[PATCH v4 10/14] xen/x86: populate PVHv2 Dom0 physical memory map

[Roger Pau Monne <roger.pau@citrix.com>]

Craft the Dom0 e820 memory map and populate it. Introduce a helper to remove
memory pages that are shared between Xen and a domain, and use it in order to
remove low 1MB RAM regions from dom_io in order to assign them to a PVHv2 Dom0.

Signed-off-by: Roger Pau Monné <roger.pau@citrix.com>
---
Cc: Jan Beulich <jbeulich@suse.com>
Cc: Andrew Cooper <andrew.cooper3@citrix.com>
---
Changes since v3:
 - Drop get_order_from_bytes_floor, it was only used by
   hvm_populate_memory_range.
 - Switch hvm_populate_memory_range to use frame numbers instead of full memory
   addresses.
 - Add a helper to steal the low 1MB RAM areas from dom_io and add them to Dom0
   as normal RAM.
 - Introduce unshare_xen_page_with_guest in order to remove pages from dom_io,
   so they can be assigned to other domains. This is needed in order to remove
   the low 1MB RAM regions from dom_io and assign them to the hardware_domain.
 - Simplify the loop in hvm_steal_ram.
 - Move definition of map_identity_mmio into this patch.

Changes since v2:
 - Introduce get_order_from_bytes_floor as a local function to
   domain_build.c.
 - Remove extra asserts.
 - Make hvm_populate_memory_range return an error code instead of panicking.
 - Fix comments and printks.
 - Use ULL sufix instead of casting to uint64_t.
 - Rename hvm_setup_vmx_unrestricted_guest to
   hvm_setup_vmx_realmode_helpers.
 - Only substract two pages from the memory calculation, that will be used
   by the MADT replacement.
 - Remove some comments.
 - Remove printing allocation information.
 - Don't stash any pages for the MADT, TSS or ident PT, those will be
   subtracted directly from RAM regions of the memory map.
 - Count the number of iterations before calling process_pending_softirqs
   when populating the memory map.
 - Move the initial call to process_pending_softirqs into construct_dom0,
   and remove the ones from construct_dom0_hvm and construct_dom0_pv.
 - Make memflags global so it can be shared between alloc_chunk and
   hvm_populate_memory_range.

Changes since RFC:
 - Use IS_ALIGNED instead of checking with PAGE_MASK.
 - Use the new %pB specifier in order to print sizes in human readable form.
 - Create a VM86 TSS for hardware that doesn't support unrestricted mode.
 - Subtract guest RAM for the identity page table and the VM86 TSS.
 - Split the creation of the unrestricted mode helper structures to a
   separate function.
 - Use preemption with paging_set_allocation.
 - Use get_order_from_bytes_floor.
---
 xen/arch/x86/domain_build.c | 310 ++++++++++++++++++++++++++++++++++++++++++--
 xen/arch/x86/mm.c           |  37 ++++++
 xen/include/asm-x86/mm.h    |   2 +
 3 files changed, 340 insertions(+), 9 deletions(-)

diff --git a/xen/arch/x86/domain_build.c b/xen/arch/x86/domain_build.c
index 2c9ebf2..8602566 100644
--- a/xen/arch/x86/domain_build.c
+++ b/xen/arch/x86/domain_build.c
@@ -22,6 +22,7 @@
 #include <xen/compat.h>
 #include <xen/libelf.h>
 #include <xen/pfn.h>
+#include <xen/guest_access.h>
 #include <asm/regs.h>
 #include <asm/system.h>
 #include <asm/io.h>
@@ -43,6 +44,9 @@ static long __initdata dom0_nrpages;
 static long __initdata dom0_min_nrpages;
 static long __initdata dom0_max_nrpages = LONG_MAX;
 
+/* Size of the VM86 TSS for virtual 8086 mode to use. */
+#define HVM_VM86_TSS_SIZE   128
+
 /*
  * dom0_mem=[min:<min_amt>,][max:<max_amt>,][<amt>]
  * 
@@ -213,11 +217,12 @@ boolean_param("ro-hpet", ro_hpet);
 #define round_pgup(_p)    (((_p)+(PAGE_SIZE-1))&PAGE_MASK)
 #define round_pgdown(_p)  ((_p)&PAGE_MASK)
 
+static unsigned int __initdata memflags = MEMF_no_dma|MEMF_exact_node;
+
 static struct page_info * __init alloc_chunk(
     struct domain *d, unsigned long max_pages)
 {
     static unsigned int __initdata last_order = MAX_ORDER;
-    static unsigned int __initdata memflags = MEMF_no_dma|MEMF_exact_node;
     struct page_info *page;
     unsigned int order = get_order_from_pages(max_pages), free_order;
 
@@ -302,7 +307,8 @@ static unsigned long __init compute_dom0_nr_pages(
             avail -= max_pdx >> s;
     }
 
-    need_paging = opt_dom0_shadow || (is_pvh_domain(d) && !iommu_hap_pt_share);
+    need_paging = opt_dom0_shadow || (has_hvm_container_domain(d) &&
+                  (!iommu_hap_pt_share || !paging_mode_hap(d)));
     for ( ; ; need_paging = 0 )
     {
         nr_pages = dom0_nrpages;
@@ -334,7 +340,8 @@ static unsigned long __init compute_dom0_nr_pages(
         avail -= dom0_paging_pages(d, nr_pages);
     }
 
-    if ( (parms->p2m_base == UNSET_ADDR) && (dom0_nrpages <= 0) &&
+    if ( is_pv_domain(d) &&
+         (parms->p2m_base == UNSET_ADDR) && (dom0_nrpages <= 0) &&
          ((dom0_min_nrpages <= 0) || (nr_pages > min_pages)) )
     {
         /*
@@ -545,11 +552,12 @@ static __init void pvh_map_all_iomem(struct domain *d, unsigned long nr_pages)
     ASSERT(nr_holes == 0);
 }
 
-static __init void pvh_setup_e820(struct domain *d, unsigned long nr_pages)
+static __init void hvm_setup_e820(struct domain *d, unsigned long nr_pages)
 {
     struct e820entry *entry, *entry_guest;
     unsigned int i;
     unsigned long pages, cur_pages = 0;
+    uint64_t start, end;
 
     /*
      * Craft the e820 memory map for Dom0 based on the hardware e820 map.
@@ -577,8 +585,19 @@ static __init void pvh_setup_e820(struct domain *d, unsigned long nr_pages)
             continue;
         }
 
-        *entry_guest = *entry;
-        pages = PFN_UP(entry_guest->size);
+        /*
+         * Make sure the start and length are aligned to PAGE_SIZE, because
+         * that's the minimum granularity of the 2nd stage translation.
+         */
+        start = ROUNDUP(entry->addr, PAGE_SIZE);
+        end = (entry->addr + entry->size) & PAGE_MASK;
+        if ( start >= end )
+            continue;
+
+        entry_guest->type = E820_RAM;
+        entry_guest->addr = start;
+        entry_guest->size = end - start;
+        pages = PFN_DOWN(entry_guest->size);
         if ( (cur_pages + pages) > nr_pages )
         {
             /* Truncate region */
@@ -1010,8 +1029,6 @@ static int __init construct_dom0_pv(
     BUG_ON(d->vcpu[0] == NULL);
     BUG_ON(v->is_initialised);
 
-    process_pending_softirqs();
-
     printk("*** LOADING DOMAIN 0 ***\n");
 
     d->max_pages = ~0U;
@@ -1637,7 +1654,7 @@ static int __init construct_dom0_pv(
         dom0_update_physmap(d, pfn, mfn, 0);
 
         pvh_map_all_iomem(d, nr_pages);
-        pvh_setup_e820(d, nr_pages);
+        hvm_setup_e820(d, nr_pages);
     }
 
     if ( d->domain_id == hardware_domid )
@@ -1653,15 +1670,289 @@ out:
     return rc;
 }
 
+static int __init modify_identity_mmio(struct domain *d, unsigned long pfn,
+                                       unsigned long nr_pages, bool map)
+{
+    int rc;
+
+    for ( ; ; )
+    {
+        rc = (map ? map_mmio_regions : unmap_mmio_regions)
+             (d, _gfn(pfn), nr_pages, _mfn(pfn));
+        if ( rc == 0 )
+            break;
+        if ( rc < 0 )
+        {
+            printk(XENLOG_WARNING
+                   "Failed to identity %smap [%#lx,%#lx) for d%d: %d\n",
+                   map ? "" : "un", pfn, pfn + nr_pages, d->domain_id, rc);
+            break;
+        }
+        nr_pages -= rc;
+        pfn += rc;
+        process_pending_softirqs();
+    }
+
+    return rc;
+}
+
+/* Populate an HVM memory range using the biggest possible order. */
+static int __init hvm_populate_memory_range(struct domain *d,
+                                            unsigned long start,
+                                            unsigned long nr_pages)
+{
+    unsigned int order, i = 0;
+    struct page_info *page;
+    int rc;
+#define MAP_MAX_ITER 64
+
+    order = MAX_ORDER;
+    while ( nr_pages != 0 )
+    {
+        unsigned int range_order = get_order_from_pages(nr_pages + 1);
+
+        order = min(range_order ? range_order - 1 : 0, order);
+        page = alloc_domheap_pages(d, order, memflags);
+        if ( page == NULL )
+        {
+            if ( order == 0 && memflags )
+            {
+                /* Try again without any memflags. */
+                memflags = 0;
+                order = MAX_ORDER;
+                continue;
+            }
+            if ( order == 0 )
+            {
+                printk("Unable to allocate memory with order 0!\n");
+                return -ENOMEM;
+            }
+            order--;
+            continue;
+        }
+
+        rc = guest_physmap_add_page(d, _gfn(start), _mfn(page_to_mfn(page)),
+                                    order);
+        if ( rc != 0 )
+        {
+            printk("Failed to populate memory: [%#lx,%lx): %d\n",
+                   start, start + (1UL << order), rc);
+            return -ENOMEM;
+        }
+        start += 1UL << order;
+        nr_pages -= 1UL << order;
+        if ( (++i % MAP_MAX_ITER) == 0 )
+            process_pending_softirqs();
+    }
+
+    return 0;
+#undef MAP_MAX_ITER
+}
+
+static int __init hvm_steal_ram(struct domain *d, unsigned long size,
+                                paddr_t limit, paddr_t *addr)
+{
+    unsigned int i = d->arch.nr_e820;
+
+    while ( i-- )
+    {
+        struct e820entry *entry = &d->arch.e820[i];
+
+        if ( entry->type != E820_RAM || entry->size < size )
+            continue;
+
+        /* Subtract from the beginning. */
+        if ( entry->addr + size < limit && entry->addr >= MB(1) )
+        {
+            *addr = entry->addr;
+            entry->addr += size;
+            entry->size -= size;
+            return 0;
+        }
+    }
+
+    return -ENOMEM;
+}
+
+static int __init hvm_setup_vmx_realmode_helpers(struct domain *d)
+{
+    p2m_type_t p2mt;
+    uint32_t rc, *ident_pt;
+    uint8_t *tss;
+    mfn_t mfn;
+    paddr_t gaddr;
+    unsigned int i;
+
+    /*
+     * Steal some space from the last found RAM region. One page will be
+     * used for the identity page tables, and the remaining space for the
+     * VM86 TSS. Note that after this not all e820 regions will be aligned
+     * to PAGE_SIZE.
+     */
+    if ( hvm_steal_ram(d, PAGE_SIZE + HVM_VM86_TSS_SIZE, ULONG_MAX, &gaddr) )
+    {
+        printk("Unable to find memory to stash the identity map and TSS\n");
+        return -ENOMEM;
+    }
+
+    /*
+     * Identity-map page table is required for running with CR0.PG=0
+     * when using Intel EPT. Create a 32-bit non-PAE page directory of
+     * superpages.
+     */
+    ident_pt = map_domain_gfn(p2m_get_hostp2m(d), _gfn(PFN_DOWN(gaddr)),
+                              &mfn, &p2mt, 0, &rc);
+    if ( ident_pt == NULL )
+    {
+        printk("Unable to map identity page tables\n");
+        return -ENOMEM;
+    }
+    for ( i = 0; i < PAGE_SIZE / sizeof(*ident_pt); i++ )
+        ident_pt[i] = ((i << 22) | _PAGE_PRESENT | _PAGE_RW | _PAGE_USER |
+                       _PAGE_ACCESSED | _PAGE_DIRTY | _PAGE_PSE);
+    unmap_domain_page(ident_pt);
+    put_page(mfn_to_page(mfn_x(mfn)));
+    d->arch.hvm_domain.params[HVM_PARAM_IDENT_PT] = gaddr;
+    gaddr += PAGE_SIZE;
+    ASSERT(IS_ALIGNED(gaddr, PAGE_SIZE));
+
+    tss = map_domain_gfn(p2m_get_hostp2m(d), _gfn(PFN_DOWN(gaddr)),
+                         &mfn, &p2mt, 0, &rc);
+    if ( tss == NULL )
+    {
+        printk("Unable to map VM86 TSS area\n");
+        return 0;
+    }
+
+    memset(tss, 0, HVM_VM86_TSS_SIZE);
+    unmap_domain_page(tss);
+    put_page(mfn_to_page(mfn_x(mfn)));
+    d->arch.hvm_domain.params[HVM_PARAM_VM86_TSS] = gaddr;
+
+    return 0;
+}
+
+static void __init hvm_steal_low_ram(struct domain *d, unsigned long start,
+                                     unsigned long nr_pages)
+{
+    unsigned long mfn;
+
+    ASSERT(start + nr_pages < PFN_DOWN(MB(1)));
+
+    for ( mfn = start; mfn < start + nr_pages; mfn++ )
+    {
+        struct page_info *pg = mfn_to_page(mfn);
+        int rc;
+
+        rc = unshare_xen_page_with_guest(pg, dom_io);
+        if ( rc )
+        {
+            printk("Unable to unshare Xen mfn %#lx: %d\n", mfn, rc);
+            continue;
+        }
+
+        share_xen_page_with_guest(pg, d, XENSHARE_writable);
+        rc = guest_physmap_add_entry(d, _gfn(mfn), _mfn(mfn), 0, p2m_ram_rw);
+        if ( rc )
+            printk("Unable to add mfn %#lx to p2m: %d\n", mfn, rc);
+    }
+}
+
+static int __init hvm_setup_p2m(struct domain *d)
+{
+    struct vcpu *v = d->vcpu[0];
+    unsigned long nr_pages;
+    unsigned int i;
+    int rc;
+    bool preempted;
+#define MB1_PAGES PFN_DOWN(MB(1))
+
+    nr_pages = compute_dom0_nr_pages(d, NULL, 0);
+
+    hvm_setup_e820(d, nr_pages);
+    do {
+        preempted = false;
+        paging_set_allocation(d, dom0_paging_pages(d, nr_pages),
+                              &preempted);
+        process_pending_softirqs();
+    } while ( preempted );
+
+    /*
+     * Memory below 1MB is identity mapped.
+     * NB: this only makes sense when booted from legacy BIOS.
+     */
+    rc = modify_identity_mmio(d, 0, PFN_DOWN(MB(1)), true);
+    if ( rc )
+    {
+        printk("Failed to identity map low 1MB: %d\n", rc);
+        return rc;
+    }
+
+    /* Populate memory map. */
+    for ( i = 0; i < d->arch.nr_e820; i++ )
+    {
+        unsigned long addr, size;
+
+        if ( d->arch.e820[i].type != E820_RAM )
+            continue;
+
+        addr = PFN_DOWN(d->arch.e820[i].addr);
+        size = PFN_DOWN(d->arch.e820[i].size);
+
+        if ( addr >= MB1_PAGES )
+            rc = hvm_populate_memory_range(d, addr, size);
+        else if ( addr + size > MB1_PAGES )
+        {
+            hvm_steal_low_ram(d, addr, MB1_PAGES - addr);
+            rc = hvm_populate_memory_range(d, MB1_PAGES,
+                                           size - (MB1_PAGES - addr));
+        }
+        else
+            hvm_steal_low_ram(d, addr, size);
+
+        if ( rc )
+            return rc;
+    }
+
+    if ( cpu_has_vmx && paging_mode_hap(d) && !vmx_unrestricted_guest(v) )
+    {
+        /*
+         * Since Dom0 cannot be migrated, we will only setup the
+         * unrestricted guest helpers if they are needed by the current
+         * hardware we are running on.
+         */
+        rc = hvm_setup_vmx_realmode_helpers(d);
+        if ( rc )
+            return rc;
+    }
+
+    return 0;
+#undef MB1_PAGES
+}
+
 static int __init construct_dom0_hvm(struct domain *d, const module_t *image,
                                      unsigned long image_headroom,
                                      module_t *initrd,
                                      void *(*bootstrap_map)(const module_t *),
                                      char *cmdline)
 {
+    int rc;
 
     printk("** Building a PVH Dom0 **\n");
 
+    /* Sanity! */
+    BUG_ON(d->domain_id);
+    BUG_ON(!d->vcpu[0]);
+
+    iommu_hwdom_init(d);
+
+    rc = hvm_setup_p2m(d);
+    if ( rc )
+    {
+        printk("Failed to setup Dom0 physical memory map\n");
+        return rc;
+    }
+
     return 0;
 }
 
@@ -1670,6 +1961,7 @@ int __init construct_dom0(struct domain *d, const module_t *image,
                           void *(*bootstrap_map)(const module_t *),
                           char *cmdline)
 {
+    process_pending_softirqs();
 
     return (is_hvm_domain(d) ? construct_dom0_hvm : construct_dom0_pv)
            (d, image, image_headroom, initrd,bootstrap_map, cmdline);
diff --git a/xen/arch/x86/mm.c b/xen/arch/x86/mm.c
index 03dcd71..a31106c 100644
--- a/xen/arch/x86/mm.c
+++ b/xen/arch/x86/mm.c
@@ -475,6 +475,43 @@ void share_xen_page_with_guest(
     spin_unlock(&d->page_alloc_lock);
 }
 
+int unshare_xen_page_with_guest(struct page_info *page, struct domain *d)
+{
+    unsigned long y, x;
+    bool drop_dom_ref;
+
+    if ( page_get_owner(page) != d || !(page->count_info & PGC_xen_heap) )
+        return -EINVAL;
+
+    spin_lock(&d->page_alloc_lock);
+
+    /* Drop the page reference so we can chanfge the owner. */
+    y = page->count_info;
+    do {
+        x = y;
+        if ( (x & (PGC_count_mask|PGC_allocated)) != (1 | PGC_allocated) )
+        {
+            spin_unlock(&d->page_alloc_lock);
+            return -EINVAL;
+        }
+        y = cmpxchg(&page->count_info, x, PGC_xen_heap);
+    } while ( y != x );
+
+    /* Remove the page form the list of domain pages. */
+    page_list_del(page, &d->xenpage_list);
+    drop_dom_ref = (--d->xenheap_pages == 0);
+
+    /* Remove the owner and clear the flags. */
+    page_set_owner(page, NULL);
+    page->u.inuse.type_info = 0;
+    spin_unlock(&d->page_alloc_lock);
+
+    if ( drop_dom_ref )
+        put_domain(d);
+
+    return 0;
+}
+
 void share_xen_page_with_privileged_guests(
     struct page_info *page, int readonly)
 {
diff --git a/xen/include/asm-x86/mm.h b/xen/include/asm-x86/mm.h
index 1b4d1c3..041692b 100644
--- a/xen/include/asm-x86/mm.h
+++ b/xen/include/asm-x86/mm.h
@@ -276,6 +276,8 @@ struct spage_info
 #define XENSHARE_readonly 1
 extern void share_xen_page_with_guest(
     struct page_info *page, struct domain *d, int readonly);
+extern int unshare_xen_page_with_guest(struct page_info *page,
+                                       struct domain *d);
 extern void share_xen_page_with_privileged_guests(
     struct page_info *page, int readonly);
 extern void free_shared_domheap_page(struct page_info *page);
-- 
2.9.3 (Apple Git-75)


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