Update Linux to v5.4.2

Change-Id: Idf6911045d9d382da2cfe01b1edff026404ac8fd
diff --git a/arch/arm/mm/Kconfig b/arch/arm/mm/Kconfig
index b169e58..0ab3a86 100644
--- a/arch/arm/mm/Kconfig
+++ b/arch/arm/mm/Kconfig
@@ -106,7 +106,7 @@
 	help
 	  The ARM922T is a version of the ARM920T, but with smaller
 	  instruction and data caches. It is used in Altera's
-	  Excalibur XA device family and Micrel's KS8695 Centaur.
+	  Excalibur XA device family and the ARM Integrator.
 
 	  Say Y if you want support for the ARM922T processor.
 	  Otherwise, say N.
@@ -663,6 +663,7 @@
 	depends on MMU && CPU_32v7 && !CPU_32v6 && !CPU_32v5 && \
 		!CPU_32v4 && !CPU_32v3
 	select PHYS_ADDR_T_64BIT
+	select SWIOTLB
 	help
 	  Say Y if you have an ARMv7 processor supporting the LPAE page
 	  table format and you would like to access memory beyond the
@@ -709,7 +710,7 @@
 	  assistance.
 
 	  A compliant bootloader is required in order to make maximum
-	  use of this feature.  Refer to Documentation/arm/Booting for
+	  use of this feature.  Refer to Documentation/arm/booting.rst for
 	  details.
 
 config SWP_EMULATE
@@ -780,6 +781,14 @@
 	  Say Y here to disable the processor instruction cache. Unless
 	  you have a reason not to or are unsure, say N.
 
+config CPU_ICACHE_MISMATCH_WORKAROUND
+	bool "Workaround for I-Cache line size mismatch between CPU cores"
+	depends on SMP && CPU_V7
+	help
+	  Some big.LITTLE systems have I-Cache line size mismatch between
+	  LITTLE and big cores.  Say Y here to enable a workaround for
+	  proper I-Cache support on such systems.  If unsure, say N.
+
 config CPU_DCACHE_DISABLE
 	bool "Disable D-Cache (C-bit)"
 	depends on (CPU_CP15 && !SMP) || CPU_V7M
@@ -867,7 +876,7 @@
 	  the CPU type fitted to the system.  This permits binaries to be
 	  run on ARMv4 through to ARMv7 without modification.
 
-	  See Documentation/arm/kernel_user_helpers.txt for details.
+	  See Documentation/arm/kernel_user_helpers.rst for details.
 
 	  However, the fixed address nature of these helpers can be used
 	  by ROP (return orientated programming) authors when creating
diff --git a/arch/arm/mm/alignment.c b/arch/arm/mm/alignment.c
index bd2c739..788c5cf 100644
--- a/arch/arm/mm/alignment.c
+++ b/arch/arm/mm/alignment.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  *  linux/arch/arm/mm/alignment.c
  *
@@ -6,10 +7,6 @@
  *  Thumb alignment fault fixups (c) 2004 MontaVista Software, Inc.
  *  - Adapted from gdb/sim/arm/thumbemu.c -- Thumb instruction emulation.
  *    Copyright (C) 1996, Cygnus Software Technologies Ltd.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
  */
 #include <linux/moduleparam.h>
 #include <linux/compiler.h>
@@ -133,7 +130,7 @@
 static int alignment_proc_show(struct seq_file *m, void *v)
 {
 	seq_printf(m, "User:\t\t%lu\n", ai_user);
-	seq_printf(m, "System:\t\t%lu (%pF)\n", ai_sys, ai_sys_last_pc);
+	seq_printf(m, "System:\t\t%lu (%pS)\n", ai_sys, ai_sys_last_pc);
 	seq_printf(m, "Skipped:\t%lu\n", ai_skipped);
 	seq_printf(m, "Half:\t\t%lu\n", ai_half);
 	seq_printf(m, "Word:\t\t%lu\n", ai_word);
@@ -327,7 +324,7 @@
 	__put32_unaligned_check("strbt", val, addr)
 
 static void
-do_alignment_finish_ldst(unsigned long addr, unsigned long instr, struct pt_regs *regs, union offset_union offset)
+do_alignment_finish_ldst(unsigned long addr, u32 instr, struct pt_regs *regs, union offset_union offset)
 {
 	if (!LDST_U_BIT(instr))
 		offset.un = -offset.un;
@@ -340,7 +337,7 @@
 }
 
 static int
-do_alignment_ldrhstrh(unsigned long addr, unsigned long instr, struct pt_regs *regs)
+do_alignment_ldrhstrh(unsigned long addr, u32 instr, struct pt_regs *regs)
 {
 	unsigned int rd = RD_BITS(instr);
 
@@ -389,8 +386,7 @@
 }
 
 static int
-do_alignment_ldrdstrd(unsigned long addr, unsigned long instr,
-		      struct pt_regs *regs)
+do_alignment_ldrdstrd(unsigned long addr, u32 instr, struct pt_regs *regs)
 {
 	unsigned int rd = RD_BITS(instr);
 	unsigned int rd2;
@@ -452,7 +448,7 @@
 }
 
 static int
-do_alignment_ldrstr(unsigned long addr, unsigned long instr, struct pt_regs *regs)
+do_alignment_ldrstr(unsigned long addr, u32 instr, struct pt_regs *regs)
 {
 	unsigned int rd = RD_BITS(instr);
 
@@ -501,7 +497,7 @@
  * PU = 10             A                    B
  */
 static int
-do_alignment_ldmstm(unsigned long addr, unsigned long instr, struct pt_regs *regs)
+do_alignment_ldmstm(unsigned long addr, u32 instr, struct pt_regs *regs)
 {
 	unsigned int rd, rn, correction, nr_regs, regbits;
 	unsigned long eaddr, newaddr;
@@ -542,7 +538,7 @@
 	 * processor for us.
 	 */
 	if (addr != eaddr) {
-		pr_err("LDMSTM: PC = %08lx, instr = %08lx, "
+		pr_err("LDMSTM: PC = %08lx, instr = %08x, "
 			"addr = %08lx, eaddr = %08lx\n",
 			 instruction_pointer(regs), instr, addr, eaddr);
 		show_regs(regs);
@@ -698,7 +694,7 @@
 			return subset[(L<<1) | ((tinstr & (1<<8)) >> 8)] |
 			    (tinstr & 255);		/* register_list */
 		}
-		/* Else fall through for illegal instruction case */
+		/* Else, fall through - for illegal instruction case */
 
 	default:
 		return BAD_INSTR;
@@ -719,10 +715,10 @@
  * 2. Register name Rt from ARMv7 is same as Rd from ARMv6 (Rd is Rt)
  */
 static void *
-do_alignment_t32_to_handler(unsigned long *pinstr, struct pt_regs *regs,
+do_alignment_t32_to_handler(u32 *pinstr, struct pt_regs *regs,
 			    union offset_union *poffset)
 {
-	unsigned long instr = *pinstr;
+	u32 instr = *pinstr;
 	u16 tinst1 = (instr >> 16) & 0xffff;
 	u16 tinst2 = instr & 0xffff;
 
@@ -754,6 +750,8 @@
 	case 0xe8e0:
 	case 0xe9e0:
 		poffset->un = (tinst2 & 0xff) << 2;
+		/* Fall through */
+
 	case 0xe940:
 	case 0xe9c0:
 		return do_alignment_ldrdstrd;
@@ -768,17 +766,48 @@
 	return NULL;
 }
 
+static int alignment_get_arm(struct pt_regs *regs, u32 *ip, u32 *inst)
+{
+	u32 instr = 0;
+	int fault;
+
+	if (user_mode(regs))
+		fault = get_user(instr, ip);
+	else
+		fault = probe_kernel_address(ip, instr);
+
+	*inst = __mem_to_opcode_arm(instr);
+
+	return fault;
+}
+
+static int alignment_get_thumb(struct pt_regs *regs, u16 *ip, u16 *inst)
+{
+	u16 instr = 0;
+	int fault;
+
+	if (user_mode(regs))
+		fault = get_user(instr, ip);
+	else
+		fault = probe_kernel_address(ip, instr);
+
+	*inst = __mem_to_opcode_thumb16(instr);
+
+	return fault;
+}
+
 static int
 do_alignment(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
 {
 	union offset_union uninitialized_var(offset);
-	unsigned long instr = 0, instrptr;
-	int (*handler)(unsigned long addr, unsigned long instr, struct pt_regs *regs);
+	unsigned long instrptr;
+	int (*handler)(unsigned long addr, u32 instr, struct pt_regs *regs);
 	unsigned int type;
-	unsigned int fault;
+	u32 instr = 0;
 	u16 tinstr = 0;
 	int isize = 4;
 	int thumb2_32b = 0;
+	int fault;
 
 	if (interrupts_enabled(regs))
 		local_irq_enable();
@@ -787,15 +816,14 @@
 
 	if (thumb_mode(regs)) {
 		u16 *ptr = (u16 *)(instrptr & ~1);
-		fault = probe_kernel_address(ptr, tinstr);
-		tinstr = __mem_to_opcode_thumb16(tinstr);
+
+		fault = alignment_get_thumb(regs, ptr, &tinstr);
 		if (!fault) {
 			if (cpu_architecture() >= CPU_ARCH_ARMv7 &&
 			    IS_T32(tinstr)) {
 				/* Thumb-2 32-bit */
-				u16 tinst2 = 0;
-				fault = probe_kernel_address(ptr + 1, tinst2);
-				tinst2 = __mem_to_opcode_thumb16(tinst2);
+				u16 tinst2;
+				fault = alignment_get_thumb(regs, ptr + 1, &tinst2);
 				instr = __opcode_thumb32_compose(tinstr, tinst2);
 				thumb2_32b = 1;
 			} else {
@@ -804,8 +832,7 @@
 			}
 		}
 	} else {
-		fault = probe_kernel_address((void *)instrptr, instr);
-		instr = __mem_to_opcode_arm(instr);
+		fault = alignment_get_arm(regs, (void *)instrptr, &instr);
 	}
 
 	if (fault) {
@@ -927,7 +954,7 @@
 	 * Oops, we didn't handle the instruction.
 	 */
 	pr_err("Alignment trap: not handling instruction "
-		"%0*lx at [<%08lx>]\n",
+		"%0*x at [<%08lx>]\n",
 		isize << 1,
 		isize == 2 ? tinstr : instr, instrptr);
 	ai_skipped += 1;
@@ -937,7 +964,7 @@
 	ai_user += 1;
 
 	if (ai_usermode & UM_WARN)
-		printk("Alignment trap: %s (%d) PC=0x%08lx Instr=0x%0*lx "
+		printk("Alignment trap: %s (%d) PC=0x%08lx Instr=0x%0*x "
 		       "Address=0x%08lx FSR 0x%03x\n", current->comm,
 			task_pid_nr(current), instrptr,
 			isize << 1,
@@ -948,15 +975,7 @@
 		goto fixup;
 
 	if (ai_usermode & UM_SIGNAL) {
-		siginfo_t si;
-
-		clear_siginfo(&si);
-		si.si_signo = SIGBUS;
-		si.si_errno = 0;
-		si.si_code = BUS_ADRALN;
-		si.si_addr = (void __user *)addr;
-
-		force_sig_info(si.si_signo, &si, current);
+		force_sig_fault(SIGBUS, BUS_ADRALN, (void __user *)addr);
 	} else {
 		/*
 		 * We're about to disable the alignment trap and return to
diff --git a/arch/arm/mm/cache-aurora-l2.h b/arch/arm/mm/cache-aurora-l2.h
deleted file mode 100644
index c861247..0000000
--- a/arch/arm/mm/cache-aurora-l2.h
+++ /dev/null
@@ -1,55 +0,0 @@
-/*
- * AURORA shared L2 cache controller support
- *
- * Copyright (C) 2012 Marvell
- *
- * Yehuda Yitschak <yehuday@marvell.com>
- * Gregory CLEMENT <gregory.clement@free-electrons.com>
- *
- * This file is licensed under the terms of the GNU General Public
- * License version 2.  This program is licensed "as is" without any
- * warranty of any kind, whether express or implied.
- */
-
-#ifndef __ASM_ARM_HARDWARE_AURORA_L2_H
-#define __ASM_ARM_HARDWARE_AURORA_L2_H
-
-#define AURORA_SYNC_REG		    0x700
-#define AURORA_RANGE_BASE_ADDR_REG  0x720
-#define AURORA_FLUSH_PHY_ADDR_REG   0x7f0
-#define AURORA_INVAL_RANGE_REG	    0x774
-#define AURORA_CLEAN_RANGE_REG	    0x7b4
-#define AURORA_FLUSH_RANGE_REG	    0x7f4
-
-#define AURORA_ACR_REPLACEMENT_OFFSET	    27
-#define AURORA_ACR_REPLACEMENT_MASK	     \
-	(0x3 << AURORA_ACR_REPLACEMENT_OFFSET)
-#define AURORA_ACR_REPLACEMENT_TYPE_WAYRR    \
-	(0 << AURORA_ACR_REPLACEMENT_OFFSET)
-#define AURORA_ACR_REPLACEMENT_TYPE_LFSR     \
-	(1 << AURORA_ACR_REPLACEMENT_OFFSET)
-#define AURORA_ACR_REPLACEMENT_TYPE_SEMIPLRU \
-	(3 << AURORA_ACR_REPLACEMENT_OFFSET)
-
-#define AURORA_ACR_FORCE_WRITE_POLICY_OFFSET	0
-#define AURORA_ACR_FORCE_WRITE_POLICY_MASK	\
-	(0x3 << AURORA_ACR_FORCE_WRITE_POLICY_OFFSET)
-#define AURORA_ACR_FORCE_WRITE_POLICY_DIS	\
-	(0 << AURORA_ACR_FORCE_WRITE_POLICY_OFFSET)
-#define AURORA_ACR_FORCE_WRITE_BACK_POLICY	\
-	(1 << AURORA_ACR_FORCE_WRITE_POLICY_OFFSET)
-#define AURORA_ACR_FORCE_WRITE_THRO_POLICY	\
-	(2 << AURORA_ACR_FORCE_WRITE_POLICY_OFFSET)
-
-#define MAX_RANGE_SIZE		1024
-
-#define AURORA_WAY_SIZE_SHIFT	2
-
-#define AURORA_CTRL_FW		0x100
-
-/* chose a number outside L2X0_CACHE_ID_PART_MASK to be sure to make
- * the distinction between a number coming from hardware and a number
- * coming from the device tree */
-#define AURORA_CACHE_ID	       0x100
-
-#endif /* __ASM_ARM_HARDWARE_AURORA_L2_H */
diff --git a/arch/arm/mm/cache-b15-rac.c b/arch/arm/mm/cache-b15-rac.c
index c6ed148..3471fc6 100644
--- a/arch/arm/mm/cache-b15-rac.c
+++ b/arch/arm/mm/cache-b15-rac.c
@@ -1,11 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Broadcom Brahma-B15 CPU read-ahead cache management functions
  *
  * Copyright (C) 2015-2016 Broadcom
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
  */
 
 #include <linux/err.h>
diff --git a/arch/arm/mm/cache-fa.S b/arch/arm/mm/cache-fa.S
index 2f0c588..3a464d1 100644
--- a/arch/arm/mm/cache-fa.S
+++ b/arch/arm/mm/cache-fa.S
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
  *  linux/arch/arm/mm/cache-fa.S
  *
@@ -7,10 +8,6 @@
  * Based on cache-v4wb.S:
  *  Copyright (C) 1997-2002 Russell king
  *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
  *  Processors: FA520 FA526 FA626	
  */
 #include <linux/linkage.h>
diff --git a/arch/arm/mm/cache-l2x0-pmu.c b/arch/arm/mm/cache-l2x0-pmu.c
index afe5b4c..993fefd 100644
--- a/arch/arm/mm/cache-l2x0-pmu.c
+++ b/arch/arm/mm/cache-l2x0-pmu.c
@@ -1,20 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * L220/L310 cache controller support
  *
  * Copyright (C) 2016 ARM Limited
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
  */
 #include <linux/errno.h>
 #include <linux/hrtimer.h>
@@ -314,14 +302,6 @@
 	    event->attach_state & PERF_ATTACH_TASK)
 		return -EINVAL;
 
-	if (event->attr.exclude_user   ||
-	    event->attr.exclude_kernel ||
-	    event->attr.exclude_hv     ||
-	    event->attr.exclude_idle   ||
-	    event->attr.exclude_host   ||
-	    event->attr.exclude_guest)
-		return -EINVAL;
-
 	if (event->cpu < 0)
 		return -EINVAL;
 
@@ -544,6 +524,7 @@
 		.del = l2x0_pmu_event_del,
 		.event_init = l2x0_pmu_event_init,
 		.attr_groups = l2x0_pmu_attr_groups,
+		.capabilities = PERF_PMU_CAP_NO_EXCLUDE,
 	};
 
 	l2x0_pmu_reset();
diff --git a/arch/arm/mm/cache-l2x0.c b/arch/arm/mm/cache-l2x0.c
index 808efbb..12c26eb 100644
--- a/arch/arm/mm/cache-l2x0.c
+++ b/arch/arm/mm/cache-l2x0.c
@@ -1,20 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * arch/arm/mm/cache-l2x0.c - L210/L220/L310 cache controller support
  *
  * Copyright (C) 2007 ARM Limited
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
  */
 #include <linux/cpu.h>
 #include <linux/err.h>
@@ -30,8 +18,8 @@
 #include <asm/cp15.h>
 #include <asm/cputype.h>
 #include <asm/hardware/cache-l2x0.h>
+#include <asm/hardware/cache-aurora-l2.h>
 #include "cache-tauros3.h"
-#include "cache-aurora-l2.h"
 
 struct l2c_init_data {
 	const char *type;
@@ -1364,8 +1352,8 @@
 	 * since cache range operations stall the CPU pipeline
 	 * until completion.
 	 */
-	if (end > start + MAX_RANGE_SIZE)
-		end = start + MAX_RANGE_SIZE;
+	if (end > start + AURORA_MAX_RANGE_SIZE)
+		end = start + AURORA_MAX_RANGE_SIZE;
 
 	/*
 	 * Cache range operations can't straddle a page boundary.
@@ -1505,6 +1493,18 @@
 		mask |= AURORA_ACR_FORCE_WRITE_POLICY_MASK;
 	}
 
+	if (of_property_read_bool(np, "marvell,ecc-enable")) {
+		mask |= AURORA_ACR_ECC_EN;
+		val |= AURORA_ACR_ECC_EN;
+	}
+
+	if (of_property_read_bool(np, "arm,parity-enable")) {
+		mask |= AURORA_ACR_PARITY_EN;
+		val |= AURORA_ACR_PARITY_EN;
+	} else if (of_property_read_bool(np, "arm,parity-disable")) {
+		mask |= AURORA_ACR_PARITY_EN;
+	}
+
 	*aux_val &= ~mask;
 	*aux_val |= val;
 	*aux_mask &= ~mask;
diff --git a/arch/arm/mm/cache-nop.S b/arch/arm/mm/cache-nop.S
index f1cc986..72d939e 100644
--- a/arch/arm/mm/cache-nop.S
+++ b/arch/arm/mm/cache-nop.S
@@ -1,8 +1,4 @@
-/*
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
+/* SPDX-License-Identifier: GPL-2.0-only */
 #include <linux/linkage.h>
 #include <linux/init.h>
 #include <asm/assembler.h>
diff --git a/arch/arm/mm/cache-tauros3.h b/arch/arm/mm/cache-tauros3.h
index 02c0a97..fa5f926 100644
--- a/arch/arm/mm/cache-tauros3.h
+++ b/arch/arm/mm/cache-tauros3.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
  * Marvell Tauros3 cache controller includes
  *
@@ -5,19 +6,6 @@
  *
  * based on GPL'ed 2.6 kernel sources
  *  (c) Marvell International Ltd.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
  */
 
 #ifndef __ASM_ARM_HARDWARE_TAUROS3_H
diff --git a/arch/arm/mm/cache-uniphier.c b/arch/arm/mm/cache-uniphier.c
index f57b080..ff28814 100644
--- a/arch/arm/mm/cache-uniphier.c
+++ b/arch/arm/mm/cache-uniphier.c
@@ -1,16 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * Copyright (C) 2015-2016 Socionext Inc.
  *   Author: Masahiro Yamada <yamada.masahiro@socionext.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
  */
 
 #define pr_fmt(fmt)		"uniphier: " fmt
diff --git a/arch/arm/mm/cache-v4.S b/arch/arm/mm/cache-v4.S
index 91e3adf..7787057 100644
--- a/arch/arm/mm/cache-v4.S
+++ b/arch/arm/mm/cache-v4.S
@@ -1,11 +1,8 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
  *  linux/arch/arm/mm/cache-v4.S
  *
  *  Copyright (C) 1997-2002 Russell king
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
  */
 #include <linux/linkage.h>
 #include <linux/init.h>
diff --git a/arch/arm/mm/cache-v4wb.S b/arch/arm/mm/cache-v4wb.S
index a5084ec..905ac2f 100644
--- a/arch/arm/mm/cache-v4wb.S
+++ b/arch/arm/mm/cache-v4wb.S
@@ -1,11 +1,8 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
  *  linux/arch/arm/mm/cache-v4wb.S
  *
  *  Copyright (C) 1997-2002 Russell king
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
  */
 #include <linux/linkage.h>
 #include <linux/init.h>
diff --git a/arch/arm/mm/cache-v4wt.S b/arch/arm/mm/cache-v4wt.S
index a0982ce..0b290c2 100644
--- a/arch/arm/mm/cache-v4wt.S
+++ b/arch/arm/mm/cache-v4wt.S
@@ -1,12 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
  *  linux/arch/arm/mm/cache-v4wt.S
  *
  *  Copyright (C) 1997-2002 Russell king
  *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
  *  ARMv4 write through cache operations support.
  *
  *  We assume that the write buffer is not enabled.
diff --git a/arch/arm/mm/cache-v6.S b/arch/arm/mm/cache-v6.S
index 2465995..f0f65eb 100644
--- a/arch/arm/mm/cache-v6.S
+++ b/arch/arm/mm/cache-v6.S
@@ -1,12 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
  *  linux/arch/arm/mm/cache-v6.S
  *
  *  Copyright (C) 2001 Deep Blue Solutions Ltd.
  *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
  *  This is the "shell" of the ARMv6 processor support.
  */
 #include <linux/linkage.h>
@@ -215,8 +212,8 @@
 #endif
 	tst	r1, #D_CACHE_LINE_SIZE - 1
 #ifdef CONFIG_DMA_CACHE_RWFO
-	ldrneb	r2, [r1, #-1]			@ read for ownership
-	strneb	r2, [r1, #-1]			@ write for ownership
+	ldrbne	r2, [r1, #-1]			@ read for ownership
+	strbne	r2, [r1, #-1]			@ write for ownership
 #endif
 	bic	r1, r1, #D_CACHE_LINE_SIZE - 1
 #ifdef HARVARD_CACHE
@@ -284,8 +281,8 @@
 	add	r0, r0, #D_CACHE_LINE_SIZE
 	cmp	r0, r1
 #ifdef CONFIG_DMA_CACHE_RWFO
-	ldrlob	r2, [r0]			@ read for ownership
-	strlob	r2, [r0]			@ write for ownership
+	ldrblo	r2, [r0]			@ read for ownership
+	strblo	r2, [r0]			@ write for ownership
 #endif
 	blo	1b
 	mov	r0, #0
diff --git a/arch/arm/mm/cache-v7.S b/arch/arm/mm/cache-v7.S
index 2149b47..0ee8fc4 100644
--- a/arch/arm/mm/cache-v7.S
+++ b/arch/arm/mm/cache-v7.S
@@ -1,13 +1,10 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
  *  linux/arch/arm/mm/cache-v7.S
  *
  *  Copyright (C) 2001 Deep Blue Solutions Ltd.
  *  Copyright (C) 2005 ARM Ltd.
  *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
  *  This is the "shell" of the ARMv7 processor support.
  */
 #include <linux/linkage.h>
@@ -19,6 +16,14 @@
 
 #include "proc-macros.S"
 
+#ifdef CONFIG_CPU_ICACHE_MISMATCH_WORKAROUND
+.globl icache_size
+	.data
+	.align	2
+icache_size:
+	.long	64
+	.text
+#endif
 /*
  * The secondary kernel init calls v7_flush_dcache_all before it enables
  * the L1; however, the L1 comes out of reset in an undefined state, so
@@ -163,6 +168,9 @@
 skip:
 	add	r10, r10, #2			@ increment cache number
 	cmp	r3, r10
+#ifdef CONFIG_ARM_ERRATA_814220
+	dsb
+#endif
 	bgt	flush_levels
 finished:
 	mov	r10, #0				@ switch back to cache level 0
@@ -284,7 +292,12 @@
 	cmp	r12, r1
 	blo	1b
 	dsb	ishst
+#ifdef CONFIG_CPU_ICACHE_MISMATCH_WORKAROUND
+	ldr	r3, =icache_size
+	ldr	r2, [r3, #0]
+#else
 	icache_line_size r2, r3
+#endif
 	sub	r3, r2, #1
 	bic	r12, r0, r3
 2:
diff --git a/arch/arm/mm/cache-v7m.S b/arch/arm/mm/cache-v7m.S
index 32aa2a2..a0035c4 100644
--- a/arch/arm/mm/cache-v7m.S
+++ b/arch/arm/mm/cache-v7m.S
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
  *  linux/arch/arm/mm/cache-v7m.S
  *
@@ -6,10 +7,6 @@
  *  Copyright (C) 2001 Deep Blue Solutions Ltd.
  *  Copyright (C) 2005 ARM Ltd.
  *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
  *  This is the "shell" of the ARMv7M processor support.
  */
 #include <linux/linkage.h>
diff --git a/arch/arm/mm/cache-xsc3l2.c b/arch/arm/mm/cache-xsc3l2.c
index 6c3edeb..d20d7af 100644
--- a/arch/arm/mm/cache-xsc3l2.c
+++ b/arch/arm/mm/cache-xsc3l2.c
@@ -1,20 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * arch/arm/mm/cache-xsc3l2.c - XScale3 L2 cache controller support
  *
  * Copyright (C) 2007 ARM Limited
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
  */
 #include <linux/init.h>
 #include <linux/highmem.h>
diff --git a/arch/arm/mm/context.c b/arch/arm/mm/context.c
index c8c8b9e..b7525b4 100644
--- a/arch/arm/mm/context.c
+++ b/arch/arm/mm/context.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  *  linux/arch/arm/mm/context.c
  *
@@ -5,10 +6,6 @@
  *  Copyright (C) 2012 ARM Limited
  *
  *  Author: Will Deacon <will.deacon@arm.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
  */
 #include <linux/init.h>
 #include <linux/sched.h>
diff --git a/arch/arm/mm/copypage-fa.c b/arch/arm/mm/copypage-fa.c
index d130a5e..7e28c26 100644
--- a/arch/arm/mm/copypage-fa.c
+++ b/arch/arm/mm/copypage-fa.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  *  linux/arch/arm/lib/copypage-fa.S
  *
@@ -6,10 +7,6 @@
  *
  * Based on copypage-v4wb.S:
  *  Copyright (C) 1995-1999 Russell King
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
  */
 #include <linux/init.h>
 #include <linux/highmem.h>
@@ -17,26 +14,25 @@
 /*
  * Faraday optimised copy_user_page
  */
-static void __naked
-fa_copy_user_page(void *kto, const void *kfrom)
+static void fa_copy_user_page(void *kto, const void *kfrom)
 {
-	asm("\
-	stmfd	sp!, {r4, lr}			@ 2\n\
-	mov	r2, %0				@ 1\n\
-1:	ldmia	r1!, {r3, r4, ip, lr}		@ 4\n\
-	stmia	r0, {r3, r4, ip, lr}		@ 4\n\
-	mcr	p15, 0, r0, c7, c14, 1		@ 1   clean and invalidate D line\n\
-	add	r0, r0, #16			@ 1\n\
-	ldmia	r1!, {r3, r4, ip, lr}		@ 4\n\
-	stmia	r0, {r3, r4, ip, lr}		@ 4\n\
-	mcr	p15, 0, r0, c7, c14, 1		@ 1   clean and invalidate D line\n\
-	add	r0, r0, #16			@ 1\n\
-	subs	r2, r2, #1			@ 1\n\
+	int tmp;
+
+	asm volatile ("\
+1:	ldmia	%1!, {r3, r4, ip, lr}		@ 4\n\
+	stmia	%0, {r3, r4, ip, lr}		@ 4\n\
+	mcr	p15, 0, %0, c7, c14, 1		@ 1   clean and invalidate D line\n\
+	add	%0, %0, #16			@ 1\n\
+	ldmia	%1!, {r3, r4, ip, lr}		@ 4\n\
+	stmia	%0, {r3, r4, ip, lr}		@ 4\n\
+	mcr	p15, 0, %0, c7, c14, 1		@ 1   clean and invalidate D line\n\
+	add	%0, %0, #16			@ 1\n\
+	subs	%2, %2, #1			@ 1\n\
 	bne	1b				@ 1\n\
-	mcr	p15, 0, r2, c7, c10, 4		@ 1   drain WB\n\
-	ldmfd	sp!, {r4, pc}			@ 3"
-	:
-	: "I" (PAGE_SIZE / 32));
+	mcr	p15, 0, %2, c7, c10, 4		@ 1   drain WB"
+	: "+&r" (kto), "+&r" (kfrom), "=&r" (tmp)
+	: "2" (PAGE_SIZE / 32)
+	: "r3", "r4", "ip", "lr");
 }
 
 void fa_copy_user_highpage(struct page *to, struct page *from,
diff --git a/arch/arm/mm/copypage-feroceon.c b/arch/arm/mm/copypage-feroceon.c
index 49ee0c1..064b19e 100644
--- a/arch/arm/mm/copypage-feroceon.c
+++ b/arch/arm/mm/copypage-feroceon.c
@@ -1,70 +1,65 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  *  linux/arch/arm/mm/copypage-feroceon.S
  *
  *  Copyright (C) 2008 Marvell Semiconductors
  *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
  * This handles copy_user_highpage and clear_user_page on Feroceon
  * more optimally than the generic implementations.
  */
 #include <linux/init.h>
 #include <linux/highmem.h>
 
-static void __naked
-feroceon_copy_user_page(void *kto, const void *kfrom)
+static void feroceon_copy_user_page(void *kto, const void *kfrom)
 {
-	asm("\
-	stmfd	sp!, {r4-r9, lr}		\n\
-	mov	ip, %2				\n\
-1:	mov	lr, r1				\n\
-	ldmia	r1!, {r2 - r9}			\n\
-	pld	[lr, #32]			\n\
-	pld	[lr, #64]			\n\
-	pld	[lr, #96]			\n\
-	pld	[lr, #128]			\n\
-	pld	[lr, #160]			\n\
-	pld	[lr, #192]			\n\
-	pld	[lr, #224]			\n\
-	stmia	r0, {r2 - r9}			\n\
-	ldmia	r1!, {r2 - r9}			\n\
-	mcr	p15, 0, r0, c7, c14, 1		@ clean and invalidate D line\n\
-	add	r0, r0, #32			\n\
-	stmia	r0, {r2 - r9}			\n\
-	ldmia	r1!, {r2 - r9}			\n\
-	mcr	p15, 0, r0, c7, c14, 1		@ clean and invalidate D line\n\
-	add	r0, r0, #32			\n\
-	stmia	r0, {r2 - r9}			\n\
-	ldmia	r1!, {r2 - r9}			\n\
-	mcr	p15, 0, r0, c7, c14, 1		@ clean and invalidate D line\n\
-	add	r0, r0, #32			\n\
-	stmia	r0, {r2 - r9}			\n\
-	ldmia	r1!, {r2 - r9}			\n\
-	mcr	p15, 0, r0, c7, c14, 1		@ clean and invalidate D line\n\
-	add	r0, r0, #32			\n\
-	stmia	r0, {r2 - r9}			\n\
-	ldmia	r1!, {r2 - r9}			\n\
-	mcr	p15, 0, r0, c7, c14, 1		@ clean and invalidate D line\n\
-	add	r0, r0, #32			\n\
-	stmia	r0, {r2 - r9}			\n\
-	ldmia	r1!, {r2 - r9}			\n\
-	mcr	p15, 0, r0, c7, c14, 1		@ clean and invalidate D line\n\
-	add	r0, r0, #32			\n\
-	stmia	r0, {r2 - r9}			\n\
-	ldmia	r1!, {r2 - r9}			\n\
-	mcr	p15, 0, r0, c7, c14, 1		@ clean and invalidate D line\n\
-	add	r0, r0, #32			\n\
-	stmia	r0, {r2 - r9}			\n\
-	subs	ip, ip, #(32 * 8)		\n\
-	mcr	p15, 0, r0, c7, c14, 1		@ clean and invalidate D line\n\
-	add	r0, r0, #32			\n\
+	int tmp;
+
+	asm volatile ("\
+1:	ldmia	%1!, {r2 - r7, ip, lr}		\n\
+	pld	[%1, #0]			\n\
+	pld	[%1, #32]			\n\
+	pld	[%1, #64]			\n\
+	pld	[%1, #96]			\n\
+	pld	[%1, #128]			\n\
+	pld	[%1, #160]			\n\
+	pld	[%1, #192]			\n\
+	stmia	%0, {r2 - r7, ip, lr}		\n\
+	ldmia	%1!, {r2 - r7, ip, lr}		\n\
+	mcr	p15, 0, %0, c7, c14, 1		@ clean and invalidate D line\n\
+	add	%0, %0, #32			\n\
+	stmia	%0, {r2 - r7, ip, lr}		\n\
+	ldmia	%1!, {r2 - r7, ip, lr}		\n\
+	mcr	p15, 0, %0, c7, c14, 1		@ clean and invalidate D line\n\
+	add	%0, %0, #32			\n\
+	stmia	%0, {r2 - r7, ip, lr}		\n\
+	ldmia	%1!, {r2 - r7, ip, lr}		\n\
+	mcr	p15, 0, %0, c7, c14, 1		@ clean and invalidate D line\n\
+	add	%0, %0, #32			\n\
+	stmia	%0, {r2 - r7, ip, lr}		\n\
+	ldmia	%1!, {r2 - r7, ip, lr}		\n\
+	mcr	p15, 0, %0, c7, c14, 1		@ clean and invalidate D line\n\
+	add	%0, %0, #32			\n\
+	stmia	%0, {r2 - r7, ip, lr}		\n\
+	ldmia	%1!, {r2 - r7, ip, lr}		\n\
+	mcr	p15, 0, %0, c7, c14, 1		@ clean and invalidate D line\n\
+	add	%0, %0, #32			\n\
+	stmia	%0, {r2 - r7, ip, lr}		\n\
+	ldmia	%1!, {r2 - r7, ip, lr}		\n\
+	mcr	p15, 0, %0, c7, c14, 1		@ clean and invalidate D line\n\
+	add	%0, %0, #32			\n\
+	stmia	%0, {r2 - r7, ip, lr}		\n\
+	ldmia	%1!, {r2 - r7, ip, lr}		\n\
+	mcr	p15, 0, %0, c7, c14, 1		@ clean and invalidate D line\n\
+	add	%0, %0, #32			\n\
+	stmia	%0, {r2 - r7, ip, lr}		\n\
+	subs	%2, %2, #(32 * 8)		\n\
+	mcr	p15, 0, %0, c7, c14, 1		@ clean and invalidate D line\n\
+	add	%0, %0, #32			\n\
 	bne	1b				\n\
-	mcr	p15, 0, ip, c7, c10, 4		@ drain WB\n\
-	ldmfd	sp!, {r4-r9, pc}"
-	:
-	: "r" (kto), "r" (kfrom), "I" (PAGE_SIZE));
+	mcr	p15, 0, %2, c7, c10, 4		@ drain WB"
+	: "+&r" (kto), "+&r" (kfrom), "=&r" (tmp)
+	: "2" (PAGE_SIZE)
+	: "r2", "r3", "r4", "r5", "r6", "r7", "ip", "lr");
 }
 
 void feroceon_copy_user_highpage(struct page *to, struct page *from,
diff --git a/arch/arm/mm/copypage-v4mc.c b/arch/arm/mm/copypage-v4mc.c
index 0224416..a94bd08 100644
--- a/arch/arm/mm/copypage-v4mc.c
+++ b/arch/arm/mm/copypage-v4mc.c
@@ -1,12 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  *  linux/arch/arm/lib/copypage-armv4mc.S
  *
  *  Copyright (C) 1995-2005 Russell King
  *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
  * This handles the mini data cache, as found on SA11x0 and XScale
  * processors.  When we copy a user page page, we map it in such a way
  * that accesses to this page will not touch the main data cache, but
@@ -40,12 +37,12 @@
  * instruction.  If your processor does not supply this, you have to write your
  * own copy_user_highpage that does the right thing.
  */
-static void __naked
-mc_copy_user_page(void *from, void *to)
+static void mc_copy_user_page(void *from, void *to)
 {
-	asm volatile(
-	"stmfd	sp!, {r4, lr}			@ 2\n\
-	mov	r4, %2				@ 1\n\
+	int tmp;
+
+	asm volatile ("\
+	.syntax unified\n\
 	ldmia	%0!, {r2, r3, ip, lr}		@ 4\n\
 1:	mcr	p15, 0, %1, c7, c6, 1		@ 1   invalidate D line\n\
 	stmia	%1!, {r2, r3, ip, lr}		@ 4\n\
@@ -55,13 +52,13 @@
 	mcr	p15, 0, %1, c7, c6, 1		@ 1   invalidate D line\n\
 	stmia	%1!, {r2, r3, ip, lr}		@ 4\n\
 	ldmia	%0!, {r2, r3, ip, lr}		@ 4\n\
-	subs	r4, r4, #1			@ 1\n\
+	subs	%2, %2, #1			@ 1\n\
 	stmia	%1!, {r2, r3, ip, lr}		@ 4\n\
-	ldmneia	%0!, {r2, r3, ip, lr}		@ 4\n\
-	bne	1b				@ 1\n\
-	ldmfd	sp!, {r4, pc}			@ 3"
-	:
-	: "r" (from), "r" (to), "I" (PAGE_SIZE / 64));
+	ldmiane	%0!, {r2, r3, ip, lr}		@ 4\n\
+	bne	1b				@ "
+	: "+&r" (from), "+&r" (to), "=&r" (tmp)
+	: "2" (PAGE_SIZE / 64)
+	: "r2", "r3", "ip", "lr");
 }
 
 void v4_mc_copy_user_highpage(struct page *to, struct page *from,
diff --git a/arch/arm/mm/copypage-v4wb.c b/arch/arm/mm/copypage-v4wb.c
index 067d0fd..c3581b2 100644
--- a/arch/arm/mm/copypage-v4wb.c
+++ b/arch/arm/mm/copypage-v4wb.c
@@ -1,11 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  *  linux/arch/arm/mm/copypage-v4wb.c
  *
  *  Copyright (C) 1995-1999 Russell King
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
  */
 #include <linux/init.h>
 #include <linux/highmem.h>
@@ -22,29 +19,29 @@
  * instruction.  If your processor does not supply this, you have to write your
  * own copy_user_highpage that does the right thing.
  */
-static void __naked
-v4wb_copy_user_page(void *kto, const void *kfrom)
+static void v4wb_copy_user_page(void *kto, const void *kfrom)
 {
-	asm("\
-	stmfd	sp!, {r4, lr}			@ 2\n\
-	mov	r2, %2				@ 1\n\
-	ldmia	r1!, {r3, r4, ip, lr}		@ 4\n\
-1:	mcr	p15, 0, r0, c7, c6, 1		@ 1   invalidate D line\n\
-	stmia	r0!, {r3, r4, ip, lr}		@ 4\n\
-	ldmia	r1!, {r3, r4, ip, lr}		@ 4+1\n\
-	stmia	r0!, {r3, r4, ip, lr}		@ 4\n\
-	ldmia	r1!, {r3, r4, ip, lr}		@ 4\n\
-	mcr	p15, 0, r0, c7, c6, 1		@ 1   invalidate D line\n\
-	stmia	r0!, {r3, r4, ip, lr}		@ 4\n\
-	ldmia	r1!, {r3, r4, ip, lr}		@ 4\n\
-	subs	r2, r2, #1			@ 1\n\
-	stmia	r0!, {r3, r4, ip, lr}		@ 4\n\
-	ldmneia	r1!, {r3, r4, ip, lr}		@ 4\n\
+	int tmp;
+
+	asm volatile ("\
+	.syntax unified\n\
+	ldmia	%1!, {r3, r4, ip, lr}		@ 4\n\
+1:	mcr	p15, 0, %0, c7, c6, 1		@ 1   invalidate D line\n\
+	stmia	%0!, {r3, r4, ip, lr}		@ 4\n\
+	ldmia	%1!, {r3, r4, ip, lr}		@ 4+1\n\
+	stmia	%0!, {r3, r4, ip, lr}		@ 4\n\
+	ldmia	%1!, {r3, r4, ip, lr}		@ 4\n\
+	mcr	p15, 0, %0, c7, c6, 1		@ 1   invalidate D line\n\
+	stmia	%0!, {r3, r4, ip, lr}		@ 4\n\
+	ldmia	%1!, {r3, r4, ip, lr}		@ 4\n\
+	subs	%2, %2, #1			@ 1\n\
+	stmia	%0!, {r3, r4, ip, lr}		@ 4\n\
+	ldmiane	%1!, {r3, r4, ip, lr}		@ 4\n\
 	bne	1b				@ 1\n\
-	mcr	p15, 0, r1, c7, c10, 4		@ 1   drain WB\n\
-	ldmfd	 sp!, {r4, pc}			@ 3"
-	:
-	: "r" (kto), "r" (kfrom), "I" (PAGE_SIZE / 64));
+	mcr	p15, 0, %1, c7, c10, 4		@ 1   drain WB"
+	: "+&r" (kto), "+&r" (kfrom), "=&r" (tmp)
+	: "2" (PAGE_SIZE / 64)
+	: "r3", "r4", "ip", "lr");
 }
 
 void v4wb_copy_user_highpage(struct page *to, struct page *from,
diff --git a/arch/arm/mm/copypage-v4wt.c b/arch/arm/mm/copypage-v4wt.c
index b85c5da..1fb1073 100644
--- a/arch/arm/mm/copypage-v4wt.c
+++ b/arch/arm/mm/copypage-v4wt.c
@@ -1,12 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  *  linux/arch/arm/mm/copypage-v4wt.S
  *
  *  Copyright (C) 1995-1999 Russell King
  *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
  *  This is for CPUs with a writethrough cache and 'flush ID cache' is
  *  the only supported cache operation.
  */
@@ -20,27 +17,27 @@
  * dirty data in the cache.  However, we do have to ensure that
  * subsequent reads are up to date.
  */
-static void __naked
-v4wt_copy_user_page(void *kto, const void *kfrom)
+static void v4wt_copy_user_page(void *kto, const void *kfrom)
 {
-	asm("\
-	stmfd	sp!, {r4, lr}			@ 2\n\
-	mov	r2, %2				@ 1\n\
-	ldmia	r1!, {r3, r4, ip, lr}		@ 4\n\
-1:	stmia	r0!, {r3, r4, ip, lr}		@ 4\n\
-	ldmia	r1!, {r3, r4, ip, lr}		@ 4+1\n\
-	stmia	r0!, {r3, r4, ip, lr}		@ 4\n\
-	ldmia	r1!, {r3, r4, ip, lr}		@ 4\n\
-	stmia	r0!, {r3, r4, ip, lr}		@ 4\n\
-	ldmia	r1!, {r3, r4, ip, lr}		@ 4\n\
-	subs	r2, r2, #1			@ 1\n\
-	stmia	r0!, {r3, r4, ip, lr}		@ 4\n\
-	ldmneia	r1!, {r3, r4, ip, lr}		@ 4\n\
+	int tmp;
+
+	asm volatile ("\
+	.syntax unified\n\
+	ldmia	%1!, {r3, r4, ip, lr}		@ 4\n\
+1:	stmia	%0!, {r3, r4, ip, lr}		@ 4\n\
+	ldmia	%1!, {r3, r4, ip, lr}		@ 4+1\n\
+	stmia	%0!, {r3, r4, ip, lr}		@ 4\n\
+	ldmia	%1!, {r3, r4, ip, lr}		@ 4\n\
+	stmia	%0!, {r3, r4, ip, lr}		@ 4\n\
+	ldmia	%1!, {r3, r4, ip, lr}		@ 4\n\
+	subs	%2, %2, #1			@ 1\n\
+	stmia	%0!, {r3, r4, ip, lr}		@ 4\n\
+	ldmiane	%1!, {r3, r4, ip, lr}		@ 4\n\
 	bne	1b				@ 1\n\
-	mcr	p15, 0, r2, c7, c7, 0		@ flush ID cache\n\
-	ldmfd	sp!, {r4, pc}			@ 3"
-	:
-	: "r" (kto), "r" (kfrom), "I" (PAGE_SIZE / 64));
+	mcr	p15, 0, %2, c7, c7, 0		@ flush ID cache"
+	: "+&r" (kto), "+&r" (kfrom), "=&r" (tmp)
+	: "2" (PAGE_SIZE / 64)
+	: "r3", "r4", "ip", "lr");
 }
 
 void v4wt_copy_user_highpage(struct page *to, struct page *from,
diff --git a/arch/arm/mm/copypage-v6.c b/arch/arm/mm/copypage-v6.c
index a698e57..a6488bb 100644
--- a/arch/arm/mm/copypage-v6.c
+++ b/arch/arm/mm/copypage-v6.c
@@ -1,11 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  *  linux/arch/arm/mm/copypage-v6.c
  *
  *  Copyright (C) 2002 Deep Blue Solutions Ltd, All Rights Reserved.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
  */
 #include <linux/init.h>
 #include <linux/spinlock.h>
diff --git a/arch/arm/mm/copypage-xsc3.c b/arch/arm/mm/copypage-xsc3.c
index 03a2042..6f0909d 100644
--- a/arch/arm/mm/copypage-xsc3.c
+++ b/arch/arm/mm/copypage-xsc3.c
@@ -1,12 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  *  linux/arch/arm/mm/copypage-xsc3.S
  *
  *  Copyright (C) 2004 Intel Corp.
  *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
  * Adapted for 3rd gen XScale core, no more mini-dcache
  * Author: Matt Gilbert (matthew.m.gilbert@intel.com)
  */
@@ -21,53 +18,46 @@
 
 /*
  * XSC3 optimised copy_user_highpage
- *  r0 = destination
- *  r1 = source
  *
  * The source page may have some clean entries in the cache already, but we
  * can safely ignore them - break_cow() will flush them out of the cache
  * if we eventually end up using our copied page.
  *
  */
-static void __naked
-xsc3_mc_copy_user_page(void *kto, const void *kfrom)
+static void xsc3_mc_copy_user_page(void *kto, const void *kfrom)
 {
-	asm("\
-	stmfd	sp!, {r4, r5, lr}		\n\
-	mov	lr, %2				\n\
+	int tmp;
+
+	asm volatile ("\
+	pld	[%1, #0]			\n\
+	pld	[%1, #32]			\n\
+1:	pld	[%1, #64]			\n\
+	pld	[%1, #96]			\n\
 						\n\
-	pld	[r1, #0]			\n\
-	pld	[r1, #32]			\n\
-1:	pld	[r1, #64]			\n\
-	pld	[r1, #96]			\n\
-						\n\
-2:	ldrd	r2, [r1], #8			\n\
-	mov	ip, r0				\n\
-	ldrd	r4, [r1], #8			\n\
-	mcr	p15, 0, ip, c7, c6, 1		@ invalidate\n\
-	strd	r2, [r0], #8			\n\
-	ldrd	r2, [r1], #8			\n\
-	strd	r4, [r0], #8			\n\
-	ldrd	r4, [r1], #8			\n\
-	strd	r2, [r0], #8			\n\
-	strd	r4, [r0], #8			\n\
-	ldrd	r2, [r1], #8			\n\
-	mov	ip, r0				\n\
-	ldrd	r4, [r1], #8			\n\
-	mcr	p15, 0, ip, c7, c6, 1		@ invalidate\n\
-	strd	r2, [r0], #8			\n\
-	ldrd	r2, [r1], #8			\n\
-	subs	lr, lr, #1			\n\
-	strd	r4, [r0], #8			\n\
-	ldrd	r4, [r1], #8			\n\
-	strd	r2, [r0], #8			\n\
-	strd	r4, [r0], #8			\n\
+2:	ldrd	r2, r3, [%1], #8		\n\
+	ldrd	r4, r5, [%1], #8		\n\
+	mcr	p15, 0, %0, c7, c6, 1		@ invalidate\n\
+	strd	r2, r3, [%0], #8		\n\
+	ldrd	r2, r3, [%1], #8		\n\
+	strd	r4, r5, [%0], #8		\n\
+	ldrd	r4, r5, [%1], #8		\n\
+	strd	r2, r3, [%0], #8		\n\
+	strd	r4, r5, [%0], #8		\n\
+	ldrd	r2, r3, [%1], #8		\n\
+	ldrd	r4, r5, [%1], #8		\n\
+	mcr	p15, 0, %0, c7, c6, 1		@ invalidate\n\
+	strd	r2, r3, [%0], #8		\n\
+	ldrd	r2, r3, [%1], #8		\n\
+	subs	%2, %2, #1			\n\
+	strd	r4, r5, [%0], #8		\n\
+	ldrd	r4, r5, [%1], #8		\n\
+	strd	r2, r3, [%0], #8		\n\
+	strd	r4, r5, [%0], #8		\n\
 	bgt	1b				\n\
-	beq	2b				\n\
-						\n\
-	ldmfd	sp!, {r4, r5, pc}"
-	:
-	: "r" (kto), "r" (kfrom), "I" (PAGE_SIZE / 64 - 1));
+	beq	2b				"
+	: "+&r" (kto), "+&r" (kfrom), "=&r" (tmp)
+	: "2" (PAGE_SIZE / 64 - 1)
+	: "r2", "r3", "r4", "r5");
 }
 
 void xsc3_mc_copy_user_highpage(struct page *to, struct page *from,
@@ -85,8 +75,6 @@
 
 /*
  * XScale optimised clear_user_page
- *  r0 = destination
- *  r1 = virtual user address of ultimate destination page
  */
 void xsc3_mc_clear_user_highpage(struct page *page, unsigned long vaddr)
 {
@@ -96,10 +84,10 @@
 	mov	r2, #0				\n\
 	mov	r3, #0				\n\
 1:	mcr	p15, 0, %0, c7, c6, 1		@ invalidate line\n\
-	strd	r2, [%0], #8			\n\
-	strd	r2, [%0], #8			\n\
-	strd	r2, [%0], #8			\n\
-	strd	r2, [%0], #8			\n\
+	strd	r2, r3, [%0], #8		\n\
+	strd	r2, r3, [%0], #8		\n\
+	strd	r2, r3, [%0], #8		\n\
+	strd	r2, r3, [%0], #8		\n\
 	subs	r1, r1, #1			\n\
 	bne	1b"
 	: "=r" (ptr)
diff --git a/arch/arm/mm/copypage-xscale.c b/arch/arm/mm/copypage-xscale.c
index 9797237..382e1c2 100644
--- a/arch/arm/mm/copypage-xscale.c
+++ b/arch/arm/mm/copypage-xscale.c
@@ -1,12 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  *  linux/arch/arm/lib/copypage-xscale.S
  *
  *  Copyright (C) 1995-2005 Russell King
  *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
  * This handles the mini data cache, as found on SA11x0 and XScale
  * processors.  When we copy a user page page, we map it in such a way
  * that accesses to this page will not touch the main data cache, but
@@ -36,52 +33,52 @@
  * Dcache aliasing issue.  The writes will be forwarded to the write buffer,
  * and merged as appropriate.
  */
-static void __naked
-mc_copy_user_page(void *from, void *to)
+static void mc_copy_user_page(void *from, void *to)
 {
+	int tmp;
+
 	/*
 	 * Strangely enough, best performance is achieved
 	 * when prefetching destination as well.  (NP)
 	 */
-	asm volatile(
-	"stmfd	sp!, {r4, r5, lr}		\n\
-	mov	lr, %2				\n\
-	pld	[r0, #0]			\n\
-	pld	[r0, #32]			\n\
-	pld	[r1, #0]			\n\
-	pld	[r1, #32]			\n\
-1:	pld	[r0, #64]			\n\
-	pld	[r0, #96]			\n\
-	pld	[r1, #64]			\n\
-	pld	[r1, #96]			\n\
-2:	ldrd	r2, [r0], #8			\n\
-	ldrd	r4, [r0], #8			\n\
-	mov	ip, r1				\n\
-	strd	r2, [r1], #8			\n\
-	ldrd	r2, [r0], #8			\n\
-	strd	r4, [r1], #8			\n\
-	ldrd	r4, [r0], #8			\n\
-	strd	r2, [r1], #8			\n\
-	strd	r4, [r1], #8			\n\
+	asm volatile ("\
+.arch xscale					\n\
+	pld	[%0, #0]			\n\
+	pld	[%0, #32]			\n\
+	pld	[%1, #0]			\n\
+	pld	[%1, #32]			\n\
+1:	pld	[%0, #64]			\n\
+	pld	[%0, #96]			\n\
+	pld	[%1, #64]			\n\
+	pld	[%1, #96]			\n\
+2:	ldrd	r2, r3, [%0], #8		\n\
+	ldrd	r4, r5, [%0], #8		\n\
+	mov	ip, %1				\n\
+	strd	r2, r3, [%1], #8		\n\
+	ldrd	r2, r3, [%0], #8		\n\
+	strd	r4, r5, [%1], #8		\n\
+	ldrd	r4, r5, [%0], #8		\n\
+	strd	r2, r3, [%1], #8		\n\
+	strd	r4, r5, [%1], #8		\n\
 	mcr	p15, 0, ip, c7, c10, 1		@ clean D line\n\
-	ldrd	r2, [r0], #8			\n\
+	ldrd	r2, r3, [%0], #8		\n\
 	mcr	p15, 0, ip, c7, c6, 1		@ invalidate D line\n\
-	ldrd	r4, [r0], #8			\n\
-	mov	ip, r1				\n\
-	strd	r2, [r1], #8			\n\
-	ldrd	r2, [r0], #8			\n\
-	strd	r4, [r1], #8			\n\
-	ldrd	r4, [r0], #8			\n\
-	strd	r2, [r1], #8			\n\
-	strd	r4, [r1], #8			\n\
+	ldrd	r4, r5, [%0], #8		\n\
+	mov	ip, %1				\n\
+	strd	r2, r3, [%1], #8		\n\
+	ldrd	r2, r3, [%0], #8		\n\
+	strd	r4, r5, [%1], #8		\n\
+	ldrd	r4, r5, [%0], #8		\n\
+	strd	r2, r3, [%1], #8		\n\
+	strd	r4, r5, [%1], #8		\n\
 	mcr	p15, 0, ip, c7, c10, 1		@ clean D line\n\
-	subs	lr, lr, #1			\n\
+	subs	%2, %2, #1			\n\
 	mcr	p15, 0, ip, c7, c6, 1		@ invalidate D line\n\
 	bgt	1b				\n\
-	beq	2b				\n\
-	ldmfd	sp!, {r4, r5, pc}		"
-	:
-	: "r" (from), "r" (to), "I" (PAGE_SIZE / 64 - 1));
+	beq	2b				"
+	: "+&r" (from), "+&r" (to), "=&r" (tmp)
+	: "2" (PAGE_SIZE / 64 - 1)
+	: "r2", "r3", "r4", "r5", "ip");
 }
 
 void xscale_mc_copy_user_highpage(struct page *to, struct page *from,
@@ -110,15 +107,16 @@
 xscale_mc_clear_user_highpage(struct page *page, unsigned long vaddr)
 {
 	void *ptr, *kaddr = kmap_atomic(page);
-	asm volatile(
-	"mov	r1, %2				\n\
+	asm volatile("\
+.arch xscale					\n\
+	mov	r1, %2				\n\
 	mov	r2, #0				\n\
 	mov	r3, #0				\n\
 1:	mov	ip, %0				\n\
-	strd	r2, [%0], #8			\n\
-	strd	r2, [%0], #8			\n\
-	strd	r2, [%0], #8			\n\
-	strd	r2, [%0], #8			\n\
+	strd	r2, r3, [%0], #8		\n\
+	strd	r2, r3, [%0], #8		\n\
+	strd	r2, r3, [%0], #8		\n\
+	strd	r2, r3, [%0], #8		\n\
 	mcr	p15, 0, ip, c7, c10, 1		@ clean D line\n\
 	subs	r1, r1, #1			\n\
 	mcr	p15, 0, ip, c7, c6, 1		@ invalidate D line\n\
diff --git a/arch/arm/mm/dma-mapping-nommu.c b/arch/arm/mm/dma-mapping-nommu.c
index f448a06..db92478 100644
--- a/arch/arm/mm/dma-mapping-nommu.c
+++ b/arch/arm/mm/dma-mapping-nommu.c
@@ -1,12 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  *  Based on linux/arch/arm/mm/dma-mapping.c
  *
  *  Copyright (C) 2000-2004 Russell King
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
  */
 
 #include <linux/export.h>
@@ -22,7 +18,7 @@
 #include "dma.h"
 
 /*
- *  dma_direct_ops is used if
+ *  The generic direct mapping code is used if
  *   - MMU/MPU is off
  *   - cpu is v7m w/o cache support
  *   - device is coherent
@@ -39,17 +35,7 @@
 				 unsigned long attrs)
 
 {
-	void *ret;
-
-	/*
-	 * Try generic allocator first if we are advertised that
-	 * consistency is not required.
-	 */
-
-	if (attrs & DMA_ATTR_NON_CONSISTENT)
-		return dma_direct_alloc(dev, size, dma_handle, gfp, attrs);
-
-	ret = dma_alloc_from_global_coherent(size, dma_handle);
+	void *ret = dma_alloc_from_global_coherent(size, dma_handle);
 
 	/*
 	 * dma_alloc_from_global_coherent() may fail because:
@@ -69,16 +55,9 @@
 			       void *cpu_addr, dma_addr_t dma_addr,
 			       unsigned long attrs)
 {
-	if (attrs & DMA_ATTR_NON_CONSISTENT) {
-		dma_direct_free(dev, size, cpu_addr, dma_addr, attrs);
-	} else {
-		int ret = dma_release_from_global_coherent(get_order(size),
-							   cpu_addr);
+	int ret = dma_release_from_global_coherent(get_order(size), cpu_addr);
 
-		WARN_ON_ONCE(ret == 0);
-	}
-
-	return;
+	WARN_ON_ONCE(ret == 0);
 }
 
 static int arm_nommu_dma_mmap(struct device *dev, struct vm_area_struct *vma,
@@ -89,8 +68,9 @@
 
 	if (dma_mmap_from_global_coherent(vma, cpu_addr, size, &ret))
 		return ret;
-
-	return dma_common_mmap(dev, vma, cpu_addr, dma_addr, size);
+	if (dma_mmap_from_dev_coherent(dev, vma, cpu_addr, size, &ret))
+		return ret;
+	return -ENXIO;
 }
 
 
@@ -208,16 +188,9 @@
 };
 EXPORT_SYMBOL(arm_nommu_dma_ops);
 
-static const struct dma_map_ops *arm_nommu_get_dma_map_ops(bool coherent)
-{
-	return coherent ? &dma_direct_ops : &arm_nommu_dma_ops;
-}
-
 void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size,
 			const struct iommu_ops *iommu, bool coherent)
 {
-	const struct dma_map_ops *dma_ops;
-
 	if (IS_ENABLED(CONFIG_CPU_V7M)) {
 		/*
 		 * Cache support for v7m is optional, so can be treated as
@@ -233,11 +206,6 @@
 		dev->archdata.dma_coherent = (get_cr() & CR_M) ? coherent : true;
 	}
 
-	dma_ops = arm_nommu_get_dma_map_ops(dev->archdata.dma_coherent);
-
-	set_dma_ops(dev, dma_ops);
-}
-
-void arch_teardown_dma_ops(struct device *dev)
-{
+	if (!dev->archdata.dma_coherent)
+		set_dma_ops(dev, &arm_nommu_dma_ops);
 }
diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c
index 1cb9c0f..7d042d5 100644
--- a/arch/arm/mm/dma-mapping.c
+++ b/arch/arm/mm/dma-mapping.c
@@ -1,15 +1,11 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  *  linux/arch/arm/mm/dma-mapping.c
  *
  *  Copyright (C) 2000-2004 Russell King
  *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
  *  DMA uncached mapping support.
  */
-#include <linux/bootmem.h>
 #include <linux/module.h>
 #include <linux/mm.h>
 #include <linux/genalloc.h>
@@ -18,7 +14,9 @@
 #include <linux/list.h>
 #include <linux/init.h>
 #include <linux/device.h>
+#include <linux/dma-direct.h>
 #include <linux/dma-mapping.h>
+#include <linux/dma-noncoherent.h>
 #include <linux/dma-contiguous.h>
 #include <linux/highmem.h>
 #include <linux/memblock.h>
@@ -38,6 +36,7 @@
 #include <asm/mach/map.h>
 #include <asm/system_info.h>
 #include <asm/dma-contiguous.h>
+#include <xen/swiotlb-xen.h>
 
 #include "dma.h"
 #include "mm.h"
@@ -180,11 +179,6 @@
 	__dma_page_cpu_to_dev(page, offset, size, dir);
 }
 
-static int arm_dma_mapping_error(struct device *dev, dma_addr_t dma_addr)
-{
-	return dma_addr == ARM_MAPPING_ERROR;
-}
-
 const struct dma_map_ops arm_dma_ops = {
 	.alloc			= arm_dma_alloc,
 	.free			= arm_dma_free,
@@ -194,12 +188,13 @@
 	.unmap_page		= arm_dma_unmap_page,
 	.map_sg			= arm_dma_map_sg,
 	.unmap_sg		= arm_dma_unmap_sg,
+	.map_resource		= dma_direct_map_resource,
 	.sync_single_for_cpu	= arm_dma_sync_single_for_cpu,
 	.sync_single_for_device	= arm_dma_sync_single_for_device,
 	.sync_sg_for_cpu	= arm_dma_sync_sg_for_cpu,
 	.sync_sg_for_device	= arm_dma_sync_sg_for_device,
-	.mapping_error		= arm_dma_mapping_error,
 	.dma_supported		= arm_dma_supported,
+	.get_required_mask	= dma_direct_get_required_mask,
 };
 EXPORT_SYMBOL(arm_dma_ops);
 
@@ -218,32 +213,15 @@
 	.get_sgtable		= arm_dma_get_sgtable,
 	.map_page		= arm_coherent_dma_map_page,
 	.map_sg			= arm_dma_map_sg,
-	.mapping_error		= arm_dma_mapping_error,
+	.map_resource		= dma_direct_map_resource,
 	.dma_supported		= arm_dma_supported,
+	.get_required_mask	= dma_direct_get_required_mask,
 };
 EXPORT_SYMBOL(arm_coherent_dma_ops);
 
 static int __dma_supported(struct device *dev, u64 mask, bool warn)
 {
-	unsigned long max_dma_pfn;
-
-	/*
-	 * If the mask allows for more memory than we can address,
-	 * and we actually have that much memory, then we must
-	 * indicate that DMA to this device is not supported.
-	 */
-	if (sizeof(mask) != sizeof(dma_addr_t) &&
-	    mask > (dma_addr_t)~0 &&
-	    dma_to_pfn(dev, ~0) < max_pfn - 1) {
-		if (warn) {
-			dev_warn(dev, "Coherent DMA mask %#llx is larger than dma_addr_t allows\n",
-				 mask);
-			dev_warn(dev, "Driver did not use or check the return value from dma_set_coherent_mask()?\n");
-		}
-		return 0;
-	}
-
-	max_dma_pfn = min(max_pfn, arm_dma_pfn_limit);
+	unsigned long max_dma_pfn = min(max_pfn, arm_dma_pfn_limit);
 
 	/*
 	 * Translate the device's DMA mask to a PFN limit.  This
@@ -362,25 +340,6 @@
 				 pgprot_t prot, struct page **ret_page,
 				 const void *caller, bool want_vaddr);
 
-static void *
-__dma_alloc_remap(struct page *page, size_t size, gfp_t gfp, pgprot_t prot,
-	const void *caller)
-{
-	/*
-	 * DMA allocation can be mapped to user space, so lets
-	 * set VM_USERMAP flags too.
-	 */
-	return dma_common_contiguous_remap(page, size,
-			VM_ARM_DMA_CONSISTENT | VM_USERMAP,
-			prot, caller);
-}
-
-static void __dma_free_remap(void *cpu_addr, size_t size)
-{
-	dma_common_free_remap(cpu_addr, size,
-			VM_ARM_DMA_CONSISTENT | VM_USERMAP);
-}
-
 #define DEFAULT_DMA_COHERENT_POOL_SIZE	SZ_256K
 static struct gen_pool *atomic_pool __ro_after_init;
 
@@ -502,8 +461,7 @@
 	}
 }
 
-static int __dma_update_pte(pte_t *pte, pgtable_t token, unsigned long addr,
-			    void *data)
+static int __dma_update_pte(pte_t *pte, unsigned long addr, void *data)
 {
 	struct page *page = virt_to_page(addr);
 	pgprot_t prot = *(pgprot_t *)data;
@@ -537,7 +495,7 @@
 	if (!want_vaddr)
 		goto out;
 
-	ptr = __dma_alloc_remap(page, size, gfp, prot, caller);
+	ptr = dma_common_contiguous_remap(page, size, prot, caller);
 	if (!ptr) {
 		__dma_free_buffer(page, size);
 		return NULL;
@@ -604,7 +562,7 @@
 		goto out;
 
 	if (PageHighMem(page)) {
-		ptr = __dma_alloc_remap(page, size, GFP_KERNEL, prot, caller);
+		ptr = dma_common_contiguous_remap(page, size, prot, caller);
 		if (!ptr) {
 			dma_release_from_contiguous(dev, page, count);
 			return NULL;
@@ -624,7 +582,7 @@
 {
 	if (want_vaddr) {
 		if (PageHighMem(page))
-			__dma_free_remap(cpu_addr, size);
+			dma_common_free_remap(cpu_addr, size);
 		else
 			__dma_remap(page, size, PAGE_KERNEL);
 	}
@@ -716,7 +674,7 @@
 static void remap_allocator_free(struct arm_dma_free_args *args)
 {
 	if (args->want_vaddr)
-		__dma_free_remap(args->cpu_addr, args->size);
+		dma_common_free_remap(args->cpu_addr, args->size);
 
 	__dma_free_buffer(args->page, args->size);
 }
@@ -775,7 +733,7 @@
 	gfp &= ~(__GFP_COMP);
 	args.gfp = gfp;
 
-	*handle = ARM_MAPPING_ERROR;
+	*handle = DMA_MAPPING_ERROR;
 	allowblock = gfpflags_allow_blocking(gfp);
 	cma = allowblock ? dev_get_cma_area(dev) : false;
 
@@ -904,17 +862,6 @@
 	__arm_dma_free(dev, size, cpu_addr, handle, attrs, true);
 }
 
-/*
- * The whole dma_get_sgtable() idea is fundamentally unsafe - it seems
- * that the intention is to allow exporting memory allocated via the
- * coherent DMA APIs through the dma_buf API, which only accepts a
- * scattertable.  This presents a couple of problems:
- * 1. Not all memory allocated via the coherent DMA APIs is backed by
- *    a struct page
- * 2. Passing coherent DMA memory into the streaming APIs is not allowed
- *    as we will try to flush the memory through a different alias to that
- *    actually being used (and the flushes are redundant.)
- */
 int arm_dma_get_sgtable(struct device *dev, struct sg_table *sgt,
 		 void *cpu_addr, dma_addr_t handle, size_t size,
 		 unsigned long attrs)
@@ -1153,6 +1100,15 @@
 
 static const struct dma_map_ops *arm_get_dma_map_ops(bool coherent)
 {
+	/*
+	 * When CONFIG_ARM_LPAE is set, physical address can extend above
+	 * 32-bits, which then can't be addressed by devices that only support
+	 * 32-bit DMA.
+	 * Use the generic dma-direct / swiotlb ops code in that case, as that
+	 * handles bounce buffering for us.
+	 */
+	if (IS_ENABLED(CONFIG_ARM_LPAE))
+		return NULL;
 	return coherent ? &arm_coherent_dma_ops : &arm_dma_ops;
 }
 
@@ -1218,7 +1174,7 @@
 	if (i == mapping->nr_bitmaps) {
 		if (extend_iommu_mapping(mapping)) {
 			spin_unlock_irqrestore(&mapping->lock, flags);
-			return ARM_MAPPING_ERROR;
+			return DMA_MAPPING_ERROR;
 		}
 
 		start = bitmap_find_next_zero_area(mapping->bitmaps[i],
@@ -1226,7 +1182,7 @@
 
 		if (start > mapping->bits) {
 			spin_unlock_irqrestore(&mapping->lock, flags);
-			return ARM_MAPPING_ERROR;
+			return DMA_MAPPING_ERROR;
 		}
 
 		bitmap_set(mapping->bitmaps[i], start, count);
@@ -1387,17 +1343,6 @@
 }
 
 /*
- * Create a CPU mapping for a specified pages
- */
-static void *
-__iommu_alloc_remap(struct page **pages, size_t size, gfp_t gfp, pgprot_t prot,
-		    const void *caller)
-{
-	return dma_common_pages_remap(pages, size,
-			VM_ARM_DMA_CONSISTENT | VM_USERMAP, prot, caller);
-}
-
-/*
  * Create a mapping in device IO address space for specified pages
  */
 static dma_addr_t
@@ -1410,7 +1355,7 @@
 	int i;
 
 	dma_addr = __alloc_iova(mapping, size);
-	if (dma_addr == ARM_MAPPING_ERROR)
+	if (dma_addr == DMA_MAPPING_ERROR)
 		return dma_addr;
 
 	iova = dma_addr;
@@ -1437,7 +1382,7 @@
 fail:
 	iommu_unmap(mapping->domain, dma_addr, iova-dma_addr);
 	__free_iova(mapping, dma_addr, size);
-	return ARM_MAPPING_ERROR;
+	return DMA_MAPPING_ERROR;
 }
 
 static int __iommu_remove_mapping(struct device *dev, dma_addr_t iova, size_t size)
@@ -1469,18 +1414,13 @@
 
 static struct page **__iommu_get_pages(void *cpu_addr, unsigned long attrs)
 {
-	struct vm_struct *area;
-
 	if (__in_atomic_pool(cpu_addr, PAGE_SIZE))
 		return __atomic_get_pages(cpu_addr);
 
 	if (attrs & DMA_ATTR_NO_KERNEL_MAPPING)
 		return cpu_addr;
 
-	area = find_vm_area(cpu_addr);
-	if (area && (area->flags & VM_ARM_DMA_CONSISTENT))
-		return area->pages;
-	return NULL;
+	return dma_common_find_pages(cpu_addr);
 }
 
 static void *__iommu_alloc_simple(struct device *dev, size_t size, gfp_t gfp,
@@ -1498,7 +1438,7 @@
 		return NULL;
 
 	*handle = __iommu_create_mapping(dev, &page, size, attrs);
-	if (*handle == ARM_MAPPING_ERROR)
+	if (*handle == DMA_MAPPING_ERROR)
 		goto err_mapping;
 
 	return addr;
@@ -1526,7 +1466,7 @@
 	struct page **pages;
 	void *addr = NULL;
 
-	*handle = ARM_MAPPING_ERROR;
+	*handle = DMA_MAPPING_ERROR;
 	size = PAGE_ALIGN(size);
 
 	if (coherent_flag  == COHERENT || !gfpflags_allow_blocking(gfp))
@@ -1547,13 +1487,13 @@
 		return NULL;
 
 	*handle = __iommu_create_mapping(dev, pages, size, attrs);
-	if (*handle == ARM_MAPPING_ERROR)
+	if (*handle == DMA_MAPPING_ERROR)
 		goto err_buffer;
 
 	if (attrs & DMA_ATTR_NO_KERNEL_MAPPING)
 		return pages;
 
-	addr = __iommu_alloc_remap(pages, size, gfp, prot,
+	addr = dma_common_pages_remap(pages, size, prot,
 				   __builtin_return_address(0));
 	if (!addr)
 		goto err_mapping;
@@ -1583,31 +1523,21 @@
 		    void *cpu_addr, dma_addr_t dma_addr, size_t size,
 		    unsigned long attrs)
 {
-	unsigned long uaddr = vma->vm_start;
-	unsigned long usize = vma->vm_end - vma->vm_start;
 	struct page **pages = __iommu_get_pages(cpu_addr, attrs);
 	unsigned long nr_pages = PAGE_ALIGN(size) >> PAGE_SHIFT;
-	unsigned long off = vma->vm_pgoff;
+	int err;
 
 	if (!pages)
 		return -ENXIO;
 
-	if (off >= nr_pages || (usize >> PAGE_SHIFT) > nr_pages - off)
+	if (vma->vm_pgoff >= nr_pages)
 		return -ENXIO;
 
-	pages += off;
+	err = vm_map_pages(vma, pages, nr_pages);
+	if (err)
+		pr_err("Remapping memory failed: %d\n", err);
 
-	do {
-		int ret = vm_insert_page(vma, uaddr, *pages++);
-		if (ret) {
-			pr_err("Remapping memory failed: %d\n", ret);
-			return ret;
-		}
-		uaddr += PAGE_SIZE;
-		usize -= PAGE_SIZE;
-	} while (usize > 0);
-
-	return 0;
+	return err;
 }
 static int arm_iommu_mmap_attrs(struct device *dev,
 		struct vm_area_struct *vma, void *cpu_addr,
@@ -1646,10 +1576,8 @@
 		return;
 	}
 
-	if ((attrs & DMA_ATTR_NO_KERNEL_MAPPING) == 0) {
-		dma_common_free_remap(cpu_addr, size,
-			VM_ARM_DMA_CONSISTENT | VM_USERMAP);
-	}
+	if ((attrs & DMA_ATTR_NO_KERNEL_MAPPING) == 0)
+		dma_common_free_remap(cpu_addr, size);
 
 	__iommu_remove_mapping(dev, handle, size);
 	__iommu_free_buffer(dev, pages, size, attrs);
@@ -1697,10 +1625,10 @@
 	int prot;
 
 	size = PAGE_ALIGN(size);
-	*handle = ARM_MAPPING_ERROR;
+	*handle = DMA_MAPPING_ERROR;
 
 	iova_base = iova = __alloc_iova(mapping, size);
-	if (iova == ARM_MAPPING_ERROR)
+	if (iova == DMA_MAPPING_ERROR)
 		return -ENOMEM;
 
 	for (count = 0, s = sg; count < (size >> PAGE_SHIFT); s = sg_next(s)) {
@@ -1740,7 +1668,7 @@
 	for (i = 1; i < nents; i++) {
 		s = sg_next(s);
 
-		s->dma_address = ARM_MAPPING_ERROR;
+		s->dma_address = DMA_MAPPING_ERROR;
 		s->dma_length = 0;
 
 		if (s->offset || (size & ~PAGE_MASK) || size + s->length > max) {
@@ -1915,7 +1843,7 @@
 	int ret, prot, len = PAGE_ALIGN(size + offset);
 
 	dma_addr = __alloc_iova(mapping, len);
-	if (dma_addr == ARM_MAPPING_ERROR)
+	if (dma_addr == DMA_MAPPING_ERROR)
 		return dma_addr;
 
 	prot = __dma_info_to_prot(dir, attrs);
@@ -1927,7 +1855,7 @@
 	return dma_addr + offset;
 fail:
 	__free_iova(mapping, dma_addr, len);
-	return ARM_MAPPING_ERROR;
+	return DMA_MAPPING_ERROR;
 }
 
 /**
@@ -2021,7 +1949,7 @@
 	size_t len = PAGE_ALIGN(size + offset);
 
 	dma_addr = __alloc_iova(mapping, len);
-	if (dma_addr == ARM_MAPPING_ERROR)
+	if (dma_addr == DMA_MAPPING_ERROR)
 		return dma_addr;
 
 	prot = __dma_info_to_prot(dir, attrs) | IOMMU_MMIO;
@@ -2033,7 +1961,7 @@
 	return dma_addr + offset;
 fail:
 	__free_iova(mapping, dma_addr, len);
-	return ARM_MAPPING_ERROR;
+	return DMA_MAPPING_ERROR;
 }
 
 /**
@@ -2106,7 +2034,6 @@
 	.map_resource		= arm_iommu_map_resource,
 	.unmap_resource		= arm_iommu_unmap_resource,
 
-	.mapping_error		= arm_dma_mapping_error,
 	.dma_supported		= arm_dma_supported,
 };
 
@@ -2125,7 +2052,6 @@
 	.map_resource	= arm_iommu_map_resource,
 	.unmap_resource	= arm_iommu_unmap_resource,
 
-	.mapping_error		= arm_dma_mapping_error,
 	.dma_supported		= arm_dma_supported,
 };
 
@@ -2287,7 +2213,7 @@
  * @dev: valid struct device pointer
  *
  * Detaches the provided device from a previously attached map.
- * This voids the dma operations (dma_map_ops pointer)
+ * This overwrites the dma_ops pointer with appropriate non-IOMMU ops.
  */
 void arm_iommu_detach_device(struct device *dev)
 {
@@ -2369,6 +2295,9 @@
 	const struct dma_map_ops *dma_ops;
 
 	dev->archdata.dma_coherent = coherent;
+#ifdef CONFIG_SWIOTLB
+	dev->dma_coherent = coherent;
+#endif
 
 	/*
 	 * Don't override the dma_ops if they have already been set. Ideally
@@ -2386,10 +2315,8 @@
 	set_dma_ops(dev, dma_ops);
 
 #ifdef CONFIG_XEN
-	if (xen_initial_domain()) {
-		dev->archdata.dev_dma_ops = dev->dma_ops;
-		dev->dma_ops = xen_dma_ops;
-	}
+	if (xen_initial_domain())
+		dev->dma_ops = &xen_swiotlb_dma_ops;
 #endif
 	dev->archdata.dma_ops_setup = true;
 }
@@ -2400,4 +2327,42 @@
 		return;
 
 	arm_teardown_iommu_dma_ops(dev);
+	/* Let arch_setup_dma_ops() start again from scratch upon re-probe */
+	set_dma_ops(dev, NULL);
 }
+
+#ifdef CONFIG_SWIOTLB
+void arch_sync_dma_for_device(struct device *dev, phys_addr_t paddr,
+		size_t size, enum dma_data_direction dir)
+{
+	__dma_page_cpu_to_dev(phys_to_page(paddr), paddr & (PAGE_SIZE - 1),
+			      size, dir);
+}
+
+void arch_sync_dma_for_cpu(struct device *dev, phys_addr_t paddr,
+		size_t size, enum dma_data_direction dir)
+{
+	__dma_page_dev_to_cpu(phys_to_page(paddr), paddr & (PAGE_SIZE - 1),
+			      size, dir);
+}
+
+long arch_dma_coherent_to_pfn(struct device *dev, void *cpu_addr,
+		dma_addr_t dma_addr)
+{
+	return dma_to_pfn(dev, dma_addr);
+}
+
+void *arch_dma_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle,
+		gfp_t gfp, unsigned long attrs)
+{
+	return __dma_alloc(dev, size, dma_handle, gfp,
+			   __get_dma_pgprot(attrs, PAGE_KERNEL), false,
+			   attrs, __builtin_return_address(0));
+}
+
+void arch_dma_free(struct device *dev, size_t size, void *cpu_addr,
+		dma_addr_t dma_handle, unsigned long attrs)
+{
+	__arm_dma_free(dev, size, cpu_addr, dma_handle, attrs, false);
+}
+#endif /* CONFIG_SWIOTLB */
diff --git a/arch/arm/mm/dump.c b/arch/arm/mm/dump.c
index 084779c..7d6291f 100644
--- a/arch/arm/mm/dump.c
+++ b/arch/arm/mm/dump.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Debug helper to dump the current kernel pagetables of the system
  * so that we can see what the various memory ranges are set to.
@@ -6,11 +7,6 @@
  * (C) Copyright 2008 Intel Corporation
  *
  * Author: Arjan van de Ven <arjan@linux.intel.com>
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; version 2
- * of the License.
  */
 #include <linux/debugfs.h>
 #include <linux/fs.h>
@@ -450,7 +446,7 @@
 static int ptdump_init(void)
 {
 	ptdump_initialize();
-	return ptdump_debugfs_register(&kernel_ptdump_info,
-					"kernel_page_tables");
+	ptdump_debugfs_register(&kernel_ptdump_info, "kernel_page_tables");
+	return 0;
 }
 __initcall(ptdump_init);
diff --git a/arch/arm/mm/fault-armv.c b/arch/arm/mm/fault-armv.c
index 4d75dae..ae857f4 100644
--- a/arch/arm/mm/fault-armv.c
+++ b/arch/arm/mm/fault-armv.c
@@ -1,12 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  *  linux/arch/arm/mm/fault-armv.c
  *
  *  Copyright (C) 1995  Linus Torvalds
  *  Modifications for ARM processor (c) 1995-2002 Russell King
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
  */
 #include <linux/sched.h>
 #include <linux/kernel.h>
diff --git a/arch/arm/mm/fault.c b/arch/arm/mm/fault.c
index 3232afb..bd0f482 100644
--- a/arch/arm/mm/fault.c
+++ b/arch/arm/mm/fault.c
@@ -1,12 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  *  linux/arch/arm/mm/fault.c
  *
  *  Copyright (C) 1995  Linus Torvalds
  *  Modifications for ARM processor (c) 1995-2004 Russell King
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
  */
 #include <linux/extable.h>
 #include <linux/signal.h>
@@ -30,43 +27,20 @@
 
 #ifdef CONFIG_MMU
 
-#ifdef CONFIG_KPROBES
-static inline int notify_page_fault(struct pt_regs *regs, unsigned int fsr)
-{
-	int ret = 0;
-
-	if (!user_mode(regs)) {
-		/* kprobe_running() needs smp_processor_id() */
-		preempt_disable();
-		if (kprobe_running() && kprobe_fault_handler(regs, fsr))
-			ret = 1;
-		preempt_enable();
-	}
-
-	return ret;
-}
-#else
-static inline int notify_page_fault(struct pt_regs *regs, unsigned int fsr)
-{
-	return 0;
-}
-#endif
-
 /*
  * This is useful to dump out the page tables associated with
  * 'addr' in mm 'mm'.
  */
-void show_pte(struct mm_struct *mm, unsigned long addr)
+void show_pte(const char *lvl, struct mm_struct *mm, unsigned long addr)
 {
 	pgd_t *pgd;
 
 	if (!mm)
 		mm = &init_mm;
 
-	pr_alert("pgd = %p\n", mm->pgd);
+	printk("%spgd = %p\n", lvl, mm->pgd);
 	pgd = pgd_offset(mm, addr);
-	pr_alert("[%08lx] *pgd=%08llx",
-			addr, (long long)pgd_val(*pgd));
+	printk("%s[%08lx] *pgd=%08llx", lvl, addr, (long long)pgd_val(*pgd));
 
 	do {
 		pud_t *pud;
@@ -121,7 +95,7 @@
 	pr_cont("\n");
 }
 #else					/* CONFIG_MMU */
-void show_pte(struct mm_struct *mm, unsigned long addr)
+void show_pte(const char *lvl, struct mm_struct *mm, unsigned long addr)
 { }
 #endif					/* CONFIG_MMU */
 
@@ -142,11 +116,12 @@
 	 * No handler, we'll have to terminate things with extreme prejudice.
 	 */
 	bust_spinlocks(1);
+	pr_alert("8<--- cut here ---\n");
 	pr_alert("Unable to handle kernel %s at virtual address %08lx\n",
 		 (addr < PAGE_SIZE) ? "NULL pointer dereference" :
 		 "paging request", addr);
 
-	show_pte(mm, addr);
+	show_pte(KERN_ALERT, mm, addr);
 	die("Oops", regs, fsr);
 	bust_spinlocks(0);
 	do_exit(SIGKILL);
@@ -157,35 +132,35 @@
  * User mode accesses just cause a SIGSEGV
  */
 static void
-__do_user_fault(struct task_struct *tsk, unsigned long addr,
-		unsigned int fsr, unsigned int sig, int code,
-		struct pt_regs *regs)
+__do_user_fault(unsigned long addr, unsigned int fsr, unsigned int sig,
+		int code, struct pt_regs *regs)
 {
-	struct siginfo si;
+	struct task_struct *tsk = current;
 
 	if (addr > TASK_SIZE)
 		harden_branch_predictor();
 
-	clear_siginfo(&si);
-
 #ifdef CONFIG_DEBUG_USER
 	if (((user_debug & UDBG_SEGV) && (sig == SIGSEGV)) ||
 	    ((user_debug & UDBG_BUS)  && (sig == SIGBUS))) {
-		printk(KERN_DEBUG "%s: unhandled page fault (%d) at 0x%08lx, code 0x%03x\n",
+		pr_err("8<--- cut here ---\n");
+		pr_err("%s: unhandled page fault (%d) at 0x%08lx, code 0x%03x\n",
 		       tsk->comm, sig, addr, fsr);
-		show_pte(tsk->mm, addr);
+		show_pte(KERN_ERR, tsk->mm, addr);
 		show_regs(regs);
 	}
 #endif
+#ifndef CONFIG_KUSER_HELPERS
+	if ((sig == SIGSEGV) && ((addr & PAGE_MASK) == 0xffff0000))
+		printk_ratelimited(KERN_DEBUG
+				   "%s: CONFIG_KUSER_HELPERS disabled at 0x%08lx\n",
+				   tsk->comm, addr);
+#endif
 
 	tsk->thread.address = addr;
 	tsk->thread.error_code = fsr;
 	tsk->thread.trap_no = 14;
-	si.si_signo = sig;
-	si.si_errno = 0;
-	si.si_code = code;
-	si.si_addr = (void __user *)addr;
-	force_sig_info(sig, &si, tsk);
+	force_sig_fault(sig, code, (void __user *)addr);
 }
 
 void do_bad_area(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
@@ -198,7 +173,7 @@
 	 * have no context to handle this fault with.
 	 */
 	if (user_mode(regs))
-		__do_user_fault(tsk, addr, fsr, SIGSEGV, SEGV_MAPERR, regs);
+		__do_user_fault(addr, fsr, SIGSEGV, SEGV_MAPERR, regs);
 	else
 		__do_kernel_fault(mm, addr, fsr, regs);
 }
@@ -216,7 +191,7 @@
 {
 	unsigned int mask = VM_READ | VM_WRITE | VM_EXEC;
 
-	if (fsr & FSR_WRITE)
+	if ((fsr & FSR_WRITE) && !(fsr & FSR_CM))
 		mask = VM_WRITE;
 	if (fsr & FSR_LNX_PF)
 		mask = VM_EXEC;
@@ -268,7 +243,7 @@
 	vm_fault_t fault;
 	unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
 
-	if (notify_page_fault(regs, fsr))
+	if (kprobe_page_fault(regs, fsr))
 		return 0;
 
 	tsk = current;
@@ -287,7 +262,7 @@
 
 	if (user_mode(regs))
 		flags |= FAULT_FLAG_USER;
-	if (fsr & FSR_WRITE)
+	if ((fsr & FSR_WRITE) && !(fsr & FSR_CM))
 		flags |= FAULT_FLAG_WRITE;
 
 	/*
@@ -394,7 +369,7 @@
 			SEGV_ACCERR : SEGV_MAPERR;
 	}
 
-	__do_user_fault(tsk, addr, fsr, sig, code, regs);
+	__do_user_fault(addr, fsr, sig, code, regs);
 	return 0;
 
 no_context:
@@ -554,21 +529,17 @@
 do_DataAbort(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
 {
 	const struct fsr_info *inf = fsr_info + fsr_fs(fsr);
-	struct siginfo info;
 
 	if (!inf->fn(addr, fsr & ~FSR_LNX_PF, regs))
 		return;
 
+	pr_alert("8<--- cut here ---\n");
 	pr_alert("Unhandled fault: %s (0x%03x) at 0x%08lx\n",
 		inf->name, fsr, addr);
-	show_pte(current->mm, addr);
+	show_pte(KERN_ALERT, current->mm, addr);
 
-	clear_siginfo(&info);
-	info.si_signo = inf->sig;
-	info.si_errno = 0;
-	info.si_code  = inf->code;
-	info.si_addr  = (void __user *)addr;
-	arm_notify_die("", regs, &info, fsr, 0);
+	arm_notify_die("", regs, inf->sig, inf->code, (void __user *)addr,
+		       fsr, 0);
 }
 
 void __init
@@ -588,7 +559,6 @@
 do_PrefetchAbort(unsigned long addr, unsigned int ifsr, struct pt_regs *regs)
 {
 	const struct fsr_info *inf = ifsr_info + fsr_fs(ifsr);
-	struct siginfo info;
 
 	if (!inf->fn(addr, ifsr | FSR_LNX_PF, regs))
 		return;
@@ -596,12 +566,8 @@
 	pr_alert("Unhandled prefetch abort: %s (0x%03x) at 0x%08lx\n",
 		inf->name, ifsr, addr);
 
-	clear_siginfo(&info);
-	info.si_signo = inf->sig;
-	info.si_errno = 0;
-	info.si_code  = inf->code;
-	info.si_addr  = (void __user *)addr;
-	arm_notify_die("", regs, &info, ifsr, 0);
+	arm_notify_die("", regs, inf->sig, inf->code, (void __user *)addr,
+		       ifsr, 0);
 }
 
 /*
diff --git a/arch/arm/mm/fault.h b/arch/arm/mm/fault.h
index c063708..9ecc209 100644
--- a/arch/arm/mm/fault.h
+++ b/arch/arm/mm/fault.h
@@ -6,6 +6,7 @@
  * Fault status register encodings.  We steal bit 31 for our own purposes.
  */
 #define FSR_LNX_PF		(1 << 31)
+#define FSR_CM			(1 << 13)
 #define FSR_WRITE		(1 << 11)
 #define FSR_FS4			(1 << 10)
 #define FSR_FS3_0		(15)
diff --git a/arch/arm/mm/flush.c b/arch/arm/mm/flush.c
index 5846962..6d89db7 100644
--- a/arch/arm/mm/flush.c
+++ b/arch/arm/mm/flush.c
@@ -1,11 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  *  linux/arch/arm/mm/flush.c
  *
  *  Copyright (C) 1995-2002 Russell King
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
  */
 #include <linux/module.h>
 #include <linux/mm.h>
@@ -207,18 +204,17 @@
 	 * coherent with the kernels mapping.
 	 */
 	if (!PageHighMem(page)) {
-		size_t page_size = PAGE_SIZE << compound_order(page);
-		__cpuc_flush_dcache_area(page_address(page), page_size);
+		__cpuc_flush_dcache_area(page_address(page), page_size(page));
 	} else {
 		unsigned long i;
 		if (cache_is_vipt_nonaliasing()) {
-			for (i = 0; i < (1 << compound_order(page)); i++) {
+			for (i = 0; i < compound_nr(page); i++) {
 				void *addr = kmap_atomic(page + i);
 				__cpuc_flush_dcache_area(addr, PAGE_SIZE);
 				kunmap_atomic(addr);
 			}
 		} else {
-			for (i = 0; i < (1 << compound_order(page)); i++) {
+			for (i = 0; i < compound_nr(page); i++) {
 				void *addr = kmap_high_get(page + i);
 				if (addr) {
 					__cpuc_flush_dcache_area(addr, PAGE_SIZE);
diff --git a/arch/arm/mm/highmem.c b/arch/arm/mm/highmem.c
index d02f818..a76f8ac 100644
--- a/arch/arm/mm/highmem.c
+++ b/arch/arm/mm/highmem.c
@@ -1,13 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * arch/arm/mm/highmem.c -- ARM highmem support
  *
  * Author:	Nicolas Pitre
  * Created:	september 8, 2008
  * Copyright:	Marvell Semiconductors Inc.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
  */
 
 #include <linux/module.h>
diff --git a/arch/arm/mm/hugetlbpage.c b/arch/arm/mm/hugetlbpage.c
index fcafb52..a1e5aac 100644
--- a/arch/arm/mm/hugetlbpage.c
+++ b/arch/arm/mm/hugetlbpage.c
@@ -1,22 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * arch/arm/mm/hugetlbpage.c
  *
  * Copyright (C) 2012 ARM Ltd.
  *
  * Based on arch/x86/include/asm/hugetlb.h and Bill Carson's patches
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
  */
 
 #include <linux/init.h>
diff --git a/arch/arm/mm/idmap.c b/arch/arm/mm/idmap.c
index 1d1edd0..a033f61 100644
--- a/arch/arm/mm/idmap.c
+++ b/arch/arm/mm/idmap.c
@@ -6,6 +6,7 @@
 
 #include <asm/cputype.h>
 #include <asm/idmap.h>
+#include <asm/hwcap.h>
 #include <asm/pgalloc.h>
 #include <asm/pgtable.h>
 #include <asm/sections.h>
@@ -110,7 +111,8 @@
 			     __idmap_text_end, 0);
 
 	/* Flush L1 for the hardware to see this page table content */
-	flush_cache_louis();
+	if (!(elf_hwcap & HWCAP_LPAE))
+		flush_cache_louis();
 
 	return 0;
 }
diff --git a/arch/arm/mm/init.c b/arch/arm/mm/init.c
index 0cc8e04..b4be3ba 100644
--- a/arch/arm/mm/init.c
+++ b/arch/arm/mm/init.c
@@ -1,17 +1,13 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  *  linux/arch/arm/mm/init.c
  *
  *  Copyright (C) 1995-2005 Russell King
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
  */
 #include <linux/kernel.h>
 #include <linux/errno.h>
 #include <linux/swap.h>
 #include <linux/init.h>
-#include <linux/bootmem.h>
 #include <linux/mman.h>
 #include <linux/sched/signal.h>
 #include <linux/sched/task.h>
@@ -25,6 +21,7 @@
 #include <linux/dma-contiguous.h>
 #include <linux/sizes.h>
 #include <linux/stop_machine.h>
+#include <linux/swiotlb.h>
 
 #include <asm/cp15.h>
 #include <asm/mach-types.h>
@@ -51,26 +48,7 @@
 }
 #endif
 
-static phys_addr_t phys_initrd_start __initdata = 0;
-static unsigned long phys_initrd_size __initdata = 0;
-
-static int __init early_initrd(char *p)
-{
-	phys_addr_t start;
-	unsigned long size;
-	char *endp;
-
-	start = memparse(p, &endp);
-	if (*endp == ',') {
-		size = memparse(endp + 1, NULL);
-
-		phys_initrd_start = start;
-		phys_initrd_size = size;
-	}
-	return 0;
-}
-early_param("initrd", early_initrd);
-
+#ifdef CONFIG_BLK_DEV_INITRD
 static int __init parse_tag_initrd(const struct tag *tag)
 {
 	pr_warn("ATAG_INITRD is deprecated; "
@@ -90,6 +68,7 @@
 }
 
 __tagtable(ATAG_INITRD2, parse_tag_initrd2);
+#endif
 
 static void __init find_limits(unsigned long *min, unsigned long *max_low,
 			       unsigned long *max_high)
@@ -196,26 +175,16 @@
 #ifdef CONFIG_HAVE_ARCH_PFN_VALID
 int pfn_valid(unsigned long pfn)
 {
+	phys_addr_t addr = __pfn_to_phys(pfn);
+
+	if (__phys_to_pfn(addr) != pfn)
+		return 0;
+
 	return memblock_is_map_memory(__pfn_to_phys(pfn));
 }
 EXPORT_SYMBOL(pfn_valid);
 #endif
 
-#ifndef CONFIG_SPARSEMEM
-static void __init arm_memory_present(void)
-{
-}
-#else
-static void __init arm_memory_present(void)
-{
-	struct memblock_region *reg;
-
-	for_each_memblock(memory, reg)
-		memory_present(0, memblock_region_memory_base_pfn(reg),
-			       memblock_region_memory_end_pfn(reg));
-}
-#endif
-
 static bool arm_memblock_steal_permitted = true;
 
 phys_addr_t __init arm_memblock_steal(phys_addr_t size, phys_addr_t align)
@@ -224,7 +193,11 @@
 
 	BUG_ON(!arm_memblock_steal_permitted);
 
-	phys = memblock_alloc_base(size, align, MEMBLOCK_ALLOC_ANYWHERE);
+	phys = memblock_phys_alloc(size, align);
+	if (!phys)
+		panic("Failed to steal %pa bytes at %pS\n",
+		      &size, (void *)_RET_IP_);
+
 	memblock_free(phys, size);
 	memblock_remove(phys, size);
 
@@ -237,12 +210,6 @@
 	phys_addr_t start;
 	unsigned long size;
 
-	/* FDT scan will populate initrd_start */
-	if (initrd_start && !phys_initrd_size) {
-		phys_initrd_start = __virt_to_phys(initrd_start);
-		phys_initrd_size = initrd_end - initrd_start;
-	}
-
 	initrd_start = initrd_end = 0;
 
 	if (!phys_initrd_size)
@@ -278,6 +245,22 @@
 #endif
 }
 
+#ifdef CONFIG_CPU_ICACHE_MISMATCH_WORKAROUND
+void check_cpu_icache_size(int cpuid)
+{
+	u32 size, ctr;
+
+	asm("mrc p15, 0, %0, c0, c0, 1" : "=r" (ctr));
+
+	size = 1 << ((ctr & 0xf) + 2);
+	if (cpuid != 0 && icache_size != size)
+		pr_info("CPU%u: detected I-Cache line size mismatch, workaround enabled\n",
+			cpuid);
+	if (icache_size > size)
+		icache_size = size;
+}
+#endif
+
 void __init arm_memblock_init(const struct machine_desc *mdesc)
 {
 	/* Register the kernel text, kernel data and initrd with memblock. */
@@ -303,21 +286,18 @@
 
 void __init bootmem_init(void)
 {
-	unsigned long min, max_low, max_high;
-
 	memblock_allow_resize();
-	max_low = max_high = 0;
 
-	find_limits(&min, &max_low, &max_high);
+	find_limits(&min_low_pfn, &max_low_pfn, &max_pfn);
 
-	early_memtest((phys_addr_t)min << PAGE_SHIFT,
-		      (phys_addr_t)max_low << PAGE_SHIFT);
+	early_memtest((phys_addr_t)min_low_pfn << PAGE_SHIFT,
+		      (phys_addr_t)max_low_pfn << PAGE_SHIFT);
 
 	/*
 	 * Sparsemem tries to allocate bootmem in memory_present(),
 	 * so must be done after the fixed reservations
 	 */
-	arm_memory_present();
+	memblocks_present();
 
 	/*
 	 * sparse_init() needs the bootmem allocator up and running.
@@ -329,16 +309,7 @@
 	 * the sparse mem_map arrays initialized by sparse_init()
 	 * for memmap_init_zone(), otherwise all PFNs are invalid.
 	 */
-	zone_sizes_init(min, max_low, max_high);
-
-	/*
-	 * This doesn't seem to be used by the Linux memory manager any
-	 * more, but is used by ll_rw_block.  If we can get rid of it, we
-	 * also get rid of some of the stuff above as well.
-	 */
-	min_low_pfn = min;
-	max_low_pfn = max_low;
-	max_pfn = max_high;
+	zone_sizes_init(min_low_pfn, max_low_pfn, max_pfn);
 }
 
 /*
@@ -498,17 +469,15 @@
  */
 void __init mem_init(void)
 {
-#ifdef CONFIG_HAVE_TCM
-	/* These pointers are filled in on TCM detection */
-	extern u32 dtcm_end;
-	extern u32 itcm_end;
+#ifdef CONFIG_ARM_LPAE
+	swiotlb_init(1);
 #endif
 
 	set_max_mapnr(pfn_to_page(max_pfn) - mem_map);
 
 	/* this will put all unused low memory onto the freelists */
 	free_unused_memmap();
-	free_all_bootmem();
+	memblock_free_all();
 
 #ifdef CONFIG_SA1111
 	/* now that our DMA memory is actually so designated, we can free it */
@@ -519,55 +488,6 @@
 
 	mem_init_print_info(NULL);
 
-#define MLK(b, t) b, t, ((t) - (b)) >> 10
-#define MLM(b, t) b, t, ((t) - (b)) >> 20
-#define MLK_ROUNDUP(b, t) b, t, DIV_ROUND_UP(((t) - (b)), SZ_1K)
-
-	pr_notice("Virtual kernel memory layout:\n"
-			"    vector  : 0x%08lx - 0x%08lx   (%4ld kB)\n"
-#ifdef CONFIG_HAVE_TCM
-			"    DTCM    : 0x%08lx - 0x%08lx   (%4ld kB)\n"
-			"    ITCM    : 0x%08lx - 0x%08lx   (%4ld kB)\n"
-#endif
-			"    fixmap  : 0x%08lx - 0x%08lx   (%4ld kB)\n"
-			"    vmalloc : 0x%08lx - 0x%08lx   (%4ld MB)\n"
-			"    lowmem  : 0x%08lx - 0x%08lx   (%4ld MB)\n"
-#ifdef CONFIG_HIGHMEM
-			"    pkmap   : 0x%08lx - 0x%08lx   (%4ld MB)\n"
-#endif
-#ifdef CONFIG_MODULES
-			"    modules : 0x%08lx - 0x%08lx   (%4ld MB)\n"
-#endif
-			"      .text : 0x%p" " - 0x%p" "   (%4td kB)\n"
-			"      .init : 0x%p" " - 0x%p" "   (%4td kB)\n"
-			"      .data : 0x%p" " - 0x%p" "   (%4td kB)\n"
-			"       .bss : 0x%p" " - 0x%p" "   (%4td kB)\n",
-
-			MLK(VECTORS_BASE, VECTORS_BASE + PAGE_SIZE),
-#ifdef CONFIG_HAVE_TCM
-			MLK(DTCM_OFFSET, (unsigned long) dtcm_end),
-			MLK(ITCM_OFFSET, (unsigned long) itcm_end),
-#endif
-			MLK(FIXADDR_START, FIXADDR_END),
-			MLM(VMALLOC_START, VMALLOC_END),
-			MLM(PAGE_OFFSET, (unsigned long)high_memory),
-#ifdef CONFIG_HIGHMEM
-			MLM(PKMAP_BASE, (PKMAP_BASE) + (LAST_PKMAP) *
-				(PAGE_SIZE)),
-#endif
-#ifdef CONFIG_MODULES
-			MLM(MODULES_VADDR, MODULES_END),
-#endif
-
-			MLK_ROUNDUP(_text, _etext),
-			MLK_ROUNDUP(__init_begin, __init_end),
-			MLK_ROUNDUP(_sdata, _edata),
-			MLK_ROUNDUP(__bss_start, __bss_stop));
-
-#undef MLK
-#undef MLM
-#undef MLK_ROUNDUP
-
 	/*
 	 * Check boundaries twice: Some fundamental inconsistencies can
 	 * be detected at build time already.
@@ -713,7 +633,8 @@
 		if (t->flags & PF_KTHREAD)
 			continue;
 		for_each_thread(t, s)
-			set_section_perms(perms, n, true, s->mm);
+			if (s->mm)
+				set_section_perms(perms, n, true, s->mm);
 	}
 	set_section_perms(perms, n, true, current->active_mm);
 	set_section_perms(perms, n, true, &init_mm);
@@ -777,27 +698,14 @@
 }
 
 #ifdef CONFIG_BLK_DEV_INITRD
-
-static int keep_initrd;
-
 void free_initrd_mem(unsigned long start, unsigned long end)
 {
-	if (!keep_initrd) {
-		if (start == initrd_start)
-			start = round_down(start, PAGE_SIZE);
-		if (end == initrd_end)
-			end = round_up(end, PAGE_SIZE);
+	if (start == initrd_start)
+		start = round_down(start, PAGE_SIZE);
+	if (end == initrd_end)
+		end = round_up(end, PAGE_SIZE);
 
-		poison_init_mem((void *)start, PAGE_ALIGN(end) - start);
-		free_reserved_area((void *)start, (void *)end, -1, "initrd");
-	}
+	poison_init_mem((void *)start, PAGE_ALIGN(end) - start);
+	free_reserved_area((void *)start, (void *)end, -1, "initrd");
 }
-
-static int __init keepinitrd_setup(char *__unused)
-{
-	keep_initrd = 1;
-	return 1;
-}
-
-__setup("keepinitrd", keepinitrd_setup);
 #endif
diff --git a/arch/arm/mm/ioremap.c b/arch/arm/mm/ioremap.c
index 5bf9443..d42b933 100644
--- a/arch/arm/mm/ioremap.c
+++ b/arch/arm/mm/ioremap.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  *  linux/arch/arm/mm/ioremap.c
  *
diff --git a/arch/arm/mm/l2c-common.c b/arch/arm/mm/l2c-common.c
index 10a3cf2..073b435 100644
--- a/arch/arm/mm/l2c-common.c
+++ b/arch/arm/mm/l2c-common.c
@@ -1,10 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Copyright (C) 2010 ARM Ltd.
  * Written by Catalin Marinas <catalin.marinas@arm.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
  */
 #include <linux/bug.h>
 #include <linux/smp.h>
diff --git a/arch/arm/mm/mm.h b/arch/arm/mm/mm.h
index 6b045c6..88c121a 100644
--- a/arch/arm/mm/mm.h
+++ b/arch/arm/mm/mm.h
@@ -8,6 +8,8 @@
 /* the upper-most page table pointer */
 extern pmd_t *top_pmd;
 
+extern int icache_size;
+
 /*
  * 0xffff8000 to 0xffffffff is reserved for any ARM architecture
  * specific hacks for copying pages efficiently, while 0xffff4000
@@ -68,9 +70,6 @@
 #define VM_ARM_MTYPE(mt)		((mt) << 20)
 #define VM_ARM_MTYPE_MASK	(0x1f << 20)
 
-/* consistent regions used by dma_alloc_attrs() */
-#define VM_ARM_DMA_CONSISTENT	0x20000000
-
 
 struct static_vm {
 	struct vm_struct vm;
diff --git a/arch/arm/mm/mmap.c b/arch/arm/mm/mmap.c
index f866870..b8d912a 100644
--- a/arch/arm/mm/mmap.c
+++ b/arch/arm/mm/mmap.c
@@ -17,33 +17,6 @@
 	((((addr)+SHMLBA-1)&~(SHMLBA-1)) +	\
 	 (((pgoff)<<PAGE_SHIFT) & (SHMLBA-1)))
 
-/* gap between mmap and stack */
-#define MIN_GAP (128*1024*1024UL)
-#define MAX_GAP ((TASK_SIZE)/6*5)
-
-static int mmap_is_legacy(struct rlimit *rlim_stack)
-{
-	if (current->personality & ADDR_COMPAT_LAYOUT)
-		return 1;
-
-	if (rlim_stack->rlim_cur == RLIM_INFINITY)
-		return 1;
-
-	return sysctl_legacy_va_layout;
-}
-
-static unsigned long mmap_base(unsigned long rnd, struct rlimit *rlim_stack)
-{
-	unsigned long gap = rlim_stack->rlim_cur;
-
-	if (gap < MIN_GAP)
-		gap = MIN_GAP;
-	else if (gap > MAX_GAP)
-		gap = MAX_GAP;
-
-	return PAGE_ALIGN(TASK_SIZE - gap - rnd);
-}
-
 /*
  * We need to ensure that shared mappings are correctly aligned to
  * avoid aliasing issues with VIPT caches.  We need to ensure that
@@ -171,31 +144,6 @@
 	return addr;
 }
 
-unsigned long arch_mmap_rnd(void)
-{
-	unsigned long rnd;
-
-	rnd = get_random_long() & ((1UL << mmap_rnd_bits) - 1);
-
-	return rnd << PAGE_SHIFT;
-}
-
-void arch_pick_mmap_layout(struct mm_struct *mm, struct rlimit *rlim_stack)
-{
-	unsigned long random_factor = 0UL;
-
-	if (current->flags & PF_RANDOMIZE)
-		random_factor = arch_mmap_rnd();
-
-	if (mmap_is_legacy(rlim_stack)) {
-		mm->mmap_base = TASK_UNMAPPED_BASE + random_factor;
-		mm->get_unmapped_area = arch_get_unmapped_area;
-	} else {
-		mm->mmap_base = mmap_base(random_factor, rlim_stack);
-		mm->get_unmapped_area = arch_get_unmapped_area_topdown;
-	}
-}
-
 /*
  * You really shouldn't be using read() or write() on /dev/mem.  This
  * might go away in the future.
diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c
index e46a6a4..48c2888 100644
--- a/arch/arm/mm/mmu.c
+++ b/arch/arm/mm/mmu.c
@@ -1,11 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  *  linux/arch/arm/mm/mmu.c
  *
  *  Copyright (C) 1995-2005 Russell King
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
  */
 #include <linux/module.h>
 #include <linux/kernel.h>
@@ -719,23 +716,22 @@
 
 #define vectors_base()	(vectors_high() ? 0xffff0000 : 0)
 
-static void __init *early_alloc_aligned(unsigned long sz, unsigned long align)
-{
-	void *ptr = __va(memblock_alloc(sz, align));
-	memset(ptr, 0, sz);
-	return ptr;
-}
-
 static void __init *early_alloc(unsigned long sz)
 {
-	return early_alloc_aligned(sz, sz);
+	void *ptr = memblock_alloc(sz, sz);
+
+	if (!ptr)
+		panic("%s: Failed to allocate %lu bytes align=0x%lx\n",
+		      __func__, sz, sz);
+
+	return ptr;
 }
 
 static void *__init late_alloc(unsigned long sz)
 {
-	void *ptr = (void *)__get_free_pages(PGALLOC_GFP, get_order(sz));
+	void *ptr = (void *)__get_free_pages(GFP_PGTABLE_KERNEL, get_order(sz));
 
-	if (!ptr || !pgtable_page_ctor(virt_to_page(ptr)))
+	if (!ptr || !pgtable_pte_page_ctor(virt_to_page(ptr)))
 		BUG();
 	return ptr;
 }
@@ -1000,7 +996,10 @@
 	if (!nr)
 		return;
 
-	svm = early_alloc_aligned(sizeof(*svm) * nr, __alignof__(*svm));
+	svm = memblock_alloc(sizeof(*svm) * nr, __alignof__(*svm));
+	if (!svm)
+		panic("%s: Failed to allocate %zu bytes align=0x%zx\n",
+		      __func__, sizeof(*svm) * nr, __alignof__(*svm));
 
 	for (md = io_desc; nr; md++, nr--) {
 		create_mapping(md);
@@ -1022,7 +1021,10 @@
 	struct vm_struct *vm;
 	struct static_vm *svm;
 
-	svm = early_alloc_aligned(sizeof(*svm), __alignof__(*svm));
+	svm = memblock_alloc(sizeof(*svm), __alignof__(*svm));
+	if (!svm)
+		panic("%s: Failed to allocate %zu bytes align=0x%zx\n",
+		      __func__, sizeof(*svm), __alignof__(*svm));
 
 	vm = &svm->vm;
 	vm->addr = (void *)addr;
@@ -1175,10 +1177,29 @@
 	 */
 	vmalloc_limit = (u64)(uintptr_t)vmalloc_min - PAGE_OFFSET + PHYS_OFFSET;
 
+	/*
+	 * The first usable region must be PMD aligned. Mark its start
+	 * as MEMBLOCK_NOMAP if it isn't
+	 */
+	for_each_memblock(memory, reg) {
+		if (!memblock_is_nomap(reg)) {
+			if (!IS_ALIGNED(reg->base, PMD_SIZE)) {
+				phys_addr_t len;
+
+				len = round_up(reg->base, PMD_SIZE) - reg->base;
+				memblock_mark_nomap(reg->base, len);
+			}
+			break;
+		}
+	}
+
 	for_each_memblock(memory, reg) {
 		phys_addr_t block_start = reg->base;
 		phys_addr_t block_end = reg->base + reg->size;
 
+		if (memblock_is_nomap(reg))
+			continue;
+
 		if (reg->base < vmalloc_limit) {
 			if (block_end > lowmem_limit)
 				/*
diff --git a/arch/arm/mm/nommu.c b/arch/arm/mm/nommu.c
index 7d67c70..24ecf8d 100644
--- a/arch/arm/mm/nommu.c
+++ b/arch/arm/mm/nommu.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  *  linux/arch/arm/mm/nommu.c
  *
diff --git a/arch/arm/mm/pageattr.c b/arch/arm/mm/pageattr.c
index 1403cb4..d546efa 100644
--- a/arch/arm/mm/pageattr.c
+++ b/arch/arm/mm/pageattr.c
@@ -1,14 +1,6 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Copyright (c) 2014, The Linux Foundation. All rights reserved.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 and
- * only version 2 as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
  */
 #include <linux/mm.h>
 #include <linux/module.h>
@@ -22,8 +14,7 @@
 	pgprot_t clear_mask;
 };
 
-static int change_page_range(pte_t *ptep, pgtable_t token, unsigned long addr,
-			void *data)
+static int change_page_range(pte_t *ptep, unsigned long addr, void *data)
 {
 	struct page_change_data *cdata = data;
 	pte_t pte = *ptep;
diff --git a/arch/arm/mm/pgd.c b/arch/arm/mm/pgd.c
index a1606d9..478bd2c 100644
--- a/arch/arm/mm/pgd.c
+++ b/arch/arm/mm/pgd.c
@@ -1,11 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  *  linux/arch/arm/mm/pgd.c
  *
  *  Copyright (C) 1998-2005 Russell King
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
  */
 #include <linux/mm.h>
 #include <linux/gfp.h>
diff --git a/arch/arm/mm/pmsa-v8.c b/arch/arm/mm/pmsa-v8.c
index 617a83d..0d7d5fb 100644
--- a/arch/arm/mm/pmsa-v8.c
+++ b/arch/arm/mm/pmsa-v8.c
@@ -165,7 +165,7 @@
 		return -EINVAL;
 
 	bar = start;
-	lar = (end - 1) & ~(PMSAv8_MINALIGN - 1);;
+	lar = (end - 1) & ~(PMSAv8_MINALIGN - 1);
 
 	bar |= PMSAv8_AP_PL1RW_PL0RW | PMSAv8_RGN_SHARED;
 	lar |= PMSAv8_LAR_IDX(PMSAv8_RGN_NORMAL) | PMSAv8_LAR_EN;
@@ -181,7 +181,7 @@
 		return -EINVAL;
 
 	bar = start;
-	lar = (end - 1) & ~(PMSAv8_MINALIGN - 1);;
+	lar = (end - 1) & ~(PMSAv8_MINALIGN - 1);
 
 	bar |= PMSAv8_AP_PL1RW_PL0RW | PMSAv8_RGN_SHARED | PMSAv8_BAR_XN;
 	lar |= PMSAv8_LAR_IDX(PMSAv8_RGN_DEVICE_nGnRnE) | PMSAv8_LAR_EN;
diff --git a/arch/arm/mm/proc-arm1020.S b/arch/arm/mm/proc-arm1020.S
index 774ef13..4fa5371 100644
--- a/arch/arm/mm/proc-arm1020.S
+++ b/arch/arm/mm/proc-arm1020.S
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  *  linux/arch/arm/mm/proc-arm1020.S: MMU functions for ARM1020
  *
@@ -5,21 +6,6 @@
  *  Copyright (C) 2000 Deep Blue Solutions Ltd.
  *  hacked for non-paged-MM by Hyok S. Choi, 2003.
  *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
- *
- *
  * These are the low level assembler for performing cache and TLB
  * functions on the arm1020.
  */
diff --git a/arch/arm/mm/proc-arm1020e.S b/arch/arm/mm/proc-arm1020e.S
index ae3c27b..5d8a833 100644
--- a/arch/arm/mm/proc-arm1020e.S
+++ b/arch/arm/mm/proc-arm1020e.S
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  *  linux/arch/arm/mm/proc-arm1020e.S: MMU functions for ARM1020
  *
@@ -5,21 +6,6 @@
  *  Copyright (C) 2000 Deep Blue Solutions Ltd.
  *  hacked for non-paged-MM by Hyok S. Choi, 2003.
  *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
- *
- *
  * These are the low level assembler for performing cache and TLB
  * functions on the arm1020e.
  */
diff --git a/arch/arm/mm/proc-arm1022.S b/arch/arm/mm/proc-arm1022.S
index dbb2413..b3dd95c 100644
--- a/arch/arm/mm/proc-arm1022.S
+++ b/arch/arm/mm/proc-arm1022.S
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  *  linux/arch/arm/mm/proc-arm1022.S: MMU functions for ARM1022E
  *
@@ -5,12 +6,6 @@
  *  Copyright (C) 2000 Deep Blue Solutions Ltd.
  *  hacked for non-paged-MM by Hyok S. Choi, 2003.
  *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- *
  * These are the low level assembler for performing cache and TLB
  * functions on the ARM1022E.
  */
diff --git a/arch/arm/mm/proc-arm1026.S b/arch/arm/mm/proc-arm1026.S
index 0b37b2c..ac5afde 100644
--- a/arch/arm/mm/proc-arm1026.S
+++ b/arch/arm/mm/proc-arm1026.S
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  *  linux/arch/arm/mm/proc-arm1026.S: MMU functions for ARM1026EJ-S
  *
@@ -5,12 +6,6 @@
  *  Copyright (C) 2000 Deep Blue Solutions Ltd.
  *  hacked for non-paged-MM by Hyok S. Choi, 2003.
  *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- *
  * These are the low level assembler for performing cache and TLB
  * functions on the ARM1026EJ-S.
  */
diff --git a/arch/arm/mm/proc-arm720.S b/arch/arm/mm/proc-arm720.S
index 3651cd7..c99d243 100644
--- a/arch/arm/mm/proc-arm720.S
+++ b/arch/arm/mm/proc-arm720.S
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  *  linux/arch/arm/mm/proc-arm720.S: MMU functions for ARM720
  *
@@ -6,21 +7,6 @@
  *  Copyright (C) 2000 ARM Limited, Deep Blue Solutions Ltd.
  *  hacked for non-paged-MM by Hyok S. Choi, 2004.
  *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
- *
- *
  * These are the low level assembler for performing cache and TLB
  * functions on the ARM720T.  The ARM720T has a writethrough IDC
  * cache, so we don't need to clean it.
diff --git a/arch/arm/mm/proc-arm740.S b/arch/arm/mm/proc-arm740.S
index 024fb77..1b4a383 100644
--- a/arch/arm/mm/proc-arm740.S
+++ b/arch/arm/mm/proc-arm740.S
@@ -1,12 +1,8 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
  *  linux/arch/arm/mm/arm740.S: utility functions for ARM740
  *
  *  Copyright (C) 2004-2006 Hyok S. Choi (hyok.choi@samsung.com)
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
  */
 #include <linux/linkage.h>
 #include <linux/init.h>
diff --git a/arch/arm/mm/proc-arm7tdmi.S b/arch/arm/mm/proc-arm7tdmi.S
index 25472d9..17a4687 100644
--- a/arch/arm/mm/proc-arm7tdmi.S
+++ b/arch/arm/mm/proc-arm7tdmi.S
@@ -1,12 +1,8 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
  *  linux/arch/arm/mm/proc-arm7tdmi.S: utility functions for ARM7TDMI
  *
  *  Copyright (C) 2003-2006 Hyok S. Choi <hyok.choi@samsung.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
  */
 #include <linux/linkage.h>
 #include <linux/init.h>
diff --git a/arch/arm/mm/proc-arm920.S b/arch/arm/mm/proc-arm920.S
index 7a14bd4..298c76b 100644
--- a/arch/arm/mm/proc-arm920.S
+++ b/arch/arm/mm/proc-arm920.S
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  *  linux/arch/arm/mm/proc-arm920.S: MMU functions for ARM920
  *
@@ -5,21 +6,6 @@
  *  Copyright (C) 2000 Deep Blue Solutions Ltd.
  *  hacked for non-paged-MM by Hyok S. Choi, 2003.
  *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
- *
- *
  * These are the low level assembler for performing cache and TLB
  * functions on the arm920.
  *
diff --git a/arch/arm/mm/proc-arm922.S b/arch/arm/mm/proc-arm922.S
index edccfcd..824be3a 100644
--- a/arch/arm/mm/proc-arm922.S
+++ b/arch/arm/mm/proc-arm922.S
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  *  linux/arch/arm/mm/proc-arm922.S: MMU functions for ARM922
  *
@@ -6,21 +7,6 @@
  *  Copyright (C) 2001 Altera Corporation
  *  hacked for non-paged-MM by Hyok S. Choi, 2003.
  *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
- *
- *
  * These are the low level assembler for performing cache and TLB
  * functions on the arm922.
  *
diff --git a/arch/arm/mm/proc-arm925.S b/arch/arm/mm/proc-arm925.S
index 32a47cc..d40cff8 100644
--- a/arch/arm/mm/proc-arm925.S
+++ b/arch/arm/mm/proc-arm925.S
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  *  linux/arch/arm/mm/arm925.S: MMU functions for ARM925
  *
@@ -11,21 +12,6 @@
  *
  *  hacked for non-paged-MM by Hyok S. Choi, 2004.
  *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
- *
- *
  * These are the low level assembler for performing cache and TLB
  * functions on the arm925.
  *
diff --git a/arch/arm/mm/proc-arm926.S b/arch/arm/mm/proc-arm926.S
index fb827c6..f3cd08f 100644
--- a/arch/arm/mm/proc-arm926.S
+++ b/arch/arm/mm/proc-arm926.S
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  *  linux/arch/arm/mm/proc-arm926.S: MMU functions for ARM926EJ-S
  *
@@ -5,21 +6,6 @@
  *  Copyright (C) 2000 Deep Blue Solutions Ltd.
  *  hacked for non-paged-MM by Hyok S. Choi, 2003.
  *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
- *
- *
  * These are the low level assembler for performing cache and TLB
  * functions on the arm926.
  *
diff --git a/arch/arm/mm/proc-arm940.S b/arch/arm/mm/proc-arm940.S
index ee5b66f..1c26d99 100644
--- a/arch/arm/mm/proc-arm940.S
+++ b/arch/arm/mm/proc-arm940.S
@@ -1,12 +1,8 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
  *  linux/arch/arm/mm/arm940.S: utility functions for ARM940T
  *
  *  Copyright (C) 2004-2006 Hyok S. Choi (hyok.choi@samsung.com)
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
  */
 #include <linux/linkage.h>
 #include <linux/init.h>
diff --git a/arch/arm/mm/proc-arm946.S b/arch/arm/mm/proc-arm946.S
index 7361837..2dc1c75 100644
--- a/arch/arm/mm/proc-arm946.S
+++ b/arch/arm/mm/proc-arm946.S
@@ -1,14 +1,10 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
  *  linux/arch/arm/mm/arm946.S: utility functions for ARM946E-S
  *
  *  Copyright (C) 2004-2006 Hyok S. Choi (hyok.choi@samsung.com)
  *
  *  (Many of cache codes are from proc-arm926.S)
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
  */
 #include <linux/linkage.h>
 #include <linux/init.h>
diff --git a/arch/arm/mm/proc-arm9tdmi.S b/arch/arm/mm/proc-arm9tdmi.S
index 7fac8c6..913c06e 100644
--- a/arch/arm/mm/proc-arm9tdmi.S
+++ b/arch/arm/mm/proc-arm9tdmi.S
@@ -1,12 +1,8 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
  *  linux/arch/arm/mm/proc-arm9tdmi.S: utility functions for ARM9TDMI
  *
  *  Copyright (C) 2003-2006 Hyok S. Choi <hyok.choi@samsung.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
  */
 #include <linux/linkage.h>
 #include <linux/init.h>
diff --git a/arch/arm/mm/proc-fa526.S b/arch/arm/mm/proc-fa526.S
index 4001b73..8120b6f 100644
--- a/arch/arm/mm/proc-fa526.S
+++ b/arch/arm/mm/proc-fa526.S
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  *  linux/arch/arm/mm/proc-fa526.S: MMU functions for FA526
  *
@@ -5,12 +6,6 @@
  *  Copyright (C) 2005 Faraday Corp.
  *  Copyright (C) 2008-2009 Paulius Zaleckas <paulius.zaleckas@teltonika.lt>
  *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- *
  * These are the low level assembler for performing cache and TLB
  * functions on the fa526.
  */
diff --git a/arch/arm/mm/proc-feroceon.S b/arch/arm/mm/proc-feroceon.S
index 92e08bf..bb6dc34 100644
--- a/arch/arm/mm/proc-feroceon.S
+++ b/arch/arm/mm/proc-feroceon.S
@@ -1,22 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  *  linux/arch/arm/mm/proc-feroceon.S: MMU functions for Feroceon
  *
  *  Heavily based on proc-arm926.S
  *  Maintainer: Assaf Hoffman <hoffman@marvell.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
  */
 
 #include <linux/linkage.h>
diff --git a/arch/arm/mm/proc-macros.S b/arch/arm/mm/proc-macros.S
index 81d0efb..5461d58 100644
--- a/arch/arm/mm/proc-macros.S
+++ b/arch/arm/mm/proc-macros.S
@@ -274,6 +274,13 @@
 	.endm
 
 .macro define_processor_functions name:req, dabort:req, pabort:req, nommu=0, suspend=0, bugs=0
+/*
+ * If we are building for big.Little with branch predictor hardening,
+ * we need the processor function tables to remain available after boot.
+ */
+#if defined(CONFIG_BIG_LITTLE) && defined(CONFIG_HARDEN_BRANCH_PREDICTOR)
+	.section ".rodata"
+#endif
 	.type	\name\()_processor_functions, #object
 	.align 2
 ENTRY(\name\()_processor_functions)
@@ -309,6 +316,9 @@
 	.endif
 
 	.size	\name\()_processor_functions, . - \name\()_processor_functions
+#if defined(CONFIG_BIG_LITTLE) && defined(CONFIG_HARDEN_BRANCH_PREDICTOR)
+	.previous
+#endif
 .endm
 
 .macro define_cache_functions name:req
diff --git a/arch/arm/mm/proc-mohawk.S b/arch/arm/mm/proc-mohawk.S
index 6f07d2e..f083085 100644
--- a/arch/arm/mm/proc-mohawk.S
+++ b/arch/arm/mm/proc-mohawk.S
@@ -1,23 +1,10 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
 /*
  *  linux/arch/arm/mm/proc-mohawk.S: MMU functions for Marvell PJ1 core
  *
  *  PJ1 (codename Mohawk) is a hybrid of the xscale3 and Marvell's own core.
  *
  *  Heavily based on proc-arm926.S and proc-xsc3.S
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
  */
 
 #include <linux/linkage.h>
diff --git a/arch/arm/mm/proc-sa110.S b/arch/arm/mm/proc-sa110.S
index ee2ce49..d5bc5d7 100644
--- a/arch/arm/mm/proc-sa110.S
+++ b/arch/arm/mm/proc-sa110.S
@@ -1,13 +1,10 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
  *  linux/arch/arm/mm/proc-sa110.S
  *
  *  Copyright (C) 1997-2002 Russell King
  *  hacked for non-paged-MM by Hyok S. Choi, 2003.
  *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
  *  MMU functions for SA110
  *
  *  These are the low level assembler for performing cache and TLB
diff --git a/arch/arm/mm/proc-sa1100.S b/arch/arm/mm/proc-sa1100.S
index 222d583..be7b611 100644
--- a/arch/arm/mm/proc-sa1100.S
+++ b/arch/arm/mm/proc-sa1100.S
@@ -1,13 +1,10 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
  *  linux/arch/arm/mm/proc-sa1100.S
  *
  *  Copyright (C) 1997-2002 Russell King
  *  hacked for non-paged-MM by Hyok S. Choi, 2003.
  *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
  *  MMU functions for SA110
  *
  *  These are the low level assembler for performing cache and TLB
diff --git a/arch/arm/mm/proc-syms.c b/arch/arm/mm/proc-syms.c
index 054b491..e212495 100644
--- a/arch/arm/mm/proc-syms.c
+++ b/arch/arm/mm/proc-syms.c
@@ -1,11 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  *  linux/arch/arm/mm/proc-syms.c
  *
  *  Copyright (C) 2000-2002 Russell King
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
  */
 #include <linux/module.h>
 #include <linux/mm.h>
diff --git a/arch/arm/mm/proc-v6.S b/arch/arm/mm/proc-v6.S
index 06d890a..c1c85eb 100644
--- a/arch/arm/mm/proc-v6.S
+++ b/arch/arm/mm/proc-v6.S
@@ -1,13 +1,10 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
  *  linux/arch/arm/mm/proc-v6.S
  *
  *  Copyright (C) 2001 Deep Blue Solutions Ltd.
  *  Modified by Catalin Marinas for noMMU support
  *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
  *  This is the "shell" of the ARMv6 processor support.
  */
 #include <linux/init.h>
diff --git a/arch/arm/mm/proc-v7-2level.S b/arch/arm/mm/proc-v7-2level.S
index f8d45ad..5db029c 100644
--- a/arch/arm/mm/proc-v7-2level.S
+++ b/arch/arm/mm/proc-v7-2level.S
@@ -1,11 +1,8 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
  * arch/arm/mm/proc-v7-2level.S
  *
  * Copyright (C) 2001 Deep Blue Solutions Ltd.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
  */
 
 #define TTB_S		(1 << 1)
diff --git a/arch/arm/mm/proc-v7-3level.S b/arch/arm/mm/proc-v7-3level.S
index 7d16bbc..1319844 100644
--- a/arch/arm/mm/proc-v7-3level.S
+++ b/arch/arm/mm/proc-v7-3level.S
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
  * arch/arm/mm/proc-v7-3level.S
  *
@@ -5,19 +6,6 @@
  * Copyright (C) 2011 ARM Ltd.
  * Author: Catalin Marinas <catalin.marinas@arm.com>
  *   based on arch/arm/mm/proc-v7-2level.S
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
  */
 #include <asm/assembler.h>
 
diff --git a/arch/arm/mm/proc-v7-bugs.c b/arch/arm/mm/proc-v7-bugs.c
index 5544b82..9a07916 100644
--- a/arch/arm/mm/proc-v7-bugs.c
+++ b/arch/arm/mm/proc-v7-bugs.c
@@ -52,8 +52,6 @@
 	case ARM_CPU_PART_CORTEX_A17:
 	case ARM_CPU_PART_CORTEX_A73:
 	case ARM_CPU_PART_CORTEX_A75:
-		if (processor.switch_mm != cpu_v7_bpiall_switch_mm)
-			goto bl_error;
 		per_cpu(harden_branch_predictor_fn, cpu) =
 			harden_branch_predictor_bpiall;
 		spectre_v2_method = "BPIALL";
@@ -61,8 +59,6 @@
 
 	case ARM_CPU_PART_CORTEX_A15:
 	case ARM_CPU_PART_BRAHMA_B15:
-		if (processor.switch_mm != cpu_v7_iciallu_switch_mm)
-			goto bl_error;
 		per_cpu(harden_branch_predictor_fn, cpu) =
 			harden_branch_predictor_iciallu;
 		spectre_v2_method = "ICIALLU";
@@ -88,11 +84,9 @@
 					  ARM_SMCCC_ARCH_WORKAROUND_1, &res);
 			if ((int)res.a0 != 0)
 				break;
-			if (processor.switch_mm != cpu_v7_hvc_switch_mm && cpu)
-				goto bl_error;
 			per_cpu(harden_branch_predictor_fn, cpu) =
 				call_hvc_arch_workaround_1;
-			processor.switch_mm = cpu_v7_hvc_switch_mm;
+			cpu_do_switch_mm = cpu_v7_hvc_switch_mm;
 			spectre_v2_method = "hypervisor";
 			break;
 
@@ -101,11 +95,9 @@
 					  ARM_SMCCC_ARCH_WORKAROUND_1, &res);
 			if ((int)res.a0 != 0)
 				break;
-			if (processor.switch_mm != cpu_v7_smc_switch_mm && cpu)
-				goto bl_error;
 			per_cpu(harden_branch_predictor_fn, cpu) =
 				call_smc_arch_workaround_1;
-			processor.switch_mm = cpu_v7_smc_switch_mm;
+			cpu_do_switch_mm = cpu_v7_smc_switch_mm;
 			spectre_v2_method = "firmware";
 			break;
 
@@ -119,11 +111,6 @@
 	if (spectre_v2_method)
 		pr_info("CPU%u: Spectre v2: using %s workaround\n",
 			smp_processor_id(), spectre_v2_method);
-	return;
-
-bl_error:
-	pr_err("CPU%u: Spectre v2: incorrect context switching function, system vulnerable\n",
-		cpu);
 }
 #else
 static void cpu_v7_spectre_init(void)
diff --git a/arch/arm/mm/proc-v7.S b/arch/arm/mm/proc-v7.S
index 339eb17..c4e8006 100644
--- a/arch/arm/mm/proc-v7.S
+++ b/arch/arm/mm/proc-v7.S
@@ -1,12 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
  *  linux/arch/arm/mm/proc-v7.S
  *
  *  Copyright (C) 2001 Deep Blue Solutions Ltd.
  *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
  *  This is the "shell" of the ARMv7 processor support.
  */
 #include <linux/arm-smccc.h>
@@ -392,6 +389,11 @@
 	orr	r10, r10, #1 << 24		@ set bit #24
 	mcr	p15, 0, r10, c15, c0, 1		@ write diagnostic register
 #endif
+#ifdef CONFIG_ARM_ERRATA_857271
+	mrc	p15, 0, r10, c15, c0, 1		@ read diagnostic register
+	orr	r10, r10, #3 << 10		@ set bits #10 and #11
+	mcr	p15, 0, r10, c15, c0, 1		@ write diagnostic register
+#endif
 	b	__errata_finish
 
 __ca17_errata:
@@ -407,6 +409,11 @@
 	orrle	r10, r10, #1 << 12		@ set bit #12
 	mcrle	p15, 0, r10, c15, c0, 1		@ write diagnostic register
 #endif
+#ifdef CONFIG_ARM_ERRATA_857272
+	mrc	p15, 0, r10, c15, c0, 1		@ read diagnostic register
+	orr	r10, r10, #3 << 10		@ set bits #10 and #11
+	mcr	p15, 0, r10, c15, c0, 1		@ write diagnostic register
+#endif
 	b	__errata_finish
 
 __v7_pj4b_setup:
diff --git a/arch/arm/mm/proc-v7m.S b/arch/arm/mm/proc-v7m.S
index 47a5acc..1a49d50 100644
--- a/arch/arm/mm/proc-v7m.S
+++ b/arch/arm/mm/proc-v7m.S
@@ -1,13 +1,10 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
  *  linux/arch/arm/mm/proc-v7m.S
  *
  *  Copyright (C) 2008 ARM Ltd.
  *  Copyright (C) 2001 Deep Blue Solutions Ltd.
  *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
  *  This is the "shell" of the ARMv7-M processor support.
  */
 #include <linux/linkage.h>
@@ -135,10 +132,11 @@
 	dsb
 	mov	r6, lr			@ save LR
 	ldr	sp, =init_thread_union + THREAD_START_SP
-	stmia	sp, {r0-r3, r12}
 	cpsie	i
 	svc	#0
 1:	cpsid	i
+	/* Calculate exc_ret */
+	orr	r10, lr, #EXC_RET_THREADMODE_PROCESSSTACK
 	ldmia	sp, {r0-r3, r12}
 	str	r5, [r12, #11 * 4]	@ restore the original SVC vector entry
 	mov	lr, r6			@ restore LR
@@ -149,10 +147,10 @@
 
 	@ Configure caches (if implemented)
 	teq     r8, #0
-	stmneia	sp, {r0-r6, lr}		@ v7m_invalidate_l1 touches r0-r6
+	stmiane	sp, {r0-r6, lr}		@ v7m_invalidate_l1 touches r0-r6
 	blne	v7m_invalidate_l1
 	teq     r8, #0			@ re-evalutae condition
-	ldmneia	sp, {r0-r6, lr}
+	ldmiane	sp, {r0-r6, lr}
 
 	@ Configure the System Control Register to ensure 8-byte stack alignment
 	@ Note the STKALIGN bit is either RW or RAO.
diff --git a/arch/arm/mm/proc-xsc3.S b/arch/arm/mm/proc-xsc3.S
index 293dcc2..1ac0fbb 100644
--- a/arch/arm/mm/proc-xsc3.S
+++ b/arch/arm/mm/proc-xsc3.S
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
  * linux/arch/arm/mm/proc-xsc3.S
  *
@@ -7,10 +8,6 @@
  * Copyright 2004 (C) Intel Corp.
  * Copyright 2005 (C) MontaVista Software, Inc.
  *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
  * MMU functions for the Intel XScale3 Core (XSC3).  The XSC3 core is
  * an extension to Intel's original XScale core that adds the following
  * features:
diff --git a/arch/arm/mm/proc-xscale.S b/arch/arm/mm/proc-xscale.S
index 3d75b79..bdb2b77 100644
--- a/arch/arm/mm/proc-xscale.S
+++ b/arch/arm/mm/proc-xscale.S
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
  *  linux/arch/arm/mm/proc-xscale.S
  *
@@ -5,10 +6,6 @@
  *  Created:	November 2000
  *  Copyright:	(C) 2000, 2001 MontaVista Software Inc.
  *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
  * MMU functions for the Intel XScale CPUs
  *
  * 2001 Aug 21:
diff --git a/arch/arm/mm/ptdump_debugfs.c b/arch/arm/mm/ptdump_debugfs.c
index be8d87b..598b636 100644
--- a/arch/arm/mm/ptdump_debugfs.c
+++ b/arch/arm/mm/ptdump_debugfs.c
@@ -24,11 +24,7 @@
 	.release	= single_release,
 };
 
-int ptdump_debugfs_register(struct ptdump_info *info, const char *name)
+void ptdump_debugfs_register(struct ptdump_info *info, const char *name)
 {
-	struct dentry *pe;
-
-	pe = debugfs_create_file(name, 0400, NULL, info, &ptdump_fops);
-	return pe ? 0 : -ENOMEM;
-
+	debugfs_create_file(name, 0400, NULL, info, &ptdump_fops);
 }
diff --git a/arch/arm/mm/pv-fixup-asm.S b/arch/arm/mm/pv-fixup-asm.S
index 1867f3e..7697789 100644
--- a/arch/arm/mm/pv-fixup-asm.S
+++ b/arch/arm/mm/pv-fixup-asm.S
@@ -1,10 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
  *  Copyright (C) 2015 Russell King
  *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
  * This assembly is required to safely remap the physical address space
  * for Keystone 2
  */
@@ -33,10 +30,10 @@
 	add	r7, r2, #0x1000
 	add	r6, r7, r6, lsr #SECTION_SHIFT - L2_ORDER
 	add	r7, r7, #PAGE_OFFSET >> (SECTION_SHIFT - L2_ORDER)
-1:	ldrd	r4, [r7]
+1:	ldrd	r4, r5, [r7]
 	adds	r4, r4, r0
 	adc	r5, r5, r1
-	strd	r4, [r7], #1 << L2_ORDER
+	strd	r4, r5, [r7], #1 << L2_ORDER
 	cmp	r7, r6
 	bls	1b
 
@@ -44,22 +41,22 @@
 	add	r7, r2, #0x1000
 	add	r7, r7, r3, lsr #SECTION_SHIFT - L2_ORDER
 	bic	r7, r7, #(1 << L2_ORDER) - 1
-	ldrd	r4, [r7]
+	ldrd	r4, r5, [r7]
 	adds	r4, r4, r0
 	adc	r5, r5, r1
-	strd	r4, [r7], #1 << L2_ORDER
-	ldrd	r4, [r7]
+	strd	r4, r5, [r7], #1 << L2_ORDER
+	ldrd	r4, r5, [r7]
 	adds	r4, r4, r0
 	adc	r5, r5, r1
-	strd	r4, [r7]
+	strd	r4, r5, [r7]
 
 	/* Update level 1 entries */
 	mov	r6, #4
 	mov	r7, r2
-2:	ldrd	r4, [r7]
+2:	ldrd	r4, r5, [r7]
 	adds	r4, r4, r0
 	adc	r5, r5, r1
-	strd	r4, [r7], #1 << L1_ORDER
+	strd	r4, r5, [r7], #1 << L1_ORDER
 	subs	r6, r6, #1
 	bne	2b
 
diff --git a/arch/arm/mm/tcm.h b/arch/arm/mm/tcm.h
index 2410192..6b80a76 100644
--- a/arch/arm/mm/tcm.h
+++ b/arch/arm/mm/tcm.h
@@ -1,6 +1,6 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
  * Copyright (C) 2008-2009 ST-Ericsson AB
- * License terms: GNU General Public License (GPL) version 2
  * TCM memory handling for ARM systems
  *
  * Author: Linus Walleij <linus.walleij@stericsson.com>
diff --git a/arch/arm/mm/tlb-fa.S b/arch/arm/mm/tlb-fa.S
index d2d9ecb..def6161 100644
--- a/arch/arm/mm/tlb-fa.S
+++ b/arch/arm/mm/tlb-fa.S
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
  *  linux/arch/arm/mm/tlb-fa.S
  *
@@ -7,10 +8,6 @@
  * Based on tlb-v4wbi.S:
  *  Copyright (C) 1997-2002 Russell King
  *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
  *  ARM architecture version 4, Faraday variation.
  *  This assume an unified TLBs, with a write buffer, and branch target buffer (BTB)
  *
diff --git a/arch/arm/mm/tlb-v4.S b/arch/arm/mm/tlb-v4.S
index a2b5dca..b962b4e 100644
--- a/arch/arm/mm/tlb-v4.S
+++ b/arch/arm/mm/tlb-v4.S
@@ -1,12 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
  *  linux/arch/arm/mm/tlbv4.S
  *
  *  Copyright (C) 1997-2002 Russell King
  *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
  *  ARM architecture version 4 TLB handling functions.
  *  These assume a split I/D TLBs, and no write buffer.
  *
diff --git a/arch/arm/mm/tlb-v4wb.S b/arch/arm/mm/tlb-v4wb.S
index 5a093b4..9348bba 100644
--- a/arch/arm/mm/tlb-v4wb.S
+++ b/arch/arm/mm/tlb-v4wb.S
@@ -1,12 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
  *  linux/arch/arm/mm/tlbv4wb.S
  *
  *  Copyright (C) 1997-2002 Russell King
  *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
  *  ARM architecture version 4 TLB handling functions.
  *  These assume a split I/D TLBs w/o I TLB entry, with a write buffer.
  *
diff --git a/arch/arm/mm/tlb-v4wbi.S b/arch/arm/mm/tlb-v4wbi.S
index 0588615..d4f9040 100644
--- a/arch/arm/mm/tlb-v4wbi.S
+++ b/arch/arm/mm/tlb-v4wbi.S
@@ -1,12 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
  *  linux/arch/arm/mm/tlbv4wbi.S
  *
  *  Copyright (C) 1997-2002 Russell King
  *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
  *  ARM architecture version 4 and version 5 TLB handling functions.
  *  These assume a split I/D TLBs, with a write buffer.
  *
diff --git a/arch/arm/mm/tlb-v6.S b/arch/arm/mm/tlb-v6.S
index 6f689be..5335b96 100644
--- a/arch/arm/mm/tlb-v6.S
+++ b/arch/arm/mm/tlb-v6.S
@@ -1,12 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
  *  linux/arch/arm/mm/tlb-v6.S
  *
  *  Copyright (C) 1997-2002 Russell King
  *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
  *  ARM architecture version 6 TLB handling functions.
  *  These assume a split I/D TLB.
  */
diff --git a/arch/arm/mm/tlb-v7.S b/arch/arm/mm/tlb-v7.S
index e5101a3..1bb28d7 100644
--- a/arch/arm/mm/tlb-v7.S
+++ b/arch/arm/mm/tlb-v7.S
@@ -1,13 +1,10 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
  *  linux/arch/arm/mm/tlb-v7.S
  *
  *  Copyright (C) 1997-2002 Russell King
  *  Modified for ARMv7 by Catalin Marinas
  *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
  *  ARM architecture version 6 TLB handling functions.
  *  These assume a split I/D TLB.
  */