x86/percpu: Move preempt_count next to current_task

Add preempt_count to pcpu_hot, since it is once of the most used
per-cpu variables.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lore.kernel.org/r/20220915111145.284170644@infradead.org

arch/x86/include/asm/current.h

@@ -15,6 +15,7 @@ struct pcpu_hot {
 	union {
 		struct {
 			struct task_struct	*current_task;
+			int			preempt_count;
 		};
 		u8	pad[64];
 	};

arch/x86/include/asm/preempt.h

@@ -4,11 +4,11 @@
 
 #include <asm/rmwcc.h>
 #include <asm/percpu.h>
+#include <asm/current.h>
+
 #include <linux/thread_info.h>
 #include <linux/static_call_types.h>
 
-DECLARE_PER_CPU(int, __preempt_count);
-
 /* We use the MSB mostly because its available */
 #define PREEMPT_NEED_RESCHED	0x80000000
 
@@ -24,7 +24,7 @@ DECLARE_PER_CPU(int, __preempt_count);
  */
 static __always_inline int preempt_count(void)
 {
-	return raw_cpu_read_4(__preempt_count) & ~PREEMPT_NEED_RESCHED;
+	return raw_cpu_read_4(pcpu_hot.preempt_count) & ~PREEMPT_NEED_RESCHED;
 }
 
 static __always_inline void preempt_count_set(int pc)
@@ -32,10 +32,10 @@ static __always_inline void preempt_count_set(int pc)
 	int old, new;
 
 	do {
-		old = raw_cpu_read_4(__preempt_count);
+		old = raw_cpu_read_4(pcpu_hot.preempt_count);
 		new = (old & PREEMPT_NEED_RESCHED) |
 			(pc & ~PREEMPT_NEED_RESCHED);
-	} while (raw_cpu_cmpxchg_4(__preempt_count, old, new) != old);
+	} while (raw_cpu_cmpxchg_4(pcpu_hot.preempt_count, old, new) != old);
 }
 
 /*
@@ -44,7 +44,7 @@ static __always_inline void preempt_count_set(int pc)
 #define init_task_preempt_count(p) do { } while (0)
 
 #define init_idle_preempt_count(p, cpu) do { \
-	per_cpu(__preempt_count, (cpu)) = PREEMPT_DISABLED; \
+	per_cpu(pcpu_hot.preempt_count, (cpu)) = PREEMPT_DISABLED; \
 } while (0)
 
 /*
@@ -58,17 +58,17 @@ static __always_inline void preempt_count_set(int pc)
 
 static __always_inline void set_preempt_need_resched(void)
 {
-	raw_cpu_and_4(__preempt_count, ~PREEMPT_NEED_RESCHED);
+	raw_cpu_and_4(pcpu_hot.preempt_count, ~PREEMPT_NEED_RESCHED);
 }
 
 static __always_inline void clear_preempt_need_resched(void)
 {
-	raw_cpu_or_4(__preempt_count, PREEMPT_NEED_RESCHED);
+	raw_cpu_or_4(pcpu_hot.preempt_count, PREEMPT_NEED_RESCHED);
 }
 
 static __always_inline bool test_preempt_need_resched(void)
 {
-	return !(raw_cpu_read_4(__preempt_count) & PREEMPT_NEED_RESCHED);
+	return !(raw_cpu_read_4(pcpu_hot.preempt_count) & PREEMPT_NEED_RESCHED);
 }
 
 /*
@@ -77,12 +77,12 @@ static __always_inline bool test_preempt_need_resched(void)
 
 static __always_inline void __preempt_count_add(int val)
 {
-	raw_cpu_add_4(__preempt_count, val);
+	raw_cpu_add_4(pcpu_hot.preempt_count, val);
 }
 
 static __always_inline void __preempt_count_sub(int val)
 {
-	raw_cpu_add_4(__preempt_count, -val);
+	raw_cpu_add_4(pcpu_hot.preempt_count, -val);
 }
 
 /*
@@ -92,7 +92,8 @@ static __always_inline void __preempt_count_sub(int val)
  */
 static __always_inline bool __preempt_count_dec_and_test(void)
 {
-	return GEN_UNARY_RMWcc("decl", __preempt_count, e, __percpu_arg([var]));
+	return GEN_UNARY_RMWcc("decl", pcpu_hot.preempt_count, e,
+			       __percpu_arg([var]));
 }
 
 /*
@@ -100,7 +101,7 @@ static __always_inline bool __preempt_count_dec_and_test(void)
  */
 static __always_inline bool should_resched(int preempt_offset)
 {
-	return unlikely(raw_cpu_read_4(__preempt_count) == preempt_offset);
+	return unlikely(raw_cpu_read_4(pcpu_hot.preempt_count) == preempt_offset);
 }
 
 #ifdef CONFIG_PREEMPTION

arch/x86/kernel/cpu/common.c

@@ -2014,6 +2014,7 @@ __setup("clearcpuid=", setup_clearcpuid);
 
 DEFINE_PER_CPU_ALIGNED(struct pcpu_hot, pcpu_hot) = {
 	.current_task	= &init_task,
+	.preempt_count	= INIT_PREEMPT_COUNT,
 };
 EXPORT_PER_CPU_SYMBOL(pcpu_hot);
 
@@ -2022,13 +2023,9 @@ DEFINE_PER_CPU_FIRST(struct fixed_percpu_data,
 		     fixed_percpu_data) __aligned(PAGE_SIZE) __visible;
 EXPORT_PER_CPU_SYMBOL_GPL(fixed_percpu_data);
 
-
 DEFINE_PER_CPU(void *, hardirq_stack_ptr);
 DEFINE_PER_CPU(bool, hardirq_stack_inuse);
 
-DEFINE_PER_CPU(int, __preempt_count) = INIT_PREEMPT_COUNT;
-EXPORT_PER_CPU_SYMBOL(__preempt_count);
-
 DEFINE_PER_CPU(unsigned long, cpu_current_top_of_stack) = TOP_OF_INIT_STACK;
 
 static void wrmsrl_cstar(unsigned long val)
@@ -2081,9 +2078,6 @@ void syscall_init(void)
 
 #else	/* CONFIG_X86_64 */
 
-DEFINE_PER_CPU(int, __preempt_count) = INIT_PREEMPT_COUNT;
-EXPORT_PER_CPU_SYMBOL(__preempt_count);
-
 /*
  * On x86_32, vm86 modifies tss.sp0, so sp0 isn't a reliable way to find
  * the top of the kernel stack.  Use an extra percpu variable to track the