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/bootmem_info.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.
 */
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;
};

/*
 * There are a lot of struct page structures associated with each HugeTLB page.
 * For tail pages, the value of compound_head is the same. So we can reuse first
 * page of head page structures. We map the virtual addresses of all the pages
 * of tail page structures to the head page struct, and then free these page
 * frames. Therefore, we need to reserve one pages as vmemmap areas.
 */
#define RESERVE_VMEMMAP_NR		1U
#define RESERVE_VMEMMAP_SIZE		(RESERVE_VMEMMAP_NR << PAGE_SHIFT)

static int __split_vmemmap_huge_pmd(pmd_t *pmd, unsigned long start)
{
	pmd_t __pmd;
	int i;
	unsigned long addr = start;
	struct page *page = pmd_page(*pmd);
	pte_t *pgtable = pte_alloc_one_kernel(&init_mm);

	if (!pgtable)
		return -ENOMEM;

	pmd_populate_kernel(&init_mm, &__pmd, pgtable);

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

		entry = mk_pte(page + 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(page))
			split_page(page, get_order(PMD_SIZE));

		/* Make pte visible before pmd. See comment in pmd_install(). */
		smp_wmb();
		pmd_populate_kernel(&init_mm, pmd, pgtable);
		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 split_vmemmap_huge_pmd(pmd_t *pmd, unsigned long start)
{
	int leaf;

	spin_lock(&init_mm.page_table_lock);
	leaf = pmd_leaf(*pmd);
	spin_unlock(&init_mm.page_table_lock);

	if (!leaf)
		return 0;

	return __split_vmemmap_huge_pmd(pmd, start);
}

static void vmemmap_pte_range(pmd_t *pmd, unsigned long addr,
			      unsigned long end,
			      struct vmemmap_remap_walk *walk)
{
	pte_t *pte = pte_offset_kernel(pmd, addr);

	/*
	 * The reuse_page is found 'first' in table walk before we start
	 * remapping (which is calling @walk->remap_pte).
	 */
	if (!walk->reuse_page) {
		walk->reuse_page = pte_page(*pte);
		/*
		 * Because the reuse address is part of the range that we are
		 * walking, skip the reuse address range.
		 */
		addr += PAGE_SIZE;
		pte++;
		walk->nr_walked++;
	}

	for (; addr != end; addr += PAGE_SIZE, pte++) {
		walk->remap_pte(pte, addr, walk);
		walk->nr_walked++;
	}
}

static int vmemmap_pmd_range(pud_t *pud, unsigned long addr,
			     unsigned long end,
			     struct vmemmap_remap_walk *walk)
{
	pmd_t *pmd;
	unsigned long next;

	pmd = pmd_offset(pud, addr);
	do {
		int ret;

		ret = split_vmemmap_huge_pmd(pmd, addr & PMD_MASK);
		if (ret)
			return ret;

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

	return 0;
}

static int vmemmap_pud_range(p4d_t *p4d, unsigned long addr,
			     unsigned long end,
			     struct vmemmap_remap_walk *walk)
{
	pud_t *pud;
	unsigned long next;

	pud = pud_offset(p4d, addr);
	do {
		int ret;

		next = pud_addr_end(addr, end);
		ret = vmemmap_pmd_range(pud, addr, next, walk);
		if (ret)
			return ret;
	} while (pud++, addr = next, addr != end);

	return 0;
}

static int vmemmap_p4d_range(pgd_t *pgd, unsigned long addr,
			     unsigned long end,
			     struct vmemmap_remap_walk *walk)
{
	p4d_t *p4d;
	unsigned long next;

	p4d = p4d_offset(pgd, addr);
	do {
		int ret;

		next = p4d_addr_end(addr, end);
		ret = vmemmap_pud_range(p4d, addr, next, walk);
		if (ret)
			return ret;
	} while (p4d++, addr = next, addr != end);

	return 0;
}

static int vmemmap_remap_range(unsigned long start, unsigned long end,
			       struct vmemmap_remap_walk *walk)
{
	unsigned long addr = start;
	unsigned long next;
	pgd_t *pgd;

	VM_BUG_ON(!PAGE_ALIGNED(start));
	VM_BUG_ON(!PAGE_ALIGNED(end));

	pgd = pgd_offset_k(addr);
	do {
		int ret;

		next = pgd_addr_end(addr, end);
		ret = vmemmap_p4d_range(pgd, addr, next, walk);
		if (ret)
			return ret;
	} while (pgd++, addr = next, addr != end);

	/*
	 * We only change the mapping of the vmemmap virtual address range
	 * [@start + PAGE_SIZE, end), so we only need to flush the TLB which
	 * belongs to the range.
	 */
	flush_tlb_kernel_range(start + PAGE_SIZE, 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);
	else
		__free_page(page);
}

/* 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) {
		list_del(&page->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;
	pte_t entry = mk_pte(walk->reuse_page, pgprot);
	struct page *page = pte_page(*pte);

	list_add_tail(&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_pages_check(). 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)
{
	int i;
	struct page *from = start + NR_RESET_STRUCT_PAGE;

	for (i = 0; i < NR_RESET_STRUCT_PAGE; i++)
		memcpy(start + i, from, sizeof(*from));
}

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(*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);

	set_pte_at(&init_mm, addr, pte, mk_pte(page, pgprot));
}

/**
 * vmemmap_remap_free - remap the vmemmap virtual address range [@start, @end)
 *			to the page which @reuse is mapped to, then free vmemmap
 *			which the range are mapped to.
 * @start:	start address of the vmemmap virtual address range that we want
 *		to remap.
 * @end:	end address of the vmemmap virtual address range that we want to
 *		remap.
 * @reuse:	reuse address.
 *
 * Return: %0 on success, negative error code otherwise.
 */
static int vmemmap_remap_free(unsigned long start, unsigned long end,
			      unsigned long reuse)
{
	int ret;
	LIST_HEAD(vmemmap_pages);
	struct vmemmap_remap_walk walk = {
		.remap_pte	= vmemmap_remap_pte,
		.reuse_addr	= reuse,
		.vmemmap_pages	= &vmemmap_pages,
	};