Merge branch 'guilt/xlog-write-rework' into xfs-5.19-for-next

fs/xfs/libxfs/xfs_log_format.h

@@ -69,7 +69,6 @@ static inline uint xlog_get_cycle(char *ptr)
 
 /* Log Clients */
 #define XFS_TRANSACTION		0x69
-#define XFS_VOLUME		0x2
 #define XFS_LOG			0xaa
 
 #define XLOG_UNMOUNT_TYPE	0x556e	/* Un for Unmount */

fs/xfs/xfs_log.h

@@ -21,42 +21,19 @@ struct xfs_log_vec {
 
 #define XFS_LOG_VEC_ORDERED	(-1)
 
-static inline void *
-xlog_prepare_iovec(struct xfs_log_vec *lv, struct xfs_log_iovec **vecp,
-		uint type)
-{
-	struct xfs_log_iovec *vec = *vecp;
-
-	if (vec) {
-		ASSERT(vec - lv->lv_iovecp < lv->lv_niovecs);
-		vec++;
-	} else {
-		vec = &lv->lv_iovecp[0];
-	}
-
-	vec->i_type = type;
-	vec->i_addr = lv->lv_buf + lv->lv_buf_len;
-
-	ASSERT(IS_ALIGNED((unsigned long)vec->i_addr, sizeof(uint64_t)));
-
-	*vecp = vec;
-	return vec->i_addr;
-}
+void *xlog_prepare_iovec(struct xfs_log_vec *lv, struct xfs_log_iovec **vecp,
+		uint type);
 
-/*
- * We need to make sure the next buffer is naturally aligned for the biggest
- * basic data type we put into it.  We already accounted for this padding when
- * sizing the buffer.
- *
- * However, this padding does not get written into the log, and hence we have to
- * track the space used by the log vectors separately to prevent log space hangs
- * due to inaccurate accounting (i.e. a leak) of the used log space through the
- * CIL context ticket.
- */
 static inline void
 xlog_finish_iovec(struct xfs_log_vec *lv, struct xfs_log_iovec *vec, int len)
 {
-	lv->lv_buf_len += round_up(len, sizeof(uint64_t));
+	struct xlog_op_header	*oph = vec->i_addr;
+
+	/* opheader tracks payload length, logvec tracks region length */
+	oph->oh_len = cpu_to_be32(len);
+
+	len += sizeof(struct xlog_op_header);
+	lv->lv_buf_len += len;
 	lv->lv_bytes += len;
 	vec->i_len = len;
 }
@@ -118,12 +95,8 @@ void	xfs_log_mount_cancel(struct xfs_mount *);
 xfs_lsn_t xlog_assign_tail_lsn(struct xfs_mount *mp);
 xfs_lsn_t xlog_assign_tail_lsn_locked(struct xfs_mount *mp);
 void	xfs_log_space_wake(struct xfs_mount *mp);
-int	  xfs_log_reserve(struct xfs_mount *mp,
-			  int		   length,
-			  int		   count,
-			  struct xlog_ticket **ticket,
-			  uint8_t		   clientid,
-			  bool		   permanent);
+int	xfs_log_reserve(struct xfs_mount *mp, int length, int count,
+			struct xlog_ticket **ticket, bool permanent);
 int	xfs_log_regrant(struct xfs_mount *mp, struct xlog_ticket *tic);
 void	xfs_log_unmount(struct xfs_mount *mp);
 bool	xfs_log_writable(struct xfs_mount *mp);

fs/xfs/xfs_log_cil.c

@@ -37,7 +37,7 @@ xlog_cil_ticket_alloc(
 {
 	struct xlog_ticket *tic;
 
-	tic = xlog_ticket_alloc(log, 0, 1, XFS_TRANSACTION, 0);
+	tic = xlog_ticket_alloc(log, 0, 1, 0);
 
 	/*
 	 * set the current reservation to zero so we know to steal the basic
@@ -214,13 +214,20 @@ xlog_cil_alloc_shadow_bufs(
 		}
 
 		/*
-		 * We 64-bit align the length of each iovec so that the start
-		 * of the next one is naturally aligned.  We'll need to
-		 * account for that slack space here. Then round nbytes up
-		 * to 64-bit alignment so that the initial buffer alignment is
-		 * easy to calculate and verify.
+		 * We 64-bit align the length of each iovec so that the start of
+		 * the next one is naturally aligned.  We'll need to account for
+		 * that slack space here.
+		 *
+		 * We also add the xlog_op_header to each region when
+		 * formatting, but that's not accounted to the size of the item
+		 * at this point. Hence we'll need an addition number of bytes
+		 * for each vector to hold an opheader.
+		 *
+		 * Then round nbytes up to 64-bit alignment so that the initial
+		 * buffer alignment is easy to calculate and verify.
 		 */
-		nbytes += niovecs * sizeof(uint64_t);
+		nbytes += niovecs *
+			(sizeof(uint64_t) + sizeof(struct xlog_op_header));
 		nbytes = round_up(nbytes, sizeof(uint64_t));
 
 		/*
@@ -277,22 +284,18 @@ xlog_cil_alloc_shadow_bufs(
 
 /*
  * Prepare the log item for insertion into the CIL. Calculate the difference in
- * log space and vectors it will consume, and if it is a new item pin it as
- * well.
+ * log space it will consume, and if it is a new item pin it as well.
  */
 STATIC void
 xfs_cil_prepare_item(
 	struct xlog		*log,
 	struct xfs_log_vec	*lv,
 	struct xfs_log_vec	*old_lv,
-	int			*diff_len,
-	int			*diff_iovecs)
+	int			*diff_len)
 {
 	/* Account for the new LV being passed in */
-	if (lv->lv_buf_len != XFS_LOG_VEC_ORDERED) {
+	if (lv->lv_buf_len != XFS_LOG_VEC_ORDERED)
 		*diff_len += lv->lv_bytes;
-		*diff_iovecs += lv->lv_niovecs;
-	}
 
 	/*
 	 * If there is no old LV, this is the first time we've seen the item in
@@ -309,7 +312,6 @@ xfs_cil_prepare_item(
 		ASSERT(lv->lv_buf_len != XFS_LOG_VEC_ORDERED);
 
 		*diff_len -= old_lv->lv_bytes;
-		*diff_iovecs -= old_lv->lv_niovecs;
 		lv->lv_item->li_lv_shadow = old_lv;
 	}
 
@@ -358,12 +360,10 @@ static void
 xlog_cil_insert_format_items(
 	struct xlog		*log,
 	struct xfs_trans	*tp,
-	int			*diff_len,
-	int			*diff_iovecs)
+	int			*diff_len)
 {
 	struct xfs_log_item	*lip;
 
-
 	/* Bail out if we didn't find a log item.  */
 	if (list_empty(&tp->t_items)) {
 		ASSERT(0);
@@ -406,7 +406,6 @@ xlog_cil_insert_format_items(
 			 * set the item up as though it is a new insertion so
 			 * that the space reservation accounting is correct.
 			 */
-			*diff_iovecs -= lv->lv_niovecs;
 			*diff_len -= lv->lv_bytes;
 
 			/* Ensure the lv is set up according to ->iop_size */
@@ -431,7 +430,7 @@ xlog_cil_insert_format_items(
 		ASSERT(IS_ALIGNED((unsigned long)lv->lv_buf, sizeof(uint64_t)));
 		lip->li_ops->iop_format(lip, lv);
 insert:
-		xfs_cil_prepare_item(log, lv, old_lv, diff_len, diff_iovecs);
+		xfs_cil_prepare_item(log, lv, old_lv, diff_len);
 	}
 }
 
@@ -451,7 +450,6 @@ xlog_cil_insert_items(
 	struct xfs_cil_ctx	*ctx = cil->xc_ctx;
 	struct xfs_log_item	*lip;
 	int			len = 0;
-	int			diff_iovecs = 0;
 	int			iclog_space;
 	int			iovhdr_res = 0, split_res = 0, ctx_res = 0;
 
@@ -461,15 +459,10 @@ xlog_cil_insert_items(
 	 * We can do this safely because the context can't checkpoint until we
 	 * are done so it doesn't matter exactly how we update the CIL.
 	 */
-	xlog_cil_insert_format_items(log, tp, &len, &diff_iovecs);
+	xlog_cil_insert_format_items(log, tp, &len);
 
 	spin_lock(&cil->xc_cil_lock);
 
-	/* account for space used by new iovec headers  */
-	iovhdr_res = diff_iovecs * sizeof(xlog_op_header_t);
-	len += iovhdr_res;
-	ctx->nvecs += diff_iovecs;
-
 	/* attach the transaction to the CIL if it has any busy extents */
 	if (!list_empty(&tp->t_busy))
 		list_splice_init(&tp->t_busy, &ctx->busy_extents);
@@ -822,7 +815,8 @@ xlog_cil_order_write(
 static int
 xlog_cil_write_chain(
 	struct xfs_cil_ctx	*ctx,
-	struct xfs_log_vec	*chain)
+	struct xfs_log_vec	*chain,
+	uint32_t		chain_len)
 {
 	struct xlog		*log = ctx->cil->xc_log;
 	int			error;
@@ -830,7 +824,7 @@ xlog_cil_write_chain(
 	error = xlog_cil_order_write(ctx->cil, ctx->sequence, _START_RECORD);
 	if (error)
 		return error;
-	return xlog_write(log, ctx, chain, ctx->ticket, XLOG_START_TRANS);
+	return xlog_write(log, ctx, chain, ctx->ticket, chain_len);
 }
 
 /*
@@ -844,9 +838,14 @@ xlog_cil_write_commit_record(
 	struct xfs_cil_ctx	*ctx)
 {
 	struct xlog		*log = ctx->cil->xc_log;
+	struct xlog_op_header	ophdr = {
+		.oh_clientid = XFS_TRANSACTION,
+		.oh_tid = cpu_to_be32(ctx->ticket->t_tid),
+		.oh_flags = XLOG_COMMIT_TRANS,
+	};
 	struct xfs_log_iovec	reg = {
-		.i_addr = NULL,
-		.i_len = 0,
+		.i_addr = &ophdr,
+		.i_len = sizeof(struct xlog_op_header),
 		.i_type = XLOG_REG_TYPE_COMMIT,
 	};
 	struct xfs_log_vec	vec = {
@@ -862,12 +861,79 @@ xlog_cil_write_commit_record(
 	if (error)
 		return error;
 
-	error = xlog_write(log, ctx, &vec, ctx->ticket, XLOG_COMMIT_TRANS);
+	/* account for space used by record data */
+	ctx->ticket->t_curr_res -= reg.i_len;
+	error = xlog_write(log, ctx, &vec, ctx->ticket, reg.i_len);
 	if (error)
 		xlog_force_shutdown(log, SHUTDOWN_LOG_IO_ERROR);
 	return error;
 }
 
+struct xlog_cil_trans_hdr {
+	struct xlog_op_header	oph[2];
+	struct xfs_trans_header	thdr;
+	struct xfs_log_iovec	lhdr[2];
+};
+
+/*
+ * Build a checkpoint transaction header to begin the journal transaction.  We
+ * need to account for the space used by the transaction header here as it is
+ * not accounted for in xlog_write().
+ *
+ * This is the only place we write a transaction header, so we also build the
+ * log opheaders that indicate the start of a log transaction and wrap the
+ * transaction header. We keep the start record in it's own log vector rather
+ * than compacting them into a single region as this ends up making the logic
+ * in xlog_write() for handling empty opheaders for start, commit and unmount
+ * records much simpler.
+ */
+static void
+xlog_cil_build_trans_hdr(
+	struct xfs_cil_ctx	*ctx,
+	struct xlog_cil_trans_hdr *hdr,
+	struct xfs_log_vec	*lvhdr,
+	int			num_iovecs)
+{
+	struct xlog_ticket	*tic = ctx->ticket;
+	__be32			tid = cpu_to_be32(tic->t_tid);
+
+	memset(hdr, 0, sizeof(*hdr));
+
+	/* Log start record */
+	hdr->oph[0].oh_tid = tid;
+	hdr->oph[0].oh_clientid = XFS_TRANSACTION;
+	hdr->oph[0].oh_flags = XLOG_START_TRANS;
+
+	/* log iovec region pointer */
+	hdr->lhdr[0].i_addr = &hdr->oph[0];
+	hdr->lhdr[0].i_len = sizeof(struct xlog_op_header);
+	hdr->lhdr[0].i_type = XLOG_REG_TYPE_LRHEADER;
+
+	/* log opheader */
+	hdr->oph[1].oh_tid = tid;
+	hdr->oph[1].oh_clientid = XFS_TRANSACTION;
+	hdr->oph[1].oh_len = cpu_to_be32(sizeof(struct xfs_trans_header));
+
+	/* transaction header in host byte order format */
+	hdr->thdr.th_magic = XFS_TRANS_HEADER_MAGIC;
+	hdr->thdr.th_type = XFS_TRANS_CHECKPOINT;
+	hdr->thdr.th_tid = tic->t_tid;
+	hdr->thdr.th_num_items = num_iovecs;
+
+	/* log iovec region pointer */
+	hdr->lhdr[1].i_addr = &hdr->oph[1];
+	hdr->lhdr[1].i_len = sizeof(struct xlog_op_header) +
+				sizeof(struct xfs_trans_header);
+	hdr->lhdr[1].i_type = XLOG_REG_TYPE_TRANSHDR;
+
+	lvhdr->lv_niovecs = 2;
+	lvhdr->lv_iovecp = &hdr->lhdr[0];
+	lvhdr->lv_bytes = hdr->lhdr[0].i_len + hdr->lhdr[1].i_len;
+	lvhdr->lv_next = ctx->lv_chain;
+
+	tic->t_curr_res -= lvhdr->lv_bytes;
+}
+
 /*
  * Push the Committed Item List to the log.
  *
@@ -892,11 +958,10 @@ xlog_cil_push_work(
 	struct xlog		*log = cil->xc_log;
 	struct xfs_log_vec	*lv;
 	struct xfs_cil_ctx	*new_ctx;
-	struct xlog_ticket	*tic;
-	int			num_iovecs;
+	int			num_iovecs = 0;
+	int			num_bytes = 0;
 	int			error = 0;
-	struct xfs_trans_header thdr;
-	struct xfs_log_iovec	lhdr;
+	struct xlog_cil_trans_hdr thdr;
 	struct xfs_log_vec	lvhdr = { NULL };
 	xfs_csn_t		push_seq;
 	bool			push_commit_stable;
@@ -975,7 +1040,6 @@ xlog_cil_push_work(
 	 * by the flush lock.
 	 */
 	lv = NULL;
-	num_iovecs = 0;
 	while (!list_empty(&cil->xc_cil)) {
 		struct xfs_log_item	*item;
 
@@ -989,6 +1053,10 @@ xlog_cil_push_work(
 		lv = item->li_lv;
 		item->li_lv = NULL;
 		num_iovecs += lv->lv_niovecs;
+
+		/* we don't write ordered log vectors */
+		if (lv->lv_buf_len != XFS_LOG_VEC_ORDERED)
+			num_bytes += lv->lv_bytes;
 	}
 
 	/*
@@ -1025,26 +1093,11 @@ xlog_cil_push_work(
 	 * Build a checkpoint transaction header and write it to the log to
 	 * begin the transaction. We need to account for the space used by the
 	 * transaction header here as it is not accounted for in xlog_write().
-	 *
-	 * The LSN we need to pass to the log items on transaction commit is
-	 * the LSN reported by the first log vector write. If we use the commit
-	 * record lsn then we can move the tail beyond the grant write head.
-	 */
-	tic = ctx->ticket;
-	thdr.th_magic = XFS_TRANS_HEADER_MAGIC;
-	thdr.th_type = XFS_TRANS_CHECKPOINT;
-	thdr.th_tid = tic->t_tid;
-	thdr.th_num_items = num_iovecs;
-	lhdr.i_addr = &thdr;
-	lhdr.i_len = sizeof(xfs_trans_header_t);
-	lhdr.i_type = XLOG_REG_TYPE_TRANSHDR;
-	tic->t_curr_res -= lhdr.i_len + sizeof(xlog_op_header_t);
-
-	lvhdr.lv_niovecs = 1;
-	lvhdr.lv_iovecp = &lhdr;
-	lvhdr.lv_next = ctx->lv_chain;
-
-	error = xlog_cil_write_chain(ctx, &lvhdr);
+	 */
+	xlog_cil_build_trans_hdr(ctx, &thdr, &lvhdr, num_iovecs);
+	num_bytes += lvhdr.lv_bytes;
+
+	error = xlog_cil_write_chain(ctx, &lvhdr, num_bytes);
 	if (error)
 		goto out_abort_free_ticket;
 
@@ -1052,7 +1105,7 @@ xlog_cil_push_work(
 	if (error)
 		goto out_abort_free_ticket;
 
-	xfs_log_ticket_ungrant(log, tic);
+	xfs_log_ticket_ungrant(log, ctx->ticket);
 
 	/*
 	 * If the checkpoint spans multiple iclogs, wait for all previous iclogs
@@ -1116,7 +1169,7 @@ xlog_cil_push_work(
 	return;
 
 out_abort_free_ticket:
-	xfs_log_ticket_ungrant(log, tic);
+	xfs_log_ticket_ungrant(log, ctx->ticket);
 	ASSERT(xlog_is_shutdown(log));
 	if (!ctx->commit_iclog) {
 		xlog_cil_committed(ctx);

fs/xfs/xfs_log_priv.h

@@ -142,19 +142,6 @@ enum xlog_iclog_state {
 
 #define XLOG_COVER_OPS		5
 
-/* Ticket reservation region accounting */ 
-#define XLOG_TIC_LEN_MAX	15
-
-/*
- * Reservation region
- * As would be stored in xfs_log_iovec but without the i_addr which
- * we don't care about.
- */
-typedef struct xlog_res {
-	uint	r_len;	/* region length		:4 */
-	uint	r_type;	/* region's transaction type	:4 */
-} xlog_res_t;
-
 typedef struct xlog_ticket {
 	struct list_head   t_queue;	 /* reserve/write queue */
 	struct task_struct *t_task;	 /* task that owns this ticket */
@@ -164,15 +151,7 @@ typedef struct xlog_ticket {
 	int		   t_unit_res;	 /* unit reservation in bytes    : 4  */
 	char		   t_ocnt;	 /* original count		 : 1  */
 	char		   t_cnt;	 /* current count		 : 1  */
-	char		   t_clientid;	 /* who does this belong to;	 : 1  */
 	uint8_t		   t_flags;	 /* properties of reservation	 : 1  */
-
-        /* reservation array fields */
-	uint		   t_res_num;                    /* num in array : 4 */
-	uint		   t_res_num_ophdrs;		 /* num op hdrs  : 4 */
-	uint		   t_res_arr_sum;		 /* array sum    : 4 */
-	uint		   t_res_o_flow;		 /* sum overflow : 4 */
-	xlog_res_t	   t_res_arr[XLOG_TIC_LEN_MAX];  /* array of res : 8 * 15 */ 
 } xlog_ticket_t;
 
 /*
@@ -211,7 +190,7 @@ typedef struct xlog_in_core {
 	u32			ic_offset;
 	enum xlog_iclog_state	ic_state;
 	unsigned int		ic_flags;
-	char			*ic_datap;	/* pointer to iclog data */
+	void			*ic_datap;	/* pointer to iclog data */
 	struct list_head	ic_callbacks;
 
 	/* reference counts need their own cacheline */
@@ -242,7 +221,6 @@ struct xfs_cil_ctx {
 	xfs_lsn_t		commit_lsn;	/* chkpt commit record lsn */
 	struct xlog_in_core	*commit_iclog;
 	struct xlog_ticket	*ticket;	/* chkpt ticket */
-	int			nvecs;		/* number of regions */
 	int			space_used;	/* aggregate size of regions */
 	struct list_head	busy_extents;	/* busy extents in chkpt */
 	struct xfs_log_vec	*lv_chain;	/* logvecs being pushed */
@@ -441,10 +419,6 @@ struct xlog {
 
 	struct xfs_kobj		l_kobj;
 
-	/* The following field are used for debugging; need to hold icloglock */
-#ifdef DEBUG
-	void			*l_iclog_bak[XLOG_MAX_ICLOGS];
-#endif
 	/* log recovery lsn tracking (for buffer submission */
 	xfs_lsn_t		l_recovery_lsn;
 
@@ -509,27 +483,14 @@ extern __le32	 xlog_cksum(struct xlog *log, struct xlog_rec_header *rhead,
 			    char *dp, int size);
 
 extern struct kmem_cache *xfs_log_ticket_cache;
-struct xlog_ticket *
-xlog_ticket_alloc(
-	struct xlog	*log,
-	int		unit_bytes,
-	int		count,
-	char		client,
-	bool		permanent);
-
-static inline void
-xlog_write_adv_cnt(void **ptr, int *len, int *off, size_t bytes)
-{
-	*ptr += bytes;
-	*len -= bytes;
-	*off += bytes;
-}
+struct xlog_ticket *xlog_ticket_alloc(struct xlog *log, int unit_bytes,
+		int count, bool permanent);
 
 void	xlog_print_tic_res(struct xfs_mount *mp, struct xlog_ticket *ticket);
 void	xlog_print_trans(struct xfs_trans *);
 int	xlog_write(struct xlog *log, struct xfs_cil_ctx *ctx,
 		struct xfs_log_vec *log_vector, struct xlog_ticket *tic,
-		uint optype);
+		uint32_t len);
 void	xfs_log_ticket_ungrant(struct xlog *log, struct xlog_ticket *ticket);
 void	xfs_log_ticket_regrant(struct xlog *log, struct xlog_ticket *ticket);
 

fs/xfs/xfs_trans.c

@@ -194,11 +194,9 @@ xfs_trans_reserve(
 			ASSERT(resp->tr_logflags & XFS_TRANS_PERM_LOG_RES);
 			error = xfs_log_regrant(mp, tp->t_ticket);
 		} else {
-			error = xfs_log_reserve(mp,
-						resp->tr_logres,
+			error = xfs_log_reserve(mp, resp->tr_logres,
 						resp->tr_logcount,
-						&tp->t_ticket, XFS_TRANSACTION,
-						permanent);
+						&tp->t_ticket, permanent);
 		}
 
 		if (error)