arm64, bpf: add internal-only MOV instruction to resolve per-CPU addrs

Support an instruction for resolving absolute addresses of per-CPU
data from their per-CPU offsets. This instruction is internal-only and
users are not allowed to use them directly. They will only be used for
internal inlining optimizations for now between BPF verifier and BPF
JITs.

Since commit 7158627686 ("arm64: percpu: implement optimised pcpu
access using tpidr_el1"), the per-cpu offset for the CPU is stored in
the tpidr_el1/2 register of that CPU.

To support this BPF instruction in the ARM64 JIT, the following ARM64
instructions are emitted:

mov dst, src		// Move src to dst, if src != dst
mrs tmp, tpidr_el1/2	// Move per-cpu offset of the current cpu in tmp.
add dst, dst, tmp	// Add the per cpu offset to the dst.

To measure the performance improvement provided by this change, the
benchmark in [1] was used:

Before:
glob-arr-inc   :   23.597 ± 0.012M/s
arr-inc        :   23.173 ± 0.019M/s
hash-inc       :   12.186 ± 0.028M/s

After:
glob-arr-inc   :   23.819 ± 0.034M/s
arr-inc        :   23.285 ± 0.017M/s
hash-inc       :   12.419 ± 0.011M/s

[1] https://github.com/anakryiko/linux/commit/8dec900975ef

Signed-off-by: Puranjay Mohan <puranjay12@gmail.com>
Acked-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/r/20240502151854.9810-4-puranjay@kernel.org
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
This commit is contained in:
Puranjay Mohan 2024-05-02 15:18:53 +00:00 committed by Alexei Starovoitov
parent 2ddec2c80b
commit 7a4c32222b
4 changed files with 38 additions and 0 deletions

View File

@ -135,6 +135,11 @@ enum aarch64_insn_special_register {
AARCH64_INSN_SPCLREG_SP_EL2 = 0xF210
};
enum aarch64_insn_system_register {
AARCH64_INSN_SYSREG_TPIDR_EL1 = 0x4684,
AARCH64_INSN_SYSREG_TPIDR_EL2 = 0x6682,
};
enum aarch64_insn_variant {
AARCH64_INSN_VARIANT_32BIT,
AARCH64_INSN_VARIANT_64BIT
@ -686,6 +691,8 @@ u32 aarch64_insn_gen_cas(enum aarch64_insn_register result,
}
#endif
u32 aarch64_insn_gen_dmb(enum aarch64_insn_mb_type type);
u32 aarch64_insn_gen_mrs(enum aarch64_insn_register result,
enum aarch64_insn_system_register sysreg);
s32 aarch64_get_branch_offset(u32 insn);
u32 aarch64_set_branch_offset(u32 insn, s32 offset);

View File

@ -1515,3 +1515,14 @@ u32 aarch64_insn_gen_dmb(enum aarch64_insn_mb_type type)
return insn;
}
u32 aarch64_insn_gen_mrs(enum aarch64_insn_register result,
enum aarch64_insn_system_register sysreg)
{
u32 insn = aarch64_insn_get_mrs_value();
insn &= ~GENMASK(19, 0);
insn |= sysreg << 5;
return aarch64_insn_encode_register(AARCH64_INSN_REGTYPE_RT,
insn, result);
}

View File

@ -297,4 +297,10 @@
#define A64_ADR(Rd, offset) \
aarch64_insn_gen_adr(0, offset, Rd, AARCH64_INSN_ADR_TYPE_ADR)
/* MRS */
#define A64_MRS_TPIDR_EL1(Rt) \
aarch64_insn_gen_mrs(Rt, AARCH64_INSN_SYSREG_TPIDR_EL1)
#define A64_MRS_TPIDR_EL2(Rt) \
aarch64_insn_gen_mrs(Rt, AARCH64_INSN_SYSREG_TPIDR_EL2)
#endif /* _BPF_JIT_H */

View File

@ -890,6 +890,15 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx,
emit(A64_ORR(1, tmp, dst, tmp), ctx);
emit(A64_MOV(1, dst, tmp), ctx);
break;
} else if (insn_is_mov_percpu_addr(insn)) {
if (dst != src)
emit(A64_MOV(1, dst, src), ctx);
if (cpus_have_cap(ARM64_HAS_VIRT_HOST_EXTN))
emit(A64_MRS_TPIDR_EL2(tmp), ctx);
else
emit(A64_MRS_TPIDR_EL1(tmp), ctx);
emit(A64_ADD(1, dst, dst, tmp), ctx);
break;
}
switch (insn->off) {
case 0:
@ -2559,6 +2568,11 @@ bool bpf_jit_supports_insn(struct bpf_insn *insn, bool in_arena)
return true;
}
bool bpf_jit_supports_percpu_insn(void)
{
return true;
}
void bpf_jit_free(struct bpf_prog *prog)
{
if (prog->jited) {