b24bad34bf
We try to avoid using cpu_loop_exit_atomic as it brings in an all-core
sync point. However on some cpu/kernel/benchmark combinations it is
starting to show up in the performance profile. To make it easier to
see whats going on add tracepoints for the slow path so we can see
what is triggering the wait.
It seems for a modern CPU it can be quite a bit, for example:
./qemu-system-aarch64 \
-machine type=virt,virtualization=on,pflash0=rom,pflash1=efivars,gic-version=max \
-smp 4 \
-accel tcg \
-device virtio-net-pci,netdev=unet \
-device virtio-scsi-pci \
-device scsi-hd,drive=hd \
-netdev user,id=unet,hostfwd=tcp::2222-:22 \
-blockdev driver=raw,node-name=hd,file.driver=host_device,file.filename=/dev/zen-ssd2/trixie-arm64,discard=unmap \
-serial mon:stdio \
-blockdev node-name=rom,driver=file,filename=(pwd)/pc-bios/edk2-aarch64-code.fd,read-only=true \
-blockdev node-name=efivars,driver=file,filename=$HOME/images/qemu-arm64-efivars \
-m 8192 \
-object memory-backend-memfd,id=mem,size=8G,share=on \
-kernel /home/alex/lsrc/linux.git/builds/arm64/arch/arm64/boot/Image -append "root=/dev/sda2 console=ttyAMA0 systemd.unit=benchmark-stress-ng.service" \
-display none -d trace:load_atom\*_fallback,trace:store_atom\*_fallback
With:
-cpu neoverse-v1,pauth-impdef=on => 2203343
With:
-cpu cortex-a76 => 0
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Reviewed-by: Pierrick Bouvier <pierrick.bouvier@linaro.org>
Signed-off-by: Alex Bennée <alex.bennee@linaro.org>
Message-Id: <20241023113406.1284676-9-alex.bennee@linaro.org>
27 lines
1.4 KiB
Plaintext
27 lines
1.4 KiB
Plaintext
# See docs/devel/tracing.rst for syntax documentation.
|
|
|
|
# TCG related tracing
|
|
# cpu-exec.c
|
|
exec_tb(void *tb, uintptr_t pc) "tb:%p pc=0x%"PRIxPTR
|
|
exec_tb_nocache(void *tb, uintptr_t pc) "tb:%p pc=0x%"PRIxPTR
|
|
exec_tb_exit(void *last_tb, unsigned int flags) "tb:%p flags=0x%x"
|
|
|
|
# cputlb.c
|
|
memory_notdirty_write_access(uint64_t vaddr, uint64_t ram_addr, unsigned size) "0x%" PRIx64 " ram_addr 0x%" PRIx64 " size %u"
|
|
memory_notdirty_set_dirty(uint64_t vaddr) "0x%" PRIx64
|
|
|
|
# translate-all.c
|
|
translate_block(void *tb, uintptr_t pc, const void *tb_code) "tb:%p, pc:0x%"PRIxPTR", tb_code:%p"
|
|
|
|
# ldst_atomicity
|
|
load_atom2_fallback(uint32_t memop, uintptr_t ra) "mop:0x%"PRIx32", ra:0x%"PRIxPTR""
|
|
load_atom4_fallback(uint32_t memop, uintptr_t ra) "mop:0x%"PRIx32", ra:0x%"PRIxPTR""
|
|
load_atom8_or_exit_fallback(uintptr_t ra) "ra:0x%"PRIxPTR""
|
|
load_atom8_fallback(uint32_t memop, uintptr_t ra) "mop:0x%"PRIx32", ra:0x%"PRIxPTR""
|
|
load_atom16_fallback(uint32_t memop, uintptr_t ra) "mop:0x%"PRIx32", ra:0x%"PRIxPTR""
|
|
load_atom16_or_exit_fallback(uintptr_t ra) "ra:0x%"PRIxPTR""
|
|
store_atom2_fallback(uint32_t memop, uintptr_t ra) "mop:0x%"PRIx32", ra:0x%"PRIxPTR""
|
|
store_atom4_fallback(uint32_t memop, uintptr_t ra) "mop:0x%"PRIx32", ra:0x%"PRIxPTR""
|
|
store_atom8_fallback(uint32_t memop, uintptr_t ra) "mop:0x%"PRIx32", ra:0x%"PRIxPTR""
|
|
store_atom16_fallback(uint32_t memop, uintptr_t ra) "mop:0x%"PRIx32", ra:0x%"PRIxPTR""
|