i386: Fix up the Node id for CPUID_8000_001E

This is part of topoext support. To keep the compatibility, it is better
we support all the combination of nr_cores and nr_threads currently
supported. By allowing more nr_cores and nr_threads, we might end up with
more nodes than we can actually support with the real hardware. We need to
fix up the node id to make this work. We can achieve this by shifting the
socket_id bits left to address more nodes.

Backports commit 631be32155dbafa1fe886f2488127956c9120ba6 from qemu

qemu/include/qemu/bitops.h

@@ -136,6 +136,16 @@ static inline int test_bit(long nr, const unsigned long *addr)
     return 1UL & (addr[BIT_WORD(nr)] >> (nr & (BITS_PER_LONG-1)));
 }
 
+/**
+ * find_last_bit - find the last set bit in a memory region
+ * @addr: The address to start the search at
+ * @size: The maximum size to search
+ *
+ * Returns the bit number of the first set bit, or size.
+ */
+unsigned long find_last_bit(const unsigned long *addr,
+                            unsigned long size);
+
 /**
  * find_next_bit - find the next set bit in a memory region
  * @addr: The address to base the search on

qemu/target/i386/cpu.c

@@ -19,6 +19,7 @@
 
 #include "qemu/osdep.h"
 #include "qemu/cutils.h"
+#include "qemu/bitops.h"
 #include "unicorn/platform.h"
 #include "uc_priv.h"
 
@@ -461,6 +462,8 @@ static void encode_topo_cpuid8000001e(CPUState *cs, X86CPU *cpu,
                                        uint32_t *ecx, uint32_t *edx)
 {
     struct core_topology topo = {0};
+    unsigned long nodes;
+    int shift;
 
     build_core_topology(cs->nr_cores, cpu->core_id, &topo);
     *eax = cpu->apic_id;
@@ -493,7 +496,28 @@ static void encode_topo_cpuid8000001e(CPUState *cs, X86CPU *cpu,
      *         2  Socket id
      *       1:0  Node id
      */
-    *ecx = ((topo.num_nodes - 1) << 8) | (cpu->socket_id << 2) | topo.node_id;
+    if (topo.num_nodes <= 4) {
+        *ecx = ((topo.num_nodes - 1) << 8) | (cpu->socket_id << 2) |
+                topo.node_id;
+    } else {
+        /*
+         * Node id fix up. Actual hardware supports up to 4 nodes. But with
+         * more than 32 cores, we may end up with more than 4 nodes.
+         * Node id is a combination of socket id and node id. Only requirement
+         * here is that this number should be unique accross the system.
+         * Shift the socket id to accommodate more nodes. We dont expect both
+         * socket id and node id to be big number at the same time. This is not
+         * an ideal config but we need to to support it. Max nodes we can have
+         * is 32 (255/8) with 8 cores per node and 255 max cores. We only need
+         * 5 bits for nodes. Find the left most set bit to represent the total
+         * number of nodes. find_last_bit returns last set bit(0 based). Left
+         * shift(+1) the socket id to represent all the nodes.
+         */
+        nodes = topo.num_nodes - 1;
+        shift = find_last_bit(&nodes, 8);
+        *ecx = ((topo.num_nodes - 1) << 8) | (cpu->socket_id << (shift + 1)) |
+                topo.node_id;
+    }
     *edx = 0;
 }
 

qemu/util/bitops.c

@@ -126,3 +126,32 @@ found_first:
 found_middle:
     return result + ctzl(~tmp);
 }
+
+unsigned long find_last_bit(const unsigned long *addr, unsigned long size)
+{
+    unsigned long words;
+    unsigned long tmp;
+
+    /* Start at final word. */
+    words = size / BITS_PER_LONG;
+
+    /* Partial final word? */
+    if (size & (BITS_PER_LONG-1)) {
+        tmp = (addr[words] & (~0UL >> (BITS_PER_LONG
+                                       - (size & (BITS_PER_LONG-1)))));
+        if (tmp) {
+            goto found;
+        }
+    }
+
+    while (words) {
+        tmp = addr[--words];
+        if (tmp) {
+        found:
+            return words * BITS_PER_LONG + BITS_PER_LONG - 1 - clzl(tmp);
+        }
+    }
+
+    /* Not found */
+    return size;
+}