From a84097e625f2b9e7f273161c004f34b7be63b348 Mon Sep 17 00:00:00 2001 From: Waiman Long Date: Sat, 21 Feb 2026 13:54:18 -0500 Subject: cgroup/cpuset: Call housekeeping_update() without holding cpus_read_lock The current cpuset partition code is able to dynamically update the sched domains of a running system and the corresponding HK_TYPE_DOMAIN housekeeping cpumask to perform what is essentially the "isolcpus=domain,..." boot command line feature at run time. The housekeeping cpumask update requires flushing a number of different workqueues which may not be safe with cpus_read_lock() held as the workqueue flushing code may acquire cpus_read_lock() or acquiring locks which have locking dependency with cpus_read_lock() down the chain. Below is an example of such circular locking problem. ====================================================== WARNING: possible circular locking dependency detected 6.18.0-test+ #2 Tainted: G S ------------------------------------------------------ test_cpuset_prs/10971 is trying to acquire lock: ffff888112ba4958 ((wq_completion)sync_wq){+.+.}-{0:0}, at: touch_wq_lockdep_map+0x7a/0x180 but task is already holding lock: ffffffffae47f450 (cpuset_mutex){+.+.}-{4:4}, at: cpuset_partition_write+0x85/0x130 which lock already depends on the new lock. the existing dependency chain (in reverse order) is: -> #4 (cpuset_mutex){+.+.}-{4:4}: -> #3 (cpu_hotplug_lock){++++}-{0:0}: -> #2 (rtnl_mutex){+.+.}-{4:4}: -> #1 ((work_completion)(&arg.work)){+.+.}-{0:0}: -> #0 ((wq_completion)sync_wq){+.+.}-{0:0}: Chain exists of: (wq_completion)sync_wq --> cpu_hotplug_lock --> cpuset_mutex 5 locks held by test_cpuset_prs/10971: #0: ffff88816810e440 (sb_writers#7){.+.+}-{0:0}, at: ksys_write+0xf9/0x1d0 #1: ffff8891ab620890 (&of->mutex#2){+.+.}-{4:4}, at: kernfs_fop_write_iter+0x260/0x5f0 #2: ffff8890a78b83e8 (kn->active#187){.+.+}-{0:0}, at: kernfs_fop_write_iter+0x2b6/0x5f0 #3: ffffffffadf32900 (cpu_hotplug_lock){++++}-{0:0}, at: cpuset_partition_write+0x77/0x130 #4: ffffffffae47f450 (cpuset_mutex){+.+.}-{4:4}, at: cpuset_partition_write+0x85/0x130 Call Trace: : touch_wq_lockdep_map+0x93/0x180 __flush_workqueue+0x111/0x10b0 housekeeping_update+0x12d/0x2d0 update_parent_effective_cpumask+0x595/0x2440 update_prstate+0x89d/0xce0 cpuset_partition_write+0xc5/0x130 cgroup_file_write+0x1a5/0x680 kernfs_fop_write_iter+0x3df/0x5f0 vfs_write+0x525/0xfd0 ksys_write+0xf9/0x1d0 do_syscall_64+0x95/0x520 entry_SYSCALL_64_after_hwframe+0x76/0x7e To avoid such a circular locking dependency problem, we have to call housekeeping_update() without holding the cpus_read_lock() and cpuset_mutex. The current set of wq's flushed by housekeeping_update() may not have work functions that call cpus_read_lock() directly, but we are likely to extend the list of wq's that are flushed in the future. Moreover, the current set of work functions may hold locks that may have cpu_hotplug_lock down the dependency chain. So housekeeping_update() is now called after releasing cpus_read_lock and cpuset_mutex at the end of a cpuset operation. These two locks are then re-acquired later before calling rebuild_sched_domains_locked(). To enable mutual exclusion between the housekeeping_update() call and other cpuset control file write actions, a new top level cpuset_top_mutex is introduced. This new mutex will be acquired first to allow sharing variables used by both code paths. However, cpuset update from CPU hotplug can still happen in parallel with the housekeeping_update() call, though that should be rare in production environment. As cpus_read_lock() is now no longer held when tmigr_isolated_exclude_cpumask() is called, it needs to acquire it directly. The lockdep_is_cpuset_held() is also updated to return true if either cpuset_top_mutex or cpuset_mutex is held. Fixes: 03ff73510169 ("cpuset: Update HK_TYPE_DOMAIN cpumask from cpuset") Signed-off-by: Waiman Long Signed-off-by: Tejun Heo --- kernel/time/timer_migration.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) (limited to 'kernel/time') diff --git a/kernel/time/timer_migration.c b/kernel/time/timer_migration.c index 6da9cd562b20..83428aa03aef 100644 --- a/kernel/time/timer_migration.c +++ b/kernel/time/timer_migration.c @@ -1559,8 +1559,6 @@ int tmigr_isolated_exclude_cpumask(struct cpumask *exclude_cpumask) cpumask_var_t cpumask __free(free_cpumask_var) = CPUMASK_VAR_NULL; int cpu; - lockdep_assert_cpus_held(); - if (!works) return -ENOMEM; if (!alloc_cpumask_var(&cpumask, GFP_KERNEL)) @@ -1570,6 +1568,7 @@ int tmigr_isolated_exclude_cpumask(struct cpumask *exclude_cpumask) * First set previously isolated CPUs as available (unisolate). * This cpumask contains only CPUs that switched to available now. */ + guard(cpus_read_lock)(); cpumask_andnot(cpumask, cpu_online_mask, exclude_cpumask); cpumask_andnot(cpumask, cpumask, tmigr_available_cpumask); @@ -1626,7 +1625,6 @@ static int __init tmigr_init_isolation(void) cpumask_andnot(cpumask, cpu_possible_mask, housekeeping_cpumask(HK_TYPE_DOMAIN)); /* Protect against RCU torture hotplug testing */ - guard(cpus_read_lock)(); return tmigr_isolated_exclude_cpumask(cpumask); } late_initcall(tmigr_init_isolation); -- cgit v1.2.3 From 6932256d3a3764f3a5e06e2cb8603be45b6a9fef Mon Sep 17 00:00:00 2001 From: Gerd Rausch Date: Wed, 25 Feb 2026 15:37:49 -0800 Subject: time/jiffies: Fix sysctl file error on configurations where USER_HZ < HZ Commit 2dc164a48e6fd ("sysctl: Create converter functions with two new macros") incorrectly returns error to user space when jiffies sysctl converter is used. The old overflow check got replaced with an unconditional one: + if (USER_HZ < HZ) + return -EINVAL; which will always be true on configurations with "USER_HZ < HZ". Remove the check; it is no longer needed as clock_t_to_jiffies() returns ULONG_MAX for the overflow case and proc_int_u2k_conv_uop() checks for "> INT_MAX" after conversion Fixes: 2dc164a48e6fd ("sysctl: Create converter functions with two new macros") Reported-by: Colm Harrington Signed-off-by: Gerd Rausch Signed-off-by: Joel Granados --- kernel/time/jiffies.c | 2 -- 1 file changed, 2 deletions(-) (limited to 'kernel/time') diff --git a/kernel/time/jiffies.c b/kernel/time/jiffies.c index a5c7d15fce72..9daf8c5d9687 100644 --- a/kernel/time/jiffies.c +++ b/kernel/time/jiffies.c @@ -256,8 +256,6 @@ EXPORT_SYMBOL(proc_dointvec_jiffies); int proc_dointvec_userhz_jiffies(const struct ctl_table *table, int dir, void *buffer, size_t *lenp, loff_t *ppos) { - if (SYSCTL_USER_TO_KERN(dir) && USER_HZ < HZ) - return -EINVAL; return proc_dointvec_conv(table, dir, buffer, lenp, ppos, do_proc_int_conv_userhz_jiffies); } -- cgit v1.2.3 From e48a869957a70cc39b4090cd27c36a86f8db9b92 Mon Sep 17 00:00:00 2001 From: Miroslav Lichvar Date: Wed, 25 Feb 2026 09:51:35 +0100 Subject: timekeeping: Fix timex status validation for auxiliary clocks The timekeeping_validate_timex() function validates the timex status of an auxiliary system clock even when the status is not to be changed, which causes unexpected errors for applications that make read-only clock_adjtime() calls, or set some other timex fields, but without clearing the status field. Do the AUX-specific status validation only when the modes field contains ADJ_STATUS, i.e. the application is actually trying to change the status. This makes the AUX-specific clock_adjtime() behavior consistent with CLOCK_REALTIME. Fixes: 4eca49d0b621 ("timekeeping: Prepare do_adtimex() for auxiliary clocks") Signed-off-by: Miroslav Lichvar Signed-off-by: Thomas Gleixner Link: https://patch.msgid.link/20260225085231.276751-1-mlichvar@redhat.com --- kernel/time/timekeeping.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'kernel/time') diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index 91fa2003351c..c07e562ee4c1 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -2653,7 +2653,8 @@ static int timekeeping_validate_timex(const struct __kernel_timex *txc, bool aux if (aux_clock) { /* Auxiliary clocks are similar to TAI and do not have leap seconds */ - if (txc->status & (STA_INS | STA_DEL)) + if (txc->modes & ADJ_STATUS && + txc->status & (STA_INS | STA_DEL)) return -EINVAL; /* No TAI offset setting */ @@ -2661,7 +2662,8 @@ static int timekeeping_validate_timex(const struct __kernel_timex *txc, bool aux return -EINVAL; /* No PPS support either */ - if (txc->status & (STA_PPSFREQ | STA_PPSTIME)) + if (txc->modes & ADJ_STATUS && + txc->status & (STA_PPSFREQ | STA_PPSTIME)) return -EINVAL; } -- cgit v1.2.3