From e9714acf8c439688884234dcac2bfc38bb607d38 Mon Sep 17 00:00:00 2001 From: Konstantin Khlebnikov Date: Mon, 8 Oct 2012 16:28:54 -0700 Subject: mm: kill vma flag VM_EXECUTABLE and mm->num_exe_file_vmas Currently the kernel sets mm->exe_file during sys_execve() and then tracks number of vmas with VM_EXECUTABLE flag in mm->num_exe_file_vmas, as soon as this counter drops to zero kernel resets mm->exe_file to NULL. Plus it resets mm->exe_file at last mmput() when mm->mm_users drops to zero. VMA with VM_EXECUTABLE flag appears after mapping file with flag MAP_EXECUTABLE, such vmas can appears only at sys_execve() or after vma splitting, because sys_mmap ignores this flag. Usually binfmt module sets mm->exe_file and mmaps executable vmas with this file, they hold mm->exe_file while task is running. comment from v2.6.25-6245-g925d1c4 ("procfs task exe symlink"), where all this stuff was introduced: > The kernel implements readlink of /proc/pid/exe by getting the file from > the first executable VMA. Then the path to the file is reconstructed and > reported as the result. > > Because of the VMA walk the code is slightly different on nommu systems. > This patch avoids separate /proc/pid/exe code on nommu systems. Instead of > walking the VMAs to find the first executable file-backed VMA we store a > reference to the exec'd file in the mm_struct. > > That reference would prevent the filesystem holding the executable file > from being unmounted even after unmapping the VMAs. So we track the number > of VM_EXECUTABLE VMAs and drop the new reference when the last one is > unmapped. This avoids pinning the mounted filesystem. exe_file's vma accounting is hooked into every file mmap/unmmap and vma split/merge just to fix some hypothetical pinning fs from umounting by mm, which already unmapped all its executable files, but still alive. Seems like currently nobody depends on this behaviour. We can try to remove this logic and keep mm->exe_file until final mmput(). mm->exe_file is still protected with mm->mmap_sem, because we want to change it via new sys_prctl(PR_SET_MM_EXE_FILE). Also via this syscall task can change its mm->exe_file and unpin mountpoint explicitly. Signed-off-by: Konstantin Khlebnikov Cc: Alexander Viro Cc: Carsten Otte Cc: Chris Metcalf Cc: Cyrill Gorcunov Cc: Eric Paris Cc: H. Peter Anvin Cc: Hugh Dickins Cc: Ingo Molnar Cc: James Morris Cc: Jason Baron Cc: Kentaro Takeda Cc: Matt Helsley Cc: Nick Piggin Cc: Oleg Nesterov Cc: Peter Zijlstra Cc: Robert Richter Cc: Suresh Siddha Cc: Tetsuo Handa Cc: Venkatesh Pallipadi Acked-by: Linus Torvalds Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/mmap.c | 25 ++++--------------------- mm/nommu.c | 11 +---------- 2 files changed, 5 insertions(+), 31 deletions(-) (limited to 'mm') diff --git a/mm/mmap.c b/mm/mmap.c index d0686d355113..c1ad2e78ea58 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -231,11 +231,8 @@ static struct vm_area_struct *remove_vma(struct vm_area_struct *vma) might_sleep(); if (vma->vm_ops && vma->vm_ops->close) vma->vm_ops->close(vma); - if (vma->vm_file) { + if (vma->vm_file) fput(vma->vm_file); - if (vma->vm_flags & VM_EXECUTABLE) - removed_exe_file_vma(vma->vm_mm); - } mpol_put(vma_policy(vma)); kmem_cache_free(vm_area_cachep, vma); return next; @@ -636,8 +633,6 @@ again: remove_next = 1 + (end > next->vm_end); if (file) { uprobe_munmap(next, next->vm_start, next->vm_end); fput(file); - if (next->vm_flags & VM_EXECUTABLE) - removed_exe_file_vma(mm); } if (next->anon_vma) anon_vma_merge(vma, next); @@ -1304,8 +1299,6 @@ munmap_back: error = file->f_op->mmap(file, vma); if (error) goto unmap_and_free_vma; - if (vm_flags & VM_EXECUTABLE) - added_exe_file_vma(mm); /* Can addr have changed?? * @@ -1987,11 +1980,8 @@ static int __split_vma(struct mm_struct * mm, struct vm_area_struct * vma, if (anon_vma_clone(new, vma)) goto out_free_mpol; - if (new->vm_file) { + if (new->vm_file) get_file(new->vm_file); - if (vma->vm_flags & VM_EXECUTABLE) - added_exe_file_vma(mm); - } if (new->vm_ops && new->vm_ops->open) new->vm_ops->open(new); @@ -2009,11 +1999,8 @@ static int __split_vma(struct mm_struct * mm, struct vm_area_struct * vma, /* Clean everything up if vma_adjust failed. */ if (new->vm_ops && new->vm_ops->close) new->vm_ops->close(new); - if (new->vm_file) { - if (vma->vm_flags & VM_EXECUTABLE) - removed_exe_file_vma(mm); + if (new->vm_file) fput(new->vm_file); - } unlink_anon_vmas(new); out_free_mpol: mpol_put(pol); @@ -2408,12 +2395,8 @@ struct vm_area_struct *copy_vma(struct vm_area_struct **vmap, new_vma->vm_start = addr; new_vma->vm_end = addr + len; new_vma->vm_pgoff = pgoff; - if (new_vma->vm_file) { + if (new_vma->vm_file) get_file(new_vma->vm_file); - - if (vma->vm_flags & VM_EXECUTABLE) - added_exe_file_vma(mm); - } if (new_vma->vm_ops && new_vma->vm_ops->open) new_vma->vm_ops->open(new_vma); vma_link(mm, new_vma, prev, rb_link, rb_parent); diff --git a/mm/nommu.c b/mm/nommu.c index 98318dcff742..9c4a7b63a4df 100644 --- a/mm/nommu.c +++ b/mm/nommu.c @@ -789,11 +789,8 @@ static void delete_vma(struct mm_struct *mm, struct vm_area_struct *vma) kenter("%p", vma); if (vma->vm_ops && vma->vm_ops->close) vma->vm_ops->close(vma); - if (vma->vm_file) { + if (vma->vm_file) fput(vma->vm_file); - if (vma->vm_flags & VM_EXECUTABLE) - removed_exe_file_vma(mm); - } put_nommu_region(vma->vm_region); kmem_cache_free(vm_area_cachep, vma); } @@ -1284,10 +1281,6 @@ unsigned long do_mmap_pgoff(struct file *file, if (file) { region->vm_file = get_file(file); vma->vm_file = get_file(file); - if (vm_flags & VM_EXECUTABLE) { - added_exe_file_vma(current->mm); - vma->vm_mm = current->mm; - } } down_write(&nommu_region_sem); @@ -1440,8 +1433,6 @@ error: kmem_cache_free(vm_region_jar, region); if (vma->vm_file) fput(vma->vm_file); - if (vma->vm_flags & VM_EXECUTABLE) - removed_exe_file_vma(vma->vm_mm); kmem_cache_free(vm_area_cachep, vma); kleave(" = %d", ret); return ret; -- cgit v1.2.1