x86: clear RDRAND CPUID bit on AMD family 15h/16h

Inspired by Linux commit c49a0a80137c7ca7d6ced4c812c9e07a949f6f24:

    There have been reports of RDRAND issues after resuming from suspend on
    some AMD family 15h and family 16h systems. This issue stems from a BIOS
    not performing the proper steps during resume to ensure RDRAND continues
    to function properly.

    Update the CPU initialization to clear the RDRAND CPUID bit for any family
    15h and 16h processor that supports RDRAND. If it is known that the family
    15h or family 16h system does not have an RDRAND resume issue or that the
    system will not be placed in suspend, the "cpuid=rdrand" kernel parameter
    can be used to stop the clearing of the RDRAND CPUID bit.

    Note, that clearing the RDRAND CPUID bit does not prevent a processor
    that normally supports the RDRAND instruction from executing it. So any
    code that determined the support based on family and model won't #UD.

Warn if no explicit choice was given on affected hardware.

Check RDRAND functions at boot as well as after S3 resume (the retry
limit chosen is entirely arbitrary).

Signed-off-by: Jan Beulich <jbeulich@suse.com>
Reviewed-by: Roger Pau Monné <roger.pau@citrix.com>
Acked-by: Andrew Cooper <andrew.cooper3@citrix.com>

diff --git a/docs/misc/xen-command-line.pandoc b/docs/misc/xen-command-line.pandoc
index ee12b0f53f69d55e2326f030edb5ea5f9a140200..e16bb901842b1744fdbeb039a69fb9b5fce6da0d 100644 (file)
--- a/docs/misc/xen-command-line.pandoc
+++ b/docs/misc/xen-command-line.pandoc
@@ -488,6 +488,10 @@ The Speculation Control hardware features `md-clear`, `ibrsb`, `stibp`, `ibpb`,
 be ignored, e.g. `no-ibrsb`, at which point Xen won't use them itself, and
 won't offer them to guests.
 
+`rdrand` can be used to override the default disabling of the feature on certain
+AMD systems.  Its negative form can of course also be used to suppress use and
+exposure of the feature.
+
 ### cpuid_mask_cpu
 > `= fam_0f_rev_[cdefg] | fam_10_rev_[bc] | fam_11_rev_b`
 

diff --git a/xen/arch/x86/cpu/amd.c b/xen/arch/x86/cpu/amd.c
index 05cbcbad731a63d7e0c7acda68a28a9fadd58b9b..0cc6853c421778fefb887ab06e21d90b44a6732d 100644 (file)
--- a/xen/arch/x86/cpu/amd.c
+++ b/xen/arch/x86/cpu/amd.c
@@ -4,6 +4,7 @@
 #include <xen/param.h>
 #include <xen/smp.h>
 #include <xen/pci.h>
+#include <xen/warning.h>
 #include <asm/io.h>
 #include <asm/msr.h>
 #include <asm/processor.h>
@@ -747,6 +748,26 @@ static void init_amd(struct cpuinfo_x86 *c)
                if (acpi_smi_cmd && (acpi_enable_value | acpi_disable_value))
                        amd_acpi_c1e_quirk = true;
                break;
+
+       case 0x15: case 0x16:
+               /*
+                * There are some Fam15/Fam16 systems where upon resume from S3
+                * firmware fails to re-setup properly functioning RDRAND.
+                * By the time we can spot the problem, it is too late to take
+                * action, and there is nothing Xen can do to repair the problem.
+                * Clear the feature unless force-enabled on the command line.
+                */
+               if (c == &boot_cpu_data &&
+                   cpu_has(c, X86_FEATURE_RDRAND) &&
+                   !is_forced_cpu_cap(X86_FEATURE_RDRAND)) {
+                       static const char __initconst text[] =
+                               "RDRAND may cease to work on this hardware upon resume from S3.\n"
+                               "Please choose an explicit cpuid={no-}rdrand setting.\n";
+
+                       setup_clear_cpu_cap(X86_FEATURE_RDRAND);
+                       warning_add(text);
+               }
+               break;
        }
 
        display_cacheinfo(c);

diff --git a/xen/arch/x86/cpu/common.c b/xen/arch/x86/cpu/common.c
index 3e0d9cbe986e771417760546c0bad4dca2f36ec6..c413188d00b9fa0b832513d34b9fa8bf9affe9f9 100644 (file)
--- a/xen/arch/x86/cpu/common.c
+++ b/xen/arch/x86/cpu/common.c
@@ -11,6 +11,7 @@
 #include <asm/io.h>
 #include <asm/mpspec.h>
 #include <asm/apic.h>
+#include <asm/random.h>
 #include <asm/setup.h>
 #include <mach_apic.h>
 #include <public/sysctl.h> /* for XEN_INVALID_{SOCKET,CORE}_ID */
@@ -98,6 +99,11 @@ void __init setup_force_cpu_cap(unsigned int cap)
        __set_bit(cap, boot_cpu_data.x86_capability);
 }
 
+bool __init is_forced_cpu_cap(unsigned int cap)
+{
+       return test_bit(cap, forced_caps);
+}
+
 static void default_init(struct cpuinfo_x86 * c)
 {
        /* Not much we can do here... */
@@ -497,6 +503,27 @@ void identify_cpu(struct cpuinfo_x86 *c)
        printk("\n");
 #endif
 
+       /*
+        * If RDRAND is available, make an attempt to check that it actually
+        * (still) works.
+        */
+       if (cpu_has(c, X86_FEATURE_RDRAND)) {
+               unsigned int prev = 0;
+
+               for (i = 0; i < 5; ++i)
+               {
+                       unsigned int cur = arch_get_random();
+
+                       if (prev && cur != prev)
+                               break;
+                       prev = cur;
+               }
+
+               if (i >= 5)
+                       printk(XENLOG_WARNING "CPU%u: RDRAND appears to not work\n",
+                              smp_processor_id());
+       }
+
        if (system_state == SYS_STATE_resume)
                return;
 

diff --git a/xen/arch/x86/cpuid.c b/xen/arch/x86/cpuid.c
index 4b734284a461524d462321f0c5aae6800a7495b7..ee11087626c440c00d3b4dce490a0eadd3d951c1 100644 (file)
--- a/xen/arch/x86/cpuid.c
+++ b/xen/arch/x86/cpuid.c
@@ -72,6 +72,9 @@ static int __init parse_xen_cpuid(const char *s)
             {
                 if ( !val )
                     setup_clear_cpu_cap(mid->bit);
+                else if ( mid->bit == X86_FEATURE_RDRAND &&
+                          (cpuid_ecx(1) & cpufeat_mask(X86_FEATURE_RDRAND)) )
+                    setup_force_cpu_cap(X86_FEATURE_RDRAND);
                 mid = NULL;
             }
 

diff --git a/xen/include/asm-x86/processor.h b/xen/include/asm-x86/processor.h
index 8f6f5a97dd7640ca862a6853d00a5218da172f00..070691882b91c72452da5a27afe303eebdd4bbae 100644 (file)
--- a/xen/include/asm-x86/processor.h
+++ b/xen/include/asm-x86/processor.h
@@ -165,6 +165,7 @@ extern const struct x86_cpu_id *x86_match_cpu(const struct x86_cpu_id table[]);
 extern void identify_cpu(struct cpuinfo_x86 *);
 extern void setup_clear_cpu_cap(unsigned int);
 extern void setup_force_cpu_cap(unsigned int);
+extern bool is_forced_cpu_cap(unsigned int);
 extern void print_cpu_info(unsigned int cpu);
 extern void init_intel_cacheinfo(struct cpuinfo_x86 *c);