Re: [PATCH v7 9/9] iommu/vt-d: Add iotlb flush for nested domain

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

 



On 2023/12/26 12:51, Yi Liu wrote:
On 2023/12/22 14:57, Tian, Kevin wrote:
From: Liu, Yi L <yi.l.liu@xxxxxxxxx>
Sent: Thursday, December 21, 2023 11:40 PM

+
+static void intel_nested_flush_cache(struct dmar_domain *domain, u64
addr,
+                     unsigned long npages, u32 *error)
+{
+    struct iommu_domain_info *info;
+    unsigned long i;
+    unsigned mask;
+    u32 fault = 0;
+
+    if (npages == U64_MAX)
+        mask = 64 - VTD_PAGE_SHIFT;
+    else
+        mask = ilog2(__roundup_pow_of_two(npages));
+
+    xa_for_each(&domain->iommu_array, i, info) {
+        nested_flush_pasid_iotlb(info->iommu, domain, addr,
npages, 0);

so IOMMU_VTD_INV_FLAGS_LEAF is defined but ignored?

yeah... it is. It is named as ih in the driver code. But it appears only
the below code is set ih. When calling iommu_flush_iotlb_psi(), the 5th
parameter (ih) may be true.

static int intel_iommu_memory_notifier(struct notifier_block *nb,
                        unsigned long val, void *v)
{
     struct memory_notify *mhp = v;
     unsigned long start_vpfn = mm_to_dma_pfn(mhp->start_pfn);
     unsigned long last_vpfn = mm_to_dma_pfn(mhp->start_pfn +
             mhp->nr_pages - 1);

     switch (val) {
     case MEM_GOING_ONLINE:
         if (iommu_domain_identity_map(si_domain,
                           start_vpfn, last_vpfn)) {
             pr_warn("Failed to build identity map for [%lx-%lx]\n",
                 start_vpfn, last_vpfn);
             return NOTIFY_BAD;
         }
         break;

     case MEM_OFFLINE:
     case MEM_CANCEL_ONLINE:
         {
             struct dmar_drhd_unit *drhd;
             struct intel_iommu *iommu;
             LIST_HEAD(freelist);

             domain_unmap(si_domain, start_vpfn, last_vpfn, &freelist);

             rcu_read_lock();
             for_each_active_iommu(iommu, drhd)
                 iommu_flush_iotlb_psi(iommu, si_domain,
                     start_vpfn, mhp->nr_pages,
                     list_empty(&freelist), 0);
             rcu_read_unlock();
             put_pages_list(&freelist);
         }
         break;
     }

     return NOTIFY_OK;
}

I passed this flag to the intel_nested_flush_cache() now as the
helper accepts an ih parameter.

--
Regards,
Yi Liu




[Index of Archives]     [Linux Wireless]     [Linux Kernel]     [ATH6KL]     [Linux Bluetooth]     [Linux Netdev]     [Kernel Newbies]     [Share Photos]     [IDE]     [Security]     [Git]     [Netfilter]     [Bugtraq]     [Yosemite News]     [MIPS Linux]     [ARM Linux]     [Linux Security]     [Linux RAID]     [Linux ATA RAID]     [Samba]     [Device Mapper]

  Powered by Linux