Message ID | 20240704102402.1644916-1-eddyz87@gmail.com (mailing list archive) |
---|---|
Headers | show |
Series | no_caller_saved_registers attribute for helper calls | expand |
Eduard Zingerman <eddyz87@gmail.com> writes: > This RFC seeks to allow using no_caller_saved_registers gcc/clang > attribute with some BPF helper functions (and kfuncs in the future). > > As documented in [1], this attribute means that function scratches > only some of the caller saved registers defined by ABI. > For BPF the set of such registers could be defined as follows: > - R0 is scratched only if function is non-void; > - R1-R5 are scratched only if corresponding parameter type is defined > in the function prototype. > > The goal of the RFC is to implement no_caller_saved_registers > (nocsr for short) in a backwards compatible manner: > - for kernels that support the feature, gain some performance boost > from better register allocation; > - for kernels that don't support the feature, allow programs execution > with minor performance losses. > > To achieve this, use a scheme suggested by Alexei Starovoitov: > - for nocsr calls clang allocates registers as-if relevant r0-r5 > registers are not scratched by the call; > - as a post-processing step, clang visits each nocsr call and adds > spill/fill for every live r0-r5; > - stack offsets used for spills/fills are allocated as minimal > stack offsets in whole function and are not used for any other > purposes; > - when kernel loads a program, it looks for such patterns > (nocsr function surrounded by spills/fills) and checks if > spill/fill stack offsets are used exclusively in nocsr patterns; > - if so, and if current JIT inlines the call to the nocsr function > (e.g. a helper call), kernel removes unnecessary spill/fill pairs; > - when old kernel loads a program, presence of spill/fill pairs > keeps BPF program valid, albeit slightly less efficient. > > Corresponding clang/llvm changes are available in [2]. > > The patch-set uses bpf_get_smp_processor_id() function as a canary, > making it the first helper with nocsr attribute. > > For example, consider the following program: > > #define __no_csr __attribute__((no_caller_saved_registers)) > #define SEC(name) __attribute__((section(name), used)) > #define bpf_printk(fmt, ...) bpf_trace_printk((fmt), sizeof(fmt), __VA_ARGS__) > > typedef unsigned int __u32; > > static long (* const bpf_trace_printk)(const char *fmt, __u32 fmt_size, ...) = (void *) 6; > static __u32 (*const bpf_get_smp_processor_id)(void) __no_csr = (void *)8; > > SEC("raw_tp") > int test(void *ctx) > { > __u32 task = bpf_get_smp_processor_id(); > bpf_printk("ctx=%p, smp=%d", ctx, task); > return 0; > } > > char _license[] SEC("license") = "GPL"; > > Compiled (using [2]) as follows: > > $ clang --target=bpf -O2 -g -c -o nocsr.bpf.o nocsr.bpf.c > $ llvm-objdump --no-show-raw-insn -Sd nocsr.bpf.o > ... > 3rd parameter for printk call removable spill/fill pair > .--- 0: r3 = r1 | > ; | __u32 task = bpf_get_smp_processor_id(); | > | 1: *(u64 *)(r10 - 0x8) = r3 <----------| > | 2: call 0x8 | > | 3: r3 = *(u64 *)(r10 - 0x8) <----------' > ; | bpf_printk("ctx=%p, smp=%d", ctx, task); > | 4: r1 = 0x0 ll > | 6: r2 = 0xf > | 7: r4 = r0 > '--> 8: call 0x6 > ; return 0; > 9: r0 = 0x0 > 10: exit > > Here is how the program looks after verifier processing: > > # bpftool prog load ./nocsr.bpf.o /sys/fs/bpf/nocsr-test > # bpftool prog dump xlated pinned /sys/fs/bpf/nocsr-test > int test(void * ctx): > ; int test(void *ctx) > 0: (bf) r3 = r1 <--------- 3rd printk parameter > ; __u32 task = bpf_get_smp_processor_id(); > 1: (b4) w0 = 197132 <--------- inlined helper call, > 2: (bf) r0 = r0 <--------- spill/fill pair removed > 3: (61) r0 = *(u32 *)(r0 +0) <--------- > ; bpf_printk("ctx=%p, smp=%d", ctx, task); > 4: (18) r1 = map[id:13][0]+0 > 6: (b7) r2 = 15 > 7: (bf) r4 = r0 > 8: (85) call bpf_trace_printk#-125920 > ; return 0; > 9: (b7) r0 = 0 > 10: (95) exit > > [1] https://clang.llvm.org/docs/AttributeReference.html#no-caller-saved-registers > [2] https://github.com/eddyz87/llvm-project/tree/bpf-no-caller-saved-registers > > Change list: > - v1 -> v2: > - assume that functions inlined by either jit or verifier > conform to no_caller_saved_registers contract (Andrii, Puranjay); > - allow nocsr rewrite for bpf_get_smp_processor_id() > on arm64 and riscv64 architectures (Puranjay); > - __arch_{x86_64,arm64,riscv64} macro for test_loader; > - moved remove_nocsr_spills_fills() inside do_misc_fixups() (Andrii); > - moved nocsr pattern detection from check_cfg() to a separate pass > (Andrii); > - various stylistic/correctness changes according to Andrii's > comments. > > Revisions: > - v1 https://lore.kernel.org/bpf/20240629094733.3863850-1-eddyz87@gmail.com/ > > Eduard Zingerman (9): > bpf: add a get_helper_proto() utility function > bpf: no_caller_saved_registers attribute for helper calls > bpf, x86, riscv, arm: no_caller_saved_registers for > bpf_get_smp_processor_id() Ran the selftest on riscv-64 on qemu: root@rv-tester:~/bpf# uname -a Linux rv-tester 6.10.0-rc2 #27 SMP Mon Jul 8 09:58:20 UTC 2024 riscv64 riscv64 riscv64 GNU/Linux root@rv-tester:~/bpf# ./test_progs -a verifier_nocsr/canary_arm64_riscv64 #496/2 verifier_nocsr/canary_arm64_riscv64:OK #496 verifier_nocsr:OK Summary: 1/1 PASSED, 0 SKIPPED, 0 FAILED Tested-by: Puranjay Mohan <puranjay@kernel.org> #riscv64 Thanks, Puranjay
On Mon, 2024-07-08 at 11:44 +0000, Puranjay Mohan wrote: [...] > Ran the selftest on riscv-64 on qemu: > > root@rv-tester:~/bpf# uname -a > Linux rv-tester 6.10.0-rc2 #27 SMP Mon Jul 8 09:58:20 UTC 2024 riscv64 riscv64 riscv64 GNU/Linux > root@rv-tester:~/bpf# ./test_progs -a verifier_nocsr/canary_arm64_riscv64 > #496/2 verifier_nocsr/canary_arm64_riscv64:OK > #496 verifier_nocsr:OK > Summary: 1/1 PASSED, 0 SKIPPED, 0 FAILED > > Tested-by: Puranjay Mohan <puranjay@kernel.org> #riscv64 Great, thank you for testing!
On Thu, Jul 4, 2024 at 3:24 AM Eduard Zingerman <eddyz87@gmail.com> wrote: > > - stack offsets used for spills/fills are allocated as minimal > stack offsets in whole function and are not used for any other > purposes; "minimal stack offset" reads odd to me. I noticed the same naming convention is used in llvm diff. imo it's odd there as well. Maybe say: llvm grows the stack that in bpf architecture always grows down and picks the lowest stack offset not used by local variables and spill/fill. > Here is how the program looks after verifier processing: > > # bpftool prog load ./nocsr.bpf.o /sys/fs/bpf/nocsr-test > # bpftool prog dump xlated pinned /sys/fs/bpf/nocsr-test > int test(void * ctx): > ; int test(void *ctx) > 0: (bf) r3 = r1 <--------- 3rd printk parameter > ; __u32 task = bpf_get_smp_processor_id(); > 1: (b4) w0 = 197132 <--------- inlined helper call, > 2: (bf) r0 = r0 <--------- spill/fill pair removed Are you using old bpftool or something? That should have been: r0 = &(void __percpu *)(r0) ? > 3: (61) r0 = *(u32 *)(r0 +0) <--------- > ; bpf_printk("ctx=%p, smp=%d", ctx, task); > 4: (18) r1 = map[id:13][0]+0 > 6: (b7) r2 = 15 > 7: (bf) r4 = r0 > 8: (85) call bpf_trace_printk#-125920 > ; return 0; > 9: (b7) r0 = 0 > 10: (95) exit
On Tue, 2024-07-09 at 18:18 -0700, Alexei Starovoitov wrote: > On Thu, Jul 4, 2024 at 3:24 AM Eduard Zingerman <eddyz87@gmail.com> wrote: > > > > - stack offsets used for spills/fills are allocated as minimal > > stack offsets in whole function and are not used for any other > > purposes; > > "minimal stack offset" reads odd to me. > I noticed the same naming convention is used in llvm diff. > imo it's odd there as well. > Maybe say: > llvm grows the stack that in bpf architecture always grows down and > picks the lowest stack offset not used by local variables > and spill/fill. Will replace "minimal" with lowest here and in LLVM diff. > > Here is how the program looks after verifier processing: > > > > # bpftool prog load ./nocsr.bpf.o /sys/fs/bpf/nocsr-test > > # bpftool prog dump xlated pinned /sys/fs/bpf/nocsr-test > > int test(void * ctx): > > ; int test(void *ctx) > > 0: (bf) r3 = r1 <--------- 3rd printk parameter > > ; __u32 task = bpf_get_smp_processor_id(); > > 1: (b4) w0 = 197132 <--------- inlined helper call, > > 2: (bf) r0 = r0 <--------- spill/fill pair removed > > Are you using old bpftool or something? > That should have been: > r0 = &(void __percpu *)(r0) > ? Yes, I was using distro-provided bpftool. Re-running with kernel version of the tool shows the __percpu thing. > > > 3: (61) r0 = *(u32 *)(r0 +0) <--------- [...]