Merge tag 'arc-4.10-rc6' of git://git.kernel.org/pub/scm/linux/kernel/git/vgupta/arc

Pull ARC fixes from Vineet Gupta:
 "Hopefully last set of changes for ARC for 4.10:

   - fix for unaligned access emulation corner case

   - fix for udelay loop inline asm regression

   - fix irq affinity finally for AXS103 board [Yuriy]

   - final fixes for setting IO-coherency sanely in SMP"

* tag 'arc-4.10-rc6' of git://git.kernel.org/pub/scm/linux/kernel/git/vgupta/arc:
  ARC: [arcompact] handle unaligned access delay slot corner case
  ARCv2: smp-boot: wake_flag polling by non-Masters needs to be uncached
  ARC: smp-boot: Decouple Non masters waiting API from jump to entry point
  ARCv2: MCIP: update the BCR per current changes
  ARC: udelay: fix inline assembler by adding LP_COUNT to clobber list
  ARCv2: MCIP: Deprecate setting of affinity in Device Tree

5 files changed, 55 insertions, 46 deletions

diff --git a/arch/arc/include/asm/delay.h b/arch/arc/include/asm/delay.h
index a36e8601114d..d5da2115d78a 100644
--- a/arch/arc/include/asm/delay.h
+++ b/arch/arc/include/asm/delay.h
@@ -26,7 +26,9 @@ static inline void __delay(unsigned long loops)
 	"	lp  1f			\n"
 	"	nop			\n"
 	"1:				\n"
-	: : "r"(loops));
+	:
+        : "r"(loops)
+        : "lp_count");
 }
 
 extern void __bad_udelay(void);
diff --git a/arch/arc/kernel/head.S b/arch/arc/kernel/head.S
index 689dd867fdff..8b90d25a15cc 100644
--- a/arch/arc/kernel/head.S
+++ b/arch/arc/kernel/head.S
@@ -71,14 +71,14 @@ ENTRY(stext)
 	GET_CPU_ID  r5
 	cmp	r5, 0
 	mov.nz	r0, r5
-#ifdef CONFIG_ARC_SMP_HALT_ON_RESET
-	; Non-Master can proceed as system would be booted sufficiently
-	jnz	first_lines_of_secondary
-#else
+	bz	.Lmaster_proceed
+
 	; Non-Masters wait for Master to boot enough and bring them up
-	jnz	arc_platform_smp_wait_to_boot
-#endif
-	; Master falls thru
+	; when they resume, tail-call to entry point
+	mov	blink, @first_lines_of_secondary
+	j	arc_platform_smp_wait_to_boot
+
+.Lmaster_proceed:
 #endif
 
 	; Clear BSS before updating any globals
diff --git a/arch/arc/kernel/mcip.c b/arch/arc/kernel/mcip.c
index 9274f8ade8c7..9f6b68fd4f3b 100644
--- a/arch/arc/kernel/mcip.c
+++ b/arch/arc/kernel/mcip.c
@@ -93,11 +93,10 @@ static void mcip_probe_n_setup(void)
 	READ_BCR(ARC_REG_MCIP_BCR, mp);
 
 	sprintf(smp_cpuinfo_buf,
-		"Extn [SMP]\t: ARConnect (v%d): %d cores with %s%s%s%s%s\n",
+		"Extn [SMP]\t: ARConnect (v%d): %d cores with %s%s%s%s\n",
 		mp.ver, mp.num_cores,
 		IS_AVAIL1(mp.ipi, "IPI "),
 		IS_AVAIL1(mp.idu, "IDU "),
-		IS_AVAIL1(mp.llm, "LLM "),
 		IS_AVAIL1(mp.dbg, "DEBUG "),
 		IS_AVAIL1(mp.gfrc, "GFRC"));
 
@@ -175,7 +174,6 @@ static void idu_irq_unmask(struct irq_data *data)
 	raw_spin_unlock_irqrestore(&mcip_lock, flags);
 }
 
-#ifdef CONFIG_SMP
 static int
 idu_irq_set_affinity(struct irq_data *data, const struct cpumask *cpumask,
 		     bool force)
@@ -205,12 +203,27 @@ idu_irq_set_affinity(struct irq_data *data, const struct cpumask *cpumask,
 
 	return IRQ_SET_MASK_OK;
 }
-#endif
+
+static void idu_irq_enable(struct irq_data *data)
+{
+	/*
+	 * By default send all common interrupts to all available online CPUs.
+	 * The affinity of common interrupts in IDU must be set manually since
+	 * in some cases the kernel will not call irq_set_affinity() by itself:
+	 *   1. When the kernel is not configured with support of SMP.
+	 *   2. When the kernel is configured with support of SMP but upper
+	 *      interrupt controllers does not support setting of the affinity
+	 *      and cannot propagate it to IDU.
+	 */
+	idu_irq_set_affinity(data, cpu_online_mask, false);
+	idu_irq_unmask(data);
+}
 
 static struct irq_chip idu_irq_chip = {
 	.name			= "MCIP IDU Intc",
 	.irq_mask		= idu_irq_mask,
 	.irq_unmask		= idu_irq_unmask,
+	.irq_enable		= idu_irq_enable,
 #ifdef CONFIG_SMP
 	.irq_set_affinity       = idu_irq_set_affinity,
 #endif
@@ -243,36 +256,14 @@ static int idu_irq_xlate(struct irq_domain *d, struct device_node *n,
 			 const u32 *intspec, unsigned int intsize,
 			 irq_hw_number_t *out_hwirq, unsigned int *out_type)
 {
-	irq_hw_number_t hwirq = *out_hwirq = intspec[0];
-	int distri = intspec[1];
-	unsigned long flags;
-
+	/*
+	 * Ignore value of interrupt distribution mode for common interrupts in
+	 * IDU which resides in intspec[1] since setting an affinity using value
+	 * from Device Tree is deprecated in ARC.
+	 */
+	*out_hwirq = intspec[0];
 	*out_type = IRQ_TYPE_NONE;
 
-	/* XXX: validate distribution scheme again online cpu mask */
-	if (distri == 0) {
-		/* 0 - Round Robin to all cpus, otherwise 1 bit per core */
-		raw_spin_lock_irqsave(&mcip_lock, flags);
-		idu_set_dest(hwirq, BIT(num_online_cpus()) - 1);
-		idu_set_mode(hwirq, IDU_M_TRIG_LEVEL, IDU_M_DISTRI_RR);
-		raw_spin_unlock_irqrestore(&mcip_lock, flags);
-	} else {
-		/*
-		 * DEST based distribution for Level Triggered intr can only
-		 * have 1 CPU, so generalize it to always contain 1 cpu
-		 */
-		int cpu = ffs(distri);
-
-		if (cpu != fls(distri))
-			pr_warn("IDU irq %lx distri mode set to cpu %x\n",
-				hwirq, cpu);
-
-		raw_spin_lock_irqsave(&mcip_lock, flags);
-		idu_set_dest(hwirq, cpu);
-		idu_set_mode(hwirq, IDU_M_TRIG_LEVEL, IDU_M_DISTRI_DEST);
-		raw_spin_unlock_irqrestore(&mcip_lock, flags);
-	}
-
 	return 0;
 }
 
diff --git a/arch/arc/kernel/smp.c b/arch/arc/kernel/smp.c
index 88674d972c9d..2afbafadb6ab 100644
--- a/arch/arc/kernel/smp.c
+++ b/arch/arc/kernel/smp.c
@@ -90,22 +90,37 @@ void __init smp_cpus_done(unsigned int max_cpus)
  */
 static volatile int wake_flag;
 
+#ifdef CONFIG_ISA_ARCOMPACT
+
+#define __boot_read(f)		f
+#define __boot_write(f, v)	f = v
+
+#else
+
+#define __boot_read(f)		arc_read_uncached_32(&f)
+#define __boot_write(f, v)	arc_write_uncached_32(&f, v)
+
+#endif
+
 static void arc_default_smp_cpu_kick(int cpu, unsigned long pc)
 {
 	BUG_ON(cpu == 0);
-	wake_flag = cpu;
+
+	__boot_write(wake_flag, cpu);
 }
 
 void arc_platform_smp_wait_to_boot(int cpu)
 {
-	while (wake_flag != cpu)
+	/* for halt-on-reset, we've waited already */
+	if (IS_ENABLED(CONFIG_ARC_SMP_HALT_ON_RESET))
+		return;
+
+	while (__boot_read(wake_flag) != cpu)
 		;
 
-	wake_flag = 0;
-	__asm__ __volatile__("j @first_lines_of_secondary	\n");
+	__boot_write(wake_flag, 0);
 }
 
-
 const char *arc_platform_smp_cpuinfo(void)
 {
 	return plat_smp_ops.info ? : "";
diff --git a/arch/arc/kernel/unaligned.c b/arch/arc/kernel/unaligned.c
index abd961f3e763..91ebe382147f 100644
--- a/arch/arc/kernel/unaligned.c
+++ b/arch/arc/kernel/unaligned.c
@@ -241,8 +241,9 @@ int misaligned_fixup(unsigned long address, struct pt_regs *regs,
 	if (state.fault)
 		goto fault;
 
+	/* clear any remanants of delay slot */
 	if (delay_mode(regs)) {
-		regs->ret = regs->bta;
+		regs->ret = regs->bta ~1U;
 		regs->status32 &= ~STATUS_DE_MASK;
 	} else {
 		regs->ret += state.instr_len;