From c350c008297643dad3c395c2fd92230142da5cf6 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Wed, 3 May 2017 15:35:32 -0700 Subject: srcu: Prevent sdp->srcu_gp_seq_needed counter wrap If a given CPU never happens to ever start an SRCU grace period, the grace-period sequence counter might wrap. If this CPU were to decide to finally start a grace period, the state of its sdp->srcu_gp_seq_needed might make it appear that it has already requested this grace period, which would prevent starting the grace period. If no other CPU ever started a grace period again, this would look like a grace-period hang. Even if some other CPU took pity and started the needed grace period, the leaf rcu_node structure's ->srcu_data_have_cbs field won't have record of the fact that this CPU has a callback pending, which would look like a very localized grace-period hang. This might seem very unlikely, but SRCU grace periods can take less than a microsecond on small systems, which means that overflow can happen in much less than an hour on a 32-bit embedded system. And embedded systems are especially likely to have long-term idle CPUs. Therefore, it makes sense to prevent this scenario from happening. This commit therefore scans each srcu_data structure occasionally, with frequency controlled by the srcutree.counter_wrap_check kernel boot parameter. This parameter can be set to something like 255 in order to exercise the counter-wrap-prevention code. Signed-off-by: Paul E. McKenney --- Documentation/admin-guide/kernel-parameters.txt | 9 +++++++++ kernel/rcu/srcutree.c | 18 ++++++++++++++++++ 2 files changed, 27 insertions(+) diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index 01b5ab92d251..6671f9b60a86 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -3810,6 +3810,15 @@ spia_pedr= spia_peddr= + srcutree.counter_wrap_check [KNL] + Specifies how frequently to check for + grace-period sequence counter wrap for the + srcu_data structure's ->srcu_gp_seq_needed field. + The greater the number of bits set in this kernel + parameter, the less frequently counter wrap will + be checked for. Note that the bottom two bits + are ignored. + srcutree.exp_holdoff [KNL] Specifies how many nanoseconds must elapse since the end of the last SRCU grace period for diff --git a/kernel/rcu/srcutree.c b/kernel/rcu/srcutree.c index c6e2a4a1628b..cc06dbfc9692 100644 --- a/kernel/rcu/srcutree.c +++ b/kernel/rcu/srcutree.c @@ -45,6 +45,10 @@ static ulong exp_holdoff = DEFAULT_SRCU_EXP_HOLDOFF; module_param(exp_holdoff, ulong, 0444); +/* Overflow-check frequency. N bits roughly says every 2**N grace periods. */ +static ulong counter_wrap_check = (ULONG_MAX >> 2); +module_param(counter_wrap_check, ulong, 0444); + static void srcu_invoke_callbacks(struct work_struct *work); static void srcu_reschedule(struct srcu_struct *sp, unsigned long delay); @@ -496,10 +500,13 @@ static void srcu_gp_end(struct srcu_struct *sp) { unsigned long cbdelay; bool cbs; + int cpu; + unsigned long flags; unsigned long gpseq; int idx; int idxnext; unsigned long mask; + struct srcu_data *sdp; struct srcu_node *snp; /* Prevent more than one additional grace period. */ @@ -538,6 +545,17 @@ static void srcu_gp_end(struct srcu_struct *sp) smp_mb(); /* GP end before CB invocation. */ srcu_schedule_cbs_snp(sp, snp, mask, cbdelay); } + + /* Occasionally prevent srcu_data counter wrap. */ + if (!(gpseq & counter_wrap_check)) + for (cpu = snp->grplo; cpu <= snp->grphi; cpu++) { + sdp = per_cpu_ptr(sp->sda, cpu); + spin_lock_irqsave(&sdp->lock, flags); + if (ULONG_CMP_GE(gpseq, + sdp->srcu_gp_seq_needed + 100)) + sdp->srcu_gp_seq_needed = gpseq; + spin_unlock_irqrestore(&sdp->lock, flags); + } } /* Callback initiation done, allow grace periods after next. */ -- cgit v1.2.3