[PATCH bpf-next v4 0/2] bpf, arm64: Support per-cpu instruction

[Puranjay Mohan]

Changes in v3 -> v4:
v3: https://lore.kernel.org/all/20240426121349.97651-1-puranjay@kernel.org/
- Fix coding style issue related to C89 standards.

Changes in v2 -> v3:
v2: https://lore.kernel.org/all/20240424173550.16359-1-puranjay@kernel.org/
- Fixed the xlated dump of percpu mov to "r0 = &(void __percpu *)(r0)"
- Made ARM64 and x86-64 use the same code for inlining. The only difference
  that remains is the per-cpu address of the cpu_number.

Changes in v1 -> v2:
v1: https://lore.kernel.org/all/20240405091707.66675-1-puranjay12@gmail.com/
- Add a patch to inline bpf_get_smp_processor_id()
- Fix an issue in MRS instruction encoding as pointed out by Will
- Remove CONFIG_SMP check because arm64 kernel always compiles with CONFIG_SMP

This series adds the support of internal only per-CPU instructions and
inlines the bpf_get_smp_processor_id() helper call for ARM64 BPF JIT.

Here is an example of calls to bpf_get_smp_processor_id() and
percpu_array_map_lookup_elem() before and after this series.

                                         BPF
                                        =====
              BEFORE                                       AFTER
             --------                                     -------

int cpu = bpf_get_smp_processor_id();           int cpu = bpf_get_smp_processor_id();
(85) call bpf_get_smp_processor_id#229032       (18) r0 = 0xffff800082072008
                                                (bf) r0 = &(void __percpu *)(r0)
                                                (61) r0 = *(u32 *)(r0 +0)


p = bpf_map_lookup_elem(map, &zero);            p = bpf_map_lookup_elem(map, &zero);
(18) r1 = map[id:78]                            (18) r1 = map[id:153]
(18) r2 = map[id:82][0]+65536                   (18) r2 = map[id:157][0]+65536
(85) call percpu_array_map_lookup_elem#313512   (07) r1 += 496
                                                (61) r0 = *(u32 *)(r2 +0)
                                                (35) if r0 >= 0x1 goto pc+5
                                                (67) r0 <<= 3
                                                (0f) r0 += r1
                                                (79) r0 = *(u64 *)(r0 +0)
                                                (bf) r0 = &(void __percpu *)(r0)
                                                (05) goto pc+1
                                                (b7) r0 = 0


                                      ARM64 JIT
                                     ===========

              BEFORE                                       AFTER
             --------                                     -------

int cpu = bpf_get_smp_processor_id();           int cpu = bpf_get_smp_processor_id();
mov     x10, #0xfffffffffffff4d0                mov     x7, #0xffff8000ffffffff
movk    x10, #0x802b, lsl #16                   movk    x7, #0x8207, lsl #16
movk    x10, #0x8000, lsl #32                   movk    x7, #0x2008
blr     x10                                     mrs     x10, tpidr_el1
add     x7, x0, #0x0                            add     x7, x7, x10
                                                ldr     w7, [x7]


p = bpf_map_lookup_elem(map, &zero);            p = bpf_map_lookup_elem(map, &zero);
mov     x0, #0xffff0003ffffffff                 mov     x0, #0xffff0003ffffffff
movk    x0, #0xce5c, lsl #16                    movk    x0, #0xe0f3, lsl #16
movk    x0, #0xca00                             movk    x0, #0x7c00
mov     x1, #0xffff8000ffffffff                 mov     x1, #0xffff8000ffffffff
movk    x1, #0x8bdb, lsl #16                    movk    x1, #0xb0c7, lsl #16
movk    x1, #0x6000                             movk    x1, #0xe000
mov     x10, #0xffffffffffff3ed0                add     x0, x0, #0x1f0
movk    x10, #0x802d, lsl #16                   ldr     w7, [x1]
movk    x10, #0x8000, lsl #32                   cmp     x7, #0x1
blr     x10                                     b.cs    0x0000000000000090
add     x7, x0, #0x0                            lsl     x7, x7, #3
                                                add     x7, x7, x0
                                                ldr     x7, [x7]
                                                mrs     x10, tpidr_el1
                                                add     x7, x7, x10
                                                b       0x0000000000000094
                                                mov     x7, #0x0

              Performance improvement found using benchmark[1]

             BEFORE                                       AFTER
            --------                                     -------

glob-arr-inc   :   23.817 ± 0.019M/s      glob-arr-inc   :   24.631 ± 0.027M/s [+ 3.41%]
arr-inc        :   23.253 ± 0.019M/s      arr-inc        :   23.742 ± 0.023M/s [+ 2.10%]
hash-inc       :   12.258 ± 0.010M/s      hash-inc       :   12.625 ± 0.004M/s [+ 3.00%]

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

Puranjay Mohan (2):
  arm64, bpf: add internal-only MOV instruction to resolve per-CPU addrs
  bpf, arm64: inline bpf_get_smp_processor_id() helper

 arch/arm64/include/asm/insn.h |  7 +++++++
 arch/arm64/lib/insn.c         | 11 +++++++++++
 arch/arm64/net/bpf_jit.h      |  6 ++++++
 arch/arm64/net/bpf_jit_comp.c | 14 ++++++++++++++
 kernel/bpf/verifier.c         | 27 ++++++++++++++++++++-------
 5 files changed, 58 insertions(+), 7 deletions(-)

-- 
2.40.1