Re: [PATCH v3] gdb: call check_typedef at beginning of dwarf_expr_context::fetch_result

[Luis Machado <luis.machado@arm.com>]

On 8/18/22 18:34, Simon Marchi wrote:
> On 8/18/22 12:51, Luis Machado wrote:
>> On 8/18/22 17:16, Simon Marchi via Gdb-patches wrote:
>>> On 7/28/22 11:33, Simon Marchi wrote:
>>>> From: Simon Marchi <simon.marchi@polymtl.ca>
>>>>
>>>> New in this version:
>>>>
>>>>    - add architecture check in test
>>>>    - add aarch64 version of the .S
>>>>
>>>> Bug 29374 shows this crash:
>>>>
>>>>       $ ./gdb -nx --data-directory=data-directory -q -batch -ex "catch throw" -ex r -ex bt a.out
>>>>       ...
>>>>       /home/simark/src/binutils-gdb/gdb/../gdbsupport/array-view.h:217: internal-error: copy: Assertion `dest.size () == src.size ()' failed.
>>>>
>>>> The backtrace is:
>>>>
>>>>       #0  internal_error (file=0x5555606504c0 "/home/simark/src/binutils-gdb/gdb/../gdbsupport/array-view.h", line=217, fmt=0x55556064b700 "%s: Assertion `%s' failed.") at /home/simark/src/binutils-gdb/gdbsupport/errors.cc:51
>>>>       #1  0x000055555d41c0bb in gdb::copy<unsigned char const, unsigned char> (src=..., dest=...) at /home/simark/src/binutils-gdb/gdb/../gdbsupport/array-view.h:217
>>>>       #2  0x000055555deef28c in dwarf_expr_context::fetch_result (this=0x7fffffffb830, type=0x621007a86830, subobj_type=0x621007a86830, subobj_offset=0, as_lval=false) at /home/simark/src/binutils-gdb/gdb/dwarf2/expr.c:1040
>>>>       #3  0x000055555def0015 in dwarf_expr_context::evaluate (this=0x7fffffffb830, addr=0x62f00004313e "0", len=1, as_lval=false, per_cu=0x60b000069550, frame=0x621007c9e910, addr_info=0x0, type=0x621007a86830, subobj_type=0x621007a86830, subobj_offset=0) at /home/simark/src/binutils-gdb/gdb/dwarf2/expr.c:1091
>>>>       #4  0x000055555e084327 in dwarf2_evaluate_loc_desc_full (type=0x621007a86830, frame=0x621007c9e910, data=0x62f00004313e "0", size=1, per_cu=0x60b000069550, per_objfile=0x613000006080, subobj_type=0x621007a86830, subobj_byte_offset=0, as_lval=false) at /home/simark/src/binutils-gdb/gdb/dwarf2/loc.c:1485
>>>>       #5  0x000055555e0849e2 in dwarf2_evaluate_loc_desc (type=0x621007a86830, frame=0x621007c9e910, data=0x62f00004313e "0", size=1, per_cu=0x60b000069550, per_objfile=0x613000006080, as_lval=false) at /home/simark/src/binutils-gdb/gdb/dwarf2/loc.c:1529
>>>>       #6  0x000055555e0828c6 in dwarf_entry_parameter_to_value (parameter=0x621007a96e58, deref_size=0x0, type=0x621007a86830, caller_frame=0x621007c9e910, per_cu=0x60b000069550, per_objfile=0x613000006080) at /home/simark/src/binutils-gdb/gdb/dwarf2/loc.c:1235
>>>>       #7  0x000055555e082f55 in value_of_dwarf_reg_entry (type=0x621007a86890, frame=0x621007acc510, kind=CALL_SITE_PARAMETER_DWARF_REG, kind_u=...) at /home/simark/src/binutils-gdb/gdb/dwarf2/loc.c:1332
>>>>       #8  0x000055555e083449 in value_of_dwarf_block_entry (type=0x621007a86890, frame=0x621007acc510, block=0x61e000033568 "T\004\205\001\240\004\004\243\001T\237\004\240\004\261\004\001T\004\261\004\304\005\004\243\001T\237\004\304\005\310\005\001T\004\310\005\311\005\004\243\001T\237", block_len=1) at /home/simark/src/binutils-gdb/gdb/dwarf2/loc.c:1365
>>>>       #9  0x000055555e094d40 in loclist_read_variable_at_entry (symbol=0x621007a99bd0, frame=0x621007acc510) at /home/simark/src/binutils-gdb/gdb/dwarf2/loc.c:3889
>>>>       #10 0x000055555f5192e0 in read_frame_arg (fp_opts=..., sym=0x621007a99bd0, frame=0x621007acc510, argp=0x7fffffffbf20, entryargp=0x7fffffffbf60) at /home/simark/src/binutils-gdb/gdb/stack.c:559
>>>>       #11 0x000055555f51c352 in print_frame_args (fp_opts=..., func=0x621007a99ad0, frame=0x621007acc510, num=-1, stream=0x6030000bad90) at /home/simark/src/binutils-gdb/gdb/stack.c:887
>>>>       #12 0x000055555f521919 in print_frame (fp_opts=..., frame=0x621007acc510, print_level=1, print_what=LOCATION, print_args=1, sal=...) at /home/simark/src/binutils-gdb/gdb/stack.c:1390
>>>>       #13 0x000055555f51f22e in print_frame_info (fp_opts=..., frame=0x621007acc510, print_level=1, print_what=LOCATION, print_args=1, set_current_sal=0) at /home/simark/src/binutils-gdb/gdb/stack.c:1116
>>>>       #14 0x000055555f526c6d in backtrace_command_1 (fp_opts=..., bt_opts=..., count_exp=0x0, from_tty=0) at /home/simark/src/binutils-gdb/gdb/stack.c:2079
>>>>       #15 0x000055555f527ae5 in backtrace_command (arg=0x0, from_tty=0) at /home/simark/src/binutils-gdb/gdb/stack.c:2198
>>>>
>>>> The problem is that the type that gets passed down to
>>>> dwarf_expr_context::fetch_result (the type of a variable of which we're
>>>> trying to read the entry value) is a typedef whose size has never been
>>>> computed yet (check_typedef has never been called on it).  As we get in
>>>> the DWARF_VALUE_STACK case (line 1028 of dwarf2/expr.c), the `len`
>>>> variable is therefore set to 0, instead of the actual type length.  We
>>>> then call allocate_value on subobj_type, which does call check_typedef,
>>>> so the length of the typedef gets filled in at that point.  We end up
>>>> passing to the copy function a source array view of length 0 and a
>>>> target array view of length 4, and the assertion fails.
>>>>
>>>> Fix this by calling check_typedef on both type and subobj_type at the
>>>> beginning of fetch_result.
>>>>
>>>> I tried writing a test for this using the DWARF assembler, but I haven't
>>>> succeeded.  It's possible that we need to get into this specific code
>>>> path (value_of_dwarf_reg_entry and all) to manage to get to
>>>> dwarf_expr_context::fetch_result with a typedef type that has never been
>>>> resolved.  In all my attempts, the typedef would always be resolved
>>>> already, so the bug wouldn't show up.
>>>>
>>>> As a fallback, I made a gdb.dwarf2 test with compiler-generated .S
>>>> files.  I don't particularly like those, but I think it's better than no
>>>> test.  The .cpp source code is the smallest reproducer I am able to make
>>>> from the reproducer given in the bug (thanks to Pedro for suggestions on
>>>> how to minimize it further than I had).  Since I tested on both amd64
>>>> and aarch64, I added versions of the test for these two architectures.
>>>>
>>>> Change-Id: I182733ad08e34df40d8bcc47af72c482fabf4900
>>>> Bug: https://sourceware.org/bugzilla/show_bug.cgi?id=29374
>>>> ---
>>>>    gdb/dwarf2/expr.c                             |     5 +
>>>>    .../gdb.dwarf2/entry-value-typedef-aarch64.S  | 12885 +++++++++++++
>>>>    .../gdb.dwarf2/entry-value-typedef-amd64.S    | 15545 ++++++++++++++++
>>>>    .../gdb.dwarf2/entry-value-typedef.cpp        |    36 +
>>>>    .../gdb.dwarf2/entry-value-typedef.exp        |    45 +
>>>>    5 files changed, 28516 insertions(+)
>>>>    create mode 100644 gdb/testsuite/gdb.dwarf2/entry-value-typedef-aarch64.S
>>>>    create mode 100644 gdb/testsuite/gdb.dwarf2/entry-value-typedef-amd64.S
>>>>    create mode 100644 gdb/testsuite/gdb.dwarf2/entry-value-typedef.cpp
>>>>    create mode 100644 gdb/testsuite/gdb.dwarf2/entry-value-typedef.exp
>>>
>>> I pushed this patch.
>>>
>>> Simon
>>
>> It seems newer compilers on aarch64 (g++ 9.4.0 or 11.2.0) don't like this test. They complain with:
>>
>> gdb compile failed, /usr/bin/ld: /tmp/cc0vjoZT.o: relocation R_AARCH64_ADR_PREL_PG_HI21 against symbol `_ZNSsD1Ev@@GLIBCXX_3.4' which may bin
>> d externally can not be used when making a shared object; recompile with -fPIC
>> /usr/bin/ld: /tmp/cc0vjoZT.o(.text+0x38): unresolvable R_AARCH64_ADR_PREL_PG_HI21 relocation against symbol `_ZNSsD1Ev@@GLIBCXX_3.4'
>> /usr/bin/ld: final link failed: bad value
>>
>> So the test doesn't run properly.
> 
> Is is that the old compiler I used (g++ 4.8 on Ubuntu 14.04, on the
> compile farm) generated non-position-independent code, but the linker
> of the newer toolchains try to build a position-independent executable?
> If so, we can re-generate the assembly files with -fPIE, and it should
> work, right?  I'll give this a try, I have access to an AArch64 machine
> with Debian 11 & g++ 10.2.1.
> 
> Simon

Yes, that might be the case. Let me know if you'd like me to regenerate it.