Searched hist:"1 acf256d96ab7ec881c40f4eeeef2e064c7e7d20" (Results 1 – 4 of 4) sorted by relevance
| /freebsd/sys/amd64/amd64/ |
| H A D | sys_machdep.c | diff 1acf256d96ab7ec881c40f4eeeef2e064c7e7d20 Wed May 30 16:35:22 CEST 2001 John Baldwin <jhb@FreeBSD.org> We can't grab the sched_lock in set_user_ldt() because when it is called
from cpu_switch(), curproc has been changed, but the sched_lock owner will
not be updated until we return to mi_switch(), thus we deadlock against
ourselves. As a workaround, push the acquire and release of sched_lock out
to the callers of set_user_ldt(). Note that we can't use a mtx_assert() in
set_user_ldt for the same reason.
Sleuting by: tmm
Tested by: tmm, dougb
diff 1acf256d96ab7ec881c40f4eeeef2e064c7e7d20 Wed May 30 16:35:22 CEST 2001 John Baldwin <jhb@FreeBSD.org> We can't grab the sched_lock in set_user_ldt() because when it is called
from cpu_switch(), curproc has been changed, but the sched_lock owner will
not be updated until we return to mi_switch(), thus we deadlock against
ourselves. As a workaround, push the acquire and release of sched_lock out
to the callers of set_user_ldt(). Note that we can't use a mtx_assert() in
set_user_ldt for the same reason.
Sleuting by: tmm
Tested by: tmm, dougb
|
| H A D | vm_machdep.c | diff 1acf256d96ab7ec881c40f4eeeef2e064c7e7d20 Wed May 30 16:35:22 CEST 2001 John Baldwin <jhb@FreeBSD.org> We can't grab the sched_lock in set_user_ldt() because when it is called
from cpu_switch(), curproc has been changed, but the sched_lock owner will
not be updated until we return to mi_switch(), thus we deadlock against
ourselves. As a workaround, push the acquire and release of sched_lock out
to the callers of set_user_ldt(). Note that we can't use a mtx_assert() in
set_user_ldt for the same reason.
Sleuting by: tmm
Tested by: tmm, dougb
diff 1acf256d96ab7ec881c40f4eeeef2e064c7e7d20 Wed May 30 16:35:22 CEST 2001 John Baldwin <jhb@FreeBSD.org> We can't grab the sched_lock in set_user_ldt() because when it is called
from cpu_switch(), curproc has been changed, but the sched_lock owner will
not be updated until we return to mi_switch(), thus we deadlock against
ourselves. As a workaround, push the acquire and release of sched_lock out
to the callers of set_user_ldt(). Note that we can't use a mtx_assert() in
set_user_ldt for the same reason.
Sleuting by: tmm
Tested by: tmm, dougb
|
| /freebsd/sys/i386/i386/ |
| H A D | sys_machdep.c | diff 1acf256d96ab7ec881c40f4eeeef2e064c7e7d20 Wed May 30 16:35:22 CEST 2001 John Baldwin <jhb@FreeBSD.org> We can't grab the sched_lock in set_user_ldt() because when it is called
from cpu_switch(), curproc has been changed, but the sched_lock owner will
not be updated until we return to mi_switch(), thus we deadlock against
ourselves. As a workaround, push the acquire and release of sched_lock out
to the callers of set_user_ldt(). Note that we can't use a mtx_assert() in
set_user_ldt for the same reason.
Sleuting by: tmm
Tested by: tmm, dougb
diff 1acf256d96ab7ec881c40f4eeeef2e064c7e7d20 Wed May 30 16:35:22 CEST 2001 John Baldwin <jhb@FreeBSD.org> We can't grab the sched_lock in set_user_ldt() because when it is called
from cpu_switch(), curproc has been changed, but the sched_lock owner will
not be updated until we return to mi_switch(), thus we deadlock against
ourselves. As a workaround, push the acquire and release of sched_lock out
to the callers of set_user_ldt(). Note that we can't use a mtx_assert() in
set_user_ldt for the same reason.
Sleuting by: tmm
Tested by: tmm, dougb
|
| H A D | vm_machdep.c | diff 1acf256d96ab7ec881c40f4eeeef2e064c7e7d20 Wed May 30 16:35:22 CEST 2001 John Baldwin <jhb@FreeBSD.org> We can't grab the sched_lock in set_user_ldt() because when it is called
from cpu_switch(), curproc has been changed, but the sched_lock owner will
not be updated until we return to mi_switch(), thus we deadlock against
ourselves. As a workaround, push the acquire and release of sched_lock out
to the callers of set_user_ldt(). Note that we can't use a mtx_assert() in
set_user_ldt for the same reason.
Sleuting by: tmm
Tested by: tmm, dougb
diff 1acf256d96ab7ec881c40f4eeeef2e064c7e7d20 Wed May 30 16:35:22 CEST 2001 John Baldwin <jhb@FreeBSD.org> We can't grab the sched_lock in set_user_ldt() because when it is called
from cpu_switch(), curproc has been changed, but the sched_lock owner will
not be updated until we return to mi_switch(), thus we deadlock against
ourselves. As a workaround, push the acquire and release of sched_lock out
to the callers of set_user_ldt(). Note that we can't use a mtx_assert() in
set_user_ldt for the same reason.
Sleuting by: tmm
Tested by: tmm, dougb
|