6.11-stable review patch. If anyone has any objections, please let me know.
------------------
From: Johannes Weiner hannes@cmpxchg.org
commit 3840cbe24cf060ea05a585ca497814609f5d47d1 upstream.
Brandon reports sporadic, non-sensical spikes in cumulative pressure time (total=) when reading cpu.pressure at a high rate. This is due to a race condition between reader aggregation and tasks changing states.
While it affects all states and all resources captured by PSI, in practice it most likely triggers with CPU pressure, since scheduling events are so frequent compared to other resource events.
The race context is the live snooping of ongoing stalls during a pressure read. The read aggregates per-cpu records for stalls that have concluded, but will also incorporate ad-hoc the duration of any active state that hasn't been recorded yet. This is important to get timely measurements of ongoing stalls. Those ad-hoc samples are calculated on-the-fly up to the current time on that CPU; since the stall hasn't concluded, it's expected that this is the minimum amount of stall time that will enter the per-cpu records once it does.
The problem is that the path that concludes the state uses a CPU clock read that is not synchronized against aggregators; the clock is read outside of the seqlock protection. This allows aggregators to race and snoop a stall with a longer duration than will actually be recorded.
With the recorded stall time being less than the last snapshot remembered by the aggregator, a subsequent sample will underflow and observe a bogus delta value, resulting in an erratic jump in pressure.
Fix this by moving the clock read of the state change into the seqlock protection. This ensures no aggregation can snoop live stalls past the time that's recorded when the state concludes.
Reported-by: Brandon Duffany brandon@buildbuddy.io Link: https://bugzilla.kernel.org/show_bug.cgi?id=219194 Link: https://lore.kernel.org/lkml/20240827121851.GB438928@cmpxchg.org/ Fixes: df77430639c9 ("psi: Reduce calls to sched_clock() in psi") Cc: stable@vger.kernel.org Signed-off-by: Johannes Weiner hannes@cmpxchg.org Reviewed-by: Chengming Zhou chengming.zhou@linux.dev Signed-off-by: Linus Torvalds torvalds@linux-foundation.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- kernel/sched/psi.c | 26 ++++++++++++-------------- 1 file changed, 12 insertions(+), 14 deletions(-)
--- a/kernel/sched/psi.c +++ b/kernel/sched/psi.c @@ -769,12 +769,13 @@ static void record_times(struct psi_grou }
static void psi_group_change(struct psi_group *group, int cpu, - unsigned int clear, unsigned int set, u64 now, + unsigned int clear, unsigned int set, bool wake_clock) { struct psi_group_cpu *groupc; unsigned int t, m; u32 state_mask; + u64 now;
lockdep_assert_rq_held(cpu_rq(cpu)); groupc = per_cpu_ptr(group->pcpu, cpu); @@ -789,6 +790,7 @@ static void psi_group_change(struct psi_ * SOME and FULL time these may have resulted in. */ write_seqcount_begin(&groupc->seq); + now = cpu_clock(cpu);
/* * Start with TSK_ONCPU, which doesn't have a corresponding @@ -899,18 +901,15 @@ void psi_task_change(struct task_struct { int cpu = task_cpu(task); struct psi_group *group; - u64 now;
if (!task->pid) return;
psi_flags_change(task, clear, set);
- now = cpu_clock(cpu); - group = task_psi_group(task); do { - psi_group_change(group, cpu, clear, set, now, true); + psi_group_change(group, cpu, clear, set, true); } while ((group = group->parent)); }
@@ -919,7 +918,6 @@ void psi_task_switch(struct task_struct { struct psi_group *group, *common = NULL; int cpu = task_cpu(prev); - u64 now = cpu_clock(cpu);
if (next->pid) { psi_flags_change(next, 0, TSK_ONCPU); @@ -936,7 +934,7 @@ void psi_task_switch(struct task_struct break; }
- psi_group_change(group, cpu, 0, TSK_ONCPU, now, true); + psi_group_change(group, cpu, 0, TSK_ONCPU, true); } while ((group = group->parent)); }
@@ -974,7 +972,7 @@ void psi_task_switch(struct task_struct do { if (group == common) break; - psi_group_change(group, cpu, clear, set, now, wake_clock); + psi_group_change(group, cpu, clear, set, wake_clock); } while ((group = group->parent));
/* @@ -986,7 +984,7 @@ void psi_task_switch(struct task_struct if ((prev->psi_flags ^ next->psi_flags) & ~TSK_ONCPU) { clear &= ~TSK_ONCPU; for (; group; group = group->parent) - psi_group_change(group, cpu, clear, set, now, wake_clock); + psi_group_change(group, cpu, clear, set, wake_clock); } } } @@ -997,8 +995,8 @@ void psi_account_irqtime(struct rq *rq, int cpu = task_cpu(curr); struct psi_group *group; struct psi_group_cpu *groupc; - u64 now, irq; s64 delta; + u64 irq;
if (static_branch_likely(&psi_disabled)) return; @@ -1011,7 +1009,6 @@ void psi_account_irqtime(struct rq *rq, if (prev && task_psi_group(prev) == group) return;
- now = cpu_clock(cpu); irq = irq_time_read(cpu); delta = (s64)(irq - rq->psi_irq_time); if (delta < 0) @@ -1019,12 +1016,15 @@ void psi_account_irqtime(struct rq *rq, rq->psi_irq_time = irq;
do { + u64 now; + if (!group->enabled) continue;
groupc = per_cpu_ptr(group->pcpu, cpu);
write_seqcount_begin(&groupc->seq); + now = cpu_clock(cpu);
record_times(groupc, now); groupc->times[PSI_IRQ_FULL] += delta; @@ -1223,11 +1223,9 @@ void psi_cgroup_restart(struct psi_group for_each_possible_cpu(cpu) { struct rq *rq = cpu_rq(cpu); struct rq_flags rf; - u64 now;
rq_lock_irq(rq, &rf); - now = cpu_clock(cpu); - psi_group_change(group, cpu, 0, 0, now, true); + psi_group_change(group, cpu, 0, 0, true); rq_unlock_irq(rq, &rf); } }