diff options
| -rw-r--r-- | Documentation/filesystems/xfs.txt | 123 | ||||
| -rw-r--r-- | MAINTAINERS | 7 | ||||
| -rw-r--r-- | fs/xfs/xfs_buf_item.c | 9 | ||||
| -rw-r--r-- | fs/xfs/xfs_file.c | 3 | ||||
| -rw-r--r-- | fs/xfs/xfs_mount.h | 8 | ||||
| -rw-r--r-- | fs/xfs/xfs_sysfs.c | 47 | ||||
| -rw-r--r-- | fs/xfs/xfs_trans.c | 2 | ||||
| -rw-r--r-- | fs/xfs/xfs_xattr.c | 1 | ||||
| -rw-r--r-- | mm/filemap.c | 14 |
9 files changed, 184 insertions, 30 deletions
diff --git a/Documentation/filesystems/xfs.txt b/Documentation/filesystems/xfs.txt index 8146e9fd5ffc..c2d44e6e117b 100644 --- a/Documentation/filesystems/xfs.txt +++ b/Documentation/filesystems/xfs.txt @@ -348,3 +348,126 @@ Removed Sysctls ---- ------- fs.xfs.xfsbufd_centisec v4.0 fs.xfs.age_buffer_centisecs v4.0 + + +Error handling +============== + +XFS can act differently according to the type of error found during its +operation. The implementation introduces the following concepts to the error +handler: + + -failure speed: + Defines how fast XFS should propagate an error upwards when a specific + error is found during the filesystem operation. It can propagate + immediately, after a defined number of retries, after a set time period, + or simply retry forever. + + -error classes: + Specifies the subsystem the error configuration will apply to, such as + metadata IO or memory allocation. Different subsystems will have + different error handlers for which behaviour can be configured. + + -error handlers: + Defines the behavior for a specific error. + +The filesystem behavior during an error can be set via sysfs files. Each +error handler works independently - the first condition met by an error handler +for a specific class will cause the error to be propagated rather than reset and +retried. + +The action taken by the filesystem when the error is propagated is context +dependent - it may cause a shut down in the case of an unrecoverable error, +it may be reported back to userspace, or it may even be ignored because +there's nothing useful we can with the error or anyone we can report it to (e.g. +during unmount). + +The configuration files are organized into the following hierarchy for each +mounted filesystem: + + /sys/fs/xfs/<dev>/error/<class>/<error>/ + +Where: + <dev> + The short device name of the mounted filesystem. This is the same device + name that shows up in XFS kernel error messages as "XFS(<dev>): ..." + + <class> + The subsystem the error configuration belongs to. As of 4.9, the defined + classes are: + + - "metadata": applies metadata buffer write IO + + <error> + The individual error handler configurations. + + +Each filesystem has "global" error configuration options defined in their top +level directory: + + /sys/fs/xfs/<dev>/error/ + + fail_at_unmount (Min: 0 Default: 1 Max: 1) + Defines the filesystem error behavior at unmount time. + + If set to a value of 1, XFS will override all other error configurations + during unmount and replace them with "immediate fail" characteristics. + i.e. no retries, no retry timeout. This will always allow unmount to + succeed when there are persistent errors present. + + If set to 0, the configured retry behaviour will continue until all + retries and/or timeouts have been exhausted. This will delay unmount + completion when there are persistent errors, and it may prevent the + filesystem from ever unmounting fully in the case of "retry forever" + handler configurations. + + Note: there is no guarantee that fail_at_unmount can be set whilst an + unmount is in progress. It is possible that the sysfs entries are + removed by the unmounting filesystem before a "retry forever" error + handler configuration causes unmount to hang, and hence the filesystem + must be configured appropriately before unmount begins to prevent + unmount hangs. + +Each filesystem has specific error class handlers that define the error +propagation behaviour for specific errors. There is also a "default" error +handler defined, which defines the behaviour for all errors that don't have +specific handlers defined. Where multiple retry constraints are configuredi for +a single error, the first retry configuration that expires will cause the error +to be propagated. The handler configurations are found in the directory: + + /sys/fs/xfs/<dev>/error/<class>/<error>/ + + max_retries (Min: -1 Default: Varies Max: INTMAX) + Defines the allowed number of retries of a specific error before + the filesystem will propagate the error. The retry count for a given + error context (e.g. a specific metadata buffer) is reset every time + there is a successful completion of the operation. + + Setting the value to "-1" will cause XFS to retry forever for this + specific error. + + Setting the value to "0" will cause XFS to fail immediately when the + specific error is reported. + + Setting the value to "N" (where 0 < N < Max) will make XFS retry the + operation "N" times before propagating the error. + + retry_timeout_seconds (Min: -1 Default: Varies Max: 1 day) + Define the amount of time (in seconds) that the filesystem is + allowed to retry its operations when the specific error is + found. + + Setting the value to "-1" will allow XFS to retry forever for this + specific error. + + Setting the value to "0" will cause XFS to fail immediately when the + specific error is reported. + + Setting the value to "N" (where 0 < N < Max) will allow XFS to retry the + operation for up to "N" seconds before propagating the error. + +Note: The default behaviour for a specific error handler is dependent on both +the class and error context. For example, the default values for +"metadata/ENODEV" are "0" rather than "-1" so that this error handler defaults +to "fail immediately" behaviour. This is done because ENODEV is a fatal, +unrecoverable error no matter how many times the metadata IO is retried. diff --git a/MAINTAINERS b/MAINTAINERS index a306795a7450..3246c85e7d95 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -12915,11 +12915,10 @@ F: arch/x86/xen/*swiotlb* F: drivers/xen/*swiotlb* XFS FILESYSTEM -P: Silicon Graphics Inc M: Dave Chinner <david@fromorbit.com> -M: xfs@oss.sgi.com -L: xfs@oss.sgi.com -W: http://oss.sgi.com/projects/xfs +M: linux-xfs@vger.kernel.org +L: linux-xfs@vger.kernel.org +W: http://xfs.org/ T: git git://git.kernel.org/pub/scm/linux/kernel/git/dgc/linux-xfs.git S: Supported F: Documentation/filesystems/xfs.txt diff --git a/fs/xfs/xfs_buf_item.c b/fs/xfs/xfs_buf_item.c index e455f9098d49..2975cb2319f4 100644 --- a/fs/xfs/xfs_buf_item.c +++ b/fs/xfs/xfs_buf_item.c @@ -865,7 +865,7 @@ xfs_buf_item_log_segment( */ if (bit) { end_bit = MIN(bit + bits_to_set, (uint)NBWORD); - mask = ((1 << (end_bit - bit)) - 1) << bit; + mask = ((1U << (end_bit - bit)) - 1) << bit; *wordp |= mask; wordp++; bits_set = end_bit - bit; @@ -888,7 +888,7 @@ xfs_buf_item_log_segment( */ end_bit = bits_to_set - bits_set; if (end_bit) { - mask = (1 << end_bit) - 1; + mask = (1U << end_bit) - 1; *wordp |= mask; } } @@ -1095,7 +1095,8 @@ xfs_buf_iodone_callback_error( bp->b_last_error != bp->b_error) { bp->b_flags |= (XBF_WRITE | XBF_DONE | XBF_WRITE_FAIL); bp->b_last_error = bp->b_error; - if (cfg->retry_timeout && !bp->b_first_retry_time) + if (cfg->retry_timeout != XFS_ERR_RETRY_FOREVER && + !bp->b_first_retry_time) bp->b_first_retry_time = jiffies; xfs_buf_ioerror(bp, 0); @@ -1111,7 +1112,7 @@ xfs_buf_iodone_callback_error( if (cfg->max_retries != XFS_ERR_RETRY_FOREVER && ++bp->b_retries > cfg->max_retries) goto permanent_error; - if (cfg->retry_timeout && + if (cfg->retry_timeout != XFS_ERR_RETRY_FOREVER && time_after(jiffies, cfg->retry_timeout + bp->b_first_retry_time)) goto permanent_error; diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c index e612a0233710..b927ea9abe33 100644 --- a/fs/xfs/xfs_file.c +++ b/fs/xfs/xfs_file.c @@ -269,6 +269,8 @@ xfs_file_dio_aio_read( return -EINVAL; } + file_accessed(iocb->ki_filp); + /* * Locking is a bit tricky here. If we take an exclusive lock for direct * IO, we effectively serialise all new concurrent read IO to this file @@ -323,7 +325,6 @@ xfs_file_dio_aio_read( } xfs_rw_iunlock(ip, XFS_IOLOCK_SHARED); - file_accessed(iocb->ki_filp); return ret; } diff --git a/fs/xfs/xfs_mount.h b/fs/xfs/xfs_mount.h index b36676cde103..efd4a5526f37 100644 --- a/fs/xfs/xfs_mount.h +++ b/fs/xfs/xfs_mount.h @@ -57,10 +57,16 @@ enum { #define XFS_ERR_RETRY_FOREVER -1 +/* + * Although retry_timeout is in jiffies which is normally an unsigned long, + * we limit the retry timeout to 86400 seconds, or one day. So even a + * signed 32-bit long is sufficient for a HZ value up to 24855. Making it + * signed lets us store the special "-1" value, meaning retry forever. + */ struct xfs_error_cfg { struct xfs_kobj kobj; int max_retries; - unsigned long retry_timeout; /* in jiffies, 0 = no timeout */ + long retry_timeout; /* in jiffies, -1 = infinite */ }; typedef struct xfs_mount { diff --git a/fs/xfs/xfs_sysfs.c b/fs/xfs/xfs_sysfs.c index 79cfd3fc5324..5f8d55d29a11 100644 --- a/fs/xfs/xfs_sysfs.c +++ b/fs/xfs/xfs_sysfs.c @@ -393,9 +393,15 @@ max_retries_show( struct kobject *kobject, char *buf) { + int retries; struct xfs_error_cfg *cfg = to_error_cfg(kobject); - return snprintf(buf, PAGE_SIZE, "%d\n", cfg->max_retries); + if (cfg->retry_timeout == XFS_ERR_RETRY_FOREVER) + retries = -1; + else + retries = cfg->max_retries; + + return snprintf(buf, PAGE_SIZE, "%d\n", retries); } static ssize_t @@ -415,7 +421,10 @@ max_retries_store( if (val < -1) return -EINVAL; - cfg->max_retries = val; + if (val == -1) + cfg->retry_timeout = XFS_ERR_RETRY_FOREVER; + else + cfg->max_retries = val; return count; } XFS_SYSFS_ATTR_RW(max_retries); @@ -425,10 +434,15 @@ retry_timeout_seconds_show( struct kobject *kobject, char *buf) { + int timeout; 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); + if (cfg->retry_timeout == XFS_ERR_RETRY_FOREVER) + timeout = -1; + else + timeout = jiffies_to_msecs(cfg->retry_timeout) / MSEC_PER_SEC; + + return snprintf(buf, PAGE_SIZE, "%d\n", timeout); } static ssize_t @@ -445,11 +459,16 @@ retry_timeout_seconds_store( if (ret) return ret; - /* 1 day timeout maximum */ - if (val < 0 || val > 86400) + /* 1 day timeout maximum, -1 means infinite */ + if (val < -1 || val > 86400) return -EINVAL; - cfg->retry_timeout = msecs_to_jiffies(val * MSEC_PER_SEC); + if (val == -1) + cfg->retry_timeout = XFS_ERR_RETRY_FOREVER; + else { + cfg->retry_timeout = msecs_to_jiffies(val * MSEC_PER_SEC); + ASSERT(msecs_to_jiffies(val * MSEC_PER_SEC) < LONG_MAX); + } return count; } XFS_SYSFS_ATTR_RW(retry_timeout_seconds); @@ -519,18 +538,19 @@ struct xfs_error_init { static const struct xfs_error_init xfs_error_meta_init[XFS_ERR_ERRNO_MAX] = { { .name = "default", .max_retries = XFS_ERR_RETRY_FOREVER, - .retry_timeout = 0, + .retry_timeout = XFS_ERR_RETRY_FOREVER, }, { .name = "EIO", .max_retries = XFS_ERR_RETRY_FOREVER, - .retry_timeout = 0, + .retry_timeout = XFS_ERR_RETRY_FOREVER, }, { .name = "ENOSPC", .max_retries = XFS_ERR_RETRY_FOREVER, - .retry_timeout = 0, + .retry_timeout = XFS_ERR_RETRY_FOREVER, }, { .name = "ENODEV", - .max_retries = 0, + .max_retries = 0, /* We can't recover from devices disappearing */ + .retry_timeout = 0, }, }; @@ -561,7 +581,10 @@ xfs_error_sysfs_init_class( goto out_error; cfg->max_retries = init[i].max_retries; - cfg->retry_timeout = msecs_to_jiffies( + if (init[i].retry_timeout == XFS_ERR_RETRY_FOREVER) + cfg->retry_timeout = XFS_ERR_RETRY_FOREVER; + else + cfg->retry_timeout = msecs_to_jiffies( init[i].retry_timeout * MSEC_PER_SEC); } return 0; diff --git a/fs/xfs/xfs_trans.c b/fs/xfs/xfs_trans.c index 5f3d33d16e67..836eb807aa88 100644 --- a/fs/xfs/xfs_trans.c +++ b/fs/xfs/xfs_trans.c @@ -217,7 +217,7 @@ undo_log: undo_blocks: if (blocks > 0) { - xfs_mod_fdblocks(tp->t_mountp, -((int64_t)blocks), rsvd); + xfs_mod_fdblocks(tp->t_mountp, (int64_t)blocks, rsvd); tp->t_blk_res = 0; } diff --git a/fs/xfs/xfs_xattr.c b/fs/xfs/xfs_xattr.c index ea62245fee26..62900938f26d 100644 --- a/fs/xfs/xfs_xattr.c +++ b/fs/xfs/xfs_xattr.c @@ -147,6 +147,7 @@ __xfs_xattr_put_listent( arraytop = context->count + prefix_len + namelen + 1; if (arraytop > context->firstu) { context->count = -1; /* insufficient space */ + context->seen_enough = 1; return 0; } offset = (char *)context->alist + context->count; diff --git a/mm/filemap.c b/mm/filemap.c index 8a287dfc5372..2f1175e86c77 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -1910,16 +1910,18 @@ generic_file_read_iter(struct kiocb *iocb, struct iov_iter *iter) if (iocb->ki_flags & IOCB_DIRECT) { struct address_space *mapping = file->f_mapping; struct inode *inode = mapping->host; + struct iov_iter data = *iter; loff_t size; size = i_size_read(inode); retval = filemap_write_and_wait_range(mapping, iocb->ki_pos, iocb->ki_pos + count - 1); - if (!retval) { - struct iov_iter data = *iter; - retval = mapping->a_ops->direct_IO(iocb, &data); - } + if (retval < 0) + goto out; + file_accessed(file); + + retval = mapping->a_ops->direct_IO(iocb, &data); if (retval > 0) { iocb->ki_pos += retval; iov_iter_advance(iter, retval); @@ -1935,10 +1937,8 @@ generic_file_read_iter(struct kiocb *iocb, struct iov_iter *iter) * DAX files, so don't bother trying. */ if (retval < 0 || !iov_iter_count(iter) || iocb->ki_pos >= size || - IS_DAX(inode)) { - file_accessed(file); + IS_DAX(inode)) goto out; - } } retval = do_generic_file_read(file, &iocb->ki_pos, iter, retval); |