Thanks to visit codestin.com
Credit goes to github.com

Skip to content

gh-96143: Clear instruction cache after mprotect call #96476

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 3 commits into from
Sep 8, 2022
Merged

gh-96143: Clear instruction cache after mprotect call #96476

Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
e000d0e
gh-96143: Clear instruction cache after mprotect call
pablogsal Sep 1, 2022
33e10bf
Add a bunch of macros
pablogsal Sep 1, 2022
fefcef3
Update Objects/perf_trampoline.c
pablogsal Sep 2, 2022
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
27 changes: 23 additions & 4 deletions Objects/perf_trampoline.c
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -149,6 +149,22 @@ typedef enum {
#include <sys/types.h>
#include <unistd.h>

#if defined(__arm__) || defined(__arm64__) || defined(__aarch64__)
#define PY_HAVE_INVALIDATE_ICACHE

#if defined(__clang__) || defined(__GNUC__)
extern void __clear_cache(void *, void*);
#endif

static void invalidate_icache(char* begin, char*end) {
#if defined(__clang__) || defined(__GNUC__)
return __clear_cache(begin, end);
#else
return;
#endif
}
#endif

/* The function pointer is passed as last argument. The other three arguments
* are passed in the same order as the function requires. This results in
* shorter, more efficient ASM code for trampoline.
Expand Down Expand Up @@ -185,6 +201,7 @@ struct trampoline_api_st {

typedef struct trampoline_api_st trampoline_api_t;


static perf_status_t perf_status = PERF_STATUS_NO_INIT;
static Py_ssize_t extra_code_index = -1;
static code_arena_t *code_arena;
Expand Down Expand Up @@ -297,10 +314,6 @@ new_code_arena(void)
memcpy(memory + i * code_size, start, code_size * sizeof(char));
}
// Some systems may prevent us from creating executable code on the fly.
// TODO: Call icache invalidation intrinsics if available:
// __builtin___clear_cache/__clear_cache (depending if clang/gcc). This is
// technically not necessary but we could be missing something so better be
// safe.
int res = mprotect(memory, mem_size, PROT_READ | PROT_EXEC);
if (res == -1) {
PyErr_SetFromErrno(PyExc_OSError);
Expand All @@ -311,6 +324,12 @@ new_code_arena(void)
return -1;
}

#ifdef PY_HAVE_INVALIDATE_ICACHE
// Before the JIT can run a block of code that has been emitted it must invalidate
// the instruction cache on some platforms like arm and aarch64.
invalidate_icache(memory, memory + mem_size);
#endif

code_arena_t *new_arena = PyMem_RawCalloc(1, sizeof(code_arena_t));
if (new_arena == NULL) {
PyErr_NoMemory();
Expand Down