Update Linux to v5.10.109
Sourced from [1]
[1] https://cdn.kernel.org/pub/linux/kernel/v5.x/linux-5.10.109.tar.xz
Change-Id: I19bca9fc6762d4e63bcf3e4cba88bbe560d9c76c
Signed-off-by: Olivier Deprez <olivier.deprez@arm.com>
diff --git a/drivers/virtio/Kconfig b/drivers/virtio/Kconfig
index 078615c..7b41130 100644
--- a/drivers/virtio/Kconfig
+++ b/drivers/virtio/Kconfig
@@ -1,11 +1,17 @@
# SPDX-License-Identifier: GPL-2.0-only
config VIRTIO
tristate
- ---help---
+ help
This option is selected by any driver which implements the virtio
bus, such as CONFIG_VIRTIO_PCI, CONFIG_VIRTIO_MMIO, CONFIG_RPMSG
or CONFIG_S390_GUEST.
+config ARCH_HAS_RESTRICTED_VIRTIO_MEMORY_ACCESS
+ bool
+ help
+ This option is selected if the architecture may need to enforce
+ VIRTIO_F_ACCESS_PLATFORM
+
menuconfig VIRTIO_MENU
bool "Virtio drivers"
default y
@@ -16,7 +22,7 @@
tristate "PCI driver for virtio devices"
depends on PCI
select VIRTIO
- ---help---
+ help
This driver provides support for virtio based paravirtual device
drivers over PCI. This requires that your VMM has appropriate PCI
virtio backends. Most QEMU based VMMs should support these devices
@@ -28,7 +34,7 @@
bool "Support for legacy virtio draft 0.9.X and older devices"
default y
depends on VIRTIO_PCI
- ---help---
+ help
Virtio PCI Card 0.9.X Draft (circa 2014) and older device support.
This option enables building a transitional driver, supporting
@@ -43,6 +49,19 @@
If unsure, say Y.
+config VIRTIO_VDPA
+ tristate "vDPA driver for virtio devices"
+ depends on VDPA
+ select VIRTIO
+ help
+ This driver provides support for virtio based paravirtual
+ device driver over vDPA bus. For this to be useful, you need
+ an appropriate vDPA device implementation that operates on a
+ physical device to allow the datapath of virtio to be
+ offloaded to hardware.
+
+ If unsure, say M.
+
config VIRTIO_PMEM
tristate "Support for virtio pmem driver"
depends on VIRTIO
@@ -58,17 +77,35 @@
tristate "Virtio balloon driver"
depends on VIRTIO
select MEMORY_BALLOON
- ---help---
+ select PAGE_REPORTING
+ help
This driver supports increasing and decreasing the amount
of memory within a KVM guest.
If unsure, say M.
+config VIRTIO_MEM
+ tristate "Virtio mem driver"
+ default m
+ depends on X86_64
+ depends on VIRTIO
+ depends on MEMORY_HOTPLUG_SPARSE
+ depends on MEMORY_HOTREMOVE
+ depends on CONTIG_ALLOC
+ help
+ This driver provides access to virtio-mem paravirtualized memory
+ devices, allowing to hotplug and hotunplug memory.
+
+ This driver was only tested under x86-64, but should theoretically
+ work on all architectures that support memory hotplug and hotremove.
+
+ If unsure, say M.
+
config VIRTIO_INPUT
tristate "Virtio input driver"
depends on VIRTIO
depends on INPUT
- ---help---
+ help
This driver supports virtio input devices such as
keyboards, mice and tablets.
@@ -78,7 +115,7 @@
tristate "Platform bus driver for memory mapped virtio devices"
depends on HAS_IOMEM && HAS_DMA
select VIRTIO
- ---help---
+ help
This drivers provides support for memory mapped virtio
platform device driver.
@@ -87,7 +124,7 @@
config VIRTIO_MMIO_CMDLINE_DEVICES
bool "Memory mapped virtio devices parameter parsing"
depends on VIRTIO_MMIO
- ---help---
+ help
Allow virtio-mmio devices instantiation via the kernel command line
or module parameters. Be aware that using incorrect parameters (base
address in particular) can crash your system - you have been warned.
@@ -95,4 +132,11 @@
If unsure, say 'N'.
+config VIRTIO_DMA_SHARED_BUFFER
+ tristate
+ depends on DMA_SHARED_BUFFER
+ help
+ This option adds a flavor of dma buffers that are backed by
+ virtio resources.
+
endif # VIRTIO_MENU
diff --git a/drivers/virtio/Makefile b/drivers/virtio/Makefile
index 3a2b5c5..591e6f7 100644
--- a/drivers/virtio/Makefile
+++ b/drivers/virtio/Makefile
@@ -6,3 +6,6 @@
virtio_pci-$(CONFIG_VIRTIO_PCI_LEGACY) += virtio_pci_legacy.o
obj-$(CONFIG_VIRTIO_BALLOON) += virtio_balloon.o
obj-$(CONFIG_VIRTIO_INPUT) += virtio_input.o
+obj-$(CONFIG_VIRTIO_VDPA) += virtio_vdpa.o
+obj-$(CONFIG_VIRTIO_MEM) += virtio_mem.o
+obj-$(CONFIG_VIRTIO_DMA_SHARED_BUFFER) += virtio_dma_buf.o
diff --git a/drivers/virtio/virtio.c b/drivers/virtio/virtio.c
index 59a05f1..441bc05 100644
--- a/drivers/virtio/virtio.c
+++ b/drivers/virtio/virtio.c
@@ -167,14 +167,28 @@
}
EXPORT_SYMBOL_GPL(virtio_add_status);
-int virtio_finalize_features(struct virtio_device *dev)
+/* Do some validation, then set FEATURES_OK */
+static int virtio_features_ok(struct virtio_device *dev)
{
- int ret = dev->config->finalize_features(dev);
unsigned status;
+ int ret;
might_sleep();
- if (ret)
- return ret;
+
+ ret = arch_has_restricted_virtio_memory_access();
+ if (ret) {
+ if (!virtio_has_feature(dev, VIRTIO_F_VERSION_1)) {
+ dev_warn(&dev->dev,
+ "device must provide VIRTIO_F_VERSION_1\n");
+ return -ENODEV;
+ }
+
+ if (!virtio_has_feature(dev, VIRTIO_F_ACCESS_PLATFORM)) {
+ dev_warn(&dev->dev,
+ "device must provide VIRTIO_F_ACCESS_PLATFORM\n");
+ return -ENODEV;
+ }
+ }
if (!virtio_has_feature(dev, VIRTIO_F_VERSION_1))
return 0;
@@ -188,7 +202,6 @@
}
return 0;
}
-EXPORT_SYMBOL_GPL(virtio_finalize_features);
static int virtio_dev_probe(struct device *_d)
{
@@ -235,13 +248,26 @@
if (device_features & (1ULL << i))
__virtio_set_bit(dev, i);
+ err = dev->config->finalize_features(dev);
+ if (err)
+ goto err;
+
if (drv->validate) {
+ u64 features = dev->features;
+
err = drv->validate(dev);
if (err)
goto err;
+
+ /* Did validation change any features? Then write them again. */
+ if (features != dev->features) {
+ err = dev->config->finalize_features(dev);
+ if (err)
+ goto err;
+ }
}
- err = virtio_finalize_features(dev);
+ err = virtio_features_ok(dev);
if (err)
goto err;
@@ -358,6 +384,12 @@
}
EXPORT_SYMBOL_GPL(register_virtio_device);
+bool is_virtio_device(struct device *dev)
+{
+ return dev->bus == &virtio_bus;
+}
+EXPORT_SYMBOL_GPL(is_virtio_device);
+
void unregister_virtio_device(struct virtio_device *dev)
{
int index = dev->index; /* save for after device release */
@@ -406,7 +438,11 @@
/* We have a driver! */
virtio_add_status(dev, VIRTIO_CONFIG_S_DRIVER);
- ret = virtio_finalize_features(dev);
+ ret = dev->config->finalize_features(dev);
+ if (ret)
+ goto err;
+
+ ret = virtio_features_ok(dev);
if (ret)
goto err;
diff --git a/drivers/virtio/virtio_balloon.c b/drivers/virtio/virtio_balloon.c
index 1e44482..481611c 100644
--- a/drivers/virtio/virtio_balloon.c
+++ b/drivers/virtio/virtio_balloon.c
@@ -14,11 +14,13 @@
#include <linux/slab.h>
#include <linux/module.h>
#include <linux/balloon_compaction.h>
+#include <linux/oom.h>
#include <linux/wait.h>
#include <linux/mm.h>
#include <linux/mount.h>
#include <linux/magic.h>
#include <linux/pseudo_fs.h>
+#include <linux/page_reporting.h>
/*
* Balloon device works in 4K page units. So each page is pointed to by
@@ -27,15 +29,18 @@
*/
#define VIRTIO_BALLOON_PAGES_PER_PAGE (unsigned)(PAGE_SIZE >> VIRTIO_BALLOON_PFN_SHIFT)
#define VIRTIO_BALLOON_ARRAY_PFNS_MAX 256
-#define VIRTBALLOON_OOM_NOTIFY_PRIORITY 80
+/* Maximum number of (4k) pages to deflate on OOM notifications. */
+#define VIRTIO_BALLOON_OOM_NR_PAGES 256
+#define VIRTIO_BALLOON_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)
+#define VIRTIO_BALLOON_HINT_BLOCK_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))
+#define VIRTIO_BALLOON_HINT_BLOCK_BYTES \
+ (1 << (VIRTIO_BALLOON_HINT_BLOCK_ORDER + PAGE_SHIFT))
+#define VIRTIO_BALLOON_HINT_BLOCK_PAGES (1 << VIRTIO_BALLOON_HINT_BLOCK_ORDER)
#ifdef CONFIG_BALLOON_COMPACTION
static struct vfsmount *balloon_mnt;
@@ -46,6 +51,7 @@
VIRTIO_BALLOON_VQ_DEFLATE,
VIRTIO_BALLOON_VQ_STATS,
VIRTIO_BALLOON_VQ_FREE_PAGE,
+ VIRTIO_BALLOON_VQ_REPORTING,
VIRTIO_BALLOON_VQ_MAX
};
@@ -111,11 +117,18 @@
/* Memory statistics */
struct virtio_balloon_stat stats[VIRTIO_BALLOON_S_NR];
- /* To register a shrinker to shrink memory upon memory pressure */
+ /* Shrinker to return free pages - VIRTIO_BALLOON_F_FREE_PAGE_HINT */
struct shrinker shrinker;
+
+ /* OOM notifier to deflate on OOM - VIRTIO_BALLOON_F_DEFLATE_ON_OOM */
+ struct notifier_block oom_nb;
+
+ /* Free page reporting device */
+ struct virtqueue *reporting_vq;
+ struct page_reporting_dev_info pr_dev_info;
};
-static struct virtio_device_id id_table[] = {
+static const struct virtio_device_id id_table[] = {
{ VIRTIO_ID_BALLOON, VIRTIO_DEV_ANY_ID },
{ 0 },
};
@@ -152,6 +165,33 @@
}
+static int virtballoon_free_page_report(struct page_reporting_dev_info *pr_dev_info,
+ struct scatterlist *sg, unsigned int nents)
+{
+ struct virtio_balloon *vb =
+ container_of(pr_dev_info, struct virtio_balloon, pr_dev_info);
+ struct virtqueue *vq = vb->reporting_vq;
+ unsigned int unused, err;
+
+ /* We should always be able to add these buffers to an empty queue. */
+ err = virtqueue_add_inbuf(vq, sg, nents, vb, GFP_NOWAIT | __GFP_NOWARN);
+
+ /*
+ * In the extremely unlikely case that something has occurred and we
+ * are able to trigger an error we will simply display a warning
+ * and exit without actually processing the pages.
+ */
+ if (WARN_ON_ONCE(err))
+ return err;
+
+ virtqueue_kick(vq);
+
+ /* When host has read buffer, this completes via balloon_ack */
+ wait_event(vb->acked, virtqueue_get_buf(vq, &unused));
+
+ return 0;
+}
+
static void set_page_pfns(struct virtio_balloon *vb,
__virtio32 pfns[], struct page *page)
{
@@ -358,12 +398,9 @@
s64 target;
u32 num_pages;
- virtio_cread(vb->vdev, struct virtio_balloon_config, num_pages,
- &num_pages);
-
/* Legacy balloon config space is LE, unlike all other devices. */
- if (!virtio_has_feature(vb->vdev, VIRTIO_F_VERSION_1))
- num_pages = le32_to_cpu((__force __le32)num_pages);
+ virtio_cread_le(vb->vdev, struct virtio_balloon_config, num_pages,
+ &num_pages);
target = num_pages;
return target - vb->num_pages;
@@ -382,7 +419,7 @@
if (!page)
break;
free_pages((unsigned long)page_address(page),
- VIRTIO_BALLOON_FREE_PAGE_ORDER);
+ VIRTIO_BALLOON_HINT_BLOCK_ORDER);
}
vb->num_free_page_blocks -= num_returned;
spin_unlock_irq(&vb->free_page_list_lock);
@@ -422,11 +459,8 @@
u32 actual = vb->num_pages;
/* Legacy balloon config space is LE, unlike all other devices. */
- if (!virtio_has_feature(vb->vdev, VIRTIO_F_VERSION_1))
- actual = (__force u32)cpu_to_le32(actual);
-
- virtio_cwrite(vb->vdev, struct virtio_balloon_config, actual,
- &actual);
+ virtio_cwrite_le(vb->vdev, struct virtio_balloon_config, actual,
+ &actual);
}
static void update_balloon_stats_func(struct work_struct *work)
@@ -480,6 +514,7 @@
names[VIRTIO_BALLOON_VQ_STATS] = NULL;
callbacks[VIRTIO_BALLOON_VQ_FREE_PAGE] = NULL;
names[VIRTIO_BALLOON_VQ_FREE_PAGE] = NULL;
+ names[VIRTIO_BALLOON_VQ_REPORTING] = NULL;
if (virtio_has_feature(vb->vdev, VIRTIO_BALLOON_F_STATS_VQ)) {
names[VIRTIO_BALLOON_VQ_STATS] = "stats";
@@ -491,6 +526,11 @@
callbacks[VIRTIO_BALLOON_VQ_FREE_PAGE] = NULL;
}
+ if (virtio_has_feature(vb->vdev, VIRTIO_BALLOON_F_REPORTING)) {
+ names[VIRTIO_BALLOON_VQ_REPORTING] = "reporting_vq";
+ callbacks[VIRTIO_BALLOON_VQ_REPORTING] = balloon_ack;
+ }
+
err = vb->vdev->config->find_vqs(vb->vdev, VIRTIO_BALLOON_VQ_MAX,
vqs, callbacks, names, NULL, NULL);
if (err)
@@ -523,6 +563,9 @@
if (virtio_has_feature(vb->vdev, VIRTIO_BALLOON_F_FREE_PAGE_HINT))
vb->free_page_vq = vqs[VIRTIO_BALLOON_VQ_FREE_PAGE];
+ if (virtio_has_feature(vb->vdev, VIRTIO_BALLOON_F_REPORTING))
+ vb->reporting_vq = vqs[VIRTIO_BALLOON_VQ_REPORTING];
+
return 0;
}
@@ -530,12 +573,10 @@
{
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);
/* Legacy balloon config space is LE, unlike all other devices. */
- if (!virtio_has_feature(vb->vdev, VIRTIO_F_VERSION_1))
- vb->cmd_id_received_cache = le32_to_cpu((__force __le32)vb->cmd_id_received_cache);
+ virtio_cread_le(vb->vdev, struct virtio_balloon_config,
+ free_page_hint_cmd_id,
+ &vb->cmd_id_received_cache);
}
return vb->cmd_id_received_cache;
@@ -551,7 +592,7 @@
while (virtqueue_get_buf(vq, &unused))
;
- vb->cmd_id_active = virtio32_to_cpu(vb->vdev,
+ vb->cmd_id_active = cpu_to_virtio32(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);
@@ -590,7 +631,7 @@
;
page = alloc_pages(VIRTIO_BALLOON_FREE_PAGE_ALLOC_FLAG,
- VIRTIO_BALLOON_FREE_PAGE_ORDER);
+ VIRTIO_BALLOON_HINT_BLOCK_ORDER);
/*
* When the allocation returns NULL, it indicates that we have got all
* the possible free pages, so return -EINTR to stop.
@@ -599,13 +640,13 @@
return -EINTR;
p = page_address(page);
- sg_init_one(&sg, p, VIRTIO_BALLOON_FREE_PAGE_SIZE);
+ sg_init_one(&sg, p, VIRTIO_BALLOON_HINT_BLOCK_BYTES);
/* 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);
+ VIRTIO_BALLOON_HINT_BLOCK_ORDER);
return err;
}
virtqueue_kick(vq);
@@ -618,7 +659,7 @@
* 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);
+ free_pages((unsigned long)p, VIRTIO_BALLOON_HINT_BLOCK_ORDER);
}
return 0;
@@ -784,57 +825,20 @@
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;
+ VIRTIO_BALLOON_HINT_BLOCK_PAGES);
+ blocks_to_free = pages_to_free / VIRTIO_BALLOON_HINT_BLOCK_PAGES;
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;
+ return blocks_freed * VIRTIO_BALLOON_HINT_BLOCK_PAGES;
}
static unsigned long virtio_balloon_shrinker_scan(struct shrinker *shrinker,
struct shrink_control *sc)
{
- unsigned long pages_to_free, pages_freed = 0;
struct virtio_balloon *vb = container_of(shrinker,
struct virtio_balloon, shrinker);
- pages_to_free = sc->nr_to_scan;
-
- if (virtio_has_feature(vb->vdev, VIRTIO_BALLOON_F_FREE_PAGE_HINT))
- pages_freed = shrink_free_pages(vb, pages_to_free);
-
- if (pages_freed >= pages_to_free)
- return pages_freed;
-
- pages_freed += shrink_balloon_pages(vb, pages_to_free - pages_freed);
-
- return pages_freed;
+ return shrink_free_pages(vb, sc->nr_to_scan);
}
static unsigned long virtio_balloon_shrinker_count(struct shrinker *shrinker,
@@ -842,12 +846,22 @@
{
struct virtio_balloon *vb = container_of(shrinker,
struct virtio_balloon, shrinker);
- unsigned long count;
- count = vb->num_pages / VIRTIO_BALLOON_PAGES_PER_PAGE;
- count += vb->num_free_page_blocks << VIRTIO_BALLOON_FREE_PAGE_ORDER;
+ return vb->num_free_page_blocks * VIRTIO_BALLOON_HINT_BLOCK_PAGES;
+}
- return count;
+static int virtio_balloon_oom_notify(struct notifier_block *nb,
+ unsigned long dummy, void *parm)
+{
+ struct virtio_balloon *vb = container_of(nb,
+ struct virtio_balloon, oom_nb);
+ unsigned long *freed = parm;
+
+ *freed += leak_balloon(vb, VIRTIO_BALLOON_OOM_NR_PAGES) /
+ VIRTIO_BALLOON_PAGES_PER_PAGE;
+ update_balloon_size(vb);
+
+ return NOTIFY_OK;
}
static void virtio_balloon_unregister_shrinker(struct virtio_balloon *vb)
@@ -867,7 +881,6 @@
static int virtballoon_probe(struct virtio_device *vdev)
{
struct virtio_balloon *vb;
- __u32 poison_val;
int err;
if (!vdev->config->get) {
@@ -933,27 +946,70 @@
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.
- */
- if (virtio_has_feature(vb->vdev, VIRTIO_BALLOON_F_DEFLATE_ON_OOM)) {
+ /*
+ * We're allowed to reuse any free pages, even if they are
+ * still to be processed by the host.
+ */
err = virtio_balloon_register_shrinker(vb);
if (err)
goto out_del_balloon_wq;
}
+
+ if (virtio_has_feature(vb->vdev, VIRTIO_BALLOON_F_DEFLATE_ON_OOM)) {
+ vb->oom_nb.notifier_call = virtio_balloon_oom_notify;
+ vb->oom_nb.priority = VIRTIO_BALLOON_OOM_NOTIFY_PRIORITY;
+ err = register_oom_notifier(&vb->oom_nb);
+ if (err < 0)
+ goto out_unregister_shrinker;
+ }
+
+ if (virtio_has_feature(vdev, VIRTIO_BALLOON_F_PAGE_POISON)) {
+ /* Start with poison val of 0 representing general init */
+ __u32 poison_val = 0;
+
+ /*
+ * Let the hypervisor know that we are expecting a
+ * specific value to be written back in balloon pages.
+ *
+ * If the PAGE_POISON value was larger than a byte we would
+ * need to byte swap poison_val here to guarantee it is
+ * little-endian. However for now it is a single byte so we
+ * can pass it as-is.
+ */
+ if (!want_init_on_free())
+ memset(&poison_val, PAGE_POISON, sizeof(poison_val));
+
+ virtio_cwrite_le(vb->vdev, struct virtio_balloon_config,
+ poison_val, &poison_val);
+ }
+
+ vb->pr_dev_info.report = virtballoon_free_page_report;
+ if (virtio_has_feature(vb->vdev, VIRTIO_BALLOON_F_REPORTING)) {
+ unsigned int capacity;
+
+ capacity = virtqueue_get_vring_size(vb->reporting_vq);
+ if (capacity < PAGE_REPORTING_CAPACITY) {
+ err = -ENOSPC;
+ goto out_unregister_oom;
+ }
+
+ err = page_reporting_register(&vb->pr_dev_info);
+ if (err)
+ goto out_unregister_oom;
+ }
+
virtio_device_ready(vdev);
if (towards_target(vb))
virtballoon_changed(vdev);
return 0;
+out_unregister_oom:
+ if (virtio_has_feature(vb->vdev, VIRTIO_BALLOON_F_DEFLATE_ON_OOM))
+ unregister_oom_notifier(&vb->oom_nb);
+out_unregister_shrinker:
+ if (virtio_has_feature(vb->vdev, VIRTIO_BALLOON_F_FREE_PAGE_HINT))
+ virtio_balloon_unregister_shrinker(vb);
out_del_balloon_wq:
if (virtio_has_feature(vdev, VIRTIO_BALLOON_F_FREE_PAGE_HINT))
destroy_workqueue(vb->balloon_wq);
@@ -992,7 +1048,11 @@
{
struct virtio_balloon *vb = vdev->priv;
+ if (virtio_has_feature(vb->vdev, VIRTIO_BALLOON_F_REPORTING))
+ page_reporting_unregister(&vb->pr_dev_info);
if (virtio_has_feature(vb->vdev, VIRTIO_BALLOON_F_DEFLATE_ON_OOM))
+ unregister_oom_notifier(&vb->oom_nb);
+ if (virtio_has_feature(vb->vdev, VIRTIO_BALLOON_F_FREE_PAGE_HINT))
virtio_balloon_unregister_shrinker(vb);
spin_lock_irq(&vb->stop_update_lock);
vb->stop_update = true;
@@ -1048,10 +1108,20 @@
static int virtballoon_validate(struct virtio_device *vdev)
{
- if (!page_poisoning_enabled())
+ /*
+ * Inform the hypervisor that our pages are poisoned or
+ * initialized. If we cannot do that then we should disable
+ * page reporting as it could potentially change the contents
+ * of our free pages.
+ */
+ if (!want_init_on_free() &&
+ (IS_ENABLED(CONFIG_PAGE_POISONING_NO_SANITY) ||
+ !page_poisoning_enabled()))
__virtio_clear_bit(vdev, VIRTIO_BALLOON_F_PAGE_POISON);
+ else if (!virtio_has_feature(vdev, VIRTIO_BALLOON_F_PAGE_POISON))
+ __virtio_clear_bit(vdev, VIRTIO_BALLOON_F_REPORTING);
- __virtio_clear_bit(vdev, VIRTIO_F_IOMMU_PLATFORM);
+ __virtio_clear_bit(vdev, VIRTIO_F_ACCESS_PLATFORM);
return 0;
}
@@ -1061,6 +1131,7 @@
VIRTIO_BALLOON_F_DEFLATE_ON_OOM,
VIRTIO_BALLOON_F_FREE_PAGE_HINT,
VIRTIO_BALLOON_F_PAGE_POISON,
+ VIRTIO_BALLOON_F_REPORTING,
};
static struct virtio_driver virtio_balloon_driver = {
diff --git a/drivers/virtio/virtio_dma_buf.c b/drivers/virtio/virtio_dma_buf.c
new file mode 100644
index 0000000..5127a2f
--- /dev/null
+++ b/drivers/virtio/virtio_dma_buf.c
@@ -0,0 +1,88 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * dma-bufs for virtio exported objects
+ *
+ * Copyright (C) 2020 Google, Inc.
+ */
+
+#include <linux/module.h>
+#include <linux/virtio_dma_buf.h>
+
+/**
+ * virtio_dma_buf_export - Creates a new dma-buf for a virtio exported object
+ * @exp_info: [in] see dma_buf_export(). ops MUST refer to a dma_buf_ops
+ * struct embedded in a virtio_dma_buf_ops.
+ *
+ * This wraps dma_buf_export() to allow virtio drivers to create a dma-buf
+ * for an virtio exported object that can be queried by other virtio drivers
+ * for the object's UUID.
+ */
+struct dma_buf *virtio_dma_buf_export
+ (const struct dma_buf_export_info *exp_info)
+{
+ const struct virtio_dma_buf_ops *virtio_ops =
+ container_of(exp_info->ops,
+ const struct virtio_dma_buf_ops, ops);
+
+ if (!exp_info->ops ||
+ exp_info->ops->attach != &virtio_dma_buf_attach ||
+ !virtio_ops->get_uuid) {
+ return ERR_PTR(-EINVAL);
+ }
+
+ return dma_buf_export(exp_info);
+}
+EXPORT_SYMBOL(virtio_dma_buf_export);
+
+/**
+ * virtio_dma_buf_attach - mandatory attach callback for virtio dma-bufs
+ */
+int virtio_dma_buf_attach(struct dma_buf *dma_buf,
+ struct dma_buf_attachment *attach)
+{
+ int ret;
+ const struct virtio_dma_buf_ops *ops =
+ container_of(dma_buf->ops,
+ const struct virtio_dma_buf_ops, ops);
+
+ if (ops->device_attach) {
+ ret = ops->device_attach(dma_buf, attach);
+ if (ret)
+ return ret;
+ }
+ return 0;
+}
+EXPORT_SYMBOL(virtio_dma_buf_attach);
+
+/**
+ * is_virtio_dma_buf - returns true if the given dma-buf is a virtio dma-buf
+ * @dma_buf: buffer to query
+ */
+bool is_virtio_dma_buf(struct dma_buf *dma_buf)
+{
+ return dma_buf->ops->attach == &virtio_dma_buf_attach;
+}
+EXPORT_SYMBOL(is_virtio_dma_buf);
+
+/**
+ * virtio_dma_buf_get_uuid - gets a virtio dma-buf's exported object's uuid
+ * @dma_buf: [in] buffer to query
+ * @uuid: [out] the uuid
+ *
+ * Returns: 0 on success, negative on failure.
+ */
+int virtio_dma_buf_get_uuid(struct dma_buf *dma_buf,
+ uuid_t *uuid)
+{
+ const struct virtio_dma_buf_ops *ops =
+ container_of(dma_buf->ops,
+ const struct virtio_dma_buf_ops, ops);
+
+ if (!is_virtio_dma_buf(dma_buf))
+ return -EINVAL;
+
+ return ops->get_uuid(dma_buf, uuid);
+}
+EXPORT_SYMBOL(virtio_dma_buf_get_uuid);
+
+MODULE_LICENSE("GPL");
diff --git a/drivers/virtio/virtio_input.c b/drivers/virtio/virtio_input.c
index 5ae5296..f1f6208 100644
--- a/drivers/virtio/virtio_input.c
+++ b/drivers/virtio/virtio_input.c
@@ -3,6 +3,7 @@
#include <linux/virtio.h>
#include <linux/virtio_config.h>
#include <linux/input.h>
+#include <linux/slab.h>
#include <uapi/linux/virtio_ids.h>
#include <uapi/linux/virtio_input.h>
@@ -112,9 +113,9 @@
{
u8 size;
- virtio_cwrite(vi->vdev, struct virtio_input_config, select, &select);
- virtio_cwrite(vi->vdev, struct virtio_input_config, subsel, &subsel);
- virtio_cread(vi->vdev, struct virtio_input_config, size, &size);
+ virtio_cwrite_le(vi->vdev, struct virtio_input_config, select, &select);
+ virtio_cwrite_le(vi->vdev, struct virtio_input_config, subsel, &subsel);
+ virtio_cread_le(vi->vdev, struct virtio_input_config, size, &size);
return size;
}
@@ -157,11 +158,11 @@
u32 mi, ma, re, fu, fl;
virtinput_cfg_select(vi, VIRTIO_INPUT_CFG_ABS_INFO, abs);
- virtio_cread(vi->vdev, struct virtio_input_config, u.abs.min, &mi);
- virtio_cread(vi->vdev, struct virtio_input_config, u.abs.max, &ma);
- virtio_cread(vi->vdev, struct virtio_input_config, u.abs.res, &re);
- virtio_cread(vi->vdev, struct virtio_input_config, u.abs.fuzz, &fu);
- virtio_cread(vi->vdev, struct virtio_input_config, u.abs.flat, &fl);
+ virtio_cread_le(vi->vdev, struct virtio_input_config, u.abs.min, &mi);
+ virtio_cread_le(vi->vdev, struct virtio_input_config, u.abs.max, &ma);
+ virtio_cread_le(vi->vdev, struct virtio_input_config, u.abs.res, &re);
+ virtio_cread_le(vi->vdev, struct virtio_input_config, u.abs.fuzz, &fu);
+ virtio_cread_le(vi->vdev, struct virtio_input_config, u.abs.flat, &fl);
input_set_abs_params(vi->idev, abs, mi, ma, fu, fl);
input_abs_set_res(vi->idev, abs, re);
}
@@ -243,14 +244,14 @@
size = virtinput_cfg_select(vi, VIRTIO_INPUT_CFG_ID_DEVIDS, 0);
if (size >= sizeof(struct virtio_input_devids)) {
- virtio_cread(vi->vdev, struct virtio_input_config,
- u.ids.bustype, &vi->idev->id.bustype);
- virtio_cread(vi->vdev, struct virtio_input_config,
- u.ids.vendor, &vi->idev->id.vendor);
- virtio_cread(vi->vdev, struct virtio_input_config,
- u.ids.product, &vi->idev->id.product);
- virtio_cread(vi->vdev, struct virtio_input_config,
- u.ids.version, &vi->idev->id.version);
+ virtio_cread_le(vi->vdev, struct virtio_input_config,
+ u.ids.bustype, &vi->idev->id.bustype);
+ virtio_cread_le(vi->vdev, struct virtio_input_config,
+ u.ids.vendor, &vi->idev->id.vendor);
+ virtio_cread_le(vi->vdev, struct virtio_input_config,
+ u.ids.product, &vi->idev->id.product);
+ virtio_cread_le(vi->vdev, struct virtio_input_config,
+ u.ids.version, &vi->idev->id.version);
} else {
vi->idev->id.bustype = BUS_VIRTUAL;
}
@@ -362,7 +363,7 @@
static unsigned int features[] = {
/* none */
};
-static struct virtio_device_id id_table[] = {
+static const struct virtio_device_id id_table[] = {
{ VIRTIO_ID_INPUT, VIRTIO_DEV_ANY_ID },
{ 0 },
};
diff --git a/drivers/virtio/virtio_mem.c b/drivers/virtio/virtio_mem.c
new file mode 100644
index 0000000..181e2f1
--- /dev/null
+++ b/drivers/virtio/virtio_mem.c
@@ -0,0 +1,1954 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Virtio-mem device driver.
+ *
+ * Copyright Red Hat, Inc. 2020
+ *
+ * Author(s): David Hildenbrand <david@redhat.com>
+ */
+
+#include <linux/virtio.h>
+#include <linux/virtio_mem.h>
+#include <linux/workqueue.h>
+#include <linux/slab.h>
+#include <linux/module.h>
+#include <linux/mm.h>
+#include <linux/memory_hotplug.h>
+#include <linux/memory.h>
+#include <linux/hrtimer.h>
+#include <linux/crash_dump.h>
+#include <linux/mutex.h>
+#include <linux/bitmap.h>
+#include <linux/lockdep.h>
+
+#include <acpi/acpi_numa.h>
+
+static bool unplug_online = true;
+module_param(unplug_online, bool, 0644);
+MODULE_PARM_DESC(unplug_online, "Try to unplug online memory");
+
+enum virtio_mem_mb_state {
+ /* Unplugged, not added to Linux. Can be reused later. */
+ VIRTIO_MEM_MB_STATE_UNUSED = 0,
+ /* (Partially) plugged, not added to Linux. Error on add_memory(). */
+ VIRTIO_MEM_MB_STATE_PLUGGED,
+ /* Fully plugged, fully added to Linux, offline. */
+ VIRTIO_MEM_MB_STATE_OFFLINE,
+ /* Partially plugged, fully added to Linux, offline. */
+ VIRTIO_MEM_MB_STATE_OFFLINE_PARTIAL,
+ /* Fully plugged, fully added to Linux, online. */
+ VIRTIO_MEM_MB_STATE_ONLINE,
+ /* Partially plugged, fully added to Linux, online. */
+ VIRTIO_MEM_MB_STATE_ONLINE_PARTIAL,
+ VIRTIO_MEM_MB_STATE_COUNT
+};
+
+struct virtio_mem {
+ struct virtio_device *vdev;
+
+ /* We might first have to unplug all memory when starting up. */
+ bool unplug_all_required;
+
+ /* Workqueue that processes the plug/unplug requests. */
+ struct work_struct wq;
+ atomic_t config_changed;
+
+ /* Virtqueue for guest->host requests. */
+ struct virtqueue *vq;
+
+ /* Wait for a host response to a guest request. */
+ wait_queue_head_t host_resp;
+
+ /* Space for one guest request and the host response. */
+ struct virtio_mem_req req;
+ struct virtio_mem_resp resp;
+
+ /* The current size of the device. */
+ uint64_t plugged_size;
+ /* The requested size of the device. */
+ uint64_t requested_size;
+
+ /* The device block size (for communicating with the device). */
+ uint64_t device_block_size;
+ /* The translated node id. NUMA_NO_NODE in case not specified. */
+ int nid;
+ /* Physical start address of the memory region. */
+ uint64_t addr;
+ /* Maximum region size in bytes. */
+ uint64_t region_size;
+
+ /* The subblock size. */
+ uint64_t subblock_size;
+ /* The number of subblocks per memory block. */
+ uint32_t nb_sb_per_mb;
+
+ /* Id of the first memory block of this device. */
+ unsigned long first_mb_id;
+ /* Id of the last memory block of this device. */
+ unsigned long last_mb_id;
+ /* Id of the last usable memory block of this device. */
+ unsigned long last_usable_mb_id;
+ /* Id of the next memory bock to prepare when needed. */
+ unsigned long next_mb_id;
+
+ /* The parent resource for all memory added via this device. */
+ struct resource *parent_resource;
+ /*
+ * Copy of "System RAM (virtio_mem)" to be used for
+ * add_memory_driver_managed().
+ */
+ const char *resource_name;
+
+ /* Summary of all memory block states. */
+ unsigned long nb_mb_state[VIRTIO_MEM_MB_STATE_COUNT];
+#define VIRTIO_MEM_NB_OFFLINE_THRESHOLD 10
+
+ /*
+ * One byte state per memory block.
+ *
+ * Allocated via vmalloc(). When preparing new blocks, resized
+ * (alloc+copy+free) when needed (crossing pages with the next mb).
+ * (when crossing pages).
+ *
+ * With 128MB memory blocks, we have states for 512GB of memory in one
+ * page.
+ */
+ uint8_t *mb_state;
+
+ /*
+ * $nb_sb_per_mb bit per memory block. Handled similar to mb_state.
+ *
+ * With 4MB subblocks, we manage 128GB of memory in one page.
+ */
+ unsigned long *sb_bitmap;
+
+ /*
+ * Mutex that protects the nb_mb_state, mb_state, and sb_bitmap.
+ *
+ * When this lock is held the pointers can't change, ONLINE and
+ * OFFLINE blocks can't change the state and no subblocks will get
+ * plugged/unplugged.
+ */
+ struct mutex hotplug_mutex;
+ bool hotplug_active;
+
+ /* An error occurred we cannot handle - stop processing requests. */
+ bool broken;
+
+ /* The driver is being removed. */
+ spinlock_t removal_lock;
+ bool removing;
+
+ /* Timer for retrying to plug/unplug memory. */
+ struct hrtimer retry_timer;
+ unsigned int retry_timer_ms;
+#define VIRTIO_MEM_RETRY_TIMER_MIN_MS 50000
+#define VIRTIO_MEM_RETRY_TIMER_MAX_MS 300000
+
+ /* Memory notifier (online/offline events). */
+ struct notifier_block memory_notifier;
+
+ /* Next device in the list of virtio-mem devices. */
+ struct list_head next;
+};
+
+/*
+ * We have to share a single online_page callback among all virtio-mem
+ * devices. We use RCU to iterate the list in the callback.
+ */
+static DEFINE_MUTEX(virtio_mem_mutex);
+static LIST_HEAD(virtio_mem_devices);
+
+static void virtio_mem_online_page_cb(struct page *page, unsigned int order);
+
+/*
+ * Register a virtio-mem device so it will be considered for the online_page
+ * callback.
+ */
+static int register_virtio_mem_device(struct virtio_mem *vm)
+{
+ int rc = 0;
+
+ /* First device registers the callback. */
+ mutex_lock(&virtio_mem_mutex);
+ if (list_empty(&virtio_mem_devices))
+ rc = set_online_page_callback(&virtio_mem_online_page_cb);
+ if (!rc)
+ list_add_rcu(&vm->next, &virtio_mem_devices);
+ mutex_unlock(&virtio_mem_mutex);
+
+ return rc;
+}
+
+/*
+ * Unregister a virtio-mem device so it will no longer be considered for the
+ * online_page callback.
+ */
+static void unregister_virtio_mem_device(struct virtio_mem *vm)
+{
+ /* Last device unregisters the callback. */
+ mutex_lock(&virtio_mem_mutex);
+ list_del_rcu(&vm->next);
+ if (list_empty(&virtio_mem_devices))
+ restore_online_page_callback(&virtio_mem_online_page_cb);
+ mutex_unlock(&virtio_mem_mutex);
+
+ synchronize_rcu();
+}
+
+/*
+ * Calculate the memory block id of a given address.
+ */
+static unsigned long virtio_mem_phys_to_mb_id(unsigned long addr)
+{
+ return addr / memory_block_size_bytes();
+}
+
+/*
+ * Calculate the physical start address of a given memory block id.
+ */
+static unsigned long virtio_mem_mb_id_to_phys(unsigned long mb_id)
+{
+ return mb_id * memory_block_size_bytes();
+}
+
+/*
+ * Calculate the subblock id of a given address.
+ */
+static unsigned long virtio_mem_phys_to_sb_id(struct virtio_mem *vm,
+ unsigned long addr)
+{
+ const unsigned long mb_id = virtio_mem_phys_to_mb_id(addr);
+ const unsigned long mb_addr = virtio_mem_mb_id_to_phys(mb_id);
+
+ return (addr - mb_addr) / vm->subblock_size;
+}
+
+/*
+ * Set the state of a memory block, taking care of the state counter.
+ */
+static void virtio_mem_mb_set_state(struct virtio_mem *vm, unsigned long mb_id,
+ enum virtio_mem_mb_state state)
+{
+ const unsigned long idx = mb_id - vm->first_mb_id;
+ enum virtio_mem_mb_state old_state;
+
+ old_state = vm->mb_state[idx];
+ vm->mb_state[idx] = state;
+
+ BUG_ON(vm->nb_mb_state[old_state] == 0);
+ vm->nb_mb_state[old_state]--;
+ vm->nb_mb_state[state]++;
+}
+
+/*
+ * Get the state of a memory block.
+ */
+static enum virtio_mem_mb_state virtio_mem_mb_get_state(struct virtio_mem *vm,
+ unsigned long mb_id)
+{
+ const unsigned long idx = mb_id - vm->first_mb_id;
+
+ return vm->mb_state[idx];
+}
+
+/*
+ * Prepare the state array for the next memory block.
+ */
+static int virtio_mem_mb_state_prepare_next_mb(struct virtio_mem *vm)
+{
+ unsigned long old_bytes = vm->next_mb_id - vm->first_mb_id + 1;
+ unsigned long new_bytes = vm->next_mb_id - vm->first_mb_id + 2;
+ int old_pages = PFN_UP(old_bytes);
+ int new_pages = PFN_UP(new_bytes);
+ uint8_t *new_mb_state;
+
+ if (vm->mb_state && old_pages == new_pages)
+ return 0;
+
+ new_mb_state = vzalloc(new_pages * PAGE_SIZE);
+ if (!new_mb_state)
+ return -ENOMEM;
+
+ mutex_lock(&vm->hotplug_mutex);
+ if (vm->mb_state)
+ memcpy(new_mb_state, vm->mb_state, old_pages * PAGE_SIZE);
+ vfree(vm->mb_state);
+ vm->mb_state = new_mb_state;
+ mutex_unlock(&vm->hotplug_mutex);
+
+ return 0;
+}
+
+#define virtio_mem_for_each_mb_state(_vm, _mb_id, _state) \
+ for (_mb_id = _vm->first_mb_id; \
+ _mb_id < _vm->next_mb_id && _vm->nb_mb_state[_state]; \
+ _mb_id++) \
+ if (virtio_mem_mb_get_state(_vm, _mb_id) == _state)
+
+#define virtio_mem_for_each_mb_state_rev(_vm, _mb_id, _state) \
+ for (_mb_id = _vm->next_mb_id - 1; \
+ _mb_id >= _vm->first_mb_id && _vm->nb_mb_state[_state]; \
+ _mb_id--) \
+ if (virtio_mem_mb_get_state(_vm, _mb_id) == _state)
+
+/*
+ * Mark all selected subblocks plugged.
+ *
+ * Will not modify the state of the memory block.
+ */
+static void virtio_mem_mb_set_sb_plugged(struct virtio_mem *vm,
+ unsigned long mb_id, int sb_id,
+ int count)
+{
+ const int bit = (mb_id - vm->first_mb_id) * vm->nb_sb_per_mb + sb_id;
+
+ __bitmap_set(vm->sb_bitmap, bit, count);
+}
+
+/*
+ * Mark all selected subblocks unplugged.
+ *
+ * Will not modify the state of the memory block.
+ */
+static void virtio_mem_mb_set_sb_unplugged(struct virtio_mem *vm,
+ unsigned long mb_id, int sb_id,
+ int count)
+{
+ const int bit = (mb_id - vm->first_mb_id) * vm->nb_sb_per_mb + sb_id;
+
+ __bitmap_clear(vm->sb_bitmap, bit, count);
+}
+
+/*
+ * Test if all selected subblocks are plugged.
+ */
+static bool virtio_mem_mb_test_sb_plugged(struct virtio_mem *vm,
+ unsigned long mb_id, int sb_id,
+ int count)
+{
+ const int bit = (mb_id - vm->first_mb_id) * vm->nb_sb_per_mb + sb_id;
+
+ if (count == 1)
+ return test_bit(bit, vm->sb_bitmap);
+
+ /* TODO: Helper similar to bitmap_set() */
+ return find_next_zero_bit(vm->sb_bitmap, bit + count, bit) >=
+ bit + count;
+}
+
+/*
+ * Test if all selected subblocks are unplugged.
+ */
+static bool virtio_mem_mb_test_sb_unplugged(struct virtio_mem *vm,
+ unsigned long mb_id, int sb_id,
+ int count)
+{
+ const int bit = (mb_id - vm->first_mb_id) * vm->nb_sb_per_mb + sb_id;
+
+ /* TODO: Helper similar to bitmap_set() */
+ return find_next_bit(vm->sb_bitmap, bit + count, bit) >= bit + count;
+}
+
+/*
+ * Find the first unplugged subblock. Returns vm->nb_sb_per_mb in case there is
+ * none.
+ */
+static int virtio_mem_mb_first_unplugged_sb(struct virtio_mem *vm,
+ unsigned long mb_id)
+{
+ const int bit = (mb_id - vm->first_mb_id) * vm->nb_sb_per_mb;
+
+ return find_next_zero_bit(vm->sb_bitmap, bit + vm->nb_sb_per_mb, bit) -
+ bit;
+}
+
+/*
+ * Prepare the subblock bitmap for the next memory block.
+ */
+static int virtio_mem_sb_bitmap_prepare_next_mb(struct virtio_mem *vm)
+{
+ const unsigned long old_nb_mb = vm->next_mb_id - vm->first_mb_id;
+ const unsigned long old_nb_bits = old_nb_mb * vm->nb_sb_per_mb;
+ const unsigned long new_nb_bits = (old_nb_mb + 1) * vm->nb_sb_per_mb;
+ int old_pages = PFN_UP(BITS_TO_LONGS(old_nb_bits) * sizeof(long));
+ int new_pages = PFN_UP(BITS_TO_LONGS(new_nb_bits) * sizeof(long));
+ unsigned long *new_sb_bitmap, *old_sb_bitmap;
+
+ if (vm->sb_bitmap && old_pages == new_pages)
+ return 0;
+
+ new_sb_bitmap = vzalloc(new_pages * PAGE_SIZE);
+ if (!new_sb_bitmap)
+ return -ENOMEM;
+
+ mutex_lock(&vm->hotplug_mutex);
+ if (new_sb_bitmap)
+ memcpy(new_sb_bitmap, vm->sb_bitmap, old_pages * PAGE_SIZE);
+
+ old_sb_bitmap = vm->sb_bitmap;
+ vm->sb_bitmap = new_sb_bitmap;
+ mutex_unlock(&vm->hotplug_mutex);
+
+ vfree(old_sb_bitmap);
+ return 0;
+}
+
+/*
+ * Try to add a memory block to Linux. This will usually only fail
+ * if out of memory.
+ *
+ * Must not be called with the vm->hotplug_mutex held (possible deadlock with
+ * onlining code).
+ *
+ * Will not modify the state of the memory block.
+ */
+static int virtio_mem_mb_add(struct virtio_mem *vm, unsigned long mb_id)
+{
+ const uint64_t addr = virtio_mem_mb_id_to_phys(mb_id);
+ int nid = vm->nid;
+
+ if (nid == NUMA_NO_NODE)
+ nid = memory_add_physaddr_to_nid(addr);
+
+ /*
+ * When force-unloading the driver and we still have memory added to
+ * Linux, the resource name has to stay.
+ */
+ if (!vm->resource_name) {
+ vm->resource_name = kstrdup_const("System RAM (virtio_mem)",
+ GFP_KERNEL);
+ if (!vm->resource_name)
+ return -ENOMEM;
+ }
+
+ dev_dbg(&vm->vdev->dev, "adding memory block: %lu\n", mb_id);
+ return add_memory_driver_managed(nid, addr, memory_block_size_bytes(),
+ vm->resource_name,
+ MEMHP_MERGE_RESOURCE);
+}
+
+/*
+ * Try to remove a memory block from Linux. Will only fail if the memory block
+ * is not offline.
+ *
+ * Must not be called with the vm->hotplug_mutex held (possible deadlock with
+ * onlining code).
+ *
+ * Will not modify the state of the memory block.
+ */
+static int virtio_mem_mb_remove(struct virtio_mem *vm, unsigned long mb_id)
+{
+ const uint64_t addr = virtio_mem_mb_id_to_phys(mb_id);
+ int nid = vm->nid;
+
+ if (nid == NUMA_NO_NODE)
+ nid = memory_add_physaddr_to_nid(addr);
+
+ dev_dbg(&vm->vdev->dev, "removing memory block: %lu\n", mb_id);
+ return remove_memory(nid, addr, memory_block_size_bytes());
+}
+
+/*
+ * Try to offline and remove a memory block from Linux.
+ *
+ * Must not be called with the vm->hotplug_mutex held (possible deadlock with
+ * onlining code).
+ *
+ * Will not modify the state of the memory block.
+ */
+static int virtio_mem_mb_offline_and_remove(struct virtio_mem *vm,
+ unsigned long mb_id)
+{
+ const uint64_t addr = virtio_mem_mb_id_to_phys(mb_id);
+ int nid = vm->nid;
+
+ if (nid == NUMA_NO_NODE)
+ nid = memory_add_physaddr_to_nid(addr);
+
+ dev_dbg(&vm->vdev->dev, "offlining and removing memory block: %lu\n",
+ mb_id);
+ return offline_and_remove_memory(nid, addr, memory_block_size_bytes());
+}
+
+/*
+ * Trigger the workqueue so the device can perform its magic.
+ */
+static void virtio_mem_retry(struct virtio_mem *vm)
+{
+ unsigned long flags;
+
+ spin_lock_irqsave(&vm->removal_lock, flags);
+ if (!vm->removing)
+ queue_work(system_freezable_wq, &vm->wq);
+ spin_unlock_irqrestore(&vm->removal_lock, flags);
+}
+
+static int virtio_mem_translate_node_id(struct virtio_mem *vm, uint16_t node_id)
+{
+ int node = NUMA_NO_NODE;
+
+#if defined(CONFIG_ACPI_NUMA)
+ if (virtio_has_feature(vm->vdev, VIRTIO_MEM_F_ACPI_PXM))
+ node = pxm_to_node(node_id);
+#endif
+ return node;
+}
+
+/*
+ * Test if a virtio-mem device overlaps with the given range. Can be called
+ * from (notifier) callbacks lockless.
+ */
+static bool virtio_mem_overlaps_range(struct virtio_mem *vm,
+ unsigned long start, unsigned long size)
+{
+ unsigned long dev_start = virtio_mem_mb_id_to_phys(vm->first_mb_id);
+ unsigned long dev_end = virtio_mem_mb_id_to_phys(vm->last_mb_id) +
+ memory_block_size_bytes();
+
+ return start < dev_end && dev_start < start + size;
+}
+
+/*
+ * Test if a virtio-mem device owns a memory block. Can be called from
+ * (notifier) callbacks lockless.
+ */
+static bool virtio_mem_owned_mb(struct virtio_mem *vm, unsigned long mb_id)
+{
+ return mb_id >= vm->first_mb_id && mb_id <= vm->last_mb_id;
+}
+
+static int virtio_mem_notify_going_online(struct virtio_mem *vm,
+ unsigned long mb_id)
+{
+ switch (virtio_mem_mb_get_state(vm, mb_id)) {
+ case VIRTIO_MEM_MB_STATE_OFFLINE_PARTIAL:
+ case VIRTIO_MEM_MB_STATE_OFFLINE:
+ return NOTIFY_OK;
+ default:
+ break;
+ }
+ dev_warn_ratelimited(&vm->vdev->dev,
+ "memory block onlining denied\n");
+ return NOTIFY_BAD;
+}
+
+static void virtio_mem_notify_offline(struct virtio_mem *vm,
+ unsigned long mb_id)
+{
+ switch (virtio_mem_mb_get_state(vm, mb_id)) {
+ case VIRTIO_MEM_MB_STATE_ONLINE_PARTIAL:
+ virtio_mem_mb_set_state(vm, mb_id,
+ VIRTIO_MEM_MB_STATE_OFFLINE_PARTIAL);
+ break;
+ case VIRTIO_MEM_MB_STATE_ONLINE:
+ virtio_mem_mb_set_state(vm, mb_id,
+ VIRTIO_MEM_MB_STATE_OFFLINE);
+ break;
+ default:
+ BUG();
+ break;
+ }
+
+ /*
+ * Trigger the workqueue, maybe we can now unplug memory. Also,
+ * when we offline and remove a memory block, this will re-trigger
+ * us immediately - which is often nice because the removal of
+ * the memory block (e.g., memmap) might have freed up memory
+ * on other memory blocks we manage.
+ */
+ virtio_mem_retry(vm);
+}
+
+static void virtio_mem_notify_online(struct virtio_mem *vm, unsigned long mb_id)
+{
+ unsigned long nb_offline;
+
+ switch (virtio_mem_mb_get_state(vm, mb_id)) {
+ case VIRTIO_MEM_MB_STATE_OFFLINE_PARTIAL:
+ virtio_mem_mb_set_state(vm, mb_id,
+ VIRTIO_MEM_MB_STATE_ONLINE_PARTIAL);
+ break;
+ case VIRTIO_MEM_MB_STATE_OFFLINE:
+ virtio_mem_mb_set_state(vm, mb_id, VIRTIO_MEM_MB_STATE_ONLINE);
+ break;
+ default:
+ BUG();
+ break;
+ }
+ nb_offline = vm->nb_mb_state[VIRTIO_MEM_MB_STATE_OFFLINE] +
+ vm->nb_mb_state[VIRTIO_MEM_MB_STATE_OFFLINE_PARTIAL];
+
+ /* see if we can add new blocks now that we onlined one block */
+ if (nb_offline == VIRTIO_MEM_NB_OFFLINE_THRESHOLD - 1)
+ virtio_mem_retry(vm);
+}
+
+static void virtio_mem_notify_going_offline(struct virtio_mem *vm,
+ unsigned long mb_id)
+{
+ const unsigned long nr_pages = PFN_DOWN(vm->subblock_size);
+ struct page *page;
+ unsigned long pfn;
+ int sb_id, i;
+
+ for (sb_id = 0; sb_id < vm->nb_sb_per_mb; sb_id++) {
+ if (virtio_mem_mb_test_sb_plugged(vm, mb_id, sb_id, 1))
+ continue;
+ /*
+ * Drop our reference to the pages so the memory can get
+ * offlined and add the unplugged pages to the managed
+ * page counters (so offlining code can correctly subtract
+ * them again).
+ */
+ pfn = PFN_DOWN(virtio_mem_mb_id_to_phys(mb_id) +
+ sb_id * vm->subblock_size);
+ adjust_managed_page_count(pfn_to_page(pfn), nr_pages);
+ for (i = 0; i < nr_pages; i++) {
+ page = pfn_to_page(pfn + i);
+ if (WARN_ON(!page_ref_dec_and_test(page)))
+ dump_page(page, "unplugged page referenced");
+ }
+ }
+}
+
+static void virtio_mem_notify_cancel_offline(struct virtio_mem *vm,
+ unsigned long mb_id)
+{
+ const unsigned long nr_pages = PFN_DOWN(vm->subblock_size);
+ unsigned long pfn;
+ int sb_id, i;
+
+ for (sb_id = 0; sb_id < vm->nb_sb_per_mb; sb_id++) {
+ if (virtio_mem_mb_test_sb_plugged(vm, mb_id, sb_id, 1))
+ continue;
+ /*
+ * Get the reference we dropped when going offline and
+ * subtract the unplugged pages from the managed page
+ * counters.
+ */
+ pfn = PFN_DOWN(virtio_mem_mb_id_to_phys(mb_id) +
+ sb_id * vm->subblock_size);
+ adjust_managed_page_count(pfn_to_page(pfn), -nr_pages);
+ for (i = 0; i < nr_pages; i++)
+ page_ref_inc(pfn_to_page(pfn + i));
+ }
+}
+
+/*
+ * This callback will either be called synchronously from add_memory() or
+ * asynchronously (e.g., triggered via user space). We have to be careful
+ * with locking when calling add_memory().
+ */
+static int virtio_mem_memory_notifier_cb(struct notifier_block *nb,
+ unsigned long action, void *arg)
+{
+ struct virtio_mem *vm = container_of(nb, struct virtio_mem,
+ memory_notifier);
+ struct memory_notify *mhp = arg;
+ const unsigned long start = PFN_PHYS(mhp->start_pfn);
+ const unsigned long size = PFN_PHYS(mhp->nr_pages);
+ const unsigned long mb_id = virtio_mem_phys_to_mb_id(start);
+ int rc = NOTIFY_OK;
+
+ if (!virtio_mem_overlaps_range(vm, start, size))
+ return NOTIFY_DONE;
+
+ /*
+ * Memory is onlined/offlined in memory block granularity. We cannot
+ * cross virtio-mem device boundaries and memory block boundaries. Bail
+ * out if this ever changes.
+ */
+ if (WARN_ON_ONCE(size != memory_block_size_bytes() ||
+ !IS_ALIGNED(start, memory_block_size_bytes())))
+ return NOTIFY_BAD;
+
+ /*
+ * Avoid circular locking lockdep warnings. We lock the mutex
+ * e.g., in MEM_GOING_ONLINE and unlock it in MEM_ONLINE. The
+ * blocking_notifier_call_chain() has it's own lock, which gets unlocked
+ * between both notifier calls and will bail out. False positive.
+ */
+ lockdep_off();
+
+ switch (action) {
+ case MEM_GOING_OFFLINE:
+ mutex_lock(&vm->hotplug_mutex);
+ if (vm->removing) {
+ rc = notifier_from_errno(-EBUSY);
+ mutex_unlock(&vm->hotplug_mutex);
+ break;
+ }
+ vm->hotplug_active = true;
+ virtio_mem_notify_going_offline(vm, mb_id);
+ break;
+ case MEM_GOING_ONLINE:
+ mutex_lock(&vm->hotplug_mutex);
+ if (vm->removing) {
+ rc = notifier_from_errno(-EBUSY);
+ mutex_unlock(&vm->hotplug_mutex);
+ break;
+ }
+ vm->hotplug_active = true;
+ rc = virtio_mem_notify_going_online(vm, mb_id);
+ break;
+ case MEM_OFFLINE:
+ virtio_mem_notify_offline(vm, mb_id);
+ vm->hotplug_active = false;
+ mutex_unlock(&vm->hotplug_mutex);
+ break;
+ case MEM_ONLINE:
+ virtio_mem_notify_online(vm, mb_id);
+ vm->hotplug_active = false;
+ mutex_unlock(&vm->hotplug_mutex);
+ break;
+ case MEM_CANCEL_OFFLINE:
+ if (!vm->hotplug_active)
+ break;
+ virtio_mem_notify_cancel_offline(vm, mb_id);
+ vm->hotplug_active = false;
+ mutex_unlock(&vm->hotplug_mutex);
+ break;
+ case MEM_CANCEL_ONLINE:
+ if (!vm->hotplug_active)
+ break;
+ vm->hotplug_active = false;
+ mutex_unlock(&vm->hotplug_mutex);
+ break;
+ default:
+ break;
+ }
+
+ lockdep_on();
+
+ return rc;
+}
+
+/*
+ * Set a range of pages PG_offline. Remember pages that were never onlined
+ * (via generic_online_page()) using PageDirty().
+ */
+static void virtio_mem_set_fake_offline(unsigned long pfn,
+ unsigned int nr_pages, bool onlined)
+{
+ for (; nr_pages--; pfn++) {
+ struct page *page = pfn_to_page(pfn);
+
+ __SetPageOffline(page);
+ if (!onlined) {
+ SetPageDirty(page);
+ /* FIXME: remove after cleanups */
+ ClearPageReserved(page);
+ }
+ }
+}
+
+/*
+ * Clear PG_offline from a range of pages. If the pages were never onlined,
+ * (via generic_online_page()), clear PageDirty().
+ */
+static void virtio_mem_clear_fake_offline(unsigned long pfn,
+ unsigned int nr_pages, bool onlined)
+{
+ for (; nr_pages--; pfn++) {
+ struct page *page = pfn_to_page(pfn);
+
+ __ClearPageOffline(page);
+ if (!onlined)
+ ClearPageDirty(page);
+ }
+}
+
+/*
+ * Release a range of fake-offline pages to the buddy, effectively
+ * fake-onlining them.
+ */
+static void virtio_mem_fake_online(unsigned long pfn, unsigned int nr_pages)
+{
+ const int order = MAX_ORDER - 1;
+ int i;
+
+ /*
+ * We are always called with subblock granularity, which is at least
+ * aligned to MAX_ORDER - 1.
+ */
+ for (i = 0; i < nr_pages; i += 1 << order) {
+ struct page *page = pfn_to_page(pfn + i);
+
+ /*
+ * If the page is PageDirty(), it was kept fake-offline when
+ * onlining the memory block. Otherwise, it was allocated
+ * using alloc_contig_range(). All pages in a subblock are
+ * alike.
+ */
+ if (PageDirty(page)) {
+ virtio_mem_clear_fake_offline(pfn + i, 1 << order,
+ false);
+ generic_online_page(page, order);
+ } else {
+ virtio_mem_clear_fake_offline(pfn + i, 1 << order,
+ true);
+ free_contig_range(pfn + i, 1 << order);
+ adjust_managed_page_count(page, 1 << order);
+ }
+ }
+}
+
+static void virtio_mem_online_page_cb(struct page *page, unsigned int order)
+{
+ const unsigned long addr = page_to_phys(page);
+ const unsigned long mb_id = virtio_mem_phys_to_mb_id(addr);
+ struct virtio_mem *vm;
+ int sb_id;
+
+ /*
+ * We exploit here that subblocks have at least MAX_ORDER - 1
+ * size/alignment and that this callback is is called with such a
+ * size/alignment. So we cannot cross subblocks and therefore
+ * also not memory blocks.
+ */
+ rcu_read_lock();
+ list_for_each_entry_rcu(vm, &virtio_mem_devices, next) {
+ if (!virtio_mem_owned_mb(vm, mb_id))
+ continue;
+
+ sb_id = virtio_mem_phys_to_sb_id(vm, addr);
+ /*
+ * If plugged, online the pages, otherwise, set them fake
+ * offline (PageOffline).
+ */
+ if (virtio_mem_mb_test_sb_plugged(vm, mb_id, sb_id, 1))
+ generic_online_page(page, order);
+ else
+ virtio_mem_set_fake_offline(PFN_DOWN(addr), 1 << order,
+ false);
+ rcu_read_unlock();
+ return;
+ }
+ rcu_read_unlock();
+
+ /* not virtio-mem memory, but e.g., a DIMM. online it */
+ generic_online_page(page, order);
+}
+
+static uint64_t virtio_mem_send_request(struct virtio_mem *vm,
+ const struct virtio_mem_req *req)
+{
+ struct scatterlist *sgs[2], sg_req, sg_resp;
+ unsigned int len;
+ int rc;
+
+ /* don't use the request residing on the stack (vaddr) */
+ vm->req = *req;
+
+ /* out: buffer for request */
+ sg_init_one(&sg_req, &vm->req, sizeof(vm->req));
+ sgs[0] = &sg_req;
+
+ /* in: buffer for response */
+ sg_init_one(&sg_resp, &vm->resp, sizeof(vm->resp));
+ sgs[1] = &sg_resp;
+
+ rc = virtqueue_add_sgs(vm->vq, sgs, 1, 1, vm, GFP_KERNEL);
+ if (rc < 0)
+ return rc;
+
+ virtqueue_kick(vm->vq);
+
+ /* wait for a response */
+ wait_event(vm->host_resp, virtqueue_get_buf(vm->vq, &len));
+
+ return virtio16_to_cpu(vm->vdev, vm->resp.type);
+}
+
+static int virtio_mem_send_plug_request(struct virtio_mem *vm, uint64_t addr,
+ uint64_t size)
+{
+ const uint64_t nb_vm_blocks = size / vm->device_block_size;
+ const struct virtio_mem_req req = {
+ .type = cpu_to_virtio16(vm->vdev, VIRTIO_MEM_REQ_PLUG),
+ .u.plug.addr = cpu_to_virtio64(vm->vdev, addr),
+ .u.plug.nb_blocks = cpu_to_virtio16(vm->vdev, nb_vm_blocks),
+ };
+
+ if (atomic_read(&vm->config_changed))
+ return -EAGAIN;
+
+ switch (virtio_mem_send_request(vm, &req)) {
+ case VIRTIO_MEM_RESP_ACK:
+ vm->plugged_size += size;
+ return 0;
+ case VIRTIO_MEM_RESP_NACK:
+ return -EAGAIN;
+ case VIRTIO_MEM_RESP_BUSY:
+ return -ETXTBSY;
+ case VIRTIO_MEM_RESP_ERROR:
+ return -EINVAL;
+ default:
+ return -ENOMEM;
+ }
+}
+
+static int virtio_mem_send_unplug_request(struct virtio_mem *vm, uint64_t addr,
+ uint64_t size)
+{
+ const uint64_t nb_vm_blocks = size / vm->device_block_size;
+ const struct virtio_mem_req req = {
+ .type = cpu_to_virtio16(vm->vdev, VIRTIO_MEM_REQ_UNPLUG),
+ .u.unplug.addr = cpu_to_virtio64(vm->vdev, addr),
+ .u.unplug.nb_blocks = cpu_to_virtio16(vm->vdev, nb_vm_blocks),
+ };
+
+ if (atomic_read(&vm->config_changed))
+ return -EAGAIN;
+
+ switch (virtio_mem_send_request(vm, &req)) {
+ case VIRTIO_MEM_RESP_ACK:
+ vm->plugged_size -= size;
+ return 0;
+ case VIRTIO_MEM_RESP_BUSY:
+ return -ETXTBSY;
+ case VIRTIO_MEM_RESP_ERROR:
+ return -EINVAL;
+ default:
+ return -ENOMEM;
+ }
+}
+
+static int virtio_mem_send_unplug_all_request(struct virtio_mem *vm)
+{
+ const struct virtio_mem_req req = {
+ .type = cpu_to_virtio16(vm->vdev, VIRTIO_MEM_REQ_UNPLUG_ALL),
+ };
+
+ switch (virtio_mem_send_request(vm, &req)) {
+ case VIRTIO_MEM_RESP_ACK:
+ vm->unplug_all_required = false;
+ vm->plugged_size = 0;
+ /* usable region might have shrunk */
+ atomic_set(&vm->config_changed, 1);
+ return 0;
+ case VIRTIO_MEM_RESP_BUSY:
+ return -ETXTBSY;
+ default:
+ return -ENOMEM;
+ }
+}
+
+/*
+ * Plug selected subblocks. Updates the plugged state, but not the state
+ * of the memory block.
+ */
+static int virtio_mem_mb_plug_sb(struct virtio_mem *vm, unsigned long mb_id,
+ int sb_id, int count)
+{
+ const uint64_t addr = virtio_mem_mb_id_to_phys(mb_id) +
+ sb_id * vm->subblock_size;
+ const uint64_t size = count * vm->subblock_size;
+ int rc;
+
+ dev_dbg(&vm->vdev->dev, "plugging memory block: %lu : %i - %i\n", mb_id,
+ sb_id, sb_id + count - 1);
+
+ rc = virtio_mem_send_plug_request(vm, addr, size);
+ if (!rc)
+ virtio_mem_mb_set_sb_plugged(vm, mb_id, sb_id, count);
+ return rc;
+}
+
+/*
+ * Unplug selected subblocks. Updates the plugged state, but not the state
+ * of the memory block.
+ */
+static int virtio_mem_mb_unplug_sb(struct virtio_mem *vm, unsigned long mb_id,
+ int sb_id, int count)
+{
+ const uint64_t addr = virtio_mem_mb_id_to_phys(mb_id) +
+ sb_id * vm->subblock_size;
+ const uint64_t size = count * vm->subblock_size;
+ int rc;
+
+ dev_dbg(&vm->vdev->dev, "unplugging memory block: %lu : %i - %i\n",
+ mb_id, sb_id, sb_id + count - 1);
+
+ rc = virtio_mem_send_unplug_request(vm, addr, size);
+ if (!rc)
+ virtio_mem_mb_set_sb_unplugged(vm, mb_id, sb_id, count);
+ return rc;
+}
+
+/*
+ * Unplug the desired number of plugged subblocks of a offline or not-added
+ * memory block. Will fail if any subblock cannot get unplugged (instead of
+ * skipping it).
+ *
+ * Will not modify the state of the memory block.
+ *
+ * Note: can fail after some subblocks were unplugged.
+ */
+static int virtio_mem_mb_unplug_any_sb(struct virtio_mem *vm,
+ unsigned long mb_id, uint64_t *nb_sb)
+{
+ int sb_id, count;
+ int rc;
+
+ sb_id = vm->nb_sb_per_mb - 1;
+ while (*nb_sb) {
+ /* Find the next candidate subblock */
+ while (sb_id >= 0 &&
+ virtio_mem_mb_test_sb_unplugged(vm, mb_id, sb_id, 1))
+ sb_id--;
+ if (sb_id < 0)
+ break;
+ /* Try to unplug multiple subblocks at a time */
+ count = 1;
+ while (count < *nb_sb && sb_id > 0 &&
+ virtio_mem_mb_test_sb_plugged(vm, mb_id, sb_id - 1, 1)) {
+ count++;
+ sb_id--;
+ }
+
+ rc = virtio_mem_mb_unplug_sb(vm, mb_id, sb_id, count);
+ if (rc)
+ return rc;
+ *nb_sb -= count;
+ sb_id--;
+ }
+
+ return 0;
+}
+
+/*
+ * Unplug all plugged subblocks of an offline or not-added memory block.
+ *
+ * Will not modify the state of the memory block.
+ *
+ * Note: can fail after some subblocks were unplugged.
+ */
+static int virtio_mem_mb_unplug(struct virtio_mem *vm, unsigned long mb_id)
+{
+ uint64_t nb_sb = vm->nb_sb_per_mb;
+
+ return virtio_mem_mb_unplug_any_sb(vm, mb_id, &nb_sb);
+}
+
+/*
+ * Prepare tracking data for the next memory block.
+ */
+static int virtio_mem_prepare_next_mb(struct virtio_mem *vm,
+ unsigned long *mb_id)
+{
+ int rc;
+
+ if (vm->next_mb_id > vm->last_usable_mb_id)
+ return -ENOSPC;
+
+ /* Resize the state array if required. */
+ rc = virtio_mem_mb_state_prepare_next_mb(vm);
+ if (rc)
+ return rc;
+
+ /* Resize the subblock bitmap if required. */
+ rc = virtio_mem_sb_bitmap_prepare_next_mb(vm);
+ if (rc)
+ return rc;
+
+ vm->nb_mb_state[VIRTIO_MEM_MB_STATE_UNUSED]++;
+ *mb_id = vm->next_mb_id++;
+ return 0;
+}
+
+/*
+ * Don't add too many blocks that are not onlined yet to avoid running OOM.
+ */
+static bool virtio_mem_too_many_mb_offline(struct virtio_mem *vm)
+{
+ unsigned long nb_offline;
+
+ nb_offline = vm->nb_mb_state[VIRTIO_MEM_MB_STATE_OFFLINE] +
+ vm->nb_mb_state[VIRTIO_MEM_MB_STATE_OFFLINE_PARTIAL];
+ return nb_offline >= VIRTIO_MEM_NB_OFFLINE_THRESHOLD;
+}
+
+/*
+ * Try to plug the desired number of subblocks and add the memory block
+ * to Linux.
+ *
+ * Will modify the state of the memory block.
+ */
+static int virtio_mem_mb_plug_and_add(struct virtio_mem *vm,
+ unsigned long mb_id,
+ uint64_t *nb_sb)
+{
+ const int count = min_t(int, *nb_sb, vm->nb_sb_per_mb);
+ int rc, rc2;
+
+ if (WARN_ON_ONCE(!count))
+ return -EINVAL;
+
+ /*
+ * Plug the requested number of subblocks before adding it to linux,
+ * so that onlining will directly online all plugged subblocks.
+ */
+ rc = virtio_mem_mb_plug_sb(vm, mb_id, 0, count);
+ if (rc)
+ return rc;
+
+ /*
+ * Mark the block properly offline before adding it to Linux,
+ * so the memory notifiers will find the block in the right state.
+ */
+ if (count == vm->nb_sb_per_mb)
+ virtio_mem_mb_set_state(vm, mb_id,
+ VIRTIO_MEM_MB_STATE_OFFLINE);
+ else
+ virtio_mem_mb_set_state(vm, mb_id,
+ VIRTIO_MEM_MB_STATE_OFFLINE_PARTIAL);
+
+ /* Add the memory block to linux - if that fails, try to unplug. */
+ rc = virtio_mem_mb_add(vm, mb_id);
+ if (rc) {
+ enum virtio_mem_mb_state new_state = VIRTIO_MEM_MB_STATE_UNUSED;
+
+ dev_err(&vm->vdev->dev,
+ "adding memory block %lu failed with %d\n", mb_id, rc);
+ rc2 = virtio_mem_mb_unplug_sb(vm, mb_id, 0, count);
+
+ /*
+ * TODO: Linux MM does not properly clean up yet in all cases
+ * where adding of memory failed - especially on -ENOMEM.
+ */
+ if (rc2)
+ new_state = VIRTIO_MEM_MB_STATE_PLUGGED;
+ virtio_mem_mb_set_state(vm, mb_id, new_state);
+ return rc;
+ }
+
+ *nb_sb -= count;
+ return 0;
+}
+
+/*
+ * Try to plug the desired number of subblocks of a memory block that
+ * is already added to Linux.
+ *
+ * Will modify the state of the memory block.
+ *
+ * Note: Can fail after some subblocks were successfully plugged.
+ */
+static int virtio_mem_mb_plug_any_sb(struct virtio_mem *vm, unsigned long mb_id,
+ uint64_t *nb_sb, bool online)
+{
+ unsigned long pfn, nr_pages;
+ int sb_id, count;
+ int rc;
+
+ if (WARN_ON_ONCE(!*nb_sb))
+ return -EINVAL;
+
+ while (*nb_sb) {
+ sb_id = virtio_mem_mb_first_unplugged_sb(vm, mb_id);
+ if (sb_id >= vm->nb_sb_per_mb)
+ break;
+ count = 1;
+ while (count < *nb_sb &&
+ sb_id + count < vm->nb_sb_per_mb &&
+ !virtio_mem_mb_test_sb_plugged(vm, mb_id, sb_id + count,
+ 1))
+ count++;
+
+ rc = virtio_mem_mb_plug_sb(vm, mb_id, sb_id, count);
+ if (rc)
+ return rc;
+ *nb_sb -= count;
+ if (!online)
+ continue;
+
+ /* fake-online the pages if the memory block is online */
+ pfn = PFN_DOWN(virtio_mem_mb_id_to_phys(mb_id) +
+ sb_id * vm->subblock_size);
+ nr_pages = PFN_DOWN(count * vm->subblock_size);
+ virtio_mem_fake_online(pfn, nr_pages);
+ }
+
+ if (virtio_mem_mb_test_sb_plugged(vm, mb_id, 0, vm->nb_sb_per_mb)) {
+ if (online)
+ virtio_mem_mb_set_state(vm, mb_id,
+ VIRTIO_MEM_MB_STATE_ONLINE);
+ else
+ virtio_mem_mb_set_state(vm, mb_id,
+ VIRTIO_MEM_MB_STATE_OFFLINE);
+ }
+
+ return 0;
+}
+
+/*
+ * Try to plug the requested amount of memory.
+ */
+static int virtio_mem_plug_request(struct virtio_mem *vm, uint64_t diff)
+{
+ uint64_t nb_sb = diff / vm->subblock_size;
+ unsigned long mb_id;
+ int rc;
+
+ if (!nb_sb)
+ return 0;
+
+ /* Don't race with onlining/offlining */
+ mutex_lock(&vm->hotplug_mutex);
+
+ /* Try to plug subblocks of partially plugged online blocks. */
+ virtio_mem_for_each_mb_state(vm, mb_id,
+ VIRTIO_MEM_MB_STATE_ONLINE_PARTIAL) {
+ rc = virtio_mem_mb_plug_any_sb(vm, mb_id, &nb_sb, true);
+ if (rc || !nb_sb)
+ goto out_unlock;
+ cond_resched();
+ }
+
+ /* Try to plug subblocks of partially plugged offline blocks. */
+ virtio_mem_for_each_mb_state(vm, mb_id,
+ VIRTIO_MEM_MB_STATE_OFFLINE_PARTIAL) {
+ rc = virtio_mem_mb_plug_any_sb(vm, mb_id, &nb_sb, false);
+ if (rc || !nb_sb)
+ goto out_unlock;
+ cond_resched();
+ }
+
+ /*
+ * We won't be working on online/offline memory blocks from this point,
+ * so we can't race with memory onlining/offlining. Drop the mutex.
+ */
+ mutex_unlock(&vm->hotplug_mutex);
+
+ /* Try to plug and add unused blocks */
+ virtio_mem_for_each_mb_state(vm, mb_id, VIRTIO_MEM_MB_STATE_UNUSED) {
+ if (virtio_mem_too_many_mb_offline(vm))
+ return -ENOSPC;
+
+ rc = virtio_mem_mb_plug_and_add(vm, mb_id, &nb_sb);
+ if (rc || !nb_sb)
+ return rc;
+ cond_resched();
+ }
+
+ /* Try to prepare, plug and add new blocks */
+ while (nb_sb) {
+ if (virtio_mem_too_many_mb_offline(vm))
+ return -ENOSPC;
+
+ rc = virtio_mem_prepare_next_mb(vm, &mb_id);
+ if (rc)
+ return rc;
+ rc = virtio_mem_mb_plug_and_add(vm, mb_id, &nb_sb);
+ if (rc)
+ return rc;
+ cond_resched();
+ }
+
+ return 0;
+out_unlock:
+ mutex_unlock(&vm->hotplug_mutex);
+ return rc;
+}
+
+/*
+ * Unplug the desired number of plugged subblocks of an offline memory block.
+ * Will fail if any subblock cannot get unplugged (instead of skipping it).
+ *
+ * Will modify the state of the memory block. Might temporarily drop the
+ * hotplug_mutex.
+ *
+ * Note: Can fail after some subblocks were successfully unplugged.
+ */
+static int virtio_mem_mb_unplug_any_sb_offline(struct virtio_mem *vm,
+ unsigned long mb_id,
+ uint64_t *nb_sb)
+{
+ int rc;
+
+ rc = virtio_mem_mb_unplug_any_sb(vm, mb_id, nb_sb);
+
+ /* some subblocks might have been unplugged even on failure */
+ if (!virtio_mem_mb_test_sb_plugged(vm, mb_id, 0, vm->nb_sb_per_mb))
+ virtio_mem_mb_set_state(vm, mb_id,
+ VIRTIO_MEM_MB_STATE_OFFLINE_PARTIAL);
+ if (rc)
+ return rc;
+
+ if (virtio_mem_mb_test_sb_unplugged(vm, mb_id, 0, vm->nb_sb_per_mb)) {
+ /*
+ * Remove the block from Linux - this should never fail.
+ * Hinder the block from getting onlined by marking it
+ * unplugged. Temporarily drop the mutex, so
+ * any pending GOING_ONLINE requests can be serviced/rejected.
+ */
+ virtio_mem_mb_set_state(vm, mb_id,
+ VIRTIO_MEM_MB_STATE_UNUSED);
+
+ mutex_unlock(&vm->hotplug_mutex);
+ rc = virtio_mem_mb_remove(vm, mb_id);
+ BUG_ON(rc);
+ mutex_lock(&vm->hotplug_mutex);
+ }
+ return 0;
+}
+
+/*
+ * Unplug the given plugged subblocks of an online memory block.
+ *
+ * Will modify the state of the memory block.
+ */
+static int virtio_mem_mb_unplug_sb_online(struct virtio_mem *vm,
+ unsigned long mb_id, int sb_id,
+ int count)
+{
+ const unsigned long nr_pages = PFN_DOWN(vm->subblock_size) * count;
+ unsigned long start_pfn;
+ int rc;
+
+ start_pfn = PFN_DOWN(virtio_mem_mb_id_to_phys(mb_id) +
+ sb_id * vm->subblock_size);
+ rc = alloc_contig_range(start_pfn, start_pfn + nr_pages,
+ MIGRATE_MOVABLE, GFP_KERNEL);
+ if (rc == -ENOMEM)
+ /* whoops, out of memory */
+ return rc;
+ if (rc)
+ return -EBUSY;
+
+ /* Mark it as fake-offline before unplugging it */
+ virtio_mem_set_fake_offline(start_pfn, nr_pages, true);
+ adjust_managed_page_count(pfn_to_page(start_pfn), -nr_pages);
+
+ /* Try to unplug the allocated memory */
+ rc = virtio_mem_mb_unplug_sb(vm, mb_id, sb_id, count);
+ if (rc) {
+ /* Return the memory to the buddy. */
+ virtio_mem_fake_online(start_pfn, nr_pages);
+ return rc;
+ }
+
+ virtio_mem_mb_set_state(vm, mb_id,
+ VIRTIO_MEM_MB_STATE_ONLINE_PARTIAL);
+ return 0;
+}
+
+/*
+ * Unplug the desired number of plugged subblocks of an online memory block.
+ * Will skip subblock that are busy.
+ *
+ * Will modify the state of the memory block. Might temporarily drop the
+ * hotplug_mutex.
+ *
+ * Note: Can fail after some subblocks were successfully unplugged. Can
+ * return 0 even if subblocks were busy and could not get unplugged.
+ */
+static int virtio_mem_mb_unplug_any_sb_online(struct virtio_mem *vm,
+ unsigned long mb_id,
+ uint64_t *nb_sb)
+{
+ int rc, sb_id;
+
+ /* If possible, try to unplug the complete block in one shot. */
+ if (*nb_sb >= vm->nb_sb_per_mb &&
+ virtio_mem_mb_test_sb_plugged(vm, mb_id, 0, vm->nb_sb_per_mb)) {
+ rc = virtio_mem_mb_unplug_sb_online(vm, mb_id, 0,
+ vm->nb_sb_per_mb);
+ if (!rc) {
+ *nb_sb -= vm->nb_sb_per_mb;
+ goto unplugged;
+ } else if (rc != -EBUSY)
+ return rc;
+ }
+
+ /* Fallback to single subblocks. */
+ for (sb_id = vm->nb_sb_per_mb - 1; sb_id >= 0 && *nb_sb; sb_id--) {
+ /* Find the next candidate subblock */
+ while (sb_id >= 0 &&
+ !virtio_mem_mb_test_sb_plugged(vm, mb_id, sb_id, 1))
+ sb_id--;
+ if (sb_id < 0)
+ break;
+
+ rc = virtio_mem_mb_unplug_sb_online(vm, mb_id, sb_id, 1);
+ if (rc == -EBUSY)
+ continue;
+ else if (rc)
+ return rc;
+ *nb_sb -= 1;
+ }
+
+unplugged:
+ /*
+ * Once all subblocks of a memory block were unplugged, offline and
+ * remove it. This will usually not fail, as no memory is in use
+ * anymore - however some other notifiers might NACK the request.
+ */
+ if (virtio_mem_mb_test_sb_unplugged(vm, mb_id, 0, vm->nb_sb_per_mb)) {
+ mutex_unlock(&vm->hotplug_mutex);
+ rc = virtio_mem_mb_offline_and_remove(vm, mb_id);
+ mutex_lock(&vm->hotplug_mutex);
+ if (!rc)
+ virtio_mem_mb_set_state(vm, mb_id,
+ VIRTIO_MEM_MB_STATE_UNUSED);
+ }
+
+ return 0;
+}
+
+/*
+ * Try to unplug the requested amount of memory.
+ */
+static int virtio_mem_unplug_request(struct virtio_mem *vm, uint64_t diff)
+{
+ uint64_t nb_sb = diff / vm->subblock_size;
+ unsigned long mb_id;
+ int rc;
+
+ if (!nb_sb)
+ return 0;
+
+ /*
+ * We'll drop the mutex a couple of times when it is safe to do so.
+ * This might result in some blocks switching the state (online/offline)
+ * and we could miss them in this run - we will retry again later.
+ */
+ mutex_lock(&vm->hotplug_mutex);
+
+ /* Try to unplug subblocks of partially plugged offline blocks. */
+ virtio_mem_for_each_mb_state_rev(vm, mb_id,
+ VIRTIO_MEM_MB_STATE_OFFLINE_PARTIAL) {
+ rc = virtio_mem_mb_unplug_any_sb_offline(vm, mb_id,
+ &nb_sb);
+ if (rc || !nb_sb)
+ goto out_unlock;
+ cond_resched();
+ }
+
+ /* Try to unplug subblocks of plugged offline blocks. */
+ virtio_mem_for_each_mb_state_rev(vm, mb_id,
+ VIRTIO_MEM_MB_STATE_OFFLINE) {
+ rc = virtio_mem_mb_unplug_any_sb_offline(vm, mb_id,
+ &nb_sb);
+ if (rc || !nb_sb)
+ goto out_unlock;
+ cond_resched();
+ }
+
+ if (!unplug_online) {
+ mutex_unlock(&vm->hotplug_mutex);
+ return 0;
+ }
+
+ /* Try to unplug subblocks of partially plugged online blocks. */
+ virtio_mem_for_each_mb_state_rev(vm, mb_id,
+ VIRTIO_MEM_MB_STATE_ONLINE_PARTIAL) {
+ rc = virtio_mem_mb_unplug_any_sb_online(vm, mb_id,
+ &nb_sb);
+ if (rc || !nb_sb)
+ goto out_unlock;
+ mutex_unlock(&vm->hotplug_mutex);
+ cond_resched();
+ mutex_lock(&vm->hotplug_mutex);
+ }
+
+ /* Try to unplug subblocks of plugged online blocks. */
+ virtio_mem_for_each_mb_state_rev(vm, mb_id,
+ VIRTIO_MEM_MB_STATE_ONLINE) {
+ rc = virtio_mem_mb_unplug_any_sb_online(vm, mb_id,
+ &nb_sb);
+ if (rc || !nb_sb)
+ goto out_unlock;
+ mutex_unlock(&vm->hotplug_mutex);
+ cond_resched();
+ mutex_lock(&vm->hotplug_mutex);
+ }
+
+ mutex_unlock(&vm->hotplug_mutex);
+ return nb_sb ? -EBUSY : 0;
+out_unlock:
+ mutex_unlock(&vm->hotplug_mutex);
+ return rc;
+}
+
+/*
+ * Try to unplug all blocks that couldn't be unplugged before, for example,
+ * because the hypervisor was busy.
+ */
+static int virtio_mem_unplug_pending_mb(struct virtio_mem *vm)
+{
+ unsigned long mb_id;
+ int rc;
+
+ virtio_mem_for_each_mb_state(vm, mb_id, VIRTIO_MEM_MB_STATE_PLUGGED) {
+ rc = virtio_mem_mb_unplug(vm, mb_id);
+ if (rc)
+ return rc;
+ virtio_mem_mb_set_state(vm, mb_id, VIRTIO_MEM_MB_STATE_UNUSED);
+ }
+
+ return 0;
+}
+
+/*
+ * Update all parts of the config that could have changed.
+ */
+static void virtio_mem_refresh_config(struct virtio_mem *vm)
+{
+ const uint64_t phys_limit = 1UL << MAX_PHYSMEM_BITS;
+ uint64_t new_plugged_size, usable_region_size, end_addr;
+
+ /* the plugged_size is just a reflection of what _we_ did previously */
+ virtio_cread_le(vm->vdev, struct virtio_mem_config, plugged_size,
+ &new_plugged_size);
+ if (WARN_ON_ONCE(new_plugged_size != vm->plugged_size))
+ vm->plugged_size = new_plugged_size;
+
+ /* calculate the last usable memory block id */
+ virtio_cread_le(vm->vdev, struct virtio_mem_config,
+ usable_region_size, &usable_region_size);
+ end_addr = vm->addr + usable_region_size;
+ end_addr = min(end_addr, phys_limit);
+ vm->last_usable_mb_id = virtio_mem_phys_to_mb_id(end_addr) - 1;
+
+ /* see if there is a request to change the size */
+ virtio_cread_le(vm->vdev, struct virtio_mem_config, requested_size,
+ &vm->requested_size);
+
+ dev_info(&vm->vdev->dev, "plugged size: 0x%llx", vm->plugged_size);
+ dev_info(&vm->vdev->dev, "requested size: 0x%llx", vm->requested_size);
+}
+
+/*
+ * Workqueue function for handling plug/unplug requests and config updates.
+ */
+static void virtio_mem_run_wq(struct work_struct *work)
+{
+ struct virtio_mem *vm = container_of(work, struct virtio_mem, wq);
+ uint64_t diff;
+ int rc;
+
+ hrtimer_cancel(&vm->retry_timer);
+
+ if (vm->broken)
+ return;
+
+retry:
+ rc = 0;
+
+ /* Make sure we start with a clean state if there are leftovers. */
+ if (unlikely(vm->unplug_all_required))
+ rc = virtio_mem_send_unplug_all_request(vm);
+
+ if (atomic_read(&vm->config_changed)) {
+ atomic_set(&vm->config_changed, 0);
+ virtio_mem_refresh_config(vm);
+ }
+
+ /* Unplug any leftovers from previous runs */
+ if (!rc)
+ rc = virtio_mem_unplug_pending_mb(vm);
+
+ if (!rc && vm->requested_size != vm->plugged_size) {
+ if (vm->requested_size > vm->plugged_size) {
+ diff = vm->requested_size - vm->plugged_size;
+ rc = virtio_mem_plug_request(vm, diff);
+ } else {
+ diff = vm->plugged_size - vm->requested_size;
+ rc = virtio_mem_unplug_request(vm, diff);
+ }
+ }
+
+ switch (rc) {
+ case 0:
+ vm->retry_timer_ms = VIRTIO_MEM_RETRY_TIMER_MIN_MS;
+ break;
+ case -ENOSPC:
+ /*
+ * We cannot add any more memory (alignment, physical limit)
+ * or we have too many offline memory blocks.
+ */
+ break;
+ case -ETXTBSY:
+ /*
+ * The hypervisor cannot process our request right now
+ * (e.g., out of memory, migrating);
+ */
+ case -EBUSY:
+ /*
+ * We cannot free up any memory to unplug it (all plugged memory
+ * is busy).
+ */
+ case -ENOMEM:
+ /* Out of memory, try again later. */
+ hrtimer_start(&vm->retry_timer, ms_to_ktime(vm->retry_timer_ms),
+ HRTIMER_MODE_REL);
+ break;
+ case -EAGAIN:
+ /* Retry immediately (e.g., the config changed). */
+ goto retry;
+ default:
+ /* Unknown error, mark as broken */
+ dev_err(&vm->vdev->dev,
+ "unknown error, marking device broken: %d\n", rc);
+ vm->broken = true;
+ }
+}
+
+static enum hrtimer_restart virtio_mem_timer_expired(struct hrtimer *timer)
+{
+ struct virtio_mem *vm = container_of(timer, struct virtio_mem,
+ retry_timer);
+
+ virtio_mem_retry(vm);
+ vm->retry_timer_ms = min_t(unsigned int, vm->retry_timer_ms * 2,
+ VIRTIO_MEM_RETRY_TIMER_MAX_MS);
+ return HRTIMER_NORESTART;
+}
+
+static void virtio_mem_handle_response(struct virtqueue *vq)
+{
+ struct virtio_mem *vm = vq->vdev->priv;
+
+ wake_up(&vm->host_resp);
+}
+
+static int virtio_mem_init_vq(struct virtio_mem *vm)
+{
+ struct virtqueue *vq;
+
+ vq = virtio_find_single_vq(vm->vdev, virtio_mem_handle_response,
+ "guest-request");
+ if (IS_ERR(vq))
+ return PTR_ERR(vq);
+ vm->vq = vq;
+
+ return 0;
+}
+
+static int virtio_mem_init(struct virtio_mem *vm)
+{
+ const uint64_t phys_limit = 1UL << MAX_PHYSMEM_BITS;
+ uint16_t node_id;
+
+ if (!vm->vdev->config->get) {
+ dev_err(&vm->vdev->dev, "config access disabled\n");
+ return -EINVAL;
+ }
+
+ /*
+ * We don't want to (un)plug or reuse any memory when in kdump. The
+ * memory is still accessible (but not mapped).
+ */
+ if (is_kdump_kernel()) {
+ dev_warn(&vm->vdev->dev, "disabled in kdump kernel\n");
+ return -EBUSY;
+ }
+
+ /* Fetch all properties that can't change. */
+ virtio_cread_le(vm->vdev, struct virtio_mem_config, plugged_size,
+ &vm->plugged_size);
+ virtio_cread_le(vm->vdev, struct virtio_mem_config, block_size,
+ &vm->device_block_size);
+ virtio_cread_le(vm->vdev, struct virtio_mem_config, node_id,
+ &node_id);
+ vm->nid = virtio_mem_translate_node_id(vm, node_id);
+ virtio_cread_le(vm->vdev, struct virtio_mem_config, addr, &vm->addr);
+ virtio_cread_le(vm->vdev, struct virtio_mem_config, region_size,
+ &vm->region_size);
+
+ /*
+ * We always hotplug memory in memory block granularity. This way,
+ * we have to wait for exactly one memory block to online.
+ */
+ if (vm->device_block_size > memory_block_size_bytes()) {
+ dev_err(&vm->vdev->dev,
+ "The block size is not supported (too big).\n");
+ return -EINVAL;
+ }
+
+ /* bad device setup - warn only */
+ if (!IS_ALIGNED(vm->addr, memory_block_size_bytes()))
+ dev_warn(&vm->vdev->dev,
+ "The alignment of the physical start address can make some memory unusable.\n");
+ if (!IS_ALIGNED(vm->addr + vm->region_size, memory_block_size_bytes()))
+ dev_warn(&vm->vdev->dev,
+ "The alignment of the physical end address can make some memory unusable.\n");
+ if (vm->addr + vm->region_size > phys_limit)
+ dev_warn(&vm->vdev->dev,
+ "Some memory is not addressable. This can make some memory unusable.\n");
+
+ /*
+ * Calculate the subblock size:
+ * - At least MAX_ORDER - 1 / pageblock_order.
+ * - At least the device block size.
+ * In the worst case, a single subblock per memory block.
+ */
+ vm->subblock_size = PAGE_SIZE * 1ul << max_t(uint32_t, MAX_ORDER - 1,
+ pageblock_order);
+ vm->subblock_size = max_t(uint64_t, vm->device_block_size,
+ vm->subblock_size);
+ vm->nb_sb_per_mb = memory_block_size_bytes() / vm->subblock_size;
+
+ /* Round up to the next full memory block */
+ vm->first_mb_id = virtio_mem_phys_to_mb_id(vm->addr - 1 +
+ memory_block_size_bytes());
+ vm->next_mb_id = vm->first_mb_id;
+ vm->last_mb_id = virtio_mem_phys_to_mb_id(vm->addr +
+ vm->region_size) - 1;
+
+ dev_info(&vm->vdev->dev, "start address: 0x%llx", vm->addr);
+ dev_info(&vm->vdev->dev, "region size: 0x%llx", vm->region_size);
+ dev_info(&vm->vdev->dev, "device block size: 0x%llx",
+ (unsigned long long)vm->device_block_size);
+ dev_info(&vm->vdev->dev, "memory block size: 0x%lx",
+ memory_block_size_bytes());
+ dev_info(&vm->vdev->dev, "subblock size: 0x%llx",
+ (unsigned long long)vm->subblock_size);
+ if (vm->nid != NUMA_NO_NODE)
+ dev_info(&vm->vdev->dev, "nid: %d", vm->nid);
+
+ return 0;
+}
+
+static int virtio_mem_create_resource(struct virtio_mem *vm)
+{
+ /*
+ * When force-unloading the driver and removing the device, we
+ * could have a garbage pointer. Duplicate the string.
+ */
+ const char *name = kstrdup(dev_name(&vm->vdev->dev), GFP_KERNEL);
+
+ if (!name)
+ return -ENOMEM;
+
+ vm->parent_resource = __request_mem_region(vm->addr, vm->region_size,
+ name, IORESOURCE_SYSTEM_RAM);
+ if (!vm->parent_resource) {
+ kfree(name);
+ dev_warn(&vm->vdev->dev, "could not reserve device region\n");
+ dev_info(&vm->vdev->dev,
+ "reloading the driver is not supported\n");
+ return -EBUSY;
+ }
+
+ /* The memory is not actually busy - make add_memory() work. */
+ vm->parent_resource->flags &= ~IORESOURCE_BUSY;
+ return 0;
+}
+
+static void virtio_mem_delete_resource(struct virtio_mem *vm)
+{
+ const char *name;
+
+ if (!vm->parent_resource)
+ return;
+
+ name = vm->parent_resource->name;
+ release_resource(vm->parent_resource);
+ kfree(vm->parent_resource);
+ kfree(name);
+ vm->parent_resource = NULL;
+}
+
+static int virtio_mem_probe(struct virtio_device *vdev)
+{
+ struct virtio_mem *vm;
+ int rc;
+
+ BUILD_BUG_ON(sizeof(struct virtio_mem_req) != 24);
+ BUILD_BUG_ON(sizeof(struct virtio_mem_resp) != 10);
+
+ vdev->priv = vm = kzalloc(sizeof(*vm), GFP_KERNEL);
+ if (!vm)
+ return -ENOMEM;
+
+ init_waitqueue_head(&vm->host_resp);
+ vm->vdev = vdev;
+ INIT_WORK(&vm->wq, virtio_mem_run_wq);
+ mutex_init(&vm->hotplug_mutex);
+ INIT_LIST_HEAD(&vm->next);
+ spin_lock_init(&vm->removal_lock);
+ hrtimer_init(&vm->retry_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
+ vm->retry_timer.function = virtio_mem_timer_expired;
+ vm->retry_timer_ms = VIRTIO_MEM_RETRY_TIMER_MIN_MS;
+
+ /* register the virtqueue */
+ rc = virtio_mem_init_vq(vm);
+ if (rc)
+ goto out_free_vm;
+
+ /* initialize the device by querying the config */
+ rc = virtio_mem_init(vm);
+ if (rc)
+ goto out_del_vq;
+
+ /* create the parent resource for all memory */
+ rc = virtio_mem_create_resource(vm);
+ if (rc)
+ goto out_del_vq;
+
+ /*
+ * If we still have memory plugged, we have to unplug all memory first.
+ * Registering our parent resource makes sure that this memory isn't
+ * actually in use (e.g., trying to reload the driver).
+ */
+ if (vm->plugged_size) {
+ vm->unplug_all_required = 1;
+ dev_info(&vm->vdev->dev, "unplugging all memory is required\n");
+ }
+
+ /* register callbacks */
+ vm->memory_notifier.notifier_call = virtio_mem_memory_notifier_cb;
+ rc = register_memory_notifier(&vm->memory_notifier);
+ if (rc)
+ goto out_del_resource;
+ rc = register_virtio_mem_device(vm);
+ if (rc)
+ goto out_unreg_mem;
+
+ virtio_device_ready(vdev);
+
+ /* trigger a config update to start processing the requested_size */
+ atomic_set(&vm->config_changed, 1);
+ queue_work(system_freezable_wq, &vm->wq);
+
+ return 0;
+out_unreg_mem:
+ unregister_memory_notifier(&vm->memory_notifier);
+out_del_resource:
+ virtio_mem_delete_resource(vm);
+out_del_vq:
+ vdev->config->del_vqs(vdev);
+out_free_vm:
+ kfree(vm);
+ vdev->priv = NULL;
+
+ return rc;
+}
+
+static void virtio_mem_remove(struct virtio_device *vdev)
+{
+ struct virtio_mem *vm = vdev->priv;
+ unsigned long mb_id;
+ int rc;
+
+ /*
+ * Make sure the workqueue won't be triggered anymore and no memory
+ * blocks can be onlined/offlined until we're finished here.
+ */
+ mutex_lock(&vm->hotplug_mutex);
+ spin_lock_irq(&vm->removal_lock);
+ vm->removing = true;
+ spin_unlock_irq(&vm->removal_lock);
+ mutex_unlock(&vm->hotplug_mutex);
+
+ /* wait until the workqueue stopped */
+ cancel_work_sync(&vm->wq);
+ hrtimer_cancel(&vm->retry_timer);
+
+ /*
+ * After we unregistered our callbacks, user space can online partially
+ * plugged offline blocks. Make sure to remove them.
+ */
+ virtio_mem_for_each_mb_state(vm, mb_id,
+ VIRTIO_MEM_MB_STATE_OFFLINE_PARTIAL) {
+ rc = virtio_mem_mb_remove(vm, mb_id);
+ BUG_ON(rc);
+ virtio_mem_mb_set_state(vm, mb_id, VIRTIO_MEM_MB_STATE_UNUSED);
+ }
+ /*
+ * After we unregistered our callbacks, user space can no longer
+ * offline partially plugged online memory blocks. No need to worry
+ * about them.
+ */
+
+ /* unregister callbacks */
+ unregister_virtio_mem_device(vm);
+ unregister_memory_notifier(&vm->memory_notifier);
+
+ /*
+ * There is no way we could reliably remove all memory we have added to
+ * the system. And there is no way to stop the driver/device from going
+ * away. Warn at least.
+ */
+ if (vm->nb_mb_state[VIRTIO_MEM_MB_STATE_OFFLINE] ||
+ vm->nb_mb_state[VIRTIO_MEM_MB_STATE_OFFLINE_PARTIAL] ||
+ vm->nb_mb_state[VIRTIO_MEM_MB_STATE_ONLINE] ||
+ vm->nb_mb_state[VIRTIO_MEM_MB_STATE_ONLINE_PARTIAL]) {
+ dev_warn(&vdev->dev, "device still has system memory added\n");
+ } else {
+ virtio_mem_delete_resource(vm);
+ kfree_const(vm->resource_name);
+ }
+
+ /* remove all tracking data - no locking needed */
+ vfree(vm->mb_state);
+ vfree(vm->sb_bitmap);
+
+ /* reset the device and cleanup the queues */
+ vdev->config->reset(vdev);
+ vdev->config->del_vqs(vdev);
+
+ kfree(vm);
+ vdev->priv = NULL;
+}
+
+static void virtio_mem_config_changed(struct virtio_device *vdev)
+{
+ struct virtio_mem *vm = vdev->priv;
+
+ atomic_set(&vm->config_changed, 1);
+ virtio_mem_retry(vm);
+}
+
+#ifdef CONFIG_PM_SLEEP
+static int virtio_mem_freeze(struct virtio_device *vdev)
+{
+ /*
+ * When restarting the VM, all memory is usually unplugged. Don't
+ * allow to suspend/hibernate.
+ */
+ dev_err(&vdev->dev, "save/restore not supported.\n");
+ return -EPERM;
+}
+
+static int virtio_mem_restore(struct virtio_device *vdev)
+{
+ return -EPERM;
+}
+#endif
+
+static unsigned int virtio_mem_features[] = {
+#if defined(CONFIG_NUMA) && defined(CONFIG_ACPI_NUMA)
+ VIRTIO_MEM_F_ACPI_PXM,
+#endif
+};
+
+static const struct virtio_device_id virtio_mem_id_table[] = {
+ { VIRTIO_ID_MEM, VIRTIO_DEV_ANY_ID },
+ { 0 },
+};
+
+static struct virtio_driver virtio_mem_driver = {
+ .feature_table = virtio_mem_features,
+ .feature_table_size = ARRAY_SIZE(virtio_mem_features),
+ .driver.name = KBUILD_MODNAME,
+ .driver.owner = THIS_MODULE,
+ .id_table = virtio_mem_id_table,
+ .probe = virtio_mem_probe,
+ .remove = virtio_mem_remove,
+ .config_changed = virtio_mem_config_changed,
+#ifdef CONFIG_PM_SLEEP
+ .freeze = virtio_mem_freeze,
+ .restore = virtio_mem_restore,
+#endif
+};
+
+module_virtio_driver(virtio_mem_driver);
+MODULE_DEVICE_TABLE(virtio, virtio_mem_id_table);
+MODULE_AUTHOR("David Hildenbrand <david@redhat.com>");
+MODULE_DESCRIPTION("Virtio-mem driver");
+MODULE_LICENSE("GPL");
diff --git a/drivers/virtio/virtio_mmio.c b/drivers/virtio/virtio_mmio.c
index e09edb5..238383f 100644
--- a/drivers/virtio/virtio_mmio.c
+++ b/drivers/virtio/virtio_mmio.c
@@ -466,10 +466,8 @@
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");
+ if (irq < 0)
return irq;
- }
err = request_irq(irq, vm_interrupt, IRQF_SHARED,
dev_name(&vdev->dev), vm_dev);
@@ -500,6 +498,36 @@
return vm_dev->pdev->name;
}
+static bool vm_get_shm_region(struct virtio_device *vdev,
+ struct virtio_shm_region *region, u8 id)
+{
+ struct virtio_mmio_device *vm_dev = to_virtio_mmio_device(vdev);
+ u64 len, addr;
+
+ /* Select the region we're interested in */
+ writel(id, vm_dev->base + VIRTIO_MMIO_SHM_SEL);
+
+ /* Read the region size */
+ len = (u64) readl(vm_dev->base + VIRTIO_MMIO_SHM_LEN_LOW);
+ len |= (u64) readl(vm_dev->base + VIRTIO_MMIO_SHM_LEN_HIGH) << 32;
+
+ region->len = len;
+
+ /* Check if region length is -1. If that's the case, the shared memory
+ * region does not exist and there is no need to proceed further.
+ */
+ if (len == ~(u64)0)
+ return false;
+
+ /* Read the region base address */
+ addr = (u64) readl(vm_dev->base + VIRTIO_MMIO_SHM_BASE_LOW);
+ addr |= (u64) readl(vm_dev->base + VIRTIO_MMIO_SHM_BASE_HIGH) << 32;
+
+ region->addr = addr;
+
+ return true;
+}
+
static const struct virtio_config_ops virtio_mmio_config_ops = {
.get = vm_get,
.set = vm_set,
@@ -512,6 +540,7 @@
.get_features = vm_get_features,
.finalize_features = vm_finalize_features,
.bus_name = vm_bus_name,
+ .get_shm_region = vm_get_shm_region,
};
@@ -531,18 +560,9 @@
static int virtio_mmio_probe(struct platform_device *pdev)
{
struct virtio_mmio_device *vm_dev;
- struct resource *mem;
unsigned long magic;
int rc;
- mem = platform_get_resource(pdev, IORESOURCE_MEM, 0);
- if (!mem)
- return -EINVAL;
-
- if (!devm_request_mem_region(&pdev->dev, mem->start,
- resource_size(mem), pdev->name))
- return -EBUSY;
-
vm_dev = devm_kzalloc(&pdev->dev, sizeof(*vm_dev), GFP_KERNEL);
if (!vm_dev)
return -ENOMEM;
@@ -554,9 +574,9 @@
INIT_LIST_HEAD(&vm_dev->virtqueues);
spin_lock_init(&vm_dev->lock);
- vm_dev->base = devm_ioremap(&pdev->dev, mem->start, resource_size(mem));
- if (vm_dev->base == NULL)
- return -EFAULT;
+ vm_dev->base = devm_platform_ioremap_resource(pdev, 0);
+ if (IS_ERR(vm_dev->base))
+ return PTR_ERR(vm_dev->base);
/* Check magic value */
magic = readl(vm_dev->base + VIRTIO_MMIO_MAGIC_VALUE);
@@ -652,11 +672,11 @@
&vm_cmdline_id, &consumed);
/*
- * sscanf() must processes at least 2 chunks; also there
+ * sscanf() must process at least 2 chunks; also there
* must be no extra characters after the last chunk, so
* str[consumed] must be '\0'
*/
- if (processed < 2 || str[consumed])
+ if (processed < 2 || str[consumed] || irq == 0)
return -EINVAL;
resources[0].flags = IORESOURCE_MEM;
diff --git a/drivers/virtio/virtio_pci_modern.c b/drivers/virtio/virtio_pci_modern.c
index 7abcc50..3d6ae5a 100644
--- a/drivers/virtio/virtio_pci_modern.c
+++ b/drivers/virtio/virtio_pci_modern.c
@@ -16,6 +16,7 @@
#include <linux/delay.h>
#define VIRTIO_PCI_NO_LEGACY
+#define VIRTIO_RING_NO_LEGACY
#include "virtio_pci_common.h"
/*
@@ -26,16 +27,16 @@
* method, i.e. 32-bit accesses for 32-bit fields, 16-bit accesses
* for 16-bit fields and 8-bit accesses for 8-bit fields.
*/
-static inline u8 vp_ioread8(u8 __iomem *addr)
+static inline u8 vp_ioread8(const u8 __iomem *addr)
{
return ioread8(addr);
}
-static inline u16 vp_ioread16 (__le16 __iomem *addr)
+static inline u16 vp_ioread16 (const __le16 __iomem *addr)
{
return ioread16(addr);
}
-static inline u32 vp_ioread32(__le32 __iomem *addr)
+static inline u32 vp_ioread32(const __le32 __iomem *addr)
{
return ioread32(addr);
}
@@ -443,6 +444,99 @@
vring_del_virtqueue(vq);
}
+static int virtio_pci_find_shm_cap(struct pci_dev *dev, u8 required_id,
+ u8 *bar, u64 *offset, u64 *len)
+{
+ int pos;
+
+ for (pos = pci_find_capability(dev, PCI_CAP_ID_VNDR); pos > 0;
+ pos = pci_find_next_capability(dev, pos, PCI_CAP_ID_VNDR)) {
+ u8 type, cap_len, id;
+ u32 tmp32;
+ u64 res_offset, res_length;
+
+ pci_read_config_byte(dev, pos + offsetof(struct virtio_pci_cap,
+ cfg_type), &type);
+ if (type != VIRTIO_PCI_CAP_SHARED_MEMORY_CFG)
+ continue;
+
+ pci_read_config_byte(dev, pos + offsetof(struct virtio_pci_cap,
+ cap_len), &cap_len);
+ if (cap_len != sizeof(struct virtio_pci_cap64)) {
+ dev_err(&dev->dev, "%s: shm cap with bad size offset:"
+ " %d size: %d\n", __func__, pos, cap_len);
+ continue;
+ }
+
+ pci_read_config_byte(dev, pos + offsetof(struct virtio_pci_cap,
+ id), &id);
+ if (id != required_id)
+ continue;
+
+ /* Type, and ID match, looks good */
+ pci_read_config_byte(dev, pos + offsetof(struct virtio_pci_cap,
+ bar), bar);
+
+ /* Read the lower 32bit of length and offset */
+ pci_read_config_dword(dev, pos + offsetof(struct virtio_pci_cap,
+ offset), &tmp32);
+ res_offset = tmp32;
+ pci_read_config_dword(dev, pos + offsetof(struct virtio_pci_cap,
+ length), &tmp32);
+ res_length = tmp32;
+
+ /* and now the top half */
+ pci_read_config_dword(dev,
+ pos + offsetof(struct virtio_pci_cap64,
+ offset_hi), &tmp32);
+ res_offset |= ((u64)tmp32) << 32;
+ pci_read_config_dword(dev,
+ pos + offsetof(struct virtio_pci_cap64,
+ length_hi), &tmp32);
+ res_length |= ((u64)tmp32) << 32;
+
+ *offset = res_offset;
+ *len = res_length;
+
+ return pos;
+ }
+ return 0;
+}
+
+static bool vp_get_shm_region(struct virtio_device *vdev,
+ struct virtio_shm_region *region, u8 id)
+{
+ struct virtio_pci_device *vp_dev = to_vp_device(vdev);
+ struct pci_dev *pci_dev = vp_dev->pci_dev;
+ u8 bar;
+ u64 offset, len;
+ phys_addr_t phys_addr;
+ size_t bar_len;
+
+ if (!virtio_pci_find_shm_cap(pci_dev, id, &bar, &offset, &len))
+ return false;
+
+ phys_addr = pci_resource_start(pci_dev, bar);
+ bar_len = pci_resource_len(pci_dev, bar);
+
+ if ((offset + len) < offset) {
+ dev_err(&pci_dev->dev, "%s: cap offset+len overflow detected\n",
+ __func__);
+ return false;
+ }
+
+ if (offset + len > bar_len) {
+ dev_err(&pci_dev->dev, "%s: bar shorter than cap offset+len\n",
+ __func__);
+ return false;
+ }
+
+ region->len = len;
+ region->addr = (u64) phys_addr + offset;
+
+ return true;
+}
+
static const struct virtio_config_ops virtio_pci_config_nodev_ops = {
.get = NULL,
.set = NULL,
@@ -457,6 +551,7 @@
.bus_name = vp_bus_name,
.set_vq_affinity = vp_set_vq_affinity,
.get_vq_affinity = vp_get_vq_affinity,
+ .get_shm_region = vp_get_shm_region,
};
static const struct virtio_config_ops virtio_pci_config_ops = {
@@ -473,6 +568,7 @@
.bus_name = vp_bus_name,
.set_vq_affinity = vp_set_vq_affinity,
.get_vq_affinity = vp_get_vq_affinity,
+ .get_shm_region = vp_get_shm_region,
};
/**
@@ -480,6 +576,7 @@
* @dev: the pci device
* @cfg_type: the VIRTIO_PCI_CAP_* value we seek
* @ioresource_types: IORESOURCE_MEM and/or IORESOURCE_IO.
+ * @bars: the bitmask of BARs
*
* Returns offset of the capability, or 0.
*/
diff --git a/drivers/virtio/virtio_ring.c b/drivers/virtio/virtio_ring.c
index e442d40..3cc2a4e 100644
--- a/drivers/virtio/virtio_ring.c
+++ b/drivers/virtio/virtio_ring.c
@@ -240,7 +240,7 @@
static bool vring_use_dma_api(struct virtio_device *vdev)
{
- if (!virtio_has_iommu_quirk(vdev))
+ if (!virtio_has_dma_quirk(vdev))
return true;
/* Otherwise, we are left to guess. */
@@ -263,7 +263,7 @@
size_t max_segment_size = SIZE_MAX;
if (vring_use_dma_api(vdev))
- max_segment_size = dma_max_mapping_size(&vdev->dev);
+ max_segment_size = dma_max_mapping_size(vdev->dev.parent);
return max_segment_size;
}
@@ -424,7 +424,7 @@
struct vring_virtqueue *vq = to_vvq(_vq);
struct scatterlist *sg;
struct vring_desc *desc;
- unsigned int i, n, avail, descs_used, uninitialized_var(prev), err_idx;
+ unsigned int i, n, avail, descs_used, prev, err_idx;
int head;
bool indirect;
@@ -992,6 +992,8 @@
head = vq->packed.next_avail_idx;
desc = alloc_indirect_packed(total_sg, gfp);
+ if (!desc)
+ return -ENOMEM;
if (unlikely(vq->vq.num_free < 1)) {
pr_debug("Can't add buf len 1 - avail = 0\n");
@@ -1101,8 +1103,9 @@
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;
+ __le16 head_flags, flags;
+ u16 head, id, prev, curr, avail_used_flags;
+ int err;
START_USE(vq);
@@ -1118,9 +1121,16 @@
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);
+ if (virtqueue_use_indirect(_vq, total_sg)) {
+ err = virtqueue_add_indirect_packed(vq, sgs, total_sg, out_sgs,
+ in_sgs, data, gfp);
+ if (err != -ENOMEM) {
+ END_USE(vq);
+ return err;
+ }
+
+ /* fall back on direct */
+ }
head = vq->packed.next_avail_idx;
avail_used_flags = vq->packed.avail_used_flags;
@@ -2234,7 +2244,7 @@
break;
case VIRTIO_F_VERSION_1:
break;
- case VIRTIO_F_IOMMU_PLATFORM:
+ case VIRTIO_F_ACCESS_PLATFORM:
break;
case VIRTIO_F_RING_PACKED:
break;
diff --git a/drivers/virtio/virtio_vdpa.c b/drivers/virtio/virtio_vdpa.c
new file mode 100644
index 0000000..3f95ded
--- /dev/null
+++ b/drivers/virtio/virtio_vdpa.c
@@ -0,0 +1,396 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * VIRTIO based driver for vDPA device
+ *
+ * Copyright (c) 2020, Red Hat. All rights reserved.
+ * Author: Jason Wang <jasowang@redhat.com>
+ *
+ */
+
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/device.h>
+#include <linux/kernel.h>
+#include <linux/slab.h>
+#include <linux/uuid.h>
+#include <linux/virtio.h>
+#include <linux/vdpa.h>
+#include <linux/virtio_config.h>
+#include <linux/virtio_ring.h>
+
+#define MOD_VERSION "0.1"
+#define MOD_AUTHOR "Jason Wang <jasowang@redhat.com>"
+#define MOD_DESC "vDPA bus driver for virtio devices"
+#define MOD_LICENSE "GPL v2"
+
+struct virtio_vdpa_device {
+ struct virtio_device vdev;
+ struct vdpa_device *vdpa;
+ u64 features;
+
+ /* The lock to protect virtqueue list */
+ spinlock_t lock;
+ /* List of virtio_vdpa_vq_info */
+ struct list_head virtqueues;
+};
+
+struct virtio_vdpa_vq_info {
+ /* the actual virtqueue */
+ struct virtqueue *vq;
+
+ /* the list node for the virtqueues list */
+ struct list_head node;
+};
+
+static inline struct virtio_vdpa_device *
+to_virtio_vdpa_device(struct virtio_device *dev)
+{
+ return container_of(dev, struct virtio_vdpa_device, vdev);
+}
+
+static struct vdpa_device *vd_get_vdpa(struct virtio_device *vdev)
+{
+ return to_virtio_vdpa_device(vdev)->vdpa;
+}
+
+static void virtio_vdpa_get(struct virtio_device *vdev, unsigned offset,
+ void *buf, unsigned len)
+{
+ struct vdpa_device *vdpa = vd_get_vdpa(vdev);
+
+ vdpa_get_config(vdpa, offset, buf, len);
+}
+
+static void virtio_vdpa_set(struct virtio_device *vdev, unsigned offset,
+ const void *buf, unsigned len)
+{
+ struct vdpa_device *vdpa = vd_get_vdpa(vdev);
+ const struct vdpa_config_ops *ops = vdpa->config;
+
+ ops->set_config(vdpa, offset, buf, len);
+}
+
+static u32 virtio_vdpa_generation(struct virtio_device *vdev)
+{
+ struct vdpa_device *vdpa = vd_get_vdpa(vdev);
+ const struct vdpa_config_ops *ops = vdpa->config;
+
+ if (ops->get_generation)
+ return ops->get_generation(vdpa);
+
+ return 0;
+}
+
+static u8 virtio_vdpa_get_status(struct virtio_device *vdev)
+{
+ struct vdpa_device *vdpa = vd_get_vdpa(vdev);
+ const struct vdpa_config_ops *ops = vdpa->config;
+
+ return ops->get_status(vdpa);
+}
+
+static void virtio_vdpa_set_status(struct virtio_device *vdev, u8 status)
+{
+ struct vdpa_device *vdpa = vd_get_vdpa(vdev);
+ const struct vdpa_config_ops *ops = vdpa->config;
+
+ return ops->set_status(vdpa, status);
+}
+
+static void virtio_vdpa_reset(struct virtio_device *vdev)
+{
+ struct vdpa_device *vdpa = vd_get_vdpa(vdev);
+
+ vdpa_reset(vdpa);
+}
+
+static bool virtio_vdpa_notify(struct virtqueue *vq)
+{
+ struct vdpa_device *vdpa = vd_get_vdpa(vq->vdev);
+ const struct vdpa_config_ops *ops = vdpa->config;
+
+ ops->kick_vq(vdpa, vq->index);
+
+ return true;
+}
+
+static irqreturn_t virtio_vdpa_config_cb(void *private)
+{
+ struct virtio_vdpa_device *vd_dev = private;
+
+ virtio_config_changed(&vd_dev->vdev);
+
+ return IRQ_HANDLED;
+}
+
+static irqreturn_t virtio_vdpa_virtqueue_cb(void *private)
+{
+ struct virtio_vdpa_vq_info *info = private;
+
+ return vring_interrupt(0, info->vq);
+}
+
+static struct virtqueue *
+virtio_vdpa_setup_vq(struct virtio_device *vdev, unsigned int index,
+ void (*callback)(struct virtqueue *vq),
+ const char *name, bool ctx)
+{
+ struct virtio_vdpa_device *vd_dev = to_virtio_vdpa_device(vdev);
+ struct vdpa_device *vdpa = vd_get_vdpa(vdev);
+ const struct vdpa_config_ops *ops = vdpa->config;
+ struct virtio_vdpa_vq_info *info;
+ struct vdpa_callback cb;
+ struct virtqueue *vq;
+ u64 desc_addr, driver_addr, device_addr;
+ unsigned long flags;
+ u32 align, num;
+ int err;
+
+ if (!name)
+ return NULL;
+
+ if (index >= vdpa->nvqs)
+ return ERR_PTR(-ENOENT);
+
+ /* Queue shouldn't already be set up. */
+ if (ops->get_vq_ready(vdpa, index))
+ return ERR_PTR(-ENOENT);
+
+ /* Allocate and fill out our active queue description */
+ info = kmalloc(sizeof(*info), GFP_KERNEL);
+ if (!info)
+ return ERR_PTR(-ENOMEM);
+
+ num = ops->get_vq_num_max(vdpa);
+ if (num == 0) {
+ err = -ENOENT;
+ goto error_new_virtqueue;
+ }
+
+ /* Create the vring */
+ align = ops->get_vq_align(vdpa);
+ vq = vring_create_virtqueue(index, num, align, vdev,
+ true, true, ctx,
+ virtio_vdpa_notify, callback, name);
+ if (!vq) {
+ err = -ENOMEM;
+ goto error_new_virtqueue;
+ }
+
+ /* Setup virtqueue callback */
+ cb.callback = virtio_vdpa_virtqueue_cb;
+ cb.private = info;
+ ops->set_vq_cb(vdpa, index, &cb);
+ ops->set_vq_num(vdpa, index, virtqueue_get_vring_size(vq));
+
+ desc_addr = virtqueue_get_desc_addr(vq);
+ driver_addr = virtqueue_get_avail_addr(vq);
+ device_addr = virtqueue_get_used_addr(vq);
+
+ if (ops->set_vq_address(vdpa, index,
+ desc_addr, driver_addr,
+ device_addr)) {
+ err = -EINVAL;
+ goto err_vq;
+ }
+
+ ops->set_vq_ready(vdpa, index, 1);
+
+ vq->priv = info;
+ info->vq = vq;
+
+ spin_lock_irqsave(&vd_dev->lock, flags);
+ list_add(&info->node, &vd_dev->virtqueues);
+ spin_unlock_irqrestore(&vd_dev->lock, flags);
+
+ return vq;
+
+err_vq:
+ vring_del_virtqueue(vq);
+error_new_virtqueue:
+ ops->set_vq_ready(vdpa, index, 0);
+ /* VDPA driver should make sure vq is stopeed here */
+ WARN_ON(ops->get_vq_ready(vdpa, index));
+ kfree(info);
+ return ERR_PTR(err);
+}
+
+static void virtio_vdpa_del_vq(struct virtqueue *vq)
+{
+ struct virtio_vdpa_device *vd_dev = to_virtio_vdpa_device(vq->vdev);
+ struct vdpa_device *vdpa = vd_dev->vdpa;
+ const struct vdpa_config_ops *ops = vdpa->config;
+ struct virtio_vdpa_vq_info *info = vq->priv;
+ unsigned int index = vq->index;
+ unsigned long flags;
+
+ spin_lock_irqsave(&vd_dev->lock, flags);
+ list_del(&info->node);
+ spin_unlock_irqrestore(&vd_dev->lock, flags);
+
+ /* Select and deactivate the queue */
+ ops->set_vq_ready(vdpa, index, 0);
+ WARN_ON(ops->get_vq_ready(vdpa, index));
+
+ vring_del_virtqueue(vq);
+
+ kfree(info);
+}
+
+static void virtio_vdpa_del_vqs(struct virtio_device *vdev)
+{
+ struct virtqueue *vq, *n;
+
+ list_for_each_entry_safe(vq, n, &vdev->vqs, list)
+ virtio_vdpa_del_vq(vq);
+}
+
+static int virtio_vdpa_find_vqs(struct virtio_device *vdev, unsigned nvqs,
+ struct virtqueue *vqs[],
+ vq_callback_t *callbacks[],
+ const char * const names[],
+ const bool *ctx,
+ struct irq_affinity *desc)
+{
+ struct virtio_vdpa_device *vd_dev = to_virtio_vdpa_device(vdev);
+ struct vdpa_device *vdpa = vd_get_vdpa(vdev);
+ const struct vdpa_config_ops *ops = vdpa->config;
+ struct vdpa_callback cb;
+ int i, err, queue_idx = 0;
+
+ for (i = 0; i < nvqs; ++i) {
+ if (!names[i]) {
+ vqs[i] = NULL;
+ continue;
+ }
+
+ vqs[i] = virtio_vdpa_setup_vq(vdev, queue_idx++,
+ callbacks[i], names[i], ctx ?
+ ctx[i] : false);
+ if (IS_ERR(vqs[i])) {
+ err = PTR_ERR(vqs[i]);
+ goto err_setup_vq;
+ }
+ }
+
+ cb.callback = virtio_vdpa_config_cb;
+ cb.private = vd_dev;
+ ops->set_config_cb(vdpa, &cb);
+
+ return 0;
+
+err_setup_vq:
+ virtio_vdpa_del_vqs(vdev);
+ return err;
+}
+
+static u64 virtio_vdpa_get_features(struct virtio_device *vdev)
+{
+ struct vdpa_device *vdpa = vd_get_vdpa(vdev);
+ const struct vdpa_config_ops *ops = vdpa->config;
+
+ return ops->get_features(vdpa);
+}
+
+static int virtio_vdpa_finalize_features(struct virtio_device *vdev)
+{
+ struct vdpa_device *vdpa = vd_get_vdpa(vdev);
+
+ /* Give virtio_ring a chance to accept features. */
+ vring_transport_features(vdev);
+
+ return vdpa_set_features(vdpa, vdev->features);
+}
+
+static const char *virtio_vdpa_bus_name(struct virtio_device *vdev)
+{
+ struct virtio_vdpa_device *vd_dev = to_virtio_vdpa_device(vdev);
+ struct vdpa_device *vdpa = vd_dev->vdpa;
+
+ return dev_name(&vdpa->dev);
+}
+
+static const struct virtio_config_ops virtio_vdpa_config_ops = {
+ .get = virtio_vdpa_get,
+ .set = virtio_vdpa_set,
+ .generation = virtio_vdpa_generation,
+ .get_status = virtio_vdpa_get_status,
+ .set_status = virtio_vdpa_set_status,
+ .reset = virtio_vdpa_reset,
+ .find_vqs = virtio_vdpa_find_vqs,
+ .del_vqs = virtio_vdpa_del_vqs,
+ .get_features = virtio_vdpa_get_features,
+ .finalize_features = virtio_vdpa_finalize_features,
+ .bus_name = virtio_vdpa_bus_name,
+};
+
+static void virtio_vdpa_release_dev(struct device *_d)
+{
+ struct virtio_device *vdev =
+ container_of(_d, struct virtio_device, dev);
+ struct virtio_vdpa_device *vd_dev =
+ container_of(vdev, struct virtio_vdpa_device, vdev);
+
+ kfree(vd_dev);
+}
+
+static int virtio_vdpa_probe(struct vdpa_device *vdpa)
+{
+ const struct vdpa_config_ops *ops = vdpa->config;
+ struct virtio_vdpa_device *vd_dev, *reg_dev = NULL;
+ int ret = -EINVAL;
+
+ vd_dev = kzalloc(sizeof(*vd_dev), GFP_KERNEL);
+ if (!vd_dev)
+ return -ENOMEM;
+
+ vd_dev->vdev.dev.parent = vdpa_get_dma_dev(vdpa);
+ vd_dev->vdev.dev.release = virtio_vdpa_release_dev;
+ vd_dev->vdev.config = &virtio_vdpa_config_ops;
+ vd_dev->vdpa = vdpa;
+ INIT_LIST_HEAD(&vd_dev->virtqueues);
+ spin_lock_init(&vd_dev->lock);
+
+ vd_dev->vdev.id.device = ops->get_device_id(vdpa);
+ if (vd_dev->vdev.id.device == 0)
+ goto err;
+
+ vd_dev->vdev.id.vendor = ops->get_vendor_id(vdpa);
+ ret = register_virtio_device(&vd_dev->vdev);
+ reg_dev = vd_dev;
+ if (ret)
+ goto err;
+
+ vdpa_set_drvdata(vdpa, vd_dev);
+
+ return 0;
+
+err:
+ if (reg_dev)
+ put_device(&vd_dev->vdev.dev);
+ else
+ kfree(vd_dev);
+ return ret;
+}
+
+static void virtio_vdpa_remove(struct vdpa_device *vdpa)
+{
+ struct virtio_vdpa_device *vd_dev = vdpa_get_drvdata(vdpa);
+
+ unregister_virtio_device(&vd_dev->vdev);
+}
+
+static struct vdpa_driver virtio_vdpa_driver = {
+ .driver = {
+ .name = "virtio_vdpa",
+ },
+ .probe = virtio_vdpa_probe,
+ .remove = virtio_vdpa_remove,
+};
+
+module_vdpa_driver(virtio_vdpa_driver);
+
+MODULE_VERSION(MOD_VERSION);
+MODULE_LICENSE(MOD_LICENSE);
+MODULE_AUTHOR(MOD_AUTHOR);
+MODULE_DESCRIPTION(MOD_DESC);