cputlb: bring back tlb_flush_count under !TLB_DEBUG

Commit f0aff0f124 ("cputlb: add assert_cpu_is_self checks") buried
the increment of tlb_flush_count under TLB_DEBUG. This results in
"info jit" always (mis)reporting 0 TLB flushes when !TLB_DEBUG.

Besides, under MTTCG tlb_flush_count is updated by several threads,
so in order not to lose counts we'd either have to use atomic ops
or distribute the counter, which is more scalable.

This patch does the latter by embedding tlb_flush_count in CPUArchState.
The global count is then easily obtained by iterating over the CPU list.

Note that this change also requires updating the accessors to
tlb_flush_count to use atomic_read/set whenever there may be conflicting
accesses (as defined in C11) to it.

Reviewed-by: Richard Henderson <rth@twiddle.net>
Reviewed-by: Alex Bennée <alex.bennee@linaro.org>
Signed-off-by: Emilio G. Cota <cota@braap.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>

2 files changed, 15 insertions, 4 deletions

diff --git a/accel/tcg/cputlb.c b/accel/tcg/cputlb.c
index bcbcc4db6c..5b1ef1442c 100644
--- a/accel/tcg/cputlb.c
+++ b/accel/tcg/cputlb.c
@@ -92,8 +92,18 @@ static void flush_all_helper(CPUState *src, run_on_cpu_func fn,
     }
 }
 
-/* statistics */
-int tlb_flush_count;
+size_t tlb_flush_count(void)
+{
+    CPUState *cpu;
+    size_t count = 0;
+
+    CPU_FOREACH(cpu) {
+        CPUArchState *env = cpu->env_ptr;
+
+        count += atomic_read(&env->tlb_flush_count);
+    }
+    return count;
+}
 
 /* This is OK because CPU architectures generally permit an
  * implementation to drop entries from the TLB at any time, so
@@ -112,7 +122,8 @@ static void tlb_flush_nocheck(CPUState *cpu)
     }
 
     assert_cpu_is_self(cpu);
-    tlb_debug("(count: %d)\n", tlb_flush_count++);
+    atomic_set(&env->tlb_flush_count, env->tlb_flush_count + 1);
+    tlb_debug("(count: %zu)\n", tlb_flush_count());
 
     tb_lock();
 
diff --git a/accel/tcg/translate-all.c b/accel/tcg/translate-all.c
index 2d1ed06065..6b5d4bece2 100644
--- a/accel/tcg/translate-all.c
+++ b/accel/tcg/translate-all.c
@@ -1936,7 +1936,7 @@ void dump_exec_info(FILE *f, fprintf_function cpu_fprintf)
             atomic_read(&tcg_ctx.tb_ctx.tb_flush_count));
     cpu_fprintf(f, "TB invalidate count %d\n",
             tcg_ctx.tb_ctx.tb_phys_invalidate_count);
-    cpu_fprintf(f, "TLB flush count     %d\n", tlb_flush_count);
+    cpu_fprintf(f, "TLB flush count     %zu\n", tlb_flush_count());
     tcg_dump_info(f, cpu_fprintf);
 
     tb_unlock();