RDMA/mlx4: Use rdma_user_mmap_io (c282da41) · Commits · EulixOS / Software / Kernel

drivers/infiniband/hw/mlx4/main.c

+24 −118

Original line number	Diff line number	Diff line
		@@ -1138,144 +1138,50 @@ static int mlx4_ib_dealloc_ucontext(struct ib_ucontext *ibcontext)
		return 0;
		}

		static void mlx4_ib_vma_open(struct vm_area_struct *area)
		{
		/* vma_open is called when a new VMA is created on top of our VMA.
		* This is done through either mremap flow or split_vma (usually due
		* to mlock, madvise, munmap, etc.). We do not support a clone of the
		* vma, as this VMA is strongly hardware related. Therefore we set the
		* vm_ops of the newly created/cloned VMA to NULL, to prevent it from
		* calling us again and trying to do incorrect actions. We assume that
		* the original vma size is exactly a single page that there will be no
		* "splitting" operations on.
		*/
		area->vm_ops = NULL;
		}

		static void mlx4_ib_vma_close(struct vm_area_struct *area)
		{
		struct mlx4_ib_vma_private_data *mlx4_ib_vma_priv_data;

		/* It's guaranteed that all VMAs opened on a FD are closed before the
		* file itself is closed, therefore no sync is needed with the regular
		* closing flow. (e.g. mlx4_ib_dealloc_ucontext) However need a sync
		* with accessing the vma as part of mlx4_ib_disassociate_ucontext.
		* The close operation is usually called under mm->mmap_sem except when
		* process is exiting. The exiting case is handled explicitly as part
		* of mlx4_ib_disassociate_ucontext.
		*/
		mlx4_ib_vma_priv_data = (struct mlx4_ib_vma_private_data *)
		area->vm_private_data;

		/* set the vma context pointer to null in the mlx4_ib driver's private
		* data to protect against a race condition in mlx4_ib_dissassociate_ucontext().
		*/
		mlx4_ib_vma_priv_data->vma = NULL;
		}

		static const struct vm_operations_struct mlx4_ib_vm_ops = {
		.open = mlx4_ib_vma_open,
		.close = mlx4_ib_vma_close
		};

		static void mlx4_ib_disassociate_ucontext(struct ib_ucontext *ibcontext)
		{
		int i;
		struct vm_area_struct *vma;
		struct mlx4_ib_ucontext *context = to_mucontext(ibcontext);

		/* need to protect from a race on closing the vma as part of
		* mlx4_ib_vma_close().
		*/
		for (i = 0; i < HW_BAR_COUNT; i++) {
		vma = context->hw_bar_info[i].vma;
		if (!vma)
		continue;

		zap_vma_ptes(context->hw_bar_info[i].vma,
		context->hw_bar_info[i].vma->vm_start, PAGE_SIZE);

		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;
		}
		}

		static void mlx4_ib_set_vma_data(struct vm_area_struct *vma,
		struct mlx4_ib_vma_private_data *vma_private_data)
		{
		vma_private_data->vma = vma;
		vma->vm_private_data = vma_private_data;
		vma->vm_ops = &mlx4_ib_vm_ops;
		}

		static int mlx4_ib_mmap(struct ib_ucontext context, struct vm_area_struct vma)
		{
		struct mlx4_ib_dev *dev = to_mdev(context->device);
		struct mlx4_ib_ucontext *mucontext = to_mucontext(context);

		if (vma->vm_end - vma->vm_start != PAGE_SIZE)
		return -EINVAL;

		if (vma->vm_pgoff == 0) {
		/* We prevent double mmaping on same context */
		if (mucontext->hw_bar_info[HW_BAR_DB].vma)
		return -EINVAL;

		vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);

		if (io_remap_pfn_range(vma, vma->vm_start,
		switch (vma->vm_pgoff) {
		case 0:
		return rdma_user_mmap_io(context, vma,
		to_mucontext(context)->uar.pfn,
		PAGE_SIZE, vma->vm_page_prot))
		return -EAGAIN;

		mlx4_ib_set_vma_data(vma, &mucontext->hw_bar_info[HW_BAR_DB]);
		PAGE_SIZE,
		pgprot_noncached(vma->vm_page_prot));

		} else if (vma->vm_pgoff == 1 && dev->dev->caps.bf_reg_size != 0) {
		/* We prevent double mmaping on same context */
		if (mucontext->hw_bar_info[HW_BAR_BF].vma)
		case 1:
		if (dev->dev->caps.bf_reg_size == 0)
		return -EINVAL;

		vma->vm_page_prot = pgprot_writecombine(vma->vm_page_prot);

		if (io_remap_pfn_range(vma, vma->vm_start,
		return rdma_user_mmap_io(
		context, vma,
		to_mucontext(context)->uar.pfn +
		dev->dev->caps.num_uars,
		PAGE_SIZE, vma->vm_page_prot))
		return -EAGAIN;

		mlx4_ib_set_vma_data(vma, &mucontext->hw_bar_info[HW_BAR_BF]);
		PAGE_SIZE, pgprot_writecombine(vma->vm_page_prot));

		} else if (vma->vm_pgoff == 3) {
		case 3: {
		struct mlx4_clock_params params;
		int ret;

		/* We prevent double mmaping on same context */
		if (mucontext->hw_bar_info[HW_BAR_CLOCK].vma)
		return -EINVAL;

		ret = mlx4_get_internal_clock_params(dev->dev, &params);

		if (ret)
		return ret;

		vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);
		if (io_remap_pfn_range(vma, vma->vm_start,
		return rdma_user_mmap_io(
		context, vma,
		(pci_resource_start(dev->dev->persist->pdev,
		params.bar) +
		params.offset)
		>> PAGE_SHIFT,
		PAGE_SIZE, vma->vm_page_prot))
		return -EAGAIN;
		params.offset) >>
		PAGE_SHIFT,
		PAGE_SIZE, pgprot_noncached(vma->vm_page_prot));
		}

		mlx4_ib_set_vma_data(vma,
		&mucontext->hw_bar_info[HW_BAR_CLOCK]);
		} else {
		default:
		return -EINVAL;
		}

		return 0;
		}

		static struct ib_pd mlx4_ib_alloc_pd(struct ib_device ibdev,

drivers/infiniband/hw/mlx4/mlx4_ib.h

+0 −5

Original line number	Diff line number	Diff line
		@@ -80,16 +80,11 @@ enum hw_bar_type {
		HW_BAR_COUNT
		};

		struct mlx4_ib_vma_private_data {
		struct vm_area_struct *vma;
		};

		struct mlx4_ib_ucontext {
		struct ib_ucontext ibucontext;
		struct mlx4_uar uar;
		struct list_head db_page_list;
		struct mutex db_page_mutex;
		struct mlx4_ib_vma_private_data hw_bar_info[HW_BAR_COUNT];
		struct list_head wqn_ranges_list;
		struct mutex wqn_ranges_mutex; /* protect wqn_ranges_list */
		};