From: Jason Gunthorpe jgg@nvidia.com
mainline inclusion from mainline-v6.11-rc1 commit ce26ea9e6e12df01432bd2a1cb8cbfa025b8a977 category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/IB4WDJ CVE: NA
Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i...
--------------------------------
The HW supports this, use the S1DSS bits to configure the behavior of SSID=0 which is the RID's translation.
If SSID's are currently being used in the CD table then just update the S1DSS bits in the STE, remove the master_domain and leave ATS alone.
For iommufd the driver design has a small problem that all the unused CD table entries are set with V=0 which will generate an event if VFIO userspace tries to use the CD entry. This patch extends this problem to include the RID as well if PASID is being used.
For BLOCKED with used PASIDs the F_STREAM_DISABLED (STRTAB_STE_1_S1DSS_TERMINATE) event is generated on untagged traffic and a substream CD table entry with V=0 (removed pasid) will generate C_BAD_CD. Arguably there is no advantage to using S1DSS over the CD entry 0 with V=0.
As we don't yet support PASID in iommufd this is a problem to resolve later, possibly by using EPD0 for unused CD table entries instead of V=0, and not using S1DSS for BLOCKED.
Tested-by: Nicolin Chen nicolinc@nvidia.com Tested-by: Shameer Kolothum shameerali.kolothum.thodi@huawei.com Reviewed-by: Nicolin Chen nicolinc@nvidia.com Reviewed-by: Jerry Snitselaar jsnitsel@redhat.com Signed-off-by: Jason Gunthorpe jgg@nvidia.com Link: https://lore.kernel.org/r/11-v9-5cd718286059+79186-smmuv3_newapi_p2b_jgg@nvi... Signed-off-by: Will Deacon will@kernel.org Signed-off-by: Kunkun Jiang jiangkunkun@huawei.com --- .../iommu/arm/arm-smmu-v3/arm-smmu-v3-test.c | 2 +- drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c | 60 +++++++++++++++---- drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h | 4 +- 3 files changed, 50 insertions(+), 16 deletions(-)
diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-test.c b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-test.c index 68aa1c61fdb3..8608504fe786 100644 --- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-test.c +++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-test.c @@ -164,7 +164,7 @@ static void arm_smmu_test_make_cdtable_ste(struct arm_smmu_ste *ste, .smmu = &smmu, };
- arm_smmu_make_cdtable_ste(ste, &master, true); + arm_smmu_make_cdtable_ste(ste, &master, true, STRTAB_STE_1_S1DSS_SSID0); }
static void arm_smmu_v3_write_ste_test_bypass_to_abort(struct kunit *test) diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c index e80b792a2a14..24f071881484 100644 --- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c +++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c @@ -1215,6 +1215,14 @@ void arm_smmu_get_ste_used(const __le64 *ent, __le64 *used_bits) STRTAB_STE_1_S1STALLD | STRTAB_STE_1_STRW | STRTAB_STE_1_EATS); used_bits[2] |= cpu_to_le64(STRTAB_STE_2_S2VMID); + + /* + * See 13.5 Summary of attribute/permission configuration fields + * for the SHCFG behavior. + */ + if (FIELD_GET(STRTAB_STE_1_S1DSS, le64_to_cpu(ent[1])) == + STRTAB_STE_1_S1DSS_BYPASS) + used_bits[1] |= cpu_to_le64(STRTAB_STE_1_SHCFG); }
/* S2 translates */ @@ -1758,7 +1766,8 @@ void arm_smmu_make_bypass_ste(struct arm_smmu_device *smmu,
VISIBLE_IF_KUNIT void arm_smmu_make_cdtable_ste(struct arm_smmu_ste *target, - struct arm_smmu_master *master, bool ats_enabled) + struct arm_smmu_master *master, bool ats_enabled, + unsigned int s1dss) { struct arm_smmu_ctx_desc_cfg *cd_table = &master->cd_table; struct arm_smmu_device *smmu = master->smmu; @@ -1772,7 +1781,7 @@ void arm_smmu_make_cdtable_ste(struct arm_smmu_ste *target, FIELD_PREP(STRTAB_STE_0_S1CDMAX, cd_table->s1cdmax));
target->data[1] = cpu_to_le64( - FIELD_PREP(STRTAB_STE_1_S1DSS, STRTAB_STE_1_S1DSS_SSID0) | + FIELD_PREP(STRTAB_STE_1_S1DSS, s1dss) | FIELD_PREP(STRTAB_STE_1_S1CIR, STRTAB_STE_1_S1C_CACHE_WBRA) | FIELD_PREP(STRTAB_STE_1_S1COR, STRTAB_STE_1_S1C_CACHE_WBRA) | FIELD_PREP(STRTAB_STE_1_S1CSH, ARM_SMMU_SH_ISH) | @@ -1783,6 +1792,11 @@ void arm_smmu_make_cdtable_ste(struct arm_smmu_ste *target, FIELD_PREP(STRTAB_STE_1_EATS, ats_enabled ? STRTAB_STE_1_EATS_TRANS : 0));
+ if ((smmu->features & ARM_SMMU_FEAT_ATTR_TYPES_OVR) && + s1dss == STRTAB_STE_1_S1DSS_BYPASS) + target->data[1] |= cpu_to_le64(FIELD_PREP( + STRTAB_STE_1_SHCFG, STRTAB_STE_1_SHCFG_INCOMING)); + if (smmu->features & ARM_SMMU_FEAT_E2H) { /* * To support BTM the streamworld needs to match the @@ -2839,6 +2853,7 @@ struct arm_smmu_attach_state { /* Inputs */ struct iommu_domain *old_domain; struct arm_smmu_master *master; + bool cd_needs_ats; ioasid_t ssid; /* Resulting state */ bool ats_enabled; @@ -2880,7 +2895,7 @@ static int arm_smmu_attach_prepare(struct arm_smmu_attach_state *state, */ lockdep_assert_held(&arm_smmu_asid_lock);
- if (smmu_domain) { + if (smmu_domain || state->cd_needs_ats) { /* * The SMMU does not support enabling ATS with bypass/abort. * When the STE is in bypass (STE.Config[2:0] == 0b100), ATS @@ -2892,7 +2907,9 @@ static int arm_smmu_attach_prepare(struct arm_smmu_attach_state *state, * tables. */ state->ats_enabled = arm_smmu_ats_supported(master); + }
+ if (smmu_domain) { master_domain = kzalloc(sizeof(*master_domain), GFP_KERNEL); if (!master_domain) return -ENOMEM; @@ -3020,7 +3037,8 @@ static int arm_smmu_attach_dev(struct iommu_domain *domain, struct device *dev) arm_smmu_make_s1_cd(&target_cd, master, smmu_domain); arm_smmu_write_cd_entry(master, IOMMU_NO_PASID, cdptr, &target_cd); - arm_smmu_make_cdtable_ste(&target, master, state.ats_enabled); + arm_smmu_make_cdtable_ste(&target, master, state.ats_enabled, + STRTAB_STE_1_S1DSS_SSID0); arm_smmu_install_ste_for_dev(master, &target); break; } @@ -3094,8 +3112,10 @@ static void arm_smmu_remove_dev_pasid(struct device *dev, ioasid_t pasid, mutex_unlock(&arm_smmu_asid_lock); }
-static int arm_smmu_attach_dev_ste(struct iommu_domain *domain, - struct device *dev, struct arm_smmu_ste *ste) +static void arm_smmu_attach_dev_ste(struct iommu_domain *domain, + struct device *dev, + struct arm_smmu_ste *ste, + unsigned int s1dss) { struct arm_smmu_master *master = dev_iommu_priv_get(dev); struct arm_smmu_attach_state state = { @@ -3104,16 +3124,28 @@ static int arm_smmu_attach_dev_ste(struct iommu_domain *domain, .ssid = IOMMU_NO_PASID, };
- if (arm_smmu_ssids_in_use(&master->cd_table)) - return -EBUSY; - /* * Do not allow any ASID to be changed while are working on the STE, * otherwise we could miss invalidations. */ mutex_lock(&arm_smmu_asid_lock);
- arm_smmu_attach_prepare(&state, domain); + /* + * If the CD table is not in use we can use the provided STE, otherwise + * we use a cdtable STE with the provided S1DSS. + */ + if (arm_smmu_ssids_in_use(&master->cd_table)) { + /* + * If a CD table has to be present then we need to run with ATS + * on even though the RID will fail ATS queries with UR. This is + * because we have no idea what the PASID's need. + */ + state.cd_needs_ats = true; + arm_smmu_attach_prepare(&state, domain); + arm_smmu_make_cdtable_ste(ste, master, state.ats_enabled, s1dss); + } else { + arm_smmu_attach_prepare(&state, domain); + } arm_smmu_install_ste_for_dev(master, ste); arm_smmu_attach_commit(&state); mutex_unlock(&arm_smmu_asid_lock); @@ -3124,7 +3156,6 @@ static int arm_smmu_attach_dev_ste(struct iommu_domain *domain, * descriptor from arm_smmu_share_asid(). */ arm_smmu_clear_cd(master, IOMMU_NO_PASID); - return 0; }
static int arm_smmu_attach_dev_identity(struct iommu_domain *domain, @@ -3134,7 +3165,8 @@ static int arm_smmu_attach_dev_identity(struct iommu_domain *domain, struct arm_smmu_master *master = dev_iommu_priv_get(dev);
arm_smmu_make_bypass_ste(master->smmu, &ste); - return arm_smmu_attach_dev_ste(domain, dev, &ste); + arm_smmu_attach_dev_ste(domain, dev, &ste, STRTAB_STE_1_S1DSS_BYPASS); + return 0; }
static const struct iommu_domain_ops arm_smmu_identity_ops = { @@ -3152,7 +3184,9 @@ static int arm_smmu_attach_dev_blocked(struct iommu_domain *domain, struct arm_smmu_ste ste;
arm_smmu_make_abort_ste(&ste); - return arm_smmu_attach_dev_ste(domain, dev, &ste); + arm_smmu_attach_dev_ste(domain, dev, &ste, + STRTAB_STE_1_S1DSS_TERMINATE); + return 0; }
static const struct iommu_domain_ops arm_smmu_blocked_ops = { diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h index 786652700f5e..c4a042ec111d 100644 --- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h +++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h @@ -842,8 +842,8 @@ void arm_smmu_make_abort_ste(struct arm_smmu_ste *target); void arm_smmu_make_bypass_ste(struct arm_smmu_device *smmu, struct arm_smmu_ste *target); void arm_smmu_make_cdtable_ste(struct arm_smmu_ste *target, - struct arm_smmu_master *master, - bool ats_enabled); + struct arm_smmu_master *master, bool ats_enabled, + unsigned int s1dss); void arm_smmu_make_s2_domain_ste(struct arm_smmu_ste *target, struct arm_smmu_master *master, struct arm_smmu_domain *smmu_domain,