Re: [PATCH V6 15/17] xfs: Enable bulkstat ioctl to support 64-bit per-inode extent counters

[Chandan Babu R <chandan.babu@oracle.com>]

On 25 Feb 2022 at 10:40, Darrick J. Wong wrote:
> On Thu, Feb 24, 2022 at 06:32:09PM +0530, Chandan Babu R wrote:
>> The following changes are made to enable userspace to obtain 64-bit extent
>> counters,
>> 1. Carve out a new 64-bit field xfs_bulkstat->bs_extents64 from
>>    xfs_bulkstat->bs_pad[] to hold 64-bit extent counter.
>> 2. Define the new flag XFS_BULK_IREQ_BULKSTAT for userspace to indicate that
>>    it is capable of receiving 64-bit extent counters.
>> 
>> Suggested-by: Darrick J. Wong <djwong@kernel.org>
>> Signed-off-by: Chandan Babu R <chandan.babu@oracle.com>
>> ---
>>  fs/xfs/libxfs/xfs_fs.h | 20 ++++++++++++++++----
>>  fs/xfs/xfs_ioctl.c     |  3 +++
>>  fs/xfs/xfs_itable.c    | 30 ++++++++++++++++++++++++++++--
>>  fs/xfs/xfs_itable.h    |  6 ++++--
>>  fs/xfs/xfs_iwalk.h     |  2 +-
>>  5 files changed, 52 insertions(+), 9 deletions(-)
>> 
>> diff --git a/fs/xfs/libxfs/xfs_fs.h b/fs/xfs/libxfs/xfs_fs.h
>> index 2204d49d0c3a..31ccbff2f16c 100644
>> --- a/fs/xfs/libxfs/xfs_fs.h
>> +++ b/fs/xfs/libxfs/xfs_fs.h
>> @@ -378,7 +378,7 @@ struct xfs_bulkstat {
>>  	uint32_t	bs_extsize_blks; /* extent size hint, blocks	*/
>>  
>>  	uint32_t	bs_nlink;	/* number of links		*/
>> -	uint32_t	bs_extents;	/* number of extents		*/
>> +	uint32_t	bs_extents;	/* 32-bit data fork extent counter */
>>  	uint32_t	bs_aextents;	/* attribute number of extents	*/
>>  	uint16_t	bs_version;	/* structure version		*/
>>  	uint16_t	bs_forkoff;	/* inode fork offset in bytes	*/
>> @@ -387,8 +387,9 @@ struct xfs_bulkstat {
>>  	uint16_t	bs_checked;	/* checked inode metadata	*/
>>  	uint16_t	bs_mode;	/* type and mode		*/
>>  	uint16_t	bs_pad2;	/* zeroed			*/
>> +	uint64_t	bs_extents64;	/* 64-bit data fork extent counter */
>>  
>> -	uint64_t	bs_pad[7];	/* zeroed			*/
>> +	uint64_t	bs_pad[6];	/* zeroed			*/
>>  };
>>  
>>  #define XFS_BULKSTAT_VERSION_V1	(1)
>> @@ -469,8 +470,19 @@ struct xfs_bulk_ireq {
>>   */
>>  #define XFS_BULK_IREQ_SPECIAL	(1 << 1)
>>  
>> -#define XFS_BULK_IREQ_FLAGS_ALL	(XFS_BULK_IREQ_AGNO | \
>> -				 XFS_BULK_IREQ_SPECIAL)
>> +/*
>> + * Return data fork extent count via xfs_bulkstat->bs_extents64 field and assign
>> + * 0 to xfs_bulkstat->bs_extents when the flag is set.  Otherwise, use
>> + * xfs_bulkstat->bs_extents for returning data fork extent count and set
>> + * xfs_bulkstat->bs_extents64 to 0. In the second case, return -EOVERFLOW and
>> + * assign 0 to xfs_bulkstat->bs_extents if data fork extent count is larger than
>> + * XFS_MAX_EXTCNT_DATA_FORK_OLD.
>> + */
>> +#define XFS_BULK_IREQ_NREXT64	(1 << 2)
>> +
>> +#define XFS_BULK_IREQ_FLAGS_ALL	(XFS_BULK_IREQ_AGNO |	 \
>> +				 XFS_BULK_IREQ_SPECIAL | \
>> +				 XFS_BULK_IREQ_NREXT64)
>>  
>>  /* Operate on the root directory inode. */
>>  #define XFS_BULK_IREQ_SPECIAL_ROOT	(1)
>> diff --git a/fs/xfs/xfs_ioctl.c b/fs/xfs/xfs_ioctl.c
>> index 2515fe8299e1..22947c5ffd34 100644
>> --- a/fs/xfs/xfs_ioctl.c
>> +++ b/fs/xfs/xfs_ioctl.c
>> @@ -813,6 +813,9 @@ xfs_bulk_ireq_setup(
>>  	if (XFS_INO_TO_AGNO(mp, breq->startino) >= mp->m_sb.sb_agcount)
>>  		return -ECANCELED;
>>  
>> +	if (hdr->flags & XFS_BULK_IREQ_NREXT64)
>> +		breq->flags |= XFS_IBULK_NREXT64;
>> +
>>  	return 0;
>>  }
>>  
>> diff --git a/fs/xfs/xfs_itable.c b/fs/xfs/xfs_itable.c
>> index c08c79d9e311..11e5245756f7 100644
>> --- a/fs/xfs/xfs_itable.c
>> +++ b/fs/xfs/xfs_itable.c
>> @@ -20,6 +20,7 @@
>>  #include "xfs_icache.h"
>>  #include "xfs_health.h"
>>  #include "xfs_trans.h"
>> +#include "xfs_errortag.h"
>>  
>>  /*
>>   * Bulk Stat
>> @@ -64,6 +65,7 @@ xfs_bulkstat_one_int(
>>  	struct xfs_inode	*ip;		/* incore inode pointer */
>>  	struct inode		*inode;
>>  	struct xfs_bulkstat	*buf = bc->buf;
>> +	xfs_extnum_t		nextents;
>>  	int			error = -EINVAL;
>>  
>>  	if (xfs_internal_inum(mp, ino))
>> @@ -102,7 +104,27 @@ xfs_bulkstat_one_int(
>>  
>>  	buf->bs_xflags = xfs_ip2xflags(ip);
>>  	buf->bs_extsize_blks = ip->i_extsize;
>> -	buf->bs_extents = xfs_ifork_nextents(&ip->i_df);
>> +
>> +	nextents = xfs_ifork_nextents(&ip->i_df);
>> +	if (!(bc->breq->flags & XFS_IBULK_NREXT64)) {
>> +		xfs_extnum_t max_nextents = XFS_MAX_EXTCNT_DATA_FORK_OLD;
>
> Nit: space between type ^^^^^ and variable name.
>

I will fix this.

>> +
>> +		if (unlikely(XFS_TEST_ERROR(false, mp,
>> +				XFS_ERRTAG_REDUCE_MAX_IEXTENTS)))
>> +			max_nextents = 10;
>> +
>> +		if (nextents > max_nextents) {
>> +			xfs_iunlock(ip, XFS_ILOCK_SHARED);
>> +			xfs_irele(ip);
>> +			error = -EOVERFLOW;
>> +			goto out;
>> +		}
>> +
>> +		buf->bs_extents = nextents;
>> +	} else {
>> +		buf->bs_extents64 = nextents;
>> +	}
>> +
>>  	xfs_bulkstat_health(ip, buf);
>>  	buf->bs_aextents = xfs_ifork_nextents(ip->i_afp);
>>  	buf->bs_forkoff = XFS_IFORK_BOFF(ip);
>> @@ -256,6 +278,7 @@ xfs_bulkstat(
>>  		.breq		= breq,
>>  	};
>>  	struct xfs_trans	*tp;
>> +	unsigned int		iwalk_flags = 0;
>>  	int			error;
>>  
>>  	if (breq->mnt_userns != &init_user_ns) {
>> @@ -279,7 +302,10 @@ xfs_bulkstat(
>>  	if (error)
>>  		goto out;
>>  
>> -	error = xfs_iwalk(breq->mp, tp, breq->startino, breq->flags,
>> +	if (breq->flags & XFS_IBULK_SAME_AG)
>> +		iwalk_flags |= XFS_IWALK_SAME_AG;
>> +
>> +	error = xfs_iwalk(breq->mp, tp, breq->startino, iwalk_flags,
>>  			xfs_bulkstat_iwalk, breq->icount, &bc);
>>  	xfs_trans_cancel(tp);
>>  out:
>> diff --git a/fs/xfs/xfs_itable.h b/fs/xfs/xfs_itable.h
>> index 7078d10c9b12..2cb5611c873e 100644
>> --- a/fs/xfs/xfs_itable.h
>> +++ b/fs/xfs/xfs_itable.h
>> @@ -13,11 +13,13 @@ struct xfs_ibulk {
>>  	xfs_ino_t		startino; /* start with this inode */
>>  	unsigned int		icount;   /* number of elements in ubuffer */
>>  	unsigned int		ocount;   /* number of records returned */
>> -	unsigned int		flags;    /* see XFS_IBULK_FLAG_* */
>> +	unsigned long long	flags;    /* see XFS_IBULK_FLAG_* */
>
> I wonder if this could have been left an unsigned int and the flags
> below assigned adjacent bits instead of widening the field...
>

Yes, this should be unsigned int because ...

>>  };
>>  
>>  /* Only iterate within the same AG as startino */
>> -#define XFS_IBULK_SAME_AG	(XFS_IWALK_SAME_AG)
>> +#define XFS_IBULK_SAME_AG	(1ULL << 0)
>> +
>> +#define XFS_IBULK_NREXT64	(1ULL << 32)
>
> ...but was your purpose here to make it really obvious that we've
> separated IWALK and IBULK?
>

... Sorry, I should have fixed this when I had removed the tight integration
with IWALK. This should have been defined as,

#define XFS_IBULK_NREXT64	(1ULL << 1)

I will fix this up as well.

>>  /*
>>   * Advance the user buffer pointer by one record of the given size.  If the
>> diff --git a/fs/xfs/xfs_iwalk.h b/fs/xfs/xfs_iwalk.h
>> index 37a795f03267..3a68766fd909 100644
>> --- a/fs/xfs/xfs_iwalk.h
>> +++ b/fs/xfs/xfs_iwalk.h
>> @@ -26,7 +26,7 @@ int xfs_iwalk_threaded(struct xfs_mount *mp, xfs_ino_t startino,
>>  		unsigned int inode_records, bool poll, void *data);
>>  
>>  /* Only iterate inodes within the same AG as @startino. */
>> -#define XFS_IWALK_SAME_AG	(0x1)
>> +#define XFS_IWALK_SAME_AG	(1 << 0)
>>  
>>  #define XFS_IWALK_FLAGS_ALL	(XFS_IWALK_SAME_AG)
>>  
>> -- 
>> 2.30.2
>> 

-- 
chandan