Merge remote-tracking branch 'remotes/stsquad/tags/pull-plugin-updates-180221-1' into staging

Plugin updates:

  - expose vdev name in PCI memory registration
  - new hwprofile plugin
  - bunch of style cleanups to contrib/plugins
  - fix call signature of inline instrumentation
  - re-factor the io_recompile code to push specialisation into hooks
  - add some acceptance tests for the plugins
  - clean-up and remove CF_NOCACHE handling from TCG
  - fix instrumentation of cpu_io_recompile sections
  - expand tests to check inline and cb count the same

# gpg: Signature made Thu 18 Feb 2021 08:24:57 GMT
# gpg:                using RSA key 6685AE99E75167BCAFC8DF35FBD0DB095A9E2A44
# gpg: Good signature from "Alex Bennée (Master Work Key) <[email protected]>" [full]
# Primary key fingerprint: 6685 AE99 E751 67BC AFC8  DF35 FBD0 DB09 5A9E 2A44

* remotes/stsquad/tags/pull-plugin-updates-180221-1: (23 commits)
  tests/acceptance: add a memory callback check
  tests/plugin: allow memory plugin to do both inline and callbacks
  tests/acceptance: add a new tests to detect counting errors
  accel/tcg: allow plugin instrumentation to be disable via cflags
  accel/tcg: remove CF_NOCACHE and special cases
  accel/tcg: re-factor non-RAM execution code
  accel/tcg: cache single instruction TB on pending replay exception
  accel/tcg: actually cache our partial icount TB
  tests/acceptance: add a new set of tests to exercise plugins
  tests/plugin: expand insn test to detect duplicate instructions
  target/sh4: Create superh_io_recompile_replay_branch
  target/mips: Create mips_io_recompile_replay_branch
  accel/tcg: Create io_recompile_replay_branch hook
  exec: Move TranslationBlock typedef to qemu/typedefs.h
  accel/tcg/plugin-gen: fix the call signature for inline callbacks
  contrib: Open brace '{' following struct go on the same line
  contrib: space required after that ','
  contrib: Add spaces around operator
  contrib: Fix some code style problems, ERROR: "foo * bar" should be "foo *bar"
  contrib: Don't use '#' flag of printf format
  ...

Signed-off-by: Peter Maydell <[email protected]>

Author: pm215

MAINTAINERS

@@ -2903,6 +2903,7 @@ S: Maintained
 F: docs/devel/tcg-plugins.rst
 F: plugins/
 F: tests/plugin/
+F: tests/acceptance/tcg_plugins.py
 F: contrib/plugins/
 
 AArch64 TCG target

accel/tcg/cpu-exec.c

@@ -224,40 +224,6 @@ cpu_tb_exec(CPUState *cpu, TranslationBlock *itb, int *tb_exit)
     return last_tb;
 }
 
-#ifndef CONFIG_USER_ONLY
-/* Execute the code without caching the generated code. An interpreter
-   could be used if available. */
-static void cpu_exec_nocache(CPUState *cpu, int max_cycles,
-                             TranslationBlock *orig_tb, bool ignore_icount)
-{
-    TranslationBlock *tb;
-    uint32_t cflags = curr_cflags() | CF_NOCACHE;
-    int tb_exit;
-
-    if (ignore_icount) {
-        cflags &= ~CF_USE_ICOUNT;
-    }
-
-    /* Should never happen.
-       We only end up here when an existing TB is too long.  */
-    cflags |= MIN(max_cycles, CF_COUNT_MASK);
-
-    mmap_lock();
-    tb = tb_gen_code(cpu, orig_tb->pc, orig_tb->cs_base,
-                     orig_tb->flags, cflags);
-    tb->orig_tb = orig_tb;
-    mmap_unlock();
-
-    /* execute the generated code */
-    trace_exec_tb_nocache(tb, tb->pc);
-    cpu_tb_exec(cpu, tb, &tb_exit);
-
-    mmap_lock();
-    tb_phys_invalidate(tb, -1);
-    mmap_unlock();
-    tcg_tb_remove(tb);
-}
-#endif
 
 static void cpu_exec_enter(CPUState *cpu)
 {
@@ -524,15 +490,12 @@ static inline bool cpu_handle_exception(CPUState *cpu, int *ret)
 #ifndef CONFIG_USER_ONLY
         if (replay_has_exception()
             && cpu_neg(cpu)->icount_decr.u16.low + cpu->icount_extra == 0) {
-            /* try to cause an exception pending in the log */
-            cpu_exec_nocache(cpu, 1, tb_find(cpu, NULL, 0, curr_cflags()), true);
+            /* Execute just one insn to trigger exception pending in the log */
+            cpu->cflags_next_tb = (curr_cflags() & ~CF_USE_ICOUNT) | 1;
         }
 #endif
-        if (cpu->exception_index < 0) {
-            return false;
-        }
+        return false;
     }
-
     if (cpu->exception_index >= EXCP_INTERRUPT) {
         /* exit request from the cpu execution loop */
         *ret = cpu->exception_index;
@@ -688,6 +651,7 @@ static inline bool cpu_handle_interrupt(CPUState *cpu,
     /* Finally, check if we need to exit to the main loop.  */
     if (unlikely(qatomic_read(&cpu->exit_request))
         || (icount_enabled()
+            && (cpu->cflags_next_tb == -1 || cpu->cflags_next_tb & CF_USE_ICOUNT)
             && cpu_neg(cpu)->icount_decr.u16.low + cpu->icount_extra == 0)) {
         qatomic_set(&cpu->exit_request, 0);
         if (cpu->exception_index == -1) {
@@ -730,16 +694,17 @@ static inline void cpu_loop_exec_tb(CPUState *cpu, TranslationBlock *tb,
     /* Ensure global icount has gone forward */
     icount_update(cpu);
     /* Refill decrementer and continue execution.  */
-    insns_left = MIN(0xffff, cpu->icount_budget);
+    insns_left = MIN(CF_COUNT_MASK, cpu->icount_budget);
     cpu_neg(cpu)->icount_decr.u16.low = insns_left;
     cpu->icount_extra = cpu->icount_budget - insns_left;
-    if (!cpu->icount_extra && insns_left < tb->icount) {
-        /* Execute any remaining instructions, then let the main loop
-         * handle the next event.
-         */
-        if (insns_left > 0) {
-            cpu_exec_nocache(cpu, insns_left, tb, false);
-        }
+
+    /*
+     * If the next tb has more instructions than we have left to
+     * execute we need to ensure we find/generate a TB with exactly
+     * insns_left instructions in it.
+     */
+    if (!cpu->icount_extra && insns_left > 0 && insns_left < tb->icount)  {
+        cpu->cflags_next_tb = (tb->cflags & ~CF_COUNT_MASK) | insns_left;
     }
 #endif
 }

accel/tcg/plugin-gen.c

@@ -320,22 +320,6 @@ static TCGOp *copy_const_ptr(TCGOp **begin_op, TCGOp *op, void *ptr)
     return op;
 }
 
-static TCGOp *copy_const_i64(TCGOp **begin_op, TCGOp *op, uint64_t v)
-{
-    if (TCG_TARGET_REG_BITS == 32) {
-        /* 2x mov_i32 */
-        op = copy_op(begin_op, op, INDEX_op_mov_i32);
-        op->args[1] = tcgv_i32_arg(tcg_constant_i32(v));
-        op = copy_op(begin_op, op, INDEX_op_mov_i32);
-        op->args[1] = tcgv_i32_arg(tcg_constant_i32(v >> 32));
-    } else {
-        /* mov_i64 */
-        op = copy_op(begin_op, op, INDEX_op_mov_i64);
-        op->args[1] = tcgv_i64_arg(tcg_constant_i64(v));
-    }
-    return op;
-}
-
 static TCGOp *copy_extu_tl_i64(TCGOp **begin_op, TCGOp *op)
 {
     if (TARGET_LONG_BITS == 32) {
@@ -374,14 +358,17 @@ static TCGOp *copy_st_i64(TCGOp **begin_op, TCGOp *op)
     return op;
 }
 
-static TCGOp *copy_add_i64(TCGOp **begin_op, TCGOp *op)
+static TCGOp *copy_add_i64(TCGOp **begin_op, TCGOp *op, uint64_t v)
 {
     if (TCG_TARGET_REG_BITS == 32) {
         /* all 32-bit backends must implement add2_i32 */
         g_assert(TCG_TARGET_HAS_add2_i32);
         op = copy_op(begin_op, op, INDEX_op_add2_i32);
+        op->args[4] = tcgv_i32_arg(tcg_constant_i32(v));
+        op->args[5] = tcgv_i32_arg(tcg_constant_i32(v >> 32));
     } else {
         op = copy_op(begin_op, op, INDEX_op_add_i64);
+        op->args[2] = tcgv_i64_arg(tcg_constant_i64(v));
     }
     return op;
 }
@@ -431,6 +418,12 @@ static TCGOp *copy_call(TCGOp **begin_op, TCGOp *op, void *empty_func,
     return op;
 }
 
+/*
+ * When we append/replace ops here we are sensitive to changing patterns of
+ * TCGOps generated by the tcg_gen_FOO calls when we generated the
+ * empty callbacks. This will assert very quickly in a debug build as
+ * we assert the ops we are replacing are the correct ones.
+ */
 static TCGOp *append_udata_cb(const struct qemu_plugin_dyn_cb *cb,
                               TCGOp *begin_op, TCGOp *op, int *cb_idx)
 {
@@ -462,11 +455,8 @@ static TCGOp *append_inline_cb(const struct qemu_plugin_dyn_cb *cb,
     /* ld_i64 */
     op = copy_ld_i64(&begin_op, op);
 
-    /* const_i64 */
-    op = copy_const_i64(&begin_op, op, cb->inline_insn.imm);
-
     /* add_i64 */
-    op = copy_add_i64(&begin_op, op);
+    op = copy_add_i64(&begin_op, op, cb->inline_insn.imm);
 
     /* st_i64 */
     op = copy_st_i64(&begin_op, op);
@@ -852,7 +842,7 @@ static void plugin_gen_inject(const struct qemu_plugin_tb *plugin_tb)
     pr_ops();
 }
 
-bool plugin_gen_tb_start(CPUState *cpu, const TranslationBlock *tb)
+bool plugin_gen_tb_start(CPUState *cpu, const TranslationBlock *tb, bool mem_only)
 {
     struct qemu_plugin_tb *ptb = tcg_ctx->plugin_tb;
     bool ret = false;
@@ -865,6 +855,7 @@ bool plugin_gen_tb_start(CPUState *cpu, const TranslationBlock *tb)
         ptb->vaddr2 = -1;
         get_page_addr_code_hostp(cpu->env_ptr, tb->pc, &ptb->haddr1);
         ptb->haddr2 = NULL;
+        ptb->mem_only = mem_only;
 
         plugin_gen_empty_callback(PLUGIN_GEN_FROM_TB);
     }