libxc: allow changing max number of hypervisor cpuid leaves

Add support for changing max number of hypervisor leaves from configuration
file.

This number can be specified using xl's standard 'cpuid' option. Only lowest
8 bits of leaf's 0x4000xx00 eax register are processed, all others are ignored.

The changes allow us to revert commit 80ecb40362
which is most likely no longer needed now anyway (Solaris bug that it addressed
has been fixed and backported to earlier releases) but leave possibility of
running unpatched version of Solaris by forcing number of leaves to 2 in the
configuration file.

Signed-off-by: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Acked-by: Ian Campbell <ian.campbell@citrix.com>
Reviewed-by: Jan Beulich <jbeulich@suse.com>

docs/man/xl.cfg.pod.5

@@ -881,9 +881,13 @@ Possible values for a single feature bit:
   'k' -> pass through the host bit value
   's' -> as 'k' but preserve across save/restore and migration (not implemented)
 
+Note: when specifying B<cpuid> for hypervisor leaves (0x4000xxxx major group)
+only the lowest 8 bits of leaf's 0x4000xx00 EAX register are processed, the rest
+are ignored (these 8 bits signify maximum number of hypervisor leaves).
+
 List of keys taking a value:
-apicidsize brandid clflush family localapicid maxleaf model nc proccount procpkg
-stepping
+apicidsize brandid clflush family localapicid maxleaf maxhvleaf model nc
+proccount procpkg stepping
 
 List of keys taking a character:
 3dnow 3dnowext 3dnowprefetch abm acpi aes altmovcr8 apic avx clfsh cmov

tools/libxc/xc_cpuid_x86.c

@@ -561,6 +561,17 @@ static int xc_cpuid_policy(
 {
     xc_dominfo_t        info;
 
+    /*
+     * For hypervisor leaves (0x4000XXXX) only 0x4000xx00.EAX[7:0] bits (max
+     * number of leaves) can be set by user. Hypervisor will enforce this so
+     * all other bits are don't-care and we can set them to zero.
+     */
+    if ( (input[0] & 0xffff0000) == 0x40000000 )
+    {
+        regs[0] = regs[1] = regs[2] = regs[3] = 0;
+        return 0;
+    }
+
     if ( xc_domain_getinfo(xch, domid, 1, &info) == 0 )
         return -EINVAL;
 

tools/libxl/libxl_cpuid.c

@@ -187,6 +187,7 @@ int libxl_cpuid_parse_config(libxl_cpuid_policy_list *cpuid, const char* str)
         {"svm_vmcbclean",0x8000000a, NA, CPUID_REG_EDX,  5,  1},
         {"svm_decode",   0x8000000a, NA, CPUID_REG_EDX,  7,  1},
         {"svm_pausefilt",0x8000000a, NA, CPUID_REG_EDX, 10,  1},
+        {"maxhvleaf",    0x40000000, NA, CPUID_REG_EAX,  0,  8},
 
         {NULL, 0, NA, CPUID_REG_INV, 0, 0}
     };

xen/arch/x86/traps.c

@@ -677,15 +677,19 @@ int cpuid_hypervisor_leaves( uint32_t idx, uint32_t sub_idx,
     struct domain *d = current->domain;
     /* Optionally shift out of the way of Viridian architectural leaves. */
     uint32_t base = is_viridian_domain(d) ? 0x40000100 : 0x40000000;
-    uint32_t limit;
+    uint32_t limit, dummy;
 
     idx -= base;
+    if ( idx > XEN_CPUID_MAX_NUM_LEAVES )
+        return 0; /* Avoid unnecessary pass through domain_cpuid() */
 
-    /*
-     * Some Solaris PV drivers fail if max > base + 2. Help them out by
-     * hiding the PVRDTSCP leaf if PVRDTSCP is disabled.
-     */
-    limit = (d->arch.tsc_mode < TSC_MODE_PVRDTSCP) ? 2 : 3;
+    /* Number of leaves may be user-specified */
+    domain_cpuid(d, base, 0, &limit, &dummy, &dummy, &dummy);
+    limit &= 0xff;
+    if ( limit < 2 )
+        limit = 2;
+    else if ( limit > XEN_CPUID_MAX_NUM_LEAVES )
+        limit = XEN_CPUID_MAX_NUM_LEAVES;
 
     if ( idx > limit ) 
         return 0;

xen/include/public/arch-x86/cpuid.h

@@ -65,4 +65,6 @@
 #define _XEN_CPUID_FEAT1_MMU_PT_UPDATE_PRESERVE_AD 0
 #define XEN_CPUID_FEAT1_MMU_PT_UPDATE_PRESERVE_AD  (1u<<0)
 
+#define XEN_CPUID_MAX_NUM_LEAVES 3
+
 #endif /* __XEN_PUBLIC_ARCH_X86_CPUID_H__ */