Hi Jean,
On 8/17/20 7:15 PM, Jean-Philippe Brucker wrote:
> The SMMU has a single ASID space, the union of shared and private ASID
> sets. This means that the SMMU driver competes with the arch allocator
> for ASIDs. Shared ASIDs are those of Linux processes, allocated by the
> arch, and contribute in broadcast TLB maintenance. Private ASIDs are
> allocated by the SMMU driver and used for "classic" map/unmap DMA. They
> require command-queue TLB invalidations.
>
> When we pin down an mm_context and get an ASID that is already in use by
> the SMMU, it belongs to a private context. We used to simply abort the
> bind, but this is unfair to users that would be unable to bind a few
> seemingly random processes. Try to allocate a new private ASID for the
> context, and make the old ASID shared.
>
> Signed-off-by: Jean-Philippe Brucker <jean-philippe@xxxxxxxxxx>
> ---
> drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h | 3 ++
> .../iommu/arm/arm-smmu-v3/arm-smmu-v3-sva.c | 36 +++++++++++++++++--
> drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c | 34 +++++++++++-------
> 3 files changed, 58 insertions(+), 15 deletions(-)
>
> 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 6b06a6f19604..90c08f156b43 100644
> --- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h
> +++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h
> @@ -678,6 +678,9 @@ struct arm_smmu_domain {
> extern struct xarray arm_smmu_asid_xa;
> extern struct mutex arm_smmu_asid_lock;
>
> +int arm_smmu_write_ctx_desc(struct arm_smmu_domain *smmu_domain, int ssid,
> + struct arm_smmu_ctx_desc *cd);
> +void arm_smmu_tlb_inv_asid(struct arm_smmu_device *smmu, u16 asid);
> bool arm_smmu_free_asid(struct arm_smmu_ctx_desc *cd);
>
> #endif /* _ARM_SMMU_V3_H */
> diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-sva.c b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-sva.c
> index 7a4f40565e06..e919ce894dd1 100644
> --- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-sva.c
> +++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-sva.c
> @@ -10,10 +10,19 @@
> #include "arm-smmu-v3.h"
> #include "../../io-pgtable-arm.h"
>
> +/*
> + * Try to reserve this ASID in the SMMU. If it is in use, try to steal it from
> + * the private entry. Careful here, we may be modifying the context tables of
> + * another SMMU!
Not sure I got what you meant by this comment.
> + */
> static struct arm_smmu_ctx_desc *
> arm_smmu_share_asid(struct mm_struct *mm, u16 asid)
> {
> + int ret;
> + u32 new_asid;
> struct arm_smmu_ctx_desc *cd;
> + struct arm_smmu_device *smmu;
> + struct arm_smmu_domain *smmu_domain;
>
> cd = xa_load(&arm_smmu_asid_xa, asid);
> if (!cd)
> @@ -27,8 +36,31 @@ arm_smmu_share_asid(struct mm_struct *mm, u16 asid)
> return cd;
> }
>
> - /* Ouch, ASID is already in use for a private cd. */
> - return ERR_PTR(-EBUSY);
> + smmu_domain = container_of(cd, struct arm_smmu_domain, s1_cfg.cd);
> + smmu = smmu_domain->smmu;
> +
> + ret = xa_alloc(&arm_smmu_asid_xa, &new_asid, cd,
> + XA_LIMIT(1, 1 << smmu->asid_bits), GFP_KERNEL);
XA_LIMIT(1, (1 << smmu->asid_bits) - 1), GFP_KERNEL)
> + if (ret)
> + return ERR_PTR(-ENOSPC);
> + /*
> + * Race with unmap: TLB invalidations will start targeting the new ASID,
> + * which isn't assigned yet. We'll do an invalidate-all on the old ASID
> + * later, so it doesn't matter.
> + */
> + cd->asid = new_asid;
> + /*
> + * Update ASID and invalidate CD in all associated masters. There will
> + * be some overlap between use of both ASIDs, until we invalidate the
> + * TLB.
> + */
> + arm_smmu_write_ctx_desc(smmu_domain, 0, cd);
> +
> + /* Invalidate TLB entries previously associated with that context */
> + arm_smmu_tlb_inv_asid(smmu, asid);
> +
> + xa_erase(&arm_smmu_asid_xa, asid);
> + return NULL;
> }
>
> __maybe_unused
> 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 9e81615744de..9e755caea525 100644
> --- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
> +++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
> @@ -873,6 +873,17 @@ static int arm_smmu_cmdq_batch_submit(struct arm_smmu_device *smmu,
> }
>
> /* Context descriptor manipulation functions */
> +void arm_smmu_tlb_inv_asid(struct arm_smmu_device *smmu, u16 asid)
> +{
> + struct arm_smmu_cmdq_ent cmd = {
> + .opcode = CMDQ_OP_TLBI_NH_ASID,
> + .tlbi.asid = asid,
> + };
> +
> + arm_smmu_cmdq_issue_cmd(smmu, &cmd);
> + arm_smmu_cmdq_issue_sync(smmu);
> +}
> +
> static void arm_smmu_sync_cd(struct arm_smmu_domain *smmu_domain,
> int ssid, bool leaf)
> {
> @@ -953,8 +964,8 @@ static __le64 *arm_smmu_get_cd_ptr(struct arm_smmu_domain *smmu_domain,
> return l1_desc->l2ptr + idx * CTXDESC_CD_DWORDS;
> }
>
> -static int arm_smmu_write_ctx_desc(struct arm_smmu_domain *smmu_domain,
> - int ssid, struct arm_smmu_ctx_desc *cd)
> +int arm_smmu_write_ctx_desc(struct arm_smmu_domain *smmu_domain, int ssid,
> + struct arm_smmu_ctx_desc *cd)
> {
> /*
> * This function handles the following cases:
> @@ -1610,15 +1621,6 @@ static void arm_smmu_tlb_inv_context(void *cookie)
> struct arm_smmu_device *smmu = smmu_domain->smmu;
> struct arm_smmu_cmdq_ent cmd;
>
> - if (smmu_domain->stage == ARM_SMMU_DOMAIN_S1) {
> - cmd.opcode = CMDQ_OP_TLBI_NH_ASID;
> - cmd.tlbi.asid = smmu_domain->s1_cfg.cd.asid;
> - cmd.tlbi.vmid = 0;
> - } else {
> - cmd.opcode = CMDQ_OP_TLBI_S12_VMALL;
> - cmd.tlbi.vmid = smmu_domain->s2_cfg.vmid;
> - }
> -
> /*
> * NOTE: when io-pgtable is in non-strict mode, we may get here with
> * PTEs previously cleared by unmaps on the current CPU not yet visible
> @@ -1626,8 +1628,14 @@ static void arm_smmu_tlb_inv_context(void *cookie)
> * insertion to guarantee those are observed before the TLBI. Do be
> * careful, 007.
> */
> - arm_smmu_cmdq_issue_cmd(smmu, &cmd);
> - arm_smmu_cmdq_issue_sync(smmu);
> + if (smmu_domain->stage == ARM_SMMU_DOMAIN_S1) {
> + arm_smmu_tlb_inv_asid(smmu, smmu_domain->s1_cfg.cd.asid);
> + } else {
> + cmd.opcode = CMDQ_OP_TLBI_S12_VMALL;
> + cmd.tlbi.vmid = smmu_domain->s2_cfg.vmid;
> + arm_smmu_cmdq_issue_cmd(smmu, &cmd);
> + arm_smmu_cmdq_issue_sync(smmu);
> + }
> arm_smmu_atc_inv_domain(smmu_domain, 0, 0, 0);
> }
>
>
Thanks
Eric
