From: Torge Matthies tmatthies@codeweavers.com
Based on a patch by Jinoh Kang from February 2022 [1]. The following description is copied from said patch:
NtFlushProcessWriteBuffers is the NT equivalent of Linux membarrier() system call. The .NET Framework garbage collector uses it to synchronize with other threads, and thus is required to avoid silent memory corruption.
[1] https://www.winehq.org/mailman3/hyperkitty/list/wine-devel@winehq.org/messag... --- dlls/ntdll/unix/server.c | 6 ++ dlls/ntdll/unix/virtual.c | 27 ++++++++- server/protocol.def | 19 ++++++- server/thread.c | 117 ++++++++++++++++++++++++++++++++++++++ server/thread.h | 1 + 5 files changed, 166 insertions(+), 4 deletions(-)
diff --git a/dlls/ntdll/unix/server.c b/dlls/ntdll/unix/server.c index 77e8d5c7566..51a83f472e1 100644 --- a/dlls/ntdll/unix/server.c +++ b/dlls/ntdll/unix/server.c @@ -574,6 +574,12 @@ static void invoke_system_apc( const apc_call_t *call, apc_result_t *result, BOO if (!self) NtClose( wine_server_ptr_handle(call->dup_handle.dst_process) ); break; } + case APC_MEMORY_BARRIER: + { + MemoryBarrier(); + result->type = call->type; + break; + } default: server_protocol_error( "get_apc_request: bad type %d\n", call->type ); break; diff --git a/dlls/ntdll/unix/virtual.c b/dlls/ntdll/unix/virtual.c index d8b888aa49e..d9d9b2b8d08 100644 --- a/dlls/ntdll/unix/virtual.c +++ b/dlls/ntdll/unix/virtual.c @@ -5025,8 +5025,31 @@ NTSTATUS WINAPI NtFlushInstructionCache( HANDLE handle, const void *addr, SIZE_T */ void WINAPI NtFlushProcessWriteBuffers(void) { - static int once = 0; - if (!once++) FIXME( "stub\n" ); + static pthread_mutex_t apc_memorybarrier_mutex = PTHREAD_MUTEX_INITIALIZER; + NTSTATUS status; + + pthread_mutex_lock( &apc_memorybarrier_mutex ); + + do + { + SERVER_START_REQ( flush_process_write_buffers ) + { + status = wine_server_call( req ); + } + SERVER_END_REQ; + } + while (status); + + do + { + select_op_t select_op; + select_op.membarrier.op = SELECT_MEMBARRIER; + status = server_select( &select_op, sizeof(select_op.membarrier), SELECT_INTERRUPTIBLE, + TIMEOUT_INFINITE, NULL, NULL ); + } + while (status); + + pthread_mutex_unlock( &apc_memorybarrier_mutex ); }
diff --git a/server/protocol.def b/server/protocol.def index 86fb10951f0..4ed05c83585 100644 --- a/server/protocol.def +++ b/server/protocol.def @@ -462,7 +462,8 @@ enum select_op SELECT_WAIT_ALL, SELECT_SIGNAL_AND_WAIT, SELECT_KEYED_EVENT_WAIT, - SELECT_KEYED_EVENT_RELEASE + SELECT_KEYED_EVENT_RELEASE, + SELECT_MEMBARRIER };
typedef union @@ -485,6 +486,10 @@ typedef union obj_handle_t handle; client_ptr_t key; } keyed_event; + struct + { + enum select_op op; /* SELECT_MEMBARRIER */ + } membarrier; } select_op_t;
enum apc_type @@ -502,7 +507,8 @@ enum apc_type APC_MAP_VIEW, APC_UNMAP_VIEW, APC_CREATE_THREAD, - APC_DUP_HANDLE + APC_DUP_HANDLE, + APC_MEMORY_BARRIER };
typedef struct @@ -611,6 +617,10 @@ typedef union unsigned int attributes; /* object attributes */ unsigned int options; /* duplicate options */ } dup_handle; + struct + { + enum apc_type type; /* APC_MEMORY_BARRIER */ + } memory_barrier; } apc_call_t;
typedef union @@ -1610,6 +1620,11 @@ enum server_fd_type @END
+/* Issue a memory barrier on other threads in the same process */ +@REQ(flush_process_write_buffers) +@END + + struct thread_info { timeout_t start_time; diff --git a/server/thread.c b/server/thread.c index f49fbf40b78..9eed1e5bbdf 100644 --- a/server/thread.c +++ b/server/thread.c @@ -112,6 +112,41 @@ static const struct object_ops thread_apc_ops = thread_apc_destroy /* destroy */ };
+/* process-wide memory barriers */ + +struct memory_barrier +{ + struct object obj; /* object header */ +}; + +static void dump_memory_barrier( struct object *obj, int verbose ); +static int memory_barrier_signaled( struct object *obj, struct wait_queue_entry *entry ); + +static const struct object_ops memory_barrier_ops = +{ + sizeof(struct memory_barrier), /* size */ + &no_type, /* type */ + dump_memory_barrier, /* dump */ + add_queue, /* add_queue */ + remove_queue, /* remove_queue */ + memory_barrier_signaled, /* signaled */ + no_satisfied, /* satisfied */ + no_signal, /* signal */ + no_get_fd, /* get_fd */ + default_map_access, /* map_access */ + default_get_sd, /* get_sd */ + default_set_sd, /* set_sd */ + no_get_full_name, /* get_full_name */ + no_lookup_name, /* lookup_name */ + no_link_name, /* link_name */ + NULL, /* unlink_name */ + no_open_file, /* open_file */ + no_kernel_obj_list, /* get_kernel_obj_list */ + no_close_handle, /* close_handle */ + no_destroy /* destroy */ +}; + +struct memory_barrier *memory_barrier_obj;
/* thread CPU context */
@@ -249,6 +284,7 @@ static inline void init_thread_structure( struct thread *thread ) thread->token = NULL; thread->desc = NULL; thread->desc_len = 0; + thread->mb_apcs_pending = 0;
thread->creation_time = current_time; thread->exit_time = 0; @@ -306,6 +342,11 @@ struct thread *create_thread( int fd, struct process *process, const struct secu struct thread *thread; int request_pipe[2];
+ if (memory_barrier_obj) + grab_object( &memory_barrier_obj->obj ); + else if (!(memory_barrier_obj = alloc_object( &memory_barrier_ops ))) + return NULL; + if (fd == -1) { if (pipe( request_pipe ) == -1) @@ -441,12 +482,14 @@ static void cleanup_thread( struct thread *thread ) thread->desktop = 0; thread->desc = NULL; thread->desc_len = 0; + thread->mb_apcs_pending = 0; }
/* destroy a thread when its refcount is 0 */ static void destroy_thread( struct object *obj ) { struct thread *thread = (struct thread *)obj; + struct memory_barrier *mb = memory_barrier_obj; assert( obj->ops == &thread_ops );
list_remove( &thread->entry ); @@ -454,6 +497,9 @@ static void destroy_thread( struct object *obj ) release_object( thread->process ); if (thread->id) free_ptid( thread->id ); if (thread->token) release_object( thread->token ); + if (mb->obj.refcount == 1) + memory_barrier_obj = NULL; + release_object( &mb->obj ); }
/* dump a thread on stdout for debugging purposes */ @@ -526,6 +572,18 @@ static struct thread_apc *create_apc( struct object *owner, const apc_call_t *ca return apc; }
+static void dump_memory_barrier( struct object *obj, int verbose ) +{ + assert( obj->ops == &memory_barrier_ops ); + fprintf( stderr, "Memory barrier\n" ); +} + +static int memory_barrier_signaled( struct object *obj, struct wait_queue_entry *entry ) +{ + struct thread *thread = entry->wait->thread; + return !thread->mb_apcs_pending; +} + /* get a thread pointer from a thread id (and increment the refcount) */ struct thread *get_thread_from_id( thread_id_t id ) { @@ -1029,6 +1087,13 @@ static int select_on( const select_op_t *select_op, data_size_t op_size, client_ current->wait->key = select_op->keyed_event.key; break;
+ case SELECT_MEMBARRIER: + object = &memory_barrier_obj->obj; + if (!object) return 1; + ret = wait_on( select_op, 1, &object, flags, when ); + if (!ret) return 1; + break; + default: set_error( STATUS_INVALID_PARAMETER ); return 1; @@ -1165,6 +1230,16 @@ int thread_queue_apc( struct process *process, struct thread *thread, struct obj return ret; }
+static void finish_membarrier_apc( struct thread_apc *apc ) +{ + struct thread *thread = (struct thread *)apc->owner; + + assert( thread ); + assert( thread->mb_apcs_pending > 0 ); + if (--thread->mb_apcs_pending) + wake_up( &memory_barrier_obj->obj, 1 ); +} + /* cancel the async procedure call owned by a specific object */ void thread_cancel_apc( struct thread *thread, struct object *owner, enum apc_type type ) { @@ -1176,6 +1251,8 @@ void thread_cancel_apc( struct thread *thread, struct object *owner, enum apc_ty if (apc->owner != owner) continue; list_remove( &apc->entry ); apc->executed = 1; + if (apc->call.type == APC_MEMORY_BARRIER) + finish_membarrier_apc( apc ); wake_up( &apc->obj, 0 ); release_object( apc ); return; @@ -1206,6 +1283,8 @@ static void clear_apc_queue( struct list *queue ) struct thread_apc *apc = LIST_ENTRY( ptr, struct thread_apc, entry ); list_remove( &apc->entry ); apc->executed = 1; + if (apc->call.type == APC_MEMORY_BARRIER) + finish_membarrier_apc( apc ); wake_up( &apc->obj, 0 ); release_object( apc ); } @@ -1650,6 +1729,8 @@ DECL_HANDLER(select) apc->result.create_thread.handle = handle; clear_error(); /* ignore errors from the above calls */ } + if (apc->call.type == APC_MEMORY_BARRIER) /* wake up caller if membarriers done */ + finish_membarrier_apc( apc ); wake_up( &apc->obj, 0 ); close_handle( current->process, req->prev_apc ); release_object( apc ); @@ -1671,6 +1752,8 @@ DECL_HANDLER(select) else { apc->executed = 1; + if (apc->call.type == APC_MEMORY_BARRIER) + finish_membarrier_apc( apc ); wake_up( &apc->obj, 0 ); } release_object( apc ); @@ -2012,3 +2095,37 @@ DECL_HANDLER(get_next_thread) set_error( STATUS_NO_MORE_ENTRIES ); release_object( process ); } + +DECL_HANDLER(flush_process_write_buffers) +{ + struct process *process = current->process; + struct thread *thread; + apc_call_t call; + + assert( memory_barrier_obj ); + + memset( &call, 0, sizeof(call) ); + call.memory_barrier.type = APC_MEMORY_BARRIER; + + LIST_FOR_EACH_ENTRY( thread, &process->thread_list, struct thread, proc_entry ) + { + struct thread_apc *apc; + int success; + + /* Do not send a memory barrier APC to the current thread or a terminated thread. */ + if (thread == current || thread->state == TERMINATED) continue; + + if (!(apc = create_apc( ¤t->obj, &call ))) break; + + if ((success = queue_apc( NULL, thread, apc ))) + thread->mb_apcs_pending++; + + release_object( apc ); + + if (!success) + { + set_error( STATUS_UNSUCCESSFUL ); + break; + } + } +} diff --git a/server/thread.h b/server/thread.h index 8dcf966a90a..c9040704700 100644 --- a/server/thread.h +++ b/server/thread.h @@ -90,6 +90,7 @@ struct thread struct list kernel_object; /* list of kernel object pointers */ data_size_t desc_len; /* thread description length in bytes */ WCHAR *desc; /* thread description string */ + int mb_apcs_pending; /* number of APCs left for the current memory barrier */ };
extern struct thread *current;