x86/boot: Fix load_system_tables() to be NMI/#MC-safe

During boot, load_system_tables() is used in reinit_bsp_stack() to switch the
virtual addresses used from their .data/.bss alias, to their directmap alias.

The structure assignment is implemented as a memset() to zero first, then a
copy-in of the new data.  This causes the NMI/#MC stack pointers to
transiently become 0, at a point where we may have an NMI watchdog running.

Rewrite the logic using a volatile tss pointer (equivalent to, but more
readable than, using ACCESS_ONCE() for all writes).

This does drop the zeroing side effect for holes in the structure, but the
backing memory for the TSS is fully zeroed anyway, and architecturally, they
are all reserved.

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

diff --git a/xen/arch/x86/cpu/common.c b/xen/arch/x86/cpu/common.c
index c413188d00b9fa0b832513d34b9fa8bf9affe9f9..09b911b3ba62f72c0a4d094c51db0956deab12f7 100644 (file)
--- a/xen/arch/x86/cpu/common.c
+++ b/xen/arch/x86/cpu/common.c
@@ -730,11 +730,12 @@ static cpumask_t cpu_initialized;
  */
 void load_system_tables(void)
 {
-       unsigned int cpu = smp_processor_id();
+       unsigned int i, cpu = smp_processor_id();
        unsigned long stack_bottom = get_stack_bottom(),
                stack_top = stack_bottom & ~(STACK_SIZE - 1);
 
-       struct tss64 *tss = &this_cpu(tss_page).tss;
+       /* The TSS may be live.  Disuade any clever optimisations. */
+       volatile struct tss64 *tss = &this_cpu(tss_page).tss;
        seg_desc_t *gdt =
                this_cpu(gdt) - FIRST_RESERVED_GDT_ENTRY;
 
@@ -747,30 +748,26 @@ void load_system_tables(void)
                .limit = (IDT_ENTRIES * sizeof(idt_entry_t)) - 1,
        };
 
-       *tss = (struct tss64){
-               /* Main stack for interrupts/exceptions. */
-               .rsp0 = stack_bottom,
-
-               /* Ring 1 and 2 stacks poisoned. */
-               .rsp1 = 0x8600111111111111ul,
-               .rsp2 = 0x8600111111111111ul,
-
-               /*
-                * MCE, NMI and Double Fault handlers get their own stacks.
-                * All others poisoned.
-                */
-               .ist = {
-                       [IST_MCE - 1] = stack_top + IST_MCE * PAGE_SIZE,
-                       [IST_DF  - 1] = stack_top + IST_DF  * PAGE_SIZE,
-                       [IST_NMI - 1] = stack_top + IST_NMI * PAGE_SIZE,
-                       [IST_DB  - 1] = stack_top + IST_DB  * PAGE_SIZE,
-
-                       [IST_MAX ... ARRAY_SIZE(tss->ist) - 1] =
-                               0x8600111111111111ul,
-               },
-
-               .bitmap = IOBMP_INVALID_OFFSET,
-       };
+       /*
+        * Set up the TSS.  Warning - may be live, and the NMI/#MC must remain
+        * valid on every instruction boundary.  (Note: these are all
+        * semantically ACCESS_ONCE() due to tss's volatile qualifier.)
+        *
+        * rsp0 refers to the primary stack.  #MC, #DF, NMI and #DB handlers
+        * each get their own stacks.  No IO Bitmap.
+        */
+       tss->rsp0 = stack_bottom;
+       tss->ist[IST_MCE - 1] = stack_top + IST_MCE * PAGE_SIZE;
+       tss->ist[IST_DF  - 1] = stack_top + IST_DF  * PAGE_SIZE;
+       tss->ist[IST_NMI - 1] = stack_top + IST_NMI * PAGE_SIZE;
+       tss->ist[IST_DB  - 1] = stack_top + IST_DB  * PAGE_SIZE;
+       tss->bitmap = IOBMP_INVALID_OFFSET;
+
+       /* All other stack pointers poisioned. */
+       for ( i = IST_MAX; i < ARRAY_SIZE(tss->ist); ++i )
+               tss->ist[i] = 0x8600111111111111ul;
+       tss->rsp1 = 0x8600111111111111ul;
+       tss->rsp2 = 0x8600111111111111ul;
 
        BUILD_BUG_ON(sizeof(*tss) <= 0x67); /* Mandated by the architecture. */