From f74059ffbcf53d8ff4db59ca9e7b07d58bd3e3c6 Mon Sep 17 00:00:00 2001 From: David McFarland Date: Fri, 4 Sep 2020 10:15:57 -0300 Subject: [PATCH] Cygwin: store tls pointer in win32 tls Use WIN32 TLS instead of stack-relative pointers for TLS. This allows windows fibers and boost coroutines to be used without crashing whenever a syscall is made from a fiber. NOTE: This should be submitted upstream, but there is a blocker first. In the main branch there are conflicts with new ARM64 support. In addition to fixing the conflicts, we should actually test whether ARM64 builds work too, first. --- winsup/cygwin/create_posix_thread.cc | 2 ++ winsup/cygwin/cygtls.cc | 15 +++++++++++++++ winsup/cygwin/dcrt0.cc | 1 + winsup/cygwin/fork.cc | 1 + winsup/cygwin/include/cygwin/config.h | 2 +- winsup/cygwin/init.cc | 12 ++++++++---- winsup/cygwin/local_includes/cygtls.h | 7 +++++-- winsup/cygwin/scripts/gendef | 15 ++++++++++----- 8 files changed, 43 insertions(+), 12 deletions(-) diff --git a/winsup/cygwin/create_posix_thread.cc b/winsup/cygwin/create_posix_thread.cc index 3fcd61707..85c1a8af3 100644 --- a/winsup/cygwin/create_posix_thread.cc +++ b/winsup/cygwin/create_posix_thread.cc @@ -52,6 +52,7 @@ pthread_wrapper (PVOID arg) /* Set stack values in TEB */ PTEB teb = NtCurrentTeb (); teb->Tib.StackBase = wrapper_arg.stackbase; + _set_tls(); teb->Tib.StackLimit = wrapper_arg.stacklimit ?: wrapper_arg.stackaddr; /* Set DeallocationStack value. If we have an application-provided stack, we set DeallocationStack to NULL, so NtTerminateThread does not deallocate @@ -250,6 +251,7 @@ create_new_main_thread_stack (PVOID &allocationbase) return NULL; NtCurrentTeb()->Tib.StackBase = ((PBYTE) allocationbase + stacksize); NtCurrentTeb()->Tib.StackLimit = stacklimit; + _set_tls(); return ((PBYTE) allocationbase + stacksize - 16); } diff --git a/winsup/cygwin/cygtls.cc b/winsup/cygwin/cygtls.cc index 13d133f47..d23f9b42a 100644 --- a/winsup/cygwin/cygtls.cc +++ b/winsup/cygwin/cygtls.cc @@ -17,6 +17,20 @@ details. */ #include "sigproc.h" #include "exception.h" +extern DWORD cygtls_slot; + +void _set_tls(TEB *teb) +{ + TlsSetValue(cygtls_slot, teb->Tib.StackBase); +} + +_cygtls* _current_tls() +{ + register void *ret; + __asm __volatile__ ("movl cygtls_slot(%%rip),%%r10d\nmovq %%gs:0x1480(,%%r10d,8),%0" : "=r" (ret) : : "r10"); + return (_cygtls *) ((PBYTE) ret - __CYGTLS_PADSIZE__); +} + /* Two calls to get the stack right... */ void _cygtls::call (DWORD (*func) (void *, void *), void *arg) @@ -25,6 +39,7 @@ _cygtls::call (DWORD (*func) (void *, void *), void *arg) /* Initialize this thread's ability to respond to things like SIGSEGV or SIGFPE. */ exception protect; + _set_tls(); _my_tls.call2 (func, arg, buf); } diff --git a/winsup/cygwin/dcrt0.cc b/winsup/cygwin/dcrt0.cc index f4c09befd..e6ba488f2 100644 --- a/winsup/cygwin/dcrt0.cc +++ b/winsup/cygwin/dcrt0.cc @@ -462,6 +462,7 @@ child_info_fork::alloc_stack () StackBase in the child to be the same as in the parent, so that the computation of _my_tls is correct. */ teb->Tib.StackBase = (PVOID) stackbase; + _set_tls(teb); } } diff --git a/winsup/cygwin/fork.cc b/winsup/cygwin/fork.cc index f88acdbbf..582f1a454 100644 --- a/winsup/cygwin/fork.cc +++ b/winsup/cygwin/fork.cc @@ -141,6 +141,7 @@ frok::child (volatile char * volatile here) myself->pid, myself->ppid, __builtin_frame_address (0)); sigproc_printf ("hParent %p, load_dlls %d", hParent, load_dlls); + _set_tls(); /* Make sure threadinfo information is properly set up. */ if (&_my_tls != _main_tls) { diff --git a/winsup/cygwin/include/cygwin/config.h b/winsup/cygwin/include/cygwin/config.h index 2a7083278..21ce484cf 100644 --- a/winsup/cygwin/include/cygwin/config.h +++ b/winsup/cygwin/include/cygwin/config.h @@ -37,7 +37,7 @@ extern inline struct _reent *__getreent (void) { register char *ret; #ifdef __x86_64__ - __asm __volatile__ ("movq %%gs:8,%0" : "=r" (ret)); + __asm __volatile__ ("movl cygtls_slot(%%rip),%%r10d\nmovq %%gs:0x1480(,%%r10d,8),%0" : "=r" (ret) : : "r10"); #else #error unimplemented for this target #endif diff --git a/winsup/cygwin/init.cc b/winsup/cygwin/init.cc index ce6484aff..392ac8600 100644 --- a/winsup/cygwin/init.cc +++ b/winsup/cygwin/init.cc @@ -11,7 +11,7 @@ details. */ #include "ntdll.h" #include "shared_info.h" -static DWORD _my_oldfunc; +DWORD NO_COPY cygtls_slot; static char *search_for = (char *) cygthread::stub; unsigned threadfunc_ix[8]; @@ -22,7 +22,9 @@ static bool dll_finished_loading; static void threadfunc_fe (VOID *arg) { - _cygtls::call ((DWORD (*) (void *, void *)) TlsGetValue (_my_oldfunc), arg); + PVOID f = TlsGetValue (cygtls_slot); + _set_tls(); + _cygtls::call ((DWORD (*) (void *, void *)) f, arg); } /* If possible, redirect the thread entry point to a cygwin routine which @@ -59,7 +61,7 @@ munge_threadfunc () for (i = 0; threadfunc_ix[i]; i++) if (!threadfunc || ebp[threadfunc_ix[i]] == threadfunc) ebp[threadfunc_ix[i]] = (char *) threadfunc_fe; - TlsSetValue (_my_oldfunc, threadfunc); + TlsSetValue (cygtls_slot, threadfunc); } } } @@ -78,6 +80,8 @@ dll_entry (HANDLE h, DWORD reason, void *static_load) switch (reason) { case DLL_PROCESS_ATTACH: + cygtls_slot = TlsAlloc (); + _set_tls(); init_console_handler (false); cygwin_hmodule = (HMODULE) h; @@ -94,7 +98,6 @@ dll_entry (HANDLE h, DWORD reason, void *static_load) memcpy (_REENT, _GLOBAL_REENT, sizeof (struct _reent)); dll_crt0_0 (); - _my_oldfunc = TlsAlloc (); dll_finished_loading = true; break; case DLL_PROCESS_DETACH: @@ -102,6 +105,7 @@ dll_entry (HANDLE h, DWORD reason, void *static_load) shared_destroy (); break; case DLL_THREAD_ATTACH: + _set_tls(); if (dll_finished_loading) munge_threadfunc (); break; diff --git a/winsup/cygwin/local_includes/cygtls.h b/winsup/cygwin/local_includes/cygtls.h index 306497a33..e3a216280 100644 --- a/winsup/cygwin/local_includes/cygtls.h +++ b/winsup/cygwin/local_includes/cygtls.h @@ -301,8 +301,11 @@ private: #include "cygerrno.h" #include "ntdll.h" -#define _my_tls (*((_cygtls *) ((PBYTE) NtCurrentTeb()->Tib.StackBase \ - - __CYGTLS_PADSIZE__))) +void _set_tls(TEB*); +inline void _set_tls() { _set_tls(NtCurrentTeb()); } +_cygtls* _current_tls(); + +#define _my_tls (*_current_tls()) extern _cygtls *_main_tls; extern _cygtls *_sig_tls; diff --git a/winsup/cygwin/scripts/gendef b/winsup/cygwin/scripts/gendef index 861a2405b..9a4479bd8 100755 --- a/winsup/cygwin/scripts/gendef +++ b/winsup/cygwin/scripts/gendef @@ -118,7 +118,8 @@ EOF .seh_proc _sigfe_maybe _sigfe_maybe: # stack is aligned on entry! .seh_endprologue - movq %gs:8,%r10 # location of bottom of stack + movl cygtls_slot(%rip),%r10d + movq %gs:0x1480(,%r10d,8),%r10 # location of bottom of stack leaq _cygtls.initialized(%r10),%r11 # where we will be looking cmpq %r11,%rsp # stack loc > than tls jge 0f # yep. we don't have a tls. @@ -131,7 +132,8 @@ _sigfe_maybe: # stack is aligned on entry! .seh_proc _sigfe _sigfe: # stack is aligned on entry! .seh_endprologue - movq %gs:8,%r10 # location of bottom of stack + movl cygtls_slot(%rip),%r10d + movq %gs:0x1480(,%r10d,8),%r10 # location of bottom of stack 1: movl \$1,%r11d xchgl %r11d,_cygtls.stacklock(%r10) # try to acquire lock testl %r11d,%r11d # it will be zero @@ -154,7 +156,8 @@ _sigfe: # stack is aligned on entry! _sigbe: # return here after cygwin syscall # stack is aligned on entry! .seh_endprologue - movq %gs:8,%r10 # address of bottom of tls + movl cygtls_slot(%rip),%r10d + movq %gs:0x1480(,%r10d,8),%r10 # address of bottom of tls 1: movl \$1,%r11d xchgl %r11d,_cygtls.stacklock(%r10) # try to acquire lock testl %r11d,%r11d # it will be zero @@ -249,7 +252,8 @@ sigdelayed: 2: .seh_endprologue - movq %gs:8,%r12 # get tls + movl cygtls_slot(%rip),%r12d + movq %gs:0x1480(,%r12d,8),%r12 # get tls movl _cygtls.saved_errno(%r12),%r15d # temporarily save saved_errno movq \$_cygtls.start_offset,%rcx # point to beginning of tls block addq %r12,%rcx # and store as first arg to method @@ -316,7 +320,8 @@ stabilize_sig_stack: subq \$0x20,%rsp .seh_stackalloc 32 .seh_endprologue - movq %gs:8,%r12 + movl cygtls_slot(%rip),%r12d + movq %gs:0x1480(,%r12d,8),%r12 1: movl \$1,%r10d xchgl %r10d,_cygtls.stacklock(%r12) # try to acquire lock testl %r10d,%r10d -- 2.50.1