* [PATCH v7 1/4] vdpa: Add suspend operation
From: Eugenio Pérez @ 2022-08-10 17:15 UTC (permalink / raw)
To: kvm, Michael S. Tsirkin, linux-kernel, Jason Wang, virtualization,
netdev
Cc: dinang, martinpo, Wu Zongyong, Piotr.Uminski, gautam.dawar,
ecree.xilinx, martinh, Stefano Garzarella, pabloc, habetsm.xilinx,
lvivier, Zhu Lingshan, tanuj.kamde, Longpeng, lulu, hanand,
Parav Pandit, Si-Wei Liu, Eli Cohen, Xie Yongji, Zhang Min,
Dan Carpenter, Christophe JAILLET
In-Reply-To: <20220810171512.2343333-1-eperezma@redhat.com>
This operation is optional: It it's not implemented, backend feature bit
will not be exposed.
Signed-off-by: Eugenio Pérez <eperezma@redhat.com>
Message-Id: <20220623160738.632852-2-eperezma@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
---
include/linux/vdpa.h | 4 ++++
1 file changed, 4 insertions(+)
diff --git a/include/linux/vdpa.h b/include/linux/vdpa.h
index 7b4a13d3bd91..d282f464d2f1 100644
--- a/include/linux/vdpa.h
+++ b/include/linux/vdpa.h
@@ -218,6 +218,9 @@ struct vdpa_map_file {
* @reset: Reset device
* @vdev: vdpa device
* Returns integer: success (0) or error (< 0)
+ * @suspend: Suspend or resume the device (optional)
+ * @vdev: vdpa device
+ * Returns integer: success (0) or error (< 0)
* @get_config_size: Get the size of the configuration space includes
* fields that are conditional on feature bits.
* @vdev: vdpa device
@@ -319,6 +322,7 @@ struct vdpa_config_ops {
u8 (*get_status)(struct vdpa_device *vdev);
void (*set_status)(struct vdpa_device *vdev, u8 status);
int (*reset)(struct vdpa_device *vdev);
+ int (*suspend)(struct vdpa_device *vdev);
size_t (*get_config_size)(struct vdpa_device *vdev);
void (*get_config)(struct vdpa_device *vdev, unsigned int offset,
void *buf, unsigned int len);
--
2.31.1
^ permalink raw reply related
* [PATCH v7 3/4] vhost-vdpa: uAPI to suspend the device
From: Eugenio Pérez @ 2022-08-10 17:15 UTC (permalink / raw)
To: kvm, Michael S. Tsirkin, linux-kernel, Jason Wang, virtualization,
netdev
Cc: dinang, martinpo, Wu Zongyong, Piotr.Uminski, gautam.dawar,
ecree.xilinx, martinh, Stefano Garzarella, pabloc, habetsm.xilinx,
lvivier, Zhu Lingshan, tanuj.kamde, Longpeng, lulu, hanand,
Parav Pandit, Si-Wei Liu, Eli Cohen, Xie Yongji, Zhang Min,
Dan Carpenter, Christophe JAILLET
In-Reply-To: <20220810171512.2343333-1-eperezma@redhat.com>
The ioctl adds support for suspending the device from userspace.
This is a must before getting virtqueue indexes (base) for live migration,
since the device could modify them after userland gets them. There are
individual ways to perform that action for some devices
(VHOST_NET_SET_BACKEND, VHOST_VSOCK_SET_RUNNING, ...) but there was no
way to perform it for any vhost device (and, in particular, vhost-vdpa).
After a successful return of the ioctl call the device must not process
more virtqueue descriptors. The device can answer to read or writes of
config fields as if it were not suspended. In particular, writing to
"queue_enable" with a value of 1 will not make the device start
processing buffers of the virtqueue.
Signed-off-by: Eugenio Pérez <eperezma@redhat.com>
Message-Id: <20220623160738.632852-4-eperezma@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
---
v7: Delete argument to ioctl, unused
---
drivers/vhost/vdpa.c | 19 +++++++++++++++++++
include/uapi/linux/vhost.h | 9 +++++++++
2 files changed, 28 insertions(+)
diff --git a/drivers/vhost/vdpa.c b/drivers/vhost/vdpa.c
index 3d636e192061..7fa671ac4bdf 100644
--- a/drivers/vhost/vdpa.c
+++ b/drivers/vhost/vdpa.c
@@ -478,6 +478,22 @@ static long vhost_vdpa_get_vqs_count(struct vhost_vdpa *v, u32 __user *argp)
return 0;
}
+/* After a successful return of ioctl the device must not process more
+ * virtqueue descriptors. The device can answer to read or writes of config
+ * fields as if it were not suspended. In particular, writing to "queue_enable"
+ * with a value of 1 will not make the device start processing buffers.
+ */
+static long vhost_vdpa_suspend(struct vhost_vdpa *v)
+{
+ struct vdpa_device *vdpa = v->vdpa;
+ const struct vdpa_config_ops *ops = vdpa->config;
+
+ if (!ops->suspend)
+ return -EOPNOTSUPP;
+
+ return ops->suspend(vdpa);
+}
+
static long vhost_vdpa_vring_ioctl(struct vhost_vdpa *v, unsigned int cmd,
void __user *argp)
{
@@ -654,6 +670,9 @@ static long vhost_vdpa_unlocked_ioctl(struct file *filep,
case VHOST_VDPA_GET_VQS_COUNT:
r = vhost_vdpa_get_vqs_count(v, argp);
break;
+ case VHOST_VDPA_SUSPEND:
+ r = vhost_vdpa_suspend(v);
+ break;
default:
r = vhost_dev_ioctl(&v->vdev, cmd, argp);
if (r == -ENOIOCTLCMD)
diff --git a/include/uapi/linux/vhost.h b/include/uapi/linux/vhost.h
index cab645d4a645..f9f115a7c75b 100644
--- a/include/uapi/linux/vhost.h
+++ b/include/uapi/linux/vhost.h
@@ -171,4 +171,13 @@
#define VHOST_VDPA_SET_GROUP_ASID _IOW(VHOST_VIRTIO, 0x7C, \
struct vhost_vring_state)
+/* Suspend a device so it does not process virtqueue requests anymore
+ *
+ * After the return of ioctl the device must preserve all the necessary state
+ * (the virtqueue vring base plus the possible device specific states) that is
+ * required for restoring in the future. The device must not change its
+ * configuration after that point.
+ */
+#define VHOST_VDPA_SUSPEND _IO(VHOST_VIRTIO, 0x7D)
+
#endif
--
2.31.1
^ permalink raw reply related
* [PATCH v7 2/4] vhost-vdpa: introduce SUSPEND backend feature bit
From: Eugenio Pérez @ 2022-08-10 17:15 UTC (permalink / raw)
To: kvm, Michael S. Tsirkin, linux-kernel, Jason Wang, virtualization,
netdev
Cc: dinang, martinpo, Wu Zongyong, Piotr.Uminski, gautam.dawar,
ecree.xilinx, martinh, Stefano Garzarella, pabloc, habetsm.xilinx,
lvivier, Zhu Lingshan, tanuj.kamde, Longpeng, lulu, hanand,
Parav Pandit, Si-Wei Liu, Eli Cohen, Xie Yongji, Zhang Min,
Dan Carpenter, Christophe JAILLET
In-Reply-To: <20220810171512.2343333-1-eperezma@redhat.com>
Userland knows if it can suspend the device or not by checking this feature
bit.
It's only offered if the vdpa driver backend implements the suspend()
operation callback, and to offer it or userland to ack it if the backend
does not offer that callback is an error.
Signed-off-by: Eugenio Pérez <eperezma@redhat.com>
Message-Id: <20220623160738.632852-3-eperezma@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
---
drivers/vhost/vdpa.c | 16 +++++++++++++++-
include/uapi/linux/vhost_types.h | 2 ++
2 files changed, 17 insertions(+), 1 deletion(-)
diff --git a/drivers/vhost/vdpa.c b/drivers/vhost/vdpa.c
index 23dcbfdfa13b..3d636e192061 100644
--- a/drivers/vhost/vdpa.c
+++ b/drivers/vhost/vdpa.c
@@ -347,6 +347,14 @@ static long vhost_vdpa_set_config(struct vhost_vdpa *v,
return 0;
}
+static bool vhost_vdpa_can_suspend(const struct vhost_vdpa *v)
+{
+ struct vdpa_device *vdpa = v->vdpa;
+ const struct vdpa_config_ops *ops = vdpa->config;
+
+ return ops->suspend;
+}
+
static long vhost_vdpa_get_features(struct vhost_vdpa *v, u64 __user *featurep)
{
struct vdpa_device *vdpa = v->vdpa;
@@ -577,7 +585,11 @@ static long vhost_vdpa_unlocked_ioctl(struct file *filep,
if (cmd == VHOST_SET_BACKEND_FEATURES) {
if (copy_from_user(&features, featurep, sizeof(features)))
return -EFAULT;
- if (features & ~VHOST_VDPA_BACKEND_FEATURES)
+ if (features & ~(VHOST_VDPA_BACKEND_FEATURES |
+ BIT_ULL(VHOST_BACKEND_F_SUSPEND)))
+ return -EOPNOTSUPP;
+ if ((features & BIT_ULL(VHOST_BACKEND_F_SUSPEND)) &&
+ !vhost_vdpa_can_suspend(v))
return -EOPNOTSUPP;
vhost_set_backend_features(&v->vdev, features);
return 0;
@@ -628,6 +640,8 @@ static long vhost_vdpa_unlocked_ioctl(struct file *filep,
break;
case VHOST_GET_BACKEND_FEATURES:
features = VHOST_VDPA_BACKEND_FEATURES;
+ if (vhost_vdpa_can_suspend(v))
+ features |= BIT_ULL(VHOST_BACKEND_F_SUSPEND);
if (copy_to_user(featurep, &features, sizeof(features)))
r = -EFAULT;
break;
diff --git a/include/uapi/linux/vhost_types.h b/include/uapi/linux/vhost_types.h
index 634cee485abb..1bdd6e363f4c 100644
--- a/include/uapi/linux/vhost_types.h
+++ b/include/uapi/linux/vhost_types.h
@@ -161,5 +161,7 @@ struct vhost_vdpa_iova_range {
* message
*/
#define VHOST_BACKEND_F_IOTLB_ASID 0x3
+/* Device can be suspended */
+#define VHOST_BACKEND_F_SUSPEND 0x4
#endif
--
2.31.1
^ permalink raw reply related
* [PATCH v7 4/4] vdpa_sim: Implement suspend vdpa op
From: Eugenio Pérez @ 2022-08-10 17:15 UTC (permalink / raw)
To: kvm, Michael S. Tsirkin, linux-kernel, Jason Wang, virtualization,
netdev
Cc: dinang, martinpo, Wu Zongyong, Piotr.Uminski, gautam.dawar,
ecree.xilinx, martinh, Stefano Garzarella, pabloc, habetsm.xilinx,
lvivier, Zhu Lingshan, tanuj.kamde, Longpeng, lulu, hanand,
Parav Pandit, Si-Wei Liu, Eli Cohen, Xie Yongji, Zhang Min,
Dan Carpenter, Christophe JAILLET
In-Reply-To: <20220810171512.2343333-1-eperezma@redhat.com>
Implement suspend operation for vdpa_sim devices, so vhost-vdpa will
offer that backend feature and userspace can effectively suspend the
device.
This is a must before get virtqueue indexes (base) for live migration,
since the device could modify them after userland gets them. There are
individual ways to perform that action for some devices
(VHOST_NET_SET_BACKEND, VHOST_VSOCK_SET_RUNNING, ...) but there was no
way to perform it for any vhost device (and, in particular, vhost-vdpa).
Reviewed-by: Stefano Garzarella <sgarzare@redhat.com>
Signed-off-by: Eugenio Pérez <eperezma@redhat.com>
Message-Id: <20220623160738.632852-5-eperezma@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
---
v7: Delete leftover resume code
---
drivers/vdpa/vdpa_sim/vdpa_sim.c | 14 ++++++++++++++
drivers/vdpa/vdpa_sim/vdpa_sim.h | 1 +
drivers/vdpa/vdpa_sim/vdpa_sim_blk.c | 3 +++
drivers/vdpa/vdpa_sim/vdpa_sim_net.c | 3 +++
4 files changed, 21 insertions(+)
diff --git a/drivers/vdpa/vdpa_sim/vdpa_sim.c b/drivers/vdpa/vdpa_sim/vdpa_sim.c
index 0f2865899647..79a50edf8998 100644
--- a/drivers/vdpa/vdpa_sim/vdpa_sim.c
+++ b/drivers/vdpa/vdpa_sim/vdpa_sim.c
@@ -107,6 +107,7 @@ static void vdpasim_do_reset(struct vdpasim *vdpasim)
for (i = 0; i < vdpasim->dev_attr.nas; i++)
vhost_iotlb_reset(&vdpasim->iommu[i]);
+ vdpasim->running = true;
spin_unlock(&vdpasim->iommu_lock);
vdpasim->features = 0;
@@ -505,6 +506,17 @@ static int vdpasim_reset(struct vdpa_device *vdpa)
return 0;
}
+static int vdpasim_suspend(struct vdpa_device *vdpa)
+{
+ struct vdpasim *vdpasim = vdpa_to_sim(vdpa);
+
+ spin_lock(&vdpasim->lock);
+ vdpasim->running = false;
+ spin_unlock(&vdpasim->lock);
+
+ return 0;
+}
+
static size_t vdpasim_get_config_size(struct vdpa_device *vdpa)
{
struct vdpasim *vdpasim = vdpa_to_sim(vdpa);
@@ -694,6 +706,7 @@ static const struct vdpa_config_ops vdpasim_config_ops = {
.get_status = vdpasim_get_status,
.set_status = vdpasim_set_status,
.reset = vdpasim_reset,
+ .suspend = vdpasim_suspend,
.get_config_size = vdpasim_get_config_size,
.get_config = vdpasim_get_config,
.set_config = vdpasim_set_config,
@@ -726,6 +739,7 @@ static const struct vdpa_config_ops vdpasim_batch_config_ops = {
.get_status = vdpasim_get_status,
.set_status = vdpasim_set_status,
.reset = vdpasim_reset,
+ .suspend = vdpasim_suspend,
.get_config_size = vdpasim_get_config_size,
.get_config = vdpasim_get_config,
.set_config = vdpasim_set_config,
diff --git a/drivers/vdpa/vdpa_sim/vdpa_sim.h b/drivers/vdpa/vdpa_sim/vdpa_sim.h
index 622782e92239..061986f30911 100644
--- a/drivers/vdpa/vdpa_sim/vdpa_sim.h
+++ b/drivers/vdpa/vdpa_sim/vdpa_sim.h
@@ -66,6 +66,7 @@ struct vdpasim {
u32 generation;
u64 features;
u32 groups;
+ bool running;
/* spinlock to synchronize iommu table */
spinlock_t iommu_lock;
};
diff --git a/drivers/vdpa/vdpa_sim/vdpa_sim_blk.c b/drivers/vdpa/vdpa_sim/vdpa_sim_blk.c
index 42d401d43911..bcdb1982c378 100644
--- a/drivers/vdpa/vdpa_sim/vdpa_sim_blk.c
+++ b/drivers/vdpa/vdpa_sim/vdpa_sim_blk.c
@@ -204,6 +204,9 @@ static void vdpasim_blk_work(struct work_struct *work)
if (!(vdpasim->status & VIRTIO_CONFIG_S_DRIVER_OK))
goto out;
+ if (!vdpasim->running)
+ goto out;
+
for (i = 0; i < VDPASIM_BLK_VQ_NUM; i++) {
struct vdpasim_virtqueue *vq = &vdpasim->vqs[i];
diff --git a/drivers/vdpa/vdpa_sim/vdpa_sim_net.c b/drivers/vdpa/vdpa_sim/vdpa_sim_net.c
index 5125976a4df8..886449e88502 100644
--- a/drivers/vdpa/vdpa_sim/vdpa_sim_net.c
+++ b/drivers/vdpa/vdpa_sim/vdpa_sim_net.c
@@ -154,6 +154,9 @@ static void vdpasim_net_work(struct work_struct *work)
spin_lock(&vdpasim->lock);
+ if (!vdpasim->running)
+ goto out;
+
if (!(vdpasim->status & VIRTIO_CONFIG_S_DRIVER_OK))
goto out;
--
2.31.1
^ permalink raw reply related
* Re: [RFC 1/1] net: move IFF_LIVE_ADDR_CHANGE to public flag
From: Johannes Berg @ 2022-08-10 17:17 UTC (permalink / raw)
To: James Prestwood, Jakub Kicinski; +Cc: netdev
In-Reply-To: <d585f719af13d7a7194e7cb734c5a7446954bf01.camel@gmail.com>
On Wed, 2022-08-10 at 09:26 -0700, James Prestwood wrote:
>
> Ok, so this is how I originally did it in those old patches:
>
> https://lore.kernel.org/linux-wireless/20190913195908.7871-2-prestwoj@gmail.com/
>
> i.e. remove_interface, change the mac, add_interface.
Hah, I didn't even remember that ... sorry.
> But before I revive those I want to make sure a flag can be advertised
> to userspace e.g. NL80211_EXT_FEATURE_LIVE_ADDRESS_CHANGE. (or
> POWERED). Since this was the reason the patches got dropped in the
> first place.
>
Well it seems that my objection then was basically that you have a
feature flag in nl80211, but it affects an RT netlink operation ...
which is a bit strange.
Thinking about that now, maybe it's not _that_ bad? Especially given
that "live" can mean different things (as discussed here), and for
wireless that doesn't necessarily mean IFF_UP, but rather something like
"IFF_UP + not active".
Jakub, what do you think?
(I'll also note you also have error handling problems in your patch, so
if/when you revive, please take a look at handling errors from add and
remove interface. Also indentation, and a comment on station/p2p-client
might be good, and the scanning check is wrong, can check scan_sdata
regardless of the iftype.)
johannes
^ permalink raw reply
* Re: [PATCH] igc: Remove _I_PHY_ID check for i225 devices
From: Tony Nguyen @ 2022-08-10 17:20 UTC (permalink / raw)
To: Linjun Bao
Cc: Jeff Kirsher, David S. Miller, intel-wired-lan, netdev,
linux-kernel
In-Reply-To: <0b4ce201-be78-5a5d-0098-0cbe14ea43fd@gmail.com>
On 8/10/2022 1:22 AM, Linjun Bao wrote:
> Yes this commit was committed to mainline about one year ago. But this commit has not been included into kernel 5.4 yet, and I encountered the probe failure when using alderlake-s with Ethernet adapter i225-LM. Since I could not directly apply the patch 7c496de538ee to kernel 5.4, so I generated this patch for kernel 5.4 usage.
>
>
> Looks like sending a duplicated patch is not expected. Would you please advise what is the proper action when encountering such case?
Sounds like you want this backported to stable. Documentation on how to
do it is here [1]. Option 3 seems to be the correct choice.
Thanks,
Tony
[1]
https://www.kernel.org/doc/html/latest/process/stable-kernel-rules.html#procedure-for-submitting-patches-to-the-stable-tree
^ permalink raw reply
* Re: [RFC 1/1] net: move IFF_LIVE_ADDR_CHANGE to public flag
From: Jakub Kicinski @ 2022-08-10 17:36 UTC (permalink / raw)
To: Johannes Berg; +Cc: James Prestwood, netdev
In-Reply-To: <9ec77cf1ffaa29aedd57c29ac77b525d0e700acf.camel@sipsolutions.net>
On Wed, 10 Aug 2022 19:17:19 +0200 Johannes Berg wrote:
> Thinking about that now, maybe it's not _that_ bad? Especially given
> that "live" can mean different things (as discussed here), and for
> wireless that doesn't necessarily mean IFF_UP, but rather something like
> "IFF_UP + not active".
>
> Jakub, what do you think?
Agreed, even tho the concept of a live address change seems generic
the implications and definition of "live" are very area specific.
Let's handwave that nl80211 is a subordinate API of RT netlink :)
^ permalink raw reply
* Re: [PATCH 2/2] net/mlx5e: Leverage sched_numa_hop_mask()
From: Jakub Kicinski @ 2022-08-10 17:42 UTC (permalink / raw)
To: Tariq Toukan
Cc: Valentin Schneider, netdev, linux-kernel, Tariq Toukan,
David S. Miller, Saeed Mahameed, Ingo Molnar, Peter Zijlstra,
Juri Lelli, Eric Dumazet, Paolo Abeni, Gal Pressman,
Vincent Guittot
In-Reply-To: <8448dade-a64a-0b6b-1ed0-dd164917eedf@gmail.com>
On Wed, 10 Aug 2022 15:57:33 +0300 Tariq Toukan wrote:
> > + for_each_cpu(cpu, mask) {
> > + cpus[i] = cpu;
> > + if (++i == ncomp_eqs)
> > + goto spread_done;
> > + }
> > + }
> > +spread_done:
> > + rcu_read_unlock();
> > ret = mlx5_irqs_request_vectors(dev, cpus, ncomp_eqs, table->comp_irqs);
> > kfree(cpus);
> > if (ret < 0)
>
> This logic is typical. Other drivers would also want to use it.
> It must be introduced as a service/API function, if not by the sched
> topology, then at least by the networking subsystem.
> Jakub, WDYT?
Agreed, no preference where the helper would live tho.
^ permalink raw reply
* This Mail is intended for you!!!
From: GoldenFx Trading Inc @ 2022-08-10 7:51 UTC (permalink / raw)
To: netdev
Warm Greetings netdev@vger.kernel.org,
This is GoldenFx trading Inc and we are writing you this mail
because we just confirmed netdev@vger.kernel.org as being the
reachable email to the next of kin of Mr. Eric Who happens to own
a portfolio containing a huge amount of Cryptocurrency on our
platform and Information reaching us, reveals that Mr. Eric is
dead and no one is yet to come and claim his portfolio with
us.
At this point, we are left with no choice than to contact you to
come and claim your relative's accumulated cryptocurrency that is
ready for withdrawal on our platform.
We will be waiting for your soonest response. Thanks
Sincerely,
Golden Fx Traders Inc.
Confidentiality: This mail is officially generated from Goldenfx
Trading Inc and it is intended for netdev@vger.kernel.org And the
information contained in this email communication (including any
attachment(s)) is strictly confidential and intended solely for
the person or entity named above. If you are not the intended
recipient of this email, you are hereby notified that any
disclosure, distribution, reproduction, or other use of this
communication is strictly prohibited. If you have received this
communication in error, please immediately notify the sender by
return email and permanently delete this communication (including
any attachment(s)) from your system.
^ permalink raw reply
* [PATCH net-next 00/10] net/smc: optimize the parallelism of SMC-R connections
From: D. Wythe @ 2022-08-10 17:47 UTC (permalink / raw)
To: kgraul, wenjia; +Cc: kuba, davem, netdev, linux-s390, linux-rdma
From: "D. Wythe" <alibuda@linux.alibaba.com>
This patch set attempts to optimize the parallelism of SMC-R connections,
mainly to reduce unnecessary blocking on locks, and to fix exceptions that
occur after thoses optimization.
According to Off-CPU graph, SMC worker's off-CPU as that:
smc_close_passive_work (1.09%)
smcr_buf_unuse (1.08%)
smc_llc_flow_initiate (1.02%)
smc_listen_work (48.17%)
__mutex_lock.isra.11 (47.96%)
An ideal SMC-R connection process should only block on the IO events
of the network, but it's quite clear that the SMC-R connection now is
queued on the lock most of the time.
The goal of this patchset is to achieve our ideal situation where
network IO events are blocked for the majority of the connection lifetime.
There are three big locks here:
1. smc_client_lgr_pending & smc_server_lgr_pending
2. llc_conf_mutex
3. rmbs_lock & sndbufs_lock
And an implementation issue:
1. confirm/delete rkey msg can't be sent concurrently while
protocol allows indeed.
Unfortunately,The above problems together affect the parallelism of
SMC-R connection. If any of them are not solved. our goal cannot
be achieved.
After this patch set, we can get a quite ideal off-CPU graph as
following:
smc_close_passive_work (41.58%)
smcr_buf_unuse (41.57%)
smc_llc_do_delete_rkey (41.57%)
smc_listen_work (39.10%)
smc_clc_wait_msg (13.18%)
tcp_recvmsg_locked (13.18)
smc_listen_find_device (25.87%)
smcr_lgr_reg_rmbs (25.87%)
smc_llc_do_confirm_rkey (25.87%)
We can see that most of the waiting times are waiting for network IO
events. This also has a certain performance improvement on our
short-lived conenction wrk/nginx benchmark test:
+--------------+------+------+-------+--------+------+--------+
|conns/qps |c4 | c8 | c16 | c32 | c64 | c200 |
+--------------+------+------+-------+--------+------+--------+
|SMC-R before |9.7k | 10k | 10k | 9.9k | 9.1k | 8.9k |
+--------------+------+------+-------+--------+------+--------+
|SMC-R now |13k | 19k | 18k | 16k | 15k | 12k |
+--------------+------+------+-------+--------+------+--------+
|TCP |15k | 35k | 51k | 80k | 100k | 162k |
+--------------+------+------+-------+--------+------+--------+
The reason why the benefit is not obvious after the number of connections has
increased dues to workqueue. If we try to change workqueue to WQ_UNBOUND, we can
obtain at least 4-5 times performance improvement, can reach up to half of TCP.
However, this is not an elegant solution, the optimization of it will be much
more complicated. But in any case, we will submit relevant optimization
patches as soon as possible.
Please note that the premise here is that the lock related problem
must be solved first, otherwise, no matter how we optimize the workqueue,
there won't be much improvement.
Because there are a lot of related changes to the code, if you have any questions
or suggestions, please let me know.
Thanks
D. Wythe
D. Wythe (10):
net/smc: remove locks smc_client_lgr_pending and
smc_server_lgr_pending
net/smc: fix SMC_CLC_DECL_ERR_REGRMB without smc_server_lgr_pending
net/smc: allow confirm/delete rkey response deliver multiplex
net/smc: make SMC_LLC_FLOW_RKEY run concurrently
net/smc: llc_conf_mutex refactor, replace it with rw_semaphore
net/smc: use read semaphores to reduce unnecessary blocking in
smc_buf_create() & smcr_buf_unuse()
net/smc: reduce unnecessary blocking in smcr_lgr_reg_rmbs()
net/smc: replace mutex rmbs_lock and sndbufs_lock with rw_semaphore
net/smc: fix potential panic dues to unprotected
smc_llc_srv_add_link()
net/smc: fix application data exception
net/smc/af_smc.c | 40 +++--
net/smc/smc_core.c | 447 +++++++++++++++++++++++++++++++++++++++++++++++------
net/smc/smc_core.h | 76 ++++++++-
net/smc/smc_llc.c | 286 +++++++++++++++++++++++++---------
net/smc/smc_llc.h | 6 +
net/smc/smc_wr.c | 10 --
net/smc/smc_wr.h | 10 ++
7 files changed, 728 insertions(+), 147 deletions(-)
--
1.8.3.1
^ permalink raw reply
* [PATCH net-next 02/10] net/smc: fix SMC_CLC_DECL_ERR_REGRMB without smc_server_lgr_pending
From: D. Wythe @ 2022-08-10 17:47 UTC (permalink / raw)
To: kgraul, wenjia; +Cc: kuba, davem, netdev, linux-s390, linux-rdma
In-Reply-To: <cover.1660152975.git.alibuda@linux.alibaba.com>
From: "D. Wythe" <alibuda@linux.alibaba.com>
As commit "net/smc: fix unexpected SMC_CLC_DECL_ERR_REGRMB error cause
by server" mentioned, it works only when all connection creations are
completely protected by smc_server_lgr_pending lock, since we already
cancel the lock, we need to re-fix the issues.
Fixes: 4940a1fdf31c ("net/smc: fix unexpected SMC_CLC_DECL_ERR_REGRMB error cause by server")
Signed-off-by: D. Wythe <alibuda@linux.alibaba.com>
---
net/smc/af_smc.c | 2 ++
net/smc/smc_core.c | 11 ++++++++---
net/smc/smc_core.h | 21 +++++++++++++++++++++
3 files changed, 31 insertions(+), 3 deletions(-)
diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c
index af4b0aa..c0842a9 100644
--- a/net/smc/af_smc.c
+++ b/net/smc/af_smc.c
@@ -2413,6 +2413,7 @@ static void smc_listen_work(struct work_struct *work)
if (rc)
goto out_unlock;
}
+ smc_conn_leave_rtoken_pending(new_smc, ini);
smc_conn_save_peer_info(new_smc, cclc);
smc_listen_out_connected(new_smc);
SMC_STAT_SERV_SUCC_INC(sock_net(newclcsock->sk), ini);
@@ -2422,6 +2423,7 @@ static void smc_listen_work(struct work_struct *work)
if (ini->is_smcd)
mutex_unlock(&smc_server_lgr_pending);
out_decl:
+ smc_conn_leave_rtoken_pending(new_smc, ini);
smc_listen_decline(new_smc, rc, ini ? ini->first_contact_local : 0,
proposal_version);
out_free:
diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c
index a3338cc..61a3854 100644
--- a/net/smc/smc_core.c
+++ b/net/smc/smc_core.c
@@ -2190,14 +2190,19 @@ int smc_conn_create(struct smc_sock *smc, struct smc_init_info *ini)
lgr->vlan_id == ini->vlan_id) &&
(role == SMC_CLNT || ini->is_smcd ||
(lgr->conns_num < SMC_RMBS_PER_LGR_MAX &&
- !bitmap_full(lgr->rtokens_used_mask, SMC_RMBS_PER_LGR_MAX)))) {
+ (SMC_RMBS_PER_LGR_MAX -
+ bitmap_weight(lgr->rtokens_used_mask, SMC_RMBS_PER_LGR_MAX)
+ > atomic_read(&lgr->rtoken_pendings))))) {
/* link group found */
ini->first_contact_local = 0;
conn->lgr = lgr;
rc = smc_lgr_register_conn(conn, false);
write_unlock_bh(&lgr->conns_lock);
- if (!rc && delayed_work_pending(&lgr->free_work))
- cancel_delayed_work(&lgr->free_work);
+ if (!rc) {
+ smc_conn_enter_rtoken_pending(smc, ini);
+ if (delayed_work_pending(&lgr->free_work))
+ cancel_delayed_work(&lgr->free_work);
+ }
break;
}
write_unlock_bh(&lgr->conns_lock);
diff --git a/net/smc/smc_core.h b/net/smc/smc_core.h
index 199f533..acc2869 100644
--- a/net/smc/smc_core.h
+++ b/net/smc/smc_core.h
@@ -293,6 +293,9 @@ struct smc_link_group {
struct rb_root conns_all; /* connection tree */
rwlock_t conns_lock; /* protects conns_all */
unsigned int conns_num; /* current # of connections */
+ atomic_t rtoken_pendings;/* number of connection that
+ * lgr assigned but no rtoken got yet
+ */
unsigned short vlan_id; /* vlan id of link group */
struct list_head sndbufs[SMC_RMBE_SIZES];/* tx buffers */
@@ -603,6 +606,24 @@ struct smc_link *smc_switch_conns(struct smc_link_group *lgr,
int smcr_nl_get_link(struct sk_buff *skb, struct netlink_callback *cb);
int smcd_nl_get_lgr(struct sk_buff *skb, struct netlink_callback *cb);
+static inline void smc_conn_enter_rtoken_pending(struct smc_sock *smc, struct smc_init_info *ini)
+{
+ struct smc_link_group *lgr;
+
+ lgr = smc->conn.lgr;
+ if (lgr && !ini->first_contact_local)
+ atomic_inc(&lgr->rtoken_pendings);
+}
+
+static inline void smc_conn_leave_rtoken_pending(struct smc_sock *smc, struct smc_init_info *ini)
+{
+ struct smc_link_group *lgr;
+
+ lgr = smc->conn.lgr;
+ if (lgr && !ini->first_contact_local)
+ atomic_dec(&lgr->rtoken_pendings);
+}
+
void smcr_lnk_cluster_on_lnk_state(struct smc_link *lnk);
static inline struct smc_link_group *smc_get_lgr(struct smc_link *link)
--
1.8.3.1
^ permalink raw reply related
* [PATCH net-next 01/10] net/smc: remove locks smc_client_lgr_pending and smc_server_lgr_pending
From: D. Wythe @ 2022-08-10 17:47 UTC (permalink / raw)
To: kgraul, wenjia; +Cc: kuba, davem, netdev, linux-s390, linux-rdma
In-Reply-To: <cover.1660152975.git.alibuda@linux.alibaba.com>
From: "D. Wythe" <alibuda@linux.alibaba.com>
This patch attempts to remove locks named smc_client_lgr_pending and
smc_server_lgr_pending, which aim to serialize the creation of link
group. However, once link group existed already, those locks are
meaningless, worse still, they make incoming connections have to be
queued one after the other.
Now, the creation of link group is no longer generated by competition,
but allocated through following strategy.
1. Try to find a suitable link group, if successd, current connection
is considered as NON first contact connection. ends.
2. Check the number of connections currently waiting for a suitable
link group to be created, if it is not less that the number of link
groups to be created multiplied by (SMC_RMBS_PER_LGR_MAX - 1), then
increase the number of link groups to be created, current connection
is considered as the first contact connection. ends.
3. Increase the number of connections currently waiting, and wait
for woken up.
4. Decrease the number of connections currently waiting, goto 1.
We wake up the connection that was put to sleep in stage 3 through
the SMC link state change event. Once the link moves out of the
SMC_LNK_ACTIVATING state, decrease the number of link groups to
be created, and then wake up at most (SMC_RMBS_PER_LGR_MAX - 1)
connections.
In the iplementation, we introduce the concept of lnk cluster, which is
a collection of links with the same characteristics (see
smcr_lnk_cluster_cmpfn() with more details), which makes it possible to
wake up efficiently in the scenario of N v.s 1.
Signed-off-by: D. Wythe <alibuda@linux.alibaba.com>
---
net/smc/af_smc.c | 11 +-
net/smc/smc_core.c | 356 ++++++++++++++++++++++++++++++++++++++++++++++++++++-
net/smc/smc_core.h | 48 ++++++++
net/smc/smc_llc.c | 9 +-
4 files changed, 411 insertions(+), 13 deletions(-)
diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c
index 79c1318..af4b0aa 100644
--- a/net/smc/af_smc.c
+++ b/net/smc/af_smc.c
@@ -1194,10 +1194,8 @@ static int smc_connect_rdma(struct smc_sock *smc,
if (reason_code)
return reason_code;
- mutex_lock(&smc_client_lgr_pending);
reason_code = smc_conn_create(smc, ini);
if (reason_code) {
- mutex_unlock(&smc_client_lgr_pending);
return reason_code;
}
@@ -1289,7 +1287,6 @@ static int smc_connect_rdma(struct smc_sock *smc,
if (reason_code)
goto connect_abort;
}
- mutex_unlock(&smc_client_lgr_pending);
smc_copy_sock_settings_to_clc(smc);
smc->connect_nonblock = 0;
@@ -1299,7 +1296,6 @@ static int smc_connect_rdma(struct smc_sock *smc,
return 0;
connect_abort:
smc_conn_abort(smc, ini->first_contact_local);
- mutex_unlock(&smc_client_lgr_pending);
smc->connect_nonblock = 0;
return reason_code;
@@ -2377,7 +2373,8 @@ static void smc_listen_work(struct work_struct *work)
if (rc)
goto out_decl;
- mutex_lock(&smc_server_lgr_pending);
+ if (ini->is_smcd)
+ mutex_lock(&smc_server_lgr_pending);
smc_close_init(new_smc);
smc_rx_init(new_smc);
smc_tx_init(new_smc);
@@ -2415,7 +2412,6 @@ static void smc_listen_work(struct work_struct *work)
ini->first_contact_local, ini);
if (rc)
goto out_unlock;
- mutex_unlock(&smc_server_lgr_pending);
}
smc_conn_save_peer_info(new_smc, cclc);
smc_listen_out_connected(new_smc);
@@ -2423,7 +2419,8 @@ static void smc_listen_work(struct work_struct *work)
goto out_free;
out_unlock:
- mutex_unlock(&smc_server_lgr_pending);
+ if (ini->is_smcd)
+ mutex_unlock(&smc_server_lgr_pending);
out_decl:
smc_listen_decline(new_smc, rc, ini ? ini->first_contact_local : 0,
proposal_version);
diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c
index ff49a11..a3338cc 100644
--- a/net/smc/smc_core.c
+++ b/net/smc/smc_core.c
@@ -46,6 +46,10 @@ struct smc_lgr_list smc_lgr_list = { /* established link groups */
.num = 0,
};
+struct smc_lgr_manager smc_lgr_manager = {
+ .lock = __SPIN_LOCK_UNLOCKED(smc_lgr_manager.lock),
+};
+
static atomic_t lgr_cnt = ATOMIC_INIT(0); /* number of existing link groups */
static DECLARE_WAIT_QUEUE_HEAD(lgrs_deleted);
@@ -55,6 +59,282 @@ static void smc_buf_free(struct smc_link_group *lgr, bool is_rmb,
static void smc_link_down_work(struct work_struct *work);
+/* SMC-R lnk cluster compare func
+ * All lnks that meet the description conditions of this function
+ * are logically aggregated, called lnk cluster.
+ * For the server side, lnk cluster is used to determine whether
+ * a new group needs to be created when processing new imcoming connections.
+ * For the client side, lnk cluster is used to determine whether
+ * to wait for link ready (in other words, first contact ready).
+ */
+static int smcr_lnk_cluster_cmpfn(struct rhashtable_compare_arg *arg, const void *obj)
+{
+ const struct smc_lnk_cluster_compare_arg *key = arg->key;
+ const struct smc_lnk_cluster *lnkc = obj;
+
+ if (memcmp(key->peer_systemid, lnkc->peer_systemid, SMC_SYSTEMID_LEN))
+ return 1;
+
+ if (memcmp(key->peer_gid, lnkc->peer_gid, SMC_GID_SIZE))
+ return 1;
+
+ if ((key->role == SMC_SERV || key->clcqpn == lnkc->clcqpn) &&
+ (key->smcr_version == SMC_V2 ||
+ !memcmp(key->peer_mac, lnkc->peer_mac, ETH_ALEN)))
+ return 0;
+
+ return 1;
+}
+
+/* SMC-R lnk cluster hash func */
+static u32 smcr_lnk_cluster_hashfn(const void *data, u32 len, u32 seed)
+{
+ const struct smc_lnk_cluster *lnkc = data;
+
+ return jhash2((u32 *)lnkc->peer_systemid, SMC_SYSTEMID_LEN / sizeof(u32), seed)
+ + (lnkc->role == SMC_SERV) ? 0 : lnkc->clcqpn;
+}
+
+/* SMC-R lnk cluster compare arg hash func */
+static u32 smcr_lnk_cluster_compare_arg_hashfn(const void *data, u32 len, u32 seed)
+{
+ const struct smc_lnk_cluster_compare_arg *key = data;
+
+ return jhash2((u32 *)key->peer_systemid, SMC_SYSTEMID_LEN / sizeof(u32), seed)
+ + (key->role == SMC_SERV) ? 0 : key->clcqpn;
+}
+
+static const struct rhashtable_params smcr_lnk_cluster_rhl_params = {
+ .head_offset = offsetof(struct smc_lnk_cluster, rnode),
+ .key_len = sizeof(struct smc_lnk_cluster_compare_arg),
+ .obj_cmpfn = smcr_lnk_cluster_cmpfn,
+ .obj_hashfn = smcr_lnk_cluster_hashfn,
+ .hashfn = smcr_lnk_cluster_compare_arg_hashfn,
+ .automatic_shrinking = true,
+};
+
+/* hold a reference for smc_lnk_cluster */
+static inline void smc_lnk_cluster_hold(struct smc_lnk_cluster *lnkc)
+{
+ if (likely(lnkc))
+ refcount_inc(&lnkc->ref);
+}
+
+/* release a reference for smc_lnk_cluster */
+static inline void smc_lnk_cluster_put(struct smc_lnk_cluster *lnkc)
+{
+ bool do_free = false;
+
+ if (!lnkc)
+ return;
+
+ if (refcount_dec_not_one(&lnkc->ref))
+ return;
+
+ spin_lock_bh(&smc_lgr_manager.lock);
+ /* last ref */
+ if (refcount_dec_and_test(&lnkc->ref)) {
+ do_free = true;
+ rhashtable_remove_fast(&smc_lgr_manager.lnk_cluster_maps, &lnkc->rnode,
+ smcr_lnk_cluster_rhl_params);
+ }
+ spin_unlock_bh(&smc_lgr_manager.lock);
+ if (do_free)
+ kfree(lnkc);
+}
+
+/* Get or create smc_lnk_cluster by key
+ * This function will hold a reference of returned smc_lnk_cluster
+ * or create a new smc_lnk_cluster with the reference initialized to 1。
+ * caller MUST call smc_lnk_cluster_put after this.
+ */
+static inline struct smc_lnk_cluster *
+smcr_lnk_get_or_create_cluster(struct smc_lnk_cluster_compare_arg *key)
+{
+ struct smc_lnk_cluster *lnkc, *tmp_lnkc;
+ bool busy_retry;
+ int err;
+
+ /* serving a hardware or software interrupt, or preemption is disabled */
+ busy_retry = !in_interrupt();
+
+ spin_lock_bh(&smc_lgr_manager.lock);
+ lnkc = rhashtable_lookup_fast(&smc_lgr_manager.lnk_cluster_maps, key,
+ smcr_lnk_cluster_rhl_params);
+ if (!lnkc) {
+ lnkc = kzalloc(sizeof(*lnkc), GFP_ATOMIC);
+ if (unlikely(!lnkc))
+ goto fail;
+
+ /* init cluster */
+ spin_lock_init(&lnkc->lock);
+ lnkc->role = key->role;
+ if (key->role == SMC_CLNT)
+ lnkc->clcqpn = key->clcqpn;
+ init_waitqueue_head(&lnkc->first_contact_waitqueue);
+ memcpy(lnkc->peer_systemid, key->peer_systemid, SMC_SYSTEMID_LEN);
+ memcpy(lnkc->peer_gid, key->peer_gid, SMC_GID_SIZE);
+ memcpy(lnkc->peer_mac, key->peer_mac, ETH_ALEN);
+ refcount_set(&lnkc->ref, 1);
+
+ do {
+ err = rhashtable_insert_fast(&smc_lgr_manager.lnk_cluster_maps,
+ &lnkc->rnode, smcr_lnk_cluster_rhl_params);
+
+ /* success or fatal error */
+ if (err != -EBUSY)
+ break;
+
+ /* impossible in fact right now */
+ if (unlikely(!busy_retry)) {
+ pr_warn_ratelimited("smc: create lnk cluster in softirq\n");
+ break;
+ }
+
+ spin_unlock_bh(&smc_lgr_manager.lock);
+ /* yeild */
+ cond_resched();
+ spin_lock_bh(&smc_lgr_manager.lock);
+
+ /* after spin_unlock_bh(), lnk_cluster_maps may be changed */
+ tmp_lnkc = rhashtable_lookup_fast(&smc_lgr_manager.lnk_cluster_maps, key,
+ smcr_lnk_cluster_rhl_params);
+
+ if (unlikely(tmp_lnkc)) {
+ pr_warn_ratelimited("smc: create cluster failed dues to duplicat key");
+ kfree(lnkc);
+ lnkc = NULL;
+ goto fail;
+ }
+ } while (1);
+
+ if (unlikely(err)) {
+ pr_warn_ratelimited("smc: rhashtable_insert_fast failed (%d)", err);
+ kfree(lnkc);
+ lnkc = NULL;
+ }
+ } else {
+ smc_lnk_cluster_hold(lnkc);
+ }
+fail:
+ spin_unlock_bh(&smc_lgr_manager.lock);
+ return lnkc;
+}
+
+/* Get or create a smc_lnk_cluster by lnk
+ * caller MUST call smc_lnk_cluster_put after this.
+ */
+static inline struct smc_lnk_cluster *smcr_lnk_get_cluster(struct smc_link *lnk)
+{
+ struct smc_lnk_cluster_compare_arg key;
+ struct smc_link_group *lgr;
+
+ lgr = lnk->lgr;
+ if (!lgr || lgr->is_smcd)
+ return NULL;
+
+ key.smcr_version = lgr->smc_version;
+ key.peer_systemid = lgr->peer_systemid;
+ key.peer_gid = lnk->peer_gid;
+ key.peer_mac = lnk->peer_mac;
+ key.role = lgr->role;
+ if (key.role == SMC_CLNT)
+ key.clcqpn = lnk->peer_qpn;
+
+ return smcr_lnk_get_or_create_cluster(&key);
+}
+
+/* Get or create a smc_lnk_cluster by ini
+ * caller MUST call smc_lnk_cluster_put after this.
+ */
+static inline struct smc_lnk_cluster *
+smcr_lnk_get_cluster_by_ini(struct smc_init_info *ini, int role)
+{
+ struct smc_lnk_cluster_compare_arg key;
+
+ if (ini->is_smcd)
+ return NULL;
+
+ key.smcr_version = ini->smcr_version;
+ key.peer_systemid = ini->peer_systemid;
+ key.peer_gid = ini->peer_gid;
+ key.peer_mac = ini->peer_mac;
+ key.role = role;
+ if (role == SMC_CLNT)
+ key.clcqpn = ini->ib_clcqpn;
+
+ return smcr_lnk_get_or_create_cluster(&key);
+}
+
+/* callback when smc link state change */
+void smcr_lnk_cluster_on_lnk_state(struct smc_link *lnk)
+{
+ struct smc_lnk_cluster *lnkc;
+ int nr = 0;
+
+ /* barrier for lnk->state */
+ smp_mb();
+
+ /* only first link can made connections block on
+ * first_contact_waitqueue
+ */
+ if (lnk->link_idx != SMC_SINGLE_LINK)
+ return;
+
+ /* state already seen */
+ if (lnk->state_record & SMC_LNK_STATE_BIT(lnk->state))
+ return;
+
+ lnkc = smcr_lnk_get_cluster(lnk);
+
+ if (unlikely(!lnkc))
+ return;
+
+ spin_lock_bh(&lnkc->lock);
+
+ /* all lnk state change should be
+ * 1. SMC_LNK_UNUSED -> SMC_LNK_TEAR_DWON (link init failed)
+ * 2. SMC_LNK_UNUSED -> SMC_LNK_ACTIVATING -> SMC_LNK_TEAR_DWON
+ * 3. SMC_LNK_UNUSED -> SMC_LNK_ACTIVATING -> SMC_LNK_INACTIVE -> SMC_LNK_TEAR_DWON
+ * 4. SMC_LNK_UNUSED -> SMC_LNK_ACTIVATING -> SMC_LNK_INACTIVE -> SMC_LNK_TEAR_DWON
+ * 5. SMC_LNK_UNUSED -> SMC_LNK_ATIVATING -> SMC_LNK_ACTIVE ->SMC_LNK_INACTIVE
+ * -> SMC_LNK_TEAR_DWON
+ */
+ switch (lnk->state) {
+ case SMC_LNK_ACTIVATING:
+ /* It's safe to hold a reference without lock
+ * dues to the smcr_lnk_get_cluster already hold one
+ */
+ smc_lnk_cluster_hold(lnkc);
+ break;
+ case SMC_LNK_TEAR_DWON:
+ if (lnk->state_record & SMC_LNK_STATE_BIT(SMC_LNK_ACTIVATING))
+ /* smc_lnk_cluster_hold in SMC_LNK_ACTIVATING */
+ smc_lnk_cluster_put(lnkc);
+ fallthrough;
+ case SMC_LNK_ACTIVE:
+ case SMC_LNK_INACTIVE:
+ if (!(lnk->state_record &
+ (SMC_LNK_STATE_BIT(SMC_LNK_ACTIVE)
+ | SMC_LNK_STATE_BIT(SMC_LNK_INACTIVE)))) {
+ lnkc->pending_capability -= (SMC_RMBS_PER_LGR_MAX - 1);
+ /* TODO: wakeup just one to perfrom first contact
+ * if record state has no SMC_LNK_ACTIVE
+ */
+ nr = SMC_RMBS_PER_LGR_MAX - 1;
+ }
+ break;
+ case SMC_LNK_UNUSED:
+ pr_warn_ratelimited("net/smc: invalid lnk state. ");
+ break;
+ }
+ SMC_LNK_STATE_RECORD(lnk, lnk->state);
+ spin_unlock_bh(&lnkc->lock);
+ if (nr)
+ wake_up_nr(&lnkc->first_contact_waitqueue, nr);
+ smc_lnk_cluster_put(lnkc); /* smc_lnk_cluster_hold in smcr_lnk_get_cluster */
+}
+
/* return head of link group list and its lock for a given link group */
static inline struct list_head *smc_lgr_list_head(struct smc_link_group *lgr,
spinlock_t **lgr_lock)
@@ -651,8 +931,10 @@ static void smcr_lgr_link_deactivate_all(struct smc_link_group *lgr)
for (i = 0; i < SMC_LINKS_PER_LGR_MAX; i++) {
struct smc_link *lnk = &lgr->lnk[i];
- if (smc_link_sendable(lnk))
+ if (smc_link_sendable(lnk)) {
lnk->state = SMC_LNK_INACTIVE;
+ smcr_lnk_cluster_on_lnk_state(lnk);
+ }
}
wake_up_all(&lgr->llc_msg_waiter);
wake_up_all(&lgr->llc_flow_waiter);
@@ -762,6 +1044,9 @@ int smcr_link_init(struct smc_link_group *lgr, struct smc_link *lnk,
atomic_set(&lnk->conn_cnt, 0);
smc_llc_link_set_uid(lnk);
INIT_WORK(&lnk->link_down_wrk, smc_link_down_work);
+ lnk->peer_qpn = ini->ib_clcqpn;
+ memcpy(lnk->peer_gid, ini->peer_gid, SMC_GID_SIZE);
+ memcpy(lnk->peer_mac, ini->peer_mac, sizeof(lnk->peer_mac));
if (!lnk->smcibdev->initialized) {
rc = (int)smc_ib_setup_per_ibdev(lnk->smcibdev);
if (rc)
@@ -792,6 +1077,7 @@ int smcr_link_init(struct smc_link_group *lgr, struct smc_link *lnk,
if (rc)
goto destroy_qp;
lnk->state = SMC_LNK_ACTIVATING;
+ smcr_lnk_cluster_on_lnk_state(lnk);
return 0;
destroy_qp:
@@ -806,6 +1092,8 @@ int smcr_link_init(struct smc_link_group *lgr, struct smc_link *lnk,
smc_ibdev_cnt_dec(lnk);
put_device(&lnk->smcibdev->ibdev->dev);
smcibdev = lnk->smcibdev;
+ lnk->state = SMC_LNK_TEAR_DWON;
+ smcr_lnk_cluster_on_lnk_state(lnk);
memset(lnk, 0, sizeof(struct smc_link));
lnk->state = SMC_LNK_UNUSED;
if (!atomic_dec_return(&smcibdev->lnk_cnt))
@@ -1263,6 +1551,8 @@ void smcr_link_clear(struct smc_link *lnk, bool log)
if (!lnk->lgr || lnk->clearing ||
lnk->state == SMC_LNK_UNUSED)
return;
+ lnk->state = SMC_LNK_TEAR_DWON;
+ smcr_lnk_cluster_on_lnk_state(lnk);
lnk->clearing = 1;
lnk->peer_qpn = 0;
smc_llc_link_clear(lnk, log);
@@ -1712,6 +2002,7 @@ void smcr_link_down_cond(struct smc_link *lnk)
{
if (smc_link_downing(&lnk->state)) {
trace_smcr_link_down(lnk, __builtin_return_address(0));
+ smcr_lnk_cluster_on_lnk_state(lnk);
smcr_link_down(lnk);
}
}
@@ -1721,6 +2012,7 @@ void smcr_link_down_cond_sched(struct smc_link *lnk)
{
if (smc_link_downing(&lnk->state)) {
trace_smcr_link_down(lnk, __builtin_return_address(0));
+ smcr_lnk_cluster_on_lnk_state(lnk);
schedule_work(&lnk->link_down_wrk);
}
}
@@ -1850,11 +2142,13 @@ int smc_conn_create(struct smc_sock *smc, struct smc_init_info *ini)
{
struct smc_connection *conn = &smc->conn;
struct net *net = sock_net(&smc->sk);
+ DECLARE_WAITQUEUE(wait, current);
+ struct smc_lnk_cluster *lnkc = NULL;
struct list_head *lgr_list;
struct smc_link_group *lgr;
enum smc_lgr_role role;
spinlock_t *lgr_lock;
- int rc = 0;
+ int rc = 0, timeo = CLC_WAIT_TIME;
lgr_list = ini->is_smcd ? &ini->ism_dev[ini->ism_selected]->lgr_list :
&smc_lgr_list.list;
@@ -1862,12 +2156,26 @@ int smc_conn_create(struct smc_sock *smc, struct smc_init_info *ini)
&smc_lgr_list.lock;
ini->first_contact_local = 1;
role = smc->listen_smc ? SMC_SERV : SMC_CLNT;
- if (role == SMC_CLNT && ini->first_contact_peer)
+
+ if (!ini->is_smcd) {
+ lnkc = smcr_lnk_get_cluster_by_ini(ini, role);
+ if (unlikely(!lnkc))
+ return SMC_CLC_DECL_INTERR;
+ }
+
+ if (role == SMC_CLNT && ini->first_contact_peer) {
+ /* first_contact */
+ spin_lock_bh(&lnkc->lock);
+ lnkc->pending_capability += (SMC_RMBS_PER_LGR_MAX - 1);
+ spin_unlock_bh(&lnkc->lock);
/* create new link group as well */
goto create;
+ }
/* determine if an existing link group can be reused */
spin_lock_bh(lgr_lock);
+ spin_lock(&lnkc->lock);
+again:
list_for_each_entry(lgr, lgr_list, list) {
write_lock_bh(&lgr->conns_lock);
if ((ini->is_smcd ?
@@ -1894,9 +2202,33 @@ int smc_conn_create(struct smc_sock *smc, struct smc_init_info *ini)
}
write_unlock_bh(&lgr->conns_lock);
}
+ if (lnkc && ini->first_contact_local) {
+ if (lnkc->pending_capability > lnkc->conns_pending) {
+ lnkc->conns_pending++;
+ add_wait_queue(&lnkc->first_contact_waitqueue, &wait);
+ spin_unlock(&lnkc->lock);
+ spin_unlock_bh(lgr_lock);
+ set_current_state(TASK_INTERRUPTIBLE);
+ /* need to wait at least once first contact done */
+ timeo = schedule_timeout(timeo);
+ set_current_state(TASK_RUNNING);
+ remove_wait_queue(&lnkc->first_contact_waitqueue, &wait);
+ spin_lock_bh(lgr_lock);
+ spin_lock(&lnkc->lock);
+
+ lnkc->conns_pending--;
+ if (timeo)
+ goto again;
+ }
+ if (role == SMC_SERV) {
+ /* first_contact */
+ lnkc->pending_capability += (SMC_RMBS_PER_LGR_MAX - 1);
+ }
+ }
+ spin_unlock(&lnkc->lock);
spin_unlock_bh(lgr_lock);
if (rc)
- return rc;
+ goto out;
if (role == SMC_CLNT && !ini->first_contact_peer &&
ini->first_contact_local) {
@@ -1904,7 +2236,8 @@ int smc_conn_create(struct smc_sock *smc, struct smc_init_info *ini)
* a new one
* send out_of_sync decline, reason synchr. error
*/
- return SMC_CLC_DECL_SYNCERR;
+ rc = SMC_CLC_DECL_SYNCERR;
+ goto out;
}
create:
@@ -1941,6 +2274,8 @@ int smc_conn_create(struct smc_sock *smc, struct smc_init_info *ini)
#endif
out:
+ /* smc_lnk_cluster_hold in smcr_lnk_get_or_create_cluster */
+ smc_lnk_cluster_put(lnkc);
return rc;
}
@@ -2599,12 +2934,23 @@ static int smc_core_reboot_event(struct notifier_block *this,
int __init smc_core_init(void)
{
+ /* init smc lnk cluster maps */
+ rhashtable_init(&smc_lgr_manager.lnk_cluster_maps, &smcr_lnk_cluster_rhl_params);
return register_reboot_notifier(&smc_reboot_notifier);
}
+static void smc_lnk_cluster_free_cb(void *ptr, void *arg)
+{
+ pr_warn("smc: smc lnk cluster refcnt leak.\n");
+ kfree(ptr);
+}
+
/* Called (from smc_exit) when module is removed */
void smc_core_exit(void)
{
unregister_reboot_notifier(&smc_reboot_notifier);
smc_lgrs_shutdown();
+ /* destroy smc lnk cluster maps */
+ rhashtable_free_and_destroy(&smc_lgr_manager.lnk_cluster_maps, smc_lnk_cluster_free_cb,
+ NULL);
}
diff --git a/net/smc/smc_core.h b/net/smc/smc_core.h
index fe8b524..199f533 100644
--- a/net/smc/smc_core.h
+++ b/net/smc/smc_core.h
@@ -15,6 +15,7 @@
#include <linux/atomic.h>
#include <linux/smc.h>
#include <linux/pci.h>
+#include <linux/rhashtable.h>
#include <rdma/ib_verbs.h>
#include <net/genetlink.h>
@@ -29,18 +30,62 @@ struct smc_lgr_list { /* list of link group definition */
u32 num; /* unique link group number */
};
+struct smc_lgr_manager { /* manager for link group */
+ struct rhashtable lnk_cluster_maps; /* maps of smc_lnk_cluster */
+ spinlock_t lock; /* lock for lgr_cm_maps */
+};
+
+struct smc_lnk_cluster {
+ struct rhash_head rnode; /* node for rhashtable */
+ struct wait_queue_head first_contact_waitqueue;
+ /* queue for non first contact to wait
+ * first contact to be established.
+ */
+ spinlock_t lock; /* protection for link group */
+ refcount_t ref; /* refcount for cluster */
+ unsigned long pending_capability;
+ /* maximum pending number of connections that
+ * need wait first contact complete.
+ */
+ unsigned long conns_pending;
+ /* connections that are waiting for first contact
+ * complete
+ */
+ u8 peer_systemid[SMC_SYSTEMID_LEN];
+ u8 peer_mac[ETH_ALEN]; /* = gid[8:10||13:15] */
+ u8 peer_gid[SMC_GID_SIZE]; /* gid of peer*/
+ int clcqpn;
+ int role;
+};
+
enum smc_lgr_role { /* possible roles of a link group */
SMC_CLNT, /* client */
SMC_SERV /* server */
};
+struct smc_lnk_cluster_compare_arg /* key for smc_lnk_cluster */
+{
+ int smcr_version;
+ enum smc_lgr_role role;
+ u8 *peer_systemid;
+ u8 *peer_gid;
+ u8 *peer_mac;
+ int clcqpn;
+};
+
enum smc_link_state { /* possible states of a link */
SMC_LNK_UNUSED, /* link is unused */
SMC_LNK_INACTIVE, /* link is inactive */
SMC_LNK_ACTIVATING, /* link is being activated */
SMC_LNK_ACTIVE, /* link is active */
+ SMC_LNK_TEAR_DWON, /* link is tear down */
};
+#define SMC_LNK_STATE_BIT(state) (1 << (state))
+
+#define SMC_LNK_STATE_RECORD(lnk, state) \
+ ((lnk)->state_record |= SMC_LNK_STATE_BIT(state))
+
#define SMC_WR_BUF_SIZE 48 /* size of work request buffer */
#define SMC_WR_BUF_V2_SIZE 8192 /* size of v2 work request buffer */
@@ -145,6 +190,7 @@ struct smc_link {
int ndev_ifidx; /* network device ifindex */
enum smc_link_state state; /* state of link */
+ int state_record; /* record of previous state */
struct delayed_work llc_testlink_wrk; /* testlink worker */
struct completion llc_testlink_resp; /* wait for rx of testlink */
int llc_testlink_time; /* testlink interval */
@@ -557,6 +603,8 @@ struct smc_link *smc_switch_conns(struct smc_link_group *lgr,
int smcr_nl_get_link(struct sk_buff *skb, struct netlink_callback *cb);
int smcd_nl_get_lgr(struct sk_buff *skb, struct netlink_callback *cb);
+void smcr_lnk_cluster_on_lnk_state(struct smc_link *lnk);
+
static inline struct smc_link_group *smc_get_lgr(struct smc_link *link)
{
return link->lgr;
diff --git a/net/smc/smc_llc.c b/net/smc/smc_llc.c
index 175026a..8134c15 100644
--- a/net/smc/smc_llc.c
+++ b/net/smc/smc_llc.c
@@ -1099,6 +1099,7 @@ int smc_llc_cli_add_link(struct smc_link *link, struct smc_llc_qentry *qentry)
goto out;
out_clear_lnk:
lnk_new->state = SMC_LNK_INACTIVE;
+ smcr_lnk_cluster_on_lnk_state(lnk_new);
smcr_link_clear(lnk_new, false);
out_reject:
smc_llc_cli_add_link_reject(qentry);
@@ -1278,6 +1279,7 @@ static void smc_llc_delete_asym_link(struct smc_link_group *lgr)
return; /* no asymmetric link */
if (!smc_link_downing(&lnk_asym->state))
return;
+ smcr_lnk_cluster_on_lnk_state(lnk_asym);
lnk_new = smc_switch_conns(lgr, lnk_asym, false);
smc_wr_tx_wait_no_pending_sends(lnk_asym);
if (!lnk_new)
@@ -1492,6 +1494,7 @@ int smc_llc_srv_add_link(struct smc_link *link,
out_err:
if (link_new) {
link_new->state = SMC_LNK_INACTIVE;
+ smcr_lnk_cluster_on_lnk_state(link_new);
smcr_link_clear(link_new, false);
}
out:
@@ -1602,8 +1605,10 @@ static void smc_llc_process_cli_delete_link(struct smc_link_group *lgr)
del_llc->reason = 0;
smc_llc_send_message(lnk, &qentry->msg); /* response */
- if (smc_link_downing(&lnk_del->state))
+ if (smc_link_downing(&lnk_del->state)) {
+ smcr_lnk_cluster_on_lnk_state(lnk);
smc_switch_conns(lgr, lnk_del, false);
+ }
smcr_link_clear(lnk_del, true);
active_links = smc_llc_active_link_count(lgr);
@@ -1676,6 +1681,7 @@ static void smc_llc_process_srv_delete_link(struct smc_link_group *lgr)
goto out; /* asymmetric link already deleted */
if (smc_link_downing(&lnk_del->state)) {
+ smcr_lnk_cluster_on_lnk_state(lnk);
if (smc_switch_conns(lgr, lnk_del, false))
smc_wr_tx_wait_no_pending_sends(lnk_del);
}
@@ -2167,6 +2173,7 @@ void smc_llc_link_active(struct smc_link *link)
schedule_delayed_work(&link->llc_testlink_wrk,
link->llc_testlink_time);
}
+ smcr_lnk_cluster_on_lnk_state(link);
}
/* called in worker context */
--
1.8.3.1
^ permalink raw reply related
* [PATCH net-next 03/10] net/smc: allow confirm/delete rkey response deliver multiplex
From: D. Wythe @ 2022-08-10 17:47 UTC (permalink / raw)
To: kgraul, wenjia; +Cc: kuba, davem, netdev, linux-s390, linux-rdma
In-Reply-To: <cover.1660152975.git.alibuda@linux.alibaba.com>
From: "D. Wythe" <alibuda@linux.alibaba.com>
We know that all flows except confirm_rkey and delete_rkey are exclusive,
confirm/delete rkey flows can run concurrently (local and remote).
Although the protocol allows, all flows are actually mutually exclusive
in implementation, dues to waiting for LLC messages is in serial.
This aggravates the time for establishing or destroying a SMC-R
connections, connections have to be queued in smc_llc_wait.
We use rtokens or rkey to correlate a confirm/delete rkey message
with its response.
Before sending a message, we put context with rtokens or rkey into
wait queue. When a response message received, we wakeup the context
which with the same rtokens or rkey against the response message.
Signed-off-by: D. Wythe <alibuda@linux.alibaba.com>
---
net/smc/smc_llc.c | 174 +++++++++++++++++++++++++++++++++++++++++-------------
net/smc/smc_wr.c | 10 ----
net/smc/smc_wr.h | 10 ++++
3 files changed, 143 insertions(+), 51 deletions(-)
diff --git a/net/smc/smc_llc.c b/net/smc/smc_llc.c
index 8134c15..b026df2 100644
--- a/net/smc/smc_llc.c
+++ b/net/smc/smc_llc.c
@@ -200,6 +200,7 @@ struct smc_llc_msg_delete_rkey_v2 { /* type 0x29 */
struct smc_llc_qentry {
struct list_head list;
struct smc_link *link;
+ void *private;
union smc_llc_msg msg;
};
@@ -479,19 +480,17 @@ int smc_llc_send_confirm_link(struct smc_link *link,
return rc;
}
-/* send LLC confirm rkey request */
-static int smc_llc_send_confirm_rkey(struct smc_link *send_link,
- struct smc_buf_desc *rmb_desc)
+/* build LLC confirm rkey request */
+static int smc_llc_build_confirm_rkey_request(struct smc_link *send_link,
+ struct smc_buf_desc *rmb_desc,
+ struct smc_wr_tx_pend_priv **priv)
{
struct smc_llc_msg_confirm_rkey *rkeyllc;
- struct smc_wr_tx_pend_priv *pend;
struct smc_wr_buf *wr_buf;
struct smc_link *link;
int i, rc, rtok_ix;
- if (!smc_wr_tx_link_hold(send_link))
- return -ENOLINK;
- rc = smc_llc_add_pending_send(send_link, &wr_buf, &pend);
+ rc = smc_llc_add_pending_send(send_link, &wr_buf, priv);
if (rc)
goto put_out;
rkeyllc = (struct smc_llc_msg_confirm_rkey *)wr_buf;
@@ -521,25 +520,20 @@ static int smc_llc_send_confirm_rkey(struct smc_link *send_link,
cpu_to_be64((uintptr_t)rmb_desc->cpu_addr) :
cpu_to_be64((u64)sg_dma_address
(rmb_desc->sgt[send_link->link_idx].sgl));
- /* send llc message */
- rc = smc_wr_tx_send(send_link, pend);
put_out:
- smc_wr_tx_link_put(send_link);
return rc;
}
-/* send LLC delete rkey request */
-static int smc_llc_send_delete_rkey(struct smc_link *link,
- struct smc_buf_desc *rmb_desc)
+/* build LLC delete rkey request */
+static int smc_llc_build_delete_rkey_request(struct smc_link *link,
+ struct smc_buf_desc *rmb_desc,
+ struct smc_wr_tx_pend_priv **priv)
{
struct smc_llc_msg_delete_rkey *rkeyllc;
- struct smc_wr_tx_pend_priv *pend;
struct smc_wr_buf *wr_buf;
int rc;
- if (!smc_wr_tx_link_hold(link))
- return -ENOLINK;
- rc = smc_llc_add_pending_send(link, &wr_buf, &pend);
+ rc = smc_llc_add_pending_send(link, &wr_buf, priv);
if (rc)
goto put_out;
rkeyllc = (struct smc_llc_msg_delete_rkey *)wr_buf;
@@ -548,10 +542,7 @@ static int smc_llc_send_delete_rkey(struct smc_link *link,
smc_llc_init_msg_hdr(&rkeyllc->hd, link->lgr, sizeof(*rkeyllc));
rkeyllc->num_rkeys = 1;
rkeyllc->rkey[0] = htonl(rmb_desc->mr[link->link_idx]->rkey);
- /* send llc message */
- rc = smc_wr_tx_send(link, pend);
put_out:
- smc_wr_tx_link_put(link);
return rc;
}
@@ -2023,7 +2014,8 @@ static void smc_llc_rx_response(struct smc_link *link,
case SMC_LLC_DELETE_RKEY:
if (flowtype != SMC_LLC_FLOW_RKEY || flow->qentry)
break; /* drop out-of-flow response */
- goto assign;
+ __wake_up(&link->lgr->llc_msg_waiter, TASK_NORMAL, 1, qentry);
+ goto free;
case SMC_LLC_CONFIRM_RKEY_CONT:
/* not used because max links is 3 */
break;
@@ -2032,6 +2024,7 @@ static void smc_llc_rx_response(struct smc_link *link,
qentry->msg.raw.hdr.common.type);
break;
}
+free:
kfree(qentry);
return;
assign:
@@ -2191,25 +2184,98 @@ void smc_llc_link_clear(struct smc_link *link, bool log)
cancel_delayed_work_sync(&link->llc_testlink_wrk);
}
+static int smc_llc_rkey_response_wake_function(struct wait_queue_entry *wq_entry,
+ unsigned int mode, int sync, void *key)
+{
+ struct smc_llc_qentry *except, *incoming;
+ u8 except_llc_type;
+
+ /* not a rkey response */
+ if (!key)
+ return 0;
+
+ except = wq_entry->private;
+ incoming = key;
+
+ except_llc_type = except->msg.raw.hdr.common.llc_type;
+
+ /* except LLC MSG TYPE mismatch */
+ if (except_llc_type != incoming->msg.raw.hdr.common.llc_type)
+ return 0;
+
+ switch (except_llc_type) {
+ case SMC_LLC_CONFIRM_RKEY:
+ if (memcmp(except->msg.confirm_rkey.rtoken, incoming->msg.confirm_rkey.rtoken,
+ sizeof(struct smc_rmb_rtoken) *
+ except->msg.confirm_rkey.rtoken[0].num_rkeys))
+ return 0;
+ break;
+ case SMC_LLC_DELETE_RKEY:
+ if (memcmp(except->msg.delete_rkey.rkey, incoming->msg.delete_rkey.rkey,
+ sizeof(__be32) * except->msg.delete_rkey.num_rkeys))
+ return 0;
+ break;
+ default:
+ panic("invalid except llc msg %d", except_llc_type);
+ return 0;
+ }
+
+ /* match, save hdr */
+ memcpy(&except->msg.raw.hdr, &incoming->msg.raw.hdr, sizeof(except->msg.raw.hdr));
+
+ wq_entry->private = except->private;
+ return woken_wake_function(wq_entry, mode, sync, NULL);
+}
+
/* register a new rtoken at the remote peer (for all links) */
int smc_llc_do_confirm_rkey(struct smc_link *send_link,
struct smc_buf_desc *rmb_desc)
{
+ long timeout = SMC_LLC_WAIT_TIME;
struct smc_link_group *lgr = send_link->lgr;
- struct smc_llc_qentry *qentry = NULL;
- int rc = 0;
+ struct smc_llc_qentry qentry;
+ struct smc_wr_tx_pend *pend;
+ struct smc_wr_tx_pend_priv *priv;
+ DEFINE_WAIT_FUNC(wait, smc_llc_rkey_response_wake_function);
+ int rc = 0, flags;
- rc = smc_llc_send_confirm_rkey(send_link, rmb_desc);
+ if (!smc_wr_tx_link_hold(send_link))
+ return -ENOLINK;
+
+ rc = smc_llc_build_confirm_rkey_request(send_link, rmb_desc, &priv);
if (rc)
goto out;
- /* receive CONFIRM RKEY response from server over RoCE fabric */
- qentry = smc_llc_wait(lgr, send_link, SMC_LLC_WAIT_TIME,
- SMC_LLC_CONFIRM_RKEY);
- if (!qentry || (qentry->msg.raw.hdr.flags & SMC_LLC_FLAG_RKEY_NEG))
+
+ pend = container_of(priv, struct smc_wr_tx_pend, priv);
+ /* make a copy of send msg */
+ memcpy(&qentry.msg.confirm_rkey, send_link->wr_tx_bufs[pend->idx].raw,
+ sizeof(qentry.msg.confirm_rkey));
+
+ qentry.private = wait.private;
+ wait.private = &qentry;
+
+ add_wait_queue(&lgr->llc_msg_waiter, &wait);
+
+ /* send llc message */
+ rc = smc_wr_tx_send(send_link, priv);
+ smc_wr_tx_link_put(send_link);
+ if (rc) {
+ remove_wait_queue(&lgr->llc_msg_waiter, &wait);
+ goto out;
+ }
+
+ while (!signal_pending(current) && timeout) {
+ timeout = wait_woken(&wait, TASK_INTERRUPTIBLE, timeout);
+ if (qentry.msg.raw.hdr.flags & SMC_LLC_FLAG_RESP)
+ break;
+ }
+
+ remove_wait_queue(&lgr->llc_msg_waiter, &wait);
+ flags = qentry.msg.raw.hdr.flags;
+
+ if (!(flags & SMC_LLC_FLAG_RESP) || flags & SMC_LLC_FLAG_RKEY_NEG)
rc = -EFAULT;
out:
- if (qentry)
- smc_llc_flow_qentry_del(&lgr->llc_flow_lcl);
return rc;
}
@@ -2217,26 +2283,52 @@ int smc_llc_do_confirm_rkey(struct smc_link *send_link,
int smc_llc_do_delete_rkey(struct smc_link_group *lgr,
struct smc_buf_desc *rmb_desc)
{
- struct smc_llc_qentry *qentry = NULL;
+ long timeout = SMC_LLC_WAIT_TIME;
+ struct smc_llc_qentry qentry;
+ struct smc_wr_tx_pend *pend;
struct smc_link *send_link;
- int rc = 0;
+ struct smc_wr_tx_pend_priv *priv;
+ DEFINE_WAIT_FUNC(wait, smc_llc_rkey_response_wake_function);
+ int rc = 0, flags;
send_link = smc_llc_usable_link(lgr);
- if (!send_link)
+ if (!send_link || !smc_wr_tx_link_hold(send_link))
return -ENOLINK;
- /* protected by llc_flow control */
- rc = smc_llc_send_delete_rkey(send_link, rmb_desc);
+ rc = smc_llc_build_delete_rkey_request(send_link, rmb_desc, &priv);
if (rc)
goto out;
- /* receive DELETE RKEY response from server over RoCE fabric */
- qentry = smc_llc_wait(lgr, send_link, SMC_LLC_WAIT_TIME,
- SMC_LLC_DELETE_RKEY);
- if (!qentry || (qentry->msg.raw.hdr.flags & SMC_LLC_FLAG_RKEY_NEG))
+
+ pend = container_of(priv, struct smc_wr_tx_pend, priv);
+ /* make a copy of send msg */
+ memcpy(&qentry.msg.delete_link, send_link->wr_tx_bufs[pend->idx].raw,
+ sizeof(qentry.msg.delete_link));
+
+ qentry.private = wait.private;
+ wait.private = &qentry;
+
+ add_wait_queue(&lgr->llc_msg_waiter, &wait);
+
+ /* send llc message */
+ rc = smc_wr_tx_send(send_link, priv);
+ smc_wr_tx_link_put(send_link);
+ if (rc) {
+ remove_wait_queue(&lgr->llc_msg_waiter, &wait);
+ goto out;
+ }
+
+ while (!signal_pending(current) && timeout) {
+ timeout = wait_woken(&wait, TASK_INTERRUPTIBLE, timeout);
+ if (qentry.msg.raw.hdr.flags & SMC_LLC_FLAG_RESP)
+ break;
+ }
+
+ remove_wait_queue(&lgr->llc_msg_waiter, &wait);
+ flags = qentry.msg.raw.hdr.flags;
+
+ if (!(flags & SMC_LLC_FLAG_RESP) || flags & SMC_LLC_FLAG_RKEY_NEG)
rc = -EFAULT;
out:
- if (qentry)
- smc_llc_flow_qentry_del(&lgr->llc_flow_lcl);
return rc;
}
diff --git a/net/smc/smc_wr.c b/net/smc/smc_wr.c
index 26f8f24..52af94f 100644
--- a/net/smc/smc_wr.c
+++ b/net/smc/smc_wr.c
@@ -37,16 +37,6 @@
static DEFINE_HASHTABLE(smc_wr_rx_hash, SMC_WR_RX_HASH_BITS);
static DEFINE_SPINLOCK(smc_wr_rx_hash_lock);
-struct smc_wr_tx_pend { /* control data for a pending send request */
- u64 wr_id; /* work request id sent */
- smc_wr_tx_handler handler;
- enum ib_wc_status wc_status; /* CQE status */
- struct smc_link *link;
- u32 idx;
- struct smc_wr_tx_pend_priv priv;
- u8 compl_requested;
-};
-
/******************************** send queue *********************************/
/*------------------------------- completion --------------------------------*/
diff --git a/net/smc/smc_wr.h b/net/smc/smc_wr.h
index a54e90a..9946ed5 100644
--- a/net/smc/smc_wr.h
+++ b/net/smc/smc_wr.h
@@ -46,6 +46,16 @@ struct smc_wr_rx_handler {
u8 type;
};
+struct smc_wr_tx_pend { /* control data for a pending send request */
+ u64 wr_id; /* work request id sent */
+ smc_wr_tx_handler handler;
+ enum ib_wc_status wc_status; /* CQE status */
+ struct smc_link *link;
+ u32 idx;
+ struct smc_wr_tx_pend_priv priv;
+ u8 compl_requested;
+};
+
/* Only used by RDMA write WRs.
* All other WRs (CDC/LLC) use smc_wr_tx_send handling WR_ID implicitly
*/
--
1.8.3.1
^ permalink raw reply related
* [PATCH net-next 04/10] net/smc: make SMC_LLC_FLOW_RKEY run concurrently
From: D. Wythe @ 2022-08-10 17:47 UTC (permalink / raw)
To: kgraul, wenjia; +Cc: kuba, davem, netdev, linux-s390, linux-rdma
In-Reply-To: <cover.1660152975.git.alibuda@linux.alibaba.com>
From: "D. Wythe" <alibuda@linux.alibaba.com>
Once confirm/delete rkey response can be multiplex delivered,
We can allow parallel execution of start (remote) or
initialization (local) a SMC_LLC_FLOW_RKEY flow.
This patch will count the flows executed in parallel, and only when
the count reaches zero will the current flow type be removed.
Signed-off-by: D. Wythe <alibuda@linux.alibaba.com>
---
net/smc/smc_core.h | 1 +
net/smc/smc_llc.c | 69 +++++++++++++++++++++++++++++++++++++++++-------------
net/smc/smc_llc.h | 6 +++++
3 files changed, 60 insertions(+), 16 deletions(-)
diff --git a/net/smc/smc_core.h b/net/smc/smc_core.h
index acc2869..8490676 100644
--- a/net/smc/smc_core.h
+++ b/net/smc/smc_core.h
@@ -286,6 +286,7 @@ enum smc_llc_flowtype {
struct smc_llc_flow {
enum smc_llc_flowtype type;
struct smc_llc_qentry *qentry;
+ refcount_t parallel_refcnt;
};
struct smc_link_group {
diff --git a/net/smc/smc_llc.c b/net/smc/smc_llc.c
index b026df2..965a3cc 100644
--- a/net/smc/smc_llc.c
+++ b/net/smc/smc_llc.c
@@ -231,10 +231,18 @@ static inline void smc_llc_flow_qentry_set(struct smc_llc_flow *flow,
flow->qentry = qentry;
}
-static void smc_llc_flow_parallel(struct smc_link_group *lgr, u8 flow_type,
+static void smc_llc_flow_parallel(struct smc_link_group *lgr, struct smc_llc_flow *flow,
struct smc_llc_qentry *qentry)
{
u8 msg_type = qentry->msg.raw.hdr.common.llc_type;
+ u8 flow_type = flow->type;
+
+ /* SMC_LLC_FLOW_RKEY can be parallel */
+ if (flow_type == SMC_LLC_FLOW_RKEY &&
+ (msg_type == SMC_LLC_CONFIRM_RKEY || msg_type == SMC_LLC_DELETE_RKEY)) {
+ refcount_inc(&flow->parallel_refcnt);
+ return;
+ }
if ((msg_type == SMC_LLC_ADD_LINK || msg_type == SMC_LLC_DELETE_LINK) &&
flow_type != msg_type && !lgr->delayed_event) {
@@ -261,7 +269,7 @@ static bool smc_llc_flow_start(struct smc_llc_flow *flow,
spin_lock_bh(&lgr->llc_flow_lock);
if (flow->type) {
/* a flow is already active */
- smc_llc_flow_parallel(lgr, flow->type, qentry);
+ smc_llc_flow_parallel(lgr, flow, qentry);
spin_unlock_bh(&lgr->llc_flow_lock);
return false;
}
@@ -280,6 +288,7 @@ static bool smc_llc_flow_start(struct smc_llc_flow *flow,
flow->type = SMC_LLC_FLOW_NONE;
}
smc_llc_flow_qentry_set(flow, qentry);
+ refcount_set(&flow->parallel_refcnt, 1);
spin_unlock_bh(&lgr->llc_flow_lock);
return true;
}
@@ -289,6 +298,7 @@ int smc_llc_flow_initiate(struct smc_link_group *lgr,
enum smc_llc_flowtype type)
{
enum smc_llc_flowtype allowed_remote = SMC_LLC_FLOW_NONE;
+ bool accept = false;
int rc;
/* all flows except confirm_rkey and delete_rkey are exclusive,
@@ -300,10 +310,39 @@ int smc_llc_flow_initiate(struct smc_link_group *lgr,
if (list_empty(&lgr->list))
return -ENODEV;
spin_lock_bh(&lgr->llc_flow_lock);
- if (lgr->llc_flow_lcl.type == SMC_LLC_FLOW_NONE &&
- (lgr->llc_flow_rmt.type == SMC_LLC_FLOW_NONE ||
- lgr->llc_flow_rmt.type == allowed_remote)) {
- lgr->llc_flow_lcl.type = type;
+
+ /* Flow is initialized only if the following conditions are met:
+ * incoming flow local flow remote flow
+ * exclusive NONE NONE
+ * SMC_LLC_FLOW_RKEY SMC_LLC_FLOW_RKEY SMC_LLC_FLOW_RKEY
+ * SMC_LLC_FLOW_RKEY NONE SMC_LLC_FLOW_RKEY
+ * SMC_LLC_FLOW_RKEY SMC_LLC_FLOW_RKEY NONE
+ */
+ switch (type) {
+ case SMC_LLC_FLOW_RKEY:
+ if (!SMC_IS_PARALLEL_FLOW(lgr->llc_flow_lcl.type))
+ break;
+ if (!SMC_IS_PARALLEL_FLOW(lgr->llc_flow_rmt.type))
+ break;
+ /* accepted */
+ accept = true;
+ break;
+ default:
+ if (!SMC_IS_NONE_FLOW(lgr->llc_flow_lcl.type))
+ break;
+ if (!SMC_IS_NONE_FLOW(lgr->llc_flow_rmt.type))
+ break;
+ /* accepted */
+ accept = true;
+ break;
+ }
+ if (accept) {
+ if (SMC_IS_NONE_FLOW(lgr->llc_flow_lcl.type)) {
+ lgr->llc_flow_lcl.type = type;
+ refcount_set(&lgr->llc_flow_lcl.parallel_refcnt, 1);
+ } else {
+ refcount_inc(&lgr->llc_flow_lcl.parallel_refcnt);
+ }
spin_unlock_bh(&lgr->llc_flow_lock);
return 0;
}
@@ -322,6 +361,10 @@ int smc_llc_flow_initiate(struct smc_link_group *lgr,
void smc_llc_flow_stop(struct smc_link_group *lgr, struct smc_llc_flow *flow)
{
spin_lock_bh(&lgr->llc_flow_lock);
+ if (!refcount_dec_and_test(&flow->parallel_refcnt)) {
+ spin_unlock_bh(&lgr->llc_flow_lock);
+ return;
+ }
memset(flow, 0, sizeof(*flow));
flow->type = SMC_LLC_FLOW_NONE;
spin_unlock_bh(&lgr->llc_flow_lock);
@@ -1729,16 +1772,14 @@ static void smc_llc_delete_link_work(struct work_struct *work)
}
/* process a confirm_rkey request from peer, remote flow */
-static void smc_llc_rmt_conf_rkey(struct smc_link_group *lgr)
+static void smc_llc_rmt_conf_rkey(struct smc_link_group *lgr, struct smc_llc_qentry *qentry)
{
struct smc_llc_msg_confirm_rkey *llc;
- struct smc_llc_qentry *qentry;
struct smc_link *link;
int num_entries;
int rk_idx;
int i;
- qentry = lgr->llc_flow_rmt.qentry;
llc = &qentry->msg.confirm_rkey;
link = qentry->link;
@@ -1765,19 +1806,16 @@ static void smc_llc_rmt_conf_rkey(struct smc_link_group *lgr)
llc->hd.flags |= SMC_LLC_FLAG_RESP;
smc_llc_init_msg_hdr(&llc->hd, link->lgr, sizeof(*llc));
smc_llc_send_message(link, &qentry->msg);
- smc_llc_flow_qentry_del(&lgr->llc_flow_rmt);
}
/* process a delete_rkey request from peer, remote flow */
-static void smc_llc_rmt_delete_rkey(struct smc_link_group *lgr)
+static void smc_llc_rmt_delete_rkey(struct smc_link_group *lgr, struct smc_llc_qentry *qentry)
{
struct smc_llc_msg_delete_rkey *llc;
- struct smc_llc_qentry *qentry;
struct smc_link *link;
u8 err_mask = 0;
int i, max;
- qentry = lgr->llc_flow_rmt.qentry;
llc = &qentry->msg.delete_rkey;
link = qentry->link;
@@ -1815,7 +1853,6 @@ static void smc_llc_rmt_delete_rkey(struct smc_link_group *lgr)
finish:
llc->hd.flags |= SMC_LLC_FLAG_RESP;
smc_llc_send_message(link, &qentry->msg);
- smc_llc_flow_qentry_del(&lgr->llc_flow_rmt);
}
static void smc_llc_protocol_violation(struct smc_link_group *lgr, u8 type)
@@ -1916,7 +1953,7 @@ static void smc_llc_event_handler(struct smc_llc_qentry *qentry)
/* new request from remote, assign to remote flow */
if (smc_llc_flow_start(&lgr->llc_flow_rmt, qentry)) {
/* process here, does not wait for more llc msgs */
- smc_llc_rmt_conf_rkey(lgr);
+ smc_llc_rmt_conf_rkey(lgr, qentry);
smc_llc_flow_stop(lgr, &lgr->llc_flow_rmt);
}
return;
@@ -1929,7 +1966,7 @@ static void smc_llc_event_handler(struct smc_llc_qentry *qentry)
/* new request from remote, assign to remote flow */
if (smc_llc_flow_start(&lgr->llc_flow_rmt, qentry)) {
/* process here, does not wait for more llc msgs */
- smc_llc_rmt_delete_rkey(lgr);
+ smc_llc_rmt_delete_rkey(lgr, qentry);
smc_llc_flow_stop(lgr, &lgr->llc_flow_rmt);
}
return;
diff --git a/net/smc/smc_llc.h b/net/smc/smc_llc.h
index 4404e52..005a81e 100644
--- a/net/smc/smc_llc.h
+++ b/net/smc/smc_llc.h
@@ -48,6 +48,12 @@ enum smc_llc_msg_type {
#define smc_link_downing(state) \
(cmpxchg(state, SMC_LNK_ACTIVE, SMC_LNK_INACTIVE) == SMC_LNK_ACTIVE)
+#define SMC_IS_NONE_FLOW(type) \
+ ((type) == SMC_LLC_FLOW_NONE)
+
+#define SMC_IS_PARALLEL_FLOW(type) \
+ (((type) == SMC_LLC_FLOW_RKEY) || SMC_IS_NONE_FLOW(type))
+
/* LLC DELETE LINK Request Reason Codes */
#define SMC_LLC_DEL_LOST_PATH 0x00010000
#define SMC_LLC_DEL_OP_INIT_TERM 0x00020000
--
1.8.3.1
^ permalink raw reply related
* [PATCH net-next 07/10] net/smc: reduce unnecessary blocking in smcr_lgr_reg_rmbs()
From: D. Wythe @ 2022-08-10 17:47 UTC (permalink / raw)
To: kgraul, wenjia; +Cc: kuba, davem, netdev, linux-s390, linux-rdma
In-Reply-To: <cover.1660152975.git.alibuda@linux.alibaba.com>
From: "D. Wythe" <alibuda@linux.alibaba.com>
Unlike smc_buf_create() and smcr_buf_unuse(), smcr_lgr_reg_rmbs() is
exclusive when assigned rmb_desc was not registered, although it can be
executed in parallel when assigned rmb_desc was registered already
and only performs read semtamics on it. Hence, we can not simply replace
it with read semaphore.
The idea here is that if the assigned rmb_desc was registered already,
use read semaphore to protect the critical section, once the assigned
rmb_desc was not registered, keep using keep write semaphore still
to keep its exclusivity.
Thanks to the reusable features of rmb_desc, which allows us to execute
in parallel in most cases.
Signed-off-by: D. Wythe <alibuda@linux.alibaba.com>
---
net/smc/af_smc.c | 19 +++++++++++++++++--
1 file changed, 17 insertions(+), 2 deletions(-)
diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c
index 51b90e2..39dbf39 100644
--- a/net/smc/af_smc.c
+++ b/net/smc/af_smc.c
@@ -516,10 +516,25 @@ static int smcr_lgr_reg_rmbs(struct smc_link *link,
{
struct smc_link_group *lgr = link->lgr;
int i, rc = 0;
+ bool slow = false;
rc = smc_llc_flow_initiate(lgr, SMC_LLC_FLOW_RKEY);
if (rc)
return rc;
+
+ down_read(&lgr->llc_conf_mutex);
+ for (i = 0; i < SMC_LINKS_PER_LGR_MAX; i++) {
+ if (!smc_link_active(&lgr->lnk[i]))
+ continue;
+ if (!rmb_desc->is_reg_mr[link->link_idx]) {
+ up_read(&lgr->llc_conf_mutex);
+ goto slow_path;
+ }
+ }
+ /* mr register already */
+ goto fast_path;
+slow_path:
+ slow = true;
/* protect against parallel smc_llc_cli_rkey_exchange() and
* parallel smcr_link_reg_buf()
*/
@@ -531,7 +546,7 @@ static int smcr_lgr_reg_rmbs(struct smc_link *link,
if (rc)
goto out;
}
-
+fast_path:
/* exchange confirm_rkey msg with peer */
rc = smc_llc_do_confirm_rkey(link, rmb_desc);
if (rc) {
@@ -540,7 +555,7 @@ static int smcr_lgr_reg_rmbs(struct smc_link *link,
}
rmb_desc->is_conf_rkey = true;
out:
- up_write(&lgr->llc_conf_mutex);
+ slow ? up_write(&lgr->llc_conf_mutex) : up_read(&lgr->llc_conf_mutex);
smc_llc_flow_stop(lgr, &lgr->llc_flow_lcl);
return rc;
}
--
1.8.3.1
^ permalink raw reply related
* [PATCH net-next 05/10] net/smc: llc_conf_mutex refactor, replace it with rw_semaphore
From: D. Wythe @ 2022-08-10 17:47 UTC (permalink / raw)
To: kgraul, wenjia; +Cc: kuba, davem, netdev, linux-s390, linux-rdma
In-Reply-To: <cover.1660152975.git.alibuda@linux.alibaba.com>
From: "D. Wythe" <alibuda@linux.alibaba.com>
llc_conf_mutex was used to protect links and link related configurations
in the same link group, for example, add or delete links. However,
in most cases, the protected critical area has only read semantics and
with no write semantics at all, such as obtaining a usable link or an
available rmb_desc.
This patch do simply code refactoring, replace mutex with rw_semaphore,
replace mutex_lock with down_write and replace mutex_unlock with
up_write.
Theoretically, this replacement is equivalent, but after this patch,
we can distinguish lock granularity according to different semantics
of critical areas.
Signed-off-by: D. Wythe <alibuda@linux.alibaba.com>
---
net/smc/af_smc.c | 8 ++++----
net/smc/smc_core.c | 20 ++++++++++----------
net/smc/smc_core.h | 2 +-
net/smc/smc_llc.c | 18 +++++++++---------
4 files changed, 24 insertions(+), 24 deletions(-)
diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c
index c0842a9..51b90e2 100644
--- a/net/smc/af_smc.c
+++ b/net/smc/af_smc.c
@@ -498,7 +498,7 @@ static int smcr_lgr_reg_sndbufs(struct smc_link *link,
return -EINVAL;
/* protect against parallel smcr_link_reg_buf() */
- mutex_lock(&lgr->llc_conf_mutex);
+ down_write(&lgr->llc_conf_mutex);
for (i = 0; i < SMC_LINKS_PER_LGR_MAX; i++) {
if (!smc_link_active(&lgr->lnk[i]))
continue;
@@ -506,7 +506,7 @@ static int smcr_lgr_reg_sndbufs(struct smc_link *link,
if (rc)
break;
}
- mutex_unlock(&lgr->llc_conf_mutex);
+ up_write(&lgr->llc_conf_mutex);
return rc;
}
@@ -523,7 +523,7 @@ static int smcr_lgr_reg_rmbs(struct smc_link *link,
/* protect against parallel smc_llc_cli_rkey_exchange() and
* parallel smcr_link_reg_buf()
*/
- mutex_lock(&lgr->llc_conf_mutex);
+ down_write(&lgr->llc_conf_mutex);
for (i = 0; i < SMC_LINKS_PER_LGR_MAX; i++) {
if (!smc_link_active(&lgr->lnk[i]))
continue;
@@ -540,7 +540,7 @@ static int smcr_lgr_reg_rmbs(struct smc_link *link,
}
rmb_desc->is_conf_rkey = true;
out:
- mutex_unlock(&lgr->llc_conf_mutex);
+ up_write(&lgr->llc_conf_mutex);
smc_llc_flow_stop(lgr, &lgr->llc_flow_lcl);
return rc;
}
diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c
index 61a3854..fc8deec 100644
--- a/net/smc/smc_core.c
+++ b/net/smc/smc_core.c
@@ -1388,10 +1388,10 @@ static void smcr_buf_unuse(struct smc_buf_desc *buf_desc, bool is_rmb,
rc = smc_llc_flow_initiate(lgr, SMC_LLC_FLOW_RKEY);
if (!rc) {
/* protect against smc_llc_cli_rkey_exchange() */
- mutex_lock(&lgr->llc_conf_mutex);
+ down_write(&lgr->llc_conf_mutex);
smc_llc_do_delete_rkey(lgr, buf_desc);
buf_desc->is_conf_rkey = false;
- mutex_unlock(&lgr->llc_conf_mutex);
+ up_write(&lgr->llc_conf_mutex);
smc_llc_flow_stop(lgr, &lgr->llc_flow_lcl);
}
}
@@ -1661,12 +1661,12 @@ static void smc_lgr_free(struct smc_link_group *lgr)
int i;
if (!lgr->is_smcd) {
- mutex_lock(&lgr->llc_conf_mutex);
+ down_write(&lgr->llc_conf_mutex);
for (i = 0; i < SMC_LINKS_PER_LGR_MAX; i++) {
if (lgr->lnk[i].state != SMC_LNK_UNUSED)
smcr_link_clear(&lgr->lnk[i], false);
}
- mutex_unlock(&lgr->llc_conf_mutex);
+ up_write(&lgr->llc_conf_mutex);
smc_llc_lgr_clear(lgr);
}
@@ -1980,12 +1980,12 @@ static void smcr_link_down(struct smc_link *lnk)
} else {
if (lgr->llc_flow_lcl.type != SMC_LLC_FLOW_NONE) {
/* another llc task is ongoing */
- mutex_unlock(&lgr->llc_conf_mutex);
+ up_write(&lgr->llc_conf_mutex);
wait_event_timeout(lgr->llc_flow_waiter,
(list_empty(&lgr->list) ||
lgr->llc_flow_lcl.type == SMC_LLC_FLOW_NONE),
SMC_LLC_WAIT_TIME);
- mutex_lock(&lgr->llc_conf_mutex);
+ down_write(&lgr->llc_conf_mutex);
}
if (!list_empty(&lgr->list)) {
smc_llc_send_delete_link(to_lnk, del_link_id,
@@ -2047,9 +2047,9 @@ static void smc_link_down_work(struct work_struct *work)
if (list_empty(&lgr->list))
return;
wake_up_all(&lgr->llc_msg_waiter);
- mutex_lock(&lgr->llc_conf_mutex);
+ down_write(&lgr->llc_conf_mutex);
smcr_link_down(link);
- mutex_unlock(&lgr->llc_conf_mutex);
+ up_write(&lgr->llc_conf_mutex);
}
static int smc_vlan_by_tcpsk_walk(struct net_device *lower_dev,
@@ -2581,7 +2581,7 @@ static int smcr_buf_map_usable_links(struct smc_link_group *lgr,
int i, rc = 0;
/* protect against parallel link reconfiguration */
- mutex_lock(&lgr->llc_conf_mutex);
+ down_write(&lgr->llc_conf_mutex);
for (i = 0; i < SMC_LINKS_PER_LGR_MAX; i++) {
struct smc_link *lnk = &lgr->lnk[i];
@@ -2593,7 +2593,7 @@ static int smcr_buf_map_usable_links(struct smc_link_group *lgr,
}
}
out:
- mutex_unlock(&lgr->llc_conf_mutex);
+ up_write(&lgr->llc_conf_mutex);
return rc;
}
diff --git a/net/smc/smc_core.h b/net/smc/smc_core.h
index 8490676..559d330 100644
--- a/net/smc/smc_core.h
+++ b/net/smc/smc_core.h
@@ -346,7 +346,7 @@ struct smc_link_group {
/* queue for llc events */
spinlock_t llc_event_q_lock;
/* protects llc_event_q */
- struct mutex llc_conf_mutex;
+ struct rw_semaphore llc_conf_mutex;
/* protects lgr reconfig. */
struct work_struct llc_add_link_work;
struct work_struct llc_del_link_work;
diff --git a/net/smc/smc_llc.c b/net/smc/smc_llc.c
index 965a3cc..d744937 100644
--- a/net/smc/smc_llc.c
+++ b/net/smc/smc_llc.c
@@ -1237,12 +1237,12 @@ static void smc_llc_process_cli_add_link(struct smc_link_group *lgr)
qentry = smc_llc_flow_qentry_clr(&lgr->llc_flow_lcl);
- mutex_lock(&lgr->llc_conf_mutex);
+ down_write(&lgr->llc_conf_mutex);
if (smc_llc_is_local_add_link(&qentry->msg))
smc_llc_cli_add_link_invite(qentry->link, qentry);
else
smc_llc_cli_add_link(qentry->link, qentry);
- mutex_unlock(&lgr->llc_conf_mutex);
+ up_write(&lgr->llc_conf_mutex);
}
static int smc_llc_active_link_count(struct smc_link_group *lgr)
@@ -1546,13 +1546,13 @@ static void smc_llc_process_srv_add_link(struct smc_link_group *lgr)
qentry = smc_llc_flow_qentry_clr(&lgr->llc_flow_lcl);
- mutex_lock(&lgr->llc_conf_mutex);
+ down_write(&lgr->llc_conf_mutex);
rc = smc_llc_srv_add_link(link, qentry);
if (!rc && lgr->type == SMC_LGR_SYMMETRIC) {
/* delete any asymmetric link */
smc_llc_delete_asym_link(lgr);
}
- mutex_unlock(&lgr->llc_conf_mutex);
+ up_write(&lgr->llc_conf_mutex);
kfree(qentry);
}
@@ -1619,7 +1619,7 @@ static void smc_llc_process_cli_delete_link(struct smc_link_group *lgr)
smc_lgr_terminate_sched(lgr);
goto out;
}
- mutex_lock(&lgr->llc_conf_mutex);
+ down_write(&lgr->llc_conf_mutex);
/* delete single link */
for (lnk_idx = 0; lnk_idx < SMC_LINKS_PER_LGR_MAX; lnk_idx++) {
if (lgr->lnk[lnk_idx].link_id != del_llc->link_num)
@@ -1655,7 +1655,7 @@ static void smc_llc_process_cli_delete_link(struct smc_link_group *lgr)
smc_lgr_terminate_sched(lgr);
}
out_unlock:
- mutex_unlock(&lgr->llc_conf_mutex);
+ up_write(&lgr->llc_conf_mutex);
out:
kfree(qentry);
}
@@ -1691,7 +1691,7 @@ static void smc_llc_process_srv_delete_link(struct smc_link_group *lgr)
int active_links;
int i;
- mutex_lock(&lgr->llc_conf_mutex);
+ down_write(&lgr->llc_conf_mutex);
qentry = smc_llc_flow_qentry_clr(&lgr->llc_flow_lcl);
lnk = qentry->link;
del_llc = &qentry->msg.delete_link;
@@ -1748,7 +1748,7 @@ static void smc_llc_process_srv_delete_link(struct smc_link_group *lgr)
smc_llc_add_link_local(lnk);
}
out:
- mutex_unlock(&lgr->llc_conf_mutex);
+ up_write(&lgr->llc_conf_mutex);
kfree(qentry);
}
@@ -2162,7 +2162,7 @@ void smc_llc_lgr_init(struct smc_link_group *lgr, struct smc_sock *smc)
spin_lock_init(&lgr->llc_flow_lock);
init_waitqueue_head(&lgr->llc_flow_waiter);
init_waitqueue_head(&lgr->llc_msg_waiter);
- mutex_init(&lgr->llc_conf_mutex);
+ init_rwsem(&lgr->llc_conf_mutex);
lgr->llc_testlink_time = READ_ONCE(net->ipv4.sysctl_tcp_keepalive_time);
}
--
1.8.3.1
^ permalink raw reply related
* [PATCH net-next 06/10] net/smc: use read semaphores to reduce unnecessary blocking in smc_buf_create() & smcr_buf_unuse()
From: D. Wythe @ 2022-08-10 17:47 UTC (permalink / raw)
To: kgraul, wenjia; +Cc: kuba, davem, netdev, linux-s390, linux-rdma
In-Reply-To: <cover.1660152975.git.alibuda@linux.alibaba.com>
From: "D. Wythe" <alibuda@linux.alibaba.com>
Following is part of Off-CPU graph during frequent SMC-R short-lived
processing:
process_one_work (51.19%)
smc_close_passive_work (28.36%)
smcr_buf_unuse (28.34%)
rwsem_down_write_slowpath (28.22%)
smc_listen_work (22.83%)
smc_clc_wait_msg (1.84%)
smc_buf_create (20.45%)
smcr_buf_map_usable_links
rwsem_down_write_slowpath (20.43%)
smcr_lgr_reg_rmbs (0.53%)
rwsem_down_write_slowpath (0.43%)
smc_llc_do_confirm_rkey (0.08%)
We can clearly see that during the connection establishment time,
waiting time of connections is not on IO, but on llc_conf_mutex.
What is more important, the core critical area (smcr_buf_unuse() &
smc_buf_create()) only perfroms read semantics on links, we can
easily replace it with read semaphore.
Signed-off-by: D. Wythe <alibuda@linux.alibaba.com>
---
net/smc/smc_core.c | 8 ++++----
1 file changed, 4 insertions(+), 4 deletions(-)
diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c
index fc8deec..113804d 100644
--- a/net/smc/smc_core.c
+++ b/net/smc/smc_core.c
@@ -1388,10 +1388,10 @@ static void smcr_buf_unuse(struct smc_buf_desc *buf_desc, bool is_rmb,
rc = smc_llc_flow_initiate(lgr, SMC_LLC_FLOW_RKEY);
if (!rc) {
/* protect against smc_llc_cli_rkey_exchange() */
- down_write(&lgr->llc_conf_mutex);
+ down_read(&lgr->llc_conf_mutex);
smc_llc_do_delete_rkey(lgr, buf_desc);
buf_desc->is_conf_rkey = false;
- up_write(&lgr->llc_conf_mutex);
+ up_read(&lgr->llc_conf_mutex);
smc_llc_flow_stop(lgr, &lgr->llc_flow_lcl);
}
}
@@ -2581,7 +2581,7 @@ static int smcr_buf_map_usable_links(struct smc_link_group *lgr,
int i, rc = 0;
/* protect against parallel link reconfiguration */
- down_write(&lgr->llc_conf_mutex);
+ down_read(&lgr->llc_conf_mutex);
for (i = 0; i < SMC_LINKS_PER_LGR_MAX; i++) {
struct smc_link *lnk = &lgr->lnk[i];
@@ -2593,7 +2593,7 @@ static int smcr_buf_map_usable_links(struct smc_link_group *lgr,
}
}
out:
- up_write(&lgr->llc_conf_mutex);
+ up_read(&lgr->llc_conf_mutex);
return rc;
}
--
1.8.3.1
^ permalink raw reply related
* [PATCH net-next 09/10] net/smc: fix potential panic dues to unprotected smc_llc_srv_add_link()
From: D. Wythe @ 2022-08-10 17:47 UTC (permalink / raw)
To: kgraul, wenjia; +Cc: kuba, davem, netdev, linux-s390, linux-rdma
In-Reply-To: <cover.1660152975.git.alibuda@linux.alibaba.com>
From: "D. Wythe" <alibuda@linux.alibaba.com>
After we optimize the parallel capability of SMC-R connection
establishment, there is a certain chance to trigger the
following panic:
PID: 5900 TASK: ffff88c1c8af4100 CPU: 1 COMMAND: "kworker/1:48"
#0 [ffff9456c1cc79a0] machine_kexec at ffffffff870665b7
#1 [ffff9456c1cc79f0] __crash_kexec at ffffffff871b4c7a
#2 [ffff9456c1cc7ab0] crash_kexec at ffffffff871b5b60
#3 [ffff9456c1cc7ac0] oops_end at ffffffff87026ce7
#4 [ffff9456c1cc7ae0] page_fault_oops at ffffffff87075715
#5 [ffff9456c1cc7b58] exc_page_fault at ffffffff87ad0654
#6 [ffff9456c1cc7b80] asm_exc_page_fault at ffffffff87c00b62
[exception RIP: ib_alloc_mr+19]
RIP: ffffffffc0c9cce3 RSP: ffff9456c1cc7c38 RFLAGS: 00010202
RAX: 0000000000000000 RBX: 0000000000000002 RCX: 0000000000000004
RDX: 0000000000000010 RSI: 0000000000000000 RDI: 0000000000000000
RBP: ffff88c1ea281d00 R8: 000000020a34ffff R9: ffff88c1350bbb20
R10: 0000000000000000 R11: 0000000000000001 R12: 0000000000000000
R13: 0000000000000010 R14: ffff88c1ab040a50 R15: ffff88c1ea281d00
ORIG_RAX: ffffffffffffffff CS: 0010 SS: 0018
#7 [ffff9456c1cc7c60] smc_ib_get_memory_region at ffffffffc0aff6df [smc]
#8 [ffff9456c1cc7c88] smcr_buf_map_link at ffffffffc0b0278c [smc]
#9 [ffff9456c1cc7ce0] __smc_buf_create at ffffffffc0b03586 [smc]
The reason here is that when the server tries to create a second link,
smc_llc_srv_add_link() has no protection and may add a new link to
link group. This breaks the security environment protected by
llc_conf_mutex.
Signed-off-by: D. Wythe <alibuda@linux.alibaba.com>
---
net/smc/af_smc.c | 2 ++
1 file changed, 2 insertions(+)
diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c
index 39dbf39..0b0c53a 100644
--- a/net/smc/af_smc.c
+++ b/net/smc/af_smc.c
@@ -1834,8 +1834,10 @@ static int smcr_serv_conf_first_link(struct smc_sock *smc)
smc_llc_link_active(link);
smcr_lgr_set_type(link->lgr, SMC_LGR_SINGLE);
+ down_write(&link->lgr->llc_conf_mutex);
/* initial contact - try to establish second link */
smc_llc_srv_add_link(link, NULL);
+ up_write(&link->lgr->llc_conf_mutex);
return 0;
}
--
1.8.3.1
^ permalink raw reply related
* [PATCH net-next 10/10] net/smc: fix application data exception
From: D. Wythe @ 2022-08-10 17:47 UTC (permalink / raw)
To: kgraul, wenjia; +Cc: kuba, davem, netdev, linux-s390, linux-rdma
In-Reply-To: <cover.1660152975.git.alibuda@linux.alibaba.com>
From: "D. Wythe" <alibuda@linux.alibaba.com>
After we optimize the parallel capability of SMC-R connection
establishment, There is a certain probability that following
exceptions will occur in the wrk benchmark test:
Running 10s test @ http://11.213.45.6:80
8 threads and 64 connections
Thread Stats Avg Stdev Max +/- Stdev
Latency 3.72ms 13.94ms 245.33ms 94.17%
Req/Sec 1.96k 713.67 5.41k 75.16%
155262 requests in 10.10s, 23.10MB read
Non-2xx or 3xx responses: 3
We will find that the error is HTTP 400 error, which is a serious
exception in our test, which means the application data was
corrupted.
Consider the following scenarios:
CPU0 CPU1
buf_desc->used = 0;
cmpxchg(buf_desc->used, 0, 1)
deal_with(buf_desc)
memset(buf_desc->cpu_addr,0);
This will cause the data received by a victim connection to be cleared,
thus triggering an HTTP 400 error in the server.
This patch exchange the order between clear used and memset, add
barrier to ensure memory consistency.
Signed-off-by: D. Wythe <alibuda@linux.alibaba.com>
---
net/smc/smc_core.c | 5 +++--
1 file changed, 3 insertions(+), 2 deletions(-)
diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c
index b90970a..7d42125 100644
--- a/net/smc/smc_core.c
+++ b/net/smc/smc_core.c
@@ -1406,8 +1406,9 @@ static void smcr_buf_unuse(struct smc_buf_desc *buf_desc, bool is_rmb,
smc_buf_free(lgr, is_rmb, buf_desc);
} else {
- buf_desc->used = 0;
- memset(buf_desc->cpu_addr, 0, buf_desc->len);
+ /* memzero_explicit provides potential memory barrier semantics */
+ memzero_explicit(buf_desc->cpu_addr, buf_desc->len);
+ WRITE_ONCE(buf_desc->used, 0);
}
}
--
1.8.3.1
^ permalink raw reply related
* [PATCH net-next 08/10] net/smc: replace mutex rmbs_lock and sndbufs_lock with rw_semaphore
From: D. Wythe @ 2022-08-10 17:47 UTC (permalink / raw)
To: kgraul, wenjia; +Cc: kuba, davem, netdev, linux-s390, linux-rdma
In-Reply-To: <cover.1660152975.git.alibuda@linux.alibaba.com>
From: "D. Wythe" <alibuda@linux.alibaba.com>
It's clear that rmbs_lock and sndbufs_lock are aims to protect the
rmbs list or the sndbufs list.
During conenction establieshment, smc_buf_get_slot() will always
be invoke, and it only performs read semantics in rmbs list and
sndbufs list.
Based on the above considerations, we replace mutex with rw_semaphore.
Only smc_buf_get_slot() use down_read() to allow smc_buf_get_slot()
run concurrently, other part use down_write() to keep exclusive
semantics.
Signed-off-by: D. Wythe <alibuda@linux.alibaba.com>
---
net/smc/smc_core.c | 55 +++++++++++++++++++++++++++---------------------------
net/smc/smc_core.h | 4 ++--
net/smc/smc_llc.c | 16 ++++++++--------
3 files changed, 38 insertions(+), 37 deletions(-)
diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c
index 113804d..b90970a 100644
--- a/net/smc/smc_core.c
+++ b/net/smc/smc_core.c
@@ -1138,8 +1138,8 @@ static int smc_lgr_create(struct smc_sock *smc, struct smc_init_info *ini)
lgr->freeing = 0;
lgr->vlan_id = ini->vlan_id;
refcount_set(&lgr->refcnt, 1); /* set lgr refcnt to 1 */
- mutex_init(&lgr->sndbufs_lock);
- mutex_init(&lgr->rmbs_lock);
+ init_rwsem(&lgr->sndbufs_lock);
+ init_rwsem(&lgr->rmbs_lock);
rwlock_init(&lgr->conns_lock);
for (i = 0; i < SMC_RMBE_SIZES; i++) {
INIT_LIST_HEAD(&lgr->sndbufs[i]);
@@ -1380,7 +1380,7 @@ struct smc_link *smc_switch_conns(struct smc_link_group *lgr,
static void smcr_buf_unuse(struct smc_buf_desc *buf_desc, bool is_rmb,
struct smc_link_group *lgr)
{
- struct mutex *lock; /* lock buffer list */
+ struct rw_semaphore *lock; /* lock buffer list */
int rc;
if (is_rmb && buf_desc->is_conf_rkey && !list_empty(&lgr->list)) {
@@ -1400,9 +1400,9 @@ static void smcr_buf_unuse(struct smc_buf_desc *buf_desc, bool is_rmb,
/* buf registration failed, reuse not possible */
lock = is_rmb ? &lgr->rmbs_lock :
&lgr->sndbufs_lock;
- mutex_lock(lock);
+ down_write(lock);
list_del(&buf_desc->list);
- mutex_unlock(lock);
+ up_write(lock);
smc_buf_free(lgr, is_rmb, buf_desc);
} else {
@@ -1506,15 +1506,16 @@ static void smcr_buf_unmap_lgr(struct smc_link *lnk)
int i;
for (i = 0; i < SMC_RMBE_SIZES; i++) {
- mutex_lock(&lgr->rmbs_lock);
+ down_write(&lgr->rmbs_lock);
list_for_each_entry_safe(buf_desc, bf, &lgr->rmbs[i], list)
smcr_buf_unmap_link(buf_desc, true, lnk);
- mutex_unlock(&lgr->rmbs_lock);
- mutex_lock(&lgr->sndbufs_lock);
+ up_write(&lgr->rmbs_lock);
+
+ down_write(&lgr->sndbufs_lock);
list_for_each_entry_safe(buf_desc, bf, &lgr->sndbufs[i],
list)
smcr_buf_unmap_link(buf_desc, false, lnk);
- mutex_unlock(&lgr->sndbufs_lock);
+ up_write(&lgr->sndbufs_lock);
}
}
@@ -2324,19 +2325,19 @@ int smc_uncompress_bufsize(u8 compressed)
* buffer size; if not available, return NULL
*/
static struct smc_buf_desc *smc_buf_get_slot(int compressed_bufsize,
- struct mutex *lock,
+ struct rw_semaphore *lock,
struct list_head *buf_list)
{
struct smc_buf_desc *buf_slot;
- mutex_lock(lock);
+ down_read(lock);
list_for_each_entry(buf_slot, buf_list, list) {
if (cmpxchg(&buf_slot->used, 0, 1) == 0) {
- mutex_unlock(lock);
+ up_read(lock);
return buf_slot;
}
}
- mutex_unlock(lock);
+ up_read(lock);
return NULL;
}
@@ -2445,13 +2446,13 @@ int smcr_link_reg_buf(struct smc_link *link, struct smc_buf_desc *buf_desc)
return 0;
}
-static int _smcr_buf_map_lgr(struct smc_link *lnk, struct mutex *lock,
+static int _smcr_buf_map_lgr(struct smc_link *lnk, struct rw_semaphore *lock,
struct list_head *lst, bool is_rmb)
{
struct smc_buf_desc *buf_desc, *bf;
int rc = 0;
- mutex_lock(lock);
+ down_write(lock);
list_for_each_entry_safe(buf_desc, bf, lst, list) {
if (!buf_desc->used)
continue;
@@ -2460,7 +2461,7 @@ static int _smcr_buf_map_lgr(struct smc_link *lnk, struct mutex *lock,
goto out;
}
out:
- mutex_unlock(lock);
+ up_write(lock);
return rc;
}
@@ -2493,37 +2494,37 @@ int smcr_buf_reg_lgr(struct smc_link *lnk)
int i, rc = 0;
/* reg all RMBs for a new link */
- mutex_lock(&lgr->rmbs_lock);
+ down_write(&lgr->rmbs_lock);
for (i = 0; i < SMC_RMBE_SIZES; i++) {
list_for_each_entry_safe(buf_desc, bf, &lgr->rmbs[i], list) {
if (!buf_desc->used)
continue;
rc = smcr_link_reg_buf(lnk, buf_desc);
if (rc) {
- mutex_unlock(&lgr->rmbs_lock);
+ up_write(&lgr->rmbs_lock);
return rc;
}
}
}
- mutex_unlock(&lgr->rmbs_lock);
+ up_write(&lgr->rmbs_lock);
if (lgr->buf_type == SMCR_PHYS_CONT_BUFS)
return rc;
/* reg all vzalloced sndbufs for a new link */
- mutex_lock(&lgr->sndbufs_lock);
+ down_write(&lgr->sndbufs_lock);
for (i = 0; i < SMC_RMBE_SIZES; i++) {
list_for_each_entry_safe(buf_desc, bf, &lgr->sndbufs[i], list) {
if (!buf_desc->used || !buf_desc->is_vm)
continue;
rc = smcr_link_reg_buf(lnk, buf_desc);
if (rc) {
- mutex_unlock(&lgr->sndbufs_lock);
+ up_write(&lgr->sndbufs_lock);
return rc;
}
}
}
- mutex_unlock(&lgr->sndbufs_lock);
+ up_write(&lgr->sndbufs_lock);
return rc;
}
@@ -2641,7 +2642,7 @@ static int __smc_buf_create(struct smc_sock *smc, bool is_smcd, bool is_rmb)
struct list_head *buf_list;
int bufsize, bufsize_short;
bool is_dgraded = false;
- struct mutex *lock; /* lock buffer list */
+ struct rw_semaphore *lock; /* lock buffer list */
int sk_buf_size;
if (is_rmb)
@@ -2689,9 +2690,9 @@ static int __smc_buf_create(struct smc_sock *smc, bool is_smcd, bool is_rmb)
SMC_STAT_RMB_ALLOC(smc, is_smcd, is_rmb);
SMC_STAT_RMB_SIZE(smc, is_smcd, is_rmb, bufsize);
buf_desc->used = 1;
- mutex_lock(lock);
+ down_write(lock);
list_add(&buf_desc->list, buf_list);
- mutex_unlock(lock);
+ up_write(lock);
break; /* found */
}
@@ -2765,9 +2766,9 @@ int smc_buf_create(struct smc_sock *smc, bool is_smcd)
/* create rmb */
rc = __smc_buf_create(smc, is_smcd, true);
if (rc) {
- mutex_lock(&smc->conn.lgr->sndbufs_lock);
+ down_write(&smc->conn.lgr->sndbufs_lock);
list_del(&smc->conn.sndbuf_desc->list);
- mutex_unlock(&smc->conn.lgr->sndbufs_lock);
+ up_write(&smc->conn.lgr->sndbufs_lock);
smc_buf_free(smc->conn.lgr, false, smc->conn.sndbuf_desc);
smc->conn.sndbuf_desc = NULL;
}
diff --git a/net/smc/smc_core.h b/net/smc/smc_core.h
index 559d330..008148c 100644
--- a/net/smc/smc_core.h
+++ b/net/smc/smc_core.h
@@ -300,9 +300,9 @@ struct smc_link_group {
unsigned short vlan_id; /* vlan id of link group */
struct list_head sndbufs[SMC_RMBE_SIZES];/* tx buffers */
- struct mutex sndbufs_lock; /* protects tx buffers */
+ struct rw_semaphore sndbufs_lock; /* protects tx buffers */
struct list_head rmbs[SMC_RMBE_SIZES]; /* rx buffers */
- struct mutex rmbs_lock; /* protects rx buffers */
+ struct rw_semaphore rmbs_lock; /* protects rx buffers */
u8 id[SMC_LGR_ID_SIZE]; /* unique lgr id */
struct delayed_work free_work; /* delayed freeing of an lgr */
diff --git a/net/smc/smc_llc.c b/net/smc/smc_llc.c
index d744937..76f9906 100644
--- a/net/smc/smc_llc.c
+++ b/net/smc/smc_llc.c
@@ -642,7 +642,7 @@ static int smc_llc_fill_ext_v2(struct smc_llc_msg_add_link_v2_ext *ext,
prim_lnk_idx = link->link_idx;
lnk_idx = link_new->link_idx;
- mutex_lock(&lgr->rmbs_lock);
+ down_write(&lgr->rmbs_lock);
ext->num_rkeys = lgr->conns_num;
if (!ext->num_rkeys)
goto out;
@@ -662,7 +662,7 @@ static int smc_llc_fill_ext_v2(struct smc_llc_msg_add_link_v2_ext *ext,
}
len += i * sizeof(ext->rt[0]);
out:
- mutex_unlock(&lgr->rmbs_lock);
+ up_write(&lgr->rmbs_lock);
return len;
}
@@ -923,7 +923,7 @@ static int smc_llc_cli_rkey_exchange(struct smc_link *link,
int rc = 0;
int i;
- mutex_lock(&lgr->rmbs_lock);
+ down_write(&lgr->rmbs_lock);
num_rkeys_send = lgr->conns_num;
buf_pos = smc_llc_get_first_rmb(lgr, &buf_lst);
do {
@@ -950,7 +950,7 @@ static int smc_llc_cli_rkey_exchange(struct smc_link *link,
break;
} while (num_rkeys_send || num_rkeys_recv);
- mutex_unlock(&lgr->rmbs_lock);
+ up_write(&lgr->rmbs_lock);
return rc;
}
@@ -1033,14 +1033,14 @@ static void smc_llc_save_add_link_rkeys(struct smc_link *link,
ext = (struct smc_llc_msg_add_link_v2_ext *)((u8 *)lgr->wr_rx_buf_v2 +
SMC_WR_TX_SIZE);
max = min_t(u8, ext->num_rkeys, SMC_LLC_RKEYS_PER_MSG_V2);
- mutex_lock(&lgr->rmbs_lock);
+ down_write(&lgr->rmbs_lock);
for (i = 0; i < max; i++) {
smc_rtoken_set(lgr, link->link_idx, link_new->link_idx,
ext->rt[i].rmb_key,
ext->rt[i].rmb_vaddr_new,
ext->rt[i].rmb_key_new);
}
- mutex_unlock(&lgr->rmbs_lock);
+ up_write(&lgr->rmbs_lock);
}
static void smc_llc_save_add_link_info(struct smc_link *link,
@@ -1349,7 +1349,7 @@ static int smc_llc_srv_rkey_exchange(struct smc_link *link,
int rc = 0;
int i;
- mutex_lock(&lgr->rmbs_lock);
+ down_write(&lgr->rmbs_lock);
num_rkeys_send = lgr->conns_num;
buf_pos = smc_llc_get_first_rmb(lgr, &buf_lst);
do {
@@ -1374,7 +1374,7 @@ static int smc_llc_srv_rkey_exchange(struct smc_link *link,
smc_llc_flow_qentry_del(&lgr->llc_flow_lcl);
} while (num_rkeys_send || num_rkeys_recv);
out:
- mutex_unlock(&lgr->rmbs_lock);
+ up_write(&lgr->rmbs_lock);
return rc;
}
--
1.8.3.1
^ permalink raw reply related
* Re: [RFC PATCH net-next] docs: net: add an explanation of VF (and other) Representors
From: Jakub Kicinski @ 2022-08-10 17:58 UTC (permalink / raw)
To: Edward Cree
Cc: ecree, netdev, davem, pabeni, edumazet, corbet, linux-doc,
linux-net-drivers, Jacob Keller, Jesse Brandeburg, Michael Chan,
Andy Gospodarek, Saeed Mahameed, Jiri Pirko, Shannon Nelson,
Simon Horman, Alexander Duyck
In-Reply-To: <572c50b0-2f10-50d5-76fc-dfa409350dbe@gmail.com>
On Wed, 10 Aug 2022 17:02:33 +0100 Edward Cree wrote:
> On 09/08/2022 04:41, Jakub Kicinski wrote:
> >> Maybe a bad word choice. I'm referring to whichever PF (which likely
> >> also has an ordinary netdevice) has administrative rights over the NIC /
> >> internal switch at a firmware level. Other names I've seen tossed
> >> around include "primary PF", "admin PF".
> >
> > I believe someone (mellanox?) used the term eswitch manager.
> > I'd use "host PF", somehow that makes most sense to me.
>
> Not sure about that, I've seen "host" used as antonym of "SoC", so
> if the device is configured with the SoC as the admin this could
> confuse people.
In the literal definition of the word "host" it is the entity which
"owns the place".
> I think whatever term we settle on, this document might need to
> have a 'Definitions' section to make it clear :S
Ack, to perhaps clarify my concern further, I've seen the term
"management PF" refer to a PF which is not a netdev PF, it only
performs management functions. Which I don't believe is what we
are describing here. So a perfect term would describe the privilege
not the function (as the primary function of such PF should still
networking).
> >> Yes, that's where I got this terminology from.
> >> "the" PCIe controller here is the one on which the mgmt PF lives. For
> >> instance you might have a NIC where you run OVS on a SoC inside the
> >> chip, that has its own PCIe controller including a PF it uses to drive
> >> the hardware v-switch (so it can offload OVS rules), in addition to
> >> the PCIe controller that exposes PFs & VFs to the host you plug it
> >> into through the physical PCIe socket / edge connector.
> >> In that case this bullet would refer to any additional PFs the SoC has
> >> besides the management one...
> >
> > IMO the model where there's a overall controller for the entire device
> > is also a mellanox limitation, due to lack of support for nested
> > switches
> Instead of "the PCIe controller" I should probably say "the local PCIe
> controller", since that's the wording the devlink-port doc uses.
SG!
> > "TX queue attached to" made me think of a netdev Tx queue with a qdisc
> > rather than just a HW queue. No better ideas tho.
>
> Would adding the word "hardware" before "TX queue" help? Have to
> admit the netdev-queue interpretation hadn't occurred to me.
It would!
> >> (And it looks like the core uses `c<N>` for my `if<N>` that you were
> >> so horrified by. Devlink-port documentation doesn't make it super
> >> clear whether controller 0 is "the controller that's in charge" or
> >> "the controller from which we're viewing things", though I think in
> >> practice it comes to the same thing.)
> >
> > I think we had a bit. Perhaps @external? The controller which doesn't
> > have @external == true should be the local one IIRC. And by extension
> > presumably in charge.
>
> Yes, and that should work fine per se. It's just not reflected in the
> phys_port_name string in any way, so legacy userland that relies on
> that won't have that piece of info (but it never did) and probably
> assumes that c0 is local.
Ack, we could check the archive but I think that's indeed the case.
^ permalink raw reply
* Re: [PATCH 2/5] dt-bindings: net: Add Broadcom BCM4377 family PCI Bluetooth
From: Rob Herring @ 2022-08-10 18:10 UTC (permalink / raw)
To: Mark Kettenis
Cc: sven, marcel, johan.hedberg, luiz.dentz, krzysztof.kozlowski+dt,
davem, edumazet, kuba, pabeni, marcan, alyssa, asahi, netdev,
devicetree, linux-arm-kernel, linux-bluetooth, linux-kernel
In-Reply-To: <d3ce6343fdaaf127@bloch.sibelius.xs4all.nl>
On Mon, Aug 01, 2022 at 05:51:23PM +0200, Mark Kettenis wrote:
> > Date: Mon, 1 Aug 2022 09:39:21 -0600
> > From: Rob Herring <robh@kernel.org>
> >
> > On Mon, Aug 01, 2022 at 12:36:30PM +0200, Sven Peter wrote:
> > > These chips are combined Wi-Fi/Bluetooth radios which expose a
> > > PCI subfunction for the Bluetooth part.
> > > They are found in Apple machines such as the x86 models with the T2
> > > chip or the arm64 models with the M1 or M2 chips.
> > >
> > > Signed-off-by: Sven Peter <sven@svenpeter.dev>
> > > ---
> > > .../bindings/net/brcm,bcm4377-bluetooth.yaml | 77 +++++++++++++++++++
> > > MAINTAINERS | 1 +
> > > 2 files changed, 78 insertions(+)
> > > create mode 100644 Documentation/devicetree/bindings/net/brcm,bcm4377-bluetooth.yaml
> > >
> > > diff --git a/Documentation/devicetree/bindings/net/brcm,bcm4377-bluetooth.yaml b/Documentation/devicetree/bindings/net/brcm,bcm4377-bluetooth.yaml
> > > new file mode 100644
> > > index 000000000000..afe6ecebd939
> > > --- /dev/null
> > > +++ b/Documentation/devicetree/bindings/net/brcm,bcm4377-bluetooth.yaml
> > > @@ -0,0 +1,77 @@
> > > +# SPDX-License-Identifier: (GPL-2.0 OR BSD-2-Clause)
> > > +%YAML 1.2
> > > +---
> > > +$id: http://devicetree.org/schemas/net/brcm,bcm4377-bluetooth.yaml#
> > > +$schema: http://devicetree.org/meta-schemas/core.yaml#
> > > +
> > > +title: Broadcom BCM4377 family PCI Bluetooth Chips
> > > +
> > > +allOf:
> > > + - $ref: bluetooth-controller.yaml#
> > > +
> > > +maintainers:
> > > + - Sven Peter <sven@svenpeter.dev>
> > > +
> > > +description:
> > > + This binding describes Broadcom BCM4377 family PCI-attached bluetooth chips
> >
> > s/PCI/PCIe/
> >
> > > + usually found in Apple machines. The Wi-Fi part of the chip is described in
> > > + bindings/net/wireless/brcm,bcm4329-fmac.yaml.
> > > +
> > > +properties:
> > > + compatible:
> > > + enum:
> > > + - pci14e4,5fa0 # BCM4377
> > > + - pci14e4,5f69 # BCM4378
> > > + - pci14e4,5f71 # BCM4387
> > > +
> > > + reg:
> > > + description: PCI device identifier.
> > > +
> > > + brcm,board-type:
> > > + $ref: /schemas/types.yaml#/definitions/string
> > > + description: Board type of the Bluetooth chip. This is used to decouple
> > > + the overall system board from the Bluetooth module and used to construct
> > > + firmware and calibration data filenames.
> > > + On Apple platforms, this should be the Apple module-instance codename
> > > + prefixed by "apple,", e.g. "apple,atlantisb".
> >
> > pattern: '^apple,.*'
> >
> > And when there's other known vendors we can add them.
> >
> > Really, I'm not all that crazy about this property. 'firmware-name'
> > doesn't work? Or perhaps this should just be a more specific compatible
> > string.
>
> This matches the property proposed here:
>
> https://patchwork.kernel.org/project/linux-wireless/patch/20220104072658.69756-2-marcan@marcan.st/
>
> Unfortunately that series didn't make progress for other reasons...
>
> There was some significant bikeshedding in the original version of that series already:
>
> https://patchwork.kernel.org/project/linux-wireless/patch/20211226153624.162281-2-marcan@marcan.st/
>
> Are you sure you want to repeat that? ;)
No, it's fine. :)
Rob
^ permalink raw reply
* [PATCH ipsec 0/2] xfrm: Fix bugs in stacked XFRM-I tunnels
From: Benedict Wong @ 2022-08-10 18:22 UTC (permalink / raw)
To: steffen.klassert, netdev; +Cc: nharold, benedictwong, lorenzo
This patch set fixes bugs that prevent stacked IPsec tunnels (via XFRM
interfaces) from receiving packets properly. The apparent cause of the
issues is that the inner tunnel’s policy checks fail to validate the
outer tunnel’s secpath entries (since it no longer has a reference to
the outer tunnel policies, and each call validates ALL secpath entries)
prior to verifying the inner tunnel’s. This patch set fixes this by
caching the list of verified secpath entries, and skipping them upon
future validation runs.
PATCH 1/2 Ensures that policies for nested tunnel mode transforms are
checked before additional decapsulation. This ensures that entries in
the secpath are verified while the context (intermediate IP addresses,
marks, etc) can be appropriately matched.
PATCH 2/2 Skips template matching for previously verified entries in
the secpath. This ensures that each tunnel is responsible for
incrementally verifying the secpath entries associated with it.
^ permalink raw reply
* [PATCH ipsec 1/2] xfrm: Check policy for nested XFRM packets in xfrm_input
From: Benedict Wong @ 2022-08-10 18:22 UTC (permalink / raw)
To: steffen.klassert, netdev; +Cc: nharold, benedictwong, lorenzo
In-Reply-To: <20220810182210.721493-1-benedictwong@google.com>
This change ensures that all nested XFRM packets have their policy
checked before decryption of the next layer, so that policies are
verified at each intermediate step of the decryption process.
This is necessary especially for nested tunnels, as the IP addresses,
protocol and ports may all change, thus not matching the previous
policies. In order to ensure that packets match the relevant inbound
templates, the xfrm_policy_check should be done before handing off to
the inner XFRM protocol to decrypt and decapsulate.
Test: Tested against Android Kernel Unit Tests
Signed-off-by: Benedict Wong <benedictwong@google.com>
Change-Id: I20c5abf39512d7f6cf438c0921a78a84e281b4e9
---
net/xfrm/xfrm_input.c | 7 +++++++
1 file changed, 7 insertions(+)
diff --git a/net/xfrm/xfrm_input.c b/net/xfrm/xfrm_input.c
index 144238a50f3d..b24df8a44585 100644
--- a/net/xfrm/xfrm_input.c
+++ b/net/xfrm/xfrm_input.c
@@ -585,6 +585,13 @@ int xfrm_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type)
goto drop;
}
+ // If nested tunnel, check outer states before context is lost.
+ if (x->outer_mode.flags & XFRM_MODE_FLAG_TUNNEL
+ && sp->len > 0
+ && !xfrm_policy_check(NULL, XFRM_POLICY_IN, skb, family)) {
+ goto drop;
+ }
+
skb->mark = xfrm_smark_get(skb->mark, x);
sp->xvec[sp->len++] = x;
--
2.37.1.595.g718a3a8f04-goog
^ permalink raw reply related
* [PATCH ipsec 2/2] xfrm: Skip checking of already-verified secpath entries
From: Benedict Wong @ 2022-08-10 18:22 UTC (permalink / raw)
To: steffen.klassert, netdev; +Cc: nharold, benedictwong, lorenzo
In-Reply-To: <20220810182210.721493-1-benedictwong@google.com>
This change fixes a bug where inbound packets to nested IPsec tunnels
fails to pass policy checks due to the inner tunnel's policy checks
not having a reference to the outer policy/template. This causes the
policy check to fail, since the first entries in the secpath correlate
to the outer tunnel, while the templates being verified are for the
inner tunnel.
In order to ensure that the appropriate policy and template context is
searchable, the policy checks must be done incrementally after each
decryption step. As such, this marks secpath entries as having been
successfully matched, skipping these on subsequent policy checks.
By skipping the immediate error return in the case where the secpath
entry had previously been validated, this change allows secpath entries
that matched a policy/template previously, while still requiring that
each searched template find a match in the secpath.
For security:
- All templates must have matching secpath entries
- Unchanged by current patch; templates that do not match any secpath
entry still return -1. This patch simply allows skipping earlier
blocks of verified secpath entries
- All entries (except trailing transport mode entries) must have a
matching template
- Unvalidated entries, including transport-mode entries still return
the errored index if it does not match the correct template.
Test: Tested against Android Kernel Unit Tests
Signed-off-by: Benedict Wong <benedictwong@google.com>
Change-Id: Ic32831cb00151d0de2e465f18ec37d5f7b680e54
---
include/net/xfrm.h | 1 +
net/xfrm/xfrm_input.c | 3 ++-
net/xfrm/xfrm_policy.c | 11 ++++++++++-
3 files changed, 13 insertions(+), 2 deletions(-)
diff --git a/include/net/xfrm.h b/include/net/xfrm.h
index c39d910d4b45..a2f2840aba6b 100644
--- a/include/net/xfrm.h
+++ b/include/net/xfrm.h
@@ -1031,6 +1031,7 @@ struct xfrm_offload {
struct sec_path {
int len;
int olen;
+ int verified_cnt;
struct xfrm_state *xvec[XFRM_MAX_DEPTH];
struct xfrm_offload ovec[XFRM_MAX_OFFLOAD_DEPTH];
diff --git a/net/xfrm/xfrm_input.c b/net/xfrm/xfrm_input.c
index b24df8a44585..895935077a91 100644
--- a/net/xfrm/xfrm_input.c
+++ b/net/xfrm/xfrm_input.c
@@ -129,6 +129,7 @@ struct sec_path *secpath_set(struct sk_buff *skb)
memset(sp->ovec, 0, sizeof(sp->ovec));
sp->olen = 0;
sp->len = 0;
+ sp->verified_cnt = 0;
return sp;
}
@@ -587,7 +588,7 @@ int xfrm_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type)
// If nested tunnel, check outer states before context is lost.
if (x->outer_mode.flags & XFRM_MODE_FLAG_TUNNEL
- && sp->len > 0
+ && sp->len > sp->verified_cnt
&& !xfrm_policy_check(NULL, XFRM_POLICY_IN, skb, family)) {
goto drop;
}
diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index f1a0bab920a5..ee620a856c6f 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -3261,7 +3261,7 @@ xfrm_state_ok(const struct xfrm_tmpl *tmpl, const struct xfrm_state *x,
*/
static inline int
xfrm_policy_ok(const struct xfrm_tmpl *tmpl, const struct sec_path *sp, int start,
- unsigned short family)
+ unsigned short family)
{
int idx = start;
@@ -3274,6 +3274,11 @@ xfrm_policy_ok(const struct xfrm_tmpl *tmpl, const struct sec_path *sp, int star
if (xfrm_state_ok(tmpl, sp->xvec[idx], family))
return ++idx;
if (sp->xvec[idx]->props.mode != XFRM_MODE_TRANSPORT) {
+ if (idx < sp->verified_cnt) {
+ // Secpath entry previously verified, continue searching
+ continue;
+ }
+
if (start == -1)
start = -2-idx;
break;
@@ -3650,6 +3655,8 @@ int __xfrm_policy_check(struct sock *sk, int dir, struct sk_buff *skb,
* Order is _important_. Later we will implement
* some barriers, but at the moment barriers
* are implied between each two transformations.
+ * Skips verifying secpath entries that have already been
+ * verified in the past.
*/
for (i = xfrm_nr-1, k = 0; i >= 0; i--) {
k = xfrm_policy_ok(tpp[i], sp, k, family);
@@ -3668,6 +3675,8 @@ int __xfrm_policy_check(struct sock *sk, int dir, struct sk_buff *skb,
}
xfrm_pols_put(pols, npols);
+ sp->verified_cnt = k;
+
return 1;
}
XFRM_INC_STATS(net, LINUX_MIB_XFRMINPOLBLOCK);
--
2.37.1.595.g718a3a8f04-goog
^ permalink raw reply related
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox