--- zzzz-none-000/linux-3.10.107/arch/arc/kernel/ctx_sw.c	2017-06-27 09:49:32.000000000 +0000
+++ scorpion-7490-727/linux-3.10.107/arch/arc/kernel/ctx_sw.c	2021-02-04 17:41:59.000000000 +0000
@@ -17,16 +17,14 @@
 #include <asm/asm-offsets.h>
 #include <linux/sched.h>
 
+#define KSP_WORD_OFF 	((TASK_THREAD + THREAD_KSP) / 4)
+
 struct task_struct *__sched
 __switch_to(struct task_struct *prev_task, struct task_struct *next_task)
 {
 	unsigned int tmp;
 	unsigned int prev = (unsigned int)prev_task;
 	unsigned int next = (unsigned int)next_task;
-	int num_words_to_skip = 1;
-#ifdef CONFIG_ARC_CURR_IN_REG
-	num_words_to_skip++;
-#endif
 
 	__asm__ __volatile__(
 		/* FP/BLINK save generated by gcc (standard function prologue */
@@ -44,13 +42,21 @@
 		"st.a    r24, [sp, -4]   \n\t"
 #ifndef CONFIG_ARC_CURR_IN_REG
 		"st.a    r25, [sp, -4]   \n\t"
+#else
+		"sub     sp, sp, 4      \n\t"	/* usual r25 placeholder */
 #endif
-		"sub     sp, sp, %4      \n\t"	/* create gutter at top */
 
 		/* set ksp of outgoing task in tsk->thread.ksp */
+#if KSP_WORD_OFF <= 255
 		"st.as   sp, [%3, %1]    \n\t"
-
-		"sync   \n\t"
+#else
+		/*
+		 * Workaround for NR_CPUS=4k
+		 * %1 is bigger than 255 (S9 offset for st.as)
+		 */
+		"add2    r24, %3, %1     \n\t"
+		"st      sp, [r24]       \n\t"
+#endif
 
 		/*
 		 * setup _current_task with incoming tsk.
@@ -76,10 +82,10 @@
 
 		/* start loading it's CALLEE reg file */
 
-		"add    sp, sp, %4     \n\t"	/* skip gutter at top */
-
 #ifndef CONFIG_ARC_CURR_IN_REG
 		"ld.ab   r25, [sp, 4]   \n\t"
+#else
+		"add    sp, sp, 4       \n\t"
 #endif
 		"ld.ab   r24, [sp, 4]   \n\t"
 		"ld.ab   r23, [sp, 4]   \n\t"
@@ -100,8 +106,7 @@
 		/* FP/BLINK restore generated by gcc (standard func epilogue */
 
 		: "=r"(tmp)
-		: "n"((TASK_THREAD + THREAD_KSP) / 4), "r"(next), "r"(prev),
-		  "n"(num_words_to_skip * 4)
+		: "n"(KSP_WORD_OFF), "r"(next), "r"(prev)
 		: "blink"
 	);