From 4749079ce033a94784cbe20a661abeac598ff057 Mon Sep 17 00:00:00 2001 From: Stefan Hajnoczi Date: Fri, 14 Feb 2020 17:17:11 +0000 Subject: [PATCH] aio-posix: make AioHandler deletion O(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 Reviewed-by: Sergio Lopez Message-id: 20200214171712.541358-5-stefanha@redhat.com Signed-off-by: Stefan Hajnoczi --- 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 1a2ce9ca26..9dd61cee7e 100644 --- a/include/block/aio.h +++ b/include/block/aio.h @@ -42,6 +42,7 @@ 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); @@ -71,7 +72,10 @@ 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 60e794a4e3..294db54eb1 100644 --- a/include/qemu/queue.h +++ b/include/qemu/queue.h @@ -158,6 +158,9 @@ 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 58765e581e..b5cfdbd2f6 100644 --- a/util/aio-posix.c +++ b/util/aio-posix.c @@ -32,10 +32,10 @@ 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 @@ -68,7 +68,7 @@ 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); @@ -196,9 +196,11 @@ 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; @@ -217,7 +219,7 @@ 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; } @@ -359,7 +361,7 @@ 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; } @@ -416,6 +418,26 @@ 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; @@ -427,7 +449,7 @@ 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) { @@ -438,21 +460,13 @@ 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; @@ -463,6 +477,7 @@ 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); @@ -530,7 +545,7 @@ 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)) { /* @@ -664,7 +679,7 @@ 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); } @@ -741,6 +756,8 @@ 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); -- 2.11.4.GIT