Emilio Cota [Tue, 24 Jan 2023 18:01:18 +0000 (18:01 +0000)]
cpu: free cpu->tb_jmp_cache with RCU
Fixes the appended use-after-free. The root cause is that
during tb invalidation we use CPU_FOREACH, and therefore
to safely free a vCPU we must wait for an RCU grace period
to elapse.
$ x86_64-linux-user/qemu-x86_64 tests/tcg/x86_64-linux-user/munmap-pthread
=================================================================
==1800604==ERROR: AddressSanitizer: heap-use-after-free on address 0x62d0005f7418 at pc 0x5593da6704eb bp 0x7f4961a7ac70 sp 0x7f4961a7ac60
READ of size 8 at 0x62d0005f7418 thread T2
#0 0x5593da6704ea in tb_jmp_cache_inval_tb ../accel/tcg/tb-maint.c:244
#1 0x5593da6704ea in do_tb_phys_invalidate ../accel/tcg/tb-maint.c:290
#2 0x5593da670631 in tb_phys_invalidate__locked ../accel/tcg/tb-maint.c:306
#3 0x5593da670631 in tb_invalidate_phys_page_range__locked ../accel/tcg/tb-maint.c:542
#4 0x5593da67106d in tb_invalidate_phys_range ../accel/tcg/tb-maint.c:614
#5 0x5593da6a64d4 in target_munmap ../linux-user/mmap.c:766
#6 0x5593da6dba05 in do_syscall1 ../linux-user/syscall.c:10105
#7 0x5593da6f564c in do_syscall ../linux-user/syscall.c:13329
#8 0x5593da49e80c in cpu_loop ../linux-user/x86_64/../i386/cpu_loop.c:233
#9 0x5593da6be28c in clone_func ../linux-user/syscall.c:6633
#10 0x7f496231cb42 in start_thread nptl/pthread_create.c:442
#11 0x7f49623ae9ff (/lib/x86_64-linux-gnu/libc.so.6+0x1269ff)
0x62d0005f7418 is located 28696 bytes inside of 32768-byte region [0x62d0005f0400,0x62d0005f8400)
freed by thread T148 here:
#0 0x7f49627b6460 in __interceptor_free ../../../../src/libsanitizer/asan/asan_malloc_linux.cpp:52
#1 0x5593da5ac057 in cpu_exec_unrealizefn ../cpu.c:180
#2 0x5593da81f851 (/home/cota/src/qemu/build/qemu-x86_64+0x484851)
Signed-off-by: Emilio Cota <cota@braap.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-Id: <20230111151628.320011-2-cota@braap.org> Signed-off-by: Alex Bennée <alex.bennee@linaro.org>
Message-Id: <20230124180127.1881110-27-alex.bennee@linaro.org>
Alex Bennée [Tue, 24 Jan 2023 18:01:17 +0000 (18:01 +0000)]
tests/tcg: add memory-sve test for aarch64
This will be helpful in debugging problems with tracking SVE memory
accesses via the TCG plugins system.
Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Alex Bennée <alex.bennee@linaro.org> Cc: Robert Henry <robhenry@microsoft.com> Cc: Aaron Lindsay <aaron@os.amperecomputing.com>
Message-Id: <20230124180127.1881110-26-alex.bennee@linaro.org>
Evgeny Iakovlev [Tue, 24 Jan 2023 18:01:16 +0000 (18:01 +0000)]
semihosting: add O_BINARY flag in host_open for NT compatibility
Windows open(2) implementation opens files in text mode by default and
needs a Windows-only O_BINARY flag to open files as binary. QEMU already
knows about that flag in osdep and it is defined to 0 on non-Windows,
so we can just add it to the host_flags for better compatibility.
Signed-off-by: Evgeny Iakovlev <eiakovlev@linux.microsoft.com> Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Reviewed-by: Bin Meng <bmeng.cn@gmail.com>
Message-Id: <20230106102018.20520-1-eiakovlev@linux.microsoft.com> Signed-off-by: Alex Bennée <alex.bennee@linaro.org>
Message-Id: <20230124180127.1881110-25-alex.bennee@linaro.org>
Keith Packard [Tue, 24 Jan 2023 18:01:15 +0000 (18:01 +0000)]
semihosting: Write back semihosting data before completion callback
'lock_user' allocates a host buffer to shadow a target buffer,
'unlock_user' copies that host buffer back to the target and frees the
host memory. If the completion function uses the target buffer, it
must be called after unlock_user to ensure the data are present.
This caused the arm-compatible TARGET_SYS_READC to fail as the
completion function, common_semi_readc_cb, pulled data from the target
buffer which would not have been gotten the console data.
I decided to fix all instances of this pattern instead of just the
console_read function to make things consistent and potentially fix
bugs in other cases.
Signed-off-by: Keith Packard <keithp@keithp.com> Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-Id: <20221012014822.1242170-1-keithp@keithp.com> Signed-off-by: Alex Bennée <alex.bennee@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org>
Message-Id: <20230124180127.1881110-24-alex.bennee@linaro.org>
Alex Bennée [Tue, 24 Jan 2023 18:01:14 +0000 (18:01 +0000)]
docs: add an introduction to the system docs
Drop the frankly misleading quickstart section for a more rounded
introduction section. This new section gives an overview of the
accelerators as well as a high level introduction to some of the key
features of the emulator. We also expand on a general form for a QEMU
command line with a hopefully not too scary worked example of what
this looks like.
Acked-by: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Alex Bennée <alex.bennee@linaro.org> Reviewed-by: Kashyap Chamarthy <kchamart@redhat.com>
Message-Id: <20230124180127.1881110-23-alex.bennee@linaro.org>
Alex Bennée [Tue, 24 Jan 2023 18:01:13 +0000 (18:01 +0000)]
semihosting: add semihosting section to the docs
The main reason to do this is to document our O_BINARY implementation
decision somewhere. However I've also moved some of the implementation
details out of qemu-options and added links between the two. As a
bonus I've highlighted the scary warnings about host access with the
appropriate RST tags.
Acked-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Alex Bennée <alex.bennee@linaro.org>
Message-Id: <20230124180127.1881110-22-alex.bennee@linaro.org>
Alex Bennée [Tue, 24 Jan 2023 18:01:12 +0000 (18:01 +0000)]
docs: add a new section to outline emulation support
This affects both system and user mode emulation so we should probably
list it up front.
Acked-by: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Alex Bennée <alex.bennee@linaro.org>
Message-Id: <20230124180127.1881110-21-alex.bennee@linaro.org>
Alex Bennée [Tue, 24 Jan 2023 18:01:11 +0000 (18:01 +0000)]
docs: add hotlinks to about preface text
Make it easier to navigate the documentation.
Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Acked-by: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Alex Bennée <alex.bennee@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org>
Message-Id: <20230124180127.1881110-20-alex.bennee@linaro.org>
Thomas Huth [Tue, 24 Jan 2023 18:01:10 +0000 (18:01 +0000)]
MAINTAINERS: Fix the entry for tests/tcg/nios2
tests/tcg/nios2/Makefile.target has accidentally been added
to the Microblaze section. Move it into the correct nios2
section instead - and while we're at it, it should also cover
the whole folder, and not only the Makefile.
Fixes: 67f80eb4d0 ("tests/tcg: enable debian-nios2-cross for test building") Signed-off-by: Thomas Huth <thuth@redhat.com> Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org>
Message-Id: <20230119130326.2030297-1-thuth@redhat.com> Signed-off-by: Alex Bennée <alex.bennee@linaro.org>
Message-Id: <20230124180127.1881110-19-alex.bennee@linaro.org>
Alex Bennée [Tue, 24 Jan 2023 18:01:09 +0000 (18:01 +0000)]
gitlab: wrap up test results for custom runners
Instead of spewing the whole log to stdout lets just define them as
build artefacts so we can examine them later. Where we are running
check-tcg run it first as those tests are yet to be integrated into
meson. To avoid confusion we don't run multiple check-tcg tests at
once.
Reviewed-by: Thomas Huth <thuth@redhat.com> Signed-off-by: Alex Bennée <alex.bennee@linaro.org>
Message-Id: <20230124180127.1881110-18-alex.bennee@linaro.org>
linux-user blocks all signals while attempting to handle guest
signals (e.g. ABRT), which means that the default TERM sent by timeout
has no effect -- KILL instead.
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-Id: <20230117035701.168514-2-richard.henderson@linaro.org>
[AJB: expanded commit message from cover letter] Signed-off-by: Alex Bennée <alex.bennee@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org>
Message-Id: <20230124180127.1881110-17-alex.bennee@linaro.org>
Alex Bennée [Tue, 24 Jan 2023 18:01:07 +0000 (18:01 +0000)]
tests/tcg: skip the vma-pthread test on CI
We are getting a lot of failures that are not related to changes so
this could be a flaky test.
Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Alex Bennée <alex.bennee@linaro.org>
Message-Id: <20230124180127.1881110-16-alex.bennee@linaro.org>
Alex Bennée [Tue, 24 Jan 2023 18:01:06 +0000 (18:01 +0000)]
tests/docker: drop debian-tricore-cross's partial status
This image is perfectly capable of building QEMU, and indeed we do
that on gitlab. Drop the DOCKER_PARTIAL_IMAGES setting so we can also
test the gitlab build locally.
Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Signed-off-by: Alex Bennée <alex.bennee@linaro.org>
Message-Id: <20230124180127.1881110-15-alex.bennee@linaro.org>
tests/docker: Install flex in debian-tricore-cross
When flex is not available, binutils sources default to the
'missing' script, but the current script available is not in
the format expected by the 'configure' script:
$ ./configure
...
/usr/src/binutils/missing: Unknown `--run' option
Try `/usr/src/binutils/missing --help' for more information
configure: WARNING: `missing' script is too old or missing
...
checking for bison... bison -y
checking for flex... no
checking for lex... no
checking for flex... /usr/src/binutils/missing flex
Alex Bennée [Tue, 24 Jan 2023 18:01:01 +0000 (18:01 +0000)]
gitlab: add lsan suppression file to workaround tcmalloc issues
The up-coming upgrade to Fedora 37 will bring in libtcmalloc as a
dependency of libglusterfs which confuses our fuzz run. Rather than
disable the build lets use LSAN's suppression mechanism to prevent the
job from failing.
Signed-off-by: Alex Bennée <alex.bennee@linaro.org> Cc: Daniel P. Berrangé <berrange@redhat.com> Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Reviewed-by: Thomas Huth <thuth@redhat.com>
Message-Id: <20230124180127.1881110-10-alex.bennee@linaro.org>
Alex Bennée [Tue, 24 Jan 2023 18:00:56 +0000 (18:00 +0000)]
tests/unit: drop hacky race avoidance in test-io-channel-command
We don't need to play timing games to ensure one socat wins over the
other, just create the fifo they both can use before spawning the
processes. However in the process we need to disable two tests for
Windows platforms as we don't have an abstraction for mkfifo().
Resolves: https://gitlab.com/qemu-project/qemu/-/issues/1403 Signed-off-by: Alex Bennée <alex.bennee@linaro.org> Reviewed-by: Thomas Huth <thuth@redhat.com>
Message-Id: <20230124180127.1881110-5-alex.bennee@linaro.org>
Alex Bennée [Tue, 24 Jan 2023 18:00:55 +0000 (18:00 +0000)]
gitlab: just use plain --cc=clang for custom runner build
I think this was because older Ubuntu's didn't alias clang to whatever
the latest version was. They do now so lets use that and not break.
Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Alex Bennée <alex.bennee@linaro.org>
Message-Id: <20230124180127.1881110-4-alex.bennee@linaro.org>
Mark Cave-Ayland [Tue, 24 Jan 2023 18:00:54 +0000 (18:00 +0000)]
gitlab: add FF_SCRIPT_SECTIONS for timings
Suggested-by: Mark Cave-Ayland <mark.cave-ayland@ilande.co.uk> Signed-off-by: Mark Cave-Ayland <mark.cave-ayland@ilande.co.uk> Signed-off-by: Alex Bennée <alex.bennee@linaro.org> Reviewed-by: Thomas Huth <thuth@redhat.com> Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Reviewed-by: Daniel P. Berrangé <berrange@redhat.com>
Message-Id: <20230124180127.1881110-3-alex.bennee@linaro.org>
Alex Bennée [Tue, 24 Jan 2023 18:00:53 +0000 (18:00 +0000)]
scripts/ci: update gitlab-runner playbook to use latest runner
We were using quite and old runner on our machines and running into
issues with stalling jobs. Gitlab in the meantime now reliably provide
the latest packaged versions of the runner under a stable URL. This
update:
- creates a per-arch subdir for builds
- switches from binary tarballs to deb packages
- re-uses the same binary for the secondary runner
- updates distro check for second to 22.04
Note this script isn't fully idempotent as we end up accumulating
runners especially during testing. However we also want to be able to
run twice with different GitLab keys (e.g. project and personal) so I
think we just have to be mindful of that during testing.
Signed-off-by: Alex Bennée <alex.bennee@linaro.org> Acked-by: Richard Henderson <richard.henderson@linaro.org>
Message-Id: <20230124180127.1881110-2-alex.bennee@linaro.org>
* tag 'python-pull-request' of https://gitlab.com/jsnow/qemu:
python/qemu/machine: use socketpair() for QMP by default
python/qmp/legacy: make QEMUMonitorProtocol accept a socket
python/qmp/protocol: add open_with_socket()
python/qmp: increase read buffer size
python/machine: Fix AF_UNIX path too long on macOS
python: QEMUMachine: enable qmp accept timeout by default
Fix some typos
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Notably, the way the keys are named is specific for image files: The
filename is shown under "image", the BDS driver under "file format", and
the BDS length under "virtual size". This does not make much sense for
nodes that are not actually supposed to be guest images, like the /file
child node shown above.
Give bdrv_node_info_dump() a @protocol parameter that gives a hint that
the respective node is probably just used for data storage and does not
necessarily present the data for a VM guest disk. This renames the keys
so that with this patch, the output becomes:
image: test.qcow2
[...]
Child node '/file':
filename: test.qcow2
protocol type: file
file length: 192 KiB (197120 bytes)
disk size: 196 KiB
Format specific information:
extent size hint: 1048576
(Perhaps we should also rename "Format specific information", but I
could not come up with anything better that will not become problematic
if we guess wrong with the protocol "heuristic".)
This change affects iotest 302, which has protocol node information in
its reference output.
Signed-off-by: Hanna Reitz <hreitz@redhat.com>
Message-Id: <20220620162704.80987-13-hreitz@redhat.com> Reviewed-by: Kevin Wolf <kwolf@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com>
Hanna Reitz [Mon, 20 Jun 2022 16:27:03 +0000 (18:27 +0200)]
qemu-img: Let info print block graph
For every node in the backing chain, collect its BlockGraphInfo struct
using bdrv_query_block_graph_info(). Print all nodes' information,
indenting child nodes and labelling them with a path constructed from
the child names leading to the node from the root (e.g. /file/file).
Note that we open each image with BDRV_O_NO_BACKING, so its backing
child is omitted from this graph, and thus presented in the previous
manner: By simply concatenating all images' information, separated with
blank lines.
This affects two iotests:
- 065: Here we try to get the format node's format specific information.
The pre-patch code does so by taking all lines from "Format specific
information:" until an empty line. This format specific information
is no longer followed by an empty line, though, but by child node
information, so limit the range by "Child node '/file':".
- 302: Calls qemu_img() for qemu-img info directly, which does not
filter the output, so the child node information ends up in the
output.
Signed-off-by: Hanna Reitz <hreitz@redhat.com>
Message-Id: <20220620162704.80987-12-hreitz@redhat.com> Reviewed-by: Kevin Wolf <kwolf@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com>
Hanna Reitz [Mon, 20 Jun 2022 16:27:02 +0000 (18:27 +0200)]
iotests/106, 214, 308: Read only one size line
These tests read size information (sometimes disk size, sometimes
virtual size) from qemu-img info's output. Once qemu-img starts
printing info about child nodes, we are going to see multiple instances
of that per image, but these tests are only interested in the first one,
so use "head -n 1" to get it.
Signed-off-by: Hanna Reitz <hreitz@redhat.com>
Message-Id: <20220620162704.80987-11-hreitz@redhat.com> Reviewed-by: Kevin Wolf <kwolf@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com>
Hanna Reitz [Mon, 20 Jun 2022 16:27:01 +0000 (18:27 +0200)]
iotests: Filter child node information
Before we let qemu-img info print child node information, have
common.filter, common.rc, and iotests.py filter it from the test output
so we get as few reference output changes as possible.
Signed-off-by: Hanna Reitz <hreitz@redhat.com>
Message-Id: <20220620162704.80987-10-hreitz@redhat.com> Tested-by: Kevin Wolf <kwolf@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com>
Hanna Reitz [Mon, 20 Jun 2022 16:27:00 +0000 (18:27 +0200)]
block/qapi: Add indentation to bdrv_node_info_dump()
In order to let qemu-img info present a block graph, add a parameter to
bdrv_node_info_dump() and bdrv_image_info_specific_dump() so that the
information of nodes below the root level can be given an indentation.
Signed-off-by: Hanna Reitz <hreitz@redhat.com>
Message-Id: <20220620162704.80987-9-hreitz@redhat.com> Reviewed-by: Kevin Wolf <kwolf@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com>
Hanna Reitz [Mon, 20 Jun 2022 16:26:59 +0000 (18:26 +0200)]
block/qapi: Introduce BlockGraphInfo
Introduce a new QAPI type BlockGraphInfo and an associated
bdrv_query_block_graph_info() function that recursively gathers
BlockNodeInfo objects through a block graph.
A follow-up patch is going to make "qemu-img info" use this to print
information about all nodes that are (usually implicitly) opened for a
given image file.
Signed-off-by: Hanna Reitz <hreitz@redhat.com>
Message-Id: <20220620162704.80987-8-hreitz@redhat.com> Reviewed-by: Kevin Wolf <kwolf@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com>
Hanna Reitz [Mon, 20 Jun 2022 16:26:58 +0000 (18:26 +0200)]
block/qapi: Let bdrv_query_image_info() recurse
There is no real reason why bdrv_query_image_info() should generally not
recurse. The ImageInfo struct has a pointer to the backing image, so it
should generally be filled, unless the caller explicitly opts out.
This moves the recursing code from bdrv_block_device_info() into
bdrv_query_image_info().
Signed-off-by: Hanna Reitz <hreitz@redhat.com>
Message-Id: <20220620162704.80987-7-hreitz@redhat.com> Reviewed-by: Kevin Wolf <kwolf@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com>
Hanna Reitz [Mon, 20 Jun 2022 16:26:57 +0000 (18:26 +0200)]
qemu-img: Use BlockNodeInfo
qemu-img info never uses ImageInfo's backing-image field, because it
opens the backing chain one by one with BDRV_O_NO_BACKING, and prints
all backing chain nodes' information consecutively. Use BlockNodeInfo
to make it clear that we only print information about a single node, and
that we are not using the backing-image field.
Notably, bdrv_image_info_dump() does not evaluate the backing-image
field, so we can easily make it take a BlockNodeInfo pointer (and
consequentially rename it to bdrv_node_info_dump()). It makes more
sense this way, because again, the interface now makes it syntactically
clear that backing-image is ignored by this function.
Signed-off-by: Hanna Reitz <hreitz@redhat.com>
Message-Id: <20220620162704.80987-6-hreitz@redhat.com> Reviewed-by: Kevin Wolf <kwolf@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com>
Hanna Reitz [Mon, 20 Jun 2022 16:26:56 +0000 (18:26 +0200)]
block: Split BlockNodeInfo off of ImageInfo
ImageInfo sometimes contains flat information, and sometimes it does
not. Split off a BlockNodeInfo struct, which only contains information
about a single node and has no link to the backing image.
We do this so we can extend BlockNodeInfo to a BlockGraphInfo struct,
which has links to all child nodes, not just the backing node. It would
be strange to base BlockGraphInfo on ImageInfo, because then this
extended struct would have two links to the backing node (one in
BlockGraphInfo as one of all the child links, and one in ImageInfo).
Furthermore, it is quite common to ignore the backing-image field
altogether: bdrv_query_image_info() does not set it, and
bdrv_image_info_dump() does not evaluate it. That signals that we
should have different structs for describing a single node and one that
has a link to the backing image.
Still, bdrv_query_image_info() and bdrv_image_info_dump() are not
changed too much in this patch. Follow-up patches will handle them.
Signed-off-by: Hanna Reitz <hreitz@redhat.com>
Message-Id: <20220620162704.80987-5-hreitz@redhat.com> Reviewed-by: Kevin Wolf <kwolf@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com>
Hanna Reitz [Mon, 20 Jun 2022 16:26:55 +0000 (18:26 +0200)]
block/vmdk: Change extent info type
VMDK's implementation of .bdrv_get_specific_info() returns information
about its extent files, ostensibly in the form of ImageInfo objects.
However, it does not get this information through
bdrv_query_image_info(), but fills only a select few fields with custom
information that does not always match the fields' purposes.
For example, @format, which is supposed to be a block driver name, is
filled with the extent type, e.g. SPARSE or FLAT.
In ImageInfo, @compressed shows whether the data that can be seen in the
image is stored in compressed form or not. For example, a compressed
qcow2 image will store compressed data in its data file, but when
accessing the qcow2 node, you will see normal data. This is not how
VMDK uses the @compressed field for its extent files: Instead, it
signifies whether accessing the extent file will yield compressed data
(which the VMDK driver then (de-)compresses).
Create a new structure to represent the extent information. This allows
us to clarify the fields' meanings, and it clearly shows that these are
not complete ImageInfo objects. (That is, if a user wants an extent
file's ImageInfo object, they will need to query it separately, and will
not get it from ImageInfoSpecificVmdk.extents.)
Note that this removes the last use of ['ImageInfo'] (i.e. an array of
ImageInfo objects), so the QAPI generator will no longer generate
ImageInfoList by default. However, we use it in qemu-img.c, so we need
to create a dummy object to force the generate to create that type,
similarly to DummyForceArrays in machine.json (introduced in commit 9f08c8ec73878122ad4b061ed334f0437afaaa32 ("qapi: Lazy creation of array
types")).
Signed-off-by: Hanna Reitz <hreitz@redhat.com>
Message-Id: <20220620162704.80987-4-hreitz@redhat.com> Reviewed-by: Kevin Wolf <kwolf@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com>
Hanna Reitz [Mon, 20 Jun 2022 16:26:54 +0000 (18:26 +0200)]
block/file: Add file-specific image info
Add some (optional) information that the file driver can provide for
image files, namely the extent size hint.
Signed-off-by: Hanna Reitz <hreitz@redhat.com>
Message-Id: <20220620162704.80987-3-hreitz@redhat.com> Reviewed-by: Kevin Wolf <kwolf@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com>
Hanna Reitz [Mon, 20 Jun 2022 16:26:53 +0000 (18:26 +0200)]
block: Improve empty format-specific info dump
When a block driver supports obtaining format-specific information, but
that object only contains optional fields, it is possible that none of
them are present, so that dump_qobject() (called by
bdrv_image_info_specific_dump()) will not print anything.
The callers of bdrv_image_info_specific_dump() put a header above this
information ("Format specific information:\n"), which will look strange
when there is nothing below. Modify bdrv_image_info_specific_dump() to
print this header instead of its callers, and only if there is indeed
something to be printed.
Signed-off-by: Hanna Reitz <hreitz@redhat.com>
Message-Id: <20220620162704.80987-2-hreitz@redhat.com> Reviewed-by: Kevin Wolf <kwolf@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com>
The inlined nbd_readXX() functions call beXX_to_cpu(), themselves
declared in <qemu/bswap.h>. This fixes when refactoring:
In file included from ../../block/nbd.c:44:
include/block/nbd.h: In function 'nbd_read16':
include/block/nbd.h:383:12: error: implicit declaration of function 'be16_to_cpu' [-Werror=implicit-function-declaration]
383 | *val = be##bits##_to_cpu(*val); \
| ^~
include/block/nbd.h:387:1: note: in expansion of macro 'DEF_NBD_READ_N'
387 | DEF_NBD_READ_N(16) /* Defines nbd_read16(). */
| ^~~~~~~~~~~~~~
Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org>
Message-Id: <20221125175328.48539-1-philmd@linaro.org> Reviewed-by: Vladimir Sementsov-Ogievskiy <vsementsov@yandex-team.ru> Reviewed-by: Kevin Wolf <kwolf@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com>
block: Rename bdrv_load/save_vmstate() to bdrv_co_load/save_vmstate()
Since these functions always run in coroutine context, adjust
their name to include "_co_", just like all other BlockDriver callbacks.
No functional change intended.
Signed-off-by: Emanuele Giuseppe Esposito <eesposit@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com>
Message-Id: <20230113204212.359076-15-kwolf@redhat.com> Reviewed-by: Emanuele Giuseppe Esposito <eesposit@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com>
block: Convert bdrv_debug_event() to co_wrapper_mixed
bdrv_debug_event() is categorized as an I/O function, and it currently
doesn't run in a coroutine. We should let it take a graph rdlock since
it traverses the block nodes graph, which however is only possible in a
coroutine.
Therefore turn it into a co_wrapper_mixed to move the actual function
into a coroutine where the lock can be taken.
Signed-off-by: Emanuele Giuseppe Esposito <eesposit@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com>
Message-Id: <20230113204212.359076-14-kwolf@redhat.com> Reviewed-by: Emanuele Giuseppe Esposito <eesposit@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com>
bdrv_lock_medium() is categorized as an I/O function, and it currently
doesn't run in a coroutine. We should let it take a graph rdlock since
it traverses the block nodes graph, which however is only possible in a
coroutine.
The only caller of this function is blk_lock_medium(). Therefore make
blk_lock_medium() a co_wrapper, so that it always creates a new
coroutine, and then make bdrv_lock_medium() a coroutine_fn where the
lock can be taken.
Signed-off-by: Emanuele Giuseppe Esposito <eesposit@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com>
Message-Id: <20230113204212.359076-13-kwolf@redhat.com> Reviewed-by: Emanuele Giuseppe Esposito <eesposit@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com>
bdrv_eject() is categorized as an I/O function, and it currently
doesn't run in a coroutine. We should let it take a graph rdlock since
it traverses the block nodes graph, which however is only possible in a
coroutine.
The only caller of this function is blk_eject(). Therefore make
blk_eject() a co_wrapper, so that it always creates a new coroutine, and
then make bdrv_eject() coroutine_fn where the lock can be taken.
Signed-off-by: Emanuele Giuseppe Esposito <eesposit@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com>
Message-Id: <20230113204212.359076-12-kwolf@redhat.com> Reviewed-by: Emanuele Giuseppe Esposito <eesposit@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com>
block: Convert bdrv_get_info() to co_wrapper_mixed
bdrv_get_info() is categorized as an I/O function, and it currently
doesn't run in a coroutine. We should let it take a graph rdlock since
it traverses the block nodes graph, which however is only possible in a
coroutine.
Therefore turn it into a co_wrapper to move the actual function into a
coroutine where the lock can be taken.
Signed-off-by: Emanuele Giuseppe Esposito <eesposit@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com>
Message-Id: <20230113204212.359076-11-kwolf@redhat.com> Reviewed-by: Emanuele Giuseppe Esposito <eesposit@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com>
block: Convert bdrv_get_allocated_file_size() to co_wrapper
bdrv_get_allocated_file_size() is categorized as an I/O function, and it
currently doesn't run in a coroutine. We should let it take a graph
rdlock since it traverses the block nodes graph, which however is only
possible in a coroutine.
Therefore turn it into a co_wrapper to move the actual function into a
coroutine where the lock can be taken.
Signed-off-by: Emanuele Giuseppe Esposito <eesposit@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com>
Message-Id: <20230113204212.359076-10-kwolf@redhat.com> Reviewed-by: Emanuele Giuseppe Esposito <eesposit@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com>
block: use bdrv_co_refresh_total_sectors when possible
In some places we are sure we are always running in a
coroutine, therefore it's useless to call the generated_co_wrapper,
instead call directly the _co_ function.
Signed-off-by: Emanuele Giuseppe Esposito <eesposit@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com>
Message-Id: <20230113204212.359076-9-kwolf@redhat.com> Reviewed-by: Emanuele Giuseppe Esposito <eesposit@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com>
block-backend: use bdrv_getlength instead of blk_getlength
The only difference is that blk_ checks if the block is available,
but this check is already performed above in blk_check_byte_request().
This is in preparation for the graph rdlock, which will be taken
by both the callers of blk_check_byte_request() and blk_getlength().
Signed-off-by: Emanuele Giuseppe Esposito <eesposit@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com>
Message-Id: <20230113204212.359076-8-kwolf@redhat.com> Reviewed-by: Emanuele Giuseppe Esposito <eesposit@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com>
block: Convert bdrv_refresh_total_sectors() to co_wrapper_mixed
BlockDriver->bdrv_getlength is categorized as IO callback, and it
currently doesn't run in a coroutine. We should let it take a graph
rdlock since the callback traverses the block nodes graph, which however
is only possible in a coroutine.
Therefore turn it into a co_wrapper to move the actual function into a
coroutine where the lock can be taken.
Because now this function creates a new coroutine and polls, we need to
take the AioContext lock where it is missing, for the only reason that
internally co_wrapper calls AIO_WAIT_WHILE and it expects to release the
AioContext lock.
This is especially messy when a co_wrapper creates a coroutine and polls
in bdrv_open_driver, because this function has so many callers in so
many context that it can easily lead to deadlocks. Therefore the new
rule for bdrv_open_driver is that the caller must always hold the
AioContext lock of the given bs (except if it is a coroutine), because
the function calls bdrv_refresh_total_sectors() which is now a
co_wrapper.
Once the rwlock is ultimated and placed in every place it needs to be,
we will poll using AIO_WAIT_WHILE_UNLOCKED and remove the AioContext
lock.
Signed-off-by: Emanuele Giuseppe Esposito <eesposit@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com>
Message-Id: <20230113204212.359076-7-kwolf@redhat.com> Reviewed-by: Emanuele Giuseppe Esposito <eesposit@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com>
block: Rename refresh_total_sectors to bdrv_refresh_total_sectors
The name is not good, not the least because we are going to convert this
to a generated co_wrapper, which adds a _co infix after the first part
of the name.
No functional change intended.
Signed-off-by: Emanuele Giuseppe Esposito <eesposit@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com>
Message-Id: <20230113204212.359076-6-kwolf@redhat.com> Reviewed-by: Emanuele Giuseppe Esposito <eesposit@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com>
bdrv_is_inserted() is categorized as an I/O function, and it currently
doesn't run in a coroutine. We should let it take a graph rdlock since
it traverses the block nodes graph, which however is only possible in a
coroutine.
Therefore turn it into a co_wrapper to move the actual function into a
coroutine where the lock can be taken.
At the same time, add also blk_is_inserted as co_wrapper_mixed, since it
is called in both coroutine and non-coroutine contexts.
Because now this function creates a new coroutine and polls, we need to
take the AioContext lock where it is missing, for the only reason that
internally c_w_mixed_bdrv_rdlock calls AIO_WAIT_WHILE and it expects to
release the AioContext lock. Once the rwlock is ultimated and placed in
every place it needs to be, we will poll using AIO_WAIT_WHILE_UNLOCKED
and remove the AioContext lock.
Signed-off-by: Emanuele Giuseppe Esposito <eesposit@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com>
Message-Id: <20230113204212.359076-5-kwolf@redhat.com> Reviewed-by: Emanuele Giuseppe Esposito <eesposit@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com>
BlockDriver->bdrv_io_unplug is categorized as IO callback, and it
currently doesn't run in a coroutine. We should let it take a graph
rdlock since the callback traverses the block nodes graph, which however
is only possible in a coroutine.
The only caller of this function is blk_io_unplug(), therefore make
blk_io_unplug() a co_wrapper, so that we're always running in a
coroutine where the lock can be taken.
Signed-off-by: Emanuele Giuseppe Esposito <eesposit@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com>
Message-Id: <20230113204212.359076-4-kwolf@redhat.com> Reviewed-by: Emanuele Giuseppe Esposito <eesposit@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com>
BlockDriver->bdrv_io_plug is categorized as IO callback, and it
currently doesn't run in a coroutine. We should let it take a graph
rdlock since the callback traverses the block nodes graph, which however
is only possible in a coroutine.
The only caller of this function is blk_io_plug(), therefore make
blk_io_plug() a co_wrapper, so that we're always running in a coroutine
where the lock can be taken.
Signed-off-by: Emanuele Giuseppe Esposito <eesposit@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com>
Message-Id: <20230113204212.359076-3-kwolf@redhat.com> Reviewed-by: Emanuele Giuseppe Esposito <eesposit@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com>
Just omit the various 'return' when the return type is void.
Signed-off-by: Emanuele Giuseppe Esposito <eesposit@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com>
Message-Id: <20230113204212.359076-2-kwolf@redhat.com> Reviewed-by: Emanuele Giuseppe Esposito <eesposit@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com>
Kevin Wolf [Thu, 12 Jan 2023 19:14:54 +0000 (20:14 +0100)]
qemu-iotests: Test qemu-img bitmap/commit exit code on error
This tests that when an error happens while writing back bitmaps to the
image file in qcow2_inactivate(), 'qemu-img bitmap/commit' actually
return an error value in their exit code instead of making the operation
look successful to scripts.
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
Message-Id: <20230112191454.169353-5-kwolf@redhat.com> Reviewed-by: Hanna Czenczek <hreitz@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com>
Thomas Huth [Mon, 30 Jan 2023 10:44:44 +0000 (11:44 +0100)]
gitlab-ci.d/buildtest: Merge the --without-default-* jobs
Let's safe some CI minutes by merging these two jobs. We can now
also drop "--disable-capstone" since the capstone submodule has
been removed a while ago. We should rather test --disable-fdt now
to check a compilation without the "dtc" submodule (for this we
have to drop i386-softmmu from the target list unfortunately).
Additionally, the qtests with s390x and sh4 are not read for
"--without-default-devices" yet, so we can only test mips64 and
avr here now.
Message-Id: <20230130104446.1286773-5-thuth@redhat.com> Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Reviewed-by: Fabiano Rosas <farosas@suse.de> Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Signed-off-by: Thomas Huth <thuth@redhat.com>
Thomas Huth [Mon, 30 Jan 2023 10:44:43 +0000 (11:44 +0100)]
tests/qtest/display-vga-test: Add proper checks if a device is available
display-vga-test currently tries to guess the usable VGA devices
according to the target architecture that is used for the test.
This of course does not work if QEMU has been built with the
"--without-default-devices" configure switch. To fix this, use the
qtest_has_device() function for the decision instead. This way
we can also consolidate most of the test functions into one single
function (that takes a parameter with the device name now), except
for the multihead test that tries to instantiate two devices and
thus is a little bit different.
Message-Id: <20230130104446.1286773-4-thuth@redhat.com> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Thomas Huth <thuth@redhat.com>
Thomas Huth [Mon, 30 Jan 2023 10:44:41 +0000 (11:44 +0100)]
gitlab-ci.d/buildtest: Remove ppc-softmmu from the clang-system job
We are also compile-testing ppc64-softmmu with clang in the "tsan-build"
job, and ppc64-softmmu covers pretty much the same code as ppc-softmmu,
so we should not lose much test coverage here by removing ppc-softmmu
from the "clang-system" job.
Message-Id: <20230130104446.1286773-2-thuth@redhat.com> Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Signed-off-by: Thomas Huth <thuth@redhat.com>
qapi, audio: Make introspection reflect build configuration more closely
Currently the -audiodev accepts any audiodev type regardless of what is
built in to QEMU. An error only occurs later at runtime when a sound
device tries to use the audio backend.
With this change QEMU will immediately reject -audiodev args that are
not compiled into the binary. The QMP schema will also be introspectable
to identify what is compiled in.
This also helps to avoid compiling code that is not required in the
binary. Note: When building the audiodevs as modules, the patch only
compiles out code for modules that we don't build at all.
Signed-off-by: Daniel P. Berrangé <berrange@redhat.com>
[thuth: Rebase, take sndio and dbus devices into account]
Message-Id: <20230123083957.20349-3-thuth@redhat.com> Signed-off-by: Thomas Huth <thuth@redhat.com>
Way back in QEMU 4.0, the -audiodev command line option was introduced
for configuring audio backends. This CLI option does not use QemuOpts
so it is not visible for introspection in 'query-command-line-options',
instead using the QAPI Audiodev type. Unfortunately there is also no
QMP command that uses the Audiodev type, so it is not introspectable
with 'query-qmp-schema' either.
This introduces a 'query-audiodev' command that simply reflects back
the list of configured -audiodev command line options. This alone is
maybe not very useful by itself, but it makes Audiodev introspectable
via 'query-qmp-schema', so that libvirt (and other upper layer tools)
can discover the available audiodevs.
Signed-off-by: Daniel P. Berrangé <berrange@redhat.com>
[thuth: Update for upcoming QEMU v8.0, and use QAPI_LIST_PREPEND]
Message-Id: <20230123083957.20349-2-thuth@redhat.com> Signed-off-by: Thomas Huth <thuth@redhat.com>
Marcel Apfelbaum [Mon, 23 Jan 2023 17:42:05 +0000 (17:42 +0000)]
docs/pcie.txt: Replace ioh3420 with pcie-root-port
Do not mention ioh3420 in the "how to" doc.
The device still works and can be used by already
existing setups, but no need to be mentioned.
Suggested-by: Andrew Jones <drjones@redhat.com> Reviewed-by: Laszlo Ersek <lersek@redhat.com> Signed-off-by: Marcel Apfelbaum <marcel@redhat.com> Signed-off-by: Daniel P. Berrangé <berrange@redhat.com>
Message-Id: <20230123174205.683979-1-berrange@redhat.com> Reviewed-by: Michael S. Tsirkin <mst@redhat.com> Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
The nested event loop is broken by design. It's only user was removed.
Drop the code as well so that nobody ever tries to use it again.
I had to fix a couple of trivial conflicts around return values because
of 025faa872bcf ("vhost-user: stick to -errno error return convention").
Signed-off-by: Greg Kurz <groug@kaod.org>
Message-Id: <20230119172424.478268-3-groug@kaod.org> Reviewed-by: Michael S. Tsirkin <mst@redhat.com> Signed-off-by: Michael S. Tsirkin <mst@redhat.com> Acked-by: Maxime Coquelin <maxime.coquelin@redhat.com>
Motivation : this is breaking vhost-user with DPDK as reported in [0].
Received unexpected msg type. Expected 22 received 40
Fail to update device iotlb
Received unexpected msg type. Expected 40 received 22
Received unexpected msg type. Expected 22 received 11
Fail to update device iotlb
Received unexpected msg type. Expected 11 received 22
vhost VQ 1 ring restore failed: -71: Protocol error (71)
Received unexpected msg type. Expected 22 received 11
Fail to update device iotlb
Received unexpected msg type. Expected 11 received 22
vhost VQ 0 ring restore failed: -71: Protocol error (71)
unable to start vhost net: 71: falling back on userspace virtio
The failing sequence that leads to the first error is :
- QEMU sends a VHOST_USER_GET_STATUS (40) request to DPDK on the master
socket
- QEMU starts a nested event loop in order to wait for the
VHOST_USER_GET_STATUS response and to be able to process messages from
the slave channel
- DPDK sends a couple of legitimate IOTLB miss messages on the slave
channel
- QEMU processes each IOTLB request and sends VHOST_USER_IOTLB_MSG (22)
updates on the master socket
- QEMU assumes to receive a response for the latest VHOST_USER_IOTLB_MSG
but it gets the response for the VHOST_USER_GET_STATUS instead
The subsequent errors have the same root cause : the nested event loop
breaks the order by design. It lures QEMU to expect responses to the
latest message sent on the master socket to arrive first.
Since this was only needed for DAX enablement which is still not merged
upstream, just drop the code for now. A working solution will have to
be merged later on. Likely protect the master socket with a mutex
and service the slave channel with a separate thread, as discussed with
Maxime in the mail thread below.
Reported-by: Yanghang Liu <yanghliu@redhat.com> Buglink: https://bugzilla.redhat.com/show_bug.cgi?id=2155173 Signed-off-by: Greg Kurz <groug@kaod.org>
Message-Id: <20230119172424.478268-2-groug@kaod.org> Reviewed-by: Michael S. Tsirkin <mst@redhat.com> Signed-off-by: Michael S. Tsirkin <mst@redhat.com> Acked-by: Stefan Hajnoczi <stefanha@redhat.com> Acked-by: Maxime Coquelin <maxime.coquelin@redhat.com>
Thomas Huth [Wed, 18 Jan 2023 12:51:32 +0000 (13:51 +0100)]
tests/qtest/bios-tables-test: Make the test less verbose by default
We are facing the issues that our test logs in the gitlab CI are
too big (and thus cut off). The bios-tables-test is one of the few
qtests that prints many lines of output by default when running with
V=1, so it contributes to this problem. Almost all other qtests are
silent with V=1 and only print debug messages with V=2 and higher.
Thus let's change the bios-tables-test to behave more like the
other tests and only print the debug messages with V=2 (or higher).
Signed-off-by: Thomas Huth <thuth@redhat.com>
Message-Id: <20230118125132.1694469-1-thuth@redhat.com> Reviewed-by: Michael S. Tsirkin <mst@redhat.com> Signed-off-by: Michael S. Tsirkin <mst@redhat.com> Reviewed-by: Daniel P. Berrangé <berrange@redhat.com> Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Reviewed-by: Igor Mammedov <imammedo@redhat.com>
Use the proper QOM type definition instead of magic string.
This also helps during eventual refactor while using git-grep.
Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org>
Message-Id: <20230117193014.83502-1-philmd@linaro.org> Reviewed-by: Michael S. Tsirkin <mst@redhat.com> Signed-off-by: Michael S. Tsirkin <mst@redhat.com> Reviewed-by: Eric Auger <eric.auger@redhat.com>
The VHOST_USER_ADD/REM_MEM_REG requests should be categorized into
non-vring specific messages, and should be sent only once.
Signed-off-by: Minghao Yuan <yuanmh12@chinatelecom.cn>
Message-Id: <20230123122119.194347-1-yuanmh12@chinatelecom.cn> Reviewed-by: Michael S. Tsirkin <mst@redhat.com> Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Igor Mammedov [Thu, 12 Jan 2023 14:03:11 +0000 (15:03 +0100)]
pcihp: generate populated non-hotpluggble slot descriptions on non-hotplug path
Generating slots descriptions populated by non-hotpluggable devices
is akward at best and complicates hotplug path (build_append_pcihp_slots)
needlessly, and builds only dynamic _DSM for such slots which is overlkill.
Clean it up and let non-hotplug path (build_append_pci_bus_devices)
to handle that task.
Such clean up effectively drops dynamic _DSM methods on non-hotpluggable
slots (even though bus itself is hotpluggable), but in practice it
affects only built-in devices (ide controllers/various bridges) that don't
use acpi-index anyways so effectively it doesn't matter (NICs are hotpluggble).
Follow up series will add static _DSM for non-hotpluggble devices/buses
that will not depend on ACPI PCI hotplug at all, and potentially would
allows us to reuse non-hotplug path elsewhere (PBX/microvm/arm-virt),
including new support for acpi-index for non-hotpluggable devices.
Signed-off-by: Igor Mammedov <imammedo@redhat.com>
Message-Id: <20230112140312.3096331-40-imammedo@redhat.com> Reviewed-by: Michael S. Tsirkin <mst@redhat.com> Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Igor Mammedov [Thu, 12 Jan 2023 14:03:10 +0000 (15:03 +0100)]
tests: acpi: whitelist DSDT before moving non-hotpluggble slots description from hotplug path
Signed-off-by: Igor Mammedov <imammedo@redhat.com>
Message-Id: <20230112140312.3096331-39-imammedo@redhat.com> Reviewed-by: Michael S. Tsirkin <mst@redhat.com> Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Igor Mammedov [Thu, 12 Jan 2023 14:03:08 +0000 (15:03 +0100)]
pcihp: acpi: ignore coldplugged bridges when composing hotpluggable slots
coldplugged bridges are not unpluggable, so there is no need
to describe slots where they are plugged as hotpluggable. To
that effect we have a condition that marks slot as non-hotpluggable
if it's populated by coldplugged bridge and prevents generation
_SUN/_EJ0 objects for it. That leaves dynamic _DSM method on
such slot (which also depends on BSEL and pcihp hardware).
This _DSM method provides only dynamic acpi-index support so far,
which is not actually used/supported by linux kernel for bridges
and it's doubtful there will be need for it at all.
So it's rather pointless to generate acpi-index related AML
for bridges and we can simplify hotplug slots generator a bit
more by completely ignoring coldplugged bridges on hotplug path.
Another point in favor of dropping dynamic _DSM support, is
that we can replace it with static _DSM if necessary since
a slot with bridge can't change during VM runtime and without
any dependency on ACPI PCI hotplug at that.
Later I plan to implement bridge specific static _DSM
PCI Firmware Specification 3.2
4.6.5. _DSM for Ignoring PCI Boot Configurations
part of spec, to fix longstanding issue with fixed IO/MEM
resource assignment that often leads to hotplugged device
being in-operational within the guest due limited IO/MEM
windows programmed on bridge at boot time.
Signed-off-by: Igor Mammedov <imammedo@redhat.com>
Message-Id: <20230112140312.3096331-37-imammedo@redhat.com> Reviewed-by: Michael S. Tsirkin <mst@redhat.com> Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Igor Mammedov [Thu, 12 Jan 2023 14:03:07 +0000 (15:03 +0100)]
tests: acpi: whitelist DSDT blobs before removing dynamic _DSM on coldplugged bridges
Signed-off-by: Igor Mammedov <imammedo@redhat.com>
Message-Id: <20230112140312.3096331-36-imammedo@redhat.com> Reviewed-by: Michael S. Tsirkin <mst@redhat.com> Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Igor Mammedov [Thu, 12 Jan 2023 14:03:05 +0000 (15:03 +0100)]
pcihp: acpi: decouple hotplug and generic slots description
Split build_append_pci_bus_devices() onto generic part that builds
AML descriptions only for populated slots which is applicable to
both hotplug disabled and enabled bridges. And a hotplug only
part that complements generic AML with hotplug depended bits
(that depend on BSEL), like _SUN/_EJ0 entries, dynamic _DSM.
Hotplug part, will generate full 'Device' descriptors for
non-populated slots (like it used to be) and complementary
'Scope' descriptors for populated slots that are hotplug capable.
i.e. something like this:
- ...
+ Name (BSEL, 0x03)
+ Scope (S00)
+ {
+ Name (ASUN, Zero)
+ Method (_DSM, 4, Serialized) // _DSM: Device-Specific Method
+ {
+ Local0 = Package (0x02)
+ {
+ BSEL,
+ ASUN
+ }
+ Return (PDSM (Arg0, Arg1, Arg2, Arg3, Local0))
+ }
+ [ ... other hotplug depended bits ]
+ }
While generic build_append_pci_bus_devices() still calls hotplug part at
its end it doesn't really depend on any hotplug bits anymore and later
both could be completely separated when it's necessary.
Main benefit though is that both build_append_pci_bus_devices() and
build_append_pcihp_slots() become more readable and it makes easier
to modify them with less risk of affecting another part. Also it opens
possibility to re-use generic part elsewhere (microvm, arm/virt).
Signed-off-by: Igor Mammedov <imammedo@redhat.com>
Message-Id: <20230112140312.3096331-34-imammedo@redhat.com> Reviewed-by: Michael S. Tsirkin <mst@redhat.com> Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Igor Mammedov [Thu, 12 Jan 2023 14:03:04 +0000 (15:03 +0100)]
tests: acpi: whitelist DSDT before decoupling PCI hotplug code from basic slots description
Signed-off-by: Igor Mammedov <imammedo@redhat.com>
Message-Id: <20230112140312.3096331-33-imammedo@redhat.com> Reviewed-by: Michael S. Tsirkin <mst@redhat.com> Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Igor Mammedov [Thu, 12 Jan 2023 14:03:03 +0000 (15:03 +0100)]
pcihp: isolate rule whether slot should be described in DSDT
Signed-off-by: Igor Mammedov <imammedo@redhat.com>
Message-Id: <20230112140312.3096331-32-imammedo@redhat.com> Reviewed-by: Michael S. Tsirkin <mst@redhat.com> Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Igor Mammedov [Thu, 12 Jan 2023 14:03:02 +0000 (15:03 +0100)]
pci: make sure pci_bus_is_express() won't error out with "discards ‘const’ qualifier"
function doesn't need RW aceess to passed in bus pointer,
make it const.
Signed-off-by: Igor Mammedov <imammedo@redhat.com>
Message-Id: <20230112140312.3096331-31-imammedo@redhat.com> Reviewed-by: Michael S. Tsirkin <mst@redhat.com> Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Igor Mammedov [Thu, 12 Jan 2023 14:03:01 +0000 (15:03 +0100)]
pcihp: make bridge describe itself using AcpiDevAmlIfClass:build_dev_aml
simplify build_append_pci_bus_devices() a bit by handling bridge
specific logic in bridge dedicated AcpiDevAmlIfClass::build_dev_aml
callback.
Signed-off-by: Igor Mammedov <imammedo@redhat.com>
Message-Id: <20230112140312.3096331-30-imammedo@redhat.com> Reviewed-by: Michael S. Tsirkin <mst@redhat.com> Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Igor Mammedov [Thu, 12 Jan 2023 14:03:00 +0000 (15:03 +0100)]
pci: acpi: wire up AcpiDevAmlIf interface to generic bridge
... so that the concrete impl. won't has to duplicate it
every time. By default it doesn't do anything unless leaf class
defines and sets AcpiDevAmlIfClass::build_dev_aml handler.
Signed-off-by: Igor Mammedov <imammedo@redhat.com>
Message-Id: <20230112140312.3096331-29-imammedo@redhat.com> Reviewed-by: Michael S. Tsirkin <mst@redhat.com> Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Igor Mammedov [Thu, 12 Jan 2023 14:02:59 +0000 (15:02 +0100)]
x86: pcihp: acpi: prepare slot ignore rule to work with self describing bridges
Before switching pci bridges to AcpiDevAmlIf interface, ensure that
ignored slots are handled correctly.
(existing rule works but only if bridge doesn't have AcpiDevAmlIf interface).
While at it rewrite related comments to be less confusing (hopefully).
Signed-off-by: Igor Mammedov <imammedo@redhat.com>
Message-Id: <20230112140312.3096331-28-imammedo@redhat.com> Reviewed-by: Michael S. Tsirkin <mst@redhat.com> Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Igor Mammedov [Thu, 12 Jan 2023 14:02:58 +0000 (15:02 +0100)]
tests: acpi: update expected blobs
previous commit added endpoint devices to bridge testcases,
which exposes extra non-hotpluggable slot in DSDT on bus where
hotplug is not available.
It should look like this (numbers may vary):
Igor Mammedov [Thu, 12 Jan 2023 14:02:57 +0000 (15:02 +0100)]
tests: acpi: add endpoint devices to bridges
to make sure that they are enumerated or ignored as expected
Signed-off-by: Igor Mammedov <imammedo@redhat.com>
Message-Id: <20230112140312.3096331-26-imammedo@redhat.com> Reviewed-by: Michael S. Tsirkin <mst@redhat.com> Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Igor Mammedov [Thu, 12 Jan 2023 14:02:56 +0000 (15:02 +0100)]
whitelist DSDT before adding endpoint devices to bridge testcases
Signed-off-by: Igor Mammedov <imammedo@redhat.com>
Message-Id: <20230112140312.3096331-25-imammedo@redhat.com> Reviewed-by: Michael S. Tsirkin <mst@redhat.com> Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
* due to ("pcihp: do not put empty PCNT in DSDT") in the most Q35 tests
...
{
Name (_ADR, 0x001F0003) // _ADR: Address
}
-
- Method (PCNT, 0, NotSerialized)
- {
- }
}
}
Igor Mammedov [Thu, 12 Jan 2023 14:02:54 +0000 (15:02 +0100)]
pcihp: do not put empty PCNT in DSDT
count number of PCNT methods that actually call Notify
and if there aren't any, drop PCNT altogether.
It mostly affects 'Q35' tests where there is no root-ports
/bridges attached and 'PC' machine when ACPI PCI hotplug is
completely disabled.
Signed-off-by: Igor Mammedov <imammedo@redhat.com>
Message-Id: <20230112140312.3096331-23-imammedo@redhat.com> Reviewed-by: Michael S. Tsirkin <mst@redhat.com> Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Igor Mammedov [Thu, 12 Jan 2023 14:02:53 +0000 (15:02 +0100)]
pcihp: compose PCNT callchain right before its user _GPE._E01
it's a stepping stone to making build_append_pci_bus_devices() suitable
for AcpiDevAmlIfClass:build_dev_aml callback and lets further simplify
it by separating PCNT generation from slots descriptions.
It also makes PCNT callchain ASL much more readable since callchain
not longer cluttered by slots descriptors.
Plus, move will let next patch easily drop empty PCNT (pc/q35)
when there is nothing hotpluggable.
Signed-off-by: Igor Mammedov <imammedo@redhat.com>
Message-Id: <20230112140312.3096331-22-imammedo@redhat.com> Reviewed-by: Michael S. Tsirkin <mst@redhat.com> Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Igor Mammedov [Thu, 12 Jan 2023 14:02:50 +0000 (15:02 +0100)]
pcihp: drop pcihp_bridge_en dependency when composing PCNT method
.. and use only BSEL presence to decide on how PCNT should be composed.
That simplifies possible combinations to consider, but mainly it makes
PCIHP AML be governed only by BSEL, which is property of PCIBus
(aka part of bridge) and as result it opens possibility to convert
build_append_pci_bus_devices() into AcpiDevAmlIf::build_dev_aml
callback to make bridges self describing.
PS:
used approach leaves unused PCNT, when ACPI hotplug is completely
disabled but that's harmless and followup commits will get rid of
it later.
Signed-off-by: Igor Mammedov <imammedo@redhat.com>
Message-Id: <20230112140312.3096331-19-imammedo@redhat.com> Reviewed-by: Michael S. Tsirkin <mst@redhat.com> Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Igor Mammedov [Thu, 12 Jan 2023 14:02:49 +0000 (15:02 +0100)]
tests: acpi: whitelist DSDT before refactoring acpi based PCI hotplug machinery
Signed-off-by: Igor Mammedov <imammedo@redhat.com>
Message-Id: <20230112140312.3096331-18-imammedo@redhat.com> Reviewed-by: Michael S. Tsirkin <mst@redhat.com> Signed-off-by: Michael S. Tsirkin <mst@redhat.com> Reviewed-by: Michael S. Tsirkin <mst@redhat.com> Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Igor Mammedov [Thu, 12 Jan 2023 14:02:48 +0000 (15:02 +0100)]
tests: acpi: add reboot cycle to bridge test
hotplugged bridges should not be described in DSDT,
while it works on cold boot, some ACPPI PCI code
are invoked during reboot.
This patch will let us catch unexpected AML if hotplug
checks are broken.
Signed-off-by: Igor Mammedov <imammedo@redhat.com>
Message-Id: <20230112140312.3096331-17-imammedo@redhat.com> Reviewed-by: Michael S. Tsirkin <mst@redhat.com> Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Igor Mammedov [Thu, 12 Jan 2023 14:02:47 +0000 (15:02 +0100)]
tests: boot_sector_test(): make it multi-shot
if the function is called the 2nd time within the same qtest session,
it will prematurely return before boot sector is executed due to
remaining signature.
Follow up patch will add VM reboot to a test case and will
call boot_sector_test() again within the same qtest env,
which may lead to above issue.
To fix it make sure signature in VM RAM is no more before
exiting boot_sector_test(), so next time it's called it
will wait boot sector is completed again.
Signed-off-by: Igor Mammedov <imammedo@redhat.com>
Message-Id: <20230112140312.3096331-16-imammedo@redhat.com> Reviewed-by: Michael S. Tsirkin <mst@redhat.com> Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Igor Mammedov [Thu, 12 Jan 2023 14:02:46 +0000 (15:02 +0100)]
tests: acpi: extend bridge tests with hotplugged bridges
with previous commit fixing malformed PCNT calls to hotplugged
bridges, it should be possible add coldplug/hotplug test when
describing PCI topology in DSDT without breeaking CI.
Signed-off-by: Igor Mammedov <imammedo@redhat.com>
Message-Id: <20230112140312.3096331-15-imammedo@redhat.com> Reviewed-by: Michael S. Tsirkin <mst@redhat.com> Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Igor Mammedov [Thu, 12 Jan 2023 14:02:45 +0000 (15:02 +0100)]
tests: boot_sector_test: avoid crashing if status is not available yet
If test case was started in paused mode (-S CLI option) and then
allowed to continue via QMP, boot_sector_test could assert on
transient state with following error:
Instead of crashing test if 'status' is not available yet, skip check
and repeat iteration again after TEST_DELAY has elapsed.
Signed-off-by: Igor Mammedov <imammedo@redhat.com>
Message-Id: <20230112140312.3096331-14-imammedo@redhat.com> Reviewed-by: Michael S. Tsirkin <mst@redhat.com> Signed-off-by: Michael S. Tsirkin <mst@redhat.com>