From 9d4949b4935831be10534d5432bf611285a572a5 Mon Sep 17 00:00:00 2001 From: Boaz Harrosh Date: Mon, 26 Feb 2018 18:50:35 +0200 Subject: dax: ->direct_access does not sleep anymore In Patch: [7a862fb] brd: remove dax support Dan Williams has removed the only might_sleep implementation of ->direct_access. So we no longer need to check for it. CC: Dan Williams Signed-off-by: Boaz Harrosh Signed-off-by: Dan Williams --- drivers/dax/super.c | 6 ------ 1 file changed, 6 deletions(-) (limited to 'drivers') diff --git a/drivers/dax/super.c b/drivers/dax/super.c index 473af694ad1c..ecdc292aa4e4 100644 --- a/drivers/dax/super.c +++ b/drivers/dax/super.c @@ -246,12 +246,6 @@ long dax_direct_access(struct dax_device *dax_dev, pgoff_t pgoff, long nr_pages, { long avail; - /* - * The device driver is allowed to sleep, in order to make the - * memory directly accessible. - */ - might_sleep(); - if (!dax_dev) return -EOPNOTSUPP; -- cgit v1.2.3 From 94db151dc89262bfa82922c44e8320cea2334667 Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Sun, 4 Feb 2018 10:34:02 -0800 Subject: vfio: disable filesystem-dax page pinning Filesystem-DAX is incompatible with 'longterm' page pinning. Without page cache indirection a DAX mapping maps filesystem blocks directly. This means that the filesystem must not modify a file's block map while any page in a mapping is pinned. In order to prevent the situation of userspace holding of filesystem operations indefinitely, disallow 'longterm' Filesystem-DAX mappings. RDMA has the same conflict and the plan there is to add a 'with lease' mechanism to allow the kernel to notify userspace that the mapping is being torn down for block-map maintenance. Perhaps something similar can be put in place for vfio. Note that xfs and ext4 still report: "DAX enabled. Warning: EXPERIMENTAL, use at your own risk" ...at mount time, and resolving the dax-dma-vs-truncate problem is one of the last hurdles to remove that designation. Acked-by: Alex Williamson Cc: Michal Hocko Cc: kvm@vger.kernel.org Cc: Reported-by: Haozhong Zhang Tested-by: Haozhong Zhang Fixes: d475c6346a38 ("dax,ext2: replace XIP read and write with DAX I/O") Reviewed-by: Christoph Hellwig Signed-off-by: Dan Williams --- drivers/vfio/vfio_iommu_type1.c | 18 +++++++++++++++--- 1 file changed, 15 insertions(+), 3 deletions(-) (limited to 'drivers') diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c index e30e29ae4819..45657e2b1ff7 100644 --- a/drivers/vfio/vfio_iommu_type1.c +++ b/drivers/vfio/vfio_iommu_type1.c @@ -338,11 +338,12 @@ static int vaddr_get_pfn(struct mm_struct *mm, unsigned long vaddr, { struct page *page[1]; struct vm_area_struct *vma; + struct vm_area_struct *vmas[1]; int ret; if (mm == current->mm) { - ret = get_user_pages_fast(vaddr, 1, !!(prot & IOMMU_WRITE), - page); + ret = get_user_pages_longterm(vaddr, 1, !!(prot & IOMMU_WRITE), + page, vmas); } else { unsigned int flags = 0; @@ -351,7 +352,18 @@ static int vaddr_get_pfn(struct mm_struct *mm, unsigned long vaddr, down_read(&mm->mmap_sem); ret = get_user_pages_remote(NULL, mm, vaddr, 1, flags, page, - NULL, NULL); + vmas, NULL); + /* + * The lifetime of a vaddr_get_pfn() page pin is + * userspace-controlled. In the fs-dax case this could + * lead to indefinite stalls in filesystem operations. + * Disallow attempts to pin fs-dax pages via this + * interface. + */ + if (ret > 0 && vma_is_fsdax(vmas[0])) { + ret = -EOPNOTSUPP; + put_page(page[0]); + } up_read(&mm->mmap_sem); } -- cgit v1.2.3 From 5fdf8e5ba5666fe153bd61f851a40078a6347822 Mon Sep 17 00:00:00 2001 From: Dave Jiang Date: Fri, 2 Mar 2018 19:31:40 -0800 Subject: libnvdimm: re-enable deep flush for pmem devices via fsync() Re-enable deep flush so that users always have a way to be sure that a write makes it all the way out to media. Writes from the PMEM driver always arrive at the NVDIMM since movnt is used to bypass the cache, and the driver relies on the ADR (Asynchronous DRAM Refresh) mechanism to flush write buffers on power failure. The Deep Flush mechanism is there to explicitly write buffers to protect against (rare) ADR failure. This change prevents a regression in deep flush behavior so that applications can continue to depend on fsync() as a mechanism to trigger deep flush in the filesystem-DAX case. Fixes: 06e8ccdab15f4 ("acpi: nfit: Add support for detect platform CPU cache...") Reviewed-by: Jeff Moyer Signed-off-by: Dave Jiang Signed-off-by: Dan Williams --- drivers/nvdimm/pmem.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'drivers') diff --git a/drivers/nvdimm/pmem.c b/drivers/nvdimm/pmem.c index 10041ac4032c..06f8dcc52ca6 100644 --- a/drivers/nvdimm/pmem.c +++ b/drivers/nvdimm/pmem.c @@ -335,8 +335,7 @@ static int pmem_attach_disk(struct device *dev, dev_warn(dev, "unable to guarantee persistence of writes\n"); fua = 0; } - wbc = nvdimm_has_cache(nd_region) && - !test_bit(ND_REGION_PERSIST_CACHE, &nd_region->flags); + wbc = nvdimm_has_cache(nd_region); if (!devm_request_mem_region(dev, res->start, resource_size(res), dev_name(&ndns->dev))) { -- cgit v1.2.3