x86/cet: Remove writeable mapping of the BSPs shadow stack

An unintended consequence of the BSP using cpu0_stack[] is that writeable
mappings to the BSPs shadow stacks are retained in the bss.  This renders
CET-SS almost useless, as an attacker can update both return addresses and the
ret will not fault.

We specifically don't want to shatter the superpage mapping .data and .bss, so
the only way to fix this is to not have the BSP stack in the main Xen image.

Break cpu_alloc_stack() out of cpu_smpboot_alloc(), and dynamically allocate
the BSP stack as early as reasonable in __start_xen().  As a consequence,
there is no need to delay the BSP's memguard_guard_stack() call.

Copy the top of cpu info block just before switching to use the new stack.
Fix a latent bug by setting %rsp to info->guest_cpu_user_regs rather than
->es; this would be buggy if reinit_bsp_stack() called schedule() (which
rewrites the GPR block) directly, but luckily it doesn't.

Finally, move cpu0_stack[] into .init, so it can be reclaimed after boot.

Signed-off-by: Andrew Cooper <andrew.cooper3@citrix.com>
Reviewed-by: Jan Beulich <jbeulich@suse.com>
(cherry picked from commit 37786b23b027ab83051175cb8ce9ac86cacfc58e)

diff --git a/xen/arch/x86/setup.c b/xen/arch/x86/setup.c
index 9e5ccebbab1bce0d5d001e3a4dcbb15b0b3bf99b..70b37d8afeae2a9b3ebd0c321b4d38e2db1954d8 100644 (file)
--- a/xen/arch/x86/setup.c
+++ b/xen/arch/x86/setup.c
@@ -152,7 +152,7 @@ unsigned long __read_mostly xen_phys_start;
 
 unsigned long __read_mostly xen_virt_end;
 
-char __section(".bss.stack_aligned") __aligned(STACK_SIZE)
+char __section(".init.bss.stack_aligned") __aligned(STACK_SIZE)
     cpu0_stack[STACK_SIZE];
 
 struct cpuinfo_x86 __read_mostly boot_cpu_data = { 0, 0, 0, 0, -1 };
@@ -704,7 +704,6 @@ static void __init noreturn reinit_bsp_stack(void)
     percpu_traps_init();
 
     stack_base[0] = stack;
-    memguard_guard_stack(stack);
 
     rc = setup_cpu_root_pgt(0);
     if ( rc )
@@ -871,6 +870,8 @@ void __init noreturn __start_xen(unsigned long mbi_p)
 {
     char *memmap_type = NULL;
     char *cmdline, *kextra, *loader;
+    void *bsp_stack;
+    struct cpu_info *info = get_cpu_info(), *bsp_info;
     unsigned int initrdidx, num_parked = 0;
     multiboot_info_t *mbi;
     module_t *mod;
@@ -903,7 +904,7 @@ void __init noreturn __start_xen(unsigned long mbi_p)
     /* Full exception support from here on in. */
 
     rdmsrl(MSR_EFER, this_cpu(efer));
-    asm volatile ( "mov %%cr4,%0" : "=r" (get_cpu_info()->cr4) );
+    asm volatile ( "mov %%cr4,%0" : "=r" (info->cr4) );
 
     /* Enable NMIs.  Our loader (e.g. Tboot) may have left them disabled. */
     enable_nmis();
@@ -1733,6 +1734,10 @@ void __init noreturn __start_xen(unsigned long mbi_p)
      */
     vm_init();
 
+    bsp_stack = cpu_alloc_stack(0);
+    if ( !bsp_stack )
+        panic("No memory for BSP stack\n");
+
     console_init_ring();
     vesa_init();
 
@@ -1991,17 +1996,18 @@ void __init noreturn __start_xen(unsigned long mbi_p)
 
     if ( bsp_delay_spec_ctrl )
     {
-        struct cpu_info *info = get_cpu_info();
-
         info->spec_ctrl_flags &= ~SCF_use_shadow;
         barrier();
         wrmsrl(MSR_SPEC_CTRL, default_xen_spec_ctrl);
         info->last_spec_ctrl = default_xen_spec_ctrl;
     }
 
-    /* Jump to the 1:1 virtual mappings of cpu0_stack. */
+    /* Copy the cpu info block, and move onto the BSP stack. */
+    bsp_info = get_cpu_info_from_stack((unsigned long)bsp_stack);
+    *bsp_info = *info;
+
     asm volatile ("mov %[stk], %%rsp; jmp %c[fn]" ::
-                  [stk] "g" (__va(__pa(get_stack_bottom()))),
+                  [stk] "g" (&bsp_info->guest_cpu_user_regs),
                   [fn] "i" (reinit_bsp_stack) : "memory");
     unreachable();
 }

diff --git a/xen/arch/x86/smpboot.c b/xen/arch/x86/smpboot.c
index 2596e4374b69f8debb3b44239d9d3b0a5292eeee..0694173173b1d6c007e3026f24fe5c9f53e9d335 100644 (file)
--- a/xen/arch/x86/smpboot.c
+++ b/xen/arch/x86/smpboot.c
@@ -1024,6 +1024,23 @@ static void cpu_smpboot_free(unsigned int cpu, bool remove)
     }
 }
 
+void *cpu_alloc_stack(unsigned int cpu)
+{
+    nodeid_t node = cpu_to_node(cpu);
+    unsigned int memflags = 0;
+    void *stack;
+
+    if ( node != NUMA_NO_NODE )
+        memflags = MEMF_node(node);
+
+    stack = alloc_xenheap_pages(STACK_ORDER, memflags);
+
+    if ( stack )
+        memguard_guard_stack(stack);
+
+    return stack;
+}
+
 static int cpu_smpboot_alloc(unsigned int cpu)
 {
     struct cpu_info *info;
@@ -1036,15 +1053,10 @@ static int cpu_smpboot_alloc(unsigned int cpu)
     if ( node != NUMA_NO_NODE )
         memflags = MEMF_node(node);
 
-    if ( stack_base[cpu] == NULL )
-    {
-        stack_base[cpu] = alloc_xenheap_pages(STACK_ORDER, memflags);
-        if ( !stack_base[cpu] )
+    if ( stack_base[cpu] == NULL &&
+         (stack_base[cpu] = cpu_alloc_stack(cpu)) == NULL )
             goto out;
 
-        memguard_guard_stack(stack_base[cpu]);
-    }
-
     info = get_cpu_info_from_stack((unsigned long)stack_base[cpu]);
     info->processor_id = cpu;
     info->per_cpu_offset = __per_cpu_offset[cpu];

diff --git a/xen/arch/x86/xen.lds.S b/xen/arch/x86/xen.lds.S
index 87e344d4dd9721eed7273057927d3f58c7398308..4c58f3209c3d1cbde9bb6cc33257c5996cb02fa5 100644 (file)
--- a/xen/arch/x86/xen.lds.S
+++ b/xen/arch/x86/xen.lds.S
@@ -199,6 +199,7 @@ SECTIONS
   } PHDR(text)
   DECL_SECTION(.init.data) {
 #endif
+       *(.init.bss.stack_aligned)
 
        *(.init.rodata)
        *(.init.rodata.*)
@@ -280,7 +281,6 @@ SECTIONS
 
   DECL_SECTION(.bss) {
        __bss_start = .;
-       *(.bss.stack_aligned)
        *(.bss.page_aligned*)
        . = ALIGN(PAGE_SIZE);
        __per_cpu_start = .;

diff --git a/xen/include/asm-x86/smp.h b/xen/include/asm-x86/smp.h
index f7485f602efa908a6c30ee31cb3bdbd8d3a60b6a..9628d7842d0a5489439506813553cd5d81277d0d 100644 (file)
--- a/xen/include/asm-x86/smp.h
+++ b/xen/include/asm-x86/smp.h
@@ -85,6 +85,8 @@ extern cpumask_t **socket_cpumask;
 extern unsigned int disabled_cpus;
 extern bool unaccounted_cpus;
 
+void *cpu_alloc_stack(unsigned int cpu);
+
 #endif /* !__ASSEMBLY__ */
 
 #endif