summaryrefslogtreecommitdiff
path: root/fs/dax.c
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2018-06-09 03:21:52 +0300
committerLinus Torvalds <torvalds@linux-foundation.org>2018-06-09 03:21:52 +0300
commit7d3bf613e99abbd96ac7b90ee3694a246c975021 (patch)
tree084e4d900025ce3459702d3a8c05ead860c67c64 /fs/dax.c
parenta3818841bd5e9b4a7e0e732c19cf3a632fcb525e (diff)
parent930218affeadd1325ea17e053f0dcecf218f5a4f (diff)
downloadlinux-7d3bf613e99abbd96ac7b90ee3694a246c975021.tar.xz
Merge tag 'libnvdimm-for-4.18' of git://git.kernel.org/pub/scm/linux/kernel/git/nvdimm/nvdimm
Pull libnvdimm updates from Dan Williams: "This adds a user for the new 'bytes-remaining' updates to memcpy_mcsafe() that you already received through Ingo via the x86-dax- for-linus pull. Not included here, but still targeting this cycle, is support for handling memory media errors (poison) consumed via userspace dax mappings. Summary: - DAX broke a fundamental assumption of truncate of file mapped pages. The truncate path assumed that it is safe to disconnect a pinned page from a file and let the filesystem reclaim the physical block. With DAX the page is equivalent to the filesystem block. Introduce dax_layout_busy_page() to enable filesystems to wait for pinned DAX pages to be released. Without this wait a filesystem could allocate blocks under active device-DMA to a new file. - DAX arranges for the block layer to be bypassed and uses dax_direct_access() + copy_to_iter() to satisfy read(2) calls. However, the memcpy_mcsafe() facility is available through the pmem block driver. In order to safely handle media errors, via the DAX block-layer bypass, introduce copy_to_iter_mcsafe(). - Fix cache management policy relative to the ACPI NFIT Platform Capabilities Structure to properly elide cache flushes when they are not necessary. The table indicates whether CPU caches are power-fail protected. Clarify that a deep flush is always performed on REQ_{FUA,PREFLUSH} requests" * tag 'libnvdimm-for-4.18' of git://git.kernel.org/pub/scm/linux/kernel/git/nvdimm/nvdimm: (21 commits) dax: Use dax_write_cache* helpers libnvdimm, pmem: Do not flush power-fail protected CPU caches libnvdimm, pmem: Unconditionally deep flush on *sync libnvdimm, pmem: Complete REQ_FLUSH => REQ_PREFLUSH acpi, nfit: Remove ecc_unit_size dax: dax_insert_mapping_entry always succeeds libnvdimm, e820: Register all pmem resources libnvdimm: Debug probe times linvdimm, pmem: Preserve read-only setting for pmem devices x86, nfit_test: Add unit test for memcpy_mcsafe() pmem: Switch to copy_to_iter_mcsafe() dax: Report bytes remaining in dax_iomap_actor() dax: Introduce a ->copy_to_iter dax operation uio, lib: Fix CONFIG_ARCH_HAS_UACCESS_MCSAFE compilation xfs, dax: introduce xfs_break_dax_layouts() xfs: prepare xfs_break_layouts() for another layout type xfs: prepare xfs_break_layouts() to be called with XFS_MMAPLOCK_EXCL mm, fs, dax: handle layout changes to pinned dax mappings mm: fix __gup_device_huge vs unmap mm: introduce MEMORY_DEVICE_FS_DAX and CONFIG_DEV_PAGEMAP_OPS ...
Diffstat (limited to 'fs/dax.c')
-rw-r--r--fs/dax.c136
1 files changed, 111 insertions, 25 deletions
diff --git a/fs/dax.c b/fs/dax.c
index 08656a2f2aa6..641192808bb6 100644
--- a/fs/dax.c
+++ b/fs/dax.c
@@ -351,6 +351,19 @@ static void dax_disassociate_entry(void *entry, struct address_space *mapping,
}
}
+static struct page *dax_busy_page(void *entry)
+{
+ unsigned long pfn;
+
+ for_each_mapped_pfn(entry, pfn) {
+ struct page *page = pfn_to_page(pfn);
+
+ if (page_ref_count(page) > 1)
+ return page;
+ }
+ return NULL;
+}
+
/*
* Find radix tree entry at given index. If it points to an exceptional entry,
* return it with the radix tree entry locked. If the radix tree doesn't
@@ -492,6 +505,90 @@ restart:
return entry;
}
+/**
+ * dax_layout_busy_page - find first pinned page in @mapping
+ * @mapping: address space to scan for a page with ref count > 1
+ *
+ * DAX requires ZONE_DEVICE mapped pages. These pages are never
+ * 'onlined' to the page allocator so they are considered idle when
+ * page->count == 1. A filesystem uses this interface to determine if
+ * any page in the mapping is busy, i.e. for DMA, or other
+ * get_user_pages() usages.
+ *
+ * It is expected that the filesystem is holding locks to block the
+ * establishment of new mappings in this address_space. I.e. it expects
+ * to be able to run unmap_mapping_range() and subsequently not race
+ * mapping_mapped() becoming true.
+ */
+struct page *dax_layout_busy_page(struct address_space *mapping)
+{
+ pgoff_t indices[PAGEVEC_SIZE];
+ struct page *page = NULL;
+ struct pagevec pvec;
+ pgoff_t index, end;
+ unsigned i;
+
+ /*
+ * In the 'limited' case get_user_pages() for dax is disabled.
+ */
+ if (IS_ENABLED(CONFIG_FS_DAX_LIMITED))
+ return NULL;
+
+ if (!dax_mapping(mapping) || !mapping_mapped(mapping))
+ return NULL;
+
+ pagevec_init(&pvec);
+ index = 0;
+ end = -1;
+
+ /*
+ * If we race get_user_pages_fast() here either we'll see the
+ * elevated page count in the pagevec_lookup and wait, or
+ * get_user_pages_fast() will see that the page it took a reference
+ * against is no longer mapped in the page tables and bail to the
+ * get_user_pages() slow path. The slow path is protected by
+ * pte_lock() and pmd_lock(). New references are not taken without
+ * holding those locks, and unmap_mapping_range() will not zero the
+ * pte or pmd without holding the respective lock, so we are
+ * guaranteed to either see new references or prevent new
+ * references from being established.
+ */
+ unmap_mapping_range(mapping, 0, 0, 1);
+
+ while (index < end && pagevec_lookup_entries(&pvec, mapping, index,
+ min(end - index, (pgoff_t)PAGEVEC_SIZE),
+ indices)) {
+ for (i = 0; i < pagevec_count(&pvec); i++) {
+ struct page *pvec_ent = pvec.pages[i];
+ void *entry;
+
+ index = indices[i];
+ if (index >= end)
+ break;
+
+ if (!radix_tree_exceptional_entry(pvec_ent))
+ continue;
+
+ xa_lock_irq(&mapping->i_pages);
+ entry = get_unlocked_mapping_entry(mapping, index, NULL);
+ if (entry)
+ page = dax_busy_page(entry);
+ put_unlocked_mapping_entry(mapping, index, entry);
+ xa_unlock_irq(&mapping->i_pages);
+ if (page)
+ break;
+ }
+ pagevec_remove_exceptionals(&pvec);
+ pagevec_release(&pvec);
+ index++;
+
+ if (page)
+ break;
+ }
+ return page;
+}
+EXPORT_SYMBOL_GPL(dax_layout_busy_page);
+
static int __dax_invalidate_mapping_entry(struct address_space *mapping,
pgoff_t index, bool trunc)
{
@@ -912,7 +1009,6 @@ static vm_fault_t dax_load_hole(struct address_space *mapping, void *entry,
unsigned long vaddr = vmf->address;
vm_fault_t ret = VM_FAULT_NOPAGE;
struct page *zero_page;
- void *entry2;
pfn_t pfn;
zero_page = ZERO_PAGE(0);
@@ -922,13 +1018,8 @@ static vm_fault_t dax_load_hole(struct address_space *mapping, void *entry,
}
pfn = page_to_pfn_t(zero_page);
- entry2 = dax_insert_mapping_entry(mapping, vmf, entry, pfn,
- RADIX_DAX_ZERO_PAGE, false);
- if (IS_ERR(entry2)) {
- ret = VM_FAULT_SIGBUS;
- goto out;
- }
-
+ dax_insert_mapping_entry(mapping, vmf, entry, pfn, RADIX_DAX_ZERO_PAGE,
+ false);
ret = vmf_insert_mixed(vmf->vma, vaddr, pfn);
out:
trace_dax_load_hole(inode, vmf, ret);
@@ -991,6 +1082,7 @@ dax_iomap_actor(struct inode *inode, loff_t pos, loff_t length, void *data,
struct iov_iter *iter = data;
loff_t end = pos + length, done = 0;
ssize_t ret = 0;
+ size_t xfer;
int id;
if (iov_iter_rw(iter) == READ) {
@@ -1054,18 +1146,20 @@ dax_iomap_actor(struct inode *inode, loff_t pos, loff_t length, void *data,
* vfs_write(), depending on which operation we are doing.
*/
if (iov_iter_rw(iter) == WRITE)
- map_len = dax_copy_from_iter(dax_dev, pgoff, kaddr,
+ xfer = dax_copy_from_iter(dax_dev, pgoff, kaddr,
map_len, iter);
else
- map_len = copy_to_iter(kaddr, map_len, iter);
- if (map_len <= 0) {
- ret = map_len ? map_len : -EFAULT;
- break;
- }
+ xfer = dax_copy_to_iter(dax_dev, pgoff, kaddr,
+ map_len, iter);
- pos += map_len;
- length -= map_len;
- done += map_len;
+ pos += xfer;
+ length -= xfer;
+ done += xfer;
+
+ if (xfer == 0)
+ ret = -EFAULT;
+ if (xfer < map_len)
+ break;
}
dax_read_unlock(id);
@@ -1240,10 +1334,6 @@ static vm_fault_t dax_iomap_pte_fault(struct vm_fault *vmf, pfn_t *pfnp,
entry = dax_insert_mapping_entry(mapping, vmf, entry, pfn,
0, write && !sync);
- if (IS_ERR(entry)) {
- error = PTR_ERR(entry);
- goto error_finish_iomap;
- }
/*
* If we are doing synchronous page fault and inode needs fsync,
@@ -1324,8 +1414,6 @@ static vm_fault_t dax_pmd_load_hole(struct vm_fault *vmf, struct iomap *iomap,
pfn = page_to_pfn_t(zero_page);
ret = dax_insert_mapping_entry(mapping, vmf, entry, pfn,
RADIX_DAX_PMD | RADIX_DAX_ZERO_PAGE, false);
- if (IS_ERR(ret))
- goto fallback;
ptl = pmd_lock(vmf->vma->vm_mm, vmf->pmd);
if (!pmd_none(*(vmf->pmd))) {
@@ -1447,8 +1535,6 @@ static vm_fault_t dax_iomap_pmd_fault(struct vm_fault *vmf, pfn_t *pfnp,
entry = dax_insert_mapping_entry(mapping, vmf, entry, pfn,
RADIX_DAX_PMD, write && !sync);
- if (IS_ERR(entry))
- goto finish_iomap;
/*
* If we are doing synchronous page fault and inode needs fsync,