qemu-devel.nongnu.org archive mirror
 help / color / mirror / Atom feed
From: Eric Auger <eric.auger@redhat.com>
To: Zhenzhong Duan <zhenzhong.duan@intel.com>, qemu-devel@nongnu.org
Cc: alex.williamson@redhat.com, clg@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,
	Yi Sun <yi.y.sun@linux.intel.com>
Subject: Re: [PATCH v7 14/23] intel_iommu: Propagate PASID-based iotlb invalidation to host
Date: Mon, 3 Nov 2025 11:04:23 +0100	[thread overview]
Message-ID: <39bd639f-4b67-4e90-bed6-299cd7315a87@redhat.com> (raw)
In-Reply-To: <20251024084349.102322-15-zhenzhong.duan@intel.com>

Hi Zhenzhong,

On 10/24/25 10:43 AM, Zhenzhong Duan wrote:
> From: Yi Liu <yi.l.liu@intel.com>
>
> This traps the guest PASID-based iotlb invalidation request and propagate it
> to host.
>
> Intel VT-d 3.0 supports nested translation in PASID granularity. Guest SVA
> support could be implemented by configuring nested translation on specific
> pasid. This is also known as dual stage DMA translation.
>
> Under such configuration, guest owns the GVA->GPA translation which is
> configured as first stage page table on host side for a specific pasid, and
> host owns GPA->HPA translation. As guest owns first stage translation table,
> piotlb invalidation should be propagated to host since host IOMMU will cache
> first level page table related mappings during DMA address translation.
>
> Signed-off-by: Yi Liu <yi.l.liu@intel.com>
> Signed-off-by: Yi Sun <yi.y.sun@linux.intel.com>
> Signed-off-by: Zhenzhong Duan <zhenzhong.duan@intel.com>
> ---
>  hw/i386/intel_iommu_internal.h |  6 +++
>  hw/i386/intel_iommu.c          | 87 ++++++++++++++++++++++++++++++++--
>  2 files changed, 90 insertions(+), 3 deletions(-)
>
> diff --git a/hw/i386/intel_iommu_internal.h b/hw/i386/intel_iommu_internal.h
> index df80af839d..97b48544d2 100644
> --- a/hw/i386/intel_iommu_internal.h
> +++ b/hw/i386/intel_iommu_internal.h
> @@ -621,6 +621,12 @@ typedef struct VTDPASIDCacheInfo {
>      uint32_t pasid;
>  } VTDPASIDCacheInfo;
>  
> +typedef struct VTDPIOTLBInvInfo {
> +    uint16_t domain_id;
> +    uint32_t pasid;
> +    struct iommu_hwpt_vtd_s1_invalidate *inv_data;
> +} VTDPIOTLBInvInfo;
> +
>  /* PASID Table Related Definitions */
>  #define VTD_PASID_DIR_BASE_ADDR_MASK  (~0xfffULL)
>  #define VTD_PASID_TABLE_BASE_ADDR_MASK (~0xfffULL)
> diff --git a/hw/i386/intel_iommu.c b/hw/i386/intel_iommu.c
> index 3789a36147..ef6477de53 100644
> --- a/hw/i386/intel_iommu.c
> +++ b/hw/i386/intel_iommu.c
> @@ -2504,11 +2504,88 @@ static int vtd_bind_guest_pasid(VTDAddressSpace *vtd_as, Error **errp)
>  
>      return ret;
>  }
> +
> +/*
> + * 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.
> + */
> +static void vtd_flush_host_piotlb_locked(gpointer key, gpointer value,
> +                                         gpointer user_data)
> +{
> +    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;
> +    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)) {
> +        return;
> +    }
> +
> +    did = VTD_SM_PASID_ENTRY_DID(&pc_entry->pasid_entry);
> +
> +    if (piotlb_info->domain_id == did && piotlb_info->pasid == PASID_0) {
> +        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,
> +                                              IOMMU_HWPT_INVALIDATE_DATA_VTD_S1,
> +                                              sizeof(*cache), &entry_num, cache,
> +                                              &local_err)) {
> +            /* Something wrong in kernel, but trying to continue */
> +            error_report_err(local_err);
> +        }
> +    }
> +}
> +
> +static void
> +vtd_flush_host_piotlb_all_locked(IntelIOMMUState *s,
> +                                 uint16_t domain_id, uint32_t pasid,
> +                                 hwaddr addr, uint64_t npages, bool ih)
> +{
> +    struct iommu_hwpt_vtd_s1_invalidate cache_info = { 0 };
> +    VTDPIOTLBInvInfo piotlb_info;
> +
> +    cache_info.addr = addr;
> +    cache_info.npages = npages;
> +    cache_info.flags = ih ? IOMMU_VTD_INV_FLAGS_LEAF : 0;
> +
> +    piotlb_info.domain_id = domain_id;
> +    piotlb_info.pasid = pasid;
> +    piotlb_info.inv_data = &cache_info;
> +
> +    /*
> +     * Go through each vtd_as instance in s->vtd_address_spaces, find out
> +     * the affected host device which need host piotlb invalidation. Piotlb
the affected host devices? There might be several of them, isn't it?
> +     * 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);
> +}
>  #else
>  static int vtd_bind_guest_pasid(VTDAddressSpace *vtd_as, Error **errp)
>  {
>      return 0;
>  }
> +
> +static void
> +vtd_flush_host_piotlb_all_locked(IntelIOMMUState *s,
> +                                 uint16_t domain_id, uint32_t pasid,
> +                                 hwaddr addr, uint64_t npages, bool ih)
> +{
> +}
>  #endif
>  
>  /* Do a context-cache device-selective invalidation.
> @@ -3155,6 +3232,7 @@ static void vtd_piotlb_pasid_invalidate(IntelIOMMUState *s,
>      vtd_iommu_lock(s);
>      g_hash_table_foreach_remove(s->iotlb, vtd_hash_remove_by_pasid,
>                                  &info);
> +    vtd_flush_host_piotlb_all_locked(s, domain_id, pasid, 0, (uint64_t)-1, 0);
UINT64_MAX

>      vtd_iommu_unlock(s);
>  
>      QLIST_FOREACH(vtd_as, &s->vtd_as_with_notifiers, next) {
> @@ -3174,7 +3252,8 @@ static void vtd_piotlb_pasid_invalidate(IntelIOMMUState *s,
>  }
>  
>  static void vtd_piotlb_page_invalidate(IntelIOMMUState *s, uint16_t domain_id,
> -                                       uint32_t pasid, hwaddr addr, uint8_t am)
> +                                       uint32_t pasid, hwaddr addr, uint8_t am,
> +                                       bool ih)
>  {
>      VTDIOTLBPageInvInfo info;
>  
> @@ -3186,6 +3265,7 @@ static void vtd_piotlb_page_invalidate(IntelIOMMUState *s, uint16_t domain_id,
>      vtd_iommu_lock(s);
>      g_hash_table_foreach_remove(s->iotlb,
>                                  vtd_hash_remove_by_page_piotlb, &info);
> +    vtd_flush_host_piotlb_all_locked(s, domain_id, pasid, addr, 1 << am, ih);
>      vtd_iommu_unlock(s);
>  
>      vtd_iotlb_page_invalidate_notify(s, domain_id, addr, am, pasid);
> @@ -3217,7 +3297,8 @@ static bool vtd_process_piotlb_desc(IntelIOMMUState *s,
>      case VTD_INV_DESC_PIOTLB_PSI_IN_PASID:
>          am = VTD_INV_DESC_PIOTLB_AM(inv_desc->val[1]);
>          addr = (hwaddr) VTD_INV_DESC_PIOTLB_ADDR(inv_desc->val[1]);
> -        vtd_piotlb_page_invalidate(s, domain_id, pasid, addr, am);
it is not obvious we hold the lock here
> +        vtd_piotlb_page_invalidate(s, domain_id, pasid, addr, am,
> +                                   VTD_INV_DESC_PIOTLB_IH(inv_desc->val[1]));
>          break;
>  
>      default:
> @@ -5439,7 +5520,7 @@ static int vtd_pri_perform_implicit_invalidation(VTDAddressSpace *vtd_as,
>      ret = 0;
>      switch (pgtt) {
>      case VTD_SM_PASID_ENTRY_FST:
> -        vtd_piotlb_page_invalidate(s, domain_id, vtd_as->pasid, addr, 0);
> +        vtd_piotlb_page_invalidate(s, domain_id, vtd_as->pasid, addr, 0, 0);
>          break;
>      /* Room for other pgtt values */
>      default:
Thanks

Eric



  reply	other threads:[~2025-11-03 10:05 UTC|newest]

Thread overview: 63+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2025-10-24  8:43 [PATCH v7 00/23] intel_iommu: Enable first stage translation for passthrough device Zhenzhong Duan
2025-10-24  8:43 ` [PATCH v7 01/23] intel_iommu: Rename vtd_ce_get_rid2pasid_entry to vtd_ce_get_pasid_entry Zhenzhong Duan
2025-10-24  8:43 ` [PATCH v7 02/23] intel_iommu: Delete RPS capability related supporting code Zhenzhong Duan
2025-10-31  7:50   ` Eric Auger
2025-10-31  9:49     ` Duan, Zhenzhong
2025-10-24  8:43 ` [PATCH v7 03/23] intel_iommu: Update terminology to match VTD spec Zhenzhong Duan
2025-10-24  8:43 ` [PATCH v7 04/23] hw/pci: Export pci_device_get_iommu_bus_devfn() and return bool Zhenzhong Duan
2025-10-24  8:43 ` [PATCH v7 05/23] hw/pci: Introduce pci_device_get_viommu_flags() Zhenzhong Duan
2025-10-24 17:18   ` Cédric Le Goater
2025-10-28  6:57     ` Duan, Zhenzhong
2025-10-28 15:19       ` Eric Auger
2025-10-24  8:43 ` [PATCH v7 06/23] intel_iommu: Implement get_viommu_flags() callback Zhenzhong Duan
2025-10-24  8:43 ` [PATCH v7 07/23] intel_iommu: Introduce a new structure VTDHostIOMMUDevice Zhenzhong Duan
2025-10-24  8:43 ` [PATCH v7 08/23] vfio/iommufd: Force creating nesting parent HWPT Zhenzhong Duan
2025-10-24 16:23   ` Cédric Le Goater
2025-10-28  6:00     ` Duan, Zhenzhong
2025-10-24  8:43 ` [PATCH v7 09/23] intel_iommu: Stick to system MR for IOMMUFD backed host device when x-flts=on Zhenzhong Duan
2025-10-31  8:09   ` Eric Auger
2025-10-31  9:52     ` Duan, Zhenzhong
2025-11-05  2:45       ` Nicolin Chen
2025-10-24  8:43 ` [PATCH v7 10/23] intel_iommu: Check for compatibility with IOMMUFD backed " Zhenzhong Duan
2025-10-24 17:29   ` Cédric Le Goater
2025-10-29  7:37     ` Duan, Zhenzhong
2025-10-24  8:43 ` [PATCH v7 11/23] intel_iommu: Fail passthrough device under PCI bridge if x-flts=on Zhenzhong Duan
2025-10-24  8:43 ` [PATCH v7 12/23] intel_iommu: Add some macros and inline functions Zhenzhong Duan
2025-10-24 16:39   ` Cédric Le Goater
2025-10-28  6:01     ` Duan, Zhenzhong
2025-11-02 11:15   ` Eric Auger
2025-11-03  3:44     ` Duan, Zhenzhong
2025-11-03  7:23       ` Eric Auger
2025-11-06  4:25         ` Duan, Zhenzhong
2025-10-24  8:43 ` [PATCH v7 13/23] intel_iommu: Bind/unbind guest page table to host Zhenzhong Duan
2025-10-24 17:01   ` Cédric Le Goater
2025-11-03  9:25     ` Eric Auger
2025-10-24 17:33   ` Cédric Le Goater
2025-10-29  9:56     ` Duan, Zhenzhong
2025-11-03  9:37   ` Eric Auger
2025-10-24  8:43 ` [PATCH v7 14/23] intel_iommu: Propagate PASID-based iotlb invalidation " Zhenzhong Duan
2025-11-03 10:04   ` Eric Auger [this message]
2025-10-24  8:43 ` [PATCH v7 15/23] intel_iommu: Replay all pasid bindings when either SRTP or TE bit is changed Zhenzhong Duan
2025-10-24  8:43 ` [PATCH v7 16/23] intel_iommu: Replay pasid bindings after context cache invalidation Zhenzhong Duan
2025-11-03 10:45   ` Eric Auger
2025-10-24  8:43 ` [PATCH v7 17/23] iommufd: Introduce a helper function to extract vendor capabilities Zhenzhong Duan
2025-10-24 16:44   ` Cédric Le Goater
2025-10-28  9:43     ` Duan, Zhenzhong
2025-10-24 17:34   ` Cédric Le Goater
2025-10-28  9:28     ` Duan, Zhenzhong
2025-11-03 12:57   ` Eric Auger
2025-10-24  8:43 ` [PATCH v7 18/23] vfio: Add a new element bypass_ro in VFIOContainer Zhenzhong Duan
2025-11-03 13:01   ` Eric Auger
2025-10-24  8:43 ` [PATCH v7 19/23] Workaround for ERRATA_772415_SPR17 Zhenzhong Duan
2025-10-24 17:36   ` Cédric Le Goater
2025-10-24 17:38   ` Cédric Le Goater
2025-11-03 13:14   ` Eric Auger
2025-10-24  8:43 ` [PATCH v7 20/23] vfio: Bypass readonly region for dirty tracking Zhenzhong Duan
2025-10-24 16:32   ` Cédric Le Goater
2025-10-28  9:47     ` Duan, Zhenzhong
2025-11-03 13:07   ` Eric Auger
2025-10-24  8:43 ` [PATCH v7 21/23] intel_iommu: Add migration support with x-flts=on Zhenzhong Duan
2025-11-03 13:16   ` Eric Auger
2025-10-24  8:43 ` [PATCH v7 22/23] intel_iommu: Enable host device when x-flts=on in scalable mode Zhenzhong Duan
2025-10-24  8:43 ` [PATCH v7 23/23] docs/devel: Add IOMMUFD nesting documentation Zhenzhong Duan
2025-11-03 13:23   ` Eric Auger

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=39bd639f-4b67-4e90-bed6-299cd7315a87@redhat.com \
    --to=eric.auger@redhat.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=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 \
    --cc=yi.y.sun@linux.intel.com \
    --cc=zhenzhong.duan@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).