core/iommu updates for v2.6.40

index 916bc81..55d95eb 100644
@@ -19,13 +19,12 @@
 #ifndef _ASM_X86_AMD_IOMMU_PROTO_H
 #define _ASM_X86_AMD_IOMMU_PROTO_H
 
-struct amd_iommu;
+#include <asm/amd_iommu_types.h>
 
 extern int amd_iommu_init_dma_ops(void);
 extern int amd_iommu_init_passthrough(void);
+extern irqreturn_t amd_iommu_int_thread(int irq, void *data);
 extern irqreturn_t amd_iommu_int_handler(int irq, void *data);
-extern void amd_iommu_flush_all_domains(void);
-extern void amd_iommu_flush_all_devices(void);
 extern void amd_iommu_apply_erratum_63(u16 devid);
 extern void amd_iommu_reset_cmd_buffer(struct amd_iommu *iommu);
 extern int amd_iommu_init_devices(void);

@@ -44,4 +43,12 @@ static inline bool is_rd890_iommu(struct pci_dev *pdev)
 	       (pdev->device == PCI_DEVICE_ID_RD890_IOMMU);
 }
 
+static inline bool iommu_feature(struct amd_iommu *iommu, u64 f)
+{
+	if (!(iommu->cap & (1 << IOMMU_CAP_EFR)))
+		return false;
+
+	return !!(iommu->features & f);
+}
+
 #endif /* _ASM_X86_AMD_IOMMU_PROTO_H  */

index e3509fc..4c99829 100644
@@ -68,12 +68,25 @@
 #define MMIO_CONTROL_OFFSET     0x0018
 #define MMIO_EXCL_BASE_OFFSET   0x0020
 #define MMIO_EXCL_LIMIT_OFFSET  0x0028
+#define MMIO_EXT_FEATURES	0x0030
 #define MMIO_CMD_HEAD_OFFSET	0x2000
 #define MMIO_CMD_TAIL_OFFSET	0x2008
 #define MMIO_EVT_HEAD_OFFSET	0x2010
 #define MMIO_EVT_TAIL_OFFSET	0x2018
 #define MMIO_STATUS_OFFSET	0x2020
 
+
+/* Extended Feature Bits */
+#define FEATURE_PREFETCH	(1ULL<<0)
+#define FEATURE_PPR		(1ULL<<1)
+#define FEATURE_X2APIC		(1ULL<<2)
+#define FEATURE_NX		(1ULL<<3)
+#define FEATURE_GT		(1ULL<<4)
+#define FEATURE_IA		(1ULL<<6)
+#define FEATURE_GA		(1ULL<<7)
+#define FEATURE_HE		(1ULL<<8)
+#define FEATURE_PC		(1ULL<<9)
+
 /* MMIO status bits */
 #define MMIO_STATUS_COM_WAIT_INT_MASK	0x04
 

@@ -113,7 +126,9 @@
 /* command specific defines */
 #define CMD_COMPL_WAIT          0x01
 #define CMD_INV_DEV_ENTRY       0x02
-#define CMD_INV_IOMMU_PAGES     0x03
+#define CMD_INV_IOMMU_PAGES	0x03
+#define CMD_INV_IOTLB_PAGES	0x04
+#define CMD_INV_ALL		0x08
 
 #define CMD_COMPL_WAIT_STORE_MASK	0x01
 #define CMD_COMPL_WAIT_INT_MASK		0x02

@@ -215,6 +230,8 @@
 #define IOMMU_PTE_IR (1ULL << 61)
 #define IOMMU_PTE_IW (1ULL << 62)
 
+#define DTE_FLAG_IOTLB	0x01
+
 #define IOMMU_PAGE_MASK (((1ULL << 52) - 1) & ~0xfffULL)
 #define IOMMU_PTE_PRESENT(pte) ((pte) & IOMMU_PTE_P)
 #define IOMMU_PTE_PAGE(pte) (phys_to_virt((pte) & IOMMU_PAGE_MASK))

@@ -227,6 +244,7 @@
 /* IOMMU capabilities */
 #define IOMMU_CAP_IOTLB   24
 #define IOMMU_CAP_NPCACHE 26
+#define IOMMU_CAP_EFR     27
 
 #define MAX_DOMAIN_ID 65536
 

@@ -249,6 +267,8 @@ extern bool amd_iommu_dump;
 
 /* global flag if IOMMUs cache non-present entries */
 extern bool amd_iommu_np_cache;
+/* Only true if all IOMMUs support device IOTLBs */
+extern bool amd_iommu_iotlb_sup;
 
 /*
  * Make iterating over all IOMMUs easier

@@ -371,6 +391,9 @@ struct amd_iommu {
 	/* flags read from acpi table */
 	u8 acpi_flags;
 
+	/* Extended features */
+	u64 features;
+
 	/*
 	 * Capability pointer. There could be more than one IOMMU per PCI
 	 * device function if there are more than one AMD IOMMU capability

@@ -409,9 +432,6 @@ struct amd_iommu {
 	/* if one, we need to send a completion wait command */
 	bool need_sync;
 
-	/* becomes true if a command buffer reset is running */
-	bool reset_in_progress;
-
 	/* default dma_ops domain for that IOMMU */
 	struct dma_ops_domain *default_dom;
 

similarity index 100%
rename from arch/x86/kernel/pci-gart_64.c
rename to arch/x86/kernel/amd_gart_64.c

847 lines not on this page · raw message

98 lines not on this page · raw message

index 55d745e..35ccf75 100644
@@ -50,20 +50,14 @@ void __init check_iommu_entries(struct iommu_table_entry *start,
 				struct iommu_table_entry *finish)
 {
 	struct iommu_table_entry *p, *q, *x;
-	char sym_p[KSYM_SYMBOL_LEN];
-	char sym_q[KSYM_SYMBOL_LEN];
 
 	/* Simple cyclic dependency checker. */
 	for (p = start; p < finish; p++) {
 		q = find_dependents_of(start, finish, p);
 		x = find_dependents_of(start, finish, q);
 		if (p == x) {
-			sprint_symbol(sym_p, (unsigned long)p->detect);
-			sprint_symbol(sym_q, (unsigned long)q->detect);
-
-			printk(KERN_ERR "CYCLIC DEPENDENCY FOUND! %s depends" \
-					" on %s and vice-versa. BREAKING IT.\n",
-					sym_p, sym_q);
+			printk(KERN_ERR "CYCLIC DEPENDENCY FOUND! %pS depends on %pS and vice-versa. BREAKING IT.\n",
+			       p->detect, q->detect);
 			/* Heavy handed way..*/
 			x->depend = 0;
 		}

@@ -72,12 +66,8 @@ void __init check_iommu_entries(struct iommu_table_entry *start,
 	for (p = start; p < finish; p++) {
 		q = find_dependents_of(p, finish, p);
 		if (q && q > p) {
-			sprint_symbol(sym_p, (unsigned long)p->detect);
-			sprint_symbol(sym_q, (unsigned long)q->detect);
-
-			printk(KERN_ERR "EXECUTION ORDER INVALID! %s "\
-					"should be called before %s!\n",
-					sym_p, sym_q);
+			printk(KERN_ERR "EXECUTION ORDER INVALID! %pS should be called before %pS!\n",
+			       p->detect, q->detect);
 		}
 	}
 }

index d552d2c..6af6b62 100644
@@ -39,6 +39,7 @@
 #include <linux/syscore_ops.h>
 #include <linux/tboot.h>
 #include <linux/dmi.h>
+#include <linux/pci-ats.h>
 #include <asm/cacheflush.h>
 #include <asm/iommu.h>
 #include "pci.h"

index 553d8ee..42fae47 100644
@@ -13,6 +13,7 @@
 #include <linux/mutex.h>
 #include <linux/string.h>
 #include <linux/delay.h>
+#include <linux/pci-ats.h>
 #include "pci.h"
 
 #define VIRTFN_ID_LEN	16

index a6ec200..4020025 100644
@@ -250,15 +250,6 @@ struct pci_sriov {
 	u8 __iomem *mstate;	/* VF Migration State Array */
 };
 
-/* Address Translation Service */
-struct pci_ats {
-	int pos;	/* capability position */
-	int stu;	/* Smallest Translation Unit */
-	int qdep;	/* Invalidate Queue Depth */
-	int ref_cnt;	/* Physical Function reference count */
-	unsigned int is_enabled:1;	/* Enable bit is set */
-};
-
 #ifdef CONFIG_PCI_IOV
 extern int pci_iov_init(struct pci_dev *dev);
 extern void pci_iov_release(struct pci_dev *dev);

@@ -269,19 +260,6 @@ extern resource_size_t pci_sriov_resource_alignment(struct pci_dev *dev,
 extern void pci_restore_iov_state(struct pci_dev *dev);
 extern int pci_iov_bus_range(struct pci_bus *bus);
 
-extern int pci_enable_ats(struct pci_dev *dev, int ps);
-extern void pci_disable_ats(struct pci_dev *dev);
-extern int pci_ats_queue_depth(struct pci_dev *dev);
-/**
- * pci_ats_enabled - query the ATS status
- * @dev: the PCI device
- *
- * Returns 1 if ATS capability is enabled, or 0 if not.
- */
-static inline int pci_ats_enabled(struct pci_dev *dev)
-{
-	return dev->ats && dev->ats->is_enabled;
-}
 #else
 static inline int pci_iov_init(struct pci_dev *dev)
 {

@@ -304,21 +282,6 @@ static inline int pci_iov_bus_range(struct pci_bus *bus)
 	return 0;
 }
 
-static inline int pci_enable_ats(struct pci_dev *dev, int ps)
-{
-	return -ENODEV;
-}
-static inline void pci_disable_ats(struct pci_dev *dev)
-{
-}
-static inline int pci_ats_queue_depth(struct pci_dev *dev)
-{
-	return -ENODEV;
-}
-static inline int pci_ats_enabled(struct pci_dev *dev)
-{
-	return 0;
-}
 #endif /* CONFIG_PCI_IOV */
 
 static inline resource_size_t pci_resource_alignment(struct pci_dev *dev,

52 lines not on this page · raw message

index 4bfb047..db07bfd 100644
@@ -649,7 +649,7 @@ out_err:
 	return -ENOMEM;
 }
 
-static int device_dma_allocations(struct device *dev)
+static int device_dma_allocations(struct device *dev, struct dma_debug_entry **out_entry)
 {
 	struct dma_debug_entry *entry;
 	unsigned long flags;

@@ -660,8 +660,10 @@ static int device_dma_allocations(struct device *dev)
 	for (i = 0; i < HASH_SIZE; ++i) {
 		spin_lock(&dma_entry_hash[i].lock);
 		list_for_each_entry(entry, &dma_entry_hash[i].list, list) {
-			if (entry->dev == dev)
+			if (entry->dev == dev) {
 				count += 1;
+				*out_entry = entry;
+			}
 		}
 		spin_unlock(&dma_entry_hash[i].lock);
 	}

@@ -674,6 +676,7 @@ static int device_dma_allocations(struct device *dev)
 static int dma_debug_device_change(struct notifier_block *nb, unsigned long action, void *data)
 {
 	struct device *dev = data;
+	struct dma_debug_entry *uninitialized_var(entry);
 	int count;
 
 	if (global_disable)

@@ -681,12 +684,17 @@ static int dma_debug_device_change(struct notifier_block *nb, unsigned long acti
 
 	switch (action) {
 	case BUS_NOTIFY_UNBOUND_DRIVER:
-		count = device_dma_allocations(dev);
+		count = device_dma_allocations(dev, &entry);
 		if (count == 0)
 			break;
-		err_printk(dev, NULL, "DMA-API: device driver has pending "
+		err_printk(dev, entry, "DMA-API: device driver has pending "
 				"DMA allocations while released from device "
-				"[count=%d]\n", count);
+				"[count=%d]\n"
+				"One of leaked entries details: "
+				"[device address=0x%016llx] [size=%llu bytes] "
+				"[mapped with %s] [mapped as %s]\n",
+			count, entry->dev_addr, entry->size,
+			dir2name[entry->direction], type2name[entry->type]);
 		break;
 	default:
 		break;