exit
fi
done
+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
-diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c
-index 7a0c800..ec5ebbb 100644
---- a/drivers/net/ethernet/realtek/r8169.c
-+++ b/drivers/net/ethernet/realtek/r8169.c
-@@ -6927,6 +6927,14 @@ rtl_init_one(struct pci_dev *pdev, const
- for (i = 0; i < ETH_ALEN; i++)
- dev->dev_addr[i] = RTL_R8(MAC0 + i);
-
-+ if (!is_valid_ether_addr(dev->dev_addr)) {
-+ /* Report it and use a random ethernet address instead */
-+ netdev_err(dev, "Invalid MAC address: %pM\n", dev->dev_addr);
-+ random_ether_addr(dev->dev_addr);
-+ netdev_info(dev, "Using random MAC address: %pM\n",
-+ dev->dev_addr);
-+ }
-+
- SET_ETHTOOL_OPS(dev, &rtl8169_ethtool_ops);
- dev->watchdog_timeo = RTL8169_TX_TIMEOUT;
-
-[PATCH] SCSI: Don't attempt to send extended INQUIRY command if skip_vpd_pages is set
+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.
-If a device has the skip_vpd_pages flag set we should simply fail the
-scsi_get_vpd_page() call.
+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
-Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
-Acked-by: Alan Stern <stern@rowland.harvard.edu>
-Tested-by: Stuart Foster <smf.linux@ntlworld.com>
-Cc: stable@vger.kernel.org
-
-diff --git a/drivers/scsi/scsi.c b/drivers/scsi/scsi.c
-index 3b1ea34..eaa808e 100644
---- a/drivers/scsi/scsi.c
-+++ b/drivers/scsi/scsi.c
-@@ -1031,6 +1031,9 @@
- {
- int i, result;
-
-+ if (sdev->skip_vpd_pages)
-+ goto fail;
-+
- /* Ask for all the pages supported by this device */
- result = scsi_vpd_inquiry(sdev, buf, 0, buf_len);
- if (result)
-commit 4d0ed18277cc6f07513ee0b04475f19cd69e75ef
-Author: Peter Hurley <peter@hurleysoftware.com>
-Date: Tue Dec 10 17:12:02 2013 -0500
+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]
- n_tty: Fix buffer overruns with larger-than-4k pastes
-
- readline() inadvertently triggers an error recovery path when
- pastes larger than 4k overrun the line discipline buffer. The
- error recovery path discards input when the line discipline buffer
- is full and operating in canonical mode and no newline has been
- received. Because readline() changes the termios to non-canonical
- mode to read the line char-by-char, the line discipline buffer
- can become full, and then when readline() restores termios back
- to canonical mode for the caller, the now-full line discipline
- buffer triggers the error recovery.
-
- When changing termios from non-canon to canon mode and the read
- buffer contains data, simulate an EOF push _without_ the
- DISABLED_CHAR in the read buffer.
-
- Importantly for the readline() problem, the termios can be
- changed back to non-canonical mode without changes to the read
- buffer occurring; ie., as if the previous termios change had not
- happened (as long as no intervening read took place).
-
- Preserve existing userspace behavior which allows '\0's already
- received in non-canon mode to be read as '\0's in canon mode
- (rather than trigger add'l EOF pushes or an actual EOF).
-
- Patch based on original proposal and discussion here
- https://bugzilla.kernel.org/show_bug.cgi?id=55991
- by Stas Sergeev <stsp@users.sourceforge.net>
-
- Reported-by: Margarita Manterola <margamanterola@gmail.com>
- Cc: Maximiliano Curia <maxy@gnuservers.com.ar>
- Cc: Pavel Machek <pavel@ucw.cz>
- Cc: Arkadiusz Miskiewicz <a.miskiewicz@gmail.com>
- Acked-by: Stas Sergeev <stsp@users.sourceforge.net>
- Signed-off-by: Peter Hurley <peter@hurleysoftware.com>
- Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+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.
-diff --git a/drivers/tty/n_tty.c b/drivers/tty/n_tty.c
-index fdc2ecd..961e6a9 100644
---- a/drivers/tty/n_tty.c
-+++ b/drivers/tty/n_tty.c
-@@ -104,6 +104,7 @@ struct n_tty_data {
-
- /* must hold exclusive termios_rwsem to reset these */
- unsigned char lnext:1, erasing:1, raw:1, real_raw:1, icanon:1;
-+ unsigned char push:1;
-
- /* shared by producer and consumer */
- char read_buf[N_TTY_BUF_SIZE];
-@@ -341,6 +342,7 @@ static void reset_buffer_flags(struct n_tty_data *ldata)
-
- ldata->erasing = 0;
- bitmap_zero(ldata->read_flags, N_TTY_BUF_SIZE);
-+ ldata->push = 0;
- }
-
- static void n_tty_packet_mode_flush(struct tty_struct *tty)
-@@ -1745,7 +1747,16 @@ static void n_tty_set_termios(struct tty_struct *tty, struct ktermios *old)
-
- if (!old || (old->c_lflag ^ tty->termios.c_lflag) & ICANON) {
- bitmap_zero(ldata->read_flags, N_TTY_BUF_SIZE);
-- ldata->line_start = ldata->canon_head = ldata->read_tail;
-+ ldata->line_start = ldata->read_tail;
-+ if (!L_ICANON(tty) || !read_cnt(ldata)) {
-+ ldata->canon_head = ldata->read_tail;
-+ ldata->push = 0;
-+ } else {
-+ set_bit((ldata->read_head - 1) & (N_TTY_BUF_SIZE - 1),
-+ ldata->read_flags);
-+ ldata->canon_head = ldata->read_head;
-+ ldata->push = 1;
-+ }
- ldata->erasing = 0;
- ldata->lnext = 0;
- }
-@@ -1951,6 +1962,12 @@ static int copy_from_read_buf(struct tty_struct *tty,
- * it copies one line of input up to and including the line-delimiting
- * character into the user-space buffer.
- *
-+ * NB: When termios is changed from non-canonical to canonical mode and
-+ * the read buffer contains data, n_tty_set_termios() simulates an EOF
-+ * push (as if C-d were input) _without_ the DISABLED_CHAR in the buffer.
-+ * This causes data already processed as input to be immediately available
-+ * as input although a newline has not been received.
-+ *
- * Called under the atomic_read_lock mutex
- *
- * n_tty_read()/consumer path:
-@@ -1997,7 +2014,7 @@ static int canon_copy_from_read_buf(struct tty_struct *tty,
- n += found;
- c = n;
-
-- if (found && read_buf(ldata, eol) == __DISABLED_CHAR) {
-+ if (found && !ldata->push && read_buf(ldata, eol) == __DISABLED_CHAR) {
- n--;
- eof_push = !n && ldata->read_tail != ldata->line_start;
- }
-@@ -2024,7 +2041,10 @@ static int canon_copy_from_read_buf(struct tty_struct *tty,
- ldata->read_tail += c;
-
- if (found) {
-- ldata->line_start = ldata->read_tail;
-+ if (!ldata->push)
-+ ldata->line_start = ldata->read_tail;
-+ else
-+ ldata->push = 0;
- tty_audit_push(tty);
- }
- return eof_push ? -EAGAIN : 0;
-From 27095111cbafd3212c7e9a4a8cef1099b7520ca8 Mon Sep 17 00:00:00 2001
-From: Kieran Clancy <clancy.kieran@gmail.com>
-Date: Fri, 28 Feb 2014 14:12:28 +0000
-Subject: ACPI / EC: Clear stale EC events on Samsung systems
+ resync io regular io
-A number of Samsung notebooks (530Uxx/535Uxx/540Uxx/550Pxx/900Xxx/etc)
-continue to log events during sleep (lid open/close, AC plug/unplug,
-battery level change), which accumulate in the EC until a buffer fills.
-After the buffer is full (tests suggest it holds 8 events), GPEs stop
-being triggered for new events. This state persists on wake or even on
-power cycle, and prevents new events from being registered until the EC
-is manually polled.
+ raise_barrier
+ wait_barrier
+ generic_make_request
+ wait_barrier
-This is the root cause of a number of bugs, including AC not being
-detected properly, lid close not triggering suspend, and low ambient
-light not triggering the keyboard backlight. The bug also seemed to be
-responsible for performance issues on at least one user's machine.
+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.
-Juan Manuel Cabo found the cause of bug and the workaround of polling
-the EC manually on wake.
-
-The loop which clears the stale events is based on an earlier patch by
-Lan Tianyu (see referenced attachment).
+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(+)
-This patch:
- - Adds a function acpi_ec_clear() which polls the EC for stale _Q
- events at most ACPI_EC_CLEAR_MAX (currently 100) times. A warning is
- logged if this limit is reached.
- - Adds a flag EC_FLAGS_CLEAR_ON_RESUME which is set to 1 if the DMI
- system vendor is Samsung. This check could be replaced by several
- more specific DMI vendor/product pairs, but it's likely that the bug
- affects more Samsung products than just the five series mentioned
- above. Further, it should not be harmful to run acpi_ec_clear() on
- systems without the bug; it will return immediately after finding no
- data waiting.
- - Runs acpi_ec_clear() on initialisation (boot), from acpi_ec_add()
- - Runs acpi_ec_clear() on wake, from acpi_ec_unblock_transactions()
+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
-References: https://bugzilla.kernel.org/show_bug.cgi?id=44161
-References: https://bugzilla.kernel.org/show_bug.cgi?id=45461
-References: https://bugzilla.kernel.org/show_bug.cgi?id=57271
-References: https://bugzilla.kernel.org/attachment.cgi?id=126801
-Suggested-by: Juan Manuel Cabo <juanmanuel.cabo@gmail.com>
-Signed-off-by: Kieran Clancy <clancy.kieran@gmail.com>
-Reviewed-by: Lan Tianyu <tianyu.lan@intel.com>
-Reviewed-by: Dennis Jansen <dennis.jansen@web.de>
-Tested-by: Kieran Clancy <clancy.kieran@gmail.com>
-Tested-by: Juan Manuel Cabo <juanmanuel.cabo@gmail.com>
-Tested-by: Dennis Jansen <dennis.jansen@web.de>
-Tested-by: Maurizio D'Addona <mauritiusdadd@gmail.com>
-Tested-by: San Zamoyski <san@plusnet.pl>
-Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
----
-diff --git a/drivers/acpi/ec.c b/drivers/acpi/ec.c
-index 959d41a..d7d32c2 100644
---- a/drivers/acpi/ec.c
-+++ b/drivers/acpi/ec.c
-@@ -67,6 +67,8 @@ enum ec_command {
- #define ACPI_EC_DELAY 500 /* Wait 500ms max. during EC ops */
- #define ACPI_EC_UDELAY_GLK 1000 /* Wait 1ms max. to get global lock */
- #define ACPI_EC_MSI_UDELAY 550 /* Wait 550us for MSI EC */
-+#define ACPI_EC_CLEAR_MAX 100 /* Maximum number of events to query
-+ * when trying to clear the EC */
-
- enum {
- EC_FLAGS_QUERY_PENDING, /* Query is pending */
-@@ -116,6 +118,7 @@ EXPORT_SYMBOL(first_ec);
- static int EC_FLAGS_MSI; /* Out-of-spec MSI controller */
- static int EC_FLAGS_VALIDATE_ECDT; /* ASUStec ECDTs need to be validated */
- static int EC_FLAGS_SKIP_DSDT_SCAN; /* Not all BIOS survive early DSDT scan */
-+static int EC_FLAGS_CLEAR_ON_RESUME; /* Needs acpi_ec_clear() on boot/resume */
-
- /* --------------------------------------------------------------------------
- Transaction Management
-@@ -440,6 +443,29 @@ acpi_handle ec_get_handle(void)
-
- EXPORT_SYMBOL(ec_get_handle);
-
-+static int acpi_ec_query_unlocked(struct acpi_ec *ec, u8 *data);
-+
-+/*
-+ * Clears stale _Q events that might have accumulated in the EC.
-+ * Run with locked ec mutex.
-+ */
-+static void acpi_ec_clear(struct acpi_ec *ec)
-+{
-+ int i, status;
-+ u8 value = 0;
-+
-+ for (i = 0; i < ACPI_EC_CLEAR_MAX; i++) {
-+ status = acpi_ec_query_unlocked(ec, &value);
-+ if (status || !value)
-+ break;
-+ }
-+
-+ if (unlikely(i == ACPI_EC_CLEAR_MAX))
-+ pr_warn("Warning: Maximum of %d stale EC events cleared\n", i);
-+ else
-+ pr_info("%d stale EC events cleared\n", i);
-+}
-+
- void acpi_ec_block_transactions(void)
- {
- struct acpi_ec *ec = first_ec;
-@@ -463,6 +489,10 @@ void acpi_ec_unblock_transactions(void)
- mutex_lock(&ec->mutex);
- /* Allow transactions to be carried out again */
- clear_bit(EC_FLAGS_BLOCKED, &ec->flags);
-+
-+ if (EC_FLAGS_CLEAR_ON_RESUME)
-+ acpi_ec_clear(ec);
-+
- mutex_unlock(&ec->mutex);
- }
-
-@@ -821,6 +851,13 @@ static int acpi_ec_add(struct acpi_device *device)
-
- /* EC is fully operational, allow queries */
- clear_bit(EC_FLAGS_QUERY_PENDING, &ec->flags);
-+
-+ /* Clear stale _Q events if hardware might require that */
-+ if (EC_FLAGS_CLEAR_ON_RESUME) {
-+ mutex_lock(&ec->mutex);
-+ acpi_ec_clear(ec);
-+ mutex_unlock(&ec->mutex);
-+ }
- return ret;
- }
-
-@@ -922,6 +959,30 @@ static int ec_enlarge_storm_threshold(const struct dmi_system_id *id)
- return 0;
- }
-
-+/*
-+ * On some hardware it is necessary to clear events accumulated by the EC during
-+ * sleep. These ECs stop reporting GPEs until they are manually polled, if too
-+ * many events are accumulated. (e.g. Samsung Series 5/9 notebooks)
-+ *
-+ * https://bugzilla.kernel.org/show_bug.cgi?id=44161
-+ *
-+ * Ideally, the EC should also be instructed NOT to accumulate events during
-+ * sleep (which Windows seems to do somehow), but the interface to control this
-+ * behaviour is not known at this time.
-+ *
-+ * Models known to be affected are Samsung 530Uxx/535Uxx/540Uxx/550Pxx/900Xxx,
-+ * however it is very likely that other Samsung models are affected.
-+ *
-+ * On systems which don't accumulate _Q events during sleep, this extra check
-+ * should be harmless.
-+ */
-+static int ec_clear_on_resume(const struct dmi_system_id *id)
-+{
-+ pr_debug("Detected system needing EC poll on resume.\n");
-+ EC_FLAGS_CLEAR_ON_RESUME = 1;
-+ return 0;
-+}
-+
- static struct dmi_system_id ec_dmi_table[] __initdata = {
- {
- ec_skip_dsdt_scan, "Compal JFL92", {
-@@ -965,6 +1026,9 @@ static struct dmi_system_id ec_dmi_table[] __initdata = {
- ec_validate_ecdt, "ASUS hardware", {
- DMI_MATCH(DMI_SYS_VENDOR, "ASUSTek Computer Inc."),
- DMI_MATCH(DMI_PRODUCT_NAME, "L4R"),}, NULL},
-+ {
-+ ec_clear_on_resume, "Samsung hardware", {
-+ DMI_MATCH(DMI_SYS_VENDOR, "SAMSUNG ELECTRONICS CO., LTD.")}, NULL},
- {},
- };
-
---
-cgit v0.9.2
+--- linux-4.14/security/selinux/include/classmap.h 2017-11-12 19:46:13.000000000 +0100
++++ linux-4.20/security/selinux/include/classmap.h 2018-12-24 00:55:59.000000000 +0100
+@@ -238,9 +238,11 @@
+ { "access", NULL } },
+ { "infiniband_endport",
+ { "manage_subnet", NULL } },
++ { "xdp_socket",
++ { COMMON_SOCK_PERMS, NULL } },
+ { NULL }
+ };
+
+-#if PF_MAX > 44
++#if PF_MAX > 45
+ #error New address family defined, please update secclass_map.
+ #endif