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

…kernel/git/tip/linux-2.6-tip

* 'iommu-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: (61 commits)
  amd-iommu: remove unnecessary "AMD IOMMU: " prefix
  amd-iommu: detach device explicitly before attaching it to a new domain
  amd-iommu: remove BUS_NOTIFY_BOUND_DRIVER handling
  dma-debug: simplify logic in driver_filter()
  dma-debug: disable/enable irqs only once in device_dma_allocations
  dma-debug: use pr_* instead of printk(KERN_* ...)
  dma-debug: code style fixes
  dma-debug: comment style fixes
  dma-debug: change hash_bucket_find from first-fit to best-fit
  x86: enable GART-IOMMU only after setting up protection methods
  amd_iommu: fix lock imbalance
  dma-debug: add documentation for the driver filter
  dma-debug: add dma_debug_driver kernel command line
  dma-debug: add debugfs file for driver filter
  dma-debug: add variables and checks for driver filter
  dma-debug: fix debug_dma_sync_sg_for_cpu and debug_dma_sync_sg_for_device
  dma-debug: use sg_dma_len accessor
  dma-debug: use sg_dma_address accessor instead of using dma_address directly
  amd-iommu: don't free dma adresses below 512MB with CONFIG_IOMMU_STRESS
  amd-iommu: don't preallocate page tables with CONFIG_IOMMU_STRESS
  ...

Documentation/DMA-API.txt

@@ -704,12 +704,24 @@ this directory the following files can currently be found:
 				The current number of free dma_debug_entries
 				in the allocator.
 
+	dma-api/driver-filter
+				You can write a name of a driver into this file
+				to limit the debug output to requests from that
+				particular driver. Write an empty string to
+				that file to disable the filter and see
+				all errors again.
+
 If you have this code compiled into your kernel it will be enabled by default.
 If you want to boot without the bookkeeping anyway you can provide
 'dma_debug=off' as a boot parameter. This will disable DMA-API debugging.
 Notice that you can not enable it again at runtime. You have to reboot to do
 so.
 
+If you want to see debug messages only for a special device driver you can
+specify the dma_debug_driver=<drivername> parameter. This will enable the
+driver filter at boot time. The debug code will only print errors for that
+driver afterwards. This filter can be disabled or changed later using debugfs.
+
 When the code disables itself at runtime this is most likely because it ran
 out of dma_debug_entries. These entries are preallocated at boot. The number
 of preallocated entries is defined per architecture. If it is too low for you

Documentation/kernel-parameters.txt

@@ -329,11 +329,6 @@ and is between 256 and 4096 characters. It is defined in the file
 				    flushed before they will be reused, which
 				    is a lot of faster
 
-	amd_iommu_size= [HW,X86-64]
-			Define the size of the aperture for the AMD IOMMU
-			driver. Possible values are:
-			'32M', '64M' (default), '128M', '256M', '512M', '1G'
-
 	amijoy.map=	[HW,JOY] Amiga joystick support
 			Map of devices attached to JOY0DAT and JOY1DAT
 			Format: <a>,<b>
@@ -646,6 +641,13 @@ and is between 256 and 4096 characters. It is defined in the file
 			DMA-API debugging code disables itself because the
 			architectural default is too low.
 
+	dma_debug_driver=<driver_name>
+			With this option the DMA-API debugging driver
+			filter feature can be enabled at boot time. Just
+			pass the driver to filter for as the parameter.
+			The filter can be disabled or changed to another
+			driver later using sysfs.
+
 	dscc4.setup=	[NET]
 
 	dtc3181e=	[HW,SCSI]

arch/x86/Kconfig.debug

@@ -159,10 +159,17 @@ config IOMMU_DEBUG
 	  options. See Documentation/x86_64/boot-options.txt for more
 	  details.
 
+config IOMMU_STRESS
+	bool "Enable IOMMU stress-test mode"
+	---help---
+	  This option disables various optimizations in IOMMU related
+	  code to do real stress testing of the IOMMU code. This option
+	  will cause a performance drop and should only be enabled for
+	  testing.
+
 config IOMMU_LEAK
 	bool "IOMMU leak tracing"
-	depends on DEBUG_KERNEL
-	depends on IOMMU_DEBUG
+	depends on IOMMU_DEBUG && DMA_API_DEBUG
 	---help---
 	  Add a simple leak tracer to the IOMMU code. This is useful when you
 	  are debugging a buggy device driver that leaks IOMMU mappings.

arch/x86/include/asm/amd_iommu.h

@@ -27,6 +27,8 @@ extern int amd_iommu_init(void);
 extern int amd_iommu_init_dma_ops(void);
 extern void amd_iommu_detect(void);
 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);
 #else
 static inline int amd_iommu_init(void) { return -ENODEV; }
 static inline void amd_iommu_detect(void) { }

arch/x86/include/asm/amd_iommu_types.h

@@ -194,6 +194,27 @@
 #define PD_DMA_OPS_MASK		(1UL << 0) /* domain used for dma_ops */
 #define PD_DEFAULT_MASK		(1UL << 1) /* domain is a default dma_ops
 					      domain for an IOMMU */
+extern bool amd_iommu_dump;
+#define DUMP_printk(format, arg...)					\
+	do {								\
+		if (amd_iommu_dump)						\
+			printk(KERN_INFO "AMD IOMMU: " format, ## arg);	\
+	} while(0);
+
+/*
+ * Make iterating over all IOMMUs easier
+ */
+#define for_each_iommu(iommu) \
+	list_for_each_entry((iommu), &amd_iommu_list, list)
+#define for_each_iommu_safe(iommu, next) \
+	list_for_each_entry_safe((iommu), (next), &amd_iommu_list, list)
+
+#define APERTURE_RANGE_SHIFT	27	/* 128 MB */
+#define APERTURE_RANGE_SIZE	(1ULL << APERTURE_RANGE_SHIFT)
+#define APERTURE_RANGE_PAGES	(APERTURE_RANGE_SIZE >> PAGE_SHIFT)
+#define APERTURE_MAX_RANGES	32	/* allows 4GB of DMA address space */
+#define APERTURE_RANGE_INDEX(a)	((a) >> APERTURE_RANGE_SHIFT)
+#define APERTURE_PAGE_INDEX(a)	(((a) >> 21) & 0x3fULL)
 
 /*
  * This structure contains generic data for  IOMMU protection domains
@@ -209,6 +230,26 @@ struct protection_domain {
 	void *priv;		/* private data */
 };
 
+/*
+ * For dynamic growth the aperture size is split into ranges of 128MB of
+ * DMA address space each. This struct represents one such range.
+ */
+struct aperture_range {
+
+	/* address allocation bitmap */
+	unsigned long *bitmap;
+
+	/*
+	 * Array of PTE pages for the aperture. In this array we save all the
+	 * leaf pages of the domain page table used for the aperture. This way
+	 * we don't need to walk the page table to find a specific PTE. We can
+	 * just calculate its address in constant time.
+	 */
+	u64 *pte_pages[64];
+
+	unsigned long offset;
+};
+
 /*
  * Data container for a dma_ops specific protection domain
  */
@@ -222,18 +263,10 @@ struct dma_ops_domain {
 	unsigned long aperture_size;
 
 	/* address we start to search for free addresses */
-	unsigned long next_bit;
-
-	/* address allocation bitmap */
-	unsigned long *bitmap;
+	unsigned long next_address;
 
-	/*
-	 * Array of PTE pages for the aperture. In this array we save all the
-	 * leaf pages of the domain page table used for the aperture. This way
-	 * we don't need to walk the page table to find a specific PTE. We can
-	 * just calculate its address in constant time.
-	 */
-	u64 **pte_pages;
+	/* address space relevant data */
+	struct aperture_range *aperture[APERTURE_MAX_RANGES];
 
 	/* This will be set to true when TLB needs to be flushed */
 	bool need_flush;