cputlb: read CPUTLBEntry.addr_write atomically

Updates can come from other threads, so readers that do not
take tlb_lock must use atomic_read to avoid undefined
behaviour (UB).

This completes the conversion to tlb_lock. This conversion results
on average in no performance loss, as the following experiments
(run on an Intel i7-6700K CPU @ 4.00GHz) show.

1. aarch64 bootup+shutdown test:

- Before:
 Performance counter stats for 'taskset -c 0 ../img/aarch64/die.sh' (10 runs):

       7487.087786      task-clock (msec)         #    0.998 CPUs utilized            ( +-  0.12% )
    31,574,905,303      cycles                    #    4.217 GHz                      ( +-  0.12% )
    57,097,908,812      instructions              #    1.81  insns per cycle          ( +-  0.08% )
    10,255,415,367      branches                  # 1369.747 M/sec                    ( +-  0.08% )
       173,278,962      branch-misses             #    1.69% of all branches          ( +-  0.18% )

       7.504481349 seconds time elapsed                                          ( +-  0.14% )

- After:
 Performance counter stats for 'taskset -c 0 ../img/aarch64/die.sh' (10 runs):

       7462.441328      task-clock (msec)         #    0.998 CPUs utilized            ( +-  0.07% )
    31,478,476,520      cycles                    #    4.218 GHz                      ( +-  0.07% )
    57,017,330,084      instructions              #    1.81  insns per cycle          ( +-  0.05% )
    10,251,929,667      branches                  # 1373.804 M/sec                    ( +-  0.05% )
       173,023,787      branch-misses             #    1.69% of all branches          ( +-  0.11% )

       7.474970463 seconds time elapsed                                          ( +-  0.07% )

2. SPEC06int:
                                              SPEC06int (test set)
                                           [Y axis: Speedup over master]
  1.15 +-+----+------+------+------+------+------+-------+------+------+------+------+------+------+----+-+
       |                                                                                                  |
   1.1 +-+.................................+++.............................+  tlb-lock-v2 (m+++x)       +-+
       |                                +++ |                   +++        tlb-lock-v3 (spinl|ck)         |
       |                    +++          |  |     +++    +++     |                           |            |
  1.05 +-+....+++...........####.........|####.+++.|......|.....###....+++...........+++....###.........+-+
       |      ###         ++#| #         |# |# ***### +++### +++#+#     |     +++     |     #|#    ###    |
     1 +-+++***+#++++####+++#++#++++++++++#++#+*+*++#++++#+#+****+#++++###++++###++++###++++#+#++++#+#+++-+
       |    *+* #    #++# ***  #   #### ***  # * *++# ****+# *| * # ****|#   |# #    #|#    #+#    # #    |
  0.95 +-+..*.*.#....#..#.*|*..#...#..#.*|*..#.*.*..#.*|.*.#.*++*.#.*++*+#.****.#....#+#....#.#..++#.#..+-+
       |    * * #    #  # *|*  #   #  # *|*  # * *  # *++* # *  * # *  * # * |* #  ++# #    # #  *** #    |
       |    * * #  ++#  # *+*  #   #  # *|*  # * *  # *  * # *  * # *  * # *++* # **** #  ++# #  * * #    |
   0.9 +-+..*.*.#...|#..#.*.*..#.++#..#.*|*..#.*.*..#.*..*.#.*..*.#.*..*.#.*..*.#.*.|*.#...|#.#..*.*.#..+-+
       |    * * #  ***  # * *  #  |#  # *+*  # * *  # *  * # *  * # *  * # *  * # *++* #   |# #  * * #    |
  0.85 +-+..*.*.#..*|*..#.*.*..#.***..#.*.*..#.*.*..#.*..*.#.*..*.#.*..*.#.*..*.#.*..*.#.****.#..*.*.#..+-+
       |    * * #  *+*  # * *  # *|*  # * *  # * *  # *  * # *  * # *  * # *  * # *  * # * |* #  * * #    |
       |    * * #  * *  # * *  # *+*  # * *  # * *  # *  * # *  * # *  * # *  * # *  * # * |* #  * * #    |
   0.8 +-+..*.*.#..*.*..#.*.*..#.*.*..#.*.*..#.*.*..#.*..*.#.*..*.#.*..*.#.*..*.#.*..*.#.*++*.#..*.*.#..+-+
       |    * * #  * *  # * *  # * *  # * *  # * *  # *  * # *  * # *  * # *  * # *  * # *  * #  * * #    |
  0.75 +-+--***##--***###-***###-***###-***###-***###-****##-****##-****##-****##-****##-****##--***##--+-+
 400.perlben401.bzip2403.gcc429.m445.gob456.hmme45462.libqua464.h26471.omnet473483.xalancbmkgeomean

  png: https://imgur.com/a/BHzpPTW

Notes:
- tlb-lock-v2 corresponds to an implementation with a mutex.
- tlb-lock-v3 corresponds to the current implementation, i.e.
  a spinlock and a single lock acquisition in tlb_set_page_with_attrs.

Signed-off-by: Emilio G. Cota <cota@braap.org>
Message-Id: <20181016153840.25877-1-cota@braap.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>

include/exec/cpu_ldst.h

@@ -126,6 +126,15 @@ extern __thread uintptr_t helper_retaddr;
 /* The memory helpers for tcg-generated code need tcg_target_long etc.  */
 #include "tcg.h"
 
+static inline target_ulong tlb_addr_write(const CPUTLBEntry *entry)
+{
+#if TCG_OVERSIZED_GUEST
+    return entry->addr_write;
+#else
+    return atomic_read(&entry->addr_write);
+#endif
+}
+
 /* Find the TLB index corresponding to the mmu_idx + address pair.  */
 static inline uintptr_t tlb_index(CPUArchState *env, uintptr_t mmu_idx,
                                   target_ulong addr)
@@ -439,7 +448,7 @@ static inline void *tlb_vaddr_to_host(CPUArchState *env, abi_ptr addr,
         tlb_addr = tlbentry->addr_read;
         break;
     case 1:
-        tlb_addr = tlbentry->addr_write;
+        tlb_addr = tlb_addr_write(tlbentry);
         break;
     case 2:
         tlb_addr = tlbentry->addr_code;