path: root/drivers/virtio/virtio_ring.c

/* Virtio ring implementation.
 *
 *  Copyright 2007 Rusty Russell IBM Corporation
 *
 *  This program is free software; you can redistribute it and/or modify
 *  it under the terms of the GNU General Public License as published by
 *  the Free Software Foundation; either version 2 of the License, or
 *  (at your option) any later version.
 *
 *  This program is distributed in the hope that it will be useful,
 *  but WITHOUT ANY WARRANTY; without even the implied warranty of
 *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 *  GNU General Public License for more details.
 *
 *  You should have received a copy of the GNU General Public License
 *  along with this program; if not, write to the Free Software
 *  Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
 */
#include <linux/virtio.h>
#include <linux/virtio_ring.h>
#include <linux/virtio_config.h>
#include <linux/device.h>
#include <linux/slab.h>
#include <linux/module.h>
#include <linux/hrtimer.h>
#include <linux/kmemleak.h>
#include <linux/dma-mapping.h>
#include <xen/xen.h>

#ifdef DEBUG
/* For development, we want to crash whenever the ring is screwed. */
#define BAD_RING(_vq, fmt, args...)				\
	do {							\
		dev_err(&(_vq)->vq.vdev->dev,			\
			"%s:"fmt, (_vq)->vq.name, ##args);	\
		BUG();						\
	} while (0)
/* Caller is supposed to guarantee no reentry. */
#define START_USE(_vq)						\
	do {							\
		if ((_vq)->in_use)				\
			panic("%s:in_use = %i\n",		\
			      (_vq)->vq.name, (_vq)->in_use);	\
		(_vq)->in_use = __LINE__;			\
	} while (0)
#define END_USE(_vq) \
	do { BUG_ON(!(_vq)->in_use); (_vq)->in_use = 0; } while(0)
#else
#define BAD_RING(_vq, fmt, args...)				\
	do {							\
		dev_err(&_vq->vq.vdev->dev,			\
			"%s:"fmt, (_vq)->vq.name, ##args);	\
		(_vq)->broken = true;				\
	} while (0)
#define START_USE(vq)
#define END_USE(vq)
#endif

struct vring_desc_state {
	void *data;			/* Data for callback. */
	struct vring_desc *indir_desc;	/* Indirect descriptor, if any. */
};

struct vring_virtqueue {
	struct virtqueue vq;

	/* Actual memory layout for this queue */
	struct vring vring;

	/* Can we use weak barriers? */
	bool weak_barriers;

	/* Other side has made a mess, don't try any more. */
	bool broken;

	/* Host supports indirect buffers */
	bool indirect;

	/* Host publishes avail event idx */
	bool event;

	/* Head of free buffer list. */
	unsigned int free_head;
	/* Number we've added since last sync. */
	unsigned int num_added;

	/* Last used index we've seen. */
	u16 last_used_idx;

	/* Last written value to avail->flags */
	u16 avail_flags_shadow;

	/* Last written value to avail->idx in guest byte order */
	u16 avail_idx_shadow;

	/* How to notify other side. FIXME: commonalize hcalls! */
	bool (*notify)(struct virtqueue *vq);

	/* DMA, allocation, and size information */
	bool we_own_ring;
	size_t queue_size_in_bytes;
	dma_addr_t queue_dma_addr;

#ifdef DEBUG
	/* They're supposed to lock for us. */
	unsigned int in_use;

	/* Figure out if their kicks are too delayed. */
	bool last_add_time_valid;
	ktime_t last_add_time;
#endif

	/* Per-descriptor state. */
	struct vring_desc_state desc_state[];
};

#define to_vvq(_vq) container_of(_vq, struct vring_virtqueue, vq)

/*
 * Modern virtio devices have feature bits to specify whether they need a
 * quirk and bypass the IOMMU. If not there, just use the DMA API.
 *
 * If there, the interaction between virtio and DMA API is messy.
 *
 * On most systems with virtio, physical addresses match bus addresses,
 * and it doesn't particularly matter whether we use the DMA API.
 *
 * On some systems, including Xen and any system with a physical device
 * that speaks virtio behind a physical IOMMU, we must use the DMA API
 * for virtio DMA to work at all.
 *
 * On other systems, including SPARC and PPC64, virtio-pci devices are
 * enumerated as though they are behind an IOMMU, but the virtio host
 * ignores the IOMMU, so we must either pretend that the IOMMU isn't
 * there or somehow map everything as the identity.
 *
 * For the time being, we preserve historic behavior and bypass the DMA
 * API.
 *
 * TODO: install a per-device DMA ops structure that does the right thing
 * taking into account all the above quirks, and use the DMA API
 * unconditionally on data path.
 */

static bool vring_use_dma_api(struct virtio_device *vdev)
{
	if (!virtio_has_iommu_quirk(vdev))
		return true;

	/* Otherwise, we are left to guess. */
	/*
	 * In theory, it's possible to have a buggy QEMU-supposed
	 * emulated Q35 IOMMU and Xen enabled at the same time.  On
	 * such a configuration, virtio has never worked and will
	 * not work without an even larger kludge.  Instead, enable
	 * the DMA API if we're a Xen guest, which at least allows
	 * all of the sensible Xen configurations to work correctly.
	 */
	if (xen_domain())
		return true;

	return false;
}

/*
 * The DMA ops on various arches are rather gnarly right now, and
 * making all of the arch DMA ops work on the vring device itself
 * is a mess.  For now, we use the parent device for DMA ops.
 */
static inline struct device *vring_dma_dev(const struct vring_virtqueue *vq)
{
	return vq->vq.vdev->dev.parent;
}

/* Map one sg entry. */
static dma_addr_t vring_map_one_sg(const struct vring_virtqueue *vq,
				   struct scatterlist *sg,
				   enum dma_data_direction direction)
{
	if (!vring_use_dma_api(vq->vq.vdev))
		return (dma_addr_t)sg_phys(sg);

	/*
	 * We can't use dma_map_sg, because we don't use scatterlists in
	 * the way it expects (we don't guarantee that the scatterlist
	 * will exist for the lifetime of the mapping).
	 */
	return dma_map_page(vring_dma_dev(vq),
			    sg_page(sg), sg->offset, sg->length,
			    direction);
}

static dma_addr_t vring_map_single(const struct vring_virtqueue *vq,
				   void *cpu_addr, size_t size,
				   enum dma_data_direction direction)
{
	if (!vring_use_dma_api(vq->vq.vdev))
		return (dma_addr_t)virt_to_phys(cpu_addr);

	return dma_map_single(vring_dma_dev(vq),
			      cpu_addr, size