Message ID | 20200113143924.11576-1-robh@kernel.org (mailing list archive) |
---|---|
State | New, archived |
Headers | show |
Series | iommu/arm-smmu-v3: Add SMMUv3.2 range invalidation support | expand |
Hi Rob, On 1/13/20 3:39 PM, Rob Herring wrote: > Arm SMMUv3.2 adds support for TLB range invalidate operations. > Support for range invalidate is determined by the RIL bit in the IDR3 > register. > > The range invalidate is in units of the leaf page size and operates on > 1-32 chunks of a power of 2 multiple pages. First we determine from the > size what power of 2 multiple we can use and then adjust the granule to > 32x that size. > > Cc: Eric Auger <eric.auger@redhat.com> > Cc: Jean-Philippe Brucker <jean-philippe@linaro.org> > Cc: Will Deacon <will@kernel.org> > Cc: Robin Murphy <robin.murphy@arm.com> > Cc: Joerg Roedel <joro@8bytes.org> > Signed-off-by: Rob Herring <robh@kernel.org> > --- > drivers/iommu/arm-smmu-v3.c | 53 +++++++++++++++++++++++++++++++++++++ > 1 file changed, 53 insertions(+) > > diff --git a/drivers/iommu/arm-smmu-v3.c b/drivers/iommu/arm-smmu-v3.c > index e91b4a098215..8b6b3e2aa383 100644 > --- a/drivers/iommu/arm-smmu-v3.c > +++ b/drivers/iommu/arm-smmu-v3.c > @@ -70,6 +70,9 @@ > #define IDR1_SSIDSIZE GENMASK(10, 6) > #define IDR1_SIDSIZE GENMASK(5, 0) > > +#define ARM_SMMU_IDR3 0xc > +#define IDR3_RIL (1 << 10) > + > #define ARM_SMMU_IDR5 0x14 > #define IDR5_STALL_MAX GENMASK(31, 16) > #define IDR5_GRAN64K (1 << 6) > @@ -327,9 +330,14 @@ > #define CMDQ_CFGI_1_LEAF (1UL << 0) > #define CMDQ_CFGI_1_RANGE GENMASK_ULL(4, 0) > > +#define CMDQ_TLBI_0_NUM GENMASK_ULL(16, 12) > +#define CMDQ_TLBI_RANGE_NUM_MAX 32 > +#define CMDQ_TLBI_0_SCALE GENMASK_ULL(24, 20) > #define CMDQ_TLBI_0_VMID GENMASK_ULL(47, 32) > #define CMDQ_TLBI_0_ASID GENMASK_ULL(63, 48) > #define CMDQ_TLBI_1_LEAF (1UL << 0) > +#define CMDQ_TLBI_1_TTL GENMASK_ULL(9, 8) > +#define CMDQ_TLBI_1_TG GENMASK_ULL(11, 10) > #define CMDQ_TLBI_1_VA_MASK GENMASK_ULL(63, 12) > #define CMDQ_TLBI_1_IPA_MASK GENMASK_ULL(51, 12) > > @@ -455,9 +463,13 @@ struct arm_smmu_cmdq_ent { > #define CMDQ_OP_TLBI_S2_IPA 0x2a > #define CMDQ_OP_TLBI_NSNH_ALL 0x30 > struct { > + u8 num; > + u8 scale; > u16 asid; > u16 vmid; > bool leaf; > + u8 ttl; > + u8 tg; > u64 addr; > } tlbi; > > @@ -595,6 +607,7 @@ struct arm_smmu_device { > #define ARM_SMMU_FEAT_HYP (1 << 12) > #define ARM_SMMU_FEAT_STALL_FORCE (1 << 13) > #define ARM_SMMU_FEAT_VAX (1 << 14) > +#define ARM_SMMU_FEAT_RANGE_INV (1 << 15) > u32 features; > > #define ARM_SMMU_OPT_SKIP_PREFETCH (1 << 0) > @@ -856,13 +869,21 @@ static int arm_smmu_cmdq_build_cmd(u64 *cmd, struct arm_smmu_cmdq_ent *ent) > cmd[1] |= FIELD_PREP(CMDQ_CFGI_1_RANGE, 31); > break; > case CMDQ_OP_TLBI_NH_VA: > + cmd[0] |= FIELD_PREP(CMDQ_TLBI_0_NUM, ent->tlbi.num); > + cmd[0] |= FIELD_PREP(CMDQ_TLBI_0_SCALE, ent->tlbi.scale); > cmd[0] |= FIELD_PREP(CMDQ_TLBI_0_ASID, ent->tlbi.asid); > cmd[1] |= FIELD_PREP(CMDQ_TLBI_1_LEAF, ent->tlbi.leaf); > + cmd[1] |= FIELD_PREP(CMDQ_TLBI_1_TTL, ent->tlbi.ttl); > + cmd[1] |= FIELD_PREP(CMDQ_TLBI_1_TG, ent->tlbi.tg); > cmd[1] |= ent->tlbi.addr & CMDQ_TLBI_1_VA_MASK; > break; > case CMDQ_OP_TLBI_S2_IPA: > + cmd[0] |= FIELD_PREP(CMDQ_TLBI_0_NUM, ent->tlbi.num); > + cmd[0] |= FIELD_PREP(CMDQ_TLBI_0_SCALE, ent->tlbi.scale); > cmd[0] |= FIELD_PREP(CMDQ_TLBI_0_VMID, ent->tlbi.vmid); > cmd[1] |= FIELD_PREP(CMDQ_TLBI_1_LEAF, ent->tlbi.leaf); > + cmd[1] |= FIELD_PREP(CMDQ_TLBI_1_TTL, ent->tlbi.ttl); > + cmd[1] |= FIELD_PREP(CMDQ_TLBI_1_TG, ent->tlbi.tg); > cmd[1] |= ent->tlbi.addr & CMDQ_TLBI_1_IPA_MASK; > break; > case CMDQ_OP_TLBI_NH_ASID: > @@ -2022,12 +2043,39 @@ static void arm_smmu_tlb_inv_range(unsigned long iova, size_t size, > cmd.tlbi.vmid = smmu_domain->s2_cfg.vmid; > } > > + if (smmu->features & ARM_SMMU_FEAT_RANGE_INV) { > + unsigned long tg, scale; > + > + /* Get the leaf page size */ > + tg = __ffs(smmu_domain->domain.pgsize_bitmap); it is unclear to me why you can't set tg with the granule parameter. > + > + /* Determine the power of 2 multiple number of pages */ > + scale = __ffs(size / (1UL << tg)); > + cmd.tlbi.scale = scale; > + > + cmd.tlbi.num = CMDQ_TLBI_RANGE_NUM_MAX - 1; Also could you explain why you use CMDQ_TLBI_RANGE_NUM_MAX. > + > + /* Convert page size of 12,14,16 (log2) to 1,2,3 */ > + cmd.tlbi.tg = ((tg - ilog2(SZ_4K)) / 2) + 1; > + > + /* Determine what level the granule is at */ > + cmd.tlbi.ttl = 4 - ((ilog2(granule) - 3) / (tg - 3)); > + > + /* Adjust granule to the maximum range */ > + granule = CMDQ_TLBI_RANGE_NUM_MAX * (1 << scale) * (1UL << tg); spec says Range = ((NUM+1)*2 ^ SCALE )*Translation_Granule_Size Thanks Eric > + } > + > while (iova < end) { > if (i == CMDQ_BATCH_ENTRIES) { > arm_smmu_cmdq_issue_cmdlist(smmu, cmds, i, false); > i = 0; > } > > + /* Only possible for range invalidate */ > + if (granule > (end - iova)) > + cmd.tlbi.num = ((end - iova) / > + (granule / CMDQ_TLBI_RANGE_NUM_MAX)) - 1; > + > cmd.tlbi.addr = iova; > arm_smmu_cmdq_build_cmd(&cmds[i * CMDQ_ENT_DWORDS], &cmd); > iova += granule; > @@ -3449,6 +3497,11 @@ static int arm_smmu_device_hw_probe(struct arm_smmu_device *smmu) > if (smmu->sid_bits <= STRTAB_SPLIT) > smmu->features &= ~ARM_SMMU_FEAT_2_LVL_STRTAB; > > + /* IDR3 */ > + reg = readl_relaxed(smmu->base + ARM_SMMU_IDR3); > + if (FIELD_GET(IDR3_RIL, reg)) > + smmu->features |= ARM_SMMU_FEAT_RANGE_INV; > + > /* IDR5 */ > reg = readl_relaxed(smmu->base + ARM_SMMU_IDR5); > >
On Wed, Jan 15, 2020 at 3:21 AM Auger Eric <eric.auger@redhat.com> wrote: > > Hi Rob, > > On 1/13/20 3:39 PM, Rob Herring wrote: > > Arm SMMUv3.2 adds support for TLB range invalidate operations. > > Support for range invalidate is determined by the RIL bit in the IDR3 > > register. > > > > The range invalidate is in units of the leaf page size and operates on > > 1-32 chunks of a power of 2 multiple pages. First we determine from the > > size what power of 2 multiple we can use and then adjust the granule to > > 32x that size. > > > > Cc: Eric Auger <eric.auger@redhat.com> > > Cc: Jean-Philippe Brucker <jean-philippe@linaro.org> > > Cc: Will Deacon <will@kernel.org> > > Cc: Robin Murphy <robin.murphy@arm.com> > > Cc: Joerg Roedel <joro@8bytes.org> > > Signed-off-by: Rob Herring <robh@kernel.org> > > --- > > drivers/iommu/arm-smmu-v3.c | 53 +++++++++++++++++++++++++++++++++++++ > > 1 file changed, 53 insertions(+) > > > > diff --git a/drivers/iommu/arm-smmu-v3.c b/drivers/iommu/arm-smmu-v3.c > > index e91b4a098215..8b6b3e2aa383 100644 > > --- a/drivers/iommu/arm-smmu-v3.c > > +++ b/drivers/iommu/arm-smmu-v3.c > > @@ -70,6 +70,9 @@ > > #define IDR1_SSIDSIZE GENMASK(10, 6) > > #define IDR1_SIDSIZE GENMASK(5, 0) > > > > +#define ARM_SMMU_IDR3 0xc > > +#define IDR3_RIL (1 << 10) > > + > > #define ARM_SMMU_IDR5 0x14 > > #define IDR5_STALL_MAX GENMASK(31, 16) > > #define IDR5_GRAN64K (1 << 6) > > @@ -327,9 +330,14 @@ > > #define CMDQ_CFGI_1_LEAF (1UL << 0) > > #define CMDQ_CFGI_1_RANGE GENMASK_ULL(4, 0) > > > > +#define CMDQ_TLBI_0_NUM GENMASK_ULL(16, 12) > > +#define CMDQ_TLBI_RANGE_NUM_MAX 32 > > +#define CMDQ_TLBI_0_SCALE GENMASK_ULL(24, 20) > > #define CMDQ_TLBI_0_VMID GENMASK_ULL(47, 32) > > #define CMDQ_TLBI_0_ASID GENMASK_ULL(63, 48) > > #define CMDQ_TLBI_1_LEAF (1UL << 0) > > +#define CMDQ_TLBI_1_TTL GENMASK_ULL(9, 8) > > +#define CMDQ_TLBI_1_TG GENMASK_ULL(11, 10) > > #define CMDQ_TLBI_1_VA_MASK GENMASK_ULL(63, 12) > > #define CMDQ_TLBI_1_IPA_MASK GENMASK_ULL(51, 12) > > > > @@ -455,9 +463,13 @@ struct arm_smmu_cmdq_ent { > > #define CMDQ_OP_TLBI_S2_IPA 0x2a > > #define CMDQ_OP_TLBI_NSNH_ALL 0x30 > > struct { > > + u8 num; > > + u8 scale; > > u16 asid; > > u16 vmid; > > bool leaf; > > + u8 ttl; > > + u8 tg; > > u64 addr; > > } tlbi; > > > > @@ -595,6 +607,7 @@ struct arm_smmu_device { > > #define ARM_SMMU_FEAT_HYP (1 << 12) > > #define ARM_SMMU_FEAT_STALL_FORCE (1 << 13) > > #define ARM_SMMU_FEAT_VAX (1 << 14) > > +#define ARM_SMMU_FEAT_RANGE_INV (1 << 15) > > u32 features; > > > > #define ARM_SMMU_OPT_SKIP_PREFETCH (1 << 0) > > @@ -856,13 +869,21 @@ static int arm_smmu_cmdq_build_cmd(u64 *cmd, struct arm_smmu_cmdq_ent *ent) > > cmd[1] |= FIELD_PREP(CMDQ_CFGI_1_RANGE, 31); > > break; > > case CMDQ_OP_TLBI_NH_VA: > > + cmd[0] |= FIELD_PREP(CMDQ_TLBI_0_NUM, ent->tlbi.num); > > + cmd[0] |= FIELD_PREP(CMDQ_TLBI_0_SCALE, ent->tlbi.scale); > > cmd[0] |= FIELD_PREP(CMDQ_TLBI_0_ASID, ent->tlbi.asid); > > cmd[1] |= FIELD_PREP(CMDQ_TLBI_1_LEAF, ent->tlbi.leaf); > > + cmd[1] |= FIELD_PREP(CMDQ_TLBI_1_TTL, ent->tlbi.ttl); > > + cmd[1] |= FIELD_PREP(CMDQ_TLBI_1_TG, ent->tlbi.tg); > > cmd[1] |= ent->tlbi.addr & CMDQ_TLBI_1_VA_MASK; > > break; > > case CMDQ_OP_TLBI_S2_IPA: > > + cmd[0] |= FIELD_PREP(CMDQ_TLBI_0_NUM, ent->tlbi.num); > > + cmd[0] |= FIELD_PREP(CMDQ_TLBI_0_SCALE, ent->tlbi.scale); > > cmd[0] |= FIELD_PREP(CMDQ_TLBI_0_VMID, ent->tlbi.vmid); > > cmd[1] |= FIELD_PREP(CMDQ_TLBI_1_LEAF, ent->tlbi.leaf); > > + cmd[1] |= FIELD_PREP(CMDQ_TLBI_1_TTL, ent->tlbi.ttl); > > + cmd[1] |= FIELD_PREP(CMDQ_TLBI_1_TG, ent->tlbi.tg); > > cmd[1] |= ent->tlbi.addr & CMDQ_TLBI_1_IPA_MASK; > > break; > > case CMDQ_OP_TLBI_NH_ASID: > > @@ -2022,12 +2043,39 @@ static void arm_smmu_tlb_inv_range(unsigned long iova, size_t size, > > cmd.tlbi.vmid = smmu_domain->s2_cfg.vmid; > > } > > > > + if (smmu->features & ARM_SMMU_FEAT_RANGE_INV) { > > + unsigned long tg, scale; > > + > > + /* Get the leaf page size */ > > + tg = __ffs(smmu_domain->domain.pgsize_bitmap); > it is unclear to me why you can't set tg with the granule parameter. granule could be 2MB sections if THP is enabled, right? > > + > > + /* Determine the power of 2 multiple number of pages */ > > + scale = __ffs(size / (1UL << tg)); > > + cmd.tlbi.scale = scale; > > + > > + cmd.tlbi.num = CMDQ_TLBI_RANGE_NUM_MAX - 1; > Also could you explain why you use CMDQ_TLBI_RANGE_NUM_MAX. How's this: /* The invalidation loop defaults to the maximum range */ And perhaps I'll move it next to setting granule. > > + > > + /* Convert page size of 12,14,16 (log2) to 1,2,3 */ > > + cmd.tlbi.tg = ((tg - ilog2(SZ_4K)) / 2) + 1; > > + > > + /* Determine what level the granule is at */ > > + cmd.tlbi.ttl = 4 - ((ilog2(granule) - 3) / (tg - 3)); > > + > > + /* Adjust granule to the maximum range */ > > + granule = CMDQ_TLBI_RANGE_NUM_MAX * (1 << scale) * (1UL << tg); > spec says > Range = ((NUM+1)*2 ^ SCALE )*Translation_Granule_Size (NUM+1) can be 1-32. I went with the logical max for CMDQ_TLBI_RANGE_NUM_MAX rather than the NUM field value max. Rob
Hi Rob, On 1/15/20 3:02 PM, Rob Herring wrote: > On Wed, Jan 15, 2020 at 3:21 AM Auger Eric <eric.auger@redhat.com> wrote: >> >> Hi Rob, >> >> On 1/13/20 3:39 PM, Rob Herring wrote: >>> Arm SMMUv3.2 adds support for TLB range invalidate operations. >>> Support for range invalidate is determined by the RIL bit in the IDR3 >>> register. >>> >>> The range invalidate is in units of the leaf page size and operates on >>> 1-32 chunks of a power of 2 multiple pages. First we determine from the >>> size what power of 2 multiple we can use and then adjust the granule to >>> 32x that size. >>> >>> Cc: Eric Auger <eric.auger@redhat.com> >>> Cc: Jean-Philippe Brucker <jean-philippe@linaro.org> >>> Cc: Will Deacon <will@kernel.org> >>> Cc: Robin Murphy <robin.murphy@arm.com> >>> Cc: Joerg Roedel <joro@8bytes.org> >>> Signed-off-by: Rob Herring <robh@kernel.org> >>> --- >>> drivers/iommu/arm-smmu-v3.c | 53 +++++++++++++++++++++++++++++++++++++ >>> 1 file changed, 53 insertions(+) >>> >>> diff --git a/drivers/iommu/arm-smmu-v3.c b/drivers/iommu/arm-smmu-v3.c >>> index e91b4a098215..8b6b3e2aa383 100644 >>> --- a/drivers/iommu/arm-smmu-v3.c >>> +++ b/drivers/iommu/arm-smmu-v3.c >>> @@ -70,6 +70,9 @@ >>> #define IDR1_SSIDSIZE GENMASK(10, 6) >>> #define IDR1_SIDSIZE GENMASK(5, 0) >>> >>> +#define ARM_SMMU_IDR3 0xc >>> +#define IDR3_RIL (1 << 10) >>> + >>> #define ARM_SMMU_IDR5 0x14 >>> #define IDR5_STALL_MAX GENMASK(31, 16) >>> #define IDR5_GRAN64K (1 << 6) >>> @@ -327,9 +330,14 @@ >>> #define CMDQ_CFGI_1_LEAF (1UL << 0) >>> #define CMDQ_CFGI_1_RANGE GENMASK_ULL(4, 0) >>> >>> +#define CMDQ_TLBI_0_NUM GENMASK_ULL(16, 12) >>> +#define CMDQ_TLBI_RANGE_NUM_MAX 32 >>> +#define CMDQ_TLBI_0_SCALE GENMASK_ULL(24, 20) >>> #define CMDQ_TLBI_0_VMID GENMASK_ULL(47, 32) >>> #define CMDQ_TLBI_0_ASID GENMASK_ULL(63, 48) >>> #define CMDQ_TLBI_1_LEAF (1UL << 0) >>> +#define CMDQ_TLBI_1_TTL GENMASK_ULL(9, 8) >>> +#define CMDQ_TLBI_1_TG GENMASK_ULL(11, 10) >>> #define CMDQ_TLBI_1_VA_MASK GENMASK_ULL(63, 12) >>> #define CMDQ_TLBI_1_IPA_MASK GENMASK_ULL(51, 12) >>> >>> @@ -455,9 +463,13 @@ struct arm_smmu_cmdq_ent { >>> #define CMDQ_OP_TLBI_S2_IPA 0x2a >>> #define CMDQ_OP_TLBI_NSNH_ALL 0x30 >>> struct { >>> + u8 num; >>> + u8 scale; >>> u16 asid; >>> u16 vmid; >>> bool leaf; >>> + u8 ttl; >>> + u8 tg; >>> u64 addr; >>> } tlbi; >>> >>> @@ -595,6 +607,7 @@ struct arm_smmu_device { >>> #define ARM_SMMU_FEAT_HYP (1 << 12) >>> #define ARM_SMMU_FEAT_STALL_FORCE (1 << 13) >>> #define ARM_SMMU_FEAT_VAX (1 << 14) >>> +#define ARM_SMMU_FEAT_RANGE_INV (1 << 15) >>> u32 features; >>> >>> #define ARM_SMMU_OPT_SKIP_PREFETCH (1 << 0) >>> @@ -856,13 +869,21 @@ static int arm_smmu_cmdq_build_cmd(u64 *cmd, struct arm_smmu_cmdq_ent *ent) >>> cmd[1] |= FIELD_PREP(CMDQ_CFGI_1_RANGE, 31); >>> break; >>> case CMDQ_OP_TLBI_NH_VA: >>> + cmd[0] |= FIELD_PREP(CMDQ_TLBI_0_NUM, ent->tlbi.num); >>> + cmd[0] |= FIELD_PREP(CMDQ_TLBI_0_SCALE, ent->tlbi.scale); >>> cmd[0] |= FIELD_PREP(CMDQ_TLBI_0_ASID, ent->tlbi.asid); >>> cmd[1] |= FIELD_PREP(CMDQ_TLBI_1_LEAF, ent->tlbi.leaf); >>> + cmd[1] |= FIELD_PREP(CMDQ_TLBI_1_TTL, ent->tlbi.ttl); >>> + cmd[1] |= FIELD_PREP(CMDQ_TLBI_1_TG, ent->tlbi.tg); >>> cmd[1] |= ent->tlbi.addr & CMDQ_TLBI_1_VA_MASK; >>> break; >>> case CMDQ_OP_TLBI_S2_IPA: >>> + cmd[0] |= FIELD_PREP(CMDQ_TLBI_0_NUM, ent->tlbi.num); >>> + cmd[0] |= FIELD_PREP(CMDQ_TLBI_0_SCALE, ent->tlbi.scale); >>> cmd[0] |= FIELD_PREP(CMDQ_TLBI_0_VMID, ent->tlbi.vmid); >>> cmd[1] |= FIELD_PREP(CMDQ_TLBI_1_LEAF, ent->tlbi.leaf); >>> + cmd[1] |= FIELD_PREP(CMDQ_TLBI_1_TTL, ent->tlbi.ttl); >>> + cmd[1] |= FIELD_PREP(CMDQ_TLBI_1_TG, ent->tlbi.tg); >>> cmd[1] |= ent->tlbi.addr & CMDQ_TLBI_1_IPA_MASK; >>> break; >>> case CMDQ_OP_TLBI_NH_ASID: >>> @@ -2022,12 +2043,39 @@ static void arm_smmu_tlb_inv_range(unsigned long iova, size_t size, >>> cmd.tlbi.vmid = smmu_domain->s2_cfg.vmid; >>> } >>> >>> + if (smmu->features & ARM_SMMU_FEAT_RANGE_INV) { >>> + unsigned long tg, scale; >>> + >>> + /* Get the leaf page size */ >>> + tg = __ffs(smmu_domain->domain.pgsize_bitmap); >> it is unclear to me why you can't set tg with the granule parameter. > > granule could be 2MB sections if THP is enabled, right? Ah OK I thought it was a page size and not a block size. I requested this feature a long time ago for virtual SMMUv3. With DPDK/VFIO the guest was sending page TLB invalidation for each page (granule=4K or 64K) part of the hugepage buffer and those were trapped by the VMM. This stalled qemu. > >>> + >>> + /* Determine the power of 2 multiple number of pages */ >>> + scale = __ffs(size / (1UL << tg)); >>> + cmd.tlbi.scale = scale; >>> + >>> + cmd.tlbi.num = CMDQ_TLBI_RANGE_NUM_MAX - 1; >> Also could you explain why you use CMDQ_TLBI_RANGE_NUM_MAX. > > How's this: > /* The invalidation loop defaults to the maximum range */ I would have expected num=0 directly. Don't we invalidate the &size in one shot as 2^scale * pages of granularity @tg? I fail to understand when NUM > 0. Thanks Eric > > And perhaps I'll move it next to setting granule. > >>> + >>> + /* Convert page size of 12,14,16 (log2) to 1,2,3 */ >>> + cmd.tlbi.tg = ((tg - ilog2(SZ_4K)) / 2) + 1; >>> + >>> + /* Determine what level the granule is at */ >>> + cmd.tlbi.ttl = 4 - ((ilog2(granule) - 3) / (tg - 3)); >>> + >>> + /* Adjust granule to the maximum range */ >>> + granule = CMDQ_TLBI_RANGE_NUM_MAX * (1 << scale) * (1UL << tg); >> spec says >> Range = ((NUM+1)*2 ^ SCALE )*Translation_Granule_Size > > (NUM+1) can be 1-32. I went with the logical max for > CMDQ_TLBI_RANGE_NUM_MAX rather than the NUM field value max. > > Rob > > _______________________________________________ > linux-arm-kernel mailing list > linux-arm-kernel@lists.infradead.org > http://lists.infradead.org/mailman/listinfo/linux-arm-kernel >
On 2020-01-15 4:32 pm, Auger Eric wrote: > Hi Rob, > > On 1/15/20 3:02 PM, Rob Herring wrote: >> On Wed, Jan 15, 2020 at 3:21 AM Auger Eric <eric.auger@redhat.com> wrote: >>> >>> Hi Rob, >>> >>> On 1/13/20 3:39 PM, Rob Herring wrote: >>>> Arm SMMUv3.2 adds support for TLB range invalidate operations. >>>> Support for range invalidate is determined by the RIL bit in the IDR3 >>>> register. >>>> >>>> The range invalidate is in units of the leaf page size and operates on >>>> 1-32 chunks of a power of 2 multiple pages. First we determine from the >>>> size what power of 2 multiple we can use and then adjust the granule to >>>> 32x that size. >>>> >>>> Cc: Eric Auger <eric.auger@redhat.com> >>>> Cc: Jean-Philippe Brucker <jean-philippe@linaro.org> >>>> Cc: Will Deacon <will@kernel.org> >>>> Cc: Robin Murphy <robin.murphy@arm.com> >>>> Cc: Joerg Roedel <joro@8bytes.org> >>>> Signed-off-by: Rob Herring <robh@kernel.org> >>>> --- >>>> drivers/iommu/arm-smmu-v3.c | 53 +++++++++++++++++++++++++++++++++++++ >>>> 1 file changed, 53 insertions(+) >>>> >>>> diff --git a/drivers/iommu/arm-smmu-v3.c b/drivers/iommu/arm-smmu-v3.c >>>> index e91b4a098215..8b6b3e2aa383 100644 >>>> --- a/drivers/iommu/arm-smmu-v3.c >>>> +++ b/drivers/iommu/arm-smmu-v3.c >>>> @@ -70,6 +70,9 @@ >>>> #define IDR1_SSIDSIZE GENMASK(10, 6) >>>> #define IDR1_SIDSIZE GENMASK(5, 0) >>>> >>>> +#define ARM_SMMU_IDR3 0xc >>>> +#define IDR3_RIL (1 << 10) >>>> + >>>> #define ARM_SMMU_IDR5 0x14 >>>> #define IDR5_STALL_MAX GENMASK(31, 16) >>>> #define IDR5_GRAN64K (1 << 6) >>>> @@ -327,9 +330,14 @@ >>>> #define CMDQ_CFGI_1_LEAF (1UL << 0) >>>> #define CMDQ_CFGI_1_RANGE GENMASK_ULL(4, 0) >>>> >>>> +#define CMDQ_TLBI_0_NUM GENMASK_ULL(16, 12) >>>> +#define CMDQ_TLBI_RANGE_NUM_MAX 32 >>>> +#define CMDQ_TLBI_0_SCALE GENMASK_ULL(24, 20) >>>> #define CMDQ_TLBI_0_VMID GENMASK_ULL(47, 32) >>>> #define CMDQ_TLBI_0_ASID GENMASK_ULL(63, 48) >>>> #define CMDQ_TLBI_1_LEAF (1UL << 0) >>>> +#define CMDQ_TLBI_1_TTL GENMASK_ULL(9, 8) >>>> +#define CMDQ_TLBI_1_TG GENMASK_ULL(11, 10) >>>> #define CMDQ_TLBI_1_VA_MASK GENMASK_ULL(63, 12) >>>> #define CMDQ_TLBI_1_IPA_MASK GENMASK_ULL(51, 12) >>>> >>>> @@ -455,9 +463,13 @@ struct arm_smmu_cmdq_ent { >>>> #define CMDQ_OP_TLBI_S2_IPA 0x2a >>>> #define CMDQ_OP_TLBI_NSNH_ALL 0x30 >>>> struct { >>>> + u8 num; >>>> + u8 scale; >>>> u16 asid; >>>> u16 vmid; >>>> bool leaf; >>>> + u8 ttl; >>>> + u8 tg; >>>> u64 addr; >>>> } tlbi; >>>> >>>> @@ -595,6 +607,7 @@ struct arm_smmu_device { >>>> #define ARM_SMMU_FEAT_HYP (1 << 12) >>>> #define ARM_SMMU_FEAT_STALL_FORCE (1 << 13) >>>> #define ARM_SMMU_FEAT_VAX (1 << 14) >>>> +#define ARM_SMMU_FEAT_RANGE_INV (1 << 15) >>>> u32 features; >>>> >>>> #define ARM_SMMU_OPT_SKIP_PREFETCH (1 << 0) >>>> @@ -856,13 +869,21 @@ static int arm_smmu_cmdq_build_cmd(u64 *cmd, struct arm_smmu_cmdq_ent *ent) >>>> cmd[1] |= FIELD_PREP(CMDQ_CFGI_1_RANGE, 31); >>>> break; >>>> case CMDQ_OP_TLBI_NH_VA: >>>> + cmd[0] |= FIELD_PREP(CMDQ_TLBI_0_NUM, ent->tlbi.num); >>>> + cmd[0] |= FIELD_PREP(CMDQ_TLBI_0_SCALE, ent->tlbi.scale); >>>> cmd[0] |= FIELD_PREP(CMDQ_TLBI_0_ASID, ent->tlbi.asid); >>>> cmd[1] |= FIELD_PREP(CMDQ_TLBI_1_LEAF, ent->tlbi.leaf); >>>> + cmd[1] |= FIELD_PREP(CMDQ_TLBI_1_TTL, ent->tlbi.ttl); >>>> + cmd[1] |= FIELD_PREP(CMDQ_TLBI_1_TG, ent->tlbi.tg); >>>> cmd[1] |= ent->tlbi.addr & CMDQ_TLBI_1_VA_MASK; >>>> break; >>>> case CMDQ_OP_TLBI_S2_IPA: >>>> + cmd[0] |= FIELD_PREP(CMDQ_TLBI_0_NUM, ent->tlbi.num); >>>> + cmd[0] |= FIELD_PREP(CMDQ_TLBI_0_SCALE, ent->tlbi.scale); >>>> cmd[0] |= FIELD_PREP(CMDQ_TLBI_0_VMID, ent->tlbi.vmid); >>>> cmd[1] |= FIELD_PREP(CMDQ_TLBI_1_LEAF, ent->tlbi.leaf); >>>> + cmd[1] |= FIELD_PREP(CMDQ_TLBI_1_TTL, ent->tlbi.ttl); >>>> + cmd[1] |= FIELD_PREP(CMDQ_TLBI_1_TG, ent->tlbi.tg); >>>> cmd[1] |= ent->tlbi.addr & CMDQ_TLBI_1_IPA_MASK; >>>> break; >>>> case CMDQ_OP_TLBI_NH_ASID: >>>> @@ -2022,12 +2043,39 @@ static void arm_smmu_tlb_inv_range(unsigned long iova, size_t size, >>>> cmd.tlbi.vmid = smmu_domain->s2_cfg.vmid; >>>> } >>>> >>>> + if (smmu->features & ARM_SMMU_FEAT_RANGE_INV) { >>>> + unsigned long tg, scale; >>>> + >>>> + /* Get the leaf page size */ >>>> + tg = __ffs(smmu_domain->domain.pgsize_bitmap); >>> it is unclear to me why you can't set tg with the granule parameter. >> >> granule could be 2MB sections if THP is enabled, right? > > Ah OK I thought it was a page size and not a block size. In hindsight, @granule might be more accurately called @leaf_size - for a non-leaf invalidate, it should always be the actual granule (i.e. page size), per __arm_lpae_unmap(). Even if we're knocking out a level 1 table, we don't walk the whole thing to find leaves at level 2 and/or level 1 to invalidate, we just knock out the range at page granularity to be safe. However for leaf invalidations we know exactly what we're taking out, so @granule may be a block size if appropriate (that definitely used to be the case, and I don't *think* the gather ops changed it). > I requested this feature a long time ago for virtual SMMUv3. With > DPDK/VFIO the guest was sending page TLB invalidation for each page > (granule=4K or 64K) part of the hugepage buffer and those were trapped > by the VMM. This stalled qemu. Heh, I remember that being awkward to comment on at the time since we were already speccing out 3.2 internally :) Robin. >>>> + >>>> + /* Determine the power of 2 multiple number of pages */ >>>> + scale = __ffs(size / (1UL << tg)); >>>> + cmd.tlbi.scale = scale; >>>> + >>>> + cmd.tlbi.num = CMDQ_TLBI_RANGE_NUM_MAX - 1; >>> Also could you explain why you use CMDQ_TLBI_RANGE_NUM_MAX. >> >> How's this: >> /* The invalidation loop defaults to the maximum range */ > I would have expected num=0 directly. Don't we invalidate the &size in > one shot as 2^scale * pages of granularity @tg? I fail to understand > when NUM > 0. > > > Thanks > > Eric >> >> And perhaps I'll move it next to setting granule. >> >>>> + >>>> + /* Convert page size of 12,14,16 (log2) to 1,2,3 */ >>>> + cmd.tlbi.tg = ((tg - ilog2(SZ_4K)) / 2) + 1; >>>> + >>>> + /* Determine what level the granule is at */ >>>> + cmd.tlbi.ttl = 4 - ((ilog2(granule) - 3) / (tg - 3)); >>>> + >>>> + /* Adjust granule to the maximum range */ >>>> + granule = CMDQ_TLBI_RANGE_NUM_MAX * (1 << scale) * (1UL << tg); >>> spec says >>> Range = ((NUM+1)*2 ^ SCALE )*Translation_Granule_Size >> >> (NUM+1) can be 1-32. I went with the logical max for >> CMDQ_TLBI_RANGE_NUM_MAX rather than the NUM field value max. >> >> Rob >> >> _______________________________________________ >> linux-arm-kernel mailing list >> linux-arm-kernel@lists.infradead.org >> http://lists.infradead.org/mailman/listinfo/linux-arm-kernel >> >
On Wed, Jan 15, 2020 at 10:33 AM Auger Eric <eric.auger@redhat.com> wrote: > > Hi Rob, > > On 1/15/20 3:02 PM, Rob Herring wrote: > > On Wed, Jan 15, 2020 at 3:21 AM Auger Eric <eric.auger@redhat.com> wrote: > >> > >> Hi Rob, > >> > >> On 1/13/20 3:39 PM, Rob Herring wrote: > >>> Arm SMMUv3.2 adds support for TLB range invalidate operations. > >>> Support for range invalidate is determined by the RIL bit in the IDR3 > >>> register. > >>> > >>> The range invalidate is in units of the leaf page size and operates on > >>> 1-32 chunks of a power of 2 multiple pages. First we determine from the > >>> size what power of 2 multiple we can use and then adjust the granule to > >>> 32x that size. > >>> @@ -2022,12 +2043,39 @@ static void arm_smmu_tlb_inv_range(unsigned long iova, size_t size, > >>> cmd.tlbi.vmid = smmu_domain->s2_cfg.vmid; > >>> } > >>> > >>> + if (smmu->features & ARM_SMMU_FEAT_RANGE_INV) { > >>> + unsigned long tg, scale; > >>> + > >>> + /* Get the leaf page size */ > >>> + tg = __ffs(smmu_domain->domain.pgsize_bitmap); > >> it is unclear to me why you can't set tg with the granule parameter. > > > > granule could be 2MB sections if THP is enabled, right? > > Ah OK I thought it was a page size and not a block size. > > I requested this feature a long time ago for virtual SMMUv3. With > DPDK/VFIO the guest was sending page TLB invalidation for each page > (granule=4K or 64K) part of the hugepage buffer and those were trapped > by the VMM. This stalled qemu. I did some more testing to make sure THP is enabled, but haven't been able to get granule to be anything but 4K. I only have the Fast Model with AHCI on PCI to test this with. Maybe I'm hitting some place where THPs aren't supported yet. > >>> + /* Determine the power of 2 multiple number of pages */ > >>> + scale = __ffs(size / (1UL << tg)); > >>> + cmd.tlbi.scale = scale; > >>> + > >>> + cmd.tlbi.num = CMDQ_TLBI_RANGE_NUM_MAX - 1; > >> Also could you explain why you use CMDQ_TLBI_RANGE_NUM_MAX. > > > > How's this: > > /* The invalidation loop defaults to the maximum range */ > I would have expected num=0 directly. Don't we invalidate the &size in > one shot as 2^scale * pages of granularity @tg? I fail to understand > when NUM > 0. NUM is > 0 anytime size is not a power of 2. For example, if size is 33 pages, then it takes 2 loops doing 32 pages and then 1 page. If size is 34 pages, then NUM is (17-1) and SCALE is 1. Rob
Hi Rob, On 1/16/20 5:57 PM, Rob Herring wrote: > On Wed, Jan 15, 2020 at 10:33 AM Auger Eric <eric.auger@redhat.com> wrote: >> >> Hi Rob, >> >> On 1/15/20 3:02 PM, Rob Herring wrote: >>> On Wed, Jan 15, 2020 at 3:21 AM Auger Eric <eric.auger@redhat.com> wrote: >>>> >>>> Hi Rob, >>>> >>>> On 1/13/20 3:39 PM, Rob Herring wrote: >>>>> Arm SMMUv3.2 adds support for TLB range invalidate operations. >>>>> Support for range invalidate is determined by the RIL bit in the IDR3 >>>>> register. >>>>> >>>>> The range invalidate is in units of the leaf page size and operates on >>>>> 1-32 chunks of a power of 2 multiple pages. First we determine from the >>>>> size what power of 2 multiple we can use and then adjust the granule to >>>>> 32x that size. > >>>>> @@ -2022,12 +2043,39 @@ static void arm_smmu_tlb_inv_range(unsigned long iova, size_t size, >>>>> cmd.tlbi.vmid = smmu_domain->s2_cfg.vmid; >>>>> } >>>>> >>>>> + if (smmu->features & ARM_SMMU_FEAT_RANGE_INV) { >>>>> + unsigned long tg, scale; >>>>> + >>>>> + /* Get the leaf page size */ >>>>> + tg = __ffs(smmu_domain->domain.pgsize_bitmap); >>>> it is unclear to me why you can't set tg with the granule parameter. >>> >>> granule could be 2MB sections if THP is enabled, right? >> >> Ah OK I thought it was a page size and not a block size. >> >> I requested this feature a long time ago for virtual SMMUv3. With >> DPDK/VFIO the guest was sending page TLB invalidation for each page >> (granule=4K or 64K) part of the hugepage buffer and those were trapped >> by the VMM. This stalled qemu. > > I did some more testing to make sure THP is enabled, but haven't been > able to get granule to be anything but 4K. I only have the Fast Model > with AHCI on PCI to test this with. Maybe I'm hitting some place where > THPs aren't supported yet. > >>>>> + /* Determine the power of 2 multiple number of pages */ >>>>> + scale = __ffs(size / (1UL << tg)); >>>>> + cmd.tlbi.scale = scale; >>>>> + >>>>> + cmd.tlbi.num = CMDQ_TLBI_RANGE_NUM_MAX - 1; >>>> Also could you explain why you use CMDQ_TLBI_RANGE_NUM_MAX. >>> >>> How's this: >>> /* The invalidation loop defaults to the maximum range */ >> I would have expected num=0 directly. Don't we invalidate the &size in >> one shot as 2^scale * pages of granularity @tg? I fail to understand >> when NUM > 0. > > NUM is > 0 anytime size is not a power of 2. For example, if size is > 33 pages, then it takes 2 loops doing 32 pages and then 1 page. If > size is 34 pages, then NUM is (17-1) and SCALE is 1. OK I get it now. I misread the scale computation as log2() :-(. I still have a doubt about the scale choice. What if you invalidate a large number of pages such as 1025 pages. scale is 0 and you end up with 32 * 32 * 2^0 + 1 * 2 * 2^0 invalidations (33). Whereas you could invalidate the whole range with 2 invalidation commands: 1 x 2^10 + 1*1^1 (packing the invalidations by largest scale). Am I correct or do I still miss something? Besides in the patch I think in the while loop the iova should be incremented with the actual number of invalidated bytes and not the max sized granule variable. Thanks Eric > > Rob > > _______________________________________________ > linux-arm-kernel mailing list > linux-arm-kernel@lists.infradead.org > http://lists.infradead.org/mailman/listinfo/linux-arm-kernel >
On Thu, Jan 16, 2020 at 3:23 PM Auger Eric <eric.auger@redhat.com> wrote: > > Hi Rob, > > On 1/16/20 5:57 PM, Rob Herring wrote: > > On Wed, Jan 15, 2020 at 10:33 AM Auger Eric <eric.auger@redhat.com> wrote: > >> > >> Hi Rob, > >> > >> On 1/15/20 3:02 PM, Rob Herring wrote: > >>> On Wed, Jan 15, 2020 at 3:21 AM Auger Eric <eric.auger@redhat.com> wrote: > >>>> > >>>> Hi Rob, > >>>> > >>>> On 1/13/20 3:39 PM, Rob Herring wrote: > >>>>> Arm SMMUv3.2 adds support for TLB range invalidate operations. > >>>>> Support for range invalidate is determined by the RIL bit in the IDR3 > >>>>> register. > >>>>> > >>>>> The range invalidate is in units of the leaf page size and operates on > >>>>> 1-32 chunks of a power of 2 multiple pages. First we determine from the > >>>>> size what power of 2 multiple we can use and then adjust the granule to > >>>>> 32x that size. > > > >>>>> @@ -2022,12 +2043,39 @@ static void arm_smmu_tlb_inv_range(unsigned long iova, size_t size, > >>>>> cmd.tlbi.vmid = smmu_domain->s2_cfg.vmid; > >>>>> } > >>>>> > >>>>> + if (smmu->features & ARM_SMMU_FEAT_RANGE_INV) { > >>>>> + unsigned long tg, scale; > >>>>> + > >>>>> + /* Get the leaf page size */ > >>>>> + tg = __ffs(smmu_domain->domain.pgsize_bitmap); > >>>> it is unclear to me why you can't set tg with the granule parameter. > >>> > >>> granule could be 2MB sections if THP is enabled, right? > >> > >> Ah OK I thought it was a page size and not a block size. > >> > >> I requested this feature a long time ago for virtual SMMUv3. With > >> DPDK/VFIO the guest was sending page TLB invalidation for each page > >> (granule=4K or 64K) part of the hugepage buffer and those were trapped > >> by the VMM. This stalled qemu. > > > > I did some more testing to make sure THP is enabled, but haven't been > > able to get granule to be anything but 4K. I only have the Fast Model > > with AHCI on PCI to test this with. Maybe I'm hitting some place where > > THPs aren't supported yet. > > > >>>>> + /* Determine the power of 2 multiple number of pages */ > >>>>> + scale = __ffs(size / (1UL << tg)); > >>>>> + cmd.tlbi.scale = scale; > >>>>> + > >>>>> + cmd.tlbi.num = CMDQ_TLBI_RANGE_NUM_MAX - 1; > >>>> Also could you explain why you use CMDQ_TLBI_RANGE_NUM_MAX. > >>> > >>> How's this: > >>> /* The invalidation loop defaults to the maximum range */ > >> I would have expected num=0 directly. Don't we invalidate the &size in > >> one shot as 2^scale * pages of granularity @tg? I fail to understand > >> when NUM > 0. > > > > NUM is > 0 anytime size is not a power of 2. For example, if size is > > 33 pages, then it takes 2 loops doing 32 pages and then 1 page. If > > size is 34 pages, then NUM is (17-1) and SCALE is 1. > OK I get it now. I misread the scale computation as log2() :-(. > > I still have a doubt about the scale choice. What if you invalidate a > large number of pages such as 1025 pages. scale is 0 and you end up with > 32 * 32 * 2^0 + 1 * 2 * 2^0 invalidations (33). Whereas you could > invalidate the whole range with 2 invalidation commands: 1 x 2^10 + > 1*1^1 (packing the invalidations by largest scale). Am I correct or do I > still miss something? No, that's correct. 33 is a lot better than 1025 though. :) 1023 pages is about the worst case if we assume we get 2MB blocks, but maybe not a good assumption given our testing so far... So thinking out loud, I guess we could iterate on power of 2 chunks of size (in units of pages) like this: while (size) { scale = fls(size); range = 1 << scale; size &= ~range; iova += range; } But that means NUM is always 0, so also not ideal. So we need to extract 5 bits from size for NUM on each iteration: while (size) { scale = __ffs(size); num = (size >> scale)) & 0x1f; size -= (num + 1) * (1 << scale); ... } So worst case, we'd have 4 invalidates for up to 4G. > Besides in the patch I think in the while loop the iova should be > incremented with the actual number of invalidated bytes and not the max > sized granule variable. Ok. Rob
diff --git a/drivers/iommu/arm-smmu-v3.c b/drivers/iommu/arm-smmu-v3.c index e91b4a098215..8b6b3e2aa383 100644 --- a/drivers/iommu/arm-smmu-v3.c +++ b/drivers/iommu/arm-smmu-v3.c @@ -70,6 +70,9 @@ #define IDR1_SSIDSIZE GENMASK(10, 6) #define IDR1_SIDSIZE GENMASK(5, 0) +#define ARM_SMMU_IDR3 0xc +#define IDR3_RIL (1 << 10) + #define ARM_SMMU_IDR5 0x14 #define IDR5_STALL_MAX GENMASK(31, 16) #define IDR5_GRAN64K (1 << 6) @@ -327,9 +330,14 @@ #define CMDQ_CFGI_1_LEAF (1UL << 0) #define CMDQ_CFGI_1_RANGE GENMASK_ULL(4, 0) +#define CMDQ_TLBI_0_NUM GENMASK_ULL(16, 12) +#define CMDQ_TLBI_RANGE_NUM_MAX 32 +#define CMDQ_TLBI_0_SCALE GENMASK_ULL(24, 20) #define CMDQ_TLBI_0_VMID GENMASK_ULL(47, 32) #define CMDQ_TLBI_0_ASID GENMASK_ULL(63, 48) #define CMDQ_TLBI_1_LEAF (1UL << 0) +#define CMDQ_TLBI_1_TTL GENMASK_ULL(9, 8) +#define CMDQ_TLBI_1_TG GENMASK_ULL(11, 10) #define CMDQ_TLBI_1_VA_MASK GENMASK_ULL(63, 12) #define CMDQ_TLBI_1_IPA_MASK GENMASK_ULL(51, 12) @@ -455,9 +463,13 @@ struct arm_smmu_cmdq_ent { #define CMDQ_OP_TLBI_S2_IPA 0x2a #define CMDQ_OP_TLBI_NSNH_ALL 0x30 struct { + u8 num; + u8 scale; u16 asid; u16 vmid; bool leaf; + u8 ttl; + u8 tg; u64 addr; } tlbi; @@ -595,6 +607,7 @@ struct arm_smmu_device { #define ARM_SMMU_FEAT_HYP (1 << 12) #define ARM_SMMU_FEAT_STALL_FORCE (1 << 13) #define ARM_SMMU_FEAT_VAX (1 << 14) +#define ARM_SMMU_FEAT_RANGE_INV (1 << 15) u32 features; #define ARM_SMMU_OPT_SKIP_PREFETCH (1 << 0) @@ -856,13 +869,21 @@ static int arm_smmu_cmdq_build_cmd(u64 *cmd, struct arm_smmu_cmdq_ent *ent) cmd[1] |= FIELD_PREP(CMDQ_CFGI_1_RANGE, 31); break; case CMDQ_OP_TLBI_NH_VA: + cmd[0] |= FIELD_PREP(CMDQ_TLBI_0_NUM, ent->tlbi.num); + cmd[0] |= FIELD_PREP(CMDQ_TLBI_0_SCALE, ent->tlbi.scale); cmd[0] |= FIELD_PREP(CMDQ_TLBI_0_ASID, ent->tlbi.asid); cmd[1] |= FIELD_PREP(CMDQ_TLBI_1_LEAF, ent->tlbi.leaf); + cmd[1] |= FIELD_PREP(CMDQ_TLBI_1_TTL, ent->tlbi.ttl); + cmd[1] |= FIELD_PREP(CMDQ_TLBI_1_TG, ent->tlbi.tg); cmd[1] |= ent->tlbi.addr & CMDQ_TLBI_1_VA_MASK; break; case CMDQ_OP_TLBI_S2_IPA: + cmd[0] |= FIELD_PREP(CMDQ_TLBI_0_NUM, ent->tlbi.num); + cmd[0] |= FIELD_PREP(CMDQ_TLBI_0_SCALE, ent->tlbi.scale); cmd[0] |= FIELD_PREP(CMDQ_TLBI_0_VMID, ent->tlbi.vmid); cmd[1] |= FIELD_PREP(CMDQ_TLBI_1_LEAF, ent->tlbi.leaf); + cmd[1] |= FIELD_PREP(CMDQ_TLBI_1_TTL, ent->tlbi.ttl); + cmd[1] |= FIELD_PREP(CMDQ_TLBI_1_TG, ent->tlbi.tg); cmd[1] |= ent->tlbi.addr & CMDQ_TLBI_1_IPA_MASK; break; case CMDQ_OP_TLBI_NH_ASID: @@ -2022,12 +2043,39 @@ static void arm_smmu_tlb_inv_range(unsigned long iova, size_t size, cmd.tlbi.vmid = smmu_domain->s2_cfg.vmid; } + if (smmu->features & ARM_SMMU_FEAT_RANGE_INV) { + unsigned long tg, scale; + + /* Get the leaf page size */ + tg = __ffs(smmu_domain->domain.pgsize_bitmap); + + /* Determine the power of 2 multiple number of pages */ + scale = __ffs(size / (1UL << tg)); + cmd.tlbi.scale = scale; + + cmd.tlbi.num = CMDQ_TLBI_RANGE_NUM_MAX - 1; + + /* Convert page size of 12,14,16 (log2) to 1,2,3 */ + cmd.tlbi.tg = ((tg - ilog2(SZ_4K)) / 2) + 1; + + /* Determine what level the granule is at */ + cmd.tlbi.ttl = 4 - ((ilog2(granule) - 3) / (tg - 3)); + + /* Adjust granule to the maximum range */ + granule = CMDQ_TLBI_RANGE_NUM_MAX * (1 << scale) * (1UL << tg); + } + while (iova < end) { if (i == CMDQ_BATCH_ENTRIES) { arm_smmu_cmdq_issue_cmdlist(smmu, cmds, i, false); i = 0; } + /* Only possible for range invalidate */ + if (granule > (end - iova)) + cmd.tlbi.num = ((end - iova) / + (granule / CMDQ_TLBI_RANGE_NUM_MAX)) - 1; + cmd.tlbi.addr = iova; arm_smmu_cmdq_build_cmd(&cmds[i * CMDQ_ENT_DWORDS], &cmd); iova += granule; @@ -3449,6 +3497,11 @@ static int arm_smmu_device_hw_probe(struct arm_smmu_device *smmu) if (smmu->sid_bits <= STRTAB_SPLIT) smmu->features &= ~ARM_SMMU_FEAT_2_LVL_STRTAB; + /* IDR3 */ + reg = readl_relaxed(smmu->base + ARM_SMMU_IDR3); + if (FIELD_GET(IDR3_RIL, reg)) + smmu->features |= ARM_SMMU_FEAT_RANGE_INV; + /* IDR5 */ reg = readl_relaxed(smmu->base + ARM_SMMU_IDR5);
Arm SMMUv3.2 adds support for TLB range invalidate operations. Support for range invalidate is determined by the RIL bit in the IDR3 register. The range invalidate is in units of the leaf page size and operates on 1-32 chunks of a power of 2 multiple pages. First we determine from the size what power of 2 multiple we can use and then adjust the granule to 32x that size. Cc: Eric Auger <eric.auger@redhat.com> Cc: Jean-Philippe Brucker <jean-philippe@linaro.org> Cc: Will Deacon <will@kernel.org> Cc: Robin Murphy <robin.murphy@arm.com> Cc: Joerg Roedel <joro@8bytes.org> Signed-off-by: Rob Herring <robh@kernel.org> --- drivers/iommu/arm-smmu-v3.c | 53 +++++++++++++++++++++++++++++++++++++ 1 file changed, 53 insertions(+)