14 files changed, 124 insertions, 66 deletions

diff --git a/arch/x86/ia32/sys_ia32.c b/arch/x86/ia32/sys_ia32.c
index 849813f398e7..5852519b2d0f 100644
--- a/arch/x86/ia32/sys_ia32.c
+++ b/arch/x86/ia32/sys_ia32.c
@@ -28,7 +28,6 @@
 #include <linux/syscalls.h>
 #include <linux/times.h>
 #include <linux/utsname.h>
-#include <linux/smp_lock.h>
 #include <linux/mm.h>
 #include <linux/uio.h>
 #include <linux/poll.h>
diff --git a/arch/x86/include/asm/fixmap.h b/arch/x86/include/asm/fixmap.h
index 4d293dced62f..9479a037419f 100644
--- a/arch/x86/include/asm/fixmap.h
+++ b/arch/x86/include/asm/fixmap.h
@@ -216,8 +216,8 @@ static inline unsigned long virt_to_fix(const unsigned long vaddr)
 }
 
 /* Return an pointer with offset calculated */
-static inline unsigned long __set_fixmap_offset(enum fixed_addresses idx,
-                                phys_addr_t phys, pgprot_t flags)
+static __always_inline unsigned long
+__set_fixmap_offset(enum fixed_addresses idx, phys_addr_t phys, pgprot_t flags)
 {
         __set_fixmap(idx, phys, flags);
         return fix_to_virt(idx) + (phys & (PAGE_SIZE - 1));
diff --git a/arch/x86/include/asm/xen/interface.h b/arch/x86/include/asm/xen/interface.h
index e8506c1f0c55..1c10c88ee4e1 100644
--- a/arch/x86/include/asm/xen/interface.h
+++ b/arch/x86/include/asm/xen/interface.h
@@ -61,9 +61,9 @@ DEFINE_GUEST_HANDLE(void);
 #define HYPERVISOR_VIRT_START mk_unsigned_long(__HYPERVISOR_VIRT_START)
 #endif
 
-#ifndef machine_to_phys_mapping
-#define machine_to_phys_mapping ((unsigned long *)HYPERVISOR_VIRT_START)
-#endif
+#define MACH2PHYS_VIRT_START  mk_unsigned_long(__MACH2PHYS_VIRT_START)
+#define MACH2PHYS_VIRT_END    mk_unsigned_long(__MACH2PHYS_VIRT_END)
+#define MACH2PHYS_NR_ENTRIES  ((MACH2PHYS_VIRT_END-MACH2PHYS_VIRT_START)>>__MACH2PHYS_SHIFT)
 
 /* Maximum number of virtual CPUs in multi-processor guests. */
 #define MAX_VIRT_CPUS 32
diff --git a/arch/x86/include/asm/xen/interface_32.h b/arch/x86/include/asm/xen/interface_32.h
index 42a7e004ae5c..8413688b2571 100644
--- a/arch/x86/include/asm/xen/interface_32.h
+++ b/arch/x86/include/asm/xen/interface_32.h
@@ -32,6 +32,11 @@
 /* And the trap vector is... */
 #define TRAP_INSTR "int $0x82"
 
+#define __MACH2PHYS_VIRT_START 0xF5800000
+#define __MACH2PHYS_VIRT_END   0xF6800000
+
+#define __MACH2PHYS_SHIFT      2
+
 /*
  * Virtual addresses beyond this are not modifiable by guest OSes. The
  * machine->physical mapping table starts at this address, read-only.
diff --git a/arch/x86/include/asm/xen/interface_64.h b/arch/x86/include/asm/xen/interface_64.h
index 100d2662b97c..839a4811cf98 100644
--- a/arch/x86/include/asm/xen/interface_64.h
+++ b/arch/x86/include/asm/xen/interface_64.h
@@ -39,18 +39,7 @@
 #define __HYPERVISOR_VIRT_END   0xFFFF880000000000
 #define __MACH2PHYS_VIRT_START  0xFFFF800000000000
 #define __MACH2PHYS_VIRT_END    0xFFFF804000000000
-
-#ifndef HYPERVISOR_VIRT_START
-#define HYPERVISOR_VIRT_START mk_unsigned_long(__HYPERVISOR_VIRT_START)
-#define HYPERVISOR_VIRT_END   mk_unsigned_long(__HYPERVISOR_VIRT_END)
-#endif
-
-#define MACH2PHYS_VIRT_START  mk_unsigned_long(__MACH2PHYS_VIRT_START)
-#define MACH2PHYS_VIRT_END    mk_unsigned_long(__MACH2PHYS_VIRT_END)
-#define MACH2PHYS_NR_ENTRIES  ((MACH2PHYS_VIRT_END-MACH2PHYS_VIRT_START)>>3)
-#ifndef machine_to_phys_mapping
-#define machine_to_phys_mapping ((unsigned long *)HYPERVISOR_VIRT_START)
-#endif
+#define __MACH2PHYS_SHIFT       3
 
 /*
  * int HYPERVISOR_set_segment_base(unsigned int which, unsigned long base)
diff --git a/arch/x86/include/asm/xen/page.h b/arch/x86/include/asm/xen/page.h
index dd8c1414b3d5..8760cc60a21c 100644
--- a/arch/x86/include/asm/xen/page.h
+++ b/arch/x86/include/asm/xen/page.h
@@ -5,6 +5,7 @@
 #include <linux/types.h>
 #include <linux/spinlock.h>
 #include <linux/pfn.h>
+#include <linux/mm.h>
 
 #include <asm/uaccess.h>
 #include <asm/page.h>
@@ -35,6 +36,8 @@ typedef struct xpaddr {
 #define MAX_DOMAIN_PAGES                                                \
     ((unsigned long)((u64)CONFIG_XEN_MAX_DOMAIN_MEMORY * 1024 * 1024 * 1024 / PAGE_SIZE))
 
+extern unsigned long *machine_to_phys_mapping;
+extern unsigned int   machine_to_phys_order;
 
 extern unsigned long get_phys_to_machine(unsigned long pfn);
 extern bool set_phys_to_machine(unsigned long pfn, unsigned long mfn);
@@ -69,10 +72,8 @@ static inline unsigned long mfn_to_pfn(unsigned long mfn)
         if (xen_feature(XENFEAT_auto_translated_physmap))
                 return mfn;
 
-#if 0
         if (unlikely((mfn >> machine_to_phys_order) != 0))
-                return max_mapnr;
-#endif
+                return ~0;
 
         pfn = 0;
         /*
diff --git a/arch/x86/kernel/cpuid.c b/arch/x86/kernel/cpuid.c
index 1b7b31ab7d86..212a6a42527c 100644
--- a/arch/x86/kernel/cpuid.c
+++ b/arch/x86/kernel/cpuid.c
@@ -33,7 +33,6 @@
 #include <linux/init.h>
 #include <linux/poll.h>
 #include <linux/smp.h>
-#include <linux/smp_lock.h>
 #include <linux/major.h>
 #include <linux/fs.h>
 #include <linux/device.h>
diff --git a/arch/x86/kernel/kgdb.c b/arch/x86/kernel/kgdb.c
index ec592caac4b4..cd21b654dec6 100644
--- a/arch/x86/kernel/kgdb.c
+++ b/arch/x86/kernel/kgdb.c
@@ -315,14 +315,18 @@ static void kgdb_remove_all_hw_break(void)
                 if (!breakinfo[i].enabled)
                         continue;
                 bp = *per_cpu_ptr(breakinfo[i].pev, cpu);
-                if (bp->attr.disabled == 1)
+                if (!bp->attr.disabled) {
+                        arch_uninstall_hw_breakpoint(bp);
+                        bp->attr.disabled = 1;
                         continue;
+                }
                 if (dbg_is_early)
                         early_dr7 &= ~encode_dr7(i, breakinfo[i].len,
                                                  breakinfo[i].type);
-                else
-                        arch_uninstall_hw_breakpoint(bp);
-                bp->attr.disabled = 1;
+                else if (hw_break_release_slot(i))
+                        printk(KERN_ERR "KGDB: hw bpt remove failed %lx\n",
+                               breakinfo[i].addr);
+                breakinfo[i].enabled = 0;
         }
 }
 
diff --git a/arch/x86/kernel/msr.c b/arch/x86/kernel/msr.c
index 7bf2dc4c8f70..12fcbe2c143e 100644
--- a/arch/x86/kernel/msr.c
+++ b/arch/x86/kernel/msr.c
@@ -30,7 +30,6 @@
 #include <linux/init.h>
 #include <linux/poll.h>
 #include <linux/smp.h>
-#include <linux/smp_lock.h>
 #include <linux/major.h>
 #include <linux/fs.h>
 #include <linux/device.h>
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index 82e144a4e514..1ca12298ffc7 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -3395,6 +3395,7 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu)
         vcpu->arch.regs[VCPU_REGS_RIP] = svm->vmcb->save.rip;
 
         load_host_msrs(vcpu);
+        kvm_load_ldt(ldt_selector);
         loadsegment(fs, fs_selector);
 #ifdef CONFIG_X86_64
         load_gs_index(gs_selector);
@@ -3402,7 +3403,6 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu)
 #else
         loadsegment(gs, gs_selector);
 #endif
-        kvm_load_ldt(ldt_selector);
 
         reload_tss(vcpu);
 
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 8da0e45ff7c9..ff21fdda0c53 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -821,10 +821,9 @@ static void vmx_save_host_state(struct kvm_vcpu *vcpu)
 #endif
 
 #ifdef CONFIG_X86_64
-        if (is_long_mode(&vmx->vcpu)) {
-                rdmsrl(MSR_KERNEL_GS_BASE, vmx->msr_host_kernel_gs_base);
+        rdmsrl(MSR_KERNEL_GS_BASE, vmx->msr_host_kernel_gs_base);
+        if (is_long_mode(&vmx->vcpu))
                 wrmsrl(MSR_KERNEL_GS_BASE, vmx->msr_guest_kernel_gs_base);
-        }
 #endif
         for (i = 0; i < vmx->save_nmsrs; ++i)
                 kvm_set_shared_msr(vmx->guest_msrs[i].index,
@@ -839,23 +838,23 @@ static void __vmx_load_host_state(struct vcpu_vmx *vmx)
 
         ++vmx->vcpu.stat.host_state_reload;
         vmx->host_state.loaded = 0;
-        if (vmx->host_state.fs_reload_needed)
-                loadsegment(fs, vmx->host_state.fs_sel);
+#ifdef CONFIG_X86_64
+        if (is_long_mode(&vmx->vcpu))
+                rdmsrl(MSR_KERNEL_GS_BASE, vmx->msr_guest_kernel_gs_base);
+#endif
         if (vmx->host_state.gs_ldt_reload_needed) {
                 kvm_load_ldt(vmx->host_state.ldt_sel);
 #ifdef CONFIG_X86_64
                 load_gs_index(vmx->host_state.gs_sel);
-                wrmsrl(MSR_KERNEL_GS_BASE, current->thread.gs);
 #else
                 loadsegment(gs, vmx->host_state.gs_sel);
 #endif
         }
+        if (vmx->host_state.fs_reload_needed)
+                loadsegment(fs, vmx->host_state.fs_sel);
         reload_tss();
 #ifdef CONFIG_X86_64
-        if (is_long_mode(&vmx->vcpu)) {
-                rdmsrl(MSR_KERNEL_GS_BASE, vmx->msr_guest_kernel_gs_base);
-                wrmsrl(MSR_KERNEL_GS_BASE, vmx->msr_host_kernel_gs_base);
-        }
+        wrmsrl(MSR_KERNEL_GS_BASE, vmx->msr_host_kernel_gs_base);
 #endif
         if (current_thread_info()->status & TS_USEDFPU)
                 clts();
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index 235c0f4d3861..02c710bebf7a 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -75,6 +75,11 @@ DEFINE_PER_CPU(struct vcpu_info, xen_vcpu_info);
 enum xen_domain_type xen_domain_type = XEN_NATIVE;
 EXPORT_SYMBOL_GPL(xen_domain_type);
 
+unsigned long *machine_to_phys_mapping = (void *)MACH2PHYS_VIRT_START;
+EXPORT_SYMBOL(machine_to_phys_mapping);
+unsigned int   machine_to_phys_order;
+EXPORT_SYMBOL(machine_to_phys_order);
+
 struct start_info *xen_start_info;
 EXPORT_SYMBOL_GPL(xen_start_info);
 
@@ -1090,6 +1095,8 @@ static void __init xen_setup_stackprotector(void)
 /* First C function to be called on Xen boot */
 asmlinkage void __init xen_start_kernel(void)
 {
+        struct physdev_set_iopl set_iopl;
+        int rc;
         pgd_t *pgd;
 
         if (!xen_start_info)
@@ -1097,6 +1104,8 @@ asmlinkage void __init xen_start_kernel(void)
 
         xen_domain_type = XEN_PV_DOMAIN;
 
+        xen_setup_machphys_mapping();
+
         /* Install Xen paravirt ops */
         pv_info = xen_info;
         pv_init_ops = xen_init_ops;
@@ -1191,8 +1200,6 @@ asmlinkage void __init xen_start_kernel(void)
         /* Allocate and initialize top and mid mfn levels for p2m structure */
         xen_build_mfn_list_list();
 
-        init_mm.pgd = pgd;
-
         /* keep using Xen gdt for now; no urgent need to change it */
 
 #ifdef CONFIG_X86_32
@@ -1202,10 +1209,18 @@ asmlinkage void __init xen_start_kernel(void)
 #else
         pv_info.kernel_rpl = 0;
 #endif
-
         /* set the limit of our address space */
         xen_reserve_top();
 
+        /* We used to do this in xen_arch_setup, but that is too late on AMD
+         * were early_cpu_init (run before ->arch_setup()) calls early_amd_init
+         * which pokes 0xcf8 port.
+         */
+        set_iopl.iopl = 1;
+        rc = HYPERVISOR_physdev_op(PHYSDEVOP_set_iopl, &set_iopl);
+        if (rc != 0)
+                xen_raw_printk("physdev_op failed %d\n", rc);
+
 #ifdef CONFIG_X86_32
         /* set up basic CPUID stuff */
         cpu_detect(&new_cpu_data);
diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c
index 21ed8d7f75a5..a1feff9e59b6 100644
--- a/arch/x86/xen/mmu.c
+++ b/arch/x86/xen/mmu.c
@@ -2034,6 +2034,20 @@ static __init void xen_map_identity_early(pmd_t *pmd, unsigned long max_pfn)
         set_page_prot(pmd, PAGE_KERNEL_RO);
 }
 
+void __init xen_setup_machphys_mapping(void)
+{
+        struct xen_machphys_mapping mapping;
+        unsigned long machine_to_phys_nr_ents;
+
+        if (HYPERVISOR_memory_op(XENMEM_machphys_mapping, &mapping) == 0) {
+                machine_to_phys_mapping = (unsigned long *)mapping.v_start;
+                machine_to_phys_nr_ents = mapping.max_mfn + 1;
+        } else {
+                machine_to_phys_nr_ents = MACH2PHYS_NR_ENTRIES;
+        }
+        machine_to_phys_order = fls(machine_to_phys_nr_ents - 1);
+}
+
 #ifdef CONFIG_X86_64
 static void convert_pfn_mfn(void *v)
 {
@@ -2119,44 +2133,83 @@ __init pgd_t *xen_setup_kernel_pagetable(pgd_t *pgd,
         return pgd;
 }
 #else   /* !CONFIG_X86_64 */
-static RESERVE_BRK_ARRAY(pmd_t, level2_kernel_pgt, PTRS_PER_PMD);
+static RESERVE_BRK_ARRAY(pmd_t, initial_kernel_pmd, PTRS_PER_PMD);
+static RESERVE_BRK_ARRAY(pmd_t, swapper_kernel_pmd, PTRS_PER_PMD);
+
+static __init void xen_write_cr3_init(unsigned long cr3)
+{
+        unsigned long pfn = PFN_DOWN(__pa(swapper_pg_dir));
+
+        BUG_ON(read_cr3() != __pa(initial_page_table));
+        BUG_ON(cr3 != __pa(swapper_pg_dir));
+
+        /*
+         * We are switching to swapper_pg_dir for the first time (from
+         * initial_page_table) and therefore need to mark that page
+         * read-only and then pin it.
+         *
+         * Xen disallows sharing of kernel PMDs for PAE
+         * guests. Therefore we must copy the kernel PMD from
+         * initial_page_table into a new kernel PMD to be used in
+         * swapper_pg_dir.
+         */
+        swapper_kernel_pmd =
+                extend_brk(sizeof(pmd_t) * PTRS_PER_PMD, PAGE_SIZE);
+        memcpy(swapper_kernel_pmd, initial_kernel_pmd,
+               sizeof(pmd_t) * PTRS_PER_PMD);
+        swapper_pg_dir[KERNEL_PGD_BOUNDARY] =
+                __pgd(__pa(swapper_kernel_pmd) | _PAGE_PRESENT);
+        set_page_prot(swapper_kernel_pmd, PAGE_KERNEL_RO);
+
+        set_page_prot(swapper_pg_dir, PAGE_KERNEL_RO);
+        xen_write_cr3(cr3);
+        pin_pagetable_pfn(MMUEXT_PIN_L3_TABLE, pfn);
+
+        pin_pagetable_pfn(MMUEXT_UNPIN_TABLE,
+                          PFN_DOWN(__pa(initial_page_table)));
+        set_page_prot(initial_page_table, PAGE_KERNEL);
+        set_page_prot(initial_kernel_pmd, PAGE_KERNEL);
+
+        pv_mmu_ops.write_cr3 = &xen_write_cr3;
+}
 
 __init pgd_t *xen_setup_kernel_pagetable(pgd_t *pgd,
                                          unsigned long max_pfn)
 {
         pmd_t *kernel_pmd;
 
-        level2_kernel_pgt = extend_brk(sizeof(pmd_t) * PTRS_PER_PMD, PAGE_SIZE);
+        initial_kernel_pmd =
+                extend_brk(sizeof(pmd_t) * PTRS_PER_PMD, PAGE_SIZE);
 
         max_pfn_mapped = PFN_DOWN(__pa(xen_start_info->pt_base) +
                                   xen_start_info->nr_pt_frames * PAGE_SIZE +
                                   512*1024);
 
         kernel_pmd = m2v(pgd[KERNEL_PGD_BOUNDARY].pgd);
-        memcpy(level2_kernel_pgt, kernel_pmd, sizeof(pmd_t) * PTRS_PER_PMD);
+        memcpy(initial_kernel_pmd, kernel_pmd, sizeof(pmd_t) * PTRS_PER_PMD);
 
-        xen_map_identity_early(level2_kernel_pgt, max_pfn);
+        xen_map_identity_early(initial_kernel_pmd, max_pfn);
 
-        memcpy(swapper_pg_dir, pgd, sizeof(pgd_t) * PTRS_PER_PGD);
-        set_pgd(&swapper_pg_dir[KERNEL_PGD_BOUNDARY],
-                        __pgd(__pa(level2_kernel_pgt) | _PAGE_PRESENT));
+        memcpy(initial_page_table, pgd, sizeof(pgd_t) * PTRS_PER_PGD);
+        initial_page_table[KERNEL_PGD_BOUNDARY] =
+                __pgd(__pa(initial_kernel_pmd) | _PAGE_PRESENT);
 
-        set_page_prot(level2_kernel_pgt, PAGE_KERNEL_RO);
-        set_page_prot(swapper_pg_dir, PAGE_KERNEL_RO);
+        set_page_prot(initial_kernel_pmd, PAGE_KERNEL_RO);
+        set_page_prot(initial_page_table, PAGE_KERNEL_RO);
         set_page_prot(empty_zero_page, PAGE_KERNEL_RO);
 
         pin_pagetable_pfn(MMUEXT_UNPIN_TABLE, PFN_DOWN(__pa(pgd)));
 
-        xen_write_cr3(__pa(swapper_pg_dir));
-
-        pin_pagetable_pfn(MMUEXT_PIN_L3_TABLE, PFN_DOWN(__pa(swapper_pg_dir)));
+        pin_pagetable_pfn(MMUEXT_PIN_L3_TABLE,
+                          PFN_DOWN(__pa(initial_page_table)));
+        xen_write_cr3(__pa(initial_page_table));
 
         memblock_x86_reserve_range(__pa(xen_start_info->pt_base),
                       __pa(xen_start_info->pt_base +
                            xen_start_info->nr_pt_frames * PAGE_SIZE),
                       "XEN PAGETABLES");
 
-        return swapper_pg_dir;
+        return initial_page_table;
 }
 #endif  /* CONFIG_X86_64 */
 
@@ -2290,7 +2343,11 @@ static const struct pv_mmu_ops xen_mmu_ops __initdata = {
         .write_cr2 = xen_write_cr2,
 
         .read_cr3 = xen_read_cr3,
+#ifdef CONFIG_X86_32
+        .write_cr3 = xen_write_cr3_init,
+#else
         .write_cr3 = xen_write_cr3,
+#endif
 
         .flush_tlb_user = xen_flush_tlb,
         .flush_tlb_kernel = xen_flush_tlb,
@@ -2627,7 +2684,8 @@ int xen_remap_domain_mfn_range(struct vm_area_struct *vma,
 
         prot = __pgprot(pgprot_val(prot) | _PAGE_IOMAP);
 
-        vma->vm_flags |= VM_IO | VM_RESERVED | VM_PFNMAP;
+        BUG_ON(!((vma->vm_flags & (VM_PFNMAP | VM_RESERVED | VM_IO)) ==
+                                (VM_PFNMAP | VM_RESERVED | VM_IO)));
 
         rmd.mfn = mfn;
         rmd.prot = prot;
diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c
index 769c4b01fa32..01afd8a94607 100644
--- a/arch/x86/xen/setup.c
+++ b/arch/x86/xen/setup.c
@@ -23,7 +23,6 @@
 #include <xen/interface/callback.h>
 #include <xen/interface/memory.h>
 #include <xen/interface/physdev.h>
-#include <xen/interface/memory.h>
 #include <xen/features.h>
 
 #include "xen-ops.h"
@@ -248,8 +247,7 @@ char * __init xen_memory_setup(void)
         else
                 extra_pages = 0;
 
-        if (!xen_initial_domain())
-                xen_add_extra_mem(extra_pages);
+        xen_add_extra_mem(extra_pages);
 
         return "Xen";
 }
@@ -337,9 +335,6 @@ void __cpuinit xen_enable_syscall(void)
 
 void __init xen_arch_setup(void)
 {
-        struct physdev_set_iopl set_iopl;
-        int rc;
-
         xen_panic_handler_init();
 
         HYPERVISOR_vm_assist(VMASST_CMD_enable, VMASST_TYPE_4gb_segments);
@@ -356,11 +351,6 @@ void __init xen_arch_setup(void)
         xen_enable_sysenter();
         xen_enable_syscall();
 
-        set_iopl.iopl = 1;
-        rc = HYPERVISOR_physdev_op(PHYSDEVOP_set_iopl, &set_iopl);
-        if (rc != 0)
-                printk(KERN_INFO "physdev_op failed %d\n", rc);
-
 #ifdef CONFIG_ACPI
         if (!(xen_start_info->flags & SIF_INITDOMAIN)) {
                 printk(KERN_INFO "ACPI in unprivileged domain disabled\n");