linux-kernel - [PATCH 4.19 064/152] net: stmmac: Prevent RX starvation in stmmac_napi

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-Id: <20190225195047.810547535@linuxfoundation.org>
Date:   Mon, 25 Feb 2019 22:10:56 +0100
From:   Greg Kroah-Hartman <gregkh@...uxfoundation.org>
To:     linux-kernel@...r.kernel.org
Cc:     Greg Kroah-Hartman <gregkh@...uxfoundation.org>,
        stable@...r.kernel.org, Joao Pinto <jpinto@...opsys.com>,
        "David S. Miller" <davem@...emloft.net>,
        Giuseppe Cavallaro <peppe.cavallaro@...com>,
        Alexandre Torgue <alexandre.torgue@...com>,
        Jose Abreu <joabreu@...opsys.com>,
        Sasha Levin <sashal@...nel.org>
Subject: [PATCH 4.19 064/152] net: stmmac: Prevent RX starvation in stmmac_napi_poll()

4.19-stable review patch.  If anyone has any objections, please let me know.

------------------

[ Upstream commit fa0be0a43f101888ac677dba31b590963eafeaa1 ]

Currently, TX is given a budget which is consumed by stmmac_tx_clean()
and stmmac_rx() is given the remaining non-consumed budget.

This is wrong and in case we are sending a large number of packets this
can starve RX because remaining budget will be low.

Let's give always the same budget for RX and TX clean.

While at it, check if we missed any interrupts while we were in NAPI
callback by looking at DMA interrupt status.

Cc: Joao Pinto <jpinto@...opsys.com>
Cc: David S. Miller <davem@...emloft.net>
Cc: Giuseppe Cavallaro <peppe.cavallaro@...com>
Cc: Alexandre Torgue <alexandre.torgue@...com>
Signed-off-by: Jose Abreu <joabreu@...opsys.com>
Signed-off-by: David S. Miller <davem@...emloft.net>
Signed-off-by: Sasha Levin <sashal@...nel.org>
---
 .../net/ethernet/stmicro/stmmac/stmmac_main.c | 27 ++++++++++---------
 1 file changed, 14 insertions(+), 13 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index 24ae244c2ee33..123b74e25ed81 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -3522,27 +3522,28 @@ static int stmmac_napi_poll(struct napi_struct *napi, int budget)
 	struct stmmac_channel *ch =
 		container_of(napi, struct stmmac_channel, napi);
 	struct stmmac_priv *priv = ch->priv_data;
-	int work_done = 0, work_rem = budget;
+	int work_done, rx_done = 0, tx_done = 0;
 	u32 chan = ch->index;
 
 	priv->xstats.napi_poll++;
 
-	if (ch->has_tx) {
-		int done = stmmac_tx_clean(priv, work_rem, chan);
+	if (ch->has_tx)
+		tx_done = stmmac_tx_clean(priv, budget, chan);
+	if (ch->has_rx)
+		rx_done = stmmac_rx(priv, budget, chan);
 
-		work_done += done;
-		work_rem -= done;
-	}
-
-	if (ch->has_rx) {
-		int done = stmmac_rx(priv, work_rem, chan);
+	work_done = max(rx_done, tx_done);
+	work_done = min(work_done, budget);
 
-		work_done += done;
-		work_rem -= done;
-	}
+	if (work_done < budget && napi_complete_done(napi, work_done)) {
+		int stat;
 
-	if (work_done < budget && napi_complete_done(napi, work_done))
 		stmmac_enable_dma_irq(priv, priv->ioaddr, chan);
+		stat = stmmac_dma_interrupt_status(priv, priv->ioaddr,
+						   &priv->xstats, chan);
+		if (stat && napi_reschedule(napi))
+			stmmac_disable_dma_irq(priv, priv->ioaddr, chan);
+	}
 
 	return work_done;
 }
-- 
2.19.1