x86/vpmu_intel: handle SMT consistently for programmable and fixed counters

The patch introduces a macro FIXED_CTR_CTRL_ANYTHREAD_MASK and uses it
to mask .Anythread bit for all counter in IA32_FIXED_CTR_CTRL MSR in all
versions of Intel Arhcitectural Performance Monitoring.  Masking .AnyThread bit
 is necesssry for two reasons:

1. We need to be consistent in the implementation. We disable .Anythread bit in
programmable counters (regardless of the version) by masking bit 21 in
IA32_PERFEVTSELx.  (See code snippet below from vpmu_intel.c)

 /* Masks used for testing whether and MSR is valid */
 #define ARCH_CTRL_MASK  (~((1ull << 32) - 1) | (1ull << 21))

But we leave it enabled in fixed function counters for version 3. Removing the
condition disables the bit in fixed function counters regardless of the version,
which is consistent with what is done for programmable counters.

2. We don't want to expose event counts from another guest (or hypervisor)
which can happen if .AnyThread bit is not masked and a VCPU is only scheduled
to run on one of the hardware threads in a hyper-threaded CPU.

Also, note that Intel SDM discourages the  use of .AnyThread bit in virtualized
 environments (per section 18.2.3.1 AnyThread Counting and Software Evolution).

Signed-off-by: Mohit Gambhir <mohit.gambhir@oracle.com>
Reviewed-by: Jan Beulich <jbeulich@suse.com>
Reviewed-by: Kevin Tian <kevin.tian@intel.com>

diff --git a/xen/arch/x86/cpu/vpmu_intel.c b/xen/arch/x86/cpu/vpmu_intel.c
index 0d66ecb931c872ca3a82adf966dadd1beac08fd5..3f0322cad2177de9c27a4a3bc4245c614ebb7f10 100644 (file)
--- a/xen/arch/x86/cpu/vpmu_intel.c
+++ b/xen/arch/x86/cpu/vpmu_intel.c
@@ -73,6 +73,7 @@ static bool_t __read_mostly full_width_write;
  */
 #define FIXED_CTR_CTRL_BITS 4
 #define FIXED_CTR_CTRL_MASK ((1 << FIXED_CTR_CTRL_BITS) - 1)
+#define FIXED_CTR_CTRL_ANYTHREAD_MASK 0x4
 
 #define ARCH_CNTR_ENABLED   (1ULL << 22)
 
@@ -946,6 +947,7 @@ int __init core2_vpmu_init(void)
 {
     u64 caps;
     unsigned int version = 0;
+    unsigned int i;
 
     if ( current_cpu_data.cpuid_level >= 0xa )
         version = MASK_EXTR(cpuid_eax(0xa), PMU_VERSION_MASK);
@@ -979,8 +981,11 @@ int __init core2_vpmu_init(void)
     full_width_write = (caps >> 13) & 1;
 
     fixed_ctrl_mask = ~((1ull << (fixed_pmc_cnt * FIXED_CTR_CTRL_BITS)) - 1);
-    if ( version == 2 )
-        fixed_ctrl_mask |= 0x444;
+    /* mask .AnyThread bits for all fixed counters */
+    for( i = 0; i < fixed_pmc_cnt; i++ )
+       fixed_ctrl_mask |=
+           (FIXED_CTR_CTRL_ANYTHREAD_MASK << (FIXED_CTR_CTRL_BITS * i));
+
     fixed_counters_mask = ~((1ull << core2_get_bitwidth_fix_count()) - 1);
     global_ctrl_mask = ~((((1ULL << fixed_pmc_cnt) - 1) << 32) |
                          ((1ULL << arch_pmc_cnt) - 1));