Merge tag 'for-linus' of git://git.armlinux.org.uk/~rmk/linux-arm

Pull ARM updates from Russell King:

 - Generalise byte swapping assembly

 - Update debug addresses for STI

 - Validate start of physical memory with DTB

 - Do not clear SCTLR.nTLSMD in decompressor

 - amba/locomo/sa1111 devices remove method return type is void

 - address markers for KASAN in page table dump

* tag 'for-linus' of git://git.armlinux.org.uk/~rmk/linux-arm:
  ARM: 9065/1: OABI compat: fix build when EPOLL is not enabled
  ARM: 9055/1: mailbox: arm_mhuv2: make remove callback return void
  amba: Make use of bus_type functions
  amba: Make the remove callback return void
  vfio: platform: simplify device removal
  amba: reorder functions
  amba: Fix resource leak for drivers without .remove
  ARM: 9054/1: arch/arm/mm/mmu.c: Remove duplicate header
  ARM: 9053/1: arm/mm/ptdump:Add address markers for KASAN regions
  ARM: 9051/1: vdso: remove unneded extra-y addition
  ARM: 9050/1: Kconfig: Select ARCH_HAVE_NMI_SAFE_CMPXCHG where possible
  ARM: 9049/1: locomo: make locomo bus's remove callback return void
  ARM: 9048/1: sa1111: make sa1111 bus's remove callback return void
  ARM: 9047/1: smp: remove unused variable
  ARM: 9046/1: decompressor: Do not clear SCTLR.nTLSMD for ARMv7+ cores
  ARM: 9045/1: uncompress: Validate start of physical memory against passed DTB
  ARM: 9042/1: debug: no uncompress debugging while semihosting
  ARM: 9041/1: sti LL_UART: add STiH418 SBC UART0 support
  ARM: 9040/1: use DEBUG_UART_PHYS and DEBUG_UART_VIRT for sti LL_UART
  ARM: 9039/1: assembler: generalize byte swapping macro into rev_l

3 files changed, 171 insertions, 10 deletions

diff --git a/arch/arm/boot/compressed/Makefile b/arch/arm/boot/compressed/Makefile
index fb521efcc6c2..fd94e27ba4fa 100644
--- a/arch/arm/boot/compressed/Makefile
+++ b/arch/arm/boot/compressed/Makefile
@@ -87,10 +87,13 @@ libfdt_objs := fdt_rw.o fdt_ro.o fdt_wip.o fdt.o
 ifeq ($(CONFIG_ARM_ATAG_DTB_COMPAT),y)
 OBJS	+= $(libfdt_objs) atags_to_fdt.o
 endif
+ifeq ($(CONFIG_USE_OF),y)
+OBJS	+= $(libfdt_objs) fdt_check_mem_start.o
+endif
 
 # -fstack-protector-strong triggers protection checks in this code,
 # but it is being used too early to link to meaningful stack_chk logic.
-$(foreach o, $(libfdt_objs) atags_to_fdt.o, \
+$(foreach o, $(libfdt_objs) atags_to_fdt.o fdt_check_mem_start.o, \
 	$(eval CFLAGS_$(o) := -I $(srctree)/scripts/dtc/libfdt -fno-stack-protector))
 
 # These were previously generated C files. When you are building the kernel
diff --git a/arch/arm/boot/compressed/fdt_check_mem_start.c b/arch/arm/boot/compressed/fdt_check_mem_start.c
new file mode 100644
index 000000000000..62450d824c3c
--- /dev/null
+++ b/arch/arm/boot/compressed/fdt_check_mem_start.c
@@ -0,0 +1,131 @@
+// SPDX-License-Identifier: GPL-2.0-only
+
+#include <linux/kernel.h>
+#include <linux/libfdt.h>
+#include <linux/sizes.h>
+
+static const void *get_prop(const void *fdt, const char *node_path,
+			    const char *property, int minlen)
+{
+	const void *prop;
+	int offset, len;
+
+	offset = fdt_path_offset(fdt, node_path);
+	if (offset < 0)
+		return NULL;
+
+	prop = fdt_getprop(fdt, offset, property, &len);
+	if (!prop || len < minlen)
+		return NULL;
+
+	return prop;
+}
+
+static uint32_t get_cells(const void *fdt, const char *name)
+{
+	const fdt32_t *prop = get_prop(fdt, "/", name, sizeof(fdt32_t));
+
+	if (!prop) {
+		/* default */
+		return 1;
+	}
+
+	return fdt32_ld(prop);
+}
+
+static uint64_t get_val(const fdt32_t *cells, uint32_t ncells)
+{
+	uint64_t r;
+
+	r = fdt32_ld(cells);
+	if (ncells > 1)
+		r = (r << 32) | fdt32_ld(cells + 1);
+
+	return r;
+}
+
+/*
+ * Check the start of physical memory
+ *
+ * Traditionally, the start address of physical memory is obtained by masking
+ * the program counter.  However, this does require that this address is a
+ * multiple of 128 MiB, precluding booting Linux on platforms where this
+ * requirement is not fulfilled.
+ * Hence validate the calculated address against the memory information in the
+ * DTB, and, if out-of-range, replace it by the real start address.
+ * To preserve backwards compatibility (systems reserving a block of memory
+ * at the start of physical memory, kdump, ...), the traditional method is
+ * always used if it yields a valid address.
+ *
+ * Return value: start address of physical memory to use
+ */
+uint32_t fdt_check_mem_start(uint32_t mem_start, const void *fdt)
+{
+	uint32_t addr_cells, size_cells, base;
+	uint32_t fdt_mem_start = 0xffffffff;
+	const fdt32_t *reg, *endp;
+	uint64_t size, end;
+	const char *type;
+	int offset, len;
+
+	if (!fdt)
+		return mem_start;
+
+	if (fdt_magic(fdt) != FDT_MAGIC)
+		return mem_start;
+
+	/* There may be multiple cells on LPAE platforms */
+	addr_cells = get_cells(fdt, "#address-cells");
+	size_cells = get_cells(fdt, "#size-cells");
+	if (addr_cells > 2 || size_cells > 2)
+		return mem_start;
+
+	/* Walk all memory nodes and regions */
+	for (offset = fdt_next_node(fdt, -1, NULL); offset >= 0;
+	     offset = fdt_next_node(fdt, offset, NULL)) {
+		type = fdt_getprop(fdt, offset, "device_type", NULL);
+		if (!type || strcmp(type, "memory"))
+			continue;
+
+		reg = fdt_getprop(fdt, offset, "linux,usable-memory", &len);
+		if (!reg)
+			reg = fdt_getprop(fdt, offset, "reg", &len);
+		if (!reg)
+			continue;
+
+		for (endp = reg + (len / sizeof(fdt32_t));
+		     endp - reg >= addr_cells + size_cells;
+		     reg += addr_cells + size_cells) {
+			size = get_val(reg + addr_cells, size_cells);
+			if (!size)
+				continue;
+
+			if (addr_cells > 1 && fdt32_ld(reg)) {
+				/* Outside 32-bit address space, skipping */
+				continue;
+			}
+
+			base = fdt32_ld(reg + addr_cells - 1);
+			end = base + size;
+			if (mem_start >= base && mem_start < end) {
+				/* Calculated address is valid, use it */
+				return mem_start;
+			}
+
+			if (base < fdt_mem_start)
+				fdt_mem_start = base;
+		}
+	}
+
+	if (fdt_mem_start == 0xffffffff) {
+		/* No usable memory found, falling back to default */
+		return mem_start;
+	}
+
+	/*
+	 * The calculated address is not usable.
+	 * Use the lowest usable physical memory address from the DTB instead,
+	 * and make sure this is a multiple of 2 MiB for phys/virt patching.
+	 */
+	return round_up(fdt_mem_start, SZ_2M);
+}
diff --git a/arch/arm/boot/compressed/head.S b/arch/arm/boot/compressed/head.S
index d9cce7238a36..b1cb1972361b 100644
--- a/arch/arm/boot/compressed/head.S
+++ b/arch/arm/boot/compressed/head.S
@@ -174,10 +174,7 @@
 		.macro	be32tocpu, val, tmp
 #ifndef __ARMEB__
 		/* convert to little endian */
-		eor	\tmp, \val, \val, ror #16
-		bic	\tmp, \tmp, #0x00ff0000
-		mov	\val, \val, ror #8
-		eor	\val, \val, \tmp, lsr #8
+		rev_l	\val, \tmp
 #endif
 		.endm
 
@@ -282,10 +279,40 @@ not_angel:
 		 * are already placing their zImage in (eg) the top 64MB
 		 * of this range.
 		 */
-		mov	r4, pc
-		and	r4, r4, #0xf8000000
+		mov	r0, pc
+		and	r0, r0, #0xf8000000
+#ifdef CONFIG_USE_OF
+		adr	r1, LC1
+#ifdef CONFIG_ARM_APPENDED_DTB
+		/*
+		 * Look for an appended DTB.  If found, we cannot use it to
+		 * validate the calculated start of physical memory, as its
+		 * memory nodes may need to be augmented by ATAGS stored at
+		 * an offset from the same start of physical memory.
+		 */
+		ldr	r2, [r1, #4]	@ get &_edata
+		add	r2, r2, r1	@ relocate it
+		ldr	r2, [r2]	@ get DTB signature
+		ldr	r3, =OF_DT_MAGIC
+		cmp	r2, r3		@ do we have a DTB there?
+		beq	1f		@ if yes, skip validation
+#endif /* CONFIG_ARM_APPENDED_DTB */
+
+		/*
+		 * Make sure we have some stack before calling C code.
+		 * No GOT fixup has occurred yet, but none of the code we're
+		 * about to call uses any global variables.
+		 */
+		ldr	sp, [r1]	@ get stack location
+		add	sp, sp, r1	@ apply relocation
+
+		/* Validate calculated start against passed DTB */
+		mov	r1, r8
+		bl	fdt_check_mem_start
+1:
+#endif /* CONFIG_USE_OF */
 		/* Determine final kernel image address. */
-		add	r4, r4, #TEXT_OFFSET
+		add	r4, r0, #TEXT_OFFSET
 #else
 		ldr	r4, =zreladdr
 #endif
@@ -1164,9 +1191,9 @@ __armv4_mmu_cache_off:
 __armv7_mmu_cache_off:
 		mrc	p15, 0, r0, c1, c0
 #ifdef CONFIG_MMU
-		bic	r0, r0, #0x000d
+		bic	r0, r0, #0x0005
 #else
-		bic	r0, r0, #0x000c
+		bic	r0, r0, #0x0004
 #endif
 		mcr	p15, 0, r0, c1, c0	@ turn MMU and cache off
 		mov	r0, #0