summaryrefslogtreecommitdiff
path: root/drivers/vfio
diff options
context:
space:
mode:
Diffstat (limited to 'drivers/vfio')
-rw-r--r--drivers/vfio/Kconfig31
-rw-r--r--drivers/vfio/Makefile11
-rw-r--r--drivers/vfio/container.c145
-rw-r--r--drivers/vfio/fsl-mc/vfio_fsl_mc.c4
-rw-r--r--drivers/vfio/fsl-mc/vfio_fsl_mc_intr.c1
-rw-r--r--drivers/vfio/group.c877
-rw-r--r--drivers/vfio/iommufd.c158
-rw-r--r--drivers/vfio/iova_bitmap.c33
-rw-r--r--drivers/vfio/pci/hisilicon/hisi_acc_vfio_pci.c162
-rw-r--r--drivers/vfio/pci/hisilicon/hisi_acc_vfio_pci.h2
-rw-r--r--drivers/vfio/pci/mlx5/cmd.c413
-rw-r--r--drivers/vfio/pci/mlx5/cmd.h96
-rw-r--r--drivers/vfio/pci/mlx5/main.c787
-rw-r--r--drivers/vfio/pci/vfio_pci.c3
-rw-r--r--drivers/vfio/pci/vfio_pci_core.c25
-rw-r--r--drivers/vfio/platform/vfio_amba.c4
-rw-r--r--drivers/vfio/platform/vfio_platform.c4
-rw-r--r--drivers/vfio/platform/vfio_platform_common.c3
-rw-r--r--drivers/vfio/vfio.h133
-rw-r--r--drivers/vfio/vfio_iommu_spapr_tce.c65
-rw-r--r--drivers/vfio/vfio_main.c1126
-rw-r--r--drivers/vfio/vfio_spapr_eeh.c107
-rw-r--r--drivers/vfio/virqfd.c17
23 files changed, 2875 insertions, 1332 deletions
diff --git a/drivers/vfio/Kconfig b/drivers/vfio/Kconfig
index 86c381ceb9a1..a8f544629467 100644
--- a/drivers/vfio/Kconfig
+++ b/drivers/vfio/Kconfig
@@ -2,8 +2,9 @@
menuconfig VFIO
tristate "VFIO Non-Privileged userspace driver framework"
select IOMMU_API
- select VFIO_IOMMU_TYPE1 if MMU && (X86 || S390 || ARM || ARM64)
+ depends on IOMMUFD || !IOMMUFD
select INTERVAL_TREE
+ select VFIO_CONTAINER if IOMMUFD=n
help
VFIO provides a framework for secure userspace device drivers.
See Documentation/driver-api/vfio.rst for more details.
@@ -11,6 +12,18 @@ menuconfig VFIO
If you don't know what to do here, say N.
if VFIO
+config VFIO_CONTAINER
+ bool "Support for the VFIO container /dev/vfio/vfio"
+ select VFIO_IOMMU_TYPE1 if MMU && (X86 || S390 || ARM || ARM64)
+ default y
+ help
+ The VFIO container is the classic interface to VFIO for establishing
+ IOMMU mappings. If N is selected here then IOMMUFD must be used to
+ manage the mappings.
+
+ Unless testing IOMMUFD say Y here.
+
+if VFIO_CONTAINER
config VFIO_IOMMU_TYPE1
tristate
default n
@@ -20,16 +33,6 @@ config VFIO_IOMMU_SPAPR_TCE
depends on SPAPR_TCE_IOMMU
default VFIO
-config VFIO_SPAPR_EEH
- tristate
- depends on EEH && VFIO_IOMMU_SPAPR_TCE
- default VFIO
-
-config VFIO_VIRQFD
- tristate
- select EVENTFD
- default n
-
config VFIO_NOIOMMU
bool "VFIO No-IOMMU support"
help
@@ -43,6 +46,12 @@ config VFIO_NOIOMMU
this mode since there is no IOMMU to provide DMA translation.
If you don't know what to do here, say N.
+endif
+
+config VFIO_VIRQFD
+ bool
+ select EVENTFD
+ default n
source "drivers/vfio/pci/Kconfig"
source "drivers/vfio/platform/Kconfig"
diff --git a/drivers/vfio/Makefile b/drivers/vfio/Makefile
index b693a1169286..70e7dcb302ef 100644
--- a/drivers/vfio/Makefile
+++ b/drivers/vfio/Makefile
@@ -1,16 +1,15 @@
# SPDX-License-Identifier: GPL-2.0
-vfio_virqfd-y := virqfd.o
-
obj-$(CONFIG_VFIO) += vfio.o
vfio-y += vfio_main.o \
- iova_bitmap.o \
- container.o
+ group.o \
+ iova_bitmap.o
+vfio-$(CONFIG_IOMMUFD) += iommufd.o
+vfio-$(CONFIG_VFIO_CONTAINER) += container.o
+vfio-$(CONFIG_VFIO_VIRQFD) += virqfd.o
-obj-$(CONFIG_VFIO_VIRQFD) += vfio_virqfd.o
obj-$(CONFIG_VFIO_IOMMU_TYPE1) += vfio_iommu_type1.o
obj-$(CONFIG_VFIO_IOMMU_SPAPR_TCE) += vfio_iommu_spapr_tce.o
-obj-$(CONFIG_VFIO_SPAPR_EEH) += vfio_spapr_eeh.o
obj-$(CONFIG_VFIO_PCI) += pci/
obj-$(CONFIG_VFIO_PLATFORM) += platform/
obj-$(CONFIG_VFIO_MDEV) += mdev/
diff --git a/drivers/vfio/container.c b/drivers/vfio/container.c
index d74164abbf40..b7a9560ab25e 100644
--- a/drivers/vfio/container.c
+++ b/drivers/vfio/container.c
@@ -188,8 +188,9 @@ void vfio_device_container_unregister(struct vfio_device *device)
device->group->container->iommu_data, device);
}
-long vfio_container_ioctl_check_extension(struct vfio_container *container,
- unsigned long arg)
+static long
+vfio_container_ioctl_check_extension(struct vfio_container *container,
+ unsigned long arg)
{
struct vfio_iommu_driver *driver;
long ret = 0;
@@ -511,14 +512,15 @@ void vfio_group_detach_container(struct vfio_group *group)
vfio_container_put(container);
}
-int vfio_device_assign_container(struct vfio_device *device)
+int vfio_group_use_container(struct vfio_group *group)
{
- struct vfio_group *group = device->group;
-
lockdep_assert_held(&group->group_lock);
- if (!group->container || !group->container->iommu_driver ||
- WARN_ON(!group->container_users))
+ /*
+ * The container fd has been assigned with VFIO_GROUP_SET_CONTAINER but
+ * VFIO_SET_IOMMU hasn't been done yet.
+ */
+ if (!group->container->iommu_driver)
return -EINVAL;
if (group->type == VFIO_NO_IOMMU && !capable(CAP_SYS_RAWIO))
@@ -529,122 +531,56 @@ int vfio_device_assign_container(struct vfio_device *device)
return 0;
}
-void vfio_device_unassign_container(struct vfio_device *device)
+void vfio_group_unuse_container(struct vfio_group *group)
{
- mutex_lock(&device->group->group_lock);
- WARN_ON(device->group->container_users <= 1);
- device->group->container_users--;
- fput(device->group->opened_file);
- mutex_unlock(&device->group->group_lock);
+ lockdep_assert_held(&group->group_lock);
+
+ WARN_ON(group->container_users <= 1);
+ group->container_users--;
+ fput(group->opened_file);
}
-/*
- * Pin contiguous user pages and return their associated host pages for local
- * domain only.
- * @device [in] : device
- * @iova [in] : starting IOVA of user pages to be pinned.
- * @npage [in] : count of pages to be pinned. This count should not
- * be greater than VFIO_PIN_PAGES_MAX_ENTRIES.
- * @prot [in] : protection flags
- * @pages[out] : array of host pages
- * Return error or number of pages pinned.
- *
- * A driver may only call this function if the vfio_device was created
- * by vfio_register_emulated_iommu_dev().
- */
-int vfio_pin_pages(struct vfio_device *device, dma_addr_t iova,
- int npage, int prot, struct page **pages)
+int vfio_device_container_pin_pages(struct vfio_device *device,
+ dma_addr_t iova, int npage,
+ int prot, struct page **pages)
{
- struct vfio_container *container;
- struct vfio_group *group = device->group;
- struct vfio_iommu_driver *driver;
- int ret;
-
- if (!pages || !npage || !vfio_assert_device_open(device))
- return -EINVAL;
+ struct vfio_container *container = device->group->container;
+ struct iommu_group *iommu_group = device->group->iommu_group;
+ struct vfio_iommu_driver *driver = container->iommu_driver;
if (npage > VFIO_PIN_PAGES_MAX_ENTRIES)
return -E2BIG;
- /* group->container cannot change while a vfio device is open */
- container = group->container;
- driver = container->iommu_driver;
- if (likely(driver && driver->ops->pin_pages))
- ret = driver->ops->pin_pages(container->iommu_data,
- group->iommu_group, iova,
- npage, prot, pages);
- else
- ret = -ENOTTY;
-
- return ret;
+ if (unlikely(!driver || !driver->ops->pin_pages))
+ return -ENOTTY;
+ return driver->ops->pin_pages(container->iommu_data, iommu_group, iova,
+ npage, prot, pages);
}
-EXPORT_SYMBOL(vfio_pin_pages);
-/*
- * Unpin contiguous host pages for local domain only.
- * @device [in] : device
- * @iova [in] : starting address of user pages to be unpinned.
- * @npage [in] : count of pages to be unpinned. This count should not
- * be greater than VFIO_PIN_PAGES_MAX_ENTRIES.
- */
-void vfio_unpin_pages(struct vfio_device *device, dma_addr_t iova, int npage)
+void vfio_device_container_unpin_pages(struct vfio_device *device,
+ dma_addr_t iova, int npage)
{
- struct vfio_container *container;
- struct vfio_iommu_driver *driver;
+ struct vfio_container *container = device->group->container;
if (WARN_ON(npage <= 0 || npage > VFIO_PIN_PAGES_MAX_ENTRIES))
return;
- if (WARN_ON(!vfio_assert_device_open(device)))
- return;
-
- /* group->container cannot change while a vfio device is open */
- container = device->group->container;
- driver = container->iommu_driver;
-
- driver->ops->unpin_pages(container->iommu_data, iova, npage);
+ container->iommu_driver->ops->unpin_pages(container->iommu_data, iova,
+ npage);
}
-EXPORT_SYMBOL(vfio_unpin_pages);
-/*
- * This interface allows the CPUs to perform some sort of virtual DMA on
- * behalf of the device.
- *
- * CPUs read/write from/into a range of IOVAs pointing to user space memory
- * into/from a kernel buffer.
- *
- * As the read/write of user space memory is conducted via the CPUs and is
- * not a real device DMA, it is not necessary to pin the user space memory.
- *
- * @device [in] : VFIO device
- * @iova [in] : base IOVA of a user space buffer
- * @data [in] : pointer to kernel buffer
- * @len [in] : kernel buffer length
- * @write : indicate read or write
- * Return error code on failure or 0 on success.
- */
-int vfio_dma_rw(struct vfio_device *device, dma_addr_t iova, void *data,
- size_t len, bool write)
+int vfio_device_container_dma_rw(struct vfio_device *device,
+ dma_addr_t iova, void *data,
+ size_t len, bool write)
{
- struct vfio_container *container;
- struct vfio_iommu_driver *driver;
- int ret = 0;
-
- if (!data || len <= 0 || !vfio_assert_device_open(device))
- return -EINVAL;
-
- /* group->container cannot change while a vfio device is open */
- container = device->group->container;
- driver = container->iommu_driver;
+ struct vfio_container *container = device->group->container;
+ struct vfio_iommu_driver *driver = container->iommu_driver;
- if (likely(driver && driver->ops->dma_rw))
- ret = driver->ops->dma_rw(container->iommu_data,
- iova, data, len, write);
- else
- ret = -ENOTTY;
- return ret;
+ if (unlikely(!driver || !driver->ops->dma_rw))
+ return -ENOTTY;
+ return driver->ops->dma_rw(container->iommu_data, iova, data, len,
+ write);
}
-EXPORT_SYMBOL(vfio_dma_rw);
int __init vfio_container_init(void)
{
@@ -678,3 +614,6 @@ void vfio_container_cleanup(void)
misc_deregister(&vfio_dev);
mutex_destroy(&vfio.iommu_drivers_lock);
}
+
+MODULE_ALIAS_MISCDEV(VFIO_MINOR);
+MODULE_ALIAS("devname:vfio/vfio");
diff --git a/drivers/vfio/fsl-mc/vfio_fsl_mc.c b/drivers/vfio/fsl-mc/vfio_fsl_mc.c
index b16874e913e4..defeb8510ace 100644
--- a/drivers/vfio/fsl-mc/vfio_fsl_mc.c
+++ b/drivers/vfio/fsl-mc/vfio_fsl_mc.c
@@ -568,7 +568,6 @@ static void vfio_fsl_mc_release_dev(struct vfio_device *core_vdev)
vfio_fsl_uninit_device(vdev);
mutex_destroy(&vdev->igate);
- vfio_free_device(core_vdev);
}
static int vfio_fsl_mc_remove(struct fsl_mc_device *mc_dev)
@@ -592,6 +591,9 @@ static const struct vfio_device_ops vfio_fsl_mc_ops = {
.read = vfio_fsl_mc_read,
.write = vfio_fsl_mc_write,
.mmap = vfio_fsl_mc_mmap,
+ .bind_iommufd = vfio_iommufd_physical_bind,
+ .unbind_iommufd = vfio_iommufd_physical_unbind,
+ .attach_ioas = vfio_iommufd_physical_attach_ioas,
};
static struct fsl_mc_driver vfio_fsl_mc_driver = {
diff --git a/drivers/vfio/fsl-mc/vfio_fsl_mc_intr.c b/drivers/vfio/fsl-mc/vfio_fsl_mc_intr.c
index 7b428eac3d3e..64d01f3fb13d 100644
--- a/drivers/vfio/fsl-mc/vfio_fsl_mc_intr.c
+++ b/drivers/vfio/fsl-mc/vfio_fsl_mc_intr.c
@@ -8,7 +8,6 @@
#include <linux/slab.h>
#include <linux/types.h>
#include <linux/eventfd.h>
-#include <linux/msi.h>
#include "linux/fsl/mc.h"
#include "vfio_fsl_mc_private.h"
diff --git a/drivers/vfio/group.c b/drivers/vfio/group.c
new file mode 100644
index 000000000000..bb24b2f0271e
--- /dev/null
+++ b/drivers/vfio/group.c
@@ -0,0 +1,877 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * VFIO core
+ *
+ * Copyright (C) 2012 Red Hat, Inc. All rights reserved.
+ * Author: Alex Williamson <alex.williamson@redhat.com>
+ *
+ * Derived from original vfio:
+ * Copyright 2010 Cisco Systems, Inc. All rights reserved.
+ * Author: Tom Lyon, pugs@cisco.com
+ */
+
+#include <linux/vfio.h>
+#include <linux/iommufd.h>
+#include <linux/anon_inodes.h>
+#include "vfio.h"
+
+static struct vfio {
+ struct class *class;
+ struct list_head group_list;
+ struct mutex group_lock; /* locks group_list */
+ struct ida group_ida;
+ dev_t group_devt;
+} vfio;
+
+static struct vfio_device *vfio_device_get_from_name(struct vfio_group *group,
+ char *buf)
+{
+ struct vfio_device *it, *device = ERR_PTR(-ENODEV);
+
+ mutex_lock(&group->device_lock);
+ list_for_each_entry(it, &group->device_list, group_next) {
+ int ret;
+
+ if (it->ops->match) {
+ ret = it->ops->match(it, buf);
+ if (ret < 0) {
+ device = ERR_PTR(ret);
+ break;
+ }
+ } else {
+ ret = !strcmp(dev_name(it->dev), buf);
+ }
+
+ if (ret && vfio_device_try_get_registration(it)) {
+ device = it;
+ break;
+ }
+ }
+ mutex_unlock(&group->device_lock);
+
+ return device;
+}
+
+/*
+ * VFIO Group fd, /dev/vfio/$GROUP
+ */
+static bool vfio_group_has_iommu(struct vfio_group *group)
+{
+ lockdep_assert_held(&group->group_lock);
+ /*
+ * There can only be users if there is a container, and if there is a
+ * container there must be users.
+ */
+ WARN_ON(!group->container != !group->container_users);
+
+ return group->container || group->iommufd;
+}
+
+/*
+ * VFIO_GROUP_UNSET_CONTAINER should fail if there are other users or
+ * if there was no container to unset. Since the ioctl is called on
+ * the group, we know that still exists, therefore the only valid
+ * transition here is 1->0.
+ */
+static int vfio_group_ioctl_unset_container(struct vfio_group *group)
+{
+ int ret = 0;
+
+ mutex_lock(&group->group_lock);
+ if (!vfio_group_has_iommu(group)) {
+ ret = -EINVAL;
+ goto out_unlock;
+ }
+ if (group->container) {
+ if (group->container_users != 1) {
+ ret = -EBUSY;
+ goto out_unlock;
+ }
+ vfio_group_detach_container(group);
+ }
+ if (group->iommufd) {
+ iommufd_ctx_put(group->iommufd);
+ group->iommufd = NULL;
+ }
+
+out_unlock:
+ mutex_unlock(&group->group_lock);
+ return ret;
+}
+
+static int vfio_group_ioctl_set_container(struct vfio_group *group,
+ int __user *arg)
+{
+ struct vfio_container *container;
+ struct iommufd_ctx *iommufd;
+ struct fd f;
+ int ret;
+ int fd;
+
+ if (get_user(fd, arg))
+ return -EFAULT;
+
+ f = fdget(fd);
+ if (!f.file)
+ return -EBADF;
+
+ mutex_lock(&group->group_lock);
+ if (vfio_group_has_iommu(group)) {
+ ret = -EINVAL;
+ goto out_unlock;
+ }
+ if (!group->iommu_group) {
+ ret = -ENODEV;
+ goto out_unlock;
+ }
+
+ container = vfio_container_from_file(f.file);
+ if (container) {
+ ret = vfio_container_attach_group(container, group);
+ goto out_unlock;
+ }
+
+ iommufd = iommufd_ctx_from_file(f.file);
+ if (!IS_ERR(iommufd)) {
+ u32 ioas_id;
+
+ ret = iommufd_vfio_compat_ioas_id(iommufd, &ioas_id);
+ if (ret) {
+ iommufd_ctx_put(group->iommufd);
+ goto out_unlock;
+ }
+
+ group->iommufd = iommufd;
+ goto out_unlock;
+ }
+
+ /* The FD passed is not recognized. */
+ ret = -EBADFD;
+
+out_unlock:
+ mutex_unlock(&group->group_lock);
+ fdput(f);
+ return ret;
+}
+
+static int vfio_device_group_open(struct vfio_device *device)
+{
+ int ret;
+
+ mutex_lock(&device->group->group_lock);
+ if (!vfio_group_has_iommu(device->group)) {
+ ret = -EINVAL;
+ goto out_unlock;
+ }
+
+ /*
+ * Here we pass the KVM pointer with the group under the lock. If the
+ * device driver will use it, it must obtain a reference and release it
+ * during close_device.
+ */
+ ret = vfio_device_open(device, device->group->iommufd,
+ device->group->kvm);
+
+out_unlock:
+ mutex_unlock(&device->group->group_lock);
+ return ret;
+}
+
+void vfio_device_group_close(struct vfio_device *device)
+{
+ mutex_lock(&device->group->group_lock);
+ vfio_device_close(device, device->group->iommufd);
+ mutex_unlock(&device->group->group_lock);
+}
+
+static struct file *vfio_device_open_file(struct vfio_device *device)
+{
+ struct file *filep;
+ int ret;
+
+ ret = vfio_device_group_open(device);
+ if (ret)
+ goto err_out;
+
+ /*
+ * We can't use anon_inode_getfd() because we need to modify
+ * the f_mode flags directly to allow more than just ioctls
+ */
+ filep = anon_inode_getfile("[vfio-device]", &vfio_device_fops,
+ device, O_RDWR);
+ if (IS_ERR(filep)) {
+ ret = PTR_ERR(filep);
+ goto err_close_device;
+ }
+
+ /*
+ * TODO: add an anon_inode interface to do this.
+ * Appears to be missing by lack of need rather than
+ * explicitly prevented. Now there's need.
+ */
+ filep->f_mode |= (FMODE_PREAD | FMODE_PWRITE);
+
+ if (device->group->type == VFIO_NO_IOMMU)
+ dev_warn(device->dev, "vfio-noiommu device opened by user "
+ "(%s:%d)\n", current->comm, task_pid_nr(current));
+ /*
+ * On success the ref of device is moved to the file and
+ * put in vfio_device_fops_release()
+ */
+ return filep;
+
+err_close_device:
+ vfio_device_group_close(device);
+err_out:
+ return ERR_PTR(ret);
+}
+
+static int vfio_group_ioctl_get_device_fd(struct vfio_group *group,
+ char __user *arg)
+{
+ struct vfio_device *device;
+ struct file *filep;
+ char *buf;
+ int fdno;
+ int ret;
+
+ buf = strndup_user(arg, PAGE_SIZE);
+ if (IS_ERR(buf))
+ return PTR_ERR(buf);
+
+ device = vfio_device_get_from_name(group, buf);
+ kfree(buf);
+ if (IS_ERR(device))
+ return PTR_ERR(device);
+
+ fdno = get_unused_fd_flags(O_CLOEXEC);
+ if (fdno < 0) {
+ ret = fdno;
+ goto err_put_device;
+ }
+
+ filep = vfio_device_open_file(device);
+ if (IS_ERR(filep)) {
+ ret = PTR_ERR(filep);
+ goto err_put_fdno;
+ }
+
+ fd_install(fdno, filep);
+ return fdno;
+
+err_put_fdno:
+ put_unused_fd(fdno);
+err_put_device:
+ vfio_device_put_registration(device);
+ return ret;
+}
+
+static int vfio_group_ioctl_get_status(struct vfio_group *group,
+ struct vfio_group_status __user *arg)
+{
+ unsigned long minsz = offsetofend(struct vfio_group_status, flags);
+ struct vfio_group_status status;
+
+ if (copy_from_user(&status, arg, minsz))
+ return -EFAULT;
+
+ if (status.argsz < minsz)
+ return -EINVAL;
+
+ status.flags = 0;
+
+ mutex_lock(&group->group_lock);
+ if (!group->iommu_group) {
+ mutex_unlock(&group->group_lock);
+ return -ENODEV;
+ }
+
+ /*
+ * With the container FD the iommu_group_claim_dma_owner() is done
+ * during SET_CONTAINER but for IOMMFD this is done during
+ * VFIO_GROUP_GET_DEVICE_FD. Meaning that with iommufd
+ * VFIO_GROUP_FLAGS_VIABLE could be set but GET_DEVICE_FD will fail due
+ * to viability.
+ */
+ if (vfio_group_has_iommu(group))
+ status.flags |= VFIO_GROUP_FLAGS_CONTAINER_SET |
+ VFIO_GROUP_FLAGS_VIABLE;
+ else if (!iommu_group_dma_owner_claimed(group->iommu_group))
+ status.flags |= VFIO_GROUP_FLAGS_VIABLE;
+ mutex_unlock(&group->group_lock);
+
+ if (copy_to_user(arg, &status, minsz))
+ return -EFAULT;
+ return 0;
+}
+
+static long vfio_group_fops_unl_ioctl(struct file *filep,
+ unsigned int cmd, unsigned long arg)
+{
+ struct vfio_group *group = filep->private_data;
+ void __user *uarg = (void __user *)arg;
+
+ switch (cmd) {
+ case VFIO_GROUP_GET_DEVICE_FD:
+ return vfio_group_ioctl_get_device_fd(group, uarg);
+ case VFIO_GROUP_GET_STATUS:
+ return vfio_group_ioctl_get_status(group, uarg);
+ case VFIO_GROUP_SET_CONTAINER:
+ return vfio_group_ioctl_set_container(group, uarg);
+ case VFIO_GROUP_UNSET_CONTAINER:
+ return vfio_group_ioctl_unset_container(group);
+ default:
+ return -ENOTTY;
+ }
+}
+
+static int vfio_group_fops_open(struct inode *inode, struct file *filep)
+{
+ struct vfio_group *group =
+ container_of(inode->i_cdev, struct vfio_group, cdev);
+ int ret;
+
+ mutex_lock(&group->group_lock);
+
+ /*
+ * drivers can be zero if this races with vfio_device_remove_group(), it
+ * will be stable at 0 under the group rwsem
+ */
+ if (refcount_read(&group->drivers) == 0) {
+ ret = -ENODEV;
+ goto out_unlock;
+ }
+
+ if (group->type == VFIO_NO_IOMMU && !capable(CAP_SYS_RAWIO)) {
+ ret = -EPERM;
+ goto out_unlock;
+ }
+
+ /*
+ * Do we need multiple instances of the group open? Seems not.
+ */
+ if (group->opened_file) {
+ ret = -EBUSY;
+ goto out_unlock;
+ }
+ group->opened_file = filep;
+ filep->private_data = group;
+ ret = 0;
+out_unlock:
+ mutex_unlock(&group->group_lock);
+ return ret;
+}
+
+static int vfio_group_fops_release(struct inode *inode, struct file *filep)
+{
+ struct vfio_group *group = filep->private_data;
+
+ filep->private_data = NULL;
+
+ mutex_lock(&group->group_lock);
+ /*
+ * Device FDs hold a group file reference, therefore the group release
+ * is only called when there are no open devices.
+ */
+ WARN_ON(group->notifier.head);
+ if (group->container)
+ vfio_group_detach_container(group);
+ if (group->iommufd) {
+ iommufd_ctx_put(group->iommufd);
+ group->iommufd = NULL;
+ }
+ group->opened_file = NULL;
+ mutex_unlock(&group->group_lock);
+ return 0;
+}
+
+static const struct file_operations vfio_group_fops = {
+ .owner = THIS_MODULE,
+ .unlocked_ioctl = vfio_group_fops_unl_ioctl,
+ .compat_ioctl = compat_ptr_ioctl,
+ .open = vfio_group_fops_open,
+ .release = vfio_group_fops_release,
+};
+
+/*
+ * Group objects - create, release, get, put, search
+ */
+static struct vfio_group *
+vfio_group_find_from_iommu(struct iommu_group *iommu_group)
+{
+ struct vfio_group *group;
+
+ lockdep_assert_held(&vfio.group_lock);
+
+ /*
+ * group->iommu_group from the vfio.group_list cannot be NULL
+ * under the vfio.group_lock.
+ */
+ list_for_each_entry(group, &vfio.group_list, vfio_next) {
+ if (group->iommu_group == iommu_group)
+ return group;
+ }
+ return NULL;
+}
+
+static void vfio_group_release(struct device *dev)
+{
+ struct vfio_group *group = container_of(dev, struct vfio_group, dev);
+
+ mutex_destroy(&group->device_lock);
+ mutex_destroy(&group->group_lock);
+ WARN_ON(group->iommu_group);
+ ida_free(&vfio.group_ida, MINOR(group->dev.devt));
+ kfree(group);
+}
+
+static struct vfio_group *vfio_group_alloc(struct iommu_group *iommu_group,
+ enum vfio_group_type type)
+{
+ struct vfio_group *group;
+ int minor;
+
+ group = kzalloc(sizeof(*group), GFP_KERNEL);
+ if (!group)
+ return ERR_PTR(-ENOMEM);
+
+ minor = ida_alloc_max(&vfio.group_ida, MINORMASK, GFP_KERNEL);
+ if (minor < 0) {
+ kfree(group);
+ return ERR_PTR(minor);
+ }
+
+ device_initialize(&group->dev);
+ group->dev.devt = MKDEV(MAJOR(vfio.group_devt), minor);
+ group->dev.class = vfio.class;
+ group->dev.release = vfio_group_release;
+ cdev_init(&group->cdev, &vfio_group_fops);
+ group->cdev.owner = THIS_MODULE;
+
+ refcount_set(&group->drivers, 1);
+ mutex_init(&group->group_lock);
+ INIT_LIST_HEAD(&group->device_list);
+ mutex_init(&group->device_lock);
+ group->iommu_group = iommu_group;
+ /* put in vfio_group_release() */
+ iommu_group_ref_get(iommu_group);
+ group->type = type;
+ BLOCKING_INIT_NOTIFIER_HEAD(&group->notifier);
+
+ return group;
+}
+
+static struct vfio_group *vfio_create_group(struct iommu_group *iommu_group,
+ enum vfio_group_type type)
+{
+ struct vfio_group *group;
+ struct vfio_group *ret;
+ int err;
+
+ lockdep_assert_held(&vfio.group_lock);
+
+ group = vfio_group_alloc(iommu_group, type);
+ if (IS_ERR(group))
+ return group;
+
+ err = dev_set_name(&group->dev, "%s%d",
+ group->type == VFIO_NO_IOMMU ? "noiommu-" : "",
+ iommu_group_id(iommu_group));
+ if (err) {
+ ret = ERR_PTR(err);
+ goto err_put;
+ }
+
+ err = cdev_device_add(&group->cdev, &group->dev);
+ if (err) {
+ ret = ERR_PTR(err);
+ goto err_put;
+ }
+
+ list_add(&group->vfio_next, &vfio.group_list);
+
+ return group;
+
+err_put:
+ put_device(&group->dev);
+ return ret;
+}
+
+static struct vfio_group *vfio_noiommu_group_alloc(struct device *dev,
+ enum vfio_group_type type)
+{
+ struct iommu_group *iommu_group;
+ struct vfio_group *group;
+ int ret;
+
+ iommu_group = iommu_group_alloc();
+ if (IS_ERR(iommu_group))
+ return ERR_CAST(iommu_group);
+
+ ret = iommu_group_set_name(iommu_group, "vfio-noiommu");
+ if (ret)
+ goto out_put_group;
+ ret = iommu_group_add_device(iommu_group, dev);
+ if (ret)
+ goto out_put_group;
+
+ mutex_lock(&vfio.group_lock);
+ group = vfio_create_group(iommu_group, type);
+ mutex_unlock(&vfio.group_lock);
+ if (IS_ERR(group)) {
+ ret = PTR_ERR(group);
+ goto out_remove_device;
+ }
+ iommu_group_put(iommu_group);
+ return group;
+
+out_remove_device:
+ iommu_group_remove_device(dev);
+out_put_group:
+ iommu_group_put(iommu_group);
+ return ERR_PTR(ret);
+}
+
+static bool vfio_group_has_device(struct vfio_group *group, struct device *dev)
+{
+ struct vfio_device *device;
+
+ mutex_lock(&group->device_lock);
+ list_for_each_entry(device, &group->device_list, group_next) {
+ if (device->dev == dev) {
+ mutex_unlock(&group->device_lock);
+ return true;
+ }
+ }
+ mutex_unlock(&group->device_lock);
+ return false;
+}
+
+static struct vfio_group *vfio_group_find_or_alloc(struct device *dev)
+{
+ struct iommu_group *iommu_group;
+ struct vfio_group *group;
+
+ iommu_group = iommu_group_get(dev);
+ if (!iommu_group && vfio_noiommu) {
+ /*
+ * With noiommu enabled, create an IOMMU group for devices that
+ * don't already have one, implying no IOMMU hardware/driver
+ * exists. Taint the kernel because we're about to give a DMA
+ * capable device to a user without IOMMU protection.
+ */
+ group = vfio_noiommu_group_alloc(dev, VFIO_NO_IOMMU);
+ if (!IS_ERR(group)) {
+ add_taint(TAINT_USER, LOCKDEP_STILL_OK);
+ dev_warn(dev, "Adding kernel taint for vfio-noiommu group on device\n");
+ }
+ return group;
+ }
+
+ if (!iommu_group)
+ return ERR_PTR(-EINVAL);
+
+ /*
+ * VFIO always sets IOMMU_CACHE because we offer no way for userspace to
+ * restore cache coherency. It has to be checked here because it is only
+ * valid for cases where we are using iommu groups.
+ */
+ if (!device_iommu_capable(dev, IOMMU_CAP_CACHE_COHERENCY)) {
+ iommu_group_put(iommu_group);
+ return ERR_PTR(-EINVAL);
+ }
+
+ mutex_lock(&vfio.group_lock);
+ group = vfio_group_find_from_iommu(iommu_group);
+ if (group) {
+ if (WARN_ON(vfio_group_has_device(group, dev)))
+ group = ERR_PTR(-EINVAL);
+ else
+ refcount_inc(&group->drivers);
+ } else {
+ group = vfio_create_group(iommu_group, VFIO_IOMMU);
+ }
+ mutex_unlock(&vfio.group_lock);
+
+ /* The vfio_group holds a reference to the iommu_group */
+ iommu_group_put(iommu_group);
+ return group;
+}
+
+int vfio_device_set_group(struct vfio_device *device,
+ enum vfio_group_type type)
+{
+ struct vfio_group *group;
+
+ if (type == VFIO_IOMMU)
+ group = vfio_group_find_or_alloc(device->dev);
+ else
+ group = vfio_noiommu_group_alloc(device->dev, type);
+
+ if (IS_ERR(group))
+ return PTR_ERR(group);
+
+ /* Our reference on group is moved to the device */
+ device->group = group;
+ return 0;
+}
+
+void vfio_device_remove_group(struct vfio_device *device)
+{
+ struct vfio_group *group = device->group;
+ struct iommu_group *iommu_group;
+
+ if (group->type == VFIO_NO_IOMMU || group->type == VFIO_EMULATED_IOMMU)
+ iommu_group_remove_device(device->dev);
+
+ /* Pairs with vfio_create_group() / vfio_group_get_from_iommu() */
+ if (!refcount_dec_and_mutex_lock(&group->drivers, &vfio.group_lock))
+ return;
+ list_del(&group->vfio_next);
+
+ /*
+ * We could concurrently probe another driver in the group that might
+ * race vfio_device_remove_group() with vfio_get_group(), so we have to
+ * ensure that the sysfs is all cleaned up under lock otherwise the
+ * cdev_device_add() will fail due to the name aready existing.
+ */
+ cdev_device_del(&group->cdev, &group->dev);
+
+ mutex_lock(&group->group_lock);
+ /*
+ * These data structures all have paired operations that can only be
+ * undone when the caller holds a live reference on the device. Since
+ * all pairs must be undone these WARN_ON's indicate some caller did not
+ * properly hold the group reference.
+ */
+ WARN_ON(!list_empty(&group->device_list));
+ WARN_ON(group->notifier.head);
+
+ /*
+ * Revoke all users of group->iommu_group. At this point we know there
+ * are no devices active because we are unplugging the last one. Setting
+ * iommu_group to NULL blocks all new users.
+ */
+ if (group->container)
+ vfio_group_detach_container(group);
+ iommu_group = group->iommu_group;
+ group->iommu_group = NULL;
+ mutex_unlock(&group->group_lock);
+ mutex_unlock(&vfio.group_lock);
+
+ iommu_group_put(iommu_group);
+ put_device(&group->dev);
+}
+
+void vfio_device_group_register(struct vfio_device *device)
+{
+ mutex_lock(&device->group->device_lock);
+ list_add(&device->group_next, &device->group->device_list);
+ mutex_unlock(&device->group->device_lock);
+}
+
+void vfio_device_group_unregister(struct vfio_device *device)
+{
+ mutex_lock(&device->group->device_lock);
+ list_del(&device->group_next);
+ mutex_unlock(&device->group->device_lock);
+}
+
+int vfio_device_group_use_iommu(struct vfio_device *device)
+{
+ struct vfio_group *group = device->group;
+ int ret = 0;
+
+ lockdep_assert_held(&group->group_lock);
+
+ if (WARN_ON(!group->container))
+ return -EINVAL;
+
+ ret = vfio_group_use_container(group);
+ if (ret)
+ return ret;
+ vfio_device_container_register(device);
+ return 0;
+}
+
+void vfio_device_group_unuse_iommu(struct vfio_device *device)
+{
+ struct vfio_group *group = device->group;
+
+ lockdep_assert_held(&group->group_lock);
+
+ if (WARN_ON(!group->container))
+ return;
+
+ vfio_device_container_unregister(device);
+ vfio_group_unuse_container(group);
+}
+
+bool vfio_device_has_container(struct vfio_device *device)
+{
+ return device->group->container;
+}
+
+/**
+ * vfio_file_iommu_group - Return the struct iommu_group for the vfio group file
+ * @file: VFIO group file
+ *
+ * The returned iommu_group is valid as long as a ref is held on the file. This
+ * returns a reference on the group. This function is deprecated, only the SPAPR
+ * path in kvm should call it.
+ */
+struct iommu_group *vfio_file_iommu_group(struct file *file)
+{
+ struct vfio_group *group = file->private_data;
+ struct iommu_group *iommu_group = NULL;
+
+ if (!IS_ENABLED(CONFIG_SPAPR_TCE_IOMMU))
+ return NULL;
+
+ if (!vfio_file_is_group(file))
+ return NULL;
+
+ mutex_lock(&group->group_lock);
+ if (group->iommu_group) {
+ iommu_group = group->iommu_group;
+ iommu_group_ref_get(iommu_group);
+ }
+ mutex_unlock(&group->group_lock);
+ return iommu_group;
+}
+EXPORT_SYMBOL_GPL(vfio_file_iommu_group);
+
+/**
+ * vfio_file_is_group - True if the file is usable with VFIO aPIS
+ * @file: VFIO group file
+ */
+bool vfio_file_is_group(struct file *file)
+{
+ return file->f_op == &vfio_group_fops;
+}
+EXPORT_SYMBOL_GPL(vfio_file_is_group);
+
+/**
+ * vfio_file_enforced_coherent - True if the DMA associated with the VFIO file
+ * is always CPU cache coherent
+ * @file: VFIO group file
+ *
+ * Enforced coherency means that the IOMMU ignores things like the PCIe no-snoop
+ * bit in DMA transactions. A return of false indicates that the user has
+ * rights to access additional instructions such as wbinvd on x86.
+ */
+bool vfio_file_enforced_coherent(struct file *file)
+{
+ struct vfio_group *group = file->private_data;
+ struct vfio_device *device;
+ bool ret = true;
+
+ if (!vfio_file_is_group(file))
+ return true;
+
+ /*
+ * If the device does not have IOMMU_CAP_ENFORCE_CACHE_COHERENCY then
+ * any domain later attached to it will also not support it. If the cap
+ * is set then the iommu_domain eventually attached to the device/group
+ * must use a domain with enforce_cache_coherency().
+ */
+ mutex_lock(&group->device_lock);
+ list_for_each_entry(device, &group->device_list, group_next) {
+ if (!device_iommu_capable(device->dev,
+ IOMMU_CAP_ENFORCE_CACHE_COHERENCY)) {
+ ret = false;
+ break;
+ }
+ }
+ mutex_unlock(&group->device_lock);
+ return ret;
+}
+EXPORT_SYMBOL_GPL(vfio_file_enforced_coherent);
+
+/**
+ * vfio_file_set_kvm - Link a kvm with VFIO drivers
+ * @file: VFIO group file
+ * @kvm: KVM to link
+ *
+ * When a VFIO device is first opened the KVM will be available in
+ * device->kvm if one was associated with the group.
+ */
+void vfio_file_set_kvm(struct file *file, struct kvm *kvm)
+{
+ struct vfio_group *group = file->private_data;
+
+ if (!vfio_file_is_group(file))
+ return;
+
+ mutex_lock(&group->group_lock);
+ group->kvm = kvm;
+ mutex_unlock(&group->group_lock);
+}
+EXPORT_SYMBOL_GPL(vfio_file_set_kvm);
+
+/**
+ * vfio_file_has_dev - True if the VFIO file is a handle for device
+ * @file: VFIO file to check
+ * @device: Device that must be part of the file
+ *
+ * Returns true if given file has permission to manipulate the given device.
+ */
+bool vfio_file_has_dev(struct file *file, struct vfio_device *device)
+{
+ struct vfio_group *group = file->private_data;
+
+ if (!vfio_file_is_group(file))
+ return false;
+
+ return group == device->group;
+}
+EXPORT_SYMBOL_GPL(vfio_file_has_dev);
+
+static char *vfio_devnode(const struct device *dev, umode_t *mode)
+{
+ return kasprintf(GFP_KERNEL, "vfio/%s", dev_name(dev));
+}
+
+int __init vfio_group_init(void)
+{
+ int ret;
+
+ ida_init(&vfio.group_ida);
+ mutex_init(&vfio.group_lock);
+ INIT_LIST_HEAD(&vfio.group_list);
+
+ ret = vfio_container_init();
+ if (ret)
+ return ret;
+
+ /* /dev/vfio/$GROUP */
+ vfio.class = class_create(THIS_MODULE, "vfio");
+ if (IS_ERR(vfio.class)) {
+ ret = PTR_ERR(vfio.class);
+ goto err_group_class;
+ }
+
+ vfio.class->devnode = vfio_devnode;
+
+ ret = alloc_chrdev_region(&vfio.group_devt, 0, MINORMASK + 1, "vfio");
+ if (ret)
+ goto err_alloc_chrdev;
+ return 0;
+
+err_alloc_chrdev:
+ class_destroy(vfio.class);
+ vfio.class = NULL;
+err_group_class:
+ vfio_container_cleanup();
+ return ret;
+}
+
+void vfio_group_cleanup(void)
+{
+ WARN_ON(!list_empty(&vfio.group_list));
+ ida_destroy(&vfio.group_ida);
+ unregister_chrdev_region(vfio.group_devt, MINORMASK + 1);
+ class_destroy(vfio.class);
+ vfio.class = NULL;
+ vfio_container_cleanup();
+}
diff --git a/drivers/vfio/iommufd.c b/drivers/vfio/iommufd.c
new file mode 100644
index 000000000000..4f82a6fa7c6c
--- /dev/null
+++ b/drivers/vfio/iommufd.c
@@ -0,0 +1,158 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (c) 2021-2022, NVIDIA CORPORATION & AFFILIATES
+ */
+#include <linux/vfio.h>
+#include <linux/iommufd.h>
+
+#include "vfio.h"
+
+MODULE_IMPORT_NS(IOMMUFD);
+MODULE_IMPORT_NS(IOMMUFD_VFIO);
+
+int vfio_iommufd_bind(struct vfio_device *vdev, struct iommufd_ctx *ictx)
+{
+ u32 ioas_id;
+ u32 device_id;
+ int ret;
+
+ lockdep_assert_held(&vdev->dev_set->lock);
+
+ /*
+ * If the driver doesn't provide this op then it means the device does
+ * not do DMA at all. So nothing to do.
+ */
+ if (!vdev->ops->bind_iommufd)
+ return 0;
+
+ ret = vdev->ops->bind_iommufd(vdev, ictx, &device_id);
+ if (ret)
+ return ret;
+
+ ret = iommufd_vfio_compat_ioas_id(ictx, &ioas_id);
+ if (ret)
+ goto err_unbind;
+ ret = vdev->ops->attach_ioas(vdev, &ioas_id);
+ if (ret)
+ goto err_unbind;
+
+ /*
+ * The legacy path has no way to return the device id or the selected
+ * pt_id
+ */
+ return 0;
+
+err_unbind:
+ if (vdev->ops->unbind_iommufd)
+ vdev->ops->unbind_iommufd(vdev);
+ return ret;
+}
+
+void vfio_iommufd_unbind(struct vfio_device *vdev)
+{
+ lockdep_assert_held(&vdev->dev_set->lock);
+
+ if (vdev->ops->unbind_iommufd)
+ vdev->ops->unbind_iommufd(vdev);
+}
+
+/*
+ * The physical standard ops mean that the iommufd_device is bound to the
+ * physical device vdev->dev that was provided to vfio_init_group_dev(). Drivers
+ * using this ops set should call vfio_register_group_dev()
+ */
+int vfio_iommufd_physical_bind(struct vfio_device *vdev,
+ struct iommufd_ctx *ictx, u32 *out_device_id)
+{
+ struct iommufd_device *idev;
+
+ idev = iommufd_device_bind(ictx, vdev->dev, out_device_id);
+ if (IS_ERR(idev))
+ return PTR_ERR(idev);
+ vdev->iommufd_device = idev;
+ return 0;
+}
+EXPORT_SYMBOL_GPL(vfio_iommufd_physical_bind);
+
+void vfio_iommufd_physical_unbind(struct vfio_device *vdev)
+{
+ lockdep_assert_held(&vdev->dev_set->lock);
+
+ if (vdev->iommufd_attached) {
+ iommufd_device_detach(vdev->iommufd_device);
+ vdev->iommufd_attached = false;
+ }
+ iommufd_device_unbind(vdev->iommufd_device);
+ vdev->iommufd_device = NULL;
+}
+EXPORT_SYMBOL_GPL(vfio_iommufd_physical_unbind);
+
+int vfio_iommufd_physical_attach_ioas(struct vfio_device *vdev, u32 *pt_id)
+{
+ int rc;
+
+ rc = iommufd_device_attach(vdev->iommufd_device, pt_id);
+ if (rc)
+ return rc;
+ vdev->iommufd_attached = true;
+ return 0;
+}
+EXPORT_SYMBOL_GPL(vfio_iommufd_physical_attach_ioas);
+
+/*
+ * The emulated standard ops mean that vfio_device is going to use the
+ * "mdev path" and will call vfio_pin_pages()/vfio_dma_rw(). Drivers using this
+ * ops set should call vfio_register_emulated_iommu_dev().
+ */
+
+static void vfio_emulated_unmap(void *data, unsigned long iova,
+ unsigned long length)
+{
+ struct vfio_device *vdev = data;
+
+ vdev->ops->dma_unmap(vdev, iova, length);
+}
+
+static const struct iommufd_access_ops vfio_user_ops = {
+ .needs_pin_pages = 1,
+ .unmap = vfio_emulated_unmap,
+};
+
+int vfio_iommufd_emulated_bind(struct vfio_device *vdev,
+ struct iommufd_ctx *ictx, u32 *out_device_id)
+{
+ lockdep_assert_held(&vdev->dev_set->lock);
+
+ vdev->iommufd_ictx = ictx;
+ iommufd_ctx_get(ictx);
+ return 0;
+}
+EXPORT_SYMBOL_GPL(vfio_iommufd_emulated_bind);
+
+void vfio_iommufd_emulated_unbind(struct vfio_device *vdev)
+{
+ lockdep_assert_held(&vdev->dev_set->lock);
+
+ if (vdev->iommufd_access) {
+ iommufd_access_destroy(vdev->iommufd_access);
+ vdev->iommufd_access = NULL;
+ }
+ iommufd_ctx_put(vdev->iommufd_ictx);
+ vdev->iommufd_ictx = NULL;
+}
+EXPORT_SYMBOL_GPL(vfio_iommufd_emulated_unbind);
+
+int vfio_iommufd_emulated_attach_ioas(struct vfio_device *vdev, u32 *pt_id)
+{
+ struct iommufd_access *user;
+
+ lockdep_assert_held(&vdev->dev_set->lock);
+
+ user = iommufd_access_create(vdev->iommufd_ictx, *pt_id, &vfio_user_ops,
+ vdev);
+ if (IS_ERR(user))
+ return PTR_ERR(user);
+ vdev->iommufd_access = user;
+ return 0;
+}
+EXPORT_SYMBOL_GPL(vfio_iommufd_emulated_attach_ioas);
diff --git a/drivers/vfio/iova_bitmap.c b/drivers/vfio/iova_bitmap.c
index 6631e8befe1b..0848f920efb7 100644
--- a/drivers/vfio/iova_bitmap.c
+++ b/drivers/vfio/iova_bitmap.c
@@ -5,6 +5,7 @@
*/
#include <linux/iova_bitmap.h>
#include <linux/mm.h>
+#include <linux/slab.h>
#include <linux/highmem.h>
#define BITS_PER_PAGE (PAGE_SIZE * BITS_PER_BYTE)
@@ -295,11 +296,13 @@ void iova_bitmap_free(struct iova_bitmap *bitmap)
*/
static unsigned long iova_bitmap_mapped_remaining(struct iova_bitmap *bitmap)
{
- unsigned long remaining;
+ unsigned long remaining, bytes;
+
+ bytes = (bitmap->mapped.npages << PAGE_SHIFT) - bitmap->mapped.pgoff;
remaining = bitmap->mapped_total_index - bitmap->mapped_base_index;
remaining = min_t(unsigned long, remaining,
- (bitmap->mapped.npages << PAGE_SHIFT) / sizeof(*bitmap->bitmap));
+ bytes / sizeof(*bitmap->bitmap));
return remaining;
}
@@ -394,29 +397,27 @@ int iova_bitmap_for_each(struct iova_bitmap *bitmap, void *opaque,
* Set the bits corresponding to the range [iova .. iova+length-1] in
* the user bitmap.
*
- * Return: The number of bits set.
*/
void iova_bitmap_set(struct iova_bitmap *bitmap,
unsigned long iova, size_t length)
{
struct iova_bitmap_map *mapped = &bitmap->mapped;
- unsigned long offset = (iova - mapped->iova) >> mapped->pgshift;
- unsigned long nbits = max_t(unsigned long, 1, length >> mapped->pgshift);
- unsigned long page_idx = offset / BITS_PER_PAGE;
- unsigned long page_offset = mapped->pgoff;
- void *kaddr;
-
- offset = offset % BITS_PER_PAGE;
+ unsigned long cur_bit = ((iova - mapped->iova) >>
+ mapped->pgshift) + mapped->pgoff * BITS_PER_BYTE;
+ unsigned long last_bit = (((iova + length - 1) - mapped->iova) >>
+ mapped->pgshift) + mapped->pgoff * BITS_PER_BYTE;
do {
- unsigned long size = min(BITS_PER_PAGE - offset, nbits);
+ unsigned int page_idx = cur_bit / BITS_PER_PAGE;
+ unsigned int offset = cur_bit % BITS_PER_PAGE;
+ unsigned int nbits = min(BITS_PER_PAGE - offset,
+ last_bit - cur_bit + 1);
+ void *kaddr;
kaddr = kmap_local_page(mapped->pages[page_idx]);
- bitmap_set(kaddr + page_offset, offset, size);
+ bitmap_set(kaddr, offset, nbits);
kunmap_local(kaddr);
- page_offset = offset = 0;
- nbits -= size;
- page_idx++;
- } while (nbits > 0);
+ cur_bit += nbits;
+ } while (cur_bit <= last_bit);
}
EXPORT_SYMBOL_GPL(iova_bitmap_set);
diff --git a/drivers/vfio/pci/hisilicon/hisi_acc_vfio_pci.c b/drivers/vfio/pci/hisilicon/hisi_acc_vfio_pci.c
index 39eeca18a0f7..0bba3b05c6c7 100644
--- a/drivers/vfio/pci/hisilicon/hisi_acc_vfio_pci.c
+++ b/drivers/vfio/pci/hisilicon/hisi_acc_vfio_pci.c
@@ -360,8 +360,8 @@ static int vf_qm_check_match(struct hisi_acc_vf_core_device *hisi_acc_vdev,
u32 que_iso_state;
int ret;
- if (migf->total_length < QM_MATCH_SIZE)
- return -EINVAL;
+ if (migf->total_length < QM_MATCH_SIZE || hisi_acc_vdev->match_done)
+ return 0;
if (vf_data->acc_magic != ACC_DEV_MAGIC) {
dev_err(dev, "failed to match ACC_DEV_MAGIC\n");
@@ -406,6 +406,7 @@ static int vf_qm_check_match(struct hisi_acc_vf_core_device *hisi_acc_vdev,
}
hisi_acc_vdev->vf_qm_state = vf_data->vf_qm_state;
+ hisi_acc_vdev->match_done = true;
return 0;
}
@@ -493,10 +494,6 @@ static int vf_qm_state_save(struct hisi_acc_vf_core_device *hisi_acc_vdev,
struct device *dev = &vf_qm->pdev->dev;
int ret;
- ret = vf_qm_get_match_data(hisi_acc_vdev, vf_data);
- if (ret)
- return ret;
-
if (unlikely(qm_wait_dev_not_ready(vf_qm))) {
/* Update state and return with match data */
vf_data->vf_qm_state = QM_NOT_READY;
@@ -673,12 +670,6 @@ static int hisi_acc_vf_load_state(struct hisi_acc_vf_core_device *hisi_acc_vdev)
struct hisi_acc_vf_migration_file *migf = hisi_acc_vdev->resuming_migf;
int ret;
- /* Check dev compatibility */
- ret = vf_qm_check_match(hisi_acc_vdev, migf);
- if (ret) {
- dev_err(dev, "failed to match the VF!\n");
- return ret;
- }
/* Recover data to VF */
ret = vf_qm_load_data(hisi_acc_vdev, migf);
if (ret) {
@@ -732,6 +723,10 @@ static ssize_t hisi_acc_vf_resume_write(struct file *filp, const char __user *bu
*pos += len;
done = len;
migf->total_length += len;
+
+ ret = vf_qm_check_match(migf->hisi_acc_vdev, migf);
+ if (ret)
+ done = -EFAULT;
out_unlock:
mutex_unlock(&migf->lock);
return done;
@@ -764,9 +759,58 @@ hisi_acc_vf_pci_resume(struct hisi_acc_vf_core_device *hisi_acc_vdev)
stream_open(migf->filp->f_inode, migf->filp);
mutex_init(&migf->lock);
+ migf->hisi_acc_vdev = hisi_acc_vdev;
return migf;
}
+static long hisi_acc_vf_precopy_ioctl(struct file *filp,
+ unsigned int cmd, unsigned long arg)
+{
+ struct hisi_acc_vf_migration_file *migf = filp->private_data;
+ struct hisi_acc_vf_core_device *hisi_acc_vdev = migf->hisi_acc_vdev;
+ loff_t *pos = &filp->f_pos;
+ struct vfio_precopy_info info;
+ unsigned long minsz;
+ int ret;
+
+ if (cmd != VFIO_MIG_GET_PRECOPY_INFO)
+ return -ENOTTY;
+
+ minsz = offsetofend(struct vfio_precopy_info, dirty_bytes);
+
+ if (copy_from_user(&info, (void __user *)arg, minsz))
+ return -EFAULT;
+ if (info.argsz < minsz)
+ return -EINVAL;
+
+ mutex_lock(&hisi_acc_vdev->state_mutex);
+ if (hisi_acc_vdev->mig_state != VFIO_DEVICE_STATE_PRE_COPY) {
+ mutex_unlock(&hisi_acc_vdev->state_mutex);
+ return -EINVAL;
+ }
+
+ mutex_lock(&migf->lock);
+
+ if (migf->disabled) {
+ ret = -ENODEV;
+ goto out;
+ }
+
+ if (*pos > migf->total_length) {
+ ret = -EINVAL;
+ goto out;
+ }
+
+ info.dirty_bytes = 0;
+ info.initial_bytes = migf->total_length - *pos;
+
+ ret = copy_to_user((void __user *)arg, &info, minsz) ? -EFAULT : 0;
+out:
+ mutex_unlock(&migf->lock);
+ mutex_unlock(&hisi_acc_vdev->state_mutex);
+ return ret;
+}
+
static ssize_t hisi_acc_vf_save_read(struct file *filp, char __user *buf, size_t len,
loff_t *pos)
{
@@ -807,12 +851,14 @@ out_unlock:
static const struct file_operations hisi_acc_vf_save_fops = {
.owner = THIS_MODULE,
.read = hisi_acc_vf_save_read,
+ .unlocked_ioctl = hisi_acc_vf_precopy_ioctl,
+ .compat_ioctl = compat_ptr_ioctl,
.release = hisi_acc_vf_release_file,
.llseek = no_llseek,
};
static struct hisi_acc_vf_migration_file *
-hisi_acc_vf_stop_copy(struct hisi_acc_vf_core_device *hisi_acc_vdev)
+hisi_acc_open_saving_migf(struct hisi_acc_vf_core_device *hisi_acc_vdev)
{
struct hisi_acc_vf_migration_file *migf;
int ret;
@@ -832,8 +878,9 @@ hisi_acc_vf_stop_copy(struct hisi_acc_vf_core_device *hisi_acc_vdev)
stream_open(migf->filp->f_inode, migf->filp);
mutex_init(&migf->lock);
+ migf->hisi_acc_vdev = hisi_acc_vdev;
- ret = vf_qm_state_save(hisi_acc_vdev, migf);
+ ret = vf_qm_get_match_data(hisi_acc_vdev, &migf->vf_data);
if (ret) {
fput(migf->filp);
return ERR_PTR(ret);
@@ -842,6 +889,44 @@ hisi_acc_vf_stop_copy(struct hisi_acc_vf_core_device *hisi_acc_vdev)
return migf;
}
+static struct hisi_acc_vf_migration_file *
+hisi_acc_vf_pre_copy(struct hisi_acc_vf_core_device *hisi_acc_vdev)
+{
+ struct hisi_acc_vf_migration_file *migf;
+
+ migf = hisi_acc_open_saving_migf(hisi_acc_vdev);
+ if (IS_ERR(migf))
+ return migf;
+
+ migf->total_length = QM_MATCH_SIZE;
+ return migf;
+}
+
+static struct hisi_acc_vf_migration_file *
+hisi_acc_vf_stop_copy(struct hisi_acc_vf_core_device *hisi_acc_vdev, bool open)
+{
+ int ret;
+ struct hisi_acc_vf_migration_file *migf = NULL;
+
+ if (open) {
+ /*
+ * Userspace didn't use PRECOPY support. Hence saving_migf
+ * is not opened yet.
+ */
+ migf = hisi_acc_open_saving_migf(hisi_acc_vdev);
+ if (IS_ERR(migf))
+ return migf;
+ } else {
+ migf = hisi_acc_vdev->saving_migf;
+ }
+
+ ret = vf_qm_state_save(hisi_acc_vdev, migf);
+ if (ret)
+ return ERR_PTR(ret);
+
+ return open ? migf : NULL;
+}
+
static int hisi_acc_vf_stop_device(struct hisi_acc_vf_core_device *hisi_acc_vdev)
{
struct device *dev = &hisi_acc_vdev->vf_dev->dev;
@@ -869,6 +954,31 @@ hisi_acc_vf_set_device_state(struct hisi_acc_vf_core_device *hisi_acc_vdev,
u32 cur = hisi_acc_vdev->mig_state;
int ret;
+ if (cur == VFIO_DEVICE_STATE_RUNNING && new == VFIO_DEVICE_STATE_PRE_COPY) {
+ struct hisi_acc_vf_migration_file *migf;
+
+ migf = hisi_acc_vf_pre_copy(hisi_acc_vdev);
+ if (IS_ERR(migf))
+ return ERR_CAST(migf);
+ get_file(migf->filp);
+ hisi_acc_vdev->saving_migf = migf;
+ return migf->filp;
+ }
+
+ if (cur == VFIO_DEVICE_STATE_PRE_COPY && new == VFIO_DEVICE_STATE_STOP_COPY) {
+ struct hisi_acc_vf_migration_file *migf;
+
+ ret = hisi_acc_vf_stop_device(hisi_acc_vdev);
+ if (ret)
+ return ERR_PTR(ret);
+
+ migf = hisi_acc_vf_stop_copy(hisi_acc_vdev, false);
+ if (IS_ERR(migf))
+ return ERR_CAST(migf);
+
+ return NULL;
+ }
+
if (cur == VFIO_DEVICE_STATE_RUNNING && new == VFIO_DEVICE_STATE_STOP) {
ret = hisi_acc_vf_stop_device(hisi_acc_vdev);
if (ret)
@@ -879,7 +989,7 @@ hisi_acc_vf_set_device_state(struct hisi_acc_vf_core_device *hisi_acc_vdev,
if (cur == VFIO_DEVICE_STATE_STOP && new == VFIO_DEVICE_STATE_STOP_COPY) {
struct hisi_acc_vf_migration_file *migf;
- migf = hisi_acc_vf_stop_copy(hisi_acc_vdev);
+ migf = hisi_acc_vf_stop_copy(hisi_acc_vdev, true);
if (IS_ERR(migf))
return ERR_CAST(migf);
get_file(migf->filp);
@@ -911,6 +1021,11 @@ hisi_acc_vf_set_device_state(struct hisi_acc_vf_core_device *hisi_acc_vdev,
return NULL;
}
+ if (cur == VFIO_DEVICE_STATE_PRE_COPY && new == VFIO_DEVICE_STATE_RUNNING) {
+ hisi_acc_vf_disable_fds(hisi_acc_vdev);
+ return NULL;
+ }
+
if (cur == VFIO_DEVICE_STATE_STOP && new == VFIO_DEVICE_STATE_RUNNING) {
hisi_acc_vf_start_device(hisi_acc_vdev);
return NULL;
@@ -958,6 +1073,14 @@ hisi_acc_vfio_pci_set_device_state(struct vfio_device *vdev,
}
static int
+hisi_acc_vfio_pci_get_data_size(struct vfio_device *vdev,
+ unsigned long *stop_copy_length)
+{
+ *stop_copy_length = sizeof(struct acc_vf_data);
+ return 0;
+}
+
+static int
hisi_acc_vfio_pci_get_device_state(struct vfio_device *vdev,
enum vfio_device_mig_state *curr_state)
{
@@ -1213,6 +1336,7 @@ static void hisi_acc_vfio_pci_close_device(struct vfio_device *core_vdev)
static const struct vfio_migration_ops hisi_acc_vfio_pci_migrn_state_ops = {
.migration_set_state = hisi_acc_vfio_pci_set_device_state,
.migration_get_state = hisi_acc_vfio_pci_get_device_state,
+ .migration_get_data_size = hisi_acc_vfio_pci_get_data_size,
};
static int hisi_acc_vfio_pci_migrn_init_dev(struct vfio_device *core_vdev)
@@ -1227,7 +1351,7 @@ static int hisi_acc_vfio_pci_migrn_init_dev(struct vfio_device *core_vdev)
hisi_acc_vdev->vf_dev = pdev;
mutex_init(&hisi_acc_vdev->state_mutex);
- core_vdev->migration_flags = VFIO_MIGRATION_STOP_COPY;
+ core_vdev->migration_flags = VFIO_MIGRATION_STOP_COPY | VFIO_MIGRATION_PRE_COPY;
core_vdev->mig_ops = &hisi_acc_vfio_pci_migrn_state_ops;
return vfio_pci_core_init_dev(core_vdev);
@@ -1246,6 +1370,9 @@ static const struct vfio_device_ops hisi_acc_vfio_pci_migrn_ops = {
.mmap = hisi_acc_vfio_pci_mmap,
.request = vfio_pci_core_request,
.match = vfio_pci_core_match,
+ .bind_iommufd = vfio_iommufd_physical_bind,
+ .unbind_iommufd = vfio_iommufd_physical_unbind,
+ .attach_ioas = vfio_iommufd_physical_attach_ioas,
};
static const struct vfio_device_ops hisi_acc_vfio_pci_ops = {
@@ -1261,6 +1388,9 @@ static const struct vfio_device_ops hisi_acc_vfio_pci_ops = {
.mmap = vfio_pci_core_mmap,
.request = vfio_pci_core_request,
.match = vfio_pci_core_match,
+ .bind_iommufd = vfio_iommufd_physical_bind,
+ .unbind_iommufd = vfio_iommufd_physical_unbind,
+ .attach_ioas = vfio_iommufd_physical_attach_ioas,
};
static int hisi_acc_vfio_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
diff --git a/drivers/vfio/pci/hisilicon/hisi_acc_vfio_pci.h b/drivers/vfio/pci/hisilicon/hisi_acc_vfio_pci.h
index 67343325b320..dcabfeec6ca1 100644
--- a/drivers/vfio/pci/hisilicon/hisi_acc_vfio_pci.h
+++ b/drivers/vfio/pci/hisilicon/hisi_acc_vfio_pci.h
@@ -91,12 +91,14 @@ struct hisi_acc_vf_migration_file {
struct mutex lock;
bool disabled;
+ struct hisi_acc_vf_core_device *hisi_acc_vdev;
struct acc_vf_data vf_data;
size_t total_length;
};
struct hisi_acc_vf_core_device {
struct vfio_pci_core_device core_device;
+ u8 match_done:1;
u8 deferred_reset:1;
/* For migration state */
struct mutex state_mutex;
diff --git a/drivers/vfio/pci/mlx5/cmd.c b/drivers/vfio/pci/mlx5/cmd.c
index c604b70437a5..64e68d13cb98 100644
--- a/drivers/vfio/pci/mlx5/cmd.c
+++ b/drivers/vfio/pci/mlx5/cmd.c
@@ -14,18 +14,36 @@ _mlx5vf_free_page_tracker_resources(struct mlx5vf_pci_core_device *mvdev);
int mlx5vf_cmd_suspend_vhca(struct mlx5vf_pci_core_device *mvdev, u16 op_mod)
{
+ struct mlx5_vf_migration_file *migf = mvdev->saving_migf;
u32 out[MLX5_ST_SZ_DW(suspend_vhca_out)] = {};
u32 in[MLX5_ST_SZ_DW(suspend_vhca_in)] = {};
+ int err;
lockdep_assert_held(&mvdev->state_mutex);
if (mvdev->mdev_detach)
return -ENOTCONN;
+ /*
+ * In case PRE_COPY is used, saving_migf is exposed while the device is
+ * running. Make sure to run only once there is no active save command.
+ * Running both in parallel, might end-up with a failure in the save
+ * command once it will try to turn on 'tracking' on a suspended device.
+ */
+ if (migf) {
+ err = wait_for_completion_interruptible(&migf->save_comp);
+ if (err)
+ return err;
+ }
+
MLX5_SET(suspend_vhca_in, in, opcode, MLX5_CMD_OP_SUSPEND_VHCA);
MLX5_SET(suspend_vhca_in, in, vhca_id, mvdev->vhca_id);
MLX5_SET(suspend_vhca_in, in, op_mod, op_mod);
- return mlx5_cmd_exec_inout(mvdev->mdev, suspend_vhca, in, out);
+ err = mlx5_cmd_exec_inout(mvdev->mdev, suspend_vhca, in, out);
+ if (migf)
+ complete(&migf->save_comp);
+
+ return err;
}
int mlx5vf_cmd_resume_vhca(struct mlx5vf_pci_core_device *mvdev, u16 op_mod)
@@ -45,23 +63,54 @@ int mlx5vf_cmd_resume_vhca(struct mlx5vf_pci_core_device *mvdev, u16 op_mod)
}
int mlx5vf_cmd_query_vhca_migration_state(struct mlx5vf_pci_core_device *mvdev,
- size_t *state_size)
+ size_t *state_size, u8 query_flags)
{
u32 out[MLX5_ST_SZ_DW(query_vhca_migration_state_out)] = {};
u32 in[MLX5_ST_SZ_DW(query_vhca_migration_state_in)] = {};
+ bool inc = query_flags & MLX5VF_QUERY_INC;
int ret;
lockdep_assert_held(&mvdev->state_mutex);
if (mvdev->mdev_detach)
return -ENOTCONN;
+ /*
+ * In case PRE_COPY is used, saving_migf is exposed while device is
+ * running. Make sure to run only once there is no active save command.
+ * Running both in parallel, might end-up with a failure in the
+ * incremental query command on un-tracked vhca.
+ */
+ if (inc) {
+ ret = wait_for_completion_interruptible(&mvdev->saving_migf->save_comp);
+ if (ret)
+ return ret;
+ if (mvdev->saving_migf->state ==
+ MLX5_MIGF_STATE_PRE_COPY_ERROR) {
+ /*
+ * In case we had a PRE_COPY error, only query full
+ * image for final image
+ */
+ if (!(query_flags & MLX5VF_QUERY_FINAL)) {
+ *state_size = 0;
+ complete(&mvdev->saving_migf->save_comp);
+ return 0;
+ }
+ query_flags &= ~MLX5VF_QUERY_INC;
+ }
+ }
+
MLX5_SET(query_vhca_migration_state_in, in, opcode,
MLX5_CMD_OP_QUERY_VHCA_MIGRATION_STATE);
MLX5_SET(query_vhca_migration_state_in, in, vhca_id, mvdev->vhca_id);
MLX5_SET(query_vhca_migration_state_in, in, op_mod, 0);
+ MLX5_SET(query_vhca_migration_state_in, in, incremental,
+ query_flags & MLX5VF_QUERY_INC);
ret = mlx5_cmd_exec_inout(mvdev->mdev, query_vhca_migration_state, in,
out);
+ if (inc)
+ complete(&mvdev->saving_migf->save_comp);
+
if (ret)
return ret;
@@ -173,6 +222,11 @@ void mlx5vf_cmd_set_migratable(struct mlx5vf_pci_core_device *mvdev,
if (MLX5_CAP_GEN(mvdev->mdev, adv_virtualization))
mvdev->core_device.vdev.log_ops = log_ops;
+ if (MLX5_CAP_GEN_2(mvdev->mdev, migration_multi_load) &&
+ MLX5_CAP_GEN_2(mvdev->mdev, migration_tracking_state))
+ mvdev->core_device.vdev.migration_flags |=
+ VFIO_MIGRATION_PRE_COPY;
+
end:
mlx5_vf_put_core_dev(mvdev->mdev);
}
@@ -210,11 +264,11 @@ err_exec:
}
static int _create_mkey(struct mlx5_core_dev *mdev, u32 pdn,
- struct mlx5_vf_migration_file *migf,
+ struct mlx5_vhca_data_buffer *buf,
struct mlx5_vhca_recv_buf *recv_buf,
u32 *mkey)
{
- size_t npages = migf ? DIV_ROUND_UP(migf->total_length, PAGE_SIZE) :
+ size_t npages = buf ? DIV_ROUND_UP(buf->allocated_length, PAGE_SIZE) :
recv_buf->npages;
int err = 0, inlen;
__be64 *mtt;
@@ -232,10 +286,10 @@ static int _create_mkey(struct mlx5_core_dev *mdev, u32 pdn,
DIV_ROUND_UP(npages, 2));
mtt = (__be64 *)MLX5_ADDR_OF(create_mkey_in, in, klm_pas_mtt);
- if (migf) {
+ if (buf) {
struct sg_dma_page_iter dma_iter;
- for_each_sgtable_dma_page(&migf->table.sgt, &dma_iter, 0)
+ for_each_sgtable_dma_page(&buf->table.sgt, &dma_iter, 0)
*mtt++ = cpu_to_be64(sg_page_iter_dma_address(&dma_iter));
} else {
int i;
@@ -255,35 +309,195 @@ static int _create_mkey(struct mlx5_core_dev *mdev, u32 pdn,
MLX5_SET(mkc, mkc, qpn, 0xffffff);
MLX5_SET(mkc, mkc, log_page_size, PAGE_SHIFT);
MLX5_SET(mkc, mkc, translations_octword_size, DIV_ROUND_UP(npages, 2));
- MLX5_SET64(mkc, mkc, len,
- migf ? migf->total_length : (npages * PAGE_SIZE));
+ MLX5_SET64(mkc, mkc, len, npages * PAGE_SIZE);
err = mlx5_core_create_mkey(mdev, mkey, in, inlen);
kvfree(in);
return err;
}
+static int mlx5vf_dma_data_buffer(struct mlx5_vhca_data_buffer *buf)
+{
+ struct mlx5vf_pci_core_device *mvdev = buf->migf->mvdev;
+ struct mlx5_core_dev *mdev = mvdev->mdev;
+ int ret;
+
+ lockdep_assert_held(&mvdev->state_mutex);
+ if (mvdev->mdev_detach)
+ return -ENOTCONN;
+
+ if (buf->dmaed || !buf->allocated_length)
+ return -EINVAL;
+
+ ret = dma_map_sgtable(mdev->device, &buf->table.sgt, buf->dma_dir, 0);
+ if (ret)
+ return ret;
+
+ ret = _create_mkey(mdev, buf->migf->pdn, buf, NULL, &buf->mkey);
+ if (ret)
+ goto err;
+
+ buf->dmaed = true;
+
+ return 0;
+err:
+ dma_unmap_sgtable(mdev->device, &buf->table.sgt, buf->dma_dir, 0);
+ return ret;
+}
+
+void mlx5vf_free_data_buffer(struct mlx5_vhca_data_buffer *buf)
+{
+ struct mlx5_vf_migration_file *migf = buf->migf;
+ struct sg_page_iter sg_iter;
+
+ lockdep_assert_held(&migf->mvdev->state_mutex);
+ WARN_ON(migf->mvdev->mdev_detach);
+
+ if (buf->dmaed) {
+ mlx5_core_destroy_mkey(migf->mvdev->mdev, buf->mkey);
+ dma_unmap_sgtable(migf->mvdev->mdev->device, &buf->table.sgt,
+ buf->dma_dir, 0);
+ }
+
+ /* Undo alloc_pages_bulk_array() */
+ for_each_sgtable_page(&buf->table.sgt, &sg_iter, 0)
+ __free_page(sg_page_iter_page(&sg_iter));
+ sg_free_append_table(&buf->table);
+ kfree(buf);
+}
+
+struct mlx5_vhca_data_buffer *
+mlx5vf_alloc_data_buffer(struct mlx5_vf_migration_file *migf,
+ size_t length,
+ enum dma_data_direction dma_dir)
+{
+ struct mlx5_vhca_data_buffer *buf;
+ int ret;
+
+ buf = kzalloc(sizeof(*buf), GFP_KERNEL);
+ if (!buf)
+ return ERR_PTR(-ENOMEM);
+
+ buf->dma_dir = dma_dir;
+ buf->migf = migf;
+ if (length) {
+ ret = mlx5vf_add_migration_pages(buf,
+ DIV_ROUND_UP_ULL(length, PAGE_SIZE));
+ if (ret)
+ goto end;
+
+ if (dma_dir != DMA_NONE) {
+ ret = mlx5vf_dma_data_buffer(buf);
+ if (ret)
+ goto end;
+ }
+ }
+
+ return buf;
+end:
+ mlx5vf_free_data_buffer(buf);
+ return ERR_PTR(ret);
+}
+
+void mlx5vf_put_data_buffer(struct mlx5_vhca_data_buffer *buf)
+{
+ spin_lock_irq(&buf->migf->list_lock);
+ list_add_tail(&buf->buf_elm, &buf->migf->avail_list);
+ spin_unlock_irq(&buf->migf->list_lock);
+}
+
+struct mlx5_vhca_data_buffer *
+mlx5vf_get_data_buffer(struct mlx5_vf_migration_file *migf,
+ size_t length, enum dma_data_direction dma_dir)
+{
+ struct mlx5_vhca_data_buffer *buf, *temp_buf;
+ struct list_head free_list;
+
+ lockdep_assert_held(&migf->mvdev->state_mutex);
+ if (migf->mvdev->mdev_detach)
+ return ERR_PTR(-ENOTCONN);
+
+ INIT_LIST_HEAD(&free_list);
+
+ spin_lock_irq(&migf->list_lock);
+ list_for_each_entry_safe(buf, temp_buf, &migf->avail_list, buf_elm) {
+ if (buf->dma_dir == dma_dir) {
+ list_del_init(&buf->buf_elm);
+ if (buf->allocated_length >= length) {
+ spin_unlock_irq(&migf->list_lock);
+ goto found;
+ }
+ /*
+ * Prevent holding redundant buffers. Put in a free
+ * list and call at the end not under the spin lock
+ * (&migf->list_lock) to mlx5vf_free_data_buffer which
+ * might sleep.
+ */
+ list_add(&buf->buf_elm, &free_list);
+ }
+ }
+ spin_unlock_irq(&migf->list_lock);
+ buf = mlx5vf_alloc_data_buffer(migf, length, dma_dir);
+
+found:
+ while ((temp_buf = list_first_entry_or_null(&free_list,
+ struct mlx5_vhca_data_buffer, buf_elm))) {
+ list_del(&temp_buf->buf_elm);
+ mlx5vf_free_data_buffer(temp_buf);
+ }
+
+ return buf;
+}
+
void mlx5vf_mig_file_cleanup_cb(struct work_struct *_work)
{
struct mlx5vf_async_data *async_data = container_of(_work,
struct mlx5vf_async_data, work);
struct mlx5_vf_migration_file *migf = container_of(async_data,
struct mlx5_vf_migration_file, async_data);
- struct mlx5_core_dev *mdev = migf->mvdev->mdev;
mutex_lock(&migf->lock);
if (async_data->status) {
- migf->is_err = true;
+ mlx5vf_put_data_buffer(async_data->buf);
+ if (async_data->header_buf)
+ mlx5vf_put_data_buffer(async_data->header_buf);
+ if (async_data->status == MLX5_CMD_STAT_BAD_RES_STATE_ERR)
+ migf->state = MLX5_MIGF_STATE_PRE_COPY_ERROR;
+ else
+ migf->state = MLX5_MIGF_STATE_ERROR;
wake_up_interruptible(&migf->poll_wait);
}
mutex_unlock(&migf->lock);
-
- mlx5_core_destroy_mkey(mdev, async_data->mkey);
- dma_unmap_sgtable(mdev->device, &migf->table.sgt, DMA_FROM_DEVICE, 0);
- mlx5_core_dealloc_pd(mdev, async_data->pdn);
kvfree(async_data->out);
+ complete(&migf->save_comp);
fput(migf->filp);
}
+static int add_buf_header(struct mlx5_vhca_data_buffer *header_buf,
+ size_t image_size)
+{
+ struct mlx5_vf_migration_file *migf = header_buf->migf;
+ struct mlx5_vf_migration_header header = {};
+ unsigned long flags;
+ struct page *page;
+ u8 *to_buff;
+
+ header.image_size = cpu_to_le64(image_size);
+ page = mlx5vf_get_migration_page(header_buf, 0);
+ if (!page)
+ return -EINVAL;
+ to_buff = kmap_local_page(page);
+ memcpy(to_buff, &header, sizeof(header));
+ kunmap_local(to_buff);
+ header_buf->length = sizeof(header);
+ header_buf->header_image_size = image_size;
+ header_buf->start_pos = header_buf->migf->max_pos;
+ migf->max_pos += header_buf->length;
+ spin_lock_irqsave(&migf->list_lock, flags);
+ list_add_tail(&header_buf->buf_elm, &migf->buf_list);
+ spin_unlock_irqrestore(&migf->list_lock, flags);
+ return 0;
+}
+
static void mlx5vf_save_callback(int status, struct mlx5_async_work *context)
{
struct mlx5vf_async_data *async_data = container_of(context,
@@ -292,67 +506,96 @@ static void mlx5vf_save_callback(int status, struct mlx5_async_work *context)
struct mlx5_vf_migration_file, async_data);
if (!status) {
- WRITE_ONCE(migf->total_length,
- MLX5_GET(save_vhca_state_out, async_data->out,
- actual_image_size));
+ size_t image_size;
+ unsigned long flags;
+
+ image_size = MLX5_GET(save_vhca_state_out, async_data->out,
+ actual_image_size);
+ if (async_data->header_buf) {
+ status = add_buf_header(async_data->header_buf, image_size);
+ if (status)
+ goto err;
+ }
+ async_data->buf->length = image_size;
+ async_data->buf->start_pos = migf->max_pos;
+ migf->max_pos += async_data->buf->length;
+ spin_lock_irqsave(&migf->list_lock, flags);
+ list_add_tail(&async_data->buf->buf_elm, &migf->buf_list);
+ spin_unlock_irqrestore(&migf->list_lock, flags);
+ migf->state = async_data->last_chunk ?
+ MLX5_MIGF_STATE_COMPLETE : MLX5_MIGF_STATE_PRE_COPY;
wake_up_interruptible(&migf->poll_wait);
}
+err:
/*
* The error and the cleanup flows can't run from an
* interrupt context
*/
+ if (status == -EREMOTEIO)
+ status = MLX5_GET(save_vhca_state_out, async_data->out, status);
async_data->status = status;
queue_work(migf->mvdev->cb_wq, &async_data->work);
}
int mlx5vf_cmd_save_vhca_state(struct mlx5vf_pci_core_device *mvdev,
- struct mlx5_vf_migration_file *migf)
+ struct mlx5_vf_migration_file *migf,
+ struct mlx5_vhca_data_buffer *buf, bool inc,
+ bool track)
{
u32 out_size = MLX5_ST_SZ_BYTES(save_vhca_state_out);
u32 in[MLX5_ST_SZ_DW(save_vhca_state_in)] = {};
+ struct mlx5_vhca_data_buffer *header_buf = NULL;
struct mlx5vf_async_data *async_data;
- struct mlx5_core_dev *mdev;
- u32 pdn, mkey;
int err;
lockdep_assert_held(&mvdev->state_mutex);
if (mvdev->mdev_detach)
return -ENOTCONN;
- mdev = mvdev->mdev;
- err = mlx5_core_alloc_pd(mdev, &pdn);
+ err = wait_for_completion_interruptible(&migf->save_comp);
if (err)
return err;
- err = dma_map_sgtable(mdev->device, &migf->table.sgt, DMA_FROM_DEVICE,
- 0);
- if (err)
- goto err_dma_map;
-
- err = _create_mkey(mdev, pdn, migf, NULL, &mkey);
- if (err)
- goto err_create_mkey;
+ if (migf->state == MLX5_MIGF_STATE_PRE_COPY_ERROR)
+ /*
+ * In case we had a PRE_COPY error, SAVE is triggered only for
+ * the final image, read device full image.
+ */
+ inc = false;
MLX5_SET(save_vhca_state_in, in, opcode,
MLX5_CMD_OP_SAVE_VHCA_STATE);
MLX5_SET(save_vhca_state_in, in, op_mod, 0);
MLX5_SET(save_vhca_state_in, in, vhca_id, mvdev->vhca_id);
- MLX5_SET(save_vhca_state_in, in, mkey, mkey);
- MLX5_SET(save_vhca_state_in, in, size, migf->total_length);
+ MLX5_SET(save_vhca_state_in, in, mkey, buf->mkey);
+ MLX5_SET(save_vhca_state_in, in, size, buf->allocated_length);
+ MLX5_SET(save_vhca_state_in, in, incremental, inc);
+ MLX5_SET(save_vhca_state_in, in, set_track, track);
async_data = &migf->async_data;
+ async_data->buf = buf;
+ async_data->last_chunk = !track;
async_data->out = kvzalloc(out_size, GFP_KERNEL);
if (!async_data->out) {
err = -ENOMEM;
goto err_out;
}
- /* no data exists till the callback comes back */
- migf->total_length = 0;
+ if (MLX5VF_PRE_COPY_SUPP(mvdev)) {
+ header_buf = mlx5vf_get_data_buffer(migf,
+ sizeof(struct mlx5_vf_migration_header), DMA_NONE);
+ if (IS_ERR(header_buf)) {
+ err = PTR_ERR(header_buf);
+ goto err_free;
+ }
+ }
+
+ if (async_data->last_chunk)
+ migf->state = MLX5_MIGF_STATE_SAVE_LAST;
+
+ async_data->header_buf = header_buf;
get_file(migf->filp);
- async_data->mkey = mkey;
- async_data->pdn = pdn;
err = mlx5_cmd_exec_cb(&migf->async_ctx, in, sizeof(in),
async_data->out,
out_size, mlx5vf_save_callback,
@@ -363,68 +606,92 @@ int mlx5vf_cmd_save_vhca_state(struct mlx5vf_pci_core_device *mvdev,
return 0;
err_exec:
+ if (header_buf)
+ mlx5vf_put_data_buffer(header_buf);
fput(migf->filp);
+err_free:
kvfree(async_data->out);
err_out:
- mlx5_core_destroy_mkey(mdev, mkey);
-err_create_mkey:
- dma_unmap_sgtable(mdev->device, &migf->table.sgt, DMA_FROM_DEVICE, 0);
-err_dma_map:
- mlx5_core_dealloc_pd(mdev, pdn);
+ complete(&migf->save_comp);
return err;
}
int mlx5vf_cmd_load_vhca_state(struct mlx5vf_pci_core_device *mvdev,
- struct mlx5_vf_migration_file *migf)
+ struct mlx5_vf_migration_file *migf,
+ struct mlx5_vhca_data_buffer *buf)
{
- struct mlx5_core_dev *mdev;
- u32 out[MLX5_ST_SZ_DW(save_vhca_state_out)] = {};
- u32 in[MLX5_ST_SZ_DW(save_vhca_state_in)] = {};
- u32 pdn, mkey;
+ u32 out[MLX5_ST_SZ_DW(load_vhca_state_out)] = {};
+ u32 in[MLX5_ST_SZ_DW(load_vhca_state_in)] = {};
int err;
lockdep_assert_held(&mvdev->state_mutex);
if (mvdev->mdev_detach)
return -ENOTCONN;
- mutex_lock(&migf->lock);
- if (!migf->total_length) {
- err = -EINVAL;
- goto end;
+ if (!buf->dmaed) {
+ err = mlx5vf_dma_data_buffer(buf);
+ if (err)
+ return err;
}
- mdev = mvdev->mdev;
- err = mlx5_core_alloc_pd(mdev, &pdn);
- if (err)
- goto end;
-
- err = dma_map_sgtable(mdev->device, &migf->table.sgt, DMA_TO_DEVICE, 0);
- if (err)
- goto err_reg;
-
- err = _create_mkey(mdev, pdn, migf, NULL, &mkey);
- if (err)
- goto err_mkey;
-
MLX5_SET(load_vhca_state_in, in, opcode,
MLX5_CMD_OP_LOAD_VHCA_STATE);
MLX5_SET(load_vhca_state_in, in, op_mod, 0);
MLX5_SET(load_vhca_state_in, in, vhca_id, mvdev->vhca_id);
- MLX5_SET(load_vhca_state_in, in, mkey, mkey);
- MLX5_SET(load_vhca_state_in, in, size, migf->total_length);
+ MLX5_SET(load_vhca_state_in, in, mkey, buf->mkey);
+ MLX5_SET(load_vhca_state_in, in, size, buf->length);
+ return mlx5_cmd_exec_inout(mvdev->mdev, load_vhca_state, in, out);
+}
- err = mlx5_cmd_exec_inout(mdev, load_vhca_state, in, out);
+int mlx5vf_cmd_alloc_pd(struct mlx5_vf_migration_file *migf)
+{
+ int err;
- mlx5_core_destroy_mkey(mdev, mkey);
-err_mkey:
- dma_unmap_sgtable(mdev->device, &migf->table.sgt, DMA_TO_DEVICE, 0);
-err_reg:
- mlx5_core_dealloc_pd(mdev, pdn);
-end:
- mutex_unlock(&migf->lock);
+ lockdep_assert_held(&migf->mvdev->state_mutex);
+ if (migf->mvdev->mdev_detach)
+ return -ENOTCONN;
+
+ err = mlx5_core_alloc_pd(migf->mvdev->mdev, &migf->pdn);
return err;
}
+void mlx5vf_cmd_dealloc_pd(struct mlx5_vf_migration_file *migf)
+{
+ lockdep_assert_held(&migf->mvdev->state_mutex);
+ if (migf->mvdev->mdev_detach)
+ return;
+
+ mlx5_core_dealloc_pd(migf->mvdev->mdev, migf->pdn);
+}
+
+void mlx5fv_cmd_clean_migf_resources(struct mlx5_vf_migration_file *migf)
+{
+ struct mlx5_vhca_data_buffer *entry;
+
+ lockdep_assert_held(&migf->mvdev->state_mutex);
+ WARN_ON(migf->mvdev->mdev_detach);
+
+ if (migf->buf) {
+ mlx5vf_free_data_buffer(migf->buf);
+ migf->buf = NULL;
+ }
+
+ if (migf->buf_header) {
+ mlx5vf_free_data_buffer(migf->buf_header);
+ migf->buf_header = NULL;
+ }
+
+ list_splice(&migf->avail_list, &migf->buf_list);
+
+ while ((entry = list_first_entry_or_null(&migf->buf_list,
+ struct mlx5_vhca_data_buffer, buf_elm))) {
+ list_del(&entry->buf_elm);
+ mlx5vf_free_data_buffer(entry);
+ }
+
+ mlx5vf_cmd_dealloc_pd(migf);
+}
+
static void combine_ranges(struct rb_root_cached *root, u32 cur_nodes,
u32 req_nodes)
{
diff --git a/drivers/vfio/pci/mlx5/cmd.h b/drivers/vfio/pci/mlx5/cmd.h
index 921d5720a1e5..5483171d57ad 100644
--- a/drivers/vfio/pci/mlx5/cmd.h
+++ b/drivers/vfio/pci/mlx5/cmd.h
@@ -12,31 +12,74 @@
#include <linux/mlx5/cq.h>
#include <linux/mlx5/qp.h>
+#define MLX5VF_PRE_COPY_SUPP(mvdev) \
+ ((mvdev)->core_device.vdev.migration_flags & VFIO_MIGRATION_PRE_COPY)
+
+enum mlx5_vf_migf_state {
+ MLX5_MIGF_STATE_ERROR = 1,
+ MLX5_MIGF_STATE_PRE_COPY_ERROR,
+ MLX5_MIGF_STATE_PRE_COPY,
+ MLX5_MIGF_STATE_SAVE_LAST,
+ MLX5_MIGF_STATE_COMPLETE,
+};
+
+enum mlx5_vf_load_state {
+ MLX5_VF_LOAD_STATE_READ_IMAGE_NO_HEADER,
+ MLX5_VF_LOAD_STATE_READ_HEADER,
+ MLX5_VF_LOAD_STATE_PREP_IMAGE,
+ MLX5_VF_LOAD_STATE_READ_IMAGE,
+ MLX5_VF_LOAD_STATE_LOAD_IMAGE,
+};
+
+struct mlx5_vf_migration_header {
+ __le64 image_size;
+ /* For future use in case we may need to change the kernel protocol */
+ __le64 flags;
+};
+
+struct mlx5_vhca_data_buffer {
+ struct sg_append_table table;
+ loff_t start_pos;
+ u64 length;
+ u64 allocated_length;
+ u64 header_image_size;
+ u32 mkey;
+ enum dma_data_direction dma_dir;
+ u8 dmaed:1;
+ struct list_head buf_elm;
+ struct mlx5_vf_migration_file *migf;
+ /* Optimize mlx5vf_get_migration_page() for sequential access */
+ struct scatterlist *last_offset_sg;
+ unsigned int sg_last_entry;
+ unsigned long last_offset;
+};
+
struct mlx5vf_async_data {
struct mlx5_async_work cb_work;
struct work_struct work;
+ struct mlx5_vhca_data_buffer *buf;
+ struct mlx5_vhca_data_buffer *header_buf;
int status;
- u32 pdn;
- u32 mkey;
+ u8 last_chunk:1;
void *out;
};
struct mlx5_vf_migration_file {
struct file *filp;
struct mutex lock;
- u8 disabled:1;
- u8 is_err:1;
+ enum mlx5_vf_migf_state state;
- struct sg_append_table table;
- size_t total_length;
- size_t allocated_length;
-
- /* Optimize mlx5vf_get_migration_page() for sequential access */
- struct scatterlist *last_offset_sg;
- unsigned int sg_last_entry;
- unsigned long last_offset;
+ enum mlx5_vf_load_state load_state;
+ u32 pdn;
+ loff_t max_pos;
+ struct mlx5_vhca_data_buffer *buf;
+ struct mlx5_vhca_data_buffer *buf_header;
+ spinlock_t list_lock;
+ struct list_head buf_list;
+ struct list_head avail_list;
struct mlx5vf_pci_core_device *mvdev;
wait_queue_head_t poll_wait;
+ struct completion save_comp;
struct mlx5_async_ctx async_ctx;
struct mlx5vf_async_data async_data;
};
@@ -113,19 +156,42 @@ struct mlx5vf_pci_core_device {
struct mlx5_core_dev *mdev;
};
+enum {
+ MLX5VF_QUERY_INC = (1UL << 0),
+ MLX5VF_QUERY_FINAL = (1UL << 1),
+};
+
int mlx5vf_cmd_suspend_vhca(struct mlx5vf_pci_core_device *mvdev, u16 op_mod);
int mlx5vf_cmd_resume_vhca(struct mlx5vf_pci_core_device *mvdev, u16 op_mod);
int mlx5vf_cmd_query_vhca_migration_state(struct mlx5vf_pci_core_device *mvdev,
- size_t *state_size);
+ size_t *state_size, u8 query_flags);
void mlx5vf_cmd_set_migratable(struct mlx5vf_pci_core_device *mvdev,
const struct vfio_migration_ops *mig_ops,
const struct vfio_log_ops *log_ops);
void mlx5vf_cmd_remove_migratable(struct mlx5vf_pci_core_device *mvdev);
void mlx5vf_cmd_close_migratable(struct mlx5vf_pci_core_device *mvdev);
int mlx5vf_cmd_save_vhca_state(struct mlx5vf_pci_core_device *mvdev,
- struct mlx5_vf_migration_file *migf);
+ struct mlx5_vf_migration_file *migf,
+ struct mlx5_vhca_data_buffer *buf, bool inc,
+ bool track);
int mlx5vf_cmd_load_vhca_state(struct mlx5vf_pci_core_device *mvdev,
- struct mlx5_vf_migration_file *migf);
+ struct mlx5_vf_migration_file *migf,
+ struct mlx5_vhca_data_buffer *buf);
+int mlx5vf_cmd_alloc_pd(struct mlx5_vf_migration_file *migf);
+void mlx5vf_cmd_dealloc_pd(struct mlx5_vf_migration_file *migf);
+void mlx5fv_cmd_clean_migf_resources(struct mlx5_vf_migration_file *migf);
+struct mlx5_vhca_data_buffer *
+mlx5vf_alloc_data_buffer(struct mlx5_vf_migration_file *migf,
+ size_t length, enum dma_data_direction dma_dir);
+void mlx5vf_free_data_buffer(struct mlx5_vhca_data_buffer *buf);
+struct mlx5_vhca_data_buffer *
+mlx5vf_get_data_buffer(struct mlx5_vf_migration_file *migf,
+ size_t length, enum dma_data_direction dma_dir);
+void mlx5vf_put_data_buffer(struct mlx5_vhca_data_buffer *buf);
+int mlx5vf_add_migration_pages(struct mlx5_vhca_data_buffer *buf,
+ unsigned int npages);
+struct page *mlx5vf_get_migration_page(struct mlx5_vhca_data_buffer *buf,
+ unsigned long offset);
void mlx5vf_state_mutex_unlock(struct mlx5vf_pci_core_device *mvdev);
void mlx5vf_disable_fds(struct mlx5vf_pci_core_device *mvdev);
void mlx5vf_mig_file_cleanup_cb(struct work_struct *_work);
diff --git a/drivers/vfio/pci/mlx5/main.c b/drivers/vfio/pci/mlx5/main.c
index fd6ccb8454a2..9feb89c6d939 100644
--- a/drivers/vfio/pci/mlx5/main.c
+++ b/drivers/vfio/pci/mlx5/main.c
@@ -32,8 +32,8 @@ static struct mlx5vf_pci_core_device *mlx5vf_drvdata(struct pci_dev *pdev)
core_device);
}
-static struct page *
-mlx5vf_get_migration_page(struct mlx5_vf_migration_file *migf,
+struct page *
+mlx5vf_get_migration_page(struct mlx5_vhca_data_buffer *buf,
unsigned long offset)
{
unsigned long cur_offset = 0;
@@ -41,20 +41,20 @@ mlx5vf_get_migration_page(struct mlx5_vf_migration_file *migf,
unsigned int i;
/* All accesses are sequential */
- if (offset < migf->last_offset || !migf->last_offset_sg) {
- migf->last_offset = 0;
- migf->last_offset_sg = migf->table.sgt.sgl;
- migf->sg_last_entry = 0;
+ if (offset < buf->last_offset || !buf->last_offset_sg) {
+ buf->last_offset = 0;
+ buf->last_offset_sg = buf->table.sgt.sgl;
+ buf->sg_last_entry = 0;
}
- cur_offset = migf->last_offset;
+ cur_offset = buf->last_offset;
- for_each_sg(migf->last_offset_sg, sg,
- migf->table.sgt.orig_nents - migf->sg_last_entry, i) {
+ for_each_sg(buf->last_offset_sg, sg,
+ buf->table.sgt.orig_nents - buf->sg_last_entry, i) {
if (offset < sg->length + cur_offset) {
- migf->last_offset_sg = sg;
- migf->sg_last_entry += i;
- migf->last_offset = cur_offset;
+ buf->last_offset_sg = sg;
+ buf->sg_last_entry += i;
+ buf->last_offset = cur_offset;
return nth_page(sg_page(sg),
(offset - cur_offset) / PAGE_SIZE);
}
@@ -63,8 +63,8 @@ mlx5vf_get_migration_page(struct mlx5_vf_migration_file *migf,
return NULL;
}
-static int mlx5vf_add_migration_pages(struct mlx5_vf_migration_file *migf,
- unsigned int npages)
+int mlx5vf_add_migration_pages(struct mlx5_vhca_data_buffer *buf,
+ unsigned int npages)
{
unsigned int to_alloc = npages;
struct page **page_list;
@@ -85,13 +85,13 @@ static int mlx5vf_add_migration_pages(struct mlx5_vf_migration_file *migf,
}
to_alloc -= filled;
ret = sg_alloc_append_table_from_pages(
- &migf->table, page_list, filled, 0,
+ &buf->table, page_list, filled, 0,
filled << PAGE_SHIFT, UINT_MAX, SG_MAX_SINGLE_ALLOC,
GFP_KERNEL);
if (ret)
goto err;
- migf->allocated_length += filled * PAGE_SIZE;
+ buf->allocated_length += filled * PAGE_SIZE;
/* clean input for another bulk allocation */
memset(page_list, 0, filled * sizeof(*page_list));
to_fill = min_t(unsigned int, to_alloc,
@@ -108,16 +108,8 @@ err:
static void mlx5vf_disable_fd(struct mlx5_vf_migration_file *migf)
{
- struct sg_page_iter sg_iter;
-
mutex_lock(&migf->lock);
- /* Undo alloc_pages_bulk_array() */
- for_each_sgtable_page(&migf->table.sgt, &sg_iter, 0)
- __free_page(sg_page_iter_page(&sg_iter));
- sg_free_append_table(&migf->table);
- migf->disabled = true;
- migf->total_length = 0;
- migf->allocated_length = 0;
+ migf->state = MLX5_MIGF_STATE_ERROR;
migf->filp->f_pos = 0;
mutex_unlock(&migf->lock);
}
@@ -132,10 +124,91 @@ static int mlx5vf_release_file(struct inode *inode, struct file *filp)
return 0;
}
+static struct mlx5_vhca_data_buffer *
+mlx5vf_get_data_buff_from_pos(struct mlx5_vf_migration_file *migf, loff_t pos,
+ bool *end_of_data)
+{
+ struct mlx5_vhca_data_buffer *buf;
+ bool found = false;
+
+ *end_of_data = false;
+ spin_lock_irq(&migf->list_lock);
+ if (list_empty(&migf->buf_list)) {
+ *end_of_data = true;
+ goto end;
+ }
+
+ buf = list_first_entry(&migf->buf_list, struct mlx5_vhca_data_buffer,
+ buf_elm);
+ if (pos >= buf->start_pos &&
+ pos < buf->start_pos + buf->length) {
+ found = true;
+ goto end;
+ }
+
+ /*
+ * As we use a stream based FD we may expect having the data always
+ * on first chunk
+ */
+ migf->state = MLX5_MIGF_STATE_ERROR;
+
+end:
+ spin_unlock_irq(&migf->list_lock);
+ return found ? buf : NULL;
+}
+
+static ssize_t mlx5vf_buf_read(struct mlx5_vhca_data_buffer *vhca_buf,
+ char __user **buf, size_t *len, loff_t *pos)
+{
+ unsigned long offset;
+ ssize_t done = 0;
+ size_t copy_len;
+
+ copy_len = min_t(size_t,
+ vhca_buf->start_pos + vhca_buf->length - *pos, *len);
+ while (copy_len) {
+ size_t page_offset;
+ struct page *page;
+ size_t page_len;
+ u8 *from_buff;
+ int ret;
+
+ offset = *pos - vhca_buf->start_pos;
+ page_offset = offset % PAGE_SIZE;
+ offset -= page_offset;
+ page = mlx5vf_get_migration_page(vhca_buf, offset);
+ if (!page)
+ return -EINVAL;
+ page_len = min_t(size_t, copy_len, PAGE_SIZE - page_offset);
+ from_buff = kmap_local_page(page);
+ ret = copy_to_user(*buf, from_buff + page_offset, page_len);
+ kunmap_local(from_buff);
+ if (ret)
+ return -EFAULT;
+ *pos += page_len;
+ *len -= page_len;
+ *buf += page_len;
+ done += page_len;
+ copy_len -= page_len;
+ }
+
+ if (*pos >= vhca_buf->start_pos + vhca_buf->length) {
+ spin_lock_irq(&vhca_buf->migf->list_lock);
+ list_del_init(&vhca_buf->buf_elm);
+ list_add_tail(&vhca_buf->buf_elm, &vhca_buf->migf->avail_list);
+ spin_unlock_irq(&vhca_buf->migf->list_lock);
+ }
+
+ return done;
+}
+
static ssize_t mlx5vf_save_read(struct file *filp, char __user *buf, size_t len,
loff_t *pos)
{
struct mlx5_vf_migration_file *migf = filp->private_data;
+ struct mlx5_vhca_data_buffer *vhca_buf;
+ bool first_loop_call = true;
+ bool end_of_data;
ssize_t done = 0;
if (pos)
@@ -144,52 +217,56 @@ static ssize_t mlx5vf_save_read(struct file *filp, char __user *buf, size_t len,
if (!(filp->f_flags & O_NONBLOCK)) {
if (wait_event_interruptible(migf->poll_wait,
- READ_ONCE(migf->total_length) || migf->is_err))
+ !list_empty(&migf->buf_list) ||
+ migf->state == MLX5_MIGF_STATE_ERROR ||
+ migf->state == MLX5_MIGF_STATE_PRE_COPY_ERROR ||
+ migf->state == MLX5_MIGF_STATE_PRE_COPY ||
+ migf->state == MLX5_MIGF_STATE_COMPLETE))
return -ERESTARTSYS;
}
mutex_lock(&migf->lock);
- if ((filp->f_flags & O_NONBLOCK) && !READ_ONCE(migf->total_length)) {
- done = -EAGAIN;
- goto out_unlock;
- }
- if (*pos > migf->total_length) {
- done = -EINVAL;
- goto out_unlock;
- }
- if (migf->disabled || migf->is_err) {
+ if (migf->state == MLX5_MIGF_STATE_ERROR) {
done = -ENODEV;
goto out_unlock;
}
- len = min_t(size_t, migf->total_length - *pos, len);
while (len) {
- size_t page_offset;
- struct page *page;
- size_t page_len;
- u8 *from_buff;
- int ret;
+ ssize_t count;
+
+ vhca_buf = mlx5vf_get_data_buff_from_pos(migf, *pos,
+ &end_of_data);
+ if (first_loop_call) {
+ first_loop_call = false;
+ /* Temporary end of file as part of PRE_COPY */
+ if (end_of_data && (migf->state == MLX5_MIGF_STATE_PRE_COPY ||
+ migf->state == MLX5_MIGF_STATE_PRE_COPY_ERROR)) {
+ done = -ENOMSG;
+ goto out_unlock;
+ }
+
+ if (end_of_data && migf->state != MLX5_MIGF_STATE_COMPLETE) {
+ if (filp->f_flags & O_NONBLOCK) {
+ done = -EAGAIN;
+ goto out_unlock;
+ }
+ }
+ }
+
+ if (end_of_data)
+ goto out_unlock;
- page_offset = (*pos) % PAGE_SIZE;
- page = mlx5vf_get_migration_page(migf, *pos - page_offset);
- if (!page) {
- if (done == 0)
- done = -EINVAL;
+ if (!vhca_buf) {
+ done = -EINVAL;
goto out_unlock;
}
- page_len = min_t(size_t, len, PAGE_SIZE - page_offset);
- from_buff = kmap_local_page(page);
- ret = copy_to_user(buf, from_buff + page_offset, page_len);
- kunmap_local(from_buff);
- if (ret) {
- done = -EFAULT;
+ count = mlx5vf_buf_read(vhca_buf, &buf, &len, pos);
+ if (count < 0) {
+ done = count;
goto out_unlock;
}
- *pos += page_len;
- len -= page_len;
- done += page_len;
- buf += page_len;
+ done += count;
}
out_unlock:
@@ -206,27 +283,188 @@ static __poll_t mlx5vf_save_poll(struct file *filp,
poll_wait(filp, &migf->poll_wait, wait);
mutex_lock(&migf->lock);
- if (migf->disabled || migf->is_err)
+ if (migf->state == MLX5_MIGF_STATE_ERROR)
pollflags = EPOLLIN | EPOLLRDNORM | EPOLLRDHUP;
- else if (READ_ONCE(migf->total_length))
+ else if (!list_empty(&migf->buf_list) ||
+ migf->state == MLX5_MIGF_STATE_COMPLETE)
pollflags = EPOLLIN | EPOLLRDNORM;
mutex_unlock(&migf->lock);
return pollflags;
}
+/*
+ * FD is exposed and user can use it after receiving an error.
+ * Mark migf in error, and wake the user.
+ */
+static void mlx5vf_mark_err(struct mlx5_vf_migration_file *migf)
+{
+ migf->state = MLX5_MIGF_STATE_ERROR;
+ wake_up_interruptible(&migf->poll_wait);
+}
+
+static long mlx5vf_precopy_ioctl(struct file *filp, unsigned int cmd,
+ unsigned long arg)
+{
+ struct mlx5_vf_migration_file *migf = filp->private_data;
+ struct mlx5vf_pci_core_device *mvdev = migf->mvdev;
+ struct mlx5_vhca_data_buffer *buf;
+ struct vfio_precopy_info info = {};
+ loff_t *pos = &filp->f_pos;
+ unsigned long minsz;
+ size_t inc_length = 0;
+ bool end_of_data;
+ int ret;
+
+ if (cmd != VFIO_MIG_GET_PRECOPY_INFO)
+ return -ENOTTY;
+
+ minsz = offsetofend(struct vfio_precopy_info, dirty_bytes);
+
+ if (copy_from_user(&info, (void __user *)arg, minsz))
+ return -EFAULT;
+
+ if (info.argsz < minsz)
+ return -EINVAL;
+
+ mutex_lock(&mvdev->state_mutex);
+ if (mvdev->mig_state != VFIO_DEVICE_STATE_PRE_COPY &&
+ mvdev->mig_state != VFIO_DEVICE_STATE_PRE_COPY_P2P) {
+ ret = -EINVAL;
+ goto err_state_unlock;
+ }
+
+ /*
+ * We can't issue a SAVE command when the device is suspended, so as
+ * part of VFIO_DEVICE_STATE_PRE_COPY_P2P no reason to query for extra
+ * bytes that can't be read.
+ */
+ if (mvdev->mig_state == VFIO_DEVICE_STATE_PRE_COPY) {
+ /*
+ * Once the query returns it's guaranteed that there is no
+ * active SAVE command.
+ * As so, the other code below is safe with the proper locks.
+ */
+ ret = mlx5vf_cmd_query_vhca_migration_state(mvdev, &inc_length,
+ MLX5VF_QUERY_INC);
+ if (ret)
+ goto err_state_unlock;
+ }
+
+ mutex_lock(&migf->lock);
+ if (migf->state == MLX5_MIGF_STATE_ERROR) {
+ ret = -ENODEV;
+ goto err_migf_unlock;
+ }
+
+ buf = mlx5vf_get_data_buff_from_pos(migf, *pos, &end_of_data);
+ if (buf) {
+ if (buf->start_pos == 0) {
+ info.initial_bytes = buf->header_image_size - *pos;
+ } else if (buf->start_pos ==
+ sizeof(struct mlx5_vf_migration_header)) {
+ /* First data buffer following the header */
+ info.initial_bytes = buf->start_pos +
+ buf->length - *pos;
+ } else {
+ info.dirty_bytes = buf->start_pos + buf->length - *pos;
+ }
+ } else {
+ if (!end_of_data) {
+ ret = -EINVAL;
+ goto err_migf_unlock;
+ }
+
+ info.dirty_bytes = inc_length;
+ }
+
+ if (!end_of_data || !inc_length) {
+ mutex_unlock(&migf->lock);
+ goto done;
+ }
+
+ mutex_unlock(&migf->lock);
+ /*
+ * We finished transferring the current state and the device has a
+ * dirty state, save a new state to be ready for.
+ */
+ buf = mlx5vf_get_data_buffer(migf, inc_length, DMA_FROM_DEVICE);
+ if (IS_ERR(buf)) {
+ ret = PTR_ERR(buf);
+ mlx5vf_mark_err(migf);
+ goto err_state_unlock;
+ }
+
+ ret = mlx5vf_cmd_save_vhca_state(mvdev, migf, buf, true, true);
+ if (ret) {
+ mlx5vf_mark_err(migf);
+ mlx5vf_put_data_buffer(buf);
+ goto err_state_unlock;
+ }
+
+done:
+ mlx5vf_state_mutex_unlock(mvdev);
+ if (copy_to_user((void __user *)arg, &info, minsz))
+ return -EFAULT;
+ return 0;
+
+err_migf_unlock:
+ mutex_unlock(&migf->lock);
+err_state_unlock:
+ mlx5vf_state_mutex_unlock(mvdev);
+ return ret;
+}
+
static const struct file_operations mlx5vf_save_fops = {
.owner = THIS_MODULE,
.read = mlx5vf_save_read,
.poll = mlx5vf_save_poll,
+ .unlocked_ioctl = mlx5vf_precopy_ioctl,
+ .compat_ioctl = compat_ptr_ioctl,
.release = mlx5vf_release_file,
.llseek = no_llseek,
};
+static int mlx5vf_pci_save_device_inc_data(struct mlx5vf_pci_core_device *mvdev)
+{
+ struct mlx5_vf_migration_file *migf = mvdev->saving_migf;
+ struct mlx5_vhca_data_buffer *buf;
+ size_t length;
+ int ret;
+
+ if (migf->state == MLX5_MIGF_STATE_ERROR)
+ return -ENODEV;
+
+ ret = mlx5vf_cmd_query_vhca_migration_state(mvdev, &length,
+ MLX5VF_QUERY_INC | MLX5VF_QUERY_FINAL);
+ if (ret)
+ goto err;
+
+ buf = mlx5vf_get_data_buffer(migf, length, DMA_FROM_DEVICE);
+ if (IS_ERR(buf)) {
+ ret = PTR_ERR(buf);
+ goto err;
+ }
+
+ ret = mlx5vf_cmd_save_vhca_state(mvdev, migf, buf, true, false);
+ if (ret)
+ goto err_save;
+
+ return 0;
+
+err_save:
+ mlx5vf_put_data_buffer(buf);
+err:
+ mlx5vf_mark_err(migf);
+ return ret;
+}
+
static struct mlx5_vf_migration_file *
-mlx5vf_pci_save_device_data(struct mlx5vf_pci_core_device *mvdev)
+mlx5vf_pci_save_device_data(struct mlx5vf_pci_core_device *mvdev, bool track)
{
struct mlx5_vf_migration_file *migf;
+ struct mlx5_vhca_data_buffer *buf;
+ size_t length;
int ret;
migf = kzalloc(sizeof(*migf), GFP_KERNEL);
@@ -236,43 +474,211 @@ mlx5vf_pci_save_device_data(struct mlx5vf_pci_core_device *mvdev)
migf->filp = anon_inode_getfile("mlx5vf_mig", &mlx5vf_save_fops, migf,
O_RDONLY);
if (IS_ERR(migf->filp)) {
- int err = PTR_ERR(migf->filp);
-
- kfree(migf);
- return ERR_PTR(err);
+ ret = PTR_ERR(migf->filp);
+ goto end;
}
+ migf->mvdev = mvdev;
+ ret = mlx5vf_cmd_alloc_pd(migf);
+ if (ret)
+ goto out_free;
+
stream_open(migf->filp->f_inode, migf->filp);
mutex_init(&migf->lock);
init_waitqueue_head(&migf->poll_wait);
+ init_completion(&migf->save_comp);
+ /*
+ * save_comp is being used as a binary semaphore built from
+ * a completion. A normal mutex cannot be used because the lock is
+ * passed between kernel threads and lockdep can't model this.
+ */
+ complete(&migf->save_comp);
mlx5_cmd_init_async_ctx(mvdev->mdev, &migf->async_ctx);
INIT_WORK(&migf->async_data.work, mlx5vf_mig_file_cleanup_cb);
- ret = mlx5vf_cmd_query_vhca_migration_state(mvdev,
- &migf->total_length);
+ INIT_LIST_HEAD(&migf->buf_list);
+ INIT_LIST_HEAD(&migf->avail_list);
+ spin_lock_init(&migf->list_lock);
+ ret = mlx5vf_cmd_query_vhca_migration_state(mvdev, &length, 0);
if (ret)
- goto out_free;
+ goto out_pd;
- ret = mlx5vf_add_migration_pages(
- migf, DIV_ROUND_UP_ULL(migf->total_length, PAGE_SIZE));
- if (ret)
- goto out_free;
+ buf = mlx5vf_alloc_data_buffer(migf, length, DMA_FROM_DEVICE);
+ if (IS_ERR(buf)) {
+ ret = PTR_ERR(buf);
+ goto out_pd;
+ }
- migf->mvdev = mvdev;
- ret = mlx5vf_cmd_save_vhca_state(mvdev, migf);
+ ret = mlx5vf_cmd_save_vhca_state(mvdev, migf, buf, false, track);
if (ret)
- goto out_free;
+ goto out_save;
return migf;
+out_save:
+ mlx5vf_free_data_buffer(buf);
+out_pd:
+ mlx5vf_cmd_dealloc_pd(migf);
out_free:
fput(migf->filp);
+end:
+ kfree(migf);
return ERR_PTR(ret);
}
+static int
+mlx5vf_append_page_to_mig_buf(struct mlx5_vhca_data_buffer *vhca_buf,
+ const char __user **buf, size_t *len,
+ loff_t *pos, ssize_t *done)
+{
+ unsigned long offset;
+ size_t page_offset;
+ struct page *page;
+ size_t page_len;
+ u8 *to_buff;
+ int ret;
+
+ offset = *pos - vhca_buf->start_pos;
+ page_offset = offset % PAGE_SIZE;
+
+ page = mlx5vf_get_migration_page(vhca_buf, offset - page_offset);
+ if (!page)
+ return -EINVAL;
+ page_len = min_t(size_t, *len, PAGE_SIZE - page_offset);
+ to_buff = kmap_local_page(page);
+ ret = copy_from_user(to_buff + page_offset, *buf, page_len);
+ kunmap_local(to_buff);
+ if (ret)
+ return -EFAULT;
+
+ *pos += page_len;
+ *done += page_len;
+ *buf += page_len;
+ *len -= page_len;
+ vhca_buf->length += page_len;
+ return 0;
+}
+
+static int
+mlx5vf_resume_read_image_no_header(struct mlx5_vhca_data_buffer *vhca_buf,
+ loff_t requested_length,
+ const char __user **buf, size_t *len,
+ loff_t *pos, ssize_t *done)
+{
+ int ret;
+
+ if (requested_length > MAX_MIGRATION_SIZE)
+ return -ENOMEM;
+
+ if (vhca_buf->allocated_length < requested_length) {
+ ret = mlx5vf_add_migration_pages(
+ vhca_buf,
+ DIV_ROUND_UP(requested_length - vhca_buf->allocated_length,
+ PAGE_SIZE));
+ if (ret)
+ return ret;
+ }
+
+ while (*len) {
+ ret = mlx5vf_append_page_to_mig_buf(vhca_buf, buf, len, pos,
+ done);
+ if (ret)
+ return ret;
+ }
+
+ return 0;
+}
+
+static ssize_t
+mlx5vf_resume_read_image(struct mlx5_vf_migration_file *migf,
+ struct mlx5_vhca_data_buffer *vhca_buf,
+ size_t image_size, const char __user **buf,
+ size_t *len, loff_t *pos, ssize_t *done,
+ bool *has_work)
+{
+ size_t copy_len, to_copy;
+ int ret;
+
+ to_copy = min_t(size_t, *len, image_size - vhca_buf->length);
+ copy_len = to_copy;
+ while (to_copy) {
+ ret = mlx5vf_append_page_to_mig_buf(vhca_buf, buf, &to_copy, pos,
+ done);
+ if (ret)
+ return ret;
+ }
+
+ *len -= copy_len;
+ if (vhca_buf->length == image_size) {
+ migf->load_state = MLX5_VF_LOAD_STATE_LOAD_IMAGE;
+ migf->max_pos += image_size;
+ *has_work = true;
+ }
+
+ return 0;
+}
+
+static int
+mlx5vf_resume_read_header(struct mlx5_vf_migration_file *migf,
+ struct mlx5_vhca_data_buffer *vhca_buf,
+ const char __user **buf,
+ size_t *len, loff_t *pos,
+ ssize_t *done, bool *has_work)
+{
+ struct page *page;
+ size_t copy_len;
+ u8 *to_buff;
+ int ret;
+
+ copy_len = min_t(size_t, *len,
+ sizeof(struct mlx5_vf_migration_header) - vhca_buf->length);
+ page = mlx5vf_get_migration_page(vhca_buf, 0);
+ if (!page)
+ return -EINVAL;
+ to_buff = kmap_local_page(page);
+ ret = copy_from_user(to_buff + vhca_buf->length, *buf, copy_len);
+ if (ret) {
+ ret = -EFAULT;
+ goto end;
+ }
+
+ *buf += copy_len;
+ *pos += copy_len;
+ *done += copy_len;
+ *len -= copy_len;
+ vhca_buf->length += copy_len;
+ if (vhca_buf->length == sizeof(struct mlx5_vf_migration_header)) {
+ u64 flags;
+
+ vhca_buf->header_image_size = le64_to_cpup((__le64 *)to_buff);
+ if (vhca_buf->header_image_size > MAX_MIGRATION_SIZE) {
+ ret = -ENOMEM;
+ goto end;
+ }
+
+ flags = le64_to_cpup((__le64 *)(to_buff +
+ offsetof(struct mlx5_vf_migration_header, flags)));
+ if (flags) {
+ ret = -EOPNOTSUPP;
+ goto end;
+ }
+
+ migf->load_state = MLX5_VF_LOAD_STATE_PREP_IMAGE;
+ migf->max_pos += vhca_buf->length;
+ *has_work = true;
+ }
+end:
+ kunmap_local(to_buff);
+ return ret;
+}
+
static ssize_t mlx5vf_resume_write(struct file *filp, const char __user *buf,
size_t len, loff_t *pos)
{
struct mlx5_vf_migration_file *migf = filp->private_data;
+ struct mlx5_vhca_data_buffer *vhca_buf = migf->buf;
+ struct mlx5_vhca_data_buffer *vhca_buf_header = migf->buf_header;
loff_t requested_length;
+ bool has_work = false;
ssize_t done = 0;
+ int ret = 0;
if (pos)
return -ESPIPE;
@@ -282,56 +688,83 @@ static ssize_t mlx5vf_resume_write(struct file *filp, const char __user *buf,
check_add_overflow((loff_t)len, *pos, &requested_length))
return -EINVAL;
- if (requested_length > MAX_MIGRATION_SIZE)
- return -ENOMEM;
-
+ mutex_lock(&migf->mvdev->state_mutex);
mutex_lock(&migf->lock);
- if (migf->disabled) {
- done = -ENODEV;
+ if (migf->state == MLX5_MIGF_STATE_ERROR) {
+ ret = -ENODEV;
goto out_unlock;
}
- if (migf->allocated_length < requested_length) {
- done = mlx5vf_add_migration_pages(
- migf,
- DIV_ROUND_UP(requested_length - migf->allocated_length,
- PAGE_SIZE));
- if (done)
- goto out_unlock;
- }
-
- while (len) {
- size_t page_offset;
- struct page *page;
- size_t page_len;
- u8 *to_buff;
- int ret;
-
- page_offset = (*pos) % PAGE_SIZE;
- page = mlx5vf_get_migration_page(migf, *pos - page_offset);
- if (!page) {
- if (done == 0)
- done = -EINVAL;
- goto out_unlock;
+ while (len || has_work) {
+ has_work = false;
+ switch (migf->load_state) {
+ case MLX5_VF_LOAD_STATE_READ_HEADER:
+ ret = mlx5vf_resume_read_header(migf, vhca_buf_header,
+ &buf, &len, pos,
+ &done, &has_work);
+ if (ret)
+ goto out_unlock;
+ break;
+ case MLX5_VF_LOAD_STATE_PREP_IMAGE:
+ {
+ u64 size = vhca_buf_header->header_image_size;
+
+ if (vhca_buf->allocated_length < size) {
+ mlx5vf_free_data_buffer(vhca_buf);
+
+ migf->buf = mlx5vf_alloc_data_buffer(migf,
+ size, DMA_TO_DEVICE);
+ if (IS_ERR(migf->buf)) {
+ ret = PTR_ERR(migf->buf);
+ migf->buf = NULL;
+ goto out_unlock;
+ }
+
+ vhca_buf = migf->buf;
+ }
+
+ vhca_buf->start_pos = migf->max_pos;
+ migf->load_state = MLX5_VF_LOAD_STATE_READ_IMAGE;
+ break;
}
+ case MLX5_VF_LOAD_STATE_READ_IMAGE_NO_HEADER:
+ ret = mlx5vf_resume_read_image_no_header(vhca_buf,
+ requested_length,
+ &buf, &len, pos, &done);
+ if (ret)
+ goto out_unlock;
+ break;
+ case MLX5_VF_LOAD_STATE_READ_IMAGE:
+ ret = mlx5vf_resume_read_image(migf, vhca_buf,
+ vhca_buf_header->header_image_size,
+ &buf, &len, pos, &done, &has_work);
+ if (ret)
+ goto out_unlock;
+ break;
+ case MLX5_VF_LOAD_STATE_LOAD_IMAGE:
+ ret = mlx5vf_cmd_load_vhca_state(migf->mvdev, migf, vhca_buf);
+ if (ret)
+ goto out_unlock;
+ migf->load_state = MLX5_VF_LOAD_STATE_READ_HEADER;
+
+ /* prep header buf for next image */
+ vhca_buf_header->length = 0;
+ vhca_buf_header->header_image_size = 0;
+ /* prep data buf for next image */
+ vhca_buf->length = 0;
- page_len = min_t(size_t, len, PAGE_SIZE - page_offset);
- to_buff = kmap_local_page(page);
- ret = copy_from_user(to_buff + page_offset, buf, page_len);
- kunmap_local(to_buff);
- if (ret) {
- done = -EFAULT;
- goto out_unlock;
+ break;
+ default:
+ break;
}
- *pos += page_len;
- len -= page_len;
- done += page_len;
- buf += page_len;
- migf->total_length += page_len;
}
+
out_unlock:
+ if (ret)
+ migf->state = MLX5_MIGF_STATE_ERROR;
mutex_unlock(&migf->lock);
- return done;
+ mlx5vf_state_mutex_unlock(migf->mvdev);
+ return ret ? ret : done;
}
static const struct file_operations mlx5vf_resume_fops = {
@@ -345,6 +778,8 @@ static struct mlx5_vf_migration_file *
mlx5vf_pci_resume_device_data(struct mlx5vf_pci_core_device *mvdev)
{
struct mlx5_vf_migration_file *migf;
+ struct mlx5_vhca_data_buffer *buf;
+ int ret;
migf = kzalloc(sizeof(*migf), GFP_KERNEL);
if (!migf)
@@ -353,20 +788,59 @@ mlx5vf_pci_resume_device_data(struct mlx5vf_pci_core_device *mvdev)
migf->filp = anon_inode_getfile("mlx5vf_mig", &mlx5vf_resume_fops, migf,
O_WRONLY);
if (IS_ERR(migf->filp)) {
- int err = PTR_ERR(migf->filp);
+ ret = PTR_ERR(migf->filp);
+ goto end;
+ }
- kfree(migf);
- return ERR_PTR(err);
+ migf->mvdev = mvdev;
+ ret = mlx5vf_cmd_alloc_pd(migf);
+ if (ret)
+ goto out_free;
+
+ buf = mlx5vf_alloc_data_buffer(migf, 0, DMA_TO_DEVICE);
+ if (IS_ERR(buf)) {
+ ret = PTR_ERR(buf);
+ goto out_pd;
+ }
+
+ migf->buf = buf;
+ if (MLX5VF_PRE_COPY_SUPP(mvdev)) {
+ buf = mlx5vf_alloc_data_buffer(migf,
+ sizeof(struct mlx5_vf_migration_header), DMA_NONE);
+ if (IS_ERR(buf)) {
+ ret = PTR_ERR(buf);
+ goto out_buf;
+ }
+
+ migf->buf_header = buf;
+ migf->load_state = MLX5_VF_LOAD_STATE_READ_HEADER;
+ } else {
+ /* Initial state will be to read the image */
+ migf->load_state = MLX5_VF_LOAD_STATE_READ_IMAGE_NO_HEADER;
}
+
stream_open(migf->filp->f_inode, migf->filp);
mutex_init(&migf->lock);
+ INIT_LIST_HEAD(&migf->buf_list);
+ INIT_LIST_HEAD(&migf->avail_list);
+ spin_lock_init(&migf->list_lock);
return migf;
+out_buf:
+ mlx5vf_free_data_buffer(migf->buf);
+out_pd:
+ mlx5vf_cmd_dealloc_pd(migf);
+out_free:
+ fput(migf->filp);
+end:
+ kfree(migf);
+ return ERR_PTR(ret);
}
void mlx5vf_disable_fds(struct mlx5vf_pci_core_device *mvdev)
{
if (mvdev->resuming_migf) {
mlx5vf_disable_fd(mvdev->resuming_migf);
+ mlx5fv_cmd_clean_migf_resources(mvdev->resuming_migf);
fput(mvdev->resuming_migf->filp);
mvdev->resuming_migf = NULL;
}
@@ -374,6 +848,7 @@ void mlx5vf_disable_fds(struct mlx5vf_pci_core_device *mvdev)
mlx5_cmd_cleanup_async_ctx(&mvdev->saving_migf->async_ctx);
cancel_work_sync(&mvdev->saving_migf->async_data.work);
mlx5vf_disable_fd(mvdev->saving_migf);
+ mlx5fv_cmd_clean_migf_resources(mvdev->saving_migf);
fput(mvdev->saving_migf->filp);
mvdev->saving_migf = NULL;
}
@@ -402,7 +877,8 @@ mlx5vf_pci_step_device_state_locked(struct mlx5vf_pci_core_device *mvdev,
return NULL;
}
- if (cur == VFIO_DEVICE_STATE_RUNNING && new == VFIO_DEVICE_STATE_RUNNING_P2P) {
+ if ((cur == VFIO_DEVICE_STATE_RUNNING && new == VFIO_DEVICE_STATE_RUNNING_P2P) ||
+ (cur == VFIO_DEVICE_STATE_PRE_COPY && new == VFIO_DEVICE_STATE_PRE_COPY_P2P)) {
ret = mlx5vf_cmd_suspend_vhca(mvdev,
MLX5_SUSPEND_VHCA_IN_OP_MOD_SUSPEND_INITIATOR);
if (ret)
@@ -410,7 +886,8 @@ mlx5vf_pci_step_device_state_locked(struct mlx5vf_pci_core_device *mvdev,
return NULL;
}
- if (cur == VFIO_DEVICE_STATE_RUNNING_P2P && new == VFIO_DEVICE_STATE_RUNNING) {
+ if ((cur == VFIO_DEVICE_STATE_RUNNING_P2P && new == VFIO_DEVICE_STATE_RUNNING) ||
+ (cur == VFIO_DEVICE_STATE_PRE_COPY_P2P && new == VFIO_DEVICE_STATE_PRE_COPY)) {
ret = mlx5vf_cmd_resume_vhca(mvdev,
MLX5_RESUME_VHCA_IN_OP_MOD_RESUME_INITIATOR);
if (ret)
@@ -421,7 +898,7 @@ mlx5vf_pci_step_device_state_locked(struct mlx5vf_pci_core_device *mvdev,
if (cur == VFIO_DEVICE_STATE_STOP && new == VFIO_DEVICE_STATE_STOP_COPY) {
struct mlx5_vf_migration_file *migf;
- migf = mlx5vf_pci_save_device_data(mvdev);
+ migf = mlx5vf_pci_save_device_data(mvdev, false);
if (IS_ERR(migf))
return ERR_CAST(migf);
get_file(migf->filp);
@@ -429,7 +906,10 @@ mlx5vf_pci_step_device_state_locked(struct mlx5vf_pci_core_device *mvdev,
return migf->filp;
}
- if ((cur == VFIO_DEVICE_STATE_STOP_COPY && new == VFIO_DEVICE_STATE_STOP)) {
+ if ((cur == VFIO_DEVICE_STATE_STOP_COPY && new == VFIO_DEVICE_STATE_STOP) ||
+ (cur == VFIO_DEVICE_STATE_PRE_COPY && new == VFIO_DEVICE_STATE_RUNNING) ||
+ (cur == VFIO_DEVICE_STATE_PRE_COPY_P2P &&
+ new == VFIO_DEVICE_STATE_RUNNING_P2P)) {
mlx5vf_disable_fds(mvdev);
return NULL;
}
@@ -446,14 +926,39 @@ mlx5vf_pci_step_device_state_locked(struct mlx5vf_pci_core_device *mvdev,
}
if (cur == VFIO_DEVICE_STATE_RESUMING && new == VFIO_DEVICE_STATE_STOP) {
- ret = mlx5vf_cmd_load_vhca_state(mvdev,
- mvdev->resuming_migf);
- if (ret)
- return ERR_PTR(ret);
+ if (!MLX5VF_PRE_COPY_SUPP(mvdev)) {
+ ret = mlx5vf_cmd_load_vhca_state(mvdev,
+ mvdev->resuming_migf,
+ mvdev->resuming_migf->buf);
+ if (ret)
+ return ERR_PTR(ret);
+ }
mlx5vf_disable_fds(mvdev);
return NULL;
}
+ if ((cur == VFIO_DEVICE_STATE_RUNNING && new == VFIO_DEVICE_STATE_PRE_COPY) ||
+ (cur == VFIO_DEVICE_STATE_RUNNING_P2P &&
+ new == VFIO_DEVICE_STATE_PRE_COPY_P2P)) {
+ struct mlx5_vf_migration_file *migf;
+
+ migf = mlx5vf_pci_save_device_data(mvdev, true);
+ if (IS_ERR(migf))
+ return ERR_CAST(migf);
+ get_file(migf->filp);
+ mvdev->saving_migf = migf;
+ return migf->filp;
+ }
+
+ if (cur == VFIO_DEVICE_STATE_PRE_COPY_P2P && new == VFIO_DEVICE_STATE_STOP_COPY) {
+ ret = mlx5vf_cmd_suspend_vhca(mvdev,
+ MLX5_SUSPEND_VHCA_IN_OP_MOD_SUSPEND_RESPONDER);
+ if (ret)
+ return ERR_PTR(ret);
+ ret = mlx5vf_pci_save_device_inc_data(mvdev);
+ return ret ? ERR_PTR(ret) : NULL;
+ }
+
/*
* vfio_mig_get_next_state() does not use arcs other than the above
*/
@@ -512,6 +1017,23 @@ mlx5vf_pci_set_device_state(struct vfio_device *vdev,
return res;
}
+static int mlx5vf_pci_get_data_size(struct vfio_device *vdev,
+ unsigned long *stop_copy_length)
+{
+ struct mlx5vf_pci_core_device *mvdev = container_of(
+ vdev, struct mlx5vf_pci_core_device, core_device.vdev);
+ size_t state_size;
+ int ret;
+
+ mutex_lock(&mvdev->state_mutex);
+ ret = mlx5vf_cmd_query_vhca_migration_state(mvdev,
+ &state_size, 0);
+ if (!ret)
+ *stop_copy_length = state_size;
+ mlx5vf_state_mutex_unlock(mvdev);
+ return ret;
+}
+
static int mlx5vf_pci_get_device_state(struct vfio_device *vdev,
enum vfio_device_mig_state *curr_state)
{
@@ -577,6 +1099,7 @@ static void mlx5vf_pci_close_device(struct vfio_device *core_vdev)
static const struct vfio_migration_ops mlx5vf_pci_mig_ops = {
.migration_set_state = mlx5vf_pci_set_device_state,
.migration_get_state = mlx5vf_pci_get_device_state,
+ .migration_get_data_size = mlx5vf_pci_get_data_size,
};
static const struct vfio_log_ops mlx5vf_pci_log_ops = {
@@ -623,6 +1146,9 @@ static const struct vfio_device_ops mlx5vf_pci_ops = {
.mmap = vfio_pci_core_mmap,
.request = vfio_pci_core_request,
.match = vfio_pci_core_match,
+ .bind_iommufd = vfio_iommufd_physical_bind,
+ .unbind_iommufd = vfio_iommufd_physical_unbind,
+ .attach_ioas = vfio_iommufd_physical_attach_ioas,
};
static int mlx5vf_pci_probe(struct pci_dev *pdev,
@@ -676,18 +1202,7 @@ static struct pci_driver mlx5vf_pci_driver = {
.driver_managed_dma = true,
};
-static void __exit mlx5vf_pci_cleanup(void)
-{
- pci_unregister_driver(&mlx5vf_pci_driver);
-}
-
-static int __init mlx5vf_pci_init(void)
-{
- return pci_register_driver(&mlx5vf_pci_driver);
-}
-
-module_init(mlx5vf_pci_init);
-module_exit(mlx5vf_pci_cleanup);
+module_pci_driver(mlx5vf_pci_driver);
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Max Gurtovoy <mgurtovoy@nvidia.com>");
diff --git a/drivers/vfio/pci/vfio_pci.c b/drivers/vfio/pci/vfio_pci.c
index 1d4919edfbde..29091ee2e984 100644
--- a/drivers/vfio/pci/vfio_pci.c
+++ b/drivers/vfio/pci/vfio_pci.c
@@ -138,6 +138,9 @@ static const struct vfio_device_ops vfio_pci_ops = {
.mmap = vfio_pci_core_mmap,
.request = vfio_pci_core_request,
.match = vfio_pci_core_match,
+ .bind_iommufd = vfio_iommufd_physical_bind,
+ .unbind_iommufd = vfio_iommufd_physical_unbind,
+ .attach_ioas = vfio_iommufd_physical_attach_ioas,
};
static int vfio_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
diff --git a/drivers/vfio/pci/vfio_pci_core.c b/drivers/vfio/pci/vfio_pci_core.c
index badc9d828cac..26a541cc64d1 100644
--- a/drivers/vfio/pci/vfio_pci_core.c
+++ b/drivers/vfio/pci/vfio_pci_core.c
@@ -27,6 +27,9 @@
#include <linux/vgaarb.h>
#include <linux/nospec.h>
#include <linux/sched/mm.h>
+#if IS_ENABLED(CONFIG_EEH)
+#include <asm/eeh.h>
+#endif
#include "vfio_pci_priv.h"
@@ -686,7 +689,9 @@ void vfio_pci_core_close_device(struct vfio_device *core_vdev)
vdev->sriov_pf_core_dev->vf_token->users--;
mutex_unlock(&vdev->sriov_pf_core_dev->vf_token->lock);
}
- vfio_spapr_pci_eeh_release(vdev->pdev);
+#if IS_ENABLED(CONFIG_EEH)
+ eeh_dev_release(vdev->pdev);
+#endif
vfio_pci_core_disable(vdev);
mutex_lock(&vdev->igate);
@@ -705,7 +710,9 @@ EXPORT_SYMBOL_GPL(vfio_pci_core_close_device);
void vfio_pci_core_finish_enable(struct vfio_pci_core_device *vdev)
{
vfio_pci_probe_mmaps(vdev);
- vfio_spapr_pci_eeh_open(vdev->pdev);
+#if IS_ENABLED(CONFIG_EEH)
+ eeh_dev_open(vdev->pdev);
+#endif
if (vdev->sriov_pf_core_dev) {
mutex_lock(&vdev->sriov_pf_core_dev->vf_token->lock);
@@ -2109,7 +2116,6 @@ void vfio_pci_core_release_dev(struct vfio_device *core_vdev)
mutex_destroy(&vdev->vma_lock);
kfree(vdev->region);
kfree(vdev->pm_save);
- vfio_free_device(core_vdev);
}
EXPORT_SYMBOL_GPL(vfio_pci_core_release_dev);
@@ -2128,7 +2134,8 @@ int vfio_pci_core_register_device(struct vfio_pci_core_device *vdev)
if (vdev->vdev.mig_ops) {
if (!(vdev->vdev.mig_ops->migration_get_state &&
- vdev->vdev.mig_ops->migration_set_state) ||
+ vdev->vdev.mig_ops->migration_set_state &&
+ vdev->vdev.mig_ops->migration_get_data_size) ||
!(vdev->vdev.migration_flags & VFIO_MIGRATION_STOP_COPY))
return -EINVAL;
}
@@ -2488,12 +2495,12 @@ static bool vfio_pci_dev_set_needs_reset(struct vfio_device_set *dev_set)
struct vfio_pci_core_device *cur;
bool needs_reset = false;
- list_for_each_entry(cur, &dev_set->device_list, vdev.dev_set_list) {
- /* No VFIO device in the set can have an open device FD */
- if (cur->vdev.open_count)
- return false;
+ /* No other VFIO device in the set can be open. */
+ if (vfio_device_set_open_count(dev_set) > 1)
+ return false;
+
+ list_for_each_entry(cur, &dev_set->device_list, vdev.dev_set_list)
needs_reset |= cur->needs_reset;
- }
return needs_reset;
}
diff --git a/drivers/vfio/platform/vfio_amba.c b/drivers/vfio/platform/vfio_amba.c
index eaea63e5294c..83fe54015595 100644
--- a/drivers/vfio/platform/vfio_amba.c
+++ b/drivers/vfio/platform/vfio_amba.c
@@ -95,7 +95,6 @@ static void vfio_amba_release_dev(struct vfio_device *core_vdev)
vfio_platform_release_common(vdev);
kfree(vdev->name);
- vfio_free_device(core_vdev);
}
static void vfio_amba_remove(struct amba_device *adev)
@@ -117,6 +116,9 @@ static const struct vfio_device_ops vfio_amba_ops = {
.read = vfio_platform_read,
.write = vfio_platform_write,
.mmap = vfio_platform_mmap,
+ .bind_iommufd = vfio_iommufd_physical_bind,
+ .unbind_iommufd = vfio_iommufd_physical_unbind,
+ .attach_ioas = vfio_iommufd_physical_attach_ioas,
};
static const struct amba_id pl330_ids[] = {
diff --git a/drivers/vfio/platform/vfio_platform.c b/drivers/vfio/platform/vfio_platform.c
index 82cedcebfd90..22a1efca32a8 100644
--- a/drivers/vfio/platform/vfio_platform.c
+++ b/drivers/vfio/platform/vfio_platform.c
@@ -83,7 +83,6 @@ static void vfio_platform_release_dev(struct vfio_device *core_vdev)
container_of(core_vdev, struct vfio_platform_device, vdev);
vfio_platform_release_common(vdev);
- vfio_free_device(core_vdev);
}
static int vfio_platform_remove(struct platform_device *pdev)
@@ -106,6 +105,9 @@ static const struct vfio_device_ops vfio_platform_ops = {
.read = vfio_platform_read,
.write = vfio_platform_write,
.mmap = vfio_platform_mmap,
+ .bind_iommufd = vfio_iommufd_physical_bind,
+ .unbind_iommufd = vfio_iommufd_physical_unbind,
+ .attach_ioas = vfio_iommufd_physical_attach_ioas,
};
static struct platform_driver vfio_platform_driver = {
diff --git a/drivers/vfio/platform/vfio_platform_common.c b/drivers/vfio/platform/vfio_platform_common.c
index 55dc4f43c31e..1a0a238ffa35 100644
--- a/drivers/vfio/platform/vfio_platform_common.c
+++ b/drivers/vfio/platform/vfio_platform_common.c
@@ -72,12 +72,11 @@ static int vfio_platform_acpi_call_reset(struct vfio_platform_device *vdev,
const char **extra_dbg)
{
#ifdef CONFIG_ACPI
- struct acpi_buffer buffer = { ACPI_ALLOCATE_BUFFER, NULL };
struct device *dev = vdev->device;
acpi_handle handle = ACPI_HANDLE(dev);
acpi_status acpi_ret;
- acpi_ret = acpi_evaluate_object(handle, "_RST", NULL, &buffer);
+ acpi_ret = acpi_evaluate_object(handle, "_RST", NULL, NULL);
if (ACPI_FAILURE(acpi_ret)) {
if (extra_dbg)
*extra_dbg = acpi_format_exception(acpi_ret);
diff --git a/drivers/vfio/vfio.h b/drivers/vfio/vfio.h
index bcad54bbab08..f8219a438bfb 100644
--- a/drivers/vfio/vfio.h
+++ b/drivers/vfio/vfio.h
@@ -6,14 +6,25 @@
#ifndef __VFIO_VFIO_H__
#define __VFIO_VFIO_H__
+#include <linux/file.h>
#include <linux/device.h>
#include <linux/cdev.h>
#include <linux/module.h>
+struct iommufd_ctx;
struct iommu_group;
struct vfio_device;
struct vfio_container;
+void vfio_device_put_registration(struct vfio_device *device);
+bool vfio_device_try_get_registration(struct vfio_device *device);
+int vfio_device_open(struct vfio_device *device,
+ struct iommufd_ctx *iommufd, struct kvm *kvm);
+void vfio_device_close(struct vfio_device *device,
+ struct iommufd_ctx *iommufd);
+
+extern const struct file_operations vfio_device_fops;
+
enum vfio_group_type {
/*
* Physical device with IOMMU backing.
@@ -54,14 +65,30 @@ struct vfio_group {
struct list_head device_list;
struct mutex device_lock;
struct list_head vfio_next;
+#if IS_ENABLED(CONFIG_VFIO_CONTAINER)
struct list_head container_next;
+#endif
enum vfio_group_type type;
struct mutex group_lock;
struct kvm *kvm;
struct file *opened_file;
struct blocking_notifier_head notifier;
+ struct iommufd_ctx *iommufd;
};
+int vfio_device_set_group(struct vfio_device *device,
+ enum vfio_group_type type);
+void vfio_device_remove_group(struct vfio_device *device);
+void vfio_device_group_register(struct vfio_device *device);
+void vfio_device_group_unregister(struct vfio_device *device);
+int vfio_device_group_use_iommu(struct vfio_device *device);
+void vfio_device_group_unuse_iommu(struct vfio_device *device);
+void vfio_device_group_close(struct vfio_device *device);
+bool vfio_device_has_container(struct vfio_device *device);
+int __init vfio_group_init(void);
+void vfio_group_cleanup(void);
+
+#if IS_ENABLED(CONFIG_VFIO_CONTAINER)
/* events for the backend driver notify callback */
enum vfio_iommu_notify_type {
VFIO_IOMMU_CONTAINER_CLOSE = 0,
@@ -109,20 +136,114 @@ struct vfio_iommu_driver {
int vfio_register_iommu_driver(const struct vfio_iommu_driver_ops *ops);
void vfio_unregister_iommu_driver(const struct vfio_iommu_driver_ops *ops);
-bool vfio_assert_device_open(struct vfio_device *device);
-
struct vfio_container *vfio_container_from_file(struct file *filep);
-int vfio_device_assign_container(struct vfio_device *device);
-void vfio_device_unassign_container(struct vfio_device *device);
+int vfio_group_use_container(struct vfio_group *group);
+void vfio_group_unuse_container(struct vfio_group *group);
int vfio_container_attach_group(struct vfio_container *container,
struct vfio_group *group);
void vfio_group_detach_container(struct vfio_group *group);
void vfio_device_container_register(struct vfio_device *device);
void vfio_device_container_unregister(struct vfio_device *device);
-long vfio_container_ioctl_check_extension(struct vfio_container *container,
- unsigned long arg);
+int vfio_device_container_pin_pages(struct vfio_device *device,
+ dma_addr_t iova, int npage,
+ int prot, struct page **pages);
+void vfio_device_container_unpin_pages(struct vfio_device *device,
+ dma_addr_t iova, int npage);
+int vfio_device_container_dma_rw(struct vfio_device *device,
+ dma_addr_t iova, void *data,
+ size_t len, bool write);
+
int __init vfio_container_init(void);
void vfio_container_cleanup(void);
+#else
+static inline struct vfio_container *
+vfio_container_from_file(struct file *filep)
+{
+ return NULL;
+}
+
+static inline int vfio_group_use_container(struct vfio_group *group)
+{
+ return -EOPNOTSUPP;
+}
+
+static inline void vfio_group_unuse_container(struct vfio_group *group)
+{
+}
+
+static inline int vfio_container_attach_group(struct vfio_container *container,
+ struct vfio_group *group)
+{
+ return -EOPNOTSUPP;
+}
+
+static inline void vfio_group_detach_container(struct vfio_group *group)
+{
+}
+
+static inline void vfio_device_container_register(struct vfio_device *device)
+{
+}
+
+static inline void vfio_device_container_unregister(struct vfio_device *device)
+{
+}
+
+static inline int vfio_device_container_pin_pages(struct vfio_device *device,
+ dma_addr_t iova, int npage,
+ int prot, struct page **pages)
+{
+ return -EOPNOTSUPP;
+}
+
+static inline void vfio_device_container_unpin_pages(struct vfio_device *device,
+ dma_addr_t iova, int npage)
+{
+}
+
+static inline int vfio_device_container_dma_rw(struct vfio_device *device,
+ dma_addr_t iova, void *data,
+ size_t len, bool write)
+{
+ return -EOPNOTSUPP;
+}
+
+static inline int vfio_container_init(void)
+{
+ return 0;
+}
+static inline void vfio_container_cleanup(void)
+{
+}
+#endif
+
+#if IS_ENABLED(CONFIG_IOMMUFD)
+int vfio_iommufd_bind(struct vfio_device *device, struct iommufd_ctx *ictx);
+void vfio_iommufd_unbind(struct vfio_device *device);
+#else
+static inline int vfio_iommufd_bind(struct vfio_device *device,
+ struct iommufd_ctx *ictx)
+{
+ return -EOPNOTSUPP;
+}
+
+static inline void vfio_iommufd_unbind(struct vfio_device *device)
+{
+}
+#endif
+
+#if IS_ENABLED(CONFIG_VFIO_VIRQFD)
+int __init vfio_virqfd_init(void);
+void vfio_virqfd_exit(void);
+#else
+static inline int __init vfio_virqfd_init(void)
+{
+ return 0;
+}
+static inline void vfio_virqfd_exit(void)
+{
+}
+#endif
#ifdef CONFIG_VFIO_NOIOMMU
extern bool vfio_noiommu __read_mostly;
diff --git a/drivers/vfio/vfio_iommu_spapr_tce.c b/drivers/vfio/vfio_iommu_spapr_tce.c
index 169f07ac162d..60a50ce8701e 100644
--- a/drivers/vfio/vfio_iommu_spapr_tce.c
+++ b/drivers/vfio/vfio_iommu_spapr_tce.c
@@ -4,6 +4,7 @@
*
* Copyright (C) 2013 IBM Corp. All rights reserved.
* Author: Alexey Kardashevskiy <aik@ozlabs.ru>
+ * Copyright Gavin Shan, IBM Corporation 2014.
*
* Derived from original vfio_iommu_type1.c:
* Copyright (C) 2012 Red Hat, Inc. All rights reserved.
@@ -773,6 +774,57 @@ static long tce_iommu_create_default_window(struct tce_container *container)
return ret;
}
+static long vfio_spapr_ioctl_eeh_pe_op(struct iommu_group *group,
+ unsigned long arg)
+{
+ struct eeh_pe *pe;
+ struct vfio_eeh_pe_op op;
+ unsigned long minsz;
+
+ pe = eeh_iommu_group_to_pe(group);
+ if (!pe)
+ return -ENODEV;
+
+ minsz = offsetofend(struct vfio_eeh_pe_op, op);
+ if (copy_from_user(&op, (void __user *)arg, minsz))
+ return -EFAULT;
+ if (op.argsz < minsz || op.flags)
+ return -EINVAL;
+
+ switch (op.op) {
+ case VFIO_EEH_PE_DISABLE:
+ return eeh_pe_set_option(pe, EEH_OPT_DISABLE);
+ case VFIO_EEH_PE_ENABLE:
+ return eeh_pe_set_option(pe, EEH_OPT_ENABLE);
+ case VFIO_EEH_PE_UNFREEZE_IO:
+ return eeh_pe_set_option(pe, EEH_OPT_THAW_MMIO);
+ case VFIO_EEH_PE_UNFREEZE_DMA:
+ return eeh_pe_set_option(pe, EEH_OPT_THAW_DMA);
+ case VFIO_EEH_PE_GET_STATE:
+ return eeh_pe_get_state(pe);
+ break;
+ case VFIO_EEH_PE_RESET_DEACTIVATE:
+ return eeh_pe_reset(pe, EEH_RESET_DEACTIVATE, true);
+ case VFIO_EEH_PE_RESET_HOT:
+ return eeh_pe_reset(pe, EEH_RESET_HOT, true);
+ case VFIO_EEH_PE_RESET_FUNDAMENTAL:
+ return eeh_pe_reset(pe, EEH_RESET_FUNDAMENTAL, true);
+ case VFIO_EEH_PE_CONFIGURE:
+ return eeh_pe_configure(pe);
+ case VFIO_EEH_PE_INJECT_ERR:
+ minsz = offsetofend(struct vfio_eeh_pe_op, err.mask);
+ if (op.argsz < minsz)
+ return -EINVAL;
+ if (copy_from_user(&op, (void __user *)arg, minsz))
+ return -EFAULT;
+
+ return eeh_pe_inject_err(pe, op.err.type, op.err.func,
+ op.err.addr, op.err.mask);
+ default:
+ return -EINVAL;
+ }
+}
+
static long tce_iommu_ioctl(void *iommu_data,
unsigned int cmd, unsigned long arg)
{
@@ -785,14 +837,12 @@ static long tce_iommu_ioctl(void *iommu_data,
switch (arg) {
case VFIO_SPAPR_TCE_IOMMU:
case VFIO_SPAPR_TCE_v2_IOMMU:
- ret = 1;
- break;
+ return 1;
+ case VFIO_EEH:
+ return eeh_enabled();
default:
- ret = vfio_spapr_iommu_eeh_ioctl(NULL, cmd, arg);
- break;
+ return 0;
}
-
- return (ret < 0) ? 0 : ret;
}
/*
@@ -1046,8 +1096,7 @@ static long tce_iommu_ioctl(void *iommu_data,
ret = 0;
list_for_each_entry(tcegrp, &container->group_list, next) {
- ret = vfio_spapr_iommu_eeh_ioctl(tcegrp->grp,
- cmd, arg);
+ ret = vfio_spapr_ioctl_eeh_pe_op(tcegrp->grp, arg);
if (ret)
return ret;
}
diff --git a/drivers/vfio/vfio_main.c b/drivers/vfio/vfio_main.c
index 2d168793d4e1..5177bb061b17 100644
--- a/drivers/vfio/vfio_main.c
+++ b/drivers/vfio/vfio_main.c
@@ -13,8 +13,6 @@
#include <linux/cdev.h>
#include <linux/compat.h>
#include <linux/device.h>
-#include <linux/file.h>
-#include <linux/anon_inodes.h>
#include <linux/fs.h>
#include <linux/idr.h>
#include <linux/iommu.h>
@@ -35,6 +33,7 @@
#include <linux/pm_runtime.h>
#include <linux/interval_tree.h>
#include <linux/iova_bitmap.h>
+#include <linux/iommufd.h>
#include "vfio.h"
#define DRIVER_VERSION "0.3"
@@ -42,17 +41,11 @@
#define DRIVER_DESC "VFIO - User Level meta-driver"
static struct vfio {
- struct class *class;
- struct list_head group_list;
- struct mutex group_lock; /* locks group_list */
- struct ida group_ida;
- dev_t group_devt;
struct class *device_class;
struct ida device_ida;
} vfio;
static DEFINE_XARRAY(vfio_device_set_xa);
-static const struct file_operations vfio_group_fops;
int vfio_assign_device_set(struct vfio_device *device, void *set_id)
{
@@ -125,208 +118,34 @@ static void vfio_release_device_set(struct vfio_device *device)
xa_unlock(&vfio_device_set_xa);
}
-/*
- * Group objects - create, release, get, put, search
- */
-static struct vfio_group *
-__vfio_group_get_from_iommu(struct iommu_group *iommu_group)
-{
- struct vfio_group *group;
-
- /*
- * group->iommu_group from the vfio.group_list cannot be NULL
- * under the vfio.group_lock.
- */
- list_for_each_entry(group, &vfio.group_list, vfio_next) {
- if (group->iommu_group == iommu_group) {
- refcount_inc(&group->drivers);
- return group;
- }
- }
- return NULL;
-}
-
-static struct vfio_group *
-vfio_group_get_from_iommu(struct iommu_group *iommu_group)
-{
- struct vfio_group *group;
-
- mutex_lock(&vfio.group_lock);
- group = __vfio_group_get_from_iommu(iommu_group);
- mutex_unlock(&vfio.group_lock);
- return group;
-}
-
-static void vfio_group_release(struct device *dev)
-{
- struct vfio_group *group = container_of(dev, struct vfio_group, dev);
-
- mutex_destroy(&group->device_lock);
- mutex_destroy(&group->group_lock);
- WARN_ON(group->iommu_group);
- ida_free(&vfio.group_ida, MINOR(group->dev.devt));
- kfree(group);
-}
-
-static struct vfio_group *vfio_group_alloc(struct iommu_group *iommu_group,
- enum vfio_group_type type)
-{
- struct vfio_group *group;
- int minor;
-
- group = kzalloc(sizeof(*group), GFP_KERNEL);
- if (!group)
- return ERR_PTR(-ENOMEM);
-
- minor = ida_alloc_max(&vfio.group_ida, MINORMASK, GFP_KERNEL);
- if (minor < 0) {
- kfree(group);
- return ERR_PTR(minor);
- }
-
- device_initialize(&group->dev);
- group->dev.devt = MKDEV(MAJOR(vfio.group_devt), minor);
- group->dev.class = vfio.class;
- group->dev.release = vfio_group_release;
- cdev_init(&group->cdev, &vfio_group_fops);
- group->cdev.owner = THIS_MODULE;
-
- refcount_set(&group->drivers, 1);
- mutex_init(&group->group_lock);
- INIT_LIST_HEAD(&group->device_list);
- mutex_init(&group->device_lock);
- group->iommu_group = iommu_group;
- /* put in vfio_group_release() */
- iommu_group_ref_get(iommu_group);
- group->type = type;
- BLOCKING_INIT_NOTIFIER_HEAD(&group->notifier);
-
- return group;
-}
-
-static struct vfio_group *vfio_create_group(struct iommu_group *iommu_group,
- enum vfio_group_type type)
+unsigned int vfio_device_set_open_count(struct vfio_device_set *dev_set)
{
- struct vfio_group *group;
- struct vfio_group *ret;
- int err;
-
- group = vfio_group_alloc(iommu_group, type);
- if (IS_ERR(group))
- return group;
-
- err = dev_set_name(&group->dev, "%s%d",
- group->type == VFIO_NO_IOMMU ? "noiommu-" : "",
- iommu_group_id(iommu_group));
- if (err) {
- ret = ERR_PTR(err);
- goto err_put;
- }
-
- mutex_lock(&vfio.group_lock);
-
- /* Did we race creating this group? */
- ret = __vfio_group_get_from_iommu(iommu_group);
- if (ret)
- goto err_unlock;
+ struct vfio_device *cur;
+ unsigned int open_count = 0;
- err = cdev_device_add(&group->cdev, &group->dev);
- if (err) {
- ret = ERR_PTR(err);
- goto err_unlock;
- }
-
- list_add(&group->vfio_next, &vfio.group_list);
-
- mutex_unlock(&vfio.group_lock);
- return group;
+ lockdep_assert_held(&dev_set->lock);
-err_unlock:
- mutex_unlock(&vfio.group_lock);
-err_put:
- put_device(&group->dev);
- return ret;
-}
-
-static void vfio_device_remove_group(struct vfio_device *device)
-{
- struct vfio_group *group = device->group;
- struct iommu_group *iommu_group;
-
- if (group->type == VFIO_NO_IOMMU || group->type == VFIO_EMULATED_IOMMU)
- iommu_group_remove_device(device->dev);
-
- /* Pairs with vfio_create_group() / vfio_group_get_from_iommu() */
- if (!refcount_dec_and_mutex_lock(&group->drivers, &vfio.group_lock))
- return;
- list_del(&group->vfio_next);
-
- /*
- * We could concurrently probe another driver in the group that might
- * race vfio_device_remove_group() with vfio_get_group(), so we have to
- * ensure that the sysfs is all cleaned up under lock otherwise the
- * cdev_device_add() will fail due to the name aready existing.
- */
- cdev_device_del(&group->cdev, &group->dev);
-
- mutex_lock(&group->group_lock);
- /*
- * These data structures all have paired operations that can only be
- * undone when the caller holds a live reference on the device. Since
- * all pairs must be undone these WARN_ON's indicate some caller did not
- * properly hold the group reference.
- */
- WARN_ON(!list_empty(&group->device_list));
- WARN_ON(group->notifier.head);
-
- /*
- * Revoke all users of group->iommu_group. At this point we know there
- * are no devices active because we are unplugging the last one. Setting
- * iommu_group to NULL blocks all new users.
- */
- if (group->container)
- vfio_group_detach_container(group);
- iommu_group = group->iommu_group;
- group->iommu_group = NULL;
- mutex_unlock(&group->group_lock);
- mutex_unlock(&vfio.group_lock);
-
- iommu_group_put(iommu_group);
- put_device(&group->dev);
+ list_for_each_entry(cur, &dev_set->device_list, dev_set_list)
+ open_count += cur->open_count;
+ return open_count;
}
+EXPORT_SYMBOL_GPL(vfio_device_set_open_count);
/*
* Device objects - create, release, get, put, search
*/
/* Device reference always implies a group reference */
-static void vfio_device_put_registration(struct vfio_device *device)
+void vfio_device_put_registration(struct vfio_device *device)
{
if (refcount_dec_and_test(&device->refcount))
complete(&device->comp);
}
-static bool vfio_device_try_get_registration(struct vfio_device *device)
+bool vfio_device_try_get_registration(struct vfio_device *device)
{
return refcount_inc_not_zero(&device->refcount);
}
-static struct vfio_device *vfio_group_get_device(struct vfio_group *group,
- struct device *dev)
-{
- struct vfio_device *device;
-
- mutex_lock(&group->device_lock);
- list_for_each_entry(device, &group->device_list, group_next) {
- if (device->dev == dev &&
- vfio_device_try_get_registration(device)) {
- mutex_unlock(&group->device_lock);
- return device;
- }
- }
- mutex_unlock(&group->device_lock);
- return NULL;
-}
-
/*
* VFIO driver API
*/
@@ -339,15 +158,15 @@ static void vfio_device_release(struct device *dev)
vfio_release_device_set(device);
ida_free(&vfio.device_ida, device->index);
- /*
- * kvfree() cannot be done here due to a life cycle mess in
- * vfio-ccw. Before the ccw part is fixed all drivers are
- * required to support @release and call vfio_free_device()
- * from there.
- */
- device->ops->release(device);
+ if (device->ops->release)
+ device->ops->release(device);
+
+ kvfree(device);
}
+static int vfio_init_device(struct vfio_device *device, struct device *dev,
+ const struct vfio_device_ops *ops);
+
/*
* Allocate and initialize vfio_device so it can be registered to vfio
* core.
@@ -386,11 +205,9 @@ EXPORT_SYMBOL_GPL(_vfio_alloc_device);
/*
* Initialize a vfio_device so it can be registered to vfio core.
- *
- * Only vfio-ccw driver should call this interface.
*/
-int vfio_init_device(struct vfio_device *device, struct device *dev,
- const struct vfio_device_ops *ops)
+static int vfio_init_device(struct vfio_device *device, struct device *dev,
+ const struct vfio_device_ops *ops)
{
int ret;
@@ -422,107 +239,16 @@ out_uninit:
ida_free(&vfio.device_ida, device->index);
return ret;
}
-EXPORT_SYMBOL_GPL(vfio_init_device);
-
-/*
- * The helper called by driver @release callback to free the device
- * structure. Drivers which don't have private data to clean can
- * simply use this helper as its @release.
- */
-void vfio_free_device(struct vfio_device *device)
-{
- kvfree(device);
-}
-EXPORT_SYMBOL_GPL(vfio_free_device);
-
-static struct vfio_group *vfio_noiommu_group_alloc(struct device *dev,
- enum vfio_group_type type)
-{
- struct iommu_group *iommu_group;
- struct vfio_group *group;
- int ret;
-
- iommu_group = iommu_group_alloc();
- if (IS_ERR(iommu_group))
- return ERR_CAST(iommu_group);
-
- ret = iommu_group_set_name(iommu_group, "vfio-noiommu");
- if (ret)
- goto out_put_group;
- ret = iommu_group_add_device(iommu_group, dev);
- if (ret)
- goto out_put_group;
-
- group = vfio_create_group(iommu_group, type);
- if (IS_ERR(group)) {
- ret = PTR_ERR(group);
- goto out_remove_device;
- }
- iommu_group_put(iommu_group);
- return group;
-
-out_remove_device:
- iommu_group_remove_device(dev);
-out_put_group:
- iommu_group_put(iommu_group);
- return ERR_PTR(ret);
-}
-
-static struct vfio_group *vfio_group_find_or_alloc(struct device *dev)
-{
- struct iommu_group *iommu_group;
- struct vfio_group *group;
-
- iommu_group = iommu_group_get(dev);
- if (!iommu_group && vfio_noiommu) {
- /*
- * With noiommu enabled, create an IOMMU group for devices that
- * don't already have one, implying no IOMMU hardware/driver
- * exists. Taint the kernel because we're about to give a DMA
- * capable device to a user without IOMMU protection.
- */
- group = vfio_noiommu_group_alloc(dev, VFIO_NO_IOMMU);
- if (!IS_ERR(group)) {
- add_taint(TAINT_USER, LOCKDEP_STILL_OK);
- dev_warn(dev, "Adding kernel taint for vfio-noiommu group on device\n");
- }
- return group;
- }
-
- if (!iommu_group)
- return ERR_PTR(-EINVAL);
-
- /*
- * VFIO always sets IOMMU_CACHE because we offer no way for userspace to
- * restore cache coherency. It has to be checked here because it is only
- * valid for cases where we are using iommu groups.
- */
- if (!device_iommu_capable(dev, IOMMU_CAP_CACHE_COHERENCY)) {
- iommu_group_put(iommu_group);
- return ERR_PTR(-EINVAL);
- }
-
- group = vfio_group_get_from_iommu(iommu_group);
- if (!group)
- group = vfio_create_group(iommu_group, VFIO_IOMMU);
-
- /* The vfio_group holds a reference to the iommu_group */
- iommu_group_put(iommu_group);
- return group;
-}
static int __vfio_register_dev(struct vfio_device *device,
- struct vfio_group *group)
+ enum vfio_group_type type)
{
- struct vfio_device *existing_device;
int ret;
- /*
- * In all cases group is the output of one of the group allocation
- * functions and we have group->drivers incremented for us.
- */
- if (IS_ERR(group))
- return PTR_ERR(group);
+ if (WARN_ON(device->ops->bind_iommufd &&
+ (!device->ops->unbind_iommufd ||
+ !device->ops->attach_ioas)))
+ return -EINVAL;
/*
* If the driver doesn't specify a set then the device is added to a
@@ -531,25 +257,13 @@ static int __vfio_register_dev(struct vfio_device *device,
if (!device->dev_set)
vfio_assign_device_set(device, device);
- existing_device = vfio_group_get_device(group, device->dev);
- if (existing_device) {
- /*
- * group->iommu_group is non-NULL because we hold the drivers
- * refcount.
- */
- dev_WARN(device->dev, "Device already exists on group %d\n",
- iommu_group_id(group->iommu_group));
- vfio_device_put_registration(existing_device);
- ret = -EBUSY;
- goto err_out;
- }
-
- /* Our reference on group is moved to the device */
- device->group = group;
-
ret = dev_set_name(&device->device, "vfio%d", device->index);
if (ret)
- goto err_out;
+ return ret;
+
+ ret = vfio_device_set_group(device, type);
+ if (ret)
+ return ret;
ret = device_add(&device->device);
if (ret)
@@ -558,9 +272,7 @@ static int __vfio_register_dev(struct vfio_device *device,
/* Refcounting can't start until the driver calls register */
refcount_set(&device->refcount, 1);
- mutex_lock(&group->device_lock);
- list_add(&device->group_next, &group->device_list);
- mutex_unlock(&group->device_lock);
+ vfio_device_group_register(device);
return 0;
err_out:
@@ -570,8 +282,7 @@ err_out:
int vfio_register_group_dev(struct vfio_device *device)
{
- return __vfio_register_dev(device,
- vfio_group_find_or_alloc(device->dev));
+ return __vfio_register_dev(device, VFIO_IOMMU);
}
EXPORT_SYMBOL_GPL(vfio_register_group_dev);
@@ -581,46 +292,15 @@ EXPORT_SYMBOL_GPL(vfio_register_group_dev);
*/
int vfio_register_emulated_iommu_dev(struct vfio_device *device)
{
- return __vfio_register_dev(device,
- vfio_noiommu_group_alloc(device->dev, VFIO_EMULATED_IOMMU));
+ return __vfio_register_dev(device, VFIO_EMULATED_IOMMU);
}
EXPORT_SYMBOL_GPL(vfio_register_emulated_iommu_dev);
-static struct vfio_device *vfio_device_get_from_name(struct vfio_group *group,
- char *buf)
-{
- struct vfio_device *it, *device = ERR_PTR(-ENODEV);
-
- mutex_lock(&group->device_lock);
- list_for_each_entry(it, &group->device_list, group_next) {
- int ret;
-
- if (it->ops->match) {
- ret = it->ops->match(it, buf);
- if (ret < 0) {
- device = ERR_PTR(ret);
- break;
- }
- } else {
- ret = !strcmp(dev_name(it->dev), buf);
- }
-
- if (ret && vfio_device_try_get_registration(it)) {
- device = it;
- break;
- }
- }
- mutex_unlock(&group->device_lock);
-
- return device;
-}
-
/*
* Decrement the device reference count and wait for the device to be
* removed. Open file descriptors for the device... */
void vfio_unregister_group_dev(struct vfio_device *device)
{
- struct vfio_group *group = device->group;
unsigned int i = 0;
bool interrupted = false;
long rc;
@@ -648,332 +328,101 @@ void vfio_unregister_group_dev(struct vfio_device *device)
}
}
- mutex_lock(&group->device_lock);
- list_del(&device->group_next);
- mutex_unlock(&group->device_lock);
+ vfio_device_group_unregister(device);
/* Balances device_add in register path */
device_del(&device->device);
+ /* Balances vfio_device_set_group in register path */
vfio_device_remove_group(device);
}
EXPORT_SYMBOL_GPL(vfio_unregister_group_dev);
-/*
- * VFIO Group fd, /dev/vfio/$GROUP
- */
-/*
- * VFIO_GROUP_UNSET_CONTAINER should fail if there are other users or
- * if there was no container to unset. Since the ioctl is called on
- * the group, we know that still exists, therefore the only valid
- * transition here is 1->0.
- */
-static int vfio_group_ioctl_unset_container(struct vfio_group *group)
-{
- int ret = 0;
-
- mutex_lock(&group->group_lock);
- if (!group->container) {
- ret = -EINVAL;
- goto out_unlock;
- }
- if (group->container_users != 1) {
- ret = -EBUSY;
- goto out_unlock;
- }
- vfio_group_detach_container(group);
-
-out_unlock:
- mutex_unlock(&group->group_lock);
- return ret;
-}
-
-static int vfio_group_ioctl_set_container(struct vfio_group *group,
- int __user *arg)
-{
- struct vfio_container *container;
- struct fd f;
- int ret;
- int fd;
-
- if (get_user(fd, arg))
- return -EFAULT;
-
- f = fdget(fd);
- if (!f.file)
- return -EBADF;
-
- mutex_lock(&group->group_lock);
- if (group->container || WARN_ON(group->container_users)) {
- ret = -EINVAL;
- goto out_unlock;
- }
- if (!group->iommu_group) {
- ret = -ENODEV;
- goto out_unlock;
- }
-
- container = vfio_container_from_file(f.file);
- ret = -EINVAL;
- if (container) {
- ret = vfio_container_attach_group(container, group);
- goto out_unlock;
- }
-
-out_unlock:
- mutex_unlock(&group->group_lock);
- fdput(f);
- return ret;
-}
-
-static const struct file_operations vfio_device_fops;
-
/* true if the vfio_device has open_device() called but not close_device() */
-bool vfio_assert_device_open(struct vfio_device *device)
+static bool vfio_assert_device_open(struct vfio_device *device)
{
return !WARN_ON_ONCE(!READ_ONCE(device->open_count));
}
-static struct file *vfio_device_open(struct vfio_device *device)
+static int vfio_device_first_open(struct vfio_device *device,
+ struct iommufd_ctx *iommufd, struct kvm *kvm)
{
- struct file *filep;
int ret;
- mutex_lock(&device->group->group_lock);
- ret = vfio_device_assign_container(device);
- mutex_unlock(&device->group->group_lock);
- if (ret)
- return ERR_PTR(ret);
-
- if (!try_module_get(device->dev->driver->owner)) {
- ret = -ENODEV;
- goto err_unassign_container;
- }
+ lockdep_assert_held(&device->dev_set->lock);
- mutex_lock(&device->dev_set->lock);
- device->open_count++;
- if (device->open_count == 1) {
- /*
- * Here we pass the KVM pointer with the group under the read
- * lock. If the device driver will use it, it must obtain a
- * reference and release it during close_device.
- */
- mutex_lock(&device->group->group_lock);
- device->kvm = device->group->kvm;
+ if (!try_module_get(device->dev->driver->owner))
+ return -ENODEV;
- if (device->ops->open_device) {
- ret = device->ops->open_device(device);
- if (ret)
- goto err_undo_count;
- }
- vfio_device_container_register(device);
- mutex_unlock(&device->group->group_lock);
- }
- mutex_unlock(&device->dev_set->lock);
+ if (iommufd)
+ ret = vfio_iommufd_bind(device, iommufd);
+ else
+ ret = vfio_device_group_use_iommu(device);
+ if (ret)
+ goto err_module_put;
- /*
- * We can't use anon_inode_getfd() because we need to modify
- * the f_mode flags directly to allow more than just ioctls
- */
- filep = anon_inode_getfile("[vfio-device]", &vfio_device_fops,
- device, O_RDWR);
- if (IS_ERR(filep)) {
- ret = PTR_ERR(filep);
- goto err_close_device;
+ device->kvm = kvm;
+ if (device->ops->open_device) {
+ ret = device->ops->open_device(device);
+ if (ret)
+ goto err_unuse_iommu;
}
+ return 0;
- /*
- * TODO: add an anon_inode interface to do this.
- * Appears to be missing by lack of need rather than
- * explicitly prevented. Now there's need.
- */
- filep->f_mode |= (FMODE_PREAD | FMODE_PWRITE);
-
- if (device->group->type == VFIO_NO_IOMMU)
- dev_warn(device->dev, "vfio-noiommu device opened by user "
- "(%s:%d)\n", current->comm, task_pid_nr(current));
- /*
- * On success the ref of device is moved to the file and
- * put in vfio_device_fops_release()
- */
- return filep;
-
-err_close_device:
- mutex_lock(&device->dev_set->lock);
- mutex_lock(&device->group->group_lock);
- if (device->open_count == 1 && device->ops->close_device) {
- device->ops->close_device(device);
-
- vfio_device_container_unregister(device);
- }
-err_undo_count:
- mutex_unlock(&device->group->group_lock);
- device->open_count--;
- if (device->open_count == 0 && device->kvm)
- device->kvm = NULL;
- mutex_unlock(&device->dev_set->lock);
+err_unuse_iommu:
+ device->kvm = NULL;
+ if (iommufd)
+ vfio_iommufd_unbind(device);
+ else
+ vfio_device_group_unuse_iommu(device);
+err_module_put:
module_put(device->dev->driver->owner);
-err_unassign_container:
- vfio_device_unassign_container(device);
- return ERR_PTR(ret);
-}
-
-static int vfio_group_ioctl_get_device_fd(struct vfio_group *group,
- char __user *arg)
-{
- struct vfio_device *device;
- struct file *filep;
- char *buf;
- int fdno;
- int ret;
-
- buf = strndup_user(arg, PAGE_SIZE);
- if (IS_ERR(buf))
- return PTR_ERR(buf);
-
- device = vfio_device_get_from_name(group, buf);
- kfree(buf);
- if (IS_ERR(device))
- return PTR_ERR(device);
-
- fdno = get_unused_fd_flags(O_CLOEXEC);
- if (fdno < 0) {
- ret = fdno;
- goto err_put_device;
- }
-
- filep = vfio_device_open(device);
- if (IS_ERR(filep)) {
- ret = PTR_ERR(filep);
- goto err_put_fdno;
- }
-
- fd_install(fdno, filep);
- return fdno;
-
-err_put_fdno:
- put_unused_fd(fdno);
-err_put_device:
- vfio_device_put_registration(device);
return ret;
}
-static int vfio_group_ioctl_get_status(struct vfio_group *group,
- struct vfio_group_status __user *arg)
-{
- unsigned long minsz = offsetofend(struct vfio_group_status, flags);
- struct vfio_group_status status;
-
- if (copy_from_user(&status, arg, minsz))
- return -EFAULT;
-
- if (status.argsz < minsz)
- return -EINVAL;
-
- status.flags = 0;
-
- mutex_lock(&group->group_lock);
- if (!group->iommu_group) {
- mutex_unlock(&group->group_lock);
- return -ENODEV;
- }
-
- if (group->container)
- status.flags |= VFIO_GROUP_FLAGS_CONTAINER_SET |
- VFIO_GROUP_FLAGS_VIABLE;
- else if (!iommu_group_dma_owner_claimed(group->iommu_group))
- status.flags |= VFIO_GROUP_FLAGS_VIABLE;
- mutex_unlock(&group->group_lock);
-
- if (copy_to_user(arg, &status, minsz))
- return -EFAULT;
- return 0;
-}
-
-static long vfio_group_fops_unl_ioctl(struct file *filep,
- unsigned int cmd, unsigned long arg)
+static void vfio_device_last_close(struct vfio_device *device,
+ struct iommufd_ctx *iommufd)
{
- struct vfio_group *group = filep->private_data;
- void __user *uarg = (void __user *)arg;
+ lockdep_assert_held(&device->dev_set->lock);
- switch (cmd) {
- case VFIO_GROUP_GET_DEVICE_FD:
- return vfio_group_ioctl_get_device_fd(group, uarg);
- case VFIO_GROUP_GET_STATUS:
- return vfio_group_ioctl_get_status(group, uarg);
- case VFIO_GROUP_SET_CONTAINER:
- return vfio_group_ioctl_set_container(group, uarg);
- case VFIO_GROUP_UNSET_CONTAINER:
- return vfio_group_ioctl_unset_container(group);
- default:
- return -ENOTTY;
- }
+ if (device->ops->close_device)
+ device->ops->close_device(device);
+ device->kvm = NULL;
+ if (iommufd)
+ vfio_iommufd_unbind(device);
+ else
+ vfio_device_group_unuse_iommu(device);
+ module_put(device->dev->driver->owner);
}
-static int vfio_group_fops_open(struct inode *inode, struct file *filep)
+int vfio_device_open(struct vfio_device *device,
+ struct iommufd_ctx *iommufd, struct kvm *kvm)
{
- struct vfio_group *group =
- container_of(inode->i_cdev, struct vfio_group, cdev);
- int ret;
-
- mutex_lock(&group->group_lock);
-
- /*
- * drivers can be zero if this races with vfio_device_remove_group(), it
- * will be stable at 0 under the group rwsem
- */
- if (refcount_read(&group->drivers) == 0) {
- ret = -ENODEV;
- goto out_unlock;
- }
+ int ret = 0;
- if (group->type == VFIO_NO_IOMMU && !capable(CAP_SYS_RAWIO)) {
- ret = -EPERM;
- goto out_unlock;
+ mutex_lock(&device->dev_set->lock);
+ device->open_count++;
+ if (device->open_count == 1) {
+ ret = vfio_device_first_open(device, iommufd, kvm);
+ if (ret)
+ device->open_count--;
}
+ mutex_unlock(&device->dev_set->lock);
- /*
- * Do we need multiple instances of the group open? Seems not.
- */
- if (group->opened_file) {
- ret = -EBUSY;
- goto out_unlock;
- }
- group->opened_file = filep;
- filep->private_data = group;
- ret = 0;
-out_unlock:
- mutex_unlock(&group->group_lock);
return ret;
}
-static int vfio_group_fops_release(struct inode *inode, struct file *filep)
+void vfio_device_close(struct vfio_device *device,
+ struct iommufd_ctx *iommufd)
{
- struct vfio_group *group = filep->private_data;
-
- filep->private_data = NULL;
-
- mutex_lock(&group->group_lock);
- /*
- * Device FDs hold a group file reference, therefore the group release
- * is only called when there are no open devices.
- */
- WARN_ON(group->notifier.head);
- if (group->container)
- vfio_group_detach_container(group);
- group->opened_file = NULL;
- mutex_unlock(&group->group_lock);
- return 0;
+ mutex_lock(&device->dev_set->lock);
+ vfio_assert_device_open(device);
+ if (device->open_count == 1)
+ vfio_device_last_close(device, iommufd);
+ device->open_count--;
+ mutex_unlock(&device->dev_set->lock);
}
-static const struct file_operations vfio_group_fops = {
- .owner = THIS_MODULE,
- .unlocked_ioctl = vfio_group_fops_unl_ioctl,
- .compat_ioctl = compat_ptr_ioctl,
- .open = vfio_group_fops_open,
- .release = vfio_group_fops_release,
-};
-
/*
* Wrapper around pm_runtime_resume_and_get().
* Return error code on failure or 0 on success.
@@ -1014,22 +463,7 @@ static int vfio_device_fops_release(struct inode *inode, struct file *filep)
{
struct vfio_device *device = filep->private_data;
- mutex_lock(&device->dev_set->lock);
- vfio_assert_device_open(device);
- mutex_lock(&device->group->group_lock);
- if (device->open_count == 1 && device->ops->close_device)
- device->ops->close_device(device);
-
- vfio_device_container_unregister(device);
- mutex_unlock(&device->group->group_lock);
- device->open_count--;
- if (device->open_count == 0)
- device->kvm = NULL;
- mutex_unlock(&device->dev_set->lock);
-
- module_put(device->dev->driver->owner);
-
- vfio_device_unassign_container(device);
+ vfio_device_group_close(device);
vfio_device_put_registration(device);
@@ -1056,7 +490,7 @@ int vfio_mig_get_next_state(struct vfio_device *device,
enum vfio_device_mig_state new_fsm,
enum vfio_device_mig_state *next_fsm)
{
- enum { VFIO_DEVICE_NUM_STATES = VFIO_DEVICE_STATE_RUNNING_P2P + 1 };
+ enum { VFIO_DEVICE_NUM_STATES = VFIO_DEVICE_STATE_PRE_COPY_P2P + 1 };
/*
* The coding in this table requires the driver to implement the
* following FSM arcs:
@@ -1071,30 +505,65 @@ int vfio_mig_get_next_state(struct vfio_device *device,
* RUNNING_P2P -> RUNNING
* RUNNING_P2P -> STOP
* STOP -> RUNNING_P2P
- * Without P2P the driver must implement:
+ *
+ * If precopy is supported then the driver must support these additional
+ * FSM arcs:
+ * RUNNING -> PRE_COPY
+ * PRE_COPY -> RUNNING
+ * PRE_COPY -> STOP_COPY
+ * However, if precopy and P2P are supported together then the driver
+ * must support these additional arcs beyond the P2P arcs above:
+ * PRE_COPY -> RUNNING
+ * PRE_COPY -> PRE_COPY_P2P
+ * PRE_COPY_P2P -> PRE_COPY
+ * PRE_COPY_P2P -> RUNNING_P2P
+ * PRE_COPY_P2P -> STOP_COPY
+ * RUNNING -> PRE_COPY
+ * RUNNING_P2P -> PRE_COPY_P2P
+ *
+ * Without P2P and precopy the driver must implement:
* RUNNING -> STOP
* STOP -> RUNNING
*
* The coding will step through multiple states for some combination
* transitions; if all optional features are supported, this means the
* following ones:
+ * PRE_COPY -> PRE_COPY_P2P -> STOP_COPY
+ * PRE_COPY -> RUNNING -> RUNNING_P2P
+ * PRE_COPY -> RUNNING -> RUNNING_P2P -> STOP
+ * PRE_COPY -> RUNNING -> RUNNING_P2P -> STOP -> RESUMING
+ * PRE_COPY_P2P -> RUNNING_P2P -> RUNNING
+ * PRE_COPY_P2P -> RUNNING_P2P -> STOP
+ * PRE_COPY_P2P -> RUNNING_P2P -> STOP -> RESUMING
* RESUMING -> STOP -> RUNNING_P2P
+ * RESUMING -> STOP -> RUNNING_P2P -> PRE_COPY_P2P
* RESUMING -> STOP -> RUNNING_P2P -> RUNNING
+ * RESUMING -> STOP -> RUNNING_P2P -> RUNNING -> PRE_COPY
* RESUMING -> STOP -> STOP_COPY
+ * RUNNING -> RUNNING_P2P -> PRE_COPY_P2P
* RUNNING -> RUNNING_P2P -> STOP
* RUNNING -> RUNNING_P2P -> STOP -> RESUMING
* RUNNING -> RUNNING_P2P -> STOP -> STOP_COPY
+ * RUNNING_P2P -> RUNNING -> PRE_COPY
* RUNNING_P2P -> STOP -> RESUMING
* RUNNING_P2P -> STOP -> STOP_COPY
+ * STOP -> RUNNING_P2P -> PRE_COPY_P2P
* STOP -> RUNNING_P2P -> RUNNING
+ * STOP -> RUNNING_P2P -> RUNNING -> PRE_COPY
* STOP_COPY -> STOP -> RESUMING
* STOP_COPY -> STOP -> RUNNING_P2P
* STOP_COPY -> STOP -> RUNNING_P2P -> RUNNING
+ *
+ * The following transitions are blocked:
+ * STOP_COPY -> PRE_COPY
+ * STOP_COPY -> PRE_COPY_P2P
*/
static const u8 vfio_from_fsm_table[VFIO_DEVICE_NUM_STATES][VFIO_DEVICE_NUM_STATES] = {
[VFIO_DEVICE_STATE_STOP] = {
[VFIO_DEVICE_STATE_STOP] = VFIO_DEVICE_STATE_STOP,
[VFIO_DEVICE_STATE_RUNNING] = VFIO_DEVICE_STATE_RUNNING_P2P,
+ [VFIO_DEVICE_STATE_PRE_COPY] = VFIO_DEVICE_STATE_RUNNING_P2P,
+ [VFIO_DEVICE_STATE_PRE_COPY_P2P] = VFIO_DEVICE_STATE_RUNNING_P2P,
[VFIO_DEVICE_STATE_STOP_COPY] = VFIO_DEVICE_STATE_STOP_COPY,
[VFIO_DEVICE_STATE_RESUMING] = VFIO_DEVICE_STATE_RESUMING,
[VFIO_DEVICE_STATE_RUNNING_P2P] = VFIO_DEVICE_STATE_RUNNING_P2P,
@@ -1103,14 +572,38 @@ int vfio_mig_get_next_state(struct vfio_device *device,
[VFIO_DEVICE_STATE_RUNNING] = {
[VFIO_DEVICE_STATE_STOP] = VFIO_DEVICE_STATE_RUNNING_P2P,
[VFIO_DEVICE_STATE_RUNNING] = VFIO_DEVICE_STATE_RUNNING,
+ [VFIO_DEVICE_STATE_PRE_COPY] = VFIO_DEVICE_STATE_PRE_COPY,
+ [VFIO_DEVICE_STATE_PRE_COPY_P2P] = VFIO_DEVICE_STATE_RUNNING_P2P,
[VFIO_DEVICE_STATE_STOP_COPY] = VFIO_DEVICE_STATE_RUNNING_P2P,
[VFIO_DEVICE_STATE_RESUMING] = VFIO_DEVICE_STATE_RUNNING_P2P,
[VFIO_DEVICE_STATE_RUNNING_P2P] = VFIO_DEVICE_STATE_RUNNING_P2P,
[VFIO_DEVICE_STATE_ERROR] = VFIO_DEVICE_STATE_ERROR,
},
+ [VFIO_DEVICE_STATE_PRE_COPY] = {
+ [VFIO_DEVICE_STATE_STOP] = VFIO_DEVICE_STATE_RUNNING,
+ [VFIO_DEVICE_STATE_RUNNING] = VFIO_DEVICE_STATE_RUNNING,
+ [VFIO_DEVICE_STATE_PRE_COPY] = VFIO_DEVICE_STATE_PRE_COPY,
+ [VFIO_DEVICE_STATE_PRE_COPY_P2P] = VFIO_DEVICE_STATE_PRE_COPY_P2P,
+ [VFIO_DEVICE_STATE_STOP_COPY] = VFIO_DEVICE_STATE_PRE_COPY_P2P,
+ [VFIO_DEVICE_STATE_RESUMING] = VFIO_DEVICE_STATE_RUNNING,
+ [VFIO_DEVICE_STATE_RUNNING_P2P] = VFIO_DEVICE_STATE_RUNNING,
+ [VFIO_DEVICE_STATE_ERROR] = VFIO_DEVICE_STATE_ERROR,
+ },
+ [VFIO_DEVICE_STATE_PRE_COPY_P2P] = {
+ [VFIO_DEVICE_STATE_STOP] = VFIO_DEVICE_STATE_RUNNING_P2P,
+ [VFIO_DEVICE_STATE_RUNNING] = VFIO_DEVICE_STATE_RUNNING_P2P,
+ [VFIO_DEVICE_STATE_PRE_COPY] = VFIO_DEVICE_STATE_PRE_COPY,
+ [VFIO_DEVICE_STATE_PRE_COPY_P2P] = VFIO_DEVICE_STATE_PRE_COPY_P2P,
+ [VFIO_DEVICE_STATE_STOP_COPY] = VFIO_DEVICE_STATE_STOP_COPY,
+ [VFIO_DEVICE_STATE_RESUMING] = VFIO_DEVICE_STATE_RUNNING_P2P,
+ [VFIO_DEVICE_STATE_RUNNING_P2P] = VFIO_DEVICE_STATE_RUNNING_P2P,
+ [VFIO_DEVICE_STATE_ERROR] = VFIO_DEVICE_STATE_ERROR,
+ },
[VFIO_DEVICE_STATE_STOP_COPY] = {
[VFIO_DEVICE_STATE_STOP] = VFIO_DEVICE_STATE_STOP,
[VFIO_DEVICE_STATE_RUNNING] = VFIO_DEVICE_STATE_STOP,
+ [VFIO_DEVICE_STATE_PRE_COPY] = VFIO_DEVICE_STATE_ERROR,
+ [VFIO_DEVICE_STATE_PRE_COPY_P2P] = VFIO_DEVICE_STATE_ERROR,
[VFIO_DEVICE_STATE_STOP_COPY] = VFIO_DEVICE_STATE_STOP_COPY,
[VFIO_DEVICE_STATE_RESUMING] = VFIO_DEVICE_STATE_STOP,
[VFIO_DEVICE_STATE_RUNNING_P2P] = VFIO_DEVICE_STATE_STOP,
@@ -1119,6 +612,8 @@ int vfio_mig_get_next_state(struct vfio_device *device,
[VFIO_DEVICE_STATE_RESUMING] = {
[VFIO_DEVICE_STATE_STOP] = VFIO_DEVICE_STATE_STOP,
[VFIO_DEVICE_STATE_RUNNING] = VFIO_DEVICE_STATE_STOP,
+ [VFIO_DEVICE_STATE_PRE_COPY] = VFIO_DEVICE_STATE_STOP,
+ [VFIO_DEVICE_STATE_PRE_COPY_P2P] = VFIO_DEVICE_STATE_STOP,
[VFIO_DEVICE_STATE_STOP_COPY] = VFIO_DEVICE_STATE_STOP,
[VFIO_DEVICE_STATE_RESUMING] = VFIO_DEVICE_STATE_RESUMING,
[VFIO_DEVICE_STATE_RUNNING_P2P] = VFIO_DEVICE_STATE_STOP,
@@ -1127,6 +622,8 @@ int vfio_mig_get_next_state(struct vfio_device *device,
[VFIO_DEVICE_STATE_RUNNING_P2P] = {
[VFIO_DEVICE_STATE_STOP] = VFIO_DEVICE_STATE_STOP,
[VFIO_DEVICE_STATE_RUNNING] = VFIO_DEVICE_STATE_RUNNING,
+ [VFIO_DEVICE_STATE_PRE_COPY] = VFIO_DEVICE_STATE_RUNNING,
+ [VFIO_DEVICE_STATE_PRE_COPY_P2P] = VFIO_DEVICE_STATE_PRE_COPY_P2P,
[VFIO_DEVICE_STATE_STOP_COPY] = VFIO_DEVICE_STATE_STOP,
[VFIO_DEVICE_STATE_RESUMING] = VFIO_DEVICE_STATE_STOP,
[VFIO_DEVICE_STATE_RUNNING_P2P] = VFIO_DEVICE_STATE_RUNNING_P2P,
@@ -1135,6 +632,8 @@ int vfio_mig_get_next_state(struct vfio_device *device,
[VFIO_DEVICE_STATE_ERROR] = {
[VFIO_DEVICE_STATE_STOP] = VFIO_DEVICE_STATE_ERROR,
[VFIO_DEVICE_STATE_RUNNING] = VFIO_DEVICE_STATE_ERROR,
+ [VFIO_DEVICE_STATE_PRE_COPY] = VFIO_DEVICE_STATE_ERROR,
+ [VFIO_DEVICE_STATE_PRE_COPY_P2P] = VFIO_DEVICE_STATE_ERROR,
[VFIO_DEVICE_STATE_STOP_COPY] = VFIO_DEVICE_STATE_ERROR,
[VFIO_DEVICE_STATE_RESUMING] = VFIO_DEVICE_STATE_ERROR,
[VFIO_DEVICE_STATE_RUNNING_P2P] = VFIO_DEVICE_STATE_ERROR,
@@ -1145,6 +644,11 @@ int vfio_mig_get_next_state(struct vfio_device *device,
static const unsigned int state_flags_table[VFIO_DEVICE_NUM_STATES] = {
[VFIO_DEVICE_STATE_STOP] = VFIO_MIGRATION_STOP_COPY,
[VFIO_DEVICE_STATE_RUNNING] = VFIO_MIGRATION_STOP_COPY,
+ [VFIO_DEVICE_STATE_PRE_COPY] =
+ VFIO_MIGRATION_STOP_COPY | VFIO_MIGRATION_PRE_COPY,
+ [VFIO_DEVICE_STATE_PRE_COPY_P2P] = VFIO_MIGRATION_STOP_COPY |
+ VFIO_MIGRATION_P2P |
+ VFIO_MIGRATION_PRE_COPY,
[VFIO_DEVICE_STATE_STOP_COPY] = VFIO_MIGRATION_STOP_COPY,
[VFIO_DEVICE_STATE_RESUMING] = VFIO_MIGRATION_STOP_COPY,
[VFIO_DEVICE_STATE_RUNNING_P2P] =
@@ -1256,6 +760,34 @@ out_copy:
return 0;
}
+static int
+vfio_ioctl_device_feature_migration_data_size(struct vfio_device *device,
+ u32 flags, void __user *arg,
+ size_t argsz)
+{
+ struct vfio_device_feature_mig_data_size data_size = {};
+ unsigned long stop_copy_length;
+ int ret;
+
+ if (!device->mig_ops)
+ return -ENOTTY;
+
+ ret = vfio_check_feature(flags, argsz, VFIO_DEVICE_FEATURE_GET,
+ sizeof(data_size));
+ if (ret != 1)
+ return ret;
+
+ ret = device->mig_ops->migration_get_data_size(device, &stop_copy_length);
+ if (ret)
+ return ret;
+
+ data_size.stop_copy_length = stop_copy_length;
+ if (copy_to_user(arg, &data_size, sizeof(data_size)))
+ return -EFAULT;
+
+ return 0;
+}
+
static int vfio_ioctl_device_feature_migration(struct vfio_device *device,
u32 flags, void __user *arg,
size_t argsz)
@@ -1483,6 +1015,10 @@ static int vfio_ioctl_device_feature(struct vfio_device *device,
return vfio_ioctl_device_feature_logging_report(
device, feature.flags, arg->data,
feature.argsz - minsz);
+ case VFIO_DEVICE_FEATURE_MIG_DATA_SIZE:
+ return vfio_ioctl_device_feature_migration_data_size(
+ device, feature.flags, arg->data,
+ feature.argsz - minsz);
default:
if (unlikely(!device->ops->device_feature))
return -EINVAL;
@@ -1552,7 +1088,7 @@ static int vfio_device_fops_mmap(struct file *filep, struct vm_area_struct *vma)
return device->ops->mmap(device, vma);
}
-static const struct file_operations vfio_device_fops = {
+const struct file_operations vfio_device_fops = {
.owner = THIS_MODULE,
.release = vfio_device_fops_release,
.read = vfio_device_fops_read,
@@ -1562,118 +1098,6 @@ static const struct file_operations vfio_device_fops = {
.mmap = vfio_device_fops_mmap,
};
-/**
- * vfio_file_iommu_group - Return the struct iommu_group for the vfio group file
- * @file: VFIO group file
- *
- * The returned iommu_group is valid as long as a ref is held on the file. This
- * returns a reference on the group. This function is deprecated, only the SPAPR
- * path in kvm should call it.
- */
-struct iommu_group *vfio_file_iommu_group(struct file *file)
-{
- struct vfio_group *group = file->private_data;
- struct iommu_group *iommu_group = NULL;
-
- if (!IS_ENABLED(CONFIG_SPAPR_TCE_IOMMU))
- return NULL;
-
- if (!vfio_file_is_group(file))
- return NULL;
-
- mutex_lock(&group->group_lock);
- if (group->iommu_group) {
- iommu_group = group->iommu_group;
- iommu_group_ref_get(iommu_group);
- }
- mutex_unlock(&group->group_lock);
- return iommu_group;
-}
-EXPORT_SYMBOL_GPL(vfio_file_iommu_group);
-
-/**
- * vfio_file_is_group - True if the file is usable with VFIO aPIS
- * @file: VFIO group file
- */
-bool vfio_file_is_group(struct file *file)
-{
- return file->f_op == &vfio_group_fops;
-}
-EXPORT_SYMBOL_GPL(vfio_file_is_group);
-
-/**
- * vfio_file_enforced_coherent - True if the DMA associated with the VFIO file
- * is always CPU cache coherent
- * @file: VFIO group file
- *
- * Enforced coherency means that the IOMMU ignores things like the PCIe no-snoop
- * bit in DMA transactions. A return of false indicates that the user has
- * rights to access additional instructions such as wbinvd on x86.
- */
-bool vfio_file_enforced_coherent(struct file *file)
-{
- struct vfio_group *group = file->private_data;
- bool ret;
-
- if (!vfio_file_is_group(file))
- return true;
-
- mutex_lock(&group->group_lock);
- if (group->container) {
- ret = vfio_container_ioctl_check_extension(group->container,
- VFIO_DMA_CC_IOMMU);
- } else {
- /*
- * Since the coherency state is determined only once a container
- * is attached the user must do so before they can prove they
- * have permission.
- */
- ret = true;
- }
- mutex_unlock(&group->group_lock);
- return ret;
-}
-EXPORT_SYMBOL_GPL(vfio_file_enforced_coherent);
-
-/**
- * vfio_file_set_kvm - Link a kvm with VFIO drivers
- * @file: VFIO group file
- * @kvm: KVM to link
- *
- * When a VFIO device is first opened the KVM will be available in
- * device->kvm if one was associated with the group.
- */
-void vfio_file_set_kvm(struct file *file, struct kvm *kvm)
-{
- struct vfio_group *group = file->private_data;
-
- if (!vfio_file_is_group(file))
- return;
-
- mutex_lock(&group->group_lock);
- group->kvm = kvm;
- mutex_unlock(&group->group_lock);
-}
-EXPORT_SYMBOL_GPL(vfio_file_set_kvm);
-
-/**
- * vfio_file_has_dev - True if the VFIO file is a handle for device
- * @file: VFIO file to check
- * @device: Device that must be part of the file
- *
- * Returns true if given file has permission to manipulate the given device.
- */
-bool vfio_file_has_dev(struct file *file, struct vfio_device *device)
-{
- struct vfio_group *group = file->private_data;
-
- if (!vfio_file_is_group(file))
- return false;
-
- return group == device->group;
-}
-EXPORT_SYMBOL_GPL(vfio_file_has_dev);
-
/*
* Sub-module support
*/
@@ -1794,34 +1218,139 @@ int vfio_set_irqs_validate_and_prepare(struct vfio_irq_set *hdr, int num_irqs,
EXPORT_SYMBOL(vfio_set_irqs_validate_and_prepare);
/*
- * Module/class support
+ * Pin contiguous user pages and return their associated host pages for local
+ * domain only.
+ * @device [in] : device
+ * @iova [in] : starting IOVA of user pages to be pinned.
+ * @npage [in] : count of pages to be pinned. This count should not
+ * be greater than VFIO_PIN_PAGES_MAX_ENTRIES.
+ * @prot [in] : protection flags
+ * @pages[out] : array of host pages
+ * Return error or number of pages pinned.
+ *
+ * A driver may only call this function if the vfio_device was created
+ * by vfio_register_emulated_iommu_dev() due to vfio_device_container_pin_pages().
*/
-static char *vfio_devnode(struct device *dev, umode_t *mode)
+int vfio_pin_pages(struct vfio_device *device, dma_addr_t iova,
+ int npage, int prot, struct page **pages)
{
- return kasprintf(GFP_KERNEL, "vfio/%s", dev_name(dev));
+ /* group->container cannot change while a vfio device is open */
+ if (!pages || !npage || WARN_ON(!vfio_assert_device_open(device)))
+ return -EINVAL;
+ if (vfio_device_has_container(device))
+ return vfio_device_container_pin_pages(device, iova,
+ npage, prot, pages);
+ if (device->iommufd_access) {
+ int ret;
+
+ if (iova > ULONG_MAX)
+ return -EINVAL;
+ /*
+ * VFIO ignores the sub page offset, npages is from the start of
+ * a PAGE_SIZE chunk of IOVA. The caller is expected to recover
+ * the sub page offset by doing:
+ * pages[0] + (iova % PAGE_SIZE)
+ */
+ ret = iommufd_access_pin_pages(
+ device->iommufd_access, ALIGN_DOWN(iova, PAGE_SIZE),
+ npage * PAGE_SIZE, pages,
+ (prot & IOMMU_WRITE) ? IOMMUFD_ACCESS_RW_WRITE : 0);
+ if (ret)
+ return ret;
+ return npage;
+ }
+ return -EINVAL;
+}
+EXPORT_SYMBOL(vfio_pin_pages);
+
+/*
+ * Unpin contiguous host pages for local domain only.
+ * @device [in] : device
+ * @iova [in] : starting address of user pages to be unpinned.
+ * @npage [in] : count of pages to be unpinned. This count should not
+ * be greater than VFIO_PIN_PAGES_MAX_ENTRIES.
+ */
+void vfio_unpin_pages(struct vfio_device *device, dma_addr_t iova, int npage)
+{
+ if (WARN_ON(!vfio_assert_device_open(device)))
+ return;
+
+ if (vfio_device_has_container(device)) {
+ vfio_device_container_unpin_pages(device, iova, npage);
+ return;
+ }
+ if (device->iommufd_access) {
+ if (WARN_ON(iova > ULONG_MAX))
+ return;
+ iommufd_access_unpin_pages(device->iommufd_access,
+ ALIGN_DOWN(iova, PAGE_SIZE),
+ npage * PAGE_SIZE);
+ return;
+ }
}
+EXPORT_SYMBOL(vfio_unpin_pages);
+/*
+ * This interface allows the CPUs to perform some sort of virtual DMA on
+ * behalf of the device.
+ *
+ * CPUs read/write from/into a range of IOVAs pointing to user space memory
+ * into/from a kernel buffer.
+ *
+ * As the read/write of user space memory is conducted via the CPUs and is
+ * not a real device DMA, it is not necessary to pin the user space memory.
+ *
+ * @device [in] : VFIO device
+ * @iova [in] : base IOVA of a user space buffer
+ * @data [in] : pointer to kernel buffer
+ * @len [in] : kernel buffer length
+ * @write : indicate read or write
+ * Return error code on failure or 0 on success.
+ */
+int vfio_dma_rw(struct vfio_device *device, dma_addr_t iova, void *data,
+ size_t len, bool write)
+{
+ if (!data || len <= 0 || !vfio_assert_device_open(device))
+ return -EINVAL;
+
+ if (vfio_device_has_container(device))
+ return vfio_device_container_dma_rw(device, iova,
+ data, len, write);
+
+ if (device->iommufd_access) {
+ unsigned int flags = 0;
+
+ if (iova > ULONG_MAX)
+ return -EINVAL;
+
+ /* VFIO historically tries to auto-detect a kthread */
+ if (!current->mm)
+ flags |= IOMMUFD_ACCESS_RW_KTHREAD;
+ if (write)
+ flags |= IOMMUFD_ACCESS_RW_WRITE;
+ return iommufd_access_rw(device->iommufd_access, iova, data,
+ len, flags);
+ }
+ return -EINVAL;
+}
+EXPORT_SYMBOL(vfio_dma_rw);
+
+/*
+ * Module/class support
+ */
static int __init vfio_init(void)
{
int ret;
- ida_init(&vfio.group_ida);
ida_init(&vfio.device_ida);
- mutex_init(&vfio.group_lock);
- INIT_LIST_HEAD(&vfio.group_list);
- ret = vfio_container_init();
+ ret = vfio_group_init();
if (ret)
return ret;
- /* /dev/vfio/$GROUP */
- vfio.class = class_create(THIS_MODULE, "vfio");
- if (IS_ERR(vfio.class)) {
- ret = PTR_ERR(vfio.class);
- goto err_group_class;
- }
-
- vfio.class->devnode = vfio_devnode;
+ ret = vfio_virqfd_init();
+ if (ret)
+ goto err_virqfd;
/* /sys/class/vfio-dev/vfioX */
vfio.device_class = class_create(THIS_MODULE, "vfio-dev");
@@ -1830,36 +1359,23 @@ static int __init vfio_init(void)
goto err_dev_class;
}
- ret = alloc_chrdev_region(&vfio.group_devt, 0, MINORMASK + 1, "vfio");
- if (ret)
- goto err_alloc_chrdev;
-
pr_info(DRIVER_DESC " version: " DRIVER_VERSION "\n");
return 0;
-err_alloc_chrdev:
- class_destroy(vfio.device_class);
- vfio.device_class = NULL;
err_dev_class:
- class_destroy(vfio.class);
- vfio.class = NULL;
-err_group_class:
- vfio_container_cleanup();
+ vfio_virqfd_exit();
+err_virqfd:
+ vfio_group_cleanup();
return ret;
}
static void __exit vfio_cleanup(void)
{
- WARN_ON(!list_empty(&vfio.group_list));
-
ida_destroy(&vfio.device_ida);
- ida_destroy(&vfio.group_ida);
- unregister_chrdev_region(vfio.group_devt, MINORMASK + 1);
class_destroy(vfio.device_class);
vfio.device_class = NULL;
- class_destroy(vfio.class);
- vfio_container_cleanup();
- vfio.class = NULL;
+ vfio_virqfd_exit();
+ vfio_group_cleanup();
xa_destroy(&vfio_device_set_xa);
}
@@ -1870,6 +1386,4 @@ MODULE_VERSION(DRIVER_VERSION);
MODULE_LICENSE("GPL v2");
MODULE_AUTHOR(DRIVER_AUTHOR);
MODULE_DESCRIPTION(DRIVER_DESC);
-MODULE_ALIAS_MISCDEV(VFIO_MINOR);
-MODULE_ALIAS("devname:vfio/vfio");
MODULE_SOFTDEP("post: vfio_iommu_type1 vfio_iommu_spapr_tce");
diff --git a/drivers/vfio/vfio_spapr_eeh.c b/drivers/vfio/vfio_spapr_eeh.c
deleted file mode 100644
index 67f55ac1d459..000000000000
--- a/drivers/vfio/vfio_spapr_eeh.c
+++ /dev/null
@@ -1,107 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * EEH functionality support for VFIO devices. The feature is only
- * available on sPAPR compatible platforms.
- *
- * Copyright Gavin Shan, IBM Corporation 2014.
- */
-
-#include <linux/module.h>
-#include <linux/uaccess.h>
-#include <linux/vfio.h>
-#include <asm/eeh.h>
-
-#define DRIVER_VERSION "0.1"
-#define DRIVER_AUTHOR "Gavin Shan, IBM Corporation"
-#define DRIVER_DESC "VFIO IOMMU SPAPR EEH"
-
-/* We might build address mapping here for "fast" path later */
-void vfio_spapr_pci_eeh_open(struct pci_dev *pdev)
-{
- eeh_dev_open(pdev);
-}
-EXPORT_SYMBOL_GPL(vfio_spapr_pci_eeh_open);
-
-void vfio_spapr_pci_eeh_release(struct pci_dev *pdev)
-{
- eeh_dev_release(pdev);
-}
-EXPORT_SYMBOL_GPL(vfio_spapr_pci_eeh_release);
-
-long vfio_spapr_iommu_eeh_ioctl(struct iommu_group *group,
- unsigned int cmd, unsigned long arg)
-{
- struct eeh_pe *pe;
- struct vfio_eeh_pe_op op;
- unsigned long minsz;
- long ret = -EINVAL;
-
- switch (cmd) {
- case VFIO_CHECK_EXTENSION:
- if (arg == VFIO_EEH)
- ret = eeh_enabled() ? 1 : 0;
- else
- ret = 0;
- break;
- case VFIO_EEH_PE_OP:
- pe = eeh_iommu_group_to_pe(group);
- if (!pe)
- return -ENODEV;
-
- minsz = offsetofend(struct vfio_eeh_pe_op, op);
- if (copy_from_user(&op, (void __user *)arg, minsz))
- return -EFAULT;
- if (op.argsz < minsz || op.flags)
- return -EINVAL;
-
- switch (op.op) {
- case VFIO_EEH_PE_DISABLE:
- ret = eeh_pe_set_option(pe, EEH_OPT_DISABLE);
- break;
- case VFIO_EEH_PE_ENABLE:
- ret = eeh_pe_set_option(pe, EEH_OPT_ENABLE);
- break;
- case VFIO_EEH_PE_UNFREEZE_IO:
- ret = eeh_pe_set_option(pe, EEH_OPT_THAW_MMIO);
- break;
- case VFIO_EEH_PE_UNFREEZE_DMA:
- ret = eeh_pe_set_option(pe, EEH_OPT_THAW_DMA);
- break;
- case VFIO_EEH_PE_GET_STATE:
- ret = eeh_pe_get_state(pe);
- break;
- case VFIO_EEH_PE_RESET_DEACTIVATE:
- ret = eeh_pe_reset(pe, EEH_RESET_DEACTIVATE, true);
- break;
- case VFIO_EEH_PE_RESET_HOT:
- ret = eeh_pe_reset(pe, EEH_RESET_HOT, true);
- break;
- case VFIO_EEH_PE_RESET_FUNDAMENTAL:
- ret = eeh_pe_reset(pe, EEH_RESET_FUNDAMENTAL, true);
- break;
- case VFIO_EEH_PE_CONFIGURE:
- ret = eeh_pe_configure(pe);
- break;
- case VFIO_EEH_PE_INJECT_ERR:
- minsz = offsetofend(struct vfio_eeh_pe_op, err.mask);
- if (op.argsz < minsz)
- return -EINVAL;
- if (copy_from_user(&op, (void __user *)arg, minsz))
- return -EFAULT;
-
- ret = eeh_pe_inject_err(pe, op.err.type, op.err.func,
- op.err.addr, op.err.mask);
- break;
- default:
- ret = -EINVAL;
- }
- }
-
- return ret;
-}
-EXPORT_SYMBOL_GPL(vfio_spapr_iommu_eeh_ioctl);
-
-MODULE_VERSION(DRIVER_VERSION);
-MODULE_LICENSE("GPL v2");
-MODULE_AUTHOR(DRIVER_AUTHOR);
-MODULE_DESCRIPTION(DRIVER_DESC);
diff --git a/drivers/vfio/virqfd.c b/drivers/vfio/virqfd.c
index 414e98d82b02..497a17b37865 100644
--- a/drivers/vfio/virqfd.c
+++ b/drivers/vfio/virqfd.c
@@ -12,15 +12,12 @@
#include <linux/file.h>
#include <linux/module.h>
#include <linux/slab.h>
-
-#define DRIVER_VERSION "0.1"
-#define DRIVER_AUTHOR "Alex Williamson <alex.williamson@redhat.com>"
-#define DRIVER_DESC "IRQFD support for VFIO bus drivers"
+#include "vfio.h"
static struct workqueue_struct *vfio_irqfd_cleanup_wq;
static DEFINE_SPINLOCK(virqfd_lock);
-static int __init vfio_virqfd_init(void)
+int __init vfio_virqfd_init(void)
{
vfio_irqfd_cleanup_wq =
create_singlethread_workqueue("vfio-irqfd-cleanup");
@@ -30,7 +27,7 @@ static int __init vfio_virqfd_init(void)
return 0;
}
-static void __exit vfio_virqfd_exit(void)
+void vfio_virqfd_exit(void)
{
destroy_workqueue(vfio_irqfd_cleanup_wq);
}
@@ -216,11 +213,3 @@ void vfio_virqfd_disable(struct virqfd **pvirqfd)
flush_workqueue(vfio_irqfd_cleanup_wq);
}
EXPORT_SYMBOL_GPL(vfio_virqfd_disable);
-
-module_init(vfio_virqfd_init);
-module_exit(vfio_virqfd_exit);
-
-MODULE_VERSION(DRIVER_VERSION);
-MODULE_LICENSE("GPL v2");
-MODULE_AUTHOR(DRIVER_AUTHOR);
-MODULE_DESCRIPTION(DRIVER_DESC);
generated by cgit (git 2.34.1) at 2025-04-13 13:54:38 +0000