Merge tag 'v4.19.50-rt22' into toradex_4.19.y-rt

Linux 4.19.50-rt22

18 files changed, 320 insertions, 78 deletions

diff --git a/arch/arc/Kconfig b/arch/arc/Kconfig
index a90c4f126050..74953e76a57d 100644
--- a/arch/arc/Kconfig
+++ b/arch/arc/Kconfig
@@ -26,6 +26,7 @@ config ARC
 	select GENERIC_IRQ_SHOW
 	select GENERIC_PCI_IOMAP
 	select GENERIC_PENDING_IRQ if SMP
+	select GENERIC_SCHED_CLOCK
 	select GENERIC_SMP_IDLE_THREAD
 	select HAVE_ARCH_KGDB
 	select HAVE_ARCH_TRACEHOOK
@@ -419,6 +420,14 @@ config ARC_HAS_ACCL_REGS
 	  (also referred to as r58:r59). These can also be used by gcc as GPR so
 	  kernel needs to save/restore per process
 
+config ARC_IRQ_NO_AUTOSAVE
+	bool "Disable hardware autosave regfile on interrupts"
+	default n
+	help
+	  On HS cores, taken interrupt auto saves the regfile on stack.
+	  This is programmable and can be optionally disabled in which case
+	  software INTERRUPT_PROLOGUE/EPILGUE do the needed work
+
 endif	# ISA_ARCV2
 
 endmenu   # "ARC CPU Configuration"
diff --git a/arch/arc/configs/hsdk_defconfig b/arch/arc/configs/hsdk_defconfig
index 2a1d2cbfee1a..651fa7978e51 100644
--- a/arch/arc/configs/hsdk_defconfig
+++ b/arch/arc/configs/hsdk_defconfig
@@ -8,6 +8,7 @@ CONFIG_NAMESPACES=y
 # CONFIG_UTS_NS is not set
 # CONFIG_PID_NS is not set
 CONFIG_BLK_DEV_INITRD=y
+CONFIG_BLK_DEV_RAM=y
 CONFIG_EMBEDDED=y
 CONFIG_PERF_EVENTS=y
 # CONFIG_VM_EVENT_COUNTERS is not set
diff --git a/arch/arc/include/asm/arcregs.h b/arch/arc/include/asm/arcregs.h
index 49bfbd879caa..bdbdaef902eb 100644
--- a/arch/arc/include/asm/arcregs.h
+++ b/arch/arc/include/asm/arcregs.h
@@ -151,6 +151,14 @@ struct bcr_isa_arcv2 {
 #endif
 };
 
+struct bcr_uarch_build_arcv2 {
+#ifdef CONFIG_CPU_BIG_ENDIAN
+	unsigned int pad:8, prod:8, maj:8, min:8;
+#else
+	unsigned int min:8, maj:8, prod:8, pad:8;
+#endif
+};
+
 struct bcr_mpy {
 #ifdef CONFIG_CPU_BIG_ENDIAN
 	unsigned int pad:8, x1616:8, dsp:4, cycles:2, type:2, ver:8;
diff --git a/arch/arc/include/asm/bitops.h b/arch/arc/include/asm/bitops.h
index 8da87feec59a..99e6d8948f4a 100644
--- a/arch/arc/include/asm/bitops.h
+++ b/arch/arc/include/asm/bitops.h
@@ -340,7 +340,7 @@ static inline __attribute__ ((const)) int __fls(unsigned long x)
 /*
  * __ffs: Similar to ffs, but zero based (0-31)
  */
-static inline __attribute__ ((const)) int __ffs(unsigned long word)
+static inline __attribute__ ((const)) unsigned long __ffs(unsigned long word)
 {
 	if (!word)
 		return word;
@@ -400,9 +400,9 @@ static inline __attribute__ ((const)) int ffs(unsigned long x)
 /*
  * __ffs: Similar to ffs, but zero based (0-31)
  */
-static inline __attribute__ ((const)) int __ffs(unsigned long x)
+static inline __attribute__ ((const)) unsigned long __ffs(unsigned long x)
 {
-	int n;
+	unsigned long n;
 
 	asm volatile(
 	"	ffs.f	%0, %1		\n"  /* 0:31; 31(Z) if src 0 */
diff --git a/arch/arc/include/asm/cache.h b/arch/arc/include/asm/cache.h
index ff7d3232764a..db681cf4959c 100644
--- a/arch/arc/include/asm/cache.h
+++ b/arch/arc/include/asm/cache.h
@@ -52,6 +52,17 @@
 #define cache_line_size()	SMP_CACHE_BYTES
 #define ARCH_DMA_MINALIGN	SMP_CACHE_BYTES
 
+/*
+ * Make sure slab-allocated buffers are 64-bit aligned when atomic64_t uses
+ * ARCv2 64-bit atomics (LLOCKD/SCONDD). This guarantess runtime 64-bit
+ * alignment for any atomic64_t embedded in buffer.
+ * Default ARCH_SLAB_MINALIGN is __alignof__(long long) which has a relaxed
+ * value of 4 (and not 8) in ARC ABI.
+ */
+#if defined(CONFIG_ARC_HAS_LL64) && defined(CONFIG_ARC_HAS_LLSC)
+#define ARCH_SLAB_MINALIGN	8
+#endif
+
 extern void arc_cache_init(void);
 extern char *arc_cache_mumbojumbo(int cpu_id, char *buf, int len);
 extern void read_decode_cache_bcr(void);
diff --git a/arch/arc/include/asm/entry-arcv2.h b/arch/arc/include/asm/entry-arcv2.h
index 309f4e6721b3..225e7df2d8ed 100644
--- a/arch/arc/include/asm/entry-arcv2.h
+++ b/arch/arc/include/asm/entry-arcv2.h
@@ -17,6 +17,33 @@
 	;
 	; Now manually save: r12, sp, fp, gp, r25
 
+#ifdef CONFIG_ARC_IRQ_NO_AUTOSAVE
+.ifnc \called_from, exception
+	st.as	r9, [sp, -10]	; save r9 in it's final stack slot
+	sub	sp, sp, 12	; skip JLI, LDI, EI
+
+	PUSH	lp_count
+	PUSHAX	lp_start
+	PUSHAX	lp_end
+	PUSH	blink
+
+	PUSH	r11
+	PUSH	r10
+
+	sub	sp, sp, 4	; skip r9
+
+	PUSH	r8
+	PUSH	r7
+	PUSH	r6
+	PUSH	r5
+	PUSH	r4
+	PUSH	r3
+	PUSH	r2
+	PUSH	r1
+	PUSH	r0
+.endif
+#endif
+
 #ifdef CONFIG_ARC_HAS_ACCL_REGS
 	PUSH	r59
 	PUSH	r58
@@ -86,6 +113,33 @@
 	POP	r59
 #endif
 
+#ifdef CONFIG_ARC_IRQ_NO_AUTOSAVE
+.ifnc \called_from, exception
+	POP	r0
+	POP	r1
+	POP	r2
+	POP	r3
+	POP	r4
+	POP	r5
+	POP	r6
+	POP	r7
+	POP	r8
+	POP	r9
+	POP	r10
+	POP	r11
+
+	POP	blink
+	POPAX	lp_end
+	POPAX	lp_start
+
+	POP	r9
+	mov	lp_count, r9
+
+	add	sp, sp, 12	; skip JLI, LDI, EI
+	ld.as	r9, [sp, -10]	; reload r9 which got clobbered
+.endif
+#endif
+
 .endm
 
 /*------------------------------------------------------------------------*/
diff --git a/arch/arc/include/asm/io.h b/arch/arc/include/asm/io.h
index c22b181e8206..2f39d9b3886e 100644
--- a/arch/arc/include/asm/io.h
+++ b/arch/arc/include/asm/io.h
@@ -12,6 +12,7 @@
 #include <linux/types.h>
 #include <asm/byteorder.h>
 #include <asm/page.h>
+#include <asm/unaligned.h>
 
 #ifdef CONFIG_ISA_ARCV2
 #include <asm/barrier.h>
@@ -94,6 +95,42 @@ static inline u32 __raw_readl(const volatile void __iomem *addr)
 	return w;
 }
 
+/*
+ * {read,write}s{b,w,l}() repeatedly access the same IO address in
+ * native endianness in 8-, 16-, 32-bit chunks {into,from} memory,
+ * @count times
+ */
+#define __raw_readsx(t,f) \
+static inline void __raw_reads##f(const volatile void __iomem *addr,	\
+				  void *ptr, unsigned int count)	\
+{									\
+	bool is_aligned = ((unsigned long)ptr % ((t) / 8)) == 0;	\
+	u##t *buf = ptr;						\
+									\
+	if (!count)							\
+		return;							\
+									\
+	/* Some ARC CPU's don't support unaligned accesses */		\
+	if (is_aligned) {						\
+		do {							\
+			u##t x = __raw_read##f(addr);			\
+			*buf++ = x;					\
+		} while (--count);					\
+	} else {							\
+		do {							\
+			u##t x = __raw_read##f(addr);			\
+			put_unaligned(x, buf++);			\
+		} while (--count);					\
+	}								\
+}
+
+#define __raw_readsb __raw_readsb
+__raw_readsx(8, b)
+#define __raw_readsw __raw_readsw
+__raw_readsx(16, w)
+#define __raw_readsl __raw_readsl
+__raw_readsx(32, l)
+
 #define __raw_writeb __raw_writeb
 static inline void __raw_writeb(u8 b, volatile void __iomem *addr)
 {
@@ -126,6 +163,35 @@ static inline void __raw_writel(u32 w, volatile void __iomem *addr)
 
 }
 
+#define __raw_writesx(t,f)						\
+static inline void __raw_writes##f(volatile void __iomem *addr, 	\
+				   const void *ptr, unsigned int count)	\
+{									\
+	bool is_aligned = ((unsigned long)ptr % ((t) / 8)) == 0;	\
+	const u##t *buf = ptr;						\
+									\
+	if (!count)							\
+		return;							\
+									\
+	/* Some ARC CPU's don't support unaligned accesses */		\
+	if (is_aligned) {						\
+		do {							\
+			__raw_write##f(*buf++, addr);			\
+		} while (--count);					\
+	} else {							\
+		do {							\
+			__raw_write##f(get_unaligned(buf++), addr);	\
+		} while (--count);					\
+	}								\
+}
+
+#define __raw_writesb __raw_writesb
+__raw_writesx(8, b)
+#define __raw_writesw __raw_writesw
+__raw_writesx(16, w)
+#define __raw_writesl __raw_writesl
+__raw_writesx(32, l)
+
 /*
  * MMIO can also get buffered/optimized in micro-arch, so barriers needed
  * Based on ARM model for the typical use case
@@ -141,10 +207,16 @@ static inline void __raw_writel(u32 w, volatile void __iomem *addr)
 #define readb(c)		({ u8  __v = readb_relaxed(c); __iormb(); __v; })
 #define readw(c)		({ u16 __v = readw_relaxed(c); __iormb(); __v; })
 #define readl(c)		({ u32 __v = readl_relaxed(c); __iormb(); __v; })
+#define readsb(p,d,l)		({ __raw_readsb(p,d,l); __iormb(); })
+#define readsw(p,d,l)		({ __raw_readsw(p,d,l); __iormb(); })
+#define readsl(p,d,l)		({ __raw_readsl(p,d,l); __iormb(); })
 
 #define writeb(v,c)		({ __iowmb(); writeb_relaxed(v,c); })
 #define writew(v,c)		({ __iowmb(); writew_relaxed(v,c); })
 #define writel(v,c)		({ __iowmb(); writel_relaxed(v,c); })
+#define writesb(p,d,l)		({ __iowmb(); __raw_writesb(p,d,l); })
+#define writesw(p,d,l)		({ __iowmb(); __raw_writesw(p,d,l); })
+#define writesl(p,d,l)		({ __iowmb(); __raw_writesl(p,d,l); })
 
 /*
  * Relaxed API for drivers which can handle barrier ordering themselves
diff --git a/arch/arc/include/asm/perf_event.h b/arch/arc/include/asm/perf_event.h
index 9185541035cc..6958545390f0 100644
--- a/arch/arc/include/asm/perf_event.h
+++ b/arch/arc/include/asm/perf_event.h
@@ -103,7 +103,8 @@ static const char * const arc_pmu_ev_hw_map[] = {
 
 	/* counts condition */
 	[PERF_COUNT_HW_INSTRUCTIONS] = "iall",
-	[PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = "ijmp", /* Excludes ZOL jumps */
+	/* All jump instructions that are taken */
+	[PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = "ijmptak",
 	[PERF_COUNT_ARC_BPOK]         = "bpok",	  /* NP-NT, PT-T, PNT-NT */
 #ifdef CONFIG_ISA_ARCV2
 	[PERF_COUNT_HW_BRANCH_MISSES] = "bpmp",
diff --git a/arch/arc/include/asm/uaccess.h b/arch/arc/include/asm/uaccess.h
index c9173c02081c..eabc3efa6c6d 100644
--- a/arch/arc/include/asm/uaccess.h
+++ b/arch/arc/include/asm/uaccess.h
@@ -207,7 +207,7 @@ raw_copy_from_user(void *to, const void __user *from, unsigned long n)
 		*/
 		  "=&r" (tmp), "+r" (to), "+r" (from)
 		:
-		: "lp_count", "lp_start", "lp_end", "memory");
+		: "lp_count", "memory");
 
 		return n;
 	}
@@ -433,7 +433,7 @@ raw_copy_to_user(void __user *to, const void *from, unsigned long n)
 		 */
 		  "=&r" (tmp), "+r" (to), "+r" (from)
 		:
-		: "lp_count", "lp_start", "lp_end", "memory");
+		: "lp_count", "memory");
 
 		return n;
 	}
@@ -653,7 +653,7 @@ static inline unsigned long __arc_clear_user(void __user *to, unsigned long n)
 	"	.previous			\n"
 	: "+r"(d_char), "+r"(res)
 	: "i"(0)
-	: "lp_count", "lp_start", "lp_end", "memory");
+	: "lp_count", "memory");
 
 	return res;
 }
@@ -686,7 +686,7 @@ __arc_strncpy_from_user(char *dst, const char __user *src, long count)
 	"	.previous			\n"
 	: "+r"(res), "+r"(dst), "+r"(src), "=r"(val)
 	: "g"(-EFAULT), "r"(count)
-	: "lp_count", "lp_start", "lp_end", "memory");
+	: "lp_count", "memory");
 
 	return res;
 }
diff --git a/arch/arc/kernel/entry-arcv2.S b/arch/arc/kernel/entry-arcv2.S
index cc558a25b8fa..562089d62d9d 100644
--- a/arch/arc/kernel/entry-arcv2.S
+++ b/arch/arc/kernel/entry-arcv2.S
@@ -209,7 +209,9 @@ restore_regs:
 ;####### Return from Intr #######
 
 debug_marker_l1:
-	bbit1.nt r0, STATUS_DE_BIT, .Lintr_ret_to_delay_slot
+	; bbit1.nt r0, STATUS_DE_BIT, .Lintr_ret_to_delay_slot
+	btst	r0, STATUS_DE_BIT		; Z flag set if bit clear
+	bnz	.Lintr_ret_to_delay_slot	; branch if STATUS_DE_BIT set
 
 .Lisr_ret_fast_path:
 	; Handle special case #1: (Entry via Exception, Return via IRQ)
diff --git a/arch/arc/kernel/head.S b/arch/arc/kernel/head.S
index 8b90d25a15cc..208bf2c9e7b0 100644
--- a/arch/arc/kernel/head.S
+++ b/arch/arc/kernel/head.S
@@ -17,6 +17,7 @@
 #include <asm/entry.h>
 #include <asm/arcregs.h>
 #include <asm/cache.h>
+#include <asm/irqflags.h>
 
 .macro CPU_EARLY_SETUP
 
@@ -47,6 +48,15 @@
 	sr	r5, [ARC_REG_DC_CTRL]
 
 1:
+
+#ifdef CONFIG_ISA_ARCV2
+	; Unaligned access is disabled at reset, so re-enable early as
+	; gcc 7.3.1 (ARC GNU 2018.03) onwards generates unaligned access
+	; by default
+	lr	r5, [status32]
+	bset	r5, r5, STATUS_AD_BIT
+	kflag	r5
+#endif
 .endm
 
 	.section .init.text, "ax",@progbits
@@ -93,10 +103,11 @@ ENTRY(stext)
 #ifdef CONFIG_ARC_UBOOT_SUPPORT
 	; Uboot - kernel ABI
 	;    r0 = [0] No uboot interaction, [1] cmdline in r2, [2] DTB in r2
-	;    r1 = magic number (board identity, unused as of now
+	;    r1 = magic number (always zero as of now)
 	;    r2 = pointer to uboot provided cmdline or external DTB in mem
-	; These are handled later in setup_arch()
+	; These are handled later in handle_uboot_args()
 	st	r0, [@uboot_tag]
+	st      r1, [@uboot_magic]
 	st	r2, [@uboot_arg]
 #endif
 
diff --git a/arch/arc/kernel/intc-arcv2.c b/arch/arc/kernel/intc-arcv2.c
index 067ea362fb3e..cf18b3e5a934 100644
--- a/arch/arc/kernel/intc-arcv2.c
+++ b/arch/arc/kernel/intc-arcv2.c
@@ -49,11 +49,13 @@ void arc_init_IRQ(void)
 
 	*(unsigned int *)&ictrl = 0;
 
+#ifndef CONFIG_ARC_IRQ_NO_AUTOSAVE
 	ictrl.save_nr_gpr_pairs = 6;	/* r0 to r11 (r12 saved manually) */
 	ictrl.save_blink = 1;
 	ictrl.save_lp_regs = 1;		/* LP_COUNT, LP_START, LP_END */
 	ictrl.save_u_to_u = 0;		/* user ctxt saved on kernel stack */
 	ictrl.save_idx_regs = 1;	/* JLI, LDI, EI */
+#endif
 
 	WRITE_AUX(AUX_IRQ_CTRL, ictrl);
 
diff --git a/arch/arc/kernel/setup.c b/arch/arc/kernel/setup.c
index b2cae79a25d7..a1218937abd6 100644
--- a/arch/arc/kernel/setup.c
+++ b/arch/arc/kernel/setup.c
@@ -35,6 +35,7 @@ unsigned int intr_to_DE_cnt;
 
 /* Part of U-boot ABI: see head.S */
 int __initdata uboot_tag;
+int __initdata uboot_magic;
 char __initdata *uboot_arg;
 
 const struct machine_desc *machine_desc;
@@ -196,13 +197,29 @@ static void read_arc_build_cfg_regs(void)
 		cpu->bpu.num_pred = 2048 << bpu.pte;
 
 		if (cpu->core.family >= 0x54) {
-			unsigned int exec_ctrl;
 
-			READ_BCR(AUX_EXEC_CTRL, exec_ctrl);
-			cpu->extn.dual_enb = !(exec_ctrl & 1);
+			struct bcr_uarch_build_arcv2 uarch;
 
-			/* dual issue always present for this core */
-			cpu->extn.dual = 1;
+			/*
+			 * The first 0x54 core (uarch maj:min 0:1 or 0:2) was
+			 * dual issue only (HS4x). But next uarch rev (1:0)
+			 * allows it be configured for single issue (HS3x)
+			 * Ensure we fiddle with dual issue only on HS4x
+			 */
+			READ_BCR(ARC_REG_MICRO_ARCH_BCR, uarch);
+
+			if (uarch.prod == 4) {
+				unsigned int exec_ctrl;
+
+				/* dual issue hardware always present */
+				cpu->extn.dual = 1;
+
+				READ_BCR(AUX_EXEC_CTRL, exec_ctrl);
+
+				/* dual issue hardware enabled ? */
+				cpu->extn.dual_enb = !(exec_ctrl & 1);
+
+			}
 		}
 	}
 
@@ -449,43 +466,87 @@ void setup_processor(void)
 	arc_chk_core_config();
 }
 
-static inline int is_kernel(unsigned long addr)
+static inline bool uboot_arg_invalid(unsigned long addr)
 {
-	if (addr >= (unsigned long)_stext && addr <= (unsigned long)_end)
-		return 1;
-	return 0;
+	/*
+	 * Check that it is a untranslated address (although MMU is not enabled
+	 * yet, it being a high address ensures this is not by fluke)
+	 */
+	if (addr < PAGE_OFFSET)
+		return true;
+
+	/* Check that address doesn't clobber resident kernel image */
+	return addr >= (unsigned long)_stext && addr <= (unsigned long)_end;
 }
 
-void __init setup_arch(char **cmdline_p)
+#define IGNORE_ARGS		"Ignore U-boot args: "
+
+/* uboot_tag values for U-boot - kernel ABI revision 0; see head.S */
+#define UBOOT_TAG_NONE		0
+#define UBOOT_TAG_CMDLINE	1
+#define UBOOT_TAG_DTB		2
+/* We always pass 0 as magic from U-boot */
+#define UBOOT_MAGIC_VALUE	0
+
+void __init handle_uboot_args(void)
 {
+	bool use_embedded_dtb = true;
+	bool append_cmdline = false;
+
 #ifdef CONFIG_ARC_UBOOT_SUPPORT
-	/* make sure that uboot passed pointer to cmdline/dtb is valid */
-	if (uboot_tag && is_kernel((unsigned long)uboot_arg))
-		panic("Invalid uboot arg\n");
+	/* check that we know this tag */
+	if (uboot_tag != UBOOT_TAG_NONE &&
+	    uboot_tag != UBOOT_TAG_CMDLINE &&
+	    uboot_tag != UBOOT_TAG_DTB) {
+		pr_warn(IGNORE_ARGS "invalid uboot tag: '%08x'\n", uboot_tag);
+		goto ignore_uboot_args;
+	}
+
+	if (uboot_magic != UBOOT_MAGIC_VALUE) {
+		pr_warn(IGNORE_ARGS "non zero uboot magic\n");
+		goto ignore_uboot_args;
+	}
 
-	/* See if u-boot passed an external Device Tree blob */
-	machine_desc = setup_machine_fdt(uboot_arg);	/* uboot_tag == 2 */
-	if (!machine_desc)
+	if (uboot_tag != UBOOT_TAG_NONE &&
+            uboot_arg_invalid((unsigned long)uboot_arg)) {
+		pr_warn(IGNORE_ARGS "invalid uboot arg: '%px'\n", uboot_arg);
+		goto ignore_uboot_args;
+	}
+
+	/* see if U-boot passed an external Device Tree blob */
+	if (uboot_tag == UBOOT_TAG_DTB) {
+		machine_desc = setup_machine_fdt((void *)uboot_arg);
+
+		/* external Device Tree blob is invalid - use embedded one */
+		use_embedded_dtb = !machine_desc;
+	}
+
+	if (uboot_tag == UBOOT_TAG_CMDLINE)
+		append_cmdline = true;
+
+ignore_uboot_args:
 #endif
-	{
-		/* No, so try the embedded one */
+
+	if (use_embedded_dtb) {
 		machine_desc = setup_machine_fdt(__dtb_start);
 		if (!machine_desc)
 			panic("Embedded DT invalid\n");
+	}
 
-		/*
-		 * If we are here, it is established that @uboot_arg didn't
-		 * point to DT blob. Instead if u-boot says it is cmdline,
-		 * append to embedded DT cmdline.
-		 * setup_machine_fdt() would have populated @boot_command_line
-		 */
-		if (uboot_tag == 1) {
-			/* Ensure a whitespace between the 2 cmdlines */
-			strlcat(boot_command_line, " ", COMMAND_LINE_SIZE);
-			strlcat(boot_command_line, uboot_arg,
-				COMMAND_LINE_SIZE);
-		}
+	/*
+	 * NOTE: @boot_command_line is populated by setup_machine_fdt() so this
+	 * append processing can only happen after.
+	 */
+	if (append_cmdline) {
+		/* Ensure a whitespace between the 2 cmdlines */
+		strlcat(boot_command_line, " ", COMMAND_LINE_SIZE);
+		strlcat(boot_command_line, uboot_arg, COMMAND_LINE_SIZE);
 	}
+}
+
+void __init setup_arch(char **cmdline_p)
+{
+	handle_uboot_args();
 
 	/* Save unparsed command line copy for /proc/cmdline */
 	*cmdline_p = boot_command_line;
diff --git a/arch/arc/kernel/troubleshoot.c b/arch/arc/kernel/troubleshoot.c
index e8d9fb452346..5c6663321e87 100644
--- a/arch/arc/kernel/troubleshoot.c
+++ b/arch/arc/kernel/troubleshoot.c
@@ -18,6 +18,8 @@
 #include <asm/arcregs.h>
 #include <asm/irqflags.h>
 
+#define ARC_PATH_MAX	256
+
 /*
  * Common routine to print scratch regs (r0-r12) or callee regs (r13-r25)
  *   -Prints 3 regs per line and a CR.
@@ -58,11 +60,12 @@ static void show_callee_regs(struct callee_regs *cregs)
 	print_reg_file(&(cregs->r13), 13);
 }
 
-static void print_task_path_n_nm(struct task_struct *tsk, char *buf)
+static void print_task_path_n_nm(struct task_struct *tsk)
 {
 	char *path_nm = NULL;
 	struct mm_struct *mm;
 	struct file *exe_file;
+	char buf[ARC_PATH_MAX];
 
 	mm = get_task_mm(tsk);
 	if (!mm)
@@ -72,7 +75,7 @@ static void print_task_path_n_nm(struct task_struct *tsk, char *buf)
 	mmput(mm);
 
 	if (exe_file) {
-		path_nm = file_path(exe_file, buf, 255);
+		path_nm = file_path(exe_file, buf, ARC_PATH_MAX-1);
 		fput(exe_file);
 	}
 
@@ -80,10 +83,9 @@ done:
 	pr_info("Path: %s\n", !IS_ERR(path_nm) ? path_nm : "?");
 }
 
-static void show_faulting_vma(unsigned long address, char *buf)
+static void show_faulting_vma(unsigned long address)
 {
 	struct vm_area_struct *vma;
-	char *nm = buf;
 	struct mm_struct *active_mm = current->active_mm;
 
 	/* can't use print_vma_addr() yet as it doesn't check for
@@ -96,8 +98,11 @@ static void show_faulting_vma(unsigned long address, char *buf)
 	 * if the container VMA is not found
 	 */
 	if (vma && (vma->vm_start <= address)) {
+		char buf[ARC_PATH_MAX];
+		char *nm = "?";
+
 		if (vma->vm_file) {
-			nm = file_path(vma->vm_file, buf, PAGE_SIZE - 1);
+			nm = file_path(vma->vm_file, buf, ARC_PATH_MAX-1);
 			if (IS_ERR(nm))
 				nm = "?";
 		}
@@ -173,13 +178,8 @@ void show_regs(struct pt_regs *regs)
 {
 	struct task_struct *tsk = current;
 	struct callee_regs *cregs;
-	char *buf;
 
-	buf = (char *)__get_free_page(GFP_KERNEL);
-	if (!buf)
-		return;
-
-	print_task_path_n_nm(tsk, buf);
+	print_task_path_n_nm(tsk);
 	show_regs_print_info(KERN_INFO);
 
 	show_ecr_verbose(regs);
@@ -189,7 +189,7 @@ void show_regs(struct pt_regs *regs)
 		(void *)regs->blink, (void *)regs->ret);
 
 	if (user_mode(regs))
-		show_faulting_vma(regs->ret, buf); /* faulting code, not data */
+		show_faulting_vma(regs->ret); /* faulting code, not data */
 
 	pr_info("[STAT32]: 0x%08lx", regs->status32);
 
@@ -221,8 +221,6 @@ void show_regs(struct pt_regs *regs)
 	cregs = (struct callee_regs *)current->thread.callee_reg;
 	if (cregs)
 		show_callee_regs(cregs);
-
-	free_page((unsigned long)buf);
 }
 
 void show_kernel_fault_diag(const char *str, struct pt_regs *regs,
diff --git a/arch/arc/lib/memcpy-archs.S b/arch/arc/lib/memcpy-archs.S
index d61044dd8b58..ea14b0bf3116 100644
--- a/arch/arc/lib/memcpy-archs.S
+++ b/arch/arc/lib/memcpy-archs.S
@@ -25,15 +25,11 @@
 #endif
 
 #ifdef CONFIG_ARC_HAS_LL64
-# define PREFETCH_READ(RX)	prefetch    [RX, 56]
-# define PREFETCH_WRITE(RX)	prefetchw   [RX, 64]
 # define LOADX(DST,RX)		ldd.ab	DST, [RX, 8]
 # define STOREX(SRC,RX)		std.ab	SRC, [RX, 8]
 # define ZOLSHFT		5
 # define ZOLAND			0x1F
 #else
-# define PREFETCH_READ(RX)	prefetch    [RX, 28]
-# define PREFETCH_WRITE(RX)	prefetchw   [RX, 32]
 # define LOADX(DST,RX)		ld.ab	DST, [RX, 4]
 # define STOREX(SRC,RX)		st.ab	SRC, [RX, 4]
 # define ZOLSHFT		4
@@ -41,8 +37,6 @@
 #endif
 
 ENTRY_CFI(memcpy)
-	prefetch [r1]		; Prefetch the read location
-	prefetchw [r0]		; Prefetch the write location
 	mov.f	0, r2
 ;;; if size is zero
 	jz.d	[blink]
@@ -72,8 +66,6 @@ ENTRY_CFI(memcpy)
 	lpnz	@.Lcopy32_64bytes
 	;; LOOP START
 	LOADX (r6, r1)
-	PREFETCH_READ (r1)
-	PREFETCH_WRITE (r3)
 	LOADX (r8, r1)
 	LOADX (r10, r1)
 	LOADX (r4, r1)
@@ -117,9 +109,7 @@ ENTRY_CFI(memcpy)
 	lpnz	@.Lcopy8bytes_1
 	;; LOOP START
 	ld.ab	r6, [r1, 4]
-	prefetch [r1, 28]	;Prefetch the next read location
 	ld.ab	r8, [r1,4]
-	prefetchw [r3, 32]	;Prefetch the next write location
 
 	SHIFT_1	(r7, r6, 24)
 	or	r7, r7, r5
@@ -162,9 +152,7 @@ ENTRY_CFI(memcpy)
 	lpnz	@.Lcopy8bytes_2
 	;; LOOP START
 	ld.ab	r6, [r1, 4]
-	prefetch [r1, 28]	;Prefetch the next read location
 	ld.ab	r8, [r1,4]
-	prefetchw [r3, 32]	;Prefetch the next write location
 
 	SHIFT_1	(r7, r6, 16)
 	or	r7, r7, r5
@@ -204,9 +192,7 @@ ENTRY_CFI(memcpy)
 	lpnz	@.Lcopy8bytes_3
 	;; LOOP START
 	ld.ab	r6, [r1, 4]
-	prefetch [r1, 28]	;Prefetch the next read location
 	ld.ab	r8, [r1,4]
-	prefetchw [r3, 32]	;Prefetch the next write location
 
 	SHIFT_1	(r7, r6, 8)
 	or	r7, r7, r5
diff --git a/arch/arc/lib/memset-archs.S b/arch/arc/lib/memset-archs.S
index 62ad4bcb841a..f230bb7092fd 100644
--- a/arch/arc/lib/memset-archs.S
+++ b/arch/arc/lib/memset-archs.S
@@ -7,11 +7,39 @@
  */
 
 #include <linux/linkage.h>
+#include <asm/cache.h>
 
-#undef PREALLOC_NOT_AVAIL
+/*
+ * The memset implementation below is optimized to use prefetchw and prealloc
+ * instruction in case of CPU with 64B L1 data cache line (L1_CACHE_SHIFT == 6)
+ * If you want to implement optimized memset for other possible L1 data cache
+ * line lengths (32B and 128B) you should rewrite code carefully checking
+ * we don't call any prefetchw/prealloc instruction for L1 cache lines which
+ * don't belongs to memset area.
+ */
+
+#if L1_CACHE_SHIFT == 6
+
+.macro PREALLOC_INSTR	reg, off
+	prealloc	[\reg, \off]
+.endm
+
+.macro PREFETCHW_INSTR	reg, off
+	prefetchw	[\reg, \off]
+.endm
+
+#else
+
+.macro PREALLOC_INSTR
+.endm
+
+.macro PREFETCHW_INSTR
+.endm
+
+#endif
 
 ENTRY_CFI(memset)
-	prefetchw [r0]		; Prefetch the write location
+	PREFETCHW_INSTR	r0, 0	; Prefetch the first write location
 	mov.f	0, r2
 ;;; if size is zero
 	jz.d	[blink]
@@ -48,11 +76,8 @@ ENTRY_CFI(memset)
 
 	lpnz	@.Lset64bytes
 	;; LOOP START
-#ifdef PREALLOC_NOT_AVAIL
-	prefetchw [r3, 64]	;Prefetch the next write location
-#else
-	prealloc  [r3, 64]
-#endif
+	PREALLOC_INSTR	r3, 64	; alloc next line w/o fetching
+
 #ifdef CONFIG_ARC_HAS_LL64
 	std.ab	r4, [r3, 8]
 	std.ab	r4, [r3, 8]
@@ -85,7 +110,6 @@ ENTRY_CFI(memset)
 	lsr.f	lp_count, r2, 5 ;Last remaining  max 124 bytes
 	lpnz	.Lset32bytes
 	;; LOOP START
-	prefetchw   [r3, 32]	;Prefetch the next write location
 #ifdef CONFIG_ARC_HAS_LL64
 	std.ab	r4, [r3, 8]
 	std.ab	r4, [r3, 8]
diff --git a/arch/arc/mm/init.c b/arch/arc/mm/init.c
index ba145065c579..f890b2f9f82f 100644
--- a/arch/arc/mm/init.c
+++ b/arch/arc/mm/init.c
@@ -138,7 +138,8 @@ void __init setup_arch_memory(void)
 	 */
 
 	memblock_add_node(low_mem_start, low_mem_sz, 0);
-	memblock_reserve(low_mem_start, __pa(_end) - low_mem_start);
+	memblock_reserve(CONFIG_LINUX_LINK_BASE,
+			 __pa(_end) - CONFIG_LINUX_LINK_BASE);
 
 #ifdef CONFIG_BLK_DEV_INITRD
 	if (initrd_start)
diff --git a/arch/arc/plat-hsdk/Kconfig b/arch/arc/plat-hsdk/Kconfig
index 9356753c2ed8..c285a83cbf08 100644
--- a/arch/arc/plat-hsdk/Kconfig
+++ b/arch/arc/plat-hsdk/Kconfig
@@ -9,6 +9,7 @@ menuconfig ARC_SOC_HSDK
 	bool "ARC HS Development Kit SOC"
 	depends on ISA_ARCV2
 	select ARC_HAS_ACCL_REGS
+	select ARC_IRQ_NO_AUTOSAVE
 	select CLK_HSDK
 	select RESET_HSDK
 	select MIGHT_HAVE_PCI