[xen master] x86/PV32: restore PAE-extended-CR3 logic

[patchbot@xxxxxxx]

commit a773adedbd913966e812bddcd6b223c2e4ce3061
Author:     Jan Beulich <jbeulich@xxxxxxxx>
AuthorDate: Mon Feb 12 09:37:18 2024 +0100
Commit:     Jan Beulich <jbeulich@xxxxxxxx>
CommitDate: Mon Feb 12 09:37:18 2024 +0100

    x86/PV32: restore PAE-extended-CR3 logic
    
    While the PAE-extended-CR3 VM assist is a 32-bit only concept, it still
    applies to guests also when run on a 64-bit hypervisor: The "extended
    CR3" format has to be used there as well, to fit the address in the only
    32-bit wide register there. As a result it was a mistake that the check
    was never enabled for that case, and was then mistakenly deleted in the
    course of removal of 32-bit-Xen code (218adf199e68 ["x86: We can assume
    CONFIG_PAGING_LEVELS==4"]).
    
    Similarly during Dom0 construction kernel awareness needs to be taken
    into account, and respective code was again mistakenly never enabled for
    32-bit Dom0 when running on 64-bit Xen (and thus wrongly deleted by
    5d1181a5ea5e ["xen: Remove x86_32 build target"]).
    
    At the same time restrict enabling of the assist for Dom0 to just the
    32-bit case. Furthermore there's no need for an atomic update there.
    
    Signed-off-by: Jan Beulich <jbeulich@xxxxxxxx>
    Acked-by: Roger Pau Monné <roger.pau@xxxxxxxxxx>
---
 xen/arch/x86/mm.c            | 17 +++++++++++++++++
 xen/arch/x86/pv/dom0_build.c | 11 +++++++----
 2 files changed, 24 insertions(+), 4 deletions(-)

diff --git a/xen/arch/x86/mm.c b/xen/arch/x86/mm.c
index b56e0d8065..4d6d7bfe4f 100644
--- a/xen/arch/x86/mm.c
+++ b/xen/arch/x86/mm.c
@@ -1504,6 +1504,23 @@ static int promote_l3_table(struct page_info *page)
     unsigned int   partial_flags = page->partial_flags;
     l3_pgentry_t   l3e = l3e_empty();
 
+    /*
+     * PAE pgdirs above 4GB are unacceptable if a 32-bit guest does not
+     * understand the weird 'extended cr3' format for dealing with high-order
+     * address bits. We cut some slack for control tools (before vcpu0 is
+     * initialised).
+     */
+    if ( is_pv_32bit_domain(d) &&
+         unlikely(!VM_ASSIST(d, pae_extended_cr3)) &&
+         mfn_x(l3mfn) >= PFN_DOWN(GB(4)) &&
+         d->vcpu[0] && d->vcpu[0]->is_initialised )
+    {
+        gdprintk(XENLOG_WARNING,
+                 "PAE pgd must be below 4GB (%#lx >= 0x100000)",
+                 mfn_x(l3mfn));
+        return -ERANGE;
+    }
+
     pl3e = map_domain_page(l3mfn);
 
     /*
diff --git a/xen/arch/x86/pv/dom0_build.c b/xen/arch/x86/pv/dom0_build.c
index 5bbed3a36a..16d08c6796 100644
--- a/xen/arch/x86/pv/dom0_build.c
+++ b/xen/arch/x86/pv/dom0_build.c
@@ -495,12 +495,12 @@ int __init dom0_construct_pv(struct domain *d,
 
     nr_pages = dom0_compute_nr_pages(d, &parms, initrd_len);
 
-    if ( parms.pae == XEN_PAE_EXTCR3 )
-            set_bit(VMASST_TYPE_pae_extended_cr3, &d->vm_assist);
-
 #ifdef CONFIG_PV32
     if ( elf_32bit(&elf) )
     {
+        if ( parms.pae == XEN_PAE_EXTCR3 )
+            __set_bit(VMASST_TYPE_pae_extended_cr3, &d->vm_assist);
+
         if ( !pv_shim && (parms.virt_hv_start_low != UNSET_ADDR) )
         {
             unsigned long value = ROUNDUP(parms.virt_hv_start_low,
@@ -599,7 +599,10 @@ int __init dom0_construct_pv(struct domain *d,
         vphysmap_start = parms.p2m_base;
         vphysmap_end   = vphysmap_start + nr_pages * sizeof(unsigned long);
     }
-    page = alloc_domheap_pages(d, order, MEMF_no_scrub);
+    page = alloc_domheap_pages(d, order,
+                               MEMF_no_scrub |
+                               (VM_ASSIST(d, pae_extended_cr3) ||
+                                !compat ? 0 : MEMF_bits(32)));
     if ( page == NULL )
         panic("Not enough RAM for domain 0 allocation\n");
     alloc_spfn = mfn_x(page_to_mfn(page));
--
generated by git-patchbot for /home/xen/git/xen.git#master