summaryrefslogtreecommitdiffstats
path: root/include
diff options
context:
space:
mode:
authorJeff Layton <jlayton@redhat.com>2017-07-06 07:02:25 -0400
committerJeff Layton <jlayton@redhat.com>2017-07-06 07:02:25 -0400
commit5660e13d2fd6af1903d4b0b98020af95ca2d638a (patch)
tree10944f111ba11bf1d3b194300018f3a45e9fd9e8 /include
parent84cbadadc6eafc4798513773a2c8fce37dcd2fb8 (diff)
downloadop-kernel-dev-5660e13d2fd6af1903d4b0b98020af95ca2d638a.zip
op-kernel-dev-5660e13d2fd6af1903d4b0b98020af95ca2d638a.tar.gz
fs: new infrastructure for writeback error handling and reporting
Most filesystems currently use mapping_set_error and filemap_check_errors for setting and reporting/clearing writeback errors at the mapping level. filemap_check_errors is indirectly called from most of the filemap_fdatawait_* functions and from filemap_write_and_wait*. These functions are called from all sorts of contexts to wait on writeback to finish -- e.g. mostly in fsync, but also in truncate calls, getattr, etc. The non-fsync callers are problematic. We should be reporting writeback errors during fsync, but many places spread over the tree clear out errors before they can be properly reported, or report errors at nonsensical times. If I get -EIO on a stat() call, there is no reason for me to assume that it is because some previous writeback failed. The fact that it also clears out the error such that a subsequent fsync returns 0 is a bug, and a nasty one since that's potentially silent data corruption. This patch adds a small bit of new infrastructure for setting and reporting errors during address_space writeback. While the above was my original impetus for adding this, I think it's also the case that current fsync semantics are just problematic for userland. Most applications that call fsync do so to ensure that the data they wrote has hit the backing store. In the case where there are multiple writers to the file at the same time, this is really hard to determine. The first one to call fsync will see any stored error, and the rest get back 0. The processes with open fds may not be associated with one another in any way. They could even be in different containers, so ensuring coordination between all fsync callers is not really an option. One way to remedy this would be to track what file descriptor was used to dirty the file, but that's rather cumbersome and would likely be slow. However, there is a simpler way to improve the semantics here without incurring too much overhead. This set adds an errseq_t to struct address_space, and a corresponding one is added to struct file. Writeback errors are recorded in the mapping's errseq_t, and the one in struct file is used as the "since" value. This changes the semantics of the Linux fsync implementation such that applications can now use it to determine whether there were any writeback errors since fsync(fd) was last called (or since the file was opened in the case of fsync having never been called). Note that those writeback errors may have occurred when writing data that was dirtied via an entirely different fd, but that's the case now with the current mapping_set_error/filemap_check_error infrastructure. This will at least prevent you from getting a false report of success. The new behavior is still consistent with the POSIX spec, and is more reliable for application developers. This patch just adds some basic infrastructure for doing this, and ensures that the f_wb_err "cursor" is properly set when a file is opened. Later patches will change the existing code to use this new infrastructure for reporting errors at fsync time. Signed-off-by: Jeff Layton <jlayton@redhat.com> Reviewed-by: Jan Kara <jack@suse.cz>
Diffstat (limited to 'include')
-rw-r--r--include/linux/fs.h60
-rw-r--r--include/trace/events/filemap.h57
2 files changed, 116 insertions, 1 deletions
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 8ac8df1..78b5c29 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -30,7 +30,7 @@
#include <linux/percpu-rwsem.h>
#include <linux/workqueue.h>
#include <linux/delayed_call.h>
-
+#include <linux/errseq.h>
#include <asm/byteorder.h>
#include <uapi/linux/fs.h>
@@ -392,6 +392,7 @@ struct address_space {
gfp_t gfp_mask; /* implicit gfp mask for allocations */
struct list_head private_list; /* ditto */
void *private_data; /* ditto */
+ errseq_t wb_err;
} __attribute__((aligned(sizeof(long))));
/*
* On most architectures that alignment is already the case; but
@@ -868,6 +869,7 @@ struct file {
struct list_head f_tfile_llink;
#endif /* #ifdef CONFIG_EPOLL */
struct address_space *f_mapping;
+ errseq_t f_wb_err;
} __attribute__((aligned(4))); /* lest something weird decides that 2 is OK */
struct file_handle {
@@ -2526,6 +2528,62 @@ extern int filemap_fdatawrite_range(struct address_space *mapping,
loff_t start, loff_t end);
extern int filemap_check_errors(struct address_space *mapping);
+extern void __filemap_set_wb_err(struct address_space *mapping, int err);
+extern int __must_check file_check_and_advance_wb_err(struct file *file);
+extern int __must_check file_write_and_wait_range(struct file *file,
+ loff_t start, loff_t end);
+
+/**
+ * filemap_set_wb_err - set a writeback error on an address_space
+ * @mapping: mapping in which to set writeback error
+ * @err: error to be set in mapping
+ *
+ * When writeback fails in some way, we must record that error so that
+ * userspace can be informed when fsync and the like are called. We endeavor
+ * to report errors on any file that was open at the time of the error. Some
+ * internal callers also need to know when writeback errors have occurred.
+ *
+ * When a writeback error occurs, most filesystems will want to call
+ * filemap_set_wb_err to record the error in the mapping so that it will be
+ * automatically reported whenever fsync is called on the file.
+ *
+ * FIXME: mention FS_* flag here?
+ */
+static inline void filemap_set_wb_err(struct address_space *mapping, int err)
+{
+ /* Fastpath for common case of no error */
+ if (unlikely(err))
+ __filemap_set_wb_err(mapping, err);
+}
+
+/**
+ * filemap_check_wb_error - has an error occurred since the mark was sampled?
+ * @mapping: mapping to check for writeback errors
+ * @since: previously-sampled errseq_t
+ *
+ * Grab the errseq_t value from the mapping, and see if it has changed "since"
+ * the given value was sampled.
+ *
+ * If it has then report the latest error set, otherwise return 0.
+ */
+static inline int filemap_check_wb_err(struct address_space *mapping,
+ errseq_t since)
+{
+ return errseq_check(&mapping->wb_err, since);
+}
+
+/**
+ * filemap_sample_wb_err - sample the current errseq_t to test for later errors
+ * @mapping: mapping to be sampled
+ *
+ * Writeback errors are always reported relative to a particular sample point
+ * in the past. This function provides those sample points.
+ */
+static inline errseq_t filemap_sample_wb_err(struct address_space *mapping)
+{
+ return errseq_sample(&mapping->wb_err);
+}
+
extern int vfs_fsync_range(struct file *file, loff_t start, loff_t end,
int datasync);
extern int vfs_fsync(struct file *file, int datasync);
diff --git a/include/trace/events/filemap.h b/include/trace/events/filemap.h
index 42febb6..ff91325 100644
--- a/include/trace/events/filemap.h
+++ b/include/trace/events/filemap.h
@@ -10,6 +10,7 @@
#include <linux/memcontrol.h>
#include <linux/device.h>
#include <linux/kdev_t.h>
+#include <linux/errseq.h>
DECLARE_EVENT_CLASS(mm_filemap_op_page_cache,
@@ -52,6 +53,62 @@ DEFINE_EVENT(mm_filemap_op_page_cache, mm_filemap_add_to_page_cache,
TP_ARGS(page)
);
+TRACE_EVENT(filemap_set_wb_err,
+ TP_PROTO(struct address_space *mapping, errseq_t eseq),
+
+ TP_ARGS(mapping, eseq),
+
+ TP_STRUCT__entry(
+ __field(unsigned long, i_ino)
+ __field(dev_t, s_dev)
+ __field(errseq_t, errseq)
+ ),
+
+ TP_fast_assign(
+ __entry->i_ino = mapping->host->i_ino;
+ __entry->errseq = eseq;
+ if (mapping->host->i_sb)
+ __entry->s_dev = mapping->host->i_sb->s_dev;
+ else
+ __entry->s_dev = mapping->host->i_rdev;
+ ),
+
+ TP_printk("dev=%d:%d ino=0x%lx errseq=0x%x",
+ MAJOR(__entry->s_dev), MINOR(__entry->s_dev),
+ __entry->i_ino, __entry->errseq)
+);
+
+TRACE_EVENT(file_check_and_advance_wb_err,
+ TP_PROTO(struct file *file, errseq_t old),
+
+ TP_ARGS(file, old),
+
+ TP_STRUCT__entry(
+ __field(struct file *, file);
+ __field(unsigned long, i_ino)
+ __field(dev_t, s_dev)
+ __field(errseq_t, old)
+ __field(errseq_t, new)
+ ),
+
+ TP_fast_assign(
+ __entry->file = file;
+ __entry->i_ino = file->f_mapping->host->i_ino;
+ if (file->f_mapping->host->i_sb)
+ __entry->s_dev =
+ file->f_mapping->host->i_sb->s_dev;
+ else
+ __entry->s_dev =
+ file->f_mapping->host->i_rdev;
+ __entry->old = old;
+ __entry->new = file->f_wb_err;
+ ),
+
+ TP_printk("file=%p dev=%d:%d ino=0x%lx old=0x%x new=0x%x",
+ __entry->file, MAJOR(__entry->s_dev),
+ MINOR(__entry->s_dev), __entry->i_ino, __entry->old,
+ __entry->new)
+);
#endif /* _TRACE_FILEMAP_H */
/* This part must be outside protection */
OpenPOWER on IntegriCloud