From: Benjamin Marzinski <bmarzins@redhat.com>
Date: Mon, 23 Mar 2009 14:03:03 -0500
Subject: [gfs2] use ->page_mkwrite for mmap()
Message-id: 20090323190303.GB23645@ether.msp.redhat.com
O-Subject: [RHEL-5.4 PATCH] bz315191 GFS2: Use ->page_mkwrite() for mmap()
Bugzilla: 315191
RH-Acked-by: Steven Whitehouse <swhiteho@redhat.com>
RH-Acked-by: Bob Peterson <rpeterso@redhat.com>

This is a backport of upstream code that cleans up the mmap() code path for
GFS2 by implementing the page_mkwrite function in GFS2. The upstream
commit for this patch is.

http://git.kernel.org/?p=linux/kernel/git/torvalds/linux-2.6.git;a=commit;h=3cc3f710ce0effe397b830826a1a081fa81f11c7

There are only minor differences between this version and the upstream
code, which are due to the differences in the kernel code that calls
page_mkwrite.  This patch was tested with QAs cluster coherency test and
the by running a full regression load with QAs distributed IO test.

-Ben

Signed-off-by: Benjamin Marzinski <bmarzins@redhat.com>

diff --git a/fs/gfs2/Makefile b/fs/gfs2/Makefile
index 04ad0ca..8fff110 100644
--- a/fs/gfs2/Makefile
+++ b/fs/gfs2/Makefile
@@ -2,7 +2,7 @@ obj-$(CONFIG_GFS2_FS) += gfs2.o
 gfs2-y := acl.o bmap.o daemon.o dir.o eaops.o eattr.o glock.o \
 	glops.o inode.o lm.o log.o lops.o locking.o main.o meta_io.o \
 	mount.o ops_address.o ops_dentry.o ops_export.o ops_file.o \
-	ops_fstype.o ops_inode.o ops_super.o ops_vm.o quota.o \
+	ops_fstype.o ops_inode.o ops_super.o quota.o \
 	recovery.o rgrp.o super.o sys.o trans.o util.o
 
 obj-$(CONFIG_GFS2_FS_LOCKING_NOLOCK) += locking/nolock/
diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c
index 9dc9d7e..c2aa549 100644
--- a/fs/gfs2/glock.c
+++ b/fs/gfs2/glock.c
@@ -567,6 +567,8 @@ static void do_xmote(struct gfs2_glock *gl, struct gfs2_holder *gh, unsigned int
 	if (test_bit(GLF_INVALIDATE_IN_PROGRESS, &gl->gl_flags))
 		glops->go_inval(gl, target == LM_ST_DEFERRED ? 0 : DIO_METADATA);
 	clear_bit(GLF_INVALIDATE_IN_PROGRESS, &gl->gl_flags);
+	smp_mb__after_clear_bit();
+	wake_up_bit(&gl->gl_flags, GLF_INVALIDATE_IN_PROGRESS);
 
 	gfs2_glock_hold(gl);
 	if (target != LM_ST_UNLOCKED && (gl->gl_state == LM_ST_SHARED ||
diff --git a/fs/gfs2/glops.c b/fs/gfs2/glops.c
index 40096f8..7ce0016 100644
--- a/fs/gfs2/glops.c
+++ b/fs/gfs2/glops.c
@@ -87,14 +87,9 @@ static void gfs2_pte_inval(struct gfs2_glock *gl)
 	if (!ip || !S_ISREG(inode->i_mode))
 		return;
 
-	if (!test_bit(GIF_PAGED, &ip->i_flags))
-		return;
-
 	unmap_shared_mapping_range(inode->i_mapping, 0, 0);
 	if (test_bit(GIF_SW_PAGED, &ip->i_flags))
 		set_bit(GLF_DIRTY, &gl->gl_flags);
-
-	clear_bit(GIF_SW_PAGED, &ip->i_flags);
 }
 
 /**
@@ -217,10 +212,8 @@ static void inode_go_inval(struct gfs2_glock *gl, int flags)
 			set_bit(GIF_INVALID, &ip->i_flags);
 	}
 
-	if (ip && S_ISREG(ip->i_inode.i_mode)) {
+	if (ip && S_ISREG(ip->i_inode.i_mode))
 		truncate_inode_pages(ip->i_inode.i_mapping, 0);
-		clear_bit(GIF_PAGED, &ip->i_flags);
-	}
 }
 
 /**
diff --git a/fs/gfs2/incore.h b/fs/gfs2/incore.h
index 99ac86c..dcd481b 100644
--- a/fs/gfs2/incore.h
+++ b/fs/gfs2/incore.h
@@ -229,7 +229,6 @@ struct gfs2_alloc {
 enum {
 	GIF_INVALID		= 0,
 	GIF_QD_LOCKED		= 1,
-	GIF_PAGED		= 2,
 	GIF_SW_PAGED		= 3,
 	GIF_USER                = 4, /* user inode, not metadata addr space */
 };
@@ -277,13 +276,7 @@ static inline struct gfs2_sbd *GFS2_SB(const struct inode *inode)
 	return inode->i_sb->s_fs_info;
 }
 
-enum {
-	GFF_DID_DIRECT_ALLOC	= 0,
-	GFF_EXLOCK = 1,
-};
-
 struct gfs2_file {
-	unsigned long f_flags;		/* GFF_... */
 	struct mutex f_fl_mutex;
 	struct gfs2_holder f_fl_gh;
 };
diff --git a/fs/gfs2/ops_address.c b/fs/gfs2/ops_address.c
index cb9156b..dc13990 100644
--- a/fs/gfs2/ops_address.c
+++ b/fs/gfs2/ops_address.c
@@ -477,19 +477,12 @@ static int gfs2_readpage(struct file *file, struct page *page)
 	struct address_space *mapping = page->mapping;
 	struct gfs2_inode *ip = GFS2_I(mapping->host);
 	struct gfs2_sbd *sdp = GFS2_SB(mapping->host);
-	struct gfs2_file *gf = NULL;
 	struct gfs2_holder gh;
 	int do_unlock = 0;
 	pgoff_t index = page->index;
 	int error = 0;
 
 	if (likely(file != &gfs2_internal_file_sentinel)) {
-		if (file) {
-			gf = file->private_data;
-			if (test_bit(GFF_EXLOCK, &gf->f_flags))
-				/* gfs2_sharewrite_nopage has grabbed the ip->i_gl already */
-				goto skip_lock;
-		}
 		unlock_page(page);
 		gfs2_holder_init(ip->i_gl, LM_ST_SHARED, 0, &gh);
 		error = gfs2_glock_nq(&gh);
@@ -503,7 +496,6 @@ static int gfs2_readpage(struct file *file, struct page *page)
 			error = AOP_TRUNCATED_PAGE;
 	}
 
-skip_lock:
 	if (!error && !PageUptodate(page)) {
 		if (gfs2_is_stuffed(ip)) {
 			error = stuffed_readpage(ip, page);
@@ -554,11 +546,6 @@ static int gfs2_readpages(struct file *file, struct address_space *mapping,
 	int do_unlock = 0;
 
 	if (likely(file != &gfs2_internal_file_sentinel)) {
-		if (file) {
-			struct gfs2_file *gf = file->private_data;
-			if (test_bit(GFF_EXLOCK, &gf->f_flags))
-				goto skip_lock;
-		}
 		gfs2_holder_init(ip->i_gl, LM_ST_SHARED,
 				 LM_FLAG_TRY_1CB, &gh);
 		do_unlock = 1;
@@ -568,12 +555,12 @@ static int gfs2_readpages(struct file *file, struct address_space *mapping,
 		if (unlikely(ret))
 			goto out_unlock;
 	}
-skip_lock:
+
 	if (!gfs2_is_stuffed(ip))
 		ret = mpage_readpages(mapping, pages, nr_pages, gfs2_block_map);
 
 	if (do_unlock) {
-		gfs2_glock_dq_m(1, &gh);
+		gfs2_glock_dq(&gh);
 		gfs2_holder_uninit(&gh);
 	}
 out:
@@ -1052,9 +1039,7 @@ static int gfs2_commit_write(struct file *file, struct page *page,
 		gfs2_quota_unlock(ip);
 		gfs2_alloc_put(ip);
 	}
-	unlock_page(page);
-	gfs2_glock_dq_m(1, &ip->i_gh);
-	lock_page(page);
+	gfs2_glock_dq(&ip->i_gh);
 	gfs2_holder_uninit(&ip->i_gh);
 	return 0;
 
@@ -1067,9 +1052,7 @@ fail_endtrans:
 		gfs2_quota_unlock(ip);
 		gfs2_alloc_put(ip);
 	}
-	unlock_page(page);
-	gfs2_glock_dq_m(1, &ip->i_gh);
-	lock_page(page);
+	gfs2_glock_dq(&ip->i_gh);
 	gfs2_holder_uninit(&ip->i_gh);
 fail_nounlock:
 	ClearPageUptodate(page);
@@ -1218,7 +1201,7 @@ static ssize_t gfs2_direct_IO(int rw, struct kiocb *iocb,
 					   iov, offset, nr_segs,
 					   gfs2_get_block_direct, NULL);
 out:
-	gfs2_glock_dq_m(1, &gh);
+	gfs2_glock_dq(&gh);
 	gfs2_holder_uninit(&gh);
 	return rv;
 }
diff --git a/fs/gfs2/ops_file.c b/fs/gfs2/ops_file.c
index 5dcde81..965aa19 100644
--- a/fs/gfs2/ops_file.c
+++ b/fs/gfs2/ops_file.c
@@ -219,7 +219,7 @@ static int gfs2_get_flags(struct file *filp, u32 __user *ptr)
 	if (put_user(fsflags, ptr))
 		error = -EFAULT;
 
-	gfs2_glock_dq_m(1, &gh);
+	gfs2_glock_dq(&gh);
 	gfs2_holder_uninit(&gh);
 	return error;
 }
@@ -353,6 +353,161 @@ static long gfs2_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
 	return -ENOTTY;
 }
 
+/**
+ * gfs2_allocate_page_backing - Use bmap to allocate blocks
+ * @page: The (locked) page to allocate backing for
+ *
+ * We try to allocate all the blocks required for the page in
+ * one go. This might fail for various reasons, so we keep
+ * trying until all the blocks to back this page are allocated.
+ * If some of the blocks are already allocated, thats ok too.
+ */
+
+static int gfs2_allocate_page_backing(struct page *page)
+{
+	struct inode *inode = page->mapping->host;
+	struct buffer_head bh;
+	unsigned long size = PAGE_CACHE_SIZE;
+	u64 lblock = page->index << (PAGE_CACHE_SHIFT - inode->i_blkbits);
+
+	do {
+		bh.b_state = 0;
+		bh.b_size = size;
+		gfs2_block_map(inode, lblock, &bh, 1);
+		if (!buffer_mapped(&bh))
+			return -EIO;
+		size -= bh.b_size;
+		lblock += (bh.b_size >> inode->i_blkbits);
+	} while(size > 0);
+	return 0;
+}
+
+/**
+ * gfs2_page_mkwrite - Make a shared, mmap()ed, page writable
+ * @vma: The virtual memory area
+ * @page: The page which is about to become writable
+ *
+ * When the page becomes writable, we need to ensure that we have
+ * blocks allocated on disk to back that page.
+ */
+
+static int gfs2_page_mkwrite(struct vm_area_struct *vma, struct page *page)
+{
+	struct inode *inode = vma->vm_file->f_dentry->d_inode;
+	struct gfs2_inode *ip = GFS2_I(inode);
+	struct gfs2_sbd *sdp = GFS2_SB(inode);
+	unsigned long last_index;
+	u64 pos = page->index << PAGE_CACHE_SHIFT;
+	unsigned int data_blocks, ind_blocks, rblocks;
+	int alloc_required = 0;
+	struct gfs2_holder gh;
+	struct gfs2_alloc *al;
+	int ret;
+
+	gfs2_holder_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, &gh);
+	ret = gfs2_glock_nq(&gh);
+	if (ret)
+		goto out;
+
+	set_bit(GIF_SW_PAGED, &ip->i_flags);
+	ret = gfs2_write_alloc_required(ip, pos, PAGE_CACHE_SIZE, &alloc_required);
+	if (ret || !alloc_required)
+		goto out_unlock;
+
+	al = gfs2_alloc_get(ip);
+	if (al == NULL) {
+		ret = -ENOMEM;
+		goto out_unlock;
+	}
+	ret = gfs2_quota_lock(ip, NO_QUOTA_CHANGE, NO_QUOTA_CHANGE);
+	if (ret)
+		goto out_alloc_put;
+	ret = gfs2_quota_check(ip, ip->i_inode.i_uid, ip->i_inode.i_gid);
+	if (ret)
+		goto out_quota_unlock;
+	gfs2_write_calc_reserv(ip, PAGE_CACHE_SIZE, &data_blocks, &ind_blocks);
+	al->al_requested = data_blocks + ind_blocks;
+	ret = gfs2_inplace_reserve(ip);
+	if (ret)
+		goto out_quota_unlock;
+
+	rblocks = RES_DINODE + ind_blocks;
+	if (gfs2_is_jdata(ip))
+		rblocks += data_blocks ? data_blocks : 1;
+	if (ind_blocks || data_blocks)
+		rblocks += RES_STATFS + RES_QUOTA;
+	ret = gfs2_trans_begin(sdp, rblocks, 0);
+	if (ret)
+		goto out_trans_fail;
+
+	lock_page(page);
+	ret = -EINVAL;
+	last_index = ip->i_inode.i_size >> PAGE_CACHE_SHIFT;
+	if (page->index > last_index)
+		goto out_unlock_page;
+	ret = 0;
+	if (!PageUptodate(page) || page->mapping != ip->i_inode.i_mapping)
+		goto out_unlock_page;
+	if (gfs2_is_stuffed(ip)) {
+		ret = gfs2_unstuff_dinode(ip, page);
+		if (ret)
+			goto out_unlock_page;
+	}
+	ret = gfs2_allocate_page_backing(page);
+
+out_unlock_page:
+	unlock_page(page);
+	gfs2_trans_end(sdp);
+out_trans_fail:
+	gfs2_inplace_release(ip);
+out_quota_unlock:
+	gfs2_quota_unlock(ip);
+out_alloc_put:
+	gfs2_alloc_put(ip);
+out_unlock:
+	gfs2_glock_dq(&gh);
+out:
+	gfs2_holder_uninit(&gh);
+	return ret;
+}
+
+static int just_schedule(void *word)
+{
+	schedule();
+	return 0;
+}
+
+static void wait_on_invalidate(struct gfs2_glock *gl)
+{
+	might_sleep();
+	wait_on_bit(&gl->gl_flags, GLF_INVALIDATE_IN_PROGRESS, just_schedule,
+		    TASK_UNINTERRUPTIBLE);
+}
+
+static struct page *gfs2_nopage(struct vm_area_struct *area,
+				unsigned long address, int *type)
+{
+	struct file *file = area->vm_file;
+	struct inode *inode = file->f_mapping->host;
+	struct gfs2_inode *ip = GFS2_I(inode);
+	struct gfs2_glock *gl = ip->i_gl;
+	struct gfs2_sbd *sdp = gl->gl_sbd;
+
+	if (likely(file != &gfs2_internal_file_sentinel)) {
+		gfs2_glock_hold(gl);
+		if (likely(!test_bit(SDF_SHUTDOWN, &sdp->sd_flags)))
+			wait_on_invalidate(gl);
+		gfs2_glock_put(gl);
+	}
+
+	return filemap_nopage(area, address, type);
+}
+
+static struct vm_operations_struct gfs2_vm_ops = {
+	.nopage = gfs2_nopage,
+	.page_mkwrite = gfs2_page_mkwrite,
+};
+
 
 /**
  * gfs2_mmap -
@@ -375,14 +530,7 @@ static int gfs2_mmap(struct file *file, struct vm_area_struct *vma)
 		return error;
 	}
 
-	/* This is VM_MAYWRITE instead of VM_WRITE because a call
-	   to mprotect() can turn on VM_WRITE later. */
-
-	if ((vma->vm_flags & (VM_MAYSHARE | VM_MAYWRITE)) ==
-	    (VM_MAYSHARE | VM_MAYWRITE))
-		vma->vm_ops = &gfs2_vm_ops_sharewrite;
-	else
-		vma->vm_ops = &gfs2_vm_ops_private;
+	vma->vm_ops = &gfs2_vm_ops;
 
 	gfs2_glock_dq_uninit(&i_gh);
 
diff --git a/fs/gfs2/ops_vm.c b/fs/gfs2/ops_vm.c
deleted file mode 100644
index ed158fe..0000000
--- a/fs/gfs2/ops_vm.c
+++ /dev/null
@@ -1,159 +0,0 @@
-/*
- * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
- * Copyright (C) 2004-2006 Red Hat, Inc.  All rights reserved.
- *
- * This copyrighted material is made available to anyone wishing to use,
- * modify, copy, or redistribute it subject to the terms and conditions
- * of the GNU General Public License version 2.
- */
-
-#include <linux/slab.h>
-#include <linux/spinlock.h>
-#include <linux/completion.h>
-#include <linux/buffer_head.h>
-#include <linux/mm.h>
-#include <linux/pagemap.h>
-#include <linux/gfs2_ondisk.h>
-#include <linux/lm_interface.h>
-
-#include "gfs2.h"
-#include "incore.h"
-#include "bmap.h"
-#include "glock.h"
-#include "inode.h"
-#include "ops_vm.h"
-#include "quota.h"
-#include "rgrp.h"
-#include "trans.h"
-#include "util.h"
-
-static struct page *gfs2_private_nopage(struct vm_area_struct *area,
-					unsigned long address, int *type)
-{
-	struct gfs2_inode *ip = GFS2_I(area->vm_file->f_mapping->host);
-
-	set_bit(GIF_PAGED, &ip->i_flags);
-	return filemap_nopage(area, address, type);
-}
-
-static int alloc_page_backing(struct gfs2_inode *ip, struct page *page)
-{
-	struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
-	unsigned long index = page->index;
-	u64 lblock = index << (PAGE_CACHE_SHIFT -
-				    sdp->sd_sb.sb_bsize_shift);
-	unsigned int blocks = PAGE_CACHE_SIZE >> sdp->sd_sb.sb_bsize_shift;
-	struct gfs2_alloc *al;
-	unsigned int data_blocks, ind_blocks;
-	unsigned int x;
-	int error;
-
-	al = gfs2_alloc_get(ip);
-
-	error = gfs2_quota_lock(ip, NO_QUOTA_CHANGE, NO_QUOTA_CHANGE);
-	if (error)
-		goto out;
-
-	error = gfs2_quota_check(ip, ip->i_inode.i_uid, ip->i_inode.i_gid);
-	if (error)
-		goto out_gunlock_q;
-
-	gfs2_write_calc_reserv(ip, PAGE_CACHE_SIZE, &data_blocks, &ind_blocks);
-
-	al->al_requested = data_blocks + ind_blocks;
-
-	error = gfs2_inplace_reserve(ip);
-	if (error)
-		goto out_gunlock_q;
-
-	error = gfs2_trans_begin(sdp, al->al_rgd->rd_length +
-				 ind_blocks + RES_DINODE +
-				 RES_STATFS + RES_QUOTA, 0);
-	if (error)
-		goto out_ipres;
-
-	if (gfs2_is_stuffed(ip)) {
-		error = gfs2_unstuff_dinode(ip, NULL);
-		if (error)
-			goto out_trans;
-	}
-
-	for (x = 0; x < blocks; ) {
-		u64 dblock;
-		unsigned int extlen;
-		int new = 1;
-
-		error = gfs2_extent_map(&ip->i_inode, lblock, &new, &dblock, &extlen);
-		if (error)
-			goto out_trans;
-
-		lblock += extlen;
-		x += extlen;
-	}
-
-out_trans:
-	gfs2_trans_end(sdp);
-out_ipres:
-	gfs2_inplace_release(ip);
-out_gunlock_q:
-	gfs2_quota_unlock(ip);
-out:
-	gfs2_alloc_put(ip);
-	return error;
-}
-
-static struct page *gfs2_sharewrite_nopage(struct vm_area_struct *area,
-					   unsigned long address, int *type)
-{
-	struct file *file = area->vm_file;
-	struct gfs2_file *gf = file->private_data;
-	struct gfs2_inode *ip = GFS2_I(file->f_mapping->host);
-	struct gfs2_holder i_gh;
-	struct page *result = NULL;
-	unsigned long index = ((address - area->vm_start) >> PAGE_CACHE_SHIFT) +
-			      area->vm_pgoff;
-	int alloc_required;
-	int error;
-
-	error = gfs2_glock_nq_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, &i_gh);
-	if (error)
-		return NULL;
-
-	set_bit(GIF_PAGED, &ip->i_flags);
-	set_bit(GIF_SW_PAGED, &ip->i_flags);
-
-	error = gfs2_write_alloc_required(ip, (u64)index << PAGE_CACHE_SHIFT,
-					  PAGE_CACHE_SIZE, &alloc_required);
-	if (error)
-		goto out;
-
-	set_bit(GFF_EXLOCK, &gf->f_flags);
-	result = filemap_nopage(area, address, type);
-	clear_bit(GFF_EXLOCK, &gf->f_flags);
-	if (!result || result == NOPAGE_OOM)
-		goto out;
-
-	if (alloc_required) {
-		error = alloc_page_backing(ip, result);
-		if (error) {
-			page_cache_release(result);
-			result = NULL;
-			goto out;
-		}
-		set_page_dirty(result);
-	}
-
-out:
-	gfs2_glock_dq_uninit(&i_gh);
-
-	return result;
-}
-
-struct vm_operations_struct gfs2_vm_ops_private = {
-	.nopage = gfs2_private_nopage,
-};
-
-struct vm_operations_struct gfs2_vm_ops_sharewrite = {
-	.nopage = gfs2_sharewrite_nopage,
-};
-