From b95c35e76b29ba812e5dabdd91592e25ec640e93 Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Thu, 1 Apr 2010 15:13:57 +0200 Subject: oom: fix the unsafe usage of badness() in proc_oom_score() proc_oom_score(task) has a reference to task_struct, but that is all. If this task was already released before we take tasklist_lock - we can't use task->group_leader, it points to nowhere - it is not safe to call badness() even if this task is ->group_leader, has_intersects_mems_allowed() assumes it is safe to iterate over ->thread_group list. - even worse, badness() can hit ->signal == NULL Add the pid_alive() check to ensure __unhash_process() was not called. Also, use "task" instead of task->group_leader. badness() should return the same result for any sub-thread. Currently this is not true, but this should be changed anyway. Signed-off-by: Oleg Nesterov Cc: stable@kernel.org Signed-off-by: Linus Torvalds --- fs/proc/base.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'fs/proc') diff --git a/fs/proc/base.c b/fs/proc/base.c index a7310841c831..b1f6e62773d3 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -442,12 +442,13 @@ static const struct file_operations proc_lstats_operations = { unsigned long badness(struct task_struct *p, unsigned long uptime); static int proc_oom_score(struct task_struct *task, char *buffer) { - unsigned long points; + unsigned long points = 0; struct timespec uptime; do_posix_clock_monotonic_gettime(&uptime); read_lock(&tasklist_lock); - points = badness(task->group_leader, uptime.tv_sec); + if (pid_alive(task)) + points = badness(task, uptime.tv_sec); read_unlock(&tasklist_lock); return sprintf(buffer, "%lu\n", points); } -- cgit v1.2.3 From d82ef020cf31504c816803b1def94eb5ff173363 Mon Sep 17 00:00:00 2001 From: KAMEZAWA Hiroyuki Date: Fri, 2 Apr 2010 09:11:29 +0900 Subject: proc: pagemap: Hold mmap_sem during page walk In initial design, walk_page_range() was designed just for walking page table and it didn't require mmap_sem. Now, find_vma() etc.. are used in walk_page_range() and we need mmap_sem around it. This patch adds mmap_sem around walk_page_range(). Because /proc//pagemap's callback routine use put_user(), we have to get rid of it to do sane fix. Changelog: 2010/Apr/2 - fixed start_vaddr and end overflow Changelog: 2010/Apr/1 - fixed start_vaddr calculation - removed unnecessary cast. - removed unnecessary change in smaps. - use GFP_TEMPORARY instead of GFP_KERNEL Signed-off-by: KAMEZAWA Hiroyuki Cc: Matt Mackall Cc: KOSAKI Motohiro Cc: San Mehat Cc: Brian Swetland Cc: Dave Hansen Cc: Andrew Morton [ Fixed kmalloc failure return code as per Matt ] Signed-off-by: Linus Torvalds --- fs/proc/task_mmu.c | 87 ++++++++++++++++++++++++------------------------------ 1 file changed, 38 insertions(+), 49 deletions(-) (limited to 'fs/proc') diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index 183f8ff5f400..096273984c3b 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -406,6 +406,7 @@ static int show_smap(struct seq_file *m, void *v) memset(&mss, 0, sizeof mss); mss.vma = vma; + /* mmap_sem is held in m_start */ if (vma->vm_mm && !is_vm_hugetlb_page(vma)) walk_page_range(vma->vm_start, vma->vm_end, &smaps_walk); @@ -552,7 +553,8 @@ const struct file_operations proc_clear_refs_operations = { }; struct pagemapread { - u64 __user *out, *end; + int pos, len; + u64 *buffer; }; #define PM_ENTRY_BYTES sizeof(u64) @@ -575,10 +577,8 @@ struct pagemapread { static int add_to_pagemap(unsigned long addr, u64 pfn, struct pagemapread *pm) { - if (put_user(pfn, pm->out)) - return -EFAULT; - pm->out++; - if (pm->out >= pm->end) + pm->buffer[pm->pos++] = pfn; + if (pm->pos >= pm->len) return PM_END_OF_BUFFER; return 0; } @@ -720,21 +720,20 @@ static int pagemap_hugetlb_range(pte_t *pte, unsigned long addr, * determine which areas of memory are actually mapped and llseek to * skip over unmapped regions. */ +#define PAGEMAP_WALK_SIZE (PMD_SIZE) static ssize_t pagemap_read(struct file *file, char __user *buf, size_t count, loff_t *ppos) { struct task_struct *task = get_proc_task(file->f_path.dentry->d_inode); - struct page **pages, *page; - unsigned long uaddr, uend; struct mm_struct *mm; struct pagemapread pm; - int pagecount; int ret = -ESRCH; struct mm_walk pagemap_walk = {}; unsigned long src; unsigned long svpfn; unsigned long start_vaddr; unsigned long end_vaddr; + int copied = 0; if (!task) goto out; @@ -757,35 +756,12 @@ static ssize_t pagemap_read(struct file *file, char __user *buf, if (!mm) goto out_task; - - uaddr = (unsigned long)buf & PAGE_MASK; - uend = (unsigned long)(buf + count); - pagecount = (PAGE_ALIGN(uend) - uaddr) / PAGE_SIZE; - ret = 0; - if (pagecount == 0) - goto out_mm; - pages = kcalloc(pagecount, sizeof(struct page *), GFP_KERNEL); + pm.len = PM_ENTRY_BYTES * (PAGEMAP_WALK_SIZE >> PAGE_SHIFT); + pm.buffer = kmalloc(pm.len, GFP_TEMPORARY); ret = -ENOMEM; - if (!pages) + if (!pm.buffer) goto out_mm; - down_read(¤t->mm->mmap_sem); - ret = get_user_pages(current, current->mm, uaddr, pagecount, - 1, 0, pages, NULL); - up_read(¤t->mm->mmap_sem); - - if (ret < 0) - goto out_free; - - if (ret != pagecount) { - pagecount = ret; - ret = -EFAULT; - goto out_pages; - } - - pm.out = (u64 __user *)buf; - pm.end = (u64 __user *)(buf + count); - pagemap_walk.pmd_entry = pagemap_pte_range; pagemap_walk.pte_hole = pagemap_pte_hole; pagemap_walk.hugetlb_entry = pagemap_hugetlb_range; @@ -807,23 +783,36 @@ static ssize_t pagemap_read(struct file *file, char __user *buf, * user buffer is tracked in "pm", and the walk * will stop when we hit the end of the buffer. */ - ret = walk_page_range(start_vaddr, end_vaddr, &pagemap_walk); - if (ret == PM_END_OF_BUFFER) - ret = 0; - /* don't need mmap_sem for these, but this looks cleaner */ - *ppos += (char __user *)pm.out - buf; - if (!ret) - ret = (char __user *)pm.out - buf; - -out_pages: - for (; pagecount; pagecount--) { - page = pages[pagecount-1]; - if (!PageReserved(page)) - SetPageDirty(page); - page_cache_release(page); + ret = 0; + while (count && (start_vaddr < end_vaddr)) { + int len; + unsigned long end; + + pm.pos = 0; + end = start_vaddr + PAGEMAP_WALK_SIZE; + /* overflow ? */ + if (end < start_vaddr || end > end_vaddr) + end = end_vaddr; + down_read(&mm->mmap_sem); + ret = walk_page_range(start_vaddr, end, &pagemap_walk); + up_read(&mm->mmap_sem); + start_vaddr = end; + + len = min(count, PM_ENTRY_BYTES * pm.pos); + if (copy_to_user(buf, pm.buffer, len) < 0) { + ret = -EFAULT; + goto out_free; + } + copied += len; + buf += len; + count -= len; } + *ppos += copied; + if (!ret || ret == PM_END_OF_BUFFER) + ret = copied; + out_free: - kfree(pages); + kfree(pm.buffer); out_mm: mmput(mm); out_task: -- cgit v1.2.3