Skip to contentSkip to conversation

Enable 1GB for Xen HVM host page

PATCH In review Wei Huang 3 participants 5 messages Feb 22, 2010 – Feb 25, 2010

lore
Share & tools
lore

Wei Huang

author
#0 lore raw

PATCH 3/4 Enable 1GB for Xen HVM host page

This patch changes P2M code to works with 1GB page now.

# HG changeset patch
# User [email protected]
# Date 1266853453 21600
# Node ID 72075d4fc39e8cd11a06bff4eb66521ab8fe952b # Parent c9b45664b423e11003358944bb8e6e976e735301 fix p2m code to support 1GB pages

xen/arch/x86/mm/p2m.c +193 -11
diff -r c9b45664b423 -r 72075d4fc39e xen/arch/x86/mm/p2m.c
@@ -187,7 +187,36 @@
 
     ASSERT(l1e_get_flags(*p2m_entry) & (_PAGE_PRESENT|_PAGE_PSE));
 
-    /* split single large page into 4KB page in P2M table */
+    /* split 1GB pages into 2MB pages */
+    if ( type == PGT_l2_page_table && (l1e_get_flags(*p2m_entry) & _PAGE_PSE) )
+    {
+        unsigned long flags, pfn;
+        struct page_info *pg = d->arch.p2m->alloc_page(d);
+        if ( pg == NULL )
+            return 0;
+        page_list_add_tail(pg, &d->arch.p2m->pages);
+        pg->u.inuse.type_info = PGT_l2_page_table | 1 | PGT_validated;
+        pg->count_info = 1;
+        
+        flags = l1e_get_flags(*p2m_entry);
+        pfn = l1e_get_pfn(*p2m_entry);
+        
+        l1_entry = map_domain_page(mfn_x(page_to_mfn(pg)));
+        for ( i = 0; i < L2_PAGETABLE_ENTRIES; i++ )
+        {
+            new_entry = l1e_from_pfn(pfn + (i * L1_PAGETABLE_ENTRIES), flags);
+            paging_write_p2m_entry(d, gfn, l1_entry+i, *table_mfn, new_entry,
+                                   2);
+        }
+        unmap_domain_page(l1_entry);
+        new_entry = l1e_from_pfn(mfn_x(page_to_mfn(pg)),
+                                 __PAGE_HYPERVISOR|_PAGE_USER); //disable PSE
+        paging_write_p2m_entry(d, gfn,
+                               p2m_entry, *table_mfn, new_entry, 3);
+    }
+
+
+    /* split single 2MB large page into 4KB page in P2M table */
     if ( type == PGT_l1_page_table && (l1e_get_flags(*p2m_entry) & _PAGE_PSE) )
     {
         unsigned long flags, pfn;
@@ -1064,6 +1093,19 @@
     if ( unlikely(d->is_dying) )
         goto out_fail;
 
+    /* Because PoD does not have cache list for 1GB pages, it has to remap
+     * 1GB region to 2MB chunks for a retry. */
+    if ( order == 18 )
+    {
+        gfn_aligned = (gfn >> order) << order;
+        for( i = 0; i < (1 << order); i += (1 << 9) )
+            set_p2m_entry(d, gfn_aligned + i, _mfn(POPULATE_ON_DEMAND_MFN), 9,
+                          p2m_populate_on_demand);
+        audit_p2m(d);
+        p2m_unlock(p2md);
+        return 0;
+    }
+
     /* If we're low, start a sweep */
     if ( order == 9 && page_list_empty(&p2md->pod.super) )
         p2m_pod_emergency_sweep_super(d);
@@ -1196,6 +1238,7 @@
     l1_pgentry_t *p2m_entry;
     l1_pgentry_t entry_content;
     l2_pgentry_t l2e_content;
+    l3_pgentry_t l3e_content;
     int rv=0;
 
     if ( tb_init_done )
@@ -1222,18 +1265,44 @@
         goto out;
 #endif
     /*
+     * Try to allocate 1GB page table if this feature is supported.
+     *
      * When using PAE Xen, we only allow 33 bits of pseudo-physical
      * address in translated guests (i.e. 8 GBytes).  This restriction
      * comes from wanting to map the P2M table into the 16MB RO_MPT hole
      * in Xen's address space for translated PV guests.
      * When using AMD's NPT on PAE Xen, we are restricted to 4GB.
      */
-    if ( !p2m_next_level(d, &table_mfn, &table, &gfn_remainder, gfn,
-                         L3_PAGETABLE_SHIFT - PAGE_SHIFT,
-                         ((CONFIG_PAGING_LEVELS == 3)
-                          ? (d->arch.hvm_domain.hap_enabled ? 4 : 8)
-                          : L3_PAGETABLE_ENTRIES),
-                         PGT_l2_page_table) )
+    if ( page_order == 18 )
+    {
+        p2m_entry = p2m_find_entry(table, &gfn_remainder, gfn,
+                                   L3_PAGETABLE_SHIFT - PAGE_SHIFT,
+                                   L3_PAGETABLE_ENTRIES);
+        ASSERT(p2m_entry);
+        if ( (l1e_get_flags(*p2m_entry) & _PAGE_PRESENT) &&
+             !(l1e_get_flags(*p2m_entry) & _PAGE_PSE) )
+        {
+            P2M_ERROR("configure P2M table L3 entry with large page\n");
+            domain_crash(d);
+            goto out;
+        }
+        
+        if ( mfn_valid(mfn) )
+            l3e_content = l3e_from_pfn(mfn_x(mfn),
+                                       p2m_type_to_flags(p2mt) | _PAGE_PSE);
+        else
+            l3e_content = l3e_empty();
+        
+        entry_content.l1 = l3e_content.l3;
+        paging_write_p2m_entry(d, gfn, p2m_entry, table_mfn, entry_content, 3);
+
+    }
+    else if ( !p2m_next_level(d, &table_mfn, &table, &gfn_remainder, gfn,
+                              L3_PAGETABLE_SHIFT - PAGE_SHIFT,
+                              ((CONFIG_PAGING_LEVELS == 3)
+                               ? (d->arch.hvm_domain.hap_enabled ? 4 : 8)
+                               : L3_PAGETABLE_ENTRIES),
+                              PGT_l2_page_table) )
         goto out;
 
     if ( page_order == 0 )
@@ -1255,7 +1324,7 @@
         /* level 1 entry */
         paging_write_p2m_entry(d, gfn, p2m_entry, table_mfn, entry_content, 1);
     }
-    else 
+    else if ( page_order == 9 )
     {
         p2m_entry = p2m_find_entry(table, &gfn_remainder, gfn,
                                    L2_PAGETABLE_SHIFT - PAGE_SHIFT,
@@ -1352,11 +1421,34 @@
 #else
         l3e += l3_table_offset(addr);
 #endif
+pod_retry_l3:
         if ( (l3e_get_flags(*l3e) & _PAGE_PRESENT) == 0 )
         {
+            if ( p2m_flags_to_type(l3e_get_flags(*l3e)) == p2m_populate_on_demand )
+            {
+                if ( q != p2m_query )
+                {
+                    if ( !p2m_pod_demand_populate(d, gfn, 18, q) )
+                        goto pod_retry_l3;
+                }
+                else
+                    *t = p2m_populate_on_demand;
+            }
             unmap_domain_page(l3e);
             return _mfn(INVALID_MFN);
         }
+        else if ( (l3e_get_flags(*l3e) & _PAGE_PSE) )
+        {
+            mfn = _mfn(l3e_get_pfn(*l3e) +
+                       l2_table_offset(addr) * L1_PAGETABLE_ENTRIES +
+                       l1_table_offset(addr));
+            *t = p2m_flags_to_type(l3e_get_flags(*l3e));
+            unmap_domain_page(l3e);
+
+            ASSERT(mfn_valid(mfn) || !p2m_is_ram(*t));
+            return (p2m_is_valid(*t)) ? mfn : _mfn(INVALID_MFN);
+        }
+
         mfn = _mfn(l3e_get_pfn(*l3e));
         unmap_domain_page(l3e);
     }
@@ -1437,10 +1529,57 @@
     {
         l1_pgentry_t l1e = l1e_empty(), *p2m_entry;
         l2_pgentry_t l2e = l2e_empty();
+        l3_pgentry_t l3e = l3e_empty();
         int ret;
 
         ASSERT(gfn < (RO_MPT_VIRT_END - RO_MPT_VIRT_START) 
                / sizeof(l1_pgentry_t));
+
+        /*
+         * Read & process L3
+         */
+        p2m_entry = (l1_pgentry_t *)
+            &__linear_l2_table[l2_linear_offset(RO_MPT_VIRT_START)
+                               + l3_linear_offset(addr)];
+    pod_retry_l3:
+        ret = __copy_from_user(&l3e, p2m_entry, sizeof(l3e));
+
+        if ( ret != 0 || !(l3e_get_flags(l3e) & _PAGE_PRESENT) )
+        {
+            if ( (l3e_get_flags(l3e) & _PAGE_PSE) &&
+                 (p2m_flags_to_type(l3e_get_flags(l3e)) == p2m_populate_on_demand) )
+            {
+                /* The read has succeeded, so we know that mapping exists */
+                if ( q != p2m_query )
+                {
+                    if ( !p2m_pod_demand_populate(current->domain, gfn, 18, q) )
+                        goto pod_retry_l3;
+                    p2mt = p2m_invalid;
+                    printk("%s: Allocate 1GB failed!\n", __func__);
+                    goto out;
+                }
+                else
+                {
+                    p2mt = p2m_populate_on_demand;
+                    goto out;
+                }
+            }
+            goto pod_retry_l2;
+        }
+
+        if ( l3e_get_flags(l3e) & _PAGE_PSE )
+        {
+            p2mt = p2m_flags_to_type(l3e_get_flags(l3e));
+            ASSERT(l3e_get_pfn(l3e) != INVALID_MFN || !p2m_is_ram(p2mt));
+            if (p2m_is_valid(p2mt) )
+                mfn = _mfn(l3e_get_pfn(l3e) + 
+                           l2_table_offset(addr) * L1_PAGETABLE_ENTRIES + 
+                           l1_table_offset(addr));
+            else
+                p2mt = p2m_mmio_dm;
+            
+            goto out;
+        }
 
         /*
          * Read & process L2
@@ -1596,8 +1735,10 @@
     while ( todo )
     {
         if ( is_hvm_domain(d) && d->arch.hvm_domain.hap_enabled )
-            order = (((gfn | mfn_x(mfn) | todo) & (SUPERPAGE_PAGES - 1)) == 0) ?
-                9 : 0;
+            order = ( (((gfn | mfn_x(mfn) | todo) & ((1ul << 18) - 1)) == 0) ) ?
+                    18 :
+                    (((gfn | mfn_x(mfn) | todo) & ((1ul << 9) - 1)) == 0) ? 9 : 0;
+
         else
             order = 0;
         if ( !d->arch.p2m->set_entry(d, gfn, mfn, order, p2mt) )
@@ -1867,6 +2008,31 @@
                     gfn += 1 << (L3_PAGETABLE_SHIFT - PAGE_SHIFT);
                     continue;
                 }
+
+                /* check for 1GB super page */
+                if ( l3e_get_flags(l3e[i3]) & _PAGE_PSE )
+                {
+                    mfn = l3e_get_pfn(l3e[i3]);
+                    ASSERT(mfn_valid(_mfn(mfn)));
+                    /* we have to cover 512x512 4K pages */
+                    for ( i2 = 0; 
+                          i2 < (L2_PAGETABLE_ENTRIES * L1_PAGETABLE_ENTRIES);
+                          i2++)
+                    {
+                        m2pfn = get_gpfn_from_mfn(mfn+i2);
+                        if ( m2pfn != (gfn + i2) )
+                        {
+                            pmbad++;
+                            P2M_PRINTK("mismatch: gfn %#lx -> mfn %#lx"
+                                       " -> gfn %#lx\n", gfn+i2, mfn+i2,
+                                       m2pfn);
+                            BUG();
+                        }
+                        gfn += 1 << (L3_PAGETABLE_SHIFT - PAGE_SHIFT);
+                        continue;
+                    }
+                }
+
                 l2e = map_domain_page(mfn_x(_mfn(l3e_get_pfn(l3e[i3]))));
                 for ( i2 = 0; i2 < L2_PAGETABLE_ENTRIES; i2++ )
                 {
@@ -2224,7 +2390,7 @@
     l1_pgentry_t l1e_content;
     l1_pgentry_t *l1e;
     l2_pgentry_t *l2e;
-    mfn_t l1mfn, l2mfn;
+    mfn_t l1mfn, l2mfn, l3mfn;
     unsigned long i1, i2, i3;
     l3_pgentry_t *l3e;
 #if CONFIG_PAGING_LEVELS == 4
@@ -2245,6 +2411,7 @@
 #if CONFIG_PAGING_LEVELS == 4
     l4e = map_domain_page(mfn_x(pagetable_get_mfn(d->arch.phys_table)));
 #else /* CONFIG_PAGING_LEVELS == 3 */
+    l3mfn = _mfn(mfn_x(pagetable_get_mfn(d->arch.phys_table)));
     l3e = map_domain_page(mfn_x(pagetable_get_mfn(d->arch.phys_table)));
 #endif
 
@@ -2255,6 +2422,7 @@
         {
             continue;
         }
+        l3mfn = _mfn(l4e_get_pfn(l4e[i4]));
         l3e = map_domain_page(l4e_get_pfn(l4e[i4]));
 #endif
         for ( i3 = 0;
@@ -2265,6 +2433,20 @@
             {
                 continue;
             }
+            if ( (l3e_get_flags(l3e[i3]) & _PAGE_PSE) )
+            {
+                flags = l3e_get_flags(l3e[i3]);
+                if ( p2m_flags_to_type(flags) != ot )
+                    continue;
+                mfn = l3e_get_pfn(l3e[i3]);
+                gfn = get_gpfn_from_mfn(mfn);
+                flags = p2m_type_to_flags(nt);
+                l1e_content = l1e_from_pfn(mfn, flags | _PAGE_PSE);
+                paging_write_p2m_entry(d, gfn, (l1_pgentry_t *)&l3e[i3],
+                                       l3mfn, l1e_content, 3);
+                continue;
+            }
+
             l2mfn = _mfn(l3e_get_pfn(l3e[i3]));
             l2e = map_domain_page(l3e_get_pfn(l3e[i3]));
             for ( i2 = 0; i2 < L2_PAGETABLE_ENTRIES; i2++ )

_______________________________________________
Xen-devel mailing list
[email protected]
http://lists.xensource.com/xen-devel

#1 lore raw
Quoted 8 lines · Wei Huang

This patch changes P2M code to works with 1GB page now.

xen/arch/x86/mm/p2m.c +0 -0
@@ -1064,6 +1093,19 @@
     if ( unlikely(d->is_dying) )

xen/arch/x86/mm/p2m.c line 1103

Quoted 10 lines
xen/arch/x86/mm/p2m.c +8 -0
         goto out_fail;
 
+    /* Because PoD does not have cache list for 1GB pages, it has to remap
+     * 1GB region to 2MB chunks for a retry. */
+    if ( order == 18 )
+    {
+        gfn_aligned = (gfn >> order) << order;
+        for( i = 0; i < (1 << order); i += (1 << 9) )
+            set_p2m_entry(d, gfn_aligned + i, _mfn(POPULATE_ON_DEMAND_MFN), 9,
+                          p2m_populate_on_demand);

I think you only need one set_p2m_entry call here - it will split the 1GB entry without needing another 511 calls.

Was the decision not to implement populate-on-demand for 1GB pages based on not thinking it's a good idea or not wanting to do the work? :) How much performance do PoD guests lose by not having it?

Quoted 18 lines
xen/arch/x86/mm/p2m.c +6 -0
+        audit_p2m(d);
+        p2m_unlock(p2md);
+        return 0;
+    }
+
     /* If we're low, start a sweep */
     if ( order == 9 && page_list_empty(&p2md->pod.super) )
         p2m_pod_emergency_sweep_super(d);
@@ -1196,6 +1238,7 @@
     l1_pgentry_t *p2m_entry;
     l1_pgentry_t entry_content;
     l2_pgentry_t l2e_content;
+    l3_pgentry_t l3e_content;
     int rv=0;
 
     if ( tb_init_done )
@@ -1222,18 +1265,44 @@
         goto out;

xen/arch/x86/mm/p2m.c line 1275

Quoted 10 lines
xen/arch/x86/mm/p2m.c +2 -0
 #endif
     /*
+     * Try to allocate 1GB page table if this feature is supported.
+     *
      * When using PAE Xen, we only allow 33 bits of pseudo-physical
      * address in translated guests (i.e. 8 GBytes).  This restriction
      * comes from wanting to map the P2M table into the 16MB RO_MPT hole
      * in Xen's address space for translated PV guests.
      * When using AMD's NPT on PAE Xen, we are restricted to 4GB.
      */

Please move this comment closer to the code it describes.

Also maybe a BUG_ON(CONFIG_PAGING_LEVELS == 3) in the order-18 case would be useful, since otherwise it looks like order-18 allocations are exempt from the restriction.

Actually, I don't see where you enforce that - do you?

Tim.

Signature · 3 lines
Tim Deegan <[email protected]>
Principal Software Engineer, XenServer Engineering
Citrix Systems UK Ltd.  (Company #02937203, SL9 0BG)
#2 lore raw

I was hoping that someone else would pick up the 1GB PoD task. :P I can try to implement this feature if deemed necessary.

-Wei

-----Original Message-----
From: Tim Deegan [mailto:[email protected]]
Sent: Tuesday, February 23, 2010 4:07 AM
To: Huang2, Wei
Cc: '[email protected]'; Keir Fraser; Xu, Dongxiao
Subject: Re: [Xen-devel] [PATCH][3/4] Enable 1GB for Xen HVM host page

Quoted 8 lines · Wei Huang

This patch changes P2M code to works with 1GB page now.

xen/arch/x86/mm/p2m.c +0 -0
@@ -1064,6 +1093,19 @@
     if ( unlikely(d->is_dying) )

xen/arch/x86/mm/p2m.c line 1103

Quoted 10 lines
xen/arch/x86/mm/p2m.c +8 -0
         goto out_fail;
 
+    /* Because PoD does not have cache list for 1GB pages, it has to remap
+     * 1GB region to 2MB chunks for a retry. */
+    if ( order == 18 )
+    {
+        gfn_aligned = (gfn >> order) << order;
+        for( i = 0; i < (1 << order); i += (1 << 9) )
+            set_p2m_entry(d, gfn_aligned + i, _mfn(POPULATE_ON_DEMAND_MFN), 9,
+                          p2m_populate_on_demand);

I think you only need one set_p2m_entry call here - it will split the 1GB entry without needing another 511 calls.

Was the decision not to implement populate-on-demand for 1GB pages based on not thinking it's a good idea or not wanting to do the work? :) How much performance do PoD guests lose by not having it?

Quoted 18 lines
xen/arch/x86/mm/p2m.c +6 -0
+        audit_p2m(d);
+        p2m_unlock(p2md);
+        return 0;
+    }
+
     /* If we're low, start a sweep */
     if ( order == 9 && page_list_empty(&p2md->pod.super) )
         p2m_pod_emergency_sweep_super(d);
@@ -1196,6 +1238,7 @@
     l1_pgentry_t *p2m_entry;
     l1_pgentry_t entry_content;
     l2_pgentry_t l2e_content;
+    l3_pgentry_t l3e_content;
     int rv=0;
 
     if ( tb_init_done )
@@ -1222,18 +1265,44 @@
         goto out;

xen/arch/x86/mm/p2m.c line 1275

Quoted 10 lines
xen/arch/x86/mm/p2m.c +2 -0
 #endif
     /*
+     * Try to allocate 1GB page table if this feature is supported.
+     *
      * When using PAE Xen, we only allow 33 bits of pseudo-physical
      * address in translated guests (i.e. 8 GBytes).  This restriction
      * comes from wanting to map the P2M table into the 16MB RO_MPT hole
      * in Xen's address space for translated PV guests.
      * When using AMD's NPT on PAE Xen, we are restricted to 4GB.
      */

Please move this comment closer to the code it describes.

Also maybe a BUG_ON(CONFIG_PAGING_LEVELS == 3) in the order-18 case would be useful, since otherwise it looks like order-18 allocations are exempt from the restriction.

Actually, I don't see where you enforce that - do you?

Tim.

Signature · 3 lines
Tim Deegan <[email protected]>
Principal Software Engineer, XenServer Engineering
Citrix Systems UK Ltd.  (Company #02937203, SL9 0BG)
#3 lore raw
Quoted 2 lines · Wei

I was hoping that someone else would pick up the 1GB PoD task. :P I can try to implement this feature if deemed necessary.

I think it will be OK - PoD is only useful with balloon drivers, which currently don't even maintain 2MB superpages, so it's probably not worth engineering up 1GB PoD.

Tim.

Quoted 82 lines

-Wei

-----Original Message-----
From: Tim Deegan [mailto:[email protected]]
Sent: Tuesday, February 23, 2010 4:07 AM
To: Huang2, Wei
Cc: '[email protected]'; Keir Fraser; Xu, Dongxiao
Subject: Re: [Xen-devel] [PATCH][3/4] Enable 1GB for Xen HVM host page

Quoted 8 lines · Wei Huang

This patch changes P2M code to works with 1GB page now.

xen/arch/x86/mm/p2m.c +0 -0
@@ -1064,6 +1093,19 @@
     if ( unlikely(d->is_dying) )

xen/arch/x86/mm/p2m.c line 1103

Quoted 10 lines
xen/arch/x86/mm/p2m.c +8 -0
         goto out_fail;
 
+    /* Because PoD does not have cache list for 1GB pages, it has to remap
+     * 1GB region to 2MB chunks for a retry. */
+    if ( order == 18 )
+    {
+        gfn_aligned = (gfn >> order) << order;
+        for( i = 0; i < (1 << order); i += (1 << 9) )
+            set_p2m_entry(d, gfn_aligned + i, _mfn(POPULATE_ON_DEMAND_MFN), 9,
+                          p2m_populate_on_demand);

I think you only need one set_p2m_entry call here - it will split the 1GB entry without needing another 511 calls.

Was the decision not to implement populate-on-demand for 1GB pages based on not thinking it's a good idea or not wanting to do the work? :) How much performance do PoD guests lose by not having it?

Quoted 18 lines
xen/arch/x86/mm/p2m.c +6 -0
+        audit_p2m(d);
+        p2m_unlock(p2md);
+        return 0;
+    }
+
     /* If we're low, start a sweep */
     if ( order == 9 && page_list_empty(&p2md->pod.super) )
         p2m_pod_emergency_sweep_super(d);
@@ -1196,6 +1238,7 @@
     l1_pgentry_t *p2m_entry;
     l1_pgentry_t entry_content;
     l2_pgentry_t l2e_content;
+    l3_pgentry_t l3e_content;
     int rv=0;
 
     if ( tb_init_done )
@@ -1222,18 +1265,44 @@
         goto out;

xen/arch/x86/mm/p2m.c line 1275

Quoted 10 lines
xen/arch/x86/mm/p2m.c +2 -0
 #endif
     /*
+     * Try to allocate 1GB page table if this feature is supported.
+     *
      * When using PAE Xen, we only allow 33 bits of pseudo-physical
      * address in translated guests (i.e. 8 GBytes).  This restriction
      * comes from wanting to map the P2M table into the 16MB RO_MPT hole
      * in Xen's address space for translated PV guests.
      * When using AMD's NPT on PAE Xen, we are restricted to 4GB.
      */

Please move this comment closer to the code it describes.

Also maybe a BUG_ON(CONFIG_PAGING_LEVELS == 3) in the order-18 case would be useful, since otherwise it looks like order-18 allocations are exempt from the restriction.

Actually, I don't see where you enforce that - do you?

Tim.

Signature · 3 lines
Tim Deegan <[email protected]>
Principal Software Engineer, XenServer Engineering
Citrix Systems UK Ltd.  (Company #02937203, SL9 0BG)
Signature · 3 lines
Tim Deegan <[email protected]>
Principal Software Engineer, XenServer Engineering
Citrix Systems UK Ltd.  (Company #02937203, SL9 0BG)
#4 lore raw
Quoted 7 lines · Tim Deegan
Quoted 2 lines · Wei

I was hoping that someone else would pick up the 1GB PoD task. :P I can try to implement this feature if deemed necessary.

I think it will be OK - PoD is only useful with balloon drivers, which currently don't even maintain 2MB superpages, so it's probably not worth engineering up 1GB PoD.

Agreed. As long as everything still functions properly when PoD is turned on, not having 1G PoD entries shouldn't be a big priority.
-George