Lockdep splat in RXE (softRoCE) driver in xarray accesses
Hi Zhu, Bob, Steve,
There seems to be a locking bug in the softRoCE driver when mounting a cifs share. See attached trace. I'm guessing the problem is that a softirq handler is accessing the xarray, but other accesses to the xarray aren't guarded by _bh or _irq markers on the lock primitives.
I wonder if rxe_pool_get_index() should just rely on the RCU read lock and not take the spinlock.
Alternatively, __rxe_add_to_pool() should be using xa_alloc_cyclic_bh() or xa_alloc_cyclic_irq().
I used the following commands:
rdma link add rxe0 type rxe netdev enp6s0 # andromeda, softRoCE mount //192.168.6.1/scratch /xfstest.scratch -o user=shares,rdma,pass=...
talking to ksmbd on the other side.
Kernel is v5.18-rc6.
David
---
infiniband rxe0: set active
infiniband rxe0: added enp6s0
RDS/IB: rxe0: added
CIFS: No dialect specified on mount. Default has changed to a more secure dialect, SMB2.1 or later (e.g. SMB3.1.1), from CIFS (SMB1). To use the less secure SMB1 dialect to access old servers which do not support SMB3.1.1 (or even SMB3 or SMB2.1) specify vers=1.0 on mount.
CIFS: Attempting to mount \\192.168.6.1\scratch
================================
WARNING: inconsistent lock state
5.18.0-rc6-build2+ #465 Not tainted
--------------------------------
inconsistent {SOFTIRQ-ON-W} -> {IN-SOFTIRQ-W} usage.
ksoftirqd/1/20 [HC0[0]:SC1[1]:HE0:SE0] takes:ffff888134d11310 (&xa->xa_lock#12){+.?.}-{2:2}, at: rxe_pool_get_index+0x19/0x69 {SOFTIRQ-ON-W} state was registered at:
mark_usage+0x169/0x17b __lock_acquire+0x50c/0x96a lock_acquire+0x2f4/0x37b _raw_spin_lock+0x2f/0x39 xa_alloc_cyclic.constprop.0+0x20/0x55 __rxe_add_to_pool+0xe3/0xf2 __ib_alloc_pd+0xa2/0x26b ib_mad_port_open+0x1ac/0x4a1 ib_mad_init_device+0x9b/0x1b9 add_client_context+0x133/0x1b3 enable_device_and_get+0x129/0x248 ib_register_device+0x256/0x2fd rxe_register_device+0x18e/0x1b7 rxe_net_add+0x57/0x71 rxe_newlink+0x71/0x8e nldev_newlink+0x200/0x26a rdma_nl_rcv_msg+0x260/0x2ab rdma_nl_rcv+0x108/0x1a7 netlink_unicast+0x1fc/0x2b3 netlink_sendmsg+0x4ce/0x51b sock_sendmsg_nosec+0x41/0x4f __sys_sendto+0x157/0x1cc __x64_sys_sendto+0x76/0x82 do_syscall_64+0x39/0x46 entry_SYSCALL_64_after_hwframe+0x44/0xae irq event stamp: 194111 hardirqs last enabled at (194110): [<ffffffff81094eb2>] __local_bh_enable_ip+0xb8/0xcc hardirqs last disabled at (194111): [<ffffffff82040077>] _raw_spin_lock_irqsave+0x1b/0x51 softirqs last enabled at (194100): [<ffffffff8240043a>] __do_softirq+0x43a/0x489 softirqs last disabled at (194105): [<ffffffff81094d30>] run_ksoftirqd+0x31/0x56
other info that might help us debug this:
Possible unsafe locking scenario:
CPU0
----
lock(&xa->xa_lock#12);
<Interrupt>
lock(&xa->xa_lock#12);*** DEADLOCK ***
no locks held by ksoftirqd/1/20.
stack backtrace: CPU: 1 PID: 20 Comm: ksoftirqd/1 Not tainted 5.18.0-rc6-build2+ #465 Hardware name: ASUS All Series/H97-PLUS, BIOS 2306 10/09/2014 Call Trace: <TASK> dump_stack_lvl+0x45/0x59 valid_state+0x56/0x61 mark_lock_irq+0x9b/0x2ec ? ret_from_fork+0x1f/0x30 ? valid_state+0x61/0x61 ? stack_trace_save+0x8f/0xbe ? filter_irq_stacks+0x58/0x58 ? jhash.constprop.0+0x1ad/0x202 ? save_trace+0x17c/0x196 mark_lock.part.0+0x10c/0x164 mark_usage+0xe6/0x17b __lock_acquire+0x50c/0x96a lock_acquire+0x2f4/0x37b ? rxe_pool_get_index+0x19/0x69 ? rcu_read_unlock+0x52/0x52 ? jhash.constprop.0+0x1ad/0x202 ? lockdep_unlock+0xde/0xe6 ? validate_chain+0x44a/0x4a8 ? req_next_wqe+0x312/0x363 _raw_spin_lock_irqsave+0x41/0x51 ? rxe_pool_get_index+0x19/0x69 rxe_pool_get_index+0x19/0x69 rxe_get_av+0xbe/0x14b rxe_requester+0x6b5/0xbb0 ? rnr_nak_timer+0x16/0x16 ? lock_downgrade+0xad/0xad ? rcu_read_lock_bh_held+0xab/0xab ? __wake_up+0xf/0xf ? mark_held_locks+0x1f/0x78 ? __local_bh_enable_ip+0xb8/0xcc ? rnr_nak_timer+0x16/0x16 rxe_do_task+0xb5/0x13d ? rxe_detach_mcast+0x1d6/0x1d6 tasklet_action_common.constprop.0+0xda/0x145 __do_softirq+0x202/0x489 ? __irq_exit_rcu+0x108/0x108 ? _local_bh_enable+0x1c/0x1c run_ksoftirqd+0x31/0x56 smpboot_thread_fn+0x35c/0x376 ? sort_range+0x1c/0x1c kthread+0x164/0x173 ? kthread_complete_and_exit+0x20/0x20 ret_from_fork+0x1f/0x30 </TASK>
CIFS: VFS: RDMA transport established
Quoted 13 lines · David Howells
Hi Zhu, Bob, Steve,
There seems to be a locking bug in the softRoCE driver when mounting a cifs share. See attached trace. I'm guessing the problem is that a softirq handler is accessing the xarray, but other accesses to the xarray aren't guarded by
_bhor_irqmarkers on the lock primitives.I wonder if
rxe_pool_get_index()should just rely on the RCU read lock and not take the spinlock.Alternatively,
__rxe_add_to_pool()should be usingxa_alloc_cyclic_bh()orxa_alloc_cyclic_irq().
Quoted 6 lines
I used the following commands:
rdma link add rxe0 type rxe netdev enp6s0 # andromeda, softRoCE mount //192.168.6.1/scratch /xfstest.scratch -o user=shares,rdma,pass=...
talking to ksmbd on the other side.
It seems a known bug. Please make tests with the patches in the attachment. If not work, please let me know.
Thanks a lot.
Zhu Yanjun
Quoted 112 lines
Kernel is v5.18-rc6.
David
---
infiniband rxe0: set active
infiniband rxe0: added enp6s0
RDS/IB: rxe0: added
CIFS: No dialect specified on mount. Default has changed to a more secure dialect, SMB2.1 or later (e.g. SMB3.1.1), from CIFS (SMB1). To use the less secure SMB1 dialect to access old servers which do not support SMB3.1.1 (or even SMB3 or SMB2.1) specify vers=1.0 on mount.
CIFS: Attempting to mount \\192.168.6.1\scratch================================
WARNING: inconsistent lock state
5.18.0-rc6-build2+ #465 Not tainted
--------------------------------
inconsistent {SOFTIRQ-ON-W} -> {IN-SOFTIRQ-W} usage.
ksoftirqd/1/20 [HC0[0]:SC1[1]:HE0:SE0] takes:ffff888134d11310(&xa->xa_lock#12){+.?.}-{2:2}, at:rxe_pool_get_index+0x19/0x69{SOFTIRQ-ON-W} state was registered at:mark_usage+0x169/0x17b __lock_acquire+0x50c/0x96a lock_acquire+0x2f4/0x37b _raw_spin_lock+0x2f/0x39 xa_alloc_cyclic.constprop.0+0x20/0x55 __rxe_add_to_pool+0xe3/0xf2 __ib_alloc_pd+0xa2/0x26b ib_mad_port_open+0x1ac/0x4a1 ib_mad_init_device+0x9b/0x1b9 add_client_context+0x133/0x1b3 enable_device_and_get+0x129/0x248 ib_register_device+0x256/0x2fd rxe_register_device+0x18e/0x1b7 rxe_net_add+0x57/0x71 rxe_newlink+0x71/0x8e nldev_newlink+0x200/0x26a rdma_nl_rcv_msg+0x260/0x2ab rdma_nl_rcv+0x108/0x1a7 netlink_unicast+0x1fc/0x2b3 netlink_sendmsg+0x4ce/0x51b sock_sendmsg_nosec+0x41/0x4f __sys_sendto+0x157/0x1cc __x64_sys_sendto+0x76/0x82 do_syscall_64+0x39/0x46 entry_SYSCALL_64_after_hwframe+0x44/0xae irq event stamp: 194111 hardirqs last enabled at (194110): [<ffffffff81094eb2>] __local_bh_enable_ip+0xb8/0xcc hardirqs last disabled at (194111): [<ffffffff82040077>] _raw_spin_lock_irqsave+0x1b/0x51 softirqs last enabled at (194100): [<ffffffff8240043a>] __do_softirq+0x43a/0x489 softirqs last disabled at (194105): [<ffffffff81094d30>] run_ksoftirqd+0x31/0x56other info that might help us debug this:
Possible unsafe locking scenario:CPU0 ---- lock(&xa->xa_lock#12); <Interrupt> lock(&xa->xa_lock#12);*** DEADLOCK ***
no locks held by ksoftirqd/1/20.
stack backtrace: CPU: 1 PID: 20 Comm: ksoftirqd/1 Not tainted 5.18.0-rc6-build2+ #465 Hardware name: ASUS All Series/H97-PLUS, BIOS 2306 10/09/2014 Call Trace: <TASK> dump_stack_lvl+0x45/0x59 valid_state+0x56/0x61 mark_lock_irq+0x9b/0x2ec ? ret_from_fork+0x1f/0x30 ? valid_state+0x61/0x61 ? stack_trace_save+0x8f/0xbe ? filter_irq_stacks+0x58/0x58 ? jhash.constprop.0+0x1ad/0x202 ? save_trace+0x17c/0x196 mark_lock.part.0+0x10c/0x164 mark_usage+0xe6/0x17b __lock_acquire+0x50c/0x96a lock_acquire+0x2f4/0x37b ? rxe_pool_get_index+0x19/0x69 ? rcu_read_unlock+0x52/0x52 ? jhash.constprop.0+0x1ad/0x202 ? lockdep_unlock+0xde/0xe6 ? validate_chain+0x44a/0x4a8 ? req_next_wqe+0x312/0x363 _raw_spin_lock_irqsave+0x41/0x51 ? rxe_pool_get_index+0x19/0x69 rxe_pool_get_index+0x19/0x69 rxe_get_av+0xbe/0x14b rxe_requester+0x6b5/0xbb0 ? rnr_nak_timer+0x16/0x16 ? lock_downgrade+0xad/0xad ? rcu_read_lock_bh_held+0xab/0xab ? __wake_up+0xf/0xf ? mark_held_locks+0x1f/0x78 ? __local_bh_enable_ip+0xb8/0xcc ? rnr_nak_timer+0x16/0x16 rxe_do_task+0xb5/0x13d ? rxe_detach_mcast+0x1d6/0x1d6 tasklet_action_common.constprop.0+0xda/0x145 __do_softirq+0x202/0x489 ? __irq_exit_rcu+0x108/0x108 ? _local_bh_enable+0x1c/0x1c run_ksoftirqd+0x31/0x56 smpboot_thread_fn+0x35c/0x376 ? sort_range+0x1c/0x1c kthread+0x164/0x173 ? kthread_complete_and_exit+0x20/0x20 ret_from_fork+0x1f/0x30 </TASK>
Quoted 2 lines
CIFS: VFS: RDMA transport established
From patchwork Fri Apr 22 19:44:13 2022
Content-Type: text/plain; charset="utf-8"
MIME-Version: 1.0
Content-Transfer-Encoding: 7bit
X-Patchwork-Submitter: Yanjun Zhu <[email protected]>
X-Patchwork-Id: 12822712
X-Patchwork-Delegate: [email protected]
Return-Path: <[email protected]>
X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on
aws-us-west-2-korg-lkml-1.web.codeaurora.org
Received: from vger.kernel.org (vger.kernel.org [23.128.96.18])
by smtp.lore.kernel.org (Postfix) with ESMTP id B8DA1C433F5 for <[email protected]>; Fri, 22 Apr 2022 03:17:50 +0000 (UTC) Received: ([email protected]) by vger.kernel.org via listexpand id S242102AbiDVDUk (ORCPT <rfc822;[email protected]>); Thu, 21 Apr 2022 23:20:40 -0400
Received: from lindbergh.monkeyblade.net ([23.128.96.19]:60894 "EHLO
lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1443716AbiDVDUj (ORCPT <rfc822;[email protected]>); Thu, 21 Apr 2022 23:20:39 -0400
Received: from mga05.intel.com (mga05.intel.com [192.55.52.43])
by lindbergh.monkeyblade.net (Postfix) with ESMTPS id 3DCFA4D623 for <[email protected]>;
Thu, 21 Apr 2022 20:17:47 -0700 (PDT)
X-IronPort-AV: E=McAfee;i="6400,9594,10324"; a="350994641"
X-IronPort-AV: E=Sophos;i="5.90,280,1643702400";
d="scan'208";a="350994641"
Received: from fmsmga008.fm.intel.com ([10.253.24.58])
by fmsmga105.fm.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384;
21 Apr 2022 20:17:46 -0700
X-ExtLoop1: 1
X-IronPort-AV: E=Sophos;i="5.90,280,1643702400";
d="scan'208";a="615218036"
Received: from unknown (HELO intel-71.bj.intel.com) ([10.238.154.71])
by fmsmga008.fm.intel.com with ESMTP; 21 Apr 2022 20:17:45 -0700
From: [email protected]
To: [email protected], [email protected], [email protected],
[email protected]
Cc: Yi Zhang <[email protected]>
Subject: [PATCHv6 1/4] RDMA/rxe: Fix dead lock caused by __rxe_add_to_pool
interrupted by rxe_pool_get_index
Date: Fri, 22 Apr 2022 15:44:13 -0400
Message-Id: <[email protected]>
X-Mailer: git-send-email 2.27.0
MIME-Version: 1.0
Precedence: bulk
List-ID: <linux-rdma.vger.kernel.org>
X-Mailing-List: [email protected]
From: Zhu Yanjun <[email protected]>
This is a dead lock problem.
The ah_pool xa_lock first is acquired in this:
{SOFTIRQ-ON-W} state was registered at:
lock_acquire+0x1d2/0x5a0 _raw_spin_lock+0x33/0x80 __rxe_add_to_pool+0x183/0x230 [rdma_rxe]
Then ah_pool xa_lock is acquired in this:
{IN-SOFTIRQ-W}:
Call Trace: <TASK> dump_stack_lvl+0x44/0x57 mark_lock.part.52.cold.79+0x3c/0x46 __lock_acquire+0x1565/0x34a0 lock_acquire+0x1d2/0x5a0 _raw_spin_lock_irqsave+0x42/0x90 rxe_pool_get_index+0x72/0x1d0 [rdma_rxe] rxe_get_av+0x168/0x2a0 [rdma_rxe] </TASK>
From the above, in the function __rxe_add_to_pool, xa_lock is acquired. Then the function __rxe_add_to_pool is interrupted by softirq. The function rxe_pool_get_index will also acquire xa_lock.
Finally, the dead lock appears.
CPU0
----
lock(&xa->xa_lock#15); <----- __rxe_add_to_pool
<Interrupt>
lock(&xa->xa_lock#15); <---- rxe_pool_get_index
*** DEADLOCK ***---V5->V6: One dead lock fix in one commitV4->V5: Commit logs are changed.V3->V4: xa_lock_irq locks are used.V2->V3: __rxe_add_to_pool is between spin_lock and spin_unlock, so
GFP_ATOMIC is used in __rxe_add_to_pool.V1->V2: Replace GFP_KERNEL with GFP_ATOMIC
--- drivers/infiniband/sw/rxe/rxe_pool.c | 11 +++++++---- 1 file changed, 7 insertions(+), 4 deletions(-)
drivers/infiniband/sw/rxe/rxe_pool.c +7 -4
@@ -106,7 +106,7 @@ void rxe_pool_init(struct rxe_dev *rxe, struct rxe_pool *pool,atomic_set (&pool->num_elem,0 ); -xa_init_flags (&pool->xa,XA_FLAGS_ALLOC ); +xa_init_flags (&pool->xa,XA_FLAGS_ALLOC |XA_FLAGS_LOCK_IRQ ); pool->limit.min = info->min_index; pool->limit.max = info->max_index; }
@@ -155,6 +155,7 @@ void *rxe_alloc(struct rxe_pool *pool)int __rxe_add_to_pool (struct rxe_pool *pool,struct rxe_pool_elem *elem) {int err; +unsigned long flags;if (WARN_ON (pool->flags &RXE_POOL_ALLOC ))return -EINVAL ;
@@ -166,8 +167,10 @@ int __rxe_add_to_pool(struct rxe_pool *pool, struct rxe_pool_elem *elem) elem->obj = (u8 *)elem - pool->elem_offset;kref_init (&elem->ref_cnt); - err =xa_alloc_cyclic (&pool->xa, &elem->index, elem, pool->limit, - &pool->next,GFP_KERNEL ); +xa_lock_irqsave (&pool->xa, flags); + err =__xa_alloc_cyclic (&pool->xa, &elem->index, elem, pool->limit, + &pool->next,GFP_ATOMIC ); +xa_unlock_irqrestore (&pool->xa, flags);if (err) goto err_cnt;
@@ -201,7 +204,7 @@ static void rxe_elem_release(struct kref *kref)struct rxe_pool_elem *elem =container_of (kref,typeof (*elem), ref_cnt);struct rxe_pool *pool = elem->pool; -xa_erase (&pool->xa, elem->index); +xa_erase_irq (&pool->xa, elem->index);if (pool->cleanup) pool->cleanup (elem);
From patchwork Fri Apr 22 19:44:14 2022
Content-Type: text/plain; charset="utf-8"
MIME-Version: 1.0
Content-Transfer-Encoding: 7bit
X-Patchwork-Submitter: Yanjun Zhu <[email protected]>
X-Patchwork-Id: 12822713
X-Patchwork-Delegate: [email protected]
Return-Path: <[email protected]>
X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on
aws-us-west-2-korg-lkml-1.web.codeaurora.org
Received: from vger.kernel.org (vger.kernel.org [23.128.96.18])
by smtp.lore.kernel.org (Postfix) with ESMTP id 6C7CAC433EF for <[email protected]>; Fri, 22 Apr 2022 03:17:51 +0000 (UTC) Received: ([email protected]) by vger.kernel.org via listexpand id S1443716AbiDVDUl (ORCPT <rfc822;[email protected]>); Thu, 21 Apr 2022 23:20:41 -0400
Received: from lindbergh.monkeyblade.net ([23.128.96.19]:60900 "EHLO
lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1443717AbiDVDUj (ORCPT <rfc822;[email protected]>); Thu, 21 Apr 2022 23:20:39 -0400
Received: from mga05.intel.com (mga05.intel.com [192.55.52.43])
by lindbergh.monkeyblade.net (Postfix) with ESMTPS id 98FCB44766 for <[email protected]>;
Thu, 21 Apr 2022 20:17:48 -0700 (PDT)
X-IronPort-AV: E=McAfee;i="6400,9594,10324"; a="350994645"
X-IronPort-AV: E=Sophos;i="5.90,280,1643702400";
d="scan'208";a="350994645"
Received: from fmsmga008.fm.intel.com ([10.253.24.58])
by fmsmga105.fm.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384;
21 Apr 2022 20:17:48 -0700
X-ExtLoop1: 1
X-IronPort-AV: E=Sophos;i="5.90,280,1643702400";
d="scan'208";a="615218047"
Received: from unknown (HELO intel-71.bj.intel.com) ([10.238.154.71])
by fmsmga008.fm.intel.com with ESMTP; 21 Apr 2022 20:17:46 -0700
From: [email protected]
To: [email protected], [email protected], [email protected],
[email protected]
Cc: Yi Zhang <[email protected]>
Subject: [PATCH 2/4] RDMA/rxe: Fix dead lock caused by rxe_alloc interrupted
by rxe_pool_get_index
Date: Fri, 22 Apr 2022 15:44:14 -0400
Message-Id: <[email protected]>
X-Mailer: git-send-email 2.27.0
In-Reply-To: <[email protected]>
References: <[email protected]>
MIME-Version: 1.0
Precedence: bulk
List-ID: <linux-rdma.vger.kernel.org>
X-Mailing-List: [email protected]
From: Zhu Yanjun <[email protected]>
The ah_pool xa_lock first is acquired in this:
{SOFTIRQ-ON-W} state was registered at:
lock_acquire+0x1d2/0x5a0 _raw_spin_lock+0x33/0x80 rxe_alloc+0x1be/0x290 [rdma_rxe]
Then ah_pool xa_lock is acquired in this:
{IN-SOFTIRQ-W}:
<TASK> __lock_acquire+0x1565/0x34a0 lock_acquire+0x1d2/0x5a0 _raw_spin_lock_irqsave+0x42/0x90 rxe_pool_get_index+0x72/0x1d0 [rdma_rxe] </TASK>
From the above, in the function rxe_alloc,xa_lock is acquired. Then the function rxe_alloc
is interrupted by softirq. The functionrxe_pool_get_index will also acquire xa_lock.
Finally, the dead lock appears.
CPU0
----
lock(&xa->xa_lock#15); <----- rxe_alloc
<Interrupt>
lock(&xa->xa_lock#15); <---- rxe_pool_get_index
*** DEADLOCK ***--- drivers/infiniband/sw/rxe/rxe_pool.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)
drivers/infiniband/sw/rxe/rxe_pool.c +2 -2
@@ -138,8 +138,8 @@ void *rxe_alloc(struct rxe_pool *pool) elem->obj = obj;kref_init (&elem->ref_cnt); - err =xa_alloc_cyclic (&pool->xa, &elem->index, elem, pool->limit, - &pool->next,GFP_KERNEL ); + err =xa_alloc_cyclic_irq (&pool->xa, &elem->index, elem, pool->limit, + &pool->next,GFP_KERNEL );if (err) goto err_free;
From patchwork Fri Apr 22 19:44:15 2022
Content-Type: text/plain; charset="utf-8"
MIME-Version: 1.0
Content-Transfer-Encoding: 7bit
X-Patchwork-Submitter: Yanjun Zhu <[email protected]>
X-Patchwork-Id: 12822714
X-Patchwork-Delegate: [email protected]
Return-Path: <[email protected]>
X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on
aws-us-west-2-korg-lkml-1.web.codeaurora.org
Received: from vger.kernel.org (vger.kernel.org [23.128.96.18])
by smtp.lore.kernel.org (Postfix) with ESMTP id 3115DC433FE for <[email protected]>; Fri, 22 Apr 2022 03:17:52 +0000 (UTC) Received: ([email protected]) by vger.kernel.org via listexpand id S1443717AbiDVDUl (ORCPT <rfc822;[email protected]>); Thu, 21 Apr 2022 23:20:41 -0400
Received: from lindbergh.monkeyblade.net ([23.128.96.19]:60912 "EHLO
lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1443718AbiDVDUl (ORCPT <rfc822;[email protected]>); Thu, 21 Apr 2022 23:20:41 -0400
Received: from mga05.intel.com (mga05.intel.com [192.55.52.43])
by lindbergh.monkeyblade.net (Postfix) with ESMTPS id BC22C44766 for <[email protected]>;
Thu, 21 Apr 2022 20:17:49 -0700 (PDT)
X-IronPort-AV: E=McAfee;i="6400,9594,10324"; a="350994648"
X-IronPort-AV: E=Sophos;i="5.90,280,1643702400";
d="scan'208";a="350994648"
Received: from fmsmga008.fm.intel.com ([10.253.24.58])
by fmsmga105.fm.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384;
21 Apr 2022 20:17:49 -0700
X-ExtLoop1: 1
X-IronPort-AV: E=Sophos;i="5.90,280,1643702400";
d="scan'208";a="615218057"
Received: from unknown (HELO intel-71.bj.intel.com) ([10.238.154.71])
by fmsmga008.fm.intel.com with ESMTP; 21 Apr 2022 20:17:48 -0700
From: [email protected]
To: [email protected], [email protected], [email protected],
[email protected]
Subject: [PATCH 3/4] RDMA/rxe: Use different xa locks on different path
Date: Fri, 22 Apr 2022 15:44:15 -0400
Message-Id: <[email protected]>
X-Mailer: git-send-email 2.27.0
In-Reply-To: <[email protected]>
References: <[email protected]>
MIME-Version: 1.0
Precedence: bulk
List-ID: <linux-rdma.vger.kernel.org>
X-Mailing-List: [email protected]
From: Zhu Yanjun <[email protected]>
The function __rxe_add_to_pool is called on different paths, and the requirement of the locks is different. The function rxe_create_ah requires xa_lock_irqsave/irqrestore while others only require xa_lock_irq.
--- drivers/infiniband/sw/rxe/rxe_pool.c | 16 +++++++++++----- 1 file changed, 11 insertions(+), 5 deletions(-)
drivers/infiniband/sw/rxe/rxe_pool.c +11 -5
@@ -155,7 +155,6 @@ void *rxe_alloc(struct rxe_pool *pool)int __rxe_add_to_pool (struct rxe_pool *pool,struct rxe_pool_elem *elem) {int err; -unsigned long flags;if (WARN_ON (pool->flags &RXE_POOL_ALLOC ))return -EINVAL ;
@@ -167,10 +166,17 @@ int __rxe_add_to_pool(struct rxe_pool *pool, struct rxe_pool_elem *elem) elem->obj = (u8 *)elem - pool->elem_offset;kref_init (&elem->ref_cnt); -xa_lock_irqsave (&pool->xa, flags); - err =__xa_alloc_cyclic (&pool->xa, &elem->index, elem, pool->limit, - &pool->next,GFP_ATOMIC ); -xa_unlock_irqrestore (&pool->xa, flags); +if (pool->type ==RXE_TYPE_AH ) { +unsigned long flags; + +xa_lock_irqsave (&pool->xa, flags); + err =__xa_alloc_cyclic (&pool->xa, &elem->index, elem, pool->limit, + &pool->next,GFP_ATOMIC ); +xa_unlock_irqrestore (&pool->xa, flags); + }else { + err =xa_alloc_cyclic_irq (&pool->xa, &elem->index, elem, pool->limit, + &pool->next,GFP_KERNEL ); + }if (err) goto err_cnt;
From patchwork Fri Apr 22 19:44:16 2022
Content-Type: text/plain; charset="utf-8"
MIME-Version: 1.0
Content-Transfer-Encoding: 7bit
X-Patchwork-Submitter: Yanjun Zhu <[email protected]>
X-Patchwork-Id: 12822715
X-Patchwork-Delegate: [email protected]
Return-Path: <[email protected]>
X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on
aws-us-west-2-korg-lkml-1.web.codeaurora.org
Received: from vger.kernel.org (vger.kernel.org [23.128.96.18])
by smtp.lore.kernel.org (Postfix) with ESMTP id 96A33C433F5 for <[email protected]>; Fri, 22 Apr 2022 03:17:55 +0000 (UTC) Received: ([email protected]) by vger.kernel.org via listexpand id S1443719AbiDVDUp (ORCPT <rfc822;[email protected]>); Thu, 21 Apr 2022 23:20:45 -0400
Received: from lindbergh.monkeyblade.net ([23.128.96.19]:60926 "EHLO
lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1443718AbiDVDUm (ORCPT <rfc822;[email protected]>); Thu, 21 Apr 2022 23:20:42 -0400
Received: from mga05.intel.com (mga05.intel.com [192.55.52.43])
by lindbergh.monkeyblade.net (Postfix) with ESMTPS id 349A844766 for <[email protected]>;
Thu, 21 Apr 2022 20:17:51 -0700 (PDT)
X-IronPort-AV: E=McAfee;i="6400,9594,10324"; a="350994649"
X-IronPort-AV: E=Sophos;i="5.90,280,1643702400";
d="scan'208";a="350994649"
Received: from fmsmga008.fm.intel.com ([10.253.24.58])
by fmsmga105.fm.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384;
21 Apr 2022 20:17:51 -0700
X-ExtLoop1: 1
X-IronPort-AV: E=Sophos;i="5.90,280,1643702400";
d="scan'208";a="615218071"
Received: from unknown (HELO intel-71.bj.intel.com) ([10.238.154.71])
by fmsmga008.fm.intel.com with ESMTP; 21 Apr 2022 20:17:49 -0700
From: [email protected]
To: [email protected], [email protected], [email protected],
[email protected]
Subject: [PATCH 4/4] RDMA/rxe: Check RDMA_CREATE_AH_SLEEPABLE in creating AH
Date: Fri, 22 Apr 2022 15:44:16 -0400
Message-Id: <[email protected]>
X-Mailer: git-send-email 2.27.0
In-Reply-To: <[email protected]>
References: <[email protected]>
MIME-Version: 1.0
Precedence: bulk
List-ID: <linux-rdma.vger.kernel.org>
X-Mailing-List: [email protected]
From: Zhu Yanjun <[email protected]>
During creating AH, the flag RDMA_CREATE_AH_SLEEPABLE should be tested.
--- drivers/infiniband/sw/rxe/rxe_mw.c | 2 +- drivers/infiniband/sw/rxe/rxe_pool.c | 14 ++++++++------ drivers/infiniband/sw/rxe/rxe_pool.h | 4 ++-- drivers/infiniband/sw/rxe/rxe_verbs.c | 18 ++++++++++++------ 4 files changed, 23 insertions(+), 15 deletions(-)
drivers/infiniband/sw/rxe/rxe_mw.c +1 -1
@@ -14,7 +14,7 @@ int rxe_alloc_mw(struct ib_mw *ibmw, struct ib_udata *udata)rxe_get (pd); - ret =rxe_add_to_pool (&rxe->mw_pool, mw); + ret =rxe_add_to_pool (&rxe->mw_pool, mw,GFP_KERNEL );if (ret) {rxe_put (pd);return ret;
drivers/infiniband/sw/rxe/rxe_pool.c +8 -6
@@ -152,7 +152,7 @@ void *rxe_alloc(struct rxe_pool *pool)return NULL ; } -int __rxe_add_to_pool (struct rxe_pool *pool,struct rxe_pool_elem *elem) +int __rxe_add_to_pool (struct rxe_pool *pool,struct rxe_pool_elem *elem,gfp_t gfp) {int err;
@@ -166,16 +166,18 @@ int __rxe_add_to_pool(struct rxe_pool *pool, struct rxe_pool_elem *elem) elem->obj = (u8 *)elem - pool->elem_offset;kref_init (&elem->ref_cnt); -if (pool->type ==RXE_TYPE_AH ) { +if ((pool->type ==RXE_TYPE_AH ) && (gfp &GFP_ATOMIC )) {unsigned long flags;xa_lock_irqsave (&pool->xa, flags); - err =__xa_alloc_cyclic (&pool->xa, &elem->index, elem, pool->limit, - &pool->next,GFP_ATOMIC ); + err =__xa_alloc_cyclic (&pool->xa, &elem->index, elem, + pool->limit, &pool->next, +GFP_ATOMIC );xa_unlock_irqrestore (&pool->xa, flags); }else { - err =xa_alloc_cyclic_irq (&pool->xa, &elem->index, elem, pool->limit, - &pool->next,GFP_KERNEL ); + err =xa_alloc_cyclic_irq (&pool->xa, &elem->index, elem, + pool->limit, &pool->next, +GFP_KERNEL ); }if (err) goto err_cnt;
drivers/infiniband/sw/rxe/rxe_pool.h +2 -2
@@ -62,9 +62,9 @@ void rxe_pool_cleanup(struct rxe_pool *pool);void *rxe_alloc (struct rxe_pool *pool);/* connect already allocated object to pool */ -int __rxe_add_to_pool (struct rxe_pool *pool,struct rxe_pool_elem *elem); +int __rxe_add_to_pool (struct rxe_pool *pool,struct rxe_pool_elem *elem,gfp_t gfp); -#define rxe_add_to_pool (pool, obj) __rxe_add_to_pool(pool, &(obj)->elem) +#define rxe_add_to_pool (pool, obj, gfp) __rxe_add_to_pool(pool, &(obj)->elem, gfp)/* lookup an indexed object from index. takes a reference on object */ void *rxe_pool_get_index (struct rxe_pool *pool,u32 index);
drivers/infiniband/sw/rxe/rxe_verbs.c +12 -6
@@ -108,7 +108,7 @@ static int rxe_alloc_ucontext(struct ib_ucontext *ibuc, struct ib_udata *udata)struct rxe_dev *rxe =to_rdev (ibuc->device);struct rxe_ucontext *uc =to_ruc (ibuc); -return rxe_add_to_pool (&rxe->uc_pool, uc); +return rxe_add_to_pool (&rxe->uc_pool, uc,GFP_KERNEL ); }static void rxe_dealloc_ucontext (struct ib_ucontext *ibuc)
@@ -142,7 +142,7 @@ static int rxe_alloc_pd(struct ib_pd *ibpd, struct ib_udata *udata)struct rxe_dev *rxe =to_rdev (ibpd->device);struct rxe_pd *pd =to_rpd (ibpd); -return rxe_add_to_pool (&rxe->pd_pool, pd); +return rxe_add_to_pool (&rxe->pd_pool, pd,GFP_KERNEL ); }static int rxe_dealloc_pd (struct ib_pd *ibpd,struct ib_udata *udata)
@@ -162,6 +162,7 @@ static int rxe_create_ah(struct ib_ah *ibah,struct rxe_ah *ah =to_rah (ibah);struct rxe_create_ah_resp __user *uresp =NULL ;int err; +gfp_t gfp;if (udata) {/* test if new user provider */
@@ -176,7 +177,12 @@ static int rxe_create_ah(struct ib_ah *ibah,if (err)return err; - err =rxe_add_to_pool (&rxe->ah_pool, ah); +if (init_attr->flags &RDMA_CREATE_AH_SLEEPABLE ) + gfp =GFP_KERNEL ; +else + gfp =GFP_ATOMIC ; + + err =rxe_add_to_pool (&rxe->ah_pool, ah, gfp);if (err)return err;
@@ -299,7 +305,7 @@ static int rxe_create_srq(struct ib_srq *ibsrq, struct ib_srq_init_attr *init,if (err) goto err1; - err =rxe_add_to_pool (&rxe->srq_pool, srq); + err =rxe_add_to_pool (&rxe->srq_pool, srq,GFP_KERNEL );if (err) goto err1;
@@ -431,7 +437,7 @@ static int rxe_create_qp(struct ib_qp *ibqp, struct ib_qp_init_attr *init, qp->is_user = false; } - err =rxe_add_to_pool (&rxe->qp_pool, qp); + err =rxe_add_to_pool (&rxe->qp_pool, qp,GFP_KERNEL );if (err)return err;
@@ -800,7 +806,7 @@ static int rxe_create_cq(struct ib_cq *ibcq, const struct ib_cq_init_attr *attr,if (err)return err; -return rxe_add_to_pool (&rxe->cq_pool, cq); +return rxe_add_to_pool (&rxe->cq_pool, cq,GFP_KERNEL ); }static int rxe_destroy_cq (struct ib_cq *ibcq,struct ib_udata *udata)