Message-Id: <1439493653-1191-5-git-send-email-jglisse@redhat.com>
Date:	Thu, 13 Aug 2015 15:20:49 -0400
From:	Jérôme Glisse <jglisse@...hat.com>
To:	<linux-kernel@...r.kernel.org>, <linux-rdma@...r.kernel.org>
Cc:	Christophe Harle <charle@...dia.com>,
	Duncan Poole <dpoole@...dia.com>,
	Sherry Cheung <SCheung@...dia.com>,
	Subhash Gutti <sgutti@...dia.com>,
	John Hubbard <jhubbard@...dia.com>,
	Mark Hairgrove <mhairgrove@...dia.com>,
	Lucien Dunning <ldunning@...dia.com>,
	Cameron Buschardt <cabuschardt@...dia.com>,
	Arvind Gopalakrishnan <arvindg@...dia.com>,
	Haggai Eran <haggaie@...lanox.com>,
	Shachar Raindel <raindel@...lanox.com>,
	Liran Liss <liranl@...lanox.com>,
	Jérôme Glisse <jglisse@...hat.com>
Subject: [RFC PATCH 4/8 v2] IB/odp/hmm: prepare for HMM code path.

This is a preparatory patch for HMM implementation of ODP (on demand
paging). It shuffle codes around that will be share between current
ODP implementation and HMM code path. It also convert many #ifdef
CONFIG to #if IS_ENABLED().

Signed-off-by: Jérôme Glisse <jglisse@...hat.com>
---
 drivers/infiniband/core/umem_odp.c           |   3 +
 drivers/infiniband/core/uverbs_cmd.c         |  24 ++++--
 drivers/infiniband/hw/mlx5/main.c            |  13 ++-
 drivers/infiniband/hw/mlx5/mem.c             |  11 ++-
 drivers/infiniband/hw/mlx5/mlx5_ib.h         |  14 ++--
 drivers/infiniband/hw/mlx5/mr.c              |  19 +++--
 drivers/infiniband/hw/mlx5/odp.c             | 118 ++++++++++++++-------------
 drivers/infiniband/hw/mlx5/qp.c              |   4 +-
 drivers/net/ethernet/mellanox/mlx5/core/eq.c |   2 +-
 drivers/net/ethernet/mellanox/mlx5/core/qp.c |   8 +-
 include/rdma/ib_umem_odp.h                   |  51 +++++++-----
 include/rdma/ib_verbs.h                      |   7 +-
 12 files changed, 159 insertions(+), 115 deletions(-)

diff --git a/drivers/infiniband/core/umem_odp.c b/drivers/infiniband/core/umem_odp.c
index 0541761..d3b65d4 100644
--- a/drivers/infiniband/core/umem_odp.c
+++ b/drivers/infiniband/core/umem_odp.c
@@ -41,6 +41,8 @@
 #include <rdma/ib_umem.h>
 #include <rdma/ib_umem_odp.h>
 
+#if IS_ENABLED(CONFIG_INFINIBAND_ON_DEMAND_PAGING_HMM)
+#else /* CONFIG_INFINIBAND_ON_DEMAND_PAGING_HMM */
 static void ib_umem_notifier_start_account(struct ib_umem *item)
 {
 	mutex_lock(&item->odp_data->umem_mutex);
@@ -667,3 +669,4 @@ void ib_umem_odp_unmap_dma_pages(struct ib_umem *umem, u64 virt,
 	mutex_unlock(&umem->odp_data->umem_mutex);
 }
 EXPORT_SYMBOL(ib_umem_odp_unmap_dma_pages);
+#endif /* CONFIG_INFINIBAND_ON_DEMAND_PAGING_HMM */
diff --git a/drivers/infiniband/core/uverbs_cmd.c b/drivers/infiniband/core/uverbs_cmd.c
index bbb02ff..53163aa 100644
--- a/drivers/infiniband/core/uverbs_cmd.c
+++ b/drivers/infiniband/core/uverbs_cmd.c
@@ -289,9 +289,12 @@ ssize_t ib_uverbs_get_context(struct ib_uverbs_file *file,
 	struct ib_uverbs_get_context_resp resp;
 	struct ib_udata                   udata;
 	struct ib_device                 *ibdev = file->device->ib_dev;
-#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING
+#if IS_ENABLED(CONFIG_INFINIBAND_ON_DEMAND_PAGING)
+#if IS_ENABLED(CONFIG_INFINIBAND_ON_DEMAND_PAGING_HMM)
+#else /* CONFIG_INFINIBAND_ON_DEMAND_PAGING_HMM */
 	struct ib_device_attr		  dev_attr;
-#endif
+#endif /* CONFIG_INFINIBAND_ON_DEMAND_PAGING_HMM */
+#endif /* CONFIG_INFINIBAND_ON_DEMAND_PAGING */
 	struct ib_ucontext		 *ucontext;
 	struct file			 *filp;
 	int ret;
@@ -334,7 +337,9 @@ ssize_t ib_uverbs_get_context(struct ib_uverbs_file *file,
 	rcu_read_unlock();
 	ucontext->closing = 0;
 
-#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING
+#if IS_ENABLED(CONFIG_INFINIBAND_ON_DEMAND_PAGING)
+#if IS_ENABLED(CONFIG_INFINIBAND_ON_DEMAND_PAGING_HMM)
+#else /* CONFIG_INFINIBAND_ON_DEMAND_PAGING_HMM */
 	ucontext->umem_tree = RB_ROOT;
 	init_rwsem(&ucontext->umem_rwsem);
 	ucontext->odp_mrs_count = 0;
@@ -345,8 +350,8 @@ ssize_t ib_uverbs_get_context(struct ib_uverbs_file *file,
 		goto err_free;
 	if (!(dev_attr.device_cap_flags & IB_DEVICE_ON_DEMAND_PAGING))
 		ucontext->invalidate_range = NULL;
-
-#endif
+#endif /* CONFIG_INFINIBAND_ON_DEMAND_PAGING_HMM */
+#endif /* CONFIG_INFINIBAND_ON_DEMAND_PAGING */
 
 	resp.num_comp_vectors = file->device->num_comp_vectors;
 
@@ -3438,7 +3443,9 @@ int ib_uverbs_ex_query_device(struct ib_uverbs_file *file,
 	if (ucore->outlen < resp.response_length + sizeof(resp.odp_caps))
 		goto end;
 
-#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING
+#if IS_ENABLED(CONFIG_INFINIBAND_ON_DEMAND_PAGING)
+#if IS_ENABLED(CONFIG_INFINIBAND_ON_DEMAND_PAGING_HMM)
+#else /* CONFIG_INFINIBAND_ON_DEMAND_PAGING_HMM */
 	resp.odp_caps.general_caps = attr.odp_caps.general_caps;
 	resp.odp_caps.per_transport_caps.rc_odp_caps =
 		attr.odp_caps.per_transport_caps.rc_odp_caps;
@@ -3447,9 +3454,10 @@ int ib_uverbs_ex_query_device(struct ib_uverbs_file *file,
 	resp.odp_caps.per_transport_caps.ud_odp_caps =
 		attr.odp_caps.per_transport_caps.ud_odp_caps;
 	resp.odp_caps.reserved = 0;
-#else
+#endif /* CONFIG_INFINIBAND_ON_DEMAND_PAGING_HMM */
+#else /* CONFIG_INFINIBAND_ON_DEMAND_PAGING */
 	memset(&resp.odp_caps, 0, sizeof(resp.odp_caps));
-#endif
+#endif /* CONFIG_INFINIBAND_ON_DEMAND_PAGING */
 	resp.response_length += sizeof(resp.odp_caps);
 
 	if (ucore->outlen < resp.response_length + sizeof(resp.timestamp_mask))
diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c
index 085c24b..da31c70 100644
--- a/drivers/infiniband/hw/mlx5/main.c
+++ b/drivers/infiniband/hw/mlx5/main.c
@@ -293,11 +293,14 @@ static int mlx5_ib_query_device(struct ib_device *ibdev,
 					   props->max_mcast_grp;
 	props->max_map_per_fmr = INT_MAX; /* no limit in ConnectIB */
 
-#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING
+#if IS_ENABLED(CONFIG_INFINIBAND_ON_DEMAND_PAGING)
+#if IS_ENABLED(CONFIG_INFINIBAND_ON_DEMAND_PAGING_HMM)
+#else /* CONFIG_INFINIBAND_ON_DEMAND_PAGING_HMM */
 	if (MLX5_CAP_GEN(mdev, pg))
 		props->device_cap_flags |= IB_DEVICE_ON_DEMAND_PAGING;
 	props->odp_caps = dev->odp_caps;
-#endif
+#endif /* CONFIG_INFINIBAND_ON_DEMAND_PAGING_HMM */
+#endif /* CONFIG_INFINIBAND_ON_DEMAND_PAGING */
 
 	return 0;
 }
@@ -673,9 +676,11 @@ static struct ib_ucontext *mlx5_ib_alloc_ucontext(struct ib_device *ibdev,
 			goto out_count;
 	}
 
-#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING
+#if IS_ENABLED(CONFIG_INFINIBAND_ON_DEMAND_PAGING)
+#if (!IS_ENABLED(CONFIG_INFINIBAND_ON_DEMAND_PAGING_HMM))
 	context->ibucontext.invalidate_range = &mlx5_ib_invalidate_range;
-#endif
+#endif /* CONFIG_INFINIBAND_ON_DEMAND_PAGING_HMM */
+#endif /* CONFIG_INFINIBAND_ON_DEMAND_PAGING */
 
 	INIT_LIST_HEAD(&context->db_page_list);
 	mutex_init(&context->db_page_mutex);
diff --git a/drivers/infiniband/hw/mlx5/mem.c b/drivers/infiniband/hw/mlx5/mem.c
index df56b7d..19354b6 100644
--- a/drivers/infiniband/hw/mlx5/mem.c
+++ b/drivers/infiniband/hw/mlx5/mem.c
@@ -120,7 +120,7 @@ void mlx5_ib_cont_pages(struct ib_umem *umem, u64 addr, int *count, int *shift,
 	*count = i;
 }
 
-#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING
+#if IS_ENABLED(CONFIG_INFINIBAND_ON_DEMAND_PAGING)
 static u64 umem_dma_to_mtt(dma_addr_t umem_dma)
 {
 	u64 mtt_entry = umem_dma & ODP_DMA_ADDR_MASK;
@@ -132,7 +132,7 @@ static u64 umem_dma_to_mtt(dma_addr_t umem_dma)
 
 	return mtt_entry;
 }
-#endif
+#endif /* CONFIG_INFINIBAND_ON_DEMAND_PAGING */
 
 /*
  * Populate the given array with bus addresses from the umem.
@@ -162,7 +162,9 @@ void __mlx5_ib_populate_pas(struct mlx5_ib_dev *dev, struct ib_umem *umem,
 	int len;
 	struct scatterlist *sg;
 	int entry;
-#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING
+#if IS_ENABLED(CONFIG_INFINIBAND_ON_DEMAND_PAGING)
+#if IS_ENABLED(CONFIG_INFINIBAND_ON_DEMAND_PAGING_HMM)
+#else /* CONFIG_INFINIBAND_ON_DEMAND_PAGING_HMM */
 	const bool odp = umem->odp_data != NULL;
 
 	if (odp) {
@@ -176,7 +178,8 @@ void __mlx5_ib_populate_pas(struct mlx5_ib_dev *dev, struct ib_umem *umem,
 		}
 		return;
 	}
-#endif
+#endif /* CONFIG_INFINIBAND_ON_DEMAND_PAGING_HMM */
+#endif /* CONFIG_INFINIBAND_ON_DEMAND_PAGING */
 
 	i = 0;
 	for_each_sg(umem->sg_head.sgl, sg, umem->nmap, entry) {
diff --git a/drivers/infiniband/hw/mlx5/mlx5_ib.h b/drivers/infiniband/hw/mlx5/mlx5_ib.h
index 79d1e7c..28b500a 100644
--- a/drivers/infiniband/hw/mlx5/mlx5_ib.h
+++ b/drivers/infiniband/hw/mlx5/mlx5_ib.h
@@ -218,7 +218,7 @@ struct mlx5_ib_qp {
 	/* Store signature errors */
 	bool			signature_en;
 
-#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING
+#if IS_ENABLED(CONFIG_INFINIBAND_ON_DEMAND_PAGING)
 	/*
 	 * A flag that is true for QP's that are in a state that doesn't
 	 * allow page faults, and shouldn't schedule any more faults.
@@ -231,7 +231,7 @@ struct mlx5_ib_qp {
 	 */
 	spinlock_t              disable_page_faults_lock;
 	struct mlx5_ib_pfault	pagefaults[MLX5_IB_PAGEFAULT_CONTEXTS];
-#endif
+#endif /* CONFIG_INFINIBAND_ON_DEMAND_PAGING */
 };
 
 struct mlx5_ib_cq_buf {
@@ -434,14 +434,14 @@ struct mlx5_ib_dev {
 	struct mlx5_mr_cache		cache;
 	struct timer_list		delay_timer;
 	int				fill_delay;
-#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING
+#if IS_ENABLED(CONFIG_INFINIBAND_ON_DEMAND_PAGING)
 	struct ib_odp_caps	odp_caps;
 	/*
 	 * Sleepable RCU that prevents destruction of MRs while they are still
 	 * being used by a page fault handler.
 	 */
 	struct srcu_struct      mr_srcu;
-#endif
+#endif /* CONFIG_INFINIBAND_ON_DEMAND_PAGING */
 };
 
 static inline struct mlx5_ib_cq *to_mibcq(struct mlx5_core_cq *mcq)
@@ -634,7 +634,7 @@ void mlx5_umr_cq_handler(struct ib_cq *cq, void *cq_context);
 int mlx5_ib_check_mr_status(struct ib_mr *ibmr, u32 check_mask,
 			    struct ib_mr_status *mr_status);
 
-#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING
+#if IS_ENABLED(CONFIG_INFINIBAND_ON_DEMAND_PAGING)
 extern struct workqueue_struct *mlx5_ib_page_fault_wq;
 
 void mlx5_ib_internal_fill_odp_caps(struct mlx5_ib_dev *dev);
@@ -647,8 +647,12 @@ int __init mlx5_ib_odp_init(void);
 void mlx5_ib_odp_cleanup(void);
 void mlx5_ib_qp_disable_pagefaults(struct mlx5_ib_qp *qp);
 void mlx5_ib_qp_enable_pagefaults(struct mlx5_ib_qp *qp);
+
+#if IS_ENABLED(CONFIG_INFINIBAND_ON_DEMAND_PAGING_HMM)
+#else /* CONFIG_INFINIBAND_ON_DEMAND_PAGING_HMM */
 void mlx5_ib_invalidate_range(struct ib_umem *umem, unsigned long start,
 			      unsigned long end);
+#endif /* CONFIG_INFINIBAND_ON_DEMAND_PAGING_HMM */
 
 #else /* CONFIG_INFINIBAND_ON_DEMAND_PAGING */
 static inline void mlx5_ib_internal_fill_odp_caps(struct mlx5_ib_dev *dev)
diff --git a/drivers/infiniband/hw/mlx5/mr.c b/drivers/infiniband/hw/mlx5/mr.c
index 3ad371d..18893611 100644
--- a/drivers/infiniband/hw/mlx5/mr.c
+++ b/drivers/infiniband/hw/mlx5/mr.c
@@ -46,7 +46,7 @@ enum {
 };
 
 #define MLX5_UMR_ALIGN 2048
-#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING
+#if IS_ENABLED(CONFIG_INFINIBAND_ON_DEMAND_PAGING)
 static __be64 mlx5_ib_update_mtt_emergency_buffer[
 		MLX5_UMR_MTT_MIN_CHUNK_SIZE/sizeof(__be64)]
 	__aligned(MLX5_UMR_ALIGN);
@@ -59,10 +59,10 @@ static int destroy_mkey(struct mlx5_ib_dev *dev, struct mlx5_ib_mr *mr)
 {
 	int err = mlx5_core_destroy_mkey(dev->mdev, &mr->mmr);
 
-#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING
+#if IS_ENABLED(CONFIG_INFINIBAND_ON_DEMAND_PAGING)
 	/* Wait until all page fault handlers using the mr complete. */
 	synchronize_srcu(&dev->mr_srcu);
-#endif
+#endif /* CONFIG_INFINIBAND_ON_DEMAND_PAGING */
 
 	return err;
 }
@@ -843,7 +843,7 @@ free_mr:
 	return mr;
 }
 
-#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING
+#if IS_ENABLED(CONFIG_INFINIBAND_ON_DEMAND_PAGING)
 int mlx5_ib_update_mtt(struct mlx5_ib_mr *mr, u64 start_page_index, int npages,
 		       int zap, void *data)
 {
@@ -1090,7 +1090,7 @@ struct ib_mr *mlx5_ib_reg_user_mr(struct ib_pd *pd, u64 start, u64 length,
 	mr->ibmr.lkey = mr->mmr.key;
 	mr->ibmr.rkey = mr->mmr.key;
 
-#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING
+#if IS_ENABLED(CONFIG_INFINIBAND_ON_DEMAND_PAGING)
 	if (umem->odp_data) {
 		/*
 		 * This barrier prevents the compiler from moving the
@@ -1113,7 +1113,7 @@ struct ib_mr *mlx5_ib_reg_user_mr(struct ib_pd *pd, u64 start, u64 length,
 		 */
 		smp_wmb();
 	}
-#endif
+#endif /* CONFIG_INFINIBAND_ON_DEMAND_PAGING */
 
 	return &mr->ibmr;
 
@@ -1202,15 +1202,18 @@ int mlx5_ib_dereg_mr(struct ib_mr *ibmr)
 	int npages = mr->npages;
 	struct ib_umem *umem = mr->umem;
 
-#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING
+#if IS_ENABLED(CONFIG_INFINIBAND_ON_DEMAND_PAGING)
 	if (umem && umem->odp_data) {
 		/* Prevent new page faults from succeeding */
 		mr->live = 0;
 		/* Wait for all running page-fault handlers to finish. */
 		synchronize_srcu(&dev->mr_srcu);
+#if IS_ENABLED(CONFIG_INFINIBAND_ON_DEMAND_PAGING_HMM)
+#else /* CONFIG_INFINIBAND_ON_DEMAND_PAGING_HMM */
 		/* Destroy all page mappings */
 		mlx5_ib_invalidate_range(umem, ib_umem_start(umem),
 					 ib_umem_end(umem));
+#endif /* CONFIG_INFINIBAND_ON_DEMAND_PAGING_HMM */
 		/*
 		 * We kill the umem before the MR for ODP,
 		 * so that there will not be any invalidations in
@@ -1222,7 +1225,7 @@ int mlx5_ib_dereg_mr(struct ib_mr *ibmr)
 		/* Avoid double-freeing the umem. */
 		umem = NULL;
 	}
-#endif
+#endif /* CONFIG_INFINIBAND_ON_DEMAND_PAGING */
 
 	clean_mr(mr);
 
diff --git a/drivers/infiniband/hw/mlx5/odp.c b/drivers/infiniband/hw/mlx5/odp.c
index df86d05..7299542 100644
--- a/drivers/infiniband/hw/mlx5/odp.c
+++ b/drivers/infiniband/hw/mlx5/odp.c
@@ -37,12 +37,29 @@
 
 #define MAX_PREFETCH_LEN (4*1024*1024U)
 
+struct workqueue_struct *mlx5_ib_page_fault_wq;
+
+static struct mlx5_ib_mr *mlx5_ib_odp_find_mr_lkey(struct mlx5_ib_dev *dev,
+						   u32 key)
+{
+	u32 base_key = mlx5_base_mkey(key);
+	struct mlx5_core_mr *mmr = __mlx5_mr_lookup(dev->mdev, base_key);
+	struct mlx5_ib_mr *mr = container_of(mmr, struct mlx5_ib_mr, mmr);
+
+	if (!mmr || mmr->key != key || !mr->live)
+		return NULL;
+
+	return container_of(mmr, struct mlx5_ib_mr, mmr);
+}
+
+#if IS_ENABLED(CONFIG_INFINIBAND_ON_DEMAND_PAGING_HMM)
+#else /* CONFIG_INFINIBAND_ON_DEMAND_PAGING_HMM */
+
+
 /* Timeout in ms to wait for an active mmu notifier to complete when handling
  * a pagefault. */
 #define MMU_NOTIFIER_TIMEOUT 1000
 
-struct workqueue_struct *mlx5_ib_page_fault_wq;
-
 void mlx5_ib_invalidate_range(struct ib_umem *umem, unsigned long start,
 			      unsigned long end)
 {
@@ -110,60 +127,6 @@ void mlx5_ib_invalidate_range(struct ib_umem *umem, unsigned long start,
 	ib_umem_odp_unmap_dma_pages(umem, start, end);
 }
 
-void mlx5_ib_internal_fill_odp_caps(struct mlx5_ib_dev *dev)
-{
-	struct ib_odp_caps *caps = &dev->odp_caps;
-
-	memset(caps, 0, sizeof(*caps));
-
-	if (!MLX5_CAP_GEN(dev->mdev, pg))
-		return;
-
-	caps->general_caps = IB_ODP_SUPPORT;
-
-	if (MLX5_CAP_ODP(dev->mdev, ud_odp_caps.send))
-		caps->per_transport_caps.ud_odp_caps |= IB_ODP_SUPPORT_SEND;
-
-	if (MLX5_CAP_ODP(dev->mdev, rc_odp_caps.send))
-		caps->per_transport_caps.rc_odp_caps |= IB_ODP_SUPPORT_SEND;
-
-	if (MLX5_CAP_ODP(dev->mdev, rc_odp_caps.receive))
-		caps->per_transport_caps.rc_odp_caps |= IB_ODP_SUPPORT_RECV;
-
-	if (MLX5_CAP_ODP(dev->mdev, rc_odp_caps.write))
-		caps->per_transport_caps.rc_odp_caps |= IB_ODP_SUPPORT_WRITE;
-
-	if (MLX5_CAP_ODP(dev->mdev, rc_odp_caps.read))
-		caps->per_transport_caps.rc_odp_caps |= IB_ODP_SUPPORT_READ;
-
-	return;
-}
-
-static struct mlx5_ib_mr *mlx5_ib_odp_find_mr_lkey(struct mlx5_ib_dev *dev,
-						   u32 key)
-{
-	u32 base_key = mlx5_base_mkey(key);
-	struct mlx5_core_mr *mmr = __mlx5_mr_lookup(dev->mdev, base_key);
-	struct mlx5_ib_mr *mr = container_of(mmr, struct mlx5_ib_mr, mmr);
-
-	if (!mmr || mmr->key != key || !mr->live)
-		return NULL;
-
-	return container_of(mmr, struct mlx5_ib_mr, mmr);
-}
-
-static void mlx5_ib_page_fault_resume(struct mlx5_ib_qp *qp,
-				      struct mlx5_ib_pfault *pfault,
-				      int error) {
-	struct mlx5_ib_dev *dev = to_mdev(qp->ibqp.pd->device);
-	int ret = mlx5_core_page_fault_resume(dev->mdev, qp->mqp.qpn,
-					      pfault->mpfault.flags,
-					      error);
-	if (ret)
-		pr_err("Failed to resolve the page fault on QP 0x%x\n",
-		       qp->mqp.qpn);
-}
-
 /*
  * Handle a single data segment in a page-fault WQE.
  *
@@ -291,6 +254,49 @@ srcu_unlock:
 	return ret ? ret : npages;
 }
 
+
+#endif /* CONFIG_INFINIBAND_ON_DEMAND_PAGING_HMM */
+
+
+void mlx5_ib_internal_fill_odp_caps(struct mlx5_ib_dev *dev)
+{
+	struct ib_odp_caps *caps = &dev->odp_caps;
+
+	memset(caps, 0, sizeof(*caps));
+
+	if (!MLX5_CAP_GEN(dev->mdev, pg))
+		return;
+
+	caps->general_caps = IB_ODP_SUPPORT;
+
+	if (MLX5_CAP_ODP(dev->mdev, ud_odp_caps.send))
+		caps->per_transport_caps.ud_odp_caps |= IB_ODP_SUPPORT_SEND;
+
+	if (MLX5_CAP_ODP(dev->mdev, rc_odp_caps.send))
+		caps->per_transport_caps.rc_odp_caps |= IB_ODP_SUPPORT_SEND;
+
+	if (MLX5_CAP_ODP(dev->mdev, rc_odp_caps.receive))
+		caps->per_transport_caps.rc_odp_caps |= IB_ODP_SUPPORT_RECV;
+
+	if (MLX5_CAP_ODP(dev->mdev, rc_odp_caps.write))
+		caps->per_transport_caps.rc_odp_caps |= IB_ODP_SUPPORT_WRITE;
+
+	if (MLX5_CAP_ODP(dev->mdev, rc_odp_caps.read))
+		caps->per_transport_caps.rc_odp_caps |= IB_ODP_SUPPORT_READ;
+}
+
+static void mlx5_ib_page_fault_resume(struct mlx5_ib_qp *qp,
+				      struct mlx5_ib_pfault *pfault,
+				      int error) {
+	struct mlx5_ib_dev *dev = to_mdev(qp->ibqp.pd->device);
+	int ret = mlx5_core_page_fault_resume(dev->mdev, qp->mqp.qpn,
+					      pfault->mpfault.flags,
+					      error);
+	if (ret)
+		pr_err("Failed to resolve the page fault on QP 0x%x\n",
+		       qp->mqp.qpn);
+}
+
 /**
  * Parse a series of data segments for page fault handling.
  *
diff --git a/drivers/infiniband/hw/mlx5/qp.c b/drivers/infiniband/hw/mlx5/qp.c
index 203c8a4..46ed2c9 100644
--- a/drivers/infiniband/hw/mlx5/qp.c
+++ b/drivers/infiniband/hw/mlx5/qp.c
@@ -3035,13 +3035,13 @@ int mlx5_ib_query_qp(struct ib_qp *ibqp, struct ib_qp_attr *qp_attr, int qp_attr
 	int mlx5_state;
 	int err = 0;
 
-#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING
+#if IS_ENABLED(CONFIG_INFINIBAND_ON_DEMAND_PAGING)
 	/*
 	 * Wait for any outstanding page faults, in case the user frees memory
 	 * based upon this query's result.
 	 */
 	flush_workqueue(mlx5_ib_page_fault_wq);
-#endif
+#endif /* CONFIG_INFINIBAND_ON_DEMAND_PAGING */
 
 	mutex_lock(&qp->mutex);
 	outb = kzalloc(sizeof(*outb), GFP_KERNEL);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eq.c b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
index a40b96d..ec7ee90 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eq.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
@@ -281,7 +281,7 @@ static int mlx5_eq_int(struct mlx5_core_dev *dev, struct mlx5_eq *eq)
 			}
 			break;
 
-#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING
+#if IS_ENABLED(CONFIG_INFINIBAND_ON_DEMAND_PAGING)
 		case MLX5_EVENT_TYPE_PAGE_FAULT:
 			mlx5_eq_pagefault(dev, eqe);
 			break;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/qp.c b/drivers/net/ethernet/mellanox/mlx5/core/qp.c
index 8b494b5..d25b7be 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/qp.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/qp.c
@@ -88,7 +88,7 @@ void mlx5_rsc_event(struct mlx5_core_dev *dev, u32 rsn, int event_type)
 	mlx5_core_put_rsc(common);
 }
 
-#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING
+#if IS_ENABLED(CONFIG_INFINIBAND_ON_DEMAND_PAGING)
 void mlx5_eq_pagefault(struct mlx5_core_dev *dev, struct mlx5_eqe *eqe)
 {
 	struct mlx5_eqe_page_fault *pf_eqe = &eqe->data.page_fault;
@@ -175,7 +175,7 @@ void mlx5_eq_pagefault(struct mlx5_core_dev *dev, struct mlx5_eqe *eqe)
 
 	mlx5_core_put_rsc(common);
 }
-#endif
+#endif /* CONFIG_INFINIBAND_ON_DEMAND_PAGING */
 
 int mlx5_core_create_qp(struct mlx5_core_dev *dev,
 			struct mlx5_core_qp *qp,
@@ -419,7 +419,7 @@ int mlx5_core_xrcd_dealloc(struct mlx5_core_dev *dev, u32 xrcdn)
 }
 EXPORT_SYMBOL_GPL(mlx5_core_xrcd_dealloc);
 
-#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING
+#if IS_ENABLED(CONFIG_INFINIBAND_ON_DEMAND_PAGING)
 int mlx5_core_page_fault_resume(struct mlx5_core_dev *dev, u32 qpn,
 				u8 flags, int error)
 {
@@ -447,4 +447,4 @@ int mlx5_core_page_fault_resume(struct mlx5_core_dev *dev, u32 qpn,
 	return err;
 }
 EXPORT_SYMBOL_GPL(mlx5_core_page_fault_resume);
-#endif
+#endif /* CONFIG_INFINIBAND_ON_DEMAND_PAGING */
diff --git a/include/rdma/ib_umem_odp.h b/include/rdma/ib_umem_odp.h
index 3da0b16..313d7f1 100644
--- a/include/rdma/ib_umem_odp.h
+++ b/include/rdma/ib_umem_odp.h
@@ -43,6 +43,8 @@ struct umem_odp_node {
 };
 
 struct ib_umem_odp {
+#if IS_ENABLED(CONFIG_INFINIBAND_ON_DEMAND_PAGING_HMM)
+#else
 	/*
 	 * An array of the pages included in the on-demand paging umem.
 	 * Indices of pages that are currently not mapped into the device will
@@ -62,8 +64,6 @@ struct ib_umem_odp {
 	 * also protects access to the mmu notifier counters.
 	 */
 	struct mutex		umem_mutex;
-	void			*private; /* for the HW driver to use. */
-
 	/* When false, use the notifier counter in the ucontext struct. */
 	bool mn_counters_active;
 	int notifiers_seq;
@@ -72,21 +72,43 @@ struct ib_umem_odp {
 	/* A linked list of umems that don't have private mmu notifier
 	 * counters yet. */
 	struct list_head no_private_counters;
+	struct completion	notifier_completion;
+#endif /* CONFIG_INFINIBAND_ON_DEMAND_PAGING_HMM */
+	void			*private; /* for the HW driver to use. */
 	struct ib_umem		*umem;
 
 	/* Tree tracking */
 	struct umem_odp_node	interval_tree;
-
-	struct completion	notifier_completion;
 	int			dying;
 };
 
-#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING
+#if IS_ENABLED(CONFIG_INFINIBAND_ON_DEMAND_PAGING)
 
 int ib_umem_odp_get(struct ib_ucontext *context, struct ib_umem *umem);
 
 void ib_umem_odp_release(struct ib_umem *umem);
 
+void rbt_ib_umem_insert(struct umem_odp_node *node, struct rb_root *root);
+void rbt_ib_umem_remove(struct umem_odp_node *node, struct rb_root *root);
+typedef int (*umem_call_back)(struct ib_umem *item, u64 start, u64 end,
+			      void *cookie);
+/*
+ * Call the callback on each ib_umem in the range. Returns the logical or of
+ * the return values of the functions called.
+ */
+int rbt_ib_umem_for_each_in_range(struct rb_root *root, u64 start, u64 end,
+				  umem_call_back cb, void *cookie);
+
+struct umem_odp_node *rbt_ib_umem_iter_first(struct rb_root *root,
+					     u64 start, u64 last);
+struct umem_odp_node *rbt_ib_umem_iter_next(struct umem_odp_node *node,
+					    u64 start, u64 last);
+
+
+#if IS_ENABLED(CONFIG_INFINIBAND_ON_DEMAND_PAGING_HMM)
+#else /* CONFIG_INFINIBAND_ON_DEMAND_PAGING_HMM */
+
+
 /*
  * The lower 2 bits of the DMA address signal the R/W permissions for
  * the entry. To upgrade the permissions, provide the appropriate
@@ -106,22 +128,6 @@ int ib_umem_odp_map_dma_pages(struct ib_umem *umem, u64 start_offset, u64 bcnt,
 void ib_umem_odp_unmap_dma_pages(struct ib_umem *umem, u64 start_offset,
 				 u64 bound);
 
-void rbt_ib_umem_insert(struct umem_odp_node *node, struct rb_root *root);
-void rbt_ib_umem_remove(struct umem_odp_node *node, struct rb_root *root);
-typedef int (*umem_call_back)(struct ib_umem *item, u64 start, u64 end,
-			      void *cookie);
-/*
- * Call the callback on each ib_umem in the range. Returns the logical or of
- * the return values of the functions called.
- */
-int rbt_ib_umem_for_each_in_range(struct rb_root *root, u64 start, u64 end,
-				  umem_call_back cb, void *cookie);
-
-struct umem_odp_node *rbt_ib_umem_iter_first(struct rb_root *root,
-					     u64 start, u64 last);
-struct umem_odp_node *rbt_ib_umem_iter_next(struct umem_odp_node *node,
-					    u64 start, u64 last);
-
 static inline int ib_umem_mmu_notifier_retry(struct ib_umem *item,
 					     unsigned long mmu_seq)
 {
@@ -145,8 +151,11 @@ static inline int ib_umem_mmu_notifier_retry(struct ib_umem *item,
 	return 0;
 }
 
+
+#endif /* CONFIG_INFINIBAND_ON_DEMAND_PAGING_HMM */
 #else /* CONFIG_INFINIBAND_ON_DEMAND_PAGING */
 
+
 static inline int ib_umem_odp_get(struct ib_ucontext *context,
 				  struct ib_umem *umem)
 {
diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h
index b0f898e..9d32df11 100644
--- a/include/rdma/ib_verbs.h
+++ b/include/rdma/ib_verbs.h
@@ -1215,7 +1215,9 @@ struct ib_ucontext {
 	int			closing;
 
 	struct pid             *tgid;
-#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING
+#if IS_ENABLED(CONFIG_INFINIBAND_ON_DEMAND_PAGING)
+#if IS_ENABLED(CONFIG_INFINIBAND_ON_DEMAND_PAGING_HMM)
+#else /* CONFIG_INFINIBAND_ON_DEMAND_PAGING_HMM */
 	struct rb_root      umem_tree;
 	/*
 	 * Protects .umem_rbroot and tree, as well as odp_mrs_count and
@@ -1230,7 +1232,8 @@ struct ib_ucontext {
 	/* A list of umems that don't have private mmu notifier counters yet. */
 	struct list_head	no_private_counters;
 	int                     odp_mrs_count;
-#endif
+#endif /* CONFIG_INFINIBAND_ON_DEMAND_PAGING_HMM */
+#endif /* CONFIG_INFINIBAND_ON_DEMAND_PAGING */
 };
 
 struct ib_uobject {
-- 
1.9.3

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/

Powered by blists - more mailing lists