xen/x86: adjust handling of the L3 user vsyscall special page table

Marking the page tableas pinned without ever actually pinning is was
probably an oversight in the first place. The main reason for the change
is more subtle, though: The write of the one present entry each here and
in the subsequently allocated L2 table engage a code path in the
hypervisor which exists only for thought-to-be-broken guests: An mmu-
update operation to a page which is neither a page table nor marked
writable. The hypervisor merely assumes (or should I say "hopes") that
the fact that a writable reference to the page can be obtained means it
is okay to actually write to that page in response to such a hypercall.

While there make all involved code and data dependent upon
X86_VSYSCALL_EMULATION (some code was already).

Signed-off-by: Jan Beulich <jbeulich@suse.com>
Reviewed-by: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Link: https://lore.kernel.org/r/1048f5b8-b726-dcc1-1216-9d5ac328ce82@suse.com
Signed-off-by: Boris Ostrovsky <boris.ostrovsky@oracle.com>

diff --git a/arch/x86/xen/mmu_pv.c b/arch/x86/xen/mmu_pv.c
index ad0fbc7..325a679 100644 (file)
--- a/arch/x86/xen/mmu_pv.c
+++ b/arch/x86/xen/mmu_pv.c
@@ -86,8 +86,10 @@
 #include "mmu.h"
 #include "debugfs.h"
 
+#ifdef CONFIG_X86_VSYSCALL_EMULATION
 /* l3 pud for userspace vsyscall mapping */
 static pud_t level3_user_vsyscall[PTRS_PER_PUD] __page_aligned_bss;
+#endif
 
 /*
  * Protects atomic reservation decrease/increase against concurrent increases.
@@ -791,7 +793,9 @@ static void __init xen_mark_pinned(struct mm_struct *mm, struct page *page,
 static void __init xen_after_bootmem(void)
 {
        static_branch_enable(&xen_struct_pages_ready);
+#ifdef CONFIG_X86_VSYSCALL_EMULATION
        SetPagePinned(virt_to_page(level3_user_vsyscall));
+#endif
        xen_pgd_walk(&init_mm, xen_mark_pinned, FIXADDR_TOP);
 }
 
@@ -1762,7 +1766,6 @@ void __init xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn)
        set_page_prot(init_top_pgt, PAGE_KERNEL_RO);
        set_page_prot(level3_ident_pgt, PAGE_KERNEL_RO);
        set_page_prot(level3_kernel_pgt, PAGE_KERNEL_RO);
-       set_page_prot(level3_user_vsyscall, PAGE_KERNEL_RO);
        set_page_prot(level2_ident_pgt, PAGE_KERNEL_RO);
        set_page_prot(level2_kernel_pgt, PAGE_KERNEL_RO);
        set_page_prot(level2_fixmap_pgt, PAGE_KERNEL_RO);
@@ -1779,6 +1782,13 @@ void __init xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn)
        /* Unpin Xen-provided one */
        pin_pagetable_pfn(MMUEXT_UNPIN_TABLE, PFN_DOWN(__pa(pgd)));
 
+#ifdef CONFIG_X86_VSYSCALL_EMULATION
+       /* Pin user vsyscall L3 */
+       set_page_prot(level3_user_vsyscall, PAGE_KERNEL_RO);
+       pin_pagetable_pfn(MMUEXT_PIN_L3_TABLE,
+                         PFN_DOWN(__pa_symbol(level3_user_vsyscall)));
+#endif
+
        /*
         * At this stage there can be no user pgd, and no page structure to
         * attach it to, so make sure we just set kernel pgd.