* [PATCH net-next 0/2] ibmvnic: Tunable parameter support
@ 2017-10-20 21:00 John Allen
2017-10-20 21:02 ` [PATCH net-next 1/2] ibmvnic: Update reset infrastructure to support tunable parameters John Allen
` (2 more replies)
0 siblings, 3 replies; 4+ messages in thread
From: John Allen @ 2017-10-20 21:00 UTC (permalink / raw)
To: netdev, Thomas Falcon, Nathan Fontenot
This series implements support for changing tunable parameters such as the
mtu, number of tx/rx queues, and number of buffers per queue via ethtool
and ifconfig.
John Allen (2):
ibmvnic: Update reset infrastructure to support tunable parameters
ibmvnic: Fix failover error path for non-fatal resets
drivers/net/ethernet/ibm/ibmvnic.c | 222 ++++++++++++++++++++++++++++++++-----
drivers/net/ethernet/ibm/ibmvnic.h | 24 +++-
2 files changed, 216 insertions(+), 30 deletions(-)
--
1.8.3.1
^ permalink raw reply [flat|nested] 4+ messages in thread
* [PATCH net-next 1/2] ibmvnic: Update reset infrastructure to support tunable parameters
2017-10-20 21:00 [PATCH net-next 0/2] ibmvnic: Tunable parameter support John Allen
@ 2017-10-20 21:02 ` John Allen
2017-10-20 21:03 ` [PATCH net-next 2/2] ibmvnic: Fix failover error path for non-fatal resets John Allen
2017-10-22 2:16 ` [PATCH net-next 0/2] ibmvnic: Tunable parameter support David Miller
2 siblings, 0 replies; 4+ messages in thread
From: John Allen @ 2017-10-20 21:02 UTC (permalink / raw)
To: netdev, Thomas Falcon, Nathan Fontenot
Update ibmvnic reset infrastructure to include a new reset option that will
allow changing of tunable parameters. There currently is no way to request
different capabilities from the vnic server on the fly so this patch
achieves this by resetting the driver and attempting to log in with the
requested changes. If the reset operation fails, the old values of the
tunable parameters are stored in the "fallback" struct and we attempt to
login with the fallback values.
Signed-off-by: John Allen <jallen@linux.vnet.ibm.com>
---
diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c
index 4bc14a9..36898b0 100644
--- a/drivers/net/ethernet/ibm/ibmvnic.c
+++ b/drivers/net/ethernet/ibm/ibmvnic.c
@@ -115,6 +115,7 @@ static union sub_crq *ibmvnic_next_scrq(struct ibmvnic_adapter *,
static int init_sub_crq_irqs(struct ibmvnic_adapter *adapter);
static int ibmvnic_init(struct ibmvnic_adapter *);
static void release_crq_queue(struct ibmvnic_adapter *);
+static int __ibmvnic_set_mac(struct net_device *netdev, struct sockaddr *p);
struct ibmvnic_stat {
char name[ETH_GSTRING_LEN];
@@ -910,6 +911,11 @@ static int ibmvnic_open(struct net_device *netdev)
mutex_lock(&adapter->reset_lock);
+ if (adapter->desired->mac) {
+ __ibmvnic_set_mac(netdev, adapter->desired->mac);
+ adapter->desired->mac = NULL;
+ }
+
if (adapter->state != VNIC_CLOSED) {
rc = ibmvnic_login(netdev);
if (rc) {
@@ -1372,7 +1378,7 @@ static void ibmvnic_set_multi(struct net_device *netdev)
}
}
-static int ibmvnic_set_mac(struct net_device *netdev, void *p)
+static int __ibmvnic_set_mac(struct net_device *netdev, struct sockaddr *p)
{
struct ibmvnic_adapter *adapter = netdev_priv(netdev);
struct sockaddr *addr = p;
@@ -1390,6 +1396,21 @@ static int ibmvnic_set_mac(struct net_device *netdev, void *p)
return 0;
}
+static int ibmvnic_set_mac(struct net_device *netdev, void *p)
+{
+ struct ibmvnic_adapter *adapter = netdev_priv(netdev);
+ struct sockaddr *addr = p;
+
+ if (adapter->state != VNIC_OPEN) {
+ memcpy(adapter->desired->mac, addr, sizeof(struct sockaddr));
+ return 0;
+ }
+
+ __ibmvnic_set_mac(netdev, addr);
+
+ return 0;
+}
+
/**
* do_reset returns zero if we are able to keep processing reset events, or
* non-zero if we hit a fatal error and must halt.
@@ -1416,6 +1437,13 @@ static int do_reset(struct ibmvnic_adapter *adapter,
if (rc)
return rc;
+ if (adapter->reset_reason == VNIC_RESET_CHANGE_PARAM ||
+ adapter->wait_for_reset) {
+ release_resources(adapter);
+ release_sub_crqs(adapter);
+ release_crq_queue(adapter);
+ }
+
if (adapter->reset_reason != VNIC_RESET_NON_FATAL) {
/* remove the closed state so when we call open it appears
* we are coming from the probed state.
@@ -1438,16 +1466,23 @@ static int do_reset(struct ibmvnic_adapter *adapter,
return 0;
}
- rc = reset_tx_pools(adapter);
- if (rc)
- return rc;
+ if (adapter->reset_reason == VNIC_RESET_CHANGE_PARAM ||
+ adapter->wait_for_reset) {
+ rc = init_resources(adapter);
+ if (rc)
+ return rc;
+ } else {
+ rc = reset_tx_pools(adapter);
+ if (rc)
+ return rc;
- rc = reset_rx_pools(adapter);
- if (rc)
- return rc;
+ rc = reset_rx_pools(adapter);
+ if (rc)
+ return rc;
- if (reset_state == VNIC_CLOSED)
- return 0;
+ if (reset_state == VNIC_CLOSED)
+ return 0;
+ }
}
rc = __ibmvnic_open(netdev);
@@ -1526,6 +1561,12 @@ static void __ibmvnic_reset(struct work_struct *work)
rwi = get_next_rwi(adapter);
}
+ if (adapter->wait_for_reset) {
+ adapter->wait_for_reset = false;
+ adapter->reset_done_rc = rc;
+ complete(&adapter->reset_done);
+ }
+
if (rc) {
netdev_dbg(adapter->netdev, "Reset failed\n");
free_all_rwi(adapter);
@@ -1705,9 +1746,42 @@ static void ibmvnic_netpoll_controller(struct net_device *dev)
}
#endif
+static int wait_for_reset(struct ibmvnic_adapter *adapter)
+{
+ adapter->fallback->mtu = adapter->req_mtu;
+ adapter->fallback->rx_queues = adapter->req_rx_queues;
+ adapter->fallback->tx_queues = adapter->req_tx_queues;
+ adapter->fallback->rx_entries = adapter->req_rx_add_entries_per_subcrq;
+ adapter->fallback->tx_entries = adapter->req_tx_entries_per_subcrq;
+
+ init_completion(&adapter->reset_done);
+ ibmvnic_reset(adapter, VNIC_RESET_CHANGE_PARAM);
+ adapter->wait_for_reset = true;
+ wait_for_completion(&adapter->reset_done);
+
+ if (adapter->reset_done_rc) {
+ adapter->desired->mtu = adapter->fallback->mtu;
+ adapter->desired->rx_queues = adapter->fallback->rx_queues;
+ adapter->desired->tx_queues = adapter->fallback->tx_queues;
+ adapter->desired->rx_entries = adapter->fallback->rx_entries;
+ adapter->desired->tx_entries = adapter->fallback->tx_entries;
+
+ init_completion(&adapter->reset_done);
+ ibmvnic_reset(adapter, VNIC_RESET_CHANGE_PARAM);
+ wait_for_completion(&adapter->reset_done);
+ }
+ adapter->wait_for_reset = false;
+
+ return adapter->reset_done_rc;
+}
+
static int ibmvnic_change_mtu(struct net_device *netdev, int new_mtu)
{
- return -EOPNOTSUPP;
+ struct ibmvnic_adapter *adapter = netdev_priv(netdev);
+
+ adapter->desired->mtu = new_mtu + ETH_HLEN;
+
+ return wait_for_reset(adapter);
}
static const struct net_device_ops ibmvnic_netdev_ops = {
@@ -1795,6 +1869,27 @@ static void ibmvnic_get_ringparam(struct net_device *netdev,
ring->rx_jumbo_pending = 0;
}
+static int ibmvnic_set_ringparam(struct net_device *netdev,
+ struct ethtool_ringparam *ring)
+{
+ struct ibmvnic_adapter *adapter = netdev_priv(netdev);
+
+ if (ring->rx_pending > adapter->max_rx_add_entries_per_subcrq ||
+ ring->tx_pending > adapter->max_tx_entries_per_subcrq) {
+ netdev_err(netdev, "Invalid request.\n");
+ netdev_err(netdev, "Max tx buffers = %llu\n",
+ adapter->max_rx_add_entries_per_subcrq);
+ netdev_err(netdev, "Max rx buffers = %llu\n",
+ adapter->max_tx_entries_per_subcrq);
+ return -EINVAL;
+ }
+
+ adapter->desired->rx_entries = ring->rx_pending;
+ adapter->desired->tx_entries = ring->tx_pending;
+
+ return wait_for_reset(adapter);
+}
+
static void ibmvnic_get_channels(struct net_device *netdev,
struct ethtool_channels *channels)
{
@@ -1810,6 +1905,17 @@ static void ibmvnic_get_channels(struct net_device *netdev,
channels->combined_count = 0;
}
+static int ibmvnic_set_channels(struct net_device *netdev,
+ struct ethtool_channels *channels)
+{
+ struct ibmvnic_adapter *adapter = netdev_priv(netdev);
+
+ adapter->desired->rx_queues = channels->rx_count;
+ adapter->desired->tx_queues = channels->tx_count;
+
+ return wait_for_reset(adapter);
+}
+
static void ibmvnic_get_strings(struct net_device *dev, u32 stringset, u8 *data)
{
struct ibmvnic_adapter *adapter = netdev_priv(dev);
@@ -1906,7 +2012,9 @@ static void ibmvnic_get_ethtool_stats(struct net_device *dev,
.set_msglevel = ibmvnic_set_msglevel,
.get_link = ibmvnic_get_link,
.get_ringparam = ibmvnic_get_ringparam,
+ .set_ringparam = ibmvnic_set_ringparam,
.get_channels = ibmvnic_get_channels,
+ .set_channels = ibmvnic_set_channels,
.get_strings = ibmvnic_get_strings,
.get_sset_count = ibmvnic_get_sset_count,
.get_ethtool_stats = ibmvnic_get_ethtool_stats,
@@ -2372,6 +2480,7 @@ static void ibmvnic_send_req_caps(struct ibmvnic_adapter *adapter, int retry)
{
struct device *dev = &adapter->vdev->dev;
union ibmvnic_crq crq;
+ int max_entries;
if (!retry) {
/* Sub-CRQ entries are 32 byte long */
@@ -2383,21 +2492,60 @@ static void ibmvnic_send_req_caps(struct ibmvnic_adapter *adapter, int retry)
return;
}
- /* Get the minimum between the queried max and the entries
- * that fit in our PAGE_SIZE
- */
- adapter->req_tx_entries_per_subcrq =
- adapter->max_tx_entries_per_subcrq > entries_page ?
- entries_page : adapter->max_tx_entries_per_subcrq;
- adapter->req_rx_add_entries_per_subcrq =
- adapter->max_rx_add_entries_per_subcrq > entries_page ?
- entries_page : adapter->max_rx_add_entries_per_subcrq;
-
- adapter->req_tx_queues = adapter->opt_tx_comp_sub_queues;
- adapter->req_rx_queues = adapter->opt_rx_comp_queues;
- adapter->req_rx_add_queues = adapter->max_rx_add_queues;
+ if (adapter->desired->mtu)
+ adapter->req_mtu = adapter->desired->mtu;
+ else
+ adapter->req_mtu = adapter->netdev->mtu + ETH_HLEN;
+
+ if (!adapter->desired->tx_entries)
+ adapter->desired->tx_entries =
+ adapter->max_tx_entries_per_subcrq;
+ if (!adapter->desired->rx_entries)
+ adapter->desired->rx_entries =
+ adapter->max_rx_add_entries_per_subcrq;
+
+ max_entries = IBMVNIC_MAX_LTB_SIZE /
+ (adapter->req_mtu + IBMVNIC_BUFFER_HLEN);
+
+ if ((adapter->req_mtu + IBMVNIC_BUFFER_HLEN) *
+ adapter->desired->tx_entries > IBMVNIC_MAX_LTB_SIZE) {
+ adapter->desired->tx_entries = max_entries;
+ }
+
+ if ((adapter->req_mtu + IBMVNIC_BUFFER_HLEN) *
+ adapter->desired->rx_entries > IBMVNIC_MAX_LTB_SIZE) {
+ adapter->desired->rx_entries = max_entries;
+ }
- adapter->req_mtu = adapter->netdev->mtu + ETH_HLEN;
+ if (adapter->desired->tx_entries)
+ adapter->req_tx_entries_per_subcrq =
+ adapter->desired->tx_entries;
+ else
+ adapter->req_tx_entries_per_subcrq =
+ adapter->max_tx_entries_per_subcrq;
+
+ if (adapter->desired->rx_entries)
+ adapter->req_rx_add_entries_per_subcrq =
+ adapter->desired->rx_entries;
+ else
+ adapter->req_rx_add_entries_per_subcrq =
+ adapter->max_rx_add_entries_per_subcrq;
+
+ if (adapter->desired->tx_queues)
+ adapter->req_tx_queues =
+ adapter->desired->tx_queues;
+ else
+ adapter->req_tx_queues =
+ adapter->opt_tx_comp_sub_queues;
+
+ if (adapter->desired->rx_queues)
+ adapter->req_rx_queues =
+ adapter->desired->rx_queues;
+ else
+ adapter->req_rx_queues =
+ adapter->opt_rx_comp_queues;
+
+ adapter->req_rx_add_queues = adapter->max_rx_add_queues;
}
memset(&crq, 0, sizeof(crq));
@@ -3211,6 +3359,7 @@ static int handle_login_rsp(union ibmvnic_crq *login_rsp_crq,
struct ibmvnic_adapter *adapter)
{
struct device *dev = &adapter->vdev->dev;
+ struct net_device *netdev = adapter->netdev;
struct ibmvnic_login_rsp_buffer *login_rsp = adapter->login_rsp_buf;
struct ibmvnic_login_buffer *login = adapter->login_buf;
int i;
@@ -3230,6 +3379,8 @@ static int handle_login_rsp(union ibmvnic_crq *login_rsp_crq,
return 0;
}
+ netdev->mtu = adapter->req_mtu - ETH_HLEN;
+
netdev_dbg(adapter->netdev, "Login Response Buffer:\n");
for (i = 0; i < (adapter->login_rsp_buf_sz - 1) / 8 + 1; i++) {
netdev_dbg(adapter->netdev, "%016lx\n",
@@ -3785,7 +3936,7 @@ static int ibmvnic_init(struct ibmvnic_adapter *adapter)
unsigned long timeout = msecs_to_jiffies(30000);
int rc;
- if (adapter->resetting) {
+ if (adapter->resetting && !adapter->wait_for_reset) {
rc = ibmvnic_reset_crq(adapter);
if (!rc)
rc = vio_enable_interrupts(adapter->vdev);
@@ -3819,7 +3970,7 @@ static int ibmvnic_init(struct ibmvnic_adapter *adapter)
return -1;
}
- if (adapter->resetting)
+ if (adapter->resetting && !adapter->wait_for_reset)
rc = reset_sub_crq_queues(adapter);
else
rc = init_sub_crqs(adapter);
@@ -3870,6 +4021,11 @@ static int ibmvnic_probe(struct vio_dev *dev, const struct vio_device_id *id)
adapter->vdev = dev;
adapter->netdev = netdev;
+ adapter->desired = kzalloc(sizeof(*adapter->desired), GFP_KERNEL);
+ adapter->desired->mac = kzalloc(sizeof(*adapter->desired->mac),
+ GFP_KERNEL);
+ adapter->fallback = kzalloc(sizeof(*adapter->fallback), GFP_KERNEL);
+
ether_addr_copy(adapter->mac_addr, mac_addr_p);
ether_addr_copy(netdev->dev_addr, adapter->mac_addr);
netdev->irq = dev->irq;
@@ -3895,6 +4051,8 @@ static int ibmvnic_probe(struct vio_dev *dev, const struct vio_device_id *id)
} while (rc == EAGAIN);
netdev->mtu = adapter->req_mtu - ETH_HLEN;
+ netdev->min_mtu = adapter->min_mtu - ETH_HLEN;
+ netdev->max_mtu = adapter->max_mtu - ETH_HLEN;
rc = device_create_file(&dev->dev, &dev_attr_failover);
if (rc)
@@ -3909,6 +4067,9 @@ static int ibmvnic_probe(struct vio_dev *dev, const struct vio_device_id *id)
dev_info(&dev->dev, "ibmvnic registered\n");
adapter->state = VNIC_PROBED;
+
+ adapter->wait_for_reset = false;
+
return 0;
ibmvnic_register_fail:
@@ -3932,6 +4093,11 @@ static int ibmvnic_remove(struct vio_dev *dev)
mutex_lock(&adapter->reset_lock);
release_resources(adapter);
+
+ kfree(adapter->desired->mac);
+ kfree(adapter->desired);
+ kfree(adapter->fallback);
+
release_sub_crqs(adapter);
release_crq_queue(adapter);
diff --git a/drivers/net/ethernet/ibm/ibmvnic.h b/drivers/net/ethernet/ibm/ibmvnic.h
index d02257c..5347a7c 100644
--- a/drivers/net/ethernet/ibm/ibmvnic.h
+++ b/drivers/net/ethernet/ibm/ibmvnic.h
@@ -38,7 +38,8 @@
/* when changing this, update IBMVNIC_IO_ENTITLEMENT_DEFAULT */
#define IBMVNIC_BUFFS_PER_POOL 100
#define IBMVNIC_MAX_TX_QUEUES 5
-
+#define IBMVNIC_MAX_LTB_SIZE ((1 << (MAX_ORDER - 1)) * PAGE_SIZE)
+#define IBMVNIC_BUFFER_HLEN 500
struct ibmvnic_login_buffer {
__be32 len;
__be32 version;
@@ -940,13 +941,23 @@ enum ibmvnic_reset_reason {VNIC_RESET_FAILOVER = 1,
VNIC_RESET_MOBILITY,
VNIC_RESET_FATAL,
VNIC_RESET_NON_FATAL,
- VNIC_RESET_TIMEOUT};
+ VNIC_RESET_TIMEOUT,
+ VNIC_RESET_CHANGE_PARAM};
struct ibmvnic_rwi {
enum ibmvnic_reset_reason reset_reason;
struct list_head list;
};
+struct ibmvnic_tunables {
+ u64 rx_queues;
+ u64 tx_queues;
+ u64 rx_entries;
+ u64 tx_entries;
+ u64 mtu;
+ struct sockaddr *mac;
+};
+
struct ibmvnic_adapter {
struct vio_dev *vdev;
struct net_device *netdev;
@@ -1007,6 +1018,10 @@ struct ibmvnic_adapter {
struct completion fw_done;
int fw_done_rc;
+ struct completion reset_done;
+ int reset_done_rc;
+ bool wait_for_reset;
+
/* partner capabilities */
u64 min_tx_queues;
u64 min_rx_queues;
@@ -1051,4 +1066,7 @@ struct ibmvnic_adapter {
struct work_struct ibmvnic_reset;
bool resetting;
bool napi_enabled, from_passive_init;
+
+ struct ibmvnic_tunables *desired;
+ struct ibmvnic_tunables *fallback;
};
^ permalink raw reply related [flat|nested] 4+ messages in thread
* [PATCH net-next 2/2] ibmvnic: Fix failover error path for non-fatal resets
2017-10-20 21:00 [PATCH net-next 0/2] ibmvnic: Tunable parameter support John Allen
2017-10-20 21:02 ` [PATCH net-next 1/2] ibmvnic: Update reset infrastructure to support tunable parameters John Allen
@ 2017-10-20 21:03 ` John Allen
2017-10-22 2:16 ` [PATCH net-next 0/2] ibmvnic: Tunable parameter support David Miller
2 siblings, 0 replies; 4+ messages in thread
From: John Allen @ 2017-10-20 21:03 UTC (permalink / raw)
To: netdev, Thomas Falcon, Nathan Fontenot
For all non-fatal reset conditions, the hypervisor will send a failover when
we attempt to initialize the crq and the vnic client is expected to handle
that failover instead of the existing non-fatal reset. To handle this, we
need to return from init with a return code that indicates that we have hit
this case.
Signed-off-by: John Allen <jallen@linux.vnet.ibm.com>
---
diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c
index ebbb083..c914d5a 100644
--- a/drivers/net/ethernet/ibm/ibmvnic.c
+++ b/drivers/net/ethernet/ibm/ibmvnic.c
@@ -1452,7 +1452,7 @@ static int do_reset(struct ibmvnic_adapter *adapter,
rc = ibmvnic_init(adapter);
if (rc)
- return 0;
+ return IBMVNIC_INIT_FAILED;
/* If the adapter was in PROBE state prior to the reset,
* exit here.
@@ -1555,7 +1555,7 @@ static void __ibmvnic_reset(struct work_struct *work)
while (rwi) {
rc = do_reset(adapter, rwi, reset_state);
kfree(rwi);
- if (rc)
+ if (rc && rc != IBMVNIC_INIT_FAILED)
break;
rwi = get_next_rwi(adapter);
diff --git a/drivers/net/ethernet/ibm/ibmvnic.h b/drivers/net/ethernet/ibm/ibmvnic.h
index 5347a7c..46eed65 100644
--- a/drivers/net/ethernet/ibm/ibmvnic.h
+++ b/drivers/net/ethernet/ibm/ibmvnic.h
@@ -30,6 +30,8 @@
#define IBMVNIC_DRIVER_VERSION "1.0.1"
#define IBMVNIC_INVALID_MAP -1
#define IBMVNIC_STATS_TIMEOUT 1
+#define IBMVNIC_INIT_FAILED 2
+
/* basic structures plus 100 2k buffers */
#define IBMVNIC_IO_ENTITLEMENT_DEFAULT 610305
^ permalink raw reply related [flat|nested] 4+ messages in thread
* Re: [PATCH net-next 0/2] ibmvnic: Tunable parameter support
2017-10-20 21:00 [PATCH net-next 0/2] ibmvnic: Tunable parameter support John Allen
2017-10-20 21:02 ` [PATCH net-next 1/2] ibmvnic: Update reset infrastructure to support tunable parameters John Allen
2017-10-20 21:03 ` [PATCH net-next 2/2] ibmvnic: Fix failover error path for non-fatal resets John Allen
@ 2017-10-22 2:16 ` David Miller
2 siblings, 0 replies; 4+ messages in thread
From: David Miller @ 2017-10-22 2:16 UTC (permalink / raw)
To: jallen; +Cc: netdev, tlfalcon, nfont
From: John Allen <jallen@linux.vnet.ibm.com>
Date: Fri, 20 Oct 2017 16:00:54 -0500
> This series implements support for changing tunable parameters such as the
> mtu, number of tx/rx queues, and number of buffers per queue via ethtool
> and ifconfig.
These patches do not apply to net-next.
^ permalink raw reply [flat|nested] 4+ messages in thread
end of thread, other threads:[~2017-10-22 2:16 UTC | newest]
Thread overview: 4+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2017-10-20 21:00 [PATCH net-next 0/2] ibmvnic: Tunable parameter support John Allen
2017-10-20 21:02 ` [PATCH net-next 1/2] ibmvnic: Update reset infrastructure to support tunable parameters John Allen
2017-10-20 21:03 ` [PATCH net-next 2/2] ibmvnic: Fix failover error path for non-fatal resets John Allen
2017-10-22 2:16 ` [PATCH net-next 0/2] ibmvnic: Tunable parameter support David Miller
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).