Merge branch 'core-iommu-for-linus' of...

Merge branch 'core-iommu-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip

* 'core-iommu-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:
  x86, gart: Rename pci-gart_64.c to amd_gart_64.c
  x86/amd-iommu: Use threaded interupt handler
  arch/x86/kernel/pci-iommu_table.c: Convert sprintf_symbol to %pS
  x86/amd-iommu: Add support for invalidate_all command
  x86/amd-iommu: Add extended feature detection
  x86/amd-iommu: Add ATS enable/disable code
  x86/amd-iommu: Add flag to indicate IOTLB support
  x86/amd-iommu: Flush device IOTLB if ATS is enabled
  x86/amd-iommu: Select PCI_IOV with AMD IOMMU driver
  PCI: Move ATS declarations in seperate header file
  dma-debug: print information about leaked entry
  x86/amd-iommu: Flush all internal TLBs when IOMMUs are enabled
  x86/amd-iommu: Rename iommu_flush_device
  x86/amd-iommu: Improve handling of full command buffer
  x86/amd-iommu: Rename iommu_flush* to domain_flush*
  x86/amd-iommu: Remove command buffer resetting logic
  x86/amd-iommu: Cleanup completion-wait handling
  x86/amd-iommu: Cleanup inv_pages command handling
  x86/amd-iommu: Move inv-dte command building to own function
  x86/amd-iommu: Move compl-wait command building to own function

Documentation/x86/x86_64/boot-options.txt

@@ -206,7 +206,7 @@ IOMMU (input/output memory management unit)
       (e.g. because you have < 3 GB memory).
       Kernel boot message: "PCI-DMA: Disabling IOMMU"
 
-   2. <arch/x86_64/kernel/pci-gart.c>: AMD GART based hardware IOMMU.
+   2. <arch/x86/kernel/amd_gart_64.c>: AMD GART based hardware IOMMU.
       Kernel boot message: "PCI-DMA: using GART IOMMU"
 
    3. <arch/x86_64/kernel/pci-swiotlb.c> : Software IOMMU implementation. Used

arch/x86/Kconfig

@@ -689,6 +689,7 @@ config AMD_IOMMU
 	bool "AMD IOMMU support"
 	select SWIOTLB
 	select PCI_MSI
+	select PCI_IOV
 	depends on X86_64 && PCI && ACPI
 	---help---
 	  With this option you can enable support for AMD IOMMU hardware in

arch/x86/include/asm/amd_iommu_proto.h

@@ -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  */

arch/x86/include/asm/amd_iommu_types.h

@@ -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;
 

arch/x86/kernel/Makefile

@@ -117,7 +117,7 @@ obj-$(CONFIG_OF)			+= devicetree.o
 ifeq ($(CONFIG_X86_64),y)
 	obj-$(CONFIG_AUDIT)		+= audit_64.o
 
-	obj-$(CONFIG_GART_IOMMU)	+= pci-gart_64.o aperture_64.o
+	obj-$(CONFIG_GART_IOMMU)	+= amd_gart_64.o aperture_64.o
 	obj-$(CONFIG_CALGARY_IOMMU)	+= pci-calgary_64.o tce_64.o
 	obj-$(CONFIG_AMD_IOMMU)		+= amd_iommu_init.o amd_iommu.o
 

arch/x86/kernel/amd_iommu_init.c

@@ -137,6 +137,7 @@ int amd_iommus_present;
 
 /* IOMMUs have a non-present cache? */
 bool amd_iommu_np_cache __read_mostly;
+bool amd_iommu_iotlb_sup __read_mostly = true;
 
 /*
  * The ACPI table parsing functions set this variable on an error
@@ -180,6 +181,12 @@ static u32 dev_table_size;	/* size of the device table */
 static u32 alias_table_size;	/* size of the alias table */
 static u32 rlookup_table_size;	/* size if the rlookup table */
 
+/*
+ * This function flushes all internal caches of
+ * the IOMMU used by this driver.
+ */
+extern void iommu_flush_all_caches(struct amd_iommu *iommu);
+
 static inline void update_last_devid(u16 devid)
 {
 	if (devid > amd_iommu_last_bdf)
@@ -293,9 +300,23 @@ static void iommu_feature_disable(struct amd_iommu *iommu, u8 bit)
 /* Function to enable the hardware */
 static void iommu_enable(struct amd_iommu *iommu)
 {
-	printk(KERN_INFO "AMD-Vi: Enabling IOMMU at %s cap 0x%hx\n",
+	static const char * const feat_str[] = {
+		"PreF", "PPR", "X2APIC", "NX", "GT", "[5]",
+		"IA", "GA", "HE", "PC", NULL
+	};
+	int i;
+
+	printk(KERN_INFO "AMD-Vi: Enabling IOMMU at %s cap 0x%hx",
 	       dev_name(&iommu->dev->dev), iommu->cap_ptr);
 
+	if (iommu->cap & (1 << IOMMU_CAP_EFR)) {
+		printk(KERN_CONT " extended features: ");
+		for (i = 0; feat_str[i]; ++i)
+			if (iommu_feature(iommu, (1ULL << i)))
+				printk(KERN_CONT " %s", feat_str[i]);
+	}
+	printk(KERN_CONT "\n");
+
 	iommu_feature_enable(iommu, CONTROL_IOMMU_EN);
 }
 
@@ -651,7 +672,7 @@ static void __init set_device_exclusion_range(u16 devid, struct ivmd_header *m)
 static void __init init_iommu_from_pci(struct amd_iommu *iommu)
 {
 	int cap_ptr = iommu->cap_ptr;
-	u32 range, misc;
+	u32 range, misc, low, high;
 	int i, j;
 
 	pci_read_config_dword(iommu->dev, cap_ptr + MMIO_CAP_HDR_OFFSET,
@@ -667,6 +688,15 @@ static void __init init_iommu_from_pci(struct amd_iommu *iommu)
 					MMIO_GET_LD(range));
 	iommu->evt_msi_num = MMIO_MSI_NUM(misc);
 
+	if (!(iommu->cap & (1 << IOMMU_CAP_IOTLB)))
+		amd_iommu_iotlb_sup = false;
+
+	/* read extended feature bits */
+	low  = readl(iommu->mmio_base + MMIO_EXT_FEATURES);
+	high = readl(iommu->mmio_base + MMIO_EXT_FEATURES + 4);
+
+	iommu->features = ((u64)high << 32) | low;
+
 	if (!is_rd890_iommu(iommu->dev))
 		return;
 
@@ -1004,10 +1034,11 @@ static int iommu_setup_msi(struct amd_iommu *iommu)
 	if (pci_enable_msi(iommu->dev))
 		return 1;
 
-	r = request_irq(iommu->dev->irq, amd_iommu_int_handler,
-			IRQF_SAMPLE_RANDOM,
-			"AMD-Vi",
-			NULL);
+	r = request_threaded_irq(iommu->dev->irq,
+				 amd_iommu_int_handler,
+				 amd_iommu_int_thread,
+				 0, "AMD-Vi",
+				 iommu->dev);
 
 	if (r) {
 		pci_disable_msi(iommu->dev);
@@ -1244,6 +1275,7 @@ static void enable_iommus(void)
 		iommu_set_exclusion_range(iommu);
 		iommu_init_msi(iommu);
 		iommu_enable(iommu);
+		iommu_flush_all_caches(iommu);
 	}
 }
 
@@ -1274,8 +1306,8 @@ static void amd_iommu_resume(void)
 	 * we have to flush after the IOMMUs are enabled because a
 	 * disabled IOMMU will never execute the commands we send
 	 */
-	amd_iommu_flush_all_devices();
-	amd_iommu_flush_all_domains();
+	for_each_iommu(iommu)
+		iommu_flush_all_caches(iommu);
 }
 
 static int amd_iommu_suspend(void)

arch/x86/kernel/pci-iommu_table.c

@@ -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);
 		}
 	}
 }

drivers/pci/intel-iommu.c

@@ -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"

drivers/pci/iov.c

@@ -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

drivers/pci/pci.h

@@ -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,

include/linux/pci-ats.h

+#ifndef LINUX_PCI_ATS_H
+#define LINUX_PCI_ATS_H
+
+/* 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_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 /* CONFIG_PCI_IOV */
+
+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 */
+
+#endif /* LINUX_PCI_ATS_H*/

lib/dma-debug.c

@@ -649,7 +649,7 @@ static int dma_debug_fs_init(void)
 	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;