Merge tag 'iommu-updates-v5.10' of git://git.kernel.org/pub/scm/linux/kernel/git/joro/iommu

Pull iommu updates from Joerg Roedel:

 - ARM-SMMU Updates from Will:

      - Continued SVM enablement, where page-table is shared with CPU

      - Groundwork to support integrated SMMU with Adreno GPU

      - Allow disabling of MSI-based polling on the kernel command-line

      - Minor driver fixes and cleanups (octal permissions, error
        messages, ...)

 - Secure Nested Paging Support for AMD IOMMU. The IOMMU will fault when
   a device tries DMA on memory owned by a guest. This needs new
   fault-types as well as a rewrite of the IOMMU memory semaphore for
   command completions.

 - Allow broken Intel IOMMUs (wrong address widths reported) to still be
   used for interrupt remapping.

 - IOMMU UAPI updates for supporting vSVA, where the IOMMU can access
   address spaces of processes running in a VM.

 - Support for the MT8167 IOMMU in the Mediatek IOMMU driver.

 - Device-tree updates for the Renesas driver to support r8a7742.

 - Several smaller fixes and cleanups all over the place.

* tag 'iommu-updates-v5.10' of git://git.kernel.org/pub/scm/linux/kernel/git/joro/iommu: (57 commits)
  iommu/vt-d: Gracefully handle DMAR units with no supported address widths
  iommu/vt-d: Check UAPI data processed by IOMMU core
  iommu/uapi: Handle data and argsz filled by users
  iommu/uapi: Rename uapi functions
  iommu/uapi: Use named union for user data
  iommu/uapi: Add argsz for user filled data
  docs: IOMMU user API
  iommu/qcom: add missing put_device() call in qcom_iommu_of_xlate()
  iommu/arm-smmu-v3: Add SVA device feature
  iommu/arm-smmu-v3: Check for SVA features
  iommu/arm-smmu-v3: Seize private ASID
  iommu/arm-smmu-v3: Share process page tables
  iommu/arm-smmu-v3: Move definitions to a header
  iommu/io-pgtable-arm: Move some definitions to a header
  iommu/arm-smmu-v3: Ensure queue is read after updating prod pointer
  iommu/amd: Re-purpose Exclusion range registers to support SNP CWWB
  iommu/amd: Add support for RMP_PAGE_FAULT and RMP_HW_ERR
  iommu/amd: Use 4K page for completion wait write-back semaphore
  iommu/tegra-smmu: Allow to group clients in same swgroup
  iommu/tegra-smmu: Fix iova->phys translation
  ...

4 files changed, 138 insertions, 15 deletions

diff --git a/drivers/iommu/amd/amd_iommu.h b/drivers/iommu/amd/amd_iommu.h
index 030ee90197a1..6b8cbdf71714 100644
--- a/drivers/iommu/amd/amd_iommu.h
+++ b/drivers/iommu/amd/amd_iommu.h
@@ -41,6 +41,15 @@ extern int amd_iommu_guest_ir;
 struct iommu_domain;
 
 extern bool amd_iommu_v2_supported(void);
+extern struct amd_iommu *get_amd_iommu(unsigned int idx);
+extern u8 amd_iommu_pc_get_max_banks(unsigned int idx);
+extern bool amd_iommu_pc_supported(void);
+extern u8 amd_iommu_pc_get_max_counters(unsigned int idx);
+extern int amd_iommu_pc_get_reg(struct amd_iommu *iommu, u8 bank, u8 cntr,
+				u8 fxn, u64 *value);
+extern int amd_iommu_pc_set_reg(struct amd_iommu *iommu, u8 bank, u8 cntr,
+				u8 fxn, u64 *value);
+
 extern int amd_iommu_register_ppr_notifier(struct notifier_block *nb);
 extern int amd_iommu_unregister_ppr_notifier(struct notifier_block *nb);
 extern void amd_iommu_domain_direct_map(struct iommu_domain *dom);
diff --git a/drivers/iommu/amd/amd_iommu_types.h b/drivers/iommu/amd/amd_iommu_types.h
index 30a5d412255a..f696ac7c5f89 100644
--- a/drivers/iommu/amd/amd_iommu_types.h
+++ b/drivers/iommu/amd/amd_iommu_types.h
@@ -93,6 +93,7 @@
 #define FEATURE_PC		(1ULL<<9)
 #define FEATURE_GAM_VAPIC	(1ULL<<21)
 #define FEATURE_EPHSUP		(1ULL<<50)
+#define FEATURE_SNP		(1ULL<<63)
 
 #define FEATURE_PASID_SHIFT	32
 #define FEATURE_PASID_MASK	(0x1fULL << FEATURE_PASID_SHIFT)
@@ -128,6 +129,8 @@
 #define EVENT_TYPE_IOTLB_INV_TO	0x7
 #define EVENT_TYPE_INV_DEV_REQ	0x8
 #define EVENT_TYPE_INV_PPR_REQ	0x9
+#define EVENT_TYPE_RMP_FAULT	0xd
+#define EVENT_TYPE_RMP_HW_ERR	0xe
 #define EVENT_DEVID_MASK	0xffff
 #define EVENT_DEVID_SHIFT	0
 #define EVENT_DOMID_MASK_LO	0xffff
@@ -595,7 +598,8 @@ struct amd_iommu {
 #endif
 
 	u32 flags;
-	volatile u64 __aligned(8) cmd_sem;
+	volatile u64 *cmd_sem;
+	u64 cmd_sem_val;
 
 #ifdef CONFIG_AMD_IOMMU_DEBUGFS
 	/* DebugFS Info */
diff --git a/drivers/iommu/amd/init.c b/drivers/iommu/amd/init.c
index 1ba6b4cc56e8..82e4af8f09bb 100644
--- a/drivers/iommu/amd/init.c
+++ b/drivers/iommu/amd/init.c
@@ -359,6 +359,29 @@ static void iommu_set_exclusion_range(struct amd_iommu *iommu)
 			&entry, sizeof(entry));
 }
 
+static void iommu_set_cwwb_range(struct amd_iommu *iommu)
+{
+	u64 start = iommu_virt_to_phys((void *)iommu->cmd_sem);
+	u64 entry = start & PM_ADDR_MASK;
+
+	if (!iommu_feature(iommu, FEATURE_SNP))
+		return;
+
+	/* Note:
+	 * Re-purpose Exclusion base/limit registers for Completion wait
+	 * write-back base/limit.
+	 */
+	memcpy_toio(iommu->mmio_base + MMIO_EXCL_BASE_OFFSET,
+		    &entry, sizeof(entry));
+
+	/* Note:
+	 * Default to 4 Kbytes, which can be specified by setting base
+	 * address equal to the limit address.
+	 */
+	memcpy_toio(iommu->mmio_base + MMIO_EXCL_LIMIT_OFFSET,
+		    &entry, sizeof(entry));
+}
+
 /* Programs the physical address of the device table into the IOMMU hardware */
 static void iommu_set_device_table(struct amd_iommu *iommu)
 {
@@ -813,6 +836,19 @@ static int iommu_init_ga(struct amd_iommu *iommu)
 	return ret;
 }
 
+static int __init alloc_cwwb_sem(struct amd_iommu *iommu)
+{
+	iommu->cmd_sem = (void *)get_zeroed_page(GFP_KERNEL);
+
+	return iommu->cmd_sem ? 0 : -ENOMEM;
+}
+
+static void __init free_cwwb_sem(struct amd_iommu *iommu)
+{
+	if (iommu->cmd_sem)
+		free_page((unsigned long)iommu->cmd_sem);
+}
+
 static void iommu_enable_xt(struct amd_iommu *iommu)
 {
 #ifdef CONFIG_IRQ_REMAP
@@ -1376,6 +1412,7 @@ static int __init init_iommu_from_acpi(struct amd_iommu *iommu,
 
 static void __init free_iommu_one(struct amd_iommu *iommu)
 {
+	free_cwwb_sem(iommu);
 	free_command_buffer(iommu);
 	free_event_buffer(iommu);
 	free_ppr_log(iommu);
@@ -1462,6 +1499,7 @@ static int __init init_iommu_one(struct amd_iommu *iommu, struct ivhd_header *h)
 	int ret;
 
 	raw_spin_lock_init(&iommu->lock);
+	iommu->cmd_sem_val = 0;
 
 	/* Add IOMMU to internal data structures */
 	list_add_tail(&iommu->list, &amd_iommu_list);
@@ -1539,6 +1577,9 @@ static int __init init_iommu_one(struct amd_iommu *iommu, struct ivhd_header *h)
 	if (!iommu->mmio_base)
 		return -ENOMEM;
 
+	if (alloc_cwwb_sem(iommu))
+		return -ENOMEM;
+
 	if (alloc_command_buffer(iommu))
 		return -ENOMEM;
 
@@ -1576,7 +1617,7 @@ static int __init init_iommu_one(struct amd_iommu *iommu, struct ivhd_header *h)
 
 /**
  * get_highest_supported_ivhd_type - Look up the appropriate IVHD type
- * @ivrs          Pointer to the IVRS header
+ * @ivrs: Pointer to the IVRS header
  *
  * This function search through all IVDB of the maximum supported IVHD
  */
@@ -1864,6 +1905,9 @@ static int __init amd_iommu_init_pci(void)
 		ret = iommu_init_pci(iommu);
 		if (ret)
 			break;
+
+		/* Need to setup range after PCI init */
+		iommu_set_cwwb_range(iommu);
 	}
 
 	/*
@@ -1927,7 +1971,7 @@ static int iommu_setup_msi(struct amd_iommu *iommu)
 #define XT_INT_VEC(x)		(((x) & 0xFFULL) << 32)
 #define XT_INT_DEST_HI(x)	((((x) >> 24) & 0xFFULL) << 56)
 
-/**
+/*
  * Setup the IntCapXT registers with interrupt routing information
  * based on the PCI MSI capability block registers, accessed via
  * MMIO MSI address low/hi and MSI data registers.
diff --git a/drivers/iommu/amd/iommu.c b/drivers/iommu/amd/iommu.c
index 9e231caa5012..4b1b02c80f55 100644
--- a/drivers/iommu/amd/iommu.c
+++ b/drivers/iommu/amd/iommu.c
@@ -486,6 +486,67 @@ static void dump_command(unsigned long phys_addr)
 		pr_err("CMD[%d]: %08x\n", i, cmd->data[i]);
 }
 
+static void amd_iommu_report_rmp_hw_error(volatile u32 *event)
+{
+	struct iommu_dev_data *dev_data = NULL;
+	int devid, vmg_tag, flags;
+	struct pci_dev *pdev;
+	u64 spa;
+
+	devid   = (event[0] >> EVENT_DEVID_SHIFT) & EVENT_DEVID_MASK;
+	vmg_tag = (event[1]) & 0xFFFF;
+	flags   = (event[1] >> EVENT_FLAGS_SHIFT) & EVENT_FLAGS_MASK;
+	spa     = ((u64)event[3] << 32) | (event[2] & 0xFFFFFFF8);
+
+	pdev = pci_get_domain_bus_and_slot(0, PCI_BUS_NUM(devid),
+					   devid & 0xff);
+	if (pdev)
+		dev_data = dev_iommu_priv_get(&pdev->dev);
+
+	if (dev_data && __ratelimit(&dev_data->rs)) {
+		pci_err(pdev, "Event logged [RMP_HW_ERROR vmg_tag=0x%04x, spa=0x%llx, flags=0x%04x]\n",
+			vmg_tag, spa, flags);
+	} else {
+		pr_err_ratelimited("Event logged [RMP_HW_ERROR device=%02x:%02x.%x, vmg_tag=0x%04x, spa=0x%llx, flags=0x%04x]\n",
+			PCI_BUS_NUM(devid), PCI_SLOT(devid), PCI_FUNC(devid),
+			vmg_tag, spa, flags);
+	}
+
+	if (pdev)
+		pci_dev_put(pdev);
+}
+
+static void amd_iommu_report_rmp_fault(volatile u32 *event)
+{
+	struct iommu_dev_data *dev_data = NULL;
+	int devid, flags_rmp, vmg_tag, flags;
+	struct pci_dev *pdev;
+	u64 gpa;
+
+	devid     = (event[0] >> EVENT_DEVID_SHIFT) & EVENT_DEVID_MASK;
+	flags_rmp = (event[0] >> EVENT_FLAGS_SHIFT) & 0xFF;
+	vmg_tag   = (event[1]) & 0xFFFF;
+	flags     = (event[1] >> EVENT_FLAGS_SHIFT) & EVENT_FLAGS_MASK;
+	gpa       = ((u64)event[3] << 32) | event[2];
+
+	pdev = pci_get_domain_bus_and_slot(0, PCI_BUS_NUM(devid),
+					   devid & 0xff);
+	if (pdev)
+		dev_data = dev_iommu_priv_get(&pdev->dev);
+
+	if (dev_data && __ratelimit(&dev_data->rs)) {
+		pci_err(pdev, "Event logged [RMP_PAGE_FAULT vmg_tag=0x%04x, gpa=0x%llx, flags_rmp=0x%04x, flags=0x%04x]\n",
+			vmg_tag, gpa, flags_rmp, flags);
+	} else {
+		pr_err_ratelimited("Event logged [RMP_PAGE_FAULT device=%02x:%02x.%x, vmg_tag=0x%04x, gpa=0x%llx, flags_rmp=0x%04x, flags=0x%04x]\n",
+			PCI_BUS_NUM(devid), PCI_SLOT(devid), PCI_FUNC(devid),
+			vmg_tag, gpa, flags_rmp, flags);
+	}
+
+	if (pdev)
+		pci_dev_put(pdev);
+}
+
 static void amd_iommu_report_page_fault(u16 devid, u16 domain_id,
 					u64 address, int flags)
 {
@@ -578,6 +639,12 @@ retry:
 			PCI_BUS_NUM(devid), PCI_SLOT(devid), PCI_FUNC(devid),
 			pasid, address, flags);
 		break;
+	case EVENT_TYPE_RMP_FAULT:
+		amd_iommu_report_rmp_fault(event);
+		break;
+	case EVENT_TYPE_RMP_HW_ERR:
+		amd_iommu_report_rmp_hw_error(event);
+		break;
 	case EVENT_TYPE_INV_PPR_REQ:
 		pasid = PPR_PASID(*((u64 *)__evt));
 		tag = event[1] & 0x03FF;
@@ -807,11 +874,11 @@ irqreturn_t amd_iommu_int_handler(int irq, void *data)
  *
  ****************************************************************************/
 
-static int wait_on_sem(volatile u64 *sem)
+static int wait_on_sem(struct amd_iommu *iommu, u64 data)
 {
 	int i = 0;
 
-	while (*sem == 0 && i < LOOP_TIMEOUT) {
+	while (*iommu->cmd_sem != data && i < LOOP_TIMEOUT) {
 		udelay(1);
 		i += 1;
 	}
@@ -842,16 +909,16 @@ static void copy_cmd_to_buffer(struct amd_iommu *iommu,
 	writel(tail, iommu->mmio_base + MMIO_CMD_TAIL_OFFSET);
 }
 
-static void build_completion_wait(struct iommu_cmd *cmd, u64 address)
+static void build_completion_wait(struct iommu_cmd *cmd,
+				  struct amd_iommu *iommu,
+				  u64 data)
 {
-	u64 paddr = iommu_virt_to_phys((void *)address);
-
-	WARN_ON(address & 0x7ULL);
+	u64 paddr = iommu_virt_to_phys((void *)iommu->cmd_sem);
 
 	memset(cmd, 0, sizeof(*cmd));
 	cmd->data[0] = lower_32_bits(paddr) | CMD_COMPL_WAIT_STORE_MASK;
 	cmd->data[1] = upper_32_bits(paddr);
-	cmd->data[2] = 1;
+	cmd->data[2] = data;
 	CMD_SET_TYPE(cmd, CMD_COMPL_WAIT);
 }
 
@@ -1060,22 +1127,21 @@ static int iommu_completion_wait(struct amd_iommu *iommu)
 	struct iommu_cmd cmd;
 	unsigned long flags;
 	int ret;
+	u64 data;
 
 	if (!iommu->need_sync)
 		return 0;
 
-
-	build_completion_wait(&cmd, (u64)&iommu->cmd_sem);
-
 	raw_spin_lock_irqsave(&iommu->lock, flags);
 
-	iommu->cmd_sem = 0;
+	data = ++iommu->cmd_sem_val;
+	build_completion_wait(&cmd, iommu, data);
 
 	ret = __iommu_queue_command_sync(iommu, &cmd, false);
 	if (ret)
 		goto out_unlock;
 
-	ret = wait_on_sem(&iommu->cmd_sem);
+	ret = wait_on_sem(iommu, data);
 
 out_unlock:
 	raw_spin_unlock_irqrestore(&iommu->lock, flags);