LKML Archive on lore.kernel.org
help / color / mirror / Atom feed
From: Nick Piggin <npiggin@suse.de>
To: Andrew Morton <akpm@osdl.org>
Cc: Linux Kernel <linux-kernel@vger.kernel.org>,
	Linux Filesystems <linux-fsdevel@vger.kernel.org>,
	Nick Piggin <npiggin@suse.de>,
	Linux Memory Management <linux-mm@kvack.org>
Subject: [patch 8/9] mm: generic_file_buffered_write iovec cleanup
Date: Mon, 29 Jan 2007 11:32:53 +0100 (CET)	[thread overview]
Message-ID: <20070129082020.23584.76646.sendpatchset@linux.site> (raw)
In-Reply-To: <20070129081905.23584.97878.sendpatchset@linux.site>

Hide some of the open-coded nr_segs tests into the iovec helpers. This is
all to simplify generic_file_buffered_write, because that gets more complex
in the next patch.

Signed-off-by: Nick Piggin <npiggin@suse.de>

Index: linux-2.6/mm/filemap.h
===================================================================
--- linux-2.6.orig/mm/filemap.h
+++ linux-2.6/mm/filemap.h
@@ -22,82 +22,82 @@ __filemap_copy_from_user_iovec_inatomic(
 
 /*
  * Copy as much as we can into the page and return the number of bytes which
- * were sucessfully copied.  If a fault is encountered then clear the page
- * out to (offset+bytes) and return the number of bytes which were copied.
- *
- * NOTE: For this to work reliably we really want copy_from_user_inatomic_nocache
- * to *NOT* zero any tail of the buffer that it failed to copy.  If it does,
- * and if the following non-atomic copy succeeds, then there is a small window
- * where the target page contains neither the data before the write, nor the
- * data after the write (it contains zero).  A read at this time will see
- * data that is inconsistent with any ordering of the read and the write.
- * (This has been detected in practice).
+ * were sucessfully copied.  If a fault is encountered then return the number of
+ * bytes which were copied.
  */
 static inline size_t
-filemap_copy_from_user(struct page *page, unsigned long offset,
-			const char __user *buf, unsigned bytes)
+filemap_copy_from_user_atomic(struct page *page, unsigned long offset,
+			const struct iovec *iov, unsigned long nr_segs,
+			size_t base, size_t bytes)
 {
 	char *kaddr;
-	int left;
+	size_t copied;
 
 	kaddr = kmap_atomic(page, KM_USER0);
-	left = __copy_from_user_inatomic_nocache(kaddr + offset, buf, bytes);
+	if (likely(nr_segs == 1)) {
+		int left;
+		char __user *buf = iov->iov_base + base;
+		left = __copy_from_user_inatomic_nocache(kaddr + offset,
+							buf, bytes);
+		copied = bytes - left;
+	} else {
+		copied = __filemap_copy_from_user_iovec_inatomic(kaddr + offset,
+							iov, base, bytes);
+	}
 	kunmap_atomic(kaddr, KM_USER0);
 
-	if (left != 0) {
-		/* Do it the slow way */
-		kaddr = kmap(page);
-		left = __copy_from_user_nocache(kaddr + offset, buf, bytes);
-		kunmap(page);
-	}
-	return bytes - left;
+	return copied;
 }
 
 /*
- * This has the same sideeffects and return value as filemap_copy_from_user().
- * The difference is that on a fault we need to memset the remainder of the
- * page (out to offset+bytes), to emulate filemap_copy_from_user()'s
- * single-segment behaviour.
+ * This has the same sideeffects and return value as
+ * filemap_copy_from_user_atomic().
+ * The difference is that it attempts to resolve faults.
  */
 static inline size_t
-filemap_copy_from_user_iovec(struct page *page, unsigned long offset,
-			const struct iovec *iov, size_t base, size_t bytes)
+filemap_copy_from_user(struct page *page, unsigned long offset,
+			const struct iovec *iov, unsigned long nr_segs,
+			 size_t base, size_t bytes)
 {
 	char *kaddr;
 	size_t copied;
 
-	kaddr = kmap_atomic(page, KM_USER0);
-	copied = __filemap_copy_from_user_iovec_inatomic(kaddr + offset, iov,
-							 base, bytes);
-	kunmap_atomic(kaddr, KM_USER0);
-	if (copied != bytes) {
-		kaddr = kmap(page);
-		copied = __filemap_copy_from_user_iovec_inatomic(kaddr + offset, iov,
-								 base, bytes);
-		if (bytes - copied)
-			memset(kaddr + offset + copied, 0, bytes - copied);
-		kunmap(page);
+	kaddr = kmap(page);
+	if (likely(nr_segs == 1)) {
+		int left;
+		char __user *buf = iov->iov_base + base;
+		left = __copy_from_user_nocache(kaddr + offset, buf, bytes);
+		copied = bytes - left;
+	} else {
+		copied = __filemap_copy_from_user_iovec_inatomic(kaddr + offset,
+							iov, base, bytes);
 	}
+	kunmap(page);
 	return copied;
 }
 
 static inline void
-filemap_set_next_iovec(const struct iovec **iovp, size_t *basep, size_t bytes)
+filemap_set_next_iovec(const struct iovec **iovp, unsigned long nr_segs,
+						 size_t *basep, size_t bytes)
 {
-	const struct iovec *iov = *iovp;
-	size_t base = *basep;
-
-	while (bytes) {
-		int copy = min(bytes, iov->iov_len - base);
-
-		bytes -= copy;
-		base += copy;
-		if (iov->iov_len == base) {
-			iov++;
-			base = 0;
+	if (likely(nr_segs == 1)) {
+		*basep += bytes;
+	} else {
+		const struct iovec *iov = *iovp;
+		size_t base = *basep;
+
+		while (bytes) {
+			int copy = min(bytes, iov->iov_len - base);
+
+			bytes -= copy;
+			base += copy;
+			if (iov->iov_len == base) {
+				iov++;
+				base = 0;
+			}
 		}
+		*iovp = iov;
+		*basep = base;
 	}
-	*iovp = iov;
-	*basep = base;
 }
 #endif
Index: linux-2.6/mm/filemap.c
===================================================================
--- linux-2.6.orig/mm/filemap.c
+++ linux-2.6/mm/filemap.c
@@ -1840,12 +1840,7 @@ generic_file_buffered_write(struct kiocb
 	/*
 	 * handle partial DIO write.  Adjust cur_iov if needed.
 	 */
-	if (likely(nr_segs == 1))
-		buf = iov->iov_base + written;
-	else {
-		filemap_set_next_iovec(&cur_iov, &iov_offset, written);
-		buf = cur_iov->iov_base + iov_offset;
-	}
+	filemap_set_next_iovec(&cur_iov, nr_segs, &iov_offset, written);
 
 	do {
 		struct page *page;
@@ -1855,6 +1850,7 @@ generic_file_buffered_write(struct kiocb
 		size_t bytes;		/* Bytes to write to page */
 		size_t copied;		/* Bytes copied from user */
 
+		buf = cur_iov->iov_base + iov_offset;
 		offset = (pos & (PAGE_CACHE_SIZE - 1));
 		index = pos >> PAGE_CACHE_SHIFT;
 		bytes = PAGE_CACHE_SIZE - offset;
@@ -1886,13 +1882,10 @@ generic_file_buffered_write(struct kiocb
 		if (unlikely(status))
 			goto fs_write_aop_error;
 
-		if (likely(nr_segs == 1))
-			copied = filemap_copy_from_user(page, offset,
-							buf, bytes);
-		else
-			copied = filemap_copy_from_user_iovec(page, offset,
-						cur_iov, iov_offset, bytes);
+		copied = filemap_copy_from_user(page, offset,
+					cur_iov, nr_segs, iov_offset, bytes);
 		flush_dcache_page(page);
+
 		status = a_ops->commit_write(file, page, offset, offset+bytes);
 		if (unlikely(status < 0))
 			goto fs_write_aop_error;
@@ -1903,20 +1896,11 @@ generic_file_buffered_write(struct kiocb
 		if (unlikely(status > 0)) /* filesystem did partial write */
 			copied = status;
 
-		if (likely(copied > 0)) {
-			written += copied;
-			count -= copied;
-			pos += copied;
-			buf += copied;
-			if (unlikely(nr_segs > 1)) {
-				filemap_set_next_iovec(&cur_iov,
-						&iov_offset, copied);
-				if (count)
-					buf = cur_iov->iov_base + iov_offset;
-			} else {
-				iov_offset += copied;
-			}
-		}
+		written += copied;
+		count -= copied;
+		pos += copied;
+		filemap_set_next_iovec(&cur_iov, nr_segs, &iov_offset, copied);
+
 		unlock_page(page);
 		mark_page_accessed(page);
 		page_cache_release(page);

  parent reply	other threads:[~2007-01-29 10:34 UTC|newest]

Thread overview: 30+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2007-01-29 10:31 [patch 0/9] buffered write deadlock fix Nick Piggin
2007-01-29 10:31 ` [patch 1/9] fs: libfs buffered write leak fix Nick Piggin
2007-02-02 23:52   ` Andrew Morton
2007-02-03  1:33     ` Nick Piggin
2007-02-03  1:58       ` Andrew Morton
2007-02-03  2:09         ` Nick Piggin
2007-02-03  2:19           ` Andrew Morton
2007-02-03  2:28             ` Nick Piggin
2007-02-03 17:49       ` Jörn Engel
2007-02-04  3:55         ` Nick Piggin
2007-01-29 10:31 ` [patch 2/9] mm: revert "generic_file_buffered_write(): handle zero length iovec segments" Nick Piggin
2007-01-29 10:32 ` [patch 3/9] mm: revert "generic_file_buffered_write(): deadlock on vectored write" Nick Piggin
2007-01-29 10:32 ` [patch 4/9] mm: generic_file_buffered_write cleanup Nick Piggin
2007-01-29 10:32 ` [patch 5/9] mm: debug write deadlocks Nick Piggin
2007-01-29 10:32 ` [patch 6/9] mm: be sure to trim blocks Nick Piggin
2007-01-29 10:32 ` [patch 7/9] mm: cleanup pagecache insertion operations Nick Piggin
2007-01-29 10:32 ` Nick Piggin [this message]
2007-01-29 10:33 ` [patch 9/9] mm: fix pagecache write deadlocks Nick Piggin
2007-01-29 11:11   ` Nick Piggin
2007-02-02 23:53   ` Andrew Morton
2007-02-03  1:38     ` Nick Piggin
2007-01-30 20:55 ` [patch 0/9] buffered write deadlock fix Andrew Morton
2007-01-30 23:21   ` Andrew Morton
2007-01-31  1:31     ` Nick Piggin
2007-01-31  0:32   ` Nick Piggin
2007-02-02 23:52 ` Andrew Morton
2007-02-03  1:22   ` Nick Piggin
2007-02-03  6:43   ` Suparna Bhattacharya
     [not found]   ` <370516630.03363@ustc.edu.cn>
2007-02-03 15:31     ` Fengguang Wu
2007-02-04  8:49 Nick Piggin
2007-02-04  8:50 ` [patch 8/9] mm: generic_file_buffered_write iovec cleanup Nick Piggin

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20070129082020.23584.76646.sendpatchset@linux.site \
    --to=npiggin@suse.de \
    --cc=akpm@osdl.org \
    --cc=linux-fsdevel@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --subject='Re: [patch 8/9] mm: generic_file_buffered_write iovec cleanup' \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).