arm64: MMU initialisation

/*

 * Copyright (C) 2012 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 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, see <http://www.gnu.org/licenses/>.

 */

#ifndef __ASM_MEMBLOCK_H

#define __ASM_MEMBLOCK_H

extern void arm64_memblock_init(void);

#endif

/*

 * Based on arch/arm/mm/init.c

 *

 * Copyright (C) 1995-2005 Russell King

 * Copyright (C) 2012 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 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, see <http://www.gnu.org/licenses/>.

 */

#include <linux/kernel.h>

#include <linux/export.h>

#include <linux/errno.h>

#include <linux/swap.h>

#include <linux/init.h>

#include <linux/bootmem.h>

#include <linux/mman.h>

#include <linux/nodemask.h>

#include <linux/initrd.h>

#include <linux/gfp.h>

#include <linux/memblock.h>

#include <linux/sort.h>

#include <linux/of_fdt.h>

#include <asm/prom.h>

#include <asm/sections.h>

#include <asm/setup.h>

#include <asm/sizes.h>

#include <asm/tlb.h>

#include "mm.h"

static unsigned long phys_initrd_start __initdata = 0;

static unsigned long phys_initrd_size __initdata = 0;

phys_addr_t memstart_addr __read_mostly = 0;

void __init early_init_dt_setup_initrd_arch(unsigned long start,

					    unsigned long end)

{

	phys_initrd_start = start;

	phys_initrd_size = end - start;

}

static int __init early_initrd(char *p)

{

	unsigned long start, 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);

#define MAX_DMA32_PFN ((4UL * 1024 * 1024 * 1024) >> PAGE_SHIFT)

static void __init zone_sizes_init(unsigned long min, unsigned long max)

{

	struct memblock_region *reg;

	unsigned long zone_size[MAX_NR_ZONES], zhole_size[MAX_NR_ZONES];

	unsigned long max_dma32 = min;

	memset(zone_size, 0, sizeof(zone_size));

#ifdef CONFIG_ZONE_DMA32

	/* 4GB maximum for 32-bit only capable devices */

	max_dma32 = min(max, MAX_DMA32_PFN);

	zone_size[ZONE_DMA32] = max_dma32 - min;

#endif

	zone_size[ZONE_NORMAL] = max - max_dma32;

	memcpy(zhole_size, zone_size, sizeof(zhole_size));

	for_each_memblock(memory, reg) {

		unsigned long start = memblock_region_memory_base_pfn(reg);

		unsigned long end = memblock_region_memory_end_pfn(reg);

		if (start >= max)

			continue;

#ifdef CONFIG_ZONE_DMA32

		if (start < max_dma32) {

			unsigned long dma_end = min(end, max_dma32);

			zhole_size[ZONE_DMA32] -= dma_end - start;

		}

#endif

		if (end > max_dma32) {

			unsigned long normal_end = min(end, max);

			unsigned long normal_start = max(start, max_dma32);

			zhole_size[ZONE_NORMAL] -= normal_end - normal_start;

		}

	}

	free_area_init_node(0, zone_size, min, zhole_size);

}

#ifdef CONFIG_HAVE_ARCH_PFN_VALID

int pfn_valid(unsigned long pfn)

{

	return memblock_is_memory(pfn << PAGE_SHIFT);

}

EXPORT_SYMBOL(pfn_valid);

#endif

#ifndef CONFIG_SPARSEMEM

static void arm64_memory_present(void)

{

}

#else

static void arm64_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

void __init arm64_memblock_init(void)

{

	u64 *reserve_map, base, size;

	/* Register the kernel text, kernel data and initrd with memblock */

	memblock_reserve(__pa(_text), _end - _text);

#ifdef CONFIG_BLK_DEV_INITRD

	if (phys_initrd_size) {

		memblock_reserve(phys_initrd_start, phys_initrd_size);

		/* Now convert initrd to virtual addresses */

		initrd_start = __phys_to_virt(phys_initrd_start);

		initrd_end = initrd_start + phys_initrd_size;

	}

#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);

	/* Reserve the dtb region */

	memblock_reserve(virt_to_phys(initial_boot_params),

			 be32_to_cpu(initial_boot_params->totalsize));

	/*

	 * Process the reserve map.  This will probably overlap the initrd

	 * and dtb locations which are already reserved, but overlapping

	 * doesn't hurt anything

	 */

	reserve_map = ((void*)initial_boot_params) +

			be32_to_cpu(initial_boot_params->off_mem_rsvmap);

	while (1) {

		base = be64_to_cpup(reserve_map++);

		size = be64_to_cpup(reserve_map++);

		if (!size)

			break;

		memblock_reserve(base, size);

	}

	memblock_allow_resize();

	memblock_dump_all();

}

void __init bootmem_init(void)

{

	unsigned long min, max;

	min = PFN_UP(memblock_start_of_DRAM());

	max = PFN_DOWN(memblock_end_of_DRAM());

	/*

	 * Sparsemem tries to allocate bootmem in memory_present(), so must be

	 * done after the fixed reservations.

	 */

	arm64_memory_present();

	sparse_init();

	zone_sizes_init(min, max);

	high_memory = __va((max << PAGE_SHIFT) - 1) + 1;

	max_pfn = max_low_pfn = max;

}

static inline int free_area(unsigned long pfn, unsigned long end, char *s)

{

	unsigned int pages = 0, size = (end - pfn) << (PAGE_SHIFT - 10);

	for (; pfn < end; pfn++) {

		struct page *page = pfn_to_page(pfn);

		ClearPageReserved(page);

		init_page_count(page);

		__free_page(page);

		pages++;

	}

	if (size && s)

		pr_info("Freeing %s memory: %dK\n", s, size);

	return pages;

}

/*

 * Poison init memory with an undefined instruction (0x0).

 */

static inline void poison_init_mem(void *s, size_t count)

{

	memset(s, 0, count);

}

#ifndef CONFIG_SPARSEMEM_VMEMMAP

static inline void free_memmap(unsigned long start_pfn, unsigned long end_pfn)

{

	struct page *start_pg, *end_pg;

	unsigned long pg, pgend;

	/*

	 * Convert start_pfn/end_pfn to a struct page pointer.

	 */

	start_pg = pfn_to_page(start_pfn - 1) + 1;

	end_pg = pfn_to_page(end_pfn - 1) + 1;

	/*

	 * Convert to physical addresses, and round start upwards and end

	 * downwards.

	 */

	pg = (unsigned long)PAGE_ALIGN(__pa(start_pg));

	pgend = (unsigned long)__pa(end_pg) & PAGE_MASK;

	/*

	 * If there are free pages between these, free the section of the

	 * memmap array.

	 */

	if (pg < pgend)

		free_bootmem(pg, pgend - pg);

}

/*

 * The mem_map array can get very big. Free the unused area of the memory map.

 */

static void __init free_unused_memmap(void)

{

	unsigned long start, prev_end = 0;

	struct memblock_region *reg;

	for_each_memblock(memory, reg) {

		start = __phys_to_pfn(reg->base);

#ifdef CONFIG_SPARSEMEM

		/*

		 * Take care not to free memmap entries that don't exist due

		 * to SPARSEMEM sections which aren't present.

		 */

		start = min(start, ALIGN(prev_end, PAGES_PER_SECTION));

#endif

		/*

		 * If we had a previous bank, and there is a space between the

		 * current bank and the previous, free it.

		 */

		if (prev_end && prev_end < start)

			free_memmap(prev_end, start);

		/*

		 * Align up here since the VM subsystem insists that the

		 * memmap entries are valid from the bank end aligned to

		 * MAX_ORDER_NR_PAGES.

		 */

		prev_end = ALIGN(start + __phys_to_pfn(reg->size),

				 MAX_ORDER_NR_PAGES);

	}

#ifdef CONFIG_SPARSEMEM

	if (!IS_ALIGNED(prev_end, PAGES_PER_SECTION))

		free_memmap(prev_end, ALIGN(prev_end, PAGES_PER_SECTION));

#endif

}

#endif	/* !CONFIG_SPARSEMEM_VMEMMAP */

/*

 * mem_init() marks the free areas in the mem_map and tells us how much memory

 * is free.  This is done after various parts of the system have claimed their

 * memory after the kernel image.

 */

void __init mem_init(void)

{

	unsigned long reserved_pages, free_pages;

	struct memblock_region *reg;

#if CONFIG_SWIOTLB

	extern void __init arm64_swiotlb_init(size_t max_size);

	arm64_swiotlb_init(max_pfn << (PAGE_SHIFT - 1));

#endif

	max_mapnr   = pfn_to_page(max_pfn + PHYS_PFN_OFFSET) - mem_map;

#ifndef CONFIG_SPARSEMEM_VMEMMAP

	/* this will put all unused low memory onto the freelists */

	free_unused_memmap();

#endif

	totalram_pages += free_all_bootmem();

	reserved_pages = free_pages = 0;

	for_each_memblock(memory, reg) {

		unsigned int pfn1, pfn2;

		struct page *page, *end;

		pfn1 = __phys_to_pfn(reg->base);

		pfn2 = pfn1 + __phys_to_pfn(reg->size);

		page = pfn_to_page(pfn1);

		end  = pfn_to_page(pfn2 - 1) + 1;

		do {

			if (PageReserved(page))

				reserved_pages++;

			else if (!page_count(page))

				free_pages++;

			page++;

		} while (page < end);

	}

	/*

	 * Since our memory may not be contiguous, calculate the real number

	 * of pages we have in this system.

	 */

	pr_info("Memory:");

	num_physpages = 0;

	for_each_memblock(memory, reg) {

		unsigned long pages = memblock_region_memory_end_pfn(reg) -

			memblock_region_memory_base_pfn(reg);

		num_physpages += pages;

		printk(" %ldMB", pages >> (20 - PAGE_SHIFT));

	}

	printk(" = %luMB total\n", num_physpages >> (20 - PAGE_SHIFT));

	pr_notice("Memory: %luk/%luk available, %luk reserved\n",

		  nr_free_pages() << (PAGE_SHIFT-10),

		  free_pages << (PAGE_SHIFT-10),

		  reserved_pages << (PAGE_SHIFT-10));

#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"

		  "    vmalloc : 0x%16lx - 0x%16lx   (%6ld MB)\n"

#ifdef CONFIG_SPARSEMEM_VMEMMAP

		  "    vmemmap : 0x%16lx - 0x%16lx   (%6ld MB)\n"

#endif

		  "    modules : 0x%16lx - 0x%16lx   (%6ld MB)\n"

		  "    memory  : 0x%16lx - 0x%16lx   (%6ld MB)\n"

		  "      .init : 0x%p" " - 0x%p" "   (%6ld kB)\n"

		  "      .text : 0x%p" " - 0x%p" "   (%6ld kB)\n"

		  "      .data : 0x%p" " - 0x%p" "   (%6ld kB)\n",

		  MLM(VMALLOC_START, VMALLOC_END),

#ifdef CONFIG_SPARSEMEM_VMEMMAP

		  MLM((unsigned long)virt_to_page(PAGE_OFFSET),

		      (unsigned long)virt_to_page(high_memory)),

#endif

		  MLM(MODULES_VADDR, MODULES_END),

		  MLM(PAGE_OFFSET, (unsigned long)high_memory),

		  MLK_ROUNDUP(__init_begin, __init_end),

		  MLK_ROUNDUP(_text, _etext),

		  MLK_ROUNDUP(_sdata, _edata));

#undef MLK

#undef MLM

#undef MLK_ROUNDUP

	/*

	 * Check boundaries twice: Some fundamental inconsistencies can be

	 * detected at build time already.

	 */

#ifdef CONFIG_COMPAT

	BUILD_BUG_ON(TASK_SIZE_32			> TASK_SIZE_64);

#endif

	BUILD_BUG_ON(TASK_SIZE_64			> MODULES_VADDR);

	BUG_ON(TASK_SIZE_64				> MODULES_VADDR);

	if (PAGE_SIZE >= 16384 && num_physpages <= 128) {

		extern int sysctl_overcommit_memory;

		/*

		 * On a machine this small we won't get anywhere without

		 * overcommit, so turn it on by default.

		 */

		sysctl_overcommit_memory = OVERCOMMIT_ALWAYS;

	}

}

void free_initmem(void)

{

	poison_init_mem(__init_begin, __init_end - __init_begin);

	totalram_pages += free_area(__phys_to_pfn(__pa(__init_begin)),

				    __phys_to_pfn(__pa(__init_end)),

				    "init");

}

#ifdef CONFIG_BLK_DEV_INITRD

static int keep_initrd;

void free_initrd_mem(unsigned long start, unsigned long end)

{

	if (!keep_initrd) {

		poison_init_mem((void *)start, PAGE_ALIGN(end) - start);

		totalram_pages += free_area(__phys_to_pfn(__pa(start)),

					    __phys_to_pfn(__pa(end)),

					    "initrd");

	}

}

static int __init keepinitrd_setup(char *__unused)

{

	keep_initrd = 1;

	return 1;

}

__setup("keepinitrd", keepinitrd_setup);

#endif

/*

 * Based on arch/arm/mm/mmu.c

 *

 * Copyright (C) 1995-2005 Russell King

 * Copyright (C) 2012 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 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, see <http://www.gnu.org/licenses/>.

 */

#include <linux/export.h>

#include <linux/kernel.h>

#include <linux/errno.h>

#include <linux/init.h>

#include <linux/mman.h>

#include <linux/nodemask.h>

#include <linux/memblock.h>

#include <linux/fs.h>

#include <asm/cputype.h>

#include <asm/sections.h>

#include <asm/setup.h>

#include <asm/sizes.h>

#include <asm/tlb.h>

#include <asm/mmu_context.h>

#include "mm.h"

/*

 * Empty_zero_page is a special page that is used for zero-initialized data

 * and COW.

 */

struct page *empty_zero_page;

EXPORT_SYMBOL(empty_zero_page);

pgprot_t pgprot_default;

EXPORT_SYMBOL(pgprot_default);

static pmdval_t prot_sect_kernel;

struct cachepolicy {

	const char	policy[16];

	u64		mair;

	u64		tcr;

};

static struct cachepolicy cache_policies[] __initdata = {

	{

		.policy		= "uncached",

		.mair		= 0x44,			/* inner, outer non-cacheable */

		.tcr		= TCR_IRGN_NC | TCR_ORGN_NC,

	}, {

		.policy		= "writethrough",

		.mair		= 0xaa,			/* inner, outer write-through, read-allocate */

		.tcr		= TCR_IRGN_WT | TCR_ORGN_WT,

	}, {

		.policy		= "writeback",

		.mair		= 0xee,			/* inner, outer write-back, read-allocate */

		.tcr		= TCR_IRGN_WBnWA | TCR_ORGN_WBnWA,

	}

};

/*

 * These are useful for identifying cache coherency problems by allowing the

 * cache or the cache and writebuffer to be turned off. It changes the Normal

 * memory caching attributes in the MAIR_EL1 register.

 */

static int __init early_cachepolicy(char *p)

{

	int i;

	u64 tmp;

	for (i = 0; i < ARRAY_SIZE(cache_policies); i++) {

		int len = strlen(cache_policies[i].policy);

		if (memcmp(p, cache_policies[i].policy, len) == 0)

			break;

	}

	if (i == ARRAY_SIZE(cache_policies)) {

		pr_err("ERROR: unknown or unsupported cache policy: %s\n", p);

		return 0;

	}

	flush_cache_all();

	/*

	 * Modify MT_NORMAL attributes in MAIR_EL1.

	 */

	asm volatile(

	"	mrs	%0, mair_el1\n"

	"	bfi	%0, %1, #%2, #8\n"

	"	msr	mair_el1, %0\n"

	"	isb\n"

	: "=&r" (tmp)

	: "r" (cache_policies[i].mair), "i" (MT_NORMAL * 8));

	/*

	 * Modify TCR PTW cacheability attributes.

	 */

	asm volatile(

	"	mrs	%0, tcr_el1\n"

	"	bic	%0, %0, %2\n"

	"	orr	%0, %0, %1\n"

	"	msr	tcr_el1, %0\n"

	"	isb\n"

	: "=&r" (tmp)

	: "r" (cache_policies[i].tcr), "r" (TCR_IRGN_MASK | TCR_ORGN_MASK));

	flush_cache_all();

	return 0;

}

early_param("cachepolicy", early_cachepolicy);

/*

 * Adjust the PMD section entries according to the CPU in use.

 */

static void __init init_mem_pgprot(void)

{

	pteval_t default_pgprot;

	int i;

	default_pgprot = PTE_ATTRINDX(MT_NORMAL);

	prot_sect_kernel = PMD_TYPE_SECT | PMD_SECT_AF | PMD_ATTRINDX(MT_NORMAL);

#ifdef CONFIG_SMP

	/*

	 * Mark memory with the "shared" attribute for SMP systems

	 */

	default_pgprot |= PTE_SHARED;

	prot_sect_kernel |= PMD_SECT_S;

#endif

	for (i = 0; i < 16; i++) {

		unsigned long v = pgprot_val(protection_map[i]);

		protection_map[i] = __pgprot(v | default_pgprot);

	}

	pgprot_default = __pgprot(PTE_TYPE_PAGE | PTE_AF | default_pgprot);

}

pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn,

			      unsigned long size, pgprot_t vma_prot)

{

	if (!pfn_valid(pfn))

		return pgprot_noncached(vma_prot);

	else if (file->f_flags & O_SYNC)

		return pgprot_writecombine(vma_prot);

	return vma_prot;

}

EXPORT_SYMBOL(phys_mem_access_prot);

static void __init *early_alloc(unsigned long sz)

{

	void *ptr = __va(memblock_alloc(sz, sz));

	memset(ptr, 0, sz);

	return ptr;

}

static void __init alloc_init_pte(pmd_t *pmd, unsigned long addr,

				  unsigned long end, unsigned long pfn)

{

	pte_t *pte;

	if (pmd_none(*pmd)) {

		pte = early_alloc(PTRS_PER_PTE * sizeof(pte_t));

		__pmd_populate(pmd, __pa(pte), PMD_TYPE_TABLE);

	}

	BUG_ON(pmd_bad(*pmd));

	pte = pte_offset_kernel(pmd, addr);

	do {

		set_pte(pte, pfn_pte(pfn, PAGE_KERNEL_EXEC));

		pfn++;

	} while (pte++, addr += PAGE_SIZE, addr != end);

}

static void __init alloc_init_pmd(pud_t *pud, unsigned long addr,

				  unsigned long end, phys_addr_t phys)

{

	pmd_t *pmd;

	unsigned long next;

	/*

	 * Check for initial section mappings in the pgd/pud and remove them.

	 */

	if (pud_none(*pud) || pud_bad(*pud)) {

		pmd = early_alloc(PTRS_PER_PMD * sizeof(pmd_t));

		pud_populate(&init_mm, pud, pmd);

	}

	pmd = pmd_offset(pud, addr);

	do {

		next = pmd_addr_end(addr, end);

		/* try section mapping first */

		if (((addr | next | phys) & ~SECTION_MASK) == 0)

			set_pmd(pmd, __pmd(phys | prot_sect_kernel));

		else

			alloc_init_pte(pmd, addr, next, __phys_to_pfn(phys));

		phys += next - addr;

	} while (pmd++, addr = next, addr != end);

}

static void __init alloc_init_pud(pgd_t *pgd, unsigned long addr,

				  unsigned long end, unsigned long phys)

{

	pud_t *pud = pud_offset(pgd, addr);

	unsigned long next;

	do {

		next = pud_addr_end(addr, end);

		alloc_init_pmd(pud, addr, next, phys);

		phys += next - addr;

	} while (pud++, addr = next, addr != end);

}

/*

 * Create the page directory entries and any necessary page tables for the

 * mapping specified by 'md'.

 */

static void __init create_mapping(phys_addr_t phys, unsigned long virt,

				  phys_addr_t size)

{

	unsigned long addr, length, end, next;

	pgd_t *pgd;

	if (virt < VMALLOC_START) {

		pr_warning("BUG: not creating mapping for 0x%016llx at 0x%016lx - outside kernel range\n",

			   phys, virt);

		return;

	}

	addr = virt & PAGE_MASK;

	length = PAGE_ALIGN(size + (virt & ~PAGE_MASK));

	pgd = pgd_offset_k(addr);

	end = addr + length;

	do {

		next = pgd_addr_end(addr, end);

		alloc_init_pud(pgd, addr, next, phys);

		phys += next - addr;

	} while (pgd++, addr = next, addr != end);

}

static void __init map_mem(void)

{

	struct memblock_region *reg;

	/* map all the memory banks */

	for_each_memblock(memory, reg) {

		phys_addr_t start = reg->base;

		phys_addr_t end = start + reg->size;

		if (start >= end)

			break;

		create_mapping(start, __phys_to_virt(start), end - start);

	}

}

/*

 * paging_init() sets up the page tables, initialises the zone memory

 * maps and sets up the zero page.

 */

void __init paging_init(void)

{

	void *zero_page;

	/*

	 * Maximum PGDIR_SIZE addressable via the initial direct kernel

	 * mapping in swapper_pg_dir.

	 */

	memblock_set_current_limit((PHYS_OFFSET & PGDIR_MASK) + PGDIR_SIZE);

	init_mem_pgprot();

	map_mem();