From 8b60d72532b6511b41d82d591fb4f509314ef15f Mon Sep 17 00:00:00 2001 From: Stefan Hajnoczi Date: Thu, 21 Dec 2023 14:24:51 -0500 Subject: [PATCH 071/101] nbd/server: only traverse NBDExport->clients from main loop thread RH-Author: Kevin Wolf RH-MergeRequest: 214: Remove AioContext lock RH-Jira: RHEL-15965 RH-Acked-by: Miroslav Rezanina RH-Acked-by: Stefan Hajnoczi RH-Commit: [2/26] e7794a3a5c363c7508ee505c4ba03d9ef8862ca9 (kmwolf/centos-qemu-kvm) The NBD clients list is currently accessed from both the export AioContext and the main loop thread. When the AioContext lock is removed there will be nothing protecting the clients list. Adding a lock around the clients list is tricky because NBDClient structs are refcounted and may be freed from the export AioContext or the main loop thread. nbd_export_request_shutdown() -> client_close() -> nbd_client_put() is also tricky because the list lock would be held while indirectly dropping references to NDBClients. A simpler approach is to only allow nbd_client_put() and client_close() calls from the main loop thread. Then the NBD clients list is only accessed from the main loop thread and no fancy locking is needed. nbd_trip() just needs to reschedule itself in the main loop AioContext before calling nbd_client_put() and client_close(). This costs more CPU cycles per NBD request so add nbd_client_put_nonzero() to optimize the common case where more references to NBDClient remain. Note that nbd_client_get() can still be called from either thread, so make NBDClient->refcount atomic. Signed-off-by: Stefan Hajnoczi Message-ID: <20231221192452.1785567-6-stefanha@redhat.com> Reviewed-by: Kevin Wolf Signed-off-by: Kevin Wolf --- nbd/server.c | 61 +++++++++++++++++++++++++++++++++++++++++++--------- 1 file changed, 51 insertions(+), 10 deletions(-) diff --git a/nbd/server.c b/nbd/server.c index 0b09ccc8dc..e91e2e0903 100644 --- a/nbd/server.c +++ b/nbd/server.c @@ -122,7 +122,7 @@ struct NBDMetaContexts { }; struct NBDClient { - int refcount; + int refcount; /* atomic */ void (*close_fn)(NBDClient *client, bool negotiated); NBDExport *exp; @@ -1501,14 +1501,17 @@ static int coroutine_fn nbd_receive_request(NBDClient *client, NBDRequest *reque #define MAX_NBD_REQUESTS 16 +/* Runs in export AioContext and main loop thread */ void nbd_client_get(NBDClient *client) { - client->refcount++; + qatomic_inc(&client->refcount); } void nbd_client_put(NBDClient *client) { - if (--client->refcount == 0) { + assert(qemu_in_main_thread()); + + if (qatomic_fetch_dec(&client->refcount) == 1) { /* The last reference should be dropped by client->close, * which is called by client_close. */ @@ -1529,8 +1532,35 @@ void nbd_client_put(NBDClient *client) } } +/* + * Tries to release the reference to @client, but only if other references + * remain. This is an optimization for the common case where we want to avoid + * the expense of scheduling nbd_client_put() in the main loop thread. + * + * Returns true upon success or false if the reference was not released because + * it is the last reference. + */ +static bool nbd_client_put_nonzero(NBDClient *client) +{ + int old = qatomic_read(&client->refcount); + int expected; + + do { + if (old == 1) { + return false; + } + + expected = old; + old = qatomic_cmpxchg(&client->refcount, expected, expected - 1); + } while (old != expected); + + return true; +} + static void client_close(NBDClient *client, bool negotiated) { + assert(qemu_in_main_thread()); + if (client->closing) { return; } @@ -2933,15 +2963,20 @@ static coroutine_fn int nbd_handle_request(NBDClient *client, static coroutine_fn void nbd_trip(void *opaque) { NBDClient *client = opaque; - NBDRequestData *req; + NBDRequestData *req = NULL; NBDRequest request = { 0 }; /* GCC thinks it can be used uninitialized */ int ret; Error *local_err = NULL; + /* + * Note that nbd_client_put() and client_close() must be called from the + * main loop thread. Use aio_co_reschedule_self() to switch AioContext + * before calling these functions. + */ + trace_nbd_trip(); if (client->closing) { - nbd_client_put(client); - return; + goto done; } if (client->quiescing) { @@ -2949,10 +2984,9 @@ static coroutine_fn void nbd_trip(void *opaque) * We're switching between AIO contexts. Don't attempt to receive a new * request and kick the main context which may be waiting for us. */ - nbd_client_put(client); client->recv_coroutine = NULL; aio_wait_kick(); - return; + goto done; } req = nbd_request_get(client); @@ -3012,8 +3046,13 @@ static coroutine_fn void nbd_trip(void *opaque) qio_channel_set_cork(client->ioc, false); done: - nbd_request_put(req); - nbd_client_put(client); + if (req) { + nbd_request_put(req); + } + if (!nbd_client_put_nonzero(client)) { + aio_co_reschedule_self(qemu_get_aio_context()); + nbd_client_put(client); + } return; disconnect: @@ -3021,6 +3060,8 @@ disconnect: error_reportf_err(local_err, "Disconnect client, due to: "); } nbd_request_put(req); + + aio_co_reschedule_self(qemu_get_aio_context()); client_close(client, true); nbd_client_put(client); } -- 2.39.3