Merge tag 'arc-4.8-rc4-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/vgupta/arc

Pull ARC fixes from Vineet Gupta:

 - support for Syscall ABI v4 with upstream gcc 6.x

 - lockdep fix (Daniel Mentz)

 - gdb register clobber (Liav Rehana)

 - couple of missing exports for modules

 - other fixes here and there

* tag 'arc-4.8-rc4-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/vgupta/arc:
  ARC: export __udivdi3 for modules
  ARC: mm: fix build breakage with STRICT_MM_TYPECHECKS
  ARC: export kmap
  ARC: Support syscall ABI v4
  ARC: use correct offset in pt_regs for saving/restoring user mode r25
  ARC: Elide redundant setup of DMA callbacks
  ARC: Call trace_hardirqs_on() before enabling irqs
diff --git a/arch/arc/include/asm/entry.h b/arch/arc/include/asm/entry.h
index ad7860c..51597f3 100644
--- a/arch/arc/include/asm/entry.h
+++ b/arch/arc/include/asm/entry.h
@@ -142,7 +142,7 @@
 
 #ifdef CONFIG_ARC_CURR_IN_REG
 	; Retrieve orig r25 and save it with rest of callee_regs
-	ld.as   r12, [r12, PT_user_r25]
+	ld	r12, [r12, PT_user_r25]
 	PUSH	r12
 #else
 	PUSH	r25
@@ -198,7 +198,7 @@
 
 	; SP is back to start of pt_regs
 #ifdef CONFIG_ARC_CURR_IN_REG
-	st.as   r12, [sp, PT_user_r25]
+	st	r12, [sp, PT_user_r25]
 #endif
 .endm
 
diff --git a/arch/arc/include/asm/irqflags-compact.h b/arch/arc/include/asm/irqflags-compact.h
index c1d3645..4c6eed8 100644
--- a/arch/arc/include/asm/irqflags-compact.h
+++ b/arch/arc/include/asm/irqflags-compact.h
@@ -188,10 +188,10 @@
 .endm
 
 .macro IRQ_ENABLE  scratch
+	TRACE_ASM_IRQ_ENABLE
 	lr	\scratch, [status32]
 	or	\scratch, \scratch, (STATUS_E1_MASK | STATUS_E2_MASK)
 	flag	\scratch
-	TRACE_ASM_IRQ_ENABLE
 .endm
 
 #endif	/* __ASSEMBLY__ */
diff --git a/arch/arc/include/asm/pgtable.h b/arch/arc/include/asm/pgtable.h
index 0f92d97..89eeb37 100644
--- a/arch/arc/include/asm/pgtable.h
+++ b/arch/arc/include/asm/pgtable.h
@@ -280,7 +280,7 @@
 
 #define pte_page(pte)		pfn_to_page(pte_pfn(pte))
 #define mk_pte(page, prot)	pfn_pte(page_to_pfn(page), prot)
-#define pfn_pte(pfn, prot)	(__pte(((pte_t)(pfn) << PAGE_SHIFT) | pgprot_val(prot)))
+#define pfn_pte(pfn, prot)	__pte(((pfn) << PAGE_SHIFT) | pgprot_val(prot))
 
 /* Don't use virt_to_pfn for macros below: could cause truncations for PAE40*/
 #define pte_pfn(pte)		(pte_val(pte) >> PAGE_SHIFT)
diff --git a/arch/arc/include/uapi/asm/elf.h b/arch/arc/include/uapi/asm/elf.h
index 0f99ac8..0037a58 100644
--- a/arch/arc/include/uapi/asm/elf.h
+++ b/arch/arc/include/uapi/asm/elf.h
@@ -13,8 +13,15 @@
 
 /* Machine specific ELF Hdr flags */
 #define EF_ARC_OSABI_MSK	0x00000f00
-#define EF_ARC_OSABI_ORIG	0x00000000   /* MUST be zero for back-compat */
-#define EF_ARC_OSABI_CURRENT	0x00000300   /* v3 (no legacy syscalls) */
+
+#define EF_ARC_OSABI_V3		0x00000300   /* v3 (no legacy syscalls) */
+#define EF_ARC_OSABI_V4		0x00000400   /* v4 (64bit data any reg align) */
+
+#if __GNUC__ < 6
+#define EF_ARC_OSABI_CURRENT	EF_ARC_OSABI_V3
+#else
+#define EF_ARC_OSABI_CURRENT	EF_ARC_OSABI_V4
+#endif
 
 typedef unsigned long elf_greg_t;
 typedef unsigned long elf_fpregset_t;
diff --git a/arch/arc/kernel/arcksyms.c b/arch/arc/kernel/arcksyms.c
index 4d9e777..000dd04 100644
--- a/arch/arc/kernel/arcksyms.c
+++ b/arch/arc/kernel/arcksyms.c
@@ -28,6 +28,7 @@
 extern void __divdf3(void);
 extern void __floatunsidf(void);
 extern void __floatunsisf(void);
+extern void __udivdi3(void);
 
 EXPORT_SYMBOL(__ashldi3);
 EXPORT_SYMBOL(__ashrdi3);
@@ -45,6 +46,7 @@
 EXPORT_SYMBOL(__divdf3);
 EXPORT_SYMBOL(__floatunsidf);
 EXPORT_SYMBOL(__floatunsisf);
+EXPORT_SYMBOL(__udivdi3);
 
 /* ARC optimised assembler routines */
 EXPORT_SYMBOL(memset);
diff --git a/arch/arc/kernel/process.c b/arch/arc/kernel/process.c
index b5db9e7..be1972b 100644
--- a/arch/arc/kernel/process.c
+++ b/arch/arc/kernel/process.c
@@ -199,7 +199,7 @@
 	}
 
 	eflags = x->e_flags;
-	if ((eflags & EF_ARC_OSABI_MSK) < EF_ARC_OSABI_CURRENT) {
+	if ((eflags & EF_ARC_OSABI_MSK) != EF_ARC_OSABI_CURRENT) {
 		pr_err("ABI mismatch - you need newer toolchain\n");
 		force_sigsegv(SIGSEGV, current);
 		return 0;
diff --git a/arch/arc/kernel/setup.c b/arch/arc/kernel/setup.c
index a946400..f52a0d0d 100644
--- a/arch/arc/kernel/setup.c
+++ b/arch/arc/kernel/setup.c
@@ -291,8 +291,10 @@
 			       cpu->dccm.base_addr, TO_KB(cpu->dccm.sz),
 			       cpu->iccm.base_addr, TO_KB(cpu->iccm.sz));
 
-	n += scnprintf(buf + n, len - n,
-		       "OS ABI [v3]\t: no-legacy-syscalls\n");
+	n += scnprintf(buf + n, len - n, "OS ABI [v%d]\t: %s\n",
+			EF_ARC_OSABI_CURRENT >> 8,
+			EF_ARC_OSABI_CURRENT == EF_ARC_OSABI_V3 ?
+			"no-legacy-syscalls" : "64-bit data any register aligned");
 
 	return buf;
 }
diff --git a/arch/arc/mm/cache.c b/arch/arc/mm/cache.c
index 5a294b2..0b10efe 100644
--- a/arch/arc/mm/cache.c
+++ b/arch/arc/mm/cache.c
@@ -921,6 +921,15 @@
 
 	printk(arc_cache_mumbojumbo(0, str, sizeof(str)));
 
+	/*
+	 * Only master CPU needs to execute rest of function:
+	 *  - Assume SMP so all cores will have same cache config so
+	 *    any geomtry checks will be same for all
+	 *  - IOC setup / dma callbacks only need to be setup once
+	 */
+	if (cpu)
+		return;
+
 	if (IS_ENABLED(CONFIG_ARC_HAS_ICACHE)) {
 		struct cpuinfo_arc_cache *ic = &cpuinfo_arc700[cpu].icache;
 
diff --git a/arch/arc/mm/highmem.c b/arch/arc/mm/highmem.c
index 04f8332..77ff64a 100644
--- a/arch/arc/mm/highmem.c
+++ b/arch/arc/mm/highmem.c
@@ -61,6 +61,7 @@
 
 	return kmap_high(page);
 }
+EXPORT_SYMBOL(kmap);
 
 void *kmap_atomic(struct page *page)
 {