4 files changed, 110 insertions, 79 deletions

diff --git a/arch/x86/xen/Kconfig b/arch/x86/xen/Kconfig
index 5cc821cb2e09..ae559fe91c25 100644
--- a/arch/x86/xen/Kconfig
+++ b/arch/x86/xen/Kconfig
@@ -49,11 +49,3 @@ config XEN_DEBUG_FS
         help
           Enable statistics output and various tuning options in debugfs.
           Enabling this option may incur a significant performance overhead.
-
-config XEN_DEBUG
-        bool "Enable Xen debug checks"
-        depends on XEN
-        default n
-        help
-          Enable various WARN_ON checks in the Xen MMU code.
-          Enabling this option WILL incur a significant performance overhead.
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index 2d69617950f7..da8afd576a6b 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -251,6 +251,7 @@ static void __init xen_init_cpuid_mask(void)
                         ~((1 << X86_FEATURE_APIC) |  /* disable local APIC */
                           (1 << X86_FEATURE_ACPI));  /* disable ACPI */
         ax = 1;
+        cx = 0;
         xen_cpuid(&ax, &bx, &cx, &dx);
 
         xsave_mask =
diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c
index 3dd53f997b11..87f6673b1207 100644
--- a/arch/x86/xen/mmu.c
+++ b/arch/x86/xen/mmu.c
@@ -495,41 +495,6 @@ static pte_t xen_make_pte(pteval_t pte)
 }
 PV_CALLEE_SAVE_REGS_THUNK(xen_make_pte);
 
-#ifdef CONFIG_XEN_DEBUG
-pte_t xen_make_pte_debug(pteval_t pte)
-{
-        phys_addr_t addr = (pte & PTE_PFN_MASK);
-        phys_addr_t other_addr;
-        bool io_page = false;
-        pte_t _pte;
-
-        if (pte & _PAGE_IOMAP)
-                io_page = true;
-
-        _pte = xen_make_pte(pte);
-
-        if (!addr)
-                return _pte;
-
-        if (io_page &&
-            (xen_initial_domain() || addr >= ISA_END_ADDRESS)) {
-                other_addr = pfn_to_mfn(addr >> PAGE_SHIFT) << PAGE_SHIFT;
-                WARN_ONCE(addr != other_addr,
-                        "0x%lx is using VM_IO, but it is 0x%lx!\n",
-                        (unsigned long)addr, (unsigned long)other_addr);
-        } else {
-                pteval_t iomap_set = (_pte.pte & PTE_FLAGS_MASK) & _PAGE_IOMAP;
-                other_addr = (_pte.pte & PTE_PFN_MASK);
-                WARN_ONCE((addr == other_addr) && (!io_page) && (!iomap_set),
-                        "0x%lx is missing VM_IO (and wasn't fixed)!\n",
-                        (unsigned long)addr);
-        }
-
-        return _pte;
-}
-PV_CALLEE_SAVE_REGS_THUNK(xen_make_pte_debug);
-#endif
-
 static pgd_t xen_make_pgd(pgdval_t pgd)
 {
         pgd = pte_pfn_to_mfn(pgd);
@@ -1992,9 +1957,6 @@ void __init xen_ident_map_ISA(void)
 
 static void __init xen_post_allocator_init(void)
 {
-#ifdef CONFIG_XEN_DEBUG
-        pv_mmu_ops.make_pte = PV_CALLEE_SAVE(xen_make_pte_debug);
-#endif
         pv_mmu_ops.set_pte = xen_set_pte;
         pv_mmu_ops.set_pmd = xen_set_pmd;
         pv_mmu_ops.set_pud = xen_set_pud;
@@ -2404,17 +2366,3 @@ out:
         return err;
 }
 EXPORT_SYMBOL_GPL(xen_remap_domain_mfn_range);
-
-#ifdef CONFIG_XEN_DEBUG_FS
-static int p2m_dump_open(struct inode *inode, struct file *filp)
-{
-        return single_open(filp, p2m_dump_show, NULL);
-}
-
-static const struct file_operations p2m_dump_fops = {
-        .open           = p2m_dump_open,
-        .read           = seq_read,
-        .llseek         = seq_lseek,
-        .release        = single_release,
-};
-#endif /* CONFIG_XEN_DEBUG_FS */
diff --git a/arch/x86/xen/p2m.c b/arch/x86/xen/p2m.c
index 58efeb9d5440..1b267e75158d 100644
--- a/arch/x86/xen/p2m.c
+++ b/arch/x86/xen/p2m.c
@@ -161,7 +161,9 @@
 #include <asm/xen/page.h>
 #include <asm/xen/hypercall.h>
 #include <asm/xen/hypervisor.h>
+#include <xen/grant_table.h>
 
+#include "multicalls.h"
 #include "xen-ops.h"
 
 static void __init m2p_override_init(void);
@@ -676,7 +678,8 @@ static unsigned long mfn_hash(unsigned long mfn)
 }
 
 /* Add an MFN override for a particular page */
-int m2p_add_override(unsigned long mfn, struct page *page, bool clear_pte)
+int m2p_add_override(unsigned long mfn, struct page *page,
+                struct gnttab_map_grant_ref *kmap_op)
 {
         unsigned long flags;
         unsigned long pfn;
@@ -692,16 +695,28 @@ int m2p_add_override(unsigned long mfn, struct page *page, bool clear_pte)
                                         "m2p_add_override: pfn %lx not mapped", pfn))
                         return -EINVAL;
         }
-
-        page->private = mfn;
+        WARN_ON(PagePrivate(page));
+        SetPagePrivate(page);
+        set_page_private(page, mfn);
         page->index = pfn_to_mfn(pfn);
 
         if (unlikely(!set_phys_to_machine(pfn, FOREIGN_FRAME(mfn))))
                 return -ENOMEM;
 
-        if (clear_pte && !PageHighMem(page))
-                /* Just zap old mapping for now */
-                pte_clear(&init_mm, address, ptep);
+        if (kmap_op != NULL) {
+                if (!PageHighMem(page)) {
+                        struct multicall_space mcs =
+                                xen_mc_entry(sizeof(*kmap_op));
+
+                        MULTI_grant_table_op(mcs.mc,
+                                        GNTTABOP_map_grant_ref, kmap_op, 1);
+
+                        xen_mc_issue(PARAVIRT_LAZY_MMU);
+                }
+                /* let's use dev_bus_addr to record the old mfn instead */
+                kmap_op->dev_bus_addr = page->index;
+                page->index = (unsigned long) kmap_op;
+        }
         spin_lock_irqsave(&m2p_override_lock, flags);
         list_add(&page->lru,  &m2p_overrides[mfn_hash(mfn)]);
         spin_unlock_irqrestore(&m2p_override_lock, flags);
@@ -735,13 +750,56 @@ int m2p_remove_override(struct page *page, bool clear_pte)
         spin_lock_irqsave(&m2p_override_lock, flags);
         list_del(&page->lru);
         spin_unlock_irqrestore(&m2p_override_lock, flags);
-        set_phys_to_machine(pfn, page->index);
+        WARN_ON(!PagePrivate(page));
+        ClearPagePrivate(page);
 
-        if (clear_pte && !PageHighMem(page))
-                set_pte_at(&init_mm, address, ptep,
-                                pfn_pte(pfn, PAGE_KERNEL));
-                /* No tlb flush necessary because the caller already
-                 * left the pte unmapped. */
+        if (clear_pte) {
+                struct gnttab_map_grant_ref *map_op =
+                        (struct gnttab_map_grant_ref *) page->index;
+                set_phys_to_machine(pfn, map_op->dev_bus_addr);
+                if (!PageHighMem(page)) {
+                        struct multicall_space mcs;
+                        struct gnttab_unmap_grant_ref *unmap_op;
+
+                        /*
+                         * It might be that we queued all the m2p grant table
+                         * hypercalls in a multicall, then m2p_remove_override
+                         * get called before the multicall has actually been
+                         * issued. In this case handle is going to -1 because
+                         * it hasn't been modified yet.
+                         */
+                        if (map_op->handle == -1)
+                                xen_mc_flush();
+                        /*
+                         * Now if map_op->handle is negative it means that the
+                         * hypercall actually returned an error.
+                         */
+                        if (map_op->handle == GNTST_general_error) {
+                                printk(KERN_WARNING "m2p_remove_override: "
+                                                "pfn %lx mfn %lx, failed to modify kernel mappings",
+                                                pfn, mfn);
+                                return -1;
+                        }
+
+                        mcs = xen_mc_entry(
+                                        sizeof(struct gnttab_unmap_grant_ref));
+                        unmap_op = mcs.args;
+                        unmap_op->host_addr = map_op->host_addr;
+                        unmap_op->handle = map_op->handle;
+                        unmap_op->dev_bus_addr = 0;
+
+                        MULTI_grant_table_op(mcs.mc,
+                                        GNTTABOP_unmap_grant_ref, unmap_op, 1);
+
+                        xen_mc_issue(PARAVIRT_LAZY_MMU);
+
+                        set_pte_at(&init_mm, address, ptep,
+                                        pfn_pte(pfn, PAGE_KERNEL));
+                        __flush_tlb_single(address);
+                        map_op->host_addr = 0;
+                }
+        } else
+                set_phys_to_machine(pfn, page->index);
 
         return 0;
 }
@@ -758,7 +816,7 @@ struct page *m2p_find_override(unsigned long mfn)
         spin_lock_irqsave(&m2p_override_lock, flags);
 
         list_for_each_entry(p, bucket, lru) {
-                if (p->private == mfn) {
+                if (page_private(p) == mfn) {
                         ret = p;
                         break;
                 }
@@ -782,17 +840,21 @@ unsigned long m2p_find_override_pfn(unsigned long mfn, unsigned long pfn)
 EXPORT_SYMBOL_GPL(m2p_find_override_pfn);
 
 #ifdef CONFIG_XEN_DEBUG_FS
-
-int p2m_dump_show(struct seq_file *m, void *v)
+#include <linux/debugfs.h>
+#include "debugfs.h"
+static int p2m_dump_show(struct seq_file *m, void *v)
 {
         static const char * const level_name[] = { "top", "middle",
-                                                "entry", "abnormal" };
-        static const char * const type_name[] = { "identity", "missing",
-                                                "pfn", "abnormal"};
+                                                "entry", "abnormal", "error"};
 #define TYPE_IDENTITY 0
 #define TYPE_MISSING 1
 #define TYPE_PFN 2
 #define TYPE_UNKNOWN 3
+        static const char * const type_name[] = {
+                                [TYPE_IDENTITY] = "identity",
+                                [TYPE_MISSING] = "missing",
+                                [TYPE_PFN] = "pfn",
+                                [TYPE_UNKNOWN] = "abnormal"};
         unsigned long pfn, prev_pfn_type = 0, prev_pfn_level = 0;
         unsigned int uninitialized_var(prev_level);
         unsigned int uninitialized_var(prev_type);
@@ -856,4 +918,32 @@ int p2m_dump_show(struct seq_file *m, void *v)
 #undef TYPE_PFN
 #undef TYPE_UNKNOWN
 }
-#endif
+
+static int p2m_dump_open(struct inode *inode, struct file *filp)
+{
+        return single_open(filp, p2m_dump_show, NULL);
+}
+
+static const struct file_operations p2m_dump_fops = {
+        .open           = p2m_dump_open,
+        .read           = seq_read,
+        .llseek         = seq_lseek,
+        .release        = single_release,
+};
+
+static struct dentry *d_mmu_debug;
+
+static int __init xen_p2m_debugfs(void)
+{
+        struct dentry *d_xen = xen_init_debugfs();
+
+        if (d_xen == NULL)
+                return -ENOMEM;
+
+        d_mmu_debug = debugfs_create_dir("mmu", d_xen);
+
+        debugfs_create_file("p2m", 0600, d_mmu_debug, NULL, &p2m_dump_fops);
+        return 0;
+}
+fs_initcall(xen_p2m_debugfs);
+#endif /* CONFIG_XEN_DEBUG_FS */