Fix T2C memory visibility race

The T2C compilation thread could set hot2 flag before compiled code was
fully visible to the main thread, causing execution of invalid function
pointers. This resulted in incorrect calculation results in the pi test.

Fixed by declaring hot2 as volatile to ensure proper cross-thread
visibility. The volatile qualifier guarantees fresh reads from memory
and prevents compiler optimizations that could reorder accesses.

Author: jserv

src/emulate.c

@@ -1122,11 +1122,13 @@ void rv_step(void *arg)
 #if RV32_HAS(T2C)
         /* executed through the tier-2 JIT compiler */
         if (block->hot2) {
+            /* hot2 is volatile, ensuring visibility across threads */
             ((exec_t2c_func_t) block->func)(rv);
             prev = NULL;
             continue;
         } /* check if invoking times of t1 generated code exceed threshold */
         else if (!block->compiled && block->n_invoke >= THRESHOLD) {
+            /* Mark block as queued for compilation to avoid re-queueing */
             block->compiled = true;
             queue_entry_t *entry = malloc(sizeof(queue_entry_t));
             entry->block = block;

src/riscv_private.h

@@ -85,8 +85,8 @@ typedef struct block {
 
     rv_insn_t *ir_head, *ir_tail; /**< the first and last ir for this block */
 #if RV32_HAS(JIT)
-    bool hot;  /**< Determine the block is potential hotspot or not */
-    bool hot2; /**< Determine the block is strong hotspot or not */
+    bool hot;           /**< Determine the block is potential hotspot or not */
+    volatile bool hot2; /**< Determine the block is strong hotspot or not */
     bool
         translatable; /**< Determine the block has RV32AF insturctions or not */
     bool has_loops;   /**< Determine the block has loop or not */

src/t2c.c

@@ -346,6 +346,7 @@ void t2c_compile(riscv_t *rv, block_t *block)
 
     jit_cache_update(rv->jit_cache, key, block->func);
 
+    /* hot2 is declared volatile, ensuring visibility across threads */
     block->hot2 = true;
 }