1 files changed, 249 insertions, 142 deletions

diff --git a/fs/xfs/xfs_log_cil.c b/fs/xfs/xfs_log_cil.c
index c9f55e4f0957..db6cb7800251 100644
--- a/fs/xfs/xfs_log_cil.c
+++ b/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
@@ -48,6 +48,38 @@ xlog_cil_ticket_alloc(
 }
 
 /*
+ * Check if the current log item was first committed in this sequence.
+ * We can't rely on just the log item being in the CIL, we have to check
+ * the recorded commit sequence number.
+ *
+ * Note: for this to be used in a non-racy manner, it has to be called with
+ * CIL flushing locked out. As a result, it should only be used during the
+ * transaction commit process when deciding what to format into the item.
+ */
+static bool
+xlog_item_in_current_chkpt(
+	struct xfs_cil		*cil,
+	struct xfs_log_item	*lip)
+{
+	if (list_empty(&lip->li_cil))
+		return false;
+
+	/*
+	 * li_seq is written on the first commit of a log item to record the
+	 * first checkpoint it is written to. Hence if it is different to the
+	 * current sequence, we're in a new checkpoint.
+	 */
+	return lip->li_seq == READ_ONCE(cil->xc_current_sequence);
+}
+
+bool
+xfs_log_item_in_current_chkpt(
+	struct xfs_log_item *lip)
+{
+	return xlog_item_in_current_chkpt(lip->li_log->l_cilp, lip);
+}
+
+/*
  * Unavoidable forward declaration - xlog_cil_push_work() calls
  * xlog_cil_ctx_alloc() itself.
  */
@@ -103,39 +135,6 @@ xlog_cil_iovec_space(
 }
 
 /*
- * shadow buffers can be large, so we need to use kvmalloc() here to ensure
- * success. Unfortunately, kvmalloc() only allows GFP_KERNEL contexts to fall
- * back to vmalloc, so we can't actually do anything useful with gfp flags to
- * control the kmalloc() behaviour within kvmalloc(). Hence kmalloc() will do
- * direct reclaim and compaction in the slow path, both of which are
- * horrendously expensive. We just want kmalloc to fail fast and fall back to
- * vmalloc if it can't get somethign straight away from the free lists or buddy
- * allocator. Hence we have to open code kvmalloc outselves here.
- *
- * Also, we are in memalloc_nofs_save task context here, so despite the use of
- * GFP_KERNEL here, we are actually going to be doing GFP_NOFS allocations. This
- * is actually the only way to make vmalloc() do GFP_NOFS allocations, so lets
- * just all pretend this is a GFP_KERNEL context operation....
- */
-static inline void *
-xlog_cil_kvmalloc(
-	size_t		buf_size)
-{
-	gfp_t		flags = GFP_KERNEL;
-	void		*p;
-
-	flags &= ~__GFP_DIRECT_RECLAIM;
-	flags |= __GFP_NOWARN | __GFP_NORETRY;
-	do {
-		p = kmalloc(buf_size, flags);
-		if (!p)
-			p = vmalloc(buf_size);
-	} while (!p);
-
-	return p;
-}
-
-/*
  * Allocate or pin log vector buffers for CIL insertion.
  *
  * The CIL currently uses disposable buffers for copying a snapshot of the
@@ -214,13 +213,20 @@ 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));
 
 		/*
@@ -244,7 +250,7 @@ xlog_cil_alloc_shadow_bufs(
 			 * storage.
 			 */
 			kmem_free(lip->li_lv_shadow);
-			lv = xlog_cil_kvmalloc(buf_size);
+			lv = xlog_kvmalloc(buf_size);
 
 			memset(lv, 0, xlog_cil_iovec_space(niovecs));
 
@@ -277,22 +283,18 @@ 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 +311,6 @@ 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 +359,10 @@ 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 +405,6 @@ 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 +429,7 @@ 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);
 	}
 }
 
@@ -445,13 +443,13 @@ insert:
 static void
 xlog_cil_insert_items(
 	struct xlog		*log,
-	struct xfs_trans	*tp)
+	struct xfs_trans	*tp,
+	uint32_t		released_space)
 {
 	struct xfs_cil		*cil = log->l_cilp;
 	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);
@@ -500,7 +493,9 @@ xlog_cil_insert_items(
 		ASSERT(tp->t_ticket->t_curr_res >= len);
 	}
 	tp->t_ticket->t_curr_res -= len;
+	tp->t_ticket->t_curr_res += released_space;
 	ctx->space_used += len;
+	ctx->space_used -= released_space;
 
 	/*
 	 * If we've overrun the reservation, dump the tx details before we move
@@ -822,7 +817,8 @@ restart:
 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 +826,7 @@ 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 +840,14 @@ 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 +863,138 @@ 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;
+}
+
+/*
+ * Pull all the log vectors off the items in the CIL, and remove the items from
+ * the CIL. We don't need the CIL lock here because it's only needed on the
+ * transaction commit side which is currently locked out by the flush lock.
+ *
+ * If a log item is marked with a whiteout, we do not need to write it to the
+ * journal and so we just move them to the whiteout list for the caller to
+ * dispose of appropriately.
+ */
+static void
+xlog_cil_build_lv_chain(
+	struct xfs_cil		*cil,
+	struct xfs_cil_ctx	*ctx,
+	struct list_head	*whiteouts,
+	uint32_t		*num_iovecs,
+	uint32_t		*num_bytes)
+{
+	struct xfs_log_vec	*lv = NULL;
+
+	while (!list_empty(&cil->xc_cil)) {
+		struct xfs_log_item	*item;
+
+		item = list_first_entry(&cil->xc_cil,
+					struct xfs_log_item, li_cil);
+
+		if (test_bit(XFS_LI_WHITEOUT, &item->li_flags)) {
+			list_move(&item->li_cil, whiteouts);
+			trace_xfs_cil_whiteout_skip(item);
+			continue;
+		}
+
+		list_del_init(&item->li_cil);
+		if (!ctx->lv_chain)
+			ctx->lv_chain = item->li_lv;
+		else
+			lv->lv_next = item->li_lv;
+		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;
+	}
+}
+
+static void
+xlog_cil_cleanup_whiteouts(
+	struct list_head	*whiteouts)
+{
+	while (!list_empty(whiteouts)) {
+		struct xfs_log_item *item = list_first_entry(whiteouts,
+						struct xfs_log_item, li_cil);
+		list_del_init(&item->li_cil);
+		trace_xfs_cil_whiteout_unpin(item);
+		item->li_ops->iop_unpin(item, 1);
+	}
+}
+
 /*
  * Push the Committed Item List to the log.
  *
@@ -890,16 +1017,15 @@ xlog_cil_push_work(
 		container_of(work, struct xfs_cil_ctx, push_work);
 	struct xfs_cil		*cil = ctx->cil;
 	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;
+	LIST_HEAD		(whiteouts);
 
 	new_ctx = xlog_cil_ctx_alloc();
 	new_ctx->ticket = xlog_cil_ticket_alloc(log);
@@ -968,28 +1094,7 @@ xlog_cil_push_work(
 	list_add(&ctx->committing, &cil->xc_committing);
 	spin_unlock(&cil->xc_push_lock);
 
-	/*
-	 * Pull all the log vectors off the items in the CIL, and remove the
-	 * items from the CIL. We don't need the CIL lock here because it's only
-	 * needed on the transaction commit side which is currently locked out
-	 * by the flush lock.
-	 */
-	lv = NULL;
-	num_iovecs = 0;
-	while (!list_empty(&cil->xc_cil)) {
-		struct xfs_log_item	*item;
-
-		item = list_first_entry(&cil->xc_cil,
-					struct xfs_log_item, li_cil);
-		list_del_init(&item->li_cil);
-		if (!ctx->lv_chain)
-			ctx->lv_chain = item->li_lv;
-		else
-			lv->lv_next = item->li_lv;
-		lv = item->li_lv;
-		item->li_lv = NULL;
-		num_iovecs += lv->lv_niovecs;
-	}
+	xlog_cil_build_lv_chain(cil, ctx, &whiteouts, &num_iovecs, &num_bytes);
 
 	/*
 	 * Switch the contexts so we can drop the context lock and move out
@@ -1025,26 +1130,11 @@ 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 +1142,7 @@ 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
@@ -1107,6 +1197,7 @@ xlog_cil_push_work(
 	/* Not safe to reference ctx now! */
 
 	spin_unlock(&log->l_icloglock);
+	xlog_cil_cleanup_whiteouts(&whiteouts);
 	return;
 
 out_skip:
@@ -1116,8 +1207,9 @@ out_skip:
 	return;
 
 out_abort_free_ticket:
-	xfs_log_ticket_ungrant(log, tic);
+	xfs_log_ticket_ungrant(log, ctx->ticket);
 	ASSERT(xlog_is_shutdown(log));
+	xlog_cil_cleanup_whiteouts(&whiteouts);
 	if (!ctx->commit_iclog) {
 		xlog_cil_committed(ctx);
 		return;
@@ -1267,6 +1359,43 @@ xlog_cil_empty(
 }
 
 /*
+ * If there are intent done items in this transaction and the related intent was
+ * committed in the current (same) CIL checkpoint, we don't need to write either
+ * the intent or intent done item to the journal as the change will be
+ * journalled atomically within this checkpoint. As we cannot remove items from
+ * the CIL here, mark the related intent with a whiteout so that the CIL push
+ * can remove it rather than writing it to the journal. Then remove the intent
+ * done item from the current transaction and release it so it doesn't get put
+ * into the CIL at all.
+ */
+static uint32_t
+xlog_cil_process_intents(
+	struct xfs_cil		*cil,
+	struct xfs_trans	*tp)
+{
+	struct xfs_log_item	*lip, *ilip, *next;
+	uint32_t		len = 0;
+
+	list_for_each_entry_safe(lip, next, &tp->t_items, li_trans) {
+		if (!(lip->li_ops->flags & XFS_ITEM_INTENT_DONE))
+			continue;
+
+		ilip = lip->li_ops->iop_intent(lip);
+		if (!ilip || !xlog_item_in_current_chkpt(cil, ilip))
+			continue;
+		set_bit(XFS_LI_WHITEOUT, &ilip->li_flags);
+		trace_xfs_cil_whiteout_mark(ilip);
+		len += ilip->li_lv->lv_bytes;
+		kmem_free(ilip->li_lv);
+		ilip->li_lv = NULL;
+
+		xfs_trans_del_item(lip);
+		lip->li_ops->iop_release(lip);
+	}
+	return len;
+}
+
+/*
  * Commit a transaction with the given vector to the Committed Item List.
  *
  * To do this, we need to format the item, pin it in memory if required and
@@ -1288,6 +1417,7 @@ xlog_cil_commit(
 {
 	struct xfs_cil		*cil = log->l_cilp;
 	struct xfs_log_item	*lip, *next;
+	uint32_t		released_space = 0;
 
 	/*
 	 * Do all necessary memory allocation before we lock the CIL.
@@ -1299,7 +1429,10 @@ xlog_cil_commit(
 	/* lock out background commit */
 	down_read(&cil->xc_ctx_lock);
 
-	xlog_cil_insert_items(log, tp);
+	if (tp->t_flags & XFS_TRANS_HAS_INTENT_DONE)
+		released_space = xlog_cil_process_intents(cil, tp);
+
+	xlog_cil_insert_items(log, tp, released_space);
 
 	if (regrant && !xlog_is_shutdown(log))
 		xfs_log_ticket_regrant(log, tp->t_ticket);
@@ -1456,32 +1589,6 @@ out_shutdown:
 }
 
 /*
- * Check if the current log item was first committed in this sequence.
- * We can't rely on just the log item being in the CIL, we have to check
- * the recorded commit sequence number.
- *
- * Note: for this to be used in a non-racy manner, it has to be called with
- * CIL flushing locked out. As a result, it should only be used during the
- * transaction commit process when deciding what to format into the item.
- */
-bool
-xfs_log_item_in_current_chkpt(
-	struct xfs_log_item	*lip)
-{
-	struct xfs_cil		*cil = lip->li_log->l_cilp;
-
-	if (list_empty(&lip->li_cil))
-		return false;
-
-	/*
-	 * li_seq is written on the first commit of a log item to record the
-	 * first checkpoint it is written to. Hence if it is different to the
-	 * current sequence, we're in a new checkpoint.
-	 */
-	return lip->li_seq == READ_ONCE(cil->xc_current_sequence);
-}
-
-/*
  * Perform initial CIL structure initialisation.
  */
 int