bench: add new micro benchmark about maps and read/write userspace memory

[yunwei37]

Description

• Add benchmark about maps
• Improve bench document

Type of change

• Bug fix (non-breaking change which fixes an issue)
• New feature (non-breaking change which adds functionality)
• Breaking change (fix or feature that would cause existing functionality to not work as expected)
• This change requires a documentation update

[yunwei37]

There are some performance problems we need to fix @Officeyutong

[Officeyutong]

There are some performance problems we need to fix @Officeyutong

What are behaviors of these issues?

[yunwei37]

What do you mean behavior?

[Officeyutong]

What do you mean behavior?

What are the performance issues?

[yunwei37]

You can see from https://github.com/eunomia-bpf/bpftime/tree/master/benchmark#maps-operations

The benchmark without inline the map op function:

Map Operation	Kernel (op - uprobe) (ns)	Userspace (op - uprobe) (ns)
__bench_hash_map_update	62827.533320	30296.051630
__bench_hash_map_lookup	15895.166920	23005.369380
__bench_hash_map_delete	19884.933980	13054.965970
__bench_array_map_update	9538.564600	6701.987970
__bench_array_map_lookup	183.155140	4305.515170
__bench_array_map_delete	216.088950	5987.507820
__bench_per_cpu_hash_map_update	33140.184290	95537.666900
__bench_per_cpu_hash_map_lookup	14089.238230	62913.855920
__bench_per_cpu_hash_map_delete	19753.563580	459826.428910
__bench_per_cpu_array_map_update	8885.238500	25728.928170
__bench_per_cpu_array_map_lookup	1838.737400	8759.420790
__bench_per_cpu_array_map_delete	1867.948100	4802.404130

[yunwei37]

Those costs are much higher than kernel eBPF maps

• per-cpu map op, include hash and array map
• array_map op (because we don't inline the map op)