diff options
Diffstat (limited to 'mm/hugetlb_vmemmap.c')
| -rw-r--r-- | mm/hugetlb_vmemmap.c | 323 |
1 files changed, 115 insertions, 208 deletions
diff --git a/mm/hugetlb_vmemmap.c b/mm/hugetlb_vmemmap.c index 791626983c2e..fcd9f7872064 100644 --- a/mm/hugetlb_vmemmap.c +++ b/mm/hugetlb_vmemmap.c @@ -1,181 +1,16 @@ // SPDX-License-Identifier: GPL-2.0 /* - * Free some vmemmap pages of HugeTLB + * Optimize vmemmap pages associated with HugeTLB * * Copyright (c) 2020, Bytedance. All rights reserved. * * Author: Muchun Song <songmuchun@bytedance.com> * - * The struct page structures (page structs) are used to describe a physical - * page frame. By default, there is a one-to-one mapping from a page frame to - * it's corresponding page struct. - * - * HugeTLB pages consist of multiple base page size pages and is supported by - * many architectures. See hugetlbpage.rst in the Documentation directory for - * more details. On the x86-64 architecture, HugeTLB pages of size 2MB and 1GB - * are currently supported. Since the base page size on x86 is 4KB, a 2MB - * HugeTLB page consists of 512 base pages and a 1GB HugeTLB page consists of - * 4096 base pages. For each base page, there is a corresponding page struct. - * - * Within the HugeTLB subsystem, only the first 4 page structs are used to - * contain unique information about a HugeTLB page. __NR_USED_SUBPAGE provides - * this upper limit. The only 'useful' information in the remaining page structs - * is the compound_head field, and this field is the same for all tail pages. - * - * By removing redundant page structs for HugeTLB pages, memory can be returned - * to the buddy allocator for other uses. - * - * Different architectures support different HugeTLB pages. For example, the - * following table is the HugeTLB page size supported by x86 and arm64 - * architectures. Because arm64 supports 4k, 16k, and 64k base pages and - * supports contiguous entries, so it supports many kinds of sizes of HugeTLB - * page. - * - * +--------------+-----------+-----------------------------------------------+ - * | Architecture | Page Size | HugeTLB Page Size | - * +--------------+-----------+-----------+-----------+-----------+-----------+ - * | x86-64 | 4KB | 2MB | 1GB | | | - * +--------------+-----------+-----------+-----------+-----------+-----------+ - * | | 4KB | 64KB | 2MB | 32MB | 1GB | - * | +-----------+-----------+-----------+-----------+-----------+ - * | arm64 | 16KB | 2MB | 32MB | 1GB | | - * | +-----------+-----------+-----------+-----------+-----------+ - * | | 64KB | 2MB | 512MB | 16GB | | - * +--------------+-----------+-----------+-----------+-----------+-----------+ - * - * When the system boot up, every HugeTLB page has more than one struct page - * structs which size is (unit: pages): - * - * struct_size = HugeTLB_Size / PAGE_SIZE * sizeof(struct page) / PAGE_SIZE - * - * Where HugeTLB_Size is the size of the HugeTLB page. We know that the size - * of the HugeTLB page is always n times PAGE_SIZE. So we can get the following - * relationship. - * - * HugeTLB_Size = n * PAGE_SIZE - * - * Then, - * - * struct_size = n * PAGE_SIZE / PAGE_SIZE * sizeof(struct page) / PAGE_SIZE - * = n * sizeof(struct page) / PAGE_SIZE - * - * We can use huge mapping at the pud/pmd level for the HugeTLB page. - * - * For the HugeTLB page of the pmd level mapping, then - * - * struct_size = n * sizeof(struct page) / PAGE_SIZE - * = PAGE_SIZE / sizeof(pte_t) * sizeof(struct page) / PAGE_SIZE - * = sizeof(struct page) / sizeof(pte_t) - * = 64 / 8 - * = 8 (pages) - * - * Where n is how many pte entries which one page can contains. So the value of - * n is (PAGE_SIZE / sizeof(pte_t)). - * - * This optimization only supports 64-bit system, so the value of sizeof(pte_t) - * is 8. And this optimization also applicable only when the size of struct page - * is a power of two. In most cases, the size of struct page is 64 bytes (e.g. - * x86-64 and arm64). So if we use pmd level mapping for a HugeTLB page, the - * size of struct page structs of it is 8 page frames which size depends on the - * size of the base page. - * - * For the HugeTLB page of the pud level mapping, then - * - * struct_size = PAGE_SIZE / sizeof(pmd_t) * struct_size(pmd) - * = PAGE_SIZE / 8 * 8 (pages) - * = PAGE_SIZE (pages) - * - * Where the struct_size(pmd) is the size of the struct page structs of a - * HugeTLB page of the pmd level mapping. - * - * E.g.: A 2MB HugeTLB page on x86_64 consists in 8 page frames while 1GB - * HugeTLB page consists in 4096. - * - * Next, we take the pmd level mapping of the HugeTLB page as an example to - * show the internal implementation of this optimization. There are 8 pages - * struct page structs associated with a HugeTLB page which is pmd mapped. - * - * Here is how things look before optimization. - * - * HugeTLB struct pages(8 pages) page frame(8 pages) - * +-----------+ ---virt_to_page---> +-----------+ mapping to +-----------+ - * | | | 0 | -------------> | 0 | - * | | +-----------+ +-----------+ - * | | | 1 | -------------> | 1 | - * | | +-----------+ +-----------+ - * | | | 2 | -------------> | 2 | - * | | +-----------+ +-----------+ - * | | | 3 | -------------> | 3 | - * | | +-----------+ +-----------+ - * | | | 4 | -------------> | 4 | - * | PMD | +-----------+ +-----------+ - * | level | | 5 | -------------> | 5 | - * | mapping | +-----------+ +-----------+ - * | | | 6 | -------------> | 6 | - * | | +-----------+ +-----------+ - * | | | 7 | -------------> | 7 | - * | | +-----------+ +-----------+ - * | | - * | | - * | | - * +-----------+ - * - * The value of page->compound_head is the same for all tail pages. The first - * page of page structs (page 0) associated with the HugeTLB page contains the 4 - * page structs necessary to describe the HugeTLB. The only use of the remaining - * pages of page structs (page 1 to page 7) is to point to page->compound_head. - * Therefore, we can remap pages 1 to 7 to page 0. Only 1 page of page structs - * will be used for each HugeTLB page. This will allow us to free the remaining - * 7 pages to the buddy allocator. - * - * Here is how things look after remapping. - * - * HugeTLB struct pages(8 pages) page frame(8 pages) - * +-----------+ ---virt_to_page---> +-----------+ mapping to +-----------+ - * | | | 0 | -------------> | 0 | - * | | +-----------+ +-----------+ - * | | | 1 | ---------------^ ^ ^ ^ ^ ^ ^ - * | | +-----------+ | | | | | | - * | | | 2 | -----------------+ | | | | | - * | | +-----------+ | | | | | - * | | | 3 | -------------------+ | | | | - * | | +-----------+ | | | | - * | | | 4 | ---------------------+ | | | - * | PMD | +-----------+ | | | - * | level | | 5 | -----------------------+ | | - * | mapping | +-----------+ | | - * | | | 6 | -------------------------+ | - * | | +-----------+ | - * | | | 7 | ---------------------------+ - * | | +-----------+ - * | | - * | | - * | | - * +-----------+ - * - * When a HugeTLB is freed to the buddy system, we should allocate 7 pages for - * vmemmap pages and restore the previous mapping relationship. - * - * For the HugeTLB page of the pud level mapping. It is similar to the former. - * We also can use this approach to free (PAGE_SIZE - 1) vmemmap pages. - * - * Apart from the HugeTLB page of the pmd/pud level mapping, some architectures - * (e.g. aarch64) provides a contiguous bit in the translation table entries - * that hints to the MMU to indicate that it is one of a contiguous set of - * entries that can be cached in a single TLB entry. - * - * The contiguous bit is used to increase the mapping size at the pmd and pte - * (last) level. So this type of HugeTLB page can be optimized only when its - * size of the struct page structs is greater than 1 page. - * - * Notice: The head vmemmap page is not freed to the buddy allocator and all - * tail vmemmap pages are mapped to the head vmemmap page frame. So we can see - * more than one struct page struct with PG_head (e.g. 8 per 2 MB HugeTLB page) - * associated with each HugeTLB page. The compound_head() can handle this - * correctly (more details refer to the comment above compound_head()). + * See Documentation/vm/vmemmap_dedup.rst */ #define pr_fmt(fmt) "HugeTLB: " fmt +#include <linux/memory_hotplug.h> #include "hugetlb_vmemmap.h" /* @@ -188,53 +23,63 @@ #define RESERVE_VMEMMAP_NR 1U #define RESERVE_VMEMMAP_SIZE (RESERVE_VMEMMAP_NR << PAGE_SHIFT) -DEFINE_STATIC_KEY_MAYBE(CONFIG_HUGETLB_PAGE_FREE_VMEMMAP_DEFAULT_ON, - hugetlb_free_vmemmap_enabled_key); -EXPORT_SYMBOL(hugetlb_free_vmemmap_enabled_key); +enum vmemmap_optimize_mode { + VMEMMAP_OPTIMIZE_OFF, + VMEMMAP_OPTIMIZE_ON, +}; -static int __init early_hugetlb_free_vmemmap_param(char *buf) -{ - /* We cannot optimize if a "struct page" crosses page boundaries. */ - if (!is_power_of_2(sizeof(struct page))) { - pr_warn("cannot free vmemmap pages because \"struct page\" crosses page boundaries\n"); - return 0; - } +DEFINE_STATIC_KEY_MAYBE(CONFIG_HUGETLB_PAGE_OPTIMIZE_VMEMMAP_DEFAULT_ON, + hugetlb_optimize_vmemmap_key); +EXPORT_SYMBOL(hugetlb_optimize_vmemmap_key); - if (!buf) - return -EINVAL; +static enum vmemmap_optimize_mode vmemmap_optimize_mode = + IS_ENABLED(CONFIG_HUGETLB_PAGE_FREE_VMEMMAP_DEFAULT_ON); - if (!strcmp(buf, "on")) - static_branch_enable(&hugetlb_free_vmemmap_enabled_key); - else if (!strcmp(buf, "off")) - static_branch_disable(&hugetlb_free_vmemmap_enabled_key); - else - return -EINVAL; +static void vmemmap_optimize_mode_switch(enum vmemmap_optimize_mode to) +{ + if (vmemmap_optimize_mode == to) + return; - return 0; + if (to == VMEMMAP_OPTIMIZE_OFF) + static_branch_dec(&hugetlb_optimize_vmemmap_key); + else + static_branch_inc(&hugetlb_optimize_vmemmap_key); + WRITE_ONCE(vmemmap_optimize_mode, to); } -early_param("hugetlb_free_vmemmap", early_hugetlb_free_vmemmap_param); -static inline unsigned long free_vmemmap_pages_size_per_hpage(struct hstate *h) +static int __init hugetlb_vmemmap_early_param(char *buf) { - return (unsigned long)free_vmemmap_pages_per_hpage(h) << PAGE_SHIFT; + bool enable; + enum vmemmap_optimize_mode mode; + + if (kstrtobool(buf, &enable)) + return -EINVAL; + + mode = enable ? VMEMMAP_OPTIMIZE_ON : VMEMMAP_OPTIMIZE_OFF; + vmemmap_optimize_mode_switch(mode); + + return 0; } +early_param("hugetlb_free_vmemmap", hugetlb_vmemmap_early_param); /* * Previously discarded vmemmap pages will be allocated and remapping * after this function returns zero. */ -int alloc_huge_page_vmemmap(struct hstate *h, struct page *head) +int hugetlb_vmemmap_alloc(struct hstate *h, struct page *head) { int ret; unsigned long vmemmap_addr = (unsigned long)head; - unsigned long vmemmap_end, vmemmap_reuse; + unsigned long vmemmap_end, vmemmap_reuse, vmemmap_pages; if (!HPageVmemmapOptimized(head)) return 0; - vmemmap_addr += RESERVE_VMEMMAP_SIZE; - vmemmap_end = vmemmap_addr + free_vmemmap_pages_size_per_hpage(h); - vmemmap_reuse = vmemmap_addr - PAGE_SIZE; + vmemmap_addr += RESERVE_VMEMMAP_SIZE; + vmemmap_pages = hugetlb_optimize_vmemmap_pages(h); + vmemmap_end = vmemmap_addr + (vmemmap_pages << PAGE_SHIFT); + vmemmap_reuse = vmemmap_addr - PAGE_SIZE; + /* * The pages which the vmemmap virtual address range [@vmemmap_addr, * @vmemmap_end) are mapped to are freed to the buddy allocator, and @@ -244,30 +89,40 @@ int alloc_huge_page_vmemmap(struct hstate *h, struct page *head) */ ret = vmemmap_remap_alloc(vmemmap_addr, vmemmap_end, vmemmap_reuse, GFP_KERNEL | __GFP_NORETRY | __GFP_THISNODE); - if (!ret) + if (!ret) { ClearHPageVmemmapOptimized(head); + static_branch_dec(&hugetlb_optimize_vmemmap_key); + } return ret; } -void free_huge_page_vmemmap(struct hstate *h, struct page *head) +void hugetlb_vmemmap_free(struct hstate *h, struct page *head) { unsigned long vmemmap_addr = (unsigned long)head; - unsigned long vmemmap_end, vmemmap_reuse; + unsigned long vmemmap_end, vmemmap_reuse, vmemmap_pages; - if (!free_vmemmap_pages_per_hpage(h)) + vmemmap_pages = hugetlb_optimize_vmemmap_pages(h); + if (!vmemmap_pages) return; - vmemmap_addr += RESERVE_VMEMMAP_SIZE; - vmemmap_end = vmemmap_addr + free_vmemmap_pages_size_per_hpage(h); - vmemmap_reuse = vmemmap_addr - PAGE_SIZE; + if (READ_ONCE(vmemmap_optimize_mode) == VMEMMAP_OPTIMIZE_OFF) + return; + + static_branch_inc(&hugetlb_optimize_vmemmap_key); + + vmemmap_addr += RESERVE_VMEMMAP_SIZE; + vmemmap_end = vmemmap_addr + (vmemmap_pages << PAGE_SHIFT); + vmemmap_reuse = vmemmap_addr - PAGE_SIZE; /* * Remap the vmemmap virtual address range [@vmemmap_addr, @vmemmap_end) * to the page which @vmemmap_reuse is mapped to, then free the pages * which the range [@vmemmap_addr, @vmemmap_end] is mapped to. */ - if (!vmemmap_remap_free(vmemmap_addr, vmemmap_end, vmemmap_reuse)) + if (vmemmap_remap_free(vmemmap_addr, vmemmap_end, vmemmap_reuse)) + static_branch_dec(&hugetlb_optimize_vmemmap_key); + else SetHPageVmemmapOptimized(head); } @@ -278,14 +133,17 @@ void __init hugetlb_vmemmap_init(struct hstate *h) /* * There are only (RESERVE_VMEMMAP_SIZE / sizeof(struct page)) struct - * page structs that can be used when CONFIG_HUGETLB_PAGE_FREE_VMEMMAP, + * page structs that can be used when CONFIG_HUGETLB_PAGE_OPTIMIZE_VMEMMAP, * so add a BUILD_BUG_ON to catch invalid usage of the tail struct page. */ BUILD_BUG_ON(__NR_USED_SUBPAGE >= RESERVE_VMEMMAP_SIZE / sizeof(struct page)); - if (!hugetlb_free_vmemmap_enabled()) + if (!is_power_of_2(sizeof(struct page))) { + pr_warn_once("cannot optimize vmemmap pages because \"struct page\" crosses page boundaries\n"); + static_branch_disable(&hugetlb_optimize_vmemmap_key); return; + } vmemmap_pages = (nr_pages * sizeof(struct page)) >> PAGE_SHIFT; /* @@ -297,8 +155,57 @@ void __init hugetlb_vmemmap_init(struct hstate *h) * hugetlbpage.rst for more details. */ if (likely(vmemmap_pages > RESERVE_VMEMMAP_NR)) - h->nr_free_vmemmap_pages = vmemmap_pages - RESERVE_VMEMMAP_NR; + h->optimize_vmemmap_pages = vmemmap_pages - RESERVE_VMEMMAP_NR; + + pr_info("can optimize %d vmemmap pages for %s\n", + h->optimize_vmemmap_pages, h->name); +} + +#ifdef CONFIG_PROC_SYSCTL +static int hugetlb_optimize_vmemmap_handler(struct ctl_table *table, int write, + void *buffer, size_t *length, + loff_t *ppos) +{ + int ret; + enum vmemmap_optimize_mode mode; + static DEFINE_MUTEX(sysctl_mutex); + + if (write && !capable(CAP_SYS_ADMIN)) + return -EPERM; + + mutex_lock(&sysctl_mutex); + mode = vmemmap_optimize_mode; + table->data = &mode; + ret = proc_dointvec_minmax(table, write, buffer, length, ppos); + if (write && !ret) + vmemmap_optimize_mode_switch(mode); + mutex_unlock(&sysctl_mutex); - pr_info("can free %d vmemmap pages for %s\n", h->nr_free_vmemmap_pages, - h->name); + return ret; +} + +static struct ctl_table hugetlb_vmemmap_sysctls[] = { + { + .procname = "hugetlb_optimize_vmemmap", + .maxlen = sizeof(enum vmemmap_optimize_mode), + .mode = 0644, + .proc_handler = hugetlb_optimize_vmemmap_handler, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE, + }, + { } +}; + +static __init int hugetlb_vmemmap_sysctls_init(void) +{ + /* + * If "memory_hotplug.memmap_on_memory" is enabled or "struct page" + * crosses page boundaries, the vmemmap pages cannot be optimized. + */ + if (!mhp_memmap_on_memory() && is_power_of_2(sizeof(struct page))) + register_sysctl_init("vm", hugetlb_vmemmap_sysctls); + + return 0; } +late_initcall(hugetlb_vmemmap_sysctls_init); +#endif /* CONFIG_PROC_SYSCTL */ |