Don’t corrupt the yyjson pool when reentering orjson.loads

orjson.loads may allocate a Python object that triggers a garbage
collection that invokes a destructor that calls orjson.loads again.
Or the destructor may release the GIL so a different thread can call
orjson.loads.  To remain safe under such reentrancy, we need to avoid
reinitializing the yyjson pool while it might still be in use.  The
simplest fix is to initialize the yyjson pool only once, like we did
before commit e9b745e.

Fixes #415.

Signed-off-by: Anders Kaseorg <[email protected]>

src/deserialize/yyjson.rs

@@ -91,22 +91,11 @@ fn read_doc_default(data: &'static str, err: &mut yyjson_read_err) -> *mut yyjso
 
 fn read_doc_with_buffer(data: &'static str, err: &mut yyjson_read_err) -> *mut yyjson_doc {
     unsafe {
-        let mut allocator = crate::yyjson::yyjson_alc {
-            malloc: None,
-            realloc: None,
-            free: None,
-            ctx: null_mut(),
-        };
-        crate::yyjson::yyjson_alc_pool_init(
-            &mut allocator,
-            YYJSON_ALLOC.get_or_init(yyjson_init).as_ptr() as *mut std::os::raw::c_void,
-            YYJSON_BUFFER_SIZE,
-        );
         yyjson_read_opts(
             data.as_ptr() as *mut c_char,
             data.len(),
             YYJSON_READ_NOFLAG,
-            std::ptr::addr_of!(allocator),
+            &YYJSON_ALLOC.get_or_init(yyjson_init).alloc,
             err,
         )
     }

src/typeref.rs

@@ -6,7 +6,7 @@ use once_cell::race::{OnceBool, OnceBox};
 use pyo3_ffi::*;
 use std::cell::UnsafeCell;
 use std::mem::MaybeUninit;
-use std::os::raw::c_char;
+use std::os::raw::{c_char, c_void};
 use std::ptr::{null_mut, NonNull};
 
 pub struct NumpyTypes {
@@ -94,28 +94,41 @@ pub const YYJSON_BUFFER_SIZE: usize = 1024 * 1024 * 8;
 
 #[cfg(feature = "yyjson")]
 #[repr(align(64))]
-pub struct YYJSONBuffer(UnsafeCell<MaybeUninit<[u8; YYJSON_BUFFER_SIZE]>>);
+struct YYJSONBuffer(UnsafeCell<MaybeUninit<[u8; YYJSON_BUFFER_SIZE]>>);
 
 #[cfg(feature = "yyjson")]
-impl YYJSONBuffer {
-    pub(crate) fn as_ptr(&self) -> *mut u8 {
-        self.0.get().cast::<u8>()
-    }
+pub struct YYJSONAlloc {
+    pub alloc: crate::yyjson::yyjson_alc,
+    _buffer: Box<YYJSONBuffer>,
 }
 
 #[cfg(feature = "yyjson")]
-pub static mut YYJSON_ALLOC: OnceBox<YYJSONBuffer> = OnceBox::new();
+pub static mut YYJSON_ALLOC: OnceBox<YYJSONAlloc> = OnceBox::new();
 
 #[cfg(feature = "yyjson")]
-pub fn yyjson_init() -> Box<YYJSONBuffer> {
+pub fn yyjson_init() -> Box<YYJSONAlloc> {
     // Using unsafe to ensure allocation happens on the heap without going through the stack
     // so we don't stack overflow in debug mode. Once rust-lang/rust#63291 is stable (Box::new_uninit)
     // we can use that instead.
     let layout = std::alloc::Layout::new::<YYJSONBuffer>();
+    let buffer = unsafe { Box::from_raw(std::alloc::alloc(layout).cast::<YYJSONBuffer>()) };
+    let mut alloc = crate::yyjson::yyjson_alc {
+        malloc: None,
+        realloc: None,
+        free: None,
+        ctx: null_mut(),
+    };
     unsafe {
-        let buffer = std::alloc::alloc(layout);
-        Box::from_raw(buffer.cast::<YYJSONBuffer>())
+        crate::yyjson::yyjson_alc_pool_init(
+            &mut alloc,
+            buffer.0.get().cast::<c_void>(),
+            YYJSON_BUFFER_SIZE,
+        );
     }
+    Box::new(YYJSONAlloc {
+        alloc,
+        _buffer: buffer,
+    })
 }
 
 #[allow(non_upper_case_globals)]

test/test_reentrant.py

@@ -0,0 +1,16 @@
+import orjson
+
+
+class C:
+    c: "C"
+
+    def __del__(self):
+        orjson.loads('"' + "a" * 10000 + '"')
+
+
+def test_reentrant():
+    c = C()
+    c.c = c
+    del c
+
+    orjson.loads("[" + "[]," * 1000 + "[]]")