8000 gh-128137: Update PyASCIIObject to handle interned field with the atomic operation by corona10 · Pull Request #128196 · python/cpython · GitHub
[go: up one dir, main page]
Skip to content

gh-128137: Update PyASCIIObject to handle interned field with the atomic operation #128196

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 19 commits into from
Jan 5, 2025
+18 −10
Merged

gh-128137: Update PyASCIIObject to handle interned field with the atomic operation #128196

Show file tree
Hide file tree
Changes from 1 commit
Commits
Show all changes
19 commits
Select commit Hold shift + click to select a range
45536d0
gh-128137: Split out interned field from state
corona10 Dec 23, 2024
f30b355
Address code review
corona10 Dec 23, 2024
18a8e6b
Maintain unused size as 24 bits
corona10 Dec 23, 2024
5c659ef
Reserve unused bit as 18 bits
corona10 Dec 23, 2024
c803475
Address code review
corona10 Dec 23, 2024
2dfd450
nit
corona10 Dec 23, 2024
69ad224
nit
corona10 Dec 23, 2024
b1b396b
Add NEWS.d
corona10 Dec 23, 2024
4327a6d
Resize struct padding
corona10 Dec 24, 2024
d86e0af
Update for WASI
corona10 Dec 24, 2024
f5c4d96
fix
corona10 Dec 24, 2024
53147e7
Address code review
corona10 Jan 1, 2025
30c2eb2
Use unsigned short instead
corona10 Jan 1, 2025
7d4955c
Address code review
corona10 Jan 2, 2025
958d0d7
Revert "Address code review"
corona10 Jan 2, 2025
fbc9c52
Add extra padding
corona10 Jan 2, 2025
2eaf1cf
Increase interned to 16bits and adjust layout
corona10 Jan 2, 2025
4fa26a8
fix
corona10 Jan 2, 2025
91907aa
nit
corona10 Jan 2, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Prev Previous commit
Next Next commit
Address code review
  • Loading branch information
@corona10
corona10 committed Dec 23, 2024
commit f30b355474b116a4b0e60c01081194c07ae653ed
14 changes: 7 additions & 7 deletions Include/cpython/unicodeobject.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -108,7 +108,7 @@ typedef struct {
3: Interned, Immortal, and Static
This categorization allows the runtime to determine the right
cleanup mechanism at runtime shutdown. */
uint16_t interned;
uint8_t interned;
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I think this remain in the state struct. It's okay for a struct to contain both non-bitfield and bitfield members:

  • It avoids a potential unnecessary breakage from moving the field
  • Keeping it in state will make it easier to keep state 32-bits due to alignment.

struct {
/* Character size:

Expand All @@ -132,21 +132,21 @@ typedef struct {
* all characters are in the range U+0000-U+10FFFF
* at least one character is in the range U+10000-U+10FFFF
*/
uint16_t kind:3;
unsigned int kind:3;
/* Compact is with respect to the allocation scheme. Compact unicode
objects only require one memory block while non-compact objects use
one block for the PyUnicodeObject struct and another for its data
buffer. */
uint16_t compact:1;
unsigned int compact:1;
/* The string only contains characters in the range U+0000-U+007F (ASCII)
and the kind is PyUnicode_1BYTE_KIND. If ascii is set and compact is
set, use the PyASCIIObject structure. */
uint16_t ascii:1;
unsigned int ascii:1;
/* The object is statically allocated. */
uint16_t statically_allocated:1;
unsigned int statically_allocated:1;
/* Padding to ensure that PyUnicode_DATA() is always aligned to
4 bytes (see issue #19537 on m68k). */
uint16_t :10;
unsigned int :10;
} state;
} PyASCIIObject;

Expand Down Expand Up @@ -196,7 +196,7 @@ typedef struct {
/* Use only if you know it's a string */
static inline unsigned int PyUnicode_CHECK_INTERNED(PyObject *op) {
#ifdef Py_GIL_DISABLED
return _Py_atomic_load_uint16_relaxed(&(_PyASCIIObject_CAST(op)->interned));
return _Py_atomic_load_uint8_relaxed(&(_PyASCIIObject_CAST(op)->interned));
#else
return _PyASCIIObject_CAST(op)->interned;
#endif
Expand Down
6 changes: 3 additions & 3 deletions Objects/unicodeobject.c
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -15726,7 +15726,7 @@ immortalize_interned(PyObject *s)
_Py_DecRefTotal(_PyThreadState_GET());
}
#endif
FT_ATOMIC_STORE_UINT16_RELAXED(_PyASCIIObject_CAST(s)->interned, SSTATE_INTERNED_IMMORTAL);
FT_ATOMIC_STORE_UINT8_RELAXED(_PyASCIIObject_CAST(s)->interned, SSTATE_INTERNED_IMMORTAL);
_Py_SetImmortal(s);
}

Expand Down Expand Up @@ -15845,7 +15845,7 @@ intern_common(PyInterpreterState *interp, PyObject *s /* stolen */,
_Py_DecRefTotal(_PyThreadState_GET());
#endif
}
FT_ATOMIC_STORE_UINT16_RELAXED(_PyASCIIObject_CAST(s)->interned, SSTATE_INTERNED_MORTAL);
FT_ATOMIC_STORE_UINT8_RELAXED(_PyASCIIObject_CAST(s)->interned, SSTATE_INTERNED_MORTAL);

/* INTERNED_MORTAL -> INTERNED_IMMORTAL (if needed) */

Expand Down Expand Up @@ -15981,7 +15981,7 @@ _PyUnicode_ClearInterned(PyInterpreterState *interp)
Py_UNREACHABLE();
}
if (!shared) {
FT_ATOMIC_STORE_UINT16_RELAXED(_PyASCIIObject_CAST(s)->interned, SSTATE_NOT_INTERNED);
FT_ATOMIC_STORE_UINT8_RELAXED(_PyASCIIObject_CAST(s)->interned, SSTATE_NOT_INTERNED);
}
}
#ifdef INTERNED_STATS
Expand Down
Loading
0