Received: from mga05.intel.com (mga05.intel.com [192.55.52.43]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id 8FFA02CAE for ; Fri, 28 Jan 2022 00:38:45 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=intel.com; i=@intel.com; q=dns/txt; s=Intel; t=1643330325; x=1674866325; h=from:to:subject:date:message-id:in-reply-to:references: mime-version:content-transfer-encoding; bh=nGeG430NBJeF9Y+vsoUaxacWf29cVhQeW2t6F+8m2pc=; b=EGERoqDCJvTaLE9i+La5rQ91CgRhcfleJOYgYI+pXkKZ1rbBWKsAGWlq S0DbxZuvdFxrkuX0noUEQs0Agm3mNHPsPfn6aX1C+BkUwHPNi1ekmq+YO pvTm6zQ3tRUxyc5BrALjsbw8nxsi6dO5rqqabnacPYR83bEKKih6TQRCR T+3l7lIqJLLXS722KuRJJ5JA52E8g0oykP0fRujQ5Eh9xNDiqfQtm7QM1 yuXW2yu8n5qBK+l4hSfoSPNpChpakwAuBukQHKkTx7/VNnyP2eMS7U+AJ ExxkA/QLloXad8TQuio0J4pmp91iOZt3wim1mhRLzUkHAWTZ9IBm4uu1i Q==; X-IronPort-AV: E=McAfee;i="6200,9189,10239"; a="333358332" X-IronPort-AV: E=Sophos;i="5.88,322,1635231600"; d="scan'208";a="333358332" Received: from orsmga006.jf.intel.com ([10.7.209.51]) by fmsmga105.fm.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 27 Jan 2022 16:38:42 -0800 X-IronPort-AV: E=Sophos;i="5.88,322,1635231600"; d="scan'208";a="480527112" Received: from otc-tsn-4.jf.intel.com ([10.23.153.135]) by orsmga006-auth.jf.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 27 Jan 2022 16:38:41 -0800 From: Kishen Maloor To: kishen.maloor@intel.com, mptcp@lists.linux.dev Subject: [PATCH mptcp-next v3 03/14] mptcp: handle local addrs announced by userspace PMs Date: Thu, 27 Jan 2022 19:38:25 -0500 Message-Id: <20220128003836.2732694-4-kishen.maloor@intel.com> X-Mailer: git-send-email 2.31.1 In-Reply-To: <20220128003836.2732694-1-kishen.maloor@intel.com> References: <20220128003836.2732694-1-kishen.maloor@intel.com> Precedence: bulk X-Mailing-List: mptcp@lists.linux.dev List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 Content-Transfer-Encoding: 8bit This change adds a new internal function to store/retrieve local addrs announced by userspace PM implementations to/from its kernel context. The function captures the requirements of three scenarios: 1) ADD_ADDR announcements (which require that a local id be provided), 2) retrieving the local id associated with an address, also where one may need to be assigned, and 3) reissuance of ADD_ADDRs when there's a successful match of addr/id. The list of all stored local addr entries is held under the MPTCP sock structure. This list, if not released by the REMOVE_ADDR flow is freed while the sock is destructed. Additionally, this function enforces the kernel imposed limit on the number of local addresses that may be used over a connection. Signed-off-by: Kishen Maloor --- v3: incorporate the new sysctl configurable limit on the # of local addresses that may be populated by userspace PMs --- net/mptcp/pm_netlink.c | 88 ++++++++++++++++++++++++++++++++++++++++++ net/mptcp/protocol.c | 2 + net/mptcp/protocol.h | 2 + 3 files changed, 92 insertions(+) diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c index 726dc0a56fca..ebec3610bb38 100644 --- a/net/mptcp/pm_netlink.c +++ b/net/mptcp/pm_netlink.c @@ -511,6 +511,34 @@ static bool mptcp_pm_alloc_anno_list(struct mptcp_sock *msk, return true; } +void mptcp_free_local_addr_list(struct mptcp_sock *msk) +{ + struct mptcp_pm_addr_entry *entry, *tmp; + struct sock *sk = (struct sock *)msk; + struct pm_nl_pernet *pernet; + LIST_HEAD(free_list); + + if (READ_ONCE(msk->pm.pm_type) == MPTCP_PM_TYPE_KERNEL) + return; + + pernet = net_generic(sock_net(sk), pm_nl_pernet_id); + + pr_debug("msk=%p", msk); + + mptcp_data_lock(sk); + list_splice_init(&msk->local_addr_list, &free_list); + spin_lock_bh(&msk->pm.lock); + msk->pm.local_addr_used = 0; + spin_unlock_bh(&msk->pm.lock); + mptcp_data_unlock(sk); + + list_for_each_entry_safe(entry, tmp, &free_list, list) { + if (entry->lsk_ref) + lsk_list_release(pernet, entry->lsk_ref); + kfree(entry); + } +} + void mptcp_pm_free_anno_list(struct mptcp_sock *msk) { struct mptcp_pm_add_entry *entry, *tmp; @@ -1007,6 +1035,66 @@ static bool address_use_port(struct mptcp_pm_addr_entry *entry) MPTCP_PM_ADDR_FLAG_SIGNAL; } +static int mptcp_userspace_pm_append_new_local_addr(struct mptcp_sock *msk, + struct mptcp_pm_addr_entry *entry) +{ + DECLARE_BITMAP(id_bitmap, MPTCP_PM_MAX_ADDR_ID + 1); + struct mptcp_pm_addr_entry *match = NULL; + struct sock *sk = (struct sock *)msk; + struct mptcp_pm_addr_entry *e; + bool addr_match = false; + bool id_match = false; + int ret = -EINVAL; + + bitmap_zero(id_bitmap, MPTCP_PM_MAX_ADDR_ID + 1); + + mptcp_data_lock(sk); + list_for_each_entry(e, &msk->local_addr_list, list) { + addr_match = addresses_equal(&e->addr, &entry->addr, true); + if (addr_match && entry->addr.id == 0) + entry->addr.id = e->addr.id; + id_match = (e->addr.id == entry->addr.id); + if (addr_match && id_match) { + match = e; + break; + } else if (addr_match || id_match) { + break; + } + __set_bit(e->addr.id, id_bitmap); + } + + if (!match && !addr_match && !id_match) { + spin_lock_bh(&msk->pm.lock); + if (msk->pm.local_addr_used < + mptcp_get_userspace_pm_local_addr_max(sock_net(sk))) { + e = kmalloc(sizeof(*e), GFP_ATOMIC); + if (!e) { + mptcp_data_unlock(sk); + return -ENOMEM; + } + + *e = *entry; + if (!e->addr.id) + e->addr.id = find_next_zero_bit(id_bitmap, + MPTCP_PM_MAX_ADDR_ID + 1, + 1); + list_add_tail_rcu(&e->list, &msk->local_addr_list); + ++msk->pm.local_addr_used; + ret = e->addr.id; + + if (e->lsk_ref && e->addr.port) + lsk_list_add_ref(e->lsk_ref); + } + spin_unlock_bh(&msk->pm.lock); + } else if (match) { + ret = entry->addr.id; + } + + mptcp_data_unlock(sk); + + return ret; +} + static int mptcp_pm_nl_append_new_local_addr(struct pm_nl_pernet *pernet, struct mptcp_pm_addr_entry *entry) { diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index 7c591177c3e8..82b4f9b76f42 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -2540,6 +2540,7 @@ static int __mptcp_init_sock(struct sock *sk) INIT_LIST_HEAD(&msk->conn_list); INIT_LIST_HEAD(&msk->join_list); INIT_LIST_HEAD(&msk->rtx_queue); + INIT_LIST_HEAD(&msk->local_addr_list); INIT_WORK(&msk->work, mptcp_worker); __skb_queue_head_init(&msk->receive_queue); msk->out_of_order_queue = RB_ROOT; @@ -3036,6 +3037,7 @@ void mptcp_destroy_common(struct mptcp_sock *msk) msk->rmem_fwd_alloc = 0; mptcp_token_destroy(msk); mptcp_pm_free_anno_list(msk); + mptcp_free_local_addr_list(msk); } static void mptcp_destroy(struct sock *sk) diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index 6cfa8ec26482..dbf0c134e923 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -281,6 +281,7 @@ struct mptcp_sock { struct sk_buff_head receive_queue; struct list_head conn_list; struct list_head rtx_queue; + struct list_head local_addr_list; struct mptcp_data_frag *first_pending; struct list_head join_list; struct socket *subflow; /* outgoing connect/listener/!mp_capable */ @@ -733,6 +734,7 @@ struct mptcp_sock *mptcp_token_get_sock(struct net *net, u32 token); struct mptcp_sock *mptcp_token_iter_next(const struct net *net, long *s_slot, long *s_num); void mptcp_token_destroy(struct mptcp_sock *msk); +void mptcp_free_local_addr_list(struct mptcp_sock *msk); void mptcp_crypto_key_sha(u64 key, u32 *token, u64 *idsn); -- 2.31.1