Merge tag 'pull-maintainer-updates-060324-1' of https://gitlab.com/stsquad/qemu into staging

maintainer updates (tests, gdbstub, plugins):

  - expand QOS_PATH_MAX_ELEMENT_SIZE to avoid LTO issues
  - support fork-follow-mode in gdbstub
  - new thread-safe scoreboard API for TCG plugins
  - suppress showing opcodes in plugin disassembly

# -----BEGIN PGP SIGNATURE-----
#
# iQEzBAABCgAdFiEEZoWumedRZ7yvyN81+9DbCVqeKkQFAmXoY7oACgkQ+9DbCVqe
# KkTdTwf8D8nUB+Ee6LuglW36vtd1ETdMfUmfRis7RIBsXZZ0Tg4+8LyfKkNi1vCL
# UMdWQTkSW79RfXr21QEtETokwLZ0CWQMdxDAWfOiz4S+uDgQyBE+lwUsy0mHBmd7
# +J4SQb3adoZ+//9KMJhRU1wL9j3ygpEoKHVJonDObU6K5XuhE18JuBE44q7FqkWl
# 0VhoLDgNxrf2PqT+LLP/O3MFLDXPVKbzrZYQF0IoqBTlcqShCoaykhSwiwCZ4Sqq
# NO9hVwZIOFOcOF4F6ZqRXaZrwERldoBwG+BeIx1ah20vKFVT12y02dQqdP/oKwe+
# /PXFXDdzs4yMOghb4Go6SiKlKT5g4A==
# =s1lF
# -----END PGP SIGNATURE-----
# gpg: Signature made Wed 06 Mar 2024 12:38:18 GMT
# gpg:                using RSA key 6685AE99E75167BCAFC8DF35FBD0DB095A9E2A44
# gpg: Good signature from "Alex Bennée (Master Work Key) <alex.bennee@linaro.org>" [full]
# Primary key fingerprint: 6685 AE99 E751 67BC AFC8  DF35 FBD0 DB09 5A9E 2A44

* tag 'pull-maintainer-updates-060324-1' of https://gitlab.com/stsquad/qemu: (29 commits)
  target/riscv: honour show_opcodes when disassembling
  target/loongarch: honour show_opcodes when disassembling
  disas/hppa: honour show_opcodes
  disas: introduce show_opcodes
  plugins: cleanup codepath for previous inline operation
  plugins: remove non per_vcpu inline operation from API
  contrib/plugins/howvec: migrate to new per_vcpu API
  contrib/plugins/hotblocks: migrate to new per_vcpu API
  tests/plugin/bb: migrate to new per_vcpu API
  tests/plugin/insn: migrate to new per_vcpu API
  tests/plugin/mem: migrate to new per_vcpu API
  tests/plugin: add test plugin for inline operations
  plugins: add inline operation per vcpu
  plugins: implement inline operation relative to cpu_index
  plugins: define qemu_plugin_u64
  plugins: scoreboard API
  tests/tcg: Add two follow-fork-mode tests
  gdbstub: Implement follow-fork-mode child
  gdbstub: Introduce gdb_handle_detach_user()
  gdbstub: Introduce gdb_handle_set_thread_user()
  ...

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

57 files changed, 1257 insertions, 338 deletions

diff --git a/accel/tcg/plugin-gen.c b/accel/tcg/plugin-gen.c
index ac6b52b..8028786 100644
--- a/accel/tcg/plugin-gen.c
+++ b/accel/tcg/plugin-gen.c
@@ -133,16 +133,28 @@ static void gen_empty_udata_cb_no_rwg(void)
  */
 static void gen_empty_inline_cb(void)
 {
+    TCGv_i32 cpu_index = tcg_temp_ebb_new_i32();
+    TCGv_ptr cpu_index_as_ptr = tcg_temp_ebb_new_ptr();
     TCGv_i64 val = tcg_temp_ebb_new_i64();
     TCGv_ptr ptr = tcg_temp_ebb_new_ptr();
 
+    tcg_gen_ld_i32(cpu_index, tcg_env,
+                   -offsetof(ArchCPU, env) + offsetof(CPUState, cpu_index));
+    /* second operand will be replaced by immediate value */
+    tcg_gen_mul_i32(cpu_index, cpu_index, cpu_index);
+    tcg_gen_ext_i32_ptr(cpu_index_as_ptr, cpu_index);
+
     tcg_gen_movi_ptr(ptr, 0);
+    tcg_gen_add_ptr(ptr, ptr, cpu_index_as_ptr);
     tcg_gen_ld_i64(val, ptr, 0);
-    /* pass an immediate != 0 so that it doesn't get optimized away */
-    tcg_gen_addi_i64(val, val, 0xdeadface);
+    /* second operand will be replaced by immediate value */
+    tcg_gen_add_i64(val, val, val);
+
     tcg_gen_st_i64(val, ptr, 0);
     tcg_temp_free_ptr(ptr);
     tcg_temp_free_i64(val);
+    tcg_temp_free_ptr(cpu_index_as_ptr);
+    tcg_temp_free_i32(cpu_index);
 }
 
 static void gen_empty_mem_cb(TCGv_i64 addr, uint32_t info)
@@ -290,12 +302,37 @@ static TCGOp *copy_const_ptr(TCGOp **begin_op, TCGOp *op, void *ptr)
     return op;
 }
 
+static TCGOp *copy_ld_i32(TCGOp **begin_op, TCGOp *op)
+{
+    return copy_op(begin_op, op, INDEX_op_ld_i32);
+}
+
+static TCGOp *copy_ext_i32_ptr(TCGOp **begin_op, TCGOp *op)
+{
+    if (UINTPTR_MAX == UINT32_MAX) {
+        op = copy_op(begin_op, op, INDEX_op_mov_i32);
+    } else {
+        op = copy_op(begin_op, op, INDEX_op_ext_i32_i64);
+    }
+    return op;
+}
+
+static TCGOp *copy_add_ptr(TCGOp **begin_op, TCGOp *op)
+{
+    if (UINTPTR_MAX == UINT32_MAX) {
+        op = copy_op(begin_op, op, INDEX_op_add_i32);
+    } else {
+        op = copy_op(begin_op, op, INDEX_op_add_i64);
+    }
+    return op;
+}
+
 static TCGOp *copy_ld_i64(TCGOp **begin_op, TCGOp *op)
 {
     if (TCG_TARGET_REG_BITS == 32) {
         /* 2x ld_i32 */
-        op = copy_op(begin_op, op, INDEX_op_ld_i32);
-        op = copy_op(begin_op, op, INDEX_op_ld_i32);
+        op = copy_ld_i32(begin_op, op);
+        op = copy_ld_i32(begin_op, op);
     } else {
         /* ld_i64 */
         op = copy_op(begin_op, op, INDEX_op_ld_i64);
@@ -331,6 +368,13 @@ static TCGOp *copy_add_i64(TCGOp **begin_op, TCGOp *op, uint64_t v)
     return op;
 }
 
+static TCGOp *copy_mul_i32(TCGOp **begin_op, TCGOp *op, uint32_t v)
+{
+    op = copy_op(begin_op, op, INDEX_op_mul_i32);
+    op->args[2] = tcgv_i32_arg(tcg_constant_i32(v));
+    return op;
+}
+
 static TCGOp *copy_st_ptr(TCGOp **begin_op, TCGOp *op)
 {
     if (UINTPTR_MAX == UINT32_MAX) {
@@ -396,18 +440,19 @@ static TCGOp *append_inline_cb(const struct qemu_plugin_dyn_cb *cb,
                                TCGOp *begin_op, TCGOp *op,
                                int *unused)
 {
-    /* const_ptr */
-    op = copy_const_ptr(&begin_op, op, cb->userp);
+    char *ptr = cb->inline_insn.entry.score->data->data;
+    size_t elem_size = g_array_get_element_size(
+        cb->inline_insn.entry.score->data);
+    size_t offset = cb->inline_insn.entry.offset;
 
-    /* ld_i64 */
+    op = copy_ld_i32(&begin_op, op);
+    op = copy_mul_i32(&begin_op, op, elem_size);
+    op = copy_ext_i32_ptr(&begin_op, op);
+    op = copy_const_ptr(&begin_op, op, ptr + offset);
+    op = copy_add_ptr(&begin_op, op);
     op = copy_ld_i64(&begin_op, op);
-
-    /* add_i64 */
     op = copy_add_i64(&begin_op, op, cb->inline_insn.imm);
-
-    /* st_i64 */
     op = copy_st_i64(&begin_op, op);
-
     return op;
 }
 
diff --git a/bsd-user/bsd-file.h b/bsd-user/bsd-file.h
index 3c00dc0..6fa2c30 100644
--- a/bsd-user/bsd-file.h
+++ b/bsd-user/bsd-file.h
@@ -641,7 +641,7 @@ static abi_long do_bsd_readlink(CPUArchState *env, abi_long arg1,
     }
     if (strcmp(p1, "/proc/curproc/file") == 0) {
         CPUState *cpu = env_cpu(env);
-        TaskState *ts = (TaskState *)cpu->opaque;
+        TaskState *ts = get_task_state(cpu);
         strncpy(p2, ts->bprm->fullpath, arg3);
         ret = MIN((abi_long)strlen(ts->bprm->fullpath), arg3);
     } else {
diff --git a/bsd-user/freebsd/os-proc.h b/bsd-user/freebsd/os-proc.h
index d641878..3003c8c 100644
--- a/bsd-user/freebsd/os-proc.h
+++ b/bsd-user/freebsd/os-proc.h
@@ -208,7 +208,7 @@ static inline abi_long do_freebsd_fork(void *cpu_env)
      */
     set_second_rval(cpu_env, child_flag);
 
-    fork_end(child_flag);
+    fork_end(ret);
 
     return ret;
 }
@@ -252,7 +252,7 @@ static inline abi_long do_freebsd_rfork(void *cpu_env, abi_long flags)
      * value: 0 for parent process, 1 for child process.
      */
     set_second_rval(cpu_env, child_flag);
-    fork_end(child_flag);
+    fork_end(ret);
 
     return ret;
 
@@ -285,7 +285,7 @@ static inline abi_long do_freebsd_pdfork(void *cpu_env, abi_ulong target_fdp,
      * value: 0 for parent process, 1 for child process.
      */
     set_second_rval(cpu_env, child_flag);
-    fork_end(child_flag);
+    fork_end(ret);
 
     return ret;
 }
diff --git a/bsd-user/main.c b/bsd-user/main.c
index 512d4ab..3dc285e 100644
--- a/bsd-user/main.c
+++ b/bsd-user/main.c
@@ -113,10 +113,13 @@ void fork_start(void)
     start_exclusive();
     cpu_list_lock();
     mmap_fork_start();
+    gdbserver_fork_start();
 }
 
-void fork_end(int child)
+void fork_end(pid_t pid)
 {
+    bool child = pid == 0;
+
     if (child) {
         CPUState *cpu, *next_cpu;
         /*
@@ -134,10 +137,12 @@ void fork_end(int child)
          * state, so we don't need to end_exclusive() here.
          */
         qemu_init_cpu_list();
-        gdbserver_fork(thread_cpu);
+        get_task_state(thread_cpu)->ts_tid = qemu_get_thread_id();
+        gdbserver_fork_end(thread_cpu, pid);
     } else {
         mmap_fork_end(child);
         cpu_list_unlock();
+        gdbserver_fork_end(thread_cpu, pid);
         end_exclusive();
     }
 }
diff --git a/bsd-user/qemu.h b/bsd-user/qemu.h
index c05c512..1b0a591 100644
--- a/bsd-user/qemu.h
+++ b/bsd-user/qemu.h
@@ -117,6 +117,11 @@ typedef struct TaskState {
     struct target_sigaltstack sigaltstack_used;
 } __attribute__((aligned(16))) TaskState;
 
+static inline TaskState *get_task_state(CPUState *cs)
+{
+    return cs->opaque;
+}
+
 void stop_all_tasks(void);
 extern const char *interp_prefix;
 extern const char *qemu_uname_release;
@@ -187,7 +192,7 @@ void cpu_loop(CPUArchState *env);
 char *target_strerror(int err);
 int get_osversion(void);
 void fork_start(void);
-void fork_end(int child);
+void fork_end(pid_t pid);
 
 #include "qemu/log.h"
 
diff --git a/bsd-user/signal.c b/bsd-user/signal.c
index f4352e4..e9f80a0 100644
--- a/bsd-user/signal.c
+++ b/bsd-user/signal.c
@@ -319,7 +319,7 @@ void host_to_target_siginfo(target_siginfo_t *tinfo, const siginfo_t *info)
 
 int block_signals(void)
 {
-    TaskState *ts = (TaskState *)thread_cpu->opaque;
+    TaskState *ts = get_task_state(thread_cpu);
     sigset_t set;
 
     /*
@@ -359,7 +359,7 @@ void dump_core_and_abort(int target_sig)
 {
     CPUState *cpu = thread_cpu;
     CPUArchState *env = cpu_env(cpu);
-    TaskState *ts = cpu->opaque;
+    TaskState *ts = get_task_state(cpu);
     int core_dumped = 0;
     int host_sig;
     struct sigaction act;
@@ -421,7 +421,7 @@ void queue_signal(CPUArchState *env, int sig, int si_type,
                   target_siginfo_t *info)
 {
     CPUState *cpu = env_cpu(env);
-    TaskState *ts = cpu->opaque;
+    TaskState *ts = get_task_state(cpu);
 
     trace_user_queue_signal(env, sig);
 
@@ -476,7 +476,7 @@ void force_sig_fault(int sig, int code, abi_ulong addr)
 static void host_signal_handler(int host_sig, siginfo_t *info, void *puc)
 {
     CPUState *cpu = thread_cpu;
-    TaskState *ts = cpu->opaque;
+    TaskState *ts = get_task_state(cpu);
     target_siginfo_t tinfo;
     ucontext_t *uc = puc;
     struct emulated_sigtable *k;
@@ -585,7 +585,7 @@ static void host_signal_handler(int host_sig, siginfo_t *info, void *puc)
 /* compare to kern/kern_sig.c sys_sigaltstack() and kern_sigaltstack() */
 abi_long do_sigaltstack(abi_ulong uss_addr, abi_ulong uoss_addr, abi_ulong sp)
 {
-    TaskState *ts = (TaskState *)thread_cpu->opaque;
+    TaskState *ts = get_task_state(thread_cpu);
     int ret;
     target_stack_t oss;
 
@@ -714,7 +714,7 @@ int do_sigaction(int sig, const struct target_sigaction *act,
 static inline abi_ulong get_sigframe(struct target_sigaction *ka,
         CPUArchState *env, size_t frame_size)
 {
-    TaskState *ts = (TaskState *)thread_cpu->opaque;
+    TaskState *ts = get_task_state(thread_cpu);
     abi_ulong sp;
 
     /* Use default user stack */
@@ -789,7 +789,7 @@ static int reset_signal_mask(target_ucontext_t *ucontext)
     int i;
     sigset_t blocked;
     target_sigset_t target_set;
-    TaskState *ts = (TaskState *)thread_cpu->opaque;
+    TaskState *ts = get_task_state(thread_cpu);
 
     for (i = 0; i < TARGET_NSIG_WORDS; i++) {
         __get_user(target_set.__bits[i], &ucontext->uc_sigmask.__bits[i]);
@@ -839,7 +839,7 @@ badframe:
 
 void signal_init(void)
 {
-    TaskState *ts = (TaskState *)thread_cpu->opaque;
+    TaskState *ts = get_task_state(thread_cpu);
     struct sigaction act;
     struct sigaction oact;
     int i;
@@ -878,7 +878,7 @@ static void handle_pending_signal(CPUArchState *env, int sig,
                                   struct emulated_sigtable *k)
 {
     CPUState *cpu = env_cpu(env);
-    TaskState *ts = cpu->opaque;
+    TaskState *ts = get_task_state(cpu);
     struct target_sigaction *sa;
     int code;
     sigset_t set;
@@ -967,7 +967,7 @@ void process_pending_signals(CPUArchState *env)
     int sig;
     sigset_t *blocked_set, set;
     struct emulated_sigtable *k;
-    TaskState *ts = cpu->opaque;
+    TaskState *ts = get_task_state(cpu);
 
     while (qatomic_read(&ts->signal_pending)) {
         sigfillset(&set);
diff --git a/contrib/plugins/hotblocks.c b/contrib/plugins/hotblocks.c
index 4de1b13..02bc507 100644
--- a/contrib/plugins/hotblocks.c
+++ b/contrib/plugins/hotblocks.c
@@ -34,8 +34,8 @@ static guint64 limit = 20;
  */
 typedef struct {
     uint64_t start_addr;
-    uint64_t exec_count;
-    int      trans_count;
+    struct qemu_plugin_scoreboard *exec_count;
+    int trans_count;
     unsigned long insns;
 } ExecCount;
 
@@ -43,7 +43,17 @@ static gint cmp_exec_count(gconstpointer a, gconstpointer b)
 {
     ExecCount *ea = (ExecCount *) a;
     ExecCount *eb = (ExecCount *) b;
-    return ea->exec_count > eb->exec_count ? -1 : 1;
+    uint64_t count_a =
+        qemu_plugin_u64_sum(qemu_plugin_scoreboard_u64(ea->exec_count));
+    uint64_t count_b =
+        qemu_plugin_u64_sum(qemu_plugin_scoreboard_u64(eb->exec_count));
+    return count_a > count_b ? -1 : 1;
+}
+
+static void exec_count_free(gpointer key, gpointer value, gpointer user_data)
+{
+    ExecCount *cnt = value;
+    qemu_plugin_scoreboard_free(cnt->exec_count);
 }
 
 static void plugin_exit(qemu_plugin_id_t id, void *p)
@@ -52,7 +62,6 @@ static void plugin_exit(qemu_plugin_id_t id, void *p)
     GList *counts, *it;
     int i;
 
-    g_mutex_lock(&lock);
     g_string_append_printf(report, "%d entries in the hash table\n",
                            g_hash_table_size(hotblocks));
     counts = g_hash_table_get_values(hotblocks);
@@ -63,16 +72,21 @@ static void plugin_exit(qemu_plugin_id_t id, void *p)
 
         for (i = 0; i < limit && it->next; i++, it = it->next) {
             ExecCount *rec = (ExecCount *) it->data;
-            g_string_append_printf(report, "0x%016"PRIx64", %d, %ld, %"PRId64"\n",
-                                   rec->start_addr, rec->trans_count,
-                                   rec->insns, rec->exec_count);
+            g_string_append_printf(
+                report, "0x%016"PRIx64", %d, %ld, %"PRId64"\n",
+                rec->start_addr, rec->trans_count,
+                rec->insns,
+                qemu_plugin_u64_sum(
+                    qemu_plugin_scoreboard_u64(rec->exec_count)));
         }
 
         g_list_free(it);
     }
-    g_mutex_unlock(&lock);
 
     qemu_plugin_outs(report->str);
+
+    g_hash_table_foreach(hotblocks, exec_count_free, NULL);
+    g_hash_table_destroy(hotblocks);
 }
 
 static void plugin_init(void)
@@ -82,15 +96,9 @@ static void plugin_init(void)
 
 static void vcpu_tb_exec(unsigned int cpu_index, void *udata)
 {
-    ExecCount *cnt;
-    uint64_t hash = (uint64_t) udata;
-
-    g_mutex_lock(&lock);
-    cnt = (ExecCount *) g_hash_table_lookup(hotblocks, (gconstpointer) hash);
-    /* should always succeed */
-    g_assert(cnt);
-    cnt->exec_count++;
-    g_mutex_unlock(&lock);
+    ExecCount *cnt = (ExecCount *)udata;
+    qemu_plugin_u64_add(qemu_plugin_scoreboard_u64(cnt->exec_count),
+                        cpu_index, 1);
 }
 
 /*
@@ -114,18 +122,20 @@ static void vcpu_tb_trans(qemu_plugin_id_t id, struct qemu_plugin_tb *tb)
         cnt->start_addr = pc;
         cnt->trans_count = 1;
         cnt->insns = insns;
+        cnt->exec_count = qemu_plugin_scoreboard_new(sizeof(uint64_t));
         g_hash_table_insert(hotblocks, (gpointer) hash, (gpointer) cnt);
     }
 
     g_mutex_unlock(&lock);
 
     if (do_inline) {
-        qemu_plugin_register_vcpu_tb_exec_inline(tb, QEMU_PLUGIN_INLINE_ADD_U64,
-                                                 &cnt->exec_count, 1);
+        qemu_plugin_register_vcpu_tb_exec_inline_per_vcpu(
+            tb, QEMU_PLUGIN_INLINE_ADD_U64,
+            qemu_plugin_scoreboard_u64(cnt->exec_count), 1);
     } else {
         qemu_plugin_register_vcpu_tb_exec_cb(tb, vcpu_tb_exec,
                                              QEMU_PLUGIN_CB_NO_REGS,
-                                             (void *)hash);
+                                             (void *)cnt);
     }
 }
 
diff --git a/contrib/plugins/howvec.c b/contrib/plugins/howvec.c
index 644a785..2d10c87 100644
--- a/contrib/plugins/howvec.c
+++ b/contrib/plugins/howvec.c
@@ -43,13 +43,13 @@ typedef struct {
     uint32_t mask;
     uint32_t pattern;
     CountType what;
-    uint64_t count;
+    qemu_plugin_u64 count;
 } InsnClassExecCount;
 
 typedef struct {
     char *insn;
     uint32_t opcode;
-    uint64_t count;
+    qemu_plugin_u64 count;
     InsnClassExecCount *class;
 } InsnExecCount;
 
@@ -159,7 +159,9 @@ static gint cmp_exec_count(gconstpointer a, gconstpointer b)
 {
     InsnExecCount *ea = (InsnExecCount *) a;
     InsnExecCount *eb = (InsnExecCount *) b;
-    return ea->count > eb->count ? -1 : 1;
+    uint64_t count_a = qemu_plugin_u64_sum(ea->count);
+    uint64_t count_b = qemu_plugin_u64_sum(eb->count);
+    return count_a > count_b ? -1 : 1;
 }
 
 static void free_record(gpointer data)
@@ -167,12 +169,14 @@ static void free_record(gpointer data)
     InsnExecCount *rec = (InsnExecCount *) data;
     g_free(rec->insn);
     g_free(rec);
+    qemu_plugin_scoreboard_free(rec->count.score);
 }
 
 static void plugin_exit(qemu_plugin_id_t id, void *p)
 {
     g_autoptr(GString) report = g_string_new("Instruction Classes:\n");
     int i;
+    uint64_t total_count;
     GList *counts;
     InsnClassExecCount *class = NULL;
 
@@ -180,11 +184,12 @@ static void plugin_exit(qemu_plugin_id_t id, void *p)
         class = &class_table[i];
         switch (class->what) {
         case COUNT_CLASS:
-            if (class->count || verbose) {
+            total_count = qemu_plugin_u64_sum(class->count);
+            if (total_count || verbose) {
                 g_string_append_printf(report,
                                        "Class: %-24s\t(%" PRId64 " hits)\n",
                                        class->class,
-                                       class->count);
+                                       total_count);
             }
             break;
         case COUNT_INDIVIDUAL:
@@ -212,7 +217,7 @@ static void plugin_exit(qemu_plugin_id_t id, void *p)
                                    "Instr: %-24s\t(%" PRId64 " hits)"
                                    "\t(op=0x%08x/%s)\n",
                                    rec->insn,
-                                   rec->count,
+                                   qemu_plugin_u64_sum(rec->count),
                                    rec->opcode,
                                    rec->class ?
                                    rec->class->class : "un-categorised");
@@ -221,6 +226,12 @@ static void plugin_exit(qemu_plugin_id_t id, void *p)
     }
 
     g_hash_table_destroy(insns);
+    for (i = 0; i < ARRAY_SIZE(class_tables); i++) {
+        for (int j = 0; j < class_tables[i].table_sz; ++j) {
+            qemu_plugin_scoreboard_free(class_tables[i].table[j].count.score);
+        }
+    }
+
 
     qemu_plugin_outs(report->str);
 }
@@ -232,11 +243,12 @@ static void plugin_init(void)
 
 static void vcpu_insn_exec_before(unsigned int cpu_index, void *udata)
 {
-    uint64_t *count = (uint64_t *) udata;
-    (*count)++;
+    struct qemu_plugin_scoreboard *score = udata;
+    qemu_plugin_u64_add(qemu_plugin_scoreboard_u64(score), cpu_index, 1);
 }
 
-static uint64_t *find_counter(struct qemu_plugin_insn *insn)
+static struct qemu_plugin_scoreboard *find_counter(
+    struct qemu_plugin_insn *insn)
 {
     int i;
     uint64_t *cnt = NULL;
@@ -265,7 +277,7 @@ static uint64_t *find_counter(struct qemu_plugin_insn *insn)
     case COUNT_NONE:
         return NULL;
     case COUNT_CLASS:
-        return &class->count;
+        return class->count.score;
     case COUNT_INDIVIDUAL:
     {
         InsnExecCount *icount;
@@ -279,13 +291,16 @@ static uint64_t *find_counter(struct qemu_plugin_insn *insn)
             icount->opcode = opcode;
             icount->insn = qemu_plugin_insn_disas(insn);
             icount->class = class;
+            struct qemu_plugin_scoreboard *score =
+                qemu_plugin_scoreboard_new(sizeof(uint64_t));
+            icount->count = qemu_plugin_scoreboard_u64(score);
 
             g_hash_table_insert(insns, GUINT_TO_POINTER(opcode),
                                 (gpointer) icount);
         }
         g_mutex_unlock(&lock);
 
-        return &icount->count;
+        return icount->count.score;
     }
     default:
         g_assert_not_reached();
@@ -300,14 +315,14 @@ static void vcpu_tb_trans(qemu_plugin_id_t id, struct qemu_plugin_tb *tb)
     size_t i;
 
     for (i = 0; i < n; i++) {
-        uint64_t *cnt;
         struct qemu_plugin_insn *insn = qemu_plugin_tb_get_insn(tb, i);
-        cnt = find_counter(insn);
+        struct qemu_plugin_scoreboard *cnt = find_counter(insn);
 
         if (cnt) {
             if (do_inline) {
-                qemu_plugin_register_vcpu_insn_exec_inline(
-                    insn, QEMU_PLUGIN_INLINE_ADD_U64, cnt, 1);
+                qemu_plugin_register_vcpu_insn_exec_inline_per_vcpu(
+                    insn, QEMU_PLUGIN_INLINE_ADD_U64,
+                    qemu_plugin_scoreboard_u64(cnt), 1);
             } else {
                 qemu_plugin_register_vcpu_insn_exec_cb(
                     insn, vcpu_insn_exec_before, QEMU_PLUGIN_CB_NO_REGS, cnt);
@@ -322,6 +337,14 @@ QEMU_PLUGIN_EXPORT int qemu_plugin_install(qemu_plugin_id_t id,
 {
     int i;
 
+    for (i = 0; i < ARRAY_SIZE(class_tables); i++) {
+        for (int j = 0; j < class_tables[i].table_sz; ++j) {
+            struct qemu_plugin_scoreboard *score =
+                qemu_plugin_scoreboard_new(sizeof(uint64_t));
+            class_tables[i].table[j].count = qemu_plugin_scoreboard_u64(score);
+        }
+    }
+
     /* Select a class table appropriate to the guest architecture */
     for (i = 0; i < ARRAY_SIZE(class_tables); i++) {
         ClassSelector *entry = &class_tables[i];
diff --git a/disas/disas.c b/disas/disas.c
index 0d2d06c..17170d2 100644
--- a/disas/disas.c
+++ b/disas/disas.c
@@ -299,6 +299,7 @@ void disas(FILE *out, const void *code, size_t size)
     s.info.buffer = code;
     s.info.buffer_vma = (uintptr_t)code;
     s.info.buffer_length = size;
+    s.info.show_opcodes = true;
 
     if (s.info.cap_arch >= 0 && cap_disas_host(&s.info, code, size)) {
         return;
diff --git a/disas/hppa.c b/disas/hppa.c
index 22dce9b..49e2231 100644
--- a/disas/hppa.c
+++ b/disas/hppa.c
@@ -1972,9 +1972,11 @@ print_insn_hppa (bfd_vma memaddr, disassemble_info *info)
 
   insn = bfd_getb32 (buffer);
 
-  info->fprintf_func(info->stream, " %02x %02x %02x %02x   ",
-                (insn >> 24) & 0xff, (insn >> 16) & 0xff,
-                (insn >>  8) & 0xff, insn & 0xff);
+  if (info->show_opcodes) {
+      info->fprintf_func(info->stream, " %02x %02x %02x %02x   ",
+                         (insn >> 24) & 0xff, (insn >> 16) & 0xff,
+                         (insn >>  8) & 0xff, insn & 0xff);
+  }
 
   for (i = 0; i < NUMOPCODES; ++i)
     {
diff --git a/disas/riscv.c b/disas/riscv.c
index 8a546d5..e236c8b 100644
--- a/disas/riscv.c
+++ b/disas/riscv.c
@@ -5192,19 +5192,21 @@ print_insn_riscv(bfd_vma memaddr, struct disassemble_info *info, rv_isa isa)
         }
     }
 
-    switch (len) {
-    case 2:
-        (*info->fprintf_func)(info->stream, INST_FMT_2, inst);
-        break;
-    case 4:
-        (*info->fprintf_func)(info->stream, INST_FMT_4, inst);
-        break;
-    case 6:
-        (*info->fprintf_func)(info->stream, INST_FMT_6, inst);
-        break;
-    default:
-        (*info->fprintf_func)(info->stream, INST_FMT_8, inst);
-        break;
+    if (info->show_opcodes) {
+        switch (len) {
+        case 2:
+            (*info->fprintf_func)(info->stream, INST_FMT_2, inst);
+            break;
+        case 4:
+            (*info->fprintf_func)(info->stream, INST_FMT_4, inst);
+            break;
+        case 6:
+            (*info->fprintf_func)(info->stream, INST_FMT_6, inst);
+            break;
+        default:
+            (*info->fprintf_func)(info->stream, INST_FMT_8, inst);
+            break;
+        }
     }
 
     disasm_inst(buf, sizeof(buf), isa, memaddr, inst,
diff --git a/gdbstub/gdbstub.c b/gdbstub/gdbstub.c
index 2909bc8..17efcae 100644
--- a/gdbstub/gdbstub.c
+++ b/gdbstub/gdbstub.c
@@ -1024,6 +1024,12 @@ static void handle_detach(GArray *params, void *user_ctx)
         pid = get_param(params, 0)->val_ul;
     }
 
+#ifdef CONFIG_USER_ONLY
+    if (gdb_handle_detach_user(pid)) {
+        return;
+    }
+#endif
+
     process = gdb_get_process(pid);
     gdb_process_breakpoint_remove_all(process);
     process->attached = false;
@@ -1099,6 +1105,7 @@ static void handle_cont_with_sig(GArray *params, void *user_ctx)
 
 static void handle_set_thread(GArray *params, void *user_ctx)
 {
+    uint32_t pid, tid;
     CPUState *cpu;
 
     if (params->len != 2) {
@@ -1116,8 +1123,14 @@ static void handle_set_thread(GArray *params, void *user_ctx)
         return;
     }
 
-    cpu = gdb_get_cpu(get_param(params, 1)->thread_id.pid,
-                      get_param(params, 1)->thread_id.tid);
+    pid = get_param(params, 1)->thread_id.pid;
+    tid = get_param(params, 1)->thread_id.tid;
+#ifdef CONFIG_USER_ONLY
+    if (gdb_handle_set_thread_user(pid, tid)) {
+        return;
+    }
+#endif
+    cpu = gdb_get_cpu(pid, tid);
     if (!cpu) {
         gdb_put_packet("E22");
         return;
@@ -1655,9 +1668,15 @@ static void handle_query_supported(GArray *params, void *user_ctx)
     g_string_append(gdbserver_state.str_buf, ";qXfer:exec-file:read+");
 #endif
 
-    if (params->len &&
-        strstr(get_param(params, 0)->data, "multiprocess+")) {
-        gdbserver_state.multiprocess = true;
+    if (params->len) {
+        const char *gdb_supported = get_param(params, 0)->data;
+
+        if (strstr(gdb_supported, "multiprocess+")) {
+            gdbserver_state.multiprocess = true;
+        }
+#if defined(CONFIG_USER_ONLY)
+        gdb_handle_query_supported_user(gdb_supported);
+#endif
     }
 
     g_string_append(gdbserver_state.str_buf, ";vContSupported+;multiprocess+");
diff --git a/gdbstub/internals.h b/gdbstub/internals.h
index 56b7c13..b472459 100644
--- a/gdbstub/internals.h
+++ b/gdbstub/internals.h
@@ -196,6 +196,9 @@ void gdb_handle_v_file_pread(GArray *params, void *user_ctx); /* user */
 void gdb_handle_v_file_readlink(GArray *params, void *user_ctx); /* user */
 void gdb_handle_query_xfer_exec_file(GArray *params, void *user_ctx); /* user */
 void gdb_handle_set_catch_syscalls(GArray *params, void *user_ctx); /* user */
+void gdb_handle_query_supported_user(const char *gdb_supported); /* user */
+bool gdb_handle_set_thread_user(uint32_t pid, uint32_t tid); /* user */
+bool gdb_handle_detach_user(uint32_t pid); /* user */
 
 void gdb_handle_query_attached(GArray *params, void *user_ctx); /* both */
 
diff --git a/gdbstub/user-target.c b/gdbstub/user-target.c
index b7d4c37..6646684 100644
--- a/gdbstub/user-target.c
+++ b/gdbstub/user-target.c
@@ -204,7 +204,7 @@ int gdb_target_signal_to_gdb(int sig)
 
 int gdb_get_cpu_index(CPUState *cpu)
 {
-    TaskState *ts = (TaskState *) cpu->opaque;
+    TaskState *ts = get_task_state(cpu);
     return ts ? ts->ts_tid : -1;
 }
 
@@ -399,7 +399,7 @@ void gdb_handle_query_xfer_exec_file(GArray *params, void *user_ctx)
         return;
     }
 
-    TaskState *ts = cpu->opaque;
+    TaskState *ts = get_task_state(cpu);
     if (!ts || !ts->bprm || !ts->bprm->filename) {
         gdb_put_packet("E00");
         return;
diff --git a/gdbstub/user.c b/gdbstub/user.c
index 14918d1..7f9f19a 100644
--- a/gdbstub/user.c
+++ b/gdbstub/user.c
@@ -25,6 +25,61 @@
 #define GDB_NR_SYSCALLS 1024
 typedef unsigned long GDBSyscallsMask[BITS_TO_LONGS(GDB_NR_SYSCALLS)];
 
+/*
+ * Forked child talks to its parent in order to let GDB enforce the
+ * follow-fork-mode. This happens inside a start_exclusive() section, so that
+ * the other threads, which may be forking too, do not interfere. The
+ * implementation relies on GDB not sending $vCont until it has detached
+ * either from the parent (follow-fork-mode child) or from the child
+ * (follow-fork-mode parent).
+ *
+ * The parent and the child share the GDB socket; at any given time only one
+ * of them is allowed to use it, as is reflected in the respective fork_state.
+ * This is negotiated via the fork_sockets pair as a reaction to $Hg.
+ *
+ * Below is a short summary of the possible state transitions:
+ *
+ *     ENABLED                     : Terminal state.
+ *     DISABLED                    : Terminal state.
+ *     ACTIVE                      : Parent initial state.
+ *     INACTIVE                    : Child initial state.
+ *     ACTIVE       -> DEACTIVATING: On $Hg.
+ *     ACTIVE       -> ENABLING    : On $D.
+ *     ACTIVE       -> DISABLING   : On $D.
+ *     ACTIVE       -> DISABLED    : On communication error.
+ *     DEACTIVATING -> INACTIVE    : On gdb_read_byte() return.
+ *     DEACTIVATING -> DISABLED    : On communication error.
+ *     INACTIVE     -> ACTIVE      : On $Hg in the peer.
+ *     INACTIVE     -> ENABLE      : On $D in the peer.
+ *     INACTIVE     -> DISABLE     : On $D in the peer.
+ *     INACTIVE     -> DISABLED    : On communication error.
+ *     ENABLING     -> ENABLED     : On gdb_read_byte() return.
+ *     ENABLING     -> DISABLED    : On communication error.
+ *     DISABLING    -> DISABLED    : On gdb_read_byte() return.
+ */
+enum GDBForkState {
+    /* Fully owning the GDB socket. */
+    GDB_FORK_ENABLED,
+    /* Working with the GDB socket; the peer is inactive. */
+    GDB_FORK_ACTIVE,
+    /* Handing off the GDB socket to the peer. */
+    GDB_FORK_DEACTIVATING,
+    /* The peer is working with the GDB socket. */
+    GDB_FORK_INACTIVE,
+    /* Asking the peer to close its GDB socket fd. */
+    GDB_FORK_ENABLING,
+    /* Asking the peer to take over, closing our GDB socket fd. */
+    GDB_FORK_DISABLING,
+    /* The peer has taken over, our GDB socket fd is closed. */
+    GDB_FORK_DISABLED,
+};
+
+enum GDBForkMessage {
+    GDB_FORK_ACTIVATE = 'a',
+    GDB_FORK_ENABLE = 'e',
+    GDB_FORK_DISABLE = 'd',
+};
+
 /* User-mode specific state */
 typedef struct {
     int fd;
@@ -36,6 +91,10 @@ typedef struct {
      */
     bool catch_all_syscalls;
     GDBSyscallsMask catch_syscalls_mask;
+    bool fork_events;
+    enum GDBForkState fork_state;
+    int fork_sockets[2];
+    pid_t fork_peer_pid, fork_peer_tid;
 } GDBUserState;
 
 static GDBUserState gdbserver_user_state;
@@ -356,16 +415,193 @@ int gdbserver_start(const char *port_or_path)
     return -1;
 }
 
-/* Disable gdb stub for child processes.  */
-void gdbserver_fork(CPUState *cpu)
+void gdbserver_fork_start(void)
 {
     if (!gdbserver_state.init || gdbserver_user_state.fd < 0) {
         return;
     }
+    if (!gdbserver_user_state.fork_events ||
+            qemu_socketpair(AF_UNIX, SOCK_STREAM, 0,
+                            gdbserver_user_state.fork_sockets) < 0) {
+        gdbserver_user_state.fork_state = GDB_FORK_DISABLED;
+        return;
+    }
+    gdbserver_user_state.fork_state = GDB_FORK_INACTIVE;
+    gdbserver_user_state.fork_peer_pid = getpid();
+    gdbserver_user_state.fork_peer_tid = qemu_get_thread_id();
+}
+
+static void disable_gdbstub(CPUState *thread_cpu)
+{
+    CPUState *cpu;
+
     close(gdbserver_user_state.fd);
     gdbserver_user_state.fd = -1;
-    cpu_breakpoint_remove_all(cpu, BP_GDB);
-    /* no cpu_watchpoint_remove_all for user-mode */
+    CPU_FOREACH(cpu) {
+        cpu_breakpoint_remove_all(cpu, BP_GDB);
+        /* no cpu_watchpoint_remove_all for user-mode */
+        cpu_single_step(cpu, 0);
+    }
+    tb_flush(thread_cpu);
+}
+
+void gdbserver_fork_end(CPUState *cpu, pid_t pid)
+{
+    char b;
+    int fd;
+
+    if (!gdbserver_state.init || gdbserver_user_state.fd < 0) {
+        return;
+    }
+
+    if (pid == -1) {
+        if (gdbserver_user_state.fork_state != GDB_FORK_DISABLED) {
+            g_assert(gdbserver_user_state.fork_state == GDB_FORK_INACTIVE);
+            close(gdbserver_user_state.fork_sockets[0]);
+            close(gdbserver_user_state.fork_sockets[1]);
+        }
+        return;
+    }
+
+    if (gdbserver_user_state.fork_state == GDB_FORK_DISABLED) {
+        if (pid == 0) {
+            disable_gdbstub(cpu);
+        }
+        return;
+    }
+
+    if (pid == 0) {
+        close(gdbserver_user_state.fork_sockets[0]);
+        fd = gdbserver_user_state.fork_sockets[1];
+        g_assert(gdbserver_state.process_num == 1);
+        g_assert(gdbserver_state.processes[0].pid ==
+                     gdbserver_user_state.fork_peer_pid);
+        g_assert(gdbserver_state.processes[0].attached);
+        gdbserver_state.processes[0].pid = getpid();
+    } else {
+        close(gdbserver_user_state.fork_sockets[1]);
+        fd = gdbserver_user_state.fork_sockets[0];
+        gdbserver_user_state.fork_state = GDB_FORK_ACTIVE;
+        gdbserver_user_state.fork_peer_pid = pid;
+        gdbserver_user_state.fork_peer_tid = pid;
+
+        if (!gdbserver_state.allow_stop_reply) {
+            goto fail;
+        }
+        g_string_printf(gdbserver_state.str_buf,
+                        "T%02xfork:p%02x.%02x;thread:p%02x.%02x;",
+                        gdb_target_signal_to_gdb(gdb_target_sigtrap()),
+                        pid, pid, (int)getpid(), qemu_get_thread_id());
+        gdb_put_strbuf();
+    }
+
+    gdbserver_state.state = RS_IDLE;
+    gdbserver_state.allow_stop_reply = false;
+    gdbserver_user_state.running_state = 0;
+    for (;;) {
+        switch (gdbserver_user_state.fork_state) {
+        case GDB_FORK_ENABLED:
+            if (gdbserver_user_state.running_state) {
+                return;
+            }
+            QEMU_FALLTHROUGH;
+        case GDB_FORK_ACTIVE:
+            if (read(gdbserver_user_state.fd, &b, 1) != 1) {
+                goto fail;
+            }
+            gdb_read_byte(b);
+            break;
+        case GDB_FORK_DEACTIVATING:
+            b = GDB_FORK_ACTIVATE;
+            if (write(fd, &b, 1) != 1) {
+                goto fail;
+            }
+            gdbserver_user_state.fork_state = GDB_FORK_INACTIVE;
+            break;
+        case GDB_FORK_INACTIVE:
+            if (read(fd, &b, 1) != 1) {
+                goto fail;
+            }
+            switch (b) {
+            case GDB_FORK_ACTIVATE:
+                gdbserver_user_state.fork_state = GDB_FORK_ACTIVE;
+                break;
+            case GDB_FORK_ENABLE:
+                close(fd);
+                gdbserver_user_state.fork_state = GDB_FORK_ENABLED;
+                break;
+            case GDB_FORK_DISABLE:
+                gdbserver_user_state.fork_state = GDB_FORK_DISABLED;
+                break;
+            default:
+                g_assert_not_reached();
+            }
+            break;
+        case GDB_FORK_ENABLING:
+            b = GDB_FORK_DISABLE;
+            if (write(fd, &b, 1) != 1) {
+                goto fail;
+            }
+            close(fd);
+            gdbserver_user_state.fork_state = GDB_FORK_ENABLED;
+            break;
+        case GDB_FORK_DISABLING:
+            b = GDB_FORK_ENABLE;
+            if (write(fd, &b, 1) != 1) {
+                goto fail;
+            }
+            gdbserver_user_state.fork_state = GDB_FORK_DISABLED;
+            break;
+        case GDB_FORK_DISABLED:
+            close(fd);
+            disable_gdbstub(cpu);
+            return;
+        default:
+            g_assert_not_reached();
+        }
+    }
+
+fail:
+    close(fd);
+    if (pid == 0) {
+        disable_gdbstub(cpu);
+    }
+}
+
+void gdb_handle_query_supported_user(const char *gdb_supported)
+{
+    if (strstr(gdb_supported, "fork-events+")) {
+        gdbserver_user_state.fork_events = true;
+    }
+    g_string_append(gdbserver_state.str_buf, ";fork-events+");
+}
+
+bool gdb_handle_set_thread_user(uint32_t pid, uint32_t tid)
+{
+    if (gdbserver_user_state.fork_state == GDB_FORK_ACTIVE &&
+            pid == gdbserver_user_state.fork_peer_pid &&
+            tid == gdbserver_user_state.fork_peer_tid) {
+        gdbserver_user_state.fork_state = GDB_FORK_DEACTIVATING;
+        gdb_put_packet("OK");
+        return true;
+    }
+    return false;
+}
+
+bool gdb_handle_detach_user(uint32_t pid)
+{
+    bool enable;
+
+    if (gdbserver_user_state.fork_state == GDB_FORK_ACTIVE) {
+        enable = pid == gdbserver_user_state.fork_peer_pid;
+        if (enable || pid == getpid()) {
+            gdbserver_user_state.fork_state = enable ? GDB_FORK_ENABLING :
+                                                       GDB_FORK_DISABLING;
+            gdb_put_packet("OK");
+            return true;
+        }
+    }
+    return false;
 }
 
 /*
diff --git a/include/disas/dis-asm.h b/include/disas/dis-asm.h
index 2324f6b..b26867b 100644
--- a/include/disas/dis-asm.h
+++ b/include/disas/dis-asm.h
@@ -396,6 +396,14 @@ typedef struct disassemble_info {
   /* Command line options specific to the target disassembler.  */
   char * disassembler_options;
 
+  /*
+   * When true instruct the disassembler it may preface the
+   * disassembly with the opcodes values if it wants to. This is
+   * mainly for the benefit of the plugin interface which doesn't want
+   * that.
+   */
+  bool show_opcodes;
+
   /* Field intended to be used by targets in any way they deem suitable.  */
   void *target_info;
 
diff --git a/include/gdbstub/user.h b/include/gdbstub/user.h
index 68b6534..4c4e5c4 100644
--- a/include/gdbstub/user.h
+++ b/include/gdbstub/user.h
@@ -46,10 +46,16 @@ static inline int gdb_handlesig(CPUState *cpu, int sig)
 void gdb_signalled(CPUArchState *as, int sig);
 
 /**
- * gdbserver_fork() - disable gdb stub for child processes.
+ * gdbserver_fork_start() - inform gdb of the upcoming fork()
+ */
+void gdbserver_fork_start(void);
+
+/**
+ * gdbserver_fork_end() - inform gdb of the completed fork()
  * @cs: CPU
+ * @pid: 0 if in child process, -1 if fork failed, child process pid otherwise
  */
-void gdbserver_fork(CPUState *cs);
+void gdbserver_fork_end(CPUState *cs, pid_t pid);
 
 /**
  * gdb_syscall_entry() - inform gdb of syscall entry and yield control to it
diff --git a/include/qemu/plugin.h b/include/qemu/plugin.h
index b3c94a3..12a96ce 100644
--- a/include/qemu/plugin.h
+++ b/include/qemu/plugin.h
@@ -92,6 +92,7 @@ struct qemu_plugin_dyn_cb {
     /* fields specific to each dyn_cb type go here */
     union {
         struct {
+            qemu_plugin_u64 entry;
             enum qemu_plugin_op op;
             uint64_t imm;
         } inline_insn;
@@ -112,6 +113,12 @@ struct qemu_plugin_insn {
     bool mem_only;
 };
 
+/* A scoreboard is an array of values, indexed by vcpu_index */
+struct qemu_plugin_scoreboard {
+    GArray *data;
+    QLIST_ENTRY(qemu_plugin_scoreboard) entry;
+};
+
 /*
  * qemu_plugin_insn allocate and cleanup functions. We don't expect to
  * cleanup many of these structures. They are reused for each fresh
diff --git a/include/qemu/qemu-plugin.h b/include/qemu/qemu-plugin.h
index 45e2ebc..4fc6c37 100644
--- a/include/qemu/qemu-plugin.h
+++ b/include/qemu/qemu-plugin.h
@@ -52,7 +52,11 @@ typedef uint64_t qemu_plugin_id_t;
  * The plugins export the API they were built against by exposing the
  * symbol qemu_plugin_version which can be checked.
  *
- * version 2: removed qemu_plugin_n_vcpus and qemu_plugin_n_max_vcpus
+ * version 2:
+ * - removed qemu_plugin_n_vcpus and qemu_plugin_n_max_vcpus
+ * - Remove qemu_plugin_register_vcpu_{tb, insn, mem}_exec_inline.
+ *   Those functions are replaced by *_per_vcpu variants, which guarantee
+ *   thread-safety for operations.
  */
 
 extern QEMU_PLUGIN_EXPORT int qemu_plugin_version;
@@ -222,6 +226,19 @@ void qemu_plugin_register_vcpu_resume_cb(qemu_plugin_id_t id,
 struct qemu_plugin_tb;
 /** struct qemu_plugin_insn - Opaque handle for a translated instruction */
 struct qemu_plugin_insn;
+/** struct qemu_plugin_scoreboard - Opaque handle for a scoreboard */
+struct qemu_plugin_scoreboard;
+
+/**
+ * typedef qemu_plugin_u64 - uint64_t member of an entry in a scoreboard
+ *
+ * This field allows to access a specific uint64_t member in one given entry,
+ * located at a specified offset. Inline operations expect this as entry.
+ */
+typedef struct {
+    struct qemu_plugin_scoreboard *score;
+    size_t offset;
+} qemu_plugin_u64;
 
 /**
  * enum qemu_plugin_cb_flags - type of callback
@@ -297,23 +314,20 @@ enum qemu_plugin_op {
 };
 
 /**
- * qemu_plugin_register_vcpu_tb_exec_inline() - execution inline op
+ * qemu_plugin_register_vcpu_tb_exec_inline_per_vcpu() - execution inline op
  * @tb: the opaque qemu_plugin_tb handle for the translation
  * @op: the type of qemu_plugin_op (e.g. ADD_U64)
- * @ptr: the target memory location for the op
+ * @entry: entry to run op
  * @imm: the op data (e.g. 1)
  *
- * Insert an inline op to every time a translated unit executes.
- * Useful if you just want to increment a single counter somewhere in
- * memory.
- *
- * Note: ops are not atomic so in multi-threaded/multi-smp situations
- * you will get inexact results.
+ * Insert an inline op on a given scoreboard entry.
  */
 QEMU_PLUGIN_API
-void qemu_plugin_register_vcpu_tb_exec_inline(struct qemu_plugin_tb *tb,
-                                              enum qemu_plugin_op op,
-                                              void *ptr, uint64_t imm);
+void qemu_plugin_register_vcpu_tb_exec_inline_per_vcpu(
+    struct qemu_plugin_tb *tb,
+    enum qemu_plugin_op op,
+    qemu_plugin_u64 entry,
+    uint64_t imm);
 
 /**
  * qemu_plugin_register_vcpu_insn_exec_cb() - register insn execution cb
@@ -331,19 +345,20 @@ void qemu_plugin_register_vcpu_insn_exec_cb(struct qemu_plugin_insn *insn,
                                             void *userdata);
 
 /**
- * qemu_plugin_register_vcpu_insn_exec_inline() - insn execution inline op
+ * qemu_plugin_register_vcpu_insn_exec_inline_per_vcpu() - insn exec inline op
  * @insn: the opaque qemu_plugin_insn handle for an instruction
  * @op: the type of qemu_plugin_op (e.g. ADD_U64)
- * @ptr: the target memory location for the op
+ * @entry: entry to run op
  * @imm: the op data (e.g. 1)
  *
- * Insert an inline op to every time an instruction executes. Useful
- * if you just want to increment a single counter somewhere in memory.
+ * Insert an inline op to every time an instruction executes.
  */
 QEMU_PLUGIN_API
-void qemu_plugin_register_vcpu_insn_exec_inline(struct qemu_plugin_insn *insn,
-                                                enum qemu_plugin_op op,
-                                                void *ptr, uint64_t imm);
+void qemu_plugin_register_vcpu_insn_exec_inline_per_vcpu(
+    struct qemu_plugin_insn *insn,
+    enum qemu_plugin_op op,
+    qemu_plugin_u64 entry,
+    uint64_t imm);
 
 /**
  * qemu_plugin_tb_n_insns() - query helper for number of insns in TB
@@ -553,24 +568,23 @@ void qemu_plugin_register_vcpu_mem_cb(struct qemu_plugin_insn *insn,
                                       void *userdata);
 
 /**
- * qemu_plugin_register_vcpu_mem_inline() - register an inline op to any memory access
+ * qemu_plugin_register_vcpu_mem_inline_per_vcpu() - inline op for mem access
  * @insn: handle for instruction to instrument
  * @rw: apply to reads, writes or both
  * @op: the op, of type qemu_plugin_op
- * @ptr: pointer memory for the op
+ * @entry: entry to run op
  * @imm: immediate data for @op
  *
  * This registers a inline op every memory access generated by the
- * instruction. This provides for a lightweight but not thread-safe
- * way of counting the number of operations done.
+ * instruction.
  */
 QEMU_PLUGIN_API
-void qemu_plugin_register_vcpu_mem_inline(struct qemu_plugin_insn *insn,
-                                          enum qemu_plugin_mem_rw rw,
-                                          enum qemu_plugin_op op, void *ptr,
-                                          uint64_t imm);
-
-
+void qemu_plugin_register_vcpu_mem_inline_per_vcpu(
+    struct qemu_plugin_insn *insn,
+    enum qemu_plugin_mem_rw rw,
+    enum qemu_plugin_op op,
+    qemu_plugin_u64 entry,
+    uint64_t imm);
 
 typedef void
 (*qemu_plugin_vcpu_syscall_cb_t)(qemu_plugin_id_t id, unsigned int vcpu_index,
@@ -752,5 +766,75 @@ QEMU_PLUGIN_API
 int qemu_plugin_read_register(struct qemu_plugin_register *handle,
                               GByteArray *buf);
 
+/**
+ * qemu_plugin_scoreboard_new() - alloc a new scoreboard
+ *
+ * @element_size: size (in bytes) for one entry
+ *
+ * Returns a pointer to a new scoreboard. It must be freed using
+ * qemu_plugin_scoreboard_free.
+ */
+QEMU_PLUGIN_API
+struct qemu_plugin_scoreboard *qemu_plugin_scoreboard_new(size_t element_size);
+
+/**
+ * qemu_plugin_scoreboard_free() - free a scoreboard
+ * @score: scoreboard to free
+ */
+QEMU_PLUGIN_API
+void qemu_plugin_scoreboard_free(struct qemu_plugin_scoreboard *score);
+
+/**
+ * qemu_plugin_scoreboard_find() - get pointer to an entry of a scoreboard
+ * @score: scoreboard to query
+ * @vcpu_index: entry index
+ *
+ * Returns address of entry of a scoreboard matching a given vcpu_index. This
+ * address can be modified later if scoreboard is resized.
+ */
+QEMU_PLUGIN_API
+void *qemu_plugin_scoreboard_find(struct qemu_plugin_scoreboard *score,
+                                  unsigned int vcpu_index);
+
+/* Macros to define a qemu_plugin_u64 */
+#define qemu_plugin_scoreboard_u64(score) \
+    (qemu_plugin_u64) {score, 0}
+#define qemu_plugin_scoreboard_u64_in_struct(score, type, member) \
+    (qemu_plugin_u64) {score, offsetof(type, member)}
+
+/**
+ * qemu_plugin_u64_add() - add a value to a qemu_plugin_u64 for a given vcpu
+ * @entry: entry to query
+ * @vcpu_index: entry index
+ * @added: value to add
+ */
+QEMU_PLUGIN_API
+void qemu_plugin_u64_add(qemu_plugin_u64 entry, unsigned int vcpu_index,
+                         uint64_t added);
+
+/**
+ * qemu_plugin_u64_get() - get value of a qemu_plugin_u64 for a given vcpu
+ * @entry: entry to query
+ * @vcpu_index: entry index
+ */
+QEMU_PLUGIN_API
+uint64_t qemu_plugin_u64_get(qemu_plugin_u64 entry, unsigned int vcpu_index);
+
+/**
+ * qemu_plugin_u64_set() - set value of a qemu_plugin_u64 for a given vcpu
+ * @entry: entry to query
+ * @vcpu_index: entry index
+ * @val: new value
+ */
+QEMU_PLUGIN_API
+void qemu_plugin_u64_set(qemu_plugin_u64 entry, unsigned int vcpu_index,
+                         uint64_t val);
+
+/**
+ * qemu_plugin_u64_sum() - return sum of all vcpu entries in a scoreboard
+ * @entry: entry to sum
+ */
+QEMU_PLUGIN_API
+uint64_t qemu_plugin_u64_sum(qemu_plugin_u64 entry);
 
 #endif /* QEMU_QEMU_PLUGIN_H */
diff --git a/include/user/safe-syscall.h b/include/user/safe-syscall.h
index 27b71cd..aa075f4 100644
--- a/include/user/safe-syscall.h
+++ b/include/user/safe-syscall.h
@@ -134,7 +134,7 @@ extern char safe_syscall_start[];
 extern char safe_syscall_end[];
 
 #define safe_syscall(...)                                                 \
-    safe_syscall_base(&((TaskState *)thread_cpu->opaque)->signal_pending, \
+    safe_syscall_base(&get_task_state(thread_cpu)->signal_pending,        \
                       __VA_ARGS__)
 
 #endif
diff --git a/linux-user/aarch64/cpu_loop.c b/linux-user/aarch64/cpu_loop.c
index 8c20dc8..71cdc8b 100644
--- a/linux-user/aarch64/cpu_loop.c
+++ b/linux-user/aarch64/cpu_loop.c
@@ -189,7 +189,7 @@ void target_cpu_copy_regs(CPUArchState *env, struct target_pt_regs *regs)
 {
     ARMCPU *cpu = env_archcpu(env);
     CPUState *cs = env_cpu(env);
-    TaskState *ts = cs->opaque;
+    TaskState *ts = get_task_state(cs);
     struct image_info *info = ts->info;
     int i;
 
diff --git a/linux-user/arm/cpu_loop.c b/linux-user/arm/cpu_loop.c
index b404117..db1a41e 100644
--- a/linux-user/arm/cpu_loop.c
+++ b/linux-user/arm/cpu_loop.c
@@ -263,7 +263,7 @@ static bool insn_is_linux_bkpt(uint32_t opcode, bool is_thumb)
 
 static bool emulate_arm_fpa11(CPUARMState *env, uint32_t opcode)
 {
-    TaskState *ts = env_cpu(env)->opaque;
+    TaskState *ts = get_task_state(env_cpu(env));
     int rc = EmulateAll(opcode, &ts->fpa, env);
     int raise, enabled;
 
@@ -514,7 +514,7 @@ void cpu_loop(CPUARMState *env)
 void target_cpu_copy_regs(CPUArchState *env, struct target_pt_regs *regs)
 {
     CPUState *cpu = env_cpu(env);
-    TaskState *ts = cpu->opaque;
+    TaskState *ts = get_task_state(cpu);
     struct image_info *info = ts->info;
     int i;
 
diff --git a/linux-user/arm/signal.c b/linux-user/arm/signal.c
index f77f692..5980633 100644
--- a/linux-user/arm/signal.c
+++ b/linux-user/arm/signal.c
@@ -177,7 +177,7 @@ setup_return(CPUARMState *env, struct target_sigaction *ka, int usig,
     abi_ulong handler = 0;
     abi_ulong handler_fdpic_GOT = 0;
     abi_ulong retcode;
-    bool is_fdpic = info_is_fdpic(((TaskState *)thread_cpu->opaque)->info);
+    bool is_fdpic = info_is_fdpic(get_task_state(thread_cpu)->info);
     bool is_rt = ka->sa_flags & TARGET_SA_SIGINFO;
     bool thumb;
 
diff --git a/linux-user/cris/cpu_loop.c b/linux-user/cris/cpu_loop.c
index 01e6ff1..04c9086 100644
--- a/linux-user/cris/cpu_loop.c
+++ b/linux-user/cris/cpu_loop.c
@@ -72,7 +72,7 @@ void cpu_loop(CPUCRISState *env)
 void target_cpu_copy_regs(CPUArchState *env, struct target_pt_regs *regs)
 {
     CPUState *cpu = env_cpu(env);
-    TaskState *ts = cpu->opaque;
+    TaskState *ts = get_task_state(cpu);
     struct image_info *info = ts->info;
 
     env->regs[0] = regs->r0;
diff --git a/linux-user/elfload.c b/linux-user/elfload.c
index 0c299a7..4dbca05 100644
--- a/linux-user/elfload.c
+++ b/linux-user/elfload.c
@@ -4404,7 +4404,7 @@ static int wmr_write_region(void *opaque, target_ulong start,
 static int elf_core_dump(int signr, const CPUArchState *env)
 {
     const CPUState *cpu = env_cpu((CPUArchState *)env);
-    const TaskState *ts = (const TaskState *)cpu->opaque;
+    const TaskState *ts = (const TaskState *)get_task_state((CPUState *)cpu);
     struct rlimit dumpsize;
     CountAndSizeRegions css;
     off_t offset, note_offset, data_offset;
diff --git a/linux-user/hppa/signal.c b/linux-user/hppa/signal.c
index d08a97d..c84557e 100644
--- a/linux-user/hppa/signal.c
+++ b/linux-user/hppa/signal.c
@@ -112,7 +112,7 @@ void setup_rt_frame(int sig, struct target_sigaction *ka,
     abi_ulong frame_addr, sp, haddr;
     struct target_rt_sigframe *frame;
     int i;
-    TaskState *ts = (TaskState *)thread_cpu->opaque;
+    TaskState *ts = get_task_state(thread_cpu);
 
     sp = get_sp_from_cpustate(env);
     if ((ka->sa_flags & TARGET_SA_ONSTACK) && !sas_ss_flags(sp)) {
diff --git a/linux-user/linuxload.c b/linux-user/linuxload.c
index 4a794f8..37f132b 100644
--- a/linux-user/linuxload.c
+++ b/linux-user/linuxload.c
@@ -89,7 +89,7 @@ static int prepare_binprm(struct linux_binprm *bprm)
 abi_ulong loader_build_argptr(int envc, int argc, abi_ulong sp,
                               abi_ulong stringp, int push_ptr)
 {
-    TaskState *ts = (TaskState *)thread_cpu->opaque;
+    TaskState *ts = get_task_state(thread_cpu);
     int n = sizeof(abi_ulong);
     abi_ulong envp;
     abi_ulong argv;
diff --git a/linux-user/m68k/cpu_loop.c b/linux-user/m68k/cpu_loop.c
index caead1c..f79b8e4 100644
--- a/linux-user/m68k/cpu_loop.c
+++ b/linux-user/m68k/cpu_loop.c
@@ -95,7 +95,7 @@ void cpu_loop(CPUM68KState *env)
 void target_cpu_copy_regs(CPUArchState *env, struct target_pt_regs *regs)
 {
     CPUState *cpu = env_cpu(env);
-    TaskState *ts = cpu->opaque;
+    TaskState *ts = get_task_state(cpu);
     struct image_info *info = ts->info;
 
     env->pc = regs->pc;
diff --git a/linux-user/m68k/target_cpu.h b/linux-user/m68k/target_cpu.h
index c3f288d..4b40c09 100644
--- a/linux-user/m68k/target_cpu.h
+++ b/linux-user/m68k/target_cpu.h
@@ -37,7 +37,7 @@ static inline void cpu_clone_regs_parent(CPUM68KState *env, unsigned flags)
 static inline void cpu_set_tls(CPUM68KState *env, target_ulong newtls)
 {
     CPUState *cs = env_cpu(env);
-    TaskState *ts = cs->opaque;
+    TaskState *ts = get_task_state(cs);
 
     ts->tp_value = newtls;
 }
diff --git a/linux-user/main.c b/linux-user/main.c
index 551acf1..41caa77 100644
--- a/linux-user/main.c
+++ b/linux-user/main.c
@@ -145,10 +145,13 @@ void fork_start(void)
     mmap_fork_start();
     cpu_list_lock();
     qemu_plugin_user_prefork_lock();
+    gdbserver_fork_start();
 }
 
-void fork_end(int child)
+void fork_end(pid_t pid)
 {
+    bool child = pid == 0;
+
     qemu_plugin_user_postfork(child);
     mmap_fork_end(child);
     if (child) {
@@ -161,10 +164,11 @@ void fork_end(int child)
             }
         }
         qemu_init_cpu_list();
-        gdbserver_fork(thread_cpu);
+        get_task_state(thread_cpu)->ts_tid = qemu_get_thread_id();
     } else {
         cpu_list_unlock();
     }
+    gdbserver_fork_end(thread_cpu, pid);
     /*
      * qemu_init_cpu_list() reinitialized the child exclusive state, but we
      * also need to keep current_cpu consistent, so call end_exclusive() for
diff --git a/linux-user/mips/cpu_loop.c b/linux-user/mips/cpu_loop.c
index 990b03e..462387a 100644
--- a/linux-user/mips/cpu_loop.c
+++ b/linux-user/mips/cpu_loop.c
@@ -214,7 +214,7 @@ done_syscall:
 void target_cpu_copy_regs(CPUArchState *env, struct target_pt_regs *regs)
 {
     CPUState *cpu = env_cpu(env);
-    TaskState *ts = cpu->opaque;
+    TaskState *ts = get_task_state(cpu);
     struct image_info *info = ts->info;
     int i;
 
diff --git a/linux-user/ppc/signal.c b/linux-user/ppc/signal.c
index 7e73028..c232424 100644
--- a/linux-user/ppc/signal.c
+++ b/linux-user/ppc/signal.c
@@ -486,7 +486,7 @@ void setup_rt_frame(int sig, struct target_sigaction *ka,
     int i, err = 0;
 #if defined(TARGET_PPC64)
     struct target_sigcontext *sc = 0;
-    struct image_info *image = ((TaskState *)thread_cpu->opaque)->info;
+    struct image_info *image = get_task_state(thread_cpu)->info;
 #endif
 
     rt_sf_addr = get_sigframe(ka, env, sizeof(*rt_sf));
@@ -673,7 +673,7 @@ abi_long do_swapcontext(CPUArchState *env, abi_ulong uold_ctx,
     }
 
     if (uold_ctx) {
-        TaskState *ts = (TaskState *)thread_cpu->opaque;
+        TaskState *ts = get_task_state(thread_cpu);
 
         if (!lock_user_struct(VERIFY_WRITE, uctx, uold_ctx, 1)) {
             return -TARGET_EFAULT;
diff --git a/linux-user/qemu.h b/linux-user/qemu.h
index 4de9ec7..32cd43d 100644
--- a/linux-user/qemu.h
+++ b/linux-user/qemu.h
@@ -162,6 +162,11 @@ typedef struct TaskState {
     uint64_t start_boottime;
 } TaskState;
 
+static inline TaskState *get_task_state(CPUState *cs)
+{
+    return cs->opaque;
+}
+
 abi_long do_brk(abi_ulong new_brk);
 int do_guest_openat(CPUArchState *cpu_env, int dirfd, const char *pathname,
                     int flags, mode_t mode, bool safe);
diff --git a/linux-user/riscv/cpu_loop.c b/linux-user/riscv/cpu_loop.c
index bffca7d..52c49c2 100644
--- a/linux-user/riscv/cpu_loop.c
+++ b/linux-user/riscv/cpu_loop.c
@@ -97,7 +97,7 @@ void cpu_loop(CPURISCVState *env)
 void target_cpu_copy_regs(CPUArchState *env, struct target_pt_regs *regs)
 {
     CPUState *cpu = env_cpu(env);
-    TaskState *ts = cpu->opaque;
+    TaskState *ts = get_task_state(cpu);
     struct image_info *info = ts->info;
 
     env->pc = regs->sepc;
diff --git a/linux-user/signal-common.h b/linux-user/signal-common.h
index 3e2dc60..a7df12f 100644
--- a/linux-user/signal-common.h
+++ b/linux-user/signal-common.h
@@ -113,7 +113,7 @@ int process_sigsuspend_mask(sigset_t **pset, target_ulong sigset,
 static inline void finish_sigsuspend_mask(int ret)
 {
     if (ret != -QEMU_ERESTARTSYS) {
-        TaskState *ts = (TaskState *)thread_cpu->opaque;
+        TaskState *ts = get_task_state(thread_cpu);
         ts->in_sigsuspend = 1;
     }
 }
diff --git a/linux-user/signal.c b/linux-user/signal.c
index d3e62ab..cc7dd78 100644
--- a/linux-user/signal.c
+++ b/linux-user/signal.c
@@ -172,7 +172,7 @@ void target_to_host_old_sigset(sigset_t *sigset,
 
 int block_signals(void)
 {
-    TaskState *ts = (TaskState *)thread_cpu->opaque;
+    TaskState *ts = get_task_state(thread_cpu);
     sigset_t set;
 
     /* It's OK to block everything including SIGSEGV, because we won't
@@ -194,7 +194,7 @@ int block_signals(void)
  */
 int do_sigprocmask(int how, const sigset_t *set, sigset_t *oldset)
 {
-    TaskState *ts = (TaskState *)thread_cpu->opaque;
+    TaskState *ts = get_task_state(thread_cpu);
 
     if (oldset) {
         *oldset = ts->signal_mask;
@@ -237,7 +237,7 @@ int do_sigprocmask(int how, const sigset_t *set, sigset_t *oldset)
  */
 void set_sigmask(const sigset_t *set)
 {
-    TaskState *ts = (TaskState *)thread_cpu->opaque;
+    TaskState *ts = get_task_state(thread_cpu);
 
     ts->signal_mask = *set;
 }
@@ -246,7 +246,7 @@ void set_sigmask(const sigset_t *set)
 
 int on_sig_stack(unsigned long sp)
 {
-    TaskState *ts = (TaskState *)thread_cpu->opaque;
+    TaskState *ts = get_task_state(thread_cpu);
 
     return (sp - ts->sigaltstack_used.ss_sp
             < ts->sigaltstack_used.ss_size);
@@ -254,7 +254,7 @@ int on_sig_stack(unsigned long sp)
 
 int sas_ss_flags(unsigned long sp)
 {
-    TaskState *ts = (TaskState *)thread_cpu->opaque;
+    TaskState *ts = get_task_state(thread_cpu);
 
     return (ts->sigaltstack_used.ss_size == 0 ? SS_DISABLE
             : on_sig_stack(sp) ? SS_ONSTACK : 0);
@@ -265,7 +265,7 @@ abi_ulong target_sigsp(abi_ulong sp, struct target_sigaction *ka)
     /*
      * This is the X/Open sanctioned signal stack switching.
      */
-    TaskState *ts = (TaskState *)thread_cpu->opaque;
+    TaskState *ts = get_task_state(thread_cpu);
 
     if ((ka->sa_flags & TARGET_SA_ONSTACK) && !sas_ss_flags(sp)) {
         return ts->sigaltstack_used.ss_sp + ts->sigaltstack_used.ss_size;
@@ -275,7 +275,7 @@ abi_ulong target_sigsp(abi_ulong sp, struct target_sigaction *ka)
 
 void target_save_altstack(target_stack_t *uss, CPUArchState *env)
 {
-    TaskState *ts = (TaskState *)thread_cpu->opaque;
+    TaskState *ts = get_task_state(thread_cpu);
 
     __put_user(ts->sigaltstack_used.ss_sp, &uss->ss_sp);
     __put_user(sas_ss_flags(get_sp_from_cpustate(env)), &uss->ss_flags);
@@ -284,7 +284,7 @@ void target_save_altstack(target_stack_t *uss, CPUArchState *env)
 
 abi_long target_restore_altstack(target_stack_t *uss, CPUArchState *env)
 {
-    TaskState *ts = (TaskState *)thread_cpu->opaque;
+    TaskState *ts = get_task_state(thread_cpu);
     size_t minstacksize = TARGET_MINSIGSTKSZ;
     target_stack_t ss;
 
@@ -571,7 +571,7 @@ static void signal_table_init(void)
 
 void signal_init(void)
 {
-    TaskState *ts = (TaskState *)thread_cpu->opaque;
+    TaskState *ts = get_task_state(thread_cpu);
     struct sigaction act, oact;
 
     /* initialize signal conversion tables */
@@ -730,7 +730,7 @@ static G_NORETURN
 void dump_core_and_abort(CPUArchState *env, int target_sig)
 {
     CPUState *cpu = env_cpu(env);
-    TaskState *ts = (TaskState *)cpu->opaque;
+    TaskState *ts = get_task_state(cpu);
     int host_sig, core_dumped = 0;
 
     /* On exit, undo the remapping of SIGABRT. */
@@ -769,7 +769,7 @@ void queue_signal(CPUArchState *env, int sig, int si_type,
                   target_siginfo_t *info)
 {
     CPUState *cpu = env_cpu(env);
-    TaskState *ts = cpu->opaque;
+    TaskState *ts = get_task_state(cpu);
 
     trace_user_queue_signal(env, sig);
 
@@ -954,7 +954,7 @@ static void host_signal_handler(int host_sig, siginfo_t *info, void *puc)
 {
     CPUState *cpu = thread_cpu;
     CPUArchState *env = cpu_env(cpu);
-    TaskState *ts = cpu->opaque;
+    TaskState *ts = get_task_state(cpu);
     target_siginfo_t tinfo;
     host_sigcontext *uc = puc;
     struct emulated_sigtable *k;
@@ -1174,7 +1174,7 @@ static void handle_pending_signal(CPUArchState *cpu_env, int sig,
     sigset_t set;
     target_sigset_t target_old_set;
     struct target_sigaction *sa;
-    TaskState *ts = cpu->opaque;
+    TaskState *ts = get_task_state(cpu);
 
     trace_user_handle_signal(cpu_env, sig);
     /* dequeue signal */
@@ -1256,7 +1256,7 @@ void process_pending_signals(CPUArchState *cpu_env)
 {
     CPUState *cpu = env_cpu(cpu_env);
     int sig;
-    TaskState *ts = cpu->opaque;
+    TaskState *ts = get_task_state(cpu);
     sigset_t set;
     sigset_t *blocked_set;
 
@@ -1316,7 +1316,7 @@ void process_pending_signals(CPUArchState *cpu_env)
 int process_sigsuspend_mask(sigset_t **pset, target_ulong sigset,
                             target_ulong sigsize)
 {
-    TaskState *ts = (TaskState *)thread_cpu->opaque;
+    TaskState *ts = get_task_state(thread_cpu);
     sigset_t *host_set = &ts->sigsuspend_mask;
     target_sigset_t *target_sigset;
 
diff --git a/linux-user/syscall.c b/linux-user/syscall.c
index bc8c065..7f30def 100644
--- a/linux-user/syscall.c
+++ b/linux-user/syscall.c
@@ -6515,7 +6515,7 @@ static void *clone_func(void *arg)
     env = info->env;
     cpu = env_cpu(env);
     thread_cpu = cpu;
-    ts = (TaskState *)cpu->opaque;
+    ts = get_task_state(cpu);
     info->tid = sys_gettid();
     task_settid(ts);
     if (info->child_tidptr)
@@ -6557,7 +6557,7 @@ static int do_fork(CPUArchState *env, unsigned int flags, abi_ulong newsp,
         flags &= ~(CLONE_VFORK | CLONE_VM);
 
     if (flags & CLONE_VM) {
-        TaskState *parent_ts = (TaskState *)cpu->opaque;
+        TaskState *parent_ts = get_task_state(cpu);
         new_thread_info info;
         pthread_attr_t attr;
 
@@ -6669,7 +6669,7 @@ static int do_fork(CPUArchState *env, unsigned int flags, abi_ulong newsp,
         if (ret == 0) {
             /* Child Process.  */
             cpu_clone_regs_child(env, newsp, flags);
-            fork_end(1);
+            fork_end(ret);
             /* There is a race condition here.  The parent process could
                theoretically read the TID in the child process before the child
                tid is set.  This would require using either ptrace
@@ -6680,7 +6680,7 @@ static int do_fork(CPUArchState *env, unsigned int flags, abi_ulong newsp,
                 put_user_u32(sys_gettid(), child_tidptr);
             if (flags & CLONE_PARENT_SETTID)
                 put_user_u32(sys_gettid(), parent_tidptr);
-            ts = (TaskState *)cpu->opaque;
+            ts = get_task_state(cpu);
             if (flags & CLONE_SETTLS)
                 cpu_set_tls (env, newtls);
             if (flags & CLONE_CHILD_CLEARTID)
@@ -6700,8 +6700,8 @@ static int do_fork(CPUArchState *env, unsigned int flags, abi_ulong newsp,
                 }
 #endif
                 put_user_u32(pid_fd, parent_tidptr);
-                }
-            fork_end(0);
+            }
+            fork_end(ret);
         }
         g_assert(!cpu_in_exclusive_context(cpu));
     }
@@ -7946,7 +7946,7 @@ int host_to_target_waitstatus(int status)
 static int open_self_cmdline(CPUArchState *cpu_env, int fd)
 {
     CPUState *cpu = env_cpu(cpu_env);
-    struct linux_binprm *bprm = ((TaskState *)cpu->opaque)->bprm;
+    struct linux_binprm *bprm = get_task_state(cpu)->bprm;
     int i;
 
     for (i = 0; i < bprm->argc; i++) {
@@ -8146,7 +8146,7 @@ static int open_self_smaps(CPUArchState *cpu_env, int fd)
 static int open_self_stat(CPUArchState *cpu_env, int fd)
 {
     CPUState *cpu = env_cpu(cpu_env);
-    TaskState *ts = cpu->opaque;
+    TaskState *ts = get_task_state(cpu);
     g_autoptr(GString) buf = g_string_new(NULL);
     int i;
 
@@ -8187,7 +8187,7 @@ static int open_self_stat(CPUArchState *cpu_env, int fd)
 static int open_self_auxv(CPUArchState *cpu_env, int fd)
 {
     CPUState *cpu = env_cpu(cpu_env);
-    TaskState *ts = cpu->opaque;
+    TaskState *ts = get_task_state(cpu);
     abi_ulong auxv = ts->info->saved_auxv;
     abi_ulong len = ts->info->auxv_len;
     char *ptr;
@@ -9012,7 +9012,7 @@ static abi_long do_syscall1(CPUArchState *cpu_env, int num, abi_long arg1,
         pthread_mutex_lock(&clone_lock);
 
         if (CPU_NEXT(first_cpu)) {
-            TaskState *ts = cpu->opaque;
+            TaskState *ts = get_task_state(cpu);
 
             if (ts->child_tidptr) {
                 put_user_u32(0, ts->child_tidptr);
@@ -9439,7 +9439,7 @@ static abi_long do_syscall1(CPUArchState *cpu_env, int num, abi_long arg1,
 #ifdef TARGET_NR_pause /* not on alpha */
     case TARGET_NR_pause:
         if (!block_signals()) {
-            sigsuspend(&((TaskState *)cpu->opaque)->signal_mask);
+            sigsuspend(&get_task_state(cpu)->signal_mask);
         }
         return -TARGET_EINTR;
 #endif
@@ -10005,7 +10005,7 @@ static abi_long do_syscall1(CPUArchState *cpu_env, int num, abi_long arg1,
             sigset_t *set;
 
 #if defined(TARGET_ALPHA)
-            TaskState *ts = cpu->opaque;
+            TaskState *ts = get_task_state(cpu);
             /* target_to_host_old_sigset will bswap back */
             abi_ulong mask = tswapal(arg1);
             set = &ts->sigsuspend_mask;
@@ -10406,7 +10406,7 @@ static abi_long do_syscall1(CPUArchState *cpu_env, int num, abi_long arg1,
     case TARGET_NR_mprotect:
         arg1 = cpu_untagged_addr(cpu, arg1);
         {
-            TaskState *ts = cpu->opaque;
+            TaskState *ts = get_task_state(cpu);
             /* Special hack to detect libc making the stack executable.  */
             if ((arg3 & PROT_GROWSDOWN)
                 && arg1 >= ts->info->stack_limit
@@ -12537,7 +12537,7 @@ static abi_long do_syscall1(CPUArchState *cpu_env, int num, abi_long arg1,
       return do_set_thread_area(cpu_env, arg1);
 #elif defined(TARGET_M68K)
       {
-          TaskState *ts = cpu->opaque;
+          TaskState *ts = get_task_state(cpu);
           ts->tp_value = arg1;
           return 0;
       }
@@ -12551,7 +12551,7 @@ static abi_long do_syscall1(CPUArchState *cpu_env, int num, abi_long arg1,
         return do_get_thread_area(cpu_env, arg1);
 #elif defined(TARGET_M68K)
         {
-            TaskState *ts = cpu->opaque;
+            TaskState *ts = get_task_state(cpu);
             return ts->tp_value;
         }
 #else
@@ -12676,7 +12676,7 @@ static abi_long do_syscall1(CPUArchState *cpu_env, int num, abi_long arg1,
 #if defined(TARGET_NR_set_tid_address)
     case TARGET_NR_set_tid_address:
     {
-        TaskState *ts = cpu->opaque;
+        TaskState *ts = get_task_state(cpu);
         ts->child_tidptr = arg1;
         /* do not call host set_tid_address() syscall, instead return tid() */
         return get_errno(sys_gettid());
diff --git a/linux-user/user-internals.h b/linux-user/user-internals.h
index c63ef45..ce11d9e 100644
--- a/linux-user/user-internals.h
+++ b/linux-user/user-internals.h
@@ -71,7 +71,7 @@ const char *target_strerror(int err);
 int get_osversion(void);
 void init_qemu_uname_release(void);
 void fork_start(void);
-void fork_end(int child);
+void fork_end(pid_t pid);
 
 /**
  * probe_guest_base:
diff --git a/linux-user/vm86.c b/linux-user/vm86.c
index c2facf3..9f512a2 100644
--- a/linux-user/vm86.c
+++ b/linux-user/vm86.c
@@ -74,7 +74,7 @@ static inline unsigned int vm_getl(CPUX86State *env,
 void save_v86_state(CPUX86State *env)
 {
     CPUState *cs = env_cpu(env);
-    TaskState *ts = cs->opaque;
+    TaskState *ts = get_task_state(cs);
     struct target_vm86plus_struct * target_v86;
 
     if (!lock_user_struct(VERIFY_WRITE, target_v86, ts->target_v86, 0))
@@ -134,7 +134,7 @@ static inline void return_to_32bit(CPUX86State *env, int retval)
 static inline int set_IF(CPUX86State *env)
 {
     CPUState *cs = env_cpu(env);
-    TaskState *ts = cs->opaque;
+    TaskState *ts = get_task_state(cs);
 
     ts->v86flags |= VIF_MASK;
     if (ts->v86flags & VIP_MASK) {
@@ -147,7 +147,7 @@ static inline int set_IF(CPUX86State *env)
 static inline void clear_IF(CPUX86State *env)
 {
     CPUState *cs = env_cpu(env);
-    TaskState *ts = cs->opaque;
+    TaskState *ts = get_task_state(cs);
 
     ts->v86flags &= ~VIF_MASK;
 }
@@ -165,7 +165,7 @@ static inline void clear_AC(CPUX86State *env)
 static inline int set_vflags_long(unsigned long eflags, CPUX86State *env)
 {
     CPUState *cs = env_cpu(env);
-    TaskState *ts = cs->opaque;
+    TaskState *ts = get_task_state(cs);
 
     set_flags(ts->v86flags, eflags, ts->v86mask);
     set_flags(env->eflags, eflags, SAFE_MASK);
@@ -179,7 +179,7 @@ static inline int set_vflags_long(unsigned long eflags, CPUX86State *env)
 static inline int set_vflags_short(unsigned short flags, CPUX86State *env)
 {
     CPUState *cs = env_cpu(env);
-    TaskState *ts = cs->opaque;
+    TaskState *ts = get_task_state(cs);
 
     set_flags(ts->v86flags, flags, ts->v86mask & 0xffff);
     set_flags(env->eflags, flags, SAFE_MASK);
@@ -193,7 +193,7 @@ static inline int set_vflags_short(unsigned short flags, CPUX86State *env)
 static inline unsigned int get_vflags(CPUX86State *env)
 {
     CPUState *cs = env_cpu(env);
-    TaskState *ts = cs->opaque;
+    TaskState *ts = get_task_state(cs);
     unsigned int flags;
 
     flags = env->eflags & RETURN_MASK;
@@ -210,7 +210,7 @@ static inline unsigned int get_vflags(CPUX86State *env)
 static void do_int(CPUX86State *env, int intno)
 {
     CPUState *cs = env_cpu(env);
-    TaskState *ts = cs->opaque;
+    TaskState *ts = get_task_state(cs);
     uint32_t int_addr, segoffs, ssp;
     unsigned int sp;
 
@@ -269,7 +269,7 @@ void handle_vm86_trap(CPUX86State *env, int trapno)
 void handle_vm86_fault(CPUX86State *env)
 {
     CPUState *cs = env_cpu(env);
-    TaskState *ts = cs->opaque;
+    TaskState *ts = get_task_state(cs);
     uint32_t csp, ssp;
     unsigned int ip, sp, newflags, newip, newcs, opcode, intno;
     int data32, pref_done;
@@ -394,7 +394,7 @@ void handle_vm86_fault(CPUX86State *env)
 int do_vm86(CPUX86State *env, long subfunction, abi_ulong vm86_addr)
 {
     CPUState *cs = env_cpu(env);
-    TaskState *ts = cs->opaque;
+    TaskState *ts = get_task_state(cs);
     struct target_vm86plus_struct * target_v86;
     int ret;
 
diff --git a/linux-user/xtensa/signal.c b/linux-user/xtensa/signal.c
index 32dcfa5..003208a 100644
--- a/linux-user/xtensa/signal.c
+++ b/linux-user/xtensa/signal.c
@@ -157,7 +157,7 @@ void setup_rt_frame(int sig, struct target_sigaction *ka,
 {
     abi_ulong frame_addr;
     struct target_rt_sigframe *frame;
-    int is_fdpic = info_is_fdpic(((TaskState *)thread_cpu->opaque)->info);
+    int is_fdpic = info_is_fdpic(get_task_state(thread_cpu)->info);
     abi_ulong handler = 0;
     abi_ulong handler_fdpic_GOT = 0;
     uint32_t ra;
diff --git a/plugins/api.c b/plugins/api.c
index 81f43c9..8fa5a60 100644
--- a/plugins/api.c
+++ b/plugins/api.c
@@ -101,12 +101,15 @@ void qemu_plugin_register_vcpu_tb_exec_cb(struct qemu_plugin_tb *tb,
     }
 }
 
-void qemu_plugin_register_vcpu_tb_exec_inline(struct qemu_plugin_tb *tb,
-                                              enum qemu_plugin_op op,
-                                              void *ptr, uint64_t imm)
+void qemu_plugin_register_vcpu_tb_exec_inline_per_vcpu(
+    struct qemu_plugin_tb *tb,
+    enum qemu_plugin_op op,
+    qemu_plugin_u64 entry,
+    uint64_t imm)
 {
     if (!tb->mem_only) {
-        plugin_register_inline_op(&tb->cbs[PLUGIN_CB_INLINE], 0, op, ptr, imm);
+        plugin_register_inline_op_on_entry(
+            &tb->cbs[PLUGIN_CB_INLINE], 0, op, entry, imm);
     }
 }
 
@@ -125,13 +128,15 @@ void qemu_plugin_register_vcpu_insn_exec_cb(struct qemu_plugin_insn *insn,
     }
 }
 
-void qemu_plugin_register_vcpu_insn_exec_inline(struct qemu_plugin_insn *insn,
-                                                enum qemu_plugin_op op,
-                                                void *ptr, uint64_t imm)
+void qemu_plugin_register_vcpu_insn_exec_inline_per_vcpu(
+    struct qemu_plugin_insn *insn,
+    enum qemu_plugin_op op,
+    qemu_plugin_u64 entry,
+    uint64_t imm)
 {
     if (!insn->mem_only) {
-        plugin_register_inline_op(&insn->cbs[PLUGIN_CB_INSN][PLUGIN_CB_INLINE],
-                                  0, op, ptr, imm);
+        plugin_register_inline_op_on_entry(
+            &insn->cbs[PLUGIN_CB_INSN][PLUGIN_CB_INLINE], 0, op, entry, imm);
     }
 }
 
@@ -147,16 +152,18 @@ void qemu_plugin_register_vcpu_mem_cb(struct qemu_plugin_insn *insn,
                                       void *udata)
 {
     plugin_register_vcpu_mem_cb(&insn->cbs[PLUGIN_CB_MEM][PLUGIN_CB_REGULAR],
-                                    cb, flags, rw, udata);
+                                cb, flags, rw, udata);
 }
 
-void qemu_plugin_register_vcpu_mem_inline(struct qemu_plugin_insn *insn,
-                                          enum qemu_plugin_mem_rw rw,
-                                          enum qemu_plugin_op op, void *ptr,
-                                          uint64_t imm)
+void qemu_plugin_register_vcpu_mem_inline_per_vcpu(
+    struct qemu_plugin_insn *insn,
+    enum qemu_plugin_mem_rw rw,
+    enum qemu_plugin_op op,
+    qemu_plugin_u64 entry,
+    uint64_t imm)
 {
-    plugin_register_inline_op(&insn->cbs[PLUGIN_CB_MEM][PLUGIN_CB_INLINE],
-                              rw, op, ptr, imm);
+    plugin_register_inline_op_on_entry(
+        &insn->cbs[PLUGIN_CB_MEM][PLUGIN_CB_INLINE], rw, op, entry, imm);
 }
 
 void qemu_plugin_register_vcpu_tb_trans_cb(qemu_plugin_id_t id,
@@ -378,7 +385,7 @@ const char *qemu_plugin_path_to_binary(void)
 {
     char *path = NULL;
 #ifdef CONFIG_USER_ONLY
-    TaskState *ts = (TaskState *) current_cpu->opaque;
+    TaskState *ts = get_task_state(current_cpu);
     path = g_strdup(ts->bprm->filename);
 #endif
     return path;
@@ -388,7 +395,7 @@ uint64_t qemu_plugin_start_code(void)
 {
     uint64_t start = 0;
 #ifdef CONFIG_USER_ONLY
-    TaskState *ts = (TaskState *) current_cpu->opaque;
+    TaskState *ts = get_task_state(current_cpu);
     start = ts->info->start_code;
 #endif
     return start;
@@ -398,7 +405,7 @@ uint64_t qemu_plugin_end_code(void)
 {
     uint64_t end = 0;
 #ifdef CONFIG_USER_ONLY
-    TaskState *ts = (TaskState *) current_cpu->opaque;
+    TaskState *ts = get_task_state(current_cpu);
     end = ts->info->end_code;
 #endif
     return end;
@@ -408,7 +415,7 @@ uint64_t qemu_plugin_entry_code(void)
 {
     uint64_t entry = 0;
 #ifdef CONFIG_USER_ONLY
-    TaskState *ts = (TaskState *) current_cpu->opaque;
+    TaskState *ts = get_task_state(current_cpu);
     entry = ts->info->entry;
 #endif
     return entry;
@@ -465,3 +472,56 @@ int qemu_plugin_read_register(struct qemu_plugin_register *reg, GByteArray *buf)
 
     return gdb_read_register(current_cpu, buf, GPOINTER_TO_INT(reg));
 }
+
+struct qemu_plugin_scoreboard *qemu_plugin_scoreboard_new(size_t element_size)
+{
+    return plugin_scoreboard_new(element_size);
+}
+
+void qemu_plugin_scoreboard_free(struct qemu_plugin_scoreboard *score)
+{
+    plugin_scoreboard_free(score);
+}
+
+void *qemu_plugin_scoreboard_find(struct qemu_plugin_scoreboard *score,
+                                  unsigned int vcpu_index)
+{
+    g_assert(vcpu_index < qemu_plugin_num_vcpus());
+    /* we can't use g_array_index since entry size is not statically known */
+    char *base_ptr = score->data->data;
+    return base_ptr + vcpu_index * g_array_get_element_size(score->data);
+}
+
+static uint64_t *plugin_u64_address(qemu_plugin_u64 entry,
+                                    unsigned int vcpu_index)
+{
+    char *ptr = qemu_plugin_scoreboard_find(entry.score, vcpu_index);
+    return (uint64_t *)(ptr + entry.offset);
+}
+
+void qemu_plugin_u64_add(qemu_plugin_u64 entry, unsigned int vcpu_index,
+                         uint64_t added)
+{
+    *plugin_u64_address(entry, vcpu_index) += added;
+}
+
+uint64_t qemu_plugin_u64_get(qemu_plugin_u64 entry,
+                             unsigned int vcpu_index)
+{
+    return *plugin_u64_address(entry, vcpu_index);
+}
+
+void qemu_plugin_u64_set(qemu_plugin_u64 entry, unsigned int vcpu_index,
+                         uint64_t val)
+{
+    *plugin_u64_address(entry, vcpu_index) = val;
+}
+
+uint64_t qemu_plugin_u64_sum(qemu_plugin_u64 entry)
+{
+    uint64_t total = 0;
+    for (int i = 0, n = qemu_plugin_num_vcpus(); i < n; ++i) {
+        total += qemu_plugin_u64_get(entry, i);
+    }
+    return total;
+}
diff --git a/plugins/core.c b/plugins/core.c
index 2db4d31..11ca20e 100644
--- a/plugins/core.c
+++ b/plugins/core.c
@@ -18,6 +18,7 @@
 #include "qemu/lockable.h"
 #include "qemu/option.h"
 #include "qemu/plugin.h"
+#include "qemu/queue.h"
 #include "qemu/rcu_queue.h"
 #include "qemu/xxhash.h"
 #include "qemu/rcu.h"
@@ -215,6 +216,35 @@ CPUPluginState *qemu_plugin_create_vcpu_state(void)
     return g_new0(CPUPluginState, 1);
 }
 
+static void plugin_grow_scoreboards__locked(CPUState *cpu)
+{
+    if (cpu->cpu_index < plugin.scoreboard_alloc_size) {
+        return;
+    }
+
+    bool need_realloc = FALSE;
+    while (cpu->cpu_index >= plugin.scoreboard_alloc_size) {
+        plugin.scoreboard_alloc_size *= 2;
+        need_realloc = TRUE;
+    }
+
+
+    if (!need_realloc || QLIST_EMPTY(&plugin.scoreboards)) {
+        /* nothing to do, we just updated sizes for future scoreboards */
+        return;
+    }
+
+    /* cpus must be stopped, as tb might still use an existing scoreboard. */
+    start_exclusive();
+    struct qemu_plugin_scoreboard *score;
+    QLIST_FOREACH(score, &plugin.scoreboards, entry) {
+        g_array_set_size(score->data, plugin.scoreboard_alloc_size);
+    }
+    /* force all tb to be flushed, as scoreboard pointers were changed. */
+    tb_flush(cpu);
+    end_exclusive();
+}
+
 void qemu_plugin_vcpu_init_hook(CPUState *cpu)
 {
     bool success;
@@ -225,6 +255,7 @@ void qemu_plugin_vcpu_init_hook(CPUState *cpu)
     success = g_hash_table_insert(plugin.cpu_ht, &cpu->cpu_index,
                                   &cpu->cpu_index);
     g_assert(success);
+    plugin_grow_scoreboards__locked(cpu);
     qemu_rec_mutex_unlock(&plugin.lock);
 
     plugin_vcpu_cb__simple(cpu, QEMU_PLUGIN_EV_VCPU_INIT);
@@ -285,17 +316,19 @@ static struct qemu_plugin_dyn_cb *plugin_get_dyn_cb(GArray **arr)
     return &g_array_index(cbs, struct qemu_plugin_dyn_cb, cbs->len - 1);
 }
 
-void plugin_register_inline_op(GArray **arr,
-                               enum qemu_plugin_mem_rw rw,
-                               enum qemu_plugin_op op, void *ptr,
-                               uint64_t imm)
+void plugin_register_inline_op_on_entry(GArray **arr,
+                                        enum qemu_plugin_mem_rw rw,
+                                        enum qemu_plugin_op op,
+                                        qemu_plugin_u64 entry,
+                                        uint64_t imm)
 {
     struct qemu_plugin_dyn_cb *dyn_cb;
 
     dyn_cb = plugin_get_dyn_cb(arr);
-    dyn_cb->userp = ptr;
+    dyn_cb->userp = NULL;
     dyn_cb->type = PLUGIN_CB_INLINE;
     dyn_cb->rw = rw;
+    dyn_cb->inline_insn.entry = entry;
     dyn_cb->inline_insn.op = op;
     dyn_cb->inline_insn.imm = imm;
 }
@@ -443,9 +476,13 @@ void qemu_plugin_flush_cb(void)
     plugin_cb__simple(QEMU_PLUGIN_EV_FLUSH);
 }
 
-void exec_inline_op(struct qemu_plugin_dyn_cb *cb)
+void exec_inline_op(struct qemu_plugin_dyn_cb *cb, int cpu_index)
 {
-    uint64_t *val = cb->userp;
+    char *ptr = cb->inline_insn.entry.score->data->data;
+    size_t elem_size = g_array_get_element_size(
+        cb->inline_insn.entry.score->data);
+    size_t offset = cb->inline_insn.entry.offset;
+    uint64_t *val = (uint64_t *)(ptr + offset + cpu_index * elem_size);
 
     switch (cb->inline_insn.op) {
     case QEMU_PLUGIN_INLINE_ADD_U64:
@@ -478,7 +515,7 @@ void qemu_plugin_vcpu_mem_cb(CPUState *cpu, uint64_t vaddr,
                            vaddr, cb->userp);
             break;
         case PLUGIN_CB_INLINE:
-            exec_inline_op(cb);
+            exec_inline_op(cb, cpu->cpu_index);
             break;
         default:
             g_assert_not_reached();
@@ -578,6 +615,8 @@ static void __attribute__((__constructor__)) plugin_init(void)
     qemu_rec_mutex_init(&plugin.lock);
     plugin.id_ht = g_hash_table_new(g_int64_hash, g_int64_equal);
     plugin.cpu_ht = g_hash_table_new(g_int_hash, g_int_equal);
+    QLIST_INIT(&plugin.scoreboards);
+    plugin.scoreboard_alloc_size = 16; /* avoid frequent reallocation */
     QTAILQ_INIT(&plugin.ctxs);
     qht_init(&plugin.dyn_cb_arr_ht, plugin_dyn_cb_arr_cmp, 16,
              QHT_MODE_AUTO_RESIZE);
@@ -588,3 +627,27 @@ int plugin_num_vcpus(void)
 {
     return plugin.num_vcpus;
 }
+
+struct qemu_plugin_scoreboard *plugin_scoreboard_new(size_t element_size)
+{
+    struct qemu_plugin_scoreboard *score =
+        g_malloc0(sizeof(struct qemu_plugin_scoreboard));
+    score->data = g_array_new(FALSE, TRUE, element_size);
+    g_array_set_size(score->data, plugin.scoreboard_alloc_size);
+
+    qemu_rec_mutex_lock(&plugin.lock);
+    QLIST_INSERT_HEAD(&plugin.scoreboards, score, entry);
+    qemu_rec_mutex_unlock(&plugin.lock);
+
+    return score;
+}
+
+void plugin_scoreboard_free(struct qemu_plugin_scoreboard *score)
+{
+    qemu_rec_mutex_lock(&plugin.lock);
+    QLIST_REMOVE(score, entry);
+    qemu_rec_mutex_unlock(&plugin.lock);
+
+    g_array_free(score->data, TRUE);
+    g_free(score);
+}
diff --git a/plugins/plugin.h b/plugins/plugin.h
index 00b3509..7c34f23 100644
--- a/plugins/plugin.h
+++ b/plugins/plugin.h
@@ -31,6 +31,8 @@ struct qemu_plugin_state {
      * but with the HT we avoid adding a field to CPUState.
      */
     GHashTable *cpu_ht;
+    QLIST_HEAD(, qemu_plugin_scoreboard) scoreboards;
+    size_t scoreboard_alloc_size;
     DECLARE_BITMAP(mask, QEMU_PLUGIN_EV_MAX);
     /*
      * @lock protects the struct as well as ctx->uninstalling.
@@ -66,10 +68,11 @@ struct qemu_plugin_ctx {
 
 struct qemu_plugin_ctx *plugin_id_to_ctx_locked(qemu_plugin_id_t id);
 
-void plugin_register_inline_op(GArray **arr,
-                               enum qemu_plugin_mem_rw rw,
-                               enum qemu_plugin_op op, void *ptr,
-                               uint64_t imm);
+void plugin_register_inline_op_on_entry(GArray **arr,
+                                        enum qemu_plugin_mem_rw rw,
+                                        enum qemu_plugin_op op,
+                                        qemu_plugin_u64 entry,
+                                        uint64_t imm);
 
 void plugin_reset_uninstall(qemu_plugin_id_t id,
                             qemu_plugin_simple_cb_t cb,
@@ -97,8 +100,12 @@ void plugin_register_vcpu_mem_cb(GArray **arr,
                                  enum qemu_plugin_mem_rw rw,
                                  void *udata);
 
-void exec_inline_op(struct qemu_plugin_dyn_cb *cb);
+void exec_inline_op(struct qemu_plugin_dyn_cb *cb, int cpu_index);
 
 int plugin_num_vcpus(void);
 
+struct qemu_plugin_scoreboard *plugin_scoreboard_new(size_t element_size);
+
+void plugin_scoreboard_free(struct qemu_plugin_scoreboard *score);
+
 #endif /* PLUGIN_H */
diff --git a/plugins/qemu-plugins.symbols b/plugins/qemu-plugins.symbols
index 27fe972..a9fac05 100644
--- a/plugins/qemu-plugins.symbols
+++ b/plugins/qemu-plugins.symbols
@@ -27,20 +27,27 @@
   qemu_plugin_register_vcpu_idle_cb;
   qemu_plugin_register_vcpu_init_cb;
   qemu_plugin_register_vcpu_insn_exec_cb;
-  qemu_plugin_register_vcpu_insn_exec_inline;
+  qemu_plugin_register_vcpu_insn_exec_inline_per_vcpu;
   qemu_plugin_register_vcpu_mem_cb;
-  qemu_plugin_register_vcpu_mem_inline;
+  qemu_plugin_register_vcpu_mem_inline_per_vcpu;
   qemu_plugin_register_vcpu_resume_cb;
   qemu_plugin_register_vcpu_syscall_cb;
   qemu_plugin_register_vcpu_syscall_ret_cb;
   qemu_plugin_register_vcpu_tb_exec_cb;
-  qemu_plugin_register_vcpu_tb_exec_inline;
+  qemu_plugin_register_vcpu_tb_exec_inline_per_vcpu;
   qemu_plugin_register_vcpu_tb_trans_cb;
   qemu_plugin_reset;
+  qemu_plugin_scoreboard_free;
+  qemu_plugin_scoreboard_find;
+  qemu_plugin_scoreboard_new;
   qemu_plugin_start_code;
   qemu_plugin_tb_get_insn;
   qemu_plugin_tb_n_insns;
   qemu_plugin_tb_vaddr;
+  qemu_plugin_u64_add;
+  qemu_plugin_u64_get;
+  qemu_plugin_u64_set;
+  qemu_plugin_u64_sum;
   qemu_plugin_uninstall;
   qemu_plugin_vcpu_for_each;
 };
diff --git a/semihosting/arm-compat-semi.c b/semihosting/arm-compat-semi.c
index 329ea11..d78c642 100644
--- a/semihosting/arm-compat-semi.c
+++ b/semihosting/arm-compat-semi.c
@@ -214,7 +214,7 @@ static target_ulong syscall_err;
 static inline uint32_t get_swi_errno(CPUState *cs)
 {
 #ifdef CONFIG_USER_ONLY
-    TaskState *ts = cs->opaque;
+    TaskState *ts = get_task_state(cs);
 
     return ts->swi_errno;
 #else
@@ -226,7 +226,7 @@ static void common_semi_cb(CPUState *cs, uint64_t ret, int err)
 {
     if (err) {
 #ifdef CONFIG_USER_ONLY
-        TaskState *ts = cs->opaque;
+        TaskState *ts = get_task_state(cs);
         ts->swi_errno = err;
 #else
         syscall_err = err;
@@ -586,7 +586,7 @@ void do_common_semihosting(CPUState *cs)
 #if !defined(CONFIG_USER_ONLY)
             const char *cmdline;
 #else
-            TaskState *ts = cs->opaque;
+            TaskState *ts = get_task_state(cs);
 #endif
             GET_ARG(0);
             GET_ARG(1);
@@ -664,7 +664,7 @@ void do_common_semihosting(CPUState *cs)
             target_ulong retvals[4];
             int i;
 #ifdef CONFIG_USER_ONLY
-            TaskState *ts = cs->opaque;
+            TaskState *ts = get_task_state(cs);
             target_ulong limit;
 #else
             LayoutInfo info = common_semi_find_bases(cs);
diff --git a/target/loongarch/disas.c b/target/loongarch/disas.c
index 2040f3e..63989a6 100644
--- a/target/loongarch/disas.c
+++ b/target/loongarch/disas.c
@@ -120,10 +120,15 @@ static const char *get_csr_name(unsigned num)
            csr_names[num] : "Undefined CSR";
 }
 
-#define output(C, INSN, FMT, ...)                                   \
-{                                                                   \
-    (C)->info->fprintf_func((C)->info->stream, "%08x   %-9s\t" FMT, \
-                            (C)->insn, INSN, ##__VA_ARGS__);        \
+#define output(C, INSN, FMT, ...)                                      \
+ {                                                                     \
+    if ((C)->info->show_opcodes) {                                     \
+        (C)->info->fprintf_func((C)->info->stream, "%08x   %-9s\t" FMT,\
+                            (C)->insn, INSN, ##__VA_ARGS__);           \
+    } else {                                                           \
+        (C)->info->fprintf_func((C)->info->stream, "%-9s\t" FMT,       \
+                            INSN, ##__VA_ARGS__);                      \
+    }                                                                  \
 }
 
 #include "decode-insns.c.inc"
diff --git a/tests/plugin/bb.c b/tests/plugin/bb.c
index df50d1f..36776de 100644
--- a/tests/plugin/bb.c
+++ b/tests/plugin/bb.c
@@ -17,27 +17,25 @@
 QEMU_PLUGIN_EXPORT int qemu_plugin_version = QEMU_PLUGIN_VERSION;
 
 typedef struct {
-    GMutex lock;
-    int index;
     uint64_t bb_count;
     uint64_t insn_count;
 } CPUCount;
 
-/* Used by the inline & linux-user counts */
-static bool do_inline;
-static CPUCount inline_count;
+static struct qemu_plugin_scoreboard *counts;
+static qemu_plugin_u64 bb_count;
+static qemu_plugin_u64 insn_count;
 
+static bool do_inline;
 /* Dump running CPU total on idle? */
 static bool idle_report;
-static GPtrArray *counts;
-static int max_cpus;
 
-static void gen_one_cpu_report(CPUCount *count, GString *report)
+static void gen_one_cpu_report(CPUCount *count, GString *report,
+                               unsigned int cpu_index)
 {
     if (count->bb_count) {
         g_string_append_printf(report, "CPU%d: "
                                "bb's: %" PRIu64", insns: %" PRIu64 "\n",
-                               count->index,
+                               cpu_index,
                                count->bb_count, count->insn_count);
     }
 }
@@ -46,20 +44,23 @@ static void plugin_exit(qemu_plugin_id_t id, void *p)
 {
     g_autoptr(GString) report = g_string_new("");
 
-    if (do_inline || !max_cpus) {
-        g_string_printf(report, "bb's: %" PRIu64", insns: %" PRIu64 "\n",
-                        inline_count.bb_count, inline_count.insn_count);
-    } else {
-        g_ptr_array_foreach(counts, (GFunc) gen_one_cpu_report, report);
+    for (int i = 0; i < qemu_plugin_num_vcpus(); ++i) {
+        CPUCount *count = qemu_plugin_scoreboard_find(counts, i);
+        gen_one_cpu_report(count, report, i);
     }
+    g_string_append_printf(report, "Total: "
+                           "bb's: %" PRIu64", insns: %" PRIu64 "\n",
+                           qemu_plugin_u64_sum(bb_count),
+                           qemu_plugin_u64_sum(insn_count));
     qemu_plugin_outs(report->str);
+    qemu_plugin_scoreboard_free(counts);
 }
 
 static void vcpu_idle(qemu_plugin_id_t id, unsigned int cpu_index)
 {
-    CPUCount *count = g_ptr_array_index(counts, cpu_index);
+    CPUCount *count = qemu_plugin_scoreboard_find(counts, cpu_index);
     g_autoptr(GString) report = g_string_new("");
-    gen_one_cpu_report(count, report);
+    gen_one_cpu_report(count, report, cpu_index);
 
     if (report->len > 0) {
         g_string_prepend(report, "Idling ");
@@ -69,14 +70,11 @@ static void vcpu_idle(qemu_plugin_id_t id, unsigned int cpu_index)
 
 static void vcpu_tb_exec(unsigned int cpu_index, void *udata)
 {
-    CPUCount *count = max_cpus ?
-        g_ptr_array_index(counts, cpu_index) : &inline_count;
+    CPUCount *count = qemu_plugin_scoreboard_find(counts, cpu_index);
 
     uintptr_t n_insns = (uintptr_t)udata;
-    g_mutex_lock(&count->lock);
     count->insn_count += n_insns;
     count->bb_count++;
-    g_mutex_unlock(&count->lock);
 }
 
 static void vcpu_tb_trans(qemu_plugin_id_t id, struct qemu_plugin_tb *tb)
@@ -84,11 +82,10 @@ static void vcpu_tb_trans(qemu_plugin_id_t id, struct qemu_plugin_tb *tb)
     size_t n_insns = qemu_plugin_tb_n_insns(tb);
 
     if (do_inline) {
-        qemu_plugin_register_vcpu_tb_exec_inline(tb, QEMU_PLUGIN_INLINE_ADD_U64,
-                                                 &inline_count.bb_count, 1);
-        qemu_plugin_register_vcpu_tb_exec_inline(tb, QEMU_PLUGIN_INLINE_ADD_U64,
-                                                 &inline_count.insn_count,
-                                                 n_insns);
+        qemu_plugin_register_vcpu_tb_exec_inline_per_vcpu(
+            tb, QEMU_PLUGIN_INLINE_ADD_U64, bb_count, 1);
+        qemu_plugin_register_vcpu_tb_exec_inline_per_vcpu(
+            tb, QEMU_PLUGIN_INLINE_ADD_U64, insn_count, n_insns);
     } else {
         qemu_plugin_register_vcpu_tb_exec_cb(tb, vcpu_tb_exec,
                                              QEMU_PLUGIN_CB_NO_REGS,
@@ -121,18 +118,10 @@ QEMU_PLUGIN_EXPORT int qemu_plugin_install(qemu_plugin_id_t id,
         }
     }
 
-    if (info->system_emulation && !do_inline) {
-        max_cpus = info->system.max_vcpus;
-        counts = g_ptr_array_new();
-        for (i = 0; i < max_cpus; i++) {
-            CPUCount *count = g_new0(CPUCount, 1);
-            g_mutex_init(&count->lock);
-            count->index = i;
-            g_ptr_array_add(counts, count);
-        }
-    } else if (!do_inline) {
-        g_mutex_init(&inline_count.lock);
-    }
+    counts = qemu_plugin_scoreboard_new(sizeof(CPUCount));
+    bb_count = qemu_plugin_scoreboard_u64_in_struct(counts, CPUCount, bb_count);
+    insn_count = qemu_plugin_scoreboard_u64_in_struct(
+        counts, CPUCount, insn_count);
 
     if (idle_report) {
         qemu_plugin_register_vcpu_idle_cb(id, vcpu_idle);
diff --git a/tests/plugin/inline.c b/tests/plugin/inline.c
new file mode 100644
index 0000000..0163e9b
--- /dev/null
+++ b/tests/plugin/inline.c
@@ -0,0 +1,186 @@
+/*
+ * Copyright (C) 2023, Pierrick Bouvier <pierrick.bouvier@linaro.org>
+ *
+ * Demonstrates and tests usage of inline ops.
+ *
+ * License: GNU GPL, version 2 or later.
+ *   See the COPYING file in the top-level directory.
+ */
+
+#include <glib.h>
+#include <stdint.h>
+#include <stdio.h>
+
+#include <qemu-plugin.h>
+
+typedef struct {
+    uint64_t count_tb;
+    uint64_t count_tb_inline;
+    uint64_t count_insn;
+    uint64_t count_insn_inline;
+    uint64_t count_mem;
+    uint64_t count_mem_inline;
+} CPUCount;
+
+static struct qemu_plugin_scoreboard *counts;
+static qemu_plugin_u64 count_tb;
+static qemu_plugin_u64 count_tb_inline;
+static qemu_plugin_u64 count_insn;
+static qemu_plugin_u64 count_insn_inline;
+static qemu_plugin_u64 count_mem;
+static qemu_plugin_u64 count_mem_inline;
+
+static uint64_t global_count_tb;
+static uint64_t global_count_insn;
+static uint64_t global_count_mem;
+static unsigned int max_cpu_index;
+static GMutex tb_lock;
+static GMutex insn_lock;
+static GMutex mem_lock;
+
+QEMU_PLUGIN_EXPORT int qemu_plugin_version = QEMU_PLUGIN_VERSION;
+
+static void stats_insn(void)
+{
+    const uint64_t expected = global_count_insn;
+    const uint64_t per_vcpu = qemu_plugin_u64_sum(count_insn);
+    const uint64_t inl_per_vcpu =
+        qemu_plugin_u64_sum(count_insn_inline);
+    printf("insn: %" PRIu64 "\n", expected);
+    printf("insn: %" PRIu64 " (per vcpu)\n", per_vcpu);
+    printf("insn: %" PRIu64 " (per vcpu inline)\n", inl_per_vcpu);
+    g_assert(expected > 0);
+    g_assert(per_vcpu == expected);
+    g_assert(inl_per_vcpu == expected);
+}
+
+static void stats_tb(void)
+{
+    const uint64_t expected = global_count_tb;
+    const uint64_t per_vcpu = qemu_plugin_u64_sum(count_tb);
+    const uint64_t inl_per_vcpu =
+        qemu_plugin_u64_sum(count_tb_inline);
+    printf("tb: %" PRIu64 "\n", expected);
+    printf("tb: %" PRIu64 " (per vcpu)\n", per_vcpu);
+    printf("tb: %" PRIu64 " (per vcpu inline)\n", inl_per_vcpu);
+    g_assert(expected > 0);
+    g_assert(per_vcpu == expected);
+    g_assert(inl_per_vcpu == expected);
+}
+
+static void stats_mem(void)
+{
+    const uint64_t expected = global_count_mem;
+    const uint64_t per_vcpu = qemu_plugin_u64_sum(count_mem);
+    const uint64_t inl_per_vcpu =
+        qemu_plugin_u64_sum(count_mem_inline);
+    printf("mem: %" PRIu64 "\n", expected);
+    printf("mem: %" PRIu64 " (per vcpu)\n", per_vcpu);
+    printf("mem: %" PRIu64 " (per vcpu inline)\n", inl_per_vcpu);
+    g_assert(expected > 0);
+    g_assert(per_vcpu == expected);
+    g_assert(inl_per_vcpu == expected);
+}
+
+static void plugin_exit(qemu_plugin_id_t id, void *udata)
+{
+    const unsigned int num_cpus = qemu_plugin_num_vcpus();
+    g_assert(num_cpus == max_cpu_index + 1);
+
+    for (int i = 0; i < num_cpus ; ++i) {
+        const uint64_t tb = qemu_plugin_u64_get(count_tb, i);
+        const uint64_t tb_inline = qemu_plugin_u64_get(count_tb_inline, i);
+        const uint64_t insn = qemu_plugin_u64_get(count_insn, i);
+        const uint64_t insn_inline = qemu_plugin_u64_get(count_insn_inline, i);
+        const uint64_t mem = qemu_plugin_u64_get(count_mem, i);
+        const uint64_t mem_inline = qemu_plugin_u64_get(count_mem_inline, i);
+        printf("cpu %d: tb (%" PRIu64 ", %" PRIu64 ") | "
+               "insn (%" PRIu64 ", %" PRIu64 ") | "
+               "mem (%" PRIu64 ", %" PRIu64 ")"
+               "\n",
+               i, tb, tb_inline, insn, insn_inline, mem, mem_inline);
+        g_assert(tb == tb_inline);
+        g_assert(insn == insn_inline);
+        g_assert(mem == mem_inline);
+    }
+
+    stats_tb();
+    stats_insn();
+    stats_mem();
+
+    qemu_plugin_scoreboard_free(counts);
+}
+
+static void vcpu_tb_exec(unsigned int cpu_index, void *udata)
+{
+    qemu_plugin_u64_add(count_tb, cpu_index, 1);
+    g_mutex_lock(&tb_lock);
+    max_cpu_index = MAX(max_cpu_index, cpu_index);
+    global_count_tb++;
+    g_mutex_unlock(&tb_lock);
+}
+
+static void vcpu_insn_exec(unsigned int cpu_index, void *udata)
+{
+    qemu_plugin_u64_add(count_insn, cpu_index, 1);
+    g_mutex_lock(&insn_lock);
+    global_count_insn++;
+    g_mutex_unlock(&insn_lock);
+}
+
+static void vcpu_mem_access(unsigned int cpu_index,
+                            qemu_plugin_meminfo_t info,
+                            uint64_t vaddr,
+                            void *userdata)
+{
+    qemu_plugin_u64_add(count_mem, cpu_index, 1);
+    g_mutex_lock(&mem_lock);
+    global_count_mem++;
+    g_mutex_unlock(&mem_lock);
+}
+
+static void vcpu_tb_trans(qemu_plugin_id_t id, struct qemu_plugin_tb *tb)
+{
+    qemu_plugin_register_vcpu_tb_exec_cb(
+        tb, vcpu_tb_exec, QEMU_PLUGIN_CB_NO_REGS, 0);
+    qemu_plugin_register_vcpu_tb_exec_inline_per_vcpu(
+        tb, QEMU_PLUGIN_INLINE_ADD_U64, count_tb_inline, 1);
+
+    for (int idx = 0; idx < qemu_plugin_tb_n_insns(tb); ++idx) {
+        struct qemu_plugin_insn *insn = qemu_plugin_tb_get_insn(tb, idx);
+        qemu_plugin_register_vcpu_insn_exec_cb(
+            insn, vcpu_insn_exec, QEMU_PLUGIN_CB_NO_REGS, 0);
+        qemu_plugin_register_vcpu_insn_exec_inline_per_vcpu(
+            insn, QEMU_PLUGIN_INLINE_ADD_U64, count_insn_inline, 1);
+        qemu_plugin_register_vcpu_mem_cb(insn, &vcpu_mem_access,
+                                         QEMU_PLUGIN_CB_NO_REGS,
+                                         QEMU_PLUGIN_MEM_RW, 0);
+        qemu_plugin_register_vcpu_mem_inline_per_vcpu(
+            insn, QEMU_PLUGIN_MEM_RW,
+            QEMU_PLUGIN_INLINE_ADD_U64,
+            count_mem_inline, 1);
+    }
+}
+
+QEMU_PLUGIN_EXPORT
+int qemu_plugin_install(qemu_plugin_id_t id, const qemu_info_t *info,
+                        int argc, char **argv)
+{
+    counts = qemu_plugin_scoreboard_new(sizeof(CPUCount));
+    count_tb = qemu_plugin_scoreboard_u64_in_struct(
+        counts, CPUCount, count_tb);
+    count_insn = qemu_plugin_scoreboard_u64_in_struct(
+        counts, CPUCount, count_insn);
+    count_mem = qemu_plugin_scoreboard_u64_in_struct(
+        counts, CPUCount, count_mem);
+    count_tb_inline = qemu_plugin_scoreboard_u64_in_struct(
+        counts, CPUCount, count_tb_inline);
+    count_insn_inline = qemu_plugin_scoreboard_u64_in_struct(
+        counts, CPUCount, count_insn_inline);
+    count_mem_inline = qemu_plugin_scoreboard_u64_in_struct(
+        counts, CPUCount, count_mem_inline);
+    qemu_plugin_register_vcpu_tb_trans_cb(id, vcpu_tb_trans);
+    qemu_plugin_register_atexit_cb(id, plugin_exit, NULL);
+
+    return 0;
+}
diff --git a/tests/plugin/insn.c b/tests/plugin/insn.c
index 54da06f..5e0aa03 100644
--- a/tests/plugin/insn.c
+++ b/tests/plugin/insn.c
@@ -16,25 +16,21 @@
 
 QEMU_PLUGIN_EXPORT int qemu_plugin_version = QEMU_PLUGIN_VERSION;
 
-#define MAX_CPUS 8 /* lets not go nuts */
-
-typedef struct {
-    uint64_t insn_count;
-} InstructionCount;
-
-static InstructionCount counts[MAX_CPUS];
-static uint64_t inline_insn_count;
+static qemu_plugin_u64 insn_count;
 
 static bool do_inline;
 static bool do_size;
 static GArray *sizes;
 
 typedef struct {
+    uint64_t hits;
+    uint64_t last_hit;
+    uint64_t total_delta;
+} MatchCount;
+
+typedef struct {
     char *match_string;
-    uint64_t hits[MAX_CPUS];
-    uint64_t last_hit[MAX_CPUS];
-    uint64_t total_delta[MAX_CPUS];
-    GPtrArray *history[MAX_CPUS];
+    struct qemu_plugin_scoreboard *counts; /* MatchCount */
 } Match;
 
 static GArray *matches;
@@ -67,41 +63,40 @@ static void vcpu_init(qemu_plugin_id_t id, unsigned int vcpu_index)
 
 static void vcpu_insn_exec_before(unsigned int cpu_index, void *udata)
 {
-    unsigned int i = cpu_index % MAX_CPUS;
-    InstructionCount *c = &counts[i];
-
-    c->insn_count++;
+    qemu_plugin_u64_add(insn_count, cpu_index, 1);
 }
 
 static void vcpu_insn_matched_exec_before(unsigned int cpu_index, void *udata)
 {
-    unsigned int i = cpu_index % MAX_CPUS;
     Instruction *insn = (Instruction *) udata;
-    Match *match = insn->match;
+    Match *insn_match = insn->match;
+    MatchCount *match = qemu_plugin_scoreboard_find(insn_match->counts,
+                                                    cpu_index);
+
     g_autoptr(GString) ts = g_string_new("");
 
     insn->hits++;
     g_string_append_printf(ts, "0x%" PRIx64 ", '%s', %"PRId64 " hits",
                            insn->vaddr, insn->disas, insn->hits);
 
-    uint64_t icount = counts[i].insn_count;
-    uint64_t delta = icount - match->last_hit[i];
+    uint64_t icount = qemu_plugin_u64_get(insn_count, cpu_index);
+    uint64_t delta = icount - match->last_hit;
 
-    match->hits[i]++;
-    match->total_delta[i] += delta;
+    match->hits++;
+    match->total_delta += delta;
 
     g_string_append_printf(ts,
-                           ", %"PRId64" match hits, "
-                           "Δ+%"PRId64 " since last match,"
+                           " , cpu %u,"
+                           " %"PRId64" match hits,"
+                           " Δ+%"PRId64 " since last match,"
                            " %"PRId64 " avg insns/match\n",
-                           match->hits[i], delta,
-                           match->total_delta[i] / match->hits[i]);
+                           cpu_index,
+                           match->hits, delta,
+                           match->total_delta / match->hits);
 
-    match->last_hit[i] = icount;
+    match->last_hit = icount;
 
     qemu_plugin_outs(ts->str);
-
-    g_ptr_array_add(match->history[i], insn);
 }
 
 static void vcpu_tb_trans(qemu_plugin_id_t id, struct qemu_plugin_tb *tb)
@@ -113,8 +108,8 @@ static void vcpu_tb_trans(qemu_plugin_id_t id, struct qemu_plugin_tb *tb)
         struct qemu_plugin_insn *insn = qemu_plugin_tb_get_insn(tb, i);
 
         if (do_inline) {
-            qemu_plugin_register_vcpu_insn_exec_inline(
-                insn, QEMU_PLUGIN_INLINE_ADD_U64, &inline_insn_count, 1);
+            qemu_plugin_register_vcpu_insn_exec_inline_per_vcpu(
+                insn, QEMU_PLUGIN_INLINE_ADD_U64, insn_count, 1);
         } else {
             uint64_t vaddr = qemu_plugin_insn_vaddr(insn);
             qemu_plugin_register_vcpu_insn_exec_cb(
@@ -136,10 +131,9 @@ static void vcpu_tb_trans(qemu_plugin_id_t id, struct qemu_plugin_tb *tb)
          * information about the instruction which we also need to
          * save if there is a hit.
          */
-        if (matches) {
+        if (matches->len) {
             char *insn_disas = qemu_plugin_insn_disas(insn);
-            int j;
-            for (j = 0; j < matches->len; j++) {
+            for (int j = 0; j < matches->len; j++) {
                 Match *m = &g_array_index(matches, Match, j);
                 if (g_str_has_prefix(insn_disas, m->match_string)) {
                     Instruction *rec = g_new0(Instruction, 1);
@@ -169,36 +163,33 @@ static void plugin_exit(qemu_plugin_id_t id, void *p)
                                        "len %d bytes: %ld insns\n", i, *cnt);
             }
         }
-    } else if (do_inline) {
-        g_string_append_printf(out, "insns: %" PRIu64 "\n", inline_insn_count);
     } else {
-        uint64_t total_insns = 0;
-        for (i = 0; i < MAX_CPUS; i++) {
-            InstructionCount *c = &counts[i];
-            if (c->insn_count) {
-                g_string_append_printf(out, "cpu %d insns: %" PRIu64 "\n",
-                                       i, c->insn_count);
-                total_insns += c->insn_count;
-            }
+        for (i = 0; i < qemu_plugin_num_vcpus(); i++) {
+            g_string_append_printf(out, "cpu %d insns: %" PRIu64 "\n",
+                                   i, qemu_plugin_u64_get(insn_count, i));
         }
         g_string_append_printf(out, "total insns: %" PRIu64 "\n",
-                               total_insns);
+                               qemu_plugin_u64_sum(insn_count));
     }
     qemu_plugin_outs(out->str);
+
+    qemu_plugin_scoreboard_free(insn_count.score);
+    for (i = 0; i < matches->len; ++i) {
+        Match *m = &g_array_index(matches, Match, i);
+        g_free(m->match_string);
+        qemu_plugin_scoreboard_free(m->counts);
+    }
+    g_array_free(matches, TRUE);
+    g_array_free(sizes, TRUE);
 }
 
 
 /* Add a match to the array of matches */
 static void parse_match(char *match)
 {
-    Match new_match = { .match_string = match };
-    int i;
-    for (i = 0; i < MAX_CPUS; i++) {
-        new_match.history[i] = g_ptr_array_new();
-    }
-    if (!matches) {
-        matches = g_array_new(false, true, sizeof(Match));
-    }
+    Match new_match = {
+        .match_string = g_strdup(match),
+        .counts = qemu_plugin_scoreboard_new(sizeof(MatchCount)) };
     g_array_append_val(matches, new_match);
 }
 
@@ -206,6 +197,10 @@ QEMU_PLUGIN_EXPORT int qemu_plugin_install(qemu_plugin_id_t id,
                                            const qemu_info_t *info,
                                            int argc, char **argv)
 {
+    matches = g_array_new(false, true, sizeof(Match));
+    /* null terminated so 0 is not a special case */
+    sizes = g_array_new(true, true, sizeof(unsigned long));
+
     for (int i = 0; i < argc; i++) {
         char *opt = argv[i];
         g_auto(GStrv) tokens = g_strsplit(opt, "=", 2);
@@ -227,9 +222,8 @@ QEMU_PLUGIN_EXPORT int qemu_plugin_install(qemu_plugin_id_t id,
         }
     }
 
-    if (do_size) {
-        sizes = g_array_new(true, true, sizeof(unsigned long));
-    }
+    insn_count = qemu_plugin_scoreboard_u64(
+        qemu_plugin_scoreboard_new(sizeof(uint64_t)));
 
     /* Register init, translation block and exit callbacks */
     qemu_plugin_register_vcpu_init_cb(id, vcpu_init);
diff --git a/tests/plugin/mem.c b/tests/plugin/mem.c
index 44e9106..b650ddd 100644
--- a/tests/plugin/mem.c
+++ b/tests/plugin/mem.c
@@ -16,9 +16,14 @@
 
 QEMU_PLUGIN_EXPORT int qemu_plugin_version = QEMU_PLUGIN_VERSION;
 
-static uint64_t inline_mem_count;
-static uint64_t cb_mem_count;
-static uint64_t io_count;
+typedef struct {
+    uint64_t mem_count;
+    uint64_t io_count;
+} CPUCount;
+
+static struct qemu_plugin_scoreboard *counts;
+static qemu_plugin_u64 mem_count;
+static qemu_plugin_u64 io_count;
 static bool do_inline, do_callback;
 static bool do_haddr;
 static enum qemu_plugin_mem_rw rw = QEMU_PLUGIN_MEM_RW;
@@ -27,16 +32,16 @@ static void plugin_exit(qemu_plugin_id_t id, void *p)
 {
     g_autoptr(GString) out = g_string_new("");
 
-    if (do_inline) {
-        g_string_printf(out, "inline mem accesses: %" PRIu64 "\n", inline_mem_count);
-    }
-    if (do_callback) {
-        g_string_append_printf(out, "callback mem accesses: %" PRIu64 "\n", cb_mem_count);
+    if (do_inline || do_callback) {
+        g_string_printf(out, "mem accesses: %" PRIu64 "\n",
+                        qemu_plugin_u64_sum(mem_count));
     }
     if (do_haddr) {
-        g_string_append_printf(out, "io accesses: %" PRIu64 "\n", io_count);
+        g_string_append_printf(out, "io accesses: %" PRIu64 "\n",
+                               qemu_plugin_u64_sum(io_count));
     }
     qemu_plugin_outs(out->str);
+    qemu_plugin_scoreboard_free(counts);
 }
 
 static void vcpu_mem(unsigned int cpu_index, qemu_plugin_meminfo_t meminfo,
@@ -46,12 +51,12 @@ static void vcpu_mem(unsigned int cpu_index, qemu_plugin_meminfo_t meminfo,
         struct qemu_plugin_hwaddr *hwaddr;
         hwaddr = qemu_plugin_get_hwaddr(meminfo, vaddr);
         if (qemu_plugin_hwaddr_is_io(hwaddr)) {
-            io_count++;
+            qemu_plugin_u64_add(io_count, cpu_index, 1);
         } else {
-            cb_mem_count++;
+            qemu_plugin_u64_add(mem_count, cpu_index, 1);
         }
     } else {
-        cb_mem_count++;
+        qemu_plugin_u64_add(mem_count, cpu_index, 1);
     }
 }
 
@@ -64,9 +69,10 @@ static void vcpu_tb_trans(qemu_plugin_id_t id, struct qemu_plugin_tb *tb)
         struct qemu_plugin_insn *insn = qemu_plugin_tb_get_insn(tb, i);
 
         if (do_inline) {
-            qemu_plugin_register_vcpu_mem_inline(insn, rw,
-                                                 QEMU_PLUGIN_INLINE_ADD_U64,
-                                                 &inline_mem_count, 1);
+            qemu_plugin_register_vcpu_mem_inline_per_vcpu(
+                insn, rw,
+                QEMU_PLUGIN_INLINE_ADD_U64,
+                mem_count, 1);
         }
         if (do_callback) {
             qemu_plugin_register_vcpu_mem_cb(insn, vcpu_mem,
@@ -117,6 +123,16 @@ QEMU_PLUGIN_EXPORT int qemu_plugin_install(qemu_plugin_id_t id,
         }
     }
 
+    if (do_inline && do_callback) {
+        fprintf(stderr,
+                "can't enable inline and callback counting at the same time\n");
+        return -1;
+    }
+
+    counts = qemu_plugin_scoreboard_new(sizeof(CPUCount));
+    mem_count = qemu_plugin_scoreboard_u64_in_struct(
+        counts, CPUCount, mem_count);
+    io_count = qemu_plugin_scoreboard_u64_in_struct(counts, CPUCount, io_count);
     qemu_plugin_register_vcpu_tb_trans_cb(id, vcpu_tb_trans);
     qemu_plugin_register_atexit_cb(id, plugin_exit, NULL);
     return 0;
diff --git a/tests/plugin/meson.build b/tests/plugin/meson.build
index e18183a..9eece5b 100644
--- a/tests/plugin/meson.build
+++ b/tests/plugin/meson.build
@@ -1,6 +1,6 @@
 t = []
 if get_option('plugins')
-  foreach i : ['bb', 'empty', 'insn', 'mem', 'syscall']
+  foreach i : ['bb', 'empty', 'inline', 'insn', 'mem', 'syscall']
     if host_os == 'windows'
       t += shared_module(i, files(i + '.c') + '../../contrib/plugins/win32_linker.c',
                         include_directories: '../../include/qemu',
diff --git a/tests/qtest/libqos/qgraph.h b/tests/qtest/libqos/qgraph.h
index 287022a..1b5de02 100644
--- a/tests/qtest/libqos/qgraph.h
+++ b/tests/qtest/libqos/qgraph.h
@@ -24,7 +24,7 @@
 #include "libqos-malloc.h"
 
 /* maximum path length */
-#define QOS_PATH_MAX_ELEMENT_SIZE 64
+#define QOS_PATH_MAX_ELEMENT_SIZE 128
 
 typedef struct QOSGraphObject QOSGraphObject;
 typedef struct QOSGraphNode QOSGraphNode;
diff --git a/tests/tcg/Makefile.target b/tests/tcg/Makefile.target
index a4c2590..f21be50 100644
--- a/tests/tcg/Makefile.target
+++ b/tests/tcg/Makefile.target
@@ -168,7 +168,7 @@ RUN_TESTS+=$(EXTRA_RUNS)
 
 # Some plugins need additional arguments above the default to fully
 # exercise things. We can define them on a per-test basis here.
-run-plugin-%-with-libmem.so: PLUGIN_ARGS=$(COMMA)inline=true$(COMMA)callback=true
+run-plugin-%-with-libmem.so: PLUGIN_ARGS=$(COMMA)inline=true
 
 ifeq ($(filter %-softmmu, $(TARGET)),)
 run-%: %
diff --git a/tests/tcg/multiarch/Makefile.target b/tests/tcg/multiarch/Makefile.target
index f11f3b0..979a0dd 100644
--- a/tests/tcg/multiarch/Makefile.target
+++ b/tests/tcg/multiarch/Makefile.target
@@ -106,6 +106,20 @@ run-gdbstub-catch-syscalls: catch-syscalls
 		--bin $< --test $(MULTIARCH_SRC)/gdbstub/catch-syscalls.py, \
 	hitting a syscall catchpoint)
 
+run-gdbstub-follow-fork-mode-child: follow-fork-mode
+	$(call run-test, $@, $(GDB_SCRIPT) \
+		--gdb $(GDB) \
+		--qemu $(QEMU) --qargs "$(QEMU_OPTS)" \
+		--bin $< --test $(MULTIARCH_SRC)/gdbstub/follow-fork-mode-child.py, \
+	following children on fork)
+
+run-gdbstub-follow-fork-mode-parent: follow-fork-mode
+	$(call run-test, $@, $(GDB_SCRIPT) \
+		--gdb $(GDB) \
+		--qemu $(QEMU) --qargs "$(QEMU_OPTS)" \
+		--bin $< --test $(MULTIARCH_SRC)/gdbstub/follow-fork-mode-parent.py, \
+	following parents on fork)
+
 else
 run-gdbstub-%:
 	$(call skip-test, "gdbstub test $*", "need working gdb with $(patsubst -%,,$(TARGET_NAME)) support")
@@ -113,7 +127,8 @@ endif
 EXTRA_RUNS += run-gdbstub-sha1 run-gdbstub-qxfer-auxv-read \
 	      run-gdbstub-proc-mappings run-gdbstub-thread-breakpoint \
 	      run-gdbstub-registers run-gdbstub-prot-none \
-	      run-gdbstub-catch-syscalls
+	      run-gdbstub-catch-syscalls run-gdbstub-follow-fork-mode-child \
+	      run-gdbstub-follow-fork-mode-parent
 
 # ARM Compatible Semi Hosting Tests
 #
diff --git a/tests/tcg/multiarch/follow-fork-mode.c b/tests/tcg/multiarch/follow-fork-mode.c
new file mode 100644
index 0000000..cb6b032
--- /dev/null
+++ b/tests/tcg/multiarch/follow-fork-mode.c
@@ -0,0 +1,56 @@
+/*
+ * Test GDB's follow-fork-mode.
+ *
+ * fork() a chain of processes.
+ * Parents sends one byte to their children, and children return their
+ * position in the chain, in order to prove that they survived GDB's fork()
+ * handling.
+ *
+ * SPDX-License-Identifier: GPL-2.0-or-later
+ */
+#include <assert.h>
+#include <stdlib.h>
+#include <sys/wait.h>
+#include <unistd.h>
+
+void break_after_fork(void)
+{
+}
+
+int main(void)
+{
+    int depth = 42, err, i, fd[2], status;
+    pid_t child, pid;
+    ssize_t n;
+    char b;
+
+    for (i = 0; i < depth; i++) {
+        err = pipe(fd);
+        assert(err == 0);
+        child = fork();
+        break_after_fork();
+        assert(child != -1);
+        if (child == 0) {
+            close(fd[1]);
+
+            n = read(fd[0], &b, 1);
+            close(fd[0]);
+            assert(n == 1);
+            assert(b == (char)i);
+        } else {
+            close(fd[0]);
+
+            b = (char)i;
+            n = write(fd[1], &b, 1);
+            close(fd[1]);
+            assert(n == 1);
+
+            pid = waitpid(child, &status, 0);
+            assert(pid == child);
+            assert(WIFEXITED(status));
+            return WEXITSTATUS(status) - 1;
+        }
+    }
+
+    return depth;
+}
diff --git a/tests/tcg/multiarch/gdbstub/follow-fork-mode-child.py b/tests/tcg/multiarch/gdbstub/follow-fork-mode-child.py
new file mode 100644
index 0000000..72a6e44
--- /dev/null
+++ b/tests/tcg/multiarch/gdbstub/follow-fork-mode-child.py
@@ -0,0 +1,40 @@
+"""Test GDB's follow-fork-mode child.
+
+SPDX-License-Identifier: GPL-2.0-or-later
+"""
+from test_gdbstub import main, report
+
+
+def run_test():
+    """Run through the tests one by one"""
+    gdb.execute("set follow-fork-mode child")
+    # Check that the parent breakpoints are unset.
+    gdb.execute("break break_after_fork")
+    # Check that the parent syscall catchpoints are unset.
+    # Skip this check on the architectures that don't have them.
+    have_fork_syscall = False
+    for fork_syscall in ("fork", "clone", "clone2", "clone3"):
+        try:
+            gdb.execute("catch syscall {}".format(fork_syscall))
+        except gdb.error:
+            pass
+        else:
+            have_fork_syscall = True
+    gdb.execute("continue")
+    for i in range(42):
+        if have_fork_syscall:
+            # syscall entry.
+            if i % 2 == 0:
+                # Check that the parent single-stepping is turned off.
+                gdb.execute("si")
+            else:
+                gdb.execute("continue")
+            # syscall exit.
+            gdb.execute("continue")
+        # break_after_fork()
+        gdb.execute("continue")
+    exitcode = int(gdb.parse_and_eval("$_exitcode"))
+    report(exitcode == 42, "{} == 42".format(exitcode))
+
+
+main(run_test)
diff --git a/tests/tcg/multiarch/gdbstub/follow-fork-mode-parent.py b/tests/tcg/multiarch/gdbstub/follow-fork-mode-parent.py
new file mode 100644
index 0000000..5c2fe72
--- /dev/null
+++ b/tests/tcg/multiarch/gdbstub/follow-fork-mode-parent.py
@@ -0,0 +1,16 @@
+"""Test GDB's follow-fork-mode parent.
+
+SPDX-License-Identifier: GPL-2.0-or-later
+"""
+from test_gdbstub import main, report
+
+
+def run_test():
+    """Run through the tests one by one"""
+    gdb.execute("set follow-fork-mode parent")
+    gdb.execute("continue")
+    exitcode = int(gdb.parse_and_eval("$_exitcode"))
+    report(exitcode == 0, "{} == 0".format(exitcode))
+
+
+main(run_test)