcl $0,%k[tmp_carries]\n\t"
-		    "addq $64, %[src]\n\t"
-		    "subl $64, %[len]\n\t"
-		    "jge 1b\n\t"
-		    "addq %[tmp_accum],%[res]\n\t"
-		    "adcq %[tmp_carries],%[res]\n\t"
-		    "adcq $0,%[res]"
-		    : [tmp_accum] "=&r"(tmp_accum),
-		      [tmp_carries] "=&r"(tmp_carries), [res] "+r"(temp64),
-		      [len] "+r"(len), [src] "+r"(buff)
-		    : "m"(*(const char *)buff));
+	if (len >= 40) {
+		temp64 = update_csum_40b(temp64, buff);
+		len -= 40;
+		if (!len)
+			return csum_finalize_sum(temp64);
+		buff += 40;
 	}
 
 	if (len & 32) {
@@ -143,7 +108,7 @@ __wsum csum_partial(const void *buff, int len, __wsum sum)
 		    : [res] "+r"(temp64)
 		    : [trail] "r"(trail));
 	}
-	return csum_tail(temp64, odd);
+	return csum_finalize_sum(temp64);
 }
 EXPORT_SYMBOL(csum_partial);
 
diff --git a/arch/x86/lib/delay.c b/arch/x86/lib/delay.c
index 0e65d00e2339..23f81ca3f06b 100644
--- a/arch/x86/lib/delay.c
+++ b/arch/x86/lib/delay.c
@@ -128,7 +128,7 @@ static void delay_halt_mwaitx(u64 unused, u64 cycles)
 
 	delay = min_t(u64, MWAITX_MAX_WAIT_CYCLES, cycles);
 	/*
-	 * Use cpu_tss_rw as a cacheline-aligned, seldomly accessed per-cpu
+	 * Use cpu_tss_rw as a cacheline-aligned, seldom accessed per-cpu
 	 * variable as the monitor target.
 	 */
 	 __monitorx(raw_cpu_ptr(&cpu_tss_rw), 0, 0);
diff --git a/arch/x86/lib/getuser.S b/arch/x86/lib/getuser.S
index 9c63713477bb..10d5ed8b5990 100644
--- a/arch/x86/lib/getuser.S
+++ b/arch/x86/lib/getuser.S
@@ -26,6 +26,7 @@
  * as they get called from within inline assembly.
  */
 
+#include <linux/export.h>
 #include <linux/linkage.h>
 #include <asm/page_types.h>
 #include <asm/errno.h>
@@ -33,7 +34,6 @@
 #include <asm/thread_info.h>
 #include <asm/asm.h>
 #include <asm/smap.h>
-#include <asm/export.h>
 
 #define ASM_BARRIER_NOSPEC ALTERNATIVE "", "lfence", X86_FEATURE_LFENCE_RDTSC
 
@@ -163,23 +163,23 @@ SYM_CODE_END(__get_user_8_handle_exception)
 #endif
 
 /* get_user */
-	_ASM_EXTABLE(1b, __get_user_handle_exception)
-	_ASM_EXTABLE(2b, __get_user_handle_exception)
-	_ASM_EXTABLE(3b, __get_user_handle_exception)
+	_ASM_EXTABLE_UA(1b, __get_user_handle_exception)
+	_ASM_EXTABLE_UA(2b, __get_user_handle_exception)
+	_ASM_EXTABLE_UA(3b, __get_user_handle_exception)
 #ifdef CONFIG_X86_64
-	_ASM_EXTABLE(4b, __get_user_handle_exception)
+	_ASM_EXTABLE_UA(4b, __get_user_handle_exception)
 #else
-	_ASM_EXTABLE(4b, __get_user_8_handle_exception)
-	_ASM_EXTABLE(5b, __get_user_8_handle_exception)
+	_ASM_EXTABLE_UA(4b, __get_user_8_handle_exception)
+	_ASM_EXTABLE_UA(5b, __get_user_8_handle_exception)
 #endif
 
 /* __get_user */
-	_ASM_EXTABLE(6b, __get_user_handle_exception)
-	_ASM_EXTABLE(7b, __get_user_handle_exception)
-	_ASM_EXTABLE(8b, __get_user_handle_exception)
+	_ASM_EXTABLE_UA(6b, __get_user_handle_exception)
+	_ASM_EXTABLE_UA(7b, __get_user_handle_exception)
+	_ASM_EXTABLE_UA(8b, __get_user_handle_exception)
 #ifdef CONFIG_X86_64
-	_ASM_EXTABLE(9b, __get_user_handle_exception)
+	_ASM_EXTABLE_UA(9b, __get_user_handle_exception)
 #else
-	_ASM_EXTABLE(9b, __get_user_8_handle_exception)
-	_ASM_EXTABLE(10b, __get_user_8_handle_exception)
+	_ASM_EXTABLE_UA(9b, __get_user_8_handle_exception)
+	_ASM_EXTABLE_UA(10b, __get_user_8_handle_exception)
 #endif
diff --git a/arch/x86/lib/hweight.S b/arch/x86/lib/hweight.S
index 0a152e51d3f5..774bdf3e6f0a 100644
--- a/arch/x86/lib/hweight.S
+++ b/arch/x86/lib/hweight.S
@@ -1,6 +1,6 @@
 /* SPDX-License-Identifier: GPL-2.0 */
+#include <linux/export.h>
 #include <linux/linkage.h>
-#include <asm/export.h>
 
 #include <asm/asm.h>
 
diff --git a/arch/x86/lib/memcpy_64.S b/arch/x86/lib/memcpy_64.S
index 8f95fb267caa..0ae2e1712e2e 100644
--- a/arch/x86/lib/memcpy_64.S
+++ b/arch/x86/lib/memcpy_64.S
@@ -1,12 +1,12 @@
 /* SPDX-License-Identifier: GPL-2.0-only */
 /* Copyright 2002 Andi Kleen */
 
+#include <linux/export.h>
 #include <linux/linkage.h>
 #include <linux/cfi_types.h>
 #include <asm/errno.h>
 #include <asm/cpufeatures.h>
 #include <asm/alternative.h>
-#include <asm/export.h>
 
 .section .noinstr.text, "ax"
 
@@ -40,7 +40,7 @@ SYM_TYPED_FUNC_START(__memcpy)
 SYM_FUNC_END(__memcpy)
 EXPORT_SYMBOL(__memcpy)
 
-SYM_FUNC_ALIAS(memcpy, __memcpy)
+SYM_FUNC_ALIAS_MEMFUNC(memcpy, __memcpy)
 EXPORT_SYMBOL(memcpy)
 
 SYM_FUNC_START_LOCAL(memcpy_orig)
diff --git a/arch/x86/lib/memmove_32.S b/arch/x86/lib/memmove_32.S
index 0588b2c0fc95..35010ba3dd6f 100644
--- a/arch/x86/lib/memmove_32.S
+++ b/arch/x86/lib/memmove_32.S
@@ -1,7 +1,7 @@
 /* SPDX-License-Identifier: GPL-2.0 */
 
+#include <linux/export.h>
 #include <linux/linkage.h>
-#include <asm/export.h>
 
 SYM_FUNC_START(memmove)
 /*
diff --git a/arch/x86/lib/memmove_64.S b/arch/x86/lib/memmove_64.S
index 0559b206fb11..1b60ae81ecd8 100644
--- a/arch/x86/lib/memmove_64.S
+++ b/arch/x86/lib/memmove_64.S
@@ -6,10 +6,10 @@
  * This assembly file is re-written from memmove_64.c file.
  *	- Copyright 2011 Fenghua Yu <fenghua.yu@intel.com>
  */
+#include <linux/export.h>
 #include <linux/linkage.h>
 #include <asm/cpufeatures.h>
 #include <asm/alternative.h>
-#include <asm/export.h>
 
 #undef memmove
 
@@ -212,5 +212,5 @@ SYM_FUNC_START(__memmove)
 SYM_FUNC_END(__memmove)
 EXPORT_SYMBOL(__memmove)
 
-SYM_FUNC_ALIAS(memmove, __memmove)
+SYM_FUNC_ALIAS_MEMFUNC(memmove, __memmove)
 EXPORT_SYMBOL(memmove)
diff --git a/arch/x86/lib/memset_64.S b/arch/x86/lib/memset_64.S
index 7c59a704c458..0199d56cb479 100644
--- a/arch/x86/lib/memset_64.S
+++ b/arch/x86/lib/memset_64.S
@@ -1,10 +1,10 @@
 /* SPDX-License-Identifier: GPL-2.0 */
 /* Copyright 2002 Andi Kleen, SuSE Labs */
 
+#include <linux/export.h>
 #include <linux/linkage.h>
 #include <asm/cpufeatures.h>
 #include <asm/alternative.h>
-#include <asm/export.h>
 
 .section .noinstr.text, "ax"
 
@@ -40,7 +40,7 @@ SYM_FUNC_START(__memset)
 SYM_FUNC_END(__memset)
 EXPORT_SYMBOL(__memset)
 
-SYM_FUNC_ALIAS(memset, __memset)
+SYM_FUNC_ALIAS_MEMFUNC(memset, __memset)
 EXPORT_SYMBOL(memset)
 
 SYM_FUNC_START_LOCAL(memset_orig)
diff --git a/arch/x86/lib/misc.c b/arch/x86/lib/misc.c
index 92cd8ecc3a2c..40b81c338ae5 100644
--- a/arch/x86/lib/misc.c
+++ b/arch/x86/lib/misc.c
@@ -8,7 +8,7 @@
  */
 int num_digits(int val)
 {
-	int m = 10;
+	long long m = 10;
 	int d = 1;
 
 	if (val < 0) {
diff --git a/arch/x86/lib/putuser.S b/arch/x86/lib/putuser.S
index 1451e0c4ae22..975c9c18263d 100644
--- a/arch/x86/lib/putuser.S
+++ b/arch/x86/lib/putuser.S
@@ -11,13 +11,12 @@
  * return an error value in addition to the "real"
  * return value.
  */
+#include <linux/export.h>
 #include <linux/linkage.h>
 #include <asm/thread_info.h>
 #include <asm/errno.h>
 #include <asm/asm.h>
 #include <asm/smap.h>
-#include <asm/export.h>
-
 
 /*
  * __put_user_X
@@ -56,7 +55,6 @@ SYM_FUNC_END(__put_user_1)
 EXPORT_SYMBOL(__put_user_1)
 
 SYM_FUNC_START(__put_user_nocheck_1)
-	ENDBR
 	ASM_STAC
 2:	movb %al,(%_ASM_CX)
 	xor %ecx,%ecx
@@ -76,7 +74,6 @@ SYM_FUNC_END(__put_user_2)
 EXPORT_SYMBOL(__put_user_2)
 
 SYM_FUNC_START(__put_user_nocheck_2)
-	ENDBR
 	ASM_STAC
 4:	movw %ax,(%_ASM_CX)
 	xor %ecx,%ecx
@@ -96,7 +93,6 @@ SYM_FUNC_END(__put_user_4)
 EXPORT_SYMBOL(__put_user_4)
 
 SYM_FUNC_START(__put_user_nocheck_4)
-	ENDBR
 	ASM_STAC
 6:	movl %eax,(%_ASM_CX)
 	xor %ecx,%ecx
@@ -119,7 +115,6 @@ SYM_FUNC_END(__put_user_8)
 EXPORT_SYMBOL(__put_user_8)
 
 SYM_FUNC_START(__put_user_nocheck_8)
-	ENDBR
 	ASM_STAC
 9:	mov %_ASM_AX,(%_ASM_CX)
 #ifdef CONFIG_X86_32
@@ -138,15 +133,15 @@ SYM_CODE_START_LOCAL(__put_user_handle_exception)
 	RET
 SYM_CODE_END(__put_user_handle_exception)
 
-	_ASM_EXTABLE(1b, __put_user_handle_exception)
-	_ASM_EXTABLE(2b, __put_user_handle_exception)
-	_ASM_EXTABLE(3b, __put_user_handle_exception)
-	_ASM_EXTABLE(4b, __put_user_handle_exception)
-	_ASM_EXTABLE(5b, __put_user_handle_exception)
-	_ASM_EXTABLE(6b, __put_user_handle_exception)
-	_ASM_EXTABLE(7b, __put_user_handle_exception)
-	_ASM_EXTABLE(9b, __put_user_handle_exception)
+	_ASM_EXTABLE_UA(1b, __put_user_handle_exception)
+	_ASM_EXTABLE_UA(2b, __put_user_handle_exception)
+	_ASM_EXTABLE_UA(3b, __put_user_handle_exception)
+	_ASM_EXTABLE_UA(4b, __put_user_handle_exception)
+	_ASM_EXTABLE_UA(5b, __put_user_handle_exception)
+	_ASM_EXTABLE_UA(6b, __put_user_handle_exception)
+	_ASM_EXTABLE_UA(7b, __put_user_handle_exception)
+	_ASM_EXTABLE_UA(9b, __put_user_handle_exception)
 #ifdef CONFIG_X86_32
-	_ASM_EXTABLE(8b, __put_user_handle_exception)
-	_ASM_EXTABLE(10b, __put_user_handle_exception)
+	_ASM_EXTABLE_UA(8b, __put_user_handle_exception)
+	_ASM_EXTABLE_UA(10b, __put_user_handle_exception)
 #endif
diff --git a/arch/x86/lib/retpoline.S b/arch/x86/lib/retpoline.S
index cd86aeb5fdd3..7b2589877d06 100644
--- a/arch/x86/lib/retpoline.S
+++ b/arch/x86/lib/retpoline.S
@@ -1,12 +1,12 @@
 /* SPDX-License-Identifier: GPL-2.0 */
 
+#include <linux/export.h>
 #include <linux/stringify.h>
 #include <linux/linkage.h>
 #include <asm/dwarf2.h>
 #include <asm/cpufeatures.h>
 #include <asm/alternative.h>
 #include <asm/asm-offsets.h>
-#include <asm/export.h>
 #include <asm/nospec-branch.h>
 #include <asm/unwind_hints.h>
 #include <asm/percpu.h>
@@ -126,11 +126,19 @@ SYM_CODE_END(__x86_indirect_jump_thunk_array)
 #include <asm/GEN-for-each-reg.h>
 #undef GEN
 #endif
+
+#ifdef CONFIG_RETHUNK
+
 /*
- * This function name is magical and is used by -mfunction-return=thunk-extern
- * for the compiler to generate JMPs to it.
+ * Be careful here: that label cannot really be removed because in
+ * some configurations and toolchains, the JMP __x86_return_thunk the
+ * compiler issues is either a short one or the compiler doesn't use
+ * relocations for same-section JMPs and that breaks the returns
+ * detection logic in apply_returns() and in objtool.
  */
-#ifdef CONFIG_RETHUNK
+	.section .text..__x86.return_thunk
+
+#ifdef CONFIG_CPU_SRSO
 
 /*
  * srso_alias_untrain_ret() and srso_alias_safe_ret() are placed at
@@ -147,29 +155,18 @@ SYM_CODE_END(__x86_indirect_jump_thunk_array)
  *
  * As a result, srso_alias_safe_ret() becomes a safe return.
  */
-#ifdef CONFIG_CPU_SRSO
-	.section .text..__x86.rethunk_untrain
-
-SYM_START(srso_alias_untrain_ret, SYM_L_GLOBAL, SYM_A_NONE)
+	.pushsection .text..__x86.rethunk_untrain
+SYM_CODE_START_NOALIGN(srso_alias_untrain_ret)
 	UNWIND_HINT_FUNC
 	ANNOTATE_NOENDBR
 	ASM_NOP2
 	lfence
 	jmp srso_alias_return_thunk
 SYM_FUNC_END(srso_alias_untrain_ret)
-__EXPORT_THUNK(srso_alias_untrain_ret)
-
-	.section .text..__x86.rethunk_safe
-#else
-/* dummy definition for alternatives */
-SYM_START(srso_alias_untrain_ret, SYM_L_GLOBAL, SYM_A_NONE)
-	ANNOTATE_UNRET_SAFE
-	ret
-	int3
-SYM_FUNC_END(srso_alias_untrain_ret)
-#endif
+	.popsection
 
-SYM_START(srso_alias_safe_ret, SYM_L_GLOBAL, SYM_A_NONE)
+	.pushsection .text..__x86.rethunk_safe
+SYM_CODE_START_NOALIGN(srso_alias_safe_ret)
 	lea 8(%_ASM_SP), %_ASM_SP
 	UNWIND_HINT_FUNC
 	ANNOTATE_UNRET_SAFE
@@ -177,14 +174,63 @@ SYM_START(srso_alias_safe_ret, SYM_L_GLOBAL, SYM_A_NONE)
 	int3
 SYM_FUNC_END(srso_alias_safe_ret)
 
-	.section .text..__x86.return_thunk
-
-SYM_CODE_START(srso_alias_return_thunk)
+SYM_CODE_START_NOALIGN(srso_alias_return_thunk)
 	UNWIND_HINT_FUNC
 	ANNOTATE_NOENDBR
 	call srso_alias_safe_ret
 	ud2
 SYM_CODE_END(srso_alias_return_thunk)
+	.popsection
+
+/*
+ * SRSO untraining sequence for Zen1/2, similar to retbleed_untrain_ret()
+ * above. On kernel entry, srso_untrain_ret() is executed which is a
+ *
+ * movabs $0xccccc30824648d48,%rax
+ *
+ * and when the return thunk executes the inner label srso_safe_ret()
+ * later, it is a stack manipulation and a RET which is mispredicted and
+ * thus a "safe" one to use.
+ */
+	.align 64
+	.skip 64 - (srso_safe_ret - srso_untrain_ret), 0xcc
+SYM_CODE_START_LOCAL_NOALIGN(srso_untrain_ret)
+	ANNOTATE_NOENDBR
+	.byte 0x48, 0xb8
+
+/*
+ * This forces the function return instruction to speculate into a trap
+ * (UD2 in srso_return_thunk() below).  This RET will then mispredict
+ * and execution will continue at the return site read from the top of
+ * the stack.
+ */
+SYM_INNER_LABEL(srso_safe_ret, SYM_L_GLOBAL)
+	lea 8(%_ASM_SP), %_ASM_SP
+	ret
+	int3
+	int3
+	/* end of movabs */
+	lfence
+	call srso_safe_ret
+	ud2
+SYM_CODE_END(srso_safe_ret)
+SYM_FUNC_END(srso_untrain_ret)
+
+SYM_CODE_START(srso_return_thunk)
+	UNWIND_HINT_FUNC
+	ANNOTATE_NOENDBR
+	call srso_safe_ret
+	ud2
+SYM_CODE_END(srso_return_thunk)
+
+#define JMP_SRSO_UNTRAIN_RET "jmp srso_untrain_ret"
+#define JMP_SRSO_ALIAS_UNTRAIN_RET "jmp srso_alias_untrain_ret"
+#else /* !CONFIG_CPU_SRSO */
+#define JMP_SRSO_UNTRAIN_RET "ud2"
+#define JMP_SRSO_ALIAS_UNTRAIN_RET "ud2"
+#endif /* CONFIG_CPU_SRSO */
+
+#ifdef CONFIG_CPU_UNRET_ENTRY
 
 /*
  * Some generic notes on the untraining sequences:
@@ -216,7 +262,7 @@ SYM_CODE_END(srso_alias_return_thunk)
  */
 	.align 64
 	.skip 64 - (retbleed_return_thunk - retbleed_untrain_ret), 0xcc
-SYM_START(retbleed_untrain_ret, SYM_L_GLOBAL, SYM_A_NONE)
+SYM_CODE_START_LOCAL_NOALIGN(retbleed_untrain_ret)
 	ANNOTATE_NOENDBR
 	/*
 	 * As executed from retbleed_untrain_ret, this is:
@@ -264,72 +310,27 @@ SYM_CODE_END(retbleed_return_thunk)
 	jmp retbleed_return_thunk
 	int3
 SYM_FUNC_END(retbleed_untrain_ret)
-__EXPORT_THUNK(retbleed_untrain_ret)
 
-/*
- * SRSO untraining sequence for Zen1/2, similar to retbleed_untrain_ret()
- * above. On kernel entry, srso_untrain_ret() is executed which is a
- *
- * movabs $0xccccc30824648d48,%rax
- *
- * and when the return thunk executes the inner label srso_safe_ret()
- * later, it is a stack manipulation and a RET which is mispredicted and
- * thus a "safe" one to use.
- */
-	.align 64
-	.skip 64 - (srso_safe_ret - srso_untrain_ret), 0xcc
-SYM_START(srso_untrain_ret, SYM_L_GLOBAL, SYM_A_NONE)
-	ANNOTATE_NOENDBR
-	.byte 0x48, 0xb8
+#define JMP_RETBLEED_UNTRAIN_RET "jmp retbleed_untrain_ret"
+#else /* !CONFIG_CPU_UNRET_ENTRY */
+#define JMP_RETBLEED_UNTRAIN_RET "ud2"
+#endif /* CONFIG_CPU_UNRET_ENTRY */
 
-/*
- * This forces the function return instruction to speculate into a trap
- * (UD2 in srso_return_thunk() below).  This RET will then mispredict
- * and execution will continue at the return site read from the top of
- * the stack.
- */
-SYM_INNER_LABEL(srso_safe_ret, SYM_L_GLOBAL)
-	lea 8(%_ASM_SP), %_ASM_SP
-	ret
-	int3
-	int3
-	/* end of movabs */
-	lfence
-	call srso_safe_ret
-	ud2
-SYM_CODE_END(srso_safe_ret)
-SYM_FUNC_END(srso_untrain_ret)
-__EXPORT_THUNK(srso_untrain_ret)
-
-SYM_CODE_START(srso_return_thunk)
-	UNWIND_HINT_FUNC
-	ANNOTATE_NOENDBR
-	call srso_safe_ret
-	ud2
-SYM_CODE_END(srso_return_thunk)
+#if defined(CONFIG_CPU_UNRET_ENTRY) || defined(CONFIG_CPU_SRSO)
 
 SYM_FUNC_START(entry_untrain_ret)
-	ALTERNATIVE_2 "jmp retbleed_untrain_ret", \
-		      "jmp srso_untrain_ret", X86_FEATURE_SRSO, \
-		      "jmp srso_alias_untrain_ret", X86_FEATURE_SRSO_ALIAS
+	ALTERNATIVE_2 JMP_RETBLEED_UNTRAIN_RET,				\
+		      JMP_SRSO_UNTRAIN_RET, X86_FEATURE_SRSO,		\
+		      JMP_SRSO_ALIAS_UNTRAIN_RET, X86_FEATURE_SRSO_ALIAS
 SYM_FUNC_END(entry_untrain_ret)
 __EXPORT_THUNK(entry_untrain_ret)
 
-SYM_CODE_START(__x86_return_thunk)
-	UNWIND_HINT_FUNC
-	ANNOTATE_NOENDBR
-	ANNOTATE_UNRET_SAFE
-	ret
-	int3
-SYM_CODE_END(__x86_return_thunk)
-EXPORT_SYMBOL(__x86_return_thunk)
-
-#endif /* CONFIG_RETHUNK */
+#endif /* CONFIG_CPU_UNRET_ENTRY || CONFIG_CPU_SRSO */
 
 #ifdef CONFIG_CALL_DEPTH_TRACKING
 
 	.align 64
-SYM_FUNC_START(__x86_return_skl)
+SYM_FUNC_START(call_depth_return_thunk)
 	ANNOTATE_NOENDBR
 	/*
 	 * Keep the hotpath in a 16byte I-fetch for the non-debug
@@ -356,6 +357,33 @@ SYM_FUNC_START(__x86_return_skl)
 	ANNOTATE_UNRET_SAFE
 	ret
 	int3
-SYM_FUNC_END(__x86_return_skl)
+SYM_FUNC_END(call_depth_return_thunk)
 
 #endif /* CONFIG_CALL_DEPTH_TRACKING */
+
+/*
+ * This function name is magical and is used by -mfunction-return=thunk-extern
+ * for the compiler to generate JMPs to it.
+ *
+ * This code is only used during kernel boot or module init.  All
+ * 'JMP __x86_return_thunk' sites are changed to something else by
+ * apply_returns().
+ *
+ * This should be converted eventually to call a warning function which
+ * should scream loudly when the default return thunk is called after
+ * alternatives have been applied.
+ *
+ * That warning function cannot BUG() because the bug splat cannot be
+ * displayed in all possible configurations, leading to users not really
+ * knowing why the machine froze.
+ */
+SYM_CODE_START(__x86_return_thunk)
+	UNWIND_HINT_FUNC
+	ANNOTATE_NOENDBR
+	ANNOTATE_UNRET_SAFE
+	ret
+	int3
+SYM_CODE_END(__x86_return_thunk)
+EXPORT_SYMBOL(__x86_return_thunk)
+
+#endif /* CONFIG_RETHUNK */