aboutsummaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
authorToshi Kani <toshi.kani@hpe.com>2016-10-07 16:59:56 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2016-10-07 18:46:28 -0700
commit74d2fad1334d12bac8fe017aba598dd66c86628b (patch)
tree9bf86d14a36fcab915619dfba1c9fe8d830cff90
parent26b4224d99615a19c002508c6e80bd3d1d783b64 (diff)
downloadlinux-futex-74d2fad1334d12bac8fe017aba598dd66c86628b.tar.gz
thp, dax: add thp_get_unmapped_area for pmd mappings
When CONFIG_FS_DAX_PMD is set, DAX supports mmap() using pmd page size. This feature relies on both mmap virtual address and FS block (i.e. physical address) to be aligned by the pmd page size. Users can use mkfs options to specify FS to align block allocations. However, aligning mmap address requires code changes to existing applications for providing a pmd-aligned address to mmap(). For instance, fio with "ioengine=mmap" performs I/Os with mmap() [1]. It calls mmap() with a NULL address, which needs to be changed to provide a pmd-aligned address for testing with DAX pmd mappings. Changing all applications that call mmap() with NULL is undesirable. Add thp_get_unmapped_area(), which can be called by filesystem's get_unmapped_area to align an mmap address by the pmd size for a DAX file. It calls the default handler, mm->get_unmapped_area(), to find a range and then aligns it for a DAX file. The patch is based on Matthew Wilcox's change that allows adding support of the pud page size easily. [1]: https://github.com/axboe/fio/blob/master/engines/mmap.c Link: http://lkml.kernel.org/r/1472497881-9323-2-git-send-email-toshi.kani@hpe.com Signed-off-by: Toshi Kani <toshi.kani@hpe.com> Reviewed-by: Dan Williams <dan.j.williams@intel.com> Cc: Matthew Wilcox <mawilcox@microsoft.com> Cc: Ross Zwisler <ross.zwisler@linux.intel.com> Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Dave Chinner <david@fromorbit.com> Cc: Jan Kara <jack@suse.cz> Cc: Theodore Ts'o <tytso@mit.edu> Cc: Andreas Dilger <adilger.kernel@dilger.ca> Cc: Mike Kravetz <mike.kravetz@oracle.com> Cc: "Kirill A. Shutemov" <kirill@shutemov.name> Cc: Hugh Dickins <hughd@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
-rw-r--r--include/linux/huge_mm.h7
-rw-r--r--mm/huge_memory.c43
2 files changed, 50 insertions, 0 deletions
diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h
index 6f14de45b5ce08..4fca5263fd4253 100644
--- a/include/linux/huge_mm.h
+++ b/include/linux/huge_mm.h
@@ -87,6 +87,10 @@ extern bool is_vma_temporary_stack(struct vm_area_struct *vma);
extern unsigned long transparent_hugepage_flags;
+extern unsigned long thp_get_unmapped_area(struct file *filp,
+ unsigned long addr, unsigned long len, unsigned long pgoff,
+ unsigned long flags);
+
extern void prep_transhuge_page(struct page *page);
extern void free_transhuge_page(struct page *page);
@@ -169,6 +173,9 @@ void put_huge_zero_page(void);
static inline void prep_transhuge_page(struct page *page) {}
#define transparent_hugepage_flags 0UL
+
+#define thp_get_unmapped_area NULL
+
static inline int
split_huge_page_to_list(struct page *page, struct list_head *list)
{
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 283583fcb1e7af..a0b0e562407dfe 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -469,6 +469,49 @@ void prep_transhuge_page(struct page *page)
set_compound_page_dtor(page, TRANSHUGE_PAGE_DTOR);
}
+unsigned long __thp_get_unmapped_area(struct file *filp, unsigned long len,
+ loff_t off, unsigned long flags, unsigned long size)
+{
+ unsigned long addr;
+ loff_t off_end = off + len;
+ loff_t off_align = round_up(off, size);
+ unsigned long len_pad;
+
+ if (off_end <= off_align || (off_end - off_align) < size)
+ return 0;
+
+ len_pad = len + size;
+ if (len_pad < len || (off + len_pad) < off)
+ return 0;
+
+ addr = current->mm->get_unmapped_area(filp, 0, len_pad,
+ off >> PAGE_SHIFT, flags);
+ if (IS_ERR_VALUE(addr))
+ return 0;
+
+ addr += (off - addr) & (size - 1);
+ return addr;
+}
+
+unsigned long thp_get_unmapped_area(struct file *filp, unsigned long addr,
+ unsigned long len, unsigned long pgoff, unsigned long flags)
+{
+ loff_t off = (loff_t)pgoff << PAGE_SHIFT;
+
+ if (addr)
+ goto out;
+ if (!IS_DAX(filp->f_mapping->host) || !IS_ENABLED(CONFIG_FS_DAX_PMD))
+ goto out;
+
+ addr = __thp_get_unmapped_area(filp, len, off, flags, PMD_SIZE);
+ if (addr)
+ return addr;
+
+ out:
+ return current->mm->get_unmapped_area(filp, addr, len, pgoff, flags);
+}
+EXPORT_SYMBOL_GPL(thp_get_unmapped_area);
+
static int __do_huge_pmd_anonymous_page(struct fault_env *fe, struct page *page,
gfp_t gfp)
{