[tip: x86/core] x86/retbleed: Move call depth to percpu hot section

[tip-bot2 for Brian Gerst]

The following commit has been merged into the x86/core branch of tip:

Commit-ID:     7ca6fc13aed7d7524d8a6e301a13f153a5976024
Gitweb:        https://git.kernel.org/tip/7ca6fc13aed7d7524d8a6e301a13f153a5976024
Author:        Brian Gerst <brgerst@xxxxxxxxx>
AuthorDate:    Mon, 03 Mar 2025 11:52:40 -05:00
Committer:     Ingo Molnar <mingo@xxxxxxxxxx>
CommitterDate: Tue, 04 Mar 2025 20:18:02 +01:00

x86/retbleed: Move call depth to percpu hot section

No functional change.

Signed-off-by: Brian Gerst <brgerst@xxxxxxxxx>
Signed-off-by: Ingo Molnar <mingo@xxxxxxxxxx>
Acked-by: Uros Bizjak <ubizjak@xxxxxxxxx>
Cc: Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx>
Cc: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
Link: https://lore.kernel.org/r/20250303165246.2175811-6-brgerst@xxxxxxxxx
---
 arch/x86/include/asm/current.h       |  3 ---
 arch/x86/include/asm/nospec-branch.h | 11 ++++++-----
 arch/x86/kernel/asm-offsets.c        |  3 ---
 arch/x86/kernel/cpu/common.c         |  8 ++++++++
 arch/x86/lib/retpoline.S             |  2 +-
 5 files changed, 15 insertions(+), 12 deletions(-)

diff --git a/arch/x86/include/asm/current.h b/arch/x86/include/asm/current.h
index f988462..8ba2c0f 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 aee26bb..44c6076 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 a98020b..6fae88f 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 a9d6153..fd224ae 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 038f49a..a26c43a 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