Update Linux to v5.4.148
Sourced from [1]
[1] https://cdn.kernel.org/pub/linux/kernel/v5.x/linux-5.4.148.tar.gz
Change-Id: Ib3d26c5ba9b022e2e03533005c4fed4d7c30b61b
Signed-off-by: Olivier Deprez <olivier.deprez@arm.com>
diff --git a/drivers/infiniband/hw/hfi1/affinity.c b/drivers/infiniband/hw/hfi1/affinity.c
index c142b23..1aeea5d 100644
--- a/drivers/infiniband/hw/hfi1/affinity.c
+++ b/drivers/infiniband/hw/hfi1/affinity.c
@@ -479,6 +479,8 @@
rvt_get_ibdev_name(&(dd)->verbs_dev.rdi), i, cpu);
}
+ free_cpumask_var(available_cpus);
+ free_cpumask_var(non_intr_cpus);
return 0;
fail:
diff --git a/drivers/infiniband/hw/hfi1/chip.c b/drivers/infiniband/hw/hfi1/chip.c
index 9b1fb84..10924f1 100644
--- a/drivers/infiniband/hw/hfi1/chip.c
+++ b/drivers/infiniband/hw/hfi1/chip.c
@@ -1685,6 +1685,14 @@
return dd->verbs_dev.n_piodrain;
}
+static u64 access_sw_ctx0_seq_drop(const struct cntr_entry *entry,
+ void *context, int vl, int mode, u64 data)
+{
+ struct hfi1_devdata *dd = context;
+
+ return dd->ctx0_seq_drop;
+}
+
static u64 access_sw_vtx_wait(const struct cntr_entry *entry,
void *context, int vl, int mode, u64 data)
{
@@ -4106,6 +4114,7 @@
static struct cntr_entry dev_cntrs[DEV_CNTR_LAST] = {
[C_RCV_OVF] = RXE32_DEV_CNTR_ELEM(RcvOverflow, RCV_BUF_OVFL_CNT, CNTR_SYNTH),
[C_RX_LEN_ERR] = RXE32_DEV_CNTR_ELEM(RxLenErr, RCV_LENGTH_ERR_CNT, CNTR_SYNTH),
+[C_RX_SHORT_ERR] = RXE32_DEV_CNTR_ELEM(RxShrErr, RCV_SHORT_ERR_CNT, CNTR_SYNTH),
[C_RX_ICRC_ERR] = RXE32_DEV_CNTR_ELEM(RxICrcErr, RCV_ICRC_ERR_CNT, CNTR_SYNTH),
[C_RX_EBP] = RXE32_DEV_CNTR_ELEM(RxEbpCnt, RCV_EBP_CNT, CNTR_SYNTH),
[C_RX_TID_FULL] = RXE32_DEV_CNTR_ELEM(RxTIDFullEr, RCV_TID_FULL_ERR_CNT,
@@ -4249,6 +4258,8 @@
access_sw_cpu_intr),
[C_SW_CPU_RCV_LIM] = CNTR_ELEM("RcvLimit", 0, 0, CNTR_NORMAL,
access_sw_cpu_rcv_limit),
+[C_SW_CTX0_SEQ_DROP] = CNTR_ELEM("SeqDrop0", 0, 0, CNTR_NORMAL,
+ access_sw_ctx0_seq_drop),
[C_SW_VTX_WAIT] = CNTR_ELEM("vTxWait", 0, 0, CNTR_NORMAL,
access_sw_vtx_wait),
[C_SW_PIO_WAIT] = CNTR_ELEM("PioWait", 0, 0, CNTR_NORMAL,
diff --git a/drivers/infiniband/hw/hfi1/chip.h b/drivers/infiniband/hw/hfi1/chip.h
index 4ca5ac8..af00619 100644
--- a/drivers/infiniband/hw/hfi1/chip.h
+++ b/drivers/infiniband/hw/hfi1/chip.h
@@ -859,6 +859,7 @@
enum {
C_RCV_OVF = 0,
C_RX_LEN_ERR,
+ C_RX_SHORT_ERR,
C_RX_ICRC_ERR,
C_RX_EBP,
C_RX_TID_FULL,
@@ -926,6 +927,7 @@
C_DC_PG_STS_TX_MBE_CNT,
C_SW_CPU_INTR,
C_SW_CPU_RCV_LIM,
+ C_SW_CTX0_SEQ_DROP,
C_SW_VTX_WAIT,
C_SW_PIO_WAIT,
C_SW_PIO_DRAIN,
diff --git a/drivers/infiniband/hw/hfi1/chip_registers.h b/drivers/infiniband/hw/hfi1/chip_registers.h
index ab3589d..fb3ec9b 100644
--- a/drivers/infiniband/hw/hfi1/chip_registers.h
+++ b/drivers/infiniband/hw/hfi1/chip_registers.h
@@ -381,6 +381,7 @@
#define DC_LCB_STS_LINK_TRANSFER_ACTIVE (DC_LCB_CSRS + 0x000000000468)
#define DC_LCB_STS_ROUND_TRIP_LTP_CNT (DC_LCB_CSRS + 0x0000000004B0)
#define RCV_LENGTH_ERR_CNT 0
+#define RCV_SHORT_ERR_CNT 2
#define RCV_ICRC_ERR_CNT 6
#define RCV_EBP_CNT 9
#define RCV_BUF_OVFL_CNT 10
diff --git a/drivers/infiniband/hw/hfi1/debugfs.c b/drivers/infiniband/hw/hfi1/debugfs.c
index d268bf9..c29da2f 100644
--- a/drivers/infiniband/hw/hfi1/debugfs.c
+++ b/drivers/infiniband/hw/hfi1/debugfs.c
@@ -985,15 +985,10 @@
static int __i2c_debugfs_open(struct inode *in, struct file *fp, u32 target)
{
struct hfi1_pportdata *ppd;
- int ret;
ppd = private2ppd(fp);
- ret = acquire_chip_resource(ppd->dd, i2c_target(target), 0);
- if (ret) /* failed - release the module */
- module_put(THIS_MODULE);
-
- return ret;
+ return acquire_chip_resource(ppd->dd, i2c_target(target), 0);
}
static int i2c1_debugfs_open(struct inode *in, struct file *fp)
@@ -1013,7 +1008,6 @@
ppd = private2ppd(fp);
release_chip_resource(ppd->dd, i2c_target(target));
- module_put(THIS_MODULE);
return 0;
}
@@ -1031,18 +1025,10 @@
static int __qsfp_debugfs_open(struct inode *in, struct file *fp, u32 target)
{
struct hfi1_pportdata *ppd;
- int ret;
-
- if (!try_module_get(THIS_MODULE))
- return -ENODEV;
ppd = private2ppd(fp);
- ret = acquire_chip_resource(ppd->dd, i2c_target(target), 0);
- if (ret) /* failed - release the module */
- module_put(THIS_MODULE);
-
- return ret;
+ return acquire_chip_resource(ppd->dd, i2c_target(target), 0);
}
static int qsfp1_debugfs_open(struct inode *in, struct file *fp)
@@ -1062,7 +1048,6 @@
ppd = private2ppd(fp);
release_chip_resource(ppd->dd, i2c_target(target));
- module_put(THIS_MODULE);
return 0;
}
diff --git a/drivers/infiniband/hw/hfi1/driver.c b/drivers/infiniband/hw/hfi1/driver.c
index 01aa1f1..941b465 100644
--- a/drivers/infiniband/hw/hfi1/driver.c
+++ b/drivers/infiniband/hw/hfi1/driver.c
@@ -734,6 +734,7 @@
{
int ret;
+ packet->rcd->dd->ctx0_seq_drop++;
/* Set up for the next packet */
packet->rhqoff += packet->rsize;
if (packet->rhqoff >= packet->maxcnt)
diff --git a/drivers/infiniband/hw/hfi1/file_ops.c b/drivers/infiniband/hw/hfi1/file_ops.c
index f9a7e9d..89e1dfd 100644
--- a/drivers/infiniband/hw/hfi1/file_ops.c
+++ b/drivers/infiniband/hw/hfi1/file_ops.c
@@ -200,23 +200,24 @@
fd = kzalloc(sizeof(*fd), GFP_KERNEL);
- if (fd) {
- fd->rec_cpu_num = -1; /* no cpu affinity by default */
- fd->mm = current->mm;
- mmgrab(fd->mm);
- fd->dd = dd;
- kobject_get(&fd->dd->kobj);
- fp->private_data = fd;
- } else {
- fp->private_data = NULL;
-
- if (atomic_dec_and_test(&dd->user_refcount))
- complete(&dd->user_comp);
-
- return -ENOMEM;
- }
-
+ if (!fd || init_srcu_struct(&fd->pq_srcu))
+ goto nomem;
+ spin_lock_init(&fd->pq_rcu_lock);
+ spin_lock_init(&fd->tid_lock);
+ spin_lock_init(&fd->invalid_lock);
+ fd->rec_cpu_num = -1; /* no cpu affinity by default */
+ fd->mm = current->mm;
+ mmgrab(fd->mm);
+ fd->dd = dd;
+ kobject_get(&fd->dd->kobj);
+ fp->private_data = fd;
return 0;
+nomem:
+ kfree(fd);
+ fp->private_data = NULL;
+ if (atomic_dec_and_test(&dd->user_refcount))
+ complete(&dd->user_comp);
+ return -ENOMEM;
}
static long hfi1_file_ioctl(struct file *fp, unsigned int cmd,
@@ -301,21 +302,30 @@
static ssize_t hfi1_write_iter(struct kiocb *kiocb, struct iov_iter *from)
{
struct hfi1_filedata *fd = kiocb->ki_filp->private_data;
- struct hfi1_user_sdma_pkt_q *pq = fd->pq;
+ struct hfi1_user_sdma_pkt_q *pq;
struct hfi1_user_sdma_comp_q *cq = fd->cq;
int done = 0, reqs = 0;
unsigned long dim = from->nr_segs;
+ int idx;
- if (!cq || !pq)
+ idx = srcu_read_lock(&fd->pq_srcu);
+ pq = srcu_dereference(fd->pq, &fd->pq_srcu);
+ if (!cq || !pq) {
+ srcu_read_unlock(&fd->pq_srcu, idx);
return -EIO;
+ }
- if (!iter_is_iovec(from) || !dim)
+ if (!iter_is_iovec(from) || !dim) {
+ srcu_read_unlock(&fd->pq_srcu, idx);
return -EINVAL;
+ }
trace_hfi1_sdma_request(fd->dd, fd->uctxt->ctxt, fd->subctxt, dim);
- if (atomic_read(&pq->n_reqs) == pq->n_max_reqs)
+ if (atomic_read(&pq->n_reqs) == pq->n_max_reqs) {
+ srcu_read_unlock(&fd->pq_srcu, idx);
return -ENOSPC;
+ }
while (dim) {
int ret;
@@ -333,6 +343,7 @@
reqs++;
}
+ srcu_read_unlock(&fd->pq_srcu, idx);
return reqs;
}
@@ -707,6 +718,7 @@
if (atomic_dec_and_test(&dd->user_refcount))
complete(&dd->user_comp);
+ cleanup_srcu_struct(&fdata->pq_srcu);
kfree(fdata);
return 0;
}
diff --git a/drivers/infiniband/hw/hfi1/firmware.c b/drivers/infiniband/hw/hfi1/firmware.c
index 2b57ba7..c090807 100644
--- a/drivers/infiniband/hw/hfi1/firmware.c
+++ b/drivers/infiniband/hw/hfi1/firmware.c
@@ -1924,6 +1924,7 @@
dd_dev_err(dd, "%s: Failed CRC check at offset %ld\n",
__func__, (ptr -
(u32 *)dd->platform_config.data));
+ ret = -EINVAL;
goto bail;
}
/* Jump the CRC DWORD */
diff --git a/drivers/infiniband/hw/hfi1/hfi.h b/drivers/infiniband/hw/hfi1/hfi.h
index fa45350..b79931c 100644
--- a/drivers/infiniband/hw/hfi1/hfi.h
+++ b/drivers/infiniband/hw/hfi1/hfi.h
@@ -1153,6 +1153,8 @@
char *boardname; /* human readable board info */
+ u64 ctx0_seq_drop;
+
/* reset value */
u64 z_int_counter;
u64 z_rcv_limit;
@@ -1436,10 +1438,13 @@
/* Private data for file operations */
struct hfi1_filedata {
+ struct srcu_struct pq_srcu;
struct hfi1_devdata *dd;
struct hfi1_ctxtdata *uctxt;
struct hfi1_user_sdma_comp_q *cq;
- struct hfi1_user_sdma_pkt_q *pq;
+ /* update side lock for SRCU */
+ spinlock_t pq_rcu_lock;
+ struct hfi1_user_sdma_pkt_q __rcu *pq;
u16 subctxt;
/* for cpu affinity; -1 if none */
int rec_cpu_num;
diff --git a/drivers/infiniband/hw/hfi1/init.c b/drivers/infiniband/hw/hfi1/init.c
index 26b792b..1256dbd 100644
--- a/drivers/infiniband/hw/hfi1/init.c
+++ b/drivers/infiniband/hw/hfi1/init.c
@@ -664,12 +664,7 @@
ppd->pkeys[default_pkey_idx] = DEFAULT_P_KEY;
ppd->part_enforce |= HFI1_PART_ENFORCE_IN;
-
- if (loopback) {
- dd_dev_err(dd, "Faking data partition 0x8001 in idx %u\n",
- !default_pkey_idx);
- ppd->pkeys[!default_pkey_idx] = 0x8001;
- }
+ ppd->pkeys[0] = 0x8001;
INIT_WORK(&ppd->link_vc_work, handle_verify_cap);
INIT_WORK(&ppd->link_up_work, handle_link_up);
@@ -845,6 +840,29 @@
}
/**
+ * destroy_workqueues - destroy per port workqueues
+ * @dd: the hfi1_ib device
+ */
+static void destroy_workqueues(struct hfi1_devdata *dd)
+{
+ int pidx;
+ struct hfi1_pportdata *ppd;
+
+ for (pidx = 0; pidx < dd->num_pports; ++pidx) {
+ ppd = dd->pport + pidx;
+
+ if (ppd->hfi1_wq) {
+ destroy_workqueue(ppd->hfi1_wq);
+ ppd->hfi1_wq = NULL;
+ }
+ if (ppd->link_wq) {
+ destroy_workqueue(ppd->link_wq);
+ ppd->link_wq = NULL;
+ }
+ }
+}
+
+/**
* enable_general_intr() - Enable the IRQs that will be handled by the
* general interrupt handler.
* @dd: valid devdata
@@ -1117,15 +1135,10 @@
* We can't count on interrupts since we are stopping.
*/
hfi1_quiet_serdes(ppd);
-
- if (ppd->hfi1_wq) {
- destroy_workqueue(ppd->hfi1_wq);
- ppd->hfi1_wq = NULL;
- }
- if (ppd->link_wq) {
- destroy_workqueue(ppd->link_wq);
- ppd->link_wq = NULL;
- }
+ if (ppd->hfi1_wq)
+ flush_workqueue(ppd->hfi1_wq);
+ if (ppd->link_wq)
+ flush_workqueue(ppd->link_wq);
}
sdma_exit(dd);
}
@@ -1814,6 +1827,7 @@
* clear dma engines, etc.
*/
shutdown_device(dd);
+ destroy_workqueues(dd);
stop_timers(dd);
diff --git a/drivers/infiniband/hw/hfi1/iowait.c b/drivers/infiniband/hw/hfi1/iowait.c
index adb4a1b..5836fe7 100644
--- a/drivers/infiniband/hw/hfi1/iowait.c
+++ b/drivers/infiniband/hw/hfi1/iowait.c
@@ -81,7 +81,9 @@
void iowait_cancel_work(struct iowait *w)
{
cancel_work_sync(&iowait_get_ib_work(w)->iowork);
- cancel_work_sync(&iowait_get_tid_work(w)->iowork);
+ /* Make sure that the iowork for TID RDMA is used */
+ if (iowait_get_tid_work(w)->iowork.func)
+ cancel_work_sync(&iowait_get_tid_work(w)->iowork);
}
/**
diff --git a/drivers/infiniband/hw/hfi1/qp.c b/drivers/infiniband/hw/hfi1/qp.c
index f8e733a..acd4400 100644
--- a/drivers/infiniband/hw/hfi1/qp.c
+++ b/drivers/infiniband/hw/hfi1/qp.c
@@ -381,7 +381,10 @@
struct hfi1_ibport *ibp =
to_iport(qp->ibqp.device, qp->port_num);
struct hfi1_pportdata *ppd = ppd_from_ibp(ibp);
- struct hfi1_devdata *dd = dd_from_ibdev(qp->ibqp.device);
+ struct hfi1_devdata *dd = ppd->dd;
+
+ if (dd->flags & HFI1_SHUTDOWN)
+ return true;
return iowait_schedule(&priv->s_iowait, ppd->hfi1_wq,
priv->s_sde ?
diff --git a/drivers/infiniband/hw/hfi1/sdma.c b/drivers/infiniband/hw/hfi1/sdma.c
index c61b602..248be21 100644
--- a/drivers/infiniband/hw/hfi1/sdma.c
+++ b/drivers/infiniband/hw/hfi1/sdma.c
@@ -3056,6 +3056,7 @@
static int _extend_sdma_tx_descs(struct hfi1_devdata *dd, struct sdma_txreq *tx)
{
int i;
+ struct sdma_desc *descp;
/* Handle last descriptor */
if (unlikely((tx->num_desc == (MAX_DESC - 1)))) {
@@ -3076,12 +3077,10 @@
if (unlikely(tx->num_desc == MAX_DESC))
goto enomem;
- tx->descp = kmalloc_array(
- MAX_DESC,
- sizeof(struct sdma_desc),
- GFP_ATOMIC);
- if (!tx->descp)
+ descp = kmalloc_array(MAX_DESC, sizeof(struct sdma_desc), GFP_ATOMIC);
+ if (!descp)
goto enomem;
+ tx->descp = descp;
/* reserve last descriptor for coalescing */
tx->desc_limit = MAX_DESC - 1;
diff --git a/drivers/infiniband/hw/hfi1/sysfs.c b/drivers/infiniband/hw/hfi1/sysfs.c
index 90f62c4..074ec71 100644
--- a/drivers/infiniband/hw/hfi1/sysfs.c
+++ b/drivers/infiniband/hw/hfi1/sysfs.c
@@ -674,7 +674,11 @@
dd_dev_err(dd,
"Skipping sc2vl sysfs info, (err %d) port %u\n",
ret, port_num);
- goto bail;
+ /*
+ * Based on the documentation for kobject_init_and_add(), the
+ * caller should call kobject_put even if this call fails.
+ */
+ goto bail_sc2vl;
}
kobject_uevent(&ppd->sc2vl_kobj, KOBJ_ADD);
@@ -684,7 +688,7 @@
dd_dev_err(dd,
"Skipping sl2sc sysfs info, (err %d) port %u\n",
ret, port_num);
- goto bail_sc2vl;
+ goto bail_sl2sc;
}
kobject_uevent(&ppd->sl2sc_kobj, KOBJ_ADD);
@@ -694,7 +698,7 @@
dd_dev_err(dd,
"Skipping vl2mtu sysfs info, (err %d) port %u\n",
ret, port_num);
- goto bail_sl2sc;
+ goto bail_vl2mtu;
}
kobject_uevent(&ppd->vl2mtu_kobj, KOBJ_ADD);
@@ -704,7 +708,7 @@
dd_dev_err(dd,
"Skipping Congestion Control sysfs info, (err %d) port %u\n",
ret, port_num);
- goto bail_vl2mtu;
+ goto bail_cc;
}
kobject_uevent(&ppd->pport_cc_kobj, KOBJ_ADD);
@@ -742,7 +746,6 @@
kobject_put(&ppd->sl2sc_kobj);
bail_sc2vl:
kobject_put(&ppd->sc2vl_kobj);
-bail:
return ret;
}
@@ -853,8 +856,13 @@
return 0;
bail:
- for (i = 0; i < dd->num_sdma; i++)
- kobject_del(&dd->per_sdma[i].kobj);
+ /*
+ * The function kobject_put() will call kobject_del() if the kobject
+ * has been added successfully. The sysfs files created under the
+ * kobject directory will also be removed during the process.
+ */
+ for (; i >= 0; i--)
+ kobject_put(&dd->per_sdma[i].kobj);
return ret;
}
@@ -867,6 +875,10 @@
struct hfi1_pportdata *ppd;
int i;
+ /* Unwind operations in hfi1_verbs_register_sysfs() */
+ for (i = 0; i < dd->num_sdma; i++)
+ kobject_put(&dd->per_sdma[i].kobj);
+
for (i = 0; i < dd->num_pports; i++) {
ppd = &dd->pport[i];
diff --git a/drivers/infiniband/hw/hfi1/tid_rdma.c b/drivers/infiniband/hw/hfi1/tid_rdma.c
index e53f542..c018fc6 100644
--- a/drivers/infiniband/hw/hfi1/tid_rdma.c
+++ b/drivers/infiniband/hw/hfi1/tid_rdma.c
@@ -3215,6 +3215,7 @@
case IB_WR_ATOMIC_CMP_AND_SWP:
case IB_WR_ATOMIC_FETCH_AND_ADD:
case IB_WR_RDMA_WRITE:
+ case IB_WR_RDMA_WRITE_WITH_IMM:
switch (prev->wr.opcode) {
case IB_WR_TID_RDMA_WRITE:
req = wqe_to_tid_req(prev);
@@ -4633,6 +4634,15 @@
*/
fpsn = full_flow_psn(flow, flow->flow_state.spsn);
req->r_ack_psn = psn;
+ /*
+ * If resync_psn points to the last flow PSN for a
+ * segment and the new segment (likely from a new
+ * request) starts with a new generation number, we
+ * need to adjust resync_psn accordingly.
+ */
+ if (flow->flow_state.generation !=
+ (resync_psn >> HFI1_KDETH_BTH_SEQ_SHIFT))
+ resync_psn = mask_psn(fpsn - 1);
flow->resync_npkts +=
delta_psn(mask_psn(resync_psn + 1), fpsn);
/*
@@ -5397,7 +5407,10 @@
struct hfi1_ibport *ibp =
to_iport(qp->ibqp.device, qp->port_num);
struct hfi1_pportdata *ppd = ppd_from_ibp(ibp);
- struct hfi1_devdata *dd = dd_from_ibdev(qp->ibqp.device);
+ struct hfi1_devdata *dd = ppd->dd;
+
+ if ((dd->flags & HFI1_SHUTDOWN))
+ return true;
return iowait_tid_schedule(&priv->s_iowait, ppd->hfi1_wq,
priv->s_sde ?
diff --git a/drivers/infiniband/hw/hfi1/user_exp_rcv.c b/drivers/infiniband/hw/hfi1/user_exp_rcv.c
index 3592a9e..4d73235 100644
--- a/drivers/infiniband/hw/hfi1/user_exp_rcv.c
+++ b/drivers/infiniband/hw/hfi1/user_exp_rcv.c
@@ -90,9 +90,6 @@
struct hfi1_devdata *dd = uctxt->dd;
int ret = 0;
- spin_lock_init(&fd->tid_lock);
- spin_lock_init(&fd->invalid_lock);
-
fd->entry_to_rb = kcalloc(uctxt->expected_count,
sizeof(struct rb_node *),
GFP_KERNEL);
@@ -165,10 +162,12 @@
if (fd->handler) {
hfi1_mmu_rb_unregister(fd->handler);
} else {
+ mutex_lock(&uctxt->exp_mutex);
if (!EXP_TID_SET_EMPTY(uctxt->tid_full_list))
unlock_exp_tids(uctxt, &uctxt->tid_full_list, fd);
if (!EXP_TID_SET_EMPTY(uctxt->tid_used_list))
unlock_exp_tids(uctxt, &uctxt->tid_used_list, fd);
+ mutex_unlock(&uctxt->exp_mutex);
}
kfree(fd->invalid_tids);
diff --git a/drivers/infiniband/hw/hfi1/user_sdma.c b/drivers/infiniband/hw/hfi1/user_sdma.c
index fd754a1..a92346e 100644
--- a/drivers/infiniband/hw/hfi1/user_sdma.c
+++ b/drivers/infiniband/hw/hfi1/user_sdma.c
@@ -141,6 +141,7 @@
*/
xchg(&pq->state, SDMA_PKT_Q_DEFERRED);
if (list_empty(&pq->busy.list)) {
+ pq->busy.lock = &sde->waitlock;
iowait_get_priority(&pq->busy);
iowait_queue(pkts_sent, &pq->busy, &sde->dmawait);
}
@@ -155,6 +156,7 @@
{
struct hfi1_user_sdma_pkt_q *pq =
container_of(wait, struct hfi1_user_sdma_pkt_q, busy);
+ pq->busy.lock = NULL;
xchg(&pq->state, SDMA_PKT_Q_ACTIVE);
wake_up(&wait->wait_dma);
};
@@ -179,7 +181,6 @@
pq = kzalloc(sizeof(*pq), GFP_KERNEL);
if (!pq)
return -ENOMEM;
-
pq->dd = dd;
pq->ctxt = uctxt->ctxt;
pq->subctxt = fd->subctxt;
@@ -236,7 +237,7 @@
goto pq_mmu_fail;
}
- fd->pq = pq;
+ rcu_assign_pointer(fd->pq, pq);
fd->cq = cq;
return 0;
@@ -257,6 +258,21 @@
return ret;
}
+static void flush_pq_iowait(struct hfi1_user_sdma_pkt_q *pq)
+{
+ unsigned long flags;
+ seqlock_t *lock = pq->busy.lock;
+
+ if (!lock)
+ return;
+ write_seqlock_irqsave(lock, flags);
+ if (!list_empty(&pq->busy.list)) {
+ list_del_init(&pq->busy.list);
+ pq->busy.lock = NULL;
+ }
+ write_sequnlock_irqrestore(lock, flags);
+}
+
int hfi1_user_sdma_free_queues(struct hfi1_filedata *fd,
struct hfi1_ctxtdata *uctxt)
{
@@ -264,8 +280,14 @@
trace_hfi1_sdma_user_free_queues(uctxt->dd, uctxt->ctxt, fd->subctxt);
- pq = fd->pq;
+ spin_lock(&fd->pq_rcu_lock);
+ pq = srcu_dereference_check(fd->pq, &fd->pq_srcu,
+ lockdep_is_held(&fd->pq_rcu_lock));
if (pq) {
+ rcu_assign_pointer(fd->pq, NULL);
+ spin_unlock(&fd->pq_rcu_lock);
+ synchronize_srcu(&fd->pq_srcu);
+ /* at this point there can be no more new requests */
if (pq->handler)
hfi1_mmu_rb_unregister(pq->handler);
iowait_sdma_drain(&pq->busy);
@@ -276,8 +298,10 @@
kfree(pq->reqs);
kfree(pq->req_in_use);
kmem_cache_destroy(pq->txreq_cache);
+ flush_pq_iowait(pq);
kfree(pq);
- fd->pq = NULL;
+ } else {
+ spin_unlock(&fd->pq_rcu_lock);
}
if (fd->cq) {
vfree(fd->cq->comps);
@@ -321,7 +345,8 @@
{
int ret = 0, i;
struct hfi1_ctxtdata *uctxt = fd->uctxt;
- struct hfi1_user_sdma_pkt_q *pq = fd->pq;
+ struct hfi1_user_sdma_pkt_q *pq =
+ srcu_dereference(fd->pq, &fd->pq_srcu);
struct hfi1_user_sdma_comp_q *cq = fd->cq;
struct hfi1_devdata *dd = pq->dd;
unsigned long idx = 0;
@@ -564,10 +589,6 @@
set_comp_state(pq, cq, info.comp_idx, QUEUED, 0);
pq->state = SDMA_PKT_Q_ACTIVE;
- /* Send the first N packets in the request to buy us some time */
- ret = user_sdma_send_pkts(req, pcount);
- if (unlikely(ret < 0 && ret != -EBUSY))
- goto free_req;
/*
* This is a somewhat blocking send implementation.
@@ -580,11 +601,12 @@
if (ret < 0) {
if (ret != -EBUSY)
goto free_req;
- wait_event_interruptible_timeout(
+ if (wait_event_interruptible_timeout(
pq->busy.wait_dma,
- (pq->state == SDMA_PKT_Q_ACTIVE),
+ pq->state == SDMA_PKT_Q_ACTIVE,
msecs_to_jiffies(
- SDMA_IOWAIT_TIMEOUT));
+ SDMA_IOWAIT_TIMEOUT)) <= 0)
+ flush_pq_iowait(pq);
}
}
*count += idx;
diff --git a/drivers/infiniband/hw/hfi1/verbs.c b/drivers/infiniband/hw/hfi1/verbs.c
index 089e201..2f6323a 100644
--- a/drivers/infiniband/hw/hfi1/verbs.c
+++ b/drivers/infiniband/hw/hfi1/verbs.c
@@ -515,10 +515,11 @@
opa_get_lid(packet->dlid, 9B));
if (!mcast)
goto drop;
+ rcu_read_lock();
list_for_each_entry_rcu(p, &mcast->qp_list, list) {
packet->qp = p->qp;
if (hfi1_do_pkey_check(packet))
- goto drop;
+ goto unlock_drop;
spin_lock_irqsave(&packet->qp->r_lock, flags);
packet_handler = qp_ok(packet);
if (likely(packet_handler))
@@ -527,6 +528,7 @@
ibp->rvp.n_pkt_drops++;
spin_unlock_irqrestore(&packet->qp->r_lock, flags);
}
+ rcu_read_unlock();
/*
* Notify rvt_multicast_detach() if it is waiting for us
* to finish.