19 files changed, 494 insertions, 89 deletions

diff --git a/arch/ia64/kernel/Makefile b/arch/ia64/kernel/Makefile
index 87fea11aecb7..c381ea954892 100644
--- a/arch/ia64/kernel/Makefile
+++ b/arch/ia64/kernel/Makefile
@@ -42,6 +42,10 @@ obj-$(CONFIG_IA64_ESI)		+= esi.o
 ifneq ($(CONFIG_IA64_ESI),)
 obj-y                           += esi_stub.o   # must be in kernel proper
 endif
+obj-$(CONFIG_DMAR)              += pci-dma.o
+ifeq ($(CONFIG_DMAR), y)
+obj-$(CONFIG_SWIOTLB)           += pci-swiotlb.o
+endif
 
 # The gate DSO image is built using a special linker script.
 targets += gate.so gate-syms.o
@@ -112,5 +116,23 @@ clean-files += $(objtree)/include/asm-ia64/nr-irqs.h
 ASM_PARAVIRT_OBJS = ivt.o entry.o
 define paravirtualized_native
 AFLAGS_$(1) += -D__IA64_ASM_PARAVIRTUALIZED_NATIVE
+AFLAGS_pvchk-sed-$(1) += -D__IA64_ASM_PARAVIRTUALIZED_PVCHECK
+extra-y += pvchk-$(1)
 endef
 $(foreach obj,$(ASM_PARAVIRT_OBJS),$(eval $(call paravirtualized_native,$(obj))))
+
+#
+# Checker for paravirtualizations of privileged operations.
+#
+quiet_cmd_pv_check_sed = PVCHK   $@
+define cmd_pv_check_sed
+        sed -f $(srctree)/arch/$(SRCARCH)/scripts/pvcheck.sed $< > $@
+endef
+
+$(obj)/pvchk-sed-%.s: $(src)/%.S $(srctree)/arch/$(SRCARCH)/scripts/pvcheck.sed FORCE
+        $(call if_changed_dep,as_s_S)
+$(obj)/pvchk-%.s: $(obj)/pvchk-sed-%.s FORCE
+        $(call if_changed,pv_check_sed)
+$(obj)/pvchk-%.o: $(obj)/pvchk-%.s FORCE
+        $(call if_changed,as_o_S)
+.PRECIOUS: $(obj)/pvchk-sed-%.s $(obj)/pvchk-%.s $(obj)/pvchk-%.o
diff --git a/arch/ia64/kernel/acpi.c b/arch/ia64/kernel/acpi.c
index 5d1eb7ee2bf6..bd7acc71e8a9 100644
--- a/arch/ia64/kernel/acpi.c
+++ b/arch/ia64/kernel/acpi.c
@@ -52,6 +52,7 @@
 #include <asm/numa.h>
 #include <asm/sal.h>
 #include <asm/cyclone.h>
+#include <asm/xen/hypervisor.h>
 
 #define BAD_MADT_ENTRY(entry, end) (                                        \
                 (!entry) || (unsigned long)entry + sizeof(*entry) > end ||  \
@@ -91,6 +92,9 @@ acpi_get_sysname(void)
         struct acpi_table_rsdp *rsdp;
         struct acpi_table_xsdt *xsdt;
         struct acpi_table_header *hdr;
+#ifdef CONFIG_DMAR
+        u64 i, nentries;
+#endif
 
         rsdp_phys = acpi_find_rsdp();
         if (!rsdp_phys) {
@@ -121,7 +125,21 @@ acpi_get_sysname(void)
                         return "uv";
                 else
                         return "sn2";
+        } else if (xen_pv_domain() && !strcmp(hdr->oem_id, "XEN")) {
+                return "xen";
+        }
+
+#ifdef CONFIG_DMAR
+        /* Look for Intel IOMMU */
+        nentries = (hdr->length - sizeof(*hdr)) /
+                         sizeof(xsdt->table_offset_entry[0]);
+        for (i = 0; i < nentries; i++) {
+                hdr = __va(xsdt->table_offset_entry[i]);
+                if (strncmp(hdr->signature, ACPI_SIG_DMAR,
+                        sizeof(ACPI_SIG_DMAR) - 1) == 0)
+                        return "dig_vtd";
         }
+#endif
 
         return "dig";
 #else
@@ -137,6 +155,10 @@ acpi_get_sysname(void)
         return "uv";
 # elif defined (CONFIG_IA64_DIG)
         return "dig";
+# elif defined (CONFIG_IA64_XEN_GUEST)
+        return "xen";
+# elif defined(CONFIG_IA64_DIG_VTD)
+        return "dig_vtd";
 # else
 #       error Unknown platform.  Fix acpi.c.
 # endif
@@ -656,6 +678,30 @@ static int __init acpi_parse_fadt(struct acpi_table_header *table)
         return 0;
 }
 
+int __init early_acpi_boot_init(void)
+{
+        int ret;
+
+        /*
+         * do a partial walk of MADT to determine how many CPUs
+         * we have including offline CPUs
+         */
+        if (acpi_table_parse(ACPI_SIG_MADT, acpi_parse_madt)) {
+                printk(KERN_ERR PREFIX "Can't find MADT\n");
+                return 0;
+        }
+
+        ret = acpi_table_parse_madt(ACPI_MADT_TYPE_LOCAL_SAPIC,
+                acpi_parse_lsapic, NR_CPUS);
+        if (ret < 1)
+                printk(KERN_ERR PREFIX
+                       "Error parsing MADT - no LAPIC entries\n");
+
+        return 0;
+}
+
+
+
 int __init acpi_boot_init(void)
 {
 
@@ -679,11 +725,6 @@ int __init acpi_boot_init(void)
                 printk(KERN_ERR PREFIX
                        "Error parsing LAPIC address override entry\n");
 
-        if (acpi_table_parse_madt(ACPI_MADT_TYPE_LOCAL_SAPIC, acpi_parse_lsapic, NR_CPUS)
-            < 1)
-                printk(KERN_ERR PREFIX
-                       "Error parsing MADT - no LAPIC entries\n");
-
         if (acpi_table_parse_madt(ACPI_MADT_TYPE_LOCAL_APIC_NMI, acpi_parse_lapic_nmi, 0)
             < 0)
                 printk(KERN_ERR PREFIX "Error parsing LAPIC NMI entry\n");
diff --git a/arch/ia64/kernel/asm-offsets.c b/arch/ia64/kernel/asm-offsets.c
index 94c44b1ccfd0..742dbb1d5a4f 100644
--- a/arch/ia64/kernel/asm-offsets.c
+++ b/arch/ia64/kernel/asm-offsets.c
@@ -16,6 +16,9 @@
 #include <asm/sigcontext.h>
 #include <asm/mca.h>
 
+#include <asm/xen/interface.h>
+#include <asm/xen/hypervisor.h>
+
 #include "../kernel/sigframe.h"
 #include "../kernel/fsyscall_gtod_data.h"
 
@@ -286,4 +289,32 @@ void foo(void)
                 offsetof (struct itc_jitter_data_t, itc_jitter));
         DEFINE(IA64_ITC_LASTCYCLE_OFFSET,
                 offsetof (struct itc_jitter_data_t, itc_lastcycle));
+
+#ifdef CONFIG_XEN
+        BLANK();
+
+        DEFINE(XEN_NATIVE_ASM, XEN_NATIVE);
+        DEFINE(XEN_PV_DOMAIN_ASM, XEN_PV_DOMAIN);
+
+#define DEFINE_MAPPED_REG_OFS(sym, field) \
+        DEFINE(sym, (XMAPPEDREGS_OFS + offsetof(struct mapped_regs, field)))
+
+        DEFINE_MAPPED_REG_OFS(XSI_PSR_I_ADDR_OFS, interrupt_mask_addr);
+        DEFINE_MAPPED_REG_OFS(XSI_IPSR_OFS, ipsr);
+        DEFINE_MAPPED_REG_OFS(XSI_IIP_OFS, iip);
+        DEFINE_MAPPED_REG_OFS(XSI_IFS_OFS, ifs);
+        DEFINE_MAPPED_REG_OFS(XSI_PRECOVER_IFS_OFS, precover_ifs);
+        DEFINE_MAPPED_REG_OFS(XSI_ISR_OFS, isr);
+        DEFINE_MAPPED_REG_OFS(XSI_IFA_OFS, ifa);
+        DEFINE_MAPPED_REG_OFS(XSI_IIPA_OFS, iipa);
+        DEFINE_MAPPED_REG_OFS(XSI_IIM_OFS, iim);
+        DEFINE_MAPPED_REG_OFS(XSI_IHA_OFS, iha);
+        DEFINE_MAPPED_REG_OFS(XSI_ITIR_OFS, itir);
+        DEFINE_MAPPED_REG_OFS(XSI_PSR_IC_OFS, interrupt_collection_enabled);
+        DEFINE_MAPPED_REG_OFS(XSI_BANKNUM_OFS, banknum);
+        DEFINE_MAPPED_REG_OFS(XSI_BANK0_R16_OFS, bank0_regs[0]);
+        DEFINE_MAPPED_REG_OFS(XSI_BANK1_R16_OFS, bank1_regs[0]);
+        DEFINE_MAPPED_REG_OFS(XSI_B0NATS_OFS, vbnat);
+        DEFINE_MAPPED_REG_OFS(XSI_B1NATS_OFS, vnat);
+#endif /* CONFIG_XEN */
 }
diff --git a/arch/ia64/kernel/entry.S b/arch/ia64/kernel/entry.S
index 0dd6c1419d8d..d435f4a7a96c 100644
--- a/arch/ia64/kernel/entry.S
+++ b/arch/ia64/kernel/entry.S
@@ -499,6 +499,7 @@ GLOBAL_ENTRY(prefetch_stack)
 END(prefetch_stack)
 
 GLOBAL_ENTRY(kernel_execve)
+        rum psr.ac
         mov r15=__NR_execve                     // put syscall number in place
         break __BREAK_SYSCALL
         br.ret.sptk.many rp
@@ -534,6 +535,11 @@ GLOBAL_ENTRY(ia64_trace_syscall)
         stf.spill [r16]=f10
         stf.spill [r17]=f11
         br.call.sptk.many rp=syscall_trace_enter // give parent a chance to catch syscall args
+        cmp.lt p6,p0=r8,r0                      // check tracehook
+        adds r2=PT(R8)+16,sp                    // r2 = &pt_regs.r8
+        adds r3=PT(R10)+16,sp                   // r3 = &pt_regs.r10
+        mov r10=0
+(p6)    br.cond.sptk strace_error               // syscall failed ->
         adds r16=PT(F6)+16,sp
         adds r17=PT(F7)+16,sp
         ;;
diff --git a/arch/ia64/kernel/head.S b/arch/ia64/kernel/head.S
index 66e491d8baac..59301c472800 100644
--- a/arch/ia64/kernel/head.S
+++ b/arch/ia64/kernel/head.S
@@ -260,7 +260,7 @@ start_ap:
          * Switch into virtual mode:
          */
         movl r16=(IA64_PSR_IT|IA64_PSR_IC|IA64_PSR_DT|IA64_PSR_RT|IA64_PSR_DFH|IA64_PSR_BN \
-                  |IA64_PSR_DI)
+                  |IA64_PSR_DI|IA64_PSR_AC)
         ;;
         mov cr.ipsr=r16
         movl r17=1f
diff --git a/arch/ia64/kernel/ivt.S b/arch/ia64/kernel/ivt.S
index 416a952b19bd..f675d8e33853 100644
--- a/arch/ia64/kernel/ivt.S
+++ b/arch/ia64/kernel/ivt.S
@@ -580,7 +580,7 @@ ENTRY(dirty_bit)
         mov b0=r29                              // restore b0
         ;;
         st8 [r17]=r18                           // store back updated PTE
-        itc.d r18                               // install updated PTE
+        ITC_D(p0, r18, r16)                     // install updated PTE
 #endif
         mov pr=r31,-1                           // restore pr
         RFI
@@ -646,7 +646,7 @@ ENTRY(iaccess_bit)
         mov b0=r29                              // restore b0
         ;;
         st8 [r17]=r18                           // store back updated PTE
-        itc.i r18                               // install updated PTE
+        ITC_I(p0, r18, r16)                     // install updated PTE
 #endif /* !CONFIG_SMP */
         mov pr=r31,-1
         RFI
@@ -698,7 +698,7 @@ ENTRY(daccess_bit)
         or r18=_PAGE_A,r18                      // set the accessed bit
         ;;
         st8 [r17]=r18                           // store back updated PTE
-        itc.d r18                               // install updated PTE
+        ITC_D(p0, r18, r16)                     // install updated PTE
 #endif
         mov b0=r29                              // restore b0
         mov pr=r31,-1
diff --git a/arch/ia64/kernel/mca.c b/arch/ia64/kernel/mca.c
index 7dd96c127177..bab1de2d2f6a 100644
--- a/arch/ia64/kernel/mca.c
+++ b/arch/ia64/kernel/mca.c
@@ -1139,7 +1139,7 @@ ia64_mca_modify_original_stack(struct pt_regs *regs,
         return previous_current;
 
 no_mod:
-        printk(KERN_INFO "cpu %d, %s %s, original stack not modified\n",
+        mprintk(KERN_INFO "cpu %d, %s %s, original stack not modified\n",
                         smp_processor_id(), type, msg);
         return previous_current;
 }
diff --git a/arch/ia64/kernel/msi_ia64.c b/arch/ia64/kernel/msi_ia64.c
index 60c6ef67ebb2..702a09c13238 100644
--- a/arch/ia64/kernel/msi_ia64.c
+++ b/arch/ia64/kernel/msi_ia64.c
@@ -5,6 +5,7 @@
 #include <linux/pci.h>
 #include <linux/irq.h>
 #include <linux/msi.h>
+#include <linux/dmar.h>
 #include <asm/smp.h>
 
 /*
@@ -162,3 +163,82 @@ void arch_teardown_msi_irq(unsigned int irq)
 
         return ia64_teardown_msi_irq(irq);
 }
+
+#ifdef CONFIG_DMAR
+#ifdef CONFIG_SMP
+static void dmar_msi_set_affinity(unsigned int irq, cpumask_t mask)
+{
+        struct irq_cfg *cfg = irq_cfg + irq;
+        struct msi_msg msg;
+        int cpu = first_cpu(mask);
+
+
+        if (!cpu_online(cpu))
+                return;
+
+        if (irq_prepare_move(irq, cpu))
+                return;
+
+        dmar_msi_read(irq, &msg);
+
+        msg.data &= ~MSI_DATA_VECTOR_MASK;
+        msg.data |= MSI_DATA_VECTOR(cfg->vector);
+        msg.address_lo &= ~MSI_ADDR_DESTID_MASK;
+        msg.address_lo |= MSI_ADDR_DESTID_CPU(cpu_physical_id(cpu));
+
+        dmar_msi_write(irq, &msg);
+        irq_desc[irq].affinity = mask;
+}
+#endif /* CONFIG_SMP */
+
+struct irq_chip dmar_msi_type = {
+        .name = "DMAR_MSI",
+        .unmask = dmar_msi_unmask,
+        .mask = dmar_msi_mask,
+        .ack = ia64_ack_msi_irq,
+#ifdef CONFIG_SMP
+        .set_affinity = dmar_msi_set_affinity,
+#endif
+        .retrigger = ia64_msi_retrigger_irq,
+};
+
+static int
+msi_compose_msg(struct pci_dev *pdev, unsigned int irq, struct msi_msg *msg)
+{
+        struct irq_cfg *cfg = irq_cfg + irq;
+        unsigned dest;
+        cpumask_t mask;
+
+        cpus_and(mask, irq_to_domain(irq), cpu_online_map);
+        dest = cpu_physical_id(first_cpu(mask));
+
+        msg->address_hi = 0;
+        msg->address_lo =
+                MSI_ADDR_HEADER |
+                MSI_ADDR_DESTMODE_PHYS |
+                MSI_ADDR_REDIRECTION_CPU |
+                MSI_ADDR_DESTID_CPU(dest);
+
+        msg->data =
+                MSI_DATA_TRIGGER_EDGE |
+                MSI_DATA_LEVEL_ASSERT |
+                MSI_DATA_DELIVERY_FIXED |
+                MSI_DATA_VECTOR(cfg->vector);
+        return 0;
+}
+
+int arch_setup_dmar_msi(unsigned int irq)
+{
+        int ret;
+        struct msi_msg msg;
+
+        ret = msi_compose_msg(NULL, irq, &msg);
+        if (ret < 0)
+                return ret;
+        dmar_msi_write(irq, &msg);
+        set_irq_chip_and_handler_name(irq, &dmar_msi_type, handle_edge_irq,
+                "edge");
+        return 0;
+}
+#endif /* CONFIG_DMAR */
+
diff --git a/arch/ia64/kernel/nr-irqs.c b/arch/ia64/kernel/nr-irqs.c
index 8273afc32db8..ee564575148e 100644
--- a/arch/ia64/kernel/nr-irqs.c
+++ b/arch/ia64/kernel/nr-irqs.c
@@ -10,6 +10,7 @@
 #include <linux/kbuild.h>
 #include <linux/threads.h>
 #include <asm/native/irq.h>
+#include <asm/xen/irq.h>
 
 void foo(void)
 {
diff --git a/arch/ia64/kernel/paravirt.c b/arch/ia64/kernel/paravirt.c
index afaf5b9a2cf0..9f14c16f6369 100644
--- a/arch/ia64/kernel/paravirt.c
+++ b/arch/ia64/kernel/paravirt.c
@@ -130,7 +130,7 @@ ia64_native_getreg_func(int regnum)
         unsigned long res = -1;
         switch (regnum) {
         CASE_GET_REG(GP);
-        CASE_GET_REG(IP);
+        /*CASE_GET_REG(IP);*/ /* returned ip value shouldn't be constant */
         CASE_GET_REG(PSR);
         CASE_GET_REG(TP);
         CASE_GET_REG(SP);
@@ -332,7 +332,7 @@ ia64_native_iosapic_write(char __iomem *iosapic, unsigned int reg, u32 val)
 
 struct pv_iosapic_ops pv_iosapic_ops = {
         .pcat_compat_init = ia64_native_iosapic_pcat_compat_init,
-        .get_irq_chip = ia64_native_iosapic_get_irq_chip,
+        .__get_irq_chip = ia64_native_iosapic_get_irq_chip,
 
         .__read = ia64_native_iosapic_read,
         .__write = ia64_native_iosapic_write,
diff --git a/arch/ia64/kernel/paravirt_inst.h b/arch/ia64/kernel/paravirt_inst.h
index 5cad6fb2ed19..64d6d810c64b 100644
--- a/arch/ia64/kernel/paravirt_inst.h
+++ b/arch/ia64/kernel/paravirt_inst.h
@@ -20,7 +20,9 @@
  *
  */
 
-#ifdef __IA64_ASM_PARAVIRTUALIZED_XEN
+#ifdef __IA64_ASM_PARAVIRTUALIZED_PVCHECK
+#include <asm/native/pvchk_inst.h>
+#elif defined(__IA64_ASM_PARAVIRTUALIZED_XEN)
 #include <asm/xen/inst.h>
 #include <asm/xen/minstate.h>
 #else
diff --git a/arch/ia64/kernel/pci-dma.c b/arch/ia64/kernel/pci-dma.c
new file mode 100644
index 000000000000..2a92f637431d
--- /dev/null
+++ b/arch/ia64/kernel/pci-dma.c
@@ -0,0 +1,119 @@
+/*
+ * Dynamic DMA mapping support.
+ */
+
+#include <linux/types.h>
+#include <linux/mm.h>
+#include <linux/string.h>
+#include <linux/pci.h>
+#include <linux/module.h>
+#include <linux/dmar.h>
+#include <asm/iommu.h>
+#include <asm/machvec.h>
+#include <linux/dma-mapping.h>
+
+#include <asm/system.h>
+
+#ifdef CONFIG_DMAR
+
+#include <linux/kernel.h>
+
+#include <asm/page.h>
+
+dma_addr_t bad_dma_address __read_mostly;
+EXPORT_SYMBOL(bad_dma_address);
+
+static int iommu_sac_force __read_mostly;
+
+int no_iommu __read_mostly;
+#ifdef CONFIG_IOMMU_DEBUG
+int force_iommu __read_mostly = 1;
+#else
+int force_iommu __read_mostly;
+#endif
+
+/* Set this to 1 if there is a HW IOMMU in the system */
+int iommu_detected __read_mostly;
+
+/* Dummy device used for NULL arguments (normally ISA). Better would
+   be probably a smaller DMA mask, but this is bug-to-bug compatible
+   to i386. */
+struct device fallback_dev = {
+        .bus_id = "fallback device",
+        .coherent_dma_mask = DMA_32BIT_MASK,
+        .dma_mask = &fallback_dev.coherent_dma_mask,
+};
+
+void __init pci_iommu_alloc(void)
+{
+        /*
+         * The order of these functions is important for
+         * fall-back/fail-over reasons
+         */
+        detect_intel_iommu();
+
+#ifdef CONFIG_SWIOTLB
+        pci_swiotlb_init();
+#endif
+}
+
+static int __init pci_iommu_init(void)
+{
+        if (iommu_detected)
+                intel_iommu_init();
+
+        return 0;
+}
+
+/* Must execute after PCI subsystem */
+fs_initcall(pci_iommu_init);
+
+void pci_iommu_shutdown(void)
+{
+        return;
+}
+
+void __init
+iommu_dma_init(void)
+{
+        return;
+}
+
+struct dma_mapping_ops *dma_ops;
+EXPORT_SYMBOL(dma_ops);
+
+int iommu_dma_supported(struct device *dev, u64 mask)
+{
+        struct dma_mapping_ops *ops = get_dma_ops(dev);
+
+        if (ops->dma_supported_op)
+                return ops->dma_supported_op(dev, mask);
+
+        /* Copied from i386. Doesn't make much sense, because it will
+           only work for pci_alloc_coherent.
+           The caller just has to use GFP_DMA in this case. */
+        if (mask < DMA_24BIT_MASK)
+                return 0;
+
+        /* Tell the device to use SAC when IOMMU force is on.  This
+           allows the driver to use cheaper accesses in some cases.
+
+           Problem with this is that if we overflow the IOMMU area and
+           return DAC as fallback address the device may not handle it
+           correctly.
+
+           As a special case some controllers have a 39bit address
+           mode that is as efficient as 32bit (aic79xx). Don't force
+           SAC for these.  Assume all masks <= 40 bits are of this
+           type. Normally this doesn't make any difference, but gives
+           more gentle handling of IOMMU overflow. */
+        if (iommu_sac_force && (mask >= DMA_40BIT_MASK)) {
+                dev_info(dev, "Force SAC with mask %lx\n", mask);
+                return 0;
+        }
+
+        return 1;
+}
+EXPORT_SYMBOL(iommu_dma_supported);
+
+#endif
diff --git a/arch/ia64/kernel/pci-swiotlb.c b/arch/ia64/kernel/pci-swiotlb.c
new file mode 100644
index 000000000000..16c50516dbc1
--- /dev/null
+++ b/arch/ia64/kernel/pci-swiotlb.c
@@ -0,0 +1,46 @@
+/* Glue code to lib/swiotlb.c */
+
+#include <linux/pci.h>
+#include <linux/cache.h>
+#include <linux/module.h>
+#include <linux/dma-mapping.h>
+
+#include <asm/swiotlb.h>
+#include <asm/dma.h>
+#include <asm/iommu.h>
+#include <asm/machvec.h>
+
+int swiotlb __read_mostly;
+EXPORT_SYMBOL(swiotlb);
+
+struct dma_mapping_ops swiotlb_dma_ops = {
+        .mapping_error = swiotlb_dma_mapping_error,
+        .alloc_coherent = swiotlb_alloc_coherent,
+        .free_coherent = swiotlb_free_coherent,
+        .map_single = swiotlb_map_single,
+        .unmap_single = swiotlb_unmap_single,
+        .sync_single_for_cpu = swiotlb_sync_single_for_cpu,
+        .sync_single_for_device = swiotlb_sync_single_for_device,
+        .sync_single_range_for_cpu = swiotlb_sync_single_range_for_cpu,
+        .sync_single_range_for_device = swiotlb_sync_single_range_for_device,
+        .sync_sg_for_cpu = swiotlb_sync_sg_for_cpu,
+        .sync_sg_for_device = swiotlb_sync_sg_for_device,
+        .map_sg = swiotlb_map_sg,
+        .unmap_sg = swiotlb_unmap_sg,
+        .dma_supported_op = swiotlb_dma_supported,
+};
+
+void __init pci_swiotlb_init(void)
+{
+        if (!iommu_detected) {
+#ifdef CONFIG_IA64_GENERIC
+                swiotlb = 1;
+                printk(KERN_INFO "PCI-DMA: Re-initialize machine vector.\n");
+                machvec_init("dig");
+                swiotlb_init();
+                dma_ops = &swiotlb_dma_ops;
+#else
+                panic("Unable to find Intel IOMMU");
+#endif
+        }
+}
diff --git a/arch/ia64/kernel/perfmon.c b/arch/ia64/kernel/perfmon.c
index fc8f3509df27..6543a5547c84 100644
--- a/arch/ia64/kernel/perfmon.c
+++ b/arch/ia64/kernel/perfmon.c
@@ -40,6 +40,7 @@
 #include <linux/capability.h>
 #include <linux/rcupdate.h>
 #include <linux/completion.h>
+#include <linux/tracehook.h>
 
 #include <asm/errno.h>
 #include <asm/intrinsics.h>
@@ -1994,11 +1995,6 @@ pfm_close(struct inode *inode, struct file *filp)
                 return -EBADF;
         }
 
-        if (filp->f_flags & FASYNC) {
-                DPRINT(("cleaning up async_queue=%p\n", ctx->ctx_async_queue));
-                pfm_do_fasync(-1, filp, ctx, 0);
-        }
-
         PROTECT_CTX(ctx, flags);
 
         state     = ctx->ctx_state;
@@ -3684,7 +3680,7 @@ pfm_restart(pfm_context_t *ctx, void *arg, int count, struct pt_regs *regs)
 
                 PFM_SET_WORK_PENDING(task, 1);
 
-                tsk_set_notify_resume(task);
+                set_notify_resume(task);
 
                 /*
                  * XXX: send reschedule if task runs on another CPU
@@ -5044,8 +5040,6 @@ pfm_handle_work(void)
 
         PFM_SET_WORK_PENDING(current, 0);
 
-        tsk_clear_notify_resume(current);
-
         regs = task_pt_regs(current);
 
         /*
@@ -5414,7 +5408,7 @@ pfm_overflow_handler(struct task_struct *task, pfm_context_t *ctx, u64 pmc0, str
                          * when coming from ctxsw, current still points to the
                          * previous task, therefore we must work with task and not current.
                          */
-                        tsk_set_notify_resume(task);
+                        set_notify_resume(task);
                 }
                 /*
                  * defer until state is changed (shorten spin window). the context is locked
diff --git a/arch/ia64/kernel/process.c b/arch/ia64/kernel/process.c
index 3ab8373103ec..c57162705147 100644
--- a/arch/ia64/kernel/process.c
+++ b/arch/ia64/kernel/process.c
@@ -28,6 +28,7 @@
 #include <linux/delay.h>
 #include <linux/kdebug.h>
 #include <linux/utsname.h>
+#include <linux/tracehook.h>
 
 #include <asm/cpu.h>
 #include <asm/delay.h>
@@ -160,21 +161,6 @@ show_regs (struct pt_regs *regs)
                 show_stack(NULL, NULL);
 }
 
-void tsk_clear_notify_resume(struct task_struct *tsk)
-{
-#ifdef CONFIG_PERFMON
-        if (tsk->thread.pfm_needs_checking)
-                return;
-#endif
-        if (test_ti_thread_flag(task_thread_info(tsk), TIF_RESTORE_RSE))
-                return;
-        clear_ti_thread_flag(task_thread_info(tsk), TIF_NOTIFY_RESUME);
-}
-
-/*
- * do_notify_resume_user():
- *      Called from notify_resume_user at entry.S, with interrupts disabled.
- */
 void
 do_notify_resume_user(sigset_t *unused, struct sigscratch *scr, long in_syscall)
 {
@@ -203,6 +189,11 @@ do_notify_resume_user(sigset_t *unused, struct sigscratch *scr, long in_syscall)
                 ia64_do_signal(scr, in_syscall);
         }
 
+        if (test_thread_flag(TIF_NOTIFY_RESUME)) {
+                clear_thread_flag(TIF_NOTIFY_RESUME);
+                tracehook_notify_resume(&scr->pt);
+        }
+
         /* copy user rbs to kernel rbs */
         if (unlikely(test_thread_flag(TIF_RESTORE_RSE))) {
                 local_irq_enable();     /* force interrupt enable */
@@ -251,7 +242,6 @@ default_idle (void)
 /* We don't actually take CPU down, just spin without interrupts. */
 static inline void play_dead(void)
 {
-        extern void ia64_cpu_local_tick (void);
         unsigned int this_cpu = smp_processor_id();
 
         /* Ack it */
diff --git a/arch/ia64/kernel/ptrace.c b/arch/ia64/kernel/ptrace.c
index 2a9943b5947f..92c9689b7d97 100644
--- a/arch/ia64/kernel/ptrace.c
+++ b/arch/ia64/kernel/ptrace.c
@@ -22,6 +22,7 @@
 #include <linux/signal.h>
 #include <linux/regset.h>
 #include <linux/elf.h>
+#include <linux/tracehook.h>
 
 #include <asm/pgtable.h>
 #include <asm/processor.h>
@@ -603,7 +604,7 @@ void ia64_ptrace_stop(void)
 {
         if (test_and_set_tsk_thread_flag(current, TIF_RESTORE_RSE))
                 return;
-        tsk_set_notify_resume(current);
+        set_notify_resume(current);
         unw_init_running(do_sync_rbs, ia64_sync_user_rbs);
 }
 
@@ -613,7 +614,6 @@ void ia64_ptrace_stop(void)
 void ia64_sync_krbs(void)
 {
         clear_tsk_thread_flag(current, TIF_RESTORE_RSE);
-        tsk_clear_notify_resume(current);
 
         unw_init_running(do_sync_rbs, ia64_sync_kernel_rbs);
 }
@@ -644,7 +644,7 @@ ptrace_attach_sync_user_rbs (struct task_struct *child)
                 spin_lock_irq(&child->sighand->siglock);
                 if (child->state == TASK_STOPPED &&
                     !test_and_set_tsk_thread_flag(child, TIF_RESTORE_RSE)) {
-                        tsk_set_notify_resume(child);
+                        set_notify_resume(child);
 
                         child->state = TASK_TRACED;
                         stopped = 1;
@@ -1232,37 +1232,16 @@ arch_ptrace (struct task_struct *child, long request, long addr, long data)
 }
 
 
-static void
-syscall_trace (void)
-{
-        /*
-         * The 0x80 provides a way for the tracing parent to
-         * distinguish between a syscall stop and SIGTRAP delivery.
-         */
-        ptrace_notify(SIGTRAP
-                      | ((current->ptrace & PT_TRACESYSGOOD) ? 0x80 : 0));
-
-        /*
-         * This isn't the same as continuing with a signal, but it
-         * will do for normal use.  strace only continues with a
-         * signal if the stopping signal is not SIGTRAP.  -brl
-         */
-        if (current->exit_code) {
-                send_sig(current->exit_code, current, 1);
-                current->exit_code = 0;
-        }
-}
-
 /* "asmlinkage" so the input arguments are preserved... */
 
-asmlinkage void
+asmlinkage long
 syscall_trace_enter (long arg0, long arg1, long arg2, long arg3,
                      long arg4, long arg5, long arg6, long arg7,
                      struct pt_regs regs)
 {
-        if (test_thread_flag(TIF_SYSCALL_TRACE) 
-            && (current->ptrace & PT_PTRACED))
-                syscall_trace();
+        if (test_thread_flag(TIF_SYSCALL_TRACE))
+                if (tracehook_report_syscall_entry(&regs))
+                        return -ENOSYS;
 
         /* copy user rbs to kernel rbs */
         if (test_thread_flag(TIF_RESTORE_RSE))
@@ -1283,6 +1262,7 @@ syscall_trace_enter (long arg0, long arg1, long arg2, long arg3,
                 audit_syscall_entry(arch, syscall, arg0, arg1, arg2, arg3);
         }
 
+        return 0;
 }
 
 /* "asmlinkage" so the input arguments are preserved... */
@@ -1292,6 +1272,8 @@ syscall_trace_leave (long arg0, long arg1, long arg2, long arg3,
                      long arg4, long arg5, long arg6, long arg7,
                      struct pt_regs regs)
 {
+        int step;
+
         if (unlikely(current->audit_context)) {
                 int success = AUDITSC_RESULT(regs.r10);
                 long result = regs.r8;
@@ -1301,10 +1283,9 @@ syscall_trace_leave (long arg0, long arg1, long arg2, long arg3,
                 audit_syscall_exit(success, result);
         }
 
-        if ((test_thread_flag(TIF_SYSCALL_TRACE)
-            || test_thread_flag(TIF_SINGLESTEP))
-            && (current->ptrace & PT_PTRACED))
-                syscall_trace();
+        step = test_thread_flag(TIF_SINGLESTEP);
+        if (step || test_thread_flag(TIF_SYSCALL_TRACE))
+                tracehook_report_syscall_exit(&regs, step);
 
         /* copy user rbs to kernel rbs */
         if (test_thread_flag(TIF_RESTORE_RSE))
@@ -1940,7 +1921,7 @@ gpregs_writeback(struct task_struct *target,
 {
         if (test_and_set_tsk_thread_flag(target, TIF_RESTORE_RSE))
                 return 0;
-        tsk_set_notify_resume(target);
+        set_notify_resume(target);
         return do_regset_call(do_gpregs_writeback, target, regset, 0, 0,
                 NULL, NULL);
 }
@@ -2199,3 +2180,68 @@ const struct user_regset_view *task_user_regset_view(struct task_struct *tsk)
 #endif
         return &user_ia64_view;
 }
+
+struct syscall_get_set_args {
+        unsigned int i;
+        unsigned int n;
+        unsigned long *args;
+        struct pt_regs *regs;
+        int rw;
+};
+
+static void syscall_get_set_args_cb(struct unw_frame_info *info, void *data)
+{
+        struct syscall_get_set_args *args = data;
+        struct pt_regs *pt = args->regs;
+        unsigned long *krbs, cfm, ndirty;
+        int i, count;
+
+        if (unw_unwind_to_user(info) < 0)
+                return;
+
+        cfm = pt->cr_ifs;
+        krbs = (unsigned long *)info->task + IA64_RBS_OFFSET/8;
+        ndirty = ia64_rse_num_regs(krbs, krbs + (pt->loadrs >> 19));
+
+        count = 0;
+        if (in_syscall(pt))
+                count = min_t(int, args->n, cfm & 0x7f);
+
+        for (i = 0; i < count; i++) {
+                if (args->rw)
+                        *ia64_rse_skip_regs(krbs, ndirty + i + args->i) =
+                                args->args[i];
+                else
+                        args->args[i] = *ia64_rse_skip_regs(krbs,
+                                ndirty + i + args->i);
+        }
+
+        if (!args->rw) {
+                while (i < args->n) {
+                        args->args[i] = 0;
+                        i++;
+                }
+        }
+}
+
+void ia64_syscall_get_set_arguments(struct task_struct *task,
+        struct pt_regs *regs, unsigned int i, unsigned int n,
+        unsigned long *args, int rw)
+{
+        struct syscall_get_set_args data = {
+                .i = i,
+                .n = n,
+                .args = args,
+                .regs = regs,
+                .rw = rw,
+        };
+
+        if (task == current)
+                unw_init_running(syscall_get_set_args_cb, &data);
+        else {
+                struct unw_frame_info ufi;
+                memset(&ufi, 0, sizeof(ufi));
+                unw_init_from_blocked_task(&ufi, task);
+                syscall_get_set_args_cb(&ufi, &data);
+        }
+}
diff --git a/arch/ia64/kernel/setup.c b/arch/ia64/kernel/setup.c
index 916ba898237f..865af27c7737 100644
--- a/arch/ia64/kernel/setup.c
+++ b/arch/ia64/kernel/setup.c
@@ -116,6 +116,13 @@ unsigned int num_io_spaces;
  */
 #define I_CACHE_STRIDE_SHIFT    5       /* Safest way to go: 32 bytes by 32 bytes */
 unsigned long ia64_i_cache_stride_shift = ~0;
+/*
+ * "clflush_cache_range()" needs to know what processor dependent stride size to
+ * use when it flushes cache lines including both d-cache and i-cache.
+ */
+/* Safest way to go: 32 bytes by 32 bytes */
+#define CACHE_STRIDE_SHIFT      5
+unsigned long ia64_cache_stride_shift = ~0;
 
 /*
  * The merge_mask variable needs to be set to (max(iommu_page_size(iommu)) - 1).  This
@@ -352,7 +359,7 @@ reserve_memory (void)
         }
 #endif
 
-#ifdef CONFIG_CRASH_KERNEL
+#ifdef CONFIG_CRASH_DUMP
         if (reserve_elfcorehdr(&rsvd_region[n].start,
                                &rsvd_region[n].end) == 0)
                 n++;
@@ -554,8 +561,12 @@ setup_arch (char **cmdline_p)
 #ifdef CONFIG_ACPI
         /* Initialize the ACPI boot-time table parser */
         acpi_table_init();
+        early_acpi_boot_init();
 # ifdef CONFIG_ACPI_NUMA
         acpi_numa_init();
+#ifdef CONFIG_ACPI_HOTPLUG_CPU
+        prefill_possible_map();
+#endif
         per_cpu_scan_finalize((cpus_weight(early_cpu_possible_map) == 0 ?
                 32 : cpus_weight(early_cpu_possible_map)),
                 additional_cpus > 0 ? additional_cpus : 0);
@@ -846,19 +857,17 @@ void __init
 setup_per_cpu_areas (void)
 {
         /* start_kernel() requires this... */
-#ifdef CONFIG_ACPI_HOTPLUG_CPU
-        prefill_possible_map();
-#endif
 }
 
 /*
- * Calculate the max. cache line size.
+ * Do the following calculations:
  *
- * In addition, the minimum of the i-cache stride sizes is calculated for
- * "flush_icache_range()".
+ * 1. the max. cache line size.
+ * 2. the minimum of the i-cache stride sizes for "flush_icache_range()".
+ * 3. the minimum of the cache stride sizes for "clflush_cache_range()".
  */
 static void __cpuinit
-get_max_cacheline_size (void)
+get_cache_info(void)
 {
         unsigned long line_size, max = 1;
         u64 l, levels, unique_caches;
@@ -872,12 +881,14 @@ get_max_cacheline_size (void)
                 max = SMP_CACHE_BYTES;
                 /* Safest setup for "flush_icache_range()" */
                 ia64_i_cache_stride_shift = I_CACHE_STRIDE_SHIFT;
+                /* Safest setup for "clflush_cache_range()" */
+                ia64_cache_stride_shift = CACHE_STRIDE_SHIFT;
                 goto out;
         }
 
         for (l = 0; l < levels; ++l) {
-                status = ia64_pal_cache_config_info(l, /* cache_type (data_or_unified)= */ 2,
-                                                    &cci);
+                /* cache_type (data_or_unified)=2 */
+                status = ia64_pal_cache_config_info(l, 2, &cci);
                 if (status != 0) {
                         printk(KERN_ERR
                                "%s: ia64_pal_cache_config_info(l=%lu, 2) failed (status=%ld)\n",
@@ -885,15 +896,21 @@ get_max_cacheline_size (void)
                         max = SMP_CACHE_BYTES;
                         /* The safest setup for "flush_icache_range()" */
                         cci.pcci_stride = I_CACHE_STRIDE_SHIFT;
+                        /* The safest setup for "clflush_cache_range()" */
+                        ia64_cache_stride_shift = CACHE_STRIDE_SHIFT;
                         cci.pcci_unified = 1;
+                } else {
+                        if (cci.pcci_stride < ia64_cache_stride_shift)
+                                ia64_cache_stride_shift = cci.pcci_stride;
+
+                        line_size = 1 << cci.pcci_line_size;
+                        if (line_size > max)
+                                max = line_size;
                 }
-                line_size = 1 << cci.pcci_line_size;
-                if (line_size > max)
-                        max = line_size;
+
                 if (!cci.pcci_unified) {
-                        status = ia64_pal_cache_config_info(l,
-                                                    /* cache_type (instruction)= */ 1,
-                                                    &cci);
+                        /* cache_type (instruction)=1*/
+                        status = ia64_pal_cache_config_info(l, 1, &cci);
                         if (status != 0) {
                                 printk(KERN_ERR
                                 "%s: ia64_pal_cache_config_info(l=%lu, 1) failed (status=%ld)\n",
@@ -947,7 +964,7 @@ cpu_init (void)
         }
 #endif
 
-        get_max_cacheline_size();
+        get_cache_info();
 
         /*
          * We can't pass "local_cpu_data" to identify_cpu() because we haven't called
diff --git a/arch/ia64/kernel/signal.c b/arch/ia64/kernel/signal.c
index 19c5a78636fc..e12500a9c443 100644
--- a/arch/ia64/kernel/signal.c
+++ b/arch/ia64/kernel/signal.c
@@ -11,6 +11,7 @@
 #include <linux/kernel.h>
 #include <linux/mm.h>
 #include <linux/ptrace.h>
+#include <linux/tracehook.h>
 #include <linux/sched.h>
 #include <linux/signal.h>
 #include <linux/smp.h>
@@ -439,6 +440,13 @@ handle_signal (unsigned long sig, struct k_sigaction *ka, siginfo_t *info, sigse
                 sigaddset(&current->blocked, sig);
         recalc_sigpending();
         spin_unlock_irq(&current->sighand->siglock);
+
+        /*
+         * Let tracing know that we've done the handler setup.
+         */
+        tracehook_signal_handler(sig, info, ka, &scr->pt,
+                                 test_thread_flag(TIF_SINGLESTEP));
+
         return 1;
 }
 
diff --git a/arch/ia64/kernel/topology.c b/arch/ia64/kernel/topology.c
index 26228e2d01ae..c75b914f2d6b 100644
--- a/arch/ia64/kernel/topology.c
+++ b/arch/ia64/kernel/topology.c
@@ -53,10 +53,12 @@ int __ref arch_register_cpu(int num)
 }
 EXPORT_SYMBOL(arch_register_cpu);
 
-void arch_unregister_cpu(int num)
+void __ref arch_unregister_cpu(int num)
 {
         unregister_cpu(&sysfs_cpus[num].cpu);
+#ifdef CONFIG_ACPI
         unmap_cpu_from_node(num, cpu_to_node(num));
+#endif
 }
 EXPORT_SYMBOL(arch_unregister_cpu);
 #else