1 files changed, 372 insertions, 75 deletions

diff --git a/fs/xfs/xfs_discard.c b/fs/xfs/xfs_discard.c
index d5787991bb5b..0b343776da8c 100644
--- a/fs/xfs/xfs_discard.c
+++ b/fs/xfs/xfs_discard.c
@@ -8,6 +8,7 @@
 #include "xfs_format.h"
 #include "xfs_log_format.h"
 #include "xfs_trans_resv.h"
+#include "xfs_trans.h"
 #include "xfs_mount.h"
 #include "xfs_btree.h"
 #include "xfs_alloc_btree.h"
@@ -18,6 +19,8 @@
 #include "xfs_trace.h"
 #include "xfs_log.h"
 #include "xfs_ag.h"
+#include "xfs_health.h"
+#include "xfs_rtbitmap.h"
 
 /*
  * Notes on an efficient, low latency fstrim algorithm
@@ -79,7 +82,7 @@ xfs_discard_endio_work(
 		container_of(work, struct xfs_busy_extents, endio_work);
 
 	xfs_extent_busy_clear(extents->mount, &extents->extent_list, false);
-	kmem_free(extents->owner);
+	kfree(extents->owner);
 }
 
 /*
@@ -120,7 +123,7 @@ xfs_discard_extents(
 		error = __blkdev_issue_discard(mp->m_ddev_targp->bt_bdev,
 				XFS_AGB_TO_DADDR(mp, busyp->agno, busyp->bno),
 				XFS_FSB_TO_BB(mp, busyp->length),
-				GFP_NOFS, &bio);
+				GFP_KERNEL, &bio);
 		if (error && error != -EOPNOTSUPP) {
 			xfs_info(mp,
 	 "discard failed for extent [0x%llx,%u], error %d",
@@ -143,18 +146,30 @@ xfs_discard_extents(
 	return error;
 }
 
+/*
+ * Care must be taken setting up the trim cursor as the perags may not have been
+ * initialised when the cursor is initialised. e.g. a clean mount which hasn't
+ * read in AGFs and the first operation run on the mounted fs is a trim. This
+ * can result in perag fields that aren't initialised until
+ * xfs_trim_gather_extents() calls xfs_alloc_read_agf() to lock down the AG for
+ * the free space search.
+ */
+struct xfs_trim_cur {
+	xfs_agblock_t	start;
+	xfs_extlen_t	count;
+	xfs_agblock_t	end;
+	xfs_extlen_t	minlen;
+	bool		by_bno;
+};
 
 static int
 xfs_trim_gather_extents(
 	struct xfs_perag	*pag,
-	xfs_daddr_t		start,
-	xfs_daddr_t		end,
-	xfs_daddr_t		minlen,
-	struct xfs_alloc_rec_incore *tcur,
-	struct xfs_busy_extents	*extents,
-	uint64_t		*blocks_trimmed)
+	struct xfs_trim_cur	*tcur,
+	struct xfs_busy_extents	*extents)
 {
 	struct xfs_mount	*mp = pag->pag_mount;
+	struct xfs_trans	*tp;
 	struct xfs_btree_cur	*cur;
 	struct xfs_buf		*agbp;
 	int			error;
@@ -168,25 +183,42 @@ xfs_trim_gather_extents(
 	 */
 	xfs_log_force(mp, XFS_LOG_SYNC);
 
-	error = xfs_alloc_read_agf(pag, NULL, 0, &agbp);
+	error = xfs_trans_alloc_empty(mp, &tp);
 	if (error)
 		return error;
 
-	cur = xfs_allocbt_init_cursor(mp, NULL, agbp, pag, XFS_BTNUM_CNT);
+	error = xfs_alloc_read_agf(pag, tp, 0, &agbp);
+	if (error)
+		goto out_trans_cancel;
 
 	/*
-	 * Look up the extent length requested in the AGF and start with it.
+	 * First time through tcur->count will not have been initialised as
+	 * pag->pagf_longest is not guaranteed to be valid before we read
+	 * the AGF buffer above.
 	 */
-	if (tcur->ar_startblock == NULLAGBLOCK)
-		error = xfs_alloc_lookup_ge(cur, 0, tcur->ar_blockcount, &i);
-	else
-		error = xfs_alloc_lookup_le(cur, tcur->ar_startblock,
-				tcur->ar_blockcount, &i);
+	if (!tcur->count)
+		tcur->count = pag->pagf_longest;
+
+	if (tcur->by_bno) {
+		/* sub-AG discard request always starts at tcur->start */
+		cur = xfs_bnobt_init_cursor(mp, tp, agbp, pag);
+		error = xfs_alloc_lookup_le(cur, tcur->start, 0, &i);
+		if (!error && !i)
+			error = xfs_alloc_lookup_ge(cur, tcur->start, 0, &i);
+	} else if (tcur->start == 0) {
+		/* first time through a by-len starts with max length */
+		cur = xfs_cntbt_init_cursor(mp, tp, agbp, pag);
+		error = xfs_alloc_lookup_ge(cur, 0, tcur->count, &i);
+	} else {
+		/* nth time through a by-len starts where we left off */
+		cur = xfs_cntbt_init_cursor(mp, tp, agbp, pag);
+		error = xfs_alloc_lookup_le(cur, tcur->start, tcur->count, &i);
+	}
 	if (error)
 		goto out_del_cursor;
 	if (i == 0) {
 		/* nothing of that length left in the AG, we are done */
-		tcur->ar_blockcount = 0;
+		tcur->count = 0;
 		goto out_del_cursor;
 	}
 
@@ -197,13 +229,12 @@ xfs_trim_gather_extents(
 	while (i) {
 		xfs_agblock_t	fbno;
 		xfs_extlen_t	flen;
-		xfs_daddr_t	dbno;
-		xfs_extlen_t	dlen;
 
 		error = xfs_alloc_get_rec(cur, &fbno, &flen, &i);
 		if (error)
 			break;
 		if (XFS_IS_CORRUPT(mp, i != 1)) {
+			xfs_btree_mark_sick(cur);
 			error = -EFSCORRUPTED;
 			break;
 		}
@@ -213,38 +244,46 @@ xfs_trim_gather_extents(
 			 * Update the cursor to point at this extent so we
 			 * restart the next batch from this extent.
 			 */
-			tcur->ar_startblock = fbno;
-			tcur->ar_blockcount = flen;
-			break;
-		}
-
-		/*
-		 * use daddr format for all range/len calculations as that is
-		 * the format the range/len variables are supplied in by
-		 * userspace.
-		 */
-		dbno = XFS_AGB_TO_DADDR(mp, pag->pag_agno, fbno);
-		dlen = XFS_FSB_TO_BB(mp, flen);
-
-		/*
-		 * Too small?  Give up.
-		 */
-		if (dlen < minlen) {
-			trace_xfs_discard_toosmall(mp, pag->pag_agno, fbno, flen);
-			tcur->ar_blockcount = 0;
+			tcur->start = fbno;
+			tcur->count = flen;
 			break;
 		}
 
 		/*
 		 * If the extent is entirely outside of the range we are
-		 * supposed to discard skip it.  Do not bother to trim
-		 * down partially overlapping ranges for now.
+		 * supposed to skip it.  Do not bother to trim down partially
+		 * overlapping ranges for now.
 		 */
-		if (dbno + dlen < start || dbno > end) {
+		if (fbno + flen < tcur->start) {
+			trace_xfs_discard_exclude(mp, pag->pag_agno, fbno, flen);
+			goto next_extent;
+		}
+		if (fbno > tcur->end) {
 			trace_xfs_discard_exclude(mp, pag->pag_agno, fbno, flen);
+			if (tcur->by_bno) {
+				tcur->count = 0;
+				break;
+			}
 			goto next_extent;
 		}
 
+		/* Trim the extent returned to the range we want. */
+		if (fbno < tcur->start) {
+			flen -= tcur->start - fbno;
+			fbno = tcur->start;
+		}
+		if (fbno + flen > tcur->end + 1)
+			flen = tcur->end - fbno + 1;
+
+		/* Too small?  Give up. */
+		if (flen < tcur->minlen) {
+			trace_xfs_discard_toosmall(mp, pag->pag_agno, fbno, flen);
+			if (tcur->by_bno)
+				goto next_extent;
+			tcur->count = 0;
+			break;
+		}
+
 		/*
 		 * If any blocks in the range are still busy, skip the
 		 * discard and try again the next time.
@@ -256,9 +295,11 @@ xfs_trim_gather_extents(
 
 		xfs_extent_busy_insert_discard(pag, fbno, flen,
 				&extents->extent_list);
-		*blocks_trimmed += flen;
 next_extent:
-		error = xfs_btree_decrement(cur, 0, &i);
+		if (tcur->by_bno)
+			error = xfs_btree_increment(cur, 0, &i);
+		else
+			error = xfs_btree_decrement(cur, 0, &i);
 		if (error)
 			break;
 
@@ -268,7 +309,7 @@ next_extent:
 		 * is no more extents to search.
 		 */
 		if (i == 0)
-			tcur->ar_blockcount = 0;
+			tcur->count = 0;
 	}
 
 	/*
@@ -279,7 +320,8 @@ next_extent:
 		xfs_extent_busy_clear(mp, &extents->extent_list, false);
 out_del_cursor:
 	xfs_btree_del_cursor(cur, error);
-	xfs_buf_relse(agbp);
+out_trans_cancel:
+	xfs_trans_cancel(tp);
 	return error;
 }
 
@@ -295,19 +337,22 @@ xfs_trim_should_stop(void)
  * we found in the last batch as the key to start the next.
  */
 static int
-xfs_trim_extents(
+xfs_trim_perag_extents(
 	struct xfs_perag	*pag,
-	xfs_daddr_t		start,
-	xfs_daddr_t		end,
-	xfs_daddr_t		minlen,
-	uint64_t		*blocks_trimmed)
+	xfs_agblock_t		start,
+	xfs_agblock_t		end,
+	xfs_extlen_t		minlen)
 {
-	struct xfs_alloc_rec_incore tcur = {
-		.ar_blockcount = pag->pagf_longest,
-		.ar_startblock = NULLAGBLOCK,
+	struct xfs_trim_cur	tcur = {
+		.start		= start,
+		.end		= end,
+		.minlen		= minlen,
 	};
 	int			error = 0;
 
+	if (start != 0 || end != pag->block_count)
+		tcur.by_bno = true;
+
 	do {
 		struct xfs_busy_extents	*extents;
 
@@ -321,8 +366,7 @@ xfs_trim_extents(
 		extents->owner = extents;
 		INIT_LIST_HEAD(&extents->extent_list);
 
-		error = xfs_trim_gather_extents(pag, start, end, minlen,
-				&tcur, extents, blocks_trimmed);
+		error = xfs_trim_gather_extents(pag, &tcur, extents);
 		if (error) {
 			kfree(extents);
 			break;
@@ -345,12 +389,256 @@ xfs_trim_extents(
 		if (xfs_trim_should_stop())
 			break;
 
-	} while (tcur.ar_blockcount != 0);
+	} while (tcur.count != 0);
 
 	return error;
 
 }
 
+static int
+xfs_trim_datadev_extents(
+	struct xfs_mount	*mp,
+	xfs_daddr_t		start,
+	xfs_daddr_t		end,
+	xfs_extlen_t		minlen)
+{
+	xfs_agnumber_t		start_agno, end_agno;
+	xfs_agblock_t		start_agbno, end_agbno;
+	xfs_daddr_t		ddev_end;
+	struct xfs_perag	*pag;
+	int			last_error = 0, error;
+
+	ddev_end = min_t(xfs_daddr_t, end,
+			 XFS_FSB_TO_BB(mp, mp->m_sb.sb_dblocks) - 1);
+
+	start_agno = xfs_daddr_to_agno(mp, start);
+	start_agbno = xfs_daddr_to_agbno(mp, start);
+	end_agno = xfs_daddr_to_agno(mp, ddev_end);
+	end_agbno = xfs_daddr_to_agbno(mp, ddev_end);
+
+	for_each_perag_range(mp, start_agno, end_agno, pag) {
+		xfs_agblock_t	agend = pag->block_count;
+
+		if (start_agno == end_agno)
+			agend = end_agbno;
+		error = xfs_trim_perag_extents(pag, start_agbno, agend, minlen);
+		if (error)
+			last_error = error;
+
+		if (xfs_trim_should_stop()) {
+			xfs_perag_rele(pag);
+			break;
+		}
+		start_agbno = 0;
+	}
+
+	return last_error;
+}
+
+#ifdef CONFIG_XFS_RT
+struct xfs_trim_rtdev {
+	/* list of rt extents to free */
+	struct list_head	extent_list;
+
+	/* minimum length that caller allows us to trim */
+	xfs_rtblock_t		minlen_fsb;
+
+	/* restart point for the rtbitmap walk */
+	xfs_rtxnum_t		restart_rtx;
+
+	/* stopping point for the current rtbitmap walk */
+	xfs_rtxnum_t		stop_rtx;
+};
+
+struct xfs_rtx_busy {
+	struct list_head	list;
+	xfs_rtblock_t		bno;
+	xfs_rtblock_t		length;
+};
+
+static void
+xfs_discard_free_rtdev_extents(
+	struct xfs_trim_rtdev	*tr)
+{
+	struct xfs_rtx_busy	*busyp, *n;
+
+	list_for_each_entry_safe(busyp, n, &tr->extent_list, list) {
+		list_del_init(&busyp->list);
+		kfree(busyp);
+	}
+}
+
+/*
+ * Walk the discard list and issue discards on all the busy extents in the
+ * list. We plug and chain the bios so that we only need a single completion
+ * call to clear all the busy extents once the discards are complete.
+ */
+static int
+xfs_discard_rtdev_extents(
+	struct xfs_mount	*mp,
+	struct xfs_trim_rtdev	*tr)
+{
+	struct block_device	*bdev = mp->m_rtdev_targp->bt_bdev;
+	struct xfs_rtx_busy	*busyp;
+	struct bio		*bio = NULL;
+	struct blk_plug		plug;
+	xfs_rtblock_t		start = NULLRTBLOCK, length = 0;
+	int			error = 0;
+
+	blk_start_plug(&plug);
+	list_for_each_entry(busyp, &tr->extent_list, list) {
+		if (start == NULLRTBLOCK)
+			start = busyp->bno;
+		length += busyp->length;
+
+		trace_xfs_discard_rtextent(mp, busyp->bno, busyp->length);
+
+		error = __blkdev_issue_discard(bdev,
+				XFS_FSB_TO_BB(mp, busyp->bno),
+				XFS_FSB_TO_BB(mp, busyp->length),
+				GFP_NOFS, &bio);
+		if (error)
+			break;
+	}
+	xfs_discard_free_rtdev_extents(tr);
+
+	if (bio) {
+		error = submit_bio_wait(bio);
+		if (error == -EOPNOTSUPP)
+			error = 0;
+		if (error)
+			xfs_info(mp,
+	 "discard failed for rtextent [0x%llx,%llu], error %d",
+				 (unsigned long long)start,
+				 (unsigned long long)length,
+				 error);
+		bio_put(bio);
+	}
+	blk_finish_plug(&plug);
+
+	return error;
+}
+
+static int
+xfs_trim_gather_rtextent(
+	struct xfs_mount		*mp,
+	struct xfs_trans		*tp,
+	const struct xfs_rtalloc_rec	*rec,
+	void				*priv)
+{
+	struct xfs_trim_rtdev		*tr = priv;
+	struct xfs_rtx_busy		*busyp;
+	xfs_rtblock_t			rbno, rlen;
+
+	if (rec->ar_startext > tr->stop_rtx) {
+		/*
+		 * If we've scanned a large number of rtbitmap blocks, update
+		 * the cursor to point at this extent so we restart the next
+		 * batch from this extent.
+		 */
+		tr->restart_rtx = rec->ar_startext;
+		return -ECANCELED;
+	}
+
+	rbno = xfs_rtx_to_rtb(mp, rec->ar_startext);
+	rlen = xfs_rtx_to_rtb(mp, rec->ar_extcount);
+
+	/* Ignore too small. */
+	if (rlen < tr->minlen_fsb) {
+		trace_xfs_discard_rttoosmall(mp, rbno, rlen);
+		return 0;
+	}
+
+	busyp = kzalloc(sizeof(struct xfs_rtx_busy), GFP_KERNEL);
+	if (!busyp)
+		return -ENOMEM;
+
+	busyp->bno = rbno;
+	busyp->length = rlen;
+	INIT_LIST_HEAD(&busyp->list);
+	list_add_tail(&busyp->list, &tr->extent_list);
+
+	tr->restart_rtx = rec->ar_startext + rec->ar_extcount;
+	return 0;
+}
+
+static int
+xfs_trim_rtdev_extents(
+	struct xfs_mount	*mp,
+	xfs_daddr_t		start,
+	xfs_daddr_t		end,
+	xfs_daddr_t		minlen)
+{
+	struct xfs_trim_rtdev	tr = {
+		.minlen_fsb	= XFS_BB_TO_FSB(mp, minlen),
+	};
+	xfs_rtxnum_t		low, high;
+	struct xfs_trans	*tp;
+	xfs_daddr_t		rtdev_daddr;
+	int			error;
+
+	INIT_LIST_HEAD(&tr.extent_list);
+
+	/* Shift the start and end downwards to match the rt device. */
+	rtdev_daddr = XFS_FSB_TO_BB(mp, mp->m_sb.sb_dblocks);
+	if (start > rtdev_daddr)
+		start -= rtdev_daddr;
+	else
+		start = 0;
+
+	if (end <= rtdev_daddr)
+		return 0;
+	end -= rtdev_daddr;
+
+	error = xfs_trans_alloc_empty(mp, &tp);
+	if (error)
+		return error;
+
+	end = min_t(xfs_daddr_t, end,
+			XFS_FSB_TO_BB(mp, mp->m_sb.sb_rblocks) - 1);
+
+	/* Convert the rt blocks to rt extents */
+	low = xfs_rtb_to_rtxup(mp, XFS_BB_TO_FSB(mp, start));
+	high = xfs_rtb_to_rtx(mp, XFS_BB_TO_FSBT(mp, end));
+
+	/*
+	 * Walk the free ranges between low and high.  The query_range function
+	 * trims the extents returned.
+	 */
+	do {
+		tr.stop_rtx = low + (mp->m_sb.sb_blocksize * NBBY);
+		xfs_rtbitmap_lock_shared(mp, XFS_RBMLOCK_BITMAP);
+		error = xfs_rtalloc_query_range(mp, tp, low, high,
+				xfs_trim_gather_rtextent, &tr);
+
+		if (error == -ECANCELED)
+			error = 0;
+		if (error) {
+			xfs_rtbitmap_unlock_shared(mp, XFS_RBMLOCK_BITMAP);
+			xfs_discard_free_rtdev_extents(&tr);
+			break;
+		}
+
+		if (list_empty(&tr.extent_list)) {
+			xfs_rtbitmap_unlock_shared(mp, XFS_RBMLOCK_BITMAP);
+			break;
+		}
+
+		error = xfs_discard_rtdev_extents(mp, &tr);
+		xfs_rtbitmap_unlock_shared(mp, XFS_RBMLOCK_BITMAP);
+		if (error)
+			break;
+
+		low = tr.restart_rtx;
+	} while (!xfs_trim_should_stop() && low <= high);
+
+	xfs_trans_cancel(tp);
+	return error;
+}
+#else
+# define xfs_trim_rtdev_extents(...)	(-EOPNOTSUPP)
+#endif /* CONFIG_XFS_RT */
+
 /*
  * trim a range of the filesystem.
  *
@@ -359,26 +647,36 @@ xfs_trim_extents(
  * addressing. FSB addressing is sparse (AGNO|AGBNO), while the incoming format
  * is a linear address range. Hence we need to use DADDR based conversions and
  * comparisons for determining the correct offset and regions to trim.
+ *
+ * The realtime device is mapped into the FITRIM "address space" immediately
+ * after the data device.
  */
 int
 xfs_ioc_trim(
 	struct xfs_mount		*mp,
 	struct fstrim_range __user	*urange)
 {
-	struct xfs_perag	*pag;
 	unsigned int		granularity =
 		bdev_discard_granularity(mp->m_ddev_targp->bt_bdev);
+	struct block_device	*rt_bdev = NULL;
 	struct fstrim_range	range;
-	xfs_daddr_t		start, end, minlen;
-	xfs_agnumber_t		agno;
-	uint64_t		blocks_trimmed = 0;
+	xfs_daddr_t		start, end;
+	xfs_extlen_t		minlen;
+	xfs_rfsblock_t		max_blocks;
 	int			error, last_error = 0;
 
 	if (!capable(CAP_SYS_ADMIN))
 		return -EPERM;
-	if (!bdev_max_discard_sectors(mp->m_ddev_targp->bt_bdev))
+	if (mp->m_rtdev_targp &&
+	    bdev_max_discard_sectors(mp->m_rtdev_targp->bt_bdev))
+		rt_bdev = mp->m_rtdev_targp->bt_bdev;
+	if (!bdev_max_discard_sectors(mp->m_ddev_targp->bt_bdev) && !rt_bdev)
 		return -EOPNOTSUPP;
 
+	if (rt_bdev)
+		granularity = max(granularity,
+				  bdev_discard_granularity(rt_bdev));
+
 	/*
 	 * We haven't recovered the log, so we cannot use our bnobt-guided
 	 * storage zapping commands.
@@ -390,7 +688,8 @@ xfs_ioc_trim(
 		return -EFAULT;
 
 	range.minlen = max_t(u64, granularity, range.minlen);
-	minlen = BTOBB(range.minlen);
+	minlen = XFS_B_TO_FSB(mp, range.minlen);
+
 	/*
 	 * Truncating down the len isn't actually quite correct, but using
 	 * BBTOB would mean we trivially get overflows for values
@@ -398,7 +697,8 @@ xfs_ioc_trim(
 	 * used by the fstrim application.  In the end it really doesn't
 	 * matter as trimming blocks is an advisory interface.
 	 */
-	if (range.start >= XFS_FSB_TO_B(mp, mp->m_sb.sb_dblocks) ||
+	max_blocks = mp->m_sb.sb_dblocks + mp->m_sb.sb_rblocks;
+	if (range.start >= XFS_FSB_TO_B(mp, max_blocks) ||
 	    range.minlen > XFS_FSB_TO_B(mp, mp->m_ag_max_usable) ||
 	    range.len < mp->m_sb.sb_blocksize)
 		return -EINVAL;
@@ -406,26 +706,23 @@ xfs_ioc_trim(
 	start = BTOBB(range.start);
 	end = start + BTOBBT(range.len) - 1;
 
-	if (end > XFS_FSB_TO_BB(mp, mp->m_sb.sb_dblocks) - 1)
-		end = XFS_FSB_TO_BB(mp, mp->m_sb.sb_dblocks) - 1;
-
-	agno = xfs_daddr_to_agno(mp, start);
-	for_each_perag_range(mp, agno, xfs_daddr_to_agno(mp, end), pag) {
-		error = xfs_trim_extents(pag, start, end, minlen,
-					  &blocks_trimmed);
+	if (bdev_max_discard_sectors(mp->m_ddev_targp->bt_bdev)) {
+		error = xfs_trim_datadev_extents(mp, start, end, minlen);
 		if (error)
 			last_error = error;
+	}
 
-		if (xfs_trim_should_stop()) {
-			xfs_perag_rele(pag);
-			break;
-		}
+	if (rt_bdev && !xfs_trim_should_stop()) {
+		error = xfs_trim_rtdev_extents(mp, start, end, minlen);
+		if (error)
+			last_error = error;
 	}
 
 	if (last_error)
 		return last_error;
 
-	range.len = XFS_FSB_TO_B(mp, blocks_trimmed);
+	range.len = min_t(unsigned long long, range.len,
+			  XFS_FSB_TO_B(mp, max_blocks) - range.start);
 	if (copy_to_user(urange, &range, sizeof(range)))
 		return -EFAULT;
 	return 0;