Merge tag 'iommu-updates-v6.6' of git://git.kernel.org/pub/scm/linux/kernel/git/joro/iommu

Pull iommu updates from Joerg Roedel:
 "Core changes:

   - Consolidate probe_device path

   - Make the PCI-SAC IOVA allocation trick PCI-only

  AMD IOMMU:

   - Consolidate PPR log handling

   - Interrupt handling improvements

   - Refcount fixes for amd_iommu_v2 driver

  Intel VT-d driver:

   - Enable idxd device DMA with pasid through iommu dma ops

   - Lift RESV_DIRECT check from VT-d driver to core

   - Miscellaneous cleanups and fixes

  ARM-SMMU drivers:

   - Device-tree binding updates:
      - Add additional compatible strings for Qualcomm SoCs
      - Allow ASIDs to be configured in the DT to work around Qualcomm's
        broken hypervisor
      - Fix clocks for Qualcomm's MSM8998 SoC

   - SMMUv2:
      - Support for Qualcomm's legacy firmware implementation featured
        on at least MSM8956 and MSM8976
      - Match compatible strings for Qualcomm SM6350 and SM6375 SoC
        variants

   - SMMUv3:
      - Use 'ida' instead of a bitmap for VMID allocation

   - Rockchip IOMMU:
      - Lift page-table allocation restrictions on newer hardware

   - Mediatek IOMMU:
      - Add MT8188 IOMMU Support

   - Renesas IOMMU:
      - Allow PCIe devices

  .. and the usual set of cleanups an smaller fixes"

* tag 'iommu-updates-v6.6' of git://git.kernel.org/pub/scm/linux/kernel/git/joro/iommu: (64 commits)
  iommu: Explicitly include correct DT includes
  iommu/amd: Remove unused declarations
  iommu/arm-smmu-qcom: Add SM6375 SMMUv2
  iommu/arm-smmu-qcom: Add SM6350 DPU compatible
  iommu/arm-smmu-qcom: Add SM6375 DPU compatible
  iommu/arm-smmu-qcom: Sort the compatible list alphabetically
  dt-bindings: arm-smmu: Fix MSM8998 clocks description
  iommu/vt-d: Remove unused extern declaration dmar_parse_dev_scope()
  iommu/vt-d: Fix to convert mm pfn to dma pfn
  iommu/vt-d: Fix to flush cache of PASID directory table
  iommu/vt-d: Remove rmrr check in domain attaching device path
  iommu: Prevent RESV_DIRECT devices from blocking domains
  dmaengine/idxd: Re-enable kernel workqueue under DMA API
  iommu/vt-d: Add set_dev_pasid callback for dma domain
  iommu/vt-d: Prepare for set_dev_pasid callback
  iommu/vt-d: Make prq draining code generic
  iommu/vt-d: Remove pasid_mutex
  iommu/vt-d: Add domain_flush_pasid_iotlb()
  iommu: Move global PASID allocation from SVA to core
  iommu: Generalize PASID 0 for normal DMA w/o PASID
  ...

5 files changed, 170 insertions, 83 deletions

diff --git a/drivers/iommu/amd/amd_iommu.h b/drivers/iommu/amd/amd_iommu.h
index 0c35018239ce..e2857109e966 100644
--- a/drivers/iommu/amd/amd_iommu.h
+++ b/drivers/iommu/amd/amd_iommu.h
@@ -12,13 +12,14 @@
 #include "amd_iommu_types.h"
 
 irqreturn_t amd_iommu_int_thread(int irq, void *data);
+irqreturn_t amd_iommu_int_thread_evtlog(int irq, void *data);
+irqreturn_t amd_iommu_int_thread_pprlog(int irq, void *data);
+irqreturn_t amd_iommu_int_thread_galog(int irq, void *data);
 irqreturn_t amd_iommu_int_handler(int irq, void *data);
 void amd_iommu_apply_erratum_63(struct amd_iommu *iommu, u16 devid);
 void amd_iommu_restart_event_logging(struct amd_iommu *iommu);
 void amd_iommu_restart_ga_log(struct amd_iommu *iommu);
-int amd_iommu_init_devices(void);
-void amd_iommu_uninit_devices(void);
-void amd_iommu_init_notifier(void);
+void amd_iommu_restart_ppr_log(struct amd_iommu *iommu);
 void amd_iommu_set_rlookup_table(struct amd_iommu *iommu, u16 devid);
 
 #ifdef CONFIG_AMD_IOMMU_DEBUGFS
diff --git a/drivers/iommu/amd/amd_iommu_types.h b/drivers/iommu/amd/amd_iommu_types.h
index dc1db6167927..7dc30c2b56b3 100644
--- a/drivers/iommu/amd/amd_iommu_types.h
+++ b/drivers/iommu/amd/amd_iommu_types.h
@@ -120,10 +120,13 @@
 #define PASID_MASK		0x0000ffff
 
 /* MMIO status bits */
-#define MMIO_STATUS_EVT_OVERFLOW_INT_MASK	BIT(0)
+#define MMIO_STATUS_EVT_OVERFLOW_MASK		BIT(0)
 #define MMIO_STATUS_EVT_INT_MASK		BIT(1)
 #define MMIO_STATUS_COM_WAIT_INT_MASK		BIT(2)
+#define MMIO_STATUS_EVT_RUN_MASK		BIT(3)
+#define MMIO_STATUS_PPR_OVERFLOW_MASK		BIT(5)
 #define MMIO_STATUS_PPR_INT_MASK		BIT(6)
+#define MMIO_STATUS_PPR_RUN_MASK		BIT(7)
 #define MMIO_STATUS_GALOG_RUN_MASK		BIT(8)
 #define MMIO_STATUS_GALOG_OVERFLOW_MASK		BIT(9)
 #define MMIO_STATUS_GALOG_INT_MASK		BIT(10)
@@ -381,15 +384,15 @@
  */
 #define DTE_FLAG_V	BIT_ULL(0)
 #define DTE_FLAG_TV	BIT_ULL(1)
+#define DTE_FLAG_GIOV	BIT_ULL(54)
+#define DTE_FLAG_GV	BIT_ULL(55)
+#define DTE_GLX_SHIFT	(56)
+#define DTE_GLX_MASK	(3)
 #define DTE_FLAG_IR	BIT_ULL(61)
 #define DTE_FLAG_IW	BIT_ULL(62)
 
 #define DTE_FLAG_IOTLB	BIT_ULL(32)
-#define DTE_FLAG_GIOV	BIT_ULL(54)
-#define DTE_FLAG_GV	BIT_ULL(55)
 #define DTE_FLAG_MASK	(0x3ffULL << 32)
-#define DTE_GLX_SHIFT	(56)
-#define DTE_GLX_MASK	(3)
 #define DEV_DOMID_MASK	0xffffULL
 
 #define DTE_GCR3_VAL_A(x)	(((x) >> 12) & 0x00007ULL)
@@ -702,12 +705,21 @@ struct amd_iommu {
 	/* event buffer virtual address */
 	u8 *evt_buf;
 
+	/* Name for event log interrupt */
+	unsigned char evt_irq_name[16];
+
 	/* Base of the PPR log, if present */
 	u8 *ppr_log;
 
+	/* Name for PPR log interrupt */
+	unsigned char ppr_irq_name[16];
+
 	/* Base of the GA log, if present */
 	u8 *ga_log;
 
+	/* Name for GA log interrupt */
+	unsigned char ga_irq_name[16];
+
 	/* Tail of the GA log, if present */
 	u8 *ga_log_tail;
 
diff --git a/drivers/iommu/amd/init.c b/drivers/iommu/amd/init.c
index ea0f1ab94178..45efb7e5d725 100644
--- a/drivers/iommu/amd/init.c
+++ b/drivers/iommu/amd/init.c
@@ -483,6 +483,10 @@ static void iommu_disable(struct amd_iommu *iommu)
 	iommu_feature_disable(iommu, CONTROL_GALOG_EN);
 	iommu_feature_disable(iommu, CONTROL_GAINT_EN);
 
+	/* Disable IOMMU PPR logging */
+	iommu_feature_disable(iommu, CONTROL_PPRLOG_EN);
+	iommu_feature_disable(iommu, CONTROL_PPRINT_EN);
+
 	/* Disable IOMMU hardware itself */
 	iommu_feature_disable(iommu, CONTROL_IOMMU_EN);
 
@@ -753,37 +757,61 @@ static int __init alloc_command_buffer(struct amd_iommu *iommu)
 }
 
 /*
+ * Interrupt handler has processed all pending events and adjusted head
+ * and tail pointer. Reset overflow mask and restart logging again.
+ */
+static void amd_iommu_restart_log(struct amd_iommu *iommu, const char *evt_type,
+				  u8 cntrl_intr, u8 cntrl_log,
+				  u32 status_run_mask, u32 status_overflow_mask)
+{
+	u32 status;
+
+	status = readl(iommu->mmio_base + MMIO_STATUS_OFFSET);
+	if (status & status_run_mask)
+		return;
+
+	pr_info_ratelimited("IOMMU %s log restarting\n", evt_type);
+
+	iommu_feature_disable(iommu, cntrl_log);
+	iommu_feature_disable(iommu, cntrl_intr);
+
+	writel(status_overflow_mask, iommu->mmio_base + MMIO_STATUS_OFFSET);
+
+	iommu_feature_enable(iommu, cntrl_intr);
+	iommu_feature_enable(iommu, cntrl_log);
+}
+
+/*
  * This function restarts event logging in case the IOMMU experienced
  * an event log buffer overflow.
  */
 void amd_iommu_restart_event_logging(struct amd_iommu *iommu)
 {
-	iommu_feature_disable(iommu, CONTROL_EVT_LOG_EN);
-	iommu_feature_enable(iommu, CONTROL_EVT_LOG_EN);
+	amd_iommu_restart_log(iommu, "Event", CONTROL_EVT_INT_EN,
+			      CONTROL_EVT_LOG_EN, MMIO_STATUS_EVT_RUN_MASK,
+			      MMIO_STATUS_EVT_OVERFLOW_MASK);
 }
 
 /*
  * This function restarts event logging in case the IOMMU experienced
- * an GA log overflow.
+ * GA log overflow.
  */
 void amd_iommu_restart_ga_log(struct amd_iommu *iommu)
 {
-	u32 status;
-
-	status = readl(iommu->mmio_base + MMIO_STATUS_OFFSET);
-	if (status & MMIO_STATUS_GALOG_RUN_MASK)
-		return;
-
-	pr_info_ratelimited("IOMMU GA Log restarting\n");
-
-	iommu_feature_disable(iommu, CONTROL_GALOG_EN);
-	iommu_feature_disable(iommu, CONTROL_GAINT_EN);
-
-	writel(MMIO_STATUS_GALOG_OVERFLOW_MASK,
-	       iommu->mmio_base + MMIO_STATUS_OFFSET);
+	amd_iommu_restart_log(iommu, "GA", CONTROL_GAINT_EN,
+			      CONTROL_GALOG_EN, MMIO_STATUS_GALOG_RUN_MASK,
+			      MMIO_STATUS_GALOG_OVERFLOW_MASK);
+}
 
-	iommu_feature_enable(iommu, CONTROL_GAINT_EN);
-	iommu_feature_enable(iommu, CONTROL_GALOG_EN);
+/*
+ * This function restarts ppr logging in case the IOMMU experienced
+ * PPR log overflow.
+ */
+void amd_iommu_restart_ppr_log(struct amd_iommu *iommu)
+{
+	amd_iommu_restart_log(iommu, "PPR", CONTROL_PPRINT_EN,
+			      CONTROL_PPRLOG_EN, MMIO_STATUS_PPR_RUN_MASK,
+			      MMIO_STATUS_PPR_OVERFLOW_MASK);
 }
 
 /*
@@ -906,6 +934,8 @@ static void iommu_enable_ppr_log(struct amd_iommu *iommu)
 	if (iommu->ppr_log == NULL)
 		return;
 
+	iommu_feature_enable(iommu, CONTROL_PPR_EN);
+
 	entry = iommu_virt_to_phys(iommu->ppr_log) | PPR_LOG_SIZE_512;
 
 	memcpy_toio(iommu->mmio_base + MMIO_PPR_LOG_OFFSET,
@@ -916,7 +946,7 @@ static void iommu_enable_ppr_log(struct amd_iommu *iommu)
 	writel(0x00, iommu->mmio_base + MMIO_PPR_TAIL_OFFSET);
 
 	iommu_feature_enable(iommu, CONTROL_PPRLOG_EN);
-	iommu_feature_enable(iommu, CONTROL_PPR_EN);
+	iommu_feature_enable(iommu, CONTROL_PPRINT_EN);
 }
 
 static void __init free_ppr_log(struct amd_iommu *iommu)
@@ -2311,6 +2341,7 @@ static int intcapxt_irqdomain_alloc(struct irq_domain *domain, unsigned int virq
 		struct irq_data *irqd = irq_domain_get_irq_data(domain, i);
 
 		irqd->chip = &intcapxt_controller;
+		irqd->hwirq = info->hwirq;
 		irqd->chip_data = info->data;
 		__irq_set_handler(i, handle_edge_irq, 0, "edge");
 	}
@@ -2337,22 +2368,14 @@ static void intcapxt_unmask_irq(struct irq_data *irqd)
 	xt.destid_0_23 = cfg->dest_apicid & GENMASK(23, 0);
 	xt.destid_24_31 = cfg->dest_apicid >> 24;
 
-	/**
-	 * Current IOMMU implementation uses the same IRQ for all
-	 * 3 IOMMU interrupts.
-	 */
-	writeq(xt.capxt, iommu->mmio_base + MMIO_INTCAPXT_EVT_OFFSET);
-	writeq(xt.capxt, iommu->mmio_base + MMIO_INTCAPXT_PPR_OFFSET);
-	writeq(xt.capxt, iommu->mmio_base + MMIO_INTCAPXT_GALOG_OFFSET);
+	writeq(xt.capxt, iommu->mmio_base + irqd->hwirq);
 }
 
 static void intcapxt_mask_irq(struct irq_data *irqd)
 {
 	struct amd_iommu *iommu = irqd->chip_data;
 
-	writeq(0, iommu->mmio_base + MMIO_INTCAPXT_EVT_OFFSET);
-	writeq(0, iommu->mmio_base + MMIO_INTCAPXT_PPR_OFFSET);
-	writeq(0, iommu->mmio_base + MMIO_INTCAPXT_GALOG_OFFSET);
+	writeq(0, iommu->mmio_base + irqd->hwirq);
 }
 
 
@@ -2415,7 +2438,8 @@ static struct irq_domain *iommu_get_irqdomain(void)
 	return iommu_irqdomain;
 }
 
-static int iommu_setup_intcapxt(struct amd_iommu *iommu)
+static int __iommu_setup_intcapxt(struct amd_iommu *iommu, const char *devname,
+				  int hwirq, irq_handler_t thread_fn)
 {
 	struct irq_domain *domain;
 	struct irq_alloc_info info;
@@ -2429,6 +2453,7 @@ static int iommu_setup_intcapxt(struct amd_iommu *iommu)
 	init_irq_alloc_info(&info, NULL);
 	info.type = X86_IRQ_ALLOC_TYPE_AMDVI;
 	info.data = iommu;
+	info.hwirq = hwirq;
 
 	irq = irq_domain_alloc_irqs(domain, 1, node, &info);
 	if (irq < 0) {
@@ -2437,7 +2462,7 @@ static int iommu_setup_intcapxt(struct amd_iommu *iommu)
 	}
 
 	ret = request_threaded_irq(irq, amd_iommu_int_handler,
-				   amd_iommu_int_thread, 0, "AMD-Vi", iommu);
+				   thread_fn, 0, devname, iommu);
 	if (ret) {
 		irq_domain_free_irqs(irq, 1);
 		irq_domain_remove(domain);
@@ -2447,6 +2472,37 @@ static int iommu_setup_intcapxt(struct amd_iommu *iommu)
 	return 0;
 }
 
+static int iommu_setup_intcapxt(struct amd_iommu *iommu)
+{
+	int ret;
+
+	snprintf(iommu->evt_irq_name, sizeof(iommu->evt_irq_name),
+		 "AMD-Vi%d-Evt", iommu->index);
+	ret = __iommu_setup_intcapxt(iommu, iommu->evt_irq_name,
+				     MMIO_INTCAPXT_EVT_OFFSET,
+				     amd_iommu_int_thread_evtlog);
+	if (ret)
+		return ret;
+
+	snprintf(iommu->ppr_irq_name, sizeof(iommu->ppr_irq_name),
+		 "AMD-Vi%d-PPR", iommu->index);
+	ret = __iommu_setup_intcapxt(iommu, iommu->ppr_irq_name,
+				     MMIO_INTCAPXT_PPR_OFFSET,
+				     amd_iommu_int_thread_pprlog);
+	if (ret)
+		return ret;
+
+#ifdef CONFIG_IRQ_REMAP
+	snprintf(iommu->ga_irq_name, sizeof(iommu->ga_irq_name),
+		 "AMD-Vi%d-GA", iommu->index);
+	ret = __iommu_setup_intcapxt(iommu, iommu->ga_irq_name,
+				     MMIO_INTCAPXT_GALOG_OFFSET,
+				     amd_iommu_int_thread_galog);
+#endif
+
+	return ret;
+}
+
 static int iommu_init_irq(struct amd_iommu *iommu)
 {
 	int ret;
@@ -2472,8 +2528,6 @@ enable_faults:
 
 	iommu_feature_enable(iommu, CONTROL_EVT_INT_EN);
 
-	if (iommu->ppr_log != NULL)
-		iommu_feature_enable(iommu, CONTROL_PPRINT_EN);
 	return 0;
 }
 
@@ -2889,8 +2943,6 @@ static void enable_iommus_vapic(void)
 static void enable_iommus(void)
 {
 	early_enable_iommus();
-	enable_iommus_vapic();
-	enable_iommus_v2();
 }
 
 static void disable_iommus(void)
@@ -3154,6 +3206,13 @@ static int amd_iommu_enable_interrupts(void)
 			goto out;
 	}
 
+	/*
+	 * Interrupt handler is ready to process interrupts. Enable
+	 * PPR and GA log interrupt for all IOMMUs.
+	 */
+	enable_iommus_vapic();
+	enable_iommus_v2();
+
 out:
 	return ret;
 }
@@ -3233,8 +3292,6 @@ static int __init state_next(void)
 		register_syscore_ops(&amd_iommu_syscore_ops);
 		ret = amd_iommu_init_pci();
 		init_state = ret ? IOMMU_INIT_ERROR : IOMMU_PCI_INIT;
-		enable_iommus_vapic();
-		enable_iommus_v2();
 		break;
 	case IOMMU_PCI_INIT:
 		ret = amd_iommu_enable_interrupts();
diff --git a/drivers/iommu/amd/iommu.c b/drivers/iommu/amd/iommu.c
index 7d7d3799199a..95bd7c25ba6f 100644
--- a/drivers/iommu/amd/iommu.c
+++ b/drivers/iommu/amd/iommu.c
@@ -841,50 +841,27 @@ static inline void
 amd_iommu_set_pci_msi_domain(struct device *dev, struct amd_iommu *iommu) { }
 #endif /* !CONFIG_IRQ_REMAP */
 
-#define AMD_IOMMU_INT_MASK	\
-	(MMIO_STATUS_EVT_OVERFLOW_INT_MASK | \
-	 MMIO_STATUS_EVT_INT_MASK | \
-	 MMIO_STATUS_PPR_INT_MASK | \
-	 MMIO_STATUS_GALOG_OVERFLOW_MASK | \
-	 MMIO_STATUS_GALOG_INT_MASK)
-
-irqreturn_t amd_iommu_int_thread(int irq, void *data)
+static void amd_iommu_handle_irq(void *data, const char *evt_type,
+				 u32 int_mask, u32 overflow_mask,
+				 void (*int_handler)(struct amd_iommu *),
+				 void (*overflow_handler)(struct amd_iommu *))
 {
 	struct amd_iommu *iommu = (struct amd_iommu *) data;
 	u32 status = readl(iommu->mmio_base + MMIO_STATUS_OFFSET);
+	u32 mask = int_mask | overflow_mask;
 
-	while (status & AMD_IOMMU_INT_MASK) {
+	while (status & mask) {
 		/* Enable interrupt sources again */
-		writel(AMD_IOMMU_INT_MASK,
-			iommu->mmio_base + MMIO_STATUS_OFFSET);
+		writel(mask, iommu->mmio_base + MMIO_STATUS_OFFSET);
 
-		if (status & MMIO_STATUS_EVT_INT_MASK) {
-			pr_devel("Processing IOMMU Event Log\n");
-			iommu_poll_events(iommu);
+		if (int_handler) {
+			pr_devel("Processing IOMMU (ivhd%d) %s Log\n",
+				 iommu->index, evt_type);
+			int_handler(iommu);
 		}
 
-		if (status & MMIO_STATUS_PPR_INT_MASK) {
-			pr_devel("Processing IOMMU PPR Log\n");
-			iommu_poll_ppr_log(iommu);
-		}
-
-#ifdef CONFIG_IRQ_REMAP
-		if (status & (MMIO_STATUS_GALOG_INT_MASK |
-			      MMIO_STATUS_GALOG_OVERFLOW_MASK)) {
-			pr_devel("Processing IOMMU GA Log\n");
-			iommu_poll_ga_log(iommu);
-		}
-
-		if (status & MMIO_STATUS_GALOG_OVERFLOW_MASK) {
-			pr_info_ratelimited("IOMMU GA Log overflow\n");
-			amd_iommu_restart_ga_log(iommu);
-		}
-#endif
-
-		if (status & MMIO_STATUS_EVT_OVERFLOW_INT_MASK) {
-			pr_info_ratelimited("IOMMU event log overflow\n");
-			amd_iommu_restart_event_logging(iommu);
-		}
+		if ((status & overflow_mask) && overflow_handler)
+			overflow_handler(iommu);
 
 		/*
 		 * Hardware bug: ERBT1312
@@ -901,6 +878,43 @@ irqreturn_t amd_iommu_int_thread(int irq, void *data)
 		 */
 		status = readl(iommu->mmio_base + MMIO_STATUS_OFFSET);
 	}
+}
+
+irqreturn_t amd_iommu_int_thread_evtlog(int irq, void *data)
+{
+	amd_iommu_handle_irq(data, "Evt", MMIO_STATUS_EVT_INT_MASK,
+			     MMIO_STATUS_EVT_OVERFLOW_MASK,
+			     iommu_poll_events, amd_iommu_restart_event_logging);
+
+	return IRQ_HANDLED;
+}
+
+irqreturn_t amd_iommu_int_thread_pprlog(int irq, void *data)
+{
+	amd_iommu_handle_irq(data, "PPR", MMIO_STATUS_PPR_INT_MASK,
+			     MMIO_STATUS_PPR_OVERFLOW_MASK,
+			     iommu_poll_ppr_log, amd_iommu_restart_ppr_log);
+
+	return IRQ_HANDLED;
+}
+
+irqreturn_t amd_iommu_int_thread_galog(int irq, void *data)
+{
+#ifdef CONFIG_IRQ_REMAP
+	amd_iommu_handle_irq(data, "GA", MMIO_STATUS_GALOG_INT_MASK,
+			     MMIO_STATUS_GALOG_OVERFLOW_MASK,
+			     iommu_poll_ga_log, amd_iommu_restart_ga_log);
+#endif
+
+	return IRQ_HANDLED;
+}
+
+irqreturn_t amd_iommu_int_thread(int irq, void *data)
+{
+	amd_iommu_int_thread_evtlog(irq, data);
+	amd_iommu_int_thread_pprlog(irq, data);
+	amd_iommu_int_thread_galog(irq, data);
+
 	return IRQ_HANDLED;
 }
 
diff --git a/drivers/iommu/amd/iommu_v2.c b/drivers/iommu/amd/iommu_v2.c
index 2596466cd5a6..57c2fb1146e2 100644
--- a/drivers/iommu/amd/iommu_v2.c
+++ b/drivers/iommu/amd/iommu_v2.c
@@ -262,8 +262,8 @@ static void put_pasid_state(struct pasid_state *pasid_state)
 
 static void put_pasid_state_wait(struct pasid_state *pasid_state)
 {
-	refcount_dec(&pasid_state->count);
-	wait_event(pasid_state->wq, !refcount_read(&pasid_state->count));
+	if (!refcount_dec_and_test(&pasid_state->count))
+		wait_event(pasid_state->wq, !refcount_read(&pasid_state->count));
 	free_pasid_state(pasid_state);
 }
 
@@ -327,6 +327,9 @@ static void free_pasid_states(struct device_state *dev_state)
 
 		put_pasid_state(pasid_state);
 
+		/* Clear the pasid state so that the pasid can be re-used */
+		clear_pasid_state(dev_state, pasid_state->pasid);
+
 		/*
 		 * This will call the mn_release function and
 		 * unbind the PASID