pagemap: check permissions and capabilities at open time

This patchset makes pagemap useable again in the safe way (after row
hammer bug it was made CAP_SYS_ADMIN-only).  This patchset restores access
for non-privileged users but hides PFNs from them.

Also it adds bit 'map-exclusive' which is set if page is mapped only here:
it helps in estimation of working set without exposing pfns and allows to
distinguish CoWed and non-CoWed private anonymous pages.

Second patch removes page-shift bits and completes migration to the new
pagemap format: flags soft-dirty and mmap-exclusive are available only in
the new format.

This patch (of 5):

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.

See http://lkml.kernel.org/r/CA+55aFyKpWrt_Ajzh1rzp_GcwZ4=6Y=kOv8hBz172CFJp6L8Tg@mail.gmail.com

Signed-off-by: Konstantin Khlebnikov <khlebnikov@yandex-team.ru>
Reviewed-by: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Reviewed-by: Mark Williamson <mwilliamson@undo-software.com>
Tested-by:  Mark Williamson <mwilliamson@undo-software.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index 3b4d825..07c86f5 100644 (file)
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -1229,40 +1229,33 @@ 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;
@@ -1275,10 +1268,10 @@ 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;
 
        /*
@@ -1305,7 +1298,7 @@ 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;
@@ -1315,24 +1308,38 @@ 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;
 }
 
@@ -1340,6 +1347,7 @@ 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 */