From 717ebfa85c8240d32d0d19d86a484c31c55c9617 Mon Sep 17 00:00:00 2001 From: "H.J. Lu" Date: Mon, 18 Mar 2024 06:40:16 -0700 Subject: x86-64: Allocate state buffer space for RDI, RSI and RBX _dl_tlsdesc_dynamic preserves RDI, RSI and RBX before realigning stack. After realigning stack, it saves RCX, RDX, R8, R9, R10 and R11. Define TLSDESC_CALL_REGISTER_SAVE_AREA to allocate space for RDI, RSI and RBX to avoid clobbering saved RDI, RSI and RBX values on stack by xsave to STATE_SAVE_OFFSET(%rsp). +==================+<- stack frame start aligned at 8 or 16 bytes | |<- RDI saved in the red zone | |<- RSI saved in the red zone | |<- RBX saved in the red zone | |<- paddings for stack realignment of 64 bytes |------------------|<- xsave buffer end aligned at 64 bytes | |<- | |<- | |<- |------------------|<- xsave buffer start at STATE_SAVE_OFFSET(%rsp) | |<- 8-byte padding for 64-byte alignment | |<- 8-byte padding for 64-byte alignment | |<- R11 | |<- R10 | |<- R9 | |<- R8 | |<- RDX | |<- RCX +==================+<- RSP aligned at 64 bytes Define TLSDESC_CALL_REGISTER_SAVE_AREA, the total register save area size for all integer registers by adding 24 to STATE_SAVE_OFFSET since RDI, RSI and RBX are saved onto stack without adjusting stack pointer first, using the red-zone. This fixes BZ #31501. Reviewed-by: Sunil K Pandey --- sysdeps/x86/cpu-features.c | 11 +++++++---- 1 file changed, 7 insertions(+), 4 deletions(-) (limited to 'sysdeps/x86/cpu-features.c') diff --git a/sysdeps/x86/cpu-features.c b/sysdeps/x86/cpu-features.c index 4ea373dffa..3d7c2819d7 100644 --- a/sysdeps/x86/cpu-features.c +++ b/sysdeps/x86/cpu-features.c @@ -311,7 +311,7 @@ update_active (struct cpu_features *cpu_features) /* NB: On AMX capable processors, ebx always includes AMX states. */ unsigned int xsave_state_full_size - = ALIGN_UP (ebx + STATE_SAVE_OFFSET, 64); + = ALIGN_UP (ebx + TLSDESC_CALL_REGISTER_SAVE_AREA, 64); cpu_features->xsave_state_size = xsave_state_full_size; @@ -401,8 +401,10 @@ update_active (struct cpu_features *cpu_features) unsigned int amx_size = (xstate_amx_comp_offsets[31] + xstate_amx_comp_sizes[31]); - amx_size = ALIGN_UP (amx_size + STATE_SAVE_OFFSET, - 64); + amx_size + = ALIGN_UP ((amx_size + + TLSDESC_CALL_REGISTER_SAVE_AREA), + 64); /* Set xsave_state_full_size to the compact AMX state size for XSAVEC. NB: xsave_state_full_size is only used in _dl_tlsdesc_dynamic_xsave and @@ -410,7 +412,8 @@ update_active (struct cpu_features *cpu_features) cpu_features->xsave_state_full_size = amx_size; #endif cpu_features->xsave_state_size - = ALIGN_UP (size + STATE_SAVE_OFFSET, 64); + = ALIGN_UP (size + TLSDESC_CALL_REGISTER_SAVE_AREA, + 64); CPU_FEATURE_SET (cpu_features, XSAVEC); } } -- cgit 1.4.1