- 4.1.16

[packages/kernel.git] / kernel-small_fixes.patch

--- linux-2.6.33/scripts/mod/modpost.c~	2010-02-24 19:52:17.000000000 +0100
+++ linux-2.6.33/scripts/mod/modpost.c	2010-03-07 14:26:47.242168558 +0100
@@ -15,7 +15,8 @@
 #include <stdio.h>
 #include <ctype.h>
 #include "modpost.h"
-#include "../../include/generated/autoconf.h"
+// PLD architectures don't use CONFIG_SYMBOL_PREFIX
+//#include "../../include/generated/autoconf.h"
 #include "../../include/linux/license.h"
 
 /* Some toolchains use a `_' prefix for all user symbols. */

--- linux-3.0/scripts/kconfig/lxdialog/check-lxdialog.sh~	2011-07-22 04:17:23.000000000 +0200
+++ linux-3.0/scripts/kconfig/lxdialog/check-lxdialog.sh	2011-08-25 21:26:04.799150642 +0200
@@ -9,6 +9,12 @@
 			$cc -print-file-name=lib${lib}.${ext} | grep -q /
 			if [ $? -eq 0 ]; then
 				echo "-l${lib}"
+				for libt in tinfow tinfo ; do
+					$cc -print-file-name=lib${libt}.${ext} | grep -q /
+					if [ $? -eq 0 ]; then
+						echo "-l${libt}"
+					fi
+				done
 				exit
 			fi
 		done

From 30927520dbae297182990bb21d08762bcc35ce1d Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 9 Sep 2015 21:55:07 -0700
Subject: [PATCH] tcp_cubic: better follow cubic curve after idle period

Jana Iyengar found an interesting issue on CUBIC :

The epoch is only updated/reset initially and when experiencing losses.
The delta "t" of now - epoch_start can be arbitrary large after app idle
as well as the bic_target. Consequentially the slope (inverse of
ca->cnt) would be really large, and eventually ca->cnt would be
lower-bounded in the end to 2 to have delayed-ACK slow-start behavior.

This particularly shows up when slow_start_after_idle is disabled
as a dangerous cwnd inflation (1.5 x RTT) after few seconds of idle
time.

Jana initial fix was to reset epoch_start if app limited,
but Neal pointed out it would ask the CUBIC algorithm to recalculate the
curve so that we again start growing steeply upward from where cwnd is
now (as CUBIC does just after a loss). Ideally we'd want the cwnd growth
curve to be the same shape, just shifted later in time by the amount of
the idle period.

Reported-by: Jana Iyengar <jri@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: Neal Cardwell <ncardwell@google.com>
Cc: Stephen Hemminger <stephen@networkplumber.org>
Cc: Sangtae Ha <sangtae.ha@gmail.com>
Cc: Lawrence Brakmo <lawrence@brakmo.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_cubic.c | 16 ++++++++++++++++
 1 file changed, 16 insertions(+)

diff --git a/net/ipv4/tcp_cubic.c b/net/ipv4/tcp_cubic.c
index 28011fb1..c6ded6b 100644
--- a/net/ipv4/tcp_cubic.c
+++ b/net/ipv4/tcp_cubic.c
@@ -151,6 +151,21 @@ static void bictcp_init(struct sock *sk)
 		tcp_sk(sk)->snd_ssthresh = initial_ssthresh;
 }
 
+static void bictcp_cwnd_event(struct sock *sk, enum tcp_ca_event event)
+{
+	if (event == CA_EVENT_TX_START) {
+		s32 delta = tcp_time_stamp - tcp_sk(sk)->lsndtime;
+		struct bictcp *ca = inet_csk_ca(sk);
+
+		/* We were application limited (idle) for a while.
+		 * Shift epoch_start to keep cwnd growth to cubic curve.
+		 */
+		if (ca->epoch_start && delta > 0)
+			ca->epoch_start += delta;
+		return;
+	}
+}
+
 /* calculate the cubic root of x using a table lookup followed by one
  * Newton-Raphson iteration.
  * Avg err ~= 0.195%
@@ -450,6 +465,7 @@ static struct tcp_congestion_ops cubictcp __read_mostly = {
 	.cong_avoid	= bictcp_cong_avoid,
 	.set_state	= bictcp_state,
 	.undo_cwnd	= bictcp_undo_cwnd,
+	.cwnd_event	= bictcp_cwnd_event,
 	.pkts_acked     = bictcp_acked,
 	.owner		= THIS_MODULE,
 	.name		= "cubic",
 
From 7a29ac474a47eb8cf212b45917683ae89d6fa13b Mon Sep 17 00:00:00 2001
From: Chris Mason <clm@fb.com>
Date: Tue, 10 Nov 2015 10:10:34 +1100
Subject: xfs: give all workqueues rescuer threads

We're consistently hitting deadlocks here with XFS on recent kernels.
After some digging through the crash files, it looks like everyone in
the system is waiting for XFS to reclaim memory.

Something like this:

PID: 2733434  TASK: ffff8808cd242800  CPU: 19  COMMAND: "java"
 #0 [ffff880019c53588] __schedule at ffffffff818c4df2
 #1 [ffff880019c535d8] schedule at ffffffff818c5517
 #2 [ffff880019c535f8] _xfs_log_force_lsn at ffffffff81316348
 #3 [ffff880019c53688] xfs_log_force_lsn at ffffffff813164fb
 #4 [ffff880019c536b8] xfs_iunpin_wait at ffffffff8130835e
 #5 [ffff880019c53728] xfs_reclaim_inode at ffffffff812fd453
 #6 [ffff880019c53778] xfs_reclaim_inodes_ag at ffffffff812fd8c7
 #7 [ffff880019c53928] xfs_reclaim_inodes_nr at ffffffff812fe433
 #8 [ffff880019c53958] xfs_fs_free_cached_objects at ffffffff8130d3b9
 #9 [ffff880019c53968] super_cache_scan at ffffffff811a6f73
#10 [ffff880019c539c8] shrink_slab at ffffffff811460e6
#11 [ffff880019c53aa8] shrink_zone at ffffffff8114a53f
#12 [ffff880019c53b48] do_try_to_free_pages at ffffffff8114a8ba
#13 [ffff880019c53be8] try_to_free_pages at ffffffff8114ad5a
#14 [ffff880019c53c78] __alloc_pages_nodemask at ffffffff8113e1b8
#15 [ffff880019c53d88] alloc_kmem_pages_node at ffffffff8113e671
#16 [ffff880019c53dd8] copy_process at ffffffff8104f781
#17 [ffff880019c53ec8] do_fork at ffffffff8105129c
#18 [ffff880019c53f38] sys_clone at ffffffff810515b6
#19 [ffff880019c53f48] stub_clone at ffffffff818c8e4d

xfs_log_force_lsn is waiting for logs to get cleaned, which is waiting
for IO, which is waiting for workers to complete the IO which is waiting
for worker threads that don't exist yet:

PID: 2752451  TASK: ffff880bd6bdda00  CPU: 37  COMMAND: "kworker/37:1"
 #0 [ffff8808d20abbb0] __schedule at ffffffff818c4df2
 #1 [ffff8808d20abc00] schedule at ffffffff818c5517
 #2 [ffff8808d20abc20] schedule_timeout at ffffffff818c7c6c
 #3 [ffff8808d20abcc0] wait_for_completion_killable at ffffffff818c6495
 #4 [ffff8808d20abd30] kthread_create_on_node at ffffffff8106ec82
 #5 [ffff8808d20abdf0] create_worker at ffffffff8106752f
 #6 [ffff8808d20abe40] worker_thread at ffffffff810699be
 #7 [ffff8808d20abec0] kthread at ffffffff8106ef59
 #8 [ffff8808d20abf50] ret_from_fork at ffffffff818c8ac8

I think we should be using WQ_MEM_RECLAIM to make sure this thread
pool makes progress when we're not able to allocate new workers.

[dchinner: make all workqueues WQ_MEM_RECLAIM]

Signed-off-by: Chris Mason <clm@fb.com>
Reviewed-by: Dave Chinner <dchinner@redhat.com>
Signed-off-by: Dave Chinner <david@fromorbit.com>
---
 fs/xfs/xfs_super.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c
index 29531ec..65fbfb7 100644
--- a/fs/xfs/xfs_super.c
+++ b/fs/xfs/xfs_super.c
@@ -838,17 +838,18 @@ xfs_init_mount_workqueues(
 		goto out_destroy_unwritten;
 
 	mp->m_reclaim_workqueue = alloc_workqueue("xfs-reclaim/%s",
-			WQ_FREEZABLE, 0, mp->m_fsname);
+			WQ_MEM_RECLAIM|WQ_FREEZABLE, 0, mp->m_fsname);
 	if (!mp->m_reclaim_workqueue)
 		goto out_destroy_cil;
 
 	mp->m_log_workqueue = alloc_workqueue("xfs-log/%s",
-			WQ_FREEZABLE|WQ_HIGHPRI, 0, mp->m_fsname);
+			WQ_MEM_RECLAIM|WQ_FREEZABLE|WQ_HIGHPRI, 0,
+			mp->m_fsname);
 	if (!mp->m_log_workqueue)
 		goto out_destroy_reclaim;
 
 	mp->m_eofblocks_workqueue = alloc_workqueue("xfs-eofblocks/%s",
-			WQ_FREEZABLE, 0, mp->m_fsname);
+			WQ_MEM_RECLAIM|WQ_FREEZABLE, 0, mp->m_fsname);
 	if (!mp->m_eofblocks_workqueue)
 		goto out_destroy_log;
 
-- 
cgit v0.11.2

From: Dave Chinner <dchinner@redhat.com>

When we do inode readahead in log recovery, we do can do the
readahead before we've replayed the icreate transaction that stamps
the buffer with inode cores. The inode readahead verifier catches
this and marks the buffer as !done to indicate that it doesn't yet
contain valid inodes.

In adding buffer error notification  (i.e. setting b_error = -EIO at
the same time as as we clear the done flag) to such a readahead
verifier failure, we can then get subsequent inode recovery failing
with this error:

XFS (dm-0): metadata I/O error: block 0xa00060 ("xlog_recover_do..(read#2)") error 5 numblks 32

This occurs when readahead completion races with icreate item replay
such as:

	inode readahead
		find buffer
		lock buffer
		submit RA io
	....
	icreate recovery
	    xfs_trans_get_buffer
		find buffer
		lock buffer
		<blocks on RA completion>
	.....
	<ra completion>
		fails verifier
		clear XBF_DONE
		set bp->b_error = -EIO
		release and unlock buffer
	<icreate gains lock>
	icreate initialises buffer
	marks buffer as done
	adds buffer to delayed write queue
	releases buffer

At this point, we have an initialised inode buffer that is up to
date but has an -EIO state registered against it. When we finally
get to recovering an inode in that buffer:

	inode item recovery
	    xfs_trans_read_buffer
		find buffer
		lock buffer
		sees XBF_DONE is set, returns buffer
	    sees bp->b_error is set
		fail log recovery!

Essentially, we need xfs_trans_get_buf_map() to clear the error status of
the buffer when doing a lookup. This function returns uninitialised
buffers, so the buffer returned can not be in an error state and
none of the code that uses this function expects b_error to be set
on return. Indeed, there is an ASSERT(!bp->b_error); in the
transaction case in xfs_trans_get_buf_map() that would have caught
this if log recovery used transactions....

This patch firstly changes the inode readahead failure to set -EIO
on the buffer, and secondly changes xfs_buf_get_map() to never
return a buffer with an error state set so this first change doesn't
cause unexpected log recovery failures.

Signed-off-by: Dave Chinner <dchinner@redhat.com>
---
 fs/xfs/libxfs/xfs_inode_buf.c | 12 +++++++-----
 fs/xfs/xfs_buf.c              |  7 +++++++
 2 files changed, 14 insertions(+), 5 deletions(-)

diff --git a/fs/xfs/libxfs/xfs_inode_buf.c b/fs/xfs/libxfs/xfs_inode_buf.c
index 1b8d98a..ff17c48 100644
--- a/fs/xfs/libxfs/xfs_inode_buf.c
+++ b/fs/xfs/libxfs/xfs_inode_buf.c
@@ -62,11 +62,12 @@ xfs_inobp_check(
  * has not had the inode cores stamped into it. Hence for readahead, the buffer
  * may be potentially invalid.
  *
- * If the readahead buffer is invalid, we don't want to mark it with an error,
- * but we do want to clear the DONE status of the buffer so that a followup read
- * will re-read it from disk. This will ensure that we don't get an unnecessary
- * warnings during log recovery and we don't get unnecssary panics on debug
- * kernels.
+ * If the readahead buffer is invalid, we need to mark it with an error and
+ * clear the DONE status of the buffer so that a followup read will re-read it
+ * from disk. We don't report the error otherwise to avoid warnings during log
+ * recovery and we don't get unnecssary panics on debug kernels. We use EIO here
+ * because all we want to do is say readahead failed; there is no-one to report
+ * the error to, so this will distinguish it from a non-ra verifier failure.
  */
 static void
 xfs_inode_buf_verify(
@@ -93,6 +94,7 @@ xfs_inode_buf_verify(
 						XFS_RANDOM_ITOBP_INOTOBP))) {
 			if (readahead) {
 				bp->b_flags &= ~XBF_DONE;
+				xfs_buf_ioerror(bp, -EIO);
 				return;
 			}
 
diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c
index 45a8ea7..ae86b16 100644
--- a/fs/xfs/xfs_buf.c
+++ b/fs/xfs/xfs_buf.c
@@ -604,6 +604,13 @@ found:
 		}
 	}
 
+	/*
+	 * Clear b_error if this is a lookup from a caller that doesn't expect
+	 * valid data to be found in the buffer.
+	 */
+	if (!(flags & XBF_READ))
+		xfs_buf_ioerror(bp, 0);
+
 	XFS_STATS_INC(xb_get);
 	trace_xfs_buf_get(bp, flags, _RET_IP_);
 	return bp;
-- 
2.5.0

_______________________________________________
xfs mailing list
xfs@oss.sgi.com
http://oss.sgi.com/mailman/listinfo/xfs
From: Dave Chinner <dchinner@redhat.com>

When we do dquot readahead in log recovery, we do not use a verifier
as the underlying buffer may not have dquots in it. e.g. the
allocation operation hasn't yet been replayed. Hence we do not want
to fail recovery because we detect an operation to be replayed has
not been run yet. This problem was addressed for inodes in commit
d891400 ("xfs: inode buffers may not be valid during recovery
readahead") but the problem was not recognised to exist for dquots
and their buffers as the dquot readahead did not have a verifier.

The result of not using a verifier is that when the buffer is then
next read to replay a dquot modification, the dquot buffer verifier
will only be attached to the buffer if *readahead is not complete*.
Hence we can read the buffer, replay the dquot changes and then add
it to the delwri submission list without it having a verifier
attached to it. This then generates warnings in xfs_buf_ioapply(),
which catches and warns about this case.

Fix this and make it handle the same readahead verifier error cases
as for inode buffers by adding a new readahead verifier that has a
write operation as well as a read operation that marks the buffer as
not done if any corruption is detected.  Also make sure we don't run
readahead if the dquot buffer has been marked as cancelled by
recovery.

This will result in readahead either succeeding and the buffer
having a valid write verifier, or readahead failing and the buffer
state requiring the subsequent read to resubmit the IO with the new
verifier.  In either case, this will result in the buffer always
ending up with a valid write verifier on it.

Note: we also need to fix the inode buffer readahead error handling
to mark the buffer with EIO. Brian noticed the code I copied from
there wrong during review, so fix it at the same time. Add comments
linking the two functions that handle readahead verifier errors
together so we don't forget this behavioural link in future.

cc: <stable@vger.kernel.org> # 3.12 - current
Signed-off-by: Dave Chinner <dchinner@redhat.com>
Reviewed-by: Brian Foster <bfoster@redhat.com>
Signed-off-by: Dave Chinner <david@fromorbit.com>
---
 fs/xfs/libxfs/xfs_dquot_buf.c  | 36 ++++++++++++++++++++++++++++++------
 fs/xfs/libxfs/xfs_inode_buf.c  |  2 ++
 fs/xfs/libxfs/xfs_quota_defs.h |  2 +-
 fs/xfs/libxfs/xfs_shared.h     |  1 +
 fs/xfs/xfs_log_recover.c       |  9 +++++++--
 5 files changed, 41 insertions(+), 9 deletions(-)

diff --git a/fs/xfs/libxfs/xfs_dquot_buf.c b/fs/xfs/libxfs/xfs_dquot_buf.c
index 11cefb2..3cc3cf7 100644
--- a/fs/xfs/libxfs/xfs_dquot_buf.c
+++ b/fs/xfs/libxfs/xfs_dquot_buf.c
@@ -54,7 +54,7 @@ xfs_dqcheck(
 	xfs_dqid_t	 id,
 	uint		 type,	  /* used only when IO_dorepair is true */
 	uint		 flags,
-	char		 *str)
+	const char	 *str)
 {
 	xfs_dqblk_t	 *d = (xfs_dqblk_t *)ddq;
 	int		errs = 0;
@@ -207,7 +207,8 @@ xfs_dquot_buf_verify_crc(
 STATIC bool
 xfs_dquot_buf_verify(
 	struct xfs_mount	*mp,
-	struct xfs_buf		*bp)
+	struct xfs_buf		*bp,
+	int			warn)
 {
 	struct xfs_dqblk	*d = (struct xfs_dqblk *)bp->b_addr;
 	xfs_dqid_t		id = 0;
@@ -240,8 +241,7 @@ xfs_dquot_buf_verify(
 		if (i == 0)
 			id = be32_to_cpu(ddq->d_id);
 
-		error = xfs_dqcheck(mp, ddq, id + i, 0, XFS_QMOPT_DOWARN,
-				       "xfs_dquot_buf_verify");
+		error = xfs_dqcheck(mp, ddq, id + i, 0, warn, __func__);
 		if (error)
 			return false;
 	}
@@ -256,7 +256,7 @@ xfs_dquot_buf_read_verify(
 
 	if (!xfs_dquot_buf_verify_crc(mp, bp))
 		xfs_buf_ioerror(bp, -EFSBADCRC);
-	else if (!xfs_dquot_buf_verify(mp, bp))
+	else if (!xfs_dquot_buf_verify(mp, bp, XFS_QMOPT_DOWARN))
 		xfs_buf_ioerror(bp, -EFSCORRUPTED);
 
 	if (bp->b_error)
@@ -264,6 +264,25 @@ xfs_dquot_buf_read_verify(
 }
 
 /*
+ * readahead errors are silent and simply leave the buffer as !done so a real
+ * read will then be run with the xfs_dquot_buf_ops verifier. See
+ * xfs_inode_buf_verify() for why we use EIO and ~XBF_DONE here rather than
+ * reporting the failure.
+ */
+static void
+xfs_dquot_buf_readahead_verify(
+	struct xfs_buf	*bp)
+{
+	struct xfs_mount	*mp = bp->b_target->bt_mount;
+
+	if (!xfs_dquot_buf_verify_crc(mp, bp) ||
+	    !xfs_dquot_buf_verify(mp, bp, 0)) {
+		xfs_buf_ioerror(bp, -EIO);
+		bp->b_flags &= ~XBF_DONE;
+	}
+}
+
+/*
  * we don't calculate the CRC here as that is done when the dquot is flushed to
  * the buffer after the update is done. This ensures that the dquot in the
  * buffer always has an up-to-date CRC value.
@@ -274,7 +293,7 @@ xfs_dquot_buf_write_verify(
 {
 	struct xfs_mount	*mp = bp->b_target->bt_mount;
 
-	if (!xfs_dquot_buf_verify(mp, bp)) {
+	if (!xfs_dquot_buf_verify(mp, bp, XFS_QMOPT_DOWARN)) {
 		xfs_buf_ioerror(bp, -EFSCORRUPTED);
 		xfs_verifier_error(bp);
 		return;
@@ -287,3 +306,8 @@ const struct xfs_buf_ops xfs_dquot_buf_ops = {
 	.verify_write = xfs_dquot_buf_write_verify,
 };
 
+const struct xfs_buf_ops xfs_dquot_buf_ra_ops = {
+
+	.verify_read = xfs_dquot_buf_readahead_verify,
+	.verify_write = xfs_dquot_buf_write_verify,
+};
diff --git a/fs/xfs/libxfs/xfs_inode_buf.c b/fs/xfs/libxfs/xfs_inode_buf.c
index ff17c48..1aabfda 100644
--- a/fs/xfs/libxfs/xfs_inode_buf.c
+++ b/fs/xfs/libxfs/xfs_inode_buf.c
@@ -68,6 +68,8 @@ xfs_inobp_check(
  * recovery and we don't get unnecssary panics on debug kernels. We use EIO here
  * because all we want to do is say readahead failed; there is no-one to report
  * the error to, so this will distinguish it from a non-ra verifier failure.
+ * Changes to this readahead error behavour also need to be reflected in
+ * xfs_dquot_buf_readahead_verify().
  */
 static void
 xfs_inode_buf_verify(
diff --git a/fs/xfs/libxfs/xfs_quota_defs.h b/fs/xfs/libxfs/xfs_quota_defs.h
index 1b0a083..f51078f 100644
--- a/fs/xfs/libxfs/xfs_quota_defs.h
+++ b/fs/xfs/libxfs/xfs_quota_defs.h
@@ -153,7 +153,7 @@ typedef __uint16_t	xfs_qwarncnt_t;
 #define XFS_QMOPT_RESBLK_MASK	(XFS_QMOPT_RES_REGBLKS | XFS_QMOPT_RES_RTBLKS)
 
 extern int xfs_dqcheck(struct xfs_mount *mp, xfs_disk_dquot_t *ddq,
-		       xfs_dqid_t id, uint type, uint flags, char *str);
+		       xfs_dqid_t id, uint type, uint flags, const char *str);
 extern int xfs_calc_dquots_per_chunk(unsigned int nbblks);
 
 #endif	/* __XFS_QUOTA_H__ */
diff --git a/fs/xfs/libxfs/xfs_shared.h b/fs/xfs/libxfs/xfs_shared.h
index 5be5297..15c3ceb 100644
--- a/fs/xfs/libxfs/xfs_shared.h
+++ b/fs/xfs/libxfs/xfs_shared.h
@@ -49,6 +49,7 @@ extern const struct xfs_buf_ops xfs_inobt_buf_ops;
 extern const struct xfs_buf_ops xfs_inode_buf_ops;
 extern const struct xfs_buf_ops xfs_inode_buf_ra_ops;
 extern const struct xfs_buf_ops xfs_dquot_buf_ops;
+extern const struct xfs_buf_ops xfs_dquot_buf_ra_ops;
 extern const struct xfs_buf_ops xfs_sb_buf_ops;
 extern const struct xfs_buf_ops xfs_sb_quiet_buf_ops;
 extern const struct xfs_buf_ops xfs_symlink_buf_ops;
diff --git a/fs/xfs/xfs_log_recover.c b/fs/xfs/xfs_log_recover.c
index c5ecaac..5991cdc 100644
--- a/fs/xfs/xfs_log_recover.c
+++ b/fs/xfs/xfs_log_recover.c
@@ -3204,6 +3204,7 @@ xlog_recover_dquot_ra_pass2(
 	struct xfs_disk_dquot	*recddq;
 	struct xfs_dq_logformat	*dq_f;
 	uint			type;
+	int			len;
 
 
 	if (mp->m_qflags == 0)
@@ -3224,8 +3225,12 @@ xlog_recover_dquot_ra_pass2(
 	ASSERT(dq_f);
 	ASSERT(dq_f->qlf_len == 1);
 
-	xfs_buf_readahead(mp->m_ddev_targp, dq_f->qlf_blkno,
-			  XFS_FSB_TO_BB(mp, dq_f->qlf_len), NULL);
+	len = XFS_FSB_TO_BB(mp, dq_f->qlf_len);
+	if (xlog_peek_buffer_cancelled(log, dq_f->qlf_blkno, len, 0))
+		return;
+
+	xfs_buf_readahead(mp->m_ddev_targp, dq_f->qlf_blkno, len,
+			  &xfs_dquot_buf_ra_ops);
 }
 
 STATIC void
-- 
2.5.0

_______________________________________________
xfs mailing list
xfs@oss.sgi.com
http://oss.sgi.com/mailman/listinfo/xfs