IOMMU Fixes for Linux v4.13-rc3

Including:
 
 	- Fix a scheduling-while-atomic bug in the AMD IOMMU driver. It
 	  was found after the checker was enabled earlier.
 
 	- A fix for the virtual APIC code in the AMD IOMMU driver which
 	  delivers device interrupts directly into KVM guests for
 	  assigned devices.
 
 	- Fixes for the recently merged lock-less page-table code for
 	  ARM. The redundant TLB syncs got reverted and locks added
 	  again around the TLB sync code.
 
 	- Fix for error handling in arm_smmu_add_device()
 
 	- Address sanitization fix for arm io-pgtable code
 -----BEGIN PGP SIGNATURE-----
 Version: GnuPG v2
 
 iQIcBAABAgAGBQJZhDD/AAoJECvwRC2XARrj3YkP/2+yZgffkQj9Xp2izSMgQYyI
 VqqYj2/oaolcbYqY5iv6OqU/W2soutU9x6Qf/PlJ4aHD+iQMlRwKqWwkiI/k5JKA
 7t1qZwzHucygBgrckjZBtNhU8sfGsCPDeu1Vw6o2rLHQvYUBEI6Hk/jS//YKIhrt
 453N2z/ABXtjFHYVLtYPrJBvSrhnKHcR55enT1AQL1nKYhF3ZqlDwiv28P6S4JhJ
 i3OWX8S2jy59Jw3H5FggNBAP4oTN3PrLdnR9EzIB7kkWXC0CJgOmlFiRfNTrh25U
 +GPXL6NHEt2EuqP+qjH2UV+Lb3IY+uekSusDLemMTIVh1Zs5U/cm5cglHZtaWzBZ
 tt+ZsGuErFAaJt26ubWOk96+9WQchgfQVedAoIise7sT6OlThQUPba7pyHAiA2/X
 umm8Fu/78cNDLQNssWNC87xvpV3TqwJVceXqIRmw8oRwTWzMfkkerOZzDhyGO/am
 UqyulMX7QQrBygmgSzd4qZvOVqRBGO2caSVdsvmrSzYeRXxBlnMrdv+gTxt65Wju
 m6MkWuFym6CbvWdHg9nUSwuX4eOIP0PpME2zXMlg7DMFJ8AJoABxLdar1cCEOKGi
 6Vq5hHQQ8pGKDIVw5Cz3YC45Fg2XOr6RjsTiDZf8gYJsEqhDHZ8XYnZ1GaFsjvVX
 +653QdN/pqWCdukUC4jc
 =Z9oV
 -----END PGP SIGNATURE-----

Merge tag 'iommu-fixes-v4.13-rc3' of git://git.kernel.org/pub/scm/linux/kernel/git/joro/iommu

Pull IOMMU fixes from Joerg Roedel:

 - fix a scheduling-while-atomic bug in the AMD IOMMU driver. It was
   found after the checker was enabled earlier.

 - a fix for the virtual APIC code in the AMD IOMMU driver which
   delivers device interrupts directly into KVM guests for assigned
   devices.

 - fixes for the recently merged lock-less page-table code for ARM. The
   redundant TLB syncs got reverted and locks added again around the TLB
   sync code.

 - fix for error handling in arm_smmu_add_device()

 - address sanitization fix for arm io-pgtable code

* tag 'iommu-fixes-v4.13-rc3' of git://git.kernel.org/pub/scm/linux/kernel/git/joro/iommu:
  iommu/amd: Fix schedule-while-atomic BUG in initialization code
  iommu/amd: Enable ga_log_intr when enabling guest_mode
  iommu/io-pgtable: Sanitise map/unmap addresses
  iommu/arm-smmu: Fix the error path in arm_smmu_add_device
  Revert "iommu/io-pgtable: Avoid redundant TLB syncs"
  iommu/mtk: Avoid redundant TLB syncs locally
  iommu/arm-smmu: Reintroduce locking around TLB sync operations

drivers/iommu/amd_iommu.c

@@ -4452,6 +4452,7 @@ static int amd_ir_set_vcpu_affinity(struct irq_data *data, void *vcpu_info)
 		/* Setting */
 		irte->hi.fields.ga_root_ptr = (pi_data->base >> 12);
 		irte->hi.fields.vector = vcpu_pi_info->vector;
+		irte->lo.fields_vapic.ga_log_intr = 1;
 		irte->lo.fields_vapic.guest_mode = 1;
 		irte->lo.fields_vapic.ga_tag = pi_data->ga_tag;
 

drivers/iommu/amd_iommu_init.c

@@ -2440,11 +2440,11 @@ static int __init state_next(void)
 		break;
 	case IOMMU_ACPI_FINISHED:
 		early_enable_iommus();
-		register_syscore_ops(&amd_iommu_syscore_ops);
 		x86_platform.iommu_shutdown = disable_iommus;
 		init_state = IOMMU_ENABLED;
 		break;
 	case IOMMU_ENABLED:
+		register_syscore_ops(&amd_iommu_syscore_ops);
 		ret = amd_iommu_init_pci();
 		init_state = ret ? IOMMU_INIT_ERROR : IOMMU_PCI_INIT;
 		enable_iommus_v2();

drivers/iommu/arm-smmu.c

@@ -400,6 +400,8 @@ struct arm_smmu_device {
 
 	u32				cavium_id_base; /* Specific to Cavium */
 
+	spinlock_t			global_sync_lock;
+
 	/* IOMMU core code handle */
 	struct iommu_device		iommu;
 };
@@ -436,7 +438,7 @@ struct arm_smmu_domain {
 	struct arm_smmu_cfg		cfg;
 	enum arm_smmu_domain_stage	stage;
 	struct mutex			init_mutex; /* Protects smmu pointer */
-	spinlock_t			cb_lock; /* Serialises ATS1* ops */
+	spinlock_t			cb_lock; /* Serialises ATS1* ops and TLB syncs */
 	struct iommu_domain		domain;
 };
 
@@ -602,9 +604,12 @@ static void __arm_smmu_tlb_sync(struct arm_smmu_device *smmu,
 static void arm_smmu_tlb_sync_global(struct arm_smmu_device *smmu)
 {
 	void __iomem *base = ARM_SMMU_GR0(smmu);
+	unsigned long flags;
 
+	spin_lock_irqsave(&smmu->global_sync_lock, flags);
 	__arm_smmu_tlb_sync(smmu, base + ARM_SMMU_GR0_sTLBGSYNC,
 			    base + ARM_SMMU_GR0_sTLBGSTATUS);
+	spin_unlock_irqrestore(&smmu->global_sync_lock, flags);
 }
 
 static void arm_smmu_tlb_sync_context(void *cookie)
@@ -612,9 +617,12 @@ static void arm_smmu_tlb_sync_context(void *cookie)
 	struct arm_smmu_domain *smmu_domain = cookie;
 	struct arm_smmu_device *smmu = smmu_domain->smmu;
 	void __iomem *base = ARM_SMMU_CB(smmu, smmu_domain->cfg.cbndx);
+	unsigned long flags;
 
+	spin_lock_irqsave(&smmu_domain->cb_lock, flags);
 	__arm_smmu_tlb_sync(smmu, base + ARM_SMMU_CB_TLBSYNC,
 			    base + ARM_SMMU_CB_TLBSTATUS);
+	spin_unlock_irqrestore(&smmu_domain->cb_lock, flags);
 }
 
 static void arm_smmu_tlb_sync_vmid(void *cookie)
@@ -1511,7 +1519,6 @@ static int arm_smmu_add_device(struct device *dev)
 
 	if (using_legacy_binding) {
 		ret = arm_smmu_register_legacy_master(dev, &smmu);
-		fwspec = dev->iommu_fwspec;
 		if (ret)
 			goto out_free;
 	} else if (fwspec && fwspec->ops == &arm_smmu_ops) {
@@ -1550,15 +1557,15 @@ static int arm_smmu_add_device(struct device *dev)
 
 	ret = arm_smmu_master_alloc_smes(dev);
 	if (ret)
-		goto out_free;
+		goto out_cfg_free;
 
 	iommu_device_link(&smmu->iommu, dev);
 
 	return 0;
 
+out_cfg_free:
+	kfree(cfg);
 out_free:
-	if (fwspec)
-		kfree(fwspec->iommu_priv);
 	iommu_fwspec_free(dev);
 	return ret;
 }
@@ -1925,6 +1932,7 @@ static int arm_smmu_device_cfg_probe(struct arm_smmu_device *smmu)
 
 	smmu->num_mapping_groups = size;
 	mutex_init(&smmu->stream_map_mutex);
+	spin_lock_init(&smmu->global_sync_lock);
 
 	if (smmu->version < ARM_SMMU_V2 || !(id & ID0_PTFS_NO_AARCH32)) {
 		smmu->features |= ARM_SMMU_FEAT_FMT_AARCH32_L;

drivers/iommu/io-pgtable-arm-v7s.c

@@ -479,6 +479,9 @@ static int arm_v7s_map(struct io_pgtable_ops *ops, unsigned long iova,
 	if (!(prot & (IOMMU_READ | IOMMU_WRITE)))
 		return 0;
 
+	if (WARN_ON(upper_32_bits(iova) || upper_32_bits(paddr)))
+		return -ERANGE;
+
 	ret = __arm_v7s_map(data, iova, paddr, size, prot, 1, data->pgd);
 	/*
 	 * Synchronise all PTE updates for the new mapping before there's
@@ -659,6 +662,9 @@ static int arm_v7s_unmap(struct io_pgtable_ops *ops, unsigned long iova,
 	struct arm_v7s_io_pgtable *data = io_pgtable_ops_to_data(ops);
 	size_t unmapped;
 
+	if (WARN_ON(upper_32_bits(iova)))
+		return 0;
+
 	unmapped = __arm_v7s_unmap(data, iova, size, 1, data->pgd);
 	if (unmapped)
 		io_pgtable_tlb_sync(&data->iop);

drivers/iommu/io-pgtable-arm.c

@@ -452,6 +452,10 @@ static int arm_lpae_map(struct io_pgtable_ops *ops, unsigned long iova,
 	if (!(iommu_prot & (IOMMU_READ | IOMMU_WRITE)))
 		return 0;
 
+	if (WARN_ON(iova >= (1ULL << data->iop.cfg.ias) ||
+		    paddr >= (1ULL << data->iop.cfg.oas)))
+		return -ERANGE;
+
 	prot = arm_lpae_prot_to_pte(data, iommu_prot);
 	ret = __arm_lpae_map(data, iova, paddr, size, prot, lvl, ptep);
 	/*
@@ -610,6 +614,9 @@ static int arm_lpae_unmap(struct io_pgtable_ops *ops, unsigned long iova,
 	arm_lpae_iopte *ptep = data->pgd;
 	int lvl = ARM_LPAE_START_LVL(data);
 
+	if (WARN_ON(iova >= (1ULL << data->iop.cfg.ias)))
+		return 0;
+
 	unmapped = __arm_lpae_unmap(data, iova, size, lvl, ptep);
 	if (unmapped)
 		io_pgtable_tlb_sync(&data->iop);

drivers/iommu/io-pgtable.h

@@ -158,14 +158,12 @@ void free_io_pgtable_ops(struct io_pgtable_ops *ops);
  * @fmt:    The page table format.
  * @cookie: An opaque token provided by the IOMMU driver and passed back to
  *          any callback routines.
- * @tlb_sync_pending: Private flag for optimising out redundant syncs.
  * @cfg:    A copy of the page table configuration.
  * @ops:    The page table operations in use for this set of page tables.
  */
 struct io_pgtable {
 	enum io_pgtable_fmt	fmt;
 	void			*cookie;
-	bool			tlb_sync_pending;
 	struct io_pgtable_cfg	cfg;
 	struct io_pgtable_ops	ops;
 };
@@ -175,22 +173,17 @@ struct io_pgtable {
 static inline void io_pgtable_tlb_flush_all(struct io_pgtable *iop)
 {
 	iop->cfg.tlb->tlb_flush_all(iop->cookie);
-	iop->tlb_sync_pending = true;
 }
 
 static inline void io_pgtable_tlb_add_flush(struct io_pgtable *iop,
 		unsigned long iova, size_t size, size_t granule, bool leaf)
 {
 	iop->cfg.tlb->tlb_add_flush(iova, size, granule, leaf, iop->cookie);
-	iop->tlb_sync_pending = true;
 }
 
 static inline void io_pgtable_tlb_sync(struct io_pgtable *iop)
 {
-	if (iop->tlb_sync_pending) {
-		iop->cfg.tlb->tlb_sync(iop->cookie);
-		iop->tlb_sync_pending = false;
-	}
+	iop->cfg.tlb->tlb_sync(iop->cookie);
 }
 
 /**

drivers/iommu/mtk_iommu.c

@@ -129,6 +129,7 @@ static void mtk_iommu_tlb_add_flush_nosync(unsigned long iova, size_t size,
 	writel_relaxed(iova, data->base + REG_MMU_INVLD_START_A);
 	writel_relaxed(iova + size - 1, data->base + REG_MMU_INVLD_END_A);
 	writel_relaxed(F_MMU_INV_RANGE, data->base + REG_MMU_INVALIDATE);
+	data->tlb_flush_active = true;
 }
 
 static void mtk_iommu_tlb_sync(void *cookie)
@@ -137,6 +138,10 @@ static void mtk_iommu_tlb_sync(void *cookie)
 	int ret;
 	u32 tmp;
 
+	/* Avoid timing out if there's nothing to wait for */
+	if (!data->tlb_flush_active)
+		return;
+
 	ret = readl_poll_timeout_atomic(data->base + REG_MMU_CPE_DONE, tmp,
 					tmp != 0, 10, 100000);
 	if (ret) {
@@ -146,6 +151,7 @@ static void mtk_iommu_tlb_sync(void *cookie)
 	}
 	/* Clear the CPE status */
 	writel_relaxed(0, data->base + REG_MMU_CPE_DONE);
+	data->tlb_flush_active = false;
 }
 
 static const struct iommu_gather_ops mtk_iommu_gather_ops = {

drivers/iommu/mtk_iommu.h

@@ -47,6 +47,7 @@ struct mtk_iommu_data {
 	struct iommu_group		*m4u_group;
 	struct mtk_smi_iommu		smi_imu;      /* SMI larb iommu info */
 	bool                            enable_4GB;
+	bool				tlb_flush_active;
 
 	struct iommu_device		iommu;
 };