From: Lu Baolu Date: Mon, 22 Jun 2020 23:13:44 +0000 (+0800) Subject: iommu/vt-d: Update scalable mode paging structure coherency X-Git-Tag: v5.4.50~83 X-Git-Url: http://review.tizen.org/git/?a=commitdiff_plain;h=33104571648b400ec211025f57c2d10b5ccc04a5;p=platform%2Fkernel%2Flinux-rpi.git iommu/vt-d: Update scalable mode paging structure coherency [ Upstream commit 04c00956ee3cd138fd38560a91452a804a8c5550 ] The Scalable-mode Page-walk Coherency (SMPWC) field in the VT-d extended capability register indicates the hardware coherency behavior on paging structures accessed through the pasid table entry. This is ignored in current code and using ECAP.C instead which is only valid in legacy mode. Fix this so that paging structure updates could be manually flushed from the cache line if hardware page walking is not snooped. Fixes: 765b6a98c1de3 ("iommu/vt-d: Enumerate the scalable mode capability") Signed-off-by: Lu Baolu Cc: Ashok Raj Cc: Kevin Tian Cc: Jacob Pan Link: https://lore.kernel.org/r/20200622231345.29722-6-baolu.lu@linux.intel.com Signed-off-by: Joerg Roedel Signed-off-by: Sasha Levin --- diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c index 773ac2b..6366b5f 100644 --- a/drivers/iommu/intel-iommu.c +++ b/drivers/iommu/intel-iommu.c @@ -611,6 +611,12 @@ struct intel_iommu *domain_get_iommu(struct dmar_domain *domain) return g_iommus[iommu_id]; } +static inline bool iommu_paging_structure_coherency(struct intel_iommu *iommu) +{ + return sm_supported(iommu) ? + ecap_smpwc(iommu->ecap) : ecap_coherent(iommu->ecap); +} + static void domain_update_iommu_coherency(struct dmar_domain *domain) { struct dmar_drhd_unit *drhd; @@ -622,7 +628,7 @@ static void domain_update_iommu_coherency(struct dmar_domain *domain) for_each_domain_iommu(i, domain) { found = true; - if (!ecap_coherent(g_iommus[i]->ecap)) { + if (!iommu_paging_structure_coherency(g_iommus[i])) { domain->iommu_coherency = 0; break; } @@ -633,7 +639,7 @@ static void domain_update_iommu_coherency(struct dmar_domain *domain) /* No hardware attached; use lowest common denominator */ rcu_read_lock(); for_each_active_iommu(iommu, drhd) { - if (!ecap_coherent(iommu->ecap)) { + if (!iommu_paging_structure_coherency(iommu)) { domain->iommu_coherency = 0; break; } @@ -2090,7 +2096,8 @@ static int domain_context_mapping_one(struct dmar_domain *domain, context_set_fault_enable(context); context_set_present(context); - domain_flush_cache(domain, context, sizeof(*context)); + if (!ecap_coherent(iommu->ecap)) + clflush_cache_range(context, sizeof(*context)); /* * It's a non-present to present mapping. If hardware doesn't cache