[dpdk-stable] patch 'kni: fix not contiguous FIFO' has been queued to stable release 19.11.1

luca.boccassi at gmail.com luca.boccassi at gmail.com
Mon Feb 17 18:45:01 CET 2020


Hi,

FYI, your patch has been queued to stable release 19.11.1

Note it hasn't been pushed to http://dpdk.org/browse/dpdk-stable yet.
It will be pushed if I get no objections before 02/19/20. So please
shout if anyone has objections.

Also note that after the patch there's a diff of the upstream commit vs the
patch applied to the branch. This will indicate if there was any rebasing
needed to apply to the stable branch. If there were code changes for rebasing
(ie: not only metadata diffs), please double check that the rebase was
correctly done.

Thanks.

Luca Boccassi

---
>From a0de960f735231c702bfe6d8ff3d1f8f4dbd9c16 Mon Sep 17 00:00:00 2001
From: Scott Wasson <scott_wasson at affirmednetworks.com>
Date: Fri, 14 Feb 2020 10:00:52 +0000
Subject: [PATCH] kni: fix not contiguous FIFO

[ upstream commit eab71b8463c9d3aeeb8c222ff6159b4125d23019 ]

KNI requires FIFO to be physically contiguous, with existing
'rte_memzone_reserve()' API this is not guaranteed by default and as a
result KNI rings and packet delivery may be broken if reserved memory
is not physically contiguous.

Fixing it by providing 'RTE_MEMZONE_IOVA_CONTIG' flag to ask physically
contiguous memory.

Bugzilla ID: 389
Fixes: 23fa86e529e4 ("memzone: enable IOVA-contiguous reserving")

Signed-off-by: Scott Wasson <scott_wasson at affirmednetworks.com>
Acked-by: Ferruh Yigit <ferruh.yigit at intel.com>
---
 lib/librte_kni/rte_kni.c | 21 ++++++++++++++-------
 1 file changed, 14 insertions(+), 7 deletions(-)

diff --git a/lib/librte_kni/rte_kni.c b/lib/librte_kni/rte_kni.c
index e388751e33..bcf82cc2d5 100644
--- a/lib/librte_kni/rte_kni.c
+++ b/lib/librte_kni/rte_kni.c
@@ -145,31 +145,38 @@ kni_reserve_mz(struct rte_kni *kni)
 	char mz_name[RTE_MEMZONE_NAMESIZE];
 
 	snprintf(mz_name, RTE_MEMZONE_NAMESIZE, KNI_TX_Q_MZ_NAME_FMT, kni->name);
-	kni->m_tx_q = rte_memzone_reserve(mz_name, KNI_FIFO_SIZE, SOCKET_ID_ANY, 0);
+	kni->m_tx_q = rte_memzone_reserve(mz_name, KNI_FIFO_SIZE, SOCKET_ID_ANY,
+			RTE_MEMZONE_IOVA_CONTIG);
 	KNI_MEM_CHECK(kni->m_tx_q == NULL, tx_q_fail);
 
 	snprintf(mz_name, RTE_MEMZONE_NAMESIZE, KNI_RX_Q_MZ_NAME_FMT, kni->name);
-	kni->m_rx_q = rte_memzone_reserve(mz_name, KNI_FIFO_SIZE, SOCKET_ID_ANY, 0);
+	kni->m_rx_q = rte_memzone_reserve(mz_name, KNI_FIFO_SIZE, SOCKET_ID_ANY,
+			RTE_MEMZONE_IOVA_CONTIG);
 	KNI_MEM_CHECK(kni->m_rx_q == NULL, rx_q_fail);
 
 	snprintf(mz_name, RTE_MEMZONE_NAMESIZE, KNI_ALLOC_Q_MZ_NAME_FMT, kni->name);
-	kni->m_alloc_q = rte_memzone_reserve(mz_name, KNI_FIFO_SIZE, SOCKET_ID_ANY, 0);
+	kni->m_alloc_q = rte_memzone_reserve(mz_name, KNI_FIFO_SIZE, SOCKET_ID_ANY,
+			RTE_MEMZONE_IOVA_CONTIG);
 	KNI_MEM_CHECK(kni->m_alloc_q == NULL, alloc_q_fail);
 
 	snprintf(mz_name, RTE_MEMZONE_NAMESIZE, KNI_FREE_Q_MZ_NAME_FMT, kni->name);
-	kni->m_free_q = rte_memzone_reserve(mz_name, KNI_FIFO_SIZE, SOCKET_ID_ANY, 0);
+	kni->m_free_q = rte_memzone_reserve(mz_name, KNI_FIFO_SIZE, SOCKET_ID_ANY,
+			RTE_MEMZONE_IOVA_CONTIG);
 	KNI_MEM_CHECK(kni->m_free_q == NULL, free_q_fail);
 
 	snprintf(mz_name, RTE_MEMZONE_NAMESIZE, KNI_REQ_Q_MZ_NAME_FMT, kni->name);
-	kni->m_req_q = rte_memzone_reserve(mz_name, KNI_FIFO_SIZE, SOCKET_ID_ANY, 0);
+	kni->m_req_q = rte_memzone_reserve(mz_name, KNI_FIFO_SIZE, SOCKET_ID_ANY,
+			RTE_MEMZONE_IOVA_CONTIG);
 	KNI_MEM_CHECK(kni->m_req_q == NULL, req_q_fail);
 
 	snprintf(mz_name, RTE_MEMZONE_NAMESIZE, KNI_RESP_Q_MZ_NAME_FMT, kni->name);
-	kni->m_resp_q = rte_memzone_reserve(mz_name, KNI_FIFO_SIZE, SOCKET_ID_ANY, 0);
+	kni->m_resp_q = rte_memzone_reserve(mz_name, KNI_FIFO_SIZE, SOCKET_ID_ANY,
+			RTE_MEMZONE_IOVA_CONTIG);
 	KNI_MEM_CHECK(kni->m_resp_q == NULL, resp_q_fail);
 
 	snprintf(mz_name, RTE_MEMZONE_NAMESIZE, KNI_SYNC_ADDR_MZ_NAME_FMT, kni->name);
-	kni->m_sync_addr = rte_memzone_reserve(mz_name, KNI_FIFO_SIZE, SOCKET_ID_ANY, 0);
+	kni->m_sync_addr = rte_memzone_reserve(mz_name, KNI_FIFO_SIZE, SOCKET_ID_ANY,
+			RTE_MEMZONE_IOVA_CONTIG);
 	KNI_MEM_CHECK(kni->m_sync_addr == NULL, sync_addr_fail);
 
 	return 0;
-- 
2.20.1

---
  Diff of the applied patch vs upstream commit (please double-check if non-empty:
---
--- -	2020-02-17 17:00:15.602617383 +0000
+++ 0009-kni-fix-not-contiguous-FIFO.patch	2020-02-17 17:00:15.275950002 +0000
@@ -1,8 +1,10 @@
-From eab71b8463c9d3aeeb8c222ff6159b4125d23019 Mon Sep 17 00:00:00 2001
+From a0de960f735231c702bfe6d8ff3d1f8f4dbd9c16 Mon Sep 17 00:00:00 2001
 From: Scott Wasson <scott_wasson at affirmednetworks.com>
 Date: Fri, 14 Feb 2020 10:00:52 +0000
 Subject: [PATCH] kni: fix not contiguous FIFO
 
+[ upstream commit eab71b8463c9d3aeeb8c222ff6159b4125d23019 ]
+
 KNI requires FIFO to be physically contiguous, with existing
 'rte_memzone_reserve()' API this is not guaranteed by default and as a
 result KNI rings and packet delivery may be broken if reserved memory
@@ -13,7 +15,6 @@
 
 Bugzilla ID: 389
 Fixes: 23fa86e529e4 ("memzone: enable IOVA-contiguous reserving")
-Cc: stable at dpdk.org
 
 Signed-off-by: Scott Wasson <scott_wasson at affirmednetworks.com>
 Acked-by: Ferruh Yigit <ferruh.yigit at intel.com>


More information about the stable mailing list