From: Bob Pearson <rpearsonhpe@gmail.com>
To: jgg@nvidia.com, zyjzyj2000@gmail.com, linux-rdma@vger.kernel.org
Cc: Bob Pearson <rpearsonhpe@gmail.com>
Subject: [RFC PATCH v9 18/26] RDMA/rxe: Convert mca read locking to RCU
Date: Thu, 27 Jan 2022 15:37:47 -0600 [thread overview]
Message-ID: <20220127213755.31697-19-rpearsonhpe@gmail.com> (raw)
In-Reply-To: <20220127213755.31697-1-rpearsonhpe@gmail.com>
Replace spinlocks with rcu read locks for read side operations
on mca.n rxe_recv.c and rxe_mcast.c. Use rcu list extensions on
write side operations and keep spinlocks to separate write threads.
Signed-off-by: Bob Pearson <rpearsonhpe@gmail.com>
---
drivers/infiniband/sw/rxe/rxe_mcast.c | 57 ++++++++++++++++-----------
drivers/infiniband/sw/rxe/rxe_recv.c | 6 +--
drivers/infiniband/sw/rxe/rxe_verbs.h | 1 +
3 files changed, 39 insertions(+), 25 deletions(-)
diff --git a/drivers/infiniband/sw/rxe/rxe_mcast.c b/drivers/infiniband/sw/rxe/rxe_mcast.c
index 865e6e85084f..c193bd4975f7 100644
--- a/drivers/infiniband/sw/rxe/rxe_mcast.c
+++ b/drivers/infiniband/sw/rxe/rxe_mcast.c
@@ -27,7 +27,8 @@
* the mcg is created and an extra kref_put when the qp count decreases
* to zero.
*
- * The qp list and the red-black tree are protected by a single
+ * The qp list is protected for read operations by RCU and the qp list and
+ * the red-black tree are protected for write operations by a single
* rxe->mcg_lock per device.
*/
@@ -270,7 +271,7 @@ void rxe_cleanup_mcg(struct kref *kref)
}
/**
- * __rxe_init_mca - initialize a new mca holding lock
+ * __rxe_init_mca_rcu - initialize a new mca holding lock
* @qp: qp object
* @mcg: mcg object
* @mca: empty space for new mca
@@ -280,7 +281,7 @@ void rxe_cleanup_mcg(struct kref *kref)
*
* Returns: 0 on success else an error
*/
-static int __rxe_init_mca(struct rxe_qp *qp, struct rxe_mcg *mcg,
+static int __rxe_init_mca_rcu(struct rxe_qp *qp, struct rxe_mcg *mcg,
struct rxe_mca *mca)
{
struct rxe_dev *rxe = to_rdev(qp->ibqp.device);
@@ -304,7 +305,7 @@ static int __rxe_init_mca(struct rxe_qp *qp, struct rxe_mcg *mcg,
rxe_add_ref(qp);
mca->qp = qp;
- list_add_tail(&mca->qp_list, &mcg->qp_list);
+ list_add_tail_rcu(&mca->qp_list, &mcg->qp_list);
return 0;
}
@@ -324,14 +325,14 @@ static int rxe_attach_mcg(struct rxe_mcg *mcg, struct rxe_qp *qp)
int err;
/* check to see if the qp is already a member of the group */
- spin_lock_bh(&rxe->mcg_lock);
- list_for_each_entry(mca, &mcg->qp_list, qp_list) {
+ rcu_read_lock();
+ list_for_each_entry_rcu(mca, &mcg->qp_list, qp_list) {
if (mca->qp == qp) {
- spin_unlock_bh(&rxe->mcg_lock);
+ rcu_read_unlock();
return 0;
}
}
- spin_unlock_bh(&rxe->mcg_lock);
+ rcu_read_unlock();
/* speculative alloc new mca without using GFP_ATOMIC */
new_mca = kzalloc(sizeof(*mca), GFP_KERNEL);
@@ -340,16 +341,19 @@ static int rxe_attach_mcg(struct rxe_mcg *mcg, struct rxe_qp *qp)
spin_lock_bh(&rxe->mcg_lock);
/* re-check to see if someone else just attached qp */
- list_for_each_entry(mca, &mcg->qp_list, qp_list) {
+ rcu_read_lock();
+ list_for_each_entry_rcu(mca, &mcg->qp_list, qp_list) {
if (mca->qp == qp) {
+ rcu_read_unlock();
kfree(new_mca);
err = 0;
goto done;
}
}
+ rcu_read_unlock();
mca = new_mca;
- err = __rxe_init_mca(qp, mcg, mca);
+ err = __rxe_init_mca_rcu(qp, mcg, mca);
if (err)
kfree(mca);
done:
@@ -359,21 +363,23 @@ static int rxe_attach_mcg(struct rxe_mcg *mcg, struct rxe_qp *qp)
}
/**
- * __rxe_cleanup_mca - cleanup mca object holding lock
+ * __rxe_cleanup_mca_rcu - cleanup mca object holding lock
* @mca: mca object
* @mcg: mcg object
*
* Context: caller must hold a reference to mcg and rxe->mcg_lock
*/
-static void __rxe_cleanup_mca(struct rxe_mca *mca, struct rxe_mcg *mcg)
+static void __rxe_cleanup_mca_rcu(struct rxe_mca *mca, struct rxe_mcg *mcg)
{
- list_del(&mca->qp_list);
+ list_del_rcu(&mca->qp_list);
atomic_dec(&mcg->qp_num);
atomic_dec(&mcg->rxe->mcg_attach);
atomic_dec(&mca->qp->mcg_num);
rxe_drop_ref(mca->qp);
+
+ kfree_rcu(mca, rcu);
}
/**
@@ -386,22 +392,29 @@ static void __rxe_cleanup_mca(struct rxe_mca *mca, struct rxe_mcg *mcg)
static int rxe_detach_mcg(struct rxe_mcg *mcg, struct rxe_qp *qp)
{
struct rxe_dev *rxe = mcg->rxe;
- struct rxe_mca *mca, *tmp;
+ struct rxe_mca *mca;
+ int ret;
spin_lock_bh(&rxe->mcg_lock);
- list_for_each_entry_safe(mca, tmp, &mcg->qp_list, qp_list) {
+ rcu_read_lock();
+ list_for_each_entry_rcu(mca, &mcg->qp_list, qp_list) {
if (mca->qp == qp) {
- __rxe_cleanup_mca(mca, mcg);
- if (atomic_read(&mcg->qp_num) <= 0)
- kref_put(&mcg->ref_cnt, __rxe_cleanup_mcg);
- spin_unlock_bh(&rxe->mcg_lock);
- kfree(mca);
- return 0;
+ rcu_read_unlock();
+ goto found;
}
}
+ rcu_read_unlock();
+ ret = -EINVAL;
+ goto done;
+found:
+ __rxe_cleanup_mca_rcu(mca, mcg);
+ if (atomic_read(&mcg->qp_num) <= 0)
+ kref_put(&mcg->ref_cnt, __rxe_cleanup_mcg);
+ ret = 0;
+done:
spin_unlock_bh(&rxe->mcg_lock);
- return -EINVAL;
+ return ret;
}
/**
diff --git a/drivers/infiniband/sw/rxe/rxe_recv.c b/drivers/infiniband/sw/rxe/rxe_recv.c
index 357a6cea1484..7f2ea61a52c1 100644
--- a/drivers/infiniband/sw/rxe/rxe_recv.c
+++ b/drivers/infiniband/sw/rxe/rxe_recv.c
@@ -267,13 +267,13 @@ static void rxe_rcv_mcast_pkt(struct sk_buff *skb)
qp_array = kmalloc_array(nmax, sizeof(qp), GFP_KERNEL);
n = 0;
- spin_lock_bh(&rxe->mcg_lock);
- list_for_each_entry(mca, &mcg->qp_list, qp_list) {
+ rcu_read_lock();
+ list_for_each_entry_rcu(mca, &mcg->qp_list, qp_list) {
qp_array[n++] = mca->qp;
if (n == nmax)
break;
}
- spin_unlock_bh(&rxe->mcg_lock);
+ rcu_read_unlock();
kref_put(&mcg->ref_cnt, rxe_cleanup_mcg);
nmax = n;
diff --git a/drivers/infiniband/sw/rxe/rxe_verbs.h b/drivers/infiniband/sw/rxe/rxe_verbs.h
index 76350d43ce2a..12bff190fc1f 100644
--- a/drivers/infiniband/sw/rxe/rxe_verbs.h
+++ b/drivers/infiniband/sw/rxe/rxe_verbs.h
@@ -365,6 +365,7 @@ struct rxe_mcg {
struct rxe_mca {
struct list_head qp_list;
struct rxe_qp *qp;
+ struct rcu_head rcu;
};
struct rxe_port {
--
2.32.0
next prev parent reply other threads:[~2022-01-27 21:38 UTC|newest]
Thread overview: 39+ messages / expand[flat|nested] mbox.gz Atom feed top
2022-01-27 21:37 [RFC PATCH v9 00/26] Bob Pearson
2022-01-27 21:37 ` [RFC PATCH v9 01/26] RDMA/rxe: Move rxe_mcast_add/delete to rxe_mcast.c Bob Pearson
2022-01-27 21:37 ` [RFC PATCH v9 02/26] RDMA/rxe: Move rxe_mcast_attach/detach " Bob Pearson
2022-01-27 21:37 ` [RFC PATCH v9 03/26] RDMA/rxe: Rename rxe_mc_grp and rxe_mc_elem Bob Pearson
2022-01-27 21:37 ` [RFC PATCH v9 04/26] RDMA/rxe: Enforce IBA o10-2.2.3 Bob Pearson
2022-01-28 12:53 ` Jason Gunthorpe
2022-01-28 16:18 ` Bob Pearson
2022-01-28 16:42 ` Jason Gunthorpe
2022-01-27 21:37 ` [RFC PATCH v9 05/26] RDMA/rxe: Remove rxe_drop_all_macst_groups Bob Pearson
2022-01-27 21:37 ` [RFC PATCH v9 06/26] RDMA/rxe: Remove qp->grp_lock and qp->grp_list Bob Pearson
2022-01-27 21:37 ` [RFC PATCH v9 07/26] RDMA/rxe: Use kzmalloc/kfree for mca Bob Pearson
2022-01-28 18:00 ` Jason Gunthorpe
2022-01-27 21:37 ` [RFC PATCH v9 08/26] RDMA/rxe: Rename grp to mcg and mce to mca Bob Pearson
2022-01-27 21:37 ` [RFC PATCH v9 09/26] RDMA/rxe: Introduce RXECB(skb) Bob Pearson
2022-01-28 18:29 ` Jason Gunthorpe
2022-01-30 17:47 ` Bob Pearson
2022-01-27 21:37 ` [RFC PATCH v9 10/26] RDMA/rxe: Split rxe_rcv_mcast_pkt into two phases Bob Pearson
2022-01-27 21:37 ` [RFC PATCH v9 11/26] RDMA/rxe: Replace locks by rxe->mcg_lock Bob Pearson
2022-01-27 21:37 ` [RFC PATCH v9 12/26] RDMA/rxe: Replace pool key by rxe->mcg_tree Bob Pearson
2022-01-28 18:32 ` Jason Gunthorpe
2022-01-30 23:23 ` Bob Pearson
2022-01-27 21:37 ` [RFC PATCH v9 13/26] RDMA/rxe: Remove key'ed object support Bob Pearson
2022-01-27 21:37 ` [RFC PATCH v9 14/26] RDMA/rxe: Remove mcg from rxe pools Bob Pearson
2022-01-27 21:37 ` [RFC PATCH v9 15/26] RDMA/rxe: Add code to cleanup mcast memory Bob Pearson
2022-01-27 21:37 ` [RFC PATCH v9 16/26] RDMA/rxe: Add comments to rxe_mcast.c Bob Pearson
2022-01-27 21:37 ` [RFC PATCH v9 17/26] RDMA/rxe: Separate code into subroutines Bob Pearson
2022-01-27 21:37 ` Bob Pearson [this message]
2022-01-28 18:39 ` [RFC PATCH v9 18/26] RDMA/rxe: Convert mca read locking to RCU Jason Gunthorpe
2022-01-27 21:37 ` [RFC PATCH v9 19/26] RDMA/rxe: Reverse the sense of RXE_POOL_NO_ALLOC Bob Pearson
2022-01-27 21:37 ` [RFC PATCH v9 20/26] RDMA/rxe: Delete _locked() APIs for pool objects Bob Pearson
2022-01-27 21:37 ` [RFC PATCH v9 21/26] RDMA/rxe: Replace obj by elem in declaration Bob Pearson
2022-01-27 21:37 ` [RFC PATCH v9 22/26] RDMA/rxe: Replace red-black trees by xarrays Bob Pearson
2022-01-27 21:37 ` [RFC PATCH v9 23/26] RDMA/rxe: Change pool locking to RCU Bob Pearson
2022-01-27 21:37 ` [RFC PATCH v9 24/26] RDMA/rxe: Add wait_for_completion to pool objects Bob Pearson
2022-01-27 21:37 ` [RFC PATCH v9 25/26] RDMA/rxe: Fix ref error in rxe_av.c Bob Pearson
2022-01-27 21:37 ` [RFC PATCH v9 26/26] RDMA/rxe: Replace mr by rkey in responder resources Bob Pearson
2022-01-28 18:42 ` [RFC PATCH v9 00/26] Jason Gunthorpe
2022-02-07 19:20 ` Bob Pearson
2022-02-07 19:38 ` Jason Gunthorpe
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20220127213755.31697-19-rpearsonhpe@gmail.com \
--to=rpearsonhpe@gmail.com \
--cc=jgg@nvidia.com \
--cc=linux-rdma@vger.kernel.org \
--cc=zyjzyj2000@gmail.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).