From: Prasad Singamsetty prasad.singamsetty@oracle.com

maillist inclusion category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I9VTE3 CVE: NA

Reference: https://lore.kernel.org/all/20240326133813.3224593-4-john.g.garry@oracle.com...

--------------------------------

An atomic write is a write issued with torn-write protection, meaning that for a power failure or any other hardware failure, all or none of the data from the write will be stored, but never a mix of old and new data.

Userspace may add flag RWF_ATOMIC to pwritev2() to indicate that the write is to be issued with torn-write prevention, according to special alignment and length rules.

For any syscall interface utilizing struct iocb, add IOCB_ATOMIC for iocb->ki_flags field to indicate the same.

A call to statx will give the relevant atomic write info for a file: - atomic_write_unit_min - atomic_write_unit_max - atomic_write_segments_max

Both min and max values must be a power-of-2.

Applications can avail of atomic write feature by ensuring that the total length of a write is a power-of-2 in size and also sized between atomic_write_unit_min and atomic_write_unit_max, inclusive. Applications must ensure that the write is at a naturally-aligned offset in the file wrt the total write length. The value in atomic_write_segments_max indicates the upper limit for IOV_ITER iovcnt.

Add file mode flag FMODE_CAN_ATOMIC_WRITE, so files which do not have the flag set will have RWF_ATOMIC rejected and not just ignored.

Add a type argument to kiocb_set_rw_flags() to allows reads which have RWF_ATOMIC set to be rejected.

Helper function generic_atomic_write_valid() can be used by FSes to verify compliant writes. There we check for iov_iter type is for ubuf, which implies iovcnt==1 for pwritev2(), which is an initial restriction for atomic_write_segments_max. Initially the only user will be bdev file operations write handler. We will rely on the block BIO submission path to ensure write sizes are compliant for the bdev, so we don't need to check atomic writes sizes yet.

Signed-off-by: Prasad Singamsetty prasad.singamsetty@oracle.com jpg: merge into single patch and much rewrite Signed-off-by: John Garry john.g.garry@oracle.com Signed-off-by: Long Li leo.lilong@huawei.com --- fs/aio.c | 8 ++++---- fs/read_write.c | 2 +- include/linux/fs.h | 33 ++++++++++++++++++++++++++++++++- include/uapi/linux/fs.h | 5 ++++- io_uring/io_uring.c | 2 +- 5 files changed, 42 insertions(+), 8 deletions(-)

diff --git a/fs/aio.c b/fs/aio.c index 00641a1ad0b3..0c5b6eece498 100644 --- a/fs/aio.c +++ b/fs/aio.c @@ -1458,7 +1458,7 @@ static void aio_complete_rw(struct kiocb *kiocb, long res, long res2) iocb_put(iocb); }

-static int aio_prep_rw(struct kiocb *req, const struct iocb *iocb) +static int aio_prep_rw(struct kiocb *req, const struct iocb *iocb, int rw_type) { int ret;

@@ -1485,7 +1485,7 @@ static int aio_prep_rw(struct kiocb *req, const struct iocb *iocb) } else req->ki_ioprio = get_current_ioprio();

- ret = kiocb_set_rw_flags(req, iocb->aio_rw_flags); + ret = kiocb_set_rw_flags(req, iocb->aio_rw_flags, rw_type); if (unlikely(ret)) return ret;

@@ -1537,7 +1537,7 @@ static int aio_read(struct kiocb *req, const struct iocb *iocb, struct file *file; int ret;

- ret = aio_prep_rw(req, iocb); + ret = aio_prep_rw(req, iocb, WRITE); if (ret) return ret; file = req->ki_filp; @@ -1565,7 +1565,7 @@ static int aio_write(struct kiocb *req, const struct iocb *iocb, struct file *file; int ret;

- ret = aio_prep_rw(req, iocb); + ret = aio_prep_rw(req, iocb, READ); if (ret) return ret; file = req->ki_filp; diff --git a/fs/read_write.c b/fs/read_write.c index 371a5a76f30e..da03b3e65cf3 100644 --- a/fs/read_write.c +++ b/fs/read_write.c @@ -726,7 +726,7 @@ static ssize_t do_iter_readv_writev(struct file *filp, struct iov_iter *iter, ssize_t ret;

init_sync_kiocb(&kiocb, filp); - ret = kiocb_set_rw_flags(&kiocb, flags); + ret = kiocb_set_rw_flags(&kiocb, flags, type); if (ret) return ret; kiocb.ki_pos = (ppos ? *ppos : 0); diff --git a/include/linux/fs.h b/include/linux/fs.h index 382a0d4dd3dd..5e37ba855083 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -41,6 +41,7 @@ #include <linux/build_bug.h> #include <linux/stddef.h> #include <linux/mount.h> +#include <linux/uio.h> #include <linux/tracepoint-defs.h>

#include <asm/byteorder.h> @@ -184,6 +185,9 @@ typedef int (dio_iodone_t)(struct kiocb *iocb, loff_t offset, /* File supports async buffered reads */ #define FMODE_BUF_RASYNC ((__force fmode_t)0x40000000)

+/* File supports atomic writes */ +#define FMODE_CAN_ATOMIC_WRITE ((__force fmode_t)0x80000000) + /* File mode control flag, expect random access pattern */ #define FMODE_CTL_RANDOM ((__force fmode_t)0x1000)

@@ -320,6 +324,7 @@ enum rw_hint { #define IOCB_SYNC (__force int) RWF_SYNC #define IOCB_NOWAIT (__force int) RWF_NOWAIT #define IOCB_APPEND (__force int) RWF_APPEND +#define IOCB_ATOMIC (__force int) RWF_ATOMIC

/* non-RWF related bits - start at 16 */ #define IOCB_EVENTFD (1 << 16) @@ -3406,7 +3411,8 @@ static inline int iocb_flags(struct file *file) return res; }

-static inline int kiocb_set_rw_flags(struct kiocb *ki, rwf_t flags) +static inline int kiocb_set_rw_flags(struct kiocb *ki, rwf_t flags, + int rw_type) { int kiocb_flags = 0;

@@ -3423,6 +3429,12 @@ static inline int kiocb_set_rw_flags(struct kiocb *ki, rwf_t flags) return -EOPNOTSUPP; kiocb_flags |= IOCB_NOIO; } + if (flags & RWF_ATOMIC) { + if (rw_type != WRITE) + return -EOPNOTSUPP; + if (!(ki->ki_filp->f_mode & FMODE_CAN_ATOMIC_WRITE)) + return -EOPNOTSUPP; + } kiocb_flags |= (__force int) (flags & RWF_SUPPORTED); if (flags & RWF_SYNC) kiocb_flags |= IOCB_DSYNC; @@ -3665,4 +3677,23 @@ static inline void fs_file_read_do_trace(struct kiocb *iocb) if (tracepoint_enabled(fs_file_read)) fs_file_read_update_args_by_trace(iocb); } + +static inline +bool generic_atomic_write_valid(loff_t pos, struct iov_iter *iter, + unsigned int unit_min, unsigned int unit_max) +{ + size_t len = iov_iter_count(iter); + + if (len < unit_min || len > unit_max) + return false; + + if (!is_power_of_2(len)) + return false; + + if (!IS_ALIGNED(pos, len)) + return false; + + return true; +} + #endif /* _LINUX_FS_H */ diff --git a/include/uapi/linux/fs.h b/include/uapi/linux/fs.h index f44eb0a04afd..78f4091ed188 100644 --- a/include/uapi/linux/fs.h +++ b/include/uapi/linux/fs.h @@ -300,8 +300,11 @@ typedef int __bitwise __kernel_rwf_t; /* per-IO O_APPEND */ #define RWF_APPEND ((__force __kernel_rwf_t)0x00000010)

+/* Atomic Write */ +#define RWF_ATOMIC ((__force __kernel_rwf_t)0x00000040) + /* mask of flags supported by the kernel */ #define RWF_SUPPORTED (RWF_HIPRI | RWF_DSYNC | RWF_SYNC | RWF_NOWAIT |\ - RWF_APPEND) + RWF_APPEND | RWF_ATOMIC)

#endif /* _UAPI_LINUX_FS_H */ diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c index 65cf70874fb3..c284e9865826 100644 --- a/io_uring/io_uring.c +++ b/io_uring/io_uring.c @@ -2956,7 +2956,7 @@ static int io_prep_rw(struct io_kiocb *req, const struct io_uring_sqe *sqe, kiocb->ki_pos = READ_ONCE(sqe->off); kiocb->ki_hint = ki_hint_validate(file_write_hint(kiocb->ki_filp)); kiocb->ki_flags = iocb_flags(kiocb->ki_filp); - ret = kiocb_set_rw_flags(kiocb, READ_ONCE(sqe->rw_flags)); + ret = kiocb_set_rw_flags(kiocb, READ_ONCE(sqe->rw_flags), rw); if (unlikely(ret)) return ret;

From: John Garry john.g.garry@oracle.com

maillist inclusion category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I9VTE3 CVE: NA

Reference: https://lore.kernel.org/all/20240326133813.3224593-1-john.g.garry@oracle.com...

--------------------------------

Add atomic write support, as follows: - add helper functions to get request_queue atomic write limits - report request_queue atomic write support limits to sysfs and update Doc - support to safely merge atomic writes - deal with splitting atomic writes - misc helper functions - add a per-request atomic write flag

New request_queue limits are added, as follows: - atomic_write_hw_max is set by the block driver and is the maximum length of an atomic write which the device may support. It is not necessarily a power-of-2. - atomic_write_max_sectors is derived from atomic_write_hw_max_sectors and max_hw_sectors. It is always a power-of-2. Atomic writes may be merged, and atomic_write_max_sectors would be the limit on a merged atomic write request size. This value is not capped at max_sectors, as the value in max_sectors can be controlled from userspace, and it would only cause trouble if userspace could limit atomic_write_unit_max_bytes and the other atomic write limits. - atomic_write_hw_unit_{min,max} are set by the block driver and are the min/max length of an atomic write unit which the device may support. They both must be a power-of-2. Typically atomic_write_hw_unit_max will hold the same value as atomic_write_hw_max. - atomic_write_unit_{min,max} are derived from atomic_write_hw_unit_{min,max}, max_hw_sectors, and block core limits. Both min and max values must be a power-of-2. - atomic_write_hw_boundary is set by the block driver. If non-zero, it indicates an LBA space boundary at which an atomic write straddles no longer is atomically executed by the disk. The value must be a power-of-2. Note that it would be acceptable to enforce a rule that atomic_write_hw_boundary_sectors is a multiple of atomic_write_hw_unit_max, but the resultant code would be more complicated.

All atomic writes limits are by default set 0 to indicate no atomic write support. Even though it is assumed by Linux that a logical block can always be atomically written, we ignore this as it is not of particular interest. Stacked devices are just not supported either for now.

An atomic write must always be submitted to the block driver as part of a single request. As such, only a single BIO must be submitted to the block layer for an atomic write. When a single atomic write BIO is submitted, it cannot be split. As such, atomic_write_unit_{max, min}_bytes are limited by the maximum guaranteed BIO size which will not be required to be split. This max size is calculated by request_queue max segments and the number of bvecs a BIO can fit, BIO_MAX_VECS. Currently we rely on userspace issuing a write with iovcnt=1 for pwritev2() - as such, we can rely on each segment containing PAGE_SIZE of data, apart from the first+last, which each can fit logical block size of data. The first+last will be LBS length/aligned as we rely on direct IO alignment rules also.

New sysfs files are added to report the following atomic write limits: - atomic_write_unit_max_bytes - same as atomic_write_unit_max_sectors in bytes - atomic_write_unit_min_bytes - same as atomic_write_unit_min_sectors in bytes - atomic_write_boundary_bytes - same as atomic_write_hw_boundary_sectors in bytes - atomic_write_max_bytes - same as atomic_write_max_sectors in bytes

Atomic writes may only be merged with other atomic writes and only under the following conditions: - total resultant request length <= atomic_write_max_bytes - the merged write does not straddle a boundary

Helper function bdev_can_atomic_write() is added to indicate whether atomic writes may be issued to a bdev. If a bdev is a partition, the partition start must be aligned with both atomic_write_unit_min_sectors and atomic_write_hw_boundary_sectors.

FSes will rely on the block layer to validate that an atomic write BIO submitted will be of valid size, so add blk_validate_atomic_write_op_size() for this purpose. Userspace expects an atomic write which is of invalid size to be rejected with -EINVAL, so add BLK_STS_INVAL for this. Also use BLK_STS_INVAL for when a BIO needs to be split, as this should mean an invalid size BIO.

Flag REQ_ATOMIC is used for indicating an atomic write.

Co-developed-by: Himanshu Madhani himanshu.madhani@oracle.com Signed-off-by: Himanshu Madhani himanshu.madhani@oracle.com Signed-off-by: John Garry john.g.garry@oracle.com Signed-off-by: Long Li leo.lilong@huawei.com --- Documentation/ABI/testing/sysfs-block | 52 +++++++++++++++ block/blk-core.c | 21 ++++++ block/blk-merge.c | 95 ++++++++++++++++++++++++++- block/blk-settings.c | 94 ++++++++++++++++++++++++++ block/blk-sysfs.c | 33 ++++++++++ include/linux/blk_types.h | 7 ++ include/linux/blkdev.h | 65 ++++++++++++++++++ 7 files changed, 366 insertions(+), 1 deletion(-)

diff --git a/Documentation/ABI/testing/sysfs-block b/Documentation/ABI/testing/sysfs-block index e34cdeeeb9d4..6cee984819b3 100644 --- a/Documentation/ABI/testing/sysfs-block +++ b/Documentation/ABI/testing/sysfs-block @@ -97,6 +97,58 @@ Description: indicates how many bytes the beginning of the device is offset from the disk's natural alignment.

+What: /sys/block/<disk>/atomic_write_max_bytes +Date: February 2024 +Contact: Himanshu Madhani himanshu.madhani@oracle.com +Description: + [RO] This parameter specifies the maximum atomic write + size reported by the device. This parameter is relevant + for merging of writes, where a merged atomic write + operation must not exceed this number of bytes. + This parameter may be greater to the value in + atomic_write_unit_max_bytes as + atomic_write_unit_max_bytes will be rounded down to a + power-of-two and atomic_write_unit_max_bytes may also be + limited by some other queue limits, such as max_segments. + This parameter - along with atomic_write_unit_min_bytes + and atomic_write_unit_max_bytes - will not be larger than + max_hw_sectors_kb, but may be larger than max_sectors_kb. + + +What: /sys/block/<disk>/atomic_write_unit_min_bytes +Date: February 2024 +Contact: Himanshu Madhani himanshu.madhani@oracle.com +Description: + [RO] This parameter specifies the smallest block which can + be written atomically with an atomic write operation. All + atomic write operations must begin at a + atomic_write_unit_min boundary and must be multiples of + atomic_write_unit_min. This value must be a power-of-two. + + +What: /sys/block/<disk>/atomic_write_unit_max_bytes +Date: February 2024 +Contact: Himanshu Madhani himanshu.madhani@oracle.com +Description: + [RO] This parameter defines the largest block which can be + written atomically with an atomic write operation. This + value must be a multiple of atomic_write_unit_min and must + be a power-of-two. This value will not be larger than + atomic_write_max_bytes. + + +What: /sys/block/<disk>/atomic_write_boundary_bytes +Date: February 2024 +Contact: Himanshu Madhani himanshu.madhani@oracle.com +Description: + [RO] A device may need to internally split I/Os which + straddle a given logical block address boundary. In that + case a single atomic write operation will be processed as + one of more sub-operations which each complete atomically. + This parameter specifies the size in bytes of the atomic + boundary if one is reported by the device. This value must + be a power-of-two. + What: /sys/block/<disk>/<partition>/alignment_offset Date: April 2009 Contact: Martin K. Petersen martin.petersen@oracle.com diff --git a/block/blk-core.c b/block/blk-core.c index 7950063c0345..27f356c07d26 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -205,6 +205,8 @@ static const struct { [BLK_STS_ZONE_OPEN_RESOURCE] = { -ETOOMANYREFS, "open zones exceeded" }, [BLK_STS_ZONE_ACTIVE_RESOURCE] = { -EOVERFLOW, "active zones exceeded" },

+ [BLK_STS_INVAL] = { -EINVAL, "invalid" }, + /* everything else not covered above: */ [BLK_STS_IOERR] = { -EIO, "I/O" }, }; @@ -819,6 +821,18 @@ static inline blk_status_t blk_check_zone_append(struct request_queue *q, return BLK_STS_OK; }

+static blk_status_t blk_validate_atomic_write_op_size(struct request_queue *q, + struct bio *bio) +{ + if (bio->bi_iter.bi_size > queue_atomic_write_unit_max_bytes(q)) + return BLK_STS_INVAL; + + if (bio->bi_iter.bi_size % queue_atomic_write_unit_min_bytes(q)) + return BLK_STS_INVAL; + + return BLK_STS_OK; +} + static noinline_for_stack bool submit_bio_checks(struct bio *bio) { struct request_queue *q = bio->bi_disk->queue; @@ -900,6 +914,13 @@ static noinline_for_stack bool submit_bio_checks(struct bio *bio) if (!q->limits.max_write_zeroes_sectors) goto not_supported; break; + case REQ_OP_WRITE: + if (bio->bi_opf & REQ_ATOMIC) { + status = blk_validate_atomic_write_op_size(q, bio); + if (status != BLK_STS_OK) + goto end_io; + } + break; default: break; } diff --git a/block/blk-merge.c b/block/blk-merge.c index a65d1d275040..7ca680a6c037 100644 --- a/block/blk-merge.c +++ b/block/blk-merge.c @@ -13,6 +13,46 @@ #include "blk.h" #include "blk-rq-qos.h"

+/* + * rq_straddles_atomic_write_boundary - check for boundary violation + * @rq: request to check + * @front: data size to be appended to front + * @back: data size to be appended to back + * + * Determine whether merging a request or bio into another request will result + * in a merged request which straddles an atomic write boundary. + * + * The value @front_adjust is the data which would be appended to the front of + * @rq, while the value @back_adjust is the data which would be appended to the + * back of @rq. Callers will typically only have either @front_adjust or + * @back_adjust as non-zero. + * + */ +static bool rq_straddles_atomic_write_boundary(struct request *rq, + unsigned int front_adjust, + unsigned int back_adjust) +{ + unsigned int boundary = queue_atomic_write_boundary_bytes(rq->q); + u64 mask, start_rq_pos, end_rq_pos; + + if (!boundary) + return false; + + start_rq_pos = blk_rq_pos(rq) << SECTOR_SHIFT; + end_rq_pos = start_rq_pos + blk_rq_bytes(rq) - 1; + + start_rq_pos -= front_adjust; + end_rq_pos += back_adjust; + + mask = ~(boundary - 1); + + /* Top bits are different, so crossed a boundary */ + if ((start_rq_pos & mask) != (end_rq_pos & mask)) + return true; + + return false; +} + static inline bool bio_will_gap(struct request_queue *q, struct request *prev_rq, struct bio *prev, struct bio *next) { @@ -145,11 +185,20 @@ static inline unsigned get_max_io_size(struct request_queue *q, struct bio *bio) { unsigned sectors = blk_max_size_offset(q, bio->bi_iter.bi_sector, 0); - unsigned max_sectors = sectors; + unsigned max_sectors; unsigned pbs = queue_physical_block_size(q) >> SECTOR_SHIFT; unsigned lbs = queue_logical_block_size(q) >> SECTOR_SHIFT; unsigned start_offset = bio->bi_iter.bi_sector & (pbs - 1);

+ /* + * We ignore lim->max_sectors for atomic writes simply because + * it may less than the bio size, which we cannot tolerate. + */ + if (bio->bi_opf & REQ_ATOMIC) + max_sectors = q->limits.atomic_write_max_sectors; + else + max_sectors = sectors; + max_sectors += start_offset; max_sectors &= ~(pbs - 1); if (max_sectors > start_offset) @@ -278,6 +327,11 @@ static struct bio *blk_bio_segment_split(struct request_queue *q, *segs = nsegs; return NULL; split: + if (bio->bi_opf & REQ_ATOMIC) { + bio->bi_status = BLK_STS_INVAL; + bio_endio(bio); + return ERR_PTR(-EINVAL); + } *segs = nsegs; return bio_split(bio, sectors, GFP_NOIO, bs); } @@ -594,6 +648,13 @@ int ll_back_merge_fn(struct request *req, struct bio *bio, unsigned int nr_segs) return 0; }

+ if (req->cmd_flags & REQ_ATOMIC) { + if (rq_straddles_atomic_write_boundary(req, + bio->bi_iter.bi_size, 0)) { + return 0; + } + } + return ll_new_hw_segment(req, bio, nr_segs); }

@@ -613,6 +674,13 @@ static int ll_front_merge_fn(struct request *req, struct bio *bio, return 0; }

+ if (req->cmd_flags & REQ_ATOMIC) { + if (rq_straddles_atomic_write_boundary(req, + 0, bio->bi_iter.bi_size)) { + return 0; + } + } + return ll_new_hw_segment(req, bio, nr_segs); }

@@ -649,6 +717,13 @@ static int ll_merge_requests_fn(struct request_queue *q, struct request *req, blk_rq_get_max_sectors(req, blk_rq_pos(req))) return 0;

+ if (req->cmd_flags & REQ_ATOMIC) { + if (rq_straddles_atomic_write_boundary(req, + 0, blk_rq_bytes(next))) { + return 0; + } + } + total_phys_segments = req->nr_phys_segments + next->nr_phys_segments; if (total_phys_segments > blk_rq_get_max_segments(req)) return 0; @@ -721,6 +796,18 @@ static enum elv_merge blk_try_req_merge(struct request *req, return ELEVATOR_NO_MERGE; }

+static bool blk_atomic_write_mergeable_rq_bio(struct request *rq, + struct bio *bio) +{ + return (rq->cmd_flags & REQ_ATOMIC) == (bio->bi_opf & REQ_ATOMIC); +} + +static bool blk_atomic_write_mergeable_rqs(struct request *rq, + struct request *next) +{ + return (rq->cmd_flags & REQ_ATOMIC) == (next->cmd_flags & REQ_ATOMIC); +} + /* * For non-mq, this has to be called with the request spinlock acquired. * For mq with scheduling, the appropriate queue wide lock should be held. @@ -752,6 +839,9 @@ static struct request *attempt_merge(struct request_queue *q, if (req->ioprio != next->ioprio) return NULL;

+ if (!blk_atomic_write_mergeable_rqs(req, next)) + return NULL; + /* * If we are allowed to merge, then append bio list * from next to rq and release next. merge_requests_fn @@ -895,6 +985,9 @@ bool blk_rq_merge_ok(struct request *rq, struct bio *bio) if (rq->ioprio != bio_prio(bio)) return false;

+ if (blk_atomic_write_mergeable_rq_bio(rq, bio) == false) + return false; + return true; }

diff --git a/block/blk-settings.c b/block/blk-settings.c index c3aa7f8ee388..754b758946a9 100644 --- a/block/blk-settings.c +++ b/block/blk-settings.c @@ -127,6 +127,41 @@ void blk_queue_bounce_limit(struct request_queue *q, u64 max_addr) } EXPORT_SYMBOL(blk_queue_bounce_limit);

+/* + * Returns max guaranteed bytes which we can fit in a bio. + * + * We always assume that we can fit in at least PAGE_SIZE in a segment, apart + * from first and last segments. + */ +static +unsigned int blk_queue_max_guaranteed_bio(struct queue_limits *limits) +{ + unsigned int max_segments = min((u16)BIO_MAX_PAGES, limits->max_segments); + unsigned int length; + + length = min(max_segments, 2U) * limits->logical_block_size; + if (max_segments > 2) + length += (max_segments - 2) * PAGE_SIZE; + + return length; +} + +static void blk_atomic_writes_update_limits(struct queue_limits *limits) +{ + unsigned int unit_limit = min(limits->max_hw_sectors << SECTOR_SHIFT, + blk_queue_max_guaranteed_bio(limits)); + + unit_limit = rounddown_pow_of_two(unit_limit); + + limits->atomic_write_max_sectors = + min(limits->atomic_write_hw_max >> SECTOR_SHIFT, + limits->max_hw_sectors); + limits->atomic_write_unit_min = + min(limits->atomic_write_hw_unit_min, unit_limit); + limits->atomic_write_unit_max = + min(limits->atomic_write_hw_unit_max, unit_limit); +} + /** * blk_queue_max_hw_sectors - set max sectors for a request for this queue * @q: the request queue for the device @@ -161,6 +196,9 @@ void blk_queue_max_hw_sectors(struct request_queue *q, unsigned int max_hw_secto max_sectors = min_not_zero(max_hw_sectors, limits->max_dev_sectors); max_sectors = min_t(unsigned int, max_sectors, BLK_DEF_MAX_SECTORS); limits->max_sectors = max_sectors; + + blk_atomic_writes_update_limits(limits); + q->backing_dev_info->io_pages = max_sectors >> (PAGE_SHIFT - 9); } EXPORT_SYMBOL(blk_queue_max_hw_sectors); @@ -196,6 +234,62 @@ void blk_queue_max_discard_sectors(struct request_queue *q, } EXPORT_SYMBOL(blk_queue_max_discard_sectors);

+/** + * blk_queue_atomic_write_max_bytes - set max bytes supported by + * the device for atomic write operations. + * @q: the request queue for the device + * @bytes: maximum bytes supported + */ +void blk_queue_atomic_write_max_bytes(struct request_queue *q, + unsigned int bytes) +{ + q->limits.atomic_write_hw_max = bytes; + blk_atomic_writes_update_limits(&q->limits); +} +EXPORT_SYMBOL(blk_queue_atomic_write_max_bytes); + +/** + * blk_queue_atomic_write_boundary_bytes - Device's logical block address space + * which an atomic write should not cross. + * @q: the request queue for the device + * @bytes: must be a power-of-two. + */ +void blk_queue_atomic_write_boundary_bytes(struct request_queue *q, + unsigned int bytes) +{ + q->limits.atomic_write_hw_boundary = bytes; +} +EXPORT_SYMBOL(blk_queue_atomic_write_boundary_bytes); + +/** + * blk_queue_atomic_write_unit_min_bytes - smallest unit that can be written + * atomically to the device. + * @q: the request queue for the device + * @bytes: must be a power-of-two. + */ +void blk_queue_atomic_write_unit_min_bytes(struct request_queue *q, + unsigned int bytes) +{ + q->limits.atomic_write_hw_unit_min = bytes; + blk_atomic_writes_update_limits(&q->limits); +} +EXPORT_SYMBOL(blk_queue_atomic_write_unit_min_bytes); + +/* + * blk_queue_atomic_write_unit_max_bytes - largest unit that can be written + * atomically to the device. + * @q: the request queue for the device + * @bytes: must be a power-of-two. + */ +void blk_queue_atomic_write_unit_max_bytes(struct request_queue *q, + unsigned int bytes) +{ + q->limits.atomic_write_hw_unit_max = bytes; + blk_atomic_writes_update_limits(&q->limits); +} +EXPORT_SYMBOL(blk_queue_atomic_write_unit_max_bytes); + + /** * blk_queue_max_write_same_sectors - set max sectors for a single write same * @q: the request queue for the device diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c index c95be9626a09..6916f1ed4590 100644 --- a/block/blk-sysfs.c +++ b/block/blk-sysfs.c @@ -126,6 +126,30 @@ static ssize_t queue_max_discard_segments_show(struct request_queue *q, return queue_var_show(queue_max_discard_segments(q), (page)); }

+static ssize_t queue_atomic_write_max_bytes_show(struct request_queue *q, + char *page) +{ + return queue_var_show(queue_atomic_write_max_bytes(q), page); +} + +static ssize_t queue_atomic_write_boundary_show(struct request_queue *q, + char *page) +{ + return queue_var_show(queue_atomic_write_boundary_bytes(q), page); +} + +static ssize_t queue_atomic_write_unit_min_show(struct request_queue *q, + char *page) +{ + return queue_var_show(queue_atomic_write_unit_min_bytes(q), page); +} + +static ssize_t queue_atomic_write_unit_max_show(struct request_queue *q, + char *page) +{ + return queue_var_show(queue_atomic_write_unit_max_bytes(q), page); +} + static ssize_t queue_max_integrity_segments_show(struct request_queue *q, char *page) { return queue_var_show(q->limits.max_integrity_segments, (page)); @@ -585,6 +609,11 @@ QUEUE_RO_ENTRY(queue_discard_max_hw, "discard_max_hw_bytes"); QUEUE_RW_ENTRY(queue_discard_max, "discard_max_bytes"); QUEUE_RO_ENTRY(queue_discard_zeroes_data, "discard_zeroes_data");

+QUEUE_RO_ENTRY(queue_atomic_write_max_bytes, "atomic_write_max_bytes"); +QUEUE_RO_ENTRY(queue_atomic_write_boundary, "atomic_write_boundary_bytes"); +QUEUE_RO_ENTRY(queue_atomic_write_unit_max, "atomic_write_unit_max_bytes"); +QUEUE_RO_ENTRY(queue_atomic_write_unit_min, "atomic_write_unit_min_bytes"); + QUEUE_RO_ENTRY(queue_write_same_max, "write_same_max_bytes"); QUEUE_RO_ENTRY(queue_write_zeroes_max, "write_zeroes_max_bytes"); QUEUE_RO_ENTRY(queue_zone_append_max, "zone_append_max_bytes"); @@ -639,6 +668,10 @@ static struct attribute *queue_attrs[] = { &queue_discard_max_entry.attr, &queue_discard_max_hw_entry.attr, &queue_discard_zeroes_data_entry.attr, + &queue_atomic_write_max_bytes_entry.attr, + &queue_atomic_write_boundary_entry.attr, + &queue_atomic_write_unit_min_entry.attr, + &queue_atomic_write_unit_max_entry.attr, &queue_write_same_max_entry.attr, &queue_write_zeroes_max_entry.attr, &queue_zone_append_max_entry.attr, diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index 1853ec569b72..996e03d50f41 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -133,6 +133,11 @@ typedef u8 __bitwise blk_status_t; */ #define BLK_STS_ZONE_ACTIVE_RESOURCE ((__force blk_status_t)16)

+/* + * Invalid size or alignment. + */ +#define BLK_STS_INVAL ((__force blk_status_t)19) + /** * blk_path_error - returns true if error may be path related * @error: status the request was completed with @@ -421,6 +426,7 @@ enum req_flag_bits { /* for driver use */ __REQ_DRV, __REQ_SWAP, /* swapping request. */ + __REQ_ATOMIC, /* for atomic write operations */ __REQ_NR_BITS, /* stops here */ };

@@ -445,6 +451,7 @@ enum req_flag_bits {

#define REQ_DRV (1ULL << __REQ_DRV) #define REQ_SWAP (1ULL << __REQ_SWAP) +#define REQ_ATOMIC (1ULL << __REQ_ATOMIC)

#define REQ_FAILFAST_MASK \ (REQ_FAILFAST_DEV | REQ_FAILFAST_TRANSPORT | REQ_FAILFAST_DRIVER) diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 2d6747877f7c..a53e70a6aeec 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -346,6 +346,16 @@ struct queue_limits { unsigned int discard_granularity; unsigned int discard_alignment;

+ /* atomic write limits */ + unsigned int atomic_write_hw_max; + unsigned int atomic_write_max_sectors; + unsigned int atomic_write_hw_boundary; + unsigned int atomic_write_hw_unit_min; + unsigned int atomic_write_unit_min; + unsigned int atomic_write_hw_unit_max; + unsigned int atomic_write_unit_max; + + unsigned short max_segments; unsigned short max_integrity_segments; unsigned short max_discard_segments; @@ -1097,6 +1107,9 @@ static inline unsigned int blk_queue_get_max_sectors(struct request *rq) if (unlikely(op == REQ_OP_WRITE_ZEROES)) return q->limits.max_write_zeroes_sectors;

+ if (rq->cmd_flags & REQ_ATOMIC) + return q->limits.atomic_write_max_sectors; + return q->limits.max_sectors; }

@@ -1187,6 +1200,14 @@ extern void blk_queue_max_zone_append_sectors(struct request_queue *q, extern void blk_queue_physical_block_size(struct request_queue *, unsigned int); extern void blk_queue_alignment_offset(struct request_queue *q, unsigned int alignment); +void blk_queue_atomic_write_max_bytes(struct request_queue *q, + unsigned int bytes); +void blk_queue_atomic_write_boundary_bytes(struct request_queue *q, + unsigned int bytes); +void blk_queue_atomic_write_unit_max_bytes(struct request_queue *q, + unsigned int bytes); +void blk_queue_atomic_write_unit_min_bytes(struct request_queue *q, + unsigned int bytes); void blk_queue_update_readahead(struct request_queue *q); extern void blk_limits_io_min(struct queue_limits *limits, unsigned int min); extern void blk_queue_io_min(struct request_queue *q, unsigned int min); @@ -1649,6 +1670,30 @@ static inline unsigned int bdev_max_active_zones(struct block_device *bdev) return 0; }

+static inline unsigned int +queue_atomic_write_unit_max_bytes(const struct request_queue *q) +{ + return q->limits.atomic_write_unit_max; +} + +static inline unsigned int +queue_atomic_write_unit_min_bytes(const struct request_queue *q) +{ + return q->limits.atomic_write_unit_min; +} + +static inline unsigned int +queue_atomic_write_boundary_bytes(const struct request_queue *q) +{ + return q->limits.atomic_write_hw_boundary; +} + +static inline unsigned int +queue_atomic_write_max_bytes(const struct request_queue *q) +{ + return q->limits.atomic_write_max_sectors << SECTOR_SHIFT; +} + static inline int queue_dma_alignment(const struct request_queue *q) { return q ? q->dma_alignment : 511; @@ -2102,4 +2147,24 @@ int fsync_bdev(struct block_device *bdev); struct super_block *freeze_bdev(struct block_device *bdev); int thaw_bdev(struct block_device *bdev, struct super_block *sb);

+static inline bool bdev_can_atomic_write(struct block_device *bdev) +{ + struct request_queue *bd_queue = bdev_get_queue(bdev); + struct queue_limits *limits = &bd_queue->limits; + + if (!limits->atomic_write_unit_min) + return false; + + if (bdev_is_partition(bdev)) { + sector_t bd_start_sect = bdev->bd_part->start_sect; + unsigned int alignment = + max(limits->atomic_write_unit_min, + limits->atomic_write_hw_boundary); + if (!IS_ALIGNED(bd_start_sect, alignment)) + return false; + } + + return true; +} + #endif /* _LINUX_BLKDEV_H */

From: John Garry john.g.garry@oracle.com

maillist inclusion category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I9VTE3 CVE: NA

Reference: https://lore.kernel.org/all/20240326133813.3224593-1-john.g.garry@oracle.com...

--------------------------------

Support atomic writes by submitting a single BIO with the REQ_ATOMIC set.

It must be ensured that the atomic write adheres to its rules, like naturally aligned offset, so call blkdev_dio_invalid() -> blkdev_atomic_write_valid() [with renaming blkdev_dio_unaligned() to blkdev_dio_invalid()] for this purpose. The BIO submission path currently checks for atomic writes which are too large, so no need to check here.

In blkdev_direct_IO(), if the nr_pages exceeds BIO_MAX_VECS, then we cannot produce a single BIO, so error in this case.

Finally set FMODE_CAN_ATOMIC_WRITE when the bdev can support atomic writes and the associated file flag is for O_DIRECT.

Signed-off-by: John Garry john.g.garry@oracle.com Signed-off-by: Long Li leo.lilong@huawei.com --- fs/block_dev.c | 30 +++++++++++++++++++++++++++++- 1 file changed, 29 insertions(+), 1 deletion(-)

diff --git a/fs/block_dev.c b/fs/block_dev.c index 749e36a49796..404c10c849a7 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -272,6 +272,9 @@ __blkdev_direct_IO_simple(struct kiocb *iocb, struct iov_iter *iter, bio.bi_end_io = blkdev_bio_end_io_simple; bio.bi_ioprio = iocb->ki_ioprio;

+ if (iocb->ki_flags & IOCB_ATOMIC) + bio.bi_opf |= REQ_ATOMIC; + ret = bio_iov_iter_get_pages(&bio, iter); if (unlikely(ret)) goto out; @@ -452,6 +455,10 @@ __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter, int nr_pages) bio->bi_opf = dio_bio_write_op(iocb); task_io_account_write(bio->bi_iter.bi_size); } + + if (iocb->ki_flags & IOCB_ATOMIC) + bio->bi_opf |= REQ_ATOMIC; + if (iocb->ki_flags & IOCB_NOWAIT) bio->bi_opf |= REQ_NOWAIT;

@@ -521,14 +528,30 @@ __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter, int nr_pages) return ret; }

+static bool blkdev_atomic_write_valid(struct block_device *bdev, loff_t pos, + struct iov_iter *iter) +{ + struct request_queue *q = bdev_get_queue(bdev); + unsigned int min_bytes = queue_atomic_write_unit_min_bytes(q); + unsigned int max_bytes = queue_atomic_write_unit_max_bytes(q); + + return generic_atomic_write_valid(pos, iter, min_bytes, max_bytes); +} + static ssize_t blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter) { int nr_pages; + bool is_atomic = iocb->ki_flags & IOCB_ATOMIC; + struct block_device *bdev = I_BDEV(iocb->ki_filp->f_mapping->host);

nr_pages = iov_iter_npages(iter, BIO_MAX_PAGES + 1); if (!nr_pages) return 0; + + if (is_atomic && !blkdev_atomic_write_valid(bdev, iocb->ki_pos, iter)) + return -EINVAL; + if (is_sync_kiocb(iocb) && nr_pages <= BIO_MAX_PAGES) return __blkdev_direct_IO_simple(iocb, iter, nr_pages);

@@ -1895,6 +1918,7 @@ EXPORT_SYMBOL(blkdev_get_by_dev); static int blkdev_open(struct inode * inode, struct file * filp) { struct block_device *bdev; + int err;

/* * Preserve backwards compatibility and allow large file access @@ -1920,7 +1944,11 @@ static int blkdev_open(struct inode * inode, struct file * filp) filp->f_mapping = bdev->bd_inode->i_mapping; filp->f_wb_err = filemap_sample_wb_err(filp->f_mapping);

- return blkdev_get(bdev, filp->f_mode, filp); + err = blkdev_get(bdev, filp->f_mode, filp); + if (!err && bdev_can_atomic_write(bdev) && filp->f_flags & O_DIRECT) + filp->f_mode |= FMODE_CAN_ATOMIC_WRITE; + + return err; }

static void __blkdev_put(struct block_device *bdev, fmode_t mode, int for_part)

From: "Darrick J. Wong" djwong@kernel.org

maillist inclusion category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I9VTE3 CVE: NA

Reference: https://lore.kernel.org/all/20240326133813.3224593-1-john.g.garry@oracle.com...

--------------------------------

Add a new inode flag to require that all file data extent mappings must be aligned (both the file offset range and the allocated space itself) to the extent size hint. Having a separate COW extent size hint is no longer allowed.

The goal here is to enable sysadmins and users to mandate that all space mappings in a file must have a startoff/blockcount that are aligned to (say) a 2MB alignment and that the startblock/blockcount will follow the same alignment.

jpg: Enforce extsize is a power-of-2 for forcealign Signed-off-by: "Darrick J. Wong" djwong@kernel.org Co-developed-by: John Garry john.g.garry@oracle.com Signed-off-by: John Garry john.g.garry@oracle.com Signed-off-by: Long Li leo.lilong@huawei.com --- fs/xfs/libxfs/xfs_format.h | 6 +++++- fs/xfs/libxfs/xfs_inode_buf.c | 40 +++++++++++++++++++++++++++++++++++ fs/xfs/libxfs/xfs_inode_buf.h | 3 +++ fs/xfs/libxfs/xfs_sb.c | 2 ++ fs/xfs/xfs_inode.c | 13 ++++++++++++ fs/xfs/xfs_inode.h | 4 ++++ fs/xfs/xfs_ioctl.c | 32 ++++++++++++++++++++++++++++ fs/xfs/xfs_mount.h | 2 ++ fs/xfs/xfs_super.c | 5 +++++ include/uapi/linux/fs.h | 2 ++ 10 files changed, 108 insertions(+), 1 deletion(-)

diff --git a/fs/xfs/libxfs/xfs_format.h b/fs/xfs/libxfs/xfs_format.h index 54832df8540f..fb537bb7dba5 100644 --- a/fs/xfs/libxfs/xfs_format.h +++ b/fs/xfs/libxfs/xfs_format.h @@ -353,6 +353,7 @@ xfs_sb_has_compat_feature( #define XFS_SB_FEAT_RO_COMPAT_RMAPBT (1 << 1) /* reverse map btree */ #define XFS_SB_FEAT_RO_COMPAT_REFLINK (1 << 2) /* reflinked files */ #define XFS_SB_FEAT_RO_COMPAT_INOBTCNT (1 << 3) /* inobt block counts */ +#define XFS_SB_FEAT_RO_COMPAT_FORCEALIGN (1 << 30) /* aligned file data extents */ #define XFS_SB_FEAT_RO_COMPAT_ALL \ (XFS_SB_FEAT_RO_COMPAT_FINOBT | \ XFS_SB_FEAT_RO_COMPAT_RMAPBT | \ @@ -972,15 +973,18 @@ static inline void xfs_dinode_put_rdev(struct xfs_dinode *dip, xfs_dev_t rdev) #define XFS_DIFLAG2_REFLINK_BIT 1 /* file's blocks may be shared */ #define XFS_DIFLAG2_COWEXTSIZE_BIT 2 /* copy on write extent size hint */ #define XFS_DIFLAG2_BIGTIME_BIT 3 /* big timestamps */ +/* data extent mappings for regular files must be aligned to extent size hint */ +#define XFS_DIFLAG2_FORCEALIGN_BIT 5

#define XFS_DIFLAG2_DAX (1 << XFS_DIFLAG2_DAX_BIT) #define XFS_DIFLAG2_REFLINK (1 << XFS_DIFLAG2_REFLINK_BIT) #define XFS_DIFLAG2_COWEXTSIZE (1 << XFS_DIFLAG2_COWEXTSIZE_BIT) #define XFS_DIFLAG2_BIGTIME (1 << XFS_DIFLAG2_BIGTIME_BIT) +#define XFS_DIFLAG2_FORCEALIGN (1 << XFS_DIFLAG2_FORCEALIGN_BIT)

#define XFS_DIFLAG2_ANY \ (XFS_DIFLAG2_DAX | XFS_DIFLAG2_REFLINK | XFS_DIFLAG2_COWEXTSIZE | \ - XFS_DIFLAG2_BIGTIME) + XFS_DIFLAG2_BIGTIME | XFS_DIFLAG2_FORCEALIGN)

static inline bool xfs_dinode_has_bigtime(const struct xfs_dinode *dip) { diff --git a/fs/xfs/libxfs/xfs_inode_buf.c b/fs/xfs/libxfs/xfs_inode_buf.c index 0970ae3fe538..dd9e5de65d52 100644 --- a/fs/xfs/libxfs/xfs_inode_buf.c +++ b/fs/xfs/libxfs/xfs_inode_buf.c @@ -574,6 +574,14 @@ xfs_dinode_verify( !xfs_has_bigtime(mp)) return __this_address;

+ if (flags2 & XFS_DIFLAG2_FORCEALIGN) { + fa = xfs_inode_validate_forcealign(mp, mode, flags, + be32_to_cpu(dip->di_extsize), + be32_to_cpu(dip->di_cowextsize)); + if (fa) + return fa; + } + return NULL; }

@@ -699,3 +707,35 @@ xfs_inode_validate_cowextsize(

return NULL; } + +/* Validate the forcealign inode flag */ +xfs_failaddr_t +xfs_inode_validate_forcealign( + struct xfs_mount *mp, + uint16_t mode, + uint16_t flags, + uint32_t extsize, + uint32_t cowextsize) +{ + /* superblock rocompat feature flag */ + if (!xfs_has_forcealign(mp)) + return __this_address; + + /* Only regular files and directories */ + if (!S_ISDIR(mode) && !S_ISREG(mode)) + return __this_address; + + /* Doesn't apply to realtime files */ + if (flags & XFS_DIFLAG_REALTIME) + return __this_address; + + /* Requires a non-zero power-of-2 extent size hint */ + if (extsize == 0 || !is_power_of_2(extsize)) + return __this_address; + + /* Requires no cow extent size hint */ + if (cowextsize != 0) + return __this_address; + + return NULL; +} diff --git a/fs/xfs/libxfs/xfs_inode_buf.h b/fs/xfs/libxfs/xfs_inode_buf.h index 05c3640e135a..1bcf1415a4b5 100644 --- a/fs/xfs/libxfs/xfs_inode_buf.h +++ b/fs/xfs/libxfs/xfs_inode_buf.h @@ -62,6 +62,9 @@ xfs_failaddr_t xfs_inode_validate_extsize(struct xfs_mount *mp, xfs_failaddr_t xfs_inode_validate_cowextsize(struct xfs_mount *mp, uint32_t cowextsize, uint16_t mode, uint16_t flags, uint64_t flags2); +xfs_failaddr_t xfs_inode_validate_forcealign(struct xfs_mount *mp, + uint16_t mode, uint16_t flags, uint32_t extsize, + uint32_t cowextsize);

static inline uint64_t xfs_inode_encode_bigtime(struct timespec64 tv) { diff --git a/fs/xfs/libxfs/xfs_sb.c b/fs/xfs/libxfs/xfs_sb.c index c099ccf2787d..a016ba008019 100644 --- a/fs/xfs/libxfs/xfs_sb.c +++ b/fs/xfs/libxfs/xfs_sb.c @@ -116,6 +116,8 @@ xfs_sb_version_to_features( features |= XFS_FEAT_REFLINK; if (sbp->sb_features_ro_compat & XFS_SB_FEAT_RO_COMPAT_INOBTCNT) features |= XFS_FEAT_INOBTCNT; + if (sbp->sb_features_ro_compat & XFS_SB_FEAT_RO_COMPAT_FORCEALIGN) + features |= XFS_FEAT_FORCEALIGN; if (sbp->sb_features_incompat & XFS_SB_FEAT_INCOMPAT_FTYPE) features |= XFS_FEAT_FTYPE; if (sbp->sb_features_incompat & XFS_SB_FEAT_INCOMPAT_SPINODES) diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c index 268bbc2d978b..c841a086cbce 100644 --- a/fs/xfs/xfs_inode.c +++ b/fs/xfs/xfs_inode.c @@ -643,6 +643,8 @@ _xfs_dic2xflags( flags |= FS_XFLAG_DAX; if (di_flags2 & XFS_DIFLAG2_COWEXTSIZE) flags |= FS_XFLAG_COWEXTSIZE; + if (di_flags2 & XFS_DIFLAG2_FORCEALIGN) + flags |= FS_XFLAG_FORCEALIGN; }

if (has_attr) @@ -759,6 +761,17 @@ xfs_inode_inherit_flags2( } if (pip->i_d.di_flags2 & XFS_DIFLAG2_DAX) ip->i_d.di_flags2 |= XFS_DIFLAG2_DAX; + if (pip->i_d.di_flags2 & XFS_DIFLAG2_FORCEALIGN) + ip->i_d.di_flags2 |= XFS_DIFLAG2_FORCEALIGN; + + if (ip->i_d.di_flags2 & XFS_DIFLAG2_FORCEALIGN) { + xfs_failaddr_t failaddr; + failaddr = xfs_inode_validate_forcealign(ip->i_mount, + VFS_I(ip)->i_mode, ip->i_d.di_flags, ip->i_d.di_extsize, + ip->i_d.di_cowextsize); + if (failaddr) + ip->i_d.di_flags2 &= ~XFS_DIFLAG2_FORCEALIGN; + } }

/* diff --git a/fs/xfs/xfs_inode.h b/fs/xfs/xfs_inode.h index b552daae323f..53a2b90486f6 100644 --- a/fs/xfs/xfs_inode.h +++ b/fs/xfs/xfs_inode.h @@ -268,6 +268,10 @@ static inline bool xfs_inode_has_bigtime(struct xfs_inode *ip) return ip->i_d.di_flags2 & XFS_DIFLAG2_BIGTIME; }

+static inline bool xfs_inode_forcealign(struct xfs_inode *ip) +{ + return ip->i_d.di_flags2 & XFS_DIFLAG2_FORCEALIGN; +} /* * Return the buftarg used for data allocations on a given inode. */ diff --git a/fs/xfs/xfs_ioctl.c b/fs/xfs/xfs_ioctl.c index 2337eb272235..a53038b8f736 100644 --- a/fs/xfs/xfs_ioctl.c +++ b/fs/xfs/xfs_ioctl.c @@ -1198,6 +1198,8 @@ xfs_flags2diflags2( di_flags2 |= XFS_DIFLAG2_DAX; if (xflags & FS_XFLAG_COWEXTSIZE) di_flags2 |= XFS_DIFLAG2_COWEXTSIZE; + if (xflags & FS_XFLAG_FORCEALIGN) + di_flags2 |= XFS_DIFLAG2_FORCEALIGN;

return di_flags2; } @@ -1236,6 +1238,22 @@ xfs_ioctl_setattr_xflags( if (di_flags2 && !xfs_has_v3inodes(mp)) return -EINVAL;

+ /* + * Force-align requires a nonzero extent size hint and a zero cow + * extent size hint. It doesn't apply to realtime files. + */ + if (fa->fsx_xflags & FS_XFLAG_FORCEALIGN) { + if (!xfs_has_forcealign(mp)) + return -EINVAL; + if (fa->fsx_xflags & FS_XFLAG_COWEXTSIZE) + return -EINVAL; + if (!(fa->fsx_xflags & (FS_XFLAG_EXTSIZE | + FS_XFLAG_EXTSZINHERIT))) + return -EINVAL; + if (fa->fsx_xflags & FS_XFLAG_REALTIME) + return -EINVAL; + } + ip->i_d.di_flags = xfs_flags2diflags(ip, fa->fsx_xflags); ip->i_d.di_flags2 = di_flags2;

@@ -1339,6 +1357,9 @@ xfs_ioctl_setattr_check_extsize( struct xfs_mount *mp = ip->i_mount; xfs_extlen_t size; xfs_fsblock_t extsize_fsb; + xfs_failaddr_t failaddr; + uint16_t new_diflags; + uint16_t new_diflags2;

if (S_ISREG(VFS_I(ip)->i_mode) && ip->i_df.if_nextents && ((ip->i_d.di_extsize << mp->m_sb.sb_blocklog) != fa->fsx_extsize)) @@ -1363,6 +1384,17 @@ xfs_ioctl_setattr_check_extsize( if (fa->fsx_extsize % size) return -EINVAL;

+ new_diflags = xfs_flags2diflags(ip, fa->fsx_xflags); + new_diflags2 = xfs_flags2diflags2(ip, fa->fsx_xflags); + if (new_diflags2 & XFS_DIFLAG2_FORCEALIGN) { + failaddr = xfs_inode_validate_forcealign(ip->i_mount, + VFS_I(ip)->i_mode, new_diflags, + XFS_B_TO_FSB(mp, fa->fsx_extsize), + XFS_B_TO_FSB(mp, fa->fsx_cowextsize)); + if (failaddr) + return -EINVAL; + } + return 0; }

diff --git a/fs/xfs/xfs_mount.h b/fs/xfs/xfs_mount.h index 21547ff97b5a..bc0ed9247f47 100644 --- a/fs/xfs/xfs_mount.h +++ b/fs/xfs/xfs_mount.h @@ -274,6 +274,7 @@ typedef struct xfs_mount { #define XFS_FEAT_INOBTCNT (1ULL << 23) /* inobt block counts */ #define XFS_FEAT_BIGTIME (1ULL << 24) /* large timestamps */ #define XFS_FEAT_NEEDSREPAIR (1ULL << 25) /* needs xfs_repair */ +#define XFS_FEAT_FORCEALIGN (1ULL << 27) /* aligned file data extents */

/* Mount features */ #define XFS_FEAT_NOATTR2 (1ULL << 48) /* disable attr2 creation */ @@ -336,6 +337,7 @@ __XFS_HAS_FEAT(realtime, REALTIME) __XFS_HAS_FEAT(inobtcounts, INOBTCNT) __XFS_HAS_FEAT(bigtime, BIGTIME) __XFS_HAS_FEAT(needsrepair, NEEDSREPAIR) +__XFS_HAS_FEAT(forcealign, FORCEALIGN)

/* * Mount features diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c index 502fb08bfd38..cc7962438f26 100644 --- a/fs/xfs/xfs_super.c +++ b/fs/xfs/xfs_super.c @@ -1639,6 +1639,7 @@ xfs_fc_fill_super( "DAX unsupported by block device. Turning off DAX."); xfs_mount_set_dax_mode(mp, XFS_DAX_NEVER); } + if (xfs_has_reflink(mp)) { xfs_alert(mp, "DAX and reflink cannot be used together!"); @@ -1657,6 +1658,10 @@ xfs_fc_fill_super( } }

+ if (xfs_has_forcealign(mp)) + xfs_warn(mp, +"EXPERIMENTAL forced data extent alignment feature in use. Use at your own risk!"); + if (xfs_has_reflink(mp)) { if (mp->m_sb.sb_rblocks) { xfs_alert(mp, diff --git a/include/uapi/linux/fs.h b/include/uapi/linux/fs.h index 78f4091ed188..822c9f4c4ce3 100644 --- a/include/uapi/linux/fs.h +++ b/include/uapi/linux/fs.h @@ -140,6 +140,8 @@ struct fsxattr { #define FS_XFLAG_FILESTREAM 0x00004000 /* use filestream allocator */ #define FS_XFLAG_DAX 0x00008000 /* use DAX for IO */ #define FS_XFLAG_COWEXTSIZE 0x00010000 /* CoW extent size allocator hint */ +/* data extent mappings for regular files must be aligned to extent size hint */ +#define FS_XFLAG_FORCEALIGN 0x00020000 #define FS_XFLAG_HASATTR 0x80000000 /* no DIFLAG for this */

/* the read-only stuff doesn't really belong here, but any other place is

From: "Darrick J. Wong" djwong@kernel.org

maillist inclusion category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I9VTE3 CVE: NA

Reference: https://lore.kernel.org/all/20240326133813.3224593-1-john.g.garry@oracle.com...

--------------------------------

The existing extsize hint code already did the work of expanding file range mapping requests so that the range is aligned to the hint value. Now add the code we need to guarantee that the space allocations are also always aligned.

XXX: still need to check all this with reflink

Signed-off-by: "Darrick J. Wong" djwong@kernel.org Co-developed-by: John Garry john.g.garry@oracle.com Signed-off-by: John Garry john.g.garry@oracle.com Signed-off-by: Long Li leo.lilong@huawei.com --- fs/xfs/libxfs/xfs_bmap.c | 16 ++++++++++++++-- fs/xfs/xfs_iomap.c | 4 +++- 2 files changed, 17 insertions(+), 3 deletions(-)

diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c index 15e9e335d167..064ce4588d4a 100644 --- a/fs/xfs/libxfs/xfs_bmap.c +++ b/fs/xfs/libxfs/xfs_bmap.c @@ -3487,6 +3487,18 @@ xfs_bmap_btalloc( args.fsbno = ap->blkno; args.oinfo = XFS_RMAP_OINFO_SKIP_UPDATE;

+ /* + * xfs_get_cowextsz_hint() returns extsz_hint for when forcealign is + * set as forcealign and cowextsz_hint are mutually exclusive + */ + if (xfs_inode_forcealign(ap->ip) && align) { + args.alignment = align; + if (stripe_align == 0 || stripe_align % align) + stripe_align = align; + } else { + args.alignment = 1; + } + /* Trim the allocation back to the maximum an AG can fit. */ args.maxlen = min(ap->length, mp->m_ag_max_usable); blen = 0; @@ -3577,7 +3589,6 @@ xfs_bmap_btalloc( args.minalignslop = 0; } } else { - args.alignment = 1; args.minalignslop = 0; } args.postallocs = 1; @@ -3604,7 +3615,8 @@ xfs_bmap_btalloc( if ((error = xfs_alloc_vextent(&args))) return error; } - if (isaligned && args.fsbno == NULLFSBLOCK) { + + if (isaligned && args.fsbno == NULLFSBLOCK && args.alignment <= 1) { /* * allocation failed, so turn off alignment and * try again. diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c index 76285db4aaec..af2fe2e2bd4b 100644 --- a/fs/xfs/xfs_iomap.c +++ b/fs/xfs/xfs_iomap.c @@ -167,7 +167,9 @@ xfs_eof_alignment( * If mounted with the "-o swalloc" option the alignment is * increased from the strip unit size to the stripe width. */ - if (mp->m_swidth && xfs_has_swalloc(mp)) + if (xfs_inode_forcealign(ip)) + align = xfs_get_extsz_hint(ip); + else if (mp->m_swidth && xfs_has_swalloc(mp)) align = mp->m_swidth; else if (mp->m_dalign) align = mp->m_dalign;

From: John Garry john.g.garry@oracle.com

maillist inclusion category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I9VTE3 CVE: NA

Reference: https://lore.kernel.org/all/20240326133813.3224593-1-john.g.garry@oracle.com...

--------------------------------

For FS_XFLAG_FORCEALIGN support, we want to treat any sub-extent IO like sub-fsblock DIO, in that we will zero the sub-extent when the mapping is unwritten.

This will be important for atomic writes support, in that atomically writing over a partially written extent would mean that we would need to do the unwritten extent conversion write separately, and the write could no longer be atomic.

It is the task of the FS to set iomap.extent_shift per iter to indicate sub-extent zeroing required.

Maybe a macro like i_blocksize() should be introduced for extent sizes, instead of using extent_shift.

Signed-off-by: John Garry john.g.garry@oracle.com Signed-off-by: Long Li leo.lilong@huawei.com --- fs/iomap/direct-io.c | 23 ++++++++++++++++------- include/linux/iomap.h | 1 + 2 files changed, 17 insertions(+), 7 deletions(-)

diff --git a/fs/iomap/direct-io.c b/fs/iomap/direct-io.c index 892a4f8109e5..6cdacdd141f6 100644 --- a/fs/iomap/direct-io.c +++ b/fs/iomap/direct-io.c @@ -210,15 +210,22 @@ iomap_dio_zero(struct iomap_dio *dio, struct iomap *iomap, loff_t pos, struct page *page = ZERO_PAGE(0); int flags = REQ_SYNC | REQ_IDLE; struct bio *bio; + unsigned size; + unsigned nr_pages = (len + PAGE_SIZE - 1) >> PAGE_SHIFT;

- bio = bio_alloc(GFP_KERNEL, 1); + bio = bio_alloc(GFP_KERNEL, nr_pages); bio_set_dev(bio, iomap->bdev); bio->bi_iter.bi_sector = iomap_sector(iomap, pos); bio->bi_private = dio; bio->bi_end_io = iomap_dio_bio_end_io;

- get_page(page); - __bio_add_page(bio, page, len, 0); + while (len > 0) { + size = len > PAGE_SIZE ? PAGE_SIZE : len; + get_page(page); + __bio_add_page(bio, page, size, 0); + len -= size; + pos += size; + } bio_set_op_attrs(bio, REQ_OP_WRITE, flags); iomap_dio_submit_bio(dio, iomap, bio, pos); } @@ -228,7 +235,7 @@ iomap_dio_bio_actor(struct inode *inode, loff_t pos, loff_t length, struct iomap_dio *dio, struct iomap *iomap) { unsigned int blkbits = blksize_bits(bdev_logical_block_size(iomap->bdev)); - unsigned int fs_block_size = i_blocksize(inode), pad; + unsigned int zeroing_size, pad; unsigned int align = iov_iter_alignment(dio->submit.iter); struct bio *bio; bool need_zeroout = false; @@ -237,6 +244,8 @@ iomap_dio_bio_actor(struct inode *inode, loff_t pos, loff_t length, size_t copied = 0; size_t orig_count;

+ zeroing_size = i_blocksize(inode) << iomap->extent_shift; + if ((pos | length | align) & ((1 << blkbits) - 1)) return -EINVAL;

@@ -280,7 +289,7 @@ iomap_dio_bio_actor(struct inode *inode, loff_t pos, loff_t length,

if (need_zeroout) { /* zero out from the start of the block to the write offset */ - pad = pos & (fs_block_size - 1); + pad = pos & (zeroing_size - 1); if (pad) iomap_dio_zero(dio, iomap, pos - pad, pad); } @@ -345,9 +354,9 @@ iomap_dio_bio_actor(struct inode *inode, loff_t pos, loff_t length, if (need_zeroout || ((dio->flags & IOMAP_DIO_WRITE) && pos >= i_size_read(inode))) { /* zero out from the end of the write to the end of the block */ - pad = pos & (fs_block_size - 1); + pad = pos & (zeroing_size - 1); if (pad) - iomap_dio_zero(dio, iomap, pos, fs_block_size - pad); + iomap_dio_zero(dio, iomap, pos, zeroing_size - pad); } out: /* Undo iter limitation to current extent */ diff --git a/include/linux/iomap.h b/include/linux/iomap.h index 0965d5f12858..d14a729d40ce 100644 --- a/include/linux/iomap.h +++ b/include/linux/iomap.h @@ -93,6 +93,7 @@ struct iomap { u64 length; /* length of mapping, bytes */ u16 type; /* type of mapping */ u16 flags; /* flags for mapping */ + unsigned int extent_shift; struct block_device *bdev; /* block device for I/O */ struct dax_device *dax_dev; /* dax_dev for dax operations */ void *inline_data;

From: John Garry john.g.garry@oracle.com

maillist inclusion category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I9VTE3 CVE: NA

Reference: https://lore.kernel.org/all/20240326133813.3224593-1-john.g.garry@oracle.com...

--------------------------------

Add a flag indicating that a regular file is enabled for atomic writes.

This is a file attribute that mirrors an ondisk inode flag. Actual support for untorn file writes (for now) depends on both the iflag and the underlying storage devices, which we can only really check at statx and pwritev2() time. This is the same story as FS_XFLAG_DAX, which signals to the fs that we should try to enable the fsdax IO path on the file (instead of the regular page cache), but applications have to query STAT_ATTR_DAX to find out if they really got that IO path.

Signed-off-by: John Garry john.g.garry@oracle.com Signed-off-by: Long Li leo.lilong@huawei.com --- include/uapi/linux/fs.h | 1 + 1 file changed, 1 insertion(+)

diff --git a/include/uapi/linux/fs.h b/include/uapi/linux/fs.h index 822c9f4c4ce3..ca8b6f6c479d 100644 --- a/include/uapi/linux/fs.h +++ b/include/uapi/linux/fs.h @@ -142,6 +142,7 @@ struct fsxattr { #define FS_XFLAG_COWEXTSIZE 0x00010000 /* CoW extent size allocator hint */ /* data extent mappings for regular files must be aligned to extent size hint */ #define FS_XFLAG_FORCEALIGN 0x00020000 +#define FS_XFLAG_ATOMICWRITES 0x00040000 /* atomic writes enabled */ #define FS_XFLAG_HASATTR 0x80000000 /* no DIFLAG for this */

/* the read-only stuff doesn't really belong here, but any other place is

From: John Garry john.g.garry@oracle.com

maillist inclusion category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I9VTE3 CVE: NA

Reference: https://lore.kernel.org/all/20240326133813.3224593-1-john.g.garry@oracle.com...

--------------------------------

Add initial support for FS_XFLAG_ATOMICWRITES for forcealign enaabled.

Current kernel support for atomic writes is based on HW support (for atomic writes). As such, it is required to ensure extent alignment with atomic_write_unit_max so that an atomic write can result in a single HW-compliant IO operation.

rtvol also guarantees extent alignment, but we are basing support initially on forcealign, which is not supported for rtvol yet.

Signed-off-by: John Garry john.g.garry@oracle.com Signed-off-by: Long Li leo.lilong@huawei.com --- fs/xfs/libxfs/xfs_format.h | 12 +++++++++--- fs/xfs/libxfs/xfs_sb.c | 2 ++ fs/xfs/xfs_inode.c | 2 ++ fs/xfs/xfs_inode.h | 6 ++++++ fs/xfs/xfs_ioctl.c | 15 +++++++++++++-- fs/xfs/xfs_mount.h | 3 +++ fs/xfs/xfs_super.c | 4 ++++ 7 files changed, 39 insertions(+), 5 deletions(-)

diff --git a/fs/xfs/libxfs/xfs_format.h b/fs/xfs/libxfs/xfs_format.h index 71629d6dfd1b..8e4d49595884 100644 --- a/fs/xfs/libxfs/xfs_format.h +++ b/fs/xfs/libxfs/xfs_format.h @@ -354,12 +354,16 @@ xfs_sb_has_compat_feature( #define XFS_SB_FEAT_RO_COMPAT_REFLINK (1 << 2) /* reflinked files */ #define XFS_SB_FEAT_RO_COMPAT_INOBTCNT (1 << 3) /* inobt block counts */ #define XFS_SB_FEAT_RO_COMPAT_FORCEALIGN (1 << 30) /* aligned file data extents */ +#define XFS_SB_FEAT_RO_COMPAT_ATOMICWRITES (1 << 31) /* atomicwrites enabled */ + #define XFS_SB_FEAT_RO_COMPAT_ALL \ (XFS_SB_FEAT_RO_COMPAT_FINOBT | \ XFS_SB_FEAT_RO_COMPAT_RMAPBT | \ XFS_SB_FEAT_RO_COMPAT_REFLINK| \ - XFS_SB_FEAT_RO_COMPAT_INOBTCNT | \ - XFS_SB_FEAT_RO_COMPAT_FORCEALIGN) + XFS_SB_FEAT_RO_COMPAT_INOBTCNT| \ + XFS_SB_FEAT_RO_COMPAT_FORCEALIGN| \ + XFS_SB_FEAT_RO_COMPAT_ATOMICWRITES) + #define XFS_SB_FEAT_RO_COMPAT_UNKNOWN ~XFS_SB_FEAT_RO_COMPAT_ALL static inline bool xfs_sb_has_ro_compat_feature( @@ -976,16 +980,18 @@ static inline void xfs_dinode_put_rdev(struct xfs_dinode *dip, xfs_dev_t rdev) #define XFS_DIFLAG2_BIGTIME_BIT 3 /* big timestamps */ /* data extent mappings for regular files must be aligned to extent size hint */ #define XFS_DIFLAG2_FORCEALIGN_BIT 5 +#define XFS_DIFLAG2_ATOMICWRITES_BIT 6

#define XFS_DIFLAG2_DAX (1 << XFS_DIFLAG2_DAX_BIT) #define XFS_DIFLAG2_REFLINK (1 << XFS_DIFLAG2_REFLINK_BIT) #define XFS_DIFLAG2_COWEXTSIZE (1 << XFS_DIFLAG2_COWEXTSIZE_BIT) #define XFS_DIFLAG2_BIGTIME (1 << XFS_DIFLAG2_BIGTIME_BIT) #define XFS_DIFLAG2_FORCEALIGN (1 << XFS_DIFLAG2_FORCEALIGN_BIT) +#define XFS_DIFLAG2_ATOMICWRITES (1 << XFS_DIFLAG2_ATOMICWRITES_BIT)

#define XFS_DIFLAG2_ANY \ (XFS_DIFLAG2_DAX | XFS_DIFLAG2_REFLINK | XFS_DIFLAG2_COWEXTSIZE | \ - XFS_DIFLAG2_BIGTIME | XFS_DIFLAG2_FORCEALIGN) + XFS_DIFLAG2_BIGTIME | XFS_DIFLAG2_FORCEALIGN | XFS_DIFLAG2_ATOMICWRITES)

static inline bool xfs_dinode_has_bigtime(const struct xfs_dinode *dip) { diff --git a/fs/xfs/libxfs/xfs_sb.c b/fs/xfs/libxfs/xfs_sb.c index a016ba008019..a4354504986c 100644 --- a/fs/xfs/libxfs/xfs_sb.c +++ b/fs/xfs/libxfs/xfs_sb.c @@ -118,6 +118,8 @@ xfs_sb_version_to_features( features |= XFS_FEAT_INOBTCNT; if (sbp->sb_features_ro_compat & XFS_SB_FEAT_RO_COMPAT_FORCEALIGN) features |= XFS_FEAT_FORCEALIGN; + if (sbp->sb_features_ro_compat & XFS_SB_FEAT_RO_COMPAT_ATOMICWRITES) + features |= XFS_FEAT_ATOMICWRITES; if (sbp->sb_features_incompat & XFS_SB_FEAT_INCOMPAT_FTYPE) features |= XFS_FEAT_FTYPE; if (sbp->sb_features_incompat & XFS_SB_FEAT_INCOMPAT_SPINODES) diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c index 368cd97ae04c..5fafc8f419cc 100644 --- a/fs/xfs/xfs_inode.c +++ b/fs/xfs/xfs_inode.c @@ -659,6 +659,8 @@ _xfs_dic2xflags( flags |= FS_XFLAG_COWEXTSIZE; if (di_flags2 & XFS_DIFLAG2_FORCEALIGN) flags |= FS_XFLAG_FORCEALIGN; + if (di_flags2 & XFS_DIFLAG2_ATOMICWRITES) + flags |= FS_XFLAG_ATOMICWRITES; }

if (has_attr) diff --git a/fs/xfs/xfs_inode.h b/fs/xfs/xfs_inode.h index 5d740f793782..b5b97be319e6 100644 --- a/fs/xfs/xfs_inode.h +++ b/fs/xfs/xfs_inode.h @@ -272,6 +272,12 @@ static inline bool xfs_inode_forcealign(struct xfs_inode *ip) { return ip->i_d.di_flags2 & XFS_DIFLAG2_FORCEALIGN; } + +static inline bool xfs_inode_atomicwrites(struct xfs_inode *ip) +{ + return ip->i_d.di_flags2 & XFS_DIFLAG2_ATOMICWRITES; +} + /* * Return the buftarg used for data allocations on a given inode. */ diff --git a/fs/xfs/xfs_ioctl.c b/fs/xfs/xfs_ioctl.c index a53038b8f736..e96ebea20991 100644 --- a/fs/xfs/xfs_ioctl.c +++ b/fs/xfs/xfs_ioctl.c @@ -1200,6 +1200,8 @@ xfs_flags2diflags2( di_flags2 |= XFS_DIFLAG2_COWEXTSIZE; if (xflags & FS_XFLAG_FORCEALIGN) di_flags2 |= XFS_DIFLAG2_FORCEALIGN; + if (xflags & FS_XFLAG_ATOMICWRITES) + di_flags2 |= XFS_DIFLAG2_ATOMICWRITES;

return di_flags2; } @@ -1212,10 +1214,12 @@ xfs_ioctl_setattr_xflags( { struct xfs_mount *mp = ip->i_mount; uint64_t di_flags2; + bool atomic_writes = fa->fsx_xflags & FS_XFLAG_ATOMICWRITES;

- /* Can't change realtime flag if any extents are allocated. */ + /* Can't change realtime or atomic flag if any extents are allocated. */ if ((ip->i_df.if_nextents || ip->i_delayed_blks) && - XFS_IS_REALTIME_INODE(ip) != (fa->fsx_xflags & FS_XFLAG_REALTIME)) + (XFS_IS_REALTIME_INODE(ip) != (fa->fsx_xflags & FS_XFLAG_REALTIME) || + atomic_writes != xfs_inode_atomicwrites(ip))) return -EINVAL;

/* If realtime flag is set then must have realtime device */ @@ -1254,6 +1258,13 @@ xfs_ioctl_setattr_xflags( return -EINVAL; }

+ if (atomic_writes) { + if (!xfs_has_atomicwrites(mp)) + return -EINVAL; + if (!(fa->fsx_xflags & FS_XFLAG_FORCEALIGN)) + return -EINVAL; + } + ip->i_d.di_flags = xfs_flags2diflags(ip, fa->fsx_xflags); ip->i_d.di_flags2 = di_flags2;

diff --git a/fs/xfs/xfs_mount.h b/fs/xfs/xfs_mount.h index bc0ed9247f47..888d6bf9bea7 100644 --- a/fs/xfs/xfs_mount.h +++ b/fs/xfs/xfs_mount.h @@ -275,6 +275,8 @@ typedef struct xfs_mount { #define XFS_FEAT_BIGTIME (1ULL << 24) /* large timestamps */ #define XFS_FEAT_NEEDSREPAIR (1ULL << 25) /* needs xfs_repair */ #define XFS_FEAT_FORCEALIGN (1ULL << 27) /* aligned file data extents */ +#define XFS_FEAT_ATOMICWRITES (1ULL << 28) /* atomic writes support */ +

/* Mount features */ #define XFS_FEAT_NOATTR2 (1ULL << 48) /* disable attr2 creation */ @@ -338,6 +340,7 @@ __XFS_HAS_FEAT(inobtcounts, INOBTCNT) __XFS_HAS_FEAT(bigtime, BIGTIME) __XFS_HAS_FEAT(needsrepair, NEEDSREPAIR) __XFS_HAS_FEAT(forcealign, FORCEALIGN) +__XFS_HAS_FEAT(atomicwrites, ATOMICWRITES)

/* * Mount features diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c index cc7962438f26..d43f76a4b99a 100644 --- a/fs/xfs/xfs_super.c +++ b/fs/xfs/xfs_super.c @@ -1662,6 +1662,10 @@ xfs_fc_fill_super( xfs_warn(mp, "EXPERIMENTAL forced data extent alignment feature in use. Use at your own risk!");

+ if (xfs_has_atomicwrites(mp)) + xfs_warn(mp, +"EXPERIMENTAL atomicwrites feature in use. Use at your own risk!"); + if (xfs_has_reflink(mp)) { if (mp->m_sb.sb_rblocks) { xfs_alert(mp,

From: John Garry john.g.garry@oracle.com

maillist inclusion category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I9VTE3 CVE: NA

Reference: https://lore.kernel.org/all/20240326133813.3224593-1-john.g.garry@oracle.com...

--------------------------------

Validate that an atomic write adheres to length/offset rules. Since we require extent alignment for atomic writes, this effectively also enforces that the BIO which iomap produces is aligned.

Signed-off-by: John Garry john.g.garry@oracle.com Signed-off-by: Long Li leo.lilong@huawei.com --- fs/xfs/xfs_file.c | 8 ++++++++ 1 file changed, 8 insertions(+)

diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c index 1e4da3479432..75d7ca8d2a4a 100644 --- a/fs/xfs/xfs_file.c +++ b/fs/xfs/xfs_file.c @@ -586,6 +586,14 @@ xfs_file_dio_aio_write( size_t count = iov_iter_count(from); struct xfs_buftarg *target = xfs_inode_buftarg(ip);

+ if (iocb->ki_flags & IOCB_ATOMIC) { + if (!generic_atomic_write_valid(iocb->ki_pos, from, + i_blocksize(inode), + XFS_FSB_TO_B(mp, xfs_get_extsz(ip)))) { + return -EINVAL; + } + } + /* DIO must be aligned to device logical sector size */ if ((iocb->ki_pos | count) & target->bt_logical_sectormask) return -EINVAL;

hulk inclusion category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I9VTE3 CVE: NA

--------------------------------

Support FS_IOC_SETATOMIC ioctl, if filesystem and file could support atomic write, then enable file's atomic write function. Database like Mysql could use this ioctl check and enable file atomic write.

Signed-off-by: Long Li leo.lilong@huawei.com --- fs/xfs/xfs_ioctl.c | 45 +++++++++++++++++++++++++++++++++++++++++ include/uapi/linux/fs.h | 1 + 2 files changed, 46 insertions(+)

diff --git a/fs/xfs/xfs_ioctl.c b/fs/xfs/xfs_ioctl.c index e96ebea20991..fbaf3d0ddd8e 100644 --- a/fs/xfs/xfs_ioctl.c +++ b/fs/xfs/xfs_ioctl.c @@ -2112,6 +2112,26 @@ xfs_fs_eofblocks_from_user( return 0; }

+static int +xfs_ioc_set_atomic_write( + struct xfs_inode *ip) +{ + struct xfs_trans *tp; + int error; + + tp = xfs_ioctl_setattr_get_trans(ip, NULL); + if (IS_ERR(tp)) { + error = PTR_ERR(tp); + goto out; + } + + ip->i_d.di_flags2 |= XFS_DIFLAG2_ATOMICWRITES; + + error = xfs_trans_commit(tp); +out: + return error; +} + /* * Note: some of the ioctl's return positive numbers as a * byte count indicating success, such as readlink_by_handle. @@ -2139,6 +2159,31 @@ xfs_file_ioctl( return xfs_ioc_getlabel(mp, arg); case FS_IOC_SETFSLABEL: return xfs_ioc_setlabel(filp, mp, arg); + case FS_IOC_SETATOMIC: + if (!xfs_has_atomicwrites(mp)) + return -1; + if (!S_ISREG(inode->i_mode)) + return -1; + if (xfs_inode_atomicwrites(ip)) + return 0; + if (!xfs_inode_forcealign(ip)) + return -1; + + xfs_ilock(ip, XFS_IOLOCK_EXCL | XFS_MMAPLOCK_EXCL); + error = xfs_ioc_set_atomic_write(ip); + xfs_iunlock(ip, XFS_IOLOCK_EXCL | XFS_MMAPLOCK_EXCL); + if (error) { + xfs_alert(mp, "%s: set ino 0x%llx atomic write fail!", + __func__, XFS_I(inode)->i_ino); + return -1; + } else { + struct xfs_buftarg *target = xfs_inode_buftarg(ip); + + if ((filp->f_flags & O_DIRECT) && + bdev_can_atomic_write(target->bt_bdev)) + filp->f_mode |= FMODE_CAN_ATOMIC_WRITE; + return 0; + } case XFS_IOC_ALLOCSP: case XFS_IOC_FREESP: case XFS_IOC_ALLOCSP64: diff --git a/include/uapi/linux/fs.h b/include/uapi/linux/fs.h index ca8b6f6c479d..332b0709756b 100644 --- a/include/uapi/linux/fs.h +++ b/include/uapi/linux/fs.h @@ -217,6 +217,7 @@ struct fsxattr { #define FS_IOC_FSSETXATTR _IOW('X', 32, struct fsxattr) #define FS_IOC_GETFSLABEL _IOR(0x94, 49, char[FSLABEL_MAX]) #define FS_IOC_SETFSLABEL _IOW(0x94, 50, char[FSLABEL_MAX]) +#define FS_IOC_SETATOMIC _IOW(0x95, 2, uint)

/* * Inode flags (FS_IOC_GETFLAGS / FS_IOC_SETFLAGS)

maillist inclusion category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I9VTE3 CVE: NA

--------------------------------

Since introduce "fs: xfs: Introduce FORCEALIGN inode flag", generic/079 report fail, the reason is that vfs_ioc_fssetxattr_check() would clear FS_XFLAG_EXTSIZE and FS_XFLAG_EXTSZINHERIT due to fa not update completely.

Signed-off-by: Long Li leo.lilong@huawei.com --- fs/xfs/xfs_ioctl.c | 4 ++++ 1 file changed, 4 insertions(+)

diff --git a/fs/xfs/xfs_ioctl.c b/fs/xfs/xfs_ioctl.c index fbaf3d0ddd8e..939b91124ce1 100644 --- a/fs/xfs/xfs_ioctl.c +++ b/fs/xfs/xfs_ioctl.c @@ -1649,6 +1649,10 @@ xfs_ioc_setxflags( }

xfs_fill_fsxattr(ip, false, &old_fa); + fa.fsx_extsize = old_fa.fsx_extsize; + fa.fsx_cowextsize = old_fa.fsx_cowextsize; + fa.fsx_projid = old_fa.fsx_projid; + fa.fsx_nextents = old_fa.fsx_nextents; error = vfs_ioc_fssetxattr_check(VFS_I(ip), &old_fa, &fa); if (error) { xfs_trans_cancel(tp);

From: John Garry john.g.garry@oracle.com

maillist inclusion category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I9VTE3 CVE: NA

Reference: https://lore.kernel.org/all/20240326133813.3224593-1-john.g.garry@oracle.com...

--------------------------------

Like we already do for rtvol, only free full extents for forcealign in xfs_free_file_space().

Signed-off-by: John Garry john.g.garry@oracle.com Signed-off-by: Long Li leo.lilong@huawei.com --- fs/xfs/xfs_bmap_util.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c index 94e5d57de432..5879f03b8660 100644 --- a/fs/xfs/xfs_bmap_util.c +++ b/fs/xfs/xfs_bmap_util.c @@ -928,8 +928,11 @@ xfs_free_file_space( startoffset_fsb = XFS_B_TO_FSB(mp, offset); endoffset_fsb = XFS_B_TO_FSBT(mp, offset + len);

- /* We can only free complete realtime extents. */ - if (XFS_IS_REALTIME_INODE(ip) && mp->m_sb.sb_rextsize > 1) { + /* Free only complete extents. */ + if (xfs_inode_forcealign(ip) && ip->i_d.di_extsize > 1) { + startoffset_fsb = roundup_64(startoffset_fsb, ip->i_d.di_extsize); + endoffset_fsb = rounddown_64(endoffset_fsb, ip->i_d.di_extsize); + } else if (XFS_IS_REALTIME_INODE(ip) && mp->m_sb.sb_rextsize > 1) { startoffset_fsb = roundup_64(startoffset_fsb, mp->m_sb.sb_rextsize); endoffset_fsb = rounddown_64(endoffset_fsb,

From: Zhang Yi yi.zhang@huawei.com

maillist inclusion category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I9VTE3 CVE: NA

Reference: https://lore.kernel.org/linux-fsdevel/20240529095206.2568162-1-yi.zhang@huaw...

--------------------------------

Add a new helper rem_u64() to only get the remainder of unsigned 64bit divide with 32bit divisor.

Signed-off-by: Zhang Yi yi.zhang@huawei.com Signed-off-by: Long Li leo.lilong@huawei.com --- include/linux/math64.h | 24 ++++++++++++++++++++++++ 1 file changed, 24 insertions(+)

diff --git a/include/linux/math64.h b/include/linux/math64.h index 66deb1fdc2ef..b5c4d1df08e5 100644 --- a/include/linux/math64.h +++ b/include/linux/math64.h @@ -3,6 +3,7 @@ #define _LINUX_MATH64_H

#include <linux/types.h> +#include <linux/log2.h> #include <vdso/math64.h> #include <asm/div64.h>

@@ -11,6 +12,20 @@ #define div64_long(x, y) div64_s64((x), (y)) #define div64_ul(x, y) div64_u64((x), (y))

+/** + * rem_u64 - remainder of unsigned 64bit divide with 32bit divisor + * @dividend: unsigned 64bit dividend + * @divisor: unsigned 32bit divisor + * + * Return: dividend % divisor + */ +static inline u32 rem_u64(u64 dividend, u32 divisor) +{ + if (is_power_of_2(divisor)) + return dividend & (divisor - 1); + return dividend % divisor; +} + /** * div_u64_rem - unsigned 64bit divide with 32bit divisor with remainder * @dividend: unsigned 64bit dividend @@ -85,6 +100,15 @@ static inline s64 div64_s64(s64 dividend, s64 divisor) #define div64_long(x, y) div_s64((x), (y)) #define div64_ul(x, y) div_u64((x), (y))

+#ifndef rem_u64 +static inline u32 rem_u64(u64 dividend, u32 divisor) +{ + if (is_power_of_2(divisor)) + return dividend & (divisor - 1); + return do_div(dividend, divisor); +} +#endif + #ifndef div_u64_rem static inline u64 div_u64_rem(u64 dividend, u32 divisor, u32 *remainder) {

From: Zhang Yi yi.zhang@huawei.com

maillist inclusion category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I9VTE3 CVE: NA

Reference: https://lore.kernel.org/linux-fsdevel/20240529095206.2568162-1-yi.zhang@huaw...

--------------------------------

When truncating down an inode, we call xfs_truncate_page() to zero out the tail partial block that beyond new EOF, which prevents exposing stale data. But xfs_truncate_page() always assumes the blocksize is i_blocksize(inode), it's not always true if we have a large allocation unit for a file and we should aligned to this unitsize, e.g. realtime inode should aligned to the rtextsize.

Current xfs_setattr_size() can't support zeroing out a large alignment size on trucate down since the process order is wrong. We first do zero out through xfs_truncate_page(), and then update inode size through truncate_setsize() immediately. If the zeroed range is larger than a folio, the write back path would not write back zeroed pagecache beyond the EOF folio, so it doesn't write zeroes to the entire tail extent and could expose stale data after an appending write into the next aligned extent.

We need to adjust the order to zero out tail aligned blocks, write back zeroed or cached data, update i_size and drop cache beyond aligned EOF block, preparing for the fix of realtime inode and supporting the upcoming forced alignment feature.

Signed-off-by: Zhang Yi yi.zhang@huawei.com Signed-off-by: Long Li leo.lilong@huawei.com --- fs/xfs/xfs_iops.c | 115 ++++++++++++++++++++++++---------------------- 1 file changed, 59 insertions(+), 56 deletions(-)

diff --git a/fs/xfs/xfs_iops.c b/fs/xfs/xfs_iops.c index d546818feab7..673f066d3ad4 100644 --- a/fs/xfs/xfs_iops.c +++ b/fs/xfs/xfs_iops.c @@ -809,7 +809,7 @@ xfs_setattr_size( int error; uint lock_flags = 0; bool did_zeroing = false; - unsigned int blocksize = i_blocksize(inode); + bool write_back = false;

ASSERT(xfs_isilocked(ip, XFS_IOLOCK_EXCL)); ASSERT(xfs_isilocked(ip, XFS_MMAPLOCK_EXCL)); @@ -846,21 +846,10 @@ xfs_setattr_size( */ inode_dio_wait(inode);

- /* - * File data changes must be complete before we start the transaction to - * modify the inode. This needs to be done before joining the inode to - * the transaction because the inode cannot be unlocked once it is a - * part of the transaction. - * - * Start with zeroing any data beyond EOF that we may expose on file - * extension, or zeroing out the rest of the block on a downward - * truncate. - */ - if (newsize > oldsize) { - trace_xfs_zero_eof(ip, oldsize, newsize - oldsize); - error = iomap_zero_range(inode, oldsize, newsize - oldsize, - &did_zeroing, &xfs_buffered_write_iomap_ops); - } else { + write_back = newsize > ip->i_d.di_size && oldsize != ip->i_d.di_size; + if (newsize < oldsize) { + unsigned int blocksize = i_blocksize(inode); + /* * iomap won't detect a dirty page over an unwritten block (or a * cow block over a hole) and subsequently skips zeroing the @@ -868,53 +857,67 @@ xfs_setattr_size( * convert the block before the pagecache truncate. */ error = filemap_write_and_wait_range(inode->i_mapping, newsize, - newsize); + roundup_64(newsize, blocksize) - 1); if (error) return error; error = iomap_truncate_page(inode, newsize, blocksize, &did_zeroing, &xfs_buffered_write_iomap_ops); - }

- if (error) - return error; + /* + * We are going to log the inode size change in this transaction + * so any previous writes that are beyond the on disk EOF and + * the new EOF that have not been written out need to be written + * here. If we do not write the data out, we expose ourselves + * to the null files problem. Note that this includes any block + * zeroing we did above; otherwise those blocks may not be + * zeroed after a crash. + */ + if (did_zeroing || write_back) { + error = filemap_write_and_wait_range(inode->i_mapping, + min_t(loff_t, ip->i_d.di_size, newsize), + roundup_64(newsize, blocksize) - 1); + if (error) + return error; + }

- /* - * We've already locked out new page faults, so now we can safely remove - * pages from the page cache knowing they won't get refaulted until we - * drop the XFS_MMAP_EXCL lock after the extent manipulations are - * complete. The truncate_setsize() call also cleans partial EOF page - * PTEs on extending truncates and hence ensures sub-page block size - * filesystems are correctly handled, too. - * - * We have to do all the page cache truncate work outside the - * transaction context as the "lock" order is page lock->log space - * reservation as defined by extent allocation in the writeback path. - * Hence a truncate can fail with ENOMEM from xfs_trans_alloc(), but - * having already truncated the in-memory version of the file (i.e. made - * user visible changes). There's not much we can do about this, except - * to hope that the caller sees ENOMEM and retries the truncate - * operation. - * - * And we update in-core i_size and truncate page cache beyond newsize - * before writeback the [di_size, newsize] range, so we're guaranteed - * not to write stale data past the new EOF on truncate down. - */ - truncate_setsize(inode, newsize); + /* + * Updating i_size after writing back to make sure the zeroed + * blocks could been written out, and drop all the page cache + * range that beyond blocksize aligned new EOF block. + * + * We've already locked out new page faults, so now we can + * safely remove pages from the page cache knowing they won't + * get refaulted until we drop the XFS_MMAP_EXCL lock after the + * extent manipulations are complete. + */ + i_size_write(inode, newsize); + truncate_pagecache(inode, roundup_64(newsize, blocksize)); + } else { + /* + * Start with zeroing any data beyond EOF that we may expose on + * file extension. + */ + if (newsize > oldsize) { + trace_xfs_zero_eof(ip, oldsize, newsize - oldsize); + error = iomap_zero_range(inode, oldsize, newsize - oldsize, + &did_zeroing, &xfs_buffered_write_iomap_ops); + if (error) + return error; + }

- /* - * We are going to log the inode size change in this transaction so - * any previous writes that are beyond the on disk EOF and the new - * EOF that have not been written out need to be written here. If we - * do not write the data out, we expose ourselves to the null files - * problem. Note that this includes any block zeroing we did above; - * otherwise those blocks may not be zeroed after a crash. - */ - if (did_zeroing || - (newsize > ip->i_d.di_size && oldsize != ip->i_d.di_size)) { - error = filemap_write_and_wait_range(VFS_I(ip)->i_mapping, - ip->i_d.di_size, newsize - 1); - if (error) - return error; + /* + * The truncate_setsize() call also cleans partial EOF page + * PTEs on extending truncates and hence ensures sub-page block + * size filesystems are correctly handled, too. + */ + truncate_setsize(inode, newsize); + + if (did_zeroing || write_back) { + error = filemap_write_and_wait_range(inode->i_mapping, + ip->i_d.di_size, newsize - 1); + if (error) + return error; + } }

error = xfs_trans_alloc(mp, &M_RES(mp)->tr_itruncate, 0, 0, 0, &tp);