Now that we switched all consumers of the URI code to use the URI
parsing functions from glib instead, we can remove our internal
URI parsing code since it is not used anymore.
Reviewed-by: Eric Blake <eblake@redhat.com>
Message-ID: <20240418101056.302103-14-thuth@redhat.com>
Signed-off-by: Thomas Huth <thuth@redhat.com>
Because non-embedded aarch64 is expected to have AdvSIMD enabled, merely
double-check with the compiler flags for __ARM_NEON and don't bother with
a runtime check. Otherwise, model the loop after the x86 SSE2 function.
Use UMAXV for the vector reduction. This is 3 cycles on cortex-a76 and
2 cycles on neoverse-n1.
Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Because the three alternatives are monotonic, we don't need
to keep a couple of bitmasks, just identify the strongest
alternative at startup.
Generalize test_buffer_is_zero_next_accel and init_accel
by always defining an accel_table array.
Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Split less-than and greater-than 256 cases.
Use unaligned accesses for head and tail.
Avoid using out-of-bounds pointers in loop boundary conditions.
Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Increase unroll factor in SIMD loops from 4x to 8x in order to move
their bottlenecks from ALU port contention to load issue rate (two loads
per cycle on popular x86 implementations).
Avoid using out-of-bounds pointers in loop boundary conditions.
Follow SSE2 implementation strategy in the AVX2 variant. Avoid use of
PTEST, which is not profitable there (like in the removed SSE4 variant).
Signed-off-by: Alexander Monakov <amonakov@ispras.ru>
Signed-off-by: Mikhail Romanov <mmromanov@ispras.ru>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-Id: <20240206204809.9859-6-amonakov@ispras.ru>
Use of prefetching in bufferiszero.c is quite questionable:
- prefetches are issued just a few CPU cycles before the corresponding
line would be hit by demand loads;
- they are done for simple access patterns, i.e. where hardware
prefetchers can perform better;
- they compete for load ports in loops that should be limited by load
port throughput rather than ALU throughput.
Signed-off-by: Alexander Monakov <amonakov@ispras.ru>
Signed-off-by: Mikhail Romanov <mmromanov@ispras.ru>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-Id: <20240206204809.9859-5-amonakov@ispras.ru>
Test for length >= 256 inline, where is is often a constant.
Before calling into the accelerated routine, sample three bytes
from the buffer, which handles most non-zero buffers.
Signed-off-by: Alexander Monakov <amonakov@ispras.ru>
Signed-off-by: Mikhail Romanov <mmromanov@ispras.ru>
Message-Id: <20240206204809.9859-3-amonakov@ispras.ru>
[rth: Use __builtin_constant_p; move the indirect call out of line.]
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
The SSE4.1 variant is virtually identical to the SSE2 variant, except
for using 'PTEST+JNZ' in place of 'PCMPEQB+PMOVMSKB+CMP+JNE' for testing
if an SSE register is all zeroes. The PTEST instruction decodes to two
uops, so it can be handled only by the complex decoder, and since
CMP+JNE are macro-fused, both sequences decode to three uops. The uops
comprising the PTEST instruction dispatch to p0 and p5 on Intel CPUs, so
PCMPEQB+PMOVMSKB is comparatively more flexible from dispatch
standpoint.
Hence, the use of PTEST brings no benefit from throughput standpoint.
Its latency is not important, since it feeds only a conditional jump,
which terminates the dependency chain.
I never observed PTEST variants to be faster on real hardware.
Signed-off-by: Alexander Monakov <amonakov@ispras.ru>
Signed-off-by: Mikhail Romanov <mmromanov@ispras.ru>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-Id: <20240206204809.9859-2-amonakov@ispras.ru>
The DEBUG_PLUGIN_GEN_OPS ifdef is replaced with "-d op_plugin".
The second pr_ops call can be obtained with "-d op".
Reviewed-by: Pierrick Bouvier <pierrick.bouvier@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Address the comment added in commit 4629ed1e98
("qerror: Finally unused, clean up"), from 2015:
/*
* These macros will go away, please don't use
* in new code, and do not add new ones!
*/
Mechanical transformation using:
$ sed -i -e "s/QERR_INVALID_PARAMETER,/\"Invalid parameter '%s'\",/" \
$(git grep -lw QERR_INVALID_PARAMETER)
Manually simplify qemu_opts_create(), and remove the macro definition
in include/qapi/qmp/qerror.h.
Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org>
Signed-off-by: Markus Armbruster <armbru@redhat.com>
Message-ID: <20240312141343.3168265-6-armbru@redhat.com>
Daniel P. Berrangé <berrange@redhat.com> pointed out that the coroutine
pool size heuristic is very conservative. Instead of halving
max_map_count, he suggested reserving 5,000 mappings for non-coroutine
users based on observations of guests he has access to.
Fixes: 86a637e481 ("coroutine: cap per-thread local pool size")
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
Reviewed-by: Daniel P. Berrangé <berrange@redhat.com>
Message-id: 20240320181232.1464819-1-stefanha@redhat.com
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
The coroutine pool implementation can hit the Linux vm.max_map_count
limit, causing QEMU to abort with "failed to allocate memory for stack"
or "failed to set up stack guard page" during coroutine creation.
This happens because per-thread pools can grow to tens of thousands of
coroutines. Each coroutine causes 2 virtual memory areas to be created.
Eventually vm.max_map_count is reached and memory-related syscalls fail.
The per-thread pool sizes are non-uniform and depend on past coroutine
usage in each thread, so it's possible for one thread to have a large
pool while another thread's pool is empty.
Switch to a new coroutine pool implementation with a global pool that
grows to a maximum number of coroutines and per-thread local pools that
are capped at hardcoded small number of coroutines.
This approach does not leave large numbers of coroutines pooled in a
thread that may not use them again. In order to perform well it
amortizes the cost of global pool accesses by working in batches of
coroutines instead of individual coroutines.
The global pool is a list. Threads donate batches of coroutines to when
they have too many and take batches from when they have too few:
.-----------------------------------.
| Batch 1 | Batch 2 | Batch 3 | ... | global_pool
`-----------------------------------'
Each thread has up to 2 batches of coroutines:
.-------------------.
| Batch 1 | Batch 2 | per-thread local_pool (maximum 2 batches)
`-------------------'
The goal of this change is to reduce the excessive number of pooled
coroutines that cause QEMU to abort when vm.max_map_count is reached
without losing the performance of an adequately sized coroutine pool.
Here are virtio-blk disk I/O benchmark results:
RW BLKSIZE IODEPTH OLD NEW CHANGE
randread 4k 1 113725 117451 +3.3%
randread 4k 8 192968 198510 +2.9%
randread 4k 16 207138 209429 +1.1%
randread 4k 32 212399 215145 +1.3%
randread 4k 64 218319 221277 +1.4%
randread 128k 1 17587 17535 -0.3%
randread 128k 8 17614 17616 +0.0%
randread 128k 16 17608 17609 +0.0%
randread 128k 32 17552 17553 +0.0%
randread 128k 64 17484 17484 +0.0%
See files/{fio.sh,test.xml.j2} for the benchmark configuration:
https://gitlab.com/stefanha/virt-playbooks/-/tree/coroutine-pool-fix-sizing
Buglink: https://issues.redhat.com/browse/RHEL-28947
Reported-by: Sanjay Rao <srao@redhat.com>
Reported-by: Boaz Ben Shabat <bbenshab@redhat.com>
Reported-by: Joe Mario <jmario@redhat.com>
Reviewed-by: Kevin Wolf <kwolf@redhat.com>
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
Message-ID: <20240318183429.1039340-1-stefanha@redhat.com>
touch_all_pages() can return early, before creating threads. In this case,
however, it leaks the MemsetContext that it has allocated at the
beginning of the function.
Reported by Coverity as CID 1534922.
Fixes: 04accf43df ("oslib-posix: initialize backend memory objects in parallel", 2024-02-06)
Reviewed-by: Mark Kanda <mark.kanda@oracle.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
SocketAddress branch @fd is documented in enum SocketAddressType,
unlike the other branches. That's because the branch's type is String
from common.json.
Use a local copy of String, so we can put the documentation in the
usual place.
Signed-off-by: Markus Armbruster <armbru@redhat.com>
Message-ID: <20240205074709.3613229-14-armbru@redhat.com>
Reviewed-by: Daniel P. Berrangé <berrange@redhat.com>
make vm-build-freebsd fails with:
ld: error: undefined symbol: inotify_init1
>>> referenced by filemonitor-inotify.c:183 (../src/util/filemonitor-inotify.c:183)
>>> util_filemonitor-inotify.c.o:(qemu_file_monitor_new) in archive libqemuutil.a
On FreeBSD the inotify functions are defined in libinotify.so. Add it
to the dependencies.
Signed-off-by: Ilya Leoshkevich <iii@linux.ibm.com>
Reviewed-by: Thomas Huth <thuth@redhat.com>
Message-ID: <20240206002344.12372-5-iii@linux.ibm.com>
Signed-off-by: Thomas Huth <thuth@redhat.com>
QEMU initializes preallocated backend memory as the objects are parsed from
the command line. This is not optimal in some cases (e.g. memory spanning
multiple NUMA nodes) because the memory objects are initialized in series.
Allow the initialization to occur in parallel (asynchronously). In order to
ensure optimal thread placement, asynchronous initialization requires prealloc
context threads to be in use.
Signed-off-by: Mark Kanda <mark.kanda@oracle.com>
Message-ID: <20240131165327.3154970-2-mark.kanda@oracle.com>
Tested-by: Mario Casquero <mcasquer@redhat.com>
Signed-off-by: David Hildenbrand <david@redhat.com>
This commit was created with scripts/clean-includes:
./scripts/clean-includes --git misc net/af-xdp.c plugins/*.c audio/pwaudio.c util/userfaultfd.c
All .c should include qemu/osdep.h first. The script performs three
related cleanups:
* Ensure .c files include qemu/osdep.h first.
* Including it in a .h is redundant, since the .c already includes
it. Drop such inclusions.
* Likewise, including headers qemu/osdep.h includes is redundant.
Drop these, too.
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Zhao Liu <zhao1.liu@intel.com>
Signed-off-by: Michael Tokarev <mjt@tls.msk.ru>
