Merge branch 'x86-iommu-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip

* 'x86-iommu-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:
  x86, iommu: Update header comments with appropriate naming
  ia64, iommu: Add a dummy iommu_table.h file in IA64.
  x86, iommu: Fix IOMMU_INIT alignment rules
  x86, doc: Adding comments about .iommu_table and its neighbors.
  x86, iommu: Utilize the IOMMU_INIT macros functionality.
  x86, VT-d: Make Intel VT-d IOMMU use IOMMU_INIT_* macros.
  x86, GART/AMD-VI: Make AMD GART and IOMMU use IOMMU_INIT_* macros.
  x86, calgary: Make Calgary IOMMU use IOMMU_INIT_* macros.
  x86, xen-swiotlb: Make Xen-SWIOTLB use IOMMU_INIT_* macros.
  x86, swiotlb: Make SWIOTLB use IOMMU_INIT_* macros.
  x86, swiotlb: Simplify SWIOTLB pci_swiotlb_detect routine.
  x86, iommu: Add proper dependency sort routine (and sanity check).
  x86, iommu: Make all IOMMU's detection routines return a value.
  x86, iommu: Add IOMMU_INIT macros, .iommu_table section, and iommu_table_entry structure

9 files changed, 207 insertions, 45 deletions

diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index 80a93dc9907..2c833d8c414 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -45,6 +45,7 @@ obj-y			+= bootflag.o e820.o
 obj-y			+= pci-dma.o quirks.o i8237.o topology.o kdebugfs.o
 obj-y			+= alternative.o i8253.o pci-nommu.o hw_breakpoint.o
 obj-y			+= tsc.o io_delay.o rtc.o
+obj-y			+= pci-iommu_table.o
 
 obj-$(CONFIG_X86_TRAMPOLINE)	+= trampoline.o
 obj-y				+= process.o
diff --git a/arch/x86/kernel/amd_iommu_init.c b/arch/x86/kernel/amd_iommu_init.c
index 3cb482e123d..6e11c813415 100644
--- a/arch/x86/kernel/amd_iommu_init.c
+++ b/arch/x86/kernel/amd_iommu_init.c
@@ -31,7 +31,7 @@
 #include <asm/iommu.h>
 #include <asm/gart.h>
 #include <asm/x86_init.h>
-
+#include <asm/iommu_table.h>
 /*
  * definitions for the ACPI scanning code
  */
@@ -1499,13 +1499,13 @@ static int __init early_amd_iommu_detect(struct acpi_table_header *table)
 	return 0;
 }
 
-void __init amd_iommu_detect(void)
+int __init amd_iommu_detect(void)
 {
 	if (no_iommu || (iommu_detected && !gart_iommu_aperture))
-		return;
+		return -ENODEV;
 
 	if (amd_iommu_disabled)
-		return;
+		return -ENODEV;
 
 	if (acpi_table_parse("IVRS", early_amd_iommu_detect) == 0) {
 		iommu_detected = 1;
@@ -1514,7 +1514,9 @@ void __init amd_iommu_detect(void)
 
 		/* Make sure ACS will be enabled */
 		pci_request_acs();
+		return 1;
 	}
+	return -ENODEV;
 }
 
 /****************************************************************************
@@ -1545,3 +1547,8 @@ static int __init parse_amd_iommu_options(char *str)
 
 __setup("amd_iommu_dump", parse_amd_iommu_dump);
 __setup("amd_iommu=", parse_amd_iommu_options);
+
+IOMMU_INIT_FINISH(amd_iommu_detect,
+		  gart_iommu_hole_init,
+		  0,
+		  0);
diff --git a/arch/x86/kernel/aperture_64.c b/arch/x86/kernel/aperture_64.c
index 377f5db3b8b..b3a16e8f070 100644
--- a/arch/x86/kernel/aperture_64.c
+++ b/arch/x86/kernel/aperture_64.c
@@ -371,7 +371,7 @@ void __init early_gart_iommu_check(void)
 
 static int __initdata printed_gart_size_msg;
 
-void __init gart_iommu_hole_init(void)
+int __init gart_iommu_hole_init(void)
 {
 	u32 agp_aper_base = 0, agp_aper_order = 0;
 	u32 aper_size, aper_alloc = 0, aper_order = 0, last_aper_order = 0;
@@ -381,7 +381,7 @@ void __init gart_iommu_hole_init(void)
 
 	if (gart_iommu_aperture_disabled || !fix_aperture ||
 	    !early_pci_allowed())
-		return;
+		return -ENODEV;
 
 	printk(KERN_INFO  "Checking aperture...\n");
 
@@ -463,8 +463,9 @@ out:
 			unsigned long n = (32 * 1024 * 1024) << last_aper_order;
 
 			insert_aperture_resource((u32)last_aper_base, n);
+			return 1;
 		}
-		return;
+		return 0;
 	}
 
 	if (!fallback_aper_force) {
@@ -500,7 +501,7 @@ out:
 			panic("Not enough memory for aperture");
 		}
 	} else {
-		return;
+		return 0;
 	}
 
 	/* Fix up the north bridges */
@@ -526,4 +527,6 @@ out:
 	}
 
 	set_up_gart_resume(aper_order, aper_alloc);
+
+	return 1;
 }
diff --git a/arch/x86/kernel/pci-calgary_64.c b/arch/x86/kernel/pci-calgary_64.c
index 078d4ec1a9d..f56a117cef6 100644
--- a/arch/x86/kernel/pci-calgary_64.c
+++ b/arch/x86/kernel/pci-calgary_64.c
@@ -47,6 +47,7 @@
 #include <asm/rio.h>
 #include <asm/bios_ebda.h>
 #include <asm/x86_init.h>
+#include <asm/iommu_table.h>
 
 #ifdef CONFIG_CALGARY_IOMMU_ENABLED_BY_DEFAULT
 int use_calgary __read_mostly = 1;
@@ -1364,7 +1365,7 @@ static int __init calgary_iommu_init(void)
 	return 0;
 }
 
-void __init detect_calgary(void)
+int __init detect_calgary(void)
 {
 	int bus;
 	void *tbl;
@@ -1378,13 +1379,13 @@ void __init detect_calgary(void)
 	 * another HW IOMMU already, bail out.
 	 */
 	if (no_iommu || iommu_detected)
-		return;
+		return -ENODEV;
 
 	if (!use_calgary)
-		return;
+		return -ENODEV;
 
 	if (!early_pci_allowed())
-		return;
+		return -ENODEV;
 
 	printk(KERN_DEBUG "Calgary: detecting Calgary via BIOS EBDA area\n");
 
@@ -1410,13 +1411,13 @@ void __init detect_calgary(void)
 	if (!rio_table_hdr) {
 		printk(KERN_DEBUG "Calgary: Unable to locate Rio Grande table "
 		       "in EBDA - bailing!\n");
-		return;
+		return -ENODEV;
 	}
 
 	ret = build_detail_arrays();
 	if (ret) {
 		printk(KERN_DEBUG "Calgary: build_detail_arrays ret %d\n", ret);
-		return;
+		return -ENOMEM;
 	}
 
 	specified_table_size = determine_tce_table_size((is_kdump_kernel() ?
@@ -1464,7 +1465,7 @@ void __init detect_calgary(void)
 
 		x86_init.iommu.iommu_init = calgary_iommu_init;
 	}
-	return;
+	return calgary_found;
 
 cleanup:
 	for (--bus; bus >= 0; --bus) {
@@ -1473,6 +1474,7 @@ cleanup:
 		if (info->tce_space)
 			free_tce_table(info->tce_space);
 	}
+	return -ENOMEM;
 }
 
 static int __init calgary_parse_options(char *p)
@@ -1594,3 +1596,5 @@ static int __init calgary_fixup_tce_spaces(void)
  * and before device_initcall.
  */
 rootfs_initcall(calgary_fixup_tce_spaces);
+
+IOMMU_INIT_POST(detect_calgary);
diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c
index 9f07cfcbd3a..9ea999a4dcc 100644
--- a/arch/x86/kernel/pci-dma.c
+++ b/arch/x86/kernel/pci-dma.c
@@ -11,9 +11,8 @@
 #include <asm/iommu.h>
 #include <asm/gart.h>
 #include <asm/calgary.h>
-#include <asm/amd_iommu.h>
 #include <asm/x86_init.h>
-#include <asm/xen/swiotlb-xen.h>
+#include <asm/iommu_table.h>
 
 static int forbid_dac __read_mostly;
 
@@ -45,6 +44,8 @@ int iommu_detected __read_mostly = 0;
  */
 int iommu_pass_through __read_mostly;
 
+extern struct iommu_table_entry __iommu_table[], __iommu_table_end[];
+
 /* Dummy device used for NULL arguments (normally ISA). */
 struct device x86_dma_fallback_dev = {
 	.init_name = "fallback device",
@@ -130,26 +131,24 @@ static void __init dma32_free_bootmem(void)
 
 void __init pci_iommu_alloc(void)
 {
+	struct iommu_table_entry *p;
+
 	/* free the range so iommu could get some range less than 4G */
 	dma32_free_bootmem();
 
-	if (pci_xen_swiotlb_detect() || pci_swiotlb_detect())
-		goto out;
-
-	gart_iommu_hole_init();
-
-	detect_calgary();
-
-	detect_intel_iommu();
+	sort_iommu_table(__iommu_table, __iommu_table_end);
+	check_iommu_entries(__iommu_table, __iommu_table_end);
 
-	/* needs to be called after gart_iommu_hole_init */
-	amd_iommu_detect();
-out:
-	pci_xen_swiotlb_init();
-
-	pci_swiotlb_init();
+	for (p = __iommu_table; p < __iommu_table_end; p++) {
+		if (p && p->detect && p->detect() > 0) {
+			p->flags |= IOMMU_DETECTED;
+			if (p->early_init)
+				p->early_init();
+			if (p->flags & IOMMU_FINISH_IF_DETECTED)
+				break;
+		}
+	}
 }
-
 void *dma_generic_alloc_coherent(struct device *dev, size_t size,
 				 dma_addr_t *dma_addr, gfp_t flag)
 {
@@ -292,6 +291,7 @@ EXPORT_SYMBOL(dma_supported);
 
 static int __init pci_iommu_init(void)
 {
+	struct iommu_table_entry *p;
 	dma_debug_init(PREALLOC_DMA_DEBUG_ENTRIES);
 
 #ifdef CONFIG_PCI
@@ -299,12 +299,10 @@ static int __init pci_iommu_init(void)
 #endif
 	x86_init.iommu.iommu_init();
 
-	if (swiotlb || xen_swiotlb) {
-		printk(KERN_INFO "PCI-DMA: "
-		       "Using software bounce buffering for IO (SWIOTLB)\n");
-		swiotlb_print_info();
-	} else
-		swiotlb_free();
+	for (p = __iommu_table; p < __iommu_table_end; p++) {
+		if (p && (p->flags & IOMMU_DETECTED) && p->late_init)
+			p->late_init();
+	}
 
 	return 0;
 }
diff --git a/arch/x86/kernel/pci-gart_64.c b/arch/x86/kernel/pci-gart_64.c
index c562207b1b3..ba0f0ca9f28 100644
--- a/arch/x86/kernel/pci-gart_64.c
+++ b/arch/x86/kernel/pci-gart_64.c
@@ -41,6 +41,7 @@
 #include <asm/dma.h>
 #include <asm/amd_nb.h>
 #include <asm/x86_init.h>
+#include <asm/iommu_table.h>
 
 static unsigned long iommu_bus_base;	/* GART remapping area (physical) */
 static unsigned long iommu_size;	/* size of remapping area bytes */
@@ -905,3 +906,4 @@ void __init gart_parse_options(char *p)
 		}
 	}
 }
+IOMMU_INIT_POST(gart_iommu_hole_init);
diff --git a/arch/x86/kernel/pci-iommu_table.c b/arch/x86/kernel/pci-iommu_table.c
new file mode 100644
index 00000000000..55d745ec118
--- /dev/null
+++ b/arch/x86/kernel/pci-iommu_table.c
@@ -0,0 +1,89 @@
+#include <linux/dma-mapping.h>
+#include <asm/iommu_table.h>
+#include <linux/string.h>
+#include <linux/kallsyms.h>
+
+
+#define DEBUG 1
+
+static struct iommu_table_entry * __init
+find_dependents_of(struct iommu_table_entry *start,
+		   struct iommu_table_entry *finish,
+		   struct iommu_table_entry *q)
+{
+	struct iommu_table_entry *p;
+
+	if (!q)
+		return NULL;
+
+	for (p = start; p < finish; p++)
+		if (p->detect == q->depend)
+			return p;
+
+	return NULL;
+}
+
+
+void __init sort_iommu_table(struct iommu_table_entry *start,
+			     struct iommu_table_entry *finish) {
+
+	struct iommu_table_entry *p, *q, tmp;
+
+	for (p = start; p < finish; p++) {
+again:
+		q = find_dependents_of(start, finish, p);
+		/* We are bit sneaky here. We use the memory address to figure
+		 * out if the node we depend on is past our point, if so, swap.
+		 */
+		if (q > p) {
+			tmp = *p;
+			memmove(p, q, sizeof(*p));
+			*q = tmp;
+			goto again;
+		}
+	}
+
+}
+
+#ifdef DEBUG
+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);
+			/* Heavy handed way..*/
+			x->depend = 0;
+		}
+	}
+
+	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);
+		}
+	}
+}
+#else
+inline void check_iommu_entries(struct iommu_table_entry *start,
+				       struct iommu_table_entry *finish)
+{
+}
+#endif
diff --git a/arch/x86/kernel/pci-swiotlb.c b/arch/x86/kernel/pci-swiotlb.c
index a5bc528d432..8f972cbddef 100644
--- a/arch/x86/kernel/pci-swiotlb.c
+++ b/arch/x86/kernel/pci-swiotlb.c
@@ -10,7 +10,8 @@
 #include <asm/iommu.h>
 #include <asm/swiotlb.h>
 #include <asm/dma.h>
-
+#include <asm/xen/swiotlb-xen.h>
+#include <asm/iommu_table.h>
 int swiotlb __read_mostly;
 
 static void *x86_swiotlb_alloc_coherent(struct device *hwdev, size_t size,
@@ -41,25 +42,42 @@ static struct dma_map_ops swiotlb_dma_ops = {
 };
 
 /*
- * pci_swiotlb_detect - set swiotlb to 1 if necessary
+ * pci_swiotlb_detect_override - set swiotlb to 1 if necessary
  *
  * This returns non-zero if we are forced to use swiotlb (by the boot
  * option).
  */
-int __init pci_swiotlb_detect(void)
+int __init pci_swiotlb_detect_override(void)
 {
 	int use_swiotlb = swiotlb | swiotlb_force;
 
+	if (swiotlb_force)
+		swiotlb = 1;
+
+	return use_swiotlb;
+}
+IOMMU_INIT_FINISH(pci_swiotlb_detect_override,
+		  pci_xen_swiotlb_detect,
+		  pci_swiotlb_init,
+		  pci_swiotlb_late_init);
+
+/*
+ * if 4GB or more detected (and iommu=off not set) return 1
+ * and set swiotlb to 1.
+ */
+int __init pci_swiotlb_detect_4gb(void)
+{
 	/* don't initialize swiotlb if iommu=off (no_iommu=1) */
 #ifdef CONFIG_X86_64
 	if (!no_iommu && max_pfn > MAX_DMA32_PFN)
 		swiotlb = 1;
 #endif
-	if (swiotlb_force)
-		swiotlb = 1;
-
-	return use_swiotlb;
+	return swiotlb;
 }
+IOMMU_INIT(pci_swiotlb_detect_4gb,
+	   pci_swiotlb_detect_override,
+	   pci_swiotlb_init,
+	   pci_swiotlb_late_init);
 
 void __init pci_swiotlb_init(void)
 {
@@ -68,3 +86,15 @@ void __init pci_swiotlb_init(void)
 		dma_ops = &swiotlb_dma_ops;
 	}
 }
+
+void __init pci_swiotlb_late_init(void)
+{
+	/* An IOMMU turned us off. */
+	if (!swiotlb)
+		swiotlb_free();
+	else {
+		printk(KERN_INFO "PCI-DMA: "
+		       "Using software bounce buffering for IO (SWIOTLB)\n");
+		swiotlb_print_info();
+	}
+}
diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S
index d0bb52296fa..38e2b67807e 100644
--- a/arch/x86/kernel/vmlinux.lds.S
+++ b/arch/x86/kernel/vmlinux.lds.S
@@ -242,6 +242,12 @@ SECTIONS
 		__x86_cpu_dev_end = .;
 	}
 
+	/*
+	 * start address and size of operations which during runtime
+	 * can be patched with virtualization friendly instructions or
+	 * baremetal native ones. Think page table operations.
+	 * Details in paravirt_types.h
+	 */
 	. = ALIGN(8);
 	.parainstructions : AT(ADDR(.parainstructions) - LOAD_OFFSET) {
 		__parainstructions = .;
@@ -249,6 +255,11 @@ SECTIONS
 		__parainstructions_end = .;
 	}
 
+	/*
+	 * struct alt_inst entries. From the header (alternative.h):
+	 * "Alternative instructions for different CPU types or capabilities"
+	 * Think locking instructions on spinlocks.
+	 */
 	. = ALIGN(8);
 	.altinstructions : AT(ADDR(.altinstructions) - LOAD_OFFSET) {
 		__alt_instructions = .;
@@ -256,11 +267,28 @@ SECTIONS
 		__alt_instructions_end = .;
 	}
 
+	/*
+	 * And here are the replacement instructions. The linker sticks
+	 * them as binary blobs. The .altinstructions has enough data to
+	 * get the address and the length of them to patch the kernel safely.
+	 */
 	.altinstr_replacement : AT(ADDR(.altinstr_replacement) - LOAD_OFFSET) {
 		*(.altinstr_replacement)
 	}
 
 	/*
+	 * struct iommu_table_entry entries are injected in this section.
+	 * It is an array of IOMMUs which during run time gets sorted depending
+	 * on its dependency order. After rootfs_initcall is complete
+	 * this section can be safely removed.
+	 */
+	.iommu_table : AT(ADDR(.iommu_table) - LOAD_OFFSET) {
+		__iommu_table = .;
+		*(.iommu_table)
+		__iommu_table_end = .;
+	}
+	. = ALIGN(8);
+	/*
 	 * .exit.text is discard at runtime, not link time, to deal with
 	 *  references from .altinstructions and .eh_frame
 	 */