From mboxrd@z Thu Jan 1 00:00:00 1970 From: Andrew Cooper Subject: Re: [PATCH] x86: don't blindly create L3 tables for the direct map Date: Mon, 30 Sep 2013 13:36:40 +0100 Message-ID: <52497058.6060800@citrix.com> References: <52498C0B02000078000F8020@nat28.tlf.novell.com> Mime-Version: 1.0 Content-Type: multipart/mixed; boundary="===============7402335263558766753==" Return-path: Received: from mail6.bemta14.messagelabs.com ([193.109.254.103]) by lists.xen.org with esmtp (Exim 4.72) (envelope-from ) id 1VQciS-0002Gb-Cn for xen-devel@lists.xenproject.org; Mon, 30 Sep 2013 12:36:45 +0000 In-Reply-To: <52498C0B02000078000F8020@nat28.tlf.novell.com> List-Unsubscribe: , List-Post: List-Help: List-Subscribe: , Sender: xen-devel-bounces@lists.xen.org Errors-To: xen-devel-bounces@lists.xen.org To: Jan Beulich Cc: xen-devel , Malcolm Crossley , Keir Fraser List-Id: xen-devel@lists.xenproject.org --===============7402335263558766753== Content-Type: multipart/alternative; boundary="------------070208030901010804000902" --------------070208030901010804000902 Content-Type: text/plain; charset="ISO-8859-1" Content-Transfer-Encoding: 7bit On 30/09/13 13:34, Jan Beulich wrote: > Now that the direct map area can extend all the way up to almost the > end of address space, this is wasteful. > > Also fold two almost redundant messages in SRAT parsing into one. > > Signed-off-by: Jan Beulich > Tested-by: Malcolm Crossley Reviewed-by: Andrew Cooper > > --- a/xen/arch/x86/mm.c > +++ b/xen/arch/x86/mm.c > @@ -137,7 +137,7 @@ l1_pgentry_t __attribute__ ((__section__ > #define PTE_UPDATE_WITH_CMPXCHG > #endif > > -bool_t __read_mostly mem_hotplug = 0; > +paddr_t __read_mostly mem_hotplug; > > /* Private domain structs for DOMID_XEN and DOMID_IO. */ > struct domain *dom_xen, *dom_io, *dom_cow; > --- a/xen/arch/x86/srat.c > +++ b/xen/arch/x86/srat.c > @@ -113,6 +113,7 @@ static __init void bad_srat(void) > apicid_to_node[i] = NUMA_NO_NODE; > for (i = 0; i < ARRAY_SIZE(pxm2node); i++) > pxm2node[i] = NUMA_NO_NODE; > + mem_hotplug = 0; > } > > /* > @@ -257,13 +258,6 @@ acpi_numa_memory_affinity_init(struct ac > return; > } > /* It is fine to add this area to the nodes data it will be used later*/ > - if (ma->flags & ACPI_SRAT_MEM_HOT_PLUGGABLE) > - { > - printk(KERN_INFO "SRAT: hot plug zone found %"PRIx64" - %"PRIx64" \n", > - start, end); > - mem_hotplug = 1; > - } > - > i = conflicting_memblks(start, end); > if (i == node) { > printk(KERN_WARNING > @@ -287,8 +281,11 @@ acpi_numa_memory_affinity_init(struct ac > if (nd->end < end) > nd->end = end; > } > - printk(KERN_INFO "SRAT: Node %u PXM %u %"PRIx64"-%"PRIx64"\n", node, pxm, > - start, end); > + if ((ma->flags & ACPI_SRAT_MEM_HOT_PLUGGABLE) && end > mem_hotplug) > + mem_hotplug = end; > + printk(KERN_INFO "SRAT: Node %u PXM %u %"PRIx64"-%"PRIx64"%s\n", > + node, pxm, start, end, > + ma->flags & ACPI_SRAT_MEM_HOT_PLUGGABLE ? " (hotplug)" : ""); > > node_memblk_range[num_node_memblks].start = start; > node_memblk_range[num_node_memblks].end = end; > --- a/xen/arch/x86/x86_64/mm.c > +++ b/xen/arch/x86/x86_64/mm.c > @@ -559,25 +559,20 @@ void __init paging_init(void) > * We setup the L3s for 1:1 mapping if host support memory hotplug > * to avoid sync the 1:1 mapping on page fault handler > */ > - if ( mem_hotplug ) > + for ( va = DIRECTMAP_VIRT_START; > + va < DIRECTMAP_VIRT_END && (void *)va < __va(mem_hotplug); > + va += (1UL << L4_PAGETABLE_SHIFT) ) > { > - unsigned long va; > - > - for ( va = DIRECTMAP_VIRT_START; > - va < DIRECTMAP_VIRT_END; > - va += (1UL << L4_PAGETABLE_SHIFT) ) > + if ( !(l4e_get_flags(idle_pg_table[l4_table_offset(va)]) & > + _PAGE_PRESENT) ) > { > - if ( !(l4e_get_flags(idle_pg_table[l4_table_offset(va)]) & > - _PAGE_PRESENT) ) > - { > - l3_pg = alloc_domheap_page(NULL, 0); > - if ( !l3_pg ) > - goto nomem; > - l3_ro_mpt = page_to_virt(l3_pg); > - clear_page(l3_ro_mpt); > - l4e_write(&idle_pg_table[l4_table_offset(va)], > - l4e_from_page(l3_pg, __PAGE_HYPERVISOR)); > - } > + l3_pg = alloc_domheap_page(NULL, 0); > + if ( !l3_pg ) > + goto nomem; > + l3_ro_mpt = page_to_virt(l3_pg); > + clear_page(l3_ro_mpt); > + l4e_write(&idle_pg_table[l4_table_offset(va)], > + l4e_from_page(l3_pg, __PAGE_HYPERVISOR)); > } > } > > --- a/xen/include/asm-x86/mm.h > +++ b/xen/include/asm-x86/mm.h > @@ -399,7 +399,7 @@ static inline int get_page_and_type(stru > int check_descriptor(const struct domain *, struct desc_struct *d); > > extern bool_t opt_allow_superpage; > -extern bool_t mem_hotplug; > +extern paddr_t mem_hotplug; > > /****************************************************************************** > * With shadow pagetables, the different kinds of address start > > > > > > _______________________________________________ > Xen-devel mailing list > Xen-devel@lists.xen.org > http://lists.xen.org/xen-devel --------------070208030901010804000902 Content-Type: text/html; charset="ISO-8859-1" Content-Transfer-Encoding: 7bit
On 30/09/13 13:34, Jan Beulich wrote:
Now that the direct map area can extend all the way up to almost the
end of address space, this is wasteful.

Also fold two almost redundant messages in SRAT parsing into one.

Signed-off-by: Jan Beulich <jbeulich@suse.com>
Tested-by: Malcolm Crossley <malcolm.crossley@citrix.com>

Reviewed-by: Andrew Cooper <andrew.cooper3@citrix.com>


--- a/xen/arch/x86/mm.c
+++ b/xen/arch/x86/mm.c
@@ -137,7 +137,7 @@ l1_pgentry_t __attribute__ ((__section__
 #define PTE_UPDATE_WITH_CMPXCHG
 #endif
 
-bool_t __read_mostly mem_hotplug = 0;
+paddr_t __read_mostly mem_hotplug;
 
 /* Private domain structs for DOMID_XEN and DOMID_IO. */
 struct domain *dom_xen, *dom_io, *dom_cow;
--- a/xen/arch/x86/srat.c
+++ b/xen/arch/x86/srat.c
@@ -113,6 +113,7 @@ static __init void bad_srat(void)
 		apicid_to_node[i] = NUMA_NO_NODE;
 	for (i = 0; i < ARRAY_SIZE(pxm2node); i++)
 		pxm2node[i] = NUMA_NO_NODE;
+	mem_hotplug = 0;
 }
 
 /*
@@ -257,13 +258,6 @@ acpi_numa_memory_affinity_init(struct ac
 		return;
 	}
 	/* It is fine to add this area to the nodes data it will be used later*/
-	if (ma->flags & ACPI_SRAT_MEM_HOT_PLUGGABLE)
-	{
-		printk(KERN_INFO "SRAT: hot plug zone found %"PRIx64" - %"PRIx64" \n",
-				start, end);
-		mem_hotplug = 1;
-	}
-
 	i = conflicting_memblks(start, end);
 	if (i == node) {
 		printk(KERN_WARNING
@@ -287,8 +281,11 @@ acpi_numa_memory_affinity_init(struct ac
 		if (nd->end < end)
 			nd->end = end;
 	}
-	printk(KERN_INFO "SRAT: Node %u PXM %u %"PRIx64"-%"PRIx64"\n", node, pxm,
-	       start, end);
+	if ((ma->flags & ACPI_SRAT_MEM_HOT_PLUGGABLE) && end > mem_hotplug)
+		mem_hotplug = end;
+	printk(KERN_INFO "SRAT: Node %u PXM %u %"PRIx64"-%"PRIx64"%s\n",
+	       node, pxm, start, end,
+	       ma->flags & ACPI_SRAT_MEM_HOT_PLUGGABLE ? " (hotplug)" : "");
 
 	node_memblk_range[num_node_memblks].start = start;
 	node_memblk_range[num_node_memblks].end = end;
--- a/xen/arch/x86/x86_64/mm.c
+++ b/xen/arch/x86/x86_64/mm.c
@@ -559,25 +559,20 @@ void __init paging_init(void)
      * We setup the L3s for 1:1 mapping if host support memory hotplug
      * to avoid sync the 1:1 mapping on page fault handler
      */
-    if ( mem_hotplug )
+    for ( va = DIRECTMAP_VIRT_START;
+          va < DIRECTMAP_VIRT_END && (void *)va < __va(mem_hotplug);
+          va += (1UL << L4_PAGETABLE_SHIFT) )
     {
-        unsigned long va;
-
-        for ( va = DIRECTMAP_VIRT_START;
-              va < DIRECTMAP_VIRT_END;
-              va += (1UL << L4_PAGETABLE_SHIFT) )
+        if ( !(l4e_get_flags(idle_pg_table[l4_table_offset(va)]) &
+              _PAGE_PRESENT) )
         {
-            if ( !(l4e_get_flags(idle_pg_table[l4_table_offset(va)]) &
-                  _PAGE_PRESENT) )
-            {
-                l3_pg = alloc_domheap_page(NULL, 0);
-                if ( !l3_pg )
-                    goto nomem;
-                l3_ro_mpt = page_to_virt(l3_pg);
-                clear_page(l3_ro_mpt);
-                l4e_write(&idle_pg_table[l4_table_offset(va)],
-                  l4e_from_page(l3_pg, __PAGE_HYPERVISOR));
-            }
+            l3_pg = alloc_domheap_page(NULL, 0);
+            if ( !l3_pg )
+                goto nomem;
+            l3_ro_mpt = page_to_virt(l3_pg);
+            clear_page(l3_ro_mpt);
+            l4e_write(&idle_pg_table[l4_table_offset(va)],
+                      l4e_from_page(l3_pg, __PAGE_HYPERVISOR));
         }
     }
 
--- a/xen/include/asm-x86/mm.h
+++ b/xen/include/asm-x86/mm.h
@@ -399,7 +399,7 @@ static inline int get_page_and_type(stru
 int check_descriptor(const struct domain *, struct desc_struct *d);
 
 extern bool_t opt_allow_superpage;
-extern bool_t mem_hotplug;
+extern paddr_t mem_hotplug;
 
 /******************************************************************************
  * With shadow pagetables, the different kinds of address start 






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

--------------070208030901010804000902-- --===============7402335263558766753== Content-Type: text/plain; charset="us-ascii" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit Content-Disposition: inline _______________________________________________ Xen-devel mailing list Xen-devel@lists.xen.org http://lists.xen.org/xen-devel --===============7402335263558766753==--