diff options
Diffstat (limited to 'sysdeps/x86')
| -rw-r--r-- | sysdeps/x86/cpu-features.c | 11 | ||||
| -rw-r--r-- | sysdeps/x86/sysdep.h | 60 |
2 files changed, 60 insertions, 11 deletions
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); } } diff --git a/sysdeps/x86/sysdep.h b/sysdeps/x86/sysdep.h index db8e576e91..7359149e17 100644 --- a/sysdeps/x86/sysdep.h +++ b/sysdeps/x86/sysdep.h @@ -38,14 +38,59 @@ #ifdef __x86_64__ /* Offset for fxsave/xsave area used by _dl_runtime_resolve. Also need space to preserve RCX, RDX, RSI, RDI, R8, R9 and RAX. It must be - aligned to 16 bytes for fxsave and 64 bytes for xsave. - - NB: Is is non-zero because of the 128-byte red-zone. Some registers - are saved on stack without adjusting stack pointer first. When we - update stack pointer to allocate more space, we need to take the - red-zone into account. */ + aligned to 16 bytes for fxsave and 64 bytes for xsave. It is non-zero + because MOV, instead of PUSH, is used to save registers onto stack. + + +==================+<- stack frame start aligned at 8 or 16 bytes + | |<- 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 + | |<- R9 + | |<- R8 + | |<- RDI + | |<- RSI + | |<- RDX + | |<- RCX + | |<- RAX + +==================+<- RSP aligned at 64 bytes + + */ # define STATE_SAVE_OFFSET (8 * 7 + 8) +/* _dl_tlsdesc_dynamic preserves RDI, RSI and RBX before realigning + stack. After realigning stack, it saves RCX, RDX, R8, R9, R10 and + R11. Allocate space for RDI, RSI and RBX to avoid clobbering saved + RDI, RSI and RBX values on stack by xsave. + + +==================+<- 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 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. */ +# define TLSDESC_CALL_REGISTER_SAVE_AREA (STATE_SAVE_OFFSET + 24) + /* Save SSE, AVX, AVX512, mask, bound and APX registers. Bound and APX registers are mutually exclusive. */ # define STATE_SAVE_MASK \ @@ -66,8 +111,9 @@ (STATE_SAVE_MASK | AMX_STATE_SAVE_MASK) #else /* Offset for fxsave/xsave area used by _dl_tlsdesc_dynamic. Since i386 - doesn't have red-zone, use 0 here. */ + uses PUSH to save registers onto stack, use 0 here. */ # define STATE_SAVE_OFFSET 0 +# define TLSDESC_CALL_REGISTER_SAVE_AREA 0 /* Save SSE, AVX, AXV512, mask and bound registers. */ # define STATE_SAVE_MASK \ |