@@ -56,7 +56,7 @@ enum {
/* Options that take no arguments */
Opt_nodevmap,
/* Cache options */
- Opt_cache_loose, Opt_fscache,
+ Opt_cache_loose, Opt_fscache, Opt_mmap,
/* Access options */
Opt_access, Opt_posixacl,
/* Error token */
@@ -74,6 +74,7 @@ static const match_table_t tokens = {
{Opt_cache, "cache=%s"},
{Opt_cache_loose, "loose"},
{Opt_fscache, "fscache"},
+ {Opt_mmap, "mmap"},
{Opt_cachetag, "cachetag=%s"},
{Opt_access, "access=%s"},
{Opt_posixacl, "posixacl"},
@@ -91,6 +92,9 @@ static int get_cache_mode(char *s)
} else if (!strcmp(s, "fscache")) {
version = CACHE_FSCACHE;
p9_debug(P9_DEBUG_9P, "Cache mode: fscache\n");
+ } else if (!strcmp(s, "mmap")) {
+ version = CACHE_MMAP;
+ p9_debug(P9_DEBUG_9P, "Cache mode: mmap\n");
} else if (!strcmp(s, "none")) {
version = CACHE_NONE;
p9_debug(P9_DEBUG_9P, "Cache mode: none\n");
@@ -220,6 +224,9 @@ static int v9fs_parse_options(struct v9fs_session_info *v9ses, char *opts)
case Opt_fscache:
v9ses->cache = CACHE_FSCACHE;
break;
+ case Opt_mmap:
+ v9ses->cache = CACHE_MMAP;
+ break;
case Opt_cachetag:
#ifdef CONFIG_9P_FSCACHE
v9ses->cachetag = match_strdup(&args[0]);
@@ -64,6 +64,7 @@ enum p9_session_flags {
enum p9_cache_modes {
CACHE_NONE,
+ CACHE_MMAP,
CACHE_LOOSE,
CACHE_FSCACHE,
};
@@ -50,6 +50,8 @@ extern const struct dentry_operations v9fs_dentry_operations;
extern const struct dentry_operations v9fs_cached_dentry_operations;
extern const struct file_operations v9fs_cached_file_operations;
extern const struct file_operations v9fs_cached_file_operations_dotl;
+extern const struct file_operations v9fs_mmap_file_operations;
+extern const struct file_operations v9fs_mmap_file_operations_dotl;
extern struct kmem_cache *v9fs_inode_cache;
struct inode *v9fs_alloc_inode(struct super_block *sb);
@@ -202,6 +202,8 @@ static int v9fs_vfs_writepage(struct page *page, struct writeback_control *wbc)
{
int retval;
+ p9_debug(P9_DEBUG_VFS, "page %p\n", page);
+
retval = v9fs_vfs_writepage_locked(page);
if (retval < 0) {
if (retval == -EAGAIN) {
@@ -282,6 +284,9 @@ static int v9fs_write_begin(struct file *filp, struct address_space *mapping,
pgoff_t index = pos >> PAGE_CACHE_SHIFT;
struct inode *inode = mapping->host;
+
+ p9_debug(P9_DEBUG_VFS, "filp %p, mapping %p\n", filp, mapping);
+
v9inode = V9FS_I(inode);
start:
page = grab_cache_page_write_begin(mapping, index, flags);
@@ -312,6 +317,8 @@ static int v9fs_write_end(struct file *filp, struct address_space *mapping,
loff_t last_pos = pos + copied;
struct inode *inode = page->mapping->host;
+ p9_debug(P9_DEBUG_VFS, "filp %p, mapping %p\n", filp, mapping);
+
if (unlikely(copied < len)) {
/*
* zero out the rest of the area
@@ -45,6 +45,7 @@
#include "cache.h"
static const struct vm_operations_struct v9fs_file_vm_ops;
+static const struct vm_operations_struct v9fs_mmap_file_vm_ops;
/**
* v9fs_file_open - open a file (or directory)
@@ -106,7 +107,9 @@ int v9fs_file_open(struct inode *inode, struct file *file)
}
mutex_unlock(&v9inode->v_mutex);
#ifdef CONFIG_9P_FSCACHE
- if (v9ses->cache)
+ /* previous check would also set cookie with CACHE_LOOSE?
+ * set_cookie does a check if v9inode->fscache anyway... */
+ if (v9ses->cache == CACHE_FSCACHE)
v9fs_cache_inode_set_cookie(inode, file);
#endif
return 0;
@@ -583,17 +586,33 @@ int v9fs_file_fsync_dotl(struct file *filp, loff_t start, loff_t end,
}
static int
-v9fs_file_mmap(struct file *file, struct vm_area_struct *vma)
+v9fs_file_mmap(struct file *filp, struct vm_area_struct *vma)
{
int retval;
- retval = generic_file_mmap(file, vma);
+
+ retval = generic_file_mmap(filp, vma);
if (!retval)
vma->vm_ops = &v9fs_file_vm_ops;
return retval;
}
+/* TODO: merge this with the previous function
+ * and set the right vm_ops depending on v9ses->cache */
+static int
+v9fs_mmap_file_mmap(struct file *filp, struct vm_area_struct *vma)
+{
+ int retval;
+
+
+ retval = generic_file_mmap(filp, vma);
+ if (!retval)
+ vma->vm_ops = &v9fs_mmap_file_vm_ops;
+
+ return retval;
+}
+
static int
v9fs_vm_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
{
@@ -662,6 +681,22 @@ v9fs_cached_file_read(struct file *filp, char __user *data, size_t count,
return do_sync_read(filp, data, count, offset);
}
+/**
+ * v9fs_mmap_file_read - read from a file
+ * @filp: file pointer to read
+ * @udata: user data buffer to read data into
+ * @count: size of buffer
+ * @offset: offset at which to read data
+ *
+ */
+static ssize_t
+v9fs_mmap_file_read(struct file *filp, char __user *data, size_t count,
+ loff_t *offset)
+{
+ /* TODO: Check if there are dirty pages */
+ return v9fs_file_read(filp, data, count, offset);
+}
+
static ssize_t
v9fs_direct_write(struct file *filp, const char __user * data,
size_t count, loff_t *offsetp)
@@ -732,12 +767,43 @@ v9fs_cached_file_write(struct file *filp, const char __user * data,
return do_sync_write(filp, data, count, offset);
}
+
+/**
+ * v9fs_mmap_file_write - write to a file
+ * @filp: file pointer to write
+ * @data: data buffer to write data from
+ * @count: size of buffer
+ * @offset: offset at which to write data
+ *
+ */
+static ssize_t
+v9fs_mmap_file_write(struct file *filp, const char __user *data,
+ size_t count, loff_t *offset)
+{
+ /* TODO: invalidate mmaps on filp's inode between offset and offset+count */
+ return v9fs_file_write(filp, data, count, offset);
+}
+
+static void v9fs_mmap_vm_close(struct vm_area_struct *vma)
+{
+ p9_debug(P9_DEBUG_VFS, "9p VMA close, %p, flushing", vma);
+ write_inode_now(file_inode(vma->vm_file), 1);
+}
+
+
static const struct vm_operations_struct v9fs_file_vm_ops = {
.fault = filemap_fault,
.page_mkwrite = v9fs_vm_page_mkwrite,
.remap_pages = generic_file_remap_pages,
};
+static const struct vm_operations_struct v9fs_mmap_file_vm_ops = {
+ .close = v9fs_mmap_vm_close,
+ .fault = filemap_fault,
+ .page_mkwrite = v9fs_vm_page_mkwrite,
+ .remap_pages = generic_file_remap_pages,
+};
+
const struct file_operations v9fs_cached_file_operations = {
.llseek = generic_file_llseek,
@@ -788,3 +854,26 @@ const struct file_operations v9fs_file_operations_dotl = {
.mmap = generic_file_readonly_mmap,
.fsync = v9fs_file_fsync_dotl,
};
+
+const struct file_operations v9fs_mmap_file_operations = {
+ .llseek = generic_file_llseek,
+ .read = v9fs_mmap_file_read,
+ .write = v9fs_mmap_file_write,
+ .open = v9fs_file_open,
+ .release = v9fs_dir_release,
+ .lock = v9fs_file_lock,
+ .mmap = v9fs_mmap_file_mmap,
+ .fsync = v9fs_file_fsync,
+};
+
+const struct file_operations v9fs_mmap_file_operations_dotl = {
+ .llseek = generic_file_llseek,
+ .read = v9fs_mmap_file_read,
+ .write = v9fs_mmap_file_write,
+ .open = v9fs_file_open,
+ .release = v9fs_dir_release,
+ .lock = v9fs_file_lock_dotl,
+ .flock = v9fs_file_flock_dotl,
+ .mmap = v9fs_mmap_file_mmap,
+ .fsync = v9fs_file_fsync_dotl,
+};
@@ -299,15 +299,20 @@ int v9fs_init_inode(struct v9fs_session_info *v9ses,
case S_IFREG:
if (v9fs_proto_dotl(v9ses)) {
inode->i_op = &v9fs_file_inode_operations_dotl;
- if (v9ses->cache)
+ if (v9ses->cache == CACHE_LOOSE || v9ses->cache == CACHE_FSCACHE)
inode->i_fop =
&v9fs_cached_file_operations_dotl;
+ else if (v9ses->cache == CACHE_MMAP)
+ inode->i_fop = &v9fs_mmap_file_operations_dotl;
else
inode->i_fop = &v9fs_file_operations_dotl;
} else {
inode->i_op = &v9fs_file_inode_operations;
- if (v9ses->cache)
- inode->i_fop = &v9fs_cached_file_operations;
+ if (v9ses->cache == CACHE_LOOSE || v9ses->cache == CACHE_FSCACHE)
+ inode->i_fop =
+ &v9fs_cached_file_operations;
+ else if (v9ses->cache == CACHE_MMAP)
+ inode->i_fop = &v9fs_mmap_file_operations;
else
inode->i_fop = &v9fs_file_operations;
}
@@ -816,7 +821,7 @@ struct dentry *v9fs_vfs_lookup(struct inode *dir, struct dentry *dentry,
* unlink. For cached mode create calls request for new
* inode. But with cache disabled, lookup should do this.
*/
- if (v9ses->cache)
+ if (v9ses->cache == CACHE_LOOSE || v9ses->cache == CACHE_FSCACHE)
inode = v9fs_get_inode_from_fid(v9ses, fid, dir->i_sb);
else
inode = v9fs_get_new_inode_from_fid(v9ses, fid, dir->i_sb);
@@ -906,7 +911,7 @@ v9fs_vfs_atomic_open(struct inode *dir, struct dentry *dentry,
file->private_data = fid;
#ifdef CONFIG_9P_FSCACHE
- if (v9ses->cache)
+ if (v9ses->cache == CACHE_LOOSE || v9ses->cache == CACHE_FSCACHE)
v9fs_cache_inode_set_cookie(dentry->d_inode, file);
#endif
@@ -1485,7 +1490,7 @@ int v9fs_refresh_inode(struct p9_fid *fid, struct inode *inode)
*/
i_size = inode->i_size;
v9fs_stat2inode(st, inode, inode->i_sb);
- if (v9ses->cache)
+ if (v9ses->cache == CACHE_LOOSE || v9ses->cache == CACHE_FSCACHE)
inode->i_size = i_size;
spin_unlock(&inode->i_lock);
out:
@@ -362,7 +362,7 @@ v9fs_vfs_atomic_open_dotl(struct inode *dir, struct dentry *dentry,
goto err_clunk_old_fid;
file->private_data = ofid;
#ifdef CONFIG_9P_FSCACHE
- if (v9ses->cache)
+ if (v9ses->cache == CACHE_LOOSE || v9ses->cache == CACHE_FSCACHE)
v9fs_cache_inode_set_cookie(inode, file);
#endif
*opened |= FILE_CREATED;
@@ -725,7 +725,7 @@ v9fs_vfs_symlink_dotl(struct inode *dir, struct dentry *dentry,
}
v9fs_invalidate_inode_attr(dir);
- if (v9ses->cache) {
+ if (v9ses->cache == CACHE_LOOSE || v9ses->cache == CACHE_FSCACHE) {
/* Now walk from the parent so we can get an unopened fid. */
fid = p9_client_walk(dfid, 1, &name, 1);
if (IS_ERR(fid)) {
@@ -983,7 +983,7 @@ int v9fs_refresh_inode_dotl(struct p9_fid *fid, struct inode *inode)
*/
i_size = inode->i_size;
v9fs_stat2inode_dotl(st, inode);
- if (v9ses->cache)
+ if (v9ses->cache == CACHE_LOOSE || v9ses->cache == CACHE_FSCACHE)
inode->i_size = i_size;
spin_unlock(&inode->i_lock);
out:
@@ -282,7 +282,7 @@ static int v9fs_drop_inode(struct inode *inode)
{
struct v9fs_session_info *v9ses;
v9ses = v9fs_inode2v9ses(inode);
- if (v9ses->cache)
+ if (v9ses->cache == CACHE_LOOSE || v9ses->cache == CACHE_FSCACHE)
return generic_drop_inode(inode);
/*
* in case of non cached mode always drop the
@@ -325,10 +325,11 @@ static int v9fs_write_inode_dotl(struct inode *inode,
* send an fsync request to server irrespective of
* wbc->sync_mode.
*/
- p9_debug(P9_DEBUG_VFS, "%s: inode %p\n", __func__, inode);
v9inode = V9FS_I(inode);
+ p9_debug(P9_DEBUG_VFS, "%s: inode %p, writeback_fid %p\n", __func__, inode, v9inode->writeback_fid);
if (!v9inode->writeback_fid)
return 0;
+
ret = p9_client_fsync(v9inode->writeback_fid, 0);
if (ret < 0) {
__mark_inode_dirty(inode, I_DIRTY_DATASYNC);
- Add cache=mmap option - Try to keep most operations synchronous Signed-off-by: Dominique Martinet <dominique.martinet@cea.fr> --- Hi, I brought up the issue of mmap being read-only with cache=none a bit ago, and worked on it since. Here's what this patch does: - Add an option cache=mmap (or just mmap, like other caches), nothing changes for default or other caches. The following assumes cache=mmap. - fills in writeback_fid on open (this could be done in v9fs_file_mmap since we don't enable buffered write either, but I wanted to keep the code shared with other caches, so we just have useless writeback fids most of the time) - flush mmap data synchronously on munmap (vma->vm_op->close), this is because we don't want to use the cache for read, so we need the modifications to take place immediately. I'm not quite sure why I had to force it, but it's lost otherwise (with buffered reads, you'd read from the mmap pages anyway and it wouldn't matter if it's flushed later - this doesn't really work for this case) What works: - msync(addr, length, MS_SYNC) (MS_SYNC might just be the default behaviour) does sync correctly; - munmap does a sync as well, obviously; - no msync/msync with MS_ASYNC will eventually flush when the kernel decides to. What doesn't: - If you want to read a file after writting in a mmap'd section with no msync (or msync with MS_ASYNC) and no munmap, you will read what the servers knows about -- so the old data. With buffered read, you'd expect the read to find about the map and use it, we don't. There is, however, what the documentation says so I don't see this as a bug. What could probably be done would be to check on read if we have dirty mapped pages and flush them before reading? I'm not too sure I like this idea. - Likewise, if you write with a map open, the map won't be updated unless something else invalidates it. I guess we should do that like the direct write function does. All in all, while I'm unhappy that I had to use write_inode_now() in vm_ops->close, I would guess it works for what it is (i.e. an unsafe feature on a networking filesystem); at least it seems better than returning ENOTSUPP for my own usage, given read mmap isn't much safer anyway, and that's why it's an option. There are a few questions/TODO marks and p9_debug lines that could go away, but figured it probably makes more sense to leave it there for an RFC patch. (Also a few lines over 80 characters I'll fix for the real deal) Comments more than welcome, thanks! fs/9p/v9fs.c | 9 ++++- fs/9p/v9fs.h | 1 + fs/9p/v9fs_vfs.h | 2 ++ fs/9p/vfs_addr.c | 7 ++++ fs/9p/vfs_file.c | 95 ++++++++++++++++++++++++++++++++++++++++++++++++-- fs/9p/vfs_inode.c | 17 +++++---- fs/9p/vfs_inode_dotl.c | 6 ++-- fs/9p/vfs_super.c | 5 +-- 8 files changed, 127 insertions(+), 15 deletions(-)