From 6f7a129e59721f6d97a0f06f7078d06f19ade69e Mon Sep 17 00:00:00 2001
From: Yutang Jiang <yutang.jiang@nxp.com>
Date: Thu, 21 Jul 2016 19:37:42 +0800
Subject: [PATCH 70/70] Revert "arm64: use fixmap region for permanent FDT
 mapping"

Signed-off-by: Yutang Jiang <yutang.jiang@nxp.com>
---
 Documentation/arm64/booting.txt |   10 +++----
 arch/arm64/include/asm/boot.h   |   14 ----------
 arch/arm64/include/asm/fixmap.h |   15 -----------
 arch/arm64/include/asm/mmu.h    |    1 -
 arch/arm64/kernel/head.S        |   39 ++++++++++++++++++++++++++-
 arch/arm64/kernel/setup.c       |   29 +++++++++++++-------
 arch/arm64/mm/init.c            |    1 +
 arch/arm64/mm/mmu.c             |   57 ---------------------------------------
 8 files changed, 62 insertions(+), 104 deletions(-)
 delete mode 100644 arch/arm64/include/asm/boot.h

--- a/Documentation/arm64/booting.txt
+++ b/Documentation/arm64/booting.txt
@@ -45,13 +45,11 @@ sees fit.)
 
 Requirement: MANDATORY
 
-The device tree blob (dtb) must be placed on an 8-byte boundary and must
-not exceed 2 megabytes in size. Since the dtb will be mapped cacheable
-using blocks of up to 2 megabytes in size, it must not be placed within
-any 2M region which must be mapped with any specific attributes.
+The device tree blob (dtb) must be placed on an 8-byte boundary within
+the first 512 megabytes from the start of the kernel image and must not
+cross a 2-megabyte boundary. This is to allow the kernel to map the
+blob using a single section mapping in the initial page tables.
 
-NOTE: versions prior to v4.2 also require that the DTB be placed within
-the 512 MB region starting at text_offset bytes below the kernel Image.
 
 3. Decompress the kernel image
 ------------------------------
--- a/arch/arm64/include/asm/boot.h
+++ /dev/null
@@ -1,14 +0,0 @@
-
-#ifndef __ASM_BOOT_H
-#define __ASM_BOOT_H
-
-#include <asm/sizes.h>
-
-/*
- * arm64 requires the DTB to be 8 byte aligned and
- * not exceed 2MB in size.
- */
-#define MIN_FDT_ALIGN		8
-#define MAX_FDT_SIZE		SZ_2M
-
-#endif
--- a/arch/arm64/include/asm/fixmap.h
+++ b/arch/arm64/include/asm/fixmap.h
@@ -18,7 +18,6 @@
 #ifndef __ASSEMBLY__
 #include <linux/kernel.h>
 #include <linux/sizes.h>
-#include <asm/boot.h>
 #include <asm/page.h>
 
 /*
@@ -34,20 +33,6 @@
  */
 enum fixed_addresses {
 	FIX_HOLE,
-
-	/*
-	 * Reserve a virtual window for the FDT that is 2 MB larger than the
-	 * maximum supported size, and put it at the top of the fixmap region.
-	 * The additional space ensures that any FDT that does not exceed
-	 * MAX_FDT_SIZE can be mapped regardless of whether it crosses any
-	 * 2 MB alignment boundaries.
-	 *
-	 * Keep this at the top so it remains 2 MB aligned.
-	 */
-#define FIX_FDT_SIZE		(MAX_FDT_SIZE + SZ_2M)
-	FIX_FDT_END,
-	FIX_FDT = FIX_FDT_END + FIX_FDT_SIZE / PAGE_SIZE - 1,
-
 	FIX_EARLYCON_MEM_BASE,
 	FIX_TEXT_POKE0,
 	__end_of_permanent_fixed_addresses,
--- a/arch/arm64/include/asm/mmu.h
+++ b/arch/arm64/include/asm/mmu.h
@@ -34,6 +34,5 @@ extern void init_mem_pgprot(void);
 extern void create_pgd_mapping(struct mm_struct *mm, phys_addr_t phys,
 			       unsigned long virt, phys_addr_t size,
 			       pgprot_t prot);
-extern void *fixmap_remap_fdt(phys_addr_t dt_phys);
 
 #endif
--- a/arch/arm64/kernel/head.S
+++ b/arch/arm64/kernel/head.S
@@ -212,6 +212,8 @@ ENTRY(stext)
 	bl	el2_setup			// Drop to EL1, w20=cpu_boot_mode
 	adrp	x24, __PHYS_OFFSET
 	bl	set_cpu_boot_mode_flag
+
+	bl	__vet_fdt
 	bl	__create_page_tables		// x25=TTBR0, x26=TTBR1
 	/*
 	 * The following calls CPU setup code, see arch/arm64/mm/proc.S for
@@ -243,6 +245,24 @@ preserve_boot_args:
 ENDPROC(preserve_boot_args)
 
 /*
+ * Determine validity of the x21 FDT pointer.
+ * The dtb must be 8-byte aligned and live in the first 512M of memory.
+ */
+__vet_fdt:
+	tst	x21, #0x7
+	b.ne	1f
+	cmp	x21, x24
+	b.lt	1f
+	mov	x0, #(1 << 29)
+	add	x0, x0, x24
+	cmp	x21, x0
+	b.ge	1f
+	ret
+1:
+	mov	x21, #0
+	ret
+ENDPROC(__vet_fdt)
+/*
  * Macro to create a table entry to the next page.
  *
  *	tbl:	page table address
@@ -306,7 +326,8 @@ ENDPROC(preserve_boot_args)
  * required to get the kernel running. The following sections are required:
  *   - identity mapping to enable the MMU (low address, TTBR0)
  *   - first few MB of the kernel linear mapping to jump to once the MMU has
- *     been enabled
+ *     been enabled, including the FDT blob (TTBR1)
+ *   - pgd entry for fixed mappings (TTBR1)
  */
 __create_page_tables:
 	adrp	x25, idmap_pg_dir
@@ -396,6 +417,22 @@ __create_page_tables:
 	create_block_map x0, x7, x3, x5, x6
 
 	/*
+	 * Map the FDT blob (maximum 2MB; must be within 512MB of
+	 * PHYS_OFFSET).
+	 */
+	mov	x3, x21				// FDT phys address
+	and	x3, x3, #~((1 << 21) - 1)	// 2MB aligned
+	mov	x6, #PAGE_OFFSET
+	sub	x5, x3, x24			// subtract PHYS_OFFSET
+	tst	x5, #~((1 << 29) - 1)		// within 512MB?
+	csel	x21, xzr, x21, ne		// zero the FDT pointer
+	b.ne	1f
+	add	x5, x5, x6			// __va(FDT blob)
+	add	x6, x5, #1 << 21		// 2MB for the FDT blob
+	sub	x6, x6, #1			// inclusive range
+	create_block_map x0, x7, x3, x5, x6
+1:
+	/*
 	 * Since the page tables have been populated with non-cacheable
 	 * accesses (MMU disabled), invalidate the idmap and swapper page
 	 * tables again to remove any speculatively loaded cache lines.
--- a/arch/arm64/kernel/setup.c
+++ b/arch/arm64/kernel/setup.c
@@ -87,6 +87,18 @@ static struct resource mem_res[] = {
 #define kernel_code mem_res[0]
 #define kernel_data mem_res[1]
 
+void __init early_print(const char *str, ...)
+{
+	char buf[256];
+	va_list ap;
+
+	va_start(ap, str);
+	vsnprintf(buf, sizeof(buf), str, ap);
+	va_end(ap);
+
+	printk("%s", buf);
+}
+
 /*
  * The recorded values of x0 .. x3 upon kernel entry.
  */
@@ -180,14 +192,12 @@ static void __init smp_build_mpidr_hash(
 
 static void __init setup_machine_fdt(phys_addr_t dt_phys)
 {
-	void *dt_virt = fixmap_remap_fdt(dt_phys);
-
-	if (!dt_virt || !early_init_dt_scan(dt_virt)) {
-		pr_crit("\n"
-			"Error: invalid device tree blob at physical address %pa (virtual address 0x%p)\n"
-			"The dtb must be 8-byte aligned and must not exceed 2 MB in size\n"
-			"\nPlease check your bootloader.",
-			&dt_phys, dt_virt);
+	if (!dt_phys || !early_init_dt_scan(phys_to_virt(dt_phys))) {
+		early_print("\n"
+			"Error: invalid device tree blob at physical address 0x%p (virtual address 0x%p)\n"
+			"The dtb must be 8-byte aligned and passed in the first 512MB of memory\n"
+			"\nPlease check your bootloader.\n",
+			dt_phys, phys_to_virt(dt_phys));
 
 		while (true)
 			cpu_relax();
@@ -294,6 +304,7 @@ void __init setup_arch(char **cmdline_p)
 	pr_info("Boot CPU: AArch64 Processor [%08x]\n", read_cpuid_id());
 
 	sprintf(init_utsname()->machine, ELF_PLATFORM);
+	setup_machine_fdt(__fdt_pointer);
 	init_mm.start_code = (unsigned long) _text;
 	init_mm.end_code   = (unsigned long) _etext;
 	init_mm.end_data   = (unsigned long) _edata;
@@ -304,8 +315,6 @@ void __init setup_arch(char **cmdline_p)
 	early_fixmap_init();
 	early_ioremap_init();
 
-	setup_machine_fdt(__fdt_pointer);
-
 	parse_early_param();
 
 	/*
--- a/arch/arm64/mm/init.c
+++ b/arch/arm64/mm/init.c
@@ -171,6 +171,7 @@ void __init arm64_memblock_init(void)
 		memblock_reserve(__virt_to_phys(initrd_start), initrd_end - initrd_start);
 #endif
 
+	early_init_fdt_reserve_self();
 	early_init_fdt_scan_reserved_mem();
 
 	/* 4GB maximum for 32-bit only capable devices */
--- a/arch/arm64/mm/mmu.c
+++ b/arch/arm64/mm/mmu.c
@@ -21,7 +21,6 @@
 #include <linux/kernel.h>
 #include <linux/errno.h>
 #include <linux/init.h>
-#include <linux/libfdt.h>
 #include <linux/mman.h>
 #include <linux/nodemask.h>
 #include <linux/memblock.h>
@@ -641,59 +640,3 @@ void __set_fixmap(enum fixed_addresses i
 		flush_tlb_kernel_range(addr, addr+PAGE_SIZE);
 	}
 }
-
-void *__init fixmap_remap_fdt(phys_addr_t dt_phys)
-{
-	const u64 dt_virt_base = __fix_to_virt(FIX_FDT);
-	pgprot_t prot = PAGE_KERNEL_RO;
-	int size, offset;
-	void *dt_virt;
-
-	/*
-	 * Check whether the physical FDT address is set and meets the minimum
-	 * alignment requirement. Since we are relying on MIN_FDT_ALIGN to be
-	 * at least 8 bytes so that we can always access the magic and size
-	 * fields of the FDT header after mapping the first chunk, double check
-	 * here if that is indeed the case.
-	 */
-	BUILD_BUG_ON(MIN_FDT_ALIGN < 8);
-	if (!dt_phys || dt_phys % MIN_FDT_ALIGN)
-		return NULL;
-
-	/*
-	 * Make sure that the FDT region can be mapped without the need to
-	 * allocate additional translation table pages, so that it is safe
-	 * to call create_mapping() this early.
-	 *
-	 * On 64k pages, the FDT will be mapped using PTEs, so we need to
-	 * be in the same PMD as the rest of the fixmap.
-	 * On 4k pages, we'll use section mappings for the FDT so we only
-	 * have to be in the same PUD.
-	 */
-	BUILD_BUG_ON(dt_virt_base % SZ_2M);
-
-	BUILD_BUG_ON(__fix_to_virt(FIX_FDT_END) >> SWAPPER_TABLE_SHIFT !=
-		     __fix_to_virt(FIX_BTMAP_BEGIN) >> SWAPPER_TABLE_SHIFT);
-
-	offset = dt_phys % SWAPPER_BLOCK_SIZE;
-	dt_virt = (void *)dt_virt_base + offset;
-
-	/* map the first chunk so we can read the size from the header */
-	create_mapping(round_down(dt_phys, SWAPPER_BLOCK_SIZE), dt_virt_base,
-		       SWAPPER_BLOCK_SIZE, prot);
-
-	if (fdt_magic(dt_virt) != FDT_MAGIC)
-		return NULL;
-
-	size = fdt_totalsize(dt_virt);
-	if (size > MAX_FDT_SIZE)
-		return NULL;
-
-	if (offset + size > SWAPPER_BLOCK_SIZE)
-		create_mapping(round_down(dt_phys, SWAPPER_BLOCK_SIZE), dt_virt_base,
-			       round_up(offset + size, SWAPPER_BLOCK_SIZE), prot);
-
-	memblock_reserve(dt_phys, size);
-
-	return dt_virt;
-}