This is a note to let you know that I've just added the patch titled
iov_iter: Introduce fault_in_iov_iter_writeable
to the 5.15-stable tree which can be found at:
http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=summary
The filename of the patch is:
iov_iter-introduce-fault_in_iov_iter_writeable.patch
and it can be found in the queue-5.15 subdirectory.
If you, or anyone else, feels it should not be added to the stable tree,
please let <stable@xxxxxxxxxxxxxxx> know about it.
>From foo@baz Fri Apr 29 11:07:48 AM CEST 2022
From: Anand Jain <anand.jain@xxxxxxxxxx>
Date: Fri, 15 Apr 2022 06:28:41 +0800
Subject: iov_iter: Introduce fault_in_iov_iter_writeable
To: stable@xxxxxxxxxxxxxxx
Cc: linux-btrfs@xxxxxxxxxxxxxxx, Andreas Gruenbacher <agruenba@xxxxxxxxxx>, Anand Jain <anand.jain@xxxxxxxxxx>
Message-ID: <8181618a0badc14fd9bbe13e26164bc601c59df9.1649951733.git.anand.jain@xxxxxxxxxx>
From: Andreas Gruenbacher <agruenba@xxxxxxxxxx>
commit cdd591fc86e38ad3899196066219fbbd845f3162 upstream
Introduce a new fault_in_iov_iter_writeable helper for safely faulting
in an iterator for writing. Uses get_user_pages() to fault in the pages
without actually writing to them, which would be destructive.
We'll use fault_in_iov_iter_writeable in gfs2 once we've determined that
the iterator passed to .read_iter isn't in memory.
Signed-off-by: Andreas Gruenbacher <agruenba@xxxxxxxxxx>
Signed-off-by: Anand Jain <anand.jain@xxxxxxxxxx>
Signed-off-by: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx>
---
include/linux/pagemap.h | 1
include/linux/uio.h | 1
lib/iov_iter.c | 39 +++++++++++++++++++++++++++++
mm/gup.c | 63 ++++++++++++++++++++++++++++++++++++++++++++++++
4 files changed, 104 insertions(+)
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -736,6 +736,7 @@ extern void add_page_wait_queue(struct p
* Fault in userspace address range.
*/
size_t fault_in_writeable(char __user *uaddr, size_t size);
+size_t fault_in_safe_writeable(const char __user *uaddr, size_t size);
size_t fault_in_readable(const char __user *uaddr, size_t size);
int add_to_page_cache_locked(struct page *page, struct address_space *mapping,
--- a/include/linux/uio.h
+++ b/include/linux/uio.h
@@ -134,6 +134,7 @@ size_t copy_page_from_iter_atomic(struct
void iov_iter_advance(struct iov_iter *i, size_t bytes);
void iov_iter_revert(struct iov_iter *i, size_t bytes);
size_t fault_in_iov_iter_readable(const struct iov_iter *i, size_t bytes);
+size_t fault_in_iov_iter_writeable(const struct iov_iter *i, size_t bytes);
size_t iov_iter_single_seg_count(const struct iov_iter *i);
size_t copy_page_to_iter(struct page *page, size_t offset, size_t bytes,
struct iov_iter *i);
--- a/lib/iov_iter.c
+++ b/lib/iov_iter.c
@@ -468,6 +468,45 @@ size_t fault_in_iov_iter_readable(const
}
EXPORT_SYMBOL(fault_in_iov_iter_readable);
+/*
+ * fault_in_iov_iter_writeable - fault in iov iterator for writing
+ * @i: iterator
+ * @size: maximum length
+ *
+ * Faults in the iterator using get_user_pages(), i.e., without triggering
+ * hardware page faults. This is primarily useful when we already know that
+ * some or all of the pages in @i aren't in memory.
+ *
+ * Returns the number of bytes not faulted in, like copy_to_user() and
+ * copy_from_user().
+ *
+ * Always returns 0 for non-user-space iterators.
+ */
+size_t fault_in_iov_iter_writeable(const struct iov_iter *i, size_t size)
+{
+ if (iter_is_iovec(i)) {
+ size_t count = min(size, iov_iter_count(i));
+ const struct iovec *p;
+ size_t skip;
+
+ size -= count;
+ for (p = i->iov, skip = i->iov_offset; count; p++, skip = 0) {
+ size_t len = min(count, p->iov_len - skip);
+ size_t ret;
+
+ if (unlikely(!len))
+ continue;
+ ret = fault_in_safe_writeable(p->iov_base + skip, len);
+ count -= len - ret;
+ if (ret)
+ break;
+ }
+ return count + size;
+ }
+ return 0;
+}
+EXPORT_SYMBOL(fault_in_iov_iter_writeable);
+
void iov_iter_init(struct iov_iter *i, unsigned int direction,
const struct iovec *iov, unsigned long nr_segs,
size_t count)
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -1716,6 +1716,69 @@ out:
}
EXPORT_SYMBOL(fault_in_writeable);
+/*
+ * fault_in_safe_writeable - fault in an address range for writing
+ * @uaddr: start of address range
+ * @size: length of address range
+ *
+ * Faults in an address range using get_user_pages, i.e., without triggering
+ * hardware page faults. This is primarily useful when we already know that
+ * some or all of the pages in the address range aren't in memory.
+ *
+ * Other than fault_in_writeable(), this function is non-destructive.
+ *
+ * Note that we don't pin or otherwise hold the pages referenced that we fault
+ * in. There's no guarantee that they'll stay in memory for any duration of
+ * time.
+ *
+ * Returns the number of bytes not faulted in, like copy_to_user() and
+ * copy_from_user().
+ */
+size_t fault_in_safe_writeable(const char __user *uaddr, size_t size)
+{
+ unsigned long start = (unsigned long)untagged_addr(uaddr);
+ unsigned long end, nstart, nend;
+ struct mm_struct *mm = current->mm;
+ struct vm_area_struct *vma = NULL;
+ int locked = 0;
+
+ nstart = start & PAGE_MASK;
+ end = PAGE_ALIGN(start + size);
+ if (end < nstart)
+ end = 0;
+ for (; nstart != end; nstart = nend) {
+ unsigned long nr_pages;
+ long ret;
+
+ if (!locked) {
+ locked = 1;
+ mmap_read_lock(mm);
+ vma = find_vma(mm, nstart);
+ } else if (nstart >= vma->vm_end)
+ vma = vma->vm_next;
+ if (!vma || vma->vm_start >= end)
+ break;
+ nend = end ? min(end, vma->vm_end) : vma->vm_end;
+ if (vma->vm_flags & (VM_IO | VM_PFNMAP))
+ continue;
+ if (nstart < vma->vm_start)
+ nstart = vma->vm_start;
+ nr_pages = (nend - nstart) / PAGE_SIZE;
+ ret = __get_user_pages_locked(mm, nstart, nr_pages,
+ NULL, NULL, &locked,
+ FOLL_TOUCH | FOLL_WRITE);
+ if (ret <= 0)
+ break;
+ nend = nstart + ret * PAGE_SIZE;
+ }
+ if (locked)
+ mmap_read_unlock(mm);
+ if (nstart == end)
+ return 0;
+ return size - min_t(size_t, nstart - start, size);
+}
+EXPORT_SYMBOL(fault_in_safe_writeable);
+
/**
* fault_in_readable - fault in userspace address range for reading
* @uaddr: start of user address range
Patches currently in stable-queue which might be from anand.jain@xxxxxxxxxx are
queue-5.15/gup-turn-fault_in_pages_-readable-writeable-into-fault_in_-readable-writeable.patch
queue-5.15/iov_iter-introduce-nofault-flag-to-disable-page-faults.patch
queue-5.15/gfs2-fix-mmap-page-fault-deadlocks-for-direct-i-o.patch
queue-5.15/iomap-support-partial-direct-i-o-on-user-copy-failures.patch
queue-5.15/mm-gup-make-fault_in_safe_writeable-use-fixup_user_fault.patch
queue-5.15/gfs2-add-wrapper-for-iomap_file_buffered_write.patch
queue-5.15/gup-introduce-foll_nofault-flag-to-disable-page-faults.patch
queue-5.15/iov_iter-introduce-fault_in_iov_iter_writeable.patch
queue-5.15/gfs2-fix-mmap-page-fault-deadlocks-for-buffered-i-o.patch
queue-5.15/btrfs-fallback-to-blocking-mode-when-doing-async-dio-over-multiple-extents.patch
queue-5.15/gfs2-clean-up-function-may_grant.patch
queue-5.15/btrfs-fix-deadlock-due-to-page-faults-during-direct-io-reads-and-writes.patch
queue-5.15/iov_iter-turn-iov_iter_fault_in_readable-into-fault_in_iov_iter_readable.patch
queue-5.15/gfs2-move-the-inode-glock-locking-to-gfs2_file_buffered_write.patch
queue-5.15/gfs2-introduce-flag-for-glock-holder-auto-demotion.patch
queue-5.15/iomap-fix-iomap_dio_rw-return-value-for-user-copies.patch
queue-5.15/gfs2-eliminate-ip-i_gh.patch
queue-5.15/iomap-add-done_before-argument-to-iomap_dio_rw.patch
