Currently thunk debug macros explicitly define %gs: segment register
prefix for their percpu variables. This is not compatible with
!CONFIG_SMP, which requires non-prefixed percpu variables.

Fix call thunks debug macros to use PER_CPU_VAR macro from percpu.h
to conditionally use %gs: segment register prefix, depending on
CONFIG_SMP.

Finally, unify ASM_ prefixed assembly macros with their non-prefixed
variants. With support of %rip-relative relocations in place, call
thunk templates allow %rip-relative addressing, so unified assembly
snippet can be used everywhere.

Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Uros Bizjak <ubizjak@gmail.com>
---
 arch/x86/include/asm/nospec-branch.h | 23 +++++++----------------
 1 file changed, 7 insertions(+), 16 deletions(-)

diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h
index f93e9b96927a..6f677be6bdb9 100644
--- a/arch/x86/include/asm/nospec-branch.h
+++ b/arch/x86/include/asm/nospec-branch.h
@@ -59,13 +59,13 @@
 
 #ifdef CONFIG_CALL_THUNKS_DEBUG
 # define CALL_THUNKS_DEBUG_INC_CALLS				\
-	incq	%gs:__x86_call_count;
+	incq	PER_CPU_VAR(__x86_call_count);
 # define CALL_THUNKS_DEBUG_INC_RETS				\
-	incq	%gs:__x86_ret_count;
+	incq	PER_CPU_VAR(__x86_ret_count);
 # define CALL_THUNKS_DEBUG_INC_STUFFS				\
-	incq	%gs:__x86_stuffs_count;
+	incq	PER_CPU_VAR(__x86_stuffs_count);
 # define CALL_THUNKS_DEBUG_INC_CTXSW				\
-	incq	%gs:__x86_ctxsw_count;
+	incq	PER_CPU_VAR(__x86_ctxsw_count);
 #else
 # define CALL_THUNKS_DEBUG_INC_CALLS
 # define CALL_THUNKS_DEBUG_INC_RETS
@@ -80,9 +80,6 @@
 #define CREDIT_CALL_DEPTH					\
 	movq	$-1, PER_CPU_VAR(pcpu_hot + X86_call_depth);
 
-#define ASM_CREDIT_CALL_DEPTH					\
-	movq	$-1, PER_CPU_VAR(pcpu_hot + X86_call_depth);
-
 #define RESET_CALL_DEPTH					\
 	xor	%eax, %eax;					\
 	bts	$63, %rax;					\
@@ -95,20 +92,14 @@
 	CALL_THUNKS_DEBUG_INC_CALLS
 
 #define INCREMENT_CALL_DEPTH					\
-	sarq	$5, %gs:pcpu_hot + X86_call_depth;		\
-	CALL_THUNKS_DEBUG_INC_CALLS
-
-#define ASM_INCREMENT_CALL_DEPTH				\
 	sarq	$5, PER_CPU_VAR(pcpu_hot + X86_call_depth);	\
 	CALL_THUNKS_DEBUG_INC_CALLS
 
 #else
 #define CREDIT_CALL_DEPTH
-#define ASM_CREDIT_CALL_DEPTH
 #define RESET_CALL_DEPTH
-#define INCREMENT_CALL_DEPTH
-#define ASM_INCREMENT_CALL_DEPTH
 #define RESET_CALL_DEPTH_FROM_CALL
+#define INCREMENT_CALL_DEPTH
 #endif
 
 /*
@@ -158,7 +149,7 @@
 	jnz	771b;					\
 	/* barrier for jnz misprediction */		\
 	lfence;						\
-	ASM_CREDIT_CALL_DEPTH				\
+	CREDIT_CALL_DEPTH				\
 	CALL_THUNKS_DEBUG_INC_CTXSW
 #else
 /*
@@ -311,7 +302,7 @@
 .macro CALL_DEPTH_ACCOUNT
 #ifdef CONFIG_CALL_DEPTH_TRACKING
 	ALTERNATIVE "",							\
-		    __stringify(ASM_INCREMENT_CALL_DEPTH), X86_FEATURE_CALL_DEPTH
+		    __stringify(INCREMENT_CALL_DEPTH), X86_FEATURE_CALL_DEPTH
 #endif
 .endm
 
-- 
2.41.0

Hi Uros,

kernel test robot noticed the following build errors:

[auto build test ERROR on tip/x86/core]
[also build test ERROR on tip/master tip/auto-latest linus/master v6.6 next-20231103]
[If your patch is applied to the wrong git tree, kindly drop us a note.
And when submitting patch, we suggest to use '--base' as documented in
https://git-scm.com/docs/git-format-patch#_base_tree_information]

url:    https://github.com/intel-lab-lkp/linux/commits/Uros-Bizjak/x86-callthunks-Move-call-thunk-template-to-S-file/20231102-193542
base:   tip/x86/core
patch link:    https://lore.kernel.org/r/20231102112850.3448745-4-ubizjak%40gmail.com
patch subject: [PATCH 3/3] x86/callthunks: Fix and unify call thunks assembly snippets
config: x86_64-allyesconfig (https://download.01.org/0day-ci/archive/20231105/202311051652.38OyamEq-lkp@intel.com/config)
compiler: gcc-12 (Debian 12.2.0-14) 12.2.0
reproduce (this is a W=1 build): (https://download.01.org/0day-ci/archive/20231105/202311051652.38OyamEq-lkp@intel.com/reproduce)

If you fix the issue in a separate patch/commit (i.e. not just a new version of
the same patch/commit), kindly add following tags
| Reported-by: kernel test robot <lkp@intel.com>
| Closes: https://lore.kernel.org/oe-kbuild-all/202311051652.38OyamEq-lkp@intel.com/

All errors (new ones prefixed by >>):

   /tmp/ccwZh9MG.s: Assembler messages:
>> /tmp/ccwZh9MG.s:27: Error: junk `(pcpu_hot+16)' after expression
>> /tmp/ccwZh9MG.s:27: Error: junk `(__x86_call_count)' after expression

-- 
0-DAY CI Kernel Test Service
https://github.com/intel/lkp-tests/wiki