From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from smtp.kernel.org (aws-us-west-2-korg-mail-1.web.codeaurora.org [10.30.226.201]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id 9E5C139DBC9; Tue, 10 Mar 2026 22:24:03 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=10.30.226.201 ARC-Seal:i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1773181443; cv=none; b=HDTHWpCn7R7Sb5q451hfnhjO7UkWEbWFDTDszxZ8knVQubitYn3j4oYrkAwo9qLzl/HpDHVNVA7QXpZLsHWO7+ey2cHYf6Hpg2pAdfM29/9LhJW+thYOGtGS9NwA97PPIG9JkWcvFfLO6gleNYdctchmAJsK/UYV1Fxk/knPuxE= ARC-Message-Signature:i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1773181443; c=relaxed/simple; bh=h6WzP0r0AUWx2dIietr1bpYe6iKtJAcIhAcJ9XgUgEQ=; h=Date:From:To:Cc:Subject:Message-ID:References:MIME-Version: Content-Type:Content-Disposition:In-Reply-To; b=YLov7DPRrioFkAGAhhc0jejgQsC3VBCvOgCbEGJ5p7CCHnS47McXFPVXOqokFZDBIAurewW7/cgGS+RCZZHDsjdlwY+xshQ7ZPk1kiKnLHsLVLRTclbutha9kQijJdxisbXepOT1X/57BUX9Eo6oJNHs70pLtFnvMPamqgsyNLA= ARC-Authentication-Results:i=1; smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=kernel.org header.i=@kernel.org header.b=JxpVN2d3; arc=none smtp.client-ip=10.30.226.201 Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=kernel.org header.i=@kernel.org header.b="JxpVN2d3" Received: by smtp.kernel.org (Postfix) with ESMTPSA id CDD53C19423; Tue, 10 Mar 2026 22:24:02 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=kernel.org; s=k20201202; t=1773181443; bh=h6WzP0r0AUWx2dIietr1bpYe6iKtJAcIhAcJ9XgUgEQ=; h=Date:From:To:Cc:Subject:References:In-Reply-To:From; b=JxpVN2d3mcTvF0YIzsrWQnLLZjmAoKM9XX6eeB5WHTxPWq6iocuLMFT/Knut6TTQc 6edLQujy4dC2w5j2bIQPaYW8yud7ezx4Stzp2O+Bnrzi4pO8zJcBaBy8nR3R/UVZHb W3euP1VDamH1k63g7jn0ghFhvL64xzno+ig5aqvggigBhKxWF8ug0DAnpzAgZSnMCx io/rgZZ7CWr6WsWJnHPkf+igPHUo6d5UFEMWrGcQ7SqRhjFmtqcAHO2XxiYgWJRN/f QQtwl79aGxv055EeDosbSsBFHNWDPV9q8Ji8ISiL+/AD5R6y655AcDIEmZGUZombgT 2Y0GErUosGY9A== Date: Tue, 10 Mar 2026 23:24:00 +0100 From: Frederic Weisbecker To: Uladzislau Rezki Cc: Joel Fernandes , "Paul E.McKenney" , Vishal Chourasia , Shrikanth Hegde , Neeraj upadhyay , RCU , LKML , Samir M Subject: Re: [PATCH v2] rcu: Latch normal synchronize_rcu() path on flood Message-ID: References: <20260302100404.2624503-1-urezki@gmail.com> <14e954e4-cfa6-4069-a25f-ccb444d17535@nvidia.com> Precedence: bulk X-Mailing-List: rcu@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 Content-Type: text/plain; charset=utf-8 Content-Disposition: inline Content-Transfer-Encoding: 8bit In-Reply-To: Le Tue, Mar 10, 2026 at 05:28:22PM +0100, Uladzislau Rezki a écrit : > Hello, Frederic! > > > Le Thu, Mar 05, 2026 at 11:59:15AM +0100, Uladzislau Rezki a écrit : > > > On Tue, Mar 03, 2026 at 03:45:58PM -0500, Joel Fernandes wrote: > > > > On Mon, 02 Mar 2026 11:04:04 +0100, Uladzislau Rezki (Sony) wrote: > > > > > > > > > * The latch is cleared only when the pending requests are fully > > > > > drained(nr == 0); > > > > > > > > > +static void rcu_sr_normal_add_req(struct rcu_synchronize *rs) > > > > > +{ > > > > > + long nr; > > > > > + > > > > > + llist_add((struct llist_node *) &rs->head, &rcu_state.srs_next); > > > > > + nr = atomic_long_inc_return(&rcu_sr_normal_count); > > > > > + > > > > > + /* Latch: only when flooded and if unlatched. */ > > > > > + if (nr >= RCU_SR_NORMAL_LATCH_THR) > > > > > + (void)atomic_cmpxchg(&rcu_sr_normal_latched, 0, 1); > > > > > +} > > > > > > > > I think there is a stuck-latch race here. Once llist_add() places the > > > > entry in srs_next, the GP kthread can pick it up and fire > > > > rcu_sr_normal_complete() before the latching cmpxchg runs. If the last > > > > in-flight completion drains count to zero in that window, the unlatch > > > > cmpxchg(latched, 1, 0) fails (latched is still 0 at that moment), and > > > > then the latching cmpxchg(latched, 0, 1) fires anyway — with count=0: > > > > > > > > CPU 0 (add_req, count just hit 64) GP kthread > > > > ---------------------------------- ---------- > > > > llist_add() <-- entry now in srs_next > > > > inc_return() --> nr = 64 > > > > [preempted] > > > > rcu_sr_normal_complete() x64: > > > > dec_return -> count: 64..1..0 > > > > count==0: > > > > cmpxchg(latched, 1, 0) > > > > --> FAILS (latched still 0) > > > > [resumes] > > > > cmpxchg(latched, 0, 1) --> latched = 1 > > > > > > > > Final state: count=0, latched=1 --> STUCK LATCH > > > > > > > > All subsequent synchronize_rcu() callers see latched==1 and take the > > > > fallback path (not counted). With no new SR-normal callers, > > > > rcu_sr_normal_complete() is never reached again, so the unlatch > > > > cmpxchg(latched, 1, 0) never fires. The latch is permanently stuck. > > > > > > > > This requires preemption for a full GP duration between llist_add() and > > > > the cmpxchg, which is probably more likely on PREEMPT_RT or heavily loaded > > > > systems. > > > > > > > > The fix: move the cmpxchg *before* llist_add(), so the entry is not > > > > visible to the GP kthread until after the latch is already set. > > > > > > > > That should fix it, thoughts? > > > > > > > Yes and thank you! > > > > > > We can improve it even more by removing atomic_cmpxchg() in > > > the rcu_sr_normal_add_req() function, because only one context > > > sees the (nr == RCU_SR_NORMAL_LATCH_THR) condition: > > > > > > > > > diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c > > > index 86dc88a70fd0..72b340940e11 100644 > > > --- a/kernel/rcu/tree.c > > > +++ b/kernel/rcu/tree.c > > > @@ -1640,7 +1640,7 @@ static struct workqueue_struct *sync_wq; > > > > > > /* Number of in-flight synchronize_rcu() calls queued on srs_next. */ > > > static atomic_long_t rcu_sr_normal_count; > > > -static atomic_t rcu_sr_normal_latched; > > > +static int rcu_sr_normal_latched; /* 0/1 */ > > > > > > static void rcu_sr_normal_complete(struct llist_node *node) > > > { > > > @@ -1662,7 +1662,7 @@ static void rcu_sr_normal_complete(struct llist_node *node) > > > * drained and if it has been latched. > > > */ > > > if (nr == 0) > > > - (void)atomic_cmpxchg(&rcu_sr_normal_latched, 1, 0); > > > + (void)cmpxchg(&rcu_sr_normal_latched, 1, 0); > > > } > > > > > > static void rcu_sr_normal_gp_cleanup_work(struct work_struct *work) > > > @@ -1808,14 +1808,22 @@ static bool rcu_sr_normal_gp_init(void) > > > > > > static void rcu_sr_normal_add_req(struct rcu_synchronize *rs) > > > { > > > - long nr; > > > + /* > > > + * Increment before publish to avoid a complete > > > + * vs enqueue race on latch. > > > + */ > > > + long nr = atomic_long_inc_return(&rcu_sr_normal_count); > > > > > > - llist_add((struct llist_node *) &rs->head, &rcu_state.srs_next); > > > - nr = atomic_long_inc_return(&rcu_sr_normal_count); > > > + /* > > > + * Latch on threshold crossing. (nr == RCU_SR_NORMAL_LATCH_THR) > > > + * can be true only for one context, avoiding contention on the > > > + * write path. > > > + */ > > > + if (nr == RCU_SR_NORMAL_LATCH_THR) > > > + WRITE_ONCE(rcu_sr_normal_latched, 1); > > > > Isn't it still racy? > > > > rcu_sr_normal_add_req rcu_sr_normal_complete > > --------------------- ---------------------- > > nr = atomic_long_dec_return(&rcu_sr_normal_count); > > // nr == 0 > > ======= PREEMPTION ======= > > // 64 tasks doing synchronize_rcu() > > rcu_sr_normal_add_req() > > WRITE_ONCE(rcu_sr_normal_latched, 1); > > cmpxchg(&rcu_sr_normal_latched, 1, 0); > > > > > > Also more generally there is nothing that orders the WRITE_ONCE() with the > > cmpxchg. > > > Yep that i know. This is rather "relaxed" mechanism rather than > a strictly ordered. The race you described can happen but i do not > find it as a problem because as noted it is relaxed policy flag. Ok, that will need a comment explaining how and why we tolerate missed latches then. > > But WRITE_ONCE() i can replace by: > > if (nr == RCU_SR_NORMAL_LATCH_THR) > cmpxchg(&rcu_sr_normal_latched, 0, 1); Possibly yes, though I'm not sure that would help. > > Is it possible to remove rcu_sr_normal_latched and simply deal with comparisons > > between rcu_sr_normal_count and RCU_SR_NORMAL_LATCH_THR? > > > It is. But the idea with latch is a bit different then just checking > threshold. The main goal is to detect flood and lath the path until > __all__ users are flushed. I.e. it implements hysteresis to prevent > repeated switches around the threshold. Good point! > With your proposal behaviour becomes different. > > Thoughts? Good thoughts! :-) -- Frederic Weisbecker SUSE Labs