| Commit message (Collapse) | Author | Files | Lines |
|---|
|
A log_mask_ln!() macro is provided which expects similar arguments as the
C version. However, the formatting works as one would expect from Rust.
To maximize code reuse the macro is just a thin wrapper around
qemu_log(). Also, just the bare minimum of logging masks is provided
which should suffice for the current use case of Rust in QEMU.
Signed-off-by: Bernhard Beschow <shentey@gmail.com>
Link: https://lore.kernel.org/r/20250615112037.11992-2-shentey@gmail.com
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
|
|
Once qemu-api is split in multiple crates, each of them will have
its own invocation of bindgen. There cannot be only one, because
there are occasional "impl" blocks for the bindgen-generated
structs (e.g. VMStateFlags or QOM classes) that have to
reside in the same crate as the bindgen-generated code.
For now, prepare for this new organization by invoking bindgen
within the qemu-api crate's build definitions; it's also a
much better place to list enums that need specific treatment
from bindgen.
Reviewed-by: Zhao Liu <zhao1.liu@intel.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
|
|
When splitting the QEMU Rust bindings into multiple crates, the
bindgen-generated structs also have to be split so that it's
possible to add "impl" blocks (e.g. for Sync/Send or Default,
or even for utility methods in cases such as VMStateFlags).
Tweak various variable definitions in meson.build, to avoid naming
conflicts once there will be multiple bindgen invocations.
Reviewed-by: Zhao Liu <zhao1.liu@intel.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
|
|
This removes undefined behavior associated to writing to uninitialized
fields, and makes it possible to remove "unsafe" from the instance_init
implementation.
However, the init function itself is still unsafe, because it must promise
(as a sort as MaybeUninit::assume_init) that all fields have been
initialized.
Reviewed-by: Zhao Liu <zhao1.liu@intel.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
|
|
This is the trick that allows the parent-field initializer to be used
only for the object that it's meant to be initialized. This way,
the owner of a MemoryRegion must be the object that embeds it.
More information is in the comments; it's best explained with a simplified
example.
Reviewed-by: Zhao Liu <zhao1.liu@intel.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
|
|
This is a smart pointer for MaybeUninit; it can be upcasted to the
already-initialized parent classes, or dereferenced to a MaybeUninit
for the class that is being initialized.
Reviewed-by: Zhao Liu <zhao1.liu@intel.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
|
|
The array of BqlRefCell<HPETTimer> is not initialized yet at the
end of instance_init. In particular, the "state" field is NonNull
and therefore it is invalid to have it as zero bytes.
Note that MaybeUninit is necessary because assigning to self.timers[index]
would trigger Drop of the old value.
Reviewed-by: Zhao Liu <zhao1.liu@intel.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
|
|
Add a macro that makes it possible to convert a MaybeUninit<> into
another MaybeUninit<> for a single field within it. Furthermore, it is
possible to use the resulting MaybeUninitField<> in APIs that take the
parent object, such as memory_region_init_io().
This allows removing some of the undefined behavior from instance_init()
functions, though this may not be the definitive implementation.
Reviewed-by: Zhao Liu <zhao1.liu@intel.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
|
|
Makes this custom_target() usage consistent with other ones in QEMU.
Fixes: 6e0dc9d2a88a ("meson: compile bundled device trees")
Signed-off-by: Bernhard Beschow <shentey@gmail.com>
Link: https://lore.kernel.org/r/20250610204131.2862-3-shentey@gmail.com
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
|
|
Commit fcb1ad456c58 ("system/datadir: Add new type constant for DTB files")
introduced a new type constant for DTB files and converted the boards with
bundled device trees to use it. Convert the other boards for consistency.
Fixes: fcb1ad456c58 ("system/datadir: Add new type constant for DTB files")
Signed-off-by: Bernhard Beschow <shentey@gmail.com>
Link: https://lore.kernel.org/r/20250610204131.2862-2-shentey@gmail.com
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
|
|
Before commit e54ef98c8a ("target/i386: do not trigger IRQ shadow for LSS"), any
write to SS in gen_movl_seg() would cause a TB exit. The changes introduced by
this commit were intended to restrict the DISAS_EOB_INHIBIT_IRQ exit to the case
where inhibit_irq is true, but missed that a DISAS_EOB_NEXT exit can still be
required when writing to SS and inhibit_irq is false.
Comparing the PE(s) && !VM86(s) section with the logic in x86_update_hflags(), we
can see that the DISAS_EOB_NEXT exit is still required for the !CODE32 case when
writing to SS in gen_movl_seg() because any change to the SS flags can affect
hflags. Similarly we can see that the existing CODE32 case is still correct since
a change to any of DS, ES and SS can affect hflags. Finally for the
gen_op_movl_seg_real() case an explicit TB exit is not needed because the segment
register selector does not affect hflags.
Update the logic in gen_movl_seg() so that a write to SS with inhibit_irq set to
false where PE(s) && !VM86(s) will generate a DISAS_EOB_NEXT exit along with the
inline comment. This has the effect of allowing Win98SE to boot in QEMU once
again.
Signed-off-by: Mark Cave-Ayland <mark.cave-ayland@ilande.co.uk>
Fixes: e54ef98c8a ("target/i386: do not trigger IRQ shadow for LSS")
Resolves: https://gitlab.com/qemu-project/qemu/-/issues/2987
Link: https://lore.kernel.org/r/20250611130315.383151-1-mark.cave-ayland@ilande.co.uk
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
|
|
As pointed out by Akihiko Odaki, all Win32 libraries in MinGW have lowercase
names. This means that on (case-insensitive) Windows you can use the mixed-case
names suggested by Microsoft or all-lowercase names, while on Linux you need to
make them lowercase.
QEMU was already using lowercase names, so there is no need to test the
mixed-case name version of libSynchronization. Remove the unnecessary test
and while at it make all the tests use "required: true".
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
|
|
The 'net_stream_send' method has a 68k byte array used for copying
data between guest and host. Skip the automatic zero-init of this
array to eliminate the performance overhead in the I/O hot path.
The 'buf1' array will be fully initialized when reading data off
the network socket.
Signed-off-by: Daniel P. Berrangé <berrange@redhat.com>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
Reviewed-by: Klaus Jensen <k.jensen@samsung.com>
Reviewed-by: Harsh Prateek Bora <harshpb@linux.ibm.com>
Message-id: 20250610123709.835102-32-berrange@redhat.com
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
|
|
The 'net_socket_send' method has a 68k byte array used for copying
data between guest and host. Skip the automatic zero-init of this
array to eliminate the performance overhead in the I/O hot path.
The 'buf1' array will be fully initialized when reading data off
the network socket.
Signed-off-by: Daniel P. Berrangé <berrange@redhat.com>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
Reviewed-by: Klaus Jensen <k.jensen@samsung.com>
Reviewed-by: Harsh Prateek Bora <harshpb@linux.ibm.com>
Message-id: 20250610123709.835102-31-berrange@redhat.com
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
|
|
The 'ufs_emulate_scsi_cmd' method has a 4k byte array used for
copying data from the device. Skip the automatic zero-init of
this array to eliminate the performance overhead in the I/O hot
path.
The 'outbuf' array will be fully initialized when data is copied
from the guest.
Signed-off-by: Daniel P. Berrangé <berrange@redhat.com>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
Reviewed-by: Klaus Jensen <k.jensen@samsung.com>
Reviewed-by: Harsh Prateek Bora <harshpb@linux.ibm.com>
Message-id: 20250610123709.835102-30-berrange@redhat.com
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
|
|
The 'megasas_dcmd_pd_get_list' and 'megasas_dcmd_get_properties'
methods have 4k structs used for copying data from the device.
Skip the automatic zero-init of this array to eliminate the
performance overhead in the I/O hot path.
The 'info' structs are manually initialized with memset(). The
compiler ought to be intelligent enough to turn the memset()
into a static initialization operation, and thus not duplicate
the automatic zero-init. Replacing memset() with '{}' makes it
unambiguous that the arrays are statically initialized.
Signed-off-by: Daniel P. Berrangé <berrange@redhat.com>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
Reviewed-by: Klaus Jensen <k.jensen@samsung.com>
Reviewed-by: Harsh Prateek Bora <harshpb@linux.ibm.com>
Message-id: 20250610123709.835102-29-berrange@redhat.com
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
|
|
The 'lsi_memcpy' method has a 4k byte array used for copying data
to/from the device. Skip the automatic zero-init of this array to
eliminate the performance overhead in the I/O hot path.
The 'buf' array will be fully initialized when data is copied.
Signed-off-by: Daniel P. Berrangé <berrange@redhat.com>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
Reviewed-by: Klaus Jensen <k.jensen@samsung.com>
Reviewed-by: Harsh Prateek Bora <harshpb@linux.ibm.com>
Message-id: 20250610123709.835102-28-berrange@redhat.com
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
|
|
The 'ohci_service_iso_td' method has a 8k byte array used for copying
data between guest and host. Skip the automatic zero-init of this
array to eliminate the performance overhead in the I/O hot path.
The 'buf' array will be fully initialized when reading data from guest
memory.
Signed-off-by: Daniel P. Berrangé <berrange@redhat.com>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
Reviewed-by: Klaus Jensen <k.jensen@samsung.com>
Reviewed-by: Harsh Prateek Bora <harshpb@linux.ibm.com>
Message-id: 20250610123709.835102-27-berrange@redhat.com
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
|
|
The 'tpm_execute' method has a pair of 4k arrays used for copying
data between guest and host. Skip the automatic zero-init of these
arrays to eliminate the performance overhead in the I/O hot path.
The two arrays will be fully initialized when reading data from
guest memory or reading data from the proxy FD.
Signed-off-by: Daniel P. Berrangé <berrange@redhat.com>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
Reviewed-by: Klaus Jensen <k.jensen@samsung.com>
Reviewed-by: Harsh Prateek Bora <harshpb@linux.ibm.com>
Message-id: 20250610123709.835102-26-berrange@redhat.com
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
|
|
The 'occ_model_tick' method has a 12k struct used for copying
data between guest and host. Skip the automatic zero-init of this
struct to eliminate the performance overhead in the I/O hot path.
The 'dynamic_data' buffer will be fully initialized when reading
data from the guest.
Signed-off-by: Daniel P. Berrangé <berrange@redhat.com>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
Reviewed-by: Klaus Jensen <k.jensen@samsung.com>
Reviewed-by: Harsh Prateek Bora <harshpb@linux.ibm.com>
Message-id: 20250610123709.835102-25-berrange@redhat.com
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
|
|
The 'nvme_map_sgl' method has a 256 element array used for copying
data from the device. Skip the automatic zero-init of this array
to eliminate the performance overhead in the I/O hot path.
The 'segment' array will be fully initialized when reading data from
the device.
The 'nme_changed_nslist' method has a 4k byte array that is manually
initialized with memset(). The compiler ought to be intelligent
enough to turn the memset() into a static initialization operation,
and thus not duplicate the automatic zero-init. Replacing memset()
with '{}' makes it unambiguous that the array is statically initialized.
Signed-off-by: Daniel P. Berrangé <berrange@redhat.com>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
Reviewed-by: Klaus Jensen <k.jensen@samsung.com>
Message-id: 20250610123709.835102-24-berrange@redhat.com
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
|
|
The 'xgmac_enet_send' method has a 8k byte array used for copying
data between guest and host. Skip the automatic zero-init of this
array to eliminate the performance overhead in the I/O hot path.
The 'frame' buffer will be fully initialized when reading guest
memory to fetch the data to send.
Signed-off-by: Daniel P. Berrangé <berrange@redhat.com>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
Message-id: 20250610123709.835102-23-berrange@redhat.com
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
|
|
The 'virtio_net_receive_rcu' method has three arrays with
VIRTQUEUE_MAX_SIZE elements, which are apprixmately 32k in
size used for copying data between guest and host. Skip the
automatic zero-init of these arrays to eliminate the
performance overhead in the I/O hot path.
The three arrays will be selectively initialized as required
when processing network buffers.
Signed-off-by: Daniel P. Berrangé <berrange@redhat.com>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
Message-id: 20250610123709.835102-22-berrange@redhat.com
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
|
|
The 'tulip_setup_frame' method has a 4k byte array used for copynig
DMA data from the device. Skip the automatic zero-init of this array
to eliminate the performance overhead in the I/O hot path.
The 'buf' array will be fully initialized when reading data from the
device.
Signed-off-by: Daniel P. Berrangé <berrange@redhat.com>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
Message-id: 20250610123709.835102-21-berrange@redhat.com
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
|
|
The 'rtl8139_transmit_one' method has a 8k byte array used for
copying data between guest and host. Skip the automatic zero-init
of this array to eliminate the performance overhead in the I/O
hot path.
The 'txbuffer' will be fully initialized when reading PCI DMA
buffers.
Signed-off-by: Daniel P. Berrangé <berrange@redhat.com>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
Message-id: 20250610123709.835102-20-berrange@redhat.com
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
|
|
The 'do_hash_operation' method has a 256 element iovec array used for
holding pointers to data that is to be hashed. Skip the automatic
zero-init of this array to eliminate the performance overhead in the
I/O hot path.
The 'iovec' array will be selectively initialized based on data that
needs to be hashed.
Signed-off-by: Daniel P. Berrangé <berrange@redhat.com>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
Message-id: 20250610123709.835102-19-berrange@redhat.com
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
|
|
The 'handle_recv_msg' method has a 4k byte array used for copying
data between the network socket and guest memory. Skip the automatic
zero-init of this array to eliminate the performance overhead in the
I/O hot path.
The 'data_buf' array will be fully initialized when data is read
off the network socket.
Signed-off-by: Daniel P. Berrangé <berrange@redhat.com>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
Message-id: 20250610123709.835102-18-berrange@redhat.com
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
|
|
The 'vmsvga_fifo_run' method has a struct which is a little over 20k
in size, used for holding image data for cursor changes. Skip the
automatic zero-init of this struct to eliminate the performance
overhead in the I/O hot path.
The cursor variable will be fully initialized only when processing
a cursor definition message from the guest.
Signed-off-by: Daniel P. Berrangé <berrange@redhat.com>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
Message-id: 20250610123709.835102-17-berrange@redhat.com
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
|
|
The 'xlnx_csu_dma_src_notify' method has a 4k byte array used for
copying DMA data. Skip the automatic zero-init of this array to
eliminate the performance overhead in the I/O hot path.
The 'buf' array will be fully initialized when data is copied.
Signed-off-by: Daniel P. Berrangé <berrange@redhat.com>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
Message-id: 20250610123709.835102-16-berrange@redhat.com
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
|
|
The 'process_mdb' method has a 4k byte array used for copying data
between the guest and the chardev backend. Skip the automatic zero-init
of this array to eliminate the performance overhead in the I/O hot
path.
The 'buffer' array will be selectively initialized when data is converted
between EBCDIC and ASCII.
Signed-off-by: Daniel P. Berrangé <berrange@redhat.com>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
Message-id: 20250610123709.835102-15-berrange@redhat.com
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
|
|
The 'out_cb' method has a 4k byte array used for copying data
between the audio backend and device. Skip the automatic zero-init
of this array to eliminate the performance overhead in the I/O hot
path.
The 'tmpbuf' array will be fully initialized when reading data from
device memory.
Signed-off-by: Daniel P. Berrangé <berrange@redhat.com>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
Message-id: 20250610123709.835102-14-berrange@redhat.com
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
|
|
The 'write_audio' method has a 4k byte array used for copying data
between the audio backend and device. Skip the automatic zero-init
of this array to eliminate the performance overhead in the I/O hot
path.
The 'tmpbuf' array will be fully initialized when reading data from
device memory.
Signed-off-by: Daniel P. Berrangé <berrange@redhat.com>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
Message-id: 20250610123709.835102-13-berrange@redhat.com
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
|
|
The 'mv88w8618_audio_callback' method has a 4k byte array used for
copying data between the audio backend and device. Skip the automatic
zero-init of this array to eliminate the performance overhead in
the I/O hot path.
The 'buf' array will be fully initialized when reading data from
device memory.
Signed-off-by: Daniel P. Berrangé <berrange@redhat.com>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
Message-id: 20250610123709.835102-12-berrange@redhat.com
[Fixed hw/audio/gus in commit message --Stefan]
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
|
|
The 'GUS_read_DMA' method has a 4k byte array used for copying
data between the audio backend and device. Skip the automatic
zero-init of this array to eliminate the performance overhead in
the I/O hot path.
The 'tmpbuf' array will be fully initialized when reading data
from device memory.
Signed-off-by: Daniel P. Berrangé <berrange@redhat.com>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
Message-id: 20250610123709.835102-11-berrange@redhat.com
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
|
|
The 'es1370_transfer_audio' method has a 4k byte array used for
copying data between the audio backend and device. Skip the automatic
zero-init of this array to eliminate the performance overhead in
the I/O hot path.
The 'tmpbuf' array will be fully initialized when reading data from
the audio backend and/or device memory.
Signed-off-by: Daniel P. Berrangé <berrange@redhat.com>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
Message-id: 20250610123709.835102-10-berrange@redhat.com
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
|
|
The 'cs_write_audio' method has a pair of byte arrays, one 4k in size
and one 8k, which are used in converting audio samples. Skip the
automatic zero-init of these arrays to eliminate the performance
overhead in the I/O hot path.
The 'tmpbuf' array will be fully initialized when reading a block of
data from the guest. The 'linbuf' array will be fully initialized
when converting the audio samples.
Signed-off-by: Daniel P. Berrangé <berrange@redhat.com>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
Message-id: 20250610123709.835102-9-berrange@redhat.com
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
|
|
The 'read_audio' & 'write_audio' methods have a 4k byte array used
for copying data between the audio backend and device. Skip the
automatic zero-init of these arrays to eliminate the performance
overhead in the I/O hot path.
The 'tmpbuf' array will be fully initialized when reading data from
the audio backend and/or device memory.
Signed-off-by: Daniel P. Berrangé <berrange@redhat.com>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
Message-id: 20250610123709.835102-8-berrange@redhat.com
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
|
|
The 'tcp_chr_read' method has a 4k byte array used for copying
data between the socket and device. Skip the automatic zero-init
of this array to eliminate the performance overhead in the I/O
hot path.
The 'buf' array will be fully initialized when reading data off
the network socket.
Signed-off-by: Daniel P. Berrangé <berrange@redhat.com>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
Message-id: 20250610123709.835102-7-berrange@redhat.com
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
|
|
The 'pty_chr_read' method has a 4k byte array used for copying
data between the PTY and device. Skip the automatic zero-init
of this array to eliminate the performance overhead in the I/O
hot path.
The 'buf' array will be fully initialized when reading data off
the PTY.
Signed-off-by: Daniel P. Berrangé <berrange@redhat.com>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
Message-id: 20250610123709.835102-6-berrange@redhat.com
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
|
|
The 'fd_chr_read' method has a 4k byte array used for copying
data between the socket and device. Skip the automatic zero-init
of this array to eliminate the performance overhead in the I/O
hot path.
The 'buf' array will be fully initialized when reading data off
the network socket.
Signed-off-by: Daniel P. Berrangé <berrange@redhat.com>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
Message-id: 20250610123709.835102-5-berrange@redhat.com
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
|
|
The 'ioq_submit' method has a struct array that is 8k in size.
Skip the automatic zero-init of this array to eliminate the
performance overhead in the I/O hot path.
The 'iocbs' array will selectively initialized when processing
the I/O data.
Signed-off-by: Daniel P. Berrangé <berrange@redhat.com>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
Message-id: 20250610123709.835102-4-berrange@redhat.com
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
|
|
Since commit 7ff9ff039380 ("meson: mitigate against use of uninitialize
stack for exploits") the -ftrivial-auto-var-init=zero compiler option is
used to zero local variables. While this reduces security risks
associated with uninitialized stack data, it introduced a measurable
bottleneck in the virtqueue_split_pop() and virtqueue_packed_pop()
functions.
These virtqueue functions are in the hot path. They are called for each
element (request) that is popped from a VIRTIO device's virtqueue. Using
__attribute__((uninitialized)) on large stack variables in these
functions improves fio randread bs=4k iodepth=64 performance from 304k
to 332k IOPS (+9%).
This issue was found using perf-top(1). virtqueue_split_pop() was one of
the top CPU consumers and the "annotate" feature showed that the memory
zeroing instructions at the beginning of the functions were hot.
Fixes: 7ff9ff039380 ("meson: mitigate against use of uninitialize stack for exploits")
Cc: Daniel P. Berrangé <berrange@redhat.com>
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
Message-id: 20250610123709.835102-3-berrange@redhat.com
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
|
|
The QEMU_UNINITIALIZED macro is to be used to skip the default compiler
variable initialization done by -ftrivial-auto-var-init=zero.
Use this in cases where there a method in the device I/O path (or other
important hot paths), that has large variables on the stack. A rule of
thumb is that "large" means a method with 4kb data in the local stack
frame. Any variables which are KB in size, should be annotated with this
attribute, to pre-emptively eliminate any potential overhead from the
compiler zero'ing memory.
Given that this turns off a security hardening feature, when using this
to flag variables, it is important that the code is double-checked to
ensure there is no possible use of uninitialized data in the method.
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
Signed-off-by: Daniel P. Berrangé <berrange@redhat.com>
Message-id: 20250610123709.835102-2-berrange@redhat.com
[DB: split off patch & rewrite guidance on when to use the annotation]
Signed-off-by: Daniel P. Berrangé <berrange@redhat.com>
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
|
|
Tested-by: Dehan Meng <demeng@redhat.com>
Reviewed-by: Yan Vugenfirer <yvugenfi@redhat.com>
Signed-off-by: Konstantin Kostiuk <kkostiuk@redhat.com>
|
|
Windows has no native equivalent API, but it would be possible to
simulate it as illustrated here (BSD-3-Clause):
https://github.com/giampaolo/psutil/pull/1485
Reviewed-by: Daniel P. Berrangé <berrange@redhat.com>
Tested-by: Dehan Meng <demeng@redhat.com>
Reviewed-by: Yan Vugenfirer <yvugenfi@redhat.com>
Signed-off-by: Konstantin Kostiuk <kkostiuk@redhat.com>
|
|
Explicitly describe every parameter rather than summarizing.
Signed-off-by: John Levon <john.levon@nutanix.com>
Reviewed-by: Cédric Le Goater <clg@redhat.com>
Link: https://lore.kernel.org/qemu-devel/20250611104753.1199796-1-john.levon@nutanix.com
Signed-off-by: Cédric Le Goater <clg@redhat.com>
|
|
Export various MSI functions, renamed with a vfio_pci prefix, for use by
CPR in subsequent patches. No functional change.
Signed-off-by: Steve Sistare <steven.sistare@oracle.com>
Reviewed-by: Cédric Le Goater <clg@redhat.com>
Link: https://lore.kernel.org/qemu-devel/1749569991-25171-18-git-send-email-steven.sistare@oracle.com
Signed-off-by: Cédric Le Goater <clg@redhat.com>
|
|
Move event_notifier_cleanup calls to a helper vfio_notifier_cleanup.
This version is trivial, and does not yet use the vdev and nr parameters.
No functional change.
Signed-off-by: Steve Sistare <steven.sistare@oracle.com>
Reviewed-by: Cédric Le Goater <clg@redhat.com>
Link: https://lore.kernel.org/qemu-devel/1749569991-25171-17-git-send-email-steven.sistare@oracle.com
Signed-off-by: Cédric Le Goater <clg@redhat.com>
|
|
Pass vdev and nr to vfio_notifier_init, for use by CPR in a subsequent
patch. No functional change.
Signed-off-by: Steve Sistare <steven.sistare@oracle.com>
Reviewed-by: Cédric Le Goater <clg@redhat.com>
Link: https://lore.kernel.org/qemu-devel/1749569991-25171-16-git-send-email-steven.sistare@oracle.com
Signed-off-by: Cédric Le Goater <clg@redhat.com>
|
|
Pass the vector number to vfio_connect_kvm_msi_virq and
vfio_remove_kvm_msi_virq, so it can be passed to their subroutines in
a subsequent patch. No functional change.
Signed-off-by: Steve Sistare <steven.sistare@oracle.com>
Reviewed-by: Cédric Le Goater <clg@redhat.com>
Link: https://lore.kernel.org/qemu-devel/1749569991-25171-15-git-send-email-steven.sistare@oracle.com
Signed-off-by: Cédric Le Goater <clg@redhat.com>
|