From ef525b012a709077ea2797e8642fae0b61234063 Mon Sep 17 00:00:00 2001 From: Samuel Williams Date: Mon, 9 May 2022 11:03:04 +1200 Subject: Explicit handling of frozen strings in `IO::Buffer#for`. (#5892) --- io_buffer.c | 122 +++++++++++++++++++++++++++++++++++++++++++++++------------- 1 file changed, 97 insertions(+), 25 deletions(-) (limited to 'io_buffer.c') diff --git a/io_buffer.c b/io_buffer.c index fb18e729a6..b0b3e9ae53 100644 --- a/io_buffer.c +++ b/io_buffer.c @@ -208,9 +208,11 @@ io_buffer_free(struct rb_io_buffer *data) io_buffer_unmap(data->base, data->size); } - if (RB_TYPE_P(data->source, T_STRING)) { - rb_str_unlocktmp(data->source); - } + // Previously we had this, but we found out due to the way GC works, we + // can't refer to any other Ruby objects here. + // if (RB_TYPE_P(data->source, T_STRING)) { + // rb_str_unlocktmp(data->source); + // } data->base = NULL; @@ -282,12 +284,65 @@ rb_io_buffer_type_allocate(VALUE self) return instance; } +static VALUE +io_buffer_for_make_instance(VALUE klass, VALUE string) +{ + VALUE instance = rb_io_buffer_type_allocate(klass); + + struct rb_io_buffer *data = NULL; + TypedData_Get_Struct(instance, struct rb_io_buffer, &rb_io_buffer_type, data); + + enum rb_io_buffer_flags flags = RB_IO_BUFFER_EXTERNAL; + + if (RB_OBJ_FROZEN(string)) + flags |= RB_IO_BUFFER_READONLY; + + io_buffer_initialize(data, RSTRING_PTR(string), RSTRING_LEN(string), flags, string); + + return instance; +} + +struct io_buffer_for_yield_instance_arguments { + VALUE klass; + VALUE string; + VALUE instance; +}; + +static VALUE +io_buffer_for_yield_instance(VALUE _arguments) { + struct io_buffer_for_yield_instance_arguments *arguments = (struct io_buffer_for_yield_instance_arguments *)_arguments; + + rb_str_locktmp(arguments->string); + + arguments->instance = io_buffer_for_make_instance(arguments->klass, arguments->string); + + return rb_yield(arguments->instance); +} + +static VALUE +io_buffer_for_yield_instance_ensure(VALUE _arguments) +{ + struct io_buffer_for_yield_instance_arguments *arguments = (struct io_buffer_for_yield_instance_arguments *)_arguments; + + if (arguments->instance != Qnil) { + rb_io_buffer_free(arguments->instance); + } + + rb_str_unlocktmp(arguments->string); + + return Qnil; +} + /* - * call-seq: IO::Buffer.for(string) -> io_buffer + * call-seq: + * IO::Buffer.for(string) -> readonly io_buffer + * IO::Buffer.for(string) {|io_buffer| ... read/write io_buffer ...} * - * Creates a IO::Buffer from the given string's memory. The buffer remains - * associated with the string, and writing to a buffer will update the string's - * contents. + * Creates a IO::Buffer from the given string's memory. Without a block a + * frozen internal copy of the string is created efficiently and used as the + * buffer source. When a block is provided, the buffer is associated directly + * with the string's internal data and updating the buffer will update the + * string. * * Until #free is invoked on the buffer, either explicitly or via the garbage * collector, the source string will be locked and cannot be modified. @@ -296,7 +351,7 @@ rb_io_buffer_type_allocate(VALUE self) * modified. * * string = 'test' - * buffer = IO::Buffer.for(str) + * buffer = IO::Buffer.for(string) * buffer.external? #=> true * * buffer.get_string(0, 1) @@ -306,29 +361,33 @@ rb_io_buffer_type_allocate(VALUE self) * * buffer.resize(100) * # in `resize': Cannot resize external buffer! (IO::Buffer::AccessError) + * + * IO::Buffer.for(string) do |buffer| + * buffer.set_string("T") + * string + * # => "Test" + * end */ VALUE rb_io_buffer_type_for(VALUE klass, VALUE string) { - io_buffer_experimental(); - StringValue(string); - VALUE instance = rb_io_buffer_type_allocate(klass); - - struct rb_io_buffer *data = NULL; - TypedData_Get_Struct(instance, struct rb_io_buffer, &rb_io_buffer_type, data); - - rb_str_locktmp(string); - - enum rb_io_buffer_flags flags = RB_IO_BUFFER_EXTERNAL; - - if (RB_OBJ_FROZEN(string)) - flags |= RB_IO_BUFFER_READONLY; + // If the string is frozen, both code paths are okay. + // If the string is not frozen, if a block is not given, it must be frozen. + if (rb_block_given_p()) { + struct io_buffer_for_yield_instance_arguments arguments = { + .klass = klass, + .string = string, + .instance = Qnil, + }; - io_buffer_initialize(data, RSTRING_PTR(string), RSTRING_LEN(string), flags, string); - - return instance; + return rb_ensure(io_buffer_for_yield_instance, (VALUE)&arguments, io_buffer_for_yield_instance_ensure, (VALUE)&arguments); + } else { + // This internally returns the source string if it's already frozen. + string = rb_str_tmp_frozen_acquire(string); + return io_buffer_for_make_instance(klass, string); + } } VALUE @@ -2079,7 +2138,20 @@ io_buffer_pwrite(VALUE self, VALUE io, VALUE length, VALUE offset) * C mechanisms like `memcpy`. * * The class is meant to be an utility for implementing more high-level mechanisms - * like Fiber::SchedulerInterface#io_read and Fiber::SchedulerInterface#io_write. + * like Fiber::SchedulerInterface#io_read and Fiber::Sc io_buffer_unmap(data->base, data->size); + } + + if (RB_TYPE_P(data->source, T_STRING)) { + rb_str_unlocktmp(data->source); + } + // Previously we had this, but we found out due to the way GC works, we + // can't refer to any other Ruby objects here. + // if (RB_TYPE_P(data->source, T_STRING)) { + // rb_str_unlocktmp(data->source); + // } + + data->base = NULL; +hedulerInterface#io_write. * * Examples of usage: * -- cgit v1.2.1