[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index] [xen master] x86/amd: fix legacy setting of SSBD on AMD Family 17h
commit eda98ea870803ea204a1928519b3f21ec6a679b6 Author: Roger Pau Monne <roger.pau@xxxxxxxxxx> AuthorDate: Wed Mar 22 11:52:07 2023 +0100 Commit: Jan Beulich <jbeulich@xxxxxxxx> CommitDate: Tue May 16 17:17:24 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> --- 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 caafe44740..9a1a3858ed 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 = ¤t_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#master
|
![]() |
Lists.xenproject.org is hosted with RackSpace, monitoring our |