Merge tag 'pull-maintainer-updates-060324-1' of https://gitlab.com/st…

…squad/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>

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;
 }
 

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 {

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;
 }

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();
     }
 }

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"
 

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 @@ long do_sigreturn(CPUArchState *env, abi_ulong addr)
 
 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);

contrib/plugins/hotblocks.c

@@ -34,16 +34,26 @@ 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;
 
 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);
     }
 }