Currently, x86, Riscv, Loongarch use the Generic Entry which makes
maintainers' work easier and codes more elegant. arm64 has already
successfully switched to the Generic IRQ Entry in commit
b3cf07851b6c ("arm64: entry: Switch to generic IRQ entry"), it is
time to completely convert arm64 to Generic Entry.
The goal is to bring arm64 in line with other architectures that already
use the generic entry infrastructure, reducing duplicated code and
making it easier to share future changes in entry/exit paths, such as
"Syscall User Dispatch" and RSEQ optimizations.
This patch set is rebased on v7.0-rc3. And the performance
benchmarks results on qemu-kvm are below:
perf bench syscall usec/op (-ve is improvement)
| Syscall | Base | Generic Entry | change % |
| ------- | ----------- | ------------- | -------- |
| basic | 0.123997 | 0.120872 | -2.57 |
| execve | 512.1173 | 504.9966 | -1.52 |
| fork | 114.1144 | 113.2301 | -1.06 |
| getpgid | 0.120182 | 0.121245 | +0.9 |
perf bench syscall ops/sec (+ve is improvement)
| Syscall | Base | Generic Entry| change % |
| ------- | -------- | ------------ | -------- |
| basic | 8064712 | 8273212 | +2.48 |
| execve | 1952 | 1980 | +1.52 |
| fork | 8763 | 8832 | +1.06 |
| getpgid | 8320704 | 8247810 | -0.9 |
Therefore, the syscall performance variation ranges from a 1% regression
to a 2.5% improvement.
IPI latency benchmark (-ve is improvement)
| Metric | Base (ns) | Generic Entry (ns)| % Change |
| -------------- | ------------- | ---------------- | -------- |
| Dry run | 1068988.5 | 1072546.5 | +0.33% |
| Self IPI | 6362086.5 | 6334899 | -0.43% |
| Normal IPI | 174613249 | 183019457 | +4.81% |
| Broadcast IPI | 455716928 | 437884726 | -3.91% |
| Broadcast lock | 469317979 | 449988738.5 | -4.12% |
Therefore, the IPI performance variation ranges from a 4.8% regression
to a 4% improvement.
It was tested ok with following test cases on QEMU virt platform:
- Stress-ng CPU stress test.
- Hackbench stress test.
- "sud" selftest testcase.
- get_set_sud, get_syscall_info, set_syscall_info, peeksiginfo
in tools/testing/selftests/ptrace.
- breakpoint_test_arm64 in selftests/breakpoints.
- syscall-abi and ptrace in tools/testing/selftests/arm64/abi
- fp-ptrace, sve-ptrace, za-ptrace in selftests/arm64/fp.
- vdso_test_getrandom in tools/testing/selftests/vDSO
- Strace tests.
The test QEMU configuration is as follows:
qemu-system-aarch64 \
-M virt \
-enable-kvm \
-cpu host \
-kernel Image \
-smp 8 \
-m 512m \
-nographic \
-no-reboot \
-device virtio-rng-pci \
-append "root=/dev/vda rw console=ttyAMA0 kgdboc=ttyAMA0,115200
\
earlycon preempt=voluntary irqchip.gicv3_pseudo_nmi=1
audit=1" \
-drive if=none,file=images/rootfs.ext4,format=raw,id=hd0 \
-device virtio-blk-device,drive=hd0 \
Changes in v13:
- Rebased on v7.0-rc3, so drop the firt applied arm64 patch.
- Use generic TIF bits to enables RSEQ optimization.
- Update most of the commit message to make it more clear.
- Link to v12:
https://lore.kernel.org/all/[email protected]/
Changes in v12:
- Rebased on "sched/core", so remove the four generic entry patches.
- Move "Expand secure_computing() in place" and
"Use syscall_get_arguments() helper" patch forward, which will group all
non-functional cleanups at the front.
- Adjust the explanation for moving rseq_syscall() before
audit_syscall_exit().
- Link to v11:
https://lore.kernel.org/all/[email protected]/
Changes in v11:
- Remove unused syscall in syscall_trace_enter().
- Update and provide a detailed explanation of the differences after
moving rseq_syscall() before audit_syscall_exit().
- Rebased on arm64 (for-next/entry), and remove the first applied 3 patchs.
- syscall_exit_to_user_mode_work() for arch reuse instead of adding
new syscall_exit_to_user_mode_work_prepare() helper.
- Link to v10:
https://lore.kernel.org/all/[email protected]/
Changes in v10:
- Rebased on v6.19-rc1, rename syscall_exit_to_user_mode_prepare() to
syscall_exit_to_user_mode_work_prepare() to avoid conflict.
- Also inline syscall_trace_enter().
- Support aarch64 for sud_benchmark.
- Update and correct the commit message.
- Add Reviewed-by.
- Link to v9:
https://lore.kernel.org/all/[email protected]/
Changes in v9:
- Move "Return early for ptrace_report_syscall_entry() error" patch ahead
to make it not introduce a regression.
- Not check _TIF_SECCOMP/SYSCALL_EMU for syscall_exit_work() in
a separate patch.
- Do not report_syscall_exit() for PTRACE_SYSEMU_SINGLESTEP in a separate
patch.
- Add two performance patch to improve the arm64 performance.
- Add Reviewed-by.
- Link to v8:
https://lore.kernel.org/all/[email protected]/
Changes in v8:
- Rename "report_syscall_enter()" to "report_syscall_entry()".
- Add ptrace_save_reg() to avoid duplication.
- Remove unused _TIF_WORK_MASK in a standalone patch.
- Align syscall_trace_enter() return value with the generic version.
- Use "scno" instead of regs->syscallno in el0_svc_common().
- Move rseq_syscall() ahead in a standalone patch to clarify it clearly.
- Rename "syscall_trace_exit()" to "syscall_exit_work()".
- Keep the goto in el0_svc_common().
- No argument was passed to __secure_computing() and check -1 not -1L.
- Remove "Add has_syscall_work() helper" patch.
- Move "Add syscall_exit_to_user_mode_prepare() helper" patch later.
- Add miss header for asm/entry-common.h.
- Update the implementation of arch_syscall_is_vdso_sigreturn().
- Add "ARCH_SYSCALL_WORK_EXIT" to be defined as "SECCOMP | SYSCALL_EMU"
to keep the behaviour unchanged.
- Add more testcases test.
- Add Reviewed-by.
- Update the commit message.
- Link to v7:
https://lore.kernel.org/all/[email protected]/
Jinjie Ruan (11):
arm64/ptrace: Refactor syscall_trace_enter/exit() to accept flags
parameter
arm64/ptrace: Expand secure_computing() in place
arm64/ptrace: Use syscall_get_arguments() helper for audit
arm64: ptrace: Move rseq_syscall() before audit_syscall_exit()
arm64: syscall: Introduce syscall_exit_to_user_mode_work()
arm64/ptrace: Define and use _TIF_SYSCALL_EXIT_WORK
arm64/ptrace: Skip syscall exit reporting for PTRACE_SYSEMU_SINGLESTEP
arm64: entry: Convert to generic entry
arm64: Inline el0_svc_common()
s390: Rename TIF_SINGLE_STEP to TIF_SINGLESTEP
arm64: Use generic TIF bits for common thread flags
kemal (1):
selftests: sud_test: Support aarch64
arch/arm64/Kconfig | 3 +-
arch/arm64/include/asm/entry-common.h | 76 ++++++++++++
arch/arm64/include/asm/syscall.h | 19 ++-
arch/arm64/include/asm/thread_info.h | 76 ++++--------
arch/arm64/kernel/debug-monitors.c | 7 ++
arch/arm64/kernel/ptrace.c | 115 ------------------
arch/arm64/kernel/signal.c | 2 +-
arch/arm64/kernel/syscall.c | 29 ++---
arch/s390/include/asm/thread_info.h | 7 +-
arch/s390/kernel/process.c | 2 +-
arch/s390/kernel/ptrace.c | 20 +--
arch/s390/kernel/signal.c | 6 +-
arch/x86/include/asm/thread_info.h | 6 +-
include/asm-generic/thread_info_tif.h | 5 +
.../syscall_user_dispatch/sud_benchmark.c | 2 +-
.../syscall_user_dispatch/sud_test.c | 4 +
16 files changed, 166 insertions(+), 213 deletions(-)
--
2.34.1
