diff mbox series

[v9,10/10] iommu/arm-smmu-v3: Add stall support for platform devices

Message ID 20210108145217.2254447-11-jean-philippe@linaro.org
State New
Headers show
Series iommu: I/O page faults for SMMUv3 | expand

Commit Message

Jean-Philippe Brucker Jan. 8, 2021, 2:52 p.m. UTC
The SMMU provides a Stall model for handling page faults in platform
devices. It is similar to PCIe PRI, but doesn't require devices to have
their own translation cache. Instead, faulting transactions are parked
and the OS is given a chance to fix the page tables and retry the
transaction.

Enable stall for devices that support it (opt-in by firmware). When an
event corresponds to a translation error, call the IOMMU fault handler.
If the fault is recoverable, it will call us back to terminate or
continue the stall.

To use stall device drivers need to enable IOMMU_DEV_FEAT_IOPF, which
initializes the fault queue for the device.

Signed-off-by: Jean-Philippe Brucker <jean-philippe@linaro.org>
---
v9: Add IOMMU_DEV_FEAT_IOPF
---
 drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h   |  61 ++++++
 .../iommu/arm/arm-smmu-v3/arm-smmu-v3-sva.c   |  70 ++++++-
 drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c   | 192 ++++++++++++++++--
 3 files changed, 306 insertions(+), 17 deletions(-)

Comments

Robin Murphy Jan. 19, 2021, 5:28 p.m. UTC | #1
On 2021-01-08 14:52, Jean-Philippe Brucker wrote:
> The SMMU provides a Stall model for handling page faults in platform
> devices. It is similar to PCIe PRI, but doesn't require devices to have
> their own translation cache. Instead, faulting transactions are parked
> and the OS is given a chance to fix the page tables and retry the
> transaction.
> 
> Enable stall for devices that support it (opt-in by firmware). When an
> event corresponds to a translation error, call the IOMMU fault handler.
> If the fault is recoverable, it will call us back to terminate or
> continue the stall.
> 
> To use stall device drivers need to enable IOMMU_DEV_FEAT_IOPF, which
> initializes the fault queue for the device.
> 
> Signed-off-by: Jean-Philippe Brucker <jean-philippe@linaro.org>
> ---
> v9: Add IOMMU_DEV_FEAT_IOPF
> ---
>   drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h   |  61 ++++++
>   .../iommu/arm/arm-smmu-v3/arm-smmu-v3-sva.c   |  70 ++++++-
>   drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c   | 192 ++++++++++++++++--
>   3 files changed, 306 insertions(+), 17 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 8ef6a1c48635..cb129870ef55 100644
> --- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h
> +++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h
> @@ -354,6 +354,13 @@
>   #define CMDQ_PRI_1_GRPID		GENMASK_ULL(8, 0)
>   #define CMDQ_PRI_1_RESP			GENMASK_ULL(13, 12)
>   
> +#define CMDQ_RESUME_0_SID		GENMASK_ULL(63, 32)
> +#define CMDQ_RESUME_0_RESP_TERM		0UL
> +#define CMDQ_RESUME_0_RESP_RETRY	1UL
> +#define CMDQ_RESUME_0_RESP_ABORT	2UL
> +#define CMDQ_RESUME_0_RESP		GENMASK_ULL(13, 12)

Nit: I think the SID field belongs here.

> +#define CMDQ_RESUME_1_STAG		GENMASK_ULL(15, 0)
> +
>   #define CMDQ_SYNC_0_CS			GENMASK_ULL(13, 12)
>   #define CMDQ_SYNC_0_CS_NONE		0
>   #define CMDQ_SYNC_0_CS_IRQ		1
> @@ -370,6 +377,25 @@
>   
>   #define EVTQ_0_ID			GENMASK_ULL(7, 0)
>   
> +#define EVT_ID_TRANSLATION_FAULT	0x10
> +#define EVT_ID_ADDR_SIZE_FAULT		0x11
> +#define EVT_ID_ACCESS_FAULT		0x12
> +#define EVT_ID_PERMISSION_FAULT		0x13
> +
> +#define EVTQ_0_SSV			(1UL << 11)
> +#define EVTQ_0_SSID			GENMASK_ULL(31, 12)
> +#define EVTQ_0_SID			GENMASK_ULL(63, 32)
> +#define EVTQ_1_STAG			GENMASK_ULL(15, 0)
> +#define EVTQ_1_STALL			(1UL << 31)
> +#define EVTQ_1_PRIV			(1UL << 33)
> +#define EVTQ_1_EXEC			(1UL << 34)
> +#define EVTQ_1_READ			(1UL << 35)

Nit: personally I'd find it a little clearer if these were named PnU, 
InD, and RnW to match the architecture, but quite possibly that's just 
me and those are gibberish to everyone else...

> +#define EVTQ_1_S2			(1UL << 39)
> +#define EVTQ_1_CLASS			GENMASK_ULL(41, 40)
> +#define EVTQ_1_TT_READ			(1UL << 44)
> +#define EVTQ_2_ADDR			GENMASK_ULL(63, 0)
> +#define EVTQ_3_IPA			GENMASK_ULL(51, 12)
> +
>   /* PRI queue */
>   #define PRIQ_ENT_SZ_SHIFT		4
>   #define PRIQ_ENT_DWORDS			((1 << PRIQ_ENT_SZ_SHIFT) >> 3)
> @@ -462,6 +488,13 @@ struct arm_smmu_cmdq_ent {
>   			enum pri_resp		resp;
>   		} pri;
>   
> +		#define CMDQ_OP_RESUME		0x44
> +		struct {
> +			u32			sid;
> +			u16			stag;
> +			u8			resp;
> +		} resume;
> +
>   		#define CMDQ_OP_CMD_SYNC	0x46
>   		struct {
>   			u64			msiaddr;
> @@ -520,6 +553,7 @@ struct arm_smmu_cmdq_batch {
>   
>   struct arm_smmu_evtq {
>   	struct arm_smmu_queue		q;
> +	struct iopf_queue		*iopf;
>   	u32				max_stalls;
>   };
>   
> @@ -656,7 +690,9 @@ struct arm_smmu_master {
>   	struct arm_smmu_stream		*streams;
>   	unsigned int			num_streams;
>   	bool				ats_enabled;
> +	bool				stall_enabled;
>   	bool				sva_enabled;
> +	bool				iopf_enabled;
>   	struct list_head		bonds;
>   	unsigned int			ssid_bits;
>   };
> @@ -675,6 +711,7 @@ struct arm_smmu_domain {
>   
>   	struct io_pgtable_ops		*pgtbl_ops;
>   	bool				non_strict;
> +	bool				stall_enabled;
>   	atomic_t			nr_ats_masters;
>   
>   	enum arm_smmu_domain_stage	stage;
> @@ -713,6 +750,10 @@ bool arm_smmu_master_sva_supported(struct arm_smmu_master *master);
>   bool arm_smmu_master_sva_enabled(struct arm_smmu_master *master);
>   int arm_smmu_master_enable_sva(struct arm_smmu_master *master);
>   int arm_smmu_master_disable_sva(struct arm_smmu_master *master);
> +bool arm_smmu_master_iopf_supported(struct arm_smmu_master *master);
> +bool arm_smmu_master_iopf_enabled(struct arm_smmu_master *master);
> +int arm_smmu_master_enable_iopf(struct arm_smmu_master *master);
> +int arm_smmu_master_disable_iopf(struct arm_smmu_master *master);
>   struct iommu_sva *arm_smmu_sva_bind(struct device *dev, struct mm_struct *mm,
>   				    void *drvdata);
>   void arm_smmu_sva_unbind(struct iommu_sva *handle);
> @@ -744,6 +785,26 @@ static inline int arm_smmu_master_disable_sva(struct arm_smmu_master *master)
>   	return -ENODEV;
>   }
>   
> +static inline bool arm_smmu_master_iopf_supported(struct arm_smmu_master *master)
> +{
> +	return false;
> +}
> +
> +static inline bool arm_smmu_master_iopf_enabled(struct arm_smmu_master *master)
> +{
> +	return false;
> +}
> +
> +static inline int arm_smmu_master_enable_iopf(struct arm_smmu_master *master)
> +{
> +	return -ENODEV;
> +}
> +
> +static inline int arm_smmu_master_disable_iopf(struct arm_smmu_master *master)
> +{
> +	return -ENODEV;
> +}
> +
>   static inline struct iommu_sva *
>   arm_smmu_sva_bind(struct device *dev, struct mm_struct *mm, void *drvdata)
>   {
> 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 e13b092e6004..17acfee4f484 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
> @@ -431,9 +431,9 @@ bool arm_smmu_sva_supported(struct arm_smmu_device *smmu)
>   	return true;
>   }
>   
> -static bool arm_smmu_iopf_supported(struct arm_smmu_master *master)
> +bool arm_smmu_master_iopf_supported(struct arm_smmu_master *master)
>   {
> -	return false;
> +	return master->stall_enabled;
>   }
>   
>   bool arm_smmu_master_sva_supported(struct arm_smmu_master *master)
> @@ -441,8 +441,18 @@ bool arm_smmu_master_sva_supported(struct arm_smmu_master *master)
>   	if (!(master->smmu->features & ARM_SMMU_FEAT_SVA))
>   		return false;
>   
> -	/* SSID and IOPF support are mandatory for the moment */
> -	return master->ssid_bits && arm_smmu_iopf_supported(master);
> +	/* SSID support is mandatory for the moment */
> +	return master->ssid_bits;
> +}
> +
> +bool arm_smmu_master_iopf_enabled(struct arm_smmu_master *master)
> +{
> +	bool enabled;
> +
> +	mutex_lock(&sva_lock);
> +	enabled = master->iopf_enabled;
> +	mutex_unlock(&sva_lock);

Forgive me for being dim, but what's the locking synchronising against 
here? If we're expecting that master->iopf_enabled can change at any 
time, isn't whatever we've read potentially already invalid as soon as 
we've dropped the lock?

> +	return enabled;
>   }
>   
>   bool arm_smmu_master_sva_enabled(struct arm_smmu_master *master)
> @@ -455,15 +465,67 @@ bool arm_smmu_master_sva_enabled(struct arm_smmu_master *master)
>   	return enabled;
>   }
>   
> +int arm_smmu_master_enable_iopf(struct arm_smmu_master *master)
> +{
> +	int ret;
> +	struct device *dev = master->dev;
> +
> +	mutex_lock(&sva_lock);
> +	if (master->stall_enabled) {
> +		ret = iopf_queue_add_device(master->smmu->evtq.iopf, dev);
> +		if (ret)
> +			goto err_unlock;
> +	}
> +
> +	ret = iommu_register_device_fault_handler(dev, iommu_queue_iopf, dev);
> +	if (ret)
> +		goto err_remove_device;
> +	master->iopf_enabled = true;
> +	mutex_unlock(&sva_lock);
> +	return 0;
> +
> +err_remove_device:
> +	iopf_queue_remove_device(master->smmu->evtq.iopf, dev);
> +err_unlock:
> +	mutex_unlock(&sva_lock);
> +	return ret;
> +}
> +
>   int arm_smmu_master_enable_sva(struct arm_smmu_master *master)
>   {
>   	mutex_lock(&sva_lock);
> +	/*
> +	 * Drivers for devices supporting PRI or stall should enable IOPF first.
> +	 * Others have device-specific fault handlers and don't need IOPF, so
> +	 * this sanity check is a bit basic.
> +	 */
> +	if (arm_smmu_master_iopf_supported(master) && !master->iopf_enabled) {
> +		mutex_unlock(&sva_lock);
> +		return -EINVAL;
> +	}
>   	master->sva_enabled = true;
>   	mutex_unlock(&sva_lock);
>   
>   	return 0;
>   }
>   
> +int arm_smmu_master_disable_iopf(struct arm_smmu_master *master)
> +{
> +	struct device *dev = master->dev;
> +
> +	mutex_lock(&sva_lock);
> +	if (master->sva_enabled) {
> +		mutex_unlock(&sva_lock);
> +		return -EBUSY;
> +	}
> +
> +	iommu_unregister_device_fault_handler(dev);
> +	iopf_queue_remove_device(master->smmu->evtq.iopf, dev);
> +	master->iopf_enabled = false;
> +	mutex_unlock(&sva_lock);
> +	return 0;
> +}
> +
>   int arm_smmu_master_disable_sva(struct arm_smmu_master *master)
>   {
>   	mutex_lock(&sva_lock);
> 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 2dbae2e6965d..1fea11d65cd3 100644
> --- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
> +++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
> @@ -32,6 +32,7 @@
>   #include <linux/amba/bus.h>
>   
>   #include "arm-smmu-v3.h"
> +#include "../../iommu-sva-lib.h"
>   
>   static bool disable_bypass = true;
>   module_param(disable_bypass, bool, 0444);
> @@ -319,6 +320,11 @@ static int arm_smmu_cmdq_build_cmd(u64 *cmd, struct arm_smmu_cmdq_ent *ent)
>   		}
>   		cmd[1] |= FIELD_PREP(CMDQ_PRI_1_RESP, ent->pri.resp);
>   		break;
> +	case CMDQ_OP_RESUME:
> +		cmd[0] |= FIELD_PREP(CMDQ_RESUME_0_SID, ent->resume.sid);
> +		cmd[0] |= FIELD_PREP(CMDQ_RESUME_0_RESP, ent->resume.resp);
> +		cmd[1] |= FIELD_PREP(CMDQ_RESUME_1_STAG, ent->resume.stag);
> +		break;
>   	case CMDQ_OP_CMD_SYNC:
>   		if (ent->sync.msiaddr) {
>   			cmd[0] |= FIELD_PREP(CMDQ_SYNC_0_CS, CMDQ_SYNC_0_CS_IRQ);
> @@ -882,6 +888,44 @@ static int arm_smmu_cmdq_batch_submit(struct arm_smmu_device *smmu,
>   	return arm_smmu_cmdq_issue_cmdlist(smmu, cmds->cmds, cmds->num, true);
>   }
>   
> +static int arm_smmu_page_response(struct device *dev,
> +				  struct iommu_fault_event *unused,
> +				  struct iommu_page_response *resp)
> +{
> +	struct arm_smmu_cmdq_ent cmd = {0};
> +	struct arm_smmu_master *master = dev_iommu_priv_get(dev);
> +	int sid = master->streams[0].id;

If that's going to be the case, should we explicitly prevent 
multi-stream devices from opting in to faults at all?

> +	if (master->stall_enabled) {
> +		cmd.opcode		= CMDQ_OP_RESUME;
> +		cmd.resume.sid		= sid;
> +		cmd.resume.stag		= resp->grpid;
> +		switch (resp->code) {
> +		case IOMMU_PAGE_RESP_INVALID:
> +		case IOMMU_PAGE_RESP_FAILURE:
> +			cmd.resume.resp = CMDQ_RESUME_0_RESP_ABORT;
> +			break;
> +		case IOMMU_PAGE_RESP_SUCCESS:
> +			cmd.resume.resp = CMDQ_RESUME_0_RESP_RETRY;
> +			break;
> +		default:
> +			return -EINVAL;
> +		}
> +	} else {
> +		return -ENODEV;
> +	}
> +
> +	arm_smmu_cmdq_issue_cmd(master->smmu, &cmd);
> +	/*
> +	 * Don't send a SYNC, it doesn't do anything for RESUME or PRI_RESP.
> +	 * RESUME consumption guarantees that the stalled transaction will be
> +	 * terminated... at some point in the future. PRI_RESP is fire and
> +	 * forget.
> +	 */
> +
> +	return 0;
> +}
> +
>   /* Context descriptor manipulation functions */
>   void arm_smmu_tlb_inv_asid(struct arm_smmu_device *smmu, u16 asid)
>   {
> @@ -991,7 +1035,6 @@ int arm_smmu_write_ctx_desc(struct arm_smmu_domain *smmu_domain, int ssid,
>   	u64 val;
>   	bool cd_live;
>   	__le64 *cdptr;
> -	struct arm_smmu_device *smmu = smmu_domain->smmu;
>   
>   	if (WARN_ON(ssid >= (1 << smmu_domain->s1_cfg.s1cdmax)))
>   		return -E2BIG;
> @@ -1036,8 +1079,7 @@ int arm_smmu_write_ctx_desc(struct arm_smmu_domain *smmu_domain, int ssid,
>   			FIELD_PREP(CTXDESC_CD_0_ASID, cd->asid) |
>   			CTXDESC_CD_0_V;
>   
> -		/* STALL_MODEL==0b10 && CD.S==0 is ILLEGAL */
> -		if (smmu->features & ARM_SMMU_FEAT_STALL_FORCE)
> +		if (smmu_domain->stall_enabled)
>   			val |= CTXDESC_CD_0_S;
>   	}
>   
> @@ -1278,7 +1320,7 @@ static void arm_smmu_write_strtab_ent(struct arm_smmu_master *master, u32 sid,
>   			 FIELD_PREP(STRTAB_STE_1_STRW, STRTAB_STE_1_STRW_NSEL1));
>   
>   		if (smmu->features & ARM_SMMU_FEAT_STALLS &&
> -		   !(smmu->features & ARM_SMMU_FEAT_STALL_FORCE))
> +		    !master->stall_enabled)
>   			dst[1] |= cpu_to_le64(STRTAB_STE_1_S1STALLD);
>   
>   		val |= (s1_cfg->cdcfg.cdtab_dma & STRTAB_STE_0_S1CTXPTR_MASK) |
> @@ -1355,7 +1397,6 @@ static int arm_smmu_init_l2_strtab(struct arm_smmu_device *smmu, u32 sid)
>   	return 0;
>   }
>   
> -__maybe_unused
>   static struct arm_smmu_master *
>   arm_smmu_find_master(struct arm_smmu_device *smmu, u32 sid)
>   {
> @@ -1382,9 +1423,96 @@ arm_smmu_find_master(struct arm_smmu_device *smmu, u32 sid)
>   }
>   
>   /* IRQ and event handlers */
> +static int arm_smmu_handle_evt(struct arm_smmu_device *smmu, u64 *evt)
> +{
> +	int ret;
> +	u32 perm = 0;
> +	struct arm_smmu_master *master;
> +	bool ssid_valid = evt[0] & EVTQ_0_SSV;
> +	u8 type = FIELD_GET(EVTQ_0_ID, evt[0]);
> +	u32 sid = FIELD_GET(EVTQ_0_SID, evt[0]);
> +	struct iommu_fault_event fault_evt = { };
> +	struct iommu_fault *flt = &fault_evt.fault;
> +
> +	/* Stage-2 is always pinned at the moment */
> +	if (evt[1] & EVTQ_1_S2)
> +		return -EFAULT;
> +
> +	master = arm_smmu_find_master(smmu, sid);
> +	if (!master)
> +		return -EINVAL;
> +
> +	if (evt[1] & EVTQ_1_READ)
> +		perm |= IOMMU_FAULT_PERM_READ;
> +	else
> +		perm |= IOMMU_FAULT_PERM_WRITE;
> +
> +	if (evt[1] & EVTQ_1_EXEC)
> +		perm |= IOMMU_FAULT_PERM_EXEC;
> +
> +	if (evt[1] & EVTQ_1_PRIV)
> +		perm |= IOMMU_FAULT_PERM_PRIV;
> +
> +	if (evt[1] & EVTQ_1_STALL) {
> +		flt->type = IOMMU_FAULT_PAGE_REQ;
> +		flt->prm = (struct iommu_fault_page_request) {
> +			.flags = IOMMU_FAULT_PAGE_REQUEST_LAST_PAGE,
> +			.grpid = FIELD_GET(EVTQ_1_STAG, evt[1]),
> +			.perm = perm,
> +			.addr = FIELD_GET(EVTQ_2_ADDR, evt[2]),
> +		};
> +
> +		if (ssid_valid) {
> +			flt->prm.flags |= IOMMU_FAULT_PAGE_REQUEST_PASID_VALID;
> +			flt->prm.pasid = FIELD_GET(EVTQ_0_SSID, evt[0]);
> +		}

So if we get a bad ATS request with R=1, or a TLB/CFG conflict or any 
other imp-def event which happens to have bit 95 set, we might try to 
report it as something pageable? I would have thought we should look at 
the event code before *anything* else.

> +	} else {
> +		flt->type = IOMMU_FAULT_DMA_UNRECOV;
> +		flt->event = (struct iommu_fault_unrecoverable) {
> +			.flags = IOMMU_FAULT_UNRECOV_ADDR_VALID |
> +				 IOMMU_FAULT_UNRECOV_FETCH_ADDR_VALID,
> +			.perm = perm,
> +			.addr = FIELD_GET(EVTQ_2_ADDR, evt[2]),
> +			.fetch_addr = FIELD_GET(EVTQ_3_IPA, evt[3]),
> +		};
> +
> +		if (ssid_valid) {
> +			flt->event.flags |= IOMMU_FAULT_UNRECOV_PASID_VALID;
> +			flt->event.pasid = FIELD_GET(EVTQ_0_SSID, evt[0]);
> +		}
> +
> +		switch (type) {
> +		case EVT_ID_TRANSLATION_FAULT:
> +		case EVT_ID_ADDR_SIZE_FAULT:
> +		case EVT_ID_ACCESS_FAULT:
> +			flt->event.reason = IOMMU_FAULT_REASON_PTE_FETCH;
> +			break;
> +		case EVT_ID_PERMISSION_FAULT:
> +			flt->event.reason = IOMMU_FAULT_REASON_PERMISSION;
> +			break;
> +		default:
> +			/* TODO: report other unrecoverable faults. */
> +			return -EFAULT;
> +		}
> +	}
> +
> +	ret = iommu_report_device_fault(master->dev, &fault_evt);
> +	if (ret && flt->type == IOMMU_FAULT_PAGE_REQ) {
> +		/* Nobody cared, abort the access */
> +		struct iommu_page_response resp = {
> +			.pasid		= flt->prm.pasid,
> +			.grpid		= flt->prm.grpid,
> +			.code		= IOMMU_PAGE_RESP_FAILURE,
> +		};
> +		arm_smmu_page_response(master->dev, NULL, &resp);
> +	}
> +
> +	return ret;
> +}
> +
>   static irqreturn_t arm_smmu_evtq_thread(int irq, void *dev)
>   {
> -	int i;
> +	int i, ret;
>   	struct arm_smmu_device *smmu = dev;
>   	struct arm_smmu_queue *q = &smmu->evtq.q;
>   	struct arm_smmu_ll_queue *llq = &q->llq;
> @@ -1394,11 +1522,14 @@ static irqreturn_t arm_smmu_evtq_thread(int irq, void *dev)
>   		while (!queue_remove_raw(q, evt)) {
>   			u8 id = FIELD_GET(EVTQ_0_ID, evt[0]);
>   
> -			dev_info(smmu->dev, "event 0x%02x received:\n", id);
> -			for (i = 0; i < ARRAY_SIZE(evt); ++i)
> -				dev_info(smmu->dev, "\t0x%016llx\n",
> -					 (unsigned long long)evt[i]);
> -
> +			ret = arm_smmu_handle_evt(smmu, evt);
> +			if (ret) {

Maybe make this an "if (!ret) continue;" to save the indentation from 
getting even more out of hand?

> +				dev_info(smmu->dev, "event 0x%02x received:\n",
> +					 id);
> +				for (i = 0; i < ARRAY_SIZE(evt); ++i)
> +					dev_info(smmu->dev, "\t0x%016llx\n",
> +						 (unsigned long long)evt[i]);
> +			}
>   		}
>   
>   		/*
> @@ -1903,6 +2034,8 @@ static int arm_smmu_domain_finalise_s1(struct arm_smmu_domain *smmu_domain,
>   
>   	cfg->s1cdmax = master->ssid_bits;
>   
> +	smmu_domain->stall_enabled = master->stall_enabled;
> +
>   	ret = arm_smmu_alloc_cd_tables(smmu_domain);
>   	if (ret)
>   		goto out_free_asid;
> @@ -2250,6 +2383,12 @@ static int arm_smmu_attach_dev(struct iommu_domain *domain, struct device *dev)
>   			smmu_domain->s1_cfg.s1cdmax, master->ssid_bits);
>   		ret = -EINVAL;
>   		goto out_unlock;
> +	} else if (smmu_domain->stage == ARM_SMMU_DOMAIN_S1 &&
> +		   smmu_domain->stall_enabled != master->stall_enabled) {

I appreciate that it's probably a fair bit more complex, but it would be 
nice to at least plan for resolving this decision later (i.e. at a point 
where a caller shows an interest in actually using stalls) in future. 
Obviously the first devices advertising stall capabilities will be the 
ones that do want to use it for their primary functionality, that are 
driving the work here. However once this all matures, firmwares may 
start annotating any stallable devices as such for completeness, rather 
than assuming any specific usage. At that point it would be a pain if, 
say, assigning two devices to the same VFIO domain for old-fashioned 
pinned DMA, was suddenly prevented for irrelevant reasons just because 
of a DT/IORT update.

> +		dev_err(dev, "cannot attach to stall-%s domain\n",
> +			smmu_domain->stall_enabled ? "enabled" : "disabled");
> +		ret = -EINVAL;
> +		goto out_unlock;
>   	}
>   
>   	master->domain = smmu_domain;
> @@ -2484,6 +2623,11 @@ static struct iommu_device *arm_smmu_probe_device(struct device *dev)
>   		master->ssid_bits = min_t(u8, master->ssid_bits,
>   					  CTXDESC_LINEAR_CDMAX);
>   
> +	if ((smmu->features & ARM_SMMU_FEAT_STALLS &&
> +	     device_property_read_bool(dev, "dma-can-stall")) ||
> +	    smmu->features & ARM_SMMU_FEAT_STALL_FORCE)
> +		master->stall_enabled = true;
> +
>   	return &smmu->iommu;
>   
>   err_free_master:
> @@ -2502,6 +2646,7 @@ static void arm_smmu_release_device(struct device *dev)
>   
>   	master = dev_iommu_priv_get(dev);
>   	WARN_ON(arm_smmu_master_sva_enabled(master));
> +	iopf_queue_remove_device(master->smmu->evtq.iopf, dev);
>   	arm_smmu_detach_dev(master);
>   	arm_smmu_disable_pasid(master);
>   	arm_smmu_remove_master(master);
> @@ -2629,6 +2774,8 @@ static bool arm_smmu_dev_has_feature(struct device *dev,
>   		return false;
>   
>   	switch (feat) {
> +	case IOMMU_DEV_FEAT_IOPF:
> +		return arm_smmu_master_iopf_supported(master);
>   	case IOMMU_DEV_FEAT_SVA:
>   		return arm_smmu_master_sva_supported(master);
>   	default:
> @@ -2645,6 +2792,8 @@ static bool arm_smmu_dev_feature_enabled(struct device *dev,
>   		return false;
>   
>   	switch (feat) {
> +	case IOMMU_DEV_FEAT_IOPF:
> +		return arm_smmu_master_iopf_enabled(master);
>   	case IOMMU_DEV_FEAT_SVA:
>   		return arm_smmu_master_sva_enabled(master);
>   	default:
> @@ -2655,6 +2804,8 @@ static bool arm_smmu_dev_feature_enabled(struct device *dev,
>   static int arm_smmu_dev_enable_feature(struct device *dev,
>   				       enum iommu_dev_features feat)
>   {
> +	struct arm_smmu_master *master = dev_iommu_priv_get(dev);
> +
>   	if (!arm_smmu_dev_has_feature(dev, feat))
>   		return -ENODEV;
>   
> @@ -2662,8 +2813,10 @@ static int arm_smmu_dev_enable_feature(struct device *dev,
>   		return -EBUSY;
>   
>   	switch (feat) {
> +	case IOMMU_DEV_FEAT_IOPF:
> +		return arm_smmu_master_enable_iopf(master);
>   	case IOMMU_DEV_FEAT_SVA:
> -		return arm_smmu_master_enable_sva(dev_iommu_priv_get(dev));
> +		return arm_smmu_master_enable_sva(master);
>   	default:
>   		return -EINVAL;
>   	}
> @@ -2672,12 +2825,16 @@ static int arm_smmu_dev_enable_feature(struct device *dev,
>   static int arm_smmu_dev_disable_feature(struct device *dev,
>   					enum iommu_dev_features feat)
>   {
> +	struct arm_smmu_master *master = dev_iommu_priv_get(dev);
> +
>   	if (!arm_smmu_dev_feature_enabled(dev, feat))
>   		return -EINVAL;
>   
>   	switch (feat) {
> +	case IOMMU_DEV_FEAT_IOPF:
> +		return arm_smmu_master_disable_iopf(master);
>   	case IOMMU_DEV_FEAT_SVA:
> -		return arm_smmu_master_disable_sva(dev_iommu_priv_get(dev));
> +		return arm_smmu_master_disable_sva(master);
>   	default:
>   		return -EINVAL;
>   	}
> @@ -2708,6 +2865,7 @@ static struct iommu_ops arm_smmu_ops = {
>   	.sva_bind		= arm_smmu_sva_bind,
>   	.sva_unbind		= arm_smmu_sva_unbind,
>   	.sva_get_pasid		= arm_smmu_sva_get_pasid,
> +	.page_response		= arm_smmu_page_response,
>   	.pgsize_bitmap		= -1UL, /* Restricted during device attach */
>   };
>   
> @@ -2785,6 +2943,7 @@ static int arm_smmu_cmdq_init(struct arm_smmu_device *smmu)
>   static int arm_smmu_init_queues(struct arm_smmu_device *smmu)
>   {
>   	int ret;
> +	bool sva = arm_smmu_sva_supported(smmu);
>   
>   	/* cmdq */
>   	ret = arm_smmu_init_one_queue(smmu, &smmu->cmdq.q, ARM_SMMU_CMDQ_PROD,
> @@ -2804,6 +2963,12 @@ static int arm_smmu_init_queues(struct arm_smmu_device *smmu)
>   	if (ret)
>   		return ret;
>   
> +	if (sva && smmu->features & ARM_SMMU_FEAT_STALLS) {

Surely you could just test for ARM_SMMU_FEAT_SVA by now rather than go 
through the whole of arm_smmu_sva_supported() again?

Robin.

> +		smmu->evtq.iopf = iopf_queue_alloc(dev_name(smmu->dev));
> +		if (!smmu->evtq.iopf)
> +			return -ENOMEM;
> +	}
> +
>   	/* priq */
>   	if (!(smmu->features & ARM_SMMU_FEAT_PRI))
>   		return 0;
> @@ -3718,6 +3883,7 @@ static int arm_smmu_device_remove(struct platform_device *pdev)
>   	iommu_device_unregister(&smmu->iommu);
>   	iommu_device_sysfs_remove(&smmu->iommu);
>   	arm_smmu_device_disable(smmu);
> +	iopf_queue_free(smmu->evtq.iopf);
>   
>   	return 0;
>   }
>
Jean-Philippe Brucker Jan. 20, 2021, 5:55 p.m. UTC | #2
On Tue, Jan 19, 2021 at 05:28:21PM +0000, Robin Murphy wrote:
> On 2021-01-08 14:52, Jean-Philippe Brucker wrote:
> > +#define EVTQ_1_PRIV			(1UL << 33)
> > +#define EVTQ_1_EXEC			(1UL << 34)
> > +#define EVTQ_1_READ			(1UL << 35)
> 
> Nit: personally I'd find it a little clearer if these were named PnU, InD,
> and RnW to match the architecture, but quite possibly that's just me and
> those are gibberish to everyone else...

No problem, I think it's still decipherable without a spec

> > +bool arm_smmu_master_iopf_enabled(struct arm_smmu_master *master)
> > +{
> > +	bool enabled;
> > +
> > +	mutex_lock(&sva_lock);
> > +	enabled = master->iopf_enabled;
> > +	mutex_unlock(&sva_lock);
> 
> Forgive me for being dim, but what's the locking synchronising against here?
> If we're expecting that master->iopf_enabled can change at any time, isn't
> whatever we've read potentially already invalid as soon as we've dropped the
> lock?

Right, no reason to lock this. I doubt the lock in sva_enabled() is
necessary either, I could remove it in a separate patch.

> > +static int arm_smmu_page_response(struct device *dev,
> > +				  struct iommu_fault_event *unused,
> > +				  struct iommu_page_response *resp)
> > +{
> > +	struct arm_smmu_cmdq_ent cmd = {0};
> > +	struct arm_smmu_master *master = dev_iommu_priv_get(dev);
> > +	int sid = master->streams[0].id;
> 
> If that's going to be the case, should we explicitly prevent multi-stream
> devices from opting in to faults at all?

Sure I'll add a check in iopf_supported(). Dealing with multi-stream
devices should be easy enough (record the incoming SID into
iommu_fault_event and fetch it back here), it just didn't seem necessary
for the moment.

> > +	if (evt[1] & EVTQ_1_STALL) {
> > +		flt->type = IOMMU_FAULT_PAGE_REQ;
> > +		flt->prm = (struct iommu_fault_page_request) {
> > +			.flags = IOMMU_FAULT_PAGE_REQUEST_LAST_PAGE,
> > +			.grpid = FIELD_GET(EVTQ_1_STAG, evt[1]),
> > +			.perm = perm,
> > +			.addr = FIELD_GET(EVTQ_2_ADDR, evt[2]),
> > +		};
> > +
> > +		if (ssid_valid) {
> > +			flt->prm.flags |= IOMMU_FAULT_PAGE_REQUEST_PASID_VALID;
> > +			flt->prm.pasid = FIELD_GET(EVTQ_0_SSID, evt[0]);
> > +		}
> 
> So if we get a bad ATS request with R=1, or a TLB/CFG conflict or any other
> imp-def event which happens to have bit 95 set, we might try to report it as
> something pageable? I would have thought we should look at the event code
> before *anything* else.

Yes I definitely need to fix this

> > @@ -2250,6 +2383,12 @@ static int arm_smmu_attach_dev(struct iommu_domain *domain, struct device *dev)
> >   			smmu_domain->s1_cfg.s1cdmax, master->ssid_bits);
> >   		ret = -EINVAL;
> >   		goto out_unlock;
> > +	} else if (smmu_domain->stage == ARM_SMMU_DOMAIN_S1 &&
> > +		   smmu_domain->stall_enabled != master->stall_enabled) {
> 
> I appreciate that it's probably a fair bit more complex, but it would be
> nice to at least plan for resolving this decision later (i.e. at a point
> where a caller shows an interest in actually using stalls) in future.
> Obviously the first devices advertising stall capabilities will be the ones
> that do want to use it for their primary functionality, that are driving the
> work here. However once this all matures, firmwares may start annotating any
> stallable devices as such for completeness, rather than assuming any
> specific usage. At that point it would be a pain if, say, assigning two
> devices to the same VFIO domain for old-fashioned pinned DMA, was suddenly
> prevented for irrelevant reasons just because of a DT/IORT update.

It is more complex but possible. Device drivers signal their intent to use
stall by enabling IOMMU_DEV_FEAT_IOPF, so we can postpone setting CD.S
until then. We'll still need to make sure all devices attached to a domain
support it, and prevent attaching a device that can't handle stall to a
stall-enabled domain since it would inherit all CDs. Then there will be
drivers wanting to receive stall events for context #0 and handle them by
issuing iommu_map() calls (unpinned VFIO, mentioned by Baolu on patch
3). That requires setting and clearing CD.S live. So it is doable but I'd
rather leave it for later.

> > @@ -2785,6 +2943,7 @@ static int arm_smmu_cmdq_init(struct arm_smmu_device *smmu)
> >   static int arm_smmu_init_queues(struct arm_smmu_device *smmu)
> >   {
> >   	int ret;
> > +	bool sva = arm_smmu_sva_supported(smmu);
> >   	/* cmdq */
> >   	ret = arm_smmu_init_one_queue(smmu, &smmu->cmdq.q, ARM_SMMU_CMDQ_PROD,
> > @@ -2804,6 +2963,12 @@ static int arm_smmu_init_queues(struct arm_smmu_device *smmu)
> >   	if (ret)
> >   		return ret;
> > +	if (sva && smmu->features & ARM_SMMU_FEAT_STALLS) {
> 
> Surely you could just test for ARM_SMMU_FEAT_SVA by now rather than go
> through the whole of arm_smmu_sva_supported() again?

Oh right, that was dumb

Thanks for the review
Jean
diff mbox series

Patch

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 8ef6a1c48635..cb129870ef55 100644
--- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h
+++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h
@@ -354,6 +354,13 @@ 
 #define CMDQ_PRI_1_GRPID		GENMASK_ULL(8, 0)
 #define CMDQ_PRI_1_RESP			GENMASK_ULL(13, 12)
 
+#define CMDQ_RESUME_0_SID		GENMASK_ULL(63, 32)
+#define CMDQ_RESUME_0_RESP_TERM		0UL
+#define CMDQ_RESUME_0_RESP_RETRY	1UL
+#define CMDQ_RESUME_0_RESP_ABORT	2UL
+#define CMDQ_RESUME_0_RESP		GENMASK_ULL(13, 12)
+#define CMDQ_RESUME_1_STAG		GENMASK_ULL(15, 0)
+
 #define CMDQ_SYNC_0_CS			GENMASK_ULL(13, 12)
 #define CMDQ_SYNC_0_CS_NONE		0
 #define CMDQ_SYNC_0_CS_IRQ		1
@@ -370,6 +377,25 @@ 
 
 #define EVTQ_0_ID			GENMASK_ULL(7, 0)
 
+#define EVT_ID_TRANSLATION_FAULT	0x10
+#define EVT_ID_ADDR_SIZE_FAULT		0x11
+#define EVT_ID_ACCESS_FAULT		0x12
+#define EVT_ID_PERMISSION_FAULT		0x13
+
+#define EVTQ_0_SSV			(1UL << 11)
+#define EVTQ_0_SSID			GENMASK_ULL(31, 12)
+#define EVTQ_0_SID			GENMASK_ULL(63, 32)
+#define EVTQ_1_STAG			GENMASK_ULL(15, 0)
+#define EVTQ_1_STALL			(1UL << 31)
+#define EVTQ_1_PRIV			(1UL << 33)
+#define EVTQ_1_EXEC			(1UL << 34)
+#define EVTQ_1_READ			(1UL << 35)
+#define EVTQ_1_S2			(1UL << 39)
+#define EVTQ_1_CLASS			GENMASK_ULL(41, 40)
+#define EVTQ_1_TT_READ			(1UL << 44)
+#define EVTQ_2_ADDR			GENMASK_ULL(63, 0)
+#define EVTQ_3_IPA			GENMASK_ULL(51, 12)
+
 /* PRI queue */
 #define PRIQ_ENT_SZ_SHIFT		4
 #define PRIQ_ENT_DWORDS			((1 << PRIQ_ENT_SZ_SHIFT) >> 3)
@@ -462,6 +488,13 @@  struct arm_smmu_cmdq_ent {
 			enum pri_resp		resp;
 		} pri;
 
+		#define CMDQ_OP_RESUME		0x44
+		struct {
+			u32			sid;
+			u16			stag;
+			u8			resp;
+		} resume;
+
 		#define CMDQ_OP_CMD_SYNC	0x46
 		struct {
 			u64			msiaddr;
@@ -520,6 +553,7 @@  struct arm_smmu_cmdq_batch {
 
 struct arm_smmu_evtq {
 	struct arm_smmu_queue		q;
+	struct iopf_queue		*iopf;
 	u32				max_stalls;
 };
 
@@ -656,7 +690,9 @@  struct arm_smmu_master {
 	struct arm_smmu_stream		*streams;
 	unsigned int			num_streams;
 	bool				ats_enabled;
+	bool				stall_enabled;
 	bool				sva_enabled;
+	bool				iopf_enabled;
 	struct list_head		bonds;
 	unsigned int			ssid_bits;
 };
@@ -675,6 +711,7 @@  struct arm_smmu_domain {
 
 	struct io_pgtable_ops		*pgtbl_ops;
 	bool				non_strict;
+	bool				stall_enabled;
 	atomic_t			nr_ats_masters;
 
 	enum arm_smmu_domain_stage	stage;
@@ -713,6 +750,10 @@  bool arm_smmu_master_sva_supported(struct arm_smmu_master *master);
 bool arm_smmu_master_sva_enabled(struct arm_smmu_master *master);
 int arm_smmu_master_enable_sva(struct arm_smmu_master *master);
 int arm_smmu_master_disable_sva(struct arm_smmu_master *master);
+bool arm_smmu_master_iopf_supported(struct arm_smmu_master *master);
+bool arm_smmu_master_iopf_enabled(struct arm_smmu_master *master);
+int arm_smmu_master_enable_iopf(struct arm_smmu_master *master);
+int arm_smmu_master_disable_iopf(struct arm_smmu_master *master);
 struct iommu_sva *arm_smmu_sva_bind(struct device *dev, struct mm_struct *mm,
 				    void *drvdata);
 void arm_smmu_sva_unbind(struct iommu_sva *handle);
@@ -744,6 +785,26 @@  static inline int arm_smmu_master_disable_sva(struct arm_smmu_master *master)
 	return -ENODEV;
 }
 
+static inline bool arm_smmu_master_iopf_supported(struct arm_smmu_master *master)
+{
+	return false;
+}
+
+static inline bool arm_smmu_master_iopf_enabled(struct arm_smmu_master *master)
+{
+	return false;
+}
+
+static inline int arm_smmu_master_enable_iopf(struct arm_smmu_master *master)
+{
+	return -ENODEV;
+}
+
+static inline int arm_smmu_master_disable_iopf(struct arm_smmu_master *master)
+{
+	return -ENODEV;
+}
+
 static inline struct iommu_sva *
 arm_smmu_sva_bind(struct device *dev, struct mm_struct *mm, void *drvdata)
 {
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 e13b092e6004..17acfee4f484 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
@@ -431,9 +431,9 @@  bool arm_smmu_sva_supported(struct arm_smmu_device *smmu)
 	return true;
 }
 
-static bool arm_smmu_iopf_supported(struct arm_smmu_master *master)
+bool arm_smmu_master_iopf_supported(struct arm_smmu_master *master)
 {
-	return false;
+	return master->stall_enabled;
 }
 
 bool arm_smmu_master_sva_supported(struct arm_smmu_master *master)
@@ -441,8 +441,18 @@  bool arm_smmu_master_sva_supported(struct arm_smmu_master *master)
 	if (!(master->smmu->features & ARM_SMMU_FEAT_SVA))
 		return false;
 
-	/* SSID and IOPF support are mandatory for the moment */
-	return master->ssid_bits && arm_smmu_iopf_supported(master);
+	/* SSID support is mandatory for the moment */
+	return master->ssid_bits;
+}
+
+bool arm_smmu_master_iopf_enabled(struct arm_smmu_master *master)
+{
+	bool enabled;
+
+	mutex_lock(&sva_lock);
+	enabled = master->iopf_enabled;
+	mutex_unlock(&sva_lock);
+	return enabled;
 }
 
 bool arm_smmu_master_sva_enabled(struct arm_smmu_master *master)
@@ -455,15 +465,67 @@  bool arm_smmu_master_sva_enabled(struct arm_smmu_master *master)
 	return enabled;
 }
 
+int arm_smmu_master_enable_iopf(struct arm_smmu_master *master)
+{
+	int ret;
+	struct device *dev = master->dev;
+
+	mutex_lock(&sva_lock);
+	if (master->stall_enabled) {
+		ret = iopf_queue_add_device(master->smmu->evtq.iopf, dev);
+		if (ret)
+			goto err_unlock;
+	}
+
+	ret = iommu_register_device_fault_handler(dev, iommu_queue_iopf, dev);
+	if (ret)
+		goto err_remove_device;
+	master->iopf_enabled = true;
+	mutex_unlock(&sva_lock);
+	return 0;
+
+err_remove_device:
+	iopf_queue_remove_device(master->smmu->evtq.iopf, dev);
+err_unlock:
+	mutex_unlock(&sva_lock);
+	return ret;
+}
+
 int arm_smmu_master_enable_sva(struct arm_smmu_master *master)
 {
 	mutex_lock(&sva_lock);
+	/*
+	 * Drivers for devices supporting PRI or stall should enable IOPF first.
+	 * Others have device-specific fault handlers and don't need IOPF, so
+	 * this sanity check is a bit basic.
+	 */
+	if (arm_smmu_master_iopf_supported(master) && !master->iopf_enabled) {
+		mutex_unlock(&sva_lock);
+		return -EINVAL;
+	}
 	master->sva_enabled = true;
 	mutex_unlock(&sva_lock);
 
 	return 0;
 }
 
+int arm_smmu_master_disable_iopf(struct arm_smmu_master *master)
+{
+	struct device *dev = master->dev;
+
+	mutex_lock(&sva_lock);
+	if (master->sva_enabled) {
+		mutex_unlock(&sva_lock);
+		return -EBUSY;
+	}
+
+	iommu_unregister_device_fault_handler(dev);
+	iopf_queue_remove_device(master->smmu->evtq.iopf, dev);
+	master->iopf_enabled = false;
+	mutex_unlock(&sva_lock);
+	return 0;
+}
+
 int arm_smmu_master_disable_sva(struct arm_smmu_master *master)
 {
 	mutex_lock(&sva_lock);
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 2dbae2e6965d..1fea11d65cd3 100644
--- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
+++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
@@ -32,6 +32,7 @@ 
 #include <linux/amba/bus.h>
 
 #include "arm-smmu-v3.h"
+#include "../../iommu-sva-lib.h"
 
 static bool disable_bypass = true;
 module_param(disable_bypass, bool, 0444);
@@ -319,6 +320,11 @@  static int arm_smmu_cmdq_build_cmd(u64 *cmd, struct arm_smmu_cmdq_ent *ent)
 		}
 		cmd[1] |= FIELD_PREP(CMDQ_PRI_1_RESP, ent->pri.resp);
 		break;
+	case CMDQ_OP_RESUME:
+		cmd[0] |= FIELD_PREP(CMDQ_RESUME_0_SID, ent->resume.sid);
+		cmd[0] |= FIELD_PREP(CMDQ_RESUME_0_RESP, ent->resume.resp);
+		cmd[1] |= FIELD_PREP(CMDQ_RESUME_1_STAG, ent->resume.stag);
+		break;
 	case CMDQ_OP_CMD_SYNC:
 		if (ent->sync.msiaddr) {
 			cmd[0] |= FIELD_PREP(CMDQ_SYNC_0_CS, CMDQ_SYNC_0_CS_IRQ);
@@ -882,6 +888,44 @@  static int arm_smmu_cmdq_batch_submit(struct arm_smmu_device *smmu,
 	return arm_smmu_cmdq_issue_cmdlist(smmu, cmds->cmds, cmds->num, true);
 }
 
+static int arm_smmu_page_response(struct device *dev,
+				  struct iommu_fault_event *unused,
+				  struct iommu_page_response *resp)
+{
+	struct arm_smmu_cmdq_ent cmd = {0};
+	struct arm_smmu_master *master = dev_iommu_priv_get(dev);
+	int sid = master->streams[0].id;
+
+	if (master->stall_enabled) {
+		cmd.opcode		= CMDQ_OP_RESUME;
+		cmd.resume.sid		= sid;
+		cmd.resume.stag		= resp->grpid;
+		switch (resp->code) {
+		case IOMMU_PAGE_RESP_INVALID:
+		case IOMMU_PAGE_RESP_FAILURE:
+			cmd.resume.resp = CMDQ_RESUME_0_RESP_ABORT;
+			break;
+		case IOMMU_PAGE_RESP_SUCCESS:
+			cmd.resume.resp = CMDQ_RESUME_0_RESP_RETRY;
+			break;
+		default:
+			return -EINVAL;
+		}
+	} else {
+		return -ENODEV;
+	}
+
+	arm_smmu_cmdq_issue_cmd(master->smmu, &cmd);
+	/*
+	 * Don't send a SYNC, it doesn't do anything for RESUME or PRI_RESP.
+	 * RESUME consumption guarantees that the stalled transaction will be
+	 * terminated... at some point in the future. PRI_RESP is fire and
+	 * forget.
+	 */
+
+	return 0;
+}
+
 /* Context descriptor manipulation functions */
 void arm_smmu_tlb_inv_asid(struct arm_smmu_device *smmu, u16 asid)
 {
@@ -991,7 +1035,6 @@  int arm_smmu_write_ctx_desc(struct arm_smmu_domain *smmu_domain, int ssid,
 	u64 val;
 	bool cd_live;
 	__le64 *cdptr;
-	struct arm_smmu_device *smmu = smmu_domain->smmu;
 
 	if (WARN_ON(ssid >= (1 << smmu_domain->s1_cfg.s1cdmax)))
 		return -E2BIG;
@@ -1036,8 +1079,7 @@  int arm_smmu_write_ctx_desc(struct arm_smmu_domain *smmu_domain, int ssid,
 			FIELD_PREP(CTXDESC_CD_0_ASID, cd->asid) |
 			CTXDESC_CD_0_V;
 
-		/* STALL_MODEL==0b10 && CD.S==0 is ILLEGAL */
-		if (smmu->features & ARM_SMMU_FEAT_STALL_FORCE)
+		if (smmu_domain->stall_enabled)
 			val |= CTXDESC_CD_0_S;
 	}
 
@@ -1278,7 +1320,7 @@  static void arm_smmu_write_strtab_ent(struct arm_smmu_master *master, u32 sid,
 			 FIELD_PREP(STRTAB_STE_1_STRW, STRTAB_STE_1_STRW_NSEL1));
 
 		if (smmu->features & ARM_SMMU_FEAT_STALLS &&
-		   !(smmu->features & ARM_SMMU_FEAT_STALL_FORCE))
+		    !master->stall_enabled)
 			dst[1] |= cpu_to_le64(STRTAB_STE_1_S1STALLD);
 
 		val |= (s1_cfg->cdcfg.cdtab_dma & STRTAB_STE_0_S1CTXPTR_MASK) |
@@ -1355,7 +1397,6 @@  static int arm_smmu_init_l2_strtab(struct arm_smmu_device *smmu, u32 sid)
 	return 0;
 }
 
-__maybe_unused
 static struct arm_smmu_master *
 arm_smmu_find_master(struct arm_smmu_device *smmu, u32 sid)
 {
@@ -1382,9 +1423,96 @@  arm_smmu_find_master(struct arm_smmu_device *smmu, u32 sid)
 }
 
 /* IRQ and event handlers */
+static int arm_smmu_handle_evt(struct arm_smmu_device *smmu, u64 *evt)
+{
+	int ret;
+	u32 perm = 0;
+	struct arm_smmu_master *master;
+	bool ssid_valid = evt[0] & EVTQ_0_SSV;
+	u8 type = FIELD_GET(EVTQ_0_ID, evt[0]);
+	u32 sid = FIELD_GET(EVTQ_0_SID, evt[0]);
+	struct iommu_fault_event fault_evt = { };
+	struct iommu_fault *flt = &fault_evt.fault;
+
+	/* Stage-2 is always pinned at the moment */
+	if (evt[1] & EVTQ_1_S2)
+		return -EFAULT;
+
+	master = arm_smmu_find_master(smmu, sid);
+	if (!master)
+		return -EINVAL;
+
+	if (evt[1] & EVTQ_1_READ)
+		perm |= IOMMU_FAULT_PERM_READ;
+	else
+		perm |= IOMMU_FAULT_PERM_WRITE;
+
+	if (evt[1] & EVTQ_1_EXEC)
+		perm |= IOMMU_FAULT_PERM_EXEC;
+
+	if (evt[1] & EVTQ_1_PRIV)
+		perm |= IOMMU_FAULT_PERM_PRIV;
+
+	if (evt[1] & EVTQ_1_STALL) {
+		flt->type = IOMMU_FAULT_PAGE_REQ;
+		flt->prm = (struct iommu_fault_page_request) {
+			.flags = IOMMU_FAULT_PAGE_REQUEST_LAST_PAGE,
+			.grpid = FIELD_GET(EVTQ_1_STAG, evt[1]),
+			.perm = perm,
+			.addr = FIELD_GET(EVTQ_2_ADDR, evt[2]),
+		};
+
+		if (ssid_valid) {
+			flt->prm.flags |= IOMMU_FAULT_PAGE_REQUEST_PASID_VALID;
+			flt->prm.pasid = FIELD_GET(EVTQ_0_SSID, evt[0]);
+		}
+	} else {
+		flt->type = IOMMU_FAULT_DMA_UNRECOV;
+		flt->event = (struct iommu_fault_unrecoverable) {
+			.flags = IOMMU_FAULT_UNRECOV_ADDR_VALID |
+				 IOMMU_FAULT_UNRECOV_FETCH_ADDR_VALID,
+			.perm = perm,
+			.addr = FIELD_GET(EVTQ_2_ADDR, evt[2]),
+			.fetch_addr = FIELD_GET(EVTQ_3_IPA, evt[3]),
+		};
+
+		if (ssid_valid) {
+			flt->event.flags |= IOMMU_FAULT_UNRECOV_PASID_VALID;
+			flt->event.pasid = FIELD_GET(EVTQ_0_SSID, evt[0]);
+		}
+
+		switch (type) {
+		case EVT_ID_TRANSLATION_FAULT:
+		case EVT_ID_ADDR_SIZE_FAULT:
+		case EVT_ID_ACCESS_FAULT:
+			flt->event.reason = IOMMU_FAULT_REASON_PTE_FETCH;
+			break;
+		case EVT_ID_PERMISSION_FAULT:
+			flt->event.reason = IOMMU_FAULT_REASON_PERMISSION;
+			break;
+		default:
+			/* TODO: report other unrecoverable faults. */
+			return -EFAULT;
+		}
+	}
+
+	ret = iommu_report_device_fault(master->dev, &fault_evt);
+	if (ret && flt->type == IOMMU_FAULT_PAGE_REQ) {
+		/* Nobody cared, abort the access */
+		struct iommu_page_response resp = {
+			.pasid		= flt->prm.pasid,
+			.grpid		= flt->prm.grpid,
+			.code		= IOMMU_PAGE_RESP_FAILURE,
+		};
+		arm_smmu_page_response(master->dev, NULL, &resp);
+	}
+
+	return ret;
+}
+
 static irqreturn_t arm_smmu_evtq_thread(int irq, void *dev)
 {
-	int i;
+	int i, ret;
 	struct arm_smmu_device *smmu = dev;
 	struct arm_smmu_queue *q = &smmu->evtq.q;
 	struct arm_smmu_ll_queue *llq = &q->llq;
@@ -1394,11 +1522,14 @@  static irqreturn_t arm_smmu_evtq_thread(int irq, void *dev)
 		while (!queue_remove_raw(q, evt)) {
 			u8 id = FIELD_GET(EVTQ_0_ID, evt[0]);
 
-			dev_info(smmu->dev, "event 0x%02x received:\n", id);
-			for (i = 0; i < ARRAY_SIZE(evt); ++i)
-				dev_info(smmu->dev, "\t0x%016llx\n",
-					 (unsigned long long)evt[i]);
-
+			ret = arm_smmu_handle_evt(smmu, evt);
+			if (ret) {
+				dev_info(smmu->dev, "event 0x%02x received:\n",
+					 id);
+				for (i = 0; i < ARRAY_SIZE(evt); ++i)
+					dev_info(smmu->dev, "\t0x%016llx\n",
+						 (unsigned long long)evt[i]);
+			}
 		}
 
 		/*
@@ -1903,6 +2034,8 @@  static int arm_smmu_domain_finalise_s1(struct arm_smmu_domain *smmu_domain,
 
 	cfg->s1cdmax = master->ssid_bits;
 
+	smmu_domain->stall_enabled = master->stall_enabled;
+
 	ret = arm_smmu_alloc_cd_tables(smmu_domain);
 	if (ret)
 		goto out_free_asid;
@@ -2250,6 +2383,12 @@  static int arm_smmu_attach_dev(struct iommu_domain *domain, struct device *dev)
 			smmu_domain->s1_cfg.s1cdmax, master->ssid_bits);
 		ret = -EINVAL;
 		goto out_unlock;
+	} else if (smmu_domain->stage == ARM_SMMU_DOMAIN_S1 &&
+		   smmu_domain->stall_enabled != master->stall_enabled) {
+		dev_err(dev, "cannot attach to stall-%s domain\n",
+			smmu_domain->stall_enabled ? "enabled" : "disabled");
+		ret = -EINVAL;
+		goto out_unlock;
 	}
 
 	master->domain = smmu_domain;
@@ -2484,6 +2623,11 @@  static struct iommu_device *arm_smmu_probe_device(struct device *dev)
 		master->ssid_bits = min_t(u8, master->ssid_bits,
 					  CTXDESC_LINEAR_CDMAX);
 
+	if ((smmu->features & ARM_SMMU_FEAT_STALLS &&
+	     device_property_read_bool(dev, "dma-can-stall")) ||
+	    smmu->features & ARM_SMMU_FEAT_STALL_FORCE)
+		master->stall_enabled = true;
+
 	return &smmu->iommu;
 
 err_free_master:
@@ -2502,6 +2646,7 @@  static void arm_smmu_release_device(struct device *dev)
 
 	master = dev_iommu_priv_get(dev);
 	WARN_ON(arm_smmu_master_sva_enabled(master));
+	iopf_queue_remove_device(master->smmu->evtq.iopf, dev);
 	arm_smmu_detach_dev(master);
 	arm_smmu_disable_pasid(master);
 	arm_smmu_remove_master(master);
@@ -2629,6 +2774,8 @@  static bool arm_smmu_dev_has_feature(struct device *dev,
 		return false;
 
 	switch (feat) {
+	case IOMMU_DEV_FEAT_IOPF:
+		return arm_smmu_master_iopf_supported(master);
 	case IOMMU_DEV_FEAT_SVA:
 		return arm_smmu_master_sva_supported(master);
 	default:
@@ -2645,6 +2792,8 @@  static bool arm_smmu_dev_feature_enabled(struct device *dev,
 		return false;
 
 	switch (feat) {
+	case IOMMU_DEV_FEAT_IOPF:
+		return arm_smmu_master_iopf_enabled(master);
 	case IOMMU_DEV_FEAT_SVA:
 		return arm_smmu_master_sva_enabled(master);
 	default:
@@ -2655,6 +2804,8 @@  static bool arm_smmu_dev_feature_enabled(struct device *dev,
 static int arm_smmu_dev_enable_feature(struct device *dev,
 				       enum iommu_dev_features feat)
 {
+	struct arm_smmu_master *master = dev_iommu_priv_get(dev);
+
 	if (!arm_smmu_dev_has_feature(dev, feat))
 		return -ENODEV;
 
@@ -2662,8 +2813,10 @@  static int arm_smmu_dev_enable_feature(struct device *dev,
 		return -EBUSY;
 
 	switch (feat) {
+	case IOMMU_DEV_FEAT_IOPF:
+		return arm_smmu_master_enable_iopf(master);
 	case IOMMU_DEV_FEAT_SVA:
-		return arm_smmu_master_enable_sva(dev_iommu_priv_get(dev));
+		return arm_smmu_master_enable_sva(master);
 	default:
 		return -EINVAL;
 	}
@@ -2672,12 +2825,16 @@  static int arm_smmu_dev_enable_feature(struct device *dev,
 static int arm_smmu_dev_disable_feature(struct device *dev,
 					enum iommu_dev_features feat)
 {
+	struct arm_smmu_master *master = dev_iommu_priv_get(dev);
+
 	if (!arm_smmu_dev_feature_enabled(dev, feat))
 		return -EINVAL;
 
 	switch (feat) {
+	case IOMMU_DEV_FEAT_IOPF:
+		return arm_smmu_master_disable_iopf(master);
 	case IOMMU_DEV_FEAT_SVA:
-		return arm_smmu_master_disable_sva(dev_iommu_priv_get(dev));
+		return arm_smmu_master_disable_sva(master);
 	default:
 		return -EINVAL;
 	}
@@ -2708,6 +2865,7 @@  static struct iommu_ops arm_smmu_ops = {
 	.sva_bind		= arm_smmu_sva_bind,
 	.sva_unbind		= arm_smmu_sva_unbind,
 	.sva_get_pasid		= arm_smmu_sva_get_pasid,
+	.page_response		= arm_smmu_page_response,
 	.pgsize_bitmap		= -1UL, /* Restricted during device attach */
 };
 
@@ -2785,6 +2943,7 @@  static int arm_smmu_cmdq_init(struct arm_smmu_device *smmu)
 static int arm_smmu_init_queues(struct arm_smmu_device *smmu)
 {
 	int ret;
+	bool sva = arm_smmu_sva_supported(smmu);
 
 	/* cmdq */
 	ret = arm_smmu_init_one_queue(smmu, &smmu->cmdq.q, ARM_SMMU_CMDQ_PROD,
@@ -2804,6 +2963,12 @@  static int arm_smmu_init_queues(struct arm_smmu_device *smmu)
 	if (ret)
 		return ret;
 
+	if (sva && smmu->features & ARM_SMMU_FEAT_STALLS) {
+		smmu->evtq.iopf = iopf_queue_alloc(dev_name(smmu->dev));
+		if (!smmu->evtq.iopf)
+			return -ENOMEM;
+	}
+
 	/* priq */
 	if (!(smmu->features & ARM_SMMU_FEAT_PRI))
 		return 0;
@@ -3718,6 +3883,7 @@  static int arm_smmu_device_remove(struct platform_device *pdev)
 	iommu_device_unregister(&smmu->iommu);
 	iommu_device_sysfs_remove(&smmu->iommu);
 	arm_smmu_device_disable(smmu);
+	iopf_queue_free(smmu->evtq.iopf);
 
 	return 0;
 }