From: Zhenzhong Duan <zhenzhong.duan@intel.com>
To: qemu-devel@nongnu.org
Cc: alex@shazbot.org, clg@redhat.com, eric.auger@redhat.com,
mst@redhat.com, jasowang@redhat.com, jgg@nvidia.com,
nicolinc@nvidia.com, skolothumtho@nvidia.com,
joao.m.martins@oracle.com, clement.mathieu--drif@bull.com,
kevin.tian@intel.com, yi.l.liu@intel.com, xudong.hao@intel.com,
Zhenzhong Duan <zhenzhong.duan@intel.com>
Subject: [PATCH v2 11/14] intel_iommu_accel: Support pasid binding/unbinding and PIOTLB flushing
Date: Thu, 26 Mar 2026 05:11:25 -0400 [thread overview]
Message-ID: <20260326091130.321483-12-zhenzhong.duan@intel.com> (raw)
In-Reply-To: <20260326091130.321483-1-zhenzhong.duan@intel.com>
We just switched to use VTDAccelPASIDCacheEntry to cache pasid entry of
passthrough device, also need to switch the binding/unbinding and PIOTLB
flushing functions to use the same structure.
After the switching, we could remove accel related code from
vtd_pasid_cache_[reset/sync]_locked() to make intel_iommu.c cleaner.
The VTDAddressSpace of PASID_0 is still useful as VTD supports a legacy
mode which needs shadow page table instead of nested page table.
Signed-off-by: Zhenzhong Duan <zhenzhong.duan@intel.com>
---
hw/i386/intel_iommu_accel.h | 2 +-
include/hw/i386/intel_iommu.h | 2 -
hw/i386/intel_iommu.c | 17 +----
hw/i386/intel_iommu_accel.c | 125 +++++++++++++++++-----------------
4 files changed, 64 insertions(+), 82 deletions(-)
diff --git a/hw/i386/intel_iommu_accel.h b/hw/i386/intel_iommu_accel.h
index 1fb7ca0af6..c72856a8ff 100644
--- a/hw/i386/intel_iommu_accel.h
+++ b/hw/i386/intel_iommu_accel.h
@@ -16,6 +16,7 @@ typedef struct VTDAccelPASIDCacheEntry {
VTDHostIOMMUDevice *vtd_hiod;
VTDPASIDEntry pasid_entry;
uint32_t pasid;
+ uint32_t fs_hwpt_id;
QLIST_ENTRY(VTDAccelPASIDCacheEntry) next;
} VTDAccelPASIDCacheEntry;
@@ -23,7 +24,6 @@ typedef struct VTDAccelPASIDCacheEntry {
bool vtd_check_hiod_accel(IntelIOMMUState *s, VTDHostIOMMUDevice *vtd_hiod,
Error **errp);
VTDHostIOMMUDevice *vtd_find_hiod_iommufd(VTDAddressSpace *as);
-bool vtd_propagate_guest_pasid(VTDAddressSpace *vtd_as, Error **errp);
void vtd_flush_host_piotlb_all_locked(IntelIOMMUState *s, uint16_t domain_id,
uint32_t pasid, hwaddr addr,
uint64_t npages, bool ih);
diff --git a/include/hw/i386/intel_iommu.h b/include/hw/i386/intel_iommu.h
index 95c76015e4..1842ba5840 100644
--- a/include/hw/i386/intel_iommu.h
+++ b/include/hw/i386/intel_iommu.h
@@ -154,8 +154,6 @@ struct VTDAddressSpace {
* with the guest IOMMU pgtables for a device.
*/
IOVATree *iova_tree;
-
- uint32_t fs_hwpt_id;
};
struct VTDIOTLBEntry {
diff --git a/hw/i386/intel_iommu.c b/hw/i386/intel_iommu.c
index b022f3cb9e..f53642a611 100644
--- a/hw/i386/intel_iommu.c
+++ b/hw/i386/intel_iommu.c
@@ -86,8 +86,6 @@ static void vtd_pasid_cache_reset_locked(IntelIOMMUState *s)
VTDPASIDCacheEntry *pc_entry = &vtd_as->pasid_cache_entry;
if (pc_entry->valid) {
pc_entry->valid = false;
- /* It's fatal to get failure during reset */
- vtd_propagate_guest_pasid(vtd_as, &error_fatal);
}
}
}
@@ -3126,8 +3124,6 @@ static void vtd_pasid_cache_sync_locked(gpointer key, gpointer value,
VTDPASIDEntry pe;
IOMMUNotifier *n;
uint16_t did;
- const char *err_prefix = "Attaching to HWPT failed: ";
- Error *local_err = NULL;
if (vtd_dev_get_pe_from_pasid(vtd_as, &pe)) {
if (!pc_entry->valid) {
@@ -3148,9 +3144,6 @@ static void vtd_pasid_cache_sync_locked(gpointer key, gpointer value,
vtd_address_space_unmap(vtd_as, n);
}
vtd_switch_address_space(vtd_as);
-
- err_prefix = "Detaching from HWPT failed: ";
- goto do_bind_unbind;
}
/*
@@ -3178,20 +3171,12 @@ static void vtd_pasid_cache_sync_locked(gpointer key, gpointer value,
if (!pc_entry->valid) {
pc_entry->pasid_entry = pe;
pc_entry->valid = true;
- } else if (vtd_pasid_entry_compare(&pe, &pc_entry->pasid_entry)) {
- err_prefix = "Replacing HWPT attachment failed: ";
- } else {
+ } else if (!vtd_pasid_entry_compare(&pe, &pc_entry->pasid_entry)) {
return;
}
vtd_switch_address_space(vtd_as);
vtd_address_space_sync(vtd_as);
-
-do_bind_unbind:
- /* TODO: Fault event injection into guest, report error to QEMU for now */
- if (!vtd_propagate_guest_pasid(vtd_as, &local_err)) {
- error_reportf_err(local_err, "%s", err_prefix);
- }
}
static void vtd_pasid_cache_sync(IntelIOMMUState *s, VTDPASIDCacheInfo *pc_info)
diff --git a/hw/i386/intel_iommu_accel.c b/hw/i386/intel_iommu_accel.c
index e9e67eb1a0..26543489fb 100644
--- a/hw/i386/intel_iommu_accel.c
+++ b/hw/i386/intel_iommu_accel.c
@@ -111,23 +111,24 @@ static bool vtd_create_fs_hwpt(VTDHostIOMMUDevice *vtd_hiod,
}
static void vtd_destroy_old_fs_hwpt(VTDHostIOMMUDevice *vtd_hiod,
- VTDAddressSpace *vtd_as)
+ VTDAccelPASIDCacheEntry *vtd_pce)
{
HostIOMMUDeviceIOMMUFD *idev = HOST_IOMMU_DEVICE_IOMMUFD(vtd_hiod->hiod);
- if (!vtd_as->fs_hwpt_id) {
+ if (!vtd_pce->fs_hwpt_id) {
return;
}
- iommufd_backend_free_id(idev->iommufd, vtd_as->fs_hwpt_id);
- vtd_as->fs_hwpt_id = 0;
+ iommufd_backend_free_id(idev->iommufd, vtd_pce->fs_hwpt_id);
+ vtd_pce->fs_hwpt_id = 0;
}
-static bool vtd_device_attach_iommufd(VTDHostIOMMUDevice *vtd_hiod,
- VTDAddressSpace *vtd_as, Error **errp)
+static bool vtd_device_attach_iommufd(VTDAccelPASIDCacheEntry *vtd_pce,
+ Error **errp)
{
+ VTDHostIOMMUDevice *vtd_hiod = vtd_pce->vtd_hiod;
HostIOMMUDeviceIOMMUFD *idev = HOST_IOMMU_DEVICE_IOMMUFD(vtd_hiod->hiod);
- VTDPASIDEntry *pe = &vtd_as->pasid_cache_entry.pasid_entry;
- uint32_t hwpt_id = idev->hwpt_id;
+ VTDPASIDEntry *pe = &vtd_pce->pasid_entry;
+ uint32_t hwpt_id = idev->hwpt_id, pasid = vtd_pce->pasid;
bool ret;
/*
@@ -147,14 +148,13 @@ static bool vtd_device_attach_iommufd(VTDHostIOMMUDevice *vtd_hiod,
}
}
- ret = host_iommu_device_iommufd_attach_hwpt(idev, IOMMU_NO_PASID, hwpt_id,
- errp);
- trace_vtd_device_attach_hwpt(idev->devid, vtd_as->pasid, hwpt_id, ret);
+ ret = host_iommu_device_iommufd_attach_hwpt(idev, pasid, hwpt_id, errp);
+ trace_vtd_device_attach_hwpt(idev->devid, pasid, hwpt_id, ret);
if (ret) {
/* Destroy old fs_hwpt if it's a replacement */
- vtd_destroy_old_fs_hwpt(vtd_hiod, vtd_as);
+ vtd_destroy_old_fs_hwpt(vtd_hiod, vtd_pce);
if (vtd_pe_pgtt_is_fst(pe)) {
- vtd_as->fs_hwpt_id = hwpt_id;
+ vtd_pce->fs_hwpt_id = hwpt_id;
}
} else if (vtd_pe_pgtt_is_fst(pe)) {
iommufd_backend_free_id(idev->iommufd, hwpt_id);
@@ -163,16 +163,17 @@ static bool vtd_device_attach_iommufd(VTDHostIOMMUDevice *vtd_hiod,
return ret;
}
-static bool vtd_device_detach_iommufd(VTDHostIOMMUDevice *vtd_hiod,
- VTDAddressSpace *vtd_as, Error **errp)
+static bool vtd_device_detach_iommufd(VTDAccelPASIDCacheEntry *vtd_pce,
+ Error **errp)
{
+ VTDHostIOMMUDevice *vtd_hiod = vtd_pce->vtd_hiod;
HostIOMMUDeviceIOMMUFD *idev = HOST_IOMMU_DEVICE_IOMMUFD(vtd_hiod->hiod);
- IntelIOMMUState *s = vtd_as->iommu_state;
- uint32_t pasid = vtd_as->pasid;
+ IntelIOMMUState *s = vtd_hiod->iommu_state;
+ uint32_t pasid = vtd_pce->pasid;
bool ret;
- if (s->dmar_enabled && s->root_scalable) {
- ret = host_iommu_device_iommufd_detach_hwpt(idev, IOMMU_NO_PASID, errp);
+ if (pasid != IOMMU_NO_PASID || (s->dmar_enabled && s->root_scalable)) {
+ ret = host_iommu_device_iommufd_detach_hwpt(idev, pasid, errp);
trace_vtd_device_detach_hwpt(idev->devid, pasid, ret);
} else {
/*
@@ -180,72 +181,47 @@ static bool vtd_device_detach_iommufd(VTDHostIOMMUDevice *vtd_hiod,
* we fallback to the default HWPT which contains shadow page table.
* So guest DMA could still work.
*/
- ret = host_iommu_device_iommufd_attach_hwpt(idev, IOMMU_NO_PASID,
+ ret = host_iommu_device_iommufd_attach_hwpt(idev, pasid,
idev->hwpt_id, errp);
trace_vtd_device_reattach_def_hwpt(idev->devid, pasid, idev->hwpt_id,
ret);
}
if (ret) {
- vtd_destroy_old_fs_hwpt(vtd_hiod, vtd_as);
+ vtd_destroy_old_fs_hwpt(vtd_hiod, vtd_pce);
}
return ret;
}
-bool vtd_propagate_guest_pasid(VTDAddressSpace *vtd_as, Error **errp)
-{
- VTDPASIDCacheEntry *pc_entry = &vtd_as->pasid_cache_entry;
- VTDHostIOMMUDevice *vtd_hiod = vtd_find_hiod_iommufd(vtd_as);
-
- /* Ignore emulated device or legacy VFIO backed device */
- if (!vtd_as->iommu_state->fsts || !vtd_hiod) {
- return true;
- }
-
- if (pc_entry->valid) {
- return vtd_device_attach_iommufd(vtd_hiod, vtd_as, errp);
- }
-
- return vtd_device_detach_iommufd(vtd_hiod, vtd_as, errp);
-}
-
/*
- * This function is a loop function for the s->vtd_address_spaces
- * list with VTDPIOTLBInvInfo as execution filter. It propagates
- * the piotlb invalidation to host.
+ * This function is a loop function for the s->vtd_host_iommu_dev
+ * and vtd_hiod->pasid_cache_list lists with VTDPIOTLBInvInfo as
+ * execution filter. It propagates the piotlb invalidation to host.
*/
-static void vtd_flush_host_piotlb_locked(gpointer key, gpointer value,
- gpointer user_data)
+static void vtd_flush_host_piotlb(VTDAccelPASIDCacheEntry *vtd_pce,
+ VTDPIOTLBInvInfo *piotlb_info)
{
- VTDPIOTLBInvInfo *piotlb_info = user_data;
- VTDAddressSpace *vtd_as = value;
- VTDHostIOMMUDevice *vtd_hiod = vtd_find_hiod_iommufd(vtd_as);
- VTDPASIDCacheEntry *pc_entry = &vtd_as->pasid_cache_entry;
+ VTDHostIOMMUDevice *vtd_hiod = vtd_pce->vtd_hiod;
+ VTDPASIDEntry *pe = &vtd_pce->pasid_entry;
uint16_t did;
- if (!vtd_hiod) {
- return;
- }
-
- assert(vtd_as->pasid == PCI_NO_PASID);
-
/* Nothing to do if there is no first stage HWPT attached */
- if (!pc_entry->valid ||
- !vtd_pe_pgtt_is_fst(&pc_entry->pasid_entry)) {
+ if (!vtd_pe_pgtt_is_fst(pe)) {
return;
}
- did = VTD_SM_PASID_ENTRY_DID(&pc_entry->pasid_entry);
+ did = VTD_SM_PASID_ENTRY_DID(pe);
- if (piotlb_info->domain_id == did && piotlb_info->pasid == PASID_0) {
+ if (piotlb_info->domain_id == did && piotlb_info->pasid == vtd_pce->pasid) {
HostIOMMUDeviceIOMMUFD *idev =
HOST_IOMMU_DEVICE_IOMMUFD(vtd_hiod->hiod);
uint32_t entry_num = 1; /* Only implement one request for simplicity */
Error *local_err = NULL;
struct iommu_hwpt_vtd_s1_invalidate *cache = piotlb_info->inv_data;
- if (!iommufd_backend_invalidate_cache(idev->iommufd, vtd_as->fs_hwpt_id,
+ if (!iommufd_backend_invalidate_cache(idev->iommufd,
+ vtd_pce->fs_hwpt_id,
IOMMU_HWPT_INVALIDATE_DATA_VTD_S1,
sizeof(*cache), &entry_num, cache,
&local_err)) {
@@ -261,6 +237,8 @@ void vtd_flush_host_piotlb_all_locked(IntelIOMMUState *s, uint16_t domain_id,
{
struct iommu_hwpt_vtd_s1_invalidate cache_info = { 0 };
VTDPIOTLBInvInfo piotlb_info;
+ VTDHostIOMMUDevice *vtd_hiod;
+ GHashTableIter as_it;
cache_info.addr = addr;
cache_info.npages = npages;
@@ -271,12 +249,19 @@ void vtd_flush_host_piotlb_all_locked(IntelIOMMUState *s, uint16_t domain_id,
piotlb_info.inv_data = &cache_info;
/*
- * Go through each vtd_as instance in s->vtd_address_spaces, find out
- * affected host devices which need host piotlb invalidation. Piotlb
- * invalidation should check pasid cache per architecture point of view.
+ * Go through each vtd_pce in vtd_hiod->pasid_cache_list for each host
+ * device, find out affected host device pasid which need host piotlb
+ * invalidation. Piotlb invalidation should check pasid cache per
+ * architecture point of view.
*/
- g_hash_table_foreach(s->vtd_address_spaces,
- vtd_flush_host_piotlb_locked, &piotlb_info);
+ g_hash_table_iter_init(&as_it, s->vtd_host_iommu_dev);
+ while (g_hash_table_iter_next(&as_it, NULL, (void **)&vtd_hiod)) {
+ VTDAccelPASIDCacheEntry *vtd_pce;
+
+ QLIST_FOREACH(vtd_pce, &vtd_hiod->pasid_cache_list, next) {
+ vtd_flush_host_piotlb(vtd_pce, &piotlb_info);
+ }
+ }
}
static void vtd_pasid_cache_invalidate_one(VTDAccelPASIDCacheEntry *vtd_pce,
@@ -284,6 +269,7 @@ static void vtd_pasid_cache_invalidate_one(VTDAccelPASIDCacheEntry *vtd_pce,
{
VTDPASIDEntry pe;
uint16_t did;
+ Error *local_err = NULL;
/*
* VTD_INV_DESC_PASIDC_G_DSI and VTD_INV_DESC_PASIDC_G_PASID_SI require
@@ -309,6 +295,9 @@ static void vtd_pasid_cache_invalidate_one(VTDAccelPASIDCacheEntry *vtd_pce,
* to be either all-zero or non-present. Either case means existing
* pasid cache should be invalidated.
*/
+ if (!vtd_device_detach_iommufd(vtd_pce, &local_err)) {
+ error_reportf_err(local_err, "%s", "Detaching from HWPT failed: ");
+ }
QLIST_REMOVE(vtd_pce, next);
g_free(vtd_pce);
@@ -333,11 +322,17 @@ static void vtd_accel_fill_pc(VTDHostIOMMUDevice *vtd_hiod, uint32_t pasid,
VTDPASIDEntry *pe)
{
VTDAccelPASIDCacheEntry *vtd_pce;
+ Error *local_err = NULL;
QLIST_FOREACH(vtd_pce, &vtd_hiod->pasid_cache_list, next) {
if (vtd_pce->pasid == pasid) {
if (vtd_pasid_entry_compare(pe, &vtd_pce->pasid_entry)) {
vtd_pce->pasid_entry = *pe;
+
+ if (!vtd_device_attach_iommufd(vtd_pce, &local_err)) {
+ error_reportf_err(local_err, "%s",
+ "Replacing HWPT attachment failed: ");
+ }
}
return;
}
@@ -348,6 +343,10 @@ static void vtd_accel_fill_pc(VTDHostIOMMUDevice *vtd_hiod, uint32_t pasid,
vtd_pce->pasid = pasid;
vtd_pce->pasid_entry = *pe;
QLIST_INSERT_HEAD(&vtd_hiod->pasid_cache_list, vtd_pce, next);
+
+ if (!vtd_device_attach_iommufd(vtd_pce, &local_err)) {
+ error_reportf_err(local_err, "%s", "Attaching to HWPT failed: ");
+ }
}
/*
--
2.47.3
next prev parent reply other threads:[~2026-03-26 9:13 UTC|newest]
Thread overview: 15+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-03-26 9:11 [PATCH v2 00/14] intel_iommu: Enable PASID support for passthrough device Zhenzhong Duan
2026-03-26 9:11 ` [PATCH v2 01/14] vfio/iommufd: Extend attach/detach_hwpt callback implementations with pasid Zhenzhong Duan
2026-03-26 9:11 ` [PATCH v2 02/14] iommufd: Extend attach/detach_hwpt callbacks to support pasid Zhenzhong Duan
2026-03-26 9:11 ` [PATCH v2 03/14] vfio/iommufd: Create nesting parent hwpt with IOMMU_HWPT_ALLOC_PASID flag Zhenzhong Duan
2026-03-26 9:11 ` [PATCH v2 04/14] intel_iommu: Create the nested " Zhenzhong Duan
2026-03-26 9:11 ` [PATCH v2 05/14] intel_iommu: Change pasid property from bool to uint8 Zhenzhong Duan
2026-03-26 9:11 ` [PATCH v2 06/14] intel_iommu: Export some functions Zhenzhong Duan
2026-03-26 9:11 ` [PATCH v2 07/14] intel_iommu_accel: Handle PASID entry addition for pc_inv_dsc request Zhenzhong Duan
2026-03-26 9:11 ` [PATCH v2 08/14] intel_iommu_accel: Handle PASID entry removal " Zhenzhong Duan
2026-03-26 9:11 ` [PATCH v2 09/14] intel_iommu_accel: Bypass PASID entry addition for just deleted entry Zhenzhong Duan
2026-03-26 9:11 ` [PATCH v2 10/14] intel_iommu_accel: Handle PASID entry removal for system reset Zhenzhong Duan
2026-03-26 9:11 ` Zhenzhong Duan [this message]
2026-03-26 9:11 ` [PATCH v2 12/14] intel_iommu_accel: drop _lock suffix in vtd_flush_host_piotlb_all_locked() Zhenzhong Duan
2026-03-26 9:11 ` [PATCH v2 13/14] intel_iommu_accel: Add pasid bits size check Zhenzhong Duan
2026-03-26 9:11 ` [PATCH v2 14/14] intel_iommu: Expose flag VIOMMU_FLAG_PASID_SUPPORTED when configured Zhenzhong Duan
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=20260326091130.321483-12-zhenzhong.duan@intel.com \
--to=zhenzhong.duan@intel.com \
--cc=alex@shazbot.org \
--cc=clement.mathieu--drif@bull.com \
--cc=clg@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=qemu-devel@nongnu.org \
--cc=skolothumtho@nvidia.com \
--cc=xudong.hao@intel.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