Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::3:2 as permitted sender) client-ip=2620:137:e000::3:2;
From:   Uros Bizjak <ubizjak@gmail.com>
To:     x86@kernel.org, linux-kernel@vger.kernel.org
Cc:     Uros Bizjak <ubizjak@gmail.com>,
        Thomas Gleixner <tglx@linutronix.de>,
        Ingo Molnar <mingo@kernel.org>, Borislav Petkov <bp@alien8.de>,
        Dave Hansen <dave.hansen@linux.intel.com>,
        "H. Peter Anvin" <hpa@zytor.com>,
        Peter Zijlstra <peterz@infradead.org>
Subject: [PATCH -tip v2 3/3] x86/callthunks: Fix and unify call thunks assembly snippets
Date:   Sun,  5 Nov 2023 22:34:37 +0100
Message-ID: <20231105213731.1878100-4-ubizjak@gmail.com>
In-Reply-To: <20231105213731.1878100-1-ubizjak@gmail.com>
References: <20231105213731.1878100-1-ubizjak@gmail.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Precedence: bulk

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