The patch titled
Subject: dax: support for transparent PUD pages
has been added to the -mm tree. Its filename is
dax-support-for-transparent-pud-pages.patch
This patch should soon appear at
http://ozlabs.org/~akpm/mmots/broken-out/dax-support-for-transparent-pud-pages.patch
and later at
http://ozlabs.org/~akpm/mmotm/broken-out/dax-support-for-transparent-pud-pages.patch
Before you just go and hit "reply", please:
a) Consider who else should be cc'ed
b) Prefer to cc a suitable mailing list as well
c) Ideally: find the original patch on the mailing list and do a
reply-to-all to that, adding suitable additional cc's
*** Remember to use Documentation/SubmitChecklist when testing your code ***
The -mm tree is included into linux-next and is updated
there every 3-4 working days
------------------------------------------------------
From: Matthew Wilcox <willy@xxxxxxxxxxxxxxx>
Subject: dax: support for transparent PUD pages
The DAX support for transparent huge PUD pages
Signed-off-by: Matthew Wilcox <willy@xxxxxxxxxxxxxxx>
Cc: Kirill A. Shutemov <kirill.shutemov@xxxxxxxxxxxxxxx>
Cc: Dave Chinner <david@xxxxxxxxxxxxx>
Cc: "Darrick J. Wong" <darrick.wong@xxxxxxxxxx>
Cc: mingming cao <mingming.cao@xxxxxxxxxx>
Cc: David Rientjes <rientjes@xxxxxxxxxx>
Cc: Ingo Molnar <mingo@xxxxxxx>
Cc: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
Cc: "H. Peter Anvin" <hpa@xxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
fs/dax.c | 175 +++++++++++++++++++++++++++++++++++++++++++++++++++++
1 file changed, 175 insertions(+)
diff -puN fs/dax.c~dax-support-for-transparent-pud-pages fs/dax.c
--- a/fs/dax.c~dax-support-for-transparent-pud-pages
+++ a/fs/dax.c
@@ -959,6 +959,178 @@ static int dax_pmd_fault(struct vm_area_
}
#endif /* !CONFIG_TRANSPARENT_HUGEPAGE */
+#ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD
+/*
+ * The 'colour' (ie low bits) within a PUD of a page offset. This comes up
+ * more often than one might expect in the below function.
+ */
+#define PG_PUD_COLOUR ((PUD_SIZE >> PAGE_SHIFT) - 1)
+
+#define dax_pud_dbg(bh, address, reason) __dax_dbg(bh, address, reason, "dax_pud")
+
+static int dax_pud_fault(struct vm_area_struct *vma, unsigned long address,
+ pud_t *pud, unsigned int flags, get_block_t get_block,
+ dax_iodone_t complete_unwritten)
+{
+ struct file *file = vma->vm_file;
+ struct address_space *mapping = file->f_mapping;
+ struct inode *inode = mapping->host;
+ struct buffer_head bh;
+ unsigned blkbits = inode->i_blkbits;
+ unsigned long pud_addr = address & PUD_MASK;
+ bool write = flags & FAULT_FLAG_WRITE;
+ struct block_device *bdev = NULL;
+ pgoff_t size, pgoff;
+ sector_t block;
+ int result = 0;
+
+ /* dax pud mappings require pfn_t_devmap() */
+ if (!IS_ENABLED(CONFIG_FS_DAX_PMD))
+ return VM_FAULT_FALLBACK;
+
+ /* Fall back to PTEs if we're going to COW */
+ if (write && !(vma->vm_flags & VM_SHARED)) {
+ split_huge_pud(vma, pud, address);
+ dax_pud_dbg(NULL, address, "cow write");
+ return VM_FAULT_FALLBACK;
+ }
+ /* If the PUD would extend outside the VMA */
+ if (pud_addr < vma->vm_start) {
+ dax_pud_dbg(NULL, address, "vma start unaligned");
+ return VM_FAULT_FALLBACK;
+ }
+ if ((pud_addr + PUD_SIZE) > vma->vm_end) {
+ dax_pud_dbg(NULL, address, "vma end unaligned");
+ return VM_FAULT_FALLBACK;
+ }
+
+ pgoff = linear_page_index(vma, pud_addr);
+ size = (i_size_read(inode) + PAGE_SIZE - 1) >> PAGE_SHIFT;
+ if (pgoff >= size)
+ return VM_FAULT_SIGBUS;
+ /* If the PUD would cover blocks out of the file */
+ if ((pgoff | PG_PUD_COLOUR) >= size) {
+ dax_pud_dbg(NULL, address,
+ "offset + huge page size > file size");
+ return VM_FAULT_FALLBACK;
+ }
+
+ memset(&bh, 0, sizeof(bh));
+ block = (sector_t)pgoff << (PAGE_SHIFT - blkbits);
+
+ bh.b_size = PUD_SIZE;
+ if (get_block(inode, block, &bh, write) != 0)
+ return VM_FAULT_SIGBUS;
+ bdev = bh.b_bdev;
+ i_mmap_lock_read(mapping);
+
+ /*
+ * If the filesystem isn't willing to tell us the length of a hole,
+ * just fall back to PTEs. Calling get_block 512 times in a loop
+ * would be silly.
+ */
+ if (!buffer_size_valid(&bh) || bh.b_size < PUD_SIZE) {
+ dax_pud_dbg(&bh, address, "allocated block too small");
+ goto fallback;
+ }
+
+ /*
+ * If we allocated new storage, make sure no process has any
+ * zero pages covering this hole
+ */
+ if (buffer_new(&bh)) {
+ i_mmap_unlock_read(mapping);
+ unmap_mapping_range(mapping, pgoff << PAGE_SHIFT, PUD_SIZE, 0);
+ i_mmap_lock_read(mapping);
+ }
+
+ /*
+ * If a truncate happened while we were allocating blocks, we may
+ * leave blocks allocated to the file that are beyond EOF. We can't
+ * take i_mutex here, so just leave them hanging; they'll be freed
+ * when the file is deleted.
+ */
+ size = (i_size_read(inode) + PAGE_SIZE - 1) >> PAGE_SHIFT;
+ if (pgoff >= size) {
+ result = VM_FAULT_SIGBUS;
+ goto out;
+ }
+ if ((pgoff | PG_PUD_COLOUR) >= size) {
+ dax_pud_dbg(&bh, address, "pgoff unaligned");
+ goto fallback;
+ }
+
+ if (!write && !buffer_mapped(&bh) && buffer_uptodate(&bh)) {
+ dax_pud_dbg(&bh, address, "no zero page");
+ goto fallback;
+ } else {
+ struct blk_dax_ctl dax = {
+ .sector = to_sector(&bh, inode),
+ .size = PUD_SIZE,
+ };
+ long length = dax_map_atomic(bdev, &dax);
+
+ if (length < 0) {
+ result = VM_FAULT_SIGBUS;
+ goto out;
+ }
+ if (length < PUD_SIZE) {
+ dax_pud_dbg(&bh, address, "dax-length too small");
+ dax_unmap_atomic(bdev, &dax);
+ goto fallback;
+ }
+ if (pfn_t_to_pfn(dax.pfn) & PG_PUD_COLOUR) {
+ dax_pud_dbg(&bh, address, "pfn unaligned");
+ dax_unmap_atomic(bdev, &dax);
+ goto fallback;
+ }
+
+ if (!pfn_t_devmap(dax.pfn)) {
+ dax_unmap_atomic(bdev, &dax);
+ dax_pud_dbg(&bh, address, "pfn not in memmap");
+ goto fallback;
+ }
+
+ if (buffer_unwritten(&bh) || buffer_new(&bh)) {
+ clear_pmem(dax.addr, PUD_SIZE);
+ wmb_pmem();
+ count_vm_event(PGMAJFAULT);
+ mem_cgroup_count_vm_event(vma->vm_mm, PGMAJFAULT);
+ result |= VM_FAULT_MAJOR;
+ }
+ dax_unmap_atomic(bdev, &dax);
+
+ dev_dbg(part_to_dev(bdev->bd_part),
+ "%s: %s addr: %lx pfn: %lx sect: %llx\n",
+ __func__, current->comm, address,
+ pfn_t_to_pfn(dax.pfn),
+ (unsigned long long) dax.sector);
+ result |= vmf_insert_pfn_pud(vma, address, pud,
+ dax.pfn, write);
+ }
+
+ out:
+ i_mmap_unlock_read(mapping);
+
+ if (buffer_unwritten(&bh))
+ complete_unwritten(&bh, !(result & VM_FAULT_ERROR));
+
+ return result;
+
+ fallback:
+ count_vm_event(THP_FAULT_FALLBACK);
+ result = VM_FAULT_FALLBACK;
+ goto out;
+}
+#else /* !CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD */
+static int dax_pud_fault(struct vm_area_struct *vma, unsigned long address,
+ pud_t *pud, unsigned int flags, get_block_t get_block,
+ dax_iodone_t complete_unwritten)
+{
+ return VM_FAULT_FALLBACK;
+}
+#endif /* !CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD */
+
/**
* dax_fault - handle a page fault on a DAX file
* @vma: The virtual memory area where the fault occurred
@@ -985,6 +1157,9 @@ int dax_fault(struct vm_area_struct *vma
case FAULT_FLAG_SIZE_PMD:
return dax_pmd_fault(vma, address, vmf->pmd, vmf->flags,
get_block, iodone);
+ case FAULT_FLAG_SIZE_PUD:
+ return dax_pud_fault(vma, address, vmf->pud, vmf->flags,
+ get_block, iodone);
default:
return VM_FAULT_FALLBACK;
}
_
Patches currently in -mm which might be from willy@xxxxxxxxxxxxxxx are
mm-convert-an-open-coded-vm_bug_on_vma.patch
mmfsdax-change-pmd_fault-to-huge_fault.patch
mm-add-support-for-pud-sized-transparent-hugepages.patch
mincore-add-support-for-puds.patch
procfs-add-support-for-puds-to-smaps-clear_refs-and-pagemap.patch
x86-add-support-for-pud-sized-transparent-hugepages.patch
dax-support-for-transparent-pud-pages.patch
ext4-support-for-pud-sized-transparent-huge-pages.patch
radix-tree-add-an-explicit-include-of-bitopsh.patch
radix-tree-test-harness.patch
radix_tree-tag-all-internal-tree-nodes-as-indirect-pointers.patch
radix_tree-loop-based-on-shift-count-not-height.patch
radix_tree-add-support-for-multi-order-entries.patch
radix_tree-add-radix_tree_dump.patch
--
To unsubscribe from this list: send the line "unsubscribe mm-commits" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
