[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

[xen stable-4.17] x86/amd: fix legacy setting of SSBD on AMD Family 17h



commit 66c930ceac3989b6dc6031bfc30e1e894fc6aebe
Author:     Roger Pau Monné <roger.pau@xxxxxxxxxx>
AuthorDate: Tue May 16 17:22:35 2023 +0200
Commit:     Jan Beulich <jbeulich@xxxxxxxx>
CommitDate: Tue May 16 17:22:35 2023 +0200

    x86/amd: fix legacy setting of SSBD on AMD Family 17h
    
    The current logic to set SSBD on AMD Family 17h and Hygon Family 18h
    processors requires that the setting of SSBD is coordinated at a core
    level, as the setting is shared between threads.  Logic was introduced
    to keep track of how many threads require SSBD active in order to
    coordinate it, such logic relies on using a per-core counter of
    threads that have SSBD active.
    
    Given the current logic, it's possible for a guest to under or
    overflow the thread counter, because each write to VIRT_SPEC_CTRL.SSBD
    by the guest gets propagated to the helper that does the per-core
    active accounting.  Overflowing the counter is not so much of an
    issue, as this would just make SSBD sticky.
    
    Underflowing however is more problematic: on non-debug Xen builds a
    guest can perform empty writes to VIRT_SPEC_CTRL that would cause the
    counter to underflow and thus the value gets saturated to the max
    value of unsigned int.  At which points attempts from any thread to
    set VIRT_SPEC_CTRL.SSBD won't get propagated to the hardware anymore,
    because the logic will see that the counter is greater than 1 and
    assume that SSBD is already active, effectively loosing the setting
    of SSBD and the protection it provides.
    
    Fix this by introducing a per-CPU variable that keeps track of whether
    the current thread has legacy SSBD active or not, and thus only
    attempt to propagate the value to the hardware once the thread
    selected value changes.
    
    This is XSA-431 / CVE-2022-42336
    
    Fixes: b2030e6730a2 ('amd/virt_ssbd: set SSBD at vCPU context switch')
    Reported-by: Andrew Cooper <andrew.cooper3@xxxxxxxxxx>
    Signed-off-by: Roger Pau Monné <roger.pau@xxxxxxxxxx>
    Reviewed-by: Jan Beulich <jbeulich@xxxxxxxx>
    master commit: eda98ea870803ea204a1928519b3f21ec6a679b6
    master date: 2023-05-16 17:17:24 +0200
---
 xen/arch/x86/cpu/amd.c | 16 ++++++++++++++++
 1 file changed, 16 insertions(+)

diff --git a/xen/arch/x86/cpu/amd.c b/xen/arch/x86/cpu/amd.c
index 1ddb55cbe5..b6a20d375a 100644
--- a/xen/arch/x86/cpu/amd.c
+++ b/xen/arch/x86/cpu/amd.c
@@ -783,12 +783,23 @@ bool __init amd_setup_legacy_ssbd(void)
        return true;
 }
 
+/*
+ * legacy_ssbd is always initialized to false because when SSBD is set
+ * from the command line guest attempts to change it are a no-op (see
+ * amd_set_legacy_ssbd()), whereas when SSBD is inactive hardware will
+ * be forced into that mode (see amd_init_ssbd()).
+ */
+static DEFINE_PER_CPU(bool, legacy_ssbd);
+
+/* Must be called only when the SSBD setting needs toggling. */
 static void core_set_legacy_ssbd(bool enable)
 {
        const struct cpuinfo_x86 *c = &current_cpu_data;
        struct ssbd_ls_cfg *status;
        unsigned long flags;
 
+       BUG_ON(this_cpu(legacy_ssbd) == enable);
+
        if ((c->x86 != 0x17 && c->x86 != 0x18) || c->x86_num_siblings <= 1) {
                BUG_ON(!set_legacy_ssbd(c, enable));
                return;
@@ -816,12 +827,17 @@ void amd_set_legacy_ssbd(bool enable)
                 */
                return;
 
+       if (this_cpu(legacy_ssbd) == enable)
+               return;
+
        if (cpu_has_virt_ssbd)
                wrmsr(MSR_VIRT_SPEC_CTRL, enable ? SPEC_CTRL_SSBD : 0, 0);
        else if (amd_legacy_ssbd)
                core_set_legacy_ssbd(enable);
        else
                ASSERT_UNREACHABLE();
+
+       this_cpu(legacy_ssbd) = enable;
 }
 
 /*
--
generated by git-patchbot for /home/xen/git/xen.git#stable-4.17



 


Rackspace

Lists.xenproject.org is hosted with RackSpace, monitoring our
servers 24x7x365 and backed by RackSpace's Fanatical Support®.