diff options
Diffstat (limited to 'kernel/rcu/srcutree.c')
| -rw-r--r-- | kernel/rcu/srcutree.c | 74 |
1 files changed, 51 insertions, 23 deletions
diff --git a/kernel/rcu/srcutree.c b/kernel/rcu/srcutree.c index 20d7a238d675..560e99ec5333 100644 --- a/kernel/rcu/srcutree.c +++ b/kernel/rcu/srcutree.c @@ -223,7 +223,7 @@ static bool init_srcu_struct_nodes(struct srcu_struct *ssp, gfp_t gfp_flags) snp->grplo = cpu; snp->grphi = cpu; } - sdp->grpmask = 1 << (cpu - sdp->mynode->grplo); + sdp->grpmask = 1UL << (cpu - sdp->mynode->grplo); } smp_store_release(&ssp->srcu_sup->srcu_size_state, SRCU_SIZE_WAIT_BARRIER); return true; @@ -255,29 +255,31 @@ static int init_srcu_struct_fields(struct srcu_struct *ssp, bool is_static) ssp->srcu_sup->sda_is_static = is_static; if (!is_static) ssp->sda = alloc_percpu(struct srcu_data); - if (!ssp->sda) { - if (!is_static) - kfree(ssp->srcu_sup); - return -ENOMEM; - } + if (!ssp->sda) + goto err_free_sup; init_srcu_struct_data(ssp); ssp->srcu_sup->srcu_gp_seq_needed_exp = 0; ssp->srcu_sup->srcu_last_gp_end = ktime_get_mono_fast_ns(); if (READ_ONCE(ssp->srcu_sup->srcu_size_state) == SRCU_SIZE_SMALL && SRCU_SIZING_IS_INIT()) { - if (!init_srcu_struct_nodes(ssp, GFP_ATOMIC)) { - if (!ssp->srcu_sup->sda_is_static) { - free_percpu(ssp->sda); - ssp->sda = NULL; - kfree(ssp->srcu_sup); - return -ENOMEM; - } - } else { - WRITE_ONCE(ssp->srcu_sup->srcu_size_state, SRCU_SIZE_BIG); - } + if (!init_srcu_struct_nodes(ssp, GFP_ATOMIC)) + goto err_free_sda; + WRITE_ONCE(ssp->srcu_sup->srcu_size_state, SRCU_SIZE_BIG); } ssp->srcu_sup->srcu_ssp = ssp; smp_store_release(&ssp->srcu_sup->srcu_gp_seq_needed, 0); /* Init done. */ return 0; + +err_free_sda: + if (!is_static) { + free_percpu(ssp->sda); + ssp->sda = NULL; + } +err_free_sup: + if (!is_static) { + kfree(ssp->srcu_sup); + ssp->srcu_sup = NULL; + } + return -ENOMEM; } #ifdef CONFIG_DEBUG_LOCK_ALLOC @@ -782,8 +784,7 @@ static void srcu_gp_start(struct srcu_struct *ssp) spin_lock_rcu_node(sdp); /* Interrupts already disabled. */ rcu_segcblist_advance(&sdp->srcu_cblist, rcu_seq_current(&ssp->srcu_sup->srcu_gp_seq)); - (void)rcu_segcblist_accelerate(&sdp->srcu_cblist, - rcu_seq_snap(&ssp->srcu_sup->srcu_gp_seq)); + WARN_ON_ONCE(!rcu_segcblist_segempty(&sdp->srcu_cblist, RCU_NEXT_TAIL)); spin_unlock_rcu_node(sdp); /* Interrupts remain disabled. */ WRITE_ONCE(ssp->srcu_sup->srcu_gp_start, jiffies); WRITE_ONCE(ssp->srcu_sup->srcu_n_exp_nodelay, 0); @@ -833,7 +834,7 @@ static void srcu_schedule_cbs_snp(struct srcu_struct *ssp, struct srcu_node *snp int cpu; for (cpu = snp->grplo; cpu <= snp->grphi; cpu++) { - if (!(mask & (1 << (cpu - snp->grplo)))) + if (!(mask & (1UL << (cpu - snp->grplo)))) continue; srcu_schedule_cbs_sdp(per_cpu_ptr(ssp->sda, cpu), delay); } @@ -1242,10 +1243,37 @@ static unsigned long srcu_gp_start_if_needed(struct srcu_struct *ssp, spin_lock_irqsave_sdp_contention(sdp, &flags); if (rhp) rcu_segcblist_enqueue(&sdp->srcu_cblist, rhp); + /* + * The snapshot for acceleration must be taken _before_ the read of the + * current gp sequence used for advancing, otherwise advancing may fail + * and acceleration may then fail too. + * + * This could happen if: + * + * 1) The RCU_WAIT_TAIL segment has callbacks (gp_num = X + 4) and the + * RCU_NEXT_READY_TAIL also has callbacks (gp_num = X + 8). + * + * 2) The grace period for RCU_WAIT_TAIL is seen as started but not + * completed so rcu_seq_current() returns X + SRCU_STATE_SCAN1. + * + * 3) This value is passed to rcu_segcblist_advance() which can't move + * any segment forward and fails. + * + * 4) srcu_gp_start_if_needed() still proceeds with callback acceleration. + * But then the call to rcu_seq_snap() observes the grace period for the + * RCU_WAIT_TAIL segment as completed and the subsequent one for the + * RCU_NEXT_READY_TAIL segment as started (ie: X + 4 + SRCU_STATE_SCAN1) + * so it returns a snapshot of the next grace period, which is X + 12. + * + * 5) The value of X + 12 is passed to rcu_segcblist_accelerate() but the + * freshly enqueued callback in RCU_NEXT_TAIL can't move to + * RCU_NEXT_READY_TAIL which already has callbacks for a previous grace + * period (gp_num = X + 8). So acceleration fails. + */ + s = rcu_seq_snap(&ssp->srcu_sup->srcu_gp_seq); rcu_segcblist_advance(&sdp->srcu_cblist, rcu_seq_current(&ssp->srcu_sup->srcu_gp_seq)); - s = rcu_seq_snap(&ssp->srcu_sup->srcu_gp_seq); - (void)rcu_segcblist_accelerate(&sdp->srcu_cblist, s); + WARN_ON_ONCE(!rcu_segcblist_accelerate(&sdp->srcu_cblist, s) && rhp); if (ULONG_CMP_LT(sdp->srcu_gp_seq_needed, s)) { sdp->srcu_gp_seq_needed = s; needgp = true; @@ -1692,6 +1720,7 @@ static void srcu_invoke_callbacks(struct work_struct *work) ssp = sdp->ssp; rcu_cblist_init(&ready_cbs); spin_lock_irq_rcu_node(sdp); + WARN_ON_ONCE(!rcu_segcblist_segempty(&sdp->srcu_cblist, RCU_NEXT_TAIL)); rcu_segcblist_advance(&sdp->srcu_cblist, rcu_seq_current(&ssp->srcu_sup->srcu_gp_seq)); if (sdp->srcu_cblist_invoking || @@ -1708,6 +1737,7 @@ static void srcu_invoke_callbacks(struct work_struct *work) rhp = rcu_cblist_dequeue(&ready_cbs); for (; rhp != NULL; rhp = rcu_cblist_dequeue(&ready_cbs)) { debug_rcu_head_unqueue(rhp); + debug_rcu_head_callback(rhp); local_bh_disable(); rhp->func(rhp); local_bh_enable(); @@ -1720,8 +1750,6 @@ static void srcu_invoke_callbacks(struct work_struct *work) */ spin_lock_irq_rcu_node(sdp); rcu_segcblist_add_len(&sdp->srcu_cblist, -len); - (void)rcu_segcblist_accelerate(&sdp->srcu_cblist, - rcu_seq_snap(&ssp->srcu_sup->srcu_gp_seq)); sdp->srcu_cblist_invoking = false; more = rcu_segcblist_ready_cbs(&sdp->srcu_cblist); spin_unlock_irq_rcu_node(sdp); |