util: Fix max socket calculation

This patch changes how the maximum socket count is calculated.

On some systems (e.g. GB200), physical_package_id values are not
contiguous or zero-based. Instead of 0..N, they may contain large
arbitrary identifiers (e.g. 256123234). The previous implementation
assumed a 0..N range and used the maximum ID value directly.

This caused:
    excessive memory allocation
    extremely large loop bounds
    OOM / DoS scenarios
    unnecessary CPU time consumption

The new implementation computes the socket count as the number of unique
package IDs present on the node, rather than relying on the maximum numeric
value.

Reviewed-by: Daniel P. Berrangé <berrange@redhat.com>
Tested-by: Daniel P. Berrangé <berrange@redhat.com>
Signed-off-by: Alexandr Semenikhin <alexandr2e78@gmail.com>

diff --git a/src/util/virhostcpu.c b/src/util/virhostcpu.c
index 09395ddb04b4a258fec5f5829cc30140f6388ea9..113aa6881ed4f84f36c5f70a46bbbff71151f5c4 100644 (file)
--- a/src/util/virhostcpu.c
+++ b/src/util/virhostcpu.c
@@ -331,6 +331,8 @@ virHostCPUParseNode(const char *node,
     int siblings;
     unsigned int cpu;
     int direrr;
+    g_autoptr(GHashTable) st = g_hash_table_new(g_direct_hash, g_direct_equal);
+    gpointer sock_resolved;
 
     *threads = 0;
     *cores = 0;
@@ -356,15 +358,29 @@ virHostCPUParseNode(const char *node,
         if (virHostCPUGetSocket(cpu, &sock) < 0)
             goto cleanup;
 
-        virBitmapSetBitExpand(sockets_map, sock);
+        if (!g_hash_table_lookup_extended(st,
+                                          GUINT_TO_POINTER(sock),
+                                          NULL,
+                                          &sock_resolved)) {
+            g_hash_table_insert(st,
+                                GUINT_TO_POINTER(sock),
+                                GUINT_TO_POINTER(sock_max));
+            sock = sock_max;
+            sock_max++;
+        } else {
+            sock = GPOINTER_TO_UINT(sock_resolved);
+        }
 
-        if (sock > sock_max)
-            sock_max = sock;
+        virBitmapSetBitExpand(sockets_map, sock);
     }
 
     if (direrr < 0)
         goto cleanup;
 
+    if (sock_max == 0) {
+        g_hash_table_insert(st, GUINT_TO_POINTER(0), GUINT_TO_POINTER(sock_max));
+    }
+
     sock_max++;
 
     /* allocate cores maps for each socket */
@@ -400,6 +416,16 @@ virHostCPUParseNode(const char *node,
 
         if (virHostCPUGetSocket(cpu, &sock) < 0)
             goto cleanup;
+
+        if (!g_hash_table_lookup_extended(st,
+                                          GUINT_TO_POINTER(sock),
+                                          NULL,
+                                          &sock_resolved)) {
+            goto cleanup;
+        }
+
+        sock = GPOINTER_TO_UINT(sock_resolved);
+
         if (!virBitmapIsBitSet(sockets_map, sock)) {
             virReportError(VIR_ERR_INTERNAL_ERROR, "%s",
                            _("CPU socket topology has changed"));