aboutsummaryrefslogtreecommitdiffstats
path: root/fs/fuse
diff options
context:
space:
mode:
Diffstat (limited to 'fs/fuse')
-rw-r--r--fs/fuse/Kconfig2
-rw-r--r--fs/fuse/control.c21
-rw-r--r--fs/fuse/dax.c45
-rw-r--r--fs/fuse/dev.c30
-rw-r--r--fs/fuse/dir.c143
-rw-r--r--fs/fuse/file.c102
-rw-r--r--fs/fuse/fuse_i.h37
-rw-r--r--fs/fuse/inode.c110
-rw-r--r--fs/fuse/ioctl.c26
-rw-r--r--fs/fuse/readdir.c10
-rw-r--r--fs/fuse/virtio_fs.c56
11 files changed, 417 insertions, 165 deletions
diff --git a/fs/fuse/Kconfig b/fs/fuse/Kconfig
index 40ce9a1c12e5..038ed0b9aaa5 100644
--- a/fs/fuse/Kconfig
+++ b/fs/fuse/Kconfig
@@ -45,7 +45,7 @@ config FUSE_DAX
select INTERVAL_TREE
depends on VIRTIO_FS
depends on FS_DAX
- depends on DAX_DRIVER
+ depends on DAX
help
This allows bypassing guest page cache and allows mapping host page
cache directly in guest address space.
diff --git a/fs/fuse/control.c b/fs/fuse/control.c
index 000d2e5627e9..247ef4f76761 100644
--- a/fs/fuse/control.c
+++ b/fs/fuse/control.c
@@ -164,7 +164,6 @@ static ssize_t fuse_conn_congestion_threshold_write(struct file *file,
{
unsigned val;
struct fuse_conn *fc;
- struct fuse_mount *fm;
ssize_t ret;
ret = fuse_conn_limit_write(file, buf, count, ppos, &val,
@@ -178,22 +177,6 @@ static ssize_t fuse_conn_congestion_threshold_write(struct file *file,
down_read(&fc->killsb);
spin_lock(&fc->bg_lock);
fc->congestion_threshold = val;
-
- /*
- * Get any fuse_mount belonging to this fuse_conn; s_bdi is
- * shared between all of them
- */
-
- if (!list_empty(&fc->mounts)) {
- fm = list_first_entry(&fc->mounts, struct fuse_mount, fc_entry);
- if (fc->num_background < fc->congestion_threshold) {
- clear_bdi_congested(fm->sb->s_bdi, BLK_RW_SYNC);
- clear_bdi_congested(fm->sb->s_bdi, BLK_RW_ASYNC);
- } else {
- set_bdi_congested(fm->sb->s_bdi, BLK_RW_SYNC);
- set_bdi_congested(fm->sb->s_bdi, BLK_RW_ASYNC);
- }
- }
spin_unlock(&fc->bg_lock);
up_read(&fc->killsb);
fuse_conn_put(fc);
@@ -275,7 +258,7 @@ int fuse_ctl_add_conn(struct fuse_conn *fc)
struct dentry *parent;
char name[32];
- if (!fuse_control_sb)
+ if (!fuse_control_sb || fc->no_control)
return 0;
parent = fuse_control_sb->s_root;
@@ -313,7 +296,7 @@ void fuse_ctl_remove_conn(struct fuse_conn *fc)
{
int i;
- if (!fuse_control_sb)
+ if (!fuse_control_sb || fc->no_control)
return;
for (i = fc->ctl_ndents - 1; i >= 0; i--) {
diff --git a/fs/fuse/dax.c b/fs/fuse/dax.c
index 713818d74de6..e23e802a8013 100644
--- a/fs/fuse/dax.c
+++ b/fs/fuse/dax.c
@@ -138,9 +138,9 @@ static struct fuse_dax_mapping *alloc_dax_mapping(struct fuse_conn_dax *fcd)
WARN_ON(fcd->nr_free_ranges <= 0);
fcd->nr_free_ranges--;
}
+ __kick_dmap_free_worker(fcd, 0);
spin_unlock(&fcd->lock);
- kick_dmap_free_worker(fcd, 0);
return dmap;
}
@@ -1241,8 +1241,8 @@ static int fuse_dax_mem_range_init(struct fuse_conn_dax *fcd)
INIT_DELAYED_WORK(&fcd->free_work, fuse_dax_free_mem_worker);
id = dax_read_lock();
- nr_pages = dax_direct_access(fcd->dev, 0, PHYS_PFN(dax_size), NULL,
- NULL);
+ nr_pages = dax_direct_access(fcd->dev, 0, PHYS_PFN(dax_size),
+ DAX_ACCESS, NULL, NULL);
dax_read_unlock(id);
if (nr_pages < 0) {
pr_debug("dax_direct_access() returned %ld\n", nr_pages);
@@ -1279,11 +1279,14 @@ out_err:
return ret;
}
-int fuse_dax_conn_alloc(struct fuse_conn *fc, struct dax_device *dax_dev)
+int fuse_dax_conn_alloc(struct fuse_conn *fc, enum fuse_dax_mode dax_mode,
+ struct dax_device *dax_dev)
{
struct fuse_conn_dax *fcd;
int err;
+ fc->dax_mode = dax_mode;
+
if (!dax_dev)
return 0;
@@ -1323,21 +1326,49 @@ bool fuse_dax_inode_alloc(struct super_block *sb, struct fuse_inode *fi)
static const struct address_space_operations fuse_dax_file_aops = {
.writepages = fuse_dax_writepages,
.direct_IO = noop_direct_IO,
- .set_page_dirty = __set_page_dirty_no_writeback,
- .invalidatepage = noop_invalidatepage,
+ .dirty_folio = noop_dirty_folio,
};
-void fuse_dax_inode_init(struct inode *inode)
+static bool fuse_should_enable_dax(struct inode *inode, unsigned int flags)
{
struct fuse_conn *fc = get_fuse_conn(inode);
+ enum fuse_dax_mode dax_mode = fc->dax_mode;
+
+ if (dax_mode == FUSE_DAX_NEVER)
+ return false;
+ /*
+ * fc->dax may be NULL in 'inode' mode when filesystem device doesn't
+ * support DAX, in which case it will silently fallback to 'never' mode.
+ */
if (!fc->dax)
+ return false;
+
+ if (dax_mode == FUSE_DAX_ALWAYS)
+ return true;
+
+ /* dax_mode is FUSE_DAX_INODE* */
+ return fc->inode_dax && (flags & FUSE_ATTR_DAX);
+}
+
+void fuse_dax_inode_init(struct inode *inode, unsigned int flags)
+{
+ if (!fuse_should_enable_dax(inode, flags))
return;
inode->i_flags |= S_DAX;
inode->i_data.a_ops = &fuse_dax_file_aops;
}
+void fuse_dax_dontcache(struct inode *inode, unsigned int flags)
+{
+ struct fuse_conn *fc = get_fuse_conn(inode);
+
+ if (fuse_is_inode_dax_mode(fc->dax_mode) &&
+ ((bool) IS_DAX(inode) != (bool) (flags & FUSE_ATTR_DAX)))
+ d_mark_dontcache(inode);
+}
+
bool fuse_dax_check_alignment(struct fuse_conn *fc, unsigned int map_alignment)
{
if (fc->dax && (map_alignment > FUSE_DAX_SHIFT)) {
diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c
index cd54a529460d..b4a6e0a1b945 100644
--- a/fs/fuse/dev.c
+++ b/fs/fuse/dev.c
@@ -315,10 +315,6 @@ void fuse_request_end(struct fuse_req *req)
wake_up(&fc->blocked_waitq);
}
- if (fc->num_background == fc->congestion_threshold && fm->sb) {
- clear_bdi_congested(fm->sb->s_bdi, BLK_RW_SYNC);
- clear_bdi_congested(fm->sb->s_bdi, BLK_RW_ASYNC);
- }
fc->num_background--;
fc->active_background--;
flush_bg_queue(fc);
@@ -540,10 +536,6 @@ static bool fuse_request_queue_background(struct fuse_req *req)
fc->num_background++;
if (fc->num_background == fc->max_background)
fc->blocked = 1;
- if (fc->num_background == fc->congestion_threshold && fm->sb) {
- set_bdi_congested(fm->sb->s_bdi, BLK_RW_SYNC);
- set_bdi_congested(fm->sb->s_bdi, BLK_RW_ASYNC);
- }
list_add_tail(&req->list, &fc->bg_queue);
flush_bg_queue(fc);
queued = true;
@@ -738,14 +730,13 @@ static int fuse_copy_fill(struct fuse_copy_state *cs)
}
} else {
size_t off;
- err = iov_iter_get_pages(cs->iter, &page, PAGE_SIZE, 1, &off);
+ err = iov_iter_get_pages2(cs->iter, &page, PAGE_SIZE, 1, &off);
if (err < 0)
return err;
BUG_ON(!err);
cs->len = err;
cs->offset = off;
cs->pg = page;
- iov_iter_advance(cs->iter, err);
}
return lock_request(cs->req);
@@ -785,7 +776,8 @@ static int fuse_check_page(struct page *page)
1 << PG_active |
1 << PG_workingset |
1 << PG_reclaim |
- 1 << PG_waiters))) {
+ 1 << PG_waiters |
+ LRU_GEN_MASK | LRU_REFS_MASK))) {
dump_page(page, "fuse: trying to steal weird page");
return 1;
}
@@ -941,7 +933,17 @@ static int fuse_copy_page(struct fuse_copy_state *cs, struct page **pagep,
while (count) {
if (cs->write && cs->pipebufs && page) {
- return fuse_ref_page(cs, page, offset, count);
+ /*
+ * Can't control lifetime of pipe buffers, so always
+ * copy user pages.
+ */
+ if (cs->req->args->user_pages) {
+ err = fuse_copy_fill(cs);
+ if (err)
+ return err;
+ } else {
+ return fuse_ref_page(cs, page, offset, count);
+ }
} else if (!cs->len) {
if (cs->move_pages && page &&
offset == 0 && count == PAGE_SIZE) {
@@ -1354,7 +1356,7 @@ static ssize_t fuse_dev_read(struct kiocb *iocb, struct iov_iter *to)
if (!fud)
return -EPERM;
- if (!iter_is_iovec(to))
+ if (!user_backed_iter(to))
return -EINVAL;
fuse_copy_init(&cs, 1, to);
@@ -1947,7 +1949,7 @@ static ssize_t fuse_dev_write(struct kiocb *iocb, struct iov_iter *from)
if (!fud)
return -EPERM;
- if (!iter_is_iovec(from))
+ if (!user_backed_iter(from))
return -EINVAL;
fuse_copy_init(&cs, 0, from);
diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c
index 0654bfedcbb0..bb97a384dc5d 100644
--- a/fs/fuse/dir.c
+++ b/fs/fuse/dir.c
@@ -11,12 +11,21 @@
#include <linux/pagemap.h>
#include <linux/file.h>
#include <linux/fs_context.h>
+#include <linux/moduleparam.h>
#include <linux/sched.h>
#include <linux/namei.h>
#include <linux/slab.h>
#include <linux/xattr.h>
#include <linux/iversion.h>
#include <linux/posix_acl.h>
+#include <linux/security.h>
+#include <linux/types.h>
+#include <linux/kernel.h>
+
+static bool __read_mostly allow_sys_admin_access;
+module_param(allow_sys_admin_access, bool, 0644);
+MODULE_PARM_DESC(allow_sys_admin_access,
+ "Allow users with CAP_SYS_ADMIN in initial userns to bypass allow_other access check");
static void fuse_advise_use_readdirplus(struct inode *dir)
{
@@ -456,6 +465,62 @@ static struct dentry *fuse_lookup(struct inode *dir, struct dentry *entry,
return ERR_PTR(err);
}
+static int get_security_context(struct dentry *entry, umode_t mode,
+ void **security_ctx, u32 *security_ctxlen)
+{
+ struct fuse_secctx *fctx;
+ struct fuse_secctx_header *header;
+ void *ctx = NULL, *ptr;
+ u32 ctxlen, total_len = sizeof(*header);
+ int err, nr_ctx = 0;
+ const char *name;
+ size_t namelen;
+
+ err = security_dentry_init_security(entry, mode, &entry->d_name,
+ &name, &ctx, &ctxlen);
+ if (err) {
+ if (err != -EOPNOTSUPP)
+ goto out_err;
+ /* No LSM is supporting this security hook. Ignore error */
+ ctxlen = 0;
+ ctx = NULL;
+ }
+
+ if (ctxlen) {
+ nr_ctx = 1;
+ namelen = strlen(name) + 1;
+ err = -EIO;
+ if (WARN_ON(namelen > XATTR_NAME_MAX + 1 || ctxlen > S32_MAX))
+ goto out_err;
+ total_len += FUSE_REC_ALIGN(sizeof(*fctx) + namelen + ctxlen);
+ }
+
+ err = -ENOMEM;
+ header = ptr = kzalloc(total_len, GFP_KERNEL);
+ if (!ptr)
+ goto out_err;
+
+ header->nr_secctx = nr_ctx;
+ header->size = total_len;
+ ptr += sizeof(*header);
+ if (nr_ctx) {
+ fctx = ptr;
+ fctx->size = ctxlen;
+ ptr += sizeof(*fctx);
+
+ strcpy(ptr, name);
+ ptr += namelen;
+
+ memcpy(ptr, ctx, ctxlen);
+ }
+ *security_ctxlen = total_len;
+ *security_ctx = header;
+ err = 0;
+out_err:
+ kfree(ctx);
+ return err;
+}
+
/*
* Atomic create+open operation
*
@@ -464,7 +529,7 @@ static struct dentry *fuse_lookup(struct inode *dir, struct dentry *entry,
*/
static int fuse_create_open(struct inode *dir, struct dentry *entry,
struct file *file, unsigned int flags,
- umode_t mode)
+ umode_t mode, u32 opcode)
{
int err;
struct inode *inode;
@@ -476,6 +541,9 @@ static int fuse_create_open(struct inode *dir, struct dentry *entry,
struct fuse_entry_out outentry;
struct fuse_inode *fi;
struct fuse_file *ff;
+ void *security_ctx = NULL;
+ u32 security_ctxlen;
+ bool trunc = flags & O_TRUNC;
/* Userspace expects S_IFREG in create mode */
BUG_ON((mode & S_IFMT) != S_IFREG);
@@ -500,12 +568,12 @@ static int fuse_create_open(struct inode *dir, struct dentry *entry,
inarg.mode = mode;
inarg.umask = current_umask();
- if (fm->fc->handle_killpriv_v2 && (flags & O_TRUNC) &&
+ if (fm->fc->handle_killpriv_v2 && trunc &&
!(flags & O_EXCL) && !capable(CAP_FSETID)) {
inarg.open_flags |= FUSE_OPEN_KILL_SUIDGID;
}
- args.opcode = FUSE_CREATE;
+ args.opcode = opcode;
args.nodeid = get_node_id(dir);
args.in_numargs = 2;
args.in_args[0].size = sizeof(inarg);
@@ -517,7 +585,20 @@ static int fuse_create_open(struct inode *dir, struct dentry *entry,
args.out_args[0].value = &outentry;
args.out_args[1].size = sizeof(outopen);
args.out_args[1].value = &outopen;
+
+ if (fm->fc->init_security) {
+ err = get_security_context(entry, mode, &security_ctx,
+ &security_ctxlen);
+ if (err)
+ goto out_put_forget_req;
+
+ args.in_numargs = 3;
+ args.in_args[2].size = security_ctxlen;
+ args.in_args[2].value = security_ctx;
+ }
+
err = fuse_simple_request(fm, &args);
+ kfree(security_ctx);
if (err)
goto out_free_ff;
@@ -549,6 +630,10 @@ static int fuse_create_open(struct inode *dir, struct dentry *entry,
} else {
file->private_data = ff;
fuse_finish_open(inode, file);
+ if (fm->fc->atomic_o_trunc && trunc)
+ truncate_pagecache(inode, 0);
+ else if (!(ff->open_flags & FOPEN_KEEP_CACHE))
+ invalidate_inode_pages2(inode->i_mapping);
}
return err;
@@ -591,7 +676,7 @@ static int fuse_atomic_open(struct inode *dir, struct dentry *entry,
if (fc->no_create)
goto mknod;
- err = fuse_create_open(dir, entry, file, flags, mode);
+ err = fuse_create_open(dir, entry, file, flags, mode, FUSE_CREATE);
if (err == -ENOSYS) {
fc->no_create = 1;
goto mknod;
@@ -620,6 +705,8 @@ static int create_new_entry(struct fuse_mount *fm, struct fuse_args *args,
struct dentry *d;
int err;
struct fuse_forget_link *forget;
+ void *security_ctx = NULL;
+ u32 security_ctxlen;
if (fuse_is_bad(dir))
return -EIO;
@@ -633,7 +720,22 @@ static int create_new_entry(struct fuse_mount *fm, struct fuse_args *args,
args->out_numargs = 1;
args->out_args[0].size = sizeof(outarg);
args->out_args[0].value = &outarg;
+
+ if (fm->fc->init_security && args->opcode != FUSE_LINK) {
+ err = get_security_context(entry, mode, &security_ctx,
+ &security_ctxlen);
+ if (err)
+ goto out_put_forget_req;
+
+ BUG_ON(args->in_numargs != 2);
+
+ args->in_numargs = 3;
+ args->in_args[2].size = security_ctxlen;
+ args->in_args[2].value = security_ctx;
+ }
+
err = fuse_simple_request(fm, args);
+ kfree(security_ctx);
if (err)
goto out_put_forget_req;
@@ -700,6 +802,23 @@ static int fuse_create(struct user_namespace *mnt_userns, struct inode *dir,
return fuse_mknod(&init_user_ns, dir, entry, mode, 0);
}
+static int fuse_tmpfile(struct user_namespace *mnt_userns, struct inode *dir,
+ struct file *file, umode_t mode)
+{
+ struct fuse_conn *fc = get_fuse_conn(dir);
+ int err;
+
+ if (fc->no_tmpfile)
+ return -EOPNOTSUPP;
+
+ err = fuse_create_open(dir, file->f_path.dentry, file, file->f_flags, mode, FUSE_TMPFILE);
+ if (err == -ENOSYS) {
+ fc->no_tmpfile = 1;
+ err = -EOPNOTSUPP;
+ }
+ return err;
+}
+
static int fuse_mkdir(struct user_namespace *mnt_userns, struct inode *dir,
struct dentry *entry, umode_t mode)
{
@@ -1133,6 +1252,9 @@ int fuse_allow_current_process(struct fuse_conn *fc)
{
const struct cred *cred;
+ if (allow_sys_admin_access && capable(CAP_SYS_ADMIN))
+ return 1;
+
if (fc->allow_other)
return current_in_userns(fc->user_ns);
@@ -1682,7 +1804,7 @@ int fuse_do_setattr(struct dentry *dentry, struct iattr *attr,
/*
* Only call invalidate_inode_pages2() after removing
- * FUSE_NOWRITE, otherwise fuse_launder_page() would deadlock.
+ * FUSE_NOWRITE, otherwise fuse_launder_folio() would deadlock.
*/
if ((is_truncate || !is_wb) &&
S_ISREG(inode->i_mode) && oldsize != outarg.attr.size) {
@@ -1808,6 +1930,7 @@ static const struct inode_operations fuse_dir_inode_operations = {
.setattr = fuse_setattr,
.create = fuse_create,
.atomic_open = fuse_atomic_open,
+ .tmpfile = fuse_tmpfile,
.mknod = fuse_mknod,
.permission = fuse_permission,
.getattr = fuse_getattr,
@@ -1866,20 +1989,20 @@ void fuse_init_dir(struct inode *inode)
fi->rdc.version = 0;
}
-static int fuse_symlink_readpage(struct file *null, struct page *page)
+static int fuse_symlink_read_folio(struct file *null, struct folio *folio)
{
- int err = fuse_readlink_page(page->mapping->host, page);
+ int err = fuse_readlink_page(folio->mapping->host, &folio->page);
if (!err)
- SetPageUptodate(page);
+ folio_mark_uptodate(folio);
- unlock_page(page);
+ folio_unlock(folio);
return err;
}
static const struct address_space_operations fuse_symlink_aops = {
- .readpage = fuse_symlink_readpage,
+ .read_folio = fuse_symlink_read_folio,
};
void fuse_init_symlink(struct inode *inode)
diff --git a/fs/fuse/file.c b/fs/fuse/file.c
index 9d6c5f6361f7..71bfb663aac5 100644
--- a/fs/fuse/file.c
+++ b/fs/fuse/file.c
@@ -210,13 +210,9 @@ void fuse_finish_open(struct inode *inode, struct file *file)
fi->attr_version = atomic64_inc_return(&fc->attr_version);
i_size_write(inode, 0);
spin_unlock(&fi->lock);
- truncate_pagecache(inode, 0);
file_update_time(file);
fuse_invalidate_attr_mask(inode, FUSE_STATX_MODSIZE);
- } else if (!(ff->open_flags & FOPEN_KEEP_CACHE)) {
- invalidate_inode_pages2(inode->i_mapping);
}
-
if ((file->f_mode & FMODE_WRITE) && fc->writeback_cache)
fuse_link_write_file(file);
}
@@ -239,30 +235,38 @@ int fuse_open_common(struct inode *inode, struct file *file, bool isdir)
if (err)
return err;
- if (is_wb_truncate || dax_truncate) {
+ if (is_wb_truncate || dax_truncate)
inode_lock(inode);
- fuse_set_nowrite(inode);
- }
if (dax_truncate) {
filemap_invalidate_lock(inode->i_mapping);
err = fuse_dax_break_layouts(inode, 0, 0);
if (err)
- goto out;
+ goto out_inode_unlock;
}
+ if (is_wb_truncate || dax_truncate)
+ fuse_set_nowrite(inode);
+
err = fuse_do_open(fm, get_node_id(inode), file, isdir);
if (!err)
fuse_finish_open(inode, file);
-out:
+ if (is_wb_truncate || dax_truncate)
+ fuse_release_nowrite(inode);
+ if (!err) {
+ struct fuse_file *ff = file->private_data;
+
+ if (fc->atomic_o_trunc && (file->f_flags & O_TRUNC))
+ truncate_pagecache(inode, 0);
+ else if (!(ff->open_flags & FOPEN_KEEP_CACHE))
+ invalidate_inode_pages2(inode->i_mapping);
+ }
if (dax_truncate)
filemap_invalidate_unlock(inode->i_mapping);
-
- if (is_wb_truncate | dax_truncate) {
- fuse_release_nowrite(inode);
+out_inode_unlock:
+ if (is_wb_truncate || dax_truncate)
inode_unlock(inode);
- }
return err;
}
@@ -338,6 +342,15 @@ static int fuse_open(struct inode *inode, struct file *file)
static int fuse_release(struct inode *inode, struct file *file)
{
+ struct fuse_conn *fc = get_fuse_conn(inode);
+
+ /*
+ * Dirty pages might remain despite write_inode_now() call from
+ * fuse_flush() due to writes racing with the close.
+ */
+ if (fc->writeback_cache)
+ write_inode_now(inode, 1);
+
fuse_release_common(file, false);
/* return value is ignored by VFS */
@@ -857,8 +870,9 @@ static int fuse_do_readpage(struct file *file, struct page *page)
return 0;
}
-static int fuse_readpage(struct file *file, struct page *page)
+static int fuse_read_folio(struct file *file, struct folio *folio)
{
+ struct page *page = &folio->page;
struct inode *inode = page->mapping->host;
int err;
@@ -966,6 +980,14 @@ static void fuse_readahead(struct readahead_control *rac)
struct fuse_io_args *ia;
struct fuse_args_pages *ap;
+ if (fc->num_background >= fc->congestion_threshold &&
+ rac->ra->async_size >= readahead_count(rac))
+ /*
+ * Congested and only async pages left, so skip the
+ * rest.
+ */
+ break;
+
nr_pages = readahead_count(rac) - nr_pages;
if (nr_pages > max_pages)
nr_pages = max_pages;
@@ -1033,7 +1055,7 @@ static unsigned int fuse_write_flags(struct kiocb *iocb)
{
unsigned int flags = iocb->ki_filp->f_flags;
- if (iocb->ki_flags & IOCB_DSYNC)
+ if (iocb_is_dsync(iocb))
flags |= O_DSYNC;
if (iocb->ki_flags & IOCB_SYNC)
flags |= O_SYNC;
@@ -1166,7 +1188,7 @@ static ssize_t fuse_fill_write_pages(struct fuse_io_args *ia,
break;
err = -ENOMEM;
- page = grab_cache_page_write_begin(mapping, index, 0);
+ page = grab_cache_page_write_begin(mapping, index);
if (!page)
break;
@@ -1392,14 +1414,13 @@ static int fuse_get_user_pages(struct fuse_args_pages *ap, struct iov_iter *ii,
while (nbytes < *nbytesp && ap->num_pages < max_pages) {
unsigned npages;
size_t start;
- ret = iov_iter_get_pages(ii, &ap->pages[ap->num_pages],
+ ret = iov_iter_get_pages2(ii, &ap->pages[ap->num_pages],
*nbytesp - nbytes,
max_pages - ap->num_pages,
&start);
if (ret < 0)
break;
- iov_iter_advance(ii, ret);
nbytes += ret;
ret += start;
@@ -1413,6 +1434,7 @@ static int fuse_get_user_pages(struct fuse_args_pages *ap, struct iov_iter *ii,
(PAGE_SIZE - ret) & (PAGE_SIZE - 1);
}
+ ap->args.user_pages = true;
if (write)
ap->args.in_pages = true;
else
@@ -1455,7 +1477,7 @@ ssize_t fuse_direct_io(struct fuse_io_priv *io, struct iov_iter *iter,
inode_unlock(inode);
}
- io->should_dirty = !write && iter_is_iovec(iter);
+ io->should_dirty = !write && user_backed_iter(iter);
while (count) {
ssize_t nres;
fl_owner_t owner = current->files;
@@ -1958,6 +1980,7 @@ err:
static int fuse_writepage(struct page *page, struct writeback_control *wbc)
{
+ struct fuse_conn *fc = get_fuse_conn(page->mapping->host);
int err;
if (fuse_page_is_writeback(page->mapping->host, page->index)) {
@@ -1973,6 +1996,10 @@ static int fuse_writepage(struct page *page, struct writeback_control *wbc)
return 0;
}
+ if (wbc->sync_mode == WB_SYNC_NONE &&
+ fc->num_background >= fc->congestion_threshold)
+ return AOP_WRITEPAGE_ACTIVATE;
+
err = fuse_writepage_locked(page);
unlock_page(page);
@@ -2226,6 +2253,10 @@ static int fuse_writepages(struct address_space *mapping,
if (fuse_is_bad(inode))
goto out;
+ if (wbc->sync_mode == WB_SYNC_NONE &&
+ fc->num_background >= fc->congestion_threshold)
+ return 0;
+
data.inode = inode;
data.wpa = NULL;
data.ff = NULL;
@@ -2255,8 +2286,7 @@ out:
* but how to implement it without killing performance need more thinking.
*/
static int fuse_write_begin(struct file *file, struct address_space *mapping,
- loff_t pos, unsigned len, unsigned flags,
- struct page **pagep, void **fsdata)
+ loff_t pos, unsigned len, struct page **pagep, void **fsdata)
{
pgoff_t index = pos >> PAGE_SHIFT;
struct fuse_conn *fc = get_fuse_conn(file_inode(file));
@@ -2266,7 +2296,7 @@ static int fuse_write_begin(struct file *file, struct address_space *mapping,
WARN_ON(!fc->writeback_cache);
- page = grab_cache_page_write_begin(mapping, index, flags);
+ page = grab_cache_page_write_begin(mapping, index);
if (!page)
goto error;
@@ -2330,17 +2360,17 @@ unlock:
return copied;
}
-static int fuse_launder_page(struct page *page)
+static int fuse_launder_folio(struct folio *folio)
{
int err = 0;
- if (clear_page_dirty_for_io(page)) {
- struct inode *inode = page->mapping->host;
+ if (folio_clear_dirty_for_io(folio)) {
+ struct inode *inode = folio->mapping->host;
/* Serialize with pending writeback for the same page */
- fuse_wait_on_page_writeback(inode, page->index);
- err = fuse_writepage_locked(page);
+ fuse_wait_on_page_writeback(inode, folio->index);
+ err = fuse_writepage_locked(&folio->page);
if (!err)
- fuse_wait_on_page_writeback(inode, page->index);
+ fuse_wait_on_page_writeback(inode, folio->index);
}
return err;
}
@@ -2910,7 +2940,7 @@ fuse_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
static int fuse_writeback_range(struct inode *inode, loff_t start, loff_t end)
{
- int err = filemap_write_and_wait_range(inode->i_mapping, start, -1);
+ int err = filemap_write_and_wait_range(inode->i_mapping, start, LLONG_MAX);
if (!err)
fuse_sync_writes(inode);
@@ -2971,6 +3001,10 @@ static long fuse_file_fallocate(struct file *file, int mode, loff_t offset,
goto out;
}
+ err = file_modified(file);
+ if (err)
+ goto out;
+
if (!(mode & FALLOC_FL_KEEP_SIZE))
set_bit(FUSE_I_SIZE_UNSTABLE, &fi->state);
@@ -3157,19 +3191,19 @@ static const struct file_operations fuse_file_operations = {
};
static const struct address_space_operations fuse_file_aops = {
- .readpage = fuse_readpage,
+ .read_folio = fuse_read_folio,
.readahead = fuse_readahead,
.writepage = fuse_writepage,
.writepages = fuse_writepages,
- .launder_page = fuse_launder_page,
- .set_page_dirty = __set_page_dirty_nobuffers,
+ .launder_folio = fuse_launder_folio,
+ .dirty_folio = filemap_dirty_folio,
.bmap = fuse_bmap,
.direct_IO = fuse_direct_IO,
.write_begin = fuse_write_begin,
.write_end = fuse_write_end,
};
-void fuse_init_file_inode(struct inode *inode)
+void fuse_init_file_inode(struct inode *inode, unsigned int flags)
{
struct fuse_inode *fi = get_fuse_inode(inode);
@@ -3183,5 +3217,5 @@ void fuse_init_file_inode(struct inode *inode)
fi->writepages = RB_ROOT;
if (IS_ENABLED(CONFIG_FUSE_DAX))
- fuse_dax_inode_init(inode);
+ fuse_dax_inode_init(inode, flags);
}
diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h
index 198637b41e19..98a9cf531873 100644
--- a/fs/fuse/fuse_i.h
+++ b/fs/fuse/fuse_i.h
@@ -256,6 +256,7 @@ struct fuse_args {
bool nocreds:1;
bool in_pages:1;
bool out_pages:1;
+ bool user_pages:1;
bool out_argvar:1;
bool page_zeroing:1;
bool page_replace:1;
@@ -480,6 +481,18 @@ struct fuse_dev {
struct list_head entry;
};
+enum fuse_dax_mode {
+ FUSE_DAX_INODE_DEFAULT, /* default */
+ FUSE_DAX_ALWAYS, /* "-o dax=always" */
+ FUSE_DAX_NEVER, /* "-o dax=never" */
+ FUSE_DAX_INODE_USER, /* "-o dax=inode" */
+};
+
+static inline bool fuse_is_inode_dax_mode(enum fuse_dax_mode mode)
+{
+ return mode == FUSE_DAX_INODE_DEFAULT || mode == FUSE_DAX_INODE_USER;
+}
+
struct fuse_fs_context {
int fd;
struct file *file;
@@ -497,7 +510,7 @@ struct fuse_fs_context {
bool no_control:1;
bool no_force_umount:1;
bool legacy_opts_show:1;
- bool dax:1;
+ enum fuse_dax_mode dax_mode;
unsigned int max_read;
unsigned int blksize;
const char *subtype;
@@ -614,7 +627,7 @@ struct fuse_conn {
/** Connection successful. Only set in INIT */
unsigned conn_init:1;
- /** Do readpages asynchronously? Only set in INIT */
+ /** Do readahead asynchronously? Only set in INIT */
unsigned async_read:1;
/** Return an unique read error after abort. Only set in INIT */
@@ -765,6 +778,15 @@ struct fuse_conn {
/* Propagate syncfs() to server */
unsigned int sync_fs:1;
+ /* Initialize security xattrs when creating a new inode */
+ unsigned int init_security:1;
+
+ /* Does the filesystem support per inode DAX? */
+ unsigned int inode_dax:1;
+
+ /* Is tmpfile not implemented by fs? */
+ unsigned int no_tmpfile:1;
+
/** The number of requests waiting for completion */
atomic_t num_waiting;
@@ -802,6 +824,9 @@ struct fuse_conn {
struct list_head devices;
#ifdef CONFIG_FUSE_DAX
+ /* Dax mode */
+ enum fuse_dax_mode dax_mode;
+
/* Dax specific conn data, non-NULL if DAX is enabled */
struct fuse_conn_dax *dax;
#endif
@@ -1007,7 +1032,7 @@ int fuse_notify_poll_wakeup(struct fuse_conn *fc,
/**
* Initialize file operations on a regular file
*/
-void fuse_init_file_inode(struct inode *inode);
+void fuse_init_file_inode(struct inode *inode, unsigned int flags);
/**
* Initialize inode operations on regular files and special files
@@ -1269,11 +1294,13 @@ ssize_t fuse_dax_read_iter(struct kiocb *iocb, struct iov_iter *to);
ssize_t fuse_dax_write_iter(struct kiocb *iocb, struct iov_iter *from);
int fuse_dax_mmap(struct file *file, struct vm_area_struct *vma);
int fuse_dax_break_layouts(struct inode *inode, u64 dmap_start, u64 dmap_end);
-int fuse_dax_conn_alloc(struct fuse_conn *fc, struct dax_device *dax_dev);
+int fuse_dax_conn_alloc(struct fuse_conn *fc, enum fuse_dax_mode mode,
+ struct dax_device *dax_dev);
void fuse_dax_conn_free(struct fuse_conn *fc);
bool fuse_dax_inode_alloc(struct super_block *sb, struct fuse_inode *fi);
-void fuse_dax_inode_init(struct inode *inode);
+void fuse_dax_inode_init(struct inode *inode, unsigned int flags);
void fuse_dax_inode_cleanup(struct inode *inode);
+void fuse_dax_dontcache(struct inode *inode, unsigned int flags);
bool fuse_dax_check_alignment(struct fuse_conn *fc, unsigned int map_alignment);
void fuse_dax_cancel_work(struct fuse_conn *fc);
diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c
index 8b89e3ba7df3..6b3beda16c1b 100644
--- a/fs/fuse/inode.c
+++ b/fs/fuse/inode.c
@@ -23,6 +23,7 @@
#include <linux/exportfs.h>
#include <linux/posix_acl.h>
#include <linux/pid_namespace.h>
+#include <uapi/linux/magic.h>
MODULE_AUTHOR("Miklos Szeredi <miklos@szeredi.hu>");
MODULE_DESCRIPTION("Filesystem in Userspace");
@@ -50,8 +51,6 @@ MODULE_PARM_DESC(max_user_congthresh,
"Global limit for the maximum congestion threshold an "
"unprivileged user can set");
-#define FUSE_SUPER_MAGIC 0x65735546
-
#define FUSE_DEFAULT_BLKSIZE 512
/** Maximum number of outstanding background requests */
@@ -73,7 +72,7 @@ static struct inode *fuse_alloc_inode(struct super_block *sb)
{
struct fuse_inode *fi;
- fi = kmem_cache_alloc(fuse_inode_cachep, GFP_KERNEL);
+ fi = alloc_inode_sb(sb, fuse_inode_cachep, GFP_KERNEL);
if (!fi)
return NULL;
@@ -181,6 +180,12 @@ void fuse_change_attributes_common(struct inode *inode, struct fuse_attr *attr,
inode->i_uid = make_kuid(fc->user_ns, attr->uid);
inode->i_gid = make_kgid(fc->user_ns, attr->gid);
inode->i_blocks = attr->blocks;
+
+ /* Sanitize nsecs */
+ attr->atimensec = min_t(u32, attr->atimensec, NSEC_PER_SEC - 1);
+ attr->mtimensec = min_t(u32, attr->mtimensec, NSEC_PER_SEC - 1);
+ attr->ctimensec = min_t(u32, attr->ctimensec, NSEC_PER_SEC - 1);
+
inode->i_atime.tv_sec = attr->atime;
inode->i_atime.tv_nsec = attr->atimensec;
/* mtime from server may be stale due to local buffered write */
@@ -301,6 +306,9 @@ void fuse_change_attributes(struct inode *inode, struct fuse_attr *attr,
if (inval)
invalidate_inode_pages2(inode->i_mapping);
}
+
+ if (IS_ENABLED(CONFIG_FUSE_DAX))
+ fuse_dax_dontcache(inode, attr->flags);
}
static void fuse_init_inode(struct inode *inode, struct fuse_attr *attr)
@@ -313,7 +321,7 @@ static void fuse_init_inode(struct inode *inode, struct fuse_attr *attr)
inode->i_ctime.tv_nsec = attr->ctimensec;
if (S_ISREG(inode->i_mode)) {
fuse_init_common(inode);
- fuse_init_file_inode(inode);
+ fuse_init_file_inode(inode, attr->flags);
} else if (S_ISDIR(inode->i_mode))
fuse_init_dir(inode);
else if (S_ISLNK(inode->i_mode))
@@ -474,8 +482,14 @@ static void fuse_umount_begin(struct super_block *sb)
{
struct fuse_conn *fc = get_fuse_conn_super(sb);
- if (!fc->no_force_umount)
- fuse_abort_conn(fc);
+ if (fc->no_force_umount)
+ return;
+
+ fuse_abort_conn(fc);
+
+ // Only retire block-device-based superblocks.
+ if (sb->s_bdev != NULL)
+ retire_super(sb);
}
static void fuse_send_destroy(struct fuse_mount *fm)
@@ -767,8 +781,12 @@ static int fuse_show_options(struct seq_file *m, struct dentry *root)
seq_printf(m, ",blksize=%lu", sb->s_blocksize);
}
#ifdef CONFIG_FUSE_DAX
- if (fc->dax)
- seq_puts(m, ",dax");
+ if (fc->dax_mode == FUSE_DAX_ALWAYS)
+ seq_puts(m, ",dax=always");
+ else if (fc->dax_mode == FUSE_DAX_NEVER)
+ seq_puts(m, ",dax=never");
+ else if (fc->dax_mode == FUSE_DAX_INODE_USER)
+ seq_puts(m, ",dax=inode");
#endif
return 0;
@@ -1109,73 +1127,80 @@ static void process_init_reply(struct fuse_mount *fm, struct fuse_args *args,
process_init_limits(fc, arg);
if (arg->minor >= 6) {
+ u64 flags = arg->flags | (u64) arg->flags2 << 32;
+
ra_pages = arg->max_readahead / PAGE_SIZE;
- if (arg->flags & FUSE_ASYNC_READ)
+ if (flags & FUSE_ASYNC_READ)
fc->async_read = 1;
- if (!(arg->flags & FUSE_POSIX_LOCKS))
+ if (!(flags & FUSE_POSIX_LOCKS))
fc->no_lock = 1;
if (arg->minor >= 17) {
- if (!(arg->flags & FUSE_FLOCK_LOCKS))
+ if (!(flags & FUSE_FLOCK_LOCKS))
fc->no_flock = 1;
} else {
- if (!(arg->flags & FUSE_POSIX_LOCKS))
+ if (!(flags & FUSE_POSIX_LOCKS))
fc->no_flock = 1;
}
- if (arg->flags & FUSE_ATOMIC_O_TRUNC)
+ if (flags & FUSE_ATOMIC_O_TRUNC)
fc->atomic_o_trunc = 1;
if (arg->minor >= 9) {
/* LOOKUP has dependency on proto version */
- if (arg->flags & FUSE_EXPORT_SUPPORT)
+ if (flags & FUSE_EXPORT_SUPPORT)
fc->export_support = 1;
}
- if (arg->flags & FUSE_BIG_WRITES)
+ if (flags & FUSE_BIG_WRITES)
fc->big_writes = 1;
- if (arg->flags & FUSE_DONT_MASK)
+ if (flags & FUSE_DONT_MASK)
fc->dont_mask = 1;
- if (arg->flags & FUSE_AUTO_INVAL_DATA)
+ if (flags & FUSE_AUTO_INVAL_DATA)
fc->auto_inval_data = 1;
- else if (arg->flags & FUSE_EXPLICIT_INVAL_DATA)
+ else if (flags & FUSE_EXPLICIT_INVAL_DATA)
fc->explicit_inval_data = 1;
- if (arg->flags & FUSE_DO_READDIRPLUS) {
+ if (flags & FUSE_DO_READDIRPLUS) {
fc->do_readdirplus = 1;
- if (arg->flags & FUSE_READDIRPLUS_AUTO)
+ if (flags & FUSE_READDIRPLUS_AUTO)
fc->readdirplus_auto = 1;
}
- if (arg->flags & FUSE_ASYNC_DIO)
+ if (flags & FUSE_ASYNC_DIO)
fc->async_dio = 1;
- if (arg->flags & FUSE_WRITEBACK_CACHE)
+ if (flags & FUSE_WRITEBACK_CACHE)
fc->writeback_cache = 1;
- if (arg->flags & FUSE_PARALLEL_DIROPS)
+ if (flags & FUSE_PARALLEL_DIROPS)
fc->parallel_dirops = 1;
- if (arg->flags & FUSE_HANDLE_KILLPRIV)
+ if (flags & FUSE_HANDLE_KILLPRIV)
fc->handle_killpriv = 1;
if (arg->time_gran && arg->time_gran <= 1000000000)
fm->sb->s_time_gran = arg->time_gran;
- if ((arg->flags & FUSE_POSIX_ACL)) {
+ if ((flags & FUSE_POSIX_ACL)) {
fc->default_permissions = 1;
fc->posix_acl = 1;
fm->sb->s_xattr = fuse_acl_xattr_handlers;
}
- if (arg->flags & FUSE_CACHE_SYMLINKS)
+ if (flags & FUSE_CACHE_SYMLINKS)
fc->cache_symlinks = 1;
- if (arg->flags & FUSE_ABORT_ERROR)
+ if (flags & FUSE_ABORT_ERROR)
fc->abort_err = 1;
- if (arg->flags & FUSE_MAX_PAGES) {
+ if (flags & FUSE_MAX_PAGES) {
fc->max_pages =
min_t(unsigned int, fc->max_pages_limit,
max_t(unsigned int, arg->max_pages, 1));
}
- if (IS_ENABLED(CONFIG_FUSE_DAX) &&
- arg->flags & FUSE_MAP_ALIGNMENT &&
- !fuse_dax_check_alignment(fc, arg->map_alignment)) {
- ok = false;
+ if (IS_ENABLED(CONFIG_FUSE_DAX)) {
+ if (flags & FUSE_MAP_ALIGNMENT &&
+ !fuse_dax_check_alignment(fc, arg->map_alignment)) {
+ ok = false;
+ }
+ if (flags & FUSE_HAS_INODE_DAX)
+ fc->inode_dax = 1;
}
- if (arg->flags & FUSE_HANDLE_KILLPRIV_V2) {
+ if (flags & FUSE_HANDLE_KILLPRIV_V2) {
fc->handle_killpriv_v2 = 1;
fm->sb->s_flags |= SB_NOSEC;
}
- if (arg->flags & FUSE_SETXATTR_EXT)
+ if (flags & FUSE_SETXATTR_EXT)
fc->setxattr_ext = 1;
+ if (flags & FUSE_SECURITY_CTX)
+ fc->init_security = 1;
} else {
ra_pages = fc->max_read / PAGE_SIZE;
fc->no_lock = 1;
@@ -1203,13 +1228,14 @@ static void process_init_reply(struct fuse_mount *fm, struct fuse_args *args,
void fuse_send_init(struct fuse_mount *fm)
{
struct fuse_init_args *ia;
+ u64 flags;
ia = kzalloc(sizeof(*ia), GFP_KERNEL | __GFP_NOFAIL);
ia->in.major = FUSE_KERNEL_VERSION;
ia->in.minor = FUSE_KERNEL_MINOR_VERSION;
ia->in.max_readahead = fm->sb->s_bdi->ra_pages * PAGE_SIZE;
- ia->in.flags |=
+ flags =
FUSE_ASYNC_READ | FUSE_POSIX_LOCKS | FUSE_ATOMIC_O_TRUNC |
FUSE_EXPORT_SUPPORT | FUSE_BIG_WRITES | FUSE_DONT_MASK |
FUSE_SPLICE_WRITE | FUSE_SPLICE_MOVE | FUSE_SPLICE_READ |
@@ -1219,13 +1245,19 @@ void fuse_send_init(struct fuse_mount *fm)
FUSE_PARALLEL_DIROPS | FUSE_HANDLE_KILLPRIV | FUSE_POSIX_ACL |
FUSE_ABORT_ERROR | FUSE_MAX_PAGES | FUSE_CACHE_SYMLINKS |
FUSE_NO_OPENDIR_SUPPORT | FUSE_EXPLICIT_INVAL_DATA |
- FUSE_HANDLE_KILLPRIV_V2 | FUSE_SETXATTR_EXT;
+ FUSE_HANDLE_KILLPRIV_V2 | FUSE_SETXATTR_EXT | FUSE_INIT_EXT |
+ FUSE_SECURITY_CTX;
#ifdef CONFIG_FUSE_DAX
if (fm->fc->dax)
- ia->in.flags |= FUSE_MAP_ALIGNMENT;
+ flags |= FUSE_MAP_ALIGNMENT;
+ if (fuse_is_inode_dax_mode(fm->fc->dax_mode))
+ flags |= FUSE_HAS_INODE_DAX;
#endif
if (fm->fc->auto_submounts)
- ia->in.flags |= FUSE_SUBMOUNTS;
+ flags |= FUSE_SUBMOUNTS;
+
+ ia->in.flags = flags;
+ ia->in.flags2 = flags >> 32;
ia->args.opcode = FUSE_INIT;
ia->args.in_numargs = 1;
@@ -1514,7 +1546,7 @@ int fuse_fill_super_common(struct super_block *sb, struct fuse_fs_context *ctx)
sb->s_subtype = ctx->subtype;
ctx->subtype = NULL;
if (IS_ENABLED(CONFIG_FUSE_DAX)) {
- err = fuse_dax_conn_alloc(fc, ctx->dax_dev);
+ err = fuse_dax_conn_alloc(fc, ctx->dax_mode, ctx->dax_dev);
if (err)
goto err;
}
diff --git a/fs/fuse/ioctl.c b/fs/fuse/ioctl.c
index fbc09dab1f85..61d8afcb10a3 100644
--- a/fs/fuse/ioctl.c
+++ b/fs/fuse/ioctl.c
@@ -9,6 +9,17 @@
#include <linux/compat.h>
#include <linux/fileattr.h>
+static ssize_t fuse_send_ioctl(struct fuse_mount *fm, struct fuse_args *args)
+{
+ ssize_t ret = fuse_simple_request(fm, args);
+
+ /* Translate ENOSYS, which shouldn't be returned from fs */
+ if (ret == -ENOSYS)
+ ret = -ENOTTY;
+
+ return ret;
+}
+
/*
* CUSE servers compiled on 32bit broke on 64bit kernels because the
* ABI was defined to be 'struct iovec' which is different on 32bit
@@ -170,7 +181,7 @@ long fuse_do_ioctl(struct file *file, unsigned int cmd, unsigned long arg,
#else
if (flags & FUSE_IOCTL_COMPAT) {
inarg.flags |= FUSE_IOCTL_32BIT;
-#ifdef CONFIG_X86_X32
+#ifdef CONFIG_X86_X32_ABI
if (in_x32_syscall())
inarg.flags |= FUSE_IOCTL_COMPAT_X32;
#endif
@@ -259,7 +270,7 @@ long fuse_do_ioctl(struct file *file, unsigned int cmd, unsigned long arg,
ap.args.out_pages = true;
ap.args.out_argvar = true;
- transferred = fuse_simple_request(fm, &ap.args);
+ transferred = fuse_send_ioctl(fm, &ap.args);
err = transferred;
if (transferred < 0)
goto out;
@@ -393,10 +404,13 @@ static int fuse_priv_ioctl(struct inode *inode, struct fuse_file *ff,
args.out_args[1].size = inarg.out_size;
args.out_args[1].value = ptr;
- err = fuse_simple_request(fm, &args);
- if (!err && outarg.flags & FUSE_IOCTL_RETRY)
- err = -EIO;
-
+ err = fuse_send_ioctl(fm, &args);
+ if (!err) {
+ if (outarg.result < 0)
+ err = outarg.result;
+ else if (outarg.flags & FUSE_IOCTL_RETRY)
+ err = -EIO;
+ }
return err;
}
diff --git a/fs/fuse/readdir.c b/fs/fuse/readdir.c
index b4e565711045..e8deaacf1832 100644
--- a/fs/fuse/readdir.c
+++ b/fs/fuse/readdir.c
@@ -77,8 +77,10 @@ static void fuse_add_dirent_to_cache(struct file *file,
goto unlock;
addr = kmap_local_page(page);
- if (!offset)
+ if (!offset) {
clear_page(addr);
+ SetPageUptodate(page);
+ }
memcpy(addr + offset, dirent, reclen);
kunmap_local(addr);
fi->rdc.size = (index << PAGE_SHIFT) + offset + reclen;
@@ -516,6 +518,12 @@ retry_locked:
page = find_get_page_flags(file->f_mapping, index,
FGP_ACCESSED | FGP_LOCK);
+ /* Page gone missing, then re-added to cache, but not initialized? */
+ if (page && !PageUptodate(page)) {
+ unlock_page(page);
+ put_page(page);
+ page = NULL;
+ }
spin_lock(&fi->rdc.lock);
if (!page) {
/*
diff --git a/fs/fuse/virtio_fs.c b/fs/fuse/virtio_fs.c
index 4cfa4bc1f579..4d8d4f16c727 100644
--- a/fs/fuse/virtio_fs.c
+++ b/fs/fuse/virtio_fs.c
@@ -8,6 +8,7 @@
#include <linux/dax.h>
#include <linux/pci.h>
#include <linux/pfn_t.h>
+#include <linux/memremap.h>
#include <linux/module.h>
#include <linux/virtio.h>
#include <linux/virtio_fs.h>
@@ -88,12 +89,21 @@ struct virtio_fs_req_work {
static int virtio_fs_enqueue_req(struct virtio_fs_vq *fsvq,
struct fuse_req *req, bool in_flight);
+static const struct constant_table dax_param_enums[] = {
+ {"always", FUSE_DAX_ALWAYS },
+ {"never", FUSE_DAX_NEVER },
+ {"inode", FUSE_DAX_INODE_USER },
+ {}
+};
+
enum {
OPT_DAX,
+ OPT_DAX_ENUM,
};
static const struct fs_parameter_spec virtio_fs_parameters[] = {
fsparam_flag("dax", OPT_DAX),
+ fsparam_enum("dax", OPT_DAX_ENUM, dax_param_enums),
{}
};
@@ -110,7 +120,10 @@ static int virtio_fs_parse_param(struct fs_context *fsc,
switch (opt) {
case OPT_DAX:
- ctx->dax = 1;
+ ctx->dax_mode = FUSE_DAX_ALWAYS;
+ break;
+ case OPT_DAX_ENUM:
+ ctx->dax_mode = result.uint_32;
break;
default:
return -EINVAL;
@@ -728,8 +741,7 @@ out:
}
/* Free virtqueues (device must already be reset) */
-static void virtio_fs_cleanup_vqs(struct virtio_device *vdev,
- struct virtio_fs *fs)
+static void virtio_fs_cleanup_vqs(struct virtio_device *vdev)
{
vdev->config->del_vqs(vdev);
}
@@ -739,11 +751,12 @@ static void virtio_fs_cleanup_vqs(struct virtio_device *vdev,
* offset.
*/
static long virtio_fs_direct_access(struct dax_device *dax_dev, pgoff_t pgoff,
- long nr_pages, void **kaddr, pfn_t *pfn)
+ long nr_pages, enum dax_access_mode mode,
+ void **kaddr, pfn_t *pfn)
{
struct virtio_fs *fs = dax_get_private(dax_dev);
phys_addr_t offset = PFN_PHYS(pgoff);
- size_t max_nr_pages = fs->window_len/PAGE_SIZE - pgoff;
+ size_t max_nr_pages = fs->window_len / PAGE_SIZE - pgoff;
if (kaddr)
*kaddr = fs->window_kaddr + offset;
@@ -753,27 +766,14 @@ static long virtio_fs_direct_access(struct dax_device *dax_dev, pgoff_t pgoff,
return nr_pages > max_nr_pages ? max_nr_pages : nr_pages;
}
-static size_t virtio_fs_copy_from_iter(struct dax_device *dax_dev,
- pgoff_t pgoff, void *addr,
- size_t bytes, struct iov_iter *i)
-{
- return copy_from_iter(addr, bytes, i);
-}
-
-static size_t virtio_fs_copy_to_iter(struct dax_device *dax_dev,
- pgoff_t pgoff, void *addr,
- size_t bytes, struct iov_iter *i)
-{
- return copy_to_iter(addr, bytes, i);
-}
-
static int virtio_fs_zero_page_range(struct dax_device *dax_dev,
pgoff_t pgoff, size_t nr_pages)
{
long rc;
void *kaddr;
- rc = dax_direct_access(dax_dev, pgoff, nr_pages, &kaddr, NULL);
+ rc = dax_direct_access(dax_dev, pgoff, nr_pages, DAX_ACCESS, &kaddr,
+ NULL);
if (rc < 0)
return rc;
memset(kaddr, 0, nr_pages << PAGE_SHIFT);
@@ -783,8 +783,6 @@ static int virtio_fs_zero_page_range(struct dax_device *dax_dev,
static const struct dax_operations virtio_fs_dax_ops = {
.direct_access = virtio_fs_direct_access,
- .copy_from_iter = virtio_fs_copy_from_iter,
- .copy_to_iter = virtio_fs_copy_to_iter,
.zero_page_range = virtio_fs_zero_page_range,
};
@@ -850,7 +848,7 @@ static int virtio_fs_setup_dax(struct virtio_device *vdev, struct virtio_fs *fs)
dev_dbg(&vdev->dev, "%s: window kaddr 0x%px phys_addr 0x%llx len 0x%llx\n",
__func__, fs->window_kaddr, cache_reg.addr, cache_reg.len);
- fs->dax_dev = alloc_dax(fs, NULL, &virtio_fs_dax_ops, 0);
+ fs->dax_dev = alloc_dax(fs, &virtio_fs_dax_ops);
if (IS_ERR(fs->dax_dev))
return PTR_ERR(fs->dax_dev);
@@ -895,8 +893,8 @@ static int virtio_fs_probe(struct virtio_device *vdev)
return 0;
out_vqs:
- vdev->config->reset(vdev);
- virtio_fs_cleanup_vqs(vdev, fs);
+ virtio_reset_device(vdev);
+ virtio_fs_cleanup_vqs(vdev);
kfree(fs->vqs);
out:
@@ -927,8 +925,8 @@ static void virtio_fs_remove(struct virtio_device *vdev)
list_del_init(&fs->list);
virtio_fs_stop_all_queues(fs);
virtio_fs_drain_all_queues_locked(fs);
- vdev->config->reset(vdev);
- virtio_fs_cleanup_vqs(vdev, fs);
+ virtio_reset_device(vdev);
+ virtio_fs_cleanup_vqs(vdev);
vdev->priv = NULL;
/* Put device reference on virtio_fs object */
@@ -1326,8 +1324,8 @@ static int virtio_fs_fill_super(struct super_block *sb, struct fs_context *fsc)
/* virtiofs allocates and installs its own fuse devices */
ctx->fudptr = NULL;
- if (ctx->dax) {
- if (!fs->dax_dev) {
+ if (ctx->dax_mode != FUSE_DAX_NEVER) {
+ if (ctx->dax_mode == FUSE_DAX_ALWAYS && !fs->dax_dev) {
err = -EINVAL;
pr_err("virtio-fs: dax can't be enabled as filesystem"
" device does not support it.\n");
Copyright © 1996 – 2023 Jason A. Donenfeld. All Rights Reverse Engineered.