/*
 * 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/cache.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.h>
#include <linux/of_fdt.h>
#include <linux/dma-mapping.h>
#include <linux/dma-contiguous.h>
#include <linux/efi.h>
#include <linux/swiotlb.h>
#include <linux/vmalloc.h>
#include <linux/mm.h>
#include <linux/kexec.h>
#include <linux/crash_dump.h>
#include <linux/kmemleak.h>

#include <asm/boot.h>
#include <asm/fixmap.h>
#include <asm/kasan.h>
#include <asm/kernel-pgtable.h>
#include <asm/memory.h>
#include <asm/numa.h>
#include <asm/sections.h>
#include <asm/setup.h>
#include <asm/sizes.h>
#include <asm/tlb.h>
#include <asm/alternative.h>

/*
 * We need to be able to catch inadvertent references to memstart_addr
 * that occur (potentially in generic code) before arm64_memblock_init()
 * executes, which assigns it its actual value. So use a default value
 * that cannot be mistaken for a real physical address.
 */
s64 memstart_addr __ro_after_init = -1;
EXPORT_SYMBOL(memstart_addr);

phys_addr_t arm64_dma32_phys_limit __ro_after_init;

#ifdef CONFIG_BLK_DEV_INITRD
static int __init early_initrd(char *p)
{
	unsigned long start, size;
	char *endp;

	start = memparse(p, &endp);
	if (*endp == ',') {
		size = memparse(endp + 1, NULL);

		initrd_start = start;
		initrd_end = start + size;
	}
	return 0;
}
early_param("initrd", early_initrd);
#endif

#ifdef CONFIG_KEXEC_CORE

/* Current arm64 boot protocol requires 2MB alignment */
#define CRASH_ALIGN			SZ_2M

#define CRASH_ADDR_LOW_MAX		arm64_dma32_phys_limit
#define CRASH_ADDR_HIGH_MAX		(PHYS_MASK + 1)
#define CRASH_HIGH_SEARCH_BASE		SZ_4G

#define DEFAULT_CRASH_KERNEL_LOW_SIZE	(128UL << 20)

static int __init reserve_crashkernel_low(unsigned long long low_size)
{
	unsigned long long low_base;

	low_base = memblock_alloc_range_nid(low_size, CRASH_ALIGN, 0, CRASH_ADDR_LOW_MAX,
						NUMA_NO_NODE, MEMBLOCK_NONE);
	if (!low_base) {
		pr_err("cannot allocate crashkernel low memory (size:0x%llx).\n", low_size);
		return -ENOMEM;
	}

	pr_info("crashkernel low memory reserved: 0x%08llx - 0x%08llx (%lld MB)\n",
		low_base, low_base + low_size, low_size >> 20);

	crashk_low_res.start = low_base;
	crashk_low_res.end   = low_base + low_size - 1;
	insert_resource(&iomem_resource, &crashk_low_res);

	return 0;
}

/*
 * reserve_crashkernel() - reserves memory for crash kernel
 *
 * This function reserves memory area given in "crashkernel=" kernel command
 * line parameter. The memory reserved is used by dump capture kernel when
 * primary kernel is crashing.
 */
static void __init reserve_crashkernel(void)
{
	unsigned long long crash_low_size = 0, search_base = 0;
	unsigned long long crash_max = CRASH_ADDR_LOW_MAX;
	unsigned long long crash_base, crash_size;
	char *cmdline = boot_command_line;
	bool fixed_base = false;
	bool high = false;
	int ret;

	/* crashkernel=X[@offset] */
	ret = parse_crashkernel(cmdline, memblock_phys_mem_size(),
				&crash_size, &crash_base);
	if (ret == -ENOENT) {
		ret = parse_crashkernel_high(cmdline, 0, &crash_size, &crash_base);
		if (ret || !crash_size)
			return;

		/*
		 * crashkernel=Y,low can be specified or not, but invalid value
		 * is not allowed.
		 */
		ret = parse_crashkernel_low(cmdline, 0, &crash_low_size, &crash_base);
		if (ret == -ENOENT)
			crash_low_size = DEFAULT_CRASH_KERNEL_LOW_SIZE;
		else if (ret)
			return;

		search_base = CRASH_HIGH_SEARCH_BASE;
		crash_max = CRASH_ADDR_HIGH_MAX;
		high = true;
	} else if (ret || !crash_size) {
		/* The specified value is invalid */
		return;
	}

	crash_size = PAGE_ALIGN(crash_size);

	/* User specifies base address explicitly. */
	if (crash_base) {
		fixed_base = true;
		search_base = crash_base;
		crash_max = crash_base + crash_size;
	}

retry:
	crash_base = memblock_alloc_range_nid(crash_size, CRASH_ALIGN,
					search_base, crash_max,
					NUMA_NO_NODE, MEMBLOCK_NONE);
	if (!crash_base) {
		/*
		 * For crashkernel=size[KMG]@offset[KMG], print out failure
		 * message if can't reserve the specified region.
		 */
		if (fixed_base) {
			pr_warn("crashkernel reservation failed - memory is in use.\n");
			return;
		}

		/*
		 * For crashkernel=size[KMG], if the first attempt was for
		 * low memory, fall back to high memory, the minimum required
		 * low memory will be reserved later.
		 */
		if (!high && crash_max == CRASH_ADDR_LOW_MAX) {
			crash_max = CRASH_ADDR_HIGH_MAX;
			search_base = CRASH_ADDR_LOW_MAX;
			crash_low_size = DEFAULT_CRASH_KERNEL_LOW_SIZE;
			goto retry;
		}

		/*
		 * For crashkernel=size[KMG],high, if the first attempt was
		 * for high memory, fall back to low memory.
		 */
		if (high && crash_max == CRASH_ADDR_HIGH_MAX) {
			crash_max = CRASH_ADDR_LOW_MAX;
			search_base = 0;
			goto retry;
		}
		pr_warn("cannot allocate crashkernel (size:0x%llx)\n",
			crash_size);
		return;
	}

	if ((crash_base >= CRASH_ADDR_LOW_MAX) && crash_low_size &&
	     reserve_crashkernel_low(crash_low_size)) {
		memblock_free(crash_base, crash_size);
		return;
	}

	pr_info("crashkernel reserved: 0x%016llx - 0x%016llx (%lld MB)\n",
		crash_base, crash_base + crash_size, crash_size >> 20);

	/*
	 * The crashkernel memory will be removed from the kernel linear
	 * map. Inform kmemleak so that it won't try to access it.
	 */
	kmemleak_ignore_phys(crash_base);
	if (crashk_low_res.end)
		kmemleak_ignore_phys(crashk_low_res.start);

	crashk_res.start = crash_base;
	crashk_res.end = crash_base + crash_size - 1;
	insert_resource(&iomem_resource, &crashk_res);
}
#else
static void __init reserve_crashkernel(void)
{
}
#endif /* CONFIG_KEXEC_CORE */

/*
 * Return the maximum physical address for ZONE_DMA32 (DMA_BIT_MASK(32)). It
 * currently assumes that for memory starting above 4G, 32-bit devices will
 * use a DMA offset.
 */
static phys_addr_t __init max_zone_dma32_phys(void)
{
	phys_addr_t offset = memblock_start_of_DRAM() & GENMASK_ULL(63, 32);
	return min(offset + (1ULL << 32), memblock_end_of_DRAM());
}

static void __init zone_sizes_init(unsigned long min, unsigned long max)
{
	unsigned long max_zone_pfns[MAX_NR_ZONES]  = {0};

#ifdef CONFIG_ZONE_DMA32
	max_zone_pfns[ZONE_DMA32] = PFN_DOWN(arm64_dma32_phys_limit);
#endif
	max_zone_pfns[ZONE_NORMAL] = max;

	free_area_init(max_zone_pfns);
}

int pfn_valid(unsigned long pfn)
{
	phys_addr_t addr = pfn << PAGE_SHIFT;

	if ((addr >> PAGE_SHIFT) != pfn)
		return 0;

#ifdef CONFIG_SPARSEMEM
	if (pfn_to_section_nr(pfn) >= NR_MEM_SECTIONS)
		return 0;

	if (!valid_section(__pfn_to_section(pfn)))
		return 0;
#endif
	return memblock_is_map_memory(addr);
}
EXPORT_SYMBOL(pfn_valid);

#ifndef CONFIG_SPARSEMEM
static void __init arm64_memory_present(void)
{
}
#else
static void __init arm64_memory_present(void)
{
	struct memblock_region *reg;

	for_each_memblock(memory, reg) {
		int nid = memblock_get_region_node(reg);

		memory_present(nid, memblock_region_memory_base_pfn(reg),
				memblock_region_memory_end_pfn(reg));
	}
}
#endif

static phys_addr_t memory_limit = PHYS_ADDR_MAX;

/*
 * Limit the memory size that was specified via FDT.
 */
static int __init early_mem(char *p)
{
	if (!p)
		return 1;

	memory_limit = memparse(p, &p) & PAGE_MASK;
	pr_notice("Memory limited to %lldMB\n", memory_limit >> 20);

	return 0;
}
early_param("mem", early_mem);

void __init arm64_memblock_init(void)
{
	s64 linear_region_size = PAGE_END - _PAGE_OFFSET(vabits_actual);

	/*
	 * Corner case: 52-bit VA capable systems running KVM in nVHE mode may
	 * be limited in their ability to support a linear map that exceeds 51
	 * bits of VA space, depending on the placement of the ID map. Given
	 * that the placement of the ID map may be randomized, let's simply
	 * limit the kernel's linear map to 51 bits as well if we detect this
	 * configuration.
	 */
	if (IS_ENABLED(CONFIG_KVM) && vabits_actual == 52 &&
	    is_hyp_mode_available() && !is_kernel_in_hyp_mode()) {
		pr_info("Capping linear region to 51 bits for KVM in nVHE mode on LVA capable hardware.\n");
		linear_region_size = min_t(u64, linear_region_size, BIT(51));
	}

	/* Remove memory above our supported physical address size */
	memblock_remove(1ULL << PHYS_MASK_SHIFT, ULLONG_MAX);

	/*
	 * Select a suitable value for the base of physical memory.
	 */
	memstart_addr = round_down(memblock_start_of_DRAM(),
				   ARM64_MEMSTART_ALIGN);

	/*
	 * Remove the memory that we will not be able to cover with the
	 * linear mapping. Take care not to clip the kernel which may be
	 * high in memory.
	 */
	memblock_remove(max_t(u64, memstart_addr + linear_region_size,
			__pa_symbol(_end)), ULLONG_MAX);
	if (memstart_addr + linear_region_size < memblock_end_of_DRAM()) {
		/* ensure that memstart_addr remains sufficiently aligned */
		memstart_addr = round_up(memblock_end_of_DRAM() - linear_region_size,
					 ARM64_MEMSTART_ALIGN);
		memblock_remove(0, memstart_addr);
	}

	/*
	 * If we are running with a 52-bit kernel VA config on a system that
	 * does not support it, we have to place the available physical
	 * memory in the 48-bit addressable part of the linear region, i.e.,
	 * we have to move it upward. Since memstart_addr represents the
	 * physical address of PAGE_OFFSET, we have to *subtract* from it.
	 */
	if (IS_ENABLED(CONFIG_ARM64_VA_BITS_52) && (vabits_actual != 52))
		memstart_addr -= _PAGE_OFFSET(48) - _PAGE_OFFSET(52);

	/*
	 * Apply the memory limit if it was set. Since the kernel may be loaded
	 * high up in memory, add back the kernel region that must be accessible
	 * via the linear mapping.
	 */
	if (memory_limit != PHYS_ADDR_MAX) {
		memblock_mem_limit_remove_map(memory_limit);
		memblock_add(__pa_symbol(_text), (u64)(_end - _text));
	}

	if (IS_ENABLED(CONFIG_BLK_DEV_INITRD) && initrd_start) {
		/*
		 * Add back the memory we just removed if it results in the
		 * initrd to become inaccessible via the linear mapping.
		 * Otherwise, this is a no-op
		 */
		u64 base = initrd_start & PAGE_MASK;
		u64 size = PAGE_ALIGN(initrd_end) - base;

		/*
		 * We can only add back the initrd memory if we don't end up
		 * with more memory than we can address via the linear mapping.
		 * It is up to the bootloader to position the kernel and the
		 * initrd reasonably close to each other (i.e., within 32 GB of
		 * each other) so that all granule/#levels combinations can
		 * always access both.
		 */
		if (WARN(base < memblock_start_of_DRAM() ||
			 base + size > memblock_start_of_DRAM() +
				       linear_region_size,
			"initrd not fully accessible via the linear mapping -- please check your bootloader ...\n")) {
			initrd_start = 0;
		} else {
			memblock_remove(base, size); /* clear MEMBLOCK_ flags */
			memblock_add(base, size);
			memblock_reserve(base, size);
		}
	}

	if (IS_ENABLED(CONFIG_RANDOMIZE_BASE)) {
		extern u16 memstart_offset_seed;
		u64 range = linear_region_size -
			    (memblock_end_of_DRAM() - memblock_start_of_DRAM());

		/*
		 * If the size of the linear region exceeds, by a sufficient
		 * margin, the size of the region that the available physical
		 * memory spans, randomize the linear region as well.
		 */
		if (memstart_offset_seed > 0 && range >= ARM64_MEMSTART_ALIGN) {
			range /= ARM64_MEMSTART_ALIGN;
			memstart_addr -= ARM64_MEMSTART_ALIGN *
					 ((range * memstart_offset_seed) >> 16);
		}
	}

	/*
	 * Register the kernel text, kernel data, initrd, and initial
	 * pagetables with memblock.
	 */
	memblock_reserve(__pa_symbol(_text), _end - _text);
#ifdef CONFIG_BLK_DEV_INITRD
	if (initrd_start) {
		memblock_reserve(initrd_start, initrd_end - initrd_start);

		/* the generic initrd code expects virtual addresses */
		initrd_start = __phys_to_virt(initrd_start);
		initrd_end = __phys_to_virt(initrd_end);
	}
#endif

	early_init_fdt_scan_reserved_mem();

	/* 4GB maximum for 32-bit only capable devices */
	if (IS_ENABLED(CONFIG_ZONE_DMA32))
		arm64_dma32_phys_limit = max_zone_dma32_phys();
	else
		arm64_dma32_phys_limit = PHYS_MASK + 1;

	reserve_crashkernel();

	high_memory = __va(memblock_end_of_DRAM() - 1) + 1;

	dma_contiguous_reserve(arm64_dma32_phys_limit);
}

void __init bootmem_init(void)
{
	unsigned long min, max;

	min = PFN_UP(memblock_start_of_DRAM());
	max = PFN_DOWN(memblock_end_of_DRAM());

	early_memtest(min << PAGE_SHIFT, max << PAGE_SHIFT);

	max_pfn = max_low_pfn = max;
	min_low_pfn = min;

	arch_numa_init();
	/*
	 * Sparsemem tries to allocate bootmem in memory_present(), so must be
	 * done after the fixed reservations.
	 * initialize node_online_map that gets used in hugetlb_cma_reserve()
	 * while allocating required CMA size across online nodes.
	 */
	arm64_memory_present();

	sparse_init();
	zone_sizes_init(min, max);

	memblock_dump_all();
}

#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)
		memblock_free(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(__phys_to_pfn(reg->base + 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)
{
	swiotlb_init(max_pfn > PFN_DOWN(arm64_dma32_phys_limit), SWIOTLB_VERBOSE);

	set_max_mapnr(max_pfn - PHYS_PFN_OFFSET);

#ifndef CONFIG_SPARSEMEM_VMEMMAP
	free_unused_memmap();
#endif
	/* this will put all unused low memory onto the freelists */
	memblock_free_all();

	mem_init_print_info(NULL);

	/*
	 * Check boundaries twice: Some fundamental inconsistencies can be
	 * detected at build time already.
	 */
#ifdef CONFIG_COMPAT
	BUILD_BUG_ON(TASK_SIZE_32 > DEFAULT_MAP_WINDOW_64);
#endif

#ifdef CONFIG_SPARSEMEM_VMEMMAP
	/*
	 * Make sure we chose the upper bound of sizeof(struct page)
	 * correctly when sizing the VMEMMAP array.
	 */
	BUILD_BUG_ON(sizeof(struct page) > (1 << STRUCT_PAGE_MAX_SHIFT));
#endif

	if (PAGE_SIZE >= 16384 && get_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)
{
	free_reserved_area(lm_alias(__init_begin),
			   lm_alias(__init_end),
			   0, "unused kernel");
	/*
	 * Unmap the __init region but leave the VM area in place. This
	 * prevents the region from being reused for kernel modules, which
	 * is not supported by kallsyms.
	 */
	unmap_kernel_range((u64)__init_begin, (u64)(__init_end - __init_begin));
}

#ifdef CONFIG_BLK_DEV_INITRD

static int keep_initrd __initdata;

void __init free_initrd_mem(unsigned long start, unsigned long end)
{
	unsigned long aligned_start, aligned_end;

	if (!keep_initrd) {
		aligned_start = __virt_to_phys(start) & PAGE_MASK;
		aligned_end = PAGE_ALIGN(__virt_to_phys(end));

		memblock_free(aligned_start, aligned_end - aligned_start);
		free_reserved_area((void *)start, (void *)end, 0, "initrd");
	}
}

static int __init keepinitrd_setup(char *__unused)
{
	keep_initrd = 1;
	return 1;
}

__setup("keepinitrd", keepinitrd_setup);
#endif

/*
 * Dump out memory limit information on panic.
 */
static int dump_mem_limit(struct notifier_block *self, unsigned long v, void *p)
{
	if (memory_limit != PHYS_ADDR_MAX) {
		pr_emerg("Memory Limit: %llu MB\n", memory_limit >> 20);
	} else {
		pr_emerg("Memory Limit: none\n");
	}
	return 0;
}

static struct notifier_block mem_limit_notifier = {
	.notifier_call = dump_mem_limit,
};

static int __init register_mem_limit_dumper(void)
{
	atomic_notifier_chain_register(&panic_notifier_list,
				       &mem_limit_notifier);
	return 0;
}
__initcall(register_mem_limit_dumper);