arm64: use the new *_relaxed macros for lower power usage

Signed-off-by: franciscofranco <franciscofranco.1990@gmail.com>
Signed-off-by: Joe Maples <joe@frap129.org>
Signed-off-by: Mister Oyster <oysterized@gmail.com>

17 files changed, 42 insertions, 39 deletions

diff --git a/arch/arm64/include/asm/compat.h b/arch/arm64/include/asm/compat.h
index a203e973b..d7a68ab51 100644
--- a/arch/arm64/include/asm/compat.h
+++ b/arch/arm64/include/asm/compat.h
@@ -288,12 +288,12 @@ struct compat_shmid64_ds {
 
 static inline int is_compat_task(void)
 {
-	return test_thread_flag(TIF_32BIT);
+	return test_thread_flag_relaxed(TIF_32BIT);
 }
 
 static inline int is_compat_thread(struct thread_info *thread)
 {
-	return test_ti_thread_flag(thread, TIF_32BIT);
+	return test_ti_thread_flag_relaxed(thread, TIF_32BIT);
 }
 
 #else /* !CONFIG_COMPAT */
diff --git a/arch/arm64/include/asm/elf.h b/arch/arm64/include/asm/elf.h
index a4e1758c4..3ba055440 100644
--- a/arch/arm64/include/asm/elf.h
+++ b/arch/arm64/include/asm/elf.h
@@ -138,7 +138,7 @@ extern int arch_setup_additional_pages(struct linux_binprm *bprm,
 
 /* 1GB of VA */
 #ifdef CONFIG_COMPAT
-#define STACK_RND_MASK			(test_thread_flag(TIF_32BIT) ? \
+#define STACK_RND_MASK			(test_thread_flag_relaxed(TIF_32BIT) ? \
 						0x7ff >> (PAGE_SHIFT - 12) : \
 						0x3ffff >> (PAGE_SHIFT - 12))
 #else
diff --git a/arch/arm64/include/asm/memory.h b/arch/arm64/include/asm/memory.h
index 34d4cb5e9..c775203d7 100644
--- a/arch/arm64/include/asm/memory.h
+++ b/arch/arm64/include/asm/memory.h
@@ -49,7 +49,7 @@
 
 #ifdef CONFIG_COMPAT
 #define TASK_SIZE_32		UL(0x100000000)
-#define TASK_SIZE		(test_thread_flag(TIF_32BIT) ? \
+#define TASK_SIZE		(test_thread_flag_relaxed(TIF_32BIT) ? \
 				TASK_SIZE_32 : TASK_SIZE_64)
 #define TASK_SIZE_OF(tsk)	(test_tsk_thread_flag(tsk, TIF_32BIT) ? \
 				TASK_SIZE_32 : TASK_SIZE_64)
diff --git a/arch/arm64/include/asm/processor.h b/arch/arm64/include/asm/processor.h
index d3dd246ed..ed23bb439 100644
--- a/arch/arm64/include/asm/processor.h
+++ b/arch/arm64/include/asm/processor.h
@@ -40,7 +40,7 @@
 #define STACK_TOP_MAX		TASK_SIZE_64
 #ifdef CONFIG_COMPAT
 #define AARCH32_VECTORS_BASE	0xffff0000
-#define STACK_TOP		(test_thread_flag(TIF_32BIT) ? \
+#define STACK_TOP		(test_thread_flag_relaxed(TIF_32BIT) ? \
 				AARCH32_VECTORS_BASE : STACK_TOP_MAX)
 #else
 #define STACK_TOP		STACK_TOP_MAX
diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c
index 28d39b95a..4b242c448 100644
--- a/arch/arm64/kernel/ptrace.c
+++ b/arch/arm64/kernel/ptrace.c
@@ -1177,10 +1177,10 @@ asmlinkage int syscall_trace_enter(struct pt_regs *regs)
 	if (secure_computing() == -1)
 		return RET_SKIP_SYSCALL_TRACE;
 
-	if (test_thread_flag(TIF_SYSCALL_TRACE))
+	if (test_thread_flag_relaxed(TIF_SYSCALL_TRACE))
 		tracehook_report_syscall(regs, PTRACE_SYSCALL_ENTER);
 
-	if (test_thread_flag(TIF_SYSCALL_TRACEPOINT))
+	if (test_thread_flag_relaxed(TIF_SYSCALL_TRACEPOINT))
 		trace_sys_enter(regs, regs->syscallno);
 
 	if (IS_SKIP_SYSCALL(regs->syscallno)) {
@@ -1211,9 +1211,9 @@ asmlinkage void syscall_trace_exit(struct pt_regs *regs)
 {
 	audit_syscall_exit(regs);
 
-	if (test_thread_flag(TIF_SYSCALL_TRACEPOINT))
+	if (test_thread_flag_relaxed(TIF_SYSCALL_TRACEPOINT))
 		trace_sys_exit(regs, regs_return_value(regs));
 
-	if (test_thread_flag(TIF_SYSCALL_TRACE))
+	if (test_thread_flag_relaxed(TIF_SYSCALL_TRACE))
 		tracehook_report_syscall(regs, PTRACE_SYSCALL_EXIT);
 }
diff --git a/drivers/input/input-compat.h b/drivers/input/input-compat.h
index 148f66fe3..5b8c62ef6 100644
--- a/drivers/input/input-compat.h
+++ b/drivers/input/input-compat.h
@@ -22,11 +22,11 @@
 #if defined(CONFIG_X86_64) || defined(CONFIG_TILE)
 #  define INPUT_COMPAT_TEST is_compat_task()
 #elif defined(CONFIG_S390)
-#  define INPUT_COMPAT_TEST test_thread_flag(TIF_31BIT)
+#  define INPUT_COMPAT_TEST test_thread_flag_relaxed(TIF_31BIT)
 #elif defined(CONFIG_MIPS)
-#  define INPUT_COMPAT_TEST test_thread_flag(TIF_32BIT_ADDR)
+#  define INPUT_COMPAT_TEST test_thread_flag_relaxed(TIF_32BIT_ADDR)
 #else
-#  define INPUT_COMPAT_TEST test_thread_flag(TIF_32BIT)
+#  define INPUT_COMPAT_TEST test_thread_flag_relaxed(TIF_32BIT)
 #endif
 
 struct input_event_compat {
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 08bd577ac..aa76cc2ae 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -2554,7 +2554,7 @@ static inline int test_and_clear_tsk_thread_flag(struct task_struct *tsk, int fl
 
 static inline int test_tsk_thread_flag(struct task_struct *tsk, int flag)
 {
-	return test_ti_thread_flag(task_thread_info(tsk), flag);
+	return test_ti_thread_flag_relaxed(task_thread_info(tsk), flag);
 }
 
 static inline void set_tsk_need_resched(struct task_struct *tsk)
diff --git a/include/linux/seqlock.h b/include/linux/seqlock.h
index 182990574..d4cf5229c 100644
--- a/include/linux/seqlock.h
+++ b/include/linux/seqlock.h
@@ -29,6 +29,7 @@
 #include <linux/spinlock.h>
 #include <linux/preempt.h>
 #include <asm/processor.h>
+#include <asm/relaxed.h>
 
 /*
  * Version using sequence counter only.
@@ -61,9 +62,9 @@ static inline unsigned __read_seqcount_begin(const seqcount_t *s)
 	unsigned ret;
 
 repeat:
-	ret = ACCESS_ONCE(s->sequence);
+	ret = cpu_relaxed_read((volatile u32 *)&s->sequence);
 	if (unlikely(ret & 1)) {
-		cpu_relax();
+		cpu_read_relax();
 		goto repeat;
 	}
 	return ret;
diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index 66a980fcf..d384b9d21 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -973,7 +973,7 @@ static void cpuset_change_task_nodemask(struct task_struct *tsk,
 	 * Allow tasks that have access to memory reserves because they have
 	 * been OOM killed to get memory anywhere.
 	 */
-	if (unlikely(test_thread_flag(TIF_MEMDIE)))
+	if (unlikely(test_thread_flag_relaxed(TIF_MEMDIE)))
 		return;
 	if (current->flags & PF_EXITING) /* Let dying task have memory */
 		return;
@@ -2451,7 +2451,7 @@ int __cpuset_node_allowed_softwall(int node, gfp_t gfp_mask)
 	 * Allow tasks that have access to memory reserves because they have
 	 * been OOM killed to get memory anywhere.
 	 */
-	if (unlikely(test_thread_flag(TIF_MEMDIE)))
+	if (unlikely(test_thread_flag_relaxed(TIF_MEMDIE)))
 		return 1;
 	if (gfp_mask & __GFP_HARDWALL)	/* If hardwall request, stop here */
 		return 0;
@@ -2504,7 +2504,7 @@ int __cpuset_node_allowed_hardwall(int node, gfp_t gfp_mask)
 	 * Allow tasks that have access to memory reserves because they have
 	 * been OOM killed to get memory anywhere.
 	 */
-	if (unlikely(test_thread_flag(TIF_MEMDIE)))
+	if (unlikely(test_thread_flag_relaxed(TIF_MEMDIE)))
 		return 1;
 	return 0;
 }
diff --git a/kernel/freezer.c b/kernel/freezer.c
index 4ada72f5f..adf590772 100644
--- a/kernel/freezer.c
+++ b/kernel/freezer.c
@@ -42,7 +42,7 @@ bool freezing_slow_path(struct task_struct *p)
 	if (p->flags & PF_NOFREEZE)
 		return false;
 
-	if (test_thread_flag(TIF_MEMDIE))
+	if (test_thread_flag_relaxed(TIF_MEMDIE))
 		return false;
 
 	if (pm_nosig_freezing || cgroup_freezing(p))
diff --git a/kernel/irq_work.c b/kernel/irq_work.c
index 55fcce606..4bcbeafc6 100644
--- a/kernel/irq_work.c
+++ b/kernel/irq_work.c
@@ -91,7 +91,7 @@ bool irq_work_needs_cpu(void)
 	struct llist_head *this_list;
 
 	this_list = &__get_cpu_var(irq_work_list);
-	if (llist_empty(this_list))
+	if (llist_empty_relaxed(this_list))
 		return false;
 
 	/* All work should have been flushed before going offline */
@@ -116,7 +116,7 @@ static void __irq_work_run(void)
 	barrier();
 
 	this_list = &__get_cpu_var(irq_work_list);
-	if (llist_empty(this_list))
+	if (llist_empty_relaxed(this_list))
 		return;
 
 	BUG_ON(!irqs_disabled());
diff --git a/kernel/mutex.c b/kernel/mutex.c
index d77807b1e..9d953374e 100644
--- a/kernel/mutex.c
+++ b/kernel/mutex.c
@@ -143,8 +143,8 @@ void mspin_lock(struct mspin_node **lock, struct mspin_node *node)
 	ACCESS_ONCE(prev->next) = node;
 	smp_wmb();
 	/* Wait until the lock holder passes the lock down */
-	while (!ACCESS_ONCE(node->locked))
-		arch_mutex_cpu_relax();
+	while (!cpu_relaxed_read(&(node->locked)))
+		cpu_read_relax();
 }
 
 static void mspin_unlock(struct mspin_node **lock, struct mspin_node *node)
@@ -158,8 +158,8 @@ static void mspin_unlock(struct mspin_node **lock, struct mspin_node *node)
 		if (cmpxchg(lock, node, NULL) == node)
 			return;
 		/* Wait until the next pointer is set */
-		while (!(next = ACCESS_ONCE(node->next)))
-			arch_mutex_cpu_relax();
+		while (!(next = (struct mspin_node*)(cpu_relaxed_read_long(&(node->next)))))
+			cpu_read_relax();
 	}
 	ACCESS_ONCE(next->locked) = 1;
 	smp_wmb();
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index c6d3219b1..265f8359e 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -1271,9 +1271,10 @@ unsigned long wait_task_inactive(struct task_struct *p, long match_state)
 		 * is actually now running somewhere else!
 		 */
 		while (task_running(rq, p)) {
-			if (match_state && unlikely(p->state != match_state))
+			if (match_state && unlikely(cpu_relaxed_read_long
+				(&(p->state)) != match_state))
 				return 0;
-			cpu_relax();
+			cpu_read_relax();
 		}
 
 		/*
@@ -1603,7 +1604,7 @@ enum ipi_msg_type {
 };
 void scheduler_ipi(void)
 {
-	if (llist_empty(&this_rq()->wake_list)
+	if (llist_empty_relaxed(&this_rq()->wake_list)
 			&& !tick_nohz_full_cpu(smp_processor_id())
 			&& !got_nohz_idle_kick()){
         mt_trace_ISR_start(IPI_RESCHEDULE);
@@ -1753,8 +1754,8 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
 	 * If the owning (remote) cpu is still in the middle of schedule() with
 	 * this task as prev, wait until its done referencing the task.
 	 */
-	while (p->on_cpu)
-		cpu_relax();
+	while (cpu_relaxed_read(&(p->on_cpu)))
+		cpu_read_relax();
 	/*
 	 * Pairs with the smp_wmb() in finish_lock_switch().
 	 */
@@ -4261,7 +4262,7 @@ int idle_cpu(int cpu)
 		return 0;
 
 #ifdef CONFIG_SMP
-	if (!llist_empty(&rq->wake_list))
+	if (!llist_empty_relaxed(&rq->wake_list))
 		return 0;
 #endif
 
diff --git a/kernel/smp.c b/kernel/smp.c
index 87f82e6cc..d02575408 100644
--- a/kernel/smp.c
+++ b/kernel/smp.c
@@ -12,6 +12,7 @@
 #include <linux/gfp.h>
 #include <linux/smp.h>
 #include <linux/cpu.h>
+#include <asm/relaxed.h>
 
 #include "smpboot.h"
 
@@ -101,8 +102,8 @@ void __init call_function_init(void)
  */
 static void csd_lock_wait(struct call_single_data *csd)
 {
-	while (csd->flags & CSD_FLAG_LOCK)
-		cpu_relax();
+	while (cpu_relaxed_read_short(&csd->flags) & CSD_FLAG_LOCK)
+		cpu_read_relax();
 }
 
 static void csd_lock(struct call_single_data *csd)
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 36300fda5..7f9608355 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -2713,7 +2713,7 @@ static int __mem_cgroup_try_charge(struct mm_struct *mm,
 	 * in system level. So, allow to go ahead dying process in addition to
 	 * MEMDIE process.
 	 */
-	if (unlikely(test_thread_flag(TIF_MEMDIE)
+	if (unlikely(test_thread_flag_relaxed(TIF_MEMDIE)
 		     || fatal_signal_pending(current)))
 		goto bypass;
 
@@ -4110,7 +4110,7 @@ static void mem_cgroup_do_uncharge(struct mem_cgroup *memcg,
 	 * because we want to do uncharge as soon as possible.
 	 */
 
-	if (!batch->do_batch || test_thread_flag(TIF_MEMDIE))
+	if (!batch->do_batch || test_thread_flag_relaxed(TIF_MEMDIE))
 		goto direct_uncharge;
 
 	if (nr_pages > 1)
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 1581cefe0..884c13be9 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -2415,7 +2415,7 @@ void warn_alloc_failed(gfp_t gfp_mask, int order, const char *fmt, ...)
 	 * of allowed nodes.
 	 */
 	if (!(gfp_mask & __GFP_NOMEMALLOC))
-		if (test_thread_flag(TIF_MEMDIE) ||
+		if (test_thread_flag_relaxed(TIF_MEMDIE) ||
 		    (current->flags & (PF_MEMALLOC | PF_EXITING)))
 			filter &= ~SHOW_MEM_FILTER_NODES;
 	if (in_interrupt() || !(gfp_mask & __GFP_WAIT))
@@ -2762,7 +2762,7 @@ gfp_to_alloc_flags(gfp_t gfp_mask)
 			alloc_flags |= ALLOC_NO_WATERMARKS;
 		else if (!in_interrupt() &&
 				((current->flags & PF_MEMALLOC) ||
-				 unlikely(test_thread_flag(TIF_MEMDIE))))
+				 unlikely(test_thread_flag_relaxed(TIF_MEMDIE))))
 			alloc_flags |= ALLOC_NO_WATERMARKS;
 	}
 #if !defined(CONFIG_CMA) || !defined(CONFIG_MTK_SVP) // SVP 15
@@ -2904,7 +2904,7 @@ rebalance:
 		goto nopage;
 
 	/* Avoid allocations with no watermarks from looping endlessly */
-	if (test_thread_flag(TIF_MEMDIE) && !(gfp_mask & __GFP_NOFAIL))
+	if (test_thread_flag_relaxed(TIF_MEMDIE) && !(gfp_mask & __GFP_NOFAIL))
 		goto nopage;
 
 	/*
diff --git a/net/rds/ib_rdma.c b/net/rds/ib_rdma.c
index a985158d9..a9724205c 100644
--- a/net/rds/ib_rdma.c
+++ b/net/rds/ib_rdma.c
@@ -593,7 +593,7 @@ static int rds_ib_flush_mr_pool(struct rds_ib_mr_pool *pool,
 
 			prepare_to_wait(&pool->flush_wait, &wait,
 					TASK_UNINTERRUPTIBLE);
-			if (llist_empty(&pool->clean_list))
+			if (llist_empty_relaxed(&pool->clean_list))
 				schedule();
 
 			ibmr = rds_ib_reuse_fmr(pool);