The following commit has been merged into the timers/urgent branch of tip:
Commit-ID: dad6a09f3148257ac1773cd90934d721d68ab595
Gitweb: https://git.kernel.org/tip/dad6a09f3148257ac1773cd90934d721d68ab595
Author: Frederic Weisbecker <frederic(a)kernel.org>
AuthorDate: Mon, 29 Jan 2024 15:56:36 -08:00
Committer: Thomas Gleixner <tglx(a)linutronix.de>
CommitterDate: Tue, 06 Feb 2024 10:56:35 +01:00
hrtimer: Report offline hrtimer enqueue
The hrtimers migration on CPU-down hotplug process has been moved
earlier, before the CPU actually goes to die. This leaves a small window
of opportunity to queue an hrtimer in a blind spot, leaving it ignored.
For example a practical case has been reported with RCU waking up a
SCHED_FIFO task right before the CPUHP_AP_IDLE_DEAD stage, queuing that
way a sched/rt timer to the local offline CPU.
Make sure such situations never go unnoticed and warn when that happens.
Fixes: 5c0930ccaad5 ("hrtimers: Push pending hrtimers away from outgoing CPU earlier")
Reported-by: Paul E. McKenney <paulmck(a)kernel.org>
Signed-off-by: Frederic Weisbecker <frederic(a)kernel.org>
Signed-off-by: Paul E. McKenney <paulmck(a)kernel.org>
Signed-off-by: Thomas Gleixner <tglx(a)linutronix.de>
Cc: stable(a)vger.kernel.org
Link: https://lore.kernel.org/r/20240129235646.3171983-4-boqun.feng@gmail.com
---
include/linux/hrtimer.h | 4 +++-
kernel/time/hrtimer.c | 3 +++
2 files changed, 6 insertions(+), 1 deletion(-)
diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h
index 87e3bed..641c456 100644
--- a/include/linux/hrtimer.h
+++ b/include/linux/hrtimer.h
@@ -157,6 +157,7 @@ enum hrtimer_base_type {
* @max_hang_time: Maximum time spent in hrtimer_interrupt
* @softirq_expiry_lock: Lock which is taken while softirq based hrtimer are
* expired
+ * @online: CPU is online from an hrtimers point of view
* @timer_waiters: A hrtimer_cancel() invocation waits for the timer
* callback to finish.
* @expires_next: absolute time of the next event, is required for remote
@@ -179,7 +180,8 @@ struct hrtimer_cpu_base {
unsigned int hres_active : 1,
in_hrtirq : 1,
hang_detected : 1,
- softirq_activated : 1;
+ softirq_activated : 1,
+ online : 1;
#ifdef CONFIG_HIGH_RES_TIMERS
unsigned int nr_events;
unsigned short nr_retries;
diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c
index 7607939..edb0f82 100644
--- a/kernel/time/hrtimer.c
+++ b/kernel/time/hrtimer.c
@@ -1085,6 +1085,7 @@ static int enqueue_hrtimer(struct hrtimer *timer,
enum hrtimer_mode mode)
{
debug_activate(timer, mode);
+ WARN_ON_ONCE(!base->cpu_base->online);
base->cpu_base->active_bases |= 1 << base->index;
@@ -2183,6 +2184,7 @@ int hrtimers_prepare_cpu(unsigned int cpu)
cpu_base->softirq_next_timer = NULL;
cpu_base->expires_next = KTIME_MAX;
cpu_base->softirq_expires_next = KTIME_MAX;
+ cpu_base->online = 1;
hrtimer_cpu_base_init_expiry_lock(cpu_base);
return 0;
}
@@ -2250,6 +2252,7 @@ int hrtimers_cpu_dying(unsigned int dying_cpu)
smp_call_function_single(ncpu, retrigger_next_event, NULL, 0);
raw_spin_unlock(&new_base->lock);
+ old_base->online = 0;
raw_spin_unlock(&old_base->lock);
return 0;
Symptom:
In case of a bad cable connection (e.g. dirty optics) a fast sequence of
network DOWN-UP-DOWN-UP could happen. UP triggers recovery of the qeth
interface. In case of a second DOWN while recovery is still ongoing, it
can happen that the IP@ of a Layer3 qeth interface is lost and will not
be recovered by the second UP.
Problem:
When registration of IP addresses with Layer 3 qeth devices fails, (e.g.
because of bad address format) the respective IP address is deleted from
its hash-table in the driver. If registration fails because of a ENETDOWN
condition, the address should stay in the hashtable, so a subsequent
recovery can restore it.
3caa4af834df ("qeth: keep ip-address after LAN_OFFLINE failure")
fixes this for registration failures during normal operation, but not
during recovery.
Solution:
Keep L3-IP address in case of ENETDOWN in qeth_l3_recover_ip(). For
consistency with qeth_l3_add_ip() we also keep it in case of EADDRINUSE,
i.e. for some reason the card already/still has this address registered.
Fixes: 4a71df50047f ("qeth: new qeth device driver")
Cc: stable(a)vger.kernel.org
Signed-off-by: Alexandra Winter <wintera(a)linux.ibm.com>
---
drivers/s390/net/qeth_l3_main.c | 9 ++++++---
1 file changed, 6 insertions(+), 3 deletions(-)
diff --git a/drivers/s390/net/qeth_l3_main.c b/drivers/s390/net/qeth_l3_main.c
index b92a32b4b114..04c64ce0a1ca 100644
--- a/drivers/s390/net/qeth_l3_main.c
+++ b/drivers/s390/net/qeth_l3_main.c
@@ -255,9 +255,10 @@ static void qeth_l3_clear_ip_htable(struct qeth_card *card, int recover)
if (!recover) {
hash_del(&addr->hnode);
kfree(addr);
- continue;
+ } else {
+ /* prepare for recovery */
+ addr->disp_flag = QETH_DISP_ADDR_ADD;
}
- addr->disp_flag = QETH_DISP_ADDR_ADD;
}
mutex_unlock(&card->ip_lock);
@@ -278,9 +279,11 @@ static void qeth_l3_recover_ip(struct qeth_card *card)
if (addr->disp_flag == QETH_DISP_ADDR_ADD) {
rc = qeth_l3_register_addr_entry(card, addr);
- if (!rc) {
+ if (!rc || rc == -EADDRINUSE || rc == -ENETDOWN) {
+ /* keep it in the records */
addr->disp_flag = QETH_DISP_ADDR_DO_NOTHING;
} else {
+ /* bad address */
hash_del(&addr->hnode);
kfree(addr);
}
--
2.40.1
From: Sinthu Raja <sinthu.raja(a)ti.com>
The below commit introduced a WARN when phy state is not in the states:
PHY_HALTED, PHY_READY and PHY_UP.
commit 744d23c71af3 ("net: phy: Warn about incorrect mdio_bus_phy_resume() state")
When cpsw resumes, there have port in PHY_NOLINK state, so the below
warning comes out. Set mac_managed_pm be true to tell mdio that the phy
resume/suspend is managed by the mac, to fix the following warning:
WARNING: CPU: 0 PID: 965 at drivers/net/phy/phy_device.c:326 mdio_bus_phy_resume+0x140/0x144
CPU: 0 PID: 965 Comm: sh Tainted: G O 6.1.46-g247b2535b2 #1
Hardware name: Generic AM33XX (Flattened Device Tree)
unwind_backtrace from show_stack+0x18/0x1c
show_stack from dump_stack_lvl+0x24/0x2c
dump_stack_lvl from __warn+0x84/0x15c
__warn from warn_slowpath_fmt+0x1a8/0x1c8
warn_slowpath_fmt from mdio_bus_phy_resume+0x140/0x144
mdio_bus_phy_resume from dpm_run_callback+0x3c/0x140
dpm_run_callback from device_resume+0xb8/0x2b8
device_resume from dpm_resume+0x144/0x314
dpm_resume from dpm_resume_end+0x14/0x20
dpm_resume_end from suspend_devices_and_enter+0xd0/0x924
suspend_devices_and_enter from pm_suspend+0x2e0/0x33c
pm_suspend from state_store+0x74/0xd0
state_store from kernfs_fop_write_iter+0x104/0x1ec
kernfs_fop_write_iter from vfs_write+0x1b8/0x358
vfs_write from ksys_write+0x78/0xf8
ksys_write from ret_fast_syscall+0x0/0x54
Exception stack(0xe094dfa8 to 0xe094dff0)
dfa0: 00000004 005c3fb8 00000001 005c3fb8 00000004 00000001
dfc0: 00000004 005c3fb8 b6f6bba0 00000004 00000004 0059edb8 00000000 00000000
dfe0: 00000004 bed918f0 b6f09bd3 b6e89a66
Cc: <stable(a)vger.kernel.org> # v6.0+
Fixes: 744d23c71af3 ("net: phy: Warn about incorrect mdio_bus_phy_resume() state")
Signed-off-by: Sinthu Raja <sinthu.raja(a)ti.com>
---
drivers/net/ethernet/ti/cpsw.c | 2 ++
1 file changed, 2 insertions(+)
diff --git a/drivers/net/ethernet/ti/cpsw.c b/drivers/net/ethernet/ti/cpsw.c
index ea85c6dd5484..c0a5abd8d9a8 100644
--- a/drivers/net/ethernet/ti/cpsw.c
+++ b/drivers/net/ethernet/ti/cpsw.c
@@ -631,6 +631,8 @@ static void cpsw_slave_open(struct cpsw_slave *slave, struct cpsw_priv *priv)
}
}
+ phy->mac_managed_pm = true;
+
slave->phy = phy;
phy_attached_info(slave->phy);
--
2.36.1
The patch titled
Subject: fat: Fix uninitialized field in nostale filehandles
has been added to the -mm mm-nonmm-unstable branch. Its filename is
fat-fix-uninitialized-field-in-nostale-filehandles.patch
This patch will shortly appear at
https://git.kernel.org/pub/scm/linux/kernel/git/akpm/25-new.git/tree/patche…
This patch will later appear in the mm-nonmm-unstable branch at
git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
Before you just go and hit "reply", please:
a) Consider who else should be cc'ed
b) Prefer to cc a suitable mailing list as well
c) Ideally: find the original patch on the mailing list and do a
reply-to-all to that, adding suitable additional cc's
*** Remember to use Documentation/process/submit-checklist.rst when testing your code ***
The -mm tree is included into linux-next via the mm-everything
branch at git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
and is updated there every 2-3 working days
------------------------------------------------------
From: Jan Kara <jack(a)suse.cz>
Subject: fat: Fix uninitialized field in nostale filehandles
Date: Mon, 5 Feb 2024 13:26:26 +0100
When fat_encode_fh_nostale() encodes file handle without a parent it
stores only first 10 bytes of the file handle. However the length of the
file handle must be a multiple of 4 so the file handle is actually 12
bytes long and the last two bytes remain uninitialized. This is not
great at we potentially leak uninitialized information with the handle
to userspace. Properly initialize the full handle length.
Link: https://lkml.kernel.org/r/20240205122626.13701-1-jack@suse.cz
Reported-by: syzbot+3ce5dea5b1539ff36769(a)syzkaller.appspotmail.com
Fixes: ea3983ace6b7 ("fat: restructure export_operations")
Signed-off-by: Jan Kara <jack(a)suse.cz>
Acked-by: OGAWA Hirofumi <hirofumi(a)mail.parknet.co.jp>
Cc: Amir Goldstein <amir73il(a)gmail.com>
Cc: <stable(a)vger.kernel.org>
Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org>
---
fs/fat/nfs.c | 6 ++++++
1 file changed, 6 insertions(+)
--- a/fs/fat/nfs.c~fat-fix-uninitialized-field-in-nostale-filehandles
+++ a/fs/fat/nfs.c
@@ -130,6 +130,12 @@ fat_encode_fh_nostale(struct inode *inod
fid->parent_i_gen = parent->i_generation;
type = FILEID_FAT_WITH_PARENT;
*lenp = FAT_FID_SIZE_WITH_PARENT;
+ } else {
+ /*
+ * We need to initialize this field because the fh is actually
+ * 12 bytes long
+ */
+ fid->parent_i_pos_hi = 0;
}
return type;
_
Patches currently in -mm which might be from jack(a)suse.cz are
fat-fix-uninitialized-field-in-nostale-filehandles.patch
The patch titled
Subject: selftests/mm: uffd-unit-test check if huge page size is 0
has been added to the -mm mm-hotfixes-unstable branch. Its filename is
selftests-mm-uffd-unit-test-check-if-huge-page-size-is-0.patch
This patch will shortly appear at
https://git.kernel.org/pub/scm/linux/kernel/git/akpm/25-new.git/tree/patche…
This patch will later appear in the mm-hotfixes-unstable branch at
git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
Before you just go and hit "reply", please:
a) Consider who else should be cc'ed
b) Prefer to cc a suitable mailing list as well
c) Ideally: find the original patch on the mailing list and do a
reply-to-all to that, adding suitable additional cc's
*** Remember to use Documentation/process/submit-checklist.rst when testing your code ***
The -mm tree is included into linux-next via the mm-everything
branch at git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
and is updated there every 2-3 working days
------------------------------------------------------
From: Terry Tritton <terry.tritton(a)linaro.org>
Subject: selftests/mm: uffd-unit-test check if huge page size is 0
Date: Mon, 5 Feb 2024 14:50:56 +0000
If HUGETLBFS is not enabled then the default_huge_page_size function will
return 0 and cause a divide by 0 error. Add a check to see if the huge page
size is 0 and skip the hugetlb tests if it is.
Link: https://lkml.kernel.org/r/20240205145055.3545806-2-terry.tritton@linaro.org
Fixes: 16a45b57cbf2 ("selftests/mm: add framework for uffd-unit-test")
Signed-off-by: Terry Tritton <terry.tritton(a)linaro.org>
Cc: Peter Griffin <peter.griffin(a)linaro.org>
Cc: Shuah Khan <shuah(a)kernel.org>
Cc: Peter Xu <peterx(a)redhat.com>
Cc: <stable(a)vger.kernel.org>
Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org>
---
tools/testing/selftests/mm/uffd-unit-tests.c | 6 ++++++
1 file changed, 6 insertions(+)
--- a/tools/testing/selftests/mm/uffd-unit-tests.c~selftests-mm-uffd-unit-test-check-if-huge-page-size-is-0
+++ a/tools/testing/selftests/mm/uffd-unit-tests.c
@@ -1517,6 +1517,12 @@ int main(int argc, char *argv[])
continue;
uffd_test_start("%s on %s", test->name, mem_type->name);
+ if ((mem_type->mem_flag == MEM_HUGETLB ||
+ mem_type->mem_flag == MEM_HUGETLB_PRIVATE) &&
+ (default_huge_page_size() == 0)) {
+ uffd_test_skip("huge page size is 0, feature missing?");
+ continue;
+ }
if (!uffd_feature_supported(test)) {
uffd_test_skip("feature missing");
continue;
_
Patches currently in -mm which might be from terry.tritton(a)linaro.org are
selftests-mm-uffd-unit-test-check-if-huge-page-size-is-0.patch
The patch titled
Subject: mm/damon/core: check apply interval in damon_do_apply_schemes()
has been added to the -mm mm-hotfixes-unstable branch. Its filename is
mm-damon-core-check-apply-interval-in-damon_do_apply_schemes.patch
This patch will shortly appear at
https://git.kernel.org/pub/scm/linux/kernel/git/akpm/25-new.git/tree/patche…
This patch will later appear in the mm-hotfixes-unstable branch at
git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
Before you just go and hit "reply", please:
a) Consider who else should be cc'ed
b) Prefer to cc a suitable mailing list as well
c) Ideally: find the original patch on the mailing list and do a
reply-to-all to that, adding suitable additional cc's
*** Remember to use Documentation/process/submit-checklist.rst when testing your code ***
The -mm tree is included into linux-next via the mm-everything
branch at git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
and is updated there every 2-3 working days
------------------------------------------------------
From: SeongJae Park <sj(a)kernel.org>
Subject: mm/damon/core: check apply interval in damon_do_apply_schemes()
Date: Mon, 5 Feb 2024 12:13:06 -0800
kdamond_apply_schemes() checks apply intervals of schemes and avoid
further applying any schemes if no scheme passed its apply interval.
However, the following schemes applying function, damon_do_apply_schemes()
iterates all schemes without the apply interval check. As a result, the
shortest apply interval is applied to all schemes. Fix the problem by
checking the apply interval in damon_do_apply_schemes().
Link: https://lkml.kernel.org/r/20240205201306.88562-1-sj@kernel.org
Fixes: 42f994b71404 ("mm/damon/core: implement scheme-specific apply interval")
Signed-off-by: SeongJae Park <sj(a)kernel.org>
Cc: <stable(a)vger.kernel.org> [6.7.x]
Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org>
---
mm/damon/core.c | 15 +++++++++++----
1 file changed, 11 insertions(+), 4 deletions(-)
--- a/mm/damon/core.c~mm-damon-core-check-apply-interval-in-damon_do_apply_schemes
+++ a/mm/damon/core.c
@@ -1026,6 +1026,9 @@ static void damon_do_apply_schemes(struc
damon_for_each_scheme(s, c) {
struct damos_quota *quota = &s->quota;
+ if (c->passed_sample_intervals != s->next_apply_sis)
+ continue;
+
if (!s->wmarks.activated)
continue;
@@ -1176,10 +1179,6 @@ static void kdamond_apply_schemes(struct
if (c->passed_sample_intervals != s->next_apply_sis)
continue;
- s->next_apply_sis +=
- (s->apply_interval_us ? s->apply_interval_us :
- c->attrs.aggr_interval) / sample_interval;
-
if (!s->wmarks.activated)
continue;
@@ -1195,6 +1194,14 @@ static void kdamond_apply_schemes(struct
damon_for_each_region_safe(r, next_r, t)
damon_do_apply_schemes(c, t, r);
}
+
+ damon_for_each_scheme(s, c) {
+ if (c->passed_sample_intervals != s->next_apply_sis)
+ continue;
+ s->next_apply_sis +=
+ (s->apply_interval_us ? s->apply_interval_us :
+ c->attrs.aggr_interval) / sample_interval;
+ }
}
/*
_
Patches currently in -mm which might be from sj(a)kernel.org are
mm-damon-sysfs-schemes-fix-wrong-damos-tried-regions-update-timeout-setup.patch
mm-damon-core-check-apply-interval-in-damon_do_apply_schemes.patch
docs-admin-guide-mm-damon-usage-use-sysfs-interface-for-tracepoints-example.patch
mm-damon-rename-config_damon_dbgfs-to-damon_dbgfs_deprecated.patch
mm-damon-dbgfs-implement-deprecation-notice-file.patch
mm-damon-dbgfs-make-debugfs-interface-deprecation-message-a-macro.patch
docs-admin-guide-mm-damon-usage-document-deprecated-file-of-damon-debugfs-interface.patch
selftets-damon-prepare-for-monitor_on-file-renaming.patch
mm-damon-dbgfs-rename-monitor_on-file-to-monitor_on_deprecated.patch
docs-admin-guide-mm-damon-usage-update-for-monitor_on-renaming.patch
docs-translations-damon-usage-update-for-monitor_on-renaming.patch