diff mbox series

[2/2] x86: cpu: fixup number of addressable IDs for logical processors sharing cache

Message ID 20220524151020.2541698-3-imammedo@redhat.com (mailing list archive)
State New, archived
Headers show
Series i386: fixup number of logical CPUs when host-cache-info=on | expand

Commit Message

Igor Mammedov May 24, 2022, 3:10 p.m. UTC
When QEMU is started with '-cpu host,host-cache-info=on', it will
passthrough host's number of logical processors sharing cache and
number of processor cores in the physical package. QEMU already
fixes up the later to correctly reflect number of configured cores
for VM, however number of logical processors sharing cache is still
comes from host CPU, which confuses guest started with:

       -machine q35,accel=kvm \
       -cpu host,host-cache-info=on,l3-cache=off \
       -smp 20,sockets=2,dies=1,cores=10,threads=1  \
       -numa node,nodeid=0,memdev=ram-node0 \
       -numa node,nodeid=1,memdev=ram-node1 \
       -numa cpu,socket-id=0,node-id=0 \
       -numa cpu,socket-id=1,node-id=1

on 2 socket Xeon 4210R host with 10 cores per socket
with CPUID[04H]:
      ...
        --- cache 3 ---
      cache type                           = unified cache (3)
      cache level                          = 0x3 (3)
      self-initializing cache level        = true
      fully associative cache              = false
      maximum IDs for CPUs sharing cache   = 0x1f (31)
      maximum IDs for cores in pkg         = 0xf (15)
      ...
that doesn't match number of logical processors VM was
configured with and as result RHEL 9.0 guest complains:

   sched: CPU #10's llc-sibling CPU #0 is not on the same node! [node: 1 != 0]. Ignoring dependency.
   WARNING: CPU: 10 PID: 0 at arch/x86/kernel/smpboot.c:421 topology_sane.isra.0+0x67/0x80
   ...
   Call Trace:
     set_cpu_sibling_map+0x176/0x590
     start_secondary+0x5b/0x150
     secondary_startup_64_no_verify+0xc2/0xcb

Fix it by capping max number of logical processors to vcpus/socket
as it was configured, which fixes the issue.

Signed-off-by: Igor Mammedov <imammedo@redhat.com>
Fixes: https://bugzilla.redhat.com/show_bug.cgi?id=2088311
---
PS:
 capping to logical cpus/socket was arbitrarily chosen (maybe
 it should be per die or something else but don't see that in spec)
---
 target/i386/cpu.c | 20 ++++++++++++++++----
 1 file changed, 16 insertions(+), 4 deletions(-)
diff mbox series

Patch

diff --git a/target/i386/cpu.c b/target/i386/cpu.c
index bbe37dce2e..ffb274dcf6 100644
--- a/target/i386/cpu.c
+++ b/target/i386/cpu.c
@@ -5276,10 +5276,22 @@  void cpu_x86_cpuid(CPUX86State *env, uint32_t index, uint32_t count,
         /* cache info: needed for Core compatibility */
         if (cpu->cache_info_passthrough) {
             x86_cpu_get_cache_cpuid(index, count, eax, ebx, ecx, edx);
-            /* QEMU gives out its own APIC IDs, never pass down bits 31..26.  */
-            *eax &= ~0xFC000000;
-            if ((*eax & 31) && cs->nr_cores > 1) {
-                *eax |= (pow2ceil(cs->nr_cores) - 1) << 26;
+            /*
+             * QEMU has its own number of cores/logical cpus,
+             * set 24..14, 31..26 bit to configured values
+             */
+            if (*eax & 31) {
+                int host_vcpus_per_cache = 1 + ((*eax & 0x3FFC000) >> 14);
+                int vcpus_per_socket = env->nr_dies * cs->nr_cores *
+                                       cs->nr_threads;
+                if (cs->nr_cores > 1) {
+                    *eax &= ~0xFC000000;
+                    *eax |= (pow2ceil(cs->nr_cores) - 1) << 26;
+                }
+                if (host_vcpus_per_cache > vcpus_per_socket) {
+                    *eax &= ~0x3FFC000;
+                    *eax |= (pow2ceil(vcpus_per_socket) - 1) << 14;
+                }
             }
         } else if (cpu->vendor_cpuid_only && IS_AMD_CPU(env)) {
             *eax = *ebx = *ecx = *edx = 0;