From: Brian Gerst <brgerst@gmail.com>
Date: Mon, 3 Mar 2025 16:52:40 +0000 (-0500)
Subject: x86/retbleed: Move call depth to percpu hot section
X-Git-Tag: v6.15-rc1~216^2~80
X-Git-Url: http://git.ipfire.org/cgi-bin/gitweb.cgi?a=commitdiff_plain;h=839be1619fb897364b782997bc2c5d072d7a79f2;p=thirdparty%2Fkernel%2Flinux.git

x86/retbleed: Move call depth to percpu hot section

No functional change.

Signed-off-by: Brian Gerst <brgerst@gmail.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Acked-by: Uros Bizjak <ubizjak@gmail.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://lore.kernel.org/r/20250303165246.2175811-6-brgerst@gmail.com
---

diff --git a/arch/x86/include/asm/current.h b/arch/x86/include/asm/current.h
index f988462d8b696..8ba2c0f8bcaf9 100644
--- a/arch/x86/include/asm/current.h
+++ b/arch/x86/include/asm/current.h
@@ -14,9 +14,6 @@ struct task_struct;
 
 struct pcpu_hot {
 	struct task_struct	*current_task;
-#ifdef CONFIG_MITIGATION_CALL_DEPTH_TRACKING
-	u64			call_depth;
-#endif
 	unsigned long		top_of_stack;
 	void			*hardirq_stack_ptr;
 	u16			softirq_pending;
diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h
index aee26bb8230f8..44c6076fd22ba 100644
--- a/arch/x86/include/asm/nospec-branch.h
+++ b/arch/x86/include/asm/nospec-branch.h
@@ -12,7 +12,6 @@
 #include <asm/msr-index.h>
 #include <asm/unwind_hints.h>
 #include <asm/percpu.h>
-#include <asm/current.h>
 
 /*
  * Call depth tracking for Intel SKL CPUs to address the RSB underflow
@@ -78,21 +77,21 @@
 #include <asm/asm-offsets.h>
 
 #define CREDIT_CALL_DEPTH					\
-	movq	$-1, PER_CPU_VAR(pcpu_hot + X86_call_depth);
+	movq	$-1, PER_CPU_VAR(__x86_call_depth);
 
 #define RESET_CALL_DEPTH					\
 	xor	%eax, %eax;					\
 	bts	$63, %rax;					\
-	movq	%rax, PER_CPU_VAR(pcpu_hot + X86_call_depth);
+	movq	%rax, PER_CPU_VAR(__x86_call_depth);
 
 #define RESET_CALL_DEPTH_FROM_CALL				\
 	movb	$0xfc, %al;					\
 	shl	$56, %rax;					\
-	movq	%rax, PER_CPU_VAR(pcpu_hot + X86_call_depth);	\
+	movq	%rax, PER_CPU_VAR(__x86_call_depth);		\
 	CALL_THUNKS_DEBUG_INC_CALLS
 
 #define INCREMENT_CALL_DEPTH					\
-	sarq	$5, PER_CPU_VAR(pcpu_hot + X86_call_depth);	\
+	sarq	$5, PER_CPU_VAR(__x86_call_depth);		\
 	CALL_THUNKS_DEBUG_INC_CALLS
 
 #else
@@ -387,6 +386,8 @@ extern void call_depth_return_thunk(void);
 		    __stringify(INCREMENT_CALL_DEPTH),		\
 		    X86_FEATURE_CALL_DEPTH)
 
+DECLARE_PER_CPU_CACHE_HOT(u64, __x86_call_depth);
+
 #ifdef CONFIG_CALL_THUNKS_DEBUG
 DECLARE_PER_CPU(u64, __x86_call_count);
 DECLARE_PER_CPU(u64, __x86_ret_count);
diff --git a/arch/x86/kernel/asm-offsets.c b/arch/x86/kernel/asm-offsets.c
index a98020bf31bb4..6fae88f8ae1e7 100644
--- a/arch/x86/kernel/asm-offsets.c
+++ b/arch/x86/kernel/asm-offsets.c
@@ -109,9 +109,6 @@ static void __used common(void)
 	OFFSET(TSS_sp2, tss_struct, x86_tss.sp2);
 	OFFSET(X86_top_of_stack, pcpu_hot, top_of_stack);
 	OFFSET(X86_current_task, pcpu_hot, current_task);
-#ifdef CONFIG_MITIGATION_CALL_DEPTH_TRACKING
-	OFFSET(X86_call_depth, pcpu_hot, call_depth);
-#endif
 #if IS_ENABLED(CONFIG_CRYPTO_ARIA_AESNI_AVX_X86_64)
 	/* Offset for fields in aria_ctx */
 	BLANK();
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index a9d61537d4a64..fd224ae57d62e 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -2075,6 +2075,14 @@ DEFINE_PER_CPU_CACHE_HOT(int, __preempt_count) = INIT_PREEMPT_COUNT;
 EXPORT_PER_CPU_SYMBOL(__preempt_count);
 
 #ifdef CONFIG_X86_64
+/*
+ * Note: Do not make this dependant on CONFIG_MITIGATION_CALL_DEPTH_TRACKING
+ * so that this space is reserved in the hot cache section even when the
+ * mitigation is disabled.
+ */
+DEFINE_PER_CPU_CACHE_HOT(u64, __x86_call_depth);
+EXPORT_PER_CPU_SYMBOL(__x86_call_depth);
+
 static void wrmsrl_cstar(unsigned long val)
 {
 	/*
diff --git a/arch/x86/lib/retpoline.S b/arch/x86/lib/retpoline.S
index 038f49a43ab43..a26c43abd47d8 100644
--- a/arch/x86/lib/retpoline.S
+++ b/arch/x86/lib/retpoline.S
@@ -343,7 +343,7 @@ SYM_FUNC_START(call_depth_return_thunk)
 	 * case.
 	 */
 	CALL_THUNKS_DEBUG_INC_RETS
-	shlq	$5, PER_CPU_VAR(pcpu_hot + X86_call_depth)
+	shlq	$5, PER_CPU_VAR(__x86_call_depth)
 	jz	1f
 	ANNOTATE_UNRET_SAFE
 	ret