Re: [PATCH 1/2] PV hugepages - Xen patch

[Dave McCracken <dcm@mccr.org>]

[-- Attachment #1: Type: text/plain, Size: 229 bytes --]

On Wednesday 08 October 2008, Keir Fraser wrote:
> Then PV superpage support must be a configuration option, and disabled by
> default.

I added a command line option to enable it.  Is this what you had in mind?

Dave McCracken


[-- Attachment #2: xen-hpage-06.patch --]
[-- Type: text/x-diff, Size: 5613 bytes --]

--- xen-unstable//./xen/include/asm-x86/x86_32/page.h	2008-07-17 09:49:27.000000000 -0500
+++ xen-hpage/./xen/include/asm-x86/x86_32/page.h	2008-10-02 15:07:34.000000000 -0500
@@ -112,7 +112,7 @@ extern unsigned int PAGE_HYPERVISOR_NOCA
  * Disallow unused flag bits plus PAT/PSE, PCD, PWT and GLOBAL.
  * Permit the NX bit if the hardware supports it.
  */
-#define BASE_DISALLOW_MASK (0xFFFFF198U & ~_PAGE_NX)
+#define BASE_DISALLOW_MASK (0xFFFFF118U & ~_PAGE_NX)
 
 #define L1_DISALLOW_MASK (BASE_DISALLOW_MASK | _PAGE_GNTTAB)
 #define L2_DISALLOW_MASK (BASE_DISALLOW_MASK)
--- xen-unstable//./xen/include/asm-x86/x86_64/page.h	2008-10-02 14:23:17.000000000 -0500
+++ xen-hpage/./xen/include/asm-x86/x86_64/page.h	2008-10-02 15:07:34.000000000 -0500
@@ -112,7 +112,7 @@ typedef l4_pgentry_t root_pgentry_t;
  * Permit the NX bit if the hardware supports it.
  * Note that range [62:52] is available for software use on x86/64.
  */
-#define BASE_DISALLOW_MASK (0xFF800198U & ~_PAGE_NX)
+#define BASE_DISALLOW_MASK (0xFF800118U & ~_PAGE_NX)
 
 #define L1_DISALLOW_MASK (BASE_DISALLOW_MASK | _PAGE_GNTTAB)
 #define L2_DISALLOW_MASK (BASE_DISALLOW_MASK)
--- xen-unstable//./xen/arch/x86/mm.c	2008-10-02 14:23:17.000000000 -0500
+++ xen-hpage/./xen/arch/x86/mm.c	2008-10-08 16:56:46.000000000 -0500
@@ -160,6 +160,9 @@ unsigned long total_pages;
 
 #define PAGE_CACHE_ATTRS (_PAGE_PAT|_PAGE_PCD|_PAGE_PWT)
 
+static int opt_allow_hugepage = 0;
+boolean_param("allowhugepage", opt_allow_hugepage);
+
 #define l1_disallow_mask(d)                                     \
     ((d != dom_io) &&                                           \
      (rangeset_is_empty((d)->iomem_caps) &&                     \
@@ -584,6 +587,28 @@ static int get_page_and_type_from_pagenr
     return rc;
 }
 
+static int
+get_data_page(struct page_info *page, struct domain *d, int writeable)
+{
+    int rc;
+
+    if (writeable)
+        rc = get_page_and_type(page, d, PGT_writable_page);
+    else
+        rc = get_page(page, d);
+
+    return rc;
+}
+
+static void
+put_data_page(struct page_info *page, int writeable)
+{
+    if (writeable)
+        put_page_and_type(page);
+    else
+        put_page(page);
+}
+
 /*
  * We allow root tables to map each other (a.k.a. linear page tables). It
  * needs some special care with reference counts and access permissions:
@@ -656,6 +681,7 @@ get_page_from_l1e(
     struct vcpu *curr = current;
     struct domain *owner;
     int okay;
+    int writeable;
 
     if ( !(l1f & _PAGE_PRESENT) )
         return 1;
@@ -698,10 +724,9 @@ get_page_from_l1e(
      * contribute to writeable mapping refcounts.  (This allows the
      * qemu-dm helper process in dom0 to map the domain's memory without
      * messing up the count of "real" writable mappings.) */
-    okay = (((l1f & _PAGE_RW) && 
-             !(unlikely(paging_mode_external(d) && (d != curr->domain))))
-            ? get_page_and_type(page, d, PGT_writable_page)
-            : get_page(page, d));
+    writeable = (l1f & _PAGE_RW) &&
+        !(unlikely(paging_mode_external(d) && (d != curr->domain)));
+    okay = get_data_page(page, d, writeable);
     if ( !okay )
     {
         MEM_LOG("Error getting mfn %lx (pfn %lx) from L1 entry %" PRIpte
@@ -759,11 +784,42 @@ get_page_from_l2e(
         MEM_LOG("Bad L2 flags %x", l2e_get_flags(l2e) & L2_DISALLOW_MASK);
         return -EINVAL;
     }
+    if ( l2e_get_flags(l2e) & _PAGE_PSE ) {
+        unsigned long mfn = l2e_get_pfn(l2e);
+        unsigned long m, me;
+        struct page_info *page = mfn_to_page(mfn);
+        int writeable;
 
-    rc = get_page_and_type_from_pagenr(
-        l2e_get_pfn(l2e), PGT_l1_page_table, d, 0);
-    if ( unlikely(rc == -EINVAL) && get_l2_linear_pagetable(l2e, pfn, d) )
-        rc = 0;
+        if (!opt_allow_hugepage)
+            return -EINVAL;
+
+        writeable = l2e_get_flags(l2e) & _PAGE_RW;
+
+        rc = get_data_page(page, d, writeable);
+        if (unlikely(!rc)) {
+            return rc;
+        }
+
+        for (m = mfn+1, me = m + (L1_PAGETABLE_ENTRIES-1); m <= me; m++) {
+            rc = get_data_page(mfn_to_page(m), d, writeable);
+            if (unlikely(!rc)) {
+                for (--m; m > mfn; --m) {
+                    put_data_page(mfn_to_page(m), writeable);
+                }
+                put_data_page(page, writeable);
+                return 0;
+            }
+        }
+#ifdef __x86_64__
+        map_pages_to_xen((unsigned long)mfn_to_virt(mfn), mfn, L1_PAGETABLE_ENTRIES,
+                         PAGE_HYPERVISOR | l2e_get_flags(l2e));
+#endif
+    } else {
+        rc = get_page_and_type_from_pagenr(
+            l2e_get_pfn(l2e), PGT_l1_page_table, d, 0);
+        if ( unlikely(rc == -EINVAL) && get_l2_linear_pagetable(l2e, pfn, d) )
+            rc = 0;
+    }
 
     return rc;
 }
@@ -955,7 +1011,19 @@ static int put_page_from_l2e(l2_pgentry_
     if ( (l2e_get_flags(l2e) & _PAGE_PRESENT) && 
          (l2e_get_pfn(l2e) != pfn) )
     {
-        put_page_and_type(l2e_get_page(l2e));
+        if (l2e_get_flags(l2e) & _PAGE_PSE) {
+            unsigned long mfn = l2e_get_pfn(l2e);
+            unsigned long m, me;
+            struct page_info *page = mfn_to_page(mfn);
+            int writeable = l2e_get_flags(l2e) & _PAGE_RW;
+
+            for (m = mfn+1, me = m + (L1_PAGETABLE_ENTRIES-1); m <= me; m++) {
+                put_data_page(mfn_to_page(m), writeable);
+            }
+            put_data_page(page, writeable);
+        } else {
+            put_page_and_type(l2e_get_page(l2e));
+        }
         return 0;
     }
     return 1;

[-- Attachment #3: Type: text/plain, Size: 138 bytes --]

_______________________________________________
Xen-devel mailing list
Xen-devel@lists.xensource.com
http://lists.xensource.com/xen-devel