x86/amd: Mitigations for Zenbleed

Zenbleed is a malfunction on AMD Zen2 uarch parts which results in corruption
of the vector registers.  An attacker can trigger this bug deliberately in
order to access stale data in the physical vector register file.  This can
include data from sibling threads, or a higher-privilege context.

Microcode is the preferred mitigation but in the case that's not available use
the chickenbit as instructed by AMD.  Re-evaluate the mitigation on late
microcode load too.

This is XSA-433 / CVE-2023-20593.

Signed-off-by: Andrew Cooper <andrew.cooper3@citrix.com>
Acked-by: Roger Pau Monné <roger.pau@citrix.com>
(cherry picked from commit f91c5ea970675637721bb7f18adaa189837eb783)

diff --git a/xen/arch/x86/cpu/amd.c b/xen/arch/x86/cpu/amd.c
index a8d2fb8a1590b3d6bef7a44bd0d10b5b1702da4f..dd4dc3157c2680bd5a2554a9ef760c03c756e007 100644 (file)
--- a/xen/arch/x86/cpu/amd.c
+++ b/xen/arch/x86/cpu/amd.c
@@ -13,6 +13,7 @@
 #include <asm/spec_ctrl.h>
 #include <asm/acpi.h>
 #include <asm/apic.h>
+#include <asm/microcode.h>
 
 #include "cpu.h"
 
@@ -756,6 +757,72 @@ void amd_init_spectral_chicken(void)
                wrmsr_safe(MSR_AMD64_DE_CFG2, val | chickenbit);
 }
 
+void amd_check_zenbleed(void)
+{
+       const struct cpu_signature *sig = &this_cpu(cpu_sig);
+       unsigned int good_rev, chickenbit = (1 << 9);
+       uint64_t val, old_val;
+
+       /*
+        * If we're virtualised, we can't do family/model checks safely, and
+        * we likely wouldn't have access to DE_CFG even if we could see a
+        * microcode revision.
+        *
+        * A hypervisor may hide AVX as a stopgap mitigation.  We're not in a
+        * position to care either way.  An admin doesn't want to be disabling
+        * AVX as a mitigation on any build of Xen with this logic present.
+        */
+       if (cpu_has_hypervisor || boot_cpu_data.x86 != 0x17)
+               return;
+
+       switch (boot_cpu_data.x86_model) {
+       case 0x30 ... 0x3f: good_rev = 0x0830107a; break;
+       case 0x60 ... 0x67: good_rev = 0x0860010b; break;
+       case 0x68 ... 0x6f: good_rev = 0x08608105; break;
+       case 0x70 ... 0x7f: good_rev = 0x08701032; break;
+       case 0xa0 ... 0xaf: good_rev = 0x08a00008; break;
+       default:
+               /*
+                * With the Fam17h check above, parts getting here are Zen1.
+                * They're not affected.
+                */
+               return;
+       }
+
+       rdmsrl(MSR_AMD64_DE_CFG, val);
+       old_val = val;
+
+       /*
+        * Microcode is the preferred mitigation, in terms of performance.
+        * However, without microcode, this chickenbit (specific to the Zen2
+        * uarch) disables Floating Point Mov-Elimination to mitigate the
+        * issue.
+        */
+       val &= ~chickenbit;
+       if (sig->rev < good_rev)
+               val |= chickenbit;
+
+       if (val == old_val)
+               /* Nothing to change. */
+               return;
+
+       /*
+        * DE_CFG is a Core-scoped MSR, and this write is racy during late
+        * microcode load.  However, both threads calculate the new value from
+        * state which is shared, and unrelated to the old value, so the
+        * result should be consistent.
+        */
+       wrmsrl(MSR_AMD64_DE_CFG, val);
+
+       /*
+        * Inform the admin that we changed something, but don't spam,
+        * especially during a late microcode load.
+        */
+       if (smp_processor_id() == 0)
+               printk(XENLOG_INFO "Zenbleed mitigation - using %s\n",
+                      val & chickenbit ? "chickenbit" : "microcode");
+}
+
 static void init_amd(struct cpuinfo_x86 *c)
 {
        u32 l, h;
@@ -1016,6 +1083,8 @@ static void init_amd(struct cpuinfo_x86 *c)
        if ((smp_processor_id() == 1) && !cpu_has(c, X86_FEATURE_ITSC))
                disable_c1_ramping();
 
+       amd_check_zenbleed();
+
        check_syscfg_dram_mod_en();
 
        amd_log_freq(c);

diff --git a/xen/arch/x86/cpu/microcode/amd.c b/xen/arch/x86/cpu/microcode/amd.c
index 809ba4967c7065a42fa4e8b25c347cf6da982c6e..90629bee0dab30b7c97d4aabef9edff9b5b6544d 100644 (file)
--- a/xen/arch/x86/cpu/microcode/amd.c
+++ b/xen/arch/x86/cpu/microcode/amd.c
@@ -254,6 +254,8 @@ static int apply_microcode(const struct microcode_patch *patch)
     printk(XENLOG_WARNING "microcode: CPU%u updated from revision %#x to %#x\n",
            cpu, old_rev, rev);
 
+    amd_check_zenbleed();
+
     return 0;
 }
 

diff --git a/xen/include/asm-x86/processor.h b/xen/include/asm-x86/processor.h
index c8745e1f31aabeb3b0c7eeb7e238c24d69df1871..7b5ba41a40a02dadea55698b8fd2513e15df240f 100644 (file)
--- a/xen/include/asm-x86/processor.h
+++ b/xen/include/asm-x86/processor.h
@@ -641,6 +641,8 @@ enum ap_boot_method {
 };
 extern enum ap_boot_method ap_boot_method;
 
+void amd_check_zenbleed(void);
+
 #endif /* !__ASSEMBLY__ */
 
 #endif /* __ASM_X86_PROCESSOR_H */