Update Linux to v5.4.2
Change-Id: Idf6911045d9d382da2cfe01b1edff026404ac8fd
diff --git a/drivers/virtio/Kconfig b/drivers/virtio/Kconfig
index 3589764..078615c 100644
--- a/drivers/virtio/Kconfig
+++ b/drivers/virtio/Kconfig
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
config VIRTIO
tristate
---help---
@@ -42,6 +43,17 @@
If unsure, say Y.
+config VIRTIO_PMEM
+ tristate "Support for virtio pmem driver"
+ depends on VIRTIO
+ depends on LIBNVDIMM
+ help
+ This driver provides access to virtio-pmem devices, storage devices
+ that are mapped into the physical address space - similar to NVDIMMs
+ - with a virtio-based flushing interface.
+
+ If unsure, say Y.
+
config VIRTIO_BALLOON
tristate "Virtio balloon driver"
depends on VIRTIO
@@ -62,12 +74,12 @@
If unsure, say M.
- config VIRTIO_MMIO
+config VIRTIO_MMIO
tristate "Platform bus driver for memory mapped virtio devices"
depends on HAS_IOMEM && HAS_DMA
- select VIRTIO
- ---help---
- This drivers provides support for memory mapped virtio
+ select VIRTIO
+ ---help---
+ This drivers provides support for memory mapped virtio
platform device driver.
If unsure, say N.
diff --git a/drivers/virtio/virtio.c b/drivers/virtio/virtio.c
index 59e36ef..a977e32 100644
--- a/drivers/virtio/virtio.c
+++ b/drivers/virtio/virtio.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
#include <linux/virtio.h>
#include <linux/spinlock.h>
#include <linux/virtio_config.h>
@@ -161,6 +162,7 @@
void virtio_add_status(struct virtio_device *dev, unsigned int status)
{
+ might_sleep();
dev->config->set_status(dev, dev->config->get_status(dev) | status);
}
EXPORT_SYMBOL_GPL(virtio_add_status);
@@ -170,6 +172,7 @@
int ret = dev->config->finalize_features(dev);
unsigned status;
+ might_sleep();
if (ret)
return ret;
diff --git a/drivers/virtio/virtio_balloon.c b/drivers/virtio/virtio_balloon.c
index d1c1f62..e05679c 100644
--- a/drivers/virtio/virtio_balloon.c
+++ b/drivers/virtio/virtio_balloon.c
@@ -1,22 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
/*
* Virtio balloon implementation, inspired by Dor Laor and Marcelo
* Tosatti's implementations.
*
* Copyright 2008 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>
@@ -31,6 +18,7 @@
#include <linux/mm.h>
#include <linux/mount.h>
#include <linux/magic.h>
+#include <linux/pseudo_fs.h>
/*
* Balloon device works in 4K page units. So each page is pointed to by
@@ -41,13 +29,38 @@
#define VIRTIO_BALLOON_ARRAY_PFNS_MAX 256
#define VIRTBALLOON_OOM_NOTIFY_PRIORITY 80
+#define VIRTIO_BALLOON_FREE_PAGE_ALLOC_FLAG (__GFP_NORETRY | __GFP_NOWARN | \
+ __GFP_NOMEMALLOC)
+/* The order of free page blocks to report to host */
+#define VIRTIO_BALLOON_FREE_PAGE_ORDER (MAX_ORDER - 1)
+/* The size of a free page block in bytes */
+#define VIRTIO_BALLOON_FREE_PAGE_SIZE \
+ (1 << (VIRTIO_BALLOON_FREE_PAGE_ORDER + PAGE_SHIFT))
+
#ifdef CONFIG_BALLOON_COMPACTION
static struct vfsmount *balloon_mnt;
#endif
+enum virtio_balloon_vq {
+ VIRTIO_BALLOON_VQ_INFLATE,
+ VIRTIO_BALLOON_VQ_DEFLATE,
+ VIRTIO_BALLOON_VQ_STATS,
+ VIRTIO_BALLOON_VQ_FREE_PAGE,
+ VIRTIO_BALLOON_VQ_MAX
+};
+
+enum virtio_balloon_config_read {
+ VIRTIO_BALLOON_CONFIG_READ_CMD_ID = 0,
+};
+
struct virtio_balloon {
struct virtio_device *vdev;
- struct virtqueue *inflate_vq, *deflate_vq, *stats_vq;
+ struct virtqueue *inflate_vq, *deflate_vq, *stats_vq, *free_page_vq;
+
+ /* Balloon's own wq for cpu-intensive work items */
+ struct workqueue_struct *balloon_wq;
+ /* The free page reporting work item submitted to the balloon wq */
+ struct work_struct report_free_page_work;
/* The balloon servicing is delegated to a freezable workqueue. */
struct work_struct update_balloon_stats_work;
@@ -56,6 +69,24 @@
/* Prevent updating balloon when it is being canceled. */
spinlock_t stop_update_lock;
bool stop_update;
+ /* Bitmap to indicate if reading the related config fields are needed */
+ unsigned long config_read_bitmap;
+
+ /* The list of allocated free pages, waiting to be given back to mm */
+ struct list_head free_page_list;
+ spinlock_t free_page_list_lock;
+ /* The number of free page blocks on the above list */
+ unsigned long num_free_page_blocks;
+ /*
+ * The cmd id received from host.
+ * Read it via virtio_balloon_cmd_id_received to get the latest value
+ * sent from host.
+ */
+ u32 cmd_id_received_cache;
+ /* The cmd id that is actively in use */
+ __virtio32 cmd_id_active;
+ /* Buffer to store the stop sign */
+ __virtio32 cmd_id_stop;
/* Waiting for host to ack the pages we released. */
wait_queue_head_t acked;
@@ -320,17 +351,6 @@
virtqueue_kick(vq);
}
-static void virtballoon_changed(struct virtio_device *vdev)
-{
- struct virtio_balloon *vb = vdev->priv;
- unsigned long flags;
-
- spin_lock_irqsave(&vb->stop_update_lock, flags);
- if (!vb->stop_update)
- queue_work(system_freezable_wq, &vb->update_balloon_size_work);
- spin_unlock_irqrestore(&vb->stop_update_lock, flags);
-}
-
static inline s64 towards_target(struct virtio_balloon *vb)
{
s64 target;
@@ -347,6 +367,54 @@
return target - vb->num_pages;
}
+/* Gives back @num_to_return blocks of free pages to mm. */
+static unsigned long return_free_pages_to_mm(struct virtio_balloon *vb,
+ unsigned long num_to_return)
+{
+ struct page *page;
+ unsigned long num_returned;
+
+ spin_lock_irq(&vb->free_page_list_lock);
+ for (num_returned = 0; num_returned < num_to_return; num_returned++) {
+ page = balloon_page_pop(&vb->free_page_list);
+ if (!page)
+ break;
+ free_pages((unsigned long)page_address(page),
+ VIRTIO_BALLOON_FREE_PAGE_ORDER);
+ }
+ vb->num_free_page_blocks -= num_returned;
+ spin_unlock_irq(&vb->free_page_list_lock);
+
+ return num_returned;
+}
+
+static void virtio_balloon_queue_free_page_work(struct virtio_balloon *vb)
+{
+ if (!virtio_has_feature(vb->vdev, VIRTIO_BALLOON_F_FREE_PAGE_HINT))
+ return;
+
+ /* No need to queue the work if the bit was already set. */
+ if (test_and_set_bit(VIRTIO_BALLOON_CONFIG_READ_CMD_ID,
+ &vb->config_read_bitmap))
+ return;
+
+ queue_work(vb->balloon_wq, &vb->report_free_page_work);
+}
+
+static void virtballoon_changed(struct virtio_device *vdev)
+{
+ struct virtio_balloon *vb = vdev->priv;
+ unsigned long flags;
+
+ spin_lock_irqsave(&vb->stop_update_lock, flags);
+ if (!vb->stop_update) {
+ queue_work(system_freezable_wq,
+ &vb->update_balloon_size_work);
+ virtio_balloon_queue_free_page_work(vb);
+ }
+ spin_unlock_irqrestore(&vb->stop_update_lock, flags);
+}
+
static void update_balloon_size(struct virtio_balloon *vb)
{
u32 actual = vb->num_pages;
@@ -377,9 +445,12 @@
update_balloon_size_work);
diff = towards_target(vb);
+ if (!diff)
+ return;
+
if (diff > 0)
diff -= fill_balloon(vb, diff);
- else if (diff < 0)
+ else
diff += leak_balloon(vb, -diff);
update_balloon_size(vb);
@@ -389,26 +460,44 @@
static int init_vqs(struct virtio_balloon *vb)
{
- struct virtqueue *vqs[3];
- vq_callback_t *callbacks[] = { balloon_ack, balloon_ack, stats_request };
- static const char * const names[] = { "inflate", "deflate", "stats" };
- int err, nvqs;
+ struct virtqueue *vqs[VIRTIO_BALLOON_VQ_MAX];
+ vq_callback_t *callbacks[VIRTIO_BALLOON_VQ_MAX];
+ const char *names[VIRTIO_BALLOON_VQ_MAX];
+ int err;
/*
- * We expect two virtqueues: inflate and deflate, and
- * optionally stat.
+ * Inflateq and deflateq are used unconditionally. The names[]
+ * will be NULL if the related feature is not enabled, which will
+ * cause no allocation for the corresponding virtqueue in find_vqs.
*/
- nvqs = virtio_has_feature(vb->vdev, VIRTIO_BALLOON_F_STATS_VQ) ? 3 : 2;
- err = virtio_find_vqs(vb->vdev, nvqs, vqs, callbacks, names, NULL);
+ callbacks[VIRTIO_BALLOON_VQ_INFLATE] = balloon_ack;
+ names[VIRTIO_BALLOON_VQ_INFLATE] = "inflate";
+ callbacks[VIRTIO_BALLOON_VQ_DEFLATE] = balloon_ack;
+ names[VIRTIO_BALLOON_VQ_DEFLATE] = "deflate";
+ names[VIRTIO_BALLOON_VQ_STATS] = NULL;
+ names[VIRTIO_BALLOON_VQ_FREE_PAGE] = NULL;
+
+ if (virtio_has_feature(vb->vdev, VIRTIO_BALLOON_F_STATS_VQ)) {
+ names[VIRTIO_BALLOON_VQ_STATS] = "stats";
+ callbacks[VIRTIO_BALLOON_VQ_STATS] = stats_request;
+ }
+
+ if (virtio_has_feature(vb->vdev, VIRTIO_BALLOON_F_FREE_PAGE_HINT)) {
+ names[VIRTIO_BALLOON_VQ_FREE_PAGE] = "free_page_vq";
+ callbacks[VIRTIO_BALLOON_VQ_FREE_PAGE] = NULL;
+ }
+
+ err = vb->vdev->config->find_vqs(vb->vdev, VIRTIO_BALLOON_VQ_MAX,
+ vqs, callbacks, names, NULL, NULL);
if (err)
return err;
- vb->inflate_vq = vqs[0];
- vb->deflate_vq = vqs[1];
+ vb->inflate_vq = vqs[VIRTIO_BALLOON_VQ_INFLATE];
+ vb->deflate_vq = vqs[VIRTIO_BALLOON_VQ_DEFLATE];
if (virtio_has_feature(vb->vdev, VIRTIO_BALLOON_F_STATS_VQ)) {
struct scatterlist sg;
unsigned int num_stats;
- vb->stats_vq = vqs[2];
+ vb->stats_vq = vqs[VIRTIO_BALLOON_VQ_STATS];
/*
* Prime this virtqueue with one buffer so the hypervisor can
@@ -426,9 +515,173 @@
}
virtqueue_kick(vb->stats_vq);
}
+
+ if (virtio_has_feature(vb->vdev, VIRTIO_BALLOON_F_FREE_PAGE_HINT))
+ vb->free_page_vq = vqs[VIRTIO_BALLOON_VQ_FREE_PAGE];
+
return 0;
}
+static u32 virtio_balloon_cmd_id_received(struct virtio_balloon *vb)
+{
+ if (test_and_clear_bit(VIRTIO_BALLOON_CONFIG_READ_CMD_ID,
+ &vb->config_read_bitmap))
+ virtio_cread(vb->vdev, struct virtio_balloon_config,
+ free_page_report_cmd_id,
+ &vb->cmd_id_received_cache);
+
+ return vb->cmd_id_received_cache;
+}
+
+static int send_cmd_id_start(struct virtio_balloon *vb)
+{
+ struct scatterlist sg;
+ struct virtqueue *vq = vb->free_page_vq;
+ int err, unused;
+
+ /* Detach all the used buffers from the vq */
+ while (virtqueue_get_buf(vq, &unused))
+ ;
+
+ vb->cmd_id_active = virtio32_to_cpu(vb->vdev,
+ virtio_balloon_cmd_id_received(vb));
+ sg_init_one(&sg, &vb->cmd_id_active, sizeof(vb->cmd_id_active));
+ err = virtqueue_add_outbuf(vq, &sg, 1, &vb->cmd_id_active, GFP_KERNEL);
+ if (!err)
+ virtqueue_kick(vq);
+ return err;
+}
+
+static int send_cmd_id_stop(struct virtio_balloon *vb)
+{
+ struct scatterlist sg;
+ struct virtqueue *vq = vb->free_page_vq;
+ int err, unused;
+
+ /* Detach all the used buffers from the vq */
+ while (virtqueue_get_buf(vq, &unused))
+ ;
+
+ sg_init_one(&sg, &vb->cmd_id_stop, sizeof(vb->cmd_id_stop));
+ err = virtqueue_add_outbuf(vq, &sg, 1, &vb->cmd_id_stop, GFP_KERNEL);
+ if (!err)
+ virtqueue_kick(vq);
+ return err;
+}
+
+static int get_free_page_and_send(struct virtio_balloon *vb)
+{
+ struct virtqueue *vq = vb->free_page_vq;
+ struct page *page;
+ struct scatterlist sg;
+ int err, unused;
+ void *p;
+
+ /* Detach all the used buffers from the vq */
+ while (virtqueue_get_buf(vq, &unused))
+ ;
+
+ page = alloc_pages(VIRTIO_BALLOON_FREE_PAGE_ALLOC_FLAG,
+ VIRTIO_BALLOON_FREE_PAGE_ORDER);
+ /*
+ * When the allocation returns NULL, it indicates that we have got all
+ * the possible free pages, so return -EINTR to stop.
+ */
+ if (!page)
+ return -EINTR;
+
+ p = page_address(page);
+ sg_init_one(&sg, p, VIRTIO_BALLOON_FREE_PAGE_SIZE);
+ /* There is always 1 entry reserved for the cmd id to use. */
+ if (vq->num_free > 1) {
+ err = virtqueue_add_inbuf(vq, &sg, 1, p, GFP_KERNEL);
+ if (unlikely(err)) {
+ free_pages((unsigned long)p,
+ VIRTIO_BALLOON_FREE_PAGE_ORDER);
+ return err;
+ }
+ virtqueue_kick(vq);
+ spin_lock_irq(&vb->free_page_list_lock);
+ balloon_page_push(&vb->free_page_list, page);
+ vb->num_free_page_blocks++;
+ spin_unlock_irq(&vb->free_page_list_lock);
+ } else {
+ /*
+ * The vq has no available entry to add this page block, so
+ * just free it.
+ */
+ free_pages((unsigned long)p, VIRTIO_BALLOON_FREE_PAGE_ORDER);
+ }
+
+ return 0;
+}
+
+static int send_free_pages(struct virtio_balloon *vb)
+{
+ int err;
+ u32 cmd_id_active;
+
+ while (1) {
+ /*
+ * If a stop id or a new cmd id was just received from host,
+ * stop the reporting.
+ */
+ cmd_id_active = virtio32_to_cpu(vb->vdev, vb->cmd_id_active);
+ if (unlikely(cmd_id_active !=
+ virtio_balloon_cmd_id_received(vb)))
+ break;
+
+ /*
+ * The free page blocks are allocated and sent to host one by
+ * one.
+ */
+ err = get_free_page_and_send(vb);
+ if (err == -EINTR)
+ break;
+ else if (unlikely(err))
+ return err;
+ }
+
+ return 0;
+}
+
+static void virtio_balloon_report_free_page(struct virtio_balloon *vb)
+{
+ int err;
+ struct device *dev = &vb->vdev->dev;
+
+ /* Start by sending the received cmd id to host with an outbuf. */
+ err = send_cmd_id_start(vb);
+ if (unlikely(err))
+ dev_err(dev, "Failed to send a start id, err = %d\n", err);
+
+ err = send_free_pages(vb);
+ if (unlikely(err))
+ dev_err(dev, "Failed to send a free page, err = %d\n", err);
+
+ /* End by sending a stop id to host with an outbuf. */
+ err = send_cmd_id_stop(vb);
+ if (unlikely(err))
+ dev_err(dev, "Failed to send a stop id, err = %d\n", err);
+}
+
+static void report_free_page_func(struct work_struct *work)
+{
+ struct virtio_balloon *vb = container_of(work, struct virtio_balloon,
+ report_free_page_work);
+ u32 cmd_id_received;
+
+ cmd_id_received = virtio_balloon_cmd_id_received(vb);
+ if (cmd_id_received == VIRTIO_BALLOON_CMD_ID_DONE) {
+ /* Pass ULONG_MAX to give back all the free pages */
+ return_free_pages_to_mm(vb, ULONG_MAX);
+ } else if (cmd_id_received != VIRTIO_BALLOON_CMD_ID_STOP &&
+ cmd_id_received !=
+ virtio32_to_cpu(vb->vdev, vb->cmd_id_active)) {
+ virtio_balloon_report_free_page(vb);
+ }
+}
+
#ifdef CONFIG_BALLOON_COMPACTION
/*
* virtballoon_migratepage - perform the balloon page migration on behalf of
@@ -493,25 +746,58 @@
return MIGRATEPAGE_SUCCESS;
}
-static struct dentry *balloon_mount(struct file_system_type *fs_type,
- int flags, const char *dev_name, void *data)
+static int balloon_init_fs_context(struct fs_context *fc)
{
- static const struct dentry_operations ops = {
- .d_dname = simple_dname,
- };
-
- return mount_pseudo(fs_type, "balloon-kvm:", NULL, &ops,
- BALLOON_KVM_MAGIC);
+ return init_pseudo(fc, BALLOON_KVM_MAGIC) ? 0 : -ENOMEM;
}
static struct file_system_type balloon_fs = {
.name = "balloon-kvm",
- .mount = balloon_mount,
+ .init_fs_context = balloon_init_fs_context,
.kill_sb = kill_anon_super,
};
#endif /* CONFIG_BALLOON_COMPACTION */
+static unsigned long shrink_free_pages(struct virtio_balloon *vb,
+ unsigned long pages_to_free)
+{
+ unsigned long blocks_to_free, blocks_freed;
+
+ pages_to_free = round_up(pages_to_free,
+ 1 << VIRTIO_BALLOON_FREE_PAGE_ORDER);
+ blocks_to_free = pages_to_free >> VIRTIO_BALLOON_FREE_PAGE_ORDER;
+ blocks_freed = return_free_pages_to_mm(vb, blocks_to_free);
+
+ return blocks_freed << VIRTIO_BALLOON_FREE_PAGE_ORDER;
+}
+
+static unsigned long leak_balloon_pages(struct virtio_balloon *vb,
+ unsigned long pages_to_free)
+{
+ return leak_balloon(vb, pages_to_free * VIRTIO_BALLOON_PAGES_PER_PAGE) /
+ VIRTIO_BALLOON_PAGES_PER_PAGE;
+}
+
+static unsigned long shrink_balloon_pages(struct virtio_balloon *vb,
+ unsigned long pages_to_free)
+{
+ unsigned long pages_freed = 0;
+
+ /*
+ * One invocation of leak_balloon can deflate at most
+ * VIRTIO_BALLOON_ARRAY_PFNS_MAX balloon pages, so we call it
+ * multiple times to deflate pages till reaching pages_to_free.
+ */
+ while (vb->num_pages && pages_freed < pages_to_free)
+ pages_freed += leak_balloon_pages(vb,
+ pages_to_free - pages_freed);
+
+ update_balloon_size(vb);
+
+ return pages_freed;
+}
+
static unsigned long virtio_balloon_shrinker_scan(struct shrinker *shrinker,
struct shrink_control *sc)
{
@@ -519,20 +805,17 @@
struct virtio_balloon *vb = container_of(shrinker,
struct virtio_balloon, shrinker);
- pages_to_free = sc->nr_to_scan * VIRTIO_BALLOON_PAGES_PER_PAGE;
+ pages_to_free = sc->nr_to_scan;
- /*
- * One invocation of leak_balloon can deflate at most
- * VIRTIO_BALLOON_ARRAY_PFNS_MAX balloon pages, so we call it
- * multiple times to deflate pages till reaching pages_to_free.
- */
- while (vb->num_pages && pages_to_free) {
- pages_to_free -= pages_freed;
- pages_freed += leak_balloon(vb, pages_to_free);
- }
- update_balloon_size(vb);
+ if (virtio_has_feature(vb->vdev, VIRTIO_BALLOON_F_FREE_PAGE_HINT))
+ pages_freed = shrink_free_pages(vb, pages_to_free);
- return pages_freed / VIRTIO_BALLOON_PAGES_PER_PAGE;
+ if (pages_freed >= pages_to_free)
+ return pages_freed;
+
+ pages_freed += shrink_balloon_pages(vb, pages_to_free - pages_freed);
+
+ return pages_freed;
}
static unsigned long virtio_balloon_shrinker_count(struct shrinker *shrinker,
@@ -540,8 +823,12 @@
{
struct virtio_balloon *vb = container_of(shrinker,
struct virtio_balloon, shrinker);
+ unsigned long count;
- return vb->num_pages / VIRTIO_BALLOON_PAGES_PER_PAGE;
+ count = vb->num_pages / VIRTIO_BALLOON_PAGES_PER_PAGE;
+ count += vb->num_free_page_blocks << VIRTIO_BALLOON_FREE_PAGE_ORDER;
+
+ return count;
}
static void virtio_balloon_unregister_shrinker(struct virtio_balloon *vb)
@@ -561,6 +848,7 @@
static int virtballoon_probe(struct virtio_device *vdev)
{
struct virtio_balloon *vb;
+ __u32 poison_val;
int err;
if (!vdev->config->get) {
@@ -604,6 +892,35 @@
}
vb->vb_dev_info.inode->i_mapping->a_ops = &balloon_aops;
#endif
+ if (virtio_has_feature(vdev, VIRTIO_BALLOON_F_FREE_PAGE_HINT)) {
+ /*
+ * There is always one entry reserved for cmd id, so the ring
+ * size needs to be at least two to report free page hints.
+ */
+ if (virtqueue_get_vring_size(vb->free_page_vq) < 2) {
+ err = -ENOSPC;
+ goto out_del_vqs;
+ }
+ vb->balloon_wq = alloc_workqueue("balloon-wq",
+ WQ_FREEZABLE | WQ_CPU_INTENSIVE, 0);
+ if (!vb->balloon_wq) {
+ err = -ENOMEM;
+ goto out_del_vqs;
+ }
+ INIT_WORK(&vb->report_free_page_work, report_free_page_func);
+ vb->cmd_id_received_cache = VIRTIO_BALLOON_CMD_ID_STOP;
+ vb->cmd_id_active = cpu_to_virtio32(vb->vdev,
+ VIRTIO_BALLOON_CMD_ID_STOP);
+ vb->cmd_id_stop = cpu_to_virtio32(vb->vdev,
+ VIRTIO_BALLOON_CMD_ID_STOP);
+ spin_lock_init(&vb->free_page_list_lock);
+ INIT_LIST_HEAD(&vb->free_page_list);
+ if (virtio_has_feature(vdev, VIRTIO_BALLOON_F_PAGE_POISON)) {
+ memset(&poison_val, PAGE_POISON, sizeof(poison_val));
+ virtio_cwrite(vb->vdev, struct virtio_balloon_config,
+ poison_val, &poison_val);
+ }
+ }
/*
* We continue to use VIRTIO_BALLOON_F_DEFLATE_ON_OOM to decide if a
* shrinker needs to be registered to relieve memory pressure.
@@ -611,7 +928,7 @@
if (virtio_has_feature(vb->vdev, VIRTIO_BALLOON_F_DEFLATE_ON_OOM)) {
err = virtio_balloon_register_shrinker(vb);
if (err)
- goto out_del_vqs;
+ goto out_del_balloon_wq;
}
virtio_device_ready(vdev);
@@ -619,6 +936,9 @@
virtballoon_changed(vdev);
return 0;
+out_del_balloon_wq:
+ if (virtio_has_feature(vdev, VIRTIO_BALLOON_F_FREE_PAGE_HINT))
+ destroy_workqueue(vb->balloon_wq);
out_del_vqs:
vdev->config->del_vqs(vdev);
out_free_vb:
@@ -652,6 +972,11 @@
cancel_work_sync(&vb->update_balloon_size_work);
cancel_work_sync(&vb->update_balloon_stats_work);
+ if (virtio_has_feature(vdev, VIRTIO_BALLOON_F_FREE_PAGE_HINT)) {
+ cancel_work_sync(&vb->report_free_page_work);
+ destroy_workqueue(vb->balloon_wq);
+ }
+
remove_common(vb);
#ifdef CONFIG_BALLOON_COMPACTION
if (vb->vb_dev_info.inode)
@@ -695,6 +1020,9 @@
static int virtballoon_validate(struct virtio_device *vdev)
{
+ if (!page_poisoning_enabled())
+ __virtio_clear_bit(vdev, VIRTIO_BALLOON_F_PAGE_POISON);
+
__virtio_clear_bit(vdev, VIRTIO_F_IOMMU_PLATFORM);
return 0;
}
@@ -703,6 +1031,8 @@
VIRTIO_BALLOON_F_MUST_TELL_HOST,
VIRTIO_BALLOON_F_STATS_VQ,
VIRTIO_BALLOON_F_DEFLATE_ON_OOM,
+ VIRTIO_BALLOON_F_FREE_PAGE_HINT,
+ VIRTIO_BALLOON_F_PAGE_POISON,
};
static struct virtio_driver virtio_balloon_driver = {
diff --git a/drivers/virtio/virtio_input.c b/drivers/virtio/virtio_input.c
index 3a0468f..5ae5296 100644
--- a/drivers/virtio/virtio_input.c
+++ b/drivers/virtio/virtio_input.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
#include <linux/module.h>
#include <linux/virtio.h>
#include <linux/virtio_config.h>
diff --git a/drivers/virtio/virtio_mmio.c b/drivers/virtio/virtio_mmio.c
index 4cd9ea5..e09edb5 100644
--- a/drivers/virtio/virtio_mmio.c
+++ b/drivers/virtio/virtio_mmio.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
/*
* Virtio memory mapped device driver
*
@@ -48,12 +49,7 @@
* virtio_mmio.device=0x100@0x100b0000:48 \
* virtio_mmio.device=1K@0x1001e000:74
*
- *
- *
* Based on Virtio PCI driver by Anthony Liguori, copyright IBM Corp. 2007
- *
- * This work is licensed under the terms of the GNU GPL, version 2 or later.
- * See the COPYING file in the top-level directory.
*/
#define pr_fmt(fmt) "virtio-mmio: " fmt
@@ -467,8 +463,13 @@
struct irq_affinity *desc)
{
struct virtio_mmio_device *vm_dev = to_virtio_mmio_device(vdev);
- unsigned int irq = platform_get_irq(vm_dev->pdev, 0);
- int i, err;
+ int irq = platform_get_irq(vm_dev->pdev, 0);
+ int i, err, queue_idx = 0;
+
+ if (irq < 0) {
+ dev_err(&vdev->dev, "Cannot get IRQ resource\n");
+ return irq;
+ }
err = request_irq(irq, vm_interrupt, IRQF_SHARED,
dev_name(&vdev->dev), vm_dev);
@@ -476,7 +477,12 @@
return err;
for (i = 0; i < nvqs; ++i) {
- vqs[i] = vm_setup_vq(vdev, i, callbacks[i], names[i],
+ if (!names[i]) {
+ vqs[i] = NULL;
+ continue;
+ }
+
+ vqs[i] = vm_setup_vq(vdev, queue_idx++, callbacks[i], names[i],
ctx ? ctx[i] : false);
if (IS_ERR(vqs[i])) {
vm_del_vqs(vdev);
diff --git a/drivers/virtio/virtio_pci_common.c b/drivers/virtio/virtio_pci_common.c
index 465a6f5..f2862f6 100644
--- a/drivers/virtio/virtio_pci_common.c
+++ b/drivers/virtio/virtio_pci_common.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
/*
* Virtio PCI driver - common functionality for all device versions
*
@@ -11,10 +12,6 @@
* Anthony Liguori <aliguori@us.ibm.com>
* Rusty Russell <rusty@rustcorp.com.au>
* Michael S. Tsirkin <mst@redhat.com>
- *
- * This work is licensed under the terms of the GNU GPL, version 2 or later.
- * See the COPYING file in the top-level directory.
- *
*/
#include "virtio_pci_common.h"
@@ -255,9 +252,11 @@
for (i = 0; i < vp_dev->msix_used_vectors; ++i)
free_irq(pci_irq_vector(vp_dev->pci_dev, i), vp_dev);
- for (i = 0; i < vp_dev->msix_vectors; i++)
- if (vp_dev->msix_affinity_masks[i])
- free_cpumask_var(vp_dev->msix_affinity_masks[i]);
+ if (vp_dev->msix_affinity_masks) {
+ for (i = 0; i < vp_dev->msix_vectors; i++)
+ if (vp_dev->msix_affinity_masks[i])
+ free_cpumask_var(vp_dev->msix_affinity_masks[i]);
+ }
if (vp_dev->msix_enabled) {
/* Disable the vector used for configuration */
@@ -285,7 +284,7 @@
{
struct virtio_pci_device *vp_dev = to_vp_device(vdev);
u16 msix_vec;
- int i, err, nvectors, allocated_vectors;
+ int i, err, nvectors, allocated_vectors, queue_idx = 0;
vp_dev->vqs = kcalloc(nvqs, sizeof(*vp_dev->vqs), GFP_KERNEL);
if (!vp_dev->vqs)
@@ -321,7 +320,7 @@
msix_vec = allocated_vectors++;
else
msix_vec = VP_MSIX_VQ_VECTOR;
- vqs[i] = vp_setup_vq(vdev, i, callbacks[i], names[i],
+ vqs[i] = vp_setup_vq(vdev, queue_idx++, callbacks[i], names[i],
ctx ? ctx[i] : false,
msix_vec);
if (IS_ERR(vqs[i])) {
@@ -356,7 +355,7 @@
const char * const names[], const bool *ctx)
{
struct virtio_pci_device *vp_dev = to_vp_device(vdev);
- int i, err;
+ int i, err, queue_idx = 0;
vp_dev->vqs = kcalloc(nvqs, sizeof(*vp_dev->vqs), GFP_KERNEL);
if (!vp_dev->vqs)
@@ -374,7 +373,7 @@
vqs[i] = NULL;
continue;
}
- vqs[i] = vp_setup_vq(vdev, i, callbacks[i], names[i],
+ vqs[i] = vp_setup_vq(vdev, queue_idx++, callbacks[i], names[i],
ctx ? ctx[i] : false,
VIRTIO_MSI_NO_VECTOR);
if (IS_ERR(vqs[i])) {
diff --git a/drivers/virtio/virtio_pci_common.h b/drivers/virtio/virtio_pci_common.h
index 0227100..b2f0eb4 100644
--- a/drivers/virtio/virtio_pci_common.h
+++ b/drivers/virtio/virtio_pci_common.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
#ifndef _DRIVERS_VIRTIO_VIRTIO_PCI_COMMON_H
#define _DRIVERS_VIRTIO_VIRTIO_PCI_COMMON_H
/*
@@ -13,10 +14,6 @@
* Anthony Liguori <aliguori@us.ibm.com>
* Rusty Russell <rusty@rustcorp.com.au>
* Michael S. Tsirkin <mst@redhat.com>
- *
- * This work is licensed under the terms of the GNU GPL, version 2 or later.
- * See the COPYING file in the top-level directory.
- *
*/
#include <linux/module.h>
diff --git a/drivers/virtio/virtio_pci_legacy.c b/drivers/virtio/virtio_pci_legacy.c
index de062fb..d62e983 100644
--- a/drivers/virtio/virtio_pci_legacy.c
+++ b/drivers/virtio/virtio_pci_legacy.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
/*
* Virtio PCI driver - legacy device support
*
@@ -11,10 +12,6 @@
* Anthony Liguori <aliguori@us.ibm.com>
* Rusty Russell <rusty@rustcorp.com.au>
* Michael S. Tsirkin <mst@redhat.com>
- *
- * This work is licensed under the terms of the GNU GPL, version 2 or later.
- * See the COPYING file in the top-level directory.
- *
*/
#include "virtio_pci_common.h"
@@ -52,7 +49,8 @@
{
struct virtio_pci_device *vp_dev = to_vp_device(vdev);
void __iomem *ioaddr = vp_dev->ioaddr +
- VIRTIO_PCI_CONFIG(vp_dev) + offset;
+ VIRTIO_PCI_CONFIG_OFF(vp_dev->msix_enabled) +
+ offset;
u8 *ptr = buf;
int i;
@@ -67,7 +65,8 @@
{
struct virtio_pci_device *vp_dev = to_vp_device(vdev);
void __iomem *ioaddr = vp_dev->ioaddr +
- VIRTIO_PCI_CONFIG(vp_dev) + offset;
+ VIRTIO_PCI_CONFIG_OFF(vp_dev->msix_enabled) +
+ offset;
const u8 *ptr = buf;
int i;
diff --git a/drivers/virtio/virtio_pci_modern.c b/drivers/virtio/virtio_pci_modern.c
index 07571da..7abcc50 100644
--- a/drivers/virtio/virtio_pci_modern.c
+++ b/drivers/virtio/virtio_pci_modern.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
/*
* Virtio PCI driver - modern (virtio 1.0) device support
*
@@ -11,10 +12,6 @@
* Anthony Liguori <aliguori@us.ibm.com>
* Rusty Russell <rusty@rustcorp.com.au>
* Michael S. Tsirkin <mst@redhat.com>
- *
- * This work is licensed under the terms of the GNU GPL, version 2 or later.
- * See the COPYING file in the top-level directory.
- *
*/
#include <linux/delay.h>
diff --git a/drivers/virtio/virtio_ring.c b/drivers/virtio/virtio_ring.c
index 814b395..867c7eb 100644
--- a/drivers/virtio/virtio_ring.c
+++ b/drivers/virtio/virtio_ring.c
@@ -1,20 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
/* 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>
@@ -44,6 +31,26 @@
} while (0)
#define END_USE(_vq) \
do { BUG_ON(!(_vq)->in_use); (_vq)->in_use = 0; } while(0)
+#define LAST_ADD_TIME_UPDATE(_vq) \
+ do { \
+ ktime_t now = ktime_get(); \
+ \
+ /* No kick or get, with .1 second between? Warn. */ \
+ if ((_vq)->last_add_time_valid) \
+ WARN_ON(ktime_to_ms(ktime_sub(now, \
+ (_vq)->last_add_time)) > 100); \
+ (_vq)->last_add_time = now; \
+ (_vq)->last_add_time_valid = true; \
+ } while (0)
+#define LAST_ADD_TIME_CHECK(_vq) \
+ do { \
+ if ((_vq)->last_add_time_valid) { \
+ WARN_ON(ktime_to_ms(ktime_sub(ktime_get(), \
+ (_vq)->last_add_time)) > 100); \
+ } \
+ } while (0)
+#define LAST_ADD_TIME_INVALID(_vq) \
+ ((_vq)->last_add_time_valid = false)
#else
#define BAD_RING(_vq, fmt, args...) \
do { \
@@ -53,18 +60,38 @@
} while (0)
#define START_USE(vq)
#define END_USE(vq)
+#define LAST_ADD_TIME_UPDATE(vq)
+#define LAST_ADD_TIME_CHECK(vq)
+#define LAST_ADD_TIME_INVALID(vq)
#endif
-struct vring_desc_state {
+struct vring_desc_state_split {
void *data; /* Data for callback. */
struct vring_desc *indir_desc; /* Indirect descriptor, if any. */
};
+struct vring_desc_state_packed {
+ void *data; /* Data for callback. */
+ struct vring_packed_desc *indir_desc; /* Indirect descriptor, if any. */
+ u16 num; /* Descriptor list length. */
+ u16 next; /* The next desc state in a list. */
+ u16 last; /* The last desc state in a list. */
+};
+
+struct vring_desc_extra_packed {
+ dma_addr_t addr; /* Buffer DMA addr. */
+ u32 len; /* Buffer length. */
+ u16 flags; /* Descriptor flags. */
+};
+
struct vring_virtqueue {
struct virtqueue vq;
- /* Actual memory layout for this queue */
- struct vring vring;
+ /* Is this a packed ring? */
+ bool packed_ring;
+
+ /* Is DMA API used? */
+ bool use_dma_api;
/* Can we use weak barriers? */
bool weak_barriers;
@@ -86,19 +113,75 @@
/* Last used index we've seen. */
u16 last_used_idx;
- /* Last written value to avail->flags */
- u16 avail_flags_shadow;
+ union {
+ /* Available for split ring */
+ struct {
+ /* Actual memory layout for this queue. */
+ struct vring vring;
- /* Last written value to avail->idx in guest byte order */
- u16 avail_idx_shadow;
+ /* Last written value to avail->flags */
+ u16 avail_flags_shadow;
+
+ /*
+ * Last written value to avail->idx in
+ * guest byte order.
+ */
+ u16 avail_idx_shadow;
+
+ /* Per-descriptor state. */
+ struct vring_desc_state_split *desc_state;
+
+ /* DMA address and size information */
+ dma_addr_t queue_dma_addr;
+ size_t queue_size_in_bytes;
+ } split;
+
+ /* Available for packed ring */
+ struct {
+ /* Actual memory layout for this queue. */
+ struct {
+ unsigned int num;
+ struct vring_packed_desc *desc;
+ struct vring_packed_desc_event *driver;
+ struct vring_packed_desc_event *device;
+ } vring;
+
+ /* Driver ring wrap counter. */
+ bool avail_wrap_counter;
+
+ /* Device ring wrap counter. */
+ bool used_wrap_counter;
+
+ /* Avail used flags. */
+ u16 avail_used_flags;
+
+ /* Index of the next avail descriptor. */
+ u16 next_avail_idx;
+
+ /*
+ * Last written value to driver->flags in
+ * guest byte order.
+ */
+ u16 event_flags_shadow;
+
+ /* Per-descriptor state. */
+ struct vring_desc_state_packed *desc_state;
+ struct vring_desc_extra_packed *desc_extra;
+
+ /* DMA address and size information */
+ dma_addr_t ring_dma_addr;
+ dma_addr_t driver_event_dma_addr;
+ dma_addr_t device_event_dma_addr;
+ size_t ring_size_in_bytes;
+ size_t event_size_in_bytes;
+ } packed;
+ };
/* 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. */
@@ -108,13 +191,27 @@
bool last_add_time_valid;
ktime_t last_add_time;
#endif
-
- /* Per-descriptor state. */
- struct vring_desc_state desc_state[];
};
+
+/*
+ * Helpers.
+ */
+
#define to_vvq(_vq) container_of(_vq, struct vring_virtqueue, vq)
+static inline bool virtqueue_use_indirect(struct virtqueue *_vq,
+ unsigned int total_sg)
+{
+ struct vring_virtqueue *vq = to_vvq(_vq);
+
+ /*
+ * If the host supports indirect descriptor tables, and we have multiple
+ * buffers, then go indirect. FIXME: tune this threshold
+ */
+ return (vq->indirect && total_sg > 1 && vq->vq.num_free);
+}
+
/*
* 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.
@@ -161,6 +258,59 @@
return false;
}
+size_t virtio_max_dma_size(struct virtio_device *vdev)
+{
+ size_t max_segment_size = SIZE_MAX;
+
+ if (vring_use_dma_api(vdev))
+ max_segment_size = dma_max_mapping_size(&vdev->dev);
+
+ return max_segment_size;
+}
+EXPORT_SYMBOL_GPL(virtio_max_dma_size);
+
+static void *vring_alloc_queue(struct virtio_device *vdev, size_t size,
+ dma_addr_t *dma_handle, gfp_t flag)
+{
+ if (vring_use_dma_api(vdev)) {
+ return dma_alloc_coherent(vdev->dev.parent, size,
+ dma_handle, flag);
+ } else {
+ void *queue = alloc_pages_exact(PAGE_ALIGN(size), flag);
+
+ if (queue) {
+ phys_addr_t phys_addr = virt_to_phys(queue);
+ *dma_handle = (dma_addr_t)phys_addr;
+
+ /*
+ * Sanity check: make sure we dind't truncate
+ * the address. The only arches I can find that
+ * have 64-bit phys_addr_t but 32-bit dma_addr_t
+ * are certain non-highmem MIPS and x86
+ * configurations, but these configurations
+ * should never allocate physical pages above 32
+ * bits, so this is fine. Just in case, throw a
+ * warning and abort if we end up with an
+ * unrepresentable address.
+ */
+ if (WARN_ON_ONCE(*dma_handle != phys_addr)) {
+ free_pages_exact(queue, PAGE_ALIGN(size));
+ return NULL;
+ }
+ }
+ return queue;
+ }
+}
+
+static void vring_free_queue(struct virtio_device *vdev, size_t size,
+ void *queue, dma_addr_t dma_handle)
+{
+ if (vring_use_dma_api(vdev))
+ dma_free_coherent(vdev->dev.parent, size, queue, dma_handle);
+ else
+ free_pages_exact(queue, PAGE_ALIGN(size));
+}
+
/*
* 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
@@ -176,7 +326,7 @@
struct scatterlist *sg,
enum dma_data_direction direction)
{
- if (!vring_use_dma_api(vq->vq.vdev))
+ if (!vq->use_dma_api)
return (dma_addr_t)sg_phys(sg);
/*
@@ -193,19 +343,33 @@
void *cpu_addr, size_t size,
enum dma_data_direction direction)
{
- if (!vring_use_dma_api(vq->vq.vdev))
+ if (!vq->use_dma_api)
return (dma_addr_t)virt_to_phys(cpu_addr);
return dma_map_single(vring_dma_dev(vq),
cpu_addr, size, direction);
}
-static void vring_unmap_one(const struct vring_virtqueue *vq,
- struct vring_desc *desc)
+static int vring_mapping_error(const struct vring_virtqueue *vq,
+ dma_addr_t addr)
+{
+ if (!vq->use_dma_api)
+ return 0;
+
+ return dma_mapping_error(vring_dma_dev(vq), addr);
+}
+
+
+/*
+ * Split ring specific functions - *_split().
+ */
+
+static void vring_unmap_one_split(const struct vring_virtqueue *vq,
+ struct vring_desc *desc)
{
u16 flags;
- if (!vring_use_dma_api(vq->vq.vdev))
+ if (!vq->use_dma_api)
return;
flags = virtio16_to_cpu(vq->vq.vdev, desc->flags);
@@ -225,17 +389,9 @@
}
}
-static int vring_mapping_error(const struct vring_virtqueue *vq,
- dma_addr_t addr)
-{
- if (!vring_use_dma_api(vq->vq.vdev))
- return 0;
-
- return dma_mapping_error(vring_dma_dev(vq), addr);
-}
-
-static struct vring_desc *alloc_indirect(struct virtqueue *_vq,
- unsigned int total_sg, gfp_t gfp)
+static struct vring_desc *alloc_indirect_split(struct virtqueue *_vq,
+ unsigned int total_sg,
+ gfp_t gfp)
{
struct vring_desc *desc;
unsigned int i;
@@ -256,14 +412,14 @@
return desc;
}
-static inline int virtqueue_add(struct virtqueue *_vq,
- struct scatterlist *sgs[],
- unsigned int total_sg,
- unsigned int out_sgs,
- unsigned int in_sgs,
- void *data,
- void *ctx,
- gfp_t gfp)
+static inline int virtqueue_add_split(struct virtqueue *_vq,
+ struct scatterlist *sgs[],
+ unsigned int total_sg,
+ unsigned int out_sgs,
+ unsigned int in_sgs,
+ void *data,
+ void *ctx,
+ gfp_t gfp)
{
struct vring_virtqueue *vq = to_vvq(_vq);
struct scatterlist *sg;
@@ -282,30 +438,17 @@
return -EIO;
}
-#ifdef DEBUG
- {
- ktime_t now = ktime_get();
-
- /* No kick or get, with .1 second between? Warn. */
- if (vq->last_add_time_valid)
- WARN_ON(ktime_to_ms(ktime_sub(now, vq->last_add_time))
- > 100);
- vq->last_add_time = now;
- vq->last_add_time_valid = true;
- }
-#endif
+ LAST_ADD_TIME_UPDATE(vq);
BUG_ON(total_sg == 0);
head = vq->free_head;
- /* If the host supports indirect descriptor tables, and we have multiple
- * buffers, then go indirect. FIXME: tune this threshold */
- if (vq->indirect && total_sg > 1 && vq->vq.num_free)
- desc = alloc_indirect(_vq, total_sg, gfp);
+ if (virtqueue_use_indirect(_vq, total_sg))
+ desc = alloc_indirect_split(_vq, total_sg, gfp);
else {
desc = NULL;
- WARN_ON_ONCE(total_sg > vq->vring.num && !vq->indirect);
+ WARN_ON_ONCE(total_sg > vq->split.vring.num && !vq->indirect);
}
if (desc) {
@@ -316,7 +459,7 @@
descs_used = 1;
} else {
indirect = false;
- desc = vq->vring.desc;
+ desc = vq->split.vring.desc;
i = head;
descs_used = total_sg;
}
@@ -372,10 +515,13 @@
if (vring_mapping_error(vq, addr))
goto unmap_release;
- vq->vring.desc[head].flags = cpu_to_virtio16(_vq->vdev, VRING_DESC_F_INDIRECT);
- vq->vring.desc[head].addr = cpu_to_virtio64(_vq->vdev, addr);
+ vq->split.vring.desc[head].flags = cpu_to_virtio16(_vq->vdev,
+ VRING_DESC_F_INDIRECT);
+ vq->split.vring.desc[head].addr = cpu_to_virtio64(_vq->vdev,
+ addr);
- vq->vring.desc[head].len = cpu_to_virtio32(_vq->vdev, total_sg * sizeof(struct vring_desc));
+ vq->split.vring.desc[head].len = cpu_to_virtio32(_vq->vdev,
+ total_sg * sizeof(struct vring_desc));
}
/* We're using some buffers from the free list. */
@@ -383,27 +529,29 @@
/* Update free pointer */
if (indirect)
- vq->free_head = virtio16_to_cpu(_vq->vdev, vq->vring.desc[head].next);
+ vq->free_head = virtio16_to_cpu(_vq->vdev,
+ vq->split.vring.desc[head].next);
else
vq->free_head = i;
/* Store token and indirect buffer state. */
- vq->desc_state[head].data = data;
+ vq->split.desc_state[head].data = data;
if (indirect)
- vq->desc_state[head].indir_desc = desc;
+ vq->split.desc_state[head].indir_desc = desc;
else
- vq->desc_state[head].indir_desc = ctx;
+ vq->split.desc_state[head].indir_desc = ctx;
/* Put entry in available array (but don't update avail->idx until they
* do sync). */
- avail = vq->avail_idx_shadow & (vq->vring.num - 1);
- vq->vring.avail->ring[avail] = cpu_to_virtio16(_vq->vdev, head);
+ avail = vq->split.avail_idx_shadow & (vq->split.vring.num - 1);
+ vq->split.vring.avail->ring[avail] = cpu_to_virtio16(_vq->vdev, head);
/* Descriptors and available array need to be set before we expose the
* new available array entries. */
virtio_wmb(vq->weak_barriers);
- vq->avail_idx_shadow++;
- vq->vring.avail->idx = cpu_to_virtio16(_vq->vdev, vq->avail_idx_shadow);
+ vq->split.avail_idx_shadow++;
+ vq->split.vring.avail->idx = cpu_to_virtio16(_vq->vdev,
+ vq->split.avail_idx_shadow);
vq->num_added++;
pr_debug("Added buffer head %i to %p\n", head, vq);
@@ -418,28 +566,1153 @@
unmap_release:
err_idx = i;
- i = head;
+
+ if (indirect)
+ i = 0;
+ else
+ i = head;
for (n = 0; n < total_sg; n++) {
if (i == err_idx)
break;
- vring_unmap_one(vq, &desc[i]);
- i = virtio16_to_cpu(_vq->vdev, vq->vring.desc[i].next);
+ vring_unmap_one_split(vq, &desc[i]);
+ i = virtio16_to_cpu(_vq->vdev, desc[i].next);
}
if (indirect)
kfree(desc);
END_USE(vq);
+ return -ENOMEM;
+}
+
+static bool virtqueue_kick_prepare_split(struct virtqueue *_vq)
+{
+ struct vring_virtqueue *vq = to_vvq(_vq);
+ u16 new, old;
+ bool needs_kick;
+
+ START_USE(vq);
+ /* We need to expose available array entries before checking avail
+ * event. */
+ virtio_mb(vq->weak_barriers);
+
+ old = vq->split.avail_idx_shadow - vq->num_added;
+ new = vq->split.avail_idx_shadow;
+ vq->num_added = 0;
+
+ LAST_ADD_TIME_CHECK(vq);
+ LAST_ADD_TIME_INVALID(vq);
+
+ if (vq->event) {
+ needs_kick = vring_need_event(virtio16_to_cpu(_vq->vdev,
+ vring_avail_event(&vq->split.vring)),
+ new, old);
+ } else {
+ needs_kick = !(vq->split.vring.used->flags &
+ cpu_to_virtio16(_vq->vdev,
+ VRING_USED_F_NO_NOTIFY));
+ }
+ END_USE(vq);
+ return needs_kick;
+}
+
+static void detach_buf_split(struct vring_virtqueue *vq, unsigned int head,
+ void **ctx)
+{
+ unsigned int i, j;
+ __virtio16 nextflag = cpu_to_virtio16(vq->vq.vdev, VRING_DESC_F_NEXT);
+
+ /* Clear data ptr. */
+ vq->split.desc_state[head].data = NULL;
+
+ /* Put back on free list: unmap first-level descriptors and find end */
+ i = head;
+
+ while (vq->split.vring.desc[i].flags & nextflag) {
+ vring_unmap_one_split(vq, &vq->split.vring.desc[i]);
+ i = virtio16_to_cpu(vq->vq.vdev, vq->split.vring.desc[i].next);
+ vq->vq.num_free++;
+ }
+
+ vring_unmap_one_split(vq, &vq->split.vring.desc[i]);
+ vq->split.vring.desc[i].next = cpu_to_virtio16(vq->vq.vdev,
+ vq->free_head);
+ vq->free_head = head;
+
+ /* Plus final descriptor */
+ vq->vq.num_free++;
+
+ if (vq->indirect) {
+ struct vring_desc *indir_desc =
+ vq->split.desc_state[head].indir_desc;
+ u32 len;
+
+ /* Free the indirect table, if any, now that it's unmapped. */
+ if (!indir_desc)
+ return;
+
+ len = virtio32_to_cpu(vq->vq.vdev,
+ vq->split.vring.desc[head].len);
+
+ BUG_ON(!(vq->split.vring.desc[head].flags &
+ cpu_to_virtio16(vq->vq.vdev, VRING_DESC_F_INDIRECT)));
+ BUG_ON(len == 0 || len % sizeof(struct vring_desc));
+
+ for (j = 0; j < len / sizeof(struct vring_desc); j++)
+ vring_unmap_one_split(vq, &indir_desc[j]);
+
+ kfree(indir_desc);
+ vq->split.desc_state[head].indir_desc = NULL;
+ } else if (ctx) {
+ *ctx = vq->split.desc_state[head].indir_desc;
+ }
+}
+
+static inline bool more_used_split(const struct vring_virtqueue *vq)
+{
+ return vq->last_used_idx != virtio16_to_cpu(vq->vq.vdev,
+ vq->split.vring.used->idx);
+}
+
+static void *virtqueue_get_buf_ctx_split(struct virtqueue *_vq,
+ unsigned int *len,
+ void **ctx)
+{
+ struct vring_virtqueue *vq = to_vvq(_vq);
+ void *ret;
+ unsigned int i;
+ u16 last_used;
+
+ START_USE(vq);
+
+ if (unlikely(vq->broken)) {
+ END_USE(vq);
+ return NULL;
+ }
+
+ if (!more_used_split(vq)) {
+ pr_debug("No more buffers in queue\n");
+ END_USE(vq);
+ return NULL;
+ }
+
+ /* Only get used array entries after they have been exposed by host. */
+ virtio_rmb(vq->weak_barriers);
+
+ last_used = (vq->last_used_idx & (vq->split.vring.num - 1));
+ i = virtio32_to_cpu(_vq->vdev,
+ vq->split.vring.used->ring[last_used].id);
+ *len = virtio32_to_cpu(_vq->vdev,
+ vq->split.vring.used->ring[last_used].len);
+
+ if (unlikely(i >= vq->split.vring.num)) {
+ BAD_RING(vq, "id %u out of range\n", i);
+ return NULL;
+ }
+ if (unlikely(!vq->split.desc_state[i].data)) {
+ BAD_RING(vq, "id %u is not a head!\n", i);
+ return NULL;
+ }
+
+ /* detach_buf_split clears data, so grab it now. */
+ ret = vq->split.desc_state[i].data;
+ detach_buf_split(vq, i, ctx);
+ vq->last_used_idx++;
+ /* If we expect an interrupt for the next entry, tell host
+ * by writing event index and flush out the write before
+ * the read in the next get_buf call. */
+ if (!(vq->split.avail_flags_shadow & VRING_AVAIL_F_NO_INTERRUPT))
+ virtio_store_mb(vq->weak_barriers,
+ &vring_used_event(&vq->split.vring),
+ cpu_to_virtio16(_vq->vdev, vq->last_used_idx));
+
+ LAST_ADD_TIME_INVALID(vq);
+
+ END_USE(vq);
+ return ret;
+}
+
+static void virtqueue_disable_cb_split(struct virtqueue *_vq)
+{
+ struct vring_virtqueue *vq = to_vvq(_vq);
+
+ if (!(vq->split.avail_flags_shadow & VRING_AVAIL_F_NO_INTERRUPT)) {
+ vq->split.avail_flags_shadow |= VRING_AVAIL_F_NO_INTERRUPT;
+ if (!vq->event)
+ vq->split.vring.avail->flags =
+ cpu_to_virtio16(_vq->vdev,
+ vq->split.avail_flags_shadow);
+ }
+}
+
+static unsigned virtqueue_enable_cb_prepare_split(struct virtqueue *_vq)
+{
+ struct vring_virtqueue *vq = to_vvq(_vq);
+ u16 last_used_idx;
+
+ START_USE(vq);
+
+ /* We optimistically turn back on interrupts, then check if there was
+ * more to do. */
+ /* Depending on the VIRTIO_RING_F_EVENT_IDX feature, we need to
+ * either clear the flags bit or point the event index at the next
+ * entry. Always do both to keep code simple. */
+ if (vq->split.avail_flags_shadow & VRING_AVAIL_F_NO_INTERRUPT) {
+ vq->split.avail_flags_shadow &= ~VRING_AVAIL_F_NO_INTERRUPT;
+ if (!vq->event)
+ vq->split.vring.avail->flags =
+ cpu_to_virtio16(_vq->vdev,
+ vq->split.avail_flags_shadow);
+ }
+ vring_used_event(&vq->split.vring) = cpu_to_virtio16(_vq->vdev,
+ last_used_idx = vq->last_used_idx);
+ END_USE(vq);
+ return last_used_idx;
+}
+
+static bool virtqueue_poll_split(struct virtqueue *_vq, unsigned last_used_idx)
+{
+ struct vring_virtqueue *vq = to_vvq(_vq);
+
+ return (u16)last_used_idx != virtio16_to_cpu(_vq->vdev,
+ vq->split.vring.used->idx);
+}
+
+static bool virtqueue_enable_cb_delayed_split(struct virtqueue *_vq)
+{
+ struct vring_virtqueue *vq = to_vvq(_vq);
+ u16 bufs;
+
+ START_USE(vq);
+
+ /* We optimistically turn back on interrupts, then check if there was
+ * more to do. */
+ /* Depending on the VIRTIO_RING_F_USED_EVENT_IDX feature, we need to
+ * either clear the flags bit or point the event index at the next
+ * entry. Always update the event index to keep code simple. */
+ if (vq->split.avail_flags_shadow & VRING_AVAIL_F_NO_INTERRUPT) {
+ vq->split.avail_flags_shadow &= ~VRING_AVAIL_F_NO_INTERRUPT;
+ if (!vq->event)
+ vq->split.vring.avail->flags =
+ cpu_to_virtio16(_vq->vdev,
+ vq->split.avail_flags_shadow);
+ }
+ /* TODO: tune this threshold */
+ bufs = (u16)(vq->split.avail_idx_shadow - vq->last_used_idx) * 3 / 4;
+
+ virtio_store_mb(vq->weak_barriers,
+ &vring_used_event(&vq->split.vring),
+ cpu_to_virtio16(_vq->vdev, vq->last_used_idx + bufs));
+
+ if (unlikely((u16)(virtio16_to_cpu(_vq->vdev, vq->split.vring.used->idx)
+ - vq->last_used_idx) > bufs)) {
+ END_USE(vq);
+ return false;
+ }
+
+ END_USE(vq);
+ return true;
+}
+
+static void *virtqueue_detach_unused_buf_split(struct virtqueue *_vq)
+{
+ struct vring_virtqueue *vq = to_vvq(_vq);
+ unsigned int i;
+ void *buf;
+
+ START_USE(vq);
+
+ for (i = 0; i < vq->split.vring.num; i++) {
+ if (!vq->split.desc_state[i].data)
+ continue;
+ /* detach_buf_split clears data, so grab it now. */
+ buf = vq->split.desc_state[i].data;
+ detach_buf_split(vq, i, NULL);
+ vq->split.avail_idx_shadow--;
+ vq->split.vring.avail->idx = cpu_to_virtio16(_vq->vdev,
+ vq->split.avail_idx_shadow);
+ END_USE(vq);
+ return buf;
+ }
+ /* That should have freed everything. */
+ BUG_ON(vq->vq.num_free != vq->split.vring.num);
+
+ END_USE(vq);
+ return NULL;
+}
+
+static struct virtqueue *vring_create_virtqueue_split(
+ unsigned int index,
+ unsigned int num,
+ unsigned int vring_align,
+ struct virtio_device *vdev,
+ bool weak_barriers,
+ bool may_reduce_num,
+ bool context,
+ bool (*notify)(struct virtqueue *),
+ void (*callback)(struct virtqueue *),
+ const char *name)
+{
+ struct virtqueue *vq;
+ void *queue = NULL;
+ dma_addr_t dma_addr;
+ size_t queue_size_in_bytes;
+ struct vring vring;
+
+ /* We assume num is a power of 2. */
+ if (num & (num - 1)) {
+ dev_warn(&vdev->dev, "Bad virtqueue length %u\n", num);
+ return NULL;
+ }
+
+ /* TODO: allocate each queue chunk individually */
+ for (; num && vring_size(num, vring_align) > PAGE_SIZE; num /= 2) {
+ queue = vring_alloc_queue(vdev, vring_size(num, vring_align),
+ &dma_addr,
+ GFP_KERNEL|__GFP_NOWARN|__GFP_ZERO);
+ if (queue)
+ break;
+ if (!may_reduce_num)
+ return NULL;
+ }
+
+ if (!num)
+ return NULL;
+
+ if (!queue) {
+ /* Try to get a single page. You are my only hope! */
+ queue = vring_alloc_queue(vdev, vring_size(num, vring_align),
+ &dma_addr, GFP_KERNEL|__GFP_ZERO);
+ }
+ if (!queue)
+ return NULL;
+
+ queue_size_in_bytes = vring_size(num, vring_align);
+ vring_init(&vring, num, queue, vring_align);
+
+ vq = __vring_new_virtqueue(index, vring, vdev, weak_barriers, context,
+ notify, callback, name);
+ if (!vq) {
+ vring_free_queue(vdev, queue_size_in_bytes, queue,
+ dma_addr);
+ return NULL;
+ }
+
+ to_vvq(vq)->split.queue_dma_addr = dma_addr;
+ to_vvq(vq)->split.queue_size_in_bytes = queue_size_in_bytes;
+ to_vvq(vq)->we_own_ring = true;
+
+ return vq;
+}
+
+
+/*
+ * Packed ring specific functions - *_packed().
+ */
+
+static void vring_unmap_state_packed(const struct vring_virtqueue *vq,
+ struct vring_desc_extra_packed *state)
+{
+ u16 flags;
+
+ if (!vq->use_dma_api)
+ return;
+
+ flags = state->flags;
+
+ if (flags & VRING_DESC_F_INDIRECT) {
+ dma_unmap_single(vring_dma_dev(vq),
+ state->addr, state->len,
+ (flags & VRING_DESC_F_WRITE) ?
+ DMA_FROM_DEVICE : DMA_TO_DEVICE);
+ } else {
+ dma_unmap_page(vring_dma_dev(vq),
+ state->addr, state->len,
+ (flags & VRING_DESC_F_WRITE) ?
+ DMA_FROM_DEVICE : DMA_TO_DEVICE);
+ }
+}
+
+static void vring_unmap_desc_packed(const struct vring_virtqueue *vq,
+ struct vring_packed_desc *desc)
+{
+ u16 flags;
+
+ if (!vq->use_dma_api)
+ return;
+
+ flags = le16_to_cpu(desc->flags);
+
+ if (flags & VRING_DESC_F_INDIRECT) {
+ dma_unmap_single(vring_dma_dev(vq),
+ le64_to_cpu(desc->addr),
+ le32_to_cpu(desc->len),
+ (flags & VRING_DESC_F_WRITE) ?
+ DMA_FROM_DEVICE : DMA_TO_DEVICE);
+ } else {
+ dma_unmap_page(vring_dma_dev(vq),
+ le64_to_cpu(desc->addr),
+ le32_to_cpu(desc->len),
+ (flags & VRING_DESC_F_WRITE) ?
+ DMA_FROM_DEVICE : DMA_TO_DEVICE);
+ }
+}
+
+static struct vring_packed_desc *alloc_indirect_packed(unsigned int total_sg,
+ gfp_t gfp)
+{
+ struct vring_packed_desc *desc;
+
+ /*
+ * We require lowmem mappings for the descriptors because
+ * otherwise virt_to_phys will give us bogus addresses in the
+ * virtqueue.
+ */
+ gfp &= ~__GFP_HIGHMEM;
+
+ desc = kmalloc_array(total_sg, sizeof(struct vring_packed_desc), gfp);
+
+ return desc;
+}
+
+static int virtqueue_add_indirect_packed(struct vring_virtqueue *vq,
+ struct scatterlist *sgs[],
+ unsigned int total_sg,
+ unsigned int out_sgs,
+ unsigned int in_sgs,
+ void *data,
+ gfp_t gfp)
+{
+ struct vring_packed_desc *desc;
+ struct scatterlist *sg;
+ unsigned int i, n, err_idx;
+ u16 head, id;
+ dma_addr_t addr;
+
+ head = vq->packed.next_avail_idx;
+ desc = alloc_indirect_packed(total_sg, gfp);
+
+ if (unlikely(vq->vq.num_free < 1)) {
+ pr_debug("Can't add buf len 1 - avail = 0\n");
+ kfree(desc);
+ END_USE(vq);
+ return -ENOSPC;
+ }
+
+ i = 0;
+ id = vq->free_head;
+ BUG_ON(id == vq->packed.vring.num);
+
+ for (n = 0; n < out_sgs + in_sgs; n++) {
+ for (sg = sgs[n]; sg; sg = sg_next(sg)) {
+ addr = vring_map_one_sg(vq, sg, n < out_sgs ?
+ DMA_TO_DEVICE : DMA_FROM_DEVICE);
+ if (vring_mapping_error(vq, addr))
+ goto unmap_release;
+
+ desc[i].flags = cpu_to_le16(n < out_sgs ?
+ 0 : VRING_DESC_F_WRITE);
+ desc[i].addr = cpu_to_le64(addr);
+ desc[i].len = cpu_to_le32(sg->length);
+ i++;
+ }
+ }
+
+ /* Now that the indirect table is filled in, map it. */
+ addr = vring_map_single(vq, desc,
+ total_sg * sizeof(struct vring_packed_desc),
+ DMA_TO_DEVICE);
+ if (vring_mapping_error(vq, addr))
+ goto unmap_release;
+
+ vq->packed.vring.desc[head].addr = cpu_to_le64(addr);
+ vq->packed.vring.desc[head].len = cpu_to_le32(total_sg *
+ sizeof(struct vring_packed_desc));
+ vq->packed.vring.desc[head].id = cpu_to_le16(id);
+
+ if (vq->use_dma_api) {
+ vq->packed.desc_extra[id].addr = addr;
+ vq->packed.desc_extra[id].len = total_sg *
+ sizeof(struct vring_packed_desc);
+ vq->packed.desc_extra[id].flags = VRING_DESC_F_INDIRECT |
+ vq->packed.avail_used_flags;
+ }
+
+ /*
+ * A driver MUST NOT make the first descriptor in the list
+ * available before all subsequent descriptors comprising
+ * the list are made available.
+ */
+ virtio_wmb(vq->weak_barriers);
+ vq->packed.vring.desc[head].flags = cpu_to_le16(VRING_DESC_F_INDIRECT |
+ vq->packed.avail_used_flags);
+
+ /* We're using some buffers from the free list. */
+ vq->vq.num_free -= 1;
+
+ /* Update free pointer */
+ n = head + 1;
+ if (n >= vq->packed.vring.num) {
+ n = 0;
+ vq->packed.avail_wrap_counter ^= 1;
+ vq->packed.avail_used_flags ^=
+ 1 << VRING_PACKED_DESC_F_AVAIL |
+ 1 << VRING_PACKED_DESC_F_USED;
+ }
+ vq->packed.next_avail_idx = n;
+ vq->free_head = vq->packed.desc_state[id].next;
+
+ /* Store token and indirect buffer state. */
+ vq->packed.desc_state[id].num = 1;
+ vq->packed.desc_state[id].data = data;
+ vq->packed.desc_state[id].indir_desc = desc;
+ vq->packed.desc_state[id].last = id;
+
+ vq->num_added += 1;
+
+ pr_debug("Added buffer head %i to %p\n", head, vq);
+ END_USE(vq);
+
+ return 0;
+
+unmap_release:
+ err_idx = i;
+
+ for (i = 0; i < err_idx; i++)
+ vring_unmap_desc_packed(vq, &desc[i]);
+
+ kfree(desc);
+
+ END_USE(vq);
+ return -ENOMEM;
+}
+
+static inline int virtqueue_add_packed(struct virtqueue *_vq,
+ struct scatterlist *sgs[],
+ unsigned int total_sg,
+ unsigned int out_sgs,
+ unsigned int in_sgs,
+ void *data,
+ void *ctx,
+ gfp_t gfp)
+{
+ struct vring_virtqueue *vq = to_vvq(_vq);
+ struct vring_packed_desc *desc;
+ struct scatterlist *sg;
+ unsigned int i, n, c, descs_used, err_idx;
+ __le16 uninitialized_var(head_flags), flags;
+ u16 head, id, uninitialized_var(prev), curr, avail_used_flags;
+
+ START_USE(vq);
+
+ BUG_ON(data == NULL);
+ BUG_ON(ctx && vq->indirect);
+
+ if (unlikely(vq->broken)) {
+ END_USE(vq);
+ return -EIO;
+ }
+
+ LAST_ADD_TIME_UPDATE(vq);
+
+ BUG_ON(total_sg == 0);
+
+ if (virtqueue_use_indirect(_vq, total_sg))
+ return virtqueue_add_indirect_packed(vq, sgs, total_sg,
+ out_sgs, in_sgs, data, gfp);
+
+ head = vq->packed.next_avail_idx;
+ avail_used_flags = vq->packed.avail_used_flags;
+
+ WARN_ON_ONCE(total_sg > vq->packed.vring.num && !vq->indirect);
+
+ desc = vq->packed.vring.desc;
+ i = head;
+ descs_used = total_sg;
+
+ if (unlikely(vq->vq.num_free < descs_used)) {
+ pr_debug("Can't add buf len %i - avail = %i\n",
+ descs_used, vq->vq.num_free);
+ END_USE(vq);
+ return -ENOSPC;
+ }
+
+ id = vq->free_head;
+ BUG_ON(id == vq->packed.vring.num);
+
+ curr = id;
+ c = 0;
+ for (n = 0; n < out_sgs + in_sgs; n++) {
+ for (sg = sgs[n]; sg; sg = sg_next(sg)) {
+ dma_addr_t addr = vring_map_one_sg(vq, sg, n < out_sgs ?
+ DMA_TO_DEVICE : DMA_FROM_DEVICE);
+ if (vring_mapping_error(vq, addr))
+ goto unmap_release;
+
+ flags = cpu_to_le16(vq->packed.avail_used_flags |
+ (++c == total_sg ? 0 : VRING_DESC_F_NEXT) |
+ (n < out_sgs ? 0 : VRING_DESC_F_WRITE));
+ if (i == head)
+ head_flags = flags;
+ else
+ desc[i].flags = flags;
+
+ desc[i].addr = cpu_to_le64(addr);
+ desc[i].len = cpu_to_le32(sg->length);
+ desc[i].id = cpu_to_le16(id);
+
+ if (unlikely(vq->use_dma_api)) {
+ vq->packed.desc_extra[curr].addr = addr;
+ vq->packed.desc_extra[curr].len = sg->length;
+ vq->packed.desc_extra[curr].flags =
+ le16_to_cpu(flags);
+ }
+ prev = curr;
+ curr = vq->packed.desc_state[curr].next;
+
+ if ((unlikely(++i >= vq->packed.vring.num))) {
+ i = 0;
+ vq->packed.avail_used_flags ^=
+ 1 << VRING_PACKED_DESC_F_AVAIL |
+ 1 << VRING_PACKED_DESC_F_USED;
+ }
+ }
+ }
+
+ if (i < head)
+ vq->packed.avail_wrap_counter ^= 1;
+
+ /* We're using some buffers from the free list. */
+ vq->vq.num_free -= descs_used;
+
+ /* Update free pointer */
+ vq->packed.next_avail_idx = i;
+ vq->free_head = curr;
+
+ /* Store token. */
+ vq->packed.desc_state[id].num = descs_used;
+ vq->packed.desc_state[id].data = data;
+ vq->packed.desc_state[id].indir_desc = ctx;
+ vq->packed.desc_state[id].last = prev;
+
+ /*
+ * A driver MUST NOT make the first descriptor in the list
+ * available before all subsequent descriptors comprising
+ * the list are made available.
+ */
+ virtio_wmb(vq->weak_barriers);
+ vq->packed.vring.desc[head].flags = head_flags;
+ vq->num_added += descs_used;
+
+ pr_debug("Added buffer head %i to %p\n", head, vq);
+ END_USE(vq);
+
+ return 0;
+
+unmap_release:
+ err_idx = i;
+ i = head;
+
+ vq->packed.avail_used_flags = avail_used_flags;
+
+ for (n = 0; n < total_sg; n++) {
+ if (i == err_idx)
+ break;
+ vring_unmap_desc_packed(vq, &desc[i]);
+ i++;
+ if (i >= vq->packed.vring.num)
+ i = 0;
+ }
+
+ END_USE(vq);
return -EIO;
}
+static bool virtqueue_kick_prepare_packed(struct virtqueue *_vq)
+{
+ struct vring_virtqueue *vq = to_vvq(_vq);
+ u16 new, old, off_wrap, flags, wrap_counter, event_idx;
+ bool needs_kick;
+ union {
+ struct {
+ __le16 off_wrap;
+ __le16 flags;
+ };
+ u32 u32;
+ } snapshot;
+
+ START_USE(vq);
+
+ /*
+ * We need to expose the new flags value before checking notification
+ * suppressions.
+ */
+ virtio_mb(vq->weak_barriers);
+
+ old = vq->packed.next_avail_idx - vq->num_added;
+ new = vq->packed.next_avail_idx;
+ vq->num_added = 0;
+
+ snapshot.u32 = *(u32 *)vq->packed.vring.device;
+ flags = le16_to_cpu(snapshot.flags);
+
+ LAST_ADD_TIME_CHECK(vq);
+ LAST_ADD_TIME_INVALID(vq);
+
+ if (flags != VRING_PACKED_EVENT_FLAG_DESC) {
+ needs_kick = (flags != VRING_PACKED_EVENT_FLAG_DISABLE);
+ goto out;
+ }
+
+ off_wrap = le16_to_cpu(snapshot.off_wrap);
+
+ wrap_counter = off_wrap >> VRING_PACKED_EVENT_F_WRAP_CTR;
+ event_idx = off_wrap & ~(1 << VRING_PACKED_EVENT_F_WRAP_CTR);
+ if (wrap_counter != vq->packed.avail_wrap_counter)
+ event_idx -= vq->packed.vring.num;
+
+ needs_kick = vring_need_event(event_idx, new, old);
+out:
+ END_USE(vq);
+ return needs_kick;
+}
+
+static void detach_buf_packed(struct vring_virtqueue *vq,
+ unsigned int id, void **ctx)
+{
+ struct vring_desc_state_packed *state = NULL;
+ struct vring_packed_desc *desc;
+ unsigned int i, curr;
+
+ state = &vq->packed.desc_state[id];
+
+ /* Clear data ptr. */
+ state->data = NULL;
+
+ vq->packed.desc_state[state->last].next = vq->free_head;
+ vq->free_head = id;
+ vq->vq.num_free += state->num;
+
+ if (unlikely(vq->use_dma_api)) {
+ curr = id;
+ for (i = 0; i < state->num; i++) {
+ vring_unmap_state_packed(vq,
+ &vq->packed.desc_extra[curr]);
+ curr = vq->packed.desc_state[curr].next;
+ }
+ }
+
+ if (vq->indirect) {
+ u32 len;
+
+ /* Free the indirect table, if any, now that it's unmapped. */
+ desc = state->indir_desc;
+ if (!desc)
+ return;
+
+ if (vq->use_dma_api) {
+ len = vq->packed.desc_extra[id].len;
+ for (i = 0; i < len / sizeof(struct vring_packed_desc);
+ i++)
+ vring_unmap_desc_packed(vq, &desc[i]);
+ }
+ kfree(desc);
+ state->indir_desc = NULL;
+ } else if (ctx) {
+ *ctx = state->indir_desc;
+ }
+}
+
+static inline bool is_used_desc_packed(const struct vring_virtqueue *vq,
+ u16 idx, bool used_wrap_counter)
+{
+ bool avail, used;
+ u16 flags;
+
+ flags = le16_to_cpu(vq->packed.vring.desc[idx].flags);
+ avail = !!(flags & (1 << VRING_PACKED_DESC_F_AVAIL));
+ used = !!(flags & (1 << VRING_PACKED_DESC_F_USED));
+
+ return avail == used && used == used_wrap_counter;
+}
+
+static inline bool more_used_packed(const struct vring_virtqueue *vq)
+{
+ return is_used_desc_packed(vq, vq->last_used_idx,
+ vq->packed.used_wrap_counter);
+}
+
+static void *virtqueue_get_buf_ctx_packed(struct virtqueue *_vq,
+ unsigned int *len,
+ void **ctx)
+{
+ struct vring_virtqueue *vq = to_vvq(_vq);
+ u16 last_used, id;
+ void *ret;
+
+ START_USE(vq);
+
+ if (unlikely(vq->broken)) {
+ END_USE(vq);
+ return NULL;
+ }
+
+ if (!more_used_packed(vq)) {
+ pr_debug("No more buffers in queue\n");
+ END_USE(vq);
+ return NULL;
+ }
+
+ /* Only get used elements after they have been exposed by host. */
+ virtio_rmb(vq->weak_barriers);
+
+ last_used = vq->last_used_idx;
+ id = le16_to_cpu(vq->packed.vring.desc[last_used].id);
+ *len = le32_to_cpu(vq->packed.vring.desc[last_used].len);
+
+ if (unlikely(id >= vq->packed.vring.num)) {
+ BAD_RING(vq, "id %u out of range\n", id);
+ return NULL;
+ }
+ if (unlikely(!vq->packed.desc_state[id].data)) {
+ BAD_RING(vq, "id %u is not a head!\n", id);
+ return NULL;
+ }
+
+ /* detach_buf_packed clears data, so grab it now. */
+ ret = vq->packed.desc_state[id].data;
+ detach_buf_packed(vq, id, ctx);
+
+ vq->last_used_idx += vq->packed.desc_state[id].num;
+ if (unlikely(vq->last_used_idx >= vq->packed.vring.num)) {
+ vq->last_used_idx -= vq->packed.vring.num;
+ vq->packed.used_wrap_counter ^= 1;
+ }
+
+ /*
+ * If we expect an interrupt for the next entry, tell host
+ * by writing event index and flush out the write before
+ * the read in the next get_buf call.
+ */
+ if (vq->packed.event_flags_shadow == VRING_PACKED_EVENT_FLAG_DESC)
+ virtio_store_mb(vq->weak_barriers,
+ &vq->packed.vring.driver->off_wrap,
+ cpu_to_le16(vq->last_used_idx |
+ (vq->packed.used_wrap_counter <<
+ VRING_PACKED_EVENT_F_WRAP_CTR)));
+
+ LAST_ADD_TIME_INVALID(vq);
+
+ END_USE(vq);
+ return ret;
+}
+
+static void virtqueue_disable_cb_packed(struct virtqueue *_vq)
+{
+ struct vring_virtqueue *vq = to_vvq(_vq);
+
+ if (vq->packed.event_flags_shadow != VRING_PACKED_EVENT_FLAG_DISABLE) {
+ vq->packed.event_flags_shadow = VRING_PACKED_EVENT_FLAG_DISABLE;
+ vq->packed.vring.driver->flags =
+ cpu_to_le16(vq->packed.event_flags_shadow);
+ }
+}
+
+static unsigned virtqueue_enable_cb_prepare_packed(struct virtqueue *_vq)
+{
+ struct vring_virtqueue *vq = to_vvq(_vq);
+
+ START_USE(vq);
+
+ /*
+ * We optimistically turn back on interrupts, then check if there was
+ * more to do.
+ */
+
+ if (vq->event) {
+ vq->packed.vring.driver->off_wrap =
+ cpu_to_le16(vq->last_used_idx |
+ (vq->packed.used_wrap_counter <<
+ VRING_PACKED_EVENT_F_WRAP_CTR));
+ /*
+ * We need to update event offset and event wrap
+ * counter first before updating event flags.
+ */
+ virtio_wmb(vq->weak_barriers);
+ }
+
+ if (vq->packed.event_flags_shadow == VRING_PACKED_EVENT_FLAG_DISABLE) {
+ vq->packed.event_flags_shadow = vq->event ?
+ VRING_PACKED_EVENT_FLAG_DESC :
+ VRING_PACKED_EVENT_FLAG_ENABLE;
+ vq->packed.vring.driver->flags =
+ cpu_to_le16(vq->packed.event_flags_shadow);
+ }
+
+ END_USE(vq);
+ return vq->last_used_idx | ((u16)vq->packed.used_wrap_counter <<
+ VRING_PACKED_EVENT_F_WRAP_CTR);
+}
+
+static bool virtqueue_poll_packed(struct virtqueue *_vq, u16 off_wrap)
+{
+ struct vring_virtqueue *vq = to_vvq(_vq);
+ bool wrap_counter;
+ u16 used_idx;
+
+ wrap_counter = off_wrap >> VRING_PACKED_EVENT_F_WRAP_CTR;
+ used_idx = off_wrap & ~(1 << VRING_PACKED_EVENT_F_WRAP_CTR);
+
+ return is_used_desc_packed(vq, used_idx, wrap_counter);
+}
+
+static bool virtqueue_enable_cb_delayed_packed(struct virtqueue *_vq)
+{
+ struct vring_virtqueue *vq = to_vvq(_vq);
+ u16 used_idx, wrap_counter;
+ u16 bufs;
+
+ START_USE(vq);
+
+ /*
+ * We optimistically turn back on interrupts, then check if there was
+ * more to do.
+ */
+
+ if (vq->event) {
+ /* TODO: tune this threshold */
+ bufs = (vq->packed.vring.num - vq->vq.num_free) * 3 / 4;
+ wrap_counter = vq->packed.used_wrap_counter;
+
+ used_idx = vq->last_used_idx + bufs;
+ if (used_idx >= vq->packed.vring.num) {
+ used_idx -= vq->packed.vring.num;
+ wrap_counter ^= 1;
+ }
+
+ vq->packed.vring.driver->off_wrap = cpu_to_le16(used_idx |
+ (wrap_counter << VRING_PACKED_EVENT_F_WRAP_CTR));
+
+ /*
+ * We need to update event offset and event wrap
+ * counter first before updating event flags.
+ */
+ virtio_wmb(vq->weak_barriers);
+ }
+
+ if (vq->packed.event_flags_shadow == VRING_PACKED_EVENT_FLAG_DISABLE) {
+ vq->packed.event_flags_shadow = vq->event ?
+ VRING_PACKED_EVENT_FLAG_DESC :
+ VRING_PACKED_EVENT_FLAG_ENABLE;
+ vq->packed.vring.driver->flags =
+ cpu_to_le16(vq->packed.event_flags_shadow);
+ }
+
+ /*
+ * We need to update event suppression structure first
+ * before re-checking for more used buffers.
+ */
+ virtio_mb(vq->weak_barriers);
+
+ if (is_used_desc_packed(vq,
+ vq->last_used_idx,
+ vq->packed.used_wrap_counter)) {
+ END_USE(vq);
+ return false;
+ }
+
+ END_USE(vq);
+ return true;
+}
+
+static void *virtqueue_detach_unused_buf_packed(struct virtqueue *_vq)
+{
+ struct vring_virtqueue *vq = to_vvq(_vq);
+ unsigned int i;
+ void *buf;
+
+ START_USE(vq);
+
+ for (i = 0; i < vq->packed.vring.num; i++) {
+ if (!vq->packed.desc_state[i].data)
+ continue;
+ /* detach_buf clears data, so grab it now. */
+ buf = vq->packed.desc_state[i].data;
+ detach_buf_packed(vq, i, NULL);
+ END_USE(vq);
+ return buf;
+ }
+ /* That should have freed everything. */
+ BUG_ON(vq->vq.num_free != vq->packed.vring.num);
+
+ END_USE(vq);
+ return NULL;
+}
+
+static struct virtqueue *vring_create_virtqueue_packed(
+ unsigned int index,
+ unsigned int num,
+ unsigned int vring_align,
+ struct virtio_device *vdev,
+ bool weak_barriers,
+ bool may_reduce_num,
+ bool context,
+ bool (*notify)(struct virtqueue *),
+ void (*callback)(struct virtqueue *),
+ const char *name)
+{
+ struct vring_virtqueue *vq;
+ struct vring_packed_desc *ring;
+ struct vring_packed_desc_event *driver, *device;
+ dma_addr_t ring_dma_addr, driver_event_dma_addr, device_event_dma_addr;
+ size_t ring_size_in_bytes, event_size_in_bytes;
+ unsigned int i;
+
+ ring_size_in_bytes = num * sizeof(struct vring_packed_desc);
+
+ ring = vring_alloc_queue(vdev, ring_size_in_bytes,
+ &ring_dma_addr,
+ GFP_KERNEL|__GFP_NOWARN|__GFP_ZERO);
+ if (!ring)
+ goto err_ring;
+
+ event_size_in_bytes = sizeof(struct vring_packed_desc_event);
+
+ driver = vring_alloc_queue(vdev, event_size_in_bytes,
+ &driver_event_dma_addr,
+ GFP_KERNEL|__GFP_NOWARN|__GFP_ZERO);
+ if (!driver)
+ goto err_driver;
+
+ device = vring_alloc_queue(vdev, event_size_in_bytes,
+ &device_event_dma_addr,
+ GFP_KERNEL|__GFP_NOWARN|__GFP_ZERO);
+ if (!device)
+ goto err_device;
+
+ vq = kmalloc(sizeof(*vq), GFP_KERNEL);
+ if (!vq)
+ goto err_vq;
+
+ vq->vq.callback = callback;
+ vq->vq.vdev = vdev;
+ vq->vq.name = name;
+ vq->vq.num_free = num;
+ vq->vq.index = index;
+ vq->we_own_ring = true;
+ vq->notify = notify;
+ vq->weak_barriers = weak_barriers;
+ vq->broken = false;
+ vq->last_used_idx = 0;
+ vq->num_added = 0;
+ vq->packed_ring = true;
+ vq->use_dma_api = vring_use_dma_api(vdev);
+ list_add_tail(&vq->vq.list, &vdev->vqs);
+#ifdef DEBUG
+ vq->in_use = false;
+ vq->last_add_time_valid = false;
+#endif
+
+ vq->indirect = virtio_has_feature(vdev, VIRTIO_RING_F_INDIRECT_DESC) &&
+ !context;
+ vq->event = virtio_has_feature(vdev, VIRTIO_RING_F_EVENT_IDX);
+
+ if (virtio_has_feature(vdev, VIRTIO_F_ORDER_PLATFORM))
+ vq->weak_barriers = false;
+
+ vq->packed.ring_dma_addr = ring_dma_addr;
+ vq->packed.driver_event_dma_addr = driver_event_dma_addr;
+ vq->packed.device_event_dma_addr = device_event_dma_addr;
+
+ vq->packed.ring_size_in_bytes = ring_size_in_bytes;
+ vq->packed.event_size_in_bytes = event_size_in_bytes;
+
+ vq->packed.vring.num = num;
+ vq->packed.vring.desc = ring;
+ vq->packed.vring.driver = driver;
+ vq->packed.vring.device = device;
+
+ vq->packed.next_avail_idx = 0;
+ vq->packed.avail_wrap_counter = 1;
+ vq->packed.used_wrap_counter = 1;
+ vq->packed.event_flags_shadow = 0;
+ vq->packed.avail_used_flags = 1 << VRING_PACKED_DESC_F_AVAIL;
+
+ vq->packed.desc_state = kmalloc_array(num,
+ sizeof(struct vring_desc_state_packed),
+ GFP_KERNEL);
+ if (!vq->packed.desc_state)
+ goto err_desc_state;
+
+ memset(vq->packed.desc_state, 0,
+ num * sizeof(struct vring_desc_state_packed));
+
+ /* Put everything in free lists. */
+ vq->free_head = 0;
+ for (i = 0; i < num-1; i++)
+ vq->packed.desc_state[i].next = i + 1;
+
+ vq->packed.desc_extra = kmalloc_array(num,
+ sizeof(struct vring_desc_extra_packed),
+ GFP_KERNEL);
+ if (!vq->packed.desc_extra)
+ goto err_desc_extra;
+
+ memset(vq->packed.desc_extra, 0,
+ num * sizeof(struct vring_desc_extra_packed));
+
+ /* No callback? Tell other side not to bother us. */
+ if (!callback) {
+ vq->packed.event_flags_shadow = VRING_PACKED_EVENT_FLAG_DISABLE;
+ vq->packed.vring.driver->flags =
+ cpu_to_le16(vq->packed.event_flags_shadow);
+ }
+
+ return &vq->vq;
+
+err_desc_extra:
+ kfree(vq->packed.desc_state);
+err_desc_state:
+ kfree(vq);
+err_vq:
+ vring_free_queue(vdev, event_size_in_bytes, device, ring_dma_addr);
+err_device:
+ vring_free_queue(vdev, event_size_in_bytes, driver, ring_dma_addr);
+err_driver:
+ vring_free_queue(vdev, ring_size_in_bytes, ring, ring_dma_addr);
+err_ring:
+ return NULL;
+}
+
+
+/*
+ * Generic functions and exported symbols.
+ */
+
+static inline int virtqueue_add(struct virtqueue *_vq,
+ struct scatterlist *sgs[],
+ unsigned int total_sg,
+ unsigned int out_sgs,
+ unsigned int in_sgs,
+ void *data,
+ void *ctx,
+ gfp_t gfp)
+{
+ struct vring_virtqueue *vq = to_vvq(_vq);
+
+ return vq->packed_ring ? virtqueue_add_packed(_vq, sgs, total_sg,
+ out_sgs, in_sgs, data, ctx, gfp) :
+ virtqueue_add_split(_vq, sgs, total_sg,
+ out_sgs, in_sgs, data, ctx, gfp);
+}
+
/**
* virtqueue_add_sgs - expose buffers to other end
- * @vq: the struct virtqueue we're talking about.
+ * @_vq: the struct virtqueue we're talking about.
* @sgs: array of terminated scatterlists.
- * @out_num: the number of scatterlists readable by other side
- * @in_num: the number of scatterlists which are writable (after readable ones)
+ * @out_sgs: the number of scatterlists readable by other side
+ * @in_sgs: the number of scatterlists which are writable (after readable ones)
* @data: the token identifying the buffer.
* @gfp: how to do memory allocations (if necessary).
*
@@ -460,6 +1733,7 @@
/* Count them first. */
for (i = 0; i < out_sgs + in_sgs; i++) {
struct scatterlist *sg;
+
for (sg = sgs[i]; sg; sg = sg_next(sg))
total_sg++;
}
@@ -538,7 +1812,7 @@
/**
* virtqueue_kick_prepare - first half of split virtqueue_kick call.
- * @vq: the struct virtqueue
+ * @_vq: the struct virtqueue
*
* Instead of virtqueue_kick(), you can do:
* if (virtqueue_kick_prepare(vq))
@@ -550,40 +1824,15 @@
bool virtqueue_kick_prepare(struct virtqueue *_vq)
{
struct vring_virtqueue *vq = to_vvq(_vq);
- u16 new, old;
- bool needs_kick;
- START_USE(vq);
- /* We need to expose available array entries before checking avail
- * event. */
- virtio_mb(vq->weak_barriers);
-
- old = vq->avail_idx_shadow - vq->num_added;
- new = vq->avail_idx_shadow;
- vq->num_added = 0;
-
-#ifdef DEBUG
- if (vq->last_add_time_valid) {
- WARN_ON(ktime_to_ms(ktime_sub(ktime_get(),
- vq->last_add_time)) > 100);
- }
- vq->last_add_time_valid = false;
-#endif
-
- if (vq->event) {
- needs_kick = vring_need_event(virtio16_to_cpu(_vq->vdev, vring_avail_event(&vq->vring)),
- new, old);
- } else {
- needs_kick = !(vq->vring.used->flags & cpu_to_virtio16(_vq->vdev, VRING_USED_F_NO_NOTIFY));
- }
- END_USE(vq);
- return needs_kick;
+ return vq->packed_ring ? virtqueue_kick_prepare_packed(_vq) :
+ virtqueue_kick_prepare_split(_vq);
}
EXPORT_SYMBOL_GPL(virtqueue_kick_prepare);
/**
* virtqueue_notify - second half of split virtqueue_kick call.
- * @vq: the struct virtqueue
+ * @_vq: the struct virtqueue
*
* This does not need to be serialized.
*
@@ -625,64 +1874,11 @@
}
EXPORT_SYMBOL_GPL(virtqueue_kick);
-static void detach_buf(struct vring_virtqueue *vq, unsigned int head,
- void **ctx)
-{
- unsigned int i, j;
- __virtio16 nextflag = cpu_to_virtio16(vq->vq.vdev, VRING_DESC_F_NEXT);
-
- /* Clear data ptr. */
- vq->desc_state[head].data = NULL;
-
- /* Put back on free list: unmap first-level descriptors and find end */
- i = head;
-
- while (vq->vring.desc[i].flags & nextflag) {
- vring_unmap_one(vq, &vq->vring.desc[i]);
- i = virtio16_to_cpu(vq->vq.vdev, vq->vring.desc[i].next);
- vq->vq.num_free++;
- }
-
- vring_unmap_one(vq, &vq->vring.desc[i]);
- vq->vring.desc[i].next = cpu_to_virtio16(vq->vq.vdev, vq->free_head);
- vq->free_head = head;
-
- /* Plus final descriptor */
- vq->vq.num_free++;
-
- if (vq->indirect) {
- struct vring_desc *indir_desc = vq->desc_state[head].indir_desc;
- u32 len;
-
- /* Free the indirect table, if any, now that it's unmapped. */
- if (!indir_desc)
- return;
-
- len = virtio32_to_cpu(vq->vq.vdev, vq->vring.desc[head].len);
-
- BUG_ON(!(vq->vring.desc[head].flags &
- cpu_to_virtio16(vq->vq.vdev, VRING_DESC_F_INDIRECT)));
- BUG_ON(len == 0 || len % sizeof(struct vring_desc));
-
- for (j = 0; j < len / sizeof(struct vring_desc); j++)
- vring_unmap_one(vq, &indir_desc[j]);
-
- kfree(indir_desc);
- vq->desc_state[head].indir_desc = NULL;
- } else if (ctx) {
- *ctx = vq->desc_state[head].indir_desc;
- }
-}
-
-static inline bool more_used(const struct vring_virtqueue *vq)
-{
- return vq->last_used_idx != virtio16_to_cpu(vq->vq.vdev, vq->vring.used->idx);
-}
-
/**
* virtqueue_get_buf - get the next used buffer
- * @vq: the struct virtqueue we're talking about.
+ * @_vq: the struct virtqueue we're talking about.
* @len: the length written into the buffer
+ * @ctx: extra context for the token
*
* If the device wrote data into the buffer, @len will be set to the
* amount written. This means you don't need to clear the buffer
@@ -699,57 +1895,9 @@
void **ctx)
{
struct vring_virtqueue *vq = to_vvq(_vq);
- void *ret;
- unsigned int i;
- u16 last_used;
- START_USE(vq);
-
- if (unlikely(vq->broken)) {
- END_USE(vq);
- return NULL;
- }
-
- if (!more_used(vq)) {
- pr_debug("No more buffers in queue\n");
- END_USE(vq);
- return NULL;
- }
-
- /* Only get used array entries after they have been exposed by host. */
- virtio_rmb(vq->weak_barriers);
-
- last_used = (vq->last_used_idx & (vq->vring.num - 1));
- i = virtio32_to_cpu(_vq->vdev, vq->vring.used->ring[last_used].id);
- *len = virtio32_to_cpu(_vq->vdev, vq->vring.used->ring[last_used].len);
-
- if (unlikely(i >= vq->vring.num)) {
- BAD_RING(vq, "id %u out of range\n", i);
- return NULL;
- }
- if (unlikely(!vq->desc_state[i].data)) {
- BAD_RING(vq, "id %u is not a head!\n", i);
- return NULL;
- }
-
- /* detach_buf clears data, so grab it now. */
- ret = vq->desc_state[i].data;
- detach_buf(vq, i, ctx);
- vq->last_used_idx++;
- /* If we expect an interrupt for the next entry, tell host
- * by writing event index and flush out the write before
- * the read in the next get_buf call. */
- if (!(vq->avail_flags_shadow & VRING_AVAIL_F_NO_INTERRUPT))
- virtio_store_mb(vq->weak_barriers,
- &vring_used_event(&vq->vring),
- cpu_to_virtio16(_vq->vdev, vq->last_used_idx));
-
-#ifdef DEBUG
- vq->last_add_time_valid = false;
-#endif
-
- END_USE(vq);
- return ret;
+ return vq->packed_ring ? virtqueue_get_buf_ctx_packed(_vq, len, ctx) :
+ virtqueue_get_buf_ctx_split(_vq, len, ctx);
}
EXPORT_SYMBOL_GPL(virtqueue_get_buf_ctx);
@@ -760,7 +1908,7 @@
EXPORT_SYMBOL_GPL(virtqueue_get_buf);
/**
* virtqueue_disable_cb - disable callbacks
- * @vq: the struct virtqueue we're talking about.
+ * @_vq: the struct virtqueue we're talking about.
*
* Note that this is not necessarily synchronous, hence unreliable and only
* useful as an optimization.
@@ -771,18 +1919,16 @@
{
struct vring_virtqueue *vq = to_vvq(_vq);
- if (!(vq->avail_flags_shadow & VRING_AVAIL_F_NO_INTERRUPT)) {
- vq->avail_flags_shadow |= VRING_AVAIL_F_NO_INTERRUPT;
- if (!vq->event)
- vq->vring.avail->flags = cpu_to_virtio16(_vq->vdev, vq->avail_flags_shadow);
- }
-
+ if (vq->packed_ring)
+ virtqueue_disable_cb_packed(_vq);
+ else
+ virtqueue_disable_cb_split(_vq);
}
EXPORT_SYMBOL_GPL(virtqueue_disable_cb);
/**
* virtqueue_enable_cb_prepare - restart callbacks after disable_cb
- * @vq: the struct virtqueue we're talking about.
+ * @_vq: the struct virtqueue we're talking about.
*
* This re-enables callbacks; it returns current queue state
* in an opaque unsigned value. This value should be later tested by
@@ -795,29 +1941,15 @@
unsigned virtqueue_enable_cb_prepare(struct virtqueue *_vq)
{
struct vring_virtqueue *vq = to_vvq(_vq);
- u16 last_used_idx;
- START_USE(vq);
-
- /* We optimistically turn back on interrupts, then check if there was
- * more to do. */
- /* Depending on the VIRTIO_RING_F_EVENT_IDX feature, we need to
- * either clear the flags bit or point the event index at the next
- * entry. Always do both to keep code simple. */
- if (vq->avail_flags_shadow & VRING_AVAIL_F_NO_INTERRUPT) {
- vq->avail_flags_shadow &= ~VRING_AVAIL_F_NO_INTERRUPT;
- if (!vq->event)
- vq->vring.avail->flags = cpu_to_virtio16(_vq->vdev, vq->avail_flags_shadow);
- }
- vring_used_event(&vq->vring) = cpu_to_virtio16(_vq->vdev, last_used_idx = vq->last_used_idx);
- END_USE(vq);
- return last_used_idx;
+ return vq->packed_ring ? virtqueue_enable_cb_prepare_packed(_vq) :
+ virtqueue_enable_cb_prepare_split(_vq);
}
EXPORT_SYMBOL_GPL(virtqueue_enable_cb_prepare);
/**
* virtqueue_poll - query pending used buffers
- * @vq: the struct virtqueue we're talking about.
+ * @_vq: the struct virtqueue we're talking about.
* @last_used_idx: virtqueue state (from call to virtqueue_enable_cb_prepare).
*
* Returns "true" if there are pending used buffers in the queue.
@@ -829,13 +1961,14 @@
struct vring_virtqueue *vq = to_vvq(_vq);
virtio_mb(vq->weak_barriers);
- return (u16)last_used_idx != virtio16_to_cpu(_vq->vdev, vq->vring.used->idx);
+ return vq->packed_ring ? virtqueue_poll_packed(_vq, last_used_idx) :
+ virtqueue_poll_split(_vq, last_used_idx);
}
EXPORT_SYMBOL_GPL(virtqueue_poll);
/**
* virtqueue_enable_cb - restart callbacks after disable_cb.
- * @vq: the struct virtqueue we're talking about.
+ * @_vq: the struct virtqueue we're talking about.
*
* This re-enables callbacks; it returns "false" if there are pending
* buffers in the queue, to detect a possible race between the driver
@@ -847,13 +1980,14 @@
bool virtqueue_enable_cb(struct virtqueue *_vq)
{
unsigned last_used_idx = virtqueue_enable_cb_prepare(_vq);
+
return !virtqueue_poll(_vq, last_used_idx);
}
EXPORT_SYMBOL_GPL(virtqueue_enable_cb);
/**
* virtqueue_enable_cb_delayed - restart callbacks after disable_cb.
- * @vq: the struct virtqueue we're talking about.
+ * @_vq: the struct virtqueue we're talking about.
*
* This re-enables callbacks but hints to the other side to delay
* interrupts until most of the available buffers have been processed;
@@ -867,40 +2001,15 @@
bool virtqueue_enable_cb_delayed(struct virtqueue *_vq)
{
struct vring_virtqueue *vq = to_vvq(_vq);
- u16 bufs;
- START_USE(vq);
-
- /* We optimistically turn back on interrupts, then check if there was
- * more to do. */
- /* Depending on the VIRTIO_RING_F_USED_EVENT_IDX feature, we need to
- * either clear the flags bit or point the event index at the next
- * entry. Always update the event index to keep code simple. */
- if (vq->avail_flags_shadow & VRING_AVAIL_F_NO_INTERRUPT) {
- vq->avail_flags_shadow &= ~VRING_AVAIL_F_NO_INTERRUPT;
- if (!vq->event)
- vq->vring.avail->flags = cpu_to_virtio16(_vq->vdev, vq->avail_flags_shadow);
- }
- /* TODO: tune this threshold */
- bufs = (u16)(vq->avail_idx_shadow - vq->last_used_idx) * 3 / 4;
-
- virtio_store_mb(vq->weak_barriers,
- &vring_used_event(&vq->vring),
- cpu_to_virtio16(_vq->vdev, vq->last_used_idx + bufs));
-
- if (unlikely((u16)(virtio16_to_cpu(_vq->vdev, vq->vring.used->idx) - vq->last_used_idx) > bufs)) {
- END_USE(vq);
- return false;
- }
-
- END_USE(vq);
- return true;
+ return vq->packed_ring ? virtqueue_enable_cb_delayed_packed(_vq) :
+ virtqueue_enable_cb_delayed_split(_vq);
}
EXPORT_SYMBOL_GPL(virtqueue_enable_cb_delayed);
/**
* virtqueue_detach_unused_buf - detach first unused buffer
- * @vq: the struct virtqueue we're talking about.
+ * @_vq: the struct virtqueue we're talking about.
*
* Returns NULL or the "data" token handed to virtqueue_add_*().
* This is not valid on an active queue; it is useful only for device
@@ -909,30 +2018,17 @@
void *virtqueue_detach_unused_buf(struct virtqueue *_vq)
{
struct vring_virtqueue *vq = to_vvq(_vq);
- unsigned int i;
- void *buf;
- START_USE(vq);
-
- for (i = 0; i < vq->vring.num; i++) {
- if (!vq->desc_state[i].data)
- continue;
- /* detach_buf clears data, so grab it now. */
- buf = vq->desc_state[i].data;
- detach_buf(vq, i, NULL);
- vq->avail_idx_shadow--;
- vq->vring.avail->idx = cpu_to_virtio16(_vq->vdev, vq->avail_idx_shadow);
- END_USE(vq);
- return buf;
- }
- /* That should have freed everything. */
- BUG_ON(vq->vq.num_free != vq->vring.num);
-
- END_USE(vq);
- return NULL;
+ return vq->packed_ring ? virtqueue_detach_unused_buf_packed(_vq) :
+ virtqueue_detach_unused_buf_split(_vq);
}
EXPORT_SYMBOL_GPL(virtqueue_detach_unused_buf);
+static inline bool more_used(const struct vring_virtqueue *vq)
+{
+ return vq->packed_ring ? more_used_packed(vq) : more_used_split(vq);
+}
+
irqreturn_t vring_interrupt(int irq, void *_vq)
{
struct vring_virtqueue *vq = to_vvq(_vq);
@@ -953,6 +2049,7 @@
}
EXPORT_SYMBOL_GPL(vring_interrupt);
+/* Only available for split ring */
struct virtqueue *__vring_new_virtqueue(unsigned int index,
struct vring vring,
struct virtio_device *vdev,
@@ -965,27 +2062,26 @@
unsigned int i;
struct vring_virtqueue *vq;
- vq = kmalloc(sizeof(*vq) + vring.num * sizeof(struct vring_desc_state),
- GFP_KERNEL);
+ if (virtio_has_feature(vdev, VIRTIO_F_RING_PACKED))
+ return NULL;
+
+ vq = kmalloc(sizeof(*vq), GFP_KERNEL);
if (!vq)
return NULL;
- vq->vring = vring;
+ vq->packed_ring = false;
vq->vq.callback = callback;
vq->vq.vdev = vdev;
vq->vq.name = name;
vq->vq.num_free = vring.num;
vq->vq.index = index;
vq->we_own_ring = false;
- vq->queue_dma_addr = 0;
- vq->queue_size_in_bytes = 0;
vq->notify = notify;
vq->weak_barriers = weak_barriers;
vq->broken = false;
vq->last_used_idx = 0;
- vq->avail_flags_shadow = 0;
- vq->avail_idx_shadow = 0;
vq->num_added = 0;
+ vq->use_dma_api = vring_use_dma_api(vdev);
list_add_tail(&vq->vq.list, &vdev->vqs);
#ifdef DEBUG
vq->in_use = false;
@@ -996,65 +2092,42 @@
!context;
vq->event = virtio_has_feature(vdev, VIRTIO_RING_F_EVENT_IDX);
+ if (virtio_has_feature(vdev, VIRTIO_F_ORDER_PLATFORM))
+ vq->weak_barriers = false;
+
+ vq->split.queue_dma_addr = 0;
+ vq->split.queue_size_in_bytes = 0;
+
+ vq->split.vring = vring;
+ vq->split.avail_flags_shadow = 0;
+ vq->split.avail_idx_shadow = 0;
+
/* No callback? Tell other side not to bother us. */
if (!callback) {
- vq->avail_flags_shadow |= VRING_AVAIL_F_NO_INTERRUPT;
+ vq->split.avail_flags_shadow |= VRING_AVAIL_F_NO_INTERRUPT;
if (!vq->event)
- vq->vring.avail->flags = cpu_to_virtio16(vdev, vq->avail_flags_shadow);
+ vq->split.vring.avail->flags = cpu_to_virtio16(vdev,
+ vq->split.avail_flags_shadow);
+ }
+
+ vq->split.desc_state = kmalloc_array(vring.num,
+ sizeof(struct vring_desc_state_split), GFP_KERNEL);
+ if (!vq->split.desc_state) {
+ kfree(vq);
+ return NULL;
}
/* Put everything in free lists. */
vq->free_head = 0;
for (i = 0; i < vring.num-1; i++)
- vq->vring.desc[i].next = cpu_to_virtio16(vdev, i + 1);
- memset(vq->desc_state, 0, vring.num * sizeof(struct vring_desc_state));
+ vq->split.vring.desc[i].next = cpu_to_virtio16(vdev, i + 1);
+ memset(vq->split.desc_state, 0, vring.num *
+ sizeof(struct vring_desc_state_split));
return &vq->vq;
}
EXPORT_SYMBOL_GPL(__vring_new_virtqueue);
-static void *vring_alloc_queue(struct virtio_device *vdev, size_t size,
- dma_addr_t *dma_handle, gfp_t flag)
-{
- if (vring_use_dma_api(vdev)) {
- return dma_alloc_coherent(vdev->dev.parent, size,
- dma_handle, flag);
- } else {
- void *queue = alloc_pages_exact(PAGE_ALIGN(size), flag);
- if (queue) {
- phys_addr_t phys_addr = virt_to_phys(queue);
- *dma_handle = (dma_addr_t)phys_addr;
-
- /*
- * Sanity check: make sure we dind't truncate
- * the address. The only arches I can find that
- * have 64-bit phys_addr_t but 32-bit dma_addr_t
- * are certain non-highmem MIPS and x86
- * configurations, but these configurations
- * should never allocate physical pages above 32
- * bits, so this is fine. Just in case, throw a
- * warning and abort if we end up with an
- * unrepresentable address.
- */
- if (WARN_ON_ONCE(*dma_handle != phys_addr)) {
- free_pages_exact(queue, PAGE_ALIGN(size));
- return NULL;
- }
- }
- return queue;
- }
-}
-
-static void vring_free_queue(struct virtio_device *vdev, size_t size,
- void *queue, dma_addr_t dma_handle)
-{
- if (vring_use_dma_api(vdev)) {
- dma_free_coherent(vdev->dev.parent, size, queue, dma_handle);
- } else {
- free_pages_exact(queue, PAGE_ALIGN(size));
- }
-}
-
struct virtqueue *vring_create_virtqueue(
unsigned int index,
unsigned int num,
@@ -1067,57 +2140,19 @@
void (*callback)(struct virtqueue *),
const char *name)
{
- struct virtqueue *vq;
- void *queue = NULL;
- dma_addr_t dma_addr;
- size_t queue_size_in_bytes;
- struct vring vring;
- /* We assume num is a power of 2. */
- if (num & (num - 1)) {
- dev_warn(&vdev->dev, "Bad virtqueue length %u\n", num);
- return NULL;
- }
+ if (virtio_has_feature(vdev, VIRTIO_F_RING_PACKED))
+ return vring_create_virtqueue_packed(index, num, vring_align,
+ vdev, weak_barriers, may_reduce_num,
+ context, notify, callback, name);
- /* TODO: allocate each queue chunk individually */
- for (; num && vring_size(num, vring_align) > PAGE_SIZE; num /= 2) {
- queue = vring_alloc_queue(vdev, vring_size(num, vring_align),
- &dma_addr,
- GFP_KERNEL|__GFP_NOWARN|__GFP_ZERO);
- if (queue)
- break;
- }
-
- if (!num)
- return NULL;
-
- if (!queue) {
- /* Try to get a single page. You are my only hope! */
- queue = vring_alloc_queue(vdev, vring_size(num, vring_align),
- &dma_addr, GFP_KERNEL|__GFP_ZERO);
- }
- if (!queue)
- return NULL;
-
- queue_size_in_bytes = vring_size(num, vring_align);
- vring_init(&vring, num, queue, vring_align);
-
- vq = __vring_new_virtqueue(index, vring, vdev, weak_barriers, context,
- notify, callback, name);
- if (!vq) {
- vring_free_queue(vdev, queue_size_in_bytes, queue,
- dma_addr);
- return NULL;
- }
-
- to_vvq(vq)->queue_dma_addr = dma_addr;
- to_vvq(vq)->queue_size_in_bytes = queue_size_in_bytes;
- to_vvq(vq)->we_own_ring = true;
-
- return vq;
+ return vring_create_virtqueue_split(index, num, vring_align,
+ vdev, weak_barriers, may_reduce_num,
+ context, notify, callback, name);
}
EXPORT_SYMBOL_GPL(vring_create_virtqueue);
+/* Only available for split ring */
struct virtqueue *vring_new_virtqueue(unsigned int index,
unsigned int num,
unsigned int vring_align,
@@ -1130,6 +2165,10 @@
const char *name)
{
struct vring vring;
+
+ if (virtio_has_feature(vdev, VIRTIO_F_RING_PACKED))
+ return NULL;
+
vring_init(&vring, num, pages, vring_align);
return __vring_new_virtqueue(index, vring, vdev, weak_barriers, context,
notify, callback, name);
@@ -1141,8 +2180,32 @@
struct vring_virtqueue *vq = to_vvq(_vq);
if (vq->we_own_ring) {
- vring_free_queue(vq->vq.vdev, vq->queue_size_in_bytes,
- vq->vring.desc, vq->queue_dma_addr);
+ if (vq->packed_ring) {
+ vring_free_queue(vq->vq.vdev,
+ vq->packed.ring_size_in_bytes,
+ vq->packed.vring.desc,
+ vq->packed.ring_dma_addr);
+
+ vring_free_queue(vq->vq.vdev,
+ vq->packed.event_size_in_bytes,
+ vq->packed.vring.driver,
+ vq->packed.driver_event_dma_addr);
+
+ vring_free_queue(vq->vq.vdev,
+ vq->packed.event_size_in_bytes,
+ vq->packed.vring.device,
+ vq->packed.device_event_dma_addr);
+
+ kfree(vq->packed.desc_state);
+ kfree(vq->packed.desc_extra);
+ } else {
+ vring_free_queue(vq->vq.vdev,
+ vq->split.queue_size_in_bytes,
+ vq->split.vring.desc,
+ vq->split.queue_dma_addr);
+
+ kfree(vq->split.desc_state);
+ }
}
list_del(&_vq->list);
kfree(vq);
@@ -1164,6 +2227,10 @@
break;
case VIRTIO_F_IOMMU_PLATFORM:
break;
+ case VIRTIO_F_RING_PACKED:
+ break;
+ case VIRTIO_F_ORDER_PLATFORM:
+ break;
default:
/* We don't understand this bit. */
__virtio_clear_bit(vdev, i);
@@ -1174,7 +2241,7 @@
/**
* virtqueue_get_vring_size - return the size of the virtqueue's vring
- * @vq: the struct virtqueue containing the vring of interest.
+ * @_vq: the struct virtqueue containing the vring of interest.
*
* Returns the size of the vring. This is mainly used for boasting to
* userspace. Unlike other operations, this need not be serialized.
@@ -1184,7 +2251,7 @@
struct vring_virtqueue *vq = to_vvq(_vq);
- return vq->vring.num;
+ return vq->packed_ring ? vq->packed.vring.num : vq->split.vring.num;
}
EXPORT_SYMBOL_GPL(virtqueue_get_vring_size);
@@ -1217,7 +2284,10 @@
BUG_ON(!vq->we_own_ring);
- return vq->queue_dma_addr;
+ if (vq->packed_ring)
+ return vq->packed.ring_dma_addr;
+
+ return vq->split.queue_dma_addr;
}
EXPORT_SYMBOL_GPL(virtqueue_get_desc_addr);
@@ -1227,8 +2297,11 @@
BUG_ON(!vq->we_own_ring);
- return vq->queue_dma_addr +
- ((char *)vq->vring.avail - (char *)vq->vring.desc);
+ if (vq->packed_ring)
+ return vq->packed.driver_event_dma_addr;
+
+ return vq->split.queue_dma_addr +
+ ((char *)vq->split.vring.avail - (char *)vq->split.vring.desc);
}
EXPORT_SYMBOL_GPL(virtqueue_get_avail_addr);
@@ -1238,14 +2311,18 @@
BUG_ON(!vq->we_own_ring);
- return vq->queue_dma_addr +
- ((char *)vq->vring.used - (char *)vq->vring.desc);
+ if (vq->packed_ring)
+ return vq->packed.device_event_dma_addr;
+
+ return vq->split.queue_dma_addr +
+ ((char *)vq->split.vring.used - (char *)vq->split.vring.desc);
}
EXPORT_SYMBOL_GPL(virtqueue_get_used_addr);
+/* Only available for split ring */
const struct vring *virtqueue_get_vring(struct virtqueue *vq)
{
- return &to_vvq(vq)->vring;
+ return &to_vvq(vq)->split.vring;
}
EXPORT_SYMBOL_GPL(virtqueue_get_vring);