Merge branch 'linus' into perfcounters/core

Conflicts:
	arch/x86/kernel/irqinit.c
	arch/x86/kernel/irqinit_64.c
	arch/x86/kernel/traps.c
	arch/x86/mm/fault.c
	include/linux/sched.h
	kernel/exit.c

78 files changed, 3848 insertions, 3043 deletions

diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index 88d1bfc847d..4f78bd68212 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -28,7 +28,7 @@ CFLAGS_paravirt.o	:= $(nostackp)
 obj-y			:= process_$(BITS).o signal.o entry_$(BITS).o
 obj-y			+= traps.o irq.o irq_$(BITS).o dumpstack_$(BITS).o
 obj-y			+= time_$(BITS).o ioport.o ldt.o dumpstack.o
-obj-y			+= setup.o i8259.o irqinit_$(BITS).o
+obj-y			+= setup.o i8259.o irqinit.o
 obj-$(CONFIG_X86_VISWS)	+= visws_quirks.o
 obj-$(CONFIG_X86_32)	+= probe_roms_32.o
 obj-$(CONFIG_X86_32)	+= sys_i386_32.o i386_ksyms_32.o
@@ -44,6 +44,7 @@ obj-y				+= process.o
 obj-y				+= i387.o xsave.o
 obj-y				+= ptrace.o
 obj-$(CONFIG_X86_DS)		+= ds.o
+obj-$(CONFIG_X86_DS_SELFTEST)		+= ds_selftest.o
 obj-$(CONFIG_X86_32)		+= tls.o
 obj-$(CONFIG_IA32_EMULATION)	+= tls.o
 obj-y				+= step.o
diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c
index 723989d7f80..631086159c5 100644
--- a/arch/x86/kernel/acpi/boot.c
+++ b/arch/x86/kernel/acpi/boot.c
@@ -33,6 +33,7 @@
 #include <linux/irq.h>
 #include <linux/bootmem.h>
 #include <linux/ioport.h>
+#include <linux/pci.h>
 
 #include <asm/pgtable.h>
 #include <asm/io_apic.h>
@@ -522,7 +523,7 @@ int acpi_gsi_to_irq(u32 gsi, unsigned int *irq)
  * success: return IRQ number (>=0)
  * failure: return < 0
  */
-int acpi_register_gsi(u32 gsi, int triggering, int polarity)
+int acpi_register_gsi(struct device *dev, u32 gsi, int trigger, int polarity)
 {
 	unsigned int irq;
 	unsigned int plat_gsi = gsi;
@@ -532,14 +533,14 @@ int acpi_register_gsi(u32 gsi, int triggering, int polarity)
 	 * Make sure all (legacy) PCI IRQs are set as level-triggered.
 	 */
 	if (acpi_irq_model == ACPI_IRQ_MODEL_PIC) {
-		if (triggering == ACPI_LEVEL_SENSITIVE)
+		if (trigger == ACPI_LEVEL_SENSITIVE)
 			eisa_set_level_irq(gsi);
 	}
 #endif
 
 #ifdef CONFIG_X86_IO_APIC
 	if (acpi_irq_model == ACPI_IRQ_MODEL_IOAPIC) {
-		plat_gsi = mp_register_gsi(gsi, triggering, polarity);
+		plat_gsi = mp_register_gsi(dev, gsi, trigger, polarity);
 	}
 #endif
 	acpi_gsi_to_irq(plat_gsi, &irq);
@@ -903,10 +904,8 @@ extern int es7000_plat;
 #endif
 
 static struct {
-	int apic_id;
 	int gsi_base;
 	int gsi_end;
-	DECLARE_BITMAP(pin_programmed, MP_MAX_IOAPIC_PIN + 1);
 } mp_ioapic_routing[MAX_IO_APICS];
 
 int mp_find_ioapic(int gsi)
@@ -986,16 +985,12 @@ void __init mp_register_ioapic(int id, u32 address, u32 gsi_base)
 
 	set_fixmap_nocache(FIX_IO_APIC_BASE_0 + idx, address);
 	mp_ioapics[idx].apicid = uniq_ioapic_id(id);
-#ifdef CONFIG_X86_32
 	mp_ioapics[idx].apicver = io_apic_get_version(idx);
-#else
-	mp_ioapics[idx].apicver = 0;
-#endif
+
 	/*
 	 * Build basic GSI lookup table to facilitate gsi->io_apic lookups
 	 * and to prevent reprogramming of IOAPIC pins (PCI GSIs).
 	 */
-	mp_ioapic_routing[idx].apic_id = mp_ioapics[idx].apicid;
 	mp_ioapic_routing[idx].gsi_base = gsi_base;
 	mp_ioapic_routing[idx].gsi_end = gsi_base +
 	    io_apic_get_redir_entries(idx);
@@ -1158,26 +1153,52 @@ void __init mp_config_acpi_legacy_irqs(void)
 	}
 }
 
-int mp_register_gsi(u32 gsi, int triggering, int polarity)
+static int mp_config_acpi_gsi(struct device *dev, u32 gsi, int trigger,
+			int polarity)
 {
+#ifdef CONFIG_X86_MPPARSE
+	struct mpc_intsrc mp_irq;
+	struct pci_dev *pdev;
+	unsigned char number;
+	unsigned int devfn;
 	int ioapic;
-	int ioapic_pin;
-#ifdef CONFIG_X86_32
-#define MAX_GSI_NUM	4096
-#define IRQ_COMPRESSION_START	64
+	u8 pin;
 
-	static int pci_irq = IRQ_COMPRESSION_START;
-	/*
-	 * Mapping between Global System Interrupts, which
-	 * represent all possible interrupts, and IRQs
-	 * assigned to actual devices.
-	 */
-	static int gsi_to_irq[MAX_GSI_NUM];
-#else
+	if (!acpi_ioapic)
+		return 0;
+	if (!dev)
+		return 0;
+	if (dev->bus != &pci_bus_type)
+		return 0;
+
+	pdev = to_pci_dev(dev);
+	number = pdev->bus->number;
+	devfn = pdev->devfn;
+	pin = pdev->pin;
+	/* print the entry should happen on mptable identically */
+	mp_irq.type = MP_INTSRC;
+	mp_irq.irqtype = mp_INT;
+	mp_irq.irqflag = (trigger == ACPI_EDGE_SENSITIVE ? 4 : 0x0c) |
+				(polarity == ACPI_ACTIVE_HIGH ? 1 : 3);
+	mp_irq.srcbus = number;
+	mp_irq.srcbusirq = (((devfn >> 3) & 0x1f) << 2) | ((pin - 1) & 3);
+	ioapic = mp_find_ioapic(gsi);
+	mp_irq.dstapic = mp_ioapics[ioapic].apicid;
+	mp_irq.dstirq = mp_find_ioapic_pin(ioapic, gsi);
+
+	save_mp_irq(&mp_irq);
+#endif
+	return 0;
+}
+
+int mp_register_gsi(struct device *dev, u32 gsi, int trigger, int polarity)
+{
+	int ioapic;
+	int ioapic_pin;
+	struct io_apic_irq_attr irq_attr;
 
 	if (acpi_irq_model != ACPI_IRQ_MODEL_IOAPIC)
 		return gsi;
-#endif
 
 	/* Don't set up the ACPI SCI because it's already set up */
 	if (acpi_gbl_FADT.sci_interrupt == gsi)
@@ -1196,93 +1217,22 @@ int mp_register_gsi(u32 gsi, int triggering, int polarity)
 		gsi = ioapic_renumber_irq(ioapic, gsi);
 #endif
 
-	/*
-	 * Avoid pin reprogramming.  PRTs typically include entries
-	 * with redundant pin->gsi mappings (but unique PCI devices);
-	 * we only program the IOAPIC on the first.
-	 */
 	if (ioapic_pin > MP_MAX_IOAPIC_PIN) {
 		printk(KERN_ERR "Invalid reference to IOAPIC pin "
-		       "%d-%d\n", mp_ioapic_routing[ioapic].apic_id,
+		       "%d-%d\n", mp_ioapics[ioapic].apicid,
 		       ioapic_pin);
 		return gsi;
 	}
-	if (test_bit(ioapic_pin, mp_ioapic_routing[ioapic].pin_programmed)) {
-		pr_debug("Pin %d-%d already programmed\n",
-			 mp_ioapic_routing[ioapic].apic_id, ioapic_pin);
-#ifdef CONFIG_X86_32
-		return (gsi < IRQ_COMPRESSION_START ? gsi : gsi_to_irq[gsi]);
-#else
-		return gsi;
-#endif
-	}
-
-	set_bit(ioapic_pin, mp_ioapic_routing[ioapic].pin_programmed);
-#ifdef CONFIG_X86_32
-	/*
-	 * For GSI >= 64, use IRQ compression
-	 */
-	if ((gsi >= IRQ_COMPRESSION_START)
-	    && (triggering == ACPI_LEVEL_SENSITIVE)) {
-		/*
-		 * For PCI devices assign IRQs in order, avoiding gaps
-		 * due to unused I/O APIC pins.
-		 */
-		int irq = gsi;
-		if (gsi < MAX_GSI_NUM) {
-			/*
-			 * Retain the VIA chipset work-around (gsi > 15), but
-			 * avoid a problem where the 8254 timer (IRQ0) is setup
-			 * via an override (so it's not on pin 0 of the ioapic),
-			 * and at the same time, the pin 0 interrupt is a PCI
-			 * type.  The gsi > 15 test could cause these two pins
-			 * to be shared as IRQ0, and they are not shareable.
-			 * So test for this condition, and if necessary, avoid
-			 * the pin collision.
-			 */
-			gsi = pci_irq++;
-			/*
-			 * Don't assign IRQ used by ACPI SCI
-			 */
-			if (gsi == acpi_gbl_FADT.sci_interrupt)
-				gsi = pci_irq++;
-			gsi_to_irq[irq] = gsi;
-		} else {
-			printk(KERN_ERR "GSI %u is too high\n", gsi);
-			return gsi;
-		}
-	}
-#endif
-	io_apic_set_pci_routing(ioapic, ioapic_pin, gsi,
-				triggering == ACPI_EDGE_SENSITIVE ? 0 : 1,
-				polarity == ACPI_ACTIVE_HIGH ? 0 : 1);
-	return gsi;
-}
 
-int mp_config_acpi_gsi(unsigned char number, unsigned int devfn, u8 pin,
-			u32 gsi, int triggering, int polarity)
-{
-#ifdef CONFIG_X86_MPPARSE
-	struct mpc_intsrc mp_irq;
-	int ioapic;
+	if (enable_update_mptable)
+		mp_config_acpi_gsi(dev, gsi, trigger, polarity);
 
-	if (!acpi_ioapic)
-		return 0;
+	set_io_apic_irq_attr(&irq_attr, ioapic, ioapic_pin,
+			     trigger == ACPI_EDGE_SENSITIVE ? 0 : 1,
+			     polarity == ACPI_ACTIVE_HIGH ? 0 : 1);
+	io_apic_set_pci_routing(dev, gsi, &irq_attr);
 
-	/* print the entry should happen on mptable identically */
-	mp_irq.type = MP_INTSRC;
-	mp_irq.irqtype = mp_INT;
-	mp_irq.irqflag = (triggering == ACPI_EDGE_SENSITIVE ? 4 : 0x0c) |
-				(polarity == ACPI_ACTIVE_HIGH ? 1 : 3);
-	mp_irq.srcbus = number;
-	mp_irq.srcbusirq = (((devfn >> 3) & 0x1f) << 2) | ((pin - 1) & 3);
-	ioapic = mp_find_ioapic(gsi);
-	mp_irq.dstapic = mp_ioapic_routing[ioapic].apic_id;
-	mp_irq.dstirq = mp_find_ioapic_pin(ioapic, gsi);
-
-	save_mp_irq(&mp_irq);
-#endif
-	return 0;
+	return gsi;
 }
 
 /*
diff --git a/arch/x86/kernel/acpi/realmode/Makefile b/arch/x86/kernel/acpi/realmode/Makefile
index 1c31cc0e9de..167bc16ce0e 100644
--- a/arch/x86/kernel/acpi/realmode/Makefile
+++ b/arch/x86/kernel/acpi/realmode/Makefile
@@ -9,7 +9,7 @@
 always		:= wakeup.bin
 targets		:= wakeup.elf wakeup.lds
 
-wakeup-y	+= wakeup.o wakemain.o video-mode.o copy.o
+wakeup-y	+= wakeup.o wakemain.o video-mode.o copy.o bioscall.o regs.o
 
 # The link order of the video-*.o modules can matter.  In particular,
 # video-vga.o *must* be listed first, followed by video-vesa.o.
diff --git a/arch/x86/kernel/acpi/realmode/bioscall.S b/arch/x86/kernel/acpi/realmode/bioscall.S
new file mode 100644
index 00000000000..f51eb0bb56c
--- /dev/null
+++ b/arch/x86/kernel/acpi/realmode/bioscall.S
@@ -0,0 +1 @@
+#include "../../../boot/bioscall.S"
diff --git a/arch/x86/kernel/acpi/realmode/regs.c b/arch/x86/kernel/acpi/realmode/regs.c
new file mode 100644
index 00000000000..6206033ba20
--- /dev/null
+++ b/arch/x86/kernel/acpi/realmode/regs.c
@@ -0,0 +1 @@
+#include "../../../boot/regs.c"
diff --git a/arch/x86/kernel/amd_iommu.c b/arch/x86/kernel/amd_iommu.c
index a97db99dad5..1c60554537c 100644
--- a/arch/x86/kernel/amd_iommu.c
+++ b/arch/x86/kernel/amd_iommu.c
@@ -55,7 +55,16 @@ struct iommu_cmd {
 static int dma_ops_unity_map(struct dma_ops_domain *dma_dom,
 			     struct unity_map_entry *e);
 static struct dma_ops_domain *find_protection_domain(u16 devid);
+static u64* alloc_pte(struct protection_domain *dom,
+		      unsigned long address, u64
+		      **pte_page, gfp_t gfp);
+static void dma_ops_reserve_addresses(struct dma_ops_domain *dom,
+				      unsigned long start_page,
+				      unsigned int pages);
 
+#ifndef BUS_NOTIFY_UNBOUND_DRIVER
+#define BUS_NOTIFY_UNBOUND_DRIVER 0x0005
+#endif
 
 #ifdef CONFIG_AMD_IOMMU_STATS
 
@@ -213,7 +222,7 @@ irqreturn_t amd_iommu_int_handler(int irq, void *data)
 {
 	struct amd_iommu *iommu;
 
-	list_for_each_entry(iommu, &amd_iommu_list, list)
+	for_each_iommu(iommu)
 		iommu_poll_events(iommu);
 
 	return IRQ_HANDLED;
@@ -440,7 +449,7 @@ static void iommu_flush_domain(u16 domid)
 	__iommu_build_inv_iommu_pages(&cmd, CMD_INV_IOMMU_ALL_PAGES_ADDRESS,
 				      domid, 1, 1);
 
-	list_for_each_entry(iommu, &amd_iommu_list, list) {
+	for_each_iommu(iommu) {
 		spin_lock_irqsave(&iommu->lock, flags);
 		__iommu_queue_command(iommu, &cmd);
 		__iommu_completion_wait(iommu);
@@ -449,6 +458,35 @@ static void iommu_flush_domain(u16 domid)
 	}
 }
 
+void amd_iommu_flush_all_domains(void)
+{
+	int i;
+
+	for (i = 1; i < MAX_DOMAIN_ID; ++i) {
+		if (!test_bit(i, amd_iommu_pd_alloc_bitmap))
+			continue;
+		iommu_flush_domain(i);
+	}
+}
+
+void amd_iommu_flush_all_devices(void)
+{
+	struct amd_iommu *iommu;
+	int i;
+
+	for (i = 0; i <= amd_iommu_last_bdf; ++i) {
+		if (amd_iommu_pd_table[i] == NULL)
+			continue;
+
+		iommu = amd_iommu_rlookup_table[i];
+		if (!iommu)
+			continue;
+
+		iommu_queue_inv_dev_entry(iommu, i);
+		iommu_completion_wait(iommu);
+	}
+}
+
 /****************************************************************************
  *
  * The functions below are used the create the page table mappings for
@@ -468,7 +506,7 @@ static int iommu_map_page(struct protection_domain *dom,
 			  unsigned long phys_addr,
 			  int prot)
 {
-	u64 __pte, *pte, *page;
+	u64 __pte, *pte;
 
 	bus_addr  = PAGE_ALIGN(bus_addr);
 	phys_addr = PAGE_ALIGN(phys_addr);
@@ -477,27 +515,7 @@ static int iommu_map_page(struct protection_domain *dom,
 	if (bus_addr > IOMMU_MAP_SIZE_L3 || !(prot & IOMMU_PROT_MASK))
 		return -EINVAL;
 
-	pte = &dom->pt_root[IOMMU_PTE_L2_INDEX(bus_addr)];
-
-	if (!IOMMU_PTE_PRESENT(*pte)) {
-		page = (u64 *)get_zeroed_page(GFP_KERNEL);
-		if (!page)
-			return -ENOMEM;
-		*pte = IOMMU_L2_PDE(virt_to_phys(page));
-	}
-
-	pte = IOMMU_PTE_PAGE(*pte);
-	pte = &pte[IOMMU_PTE_L1_INDEX(bus_addr)];
-
-	if (!IOMMU_PTE_PRESENT(*pte)) {
-		page = (u64 *)get_zeroed_page(GFP_KERNEL);
-		if (!page)
-			return -ENOMEM;
-		*pte = IOMMU_L1_PDE(virt_to_phys(page));
-	}
-
-	pte = IOMMU_PTE_PAGE(*pte);
-	pte = &pte[IOMMU_PTE_L0_INDEX(bus_addr)];
+	pte = alloc_pte(dom, bus_addr, NULL, GFP_KERNEL);
 
 	if (IOMMU_PTE_PRESENT(*pte))
 		return -EBUSY;
@@ -595,7 +613,8 @@ static int dma_ops_unity_map(struct dma_ops_domain *dma_dom,
 		 * as allocated in the aperture
 		 */
 		if (addr < dma_dom->aperture_size)
-			__set_bit(addr >> PAGE_SHIFT, dma_dom->bitmap);
+			__set_bit(addr >> PAGE_SHIFT,
+				  dma_dom->aperture[0]->bitmap);
 	}
 
 	return 0;
@@ -632,42 +651,191 @@ static int init_unity_mappings_for_device(struct dma_ops_domain *dma_dom,
  ****************************************************************************/
 
 /*
- * The address allocator core function.
+ * The address allocator core functions.
  *
  * called with domain->lock held
  */
+
+/*
+ * This function checks if there is a PTE for a given dma address. If
+ * there is one, it returns the pointer to it.
+ */
+static u64* fetch_pte(struct protection_domain *domain,
+		      unsigned long address)
+{
+	u64 *pte;
+
+	pte = &domain->pt_root[IOMMU_PTE_L2_INDEX(address)];
+
+	if (!IOMMU_PTE_PRESENT(*pte))
+		return NULL;
+
+	pte = IOMMU_PTE_PAGE(*pte);
+	pte = &pte[IOMMU_PTE_L1_INDEX(address)];
+
+	if (!IOMMU_PTE_PRESENT(*pte))
+		return NULL;
+
+	pte = IOMMU_PTE_PAGE(*pte);
+	pte = &pte[IOMMU_PTE_L0_INDEX(address)];
+
+	return pte;
+}
+
+/*
+ * This function is used to add a new aperture range to an existing
+ * aperture in case of dma_ops domain allocation or address allocation
+ * failure.
+ */
+static int alloc_new_range(struct amd_iommu *iommu,
+			   struct dma_ops_domain *dma_dom,
+			   bool populate, gfp_t gfp)
+{
+	int index = dma_dom->aperture_size >> APERTURE_RANGE_SHIFT;
+	int i;
+
+#ifdef CONFIG_IOMMU_STRESS