x86: highmem handling assistance hypercalls

While looking at the origin of very frequently executed hypercalls I
realized that the high page accessor functions in Linux would be good
candidates to handle in the hypervisor - clearing or copying to/from
a high page is a pretty frequent operation (provided there's enough
memory in the domain). While prior to the first submission I only
measured kernel builds (where the results are not hinting at a
meaningful improvement), I now found time to do a more specific
analysis: page clearing is being improved by about 20%, page copying
doesn't seem to significantly benefit (though that may be an effect of
the simplistic copy_page() implementation Xen currently uses) -
nevertheless I would think that if one function is supported by the
hypervisor, then the other should also be.

Signed-off-by: Jan Beulich <jbeulich@novell.com>

5 files changed, 106 insertions, 2 deletions

diff --git a/xen/arch/x86/mm.c b/xen/arch/x86/mm.c
index 248c130a27..b2a9c3a085 100644
--- a/xen/arch/x86/mm.c
+++ b/xen/arch/x86/mm.c
@@ -2431,6 +2431,29 @@ static inline cpumask_t vcpumask_to_pcpumask(
     return pmask;
 }
 
+#ifdef __i386__
+static inline void *fixmap_domain_page(unsigned long mfn)
+{
+    unsigned int cpu = smp_processor_id();
+    void *ptr = (void *)fix_to_virt(FIX_PAE_HIGHMEM_0 + cpu);
+
+    l1e_write(fix_pae_highmem_pl1e - cpu,
+              l1e_from_pfn(mfn, __PAGE_HYPERVISOR));
+    flush_tlb_one_local(ptr);
+    return ptr;
+}
+static inline void fixunmap_domain_page(const void *ptr)
+{
+    unsigned int cpu = virt_to_fix((unsigned long)ptr) - FIX_PAE_HIGHMEM_0;
+
+    l1e_write(fix_pae_highmem_pl1e - cpu, l1e_empty());
+    this_cpu(make_cr3_timestamp) = this_cpu(tlbflush_time);
+}
+#else
+#define fixmap_domain_page(mfn) mfn_to_virt(mfn)
+#define fixunmap_domain_page(ptr) ((void)(ptr))
+#endif
+
 int do_mmuext_op(
     XEN_GUEST_HANDLE(mmuext_op_t) uops,
     unsigned int count,
@@ -2700,6 +2723,66 @@ int do_mmuext_op(
             break;
         }
 
+        case MMUEXT_CLEAR_PAGE:
+        {
+            unsigned char *ptr;
+
+            okay = !get_page_and_type_from_pagenr(mfn, PGT_writable_page,
+                                                  FOREIGNDOM, 0);
+            if ( unlikely(!okay) )
+            {
+                MEM_LOG("Error while clearing mfn %lx", mfn);
+                break;
+            }
+
+            /* A page is dirtied when it's being cleared. */
+            paging_mark_dirty(d, mfn);
+
+            ptr = fixmap_domain_page(mfn);
+            clear_page(ptr);
+            fixunmap_domain_page(ptr);
+
+            put_page_and_type(page);
+            break;
+        }
+
+        case MMUEXT_COPY_PAGE:
+        {
+            const unsigned char *src;
+            unsigned char *dst;
+            unsigned long src_mfn;
+
+            src_mfn = gmfn_to_mfn(FOREIGNDOM, op.arg2.src_mfn);
+            okay = get_page_from_pagenr(src_mfn, FOREIGNDOM);
+            if ( unlikely(!okay) )
+            {
+                MEM_LOG("Error while copying from mfn %lx", src_mfn);
+                break;
+            }
+
+            okay = !get_page_and_type_from_pagenr(mfn, PGT_writable_page,
+                                                  FOREIGNDOM, 0);
+            if ( unlikely(!okay) )
+            {
+                put_page(mfn_to_page(src_mfn));
+                MEM_LOG("Error while copying to mfn %lx", mfn);
+                break;
+            }
+
+            /* A page is dirtied when it's being copied to. */
+            paging_mark_dirty(d, mfn);
+
+            src = map_domain_page(src_mfn);
+            dst = fixmap_domain_page(mfn);
+            copy_page(dst, src);
+            fixunmap_domain_page(dst);
+            unmap_domain_page(src);
+
+            put_page_and_type(page);
+            put_page(mfn_to_page(src_mfn));
+            break;
+        }
+
         default:
             MEM_LOG("Invalid extended pt command 0x%x", op.cmd);
             rc = -ENOSYS;
diff --git a/xen/arch/x86/x86_64/compat/mm.c b/xen/arch/x86/x86_64/compat/mm.c
index 913760c14f..942c35a1e2 100644
--- a/xen/arch/x86/x86_64/compat/mm.c
+++ b/xen/arch/x86/x86_64/compat/mm.c
@@ -231,6 +231,8 @@ int compat_mmuext_op(XEN_GUEST_HANDLE(mmuext_op_compat_t) cmp_uops,
             case MMUEXT_PIN_L4_TABLE:
             case MMUEXT_UNPIN_TABLE:
             case MMUEXT_NEW_BASEPTR:
+            case MMUEXT_CLEAR_PAGE:
+            case MMUEXT_COPY_PAGE:
                 arg1 = XLAT_mmuext_op_arg1_mfn;
                 break;
             default:
@@ -258,6 +260,9 @@ int compat_mmuext_op(XEN_GUEST_HANDLE(mmuext_op_compat_t) cmp_uops,
             case MMUEXT_INVLPG_MULTI:
                 arg2 = XLAT_mmuext_op_arg2_vcpumask;
                 break;
+            case MMUEXT_COPY_PAGE:
+                arg2 = XLAT_mmuext_op_arg2_src_mfn;
+                break;
             default:
                 arg2 = -1;
                 break;
diff --git a/xen/common/kernel.c b/xen/common/kernel.c
index 2a88602e51..f3af91f2ed 100644
--- a/xen/common/kernel.c
+++ b/xen/common/kernel.c
@@ -221,7 +221,8 @@ DO(xen_version)(int cmd, XEN_GUEST_HANDLE(void) arg)
                 fi.submap |= 1U << XENFEAT_supervisor_mode_kernel;
 #ifdef CONFIG_X86
             if ( !is_hvm_vcpu(current) )
-                fi.submap |= 1U << XENFEAT_mmu_pt_update_preserve_ad;
+                fi.submap |= (1U << XENFEAT_mmu_pt_update_preserve_ad) |
+                             (1U << XENFEAT_highmem_assist);
 #endif
             break;
         default:
diff --git a/xen/include/public/features.h b/xen/include/public/features.h
index 05fc5dc464..16e5ee4d49 100644
--- a/xen/include/public/features.h
+++ b/xen/include/public/features.h
@@ -59,6 +59,9 @@
 /* x86: Does this Xen host support the MMU_PT_UPDATE_PRESERVE_AD hypercall? */
 #define XENFEAT_mmu_pt_update_preserve_ad  5
 
+/* x86: Does this Xen host support the MMU_{CLEAR,COPY}_PAGE hypercall? */
+#define XENFEAT_highmem_assist             6
+
 #define XENFEAT_NR_SUBMAPS 1
 
 #endif /* __XEN_PUBLIC_FEATURES_H__ */
diff --git a/xen/include/public/xen.h b/xen/include/public/xen.h
index 4b444b4c71..5292232819 100644
--- a/xen/include/public/xen.h
+++ b/xen/include/public/xen.h
@@ -231,6 +231,13 @@ DEFINE_XEN_GUEST_HANDLE(xen_pfn_t);
  * cmd: MMUEXT_SET_LDT
  * linear_addr: Linear address of LDT base (NB. must be page-aligned).
  * nr_ents: Number of entries in LDT.
+ *
+ * cmd: MMUEXT_CLEAR_PAGE
+ * mfn: Machine frame number to be cleared.
+ *
+ * cmd: MMUEXT_COPY_PAGE
+ * mfn: Machine frame number of the destination page.
+ * src_mfn: Machine frame number of the source page.
  */
 #define MMUEXT_PIN_L1_TABLE      0
 #define MMUEXT_PIN_L2_TABLE      1
@@ -247,12 +254,15 @@ DEFINE_XEN_GUEST_HANDLE(xen_pfn_t);
 #define MMUEXT_FLUSH_CACHE      12
 #define MMUEXT_SET_LDT          13
 #define MMUEXT_NEW_USER_BASEPTR 15
+#define MMUEXT_CLEAR_PAGE       16
+#define MMUEXT_COPY_PAGE        17
 
 #ifndef __ASSEMBLY__
 struct mmuext_op {
     unsigned int cmd;
     union {
-        /* [UN]PIN_TABLE, NEW_BASEPTR, NEW_USER_BASEPTR */
+        /* [UN]PIN_TABLE, NEW_BASEPTR, NEW_USER_BASEPTR
+         * CLEAR_PAGE, COPY_PAGE */
         xen_pfn_t     mfn;
         /* INVLPG_LOCAL, INVLPG_ALL, SET_LDT */
         unsigned long linear_addr;
@@ -266,6 +276,8 @@ struct mmuext_op {
 #else
         void *vcpumask;
 #endif
+        /* COPY_PAGE */
+        xen_pfn_t src_mfn;
     } arg2;
 };
 typedef struct mmuext_op mmuext_op_t;