diff --git a/fs/xfs/xfs_buf.h b/fs/xfs/xfs_buf.h index adef116db0c3f5c6c285ba7ffc73ddcfb81c63e6..8bfb974f0772844af09b11373fe11337d50685d7 100644 --- a/fs/xfs/xfs_buf.h +++ b/fs/xfs/xfs_buf.h @@ -183,7 +183,26 @@ typedef struct xfs_buf { unsigned int b_page_count; /* size of page array */ unsigned int b_offset; /* page offset in first page */ int b_error; /* error code on I/O */ - int b_last_error; /* previous async I/O error */ + + /* + * async write failure retry count. Initialised to zero on the first + * failure, then when it exceeds the maximum configured without a + * success the write is considered to be failed permanently and the + * iodone handler will take appropriate action. + * + * For retry timeouts, we record the jiffie of the first failure. This + * means that we can change the retry timeout for buffers already under + * I/O and thus avoid getting stuck in a retry loop with a long timeout. + * + * last_error is used to ensure that we are getting repeated errors, not + * different errors. e.g. a block device might change ENOSPC to EIO when + * a failure timeout occurs, so we want to re-initialise the error + * retry behaviour appropriately when that happens. + */ + int b_retries; + unsigned long b_first_retry_time; /* in jiffies */ + int b_last_error; + const struct xfs_buf_ops *b_ops; #ifdef XFS_BUF_LOCK_TRACKING diff --git a/fs/xfs/xfs_buf_item.c b/fs/xfs/xfs_buf_item.c index b8d0cd4adb8190007be715ebbdf38582a4cb277e..0d95c59f7c6804ac214cce1419bc0ed51176f151 100644 --- a/fs/xfs/xfs_buf_item.c +++ b/fs/xfs/xfs_buf_item.c @@ -1085,6 +1085,9 @@ xfs_buf_iodone_callback_error( bp->b_flags |= (XBF_WRITE | XBF_ASYNC | XBF_DONE | XBF_WRITE_FAIL); bp->b_last_error = bp->b_error; + bp->b_retries = 0; + bp->b_first_retry_time = jiffies; + xfs_buf_ioerror(bp, 0); xfs_buf_submit(bp); return true; @@ -1095,8 +1098,13 @@ xfs_buf_iodone_callback_error( * error configuration we have been set up to use. */ cfg = xfs_error_get_cfg(mp, XFS_ERR_METADATA, bp->b_error); - if (!cfg->max_retries) - goto permanent_error; + + if (cfg->max_retries != XFS_ERR_RETRY_FOREVER && + ++bp->b_retries > cfg->max_retries) + goto permanent_error; + if (cfg->retry_timeout && + time_after(jiffies, cfg->retry_timeout + bp->b_first_retry_time)) + goto permanent_error; /* still a transient error, higher layers will retry */ xfs_buf_ioerror(bp, 0); @@ -1139,6 +1147,7 @@ xfs_buf_iodone_callbacks( * retry state here in preparation for the next error that may occur. */ bp->b_last_error = 0; + bp->b_retries = 0; xfs_buf_do_callbacks(bp); bp->b_fspriv = NULL; diff --git a/fs/xfs/xfs_mount.h b/fs/xfs/xfs_mount.h index 0c5a97644d78a8c57440341f9853d69a40b00a5b..2fafa9438bcf59172a636057d6ead6e75dafcc6b 100644 --- a/fs/xfs/xfs_mount.h +++ b/fs/xfs/xfs_mount.h @@ -52,9 +52,12 @@ enum { XFS_ERR_ERRNO_MAX, }; +#define XFS_ERR_RETRY_FOREVER -1 + struct xfs_error_cfg { struct xfs_kobj kobj; int max_retries; + unsigned long retry_timeout; /* in jiffies, 0 = no timeout */ }; typedef struct xfs_mount { diff --git a/fs/xfs/xfs_sysfs.c b/fs/xfs/xfs_sysfs.c index 71046d9049854399a52f106b03fcc49f8f90cd87..918d144febd9eb097b04b442be9eb5bcf7a4db78 100644 --- a/fs/xfs/xfs_sysfs.c +++ b/fs/xfs/xfs_sysfs.c @@ -374,10 +374,6 @@ struct kobj_type xfs_log_ktype = { * and any other future type of IO (e.g. special inode or directory error * handling) we care to support. */ -static struct attribute *xfs_error_attrs[] = { - NULL, -}; - static inline struct xfs_error_cfg * to_error_cfg(struct kobject *kobject) { @@ -385,6 +381,79 @@ to_error_cfg(struct kobject *kobject) return container_of(kobj, struct xfs_error_cfg, kobj); } +static ssize_t +max_retries_show( + struct kobject *kobject, + char *buf) +{ + struct xfs_error_cfg *cfg = to_error_cfg(kobject); + + return snprintf(buf, PAGE_SIZE, "%d\n", cfg->max_retries); +} + +static ssize_t +max_retries_store( + struct kobject *kobject, + const char *buf, + size_t count) +{ + struct xfs_error_cfg *cfg = to_error_cfg(kobject); + int ret; + int val; + + ret = kstrtoint(buf, 0, &val); + if (ret) + return ret; + + if (val < -1) + return -EINVAL; + + cfg->max_retries = val; + return count; +} +XFS_SYSFS_ATTR_RW(max_retries); + +static ssize_t +retry_timeout_seconds_show( + struct kobject *kobject, + char *buf) +{ + struct xfs_error_cfg *cfg = to_error_cfg(kobject); + + return snprintf(buf, PAGE_SIZE, "%ld\n", + jiffies_to_msecs(cfg->retry_timeout) / MSEC_PER_SEC); +} + +static ssize_t +retry_timeout_seconds_store( + struct kobject *kobject, + const char *buf, + size_t count) +{ + struct xfs_error_cfg *cfg = to_error_cfg(kobject); + int ret; + int val; + + ret = kstrtoint(buf, 0, &val); + if (ret) + return ret; + + /* 1 day timeout maximum */ + if (val < 0 || val > 86400) + return -EINVAL; + + cfg->retry_timeout = msecs_to_jiffies(val * MSEC_PER_SEC); + return count; +} +XFS_SYSFS_ATTR_RW(retry_timeout_seconds); + +static struct attribute *xfs_error_attrs[] = { + ATTR_LIST(max_retries), + ATTR_LIST(retry_timeout_seconds), + NULL, +}; + + struct kobj_type xfs_error_cfg_ktype = { .release = xfs_sysfs_release, .sysfs_ops = &xfs_sysfs_ops, @@ -404,11 +473,13 @@ struct kobj_type xfs_error_ktype = { struct xfs_error_init { char *name; int max_retries; + int retry_timeout; /* in seconds */ }; static const struct xfs_error_init xfs_error_meta_init[XFS_ERR_ERRNO_MAX] = { { .name = "default", .max_retries = -1, + .retry_timeout = 0, }, }; @@ -439,6 +510,8 @@ xfs_error_sysfs_init_class( goto out_error; cfg->max_retries = init[i].max_retries; + cfg->retry_timeout = msecs_to_jiffies( + init[i].retry_timeout * MSEC_PER_SEC); } return 0;