From: Koichiro Den <den@valinux.co.jp>
To: Jon Mason <jdmason@kudzu.us>, Dave Jiang <dave.jiang@intel.com>,
Allen Hubbe <allenbh@gmail.com>, Frank Li <Frank.Li@kernel.org>,
Logan Gunthorpe <logang@deltatee.com>
Cc: fuyuanli <fuyuanli0722@gmail.com>,
Greg Kroah-Hartman <gregkh@linuxfoundation.org>,
Nicholas Bellinger <nab@linux-iscsi.org>,
Joey Zhang <joey.zhang@microchip.com>,
ntb@lists.linux.dev, linux-kernel@vger.kernel.org,
stable@vger.kernel.org
Subject: [PATCH v3 09/15] NTB: ntb_transport: Stop RX tasklet scheduling before freeing a queue
Date: Tue, 29 Sep 2026 00:25:44 +0900 [thread overview]
Message-ID: <20260928152550.3354675-10-den@valinux.co.jp> (raw)
In-Reply-To: <20260928152550.3354675-1-den@valinux.co.jp>
A caller can read qp->active before teardown clears it, then schedule
the RX tasklet after tasklet_kill() returns. The MSI handler does not
check active at all. Teardown also releases DMA channels before
draining the tasklet.
Protect active updates and the check-and-schedule sequence with
rx_sched_lock, including the MSI path. Clear active under the lock,
then drain the tasklet before releasing DMA channels or queue entries.
QP link work is already disabled, so it cannot reactivate RX. Use a
separate lock to avoid contention with RX list operations.
Fixes: e902133162af ("ntb: stop tasklet from spinning forever during shutdown.")
Cc: stable@vger.kernel.org
Reviewed-by: Logan Gunthorpe <logang@deltatee.com>
Reviewed-by: Dave Jiang <dave.jiang@intel.com>
Signed-off-by: Koichiro Den <den@valinux.co.jp>
---
Changes in v3:
- Add Reviewed-by tag. No code changes.
drivers/ntb/ntb_transport.c | 50 +++++++++++++++++++++++--------------
1 file changed, 31 insertions(+), 19 deletions(-)
diff --git a/drivers/ntb/ntb_transport.c b/drivers/ntb/ntb_transport.c
index 556e1d255284..30411e118a7e 100644
--- a/drivers/ntb/ntb_transport.c
+++ b/drivers/ntb/ntb_transport.c
@@ -180,6 +180,8 @@ struct ntb_transport_qp {
unsigned int rx_max_frame;
unsigned int rx_alloc_entry;
dma_cookie_t last_cookie;
+ /* Protect active and RX tasklet scheduling. */
+ spinlock_t rx_sched_lock;
struct tasklet_struct rxc_db_work;
void (*event_handler)(void *data, int status);
@@ -650,11 +652,26 @@ static int ntb_transport_setup_qp_mw(struct ntb_transport_ctx *nt,
return 0;
}
+static void ntb_transport_set_qp_active(struct ntb_transport_qp *qp, bool active)
+{
+ guard(spinlock_irqsave)(&qp->rx_sched_lock);
+
+ qp->active = active;
+}
+
+static void ntb_transport_schedule_rxc(struct ntb_transport_qp *qp)
+{
+ guard(spinlock_irqsave)(&qp->rx_sched_lock);
+
+ if (qp->active)
+ tasklet_schedule(&qp->rxc_db_work);
+}
+
static irqreturn_t ntb_transport_isr(int irq, void *dev)
{
struct ntb_transport_qp *qp = dev;
- tasklet_schedule(&qp->rxc_db_work);
+ ntb_transport_schedule_rxc(qp);
return IRQ_HANDLED;
}
@@ -896,7 +913,7 @@ static int ntb_set_mw(struct ntb_transport_ctx *nt, int num_mw,
static void ntb_qp_link_context_reset(struct ntb_transport_qp *qp)
{
qp->link_is_up = false;
- qp->active = false;
+ ntb_transport_set_qp_active(qp, false);
qp->tx_index = 0;
qp->rx_index = 0;
@@ -1156,13 +1173,12 @@ static void ntb_qp_link_work(struct work_struct *work)
if (val & BIT(qp->qp_num)) {
dev_info(&pdev->dev, "qp %d: Link Up\n", qp->qp_num);
qp->link_is_up = true;
- qp->active = true;
+ ntb_transport_set_qp_active(qp, true);
if (qp->event_handler)
qp->event_handler(qp->cb_data, qp->link_is_up);
- if (qp->active)
- tasklet_schedule(&qp->rxc_db_work);
+ ntb_transport_schedule_rxc(qp);
} else {
ntb_transport_schedule_qp_link(qp,
msecs_to_jiffies(NTB_LINK_DOWN_TIMEOUT));
@@ -1190,6 +1206,7 @@ static int ntb_transport_init_queue(struct ntb_transport_ctx *nt,
qp->ndev = nt->ndev;
atomic_set(&qp->client_ready, false);
qp->event_handler = NULL;
+ spin_lock_init(&qp->rx_sched_lock);
ntb_qp_link_context_reset(qp);
if (mw_num < qp_count % mw_count)
@@ -1726,8 +1743,7 @@ static void ntb_transport_rxc_db(unsigned long data)
if (i == qp->rx_max_entry) {
/* there is more work to do */
- if (qp->active)
- tasklet_schedule(&qp->rxc_db_work);
+ ntb_transport_schedule_rxc(qp);
} else if (ntb_db_read(qp->ndev) & BIT_ULL(qp->qp_num)) {
/* the doorbell bit is set: clear it */
ntb_db_clear(qp->ndev, BIT_ULL(qp->qp_num));
@@ -1738,8 +1754,7 @@ static void ntb_transport_rxc_db(unsigned long data)
* ntb_process_rxc and clearing the doorbell bit:
* there might be some more work to do.
*/
- if (qp->active)
- tasklet_schedule(&qp->rxc_db_work);
+ ntb_transport_schedule_rxc(qp);
}
}
@@ -2206,7 +2221,11 @@ void ntb_transport_free_queue(struct ntb_transport_qp *qp)
disable_work_sync(&qp->link_cleanup);
disable_delayed_work_sync(&qp->link_work);
qp->link_is_up = false;
- qp->active = false;
+ ntb_transport_set_qp_active(qp, false);
+
+ qp_bit = BIT_ULL(qp->qp_num);
+ ntb_db_set_mask(qp->ndev, qp_bit);
+ tasklet_kill(&qp->rxc_db_work);
if (qp->tx_offload_thread) {
kthread_stop(qp->tx_offload_thread);
@@ -2248,11 +2267,6 @@ void ntb_transport_free_queue(struct ntb_transport_qp *qp)
dma_release_channel(chan);
}
- qp_bit = BIT_ULL(qp->qp_num);
-
- ntb_db_set_mask(qp->ndev, qp_bit);
- tasklet_kill(&qp->rxc_db_work);
-
qp->cb_data = NULL;
qp->rx_handler = NULL;
qp->tx_handler = NULL;
@@ -2347,8 +2361,7 @@ int ntb_transport_rx_enqueue(struct ntb_transport_qp *qp, void *cb, void *data,
ntb_list_add(&qp->ntb_rx_q_lock, &entry->entry, &qp->rx_pend_q);
- if (qp->active)
- tasklet_schedule(&qp->rxc_db_work);
+ ntb_transport_schedule_rxc(qp);
return 0;
}
@@ -2545,8 +2558,7 @@ static void ntb_transport_doorbell_callback(void *data, int vector)
qp_num = __ffs(db_bits);
qp = &nt->qp_vec[qp_num];
- if (qp->active)
- tasklet_schedule(&qp->rxc_db_work);
+ ntb_transport_schedule_rxc(qp);
db_bits &= ~BIT_ULL(qp_num);
}
--
2.51.0
next prev parent reply other threads:[~2026-09-28 15:26 UTC|newest]
Thread overview: 25+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-09-28 15:25 [PATCH v3 00/15] NTB: ntb_transport: Miscellaneous fixes Koichiro Den
2026-09-28 15:25 ` [PATCH v3 01/15] NTB: ntb_transport: Remove the device debugfs directory Koichiro Den
2026-09-28 15:25 ` [PATCH v3 02/15] NTB: ntb_transport: Start TX offload thread after queue setup Koichiro Den
2026-09-28 15:25 ` [PATCH v3 03/15] NTB: ntb_transport: Make link setup flags atomic Koichiro Den
2026-09-28 15:53 ` Logan Gunthorpe
2026-10-09 23:08 ` Dave Jiang
2026-09-28 15:25 ` [PATCH v3 04/15] NTB: ntb_transport: Avoid deadlock when cancelling link work Koichiro Den
2026-10-09 23:09 ` Dave Jiang
2026-09-28 15:25 ` [PATCH v3 05/15] NTB: ntb_transport: Publish link state after QP setup Koichiro Den
2026-09-28 15:25 ` [PATCH v3 06/15] NTB: ntb_transport: Avoid losing QP link-up requests Koichiro Den
2026-09-28 16:57 ` Logan Gunthorpe
2026-09-29 1:43 ` Koichiro Den
2026-10-09 23:11 ` Dave Jiang
2026-10-15 3:50 ` Koichiro Den
2026-10-27 15:03 ` Koichiro Den
2026-09-28 15:25 ` [PATCH v3 07/15] NTB: ntb_transport: Clear link state before QP cleanup Koichiro Den
2026-09-28 15:25 ` [PATCH v3 08/15] NTB: ntb_transport: Stop QP work before freeing a queue Koichiro Den
2026-10-09 23:11 ` Dave Jiang
2026-09-28 15:25 ` Koichiro Den [this message]
2026-09-28 15:25 ` [PATCH v3 10/15] NTB: ntb_transport: Drain RX tasklets during link cleanup Koichiro Den
2026-09-28 15:25 ` [PATCH v3 11/15] NTB: ntb_transport: Wait for RX completions before resetting a QP Koichiro Den
2026-09-28 15:25 ` [PATCH v3 12/15] NTB: ntb_transport: Prepare remote RX info accesses for MW teardown Koichiro Den
2026-09-28 15:25 ` [PATCH v3 13/15] NTB: ntb_transport: Clear QP pointers when freeing an MW Koichiro Den
2026-09-28 15:25 ` [PATCH v3 14/15] NTB: ntb_transport: Abort link setup on QP MW allocation failure Koichiro Den
2026-09-28 15:25 ` [PATCH v3 15/15] NTB: ntb_transport: Remove clients before freeing transport resources Koichiro Den
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=20260928152550.3354675-10-den@valinux.co.jp \
--to=den@valinux.co.jp \
--cc=Frank.Li@kernel.org \
--cc=allenbh@gmail.com \
--cc=dave.jiang@intel.com \
--cc=fuyuanli0722@gmail.com \
--cc=gregkh@linuxfoundation.org \
--cc=jdmason@kudzu.us \
--cc=joey.zhang@microchip.com \
--cc=linux-kernel@vger.kernel.org \
--cc=logang@deltatee.com \
--cc=nab@linux-iscsi.org \
--cc=ntb@lists.linux.dev \
--cc=stable@vger.kernel.org \
/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
all inboxes | Powered by JetHome®