CodeQL / Analyze (actions) (push) Canceled after 0s
CodeQL / Analyze (python) (push) Canceled after 0s
pre-commit / pre-commit (push) Canceled after 0s
Multi-Arch CI / setup (push) Canceled after 0s
Publish build_manylinux_x86_64 images / publish_build_manylinux_x86_64 (push) Canceled after 0s
Setup (Multi-Arch) / setup (push) Canceled after 0s
Multi-Arch CI / Linux::${{ fromJSON(needs.setup.outputs.linux_build_config || '{}').build_variant_label || 'skip' }} (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Publish no_rocm_image_ubi10 image / publish_no_rocm_image_ubi10 (push) Canceled after 0s
Multi-Arch CI / Windows::${{ fromJSON(needs.setup.outputs.windows_build_config || '{}').build_variant_label || 'skip' }} (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Multi-Arch CI / Manifest Diff (push) Canceled after 0s
TheRock Manifest Diff Report / Generate Manifest Diff Report (push) Canceled after 0s
Multi-Arch CI / CI Summary (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04 (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04_ocl_rt images / publish_no_rocm_image_ubuntu24_04_ocl_rt (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_rocgdb (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04_rocgdb images / publish_no_rocm_image_ubuntu24_04_rocgdb (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_ocl_rt (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Unit Tests / Unit Tests :: ubuntu-24.04 (push) Canceled after 0s
Unit Tests / Unit Tests :: windows-2022 (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_media (push) Canceled after 0s
Unit Tests / Unit Tests Summary (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_openmpi (push) Canceled after 0s
174 lines
4.9 KiB
ArmAsm
174 lines
4.9 KiB
ArmAsm
#include "../builtins/assembly.h"
|
|
#include "../sanitizer_common/sanitizer_asm.h"
|
|
|
|
.macro SAVE_REGISTERS
|
|
stp x1, x2, [sp, #-16]!
|
|
stp x3, x4, [sp, #-16]!
|
|
stp x5, x6, [sp, #-16]!
|
|
stp x7, x30, [sp, #-16]!
|
|
stp q0, q1, [sp, #-32]!
|
|
stp q2, q3, [sp, #-32]!
|
|
stp q4, q5, [sp, #-32]!
|
|
stp q6, q7, [sp, #-32]!
|
|
// x8 is the indirect result register and needs to be preserved for the body of the function to use.
|
|
stp x8, x0, [sp, #-16]!
|
|
.endm
|
|
|
|
.macro RESTORE_REGISTERS
|
|
ldp x8, x0, [sp], #16
|
|
ldp q6, q7, [sp], #32
|
|
ldp q4, q5, [sp], #32
|
|
ldp q2, q3, [sp], #32
|
|
ldp q0, q1, [sp], #32
|
|
ldp x7, x30, [sp], #16
|
|
ldp x5, x6, [sp], #16
|
|
ldp x3, x4, [sp], #16
|
|
ldp x1, x2, [sp], #16
|
|
.endm
|
|
|
|
.macro LOAD_HANDLER_ADDR reg handler
|
|
#if !defined(XRAY_PIC)
|
|
adrp \reg, ASM_SYMBOL(\handler)
|
|
ldr \reg, [\reg, :lo12:ASM_SYMBOL(\handler)]
|
|
#else
|
|
adrp \reg, :got:ASM_SYMBOL(\handler)
|
|
ldr \reg, [\reg, :got_lo12:ASM_SYMBOL(\handler)]
|
|
ldr \reg, [\reg]
|
|
#endif
|
|
.endm
|
|
|
|
TEXT_SECTION
|
|
.p2align 2
|
|
.global ASM_SYMBOL(__xray_FunctionEntry)
|
|
ASM_HIDDEN(__xray_FunctionEntry)
|
|
ASM_TYPE_FUNCTION(__xray_FunctionEntry)
|
|
ASM_SYMBOL(__xray_FunctionEntry):
|
|
/* Move the return address beyond the end of sled data. The 12 bytes of
|
|
data are inserted in the code of the runtime patch, between the call
|
|
instruction and the instruction returned into. The data contains 32
|
|
bits of instrumented function ID and 64 bits of the address of
|
|
the current trampoline. */
|
|
add x30, x30, #12
|
|
// Push the registers which may be modified by the handler function.
|
|
SAVE_REGISTERS
|
|
|
|
// Load the handler function pointer.
|
|
LOAD_HANDLER_ADDR x2, _ZN6__xray19XRayPatchedFunctionE
|
|
cbz x2, 1f
|
|
// Set w0 to the function ID (w17). Set x1 to XRayEntryType::ENTRY = 0.
|
|
mov w0, w17
|
|
mov x1, #0
|
|
// Call the handler with 2 parameters.
|
|
blr x2
|
|
1:
|
|
RESTORE_REGISTERS
|
|
ret
|
|
ASM_SIZE(__xray_FunctionEntry)
|
|
|
|
.p2align 2
|
|
.global ASM_SYMBOL(__xray_FunctionExit)
|
|
ASM_HIDDEN(__xray_FunctionExit)
|
|
ASM_TYPE_FUNCTION(__xray_FunctionExit)
|
|
ASM_SYMBOL(__xray_FunctionExit):
|
|
/* Move the return address beyond the end of sled data. The 12 bytes of
|
|
data are inserted in the code of the runtime patch, between the call
|
|
instruction and the instruction returned into. The data contains 32
|
|
bits of instrumented function ID and 64 bits of the address of
|
|
the current trampoline. */
|
|
add x30, x30, #12
|
|
SAVE_REGISTERS
|
|
|
|
// Load the handler function pointer into x2.
|
|
LOAD_HANDLER_ADDR x2, _ZN6__xray19XRayPatchedFunctionE
|
|
cbz x2, 1f
|
|
// Set w0 to the function ID (w17). Set x1 to XRayEntryType::EXIT = 1.
|
|
mov w0, w17
|
|
mov x1, #1
|
|
// Call the handler with 2 parameters.
|
|
blr x2
|
|
1:
|
|
RESTORE_REGISTERS
|
|
ret
|
|
ASM_SIZE(__xray_FunctionExit)
|
|
|
|
.p2align 2
|
|
.global ASM_SYMBOL(__xray_FunctionTailExit)
|
|
ASM_HIDDEN(__xray_FunctionTailExit)
|
|
ASM_TYPE_FUNCTION(__xray_FunctionTailExit)
|
|
ASM_SYMBOL(__xray_FunctionTailExit):
|
|
/* Move the return address beyond the end of sled data. The 12 bytes of
|
|
data are inserted in the code of the runtime patch, between the call
|
|
instruction and the instruction returned into. The data contains 32
|
|
bits of instrumented function ID and 64 bits of the address of
|
|
the current trampoline. */
|
|
add x30, x30, #12
|
|
// Save the registers which may be modified by the handler function.
|
|
SAVE_REGISTERS
|
|
// Load the handler function pointer into x2.
|
|
LOAD_HANDLER_ADDR x2, _ZN6__xray19XRayPatchedFunctionE
|
|
cbz x2, 1f
|
|
// Set w0 to the function ID (w17). Set x1 to XRayEntryType::TAIL = 2.
|
|
mov w0, w17
|
|
mov x1, #2
|
|
// Call the handler with 2 parameters.
|
|
blr x2
|
|
1:
|
|
RESTORE_REGISTERS
|
|
ret
|
|
ASM_SIZE(__xray_FunctionTailExit)
|
|
|
|
.p2align 2
|
|
.global ASM_SYMBOL(__xray_ArgLoggerEntry)
|
|
ASM_HIDDEN(__xray_ArgLoggerEntry)
|
|
ASM_TYPE_FUNCTION(__xray_ArgLoggerEntry)
|
|
ASM_SYMBOL(__xray_ArgLoggerEntry):
|
|
add x30, x30, #12
|
|
// Push the registers which may be modified by the handler function.
|
|
SAVE_REGISTERS
|
|
|
|
LOAD_HANDLER_ADDR x8, _ZN6__xray13XRayArgLoggerE
|
|
cbnz x8, 2f
|
|
|
|
// Load the handler function pointer.
|
|
LOAD_HANDLER_ADDR x8, _ZN6__xray19XRayPatchedFunctionE
|
|
cbz x8, 1f
|
|
|
|
2:
|
|
mov x2, x0
|
|
mov x1, #3 // XRayEntryType::LOG_ARGS_ENTRY
|
|
mov w0, w17
|
|
blr x8
|
|
|
|
1:
|
|
RESTORE_REGISTERS
|
|
ret
|
|
ASM_SIZE(__xray_ArgLoggerEntry)
|
|
|
|
// __xray_*Event have default visibility so that they can be referenced by user
|
|
// DSOs that do not link against the runtime.
|
|
.global ASM_SYMBOL(__xray_CustomEvent)
|
|
ASM_TYPE_FUNCTION(__xray_CustomEvent)
|
|
ASM_SYMBOL(__xray_CustomEvent):
|
|
SAVE_REGISTERS
|
|
LOAD_HANDLER_ADDR x8, _ZN6__xray22XRayPatchedCustomEventE
|
|
cbz x8, 1f
|
|
blr x8
|
|
1:
|
|
RESTORE_REGISTERS
|
|
ret
|
|
ASM_SIZE(__xray_CustomEvent)
|
|
|
|
.global ASM_SYMBOL(__xray_TypedEvent)
|
|
ASM_TYPE_FUNCTION(__xray_TypedEvent)
|
|
ASM_SYMBOL(__xray_TypedEvent):
|
|
SAVE_REGISTERS
|
|
LOAD_HANDLER_ADDR x8, _ZN6__xray21XRayPatchedTypedEventE
|
|
cbz x8, 1f
|
|
blr x8
|
|
1:
|
|
RESTORE_REGISTERS
|
|
ret
|
|
ASM_SIZE(__xray_TypedEvent)
|
|
|
|
NO_EXEC_STACK_DIRECTIVE
|