10 files changed, 51 insertions, 85 deletions

diff --git a/drivers/infiniband/hw/hfi1/chip.c b/drivers/infiniband/hw/hfi1/chip.c
index 16861d9ba1b7..229d5d4cafe8 100644
--- a/drivers/infiniband/hw/hfi1/chip.c
+++ b/drivers/infiniband/hw/hfi1/chip.c
@@ -14675,8 +14675,8 @@ void hfi1_start_cleanup(struct hfi1_devdata *dd)
  */
 static int init_asic_data(struct hfi1_devdata *dd)
 {
-	unsigned long flags;
-	struct hfi1_devdata *tmp, *peer = NULL;
+	unsigned long index;
+	struct hfi1_devdata *peer;
 	struct hfi1_asic_data *asic_data;
 	int ret = 0;
 
@@ -14685,14 +14685,12 @@ static int init_asic_data(struct hfi1_devdata *dd)
 	if (!asic_data)
 		return -ENOMEM;
 
-	spin_lock_irqsave(&hfi1_devs_lock, flags);
+	xa_lock_irq(&hfi1_dev_table);
 	/* Find our peer device */
-	list_for_each_entry(tmp, &hfi1_dev_list, list) {
-		if ((HFI_BASE_GUID(dd) == HFI_BASE_GUID(tmp)) &&
-		    dd->unit != tmp->unit) {
-			peer = tmp;
+	xa_for_each(&hfi1_dev_table, index, peer) {
+		if ((HFI_BASE_GUID(dd) == HFI_BASE_GUID(peer)) &&
+		    dd->unit != peer->unit)
 			break;
-		}
 	}
 
 	if (peer) {
@@ -14704,7 +14702,7 @@ static int init_asic_data(struct hfi1_devdata *dd)
 		mutex_init(&dd->asic_data->asic_resource_mutex);
 	}
 	dd->asic_data->dds[dd->hfi1_id] = dd; /* self back-pointer */
-	spin_unlock_irqrestore(&hfi1_devs_lock, flags);
+	xa_unlock_irq(&hfi1_dev_table);
 
 	/* first one through - set up i2c devices */
 	if (!peer)
diff --git a/drivers/infiniband/hw/hfi1/debugfs.c b/drivers/infiniband/hw/hfi1/debugfs.c
index 427ba0ce74a5..057bb82c664f 100644
--- a/drivers/infiniband/hw/hfi1/debugfs.c
+++ b/drivers/infiniband/hw/hfi1/debugfs.c
@@ -1302,15 +1302,15 @@ static void _driver_stats_seq_stop(struct seq_file *s, void *v)
 
 static u64 hfi1_sps_ints(void)
 {
-	unsigned long flags;
+	unsigned long index, flags;
 	struct hfi1_devdata *dd;
 	u64 sps_ints = 0;
 
-	spin_lock_irqsave(&hfi1_devs_lock, flags);
-	list_for_each_entry(dd, &hfi1_dev_list, list) {
+	xa_lock_irqsave(&hfi1_dev_table, flags);
+	xa_for_each(&hfi1_dev_table, index, dd) {
 		sps_ints += get_all_cpu_total(dd->int_counter);
 	}
-	spin_unlock_irqrestore(&hfi1_devs_lock, flags);
+	xa_unlock_irqrestore(&hfi1_dev_table, flags);
 	return sps_ints;
 }
 
diff --git a/drivers/infiniband/hw/hfi1/driver.c b/drivers/infiniband/hw/hfi1/driver.c
index 1f4fe0269b51..129e48ec9ee0 100644
--- a/drivers/infiniband/hw/hfi1/driver.c
+++ b/drivers/infiniband/hw/hfi1/driver.c
@@ -72,8 +72,6 @@
  */
 const char ib_hfi1_version[] = HFI1_DRIVER_VERSION "\n";
 
-DEFINE_SPINLOCK(hfi1_devs_lock);
-LIST_HEAD(hfi1_dev_list);
 DEFINE_MUTEX(hfi1_mutex);	/* general driver use */
 
 unsigned int hfi1_max_mtu = HFI1_DEFAULT_MAX_MTU;
@@ -175,11 +173,11 @@ int hfi1_count_active_units(void)
 {
 	struct hfi1_devdata *dd;
 	struct hfi1_pportdata *ppd;
-	unsigned long flags;
+	unsigned long index, flags;
 	int pidx, nunits_active = 0;
 
-	spin_lock_irqsave(&hfi1_devs_lock, flags);
-	list_for_each_entry(dd, &hfi1_dev_list, list) {
+	xa_lock_irqsave(&hfi1_dev_table, flags);
+	xa_for_each(&hfi1_dev_table, index, dd) {
 		if (!(dd->flags & HFI1_PRESENT) || !dd->kregbase1)
 			continue;
 		for (pidx = 0; pidx < dd->num_pports; ++pidx) {
@@ -190,7 +188,7 @@ int hfi1_count_active_units(void)
 			}
 		}
 	}
-	spin_unlock_irqrestore(&hfi1_devs_lock, flags);
+	xa_unlock_irqrestore(&hfi1_dev_table, flags);
 	return nunits_active;
 }
 
diff --git a/drivers/infiniband/hw/hfi1/hfi.h b/drivers/infiniband/hw/hfi1/hfi.h
index 048b5d73ba39..b458c218842b 100644
--- a/drivers/infiniband/hw/hfi1/hfi.h
+++ b/drivers/infiniband/hw/hfi1/hfi.h
@@ -54,7 +54,6 @@
 #include <linux/list.h>
 #include <linux/scatterlist.h>
 #include <linux/slab.h>
-#include <linux/idr.h>
 #include <linux/io.h>
 #include <linux/fs.h>
 #include <linux/completion.h>
@@ -65,6 +64,7 @@
 #include <linux/kthread.h>
 #include <linux/i2c.h>
 #include <linux/i2c-algo-bit.h>
+#include <linux/xarray.h>
 #include <rdma/ib_hdrs.h>
 #include <rdma/opa_addr.h>
 #include <linux/rhashtable.h>
@@ -1021,8 +1021,8 @@ struct hfi1_asic_data {
 struct hfi1_vnic_data {
 	struct hfi1_ctxtdata *ctxt[HFI1_NUM_VNIC_CTXT];
 	struct kmem_cache *txreq_cache;
+	struct xarray vesws;
 	u8 num_vports;
-	struct idr vesw_idr;
 	u8 rmt_start;
 	u8 num_ctxt;
 };
@@ -1041,7 +1041,6 @@ struct sdma_vl_map;
 typedef int (*send_routine)(struct rvt_qp *, struct hfi1_pkt_state *, u64);
 struct hfi1_devdata {
 	struct hfi1_ibdev verbs_dev;     /* must be first */
-	struct list_head list;
 	/* pointers to related structs for this device */
 	/* pci access data structure */
 	struct pci_dev *pcidev;
@@ -1426,8 +1425,7 @@ struct hfi1_filedata {
 	struct mm_struct *mm;
 };
 
-extern struct list_head hfi1_dev_list;
-extern spinlock_t hfi1_devs_lock;
+extern struct xarray hfi1_dev_table;
 struct hfi1_devdata *hfi1_lookup(int unit);
 
 static inline unsigned long uctxt_offset(struct hfi1_ctxtdata *uctxt)
diff --git a/drivers/infiniband/hw/hfi1/init.c b/drivers/infiniband/hw/hfi1/init.c
index faaaac8fbc55..e4c2ae4f1cb3 100644
--- a/drivers/infiniband/hw/hfi1/init.c
+++ b/drivers/infiniband/hw/hfi1/init.c
@@ -49,7 +49,7 @@
 #include <linux/netdevice.h>
 #include <linux/vmalloc.h>
 #include <linux/delay.h>
-#include <linux/idr.h>
+#include <linux/xarray.h>
 #include <linux/module.h>
 #include <linux/printk.h>
 #include <linux/hrtimer.h>
@@ -124,7 +124,7 @@ MODULE_PARM_DESC(user_credit_return_threshold, "Credit return threshold for user
 
 static inline u64 encode_rcv_header_entry_size(u16 size);
 
-static struct idr hfi1_unit_table;
+DEFINE_XARRAY_FLAGS(hfi1_dev_table, XA_FLAGS_ALLOC | XA_FLAGS_LOCK_IRQ);
 
 static int hfi1_create_kctxt(struct hfi1_devdata *dd,
 			     struct hfi1_pportdata *ppd)
@@ -469,7 +469,7 @@ int hfi1_create_ctxtdata(struct hfi1_pportdata *ppd, int numa,
 		if (rcd->egrbufs.size < hfi1_max_mtu) {
 			rcd->egrbufs.size = __roundup_pow_of_two(hfi1_max_mtu);
 			hfi1_cdbg(PROC,
-				  "ctxt%u: eager bufs size too small. Adjusting to %zu\n",
+				  "ctxt%u: eager bufs size too small. Adjusting to %u\n",
 				    rcd->ctxt, rcd->egrbufs.size);
 		}
 		rcd->egrbufs.rcvtid_size = HFI1_MAX_EAGER_BUFFER_SIZE;
@@ -1018,21 +1018,9 @@ done:
 	return ret;
 }
 
-static inline struct hfi1_devdata *__hfi1_lookup(int unit)
-{
-	return idr_find(&hfi1_unit_table, unit);
-}
-
 struct hfi1_devdata *hfi1_lookup(int unit)
 {
-	struct hfi1_devdata *dd;
-	unsigned long flags;
-
-	spin_lock_irqsave(&hfi1_devs_lock, flags);
-	dd = __hfi1_lookup(unit);
-	spin_unlock_irqrestore(&hfi1_devs_lock, flags);
-
-	return dd;
+	return xa_load(&hfi1_dev_table, unit);
 }
 
 /*
@@ -1200,7 +1188,7 @@ void hfi1_free_ctxtdata(struct hfi1_devdata *dd, struct hfi1_ctxtdata *rcd)
 /*
  * Release our hold on the shared asic data.  If we are the last one,
  * return the structure to be finalized outside the lock.  Must be
- * holding hfi1_devs_lock.
+ * holding hfi1_dev_table lock.
  */
 static struct hfi1_asic_data *release_asic_data(struct hfi1_devdata *dd)
 {
@@ -1236,13 +1224,10 @@ static void hfi1_clean_devdata(struct hfi1_devdata *dd)
 	struct hfi1_asic_data *ad;
 	unsigned long flags;
 
-	spin_lock_irqsave(&hfi1_devs_lock, flags);
-	if (!list_empty(&dd->list)) {
-		idr_remove(&hfi1_unit_table, dd->unit);
-		list_del_init(&dd->list);
-	}
+	xa_lock_irqsave(&hfi1_dev_table, flags);
+	__xa_erase(&hfi1_dev_table, dd->unit);
 	ad = release_asic_data(dd);
-	spin_unlock_irqrestore(&hfi1_devs_lock, flags);
+	xa_unlock_irqrestore(&hfi1_dev_table, flags);
 
 	finalize_asic_data(dd, ad);
 	free_platform_config(dd);
@@ -1286,13 +1271,10 @@ void hfi1_free_devdata(struct hfi1_devdata *dd)
  * Must be done via verbs allocator, because the verbs cleanup process
  * both does cleanup and free of the data structure.
  * "extra" is for chip-specific data.
- *
- * Use the idr mechanism to get a unit number for this unit.
  */
 static struct hfi1_devdata *hfi1_alloc_devdata(struct pci_dev *pdev,
 					       size_t extra)
 {
-	unsigned long flags;
 	struct hfi1_devdata *dd;
 	int ret, nports;
 
@@ -1307,21 +1289,10 @@ static struct hfi1_devdata *hfi1_alloc_devdata(struct pci_dev *pdev,
 	dd->pport = (struct hfi1_pportdata *)(dd + 1);
 	dd->pcidev = pdev;
 	pci_set_drvdata(pdev, dd);
-
-	INIT_LIST_HEAD(&dd->list);
-	idr_preload(GFP_KERNEL);
-	spin_lock_irqsave(&hfi1_devs_lock, flags);
-
-	ret = idr_alloc(&hfi1_unit_table, dd, 0, 0, GFP_NOWAIT);
-	if (ret >= 0) {
-		dd->unit = ret;
-		list_add(&dd->list, &hfi1_dev_list);
-	}
 	dd->node = NUMA_NO_NODE;
 
-	spin_unlock_irqrestore(&hfi1_devs_lock, flags);
-	idr_preload_end();
-
+	ret = xa_alloc_irq(&hfi1_dev_table, &dd->unit, dd, xa_limit_32b,
+			GFP_KERNEL);
 	if (ret < 0) {
 		dev_err(&pdev->dev,
 			"Could not allocate unit ID: error %d\n", -ret);
@@ -1522,8 +1493,6 @@ static int __init hfi1_mod_init(void)
 	 * These must be called before the driver is registered with
 	 * the PCI subsystem.
 	 */
-	idr_init(&hfi1_unit_table);
-
 	hfi1_dbg_init();
 	ret = pci_register_driver(&hfi1_pci_driver);
 	if (ret < 0) {
@@ -1534,7 +1503,6 @@ static int __init hfi1_mod_init(void)
 
 bail_dev:
 	hfi1_dbg_exit();
-	idr_destroy(&hfi1_unit_table);
 	dev_cleanup();
 bail:
 	return ret;
@@ -1552,7 +1520,7 @@ static void __exit hfi1_mod_cleanup(void)
 	node_affinity_destroy_all();
 	hfi1_dbg_exit();
 
-	idr_destroy(&hfi1_unit_table);
+	WARN_ON(!xa_empty(&hfi1_dev_table));
 	dispose_firmware();	/* asymmetric with obtain_firmware() */
 	dev_cleanup();
 }
@@ -2071,7 +2039,7 @@ int hfi1_setup_eagerbufs(struct hfi1_ctxtdata *rcd)
 	rcd->egrbufs.size = alloced_bytes;
 
 	hfi1_cdbg(PROC,
-		  "ctxt%u: Alloced %u rcv tid entries @ %uKB, total %zuKB\n",
+		  "ctxt%u: Alloced %u rcv tid entries @ %uKB, total %uKB\n",
 		  rcd->ctxt, rcd->egrbufs.alloced,
 		  rcd->egrbufs.rcvtid_size / 1024, rcd->egrbufs.size / 1024);
 
diff --git a/drivers/infiniband/hw/hfi1/qp.c b/drivers/infiniband/hw/hfi1/qp.c
index eba300330a02..4e0e9fc0a777 100644
--- a/drivers/infiniband/hw/hfi1/qp.c
+++ b/drivers/infiniband/hw/hfi1/qp.c
@@ -742,6 +742,8 @@ void *qp_priv_alloc(struct rvt_dev_info *rdi, struct rvt_qp *qp)
 		iowait_wakeup,
 		iowait_sdma_drained,
 		hfi1_init_priority);
+	/* Init to a value to start the running average correctly */
+	priv->s_running_pkt_size = piothreshold / 2;
 	return priv;
 }
 
diff --git a/drivers/infiniband/hw/hfi1/trace_dbg.h b/drivers/infiniband/hw/hfi1/trace_dbg.h
index e62171fb7379..de7a87392b8d 100644
--- a/drivers/infiniband/hw/hfi1/trace_dbg.h
+++ b/drivers/infiniband/hw/hfi1/trace_dbg.h
@@ -86,14 +86,14 @@ DECLARE_EVENT_CLASS(hfi1_trace_template,
  * actual function to work and can not be in a macro.
  */
 #define __hfi1_trace_def(lvl) \
-void __hfi1_trace_##lvl(const char *funct, char *fmt, ...);		\
+void __printf(2, 3) __hfi1_trace_##lvl(const char *funct, char *fmt, ...); \
 									\
 DEFINE_EVENT(hfi1_trace_template, hfi1_ ##lvl,				\
 	TP_PROTO(const char *function, struct va_format *vaf),		\
 	TP_ARGS(function, vaf))
 
 #define __hfi1_trace_fn(lvl) \
-void __hfi1_trace_##lvl(const char *func, char *fmt, ...)		\
+void __printf(2, 3) __hfi1_trace_##lvl(const char *func, char *fmt, ...)\
 {									\
 	struct va_format vaf = {					\
 		.fmt = fmt,						\
diff --git a/drivers/infiniband/hw/hfi1/verbs.c b/drivers/infiniband/hw/hfi1/verbs.c
index 55a56b3d7f83..1eb4105b2d22 100644
--- a/drivers/infiniband/hw/hfi1/verbs.c
+++ b/drivers/infiniband/hw/hfi1/verbs.c
@@ -1223,15 +1223,16 @@ static inline send_routine get_send_routine(struct rvt_qp *qp,
 	case IB_QPT_UD:
 		break;
 	case IB_QPT_UC:
-	case IB_QPT_RC: {
+	case IB_QPT_RC:
+		priv->s_running_pkt_size =
+			(tx->s_cur_size + priv->s_running_pkt_size) / 2;
 		if (piothreshold &&
-		    tx->s_cur_size <= min(piothreshold, qp->pmtu) &&
+		    priv->s_running_pkt_size <= min(piothreshold, qp->pmtu) &&
 		    (BIT(ps->opcode & OPMASK) & pio_opmask[ps->opcode >> 5]) &&
 		    iowait_sdma_pending(&priv->s_iowait) == 0 &&
 		    !sdma_txreq_built(&tx->txreq))
 			return dd->process_pio_send;
 		break;
-	}
 	default:
 		break;
 	}
@@ -1739,15 +1740,15 @@ static struct rdma_hw_stats *alloc_hw_stats(struct ib_device *ibdev,
 
 static u64 hfi1_sps_ints(void)
 {
-	unsigned long flags;
+	unsigned long index, flags;
 	struct hfi1_devdata *dd;
 	u64 sps_ints = 0;
 
-	spin_lock_irqsave(&hfi1_devs_lock, flags);
-	list_for_each_entry(dd, &hfi1_dev_list, list) {
+	xa_lock_irqsave(&hfi1_dev_table, flags);
+	xa_for_each(&hfi1_dev_table, index, dd) {
 		sps_ints += get_all_cpu_total(dd->int_counter);
 	}
-	spin_unlock_irqrestore(&hfi1_devs_lock, flags);
+	xa_unlock_irqrestore(&hfi1_dev_table, flags);
 	return sps_ints;
 }
 
diff --git a/drivers/infiniband/hw/hfi1/verbs.h b/drivers/infiniband/hw/hfi1/verbs.h
index 62ace0b2d17a..7ecb8ed4a1d9 100644
--- a/drivers/infiniband/hw/hfi1/verbs.h
+++ b/drivers/infiniband/hw/hfi1/verbs.h
@@ -170,6 +170,7 @@ struct hfi1_qp_priv {
 	struct tid_flow_state flow_state;
 	struct tid_rdma_qp_params tid_rdma;
 	struct rvt_qp *owner;
+	u16 s_running_pkt_size;
 	u8 hdr_type; /* 9B or 16B */
 	struct rvt_sge_state tid_ss;       /* SGE state pointer for 2nd leg */
 	atomic_t n_requests;               /* # of TID RDMA requests in the */
diff --git a/drivers/infiniband/hw/hfi1/vnic_main.c b/drivers/infiniband/hw/hfi1/vnic_main.c
index a922db58be14..4d5683919b1f 100644
--- a/drivers/infiniband/hw/hfi1/vnic_main.c
+++ b/drivers/infiniband/hw/hfi1/vnic_main.c
@@ -162,12 +162,12 @@ static void deallocate_vnic_ctxt(struct hfi1_devdata *dd,
 
 void hfi1_vnic_setup(struct hfi1_devdata *dd)
 {
-	idr_init(&dd->vnic.vesw_idr);
+	xa_init(&dd->vnic.vesws);
 }
 
 void hfi1_vnic_cleanup(struct hfi1_devdata *dd)
 {
-	idr_destroy(&dd->vnic.vesw_idr);
+	WARN_ON(!xa_empty(&dd->vnic.vesws));
 }
 
 #define SUM_GRP_COUNTERS(stats, qstats, x_grp) do {            \
@@ -534,7 +534,7 @@ void hfi1_vnic_bypass_rcv(struct hfi1_packet *packet)
 	l4_type = hfi1_16B_get_l4(packet->ebuf);
 	if (likely(l4_type == OPA_16B_L4_ETHR)) {
 		vesw_id = HFI1_VNIC_GET_VESWID(packet->ebuf);
-		vinfo = idr_find(&dd->vnic.vesw_idr, vesw_id);
+		vinfo = xa_load(&dd->vnic.vesws, vesw_id);
 
 		/*
 		 * In case of invalid vesw id, count the error on
@@ -542,9 +542,10 @@ void hfi1_vnic_bypass_rcv(struct hfi1_packet *packet)
 		 */
 		if (unlikely(!vinfo)) {
 			struct hfi1_vnic_vport_info *vinfo_tmp;
-			int id_tmp = 0;
+			unsigned long index = 0;
 
-			vinfo_tmp =  idr_get_next(&dd->vnic.vesw_idr, &id_tmp);
+			vinfo_tmp = xa_find(&dd->vnic.vesws, &index, ULONG_MAX,
+					XA_PRESENT);
 			if (vinfo_tmp) {
 				spin_lock(&vport_cntr_lock);
 				vinfo_tmp->stats[0].netstats.rx_nohandler++;
@@ -598,8 +599,7 @@ static int hfi1_vnic_up(struct hfi1_vnic_vport_info *vinfo)
 	if (!vinfo->vesw_id)
 		return -EINVAL;
 
-	rc = idr_alloc(&dd->vnic.vesw_idr, vinfo, vinfo->vesw_id,
-		       vinfo->vesw_id + 1, GFP_NOWAIT);
+	rc = xa_insert(&dd->vnic.vesws, vinfo->vesw_id, vinfo, GFP_KERNEL);
 	if (rc < 0)
 		return rc;
 
@@ -625,7 +625,7 @@ static void hfi1_vnic_down(struct hfi1_vnic_vport_info *vinfo)
 	clear_bit(HFI1_VNIC_UP, &vinfo->flags);
 	netif_carrier_off(vinfo->netdev);
 	netif_tx_disable(vinfo->netdev);
-	idr_remove(&dd->vnic.vesw_idr, vinfo->vesw_id);
+	xa_erase(&dd->vnic.vesws, vinfo->vesw_id);
 
 	/* ensure irqs see the change */
 	msix_vnic_synchronize_irq(dd);