16 files changed, 183 insertions, 124 deletions

diff --git a/arch/x86/ia32/ia32entry.S b/arch/x86/ia32/ia32entry.S
index 59b4556a5b92..e790bc1fbfa3 100644
--- a/arch/x86/ia32/ia32entry.S
+++ b/arch/x86/ia32/ia32entry.S
@@ -626,7 +626,7 @@ ia32_sys_call_table:
         .quad stub32_sigreturn
         .quad stub32_clone              /* 120 */
         .quad sys_setdomainname
-        .quad sys_uname
+        .quad sys_newuname
         .quad sys_modify_ldt
         .quad compat_sys_adjtimex
         .quad sys32_mprotect            /* 125 */
diff --git a/arch/x86/include/asm/amd_iommu_types.h b/arch/x86/include/asm/amd_iommu_types.h
index ba19ad4c47d0..86a0ff0aeac7 100644
--- a/arch/x86/include/asm/amd_iommu_types.h
+++ b/arch/x86/include/asm/amd_iommu_types.h
@@ -21,6 +21,7 @@
 #define _ASM_X86_AMD_IOMMU_TYPES_H
 
 #include <linux/types.h>
+#include <linux/mutex.h>
 #include <linux/list.h>
 #include <linux/spinlock.h>
 
@@ -140,6 +141,7 @@
 
 /* constants to configure the command buffer */
 #define CMD_BUFFER_SIZE    8192
+#define CMD_BUFFER_UNINITIALIZED 1
 #define CMD_BUFFER_ENTRIES 512
 #define MMIO_CMD_SIZE_SHIFT 56
 #define MMIO_CMD_SIZE_512 (0x9ULL << MMIO_CMD_SIZE_SHIFT)
@@ -237,6 +239,7 @@ struct protection_domain {
         struct list_head list;  /* for list of all protection domains */
         struct list_head dev_list; /* List of all devices in this domain */
         spinlock_t lock;        /* mostly used to lock the page table*/
+        struct mutex api_lock;  /* protect page tables in the iommu-api path */
         u16 id;                 /* the domain id written to the device table */
         int mode;               /* paging mode (0-6 levels) */
         u64 *pt_root;           /* page table root pointer */
diff --git a/arch/x86/include/asm/lguest_hcall.h b/arch/x86/include/asm/lguest_hcall.h
index ba0eed8aa1a6..b60f2924c413 100644
--- a/arch/x86/include/asm/lguest_hcall.h
+++ b/arch/x86/include/asm/lguest_hcall.h
@@ -28,22 +28,39 @@
 
 #ifndef __ASSEMBLY__
 #include <asm/hw_irq.h>
-#include <asm/kvm_para.h>
 
 /*G:030
  * But first, how does our Guest contact the Host to ask for privileged
  * operations?  There are two ways: the direct way is to make a "hypercall",
  * to make requests of the Host Itself.
  *
- * We use the KVM hypercall mechanism, though completely different hypercall
- * numbers. Seventeen hypercalls are available: the hypercall number is put in
- * the %eax register, and the arguments (when required) are placed in %ebx,
- * %ecx, %edx and %esi.  If a return value makes sense, it's returned in %eax.
+ * Our hypercall mechanism uses the highest unused trap code (traps 32 and
+ * above are used by real hardware interrupts).  Seventeen hypercalls are
+ * available: the hypercall number is put in the %eax register, and the
+ * arguments (when required) are placed in %ebx, %ecx, %edx and %esi.
+ * If a return value makes sense, it's returned in %eax.
  *
  * Grossly invalid calls result in Sudden Death at the hands of the vengeful
  * Host, rather than returning failure.  This reflects Winston Churchill's
  * definition of a gentleman: "someone who is only rude intentionally".
-:*/
+ */
+static inline unsigned long
+hcall(unsigned long call,
+      unsigned long arg1, unsigned long arg2, unsigned long arg3,
+      unsigned long arg4)
+{
+        /* "int" is the Intel instruction to trigger a trap. */
+        asm volatile("int $" __stringify(LGUEST_TRAP_ENTRY)
+                     /* The call in %eax (aka "a") might be overwritten */
+                     : "=a"(call)
+                       /* The arguments are in %eax, %ebx, %ecx, %edx & %esi */
+                     : "a"(call), "b"(arg1), "c"(arg2), "d"(arg3), "S"(arg4)
+                       /* "memory" means this might write somewhere in memory.
+                        * This isn't true for all calls, but it's safe to tell
+                        * gcc that it might happen so it doesn't get clever. */
+                     : "memory");
+        return call;
+}
 
 /* Can't use our min() macro here: needs to be a constant */
 #define LGUEST_IRQS (NR_IRQS < 32 ? NR_IRQS: 32)
diff --git a/arch/x86/kernel/amd_iommu.c b/arch/x86/kernel/amd_iommu.c
index f3dadb571d9b..f854d89b7edf 100644
--- a/arch/x86/kernel/amd_iommu.c
+++ b/arch/x86/kernel/amd_iommu.c
@@ -118,7 +118,7 @@ static bool check_device(struct device *dev)
                 return false;
 
         /* No device or no PCI device */
-        if (!dev || dev->bus != &pci_bus_type)
+        if (dev->bus != &pci_bus_type)
                 return false;
 
         devid = get_device_id(dev);
@@ -392,6 +392,7 @@ static int __iommu_queue_command(struct amd_iommu *iommu, struct iommu_cmd *cmd)
         u32 tail, head;
         u8 *target;
 
+        WARN_ON(iommu->cmd_buf_size & CMD_BUFFER_UNINITIALIZED);
         tail = readl(iommu->mmio_base + MMIO_CMD_TAIL_OFFSET);
         target = iommu->cmd_buf + tail;
         memcpy_toio(target, cmd, sizeof(*cmd));
@@ -2186,7 +2187,7 @@ static void prealloc_protection_domains(void)
         struct dma_ops_domain *dma_dom;
         u16 devid;
 
-        while ((dev = pci_get_device(PCI_ANY_ID, PCI_ANY_ID, dev)) != NULL) {
+        for_each_pci_dev(dev) {
 
                 /* Do we handle this device? */
                 if (!check_device(&dev->dev))
@@ -2298,7 +2299,7 @@ static void cleanup_domain(struct protection_domain *domain)
         list_for_each_entry_safe(dev_data, next, &domain->dev_list, list) {
                 struct device *dev = dev_data->dev;
 
-                do_detach(dev);
+                __detach_device(dev);
                 atomic_set(&dev_data->bind, 0);
         }
 
@@ -2327,6 +2328,7 @@ static struct protection_domain *protection_domain_alloc(void)
                 return NULL;
 
         spin_lock_init(&domain->lock);
+        mutex_init(&domain->api_lock);
         domain->id = domain_id_alloc();
         if (!domain->id)
                 goto out_err;
@@ -2379,9 +2381,7 @@ static void amd_iommu_domain_destroy(struct iommu_domain *dom)
 
         free_pagetable(domain);
 
-        domain_id_free(domain->id);
-
-        kfree(domain);
+        protection_domain_free(domain);
 
         dom->priv = NULL;
 }
@@ -2456,6 +2456,8 @@ static int amd_iommu_map_range(struct iommu_domain *dom,
         iova  &= PAGE_MASK;
         paddr &= PAGE_MASK;
 
+        mutex_lock(&domain->api_lock);
+
         for (i = 0; i < npages; ++i) {
                 ret = iommu_map_page(domain, iova, paddr, prot, PM_MAP_4k);
                 if (ret)
@@ -2465,6 +2467,8 @@ static int amd_iommu_map_range(struct iommu_domain *dom,
                 paddr += PAGE_SIZE;
         }
 
+        mutex_unlock(&domain->api_lock);
+
         return 0;
 }
 
@@ -2477,12 +2481,16 @@ static void amd_iommu_unmap_range(struct iommu_domain *dom,
 
         iova  &= PAGE_MASK;
 
+        mutex_lock(&domain->api_lock);
+
         for (i = 0; i < npages; ++i) {
                 iommu_unmap_page(domain, iova, PM_MAP_4k);
                 iova  += PAGE_SIZE;
         }
 
         iommu_flush_tlb_pde(domain);
+
+        mutex_unlock(&domain->api_lock);
 }
 
 static phys_addr_t amd_iommu_iova_to_phys(struct iommu_domain *dom,
diff --git a/arch/x86/kernel/amd_iommu_init.c b/arch/x86/kernel/amd_iommu_init.c
index 42f5350b908f..6360abf993d4 100644
--- a/arch/x86/kernel/amd_iommu_init.c
+++ b/arch/x86/kernel/amd_iommu_init.c
@@ -138,9 +138,9 @@ int amd_iommus_present;
 bool amd_iommu_np_cache __read_mostly;
 
 /*
- * Set to true if ACPI table parsing and hardware intialization went properly
+ * The ACPI table parsing functions set this variable on an error
  */
-static bool amd_iommu_initialized;
+static int __initdata amd_iommu_init_err;
 
 /*
  * List of protection domains - used during resume
@@ -391,9 +391,11 @@ static int __init find_last_devid_acpi(struct acpi_table_header *table)
          */
         for (i = 0; i < table->length; ++i)
                 checksum += p[i];
-        if (checksum != 0)
+        if (checksum != 0) {
                 /* ACPI table corrupt */
-                return -ENODEV;
+                amd_iommu_init_err = -ENODEV;
+                return 0;
+        }
 
         p += IVRS_HEADER_LENGTH;
 
@@ -436,7 +438,7 @@ static u8 * __init alloc_command_buffer(struct amd_iommu *iommu)
         if (cmd_buf == NULL)
                 return NULL;
 
-        iommu->cmd_buf_size = CMD_BUFFER_SIZE;
+        iommu->cmd_buf_size = CMD_BUFFER_SIZE | CMD_BUFFER_UNINITIALIZED;
 
         return cmd_buf;
 }
@@ -472,12 +474,13 @@ static void iommu_enable_command_buffer(struct amd_iommu *iommu)
                     &entry, sizeof(entry));
 
         amd_iommu_reset_cmd_buffer(iommu);
+        iommu->cmd_buf_size &= ~(CMD_BUFFER_UNINITIALIZED);
 }
 
 static void __init free_command_buffer(struct amd_iommu *iommu)
 {
         free_pages((unsigned long)iommu->cmd_buf,
-                   get_order(iommu->cmd_buf_size));
+                   get_order(iommu->cmd_buf_size & ~(CMD_BUFFER_UNINITIALIZED)));
 }
 
 /* allocates the memory where the IOMMU will log its events to */
@@ -920,11 +923,16 @@ static int __init init_iommu_all(struct acpi_table_header *table)
                                     h->mmio_phys);
 
                         iommu = kzalloc(sizeof(struct amd_iommu), GFP_KERNEL);
-                        if (iommu == NULL)
-                                return -ENOMEM;
+                        if (iommu == NULL) {
+                                amd_iommu_init_err = -ENOMEM;
+                                return 0;
+                        }
+
                         ret = init_iommu_one(iommu, h);
-                        if (ret)
-                                return ret;
+                        if (ret) {
+                                amd_iommu_init_err = ret;
+                                return 0;
+                        }
                         break;
                 default:
                         break;
@@ -934,8 +942,6 @@ static int __init init_iommu_all(struct acpi_table_header *table)
         }
         WARN_ON(p != end);
 
-        amd_iommu_initialized = true;
-
         return 0;
 }
 
@@ -1211,6 +1217,10 @@ static int __init amd_iommu_init(void)
         if (acpi_table_parse("IVRS", find_last_devid_acpi) != 0)
                 return -ENODEV;
 
+        ret = amd_iommu_init_err;
+        if (ret)
+                goto out;
+
         dev_table_size     = tbl_size(DEV_TABLE_ENTRY_SIZE);
         alias_table_size   = tbl_size(ALIAS_TABLE_ENTRY_SIZE);
         rlookup_table_size = tbl_size(RLOOKUP_TABLE_ENTRY_SIZE);
@@ -1270,12 +1280,19 @@ static int __init amd_iommu_init(void)
         if (acpi_table_parse("IVRS", init_iommu_all) != 0)
                 goto free;
 
-        if (!amd_iommu_initialized)
+        if (amd_iommu_init_err) {
+                ret = amd_iommu_init_err;
                 goto free;
+        }
 
         if (acpi_table_parse("IVRS", init_memory_definitions) != 0)
                 goto free;
 
+        if (amd_iommu_init_err) {
+                ret = amd_iommu_init_err;
+                goto free;
+        }
+
         ret = sysdev_class_register(&amd_iommu_sysdev_class);
         if (ret)
                 goto free;
@@ -1288,6 +1305,8 @@ static int __init amd_iommu_init(void)
         if (ret)
                 goto free;
 
+        enable_iommus();
+
         if (iommu_pass_through)
                 ret = amd_iommu_init_passthrough();
         else
@@ -1300,8 +1319,6 @@ static int __init amd_iommu_init(void)
 
         amd_iommu_init_notifier();
 
-        enable_iommus();
-
         if (iommu_pass_through)
                 goto out;
 
@@ -1315,6 +1332,7 @@ out:
         return ret;
 
 free:
+        disable_iommus();
 
         amd_iommu_uninit_devices();
 
diff --git a/arch/x86/kernel/aperture_64.c b/arch/x86/kernel/aperture_64.c
index 3704997e8b25..b5d8b0bcf235 100644
--- a/arch/x86/kernel/aperture_64.c
+++ b/arch/x86/kernel/aperture_64.c
@@ -393,6 +393,7 @@ void __init gart_iommu_hole_init(void)
         for (i = 0; i < ARRAY_SIZE(bus_dev_ranges); i++) {
                 int bus;
                 int dev_base, dev_limit;
+                u32 ctl;
 
                 bus = bus_dev_ranges[i].bus;
                 dev_base = bus_dev_ranges[i].dev_base;
@@ -406,7 +407,19 @@ void __init gart_iommu_hole_init(void)
                         gart_iommu_aperture = 1;
                         x86_init.iommu.iommu_init = gart_iommu_init;
 
-                        aper_order = (read_pci_config(bus, slot, 3, AMD64_GARTAPERTURECTL) >> 1) & 7;
+                        ctl = read_pci_config(bus, slot, 3,
+                                              AMD64_GARTAPERTURECTL);
+
+                        /*
+                         * Before we do anything else disable the GART. It may
+                         * still be enabled if we boot into a crash-kernel here.
+                         * Reconfiguring the GART while it is enabled could have
+                         * unknown side-effects.
+                         */
+                        ctl &= ~GARTEN;
+                        write_pci_config(bus, slot, 3, AMD64_GARTAPERTURECTL, ctl);
+
+                        aper_order = (ctl >> 1) & 7;
                         aper_size = (32 * 1024 * 1024) << aper_order;
                         aper_base = read_pci_config(bus, slot, 3, AMD64_GARTAPERTUREBASE) & 0x7fff;
                         aper_base <<= 25;
diff --git a/arch/x86/kernel/cpu/vmware.c b/arch/x86/kernel/cpu/vmware.c
index 1cbed97b59cf..dfdb4dba2320 100644
--- a/arch/x86/kernel/cpu/vmware.c
+++ b/arch/x86/kernel/cpu/vmware.c
@@ -22,6 +22,7 @@
  */
 
 #include <linux/dmi.h>
+#include <linux/module.h>
 #include <asm/div64.h>
 #include <asm/vmware.h>
 #include <asm/x86_init.h>
@@ -101,6 +102,7 @@ int vmware_platform(void)
 
         return 0;
 }
+EXPORT_SYMBOL(vmware_platform);
 
 /*
  * VMware hypervisor takes care of exporting a reliable TSC to the guest.
diff --git a/arch/x86/kernel/crash.c b/arch/x86/kernel/crash.c
index a4849c10a77e..ebd4c51d096a 100644
--- a/arch/x86/kernel/crash.c
+++ b/arch/x86/kernel/crash.c
@@ -27,7 +27,6 @@
 #include <asm/cpu.h>
 #include <asm/reboot.h>
 #include <asm/virtext.h>
-#include <asm/x86_init.h>
 
 #if defined(CONFIG_SMP) && defined(CONFIG_X86_LOCAL_APIC)
 
@@ -103,10 +102,5 @@ void native_machine_crash_shutdown(struct pt_regs *regs)
 #ifdef CONFIG_HPET_TIMER
         hpet_disable();
 #endif
-
-#ifdef CONFIG_X86_64
-        x86_platform.iommu_shutdown();
-#endif
-
         crash_save_cpu(regs, safe_smp_processor_id());
 }
diff --git a/arch/x86/kernel/dumpstack.h b/arch/x86/kernel/dumpstack.h
index e39e77168a37..e1a93be4fd44 100644
--- a/arch/x86/kernel/dumpstack.h
+++ b/arch/x86/kernel/dumpstack.h
@@ -14,6 +14,8 @@
 #define get_bp(bp) asm("movq %%rbp, %0" : "=r" (bp) :)
 #endif
 
+#include <linux/uaccess.h>
+
 extern void
 show_trace_log_lvl(struct task_struct *task, struct pt_regs *regs,
                 unsigned long *stack, unsigned long bp, char *log_lvl);
@@ -42,8 +44,10 @@ static inline unsigned long rewind_frame_pointer(int n)
         get_bp(frame);
 
 #ifdef CONFIG_FRAME_POINTER
-        while (n--)
-                frame = frame->next_frame;
+        while (n--) {
+                if (probe_kernel_address(&frame->next_frame, frame))
+                        break;
+        }
 #endif
 
         return (unsigned long)frame;
diff --git a/arch/x86/kernel/pci-gart_64.c b/arch/x86/kernel/pci-gart_64.c
index 68cd24f9deae..0f7f130caa67 100644
--- a/arch/x86/kernel/pci-gart_64.c
+++ b/arch/x86/kernel/pci-gart_64.c
@@ -565,6 +565,9 @@ static void enable_gart_translations(void)
 
                 enable_gart_translation(dev, __pa(agp_gatt_table));
         }
+
+        /* Flush the GART-TLB to remove stale entries */
+        k8_flush_garts();
 }
 
 /*
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index 48aeee8eefb0..19a8906bcaa2 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -1490,8 +1490,8 @@ static int mmu_zap_unsync_children(struct kvm *kvm,
                 for_each_sp(pages, sp, parents, i) {
                         kvm_mmu_zap_page(kvm, sp);
                         mmu_pages_clear_parents(&parents);
+                        zapped++;
                 }
-                zapped += pages.nr;
                 kvm_mmu_pages_init(parent, &parents, &pages);
         }
 
@@ -1542,14 +1542,16 @@ void kvm_mmu_change_mmu_pages(struct kvm *kvm, unsigned int kvm_nr_mmu_pages)
          */
 
         if (used_pages > kvm_nr_mmu_pages) {
-                while (used_pages > kvm_nr_mmu_pages) {
+                while (used_pages > kvm_nr_mmu_pages &&
+                        !list_empty(&kvm->arch.active_mmu_pages)) {
                         struct kvm_mmu_page *page;
 
                         page = container_of(kvm->arch.active_mmu_pages.prev,
                                             struct kvm_mmu_page, link);
-                        kvm_mmu_zap_page(kvm, page);
+                        used_pages -= kvm_mmu_zap_page(kvm, page);
                         used_pages--;
                 }
+                kvm_nr_mmu_pages = used_pages;
                 kvm->arch.n_free_mmu_pages = 0;
         }
         else
@@ -1596,7 +1598,8 @@ static void mmu_unshadow(struct kvm *kvm, gfn_t gfn)
                     && !sp->role.invalid) {
                         pgprintk("%s: zap %lx %x\n",
                                  __func__, gfn, sp->role.word);
-                        kvm_mmu_zap_page(kvm, sp);
+                        if (kvm_mmu_zap_page(kvm, sp))
+                                nn = bucket->first;
                 }
         }
 }
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index 445c59411ed0..2ba58206812a 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -706,29 +706,28 @@ static struct kvm_vcpu *svm_create_vcpu(struct kvm *kvm, unsigned int id)
         if (err)
                 goto free_svm;
 
+        err = -ENOMEM;
         page = alloc_page(GFP_KERNEL);
-        if (!page) {
-                err = -ENOMEM;
+        if (!page)
                 goto uninit;
-        }
 
-        err = -ENOMEM;
         msrpm_pages = alloc_pages(GFP_KERNEL, MSRPM_ALLOC_ORDER);
         if (!msrpm_pages)
-                goto uninit;
+                goto free_page1;
 
         nested_msrpm_pages = alloc_pages(GFP_KERNEL, MSRPM_ALLOC_ORDER);
         if (!nested_msrpm_pages)
-                goto uninit;
-
-        svm->msrpm = page_address(msrpm_pages);
-        svm_vcpu_init_msrpm(svm->msrpm);
+                goto free_page2;
 
         hsave_page = alloc_page(GFP_KERNEL);
         if (!hsave_page)
-                goto uninit;
+                goto free_page3;
+
         svm->nested.hsave = page_address(hsave_page);
 
+        svm->msrpm = page_address(msrpm_pages);
+        svm_vcpu_init_msrpm(svm->msrpm);
+
         svm->nested.msrpm = page_address(nested_msrpm_pages);
 
         svm->vmcb = page_address(page);
@@ -744,6 +743,12 @@ static struct kvm_vcpu *svm_create_vcpu(struct kvm *kvm, unsigned int id)
 
         return &svm->vcpu;
 
+free_page3:
+        __free_pages(nested_msrpm_pages, MSRPM_ALLOC_ORDER);
+free_page2:
+        __free_pages(msrpm_pages, MSRPM_ALLOC_ORDER);
+free_page1:
+        __free_page(page);
 uninit:
         kvm_vcpu_uninit(&svm->vcpu);
 free_svm:
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 686492ed3079..bc933cfb4e66 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -77,6 +77,8 @@ module_param(emulate_invalid_guest_state, bool, S_IRUGO);
 #define KVM_PMODE_VM_CR4_ALWAYS_ON (X86_CR4_PAE | X86_CR4_VMXE)
 #define KVM_RMODE_VM_CR4_ALWAYS_ON (X86_CR4_VME | X86_CR4_PAE | X86_CR4_VMXE)
 
+#define RMODE_GUEST_OWNED_EFLAGS_BITS (~(X86_EFLAGS_IOPL | X86_EFLAGS_VM))
+
 /*
  * These 2 parameters are used to config the controls for Pause-Loop Exiting:
  * ple_gap:    upper bound on the amount of time between two successive
@@ -131,7 +133,7 @@ struct vcpu_vmx {
         } host_state;
         struct {
                 int vm86_active;
-                u8 save_iopl;
+                ulong save_rflags;
                 struct kvm_save_segment {
                         u16 selector;
                         unsigned long base;
@@ -818,18 +820,23 @@ static void vmx_fpu_deactivate(struct kvm_vcpu *vcpu)
 
 static unsigned long vmx_get_rflags(struct kvm_vcpu *vcpu)
 {
-        unsigned long rflags;
+        unsigned long rflags, save_rflags;
 
         rflags = vmcs_readl(GUEST_RFLAGS);
-        if (to_vmx(vcpu)->rmode.vm86_active)
-                rflags &= ~(unsigned long)(X86_EFLAGS_IOPL | X86_EFLAGS_VM);
+        if (to_vmx(vcpu)->rmode.vm86_active) {
+                rflags &= RMODE_GUEST_OWNED_EFLAGS_BITS;
+                save_rflags = to_vmx(vcpu)->rmode.save_rflags;
+                rflags |= save_rflags & ~RMODE_GUEST_OWNED_EFLAGS_BITS;
+        }
         return rflags;
 }
 
 static void vmx_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags)
 {
-        if (to_vmx(vcpu)->rmode.vm86_active)
+        if (to_vmx(vcpu)->rmode.vm86_active) {
+                to_vmx(vcpu)->rmode.save_rflags = rflags;
                 rflags |= X86_EFLAGS_IOPL | X86_EFLAGS_VM;
+        }
         vmcs_writel(GUEST_RFLAGS, rflags);
 }
 
@@ -1483,8 +1490,8 @@ static void enter_pmode(struct kvm_vcpu *vcpu)
         vmcs_write32(GUEST_TR_AR_BYTES, vmx->rmode.tr.ar);
 
         flags = vmcs_readl(GUEST_RFLAGS);
-        flags &= ~(X86_EFLAGS_IOPL | X86_EFLAGS_VM);
-        flags |= (vmx->rmode.save_iopl << IOPL_SHIFT);
+        flags &= RMODE_GUEST_OWNED_EFLAGS_BITS;
+        flags |= vmx->rmode.save_rflags & ~RMODE_GUEST_OWNED_EFLAGS_BITS;
         vmcs_writel(GUEST_RFLAGS, flags);
 
         vmcs_writel(GUEST_CR4, (vmcs_readl(GUEST_CR4) & ~X86_CR4_VME) |
@@ -1557,8 +1564,7 @@ static void enter_rmode(struct kvm_vcpu *vcpu)
         vmcs_write32(GUEST_TR_AR_BYTES, 0x008b);
 
         flags = vmcs_readl(GUEST_RFLAGS);
-        vmx->rmode.save_iopl
-                = (flags & X86_EFLAGS_IOPL) >> IOPL_SHIFT;
+        vmx->rmode.save_rflags = flags;
 
         flags |= X86_EFLAGS_IOPL | X86_EFLAGS_VM;
 
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 24cd0ee896e9..3c4ca98ad27f 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -433,8 +433,6 @@ void kvm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0)
 
 #ifdef CONFIG_X86_64
         if (cr0 & 0xffffffff00000000UL) {
-                printk(KERN_DEBUG "set_cr0: 0x%lx #GP, reserved bits 0x%lx\n",
-                       cr0, kvm_read_cr0(vcpu));
                 kvm_inject_gp(vcpu, 0);
                 return;
         }
@@ -443,14 +441,11 @@ void kvm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0)
         cr0 &= ~CR0_RESERVED_BITS;
 
         if ((cr0 & X86_CR0_NW) && !(cr0 & X86_CR0_CD)) {
-                printk(KERN_DEBUG "set_cr0: #GP, CD == 0 && NW == 1\n");
                 kvm_inject_gp(vcpu, 0);
                 return;
         }
 
         if ((cr0 & X86_CR0_PG) && !(cr0 & X86_CR0_PE)) {
-                printk(KERN_DEBUG "set_cr0: #GP, set PG flag "
-                       "and a clear PE flag\n");
                 kvm_inject_gp(vcpu, 0);
                 return;
         }
@@ -461,15 +456,11 @@ void kvm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0)
                         int cs_db, cs_l;
 
                         if (!is_pae(vcpu)) {
-                                printk(KERN_DEBUG "set_cr0: #GP, start paging "
-                                       "in long mode while PAE is disabled\n");
                                 kvm_inject_gp(vcpu, 0);
                                 return;
                         }
                         kvm_x86_ops->get_cs_db_l_bits(vcpu, &cs_db, &cs_l);
                         if (cs_l) {
-                                printk(KERN_DEBUG "set_cr0: #GP, start paging "
-                                       "in long mode while CS.L == 1\n");
                                 kvm_inject_gp(vcpu, 0);
                                 return;
 
@@ -477,8 +468,6 @@ void kvm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0)
                 } else
 #endif
                 if (is_pae(vcpu) && !load_pdptrs(vcpu, vcpu->arch.cr3)) {
-                        printk(KERN_DEBUG "set_cr0: #GP, pdptrs "
-                               "reserved bits\n");
                         kvm_inject_gp(vcpu, 0);
                         return;
                 }
@@ -505,28 +494,23 @@ void kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
         unsigned long pdptr_bits = X86_CR4_PGE | X86_CR4_PSE | X86_CR4_PAE;
 
         if (cr4 & CR4_RESERVED_BITS) {
-                printk(KERN_DEBUG "set_cr4: #GP, reserved bits\n");
                 kvm_inject_gp(vcpu, 0);
                 return;
         }
 
         if (is_long_mode(vcpu)) {
                 if (!(cr4 & X86_CR4_PAE)) {
-                        printk(KERN_DEBUG "set_cr4: #GP, clearing PAE while "
-                               "in long mode\n");
                         kvm_inject_gp(vcpu, 0);
                         return;
                 }
         } else if (is_paging(vcpu) && (cr4 & X86_CR4_PAE)
                    && ((cr4 ^ old_cr4) & pdptr_bits)
                    && !load_pdptrs(vcpu, vcpu->arch.cr3)) {
-                printk(KERN_DEBUG "set_cr4: #GP, pdptrs reserved bits\n");
                 kvm_inject_gp(vcpu, 0);
                 return;
         }
 
         if (cr4 & X86_CR4_VMXE) {
-                printk(KERN_DEBUG "set_cr4: #GP, setting VMXE\n");
                 kvm_inject_gp(vcpu, 0);
                 return;
         }
@@ -547,21 +531,16 @@ void kvm_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3)
 
         if (is_long_mode(vcpu)) {
                 if (cr3 & CR3_L_MODE_RESERVED_BITS) {
-                        printk(KERN_DEBUG "set_cr3: #GP, reserved bits\n");
                         kvm_inject_gp(vcpu, 0);
                         return;
                 }
         } else {
                 if (is_pae(vcpu)) {
                         if (cr3 & CR3_PAE_RESERVED_BITS) {
-                                printk(KERN_DEBUG
-                                       "set_cr3: #GP, reserved bits\n");
                                 kvm_inject_gp(vcpu, 0);
                                 return;
                         }
                         if (is_paging(vcpu) && !load_pdptrs(vcpu, cr3)) {
-                                printk(KERN_DEBUG "set_cr3: #GP, pdptrs "
-                                       "reserved bits\n");
                                 kvm_inject_gp(vcpu, 0);
                                 return;
                         }
@@ -593,7 +572,6 @@ EXPORT_SYMBOL_GPL(kvm_set_cr3);
 void kvm_set_cr8(struct kvm_vcpu *vcpu, unsigned long cr8)
 {
         if (cr8 & CR8_RESERVED_BITS) {
-                printk(KERN_DEBUG "set_cr8: #GP, reserved bits 0x%lx\n", cr8);
                 kvm_inject_gp(vcpu, 0);
                 return;
         }
@@ -649,15 +627,12 @@ static u32 emulated_msrs[] = {
 static void set_efer(struct kvm_vcpu *vcpu, u64 efer)
 {
         if (efer & efer_reserved_bits) {
-                printk(KERN_DEBUG "set_efer: 0x%llx #GP, reserved bits\n",
-                       efer);
                 kvm_inject_gp(vcpu, 0);
                 return;
         }
 
         if (is_paging(vcpu)
             && (vcpu->arch.efer & EFER_LME) != (efer & EFER_LME)) {
-                printk(KERN_DEBUG "set_efer: #GP, change LME while paging\n");
                 kvm_inject_gp(vcpu, 0);
                 return;
         }
@@ -667,7 +642,6 @@ static void set_efer(struct kvm_vcpu *vcpu, u64 efer)
 
                 feat = kvm_find_cpuid_entry(vcpu, 0x80000001, 0);
                 if (!feat || !(feat->edx & bit(X86_FEATURE_FXSR_OPT))) {
-                        printk(KERN_DEBUG "set_efer: #GP, enable FFXSR w/o CPUID capability\n");
                         kvm_inject_gp(vcpu, 0);
                         return;
                 }
@@ -678,7 +652,6 @@ static void set_efer(struct kvm_vcpu *vcpu, u64 efer)
 
                 feat = kvm_find_cpuid_entry(vcpu, 0x80000001, 0);
                 if (!feat || !(feat->ecx & bit(X86_FEATURE_SVM))) {
-                        printk(KERN_DEBUG "set_efer: #GP, enable SVM w/o SVM\n");
                         kvm_inject_gp(vcpu, 0);
                         return;
                 }
@@ -967,9 +940,13 @@ static int set_msr_mce(struct kvm_vcpu *vcpu, u32 msr, u64 data)
                 if (msr >= MSR_IA32_MC0_CTL &&
                     msr < MSR_IA32_MC0_CTL + 4 * bank_num) {
                         u32 offset = msr - MSR_IA32_MC0_CTL;
-                        /* only 0 or all 1s can be written to IA32_MCi_CTL */
+                        /* only 0 or all 1s can be written to IA32_MCi_CTL
+                         * some Linux kernels though clear bit 10 in bank 4 to
+                         * workaround a BIOS/GART TBL issue on AMD K8s, ignore
+                         * this to avoid an uncatched #GP in the guest
+                         */
                         if ((offset & 0x3) == 0 &&
-                            data != 0 && data != ~(u64)0)
+                            data != 0 && (data | (1 << 10)) != ~(u64)0)
                                 return -1;
                         vcpu->arch.mce_banks[offset] = data;
                         break;
@@ -2635,8 +2612,9 @@ static int kvm_vm_ioctl_reinject(struct kvm *kvm,
 int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm,
                                       struct kvm_dirty_log *log)
 {
-        int r, n, i;
+        int r, i;
         struct kvm_memory_slot *memslot;
+        unsigned long n;
         unsigned long is_dirty = 0;
         unsigned long *dirty_bitmap = NULL;
 
@@ -2651,7 +2629,7 @@ int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm,
         if (!memslot->dirty_bitmap)
                 goto out;
 
-        n = ALIGN(memslot->npages, BITS_PER_LONG) / 8;
+        n = kvm_dirty_bitmap_bytes(memslot);
 
         r = -ENOMEM;
         dirty_bitmap = vmalloc(n);
@@ -4483,7 +4461,9 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
                 kvm_set_cr8(vcpu, kvm_run->cr8);
 
         if (vcpu->arch.pio.cur_count) {
+                vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu);
                 r = complete_pio(vcpu);
+                srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx);
                 if (r)
                         goto out;
         }
@@ -5146,6 +5126,7 @@ int kvm_task_switch(struct kvm_vcpu *vcpu, u16 tss_selector, int reason)
         int ret = 0;
         u32 old_tss_base = get_segment_base(vcpu, VCPU_SREG_TR);
         u16 old_tss_sel = get_segment_selector(vcpu, VCPU_SREG_TR);
+        u32 desc_limit;
 
         old_tss_base = kvm_mmu_gva_to_gpa_write(vcpu, old_tss_base, NULL);
 
@@ -5168,7 +5149,10 @@ int kvm_task_switch(struct kvm_vcpu *vcpu, u16 tss_selector, int reason)
                 }
         }
 
-        if (!nseg_desc.p || get_desc_limit(&nseg_desc) < 0x67) {
+        desc_limit = get_desc_limit(&nseg_desc);
+        if (!nseg_desc.p ||
+            ((desc_limit < 0x67 && (nseg_desc.type & 8)) ||
+             desc_limit < 0x2b)) {
                 kvm_queue_exception_e(vcpu, TS_VECTOR, tss_selector & 0xfffc);
                 return 1;
         }
diff --git a/arch/x86/lguest/boot.c b/arch/x86/lguest/boot.c
index 7e59dc1d3fc2..2bdf628066bd 100644
--- a/arch/x86/lguest/boot.c
+++ b/arch/x86/lguest/boot.c
@@ -115,7 +115,7 @@ static void async_hcall(unsigned long call, unsigned long arg1,
         local_irq_save(flags);
         if (lguest_data.hcall_status[next_call] != 0xFF) {
                 /* Table full, so do normal hcall which will flush table. */
-                kvm_hypercall4(call, arg1, arg2, arg3, arg4);
+                hcall(call, arg1, arg2, arg3, arg4);
         } else {
                 lguest_data.hcalls[next_call].arg0 = call;
                 lguest_data.hcalls[next_call].arg1 = arg1;
@@ -145,46 +145,45 @@ static void async_hcall(unsigned long call, unsigned long arg1,
  * So, when we're in lazy mode, we call async_hcall() to store the call for
  * future processing:
  */
-static void lazy_hcall1(unsigned long call,
-                       unsigned long arg1)
+static void lazy_hcall1(unsigned long call, unsigned long arg1)
 {
         if (paravirt_get_lazy_mode() == PARAVIRT_LAZY_NONE)
-                kvm_hypercall1(call, arg1);
+                hcall(call, arg1, 0, 0, 0);
         else
                 async_hcall(call, arg1, 0, 0, 0);
 }
 
 /* You can imagine what lazy_hcall2, 3 and 4 look like. :*/
 static void lazy_hcall2(unsigned long call,
-                       unsigned long arg1,
-                       unsigned long arg2)
+                        unsigned long arg1,
+                        unsigned long arg2)
 {
         if (paravirt_get_lazy_mode() == PARAVIRT_LAZY_NONE)
-                kvm_hypercall2(call, arg1, arg2);
+                hcall(call, arg1, arg2, 0, 0);
         else
                 async_hcall(call, arg1, arg2, 0, 0);
 }
 
 static void lazy_hcall3(unsigned long call,
-                       unsigned long arg1,
-                       unsigned long arg2,
-                       unsigned long arg3)
+                        unsigned long arg1,
+                        unsigned long arg2,
+                        unsigned long arg3)
 {
         if (paravirt_get_lazy_mode() == PARAVIRT_LAZY_NONE)
-                kvm_hypercall3(call, arg1, arg2, arg3);
+                hcall(call, arg1, arg2, arg3, 0);
         else
                 async_hcall(call, arg1, arg2, arg3, 0);
 }
 
 #ifdef CONFIG_X86_PAE
 static void lazy_hcall4(unsigned long call,
-                       unsigned long arg1,
-                       unsigned long arg2,
-                       unsigned long arg3,
-                       unsigned long arg4)
+                        unsigned long arg1,
+                        unsigned long arg2,
+                        unsigned long arg3,
+                        unsigned long arg4)
 {
         if (paravirt_get_lazy_mode() == PARAVIRT_LAZY_NONE)
-                kvm_hypercall4(call, arg1, arg2, arg3, arg4);
+                hcall(call, arg1, arg2, arg3, arg4);
         else
                 async_hcall(call, arg1, arg2, arg3, arg4);
 }
@@ -196,13 +195,13 @@ static void lazy_hcall4(unsigned long call,
 :*/
 static void lguest_leave_lazy_mmu_mode(void)
 {
-        kvm_hypercall0(LHCALL_FLUSH_ASYNC);
+        hcall(LHCALL_FLUSH_ASYNC, 0, 0, 0, 0);
         paravirt_leave_lazy_mmu();
 }
 
 static void lguest_end_context_switch(struct task_struct *next)
 {
-        kvm_hypercall0(LHCALL_FLUSH_ASYNC);
+        hcall(LHCALL_FLUSH_ASYNC, 0, 0, 0, 0);
         paravirt_end_context_switch(next);
 }
 
@@ -286,7 +285,7 @@ static void lguest_write_idt_entry(gate_desc *dt,
         /* Keep the local copy up to date. */
         native_write_idt_entry(dt, entrynum, g);
         /* Tell Host about this new entry. */
-        kvm_hypercall3(LHCALL_LOAD_IDT_ENTRY, entrynum, desc[0], desc[1]);
+        hcall(LHCALL_LOAD_IDT_ENTRY, entrynum, desc[0], desc[1], 0);
 }
 
 /*
@@ -300,7 +299,7 @@ static void lguest_load_idt(const struct desc_ptr *desc)
         struct desc_struct *idt = (void *)desc->address;
 
         for (i = 0; i < (desc->size+1)/8; i++)
-                kvm_hypercall3(LHCALL_LOAD_IDT_ENTRY, i, idt[i].a, idt[i].b);
+                hcall(LHCALL_LOAD_IDT_ENTRY, i, idt[i].a, idt[i].b, 0);
 }
 
 /*
@@ -321,7 +320,7 @@ static void lguest_load_gdt(const struct desc_ptr *desc)
         struct desc_struct *gdt = (void *)desc->address;
 
         for (i = 0; i < (desc->size+1)/8; i++)
-                kvm_hypercall3(LHCALL_LOAD_GDT_ENTRY, i, gdt[i].a, gdt[i].b);
+                hcall(LHCALL_LOAD_GDT_ENTRY, i, gdt[i].a, gdt[i].b, 0);
 }
 
 /*
@@ -334,8 +333,8 @@ static void lguest_write_gdt_entry(struct desc_struct *dt, int entrynum,
 {
         native_write_gdt_entry(dt, entrynum, desc, type);
         /* Tell Host about this new entry. */
-        kvm_hypercall3(LHCALL_LOAD_GDT_ENTRY, entrynum,
-                       dt[entrynum].a, dt[entrynum].b);
+        hcall(LHCALL_LOAD_GDT_ENTRY, entrynum,
+              dt[entrynum].a, dt[entrynum].b, 0);
 }
 
 /*
@@ -931,7 +930,7 @@ static int lguest_clockevent_set_next_event(unsigned long delta,
         }
 
         /* Please wake us this far in the future. */
-        kvm_hypercall1(LHCALL_SET_CLOCKEVENT, delta);
+        hcall(LHCALL_SET_CLOCKEVENT, delta, 0, 0, 0);
         return 0;
 }
 
@@ -942,7 +941,7 @@ static void lguest_clockevent_set_mode(enum clock_event_mode mode,
         case CLOCK_EVT_MODE_UNUSED:
         case CLOCK_EVT_MODE_SHUTDOWN:
                 /* A 0 argument shuts the clock down. */
-                kvm_hypercall0(LHCALL_SET_CLOCKEVENT);
+                hcall(LHCALL_SET_CLOCKEVENT, 0, 0, 0, 0);
                 break;
         case CLOCK_EVT_MODE_ONESHOT:
                 /* This is what we expect. */
@@ -1100,7 +1099,7 @@ static void set_lguest_basic_apic_ops(void)
 /* STOP!  Until an interrupt comes in. */
 static void lguest_safe_halt(void)
 {
-        kvm_hypercall0(LHCALL_HALT);
+        hcall(LHCALL_HALT, 0, 0, 0, 0);
 }
 
 /*
@@ -1112,8 +1111,8 @@ static void lguest_safe_halt(void)
  */
 static void lguest_power_off(void)
 {
-        kvm_hypercall2(LHCALL_SHUTDOWN, __pa("Power down"),
-                                        LGUEST_SHUTDOWN_POWEROFF);
+        hcall(LHCALL_SHUTDOWN, __pa("Power down"),
+              LGUEST_SHUTDOWN_POWEROFF, 0, 0);
 }
 
 /*
@@ -1123,7 +1122,7 @@ static void lguest_power_off(void)
  */
 static int lguest_panic(struct notifier_block *nb, unsigned long l, void *p)
 {
-        kvm_hypercall2(LHCALL_SHUTDOWN, __pa(p), LGUEST_SHUTDOWN_POWEROFF);
+        hcall(LHCALL_SHUTDOWN, __pa(p), LGUEST_SHUTDOWN_POWEROFF, 0, 0);
         /* The hcall won't return, but to keep gcc happy, we're "done". */
         return NOTIFY_DONE;
 }
@@ -1162,7 +1161,7 @@ static __init int early_put_chars(u32 vtermno, const char *buf, int count)
                 len = sizeof(scratch) - 1;
         scratch[len] = '\0';
         memcpy(scratch, buf, len);
-        kvm_hypercall1(LHCALL_NOTIFY, __pa(scratch));
+        hcall(LHCALL_NOTIFY, __pa(scratch), 0, 0, 0);
 
         /* This routine returns the number of bytes actually written. */
         return len;
@@ -1174,7 +1173,7 @@ static __init int early_put_chars(u32 vtermno, const char *buf, int count)
  */
 static void lguest_restart(char *reason)
 {
-        kvm_hypercall2(LHCALL_SHUTDOWN, __pa(reason), LGUEST_SHUTDOWN_RESTART);
+        hcall(LHCALL_SHUTDOWN, __pa(reason), LGUEST_SHUTDOWN_RESTART, 0, 0);
 }
 
 /*G:050
diff --git a/arch/x86/lguest/i386_head.S b/arch/x86/lguest/i386_head.S
index 27eac0faee48..4f420c2f2d55 100644
--- a/arch/x86/lguest/i386_head.S
+++ b/arch/x86/lguest/i386_head.S
@@ -32,7 +32,7 @@ ENTRY(lguest_entry)
          */
         movl $LHCALL_LGUEST_INIT, %eax
         movl $lguest_data - __PAGE_OFFSET, %ebx
-        .byte 0x0f,0x01,0xc1 /* KVM_HYPERCALL */
+        int $LGUEST_TRAP_ENTRY
 
         /* Set up the initial stack so we can run C code. */
         movl $(init_thread_union+THREAD_SIZE),%esp