xfs_log.c

linux 内核源代码

/*
 * Copyright (c) 2000-2005 Silicon Graphics, Inc.
 * All Rights Reserved.
 *
 * This program is free software; you can redistribute it and/or
 * modify it under the terms of the GNU General Public License as
 * published by the Free Software Foundation.
 *
 * This program is distributed in the hope that it would be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 * GNU General Public License for more details.
 *
 * You should have received a copy of the GNU General Public License
 * along with this program; if not, write the Free Software Foundation,
 * Inc.,  51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
 */
#include "xfs.h"
#include "xfs_fs.h"
#include "xfs_types.h"
#include "xfs_bit.h"
#include "xfs_log.h"
#include "xfs_inum.h"
#include "xfs_trans.h"
#include "xfs_sb.h"
#include "xfs_ag.h"
#include "xfs_dir2.h"
#include "xfs_dmapi.h"
#include "xfs_mount.h"
#include "xfs_error.h"
#include "xfs_log_priv.h"
#include "xfs_buf_item.h"
#include "xfs_bmap_btree.h"
#include "xfs_alloc_btree.h"
#include "xfs_ialloc_btree.h"
#include "xfs_log_recover.h"
#include "xfs_trans_priv.h"
#include "xfs_dir2_sf.h"
#include "xfs_attr_sf.h"
#include "xfs_dinode.h"
#include "xfs_inode.h"
#include "xfs_rw.h"


#define xlog_write_adv_cnt(ptr, len, off, bytes) \
	{ (ptr) += (bytes); \
	  (len) -= (bytes); \
	  (off) += (bytes);}

/* Local miscellaneous function prototypes */
STATIC int	 xlog_bdstrat_cb(struct xfs_buf *);
STATIC int	 xlog_commit_record(xfs_mount_t *mp, xlog_ticket_t *ticket,
				    xlog_in_core_t **, xfs_lsn_t *);
STATIC xlog_t *  xlog_alloc_log(xfs_mount_t	*mp,
				xfs_buftarg_t	*log_target,
				xfs_daddr_t	blk_offset,
				int		num_bblks);
STATIC int	 xlog_space_left(xlog_t *log, int cycle, int bytes);
STATIC int	 xlog_sync(xlog_t *log, xlog_in_core_t *iclog);
STATIC void	 xlog_dealloc_log(xlog_t *log);
STATIC int	 xlog_write(xfs_mount_t *mp, xfs_log_iovec_t region[],
			    int nentries, xfs_log_ticket_t tic,
			    xfs_lsn_t *start_lsn,
			    xlog_in_core_t **commit_iclog,
			    uint flags);

/* local state machine functions */
STATIC void xlog_state_done_syncing(xlog_in_core_t *iclog, int);
STATIC void xlog_state_do_callback(xlog_t *log,int aborted, xlog_in_core_t *iclog);
STATIC int  xlog_state_get_iclog_space(xlog_t		*log,
				       int		len,
				       xlog_in_core_t	**iclog,
				       xlog_ticket_t	*ticket,
				       int		*continued_write,
				       int		*logoffsetp);
STATIC void xlog_state_put_ticket(xlog_t	*log,
				  xlog_ticket_t *tic);
STATIC int  xlog_state_release_iclog(xlog_t		*log,
				     xlog_in_core_t	*iclog);
STATIC void xlog_state_switch_iclogs(xlog_t		*log,
				     xlog_in_core_t *iclog,
				     int		eventual_size);
STATIC int  xlog_state_sync(xlog_t			*log,
			    xfs_lsn_t 			lsn,
			    uint			flags,
			    int				*log_flushed);
STATIC int  xlog_state_sync_all(xlog_t *log, uint flags, int *log_flushed);
STATIC void xlog_state_want_sync(xlog_t	*log, xlog_in_core_t *iclog);

/* local functions to manipulate grant head */
STATIC int  xlog_grant_log_space(xlog_t		*log,
				 xlog_ticket_t	*xtic);
STATIC void xlog_grant_push_ail(xfs_mount_t	*mp,
				int		need_bytes);
STATIC void xlog_regrant_reserve_log_space(xlog_t	 *log,
					   xlog_ticket_t *ticket);
STATIC int xlog_regrant_write_log_space(xlog_t		*log,
					 xlog_ticket_t  *ticket);
STATIC void xlog_ungrant_log_space(xlog_t	 *log,
				   xlog_ticket_t *ticket);


/* local ticket functions */
STATIC void		xlog_state_ticket_alloc(xlog_t *log);
STATIC xlog_ticket_t	*xlog_ticket_get(xlog_t *log,
					 int	unit_bytes,
					 int	count,
					 char	clientid,
					 uint	flags);
STATIC void		xlog_ticket_put(xlog_t *log, xlog_ticket_t *ticket);

#if defined(DEBUG)
STATIC void	xlog_verify_dest_ptr(xlog_t *log, __psint_t ptr);
STATIC void	xlog_verify_grant_head(xlog_t *log, int equals);
STATIC void	xlog_verify_iclog(xlog_t *log, xlog_in_core_t *iclog,
				  int count, boolean_t syncing);
STATIC void	xlog_verify_tail_lsn(xlog_t *log, xlog_in_core_t *iclog,
				     xfs_lsn_t tail_lsn);
#else
#define xlog_verify_dest_ptr(a,b)
#define xlog_verify_grant_head(a,b)
#define xlog_verify_iclog(a,b,c,d)
#define xlog_verify_tail_lsn(a,b,c)
#endif

STATIC int	xlog_iclogs_empty(xlog_t *log);

#if defined(XFS_LOG_TRACE)
void
xlog_trace_loggrant(xlog_t *log, xlog_ticket_t *tic, xfs_caddr_t string)
{
	unsigned long cnts;

	if (!log->l_grant_trace) {
		log->l_grant_trace = ktrace_alloc(2048, KM_NOSLEEP);
		if (!log->l_grant_trace)
			return;
	}
	/* ticket counts are 1 byte each */
	cnts = ((unsigned long)tic->t_ocnt) | ((unsigned long)tic->t_cnt) << 8;

	ktrace_enter(log->l_grant_trace,
		     (void *)tic,
		     (void *)log->l_reserve_headq,
		     (void *)log->l_write_headq,
		     (void *)((unsigned long)log->l_grant_reserve_cycle),
		     (void *)((unsigned long)log->l_grant_reserve_bytes),
		     (void *)((unsigned long)log->l_grant_write_cycle),
		     (void *)((unsigned long)log->l_grant_write_bytes),
		     (void *)((unsigned long)log->l_curr_cycle),
		     (void *)((unsigned long)log->l_curr_block),
		     (void *)((unsigned long)CYCLE_LSN(log->l_tail_lsn)),
		     (void *)((unsigned long)BLOCK_LSN(log->l_tail_lsn)),
		     (void *)string,
		     (void *)((unsigned long)tic->t_trans_type),
		     (void *)cnts,
		     (void *)((unsigned long)tic->t_curr_res),
		     (void *)((unsigned long)tic->t_unit_res));
}

void
xlog_trace_iclog(xlog_in_core_t *iclog, uint state)
{
	if (!iclog->ic_trace)
		iclog->ic_trace = ktrace_alloc(256, KM_SLEEP);
	ktrace_enter(iclog->ic_trace,
		     (void *)((unsigned long)state),
		     (void *)((unsigned long)current_pid()),
		     (void *)NULL, (void *)NULL, (void *)NULL, (void *)NULL,
		     (void *)NULL, (void *)NULL, (void *)NULL, (void *)NULL,
		     (void *)NULL, (void *)NULL, (void *)NULL, (void *)NULL,
		     (void *)NULL, (void *)NULL);
}
#else
#define	xlog_trace_loggrant(log,tic,string)
#define	xlog_trace_iclog(iclog,state)
#endif /* XFS_LOG_TRACE */


static void
xlog_ins_ticketq(struct xlog_ticket **qp, struct xlog_ticket *tic)
{
	if (*qp) {
		tic->t_next	    = (*qp);
		tic->t_prev	    = (*qp)->t_prev;
		(*qp)->t_prev->t_next = tic;
		(*qp)->t_prev	    = tic;
	} else {
		tic->t_prev = tic->t_next = tic;
		*qp = tic;
	}

	tic->t_flags |= XLOG_TIC_IN_Q;
}

static void
xlog_del_ticketq(struct xlog_ticket **qp, struct xlog_ticket *tic)
{
	if (tic == tic->t_next) {
		*qp = NULL;
	} else {
		*qp = tic->t_next;
		tic->t_next->t_prev = tic->t_prev;
		tic->t_prev->t_next = tic->t_next;
	}

	tic->t_next = tic->t_prev = NULL;
	tic->t_flags &= ~XLOG_TIC_IN_Q;
}

static void
xlog_grant_sub_space(struct log *log, int bytes)
{
	log->l_grant_write_bytes -= bytes;
	if (log->l_grant_write_bytes < 0) {
		log->l_grant_write_bytes += log->l_logsize;
		log->l_grant_write_cycle--;
	}

	log->l_grant_reserve_bytes -= bytes;
	if ((log)->l_grant_reserve_bytes < 0) {
		log->l_grant_reserve_bytes += log->l_logsize;
		log->l_grant_reserve_cycle--;
	}

}

static void
xlog_grant_add_space_write(struct log *log, int bytes)
{
	log->l_grant_write_bytes += bytes;
	if (log->l_grant_write_bytes > log->l_logsize) {
		log->l_grant_write_bytes -= log->l_logsize;
		log->l_grant_write_cycle++;
	}
}

static void
xlog_grant_add_space_reserve(struct log *log, int bytes)
{
	log->l_grant_reserve_bytes += bytes;
	if (log->l_grant_reserve_bytes > log->l_logsize) {
		log->l_grant_reserve_bytes -= log->l_logsize;
		log->l_grant_reserve_cycle++;
	}
}

static inline void
xlog_grant_add_space(struct log *log, int bytes)
{
	xlog_grant_add_space_write(log, bytes);
	xlog_grant_add_space_reserve(log, bytes);
}

static void
xlog_tic_reset_res(xlog_ticket_t *tic)
{
	tic->t_res_num = 0;
	tic->t_res_arr_sum = 0;
	tic->t_res_num_ophdrs = 0;
}

static void
xlog_tic_add_region(xlog_ticket_t *tic, uint len, uint type)
{
	if (tic->t_res_num == XLOG_TIC_LEN_MAX) {
		/* add to overflow and start again */
		tic->t_res_o_flow += tic->t_res_arr_sum;
		tic->t_res_num = 0;
		tic->t_res_arr_sum = 0;
	}

	tic->t_res_arr[tic->t_res_num].r_len = len;
	tic->t_res_arr[tic->t_res_num].r_type = type;
	tic->t_res_arr_sum += len;
	tic->t_res_num++;
}

/*
 * NOTES:
 *
 *	1. currblock field gets updated at startup and after in-core logs
 *		marked as with WANT_SYNC.
 */

/*
 * This routine is called when a user of a log manager ticket is done with
 * the reservation.  If the ticket was ever used, then a commit record for
 * the associated transaction is written out as a log operation header with
 * no data.  The flag XLOG_TIC_INITED is set when the first write occurs with
 * a given ticket.  If the ticket was one with a permanent reservation, then
 * a few operations are done differently.  Permanent reservation tickets by
 * default don't release the reservation.  They just commit the current
 * transaction with the belief that the reservation is still needed.  A flag
 * must be passed in before permanent reservations are actually released.
 * When these type of tickets are not released, they need to be set into
 * the inited state again.  By doing this, a start record will be written
 * out when the next write occurs.
 */
xfs_lsn_t
xfs_log_done(xfs_mount_t	*mp,
	     xfs_log_ticket_t	xtic,
	     void		**iclog,
	     uint		flags)
{
	xlog_t		*log    = mp->m_log;
	xlog_ticket_t	*ticket = (xfs_log_ticket_t) xtic;
	xfs_lsn_t	lsn	= 0;

	if (XLOG_FORCED_SHUTDOWN(log) ||
	    /*
	     * If nothing was ever written, don't write out commit record.
	     * If we get an error, just continue and give back the log ticket.
	     */
	    (((ticket->t_flags & XLOG_TIC_INITED) == 0) &&
	     (xlog_commit_record(mp, ticket,
				 (xlog_in_core_t **)iclog, &lsn)))) {
		lsn = (xfs_lsn_t) -1;
		if (ticket->t_flags & XLOG_TIC_PERM_RESERV) {
			flags |= XFS_LOG_REL_PERM_RESERV;
		}
	}


	if ((ticket->t_flags & XLOG_TIC_PERM_RESERV) == 0 ||
	    (flags & XFS_LOG_REL_PERM_RESERV)) {
		/*
		 * Release ticket if not permanent reservation or a specific
		 * request has been made to release a permanent reservation.
		 */
		xlog_trace_loggrant(log, ticket, "xfs_log_done: (non-permanent)");
		xlog_ungrant_log_space(log, ticket);
		xlog_state_put_ticket(log, ticket);
	} else {
		xlog_trace_loggrant(log, ticket, "xfs_log_done: (permanent)");
		xlog_regrant_reserve_log_space(log, ticket);
	}

	/* If this ticket was a permanent reservation and we aren't
	 * trying to release it, reset the inited flags; so next time
	 * we write, a start record will be written out.
	 */
	if ((ticket->t_flags & XLOG_TIC_PERM_RESERV) &&
	    (flags & XFS_LOG_REL_PERM_RESERV) == 0)
		ticket->t_flags |= XLOG_TIC_INITED;

	return lsn;
}	/* xfs_log_done */


/*
 * Force the in-core log to disk.  If flags == XFS_LOG_SYNC,
 *	the force is done synchronously.
 *
 * Asynchronous forces are implemented by setting the WANT_SYNC
 * bit in the appropriate in-core log and then returning.
 *
 * Synchronous forces are implemented with a semaphore.  All callers
 * to force a given lsn to disk will wait on a semaphore attached to the
 * specific in-core log.  When given in-core log finally completes its
 * write to disk, that thread will wake up all threads waiting on the
 * semaphore.
 */
int
_xfs_log_force(
	xfs_mount_t	*mp,
	xfs_lsn_t	lsn,
	uint		flags,
	int		*log_flushed)
{
	xlog_t		*log = mp->m_log;
	int		dummy;

	if (!log_flushed)
		log_flushed = &dummy;

	ASSERT(flags & XFS_LOG_FORCE);

	XFS_STATS_INC(xs_log_force);

	if (log->l_flags & XLOG_IO_ERROR)
		return XFS_ERROR(EIO);
	if (lsn == 0)
		return xlog_state_sync_all(log, flags, log_flushed);
	else
		return xlog_state_sync(log, lsn, flags, log_flushed);
}	/* xfs_log_force */

/*
 * Attaches a new iclog I/O completion callback routine during
 * transaction commit.  If the log is in error state, a non-zero
 * return code is handed back and the caller is responsible for
 * executing the callback at an appropriate time.
 */
int
xfs_log_notify(xfs_mount_t	  *mp,		/* mount of partition */
	       void		  *iclog_hndl,	/* iclog to hang callback off */
	       xfs_log_callback_t *cb)
{
	xlog_t *log = mp->m_log;
	xlog_in_core_t	  *iclog = (xlog_in_core_t *)iclog_hndl;
	int	abortflg, spl;

	cb->cb_next = NULL;
	spl = LOG_LOCK(log);
	abortflg = (iclog->ic_state & XLOG_STATE_IOERROR);
	if (!abortflg) {
		ASSERT_ALWAYS((iclog->ic_state == XLOG_STATE_ACTIVE) ||
			      (iclog->ic_state == XLOG_STATE_WANT_SYNC));
		cb->cb_next = NULL;
		*(iclog->ic_callback_tail) = cb;
		iclog->ic_callback_tail = &(cb->cb_next);
	}
	LOG_UNLOCK(log, spl);
	return abortflg;
}	/* xfs_log_notify */

int
xfs_log_release_iclog(xfs_mount_t *mp,
		      void	  *iclog_hndl)
{
	xlog_t *log = mp->m_log;
	xlog_in_core_t	  *iclog = (xlog_in_core_t *)iclog_hndl;

	if (xlog_state_release_iclog(log, iclog)) {
		xfs_force_shutdown(mp, SHUTDOWN_LOG_IO_ERROR);
		return EIO;
	}

	return 0;
}

/*
 *  1. Reserve an amount of on-disk log space and return a ticket corresponding
 *	to the reservation.
 *  2. Potentially, push buffers at tail of log to disk.
 *
 * Each reservation is going to reserve extra space for a log record header.
 * When writes happen to the on-disk log, we don't subtract the length of the
 * log record header from any reservation.  By wasting space in each
 * reservation, we prevent over allocation problems.
 */
int