---- 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. */
-
-From: Stephen Hemminger <shemminger@vyatta.com>
+From: Shaohua Li <shli@fb.com>
-Some BIOS's don't setup power management correctly (what else is
-new) and don't allow use of PCI Express power control. Add a special
-exception module parameter to allow working around this issue.
-Based on slightly different patch by Knut Petersen.
+Basically this is a copy of commit 001e4a8775f6(ext4: implement cgroup
+writeback support). Tested with a fio test, verified writeback is
+throttled against cgroup io.max write bandwidth, also verified moving
+the fio test to another cgroup and the writeback is throttled against
+new cgroup setting.
-Reported-by: Arkadiusz Miskiewicz <arekm@maven.pl>
-Signed-off-by: Stephen Hemminger <shemminger@vyatta.com>
+Cc: Tejun Heo <tj@kernel.org>
+Signed-off-by: Shaohua Li <shli@fb.com>
---
-Patch against -net (ie. 3.3.0)
-
---- a/drivers/net/ethernet/marvell/sky2.c 2012-01-10 10:56:56.855156017 -0800
-+++ b/drivers/net/ethernet/marvell/sky2.c 2012-03-21 08:25:52.400929532 -0700
-@@ -95,6 +95,10 @@ static int disable_msi = 0;
- module_param(disable_msi, int, 0);
- MODULE_PARM_DESC(disable_msi, "Disable Message Signaled Interrupt (MSI)");
-
-+static int legacy_pme = 0;
-+module_param(legacy_pme, int, 0);
-+MODULE_PARM_DESC(legacy_pme, "Legacy power management");
-+
- static DEFINE_PCI_DEVICE_TABLE(sky2_id_table) = {
- { PCI_DEVICE(PCI_VENDOR_ID_SYSKONNECT, 0x9000) }, /* SK-9Sxx */
- { PCI_DEVICE(PCI_VENDOR_ID_SYSKONNECT, 0x9E00) }, /* SK-9Exx */
-@@ -867,6 +871,13 @@ static void sky2_wol_init(struct sky2_po
- /* Disable PiG firmware */
- sky2_write16(hw, B0_CTST, Y2_HW_WOL_OFF);
-
-+ /* Needed by some broken BIOSes, use PCI rather than PCI-e for WOL */
-+ if (legacy_pme) {
-+ u32 reg1 = sky2_pci_read32(hw, PCI_DEV_REG1);
-+ reg1 |= PCI_Y2_PME_LEGACY;
-+ sky2_pci_write32(hw, PCI_DEV_REG1, reg1);
-+ }
-+
- /* block receiver */
- sky2_write8(hw, SK_REG(port, RX_GMF_CTRL_T), GMF_RST_SET);
- sky2_read32(hw, B0_CTST);
-
-
-The RCU problem is likely to be a separate issue. It might even be a
-result of the use-after-free problem with the elevator.
-
-At any rate, it's clear that the crash in the refcounting log you
-posted occurred because scsi_setup_blk_pc_cmnd() called
-scsi_prep_state_check(), which tried to dereference the NULL pointer.
-
-Would you like to try this patch to see if it fixes the problem? As I
-said before, I'm not certain it's the best thing to do, but it worked
-on my system.
-
-Alan Stern
-
-
-Index: usb-3.0/drivers/scsi/scsi_lib.c
-===================================================================
---- usb-3.0.orig/drivers/scsi/scsi_lib.c
-+++ usb-3.0/drivers/scsi/scsi_lib.c
-@@ -1247,6 +1247,8 @@ int scsi_prep_fn(struct request_queue *q
- struct scsi_device *sdev = q->queuedata;
- int ret = BLKPREP_KILL;
-
-+ if (!sdev)
-+ return ret;
- if (req->cmd_type == REQ_TYPE_BLOCK_PC)
- ret = scsi_setup_blk_pc_cmnd(sdev, req);
- return scsi_prep_return(q, req, ret);
-Index: usb-3.0/drivers/scsi/scsi_sysfs.c
-===================================================================
---- usb-3.0.orig/drivers/scsi/scsi_sysfs.c
-+++ usb-3.0/drivers/scsi/scsi_sysfs.c
-@@ -322,6 +322,8 @@ static void scsi_device_dev_release_user
- kfree(evt);
+ fs/xfs/xfs_aops.c | 2 ++
+ fs/xfs/xfs_super.c | 1 +
+ 2 files changed, 3 insertions(+)
+
+--- linux-4.19/fs/xfs/xfs_aops.c.org 2018-11-21 10:31:12.348955352 +0100
++++ linux-4.19/fs/xfs/xfs_aops.c 2018-11-21 10:34:35.241764742 +0100
+@@ -613,8 +613,10 @@ xfs_add_to_ioend(
+ list_add(&wpc->ioend->io_list, iolist);
+ wpc->ioend = xfs_alloc_ioend(inode, wpc->io_type, offset,
+ bdev, sector);
++ wbc_init_bio(wbc, wpc->ioend->io_bio);
}
-+ /* Freeing the queue signals to block that we're done */
-+ scsi_free_queue(sdev->request_queue);
- blk_put_queue(sdev->request_queue);
- /* NULL queue means the device can't be used */
- sdev->request_queue = NULL;
-@@ -936,8 +938,6 @@ void __scsi_remove_device(struct scsi_de
- /* cause the request function to reject all I/O requests */
- sdev->request_queue->queuedata = NULL;
++ wbc_account_io(wbc, page, len);
+ if (!__bio_try_merge_page(wpc->ioend->io_bio, page, len, poff)) {
+ if (iop)
+ atomic_inc(&iop->write_count);
+diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c
+index 584cf2d..aea3bc2 100644
+--- a/fs/xfs/xfs_super.c
++++ b/fs/xfs/xfs_super.c
+@@ -1634,6 +1634,7 @@ xfs_fs_fill_super(
+ sb->s_max_links = XFS_MAXLINK;
+ sb->s_time_gran = 1;
+ set_posix_acl_flag(sb);
++ sb->s_iflags |= SB_I_CGROUPWB;
-- /* Freeing the queue signals to block that we're done */
-- scsi_free_queue(sdev->request_queue);
- put_device(dev);
- }
-
-
-
---
-To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
-the body of a message to majordomo@vger.kernel.org
-More majordomo info at http://vger.kernel.org/majordomo-info.html
-Please read the FAQ at http://www.tux.org/lkml/
---- 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
-
-
+ /* version 5 superblocks support inode version counters. */
+ if (XFS_SB_VERSION_NUM(&mp->m_sb) == XFS_SB_VERSION_5)
+From e820d55cb99dd93ac2dc949cf486bb187e5cd70d Mon Sep 17 00:00:00 2001
+From: Guoqing Jiang <gqjiang@suse.com>
+Date: Wed, 19 Dec 2018 14:19:25 +0800
+Subject: md: fix raid10 hang issue caused by barrier
+MIME-Version: 1.0
+Content-Type: text/plain; charset=UTF-8
+Content-Transfer-Encoding: 8bit
+
+When both regular IO and resync IO happen at the same time,
+and if we also need to split regular. Then we can see tasks
+hang due to barrier.
+
+1. resync thread
+[ 1463.757205] INFO: task md1_resync:5215 blocked for more than 480 seconds.
+[ 1463.757207] Not tainted 4.19.5-1-default #1
+[ 1463.757209] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message.
+[ 1463.757212] md1_resync D 0 5215 2 0x80000000
+[ 1463.757216] Call Trace:
+[ 1463.757223] ? __schedule+0x29a/0x880
+[ 1463.757231] ? raise_barrier+0x8d/0x140 [raid10]
+[ 1463.757236] schedule+0x78/0x110
+[ 1463.757243] raise_barrier+0x8d/0x140 [raid10]
+[ 1463.757248] ? wait_woken+0x80/0x80
+[ 1463.757257] raid10_sync_request+0x1f6/0x1e30 [raid10]
+[ 1463.757265] ? _raw_spin_unlock_irq+0x22/0x40
+[ 1463.757284] ? is_mddev_idle+0x125/0x137 [md_mod]
+[ 1463.757302] md_do_sync.cold.78+0x404/0x969 [md_mod]
+[ 1463.757311] ? wait_woken+0x80/0x80
+[ 1463.757336] ? md_rdev_init+0xb0/0xb0 [md_mod]
+[ 1463.757351] md_thread+0xe9/0x140 [md_mod]
+[ 1463.757358] ? _raw_spin_unlock_irqrestore+0x2e/0x60
+[ 1463.757364] ? __kthread_parkme+0x4c/0x70
+[ 1463.757369] kthread+0x112/0x130
+[ 1463.757374] ? kthread_create_worker_on_cpu+0x40/0x40
+[ 1463.757380] ret_from_fork+0x3a/0x50
+
+2. regular IO
+[ 1463.760679] INFO: task kworker/0:8:5367 blocked for more than 480 seconds.
+[ 1463.760683] Not tainted 4.19.5-1-default #1
+[ 1463.760684] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message.
+[ 1463.760687] kworker/0:8 D 0 5367 2 0x80000000
+[ 1463.760718] Workqueue: md submit_flushes [md_mod]
+[ 1463.760721] Call Trace:
+[ 1463.760731] ? __schedule+0x29a/0x880
+[ 1463.760741] ? wait_barrier+0xdd/0x170 [raid10]
+[ 1463.760746] schedule+0x78/0x110
+[ 1463.760753] wait_barrier+0xdd/0x170 [raid10]
+[ 1463.760761] ? wait_woken+0x80/0x80
+[ 1463.760768] raid10_write_request+0xf2/0x900 [raid10]
+[ 1463.760774] ? wait_woken+0x80/0x80
+[ 1463.760778] ? mempool_alloc+0x55/0x160
+[ 1463.760795] ? md_write_start+0xa9/0x270 [md_mod]
+[ 1463.760801] ? try_to_wake_up+0x44/0x470
+[ 1463.760810] raid10_make_request+0xc1/0x120 [raid10]
+[ 1463.760816] ? wait_woken+0x80/0x80
+[ 1463.760831] md_handle_request+0x121/0x190 [md_mod]
+[ 1463.760851] md_make_request+0x78/0x190 [md_mod]
+[ 1463.760860] generic_make_request+0x1c6/0x470
+[ 1463.760870] raid10_write_request+0x77a/0x900 [raid10]
+[ 1463.760875] ? wait_woken+0x80/0x80
+[ 1463.760879] ? mempool_alloc+0x55/0x160
+[ 1463.760895] ? md_write_start+0xa9/0x270 [md_mod]
+[ 1463.760904] raid10_make_request+0xc1/0x120 [raid10]
+[ 1463.760910] ? wait_woken+0x80/0x80
+[ 1463.760926] md_handle_request+0x121/0x190 [md_mod]
+[ 1463.760931] ? _raw_spin_unlock_irq+0x22/0x40
+[ 1463.760936] ? finish_task_switch+0x74/0x260
+[ 1463.760954] submit_flushes+0x21/0x40 [md_mod]
+
+So resync io is waiting for regular write io to complete to
+decrease nr_pending (conf->barrier++ is called before waiting).
+The regular write io splits another bio after call wait_barrier
+which call nr_pending++, then the splitted bio would continue
+with raid10_write_request -> wait_barrier, so the splitted bio
+has to wait for barrier to be zero, then deadlock happens as
+follows.
+
+ resync io regular io
+
+ raise_barrier
+ wait_barrier
+ generic_make_request
+ wait_barrier
+
+To resolve the issue, we need to call allow_barrier to decrease
+nr_pending before generic_make_request since regular IO is not
+issued to underlying devices, and wait_barrier is called again
+to ensure no internal IO happening.
+
+Fixes: fc9977dd069e ("md/raid10: simplify the splitting of requests.")
+Reported-and-tested-by: SiniĊĦa Bandin <sinisa@4net.rs>
+Signed-off-by: Guoqing Jiang <gqjiang@suse.com>
+Signed-off-by: Shaohua Li <shli@fb.com>
+---
+ drivers/md/raid10.c | 4 ++++
+ 1 file changed, 4 insertions(+)
+
+diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
+index 76c92e31afc0..abb5d382f64d 100644
+--- a/drivers/md/raid10.c
++++ b/drivers/md/raid10.c
+@@ -1209,7 +1209,9 @@ static void raid10_read_request(struct mddev *mddev, struct bio *bio,
+ struct bio *split = bio_split(bio, max_sectors,
+ gfp, &conf->bio_split);
+ bio_chain(split, bio);
++ allow_barrier(conf);
+ generic_make_request(bio);
++ wait_barrier(conf);
+ bio = split;
+ r10_bio->master_bio = bio;
+ r10_bio->sectors = max_sectors;
+@@ -1492,7 +1494,9 @@ retry_write:
+ struct bio *split = bio_split(bio, r10_bio->sectors,
+ GFP_NOIO, &conf->bio_split);
+ bio_chain(split, bio);
++ allow_barrier(conf);
+ generic_make_request(bio);
++ wait_barrier(conf);
+ bio = split;
+ r10_bio->master_bio = bio;
+ }
+--
+cgit 1.2-0.3.lf.el7
projects / packages / kernel.git / blobdiff