cputlb: Count "partial" and "elided" tlb flushes

Our only statistic so far was "full" tlb flushes, where all mmu_idx
are flushed at the same time.

Now count "partial" tlb flushes where sets of mmu_idx are flushed,
but the set is not maximal.  Account one per mmu_idx flushed, as
that is the unit of work performed.

We don't actually count elided flushes yet, but go ahead and change
the interface presented to the monitor all at once.

Tested-by: Emilio G. Cota <cota@braap.org>
Reviewed-by: Emilio G. Cota <cota@braap.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>

accel/tcg/cputlb.c

@@ -100,17 +100,21 @@ static void flush_all_helper(CPUState *src, run_on_cpu_func fn,
     }
 }
 
-size_t tlb_flush_count(void)
+void tlb_flush_counts(size_t *pfull, size_t *ppart, size_t *pelide)
 {
     CPUState *cpu;
-    size_t count = 0;
+    size_t full = 0, part = 0, elide = 0;
 
     CPU_FOREACH(cpu) {
         CPUArchState *env = cpu->env_ptr;
 
-        count += atomic_read(&env->tlb_flush_count);
+        full += atomic_read(&env->tlb_c.full_flush_count);
+        part += atomic_read(&env->tlb_c.part_flush_count);
+        elide += atomic_read(&env->tlb_c.elide_flush_count);
     }
-    return count;
+    *pfull = full;
+    *ppart = part;
+    *pelide = elide;
 }
 
 static void tlb_flush_one_mmuidx_locked(CPUArchState *env, int mmu_idx)
@@ -145,7 +149,11 @@ static void tlb_flush_by_mmuidx_async_work(CPUState *cpu, run_on_cpu_data data)
     cpu_tb_jmp_cache_clear(cpu);
 
     if (mmu_idx_bitmask == ALL_MMUIDX_BITS) {
-        atomic_set(&env->tlb_flush_count, env->tlb_flush_count + 1);
+        atomic_set(&env->tlb_c.full_flush_count,
+                   env->tlb_c.full_flush_count + 1);
+    } else {
+        atomic_set(&env->tlb_c.part_flush_count,
+                   env->tlb_c.part_flush_count + ctpop16(mmu_idx_bitmask));
     }
 }
 

accel/tcg/translate-all.c

@@ -2290,7 +2290,7 @@ void dump_exec_info(FILE *f, fprintf_function cpu_fprintf)
 {
     struct tb_tree_stats tst = {};
     struct qht_stats hst;
-    size_t nb_tbs;
+    size_t nb_tbs, flush_full, flush_part, flush_elide;
 
     tcg_tb_foreach(tb_tree_stats_iter, &tst);
     nb_tbs = tst.nb_tbs;
@@ -2326,7 +2326,11 @@ void dump_exec_info(FILE *f, fprintf_function cpu_fprintf)
     cpu_fprintf(f, "TB flush count      %u\n",
                 atomic_read(&tb_ctx.tb_flush_count));
     cpu_fprintf(f, "TB invalidate count %zu\n", tcg_tb_phys_invalidate_count());
-    cpu_fprintf(f, "TLB flush count     %zu\n", tlb_flush_count());
+
+    tlb_flush_counts(&flush_full, &flush_part, &flush_elide);
+    cpu_fprintf(f, "TLB full flushes    %zu\n", flush_full);
+    cpu_fprintf(f, "TLB partial flushes %zu\n", flush_part);
+    cpu_fprintf(f, "TLB elided flushes  %zu\n", flush_elide);
     tcg_dump_info(f, cpu_fprintf);
 }
 

include/exec/cpu-defs.h

@@ -166,6 +166,15 @@ typedef struct CPUTLBCommon {
      * mmu_idx may be discarded.  Protected by tlb_c.lock.
      */
     uint16_t pending_flush;
+
+    /*
+     * Statistics.  These are not lock protected, but are read and
+     * written atomically.  This allows the monitor to print a snapshot
+     * of the stats without interfering with the cpu.
+     */
+    size_t full_flush_count;
+    size_t part_flush_count;
+    size_t elide_flush_count;
 } CPUTLBCommon;
 
 /*
@@ -179,8 +188,7 @@ typedef struct CPUTLBCommon {
     CPUTLBEntry tlb_table[NB_MMU_MODES][CPU_TLB_SIZE];                  \
     CPUTLBEntry tlb_v_table[NB_MMU_MODES][CPU_VTLB_SIZE];               \
     CPUIOTLBEntry iotlb[NB_MMU_MODES][CPU_TLB_SIZE];                    \
-    CPUIOTLBEntry iotlb_v[NB_MMU_MODES][CPU_VTLB_SIZE];                 \
-    size_t tlb_flush_count;
+    CPUIOTLBEntry iotlb_v[NB_MMU_MODES][CPU_VTLB_SIZE];
 
 #else
 

include/exec/cputlb.h

@@ -23,6 +23,6 @@
 /* cputlb.c */
 void tlb_protect_code(ram_addr_t ram_addr);
 void tlb_unprotect_code(ram_addr_t ram_addr);
-size_t tlb_flush_count(void);
+void tlb_flush_counts(size_t *full, size_t *part, size_t *elide);
 #endif
 #endif