Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1753318AbbGNPjh (ORCPT ); Tue, 14 Jul 2015 11:39:37 -0400 Received: from forward-corp1g.mail.yandex.net ([95.108.253.251]:50230 "EHLO forward-corp1g.mail.yandex.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752481AbbGNPhj (ORCPT ); Tue, 14 Jul 2015 11:37:39 -0400 Authentication-Results: smtpcorp4.mail.yandex.net; dkim=pass header.i=@yandex-team.ru Subject: [PATCH v4 1/5] pagemap: check permissions and capabilities at open time From: Konstantin Khlebnikov To: linux-mm@kvack.org, Andrew Morton , Naoya Horiguchi Cc: "Kirill A. Shutemov" , Mark Williamson , linux-kernel@vger.kernel.org, linux-api@vger.kernel.org Date: Tue, 14 Jul 2015 18:37:35 +0300 Message-ID: <20150714153735.29844.38428.stgit@buzz> In-Reply-To: <20150714152516.29844.69929.stgit@buzz> References: <20150714152516.29844.69929.stgit@buzz> User-Agent: StGit/0.17.1-dirty MIME-Version: 1.0 Content-Type: text/plain; charset="utf-8" Content-Transfer-Encoding: 7bit Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 4031 Lines: 141 This patch moves permission checks from pagemap_read() into pagemap_open(). Pointer to mm is saved in file->private_data. This reference pins only mm_struct itself. /proc/*/mem, maps, smaps already work in the same way. Signed-off-by: Konstantin Khlebnikov Link: http://lkml.kernel.org/r/CA+55aFyKpWrt_Ajzh1rzp_GcwZ4=6Y=kOv8hBz172CFJp6L8Tg@mail.gmail.com --- fs/proc/task_mmu.c | 48 ++++++++++++++++++++++++++++-------------------- 1 file changed, 28 insertions(+), 20 deletions(-) diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index ca1e091881d4..270bf7cbc8a5 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -1227,40 +1227,33 @@ static int pagemap_hugetlb_range(pte_t *pte, unsigned long hmask, 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_inode(file)); - struct mm_struct *mm; + struct mm_struct *mm = file->private_data; struct pagemapread pm; - 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; + int ret = 0, copied = 0; - if (!task) + if (!mm || !atomic_inc_not_zero(&mm->mm_users)) goto out; ret = -EINVAL; /* file position must be aligned */ if ((*ppos % PM_ENTRY_BYTES) || (count % PM_ENTRY_BYTES)) - goto out_task; + goto out_mm; ret = 0; if (!count) - goto out_task; + goto out_mm; pm.v2 = soft_dirty_cleared; pm.len = (PAGEMAP_WALK_SIZE >> PAGE_SHIFT); pm.buffer = kmalloc(pm.len * PM_ENTRY_BYTES, GFP_TEMPORARY); ret = -ENOMEM; if (!pm.buffer) - goto out_task; - - mm = mm_access(task, PTRACE_MODE_READ); - ret = PTR_ERR(mm); - if (!mm || IS_ERR(mm)) - goto out_free; + goto out_mm; pagemap_walk.pmd_entry = pagemap_pte_range; pagemap_walk.pte_hole = pagemap_pte_hole; @@ -1273,10 +1266,10 @@ static ssize_t pagemap_read(struct file *file, char __user *buf, src = *ppos; svpfn = src / PM_ENTRY_BYTES; start_vaddr = svpfn << PAGE_SHIFT; - end_vaddr = TASK_SIZE_OF(task); + end_vaddr = mm->task_size; /* watch out for wraparound */ - if (svpfn > TASK_SIZE_OF(task) >> PAGE_SHIFT) + if (svpfn > mm->task_size >> PAGE_SHIFT) start_vaddr = end_vaddr; /* @@ -1303,7 +1296,7 @@ static ssize_t pagemap_read(struct file *file, char __user *buf, len = min(count, PM_ENTRY_BYTES * pm.pos); if (copy_to_user(buf, pm.buffer, len)) { ret = -EFAULT; - goto out_mm; + goto out_free; } copied += len; buf += len; @@ -1313,24 +1306,38 @@ static ssize_t pagemap_read(struct file *file, char __user *buf, if (!ret || ret == PM_END_OF_BUFFER) ret = copied; -out_mm: - mmput(mm); out_free: kfree(pm.buffer); -out_task: - put_task_struct(task); +out_mm: + mmput(mm); out: return ret; } static int pagemap_open(struct inode *inode, struct file *file) { + struct mm_struct *mm; + /* do not disclose physical addresses: attack vector */ if (!capable(CAP_SYS_ADMIN)) return -EPERM; pr_warn_once("Bits 55-60 of /proc/PID/pagemap entries are about " "to stop being page-shift some time soon. See the " "linux/Documentation/vm/pagemap.txt for details.\n"); + + mm = proc_mem_open(inode, PTRACE_MODE_READ); + if (IS_ERR(mm)) + return PTR_ERR(mm); + file->private_data = mm; + return 0; +} + +static int pagemap_release(struct inode *inode, struct file *file) +{ + struct mm_struct *mm = file->private_data; + + if (mm) + mmdrop(mm); return 0; } @@ -1338,6 +1345,7 @@ const struct file_operations proc_pagemap_operations = { .llseek = mem_lseek, /* borrow this */ .read = pagemap_read, .open = pagemap_open, + .release = pagemap_release, }; #endif /* CONFIG_PROC_PAGE_MONITOR */ -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/