path: root/fs/fuse/virtio_fs.c

// SPDX-License-Identifier: GPL-2.0
/*
 * virtio-fs: Virtio Filesystem
 * Copyright (C) 2018 Red Hat, Inc.
 */

#include <linux/fs.h>
#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>
#include <linux/delay.h>
#include <linux/fs_context.h>
#include <linux/fs_parser.h>
#include <linux/highmem.h>
#include <linux/uio.h>
#include "fuse_i.h"

/* Used to help calculate the FUSE connection's max_pages limit for a request's
 * size. Parts of the struct fuse_req are sliced into scattergather lists in
 * addition to the pages used, so this can help account for that overhead.
 */
#define FUSE_HEADER_OVERHEAD    4

/* List of virtio-fs device instances and a lock for the list. Also provides
 * mutual exclusion in device removal and mounting path
 */
static DEFINE_MUTEX(virtio_fs_mutex);
static LIST_HEAD(virtio_fs_instances);

enum {
	VQ_HIPRIO,
	VQ_REQUEST
};

#define VQ_NAME_LEN	24

/* Per-virtqueue state */
struct virtio_fs_vq {
	spinlock_t lock;
	struct virtqueue *vq;     /* protected by ->lock */
	struct work_struct done_work;
	struct list_head queued_reqs;
	struct list_head end_reqs;	/* End these requests */
	struct delayed_work dispatch_work;
	struct fuse_dev *fud;
	bool connected;
	long in_flight;
	struct completion in_flight_zero; /* No inflight requests */
	char name[VQ_NAME_LEN];
} ____cacheline_aligned_in_smp;

/* A virtio-fs device instance */
struct virtio_fs {
	struct kref refcount;
	struct list_head list;    /* on virtio_fs_instances */
	char *tag;
	struct virtio_fs_vq *vqs;
	unsigned int nvqs;               /* number of virtqueues */
	unsigned int num_request_queues; /* number of request queues */
	struct dax_device *dax_dev;

	/* DAX memory window where file contents are mapped */
	void *window_kaddr;
	phys_addr_t window_phys_addr;
	size_t window_len;
};

struct virtio_fs_forget_req {
	struct fuse_in_header ih;
	struct fuse_forget_in arg;
};

struct virtio_fs_forget {
	/* This request can be temporarily queued on virt queue */
	struct list_head list;
	struct virtio_fs_forget_req req;
};

struct virtio_fs_req_work {
	struct fuse_req *req;
	struct virtio_fs_vq *fsvq;
	struct work_struct done_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),
	{}
};

static int virtio_fs_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;

	opt = fs_parse(fsc, virtio_fs_parameters, param, &result);
	if (opt < 0)
		return opt;

	switch (opt) {
	case OPT_DAX:
		ctx->dax_mode = FUSE_DAX_ALWAYS;
		break;
	case OPT_DAX_ENUM:
		ctx->dax_mode = result.uint_32;
		break;
	default:
		return -EINVAL;
	}

	return 0;
}

static void virtio_fs_free_fsc(struct fs_context *fsc)
{
	struct fuse_fs_context *ctx = fsc->fs_private;

	kfree(ctx);
}

static inline struct virtio_fs_vq *vq_to_fsvq(struct virtqueue *vq)
{
	struct virtio_fs *fs = vq->vdev->priv;

	return &fs->vqs[vq->index];
}

/* Should be called with fsvq->lock held. */
static inline void inc_in_flight_req(struct virtio_fs_vq *fsvq)
{
	fsvq->in_flight++;
}

/* Should be called with fsvq->lock held. */
static inline void dec_in_flight_req(struct virtio_fs_vq *fsvq)
{
	WARN_ON(fsvq->in_flight <= 0);
	fsvq->in_flight--;
	if (!fsvq->in_flight)
		complete(&fsvq->in_flight_zero);
}

static void release_virtio_fs_obj(struct kref *ref)
{
	struct virtio_fs *vfs = container_of(ref, struct virtio_fs, refcount);

	kfree(vfs->vqs);
	kfree(vfs);
}

/* Make sure virtiofs_mutex is held */
static void virtio_fs_put(struct virtio_fs *fs)
{
	kref_put(&fs->refcount, release_virtio_fs_obj);
}

static void virtio_fs_fiq_release(struct fuse_iqueue *fiq)
{
	struct virtio_fs *vfs = fiq->priv;

	mutex_lock(&virtio_fs_mutex);
	virtio_fs_put(vfs);
	mutex_unlock(&virtio_fs_mutex);
}

static void virtio_fs_drain_queue(struct virtio_fs_vq *fsvq)
{
	WARN_ON(fsvq->in_flight < 0);

	/* Wait for in flight requests to finish.*/
	spin_lock(&fsvq->lock);
	if (fsvq->in_flight) {
		/* We are holding virtio_fs_mutex. There should not be any
		 * waiters waiting for completion.
		 */
		reinit_completion(&fsvq->in_flight_zero);
		spin_unlock(&fsvq->lock);
		wait_for_completion(&fsvq->in_flight_zero);
	} else {
		spin_unlock(&fsvq->lock);
	}

	flush_work(&fsvq->done_work);
	flush_delayed_work(&fsvq->dispatch_work);
}

static void virtio_fs_drain_all_queues_locked(struct virtio_fs *fs)
{
	struct virtio_fs_vq *fsvq;
	int i;

	for (i = 0; i < fs->nvqs; i++) {
		fsvq = &fs->vqs[i];
		virtio_fs_drain_queue(fsvq);
	}
}

static void virtio_fs_drain_all_queues(struct virtio_fs *fs)
{
	/* Provides mutual exclusion between ->remove and ->kill_sb
	 * paths. We don't want both of these draining queue at the
	 * same time. Current completion logic reinits completion
	 * and that means there should not be any other thread
	 * doing reinit or waiting for completion already.
	 */
	mutex_lock(&virtio_fs_mutex);
	virtio_fs_drain_all_queues_locked(fs);
	mutex_unlock(&virtio_fs_mutex);
}

static void virtio_fs_start_all_queues(struct virtio_fs *fs)
{
	struct virtio_fs_vq *fsvq;
	int i;

	for (i = 0; i < fs->nvqs; i++) {
		fsvq = &fs->vqs[i];
		spin_lock(&fsvq->lock);
		fsvq->connected = true;
		spin_unlock(&fsvq->lock);
	}
}

/* Add a new instance to the list or return -EEXIST if tag name exists*/
static int virtio_fs_add_instance(struct virtio_fs *fs)
{
	struct virtio_fs *fs2;
	bool duplicate = false;

	mutex_lock(&virtio_fs_mutex);

	list_for_each_entry(fs2, &virtio_fs_instances, list) {
		if (strcmp(fs->tag, fs2->tag) == 0)
			duplicate = true;
	}

	if (!duplicate)
		list_add_tail(&fs->list, &virtio_fs_instances);

	mutex_unlock(&virtio_fs_mutex);

	if (duplicate)
		return -EEXIST;
	return 0;
}

/* Return the virtio_fs with a given tag, or NULL */
static struct virtio_fs *virtio_fs_find_instance(const char *tag)
{
	struct virtio_fs *fs;

	mutex_lock(&virtio_fs_mutex);

	list_for_each_entry(fs, &virtio_fs_instances, list) {
		if (strcmp(fs->tag, tag) == 0) {
			kref_get(&fs->refcount);
			goto found;
		}
	}

	fs = NULL; /* not found */

found:
	mutex_unlock(&virtio_fs_mutex);

	return fs;
}

static void virtio_fs_free_devs(struct virtio_fs *fs)
{
	unsigned int i;

	for (i = 0; i < fs->nvqs; i++) {
		struct virtio_fs_vq *fsvq = &fs->vqs[i];

		if (!fsvq->fud)
			continue;

		fuse_dev_free(fsvq->fud);
		fsvq->fud = NULL;
	}
}

/* Read filesystem name from virtio config into fs->tag (must kfree()). */
static int virtio_fs_read_tag(struct virtio_device *vdev, struct virtio_fs *fs)
{
	char tag_buf[sizeof_field(struct virtio_fs_config, tag)];
	char *end;
	size_t len;

	virtio_cread_bytes(vdev, offsetof(struct virtio_fs_config, tag),
			   &tag_buf, sizeof(tag_buf));
	end = memchr(tag_buf, '\0', sizeof(tag_buf));
	if (end == tag_buf)
		return -EINVAL; /* empty tag */
	if (!end)
		end = &tag_buf[sizeof(tag_buf)];

	len