linux-next: manual merge of the akpm-current tree with the tip tree

[Stephen Rothwell]

Hi Andrew,

Today's linux-next merge of the akpm-current tree got a conflict in:

  kernel/fork.c

between commit:

  5e28fd0b5fdb ("arch: Allow arch_dup_mmap() to fail")

from the tip tree and commit:

  120bd8608675 ("include/linux/sched/mm.h: uninline mmdrop_async(), etc")

from the akpm-current tree.

I fixed it up (see below) and can carry the fix as necessary. This
is now fixed as far as linux-next is concerned, but any non trivial
conflicts should be mentioned to your upstream maintainer when your tree
is submitted for merging.  You may also want to consider cooperating
with the maintainer of the conflicting tree to minimise any particularly
complex conflicts.

-- 
Cheers,
Stephen Rothwell

diff --cc kernel/fork.c
index bed0eaf7233f,7fccd819866f..000000000000
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@@ -391,6 -391,241 +392,240 @@@ void free_task(struct task_struct *tsk
  }
  EXPORT_SYMBOL(free_task);
  
+ #ifdef CONFIG_MMU
+ static __latent_entropy int dup_mmap(struct mm_struct *mm,
+ 					struct mm_struct *oldmm)
+ {
+ 	struct vm_area_struct *mpnt, *tmp, *prev, **pprev;
+ 	struct rb_node **rb_link, *rb_parent;
+ 	int retval;
+ 	unsigned long charge;
+ 	LIST_HEAD(uf);
+ 
+ 	uprobe_start_dup_mmap();
+ 	if (down_write_killable(&oldmm->mmap_sem)) {
+ 		retval = -EINTR;
+ 		goto fail_uprobe_end;
+ 	}
+ 	flush_cache_dup_mm(oldmm);
+ 	uprobe_dup_mmap(oldmm, mm);
+ 	/*
+ 	 * Not linked in yet - no deadlock potential:
+ 	 */
+ 	down_write_nested(&mm->mmap_sem, SINGLE_DEPTH_NESTING);
+ 
+ 	/* No ordering required: file already has been exposed. */
+ 	RCU_INIT_POINTER(mm->exe_file, get_mm_exe_file(oldmm));
+ 
+ 	mm->total_vm = oldmm->total_vm;
+ 	mm->data_vm = oldmm->data_vm;
+ 	mm->exec_vm = oldmm->exec_vm;
+ 	mm->stack_vm = oldmm->stack_vm;
+ 
+ 	rb_link = &mm->mm_rb.rb_node;
+ 	rb_parent = NULL;
+ 	pprev = &mm->mmap;
+ 	retval = ksm_fork(mm, oldmm);
+ 	if (retval)
+ 		goto out;
+ 	retval = khugepaged_fork(mm, oldmm);
+ 	if (retval)
+ 		goto out;
+ 
+ 	prev = NULL;
+ 	for (mpnt = oldmm->mmap; mpnt; mpnt = mpnt->vm_next) {
+ 		struct file *file;
+ 
+ 		if (mpnt->vm_flags & VM_DONTCOPY) {
+ 			vm_stat_account(mm, mpnt->vm_flags, -vma_pages(mpnt));
+ 			continue;
+ 		}
+ 		charge = 0;
+ 		if (mpnt->vm_flags & VM_ACCOUNT) {
+ 			unsigned long len = vma_pages(mpnt);
+ 
+ 			if (security_vm_enough_memory_mm(oldmm, len)) /* sic */
+ 				goto fail_nomem;
+ 			charge = len;
+ 		}
+ 		tmp = kmem_cache_alloc(vm_area_cachep, GFP_KERNEL);
+ 		if (!tmp)
+ 			goto fail_nomem;
+ 		*tmp = *mpnt;
+ 		INIT_LIST_HEAD(&tmp->anon_vma_chain);
+ 		retval = vma_dup_policy(mpnt, tmp);
+ 		if (retval)
+ 			goto fail_nomem_policy;
+ 		tmp->vm_mm = mm;
+ 		retval = dup_userfaultfd(tmp, &uf);
+ 		if (retval)
+ 			goto fail_nomem_anon_vma_fork;
+ 		if (tmp->vm_flags & VM_WIPEONFORK) {
+ 			/* VM_WIPEONFORK gets a clean slate in the child. */
+ 			tmp->anon_vma = NULL;
+ 			if (anon_vma_prepare(tmp))
+ 				goto fail_nomem_anon_vma_fork;
+ 		} else if (anon_vma_fork(tmp, mpnt))
+ 			goto fail_nomem_anon_vma_fork;
+ 		tmp->vm_flags &= ~(VM_LOCKED | VM_LOCKONFAULT);
+ 		tmp->vm_next = tmp->vm_prev = NULL;
+ 		file = tmp->vm_file;
+ 		if (file) {
+ 			struct inode *inode = file_inode(file);
+ 			struct address_space *mapping = file->f_mapping;
+ 
+ 			get_file(file);
+ 			if (tmp->vm_flags & VM_DENYWRITE)
+ 				atomic_dec(&inode->i_writecount);
+ 			i_mmap_lock_write(mapping);
+ 			if (tmp->vm_flags & VM_SHARED)
+ 				atomic_inc(&mapping->i_mmap_writable);
+ 			flush_dcache_mmap_lock(mapping);
+ 			/* insert tmp into the share list, just after mpnt */
+ 			vma_interval_tree_insert_after(tmp, mpnt,
+ 					&mapping->i_mmap);
+ 			flush_dcache_mmap_unlock(mapping);
+ 			i_mmap_unlock_write(mapping);
+ 		}
+ 
+ 		/*
+ 		 * Clear hugetlb-related page reserves for children. This only
+ 		 * affects MAP_PRIVATE mappings. Faults generated by the child
+ 		 * are not guaranteed to succeed, even if read-only
+ 		 */
+ 		if (is_vm_hugetlb_page(tmp))
+ 			reset_vma_resv_huge_pages(tmp);
+ 
+ 		/*
+ 		 * Link in the new vma and copy the page table entries.
+ 		 */
+ 		*pprev = tmp;
+ 		pprev = &tmp->vm_next;
+ 		tmp->vm_prev = prev;
+ 		prev = tmp;
+ 
+ 		__vma_link_rb(mm, tmp, rb_link, rb_parent);
+ 		rb_link = &tmp->vm_rb.rb_right;
+ 		rb_parent = &tmp->vm_rb;
+ 
+ 		mm->map_count++;
+ 		if (!(tmp->vm_flags & VM_WIPEONFORK))
+ 			retval = copy_page_range(mm, oldmm, mpnt);
+ 
+ 		if (tmp->vm_ops && tmp->vm_ops->open)
+ 			tmp->vm_ops->open(tmp);
+ 
+ 		if (retval)
+ 			goto out;
+ 	}
+ 	/* a new mm has just been created */
 -	arch_dup_mmap(oldmm, mm);
 -	retval = 0;
++	retval = arch_dup_mmap(oldmm, mm);
+ out:
+ 	up_write(&mm->mmap_sem);
+ 	flush_tlb_mm(oldmm);
+ 	up_write(&oldmm->mmap_sem);
+ 	dup_userfaultfd_complete(&uf);
+ fail_uprobe_end:
+ 	uprobe_end_dup_mmap();
+ 	return retval;
+ fail_nomem_anon_vma_fork:
+ 	mpol_put(vma_policy(tmp));
+ fail_nomem_policy:
+ 	kmem_cache_free(vm_area_cachep, tmp);
+ fail_nomem:
+ 	retval = -ENOMEM;
+ 	vm_unacct_memory(charge);
+ 	goto out;
+ }
+ 
+ static inline int mm_alloc_pgd(struct mm_struct *mm)
+ {
+ 	mm->pgd = pgd_alloc(mm);
+ 	if (unlikely(!mm->pgd))
+ 		return -ENOMEM;
+ 	return 0;
+ }
+ 
+ static inline void mm_free_pgd(struct mm_struct *mm)
+ {
+ 	pgd_free(mm, mm->pgd);
+ }
+ #else
+ static int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm)
+ {
+ 	down_write(&oldmm->mmap_sem);
+ 	RCU_INIT_POINTER(mm->exe_file, get_mm_exe_file(oldmm));
+ 	up_write(&oldmm->mmap_sem);
+ 	return 0;
+ }
+ #define mm_alloc_pgd(mm)	(0)
+ #define mm_free_pgd(mm)
+ #endif /* CONFIG_MMU */
+ 
+ static void check_mm(struct mm_struct *mm)
+ {
+ 	int i;
+ 
+ 	for (i = 0; i < NR_MM_COUNTERS; i++) {
+ 		long x = atomic_long_read(&mm->rss_stat.count[i]);
+ 
+ 		if (unlikely(x))
+ 			printk(KERN_ALERT "BUG: Bad rss-counter state "
+ 					  "mm:%p idx:%d val:%ld\n", mm, i, x);
+ 	}
+ 
+ 	if (mm_pgtables_bytes(mm))
+ 		pr_alert("BUG: non-zero pgtables_bytes on freeing mm: %ld\n",
+ 				mm_pgtables_bytes(mm));
+ 
+ #if defined(CONFIG_TRANSPARENT_HUGEPAGE) && !USE_SPLIT_PMD_PTLOCKS
+ 	VM_BUG_ON_MM(mm->pmd_huge_pte, mm);
+ #endif
+ }
+ 
+ #define allocate_mm()	(kmem_cache_alloc(mm_cachep, GFP_KERNEL))
+ #define free_mm(mm)	(kmem_cache_free(mm_cachep, (mm)))
+ 
+ /*
+  * Called when the last reference to the mm
+  * is dropped: either by a lazy thread or by
+  * mmput. Free the page directory and the mm.
+  */
+ static void __mmdrop(struct mm_struct *mm)
+ {
+ 	BUG_ON(mm == &init_mm);
+ 	mm_free_pgd(mm);
+ 	destroy_context(mm);
+ 	hmm_mm_destroy(mm);
+ 	mmu_notifier_mm_destroy(mm);
+ 	check_mm(mm);
+ 	put_user_ns(mm->user_ns);
+ 	free_mm(mm);
+ }
+ 
+ void mmdrop(struct mm_struct *mm)
+ {
+ 	if (unlikely(atomic_dec_and_test(&mm->mm_count)))
+ 		__mmdrop(mm);
+ }
+ EXPORT_SYMBOL_GPL(mmdrop);
+ 
+ static void mmdrop_async_fn(struct work_struct *work)
+ {
+ 	struct mm_struct *mm;
+ 
+ 	mm = container_of(work, struct mm_struct, async_put_work);
+ 	__mmdrop(mm);
+ }
+ 
+ static void mmdrop_async(struct mm_struct *mm)
+ {
+ 	if (unlikely(atomic_dec_and_test(&mm->mm_count))) {
+ 		INIT_WORK(&mm->async_put_work, mmdrop_async_fn);
+ 		schedule_work(&mm->async_put_work);
+ 	}
+ }
+ 
  static inline void free_signal_struct(struct signal_struct *sig)
  {
  	taskstats_tgid_free(sig);