generic: Test page faults during read and write

Some filesystems have problems when the buffer passed to read or
write is memory-mapped to the file being read from or written to,
and the buffer needs to be faulted in during the read or write.
That's not common, but filesystems are still required to cope with
it, and if they fail this test, then they will also fail more
complex scenarios that involve multiple files.

Signed-off-by: Andreas Gruenbacher <agruenba@redhat.com>
Reviewed-by: Darrick J. Wong <djwong@kernel.org>
Signed-off-by: Eryu Guan <guaneryu@gmail.com>

diff --git a/.gitignore b/.gitignore
index 2d72b064d5534dfe4edff284dbe9d08380900711..9e6d2fd596d867b2b87d54ad98250a368e9c6eda 100644 (file)
--- a/.gitignore
+++ b/.gitignore
@@ -105,6 +105,7 @@ tags
 /src/metaperf
 /src/mkswap
 /src/mmapcat
+/src/mmap-rw-fault
 /src/mmap-write-concurrent
 /src/multi_open_unlink
 /src/nametest

diff --git a/src/Makefile b/src/Makefile
index 884bd86a03f2c592bffa3821428a047bfc3911fd..25ab061d512796efcc60ba33ae3a584277a587c5 100644 (file)
--- a/src/Makefile
+++ b/src/Makefile
@@ -18,7 +18,7 @@ TARGETS = dirstress fill fill2 getpagesize holes lstat64 \
        t_ext4_dax_journal_corruption t_ext4_dax_inline_corruption \
        t_ofd_locks t_mmap_collision mmap-write-concurrent \
        t_get_file_time t_create_short_dirs t_create_long_dirs t_enospc \
-       t_mmap_writev_overlap checkpoint_journal
+       t_mmap_writev_overlap checkpoint_journal mmap-rw-fault
 
 LINUX_TARGETS = xfsctl bstat t_mtab getdevicesize preallo_rw_pattern_reader \
        preallo_rw_pattern_writer ftrunc trunc fs_perms testx looptest \

diff --git a/src/mmap-rw-fault.c b/src/mmap-rw-fault.c
new file mode 100644 (file)
index 0000000..82f9d97
--- /dev/null
+++ b/src/mmap-rw-fault.c
@@ -0,0 +1,186 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2021 Red Hat, Inc.  All Rights Reserved.
+ * Written by Andreas Gruenbacher (agruenba@redhat.com)
+ */
+
+/* Trigger page faults in the same file during read and write. */
+
+#ifndef _GNU_SOURCE
+#define _GNU_SOURCE /* to get definition of O_DIRECT flag. */
+#endif
+
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <sys/mman.h>
+#include <fcntl.h>
+#include <unistd.h>
+#include <stdlib.h>
+#include <stdio.h>
+#include <string.h>
+#include <errno.h>
+#include <err.h>
+
+char *filename;
+unsigned int page_size;
+void *page;
+char *addr;
+int fd;
+ssize_t ret;
+
+/*
+ * Leave a hole at the beginning of the test file and initialize a block of
+ * @page_size bytes at offset @page_size to @c.  Then, reopen the file and
+ * mmap the first two pages.
+ */
+void init(char c, int flags)
+{
+       fd = open(filename, O_CREAT | O_TRUNC | O_WRONLY | O_DIRECT, 0666);
+       if (fd == -1)
+               goto fail;
+       memset(page, c, page_size);
+       ret = pwrite(fd, page, page_size, page_size);
+       if (ret != page_size)
+               goto fail;
+       if (close(fd))
+               goto fail;
+
+       fd = open(filename, flags);
+       if (fd == -1)
+               goto fail;
+       addr = mmap(NULL, 2 * page_size, PROT_READ | PROT_WRITE, MAP_PRIVATE, fd, 0);
+       if (addr == MAP_FAILED)
+               err(1, NULL);
+       return;
+
+fail:
+       err(1, "%s", filename);
+}
+
+void done(void)
+{
+       if (fsync(fd))
+               goto fail;
+       if (close(fd))
+               goto fail;
+       return;
+
+fail:
+       err(1, "%s", filename);
+}
+
+static ssize_t do_read(int fd, void *buf, size_t count, off_t offset)
+{
+       ssize_t count2 = 0, ret;
+
+       do {
+               ret = pread(fd, buf, count, offset);
+               if (ret == -1) {
+                       if (errno == EINTR)
+                               continue;
+                       break;
+               }
+               if (ret == 0)
+                       break;
+               count2 += ret;
+               buf += ret;
+               count -= ret;
+       } while (count);
+       return count2;
+}
+
+static ssize_t do_write(int fd, const void *buf, size_t count, off_t offset)
+{
+       ssize_t count2 = 0, ret;
+
+       do {
+               ret = pwrite(fd, buf, count, offset);
+               if (ret == -1) {
+                       if (errno == EINTR)
+                               continue;
+                       break;
+               }
+               if (ret == 0)
+                       break;
+               count2 += ret;
+               buf += ret;
+               count -= ret;
+       } while (count);
+       return count2;
+}
+
+int main(int argc, char *argv[])
+{
+       if (argc != 2)
+               errx(1, "no test filename argument given");
+       filename = argv[1];
+
+       page_size = ret = sysconf(_SC_PAGE_SIZE);
+       if (ret == -1)
+               err(1, NULL);
+
+       ret = posix_memalign(&page, page_size, page_size);
+       if (ret) {
+               errno = ENOMEM;
+               err(1, NULL);
+       }
+
+       /*
+        * Make sure page faults during pread are handled correctly:
+        * read from an allocated area on disk into page 0.
+        */
+       init('a', O_RDWR);
+       ret = do_read(fd, addr, page_size, page_size);
+       if (ret != page_size)
+               err(1, "pread %s: %ld != %u", filename, ret, page_size);
+       if (memcmp(addr, page, page_size))
+               errx(1, "pread is broken");
+       done();
+
+       init('b', O_RDWR | O_DIRECT);
+       ret = do_read(fd, addr, page_size, page_size);
+       if (ret != page_size)
+               err(1, "pread %s (O_DIRECT): %ld != %u", filename, ret, page_size);
+       if (memcmp(addr, page, page_size))
+               errx(1, "pread (D_DIRECT) is broken");
+       done();
+
+       /*
+        * Make sure page faults during pwrite are handled correctly:
+        * write from an allocated area on disk into page 0.
+        */
+       init('c', O_RDWR);
+       ret = do_write(fd, addr + page_size, page_size, 0);
+       if (ret != page_size)
+               err(1, "pwrite %s: %ld != %u", filename, ret, page_size);
+       if (memcmp(addr, page, page_size))
+               errx(1, "pwrite is broken");
+       done();
+
+       init('d', O_RDWR | O_DIRECT);
+       ret = do_write(fd, addr + page_size, page_size, 0);
+       if (ret != page_size)
+               err(1, "pwrite %s (O_DIRECT): %ld != %u", filename, ret, page_size);
+       if (memcmp(addr, page, page_size))
+               errx(1, "pwrite (O_DIRECT) is broken");
+       done();
+
+       /*
+        * Reading from a hole under O_DIRECT takes a different code path in
+        * the kernel.  Read from a hole into page 0 to test that.  (It
+        * shouldn't matter that the hole and page 0 coincide.)
+        */
+       init('e', O_RDWR | O_DIRECT);
+       ret = do_read(fd, addr, page_size, 0);
+       if (ret != page_size)
+               err(1, "pread %s (O_DIRECT) from hole: %ld != %u", filename, ret, page_size);
+       memset(page, 0, page_size);
+       if (memcmp(addr, page, page_size))
+               errx(1, "pread (D_DIRECT) from hole is broken");
+       done();
+
+       if (unlink(filename))
+               err(1, "unlink %s", filename);
+
+       return 0;
+}

diff --git a/tests/generic/647 b/tests/generic/647
new file mode 100755 (executable)
index 0000000..2e74497
--- /dev/null
+++ b/tests/generic/647
@@ -0,0 +1,35 @@
+#! /bin/bash
+# SPDX-License-Identifier: GPL-2.0
+# Copyright (c) 2021 Red Hat, Inc.  All Rights Reserved.
+#
+# FS QA Test 647
+#
+# Trigger page faults in the same file during read and write
+#
+. ./common/preamble
+_begin_fstest auto quick
+
+# Override the default cleanup function.
+_cleanup()
+{
+       cd /
+       rm -f $tmp.*
+       rm -f $TEST_DIR/mmap-rw-fault.tmp
+}
+
+# get standard environment, filters and checks
+. ./common/rc
+. ./common/filter
+
+# real QA test starts here
+
+_supported_fs generic
+_require_test
+_require_test_program mmap-rw-fault
+
+echo "Silence is golden"
+
+$here/src/mmap-rw-fault $TEST_DIR/mmap-rw-fault.tmp
+
+status=$?
+exit

diff --git a/tests/generic/647.out b/tests/generic/647.out
new file mode 100644 (file)
index 0000000..439e5c5
--- /dev/null
+++ b/tests/generic/647.out
@@ -0,0 +1,2 @@
+QA output created by 647
+Silence is golden