Re: [PATCH v2 11/19] intel_iommu: Handle PASID entry adding

[Eric Auger <eric.auger@redhat.com>]

Hi Zhenzhong,

On 6/20/25 9:18 AM, Zhenzhong Duan wrote:
> When guest modifies a PASID entry, QEMU will capture the guest pasid selective
> pasid cache invalidation, allocate or remove a VTDAddressSpace instance per the
> invalidation reasons:
>
>     a) a present pasid entry moved to non-present
>     b) a present pasid entry to be a present entry
>     c) a non-present pasid entry moved to present
>
> This handles c).

As you use the replay terminology in the patch, please explain what it
means in that case and how the patch achieve above goal.
>
> 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 |   1 +
>  hw/i386/intel_iommu.c          | 169 ++++++++++++++++++++++++++++++++-
>  2 files changed, 169 insertions(+), 1 deletion(-)
>
> diff --git a/hw/i386/intel_iommu_internal.h b/hw/i386/intel_iommu_internal.h
> index 01c881ed4d..025787b3b9 100644
> --- a/hw/i386/intel_iommu_internal.h
> +++ b/hw/i386/intel_iommu_internal.h
> @@ -558,6 +558,7 @@ typedef struct VTDRootEntry VTDRootEntry;
>  #define VTD_CTX_ENTRY_LEGACY_SIZE     16
>  #define VTD_CTX_ENTRY_SCALABLE_SIZE   32
>  
> +#define VTD_SM_CONTEXT_ENTRY_PDTS(val)      (((val) >> 9) & 0x7)
>  #define VTD_SM_CONTEXT_ENTRY_RID2PASID_MASK 0xfffff
>  #define VTD_SM_CONTEXT_ENTRY_RSVD_VAL0(aw)  (0x1e0ULL | ~VTD_HAW_MASK(aw))
>  #define VTD_SM_CONTEXT_ENTRY_RSVD_VAL1      0xffffffffffe00000ULL
> diff --git a/hw/i386/intel_iommu.c b/hw/i386/intel_iommu.c
> index 1db581d14a..f4273dc640 100644
> --- a/hw/i386/intel_iommu.c
> +++ b/hw/i386/intel_iommu.c
> @@ -826,6 +826,11 @@ static inline bool vtd_pe_type_check(IntelIOMMUState *s, VTDPASIDEntry *pe)
>      }
>  }
>  
> +static inline uint32_t vtd_sm_ce_get_pdt_entry_num(VTDContextEntry *ce)
> +{
> +    return 1U << (VTD_SM_CONTEXT_ENTRY_PDTS(ce->val[0]) + 7);
> +}
> +
>  static inline uint16_t vtd_pe_get_did(VTDPASIDEntry *pe)
>  {
>      return VTD_SM_PASID_ENTRY_DID((pe)->val[1]);
> @@ -3246,6 +3251,159 @@ remove:
>      return true;
>  }
>  
> +static void vtd_sm_pasid_table_walk_one(IntelIOMMUState *s,
> +                                        dma_addr_t pt_base,
> +                                        int start,
> +                                        int end,
> +                                        VTDPASIDCacheInfo *info)
> +{
> +    VTDPASIDEntry pe;
> +    int pasid = start;
> +    int pasid_next;
> +
> +    while (pasid < end) {
> +        pasid_next = pasid + 1;
> +
> +        if (!vtd_get_pe_in_pasid_leaf_table(s, pasid, pt_base, &pe)
> +            && vtd_pe_present(&pe)) {
> +            int bus_n = pci_bus_num(info->bus), devfn = info->devfn;
> +            uint16_t sid = PCI_BUILD_BDF(bus_n, devfn);
> +            VTDAddressSpace *vtd_as;
> +
> +            vtd_iommu_lock(s);
> +            /*
> +             * When indexed by rid2pasid, vtd_as should have been created,
> +             * e.g., by PCI subsystem. For other iommu pasid, we need to
> +             * create vtd_as dynamically. The other iommu pasid is same as
> +             * PCI's pasid, so it's used as input of vtd_find_add_as().
> +             */
> +            vtd_as = vtd_as_from_iommu_pasid_locked(s, sid, pasid);
> +            vtd_iommu_unlock(s);
> +            if (!vtd_as) {
> +                vtd_as = vtd_find_add_as(s, info->bus, devfn, pasid);
> +            }
> +
> +            if ((info->type == VTD_PASID_CACHE_DOMSI ||
> +                 info->type == VTD_PASID_CACHE_PASIDSI) &&
> +                !(info->domain_id == vtd_pe_get_did(&pe))) {
> +                /*
> +                 * VTD_PASID_CACHE_DOMSI and VTD_PASID_CACHE_PASIDSI
> +                 * requires domain ID check. If domain Id check fail,
> +                 * go to next pasid.
> +                 */
> +                pasid = pasid_next;
> +                continue;
> +            }
> +            if (vtd_fill_pe_in_cache(s, vtd_as, &pe)) {
> +                pasid_cache_info_set_error(info);
> +            }
> +        }
> +        pasid = pasid_next;
> +    }
> +}
> +
> +/*
> + * Currently, VT-d scalable mode pasid table is a two level table,
do you mean PASID dir + PASID table? in the positive I would use that
terminology directly.
> + * this function aims to loop a range of PASIDs in a given pasid
aims at looping over a range of PASIDs in a given table?
so what do you call a table here? is a a PASID directory ot a PASID table.
> + * table to identify the pasid config in guest.
> + */
> +static void vtd_sm_pasid_table_walk(IntelIOMMUState *s,
> +                                    dma_addr_t pdt_base,
> +                                    int start,
> +                                    int end,
> +                                    VTDPASIDCacheInfo *info)
> +{
> +    VTDPASIDDirEntry pdire;
> +    int pasid = start;
> +    int pasid_next;
> +    dma_addr_t pt_base;
> +
> +    while (pasid < end) {
> +        pasid_next = ((end - pasid) > VTD_PASID_TBL_ENTRY_NUM) ?
> +                      (pasid + VTD_PASID_TBL_ENTRY_NUM) : end;
> +        if (!vtd_get_pdire_from_pdir_table(pdt_base, pasid, &pdire)
> +            && vtd_pdire_present(&pdire)) {
> +            pt_base = pdire.val & VTD_PASID_TABLE_BASE_ADDR_MASK;
> +            vtd_sm_pasid_table_walk_one(s, pt_base, pasid, pasid_next, info);
> +        }
> +        pasid = pasid_next;
> +    }
> +}
> +
> +static void vtd_replay_pasid_bind_for_dev(IntelIOMMUState *s,
> +                                          int start, int end,
> +                                          VTDPASIDCacheInfo *info)
> +{
> +    VTDContextEntry ce;
> +
> +    if (!vtd_dev_to_context_entry(s, pci_bus_num(info->bus), info->devfn,
> +                                  &ce)) {
> +        uint32_t max_pasid;
> +
> +        max_pasid = vtd_sm_ce_get_pdt_entry_num(&ce) * VTD_PASID_TBL_ENTRY_NUM;
> +        if (end > max_pasid) {
> +            end = max_pasid;
> +        }
> +        vtd_sm_pasid_table_walk(s,
> +                                VTD_CE_GET_PASID_DIR_TABLE(&ce),
> +                                start,
> +                                end,
> +                                info);
> +    }
> +}
> +
> +/*
> + * This function replay the guest pasid bindings to hosts by
replays, host
> + * walking the guest PASID table. This ensures host will have
> + * latest guest pasid bindings.
> + */
> +static void vtd_replay_guest_pasid_bindings(IntelIOMMUState *s,
> +                                            VTDPASIDCacheInfo *pc_info)
> +{
> +    VTDHostIOMMUDevice *vtd_hiod;
> +    int start = 0, end = 1; /* only rid2pasid is supported */
> +    VTDPASIDCacheInfo walk_info;
> +    GHashTableIter as_it;
> +
> +    switch (pc_info->type) {
> +    case VTD_PASID_CACHE_PASIDSI:
> +        start = pc_info->pasid;
> +        end = pc_info->pasid + 1;
> +        /*
> +         * PASID selective invalidation is within domain,
> +         * thus fall through.
this is still not totally clean to me. For domsi I would have expected a
different setting of start and end?
> +         */
> +    case VTD_PASID_CACHE_DOMSI:
fall though clause here and above?
> +    case VTD_PASID_CACHE_GLOBAL_INV:
> +        /* loop all assigned devices */
> +        break;
> +    default:
> +        error_report("invalid pc_info->type for replay");
> +        abort();
> +    }
> +
> +    /*
> +     * In this replay, only needs to care about the devices which
one only needs to care
> +     * are backed by host IOMMU. For such devices, their vtd_hiod
Those devices have a corresponding vtd_hiod in s->vtd_host_iommu_dev
> +     * instances are in the s->vtd_host_iommu_dev. For devices which
> +     * are not backed by host IOMMU, it is not necessary to replay
> +     * the bindings since their cache could be re-created in the future
> +     * DMA address translation. Access to vtd_host_iommu_dev is already
> +     * protected by BQL, so no iommu lock needed here.
> +     */
> +    walk_info = *pc_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)) {
> +        /* bus|devfn fields are not identical with pc_info */
Can you clarify?
> +        walk_info.bus = vtd_hiod->bus;
> +        walk_info.devfn = vtd_hiod->devfn;
> +        vtd_replay_pasid_bind_for_dev(s, start, end, &walk_info);
> +    }
> +    if (walk_info.error_happened) {
> +        pasid_cache_info_set_error(pc_info);
> +    }
> +}
> +
>  /*
>   * This function syncs the pasid bindings between guest and host.
>   * It includes updating the pasid cache in vIOMMU and updating the
> @@ -3301,7 +3459,16 @@ static void vtd_pasid_cache_sync(IntelIOMMUState *s,
>                                  pc_info);
>      vtd_iommu_unlock(s);
>  
> -    /* TODO: Step 2: loop all the existing vtd_hiod instances for pasid bind. */
> +    /*
> +     * Step 2: loop all the existing vtd_hiod instances for pasid bind.
> +     * Ideally, needs to loop all devices to find if there is any new
> +     * PASID binding regards to the PASID cache invalidation request.
> +     * But it is enough to loop the devices which are backed by host
> +     * IOMMU. For devices backed by vIOMMU (a.k.a emulated devices),
> +     * if new PASID happened on them, their vtd_as instance could
> +     * be created during future vIOMMU DMA translation.
the above comment is somehow redundant with the previous one
> +     */
> +    vtd_replay_guest_pasid_bindings(s, pc_info);
>  }
>  
>  static bool vtd_process_pasid_desc(IntelIOMMUState *s,
Thanks

Eric