mirrors/qemu
0
0
Fork 0
mirror of https://github.com/qemu/qemu.git synced 2024-12-11 20:53:51 +08:00
Code Issues Packages Projects Releases Wiki Activity
1fda6198e4
qemu/util/qemu-coroutine.c

149 lines
3.9 KiB
C
Raw Normal View History

coroutine: introduce coroutines Asynchronous code is becoming very complex. At the same time synchronous code is growing because it is convenient to write. Sometimes duplicate code paths are even added, one synchronous and the other asynchronous. This patch introduces coroutines which allow code that looks synchronous but is asynchronous under the covers. A coroutine has its own stack and is therefore able to preserve state across blocking operations, which traditionally require callback functions and manual marshalling of parameters. Creating and starting a coroutine is easy: coroutine = qemu_coroutine_create(my_coroutine); qemu_coroutine_enter(coroutine, my_data); The coroutine then executes until it returns or yields: void coroutine_fn my_coroutine(void *opaque) { MyData *my_data = opaque; /* do some work */ qemu_coroutine_yield(); /* do some more work */ } Yielding switches control back to the caller of qemu_coroutine_enter(). This is typically used to switch back to the main thread's event loop after issuing an asynchronous I/O request. The request callback will then invoke qemu_coroutine_enter() once more to switch back to the coroutine. Note that if coroutines are used only from threads which hold the global mutex they will never execute concurrently. This makes programming with coroutines easier than with threads. Race conditions cannot occur since only one coroutine may be active at any time. Other coroutines can only run across yield. This coroutines implementation is based on the gtk-vnc implementation written by Anthony Liguori <anthony@codemonkey.ws> but it has been significantly rewritten by Kevin Wolf <kwolf@redhat.com> to use setjmp()/longjmp() instead of the more expensive swapcontext() and by Paolo Bonzini <pbonzini@redhat.com> for Windows Fibers support. Signed-off-by: Kevin Wolf <kwolf@redhat.com> Signed-off-by: Stefan Hajnoczi <stefanha@linux.vnet.ibm.com>
2011-01-18 00:08:14 +08:00
/*
* QEMU coroutines
*
* Copyright IBM, Corp. 2011
*
* Authors:
* Stefan Hajnoczi <stefanha@linux.vnet.ibm.com>
* Kevin Wolf <kwolf@redhat.com>
*
* This work is licensed under the terms of the GNU LGPL, version 2 or later.
* See the COPYING.LIB file in the top-level directory.
*
*/
util: Clean up includes Clean up includes so that osdep.h is included first and headers which it implies are not included manually. This commit was created with scripts/clean-includes. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Message-id: 1454089805-5470-6-git-send-email-peter.maydell@linaro.org
2016-01-30 01:49:55 +08:00
#include "qemu/osdep.h"
coroutine: introduce coroutines Asynchronous code is becoming very complex. At the same time synchronous code is growing because it is convenient to write. Sometimes duplicate code paths are even added, one synchronous and the other asynchronous. This patch introduces coroutines which allow code that looks synchronous but is asynchronous under the covers. A coroutine has its own stack and is therefore able to preserve state across blocking operations, which traditionally require callback functions and manual marshalling of parameters. Creating and starting a coroutine is easy: coroutine = qemu_coroutine_create(my_coroutine); qemu_coroutine_enter(coroutine, my_data); The coroutine then executes until it returns or yields: void coroutine_fn my_coroutine(void *opaque) { MyData *my_data = opaque; /* do some work */ qemu_coroutine_yield(); /* do some more work */ } Yielding switches control back to the caller of qemu_coroutine_enter(). This is typically used to switch back to the main thread's event loop after issuing an asynchronous I/O request. The request callback will then invoke qemu_coroutine_enter() once more to switch back to the coroutine. Note that if coroutines are used only from threads which hold the global mutex they will never execute concurrently. This makes programming with coroutines easier than with threads. Race conditions cannot occur since only one coroutine may be active at any time. Other coroutines can only run across yield. This coroutines implementation is based on the gtk-vnc implementation written by Anthony Liguori <anthony@codemonkey.ws> but it has been significantly rewritten by Kevin Wolf <kwolf@redhat.com> to use setjmp()/longjmp() instead of the more expensive swapcontext() and by Paolo Bonzini <pbonzini@redhat.com> for Windows Fibers support. Signed-off-by: Kevin Wolf <kwolf@redhat.com> Signed-off-by: Stefan Hajnoczi <stefanha@linux.vnet.ibm.com>
2011-01-18 00:08:14 +08:00
#include "trace.h"
#include "qemu-common.h"
coroutine: protect global pool with a mutex The coroutine freelist is a global pool of unused coroutines. It avoids the setup/teardown overhead associated with the coroutine lifecycle. Since the pool is global, we need to synchronize access so that coroutines can be used outside the BQL. Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
2013-05-17 21:51:25 +08:00
#include "qemu/thread.h"
coroutine: rewrite pool to avoid mutex This patch removes the mutex by using fancy lock-free manipulation of the pool. Lock-free stacks and queues are not hard, but they can suffer from the ABA problem so they are better avoided unless you have some deferred reclamation scheme like RCU. Otherwise you have to stick with adding to a list, and emptying it completely. This is what this patch does, by coupling a lock-free global list of available coroutines with per-CPU lists that are actually used on coroutine creation. Whenever the destruction pool is big enough, the next thread that runs out of coroutines will steal the whole destruction pool. This is positive in two ways: 1) the allocation does not have to do any atomic operation in the fast path, it's entirely using thread-local storage. Once every POOL_BATCH_SIZE allocations it will do a single atomic_xchg. Release does an atomic_cmpxchg loop, that hopefully doesn't cause any starvation, and an atomic_inc. A later patch will also remove atomic operations from the release path, and try to avoid the atomic_xchg altogether---succeeding in doing so if all devices either use ioeventfd or are not submitting requests actively. 2) in theory this should be completely adaptive. The number of coroutines around should be a little more than POOL_BATCH_SIZE * number of allocating threads; so this also empties qemu_coroutine_adjust_pool_size. (The previous pool size was POOL_BATCH_SIZE * number of block backends, so it was a bit more generous. But if you actually have many high-iodepth disks, it's better to put them in different iothreads, which will also use separate thread pools and aio=native file descriptors). This speeds up perf/cost (in tests/test-coroutine) by a factor of ~1.33. No matter if we end with some kind of coroutine bypass scheme or not, it cannot hurt to optimize hot code. Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> Reviewed-by: Fam Zheng <famz@redhat.com> Message-id: 1417518350-6167-6-git-send-email-pbonzini@redhat.com Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
2014-12-02 19:05:48 +08:00
#include "qemu/atomic.h"
coroutine: move into libqemuutil.a library The coroutine files are currently referenced by the block-obj-y variable. The coroutine functionality though is already used by more than just the block code. eg migration code uses coroutine yield. In the future the I/O channel code will also use the coroutine yield functionality. Since the coroutine code is nicely self-contained it can be easily built as part of the libqemuutil.a library, making it widely available. The headers are also moved into include/qemu, instead of the include/block directory, since they are now part of the util codebase, and the impl was never in the block/ directory either. Signed-off-by: Daniel P. Berrange <berrange@redhat.com>
2015-09-01 21:48:02 +08:00
#include "qemu/coroutine.h"
#include "qemu/coroutine_int.h"
coroutine: introduce coroutines Asynchronous code is becoming very complex. At the same time synchronous code is growing because it is convenient to write. Sometimes duplicate code paths are even added, one synchronous and the other asynchronous. This patch introduces coroutines which allow code that looks synchronous but is asynchronous under the covers. A coroutine has its own stack and is therefore able to preserve state across blocking operations, which traditionally require callback functions and manual marshalling of parameters. Creating and starting a coroutine is easy: coroutine = qemu_coroutine_create(my_coroutine); qemu_coroutine_enter(coroutine, my_data); The coroutine then executes until it returns or yields: void coroutine_fn my_coroutine(void *opaque) { MyData *my_data = opaque; /* do some work */ qemu_coroutine_yield(); /* do some more work */ } Yielding switches control back to the caller of qemu_coroutine_enter(). This is typically used to switch back to the main thread's event loop after issuing an asynchronous I/O request. The request callback will then invoke qemu_coroutine_enter() once more to switch back to the coroutine. Note that if coroutines are used only from threads which hold the global mutex they will never execute concurrently. This makes programming with coroutines easier than with threads. Race conditions cannot occur since only one coroutine may be active at any time. Other coroutines can only run across yield. This coroutines implementation is based on the gtk-vnc implementation written by Anthony Liguori <anthony@codemonkey.ws> but it has been significantly rewritten by Kevin Wolf <kwolf@redhat.com> to use setjmp()/longjmp() instead of the more expensive swapcontext() and by Paolo Bonzini <pbonzini@redhat.com> for Windows Fibers support. Signed-off-by: Kevin Wolf <kwolf@redhat.com> Signed-off-by: Stefan Hajnoczi <stefanha@linux.vnet.ibm.com>
2011-01-18 00:08:14 +08:00
coroutine: move pooling to common code The coroutine pool code is duplicated between the ucontext and sigaltstack backends, and absent from the win32 backend. But the code can be shared easily by moving it to qemu-coroutine.c. Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com>
2013-02-19 18:59:09 +08:00
enum {
coroutine: rewrite pool to avoid mutex This patch removes the mutex by using fancy lock-free manipulation of the pool. Lock-free stacks and queues are not hard, but they can suffer from the ABA problem so they are better avoided unless you have some deferred reclamation scheme like RCU. Otherwise you have to stick with adding to a list, and emptying it completely. This is what this patch does, by coupling a lock-free global list of available coroutines with per-CPU lists that are actually used on coroutine creation. Whenever the destruction pool is big enough, the next thread that runs out of coroutines will steal the whole destruction pool. This is positive in two ways: 1) the allocation does not have to do any atomic operation in the fast path, it's entirely using thread-local storage. Once every POOL_BATCH_SIZE allocations it will do a single atomic_xchg. Release does an atomic_cmpxchg loop, that hopefully doesn't cause any starvation, and an atomic_inc. A later patch will also remove atomic operations from the release path, and try to avoid the atomic_xchg altogether---succeeding in doing so if all devices either use ioeventfd or are not submitting requests actively. 2) in theory this should be completely adaptive. The number of coroutines around should be a little more than POOL_BATCH_SIZE * number of allocating threads; so this also empties qemu_coroutine_adjust_pool_size. (The previous pool size was POOL_BATCH_SIZE * number of block backends, so it was a bit more generous. But if you actually have many high-iodepth disks, it's better to put them in different iothreads, which will also use separate thread pools and aio=native file descriptors). This speeds up perf/cost (in tests/test-coroutine) by a factor of ~1.33. No matter if we end with some kind of coroutine bypass scheme or not, it cannot hurt to optimize hot code. Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> Reviewed-by: Fam Zheng <famz@redhat.com> Message-id: 1417518350-6167-6-git-send-email-pbonzini@redhat.com Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
2014-12-02 19:05:48 +08:00
POOL_BATCH_SIZE = 64,
coroutine: move pooling to common code The coroutine pool code is duplicated between the ucontext and sigaltstack backends, and absent from the win32 backend. But the code can be shared easily by moving it to qemu-coroutine.c. Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com>
2013-02-19 18:59:09 +08:00
};
/** Free list to speed up creation */
coroutine: rewrite pool to avoid mutex This patch removes the mutex by using fancy lock-free manipulation of the pool. Lock-free stacks and queues are not hard, but they can suffer from the ABA problem so they are better avoided unless you have some deferred reclamation scheme like RCU. Otherwise you have to stick with adding to a list, and emptying it completely. This is what this patch does, by coupling a lock-free global list of available coroutines with per-CPU lists that are actually used on coroutine creation. Whenever the destruction pool is big enough, the next thread that runs out of coroutines will steal the whole destruction pool. This is positive in two ways: 1) the allocation does not have to do any atomic operation in the fast path, it's entirely using thread-local storage. Once every POOL_BATCH_SIZE allocations it will do a single atomic_xchg. Release does an atomic_cmpxchg loop, that hopefully doesn't cause any starvation, and an atomic_inc. A later patch will also remove atomic operations from the release path, and try to avoid the atomic_xchg altogether---succeeding in doing so if all devices either use ioeventfd or are not submitting requests actively. 2) in theory this should be completely adaptive. The number of coroutines around should be a little more than POOL_BATCH_SIZE * number of allocating threads; so this also empties qemu_coroutine_adjust_pool_size. (The previous pool size was POOL_BATCH_SIZE * number of block backends, so it was a bit more generous. But if you actually have many high-iodepth disks, it's better to put them in different iothreads, which will also use separate thread pools and aio=native file descriptors). This speeds up perf/cost (in tests/test-coroutine) by a factor of ~1.33. No matter if we end with some kind of coroutine bypass scheme or not, it cannot hurt to optimize hot code. Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> Reviewed-by: Fam Zheng <famz@redhat.com> Message-id: 1417518350-6167-6-git-send-email-pbonzini@redhat.com Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
2014-12-02 19:05:48 +08:00
static QSLIST_HEAD(, Coroutine) release_pool = QSLIST_HEAD_INITIALIZER(pool);
static unsigned int release_pool_size;
static __thread QSLIST_HEAD(, Coroutine) alloc_pool = QSLIST_HEAD_INITIALIZER(pool);
coroutine: try harder not to delete coroutines Placing coroutines on the global pool should be preferrable, because it can help all threads. But if the global pool is full, we can still try to save some allocations by stashing completed coroutines on the local pool. This is quite cheap too, because it does not require atomic operations, and provides a gain of 15% in the best case. Signed-off-by: Peter Lieven <pl@kamp.de> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> Reviewed-by: Fam Zheng <famz@redhat.com> Message-id: 1417518350-6167-8-git-send-email-pbonzini@redhat.com Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
2014-12-02 19:05:50 +08:00
static __thread unsigned int alloc_pool_size;
coroutine: rewrite pool to avoid mutex This patch removes the mutex by using fancy lock-free manipulation of the pool. Lock-free stacks and queues are not hard, but they can suffer from the ABA problem so they are better avoided unless you have some deferred reclamation scheme like RCU. Otherwise you have to stick with adding to a list, and emptying it completely. This is what this patch does, by coupling a lock-free global list of available coroutines with per-CPU lists that are actually used on coroutine creation. Whenever the destruction pool is big enough, the next thread that runs out of coroutines will steal the whole destruction pool. This is positive in two ways: 1) the allocation does not have to do any atomic operation in the fast path, it's entirely using thread-local storage. Once every POOL_BATCH_SIZE allocations it will do a single atomic_xchg. Release does an atomic_cmpxchg loop, that hopefully doesn't cause any starvation, and an atomic_inc. A later patch will also remove atomic operations from the release path, and try to avoid the atomic_xchg altogether---succeeding in doing so if all devices either use ioeventfd or are not submitting requests actively. 2) in theory this should be completely adaptive. The number of coroutines around should be a little more than POOL_BATCH_SIZE * number of allocating threads; so this also empties qemu_coroutine_adjust_pool_size. (The previous pool size was POOL_BATCH_SIZE * number of block backends, so it was a bit more generous. But if you actually have many high-iodepth disks, it's better to put them in different iothreads, which will also use separate thread pools and aio=native file descriptors). This speeds up perf/cost (in tests/test-coroutine) by a factor of ~1.33. No matter if we end with some kind of coroutine bypass scheme or not, it cannot hurt to optimize hot code. Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> Reviewed-by: Fam Zheng <famz@redhat.com> Message-id: 1417518350-6167-6-git-send-email-pbonzini@redhat.com Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
2014-12-02 19:05:48 +08:00
static __thread Notifier coroutine_pool_cleanup_notifier;
static void coroutine_pool_cleanup(Notifier *n, void *value)
{
Coroutine *co;
Coroutine *tmp;
QSLIST_FOREACH_SAFE(co, &alloc_pool, pool_next, tmp) {
QSLIST_REMOVE_HEAD(&alloc_pool, pool_next);
qemu_coroutine_delete(co);
}
}
coroutine: move pooling to common code The coroutine pool code is duplicated between the ucontext and sigaltstack backends, and absent from the win32 backend. But the code can be shared easily by moving it to qemu-coroutine.c. Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com>
2013-02-19 18:59:09 +08:00
coroutine: move entry argument to qemu_coroutine_create In practice the entry argument is always known at creation time, and it is confusing that sometimes qemu_coroutine_enter is used with a non-NULL argument to re-enter a coroutine (this happens in block/sheepdog.c and tests/test-coroutine.c). So pass the opaque value at creation time, for consistency with e.g. aio_bh_new. Mostly done with the following semantic patch: @ entry1 @ expression entry, arg, co; @@ - co = qemu_coroutine_create(entry); + co = qemu_coroutine_create(entry, arg); ... - qemu_coroutine_enter(co, arg); + qemu_coroutine_enter(co); @ entry2 @ expression entry, arg; identifier co; @@ - Coroutine *co = qemu_coroutine_create(entry); + Coroutine *co = qemu_coroutine_create(entry, arg); ... - qemu_coroutine_enter(co, arg); + qemu_coroutine_enter(co); @ entry3 @ expression entry, arg; @@ - qemu_coroutine_enter(qemu_coroutine_create(entry), arg); + qemu_coroutine_enter(qemu_coroutine_create(entry, arg)); @ reentry @ expression co; @@ - qemu_coroutine_enter(co, NULL); + qemu_coroutine_enter(co); except for the aforementioned few places where the semantic patch stumbled (as expected) and for test_co_queue, which would otherwise produce an uninitialized variable warning. Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> Reviewed-by: Fam Zheng <famz@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com>
2016-07-05 01:10:01 +08:00
Coroutine *qemu_coroutine_create(CoroutineEntry *entry, void *opaque)
coroutine: introduce coroutines Asynchronous code is becoming very complex. At the same time synchronous code is growing because it is convenient to write. Sometimes duplicate code paths are even added, one synchronous and the other asynchronous. This patch introduces coroutines which allow code that looks synchronous but is asynchronous under the covers. A coroutine has its own stack and is therefore able to preserve state across blocking operations, which traditionally require callback functions and manual marshalling of parameters. Creating and starting a coroutine is easy: coroutine = qemu_coroutine_create(my_coroutine); qemu_coroutine_enter(coroutine, my_data); The coroutine then executes until it returns or yields: void coroutine_fn my_coroutine(void *opaque) { MyData *my_data = opaque; /* do some work */ qemu_coroutine_yield(); /* do some more work */ } Yielding switches control back to the caller of qemu_coroutine_enter(). This is typically used to switch back to the main thread's event loop after issuing an asynchronous I/O request. The request callback will then invoke qemu_coroutine_enter() once more to switch back to the coroutine. Note that if coroutines are used only from threads which hold the global mutex they will never execute concurrently. This makes programming with coroutines easier than with threads. Race conditions cannot occur since only one coroutine may be active at any time. Other coroutines can only run across yield. This coroutines implementation is based on the gtk-vnc implementation written by Anthony Liguori <anthony@codemonkey.ws> but it has been significantly rewritten by Kevin Wolf <kwolf@redhat.com> to use setjmp()/longjmp() instead of the more expensive swapcontext() and by Paolo Bonzini <pbonzini@redhat.com> for Windows Fibers support. Signed-off-by: Kevin Wolf <kwolf@redhat.com> Signed-off-by: Stefan Hajnoczi <stefanha@linux.vnet.ibm.com>
2011-01-18 00:08:14 +08:00
{
coroutine: add ./configure --disable-coroutine-pool The 'gthread' coroutine backend was written before the freelist (aka pool) existed in qemu-coroutine.c. This means that every thread is expected to exit when its coroutine terminates. It is not possible to reuse threads from a pool. This patch automatically disables the pool when 'gthread' is used. This allows the 'gthread' backend to work again (for example, tests/test-coroutine completes successfully instead of hanging). I considered implementing thread reuse but I don't want quirks like CPU affinity differences due to coroutine threads being recycled. The 'gthread' backend is a reference backend and it's therefore okay to skip the pool optimization. Note this patch also makes it easy to toggle the pool for benchmarking purposes: ./configure --with-coroutine-backend=ucontext \ --disable-coroutine-pool Reported-by: Gabriel Kerneis <gabriel@kerneis.info> Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> Reviewed-by: Gabriel Kerneis <gabriel@kerneis.info> Signed-off-by: Kevin Wolf <kwolf@redhat.com>
2013-09-11 22:42:35 +08:00
Coroutine *co = NULL;
coroutine: move pooling to common code The coroutine pool code is duplicated between the ucontext and sigaltstack backends, and absent from the win32 backend. But the code can be shared easily by moving it to qemu-coroutine.c. Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com>
2013-02-19 18:59:09 +08:00
coroutine: add ./configure --disable-coroutine-pool The 'gthread' coroutine backend was written before the freelist (aka pool) existed in qemu-coroutine.c. This means that every thread is expected to exit when its coroutine terminates. It is not possible to reuse threads from a pool. This patch automatically disables the pool when 'gthread' is used. This allows the 'gthread' backend to work again (for example, tests/test-coroutine completes successfully instead of hanging). I considered implementing thread reuse but I don't want quirks like CPU affinity differences due to coroutine threads being recycled. The 'gthread' backend is a reference backend and it's therefore okay to skip the pool optimization. Note this patch also makes it easy to toggle the pool for benchmarking purposes: ./configure --with-coroutine-backend=ucontext \ --disable-coroutine-pool Reported-by: Gabriel Kerneis <gabriel@kerneis.info> Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> Reviewed-by: Gabriel Kerneis <gabriel@kerneis.info> Signed-off-by: Kevin Wolf <kwolf@redhat.com>
2013-09-11 22:42:35 +08:00
if (CONFIG_COROUTINE_POOL) {
coroutine: rewrite pool to avoid mutex This patch removes the mutex by using fancy lock-free manipulation of the pool. Lock-free stacks and queues are not hard, but they can suffer from the ABA problem so they are better avoided unless you have some deferred reclamation scheme like RCU. Otherwise you have to stick with adding to a list, and emptying it completely. This is what this patch does, by coupling a lock-free global list of available coroutines with per-CPU lists that are actually used on coroutine creation. Whenever the destruction pool is big enough, the next thread that runs out of coroutines will steal the whole destruction pool. This is positive in two ways: 1) the allocation does not have to do any atomic operation in the fast path, it's entirely using thread-local storage. Once every POOL_BATCH_SIZE allocations it will do a single atomic_xchg. Release does an atomic_cmpxchg loop, that hopefully doesn't cause any starvation, and an atomic_inc. A later patch will also remove atomic operations from the release path, and try to avoid the atomic_xchg altogether---succeeding in doing so if all devices either use ioeventfd or are not submitting requests actively. 2) in theory this should be completely adaptive. The number of coroutines around should be a little more than POOL_BATCH_SIZE * number of allocating threads; so this also empties qemu_coroutine_adjust_pool_size. (The previous pool size was POOL_BATCH_SIZE * number of block backends, so it was a bit more generous. But if you actually have many high-iodepth disks, it's better to put them in different iothreads, which will also use separate thread pools and aio=native file descriptors). This speeds up perf/cost (in tests/test-coroutine) by a factor of ~1.33. No matter if we end with some kind of coroutine bypass scheme or not, it cannot hurt to optimize hot code. Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> Reviewed-by: Fam Zheng <famz@redhat.com> Message-id: 1417518350-6167-6-git-send-email-pbonzini@redhat.com Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
2014-12-02 19:05:48 +08:00
co = QSLIST_FIRST(&alloc_pool);
if (!co) {
if (release_pool_size > POOL_BATCH_SIZE) {
/* Slow path; a good place to register the destructor, too. */
if (!coroutine_pool_cleanup_notifier.notify) {
coroutine_pool_cleanup_notifier.notify = coroutine_pool_cleanup;
qemu_thread_atexit_add(&coroutine_pool_cleanup_notifier);
}
/* This is not exact; there could be a little skew between
* release_pool_size and the actual size of release_pool. But
* it is just a heuristic, it does not need to be perfect.
*/
coroutine: try harder not to delete coroutines Placing coroutines on the global pool should be preferrable, because it can help all threads. But if the global pool is full, we can still try to save some allocations by stashing completed coroutines on the local pool. This is quite cheap too, because it does not require atomic operations, and provides a gain of 15% in the best case. Signed-off-by: Peter Lieven <pl@kamp.de> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> Reviewed-by: Fam Zheng <famz@redhat.com> Message-id: 1417518350-6167-8-git-send-email-pbonzini@redhat.com Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
2014-12-02 19:05:50 +08:00
alloc_pool_size = atomic_xchg(&release_pool_size, 0);
coroutine: rewrite pool to avoid mutex This patch removes the mutex by using fancy lock-free manipulation of the pool. Lock-free stacks and queues are not hard, but they can suffer from the ABA problem so they are better avoided unless you have some deferred reclamation scheme like RCU. Otherwise you have to stick with adding to a list, and emptying it completely. This is what this patch does, by coupling a lock-free global list of available coroutines with per-CPU lists that are actually used on coroutine creation. Whenever the destruction pool is big enough, the next thread that runs out of coroutines will steal the whole destruction pool. This is positive in two ways: 1) the allocation does not have to do any atomic operation in the fast path, it's entirely using thread-local storage. Once every POOL_BATCH_SIZE allocations it will do a single atomic_xchg. Release does an atomic_cmpxchg loop, that hopefully doesn't cause any starvation, and an atomic_inc. A later patch will also remove atomic operations from the release path, and try to avoid the atomic_xchg altogether---succeeding in doing so if all devices either use ioeventfd or are not submitting requests actively. 2) in theory this should be completely adaptive. The number of coroutines around should be a little more than POOL_BATCH_SIZE * number of allocating threads; so this also empties qemu_coroutine_adjust_pool_size. (The previous pool size was POOL_BATCH_SIZE * number of block backends, so it was a bit more generous. But if you actually have many high-iodepth disks, it's better to put them in different iothreads, which will also use separate thread pools and aio=native file descriptors). This speeds up perf/cost (in tests/test-coroutine) by a factor of ~1.33. No matter if we end with some kind of coroutine bypass scheme or not, it cannot hurt to optimize hot code. Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> Reviewed-by: Fam Zheng <famz@redhat.com> Message-id: 1417518350-6167-6-git-send-email-pbonzini@redhat.com Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
2014-12-02 19:05:48 +08:00
QSLIST_MOVE_ATOMIC(&alloc_pool, &release_pool);
co = QSLIST_FIRST(&alloc_pool);
}
}
coroutine: add ./configure --disable-coroutine-pool The 'gthread' coroutine backend was written before the freelist (aka pool) existed in qemu-coroutine.c. This means that every thread is expected to exit when its coroutine terminates. It is not possible to reuse threads from a pool. This patch automatically disables the pool when 'gthread' is used. This allows the 'gthread' backend to work again (for example, tests/test-coroutine completes successfully instead of hanging). I considered implementing thread reuse but I don't want quirks like CPU affinity differences due to coroutine threads being recycled. The 'gthread' backend is a reference backend and it's therefore okay to skip the pool optimization. Note this patch also makes it easy to toggle the pool for benchmarking purposes: ./configure --with-coroutine-backend=ucontext \ --disable-coroutine-pool Reported-by: Gabriel Kerneis <gabriel@kerneis.info> Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> Reviewed-by: Gabriel Kerneis <gabriel@kerneis.info> Signed-off-by: Kevin Wolf <kwolf@redhat.com>
2013-09-11 22:42:35 +08:00
if (co) {
coroutine: rewrite pool to avoid mutex This patch removes the mutex by using fancy lock-free manipulation of the pool. Lock-free stacks and queues are not hard, but they can suffer from the ABA problem so they are better avoided unless you have some deferred reclamation scheme like RCU. Otherwise you have to stick with adding to a list, and emptying it completely. This is what this patch does, by coupling a lock-free global list of available coroutines with per-CPU lists that are actually used on coroutine creation. Whenever the destruction pool is big enough, the next thread that runs out of coroutines will steal the whole destruction pool. This is positive in two ways: 1) the allocation does not have to do any atomic operation in the fast path, it's entirely using thread-local storage. Once every POOL_BATCH_SIZE allocations it will do a single atomic_xchg. Release does an atomic_cmpxchg loop, that hopefully doesn't cause any starvation, and an atomic_inc. A later patch will also remove atomic operations from the release path, and try to avoid the atomic_xchg altogether---succeeding in doing so if all devices either use ioeventfd or are not submitting requests actively. 2) in theory this should be completely adaptive. The number of coroutines around should be a little more than POOL_BATCH_SIZE * number of allocating threads; so this also empties qemu_coroutine_adjust_pool_size. (The previous pool size was POOL_BATCH_SIZE * number of block backends, so it was a bit more generous. But if you actually have many high-iodepth disks, it's better to put them in different iothreads, which will also use separate thread pools and aio=native file descriptors). This speeds up perf/cost (in tests/test-coroutine) by a factor of ~1.33. No matter if we end with some kind of coroutine bypass scheme or not, it cannot hurt to optimize hot code. Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> Reviewed-by: Fam Zheng <famz@redhat.com> Message-id: 1417518350-6167-6-git-send-email-pbonzini@redhat.com Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
2014-12-02 19:05:48 +08:00
QSLIST_REMOVE_HEAD(&alloc_pool, pool_next);
coroutine: try harder not to delete coroutines Placing coroutines on the global pool should be preferrable, because it can help all threads. But if the global pool is full, we can still try to save some allocations by stashing completed coroutines on the local pool. This is quite cheap too, because it does not require atomic operations, and provides a gain of 15% in the best case. Signed-off-by: Peter Lieven <pl@kamp.de> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> Reviewed-by: Fam Zheng <famz@redhat.com> Message-id: 1417518350-6167-8-git-send-email-pbonzini@redhat.com Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
2014-12-02 19:05:50 +08:00
alloc_pool_size--;
coroutine: add ./configure --disable-coroutine-pool The 'gthread' coroutine backend was written before the freelist (aka pool) existed in qemu-coroutine.c. This means that every thread is expected to exit when its coroutine terminates. It is not possible to reuse threads from a pool. This patch automatically disables the pool when 'gthread' is used. This allows the 'gthread' backend to work again (for example, tests/test-coroutine completes successfully instead of hanging). I considered implementing thread reuse but I don't want quirks like CPU affinity differences due to coroutine threads being recycled. The 'gthread' backend is a reference backend and it's therefore okay to skip the pool optimization. Note this patch also makes it easy to toggle the pool for benchmarking purposes: ./configure --with-coroutine-backend=ucontext \ --disable-coroutine-pool Reported-by: Gabriel Kerneis <gabriel@kerneis.info> Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> Reviewed-by: Gabriel Kerneis <gabriel@kerneis.info> Signed-off-by: Kevin Wolf <kwolf@redhat.com>
2013-09-11 22:42:35 +08:00
}
coroutine: protect global pool with a mutex The coroutine freelist is a global pool of unused coroutines. It avoids the setup/teardown overhead associated with the coroutine lifecycle. Since the pool is global, we need to synchronize access so that coroutines can be used outside the BQL. Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
2013-05-17 21:51:25 +08:00
}
if (!co) {
coroutine: move pooling to common code The coroutine pool code is duplicated between the ucontext and sigaltstack backends, and absent from the win32 backend. But the code can be shared easily by moving it to qemu-coroutine.c. Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com>
2013-02-19 18:59:09 +08:00
co = qemu_coroutine_new();
}
coroutine: introduce coroutines Asynchronous code is becoming very complex. At the same time synchronous code is growing because it is convenient to write. Sometimes duplicate code paths are even added, one synchronous and the other asynchronous. This patch introduces coroutines which allow code that looks synchronous but is asynchronous under the covers. A coroutine has its own stack and is therefore able to preserve state across blocking operations, which traditionally require callback functions and manual marshalling of parameters. Creating and starting a coroutine is easy: coroutine = qemu_coroutine_create(my_coroutine); qemu_coroutine_enter(coroutine, my_data); The coroutine then executes until it returns or yields: void coroutine_fn my_coroutine(void *opaque) { MyData *my_data = opaque; /* do some work */ qemu_coroutine_yield(); /* do some more work */ } Yielding switches control back to the caller of qemu_coroutine_enter(). This is typically used to switch back to the main thread's event loop after issuing an asynchronous I/O request. The request callback will then invoke qemu_coroutine_enter() once more to switch back to the coroutine. Note that if coroutines are used only from threads which hold the global mutex they will never execute concurrently. This makes programming with coroutines easier than with threads. Race conditions cannot occur since only one coroutine may be active at any time. Other coroutines can only run across yield. This coroutines implementation is based on the gtk-vnc implementation written by Anthony Liguori <anthony@codemonkey.ws> but it has been significantly rewritten by Kevin Wolf <kwolf@redhat.com> to use setjmp()/longjmp() instead of the more expensive swapcontext() and by Paolo Bonzini <pbonzini@redhat.com> for Windows Fibers support. Signed-off-by: Kevin Wolf <kwolf@redhat.com> Signed-off-by: Stefan Hajnoczi <stefanha@linux.vnet.ibm.com>
2011-01-18 00:08:14 +08:00
co->entry = entry;
coroutine: move entry argument to qemu_coroutine_create In practice the entry argument is always known at creation time, and it is confusing that sometimes qemu_coroutine_enter is used with a non-NULL argument to re-enter a coroutine (this happens in block/sheepdog.c and tests/test-coroutine.c). So pass the opaque value at creation time, for consistency with e.g. aio_bh_new. Mostly done with the following semantic patch: @ entry1 @ expression entry, arg, co; @@ - co = qemu_coroutine_create(entry); + co = qemu_coroutine_create(entry, arg); ... - qemu_coroutine_enter(co, arg); + qemu_coroutine_enter(co); @ entry2 @ expression entry, arg; identifier co; @@ - Coroutine *co = qemu_coroutine_create(entry); + Coroutine *co = qemu_coroutine_create(entry, arg); ... - qemu_coroutine_enter(co, arg); + qemu_coroutine_enter(co); @ entry3 @ expression entry, arg; @@ - qemu_coroutine_enter(qemu_coroutine_create(entry), arg); + qemu_coroutine_enter(qemu_coroutine_create(entry, arg)); @ reentry @ expression co; @@ - qemu_coroutine_enter(co, NULL); + qemu_coroutine_enter(co); except for the aforementioned few places where the semantic patch stumbled (as expected) and for test_co_queue, which would otherwise produce an uninitialized variable warning. Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> Reviewed-by: Fam Zheng <famz@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com>
2016-07-05 01:10:01 +08:00
co->entry_arg = opaque;
coroutine: use QSIMPLEQ instead of QTAILQ CoQueue do not need to remove any element but the head of the list; processing is always strictly FIFO. Therefore, the simpler singly-linked QSIMPLEQ can be used instead. Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> Reviewed-by: Fam Zheng <famz@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com>
2016-07-05 01:09:59 +08:00
QSIMPLEQ_INIT(&co->co_queue_wakeup);
coroutine: introduce coroutines Asynchronous code is becoming very complex. At the same time synchronous code is growing because it is convenient to write. Sometimes duplicate code paths are even added, one synchronous and the other asynchronous. This patch introduces coroutines which allow code that looks synchronous but is asynchronous under the covers. A coroutine has its own stack and is therefore able to preserve state across blocking operations, which traditionally require callback functions and manual marshalling of parameters. Creating and starting a coroutine is easy: coroutine = qemu_coroutine_create(my_coroutine); qemu_coroutine_enter(coroutine, my_data); The coroutine then executes until it returns or yields: void coroutine_fn my_coroutine(void *opaque) { MyData *my_data = opaque; /* do some work */ qemu_coroutine_yield(); /* do some more work */ } Yielding switches control back to the caller of qemu_coroutine_enter(). This is typically used to switch back to the main thread's event loop after issuing an asynchronous I/O request. The request callback will then invoke qemu_coroutine_enter() once more to switch back to the coroutine. Note that if coroutines are used only from threads which hold the global mutex they will never execute concurrently. This makes programming with coroutines easier than with threads. Race conditions cannot occur since only one coroutine may be active at any time. Other coroutines can only run across yield. This coroutines implementation is based on the gtk-vnc implementation written by Anthony Liguori <anthony@codemonkey.ws> but it has been significantly rewritten by Kevin Wolf <kwolf@redhat.com> to use setjmp()/longjmp() instead of the more expensive swapcontext() and by Paolo Bonzini <pbonzini@redhat.com> for Windows Fibers support. Signed-off-by: Kevin Wolf <kwolf@redhat.com> Signed-off-by: Stefan Hajnoczi <stefanha@linux.vnet.ibm.com>
2011-01-18 00:08:14 +08:00
return co;
}
coroutine: move pooling to common code The coroutine pool code is duplicated between the ucontext and sigaltstack backends, and absent from the win32 backend. But the code can be shared easily by moving it to qemu-coroutine.c. Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com>
2013-02-19 18:59:09 +08:00
static void coroutine_delete(Coroutine *co)
{
coroutine: rewrite pool to avoid mutex This patch removes the mutex by using fancy lock-free manipulation of the pool. Lock-free stacks and queues are not hard, but they can suffer from the ABA problem so they are better avoided unless you have some deferred reclamation scheme like RCU. Otherwise you have to stick with adding to a list, and emptying it completely. This is what this patch does, by coupling a lock-free global list of available coroutines with per-CPU lists that are actually used on coroutine creation. Whenever the destruction pool is big enough, the next thread that runs out of coroutines will steal the whole destruction pool. This is positive in two ways: 1) the allocation does not have to do any atomic operation in the fast path, it's entirely using thread-local storage. Once every POOL_BATCH_SIZE allocations it will do a single atomic_xchg. Release does an atomic_cmpxchg loop, that hopefully doesn't cause any starvation, and an atomic_inc. A later patch will also remove atomic operations from the release path, and try to avoid the atomic_xchg altogether---succeeding in doing so if all devices either use ioeventfd or are not submitting requests actively. 2) in theory this should be completely adaptive. The number of coroutines around should be a little more than POOL_BATCH_SIZE * number of allocating threads; so this also empties qemu_coroutine_adjust_pool_size. (The previous pool size was POOL_BATCH_SIZE * number of block backends, so it was a bit more generous. But if you actually have many high-iodepth disks, it's better to put them in different iothreads, which will also use separate thread pools and aio=native file descriptors). This speeds up perf/cost (in tests/test-coroutine) by a factor of ~1.33. No matter if we end with some kind of coroutine bypass scheme or not, it cannot hurt to optimize hot code. Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> Reviewed-by: Fam Zheng <famz@redhat.com> Message-id: 1417518350-6167-6-git-send-email-pbonzini@redhat.com Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
2014-12-02 19:05:48 +08:00
co->caller = NULL;
coroutine: add ./configure --disable-coroutine-pool The 'gthread' coroutine backend was written before the freelist (aka pool) existed in qemu-coroutine.c. This means that every thread is expected to exit when its coroutine terminates. It is not possible to reuse threads from a pool. This patch automatically disables the pool when 'gthread' is used. This allows the 'gthread' backend to work again (for example, tests/test-coroutine completes successfully instead of hanging). I considered implementing thread reuse but I don't want quirks like CPU affinity differences due to coroutine threads being recycled. The 'gthread' backend is a reference backend and it's therefore okay to skip the pool optimization. Note this patch also makes it easy to toggle the pool for benchmarking purposes: ./configure --with-coroutine-backend=ucontext \ --disable-coroutine-pool Reported-by: Gabriel Kerneis <gabriel@kerneis.info> Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> Reviewed-by: Gabriel Kerneis <gabriel@kerneis.info> Signed-off-by: Kevin Wolf <kwolf@redhat.com>
2013-09-11 22:42:35 +08:00
if (CONFIG_COROUTINE_POOL) {
coroutine: rewrite pool to avoid mutex This patch removes the mutex by using fancy lock-free manipulation of the pool. Lock-free stacks and queues are not hard, but they can suffer from the ABA problem so they are better avoided unless you have some deferred reclamation scheme like RCU. Otherwise you have to stick with adding to a list, and emptying it completely. This is what this patch does, by coupling a lock-free global list of available coroutines with per-CPU lists that are actually used on coroutine creation. Whenever the destruction pool is big enough, the next thread that runs out of coroutines will steal the whole destruction pool. This is positive in two ways: 1) the allocation does not have to do any atomic operation in the fast path, it's entirely using thread-local storage. Once every POOL_BATCH_SIZE allocations it will do a single atomic_xchg. Release does an atomic_cmpxchg loop, that hopefully doesn't cause any starvation, and an atomic_inc. A later patch will also remove atomic operations from the release path, and try to avoid the atomic_xchg altogether---succeeding in doing so if all devices either use ioeventfd or are not submitting requests actively. 2) in theory this should be completely adaptive. The number of coroutines around should be a little more than POOL_BATCH_SIZE * number of allocating threads; so this also empties qemu_coroutine_adjust_pool_size. (The previous pool size was POOL_BATCH_SIZE * number of block backends, so it was a bit more generous. But if you actually have many high-iodepth disks, it's better to put them in different iothreads, which will also use separate thread pools and aio=native file descriptors). This speeds up perf/cost (in tests/test-coroutine) by a factor of ~1.33. No matter if we end with some kind of coroutine bypass scheme or not, it cannot hurt to optimize hot code. Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> Reviewed-by: Fam Zheng <famz@redhat.com> Message-id: 1417518350-6167-6-git-send-email-pbonzini@redhat.com Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
2014-12-02 19:05:48 +08:00
if (release_pool_size < POOL_BATCH_SIZE * 2) {
QSLIST_INSERT_HEAD_ATOMIC(&release_pool, co, pool_next);
atomic_inc(&release_pool_size);
coroutine: add ./configure --disable-coroutine-pool The 'gthread' coroutine backend was written before the freelist (aka pool) existed in qemu-coroutine.c. This means that every thread is expected to exit when its coroutine terminates. It is not possible to reuse threads from a pool. This patch automatically disables the pool when 'gthread' is used. This allows the 'gthread' backend to work again (for example, tests/test-coroutine completes successfully instead of hanging). I considered implementing thread reuse but I don't want quirks like CPU affinity differences due to coroutine threads being recycled. The 'gthread' backend is a reference backend and it's therefore okay to skip the pool optimization. Note this patch also makes it easy to toggle the pool for benchmarking purposes: ./configure --with-coroutine-backend=ucontext \ --disable-coroutine-pool Reported-by: Gabriel Kerneis <gabriel@kerneis.info> Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> Reviewed-by: Gabriel Kerneis <gabriel@kerneis.info> Signed-off-by: Kevin Wolf <kwolf@redhat.com>
2013-09-11 22:42:35 +08:00
return;
}
coroutine: try harder not to delete coroutines Placing coroutines on the global pool should be preferrable, because it can help all threads. But if the global pool is full, we can still try to save some allocations by stashing completed coroutines on the local pool. This is quite cheap too, because it does not require atomic operations, and provides a gain of 15% in the best case. Signed-off-by: Peter Lieven <pl@kamp.de> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> Reviewed-by: Fam Zheng <famz@redhat.com> Message-id: 1417518350-6167-8-git-send-email-pbonzini@redhat.com Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
2014-12-02 19:05:50 +08:00
if (alloc_pool_size < POOL_BATCH_SIZE) {
QSLIST_INSERT_HEAD(&alloc_pool, co, pool_next);
alloc_pool_size++;
return;
}
coroutine: move pooling to common code The coroutine pool code is duplicated between the ucontext and sigaltstack backends, and absent from the win32 backend. But the code can be shared easily by moving it to qemu-coroutine.c. Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com>
2013-02-19 18:59:09 +08:00
}
qemu_coroutine_delete(co);
}
coroutine: move entry argument to qemu_coroutine_create In practice the entry argument is always known at creation time, and it is confusing that sometimes qemu_coroutine_enter is used with a non-NULL argument to re-enter a coroutine (this happens in block/sheepdog.c and tests/test-coroutine.c). So pass the opaque value at creation time, for consistency with e.g. aio_bh_new. Mostly done with the following semantic patch: @ entry1 @ expression entry, arg, co; @@ - co = qemu_coroutine_create(entry); + co = qemu_coroutine_create(entry, arg); ... - qemu_coroutine_enter(co, arg); + qemu_coroutine_enter(co); @ entry2 @ expression entry, arg; identifier co; @@ - Coroutine *co = qemu_coroutine_create(entry); + Coroutine *co = qemu_coroutine_create(entry, arg); ... - qemu_coroutine_enter(co, arg); + qemu_coroutine_enter(co); @ entry3 @ expression entry, arg; @@ - qemu_coroutine_enter(qemu_coroutine_create(entry), arg); + qemu_coroutine_enter(qemu_coroutine_create(entry, arg)); @ reentry @ expression co; @@ - qemu_coroutine_enter(co, NULL); + qemu_coroutine_enter(co); except for the aforementioned few places where the semantic patch stumbled (as expected) and for test_co_queue, which would otherwise produce an uninitialized variable warning. Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> Reviewed-by: Fam Zheng <famz@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com>
2016-07-05 01:10:01 +08:00
void qemu_coroutine_enter(Coroutine *co)
coroutine: introduce coroutines Asynchronous code is becoming very complex. At the same time synchronous code is growing because it is convenient to write. Sometimes duplicate code paths are even added, one synchronous and the other asynchronous. This patch introduces coroutines which allow code that looks synchronous but is asynchronous under the covers. A coroutine has its own stack and is therefore able to preserve state across blocking operations, which traditionally require callback functions and manual marshalling of parameters. Creating and starting a coroutine is easy: coroutine = qemu_coroutine_create(my_coroutine); qemu_coroutine_enter(coroutine, my_data); The coroutine then executes until it returns or yields: void coroutine_fn my_coroutine(void *opaque) { MyData *my_data = opaque; /* do some work */ qemu_coroutine_yield(); /* do some more work */ } Yielding switches control back to the caller of qemu_coroutine_enter(). This is typically used to switch back to the main thread's event loop after issuing an asynchronous I/O request. The request callback will then invoke qemu_coroutine_enter() once more to switch back to the coroutine. Note that if coroutines are used only from threads which hold the global mutex they will never execute concurrently. This makes programming with coroutines easier than with threads. Race conditions cannot occur since only one coroutine may be active at any time. Other coroutines can only run across yield. This coroutines implementation is based on the gtk-vnc implementation written by Anthony Liguori <anthony@codemonkey.ws> but it has been significantly rewritten by Kevin Wolf <kwolf@redhat.com> to use setjmp()/longjmp() instead of the more expensive swapcontext() and by Paolo Bonzini <pbonzini@redhat.com> for Windows Fibers support. Signed-off-by: Kevin Wolf <kwolf@redhat.com> Signed-off-by: Stefan Hajnoczi <stefanha@linux.vnet.ibm.com>
2011-01-18 00:08:14 +08:00
{
Coroutine *self = qemu_coroutine_self();
coroutine: Clean up qemu_coroutine_enter() qemu_coroutine_enter() is now the only user of coroutine_swap(). Both functions are short, so inline it. Also, using COROUTINE_YIELD is now even more confusing because this code is never called during qemu_coroutine_yield() any more. In fact, this value is never read back, so we can just introduce a new COROUTINE_ENTER which documents the purpose of the task switch better. Signed-off-by: Kevin Wolf <kwolf@redhat.com> Reviewed-by: Paolo Bonzini <pbonzini@redhat.com>
2015-02-10 18:31:52 +08:00
CoroutineAction ret;
coroutine: introduce coroutines Asynchronous code is becoming very complex. At the same time synchronous code is growing because it is convenient to write. Sometimes duplicate code paths are even added, one synchronous and the other asynchronous. This patch introduces coroutines which allow code that looks synchronous but is asynchronous under the covers. A coroutine has its own stack and is therefore able to preserve state across blocking operations, which traditionally require callback functions and manual marshalling of parameters. Creating and starting a coroutine is easy: coroutine = qemu_coroutine_create(my_coroutine); qemu_coroutine_enter(coroutine, my_data); The coroutine then executes until it returns or yields: void coroutine_fn my_coroutine(void *opaque) { MyData *my_data = opaque; /* do some work */ qemu_coroutine_yield(); /* do some more work */ } Yielding switches control back to the caller of qemu_coroutine_enter(). This is typically used to switch back to the main thread's event loop after issuing an asynchronous I/O request. The request callback will then invoke qemu_coroutine_enter() once more to switch back to the coroutine. Note that if coroutines are used only from threads which hold the global mutex they will never execute concurrently. This makes programming with coroutines easier than with threads. Race conditions cannot occur since only one coroutine may be active at any time. Other coroutines can only run across yield. This coroutines implementation is based on the gtk-vnc implementation written by Anthony Liguori <anthony@codemonkey.ws> but it has been significantly rewritten by Kevin Wolf <kwolf@redhat.com> to use setjmp()/longjmp() instead of the more expensive swapcontext() and by Paolo Bonzini <pbonzini@redhat.com> for Windows Fibers support. Signed-off-by: Kevin Wolf <kwolf@redhat.com> Signed-off-by: Stefan Hajnoczi <stefanha@linux.vnet.ibm.com>
2011-01-18 00:08:14 +08:00
coroutine: move entry argument to qemu_coroutine_create In practice the entry argument is always known at creation time, and it is confusing that sometimes qemu_coroutine_enter is used with a non-NULL argument to re-enter a coroutine (this happens in block/sheepdog.c and tests/test-coroutine.c). So pass the opaque value at creation time, for consistency with e.g. aio_bh_new. Mostly done with the following semantic patch: @ entry1 @ expression entry, arg, co; @@ - co = qemu_coroutine_create(entry); + co = qemu_coroutine_create(entry, arg); ... - qemu_coroutine_enter(co, arg); + qemu_coroutine_enter(co); @ entry2 @ expression entry, arg; identifier co; @@ - Coroutine *co = qemu_coroutine_create(entry); + Coroutine *co = qemu_coroutine_create(entry, arg); ... - qemu_coroutine_enter(co, arg); + qemu_coroutine_enter(co); @ entry3 @ expression entry, arg; @@ - qemu_coroutine_enter(qemu_coroutine_create(entry), arg); + qemu_coroutine_enter(qemu_coroutine_create(entry, arg)); @ reentry @ expression co; @@ - qemu_coroutine_enter(co, NULL); + qemu_coroutine_enter(co); except for the aforementioned few places where the semantic patch stumbled (as expected) and for test_co_queue, which would otherwise produce an uninitialized variable warning. Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> Reviewed-by: Fam Zheng <famz@redhat.com> Signed-off-by: Kevin Wolf <kwolf@redhat.com>
2016-07-05 01:10:01 +08:00
trace_qemu_coroutine_enter(self, co, co->entry_arg);
coroutine: introduce coroutines Asynchronous code is becoming very complex. At the same time synchronous code is growing because it is convenient to write. Sometimes duplicate code paths are even added, one synchronous and the other asynchronous. This patch introduces coroutines which allow code that looks synchronous but is asynchronous under the covers. A coroutine has its own stack and is therefore able to preserve state across blocking operations, which traditionally require callback functions and manual marshalling of parameters. Creating and starting a coroutine is easy: coroutine = qemu_coroutine_create(my_coroutine); qemu_coroutine_enter(coroutine, my_data); The coroutine then executes until it returns or yields: void coroutine_fn my_coroutine(void *opaque) { MyData *my_data = opaque; /* do some work */ qemu_coroutine_yield(); /* do some more work */ } Yielding switches control back to the caller of qemu_coroutine_enter(). This is typically used to switch back to the main thread's event loop after issuing an asynchronous I/O request. The request callback will then invoke qemu_coroutine_enter() once more to switch back to the coroutine. Note that if coroutines are used only from threads which hold the global mutex they will never execute concurrently. This makes programming with coroutines easier than with threads. Race conditions cannot occur since only one coroutine may be active at any time. Other coroutines can only run across yield. This coroutines implementation is based on the gtk-vnc implementation written by Anthony Liguori <anthony@codemonkey.ws> but it has been significantly rewritten by Kevin Wolf <kwolf@redhat.com> to use setjmp()/longjmp() instead of the more expensive swapcontext() and by Paolo Bonzini <pbonzini@redhat.com> for Windows Fibers support. Signed-off-by: Kevin Wolf <kwolf@redhat.com> Signed-off-by: Stefan Hajnoczi <stefanha@linux.vnet.ibm.com>
2011-01-18 00:08:14 +08:00
if (co->caller) {
fprintf(stderr, "Co-routine re-entered recursively\n");
abort();
}
co->caller = self;
coroutine: Clean up qemu_coroutine_enter() qemu_coroutine_enter() is now the only user of coroutine_swap(). Both functions are short, so inline it. Also, using COROUTINE_YIELD is now even more confusing because this code is never called during qemu_coroutine_yield() any more. In fact, this value is never read back, so we can just introduce a new COROUTINE_ENTER which documents the purpose of the task switch better. Signed-off-by: Kevin Wolf <kwolf@redhat.com> Reviewed-by: Paolo Bonzini <pbonzini@redhat.com>
2015-02-10 18:31:52 +08:00
ret = qemu_coroutine_switch(self, co, COROUTINE_ENTER);
qemu_co_queue_run_restart(co);
switch (ret) {
case COROUTINE_YIELD:
return;
case COROUTINE_TERMINATE:
coroutine: Assert that no locks are held on termination A coroutine that takes a lock must also release it again. If the coroutine terminates without having released all its locks, it's buggy and we'll probably run into a deadlock sooner or later. Make sure that we don't get such cases. Signed-off-by: Kevin Wolf <kwolf@redhat.com> Reviewed-by: Paolo Bonzini <pbonzini@redhat.com> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
2016-08-11 23:51:59 +08:00
assert(!co->locks_held);
coroutine: Clean up qemu_coroutine_enter() qemu_coroutine_enter() is now the only user of coroutine_swap(). Both functions are short, so inline it. Also, using COROUTINE_YIELD is now even more confusing because this code is never called during qemu_coroutine_yield() any more. In fact, this value is never read back, so we can just introduce a new COROUTINE_ENTER which documents the purpose of the task switch better. Signed-off-by: Kevin Wolf <kwolf@redhat.com> Reviewed-by: Paolo Bonzini <pbonzini@redhat.com>
2015-02-10 18:31:52 +08:00
trace_qemu_coroutine_terminate(co);
coroutine_delete(co);
return;
default:
abort();
}
coroutine: introduce coroutines Asynchronous code is becoming very complex. At the same time synchronous code is growing because it is convenient to write. Sometimes duplicate code paths are even added, one synchronous and the other asynchronous. This patch introduces coroutines which allow code that looks synchronous but is asynchronous under the covers. A coroutine has its own stack and is therefore able to preserve state across blocking operations, which traditionally require callback functions and manual marshalling of parameters. Creating and starting a coroutine is easy: coroutine = qemu_coroutine_create(my_coroutine); qemu_coroutine_enter(coroutine, my_data); The coroutine then executes until it returns or yields: void coroutine_fn my_coroutine(void *opaque) { MyData *my_data = opaque; /* do some work */ qemu_coroutine_yield(); /* do some more work */ } Yielding switches control back to the caller of qemu_coroutine_enter(). This is typically used to switch back to the main thread's event loop after issuing an asynchronous I/O request. The request callback will then invoke qemu_coroutine_enter() once more to switch back to the coroutine. Note that if coroutines are used only from threads which hold the global mutex they will never execute concurrently. This makes programming with coroutines easier than with threads. Race conditions cannot occur since only one coroutine may be active at any time. Other coroutines can only run across yield. This coroutines implementation is based on the gtk-vnc implementation written by Anthony Liguori <anthony@codemonkey.ws> but it has been significantly rewritten by Kevin Wolf <kwolf@redhat.com> to use setjmp()/longjmp() instead of the more expensive swapcontext() and by Paolo Bonzini <pbonzini@redhat.com> for Windows Fibers support. Signed-off-by: Kevin Wolf <kwolf@redhat.com> Signed-off-by: Stefan Hajnoczi <stefanha@linux.vnet.ibm.com>
2011-01-18 00:08:14 +08:00
}
void coroutine_fn qemu_coroutine_yield(void)
{
Coroutine *self = qemu_coroutine_self();
Coroutine *to = self->caller;
trace_qemu_coroutine_yield(self, to);
if (!to) {
fprintf(stderr, "Co-routine is yielding to no one\n");
abort();
}
self->caller = NULL;
coroutine: Fix use after free with qemu_coroutine_yield() Instead of using the same function for entering and exiting coroutines, and hoping that it doesn't add any functionality that hurts with the parameters used for exiting, we can just directly call into the real task switch in qemu_coroutine_switch(). This fixes a use-after-free scenario where reentering a coroutine that has yielded still accesses the old parent coroutine (which may have meanwhile terminated) in the part of coroutine_swap() that follows qemu_coroutine_switch(). Cc: qemu-stable@nongnu.org Signed-off-by: Kevin Wolf <kwolf@redhat.com> Reviewed-by: Paolo Bonzini <pbonzini@redhat.com>
2015-02-10 18:17:53 +08:00
qemu_coroutine_switch(self, to, COROUTINE_YIELD);
coroutine: introduce coroutines Asynchronous code is becoming very complex. At the same time synchronous code is growing because it is convenient to write. Sometimes duplicate code paths are even added, one synchronous and the other asynchronous. This patch introduces coroutines which allow code that looks synchronous but is asynchronous under the covers. A coroutine has its own stack and is therefore able to preserve state across blocking operations, which traditionally require callback functions and manual marshalling of parameters. Creating and starting a coroutine is easy: coroutine = qemu_coroutine_create(my_coroutine); qemu_coroutine_enter(coroutine, my_data); The coroutine then executes until it returns or yields: void coroutine_fn my_coroutine(void *opaque) { MyData *my_data = opaque; /* do some work */ qemu_coroutine_yield(); /* do some more work */ } Yielding switches control back to the caller of qemu_coroutine_enter(). This is typically used to switch back to the main thread's event loop after issuing an asynchronous I/O request. The request callback will then invoke qemu_coroutine_enter() once more to switch back to the coroutine. Note that if coroutines are used only from threads which hold the global mutex they will never execute concurrently. This makes programming with coroutines easier than with threads. Race conditions cannot occur since only one coroutine may be active at any time. Other coroutines can only run across yield. This coroutines implementation is based on the gtk-vnc implementation written by Anthony Liguori <anthony@codemonkey.ws> but it has been significantly rewritten by Kevin Wolf <kwolf@redhat.com> to use setjmp()/longjmp() instead of the more expensive swapcontext() and by Paolo Bonzini <pbonzini@redhat.com> for Windows Fibers support. Signed-off-by: Kevin Wolf <kwolf@redhat.com> Signed-off-by: Stefan Hajnoczi <stefanha@linux.vnet.ibm.com>
2011-01-18 00:08:14 +08:00
}
Reference in New Issue Copy Permalink