bpftool: Enable aarch64 ISA extensions for JIT disassembly

bpftool: Enable aarch64 ISA extensions for JIT disassembly

The LLVM disassembler needs ISA extension features enabled to correctly
decode instructions from those extensions. On aarch64, without these
features, instructions like LSE atomics (e.g. ldaddal) are silently
decoded as incorrect instructions and disassembly is truncated.

Use LLVMCreateDisasmCPUFeatures() with "+all" features for aarch64
targets so that the disassembler can handle any instruction the kernel
JIT might emit.

Before:

int bench_trigger_uprobe(void * ctx):
bpf_prog_538c6a43d1c6b84c_bench_trigger_uprobe:
; int cpu = bpf_get_smp_processor_id();
   0:   mov     x9, x30
   4:   nop
   8:   stp     x29, x30, [sp, #-16]!
   c:   mov     x29, sp
  10:   stp     xzr, x26, [sp, #-16]!
  14:   mov     x26, sp
  18:   mrs     x10, SP_EL0
  1c:   ldr     w7, [x10, #16]
; __sync_add_and_fetch(&hits[cpu & CPU_MASK].value, 1);
  20:   and     w7, w7, #0xff
; __sync_add_and_fetch(&hits[cpu & CPU_MASK].value, 1);
  24:   lsl     x7, x7, #7
  28:   mov     x0, #-281474976710656
  2c:   movk    x0, #32768, lsl #32
  30:   movk    x0, #35407, lsl #16
  34:   add     x0, x0, x7
  38:   mov     x1, #1
; __sync_add_and_fetch(&hits[cpu & CPU_MASK].value, 1);
  3c:   mov     x1, #1

After:

int bench_trigger_uprobe(void * ctx):
bpf_prog_538c6a43d1c6b84c_bench_trigger_uprobe:
; int cpu = bpf_get_smp_processor_id();
   0:   mov     x9, x30
   4:   nop
   8:   stp     x29, x30, [sp, #-16]!
   c:   mov     x29, sp
  10:   stp     xzr, x26, [sp, #-16]!
  14:   mov     x26, sp
  18:   mrs     x10, SP_EL0
  1c:   ldr     w7, [x10, #16]
; __sync_add_and_fetch(&hits[cpu & CPU_MASK].value, 1);
  20:   and     w7, w7, #0xff
; __sync_add_and_fetch(&hits[cpu & CPU_MASK].value, 1);
  24:   lsl     x7, x7, #7
  28:   mov     x0, #-281474976710656
  2c:   movk    x0, #32768, lsl #32
  30:   movk    x0, #35407, lsl #16
  34:   add     x0, x0, x7
  38:   mov     x1, #1
; __sync_add_and_fetch(&hits[cpu & CPU_MASK].value, 1);
  3c:   ldaddal x1, x1, [x0]
; return 0;
  40:   mov     w7, #0
  44:   ldp     xzr, x26, [sp], #16
  48:   ldp     x29, x30, [sp], #16
  4c:   mov     x0, x7
  50:   ret
  54:   nop
  58:   ldr     x10, #8
  5c:   br      x10

Signed-off-by: Puranjay Mohan <puranjay@kernel.org>
Acked-by: Yonghong Song <yonghong.song@linux.dev>
Acked-by: Leon Hwang <leon.hwang@linux.dev>
Acked-by: Quentin Monnet <qmo@kernel.org>
Reviewed-by: Emil Tsalapatis <emil@etsalapatis.com>
Link: https://lore.kernel.org/r/20260318172259.2882792-1-puranjay@kernel.org
Signed-off-by: Alexei Starovoitov <ast@kernel.org>