x86/xpti: Hide almost all of .text and all .data/.rodata/.bss mappings

The current XPTI implementation isolates the directmap (and therefore a lot of
guest data), but a large quantity of CPU0's state (including its stack)
remains visible.

Furthermore, an attacker able to read .text is in a vastly superior position
to normal when it comes to fingerprinting Xen for known vulnerabilities, or
scanning for ROP/Spectre gadgets.

Collect together the entrypoints in .text.entry (currently 3x4k frames, but
can almost certainly be slimmed down), and create a common mapping which is
inserted into each per-cpu shadow.  The stubs are also inserted into this
mapping by pointing at the in-use L2.  This allows stubs allocated later (SMP
boot, or CPU hotplug) to work without further changes to the common mappings.

Signed-off-by: Andrew Cooper <andrew.cooper3@citrix.com>
Reviewed-by: Jan Beulich <jbeulich@suse.com>

docs/misc/xen-command-line.markdown

@@ -1935,9 +1935,6 @@ mode.
 Override default selection of whether to isolate 64-bit PV guest page
 tables.
 
-** WARNING: Not yet a complete isolation implementation, but better than
-nothing. **
-
 ### xsave
 > `= <boolean>`
 

xen/arch/x86/smpboot.c

@@ -622,6 +622,9 @@ unsigned long alloc_stub_page(unsigned int cpu, unsigned long *mfn)
         unmap_domain_page(memset(__map_domain_page(pg), 0xcc, PAGE_SIZE));
     }
 
+    /* Confirm that all stubs fit in a single L3 entry. */
+    BUILD_BUG_ON(NR_CPUS * PAGE_SIZE > (1u << L3_PAGETABLE_SHIFT));
+
     stub_va = XEN_VIRT_END - (cpu + 1) * PAGE_SIZE;
     if ( map_pages_to_xen(stub_va, mfn_x(page_to_mfn(pg)), 1,
                           PAGE_HYPERVISOR_RX | MAP_SMALL_PAGES) )
@@ -646,13 +649,24 @@ static int clone_mapping(const void *ptr, root_pgentry_t *rpt)
 {
     unsigned long linear = (unsigned long)ptr, pfn;
     unsigned int flags;
-    l3_pgentry_t *pl3e = l4e_to_l3e(idle_pg_table[root_table_offset(linear)]) +
-                         l3_table_offset(linear);
+    l3_pgentry_t *pl3e;
     l2_pgentry_t *pl2e;
     l1_pgentry_t *pl1e;
 
-    if ( linear < DIRECTMAP_VIRT_START )
-        return 0;
+    /*
+     * Sanity check 'linear'.  We only allow cloning from the Xen virtual
+     * range, and in particular, only from the directmap and .text ranges.
+     */
+    if ( root_table_offset(linear) > ROOT_PAGETABLE_LAST_XEN_SLOT ||
+         root_table_offset(linear) < ROOT_PAGETABLE_FIRST_XEN_SLOT )
+        return -EINVAL;
+
+    if ( linear < XEN_VIRT_START ||
+         (linear >= XEN_VIRT_END && linear < DIRECTMAP_VIRT_START) )
+        return -EINVAL;
+
+    pl3e = l4e_to_l3e(idle_pg_table[root_table_offset(linear)]) +
+        l3_table_offset(linear);
 
     flags = l3e_get_flags(*pl3e);
     ASSERT(flags & _PAGE_PRESENT);
@@ -744,8 +758,12 @@ static __read_mostly int8_t opt_xpti = -1;
 boolean_param("xpti", opt_xpti);
 DEFINE_PER_CPU(root_pgentry_t *, root_pgt);
 
+extern const char _stextentry[], _etextentry[];
+
 static int setup_cpu_root_pgt(unsigned int cpu)
 {
+    static root_pgentry_t common_pgt;
+
     root_pgentry_t *rpt;
     unsigned int off;
     int rc;
@@ -764,8 +782,35 @@ static int setup_cpu_root_pgt(unsigned int cpu)
         idle_pg_table[root_table_offset(RO_MPT_VIRT_START)];
     /* SH_LINEAR_PT inserted together with guest mappings. */
     /* PERDOMAIN inserted during context switch. */
-    rpt[root_table_offset(XEN_VIRT_START)] =
-        idle_pg_table[root_table_offset(XEN_VIRT_START)];
+
+    /* One-time setup of common_pgt, which maps .text.entry and the stubs. */
+    if ( unlikely(!root_get_intpte(common_pgt)) )
+    {
+        unsigned long stubs_linear = XEN_VIRT_END - 1;
+        l3_pgentry_t *stubs_main, *stubs_shadow;
+        const char *ptr;
+
+        for ( rc = 0, ptr = _stextentry;
+              !rc && ptr < _etextentry; ptr += PAGE_SIZE )
+            rc = clone_mapping(ptr, rpt);
+
+        if ( rc )
+            return rc;
+
+        /* Confirm that all stubs fit in a single L3 entry. */
+        BUILD_BUG_ON(NR_CPUS * PAGE_SIZE > (1u << L3_PAGETABLE_SHIFT));
+
+        stubs_main = l4e_to_l3e(idle_pg_table[l4_table_offset(stubs_linear)]);
+        stubs_shadow = l4e_to_l3e(rpt[l4_table_offset(stubs_linear)]);
+
+        /* Splice into the regular L2 mapping the stubs. */
+        stubs_shadow[l3_table_offset(stubs_linear)] =
+            stubs_main[l3_table_offset(stubs_linear)];
+
+        common_pgt = rpt[root_table_offset(XEN_VIRT_START)];
+    }
+
+    rpt[root_table_offset(XEN_VIRT_START)] = common_pgt;
 
     /* Install direct map page table entries for stack, IDT, and TSS. */
     for ( off = rc = 0; !rc && off < STACK_SIZE; off += PAGE_SIZE )

xen/arch/x86/x86_64/compat/entry.S

@@ -13,6 +13,8 @@
 #include <public/xen.h>
 #include <irq_vectors.h>
 
+        .section .text.entry, "ax", @progbits
+
 ENTRY(entry_int82)
         ASM_CLAC
         pushq $0
@@ -270,6 +272,9 @@ ENTRY(compat_int80_direct_trap)
         call  compat_create_bounce_frame
         jmp   compat_test_all_events
 
+        /* compat_create_bounce_frame & helpers don't need to be in .text.entry */
+        .text
+
 /* CREATE A BASIC EXCEPTION FRAME ON GUEST OS (RING-1) STACK:            */
 /*   {[ERRCODE,] EIP, CS, EFLAGS, [ESP, SS]}                             */
 /* %rdx: trap_bounce, %rbx: struct vcpu                                  */

xen/arch/x86/x86_64/entry.S

@@ -14,6 +14,8 @@
 #include <public/xen.h>
 #include <irq_vectors.h>
 
+        .section .text.entry, "ax", @progbits
+
 /* %rbx: struct vcpu */
 ENTRY(switch_to_kernel)
         leaq  VCPU_trap_bounce(%rbx),%rdx
@@ -357,6 +359,9 @@ int80_slow_path:
         subq  $2,UREGS_rip(%rsp)
         jmp   handle_exception_saved
 
+        /* create_bounce_frame & helpers don't need to be in .text.entry */
+        .text
+
 /* CREATE A BASIC EXCEPTION FRAME ON GUEST OS STACK:                     */
 /*   { RCX, R11, [ERRCODE,] RIP, CS, RFLAGS, RSP, SS }                   */
 /* %rdx: trap_bounce, %rbx: struct vcpu                                  */
@@ -487,6 +492,8 @@ ENTRY(dom_crash_sync_extable)
         jmp   asm_domain_crash_synchronous /* Does not return */
         .popsection
 
+        .section .text.entry, "ax", @progbits
+
 ENTRY(common_interrupt)
         SAVE_ALL CLAC
 
@@ -845,7 +852,7 @@ GLOBAL(trap_nop)
         iretq
 
 /* Table of automatically generated entry points.  One per vector. */
-        .section .init.rodata, "a", @progbits
+        .pushsection .init.rodata, "a", @progbits
 GLOBAL(autogen_entrypoints)
         /* pop into the .init.rodata section and record an entry point. */
         .macro entrypoint ent
@@ -854,7 +861,7 @@ GLOBAL(autogen_entrypoints)
         .popsection
         .endm
 
-        .text
+        .popsection
 autogen_stubs: /* Automatically generated stubs. */
 
         vec = 0

xen/arch/x86/xen.lds.S

@@ -67,6 +67,13 @@ SECTIONS
        *(.text)
        *(.text.__x86_indirect_thunk_*)
        *(.text.page_aligned)
+
+       . = ALIGN(PAGE_SIZE);
+       _stextentry = .;
+       *(.text.entry)
+       . = ALIGN(PAGE_SIZE);
+       _etextentry = .;
+
        *(.text.cold)
        *(.text.unlikely)
        *(.fixup)