This commit renames the ->gp_seq[] field in struct rcu_segcblist to ->gp_seq_full[] and changes its type from unsigned long to struct rcu_gp_oldstate. This prepares the callback tracking infrastructure to support both normal and expedited grace periods.
All function signatures are updated to pass struct rcu_gp_oldstate pointers: rcu_segcblist_nextgp(), rcu_segcblist_advance(), and rcu_segcblist_accelerate() now take struct rcu_gp_oldstate * instead of unsigned long. All callers are updated to use the .rgos_norm field for comparisons and assignments. The SRCU and Tasks RCU wrappers now construct an rcu_gp_oldstate with just .rgos_norm set and forward to the core functions. No functional change: only the .rgos_norm field is used in place of gp_seq. Reviewed-by: Paul E. McKenney <[email protected]> Signed-off-by: Puranjay Mohan <[email protected]> --- include/linux/rcu_segcblist.h | 2 +- include/trace/events/rcu.h | 5 +++-- kernel/rcu/rcu_segcblist.c | 30 +++++++++++++++++------------- kernel/rcu/rcu_segcblist.h | 6 +++--- kernel/rcu/tree.c | 25 ++++++++++++++----------- kernel/rcu/tree_nocb.h | 29 +++++++++++++++-------------- 6 files changed, 53 insertions(+), 44 deletions(-) diff --git a/include/linux/rcu_segcblist.h b/include/linux/rcu_segcblist.h index 2fdc2208f1ca..59c68f2ba113 100644 --- a/include/linux/rcu_segcblist.h +++ b/include/linux/rcu_segcblist.h @@ -190,7 +190,7 @@ struct rcu_cblist { struct rcu_segcblist { struct rcu_head *head; struct rcu_head **tails[RCU_CBLIST_NSEGS]; - unsigned long gp_seq[RCU_CBLIST_NSEGS]; + struct rcu_gp_oldstate gp_seq_full[RCU_CBLIST_NSEGS]; #ifdef CONFIG_RCU_NOCB_CPU atomic_long_t len; #else diff --git a/include/trace/events/rcu.h b/include/trace/events/rcu.h index 5fbdabe3faea..2b859b274592 100644 --- a/include/trace/events/rcu.h +++ b/include/trace/events/rcu.h @@ -547,10 +547,11 @@ TRACE_EVENT_RCU(rcu_segcb_stats, ), TP_fast_assign( + int i; __entry->ctx = ctx; memcpy(__entry->seglen, rs->seglen, RCU_CBLIST_NSEGS * sizeof(long)); - memcpy(__entry->gp_seq, rs->gp_seq, RCU_CBLIST_NSEGS * sizeof(unsigned long)); - + for (i = 0; i < RCU_CBLIST_NSEGS; i++) + __entry->gp_seq[i] = rs->gp_seq_full[i].rgos_norm; ), TP_printk("%s seglen: (DONE=%ld, WAIT=%ld, NEXT_READY=%ld, NEXT=%ld) " diff --git a/kernel/rcu/rcu_segcblist.c b/kernel/rcu/rcu_segcblist.c index 421f1dadb5e5..00e164db8b74 100644 --- a/kernel/rcu/rcu_segcblist.c +++ b/kernel/rcu/rcu_segcblist.c @@ -238,8 +238,8 @@ void rcu_segcblist_init(struct rcu_segcblist *rsclp) { int i; - BUILD_BUG_ON(RCU_NEXT_TAIL + 1 != ARRAY_SIZE(rsclp->gp_seq)); - BUILD_BUG_ON(ARRAY_SIZE(rsclp->tails) != ARRAY_SIZE(rsclp->gp_seq)); + BUILD_BUG_ON(RCU_NEXT_TAIL + 1 != ARRAY_SIZE(rsclp->gp_seq_full)); + BUILD_BUG_ON(ARRAY_SIZE(rsclp->tails) != ARRAY_SIZE(rsclp->gp_seq_full)); rsclp->head = NULL; for (i = 0; i < RCU_CBLIST_NSEGS; i++) { rsclp->tails[i] = &rsclp->head; @@ -307,13 +307,13 @@ struct rcu_head *rcu_segcblist_first_pend_cb(struct rcu_segcblist *rsclp) /* * Return false if there are no CBs awaiting grace periods, otherwise, - * return true and store the nearest waited-upon grace period into *lp. + * return true and store the nearest waited-upon grace period state into *rgosp. */ -bool rcu_segcblist_nextgp(struct rcu_segcblist *rsclp, unsigned long *lp) +bool rcu_segcblist_nextgp(struct rcu_segcblist *rsclp, struct rcu_gp_oldstate *rgosp) { if (!rcu_segcblist_pend_cbs(rsclp)) return false; - *lp = rsclp->gp_seq[RCU_WAIT_TAIL]; + *rgosp = rsclp->gp_seq_full[RCU_WAIT_TAIL]; return true; } @@ -488,7 +488,7 @@ static void rcu_segcblist_advance_compact(struct rcu_segcblist *rsclp, int i) break; /* No more callbacks. */ WRITE_ONCE(rsclp->tails[j], rsclp->tails[i]); rcu_segcblist_move_seglen(rsclp, i, j); - rsclp->gp_seq[j] = rsclp->gp_seq[i]; + rsclp->gp_seq_full[j] = rsclp->gp_seq_full[i]; } } @@ -496,7 +496,7 @@ static void rcu_segcblist_advance_compact(struct rcu_segcblist *rsclp, int i) * Advance the callbacks in the specified rcu_segcblist structure based * on the current value passed in for the grace-period counter. */ -void rcu_segcblist_advance(struct rcu_segcblist *rsclp, unsigned long seq) +void rcu_segcblist_advance(struct rcu_segcblist *rsclp, struct rcu_gp_oldstate *rgosp) { int i; @@ -509,7 +509,7 @@ void rcu_segcblist_advance(struct rcu_segcblist *rsclp, unsigned long seq) * are ready to invoke, and put them into the RCU_DONE_TAIL segment. */ for (i = RCU_WAIT_TAIL; i < RCU_NEXT_TAIL; i++) { - if (ULONG_CMP_LT(seq, rsclp->gp_seq[i])) + if (ULONG_CMP_LT(rgosp->rgos_norm, rsclp->gp_seq_full[i].rgos_norm)) break; WRITE_ONCE(rsclp->tails[RCU_DONE_TAIL], rsclp->tails[i]); rcu_segcblist_move_seglen(rsclp, i, RCU_DONE_TAIL); @@ -537,7 +537,7 @@ void rcu_segcblist_advance(struct rcu_segcblist *rsclp, unsigned long seq) * ready to invoke. Returns true if there are callbacks that won't be * ready to invoke until seq, false otherwise. */ -bool rcu_segcblist_accelerate(struct rcu_segcblist *rsclp, unsigned long seq) +bool rcu_segcblist_accelerate(struct rcu_segcblist *rsclp, struct rcu_gp_oldstate *rgosp) { int i, j; @@ -555,7 +555,7 @@ bool rcu_segcblist_accelerate(struct rcu_segcblist *rsclp, unsigned long seq) */ for (i = RCU_NEXT_READY_TAIL; i > RCU_DONE_TAIL; i--) if (!rcu_segcblist_segempty(rsclp, i) && - ULONG_CMP_LT(rsclp->gp_seq[i], seq)) + ULONG_CMP_LT(rsclp->gp_seq_full[i].rgos_norm, rgosp->rgos_norm)) break; /* @@ -595,7 +595,7 @@ bool rcu_segcblist_accelerate(struct rcu_segcblist *rsclp, unsigned long seq) */ for (; i < RCU_NEXT_TAIL; i++) { WRITE_ONCE(rsclp->tails[i], rsclp->tails[RCU_NEXT_TAIL]); - rsclp->gp_seq[i] = seq; + rsclp->gp_seq_full[i].rgos_norm = rgosp->rgos_norm; } return true; } @@ -637,10 +637,14 @@ void rcu_segcblist_merge(struct rcu_segcblist *dst_rsclp, void srcu_segcblist_advance(struct rcu_segcblist *rsclp, unsigned long seq) { - rcu_segcblist_advance(rsclp, seq); + struct rcu_gp_oldstate rgos = { .rgos_norm = seq }; + + rcu_segcblist_advance(rsclp, &rgos); } bool srcu_segcblist_accelerate(struct rcu_segcblist *rsclp, unsigned long seq) { - return rcu_segcblist_accelerate(rsclp, seq); + struct rcu_gp_oldstate rgos = { .rgos_norm = seq }; + + return rcu_segcblist_accelerate(rsclp, &rgos); } diff --git a/kernel/rcu/rcu_segcblist.h b/kernel/rcu/rcu_segcblist.h index 956f2967d9d2..2c06ab830a3d 100644 --- a/kernel/rcu/rcu_segcblist.h +++ b/kernel/rcu/rcu_segcblist.h @@ -124,7 +124,7 @@ bool rcu_segcblist_ready_cbs(struct rcu_segcblist *rsclp); bool rcu_segcblist_pend_cbs(struct rcu_segcblist *rsclp); struct rcu_head *rcu_segcblist_first_cb(struct rcu_segcblist *rsclp); struct rcu_head *rcu_segcblist_first_pend_cb(struct rcu_segcblist *rsclp); -bool rcu_segcblist_nextgp(struct rcu_segcblist *rsclp, unsigned long *lp); +bool rcu_segcblist_nextgp(struct rcu_segcblist *rsclp, struct rcu_gp_oldstate *rgosp); void rcu_segcblist_enqueue(struct rcu_segcblist *rsclp, struct rcu_head *rhp); bool rcu_segcblist_entrain(struct rcu_segcblist *rsclp, @@ -139,8 +139,8 @@ void rcu_segcblist_insert_done_cbs(struct rcu_segcblist *rsclp, struct rcu_cblist *rclp); void rcu_segcblist_insert_pend_cbs(struct rcu_segcblist *rsclp, struct rcu_cblist *rclp); -void rcu_segcblist_advance(struct rcu_segcblist *rsclp, unsigned long seq); -bool rcu_segcblist_accelerate(struct rcu_segcblist *rsclp, unsigned long seq); +void rcu_segcblist_advance(struct rcu_segcblist *rsclp, struct rcu_gp_oldstate *rgosp); +bool rcu_segcblist_accelerate(struct rcu_segcblist *rsclp, struct rcu_gp_oldstate *rgosp); void rcu_segcblist_merge(struct rcu_segcblist *dst_rsclp, struct rcu_segcblist *src_rsclp); void srcu_segcblist_advance(struct rcu_segcblist *rsclp, unsigned long seq); diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index 55df6d37145e..cbc170dc3f72 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -1142,7 +1142,7 @@ static void rcu_gp_kthread_wake(void) */ static bool rcu_accelerate_cbs(struct rcu_node *rnp, struct rcu_data *rdp) { - unsigned long gp_seq_req; + struct rcu_gp_oldstate rgos; bool ret = false; rcu_lockdep_assert_cblist_protected(rdp); @@ -1164,15 +1164,15 @@ static bool rcu_accelerate_cbs(struct rcu_node *rnp, struct rcu_data *rdp) * accelerating callback invocation to an earlier grace-period * number. */ - gp_seq_req = rcu_seq_snap(&rcu_state.gp_seq); - if (rcu_segcblist_accelerate(&rdp->cblist, gp_seq_req)) - ret = rcu_start_this_gp(rnp, rdp, gp_seq_req); + rgos.rgos_norm = rcu_seq_snap(&rcu_state.gp_seq); + if (rcu_segcblist_accelerate(&rdp->cblist, &rgos)) + ret = rcu_start_this_gp(rnp, rdp, rgos.rgos_norm); /* Trace depending on how much we were able to accelerate. */ if (rcu_segcblist_restempty(&rdp->cblist, RCU_WAIT_TAIL)) - trace_rcu_grace_period(rcu_state.name, gp_seq_req, TPS("AccWaitCB")); + trace_rcu_grace_period(rcu_state.name, rgos.rgos_norm, TPS("AccWaitCB")); else - trace_rcu_grace_period(rcu_state.name, gp_seq_req, TPS("AccReadyCB")); + trace_rcu_grace_period(rcu_state.name, rgos.rgos_norm, TPS("AccReadyCB")); trace_rcu_segcb_stats(&rdp->cblist, TPS("SegCbPostAcc")); @@ -1189,14 +1189,14 @@ static bool rcu_accelerate_cbs(struct rcu_node *rnp, struct rcu_data *rdp) static void rcu_accelerate_cbs_unlocked(struct rcu_node *rnp, struct rcu_data *rdp) { - unsigned long c; + struct rcu_gp_oldstate rgos; bool needwake; rcu_lockdep_assert_cblist_protected(rdp); - c = rcu_seq_snap(&rcu_state.gp_seq); - if (!READ_ONCE(rdp->gpwrap) && ULONG_CMP_GE(rdp->gp_seq_needed, c)) { + rgos.rgos_norm = rcu_seq_snap(&rcu_state.gp_seq); + if (!READ_ONCE(rdp->gpwrap) && ULONG_CMP_GE(rdp->gp_seq_needed, rgos.rgos_norm)) { /* Old request still live, so mark recent callbacks. */ - (void)rcu_segcblist_accelerate(&rdp->cblist, c); + (void)rcu_segcblist_accelerate(&rdp->cblist, &rgos); return; } raw_spin_lock_rcu_node(rnp); /* irqs already disabled. */ @@ -1218,6 +1218,8 @@ static void rcu_accelerate_cbs_unlocked(struct rcu_node *rnp, */ static bool rcu_advance_cbs(struct rcu_node *rnp, struct rcu_data *rdp) { + struct rcu_gp_oldstate rgos; + rcu_lockdep_assert_cblist_protected(rdp); raw_lockdep_assert_held_rcu_node(rnp); @@ -1229,7 +1231,8 @@ static bool rcu_advance_cbs(struct rcu_node *rnp, struct rcu_data *rdp) * Find all callbacks whose ->gp_seq numbers indicate that they * are ready to invoke, and put them into the RCU_DONE_TAIL sublist. */ - rcu_segcblist_advance(&rdp->cblist, rnp->gp_seq); + rgos.rgos_norm = rnp->gp_seq; + rcu_segcblist_advance(&rdp->cblist, &rgos); /* Classify any remaining callbacks. */ return rcu_accelerate_cbs(rnp, rdp); diff --git a/kernel/rcu/tree_nocb.h b/kernel/rcu/tree_nocb.h index 1047b30cd46b..1837eedfb8c2 100644 --- a/kernel/rcu/tree_nocb.h +++ b/kernel/rcu/tree_nocb.h @@ -433,7 +433,7 @@ static bool rcu_nocb_try_bypass(struct rcu_data *rdp, struct rcu_head *rhp, bool lazy) { unsigned long c; - unsigned long cur_gp_seq; + struct rcu_gp_oldstate cur_gp_seq_full; unsigned long j = jiffies; long ncbs = rcu_cblist_n_cbs(&rdp->nocb_bypass); long lazy_len = READ_ONCE(rdp->lazy_len); @@ -501,8 +501,8 @@ static bool rcu_nocb_try_bypass(struct rcu_data *rdp, struct rcu_head *rhp, return false; // Caller must enqueue the callback. } if (j != rdp->nocb_gp_adv_time && - rcu_segcblist_nextgp(&rdp->cblist, &cur_gp_seq) && - rcu_seq_done(&rdp->mynode->gp_seq, cur_gp_seq)) { + rcu_segcblist_nextgp(&rdp->cblist, &cur_gp_seq_full) && + rcu_seq_done(&rdp->mynode->gp_seq, cur_gp_seq_full.rgos_norm)) { rcu_advance_cbs_nowake(rdp->mynode, rdp); rdp->nocb_gp_adv_time = j; } @@ -659,7 +659,7 @@ static void nocb_gp_wait(struct rcu_data *my_rdp) { bool bypass = false; int __maybe_unused cpu = my_rdp->cpu; - unsigned long cur_gp_seq; + struct rcu_gp_oldstate cur_gp_seq_full; unsigned long flags; bool gotcbs = false; unsigned long j = jiffies; @@ -730,8 +730,8 @@ static void nocb_gp_wait(struct rcu_data *my_rdp) needwake_gp = false; if (!rcu_segcblist_restempty(&rdp->cblist, RCU_NEXT_READY_TAIL) || - (rcu_segcblist_nextgp(&rdp->cblist, &cur_gp_seq) && - rcu_seq_done(&rnp->gp_seq, cur_gp_seq))) { + (rcu_segcblist_nextgp(&rdp->cblist, &cur_gp_seq_full) && + rcu_seq_done(&rnp->gp_seq, cur_gp_seq_full.rgos_norm))) { raw_spin_lock_rcu_node(rnp); /* irqs disabled. */ needwake_gp = rcu_advance_cbs(rnp, rdp); wasempty = rcu_segcblist_restempty(&rdp->cblist, @@ -742,10 +742,10 @@ static void nocb_gp_wait(struct rcu_data *my_rdp) WARN_ON_ONCE(wasempty && !rcu_segcblist_restempty(&rdp->cblist, RCU_NEXT_READY_TAIL)); - if (rcu_segcblist_nextgp(&rdp->cblist, &cur_gp_seq)) { + if (rcu_segcblist_nextgp(&rdp->cblist, &cur_gp_seq_full)) { if (!needwait_gp || - ULONG_CMP_LT(cur_gp_seq, wait_gp_seq)) - wait_gp_seq = cur_gp_seq; + ULONG_CMP_LT(cur_gp_seq_full.rgos_norm, wait_gp_seq)) + wait_gp_seq = cur_gp_seq_full.rgos_norm; needwait_gp = true; trace_rcu_nocb_wake(rcu_state.name, rdp->cpu, TPS("NeedWaitGP")); @@ -877,7 +877,7 @@ static inline bool nocb_cb_wait_cond(struct rcu_data *rdp) static void nocb_cb_wait(struct rcu_data *rdp) { struct rcu_segcblist *cblist = &rdp->cblist; - unsigned long cur_gp_seq; + struct rcu_gp_oldstate cur_gp_seq_full; unsigned long flags; bool needwake_gp = false; struct rcu_node *rnp = rdp->mynode; @@ -918,8 +918,8 @@ static void nocb_cb_wait(struct rcu_data *rdp) local_bh_enable(); lockdep_assert_irqs_enabled(); rcu_nocb_lock_irqsave(rdp, flags); - if (rcu_segcblist_nextgp(cblist, &cur_gp_seq) && - rcu_seq_done(&rnp->gp_seq, cur_gp_seq) && + if (rcu_segcblist_nextgp(cblist, &cur_gp_seq_full) && + rcu_seq_done(&rnp->gp_seq, cur_gp_seq_full.rgos_norm) && raw_spin_trylock_rcu_node(rnp)) { /* irqs already disabled. */ needwake_gp = rcu_advance_cbs(rdp->mynode, rdp); raw_spin_unlock_rcu_node(rnp); /* irqs remain disabled. */ @@ -1569,9 +1569,10 @@ static void show_rcu_nocb_state(struct rcu_data *rdp) nocb_entry_rdp); sprintf(bufd, "%ld", rsclp->seglen[RCU_DONE_TAIL]); - sprintf(bufw, "%ld(%ld)", rsclp->seglen[RCU_WAIT_TAIL], rsclp->gp_seq[RCU_WAIT_TAIL]); + sprintf(bufw, "%ld(%ld)", rsclp->seglen[RCU_WAIT_TAIL], + rsclp->gp_seq_full[RCU_WAIT_TAIL].rgos_norm); sprintf(bufr, "%ld(%ld)", rsclp->seglen[RCU_NEXT_READY_TAIL], - rsclp->gp_seq[RCU_NEXT_READY_TAIL]); + rsclp->gp_seq_full[RCU_NEXT_READY_TAIL].rgos_norm); sprintf(bufn, "%ld", rsclp->seglen[RCU_NEXT_TAIL]); sprintf(bufb, "%ld", rcu_cblist_n_cbs(&rdp->nocb_bypass)); pr_info(" CB %d^%d->%d %c%c%c%c%c F%ld L%ld C%d %c%s%c%s%c%s%c%s%c%s q%ld %c CPU %d%s\n", -- 2.52.0
