From: Eric Auger <eric.auger@redhat.com>
To: eric.auger.pro@gmail.com, eric.auger@redhat.com,
qemu-devel@nongnu.org, qemu-arm@nongnu.org,
peter.maydell@linaro.org, mst@redhat.com,
alex.williamson@redhat.com, jacob.jun.pan@linux.intel.com,
yi.l.liu@intel.com
Cc: jean-philippe@linaro.org, tnowicki@marvell.com, maz@kernel.org,
zhangfei.gao@foxmail.com, peterx@redhat.com,
shameerali.kolothum.thodi@huawei.com, zhangfei.gao@linaro.org,
bbhushan2@marvell.com, will@kernel.org
Subject: [RFC v6 12/24] vfio: Set up nested stage mappings
Date: Fri, 20 Mar 2020 17:58:28 +0100 [thread overview]
Message-ID: <20200320165840.30057-13-eric.auger@redhat.com> (raw)
In-Reply-To: <20200320165840.30057-1-eric.auger@redhat.com>
In nested mode, legacy vfio_iommu_map_notify cannot be used as
there is no "caching" mode and we do not trap on map.
On Intel, vfio_iommu_map_notify was used to DMA map the RAM
through the host single stage.
With nested mode, we need to setup the stage 2 and the stage 1
separately. This patch introduces a prereg_listener to setup
the stage 2 mapping.
The stage 1 mapping, owned by the guest, is passed to the host
when the guest invalidates the stage 1 configuration, through
a dedicated PCIPASIDOps callback. Guest IOTLB invalidations
are cascaded downto the host through another IOMMU MR UNMAP
notifier.
Signed-off-by: Eric Auger <eric.auger@redhat.com>
---
v6 -> v7:
- remove PASID based invalidation
v5 -> v6:
- add error_report_err()
- remove the abort in case of nested stage case
v4 -> v5:
- use VFIO_IOMMU_SET_PASID_TABLE
- use PCIPASIDOps for config notification
v3 -> v4:
- use iommu_inv_pasid_info for ASID invalidation
v2 -> v3:
- use VFIO_IOMMU_ATTACH_PASID_TABLE
- new user API
- handle leaf
v1 -> v2:
- adapt to uapi changes
- pass the asid
- pass IOMMU_NOTIFIER_S1_CFG when initializing the config notifier
---
hw/vfio/common.c | 112 ++++++++++++++++++++++++++++++++++++++++---
hw/vfio/pci.c | 21 ++++++++
hw/vfio/trace-events | 2 +
3 files changed, 129 insertions(+), 6 deletions(-)
diff --git a/hw/vfio/common.c b/hw/vfio/common.c
index e067009da8..c0ae59bfe6 100644
--- a/hw/vfio/common.c
+++ b/hw/vfio/common.c
@@ -446,6 +446,44 @@ static bool vfio_get_vaddr(IOMMUTLBEntry *iotlb, void **vaddr,
return true;
}
+/* Propagate a guest IOTLB invalidation to the host (nested mode) */
+static void vfio_iommu_unmap_notify(IOMMUNotifier *n, IOMMUTLBEntry *iotlb)
+{
+ VFIOGuestIOMMU *giommu = container_of(n, VFIOGuestIOMMU, n);
+ hwaddr start = iotlb->iova + giommu->iommu_offset;
+
+ VFIOContainer *container = giommu->container;
+ struct vfio_iommu_type1_cache_invalidate ustruct;
+ size_t size = iotlb->addr_mask + 1;
+ int ret;
+
+ assert(iotlb->perm == IOMMU_NONE);
+
+ ustruct.argsz = sizeof(ustruct);
+ ustruct.flags = 0;
+ ustruct.info.version = IOMMU_CACHE_INVALIDATE_INFO_VERSION_1;
+
+ ustruct.info.cache = IOMMU_CACHE_INV_TYPE_IOTLB;
+ ustruct.info.granularity = IOMMU_INV_GRANU_ADDR;
+ ustruct.info.addr_info.flags = IOMMU_INV_ADDR_FLAGS_ARCHID;
+ if (iotlb->leaf) {
+ ustruct.info.addr_info.flags |= IOMMU_INV_ADDR_FLAGS_LEAF;
+ }
+ ustruct.info.addr_info.archid = iotlb->arch_id;
+ ustruct.info.addr_info.addr = start;
+ ustruct.info.addr_info.granule_size = size;
+ ustruct.info.addr_info.nb_granules = 1;
+ trace_vfio_iommu_addr_inv_iotlb(iotlb->arch_id, start, size, 1,
+ iotlb->leaf);
+
+ ret = ioctl(container->fd, VFIO_IOMMU_CACHE_INVALIDATE, &ustruct);
+ if (ret) {
+ error_report("%p: failed to invalidate CACHE for 0x%"PRIx64
+ " mask=0x%"PRIx64" (%d)",
+ container, start, iotlb->addr_mask, ret);
+ }
+}
+
static void vfio_iommu_map_notify(IOMMUNotifier *n, IOMMUTLBEntry *iotlb)
{
VFIOGuestIOMMU *giommu = container_of(n, VFIOGuestIOMMU, n);
@@ -615,6 +653,35 @@ static void vfio_dma_unmap_ram_section(VFIOContainer *container,
}
}
+static void vfio_prereg_listener_region_add(MemoryListener *listener,
+ MemoryRegionSection *section)
+{
+ VFIOContainer *container =
+ container_of(listener, VFIOContainer, prereg_listener);
+ Error *err = NULL;
+
+ if (!memory_region_is_ram(section->mr)) {
+ return;
+ }
+
+ vfio_dma_map_ram_section(container, section, &err);
+ if (err) {
+ error_report_err(err);
+ }
+}
+static void vfio_prereg_listener_region_del(MemoryListener *listener,
+ MemoryRegionSection *section)
+{
+ VFIOContainer *container =
+ container_of(listener, VFIOContainer, prereg_listener);
+
+ if (!memory_region_is_ram(section->mr)) {
+ return;
+ }
+
+ vfio_dma_unmap_ram_section(container, section);
+}
+
static void vfio_listener_region_add(MemoryListener *listener,
MemoryRegionSection *section)
{
@@ -717,9 +784,10 @@ static void vfio_listener_region_add(MemoryListener *listener,
memory_region_ref(section->mr);
if (memory_region_is_iommu(section->mr)) {
+ IOMMUNotify notify;
VFIOGuestIOMMU *giommu;
IOMMUMemoryRegion *iommu_mr = IOMMU_MEMORY_REGION(section->mr);
- int iommu_idx;
+ int iommu_idx, flags;
trace_vfio_listener_region_add_iommu(iova, end);
/*
@@ -738,8 +806,18 @@ static void vfio_listener_region_add(MemoryListener *listener,
llend = int128_sub(llend, int128_one());
iommu_idx = memory_region_iommu_attrs_to_index(iommu_mr,
MEMTXATTRS_UNSPECIFIED);
- iommu_notifier_init(&giommu->n, vfio_iommu_map_notify,
- IOMMU_NOTIFIER_ALL,
+
+ if (container->iommu_type == VFIO_TYPE1_NESTING_IOMMU) {
+ /* IOTLB unmap notifier to propagate guest IOTLB invalidations */
+ flags = IOMMU_NOTIFIER_UNMAP;
+ notify = vfio_iommu_unmap_notify;
+ } else {
+ /* MAP/UNMAP IOTLB notifier */
+ flags = IOMMU_NOTIFIER_ALL;
+ notify = vfio_iommu_map_notify;
+ }
+
+ iommu_notifier_init(&giommu->n, notify, flags,
section->offset_within_region,
int128_get64(llend),
iommu_idx);
@@ -751,7 +829,9 @@ static void vfio_listener_region_add(MemoryListener *listener,
goto fail;
}
QLIST_INSERT_HEAD(&container->giommu_list, giommu, giommu_next);
- memory_region_iommu_replay(giommu->iommu, &giommu->n);
+ if (flags & IOMMU_NOTIFIER_MAP) {
+ memory_region_iommu_replay(giommu->iommu, &giommu->n);
+ }
return;
}
@@ -846,15 +926,21 @@ static void vfio_listener_region_del(MemoryListener *listener,
}
}
-static const MemoryListener vfio_memory_listener = {
+static MemoryListener vfio_memory_listener = {
.region_add = vfio_listener_region_add,
.region_del = vfio_listener_region_del,
};
+static MemoryListener vfio_memory_prereg_listener = {
+ .region_add = vfio_prereg_listener_region_add,
+ .region_del = vfio_prereg_listener_region_del,
+};
+
static void vfio_listener_release(VFIOContainer *container)
{
memory_listener_unregister(&container->listener);
- if (container->iommu_type == VFIO_SPAPR_TCE_v2_IOMMU) {
+ if (container->iommu_type == VFIO_SPAPR_TCE_v2_IOMMU ||
+ container->iommu_type == VFIO_TYPE1_NESTING_IOMMU) {
memory_listener_unregister(&container->prereg_listener);
}
}
@@ -1352,6 +1438,20 @@ static int vfio_connect_container(VFIOGroup *group, AddressSpace *as,
}
vfio_host_win_add(container, 0, (hwaddr)-1, info.iova_pgsizes);
container->pgsizes = info.iova_pgsizes;
+
+ if (container->iommu_type == VFIO_TYPE1_NESTING_IOMMU) {
+ container->prereg_listener = vfio_memory_prereg_listener;
+ memory_listener_register(&container->prereg_listener,
+ &address_space_memory);
+ if (container->error) {
+ memory_listener_unregister(&container->prereg_listener);
+ ret = -1;
+ error_propagate_prepend(errp, container->error,
+ "RAM memory listener initialization failed "
+ "for container");
+ goto free_container_exit;
+ }
+ }
break;
}
case VFIO_SPAPR_TCE_v2_IOMMU:
diff --git a/hw/vfio/pci.c b/hw/vfio/pci.c
index 5e75a95129..fc314cc6a9 100644
--- a/hw/vfio/pci.c
+++ b/hw/vfio/pci.c
@@ -2712,6 +2712,25 @@ static void vfio_unregister_req_notifier(VFIOPCIDevice *vdev)
vdev->req_enabled = false;
}
+static int vfio_iommu_set_pasid_table(PCIBus *bus, int32_t devfn,
+ IOMMUConfig *config)
+{
+ PCIDevice *pdev = bus->devices[devfn];
+ VFIOPCIDevice *vdev = DO_UPCAST(VFIOPCIDevice, pdev, pdev);
+ VFIOContainer *container = vdev->vbasedev.group->container;
+ struct vfio_iommu_type1_set_pasid_table info;
+
+ info.argsz = sizeof(info);
+ info.flags = VFIO_PASID_TABLE_FLAG_SET;
+ memcpy(&info.config, &config->pasid_cfg, sizeof(config->pasid_cfg));
+
+ return ioctl(container->fd, VFIO_IOMMU_SET_PASID_TABLE, &info);
+}
+
+static PCIPASIDOps vfio_pci_pasid_ops = {
+ .set_pasid_table = vfio_iommu_set_pasid_table,
+};
+
static void vfio_realize(PCIDevice *pdev, Error **errp)
{
VFIOPCIDevice *vdev = PCI_VFIO(pdev);
@@ -3028,6 +3047,8 @@ static void vfio_realize(PCIDevice *pdev, Error **errp)
vfio_register_req_notifier(vdev);
vfio_setup_resetfn_quirk(vdev);
+ pci_setup_pasid_ops(pdev, &vfio_pci_pasid_ops);
+
return;
out_deregister:
diff --git a/hw/vfio/trace-events b/hw/vfio/trace-events
index 410801de6e..9f1868af2d 100644
--- a/hw/vfio/trace-events
+++ b/hw/vfio/trace-events
@@ -115,6 +115,8 @@ vfio_region_sparse_mmap_header(const char *name, int index, int nr_areas) "Devic
vfio_region_sparse_mmap_entry(int i, unsigned long start, unsigned long end) "sparse entry %d [0x%lx - 0x%lx]"
vfio_get_dev_region(const char *name, int index, uint32_t type, uint32_t subtype) "%s index %d, %08x/%0x8"
vfio_dma_unmap_overflow_workaround(void) ""
+vfio_iommu_addr_inv_iotlb(int asid, uint64_t addr, uint64_t size, uint64_t nb_granules, bool leaf) "nested IOTLB invalidate asid=%d, addr=0x%"PRIx64" granule_size=0x%"PRIx64" nb_granules=0x%"PRIx64" leaf=%d"
+vfio_iommu_asid_inv_iotlb(int asid) "nested IOTLB invalidate asid=%d"
# platform.c
vfio_platform_base_device_init(char *name, int groupid) "%s belongs to group #%d"
--
2.20.1
next prev parent reply other threads:[~2020-03-20 17:06 UTC|newest]
Thread overview: 40+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-03-20 16:58 [RFC v6 00/24] vSMMUv3/pSMMUv3 2 stage VFIO integration Eric Auger
2020-03-20 16:58 ` [RFC v6 01/24] update-linux-headers: Import iommu.h Eric Auger
2020-03-26 12:58 ` Liu, Yi L
2020-03-26 17:51 ` Auger Eric
2020-03-20 16:58 ` [RFC v6 02/24] header update against 5.6.0-rc3 and IOMMU/VFIO nested stage APIs Eric Auger
2020-03-20 16:58 ` [RFC v6 03/24] memory: Add IOMMU_ATTR_VFIO_NESTED IOMMU memory region attribute Eric Auger
2020-03-20 16:58 ` [RFC v6 04/24] memory: Add IOMMU_ATTR_MSI_TRANSLATE " Eric Auger
2020-03-20 16:58 ` [RFC v6 05/24] memory: Introduce IOMMU Memory Region inject_faults API Eric Auger
2020-03-26 13:13 ` Liu, Yi L
2020-03-20 16:58 ` [RFC v6 06/24] memory: Add arch_id and leaf fields in IOTLBEntry Eric Auger
2020-03-20 16:58 ` [RFC v6 07/24] iommu: Introduce generic header Eric Auger
2020-03-20 16:58 ` [RFC v6 08/24] pci: introduce PCIPASIDOps to PCIDevice Eric Auger
2020-03-26 13:01 ` Liu, Yi L
2020-03-20 16:58 ` [RFC v6 09/24] vfio: Force nested if iommu requires it Eric Auger
2020-03-31 6:34 ` Liu, Yi L
2020-03-31 8:04 ` Auger Eric
2020-03-31 8:34 ` Liu, Yi L
2020-03-20 16:58 ` [RFC v6 10/24] vfio: Introduce hostwin_from_range helper Eric Auger
2020-03-20 16:58 ` [RFC v6 11/24] vfio: Introduce helpers to DMA map/unmap a RAM section Eric Auger
2020-03-20 16:58 ` Eric Auger [this message]
2020-03-20 16:58 ` [RFC v6 13/24] vfio: Pass stage 1 MSI bindings to the host Eric Auger
2020-03-20 16:58 ` [RFC v6 14/24] vfio: Helper to get IRQ info including capabilities Eric Auger
2020-03-20 16:58 ` [RFC v6 15/24] vfio/pci: Register handler for iommu fault Eric Auger
2020-03-20 16:58 ` [RFC v6 16/24] vfio/pci: Set up the DMA FAULT region Eric Auger
2020-03-20 16:58 ` [RFC v6 17/24] vfio/pci: Implement the DMA fault handler Eric Auger
2020-03-20 16:58 ` [RFC v6 18/24] hw/arm/smmuv3: Advertise MSI_TRANSLATE attribute Eric Auger
2020-03-20 16:58 ` [RFC v6 19/24] hw/arm/smmuv3: Store the PASID table GPA in the translation config Eric Auger
2020-03-20 16:58 ` [RFC v6 20/24] hw/arm/smmuv3: Fill the IOTLBEntry arch_id on NH_VA invalidation Eric Auger
2020-03-20 16:58 ` [RFC v6 21/24] hw/arm/smmuv3: Fill the IOTLBEntry leaf field " Eric Auger
2020-03-20 16:58 ` [RFC v6 22/24] hw/arm/smmuv3: Pass stage 1 configurations to the host Eric Auger
2020-03-20 16:58 ` [RFC v6 23/24] hw/arm/smmuv3: Implement fault injection Eric Auger
2020-03-20 16:58 ` [RFC v6 24/24] hw/arm/smmuv3: Allow MAP notifiers Eric Auger
2020-03-25 11:35 ` [RFC v6 00/24] vSMMUv3/pSMMUv3 2 stage VFIO integration Shameerali Kolothum Thodi
2020-03-25 12:42 ` Auger Eric
2020-04-03 10:45 ` Auger Eric
2020-04-03 12:10 ` Shameerali Kolothum Thodi
2020-03-31 6:42 ` Zhangfei Gao
2020-03-31 8:12 ` Auger Eric
2020-03-31 8:24 ` Zhangfei Gao
2020-04-02 16:46 ` Auger Eric
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20200320165840.30057-13-eric.auger@redhat.com \
--to=eric.auger@redhat.com \
--cc=alex.williamson@redhat.com \
--cc=bbhushan2@marvell.com \
--cc=eric.auger.pro@gmail.com \
--cc=jacob.jun.pan@linux.intel.com \
--cc=jean-philippe@linaro.org \
--cc=maz@kernel.org \
--cc=mst@redhat.com \
--cc=peter.maydell@linaro.org \
--cc=peterx@redhat.com \
--cc=qemu-arm@nongnu.org \
--cc=qemu-devel@nongnu.org \
--cc=shameerali.kolothum.thodi@huawei.com \
--cc=tnowicki@marvell.com \
--cc=will@kernel.org \
--cc=yi.l.liu@intel.com \
--cc=zhangfei.gao@foxmail.com \
--cc=zhangfei.gao@linaro.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).