Merge tag 'v5.1-rc6' into for-5.2/block

Pull in v5.1-rc6 to resolve two conflicts. One is in BFQ, in just a
comment, and is trivial. The other one is a conflict due to a later fix
in the bio multi-page work, and needs a bit more care.

* tag 'v5.1-rc6': (770 commits)
  Linux 5.1-rc6
  block: make sure that bvec length can't be overflow
  block: kill all_q_node in request_queue
  x86/cpu/intel: Lower the "ENERGY_PERF_BIAS: Set to normal" message's log priority
  coredump: fix race condition between mmget_not_zero()/get_task_mm() and core dumping
  mm/kmemleak.c: fix unused-function warning
  init: initialize jump labels before command line option parsing
  kernel/watchdog_hld.c: hard lockup message should end with a newline
  kcov: improve CONFIG_ARCH_HAS_KCOV help text
  mm: fix inactive list balancing between NUMA nodes and cgroups
  mm/hotplug: treat CMA pages as unmovable
  proc: fixup proc-pid-vm test
  proc: fix map_files test on F29
  mm/vmstat.c: fix /proc/vmstat format for CONFIG_DEBUG_TLBFLUSH=y CONFIG_SMP=n
  mm/memory_hotplug: do not unlock after failing to take the device_hotplug_lock
  mm: swapoff: shmem_unuse() stop eviction without igrab()
  mm: swapoff: take notice of completion sooner
  mm: swapoff: remove too limiting SWAP_UNUSE_MAX_TRIES
  mm: swapoff: shmem_find_swap_entries() filter out other types
  slab: store tagged freelist for off-slab slabmgmt
  ...

Signed-off-by: Jens Axboe <axboe@kernel.dk>

1 files changed, 35 insertions, 46 deletions

diff --git a/net/ipv4/tcp_dctcp.c b/net/ipv4/tcp_dctcp.c
index cd4814f7e962..477cb4aa456c 100644
--- a/net/ipv4/tcp_dctcp.c
+++ b/net/ipv4/tcp_dctcp.c
@@ -49,9 +49,8 @@
 #define DCTCP_MAX_ALPHA	1024U
 
 struct dctcp {
-	u32 acked_bytes_ecn;
-	u32 acked_bytes_total;
-	u32 prior_snd_una;
+	u32 old_delivered;
+	u32 old_delivered_ce;
 	u32 prior_rcv_nxt;
 	u32 dctcp_alpha;
 	u32 next_seq;
@@ -67,19 +66,14 @@ static unsigned int dctcp_alpha_on_init __read_mostly = DCTCP_MAX_ALPHA;
 module_param(dctcp_alpha_on_init, uint, 0644);
 MODULE_PARM_DESC(dctcp_alpha_on_init, "parameter for initial alpha value");
 
-static unsigned int dctcp_clamp_alpha_on_loss __read_mostly;
-module_param(dctcp_clamp_alpha_on_loss, uint, 0644);
-MODULE_PARM_DESC(dctcp_clamp_alpha_on_loss,
-		 "parameter for clamping alpha on loss");
-
 static struct tcp_congestion_ops dctcp_reno;
 
 static void dctcp_reset(const struct tcp_sock *tp, struct dctcp *ca)
 {
 	ca->next_seq = tp->snd_nxt;
 
-	ca->acked_bytes_ecn = 0;
-	ca->acked_bytes_total = 0;
+	ca->old_delivered = tp->delivered;
+	ca->old_delivered_ce = tp->delivered_ce;
 }
 
 static void dctcp_init(struct sock *sk)
@@ -91,7 +85,6 @@ static void dctcp_init(struct sock *sk)
 	     sk->sk_state == TCP_CLOSE)) {
 		struct dctcp *ca = inet_csk_ca(sk);
 
-		ca->prior_snd_una = tp->snd_una;
 		ca->prior_rcv_nxt = tp->rcv_nxt;
 
 		ca->dctcp_alpha = min(dctcp_alpha_on_init, DCTCP_MAX_ALPHA);
@@ -123,37 +116,25 @@ static void dctcp_update_alpha(struct sock *sk, u32 flags)
 {
 	const struct tcp_sock *tp = tcp_sk(sk);
 	struct dctcp *ca = inet_csk_ca(sk);
-	u32 acked_bytes = tp->snd_una - ca->prior_snd_una;
-
-	/* If ack did not advance snd_una, count dupack as MSS size.
-	 * If ack did update window, do not count it at all.
-	 */
-	if (acked_bytes == 0 && !(flags & CA_ACK_WIN_UPDATE))
-		acked_bytes = inet_csk(sk)->icsk_ack.rcv_mss;
-	if (acked_bytes) {
-		ca->acked_bytes_total += acked_bytes;
-		ca->prior_snd_una = tp->snd_una;
-
-		if (flags & CA_ACK_ECE)
-			ca->acked_bytes_ecn += acked_bytes;
-	}
 
 	/* Expired RTT */
 	if (!before(tp->snd_una, ca->next_seq)) {
-		u64 bytes_ecn = ca->acked_bytes_ecn;
+		u32 delivered_ce = tp->delivered_ce - ca->old_delivered_ce;
 		u32 alpha = ca->dctcp_alpha;
 
 		/* alpha = (1 - g) * alpha + g * F */
 
 		alpha -= min_not_zero(alpha, alpha >> dctcp_shift_g);
-		if (bytes_ecn) {
+		if (delivered_ce) {
+			u32 delivered = tp->delivered - ca->old_delivered;
+
 			/* If dctcp_shift_g == 1, a 32bit value would overflow
-			 * after 8 Mbytes.
+			 * after 8 M packets.
 			 */
-			bytes_ecn <<= (10 - dctcp_shift_g);
-			do_div(bytes_ecn, max(1U, ca->acked_bytes_total));
+			delivered_ce <<= (10 - dctcp_shift_g);
+			delivered_ce /= max(1U, delivered);
 
-			alpha = min(alpha + (u32)bytes_ecn, DCTCP_MAX_ALPHA);
+			alpha = min(alpha + delivered_ce, DCTCP_MAX_ALPHA);
 		}
 		/* dctcp_alpha can be read from dctcp_get_info() without
 		 * synchro, so we ask compiler to not use dctcp_alpha
@@ -164,21 +145,23 @@ static void dctcp_update_alpha(struct sock *sk, u32 flags)
 	}
 }
 
-static void dctcp_state(struct sock *sk, u8 new_state)
+static void dctcp_react_to_loss(struct sock *sk)
 {
-	if (dctcp_clamp_alpha_on_loss && new_state == TCP_CA_Loss) {
-		struct dctcp *ca = inet_csk_ca(sk);
+	struct dctcp *ca = inet_csk_ca(sk);
+	struct tcp_sock *tp = tcp_sk(sk);
 
-		/* If this extension is enabled, we clamp dctcp_alpha to
-		 * max on packet loss; the motivation is that dctcp_alpha
-		 * is an indicator to the extend of congestion and packet
-		 * loss is an indicator of extreme congestion; setting
-		 * this in practice turned out to be beneficial, and
-		 * effectively assumes total congestion which reduces the
-		 * window by half.
-		 */
-		ca->dctcp_alpha = DCTCP_MAX_ALPHA;
-	}
+	ca->loss_cwnd = tp->snd_cwnd;
+	tp->snd_ssthresh = max(tp->snd_cwnd >> 1U, 2U);
+}
+
+static void dctcp_state(struct sock *sk, u8 new_state)
+{
+	if (new_state == TCP_CA_Recovery &&
+	    new_state != inet_csk(sk)->icsk_ca_state)
+		dctcp_react_to_loss(sk);
+	/* We handle RTO in dctcp_cwnd_event to ensure that we perform only
+	 * one loss-adjustment per RTT.
+	 */
 }
 
 static void dctcp_cwnd_event(struct sock *sk, enum tcp_ca_event ev)
@@ -190,6 +173,9 @@ static void dctcp_cwnd_event(struct sock *sk, enum tcp_ca_event ev)
 	case CA_EVENT_ECN_NO_CE:
 		dctcp_ece_ack_update(sk, ev, &ca->prior_rcv_nxt, &ca->ce_state);
 		break;
+	case CA_EVENT_LOSS:
+		dctcp_react_to_loss(sk);
+		break;
 	default:
 		/* Don't care for the rest. */
 		break;
@@ -200,6 +186,7 @@ static size_t dctcp_get_info(struct sock *sk, u32 ext, int *attr,
 			     union tcp_cc_info *info)
 {
 	const struct dctcp *ca = inet_csk_ca(sk);
+	const struct tcp_sock *tp = tcp_sk(sk);
 
 	/* Fill it also in case of VEGASINFO due to req struct limits.
 	 * We can still correctly retrieve it later.
@@ -211,8 +198,10 @@ static size_t dctcp_get_info(struct sock *sk, u32 ext, int *attr,
 			info->dctcp.dctcp_enabled = 1;
 			info->dctcp.dctcp_ce_state = (u16) ca->ce_state;
 			info->dctcp.dctcp_alpha = ca->dctcp_alpha;
-			info->dctcp.dctcp_ab_ecn = ca->acked_bytes_ecn;
-			info->dctcp.dctcp_ab_tot = ca->acked_bytes_total;
+			info->dctcp.dctcp_ab_ecn = tp->mss_cache *
+						   (tp->delivered_ce - ca->old_delivered_ce);
+			info->dctcp.dctcp_ab_tot = tp->mss_cache *
+						   (tp->delivered - ca->old_delivered);
 		}
 
 		*attr = INET_DIAG_DCTCPINFO;