RE: [PATCH v3] net/iavf: fix iavf query stats in intr thread

> -Original Message- > From: Ferruh Yigit > Sent: Monday, March 27, 2023 8:38 PM > To: Deng, KaiwenX ; dev@dpdk.org > Cc: sta...@dpdk.org; Yang, Qiming ; Zhou, YidingX > ; Chas Williams ; Min Hu (Connor) > ; Wu, Jingjing ; Xing, Beilei > ; Mike Pattrick ; Zhang, Qi Z > ; Doherty, Declan

Re: [PATCH v4 1/3] net/gve: switch license from MIT to BSD-3

On 3/29/2023 3:27 AM, Junfeng Guo wrote: > Switch license from MIT to BSD-3 for GVE base code. > In the meantime, remove MIT license exception for GVE driver. > > Signed-off-by: Rushil Gupta > Signed-off-by: Joshua Washington > Signed-off-by: Junfeng Guo > Signed-off-by: Jeroen de Borst Acked

Re: [PATCH 06/16] net/hns3: separate the setting of hash algorithm

On 3/29/2023 2:58 AM, lihuisong (C) wrote: > > 在 2023/3/11 3:36, Ferruh Yigit 写道: >> On 3/10/2023 9:35 AM, Dongdong Liu wrote: >>> From: Huisong Li >>> >>> Currently, the setting of hash algorithm comes from the >>> default configuration in driver and the rte_flow interface. >>> The hash algorith

[PATCH] doc: add tested platforms with NVIDIA NICs

Add tested platforms with NVIDIA NICs to the 23.03 release notes. Signed-off-by: Raslan Darawsheh --- doc/guides/rel_notes/release_23_03.rst | 149 + 1 file changed, 149 insertions(+) diff --git a/doc/guides/rel_notes/release_23_03.rst b/doc/guides/rel_notes/release_23_

RE: rte_atomic API compatibility & standard atomics

> From: Tyler Retzlaff [mailto:roret...@linux.microsoft.com] > Sent: Tuesday, 28 March 2023 20.46 > > On Mon, Mar 27, 2023 at 10:08:10PM +0200, Morten Brørup wrote: > > > From: Tyler Retzlaff [mailto:roret...@linux.microsoft.com] > > > Sent: Monday, 27 March 2023 21.39 > > > > > > Hi folks, > > >

[PATCH] eal/x86: remove redundant round to improve performance

In rte_memcpy_aligned(), one redundant round is taken in the 64 bytes block copy loops if the size is a multiple of 64. So, let the catch-up copy the last 64 bytes in this case. Suggested-by: Morten Brørup Signed-off-by: Leyi Rong --- lib/eal/x86/include/rte_memcpy.h | 2 +- 1 file changed, 1 i

RE: [PATCH] eal/x86: remove redundant round to improve performance

> From: Leyi Rong [mailto:leyi.r...@intel.com] > Sent: Wednesday, 29 March 2023 11.17 > > In rte_memcpy_aligned(), one redundant round is taken in the 64 bytes > block copy loops if the size is a multiple of 64. So, let the catch-up > copy the last 64 bytes in this case. > > Suggested-by: Morten

Re: [PATCH] eal/x86: remove redundant round to improve performance

On Wed, Mar 29, 2023 at 05:16:58PM +0800, Leyi Rong wrote: > In rte_memcpy_aligned(), one redundant round is taken in the 64 bytes > block copy loops if the size is a multiple of 64. So, let the catch-up > copy the last 64 bytes in this case. > > Suggested-by: Morten Brørup > Signed-off-by: Leyi

[PATCH] maintainers: update for FIPS validation

Add co-maintainer for FIPS validation example. Signed-off-by: Gowrishankar Muthukrishnan --- MAINTAINERS | 1 + 1 file changed, 1 insertion(+) diff --git a/MAINTAINERS b/MAINTAINERS index 280058adfc..8df23e5099 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -1809,6 +1809,7 @@ F: doc/guides/sampl

RE: [PATCH] maintainers: update for FIPS validation

> Subject: [PATCH] maintainers: update for FIPS validation > > Add co-maintainer for FIPS validation example. > > Signed-off-by: Gowrishankar Muthukrishnan Acked-by: Akhil Goyal

Re: [PATCH 2/2] net/gve: update copyright holders

28/03/2023 11:35, Guo, Junfeng: > The background is that, in the past (DPDK 22.11) we didn't get the approval > of license from Google, thus chose the MIT License for the base code, and > BSD-3 License for GVE common code (without the files in /base folder). > We also left the copyright holder of

[Bug 1202] valdez alaska hotels

https://bugs.dpdk.org/show_bug.cgi?id=1202 Bug ID: 1202 Summary: valdez alaska hotels Product: DPDK Version: 22.07 Hardware: All OS: All Status: UNCONFIRMED Severity: normal Priority: Normal

[Bug 1202] valdez alaska hotels

https://bugs.dpdk.org/show_bug.cgi?id=1202 David Marchand (david.march...@redhat.com) changed: What|Removed |Added Status|UNCONFIRMED |RESOLVED

Re: Reg: Link Bonding of VFs and PF admin down

On Wed, 29 Mar 2023 12:27:16 +0530 bharath paulraj wrote: > Hello Team, > > I have two X710 NICs in the hypervisor and created the VFs on those NICs. > PF is managed by the Linux kernel, while the VF is managed by DPDK. I am > using the "test-pmd" application to test the bonding functionality, >

Re: [PATCH v3 03/15] graph: move node process into inline function

On Wed, 29 Mar 2023 15:43:28 +0900 Zhirun Yan wrote: > +/** > + * @internal > + * > + * Enqueue a given node to the tail of the graph reel. > + * > + * @param graph > + * Pointer Graph object. > + * @param node > + * Pointer to node object to be enqueued. > + */ > +static __rte_always_inline

Re: [PATCH v3 03/15] graph: move node process into inline function

On Wed, Mar 29, 2023 at 9:04 PM Stephen Hemminger wrote: > > On Wed, 29 Mar 2023 15:43:28 +0900 > Zhirun Yan wrote: > > > +/** > > + * @internal > > + * > > + * Enqueue a given node to the tail of the graph reel. > > + * > > + * @param graph > > + * Pointer Graph object. > > + * @param node > >

Re: [PATCH] gro : ipv6 changes to support GRO for TCP/ipv6

Hi, I would like to get a review on the following patch where support is added for IPv6 GRO. Thanks, Param. On Thu, Oct 20, 2022 at 5:43 PM Kumara Parameshwaran < kumaraparames...@gmail.com> wrote: > From: Kumara Parameshwaran > > The patch adds GRO support for TCP/ipv6 packets. This does not

Reminder - DPDK CI Community Testing Meeting - Tomorrow 3/30/23 @ 6am PDT/9am EDT/1300h GMT

Good Evening, Tomorrow DPDK will be holding its CI Community Testing Meeting - 6am PDT/9am EDT/1300h GMT. Zoom information to follow. We look forward to seeing you there Thanks, Nathan Nathan C. Southern, Project Coordinator Data Plane Development Kit The Linux Foundation 248.835.4812 (m

Re: [PATCH v8 04/22] efd: replace RTE_LOGTYPE_EFD with dynamic type

On Tue, 21 Feb 2023 15:55:29 +0100 David Marchand wrote: > On Tue, Feb 21, 2023 at 12:36 AM Stephen Hemminger > wrote: > > > > Replace all uses of the global logtype with a dynamic log type. > > > > Signed-off-by: Stephen Hemminger > > --- > > lib/eal/common/eal_common_log.c | 1 - > > lib/eal

[PATCH v12 00/22] Covert static log types in libraries to dynamic

This patchset removes the main uses of static LOGTYPE's in DPDK libraries. It starts with the easy one and goes on to the more complex ones. There are several options on how to treat the old static types: leave them there, mark as deprecated, or remove them. This version removes them since there i

[PATCH v12 01/22] gso: don't log message on non TCP/UDP

If a large packet is passed into GSO routines of unknown protocol then library would log a message. Better to tell the application instead of logging. Fixes: 119583797b6a ("gso: support TCP/IPv4 GSO") Reviewed-by: Jiayu Hu Signed-off-by: Stephen Hemminger --- lib/gso/rte_gso.c | 4 +--- lib/gso

[PATCH v12 02/22] eal: drop no longer used GSO logtype

The message that used this was replaced in previous patch. Signed-off-by: Stephen Hemminger --- lib/eal/common/eal_common_log.c | 1 - lib/eal/include/rte_log.h | 2 +- 2 files changed, 1 insertion(+), 2 deletions(-) diff --git a/lib/eal/common/eal_common_log.c b/lib/eal/common/eal_common

[PATCH v12 03/22] log: drop unused RTE_LOGTYPE_TIMER

The timer code does not use rte_log. Signed-off-by: Stephen Hemminger --- lib/eal/common/eal_common_log.c | 1 - lib/eal/include/rte_log.h | 2 +- 2 files changed, 1 insertion(+), 2 deletions(-) diff --git a/lib/eal/common/eal_common_log.c b/lib/eal/common/eal_common_log.c index 894701e8c

[PATCH v12 04/22] efd: convert RTE_LOGTYPE_EFD to dynamic type

Replace all uses of the global logtype with a dynamic log type. Signed-off-by: Stephen Hemminger --- lib/eal/common/eal_common_log.c | 1 - lib/eal/include/rte_log.h | 2 +- lib/efd/rte_efd.c | 4 3 files changed, 5 insertions(+), 2 deletions(-) diff --git a/lib/eal/com

[PATCH v12 05/22] mbuf: convert RTE_LOGTYPE_MBUF to dynamic type

Introduce a new dynamic logtype for mbuf related messages. Since this is used in multiple files put one macro in mbuf_log.h Signed-off-by: Stephen Hemminger --- lib/eal/common/eal_common_log.c | 1 - lib/eal/include/rte_log.h | 2 +- lib/mbuf/mbuf_log.h | 4 lib/mbuf/rte_m

[PATCH v12 06/22] acl: convert RTE_LOGTYPE_ACL to dynamic type

Get rid of RTE_LOGTYPE_ACL and RTE_LOGTYPE_MALLOC. For ACL library use a dynamic type. The one message using RTE_LOGTYPE_MALLOC should have been under the ACL logtype anyway. The test code should not have been using fixed log type so just change that to stderr. Signed-off-by: Stephen Hemminger -

[PATCH v12 07/22] examples/power: replace use of RTE_LOGTYPE_POWER

Don't use static logtype in sample application. Signed-off-by: Stephen Hemminger Acked-by: David Hunt --- examples/distributor/main.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/examples/distributor/main.c b/examples/distributor/main.c index 21304d661873..542f76cf9664 10

[PATCH v12 08/22] examples/l3fwd-power: replace use of RTE_LOGTYPE_POWER

Convert to using a dynamic logtype for the application. Signed-off-by: Stephen Hemminger Acked-by: David Hunt --- examples/l3fwd-power/main.c | 17 + 1 file changed, 9 insertions(+), 8 deletions(-) diff --git a/examples/l3fwd-power/main.c b/examples/l3fwd-power/main.c index 3f0

[PATCH v12 10/22] ring: convert RTE_LOGTYPE_RING to dynamic type

The logtype for ring only used in library. Signed-off-by: Stephen Hemminger --- lib/eal/common/eal_common_log.c | 1 - lib/eal/include/rte_log.h | 2 +- lib/ring/rte_ring.c | 3 +++ 3 files changed, 4 insertions(+), 2 deletions(-) diff --git a/lib/eal/common/eal_common_log.c b

[PATCH v12 09/22] power: convert RTE_LOGTYPE_POWER to dynamic type

Use dynamic log type for power library. Also replace use of RTE_LOGTYPE_USER1 with lib.power.guest. Signed-off-by: Stephen Hemminger Acked-by: David Hunt --- lib/eal/common/eal_common_log.c | 1 - lib/eal/include/rte_log.h | 2 +- lib/power/guest_channel.c | 3 ++- lib/power/power_c

[PATCH v12 11/22] mempool: convert RTE_LOGTYPE_MEMPOOL to dynamic type

Convert from RTE_LOGTYPE_MEMPOOL to logtype_mempool. Signed-off-by: Stephen Hemminger --- lib/eal/common/eal_common_log.c | 1 - lib/eal/include/rte_log.h | 2 +- lib/mempool/rte_mempool.c | 2 ++ lib/mempool/rte_mempool.h | 8 lib/mempool/version.map | 3 +++

[PATCH v12 12/22] lpm: convert RTE_LOGTYPE_LPM to dynamic types

Split lpm and lpm6 into separate log types since they are in different files and user may want to change log levels for IPv4 vs IPv6. For rib and fib libraries give them own types as well. Signed-off-by: Stephen Hemminger --- lib/eal/common/eal_common_log.c | 1 - lib/eal/include/rte_log.h

[PATCH v12 13/22] kni: convert RTE_LOGTYPE_KNI to dynamic type

Even though KNI will eventually disappear, fix the logtype now. Signed-off-by: Stephen Hemminger --- lib/eal/common/eal_common_log.c | 1 - lib/eal/include/rte_log.h | 2 +- lib/kni/rte_kni.c | 3 +++ 3 files changed, 4 insertions(+), 2 deletions(-) diff --git a/lib/eal/comm

[PATCH v12 14/22] sched: convert RTE_LOGTYPE_SCHED to dynamic type

Also can remove unused RTE_LOGTYPE_METER Signed-off-by: Stephen Hemminger --- lib/eal/common/eal_common_log.c | 2 -- lib/eal/include/rte_log.h | 4 ++-- lib/sched/rte_pie.c | 1 + lib/sched/rte_sched.c | 5 + lib/sched/rte_sched_log.h | 4 5 files chan

[PATCH v12 15/22] examples/ipsec-secgw: replace RTE_LOGTYPE_PORT

Looks like some code got copy/paste in to the IPSEC gateway example from another place. Shouldn't be using RTE_LOGTYPE_PORT here. Fixes: ec17993a145a ("examples/ipsec-secgw: support security offload") Acked-by: Akhil Goyal Signed-off-by: Stephen Hemminger --- examples/ipsec-secgw/sa.c | 6 +++--

[PATCH v12 17/22] hash: move rte_thash_gfni stubs out of header file

Having stubs in header file makes it harder to update RTE_LOG(). Also modify to only print warning once. Signed-off-by: Stephen Hemminger --- lib/hash/meson.build | 8 ++- lib/hash/rte_thash_gfni.c | 47 +++ lib/hash/rte_thash_gfni.h | 30 ---

[PATCH v12 16/22] port: convert RTE_LOGTYPE_PORT to dynamic type

Split up the single static RTE_LOGTYPE_PORT into separate sub types for each component: port.ethdev, port.evendev, ... Signed-off-by: Stephen Hemminger --- lib/eal/common/eal_common_log.c | 1 - lib/eal/include/rte_log.h | 2 +- lib/port/rte_port_ethdev.c | 3 +++ lib/port/rte_port_ev

[PATCH v12 18/22] hash: move rte_hash_set_alg out header

The code for setting algorithm for hash is not at all perf sensitive, and doing it inline has a couple of problems. First, it means that if multiple files include the header, then the initialization gets done multiple times. But also, it makes it harder to fix usage of RTE_LOG(). Despite what the

[PATCH v12 19/22] hash: convert RTE_LOGTYPE_HASH to dynamic type

Use dynamic type for hash and add subtypes for crc and gfni. Signed-off-by: Stephen Hemminger --- lib/eal/common/eal_common_log.c | 1 - lib/eal/include/rte_log.h | 2 +- lib/hash/rte_cuckoo_hash.c | 5 + lib/hash/rte_fbk_hash.c | 5 + lib/hash/rte_thash.c|

[PATCH v12 21/22] app/test: remove use of RTE_LOGTYPE_PIPELINE

Instead of using static type PIPELINE for logging in test application use stderr instead. If not testing RTE_LOG() better to not use it since log also goes to syslog. Signed-off-by: Stephen Hemminger --- app/test/test_table_acl.c | 50 -- app/test/test_table

[PATCH v12 20/22] table: convert RTE_LOGTYPE_TABLE to dynamic type

Make an alias for RTE_LOGTYPE_TABLE in rte_table.h and use it. Signed-off-by: Stephen Hemminger --- lib/eal/common/eal_common_log.c | 1 - lib/eal/include/rte_log.h | 2 +- lib/table/meson.build | 1 + lib/table/rte_table.c | 8 lib/table/rte_table.h

[PATCH v12 22/22] pipeline: convert RTE_LOGTYPE_PIPELINE to dynamic type

Convert RTE_LOGTYPE_PIPELINE to a dynamic value. Signed-off-by: Stephen Hemminger --- lib/eal/common/eal_common_log.c | 1 - lib/eal/include/rte_log.h | 2 +- lib/pipeline/rte_pipeline.c | 2 ++ lib/pipeline/rte_pipeline.h | 5 + 4 files changed, 8 insertions(+), 2 deletions(-)

RE: [PATCH v3 04/15] graph: add get/set graph worker model APIs

> -Original Message- > From: Stephen Hemminger > Sent: Wednesday, March 29, 2023 11:35 PM > To: Yan, Zhirun > Cc: dev@dpdk.org; jer...@marvell.com; kirankum...@marvell.com; > ndabilpu...@marvell.com; Liang, Cunming ; Wang, > Haiyue > Subject: Re: [PATCH v3 04/15] graph: add get/set gr

Regarding DPDK API's like rte_timer_subsystem_init/rte_hash_create etc. in VPP

Hi, While trying to port some code to VPP (which uses DPDK as the backend driver), I am running into a problem that calls to API's like rte_timer_subsystem_init, rte_hash_create are failing while allocation of memory. This is presumably because VPP inits the EAL with the following arguments -- -

[PATCH v4 00/15] graph enhancement for multi-core dispatch

V4: Fix CI build issues about undefined reference of sched apis. Remove inline for model setting. V3: Fix CI build issues about TLS and typo. V2: Use git mv to keep git history. Use TLS for per-thread local storage. Change model name to mcore dispatch. Change API with specific mode name. Split bi

[PATCH v4 01/15] graph: rename rte_graph_work as common

Rename rte_graph_work.h to rte_graph_work_common.h for supporting multiple graph worker model. Signed-off-by: Haiyue Wang Signed-off-by: Cunming Liang Signed-off-by: Zhirun Yan --- MAINTAINERS | 1 + lib/graph/graph_pcap.c

[PATCH v4 02/15] graph: split graph worker into common and default model

To support multiple graph worker model, split graph into common and default. Naming the current walk function as rte_graph_model_rtc cause the default model is RTC(Run-to-completion). Signed-off-by: Haiyue Wang Signed-off-by: Cunming Liang Signed-off-by: Zhirun Yan --- lib/graph/graph_pcap.c

[PATCH v4 03/15] graph: move node process into inline function

Node process is a single and reusable block, move the code into an inline function. Signed-off-by: Haiyue Wang Signed-off-by: Cunming Liang Signed-off-by: Zhirun Yan --- lib/graph/rte_graph_model_rtc.h | 20 ++--- lib/graph/rte_graph_worker_common.h | 33 +++

[PATCH v4 04/15] graph: add get/set graph worker model APIs

Add new get/set APIs to configure graph worker model which is used to determine which model will be chosen. Signed-off-by: Haiyue Wang Signed-off-by: Cunming Liang Signed-off-by: Zhirun Yan --- lib/graph/meson.build | 1 + lib/graph/rte_graph_worker.c| 54 +++

[PATCH v4 05/15] graph: introduce graph node core affinity API

Add lcore_id for node to hold affinity core id and impl rte_graph_model_dispatch_lcore_affinity_set to set node affinity with specific lcore. Signed-off-by: Haiyue Wang Signed-off-by: Cunming Liang Signed-off-by: Zhirun Yan --- lib/graph/graph_private.h| 1 + lib/graph/meson.build

[PATCH v4 06/15] graph: introduce graph bind unbind API

Add lcore_id for graph to hold affinity core id where graph would run on. Add bind/unbind API to set/unset graph affinity attribute. lcore_id will be set as MAX by default, it means not enable this attribute. Signed-off-by: Haiyue Wang Signed-off-by: Cunming Liang Signed-off-by: Zhirun Yan ---

[PATCH v4 07/15] graph: introduce graph clone API for other worker core

This patch adds graph API for supporting to clone the graph object for a specified worker core. The new graph will also clone all nodes. Signed-off-by: Haiyue Wang Signed-off-by: Cunming Liang Signed-off-by: Zhirun Yan --- lib/graph/graph.c | 110 ++

[PATCH v4 08/15] graph: add struct for stream moving between cores

Add graph_sched_wq_node to hold graph scheduling workqueue node. Signed-off-by: Haiyue Wang Signed-off-by: Cunming Liang Signed-off-by: Zhirun Yan --- lib/graph/graph.c | 1 + lib/graph/graph_populate.c | 1 + lib/graph/graph_private.h | 12

[PATCH v4 09/15] graph: introduce stream moving cross cores

This patch introduces key functions to allow a worker thread to enable enqueue and move streams of objects to the next nodes over different cores. Signed-off-by: Haiyue Wang Signed-off-by: Cunming Liang Signed-off-by: Zhirun Yan --- lib/graph/graph_private.h| 27 + lib/graph/m

[PATCH v4 10/15] graph: enable create and destroy graph scheduling workqueue

This patch enables to create and destroy scheduling workqueue into common graph operations. Signed-off-by: Haiyue Wang Signed-off-by: Cunming Liang Signed-off-by: Zhirun Yan --- lib/graph/graph.c | 9 + 1 file changed, 9 insertions(+) diff --git a/lib/graph/graph.c b/lib/graph/graph.c

[PATCH v4 11/15] graph: introduce graph walk by cross-core dispatch

This patch introduces the task scheduler mechanism to enable dispatching tasks to another worker cores. Currently, there is only a local work queue for one graph to walk. We introduce a scheduler worker queue in each worker core for dispatching tasks. It will perform the walk on scheduler work queu

[PATCH v4 12/15] graph: enable graph multicore dispatch scheduler model

This patch enables to chose new scheduler model. Signed-off-by: Haiyue Wang Signed-off-by: Cunming Liang Signed-off-by: Zhirun Yan --- lib/graph/rte_graph_worker.h | 9 - 1 file changed, 8 insertions(+), 1 deletion(-) diff --git a/lib/graph/rte_graph_worker.h b/lib/graph/rte_graph_wor

[PATCH v4 13/15] graph: add stats for cross-core dispatching

Add stats for cross-core dispatching scheduler if stats collection is enabled. Signed-off-by: Haiyue Wang Signed-off-by: Cunming Liang Signed-off-by: Zhirun Yan --- lib/graph/graph_debug.c | 6 +++ lib/graph/graph_stats.c | 74 +--- lib/graph/

[PATCH v4 14/15] examples/l3fwd-graph: introduce multicore dispatch worker model

Add new parameter "model" to choose dispatch or rtc worker model. And in dispatch model, the node will affinity to worker core successively. Note: only support one RX node for remote model in current implementation. ./dpdk-l3fwd-graph -l 8,9,10,11 -n 4 -- -p 0x1 --config="(0,0,9)" -P --model="di

[PATCH v4 15/15] doc: update multicore dispatch model in graph guides

Update graph documentation to introduce new multicore dispatch model. Signed-off-by: Haiyue Wang Signed-off-by: Cunming Liang Signed-off-by: Zhirun Yan --- doc/guides/prog_guide/graph_lib.rst | 59 +++-- 1 file changed, 55 insertions(+), 4 deletions(-) diff --git a/doc

[PATCH v5 0/3] Recycle buffers from Tx to Rx

Currently, the transmit side frees the buffers into the lcore cache and the receive side allocates buffers from the lcore cache. The transmit side typically frees 32 buffers resulting in 32*8=256B of stores to lcore cache. The receive side allocates 32 buffers and stores them in the receive side so

[PATCH v5 1/3] ethdev: add API for buffer recycle mode

There are 4 upper APIs for buffer recycle mode: 1. 'rte_eth_rx_queue_buf_recycle_info_get' This is to retrieve buffer ring information about given ports's Rx queue in buffer recycle mode. And due to this, buffer recycle can be no longer limited to the same driver in Rx and Tx. 2. 'rte_eth_dev_buf_

[PATCH v5 2/3] net/i40e: implement recycle buffer mode

Define specific function implementation for i40e driver. Currently, recycle buffer mode can support 128bit vector path and avx2 path. And can be enabled both in fast free and no fast free mode. Suggested-by: Honnappa Nagarahalli Signed-off-by: Feifei Wang Reviewed-by: Ruifeng Wang Reviewed-by:

[PATCH v5 3/3] net/ixgbe: implement recycle buffer mode

Define specific function implementation for ixgbe driver. Currently, recycle buffer mode can support 128bit vector path. And can be enabled both in fast free and no fast free mode. Suggested-by: Honnappa Nagarahalli Signed-off-by: Feifei Wang Reviewed-by: Ruifeng Wang Reviewed-by: Honnappa Naga