summaryrefslogtreecommitdiffstats
path: root/fs/fuse
diff options
context:
space:
mode:
Diffstat (limited to 'fs/fuse')
-rw-r--r--fs/fuse/Kconfig11
-rw-r--r--fs/fuse/Makefile2
-rw-r--r--fs/fuse/control.c6
-rw-r--r--fs/fuse/cuse.c4
-rw-r--r--fs/fuse/dev.c157
-rw-r--r--fs/fuse/dir.c49
-rw-r--r--fs/fuse/file.c473
-rw-r--r--fs/fuse/fuse_i.h153
-rw-r--r--fs/fuse/inode.c73
-rw-r--r--fs/fuse/ioctl.c60
-rw-r--r--fs/fuse/iomode.c276
-rw-r--r--fs/fuse/passthrough.c355
-rw-r--r--fs/fuse/readdir.c4
-rw-r--r--fs/fuse/virtio_fs.c230
14 files changed, 1555 insertions, 298 deletions
diff --git a/fs/fuse/Kconfig b/fs/fuse/Kconfig
index 038ed0b9aa..8674dbfbe5 100644
--- a/fs/fuse/Kconfig
+++ b/fs/fuse/Kconfig
@@ -52,3 +52,14 @@ config FUSE_DAX
If you want to allow mounting a Virtio Filesystem with the "dax"
option, answer Y.
+
+config FUSE_PASSTHROUGH
+ bool "FUSE passthrough operations support"
+ default y
+ depends on FUSE_FS
+ select FS_STACK
+ help
+ This allows bypassing FUSE server by mapping specific FUSE operations
+ to be performed directly on a backing file.
+
+ If you want to allow passthrough operations, answer Y.
diff --git a/fs/fuse/Makefile b/fs/fuse/Makefile
index 0c48b35c05..6e0228c6d0 100644
--- a/fs/fuse/Makefile
+++ b/fs/fuse/Makefile
@@ -8,6 +8,8 @@ obj-$(CONFIG_CUSE) += cuse.o
obj-$(CONFIG_VIRTIO_FS) += virtiofs.o
fuse-y := dev.o dir.o file.o inode.o control.o xattr.o acl.o readdir.o ioctl.o
+fuse-y += iomode.o
fuse-$(CONFIG_FUSE_DAX) += dax.o
+fuse-$(CONFIG_FUSE_PASSTHROUGH) += passthrough.o
virtiofs-y := virtio_fs.o
diff --git a/fs/fuse/control.c b/fs/fuse/control.c
index 284a350064..97ac994ff7 100644
--- a/fs/fuse/control.c
+++ b/fs/fuse/control.c
@@ -174,11 +174,7 @@ static ssize_t fuse_conn_congestion_threshold_write(struct file *file,
if (!fc)
goto out;
- down_read(&fc->killsb);
- spin_lock(&fc->bg_lock);
- fc->congestion_threshold = val;
- spin_unlock(&fc->bg_lock);
- up_read(&fc->killsb);
+ WRITE_ONCE(fc->congestion_threshold, val);
fuse_conn_put(fc);
out:
return ret;
diff --git a/fs/fuse/cuse.c b/fs/fuse/cuse.c
index b6cad106c3..0b2da7b7e2 100644
--- a/fs/fuse/cuse.c
+++ b/fs/fuse/cuse.c
@@ -310,6 +310,10 @@ struct cuse_init_args {
/**
* cuse_process_init_reply - finish initializing CUSE channel
*
+ * @fm: The fuse mount information containing the CUSE connection.
+ * @args: The arguments passed to the init reply.
+ * @error: The error code signifying if any error occurred during the process.
+ *
* This function creates the character device and sets up all the
* required data structures for it. Please read the comment at the
* top of this file for high level overview.
diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c
index 1a8f82f478..9eb191b5c4 100644
--- a/fs/fuse/dev.c
+++ b/fs/fuse/dev.c
@@ -1775,6 +1775,62 @@ copy_finish:
return err;
}
+/*
+ * Resending all processing queue requests.
+ *
+ * During a FUSE daemon panics and failover, it is possible for some inflight
+ * requests to be lost and never returned. As a result, applications awaiting
+ * replies would become stuck forever. To address this, we can use notification
+ * to trigger resending of these pending requests to the FUSE daemon, ensuring
+ * they are properly processed again.
+ *
+ * Please note that this strategy is applicable only to idempotent requests or
+ * if the FUSE daemon takes careful measures to avoid processing duplicated
+ * non-idempotent requests.
+ */
+static void fuse_resend(struct fuse_conn *fc)
+{
+ struct fuse_dev *fud;
+ struct fuse_req *req, *next;
+ struct fuse_iqueue *fiq = &fc->iq;
+ LIST_HEAD(to_queue);
+ unsigned int i;
+
+ spin_lock(&fc->lock);
+ if (!fc->connected) {
+ spin_unlock(&fc->lock);
+ return;
+ }
+
+ list_for_each_entry(fud, &fc->devices, entry) {
+ struct fuse_pqueue *fpq = &fud->pq;
+
+ spin_lock(&fpq->lock);
+ for (i = 0; i < FUSE_PQ_HASH_SIZE; i++)
+ list_splice_tail_init(&fpq->processing[i], &to_queue);
+ spin_unlock(&fpq->lock);
+ }
+ spin_unlock(&fc->lock);
+
+ list_for_each_entry_safe(req, next, &to_queue, list) {
+ set_bit(FR_PENDING, &req->flags);
+ clear_bit(FR_SENT, &req->flags);
+ /* mark the request as resend request */
+ req->in.h.unique |= FUSE_UNIQUE_RESEND;
+ }
+
+ spin_lock(&fiq->lock);
+ /* iq and pq requests are both oldest to newest */
+ list_splice(&to_queue, &fiq->pending);
+ fiq->ops->wake_pending_and_unlock(fiq);
+}
+
+static int fuse_notify_resend(struct fuse_conn *fc)
+{
+ fuse_resend(fc);
+ return 0;
+}
+
static int fuse_notify(struct fuse_conn *fc, enum fuse_notify_code code,
unsigned int size, struct fuse_copy_state *cs)
{
@@ -1800,6 +1856,9 @@ static int fuse_notify(struct fuse_conn *fc, enum fuse_notify_code code,
case FUSE_NOTIFY_DELETE:
return fuse_notify_delete(fc, size, cs);
+ case FUSE_NOTIFY_RESEND:
+ return fuse_notify_resend(fc);
+
default:
fuse_copy_finish(cs);
return -EINVAL;
@@ -2251,43 +2310,91 @@ static int fuse_device_clone(struct fuse_conn *fc, struct file *new)
return 0;
}
-static long fuse_dev_ioctl(struct file *file, unsigned int cmd,
- unsigned long arg)
+static long fuse_dev_ioctl_clone(struct file *file, __u32 __user *argp)
{
int res;
int oldfd;
struct fuse_dev *fud = NULL;
struct fd f;
+ if (get_user(oldfd, argp))
+ return -EFAULT;
+
+ f = fdget(oldfd);
+ if (!f.file)
+ return -EINVAL;
+
+ /*
+ * Check against file->f_op because CUSE
+ * uses the same ioctl handler.
+ */
+ if (f.file->f_op == file->f_op)
+ fud = fuse_get_dev(f.file);
+
+ res = -EINVAL;
+ if (fud) {
+ mutex_lock(&fuse_mutex);
+ res = fuse_device_clone(fud->fc, file);
+ mutex_unlock(&fuse_mutex);
+ }
+
+ fdput(f);
+ return res;
+}
+
+static long fuse_dev_ioctl_backing_open(struct file *file,
+ struct fuse_backing_map __user *argp)
+{
+ struct fuse_dev *fud = fuse_get_dev(file);
+ struct fuse_backing_map map;
+
+ if (!fud)
+ return -EPERM;
+
+ if (!IS_ENABLED(CONFIG_FUSE_PASSTHROUGH))
+ return -EOPNOTSUPP;
+
+ if (copy_from_user(&map, argp, sizeof(map)))
+ return -EFAULT;
+
+ return fuse_backing_open(fud->fc, &map);
+}
+
+static long fuse_dev_ioctl_backing_close(struct file *file, __u32 __user *argp)
+{
+ struct fuse_dev *fud = fuse_get_dev(file);
+ int backing_id;
+
+ if (!fud)
+ return -EPERM;
+
+ if (!IS_ENABLED(CONFIG_FUSE_PASSTHROUGH))
+ return -EOPNOTSUPP;
+
+ if (get_user(backing_id, argp))
+ return -EFAULT;
+
+ return fuse_backing_close(fud->fc, backing_id);
+}
+
+static long fuse_dev_ioctl(struct file *file, unsigned int cmd,
+ unsigned long arg)
+{
+ void __user *argp = (void __user *)arg;
+
switch (cmd) {
case FUSE_DEV_IOC_CLONE:
- if (get_user(oldfd, (__u32 __user *)arg))
- return -EFAULT;
+ return fuse_dev_ioctl_clone(file, argp);
- f = fdget(oldfd);
- if (!f.file)
- return -EINVAL;
+ case FUSE_DEV_IOC_BACKING_OPEN:
+ return fuse_dev_ioctl_backing_open(file, argp);
+
+ case FUSE_DEV_IOC_BACKING_CLOSE:
+ return fuse_dev_ioctl_backing_close(file, argp);
- /*
- * Check against file->f_op because CUSE
- * uses the same ioctl handler.
- */
- if (f.file->f_op == file->f_op)
- fud = fuse_get_dev(f.file);
-
- res = -EINVAL;
- if (fud) {
- mutex_lock(&fuse_mutex);
- res = fuse_device_clone(fud->fc, file);
- mutex_unlock(&fuse_mutex);
- }
- fdput(f);
- break;
default:
- res = -ENOTTY;
- break;
+ return -ENOTTY;
}
- return res;
}
const struct file_operations fuse_dev_operations = {
diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c
index bd3b21d485..2b0d4781f3 100644
--- a/fs/fuse/dir.c
+++ b/fs/fuse/dir.c
@@ -619,7 +619,7 @@ static int fuse_create_open(struct inode *dir, struct dentry *entry,
FUSE_ARGS(args);
struct fuse_forget_link *forget;
struct fuse_create_in inarg;
- struct fuse_open_out outopen;
+ struct fuse_open_out *outopenp;
struct fuse_entry_out outentry;
struct fuse_inode *fi;
struct fuse_file *ff;
@@ -634,7 +634,7 @@ static int fuse_create_open(struct inode *dir, struct dentry *entry,
goto out_err;
err = -ENOMEM;
- ff = fuse_file_alloc(fm);
+ ff = fuse_file_alloc(fm, true);
if (!ff)
goto out_put_forget_req;
@@ -663,8 +663,10 @@ static int fuse_create_open(struct inode *dir, struct dentry *entry,
args.out_numargs = 2;
args.out_args[0].size = sizeof(outentry);
args.out_args[0].value = &outentry;
- args.out_args[1].size = sizeof(outopen);
- args.out_args[1].value = &outopen;
+ /* Store outarg for fuse_finish_open() */
+ outopenp = &ff->args->open_outarg;
+ args.out_args[1].size = sizeof(*outopenp);
+ args.out_args[1].value = outopenp;
err = get_create_ext(&args, dir, entry, mode);
if (err)
@@ -680,9 +682,9 @@ static int fuse_create_open(struct inode *dir, struct dentry *entry,
fuse_invalid_attr(&outentry.attr))
goto out_free_ff;
- ff->fh = outopen.fh;
+ ff->fh = outopenp->fh;
ff->nodeid = outentry.nodeid;
- ff->open_flags = outopen.open_flags;
+ ff->open_flags = outopenp->open_flags;
inode = fuse_iget(dir->i_sb, outentry.nodeid, outentry.generation,
&outentry.attr, ATTR_TIMEOUT(&outentry), 0);
if (!inode) {
@@ -696,13 +698,15 @@ static int fuse_create_open(struct inode *dir, struct dentry *entry,
d_instantiate(entry, inode);
fuse_change_entry_timeout(entry, &outentry);
fuse_dir_changed(dir);
- err = finish_open(file, entry, generic_file_open);
+ err = generic_file_open(inode, file);
+ if (!err) {
+ file->private_data = ff;
+ err = finish_open(file, entry, fuse_finish_open);
+ }
if (err) {
fi = get_fuse_inode(inode);
fuse_sync_release(fi, ff, flags);
} 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))
@@ -1490,7 +1494,7 @@ static int fuse_perm_getattr(struct inode *inode, int mask)
*
* 1) Local access checking ('default_permissions' mount option) based
* on file mode. This is the plain old disk filesystem permission
- * modell.
+ * model.
*
* 2) "Remote" access checking, where server is responsible for
* checking permission in each inode operation. An exception to this
@@ -1635,7 +1639,30 @@ out_err:
static int fuse_dir_open(struct inode *inode, struct file *file)
{
- return fuse_open_common(inode, file, true);
+ struct fuse_mount *fm = get_fuse_mount(inode);
+ int err;
+
+ if (fuse_is_bad(inode))
+ return -EIO;
+
+ err = generic_file_open(inode, file);
+ if (err)
+ return err;
+
+ err = fuse_do_open(fm, get_node_id(inode), file, true);
+ if (!err) {
+ struct fuse_file *ff = file->private_data;
+
+ /*
+ * Keep handling FOPEN_STREAM and FOPEN_NONSEEKABLE for
+ * directories for backward compatibility, though it's unlikely
+ * to be useful.
+ */
+ if (ff->open_flags & (FOPEN_STREAM | FOPEN_NONSEEKABLE))
+ nonseekable_open(inode, file);
+ }
+
+ return err;
}
static int fuse_dir_release(struct inode *inode, struct file *file)
diff --git a/fs/fuse/file.c b/fs/fuse/file.c
index b9cff9b6ca..f39456c65e 100644
--- a/fs/fuse/file.c
+++ b/fs/fuse/file.c
@@ -20,6 +20,7 @@
#include <linux/fs.h>
#include <linux/filelock.h>
#include <linux/splice.h>
+#include <linux/task_io_accounting_ops.h>
static int fuse_send_open(struct fuse_mount *fm, u64 nodeid,
unsigned int open_flags, int opcode,
@@ -50,13 +51,7 @@ static int fuse_send_open(struct fuse_mount *fm, u64 nodeid,
return fuse_simple_request(fm, &args);
}
-struct fuse_release_args {
- struct fuse_args args;
- struct fuse_release_in inarg;
- struct inode *inode;
-};
-
-struct fuse_file *fuse_file_alloc(struct fuse_mount *fm)
+struct fuse_file *fuse_file_alloc(struct fuse_mount *fm, bool release)
{
struct fuse_file *ff;
@@ -65,15 +60,15 @@ struct fuse_file *fuse_file_alloc(struct fuse_mount *fm)
return NULL;
ff->fm = fm;
- ff->release_args = kzalloc(sizeof(*ff->release_args),
- GFP_KERNEL_ACCOUNT);
- if (!ff->release_args) {
- kfree(ff);
- return NULL;
+ if (release) {
+ ff->args = kzalloc(sizeof(*ff->args), GFP_KERNEL_ACCOUNT);
+ if (!ff->args) {
+ kfree(ff);
+ return NULL;
+ }
}
INIT_LIST_HEAD(&ff->write_entry);
- mutex_init(&ff->readdir.lock);
refcount_set(&ff->count, 1);
RB_CLEAR_NODE(&ff->polled_node);
init_waitqueue_head(&ff->poll_wait);
@@ -85,8 +80,7 @@ struct fuse_file *fuse_file_alloc(struct fuse_mount *fm)
void fuse_file_free(struct fuse_file *ff)
{
- kfree(ff->release_args);
- mutex_destroy(&ff->readdir.lock);
+ kfree(ff->args);
kfree(ff);
}
@@ -105,14 +99,17 @@ static void fuse_release_end(struct fuse_mount *fm, struct fuse_args *args,
kfree(ra);
}
-static void fuse_file_put(struct fuse_file *ff, bool sync, bool isdir)
+static void fuse_file_put(struct fuse_file *ff, bool sync)
{
if (refcount_dec_and_test(&ff->count)) {
- struct fuse_args *args = &ff->release_args->args;
+ struct fuse_release_args *ra = &ff->args->release_args;
+ struct fuse_args *args = (ra ? &ra->args : NULL);
- if (isdir ? ff->fm->fc->no_opendir : ff->fm->fc->no_open) {
- /* Do nothing when client does not implement 'open' */
- fuse_release_end(ff->fm, args, 0);
+ if (ra && ra->inode)
+ fuse_file_io_release(ff, ra->inode);
+
+ if (!args) {
+ /* Do nothing when server does not implement 'open' */
} else if (sync) {
fuse_simple_request(ff->fm, args);
fuse_release_end(ff->fm, args, 0);
@@ -132,27 +129,31 @@ struct fuse_file *fuse_file_open(struct fuse_mount *fm, u64 nodeid,
struct fuse_conn *fc = fm->fc;
struct fuse_file *ff;
int opcode = isdir ? FUSE_OPENDIR : FUSE_OPEN;
+ bool open = isdir ? !fc->no_opendir : !fc->no_open;
- ff = fuse_file_alloc(fm);
+ ff = fuse_file_alloc(fm, open);
if (!ff)
return ERR_PTR(-ENOMEM);
ff->fh = 0;
/* Default for no-open */
ff->open_flags = FOPEN_KEEP_CACHE | (isdir ? FOPEN_CACHE_DIR : 0);
- if (isdir ? !fc->no_opendir : !fc->no_open) {
- struct fuse_open_out outarg;
+ if (open) {
+ /* Store outarg for fuse_finish_open() */
+ struct fuse_open_out *outargp = &ff->args->open_outarg;
int err;
- err = fuse_send_open(fm, nodeid, open_flags, opcode, &outarg);
+ err = fuse_send_open(fm, nodeid, open_flags, opcode, outargp);
if (!err) {
- ff->fh = outarg.fh;
- ff->open_flags = outarg.open_flags;
-
+ ff->fh = outargp->fh;
+ ff->open_flags = outargp->open_flags;
} else if (err != -ENOSYS) {
fuse_file_free(ff);
return ERR_PTR(err);
} else {
+ /* No release needed */
+ kfree(ff->args);
+ ff->args = NULL;
if (isdir)
fc->no_opendir = 1;
else
@@ -195,40 +196,50 @@ static void fuse_link_write_file(struct file *file)
spin_unlock(&fi->lock);
}
-void fuse_finish_open(struct inode *inode, struct file *file)
+int fuse_finish_open(struct inode *inode, struct file *file)
{
struct fuse_file *ff = file->private_data;
struct fuse_conn *fc = get_fuse_conn(inode);
+ int err;
+
+ err = fuse_file_io_open(file, inode);
+ if (err)
+ return err;
if (ff->open_flags & FOPEN_STREAM)
stream_open(inode, file);
else if (ff->open_flags & FOPEN_NONSEEKABLE)
nonseekable_open(inode, file);
- if (fc->atomic_o_trunc && (file->f_flags & O_TRUNC)) {
- struct fuse_inode *fi = get_fuse_inode(inode);
-
- spin_lock(&fi->lock);
- fi->attr_version = atomic64_inc_return(&fc->attr_version);
- i_size_write(inode, 0);
- spin_unlock(&fi->lock);
- file_update_time(file);
- fuse_invalidate_attr_mask(inode, FUSE_STATX_MODSIZE);
- }
if ((file->f_mode & FMODE_WRITE) && fc->writeback_cache)
fuse_link_write_file(file);
+
+ return 0;
}
-int fuse_open_common(struct inode *inode, struct file *file, bool isdir)
+static void fuse_truncate_update_attr(struct inode *inode, struct file *file)
+{
+ struct fuse_conn *fc = get_fuse_conn(inode);
+ struct fuse_inode *fi = get_fuse_inode(inode);
+
+ spin_lock(&fi->lock);
+ fi->attr_version = atomic64_inc_return(&fc->attr_version);
+ i_size_write(inode, 0);
+ spin_unlock(&fi->lock);
+ file_update_time(file);
+ fuse_invalidate_attr_mask(inode, FUSE_STATX_MODSIZE);
+}
+
+static int fuse_open(struct inode *inode, struct file *file)
{
struct fuse_mount *fm = get_fuse_mount(inode);
+ struct fuse_inode *fi = get_fuse_inode(inode);
struct fuse_conn *fc = fm->fc;
+ struct fuse_file *ff;
int err;
- bool is_wb_truncate = (file->f_flags & O_TRUNC) &&
- fc->atomic_o_trunc &&
- fc->writeback_cache;
- bool dax_truncate = (file->f_flags & O_TRUNC) &&
- fc->atomic_o_trunc && FUSE_IS_DAX(inode);
+ bool is_truncate = (file->f_flags & O_TRUNC) && fc->atomic_o_trunc;
+ bool is_wb_truncate = is_truncate && fc->writeback_cache;
+ bool dax_truncate = is_truncate && FUSE_IS_DAX(inode);
if (fuse_is_bad(inode))
return -EIO;
@@ -250,16 +261,20 @@ int fuse_open_common(struct inode *inode, struct file *file, bool isdir)
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);
+ err = fuse_do_open(fm, get_node_id(inode), file, false);
+ if (!err) {
+ ff = file->private_data;
+ err = fuse_finish_open(inode, file);
+ if (err)
+ fuse_sync_release(fi, ff, file->f_flags);
+ else if (is_truncate)
+ fuse_truncate_update_attr(inode, file);
+ }
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))
+ if (is_truncate)
truncate_pagecache(inode, 0);
else if (!(ff->open_flags & FOPEN_KEEP_CACHE))
invalidate_inode_pages2(inode->i_mapping);
@@ -274,10 +289,13 @@ out_inode_unlock:
}
static void fuse_prepare_release(struct fuse_inode *fi, struct fuse_file *ff,
- unsigned int flags, int opcode)
+ unsigned int flags, int opcode, bool sync)
{
struct fuse_conn *fc = ff->fm->fc;
- struct fuse_release_args *ra = ff->release_args;
+ struct fuse_release_args *ra = &ff->args->release_args;
+
+ if (fuse_file_passthrough(ff))
+ fuse_passthrough_release(ff, fuse_inode_backing(fi));
/* Inode is NULL on error path of fuse_create_open() */
if (likely(fi)) {
@@ -292,6 +310,11 @@ static void fuse_prepare_release(struct fuse_inode *fi, struct fuse_file *ff,
wake_up_interruptible_all(&ff->poll_wait);
+ if (!ra)
+ return;
+
+ /* ff->args was used for open outarg */
+ memset(ff->args, 0, sizeof(*ff->args));
ra->inarg.fh = ff->fh;
ra->inarg.flags = flags;
ra->args.in_numargs = 1;
@@ -301,23 +324,28 @@ static void fuse_prepare_release(struct fuse_inode *fi, struct fuse_file *ff,
ra->args.nodeid = ff->nodeid;
ra->args.force = true;
ra->args.nocreds = true;
+
+ /*
+ * Hold inode until release is finished.
+ * From fuse_sync_release() the refcount is 1 and everything's
+ * synchronous, so we are fine with not doing igrab() here.
+ */
+ ra->inode = sync ? NULL : igrab(&fi->inode);
}
void fuse_file_release(struct inode *inode, struct fuse_file *ff,
unsigned int open_flags, fl_owner_t id, bool isdir)
{
struct fuse_inode *fi = get_fuse_inode(inode);
- struct fuse_release_args *ra = ff->release_args;
+ struct fuse_release_args *ra = &ff->args->release_args;
int opcode = isdir ? FUSE_RELEASEDIR : FUSE_RELEASE;
- fuse_prepare_release(fi, ff, open_flags, opcode);
+ fuse_prepare_release(fi, ff, open_flags, opcode, false);
- if (ff->flock) {
+ if (ra && ff->flock) {
ra->inarg.release_flags |= FUSE_RELEASE_FLOCK_UNLOCK;
ra->inarg.lock_owner = fuse_lock_owner_id(ff->fm->fc, id);
}
- /* Hold inode until release is finished */
- ra->inode = igrab(inode);
/*
* Normally this will send the RELEASE request, however if
@@ -328,7 +356,7 @@ void fuse_file_release(struct inode *inode, struct fuse_file *ff,
* synchronous RELEASE is allowed (and desirable) in this case
* because the server can be trusted not to screw up.
*/
- fuse_file_put(ff, ff->fm->fc->destroy, isdir);
+ fuse_file_put(ff, ff->fm->fc->destroy);
}
void fuse_release_common(struct file *file, bool isdir)
@@ -337,11 +365,6 @@ void fuse_release_common(struct file *file, bool isdir)
(fl_owner_t) file, isdir);
}
-static int fuse_open(struct inode *inode, struct file *file)
-{
- return fuse_open_common(inode, file, false);
-}
-
static int fuse_release(struct inode *inode, struct file *file)
{
struct fuse_conn *fc = get_fuse_conn(inode);
@@ -363,12 +386,8 @@ void fuse_sync_release(struct fuse_inode *fi, struct fuse_file *ff,
unsigned int flags)
{
WARN_ON(refcount_read(&ff->count) > 1);
- fuse_prepare_release(fi, ff, flags, FUSE_RELEASE);
- /*
- * iput(NULL) is a no-op and since the refcount is 1 and everything's
- * synchronous, we are fine with not doing igrab() here"
- */
- fuse_file_put(ff, true, false);
+ fuse_prepare_release(fi, ff, flags, FUSE_RELEASE, true);
+ fuse_file_put(ff, true);
}
EXPORT_SYMBOL_GPL(fuse_sync_release);
@@ -634,7 +653,8 @@ static void fuse_release_user_pages(struct fuse_args_pages *ap,
for (i = 0; i < ap->num_pages; i++) {
if (should_dirty)
set_page_dirty_lock(ap->pages[i]);
- put_page(ap->pages[i]);
+ if (ap->args.is_pinned)
+ unpin_user_page(ap->pages[i]);
}
}
@@ -915,17 +935,13 @@ static void fuse_readpages_end(struct fuse_mount *fm, struct fuse_args *args,
}
for (i = 0; i < ap->num_pages; i++) {
- struct page *page = ap->pages[i];
+ struct folio *folio = page_folio(ap->pages[i]);
- if (!err)
- SetPageUptodate(page);
- else
- SetPageError(page);
- unlock_page(page);
- put_page(page);
+ folio_end_read(folio, !err);
+ folio_put(folio);
}
if (ia->ff)
- fuse_file_put(ia->ff, false, false);
+ fuse_file_put(ia->ff, false);
fuse_io_free(ia);
}
@@ -1299,13 +1315,93 @@ static ssize_t fuse_perform_write(struct kiocb *iocb, struct iov_iter *ii)
return res;
}
+static bool fuse_io_past_eof(struct kiocb *iocb, struct iov_iter *iter)
+{
+ struct inode *inode = file_inode(iocb->ki_filp);
+
+ return iocb->ki_pos + iov_iter_count(iter) > i_size_read(inode);
+}
+
+/*
+ * @return true if an exclusive lock for direct IO writes is needed
+ */
+static bool fuse_dio_wr_exclusive_lock(struct kiocb *iocb, struct iov_iter *from)
+{
+ struct file *file = iocb->ki_filp;
+ struct fuse_file *ff = file->private_data;
+ struct inode *inode = file_inode(iocb->ki_filp);
+ struct fuse_inode *fi = get_fuse_inode(inode);
+
+ /* Server side has to advise that it supports parallel dio writes. */
+ if (!(ff->open_flags & FOPEN_PARALLEL_DIRECT_WRITES))
+ return true;
+
+ /*
+ * Append will need to know the eventual EOF - always needs an
+ * exclusive lock.
+ */
+ if (iocb->ki_flags & IOCB_APPEND)
+ return true;
+
+ /* shared locks are not allowed with parallel page cache IO */
+ if (test_bit(FUSE_I_CACHE_IO_MODE, &fi->state))
+ return false;
+
+ /* Parallel dio beyond EOF is not supported, at least for now. */
+ if (fuse_io_past_eof(iocb, from))
+ return true;
+
+ return false;
+}
+
+static void fuse_dio_lock(struct kiocb *iocb, struct iov_iter *from,
+ bool *exclusive)
+{
+ struct inode *inode = file_inode(iocb->ki_filp);
+ struct fuse_inode *fi = get_fuse_inode(inode);
+
+ *exclusive = fuse_dio_wr_exclusive_lock(iocb, from);
+ if (*exclusive) {
+ inode_lock(inode);
+ } else {
+ inode_lock_shared(inode);
+ /*
+ * New parallal dio allowed only if inode is not in caching
+ * mode and denies new opens in caching mode. This check
+ * should be performed only after taking shared inode lock.
+ * Previous past eof check was without inode lock and might
+ * have raced, so check it again.
+ */
+ if (fuse_io_past_eof(iocb, from) ||
+ fuse_inode_uncached_io_start(fi, NULL) != 0) {
+ inode_unlock_shared(inode);
+ inode_lock(inode);
+ *exclusive = true;
+ }
+ }
+}
+
+static void fuse_dio_unlock(struct kiocb *iocb, bool exclusive)
+{
+ struct inode *inode = file_inode(iocb->ki_filp);
+ struct fuse_inode *fi = get_fuse_inode(inode);
+
+ if (exclusive) {
+ inode_unlock(inode);
+ } else {
+ /* Allow opens in caching mode after last parallel dio end */
+ fuse_inode_uncached_io_end(fi);
+ inode_unlock_shared(inode);
+ }
+}
+
static ssize_t fuse_cache_write_iter(struct kiocb *iocb, struct iov_iter *from)
{
struct file *file = iocb->ki_filp;
struct address_space *mapping = file->f_mapping;
ssize_t written = 0;
struct inode *inode = mapping->host;
- ssize_t err;
+ ssize_t err, count;
struct fuse_conn *fc = get_fuse_conn(inode);
if (fc->writeback_cache) {
@@ -1327,10 +1423,12 @@ static ssize_t fuse_cache_write_iter(struct kiocb *iocb, struct iov_iter *from)
writethrough:
inode_lock(inode);
- err = generic_write_checks(iocb, from);
+ err = count = generic_write_checks(iocb, from);
if (err <= 0)
goto out;
+ task_io_account_write(count);
+
err = file_remove_privs(file);
if (err)
goto out;
@@ -1392,10 +1490,13 @@ 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_pages2(ii, &ap->pages[ap->num_pages],
- *nbytesp - nbytes,
- max_pages - ap->num_pages,
- &start);
+ struct page **pt_pages;
+
+ pt_pages = &ap->pages[ap->num_pages];
+ ret = iov_iter_extract_pages(ii, &pt_pages,
+ *nbytesp - nbytes,
+ max_pages - ap->num_pages,
+ 0, &start);
if (ret < 0)
break;
@@ -1412,6 +1513,7 @@ static int fuse_get_user_pages(struct fuse_args_pages *ap, struct iov_iter *ii,
(PAGE_SIZE - ret) & (PAGE_SIZE - 1);
}
+ ap->args.is_pinned = iov_iter_extract_will_pin(ii);
ap->args.user_pages = true;
if (write)
ap->args.in_pages = true;
@@ -1558,51 +1660,17 @@ static ssize_t fuse_direct_read_iter(struct kiocb *iocb, struct iov_iter *to)
return res;
}
-static bool fuse_direct_write_extending_i_size(struct kiocb *iocb,
- struct iov_iter *iter)
-{
- struct inode *inode = file_inode(iocb->ki_filp);
-
- return iocb->ki_pos + iov_iter_count(iter) > i_size_read(inode);
-}
-
static ssize_t fuse_direct_write_iter(struct kiocb *iocb, struct iov_iter *from)
{
struct inode *inode = file_inode(iocb->ki_filp);
- struct file *file = iocb->ki_filp;
- struct fuse_file *ff = file->private_data;
struct fuse_io_priv io = FUSE_IO_PRIV_SYNC(iocb);
ssize_t res;
- bool exclusive_lock =
- !(ff->open_flags & FOPEN_PARALLEL_DIRECT_WRITES) ||
- get_fuse_conn(inode)->direct_io_allow_mmap ||
- iocb->ki_flags & IOCB_APPEND ||
- fuse_direct_write_extending_i_size(iocb, from);
-
- /*
- * Take exclusive lock if
- * - Parallel direct writes are disabled - a user space decision
- * - Parallel direct writes are enabled and i_size is being extended.
- * - Shared mmap on direct_io file is supported (FUSE_DIRECT_IO_ALLOW_MMAP).
- * This might not be needed at all, but needs further investigation.
- */
- if (exclusive_lock)
- inode_lock(inode);
- else {
- inode_lock_shared(inode);
-
- /* A race with truncate might have come up as the decision for
- * the lock type was done without holding the lock, check again.
- */
- if (fuse_direct_write_extending_i_size(iocb, from)) {
- inode_unlock_shared(inode);
- inode_lock(inode);
- exclusive_lock = true;
- }
- }
+ bool exclusive;
+ fuse_dio_lock(iocb, from, &exclusive);
res = generic_write_checks(iocb, from);
if (res > 0) {
+ task_io_account_write(res);
if (!is_sync_kiocb(iocb) && iocb->ki_flags & IOCB_DIRECT) {
res = fuse_direct_IO(iocb, from);
} else {
@@ -1611,10 +1679,7 @@ static ssize_t fuse_direct_write_iter(struct kiocb *iocb, struct iov_iter *from)
fuse_write_update_attr(inode, iocb->ki_pos, res);
}
}
- if (exclusive_lock)
- inode_unlock(inode);
- else
- inode_unlock_shared(inode);
+ fuse_dio_unlock(iocb, exclusive);
return res;
}
@@ -1631,10 +1696,13 @@ static ssize_t fuse_file_read_iter(struct kiocb *iocb, struct iov_iter *to)
if (FUSE_IS_DAX(inode))
return fuse_dax_read_iter(iocb, to);
- if (!(ff->open_flags & FOPEN_DIRECT_IO))
- return fuse_cache_read_iter(iocb, to);
- else
+ /* FOPEN_DIRECT_IO overrides FOPEN_PASSTHROUGH */
+ if (ff->open_flags & FOPEN_DIRECT_IO)
return fuse_direct_read_iter(iocb, to);
+ else if (fuse_file_passthrough(ff))
+ return fuse_passthrough_read_iter(iocb, to);
+ else
+ return fuse_cache_read_iter(iocb, to);
}
static ssize_t fuse_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
@@ -1649,10 +1717,38 @@ static ssize_t fuse_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
if (FUSE_IS_DAX(inode))
return fuse_dax_write_iter(iocb, from);
- if (!(ff->open_flags & FOPEN_DIRECT_IO))
+ /* FOPEN_DIRECT_IO overrides FOPEN_PASSTHROUGH */
+ if (ff->open_flags & FOPEN_DIRECT_IO)
+ return fuse_direct_write_iter(iocb, from);
+ else if (fuse_file_passthrough(ff))
+ return fuse_passthrough_write_iter(iocb, from);
+ else
return fuse_cache_write_iter(iocb, from);
+}
+
+static ssize_t fuse_splice_read(struct file *in, loff_t *ppos,
+ struct pipe_inode_info *pipe, size_t len,
+ unsigned int flags)
+{
+ struct fuse_file *ff = in->private_data;
+
+ /* FOPEN_DIRECT_IO overrides FOPEN_PASSTHROUGH */
+ if (fuse_file_passthrough(ff) && !(ff->open_flags & FOPEN_DIRECT_IO))
+ return fuse_passthrough_splice_read(in, ppos, pipe, len, flags);
else
- return fuse_direct_write_iter(iocb, from);
+ return filemap_splice_read(in, ppos, pipe, len, flags);
+}
+
+static ssize_t fuse_splice_write(struct pipe_inode_info *pipe, struct file *out,
+ loff_t *ppos, size_t len, unsigned int flags)
+{
+ struct fuse_file *ff = out->private_data;
+
+ /* FOPEN_DIRECT_IO overrides FOPEN_PASSTHROUGH */
+ if (fuse_file_passthrough(ff) && !(ff->open_flags & FOPEN_DIRECT_IO))
+ return fuse_passthrough_splice_write(pipe, out, ppos, len, flags);
+ else
+ return iter_file_splice_write(pipe, out, ppos, len, flags);
}
static void fuse_writepage_free(struct fuse_writepage_args *wpa)
@@ -1667,7 +1763,7 @@ static void fuse_writepage_free(struct fuse_writepage_args *wpa)
__free_page(ap->pages[i]);
if (wpa->ia.ff)
- fuse_file_put(wpa->ia.ff, false, false);
+ fuse_file_put(wpa->ia.ff, false);
kfree(ap->pages);
kfree(wpa);
@@ -1909,7 +2005,7 @@ int fuse_write_inode(struct inode *inode, struct writeback_control *wbc)
ff = __fuse_write_file_get(fi);
err = fuse_flush_times(inode, ff);
if (ff)
- fuse_file_put(ff, false, false);
+ fuse_file_put(ff, false);
return err;
}
@@ -1947,26 +2043,26 @@ static void fuse_writepage_add_to_bucket(struct fuse_conn *fc,
rcu_read_unlock();
}
-static int fuse_writepage_locked(struct page *page)
+static int fuse_writepage_locked(struct folio *folio)
{
- struct address_space *mapping = page->mapping;
+ struct address_space *mapping = folio->mapping;
struct inode *inode = mapping->host;
struct fuse_conn *fc = get_fuse_conn(inode);
struct fuse_inode *fi = get_fuse_inode(inode);
struct fuse_writepage_args *wpa;
struct fuse_args_pages *ap;
- struct page *tmp_page;
+ struct folio *tmp_folio;
int error = -ENOMEM;
- set_page_writeback(page);
+ folio_start_writeback(folio);
wpa = fuse_writepage_args_alloc();
if (!wpa)
goto err;
ap = &wpa->ia.ap;
- tmp_page = alloc_page(GFP_NOFS | __GFP_HIGHMEM);
- if (!tmp_page)
+ tmp_folio = folio_alloc(GFP_NOFS | __GFP_HIGHMEM, 0);
+ if (!tmp_folio)
goto err_free;
error = -EIO;
@@ -1975,21 +2071,21 @@ static int fuse_writepage_locked(struct page *page)
goto err_nofile;
fuse_writepage_add_to_bucket(fc, wpa);
- fuse_write_args_fill(&wpa->ia, wpa->ia.ff, page_offset(page), 0);
+ fuse_write_args_fill(&wpa->ia, wpa->ia.ff, folio_pos(folio), 0);
- copy_highpage(tmp_page, page);
+ folio_copy(tmp_folio, folio);
wpa->ia.write.in.write_flags |= FUSE_WRITE_CACHE;
wpa->next = NULL;
ap->args.in_pages = true;
ap->num_pages = 1;
- ap->pages[0] = tmp_page;
+ ap->pages[0] = &tmp_folio->page;
ap->descs[0].offset = 0;
ap->descs[0].length = PAGE_SIZE;
ap->args.end = fuse_writepage_end;
wpa->inode = inode;
inc_wb_stat(&inode_to_bdi(inode)->wb, WB_WRITEBACK);
- inc_node_page_state(tmp_page, NR_WRITEBACK_TEMP);
+ node_stat_add_folio(tmp_folio, NR_WRITEBACK_TEMP);
spin_lock(&fi->lock);
tree_insert(&fi->writepages, wpa);
@@ -1997,48 +2093,20 @@ static int fuse_writepage_locked(struct page *page)
fuse_flush_writepages(inode);
spin_unlock(&fi->lock);
- end_page_writeback(page);
+ folio_end_writeback(folio);
return 0;
err_nofile:
- __free_page(tmp_page);
+ folio_put(tmp_folio);
err_free:
kfree(wpa);
err:
- mapping_set_error(page->mapping, error);
- end_page_writeback(page);
+ mapping_set_error(folio->mapping, error);
+ folio_end_writeback(folio);
return error;
}
-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)) {
- /*
- * ->writepages() should be called for sync() and friends. We
- * should only get here on direct reclaim and then we are
- * allowed to skip a page which is already in flight
- */
- WARN_ON(wbc->sync_mode == WB_SYNC_ALL);
-
- redirty_page_for_writepage(wbc, page);
- unlock_page(page);
- 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);
-
- return err;
-}
-
struct fuse_fill_wb_data {
struct fuse_writepage_args *wpa;
struct fuse_file *ff;
@@ -2307,7 +2375,7 @@ static int fuse_writepages(struct address_space *mapping,
fuse_writepages_send(&data);
}
if (data.ff)
- fuse_file_put(data.ff, false, false);
+ fuse_file_put(data.ff, false);
kfree(data.orig_pages);
out:
@@ -2401,7 +2469,7 @@ static int fuse_launder_folio(struct folio *folio)
/* Serialize with pending writeback for the same page */
fuse_wait_on_page_writeback(inode, folio->index);
- err = fuse_writepage_locked(&folio->page);
+ err = fuse_writepage_locked(folio);
if (!err)
fuse_wait_on_page_writeback(inode, folio->index);
}
@@ -2462,11 +2530,27 @@ static int fuse_file_mmap(struct file *file, struct vm_area_struct *vma)
{
struct fuse_file *ff = file->private_data;
struct fuse_conn *fc = ff->fm->fc;
+ struct inode *inode = file_inode(file);
+ int rc;
/* DAX mmap is superior to direct_io mmap */
- if (FUSE_IS_DAX(file_inode(file)))
+ if (FUSE_IS_DAX(inode))
return fuse_dax_mmap(file, vma);
+ /*
+ * If inode is in passthrough io mode, because it has some file open
+ * in passthrough mode, either mmap to backing file or fail mmap,
+ * because mixing cached mmap and passthrough io mode is not allowed.
+ */
+ if (fuse_file_passthrough(ff))
+ return fuse_passthrough_mmap(file, vma);
+ else if (fuse_inode_backing(get_fuse_inode(inode)))
+ return -ENODEV;
+
+ /*
+ * FOPEN_DIRECT_IO handling is special compared to O_DIRECT,
+ * as does not allow MAP_SHARED mmap without FUSE_DIRECT_IO_ALLOW_MMAP.
+ */
if (ff->open_flags & FOPEN_DIRECT_IO) {
/*
* Can't provide the coherency needed for MAP_SHARED
@@ -2481,6 +2565,17 @@ static int fuse_file_mmap(struct file *file, struct vm_area_struct *vma)
/* MAP_PRIVATE */
return generic_file_mmap(file, vma);
}
+
+ /*
+ * First mmap of direct_io file enters caching inode io mode.
+ * Also waits for parallel dio writers to go into serial mode
+ * (exclusive instead of shared lock).
+ * After first mmap, the inode stays in caching io mode until
+ * the direct_io file release.
+ */
+ rc = fuse_file_cached_io_open(inode, ff);
+ if (rc)
+ return rc;
}
if ((vma->vm_flags & VM_SHARED) && (vma->vm_flags & VM_MAYWRITE))
@@ -2513,14 +2608,14 @@ static int convert_fuse_file_lock(struct fuse_conn *fc,
* translate it into the caller's pid namespace.
*/
rcu_read_lock();
- fl->fl_pid = pid_nr_ns(find_pid_ns(ffl->pid, fc->pid_ns), &init_pid_ns);
+ fl->c.flc_pid = pid_nr_ns(find_pid_ns(ffl->pid, fc->pid_ns), &init_pid_ns);
rcu_read_unlock();
break;
default:
return -EIO;
}
- fl->fl_type = ffl->type;
+ fl->c.flc_type = ffl->type;
return 0;
}
@@ -2534,10 +2629,10 @@ static void fuse_lk_fill(struct fuse_args *args, struct file *file,
memset(inarg, 0, sizeof(*inarg));
inarg->fh = ff->fh;
- inarg->owner = fuse_lock_owner_id(fc, fl->fl_owner);
+ inarg->owner = fuse_lock_owner_id(fc, fl->c.flc_owner);
inarg->lk.start = fl->fl_start;
inarg->lk.end = fl->fl_end;
- inarg->lk.type = fl->fl_type;
+ inarg->lk.type = fl->c.flc_type;
inarg->lk.pid = pid;
if (flock)
inarg->lk_flags |= FUSE_LK_FLOCK;
@@ -2574,8 +2669,8 @@ static int fuse_setlk(struct file *file, struct file_lock *fl, int flock)
struct fuse_mount *fm = get_fuse_mount(inode);
FUSE_ARGS(args);
struct fuse_lk_in inarg;
- int opcode = (fl->fl_flags & FL_SLEEP) ? FUSE_SETLKW : FUSE_SETLK;
- struct pid *pid = fl->fl_type != F_UNLCK ? task_tgid(current) : NULL;
+ int opcode = (fl->c.flc_flags & FL_SLEEP) ? FUSE_SETLKW : FUSE_SETLK;
+ struct pid *pid = fl->c.flc_type != F_UNLCK ? task_tgid(current) : NULL;
pid_t pid_nr = pid_nr_ns(pid, fm->fc->pid_ns);
int err;
@@ -2584,10 +2679,6 @@ static int fuse_setlk(struct file *file, struct file_lock *fl, int flock)
return -ENOLCK;
}
- /* Unlock on close is handled by the flush method */
- if ((fl->fl_flags & FL_CLOSE_POSIX) == FL_CLOSE_POSIX)
- return 0;
-
fuse_lk_fill(&args, file, fl, opcode, pid_nr, flock, &inarg);
err = fuse_simple_request(fm, &args);
@@ -3217,8 +3308,8 @@ static const struct file_operations fuse_file_operations = {
.lock = fuse_file_lock,
.get_unmapped_area = thp_get_unmapped_area,
.flock = fuse_file_flock,
- .splice_read = filemap_splice_read,
- .splice_write = iter_file_splice_write,
+ .splice_read = fuse_splice_read,
+ .splice_write = fuse_splice_write,
.unlocked_ioctl = fuse_file_ioctl,
.compat_ioctl = fuse_file_compat_ioctl,
.poll = fuse_file_poll,
@@ -3229,10 +3320,10 @@ static const struct file_operations fuse_file_operations = {
static const struct address_space_operations fuse_file_aops = {
.read_folio = fuse_read_folio,
.readahead = fuse_readahead,
- .writepage = fuse_writepage,
.writepages = fuse_writepages,
.launder_folio = fuse_launder_folio,
.dirty_folio = filemap_dirty_folio,
+ .migrate_folio = filemap_migrate_folio,
.bmap = fuse_bmap,
.direct_IO = fuse_direct_IO,
.write_begin = fuse_write_begin,
@@ -3249,7 +3340,9 @@ void fuse_init_file_inode(struct inode *inode, unsigned int flags)
INIT_LIST_HEAD(&fi->write_files);
INIT_LIST_HEAD(&fi->queued_writes);
fi->writectr = 0;
+ fi->iocachectr = 0;
init_waitqueue_head(&fi->page_waitq);
+ init_waitqueue_head(&fi->direct_io_waitq);
fi->writepages = RB_ROOT;
if (IS_ENABLED(CONFIG_FUSE_DAX))
diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h
index 20924e799c..f239196103 100644
--- a/fs/fuse/fuse_i.h
+++ b/fs/fuse/fuse_i.h
@@ -76,6 +76,16 @@ struct fuse_submount_lookup {
struct fuse_forget_link *forget;
};
+/** Container for data related to mapping to backing file */
+struct fuse_backing {
+ struct file *file;
+ struct cred *cred;
+
+ /** refcount */
+ refcount_t count;
+ struct rcu_head rcu;
+};
+
/** FUSE inode */
struct fuse_inode {
/** Inode data */
@@ -111,7 +121,7 @@ struct fuse_inode {
u64 attr_version;
union {
- /* Write related fields (regular file only) */
+ /* read/write io cache (regular file only) */
struct {
/* Files usable in writepage. Protected by fi->lock */
struct list_head write_files;
@@ -123,9 +133,15 @@ struct fuse_inode {
* (FUSE_NOWRITE) means more writes are blocked */
int writectr;
+ /** Number of files/maps using page cache */
+ int iocachectr;
+
/* Waitq for writepage completion */
wait_queue_head_t page_waitq;
+ /* waitq for direct-io completion */
+ wait_queue_head_t direct_io_waitq;
+
/* List of writepage requestst (pending or sent) */
struct rb_root writepages;
};
@@ -173,6 +189,10 @@ struct fuse_inode {
#endif
/** Submount specific lookup tracking */
struct fuse_submount_lookup *submount_lookup;
+#ifdef CONFIG_FUSE_PASSTHROUGH
+ /** Reference to backing file in passthrough mode */
+ struct fuse_backing *fb;
+#endif
};
/** FUSE inode state bits */
@@ -187,19 +207,21 @@ enum {
FUSE_I_BAD,
/* Has btime */
FUSE_I_BTIME,
+ /* Wants or already has page cache IO */
+ FUSE_I_CACHE_IO_MODE,
};
struct fuse_conn;
struct fuse_mount;
-struct fuse_release_args;
+union fuse_file_args;
/** FUSE specific file data */
struct fuse_file {
/** Fuse connection for this file */
struct fuse_mount *fm;
- /* Argument space reserved for release */
- struct fuse_release_args *release_args;
+ /* Argument space reserved for open/release */
+ union fuse_file_args *args;
/** Kernel file handle guaranteed to be unique */
u64 kh;
@@ -221,12 +243,6 @@ struct fuse_file {
/* Readdir related */
struct {
- /*
- * Protects below fields against (crazy) parallel readdir on
- * same open file. Uncontended in the normal case.
- */
- struct mutex lock;
-
/* Dir stream position */
loff_t pos;
@@ -244,6 +260,15 @@ struct fuse_file {
/** Wait queue head for poll */
wait_queue_head_t poll_wait;
+ /** Does file hold a fi->iocachectr refcount? */
+ enum { IOM_NONE, IOM_CACHED, IOM_UNCACHED } iomode;
+
+#ifdef CONFIG_FUSE_PASSTHROUGH
+ /** Reference to backing file in passthrough mode */
+ struct file *passthrough;
+ const struct cred *cred;
+#endif
+
/** Has flock been performed on this file? */
bool flock:1;
};
@@ -283,6 +308,7 @@ struct fuse_args {
bool page_replace:1;
bool may_block:1;
bool is_ext:1;
+ bool is_pinned:1;
struct fuse_in_arg in_args[3];
struct fuse_arg out_args[2];
void (*end)(struct fuse_mount *fm, struct fuse_args *args, int error);
@@ -295,6 +321,19 @@ struct fuse_args_pages {
unsigned int num_pages;
};
+struct fuse_release_args {
+ struct fuse_args args;
+ struct fuse_release_in inarg;
+ struct inode *inode;
+};
+
+union fuse_file_args {
+ /* Used during open() */
+ struct fuse_open_out open_outarg;
+ /* Used during release() */
+ struct fuse_release_args release_args;
+};
+
#define FUSE_ARGS(args) struct fuse_args args = {}
/** The request IO state (for asynchronous processing) */
@@ -818,6 +857,12 @@ struct fuse_conn {
/* Is statx not implemented by fs? */
unsigned int no_statx:1;
+ /** Passthrough support for read/write IO */
+ unsigned int passthrough:1;
+
+ /** Maximum stack depth for passthrough backing files */
+ int max_stack_depth;
+
/** The number of requests waiting for completion */
atomic_t num_waiting;
@@ -867,6 +912,11 @@ struct fuse_conn {
/* New writepages go into this bucket */
struct fuse_sync_bucket __rcu *curr_bucket;
+
+#ifdef CONFIG_FUSE_PASSTHROUGH
+ /** IDR for backing files ids */
+ struct idr backing_files_map;
+#endif
};
/*
@@ -1031,14 +1081,9 @@ void fuse_read_args_fill(struct fuse_io_args *ia, struct file *file, loff_t pos,
size_t count, int opcode);
-/**
- * Send OPEN or OPENDIR request
- */
-int fuse_open_common(struct inode *inode, struct file *file, bool isdir);
-
-struct fuse_file *fuse_file_alloc(struct fuse_mount *fm);
+struct fuse_file *fuse_file_alloc(struct fuse_mount *fm, bool release);
void fuse_file_free(struct fuse_file *ff);
-void fuse_finish_open(struct inode *inode, struct file *file);
+int fuse_finish_open(struct inode *inode, struct file *file);
void fuse_sync_release(struct fuse_inode *fi, struct fuse_file *ff,
unsigned int flags);
@@ -1348,11 +1393,83 @@ int fuse_fileattr_get(struct dentry *dentry, struct fileattr *fa);
int fuse_fileattr_set(struct mnt_idmap *idmap,
struct dentry *dentry, struct fileattr *fa);
-/* file.c */
+/* iomode.c */
+int fuse_file_cached_io_open(struct inode *inode, struct fuse_file *ff);
+int fuse_inode_uncached_io_start(struct fuse_inode *fi,
+ struct fuse_backing *fb);
+void fuse_inode_uncached_io_end(struct fuse_inode *fi);
+
+int fuse_file_io_open(struct file *file, struct inode *inode);
+void fuse_file_io_release(struct fuse_file *ff, struct inode *inode);
+/* file.c */
struct fuse_file *fuse_file_open(struct fuse_mount *fm, u64 nodeid,
unsigned int open_flags, bool isdir);
void fuse_file_release(struct inode *inode, struct fuse_file *ff,
unsigned int open_flags, fl_owner_t id, bool isdir);
+/* passthrough.c */
+static inline struct fuse_backing *fuse_inode_backing(struct fuse_inode *fi)
+{
+#ifdef CONFIG_FUSE_PASSTHROUGH
+ return READ_ONCE(fi->fb);
+#else
+ return NULL;
+#endif
+}
+
+static inline struct fuse_backing *fuse_inode_backing_set(struct fuse_inode *fi,
+ struct fuse_backing *fb)
+{
+#ifdef CONFIG_FUSE_PASSTHROUGH
+ return xchg(&fi->fb, fb);
+#else
+ return NULL;
+#endif
+}
+
+#ifdef CONFIG_FUSE_PASSTHROUGH
+struct fuse_backing *fuse_backing_get(struct fuse_backing *fb);
+void fuse_backing_put(struct fuse_backing *fb);
+#else
+
+static inline struct fuse_backing *fuse_backing_get(struct fuse_backing *fb)
+{
+ return NULL;
+}
+
+static inline void fuse_backing_put(struct fuse_backing *fb)
+{
+}
+#endif
+
+void fuse_backing_files_init(struct fuse_conn *fc);
+void fuse_backing_files_free(struct fuse_conn *fc);
+int fuse_backing_open(struct fuse_conn *fc, struct fuse_backing_map *map);
+int fuse_backing_close(struct fuse_conn *fc, int backing_id);
+
+struct fuse_backing *fuse_passthrough_open(struct file *file,
+ struct inode *inode,
+ int backing_id);
+void fuse_passthrough_release(struct fuse_file *ff, struct fuse_backing *fb);
+
+static inline struct file *fuse_file_passthrough(struct fuse_file *ff)
+{
+#ifdef CONFIG_FUSE_PASSTHROUGH
+ return ff->passthrough;
+#else
+ return NULL;
+#endif
+}
+
+ssize_t fuse_passthrough_read_iter(struct kiocb *iocb, struct iov_iter *iter);
+ssize_t fuse_passthrough_write_iter(struct kiocb *iocb, struct iov_iter *iter);
+ssize_t fuse_passthrough_splice_read(struct file *in, loff_t *ppos,
+ struct pipe_inode_info *pipe,
+ size_t len, unsigned int flags);
+ssize_t fuse_passthrough_splice_write(struct pipe_inode_info *pipe,
+ struct file *out, loff_t *ppos,
+ size_t len, unsigned int flags);
+ssize_t fuse_passthrough_mmap(struct file *file, struct vm_area_struct *vma);
+
#endif /* _FS_FUSE_I_H */
diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c
index f73865751c..32fe6fa72f 100644
--- a/fs/fuse/inode.c
+++ b/fs/fuse/inode.c
@@ -111,6 +111,9 @@ static struct inode *fuse_alloc_inode(struct super_block *sb)
if (IS_ENABLED(CONFIG_FUSE_DAX) && !fuse_dax_inode_alloc(sb, fi))
goto out_free_forget;
+ if (IS_ENABLED(CONFIG_FUSE_PASSTHROUGH))
+ fuse_inode_backing_set(fi, NULL);
+
return &fi->inode;
out_free_forget:
@@ -129,6 +132,9 @@ static void fuse_free_inode(struct inode *inode)
#ifdef CONFIG_FUSE_DAX
kfree(fi->dax);
#endif
+ if (IS_ENABLED(CONFIG_FUSE_PASSTHROUGH))
+ fuse_backing_put(fuse_inode_backing(fi));
+
kmem_cache_free(fuse_inode_cachep, fi);
}
@@ -169,6 +175,7 @@ static void fuse_evict_inode(struct inode *inode)
}
}
if (S_ISREG(inode->i_mode) && !fuse_is_bad(inode)) {
+ WARN_ON(fi->iocachectr != 0);
WARN_ON(!list_empty(&fi->write_files));
WARN_ON(!list_empty(&fi->queued_writes));
}
@@ -748,6 +755,8 @@ static int fuse_parse_param(struct fs_context *fsc, struct fs_parameter *param)
struct fs_parse_result result;
struct fuse_fs_context *ctx = fsc->fs_private;
int opt;
+ kuid_t kuid;
+ kgid_t kgid;
if (fsc->purpose == FS_CONTEXT_FOR_RECONFIGURE) {
/*
@@ -792,16 +801,30 @@ static int fuse_parse_param(struct fs_context *fsc, struct fs_parameter *param)
break;
case OPT_USER_ID:
- ctx->user_id = make_kuid(fsc->user_ns, result.uint_32);
- if (!uid_valid(ctx->user_id))
+ kuid = make_kuid(fsc->user_ns, result.uint_32);
+ if (!uid_valid(kuid))
+ return invalfc(fsc, "Invalid user_id");
+ /*
+ * The requested uid must be representable in the
+ * filesystem's idmapping.
+ */
+ if (!kuid_has_mapping(fsc->user_ns, kuid))
return invalfc(fsc, "Invalid user_id");
+ ctx->user_id = kuid;
ctx->user_id_present = true;
break;
case OPT_GROUP_ID:
- ctx->group_id = make_kgid(fsc->user_ns, result.uint_32);
- if (!gid_valid(ctx->group_id))
+ kgid = make_kgid(fsc->user_ns, result.uint_32);;
+ if (!gid_valid(kgid))
+ return invalfc(fsc, "Invalid group_id");
+ /*
+ * The requested gid must be representable in the
+ * filesystem's idmapping.
+ */
+ if (!kgid_has_mapping(fsc->user_ns, kgid))
return invalfc(fsc, "Invalid group_id");
+ ctx->group_id = kgid;
ctx->group_id_present = true;
break;
@@ -927,6 +950,9 @@ void fuse_conn_init(struct fuse_conn *fc, struct fuse_mount *fm,
fc->max_pages = FUSE_DEFAULT_MAX_PAGES_PER_REQ;
fc->max_pages_limit = FUSE_MAX_MAX_PAGES;
+ if (IS_ENABLED(CONFIG_FUSE_PASSTHROUGH))
+ fuse_backing_files_init(fc);
+
INIT_LIST_HEAD(&fc->mounts);
list_add(&fm->fc_entry, &fc->mounts);
fm->fc = fc;
@@ -957,6 +983,8 @@ void fuse_conn_put(struct fuse_conn *fc)
WARN_ON(atomic_read(&bucket->count) != 1);
kfree(bucket);
}
+ if (IS_ENABLED(CONFIG_FUSE_PASSTHROUGH))
+ fuse_backing_files_free(fc);
call_rcu(&fc->rcu, delayed_release);
}
}
@@ -977,7 +1005,7 @@ static struct inode *fuse_get_root_inode(struct super_block *sb, unsigned mode)
attr.mode = mode;
attr.ino = FUSE_ROOT_ID;
attr.nlink = 1;
- return fuse_iget(sb, 1, 0, &attr, 0, 0);
+ return fuse_iget(sb, FUSE_ROOT_ID, 0, &attr, 0, 0);
}
struct fuse_inode_handle {
@@ -1120,6 +1148,11 @@ static struct dentry *fuse_get_parent(struct dentry *child)
return parent;
}
+/* only for fid encoding; no support for file handle */
+static const struct export_operations fuse_export_fid_operations = {
+ .encode_fh = fuse_encode_fh,
+};
+
static const struct export_operations fuse_export_operations = {
.fh_to_dentry = fuse_fh_to_dentry,
.fh_to_parent = fuse_fh_to_parent,
@@ -1294,6 +1327,26 @@ static void process_init_reply(struct fuse_mount *fm, struct fuse_args *args,
fc->create_supp_group = 1;
if (flags & FUSE_DIRECT_IO_ALLOW_MMAP)
fc->direct_io_allow_mmap = 1;
+ /*
+ * max_stack_depth is the max stack depth of FUSE fs,
+ * so it has to be at least 1 to support passthrough
+ * to backing files.
+ *
+ * with max_stack_depth > 1, the backing files can be
+ * on a stacked fs (e.g. overlayfs) themselves and with
+ * max_stack_depth == 1, FUSE fs can be stacked as the
+ * underlying fs of a stacked fs (e.g. overlayfs).
+ */
+ if (IS_ENABLED(CONFIG_FUSE_PASSTHROUGH) &&
+ (flags & FUSE_PASSTHROUGH) &&
+ arg->max_stack_depth > 0 &&
+ arg->max_stack_depth <= FILESYSTEM_MAX_STACK_DEPTH) {
+ fc->passthrough = 1;
+ fc->max_stack_depth = arg->max_stack_depth;
+ fm->sb->s_stack_depth = arg->max_stack_depth;
+ }
+ if (flags & FUSE_NO_EXPORT_SUPPORT)
+ fm->sb->s_export_op = &fuse_export_fid_operations;
} else {
ra_pages = fc->max_read / PAGE_SIZE;
fc->no_lock = 1;
@@ -1340,7 +1393,8 @@ void fuse_send_init(struct fuse_mount *fm)
FUSE_NO_OPENDIR_SUPPORT | FUSE_EXPLICIT_INVAL_DATA |
FUSE_HANDLE_KILLPRIV_V2 | FUSE_SETXATTR_EXT | FUSE_INIT_EXT |
FUSE_SECURITY_CTX | FUSE_CREATE_SUPP_GROUP |
- FUSE_HAS_EXPIRE_ONLY | FUSE_DIRECT_IO_ALLOW_MMAP;
+ FUSE_HAS_EXPIRE_ONLY | FUSE_DIRECT_IO_ALLOW_MMAP |
+ FUSE_NO_EXPORT_SUPPORT | FUSE_HAS_RESEND;
#ifdef CONFIG_FUSE_DAX
if (fm->fc->dax)
flags |= FUSE_MAP_ALIGNMENT;
@@ -1349,6 +1403,8 @@ void fuse_send_init(struct fuse_mount *fm)
#endif
if (fm->fc->auto_submounts)
flags |= FUSE_SUBMOUNTS;
+ if (IS_ENABLED(CONFIG_FUSE_PASSTHROUGH))
+ flags |= FUSE_PASSTHROUGH;
ia->in.flags = flags;
ia->in.flags2 = flags >> 32;
@@ -1499,8 +1555,8 @@ static void fuse_fill_attr_from_inode(struct fuse_attr *attr,
.ctimensec = ctime.tv_nsec,
.mode = fi->inode.i_mode,
.nlink = fi->inode.i_nlink,
- .uid = fi->inode.i_uid.val,
- .gid = fi->inode.i_gid.val,
+ .uid = __kuid_val(fi->inode.i_uid),
+ .gid = __kgid_val(fi->inode.i_gid),
.rdev = fi->inode.i_rdev,
.blksize = 1u << fi->inode.i_blkbits,
};
@@ -1537,6 +1593,7 @@ static int fuse_fill_super_submount(struct super_block *sb,
sb->s_bdi = bdi_get(parent_sb->s_bdi);
sb->s_xattr = parent_sb->s_xattr;
+ sb->s_export_op = parent_sb->s_export_op;
sb->s_time_gran = parent_sb->s_time_gran;
sb->s_blocksize = parent_sb->s_blocksize;
sb->s_blocksize_bits = parent_sb->s_blocksize_bits;
diff --git a/fs/fuse/ioctl.c b/fs/fuse/ioctl.c
index 726640fa43..572ce8a82c 100644
--- a/fs/fuse/ioctl.c
+++ b/fs/fuse/ioctl.c
@@ -8,6 +8,7 @@
#include <linux/uio.h>
#include <linux/compat.h>
#include <linux/fileattr.h>
+#include <linux/fsverity.h>
static ssize_t fuse_send_ioctl(struct fuse_mount *fm, struct fuse_args *args,
struct fuse_ioctl_out *outarg)
@@ -117,6 +118,53 @@ static int fuse_copy_ioctl_iovec(struct fuse_conn *fc, struct iovec *dst,
return 0;
}
+/* For fs-verity, determine iov lengths from input */
+static int fuse_setup_measure_verity(unsigned long arg, struct iovec *iov)
+{
+ __u16 digest_size;
+ struct fsverity_digest __user *uarg = (void __user *)arg;
+
+ if (copy_from_user(&digest_size, &uarg->digest_size, sizeof(digest_size)))
+ return -EFAULT;
+
+ if (digest_size > SIZE_MAX - sizeof(struct fsverity_digest))
+ return -EINVAL;
+
+ iov->iov_len = sizeof(struct fsverity_digest) + digest_size;
+
+ return 0;
+}
+
+static int fuse_setup_enable_verity(unsigned long arg, struct iovec *iov,
+ unsigned int *in_iovs)
+{
+ struct fsverity_enable_arg enable;
+ struct fsverity_enable_arg __user *uarg = (void __user *)arg;
+ const __u32 max_buffer_len = FUSE_MAX_MAX_PAGES * PAGE_SIZE;
+
+ if (copy_from_user(&enable, uarg, sizeof(enable)))
+ return -EFAULT;
+
+ if (enable.salt_size > max_buffer_len || enable.sig_size > max_buffer_len)
+ return -ENOMEM;
+
+ if (enable.salt_size > 0) {
+ iov++;
+ (*in_iovs)++;
+
+ iov->iov_base = u64_to_user_ptr(enable.salt_ptr);
+ iov->iov_len = enable.salt_size;
+ }
+
+ if (enable.sig_size > 0) {
+ iov++;
+ (*in_iovs)++;
+
+ iov->iov_base = u64_to_user_ptr(enable.sig_ptr);
+ iov->iov_len = enable.sig_size;
+ }
+ return 0;
+}
/*
* For ioctls, there is no generic way to determine how much memory
@@ -227,6 +275,18 @@ long fuse_do_ioctl(struct file *file, unsigned int cmd, unsigned long arg,
out_iov = iov;
out_iovs = 1;
}
+
+ err = 0;
+ switch (cmd) {
+ case FS_IOC_MEASURE_VERITY:
+ err = fuse_setup_measure_verity(arg, iov);
+ break;
+ case FS_IOC_ENABLE_VERITY:
+ err = fuse_setup_enable_verity(arg, iov, &in_iovs);
+ break;
+ }
+ if (err)
+ goto out;
}
retry:
diff --git a/fs/fuse/iomode.c b/fs/fuse/iomode.c
new file mode 100644
index 0000000000..c99e285f31
--- /dev/null
+++ b/fs/fuse/iomode.c
@@ -0,0 +1,276 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * FUSE inode io modes.
+ *
+ * Copyright (c) 2024 CTERA Networks.
+ */
+
+#include "fuse_i.h"
+
+#include <linux/kernel.h>
+#include <linux/sched.h>
+#include <linux/file.h>
+#include <linux/fs.h>
+
+/*
+ * Return true if need to wait for new opens in caching mode.
+ */
+static inline bool fuse_is_io_cache_wait(struct fuse_inode *fi)
+{
+ return READ_ONCE(fi->iocachectr) < 0 && !fuse_inode_backing(fi);
+}
+
+/*
+ * Called on cached file open() and on first mmap() of direct_io file.
+ * Takes cached_io inode mode reference to be dropped on file release.
+ *
+ * Blocks new parallel dio writes and waits for the in-progress parallel dio
+ * writes to complete.
+ */
+int fuse_file_cached_io_open(struct inode *inode, struct fuse_file *ff)
+{
+ struct fuse_inode *fi = get_fuse_inode(inode);
+
+ /* There are no io modes if server does not implement open */
+ if (!ff->args)
+ return 0;
+
+ spin_lock(&fi->lock);
+ /*
+ * Setting the bit advises new direct-io writes to use an exclusive
+ * lock - without it the wait below might be forever.
+ */
+ while (fuse_is_io_cache_wait(fi)) {
+ set_bit(FUSE_I_CACHE_IO_MODE, &fi->state);
+ spin_unlock(&fi->lock);
+ wait_event(fi->direct_io_waitq, !fuse_is_io_cache_wait(fi));
+ spin_lock(&fi->lock);
+ }
+
+ /*
+ * Check if inode entered passthrough io mode while waiting for parallel
+ * dio write completion.
+ */
+ if (fuse_inode_backing(fi)) {
+ clear_bit(FUSE_I_CACHE_IO_MODE, &fi->state);
+ spin_unlock(&fi->lock);
+ return -ETXTBSY;
+ }
+
+ WARN_ON(ff->iomode == IOM_UNCACHED);
+ if (ff->iomode == IOM_NONE) {
+ ff->iomode = IOM_CACHED;
+ if (fi->iocachectr == 0)
+ set_bit(FUSE_I_CACHE_IO_MODE, &fi->state);
+ fi->iocachectr++;
+ }
+ spin_unlock(&fi->lock);
+ return 0;
+}
+
+static void fuse_file_cached_io_release(struct fuse_file *ff,
+ struct fuse_inode *fi)
+{
+ spin_lock(&fi->lock);
+ WARN_ON(fi->iocachectr <= 0);
+ WARN_ON(ff->iomode != IOM_CACHED);
+ ff->iomode = IOM_NONE;
+ fi->iocachectr--;
+ if (fi->iocachectr == 0)
+ clear_bit(FUSE_I_CACHE_IO_MODE, &fi->state);
+ spin_unlock(&fi->lock);
+}
+
+/* Start strictly uncached io mode where cache access is not allowed */
+int fuse_inode_uncached_io_start(struct fuse_inode *fi, struct fuse_backing *fb)
+{
+ struct fuse_backing *oldfb;
+ int err = 0;
+
+ spin_lock(&fi->lock);
+ /* deny conflicting backing files on same fuse inode */
+ oldfb = fuse_inode_backing(fi);
+ if (fb && oldfb && oldfb != fb) {
+ err = -EBUSY;
+ goto unlock;
+ }
+ if (fi->iocachectr > 0) {
+ err = -ETXTBSY;
+ goto unlock;
+ }
+ fi->iocachectr--;
+
+ /* fuse inode holds a single refcount of backing file */
+ if (fb && !oldfb) {
+ oldfb = fuse_inode_backing_set(fi, fb);
+ WARN_ON_ONCE(oldfb != NULL);
+ } else {
+ fuse_backing_put(fb);
+ }
+unlock:
+ spin_unlock(&fi->lock);
+ return err;
+}
+
+/* Takes uncached_io inode mode reference to be dropped on file release */
+static int fuse_file_uncached_io_open(struct inode *inode,
+ struct fuse_file *ff,
+ struct fuse_backing *fb)
+{
+ struct fuse_inode *fi = get_fuse_inode(inode);
+ int err;
+
+ err = fuse_inode_uncached_io_start(fi, fb);
+ if (err)
+ return err;
+
+ WARN_ON(ff->iomode != IOM_NONE);
+ ff->iomode = IOM_UNCACHED;
+ return 0;
+}
+
+void fuse_inode_uncached_io_end(struct fuse_inode *fi)
+{
+ struct fuse_backing *oldfb = NULL;
+
+ spin_lock(&fi->lock);
+ WARN_ON(fi->iocachectr >= 0);
+ fi->iocachectr++;
+ if (!fi->iocachectr) {
+ wake_up(&fi->direct_io_waitq);
+ oldfb = fuse_inode_backing_set(fi, NULL);
+ }
+ spin_unlock(&fi->lock);
+ if (oldfb)
+ fuse_backing_put(oldfb);
+}
+
+/* Drop uncached_io reference from passthrough open */
+static void fuse_file_uncached_io_release(struct fuse_file *ff,
+ struct fuse_inode *fi)
+{
+ WARN_ON(ff->iomode != IOM_UNCACHED);
+ ff->iomode = IOM_NONE;
+ fuse_inode_uncached_io_end(fi);
+}
+
+/*
+ * Open flags that are allowed in combination with FOPEN_PASSTHROUGH.
+ * A combination of FOPEN_PASSTHROUGH and FOPEN_DIRECT_IO means that read/write
+ * operations go directly to the server, but mmap is done on the backing file.
+ * FOPEN_PASSTHROUGH mode should not co-exist with any users of the fuse inode
+ * page cache, so FOPEN_KEEP_CACHE is a strange and undesired combination.
+ */
+#define FOPEN_PASSTHROUGH_MASK \
+ (FOPEN_PASSTHROUGH | FOPEN_DIRECT_IO | FOPEN_PARALLEL_DIRECT_WRITES | \
+ FOPEN_NOFLUSH)
+
+static int fuse_file_passthrough_open(struct inode *inode, struct file *file)
+{
+ struct fuse_file *ff = file->private_data;
+ struct fuse_conn *fc = get_fuse_conn(inode);
+ struct fuse_backing *fb;
+ int err;
+
+ /* Check allowed conditions for file open in passthrough mode */
+ if (!IS_ENABLED(CONFIG_FUSE_PASSTHROUGH) || !fc->passthrough ||
+ (ff->open_flags & ~FOPEN_PASSTHROUGH_MASK))
+ return -EINVAL;
+
+ fb = fuse_passthrough_open(file, inode,
+ ff->args->open_outarg.backing_id);
+ if (IS_ERR(fb))
+ return PTR_ERR(fb);
+
+ /* First passthrough file open denies caching inode io mode */
+ err = fuse_file_uncached_io_open(inode, ff, fb);
+ if (!err)
+ return 0;
+
+ fuse_passthrough_release(ff, fb);
+ fuse_backing_put(fb);
+
+ return err;
+}
+
+/* Request access to submit new io to inode via open file */
+int fuse_file_io_open(struct file *file, struct inode *inode)
+{
+ struct fuse_file *ff = file->private_data;
+ struct fuse_inode *fi = get_fuse_inode(inode);
+ int err;
+
+ /*
+ * io modes are not relevant with DAX and with server that does not
+ * implement open.
+ */
+ if (FUSE_IS_DAX(inode) || !ff->args)
+ return 0;
+
+ /*
+ * Server is expected to use FOPEN_PASSTHROUGH for all opens of an inode
+ * which is already open for passthrough.
+ */
+ err = -EINVAL;
+ if (fuse_inode_backing(fi) && !(ff->open_flags & FOPEN_PASSTHROUGH))
+ goto fail;
+
+ /*
+ * FOPEN_PARALLEL_DIRECT_WRITES requires FOPEN_DIRECT_IO.
+ */
+ if (!(ff->open_flags & FOPEN_DIRECT_IO))
+ ff->open_flags &= ~FOPEN_PARALLEL_DIRECT_WRITES;
+
+ /*
+ * First passthrough file open denies caching inode io mode.
+ * First caching file open enters caching inode io mode.
+ *
+ * Note that if user opens a file open with O_DIRECT, but server did
+ * not specify FOPEN_DIRECT_IO, a later fcntl() could remove O_DIRECT,
+ * so we put the inode in caching mode to prevent parallel dio.
+ */
+ if ((ff->open_flags & FOPEN_DIRECT_IO) &&
+ !(ff->open_flags & FOPEN_PASSTHROUGH))
+ return 0;
+
+ if (ff->open_flags & FOPEN_PASSTHROUGH)
+ err = fuse_file_passthrough_open(inode, file);
+ else
+ err = fuse_file_cached_io_open(inode, ff);
+ if (err)
+ goto fail;
+
+ return 0;
+
+fail:
+ pr_debug("failed to open file in requested io mode (open_flags=0x%x, err=%i).\n",
+ ff->open_flags, err);
+ /*
+ * The file open mode determines the inode io mode.
+ * Using incorrect open mode is a server mistake, which results in
+ * user visible failure of open() with EIO error.
+ */
+ return -EIO;
+}
+
+/* No more pending io and no new io possible to inode via open/mmapped file */
+void fuse_file_io_release(struct fuse_file *ff, struct inode *inode)
+{
+ struct fuse_inode *fi = get_fuse_inode(inode);
+
+ /*
+ * Last passthrough file close allows caching inode io mode.
+ * Last caching file close exits caching inode io mode.
+ */
+ switch (ff->iomode) {
+ case IOM_NONE:
+ /* Nothing to do */
+ break;
+ case IOM_UNCACHED:
+ fuse_file_uncached_io_release(ff, fi);
+ break;
+ case IOM_CACHED:
+ fuse_file_cached_io_release(ff, fi);
+ break;
+ }
+}
diff --git a/fs/fuse/passthrough.c b/fs/fuse/passthrough.c
new file mode 100644
index 0000000000..9666d13884
--- /dev/null
+++ b/fs/fuse/passthrough.c
@@ -0,0 +1,355 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * FUSE passthrough to backing file.
+ *
+ * Copyright (c) 2023 CTERA Networks.
+ */
+
+#include "fuse_i.h"
+
+#include <linux/file.h>
+#include <linux/backing-file.h>
+#include <linux/splice.h>
+
+static void fuse_file_accessed(struct file *file)
+{
+ struct inode *inode = file_inode(file);
+
+ fuse_invalidate_atime(inode);
+}
+
+static void fuse_file_modified(struct file *file)
+{
+ struct inode *inode = file_inode(file);
+
+ fuse_invalidate_attr_mask(inode, FUSE_STATX_MODSIZE);
+}
+
+ssize_t fuse_passthrough_read_iter(struct kiocb *iocb, struct iov_iter *iter)
+{
+ struct file *file = iocb->ki_filp;
+ struct fuse_file *ff = file->private_data;
+ struct file *backing_file = fuse_file_passthrough(ff);
+ size_t count = iov_iter_count(iter);
+ ssize_t ret;
+ struct backing_file_ctx ctx = {
+ .cred = ff->cred,
+ .user_file = file,
+ .accessed = fuse_file_accessed,
+ };
+
+
+ pr_debug("%s: backing_file=0x%p, pos=%lld, len=%zu\n", __func__,
+ backing_file, iocb->ki_pos, count);
+
+ if (!count)
+ return 0;
+
+ ret = backing_file_read_iter(backing_file, iter, iocb, iocb->ki_flags,
+ &ctx);
+
+ return ret;
+}
+
+ssize_t fuse_passthrough_write_iter(struct kiocb *iocb,
+ struct iov_iter *iter)
+{
+ struct file *file = iocb->ki_filp;
+ struct inode *inode = file_inode(file);
+ struct fuse_file *ff = file->private_data;
+ struct file *backing_file = fuse_file_passthrough(ff);
+ size_t count = iov_iter_count(iter);
+ ssize_t ret;
+ struct backing_file_ctx ctx = {
+ .cred = ff->cred,
+ .user_file = file,
+ .end_write = fuse_file_modified,
+ };
+
+ pr_debug("%s: backing_file=0x%p, pos=%lld, len=%zu\n", __func__,
+ backing_file, iocb->ki_pos, count);
+
+ if (!count)
+ return 0;
+
+ inode_lock(inode);
+ ret = backing_file_write_iter(backing_file, iter, iocb, iocb->ki_flags,
+ &ctx);
+ inode_unlock(inode);
+
+ return ret;
+}
+
+ssize_t fuse_passthrough_splice_read(struct file *in, loff_t *ppos,
+ struct pipe_inode_info *pipe,
+ size_t len, unsigned int flags)
+{
+ struct fuse_file *ff = in->private_data;
+ struct file *backing_file = fuse_file_passthrough(ff);
+ struct backing_file_ctx ctx = {
+ .cred = ff->cred,
+ .user_file = in,
+ .accessed = fuse_file_accessed,
+ };
+
+ pr_debug("%s: backing_file=0x%p, pos=%lld, len=%zu, flags=0x%x\n", __func__,
+ backing_file, ppos ? *ppos : 0, len, flags);
+
+ return backing_file_splice_read(backing_file, ppos, pipe, len, flags,
+ &ctx);
+}
+
+ssize_t fuse_passthrough_splice_write(struct pipe_inode_info *pipe,
+ struct file *out, loff_t *ppos,
+ size_t len, unsigned int flags)
+{
+ struct fuse_file *ff = out->private_data;
+ struct file *backing_file = fuse_file_passthrough(ff);
+ struct inode *inode = file_inode(out);
+ ssize_t ret;
+ struct backing_file_ctx ctx = {
+ .cred = ff->cred,
+ .user_file = out,
+ .end_write = fuse_file_modified,
+ };
+
+ pr_debug("%s: backing_file=0x%p, pos=%lld, len=%zu, flags=0x%x\n", __func__,
+ backing_file, ppos ? *ppos : 0, len, flags);
+
+ inode_lock(inode);
+ ret = backing_file_splice_write(pipe, backing_file, ppos, len, flags,
+ &ctx);
+ inode_unlock(inode);
+
+ return ret;
+}
+
+ssize_t fuse_passthrough_mmap(struct file *file, struct vm_area_struct *vma)
+{
+ struct fuse_file *ff = file->private_data;
+ struct file *backing_file = fuse_file_passthrough(ff);
+ struct backing_file_ctx ctx = {
+ .cred = ff->cred,
+ .user_file = file,
+ .accessed = fuse_file_accessed,
+ };
+
+ pr_debug("%s: backing_file=0x%p, start=%lu, end=%lu\n", __func__,
+ backing_file, vma->vm_start, vma->vm_end);
+
+ return backing_file_mmap(backing_file, vma, &ctx);
+}
+
+struct fuse_backing *fuse_backing_get(struct fuse_backing *fb)
+{
+ if (fb && refcount_inc_not_zero(&fb->count))
+ return fb;
+ return NULL;
+}
+
+static void fuse_backing_free(struct fuse_backing *fb)
+{
+ pr_debug("%s: fb=0x%p\n", __func__, fb);
+
+ if (fb->file)
+ fput(fb->file);
+ put_cred(fb->cred);
+ kfree_rcu(fb, rcu);
+}
+
+void fuse_backing_put(struct fuse_backing *fb)
+{
+ if (fb && refcount_dec_and_test(&fb->count))
+ fuse_backing_free(fb);
+}
+
+void fuse_backing_files_init(struct fuse_conn *fc)
+{
+ idr_init(&fc->backing_files_map);
+}
+
+static int fuse_backing_id_alloc(struct fuse_conn *fc, struct fuse_backing *fb)
+{
+ int id;
+
+ idr_preload(GFP_KERNEL);
+ spin_lock(&fc->lock);
+ /* FIXME: xarray might be space inefficient */
+ id = idr_alloc_cyclic(&fc->backing_files_map, fb, 1, 0, GFP_ATOMIC);
+ spin_unlock(&fc->lock);
+ idr_preload_end();
+
+ WARN_ON_ONCE(id == 0);
+ return id;
+}
+
+static struct fuse_backing *fuse_backing_id_remove(struct fuse_conn *fc,
+ int id)
+{
+ struct fuse_backing *fb;
+
+ spin_lock(&fc->lock);
+ fb = idr_remove(&fc->backing_files_map, id);
+ spin_unlock(&fc->lock);
+
+ return fb;
+}
+
+static int fuse_backing_id_free(int id, void *p, void *data)
+{
+ struct fuse_backing *fb = p;
+
+ WARN_ON_ONCE(refcount_read(&fb->count) != 1);
+ fuse_backing_free(fb);
+ return 0;
+}
+
+void fuse_backing_files_free(struct fuse_conn *fc)
+{
+ idr_for_each(&fc->backing_files_map, fuse_backing_id_free, NULL);
+ idr_destroy(&fc->backing_files_map);
+}
+
+int fuse_backing_open(struct fuse_conn *fc, struct fuse_backing_map *map)
+{
+ struct file *file;
+ struct super_block *backing_sb;
+ struct fuse_backing *fb = NULL;
+ int res;
+
+ pr_debug("%s: fd=%d flags=0x%x\n", __func__, map->fd, map->flags);
+
+ /* TODO: relax CAP_SYS_ADMIN once backing files are visible to lsof */
+ res = -EPERM;
+ if (!fc->passthrough || !capable(CAP_SYS_ADMIN))
+ goto out;
+
+ res = -EINVAL;
+ if (map->flags || map->padding)
+ goto out;
+
+ file = fget(map->fd);
+ res = -EBADF;
+ if (!file)
+ goto out;
+
+ res = -EOPNOTSUPP;
+ if (!file->f_op->read_iter || !file->f_op->write_iter)
+ goto out_fput;
+
+ backing_sb = file_inode(file)->i_sb;
+ res = -ELOOP;
+ if (backing_sb->s_stack_depth >= fc->max_stack_depth)
+ goto out_fput;
+
+ fb = kmalloc(sizeof(struct fuse_backing), GFP_KERNEL);
+ res = -ENOMEM;
+ if (!fb)
+ goto out_fput;
+
+ fb->file = file;
+ fb->cred = prepare_creds();
+ refcount_set(&fb->count, 1);
+
+ res = fuse_backing_id_alloc(fc, fb);
+ if (res < 0) {
+ fuse_backing_free(fb);
+ fb = NULL;
+ }
+
+out:
+ pr_debug("%s: fb=0x%p, ret=%i\n", __func__, fb, res);
+
+ return res;
+
+out_fput:
+ fput(file);
+ goto out;
+}
+
+int fuse_backing_close(struct fuse_conn *fc, int backing_id)
+{
+ struct fuse_backing *fb = NULL;
+ int err;
+
+ pr_debug("%s: backing_id=%d\n", __func__, backing_id);
+
+ /* TODO: relax CAP_SYS_ADMIN once backing files are visible to lsof */
+ err = -EPERM;
+ if (!fc->passthrough || !capable(CAP_SYS_ADMIN))
+ goto out;
+
+ err = -EINVAL;
+ if (backing_id <= 0)
+ goto out;
+
+ err = -ENOENT;
+ fb = fuse_backing_id_remove(fc, backing_id);
+ if (!fb)
+ goto out;
+
+ fuse_backing_put(fb);
+ err = 0;
+out:
+ pr_debug("%s: fb=0x%p, err=%i\n", __func__, fb, err);
+
+ return err;
+}
+
+/*
+ * Setup passthrough to a backing file.
+ *
+ * Returns an fb object with elevated refcount to be stored in fuse inode.
+ */
+struct fuse_backing *fuse_passthrough_open(struct file *file,
+ struct inode *inode,
+ int backing_id)
+{
+ struct fuse_file *ff = file->private_data;
+ struct fuse_conn *fc = ff->fm->fc;
+ struct fuse_backing *fb = NULL;
+ struct file *backing_file;
+ int err;
+
+ err = -EINVAL;
+ if (backing_id <= 0)
+ goto out;
+
+ rcu_read_lock();
+ fb = idr_find(&fc->backing_files_map, backing_id);
+ fb = fuse_backing_get(fb);
+ rcu_read_unlock();
+
+ err = -ENOENT;
+ if (!fb)
+ goto out;
+
+ /* Allocate backing file per fuse file to store fuse path */
+ backing_file = backing_file_open(&file->f_path, file->f_flags,
+ &fb->file->f_path, fb->cred);
+ err = PTR_ERR(backing_file);
+ if (IS_ERR(backing_file)) {
+ fuse_backing_put(fb);
+ goto out;
+ }
+
+ err = 0;
+ ff->passthrough = backing_file;
+ ff->cred = get_cred(fb->cred);
+out:
+ pr_debug("%s: backing_id=%d, fb=0x%p, backing_file=0x%p, err=%i\n", __func__,
+ backing_id, fb, ff->passthrough, err);
+
+ return err ? ERR_PTR(err) : fb;
+}
+
+void fuse_passthrough_release(struct fuse_file *ff, struct fuse_backing *fb)
+{
+ pr_debug("%s: fb=0x%p, backing_file=0x%p\n", __func__,
+ fb, ff->passthrough);
+
+ fput(ff->passthrough);
+ ff->passthrough = NULL;
+ put_cred(ff->cred);
+ ff->cred = NULL;
+}
diff --git a/fs/fuse/readdir.c b/fs/fuse/readdir.c
index c66a54d6c7..0377b6dc24 100644
--- a/fs/fuse/readdir.c
+++ b/fs/fuse/readdir.c
@@ -592,15 +592,11 @@ int fuse_readdir(struct file *file, struct dir_context *ctx)
if (fuse_is_bad(inode))
return -EIO;
- mutex_lock(&ff->readdir.lock);
-
err = UNCACHED;
if (ff->open_flags & FOPEN_CACHE_DIR)
err = fuse_readdir_cached(file, ctx);
if (err == UNCACHED)
err = fuse_readdir_uncached(file, ctx);
- mutex_unlock(&ff->readdir.lock);
-
return err;
}
diff --git a/fs/fuse/virtio_fs.c b/fs/fuse/virtio_fs.c
index 5f1be1da92..1a52a51b6b 100644
--- a/fs/fuse/virtio_fs.c
+++ b/fs/fuse/virtio_fs.c
@@ -7,6 +7,8 @@
#include <linux/fs.h>
#include <linux/dax.h>
#include <linux/pci.h>
+#include <linux/interrupt.h>
+#include <linux/group_cpus.h>
#include <linux/pfn_t.h>
#include <linux/memremap.h>
#include <linux/module.h>
@@ -16,6 +18,7 @@
#include <linux/fs_context.h>
#include <linux/fs_parser.h>
#include <linux/highmem.h>
+#include <linux/cleanup.h>
#include <linux/uio.h>
#include "fuse_i.h"
@@ -31,6 +34,9 @@
static DEFINE_MUTEX(virtio_fs_mutex);
static LIST_HEAD(virtio_fs_instances);
+/* The /sys/fs/virtio_fs/ kset */
+static struct kset *virtio_fs_kset;
+
enum {
VQ_HIPRIO,
VQ_REQUEST
@@ -55,7 +61,7 @@ struct virtio_fs_vq {
/* A virtio-fs device instance */
struct virtio_fs {
- struct kref refcount;
+ struct kobject kobj;
struct list_head list; /* on virtio_fs_instances */
char *tag;
struct virtio_fs_vq *vqs;
@@ -63,6 +69,8 @@ struct virtio_fs {
unsigned int num_request_queues; /* number of request queues */
struct dax_device *dax_dev;
+ unsigned int *mq_map; /* index = cpu id, value = request vq id */
+
/* DAX memory window where file contents are mapped */
void *window_kaddr;
phys_addr_t window_phys_addr;
@@ -161,18 +169,41 @@ static inline void dec_in_flight_req(struct virtio_fs_vq *fsvq)
complete(&fsvq->in_flight_zero);
}
-static void release_virtio_fs_obj(struct kref *ref)
+static ssize_t tag_show(struct kobject *kobj,
+ struct kobj_attribute *attr, char *buf)
+{
+ struct virtio_fs *fs = container_of(kobj, struct virtio_fs, kobj);
+
+ return sysfs_emit(buf, "%s\n", fs->tag);
+}
+
+static struct kobj_attribute virtio_fs_tag_attr = __ATTR_RO(tag);
+
+static struct attribute *virtio_fs_attrs[] = {
+ &virtio_fs_tag_attr.attr,
+ NULL
+};
+ATTRIBUTE_GROUPS(virtio_fs);
+
+static void virtio_fs_ktype_release(struct kobject *kobj)
{
- struct virtio_fs *vfs = container_of(ref, struct virtio_fs, refcount);
+ struct virtio_fs *vfs = container_of(kobj, struct virtio_fs, kobj);
+ kfree(vfs->mq_map);
kfree(vfs->vqs);
kfree(vfs);
}
+static const struct kobj_type virtio_fs_ktype = {
+ .release = virtio_fs_ktype_release,
+ .sysfs_ops = &kobj_sysfs_ops,
+ .default_groups = virtio_fs_groups,
+};
+
/* Make sure virtiofs_mutex is held */
static void virtio_fs_put(struct virtio_fs *fs)
{
- kref_put(&fs->refcount, release_virtio_fs_obj);
+ kobject_put(&fs->kobj);
}
static void virtio_fs_fiq_release(struct fuse_iqueue *fiq)
@@ -243,25 +274,46 @@ static void virtio_fs_start_all_queues(struct virtio_fs *fs)
}
/* Add a new instance to the list or return -EEXIST if tag name exists*/
-static int virtio_fs_add_instance(struct virtio_fs *fs)
+static int virtio_fs_add_instance(struct virtio_device *vdev,
+ struct virtio_fs *fs)
{
struct virtio_fs *fs2;
- bool duplicate = false;
+ int ret;
mutex_lock(&virtio_fs_mutex);
list_for_each_entry(fs2, &virtio_fs_instances, list) {
- if (strcmp(fs->tag, fs2->tag) == 0)
- duplicate = true;
+ if (strcmp(fs->tag, fs2->tag) == 0) {
+ mutex_unlock(&virtio_fs_mutex);
+ return -EEXIST;
+ }
}
- if (!duplicate)
- list_add_tail(&fs->list, &virtio_fs_instances);
+ /* Use the virtio_device's index as a unique identifier, there is no
+ * need to allocate our own identifiers because the virtio_fs instance
+ * is only visible to userspace as long as the underlying virtio_device
+ * exists.
+ */
+ fs->kobj.kset = virtio_fs_kset;
+ ret = kobject_add(&fs->kobj, NULL, "%d", vdev->index);
+ if (ret < 0) {
+ mutex_unlock(&virtio_fs_mutex);
+ return ret;
+ }
+
+ ret = sysfs_create_link(&fs->kobj, &vdev->dev.kobj, "device");
+ if (ret < 0) {
+ kobject_del(&fs->kobj);
+ mutex_unlock(&virtio_fs_mutex);
+ return ret;
+ }
+
+ list_add_tail(&fs->list, &virtio_fs_instances);
mutex_unlock(&virtio_fs_mutex);
- if (duplicate)
- return -EEXIST;
+ kobject_uevent(&fs->kobj, KOBJ_ADD);
+
return 0;
}
@@ -274,7 +326,7 @@ static struct virtio_fs *virtio_fs_find_instance(const char *tag)
list_for_each_entry(fs, &virtio_fs_instances, list) {
if (strcmp(fs->tag, tag) == 0) {
- kref_get(&fs->refcount);
+ kobject_get(&fs->kobj);
goto found;
}
}
@@ -323,6 +375,16 @@ static int virtio_fs_read_tag(struct virtio_device *vdev, struct virtio_fs *fs)
return -ENOMEM;
memcpy(fs->tag, tag_buf, len);
fs->tag[len] = '\0';
+
+ /* While the VIRTIO specification allows any character, newlines are
+ * awkward on mount(8) command-lines and cause problems in the sysfs
+ * "tag" attr and uevent TAG= properties. Forbid them.
+ */
+ if (strchr(fs->tag, '\n')) {
+ dev_dbg(&vdev->dev, "refusing virtiofs tag with newline character\n");
+ return -EINVAL;
+ }
+
return 0;
}
@@ -345,7 +407,7 @@ static void virtio_fs_hiprio_done_work(struct work_struct *work)
kfree(req);
dec_in_flight_req(fsvq);
}
- } while (!virtqueue_enable_cb(vq) && likely(!virtqueue_is_broken(vq)));
+ } while (!virtqueue_enable_cb(vq));
spin_unlock(&fsvq->lock);
}
@@ -627,7 +689,7 @@ static void virtio_fs_requests_done_work(struct work_struct *work)
list_move_tail(&req->list, &reqs);
spin_unlock(&fpq->lock);
}
- } while (!virtqueue_enable_cb(vq) && likely(!virtqueue_is_broken(vq)));
+ } while (!virtqueue_enable_cb(vq));
spin_unlock(&fsvq->lock);
/* End requests */
@@ -649,6 +711,44 @@ static void virtio_fs_requests_done_work(struct work_struct *work)
}
}
+static void virtio_fs_map_queues(struct virtio_device *vdev, struct virtio_fs *fs)
+{
+ const struct cpumask *mask, *masks;
+ unsigned int q, cpu;
+
+ /* First attempt to map using existing transport layer affinities
+ * e.g. PCIe MSI-X
+ */
+ if (!vdev->config->get_vq_affinity)
+ goto fallback;
+
+ for (q = 0; q < fs->num_request_queues; q++) {
+ mask = vdev->config->get_vq_affinity(vdev, VQ_REQUEST + q);
+ if (!mask)
+ goto fallback;
+
+ for_each_cpu(cpu, mask)
+ fs->mq_map[cpu] = q;
+ }
+
+ return;
+fallback:
+ /* Attempt to map evenly in groups over the CPUs */
+ masks = group_cpus_evenly(fs->num_request_queues);
+ /* If even this fails we default to all CPUs use queue zero */
+ if (!masks) {
+ for_each_possible_cpu(cpu)
+ fs->mq_map[cpu] = 0;
+ return;
+ }
+
+ for (q = 0; q < fs->num_request_queues; q++) {
+ for_each_cpu(cpu, &masks[q])
+ fs->mq_map[cpu] = q;
+ }
+ kfree(masks);
+}
+
/* Virtqueue interrupt handler */
static void virtio_fs_vq_done(struct virtqueue *vq)
{
@@ -685,6 +785,11 @@ static int virtio_fs_setup_vqs(struct virtio_device *vdev,
{
struct virtqueue **vqs;
vq_callback_t **callbacks;
+ /* Specify pre_vectors to ensure that the queues before the
+ * request queues (e.g. hiprio) don't claim any of the CPUs in
+ * the multi-queue mapping and interrupt affinities
+ */
+ struct irq_affinity desc = { .pre_vectors = VQ_REQUEST };
const char **names;
unsigned int i;
int ret = 0;
@@ -694,6 +799,9 @@ static int virtio_fs_setup_vqs(struct virtio_device *vdev,
if (fs->num_request_queues == 0)
return -EINVAL;
+ /* Truncate nr of request queues to nr_cpu_id */
+ fs->num_request_queues = min_t(unsigned int, fs->num_request_queues,
+ nr_cpu_ids);
fs->nvqs = VQ_REQUEST + fs->num_request_queues;
fs->vqs = kcalloc(fs->nvqs, sizeof(fs->vqs[VQ_HIPRIO]), GFP_KERNEL);
if (!fs->vqs)
@@ -703,7 +811,9 @@ static int virtio_fs_setup_vqs(struct virtio_device *vdev,
callbacks = kmalloc_array(fs->nvqs, sizeof(callbacks[VQ_HIPRIO]),
GFP_KERNEL);
names = kmalloc_array(fs->nvqs, sizeof(names[VQ_HIPRIO]), GFP_KERNEL);
- if (!vqs || !callbacks || !names) {
+ fs->mq_map = kcalloc_node(nr_cpu_ids, sizeof(*fs->mq_map), GFP_KERNEL,
+ dev_to_node(&vdev->dev));
+ if (!vqs || !callbacks || !names || !fs->mq_map) {
ret = -ENOMEM;
goto out;
}
@@ -723,7 +833,7 @@ static int virtio_fs_setup_vqs(struct virtio_device *vdev,
names[i] = fs->vqs[i].name;
}
- ret = virtio_find_vqs(vdev, fs->nvqs, vqs, callbacks, names, NULL);
+ ret = virtio_find_vqs(vdev, fs->nvqs, vqs, callbacks, names, &desc);
if (ret < 0)
goto out;
@@ -735,8 +845,10 @@ out:
kfree(names);
kfree(callbacks);
kfree(vqs);
- if (ret)
+ if (ret) {
kfree(fs->vqs);
+ kfree(fs->mq_map);
+ }
return ret;
}
@@ -795,8 +907,11 @@ static void virtio_fs_cleanup_dax(void *data)
put_dax(dax_dev);
}
+DEFINE_FREE(cleanup_dax, struct dax_dev *, if (!IS_ERR_OR_NULL(_T)) virtio_fs_cleanup_dax(_T))
+
static int virtio_fs_setup_dax(struct virtio_device *vdev, struct virtio_fs *fs)
{
+ struct dax_device *dax_dev __free(cleanup_dax) = NULL;
struct virtio_shm_region cache_reg;
struct dev_pagemap *pgmap;
bool have_cache;
@@ -804,6 +919,12 @@ static int virtio_fs_setup_dax(struct virtio_device *vdev, struct virtio_fs *fs)
if (!IS_ENABLED(CONFIG_FUSE_DAX))
return 0;
+ dax_dev = alloc_dax(fs, &virtio_fs_dax_ops);
+ if (IS_ERR(dax_dev)) {
+ int rc = PTR_ERR(dax_dev);
+ return rc == -EOPNOTSUPP ? 0 : rc;
+ }
+
/* Get cache region */
have_cache = virtio_get_shm_region(vdev, &cache_reg,
(u8)VIRTIO_FS_SHMCAP_ID_CACHE);
@@ -849,10 +970,7 @@ 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, &virtio_fs_dax_ops);
- if (IS_ERR(fs->dax_dev))
- return PTR_ERR(fs->dax_dev);
-
+ fs->dax_dev = no_free_ptr(dax_dev);
return devm_add_action_or_reset(&vdev->dev, virtio_fs_cleanup_dax,
fs->dax_dev);
}
@@ -865,7 +983,7 @@ static int virtio_fs_probe(struct virtio_device *vdev)
fs = kzalloc(sizeof(*fs), GFP_KERNEL);
if (!fs)
return -ENOMEM;
- kref_init(&fs->refcount);
+ kobject_init(&fs->kobj, &virtio_fs_ktype);
vdev->priv = fs;
ret = virtio_fs_read_tag(vdev, fs);
@@ -876,7 +994,7 @@ static int virtio_fs_probe(struct virtio_device *vdev)
if (ret < 0)
goto out;
- /* TODO vq affinity */
+ virtio_fs_map_queues(vdev, fs);
ret = virtio_fs_setup_dax(vdev, fs);
if (ret < 0)
@@ -887,7 +1005,7 @@ static int virtio_fs_probe(struct virtio_device *vdev)
*/
virtio_device_ready(vdev);
- ret = virtio_fs_add_instance(fs);
+ ret = virtio_fs_add_instance(vdev, fs);
if (ret < 0)
goto out_vqs;
@@ -896,11 +1014,10 @@ static int virtio_fs_probe(struct virtio_device *vdev)
out_vqs:
virtio_reset_device(vdev);
virtio_fs_cleanup_vqs(vdev);
- kfree(fs->vqs);
out:
vdev->priv = NULL;
- kfree(fs);
+ kobject_put(&fs->kobj);
return ret;
}
@@ -924,6 +1041,8 @@ static void virtio_fs_remove(struct virtio_device *vdev)
mutex_lock(&virtio_fs_mutex);
/* This device is going away. No one should get new reference */
list_del_init(&fs->list);
+ sysfs_remove_link(&fs->kobj, "device");
+ kobject_del(&fs->kobj);
virtio_fs_stop_all_queues(fs);
virtio_fs_drain_all_queues_locked(fs);
virtio_reset_device(vdev);
@@ -959,7 +1078,6 @@ static const unsigned int feature_table[] = {};
static struct virtio_driver virtio_fs_driver = {
.driver.name = KBUILD_MODNAME,
- .driver.owner = THIS_MODULE,
.id_table = id_table,
.feature_table = feature_table,
.feature_table_size = ARRAY_SIZE(feature_table),
@@ -1224,7 +1342,7 @@ out:
static void virtio_fs_wake_pending_and_unlock(struct fuse_iqueue *fiq)
__releases(fiq->lock)
{
- unsigned int queue_id = VQ_REQUEST; /* TODO multiqueue */
+ unsigned int queue_id;
struct virtio_fs *fs;
struct fuse_req *req;
struct virtio_fs_vq *fsvq;
@@ -1238,11 +1356,13 @@ __releases(fiq->lock)
spin_unlock(&fiq->lock);
fs = fiq->priv;
+ queue_id = VQ_REQUEST + fs->mq_map[raw_smp_processor_id()];
- pr_debug("%s: opcode %u unique %#llx nodeid %#llx in.len %u out.len %u\n",
- __func__, req->in.h.opcode, req->in.h.unique,
+ pr_debug("%s: opcode %u unique %#llx nodeid %#llx in.len %u out.len %u queue_id %u\n",
+ __func__, req->in.h.opcode, req->in.h.unique,
req->in.h.nodeid, req->in.h.len,
- fuse_len_args(req->args->out_numargs, req->args->out_args));
+ fuse_len_args(req->args->out_numargs, req->args->out_args),
+ queue_id);
fsvq = &fs->vqs[queue_id];
ret = virtio_fs_enqueue_req(fsvq, req, false);
@@ -1510,21 +1630,56 @@ static struct file_system_type virtio_fs_type = {
.kill_sb = virtio_kill_sb,
};
+static int virtio_fs_uevent(const struct kobject *kobj, struct kobj_uevent_env *env)
+{
+ const struct virtio_fs *fs = container_of(kobj, struct virtio_fs, kobj);
+
+ add_uevent_var(env, "TAG=%s", fs->tag);
+ return 0;
+}
+
+static const struct kset_uevent_ops virtio_fs_uevent_ops = {
+ .uevent = virtio_fs_uevent,
+};
+
+static int __init virtio_fs_sysfs_init(void)
+{
+ virtio_fs_kset = kset_create_and_add("virtiofs", &virtio_fs_uevent_ops,
+ fs_kobj);
+ if (!virtio_fs_kset)
+ return -ENOMEM;
+ return 0;
+}
+
+static void virtio_fs_sysfs_exit(void)
+{
+ kset_unregister(virtio_fs_kset);
+ virtio_fs_kset = NULL;
+}
+
static int __init virtio_fs_init(void)
{
int ret;
- ret = register_virtio_driver(&virtio_fs_driver);
+ ret = virtio_fs_sysfs_init();
if (ret < 0)
return ret;
+ ret = register_virtio_driver(&virtio_fs_driver);
+ if (ret < 0)
+ goto sysfs_exit;
+
ret = register_filesystem(&virtio_fs_type);
- if (ret < 0) {
- unregister_virtio_driver(&virtio_fs_driver);
- return ret;
- }
+ if (ret < 0)
+ goto unregister_virtio_driver;
return 0;
+
+unregister_virtio_driver:
+ unregister_virtio_driver(&virtio_fs_driver);
+sysfs_exit:
+ virtio_fs_sysfs_exit();
+ return ret;
}
module_init(virtio_fs_init);
@@ -1532,6 +1687,7 @@ static void __exit virtio_fs_exit(void)
{
unregister_filesystem(&virtio_fs_type);
unregister_virtio_driver(&virtio_fs_driver);
+ virtio_fs_sysfs_exit();
}
module_exit(virtio_fs_exit);
generated by cgit v1.2.3 (git 2.39.1) at 2024-09-29 13:23:22 +0000