5 files changed, 168 insertions, 75 deletions

diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index 82cd39a6cbd3..12a3159333bc 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -42,6 +42,7 @@
 #include <asm/xen/hypervisor.h>
 #include <asm/fixmap.h>
 #include <asm/processor.h>
+#include <asm/proto.h>
 #include <asm/msr-index.h>
 #include <asm/setup.h>
 #include <asm/desc.h>
@@ -168,21 +169,23 @@ static void __init xen_banner(void)
                xen_feature(XENFEAT_mmu_pt_update_preserve_ad) ? " (preserve-AD)" : "");
 }
 
+static __read_mostly unsigned int cpuid_leaf1_edx_mask = ~0;
+static __read_mostly unsigned int cpuid_leaf1_ecx_mask = ~0;
+
 static void xen_cpuid(unsigned int *ax, unsigned int *bx,
                       unsigned int *cx, unsigned int *dx)
 {
+        unsigned maskecx = ~0;
         unsigned maskedx = ~0;
 
         /*
          * Mask out inconvenient features, to try and disable as many
          * unsupported kernel subsystems as possible.
          */
-        if (*ax == 1)
-                maskedx = ~((1 << X86_FEATURE_APIC) |  /* disable APIC */
-                            (1 << X86_FEATURE_ACPI) |  /* disable ACPI */
-                            (1 << X86_FEATURE_MCE)  |  /* disable MCE */
-                            (1 << X86_FEATURE_MCA)  |  /* disable MCA */
-                            (1 << X86_FEATURE_ACC));   /* thermal monitoring */
+        if (*ax == 1) {
+                maskecx = cpuid_leaf1_ecx_mask;
+                maskedx = cpuid_leaf1_edx_mask;
+        }
 
         asm(XEN_EMULATE_PREFIX "cpuid"
                 : "=a" (*ax),
@@ -190,9 +193,43 @@ static void xen_cpuid(unsigned int *ax, unsigned int *bx,
                   "=c" (*cx),
                   "=d" (*dx)
                 : "0" (*ax), "2" (*cx));
+
+        *cx &= maskecx;
         *dx &= maskedx;
 }
 
+static __init void xen_init_cpuid_mask(void)
+{
+        unsigned int ax, bx, cx, dx;
+
+        cpuid_leaf1_edx_mask =
+                ~((1 << X86_FEATURE_MCE)  |  /* disable MCE */
+                  (1 << X86_FEATURE_MCA)  |  /* disable MCA */
+                  (1 << X86_FEATURE_ACC));   /* thermal monitoring */
+
+        if (!xen_initial_domain())
+                cpuid_leaf1_edx_mask &=
+                        ~((1 << X86_FEATURE_APIC) |  /* disable local APIC */
+                          (1 << X86_FEATURE_ACPI));  /* disable ACPI */
+
+        ax = 1;
+        xen_cpuid(&ax, &bx, &cx, &dx);
+
+        /* cpuid claims we support xsave; try enabling it to see what happens */
+        if (cx & (1 << (X86_FEATURE_XSAVE % 32))) {
+                unsigned long cr4;
+
+                set_in_cr4(X86_CR4_OSXSAVE);
+                
+                cr4 = read_cr4();
+
+                if ((cr4 & X86_CR4_OSXSAVE) == 0)
+                        cpuid_leaf1_ecx_mask &= ~(1 << (X86_FEATURE_XSAVE % 32));
+
+                clear_in_cr4(X86_CR4_OSXSAVE);
+        }
+}
+
 static void xen_set_debugreg(int reg, unsigned long val)
 {
         HYPERVISOR_set_debugreg(reg, val);
@@ -203,10 +240,10 @@ static unsigned long xen_get_debugreg(int reg)
         return HYPERVISOR_get_debugreg(reg);
 }
 
-void xen_leave_lazy(void)
+static void xen_end_context_switch(struct task_struct *next)
 {
-        paravirt_leave_lazy(paravirt_get_lazy_mode());
         xen_mc_flush();
+        paravirt_end_context_switch(next);
 }
 
 static unsigned long xen_store_tr(void)
@@ -284,12 +321,11 @@ static void xen_set_ldt(const void *addr, unsigned entries)
 
 static void xen_load_gdt(const struct desc_ptr *dtr)
 {
-        unsigned long *frames;
         unsigned long va = dtr->address;
         unsigned int size = dtr->size + 1;
         unsigned pages = (size + PAGE_SIZE - 1) / PAGE_SIZE;
+        unsigned long frames[pages];
         int f;
-        struct multicall_space mcs;
 
         /* A GDT can be up to 64k in size, which corresponds to 8192
            8-byte entries, or 16 4k pages.. */
@@ -297,19 +333,26 @@ static void xen_load_gdt(const struct desc_ptr *dtr)
         BUG_ON(size > 65536);
         BUG_ON(va & ~PAGE_MASK);
 
-        mcs = xen_mc_entry(sizeof(*frames) * pages);
-        frames = mcs.args;
-
         for (f = 0; va < dtr->address + size; va += PAGE_SIZE, f++) {
-                frames[f] = arbitrary_virt_to_mfn((void *)va);
+                int level;
+                pte_t *ptep = lookup_address(va, &level);
+                unsigned long pfn, mfn;
+                void *virt;
+
+                BUG_ON(ptep == NULL);
+
+                pfn = pte_pfn(*ptep);
+                mfn = pfn_to_mfn(pfn);
+                virt = __va(PFN_PHYS(pfn));
+
+                frames[f] = mfn;
 
                 make_lowmem_page_readonly((void *)va);
-                make_lowmem_page_readonly(mfn_to_virt(frames[f]));
+                make_lowmem_page_readonly(virt);
         }
 
-        MULTI_set_gdt(mcs.mc, frames, size / sizeof(struct desc_struct));
-
-        xen_mc_issue(PARAVIRT_LAZY_CPU);
+        if (HYPERVISOR_set_gdt(frames, size / sizeof(struct desc_struct)))
+                BUG();
 }
 
 static void load_TLS_descriptor(struct thread_struct *t,
@@ -385,7 +428,7 @@ static void xen_write_ldt_entry(struct desc_struct *dt, int entrynum,
 static int cvt_gate_to_trap(int vector, const gate_desc *val,
                             struct trap_info *info)
 {
-        if (val->type != 0xf && val->type != 0xe)
+        if (val->type != GATE_TRAP && val->type != GATE_INTERRUPT)
                 return 0;
 
         info->vector = vector;
@@ -393,8 +436,8 @@ static int cvt_gate_to_trap(int vector, const gate_desc *val,
         info->cs = gate_segment(*val);
         info->flags = val->dpl;
         /* interrupt gates clear IF */
-        if (val->type == 0xe)
-                info->flags |= 4;
+        if (val->type == GATE_INTERRUPT)
+                info->flags |= 1 << 2;
 
         return 1;
 }
@@ -817,10 +860,8 @@ static const struct pv_cpu_ops xen_cpu_ops __initdata = {
         /* Xen takes care of %gs when switching to usermode for us */
         .swapgs = paravirt_nop,
 
-        .lazy_mode = {
-                .enter = paravirt_enter_lazy_cpu,
-                .leave = xen_leave_lazy,
-        },
+        .start_context_switch = paravirt_start_context_switch,
+        .end_context_switch = xen_end_context_switch,
 };
 
 static const struct pv_apic_ops xen_apic_ops __initdata = {
@@ -872,7 +913,6 @@ static const struct machine_ops __initdata xen_machine_ops = {
         .emergency_restart = xen_emergency_restart,
 };
 
-
 /* First C function to be called on Xen boot */
 asmlinkage void __init xen_start_kernel(void)
 {
@@ -897,6 +937,8 @@ asmlinkage void __init xen_start_kernel(void)
 
         xen_init_irq_ops();
 
+        xen_init_cpuid_mask();
+
 #ifdef CONFIG_X86_LOCAL_APIC
         /*
          * set up the basic apic ops.
@@ -938,6 +980,11 @@ asmlinkage void __init xen_start_kernel(void)
         if (!xen_initial_domain())
                 __supported_pte_mask &= ~(_PAGE_PWT | _PAGE_PCD);
 
+#ifdef CONFIG_X86_64
+        /* Work out if we support NX */
+        check_efer();
+#endif
+
         /* Don't do the full vcpu_info placement stuff until we have a
            possible map and a non-dummy shared_info. */
         per_cpu(xen_vcpu, 0) = &HYPERVISOR_shared_info->vcpu_info[0];
diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c
index db3802fb7b84..77b242c9a11e 100644
--- a/arch/x86/xen/mmu.c
+++ b/arch/x86/xen/mmu.c
@@ -184,7 +184,7 @@ static inline unsigned p2m_index(unsigned long pfn)
 }
 
 /* Build the parallel p2m_top_mfn structures */
-void xen_setup_mfn_list_list(void)
+static void __init xen_build_mfn_list_list(void)
 {
         unsigned pfn, idx;
 
@@ -198,7 +198,10 @@ void xen_setup_mfn_list_list(void)
                 unsigned topidx = idx * P2M_ENTRIES_PER_PAGE;
                 p2m_top_mfn_list[idx] = virt_to_mfn(&p2m_top_mfn[topidx]);
         }
+}
 
+void xen_setup_mfn_list_list(void)
+{
         BUG_ON(HYPERVISOR_shared_info == &xen_dummy_shared_info);
 
         HYPERVISOR_shared_info->arch.pfn_to_mfn_frame_list_list =
@@ -218,6 +221,8 @@ void __init xen_build_dynamic_phys_to_machine(void)
 
                 p2m_top[topidx] = &mfn_list[pfn];
         }
+
+        xen_build_mfn_list_list();
 }
 
 unsigned long get_phys_to_machine(unsigned long pfn)
@@ -233,47 +238,74 @@ unsigned long get_phys_to_machine(unsigned long pfn)
 }
 EXPORT_SYMBOL_GPL(get_phys_to_machine);
 
-static void alloc_p2m(unsigned long **pp, unsigned long *mfnp)
+/* install a  new p2m_top page */
+bool install_p2mtop_page(unsigned long pfn, unsigned long *p)
 {
-        unsigned long *p;
+        unsigned topidx = p2m_top_index(pfn);
+        unsigned long **pfnp, *mfnp;
         unsigned i;
 
-        p = (void *)__get_free_page(GFP_KERNEL | __GFP_NOFAIL);
-        BUG_ON(p == NULL);
+        pfnp = &p2m_top[topidx];
+        mfnp = &p2m_top_mfn[topidx];
 
         for (i = 0; i < P2M_ENTRIES_PER_PAGE; i++)
                 p[i] = INVALID_P2M_ENTRY;
 
-        if (cmpxchg(pp, p2m_missing, p) != p2m_missing)
-                free_page((unsigned long)p);
-        else
+        if (cmpxchg(pfnp, p2m_missing, p) == p2m_missing) {
                 *mfnp = virt_to_mfn(p);
+                return true;
+        }
+
+        return false;
 }
 
-void set_phys_to_machine(unsigned long pfn, unsigned long mfn)
+static void alloc_p2m(unsigned long pfn)
 {
-        unsigned topidx, idx;
+        unsigned long *p;
 
-        if (unlikely(xen_feature(XENFEAT_auto_translated_physmap))) {
-                BUG_ON(pfn != mfn && mfn != INVALID_P2M_ENTRY);
-                return;
-        }
+        p = (void *)__get_free_page(GFP_KERNEL | __GFP_NOFAIL);
+        BUG_ON(p == NULL);
+
+        if (!install_p2mtop_page(pfn, p))
+                free_page((unsigned long)p);
+}
+
+/* Try to install p2m mapping; fail if intermediate bits missing */
+bool __set_phys_to_machine(unsigned long pfn, unsigned long mfn)
+{
+        unsigned topidx, idx;
 
         if (unlikely(pfn >= MAX_DOMAIN_PAGES)) {
                 BUG_ON(mfn != INVALID_P2M_ENTRY);
-                return;
+                return true;
         }
 
         topidx = p2m_top_index(pfn);
         if (p2m_top[topidx] == p2m_missing) {
-                /* no need to allocate a page to store an invalid entry */
                 if (mfn == INVALID_P2M_ENTRY)
-                        return;
-                alloc_p2m(&p2m_top[topidx], &p2m_top_mfn[topidx]);
+                        return true;
+                return false;
         }
 
         idx = p2m_index(pfn);
         p2m_top[topidx][idx] = mfn;
+
+        return true;
+}
+
+void set_phys_to_machine(unsigned long pfn, unsigned long mfn)
+{
+        if (unlikely(xen_feature(XENFEAT_auto_translated_physmap))) {
+                BUG_ON(pfn != mfn && mfn != INVALID_P2M_ENTRY);
+                return;
+        }
+
+        if (unlikely(!__set_phys_to_machine(pfn, mfn)))  {
+                alloc_p2m(pfn);
+
+                if (!__set_phys_to_machine(pfn, mfn))
+                        BUG();
+        }
 }
 
 unsigned long arbitrary_virt_to_mfn(void *vaddr)
@@ -419,10 +451,6 @@ void set_pte_mfn(unsigned long vaddr, unsigned long mfn, pgprot_t flags)
 void xen_set_pte_at(struct mm_struct *mm, unsigned long addr,
                     pte_t *ptep, pte_t pteval)
 {
-        /* updates to init_mm may be done without lock */
-        if (mm == &init_mm)
-                preempt_disable();
-
         ADD_STATS(set_pte_at, 1);
 //      ADD_STATS(set_pte_at_pinned, xen_page_pinned(ptep));
         ADD_STATS(set_pte_at_current, mm == current->mm);
@@ -443,9 +471,7 @@ void xen_set_pte_at(struct mm_struct *mm, unsigned long addr,
         }
         xen_set_pte(ptep, pteval);
 
-out:
-        if (mm == &init_mm)
-                preempt_enable();
+out:    return;
 }
 
 pte_t xen_ptep_modify_prot_start(struct mm_struct *mm,
@@ -987,7 +1013,7 @@ static __init int xen_mark_pinned(struct mm_struct *mm, struct page *page,
         return 0;
 }
 
-void __init xen_mark_init_mm_pinned(void)
+static void __init xen_mark_init_mm_pinned(void)
 {
         xen_pgd_walk(&init_mm, xen_mark_pinned, FIXADDR_TOP);
 }
@@ -1119,10 +1145,8 @@ static void drop_other_mm_ref(void *info)
 
         /* If this cpu still has a stale cr3 reference, then make sure
            it has been flushed. */
-        if (percpu_read(xen_current_cr3) == __pa(mm->pgd)) {
+        if (percpu_read(xen_current_cr3) == __pa(mm->pgd))
                 load_cr3(swapper_pg_dir);
-                arch_flush_lazy_cpu_mode();
-        }
 }
 
 static void xen_drop_mm_ref(struct mm_struct *mm)
@@ -1135,7 +1159,6 @@ static void xen_drop_mm_ref(struct mm_struct *mm)
                         load_cr3(swapper_pg_dir);
                 else
                         leave_mm(smp_processor_id());
-                arch_flush_lazy_cpu_mode();
         }
 
         /* Get the "official" set of cpus referring to our pagetable. */
@@ -1270,8 +1293,8 @@ static void xen_flush_tlb_others(const struct cpumask *cpus,
         } *args;
         struct multicall_space mcs;
 
-        BUG_ON(cpumask_empty(cpus));
-        BUG_ON(!mm);
+        if (cpumask_empty(cpus))
+                return;         /* nothing to do */
 
         mcs = xen_mc_entry(sizeof(*args));
         args = mcs.args;
@@ -1438,6 +1461,15 @@ static __init void xen_set_pte_init(pte_t *ptep, pte_t pte)
 }
 #endif
 
+static void pin_pagetable_pfn(unsigned cmd, unsigned long pfn)
+{
+        struct mmuext_op op;
+        op.cmd = cmd;
+        op.arg1.mfn = pfn_to_mfn(pfn);
+        if (HYPERVISOR_mmuext_op(&op, 1, NULL, DOMID_SELF))
+                BUG();
+}
+
 /* Early in boot, while setting up the initial pagetable, assume
    everything is pinned. */
 static __init void xen_alloc_pte_init(struct mm_struct *mm, unsigned long pfn)
@@ -1446,22 +1478,29 @@ static __init void xen_alloc_pte_init(struct mm_struct *mm, unsigned long pfn)
         BUG_ON(mem_map);        /* should only be used early */
 #endif
         make_lowmem_page_readonly(__va(PFN_PHYS(pfn)));
+        pin_pagetable_pfn(MMUEXT_PIN_L1_TABLE, pfn);
+}
+
+/* Used for pmd and pud */
+static __init void xen_alloc_pmd_init(struct mm_struct *mm, unsigned long pfn)
+{
+#ifdef CONFIG_FLATMEM
+        BUG_ON(mem_map);        /* should only be used early */
+#endif
+        make_lowmem_page_readonly(__va(PFN_PHYS(pfn)));
 }
 
 /* Early release_pte assumes that all pts are pinned, since there's
    only init_mm and anything attached to that is pinned. */
-static void xen_release_pte_init(unsigned long pfn)
+static __init void xen_release_pte_init(unsigned long pfn)
 {
+        pin_pagetable_pfn(MMUEXT_UNPIN_TABLE, pfn);
         make_lowmem_page_readwrite(__va(PFN_PHYS(pfn)));
 }
 
-static void pin_pagetable_pfn(unsigned cmd, unsigned long pfn)
+static __init void xen_release_pmd_init(unsigned long pfn)
 {
-        struct mmuext_op op;
-        op.cmd = cmd;
-        op.arg1.mfn = pfn_to_mfn(pfn);
-        if (HYPERVISOR_mmuext_op(&op, 1, NULL, DOMID_SELF))
-                BUG();
+        make_lowmem_page_readwrite(__va(PFN_PHYS(pfn)));
 }
 
 /* This needs to make sure the new pte page is pinned iff its being
@@ -1819,6 +1858,13 @@ __init void xen_post_allocator_init(void)
         xen_mark_init_mm_pinned();
 }
 
+static void xen_leave_lazy_mmu(void)
+{
+        preempt_disable();
+        xen_mc_flush();
+        paravirt_leave_lazy_mmu();
+        preempt_enable();
+}
 
 const struct pv_mmu_ops xen_mmu_ops __initdata = {
         .pagetable_setup_start = xen_pagetable_setup_start,
@@ -1843,9 +1889,9 @@ const struct pv_mmu_ops xen_mmu_ops __initdata = {
 
         .alloc_pte = xen_alloc_pte_init,
         .release_pte = xen_release_pte_init,
-        .alloc_pmd = xen_alloc_pte_init,
+        .alloc_pmd = xen_alloc_pmd_init,
         .alloc_pmd_clone = paravirt_nop,
-        .release_pmd = xen_release_pte_init,
+        .release_pmd = xen_release_pmd_init,
 
 #ifdef CONFIG_HIGHPTE
         .kmap_atomic_pte = xen_kmap_atomic_pte,
@@ -1883,8 +1929,8 @@ const struct pv_mmu_ops xen_mmu_ops __initdata = {
         .make_pud = PV_CALLEE_SAVE(xen_make_pud),
         .set_pgd = xen_set_pgd_hyper,
 
-        .alloc_pud = xen_alloc_pte_init,
-        .release_pud = xen_release_pte_init,
+        .alloc_pud = xen_alloc_pmd_init,
+        .release_pud = xen_release_pmd_init,
 #endif  /* PAGETABLE_LEVELS == 4 */
 
         .activate_mm = xen_activate_mm,
@@ -1893,7 +1939,7 @@ const struct pv_mmu_ops xen_mmu_ops __initdata = {
 
         .lazy_mode = {
                 .enter = paravirt_enter_lazy_mmu,
-                .leave = xen_leave_lazy,
+                .leave = xen_leave_lazy_mmu,
         },
 
         .set_fixmap = xen_set_fixmap,
diff --git a/arch/x86/xen/mmu.h b/arch/x86/xen/mmu.h
index 24d1b44a337d..da7302624897 100644
--- a/arch/x86/xen/mmu.h
+++ b/arch/x86/xen/mmu.h
@@ -11,6 +11,9 @@ enum pt_level {
 };
 
 
+bool __set_phys_to_machine(unsigned long pfn, unsigned long mfn);
+bool install_p2mtop_page(unsigned long pfn, unsigned long *p);
+
 void set_pte_mfn(unsigned long vaddr, unsigned long pfn, pgprot_t flags);
 
 
diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c
index 585a6e330837..429834ec1687 100644
--- a/arch/x86/xen/smp.c
+++ b/arch/x86/xen/smp.c
@@ -317,7 +317,7 @@ static int __cpuinit xen_cpu_up(unsigned int cpu)
         BUG_ON(rc);
 
         while(per_cpu(cpu_state, cpu) != CPU_ONLINE) {
-                HYPERVISOR_sched_op(SCHEDOP_yield, 0);
+                HYPERVISOR_sched_op(SCHEDOP_yield, NULL);
                 barrier();
         }
 
@@ -422,7 +422,7 @@ static void xen_smp_send_call_function_ipi(const struct cpumask *mask)
         /* Make sure other vcpus get a chance to run if they need to. */
         for_each_cpu(cpu, mask) {
                 if (xen_vcpu_stolen(cpu)) {
-                        HYPERVISOR_sched_op(SCHEDOP_yield, 0);
+                        HYPERVISOR_sched_op(SCHEDOP_yield, NULL);
                         break;
                 }
         }
diff --git a/arch/x86/xen/xen-ops.h b/arch/x86/xen/xen-ops.h
index 2f5ef2632ea2..5c50a1017a37 100644
--- a/arch/x86/xen/xen-ops.h
+++ b/arch/x86/xen/xen-ops.h
@@ -30,7 +30,6 @@ pgd_t *xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn);
 void xen_ident_map_ISA(void);
 void xen_reserve_top(void);
 
-void xen_leave_lazy(void);
 void xen_post_allocator_init(void);
 
 char * __init xen_memory_setup(void);
@@ -57,8 +56,6 @@ irqreturn_t xen_debug_interrupt(int irq, void *dev_id);
 
 bool xen_vcpu_stolen(int vcpu);
 
-void xen_mark_init_mm_pinned(void);
-
 void xen_setup_vcpu_info_placement(void);
 
 #ifdef CONFIG_SMP