The following changes since commit 9ac5df20f51fabcba0d902025df4bd7ea987c158: Merge remote-tracking branch 'remotes/pmaydell/tags/pull-target-arm-20200221-1' into staging (2020-02-21 16:18:38 +0000) are available in the Git repository at: https://github.com/stefanha/qemu.git tags/block-pull-request for you to fetch changes up to e5c59355ae9f724777c61c859292ec9db2c8c2ab: fuzz: add documentation to docs/devel/ (2020-02-22 08:26:48 +0000) ---------------------------------------------------------------- Pull request This pull request contains a virtio-blk/scsi performance optimization, event loop scalability improvements, and a qtest-based device fuzzing framework. I am including the fuzzing patches because I have reviewed them and Thomas Huth is currently away on leave. ---------------------------------------------------------------- Alexander Bulekov (22): softmmu: move vl.c to softmmu/ softmmu: split off vl.c:main() into main.c module: check module wasn't already initialized fuzz: add FUZZ_TARGET module type qtest: add qtest_server_send abstraction libqtest: add a layer of abstraction to send/recv libqtest: make bufwrite rely on the TransportOps qtest: add in-process incoming command handler libqos: rename i2c_send and i2c_recv libqos: split qos-test and libqos makefile vars libqos: move useful qos-test funcs to qos_external fuzz: add fuzzer skeleton exec: keep ram block across fork when using qtest main: keep rcu_atfork callback enabled for qtest fuzz: support for fork-based fuzzing. fuzz: add support for qos-assisted fuzz targets fuzz: add target/fuzz makefile rules fuzz: add configure flag --enable-fuzzing fuzz: add i440fx fuzz targets fuzz: add virtio-net fuzz target fuzz: add virtio-scsi fuzz target fuzz: add documentation to docs/devel/ Denis Plotnikov (1): virtio: increase virtqueue size for virtio-scsi and virtio-blk Paolo Bonzini (1): rcu_queue: add QSLIST functions Stefan Hajnoczi (7): aio-posix: avoid reacquiring rcu_read_lock() when polling util/async: make bh_aio_poll() O(1) aio-posix: fix use after leaving scope in aio_poll() aio-posix: don't pass ns timeout to epoll_wait() qemu/queue.h: add QLIST_SAFE_REMOVE() aio-posix: make AioHandler deletion O(1) aio-posix: make AioHandler dispatch O(1) with epoll MAINTAINERS | 11 +- Makefile | 15 +- Makefile.objs | 2 - Makefile.target | 19 ++- block.c | 5 +- chardev/spice.c | 4 +- configure | 39 +++++ docs/devel/fuzzing.txt | 116 ++++++++++++++ exec.c | 12 +- hw/block/virtio-blk.c | 2 +- hw/core/machine.c | 2 + hw/scsi/virtio-scsi.c | 2 +- include/block/aio.h | 26 ++- include/qemu/module.h | 4 +- include/qemu/queue.h | 32 +++- include/qemu/rcu_queue.h | 47 ++++++ include/sysemu/qtest.h | 4 + include/sysemu/sysemu.h | 4 + qtest.c | 31 +++- scripts/checkpatch.pl | 2 +- scripts/get_maintainer.pl | 3 +- softmmu/Makefile.objs | 3 + softmmu/main.c | 53 +++++++ vl.c => softmmu/vl.c | 48 +++--- tests/Makefile.include | 2 + tests/qtest/Makefile.include | 72 +++++---- tests/qtest/fuzz/Makefile.include | 18 +++ tests/qtest/fuzz/fork_fuzz.c | 55 +++++++ tests/qtest/fuzz/fork_fuzz.h | 23 +++ tests/qtest/fuzz/fork_fuzz.ld | 37 +++++ tests/qtest/fuzz/fuzz.c | 179 +++++++++++++++++++++ tests/qtest/fuzz/fuzz.h | 95 +++++++++++ tests/qtest/fuzz/i440fx_fuzz.c | 193 ++++++++++++++++++++++ tests/qtest/fuzz/qos_fuzz.c | 234 +++++++++++++++++++++++++++ tests/qtest/fuzz/qos_fuzz.h | 33 ++++ tests/qtest/fuzz/virtio_net_fuzz.c | 198 +++++++++++++++++++++++ tests/qtest/fuzz/virtio_scsi_fuzz.c | 213 +++++++++++++++++++++++++ tests/qtest/libqos/i2c.c | 10 +- tests/qtest/libqos/i2c.h | 4 +- tests/qtest/libqos/qos_external.c | 168 ++++++++++++++++++++ tests/qtest/libqos/qos_external.h | 28 ++++ tests/qtest/libqtest.c | 119 ++++++++++++-- tests/qtest/libqtest.h | 4 + tests/qtest/pca9552-test.c | 10 +- tests/qtest/qos-test.c | 132 +--------------- tests/test-aio.c | 3 +- tests/test-rcu-list.c | 16 ++ tests/test-rcu-slist.c | 2 + util/aio-posix.c | 187 +++++++++++++++------- util/async.c | 237 ++++++++++++++++------------ util/module.c | 7 + 51 files changed, 2365 insertions(+), 400 deletions(-) create mode 100644 docs/devel/fuzzing.txt create mode 100644 softmmu/Makefile.objs create mode 100644 softmmu/main.c rename vl.c => softmmu/vl.c (99%) create mode 100644 tests/qtest/fuzz/Makefile.include create mode 100644 tests/qtest/fuzz/fork_fuzz.c create mode 100644 tests/qtest/fuzz/fork_fuzz.h create mode 100644 tests/qtest/fuzz/fork_fuzz.ld create mode 100644 tests/qtest/fuzz/fuzz.c create mode 100644 tests/qtest/fuzz/fuzz.h create mode 100644 tests/qtest/fuzz/i440fx_fuzz.c create mode 100644 tests/qtest/fuzz/qos_fuzz.c create mode 100644 tests/qtest/fuzz/qos_fuzz.h create mode 100644 tests/qtest/fuzz/virtio_net_fuzz.c create mode 100644 tests/qtest/fuzz/virtio_scsi_fuzz.c create mode 100644 tests/qtest/libqos/qos_external.c create mode 100644 tests/qtest/libqos/qos_external.h create mode 100644 tests/test-rcu-slist.c -- 2.24.1 From: Denis Plotnikov <dplotnikov@virtuozzo.com> The goal is to reduce the amount of requests issued by a guest on 1M reads/writes. This rises the performance up to 4% on that kind of disk access pattern. The maximum chunk size to be used for the guest disk accessing is limited with seg_max parameter, which represents the max amount of pices in the scatter-geather list in one guest disk request. Since seg_max is virqueue_size dependent, increasing the virtqueue size increases seg_max, which, in turn, increases the maximum size of data to be read/write from a guest disk. More details in the original problem statment: https://lists.gnu.org/archive/html/qemu-devel/2017-12/msg03721.html Suggested-by: Denis V. Lunev <den@openvz.org> Signed-off-by: Denis Plotnikov <dplotnikov@virtuozzo.com> Message-id: 20200214074648.958-1-dplotnikov@virtuozzo.com Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- hw/block/virtio-blk.c | 2 +- hw/core/machine.c | 2 ++ hw/scsi/virtio-scsi.c | 2 +- 3 files changed, 4 insertions(+), 2 deletions(-) diff --git a/hw/block/virtio-blk.c b/hw/block/virtio-blk.c index XXXXXXX..XXXXXXX 100644 --- a/hw/block/virtio-blk.c +++ b/hw/block/virtio-blk.c @@ -XXX,XX +XXX,XX @@ static Property virtio_blk_properties[] = { DEFINE_PROP_BIT("request-merging", VirtIOBlock, conf.request_merging, 0, true), DEFINE_PROP_UINT16("num-queues", VirtIOBlock, conf.num_queues, 1), - DEFINE_PROP_UINT16("queue-size", VirtIOBlock, conf.queue_size, 128), + DEFINE_PROP_UINT16("queue-size", VirtIOBlock, conf.queue_size, 256), DEFINE_PROP_BOOL("seg-max-adjust", VirtIOBlock, conf.seg_max_adjust, true), DEFINE_PROP_LINK("iothread", VirtIOBlock, conf.iothread, TYPE_IOTHREAD, IOThread *), diff --git a/hw/core/machine.c b/hw/core/machine.c index XXXXXXX..XXXXXXX 100644 --- a/hw/core/machine.c +++ b/hw/core/machine.c @@ -XXX,XX +XXX,XX @@ #include "hw/mem/nvdimm.h" GlobalProperty hw_compat_4_2[] = { + { "virtio-blk-device", "queue-size", "128"}, + { "virtio-scsi-device", "virtqueue_size", "128"}, { "virtio-blk-device", "x-enable-wce-if-config-wce", "off" }, { "virtio-blk-device", "seg-max-adjust", "off"}, { "virtio-scsi-device", "seg_max_adjust", "off"}, diff --git a/hw/scsi/virtio-scsi.c b/hw/scsi/virtio-scsi.c index XXXXXXX..XXXXXXX 100644 --- a/hw/scsi/virtio-scsi.c +++ b/hw/scsi/virtio-scsi.c @@ -XXX,XX +XXX,XX @@ static void virtio_scsi_device_unrealize(DeviceState *dev, Error **errp) static Property virtio_scsi_properties[] = { DEFINE_PROP_UINT32("num_queues", VirtIOSCSI, parent_obj.conf.num_queues, 1), DEFINE_PROP_UINT32("virtqueue_size", VirtIOSCSI, - parent_obj.conf.virtqueue_size, 128), + parent_obj.conf.virtqueue_size, 256), DEFINE_PROP_BOOL("seg_max_adjust", VirtIOSCSI, parent_obj.conf.seg_max_adjust, true), DEFINE_PROP_UINT32("max_sectors", VirtIOSCSI, parent_obj.conf.max_sectors, -- 2.24.1 The first rcu_read_lock/unlock() is expensive. Nested calls are cheap. This optimization increases IOPS from 73k to 162k with a Linux guest that has 2 virtio-blk,num-queues=1 and 99 virtio-blk,num-queues=32 devices. Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> Reviewed-by: Paolo Bonzini <pbonzini@redhat.com> Message-id: 20200218182708.914552-1-stefanha@redhat.com Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- util/aio-posix.c | 11 +++++++++++ 1 file changed, 11 insertions(+) diff --git a/util/aio-posix.c b/util/aio-posix.c index XXXXXXX..XXXXXXX 100644 --- a/util/aio-posix.c +++ b/util/aio-posix.c @@ -XXX,XX +XXX,XX @@ #include "qemu/osdep.h" #include "block/block.h" +#include "qemu/rcu.h" #include "qemu/rcu_queue.h" #include "qemu/sockets.h" #include "qemu/cutils.h" @@ -XXX,XX +XXX,XX @@ static bool run_poll_handlers_once(AioContext *ctx, int64_t *timeout) bool progress = false; AioHandler *node; + /* + * Optimization: ->io_poll() handlers often contain RCU read critical + * sections and we therefore see many rcu_read_lock() -> rcu_read_unlock() + * -> rcu_read_lock() -> ... sequences with expensive memory + * synchronization primitives. Make the entire polling loop an RCU + * critical section because nested rcu_read_lock()/rcu_read_unlock() calls + * are cheap. + */ + RCU_READ_LOCK_GUARD(); + QLIST_FOREACH_RCU(node, &ctx->aio_handlers, node) { if (!node->deleted && node->io_poll && aio_node_check(ctx, node->is_external) && -- 2.24.1 From: Paolo Bonzini <pbonzini@redhat.com> QSLIST is the only family of lists for which we do not have RCU-friendly accessors, add them. Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Message-id: 20200220103828.24525-1-pbonzini@redhat.com Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- include/qemu/queue.h | 15 +++++++++++-- include/qemu/rcu_queue.h | 47 ++++++++++++++++++++++++++++++++++++++++ tests/Makefile.include | 2 ++ tests/test-rcu-list.c | 16 ++++++++++++++ tests/test-rcu-slist.c | 2 ++ 5 files changed, 80 insertions(+), 2 deletions(-) create mode 100644 tests/test-rcu-slist.c diff --git a/include/qemu/queue.h b/include/qemu/queue.h index XXXXXXX..XXXXXXX 100644 --- a/include/qemu/queue.h +++ b/include/qemu/queue.h @@ -XXX,XX +XXX,XX @@ struct { \ (head)->slh_first = (head)->slh_first->field.sle_next; \ } while (/*CONSTCOND*/0) -#define QSLIST_REMOVE_AFTER(slistelm, field) do { \ +#define QSLIST_REMOVE_AFTER(slistelm, field) do { \ (slistelm)->field.sle_next = \ - QSLIST_NEXT(QSLIST_NEXT((slistelm), field), field); \ + QSLIST_NEXT(QSLIST_NEXT((slistelm), field), field); \ +} while (/*CONSTCOND*/0) + +#define QSLIST_REMOVE(head, elm, type, field) do { \ + if ((head)->slh_first == (elm)) { \ + QSLIST_REMOVE_HEAD((head), field); \ + } else { \ + struct type *curelm = (head)->slh_first; \ + while (curelm->field.sle_next != (elm)) \ + curelm = curelm->field.sle_next; \ + curelm->field.sle_next = curelm->field.sle_next->field.sle_next; \ + } \ } while (/*CONSTCOND*/0) #define QSLIST_FOREACH(var, head, field) \ diff --git a/include/qemu/rcu_queue.h b/include/qemu/rcu_queue.h index XXXXXXX..XXXXXXX 100644 --- a/include/qemu/rcu_queue.h +++ b/include/qemu/rcu_queue.h @@ -XXX,XX +XXX,XX @@ extern "C" { (var) && ((next) = atomic_rcu_read(&(var)->field.tqe_next), 1); \ (var) = (next)) +/* + * RCU singly-linked list + */ + +/* Singly-linked list access methods */ +#define QSLIST_EMPTY_RCU(head) (atomic_read(&(head)->slh_first) == NULL) +#define QSLIST_FIRST_RCU(head) atomic_rcu_read(&(head)->slh_first) +#define QSLIST_NEXT_RCU(elm, field) atomic_rcu_read(&(elm)->field.sle_next) + +/* Singly-linked list functions */ +#define QSLIST_INSERT_HEAD_RCU(head, elm, field) do { \ + (elm)->field.sle_next = (head)->slh_first; \ + atomic_rcu_set(&(head)->slh_first, (elm)); \ +} while (/*CONSTCOND*/0) + +#define QSLIST_INSERT_AFTER_RCU(head, listelm, elm, field) do { \ + (elm)->field.sle_next = (listelm)->field.sle_next; \ + atomic_rcu_set(&(listelm)->field.sle_next, (elm)); \ +} while (/*CONSTCOND*/0) + +#define QSLIST_REMOVE_HEAD_RCU(head, field) do { \ + atomic_set(&(head)->slh_first, (head)->slh_first->field.sle_next); \ +} while (/*CONSTCOND*/0) + +#define QSLIST_REMOVE_RCU(head, elm, type, field) do { \ + if ((head)->slh_first == (elm)) { \ + QSLIST_REMOVE_HEAD_RCU((head), field); \ + } else { \ + struct type *curr = (head)->slh_first; \ + while (curr->field.sle_next != (elm)) { \ + curr = curr->field.sle_next; \ + } \ + atomic_set(&curr->field.sle_next, \ + curr->field.sle_next->field.sle_next); \ + } \ +} while (/*CONSTCOND*/0) + +#define QSLIST_FOREACH_RCU(var, head, field) \ + for ((var) = atomic_rcu_read(&(head)->slh_first); \ + (var); \ + (var) = atomic_rcu_read(&(var)->field.sle_next)) + +#define QSLIST_FOREACH_SAFE_RCU(var, head, field, next) \ + for ((var) = atomic_rcu_read(&(head)->slh_first); \ + (var) && ((next) = atomic_rcu_read(&(var)->field.sle_next), 1); \ + (var) = (next)) + #ifdef __cplusplus } #endif diff --git a/tests/Makefile.include b/tests/Makefile.include index XXXXXXX..XXXXXXX 100644 --- a/tests/Makefile.include +++ b/tests/Makefile.include @@ -XXX,XX +XXX,XX @@ check-unit-y += tests/rcutorture$(EXESUF) check-unit-y += tests/test-rcu-list$(EXESUF) check-unit-y += tests/test-rcu-simpleq$(EXESUF) check-unit-y += tests/test-rcu-tailq$(EXESUF) +check-unit-y += tests/test-rcu-slist$(EXESUF) check-unit-y += tests/test-qdist$(EXESUF) check-unit-y += tests/test-qht$(EXESUF) check-unit-y += tests/test-qht-par$(EXESUF) @@ -XXX,XX +XXX,XX @@ tests/rcutorture$(EXESUF): tests/rcutorture.o $(test-util-obj-y) tests/test-rcu-list$(EXESUF): tests/test-rcu-list.o $(test-util-obj-y) tests/test-rcu-simpleq$(EXESUF): tests/test-rcu-simpleq.o $(test-util-obj-y) tests/test-rcu-tailq$(EXESUF): tests/test-rcu-tailq.o $(test-util-obj-y) +tests/test-rcu-slist$(EXESUF): tests/test-rcu-slist.o $(test-util-obj-y) tests/test-qdist$(EXESUF): tests/test-qdist.o $(test-util-obj-y) tests/test-qht$(EXESUF): tests/test-qht.o $(test-util-obj-y) tests/test-qht-par$(EXESUF): tests/test-qht-par.o tests/qht-bench$(EXESUF) $(test-util-obj-y) diff --git a/tests/test-rcu-list.c b/tests/test-rcu-list.c index XXXXXXX..XXXXXXX 100644 --- a/tests/test-rcu-list.c +++ b/tests/test-rcu-list.c @@ -XXX,XX +XXX,XX @@ struct list_element { QSIMPLEQ_ENTRY(list_element) entry; #elif TEST_LIST_TYPE == 3 QTAILQ_ENTRY(list_element) entry; +#elif TEST_LIST_TYPE == 4 + QSLIST_ENTRY(list_element) entry; #else #error Invalid TEST_LIST_TYPE #endif @@ -XXX,XX +XXX,XX @@ static QTAILQ_HEAD(, list_element) Q_list_head; #define TEST_LIST_INSERT_HEAD_RCU QTAILQ_INSERT_HEAD_RCU #define TEST_LIST_FOREACH_RCU QTAILQ_FOREACH_RCU #define TEST_LIST_FOREACH_SAFE_RCU QTAILQ_FOREACH_SAFE_RCU + +#elif TEST_LIST_TYPE == 4 +static QSLIST_HEAD(, list_element) Q_list_head; + +#define TEST_NAME "qslist" +#define TEST_LIST_REMOVE_RCU(el, f) \ + QSLIST_REMOVE_RCU(&Q_list_head, el, list_element, f) + +#define TEST_LIST_INSERT_AFTER_RCU(list_el, el, f) \ + QSLIST_INSERT_AFTER_RCU(&Q_list_head, list_el, el, f) + +#define TEST_LIST_INSERT_HEAD_RCU QSLIST_INSERT_HEAD_RCU +#define TEST_LIST_FOREACH_RCU QSLIST_FOREACH_RCU +#define TEST_LIST_FOREACH_SAFE_RCU QSLIST_FOREACH_SAFE_RCU #else #error Invalid TEST_LIST_TYPE #endif diff --git a/tests/test-rcu-slist.c b/tests/test-rcu-slist.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/tests/test-rcu-slist.c @@ -XXX,XX +XXX,XX @@ +#define TEST_LIST_TYPE 4 +#include "test-rcu-list.c" -- 2.24.1 The ctx->first_bh list contains all created BHs, including those that are not scheduled. The list is iterated by the event loop and therefore has O(n) time complexity with respected to the number of created BHs. Rewrite BHs so that only scheduled or deleted BHs are enqueued. Only BHs that actually require action will be iterated. One semantic change is required: qemu_bh_delete() enqueues the BH and therefore invokes aio_notify(). The tests/test-aio.c:test_source_bh_delete_from_cb() test case assumed that g_main_context_iteration(NULL, false) returns false after qemu_bh_delete() but it now returns true for one iteration. Fix up the test case. This patch makes aio_compute_timeout() and aio_bh_poll() drop from a CPU profile reported by perf-top(1). Previously they combined to 9% CPU utilization when AioContext polling is commented out and the guest has 2 virtio-blk,num-queues=1 and 99 virtio-blk,num-queues=32 devices. Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> Reviewed-by: Paolo Bonzini <pbonzini@redhat.com> Message-id: 20200221093951.1414693-1-stefanha@redhat.com Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- include/block/aio.h | 20 +++- tests/test-aio.c | 3 +- util/async.c | 237 ++++++++++++++++++++++++++------------------ 3 files changed, 158 insertions(+), 102 deletions(-) diff --git a/include/block/aio.h b/include/block/aio.h index XXXXXXX..XXXXXXX 100644 --- a/include/block/aio.h +++ b/include/block/aio.h @@ -XXX,XX +XXX,XX @@ struct ThreadPool; struct LinuxAioState; struct LuringState; +/* + * Each aio_bh_poll() call carves off a slice of the BH list, so that newly + * scheduled BHs are not processed until the next aio_bh_poll() call. All + * active aio_bh_poll() calls chain their slices together in a list, so that + * nested aio_bh_poll() calls process all scheduled bottom halves. + */ +typedef QSLIST_HEAD(, QEMUBH) BHList; +typedef struct BHListSlice BHListSlice; +struct BHListSlice { + BHList bh_list; + QSIMPLEQ_ENTRY(BHListSlice) next; +}; + struct AioContext { GSource source; @@ -XXX,XX +XXX,XX @@ struct AioContext { */ QemuLockCnt list_lock; - /* Anchor of the list of Bottom Halves belonging to the context */ - struct QEMUBH *first_bh; + /* Bottom Halves pending aio_bh_poll() processing */ + BHList bh_list; + + /* Chained BH list slices for each nested aio_bh_poll() call */ + QSIMPLEQ_HEAD(, BHListSlice) bh_slice_list; /* Used by aio_notify. * diff --git a/tests/test-aio.c b/tests/test-aio.c index XXXXXXX..XXXXXXX 100644 --- a/tests/test-aio.c +++ b/tests/test-aio.c @@ -XXX,XX +XXX,XX @@ static void test_source_bh_delete_from_cb(void) g_assert_cmpint(data1.n, ==, data1.max); g_assert(data1.bh == NULL); - g_assert(!g_main_context_iteration(NULL, false)); + assert(g_main_context_iteration(NULL, false)); + assert(!g_main_context_iteration(NULL, false)); } static void test_source_bh_delete_from_cb_many(void) diff --git a/util/async.c b/util/async.c index XXXXXXX..XXXXXXX 100644 --- a/util/async.c +++ b/util/async.c @@ -XXX,XX +XXX,XX @@ #include "block/thread-pool.h" #include "qemu/main-loop.h" #include "qemu/atomic.h" +#include "qemu/rcu_queue.h" #include "block/raw-aio.h" #include "qemu/coroutine_int.h" #include "trace.h" @@ -XXX,XX +XXX,XX @@ /***********************************************************/ /* bottom halves (can be seen as timers which expire ASAP) */ +/* QEMUBH::flags values */ +enum { + /* Already enqueued and waiting for aio_bh_poll() */ + BH_PENDING = (1 << 0), + + /* Invoke the callback */ + BH_SCHEDULED = (1 << 1), + + /* Delete without invoking callback */ + BH_DELETED = (1 << 2), + + /* Delete after invoking callback */ + BH_ONESHOT = (1 << 3), + + /* Schedule periodically when the event loop is idle */ + BH_IDLE = (1 << 4), +}; + struct QEMUBH { AioContext *ctx; QEMUBHFunc *cb; void *opaque; - QEMUBH *next; - bool scheduled; - bool idle; - bool deleted; + QSLIST_ENTRY(QEMUBH) next; + unsigned flags; }; +/* Called concurrently from any thread */ +static void aio_bh_enqueue(QEMUBH *bh, unsigned new_flags) +{ + AioContext *ctx = bh->ctx; + unsigned old_flags; + + /* + * The memory barrier implicit in atomic_fetch_or makes sure that: + * 1. idle & any writes needed by the callback are done before the + * locations are read in the aio_bh_poll. + * 2. ctx is loaded before the callback has a chance to execute and bh + * could be freed. + */ + old_flags = atomic_fetch_or(&bh->flags, BH_PENDING | new_flags); + if (!(old_flags & BH_PENDING)) { + QSLIST_INSERT_HEAD_ATOMIC(&ctx->bh_list, bh, next); + } + + aio_notify(ctx); +} + +/* Only called from aio_bh_poll() and aio_ctx_finalize() */ +static QEMUBH *aio_bh_dequeue(BHList *head, unsigned *flags) +{ + QEMUBH *bh = QSLIST_FIRST_RCU(head); + + if (!bh) { + return NULL; + } + + QSLIST_REMOVE_HEAD(head, next); + + /* + * The atomic_and is paired with aio_bh_enqueue(). The implicit memory + * barrier ensures that the callback sees all writes done by the scheduling + * thread. It also ensures that the scheduling thread sees the cleared + * flag before bh->cb has run, and thus will call aio_notify again if + * necessary. + */ + *flags = atomic_fetch_and(&bh->flags, + ~(BH_PENDING | BH_SCHEDULED | BH_IDLE)); + return bh; +} + void aio_bh_schedule_oneshot(AioContext *ctx, QEMUBHFunc *cb, void *opaque) { QEMUBH *bh; @@ -XXX,XX +XXX,XX @@ void aio_bh_schedule_oneshot(AioContext *ctx, QEMUBHFunc *cb, void *opaque) .cb = cb, .opaque = opaque, }; - qemu_lockcnt_lock(&ctx->list_lock); - bh->next = ctx->first_bh; - bh->scheduled = 1; - bh->deleted = 1; - /* Make sure that the members are ready before putting bh into list */ - smp_wmb(); - ctx->first_bh = bh; - qemu_lockcnt_unlock(&ctx->list_lock); - aio_notify(ctx); + aio_bh_enqueue(bh, BH_SCHEDULED | BH_ONESHOT); } QEMUBH *aio_bh_new(AioContext *ctx, QEMUBHFunc *cb, void *opaque) @@ -XXX,XX +XXX,XX @@ QEMUBH *aio_bh_new(AioContext *ctx, QEMUBHFunc *cb, void *opaque) .cb = cb, .opaque = opaque, }; - qemu_lockcnt_lock(&ctx->list_lock); - bh->next = ctx->first_bh; - /* Make sure that the members are ready before putting bh into list */ - smp_wmb(); - ctx->first_bh = bh; - qemu_lockcnt_unlock(&ctx->list_lock); return bh; } @@ -XXX,XX +XXX,XX @@ void aio_bh_call(QEMUBH *bh) bh->cb(bh->opaque); } -/* Multiple occurrences of aio_bh_poll cannot be called concurrently. - * The count in ctx->list_lock is incremented before the call, and is - * not affected by the call. - */ +/* Multiple occurrences of aio_bh_poll cannot be called concurrently. */ int aio_bh_poll(AioContext *ctx) { - QEMUBH *bh, **bhp, *next; - int ret; - bool deleted = false; - - ret = 0; - for (bh = atomic_rcu_read(&ctx->first_bh); bh; bh = next) { - next = atomic_rcu_read(&bh->next); - /* The atomic_xchg is paired with the one in qemu_bh_schedule. The - * implicit memory barrier ensures that the callback sees all writes - * done by the scheduling thread. It also ensures that the scheduling - * thread sees the zero before bh->cb has run, and thus will call - * aio_notify again if necessary. - */ - if (atomic_xchg(&bh->scheduled, 0)) { + BHListSlice slice; + BHListSlice *s; + int ret = 0; + + QSLIST_MOVE_ATOMIC(&slice.bh_list, &ctx->bh_list); + QSIMPLEQ_INSERT_TAIL(&ctx->bh_slice_list, &slice, next); + + while ((s = QSIMPLEQ_FIRST(&ctx->bh_slice_list))) { + QEMUBH *bh; + unsigned flags; + + bh = aio_bh_dequeue(&s->bh_list, &flags); + if (!bh) { + QSIMPLEQ_REMOVE_HEAD(&ctx->bh_slice_list, next); + continue; + } + + if ((flags & (BH_SCHEDULED | BH_DELETED)) == BH_SCHEDULED) { /* Idle BHs don't count as progress */ - if (!bh->idle) { + if (!(flags & BH_IDLE)) { ret = 1; } - bh->idle = 0; aio_bh_call(bh); } - if (bh->deleted) { - deleted = true; + if (flags & (BH_DELETED | BH_ONESHOT)) { + g_free(bh); } } - /* remove deleted bhs */ - if (!deleted) { - return ret; - } - - if (qemu_lockcnt_dec_if_lock(&ctx->list_lock)) { - bhp = &ctx->first_bh; - while (*bhp) { - bh = *bhp; - if (bh->deleted && !bh->scheduled) { - *bhp = bh->next; - g_free(bh); - } else { - bhp = &bh->next; - } - } - qemu_lockcnt_inc_and_unlock(&ctx->list_lock); - } return ret; } void qemu_bh_schedule_idle(QEMUBH *bh) { - bh->idle = 1; - /* Make sure that idle & any writes needed by the callback are done - * before the locations are read in the aio_bh_poll. - */ - atomic_mb_set(&bh->scheduled, 1); + aio_bh_enqueue(bh, BH_SCHEDULED | BH_IDLE); } void qemu_bh_schedule(QEMUBH *bh) { - AioContext *ctx; - - ctx = bh->ctx; - bh->idle = 0; - /* The memory barrier implicit in atomic_xchg makes sure that: - * 1. idle & any writes needed by the callback are done before the - * locations are read in the aio_bh_poll. - * 2. ctx is loaded before scheduled is set and the callback has a chance - * to execute. - */ - if (atomic_xchg(&bh->scheduled, 1) == 0) { - aio_notify(ctx); - } + aio_bh_enqueue(bh, BH_SCHEDULED); } - /* This func is async. */ void qemu_bh_cancel(QEMUBH *bh) { - atomic_mb_set(&bh->scheduled, 0); + atomic_and(&bh->flags, ~BH_SCHEDULED); } /* This func is async.The bottom half will do the delete action at the finial @@ -XXX,XX +XXX,XX @@ void qemu_bh_cancel(QEMUBH *bh) */ void qemu_bh_delete(QEMUBH *bh) { - bh->scheduled = 0; - bh->deleted = 1; + aio_bh_enqueue(bh, BH_DELETED); } -int64_t -aio_compute_timeout(AioContext *ctx) +static int64_t aio_compute_bh_timeout(BHList *head, int timeout) { - int64_t deadline; - int timeout = -1; QEMUBH *bh; - for (bh = atomic_rcu_read(&ctx->first_bh); bh; - bh = atomic_rcu_read(&bh->next)) { - if (bh->scheduled) { - if (bh->idle) { + QSLIST_FOREACH_RCU(bh, head, next) { + if ((bh->flags & (BH_SCHEDULED | BH_DELETED)) == BH_SCHEDULED) { + if (bh->flags & BH_IDLE) { /* idle bottom halves will be polled at least * every 10ms */ timeout = 10000000; @@ -XXX,XX +XXX,XX @@ aio_compute_timeout(AioContext *ctx) } } + return timeout; +} + +int64_t +aio_compute_timeout(AioContext *ctx) +{ + BHListSlice *s; + int64_t deadline; + int timeout = -1; + + timeout = aio_compute_bh_timeout(&ctx->bh_list, timeout); + if (timeout == 0) { + return 0; + } + + QSIMPLEQ_FOREACH(s, &ctx->bh_slice_list, next) { + timeout = aio_compute_bh_timeout(&s->bh_list, timeout); + if (timeout == 0) { + return 0; + } + } + deadline = timerlistgroup_deadline_ns(&ctx->tlg); if (deadline == 0) { return 0; @@ -XXX,XX +XXX,XX @@ aio_ctx_check(GSource *source) { AioContext *ctx = (AioContext *) source; QEMUBH *bh; + BHListSlice *s; atomic_and(&ctx->notify_me, ~1); aio_notify_accept(ctx); - for (bh = ctx->first_bh; bh; bh = bh->next) { - if (bh->scheduled) { + QSLIST_FOREACH_RCU(bh, &ctx->bh_list, next) { + if ((bh->flags & (BH_SCHEDULED | BH_DELETED)) == BH_SCHEDULED) { return true; } } + + QSIMPLEQ_FOREACH(s, &ctx->bh_slice_list, next) { + QSLIST_FOREACH_RCU(bh, &s->bh_list, next) { + if ((bh->flags & (BH_SCHEDULED | BH_DELETED)) == BH_SCHEDULED) { + return true; + } + } + } return aio_pending(ctx) || (timerlistgroup_deadline_ns(&ctx->tlg) == 0); } @@ -XXX,XX +XXX,XX @@ static void aio_ctx_finalize(GSource *source) { AioContext *ctx = (AioContext *) source; + QEMUBH *bh; + unsigned flags; thread_pool_free(ctx->thread_pool); @@ -XXX,XX +XXX,XX @@ aio_ctx_finalize(GSource *source) assert(QSLIST_EMPTY(&ctx->scheduled_coroutines)); qemu_bh_delete(ctx->co_schedule_bh); - qemu_lockcnt_lock(&ctx->list_lock); - assert(!qemu_lockcnt_count(&ctx->list_lock)); - while (ctx->first_bh) { - QEMUBH *next = ctx->first_bh->next; + /* There must be no aio_bh_poll() calls going on */ + assert(QSIMPLEQ_EMPTY(&ctx->bh_slice_list)); + while ((bh = aio_bh_dequeue(&ctx->bh_list, &flags))) { /* qemu_bh_delete() must have been called on BHs in this AioContext */ - assert(ctx->first_bh->deleted); + assert(flags & BH_DELETED); - g_free(ctx->first_bh); - ctx->first_bh = next; + g_free(bh); } - qemu_lockcnt_unlock(&ctx->list_lock); aio_set_event_notifier(ctx, &ctx->notifier, false, NULL, NULL); event_notifier_cleanup(&ctx->notifier); @@ -XXX,XX +XXX,XX @@ AioContext *aio_context_new(Error **errp) AioContext *ctx; ctx = (AioContext *) g_source_new(&aio_source_funcs, sizeof(AioContext)); + QSLIST_INIT(&ctx->bh_list); + QSIMPLEQ_INIT(&ctx->bh_slice_list); aio_context_setup(ctx); ret = event_notifier_init(&ctx->notifier, false); -- 2.24.1 epoll_handler is a stack variable and must not be accessed after it goes out of scope: if (aio_epoll_check_poll(ctx, pollfds, npfd, timeout)) { AioHandler epoll_handler; ... add_pollfd(&epoll_handler); ret = aio_epoll(ctx, pollfds, npfd, timeout); } ... ... /* if we have any readable fds, dispatch event */ if (ret > 0) { for (i = 0; i < npfd; i++) { nodes[i]->pfd.revents = pollfds[i].revents; } } nodes[0] is &epoll_handler, which has already gone out of scope. There is no need to use pollfds[] for epoll. We don't need an AioHandler for the epoll fd. Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> Reviewed-by: Sergio Lopez <slp@redhat.com> Message-id: 20200214171712.541358-2-stefanha@redhat.com Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- util/aio-posix.c | 20 ++++++++------------ 1 file changed, 8 insertions(+), 12 deletions(-) diff --git a/util/aio-posix.c b/util/aio-posix.c index XXXXXXX..XXXXXXX 100644 --- a/util/aio-posix.c +++ b/util/aio-posix.c @@ -XXX,XX +XXX,XX @@ static void aio_epoll_update(AioContext *ctx, AioHandler *node, bool is_new) } } -static int aio_epoll(AioContext *ctx, GPollFD *pfds, - unsigned npfd, int64_t timeout) +static int aio_epoll(AioContext *ctx, int64_t timeout) { + GPollFD pfd = { + .fd = ctx->epollfd, + .events = G_IO_IN | G_IO_OUT | G_IO_HUP | G_IO_ERR, + }; AioHandler *node; int i, ret = 0; struct epoll_event events[128]; - assert(npfd == 1); - assert(pfds[0].fd == ctx->epollfd); if (timeout > 0) { - ret = qemu_poll_ns(pfds, npfd, timeout); + ret = qemu_poll_ns(&pfd, 1, timeout); } if (timeout <= 0 || ret > 0) { ret = epoll_wait(ctx->epollfd, events, @@ -XXX,XX +XXX,XX @@ bool aio_poll(AioContext *ctx, bool blocking) /* wait until next event */ if (aio_epoll_check_poll(ctx, pollfds, npfd, timeout)) { - AioHandler epoll_handler; - - epoll_handler.pfd.fd = ctx->epollfd; - epoll_handler.pfd.events = G_IO_IN | G_IO_OUT | G_IO_HUP | G_IO_ERR; - npfd = 0; - add_pollfd(&epoll_handler); - ret = aio_epoll(ctx, pollfds, npfd, timeout); + npfd = 0; /* pollfds[] is not being used */ + ret = aio_epoll(ctx, timeout); } else { ret = qemu_poll_ns(pollfds, npfd, timeout); } -- 2.24.1 Don't pass the nanosecond timeout into epoll_wait(), which expects milliseconds. The epoll_wait() timeout value does not matter if qemu_poll_ns() determined that the poll fd is ready, but passing a value in the wrong units is still ugly. Pass a 0 timeout to epoll_wait() instead. Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> Reviewed-by: Sergio Lopez <slp@redhat.com> Message-id: 20200214171712.541358-3-stefanha@redhat.com Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- util/aio-posix.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/util/aio-posix.c b/util/aio-posix.c index XXXXXXX..XXXXXXX 100644 --- a/util/aio-posix.c +++ b/util/aio-posix.c @@ -XXX,XX +XXX,XX @@ static int aio_epoll(AioContext *ctx, int64_t timeout) if (timeout > 0) { ret = qemu_poll_ns(&pfd, 1, timeout); + if (ret > 0) { + timeout = 0; + } } if (timeout <= 0 || ret > 0) { ret = epoll_wait(ctx->epollfd, events, -- 2.24.1 QLIST_REMOVE() assumes the element is in a list. It also leaves the element's linked list pointers dangling. Introduce a safe version of QLIST_REMOVE() and convert open-coded instances of this pattern. Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> Reviewed-by: Sergio Lopez <slp@redhat.com> Message-id: 20200214171712.541358-4-stefanha@redhat.com Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- block.c | 5 +---- chardev/spice.c | 4 +--- include/qemu/queue.h | 14 ++++++++++++++ 3 files changed, 16 insertions(+), 7 deletions(-) diff --git a/block.c b/block.c index XXXXXXX..XXXXXXX 100644 --- a/block.c +++ b/block.c @@ -XXX,XX +XXX,XX @@ BdrvChild *bdrv_attach_child(BlockDriverState *parent_bs, static void bdrv_detach_child(BdrvChild *child) { - if (child->next.le_prev) { - QLIST_REMOVE(child, next); - child->next.le_prev = NULL; - } + QLIST_SAFE_REMOVE(child, next); bdrv_replace_child(child, NULL); diff --git a/chardev/spice.c b/chardev/spice.c index XXXXXXX..XXXXXXX 100644 --- a/chardev/spice.c +++ b/chardev/spice.c @@ -XXX,XX +XXX,XX @@ static void char_spice_finalize(Object *obj) vmc_unregister_interface(s); - if (s->next.le_prev) { - QLIST_REMOVE(s, next); - } + QLIST_SAFE_REMOVE(s, next); g_free((char *)s->sin.subtype); g_free((char *)s->sin.portname); diff --git a/include/qemu/queue.h b/include/qemu/queue.h index XXXXXXX..XXXXXXX 100644 --- a/include/qemu/queue.h +++ b/include/qemu/queue.h @@ -XXX,XX +XXX,XX @@ struct { \ *(elm)->field.le_prev = (elm)->field.le_next; \ } while (/*CONSTCOND*/0) +/* + * Like QLIST_REMOVE() but safe to call when elm is not in a list + */ +#define QLIST_SAFE_REMOVE(elm, field) do { \ + if ((elm)->field.le_prev != NULL) { \ + if ((elm)->field.le_next != NULL) \ + (elm)->field.le_next->field.le_prev = \ + (elm)->field.le_prev; \ + *(elm)->field.le_prev = (elm)->field.le_next; \ + (elm)->field.le_next = NULL; \ + (elm)->field.le_prev = NULL; \ + } \ +} while (/*CONSTCOND*/0) + #define QLIST_FOREACH(var, head, field) \ for ((var) = ((head)->lh_first); \ (var); \ -- 2.24.1 It is not necessary to scan all AioHandlers for deletion. Keep a list of deleted handlers instead of scanning the full list of all handlers. The AioHandler->deleted field can be dropped. Let's check if the handler has been inserted into the deleted list instead. Add a new QLIST_IS_INSERTED() API for this check. Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> Reviewed-by: Sergio Lopez <slp@redhat.com> Message-id: 20200214171712.541358-5-stefanha@redhat.com Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- include/block/aio.h | 6 ++++- include/qemu/queue.h | 3 +++ util/aio-posix.c | 53 +++++++++++++++++++++++++++++--------------- 3 files changed, 43 insertions(+), 19 deletions(-) diff --git a/include/block/aio.h b/include/block/aio.h index XXXXXXX..XXXXXXX 100644 --- a/include/block/aio.h +++ b/include/block/aio.h @@ -XXX,XX +XXX,XX @@ void qemu_aio_unref(void *p); void qemu_aio_ref(void *p); typedef struct AioHandler AioHandler; +typedef QLIST_HEAD(, AioHandler) AioHandlerList; typedef void QEMUBHFunc(void *opaque); typedef bool AioPollFn(void *opaque); typedef void IOHandler(void *opaque); @@ -XXX,XX +XXX,XX @@ struct AioContext { QemuRecMutex lock; /* The list of registered AIO handlers. Protected by ctx->list_lock. */ - QLIST_HEAD(, AioHandler) aio_handlers; + AioHandlerList aio_handlers; + + /* The list of AIO handlers to be deleted. Protected by ctx->list_lock. */ + AioHandlerList deleted_aio_handlers; /* Used to avoid unnecessary event_notifier_set calls in aio_notify; * accessed with atomic primitives. If this field is 0, everything diff --git a/include/qemu/queue.h b/include/qemu/queue.h index XXXXXXX..XXXXXXX 100644 --- a/include/qemu/queue.h +++ b/include/qemu/queue.h @@ -XXX,XX +XXX,XX @@ struct { \ } \ } while (/*CONSTCOND*/0) +/* Is elm in a list? */ +#define QLIST_IS_INSERTED(elm, field) ((elm)->field.le_prev != NULL) + #define QLIST_FOREACH(var, head, field) \ for ((var) = ((head)->lh_first); \ (var); \ diff --git a/util/aio-posix.c b/util/aio-posix.c index XXXXXXX..XXXXXXX 100644 --- a/util/aio-posix.c +++ b/util/aio-posix.c @@ -XXX,XX +XXX,XX @@ struct AioHandler AioPollFn *io_poll; IOHandler *io_poll_begin; IOHandler *io_poll_end; - int deleted; void *opaque; bool is_external; QLIST_ENTRY(AioHandler) node; + QLIST_ENTRY(AioHandler) node_deleted; }; #ifdef CONFIG_EPOLL_CREATE1 @@ -XXX,XX +XXX,XX @@ static bool aio_epoll_try_enable(AioContext *ctx) QLIST_FOREACH_RCU(node, &ctx->aio_handlers, node) { int r; - if (node->deleted || !node->pfd.events) { + if (QLIST_IS_INSERTED(node, node_deleted) || !node->pfd.events) { continue; } event.events = epoll_events_from_pfd(node->pfd.events); @@ -XXX,XX +XXX,XX @@ static AioHandler *find_aio_handler(AioContext *ctx, int fd) AioHandler *node; QLIST_FOREACH(node, &ctx->aio_handlers, node) { - if (node->pfd.fd == fd) - if (!node->deleted) + if (node->pfd.fd == fd) { + if (!QLIST_IS_INSERTED(node, node_deleted)) { return node; + } + } } return NULL; @@ -XXX,XX +XXX,XX @@ static bool aio_remove_fd_handler(AioContext *ctx, AioHandler *node) /* If a read is in progress, just mark the node as deleted */ if (qemu_lockcnt_count(&ctx->list_lock)) { - node->deleted = 1; + QLIST_INSERT_HEAD_RCU(&ctx->deleted_aio_handlers, node, node_deleted); node->pfd.revents = 0; return false; } @@ -XXX,XX +XXX,XX @@ static void poll_set_started(AioContext *ctx, bool started) QLIST_FOREACH_RCU(node, &ctx->aio_handlers, node) { IOHandler *fn; - if (node->deleted) { + if (QLIST_IS_INSERTED(node, node_deleted)) { continue; } @@ -XXX,XX +XXX,XX @@ bool aio_pending(AioContext *ctx) return result; } +static void aio_free_deleted_handlers(AioContext *ctx) +{ + AioHandler *node; + + if (QLIST_EMPTY_RCU(&ctx->deleted_aio_handlers)) { + return; + } + if (!qemu_lockcnt_dec_if_lock(&ctx->list_lock)) { + return; /* we are nested, let the parent do the freeing */ + } + + while ((node = QLIST_FIRST_RCU(&ctx->deleted_aio_handlers))) { + QLIST_REMOVE(node, node); + QLIST_REMOVE(node, node_deleted); + g_free(node); + } + + qemu_lockcnt_inc_and_unlock(&ctx->list_lock); +} + static bool aio_dispatch_handlers(AioContext *ctx) { AioHandler *node, *tmp; @@ -XXX,XX +XXX,XX @@ static bool aio_dispatch_handlers(AioContext *ctx) revents = node->pfd.revents & node->pfd.events; node->pfd.revents = 0; - if (!node->deleted && + if (!QLIST_IS_INSERTED(node, node_deleted) && (revents & (G_IO_IN | G_IO_HUP | G_IO_ERR)) && aio_node_check(ctx, node->is_external) && node->io_read) { @@ -XXX,XX +XXX,XX @@ static bool aio_dispatch_handlers(AioContext *ctx) progress = true; } } - if (!node->deleted && + if (!QLIST_IS_INSERTED(node, node_deleted) && (revents & (G_IO_OUT | G_IO_ERR)) && aio_node_check(ctx, node->is_external) && node->io_write) { node->io_write(node->opaque); progress = true; } - - if (node->deleted) { - if (qemu_lockcnt_dec_if_lock(&ctx->list_lock)) { - QLIST_REMOVE(node, node); - g_free(node); - qemu_lockcnt_inc_and_unlock(&ctx->list_lock); - } - } } return progress; @@ -XXX,XX +XXX,XX @@ void aio_dispatch(AioContext *ctx) qemu_lockcnt_inc(&ctx->list_lock); aio_bh_poll(ctx); aio_dispatch_handlers(ctx); + aio_free_deleted_handlers(ctx); qemu_lockcnt_dec(&ctx->list_lock); timerlistgroup_run_timers(&ctx->tlg); @@ -XXX,XX +XXX,XX @@ static bool run_poll_handlers_once(AioContext *ctx, int64_t *timeout) RCU_READ_LOCK_GUARD(); QLIST_FOREACH_RCU(node, &ctx->aio_handlers, node) { - if (!node->deleted && node->io_poll && + if (!QLIST_IS_INSERTED(node, node_deleted) && node->io_poll && aio_node_check(ctx, node->is_external) && node->io_poll(node->opaque)) { /* @@ -XXX,XX +XXX,XX @@ bool aio_poll(AioContext *ctx, bool blocking) if (!aio_epoll_enabled(ctx)) { QLIST_FOREACH_RCU(node, &ctx->aio_handlers, node) { - if (!node->deleted && node->pfd.events + if (!QLIST_IS_INSERTED(node, node_deleted) && node->pfd.events && aio_node_check(ctx, node->is_external)) { add_pollfd(node); } @@ -XXX,XX +XXX,XX @@ bool aio_poll(AioContext *ctx, bool blocking) progress |= aio_dispatch_handlers(ctx); } + aio_free_deleted_handlers(ctx); + qemu_lockcnt_dec(&ctx->list_lock); progress |= timerlistgroup_run_timers(&ctx->tlg); -- 2.24.1 File descriptor monitoring is O(1) with epoll(7), but aio_dispatch_handlers() still scans all AioHandlers instead of dispatching just those that are ready. This makes aio_poll() O(n) with respect to the total number of registered handlers. Add a local ready_list to aio_poll() so that each nested aio_poll() builds a list of handlers ready to be dispatched. Since file descriptor polling is level-triggered, nested aio_poll() calls also see fds that were ready in the parent but not yet dispatched. This guarantees that nested aio_poll() invocations will dispatch all fds, even those that became ready before the nested invocation. Since only handlers ready to be dispatched are placed onto the ready_list, the new aio_dispatch_ready_handlers() function provides O(1) dispatch. Note that AioContext polling is still O(n) and currently cannot be fully disabled. This still needs to be fixed before aio_poll() is fully O(1). Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> Reviewed-by: Sergio Lopez <slp@redhat.com> Message-id: 20200214171712.541358-6-stefanha@redhat.com [Fix compilation error on macOS where there is no epoll(87). The aio_epoll() prototype was out of date and aio_add_ready_list() needed to be moved outside the ifdef. --Stefan] Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- util/aio-posix.c | 110 +++++++++++++++++++++++++++++++++-------------- 1 file changed, 78 insertions(+), 32 deletions(-) diff --git a/util/aio-posix.c b/util/aio-posix.c index XXXXXXX..XXXXXXX 100644 --- a/util/aio-posix.c +++ b/util/aio-posix.c @@ -XXX,XX +XXX,XX @@ struct AioHandler void *opaque; bool is_external; QLIST_ENTRY(AioHandler) node; + QLIST_ENTRY(AioHandler) node_ready; /* only used during aio_poll() */ QLIST_ENTRY(AioHandler) node_deleted; }; +/* Add a handler to a ready list */ +static void add_ready_handler(AioHandlerList *ready_list, + AioHandler *node, + int revents) +{ + QLIST_SAFE_REMOVE(node, node_ready); /* remove from nested parent's list */ + node->pfd.revents = revents; + QLIST_INSERT_HEAD(ready_list, node, node_ready); +} + #ifdef CONFIG_EPOLL_CREATE1 /* The fd number threshold to switch to epoll */ @@ -XXX,XX +XXX,XX @@ static void aio_epoll_update(AioContext *ctx, AioHandler *node, bool is_new) } } -static int aio_epoll(AioContext *ctx, int64_t timeout) +static int aio_epoll(AioContext *ctx, AioHandlerList *ready_list, + int64_t timeout) { GPollFD pfd = { .fd = ctx->epollfd, @@ -XXX,XX +XXX,XX @@ static int aio_epoll(AioContext *ctx, int64_t timeout) } for (i = 0; i < ret; i++) { int ev = events[i].events; + int revents = (ev & EPOLLIN ? G_IO_IN : 0) | + (ev & EPOLLOUT ? G_IO_OUT : 0) | + (ev & EPOLLHUP ? G_IO_HUP : 0) | + (ev & EPOLLERR ? G_IO_ERR : 0); + node = events[i].data.ptr; - node->pfd.revents = (ev & EPOLLIN ? G_IO_IN : 0) | - (ev & EPOLLOUT ? G_IO_OUT : 0) | - (ev & EPOLLHUP ? G_IO_HUP : 0) | - (ev & EPOLLERR ? G_IO_ERR : 0); + add_ready_handler(ready_list, node, revents); } } out: @@ -XXX,XX +XXX,XX @@ static void aio_epoll_update(AioContext *ctx, AioHandler *node, bool is_new) { } -static int aio_epoll(AioContext *ctx, GPollFD *pfds, - unsigned npfd, int64_t timeout) +static int aio_epoll(AioContext *ctx, AioHandlerList *ready_list, + int64_t timeout) { assert(false); } @@ -XXX,XX +XXX,XX @@ static void aio_free_deleted_handlers(AioContext *ctx) qemu_lockcnt_inc_and_unlock(&ctx->list_lock); } -static bool aio_dispatch_handlers(AioContext *ctx) +static bool aio_dispatch_handler(AioContext *ctx, AioHandler *node) { - AioHandler *node, *tmp; bool progress = false; + int revents; - QLIST_FOREACH_SAFE_RCU(node, &ctx->aio_handlers, node, tmp) { - int revents; + revents = node->pfd.revents & node->pfd.events; + node->pfd.revents = 0; - revents = node->pfd.revents & node->pfd.events; - node->pfd.revents = 0; + if (!QLIST_IS_INSERTED(node, node_deleted) && + (revents & (G_IO_IN | G_IO_HUP | G_IO_ERR)) && + aio_node_check(ctx, node->is_external) && + node->io_read) { + node->io_read(node->opaque); - if (!QLIST_IS_INSERTED(node, node_deleted) && - (revents & (G_IO_IN | G_IO_HUP | G_IO_ERR)) && - aio_node_check(ctx, node->is_external) && - node->io_read) { - node->io_read(node->opaque); - - /* aio_notify() does not count as progress */ - if (node->opaque != &ctx->notifier) { - progress = true; - } - } - if (!QLIST_IS_INSERTED(node, node_deleted) && - (revents & (G_IO_OUT | G_IO_ERR)) && - aio_node_check(ctx, node->is_external) && - node->io_write) { - node->io_write(node->opaque); + /* aio_notify() does not count as progress */ + if (node->opaque != &ctx->notifier) { progress = true; } } + if (!QLIST_IS_INSERTED(node, node_deleted) && + (revents & (G_IO_OUT | G_IO_ERR)) && + aio_node_check(ctx, node->is_external) && + node->io_write) { + node->io_write(node->opaque); + progress = true; + } + + return progress; +} + +/* + * If we have a list of ready handlers then this is more efficient than + * scanning all handlers with aio_dispatch_handlers(). + */ +static bool aio_dispatch_ready_handlers(AioContext *ctx, + AioHandlerList *ready_list) +{ + bool progress = false; + AioHandler *node; + + while ((node = QLIST_FIRST(ready_list))) { + QLIST_SAFE_REMOVE(node, node_ready); + progress = aio_dispatch_handler(ctx, node) || progress; + } + + return progress; +} + +/* Slower than aio_dispatch_ready_handlers() but only used via glib */ +static bool aio_dispatch_handlers(AioContext *ctx) +{ + AioHandler *node, *tmp; + bool progress = false; + + QLIST_FOREACH_SAFE_RCU(node, &ctx->aio_handlers, node, tmp) { + progress = aio_dispatch_handler(ctx, node) || progress; + } return progress; } @@ -XXX,XX +XXX,XX @@ static bool try_poll_mode(AioContext *ctx, int64_t *timeout) bool aio_poll(AioContext *ctx, bool blocking) { + AioHandlerList ready_list = QLIST_HEAD_INITIALIZER(ready_list); AioHandler *node; int i; int ret = 0; @@ -XXX,XX +XXX,XX @@ bool aio_poll(AioContext *ctx, bool blocking) /* wait until next event */ if (aio_epoll_check_poll(ctx, pollfds, npfd, timeout)) { npfd = 0; /* pollfds[] is not being used */ - ret = aio_epoll(ctx, timeout); + ret = aio_epoll(ctx, &ready_list, timeout); } else { ret = qemu_poll_ns(pollfds, npfd, timeout); } @@ -XXX,XX +XXX,XX @@ bool aio_poll(AioContext *ctx, bool blocking) /* if we have any readable fds, dispatch event */ if (ret > 0) { for (i = 0; i < npfd; i++) { - nodes[i]->pfd.revents = pollfds[i].revents; + int revents = pollfds[i].revents; + + if (revents) { + add_ready_handler(&ready_list, nodes[i], revents); + } } } @@ -XXX,XX +XXX,XX @@ bool aio_poll(AioContext *ctx, bool blocking) progress |= aio_bh_poll(ctx); if (ret > 0) { - progress |= aio_dispatch_handlers(ctx); + progress |= aio_dispatch_ready_handlers(ctx, &ready_list); } aio_free_deleted_handlers(ctx); -- 2.24.1 From: Alexander Bulekov <alxndr@bu.edu> Move vl.c to a separate directory, similar to linux-user/ Update the chechpatch and get_maintainer scripts, since they relied on /vl.c for top_of_tree checks. Signed-off-by: Alexander Bulekov <alxndr@bu.edu> Reviewed-by: Darren Kenny <darren.kenny@oracle.com> Message-id: 20200220041118.23264-2-alxndr@bu.edu Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- MAINTAINERS | 2 +- Makefile.objs | 2 -- Makefile.target | 1 + scripts/checkpatch.pl | 2 +- scripts/get_maintainer.pl | 3 ++- softmmu/Makefile.objs | 2 ++ vl.c => softmmu/vl.c | 0 7 files changed, 7 insertions(+), 5 deletions(-) create mode 100644 softmmu/Makefile.objs rename vl.c => softmmu/vl.c (100%) diff --git a/MAINTAINERS b/MAINTAINERS index XXXXXXX..XXXXXXX 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -XXX,XX +XXX,XX @@ F: include/qemu/main-loop.h F: include/sysemu/runstate.h F: util/main-loop.c F: util/qemu-timer.c -F: vl.c +F: softmmu/vl.c F: qapi/run-state.json Human Monitor (HMP) diff --git a/Makefile.objs b/Makefile.objs index XXXXXXX..XXXXXXX 100644 --- a/Makefile.objs +++ b/Makefile.objs @@ -XXX,XX +XXX,XX @@ common-obj-y += ui/ common-obj-m += ui/ common-obj-y += dma-helpers.o -common-obj-y += vl.o -vl.o-cflags := $(GPROF_CFLAGS) $(SDL_CFLAGS) common-obj-$(CONFIG_TPM) += tpm.o common-obj-y += backends/ diff --git a/Makefile.target b/Makefile.target index XXXXXXX..XXXXXXX 100644 --- a/Makefile.target +++ b/Makefile.target @@ -XXX,XX +XXX,XX @@ obj-y += qapi/ obj-y += memory.o obj-y += memory_mapping.o obj-y += migration/ram.o +obj-y += softmmu/ LIBS := $(libs_softmmu) $(LIBS) # Hardware support diff --git a/scripts/checkpatch.pl b/scripts/checkpatch.pl index XXXXXXX..XXXXXXX 100755 --- a/scripts/checkpatch.pl +++ b/scripts/checkpatch.pl @@ -XXX,XX +XXX,XX @@ sub top_of_kernel_tree { my @tree_check = ( "COPYING", "MAINTAINERS", "Makefile", "README.rst", "docs", "VERSION", - "vl.c" + "linux-user", "softmmu" ); foreach my $check (@tree_check) { diff --git a/scripts/get_maintainer.pl b/scripts/get_maintainer.pl index XXXXXXX..XXXXXXX 100755 --- a/scripts/get_maintainer.pl +++ b/scripts/get_maintainer.pl @@ -XXX,XX +XXX,XX @@ sub top_of_tree { && (-f "${lk_path}Makefile") && (-d "${lk_path}docs") && (-f "${lk_path}VERSION") - && (-f "${lk_path}vl.c")) { + && (-d "${lk_path}linux-user/") + && (-d "${lk_path}softmmu/")) { return 1; } return 0; diff --git a/softmmu/Makefile.objs b/softmmu/Makefile.objs new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/softmmu/Makefile.objs @@ -XXX,XX +XXX,XX @@ +obj-y += vl.o +vl.o-cflags := $(GPROF_CFLAGS) $(SDL_CFLAGS) diff --git a/vl.c b/softmmu/vl.c similarity index 100% rename from vl.c rename to softmmu/vl.c -- 2.24.1 From: Alexander Bulekov <alxndr@bu.edu> A program might rely on functions implemented in vl.c, but implement its own main(). By placing main into a separate source file, there are no complaints about duplicate main()s when linking against vl.o. For example, the virtual-device fuzzer uses a main() provided by libfuzzer, and needs to perform some initialization before running the softmmu initialization. Now, main simply calls three vl.c functions which handle the guest initialization, main loop and cleanup. Signed-off-by: Alexander Bulekov <alxndr@bu.edu> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Reviewed-by: Darren Kenny <darren.kenny@oracle.com> Message-id: 20200220041118.23264-3-alxndr@bu.edu Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- MAINTAINERS | 1 + Makefile.target | 2 +- include/sysemu/sysemu.h | 4 ++++ softmmu/Makefile.objs | 1 + softmmu/main.c | 53 +++++++++++++++++++++++++++++++++++++++++ softmmu/vl.c | 36 +++++++--------------------- 6 files changed, 69 insertions(+), 28 deletions(-) create mode 100644 softmmu/main.c diff --git a/MAINTAINERS b/MAINTAINERS index XXXXXXX..XXXXXXX 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -XXX,XX +XXX,XX @@ F: include/sysemu/runstate.h F: util/main-loop.c F: util/qemu-timer.c F: softmmu/vl.c +F: softmmu/main.c F: qapi/run-state.json Human Monitor (HMP) diff --git a/Makefile.target b/Makefile.target index XXXXXXX..XXXXXXX 100644 --- a/Makefile.target +++ b/Makefile.target @@ -XXX,XX +XXX,XX @@ endif COMMON_LDADDS = ../libqemuutil.a # build either PROG or PROGW -$(QEMU_PROG_BUILD): $(all-obj-y) $(COMMON_LDADDS) +$(QEMU_PROG_BUILD): $(all-obj-y) $(COMMON_LDADDS) $(softmmu-main-y) $(call LINK, $(filter-out %.mak, $^)) ifdef CONFIG_DARWIN $(call quiet-command,Rez -append $(SRC_PATH)/pc-bios/qemu.rsrc -o $@,"REZ","$(TARGET_DIR)$@") diff --git a/include/sysemu/sysemu.h b/include/sysemu/sysemu.h index XXXXXXX..XXXXXXX 100644 --- a/include/sysemu/sysemu.h +++ b/include/sysemu/sysemu.h @@ -XXX,XX +XXX,XX @@ QemuOpts *qemu_get_machine_opts(void); bool defaults_enabled(void); +void qemu_init(int argc, char **argv, char **envp); +void qemu_main_loop(void); +void qemu_cleanup(void); + extern QemuOptsList qemu_legacy_drive_opts; extern QemuOptsList qemu_common_drive_opts; extern QemuOptsList qemu_drive_opts; diff --git a/softmmu/Makefile.objs b/softmmu/Makefile.objs index XXXXXXX..XXXXXXX 100644 --- a/softmmu/Makefile.objs +++ b/softmmu/Makefile.objs @@ -XXX,XX +XXX,XX @@ +softmmu-main-y = softmmu/main.o obj-y += vl.o vl.o-cflags := $(GPROF_CFLAGS) $(SDL_CFLAGS) diff --git a/softmmu/main.c b/softmmu/main.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/softmmu/main.c @@ -XXX,XX +XXX,XX @@ +/* + * QEMU System Emulator + * + * Copyright (c) 2003-2020 Fabrice Bellard + * + * Permission is hereby granted, free of charge, to any person obtaining a copy + * of this software and associated documentation files (the "Software"), to deal + * in the Software without restriction, including without limitation the rights + * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell + * copies of the Software, and to permit persons to whom the Software is + * furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, + * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN + * THE SOFTWARE. + */ + +#include "qemu/osdep.h" +#include "qemu-common.h" +#include "sysemu/sysemu.h" + +#ifdef CONFIG_SDL +#if defined(__APPLE__) || defined(main) +#include <SDL.h> +int main(int argc, char **argv) +{ + return qemu_main(argc, argv, NULL); +} +#undef main +#define main qemu_main +#endif +#endif /* CONFIG_SDL */ + +#ifdef CONFIG_COCOA +#undef main +#define main qemu_main +#endif /* CONFIG_COCOA */ + +int main(int argc, char **argv, char **envp) +{ + qemu_init(argc, argv, envp); + qemu_main_loop(); + qemu_cleanup(); + + return 0; +} diff --git a/softmmu/vl.c b/softmmu/vl.c index XXXXXXX..XXXXXXX 100644 --- a/softmmu/vl.c +++ b/softmmu/vl.c @@ -XXX,XX +XXX,XX @@ #include "sysemu/seccomp.h" #include "sysemu/tcg.h" -#ifdef CONFIG_SDL -#if defined(__APPLE__) || defined(main) -#include <SDL.h> -int qemu_main(int argc, char **argv, char **envp); -int main(int argc, char **argv) -{ - return qemu_main(argc, argv, NULL); -} -#undef main -#define main qemu_main -#endif -#endif /* CONFIG_SDL */ - -#ifdef CONFIG_COCOA -#undef main -#define main qemu_main -#endif /* CONFIG_COCOA */ - - #include "qemu/error-report.h" #include "qemu/sockets.h" #include "sysemu/accel.h" @@ -XXX,XX +XXX,XX @@ static bool main_loop_should_exit(void) return false; } -static void main_loop(void) +void qemu_main_loop(void) { #ifdef CONFIG_PROFILER int64_t ti; @@ -XXX,XX +XXX,XX @@ static void configure_accelerators(const char *progname) } } -int main(int argc, char **argv, char **envp) +void qemu_init(int argc, char **argv, char **envp) { int i; int snapshot, linux_boot; @@ -XXX,XX +XXX,XX @@ int main(int argc, char **argv, char **envp) case QEMU_OPTION_watchdog: if (watchdog) { error_report("only one watchdog option may be given"); - return 1; + exit(1); } watchdog = optarg; break; @@ -XXX,XX +XXX,XX @@ int main(int argc, char **argv, char **envp) parse_numa_opts(current_machine); /* do monitor/qmp handling at preconfig state if requested */ - main_loop(); + qemu_main_loop(); audio_init_audiodevs(); @@ -XXX,XX +XXX,XX @@ int main(int argc, char **argv, char **envp) if (vmstate_dump_file) { /* dump and exit */ dump_vmstate_json_to_file(vmstate_dump_file); - return 0; + exit(0); } if (incoming) { @@ -XXX,XX +XXX,XX @@ int main(int argc, char **argv, char **envp) accel_setup_post(current_machine); os_setup_post(); - main_loop(); + return; +} +void qemu_cleanup(void) +{ gdbserver_cleanup(); /* @@ -XXX,XX +XXX,XX @@ int main(int argc, char **argv, char **envp) qemu_chr_cleanup(); user_creatable_cleanup(); /* TODO: unref root container, check all devices are ok */ - - return 0; } -- 2.24.1 From: Alexander Bulekov <alxndr@bu.edu> The virtual-device fuzzer must initialize QOM, prior to running vl:qemu_init, so that it can use the qos_graph to identify the arguments required to initialize a guest for libqos-assisted fuzzing. This change prevents errors when vl:qemu_init tries to (re)initialize the previously initialized QOM module. Signed-off-by: Alexander Bulekov <alxndr@bu.edu> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Reviewed-by: Darren Kenny <darren.kenny@oracle.com> Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com> Message-id: 20200220041118.23264-4-alxndr@bu.edu Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- util/module.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/util/module.c b/util/module.c index XXXXXXX..XXXXXXX 100644 --- a/util/module.c +++ b/util/module.c @@ -XXX,XX +XXX,XX @@ typedef struct ModuleEntry typedef QTAILQ_HEAD(, ModuleEntry) ModuleTypeList; static ModuleTypeList init_type_list[MODULE_INIT_MAX]; +static bool modules_init_done[MODULE_INIT_MAX]; static ModuleTypeList dso_init_list; @@ -XXX,XX +XXX,XX @@ void module_call_init(module_init_type type) ModuleTypeList *l; ModuleEntry *e; + if (modules_init_done[type]) { + return; + } + l = find_type(type); QTAILQ_FOREACH(e, l, node) { e->init(); } + + modules_init_done[type] = true; } #ifdef CONFIG_MODULES -- 2.24.1 From: Alexander Bulekov <alxndr@bu.edu> Signed-off-by: Alexander Bulekov <alxndr@bu.edu> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Reviewed-by: Darren Kenny <darren.kenny@oracle.com> Message-id: 20200220041118.23264-5-alxndr@bu.edu Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- include/qemu/module.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/include/qemu/module.h b/include/qemu/module.h index XXXXXXX..XXXXXXX 100644 --- a/include/qemu/module.h +++ b/include/qemu/module.h @@ -XXX,XX +XXX,XX @@ typedef enum { MODULE_INIT_TRACE, MODULE_INIT_XEN_BACKEND, MODULE_INIT_LIBQOS, + MODULE_INIT_FUZZ_TARGET, MODULE_INIT_MAX } module_init_type; @@ -XXX,XX +XXX,XX @@ typedef enum { #define xen_backend_init(function) module_init(function, \ MODULE_INIT_XEN_BACKEND) #define libqos_init(function) module_init(function, MODULE_INIT_LIBQOS) - +#define fuzz_target_init(function) module_init(function, \ + MODULE_INIT_FUZZ_TARGET) #define block_module_load_one(lib) module_load_one("block-", lib) #define ui_module_load_one(lib) module_load_one("ui-", lib) #define audio_module_load_one(lib) module_load_one("audio-", lib) -- 2.24.1 From: Alexander Bulekov <alxndr@bu.edu> qtest_server_send is a function pointer specifying the handler used to transmit data to the qtest client. In the standard configuration, this calls the CharBackend handler, but now it is possible for other types of handlers, e.g direct-function calls if the qtest client and server exist within the same process (inproc) Signed-off-by: Alexander Bulekov <alxndr@bu.edu> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Reviewed-by: Darren Kenny <darren.kenny@oracle.com> Acked-by: Thomas Huth <thuth@redhat.com> Message-id: 20200220041118.23264-6-alxndr@bu.edu Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- include/sysemu/qtest.h | 3 +++ qtest.c | 18 ++++++++++++++++-- 2 files changed, 19 insertions(+), 2 deletions(-) diff --git a/include/sysemu/qtest.h b/include/sysemu/qtest.h index XXXXXXX..XXXXXXX 100644 --- a/include/sysemu/qtest.h +++ b/include/sysemu/qtest.h @@ -XXX,XX +XXX,XX @@ bool qtest_driver(void); void qtest_server_init(const char *qtest_chrdev, const char *qtest_log, Error **errp); +void qtest_server_set_send_handler(void (*send)(void *, const char *), + void *opaque); + #endif diff --git a/qtest.c b/qtest.c index XXXXXXX..XXXXXXX 100644 --- a/qtest.c +++ b/qtest.c @@ -XXX,XX +XXX,XX @@ static GString *inbuf; static int irq_levels[MAX_IRQ]; static qemu_timeval start_time; static bool qtest_opened; +static void (*qtest_server_send)(void*, const char*); +static void *qtest_server_send_opaque; #define FMT_timeval "%ld.%06ld" @@ -XXX,XX +XXX,XX @@ static void GCC_FMT_ATTR(1, 2) qtest_log_send(const char *fmt, ...) va_end(ap); } -static void do_qtest_send(CharBackend *chr, const char *str, size_t len) +static void qtest_server_char_be_send(void *opaque, const char *str) { + size_t len = strlen(str); + CharBackend* chr = (CharBackend *)opaque; qemu_chr_fe_write_all(chr, (uint8_t *)str, len); if (qtest_log_fp && qtest_opened) { fprintf(qtest_log_fp, "%s", str); @@ -XXX,XX +XXX,XX @@ static void do_qtest_send(CharBackend *chr, const char *str, size_t len) static void qtest_send(CharBackend *chr, const char *str) { - do_qtest_send(chr, str, strlen(str)); + qtest_server_send(qtest_server_send_opaque, str); } static void GCC_FMT_ATTR(2, 3) qtest_sendf(CharBackend *chr, @@ -XXX,XX +XXX,XX @@ void qtest_server_init(const char *qtest_chrdev, const char *qtest_log, Error ** qemu_chr_fe_set_echo(&qtest_chr, true); inbuf = g_string_new(""); + + if (!qtest_server_send) { + qtest_server_set_send_handler(qtest_server_char_be_send, &qtest_chr); + } +} + +void qtest_server_set_send_handler(void (*send)(void*, const char*), void *opaque) +{ + qtest_server_send = send; + qtest_server_send_opaque = opaque; } bool qtest_driver(void) -- 2.24.1 From: Alexander Bulekov <alxndr@bu.edu> This makes it simple to swap the transport functions for qtest commands to and from the qtest client. For example, now it is possible to directly pass qtest commands to a server handler that exists within the same process, without the standard way of writing to a file descriptor. Signed-off-by: Alexander Bulekov <alxndr@bu.edu> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Reviewed-by: Darren Kenny <darren.kenny@oracle.com> Message-id: 20200220041118.23264-7-alxndr@bu.edu Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- tests/qtest/libqtest.c | 48 ++++++++++++++++++++++++++++++++++-------- 1 file changed, 39 insertions(+), 9 deletions(-) diff --git a/tests/qtest/libqtest.c b/tests/qtest/libqtest.c index XXXXXXX..XXXXXXX 100644 --- a/tests/qtest/libqtest.c +++ b/tests/qtest/libqtest.c @@ -XXX,XX +XXX,XX @@ #define SOCKET_TIMEOUT 50 #define SOCKET_MAX_FDS 16 + +typedef void (*QTestSendFn)(QTestState *s, const char *buf); +typedef GString* (*QTestRecvFn)(QTestState *); + +typedef struct QTestClientTransportOps { + QTestSendFn send; /* for sending qtest commands */ + QTestRecvFn recv_line; /* for receiving qtest command responses */ +} QTestTransportOps; + struct QTestState { int fd; @@ -XXX,XX +XXX,XX @@ struct QTestState bool big_endian; bool irq_level[MAX_IRQ]; GString *rx; + QTestTransportOps ops; }; static GHookList abrt_hooks; @@ -XXX,XX +XXX,XX @@ static struct sigaction sigact_old; static int qtest_query_target_endianness(QTestState *s); +static void qtest_client_socket_send(QTestState*, const char *buf); +static void socket_send(int fd, const char *buf, size_t size); + +static GString *qtest_client_socket_recv_line(QTestState *); + +static void qtest_client_set_tx_handler(QTestState *s, QTestSendFn send); +static void qtest_client_set_rx_handler(QTestState *s, QTestRecvFn recv); + static int init_socket(const char *socket_path) { struct sockaddr_un addr; @@ -XXX,XX +XXX,XX @@ QTestState *qtest_init_without_qmp_handshake(const char *extra_args) sock = init_socket(socket_path); qmpsock = init_socket(qmp_socket_path); + qtest_client_set_rx_handler(s, qtest_client_socket_recv_line); + qtest_client_set_tx_handler(s, qtest_client_socket_send); + qtest_add_abrt_handler(kill_qemu_hook_func, s); command = g_strdup_printf("exec %s " @@ -XXX,XX +XXX,XX @@ static void socket_send(int fd, const char *buf, size_t size) } } -static void socket_sendf(int fd, const char *fmt, va_list ap) +static void qtest_client_socket_send(QTestState *s, const char *buf) { - gchar *str = g_strdup_vprintf(fmt, ap); - size_t size = strlen(str); - - socket_send(fd, str, size); - g_free(str); + socket_send(s->fd, buf, strlen(buf)); } static void GCC_FMT_ATTR(2, 3) qtest_sendf(QTestState *s, const char *fmt, ...) @@ -XXX,XX +XXX,XX @@ static void GCC_FMT_ATTR(2, 3) qtest_sendf(QTestState *s, const char *fmt, ...) va_list ap; va_start(ap, fmt); - socket_sendf(s->fd, fmt, ap); + gchar *str = g_strdup_vprintf(fmt, ap); va_end(ap); + + s->ops.send(s, str); + g_free(str); } /* Sends a message and file descriptors to the socket. @@ -XXX,XX +XXX,XX @@ static void socket_send_fds(int socket_fd, int *fds, size_t fds_num, g_assert_cmpint(ret, >, 0); } -static GString *qtest_recv_line(QTestState *s) +static GString *qtest_client_socket_recv_line(QTestState *s) { GString *line; size_t offset; @@ -XXX,XX +XXX,XX @@ static gchar **qtest_rsp(QTestState *s, int expected_args) int i; redo: - line = qtest_recv_line(s); + line = s->ops.recv_line(s); words = g_strsplit(line->str, " ", 0); g_string_free(line, TRUE); @@ -XXX,XX +XXX,XX @@ void qmp_assert_error_class(QDict *rsp, const char *class) qobject_unref(rsp); } + +static void qtest_client_set_tx_handler(QTestState *s, + QTestSendFn send) +{ + s->ops.send = send; +} +static void qtest_client_set_rx_handler(QTestState *s, QTestRecvFn recv) +{ + s->ops.recv_line = recv; +} -- 2.24.1 From: Alexander Bulekov <alxndr@bu.edu> When using qtest "in-process" communication, qtest_sendf directly calls a function in the server (qtest.c). Previously, bufwrite used socket_send, which bypasses the TransportOps enabling the call into qtest.c. This change replaces the socket_send calls with ops->send, maintaining the benefits of the direct socket_send call, while adding support for in-process qtest calls. Signed-off-by: Alexander Bulekov <alxndr@bu.edu> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Reviewed-by: Darren Kenny <darren.kenny@oracle.com> Message-id: 20200220041118.23264-8-alxndr@bu.edu Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- tests/qtest/libqtest.c | 71 ++++++++++++++++++++++++++++++++++++++++-- tests/qtest/libqtest.h | 4 +++ 2 files changed, 73 insertions(+), 2 deletions(-) diff --git a/tests/qtest/libqtest.c b/tests/qtest/libqtest.c index XXXXXXX..XXXXXXX 100644 --- a/tests/qtest/libqtest.c +++ b/tests/qtest/libqtest.c @@ -XXX,XX +XXX,XX @@ typedef void (*QTestSendFn)(QTestState *s, const char *buf); +typedef void (*ExternalSendFn)(void *s, const char *buf); typedef GString* (*QTestRecvFn)(QTestState *); typedef struct QTestClientTransportOps { QTestSendFn send; /* for sending qtest commands */ + + /* + * use external_send to send qtest command strings through functions which + * do not accept a QTestState as the first parameter. + */ + ExternalSendFn external_send; + QTestRecvFn recv_line; /* for receiving qtest command responses */ } QTestTransportOps; @@ -XXX,XX +XXX,XX @@ void qtest_bufwrite(QTestState *s, uint64_t addr, const void *data, size_t size) bdata = g_base64_encode(data, size); qtest_sendf(s, "b64write 0x%" PRIx64 " 0x%zx ", addr, size); - socket_send(s->fd, bdata, strlen(bdata)); - socket_send(s->fd, "\n", 1); + s->ops.send(s, bdata); + s->ops.send(s, "\n"); qtest_rsp(s, 0); g_free(bdata); } @@ -XXX,XX +XXX,XX @@ static void qtest_client_set_rx_handler(QTestState *s, QTestRecvFn recv) { s->ops.recv_line = recv; } +/* A type-safe wrapper for s->send() */ +static void send_wrapper(QTestState *s, const char *buf) +{ + s->ops.external_send(s, buf); +} + +static GString *qtest_client_inproc_recv_line(QTestState *s) +{ + GString *line; + size_t offset; + char *eol; + + eol = strchr(s->rx->str, '\n'); + offset = eol - s->rx->str; + line = g_string_new_len(s->rx->str, offset); + g_string_erase(s->rx, 0, offset + 1); + return line; +} + +QTestState *qtest_inproc_init(QTestState **s, bool log, const char* arch, + void (*send)(void*, const char*)) +{ + QTestState *qts; + qts = g_new0(QTestState, 1); + *s = qts; /* Expose qts early on, since the query endianness relies on it */ + qts->wstatus = 0; + for (int i = 0; i < MAX_IRQ; i++) { + qts->irq_level[i] = false; + } + + qtest_client_set_rx_handler(qts, qtest_client_inproc_recv_line); + + /* send() may not have a matching protoype, so use a type-safe wrapper */ + qts->ops.external_send = send; + qtest_client_set_tx_handler(qts, send_wrapper); + + qts->big_endian = qtest_query_target_endianness(qts); + + /* + * Set a dummy path for QTEST_QEMU_BINARY. Doesn't need to exist, but this + * way, qtest_get_arch works for inproc qtest. + */ + gchar *bin_path = g_strconcat("/qemu-system-", arch, NULL); + setenv("QTEST_QEMU_BINARY", bin_path, 0); + g_free(bin_path); + + return qts; +} + +void qtest_client_inproc_recv(void *opaque, const char *str) +{ + QTestState *qts = *(QTestState **)opaque; + + if (!qts->rx) { + qts->rx = g_string_new(NULL); + } + g_string_append(qts->rx, str); + return; +} diff --git a/tests/qtest/libqtest.h b/tests/qtest/libqtest.h index XXXXXXX..XXXXXXX 100644 --- a/tests/qtest/libqtest.h +++ b/tests/qtest/libqtest.h @@ -XXX,XX +XXX,XX @@ bool qtest_probe_child(QTestState *s); */ void qtest_set_expected_status(QTestState *s, int status); +QTestState *qtest_inproc_init(QTestState **s, bool log, const char* arch, + void (*send)(void*, const char*)); + +void qtest_client_inproc_recv(void *opaque, const char *str); #endif -- 2.24.1 From: Alexander Bulekov <alxndr@bu.edu> The handler allows a qtest client to send commands to the server by directly calling a function, rather than using a file/CharBackend Signed-off-by: Alexander Bulekov <alxndr@bu.edu> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Reviewed-by: Darren Kenny <darren.kenny@oracle.com> Message-id: 20200220041118.23264-9-alxndr@bu.edu Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- include/sysemu/qtest.h | 1 + qtest.c | 13 +++++++++++++ 2 files changed, 14 insertions(+) diff --git a/include/sysemu/qtest.h b/include/sysemu/qtest.h index XXXXXXX..XXXXXXX 100644 --- a/include/sysemu/qtest.h +++ b/include/sysemu/qtest.h @@ -XXX,XX +XXX,XX @@ void qtest_server_init(const char *qtest_chrdev, const char *qtest_log, Error ** void qtest_server_set_send_handler(void (*send)(void *, const char *), void *opaque); +void qtest_server_inproc_recv(void *opaque, const char *buf); #endif diff --git a/qtest.c b/qtest.c index XXXXXXX..XXXXXXX 100644 --- a/qtest.c +++ b/qtest.c @@ -XXX,XX +XXX,XX @@ bool qtest_driver(void) { return qtest_chr.chr != NULL; } + +void qtest_server_inproc_recv(void *dummy, const char *buf) +{ + static GString *gstr; + if (!gstr) { + gstr = g_string_new(NULL); + } + g_string_append(gstr, buf); + if (gstr->str[gstr->len - 1] == '\n') { + qtest_process_inbuf(NULL, gstr); + g_string_truncate(gstr, 0); + } +} -- 2.24.1 From: Alexander Bulekov <alxndr@bu.edu> The names i2c_send and i2c_recv collide with functions defined in hw/i2c/core.c. This causes an error when linking against libqos and softmmu simultaneously (for example when using qtest inproc). Rename the libqos functions to avoid this. Signed-off-by: Alexander Bulekov <alxndr@bu.edu> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Reviewed-by: Darren Kenny <darren.kenny@oracle.com> Acked-by: Thomas Huth <thuth@redhat.com> Message-id: 20200220041118.23264-10-alxndr@bu.edu Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- tests/qtest/libqos/i2c.c | 10 +++++----- tests/qtest/libqos/i2c.h | 4 ++-- tests/qtest/pca9552-test.c | 10 +++++----- 3 files changed, 12 insertions(+), 12 deletions(-) diff --git a/tests/qtest/libqos/i2c.c b/tests/qtest/libqos/i2c.c index XXXXXXX..XXXXXXX 100644 --- a/tests/qtest/libqos/i2c.c +++ b/tests/qtest/libqos/i2c.c @@ -XXX,XX +XXX,XX @@ #include "libqos/i2c.h" #include "libqtest.h" -void i2c_send(QI2CDevice *i2cdev, const uint8_t *buf, uint16_t len) +void qi2c_send(QI2CDevice *i2cdev, const uint8_t *buf, uint16_t len) { i2cdev->bus->send(i2cdev->bus, i2cdev->addr, buf, len); } -void i2c_recv(QI2CDevice *i2cdev, uint8_t *buf, uint16_t len) +void qi2c_recv(QI2CDevice *i2cdev, uint8_t *buf, uint16_t len) { i2cdev->bus->recv(i2cdev->bus, i2cdev->addr, buf, len); } @@ -XXX,XX +XXX,XX @@ void i2c_recv(QI2CDevice *i2cdev, uint8_t *buf, uint16_t len) void i2c_read_block(QI2CDevice *i2cdev, uint8_t reg, uint8_t *buf, uint16_t len) { - i2c_send(i2cdev, &reg, 1); - i2c_recv(i2cdev, buf, len); + qi2c_send(i2cdev, &reg, 1); + qi2c_recv(i2cdev, buf, len); } void i2c_write_block(QI2CDevice *i2cdev, uint8_t reg, @@ -XXX,XX +XXX,XX @@ void i2c_write_block(QI2CDevice *i2cdev, uint8_t reg, uint8_t *cmd = g_malloc(len + 1); cmd[0] = reg; memcpy(&cmd[1], buf, len); - i2c_send(i2cdev, cmd, len + 1); + qi2c_send(i2cdev, cmd, len + 1); g_free(cmd); } diff --git a/tests/qtest/libqos/i2c.h b/tests/qtest/libqos/i2c.h index XXXXXXX..XXXXXXX 100644 --- a/tests/qtest/libqos/i2c.h +++ b/tests/qtest/libqos/i2c.h @@ -XXX,XX +XXX,XX @@ struct QI2CDevice { void *i2c_device_create(void *i2c_bus, QGuestAllocator *alloc, void *addr); void add_qi2c_address(QOSGraphEdgeOptions *opts, QI2CAddress *addr); -void i2c_send(QI2CDevice *dev, const uint8_t *buf, uint16_t len); -void i2c_recv(QI2CDevice *dev, uint8_t *buf, uint16_t len); +void qi2c_send(QI2CDevice *dev, const uint8_t *buf, uint16_t len); +void qi2c_recv(QI2CDevice *dev, uint8_t *buf, uint16_t len); void i2c_read_block(QI2CDevice *dev, uint8_t reg, uint8_t *buf, uint16_t len); diff --git a/tests/qtest/pca9552-test.c b/tests/qtest/pca9552-test.c index XXXXXXX..XXXXXXX 100644 --- a/tests/qtest/pca9552-test.c +++ b/tests/qtest/pca9552-test.c @@ -XXX,XX +XXX,XX @@ static void receive_autoinc(void *obj, void *data, QGuestAllocator *alloc) pca9552_init(i2cdev); - i2c_send(i2cdev, &reg, 1); + qi2c_send(i2cdev, &reg, 1); /* PCA9552_LS0 */ - i2c_recv(i2cdev, &resp, 1); + qi2c_recv(i2cdev, &resp, 1); g_assert_cmphex(resp, ==, 0x54); /* PCA9552_LS1 */ - i2c_recv(i2cdev, &resp, 1); + qi2c_recv(i2cdev, &resp, 1); g_assert_cmphex(resp, ==, 0x55); /* PCA9552_LS2 */ - i2c_recv(i2cdev, &resp, 1); + qi2c_recv(i2cdev, &resp, 1); g_assert_cmphex(resp, ==, 0x55); /* PCA9552_LS3 */ - i2c_recv(i2cdev, &resp, 1); + qi2c_recv(i2cdev, &resp, 1); g_assert_cmphex(resp, ==, 0x54); } -- 2.24.1 From: Alexander Bulekov <alxndr@bu.edu> Most qos-related objects were specified in the qos-test-obj-y variable. qos-test-obj-y also included qos-test.o which defines a main(). This made it difficult to repurpose qos-test-obj-y to link anything beside tests/qos-test against libqos. This change separates objects that are libqos-specific and ones that are qos-test specific into different variables. Signed-off-by: Alexander Bulekov <alxndr@bu.edu> Reviewed-by: Darren Kenny <darren.kenny@oracle.com> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com> Message-id: 20200220041118.23264-11-alxndr@bu.edu Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- tests/qtest/Makefile.include | 71 ++++++++++++++++++------------------ 1 file changed, 36 insertions(+), 35 deletions(-) diff --git a/tests/qtest/Makefile.include b/tests/qtest/Makefile.include index XXXXXXX..XXXXXXX 100644 --- a/tests/qtest/Makefile.include +++ b/tests/qtest/Makefile.include @@ -XXX,XX +XXX,XX @@ check-qtest-s390x-y += migration-test # libqos / qgraph : libqgraph-obj-y = tests/qtest/libqos/qgraph.o -libqos-obj-y = $(libqgraph-obj-y) tests/qtest/libqos/pci.o tests/qtest/libqos/fw_cfg.o -libqos-obj-y += tests/qtest/libqos/malloc.o -libqos-obj-y += tests/qtest/libqos/libqos.o -libqos-spapr-obj-y = $(libqos-obj-y) tests/qtest/libqos/malloc-spapr.o +libqos-core-obj-y = $(libqgraph-obj-y) tests/qtest/libqos/pci.o tests/qtest/libqos/fw_cfg.o +libqos-core-obj-y += tests/qtest/libqos/malloc.o +libqos-core-obj-y += tests/qtest/libqos/libqos.o +libqos-spapr-obj-y = $(libqos-core-obj-y) tests/qtest/libqos/malloc-spapr.o libqos-spapr-obj-y += tests/qtest/libqos/libqos-spapr.o libqos-spapr-obj-y += tests/qtest/libqos/rtas.o libqos-spapr-obj-y += tests/qtest/libqos/pci-spapr.o -libqos-pc-obj-y = $(libqos-obj-y) tests/qtest/libqos/pci-pc.o +libqos-pc-obj-y = $(libqos-core-obj-y) tests/qtest/libqos/pci-pc.o libqos-pc-obj-y += tests/qtest/libqos/malloc-pc.o tests/qtest/libqos/libqos-pc.o libqos-pc-obj-y += tests/qtest/libqos/ahci.o libqos-usb-obj-y = $(libqos-spapr-obj-y) $(libqos-pc-obj-y) tests/qtest/libqos/usb.o # qos devices: -qos-test-obj-y = tests/qtest/qos-test.o $(libqgraph-obj-y) -qos-test-obj-y += $(libqos-pc-obj-y) $(libqos-spapr-obj-y) -qos-test-obj-y += tests/qtest/libqos/e1000e.o -qos-test-obj-y += tests/qtest/libqos/i2c.o -qos-test-obj-y += tests/qtest/libqos/i2c-imx.o -qos-test-obj-y += tests/qtest/libqos/i2c-omap.o -qos-test-obj-y += tests/qtest/libqos/sdhci.o -qos-test-obj-y += tests/qtest/libqos/tpci200.o -qos-test-obj-y += tests/qtest/libqos/virtio.o -qos-test-obj-$(CONFIG_VIRTFS) += tests/qtest/libqos/virtio-9p.o -qos-test-obj-y += tests/qtest/libqos/virtio-balloon.o -qos-test-obj-y += tests/qtest/libqos/virtio-blk.o -qos-test-obj-y += tests/qtest/libqos/virtio-mmio.o -qos-test-obj-y += tests/qtest/libqos/virtio-net.o -qos-test-obj-y += tests/qtest/libqos/virtio-pci.o -qos-test-obj-y += tests/qtest/libqos/virtio-pci-modern.o -qos-test-obj-y += tests/qtest/libqos/virtio-rng.o -qos-test-obj-y += tests/qtest/libqos/virtio-scsi.o -qos-test-obj-y += tests/qtest/libqos/virtio-serial.o +libqos-obj-y = $(libqgraph-obj-y) +libqos-obj-y += $(libqos-pc-obj-y) $(libqos-spapr-obj-y) +libqos-obj-y += tests/qtest/libqos/e1000e.o +libqos-obj-y += tests/qtest/libqos/i2c.o +libqos-obj-y += tests/qtest/libqos/i2c-imx.o +libqos-obj-y += tests/qtest/libqos/i2c-omap.o +libqos-obj-y += tests/qtest/libqos/sdhci.o +libqos-obj-y += tests/qtest/libqos/tpci200.o +libqos-obj-y += tests/qtest/libqos/virtio.o +libqos-obj-$(CONFIG_VIRTFS) += tests/qtest/libqos/virtio-9p.o +libqos-obj-y += tests/qtest/libqos/virtio-balloon.o +libqos-obj-y += tests/qtest/libqos/virtio-blk.o +libqos-obj-y += tests/qtest/libqos/virtio-mmio.o +libqos-obj-y += tests/qtest/libqos/virtio-net.o +libqos-obj-y += tests/qtest/libqos/virtio-pci.o +libqos-obj-y += tests/qtest/libqos/virtio-pci-modern.o +libqos-obj-y += tests/qtest/libqos/virtio-rng.o +libqos-obj-y += tests/qtest/libqos/virtio-scsi.o +libqos-obj-y += tests/qtest/libqos/virtio-serial.o # qos machines: -qos-test-obj-y += tests/qtest/libqos/aarch64-xlnx-zcu102-machine.o -qos-test-obj-y += tests/qtest/libqos/arm-imx25-pdk-machine.o -qos-test-obj-y += tests/qtest/libqos/arm-n800-machine.o -qos-test-obj-y += tests/qtest/libqos/arm-raspi2-machine.o -qos-test-obj-y += tests/qtest/libqos/arm-sabrelite-machine.o -qos-test-obj-y += tests/qtest/libqos/arm-smdkc210-machine.o -qos-test-obj-y += tests/qtest/libqos/arm-virt-machine.o -qos-test-obj-y += tests/qtest/libqos/arm-xilinx-zynq-a9-machine.o -qos-test-obj-y += tests/qtest/libqos/ppc64_pseries-machine.o -qos-test-obj-y += tests/qtest/libqos/x86_64_pc-machine.o +libqos-obj-y += tests/qtest/libqos/aarch64-xlnx-zcu102-machine.o +libqos-obj-y += tests/qtest/libqos/arm-imx25-pdk-machine.o +libqos-obj-y += tests/qtest/libqos/arm-n800-machine.o +libqos-obj-y += tests/qtest/libqos/arm-raspi2-machine.o +libqos-obj-y += tests/qtest/libqos/arm-sabrelite-machine.o +libqos-obj-y += tests/qtest/libqos/arm-smdkc210-machine.o +libqos-obj-y += tests/qtest/libqos/arm-virt-machine.o +libqos-obj-y += tests/qtest/libqos/arm-xilinx-zynq-a9-machine.o +libqos-obj-y += tests/qtest/libqos/ppc64_pseries-machine.o +libqos-obj-y += tests/qtest/libqos/x86_64_pc-machine.o # qos tests: +qos-test-obj-y += tests/qtest/qos-test.o qos-test-obj-y += tests/qtest/ac97-test.o qos-test-obj-y += tests/qtest/ds1338-test.o qos-test-obj-y += tests/qtest/e1000-test.o @@ -XXX,XX +XXX,XX @@ check-unit-y += tests/test-qgraph$(EXESUF) tests/test-qgraph$(EXESUF): tests/test-qgraph.o $(libqgraph-obj-y) check-qtest-generic-y += qos-test -tests/qtest/qos-test$(EXESUF): $(qos-test-obj-y) +tests/qtest/qos-test$(EXESUF): $(qos-test-obj-y) $(libqos-obj-y) # QTest dependencies: tests/qtest/qmp-test$(EXESUF): tests/qtest/qmp-test.o -- 2.24.1 From: Alexander Bulekov <alxndr@bu.edu> The moved functions are not specific to qos-test and might be useful elsewhere. For example the virtual-device fuzzer makes use of them for qos-assisted fuzz-targets. Signed-off-by: Alexander Bulekov <alxndr@bu.edu> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com> Reviewed-by: Darren Kenny <darren.kenny@oracle.com> Message-id: 20200220041118.23264-12-alxndr@bu.edu Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- tests/qtest/Makefile.include | 1 + tests/qtest/libqos/qos_external.c | 168 ++++++++++++++++++++++++++++++ tests/qtest/libqos/qos_external.h | 28 +++++ tests/qtest/qos-test.c | 132 +---------------------- 4 files changed, 198 insertions(+), 131 deletions(-) create mode 100644 tests/qtest/libqos/qos_external.c create mode 100644 tests/qtest/libqos/qos_external.h diff --git a/tests/qtest/Makefile.include b/tests/qtest/Makefile.include index XXXXXXX..XXXXXXX 100644 --- a/tests/qtest/Makefile.include +++ b/tests/qtest/Makefile.include @@ -XXX,XX +XXX,XX @@ libqos-usb-obj-y = $(libqos-spapr-obj-y) $(libqos-pc-obj-y) tests/qtest/libqos/u # qos devices: libqos-obj-y = $(libqgraph-obj-y) libqos-obj-y += $(libqos-pc-obj-y) $(libqos-spapr-obj-y) +libqos-obj-y += tests/qtest/libqos/qos_external.o libqos-obj-y += tests/qtest/libqos/e1000e.o libqos-obj-y += tests/qtest/libqos/i2c.o libqos-obj-y += tests/qtest/libqos/i2c-imx.o diff --git a/tests/qtest/libqos/qos_external.c b/tests/qtest/libqos/qos_external.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/tests/qtest/libqos/qos_external.c @@ -XXX,XX +XXX,XX @@ +/* + * libqos driver framework + * + * Copyright (c) 2018 Emanuele Giuseppe Esposito <e.emanuelegiuseppe@gmail.com> + * + * This library is free software; you can redistribute it and/or + * modify it under the terms of the GNU Lesser General Public + * License version 2 as published by the Free Software Foundation. + * + * This library is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * Lesser General Public License for more details. + * + * You should have received a copy of the GNU Lesser General Public + * License along with this library; if not, see <http://www.gnu.org/licenses/> + */ + +#include "qemu/osdep.h" +#include <getopt.h> +#include "libqtest.h" +#include "qapi/qmp/qdict.h" +#include "qapi/qmp/qbool.h" +#include "qapi/qmp/qstring.h" +#include "qemu/module.h" +#include "qapi/qmp/qlist.h" +#include "libqos/malloc.h" +#include "libqos/qgraph.h" +#include "libqos/qgraph_internal.h" +#include "libqos/qos_external.h" + + + +void apply_to_node(const char *name, bool is_machine, bool is_abstract) +{ + char *machine_name = NULL; + if (is_machine) { + const char *arch = qtest_get_arch(); + machine_name = g_strconcat(arch, "/", name, NULL); + name = machine_name; + } + qos_graph_node_set_availability(name, true); + if (is_abstract) { + qos_delete_cmd_line(name); + } + g_free(machine_name); +} + +/** + * apply_to_qlist(): using QMP queries QEMU for a list of + * machines and devices available, and sets the respective node + * as true. If a node is found, also all its produced and contained + * child are marked available. + * + * See qos_graph_node_set_availability() for more info + */ +void apply_to_qlist(QList *list, bool is_machine) +{ + const QListEntry *p; + const char *name; + bool abstract; + QDict *minfo; + QObject *qobj; + QString *qstr; + QBool *qbool; + + for (p = qlist_first(list); p; p = qlist_next(p)) { + minfo = qobject_to(QDict, qlist_entry_obj(p)); + qobj = qdict_get(minfo, "name"); + qstr = qobject_to(QString, qobj); + name = qstring_get_str(qstr); + + qobj = qdict_get(minfo, "abstract"); + if (qobj) { + qbool = qobject_to(QBool, qobj); + abstract = qbool_get_bool(qbool); + } else { + abstract = false; + } + + apply_to_node(name, is_machine, abstract); + qobj = qdict_get(minfo, "alias"); + if (qobj) { + qstr = qobject_to(QString, qobj); + name = qstring_get_str(qstr); + apply_to_node(name, is_machine, abstract); + } + } +} + +QGuestAllocator *get_machine_allocator(QOSGraphObject *obj) +{ + return obj->get_driver(obj, "memory"); +} + +/** + * allocate_objects(): given an array of nodes @arg, + * walks the path invoking all constructors and + * passing the corresponding parameter in order to + * continue the objects allocation. + * Once the test is reached, return the object it consumes. + * + * Since the machine and QEDGE_CONSUMED_BY nodes allocate + * memory in the constructor, g_test_queue_destroy is used so + * that after execution they can be safely free'd. (The test's + * ->before callback is also welcome to use g_test_queue_destroy). + * + * Note: as specified in walk_path() too, @arg is an array of + * char *, where arg[0] is a pointer to the command line + * string that will be used to properly start QEMU when executing + * the test, and the remaining elements represent the actual objects + * that will be allocated. + */ +void *allocate_objects(QTestState *qts, char **path, QGuestAllocator **p_alloc) +{ + int current = 0; + QGuestAllocator *alloc; + QOSGraphObject *parent = NULL; + QOSGraphEdge *edge; + QOSGraphNode *node; + void *edge_arg; + void *obj; + + node = qos_graph_get_node(path[current]); + g_assert(node->type == QNODE_MACHINE); + + obj = qos_machine_new(node, qts); + qos_object_queue_destroy(obj); + + alloc = get_machine_allocator(obj); + if (p_alloc) { + *p_alloc = alloc; + } + + for (;;) { + if (node->type != QNODE_INTERFACE) { + qos_object_start_hw(obj); + parent = obj; + } + + /* follow edge and get object for next node constructor */ + current++; + edge = qos_graph_get_edge(path[current - 1], path[current]); + node = qos_graph_get_node(path[current]); + + if (node->type == QNODE_TEST) { + g_assert(qos_graph_edge_get_type(edge) == QEDGE_CONSUMED_BY); + return obj; + } + + switch (qos_graph_edge_get_type(edge)) { + case QEDGE_PRODUCES: + obj = parent->get_driver(parent, path[current]); + break; + + case QEDGE_CONSUMED_BY: + edge_arg = qos_graph_edge_get_arg(edge); + obj = qos_driver_new(node, obj, alloc, edge_arg); + qos_object_queue_destroy(obj); + break; + + case QEDGE_CONTAINS: + obj = parent->get_device(parent, path[current]); + break; + } + } +} + diff --git a/tests/qtest/libqos/qos_external.h b/tests/qtest/libqos/qos_external.h new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/tests/qtest/libqos/qos_external.h @@ -XXX,XX +XXX,XX @@ +/* + * libqos driver framework + * + * Copyright (c) 2018 Emanuele Giuseppe Esposito <e.emanuelegiuseppe@gmail.com> + * + * This library is free software; you can redistribute it and/or + * modify it under the terms of the GNU Lesser General Public + * License version 2 as published by the Free Software Foundation. + * + * This library is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * Lesser General Public License for more details. + * + * You should have received a copy of the GNU Lesser General Public + * License along with this library; if not, see <http://www.gnu.org/licenses/> + */ + +#ifndef QOS_EXTERNAL_H +#define QOS_EXTERNAL_H +#include "libqos/qgraph.h" + +void apply_to_node(const char *name, bool is_machine, bool is_abstract); +void apply_to_qlist(QList *list, bool is_machine); +QGuestAllocator *get_machine_allocator(QOSGraphObject *obj); +void *allocate_objects(QTestState *qts, char **path, QGuestAllocator **p_alloc); + +#endif diff --git a/tests/qtest/qos-test.c b/tests/qtest/qos-test.c index XXXXXXX..XXXXXXX 100644 --- a/tests/qtest/qos-test.c +++ b/tests/qtest/qos-test.c @@ -XXX,XX +XXX,XX @@ #include "libqos/malloc.h" #include "libqos/qgraph.h" #include "libqos/qgraph_internal.h" +#include "libqos/qos_external.h" static char *old_path; -static void apply_to_node(const char *name, bool is_machine, bool is_abstract) -{ - char *machine_name = NULL; - if (is_machine) { - const char *arch = qtest_get_arch(); - machine_name = g_strconcat(arch, "/", name, NULL); - name = machine_name; - } - qos_graph_node_set_availability(name, true); - if (is_abstract) { - qos_delete_cmd_line(name); - } - g_free(machine_name); -} -/** - * apply_to_qlist(): using QMP queries QEMU for a list of - * machines and devices available, and sets the respective node - * as true. If a node is found, also all its produced and contained - * child are marked available. - * - * See qos_graph_node_set_availability() for more info - */ -static void apply_to_qlist(QList *list, bool is_machine) -{ - const QListEntry *p; - const char *name; - bool abstract; - QDict *minfo; - QObject *qobj; - QString *qstr; - QBool *qbool; - - for (p = qlist_first(list); p; p = qlist_next(p)) { - minfo = qobject_to(QDict, qlist_entry_obj(p)); - qobj = qdict_get(minfo, "name"); - qstr = qobject_to(QString, qobj); - name = qstring_get_str(qstr); - - qobj = qdict_get(minfo, "abstract"); - if (qobj) { - qbool = qobject_to(QBool, qobj); - abstract = qbool_get_bool(qbool); - } else { - abstract = false; - } - - apply_to_node(name, is_machine, abstract); - qobj = qdict_get(minfo, "alias"); - if (qobj) { - qstr = qobject_to(QString, qobj); - name = qstring_get_str(qstr); - apply_to_node(name, is_machine, abstract); - } - } -} /** * qos_set_machines_devices_available(): sets availability of qgraph @@ -XXX,XX +XXX,XX @@ static void qos_set_machines_devices_available(void) qobject_unref(response); } -static QGuestAllocator *get_machine_allocator(QOSGraphObject *obj) -{ - return obj->get_driver(obj, "memory"); -} static void restart_qemu_or_continue(char *path) { @@ -XXX,XX +XXX,XX @@ void qos_invalidate_command_line(void) old_path = NULL; } -/** - * allocate_objects(): given an array of nodes @arg, - * walks the path invoking all constructors and - * passing the corresponding parameter in order to - * continue the objects allocation. - * Once the test is reached, return the object it consumes. - * - * Since the machine and QEDGE_CONSUMED_BY nodes allocate - * memory in the constructor, g_test_queue_destroy is used so - * that after execution they can be safely free'd. (The test's - * ->before callback is also welcome to use g_test_queue_destroy). - * - * Note: as specified in walk_path() too, @arg is an array of - * char *, where arg[0] is a pointer to the command line - * string that will be used to properly start QEMU when executing - * the test, and the remaining elements represent the actual objects - * that will be allocated. - */ -static void *allocate_objects(QTestState *qts, char **path, QGuestAllocator **p_alloc) -{ - int current = 0; - QGuestAllocator *alloc; - QOSGraphObject *parent = NULL; - QOSGraphEdge *edge; - QOSGraphNode *node; - void *edge_arg; - void *obj; - - node = qos_graph_get_node(path[current]); - g_assert(node->type == QNODE_MACHINE); - - obj = qos_machine_new(node, qts); - qos_object_queue_destroy(obj); - - alloc = get_machine_allocator(obj); - if (p_alloc) { - *p_alloc = alloc; - } - - for (;;) { - if (node->type != QNODE_INTERFACE) { - qos_object_start_hw(obj); - parent = obj; - } - - /* follow edge and get object for next node constructor */ - current++; - edge = qos_graph_get_edge(path[current - 1], path[current]); - node = qos_graph_get_node(path[current]); - - if (node->type == QNODE_TEST) { - g_assert(qos_graph_edge_get_type(edge) == QEDGE_CONSUMED_BY); - return obj; - } - - switch (qos_graph_edge_get_type(edge)) { - case QEDGE_PRODUCES: - obj = parent->get_driver(parent, path[current]); - break; - - case QEDGE_CONSUMED_BY: - edge_arg = qos_graph_edge_get_arg(edge); - obj = qos_driver_new(node, obj, alloc, edge_arg); - qos_object_queue_destroy(obj); - break; - - case QEDGE_CONTAINS: - obj = parent->get_device(parent, path[current]); - break; - } - } -} /* The argument to run_one_test, which is the test function that is registered * with GTest, is a vector of strings. The first item is the initial command -- 2.24.1 From: Alexander Bulekov <alxndr@bu.edu> tests/fuzz/fuzz.c serves as the entry point for the virtual-device fuzzer. Namely, libfuzzer invokes the LLVMFuzzerInitialize and LLVMFuzzerTestOneInput functions, both of which are defined in this file. This change adds a "FuzzTarget" struct, along with the fuzz_add_target function, which should be used to define new fuzz targets. Signed-off-by: Alexander Bulekov <alxndr@bu.edu> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Reviewed-by: Darren Kenny <darren.kenny@oracle.com> Message-id: 20200220041118.23264-13-alxndr@bu.edu Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- MAINTAINERS | 8 ++ tests/qtest/fuzz/Makefile.include | 6 + tests/qtest/fuzz/fuzz.c | 179 ++++++++++++++++++++++++++++++ tests/qtest/fuzz/fuzz.h | 95 ++++++++++++++++ 4 files changed, 288 insertions(+) create mode 100644 tests/qtest/fuzz/Makefile.include create mode 100644 tests/qtest/fuzz/fuzz.c create mode 100644 tests/qtest/fuzz/fuzz.h diff --git a/MAINTAINERS b/MAINTAINERS index XXXXXXX..XXXXXXX 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -XXX,XX +XXX,XX @@ F: qtest.c F: accel/qtest.c F: tests/qtest/ +Device Fuzzing +M: Alexander Bulekov <alxndr@bu.edu> +R: Paolo Bonzini <pbonzini@redhat.com> +R: Bandan Das <bsd@redhat.com> +R: Stefan Hajnoczi <stefanha@redhat.com> +S: Maintained +F: tests/qtest/fuzz/ + Register API M: Alistair Francis <alistair@alistair23.me> S: Maintained diff --git a/tests/qtest/fuzz/Makefile.include b/tests/qtest/fuzz/Makefile.include new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/tests/qtest/fuzz/Makefile.include @@ -XXX,XX +XXX,XX @@ +QEMU_PROG_FUZZ=qemu-fuzz-$(TARGET_NAME)$(EXESUF) + +fuzz-obj-y += tests/qtest/libqtest.o +fuzz-obj-y += tests/qtest/fuzz/fuzz.o # Fuzzer skeleton + +FUZZ_CFLAGS += -I$(SRC_PATH)/tests -I$(SRC_PATH)/tests/qtest diff --git a/tests/qtest/fuzz/fuzz.c b/tests/qtest/fuzz/fuzz.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/tests/qtest/fuzz/fuzz.c @@ -XXX,XX +XXX,XX @@ +/* + * fuzzing driver + * + * Copyright Red Hat Inc., 2019 + * + * Authors: + * Alexander Bulekov <alxndr@bu.edu> + * + * This work is licensed under the terms of the GNU GPL, version 2 or later. + * See the COPYING file in the top-level directory. + * + */ + +#include "qemu/osdep.h" + +#include <wordexp.h> + +#include "sysemu/qtest.h" +#include "sysemu/runstate.h" +#include "sysemu/sysemu.h" +#include "qemu/main-loop.h" +#include "tests/qtest/libqtest.h" +#include "tests/qtest/libqos/qgraph.h" +#include "fuzz.h" + +#define MAX_EVENT_LOOPS 10 + +typedef struct FuzzTargetState { + FuzzTarget *target; + QSLIST_ENTRY(FuzzTargetState) target_list; +} FuzzTargetState; + +typedef QSLIST_HEAD(, FuzzTargetState) FuzzTargetList; + +static const char *fuzz_arch = TARGET_NAME; + +static FuzzTargetList *fuzz_target_list; +static FuzzTarget *fuzz_target; +static QTestState *fuzz_qts; + + + +void flush_events(QTestState *s) +{ + int i = MAX_EVENT_LOOPS; + while (g_main_context_pending(NULL) && i-- > 0) { + main_loop_wait(false); + } +} + +static QTestState *qtest_setup(void) +{ + qtest_server_set_send_handler(&qtest_client_inproc_recv, &fuzz_qts); + return qtest_inproc_init(&fuzz_qts, false, fuzz_arch, + &qtest_server_inproc_recv); +} + +void fuzz_add_target(const FuzzTarget *target) +{ + FuzzTargetState *tmp; + FuzzTargetState *target_state; + if (!fuzz_target_list) { + fuzz_target_list = g_new0(FuzzTargetList, 1); + } + + QSLIST_FOREACH(tmp, fuzz_target_list, target_list) { + if (g_strcmp0(tmp->target->name, target->name) == 0) { + fprintf(stderr, "Error: Fuzz target name %s already in use\n", + target->name); + abort(); + } + } + target_state = g_new0(FuzzTargetState, 1); + target_state->target = g_new0(FuzzTarget, 1); + *(target_state->target) = *target; + QSLIST_INSERT_HEAD(fuzz_target_list, target_state, target_list); +} + + + +static void usage(char *path) +{ + printf("Usage: %s --fuzz-target=FUZZ_TARGET [LIBFUZZER ARGUMENTS]\n", path); + printf("where FUZZ_TARGET is one of:\n"); + FuzzTargetState *tmp; + if (!fuzz_target_list) { + fprintf(stderr, "Fuzz target list not initialized\n"); + abort(); + } + QSLIST_FOREACH(tmp, fuzz_target_list, target_list) { + printf(" * %s : %s\n", tmp->target->name, + tmp->target->description); + } + exit(0); +} + +static FuzzTarget *fuzz_get_target(char* name) +{ + FuzzTargetState *tmp; + if (!fuzz_target_list) { + fprintf(stderr, "Fuzz target list not initialized\n"); + abort(); + } + + QSLIST_FOREACH(tmp, fuzz_target_list, target_list) { + if (strcmp(tmp->target->name, name) == 0) { + return tmp->target; + } + } + return NULL; +} + + +/* Executed for each fuzzing-input */ +int LLVMFuzzerTestOneInput(const unsigned char *Data, size_t Size) +{ + /* + * Do the pre-fuzz-initialization before the first fuzzing iteration, + * instead of before the actual fuzz loop. This is needed since libfuzzer + * may fork off additional workers, prior to the fuzzing loop, and if + * pre_fuzz() sets up e.g. shared memory, this should be done for the + * individual worker processes + */ + static int pre_fuzz_done; + if (!pre_fuzz_done && fuzz_target->pre_fuzz) { + fuzz_target->pre_fuzz(fuzz_qts); + pre_fuzz_done = true; + } + + fuzz_target->fuzz(fuzz_qts, Data, Size); + return 0; +} + +/* Executed once, prior to fuzzing */ +int LLVMFuzzerInitialize(int *argc, char ***argv, char ***envp) +{ + + char *target_name; + + /* Initialize qgraph and modules */ + qos_graph_init(); + module_call_init(MODULE_INIT_FUZZ_TARGET); + module_call_init(MODULE_INIT_QOM); + module_call_init(MODULE_INIT_LIBQOS); + + if (*argc <= 1) { + usage(**argv); + } + + /* Identify the fuzz target */ + target_name = (*argv)[1]; + if (!strstr(target_name, "--fuzz-target=")) { + usage(**argv); + } + + target_name += strlen("--fuzz-target="); + + fuzz_target = fuzz_get_target(target_name); + if (!fuzz_target) { + usage(**argv); + } + + fuzz_qts = qtest_setup(); + + if (fuzz_target->pre_vm_init) { + fuzz_target->pre_vm_init(); + } + + /* Run QEMU's softmmu main with the fuzz-target dependent arguments */ + const char *init_cmdline = fuzz_target->get_init_cmdline(fuzz_target); + + /* Split the runcmd into an argv and argc */ + wordexp_t result; + wordexp(init_cmdline, &result, 0); + + qemu_init(result.we_wordc, result.we_wordv, NULL); + + return 0; +} diff --git a/tests/qtest/fuzz/fuzz.h b/tests/qtest/fuzz/fuzz.h new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/tests/qtest/fuzz/fuzz.h @@ -XXX,XX +XXX,XX @@ +/* + * fuzzing driver + * + * Copyright Red Hat Inc., 2019 + * + * Authors: + * Alexander Bulekov <alxndr@bu.edu> + * + * This work is licensed under the terms of the GNU GPL, version 2 or later. + * See the COPYING file in the top-level directory. + * + */ + +#ifndef FUZZER_H_ +#define FUZZER_H_ + +#include "qemu/osdep.h" +#include "qemu/units.h" +#include "qapi/error.h" + +#include "tests/qtest/libqtest.h" + +/** + * A libfuzzer fuzzing target + * + * The QEMU fuzzing binary is built with all available targets, each + * with a unique @name that can be specified on the command-line to + * select which target should run. + * + * A target must implement ->fuzz() to process a random input. If QEMU + * crashes in ->fuzz() then libfuzzer will record a failure. + * + * Fuzzing targets are registered with fuzz_add_target(): + * + * static const FuzzTarget fuzz_target = { + * .name = "my-device-fifo", + * .description = "Fuzz the FIFO buffer registers of my-device", + * ... + * }; + * + * static void register_fuzz_target(void) + * { + * fuzz_add_target(&fuzz_target); + * } + * fuzz_target_init(register_fuzz_target); + */ +typedef struct FuzzTarget { + const char *name; /* target identifier (passed to --fuzz-target=)*/ + const char *description; /* help text */ + + + /* + * returns the arg-list that is passed to qemu/softmmu init() + * Cannot be NULL + */ + const char* (*get_init_cmdline)(struct FuzzTarget *); + + /* + * will run once, prior to running qemu/softmmu init. + * eg: set up shared-memory for communication with the child-process + * Can be NULL + */ + void(*pre_vm_init)(void); + + /* + * will run once, after QEMU has been initialized, prior to the fuzz-loop. + * eg: detect the memory map + * Can be NULL + */ + void(*pre_fuzz)(QTestState *); + + /* + * accepts and executes an input from libfuzzer. this is repeatedly + * executed during the fuzzing loop. Its should handle setup, input + * execution and cleanup. + * Cannot be NULL + */ + void(*fuzz)(QTestState *, const unsigned char *, size_t); + +} FuzzTarget; + +void flush_events(QTestState *); +void reboot(QTestState *); + +/* + * makes a copy of *target and adds it to the target-list. + * i.e. fine to set up target on the caller's stack + */ +void fuzz_add_target(const FuzzTarget *target); + +int LLVMFuzzerTestOneInput(const unsigned char *Data, size_t Size); +int LLVMFuzzerInitialize(int *argc, char ***argv, char ***envp); + +#endif + -- 2.24.1 From: Alexander Bulekov <alxndr@bu.edu> Ram blocks were marked MADV_DONTFORK breaking fuzzing-tests which execute each test-input in a forked process. Signed-off-by: Alexander Bulekov <alxndr@bu.edu> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Reviewed-by: Darren Kenny <darren.kenny@oracle.com> Message-id: 20200220041118.23264-14-alxndr@bu.edu Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- exec.c | 12 ++++++++++-- 1 file changed, 10 insertions(+), 2 deletions(-) diff --git a/exec.c b/exec.c index XXXXXXX..XXXXXXX 100644 --- a/exec.c +++ b/exec.c @@ -XXX,XX +XXX,XX @@ #include "sysemu/kvm.h" #include "sysemu/sysemu.h" #include "sysemu/tcg.h" +#include "sysemu/qtest.h" #include "qemu/timer.h" #include "qemu/config-file.h" #include "qemu/error-report.h" @@ -XXX,XX +XXX,XX @@ static void ram_block_add(RAMBlock *new_block, Error **errp, bool shared) if (new_block->host) { qemu_ram_setup_dump(new_block->host, new_block->max_length); qemu_madvise(new_block->host, new_block->max_length, QEMU_MADV_HUGEPAGE); - /* MADV_DONTFORK is also needed by KVM in absence of synchronous MMU */ - qemu_madvise(new_block->host, new_block->max_length, QEMU_MADV_DONTFORK); + /* + * MADV_DONTFORK is also needed by KVM in absence of synchronous MMU + * Configure it unless the machine is a qtest server, in which case + * KVM is not used and it may be forked (eg for fuzzing purposes). + */ + if (!qtest_enabled()) { + qemu_madvise(new_block->host, new_block->max_length, + QEMU_MADV_DONTFORK); + } ram_block_notify_add(new_block->host, new_block->max_length); } } -- 2.24.1 From: Alexander Bulekov <alxndr@bu.edu> The qtest-based fuzzer makes use of forking to reset-state between tests. Keep the callback enabled, so the call_rcu thread gets created within the child process. Signed-off-by: Alexander Bulekov <alxndr@bu.edu> Reviewed-by: Darren Kenny <darren.kenny@oracle.com> Acked-by: Stefan Hajnoczi <stefanha@redhat.com> Message-id: 20200220041118.23264-15-alxndr@bu.edu Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- softmmu/vl.c | 12 +++++++++++- 1 file changed, 11 insertions(+), 1 deletion(-) diff --git a/softmmu/vl.c b/softmmu/vl.c index XXXXXXX..XXXXXXX 100644 --- a/softmmu/vl.c +++ b/softmmu/vl.c @@ -XXX,XX +XXX,XX @@ void qemu_init(int argc, char **argv, char **envp) set_memory_options(&ram_slots, &maxram_size, machine_class); os_daemonize(); - rcu_disable_atfork(); + + /* + * If QTest is enabled, keep the rcu_atfork enabled, since system processes + * may be forked testing purposes (e.g. fork-server based fuzzing) The fork + * should happen before a signle cpu instruction is executed, to prevent + * deadlocks. See commit 73c6e40, rcu: "completely disable pthread_atfork + * callbacks as soon as possible" + */ + if (!qtest_enabled()) { + rcu_disable_atfork(); + } if (pid_file && !qemu_write_pidfile(pid_file, &err)) { error_reportf_err(err, "cannot create PID file: "); -- 2.24.1 From: Alexander Bulekov <alxndr@bu.edu> fork() is a simple way to ensure that state does not leak in between fuzzing runs. Unfortunately, the fuzzer mutation engine relies on bitmaps which contain coverage information for each fuzzing run, and these bitmaps should be copied from the child to the parent(where the mutation occurs). These bitmaps are created through compile-time instrumentation and they are not shared with fork()-ed processes, by default. To address this, we create a shared memory region, adjust its size and map it _over_ the counter region. Furthermore, libfuzzer doesn't generally expose the globals that specify the location of the counters/coverage bitmap. As a workaround, we rely on a custom linker script which forces all of the bitmaps we care about to be placed in a contiguous region, which is easy to locate and mmap over. Signed-off-by: Alexander Bulekov <alxndr@bu.edu> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Reviewed-by: Darren Kenny <darren.kenny@oracle.com> Message-id: 20200220041118.23264-16-alxndr@bu.edu Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- tests/qtest/fuzz/Makefile.include | 5 +++ tests/qtest/fuzz/fork_fuzz.c | 55 +++++++++++++++++++++++++++++++ tests/qtest/fuzz/fork_fuzz.h | 23 +++++++++++++ tests/qtest/fuzz/fork_fuzz.ld | 37 +++++++++++++++++++++ 4 files changed, 120 insertions(+) create mode 100644 tests/qtest/fuzz/fork_fuzz.c create mode 100644 tests/qtest/fuzz/fork_fuzz.h create mode 100644 tests/qtest/fuzz/fork_fuzz.ld diff --git a/tests/qtest/fuzz/Makefile.include b/tests/qtest/fuzz/Makefile.include index XXXXXXX..XXXXXXX 100644 --- a/tests/qtest/fuzz/Makefile.include +++ b/tests/qtest/fuzz/Makefile.include @@ -XXX,XX +XXX,XX @@ QEMU_PROG_FUZZ=qemu-fuzz-$(TARGET_NAME)$(EXESUF) fuzz-obj-y += tests/qtest/libqtest.o fuzz-obj-y += tests/qtest/fuzz/fuzz.o # Fuzzer skeleton +fuzz-obj-y += tests/qtest/fuzz/fork_fuzz.o FUZZ_CFLAGS += -I$(SRC_PATH)/tests -I$(SRC_PATH)/tests/qtest + +# Linker Script to force coverage-counters into known regions which we can mark +# shared +FUZZ_LDFLAGS += -Xlinker -T$(SRC_PATH)/tests/qtest/fuzz/fork_fuzz.ld diff --git a/tests/qtest/fuzz/fork_fuzz.c b/tests/qtest/fuzz/fork_fuzz.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/tests/qtest/fuzz/fork_fuzz.c @@ -XXX,XX +XXX,XX @@ +/* + * Fork-based fuzzing helpers + * + * Copyright Red Hat Inc., 2019 + * + * Authors: + * Alexander Bulekov <alxndr@bu.edu> + * + * This work is licensed under the terms of the GNU GPL, version 2 or later. + * See the COPYING file in the top-level directory. + * + */ + +#include "qemu/osdep.h" +#include "fork_fuzz.h" + + +void counter_shm_init(void) +{ + char *shm_path = g_strdup_printf("/qemu-fuzz-cntrs.%d", getpid()); + int fd = shm_open(shm_path, O_CREAT | O_RDWR, S_IRUSR | S_IWUSR); + g_free(shm_path); + + if (fd == -1) { + perror("Error: "); + exit(1); + } + if (ftruncate(fd, &__FUZZ_COUNTERS_END - &__FUZZ_COUNTERS_START) == -1) { + perror("Error: "); + exit(1); + } + /* Copy what's in the counter region to the shm.. */ + void *rptr = mmap(NULL , + &__FUZZ_COUNTERS_END - &__FUZZ_COUNTERS_START, + PROT_READ | PROT_WRITE, MAP_SHARED, fd, 0); + memcpy(rptr, + &__FUZZ_COUNTERS_START, + &__FUZZ_COUNTERS_END - &__FUZZ_COUNTERS_START); + + munmap(rptr, &__FUZZ_COUNTERS_END - &__FUZZ_COUNTERS_START); + + /* And map the shm over the counter region */ + rptr = mmap(&__FUZZ_COUNTERS_START, + &__FUZZ_COUNTERS_END - &__FUZZ_COUNTERS_START, + PROT_READ | PROT_WRITE, MAP_SHARED | MAP_FIXED, fd, 0); + + close(fd); + + if (!rptr) { + perror("Error: "); + exit(1); + } +} + + diff --git a/tests/qtest/fuzz/fork_fuzz.h b/tests/qtest/fuzz/fork_fuzz.h new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/tests/qtest/fuzz/fork_fuzz.h @@ -XXX,XX +XXX,XX @@ +/* + * Fork-based fuzzing helpers + * + * Copyright Red Hat Inc., 2019 + * + * Authors: + * Alexander Bulekov <alxndr@bu.edu> + * + * This work is licensed under the terms of the GNU GPL, version 2 or later. + * See the COPYING file in the top-level directory. + * + */ + +#ifndef FORK_FUZZ_H +#define FORK_FUZZ_H + +extern uint8_t __FUZZ_COUNTERS_START; +extern uint8_t __FUZZ_COUNTERS_END; + +void counter_shm_init(void); + +#endif + diff --git a/tests/qtest/fuzz/fork_fuzz.ld b/tests/qtest/fuzz/fork_fuzz.ld new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/tests/qtest/fuzz/fork_fuzz.ld @@ -XXX,XX +XXX,XX @@ +/* We adjust linker script modification to place all of the stuff that needs to + * persist across fuzzing runs into a contiguous seciton of memory. Then, it is + * easy to re-map the counter-related memory as shared. +*/ + +SECTIONS +{ + .data.fuzz_start : ALIGN(4K) + { + __FUZZ_COUNTERS_START = .; + __start___sancov_cntrs = .; + *(_*sancov_cntrs); + __stop___sancov_cntrs = .; + + /* Lowest stack counter */ + *(__sancov_lowest_stack); + } + .data.fuzz_ordered : + { + /* Coverage counters. They're not necessary for fuzzing, but are useful + * for analyzing the fuzzing performance + */ + __start___llvm_prf_cnts = .; + *(*llvm_prf_cnts); + __stop___llvm_prf_cnts = .; + + /* Internal Libfuzzer TracePC object which contains the ValueProfileMap */ + FuzzerTracePC*(.bss*); + } + .data.fuzz_end : ALIGN(4K) + { + __FUZZ_COUNTERS_END = .; + } +} +/* Dont overwrite the SECTIONS in the default linker script. Instead insert the + * above into the default script */ +INSERT AFTER .data; -- 2.24.1 From: Alexander Bulekov <alxndr@bu.edu> Signed-off-by: Alexander Bulekov <alxndr@bu.edu> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Reviewed-by: Darren Kenny <darren.kenny@oracle.com> Message-id: 20200220041118.23264-17-alxndr@bu.edu Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- tests/qtest/fuzz/Makefile.include | 2 + tests/qtest/fuzz/qos_fuzz.c | 234 ++++++++++++++++++++++++++++++ tests/qtest/fuzz/qos_fuzz.h | 33 +++++ 3 files changed, 269 insertions(+) create mode 100644 tests/qtest/fuzz/qos_fuzz.c create mode 100644 tests/qtest/fuzz/qos_fuzz.h diff --git a/tests/qtest/fuzz/Makefile.include b/tests/qtest/fuzz/Makefile.include index XXXXXXX..XXXXXXX 100644 --- a/tests/qtest/fuzz/Makefile.include +++ b/tests/qtest/fuzz/Makefile.include @@ -XXX,XX +XXX,XX @@ QEMU_PROG_FUZZ=qemu-fuzz-$(TARGET_NAME)$(EXESUF) fuzz-obj-y += tests/qtest/libqtest.o +fuzz-obj-y += $(libqos-obj-y) fuzz-obj-y += tests/qtest/fuzz/fuzz.o # Fuzzer skeleton fuzz-obj-y += tests/qtest/fuzz/fork_fuzz.o +fuzz-obj-y += tests/qtest/fuzz/qos_fuzz.o FUZZ_CFLAGS += -I$(SRC_PATH)/tests -I$(SRC_PATH)/tests/qtest diff --git a/tests/qtest/fuzz/qos_fuzz.c b/tests/qtest/fuzz/qos_fuzz.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/tests/qtest/fuzz/qos_fuzz.c @@ -XXX,XX +XXX,XX @@ +/* + * QOS-assisted fuzzing helpers + * + * Copyright (c) 2018 Emanuele Giuseppe Esposito <e.emanuelegiuseppe@gmail.com> + * + * This library is free software; you can redistribute it and/or + * modify it under the terms of the GNU Lesser General Public + * License version 2 as published by the Free Software Foundation. + * + * This library is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * Lesser General Public License for more details. + * + * You should have received a copy of the GNU Lesser General Public + * License along with this library; if not, see <http://www.gnu.org/licenses/> + */ + +#include "qemu/osdep.h" +#include "qemu/units.h" +#include "qapi/error.h" +#include "qemu-common.h" +#include "exec/memory.h" +#include "exec/address-spaces.h" +#include "sysemu/sysemu.h" +#include "qemu/main-loop.h" + +#include "tests/qtest/libqtest.h" +#include "tests/qtest/libqos/malloc.h" +#include "tests/qtest/libqos/qgraph.h" +#include "tests/qtest/libqos/qgraph_internal.h" +#include "tests/qtest/libqos/qos_external.h" + +#include "fuzz.h" +#include "qos_fuzz.h" + +#include "qapi/qapi-commands-machine.h" +#include "qapi/qapi-commands-qom.h" +#include "qapi/qmp/qlist.h" + + +void *fuzz_qos_obj; +QGuestAllocator *fuzz_qos_alloc; + +static const char *fuzz_target_name; +static char **fuzz_path_vec; + +/* + * Replaced the qmp commands with direct qmp_marshal calls. + * Probably there is a better way to do this + */ +static void qos_set_machines_devices_available(void) +{ + QDict *req = qdict_new(); + QObject *response; + QDict *args = qdict_new(); + QList *lst; + Error *err = NULL; + + qmp_marshal_query_machines(NULL, &response, &err); + assert(!err); + lst = qobject_to(QList, response); + apply_to_qlist(lst, true); + + qobject_unref(response); + + + qdict_put_str(req, "execute", "qom-list-types"); + qdict_put_str(args, "implements", "device"); + qdict_put_bool(args, "abstract", true); + qdict_put_obj(req, "arguments", (QObject *) args); + + qmp_marshal_qom_list_types(args, &response, &err); + assert(!err); + lst = qobject_to(QList, response); + apply_to_qlist(lst, false); + qobject_unref(response); + qobject_unref(req); +} + +static char **current_path; + +void *qos_allocate_objects(QTestState *qts, QGuestAllocator **p_alloc) +{ + return allocate_objects(qts, current_path + 1, p_alloc); +} + +static const char *qos_build_main_args(void) +{ + char **path = fuzz_path_vec; + QOSGraphNode *test_node; + GString *cmd_line = g_string_new(path[0]); + void *test_arg; + + if (!path) { + fprintf(stderr, "QOS Path not found\n"); + abort(); + } + + /* Before test */ + current_path = path; + test_node = qos_graph_get_node(path[(g_strv_length(path) - 1)]); + test_arg = test_node->u.test.arg; + if (test_node->u.test.before) { + test_arg = test_node->u.test.before(cmd_line, test_arg); + } + /* Prepend the arguments that we need */ + g_string_prepend(cmd_line, + TARGET_NAME " -display none -machine accel=qtest -m 64 "); + return cmd_line->str; +} + +/* + * This function is largely a copy of qos-test.c:walk_path. Since walk_path + * is itself a callback, its a little annoying to add another argument/layer of + * indirection + */ +static void walk_path(QOSGraphNode *orig_path, int len) +{ + QOSGraphNode *path; + QOSGraphEdge *edge; + + /* etype set to QEDGE_CONSUMED_BY so that machine can add to the command line */ + QOSEdgeType etype = QEDGE_CONSUMED_BY; + + /* twice QOS_PATH_MAX_ELEMENT_SIZE since each edge can have its arg */ + char **path_vec = g_new0(char *, (QOS_PATH_MAX_ELEMENT_SIZE * 2)); + int path_vec_size = 0; + + char *after_cmd, *before_cmd, *after_device; + GString *after_device_str = g_string_new(""); + char *node_name = orig_path->name, *path_str; + + GString *cmd_line = g_string_new(""); + GString *cmd_line2 = g_string_new(""); + + path = qos_graph_get_node(node_name); /* root */ + node_name = qos_graph_edge_get_dest(path->path_edge); /* machine name */ + + path_vec[path_vec_size++] = node_name; + path_vec[path_vec_size++] = qos_get_machine_type(node_name); + + for (;;) { + path = qos_graph_get_node(node_name); + if (!path->path_edge) { + break; + } + + node_name = qos_graph_edge_get_dest(path->path_edge); + + /* append node command line + previous edge command line */ + if (path->command_line && etype == QEDGE_CONSUMED_BY) { + g_string_append(cmd_line, path->command_line); + g_string_append(cmd_line, after_device_str->str); + g_string_truncate(after_device_str, 0); + } + + path_vec[path_vec_size++] = qos_graph_edge_get_name(path->path_edge); + /* detect if edge has command line args */ + after_cmd = qos_graph_edge_get_after_cmd_line(path->path_edge); + after_device = qos_graph_edge_get_extra_device_opts(path->path_edge); + before_cmd = qos_graph_edge_get_before_cmd_line(path->path_edge); + edge = qos_graph_get_edge(path->name, node_name); + etype = qos_graph_edge_get_type(edge); + + if (before_cmd) { + g_string_append(cmd_line, before_cmd); + } + if (after_cmd) { + g_string_append(cmd_line2, after_cmd); + } + if (after_device) { + g_string_append(after_device_str, after_device); + } + } + + path_vec[path_vec_size++] = NULL; + g_string_append(cmd_line, after_device_str->str); + g_string_free(after_device_str, true); + + g_string_append(cmd_line, cmd_line2->str); + g_string_free(cmd_line2, true); + + /* + * here position 0 has <arch>/<machine>, position 1 has <machine>. + * The path must not have the <arch>, qtest_add_data_func adds it. + */ + path_str = g_strjoinv("/", path_vec + 1); + + /* Check that this is the test we care about: */ + char *test_name = strrchr(path_str, '/') + 1; + if (strcmp(test_name, fuzz_target_name) == 0) { + /* + * put arch/machine in position 1 so run_one_test can do its work + * and add the command line at position 0. + */ + path_vec[1] = path_vec[0]; + path_vec[0] = g_string_free(cmd_line, false); + + fuzz_path_vec = path_vec; + } else { + g_free(path_vec); + } + + g_free(path_str); +} + +static const char *qos_get_cmdline(FuzzTarget *t) +{ + /* + * Set a global variable that we use to identify the qos_path for our + * fuzz_target + */ + fuzz_target_name = t->name; + qos_set_machines_devices_available(); + qos_graph_foreach_test_path(walk_path); + return qos_build_main_args(); +} + +void fuzz_add_qos_target( + FuzzTarget *fuzz_opts, + const char *interface, + QOSGraphTestOptions *opts + ) +{ + qos_add_test(fuzz_opts->name, interface, NULL, opts); + fuzz_opts->get_init_cmdline = qos_get_cmdline; + fuzz_add_target(fuzz_opts); +} + +void qos_init_path(QTestState *s) +{ + fuzz_qos_obj = qos_allocate_objects(s , &fuzz_qos_alloc); +} diff --git a/tests/qtest/fuzz/qos_fuzz.h b/tests/qtest/fuzz/qos_fuzz.h new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/tests/qtest/fuzz/qos_fuzz.h @@ -XXX,XX +XXX,XX @@ +/* + * QOS-assisted fuzzing helpers + * + * Copyright Red Hat Inc., 2019 + * + * Authors: + * Alexander Bulekov <alxndr@bu.edu> + * + * This work is licensed under the terms of the GNU GPL, version 2 or later. + * See the COPYING file in the top-level directory. + */ + +#ifndef _QOS_FUZZ_H_ +#define _QOS_FUZZ_H_ + +#include "tests/qtest/fuzz/fuzz.h" +#include "tests/qtest/libqos/qgraph.h" + +int qos_fuzz(const unsigned char *Data, size_t Size); +void qos_setup(void); + +extern void *fuzz_qos_obj; +extern QGuestAllocator *fuzz_qos_alloc; + +void fuzz_add_qos_target( + FuzzTarget *fuzz_opts, + const char *interface, + QOSGraphTestOptions *opts + ); + +void qos_init_path(QTestState *); + +#endif -- 2.24.1 From: Alexander Bulekov <alxndr@bu.edu> Signed-off-by: Alexander Bulekov <alxndr@bu.edu> Reviewed-by: Darren Kenny <darren.kenny@oracle.com> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Message-id: 20200220041118.23264-18-alxndr@bu.edu Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- Makefile | 15 ++++++++++++++- Makefile.target | 16 ++++++++++++++++ 2 files changed, 30 insertions(+), 1 deletion(-) diff --git a/Makefile b/Makefile index XXXXXXX..XXXXXXX 100644 --- a/Makefile +++ b/Makefile @@ -XXX,XX +XXX,XX @@ config-host.h-timestamp: config-host.mak qemu-options.def: $(SRC_PATH)/qemu-options.hx $(SRC_PATH)/scripts/hxtool $(call quiet-command,sh $(SRC_PATH)/scripts/hxtool -h < $< > $@,"GEN","$@") -TARGET_DIRS_RULES := $(foreach t, all clean install, $(addsuffix /$(t), $(TARGET_DIRS))) +TARGET_DIRS_RULES := $(foreach t, all fuzz clean install, $(addsuffix /$(t), $(TARGET_DIRS))) SOFTMMU_ALL_RULES=$(filter %-softmmu/all, $(TARGET_DIRS_RULES)) $(SOFTMMU_ALL_RULES): $(authz-obj-y) @@ -XXX,XX +XXX,XX @@ ifdef DECOMPRESS_EDK2_BLOBS $(SOFTMMU_ALL_RULES): $(edk2-decompressed) endif +SOFTMMU_FUZZ_RULES=$(filter %-softmmu/fuzz, $(TARGET_DIRS_RULES)) +$(SOFTMMU_FUZZ_RULES): $(authz-obj-y) +$(SOFTMMU_FUZZ_RULES): $(block-obj-y) +$(SOFTMMU_FUZZ_RULES): $(chardev-obj-y) +$(SOFTMMU_FUZZ_RULES): $(crypto-obj-y) +$(SOFTMMU_FUZZ_RULES): $(io-obj-y) +$(SOFTMMU_FUZZ_RULES): config-all-devices.mak +$(SOFTMMU_FUZZ_RULES): $(edk2-decompressed) + .PHONY: $(TARGET_DIRS_RULES) # The $(TARGET_DIRS_RULES) are of the form SUBDIR/GOAL, so that # $(dir $@) yields the sub-directory, and $(notdir $@) yields the sub-goal @@ -XXX,XX +XXX,XX @@ subdir-slirp: slirp/all $(filter %/all, $(TARGET_DIRS_RULES)): libqemuutil.a $(common-obj-y) \ $(qom-obj-y) +$(filter %/fuzz, $(TARGET_DIRS_RULES)): libqemuutil.a $(common-obj-y) \ + $(qom-obj-y) $(crypto-user-obj-$(CONFIG_USER_ONLY)) + ROM_DIRS = $(addprefix pc-bios/, $(ROMS)) ROM_DIRS_RULES=$(foreach t, all clean, $(addsuffix /$(t), $(ROM_DIRS))) # Only keep -O and -g cflags @@ -XXX,XX +XXX,XX @@ $(ROM_DIRS_RULES): .PHONY: recurse-all recurse-clean recurse-install recurse-all: $(addsuffix /all, $(TARGET_DIRS) $(ROM_DIRS)) +recurse-fuzz: $(addsuffix /fuzz, $(TARGET_DIRS) $(ROM_DIRS)) recurse-clean: $(addsuffix /clean, $(TARGET_DIRS) $(ROM_DIRS)) recurse-install: $(addsuffix /install, $(TARGET_DIRS)) $(addsuffix /install, $(TARGET_DIRS)): all diff --git a/Makefile.target b/Makefile.target index XXXXXXX..XXXXXXX 100644 --- a/Makefile.target +++ b/Makefile.target @@ -XXX,XX +XXX,XX @@ ifdef CONFIG_TRACE_SYSTEMTAP rm -f *.stp endif +ifdef CONFIG_FUZZ +include $(SRC_PATH)/tests/qtest/fuzz/Makefile.include +include $(SRC_PATH)/tests/qtest/Makefile.include + +fuzz: fuzz-vars +fuzz-vars: QEMU_CFLAGS := $(FUZZ_CFLAGS) $(QEMU_CFLAGS) +fuzz-vars: QEMU_LDFLAGS := $(FUZZ_LDFLAGS) $(QEMU_LDFLAGS) +fuzz-vars: $(QEMU_PROG_FUZZ) +dummy := $(call unnest-vars,, fuzz-obj-y) + + +$(QEMU_PROG_FUZZ): config-devices.mak $(all-obj-y) $(COMMON_LDADDS) $(fuzz-obj-y) + $(call LINK, $(filter-out %.mak, $^)) + +endif + install: all ifneq ($(PROGS),) $(call install-prog,$(PROGS),$(DESTDIR)$(bindir)) -- 2.24.1 From: Alexander Bulekov <alxndr@bu.edu> Signed-off-by: Alexander Bulekov <alxndr@bu.edu> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com> Reviewed-by: Darren Kenny <darren.kenny@oracle.com> Message-id: 20200220041118.23264-19-alxndr@bu.edu Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- configure | 39 +++++++++++++++++++++++++++++++++++++++ 1 file changed, 39 insertions(+) diff --git a/configure b/configure index XXXXXXX..XXXXXXX 100755 --- a/configure +++ b/configure @@ -XXX,XX +XXX,XX @@ debug_mutex="no" libpmem="" default_devices="yes" plugins="no" +fuzzing="no" supported_cpu="no" supported_os="no" @@ -XXX,XX +XXX,XX @@ int main(void) { return 0; } EOF } +write_c_fuzzer_skeleton() { + cat > $TMPC <<EOF +#include <stdint.h> +#include <sys/types.h> +int LLVMFuzzerTestOneInput(const uint8_t *Data, size_t Size); +int LLVMFuzzerTestOneInput(const uint8_t *Data, size_t Size) { return 0; } +EOF +} + if check_define __linux__ ; then targetos="Linux" elif check_define _WIN32 ; then @@ -XXX,XX +XXX,XX @@ for opt do ;; --disable-containers) use_containers="no" ;; + --enable-fuzzing) fuzzing=yes + ;; + --disable-fuzzing) fuzzing=no + ;; *) echo "ERROR: unknown option $opt" echo "Try '$0 --help' for more information" @@ -XXX,XX +XXX,XX @@ EOF fi fi +########################################## +# checks for fuzzer +if test "$fuzzing" = "yes" ; then + write_c_fuzzer_skeleton + if compile_prog "$CPU_CFLAGS -Werror -fsanitize=address,fuzzer" ""; then + have_fuzzer=yes + fi +fi + ########################################## # check for libpmem @@ -XXX,XX +XXX,XX @@ echo "libpmem support $libpmem" echo "libudev $libudev" echo "default devices $default_devices" echo "plugin support $plugins" +echo "fuzzing support $fuzzing" if test "$supported_cpu" = "no"; then echo @@ -XXX,XX +XXX,XX @@ fi if test "$sheepdog" = "yes" ; then echo "CONFIG_SHEEPDOG=y" >> $config_host_mak fi +if test "$fuzzing" = "yes" ; then + if test "$have_fuzzer" = "yes"; then + FUZZ_LDFLAGS=" -fsanitize=address,fuzzer" + FUZZ_CFLAGS=" -fsanitize=address,fuzzer" + CFLAGS=" -fsanitize=address,fuzzer-no-link" + else + error_exit "Your compiler doesn't support -fsanitize=address,fuzzer" + exit 1 + fi +fi if test "$plugins" = "yes" ; then echo "CONFIG_PLUGIN=y" >> $config_host_mak @@ -XXX,XX +XXX,XX @@ if test "$libudev" != "no"; then echo "CONFIG_LIBUDEV=y" >> $config_host_mak echo "LIBUDEV_LIBS=$libudev_libs" >> $config_host_mak fi +if test "$fuzzing" != "no"; then + echo "CONFIG_FUZZ=y" >> $config_host_mak + echo "FUZZ_CFLAGS=$FUZZ_CFLAGS" >> $config_host_mak + echo "FUZZ_LDFLAGS=$FUZZ_LDFLAGS" >> $config_host_mak +fi if test "$edk2_blobs" = "yes" ; then echo "DECOMPRESS_EDK2_BLOBS=y" >> $config_host_mak -- 2.24.1 From: Alexander Bulekov <alxndr@bu.edu> These three targets should simply fuzz reads/writes to a couple ioports, but they mostly serve as examples of different ways to write targets. They demonstrate using qtest and qos for fuzzing, as well as using rebooting and forking to reset state, or not resetting it at all. Signed-off-by: Alexander Bulekov <alxndr@bu.edu> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Reviewed-by: Darren Kenny <darren.kenny@oracle.com> Message-id: 20200220041118.23264-20-alxndr@bu.edu Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- tests/qtest/fuzz/Makefile.include | 3 + tests/qtest/fuzz/i440fx_fuzz.c | 193 ++++++++++++++++++++++++++++++ 2 files changed, 196 insertions(+) create mode 100644 tests/qtest/fuzz/i440fx_fuzz.c diff --git a/tests/qtest/fuzz/Makefile.include b/tests/qtest/fuzz/Makefile.include index XXXXXXX..XXXXXXX 100644 --- a/tests/qtest/fuzz/Makefile.include +++ b/tests/qtest/fuzz/Makefile.include @@ -XXX,XX +XXX,XX @@ fuzz-obj-y += tests/qtest/fuzz/fuzz.o # Fuzzer skeleton fuzz-obj-y += tests/qtest/fuzz/fork_fuzz.o fuzz-obj-y += tests/qtest/fuzz/qos_fuzz.o +# Targets +fuzz-obj-y += tests/qtest/fuzz/i440fx_fuzz.o + FUZZ_CFLAGS += -I$(SRC_PATH)/tests -I$(SRC_PATH)/tests/qtest # Linker Script to force coverage-counters into known regions which we can mark diff --git a/tests/qtest/fuzz/i440fx_fuzz.c b/tests/qtest/fuzz/i440fx_fuzz.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/tests/qtest/fuzz/i440fx_fuzz.c @@ -XXX,XX +XXX,XX @@ +/* + * I440FX Fuzzing Target + * + * Copyright Red Hat Inc., 2019 + * + * Authors: + * Alexander Bulekov <alxndr@bu.edu> + * + * This work is licensed under the terms of the GNU GPL, version 2 or later. + * See the COPYING file in the top-level directory. + */ + +#include "qemu/osdep.h" + +#include "qemu/main-loop.h" +#include "tests/qtest/libqtest.h" +#include "tests/qtest/libqos/pci.h" +#include "tests/qtest/libqos/pci-pc.h" +#include "fuzz.h" +#include "fuzz/qos_fuzz.h" +#include "fuzz/fork_fuzz.h" + + +#define I440FX_PCI_HOST_BRIDGE_CFG 0xcf8 +#define I440FX_PCI_HOST_BRIDGE_DATA 0xcfc + +/* + * the input to the fuzzing functions below is a buffer of random bytes. we + * want to convert these bytes into a sequence of qtest or qos calls. to do + * this we define some opcodes: + */ +enum action_id { + WRITEB, + WRITEW, + WRITEL, + READB, + READW, + READL, + ACTION_MAX +}; + +static void i440fx_fuzz_qtest(QTestState *s, + const unsigned char *Data, size_t Size) { + /* + * loop over the Data, breaking it up into actions. each action has an + * opcode, address offset and value + */ + typedef struct QTestFuzzAction { + uint8_t opcode; + uint8_t addr; + uint32_t value; + } QTestFuzzAction; + QTestFuzzAction a; + + while (Size >= sizeof(a)) { + /* make a copy of the action so we can normalize the values in-place */ + memcpy(&a, Data, sizeof(a)); + /* select between two i440fx Port IO addresses */ + uint16_t addr = a.addr % 2 ? I440FX_PCI_HOST_BRIDGE_CFG : + I440FX_PCI_HOST_BRIDGE_DATA; + switch (a.opcode % ACTION_MAX) { + case WRITEB: + qtest_outb(s, addr, (uint8_t)a.value); + break; + case WRITEW: + qtest_outw(s, addr, (uint16_t)a.value); + break; + case WRITEL: + qtest_outl(s, addr, (uint32_t)a.value); + break; + case READB: + qtest_inb(s, addr); + break; + case READW: + qtest_inw(s, addr); + break; + case READL: + qtest_inl(s, addr); + break; + } + /* Move to the next operation */ + Size -= sizeof(a); + Data += sizeof(a); + } + flush_events(s); +} + +static void i440fx_fuzz_qos(QTestState *s, + const unsigned char *Data, size_t Size) { + /* + * Same as i440fx_fuzz_qtest, but using QOS. devfn is incorporated into the + * value written over Port IO + */ + typedef struct QOSFuzzAction { + uint8_t opcode; + uint8_t offset; + int devfn; + uint32_t value; + } QOSFuzzAction; + + static QPCIBus *bus; + if (!bus) { + bus = qpci_new_pc(s, fuzz_qos_alloc); + } + + QOSFuzzAction a; + while (Size >= sizeof(a)) { + memcpy(&a, Data, sizeof(a)); + switch (a.opcode % ACTION_MAX) { + case WRITEB: + bus->config_writeb(bus, a.devfn, a.offset, (uint8_t)a.value); + break; + case WRITEW: + bus->config_writew(bus, a.devfn, a.offset, (uint16_t)a.value); + break; + case WRITEL: + bus->config_writel(bus, a.devfn, a.offset, (uint32_t)a.value); + break; + case READB: + bus->config_readb(bus, a.devfn, a.offset); + break; + case READW: + bus->config_readw(bus, a.devfn, a.offset); + break; + case READL: + bus->config_readl(bus, a.devfn, a.offset); + break; + } + Size -= sizeof(a); + Data += sizeof(a); + } + flush_events(s); +} + +static void i440fx_fuzz_qos_fork(QTestState *s, + const unsigned char *Data, size_t Size) { + if (fork() == 0) { + i440fx_fuzz_qos(s, Data, Size); + _Exit(0); + } else { + wait(NULL); + } +} + +static const char *i440fx_qtest_argv = TARGET_NAME " -machine accel=qtest" + "-m 0 -display none"; +static const char *i440fx_argv(FuzzTarget *t) +{ + return i440fx_qtest_argv; +} + +static void fork_init(void) +{ + counter_shm_init(); +} + +static void register_pci_fuzz_targets(void) +{ + /* Uses simple qtest commands and reboots to reset state */ + fuzz_add_target(&(FuzzTarget){ + .name = "i440fx-qtest-reboot-fuzz", + .description = "Fuzz the i440fx using raw qtest commands and" + "rebooting after each run", + .get_init_cmdline = i440fx_argv, + .fuzz = i440fx_fuzz_qtest}); + + /* Uses libqos and forks to prevent state leakage */ + fuzz_add_qos_target(&(FuzzTarget){ + .name = "i440fx-qos-fork-fuzz", + .description = "Fuzz the i440fx using raw qtest commands and" + "rebooting after each run", + .pre_vm_init = &fork_init, + .fuzz = i440fx_fuzz_qos_fork,}, + "i440FX-pcihost", + &(QOSGraphTestOptions){} + ); + + /* + * Uses libqos. Doesn't do anything to reset state. Note that if we were to + * reboot after each run, we would also have to redo the qos-related + * initialization (qos_init_path) + */ + fuzz_add_qos_target(&(FuzzTarget){ + .name = "i440fx-qos-noreset-fuzz", + .description = "Fuzz the i440fx using raw qtest commands and" + "rebooting after each run", + .fuzz = i440fx_fuzz_qos,}, + "i440FX-pcihost", + &(QOSGraphTestOptions){} + ); +} + +fuzz_target_init(register_pci_fuzz_targets); -- 2.24.1 From: Alexander Bulekov <alxndr@bu.edu> The virtio-net fuzz target feeds inputs to all three virtio-net virtqueues, and uses forking to avoid leaking state between fuzz runs. Signed-off-by: Alexander Bulekov <alxndr@bu.edu> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Reviewed-by: Darren Kenny <darren.kenny@oracle.com> Message-id: 20200220041118.23264-21-alxndr@bu.edu Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- tests/qtest/fuzz/Makefile.include | 1 + tests/qtest/fuzz/virtio_net_fuzz.c | 198 +++++++++++++++++++++++++++++ 2 files changed, 199 insertions(+) create mode 100644 tests/qtest/fuzz/virtio_net_fuzz.c diff --git a/tests/qtest/fuzz/Makefile.include b/tests/qtest/fuzz/Makefile.include index XXXXXXX..XXXXXXX 100644 --- a/tests/qtest/fuzz/Makefile.include +++ b/tests/qtest/fuzz/Makefile.include @@ -XXX,XX +XXX,XX @@ fuzz-obj-y += tests/qtest/fuzz/qos_fuzz.o # Targets fuzz-obj-y += tests/qtest/fuzz/i440fx_fuzz.o +fuzz-obj-y += tests/qtest/fuzz/virtio_net_fuzz.o FUZZ_CFLAGS += -I$(SRC_PATH)/tests -I$(SRC_PATH)/tests/qtest diff --git a/tests/qtest/fuzz/virtio_net_fuzz.c b/tests/qtest/fuzz/virtio_net_fuzz.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/tests/qtest/fuzz/virtio_net_fuzz.c @@ -XXX,XX +XXX,XX @@ +/* + * virtio-net Fuzzing Target + * + * Copyright Red Hat Inc., 2019 + * + * Authors: + * Alexander Bulekov <alxndr@bu.edu> + * + * This work is licensed under the terms of the GNU GPL, version 2 or later. + * See the COPYING file in the top-level directory. + */ + +#include "qemu/osdep.h" + +#include "standard-headers/linux/virtio_config.h" +#include "tests/qtest/libqtest.h" +#include "tests/qtest/libqos/virtio-net.h" +#include "fuzz.h" +#include "fork_fuzz.h" +#include "qos_fuzz.h" + + +#define QVIRTIO_NET_TIMEOUT_US (30 * 1000 * 1000) +#define QVIRTIO_RX_VQ 0 +#define QVIRTIO_TX_VQ 1 +#define QVIRTIO_CTRL_VQ 2 + +static int sockfds[2]; +static bool sockfds_initialized; + +static void virtio_net_fuzz_multi(QTestState *s, + const unsigned char *Data, size_t Size, bool check_used) +{ + typedef struct vq_action { + uint8_t queue; + uint8_t length; + uint8_t write; + uint8_t next; + uint8_t rx; + } vq_action; + + uint32_t free_head = 0; + + QGuestAllocator *t_alloc = fuzz_qos_alloc; + + QVirtioNet *net_if = fuzz_qos_obj; + QVirtioDevice *dev = net_if->vdev; + QVirtQueue *q; + vq_action vqa; + while (Size >= sizeof(vqa)) { + memcpy(&vqa, Data, sizeof(vqa)); + Data += sizeof(vqa); + Size -= sizeof(vqa); + + q = net_if->queues[vqa.queue % 3]; + + vqa.length = vqa.length >= Size ? Size : vqa.length; + + /* + * Only attempt to write incoming packets, when using the socket + * backend. Otherwise, always place the input on a virtqueue. + */ + if (vqa.rx && sockfds_initialized) { + write(sockfds[0], Data, vqa.length); + } else { + vqa.rx = 0; + uint64_t req_addr = guest_alloc(t_alloc, vqa.length); + /* + * If checking used ring, ensure that the fuzzer doesn't trigger + * trivial asserion failure on zero-zied buffer + */ + qtest_memwrite(s, req_addr, Data, vqa.length); + + + free_head = qvirtqueue_add(s, q, req_addr, vqa.length, + vqa.write, vqa.next); + qvirtqueue_add(s, q, req_addr, vqa.length, vqa.write , vqa.next); + qvirtqueue_kick(s, dev, q, free_head); + } + + /* Run the main loop */ + qtest_clock_step(s, 100); + flush_events(s); + + /* Wait on used descriptors */ + if (check_used && !vqa.rx) { + gint64 start_time = g_get_monotonic_time(); + /* + * normally, we could just use qvirtio_wait_used_elem, but since we + * must manually run the main-loop for all the bhs to run, we use + * this hack with flush_events(), to run the main_loop + */ + while (!vqa.rx && q != net_if->queues[QVIRTIO_RX_VQ]) { + uint32_t got_desc_idx; + /* Input led to a virtio_error */ + if (dev->bus->get_status(dev) & VIRTIO_CONFIG_S_NEEDS_RESET) { + break; + } + if (dev->bus->get_queue_isr_status(dev, q) && + qvirtqueue_get_buf(s, q, &got_desc_idx, NULL)) { + g_assert_cmpint(got_desc_idx, ==, free_head); + break; + } + g_assert(g_get_monotonic_time() - start_time + <= QVIRTIO_NET_TIMEOUT_US); + + /* Run the main loop */ + qtest_clock_step(s, 100); + flush_events(s); + } + } + Data += vqa.length; + Size -= vqa.length; + } +} + +static void virtio_net_fork_fuzz(QTestState *s, + const unsigned char *Data, size_t Size) +{ + if (fork() == 0) { + virtio_net_fuzz_multi(s, Data, Size, false); + flush_events(s); + _Exit(0); + } else { + wait(NULL); + } +} + +static void virtio_net_fork_fuzz_check_used(QTestState *s, + const unsigned char *Data, size_t Size) +{ + if (fork() == 0) { + virtio_net_fuzz_multi(s, Data, Size, true); + flush_events(s); + _Exit(0); + } else { + wait(NULL); + } +} + +static void virtio_net_pre_fuzz(QTestState *s) +{ + qos_init_path(s); + counter_shm_init(); +} + +static void *virtio_net_test_setup_socket(GString *cmd_line, void *arg) +{ + int ret = socketpair(PF_UNIX, SOCK_STREAM, 0, sockfds); + g_assert_cmpint(ret, !=, -1); + fcntl(sockfds[0], F_SETFL, O_NONBLOCK); + sockfds_initialized = true; + g_string_append_printf(cmd_line, " -netdev socket,fd=%d,id=hs0 ", + sockfds[1]); + return arg; +} + +static void *virtio_net_test_setup_user(GString *cmd_line, void *arg) +{ + g_string_append_printf(cmd_line, " -netdev user,id=hs0 "); + return arg; +} + +static void register_virtio_net_fuzz_targets(void) +{ + fuzz_add_qos_target(&(FuzzTarget){ + .name = "virtio-net-socket", + .description = "Fuzz the virtio-net virtual queues. Fuzz incoming " + "traffic using the socket backend", + .pre_fuzz = &virtio_net_pre_fuzz, + .fuzz = virtio_net_fork_fuzz,}, + "virtio-net", + &(QOSGraphTestOptions){.before = virtio_net_test_setup_socket} + ); + + fuzz_add_qos_target(&(FuzzTarget){ + .name = "virtio-net-socket-check-used", + .description = "Fuzz the virtio-net virtual queues. Wait for the " + "descriptors to be used. Timeout may indicate improperly handled " + "input", + .pre_fuzz = &virtio_net_pre_fuzz, + .fuzz = virtio_net_fork_fuzz_check_used,}, + "virtio-net", + &(QOSGraphTestOptions){.before = virtio_net_test_setup_socket} + ); + fuzz_add_qos_target(&(FuzzTarget){ + .name = "virtio-net-slirp", + .description = "Fuzz the virtio-net virtual queues with the slirp " + " backend. Warning: May result in network traffic emitted from the " + " process. Run in an isolated network environment.", + .pre_fuzz = &virtio_net_pre_fuzz, + .fuzz = virtio_net_fork_fuzz,}, + "virtio-net", + &(QOSGraphTestOptions){.before = virtio_net_test_setup_user} + ); +} + +fuzz_target_init(register_virtio_net_fuzz_targets); -- 2.24.1 From: Alexander Bulekov <alxndr@bu.edu> The virtio-scsi fuzz target sets up and fuzzes the available virtio-scsi queues. After an element is placed on a queue, the fuzzer can select whether to perform a kick, or continue adding elements. Signed-off-by: Alexander Bulekov <alxndr@bu.edu> Reviewed-by: Darren Kenny <darren.kenny@oracle.com> Message-id: 20200220041118.23264-22-alxndr@bu.edu Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- tests/qtest/fuzz/Makefile.include | 1 + tests/qtest/fuzz/virtio_scsi_fuzz.c | 213 ++++++++++++++++++++++++++++ 2 files changed, 214 insertions(+) create mode 100644 tests/qtest/fuzz/virtio_scsi_fuzz.c diff --git a/tests/qtest/fuzz/Makefile.include b/tests/qtest/fuzz/Makefile.include index XXXXXXX..XXXXXXX 100644 --- a/tests/qtest/fuzz/Makefile.include +++ b/tests/qtest/fuzz/Makefile.include @@ -XXX,XX +XXX,XX @@ fuzz-obj-y += tests/qtest/fuzz/qos_fuzz.o # Targets fuzz-obj-y += tests/qtest/fuzz/i440fx_fuzz.o fuzz-obj-y += tests/qtest/fuzz/virtio_net_fuzz.o +fuzz-obj-y += tests/qtest/fuzz/virtio_scsi_fuzz.o FUZZ_CFLAGS += -I$(SRC_PATH)/tests -I$(SRC_PATH)/tests/qtest diff --git a/tests/qtest/fuzz/virtio_scsi_fuzz.c b/tests/qtest/fuzz/virtio_scsi_fuzz.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/tests/qtest/fuzz/virtio_scsi_fuzz.c @@ -XXX,XX +XXX,XX @@ +/* + * virtio-serial Fuzzing Target + * + * Copyright Red Hat Inc., 2019 + * + * Authors: + * Alexander Bulekov <alxndr@bu.edu> + * + * This work is licensed under the terms of the GNU GPL, version 2 or later. + * See the COPYING file in the top-level directory. + */ + +#include "qemu/osdep.h" + +#include "tests/qtest/libqtest.h" +#include "libqos/virtio-scsi.h" +#include "libqos/virtio.h" +#include "libqos/virtio-pci.h" +#include "standard-headers/linux/virtio_ids.h" +#include "standard-headers/linux/virtio_pci.h" +#include "standard-headers/linux/virtio_scsi.h" +#include "fuzz.h" +#include "fork_fuzz.h" +#include "qos_fuzz.h" + +#define PCI_SLOT 0x02 +#define PCI_FN 0x00 +#define QVIRTIO_SCSI_TIMEOUT_US (1 * 1000 * 1000) + +#define MAX_NUM_QUEUES 64 + +/* Based on tests/virtio-scsi-test.c */ +typedef struct { + int num_queues; + QVirtQueue *vq[MAX_NUM_QUEUES + 2]; +} QVirtioSCSIQueues; + +static QVirtioSCSIQueues *qvirtio_scsi_init(QVirtioDevice *dev, uint64_t mask) +{ + QVirtioSCSIQueues *vs; + uint64_t feat; + int i; + + vs = g_new0(QVirtioSCSIQueues, 1); + + feat = qvirtio_get_features(dev); + if (mask) { + feat &= ~QVIRTIO_F_BAD_FEATURE | mask; + } else { + feat &= ~(QVIRTIO_F_BAD_FEATURE | (1ull << VIRTIO_RING_F_EVENT_IDX)); + } + qvirtio_set_features(dev, feat); + + vs->num_queues = qvirtio_config_readl(dev, 0); + + for (i = 0; i < vs->num_queues + 2; i++) { + vs->vq[i] = qvirtqueue_setup(dev, fuzz_qos_alloc, i); + } + + qvirtio_set_driver_ok(dev); + + return vs; +} + +static void virtio_scsi_fuzz(QTestState *s, QVirtioSCSIQueues* queues, + const unsigned char *Data, size_t Size) +{ + /* + * Data is a sequence of random bytes. We split them up into "actions", + * followed by data: + * [vqa][dddddddd][vqa][dddd][vqa][dddddddddddd] ... + * The length of the data is specified by the preceding vqa.length + */ + typedef struct vq_action { + uint8_t queue; + uint8_t length; + uint8_t write; + uint8_t next; + uint8_t kick; + } vq_action; + + /* Keep track of the free head for each queue we interact with */ + bool vq_touched[MAX_NUM_QUEUES + 2] = {0}; + uint32_t free_head[MAX_NUM_QUEUES + 2]; + + QGuestAllocator *t_alloc = fuzz_qos_alloc; + + QVirtioSCSI *scsi = fuzz_qos_obj; + QVirtioDevice *dev = scsi->vdev; + QVirtQueue *q; + vq_action vqa; + while (Size >= sizeof(vqa)) { + /* Copy the action, so we can normalize length, queue and flags */ + memcpy(&vqa, Data, sizeof(vqa)); + + Data += sizeof(vqa); + Size -= sizeof(vqa); + + vqa.queue = vqa.queue % queues->num_queues; + /* Cap length at the number of remaining bytes in data */ + vqa.length = vqa.length >= Size ? Size : vqa.length; + vqa.write = vqa.write & 1; + vqa.next = vqa.next & 1; + vqa.kick = vqa.kick & 1; + + + q = queues->vq[vqa.queue]; + + /* Copy the data into ram, and place it on the virtqueue */ + uint64_t req_addr = guest_alloc(t_alloc, vqa.length); + qtest_memwrite(s, req_addr, Data, vqa.length); + if (vq_touched[vqa.queue] == 0) { + vq_touched[vqa.queue] = 1; + free_head[vqa.queue] = qvirtqueue_add(s, q, req_addr, vqa.length, + vqa.write, vqa.next); + } else { + qvirtqueue_add(s, q, req_addr, vqa.length, vqa.write , vqa.next); + } + + if (vqa.kick) { + qvirtqueue_kick(s, dev, q, free_head[vqa.queue]); + free_head[vqa.queue] = 0; + } + Data += vqa.length; + Size -= vqa.length; + } + /* In the end, kick each queue we interacted with */ + for (int i = 0; i < MAX_NUM_QUEUES + 2; i++) { + if (vq_touched[i]) { + qvirtqueue_kick(s, dev, queues->vq[i], free_head[i]); + } + } +} + +static void virtio_scsi_fork_fuzz(QTestState *s, + const unsigned char *Data, size_t Size) +{ + QVirtioSCSI *scsi = fuzz_qos_obj; + static QVirtioSCSIQueues *queues; + if (!queues) { + queues = qvirtio_scsi_init(scsi->vdev, 0); + } + if (fork() == 0) { + virtio_scsi_fuzz(s, queues, Data, Size); + flush_events(s); + _Exit(0); + } else { + wait(NULL); + } +} + +static void virtio_scsi_with_flag_fuzz(QTestState *s, + const unsigned char *Data, size_t Size) +{ + QVirtioSCSI *scsi = fuzz_qos_obj; + static QVirtioSCSIQueues *queues; + + if (fork() == 0) { + if (Size >= sizeof(uint64_t)) { + queues = qvirtio_scsi_init(scsi->vdev, *(uint64_t *)Data); + virtio_scsi_fuzz(s, queues, + Data + sizeof(uint64_t), Size - sizeof(uint64_t)); + flush_events(s); + } + _Exit(0); + } else { + wait(NULL); + } +} + +static void virtio_scsi_pre_fuzz(QTestState *s) +{ + qos_init_path(s); + counter_shm_init(); +} + +static void *virtio_scsi_test_setup(GString *cmd_line, void *arg) +{ + g_string_append(cmd_line, + " -drive file=blkdebug::null-co://," + "file.image.read-zeroes=on," + "if=none,id=dr1,format=raw,file.align=4k " + "-device scsi-hd,drive=dr1,lun=0,scsi-id=1"); + return arg; +} + + +static void register_virtio_scsi_fuzz_targets(void) +{ + fuzz_add_qos_target(&(FuzzTarget){ + .name = "virtio-scsi-fuzz", + .description = "Fuzz the virtio-scsi virtual queues, forking" + "for each fuzz run", + .pre_vm_init = &counter_shm_init, + .pre_fuzz = &virtio_scsi_pre_fuzz, + .fuzz = virtio_scsi_fork_fuzz,}, + "virtio-scsi", + &(QOSGraphTestOptions){.before = virtio_scsi_test_setup} + ); + + fuzz_add_qos_target(&(FuzzTarget){ + .name = "virtio-scsi-flags-fuzz", + .description = "Fuzz the virtio-scsi virtual queues, forking" + "for each fuzz run (also fuzzes the virtio flags)", + .pre_vm_init = &counter_shm_init, + .pre_fuzz = &virtio_scsi_pre_fuzz, + .fuzz = virtio_scsi_with_flag_fuzz,}, + "virtio-scsi", + &(QOSGraphTestOptions){.before = virtio_scsi_test_setup} + ); +} + +fuzz_target_init(register_virtio_scsi_fuzz_targets); -- 2.24.1 From: Alexander Bulekov <alxndr@bu.edu> Signed-off-by: Alexander Bulekov <alxndr@bu.edu> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Reviewed-by: Darren Kenny <darren.kenny@oracle.com> Message-id: 20200220041118.23264-23-alxndr@bu.edu Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- docs/devel/fuzzing.txt | 116 +++++++++++++++++++++++++++++++++++++++++ 1 file changed, 116 insertions(+) create mode 100644 docs/devel/fuzzing.txt diff --git a/docs/devel/fuzzing.txt b/docs/devel/fuzzing.txt new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/docs/devel/fuzzing.txt @@ -XXX,XX +XXX,XX @@ += Fuzzing = + +== Introduction == + +This document describes the virtual-device fuzzing infrastructure in QEMU and +how to use it to implement additional fuzzers. + +== Basics == + +Fuzzing operates by passing inputs to an entry point/target function. The +fuzzer tracks the code coverage triggered by the input. Based on these +findings, the fuzzer mutates the input and repeats the fuzzing. + +To fuzz QEMU, we rely on libfuzzer. Unlike other fuzzers such as AFL, libfuzzer +is an _in-process_ fuzzer. For the developer, this means that it is their +responsibility to ensure that state is reset between fuzzing-runs. + +== Building the fuzzers == + +NOTE: If possible, build a 32-bit binary. When forking, the 32-bit fuzzer is +much faster, since the page-map has a smaller size. This is due to the fact that +AddressSanitizer mmaps ~20TB of memory, as part of its detection. This results +in a large page-map, and a much slower fork(). + +To build the fuzzers, install a recent version of clang: +Configure with (substitute the clang binaries with the version you installed): + + CC=clang-8 CXX=clang++-8 /path/to/configure --enable-fuzzing + +Fuzz targets are built similarly to system/softmmu: + + make i386-softmmu/fuzz + +This builds ./i386-softmmu/qemu-fuzz-i386 + +The first option to this command is: --fuzz_taget=FUZZ_NAME +To list all of the available fuzzers run qemu-fuzz-i386 with no arguments. + +eg: + ./i386-softmmu/qemu-fuzz-i386 --fuzz-target=virtio-net-fork-fuzz + +Internally, libfuzzer parses all arguments that do not begin with "--". +Information about these is available by passing -help=1 + +Now the only thing left to do is wait for the fuzzer to trigger potential +crashes. + +== Adding a new fuzzer == +Coverage over virtual devices can be improved by adding additional fuzzers. +Fuzzers are kept in tests/qtest/fuzz/ and should be added to +tests/qtest/fuzz/Makefile.include + +Fuzzers can rely on both qtest and libqos to communicate with virtual devices. + +1. Create a new source file. For example ``tests/qtest/fuzz/foo-device-fuzz.c``. + +2. Write the fuzzing code using the libqtest/libqos API. See existing fuzzers +for reference. + +3. Register the fuzzer in ``tests/fuzz/Makefile.include`` by appending the +corresponding object to fuzz-obj-y + +Fuzzers can be more-or-less thought of as special qtest programs which can +modify the qtest commands and/or qtest command arguments based on inputs +provided by libfuzzer. Libfuzzer passes a byte array and length. Commonly the +fuzzer loops over the byte-array interpreting it as a list of qtest commands, +addresses, or values. + += Implementation Details = + +== The Fuzzer's Lifecycle == + +The fuzzer has two entrypoints that libfuzzer calls. libfuzzer provides it's +own main(), which performs some setup, and calls the entrypoints: + +LLVMFuzzerInitialize: called prior to fuzzing. Used to initialize all of the +necessary state + +LLVMFuzzerTestOneInput: called for each fuzzing run. Processes the input and +resets the state at the end of each run. + +In more detail: + +LLVMFuzzerInitialize parses the arguments to the fuzzer (must start with two +dashes, so they are ignored by libfuzzer main()). Currently, the arguments +select the fuzz target. Then, the qtest client is initialized. If the target +requires qos, qgraph is set up and the QOM/LIBQOS modules are initialized. +Then the QGraph is walked and the QEMU cmd_line is determined and saved. + +After this, the vl.c:qemu__main is called to set up the guest. There are +target-specific hooks that can be called before and after qemu_main, for +additional setup(e.g. PCI setup, or VM snapshotting). + +LLVMFuzzerTestOneInput: Uses qtest/qos functions to act based on the fuzz +input. It is also responsible for manually calling the main loop/main_loop_wait +to ensure that bottom halves are executed and any cleanup required before the +next input. + +Since the same process is reused for many fuzzing runs, QEMU state needs to +be reset at the end of each run. There are currently two implemented +options for resetting state: +1. Reboot the guest between runs. + Pros: Straightforward and fast for simple fuzz targets. + Cons: Depending on the device, does not reset all device state. If the + device requires some initialization prior to being ready for fuzzing + (common for QOS-based targets), this initialization needs to be done after + each reboot. + Example target: i440fx-qtest-reboot-fuzz +2. Run each test case in a separate forked process and copy the coverage + information back to the parent. This is fairly similar to AFL's "deferred" + fork-server mode [3] + Pros: Relatively fast. Devices only need to be initialized once. No need + to do slow reboots or vmloads. + Cons: Not officially supported by libfuzzer. Does not work well for devices + that rely on dedicated threads. + Example target: virtio-net-fork-fuzz -- 2.24.1 The following changes since commit 1214d55d1c41fbab3a9973a05085b8760647e411: Merge remote-tracking branch 'remotes/nvme/tags/nvme-next-pull-request' into staging (2021-02-09 13:24:37 +0000) are available in the Git repository at: https://gitlab.com/stefanha/qemu.git tags/block-pull-request for you to fetch changes up to eb847c42296497978942f738cd41dc29a35a49b2: docs: fix Parallels Image "dirty bitmap" section (2021-02-10 09:23:28 +0000) ---------------------------------------------------------------- Pull request v4: * Add PCI_EXPRESS Kconfig dependency to fix s390x in "multi-process: setup PCI host bridge for remote device" [Philippe and Thomas] ---------------------------------------------------------------- Denis V. Lunev (1): docs: fix Parallels Image "dirty bitmap" section Elena Ufimtseva (8): multi-process: add configure and usage information io: add qio_channel_writev_full_all helper io: add qio_channel_readv_full_all_eof & qio_channel_readv_full_all helpers multi-process: define MPQemuMsg format and transmission functions multi-process: introduce proxy object multi-process: add proxy communication functions multi-process: Forward PCI config space acceses to the remote process multi-process: perform device reset in the remote process Jagannathan Raman (11): memory: alloc RAM from file at offset multi-process: Add config option for multi-process QEMU multi-process: setup PCI host bridge for remote device multi-process: setup a machine object for remote device process multi-process: Initialize message handler in remote device multi-process: Associate fd of a PCIDevice with its object multi-process: setup memory manager for remote device multi-process: PCI BAR read/write handling for proxy & remote endpoints multi-process: Synchronize remote memory multi-process: create IOHUB object to handle irq multi-process: Retrieve PCI info from remote process John G Johnson (1): multi-process: add the concept description to docs/devel/qemu-multiprocess Stefan Hajnoczi (6): .github: point Repo Lockdown bot to GitLab repo gitmodules: use GitLab repos instead of qemu.org gitlab-ci: remove redundant GitLab repo URL command docs: update README to use GitLab repo URLs pc-bios: update mirror URLs to GitLab get_maintainer: update repo URL to GitLab MAINTAINERS | 24 + README.rst | 4 +- docs/devel/index.rst | 1 + docs/devel/multi-process.rst | 966 ++++++++++++++++++++++ docs/system/index.rst | 1 + docs/system/multi-process.rst | 64 ++ docs/interop/parallels.txt | 2 +- configure | 10 + meson.build | 5 +- hw/remote/trace.h | 1 + include/exec/memory.h | 2 + include/exec/ram_addr.h | 4 +- include/hw/pci-host/remote.h | 30 + include/hw/pci/pci_ids.h | 3 + include/hw/remote/iohub.h | 42 + include/hw/remote/machine.h | 38 + include/hw/remote/memory.h | 19 + include/hw/remote/mpqemu-link.h | 99 +++ include/hw/remote/proxy-memory-listener.h | 28 + include/hw/remote/proxy.h | 48 ++ include/io/channel.h | 78 ++ include/qemu/mmap-alloc.h | 4 +- include/sysemu/iothread.h | 6 + backends/hostmem-memfd.c | 2 +- hw/misc/ivshmem.c | 3 +- hw/pci-host/remote.c | 75 ++ hw/remote/iohub.c | 119 +++ hw/remote/machine.c | 80 ++ hw/remote/memory.c | 65 ++ hw/remote/message.c | 230 ++++++ hw/remote/mpqemu-link.c | 267 ++++++ hw/remote/proxy-memory-listener.c | 227 +++++ hw/remote/proxy.c | 379 +++++++++ hw/remote/remote-obj.c | 203 +++++ io/channel.c | 116 ++- iothread.c | 6 + softmmu/memory.c | 3 +- softmmu/physmem.c | 12 +- util/mmap-alloc.c | 8 +- util/oslib-posix.c | 2 +- .github/lockdown.yml | 8 +- .gitlab-ci.yml | 1 - .gitmodules | 44 +- Kconfig.host | 4 + hw/Kconfig | 1 + hw/meson.build | 1 + hw/pci-host/Kconfig | 3 + hw/pci-host/meson.build | 1 + hw/remote/Kconfig | 4 + hw/remote/meson.build | 13 + hw/remote/trace-events | 4 + pc-bios/README | 4 +- scripts/get_maintainer.pl | 2 +- 53 files changed, 3296 insertions(+), 70 deletions(-) create mode 100644 docs/devel/multi-process.rst create mode 100644 docs/system/multi-process.rst create mode 100644 hw/remote/trace.h create mode 100644 include/hw/pci-host/remote.h create mode 100644 include/hw/remote/iohub.h create mode 100644 include/hw/remote/machine.h create mode 100644 include/hw/remote/memory.h create mode 100644 include/hw/remote/mpqemu-link.h create mode 100644 include/hw/remote/proxy-memory-listener.h create mode 100644 include/hw/remote/proxy.h create mode 100644 hw/pci-host/remote.c create mode 100644 hw/remote/iohub.c create mode 100644 hw/remote/machine.c create mode 100644 hw/remote/memory.c create mode 100644 hw/remote/message.c create mode 100644 hw/remote/mpqemu-link.c create mode 100644 hw/remote/proxy-memory-listener.c create mode 100644 hw/remote/proxy.c create mode 100644 hw/remote/remote-obj.c create mode 100644 hw/remote/Kconfig create mode 100644 hw/remote/meson.build create mode 100644 hw/remote/trace-events -- 2.29.2 Use the GitLab repo URL as the main repo location in order to reduce load on qemu.org. Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> Reviewed-by: Wainer dos Santos Moschetta <wainersm@redhat.com> Reviewed-by: Thomas Huth <thuth@redhat.com> Message-id: 20210111115017.156802-2-stefanha@redhat.com Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- .github/lockdown.yml | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/.github/lockdown.yml b/.github/lockdown.yml index XXXXXXX..XXXXXXX 100644 --- a/.github/lockdown.yml +++ b/.github/lockdown.yml @@ -XXX,XX +XXX,XX @@ issues: comment: | Thank you for your interest in the QEMU project. - This repository is a read-only mirror of the project's master - repostories hosted on https://git.qemu.org/git/qemu.git. + This repository is a read-only mirror of the project's repostories hosted + at https://gitlab.com/qemu-project/qemu.git. The project does not process issues filed on GitHub. The project issues are tracked on Launchpad: @@ -XXX,XX +XXX,XX @@ pulls: comment: | Thank you for your interest in the QEMU project. - This repository is a read-only mirror of the project's master - repostories hosted on https://git.qemu.org/git/qemu.git. + This repository is a read-only mirror of the project's repostories hosted + on https://gitlab.com/qemu-project/qemu.git. The project does not process merge requests filed on GitHub. QEMU welcomes contributions of code (either fixing bugs or adding new -- 2.29.2 qemu.org is running out of bandwidth and the QEMU project is moving towards a gating CI on GitLab. Use the GitLab repos instead of qemu.org (they will become mirrors). Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> Reviewed-by: Wainer dos Santos Moschetta <wainersm@redhat.com> Reviewed-by: Thomas Huth <thuth@redhat.com> Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com> Message-id: 20210111115017.156802-3-stefanha@redhat.com Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- .gitmodules | 44 ++++++++++++++++++++++---------------------- 1 file changed, 22 insertions(+), 22 deletions(-) diff --git a/.gitmodules b/.gitmodules index XXXXXXX..XXXXXXX 100644 --- a/.gitmodules +++ b/.gitmodules @@ -XXX,XX +XXX,XX @@ [submodule "roms/seabios"] path = roms/seabios - url = https://git.qemu.org/git/seabios.git/ + url = https://gitlab.com/qemu-project/seabios.git/ [submodule "roms/SLOF"] path = roms/SLOF - url = https://git.qemu.org/git/SLOF.git + url = https://gitlab.com/qemu-project/SLOF.git [submodule "roms/ipxe"] path = roms/ipxe - url = https://git.qemu.org/git/ipxe.git + url = https://gitlab.com/qemu-project/ipxe.git [submodule "roms/openbios"] path = roms/openbios - url = https://git.qemu.org/git/openbios.git + url = https://gitlab.com/qemu-project/openbios.git [submodule "roms/qemu-palcode"] path = roms/qemu-palcode - url = https://git.qemu.org/git/qemu-palcode.git + url = https://gitlab.com/qemu-project/qemu-palcode.git [submodule "roms/sgabios"] path = roms/sgabios - url = https://git.qemu.org/git/sgabios.git + url = https://gitlab.com/qemu-project/sgabios.git [submodule "dtc"] path = dtc - url = https://git.qemu.org/git/dtc.git + url = https://gitlab.com/qemu-project/dtc.git [submodule "roms/u-boot"] path = roms/u-boot - url = https://git.qemu.org/git/u-boot.git + url = https://gitlab.com/qemu-project/u-boot.git [submodule "roms/skiboot"] path = roms/skiboot - url = https://git.qemu.org/git/skiboot.git + url = https://gitlab.com/qemu-project/skiboot.git [submodule "roms/QemuMacDrivers"] path = roms/QemuMacDrivers - url = https://git.qemu.org/git/QemuMacDrivers.git + url = https://gitlab.com/qemu-project/QemuMacDrivers.git [submodule "ui/keycodemapdb"] path = ui/keycodemapdb - url = https://git.qemu.org/git/keycodemapdb.git + url = https://gitlab.com/qemu-project/keycodemapdb.git [submodule "capstone"] path = capstone - url = https://git.qemu.org/git/capstone.git + url = https://gitlab.com/qemu-project/capstone.git [submodule "roms/seabios-hppa"] path = roms/seabios-hppa - url = https://git.qemu.org/git/seabios-hppa.git + url = https://gitlab.com/qemu-project/seabios-hppa.git [submodule "roms/u-boot-sam460ex"] path = roms/u-boot-sam460ex - url = https://git.qemu.org/git/u-boot-sam460ex.git + url = https://gitlab.com/qemu-project/u-boot-sam460ex.git [submodule "tests/fp/berkeley-testfloat-3"] path = tests/fp/berkeley-testfloat-3 - url = https://git.qemu.org/git/berkeley-testfloat-3.git + url = https://gitlab.com/qemu-project/berkeley-testfloat-3.git [submodule "tests/fp/berkeley-softfloat-3"] path = tests/fp/berkeley-softfloat-3 - url = https://git.qemu.org/git/berkeley-softfloat-3.git + url = https://gitlab.com/qemu-project/berkeley-softfloat-3.git [submodule "roms/edk2"] path = roms/edk2 - url = https://git.qemu.org/git/edk2.git + url = https://gitlab.com/qemu-project/edk2.git [submodule "slirp"] path = slirp - url = https://git.qemu.org/git/libslirp.git + url = https://gitlab.com/qemu-project/libslirp.git [submodule "roms/opensbi"] path = roms/opensbi - url = https://git.qemu.org/git/opensbi.git + url = https://gitlab.com/qemu-project/opensbi.git [submodule "roms/qboot"] path = roms/qboot - url = https://git.qemu.org/git/qboot.git + url = https://gitlab.com/qemu-project/qboot.git [submodule "meson"] path = meson - url = https://git.qemu.org/git/meson.git + url = https://gitlab.com/qemu-project/meson.git [submodule "roms/vbootrom"] path = roms/vbootrom - url = https://git.qemu.org/git/vbootrom.git + url = https://gitlab.com/qemu-project/vbootrom.git -- 2.29.2 It is no longer necessary to point .gitmodules at GitLab repos when running in GitLab CI since they are now used all the time. Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> Reviewed-by: Wainer dos Santos Moschetta <wainersm@redhat.com> Reviewed-by: Thomas Huth <thuth@redhat.com> Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com> Message-id: 20210111115017.156802-4-stefanha@redhat.com Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- .gitlab-ci.yml | 1 - 1 file changed, 1 deletion(-) diff --git a/.gitlab-ci.yml b/.gitlab-ci.yml index XXXXXXX..XXXXXXX 100644 --- a/.gitlab-ci.yml +++ b/.gitlab-ci.yml @@ -XXX,XX +XXX,XX @@ include: image: $CI_REGISTRY_IMAGE/qemu/$IMAGE:latest before_script: - JOBS=$(expr $(nproc) + 1) - - sed -i s,git.qemu.org/git,gitlab.com/qemu-project, .gitmodules script: - mkdir build - cd build -- 2.29.2 qemu.org is running out of bandwidth and the QEMU project is moving towards a gating CI on GitLab. Use the GitLab repos instead of qemu.org (they will become mirrors). Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> Reviewed-by: Wainer dos Santos Moschetta <wainersm@redhat.com> Reviewed-by: Thomas Huth <thuth@redhat.com> Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com> Message-id: 20210111115017.156802-5-stefanha@redhat.com Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- README.rst | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/README.rst b/README.rst index XXXXXXX..XXXXXXX 100644 --- a/README.rst +++ b/README.rst @@ -XXX,XX +XXX,XX @@ The QEMU source code is maintained under the GIT version control system. .. code-block:: shell - git clone https://git.qemu.org/git/qemu.git + git clone https://gitlab.com/qemu-project/qemu.git When submitting patches, one common approach is to use 'git format-patch' and/or 'git send-email' to format & send the mail to the @@ -XXX,XX +XXX,XX @@ The QEMU website is also maintained under source control. .. code-block:: shell - git clone https://git.qemu.org/git/qemu-web.git + git clone https://gitlab.com/qemu-project/qemu-web.git * `<https://www.qemu.org/2017/02/04/the-new-qemu-website-is-up/>`_ -- 2.29.2 qemu.org is running out of bandwidth and the QEMU project is moving towards a gating CI on GitLab. Use the GitLab repos instead of qemu.org (they will become mirrors). Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> Reviewed-by: Wainer dos Santos Moschetta <wainersm@redhat.com> Reviewed-by: Thomas Huth <thuth@redhat.com> Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com> Message-id: 20210111115017.156802-6-stefanha@redhat.com Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- pc-bios/README | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/pc-bios/README b/pc-bios/README index XXXXXXX..XXXXXXX 100644 --- a/pc-bios/README +++ b/pc-bios/README @@ -XXX,XX +XXX,XX @@ legacy x86 software to communicate with an attached serial console as if a video card were attached. The master sources reside in a subversion repository at http://sgabios.googlecode.com/svn/trunk. A git mirror is - available at https://git.qemu.org/git/sgabios.git. + available at https://gitlab.com/qemu-project/sgabios.git. - The PXE roms come from the iPXE project. Built with BANNER_TIME 0. Sources available at http://ipxe.org. Vendor:Device ID -> ROM mapping: @@ -XXX,XX +XXX,XX @@ - The u-boot binary for e500 comes from the upstream denx u-boot project where it was compiled using the qemu-ppce500 target. - A git mirror is available at: https://git.qemu.org/git/u-boot.git + A git mirror is available at: https://gitlab.com/qemu-project/u-boot.git The hash used to compile the current version is: 2072e72 - Skiboot (https://github.com/open-power/skiboot/) is an OPAL -- 2.29.2 qemu.org is running out of bandwidth and the QEMU project is moving towards a gating CI on GitLab. Use the GitLab repos instead of qemu.org (they will become mirrors). Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> Reviewed-by: Wainer dos Santos Moschetta <wainersm@redhat.com> Reviewed-by: Thomas Huth <thuth@redhat.com> Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com> Message-id: 20210111115017.156802-7-stefanha@redhat.com Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- scripts/get_maintainer.pl | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/scripts/get_maintainer.pl b/scripts/get_maintainer.pl index XXXXXXX..XXXXXXX 100755 --- a/scripts/get_maintainer.pl +++ b/scripts/get_maintainer.pl @@ -XXX,XX +XXX,XX @@ sub vcs_exists { warn("$P: No supported VCS found. Add --nogit to options?\n"); warn("Using a git repository produces better results.\n"); warn("Try latest git repository using:\n"); - warn("git clone https://git.qemu.org/git/qemu.git\n"); + warn("git clone https://gitlab.com/qemu-project/qemu.git\n"); $printed_novcs = 1; } return 0; -- 2.29.2 From: John G Johnson <john.g.johnson@oracle.com> Signed-off-by: John G Johnson <john.g.johnson@oracle.com> Signed-off-by: Elena Ufimtseva <elena.ufimtseva@oracle.com> Signed-off-by: Jagannathan Raman <jag.raman@oracle.com> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Message-id: 02a68adef99f5df6a380bf8fd7b90948777e411c.1611938319.git.jag.raman@oracle.com Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- MAINTAINERS | 7 + docs/devel/index.rst | 1 + docs/devel/multi-process.rst | 966 +++++++++++++++++++++++++++++++++++ 3 files changed, 974 insertions(+) create mode 100644 docs/devel/multi-process.rst diff --git a/MAINTAINERS b/MAINTAINERS index XXXXXXX..XXXXXXX 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -XXX,XX +XXX,XX @@ S: Maintained F: hw/semihosting/ F: include/hw/semihosting/ +Multi-process QEMU +M: Elena Ufimtseva <elena.ufimtseva@oracle.com> +M: Jagannathan Raman <jag.raman@oracle.com> +M: John G Johnson <john.g.johnson@oracle.com> +S: Maintained +F: docs/devel/multi-process.rst + Build and test automation ------------------------- Build and test automation diff --git a/docs/devel/index.rst b/docs/devel/index.rst index XXXXXXX..XXXXXXX 100644 --- a/docs/devel/index.rst +++ b/docs/devel/index.rst @@ -XXX,XX +XXX,XX @@ Contents: clocks qom block-coroutine-wrapper + multi-process diff --git a/docs/devel/multi-process.rst b/docs/devel/multi-process.rst new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/docs/devel/multi-process.rst @@ -XXX,XX +XXX,XX @@ +This is the design document for multi-process QEMU. It does not +necessarily reflect the status of the current implementation, which +may lack features or be considerably different from what is described +in this document. This document is still useful as a description of +the goals and general direction of this feature. + +Please refer to the following wiki for latest details: +https://wiki.qemu.org/Features/MultiProcessQEMU + +Multi-process QEMU +=================== + +QEMU is often used as the hypervisor for virtual machines running in the +Oracle cloud. Since one of the advantages of cloud computing is the +ability to run many VMs from different tenants in the same cloud +infrastructure, a guest that compromised its hypervisor could +potentially use the hypervisor's access privileges to access data it is +not authorized for. + +QEMU can be susceptible to security attacks because it is a large, +monolithic program that provides many features to the VMs it services. +Many of these features can be configured out of QEMU, but even a reduced +configuration QEMU has a large amount of code a guest can potentially +attack. Separating QEMU reduces the attack surface by aiding to +limit each component in the system to only access the resources that +it needs to perform its job. + +QEMU services +------------- + +QEMU can be broadly described as providing three main services. One is a +VM control point, where VMs can be created, migrated, re-configured, and +destroyed. A second is to emulate the CPU instructions within the VM, +often accelerated by HW virtualization features such as Intel's VT +extensions. Finally, it provides IO services to the VM by emulating HW +IO devices, such as disk and network devices. + +A multi-process QEMU +~~~~~~~~~~~~~~~~~~~~ + +A multi-process QEMU involves separating QEMU services into separate +host processes. Each of these processes can be given only the privileges +it needs to provide its service, e.g., a disk service could be given +access only to the disk images it provides, and not be allowed to +access other files, or any network devices. An attacker who compromised +this service would not be able to use this exploit to access files or +devices beyond what the disk service was given access to. + +A QEMU control process would remain, but in multi-process mode, will +have no direct interfaces to the VM. During VM execution, it would still +provide the user interface to hot-plug devices or live migrate the VM. + +A first step in creating a multi-process QEMU is to separate IO services +from the main QEMU program, which would continue to provide CPU +emulation. i.e., the control process would also be the CPU emulation +process. In a later phase, CPU emulation could be separated from the +control process. + +Separating IO services +---------------------- + +Separating IO services into individual host processes is a good place to +begin for a couple of reasons. One is the sheer number of IO devices QEMU +can emulate provides a large surface of interfaces which could potentially +be exploited, and, indeed, have been a source of exploits in the past. +Another is the modular nature of QEMU device emulation code provides +interface points where the QEMU functions that perform device emulation +can be separated from the QEMU functions that manage the emulation of +guest CPU instructions. The devices emulated in the separate process are +referred to as remote devices. + +QEMU device emulation +~~~~~~~~~~~~~~~~~~~~~ + +QEMU uses an object oriented SW architecture for device emulation code. +Configured objects are all compiled into the QEMU binary, then objects +are instantiated by name when used by the guest VM. For example, the +code to emulate a device named "foo" is always present in QEMU, but its +instantiation code is only run when the device is included in the target +VM. (e.g., via the QEMU command line as *-device foo*) + +The object model is hierarchical, so device emulation code names its +parent object (such as "pci-device" for a PCI device) and QEMU will +instantiate a parent object before calling the device's instantiation +code. + +Current separation models +~~~~~~~~~~~~~~~~~~~~~~~~~ + +In order to separate the device emulation code from the CPU emulation +code, the device object code must run in a different process. There are +a couple of existing QEMU features that can run emulation code +separately from the main QEMU process. These are examined below. + +vhost user model +^^^^^^^^^^^^^^^^ + +Virtio guest device drivers can be connected to vhost user applications +in order to perform their IO operations. This model uses special virtio +device drivers in the guest and vhost user device objects in QEMU, but +once the QEMU vhost user code has configured the vhost user application, +mission-mode IO is performed by the application. The vhost user +application is a daemon process that can be contacted via a known UNIX +domain socket. + +vhost socket +'''''''''''' + +As mentioned above, one of the tasks of the vhost device object within +QEMU is to contact the vhost application and send it configuration +information about this device instance. As part of the configuration +process, the application can also be sent other file descriptors over +the socket, which then can be used by the vhost user application in +various ways, some of which are described below. + +vhost MMIO store acceleration +''''''''''''''''''''''''''''' + +VMs are often run using HW virtualization features via the KVM kernel +driver. This driver allows QEMU to accelerate the emulation of guest CPU +instructions by running the guest in a virtual HW mode. When the guest +executes instructions that cannot be executed by virtual HW mode, +execution returns to the KVM driver so it can inform QEMU to emulate the +instructions in SW. + +One of the events that can cause a return to QEMU is when a guest device +driver accesses an IO location. QEMU then dispatches the memory +operation to the corresponding QEMU device object. In the case of a +vhost user device, the memory operation would need to be sent over a +socket to the vhost application. This path is accelerated by the QEMU +virtio code by setting up an eventfd file descriptor that the vhost +application can directly receive MMIO store notifications from the KVM +driver, instead of needing them to be sent to the QEMU process first. + +vhost interrupt acceleration +'''''''''''''''''''''''''''' + +Another optimization used by the vhost application is the ability to +directly inject interrupts into the VM via the KVM driver, again, +bypassing the need to send the interrupt back to the QEMU process first. +The QEMU virtio setup code configures the KVM driver with an eventfd +that triggers the device interrupt in the guest when the eventfd is +written. This irqfd file descriptor is then passed to the vhost user +application program. + +vhost access to guest memory +'''''''''''''''''''''''''''' + +The vhost application is also allowed to directly access guest memory, +instead of needing to send the data as messages to QEMU. This is also +done with file descriptors sent to the vhost user application by QEMU. +These descriptors can be passed to ``mmap()`` by the vhost application +to map the guest address space into the vhost application. + +IOMMUs introduce another level of complexity, since the address given to +the guest virtio device to DMA to or from is not a guest physical +address. This case is handled by having vhost code within QEMU register +as a listener for IOMMU mapping changes. The vhost application maintains +a cache of IOMMMU translations: sending translation requests back to +QEMU on cache misses, and in turn receiving flush requests from QEMU +when mappings are purged. + +applicability to device separation +'''''''''''''''''''''''''''''''''' + +Much of the vhost model can be re-used by separated device emulation. In +particular, the ideas of using a socket between QEMU and the device +emulation application, using a file descriptor to inject interrupts into +the VM via KVM, and allowing the application to ``mmap()`` the guest +should be re used. + +There are, however, some notable differences between how a vhost +application works and the needs of separated device emulation. The most +basic is that vhost uses custom virtio device drivers which always +trigger IO with MMIO stores. A separated device emulation model must +work with existing IO device models and guest device drivers. MMIO loads +break vhost store acceleration since they are synchronous - guest +progress cannot continue until the load has been emulated. By contrast, +stores are asynchronous, the guest can continue after the store event +has been sent to the vhost application. + +Another difference is that in the vhost user model, a single daemon can +support multiple QEMU instances. This is contrary to the security regime +desired, in which the emulation application should only be allowed to +access the files or devices the VM it's running on behalf of can access. +#### qemu-io model + +Qemu-io is a test harness used to test changes to the QEMU block backend +object code. (e.g., the code that implements disk images for disk driver +emulation) Qemu-io is not a device emulation application per se, but it +does compile the QEMU block objects into a separate binary from the main +QEMU one. This could be useful for disk device emulation, since its +emulation applications will need to include the QEMU block objects. + +New separation model based on proxy objects +------------------------------------------- + +A different model based on proxy objects in the QEMU program +communicating with remote emulation programs could provide separation +while minimizing the changes needed to the device emulation code. The +rest of this section is a discussion of how a proxy object model would +work. + +Remote emulation processes +~~~~~~~~~~~~~~~~~~~~~~~~~~ + +The remote emulation process will run the QEMU object hierarchy without +modification. The device emulation objects will be also be based on the +QEMU code, because for anything but the simplest device, it would not be +a tractable to re-implement both the object model and the many device +backends that QEMU has. + +The processes will communicate with the QEMU process over UNIX domain +sockets. The processes can be executed either as standalone processes, +or be executed by QEMU. In both cases, the host backends the emulation +processes will provide are specified on its command line, as they would +be for QEMU. For example: + +:: + + disk-proc -blockdev driver=file,node-name=file0,filename=disk-file0 \ + -blockdev driver=qcow2,node-name=drive0,file=file0 + +would indicate process *disk-proc* uses a qcow2 emulated disk named +*file0* as its backend. + +Emulation processes may emulate more than one guest controller. A common +configuration might be to put all controllers of the same device class +(e.g., disk, network, etc.) in a single process, so that all backends of +the same type can be managed by a single QMP monitor. + +communication with QEMU +^^^^^^^^^^^^^^^^^^^^^^^ + +The first argument to the remote emulation process will be a Unix domain +socket that connects with the Proxy object. This is a required argument. + +:: + + disk-proc <socket number> <backend list> + +remote process QMP monitor +^^^^^^^^^^^^^^^^^^^^^^^^^^ + +Remote emulation processes can be monitored via QMP, similar to QEMU +itself. The QMP monitor socket is specified the same as for a QEMU +process: + +:: + + disk-proc -qmp unix:/tmp/disk-mon,server + +can be monitored over the UNIX socket path */tmp/disk-mon*. + +QEMU command line +~~~~~~~~~~~~~~~~~ + +Each remote device emulated in a remote process on the host is +represented as a *-device* of type *pci-proxy-dev*. A socket +sub-option to this option specifies the Unix socket that connects +to the remote process. An *id* sub-option is required, and it should +be the same id as used in the remote process. + +:: + + qemu-system-x86_64 ... -device pci-proxy-dev,id=lsi0,socket=3 + +can be used to add a device emulated in a remote process + + +QEMU management of remote processes +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +QEMU is not aware of the type of type of the remote PCI device. It is +a pass through device as far as QEMU is concerned. + +communication with emulation process +^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ + +primary channel +''''''''''''''' + +The primary channel (referred to as com in the code) is used to bootstrap +the remote process. It is also used to pass on device-agnostic commands +like reset. + +per-device channels +''''''''''''''''''' + +Each remote device communicates with QEMU using a dedicated communication +channel. The proxy object sets up this channel using the primary +channel during its initialization. + +QEMU device proxy objects +~~~~~~~~~~~~~~~~~~~~~~~~~ + +QEMU has an object model based on sub-classes inherited from the +"object" super-class. The sub-classes that are of interest here are the +"device" and "bus" sub-classes whose child sub-classes make up the +device tree of a QEMU emulated system. + +The proxy object model will use device proxy objects to replace the +device emulation code within the QEMU process. These objects will live +in the same place in the object and bus hierarchies as the objects they +replace. i.e., the proxy object for an LSI SCSI controller will be a +sub-class of the "pci-device" class, and will have the same PCI bus +parent and the same SCSI bus child objects as the LSI controller object +it replaces. + +It is worth noting that the same proxy object is used to mediate with +all types of remote PCI devices. + +object initialization +^^^^^^^^^^^^^^^^^^^^^ + +The Proxy device objects are initialized in the exact same manner in +which any other QEMU device would be initialized. + +In addition, the Proxy objects perform the following two tasks: +- Parses the "socket" sub option and connects to the remote process +using this channel +- Uses the "id" sub-option to connect to the emulated device on the +separate process + +class\_init +''''''''''' + +The ``class_init()`` method of a proxy object will, in general behave +similarly to the object it replaces, including setting any static +properties and methods needed by the proxy. + +instance\_init / realize +'''''''''''''''''''''''' + +The ``instance_init()`` and ``realize()`` functions would only need to +perform tasks related to being a proxy, such are registering its own +MMIO handlers, or creating a child bus that other proxy devices can be +attached to later. + +Other tasks will be device-specific. For example, PCI device objects +will initialize the PCI config space in order to make a valid PCI device +tree within the QEMU process. + +address space registration +^^^^^^^^^^^^^^^^^^^^^^^^^^ + +Most devices are driven by guest device driver accesses to IO addresses +or ports. The QEMU device emulation code uses QEMU's memory region +function calls (such as ``memory_region_init_io()``) to add callback +functions that QEMU will invoke when the guest accesses the device's +areas of the IO address space. When a guest driver does access the +device, the VM will exit HW virtualization mode and return to QEMU, +which will then lookup and execute the corresponding callback function. + +A proxy object would need to mirror the memory region calls the actual +device emulator would perform in its initialization code, but with its +own callbacks. When invoked by QEMU as a result of a guest IO operation, +they will forward the operation to the device emulation process. + +PCI config space +^^^^^^^^^^^^^^^^ + +PCI devices also have a configuration space that can be accessed by the +guest driver. Guest accesses to this space is not handled by the device +emulation object, but by its PCI parent object. Much of this space is +read-only, but certain registers (especially BAR and MSI-related ones) +need to be propagated to the emulation process. + +PCI parent proxy +'''''''''''''''' + +One way to propagate guest PCI config accesses is to create a +"pci-device-proxy" class that can serve as the parent of a PCI device +proxy object. This class's parent would be "pci-device" and it would +override the PCI parent's ``config_read()`` and ``config_write()`` +methods with ones that forward these operations to the emulation +program. + +interrupt receipt +^^^^^^^^^^^^^^^^^ + +A proxy for a device that generates interrupts will need to create a +socket to receive interrupt indications from the emulation process. An +incoming interrupt indication would then be sent up to its bus parent to +be injected into the guest. For example, a PCI device object may use +``pci_set_irq()``. + +live migration +^^^^^^^^^^^^^^ + +The proxy will register to save and restore any *vmstate* it needs over +a live migration event. The device proxy does not need to manage the +remote device's *vmstate*; that will be handled by the remote process +proxy (see below). + +QEMU remote device operation +~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +Generic device operations, such as DMA, will be performed by the remote +process proxy by sending messages to the remote process. + +DMA operations +^^^^^^^^^^^^^^ + +DMA operations would be handled much like vhost applications do. One of +the initial messages sent to the emulation process is a guest memory +table. Each entry in this table consists of a file descriptor and size +that the emulation process can ``mmap()`` to directly access guest +memory, similar to ``vhost_user_set_mem_table()``. Note guest memory +must be backed by file descriptors, such as when QEMU is given the +*-mem-path* command line option. + +IOMMU operations +^^^^^^^^^^^^^^^^ + +When the emulated system includes an IOMMU, the remote process proxy in +QEMU will need to create a socket for IOMMU requests from the emulation +process. It will handle those requests with an +``address_space_get_iotlb_entry()`` call. In order to handle IOMMU +unmaps, the remote process proxy will also register as a listener on the +device's DMA address space. When an IOMMU memory region is created +within the DMA address space, an IOMMU notifier for unmaps will be added +to the memory region that will forward unmaps to the emulation process +over the IOMMU socket. + +device hot-plug via QMP +^^^^^^^^^^^^^^^^^^^^^^^ + +An QMP "device\_add" command can add a device emulated by a remote +process. It will also have "rid" option to the command, just as the +*-device* command line option does. The remote process may either be one +started at QEMU startup, or be one added by the "add-process" QMP +command described above. In either case, the remote process proxy will +forward the new device's JSON description to the corresponding emulation +process. + +live migration +^^^^^^^^^^^^^^ + +The remote process proxy will also register for live migration +notifications with ``vmstate_register()``. When called to save state, +the proxy will send the remote process a secondary socket file +descriptor to save the remote process's device *vmstate* over. The +incoming byte stream length and data will be saved as the proxy's +*vmstate*. When the proxy is resumed on its new host, this *vmstate* +will be extracted, and a secondary socket file descriptor will be sent +to the new remote process through which it receives the *vmstate* in +order to restore the devices there. + +device emulation in remote process +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +The parts of QEMU that the emulation program will need include the +object model; the memory emulation objects; the device emulation objects +of the targeted device, and any dependent devices; and, the device's +backends. It will also need code to setup the machine environment, +handle requests from the QEMU process, and route machine-level requests +(such as interrupts or IOMMU mappings) back to the QEMU process. + +initialization +^^^^^^^^^^^^^^ + +The process initialization sequence will follow the same sequence +followed by QEMU. It will first initialize the backend objects, then +device emulation objects. The JSON descriptions sent by the QEMU process +will drive which objects need to be created. + +- address spaces + +Before the device objects are created, the initial address spaces and +memory regions must be configured with ``memory_map_init()``. This +creates a RAM memory region object (*system\_memory*) and an IO memory +region object (*system\_io*). + +- RAM + +RAM memory region creation will follow how ``pc_memory_init()`` creates +them, but must use ``memory_region_init_ram_from_fd()`` instead of +``memory_region_allocate_system_memory()``. The file descriptors needed +will be supplied by the guest memory table from above. Those RAM regions +would then be added to the *system\_memory* memory region with +``memory_region_add_subregion()``. + +- PCI + +IO initialization will be driven by the JSON descriptions sent from the +QEMU process. For a PCI device, a PCI bus will need to be created with +``pci_root_bus_new()``, and a PCI memory region will need to be created +and added to the *system\_memory* memory region with +``memory_region_add_subregion_overlap()``. The overlap version is +required for architectures where PCI memory overlaps with RAM memory. + +MMIO handling +^^^^^^^^^^^^^ + +The device emulation objects will use ``memory_region_init_io()`` to +install their MMIO handlers, and ``pci_register_bar()`` to associate +those handlers with a PCI BAR, as they do within QEMU currently. + +In order to use ``address_space_rw()`` in the emulation process to +handle MMIO requests from QEMU, the PCI physical addresses must be the +same in the QEMU process and the device emulation process. In order to +accomplish that, guest BAR programming must also be forwarded from QEMU +to the emulation process. + +interrupt injection +^^^^^^^^^^^^^^^^^^^ + +When device emulation wants to inject an interrupt into the VM, the +request climbs the device's bus object hierarchy until the point where a +bus object knows how to signal the interrupt to the guest. The details +depend on the type of interrupt being raised. + +- PCI pin interrupts + +On x86 systems, there is an emulated IOAPIC object attached to the root +PCI bus object, and the root PCI object forwards interrupt requests to +it. The IOAPIC object, in turn, calls the KVM driver to inject the +corresponding interrupt into the VM. The simplest way to handle this in +an emulation process would be to setup the root PCI bus driver (via +``pci_bus_irqs()``) to send a interrupt request back to the QEMU +process, and have the device proxy object reflect it up the PCI tree +there. + +- PCI MSI/X interrupts + +PCI MSI/X interrupts are implemented in HW as DMA writes to a +CPU-specific PCI address. In QEMU on x86, a KVM APIC object receives +these DMA writes, then calls into the KVM driver to inject the interrupt +into the VM. A simple emulation process implementation would be to send +the MSI DMA address from QEMU as a message at initialization, then +install an address space handler at that address which forwards the MSI +message back to QEMU. + +DMA operations +^^^^^^^^^^^^^^ + +When a emulation object wants to DMA into or out of guest memory, it +first must use dma\_memory\_map() to convert the DMA address to a local +virtual address. The emulation process memory region objects setup above +will be used to translate the DMA address to a local virtual address the +device emulation code can access. + +IOMMU +^^^^^ + +When an IOMMU is in use in QEMU, DMA translation uses IOMMU memory +regions to translate the DMA address to a guest physical address before +that physical address can be translated to a local virtual address. The +emulation process will need similar functionality. + +- IOTLB cache + +The emulation process will maintain a cache of recent IOMMU translations +(the IOTLB). When the translate() callback of an IOMMU memory region is +invoked, the IOTLB cache will be searched for an entry that will map the +DMA address to a guest PA. On a cache miss, a message will be sent back +to QEMU requesting the corresponding translation entry, which be both be +used to return a guest address and be added to the cache. + +- IOTLB purge + +The IOMMU emulation will also need to act on unmap requests from QEMU. +These happen when the guest IOMMU driver purges an entry from the +guest's translation table. + +live migration +^^^^^^^^^^^^^^ + +When a remote process receives a live migration indication from QEMU, it +will set up a channel using the received file descriptor with +``qio_channel_socket_new_fd()``. This channel will be used to create a +*QEMUfile* that can be passed to ``qemu_save_device_state()`` to send +the process's device state back to QEMU. This method will be reversed on +restore - the channel will be passed to ``qemu_loadvm_state()`` to +restore the device state. + +Accelerating device emulation +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +The messages that are required to be sent between QEMU and the emulation +process can add considerable latency to IO operations. The optimizations +described below attempt to ameliorate this effect by allowing the +emulation process to communicate directly with the kernel KVM driver. +The KVM file descriptors created would be passed to the emulation process +via initialization messages, much like the guest memory table is done. +#### MMIO acceleration + +Vhost user applications can receive guest virtio driver stores directly +from KVM. The issue with the eventfd mechanism used by vhost user is +that it does not pass any data with the event indication, so it cannot +handle guest loads or guest stores that carry store data. This concept +could, however, be expanded to cover more cases. + +The expanded idea would require a new type of KVM device: +*KVM\_DEV\_TYPE\_USER*. This device has two file descriptors: a master +descriptor that QEMU can use for configuration, and a slave descriptor +that the emulation process can use to receive MMIO notifications. QEMU +would create both descriptors using the KVM driver, and pass the slave +descriptor to the emulation process via an initialization message. + +data structures +^^^^^^^^^^^^^^^ + +- guest physical range + +The guest physical range structure describes the address range that a +device will respond to. It includes the base and length of the range, as +well as which bus the range resides on (e.g., on an x86machine, it can +specify whether the range refers to memory or IO addresses). + +A device can have multiple physical address ranges it responds to (e.g., +a PCI device can have multiple BARs), so the structure will also include +an enumerated identifier to specify which of the device's ranges is +being referred to. + ++--------+----------------------------+ +| Name | Description | ++========+============================+ +| addr | range base address | ++--------+----------------------------+ +| len | range length | ++--------+----------------------------+ +| bus | addr type (memory or IO) | ++--------+----------------------------+ +| id | range ID (e.g., PCI BAR) | ++--------+----------------------------+ + +- MMIO request structure + +This structure describes an MMIO operation. It includes which guest +physical range the MMIO was within, the offset within that range, the +MMIO type (e.g., load or store), and its length and data. It also +includes a sequence number that can be used to reply to the MMIO, and +the CPU that issued the MMIO. + ++----------+------------------------+ +| Name | Description | ++==========+========================+ +| rid | range MMIO is within | ++----------+------------------------+ +| offset | offset withing *rid* | ++----------+------------------------+ +| type | e.g., load or store | ++----------+------------------------+ +| len | MMIO length | ++----------+------------------------+ +| data | store data | ++----------+------------------------+ +| seq | sequence ID | ++----------+------------------------+ + +- MMIO request queues + +MMIO request queues are FIFO arrays of MMIO request structures. There +are two queues: pending queue is for MMIOs that haven't been read by the +emulation program, and the sent queue is for MMIOs that haven't been +acknowledged. The main use of the second queue is to validate MMIO +replies from the emulation program. + +- scoreboard + +Each CPU in the VM is emulated in QEMU by a separate thread, so multiple +MMIOs may be waiting to be consumed by an emulation program and multiple +threads may be waiting for MMIO replies. The scoreboard would contain a +wait queue and sequence number for the per-CPU threads, allowing them to +be individually woken when the MMIO reply is received from the emulation +program. It also tracks the number of posted MMIO stores to the device +that haven't been replied to, in order to satisfy the PCI constraint +that a load to a device will not complete until all previous stores to +that device have been completed. + +- device shadow memory + +Some MMIO loads do not have device side-effects. These MMIOs can be +completed without sending a MMIO request to the emulation program if the +emulation program shares a shadow image of the device's memory image +with the KVM driver. + +The emulation program will ask the KVM driver to allocate memory for the +shadow image, and will then use ``mmap()`` to directly access it. The +emulation program can control KVM access to the shadow image by sending +KVM an access map telling it which areas of the image have no +side-effects (and can be completed immediately), and which require a +MMIO request to the emulation program. The access map can also inform +the KVM drive which size accesses are allowed to the image. + +master descriptor +^^^^^^^^^^^^^^^^^ + +The master descriptor is used by QEMU to configure the new KVM device. +The descriptor would be returned by the KVM driver when QEMU issues a +*KVM\_CREATE\_DEVICE* ``ioctl()`` with a *KVM\_DEV\_TYPE\_USER* type. + +KVM\_DEV\_TYPE\_USER device ops + + +The *KVM\_DEV\_TYPE\_USER* operations vector will be registered by a +``kvm_register_device_ops()`` call when the KVM system in initialized by +``kvm_init()``. These device ops are called by the KVM driver when QEMU +executes certain ``ioctl()`` operations on its KVM file descriptor. They +include: + +- create + +This routine is called when QEMU issues a *KVM\_CREATE\_DEVICE* +``ioctl()`` on its per-VM file descriptor. It will allocate and +initialize a KVM user device specific data structure, and assign the +*kvm\_device* private field to it. + +- ioctl + +This routine is invoked when QEMU issues an ``ioctl()`` on the master +descriptor. The ``ioctl()`` commands supported are defined by the KVM +device type. *KVM\_DEV\_TYPE\_USER* ones will need several commands: + +*KVM\_DEV\_USER\_SLAVE\_FD* creates the slave file descriptor that will +be passed to the device emulation program. Only one slave can be created +by each master descriptor. The file operations performed by this +descriptor are described below. + +The *KVM\_DEV\_USER\_PA\_RANGE* command configures a guest physical +address range that the slave descriptor will receive MMIO notifications +for. The range is specified by a guest physical range structure +argument. For buses that assign addresses to devices dynamically, this +command can be executed while the guest is running, such as the case +when a guest changes a device's PCI BAR registers. + +*KVM\_DEV\_USER\_PA\_RANGE* will use ``kvm_io_bus_register_dev()`` to +register *kvm\_io\_device\_ops* callbacks to be invoked when the guest +performs a MMIO operation within the range. When a range is changed, +``kvm_io_bus_unregister_dev()`` is used to remove the previous +instantiation. + +*KVM\_DEV\_USER\_TIMEOUT* will configure a timeout value that specifies +how long KVM will wait for the emulation process to respond to a MMIO +indication. + +- destroy + +This routine is called when the VM instance is destroyed. It will need +to destroy the slave descriptor; and free any memory allocated by the +driver, as well as the *kvm\_device* structure itself. + +slave descriptor +^^^^^^^^^^^^^^^^ + +The slave descriptor will have its own file operations vector, which +responds to system calls on the descriptor performed by the device +emulation program. + +- read + +A read returns any pending MMIO requests from the KVM driver as MMIO +request structures. Multiple structures can be returned if there are +multiple MMIO operations pending. The MMIO requests are moved from the +pending queue to the sent queue, and if there are threads waiting for +space in the pending to add new MMIO operations, they will be woken +here. + +- write + +A write also consists of a set of MMIO requests. They are compared to +the MMIO requests in the sent queue. Matches are removed from the sent +queue, and any threads waiting for the reply are woken. If a store is +removed, then the number of posted stores in the per-CPU scoreboard is +decremented. When the number is zero, and a non side-effect load was +waiting for posted stores to complete, the load is continued. + +- ioctl + +There are several ioctl()s that can be performed on the slave +descriptor. + +A *KVM\_DEV\_USER\_SHADOW\_SIZE* ``ioctl()`` causes the KVM driver to +allocate memory for the shadow image. This memory can later be +``mmap()``\ ed by the emulation process to share the emulation's view of +device memory with the KVM driver. + +A *KVM\_DEV\_USER\_SHADOW\_CTRL* ``ioctl()`` controls access to the +shadow image. It will send the KVM driver a shadow control map, which +specifies which areas of the image can complete guest loads without +sending the load request to the emulation program. It will also specify +the size of load operations that are allowed. + +- poll + +An emulation program will use the ``poll()`` call with a *POLLIN* flag +to determine if there are MMIO requests waiting to be read. It will +return if the pending MMIO request queue is not empty. + +- mmap + +This call allows the emulation program to directly access the shadow +image allocated by the KVM driver. As device emulation updates device +memory, changes with no side-effects will be reflected in the shadow, +and the KVM driver can satisfy guest loads from the shadow image without +needing to wait for the emulation program. + +kvm\_io\_device ops +^^^^^^^^^^^^^^^^^^^ + +Each KVM per-CPU thread can handle MMIO operation on behalf of the guest +VM. KVM will use the MMIO's guest physical address to search for a +matching *kvm\_io\_device* to see if the MMIO can be handled by the KVM +driver instead of exiting back to QEMU. If a match is found, the +corresponding callback will be invoked. + +- read + +This callback is invoked when the guest performs a load to the device. +Loads with side-effects must be handled synchronously, with the KVM +driver putting the QEMU thread to sleep waiting for the emulation +process reply before re-starting the guest. Loads that do not have +side-effects may be optimized by satisfying them from the shadow image, +if there are no outstanding stores to the device by this CPU. PCI memory +ordering demands that a load cannot complete before all older stores to +the same device have been completed. + +- write + +Stores can be handled asynchronously unless the pending MMIO request +queue is full. In this case, the QEMU thread must sleep waiting for +space in the queue. Stores will increment the number of posted stores in +the per-CPU scoreboard, in order to implement the PCI ordering +constraint above. + +interrupt acceleration +^^^^^^^^^^^^^^^^^^^^^^ + +This performance optimization would work much like a vhost user +application does, where the QEMU process sets up *eventfds* that cause +the device's corresponding interrupt to be triggered by the KVM driver. +These irq file descriptors are sent to the emulation process at +initialization, and are used when the emulation code raises a device +interrupt. + +intx acceleration +''''''''''''''''' + +Traditional PCI pin interrupts are level based, so, in addition to an +irq file descriptor, a re-sampling file descriptor needs to be sent to +the emulation program. This second file descriptor allows multiple +devices sharing an irq to be notified when the interrupt has been +acknowledged by the guest, so they can re-trigger the interrupt if their +device has not de-asserted its interrupt. + +intx irq descriptor + + +The irq descriptors are created by the proxy object +``using event_notifier_init()`` to create the irq and re-sampling +*eventds*, and ``kvm_vm_ioctl(KVM_IRQFD)`` to bind them to an interrupt. +The interrupt route can be found with +``pci_device_route_intx_to_irq()``. + +intx routing changes + + +Intx routing can be changed when the guest programs the APIC the device +pin is connected to. The proxy object in QEMU will use +``pci_device_set_intx_routing_notifier()`` to be informed of any guest +changes to the route. This handler will broadly follow the VFIO +interrupt logic to change the route: de-assigning the existing irq +descriptor from its route, then assigning it the new route. (see +``vfio_intx_update()``) + +MSI/X acceleration +'''''''''''''''''' + +MSI/X interrupts are sent as DMA transactions to the host. The interrupt +data contains a vector that is programmed by the guest, A device may have +multiple MSI interrupts associated with it, so multiple irq descriptors +may need to be sent to the emulation program. + +MSI/X irq descriptor + + +This case will also follow the VFIO example. For each MSI/X interrupt, +an *eventfd* is created, a virtual interrupt is allocated by +``kvm_irqchip_add_msi_route()``, and the virtual interrupt is bound to +the eventfd with ``kvm_irqchip_add_irqfd_notifier()``. + +MSI/X config space changes + + +The guest may dynamically update several MSI-related tables in the +device's PCI config space. These include per-MSI interrupt enables and +vector data. Additionally, MSIX tables exist in device memory space, not +config space. Much like the BAR case above, the proxy object must look +at guest config space programming to keep the MSI interrupt state +consistent between QEMU and the emulation program. + +-------------- + +Disaggregated CPU emulation +--------------------------- + +After IO services have been disaggregated, a second phase would be to +separate a process to handle CPU instruction emulation from the main +QEMU control function. There are no object separation points for this +code, so the first task would be to create one. + +Host access controls +-------------------- + +Separating QEMU relies on the host OS's access restriction mechanisms to +enforce that the differing processes can only access the objects they +are entitled to. There are a couple types of mechanisms usually provided +by general purpose OSs. + +Discretionary access control +~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +Discretionary access control allows each user to control who can access +their files. In Linux, this type of control is usually too coarse for +QEMU separation, since it only provides three separate access controls: +one for the same user ID, the second for users IDs with the same group +ID, and the third for all other user IDs. Each device instance would +need a separate user ID to provide access control, which is likely to be +unwieldy for dynamically created VMs. + +Mandatory access control +~~~~~~~~~~~~~~~~~~~~~~~~ + +Mandatory access control allows the OS to add an additional set of +controls on top of discretionary access for the OS to control. It also +adds other attributes to processes and files such as types, roles, and +categories, and can establish rules for how processes and files can +interact. + +Type enforcement +^^^^^^^^^^^^^^^^ + +Type enforcement assigns a *type* attribute to processes and files, and +allows rules to be written on what operations a process with a given +type can perform on a file with a given type. QEMU separation could take +advantage of type enforcement by running the emulation processes with +different types, both from the main QEMU process, and from the emulation +processes of different classes of devices. + +For example, guest disk images and disk emulation processes could have +types separate from the main QEMU process and non-disk emulation +processes, and the type rules could prevent processes other than disk +emulation ones from accessing guest disk images. Similarly, network +emulation processes can have a type separate from the main QEMU process +and non-network emulation process, and only that type can access the +host tun/tap device used to provide guest networking. + +Category enforcement +^^^^^^^^^^^^^^^^^^^^ + +Category enforcement assigns a set of numbers within a given range to +the process or file. The process is granted access to the file if the +process's set is a superset of the file's set. This enforcement can be +used to separate multiple instances of devices in the same class. + +For example, if there are multiple disk devices provides to a guest, +each device emulation process could be provisioned with a separate +category. The different device emulation processes would not be able to +access each other's backing disk images. + +Alternatively, categories could be used in lieu of the type enforcement +scheme described above. In this scenario, different categories would be +used to prevent device emulation processes in different classes from +accessing resources assigned to other classes. -- 2.29.2 From: Elena Ufimtseva <elena.ufimtseva@oracle.com> Adds documentation explaining the command-line arguments needed to use multi-process. Signed-off-by: Elena Ufimtseva <elena.ufimtseva@oracle.com> Signed-off-by: Jagannathan Raman <jag.raman@oracle.com> Signed-off-by: John G Johnson <john.g.johnson@oracle.com> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Message-id: 49f757a84e5dd6fae14b22544897d1124c5fdbad.1611938319.git.jag.raman@oracle.com [Move orphan docs/multi-process.rst document into docs/system/ and add it to index.rst to prevent Sphinx "document isn't included in any toctree" error. --Stefan] Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- MAINTAINERS | 1 + docs/system/index.rst | 1 + docs/system/multi-process.rst | 64 +++++++++++++++++++++++++++++++++++ 3 files changed, 66 insertions(+) create mode 100644 docs/system/multi-process.rst diff --git a/MAINTAINERS b/MAINTAINERS index XXXXXXX..XXXXXXX 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -XXX,XX +XXX,XX @@ M: Jagannathan Raman <jag.raman@oracle.com> M: John G Johnson <john.g.johnson@oracle.com> S: Maintained F: docs/devel/multi-process.rst +F: docs/system/multi-process.rst Build and test automation ------------------------- diff --git a/docs/system/index.rst b/docs/system/index.rst index XXXXXXX..XXXXXXX 100644 --- a/docs/system/index.rst +++ b/docs/system/index.rst @@ -XXX,XX +XXX,XX @@ Contents: pr-manager targets security + multi-process deprecated removed-features build-platforms diff --git a/docs/system/multi-process.rst b/docs/system/multi-process.rst new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/docs/system/multi-process.rst @@ -XXX,XX +XXX,XX @@ +Multi-process QEMU +================== + +This document describes how to configure and use multi-process qemu. +For the design document refer to docs/devel/qemu-multiprocess. + +1) Configuration +---------------- + +multi-process is enabled by default for targets that enable KVM + + +2) Usage +-------- + +Multi-process QEMU requires an orchestrator to launch. + +Following is a description of command-line used to launch mpqemu. + +* Orchestrator: + + - The Orchestrator creates a unix socketpair + + - It launches the remote process and passes one of the + sockets to it via command-line. + + - It then launches QEMU and specifies the other socket as an option + to the Proxy device object + +* Remote Process: + + - QEMU can enter remote process mode by using the "remote" machine + option. + + - The orchestrator creates a "remote-object" with details about + the device and the file descriptor for the device + + - The remaining options are no different from how one launches QEMU with + devices. + + - Example command-line for the remote process is as follows: + + /usr/bin/qemu-system-x86_64 \ + -machine x-remote \ + -device lsi53c895a,id=lsi0 \ + -drive id=drive_image2,file=/build/ol7-nvme-test-1.qcow2 \ + -device scsi-hd,id=drive2,drive=drive_image2,bus=lsi0.0,scsi-id=0 \ + -object x-remote-object,id=robj1,devid=lsi1,fd=4, + +* QEMU: + + - Since parts of the RAM are shared between QEMU & remote process, a + memory-backend-memfd is required to facilitate this, as follows: + + -object memory-backend-memfd,id=mem,size=2G + + - A "x-pci-proxy-dev" device is created for each of the PCI devices emulated + in the remote process. A "socket" sub-option specifies the other end of + unix channel created by orchestrator. The "id" sub-option must be specified + and should be the same as the "id" specified for the remote PCI device + + - Example commandline for QEMU is as follows: + + -device x-pci-proxy-dev,id=lsi0,socket=3 -- 2.29.2 From: Jagannathan Raman <jag.raman@oracle.com> Allow RAM MemoryRegion to be created from an offset in a file, instead of allocating at offset of 0 by default. This is needed to synchronize RAM between QEMU & remote process. Signed-off-by: Jagannathan Raman <jag.raman@oracle.com> Signed-off-by: John G Johnson <john.g.johnson@oracle.com> Signed-off-by: Elena Ufimtseva <elena.ufimtseva@oracle.com> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Message-id: 609996697ad8617e3b01df38accc5c208c24d74e.1611938319.git.jag.raman@oracle.com Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- include/exec/memory.h | 2 ++ include/exec/ram_addr.h | 4 ++-- include/qemu/mmap-alloc.h | 4 +++- backends/hostmem-memfd.c | 2 +- hw/misc/ivshmem.c | 3 ++- softmmu/memory.c | 3 ++- softmmu/physmem.c | 12 +++++++----- util/mmap-alloc.c | 8 +++++--- util/oslib-posix.c | 2 +- 9 files changed, 25 insertions(+), 15 deletions(-) diff --git a/include/exec/memory.h b/include/exec/memory.h index XXXXXXX..XXXXXXX 100644 --- a/include/exec/memory.h +++ b/include/exec/memory.h @@ -XXX,XX +XXX,XX @@ void memory_region_init_ram_from_file(MemoryRegion *mr, * @size: size of the region. * @share: %true if memory must be mmaped with the MAP_SHARED flag * @fd: the fd to mmap. + * @offset: offset within the file referenced by fd * @errp: pointer to Error*, to store an error if it happens. * * Note that this function does not do anything to cause the data in the @@ -XXX,XX +XXX,XX @@ void memory_region_init_ram_from_fd(MemoryRegion *mr, uint64_t size, bool share, int fd, + ram_addr_t offset, Error **errp); #endif diff --git a/include/exec/ram_addr.h b/include/exec/ram_addr.h index XXXXXXX..XXXXXXX 100644 --- a/include/exec/ram_addr.h +++ b/include/exec/ram_addr.h @@ -XXX,XX +XXX,XX @@ RAMBlock *qemu_ram_alloc_from_file(ram_addr_t size, MemoryRegion *mr, uint32_t ram_flags, const char *mem_path, bool readonly, Error **errp); RAMBlock *qemu_ram_alloc_from_fd(ram_addr_t size, MemoryRegion *mr, - uint32_t ram_flags, int fd, bool readonly, - Error **errp); + uint32_t ram_flags, int fd, off_t offset, + bool readonly, Error **errp); RAMBlock *qemu_ram_alloc_from_ptr(ram_addr_t size, void *host, MemoryRegion *mr, Error **errp); diff --git a/include/qemu/mmap-alloc.h b/include/qemu/mmap-alloc.h index XXXXXXX..XXXXXXX 100644 --- a/include/qemu/mmap-alloc.h +++ b/include/qemu/mmap-alloc.h @@ -XXX,XX +XXX,XX @@ size_t qemu_mempath_getpagesize(const char *mem_path); * @readonly: true for a read-only mapping, false for read/write. * @shared: map has RAM_SHARED flag. * @is_pmem: map has RAM_PMEM flag. + * @map_offset: map starts at offset of map_offset from the start of fd * * Return: * On success, return a pointer to the mapped area. @@ -XXX,XX +XXX,XX @@ void *qemu_ram_mmap(int fd, size_t align, bool readonly, bool shared, - bool is_pmem); + bool is_pmem, + off_t map_offset); void qemu_ram_munmap(int fd, void *ptr, size_t size); diff --git a/backends/hostmem-memfd.c b/backends/hostmem-memfd.c index XXXXXXX..XXXXXXX 100644 --- a/backends/hostmem-memfd.c +++ b/backends/hostmem-memfd.c @@ -XXX,XX +XXX,XX @@ memfd_backend_memory_alloc(HostMemoryBackend *backend, Error **errp) name = host_memory_backend_get_name(backend); memory_region_init_ram_from_fd(&backend->mr, OBJECT(backend), name, backend->size, - backend->share, fd, errp); + backend->share, fd, 0, errp); g_free(name); } diff --git a/hw/misc/ivshmem.c b/hw/misc/ivshmem.c index XXXXXXX..XXXXXXX 100644 --- a/hw/misc/ivshmem.c +++ b/hw/misc/ivshmem.c @@ -XXX,XX +XXX,XX @@ static void process_msg_shmem(IVShmemState *s, int fd, Error **errp) /* mmap the region and map into the BAR2 */ memory_region_init_ram_from_fd(&s->server_bar2, OBJECT(s), - "ivshmem.bar2", size, true, fd, &local_err); + "ivshmem.bar2", size, true, fd, 0, + &local_err); if (local_err) { error_propagate(errp, local_err); return; diff --git a/softmmu/memory.c b/softmmu/memory.c index XXXXXXX..XXXXXXX 100644 --- a/softmmu/memory.c +++ b/softmmu/memory.c @@ -XXX,XX +XXX,XX @@ void memory_region_init_ram_from_fd(MemoryRegion *mr, uint64_t size, bool share, int fd, + ram_addr_t offset, Error **errp) { Error *err = NULL; @@ -XXX,XX +XXX,XX @@ void memory_region_init_ram_from_fd(MemoryRegion *mr, mr->destructor = memory_region_destructor_ram; mr->ram_block = qemu_ram_alloc_from_fd(size, mr, share ? RAM_SHARED : 0, - fd, false, &err); + fd, offset, false, &err); if (err) { mr->size = int128_zero(); object_unparent(OBJECT(mr)); diff --git a/softmmu/physmem.c b/softmmu/physmem.c index XXXXXXX..XXXXXXX 100644 --- a/softmmu/physmem.c +++ b/softmmu/physmem.c @@ -XXX,XX +XXX,XX @@ static void *file_ram_alloc(RAMBlock *block, int fd, bool readonly, bool truncate, + off_t offset, Error **errp) { void *area; @@ -XXX,XX +XXX,XX @@ static void *file_ram_alloc(RAMBlock *block, } area = qemu_ram_mmap(fd, memory, block->mr->align, readonly, - block->flags & RAM_SHARED, block->flags & RAM_PMEM); + block->flags & RAM_SHARED, block->flags & RAM_PMEM, + offset); if (area == MAP_FAILED) { error_setg_errno(errp, errno, "unable to map backing store for guest RAM"); @@ -XXX,XX +XXX,XX @@ static void ram_block_add(RAMBlock *new_block, Error **errp, bool shared) #ifdef CONFIG_POSIX RAMBlock *qemu_ram_alloc_from_fd(ram_addr_t size, MemoryRegion *mr, - uint32_t ram_flags, int fd, bool readonly, - Error **errp) + uint32_t ram_flags, int fd, off_t offset, + bool readonly, Error **errp) { RAMBlock *new_block; Error *local_err = NULL; @@ -XXX,XX +XXX,XX @@ RAMBlock *qemu_ram_alloc_from_fd(ram_addr_t size, MemoryRegion *mr, new_block->max_length = size; new_block->flags = ram_flags; new_block->host = file_ram_alloc(new_block, size, fd, readonly, - !file_size, errp); + !file_size, offset, errp); if (!new_block->host) { g_free(new_block); return NULL; @@ -XXX,XX +XXX,XX @@ RAMBlock *qemu_ram_alloc_from_file(ram_addr_t size, MemoryRegion *mr, return NULL; } - block = qemu_ram_alloc_from_fd(size, mr, ram_flags, fd, readonly, errp); + block = qemu_ram_alloc_from_fd(size, mr, ram_flags, fd, 0, readonly, errp); if (!block) { if (created) { unlink(mem_path); diff --git a/util/mmap-alloc.c b/util/mmap-alloc.c index XXXXXXX..XXXXXXX 100644 --- a/util/mmap-alloc.c +++ b/util/mmap-alloc.c @@ -XXX,XX +XXX,XX @@ void *qemu_ram_mmap(int fd, size_t align, bool readonly, bool shared, - bool is_pmem) + bool is_pmem, + off_t map_offset) { int prot; int flags; @@ -XXX,XX +XXX,XX @@ void *qemu_ram_mmap(int fd, prot = PROT_READ | (readonly ? 0 : PROT_WRITE); - ptr = mmap(guardptr + offset, size, prot, flags | map_sync_flags, fd, 0); + ptr = mmap(guardptr + offset, size, prot, + flags | map_sync_flags, fd, map_offset); if (ptr == MAP_FAILED && map_sync_flags) { if (errno == ENOTSUP) { @@ -XXX,XX +XXX,XX @@ void *qemu_ram_mmap(int fd, * if map failed with MAP_SHARED_VALIDATE | MAP_SYNC, * we will remove these flags to handle compatibility. */ - ptr = mmap(guardptr + offset, size, prot, flags, fd, 0); + ptr = mmap(guardptr + offset, size, prot, flags, fd, map_offset); } if (ptr == MAP_FAILED) { diff --git a/util/oslib-posix.c b/util/oslib-posix.c index XXXXXXX..XXXXXXX 100644 --- a/util/oslib-posix.c +++ b/util/oslib-posix.c @@ -XXX,XX +XXX,XX @@ void *qemu_memalign(size_t alignment, size_t size) void *qemu_anon_ram_alloc(size_t size, uint64_t *alignment, bool shared) { size_t align = QEMU_VMALLOC_ALIGN; - void *ptr = qemu_ram_mmap(-1, size, align, false, shared, false); + void *ptr = qemu_ram_mmap(-1, size, align, false, shared, false, 0); if (ptr == MAP_FAILED) { return NULL; -- 2.29.2 From: Jagannathan Raman <jag.raman@oracle.com> Add configuration options to enable or disable multiprocess QEMU code Signed-off-by: John G Johnson <john.g.johnson@oracle.com> Signed-off-by: Jagannathan Raman <jag.raman@oracle.com> Signed-off-by: Elena Ufimtseva <elena.ufimtseva@oracle.com> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Message-id: 6cc37253e35418ebd7b675a31a3df6e3c7a12dc1.1611938319.git.jag.raman@oracle.com Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- configure | 10 ++++++++++ meson.build | 4 +++- Kconfig.host | 4 ++++ hw/Kconfig | 1 + hw/remote/Kconfig | 3 +++ 5 files changed, 21 insertions(+), 1 deletion(-) create mode 100644 hw/remote/Kconfig diff --git a/configure b/configure index XXXXXXX..XXXXXXX 100755 --- a/configure +++ b/configure @@ -XXX,XX +XXX,XX @@ skip_meson=no gettext="auto" fuse="auto" fuse_lseek="auto" +multiprocess="no" malloc_trim="auto" @@ -XXX,XX +XXX,XX @@ Linux) linux="yes" linux_user="yes" vhost_user=${default_feature:-yes} + multiprocess=${default_feature:-yes} ;; esac @@ -XXX,XX +XXX,XX @@ for opt do ;; --disable-fuse-lseek) fuse_lseek="disabled" ;; + --enable-multiprocess) multiprocess="yes" + ;; + --disable-multiprocess) multiprocess="no" + ;; *) echo "ERROR: unknown option $opt" echo "Try '$0 --help' for more information" @@ -XXX,XX +XXX,XX @@ disabled with --disable-FEATURE, default is enabled if available libdaxctl libdaxctl support fuse FUSE block device export fuse-lseek SEEK_HOLE/SEEK_DATA support for FUSE exports + multiprocess Multiprocess QEMU support NOTE: The object files are built at the place where configure is launched EOF @@ -XXX,XX +XXX,XX @@ fi if test "$have_mlockall" = "yes" ; then echo "HAVE_MLOCKALL=y" >> $config_host_mak fi +if test "$multiprocess" = "yes" ; then + echo "CONFIG_MULTIPROCESS_ALLOWED=y" >> $config_host_mak +fi if test "$fuzzing" = "yes" ; then # If LIB_FUZZING_ENGINE is set, assume we are running on OSS-Fuzz, and the # needed CFLAGS have already been provided diff --git a/meson.build b/meson.build index XXXXXXX..XXXXXXX 100644 --- a/meson.build +++ b/meson.build @@ -XXX,XX +XXX,XX @@ host_kconfig = \ ('CONFIG_VHOST_KERNEL' in config_host ? ['CONFIG_VHOST_KERNEL=y'] : []) + \ (have_virtfs ? ['CONFIG_VIRTFS=y'] : []) + \ ('CONFIG_LINUX' in config_host ? ['CONFIG_LINUX=y'] : []) + \ - ('CONFIG_PVRDMA' in config_host ? ['CONFIG_PVRDMA=y'] : []) + ('CONFIG_PVRDMA' in config_host ? ['CONFIG_PVRDMA=y'] : []) + \ + ('CONFIG_MULTIPROCESS_ALLOWED' in config_host ? ['CONFIG_MULTIPROCESS_ALLOWED=y'] : []) ignored = [ 'TARGET_XML_FILES', 'TARGET_ABI_DIR', 'TARGET_ARCH' ] @@ -XXX,XX +XXX,XX @@ summary_info += {'libpmem support': config_host.has_key('CONFIG_LIBPMEM')} summary_info += {'libdaxctl support': config_host.has_key('CONFIG_LIBDAXCTL')} summary_info += {'libudev': libudev.found()} summary_info += {'FUSE lseek': fuse_lseek.found()} +summary_info += {'Multiprocess QEMU': config_host.has_key('CONFIG_MULTIPROCESS_ALLOWED')} summary(summary_info, bool_yn: true, section: 'Dependencies') if not supported_cpus.contains(cpu) diff --git a/Kconfig.host b/Kconfig.host index XXXXXXX..XXXXXXX 100644 --- a/Kconfig.host +++ b/Kconfig.host @@ -XXX,XX +XXX,XX @@ config VIRTFS config PVRDMA bool + +config MULTIPROCESS_ALLOWED + bool + imply MULTIPROCESS diff --git a/hw/Kconfig b/hw/Kconfig index XXXXXXX..XXXXXXX 100644 --- a/hw/Kconfig +++ b/hw/Kconfig @@ -XXX,XX +XXX,XX @@ source pci-host/Kconfig source pcmcia/Kconfig source pci/Kconfig source rdma/Kconfig +source remote/Kconfig source rtc/Kconfig source scsi/Kconfig source sd/Kconfig diff --git a/hw/remote/Kconfig b/hw/remote/Kconfig new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/hw/remote/Kconfig @@ -XXX,XX +XXX,XX @@ +config MULTIPROCESS + bool + depends on PCI && KVM -- 2.29.2 From: Jagannathan Raman <jag.raman@oracle.com> PCI host bridge is setup for the remote device process. It is implemented using remote-pcihost object. It is an extension of the PCI host bridge setup by QEMU. Remote-pcihost configures a PCI bus which could be used by the remote PCI device to latch on to. Signed-off-by: Jagannathan Raman <jag.raman@oracle.com> Signed-off-by: John G Johnson <john.g.johnson@oracle.com> Signed-off-by: Elena Ufimtseva <elena.ufimtseva@oracle.com> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Message-id: 0871ba857abb2eafacde07e7fe66a3f12415bfb2.1611938319.git.jag.raman@oracle.com [Added PCI_EXPRESS condition in hw/remote/Kconfig since remote-pcihost needs PCIe. This solves "make check" failure on s390x. Fix suggested by Philippe Mathieu-Daudé <philmd@redhat.com> and Thomas Huth <thuth@redhat.com>. --Stefan] Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- MAINTAINERS | 2 + include/hw/pci-host/remote.h | 29 ++++++++++++++ hw/pci-host/remote.c | 75 ++++++++++++++++++++++++++++++++++++ hw/pci-host/Kconfig | 3 ++ hw/pci-host/meson.build | 1 + hw/remote/Kconfig | 3 +- 6 files changed, 112 insertions(+), 1 deletion(-) create mode 100644 include/hw/pci-host/remote.h create mode 100644 hw/pci-host/remote.c diff --git a/MAINTAINERS b/MAINTAINERS index XXXXXXX..XXXXXXX 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -XXX,XX +XXX,XX @@ M: John G Johnson <john.g.johnson@oracle.com> S: Maintained F: docs/devel/multi-process.rst F: docs/system/multi-process.rst +F: hw/pci-host/remote.c +F: include/hw/pci-host/remote.h Build and test automation ------------------------- diff --git a/include/hw/pci-host/remote.h b/include/hw/pci-host/remote.h new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/include/hw/pci-host/remote.h @@ -XXX,XX +XXX,XX @@ +/* + * PCI Host for remote device + * + * Copyright © 2018, 2021 Oracle and/or its affiliates. + * + * This work is licensed under the terms of the GNU GPL, version 2 or later. + * See the COPYING file in the top-level directory. + * + */ + +#ifndef REMOTE_PCIHOST_H +#define REMOTE_PCIHOST_H + +#include "exec/memory.h" +#include "hw/pci/pcie_host.h" + +#define TYPE_REMOTE_PCIHOST "remote-pcihost" +OBJECT_DECLARE_SIMPLE_TYPE(RemotePCIHost, REMOTE_PCIHOST) + +struct RemotePCIHost { + /*< private >*/ + PCIExpressHost parent_obj; + /*< public >*/ + + MemoryRegion *mr_pci_mem; + MemoryRegion *mr_sys_io; +}; + +#endif diff --git a/hw/pci-host/remote.c b/hw/pci-host/remote.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/hw/pci-host/remote.c @@ -XXX,XX +XXX,XX @@ +/* + * Remote PCI host device + * + * Unlike PCI host devices that model physical hardware, the purpose + * of this PCI host is to host multi-process QEMU devices. + * + * Multi-process QEMU extends the PCI host of a QEMU machine into a + * remote process. Any PCI device attached to the remote process is + * visible in the QEMU guest. This allows existing QEMU device models + * to be reused in the remote process. + * + * This PCI host is purely a container for PCI devices. It's fake in the + * sense that the guest never sees this PCI host and has no way of + * accessing it. Its job is just to provide the environment that QEMU + * PCI device models need when running in a remote process. + * + * Copyright © 2018, 2021 Oracle and/or its affiliates. + * + * This work is licensed under the terms of the GNU GPL, version 2 or later. + * See the COPYING file in the top-level directory. + * + */ + +#include "qemu/osdep.h" +#include "qemu-common.h" + +#include "hw/pci/pci.h" +#include "hw/pci/pci_host.h" +#include "hw/pci/pcie_host.h" +#include "hw/qdev-properties.h" +#include "hw/pci-host/remote.h" +#include "exec/memory.h" + +static const char *remote_pcihost_root_bus_path(PCIHostState *host_bridge, + PCIBus *rootbus) +{ + return "0000:00"; +} + +static void remote_pcihost_realize(DeviceState *dev, Error **errp) +{ + PCIHostState *pci = PCI_HOST_BRIDGE(dev); + RemotePCIHost *s = REMOTE_PCIHOST(dev); + + pci->bus = pci_root_bus_new(DEVICE(s), "remote-pci", + s->mr_pci_mem, s->mr_sys_io, + 0, TYPE_PCIE_BUS); +} + +static void remote_pcihost_class_init(ObjectClass *klass, void *data) +{ + DeviceClass *dc = DEVICE_CLASS(klass); + PCIHostBridgeClass *hc = PCI_HOST_BRIDGE_CLASS(klass); + + hc->root_bus_path = remote_pcihost_root_bus_path; + dc->realize = remote_pcihost_realize; + + dc->user_creatable = false; + set_bit(DEVICE_CATEGORY_BRIDGE, dc->categories); + dc->fw_name = "pci"; +} + +static const TypeInfo remote_pcihost_info = { + .name = TYPE_REMOTE_PCIHOST, + .parent = TYPE_PCIE_HOST_BRIDGE, + .instance_size = sizeof(RemotePCIHost), + .class_init = remote_pcihost_class_init, +}; + +static void remote_pcihost_register(void) +{ + type_register_static(&remote_pcihost_info); +} + +type_init(remote_pcihost_register) diff --git a/hw/pci-host/Kconfig b/hw/pci-host/Kconfig index XXXXXXX..XXXXXXX 100644 --- a/hw/pci-host/Kconfig +++ b/hw/pci-host/Kconfig @@ -XXX,XX +XXX,XX @@ config PCI_POWERNV select PCI_EXPRESS select MSI_NONBROKEN select PCIE_PORT + +config REMOTE_PCIHOST + bool diff --git a/hw/pci-host/meson.build b/hw/pci-host/meson.build index XXXXXXX..XXXXXXX 100644 --- a/hw/pci-host/meson.build +++ b/hw/pci-host/meson.build @@ -XXX,XX +XXX,XX @@ pci_ss.add(when: 'CONFIG_PCI_EXPRESS_XILINX', if_true: files('xilinx-pcie.c')) pci_ss.add(when: 'CONFIG_PCI_I440FX', if_true: files('i440fx.c')) pci_ss.add(when: 'CONFIG_PCI_SABRE', if_true: files('sabre.c')) pci_ss.add(when: 'CONFIG_XEN_IGD_PASSTHROUGH', if_true: files('xen_igd_pt.c')) +pci_ss.add(when: 'CONFIG_REMOTE_PCIHOST', if_true: files('remote.c')) # PPC devices pci_ss.add(when: 'CONFIG_PREP_PCI', if_true: files('prep.c')) diff --git a/hw/remote/Kconfig b/hw/remote/Kconfig index XXXXXXX..XXXXXXX 100644 --- a/hw/remote/Kconfig +++ b/hw/remote/Kconfig @@ -XXX,XX +XXX,XX @@ config MULTIPROCESS bool - depends on PCI && KVM + depends on PCI && PCI_EXPRESS && KVM + select REMOTE_PCIHOST -- 2.29.2 From: Jagannathan Raman <jag.raman@oracle.com> x-remote-machine object sets up various subsystems of the remote device process. Instantiate PCI host bridge object and initialize RAM, IO & PCI memory regions. Signed-off-by: John G Johnson <john.g.johnson@oracle.com> Signed-off-by: Jagannathan Raman <jag.raman@oracle.com> Signed-off-by: Elena Ufimtseva <elena.ufimtseva@oracle.com> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Message-id: c537f38d17f90453ca610c6b70cf3480274e0ba1.1611938319.git.jag.raman@oracle.com Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- MAINTAINERS | 2 ++ include/hw/pci-host/remote.h | 1 + include/hw/remote/machine.h | 27 ++++++++++++++ hw/remote/machine.c | 70 ++++++++++++++++++++++++++++++++++++ hw/meson.build | 1 + hw/remote/meson.build | 5 +++ 6 files changed, 106 insertions(+) create mode 100644 include/hw/remote/machine.h create mode 100644 hw/remote/machine.c create mode 100644 hw/remote/meson.build diff --git a/MAINTAINERS b/MAINTAINERS index XXXXXXX..XXXXXXX 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -XXX,XX +XXX,XX @@ F: docs/devel/multi-process.rst F: docs/system/multi-process.rst F: hw/pci-host/remote.c F: include/hw/pci-host/remote.h +F: hw/remote/machine.c +F: include/hw/remote/machine.h Build and test automation ------------------------- diff --git a/include/hw/pci-host/remote.h b/include/hw/pci-host/remote.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/pci-host/remote.h +++ b/include/hw/pci-host/remote.h @@ -XXX,XX +XXX,XX @@ struct RemotePCIHost { MemoryRegion *mr_pci_mem; MemoryRegion *mr_sys_io; + MemoryRegion *mr_sys_mem; }; #endif diff --git a/include/hw/remote/machine.h b/include/hw/remote/machine.h new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/include/hw/remote/machine.h @@ -XXX,XX +XXX,XX @@ +/* + * Remote machine configuration + * + * Copyright © 2018, 2021 Oracle and/or its affiliates. + * + * This work is licensed under the terms of the GNU GPL, version 2 or later. + * See the COPYING file in the top-level directory. + * + */ + +#ifndef REMOTE_MACHINE_H +#define REMOTE_MACHINE_H + +#include "qom/object.h" +#include "hw/boards.h" +#include "hw/pci-host/remote.h" + +struct RemoteMachineState { + MachineState parent_obj; + + RemotePCIHost *host; +}; + +#define TYPE_REMOTE_MACHINE "x-remote-machine" +OBJECT_DECLARE_SIMPLE_TYPE(RemoteMachineState, REMOTE_MACHINE) + +#endif diff --git a/hw/remote/machine.c b/hw/remote/machine.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/hw/remote/machine.c @@ -XXX,XX +XXX,XX @@ +/* + * Machine for remote device + * + * This machine type is used by the remote device process in multi-process + * QEMU. QEMU device models depend on parent busses, interrupt controllers, + * memory regions, etc. The remote machine type offers this environment so + * that QEMU device models can be used as remote devices. + * + * Copyright © 2018, 2021 Oracle and/or its affiliates. + * + * This work is licensed under the terms of the GNU GPL, version 2 or later. + * See the COPYING file in the top-level directory. + * + */ + +#include "qemu/osdep.h" +#include "qemu-common.h" + +#include "hw/remote/machine.h" +#include "exec/address-spaces.h" +#include "exec/memory.h" +#include "qapi/error.h" + +static void remote_machine_init(MachineState *machine) +{ + MemoryRegion *system_memory, *system_io, *pci_memory; + RemoteMachineState *s = REMOTE_MACHINE(machine); + RemotePCIHost *rem_host; + + system_memory = get_system_memory(); + system_io = get_system_io(); + + pci_memory = g_new(MemoryRegion, 1); + memory_region_init(pci_memory, NULL, "pci", UINT64_MAX); + + rem_host = REMOTE_PCIHOST(qdev_new(TYPE_REMOTE_PCIHOST)); + + rem_host->mr_pci_mem = pci_memory; + rem_host->mr_sys_mem = system_memory; + rem_host->mr_sys_io = system_io; + + s->host = rem_host; + + object_property_add_child(OBJECT(s), "remote-pcihost", OBJECT(rem_host)); + memory_region_add_subregion_overlap(system_memory, 0x0, pci_memory, -1); + + qdev_realize(DEVICE(rem_host), sysbus_get_default(), &error_fatal); +} + +static void remote_machine_class_init(ObjectClass *oc, void *data) +{ + MachineClass *mc = MACHINE_CLASS(oc); + + mc->init = remote_machine_init; + mc->desc = "Experimental remote machine"; +} + +static const TypeInfo remote_machine = { + .name = TYPE_REMOTE_MACHINE, + .parent = TYPE_MACHINE, + .instance_size = sizeof(RemoteMachineState), + .class_init = remote_machine_class_init, +}; + +static void remote_machine_register_types(void) +{ + type_register_static(&remote_machine); +} + +type_init(remote_machine_register_types); diff --git a/hw/meson.build b/hw/meson.build index XXXXXXX..XXXXXXX 100644 --- a/hw/meson.build +++ b/hw/meson.build @@ -XXX,XX +XXX,XX @@ subdir('moxie') subdir('nios2') subdir('openrisc') subdir('ppc') +subdir('remote') subdir('riscv') subdir('rx') subdir('s390x') diff --git a/hw/remote/meson.build b/hw/remote/meson.build new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/hw/remote/meson.build @@ -XXX,XX +XXX,XX @@ +remote_ss = ss.source_set() + +remote_ss.add(when: 'CONFIG_MULTIPROCESS', if_true: files('machine.c')) + +softmmu_ss.add_all(when: 'CONFIG_MULTIPROCESS', if_true: remote_ss) -- 2.29.2 From: Elena Ufimtseva <elena.ufimtseva@oracle.com> Adds qio_channel_writev_full_all() to transmit both data and FDs. Refactors existing code to use this helper. Signed-off-by: Elena Ufimtseva <elena.ufimtseva@oracle.com> Signed-off-by: John G Johnson <john.g.johnson@oracle.com> Signed-off-by: Jagannathan Raman <jag.raman@oracle.com> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Acked-by: Daniel P. Berrangé <berrange@redhat.com> Message-id: 480fbf1fe4152495d60596c9b665124549b426a5.1611938319.git.jag.raman@oracle.com Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- include/io/channel.h | 25 +++++++++++++++++++++++++ io/channel.c | 15 ++++++++++++++- 2 files changed, 39 insertions(+), 1 deletion(-) diff --git a/include/io/channel.h b/include/io/channel.h index XXXXXXX..XXXXXXX 100644 --- a/include/io/channel.h +++ b/include/io/channel.h @@ -XXX,XX +XXX,XX @@ void qio_channel_set_aio_fd_handler(QIOChannel *ioc, IOHandler *io_write, void *opaque); +/** + * qio_channel_writev_full_all: + * @ioc: the channel object + * @iov: the array of memory regions to write data from + * @niov: the length of the @iov array + * @fds: an array of file handles to send + * @nfds: number of file handles in @fds + * @errp: pointer to a NULL-initialized error object + * + * + * Behaves like qio_channel_writev_full but will attempt + * to send all data passed (file handles and memory regions). + * The function will wait for all requested data + * to be written, yielding from the current coroutine + * if required. + * + * Returns: 0 if all bytes were written, or -1 on error + */ + +int qio_channel_writev_full_all(QIOChannel *ioc, + const struct iovec *iov, + size_t niov, + int *fds, size_t nfds, + Error **errp); + #endif /* QIO_CHANNEL_H */ diff --git a/io/channel.c b/io/channel.c index XXXXXXX..XXXXXXX 100644 --- a/io/channel.c +++ b/io/channel.c @@ -XXX,XX +XXX,XX @@ int qio_channel_writev_all(QIOChannel *ioc, const struct iovec *iov, size_t niov, Error **errp) +{ + return qio_channel_writev_full_all(ioc, iov, niov, NULL, 0, errp); +} + +int qio_channel_writev_full_all(QIOChannel *ioc, + const struct iovec *iov, + size_t niov, + int *fds, size_t nfds, + Error **errp) { int ret = -1; struct iovec *local_iov = g_new(struct iovec, niov); @@ -XXX,XX +XXX,XX @@ int qio_channel_writev_all(QIOChannel *ioc, while (nlocal_iov > 0) { ssize_t len; - len = qio_channel_writev(ioc, local_iov, nlocal_iov, errp); + len = qio_channel_writev_full(ioc, local_iov, nlocal_iov, fds, nfds, + errp); if (len == QIO_CHANNEL_ERR_BLOCK) { if (qemu_in_coroutine()) { qio_channel_yield(ioc, G_IO_OUT); @@ -XXX,XX +XXX,XX @@ int qio_channel_writev_all(QIOChannel *ioc, } iov_discard_front(&local_iov, &nlocal_iov, len); + + fds = NULL; + nfds = 0; } ret = 0; -- 2.29.2 From: Elena Ufimtseva <elena.ufimtseva@oracle.com> Adds qio_channel_readv_full_all_eof() and qio_channel_readv_full_all() to read both data and FDs. Refactors existing code to use these helpers. Signed-off-by: Elena Ufimtseva <elena.ufimtseva@oracle.com> Signed-off-by: John G Johnson <john.g.johnson@oracle.com> Signed-off-by: Jagannathan Raman <jag.raman@oracle.com> Acked-by: Daniel P. Berrangé <berrange@redhat.com> Message-id: b059c4cc0fb741e794d644c144cc21372cad877d.1611938319.git.jag.raman@oracle.com Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- include/io/channel.h | 53 +++++++++++++++++++++++ io/channel.c | 101 ++++++++++++++++++++++++++++++++++--------- 2 files changed, 134 insertions(+), 20 deletions(-) diff --git a/include/io/channel.h b/include/io/channel.h index XXXXXXX..XXXXXXX 100644 --- a/include/io/channel.h +++ b/include/io/channel.h @@ -XXX,XX +XXX,XX @@ void qio_channel_set_aio_fd_handler(QIOChannel *ioc, IOHandler *io_write, void *opaque); +/** + * qio_channel_readv_full_all_eof: + * @ioc: the channel object + * @iov: the array of memory regions to read data to + * @niov: the length of the @iov array + * @fds: an array of file handles to read + * @nfds: number of file handles in @fds + * @errp: pointer to a NULL-initialized error object + * + * + * Performs same function as qio_channel_readv_all_eof. + * Additionally, attempts to read file descriptors shared + * over the channel. The function will wait for all + * requested data to be read, yielding from the current + * coroutine if required. data refers to both file + * descriptors and the iovs. + * + * Returns: 1 if all bytes were read, 0 if end-of-file + * occurs without data, or -1 on error + */ + +int qio_channel_readv_full_all_eof(QIOChannel *ioc, + const struct iovec *iov, + size_t niov, + int **fds, size_t *nfds, + Error **errp); + +/** + * qio_channel_readv_full_all: + * @ioc: the channel object + * @iov: the array of memory regions to read data to + * @niov: the length of the @iov array + * @fds: an array of file handles to read + * @nfds: number of file handles in @fds + * @errp: pointer to a NULL-initialized error object + * + * + * Performs same function as qio_channel_readv_all_eof. + * Additionally, attempts to read file descriptors shared + * over the channel. The function will wait for all + * requested data to be read, yielding from the current + * coroutine if required. data refers to both file + * descriptors and the iovs. + * + * Returns: 0 if all bytes were read, or -1 on error + */ + +int qio_channel_readv_full_all(QIOChannel *ioc, + const struct iovec *iov, + size_t niov, + int **fds, size_t *nfds, + Error **errp); + /** * qio_channel_writev_full_all: * @ioc: the channel object diff --git a/io/channel.c b/io/channel.c index XXXXXXX..XXXXXXX 100644 --- a/io/channel.c +++ b/io/channel.c @@ -XXX,XX +XXX,XX @@ int qio_channel_readv_all_eof(QIOChannel *ioc, const struct iovec *iov, size_t niov, Error **errp) +{ + return qio_channel_readv_full_all_eof(ioc, iov, niov, NULL, NULL, errp); +} + +int qio_channel_readv_all(QIOChannel *ioc, + const struct iovec *iov, + size_t niov, + Error **errp) +{ + return qio_channel_readv_full_all(ioc, iov, niov, NULL, NULL, errp); +} + +int qio_channel_readv_full_all_eof(QIOChannel *ioc, + const struct iovec *iov, + size_t niov, + int **fds, size_t *nfds, + Error **errp) { int ret = -1; struct iovec *local_iov = g_new(struct iovec, niov); struct iovec *local_iov_head = local_iov; unsigned int nlocal_iov = niov; + int **local_fds = fds; + size_t *local_nfds = nfds; bool partial = false; + if (nfds) { + *nfds = 0; + } + + if (fds) { + *fds = NULL; + } + nlocal_iov = iov_copy(local_iov, nlocal_iov, iov, niov, 0, iov_size(iov, niov)); - while (nlocal_iov > 0) { + while ((nlocal_iov > 0) || local_fds) { ssize_t len; - len = qio_channel_readv(ioc, local_iov, nlocal_iov, errp); + len = qio_channel_readv_full(ioc, local_iov, nlocal_iov, local_fds, + local_nfds, errp); if (len == QIO_CHANNEL_ERR_BLOCK) { if (qemu_in_coroutine()) { qio_channel_yield(ioc, G_IO_IN); @@ -XXX,XX +XXX,XX @@ int qio_channel_readv_all_eof(QIOChannel *ioc, qio_channel_wait(ioc, G_IO_IN); } continue; - } else if (len < 0) { - goto cleanup; - } else if (len == 0) { - if (partial) { - error_setg(errp, - "Unexpected end-of-file before all bytes were read"); - } else { + } + + if (len == 0) { + if (local_nfds && *local_nfds) { + /* + * Got some FDs, but no data yet. This isn't an EOF + * scenario (yet), so carry on to try to read data + * on next loop iteration + */ + goto next_iter; + } else if (!partial) { + /* No fds and no data - EOF before any data read */ ret = 0; + goto cleanup; + } else { + len = -1; + error_setg(errp, + "Unexpected end-of-file before all data were read"); + /* Fallthrough into len < 0 handling */ + } + } + + if (len < 0) { + /* Close any FDs we previously received */ + if (nfds && fds) { + size_t i; + for (i = 0; i < (*nfds); i++) { + close((*fds)[i]); + } + g_free(*fds); + *fds = NULL; + *nfds = 0; } goto cleanup; } + if (nlocal_iov) { + iov_discard_front(&local_iov, &nlocal_iov, len); + } + +next_iter: partial = true; - iov_discard_front(&local_iov, &nlocal_iov, len); + local_fds = NULL; + local_nfds = NULL; } ret = 1; @@ -XXX,XX +XXX,XX @@ int qio_channel_readv_all_eof(QIOChannel *ioc, return ret; } -int qio_channel_readv_all(QIOChannel *ioc, - const struct iovec *iov, - size_t niov, - Error **errp) +int qio_channel_readv_full_all(QIOChannel *ioc, + const struct iovec *iov, + size_t niov, + int **fds, size_t *nfds, + Error **errp) { - int ret = qio_channel_readv_all_eof(ioc, iov, niov, errp); + int ret = qio_channel_readv_full_all_eof(ioc, iov, niov, fds, nfds, errp); if (ret == 0) { - ret = -1; - error_setg(errp, - "Unexpected end-of-file before all bytes were read"); - } else if (ret == 1) { - ret = 0; + error_prepend(errp, + "Unexpected end-of-file before all data were read."); + return -1; } + if (ret == 1) { + return 0; + } + return ret; } -- 2.29.2 From: Elena Ufimtseva <elena.ufimtseva@oracle.com> Defines MPQemuMsg, which is the message that is sent to the remote process. This message is sent over QIOChannel and is used to command the remote process to perform various tasks. Define transmission functions used by proxy and by remote. Signed-off-by: Jagannathan Raman <jag.raman@oracle.com> Signed-off-by: John G Johnson <john.g.johnson@oracle.com> Signed-off-by: Elena Ufimtseva <elena.ufimtseva@oracle.com> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Message-id: 56ca8bcf95195b2b195b08f6b9565b6d7410bce5.1611938319.git.jag.raman@oracle.com [Replace struct iovec send[2] = {0} with {} to make clang happy as suggested by Peter Maydell <peter.maydell@linaro.org>. --Stefan] Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- MAINTAINERS | 2 + meson.build | 1 + hw/remote/trace.h | 1 + include/hw/remote/mpqemu-link.h | 63 ++++++++++ include/sysemu/iothread.h | 6 + hw/remote/mpqemu-link.c | 205 ++++++++++++++++++++++++++++++++ iothread.c | 6 + hw/remote/meson.build | 1 + hw/remote/trace-events | 4 + 9 files changed, 289 insertions(+) create mode 100644 hw/remote/trace.h create mode 100644 include/hw/remote/mpqemu-link.h create mode 100644 hw/remote/mpqemu-link.c create mode 100644 hw/remote/trace-events diff --git a/MAINTAINERS b/MAINTAINERS index XXXXXXX..XXXXXXX 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -XXX,XX +XXX,XX @@ F: hw/pci-host/remote.c F: include/hw/pci-host/remote.h F: hw/remote/machine.c F: include/hw/remote/machine.h +F: hw/remote/mpqemu-link.c +F: include/hw/remote/mpqemu-link.h Build and test automation ------------------------- diff --git a/meson.build b/meson.build index XXXXXXX..XXXXXXX 100644 --- a/meson.build +++ b/meson.build @@ -XXX,XX +XXX,XX @@ if have_system 'net', 'softmmu', 'ui', + 'hw/remote', ] endif if have_system or have_user diff --git a/hw/remote/trace.h b/hw/remote/trace.h new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/hw/remote/trace.h @@ -0,0 +1 @@ +#include "trace/trace-hw_remote.h" diff --git a/include/hw/remote/mpqemu-link.h b/include/hw/remote/mpqemu-link.h new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/include/hw/remote/mpqemu-link.h @@ -XXX,XX +XXX,XX @@ +/* + * Communication channel between QEMU and remote device process + * + * Copyright © 2018, 2021 Oracle and/or its affiliates. + * + * This work is licensed under the terms of the GNU GPL, version 2 or later. + * See the COPYING file in the top-level directory. + * + */ + +#ifndef MPQEMU_LINK_H +#define MPQEMU_LINK_H + +#include "qom/object.h" +#include "qemu/thread.h" +#include "io/channel.h" + +#define REMOTE_MAX_FDS 8 + +#define MPQEMU_MSG_HDR_SIZE offsetof(MPQemuMsg, data.u64) + +/** + * MPQemuCmd: + * + * MPQemuCmd enum type to specify the command to be executed on the remote + * device. + * + * This uses a private protocol between QEMU and the remote process. vfio-user + * protocol would supersede this in the future. + * + */ +typedef enum { + MPQEMU_CMD_MAX, +} MPQemuCmd; + +/** + * MPQemuMsg: + * @cmd: The remote command + * @size: Size of the data to be shared + * @data: Structured data + * @fds: File descriptors to be shared with remote device + * + * MPQemuMsg Format of the message sent to the remote device from QEMU. + * + */ +typedef struct { + int cmd; + size_t size; + + union { + uint64_t u64; + } data; + + int fds[REMOTE_MAX_FDS]; + int num_fds; +} MPQemuMsg; + +bool mpqemu_msg_send(MPQemuMsg *msg, QIOChannel *ioc, Error **errp); +bool mpqemu_msg_recv(MPQemuMsg *msg, QIOChannel *ioc, Error **errp); + +bool mpqemu_msg_valid(MPQemuMsg *msg); + +#endif diff --git a/include/sysemu/iothread.h b/include/sysemu/iothread.h index XXXXXXX..XXXXXXX 100644 --- a/include/sysemu/iothread.h +++ b/include/sysemu/iothread.h @@ -XXX,XX +XXX,XX @@ IOThread *iothread_create(const char *id, Error **errp); void iothread_stop(IOThread *iothread); void iothread_destroy(IOThread *iothread); +/* + * Returns true if executing withing IOThread context, + * false otherwise. + */ +bool qemu_in_iothread(void); + #endif /* IOTHREAD_H */ diff --git a/hw/remote/mpqemu-link.c b/hw/remote/mpqemu-link.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/hw/remote/mpqemu-link.c @@ -XXX,XX +XXX,XX @@ +/* + * Communication channel between QEMU and remote device process + * + * Copyright © 2018, 2021 Oracle and/or its affiliates. + * + * This work is licensed under the terms of the GNU GPL, version 2 or later. + * See the COPYING file in the top-level directory. + * + */ + +#include "qemu/osdep.h" +#include "qemu-common.h" + +#include "qemu/module.h" +#include "hw/remote/mpqemu-link.h" +#include "qapi/error.h" +#include "qemu/iov.h" +#include "qemu/error-report.h" +#include "qemu/main-loop.h" +#include "io/channel.h" +#include "sysemu/iothread.h" +#include "trace.h" + +/* + * Send message over the ioc QIOChannel. + * This function is safe to call from: + * - main loop in co-routine context. Will block the main loop if not in + * co-routine context; + * - vCPU thread with no co-routine context and if the channel is not part + * of the main loop handling; + * - IOThread within co-routine context, outside of co-routine context + * will block IOThread; + * Returns true if no errors were encountered, false otherwise. + */ +bool mpqemu_msg_send(MPQemuMsg *msg, QIOChannel *ioc, Error **errp) +{ + ERRP_GUARD(); + bool iolock = qemu_mutex_iothread_locked(); + bool iothread = qemu_in_iothread(); + struct iovec send[2] = {}; + int *fds = NULL; + size_t nfds = 0; + bool ret = false; + + send[0].iov_base = msg; + send[0].iov_len = MPQEMU_MSG_HDR_SIZE; + + send[1].iov_base = (void *)&msg->data; + send[1].iov_len = msg->size; + + if (msg->num_fds) { + nfds = msg->num_fds; + fds = msg->fds; + } + + /* + * Dont use in IOThread out of co-routine context as + * it will block IOThread. + */ + assert(qemu_in_coroutine() || !iothread); + + /* + * Skip unlocking/locking iothread lock when the IOThread is running + * in co-routine context. Co-routine context is asserted above + * for IOThread case. + * Also skip lock handling while in a co-routine in the main context. + */ + if (iolock && !iothread && !qemu_in_coroutine()) { + qemu_mutex_unlock_iothread(); + } + + if (!qio_channel_writev_full_all(ioc, send, G_N_ELEMENTS(send), + fds, nfds, errp)) { + ret = true; + } else { + trace_mpqemu_send_io_error(msg->cmd, msg->size, nfds); + } + + if (iolock && !iothread && !qemu_in_coroutine()) { + /* See above comment why skip locking here. */ + qemu_mutex_lock_iothread(); + } + + return ret; +} + +/* + * Read message from the ioc QIOChannel. + * This function is safe to call from: + * - From main loop in co-routine context. Will block the main loop if not in + * co-routine context; + * - From vCPU thread with no co-routine context and if the channel is not part + * of the main loop handling; + * - From IOThread within co-routine context, outside of co-routine context + * will block IOThread; + */ +static ssize_t mpqemu_read(QIOChannel *ioc, void *buf, size_t len, int **fds, + size_t *nfds, Error **errp) +{ + ERRP_GUARD(); + struct iovec iov = { .iov_base = buf, .iov_len = len }; + bool iolock = qemu_mutex_iothread_locked(); + bool iothread = qemu_in_iothread(); + int ret = -1; + + /* + * Dont use in IOThread out of co-routine context as + * it will block IOThread. + */ + assert(qemu_in_coroutine() || !iothread); + + if (iolock && !iothread && !qemu_in_coroutine()) { + qemu_mutex_unlock_iothread(); + } + + ret = qio_channel_readv_full_all_eof(ioc, &iov, 1, fds, nfds, errp); + + if (iolock && !iothread && !qemu_in_coroutine()) { + qemu_mutex_lock_iothread(); + } + + return (ret <= 0) ? ret : iov.iov_len; +} + +bool mpqemu_msg_recv(MPQemuMsg *msg, QIOChannel *ioc, Error **errp) +{ + ERRP_GUARD(); + g_autofree int *fds = NULL; + size_t nfds = 0; + ssize_t len; + bool ret = false; + + len = mpqemu_read(ioc, msg, MPQEMU_MSG_HDR_SIZE, &fds, &nfds, errp); + if (len <= 0) { + goto fail; + } else if (len != MPQEMU_MSG_HDR_SIZE) { + error_setg(errp, "Message header corrupted"); + goto fail; + } + + if (msg->size > sizeof(msg->data)) { + error_setg(errp, "Invalid size for message"); + goto fail; + } + + if (!msg->size) { + goto copy_fds; + } + + len = mpqemu_read(ioc, &msg->data, msg->size, NULL, NULL, errp); + if (len <= 0) { + goto fail; + } + if (len != msg->size) { + error_setg(errp, "Unable to read full message"); + goto fail; + } + +copy_fds: + msg->num_fds = nfds; + if (nfds > G_N_ELEMENTS(msg->fds)) { + error_setg(errp, + "Overflow error: received %zu fds, more than max of %d fds", + nfds, REMOTE_MAX_FDS); + goto fail; + } + if (nfds) { + memcpy(msg->fds, fds, nfds * sizeof(int)); + } + + ret = true; + +fail: + if (*errp) { + trace_mpqemu_recv_io_error(msg->cmd, msg->size, nfds); + } + while (*errp && nfds) { + close(fds[nfds - 1]); + nfds--; + } + + return ret; +} + +bool mpqemu_msg_valid(MPQemuMsg *msg) +{ + if (msg->cmd >= MPQEMU_CMD_MAX && msg->cmd < 0) { + return false; + } + + /* Verify FDs. */ + if (msg->num_fds >= REMOTE_MAX_FDS) { + return false; + } + + if (msg->num_fds > 0) { + for (int i = 0; i < msg->num_fds; i++) { + if (fcntl(msg->fds[i], F_GETFL) == -1) { + return false; + } + } + } + + return true; +} diff --git a/iothread.c b/iothread.c index XXXXXXX..XXXXXXX 100644 --- a/iothread.c +++ b/iothread.c @@ -XXX,XX +XXX,XX @@ IOThread *iothread_by_id(const char *id) { return IOTHREAD(object_resolve_path_type(id, TYPE_IOTHREAD, NULL)); } + +bool qemu_in_iothread(void) +{ + return qemu_get_current_aio_context() == qemu_get_aio_context() ? + false : true; +} diff --git a/hw/remote/meson.build b/hw/remote/meson.build index XXXXXXX..XXXXXXX 100644 --- a/hw/remote/meson.build +++ b/hw/remote/meson.build @@ -XXX,XX +XXX,XX @@ remote_ss = ss.source_set() remote_ss.add(when: 'CONFIG_MULTIPROCESS', if_true: files('machine.c')) +remote_ss.add(when: 'CONFIG_MULTIPROCESS', if_true: files('mpqemu-link.c')) softmmu_ss.add_all(when: 'CONFIG_MULTIPROCESS', if_true: remote_ss) diff --git a/hw/remote/trace-events b/hw/remote/trace-events new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/hw/remote/trace-events @@ -XXX,XX +XXX,XX @@ +# multi-process trace events + +mpqemu_send_io_error(int cmd, int size, int nfds) "send command %d size %d, %d file descriptors to remote process" +mpqemu_recv_io_error(int cmd, int size, int nfds) "failed to receive %d size %d, %d file descriptors to remote process" -- 2.29.2 From: Jagannathan Raman <jag.raman@oracle.com> Initializes the message handler function in the remote process. It is called whenever there's an event pending on QIOChannel that registers this function. Signed-off-by: Elena Ufimtseva <elena.ufimtseva@oracle.com> Signed-off-by: John G Johnson <john.g.johnson@oracle.com> Signed-off-by: Jagannathan Raman <jag.raman@oracle.com> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Message-id: 99d38d8b93753a6409ac2340e858858cda59ab1b.1611938319.git.jag.raman@oracle.com Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- MAINTAINERS | 1 + include/hw/remote/machine.h | 9 ++++++ hw/remote/message.c | 57 +++++++++++++++++++++++++++++++++++++ hw/remote/meson.build | 1 + 4 files changed, 68 insertions(+) create mode 100644 hw/remote/message.c diff --git a/MAINTAINERS b/MAINTAINERS index XXXXXXX..XXXXXXX 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -XXX,XX +XXX,XX @@ F: hw/remote/machine.c F: include/hw/remote/machine.h F: hw/remote/mpqemu-link.c F: include/hw/remote/mpqemu-link.h +F: hw/remote/message.c Build and test automation ------------------------- diff --git a/include/hw/remote/machine.h b/include/hw/remote/machine.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/remote/machine.h +++ b/include/hw/remote/machine.h @@ -XXX,XX +XXX,XX @@ #include "qom/object.h" #include "hw/boards.h" #include "hw/pci-host/remote.h" +#include "io/channel.h" struct RemoteMachineState { MachineState parent_obj; @@ -XXX,XX +XXX,XX @@ struct RemoteMachineState { RemotePCIHost *host; }; +/* Used to pass to co-routine device and ioc. */ +typedef struct RemoteCommDev { + PCIDevice *dev; + QIOChannel *ioc; +} RemoteCommDev; + #define TYPE_REMOTE_MACHINE "x-remote-machine" OBJECT_DECLARE_SIMPLE_TYPE(RemoteMachineState, REMOTE_MACHINE) +void coroutine_fn mpqemu_remote_msg_loop_co(void *data); + #endif diff --git a/hw/remote/message.c b/hw/remote/message.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/hw/remote/message.c @@ -XXX,XX +XXX,XX @@ +/* + * Copyright © 2020, 2021 Oracle and/or its affiliates. + * + * This work is licensed under the terms of the GNU GPL-v2, version 2 or later. + * + * See the COPYING file in the top-level directory. + * + */ + +#include "qemu/osdep.h" +#include "qemu-common.h" + +#include "hw/remote/machine.h" +#include "io/channel.h" +#include "hw/remote/mpqemu-link.h" +#include "qapi/error.h" +#include "sysemu/runstate.h" + +void coroutine_fn mpqemu_remote_msg_loop_co(void *data) +{ + g_autofree RemoteCommDev *com = (RemoteCommDev *)data; + PCIDevice *pci_dev = NULL; + Error *local_err = NULL; + + assert(com->ioc); + + pci_dev = com->dev; + for (; !local_err;) { + MPQemuMsg msg = {0}; + + if (!mpqemu_msg_recv(&msg, com->ioc, &local_err)) { + break; + } + + if (!mpqemu_msg_valid(&msg)) { + error_setg(&local_err, "Received invalid message from proxy" + "in remote process pid="FMT_pid"", + getpid()); + break; + } + + switch (msg.cmd) { + default: + error_setg(&local_err, + "Unknown command (%d) received for device %s" + " (pid="FMT_pid")", + msg.cmd, DEVICE(pci_dev)->id, getpid()); + } + } + + if (local_err) { + error_report_err(local_err); + qemu_system_shutdown_request(SHUTDOWN_CAUSE_HOST_ERROR); + } else { + qemu_system_shutdown_request(SHUTDOWN_CAUSE_GUEST_SHUTDOWN); + } +} diff --git a/hw/remote/meson.build b/hw/remote/meson.build index XXXXXXX..XXXXXXX 100644 --- a/hw/remote/meson.build +++ b/hw/remote/meson.build @@ -XXX,XX +XXX,XX @@ remote_ss = ss.source_set() remote_ss.add(when: 'CONFIG_MULTIPROCESS', if_true: files('machine.c')) remote_ss.add(when: 'CONFIG_MULTIPROCESS', if_true: files('mpqemu-link.c')) +remote_ss.add(when: 'CONFIG_MULTIPROCESS', if_true: files('message.c')) softmmu_ss.add_all(when: 'CONFIG_MULTIPROCESS', if_true: remote_ss) -- 2.29.2 From: Jagannathan Raman <jag.raman@oracle.com> Associate the file descriptor for a PCIDevice in remote process with DeviceState object. Signed-off-by: Elena Ufimtseva <elena.ufimtseva@oracle.com> Signed-off-by: John G Johnson <john.g.johnson@oracle.com> Signed-off-by: Jagannathan Raman <jag.raman@oracle.com> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Message-id: f405a2ed5d7518b87bea7c59cfdf334d67e5ee51.1611938319.git.jag.raman@oracle.com Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- MAINTAINERS | 1 + hw/remote/remote-obj.c | 203 +++++++++++++++++++++++++++++++++++++++++ hw/remote/meson.build | 1 + 3 files changed, 205 insertions(+) create mode 100644 hw/remote/remote-obj.c diff --git a/MAINTAINERS b/MAINTAINERS index XXXXXXX..XXXXXXX 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -XXX,XX +XXX,XX @@ F: include/hw/remote/machine.h F: hw/remote/mpqemu-link.c F: include/hw/remote/mpqemu-link.h F: hw/remote/message.c +F: hw/remote/remote-obj.c Build and test automation ------------------------- diff --git a/hw/remote/remote-obj.c b/hw/remote/remote-obj.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/hw/remote/remote-obj.c @@ -XXX,XX +XXX,XX @@ +/* + * Copyright © 2020, 2021 Oracle and/or its affiliates. + * + * This work is licensed under the terms of the GNU GPL-v2, version 2 or later. + * + * See the COPYING file in the top-level directory. + * + */ + +#include "qemu/osdep.h" +#include "qemu-common.h" + +#include "qemu/error-report.h" +#include "qemu/notify.h" +#include "qom/object_interfaces.h" +#include "hw/qdev-core.h" +#include "io/channel.h" +#include "hw/qdev-core.h" +#include "hw/remote/machine.h" +#include "io/channel-util.h" +#include "qapi/error.h" +#include "sysemu/sysemu.h" +#include "hw/pci/pci.h" +#include "qemu/sockets.h" +#include "monitor/monitor.h" + +#define TYPE_REMOTE_OBJECT "x-remote-object" +OBJECT_DECLARE_TYPE(RemoteObject, RemoteObjectClass, REMOTE_OBJECT) + +struct RemoteObjectClass { + ObjectClass parent_class; + + unsigned int nr_devs; + unsigned int max_devs; +}; + +struct RemoteObject { + /* private */ + Object parent; + + Notifier machine_done; + + int32_t fd; + char *devid; + + QIOChannel *ioc; + + DeviceState *dev; + DeviceListener listener; +}; + +static void remote_object_set_fd(Object *obj, const char *str, Error **errp) +{ + RemoteObject *o = REMOTE_OBJECT(obj); + int fd = -1; + + fd = monitor_fd_param(monitor_cur(), str, errp); + if (fd == -1) { + error_prepend(errp, "Could not parse remote object fd %s:", str); + return; + } + + if (!fd_is_socket(fd)) { + error_setg(errp, "File descriptor '%s' is not a socket", str); + close(fd); + return; + } + + o->fd = fd; +} + +static void remote_object_set_devid(Object *obj, const char *str, Error **errp) +{ + RemoteObject *o = REMOTE_OBJECT(obj); + + g_free(o->devid); + + o->devid = g_strdup(str); +} + +static void remote_object_unrealize_listener(DeviceListener *listener, + DeviceState *dev) +{ + RemoteObject *o = container_of(listener, RemoteObject, listener); + + if (o->dev == dev) { + object_unref(OBJECT(o)); + } +} + +static void remote_object_machine_done(Notifier *notifier, void *data) +{ + RemoteObject *o = container_of(notifier, RemoteObject, machine_done); + DeviceState *dev = NULL; + QIOChannel *ioc = NULL; + Coroutine *co = NULL; + RemoteCommDev *comdev = NULL; + Error *err = NULL; + + dev = qdev_find_recursive(sysbus_get_default(), o->devid); + if (!dev || !object_dynamic_cast(OBJECT(dev), TYPE_PCI_DEVICE)) { + error_report("%s is not a PCI device", o->devid); + return; + } + + ioc = qio_channel_new_fd(o->fd, &err); + if (!ioc) { + error_report_err(err); + return; + } + qio_channel_set_blocking(ioc, false, NULL); + + o->dev = dev; + + o->listener.unrealize = remote_object_unrealize_listener; + device_listener_register(&o->listener); + + /* co-routine should free this. */ + comdev = g_new0(RemoteCommDev, 1); + *comdev = (RemoteCommDev) { + .ioc = ioc, + .dev = PCI_DEVICE(dev), + }; + + co = qemu_coroutine_create(mpqemu_remote_msg_loop_co, comdev); + qemu_coroutine_enter(co); +} + +static void remote_object_init(Object *obj) +{ + RemoteObjectClass *k = REMOTE_OBJECT_GET_CLASS(obj); + RemoteObject *o = REMOTE_OBJECT(obj); + + if (k->nr_devs >= k->max_devs) { + error_report("Reached maximum number of devices: %u", k->max_devs); + return; + } + + o->ioc = NULL; + o->fd = -1; + o->devid = NULL; + + k->nr_devs++; + + o->machine_done.notify = remote_object_machine_done; + qemu_add_machine_init_done_notifier(&o->machine_done); +} + +static void remote_object_finalize(Object *obj) +{ + RemoteObjectClass *k = REMOTE_OBJECT_GET_CLASS(obj); + RemoteObject *o = REMOTE_OBJECT(obj); + + device_listener_unregister(&o->listener); + + if (o->ioc) { + qio_channel_shutdown(o->ioc, QIO_CHANNEL_SHUTDOWN_BOTH, NULL); + qio_channel_close(o->ioc, NULL); + } + + object_unref(OBJECT(o->ioc)); + + k->nr_devs--; + g_free(o->devid); +} + +static void remote_object_class_init(ObjectClass *klass, void *data) +{ + RemoteObjectClass *k = REMOTE_OBJECT_CLASS(klass); + + /* + * Limit number of supported devices to 1. This is done to avoid devices + * from one VM accessing the RAM of another VM. This is done until we + * start using separate address spaces for individual devices. + */ + k->max_devs = 1; + k->nr_devs = 0; + + object_class_property_add_str(klass, "fd", NULL, remote_object_set_fd); + object_class_property_add_str(klass, "devid", NULL, + remote_object_set_devid); +} + +static const TypeInfo remote_object_info = { + .name = TYPE_REMOTE_OBJECT, + .parent = TYPE_OBJECT, + .instance_size = sizeof(RemoteObject), + .instance_init = remote_object_init, + .instance_finalize = remote_object_finalize, + .class_size = sizeof(RemoteObjectClass), + .class_init = remote_object_class_init, + .interfaces = (InterfaceInfo[]) { + { TYPE_USER_CREATABLE }, + { } + } +}; + +static void register_types(void) +{ + type_register_static(&remote_object_info); +} + +type_init(register_types); diff --git a/hw/remote/meson.build b/hw/remote/meson.build index XXXXXXX..XXXXXXX 100644 --- a/hw/remote/meson.build +++ b/hw/remote/meson.build @@ -XXX,XX +XXX,XX @@ remote_ss = ss.source_set() remote_ss.add(when: 'CONFIG_MULTIPROCESS', if_true: files('machine.c')) remote_ss.add(when: 'CONFIG_MULTIPROCESS', if_true: files('mpqemu-link.c')) remote_ss.add(when: 'CONFIG_MULTIPROCESS', if_true: files('message.c')) +remote_ss.add(when: 'CONFIG_MULTIPROCESS', if_true: files('remote-obj.c')) softmmu_ss.add_all(when: 'CONFIG_MULTIPROCESS', if_true: remote_ss) -- 2.29.2 From: Jagannathan Raman <jag.raman@oracle.com> SyncSysMemMsg message format is defined. It is used to send file descriptors of the RAM regions to remote device. RAM on the remote device is configured with a set of file descriptors. Old RAM regions are deleted and new regions, each with an fd, is added to the RAM. Signed-off-by: Jagannathan Raman <jag.raman@oracle.com> Signed-off-by: John G Johnson <john.g.johnson@oracle.com> Signed-off-by: Elena Ufimtseva <elena.ufimtseva@oracle.com> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Message-id: 7d2d1831d812e85f681e7a8ab99e032cf4704689.1611938319.git.jag.raman@oracle.com Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- MAINTAINERS | 2 + include/hw/remote/memory.h | 19 ++++++++++ include/hw/remote/mpqemu-link.h | 10 +++++ hw/remote/memory.c | 65 +++++++++++++++++++++++++++++++++ hw/remote/mpqemu-link.c | 11 ++++++ hw/remote/meson.build | 2 + 6 files changed, 109 insertions(+) create mode 100644 include/hw/remote/memory.h create mode 100644 hw/remote/memory.c diff --git a/MAINTAINERS b/MAINTAINERS index XXXXXXX..XXXXXXX 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -XXX,XX +XXX,XX @@ F: hw/remote/mpqemu-link.c F: include/hw/remote/mpqemu-link.h F: hw/remote/message.c F: hw/remote/remote-obj.c +F: include/hw/remote/memory.h +F: hw/remote/memory.c Build and test automation ------------------------- diff --git a/include/hw/remote/memory.h b/include/hw/remote/memory.h new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/include/hw/remote/memory.h @@ -XXX,XX +XXX,XX @@ +/* + * Memory manager for remote device + * + * Copyright © 2018, 2021 Oracle and/or its affiliates. + * + * This work is licensed under the terms of the GNU GPL, version 2 or later. + * See the COPYING file in the top-level directory. + * + */ + +#ifndef REMOTE_MEMORY_H +#define REMOTE_MEMORY_H + +#include "exec/hwaddr.h" +#include "hw/remote/mpqemu-link.h" + +void remote_sysmem_reconfig(MPQemuMsg *msg, Error **errp); + +#endif diff --git a/include/hw/remote/mpqemu-link.h b/include/hw/remote/mpqemu-link.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/remote/mpqemu-link.h +++ b/include/hw/remote/mpqemu-link.h @@ -XXX,XX +XXX,XX @@ #include "qom/object.h" #include "qemu/thread.h" #include "io/channel.h" +#include "exec/hwaddr.h" #define REMOTE_MAX_FDS 8 @@ -XXX,XX +XXX,XX @@ * */ typedef enum { + MPQEMU_CMD_SYNC_SYSMEM, MPQEMU_CMD_MAX, } MPQemuCmd; +typedef struct { + hwaddr gpas[REMOTE_MAX_FDS]; + uint64_t sizes[REMOTE_MAX_FDS]; + off_t offsets[REMOTE_MAX_FDS]; +} SyncSysmemMsg; + /** * MPQemuMsg: * @cmd: The remote command @@ -XXX,XX +XXX,XX @@ typedef enum { * MPQemuMsg Format of the message sent to the remote device from QEMU. * */ + typedef struct { int cmd; size_t size; union { uint64_t u64; + SyncSysmemMsg sync_sysmem; } data; int fds[REMOTE_MAX_FDS]; diff --git a/hw/remote/memory.c b/hw/remote/memory.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/hw/remote/memory.c @@ -XXX,XX +XXX,XX @@ +/* + * Memory manager for remote device + * + * Copyright © 2018, 2021 Oracle and/or its affiliates. + * + * This work is licensed under the terms of the GNU GPL, version 2 or later. + * See the COPYING file in the top-level directory. + * + */ + +#include "qemu/osdep.h" +#include "qemu-common.h" + +#include "hw/remote/memory.h" +#include "exec/address-spaces.h" +#include "exec/ram_addr.h" +#include "qapi/error.h" + +static void remote_sysmem_reset(void) +{ + MemoryRegion *sysmem, *subregion, *next; + + sysmem = get_system_memory(); + + QTAILQ_FOREACH_SAFE(subregion, &sysmem->subregions, subregions_link, next) { + if (subregion->ram) { + memory_region_del_subregion(sysmem, subregion); + object_unparent(OBJECT(subregion)); + } + } +} + +void remote_sysmem_reconfig(MPQemuMsg *msg, Error **errp) +{ + ERRP_GUARD(); + SyncSysmemMsg *sysmem_info = &msg->data.sync_sysmem; + MemoryRegion *sysmem, *subregion; + static unsigned int suffix; + int region; + + sysmem = get_system_memory(); + + remote_sysmem_reset(); + + for (region = 0; region < msg->num_fds; region++) { + g_autofree char *name; + subregion = g_new(MemoryRegion, 1); + name = g_strdup_printf("remote-mem-%u", suffix++); + memory_region_init_ram_from_fd(subregion, NULL, + name, sysmem_info->sizes[region], + true, msg->fds[region], + sysmem_info->offsets[region], + errp); + + if (*errp) { + g_free(subregion); + remote_sysmem_reset(); + return; + } + + memory_region_add_subregion(sysmem, sysmem_info->gpas[region], + subregion); + + } +} diff --git a/hw/remote/mpqemu-link.c b/hw/remote/mpqemu-link.c index XXXXXXX..XXXXXXX 100644 --- a/hw/remote/mpqemu-link.c +++ b/hw/remote/mpqemu-link.c @@ -XXX,XX +XXX,XX @@ bool mpqemu_msg_valid(MPQemuMsg *msg) } } + /* Verify message specific fields. */ + switch (msg->cmd) { + case MPQEMU_CMD_SYNC_SYSMEM: + if (msg->num_fds == 0 || msg->size != sizeof(SyncSysmemMsg)) { + return false; + } + break; + default: + break; + } + return true; } diff --git a/hw/remote/meson.build b/hw/remote/meson.build index XXXXXXX..XXXXXXX 100644 --- a/hw/remote/meson.build +++ b/hw/remote/meson.build @@ -XXX,XX +XXX,XX @@ remote_ss.add(when: 'CONFIG_MULTIPROCESS', if_true: files('mpqemu-link.c')) remote_ss.add(when: 'CONFIG_MULTIPROCESS', if_true: files('message.c')) remote_ss.add(when: 'CONFIG_MULTIPROCESS', if_true: files('remote-obj.c')) +specific_ss.add(when: 'CONFIG_MULTIPROCESS', if_true: files('memory.c')) + softmmu_ss.add_all(when: 'CONFIG_MULTIPROCESS', if_true: remote_ss) -- 2.29.2 From: Elena Ufimtseva <elena.ufimtseva@oracle.com> Defines a PCI Device proxy object as a child of TYPE_PCI_DEVICE. Signed-off-by: Elena Ufimtseva <elena.ufimtseva@oracle.com> Signed-off-by: Jagannathan Raman <jag.raman@oracle.com> Signed-off-by: John G Johnson <john.g.johnson@oracle.com> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Message-id: b5186ebfedf8e557044d09a768846c59230ad3a7.1611938319.git.jag.raman@oracle.com Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- MAINTAINERS | 2 + include/hw/remote/proxy.h | 33 +++++++++++++ hw/remote/proxy.c | 99 +++++++++++++++++++++++++++++++++++++++ hw/remote/meson.build | 1 + 4 files changed, 135 insertions(+) create mode 100644 include/hw/remote/proxy.h create mode 100644 hw/remote/proxy.c diff --git a/MAINTAINERS b/MAINTAINERS index XXXXXXX..XXXXXXX 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -XXX,XX +XXX,XX @@ F: hw/remote/message.c F: hw/remote/remote-obj.c F: include/hw/remote/memory.h F: hw/remote/memory.c +F: hw/remote/proxy.c +F: include/hw/remote/proxy.h Build and test automation ------------------------- diff --git a/include/hw/remote/proxy.h b/include/hw/remote/proxy.h new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/include/hw/remote/proxy.h @@ -XXX,XX +XXX,XX @@ +/* + * Copyright © 2018, 2021 Oracle and/or its affiliates. + * + * This work is licensed under the terms of the GNU GPL, version 2 or later. + * See the COPYING file in the top-level directory. + * + */ + +#ifndef PROXY_H +#define PROXY_H + +#include "hw/pci/pci.h" +#include "io/channel.h" + +#define TYPE_PCI_PROXY_DEV "x-pci-proxy-dev" +OBJECT_DECLARE_SIMPLE_TYPE(PCIProxyDev, PCI_PROXY_DEV) + +struct PCIProxyDev { + PCIDevice parent_dev; + char *fd; + + /* + * Mutex used to protect the QIOChannel fd from + * the concurrent access by the VCPUs since proxy + * blocks while awaiting for the replies from the + * process remote. + */ + QemuMutex io_mutex; + QIOChannel *ioc; + Error *migration_blocker; +}; + +#endif /* PROXY_H */ diff --git a/hw/remote/proxy.c b/hw/remote/proxy.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/hw/remote/proxy.c @@ -XXX,XX +XXX,XX @@ +/* + * Copyright © 2018, 2021 Oracle and/or its affiliates. + * + * This work is licensed under the terms of the GNU GPL, version 2 or later. + * See the COPYING file in the top-level directory. + * + */ + +#include "qemu/osdep.h" +#include "qemu-common.h" + +#include "hw/remote/proxy.h" +#include "hw/pci/pci.h" +#include "qapi/error.h" +#include "io/channel-util.h" +#include "hw/qdev-properties.h" +#include "monitor/monitor.h" +#include "migration/blocker.h" +#include "qemu/sockets.h" + +static void pci_proxy_dev_realize(PCIDevice *device, Error **errp) +{ + ERRP_GUARD(); + PCIProxyDev *dev = PCI_PROXY_DEV(device); + int fd; + + if (!dev->fd) { + error_setg(errp, "fd parameter not specified for %s", + DEVICE(device)->id); + return; + } + + fd = monitor_fd_param(monitor_cur(), dev->fd, errp); + if (fd == -1) { + error_prepend(errp, "proxy: unable to parse fd %s: ", dev->fd); + return; + } + + if (!fd_is_socket(fd)) { + error_setg(errp, "proxy: fd %d is not a socket", fd); + close(fd); + return; + } + + dev->ioc = qio_channel_new_fd(fd, errp); + + error_setg(&dev->migration_blocker, "%s does not support migration", + TYPE_PCI_PROXY_DEV); + migrate_add_blocker(dev->migration_blocker, errp); + + qemu_mutex_init(&dev->io_mutex); + qio_channel_set_blocking(dev->ioc, true, NULL); +} + +static void pci_proxy_dev_exit(PCIDevice *pdev) +{ + PCIProxyDev *dev = PCI_PROXY_DEV(pdev); + + if (dev->ioc) { + qio_channel_close(dev->ioc, NULL); + } + + migrate_del_blocker(dev->migration_blocker); + + error_free(dev->migration_blocker); +} + +static Property proxy_properties[] = { + DEFINE_PROP_STRING("fd", PCIProxyDev, fd), + DEFINE_PROP_END_OF_LIST(), +}; + +static void pci_proxy_dev_class_init(ObjectClass *klass, void *data) +{ + DeviceClass *dc = DEVICE_CLASS(klass); + PCIDeviceClass *k = PCI_DEVICE_CLASS(klass); + + k->realize = pci_proxy_dev_realize; + k->exit = pci_proxy_dev_exit; + device_class_set_props(dc, proxy_properties); +} + +static const TypeInfo pci_proxy_dev_type_info = { + .name = TYPE_PCI_PROXY_DEV, + .parent = TYPE_PCI_DEVICE, + .instance_size = sizeof(PCIProxyDev), + .class_init = pci_proxy_dev_class_init, + .interfaces = (InterfaceInfo[]) { + { INTERFACE_CONVENTIONAL_PCI_DEVICE }, + { }, + }, +}; + +static void pci_proxy_dev_register_types(void) +{ + type_register_static(&pci_proxy_dev_type_info); +} + +type_init(pci_proxy_dev_register_types) diff --git a/hw/remote/meson.build b/hw/remote/meson.build index XXXXXXX..XXXXXXX 100644 --- a/hw/remote/meson.build +++ b/hw/remote/meson.build @@ -XXX,XX +XXX,XX @@ remote_ss.add(when: 'CONFIG_MULTIPROCESS', if_true: files('machine.c')) remote_ss.add(when: 'CONFIG_MULTIPROCESS', if_true: files('mpqemu-link.c')) remote_ss.add(when: 'CONFIG_MULTIPROCESS', if_true: files('message.c')) remote_ss.add(when: 'CONFIG_MULTIPROCESS', if_true: files('remote-obj.c')) +remote_ss.add(when: 'CONFIG_MULTIPROCESS', if_true: files('proxy.c')) specific_ss.add(when: 'CONFIG_MULTIPROCESS', if_true: files('memory.c')) -- 2.29.2 From: Elena Ufimtseva <elena.ufimtseva@oracle.com> Signed-off-by: Elena Ufimtseva <elena.ufimtseva@oracle.com> Signed-off-by: Jagannathan Raman <jag.raman@oracle.com> Signed-off-by: John G Johnson <john.g.johnson@oracle.com> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Message-id: d54edb4176361eed86b903e8f27058363b6c83b3.1611938319.git.jag.raman@oracle.com Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- include/hw/remote/mpqemu-link.h | 4 ++++ hw/remote/mpqemu-link.c | 34 +++++++++++++++++++++++++++++++++ 2 files changed, 38 insertions(+) diff --git a/include/hw/remote/mpqemu-link.h b/include/hw/remote/mpqemu-link.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/remote/mpqemu-link.h +++ b/include/hw/remote/mpqemu-link.h @@ -XXX,XX +XXX,XX @@ #include "qemu/thread.h" #include "io/channel.h" #include "exec/hwaddr.h" +#include "io/channel-socket.h" +#include "hw/remote/proxy.h" #define REMOTE_MAX_FDS 8 @@ -XXX,XX +XXX,XX @@ typedef struct { bool mpqemu_msg_send(MPQemuMsg *msg, QIOChannel *ioc, Error **errp); bool mpqemu_msg_recv(MPQemuMsg *msg, QIOChannel *ioc, Error **errp); +uint64_t mpqemu_msg_send_and_await_reply(MPQemuMsg *msg, PCIProxyDev *pdev, + Error **errp); bool mpqemu_msg_valid(MPQemuMsg *msg); #endif diff --git a/hw/remote/mpqemu-link.c b/hw/remote/mpqemu-link.c index XXXXXXX..XXXXXXX 100644 --- a/hw/remote/mpqemu-link.c +++ b/hw/remote/mpqemu-link.c @@ -XXX,XX +XXX,XX @@ fail: return ret; } +/* + * Send msg and wait for a reply with command code RET_MSG. + * Returns the message received of size u64 or UINT64_MAX + * on error. + * Called from VCPU thread in non-coroutine context. + * Used by the Proxy object to communicate to remote processes. + */ +uint64_t mpqemu_msg_send_and_await_reply(MPQemuMsg *msg, PCIProxyDev *pdev, + Error **errp) +{ + ERRP_GUARD(); + MPQemuMsg msg_reply = {0}; + uint64_t ret = UINT64_MAX; + + assert(!qemu_in_coroutine()); + + QEMU_LOCK_GUARD(&pdev->io_mutex); + if (!mpqemu_msg_send(msg, pdev->ioc, errp)) { + return ret; + } + + if (!mpqemu_msg_recv(&msg_reply, pdev->ioc, errp)) { + return ret; + } + + if (!mpqemu_msg_valid(&msg_reply)) { + error_setg(errp, "ERROR: Invalid reply received for command %d", + msg->cmd); + return ret; + } + + return msg_reply.data.u64; +} + bool mpqemu_msg_valid(MPQemuMsg *msg) { if (msg->cmd >= MPQEMU_CMD_MAX && msg->cmd < 0) { -- 2.29.2 From: Elena Ufimtseva <elena.ufimtseva@oracle.com> The Proxy Object sends the PCI config space accesses as messages to the remote process over the communication channel Signed-off-by: Elena Ufimtseva <elena.ufimtseva@oracle.com> Signed-off-by: Jagannathan Raman <jag.raman@oracle.com> Signed-off-by: John G Johnson <john.g.johnson@oracle.com> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Message-id: d3c94f4618813234655356c60e6f0d0362ff42d6.1611938319.git.jag.raman@oracle.com Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- include/hw/remote/mpqemu-link.h | 10 ++++++ hw/remote/message.c | 60 +++++++++++++++++++++++++++++++++ hw/remote/mpqemu-link.c | 8 ++++- hw/remote/proxy.c | 55 ++++++++++++++++++++++++++++++ 4 files changed, 132 insertions(+), 1 deletion(-) diff --git a/include/hw/remote/mpqemu-link.h b/include/hw/remote/mpqemu-link.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/remote/mpqemu-link.h +++ b/include/hw/remote/mpqemu-link.h @@ -XXX,XX +XXX,XX @@ */ typedef enum { MPQEMU_CMD_SYNC_SYSMEM, + MPQEMU_CMD_RET, + MPQEMU_CMD_PCI_CFGWRITE, + MPQEMU_CMD_PCI_CFGREAD, MPQEMU_CMD_MAX, } MPQemuCmd; @@ -XXX,XX +XXX,XX @@ typedef struct { off_t offsets[REMOTE_MAX_FDS]; } SyncSysmemMsg; +typedef struct { + uint32_t addr; + uint32_t val; + int len; +} PciConfDataMsg; + /** * MPQemuMsg: * @cmd: The remote command @@ -XXX,XX +XXX,XX @@ typedef struct { union { uint64_t u64; + PciConfDataMsg pci_conf_data; SyncSysmemMsg sync_sysmem; } data; diff --git a/hw/remote/message.c b/hw/remote/message.c index XXXXXXX..XXXXXXX 100644 --- a/hw/remote/message.c +++ b/hw/remote/message.c @@ -XXX,XX +XXX,XX @@ #include "hw/remote/mpqemu-link.h" #include "qapi/error.h" #include "sysemu/runstate.h" +#include "hw/pci/pci.h" + +static void process_config_write(QIOChannel *ioc, PCIDevice *dev, + MPQemuMsg *msg, Error **errp); +static void process_config_read(QIOChannel *ioc, PCIDevice *dev, + MPQemuMsg *msg, Error **errp); void coroutine_fn mpqemu_remote_msg_loop_co(void *data) { @@ -XXX,XX +XXX,XX @@ void coroutine_fn mpqemu_remote_msg_loop_co(void *data) } switch (msg.cmd) { + case MPQEMU_CMD_PCI_CFGWRITE: + process_config_write(com->ioc, pci_dev, &msg, &local_err); + break; + case MPQEMU_CMD_PCI_CFGREAD: + process_config_read(com->ioc, pci_dev, &msg, &local_err); + break; default: error_setg(&local_err, "Unknown command (%d) received for device %s" @@ -XXX,XX +XXX,XX @@ void coroutine_fn mpqemu_remote_msg_loop_co(void *data) qemu_system_shutdown_request(SHUTDOWN_CAUSE_GUEST_SHUTDOWN); } } + +static void process_config_write(QIOChannel *ioc, PCIDevice *dev, + MPQemuMsg *msg, Error **errp) +{ + ERRP_GUARD(); + PciConfDataMsg *conf = (PciConfDataMsg *)&msg->data.pci_conf_data; + MPQemuMsg ret = { 0 }; + + if ((conf->addr + sizeof(conf->val)) > pci_config_size(dev)) { + error_setg(errp, "Bad address for PCI config write, pid "FMT_pid".", + getpid()); + ret.data.u64 = UINT64_MAX; + } else { + pci_default_write_config(dev, conf->addr, conf->val, conf->len); + } + + ret.cmd = MPQEMU_CMD_RET; + ret.size = sizeof(ret.data.u64); + + if (!mpqemu_msg_send(&ret, ioc, NULL)) { + error_prepend(errp, "Error returning code to proxy, pid "FMT_pid": ", + getpid()); + } +} + +static void process_config_read(QIOChannel *ioc, PCIDevice *dev, + MPQemuMsg *msg, Error **errp) +{ + ERRP_GUARD(); + PciConfDataMsg *conf = (PciConfDataMsg *)&msg->data.pci_conf_data; + MPQemuMsg ret = { 0 }; + + if ((conf->addr + sizeof(conf->val)) > pci_config_size(dev)) { + error_setg(errp, "Bad address for PCI config read, pid "FMT_pid".", + getpid()); + ret.data.u64 = UINT64_MAX; + } else { + ret.data.u64 = pci_default_read_config(dev, conf->addr, conf->len); + } + + ret.cmd = MPQEMU_CMD_RET; + ret.size = sizeof(ret.data.u64); + + if (!mpqemu_msg_send(&ret, ioc, NULL)) { + error_prepend(errp, "Error returning code to proxy, pid "FMT_pid": ", + getpid()); + } +} diff --git a/hw/remote/mpqemu-link.c b/hw/remote/mpqemu-link.c index XXXXXXX..XXXXXXX 100644 --- a/hw/remote/mpqemu-link.c +++ b/hw/remote/mpqemu-link.c @@ -XXX,XX +XXX,XX @@ uint64_t mpqemu_msg_send_and_await_reply(MPQemuMsg *msg, PCIProxyDev *pdev, return ret; } - if (!mpqemu_msg_valid(&msg_reply)) { + if (!mpqemu_msg_valid(&msg_reply) || msg_reply.cmd != MPQEMU_CMD_RET) { error_setg(errp, "ERROR: Invalid reply received for command %d", msg->cmd); return ret; @@ -XXX,XX +XXX,XX @@ bool mpqemu_msg_valid(MPQemuMsg *msg) return false; } break; + case MPQEMU_CMD_PCI_CFGWRITE: + case MPQEMU_CMD_PCI_CFGREAD: + if (msg->size != sizeof(PciConfDataMsg)) { + return false; + } + break; default: break; } diff --git a/hw/remote/proxy.c b/hw/remote/proxy.c index XXXXXXX..XXXXXXX 100644 --- a/hw/remote/proxy.c +++ b/hw/remote/proxy.c @@ -XXX,XX +XXX,XX @@ #include "monitor/monitor.h" #include "migration/blocker.h" #include "qemu/sockets.h" +#include "hw/remote/mpqemu-link.h" +#include "qemu/error-report.h" static void pci_proxy_dev_realize(PCIDevice *device, Error **errp) { @@ -XXX,XX +XXX,XX @@ static void pci_proxy_dev_exit(PCIDevice *pdev) error_free(dev->migration_blocker); } +static void config_op_send(PCIProxyDev *pdev, uint32_t addr, uint32_t *val, + int len, unsigned int op) +{ + MPQemuMsg msg = { 0 }; + uint64_t ret = -EINVAL; + Error *local_err = NULL; + + msg.cmd = op; + msg.data.pci_conf_data.addr = addr; + msg.data.pci_conf_data.val = (op == MPQEMU_CMD_PCI_CFGWRITE) ? *val : 0; + msg.data.pci_conf_data.len = len; + msg.size = sizeof(PciConfDataMsg); + + ret = mpqemu_msg_send_and_await_reply(&msg, pdev, &local_err); + if (local_err) { + error_report_err(local_err); + } + + if (ret == UINT64_MAX) { + error_report("Failed to perform PCI config %s operation", + (op == MPQEMU_CMD_PCI_CFGREAD) ? "READ" : "WRITE"); + } + + if (op == MPQEMU_CMD_PCI_CFGREAD) { + *val = (uint32_t)ret; + } +} + +static uint32_t pci_proxy_read_config(PCIDevice *d, uint32_t addr, int len) +{ + uint32_t val; + + config_op_send(PCI_PROXY_DEV(d), addr, &val, len, MPQEMU_CMD_PCI_CFGREAD); + + return val; +} + +static void pci_proxy_write_config(PCIDevice *d, uint32_t addr, uint32_t val, + int len) +{ + /* + * Some of the functions access the copy of remote device's PCI config + * space which is cached in the proxy device. Therefore, maintain + * it updated. + */ + pci_default_write_config(d, addr, val, len); + + config_op_send(PCI_PROXY_DEV(d), addr, &val, len, MPQEMU_CMD_PCI_CFGWRITE); +} + static Property proxy_properties[] = { DEFINE_PROP_STRING("fd", PCIProxyDev, fd), DEFINE_PROP_END_OF_LIST(), @@ -XXX,XX +XXX,XX @@ static void pci_proxy_dev_class_init(ObjectClass *klass, void *data) k->realize = pci_proxy_dev_realize; k->exit = pci_proxy_dev_exit; + k->config_read = pci_proxy_read_config; + k->config_write = pci_proxy_write_config; + device_class_set_props(dc, proxy_properties); } -- 2.29.2 From: Jagannathan Raman <jag.raman@oracle.com> Proxy device object implements handler for PCI BAR writes and reads. The handler uses BAR_WRITE/BAR_READ message to communicate to the remote process with the BAR address and value to be written/read. The remote process implements handler for BAR_WRITE/BAR_READ message. Signed-off-by: Jagannathan Raman <jag.raman@oracle.com> Signed-off-by: Elena Ufimtseva <elena.ufimtseva@oracle.com> Signed-off-by: John G Johnson <john.g.johnson@oracle.com> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Message-id: a8b76714a9688be5552c4c92d089bc9e8a4707ff.1611938319.git.jag.raman@oracle.com Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- include/hw/remote/mpqemu-link.h | 10 ++++ include/hw/remote/proxy.h | 9 ++++ hw/remote/message.c | 83 +++++++++++++++++++++++++++++++++ hw/remote/mpqemu-link.c | 6 +++ hw/remote/proxy.c | 60 ++++++++++++++++++++++++ 5 files changed, 168 insertions(+) diff --git a/include/hw/remote/mpqemu-link.h b/include/hw/remote/mpqemu-link.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/remote/mpqemu-link.h +++ b/include/hw/remote/mpqemu-link.h @@ -XXX,XX +XXX,XX @@ typedef enum { MPQEMU_CMD_RET, MPQEMU_CMD_PCI_CFGWRITE, MPQEMU_CMD_PCI_CFGREAD, + MPQEMU_CMD_BAR_WRITE, + MPQEMU_CMD_BAR_READ, MPQEMU_CMD_MAX, } MPQemuCmd; @@ -XXX,XX +XXX,XX @@ typedef struct { int len; } PciConfDataMsg; +typedef struct { + hwaddr addr; + uint64_t val; + unsigned size; + bool memory; +} BarAccessMsg; + /** * MPQemuMsg: * @cmd: The remote command @@ -XXX,XX +XXX,XX @@ typedef struct { uint64_t u64; PciConfDataMsg pci_conf_data; SyncSysmemMsg sync_sysmem; + BarAccessMsg bar_access; } data; int fds[REMOTE_MAX_FDS]; diff --git a/include/hw/remote/proxy.h b/include/hw/remote/proxy.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/remote/proxy.h +++ b/include/hw/remote/proxy.h @@ -XXX,XX +XXX,XX @@ #define TYPE_PCI_PROXY_DEV "x-pci-proxy-dev" OBJECT_DECLARE_SIMPLE_TYPE(PCIProxyDev, PCI_PROXY_DEV) +typedef struct ProxyMemoryRegion { + PCIProxyDev *dev; + MemoryRegion mr; + bool memory; + bool present; + uint8_t type; +} ProxyMemoryRegion; + struct PCIProxyDev { PCIDevice parent_dev; char *fd; @@ -XXX,XX +XXX,XX @@ struct PCIProxyDev { QemuMutex io_mutex; QIOChannel *ioc; Error *migration_blocker; + ProxyMemoryRegion region[PCI_NUM_REGIONS]; }; #endif /* PROXY_H */ diff --git a/hw/remote/message.c b/hw/remote/message.c index XXXXXXX..XXXXXXX 100644 --- a/hw/remote/message.c +++ b/hw/remote/message.c @@ -XXX,XX +XXX,XX @@ #include "qapi/error.h" #include "sysemu/runstate.h" #include "hw/pci/pci.h" +#include "exec/memattrs.h" static void process_config_write(QIOChannel *ioc, PCIDevice *dev, MPQemuMsg *msg, Error **errp); static void process_config_read(QIOChannel *ioc, PCIDevice *dev, MPQemuMsg *msg, Error **errp); +static void process_bar_write(QIOChannel *ioc, MPQemuMsg *msg, Error **errp); +static void process_bar_read(QIOChannel *ioc, MPQemuMsg *msg, Error **errp); void coroutine_fn mpqemu_remote_msg_loop_co(void *data) { @@ -XXX,XX +XXX,XX @@ void coroutine_fn mpqemu_remote_msg_loop_co(void *data) case MPQEMU_CMD_PCI_CFGREAD: process_config_read(com->ioc, pci_dev, &msg, &local_err); break; + case MPQEMU_CMD_BAR_WRITE: + process_bar_write(com->ioc, &msg, &local_err); + break; + case MPQEMU_CMD_BAR_READ: + process_bar_read(com->ioc, &msg, &local_err); + break; default: error_setg(&local_err, "Unknown command (%d) received for device %s" @@ -XXX,XX +XXX,XX @@ static void process_config_read(QIOChannel *ioc, PCIDevice *dev, getpid()); } } + +static void process_bar_write(QIOChannel *ioc, MPQemuMsg *msg, Error **errp) +{ + ERRP_GUARD(); + BarAccessMsg *bar_access = &msg->data.bar_access; + AddressSpace *as = + bar_access->memory ? &address_space_memory : &address_space_io; + MPQemuMsg ret = { 0 }; + MemTxResult res; + uint64_t val; + + if (!is_power_of_2(bar_access->size) || + (bar_access->size > sizeof(uint64_t))) { + ret.data.u64 = UINT64_MAX; + goto fail; + } + + val = cpu_to_le64(bar_access->val); + + res = address_space_rw(as, bar_access->addr, MEMTXATTRS_UNSPECIFIED, + (void *)&val, bar_access->size, true); + + if (res != MEMTX_OK) { + error_setg(errp, "Bad address %"PRIx64" for mem write, pid "FMT_pid".", + bar_access->addr, getpid()); + ret.data.u64 = -1; + } + +fail: + ret.cmd = MPQEMU_CMD_RET; + ret.size = sizeof(ret.data.u64); + + if (!mpqemu_msg_send(&ret, ioc, NULL)) { + error_prepend(errp, "Error returning code to proxy, pid "FMT_pid": ", + getpid()); + } +} + +static void process_bar_read(QIOChannel *ioc, MPQemuMsg *msg, Error **errp) +{ + ERRP_GUARD(); + BarAccessMsg *bar_access = &msg->data.bar_access; + MPQemuMsg ret = { 0 }; + AddressSpace *as; + MemTxResult res; + uint64_t val = 0; + + as = bar_access->memory ? &address_space_memory : &address_space_io; + + if (!is_power_of_2(bar_access->size) || + (bar_access->size > sizeof(uint64_t))) { + val = UINT64_MAX; + goto fail; + } + + res = address_space_rw(as, bar_access->addr, MEMTXATTRS_UNSPECIFIED, + (void *)&val, bar_access->size, false); + + if (res != MEMTX_OK) { + error_setg(errp, "Bad address %"PRIx64" for mem read, pid "FMT_pid".", + bar_access->addr, getpid()); + val = UINT64_MAX; + } + +fail: + ret.cmd = MPQEMU_CMD_RET; + ret.data.u64 = le64_to_cpu(val); + ret.size = sizeof(ret.data.u64); + + if (!mpqemu_msg_send(&ret, ioc, NULL)) { + error_prepend(errp, "Error returning code to proxy, pid "FMT_pid": ", + getpid()); + } +} diff --git a/hw/remote/mpqemu-link.c b/hw/remote/mpqemu-link.c index XXXXXXX..XXXXXXX 100644 --- a/hw/remote/mpqemu-link.c +++ b/hw/remote/mpqemu-link.c @@ -XXX,XX +XXX,XX @@ bool mpqemu_msg_valid(MPQemuMsg *msg) return false; } break; + case MPQEMU_CMD_BAR_WRITE: + case MPQEMU_CMD_BAR_READ: + if ((msg->size != sizeof(BarAccessMsg)) || (msg->num_fds != 0)) { + return false; + } + break; default: break; } diff --git a/hw/remote/proxy.c b/hw/remote/proxy.c index XXXXXXX..XXXXXXX 100644 --- a/hw/remote/proxy.c +++ b/hw/remote/proxy.c @@ -XXX,XX +XXX,XX @@ static void pci_proxy_dev_register_types(void) } type_init(pci_proxy_dev_register_types) + +static void send_bar_access_msg(PCIProxyDev *pdev, MemoryRegion *mr, + bool write, hwaddr addr, uint64_t *val, + unsigned size, bool memory) +{ + MPQemuMsg msg = { 0 }; + long ret = -EINVAL; + Error *local_err = NULL; + + msg.size = sizeof(BarAccessMsg); + msg.data.bar_access.addr = mr->addr + addr; + msg.data.bar_access.size = size; + msg.data.bar_access.memory = memory; + + if (write) { + msg.cmd = MPQEMU_CMD_BAR_WRITE; + msg.data.bar_access.val = *val; + } else { + msg.cmd = MPQEMU_CMD_BAR_READ; + } + + ret = mpqemu_msg_send_and_await_reply(&msg, pdev, &local_err); + if (local_err) { + error_report_err(local_err); + } + + if (!write) { + *val = ret; + } +} + +static void proxy_bar_write(void *opaque, hwaddr addr, uint64_t val, + unsigned size) +{ + ProxyMemoryRegion *pmr = opaque; + + send_bar_access_msg(pmr->dev, &pmr->mr, true, addr, &val, size, + pmr->memory); +} + +static uint64_t proxy_bar_read(void *opaque, hwaddr addr, unsigned size) +{ + ProxyMemoryRegion *pmr = opaque; + uint64_t val; + + send_bar_access_msg(pmr->dev, &pmr->mr, false, addr, &val, size, + pmr->memory); + + return val; +} + +const MemoryRegionOps proxy_mr_ops = { + .read = proxy_bar_read, + .write = proxy_bar_write, + .endianness = DEVICE_NATIVE_ENDIAN, + .impl = { + .min_access_size = 1, + .max_access_size = 8, + }, +}; -- 2.29.2 From: Jagannathan Raman <jag.raman@oracle.com> Add ProxyMemoryListener object which is used to keep the view of the RAM in sync between QEMU and remote process. A MemoryListener is registered for system-memory AddressSpace. The listener sends SYNC_SYSMEM message to the remote process when memory listener commits the changes to memory, the remote process receives the message and processes it in the handler for SYNC_SYSMEM message. Signed-off-by: Jagannathan Raman <jag.raman@oracle.com> Signed-off-by: John G Johnson <john.g.johnson@oracle.com> Signed-off-by: Elena Ufimtseva <elena.ufimtseva@oracle.com> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Message-id: 04fe4e6a9ca90d4f11ab6f59be7652f5b086a071.1611938319.git.jag.raman@oracle.com Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- MAINTAINERS | 2 + include/hw/remote/proxy-memory-listener.h | 28 +++ include/hw/remote/proxy.h | 2 + hw/remote/message.c | 4 + hw/remote/proxy-memory-listener.c | 227 ++++++++++++++++++++++ hw/remote/proxy.c | 6 + hw/remote/meson.build | 1 + 7 files changed, 270 insertions(+) create mode 100644 include/hw/remote/proxy-memory-listener.h create mode 100644 hw/remote/proxy-memory-listener.c diff --git a/MAINTAINERS b/MAINTAINERS index XXXXXXX..XXXXXXX 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -XXX,XX +XXX,XX @@ F: include/hw/remote/memory.h F: hw/remote/memory.c F: hw/remote/proxy.c F: include/hw/remote/proxy.h +F: hw/remote/proxy-memory-listener.c +F: include/hw/remote/proxy-memory-listener.h Build and test automation ------------------------- diff --git a/include/hw/remote/proxy-memory-listener.h b/include/hw/remote/proxy-memory-listener.h new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/include/hw/remote/proxy-memory-listener.h @@ -XXX,XX +XXX,XX @@ +/* + * Copyright © 2018, 2021 Oracle and/or its affiliates. + * + * This work is licensed under the terms of the GNU GPL, version 2 or later. + * See the COPYING file in the top-level directory. + * + */ + +#ifndef PROXY_MEMORY_LISTENER_H +#define PROXY_MEMORY_LISTENER_H + +#include "exec/memory.h" +#include "io/channel.h" + +typedef struct ProxyMemoryListener { + MemoryListener listener; + + int n_mr_sections; + MemoryRegionSection *mr_sections; + + QIOChannel *ioc; +} ProxyMemoryListener; + +void proxy_memory_listener_configure(ProxyMemoryListener *proxy_listener, + QIOChannel *ioc); +void proxy_memory_listener_deconfigure(ProxyMemoryListener *proxy_listener); + +#endif diff --git a/include/hw/remote/proxy.h b/include/hw/remote/proxy.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/remote/proxy.h +++ b/include/hw/remote/proxy.h @@ -XXX,XX +XXX,XX @@ #include "hw/pci/pci.h" #include "io/channel.h" +#include "hw/remote/proxy-memory-listener.h" #define TYPE_PCI_PROXY_DEV "x-pci-proxy-dev" OBJECT_DECLARE_SIMPLE_TYPE(PCIProxyDev, PCI_PROXY_DEV) @@ -XXX,XX +XXX,XX @@ struct PCIProxyDev { QemuMutex io_mutex; QIOChannel *ioc; Error *migration_blocker; + ProxyMemoryListener proxy_listener; ProxyMemoryRegion region[PCI_NUM_REGIONS]; }; diff --git a/hw/remote/message.c b/hw/remote/message.c index XXXXXXX..XXXXXXX 100644 --- a/hw/remote/message.c +++ b/hw/remote/message.c @@ -XXX,XX +XXX,XX @@ #include "sysemu/runstate.h" #include "hw/pci/pci.h" #include "exec/memattrs.h" +#include "hw/remote/memory.h" static void process_config_write(QIOChannel *ioc, PCIDevice *dev, MPQemuMsg *msg, Error **errp); @@ -XXX,XX +XXX,XX @@ void coroutine_fn mpqemu_remote_msg_loop_co(void *data) case MPQEMU_CMD_BAR_READ: process_bar_read(com->ioc, &msg, &local_err); break; + case MPQEMU_CMD_SYNC_SYSMEM: + remote_sysmem_reconfig(&msg, &local_err); + break; default: error_setg(&local_err, "Unknown command (%d) received for device %s" diff --git a/hw/remote/proxy-memory-listener.c b/hw/remote/proxy-memory-listener.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/hw/remote/proxy-memory-listener.c @@ -XXX,XX +XXX,XX @@ +/* + * Copyright © 2018, 2021 Oracle and/or its affiliates. + * + * This work is licensed under the terms of the GNU GPL, version 2 or later. + * See the COPYING file in the top-level directory. + * + */ + +#include "qemu/osdep.h" +#include "qemu-common.h" + +#include "qemu/compiler.h" +#include "qemu/int128.h" +#include "qemu/range.h" +#include "exec/memory.h" +#include "exec/cpu-common.h" +#include "cpu.h" +#include "exec/ram_addr.h" +#include "exec/address-spaces.h" +#include "qapi/error.h" +#include "hw/remote/mpqemu-link.h" +#include "hw/remote/proxy-memory-listener.h" + +/* + * TODO: get_fd_from_hostaddr(), proxy_mrs_can_merge() and + * proxy_memory_listener_commit() defined below perform tasks similar to the + * functions defined in vhost-user.c. These functions are good candidates + * for refactoring. + * + */ + +static void proxy_memory_listener_reset(MemoryListener *listener) +{ + ProxyMemoryListener *proxy_listener = container_of(listener, + ProxyMemoryListener, + listener); + int mrs; + + for (mrs = 0; mrs < proxy_listener->n_mr_sections; mrs++) { + memory_region_unref(proxy_listener->mr_sections[mrs].mr); + } + + g_free(proxy_listener->mr_sections); + proxy_listener->mr_sections = NULL; + proxy_listener->n_mr_sections = 0; +} + +static int get_fd_from_hostaddr(uint64_t host, ram_addr_t *offset) +{ + MemoryRegion *mr; + ram_addr_t off; + + /** + * Assumes that the host address is a valid address as it's + * coming from the MemoryListener system. In the case host + * address is not valid, the following call would return + * the default subregion of "system_memory" region, and + * not NULL. So it's not possible to check for NULL here. + */ + mr = memory_region_from_host((void *)(uintptr_t)host, &off); + + if (offset) { + *offset = off; + } + + return memory_region_get_fd(mr); +} + +static bool proxy_mrs_can_merge(uint64_t host, uint64_t prev_host, size_t size) +{ + if (((prev_host + size) != host)) { + return false; + } + + if (get_fd_from_hostaddr(host, NULL) != + get_fd_from_hostaddr(prev_host, NULL)) { + return false; + } + + return true; +} + +static bool try_merge(ProxyMemoryListener *proxy_listener, + MemoryRegionSection *section) +{ + uint64_t mrs_size, mrs_gpa, mrs_page; + MemoryRegionSection *prev_sec; + bool merged = false; + uintptr_t mrs_host; + RAMBlock *mrs_rb; + + if (!proxy_listener->n_mr_sections) { + return false; + } + + mrs_rb = section->mr->ram_block; + mrs_page = (uint64_t)qemu_ram_pagesize(mrs_rb); + mrs_size = int128_get64(section->size); + mrs_gpa = section->offset_within_address_space; + mrs_host = (uintptr_t)memory_region_get_ram_ptr(section->mr) + + section->offset_within_region; + + if (get_fd_from_hostaddr(mrs_host, NULL) < 0) { + return true; + } + + mrs_host = mrs_host & ~(mrs_page - 1); + mrs_gpa = mrs_gpa & ~(mrs_page - 1); + mrs_size = ROUND_UP(mrs_size, mrs_page); + + prev_sec = proxy_listener->mr_sections + + (proxy_listener->n_mr_sections - 1); + uint64_t prev_gpa_start = prev_sec->offset_within_address_space; + uint64_t prev_size = int128_get64(prev_sec->size); + uint64_t prev_gpa_end = range_get_last(prev_gpa_start, prev_size); + uint64_t prev_host_start = + (uintptr_t)memory_region_get_ram_ptr(prev_sec->mr) + + prev_sec->offset_within_region; + uint64_t prev_host_end = range_get_last(prev_host_start, prev_size); + + if (mrs_gpa <= (prev_gpa_end + 1)) { + g_assert(mrs_gpa > prev_gpa_start); + + if ((section->mr == prev_sec->mr) && + proxy_mrs_can_merge(mrs_host, prev_host_start, + (mrs_gpa - prev_gpa_start))) { + uint64_t max_end = MAX(prev_host_end, mrs_host + mrs_size); + merged = true; + prev_sec->offset_within_address_space = + MIN(prev_gpa_start, mrs_gpa); + prev_sec->offset_within_region = + MIN(prev_host_start, mrs_host) - + (uintptr_t)memory_region_get_ram_ptr(prev_sec->mr); + prev_sec->size = int128_make64(max_end - MIN(prev_host_start, + mrs_host)); + } + } + + return merged; +} + +static void proxy_memory_listener_region_addnop(MemoryListener *listener, + MemoryRegionSection *section) +{ + ProxyMemoryListener *proxy_listener = container_of(listener, + ProxyMemoryListener, + listener); + + if (!memory_region_is_ram(section->mr) || + memory_region_is_rom(section->mr)) { + return; + } + + if (try_merge(proxy_listener, section)) { + return; + } + + ++proxy_listener->n_mr_sections; + proxy_listener->mr_sections = g_renew(MemoryRegionSection, + proxy_listener->mr_sections, + proxy_listener->n_mr_sections); + proxy_listener->mr_sections[proxy_listener->n_mr_sections - 1] = *section; + proxy_listener->mr_sections[proxy_listener->n_mr_sections - 1].fv = NULL; + memory_region_ref(section->mr); +} + +static void proxy_memory_listener_commit(MemoryListener *listener) +{ + ProxyMemoryListener *proxy_listener = container_of(listener, + ProxyMemoryListener, + listener); + MPQemuMsg msg; + MemoryRegionSection *section; + ram_addr_t offset; + uintptr_t host_addr; + int region; + Error *local_err = NULL; + + memset(&msg, 0, sizeof(MPQemuMsg)); + + msg.cmd = MPQEMU_CMD_SYNC_SYSMEM; + msg.num_fds = proxy_listener->n_mr_sections; + msg.size = sizeof(SyncSysmemMsg); + if (msg.num_fds > REMOTE_MAX_FDS) { + error_report("Number of fds is more than %d", REMOTE_MAX_FDS); + return; + } + + for (region = 0; region < proxy_listener->n_mr_sections; region++) { + section = &proxy_listener->mr_sections[region]; + msg.data.sync_sysmem.gpas[region] = + section->offset_within_address_space; + msg.data.sync_sysmem.sizes[region] = int128_get64(section->size); + host_addr = (uintptr_t)memory_region_get_ram_ptr(section->mr) + + section->offset_within_region; + msg.fds[region] = get_fd_from_hostaddr(host_addr, &offset); + msg.data.sync_sysmem.offsets[region] = offset; + } + if (!mpqemu_msg_send(&msg, proxy_listener->ioc, &local_err)) { + error_report_err(local_err); + } +} + +void proxy_memory_listener_deconfigure(ProxyMemoryListener *proxy_listener) +{ + memory_listener_unregister(&proxy_listener->listener); + + proxy_memory_listener_reset(&proxy_listener->listener); +} + +void proxy_memory_listener_configure(ProxyMemoryListener *proxy_listener, + QIOChannel *ioc) +{ + proxy_listener->n_mr_sections = 0; + proxy_listener->mr_sections = NULL; + + proxy_listener->ioc = ioc; + + proxy_listener->listener.begin = proxy_memory_listener_reset; + proxy_listener->listener.commit = proxy_memory_listener_commit; + proxy_listener->listener.region_add = proxy_memory_listener_region_addnop; + proxy_listener->listener.region_nop = proxy_memory_listener_region_addnop; + proxy_listener->listener.priority = 10; + + memory_listener_register(&proxy_listener->listener, + &address_space_memory); +} diff --git a/hw/remote/proxy.c b/hw/remote/proxy.c index XXXXXXX..XXXXXXX 100644 --- a/hw/remote/proxy.c +++ b/hw/remote/proxy.c @@ -XXX,XX +XXX,XX @@ #include "qemu/sockets.h" #include "hw/remote/mpqemu-link.h" #include "qemu/error-report.h" +#include "hw/remote/proxy-memory-listener.h" +#include "qom/object.h" static void pci_proxy_dev_realize(PCIDevice *device, Error **errp) { @@ -XXX,XX +XXX,XX @@ static void pci_proxy_dev_realize(PCIDevice *device, Error **errp) qemu_mutex_init(&dev->io_mutex); qio_channel_set_blocking(dev->ioc, true, NULL); + + proxy_memory_listener_configure(&dev->proxy_listener, dev->ioc); } static void pci_proxy_dev_exit(PCIDevice *pdev) @@ -XXX,XX +XXX,XX @@ static void pci_proxy_dev_exit(PCIDevice *pdev) migrate_del_blocker(dev->migration_blocker); error_free(dev->migration_blocker); + + proxy_memory_listener_deconfigure(&dev->proxy_listener); } static void config_op_send(PCIProxyDev *pdev, uint32_t addr, uint32_t *val, diff --git a/hw/remote/meson.build b/hw/remote/meson.build index XXXXXXX..XXXXXXX 100644 --- a/hw/remote/meson.build +++ b/hw/remote/meson.build @@ -XXX,XX +XXX,XX @@ remote_ss.add(when: 'CONFIG_MULTIPROCESS', if_true: files('remote-obj.c')) remote_ss.add(when: 'CONFIG_MULTIPROCESS', if_true: files('proxy.c')) specific_ss.add(when: 'CONFIG_MULTIPROCESS', if_true: files('memory.c')) +specific_ss.add(when: 'CONFIG_MULTIPROCESS', if_true: files('proxy-memory-listener.c')) softmmu_ss.add_all(when: 'CONFIG_MULTIPROCESS', if_true: remote_ss) -- 2.29.2 From: Jagannathan Raman <jag.raman@oracle.com> IOHUB object is added to manage PCI IRQs. It uses KVM_IRQFD ioctl to create irqfd to injecting PCI interrupts to the guest. IOHUB object forwards the irqfd to the remote process. Remote process uses this fd to directly send interrupts to the guest, bypassing QEMU. Signed-off-by: John G Johnson <john.g.johnson@oracle.com> Signed-off-by: Jagannathan Raman <jag.raman@oracle.com> Signed-off-by: Elena Ufimtseva <elena.ufimtseva@oracle.com> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Message-id: 51d5c3d54e28a68b002e3875c59599c9f5a424a1.1611938319.git.jag.raman@oracle.com Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- MAINTAINERS | 2 + include/hw/pci/pci_ids.h | 3 + include/hw/remote/iohub.h | 42 +++++++++++ include/hw/remote/machine.h | 2 + include/hw/remote/mpqemu-link.h | 1 + include/hw/remote/proxy.h | 4 ++ hw/remote/iohub.c | 119 ++++++++++++++++++++++++++++++++ hw/remote/machine.c | 10 +++ hw/remote/message.c | 4 ++ hw/remote/mpqemu-link.c | 5 ++ hw/remote/proxy.c | 56 +++++++++++++++ hw/remote/meson.build | 1 + 12 files changed, 249 insertions(+) create mode 100644 include/hw/remote/iohub.h create mode 100644 hw/remote/iohub.c diff --git a/MAINTAINERS b/MAINTAINERS index XXXXXXX..XXXXXXX 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -XXX,XX +XXX,XX @@ F: hw/remote/proxy.c F: include/hw/remote/proxy.h F: hw/remote/proxy-memory-listener.c F: include/hw/remote/proxy-memory-listener.h +F: hw/remote/iohub.c +F: include/hw/remote/iohub.h Build and test automation ------------------------- diff --git a/include/hw/pci/pci_ids.h b/include/hw/pci/pci_ids.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/pci/pci_ids.h +++ b/include/hw/pci/pci_ids.h @@ -XXX,XX +XXX,XX @@ #define PCI_DEVICE_ID_SUN_SIMBA 0x5000 #define PCI_DEVICE_ID_SUN_SABRE 0xa000 +#define PCI_VENDOR_ID_ORACLE 0x108e +#define PCI_DEVICE_ID_REMOTE_IOHUB 0xb000 + #define PCI_VENDOR_ID_CMD 0x1095 #define PCI_DEVICE_ID_CMD_646 0x0646 diff --git a/include/hw/remote/iohub.h b/include/hw/remote/iohub.h new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/include/hw/remote/iohub.h @@ -XXX,XX +XXX,XX @@ +/* + * IO Hub for remote device + * + * Copyright © 2018, 2021 Oracle and/or its affiliates. + * + * This work is licensed under the terms of the GNU GPL, version 2 or later. + * See the COPYING file in the top-level directory. + * + */ + +#ifndef REMOTE_IOHUB_H +#define REMOTE_IOHUB_H + +#include "hw/pci/pci.h" +#include "qemu/event_notifier.h" +#include "qemu/thread-posix.h" +#include "hw/remote/mpqemu-link.h" + +#define REMOTE_IOHUB_NB_PIRQS PCI_DEVFN_MAX + +typedef struct ResampleToken { + void *iohub; + int pirq; +} ResampleToken; + +typedef struct RemoteIOHubState { + PCIDevice d; + EventNotifier irqfds[REMOTE_IOHUB_NB_PIRQS]; + EventNotifier resamplefds[REMOTE_IOHUB_NB_PIRQS]; + unsigned int irq_level[REMOTE_IOHUB_NB_PIRQS]; + ResampleToken token[REMOTE_IOHUB_NB_PIRQS]; + QemuMutex irq_level_lock[REMOTE_IOHUB_NB_PIRQS]; +} RemoteIOHubState; + +int remote_iohub_map_irq(PCIDevice *pci_dev, int intx); +void remote_iohub_set_irq(void *opaque, int pirq, int level); +void process_set_irqfd_msg(PCIDevice *pci_dev, MPQemuMsg *msg); + +void remote_iohub_init(RemoteIOHubState *iohub); +void remote_iohub_finalize(RemoteIOHubState *iohub); + +#endif diff --git a/include/hw/remote/machine.h b/include/hw/remote/machine.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/remote/machine.h +++ b/include/hw/remote/machine.h @@ -XXX,XX +XXX,XX @@ #include "hw/boards.h" #include "hw/pci-host/remote.h" #include "io/channel.h" +#include "hw/remote/iohub.h" struct RemoteMachineState { MachineState parent_obj; RemotePCIHost *host; + RemoteIOHubState iohub; }; /* Used to pass to co-routine device and ioc. */ diff --git a/include/hw/remote/mpqemu-link.h b/include/hw/remote/mpqemu-link.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/remote/mpqemu-link.h +++ b/include/hw/remote/mpqemu-link.h @@ -XXX,XX +XXX,XX @@ typedef enum { MPQEMU_CMD_PCI_CFGREAD, MPQEMU_CMD_BAR_WRITE, MPQEMU_CMD_BAR_READ, + MPQEMU_CMD_SET_IRQFD, MPQEMU_CMD_MAX, } MPQemuCmd; diff --git a/include/hw/remote/proxy.h b/include/hw/remote/proxy.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/remote/proxy.h +++ b/include/hw/remote/proxy.h @@ -XXX,XX +XXX,XX @@ #include "hw/pci/pci.h" #include "io/channel.h" #include "hw/remote/proxy-memory-listener.h" +#include "qemu/event_notifier.h" #define TYPE_PCI_PROXY_DEV "x-pci-proxy-dev" OBJECT_DECLARE_SIMPLE_TYPE(PCIProxyDev, PCI_PROXY_DEV) @@ -XXX,XX +XXX,XX @@ struct PCIProxyDev { QIOChannel *ioc; Error *migration_blocker; ProxyMemoryListener proxy_listener; + int virq; + EventNotifier intr; + EventNotifier resample; ProxyMemoryRegion region[PCI_NUM_REGIONS]; }; diff --git a/hw/remote/iohub.c b/hw/remote/iohub.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/hw/remote/iohub.c @@ -XXX,XX +XXX,XX @@ +/* + * Remote IO Hub + * + * Copyright © 2018, 2021 Oracle and/or its affiliates. + * + * This work is licensed under the terms of the GNU GPL, version 2 or later. + * See the COPYING file in the top-level directory. + * + */ + +#include "qemu/osdep.h" +#include "qemu-common.h" + +#include "hw/pci/pci.h" +#include "hw/pci/pci_ids.h" +#include "hw/pci/pci_bus.h" +#include "qemu/thread.h" +#include "hw/boards.h" +#include "hw/remote/machine.h" +#include "hw/remote/iohub.h" +#include "qemu/main-loop.h" + +void remote_iohub_init(RemoteIOHubState *iohub) +{ + int pirq; + + memset(&iohub->irqfds, 0, sizeof(iohub->irqfds)); + memset(&iohub->resamplefds, 0, sizeof(iohub->resamplefds)); + + for (pirq = 0; pirq < REMOTE_IOHUB_NB_PIRQS; pirq++) { + qemu_mutex_init(&iohub->irq_level_lock[pirq]); + iohub->irq_level[pirq] = 0; + event_notifier_init_fd(&iohub->irqfds[pirq], -1); + event_notifier_init_fd(&iohub->resamplefds[pirq], -1); + } +} + +void remote_iohub_finalize(RemoteIOHubState *iohub) +{ + int pirq; + + for (pirq = 0; pirq < REMOTE_IOHUB_NB_PIRQS; pirq++) { + qemu_set_fd_handler(event_notifier_get_fd(&iohub->resamplefds[pirq]), + NULL, NULL, NULL); + event_notifier_cleanup(&iohub->irqfds[pirq]); + event_notifier_cleanup(&iohub->resamplefds[pirq]); + qemu_mutex_destroy(&iohub->irq_level_lock[pirq]); + } +} + +int remote_iohub_map_irq(PCIDevice *pci_dev, int intx) +{ + return pci_dev->devfn; +} + +void remote_iohub_set_irq(void *opaque, int pirq, int level) +{ + RemoteIOHubState *iohub = opaque; + + assert(pirq >= 0); + assert(pirq < PCI_DEVFN_MAX); + + QEMU_LOCK_GUARD(&iohub->irq_level_lock[pirq]); + + if (level) { + if (++iohub->irq_level[pirq] == 1) { + event_notifier_set(&iohub->irqfds[pirq]); + } + } else if (iohub->irq_level[pirq] > 0) { + iohub->irq_level[pirq]--; + } +} + +static void intr_resample_handler(void *opaque) +{ + ResampleToken *token = opaque; + RemoteIOHubState *iohub = token->iohub; + int pirq, s; + + pirq = token->pirq; + + s = event_notifier_test_and_clear(&iohub->resamplefds[pirq]); + + assert(s >= 0); + + QEMU_LOCK_GUARD(&iohub->irq_level_lock[pirq]); + + if (iohub->irq_level[pirq]) { + event_notifier_set(&iohub->irqfds[pirq]); + } +} + +void process_set_irqfd_msg(PCIDevice *pci_dev, MPQemuMsg *msg) +{ + RemoteMachineState *machine = REMOTE_MACHINE(current_machine); + RemoteIOHubState *iohub = &machine->iohub; + int pirq, intx; + + intx = pci_get_byte(pci_dev->config + PCI_INTERRUPT_PIN) - 1; + + pirq = remote_iohub_map_irq(pci_dev, intx); + + if (event_notifier_get_fd(&iohub->irqfds[pirq]) != -1) { + qemu_set_fd_handler(event_notifier_get_fd(&iohub->resamplefds[pirq]), + NULL, NULL, NULL); + event_notifier_cleanup(&iohub->irqfds[pirq]); + event_notifier_cleanup(&iohub->resamplefds[pirq]); + memset(&iohub->token[pirq], 0, sizeof(ResampleToken)); + } + + event_notifier_init_fd(&iohub->irqfds[pirq], msg->fds[0]); + event_notifier_init_fd(&iohub->resamplefds[pirq], msg->fds[1]); + + iohub->token[pirq].iohub = iohub; + iohub->token[pirq].pirq = pirq; + + qemu_set_fd_handler(msg->fds[1], intr_resample_handler, NULL, + &iohub->token[pirq]); +} diff --git a/hw/remote/machine.c b/hw/remote/machine.c index XXXXXXX..XXXXXXX 100644 --- a/hw/remote/machine.c +++ b/hw/remote/machine.c @@ -XXX,XX +XXX,XX @@ #include "exec/address-spaces.h" #include "exec/memory.h" #include "qapi/error.h" +#include "hw/pci/pci_host.h" +#include "hw/remote/iohub.h" static void remote_machine_init(MachineState *machine) { MemoryRegion *system_memory, *system_io, *pci_memory; RemoteMachineState *s = REMOTE_MACHINE(machine); RemotePCIHost *rem_host; + PCIHostState *pci_host; system_memory = get_system_memory(); system_io = get_system_io(); @@ -XXX,XX +XXX,XX @@ static void remote_machine_init(MachineState *machine) memory_region_add_subregion_overlap(system_memory, 0x0, pci_memory, -1); qdev_realize(DEVICE(rem_host), sysbus_get_default(), &error_fatal); + + pci_host = PCI_HOST_BRIDGE(rem_host); + + remote_iohub_init(&s->iohub); + + pci_bus_irqs(pci_host->bus, remote_iohub_set_irq, remote_iohub_map_irq, + &s->iohub, REMOTE_IOHUB_NB_PIRQS); } static void remote_machine_class_init(ObjectClass *oc, void *data) diff --git a/hw/remote/message.c b/hw/remote/message.c index XXXXXXX..XXXXXXX 100644 --- a/hw/remote/message.c +++ b/hw/remote/message.c @@ -XXX,XX +XXX,XX @@ #include "hw/pci/pci.h" #include "exec/memattrs.h" #include "hw/remote/memory.h" +#include "hw/remote/iohub.h" static void process_config_write(QIOChannel *ioc, PCIDevice *dev, MPQemuMsg *msg, Error **errp); @@ -XXX,XX +XXX,XX @@ void coroutine_fn mpqemu_remote_msg_loop_co(void *data) case MPQEMU_CMD_SYNC_SYSMEM: remote_sysmem_reconfig(&msg, &local_err); break; + case MPQEMU_CMD_SET_IRQFD: + process_set_irqfd_msg(pci_dev, &msg); + break; default: error_setg(&local_err, "Unknown command (%d) received for device %s" diff --git a/hw/remote/mpqemu-link.c b/hw/remote/mpqemu-link.c index XXXXXXX..XXXXXXX 100644 --- a/hw/remote/mpqemu-link.c +++ b/hw/remote/mpqemu-link.c @@ -XXX,XX +XXX,XX @@ bool mpqemu_msg_valid(MPQemuMsg *msg) return false; } break; + case MPQEMU_CMD_SET_IRQFD: + if (msg->size || (msg->num_fds != 2)) { + return false; + } + break; default: break; } diff --git a/hw/remote/proxy.c b/hw/remote/proxy.c index XXXXXXX..XXXXXXX 100644 --- a/hw/remote/proxy.c +++ b/hw/remote/proxy.c @@ -XXX,XX +XXX,XX @@ #include "qemu/error-report.h" #include "hw/remote/proxy-memory-listener.h" #include "qom/object.h" +#include "qemu/event_notifier.h" +#include "sysemu/kvm.h" +#include "util/event_notifier-posix.c" + +static void proxy_intx_update(PCIDevice *pci_dev) +{ + PCIProxyDev *dev = PCI_PROXY_DEV(pci_dev); + PCIINTxRoute route; + int pin = pci_get_byte(pci_dev->config + PCI_INTERRUPT_PIN) - 1; + + if (dev->virq != -1) { + kvm_irqchip_remove_irqfd_notifier_gsi(kvm_state, &dev->intr, dev->virq); + dev->virq = -1; + } + + route = pci_device_route_intx_to_irq(pci_dev, pin); + + dev->virq = route.irq; + + if (dev->virq != -1) { + kvm_irqchip_add_irqfd_notifier_gsi(kvm_state, &dev->intr, + &dev->resample, dev->virq); + } +} + +static void setup_irqfd(PCIProxyDev *dev) +{ + PCIDevice *pci_dev = PCI_DEVICE(dev); + MPQemuMsg msg; + Error *local_err = NULL; + + event_notifier_init(&dev->intr, 0); + event_notifier_init(&dev->resample, 0); + + memset(&msg, 0, sizeof(MPQemuMsg)); + msg.cmd = MPQEMU_CMD_SET_IRQFD; + msg.num_fds = 2; + msg.fds[0] = event_notifier_get_fd(&dev->intr); + msg.fds[1] = event_notifier_get_fd(&dev->resample); + msg.size = 0; + + if (!mpqemu_msg_send(&msg, dev->ioc, &local_err)) { + error_report_err(local_err); + } + + dev->virq = -1; + + proxy_intx_update(pci_dev); + + pci_device_set_intx_routing_notifier(pci_dev, proxy_intx_update); +} static void pci_proxy_dev_realize(PCIDevice *device, Error **errp) { @@ -XXX,XX +XXX,XX @@ static void pci_proxy_dev_realize(PCIDevice *device, Error **errp) qio_channel_set_blocking(dev->ioc, true, NULL); proxy_memory_listener_configure(&dev->proxy_listener, dev->ioc); + + setup_irqfd(dev); } static void pci_proxy_dev_exit(PCIDevice *pdev) @@ -XXX,XX +XXX,XX @@ static void pci_proxy_dev_exit(PCIDevice *pdev) error_free(dev->migration_blocker); proxy_memory_listener_deconfigure(&dev->proxy_listener); + + event_notifier_cleanup(&dev->intr); + event_notifier_cleanup(&dev->resample); } static void config_op_send(PCIProxyDev *pdev, uint32_t addr, uint32_t *val, diff --git a/hw/remote/meson.build b/hw/remote/meson.build index XXXXXXX..XXXXXXX 100644 --- a/hw/remote/meson.build +++ b/hw/remote/meson.build @@ -XXX,XX +XXX,XX @@ remote_ss.add(when: 'CONFIG_MULTIPROCESS', if_true: files('mpqemu-link.c')) remote_ss.add(when: 'CONFIG_MULTIPROCESS', if_true: files('message.c')) remote_ss.add(when: 'CONFIG_MULTIPROCESS', if_true: files('remote-obj.c')) remote_ss.add(when: 'CONFIG_MULTIPROCESS', if_true: files('proxy.c')) +remote_ss.add(when: 'CONFIG_MULTIPROCESS', if_true: files('iohub.c')) specific_ss.add(when: 'CONFIG_MULTIPROCESS', if_true: files('memory.c')) specific_ss.add(when: 'CONFIG_MULTIPROCESS', if_true: files('proxy-memory-listener.c')) -- 2.29.2 From: Jagannathan Raman <jag.raman@oracle.com> Retrieve PCI configuration info about the remote device and configure the Proxy PCI object based on the returned information Signed-off-by: Elena Ufimtseva <elena.ufimtseva@oracle.com> Signed-off-by: John G Johnson <john.g.johnson@oracle.com> Signed-off-by: Jagannathan Raman <jag.raman@oracle.com> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Message-id: 85ee367bbb993aa23699b44cfedd83b4ea6d5221.1611938319.git.jag.raman@oracle.com Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- hw/remote/proxy.c | 84 +++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 84 insertions(+) diff --git a/hw/remote/proxy.c b/hw/remote/proxy.c index XXXXXXX..XXXXXXX 100644 --- a/hw/remote/proxy.c +++ b/hw/remote/proxy.c @@ -XXX,XX +XXX,XX @@ #include "sysemu/kvm.h" #include "util/event_notifier-posix.c" +static void probe_pci_info(PCIDevice *dev, Error **errp); + static void proxy_intx_update(PCIDevice *pci_dev) { PCIProxyDev *dev = PCI_PROXY_DEV(pci_dev); @@ -XXX,XX +XXX,XX @@ static void pci_proxy_dev_realize(PCIDevice *device, Error **errp) { ERRP_GUARD(); PCIProxyDev *dev = PCI_PROXY_DEV(device); + uint8_t *pci_conf = device->config; int fd; if (!dev->fd) { @@ -XXX,XX +XXX,XX @@ static void pci_proxy_dev_realize(PCIDevice *device, Error **errp) qemu_mutex_init(&dev->io_mutex); qio_channel_set_blocking(dev->ioc, true, NULL); + pci_conf[PCI_LATENCY_TIMER] = 0xff; + pci_conf[PCI_INTERRUPT_PIN] = 0x01; + proxy_memory_listener_configure(&dev->proxy_listener, dev->ioc); setup_irqfd(dev); + + probe_pci_info(PCI_DEVICE(dev), errp); } static void pci_proxy_dev_exit(PCIDevice *pdev) @@ -XXX,XX +XXX,XX @@ const MemoryRegionOps proxy_mr_ops = { .max_access_size = 8, }, }; + +static void probe_pci_info(PCIDevice *dev, Error **errp) +{ + PCIDeviceClass *pc = PCI_DEVICE_GET_CLASS(dev); + uint32_t orig_val, new_val, base_class, val; + PCIProxyDev *pdev = PCI_PROXY_DEV(dev); + DeviceClass *dc = DEVICE_CLASS(pc); + uint8_t type; + int i, size; + + config_op_send(pdev, PCI_VENDOR_ID, &val, 2, MPQEMU_CMD_PCI_CFGREAD); + pc->vendor_id = (uint16_t)val; + + config_op_send(pdev, PCI_DEVICE_ID, &val, 2, MPQEMU_CMD_PCI_CFGREAD); + pc->device_id = (uint16_t)val; + + config_op_send(pdev, PCI_CLASS_DEVICE, &val, 2, MPQEMU_CMD_PCI_CFGREAD); + pc->class_id = (uint16_t)val; + + config_op_send(pdev, PCI_SUBSYSTEM_ID, &val, 2, MPQEMU_CMD_PCI_CFGREAD); + pc->subsystem_id = (uint16_t)val; + + base_class = pc->class_id >> 4; + switch (base_class) { + case PCI_BASE_CLASS_BRIDGE: + set_bit(DEVICE_CATEGORY_BRIDGE, dc->categories); + break; + case PCI_BASE_CLASS_STORAGE: + set_bit(DEVICE_CATEGORY_STORAGE, dc->categories); + break; + case PCI_BASE_CLASS_NETWORK: + set_bit(DEVICE_CATEGORY_NETWORK, dc->categories); + break; + case PCI_BASE_CLASS_INPUT: + set_bit(DEVICE_CATEGORY_INPUT, dc->categories); + break; + case PCI_BASE_CLASS_DISPLAY: + set_bit(DEVICE_CATEGORY_DISPLAY, dc->categories); + break; + case PCI_BASE_CLASS_PROCESSOR: + set_bit(DEVICE_CATEGORY_CPU, dc->categories); + break; + default: + set_bit(DEVICE_CATEGORY_MISC, dc->categories); + break; + } + + for (i = 0; i < PCI_NUM_REGIONS; i++) { + config_op_send(pdev, PCI_BASE_ADDRESS_0 + (4 * i), &orig_val, 4, + MPQEMU_CMD_PCI_CFGREAD); + new_val = 0xffffffff; + config_op_send(pdev, PCI_BASE_ADDRESS_0 + (4 * i), &new_val, 4, + MPQEMU_CMD_PCI_CFGWRITE); + config_op_send(pdev, PCI_BASE_ADDRESS_0 + (4 * i), &new_val, 4, + MPQEMU_CMD_PCI_CFGREAD); + size = (~(new_val & 0xFFFFFFF0)) + 1; + config_op_send(pdev, PCI_BASE_ADDRESS_0 + (4 * i), &orig_val, 4, + MPQEMU_CMD_PCI_CFGWRITE); + type = (new_val & 0x1) ? + PCI_BASE_ADDRESS_SPACE_IO : PCI_BASE_ADDRESS_SPACE_MEMORY; + + if (size) { + g_autofree char *name; + pdev->region[i].dev = pdev; + pdev->region[i].present = true; + if (type == PCI_BASE_ADDRESS_SPACE_MEMORY) { + pdev->region[i].memory = true; + } + name = g_strdup_printf("bar-region-%d", i); + memory_region_init_io(&pdev->region[i].mr, OBJECT(pdev), + &proxy_mr_ops, &pdev->region[i], + name, size); + pci_register_bar(dev, i, type, &pdev->region[i].mr); + } + } +} -- 2.29.2 From: Elena Ufimtseva <elena.ufimtseva@oracle.com> Perform device reset in the remote process when QEMU performs device reset. This is required to reset the internal state (like registers, etc...) of emulated devices Signed-off-by: Elena Ufimtseva <elena.ufimtseva@oracle.com> Signed-off-by: John G Johnson <john.g.johnson@oracle.com> Signed-off-by: Jagannathan Raman <jag.raman@oracle.com> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Message-id: 7cb220a51f565dc0817bd76e2f540e89c2d2b850.1611938319.git.jag.raman@oracle.com Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- include/hw/remote/mpqemu-link.h | 1 + hw/remote/message.c | 22 ++++++++++++++++++++++ hw/remote/proxy.c | 19 +++++++++++++++++++ 3 files changed, 42 insertions(+) diff --git a/include/hw/remote/mpqemu-link.h b/include/hw/remote/mpqemu-link.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/remote/mpqemu-link.h +++ b/include/hw/remote/mpqemu-link.h @@ -XXX,XX +XXX,XX @@ typedef enum { MPQEMU_CMD_BAR_WRITE, MPQEMU_CMD_BAR_READ, MPQEMU_CMD_SET_IRQFD, + MPQEMU_CMD_DEVICE_RESET, MPQEMU_CMD_MAX, } MPQemuCmd; diff --git a/hw/remote/message.c b/hw/remote/message.c index XXXXXXX..XXXXXXX 100644 --- a/hw/remote/message.c +++ b/hw/remote/message.c @@ -XXX,XX +XXX,XX @@ #include "exec/memattrs.h" #include "hw/remote/memory.h" #include "hw/remote/iohub.h" +#include "sysemu/reset.h" static void process_config_write(QIOChannel *ioc, PCIDevice *dev, MPQemuMsg *msg, Error **errp); @@ -XXX,XX +XXX,XX @@ static void process_config_read(QIOChannel *ioc, PCIDevice *dev, MPQemuMsg *msg, Error **errp); static void process_bar_write(QIOChannel *ioc, MPQemuMsg *msg, Error **errp); static void process_bar_read(QIOChannel *ioc, MPQemuMsg *msg, Error **errp); +static void process_device_reset_msg(QIOChannel *ioc, PCIDevice *dev, + Error **errp); void coroutine_fn mpqemu_remote_msg_loop_co(void *data) { @@ -XXX,XX +XXX,XX @@ void coroutine_fn mpqemu_remote_msg_loop_co(void *data) case MPQEMU_CMD_SET_IRQFD: process_set_irqfd_msg(pci_dev, &msg); break; + case MPQEMU_CMD_DEVICE_RESET: + process_device_reset_msg(com->ioc, pci_dev, &local_err); + break; default: error_setg(&local_err, "Unknown command (%d) received for device %s" @@ -XXX,XX +XXX,XX @@ fail: getpid()); } } + +static void process_device_reset_msg(QIOChannel *ioc, PCIDevice *dev, + Error **errp) +{ + DeviceClass *dc = DEVICE_GET_CLASS(dev); + DeviceState *s = DEVICE(dev); + MPQemuMsg ret = { 0 }; + + if (dc->reset) { + dc->reset(s); + } + + ret.cmd = MPQEMU_CMD_RET; + + mpqemu_msg_send(&ret, ioc, errp); +} diff --git a/hw/remote/proxy.c b/hw/remote/proxy.c index XXXXXXX..XXXXXXX 100644 --- a/hw/remote/proxy.c +++ b/hw/remote/proxy.c @@ -XXX,XX +XXX,XX @@ #include "util/event_notifier-posix.c" static void probe_pci_info(PCIDevice *dev, Error **errp); +static void proxy_device_reset(DeviceState *dev); static void proxy_intx_update(PCIDevice *pci_dev) { @@ -XXX,XX +XXX,XX @@ static void pci_proxy_dev_class_init(ObjectClass *klass, void *data) k->config_read = pci_proxy_read_config; k->config_write = pci_proxy_write_config; + dc->reset = proxy_device_reset; + device_class_set_props(dc, proxy_properties); } @@ -XXX,XX +XXX,XX @@ static void probe_pci_info(PCIDevice *dev, Error **errp) } } } + +static void proxy_device_reset(DeviceState *dev) +{ + PCIProxyDev *pdev = PCI_PROXY_DEV(dev); + MPQemuMsg msg = { 0 }; + Error *local_err = NULL; + + msg.cmd = MPQEMU_CMD_DEVICE_RESET; + msg.size = 0; + + mpqemu_msg_send_and_await_reply(&msg, pdev, &local_err); + if (local_err) { + error_report_err(local_err); + } + +} -- 2.29.2 From: "Denis V. Lunev" <den@openvz.org> Original specification says that l1 table size if 64 * l1_size, which is obviously wrong. The size of the l1 entry is 64 _bits_, not bytes. Thus 64 is to be replaces with 8 as specification says about bytes. There is also minor tweak, field name is renamed from l1 to l1_table, which matches with the later text. Signed-off-by: Denis V. Lunev <den@openvz.org> Reviewed-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> Message-id: 20210128171313.2210947-1-den@openvz.org CC: Stefan Hajnoczi <stefanha@redhat.com> CC: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com> [Replace the original commit message "docs: fix mistake in dirty bitmap feature description" as suggested by Eric Blake. --Stefan] Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com> --- docs/interop/parallels.txt | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/docs/interop/parallels.txt b/docs/interop/parallels.txt index XXXXXXX..XXXXXXX 100644 --- a/docs/interop/parallels.txt +++ b/docs/interop/parallels.txt @@ -XXX,XX +XXX,XX @@ of its data area are: 28 - 31: l1_size The number of entries in the L1 table of the bitmap. - variable: l1 (64 * l1_size bytes) + variable: l1_table (8 * l1_size bytes) L1 offset table (in bytes) A dirty bitmap is stored using a one-level structure for the mapping to host -- 2.29.2