mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git
synced 2026-05-16 09:02:21 -04:00
8bf0cb97ed
On PREEMPT_RT kernels, vfree() can sleep because spin_lock is converted to rt_mutex. dml2_destroy() calls vfree() while inside an FPU-guarded region (preempt_count=2), which is illegal. dml2_wrapper_fpu.c is compiled with CC_FLAGS_FPU which defines _LINUX_FPU_COMPILATION_UNIT, making DC_RUN_WITH_PREEMPTION_ENABLED() resolve to a no-op. This prevents the macro from cycling FPU context off/on around vfree(). Move dml2_destroy() to dml2_wrapper.c (non-FPU compilation unit) where DC_RUN_WITH_PREEMPTION_ENABLED() properly cycles DC_FP_END/ DC_FP_START around vfree(). This pairs it with dml2_allocate_memory() which already lives there. Reviewed-by: Dillon Varone <dillon.varone@amd.com> Signed-off-by: Rafal Ostrowski <rafal.ostrowski@amd.com> Signed-off-by: Chenyu Chen <chen-yu.chen@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>