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

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

[Stephen Rothwell]

[-- Attachment #1: Type: text/plain, Size: 1536 bytes --]

Hi all,

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

  include/linux/mm.h

between commit:

  de2860f46362 ("mm: Add kvrealloc()")

from the xfs tree and commit:

  dcda39e2fd16 ("mm: move kvmalloc-related functions to slab.h")

from the akpm-current tree.

I fixed it up (I moved it to slab.h like the latter did with the other
functions - 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.

From: Stephen Rothwell <sfr@canb.auug.org.au>
Date: Wed, 11 Aug 2021 18:30:48 +1000
Subject: [PATCH] move kvrealloc to slab.h as well

Signed-off-by: Stephen Rothwell <sfr@canb.auug.org.au>
---
 include/linux/slab.h | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/include/linux/slab.h b/include/linux/slab.h
index 2c0d80cca6b8..05b8a316dc33 100644
--- a/include/linux/slab.h
+++ b/include/linux/slab.h
@@ -761,6 +761,8 @@ static inline void *kvcalloc(size_t n, size_t size, gfp_t flags)
 	return kvmalloc_array(n, size, flags | __GFP_ZERO);
 }
 
+void *kvrealloc(const void *p, size_t oldsize, size_t newsize,
+		gfp_t flags);
 void kvfree(const void *addr);
 void kvfree_sensitive(const void *addr, size_t len);
 
-- 
2.30.2

-- 
Cheers,
Stephen Rothwell

[-- Attachment #2: OpenPGP digital signature --]
[-- Type: application/pgp-signature, Size: 488 bytes --]

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

[Stephen Rothwell]

Hi Andrew,

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

  include/linux/iomap.h

between commit:

  8ff6daa17b6a ("iomap: constify struct iomap_ops")

from the xfs tree and commit:

  d6fb008f420c ("mm, fs: reduce fault, page_mkwrite, and pfn_mkwrite to take only vmf")

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 include/linux/iomap.h
index 891459caa278,857e440af9d5..000000000000
--- a/include/linux/iomap.h
+++ b/include/linux/iomap.h
@@@ -72,17 -72,16 +72,16 @@@ struct iomap_ops 
  };
  
  ssize_t iomap_file_buffered_write(struct kiocb *iocb, struct iov_iter *from,
 -		struct iomap_ops *ops);
 +		const struct iomap_ops *ops);
  int iomap_file_dirty(struct inode *inode, loff_t pos, loff_t len,
 -		struct iomap_ops *ops);
 +		const struct iomap_ops *ops);
  int iomap_zero_range(struct inode *inode, loff_t pos, loff_t len,
 -		bool *did_zero, struct iomap_ops *ops);
 +		bool *did_zero, const struct iomap_ops *ops);
  int iomap_truncate_page(struct inode *inode, loff_t pos, bool *did_zero,
 -		struct iomap_ops *ops);
 -int iomap_page_mkwrite(struct vm_fault *vmf, struct iomap_ops *ops);
 +		const struct iomap_ops *ops);
- int iomap_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf,
- 		const struct iomap_ops *ops);
++int iomap_page_mkwrite(struct vm_fault *vmf, const struct iomap_ops *ops);
  int iomap_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
 -		loff_t start, loff_t len, struct iomap_ops *ops);
 +		loff_t start, loff_t len, const struct iomap_ops *ops);
  
  /*
   * Flags for direct I/O ->end_io:

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

[Stephen Rothwell]

Hi Andrew,

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

  include/linux/dax.h

between commit:

  8ff6daa17b6a ("omap: constify struct iomap_ops")

from the xfs tree and commits:

  d6fb008f420c ("mm, fs: reduce fault, page_mkwrite, and pfn_mkwrite to take only vmf")
  db09ccff3e4e ("mm: replace FAULT_FLAG_SIZE with parameter to huge_fault")

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 include/linux/dax.h
index 2983e52efd07,df63730e86d2..000000000000
--- a/include/linux/dax.h
+++ b/include/linux/dax.h
@@@ -37,9 -37,9 +37,9 @@@ static inline void *dax_radix_locked_en
  }
  
  ssize_t dax_iomap_rw(struct kiocb *iocb, struct iov_iter *iter,
 -		struct iomap_ops *ops);
 +		const struct iomap_ops *ops);
- int dax_iomap_fault(struct vm_area_struct *vma, struct vm_fault *vmf,
- 			const struct iomap_ops *ops);
+ int dax_iomap_fault(struct vm_fault *vmf, enum page_entry_size pe_size,
 -		struct iomap_ops *ops);
++		const struct iomap_ops *ops);
  int dax_delete_mapping_entry(struct address_space *mapping, pgoff_t index);
  int dax_invalidate_mapping_entry(struct address_space *mapping, pgoff_t index);
  int dax_invalidate_mapping_entry_sync(struct address_space *mapping,

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

[Stephen Rothwell]

Hi Andrew,

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

  fs/iomap.c

between commit:

  8ff6daa17b6a ("iomap: constify struct iomap_ops")

from the xfs tree and commit:

  d6fb008f420c ("mm, fs: reduce fault, page_mkwrite, and pfn_mkwrite to take only vmf")

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 fs/iomap.c
index d89f70bbb952,ccba165bed49..000000000000
--- a/fs/iomap.c
+++ b/fs/iomap.c
@@@ -445,11 -445,10 +445,10 @@@ iomap_page_mkwrite_actor(struct inode *
  	return length;
  }
  
- int iomap_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf,
- 		const struct iomap_ops *ops)
 -int iomap_page_mkwrite(struct vm_fault *vmf, struct iomap_ops *ops)
++int iomap_page_mkwrite(struct vm_fault *vmf, const struct iomap_ops *ops)
  {
  	struct page *page = vmf->page;
- 	struct inode *inode = file_inode(vma->vm_file);
+ 	struct inode *inode = file_inode(vmf->vma->vm_file);
  	unsigned long length;
  	loff_t offset, size;
  	ssize_t ret;

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

[Stephen Rothwell]

Hi Andrew,

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

  fs/dax.c

between commit:

  8ff6daa17b6a ("iomap: constify struct iomap_ops")

from the xfs tree and commit:

  5dce5c335124 ("mm,fs,dax: change ->pmd_fault to ->huge_fault")

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 fs/dax.c
index 99b5b4458a78,97b8ecbed1c4..000000000000
--- a/fs/dax.c
+++ b/fs/dax.c
@@@ -1116,20 -1114,9 +1118,9 @@@ static int dax_fault_return(int error
  	return VM_FAULT_SIGBUS;
  }
  
- /**
-  * dax_iomap_fault - handle a page fault on a DAX file
-  * @vma: The virtual memory area where the fault occurred
-  * @vmf: The description of the fault
-  * @ops: iomap ops passed from the file system
-  *
-  * When a page fault occurs, filesystems may call this helper in their fault
-  * or mkwrite handler for DAX files. Assumes the caller has done all the
-  * necessary locking for the page fault to proceed successfully.
-  */
- int dax_iomap_fault(struct vm_area_struct *vma, struct vm_fault *vmf,
- 			const struct iomap_ops *ops)
 -static int dax_iomap_pte_fault(struct vm_fault *vmf, struct iomap_ops *ops)
++static int dax_iomap_pte_fault(struct vm_fault *vmf, const struct iomap_ops *ops)
  {
- 	struct address_space *mapping = vma->vm_file->f_mapping;
+ 	struct address_space *mapping = vmf->vma->vm_file->f_mapping;
  	struct inode *inode = mapping->host;
  	unsigned long vaddr = vmf->address;
  	loff_t pos = (loff_t)vmf->pgoff << PAGE_SHIFT;
@@@ -1309,28 -1300,33 +1304,33 @@@ static int dax_pmd_load_hole(struct vm_
  	ret = dax_insert_mapping_entry(mapping, vmf, *entryp, 0,
  			RADIX_DAX_PMD | RADIX_DAX_HZP);
  	if (IS_ERR(ret))
- 		return VM_FAULT_FALLBACK;
+ 		goto fallback;
  	*entryp = ret;
  
- 	ptl = pmd_lock(vma->vm_mm, pmd);
- 	if (!pmd_none(*pmd)) {
+ 	ptl = pmd_lock(vmf->vma->vm_mm, vmf->pmd);
+ 	if (!pmd_none(*(vmf->pmd))) {
  		spin_unlock(ptl);
- 		return VM_FAULT_FALLBACK;
+ 		goto fallback;
  	}
  
- 	pmd_entry = mk_pmd(zero_page, vma->vm_page_prot);
+ 	pmd_entry = mk_pmd(zero_page, vmf->vma->vm_page_prot);
  	pmd_entry = pmd_mkhuge(pmd_entry);
- 	set_pmd_at(vma->vm_mm, pmd_addr, pmd, pmd_entry);
+ 	set_pmd_at(vmf->vma->vm_mm, pmd_addr, vmf->pmd, pmd_entry);
  	spin_unlock(ptl);
+ 	trace_dax_pmd_load_hole(inode, vmf, zero_page, ret);
  	return VM_FAULT_NOPAGE;
+ 
+ fallback:
+ 	trace_dax_pmd_load_hole_fallback(inode, vmf, zero_page, ret);
+ 	return VM_FAULT_FALLBACK;
  }
  
- int dax_iomap_pmd_fault(struct vm_area_struct *vma, unsigned long address,
- 		pmd_t *pmd, unsigned int flags, const struct iomap_ops *ops)
 -static int dax_iomap_pmd_fault(struct vm_fault *vmf, struct iomap_ops *ops)
++static int dax_iomap_pmd_fault(struct vm_fault *vmf, const struct iomap_ops *ops)
  {
+ 	struct vm_area_struct *vma = vmf->vma;
  	struct address_space *mapping = vma->vm_file->f_mapping;
- 	unsigned long pmd_addr = address & PMD_MASK;
- 	bool write = flags & FAULT_FLAG_WRITE;
+ 	unsigned long pmd_addr = vmf->address & PMD_MASK;
+ 	bool write = vmf->flags & FAULT_FLAG_WRITE;
  	unsigned int iomap_flags = (write ? IOMAP_WRITE : 0) | IOMAP_FAULT;
  	struct inode *inode = mapping->host;
  	int result = VM_FAULT_FALLBACK;
@@@ -1429,10 -1422,40 +1426,40 @@@
  	}
   fallback:
  	if (result == VM_FAULT_FALLBACK) {
- 		split_huge_pmd(vma, pmd, address);
+ 		split_huge_pmd(vma, vmf->pmd, vmf->address);
  		count_vm_event(THP_FAULT_FALLBACK);
  	}
+ out:
+ 	trace_dax_pmd_fault_done(inode, vmf, max_pgoff, result);
  	return result;
  }
- EXPORT_SYMBOL_GPL(dax_iomap_pmd_fault);
+ #else
 -static int dax_iomap_pmd_fault(struct vm_fault *vmf, struct iomap_ops *ops)
++static int dax_iomap_pmd_fault(struct vm_fault *vmf, const struct iomap_ops *ops)
+ {
+ 	return VM_FAULT_FALLBACK;
+ }
  #endif /* CONFIG_FS_DAX_PMD */
+ 
+ /**
+  * dax_iomap_fault - handle a page fault on a DAX file
+  * @vmf: The description of the fault
+  * @ops: iomap ops passed from the file system
+  *
+  * When a page fault occurs, filesystems may call this helper in
+  * their fault handler for DAX files. dax_iomap_fault() assumes the caller
+  * has done all the necessary locking for page fault to proceed
+  * successfully.
+  */
+ int dax_iomap_fault(struct vm_fault *vmf, enum page_entry_size pe_size,
 -		struct iomap_ops *ops)
++		const struct iomap_ops *ops)
+ {
+ 	switch (pe_size) {
+ 	case PE_SIZE_PTE:
+ 		return dax_iomap_pte_fault(vmf, ops);
+ 	case PE_SIZE_PMD:
+ 		return dax_iomap_pmd_fault(vmf, ops);
+ 	default:
+ 		return VM_FAULT_FALLBACK;
+ 	}
+ }
+ EXPORT_SYMBOL_GPL(dax_iomap_fault);

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

[Stephen Rothwell]

Hi Andrew,

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

  fs/ocfs2/aops.c

between commit:

  187372a3b9fa ("direct-io: always call ->end_io if non-NULL")

from the xfs tree and commit:

  8e1fbb488a18 ("ocfs2: fix sparse file & data ordering issue in direct io")

from the akpm-current tree.

I fixed it up (I think - see below) and can carry the fix as necessary
(no action is required).

-- 
Cheers,
Stephen Rothwell

diff --cc fs/ocfs2/aops.c
index 5dcc5f5a842e,3d3952ebe101..000000000000
--- a/fs/ocfs2/aops.c
+++ b/fs/ocfs2/aops.c
@@@ -2476,6 -2099,356 +2099,361 @@@ static int ocfs2_write_end(struct file 
  	return ret;
  }
  
+ struct ocfs2_dio_write_ctxt {
+ 	struct list_head	dw_zero_list;
+ 	unsigned		dw_zero_count;
+ 	int			dw_orphaned;
+ 	pid_t			dw_writer_pid;
+ };
+ 
+ static struct ocfs2_dio_write_ctxt *
+ ocfs2_dio_alloc_write_ctx(struct buffer_head *bh, int *alloc)
+ {
+ 	struct ocfs2_dio_write_ctxt *dwc = NULL;
+ 
+ 	if (bh->b_private)
+ 		return bh->b_private;
+ 
+ 	dwc = kmalloc(sizeof(struct ocfs2_dio_write_ctxt), GFP_NOFS);
+ 	if (dwc == NULL)
+ 		return NULL;
+ 	INIT_LIST_HEAD(&dwc->dw_zero_list);
+ 	dwc->dw_zero_count = 0;
+ 	dwc->dw_orphaned = 0;
+ 	dwc->dw_writer_pid = task_pid_nr(current);
+ 	bh->b_private = dwc;
+ 	*alloc = 1;
+ 
+ 	return dwc;
+ }
+ 
+ static void ocfs2_dio_free_write_ctx(struct inode *inode,
+ 				     struct ocfs2_dio_write_ctxt *dwc)
+ {
+ 	ocfs2_free_unwritten_list(inode, &dwc->dw_zero_list);
+ 	kfree(dwc);
+ }
+ 
+ /*
+  * TODO: Make this into a generic get_blocks function.
+  *
+  * From do_direct_io in direct-io.c:
+  *  "So what we do is to permit the ->get_blocks function to populate
+  *   bh.b_size with the size of IO which is permitted at this offset and
+  *   this i_blkbits."
+  *
+  * This function is called directly from get_more_blocks in direct-io.c.
+  *
+  * called like this: dio->get_blocks(dio->inode, fs_startblk,
+  * 					fs_count, map_bh, dio->rw == WRITE);
+  */
+ static int ocfs2_dio_get_block(struct inode *inode, sector_t iblock,
+ 			       struct buffer_head *bh_result, int create)
+ {
+ 	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
+ 	struct ocfs2_inode_info *oi = OCFS2_I(inode);
+ 	struct ocfs2_write_ctxt *wc;
+ 	struct ocfs2_write_cluster_desc *desc = NULL;
+ 	struct ocfs2_dio_write_ctxt *dwc = NULL;
+ 	struct buffer_head *di_bh = NULL;
+ 	u64 p_blkno;
+ 	loff_t pos = iblock << inode->i_sb->s_blocksize_bits;
+ 	unsigned len, total_len = bh_result->b_size;
+ 	int ret = 0, first_get_block = 0;
+ 
+ 	len = osb->s_clustersize - (pos & (osb->s_clustersize - 1));
+ 	len = min(total_len, len);
+ 
+ 	mlog(0, "get block of %lu at %llu:%u req %u\n",
+ 			inode->i_ino, pos, len, total_len);
+ 
+ 	/*
+ 	 * Because we need to change file size in ocfs2_dio_end_io_write(), or
+ 	 * we may need to add it to orphan dir. So can not fall to fast path
+ 	 * while file size will be changed.
+ 	 */
+ 	if (pos + total_len <= i_size_read(inode)) {
+ 		down_read(&oi->ip_alloc_sem);
+ 		/* This is the fast path for re-write. */
+ 		ret = ocfs2_get_block(inode, iblock, bh_result, create);
+ 
+ 		up_read(&oi->ip_alloc_sem);
+ 
+ 		if (buffer_mapped(bh_result) &&
+ 		    !buffer_new(bh_result) &&
+ 		    ret == 0)
+ 			goto out;
+ 
+ 		/* Clear state set by ocfs2_get_block. */
+ 		bh_result->b_state = 0;
+ 	}
+ 
+ 	dwc = ocfs2_dio_alloc_write_ctx(bh_result, &first_get_block);
+ 	if (unlikely(dwc == NULL)) {
+ 		ret = -ENOMEM;
+ 		mlog_errno(ret);
+ 		goto out;
+ 	}
+ 
+ 	if (ocfs2_clusters_for_bytes(inode->i_sb, pos + total_len) >
+ 	    ocfs2_clusters_for_bytes(inode->i_sb, i_size_read(inode)) &&
+ 	    !dwc->dw_orphaned) {
+ 		/*
+ 		 * when we are going to alloc extents beyond file size, add the
+ 		 * inode to orphan dir, so we can recall those spaces when
+ 		 * system crashed during write.
+ 		 */
+ 		ret = ocfs2_add_inode_to_orphan(osb, inode);
+ 		if (ret < 0) {
+ 			mlog_errno(ret);
+ 			goto out;
+ 		}
+ 		dwc->dw_orphaned = 1;
+ 	}
+ 
+ 	ret = ocfs2_inode_lock(inode, &di_bh, 1);
+ 	if (ret) {
+ 		mlog_errno(ret);
+ 		goto out;
+ 	}
+ 
+ 	down_write(&oi->ip_alloc_sem);
+ 
+ 	if (first_get_block) {
+ 		if (ocfs2_sparse_alloc(OCFS2_SB(inode->i_sb)))
+ 			ret = ocfs2_zero_tail(inode, di_bh, pos);
+ 		else
+ 			ret = ocfs2_expand_nonsparse_inode(inode, di_bh, pos,
+ 							   total_len, NULL);
+ 		if (ret < 0) {
+ 			mlog_errno(ret);
+ 			goto unlock;
+ 		}
+ 	}
+ 
+ 	ret = ocfs2_write_begin_nolock(inode->i_mapping, pos, len,
+ 				       OCFS2_WRITE_DIRECT, NULL,
+ 				       (void **)&wc, di_bh, NULL);
+ 	if (ret) {
+ 		mlog_errno(ret);
+ 		goto unlock;
+ 	}
+ 
+ 	desc = &wc->w_desc[0];
+ 
+ 	p_blkno = ocfs2_clusters_to_blocks(inode->i_sb, desc->c_phys);
+ 	BUG_ON(p_blkno == 0);
+ 	p_blkno += iblock & (u64)(ocfs2_clusters_to_blocks(inode->i_sb, 1) - 1);
+ 
+ 	map_bh(bh_result, inode->i_sb, p_blkno);
+ 	bh_result->b_size = len;
+ 	if (desc->c_needs_zero)
+ 		set_buffer_new(bh_result);
+ 
+ 	/* May sleep in end_io. It should not happen in a irq context. So defer
+ 	 * it to dio work queue. */
+ 	set_buffer_defer_completion(bh_result);
+ 
+ 	if (!list_empty(&wc->w_unwritten_list)) {
+ 		struct ocfs2_unwritten_extent *ue = NULL;
+ 
+ 		ue = list_first_entry(&wc->w_unwritten_list,
+ 				      struct ocfs2_unwritten_extent,
+ 				      ue_node);
+ 		BUG_ON(ue->ue_cpos != desc->c_cpos);
+ 		/* The physical address may be 0, fill it. */
+ 		ue->ue_phys = desc->c_phys;
+ 
+ 		list_splice_tail_init(&wc->w_unwritten_list, &dwc->dw_zero_list);
+ 		dwc->dw_zero_count++;
+ 	}
+ 
+ 	ret = ocfs2_write_end_nolock(inode->i_mapping, pos, len, len, NULL, wc);
+ 	BUG_ON(ret != len);
+ 	ret = 0;
+ unlock:
+ 	up_write(&oi->ip_alloc_sem);
+ 	ocfs2_inode_unlock(inode, 1);
+ 	brelse(di_bh);
+ out:
+ 	if (ret < 0)
+ 		ret = -EIO;
+ 	return ret;
+ }
+ 
+ static void ocfs2_dio_end_io_write(struct inode *inode,
+ 				   struct ocfs2_dio_write_ctxt *dwc,
+ 				   loff_t offset,
+ 				   ssize_t bytes)
+ {
+ 	struct ocfs2_cached_dealloc_ctxt dealloc;
+ 	struct ocfs2_extent_tree et;
+ 	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
+ 	struct ocfs2_inode_info *oi = OCFS2_I(inode);
+ 	struct ocfs2_unwritten_extent *ue = NULL;
+ 	struct buffer_head *di_bh = NULL;
+ 	struct ocfs2_dinode *di;
+ 	struct ocfs2_alloc_context *data_ac = NULL;
+ 	struct ocfs2_alloc_context *meta_ac = NULL;
+ 	handle_t *handle = NULL;
+ 	loff_t end = offset + bytes;
+ 	int ret = 0, credits = 0, locked = 0;
+ 
+ 	ocfs2_init_dealloc_ctxt(&dealloc);
+ 
+ 	/* We do clear unwritten, delete orphan, change i_size here. If neither
+ 	 * of these happen, we can skip all this. */
+ 	if (list_empty(&dwc->dw_zero_list) &&
+ 	    end <= i_size_read(inode) &&
+ 	    !dwc->dw_orphaned)
+ 		goto out;
+ 
+ 	/* ocfs2_file_write_iter will get i_mutex, so we need not lock if we
+ 	 * are in that context. */
+ 	if (dwc->dw_writer_pid != task_pid_nr(current)) {
+ 		mutex_lock(&inode->i_mutex);
+ 		locked = 1;
+ 	}
+ 
+ 	ret = ocfs2_inode_lock(inode, &di_bh, 1);
+ 	if (ret < 0) {
+ 		mlog_errno(ret);
+ 		goto out;
+ 	}
+ 
+ 	down_write(&oi->ip_alloc_sem);
+ 
+ 	/* Delete orphan before acquire i_mutex. */
+ 	if (dwc->dw_orphaned) {
+ 		BUG_ON(dwc->dw_writer_pid != task_pid_nr(current));
+ 
+ 		end = end > i_size_read(inode) ? end : 0;
+ 
+ 		ret = ocfs2_del_inode_from_orphan(osb, inode, di_bh,
+ 				!!end, end);
+ 		if (ret < 0)
+ 			mlog_errno(ret);
+ 	}
+ 
+ 	di = (struct ocfs2_dinode *)di_bh;
+ 
+ 	ocfs2_init_dinode_extent_tree(&et, INODE_CACHE(inode), di_bh);
+ 
+ 	ret = ocfs2_lock_allocators(inode, &et, 0, dwc->dw_zero_count*2,
+ 				    &data_ac, &meta_ac);
+ 	if (ret) {
+ 		mlog_errno(ret);
+ 		goto unlock;
+ 	}
+ 
+ 	credits = ocfs2_calc_extend_credits(inode->i_sb, &di->id2.i_list);
+ 
+ 	handle = ocfs2_start_trans(osb, credits);
+ 	if (IS_ERR(handle)) {
+ 		ret = PTR_ERR(handle);
+ 		mlog_errno(ret);
+ 		goto unlock;
+ 	}
+ 	ret = ocfs2_journal_access_di(handle, INODE_CACHE(inode), di_bh,
+ 				      OCFS2_JOURNAL_ACCESS_WRITE);
+ 	if (ret) {
+ 		mlog_errno(ret);
+ 		goto commit;
+ 	}
+ 
+ 	list_for_each_entry(ue, &dwc->dw_zero_list, ue_node) {
+ 		ret = ocfs2_mark_extent_written(inode, &et, handle,
+ 						ue->ue_cpos, 1,
+ 						ue->ue_phys,
+ 						meta_ac, &dealloc);
+ 		if (ret < 0) {
+ 			mlog_errno(ret);
+ 			break;
+ 		}
+ 	}
+ 
+ 	if (end > i_size_read(inode)) {
+ 		ret = ocfs2_set_inode_size(handle, inode, di_bh, end);
+ 		if (ret < 0)
+ 			mlog_errno(ret);
+ 	}
+ commit:
+ 	ocfs2_commit_trans(osb, handle);
+ unlock:
+ 	up_write(&oi->ip_alloc_sem);
+ 	ocfs2_inode_unlock(inode, 1);
+ 	brelse(di_bh);
+ out:
+ 	if (data_ac)
+ 		ocfs2_free_alloc_context(data_ac);
+ 	if (meta_ac)
+ 		ocfs2_free_alloc_context(meta_ac);
+ 	ocfs2_run_deallocs(osb, &dealloc);
+ 	if (locked)
+ 		mutex_unlock(&inode->i_mutex);
+ 	ocfs2_dio_free_write_ctx(inode, dwc);
+ }
+ 
+ /*
+  * ocfs2_dio_end_io is called by the dio core when a dio is finished.  We're
+  * particularly interested in the aio/dio case.  We use the rw_lock DLM lock
+  * to protect io on one node from truncation on another.
+  */
 -static void ocfs2_dio_end_io(struct kiocb *iocb,
 -			     loff_t offset,
 -			     ssize_t bytes,
 -			     void *private)
++static int ocfs2_dio_end_io(struct kiocb *iocb,
++			    loff_t offset,
++			    ssize_t bytes,
++			    void *private)
+ {
+ 	struct inode *inode = file_inode(iocb->ki_filp);
+ 	int level;
+ 
++	if (bytes <= 0)
++		return 0;
++
+ 	/* this io's submitter should not have unlocked this before we could */
+ 	BUG_ON(!ocfs2_iocb_is_rw_locked(iocb));
+ 
+ 	if (private)
+ 		ocfs2_dio_end_io_write(inode, private, offset, bytes);
+ 
+ 	ocfs2_iocb_clear_rw_locked(iocb);
+ 
+ 	level = ocfs2_iocb_rw_locked_level(iocb);
+ 	ocfs2_rw_unlock(inode, level);
++
++	return 0;
+ }
+ 
+ static ssize_t ocfs2_direct_IO(struct kiocb *iocb, struct iov_iter *iter,
+ 			       loff_t offset)
+ {
+ 	struct file *file = iocb->ki_filp;
+ 	struct inode *inode = file_inode(file)->i_mapping->host;
+ 	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
+ 	loff_t end = offset + iter->count;
+ 	get_block_t *get_block;
+ 
+ 	/*
+ 	 * Fallback to buffered I/O if we see an inode without
+ 	 * extents.
+ 	 */
+ 	if (OCFS2_I(inode)->ip_dyn_features & OCFS2_INLINE_DATA_FL)
+ 		return 0;
+ 
+ 	/* Fallback to buffered I/O if we do not support append dio. */
+ 	if (end > i_size_read(inode) && !ocfs2_supports_append_dio(osb))
+ 		return 0;
+ 
+ 	if (iov_iter_rw(iter) == READ)
+ 		get_block = ocfs2_get_block;
+ 	else
+ 		get_block = ocfs2_dio_get_block;
+ 
+ 	return __blockdev_direct_IO(iocb, inode, inode->i_sb->s_bdev,
+ 				    iter, offset, get_block,
+ 				    ocfs2_dio_end_io, NULL, 0);
+ }
+ 
  const struct address_space_operations ocfs2_aops = {
  	.readpage		= ocfs2_readpage,
  	.readpages		= ocfs2_readpages,

_______________________________________________
xfs mailing list
xfs@oss.sgi.com
http://oss.sgi.com/mailman/listinfo/xfs