netfs: zero the tail of a short DIO/unbuffered readgrafted

The buffered read collector zero-fills the tail of a short read that
stops below the inode's i_size (netfs_clear_unread()), so a read that
races an extending write still returns the expected number of bytes.
The non-buffered collector path does no such thing: it just records
how much was transferred.

Add the same zero-fill for the non-buffered case, gated on
NETFS_SREQ_CLEAR_TAIL: a subreq's source sets that flag when a short
result from it is known to be safe to treat as a hole, as opposed to
NETFS_SREQ_HIT_EOF, which means the read genuinely ran off the end of
the file and should be reported short as-is. Only CLEAR_TAIL should
zero-fill here; a real EOF must stay a real short read.

No source currently sets CLEAR_TAIL on an unbuffered/DIO subrequest,
so this is inert on its own -- a following change teaches cifs to set
it in the one case that needs it.

Fixes: e2d46f2ec332 ("netfs: Change the read result collector to only use one work item")
Reviewed-by: David Howells <dhowells@redhat.com>
Reviewed-by: Namjae Jeon <linkinjeon@kernel.org>
Signed-off-by: Paulo Alcantara <pc@manguebit.org>
Cc: Christian Brauner <brauner@kernel.org>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Ronnie Sahlberg <ronniesahlberg@gmail.com>
Cc: Shyam Prasad N <sprasad@microsoft.com>
Cc: Tom Talpey <tom@talpey.com>
Cc: Bharath SM <bharathsm@microsoft.com>
Cc: stable@vger.kernel.org

1 files changed, 123 insertions, 0 deletions

diff --git a/tools/testing/vma/shared.c b/tools/testing/vma/shared.c
new file mode 100644
index 000000000..4a39c9d50
--- /dev/null
+++ b/tools/testing/vma/shared.c
@@ -0,0 +1,123 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+
+#include "shared.h"
+
+
+bool fail_prealloc;
+unsigned long mmap_min_addr = CONFIG_DEFAULT_MMAP_MIN_ADDR;
+unsigned long dac_mmap_min_addr = CONFIG_DEFAULT_MMAP_MIN_ADDR;
+unsigned long stack_guard_gap = 256UL<<PAGE_SHIFT;
+
+const struct vm_operations_struct vma_dummy_vm_ops;
+struct anon_vma dummy_anon_vma;
+struct task_struct __current;
+
+struct vm_area_struct *alloc_vma(struct mm_struct *mm,
+		unsigned long start, unsigned long end,
+		pgoff_t pgoff, vma_flags_t vma_flags)
+{
+	struct vm_area_struct *vma = vm_area_alloc(mm);
+
+	if (vma == NULL)
+		return NULL;
+
+	vma->vm_start = start;
+	vma->vm_end = end;
+	vma_set_pgoff(vma, pgoff);
+	vma_set_anon_pgoff(vma, start >> PAGE_SHIFT);
+	vma->flags = vma_flags;
+	vma_assert_detached(vma);
+
+	return vma;
+}
+
+void detach_free_vma(struct vm_area_struct *vma)
+{
+	vma_mark_detached(vma);
+	vm_area_free(vma);
+}
+
+struct vm_area_struct *alloc_and_link_vma(struct mm_struct *mm,
+		unsigned long start, unsigned long end,
+		pgoff_t pgoff, vma_flags_t vma_flags)
+{
+	struct vm_area_struct *vma = alloc_vma(mm, start, end, pgoff, vma_flags);
+
+	if (vma == NULL)
+		return NULL;
+
+	if (attach_vma(mm, vma)) {
+		detach_free_vma(vma);
+		return NULL;
+	}
+
+	/*
+	 * Reset this counter which we use to track whether writes have
+	 * begun. Linking to the tree will have caused this to be incremented,
+	 * which means we will get a false positive otherwise.
+	 */
+	vma->vm_lock_seq = UINT_MAX;
+
+	return vma;
+}
+
+void reset_dummy_anon_vma(void)
+{
+	dummy_anon_vma.was_cloned = false;
+	dummy_anon_vma.was_unlinked = false;
+}
+
+int cleanup_mm(struct mm_struct *mm, struct vma_iterator *vmi)
+{
+	struct vm_area_struct *vma;
+	int count = 0;
+
+	fail_prealloc = false;
+	reset_dummy_anon_vma();
+
+	vma_iter_set(vmi, 0);
+	for_each_vma(*vmi, vma) {
+		detach_free_vma(vma);
+		count++;
+	}
+
+	mtree_destroy(&mm->mm_mt);
+	mm->map_count = 0;
+	return count;
+}
+
+bool vma_write_started(struct vm_area_struct *vma)
+{
+	int seq = vma->vm_lock_seq;
+
+	/* We reset after each check. */
+	vma->vm_lock_seq = UINT_MAX;
+
+	/* The vma_start_write() stub simply increments this value. */
+	return seq > -1;
+}
+
+void __vma_set_dummy_anon_vma(struct vm_area_struct *vma,
+		struct anon_vma_chain *avc, struct anon_vma *anon_vma)
+{
+	vma->anon_vma = anon_vma;
+	INIT_LIST_HEAD(&vma->anon_vma_chain);
+	list_add(&avc->same_vma, &vma->anon_vma_chain);
+	avc->anon_vma = vma->anon_vma;
+}
+
+void vma_set_dummy_anon_vma(struct vm_area_struct *vma,
+		struct anon_vma_chain *avc)
+{
+	__vma_set_dummy_anon_vma(vma, avc, &dummy_anon_vma);
+}
+
+struct task_struct *get_current(void)
+{
+	return &__current;
+}
+
+unsigned long rlimit(unsigned int limit)
+{
+	return (unsigned long)-1;
+}