path: root/mm/hugetlb_vmemmap.c

// SPDX-License-Identifier: GPL-2.0
/*
 * HugeTLB Vmemmap Optimization (HVO)
 *
 * Copyright (c) 2020, ByteDance. All rights reserved.
 *
 *     Author: Muchun Song <songmuchun@bytedance.com>
 *
 * See Documentation/mm/vmemmap_dedup.rst
 */
#define pr_fmt(fmt)	"HugeTLB: " fmt

#include <linux/pgtable.h>
#include <linux/moduleparam.h>
#include <linux/bootmem_info.h>
#include <linux/mmdebug.h>
#include <linux/pagewalk.h>
#include <asm/pgalloc.h>
#include <asm/tlbflush.h>
#include "hugetlb_vmemmap.h"

/**
 * struct vmemmap_remap_walk - walk vmemmap page table
 *
 * @remap_pte:		called for each lowest-level entry (PTE).
 * @nr_walked:		the number of walked pte.
 * @reuse_page:		the page which is reused for the tail vmemmap pages.
 * @reuse_addr:		the virtual address of the @reuse_page page.
 * @vmemmap_pages:	the list head of the vmemmap pages that can be freed
 *			or is mapped from.
 * @flags:		used to modify behavior in vmemmap page table walking
 *			operations.
 */
struct vmemmap_remap_walk {
	void			(*remap_pte)(pte_t *pte, unsigned long addr,
					     struct vmemmap_remap_walk *walk);
	unsigned long		nr_walked;
	struct page		*reuse_page;
	unsigned long		reuse_addr;
	struct list_head	*vmemmap_pages;

/* Skip the TLB flush when we split the PMD */
#define VMEMMAP_SPLIT_NO_TLB_FLUSH	BIT(0)
/* Skip the TLB flush when we remap the PTE */
#define VMEMMAP_REMAP_NO_TLB_FLUSH	BIT(1)
	unsigned long		flags;
};

static int vmemmap_split_pmd(pmd_t *pmd, struct page *head, unsigned long start,
			     struct vmemmap_remap_walk *walk)
{
	pmd_t __pmd;
	int i;
	unsigned long addr = start;
	pte_t *pgtable;

	pgtable = pte_alloc_one_kernel(&init_mm);
	if (!pgtable)
		return -ENOMEM;

	pmd_populate_kernel(&init_mm, &__pmd, pgtable);

	for (i = 0; i < PTRS_PER_PTE; i++, addr += PAGE_SIZE) {
		pte_t entry, *pte;
		pgprot_t pgprot = PAGE_KERNEL;

		entry = mk_pte(head + i, pgprot);
		pte = pte_offset_kernel(&__pmd, addr);
		set_pte_at(&init_mm, addr, pte, entry);
	}

	spin_lock(&init_mm.page_table_lock);
	if (likely(pmd_leaf(*pmd))) {
		/*
		 * Higher order allocations from buddy allocator must be able to
		 * be treated as indepdenent small pages (as they can be freed
		 * individually).
		 */
		if (!PageReserved(head))
			split_page(head, get_order(PMD_SIZE));

		/* Make pte visible before pmd. See comment in pmd_install(). */
		smp_wmb();
		pmd_populate_kernel(&init_mm, pmd, pgtable);
		if (!(walk->flags & VMEMMAP_SPLIT_NO_TLB_FLUSH))
			flush_tlb_kernel_range(start, start + PMD_SIZE);
	} else {
		pte_free_kernel(&init_mm, pgtable);
	}
	spin_unlock(&init_mm.page_table_lock);

	return 0;
}

static int vmemmap_pmd_entry(pmd_t *pmd, unsigned long addr,
			     unsigned long next, struct mm_walk *walk)
{
	int ret = 0;
	struct page *head;
	struct vmemmap_remap_walk *vmemmap_walk = walk->private;

	/* Only splitting, not remapping the vmemmap pages. */
	if (!vmemmap_walk->remap_pte)
		walk->action = ACTION_CONTINUE;

	spin_lock(&init_mm.page_table_lock);
	head = pmd_leaf(*pmd) ? pmd_page(*pmd) : NULL;
	/*
	 * Due to HugeTLB alignment requirements and the vmemmap
	 * pages being at the start of the hotplugged memory
	 * region in memory_hotplug.memmap_on_memory case. Checking
	 * the vmemmap page associated with the first vmemmap page
	 * if it is self-hosted is sufficient.
	 *
	 * [                  hotplugged memory                  ]
	 * [        section        ][...][        section        ]
	 * [ vmemmap ][              usable memory               ]
	 *   ^  | ^                        |
	 *   +--+ |                        |
	 *        +------------------------+
	 */
	if (IS_ENABLED(CONFIG_MEMORY_HOTPLUG) && unlikely(!vmemmap_walk->nr_walked)) {
		struct page *page = head ? head + pte_index(addr) :
				    pte_page(ptep_get(pte_offset_kernel(pmd, addr)));

		if (PageVmemmapSelfHosted(page))
			ret = -ENOTSUPP;
	}
	spin_unlock(&init_mm.page_table_lock);
	if (!head || ret)
		return ret;

	return vmemmap_split_pmd(pmd, head, addr & PMD_MASK, vmemmap_walk);
}

static int vmemmap_pte_entry(pte_t *pte, unsigned long addr,
			     unsigned long next, struct mm_walk *walk)
{
	struct vmemmap_remap_walk *vmemmap_walk = walk->private;

	/*
	 * The reuse_page is found 'first' in page table walking before
	 * starting remapping.
	 */
	if (!vmemmap_walk->reuse_page)
		vmemmap_walk->reuse_page = pte_page(ptep_get(pte));
	else
		vmemmap_walk->remap_pte(pte, addr, vmemmap_walk);
	vmemmap_walk->nr_walked++;

	return 0;
}

static const struct mm_walk_ops vmemmap_remap_ops = {
	.pmd_entry	= vmemmap_pmd_entry,
	.pte_entry	= vmemmap_pte_entry,
};

static int vmemmap_remap_range(unsigned long start, unsigned long end,
			       struct vmemmap_remap_walk *walk)
{
	int ret;

	VM_BUG_ON(!PAGE_ALIGNED(start | end));

	mmap_read_lock(&init_mm);
	ret = walk_page_range_novma(&init_mm, start, end, &vmemmap_remap_ops,
				    NULL, walk);
	mmap_read_unlock(&init_mm);
	if (ret)
		return ret;

	if (walk->remap_pte && !(walk->flags & VMEMMAP_REMAP_NO_TLB_FLUSH))
		flush_tlb_kernel_range(start, end);

	return 0;
}

/*
 * Free a vmemmap page. A vmemmap page can be allocated from the memblock
 * allocator or buddy allocator. If the PG_reserved flag is set, it means
 * that it allocated from the memblock allocator, just free it via the
 * free_bootmem_page(). Otherwise, use __free_page().
 */
static inline void free_vmemmap_page(struct page *page)
{
	if (PageReserved(page)) {
		free_bootmem_page(page);
		mod_node_page_state(page_pgdat(page), NR_MEMMAP_BOOT, -1);
	} else {
		__free_page(page);
		mod_node_page_state(page_pgdat(page), NR_MEMMAP, -1);
	}
}

/* Free a list of the vmemmap pages */
static void free_vmemmap_page_list(struct list_head *list)
{
	struct page *page, *next;

	list_for_each_entry_safe(page, next, list, lru)
		free_vmemmap_page(page);
}

static void vmemmap_remap_pte(pte_t *pte, unsigned long addr,
			      struct vmemmap_remap_walk *walk)
{
	/*
	 * Remap the tail pages as read-only to catch illegal write operation
	 * to the tail pages.
	 */
	pgprot_t pgprot = PAGE_KERNEL_RO;
	struct page *page = pte_page(ptep_get(pte));
	pte_t entry;

	/* Remapping the head page requires r/w */
	if (unlikely(addr == walk->reuse_addr)) {
		pgprot = PAGE_KERNEL;
		list_del(&walk->reuse_page->lru);

		/*
		 * Makes sure that preceding stores to the page contents from
		 * vmemmap_remap_free() become visible before the set_pte_at()
		 * write.
		 */
		smp_wmb();
	}

	entry = mk_pte(walk->reuse_page, pgprot);
	list_add(&page->lru, walk->vmemmap_pages);
	set_pte_at(&init_mm, addr, pte, entry);
}

/*
 * How many struct page structs need to be reset. When we reuse the head
 * struct page, the special metadata (e.g. page->flags or page->mapping)
 * cannot copy to the tail struct page structs. The invalid value will be
 * checked in the free_tail_page_prepare(). In order to avoid the message
 * of "corrupted mapping in tail page". We need to reset at least 3 (one
 * head struct page struct and two tail struct page structs) struct page
 * structs.
 */
#define NR_RESET_STRUCT_PAGE		3

static inline void reset_struct_pages(struct page *start)
{
	struct page *from = start + NR_RESET_STRUCT_PAGE;

	BUILD_BUG_ON(NR_RESET_STRUCT_PAGE * 2 > PAGE_SIZE / sizeof(struct page));
	memcpy(start, from, sizeof(*from) * NR_RESET_STRUCT_PAGE);
}

static void vmemmap_restore_pte(pte_t *pte, unsigned long addr,
				struct vmemmap_remap_walk *walk)
{
	pgprot_t pgprot = PAGE_KERNEL;
	struct page *page;
	void *to;

	BUG_ON(pte_page(ptep_get(pte)) != walk->reuse_page);

	page = list_first_entry(walk->vmemmap_pages, struct page, lru);
	list_del(&page->lru);
	to = page_to_virt(page);
	copy_page(to, (void *)walk->reuse_addr);
	reset_struct_pages(to);

	/*
	 * Makes sure that preceding stores to the page contents become visible
	 * before the set_pte_at() write.
	 */
	smp_wmb();
	set_pte_at(&init_mm, addr, pte, mk_pte(page, pgprot));
}

/**
 * vmemmap_remap_split - split the vmemmap virtual address range [@start, @end)
 *                      backing PMDs of the directmap into PTEs
 * @start:     start address of the vmemmap virtual address range that we want
 *             to remap.
 * @end:       end address of the vmemmap virtual