9 files changed, 107 insertions, 59 deletions

diff --git a/drivers/infiniband/hw/hfi1/chip.c b/drivers/infiniband/hw/hfi1/chip.c
index 3be62ef154d1..7853b0caad32 100644
--- a/drivers/infiniband/hw/hfi1/chip.c
+++ b/drivers/infiniband/hw/hfi1/chip.c
@@ -6379,18 +6379,17 @@ static void lcb_shutdown(struct hfi1_devdata *dd, int abort)
  *
  * The expectation is that the caller of this routine would have taken
  * care of properly transitioning the link into the correct state.
+ * NOTE: the caller needs to acquire the dd->dc8051_lock lock
+ *       before calling this function.
  */
-static void dc_shutdown(struct hfi1_devdata *dd)
+static void _dc_shutdown(struct hfi1_devdata *dd)
 {
-	unsigned long flags;
+	lockdep_assert_held(&dd->dc8051_lock);
 
-	spin_lock_irqsave(&dd->dc8051_lock, flags);
-	if (dd->dc_shutdown) {
-		spin_unlock_irqrestore(&dd->dc8051_lock, flags);
+	if (dd->dc_shutdown)
 		return;
-	}
+
 	dd->dc_shutdown = 1;
-	spin_unlock_irqrestore(&dd->dc8051_lock, flags);
 	/* Shutdown the LCB */
 	lcb_shutdown(dd, 1);
 	/*
@@ -6401,35 +6400,45 @@ static void dc_shutdown(struct hfi1_devdata *dd)
 	write_csr(dd, DC_DC8051_CFG_RST, 0x1);
 }
 
+static void dc_shutdown(struct hfi1_devdata *dd)
+{
+	mutex_lock(&dd->dc8051_lock);
+	_dc_shutdown(dd);
+	mutex_unlock(&dd->dc8051_lock);
+}
+
 /*
  * Calling this after the DC has been brought out of reset should not
  * do any damage.
+ * NOTE: the caller needs to acquire the dd->dc8051_lock lock
+ *       before calling this function.
  */
-static void dc_start(struct hfi1_devdata *dd)
+static void _dc_start(struct hfi1_devdata *dd)
 {
-	unsigned long flags;
-	int ret;
+	lockdep_assert_held(&dd->dc8051_lock);
 
-	spin_lock_irqsave(&dd->dc8051_lock, flags);
 	if (!dd->dc_shutdown)
-		goto done;
-	spin_unlock_irqrestore(&dd->dc8051_lock, flags);
+		return;
+
 	/* Take the 8051 out of reset */
 	write_csr(dd, DC_DC8051_CFG_RST, 0ull);
 	/* Wait until 8051 is ready */
-	ret = wait_fm_ready(dd, TIMEOUT_8051_START);
-	if (ret) {
+	if (wait_fm_ready(dd, TIMEOUT_8051_START))
 		dd_dev_err(dd, "%s: timeout starting 8051 firmware\n",
 			   __func__);
-	}
+
 	/* Take away reset for LCB and RX FPE (set in lcb_shutdown). */
 	write_csr(dd, DCC_CFG_RESET, 0x10);
 	/* lcb_shutdown() with abort=1 does not restore these */
 	write_csr(dd, DC_LCB_ERR_EN, dd->lcb_err_en);
-	spin_lock_irqsave(&dd->dc8051_lock, flags);
 	dd->dc_shutdown = 0;
-done:
-	spin_unlock_irqrestore(&dd->dc8051_lock, flags);
+}
+
+static void dc_start(struct hfi1_devdata *dd)
+{
+	mutex_lock(&dd->dc8051_lock);
+	_dc_start(dd);
+	mutex_unlock(&dd->dc8051_lock);
 }
 
 /*
@@ -8418,16 +8427,11 @@ static int do_8051_command(
 {
 	u64 reg, completed;
 	int return_code;
-	unsigned long flags;
 	unsigned long timeout;
 
 	hfi1_cdbg(DC8051, "type %d, data 0x%012llx", type, in_data);
 
-	/*
-	 * Alternative to holding the lock for a long time:
-	 * - keep busy wait - have other users bounce off
-	 */
-	spin_lock_irqsave(&dd->dc8051_lock, flags);
+	mutex_lock(&dd->dc8051_lock);
 
 	/* We can't send any commands to the 8051 if it's in reset */
 	if (dd->dc_shutdown) {
@@ -8453,10 +8457,8 @@ static int do_8051_command(
 			return_code = -ENXIO;
 			goto fail;
 		}
-		spin_unlock_irqrestore(&dd->dc8051_lock, flags);
-		dc_shutdown(dd);
-		dc_start(dd);
-		spin_lock_irqsave(&dd->dc8051_lock, flags);
+		_dc_shutdown(dd);
+		_dc_start(dd);
 	}
 
 	/*
@@ -8534,8 +8536,7 @@ static int do_8051_command(
 	write_csr(dd, DC_DC8051_CFG_HOST_CMD_0, 0);
 
 fail:
-	spin_unlock_irqrestore(&dd->dc8051_lock, flags);
-
+	mutex_unlock(&dd->dc8051_lock);
 	return return_code;
 }
 
@@ -11849,6 +11850,10 @@ static void free_cntrs(struct hfi1_devdata *dd)
 	dd->scntrs = NULL;
 	kfree(dd->cntrnames);
 	dd->cntrnames = NULL;
+	if (dd->update_cntr_wq) {
+		destroy_workqueue(dd->update_cntr_wq);
+		dd->update_cntr_wq = NULL;
+	}
 }
 
 static u64 read_dev_port_cntr(struct hfi1_devdata *dd, struct cntr_entry *entry,
@@ -12004,7 +12009,7 @@ u64 write_port_cntr(struct hfi1_pportdata *ppd, int index, int vl, u64 data)
 	return write_dev_port_cntr(ppd->dd, entry, sval, ppd, vl, data);
 }
 
-static void update_synth_timer(unsigned long opaque)
+static void do_update_synth_timer(struct work_struct *work)
 {
 	u64 cur_tx;
 	u64 cur_rx;
@@ -12013,8 +12018,8 @@ static void update_synth_timer(unsigned long opaque)
 	int i, j, vl;
 	struct hfi1_pportdata *ppd;
 	struct cntr_entry *entry;
-
-	struct hfi1_devdata *dd = (struct hfi1_devdata *)opaque;
+	struct hfi1_devdata *dd = container_of(work, struct hfi1_devdata,
+					       update_cntr_work);
 
 	/*
 	 * Rather than keep beating on the CSRs pick a minimal set that we can
@@ -12097,7 +12102,13 @@ static void update_synth_timer(unsigned long opaque)
 	} else {
 		hfi1_cdbg(CNTR, "[%d] No update necessary", dd->unit);
 	}
+}
+
+static void update_synth_timer(unsigned long opaque)
+{
+	struct hfi1_devdata *dd = (struct hfi1_devdata *)opaque;
 
+	queue_work(dd->update_cntr_wq, &dd->update_cntr_work);
 	mod_timer(&dd->synth_stats_timer, jiffies + HZ * SYNTH_CNT_TIME);
 }
 
@@ -12333,6 +12344,13 @@ static int init_cntrs(struct hfi1_devdata *dd)
 	if (init_cpu_counters(dd))
 		goto bail;
 
+	dd->update_cntr_wq = alloc_ordered_workqueue("hfi1_update_cntr_%d",
+						     WQ_MEM_RECLAIM, dd->unit);
+	if (!dd->update_cntr_wq)
+		goto bail;
+
+	INIT_WORK(&dd->update_cntr_work, do_update_synth_timer);
+
 	mod_timer(&dd->synth_stats_timer, jiffies + HZ * SYNTH_CNT_TIME);
 	return 0;
 bail:
diff --git a/drivers/infiniband/hw/hfi1/hfi.h b/drivers/infiniband/hw/hfi1/hfi.h
index cc87fd4e534b..a3279f3d2578 100644
--- a/drivers/infiniband/hw/hfi1/hfi.h
+++ b/drivers/infiniband/hw/hfi1/hfi.h
@@ -475,7 +475,7 @@ struct rvt_sge_state;
 #define HFI1_PART_ENFORCE_OUT	0x2
 
 /* how often we check for synthetic counter wrap around */
-#define SYNTH_CNT_TIME 2
+#define SYNTH_CNT_TIME 3
 
 /* Counter flags */
 #define CNTR_NORMAL		0x0 /* Normal counters, just read register */
@@ -929,8 +929,9 @@ struct hfi1_devdata {
 	spinlock_t rcvctrl_lock; /* protect changes to RcvCtrl */
 	/* around rcd and (user ctxts) ctxt_cnt use (intr vs free) */
 	spinlock_t uctxt_lock; /* rcd and user context changes */
-	/* exclusive access to 8051 */
-	spinlock_t dc8051_lock;
+	struct mutex dc8051_lock; /* exclusive access to 8051 */
+	struct workqueue_struct *update_cntr_wq;
+	struct work_struct update_cntr_work;
 	/* exclusive access to 8051 memory */
 	spinlock_t dc8051_memlock;
 	int dc8051_timed_out;	/* remember if the 8051 timed out */
diff --git a/drivers/infiniband/hw/hfi1/init.c b/drivers/infiniband/hw/hfi1/init.c
index a3dd27b1305d..84a97f3f9299 100644
--- a/drivers/infiniband/hw/hfi1/init.c
+++ b/drivers/infiniband/hw/hfi1/init.c
@@ -1078,11 +1078,11 @@ struct hfi1_devdata *hfi1_alloc_devdata(struct pci_dev *pdev, size_t extra)
 	spin_lock_init(&dd->uctxt_lock);
 	spin_lock_init(&dd->hfi1_diag_trans_lock);
 	spin_lock_init(&dd->sc_init_lock);
-	spin_lock_init(&dd->dc8051_lock);
 	spin_lock_init(&dd->dc8051_memlock);
 	seqlock_init(&dd->sc2vl_lock);
 	spin_lock_init(&dd->sde_map_lock);
 	spin_lock_init(&dd->pio_map_lock);
+	mutex_init(&dd->dc8051_lock);
 	init_waitqueue_head(&dd->event_queue);
 
 	dd->int_counter = alloc_percpu(u64);
diff --git a/drivers/infiniband/hw/mlx4/main.c b/drivers/infiniband/hw/mlx4/main.c
index c41c8d0a4ac0..19bc1c2186ff 100644
--- a/drivers/infiniband/hw/mlx4/main.c
+++ b/drivers/infiniband/hw/mlx4/main.c
@@ -1168,7 +1168,7 @@ static void mlx4_ib_disassociate_ucontext(struct ib_ucontext *ibcontext)
 	/* need to protect from a race on closing the vma as part of
 	 * mlx4_ib_vma_close().
 	 */
-	down_read(&owning_mm->mmap_sem);
+	down_write(&owning_mm->mmap_sem);
 	for (i = 0; i < HW_BAR_COUNT; i++) {
 		vma = context->hw_bar_info[i].vma;
 		if (!vma)
@@ -1182,11 +1182,13 @@ static void mlx4_ib_disassociate_ucontext(struct ib_ucontext *ibcontext)
 			BUG_ON(1);
 		}
 
+		context->hw_bar_info[i].vma->vm_flags &=
+			~(VM_SHARED | VM_MAYSHARE);
 		/* context going to be destroyed, should not access ops any more */
 		context->hw_bar_info[i].vma->vm_ops = NULL;
 	}
 
-	up_read(&owning_mm->mmap_sem);
+	up_write(&owning_mm->mmap_sem);
 	mmput(owning_mm);
 	put_task_struct(owning_process);
 }
diff --git a/drivers/infiniband/hw/mlx5/cq.c b/drivers/infiniband/hw/mlx5/cq.c
index 9cdcff77b9a8..fc62a7ded734 100644
--- a/drivers/infiniband/hw/mlx5/cq.c
+++ b/drivers/infiniband/hw/mlx5/cq.c
@@ -172,6 +172,8 @@ static void handle_responder(struct ib_wc *wc, struct mlx5_cqe64 *cqe,
 	struct mlx5_ib_srq *srq;
 	struct mlx5_ib_wq *wq;
 	u16 wqe_ctr;
+	u8  roce_packet_type;
+	bool vlan_present;
 	u8 g;
 
 	if (qp->ibqp.srq || qp->ibqp.xrcd) {
@@ -223,7 +225,6 @@ static void handle_responder(struct ib_wc *wc, struct mlx5_cqe64 *cqe,
 		break;
 	}
 	wc->slid	   = be16_to_cpu(cqe->slid);
-	wc->sl		   = (be32_to_cpu(cqe->flags_rqpn) >> 24) & 0xf;
 	wc->src_qp	   = be32_to_cpu(cqe->flags_rqpn) & 0xffffff;
 	wc->dlid_path_bits = cqe->ml_path;
 	g = (be32_to_cpu(cqe->flags_rqpn) >> 28) & 3;
@@ -237,10 +238,22 @@ static void handle_responder(struct ib_wc *wc, struct mlx5_cqe64 *cqe,
 		wc->pkey_index = 0;
 	}
 
-	if (ll != IB_LINK_LAYER_ETHERNET)
+	if (ll != IB_LINK_LAYER_ETHERNET) {
+		wc->sl = (be32_to_cpu(cqe->flags_rqpn) >> 24) & 0xf;
 		return;
+	}
+
+	vlan_present = cqe->l4_l3_hdr_type & 0x1;
+	roce_packet_type   = (be32_to_cpu(cqe->flags_rqpn) >> 24) & 0x3;
+	if (vlan_present) {
+		wc->vlan_id = (be16_to_cpu(cqe->vlan_info)) & 0xfff;
+		wc->sl = (be16_to_cpu(cqe->vlan_info) >> 13) & 0x7;
+		wc->wc_flags |= IB_WC_WITH_VLAN;
+	} else {
+		wc->sl = 0;
+	}
 
-	switch (wc->sl & 0x3) {
+	switch (roce_packet_type) {
 	case MLX5_CQE_ROCE_L3_HEADER_TYPE_GRH:
 		wc->network_hdr_type = RDMA_NETWORK_IB;
 		break;
diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c
index 5e29fbd3a5a0..d7da1dca765f 100644
--- a/drivers/infiniband/hw/mlx5/main.c
+++ b/drivers/infiniband/hw/mlx5/main.c
@@ -1313,7 +1313,7 @@ static void mlx5_ib_disassociate_ucontext(struct ib_ucontext *ibcontext)
 	/* need to protect from a race on closing the vma as part of
 	 * mlx5_ib_vma_close.
 	 */
-	down_read(&owning_mm->mmap_sem);
+	down_write(&owning_mm->mmap_sem);
 	list_for_each_entry_safe(vma_private, n, &context->vma_private_list,
 				 list) {
 		vma = vma_private->vma;
@@ -1323,11 +1323,12 @@ static void mlx5_ib_disassociate_ucontext(struct ib_ucontext *ibcontext)
 		/* context going to be destroyed, should
 		 * not access ops any more.
 		 */
+		vma->vm_flags &= ~(VM_SHARED | VM_MAYSHARE);
 		vma->vm_ops = NULL;
 		list_del(&vma_private->list);
 		kfree(vma_private);
 	}
-	up_read(&owning_mm->mmap_sem);
+	up_write(&owning_mm->mmap_sem);
 	mmput(owning_mm);
 	put_task_struct(owning_process);
 }
diff --git a/drivers/infiniband/hw/mlx5/qp.c b/drivers/infiniband/hw/mlx5/qp.c
index fdd156101a72..403df3591d29 100644
--- a/drivers/infiniband/hw/mlx5/qp.c
+++ b/drivers/infiniband/hw/mlx5/qp.c
@@ -1130,7 +1130,7 @@ static void destroy_raw_packet_qp_sq(struct mlx5_ib_dev *dev,
 	ib_umem_release(sq->ubuffer.umem);
 }
 
-static int get_rq_pas_size(void *qpc)
+static size_t get_rq_pas_size(void *qpc)
 {
 	u32 log_page_size = MLX5_GET(qpc, qpc, log_page_size) + 12;
 	u32 log_rq_stride = MLX5_GET(qpc, qpc, log_rq_stride);
@@ -1146,7 +1146,8 @@ static int get_rq_pas_size(void *qpc)
 }
 
 static int create_raw_packet_qp_rq(struct mlx5_ib_dev *dev,
-				   struct mlx5_ib_rq *rq, void *qpin)
+				   struct mlx5_ib_rq *rq, void *qpin,
+				   size_t qpinlen)
 {
 	struct mlx5_ib_qp *mqp = rq->base.container_mibqp;
 	__be64 *pas;
@@ -1155,9 +1156,12 @@ static int create_raw_packet_qp_rq(struct mlx5_ib_dev *dev,
 	void *rqc;
 	void *wq;
 	void *qpc = MLX5_ADDR_OF(create_qp_in, qpin, qpc);
-	int inlen;
+	size_t rq_pas_size = get_rq_pas_size(qpc);
+	size_t inlen;
 	int err;
-	u32 rq_pas_size = get_rq_pas_size(qpc);
+
+	if (qpinlen < rq_pas_size + MLX5_BYTE_OFF(create_qp_in, pas))
+		return -EINVAL;
 
 	inlen = MLX5_ST_SZ_BYTES(create_rq_in) + rq_pas_size;
 	in = mlx5_vzalloc(inlen);
@@ -1235,7 +1239,7 @@ static void destroy_raw_packet_qp_tir(struct mlx5_ib_dev *dev,
 }
 
 static int create_raw_packet_qp(struct mlx5_ib_dev *dev, struct mlx5_ib_qp *qp,
-				u32 *in,
+				u32 *in, size_t inlen,
 				struct ib_pd *pd)
 {
 	struct mlx5_ib_raw_packet_qp *raw_packet_qp = &qp->raw_packet_qp;
@@ -1262,7 +1266,7 @@ static int create_raw_packet_qp(struct mlx5_ib_dev *dev, struct mlx5_ib_qp *qp,
 	if (qp->rq.wqe_cnt) {
 		rq->base.container_mibqp = qp;
 
-		err = create_raw_packet_qp_rq(dev, rq, in);
+		err = create_raw_packet_qp_rq(dev, rq, in, inlen);
 		if (err)
 			goto err_destroy_sq;
 
@@ -1753,10 +1757,15 @@ static int create_qp_common(struct mlx5_ib_dev *dev, struct ib_pd *pd,
 		qp->flags |= MLX5_IB_QP_LSO;
 	}
 
+	if (inlen < 0) {
+		err = -EINVAL;
+		goto err;
+	}
+
 	if (init_attr->qp_type == IB_QPT_RAW_PACKET) {
 		qp->raw_packet_qp.sq.ubuffer.buf_addr = ucmd.sq_buf_addr;
 		raw_packet_qp_copy_info(qp, &qp->raw_packet_qp);
-		err = create_raw_packet_qp(dev, qp, in, pd);
+		err = create_raw_packet_qp(dev, qp, in, inlen, pd);
 	} else {
 		err = mlx5_core_create_qp(dev->mdev, &base->mqp, in, inlen);
 	}
@@ -1796,6 +1805,7 @@ err_create:
 	else if (qp->create_type == MLX5_QP_KERNEL)
 		destroy_qp_kernel(dev, qp);
 
+err:
 	kvfree(in);
 	return err;
 }
diff --git a/drivers/infiniband/hw/mlx5/srq.c b/drivers/infiniband/hw/mlx5/srq.c
index d61fd2c727c0..5c1dbe2f8757 100644
--- a/drivers/infiniband/hw/mlx5/srq.c
+++ b/drivers/infiniband/hw/mlx5/srq.c
@@ -243,8 +243,8 @@ struct ib_srq *mlx5_ib_create_srq(struct ib_pd *pd,
 {
 	struct mlx5_ib_dev *dev = to_mdev(pd->device);
 	struct mlx5_ib_srq *srq;
-	int desc_size;
-	int buf_size;
+	size_t desc_size;
+	size_t buf_size;
 	int err;
 	struct mlx5_srq_attr in = {0};
 	__u32 max_srq_wqes = 1 << MLX5_CAP_GEN(dev->mdev, log_max_srq_sz);
@@ -268,15 +268,18 @@ struct ib_srq *mlx5_ib_create_srq(struct ib_pd *pd,
 
 	desc_size = sizeof(struct mlx5_wqe_srq_next_seg) +
 		    srq->msrq.max_gs * sizeof(struct mlx5_wqe_data_seg);
+	if (desc_size == 0 || srq->msrq.max_gs > desc_size)
+		return ERR_PTR(-EINVAL);
 	desc_size = roundup_pow_of_two(desc_size);
-	desc_size = max_t(int, 32, desc_size);
+	desc_size = max_t(size_t, 32, desc_size);
+	if (desc_size < sizeof(struct mlx5_wqe_srq_next_seg))
+		return ERR_PTR(-EINVAL);
 	srq->msrq.max_avail_gather = (desc_size - sizeof(struct mlx5_wqe_srq_next_seg)) /
 		sizeof(struct mlx5_wqe_data_seg);
 	srq->msrq.wqe_shift = ilog2(desc_size);
 	buf_size = srq->msrq.max * desc_size;
-	mlx5_ib_dbg(dev, "desc_size 0x%x, req wr 0x%x, srq size 0x%x, max_gs 0x%x, max_avail_gather 0x%x\n",
-		    desc_size, init_attr->attr.max_wr, srq->msrq.max, srq->msrq.max_gs,
-		    srq->msrq.max_avail_gather);
+	if (buf_size < desc_size)
+		return ERR_PTR(-EINVAL);
 	in.type = init_attr->srq_type;
 
 	if (pd->uobject)
diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_stats.c b/drivers/infiniband/hw/ocrdma/ocrdma_stats.c
index 8bef09a8c49f..265943069b35 100644
--- a/drivers/infiniband/hw/ocrdma/ocrdma_stats.c
+++ b/drivers/infiniband/hw/ocrdma/ocrdma_stats.c
@@ -836,7 +836,7 @@ void ocrdma_add_port_stats(struct ocrdma_dev *dev)
 
 	dev->reset_stats.type = OCRDMA_RESET_STATS;
 	dev->reset_stats.dev = dev;
-	if (!debugfs_create_file("reset_stats", S_IRUSR, dev->dir,
+	if (!debugfs_create_file("reset_stats", 0200, dev->dir,
 				&dev->reset_stats, &ocrdma_dbg_ops))
 		goto err;