OpenCloudOS-Kernel/drivers/virtio/virtio.c

572 lines
14 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0-only
#include <linux/virtio.h>
#include <linux/spinlock.h>
#include <linux/virtio_config.h>
#include <linux/virtio_anchor.h>
#include <linux/module.h>
#include <linux/idr.h>
#include <linux/of.h>
#include <uapi/linux/virtio_ids.h>
/* Unique numbering for virtio devices. */
static DEFINE_IDA(virtio_index_ida);
static ssize_t device_show(struct device *_d,
struct device_attribute *attr, char *buf)
{
struct virtio_device *dev = dev_to_virtio(_d);
return sprintf(buf, "0x%04x\n", dev->id.device);
}
static DEVICE_ATTR_RO(device);
static ssize_t vendor_show(struct device *_d,
struct device_attribute *attr, char *buf)
{
struct virtio_device *dev = dev_to_virtio(_d);
return sprintf(buf, "0x%04x\n", dev->id.vendor);
}
static DEVICE_ATTR_RO(vendor);
static ssize_t status_show(struct device *_d,
struct device_attribute *attr, char *buf)
{
struct virtio_device *dev = dev_to_virtio(_d);
return sprintf(buf, "0x%08x\n", dev->config->get_status(dev));
}
static DEVICE_ATTR_RO(status);
static ssize_t modalias_show(struct device *_d,
struct device_attribute *attr, char *buf)
{
struct virtio_device *dev = dev_to_virtio(_d);
return sprintf(buf, "virtio:d%08Xv%08X\n",
dev->id.device, dev->id.vendor);
}
static DEVICE_ATTR_RO(modalias);
static ssize_t features_show(struct device *_d,
struct device_attribute *attr, char *buf)
{
struct virtio_device *dev = dev_to_virtio(_d);
unsigned int i;
ssize_t len = 0;
/* We actually represent this as a bitstring, as it could be
* arbitrary length in future. */
for (i = 0; i < sizeof(dev->features)*8; i++)
len += sprintf(buf+len, "%c",
__virtio_test_bit(dev, i) ? '1' : '0');
len += sprintf(buf+len, "\n");
return len;
}
static DEVICE_ATTR_RO(features);
static struct attribute *virtio_dev_attrs[] = {
&dev_attr_device.attr,
&dev_attr_vendor.attr,
&dev_attr_status.attr,
&dev_attr_modalias.attr,
&dev_attr_features.attr,
NULL,
};
ATTRIBUTE_GROUPS(virtio_dev);
static inline int virtio_id_match(const struct virtio_device *dev,
const struct virtio_device_id *id)
{
if (id->device != dev->id.device && id->device != VIRTIO_DEV_ANY_ID)
return 0;
return id->vendor == VIRTIO_DEV_ANY_ID || id->vendor == dev->id.vendor;
}
/* This looks through all the IDs a driver claims to support. If any of them
* match, we return 1 and the kernel will call virtio_dev_probe(). */
static int virtio_dev_match(struct device *_dv, struct device_driver *_dr)
{
unsigned int i;
struct virtio_device *dev = dev_to_virtio(_dv);
const struct virtio_device_id *ids;
ids = drv_to_virtio(_dr)->id_table;
for (i = 0; ids[i].device; i++)
if (virtio_id_match(dev, &ids[i]))
return 1;
return 0;
}
static int virtio_uevent(struct device *_dv, struct kobj_uevent_env *env)
{
struct virtio_device *dev = dev_to_virtio(_dv);
return add_uevent_var(env, "MODALIAS=virtio:d%08Xv%08X",
dev->id.device, dev->id.vendor);
}
void virtio_check_driver_offered_feature(const struct virtio_device *vdev,
unsigned int fbit)
{
unsigned int i;
struct virtio_driver *drv = drv_to_virtio(vdev->dev.driver);
for (i = 0; i < drv->feature_table_size; i++)
if (drv->feature_table[i] == fbit)
return;
if (drv->feature_table_legacy) {
for (i = 0; i < drv->feature_table_size_legacy; i++)
if (drv->feature_table_legacy[i] == fbit)
return;
}
BUG();
}
EXPORT_SYMBOL_GPL(virtio_check_driver_offered_feature);
static void __virtio_config_changed(struct virtio_device *dev)
{
struct virtio_driver *drv = drv_to_virtio(dev->dev.driver);
if (!dev->config_enabled)
dev->config_change_pending = true;
else if (drv && drv->config_changed)
drv->config_changed(dev);
}
void virtio_config_changed(struct virtio_device *dev)
{
unsigned long flags;
spin_lock_irqsave(&dev->config_lock, flags);
__virtio_config_changed(dev);
spin_unlock_irqrestore(&dev->config_lock, flags);
}
EXPORT_SYMBOL_GPL(virtio_config_changed);
static void virtio_config_disable(struct virtio_device *dev)
{
spin_lock_irq(&dev->config_lock);
dev->config_enabled = false;
spin_unlock_irq(&dev->config_lock);
}
static void virtio_config_enable(struct virtio_device *dev)
{
spin_lock_irq(&dev->config_lock);
dev->config_enabled = true;
if (dev->config_change_pending)
__virtio_config_changed(dev);
dev->config_change_pending = false;
spin_unlock_irq(&dev->config_lock);
}
void virtio_add_status(struct virtio_device *dev, unsigned int status)
{
might_sleep();
dev->config->set_status(dev, dev->config->get_status(dev) | status);
}
EXPORT_SYMBOL_GPL(virtio_add_status);
virtio: acknowledge all features before access The feature negotiation was designed in a way that makes it possible for devices to know which config fields will be accessed by drivers. This is broken since commit 404123c2db79 ("virtio: allow drivers to validate features") with fallout in at least block and net. We have a partial work-around in commit 2f9a174f918e ("virtio: write back F_VERSION_1 before validate") which at least lets devices find out which format should config space have, but this is a partial fix: guests should not access config space without acknowledging features since otherwise we'll never be able to change the config space format. To fix, split finalize_features from virtio_finalize_features and call finalize_features with all feature bits before validation, and then - if validation changed any bits - once again after. Since virtio_finalize_features no longer writes out features rename it to virtio_features_ok - since that is what it does: checks that features are ok with the device. As a side effect, this also reduces the amount of hypervisor accesses - we now only acknowledge features once unless we are clearing any features when validating (which is uncommon). IRC I think that this was more or less always the intent in the spec but unfortunately the way the spec is worded does not say this explicitly, I plan to address this at the spec level, too. Acked-by: Jason Wang <jasowang@redhat.com> Cc: stable@vger.kernel.org Fixes: 404123c2db79 ("virtio: allow drivers to validate features") Fixes: 2f9a174f918e ("virtio: write back F_VERSION_1 before validate") Cc: "Halil Pasic" <pasic@linux.ibm.com> Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
2022-01-15 03:58:41 +08:00
/* Do some validation, then set FEATURES_OK */
static int virtio_features_ok(struct virtio_device *dev)
{
unsigned int status;
might_sleep();
if (virtio_check_mem_acc_cb(dev)) {
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;
virtio_add_status(dev, VIRTIO_CONFIG_S_FEATURES_OK);
status = dev->config->get_status(dev);
if (!(status & VIRTIO_CONFIG_S_FEATURES_OK)) {
dev_err(&dev->dev, "virtio: device refuses features: %x\n",
status);
return -ENODEV;
}
return 0;
}
/**
* virtio_reset_device - quiesce device for removal
* @dev: the device to reset
*
* Prevents device from sending interrupts and accessing memory.
*
* Generally used for cleanup during driver / device removal.
*
* Once this has been invoked, caller must ensure that
* virtqueue_notify / virtqueue_kick are not in progress.
*
* Note: this guarantees that vq callbacks are not in progress, however caller
* is responsible for preventing access from other contexts, such as a system
* call/workqueue/bh. Invoking virtio_break_device then flushing any such
* contexts is one way to handle that.
* */
void virtio_reset_device(struct virtio_device *dev)
{
#ifdef CONFIG_VIRTIO_HARDEN_NOTIFICATION
virtio: harden vring IRQ This is a rework on the previous IRQ hardening that is done for virtio-pci where several drawbacks were found and were reverted: 1) try to use IRQF_NO_AUTOEN which is not friendly to affinity managed IRQ that is used by some device such as virtio-blk 2) done only for PCI transport The vq->broken is re-used in this patch for implementing the IRQ hardening. The vq->broken is set to true during both initialization and reset. And the vq->broken is set to false in virtio_device_ready(). Then vring_interrupt() can check and return when vq->broken is true. And in this case, switch to return IRQ_NONE to let the interrupt core aware of such invalid interrupt to prevent IRQ storm. The reason of using a per queue variable instead of a per device one is that we may need it for per queue reset hardening in the future. Note that the hardening is only done for vring interrupt since the config interrupt hardening is already done in commit 22b7050a024d7 ("virtio: defer config changed notifications"). But the method that is used by config interrupt can't be reused by the vring interrupt handler because it uses spinlock to do the synchronization which is expensive. Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Peter Zijlstra <peterz@infradead.org> Cc: "Paul E. McKenney" <paulmck@kernel.org> Cc: Marc Zyngier <maz@kernel.org> Cc: Halil Pasic <pasic@linux.ibm.com> Cc: Cornelia Huck <cohuck@redhat.com> Cc: Vineeth Vijayan <vneethv@linux.ibm.com> Cc: Peter Oberparleiter <oberpar@linux.ibm.com> Cc: linux-s390@vger.kernel.org Signed-off-by: Jason Wang <jasowang@redhat.com> Message-Id: <20220527060120.20964-9-jasowang@redhat.com> Signed-off-by: Michael S. Tsirkin <mst@redhat.com> Reviewed-by: Xuan Zhuo <xuanzhuo@linux.alibaba.com>
2022-05-27 14:01:19 +08:00
/*
* The below virtio_synchronize_cbs() guarantees that any
* interrupt for this line arriving after
* virtio_synchronize_vqs() has completed is guaranteed to see
* vq->broken as true.
*/
virtio_break_device(dev);
virtio_synchronize_cbs(dev);
#endif
virtio: harden vring IRQ This is a rework on the previous IRQ hardening that is done for virtio-pci where several drawbacks were found and were reverted: 1) try to use IRQF_NO_AUTOEN which is not friendly to affinity managed IRQ that is used by some device such as virtio-blk 2) done only for PCI transport The vq->broken is re-used in this patch for implementing the IRQ hardening. The vq->broken is set to true during both initialization and reset. And the vq->broken is set to false in virtio_device_ready(). Then vring_interrupt() can check and return when vq->broken is true. And in this case, switch to return IRQ_NONE to let the interrupt core aware of such invalid interrupt to prevent IRQ storm. The reason of using a per queue variable instead of a per device one is that we may need it for per queue reset hardening in the future. Note that the hardening is only done for vring interrupt since the config interrupt hardening is already done in commit 22b7050a024d7 ("virtio: defer config changed notifications"). But the method that is used by config interrupt can't be reused by the vring interrupt handler because it uses spinlock to do the synchronization which is expensive. Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Peter Zijlstra <peterz@infradead.org> Cc: "Paul E. McKenney" <paulmck@kernel.org> Cc: Marc Zyngier <maz@kernel.org> Cc: Halil Pasic <pasic@linux.ibm.com> Cc: Cornelia Huck <cohuck@redhat.com> Cc: Vineeth Vijayan <vneethv@linux.ibm.com> Cc: Peter Oberparleiter <oberpar@linux.ibm.com> Cc: linux-s390@vger.kernel.org Signed-off-by: Jason Wang <jasowang@redhat.com> Message-Id: <20220527060120.20964-9-jasowang@redhat.com> Signed-off-by: Michael S. Tsirkin <mst@redhat.com> Reviewed-by: Xuan Zhuo <xuanzhuo@linux.alibaba.com>
2022-05-27 14:01:19 +08:00
dev->config->reset(dev);
}
EXPORT_SYMBOL_GPL(virtio_reset_device);
static int virtio_dev_probe(struct device *_d)
{
int err, i;
struct virtio_device *dev = dev_to_virtio(_d);
struct virtio_driver *drv = drv_to_virtio(dev->dev.driver);
u64 device_features;
u64 driver_features;
u64 driver_features_legacy;
/* We have a driver! */
virtio_add_status(dev, VIRTIO_CONFIG_S_DRIVER);
/* Figure out what features the device supports. */
device_features = dev->config->get_features(dev);
/* Figure out what features the driver supports. */
driver_features = 0;
for (i = 0; i < drv->feature_table_size; i++) {
unsigned int f = drv->feature_table[i];
BUG_ON(f >= 64);
driver_features |= (1ULL << f);
}
/* Some drivers have a separate feature table for virtio v1.0 */
if (drv->feature_table_legacy) {
driver_features_legacy = 0;
for (i = 0; i < drv->feature_table_size_legacy; i++) {
unsigned int f = drv->feature_table_legacy[i];
BUG_ON(f >= 64);
driver_features_legacy |= (1ULL << f);
}
} else {
driver_features_legacy = driver_features;
}
if (device_features & (1ULL << VIRTIO_F_VERSION_1))
dev->features = driver_features & device_features;
else
dev->features = driver_features_legacy & device_features;
/* Transport features always preserved to pass to finalize_features. */
for (i = VIRTIO_TRANSPORT_F_START; i < VIRTIO_TRANSPORT_F_END; i++)
if (device_features & (1ULL << i))
__virtio_set_bit(dev, i);
virtio: acknowledge all features before access The feature negotiation was designed in a way that makes it possible for devices to know which config fields will be accessed by drivers. This is broken since commit 404123c2db79 ("virtio: allow drivers to validate features") with fallout in at least block and net. We have a partial work-around in commit 2f9a174f918e ("virtio: write back F_VERSION_1 before validate") which at least lets devices find out which format should config space have, but this is a partial fix: guests should not access config space without acknowledging features since otherwise we'll never be able to change the config space format. To fix, split finalize_features from virtio_finalize_features and call finalize_features with all feature bits before validation, and then - if validation changed any bits - once again after. Since virtio_finalize_features no longer writes out features rename it to virtio_features_ok - since that is what it does: checks that features are ok with the device. As a side effect, this also reduces the amount of hypervisor accesses - we now only acknowledge features once unless we are clearing any features when validating (which is uncommon). IRC I think that this was more or less always the intent in the spec but unfortunately the way the spec is worded does not say this explicitly, I plan to address this at the spec level, too. Acked-by: Jason Wang <jasowang@redhat.com> Cc: stable@vger.kernel.org Fixes: 404123c2db79 ("virtio: allow drivers to validate features") Fixes: 2f9a174f918e ("virtio: write back F_VERSION_1 before validate") Cc: "Halil Pasic" <pasic@linux.ibm.com> Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
2022-01-15 03:58:41 +08:00
err = dev->config->finalize_features(dev);
if (err)
goto err;
if (drv->validate) {
virtio: acknowledge all features before access The feature negotiation was designed in a way that makes it possible for devices to know which config fields will be accessed by drivers. This is broken since commit 404123c2db79 ("virtio: allow drivers to validate features") with fallout in at least block and net. We have a partial work-around in commit 2f9a174f918e ("virtio: write back F_VERSION_1 before validate") which at least lets devices find out which format should config space have, but this is a partial fix: guests should not access config space without acknowledging features since otherwise we'll never be able to change the config space format. To fix, split finalize_features from virtio_finalize_features and call finalize_features with all feature bits before validation, and then - if validation changed any bits - once again after. Since virtio_finalize_features no longer writes out features rename it to virtio_features_ok - since that is what it does: checks that features are ok with the device. As a side effect, this also reduces the amount of hypervisor accesses - we now only acknowledge features once unless we are clearing any features when validating (which is uncommon). IRC I think that this was more or less always the intent in the spec but unfortunately the way the spec is worded does not say this explicitly, I plan to address this at the spec level, too. Acked-by: Jason Wang <jasowang@redhat.com> Cc: stable@vger.kernel.org Fixes: 404123c2db79 ("virtio: allow drivers to validate features") Fixes: 2f9a174f918e ("virtio: write back F_VERSION_1 before validate") Cc: "Halil Pasic" <pasic@linux.ibm.com> Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
2022-01-15 03:58:41 +08:00
u64 features = dev->features;
err = drv->validate(dev);
if (err)
goto err;
virtio: acknowledge all features before access The feature negotiation was designed in a way that makes it possible for devices to know which config fields will be accessed by drivers. This is broken since commit 404123c2db79 ("virtio: allow drivers to validate features") with fallout in at least block and net. We have a partial work-around in commit 2f9a174f918e ("virtio: write back F_VERSION_1 before validate") which at least lets devices find out which format should config space have, but this is a partial fix: guests should not access config space without acknowledging features since otherwise we'll never be able to change the config space format. To fix, split finalize_features from virtio_finalize_features and call finalize_features with all feature bits before validation, and then - if validation changed any bits - once again after. Since virtio_finalize_features no longer writes out features rename it to virtio_features_ok - since that is what it does: checks that features are ok with the device. As a side effect, this also reduces the amount of hypervisor accesses - we now only acknowledge features once unless we are clearing any features when validating (which is uncommon). IRC I think that this was more or less always the intent in the spec but unfortunately the way the spec is worded does not say this explicitly, I plan to address this at the spec level, too. Acked-by: Jason Wang <jasowang@redhat.com> Cc: stable@vger.kernel.org Fixes: 404123c2db79 ("virtio: allow drivers to validate features") Fixes: 2f9a174f918e ("virtio: write back F_VERSION_1 before validate") Cc: "Halil Pasic" <pasic@linux.ibm.com> Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
2022-01-15 03:58:41 +08:00
/* Did validation change any features? Then write them again. */
if (features != dev->features) {
err = dev->config->finalize_features(dev);
if (err)
goto err;
}
}
virtio: acknowledge all features before access The feature negotiation was designed in a way that makes it possible for devices to know which config fields will be accessed by drivers. This is broken since commit 404123c2db79 ("virtio: allow drivers to validate features") with fallout in at least block and net. We have a partial work-around in commit 2f9a174f918e ("virtio: write back F_VERSION_1 before validate") which at least lets devices find out which format should config space have, but this is a partial fix: guests should not access config space without acknowledging features since otherwise we'll never be able to change the config space format. To fix, split finalize_features from virtio_finalize_features and call finalize_features with all feature bits before validation, and then - if validation changed any bits - once again after. Since virtio_finalize_features no longer writes out features rename it to virtio_features_ok - since that is what it does: checks that features are ok with the device. As a side effect, this also reduces the amount of hypervisor accesses - we now only acknowledge features once unless we are clearing any features when validating (which is uncommon). IRC I think that this was more or less always the intent in the spec but unfortunately the way the spec is worded does not say this explicitly, I plan to address this at the spec level, too. Acked-by: Jason Wang <jasowang@redhat.com> Cc: stable@vger.kernel.org Fixes: 404123c2db79 ("virtio: allow drivers to validate features") Fixes: 2f9a174f918e ("virtio: write back F_VERSION_1 before validate") Cc: "Halil Pasic" <pasic@linux.ibm.com> Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
2022-01-15 03:58:41 +08:00
err = virtio_features_ok(dev);
if (err)
goto err;
err = drv->probe(dev);
if (err)
goto err;
/* If probe didn't do it, mark device DRIVER_OK ourselves. */
if (!(dev->config->get_status(dev) & VIRTIO_CONFIG_S_DRIVER_OK))
virtio_device_ready(dev);
if (drv->scan)
drv->scan(dev);
virtio_config_enable(dev);
return 0;
err:
virtio_add_status(dev, VIRTIO_CONFIG_S_FAILED);
return err;
}
bus: Make remove callback return void The driver core ignores the return value of this callback because there is only little it can do when a device disappears. This is the final bit of a long lasting cleanup quest where several buses were converted to also return void from their remove callback. Additionally some resource leaks were fixed that were caused by drivers returning an error code in the expectation that the driver won't go away. With struct bus_type::remove returning void it's prevented that newly implemented buses return an ignored error code and so don't anticipate wrong expectations for driver authors. Reviewed-by: Tom Rix <trix@redhat.com> (For fpga) Reviewed-by: Mathieu Poirier <mathieu.poirier@linaro.org> Reviewed-by: Cornelia Huck <cohuck@redhat.com> (For drivers/s390 and drivers/vfio) Acked-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk> (For ARM, Amba and related parts) Acked-by: Mark Brown <broonie@kernel.org> Acked-by: Chen-Yu Tsai <wens@csie.org> (for sunxi-rsb) Acked-by: Pali Rohár <pali@kernel.org> Acked-by: Mauro Carvalho Chehab <mchehab@kernel.org> (for media) Acked-by: Hans de Goede <hdegoede@redhat.com> (For drivers/platform) Acked-by: Alexandre Belloni <alexandre.belloni@bootlin.com> Acked-By: Vinod Koul <vkoul@kernel.org> Acked-by: Juergen Gross <jgross@suse.com> (For xen) Acked-by: Lee Jones <lee.jones@linaro.org> (For mfd) Acked-by: Johannes Thumshirn <jth@kernel.org> (For mcb) Acked-by: Johan Hovold <johan@kernel.org> Acked-by: Srinivas Kandagatla <srinivas.kandagatla@linaro.org> (For slimbus) Acked-by: Kirti Wankhede <kwankhede@nvidia.com> (For vfio) Acked-by: Maximilian Luz <luzmaximilian@gmail.com> Acked-by: Heikki Krogerus <heikki.krogerus@linux.intel.com> (For ulpi and typec) Acked-by: Samuel Iglesias Gonsálvez <siglesias@igalia.com> (For ipack) Acked-by: Geoff Levand <geoff@infradead.org> (For ps3) Acked-by: Yehezkel Bernat <YehezkelShB@gmail.com> (For thunderbolt) Acked-by: Alexander Shishkin <alexander.shishkin@linux.intel.com> (For intel_th) Acked-by: Dominik Brodowski <linux@dominikbrodowski.net> (For pcmcia) Acked-by: Rafael J. Wysocki <rafael@kernel.org> (For ACPI) Acked-by: Bjorn Andersson <bjorn.andersson@linaro.org> (rpmsg and apr) Acked-by: Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com> (For intel-ish-hid) Acked-by: Dan Williams <dan.j.williams@intel.com> (For CXL, DAX, and NVDIMM) Acked-by: William Breathitt Gray <vilhelm.gray@gmail.com> (For isa) Acked-by: Stefan Richter <stefanr@s5r6.in-berlin.de> (For firewire) Acked-by: Benjamin Tissoires <benjamin.tissoires@redhat.com> (For hid) Acked-by: Thorsten Scherer <t.scherer@eckelmann.de> (For siox) Acked-by: Sven Van Asbroeck <TheSven73@gmail.com> (For anybuss) Acked-by: Ulf Hansson <ulf.hansson@linaro.org> (For MMC) Acked-by: Wolfram Sang <wsa@kernel.org> # for I2C Acked-by: Sudeep Holla <sudeep.holla@arm.com> Acked-by: Geert Uytterhoeven <geert@linux-m68k.org> Acked-by: Dmitry Torokhov <dmitry.torokhov@gmail.com> Acked-by: Finn Thain <fthain@linux-m68k.org> Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de> Link: https://lore.kernel.org/r/20210713193522.1770306-6-u.kleine-koenig@pengutronix.de Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2021-07-14 03:35:22 +08:00
static void virtio_dev_remove(struct device *_d)
{
struct virtio_device *dev = dev_to_virtio(_d);
struct virtio_driver *drv = drv_to_virtio(dev->dev.driver);
virtio_config_disable(dev);
drv->remove(dev);
/* Driver should have reset device. */
WARN_ON_ONCE(dev->config->get_status(dev));
/* Acknowledge the device's existence again. */
virtio_add_status(dev, VIRTIO_CONFIG_S_ACKNOWLEDGE);
of_node_put(dev->dev.of_node);
}
static struct bus_type virtio_bus = {
.name = "virtio",
.match = virtio_dev_match,
.dev_groups = virtio_dev_groups,
.uevent = virtio_uevent,
.probe = virtio_dev_probe,
.remove = virtio_dev_remove,
};
int register_virtio_driver(struct virtio_driver *driver)
{
/* Catch this early. */
BUG_ON(driver->feature_table_size && !driver->feature_table);
driver->driver.bus = &virtio_bus;
return driver_register(&driver->driver);
}
EXPORT_SYMBOL_GPL(register_virtio_driver);
void unregister_virtio_driver(struct virtio_driver *driver)
{
driver_unregister(&driver->driver);
}
EXPORT_SYMBOL_GPL(unregister_virtio_driver);
static int virtio_device_of_init(struct virtio_device *dev)
{
struct device_node *np, *pnode = dev_of_node(dev->dev.parent);
char compat[] = "virtio,deviceXXXXXXXX";
int ret, count;
if (!pnode)
return 0;
count = of_get_available_child_count(pnode);
if (!count)
return 0;
/* There can be only 1 child node */
if (WARN_ON(count > 1))
return -EINVAL;
np = of_get_next_available_child(pnode, NULL);
if (WARN_ON(!np))
return -ENODEV;
ret = snprintf(compat, sizeof(compat), "virtio,device%x", dev->id.device);
BUG_ON(ret >= sizeof(compat));
/*
* On powerpc/pseries virtio devices are PCI devices so PCI
* vendor/device ids play the role of the "compatible" property.
* Simply don't init of_node in this case.
*/
if (!of_device_is_compatible(np, compat)) {
ret = 0;
goto out;
}
dev->dev.of_node = np;
return 0;
out:
of_node_put(np);
return ret;
}
/**
* register_virtio_device - register virtio device
* @dev : virtio device to be registered
*
* On error, the caller must call put_device on &@dev->dev (and not kfree),
* as another code path may have obtained a reference to @dev.
*
* Returns: 0 on suceess, -error on failure
*/
int register_virtio_device(struct virtio_device *dev)
{
int err;
dev->dev.bus = &virtio_bus;
device_initialize(&dev->dev);
/* Assign a unique device index and hence name. */
err = ida_alloc(&virtio_index_ida, GFP_KERNEL);
if (err < 0)
goto out;
dev->index = err;
err = dev_set_name(&dev->dev, "virtio%u", dev->index);
if (err)
goto out_ida_remove;
err = virtio_device_of_init(dev);
if (err)
goto out_ida_remove;
spin_lock_init(&dev->config_lock);
dev->config_enabled = false;
dev->config_change_pending = false;
virtio: harden vring IRQ This is a rework on the previous IRQ hardening that is done for virtio-pci where several drawbacks were found and were reverted: 1) try to use IRQF_NO_AUTOEN which is not friendly to affinity managed IRQ that is used by some device such as virtio-blk 2) done only for PCI transport The vq->broken is re-used in this patch for implementing the IRQ hardening. The vq->broken is set to true during both initialization and reset. And the vq->broken is set to false in virtio_device_ready(). Then vring_interrupt() can check and return when vq->broken is true. And in this case, switch to return IRQ_NONE to let the interrupt core aware of such invalid interrupt to prevent IRQ storm. The reason of using a per queue variable instead of a per device one is that we may need it for per queue reset hardening in the future. Note that the hardening is only done for vring interrupt since the config interrupt hardening is already done in commit 22b7050a024d7 ("virtio: defer config changed notifications"). But the method that is used by config interrupt can't be reused by the vring interrupt handler because it uses spinlock to do the synchronization which is expensive. Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Peter Zijlstra <peterz@infradead.org> Cc: "Paul E. McKenney" <paulmck@kernel.org> Cc: Marc Zyngier <maz@kernel.org> Cc: Halil Pasic <pasic@linux.ibm.com> Cc: Cornelia Huck <cohuck@redhat.com> Cc: Vineeth Vijayan <vneethv@linux.ibm.com> Cc: Peter Oberparleiter <oberpar@linux.ibm.com> Cc: linux-s390@vger.kernel.org Signed-off-by: Jason Wang <jasowang@redhat.com> Message-Id: <20220527060120.20964-9-jasowang@redhat.com> Signed-off-by: Michael S. Tsirkin <mst@redhat.com> Reviewed-by: Xuan Zhuo <xuanzhuo@linux.alibaba.com>
2022-05-27 14:01:19 +08:00
INIT_LIST_HEAD(&dev->vqs);
spin_lock_init(&dev->vqs_list_lock);
/* We always start by resetting the device, in case a previous
* driver messed it up. This also tests that code path a little. */
virtio_reset_device(dev);
/* Acknowledge that we've seen the device. */
virtio_add_status(dev, VIRTIO_CONFIG_S_ACKNOWLEDGE);
/*
* device_add() causes the bus infrastructure to look for a matching
* driver.
*/
err = device_add(&dev->dev);
if (err)
goto out_of_node_put;
return 0;
out_of_node_put:
of_node_put(dev->dev.of_node);
out_ida_remove:
ida_free(&virtio_index_ida, dev->index);
out:
virtio_add_status(dev, VIRTIO_CONFIG_S_FAILED);
return err;
}
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 */
device_unregister(&dev->dev);
ida_free(&virtio_index_ida, index);
}
EXPORT_SYMBOL_GPL(unregister_virtio_device);
#ifdef CONFIG_PM_SLEEP
int virtio_device_freeze(struct virtio_device *dev)
{
struct virtio_driver *drv = drv_to_virtio(dev->dev.driver);
virtio_config_disable(dev);
dev->failed = dev->config->get_status(dev) & VIRTIO_CONFIG_S_FAILED;
if (drv && drv->freeze)
return drv->freeze(dev);
return 0;
}
EXPORT_SYMBOL_GPL(virtio_device_freeze);
int virtio_device_restore(struct virtio_device *dev)
{
struct virtio_driver *drv = drv_to_virtio(dev->dev.driver);
int ret;
/* We always start by resetting the device, in case a previous
* driver messed it up. */
virtio_reset_device(dev);
/* Acknowledge that we've seen the device. */
virtio_add_status(dev, VIRTIO_CONFIG_S_ACKNOWLEDGE);
/* Maybe driver failed before freeze.
* Restore the failed status, for debugging. */
if (dev->failed)
virtio_add_status(dev, VIRTIO_CONFIG_S_FAILED);
if (!drv)
return 0;
/* We have a driver! */
virtio_add_status(dev, VIRTIO_CONFIG_S_DRIVER);
virtio: acknowledge all features before access The feature negotiation was designed in a way that makes it possible for devices to know which config fields will be accessed by drivers. This is broken since commit 404123c2db79 ("virtio: allow drivers to validate features") with fallout in at least block and net. We have a partial work-around in commit 2f9a174f918e ("virtio: write back F_VERSION_1 before validate") which at least lets devices find out which format should config space have, but this is a partial fix: guests should not access config space without acknowledging features since otherwise we'll never be able to change the config space format. To fix, split finalize_features from virtio_finalize_features and call finalize_features with all feature bits before validation, and then - if validation changed any bits - once again after. Since virtio_finalize_features no longer writes out features rename it to virtio_features_ok - since that is what it does: checks that features are ok with the device. As a side effect, this also reduces the amount of hypervisor accesses - we now only acknowledge features once unless we are clearing any features when validating (which is uncommon). IRC I think that this was more or less always the intent in the spec but unfortunately the way the spec is worded does not say this explicitly, I plan to address this at the spec level, too. Acked-by: Jason Wang <jasowang@redhat.com> Cc: stable@vger.kernel.org Fixes: 404123c2db79 ("virtio: allow drivers to validate features") Fixes: 2f9a174f918e ("virtio: write back F_VERSION_1 before validate") Cc: "Halil Pasic" <pasic@linux.ibm.com> Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
2022-01-15 03:58:41 +08:00
ret = dev->config->finalize_features(dev);
if (ret)
goto err;
ret = virtio_features_ok(dev);
if (ret)
goto err;
if (drv->restore) {
ret = drv->restore(dev);
if (ret)
goto err;
}
/* If restore didn't do it, mark device DRIVER_OK ourselves. */
if (!(dev->config->get_status(dev) & VIRTIO_CONFIG_S_DRIVER_OK))
virtio_device_ready(dev);
virtio_config_enable(dev);
return 0;
err:
virtio_add_status(dev, VIRTIO_CONFIG_S_FAILED);
return ret;
}
EXPORT_SYMBOL_GPL(virtio_device_restore);
#endif
static int virtio_init(void)
{
if (bus_register(&virtio_bus) != 0)
panic("virtio bus registration failed");
return 0;
}
static void __exit virtio_exit(void)
{
bus_unregister(&virtio_bus);
ida_destroy(&virtio_index_ida);
}
core_initcall(virtio_init);
module_exit(virtio_exit);
MODULE_LICENSE("GPL");