[PATCH v2 3/7] x86/altcall: Optimise away endbr64 instruction where possible

[Andrew Cooper <andrew.cooper3@xxxxxxxxxx>]

With altcall, we convert indirect branches into direct ones.  With that
complete, none of the potential targets need an endbr64 instruction.

Furthermore, removing the endbr64 instructions is a security defence-in-depth
improvement, because it limits the options available to an attacker who has
managed to hijack a function pointer.

Introduce new .init.{ro,}data.cf_clobber sections.  Have _apply_alternatives()
walk over this, looking for any pointers into .text, and clobber an endbr64
instruction if found.  This is some minor structure (ab)use but it works
alarmingly well.

Signed-off-by: Andrew Cooper <andrew.cooper3@xxxxxxxxxx>
---
CC: Jan Beulich <JBeulich@xxxxxxxx>
CC: Roger Pau Monné <roger.pau@xxxxxxxxxx>
CC: Wei Liu <wl@xxxxxxx>

It would be nice for the printk() to say "optimised away %u of %u", but the
latter number can only feasibly come from post-processing of xen-syms during
the build.

v2:
 * Drop hard tabs
 * Add __initconst_cf_clobber too
 * Change types to reduce casting
---
 xen/arch/x86/alternative.c | 38 ++++++++++++++++++++++++++++++++++++++
 xen/arch/x86/xen.lds.S     |  6 ++++++
 xen/include/xen/init.h     |  3 +++
 3 files changed, 47 insertions(+)

diff --git a/xen/arch/x86/alternative.c b/xen/arch/x86/alternative.c
index 65537fe1f0bd..dd4609070001 100644
--- a/xen/arch/x86/alternative.c
+++ b/xen/arch/x86/alternative.c
@@ -173,6 +173,9 @@ text_poke(void *addr, const void *opcode, size_t len)
     return memcpy(addr, opcode, len);
 }
 
+extern void *const __initdata_cf_clobber_start[];
+extern void *const __initdata_cf_clobber_end[];
+
 /*
  * Replace instructions with better alternatives for this CPU type.
  * This runs before SMP is initialized to avoid SMP problems with
@@ -330,6 +333,41 @@ static void init_or_livepatch _apply_alternatives(struct 
alt_instr *start,
         add_nops(buf + a->repl_len, total_len - a->repl_len);
         text_poke(orig, buf, total_len);
     }
+
+    /*
+     * Clobber endbr64 instructions now that altcall has finished optimising
+     * all indirect branches to direct ones.
+     */
+    if ( force && cpu_has_xen_ibt )
+    {
+        void *const *val;
+        unsigned int clobbered = 0;
+
+        /*
+         * This is some minor structure (ab)use.  We walk the entire contents
+         * of .init.{ro,}data.cf_clobber as if it were an array of pointers.
+         *
+         * If the pointer points into .text, and at an endbr64 instruction,
+         * nop out the endbr64.  This causes the pointer to no longer be a
+         * legal indirect branch target under CET-IBT.  This is a
+         * defence-in-depth measure, to reduce the options available to an
+         * adversary who has managed to hijack a function pointer.
+         */
+        for ( val = __initdata_cf_clobber_start;
+              val < __initdata_cf_clobber_end;
+              val++ )
+        {
+            void *ptr = *val;
+
+            if ( !is_kernel_text(ptr) || !is_endbr64(ptr) )
+                continue;
+
+            add_nops(ptr, 4);
+            clobbered++;
+        }
+
+        printk("altcall: Optimised away %u endbr64 instructions\n", clobbered);
+    }
 }
 
 void init_or_livepatch apply_alternatives(struct alt_instr *start,
diff --git a/xen/arch/x86/xen.lds.S b/xen/arch/x86/xen.lds.S
index ca22e984f807..c399178ac123 100644
--- a/xen/arch/x86/xen.lds.S
+++ b/xen/arch/x86/xen.lds.S
@@ -221,6 +221,12 @@ SECTIONS
        *(.initcall1.init)
        __initcall_end = .;
 
+       . = ALIGN(POINTER_ALIGN);
+       __initdata_cf_clobber_start = .;
+       *(.init.data.cf_clobber)
+       *(.init.rodata.cf_clobber)
+       __initdata_cf_clobber_end = .;
+
        *(.init.data)
        *(.init.data.rel)
        *(.init.data.rel.*)
diff --git a/xen/include/xen/init.h b/xen/include/xen/init.h
index bfe789e93f6b..0af0e234ec80 100644
--- a/xen/include/xen/init.h
+++ b/xen/include/xen/init.h
@@ -18,6 +18,9 @@
 #define __init_call(lvl)  __used_section(".initcall" lvl ".init")
 #define __exit_call       __used_section(".exitcall.exit")
 
+#define __initdata_cf_clobber  __section(".init.data.cf_clobber")
+#define __initconst_cf_clobber __section(".init.rodata.cf_clobber")
+
 /* These macros are used to mark some functions or 
  * initialized data (doesn't apply to uninitialized data)
  * as `initialization' functions. The kernel can take this
-- 
2.11.0