Merge remote-tracking branch 'remotes/rth/tags/pull-tcg-20151007' into staging

Do away with TB retranslation

# gpg: Signature made Wed 07 Oct 2015 10:42:08 BST using RSA key ID 4DD0279B
# gpg: Good signature from "Richard Henderson <rth7680@gmail.com>"
# gpg:                 aka "Richard Henderson <rth@redhat.com>"
# gpg:                 aka "Richard Henderson <rth@twiddle.net>"

* remotes/rth/tags/pull-tcg-20151007: (26 commits)
  tcg: Adjust CODE_GEN_AVG_BLOCK_SIZE
  tcg: Check for overflow via highwater mark
  tcg: Allocate a guard page after code_gen_buffer
  tcg: Emit prologue to the beginning of code_gen_buffer
  tcg: Remove tcg_gen_code_search_pc
  tcg: Remove gen_intermediate_code_pc
  tcg: Save insn data and use it in cpu_restore_state_from_tb
  tcg: Pass data argument to restore_state_to_opc
  tcg: Add TCG_MAX_INSNS
  target-*: Drop cpu_gen_code define
  tcg: Merge cpu_gen_code into tb_gen_code
  target-sparc: Add npc state to insn_start
  target-sparc: Remove gen_opc_jump_pc
  target-sparc: Split out gen_branch_n
  target-sparc: Tidy gen_branch_a interface
  target-cris: Mirror gen_opc_pc into insn_start
  target-sh4: Add flags state to insn_start
  target-s390x: Add cc_op state to insn_start
  target-mips: Add delayed branch state to insn_start
  target-i386: Add cc_op state to insn_start
  ...

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>

2 files changed, 24 insertions, 15 deletions

diff --git a/include/exec/exec-all.h b/include/exec/exec-all.h
index a3719b7f0d..a63fd6015e 100644
--- a/include/exec/exec-all.h
+++ b/include/exec/exec-all.h
@@ -62,24 +62,15 @@ typedef struct TranslationBlock TranslationBlock;
 #define OPC_BUF_SIZE 640
 #define OPC_MAX_SIZE (OPC_BUF_SIZE - MAX_OP_PER_INSTR)
 
-/* Maximum size a TCG op can expand to.  This is complicated because a
-   single op may require several host instructions and register reloads.
-   For now take a wild guess at 192 bytes, which should allow at least
-   a couple of fixup instructions per argument.  */
-#define TCG_MAX_OP_SIZE 192
-
 #define OPPARAM_BUF_SIZE (OPC_BUF_SIZE * MAX_OPC_PARAM)
 
 #include "qemu/log.h"
 
 void gen_intermediate_code(CPUArchState *env, struct TranslationBlock *tb);
-void gen_intermediate_code_pc(CPUArchState *env, struct TranslationBlock *tb);
 void restore_state_to_opc(CPUArchState *env, struct TranslationBlock *tb,
-                          int pc_pos);
+                          target_ulong *data);
 
 void cpu_gen_init(void);
-int cpu_gen_code(CPUArchState *env, struct TranslationBlock *tb,
-                 int *gen_code_size_ptr);
 bool cpu_restore_state(CPUState *cpu, uintptr_t searched_pc);
 void page_size_init(void);
 
@@ -170,13 +161,14 @@ static inline void tlb_flush_by_mmuidx(CPUState *cpu, ...)
 #define CODE_GEN_PHYS_HASH_BITS     15
 #define CODE_GEN_PHYS_HASH_SIZE     (1 << CODE_GEN_PHYS_HASH_BITS)
 
-/* estimated block size for TB allocation */
-/* XXX: use a per code average code fragment size and modulate it
-   according to the host CPU */
+/* Estimated block size for TB allocation.  */
+/* ??? The following is based on a 2015 survey of x86_64 host output.
+   Better would seem to be some sort of dynamically sized TB array,
+   adapting to the block sizes actually being produced.  */
 #if defined(CONFIG_SOFTMMU)
-#define CODE_GEN_AVG_BLOCK_SIZE 128
+#define CODE_GEN_AVG_BLOCK_SIZE 400
 #else
-#define CODE_GEN_AVG_BLOCK_SIZE 64
+#define CODE_GEN_AVG_BLOCK_SIZE 150
 #endif
 
 #if defined(__arm__) || defined(_ARCH_PPC) \
@@ -201,6 +193,7 @@ struct TranslationBlock {
 #define CF_USE_ICOUNT  0x20000
 
     void *tc_ptr;    /* pointer to the translated code */
+    uint8_t *tc_search;  /* pointer to search data */
     /* next matching tb for physical address. */
     struct TranslationBlock *phys_hash_next;
     /* original tb when cflags has CF_NOCACHE */
diff --git a/include/qom/cpu.h b/include/qom/cpu.h
index 9405554a2b..b613ff0329 100644
--- a/include/qom/cpu.h
+++ b/include/qom/cpu.h
@@ -721,6 +721,7 @@ void cpu_single_step(CPUState *cpu, int enabled);
 /* 0x08 currently unused */
 #define BP_GDB                0x10
 #define BP_CPU                0x20
+#define BP_ANY                (BP_GDB | BP_CPU)
 #define BP_WATCHPOINT_HIT_READ 0x40
 #define BP_WATCHPOINT_HIT_WRITE 0x80
 #define BP_WATCHPOINT_HIT (BP_WATCHPOINT_HIT_READ | BP_WATCHPOINT_HIT_WRITE)
@@ -731,6 +732,21 @@ int cpu_breakpoint_remove(CPUState *cpu, vaddr pc, int flags);
 void cpu_breakpoint_remove_by_ref(CPUState *cpu, CPUBreakpoint *breakpoint);
 void cpu_breakpoint_remove_all(CPUState *cpu, int mask);
 
+/* Return true if PC matches an installed breakpoint.  */
+static inline bool cpu_breakpoint_test(CPUState *cpu, vaddr pc, int mask)
+{
+    CPUBreakpoint *bp;
+
+    if (unlikely(!QTAILQ_EMPTY(&cpu->breakpoints))) {
+        QTAILQ_FOREACH(bp, &cpu->breakpoints, entry) {
+            if (bp->pc == pc && (bp->flags & mask)) {
+                return true;
+            }
+        }
+    }
+    return false;
+}
+
 int cpu_watchpoint_insert(CPUState *cpu, vaddr addr, vaddr len,
                           int flags, CPUWatchpoint **watchpoint);
 int cpu_watchpoint_remove(CPUState *cpu, vaddr addr,