arm64: place initial page tables above the kernel

Currently we place swapper_pg_dir and idmap_pg_dir below the kernel
image, between PHYS_OFFSET and (PHYS_OFFSET + TEXT_OFFSET). However,
bootloaders may use portions of this memory below the kernel and we do
not parse the memory reservation list until after the MMU has been
enabled. As such we may clobber some memory a bootloader wishes to have
preserved.

To enable the use of all of this memory by bootloaders (when the
required memory reservations are communicated to the kernel) it is
necessary to move our initial page tables elsewhere. As we currently
have an effectively unbound requirement for memory at the end of the
kernel image for .bss, we can place the page tables here.

This patch moves the initial page table to the end of the kernel image,
after the BSS. As they do not consist of any initialised data they will
be stripped from the kernel Image as with the BSS. The BSS clearing
routine is updated to stop at __bss_stop rather than _end so as to not
clobber the page tables, and memory reservations made redundant by the
new organisation are removed.
Signed-off-by: Mark Rutland <mark.rutland@arm.com>
Tested-by: Laura Abbott <lauraa@codeaurora.org>
Acked-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>

arch/arm64/include/asm/page.h

@@ -31,6 +31,15 @@
 /* We do define AT_SYSINFO_EHDR but don't use the gate mechanism */
 #define __HAVE_ARCH_GATE_AREA		1
 
+/*
+ * The idmap and swapper page tables need some space reserved in the kernel
+ * image. The idmap only requires a pgd and a next level table to (section) map
+ * the kernel, while the swapper also maps the FDT and requires an additional
+ * table to map an early UART. See __create_page_tables for more information.
+ */
+#define SWAPPER_DIR_SIZE	(3 * PAGE_SIZE)
+#define IDMAP_DIR_SIZE		(2 * PAGE_SIZE)
+
 #ifndef __ASSEMBLY__
 
 #ifdef CONFIG_ARM64_64K_PAGES

arch/arm64/kernel/head.S

@@ -35,29 +35,17 @@
 #include <asm/page.h>
 #include <asm/virt.h>
 
-/*
- * swapper_pg_dir is the virtual address of the initial page table. We place
- * the page tables 3 * PAGE_SIZE below KERNEL_RAM_VADDR. The idmap_pg_dir has
- * 2 pages and is placed below swapper_pg_dir.
- */
 #define KERNEL_RAM_VADDR	(PAGE_OFFSET + TEXT_OFFSET)
 
 #if (KERNEL_RAM_VADDR & 0xfffff) != 0x80000
 #error KERNEL_RAM_VADDR must start at 0xXXX80000
 #endif
 
-#define SWAPPER_DIR_SIZE	(3 * PAGE_SIZE)
-#define IDMAP_DIR_SIZE		(2 * PAGE_SIZE)
-
-	.globl	swapper_pg_dir
-	.equ	swapper_pg_dir, KERNEL_RAM_VADDR - SWAPPER_DIR_SIZE
-
-	.globl	idmap_pg_dir
-	.equ	idmap_pg_dir, swapper_pg_dir - IDMAP_DIR_SIZE
-
-	.macro	pgtbl, ttb0, ttb1, phys
-	add	\ttb1, \phys, #TEXT_OFFSET - SWAPPER_DIR_SIZE
-	sub	\ttb0, \ttb1, #IDMAP_DIR_SIZE
+	.macro	pgtbl, ttb0, ttb1, virt_to_phys
+	ldr	\ttb1, =swapper_pg_dir
+	ldr	\ttb0, =idmap_pg_dir
+	add	\ttb1, \ttb1, \virt_to_phys
+	add	\ttb0, \ttb0, \virt_to_phys
 	.endm
 
 #ifdef CONFIG_ARM64_64K_PAGES
@@ -413,7 +401,7 @@ ENTRY(secondary_startup)
 	mov	x23, x0				// x23=current cpu_table
 	cbz	x23, __error_p			// invalid processor (x23=0)?
 
-	pgtbl	x25, x26, x24			// x25=TTBR0, x26=TTBR1
+	pgtbl	x25, x26, x28			// x25=TTBR0, x26=TTBR1
 	ldr	x12, [x23, #CPU_INFO_SETUP]
 	add	x12, x12, x28			// __virt_to_phys
 	blr	x12				// initialise processor
@@ -527,7 +515,7 @@ ENDPROC(__calc_phys_offset)
  *   - pgd entry for fixed mappings (TTBR1)
  */
 __create_page_tables:
-	pgtbl	x25, x26, x24			// idmap_pg_dir and swapper_pg_dir addresses
+	pgtbl	x25, x26, x28			// idmap_pg_dir and swapper_pg_dir addresses
 	mov	x27, lr
 
 	/*
@@ -616,7 +604,7 @@ ENDPROC(__create_page_tables)
 __switch_data:
 	.quad	__mmap_switched
 	.quad	__bss_start			// x6
-	.quad	_end				// x7
+	.quad	__bss_stop			// x7
 	.quad	processor_id			// x4
 	.quad	__fdt_pointer			// x5
 	.quad	memstart_addr			// x6

arch/arm64/kernel/vmlinux.lds.S

@@ -104,6 +104,13 @@ SECTIONS
 	_edata = .;
 
 	BSS_SECTION(0, 0, 0)
+
+	. = ALIGN(PAGE_SIZE);
+	idmap_pg_dir = .;
+	. += IDMAP_DIR_SIZE;
+	swapper_pg_dir = .;
+	. += SWAPPER_DIR_SIZE;
+
 	_end = .;
 
 	STABS_DEBUG

arch/arm64/mm/init.c

@@ -128,20 +128,16 @@ void __init arm64_memblock_init(void)
 {
 	phys_addr_t dma_phys_limit = 0;
 
-	/* Register the kernel text, kernel data and initrd with memblock */
+	/*
+	 * Register the kernel text, kernel data, initrd, and initial
+	 * pagetables with memblock.
+	 */
 	memblock_reserve(__pa(_text), _end - _text);
 #ifdef CONFIG_BLK_DEV_INITRD
 	if (initrd_start)
 		memblock_reserve(__virt_to_phys(initrd_start), initrd_end - initrd_start);
 #endif
 
-	/*
-	 * Reserve the page tables.  These are already in use,
-	 * and can only be in node 0.
-	 */
-	memblock_reserve(__pa(swapper_pg_dir), SWAPPER_DIR_SIZE);
-	memblock_reserve(__pa(idmap_pg_dir), IDMAP_DIR_SIZE);
-
 	early_init_fdt_scan_reserved_mem();
 
 	/* 4GB maximum for 32-bit only capable devices */