[GPU] add format::b_fs_yx_fsv4 to onednn::conv support list

[sungeunk]

Description of the issue(symptom, root-cause, how it was resolved)

• This issue can be reproduced on the machine which the onednn is working.
• It cannot create the onednn primitive with this error msg: "Check 'shape_consistent' failed at src/plugins/intel_gpu/src/graph/impls/onednn/convolution_onednn.cpp:264: [GPU] Input shape and output shape of weight reorder should be same."
• root-cause: At add_required_reorders pass, b_fs_fsv4 is chosen for input0 via find_data_format(). b_fs_fsv4 is not in supported list for onednn::conv. it chooses bfzyx for in/out of conv via test_format().

The code and line that caused this issue (if it is not changed directly)

• src/plugins/intel_gpu/src/graph/impls/onednn/convolution_onednn.cpp (test_format)

Reproduction step and snapshot (if applicable. Do not attach for customer model)

• reproducer is attached in the ticket.

Problematic graph

cldnn_program_1_15_prepare_buffer_fusing.graph

cldnn_program_1_16_add_required_reorders.graph

Checklist

• Is it a proper fix? (not a workaround)
• Did you include test case for this fix, if necessary?
• Did you review existing test that can be extended to cover this scenario? Which test did you review?
  -> In add_required_reorder pass, this convolution should be chosen wrong format via test_format() to reproduce the issue.

Tickets:

• 174951

[isanghao]

could you reuse existing case? I think there should be something we can use by parametrization

[sungeunk]

There is no test with parameterization for onednn. In almost test, it uses 'force_implementations()' func to set format to issue node. but the test for this issue needs to check has_impl due to it doesn't call the test_format() in add_required_reorders pass. test_format() occurs this issue.

[isanghao]

LGTM