From: Zhenzhong Duan <zhenzhong.duan@intel.com>
To: qemu-devel@nongnu.org
Cc: alex.williamson@redhat.com, clg@redhat.com,
eric.auger@redhat.com, mst@redhat.com, jasowang@redhat.com,
peterx@redhat.com, ddutile@redhat.com, jgg@nvidia.com,
nicolinc@nvidia.com, skolothumtho@nvidia.com,
joao.m.martins@oracle.com, clement.mathieu--drif@eviden.com,
kevin.tian@intel.com, yi.l.liu@intel.com, chao.p.peng@intel.com,
Zhenzhong Duan <zhenzhong.duan@intel.com>
Subject: [PATCH v6 18/22] iommufd: Introduce a helper function to extract vendor capabilities
Date: Thu, 18 Sep 2025 04:57:57 -0400 [thread overview]
Message-ID: <20250918085803.796942-19-zhenzhong.duan@intel.com> (raw)
In-Reply-To: <20250918085803.796942-1-zhenzhong.duan@intel.com>
In VFIO core, we call iommufd_backend_get_device_info() to return vendor
specific hardware information data, but it's not good to extract this raw
data in VFIO core.
Introduce host_iommu_extract_vendor_caps() to help extracting the raw
data and return a bitmap in iommufd.c because it's the place defining
iommufd_backend_get_device_info().
The other choice is to put vendor data extracting code in vendor vIOMMU
emulation file, but that will make those files mixed with vIOMMU
emulation and host IOMMU extracting code, also need a new callback in
PCIIOMMUOps. So we choose a simpler way as above.
Suggested-by: Nicolin Chen <nicolinc@nvidia.com>
Signed-off-by: Zhenzhong Duan <zhenzhong.duan@intel.com>
---
include/hw/iommu.h | 5 +++++
include/system/host_iommu_device.h | 16 ++++++++++++++++
backends/iommufd.c | 13 +++++++++++++
3 files changed, 34 insertions(+)
diff --git a/include/hw/iommu.h b/include/hw/iommu.h
index 65d652950a..9b343e64b0 100644
--- a/include/hw/iommu.h
+++ b/include/hw/iommu.h
@@ -16,4 +16,9 @@ enum {
VIOMMU_FLAG_WANT_NESTING_PARENT = BIT_ULL(0),
};
+enum {
+ /* Nesting parent HWPT shouldn't have readonly mapping, due to errata */
+ IOMMU_HW_NESTING_PARENT_BYPASS_RO = BIT_ULL(0),
+};
+
#endif /* HW_IOMMU_H */
diff --git a/include/system/host_iommu_device.h b/include/system/host_iommu_device.h
index ab849a4a82..41c9159605 100644
--- a/include/system/host_iommu_device.h
+++ b/include/system/host_iommu_device.h
@@ -39,6 +39,22 @@ typedef struct HostIOMMUDeviceCaps {
uint64_t hw_caps;
VendorCaps vendor_caps;
} HostIOMMUDeviceCaps;
+
+/**
+ * host_iommu_extract_vendor_caps: Extract vendor capabilities
+ *
+ * This function converts @type specific hardware information data
+ * into a standard bitmap format.
+ *
+ * @type: IOMMU Hardware Info Types
+ *
+ * @VendorCaps: IOMMU @type specific hardware information data
+ *
+ * Returns: 64bit bitmap with each bit represents a capability of host
+ * IOMMU that we want to expose. See IOMMU_HW_* in include/hw/iommu.h
+ * for all possible capabilities currently exposed.
+ */
+uint64_t host_iommu_extract_vendor_caps(uint32_t type, VendorCaps *caps);
#endif
#define TYPE_HOST_IOMMU_DEVICE "host-iommu-device"
diff --git a/backends/iommufd.c b/backends/iommufd.c
index 2a33c7ab0b..0bb1ed40d3 100644
--- a/backends/iommufd.c
+++ b/backends/iommufd.c
@@ -19,6 +19,7 @@
#include "migration/cpr.h"
#include "monitor/monitor.h"
#include "trace.h"
+#include "hw/iommu.h"
#include "hw/vfio/vfio-device.h"
#include <sys/ioctl.h>
#include <linux/iommufd.h>
@@ -410,6 +411,18 @@ bool iommufd_backend_get_device_info(IOMMUFDBackend *be, uint32_t devid,
return true;
}
+uint64_t host_iommu_extract_vendor_caps(uint32_t type, VendorCaps *caps)
+{
+ uint64_t vendor_caps = 0;
+
+ if (type == IOMMU_HW_INFO_TYPE_INTEL_VTD &&
+ caps->vtd.flags & IOMMU_HW_INFO_VTD_ERRATA_772415_SPR17) {
+ vendor_caps |= IOMMU_HW_NESTING_PARENT_BYPASS_RO;
+ }
+
+ return vendor_caps;
+}
+
bool iommufd_backend_invalidate_cache(IOMMUFDBackend *be, uint32_t id,
uint32_t data_type, uint32_t entry_len,
uint32_t *entry_num, void *data,
--
2.47.1
next prev parent reply other threads:[~2025-09-18 9:06 UTC|newest]
Thread overview: 57+ messages / expand[flat|nested] mbox.gz Atom feed top
2025-09-18 8:57 [PATCH v6 00/22] intel_iommu: Enable first stage translation for passthrough device Zhenzhong Duan
2025-09-18 8:57 ` [PATCH v6 01/22] intel_iommu: Rename vtd_ce_get_rid2pasid_entry to vtd_ce_get_pasid_entry Zhenzhong Duan
2025-09-18 8:57 ` [PATCH v6 02/22] intel_iommu: Delete RPS capability related supporting code Zhenzhong Duan
2025-09-30 13:49 ` Eric Auger
2025-10-09 10:10 ` Duan, Zhenzhong
2025-10-12 12:30 ` Yi Liu
2025-09-18 8:57 ` [PATCH v6 03/22] intel_iommu: Update terminology to match VTD spec Zhenzhong Duan
2025-09-30 7:45 ` Eric Auger
2025-10-12 12:30 ` Yi Liu
2025-10-13 6:20 ` Duan, Zhenzhong
2025-09-18 8:57 ` [PATCH v6 04/22] hw/pci: Export pci_device_get_iommu_bus_devfn() and return bool Zhenzhong Duan
2025-09-18 8:57 ` [PATCH v6 05/22] hw/pci: Introduce pci_device_get_viommu_flags() Zhenzhong Duan
2025-09-23 18:47 ` Nicolin Chen
2025-09-24 7:05 ` Duan, Zhenzhong
2025-09-24 8:21 ` Nicolin Chen
2025-09-26 2:54 ` Duan, Zhenzhong
2025-09-30 13:55 ` Eric Auger
2025-10-12 12:26 ` Yi Liu
2025-10-13 6:24 ` Duan, Zhenzhong
2025-09-18 8:57 ` [PATCH v6 06/22] intel_iommu: Implement get_viommu_flags() callback Zhenzhong Duan
2025-10-12 12:28 ` Yi Liu
2025-10-13 6:26 ` Duan, Zhenzhong
2025-09-18 8:57 ` [PATCH v6 07/22] intel_iommu: Introduce a new structure VTDHostIOMMUDevice Zhenzhong Duan
2025-09-18 8:57 ` [PATCH v6 08/22] vfio/iommufd: Force creating nesting parent HWPT Zhenzhong Duan
2025-09-30 14:19 ` Eric Auger
2025-10-12 12:33 ` Yi Liu
2025-09-18 8:57 ` [PATCH v6 09/22] intel_iommu: Stick to system MR for IOMMUFD backed host device when x-fls=on Zhenzhong Duan
2025-09-30 15:04 ` Eric Auger
2025-10-09 10:10 ` Duan, Zhenzhong
2025-10-12 12:51 ` Yi Liu
2025-09-18 8:57 ` [PATCH v6 10/22] intel_iommu: Check for compatibility with IOMMUFD backed device when x-flts=on Zhenzhong Duan
2025-10-12 12:55 ` Yi Liu
2025-10-13 6:48 ` Duan, Zhenzhong
2025-09-18 8:57 ` [PATCH v6 11/22] intel_iommu: Fail passthrough device under PCI bridge if x-flts=on Zhenzhong Duan
2025-09-18 8:57 ` [PATCH v6 12/22] intel_iommu: Handle PASID cache invalidation Zhenzhong Duan
2025-10-12 14:58 ` Yi Liu
2025-10-13 7:37 ` Duan, Zhenzhong
2025-10-13 12:53 ` Yi Liu
2025-09-18 8:57 ` [PATCH v6 13/22] intel_iommu: Reset pasid cache when system level reset Zhenzhong Duan
2025-10-13 10:25 ` Yi Liu
2025-09-18 8:57 ` [PATCH v6 14/22] intel_iommu: Add some macros and inline functions Zhenzhong Duan
2025-10-13 10:25 ` Yi Liu
2025-09-18 8:57 ` [PATCH v6 15/22] intel_iommu: Bind/unbind guest page table to host Zhenzhong Duan
2025-09-18 8:57 ` [PATCH v6 16/22] intel_iommu: Propagate PASID-based iotlb invalidation " Zhenzhong Duan
2025-09-18 8:57 ` [PATCH v6 17/22] intel_iommu: Replay all pasid bindings when either SRTP or TE bit is changed Zhenzhong Duan
2025-09-18 8:57 ` Zhenzhong Duan [this message]
2025-09-23 19:45 ` [PATCH v6 18/22] iommufd: Introduce a helper function to extract vendor capabilities Nicolin Chen
2025-09-24 8:05 ` Duan, Zhenzhong
2025-09-24 8:27 ` Nicolin Chen
2025-09-26 2:54 ` Duan, Zhenzhong
2025-09-18 8:57 ` [PATCH v6 19/22] vfio: Add a new element bypass_ro in VFIOContainerBase Zhenzhong Duan
2025-09-26 12:25 ` Cédric Le Goater
2025-09-18 8:57 ` [PATCH v6 20/22] Workaround for ERRATA_772415_SPR17 Zhenzhong Duan
2025-09-18 8:58 ` [PATCH v6 21/22] intel_iommu: Enable host device when x-flts=on in scalable mode Zhenzhong Duan
2025-09-18 8:58 ` [PATCH v6 22/22] docs/devel: Add IOMMUFD nesting documentation Zhenzhong Duan
2025-09-18 10:00 ` Cédric Le Goater
2025-09-19 2:17 ` Duan, Zhenzhong
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=20250918085803.796942-19-zhenzhong.duan@intel.com \
--to=zhenzhong.duan@intel.com \
--cc=alex.williamson@redhat.com \
--cc=chao.p.peng@intel.com \
--cc=clement.mathieu--drif@eviden.com \
--cc=clg@redhat.com \
--cc=ddutile@redhat.com \
--cc=eric.auger@redhat.com \
--cc=jasowang@redhat.com \
--cc=jgg@nvidia.com \
--cc=joao.m.martins@oracle.com \
--cc=kevin.tian@intel.com \
--cc=mst@redhat.com \
--cc=nicolinc@nvidia.com \
--cc=peterx@redhat.com \
--cc=qemu-devel@nongnu.org \
--cc=skolothumtho@nvidia.com \
--cc=yi.l.liu@intel.com \
/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).