1 files changed, 90 insertions, 44 deletions

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,