diff options
Diffstat (limited to 'fs/proc/task_mmu.c')
| -rw-r--r-- | fs/proc/task_mmu.c | 234 |
1 files changed, 234 insertions, 0 deletions
diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index 200e3b29aa22..6a44fb94228c 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -14,6 +14,8 @@ #include <linux/swapops.h> #include <linux/mmu_notifier.h> #include <linux/page_idle.h> +#include <linux/mm_inline.h> +#include <linux/ctype.h> #include <asm/elf.h> #include <asm/uaccess.h> @@ -1420,6 +1422,238 @@ const struct file_operations proc_pagemap_operations = { }; #endif /* CONFIG_PROC_PAGE_MONITOR */ +#ifdef CONFIG_PROCESS_RECLAIM +static int reclaim_pte_range(pmd_t *pmd, unsigned long addr, + unsigned long end, struct mm_walk *walk) +{ + struct reclaim_param *rp = walk->private; + struct vm_area_struct *vma = rp->vma; + pte_t *pte, ptent; + spinlock_t *ptl; + struct page *page; + LIST_HEAD(page_list); + int isolated; + int reclaimed; + + split_huge_page_pmd(vma, addr, pmd); + if (pmd_trans_unstable(pmd) || !rp->nr_to_reclaim) + return 0; +cont: + isolated = 0; + pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl); + for (; addr != end; pte++, addr += PAGE_SIZE) { + ptent = *pte; + if (!pte_present(ptent)) + continue; + + page = vm_normal_page(vma, addr, ptent); + if (!page) + continue; + + if (isolate_lru_page(page)) + continue; + + list_add(&page->lru, &page_list); + inc_zone_page_state(page, NR_ISOLATED_ANON + + page_is_file_cache(page)); + isolated++; + rp->nr_scanned++; + if ((isolated >= SWAP_CLUSTER_MAX) || !rp->nr_to_reclaim) + break; + } + pte_unmap_unlock(pte - 1, ptl); + reclaimed = reclaim_pages_from_list(&page_list, vma); + rp->nr_reclaimed += reclaimed; + rp->nr_to_reclaim -= reclaimed; + if (rp->nr_to_reclaim < 0) + rp->nr_to_reclaim = 0; + + if (rp->nr_to_reclaim && (addr != end)) + goto cont; + + cond_resched(); + return 0; +} + +enum reclaim_type { + RECLAIM_FILE, + RECLAIM_ANON, + RECLAIM_ALL, + RECLAIM_RANGE, +}; + +struct reclaim_param reclaim_task_anon(struct task_struct *task, + int nr_to_reclaim) +{ + struct mm_struct *mm; + struct vm_area_struct *vma; + struct mm_walk reclaim_walk = {}; + struct reclaim_param rp; + + rp.nr_reclaimed = 0; + rp.nr_scanned = 0; + get_task_struct(task); + mm = get_task_mm(task); + if (!mm) + goto out; + + reclaim_walk.mm = mm; + reclaim_walk.pmd_entry = reclaim_pte_range; + + rp.nr_to_reclaim = nr_to_reclaim; + reclaim_walk.private = &rp; + + down_read(&mm->mmap_sem); + for (vma = mm->mmap; vma; vma = vma->vm_next) { + if (is_vm_hugetlb_page(vma)) + continue; + + if (vma->vm_file) + continue; + + if (!rp.nr_to_reclaim) + break; + + rp.vma = vma; + walk_page_range(vma->vm_start, vma->vm_end, + &reclaim_walk); + } + + flush_tlb_mm(mm); + up_read(&mm->mmap_sem); + mmput(mm); +out: + put_task_struct(task); + return rp; +} + +static ssize_t reclaim_write(struct file *file, const char __user *buf, + size_t count, loff_t *ppos) +{ + struct task_struct *task; + char buffer[200]; + struct mm_struct *mm; + struct vm_area_struct *vma; + enum reclaim_type type; + char *type_buf; + struct mm_walk reclaim_walk = {}; + unsigned long start = 0; + unsigned long end = 0; + struct reclaim_param rp; + + memset(buffer, 0, sizeof(buffer)); + if (count > sizeof(buffer) - 1) + count = sizeof(buffer) - 1; + + if (copy_from_user(buffer, buf, count)) + return -EFAULT; + + type_buf = strstrip(buffer); + if (!strcmp(type_buf, "file")) + type = RECLAIM_FILE; + else if (!strcmp(type_buf, "anon")) + type = RECLAIM_ANON; + else if (!strcmp(type_buf, "all")) + type = RECLAIM_ALL; + else if (isdigit(*type_buf)) + type = RECLAIM_RANGE; + else + goto out_err; + + if (type == RECLAIM_RANGE) { + char *token; + unsigned long long len, len_in, tmp; + token = strsep(&type_buf, " "); + if (!token) + goto out_err; + tmp = memparse(token, &token); + if (tmp & ~PAGE_MASK || tmp > ULONG_MAX) + goto out_err; + start = tmp; + + token = strsep(&type_buf, " "); + if (!token) + goto out_err; + len_in = memparse(token, &token); + len = (len_in + ~PAGE_MASK) & PAGE_MASK; + if (len > ULONG_MAX) + goto out_err; + /* + * Check to see whether len was rounded up from small -ve + * to zero. + */ + if (len_in && !len) + goto out_err; + + end = start + len; + if (end < start) + goto out_err; + } + + task = get_proc_task(file->f_path.dentry->d_inode); + if (!task) + return -ESRCH; + + mm = get_task_mm(task); + if (!mm) + goto out; + + reclaim_walk.mm = mm; + reclaim_walk.pmd_entry = reclaim_pte_range; + + rp.nr_to_reclaim = ~0; + rp.nr_reclaimed = 0; + reclaim_walk.private = &rp; + + down_read(&mm->mmap_sem); + if (type == RECLAIM_RANGE) { + vma = find_vma(mm, start); + while (vma) { + if (vma->vm_start > end) + break; + if (is_vm_hugetlb_page(vma)) + continue; + + rp.vma = vma; + walk_page_range(max(vma->vm_start, start), + min(vma->vm_end, end), + &reclaim_walk); + vma = vma->vm_next; + } + } else { + for (vma = mm->mmap; vma; vma = vma->vm_next) { + if (is_vm_hugetlb_page(vma)) + continue; + + if (type == RECLAIM_ANON && vma->vm_file) + continue; + + if (type == RECLAIM_FILE && !vma->vm_file) + continue; + + rp.vma = vma; + walk_page_range(vma->vm_start, vma->vm_end, + &reclaim_walk); + } + } + + flush_tlb_mm(mm); + up_read(&mm->mmap_sem); + mmput(mm); +out: + put_task_struct(task); + return count; + +out_err: + return -EINVAL; +} + +const struct file_operations proc_reclaim_operations = { + .write = reclaim_write, + .llseek = noop_llseek, +}; +#endif + #ifdef CONFIG_NUMA struct numa_maps { |