[xen staging-4.14] x86/CET: Fix S3 resume with shadow stacks active

[patchbot@xxxxxxx]

commit 1bb2a88f0cb9564bfd2fe546938aeffe3d7ee460
Author:     Andrew Cooper <andrew.cooper3@xxxxxxxxxx>
AuthorDate: Thu Feb 24 12:18:00 2022 +0000
Commit:     Andrew Cooper <andrew.cooper3@xxxxxxxxxx>
CommitDate: Fri Mar 25 17:11:55 2022 +0000

    x86/CET: Fix S3 resume with shadow stacks active
    
    The original shadow stack support has an error on S3 resume with very 
bizarre
    fallout.  The BSP comes back up, but APs fail with:
    
      (XEN) Enabling non-boot CPUs ...
      (XEN) Stuck ??
      (XEN) Error bringing CPU1 up: -5
    
    and then later (on at least two Intel TigerLake platforms), the next HVM 
vCPU
    to be scheduled on the BSP dies with:
    
      (XEN) d1v0 Unexpected vmexit: reason 3
      (XEN) domain_crash called from vmx.c:4304
      (XEN) Domain 1 (vcpu#0) crashed on cpu#0:
    
    The VMExit reason is EXIT_REASON_INIT, which has nothing to do with the
    scheduled vCPU, and will be addressed in a subsequent patch.  It is a
    consequence of the APs triple faulting.
    
    The reason the APs triple fault is because we don't tear down the stacks on
    suspend.  The idle/play_dead loop is killed in the middle of running, 
meaning
    that the supervisor token is left busy.
    
    On resume, SETSSBSY finds busy bit set, suffers #CP and triple faults 
because
    the IDT isn't configured this early.
    
    Rework the AP bring-up path to (re)create the supervisor token.  This 
ensures
    the primary stack is non-busy before use.
    
    Note: There are potential issues with the IST shadow stacks too, but fixing
          those is more involved.
    
    Fixes: b60ab42db2f0 ("x86/shstk: Activate Supervisor Shadow Stacks")
    Link: https://github.com/QubesOS/qubes-issues/issues/7283
    Reported-by: Thiner Logoer <logoerthiner1@xxxxxxx>
    Reported-by: Marek Marczykowski-Górecki <marmarek@xxxxxxxxxxxxxxxxxxxxxx>
    Signed-off-by: Andrew Cooper <andrew.cooper3@xxxxxxxxxx>
    Tested-by: Thiner Logoer <logoerthiner1@xxxxxxx>
    Tested-by: Marek Marczykowski-Górecki <marmarek@xxxxxxxxxxxxxxxxxxxxxx>
    Reviewed-by: Jan Beulich <jbeulich@xxxxxxxx>
    (cherry picked from commit 7d9589239ec068c944190408b9838774d5ec1f8f)
---
 xen/arch/x86/boot/x86_64.S | 18 +++++++++++++-----
 1 file changed, 13 insertions(+), 5 deletions(-)

diff --git a/xen/arch/x86/boot/x86_64.S b/xen/arch/x86/boot/x86_64.S
index 94b1d984cf..f11b5d0679 100644
--- a/xen/arch/x86/boot/x86_64.S
+++ b/xen/arch/x86/boot/x86_64.S
@@ -51,13 +51,21 @@ ENTRY(__high_start)
         test    $CET_SHSTK_EN, %al
         jz      .L_ap_cet_done
 
-        /* Derive MSR_PL0_SSP from %rsp (token written when stack is 
allocated). */
-        mov     $MSR_PL0_SSP, %ecx
+        /* Derive the supervisor token address from %rsp. */
         mov     %rsp, %rdx
+        and     $~(STACK_SIZE - 1), %rdx
+        or      $(PRIMARY_SHSTK_SLOT + 1) * PAGE_SIZE - 8, %rdx
+
+        /*
+         * Write a new supervisor token.  Doesn't matter on boot, but for S3
+         * resume this clears the busy bit.
+         */
+        wrssq   %rdx, (%rdx)
+
+        /* Point MSR_PL0_SSP at the token. */
+        mov     $MSR_PL0_SSP, %ecx
+        mov     %edx, %eax
         shr     $32, %rdx
-        mov     %esp, %eax
-        and     $~(STACK_SIZE - 1), %eax
-        or      $(PRIMARY_SHSTK_SLOT + 1) * PAGE_SIZE - 8, %eax
         wrmsr
 
         setssbsy
--
generated by git-patchbot for /home/xen/git/xen.git#staging-4.14