* Re: [PATCH v6 net-next 04/19] ionic: Add port management commands
From: Jakub Kicinski @ 2019-08-29 22:46 UTC (permalink / raw)
To: Shannon Nelson; +Cc: netdev, davem
In-Reply-To: <20190829182720.68419-5-snelson@pensando.io>
On Thu, 29 Aug 2019 11:27:05 -0700, Shannon Nelson wrote:
> The port management commands apply to the physical port
> associated with the PCI device, which might be shared among
> several logical interfaces.
>
> Signed-off-by: Shannon Nelson <snelson@pensando.io>
> ---
> drivers/net/ethernet/pensando/ionic/ionic.h | 4 +
> .../ethernet/pensando/ionic/ionic_bus_pci.c | 16 ++++
> .../net/ethernet/pensando/ionic/ionic_dev.c | 92 +++++++++++++++++++
> .../net/ethernet/pensando/ionic/ionic_dev.h | 13 +++
> .../net/ethernet/pensando/ionic/ionic_main.c | 86 +++++++++++++++++
> 5 files changed, 211 insertions(+)
>
> diff --git a/drivers/net/ethernet/pensando/ionic/ionic.h b/drivers/net/ethernet/pensando/ionic/ionic.h
> index 89ad9c590736..4960effd2bcc 100644
> --- a/drivers/net/ethernet/pensando/ionic/ionic.h
> +++ b/drivers/net/ethernet/pensando/ionic/ionic.h
> @@ -42,4 +42,8 @@ int ionic_identify(struct ionic *ionic);
> int ionic_init(struct ionic *ionic);
> int ionic_reset(struct ionic *ionic);
>
> +int ionic_port_identify(struct ionic *ionic);
> +int ionic_port_init(struct ionic *ionic);
> +int ionic_port_reset(struct ionic *ionic);
> +
> #endif /* _IONIC_H_ */
> diff --git a/drivers/net/ethernet/pensando/ionic/ionic_bus_pci.c b/drivers/net/ethernet/pensando/ionic/ionic_bus_pci.c
> index 286b4b450a73..804dd43e92a6 100644
> --- a/drivers/net/ethernet/pensando/ionic/ionic_bus_pci.c
> +++ b/drivers/net/ethernet/pensando/ionic/ionic_bus_pci.c
> @@ -138,12 +138,27 @@ static int ionic_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
> goto err_out_teardown;
> }
>
> + /* Configure the ports */
> + err = ionic_port_identify(ionic);
> + if (err) {
> + dev_err(dev, "Cannot identify port: %d, aborting\n", err);
> + goto err_out_reset;
> + }
> +
> + err = ionic_port_init(ionic);
> + if (err) {
> + dev_err(dev, "Cannot init port: %d, aborting\n", err);
> + goto err_out_reset;
> + }
> +
> err = ionic_devlink_register(ionic);
> if (err)
> dev_err(dev, "Cannot register devlink: %d\n", err);
>
> return 0;
>
> +err_out_reset:
> + ionic_reset(ionic);
> err_out_teardown:
> ionic_dev_teardown(ionic);
> err_out_unmap_bars:
> @@ -170,6 +185,7 @@ static void ionic_remove(struct pci_dev *pdev)
> return;
>
> ionic_devlink_unregister(ionic);
> + ionic_port_reset(ionic);
> ionic_reset(ionic);
> ionic_dev_teardown(ionic);
> ionic_unmap_bars(ionic);
> diff --git a/drivers/net/ethernet/pensando/ionic/ionic_dev.c b/drivers/net/ethernet/pensando/ionic/ionic_dev.c
> index 0bf1bd6bd7b1..3137776e9191 100644
> --- a/drivers/net/ethernet/pensando/ionic/ionic_dev.c
> +++ b/drivers/net/ethernet/pensando/ionic/ionic_dev.c
> @@ -134,3 +134,95 @@ void ionic_dev_cmd_reset(struct ionic_dev *idev)
>
> ionic_dev_cmd_go(idev, &cmd);
> }
> +
> +/* Port commands */
> +void ionic_dev_cmd_port_identify(struct ionic_dev *idev)
> +{
> + union ionic_dev_cmd cmd = {
> + .port_init.opcode = IONIC_CMD_PORT_IDENTIFY,
> + .port_init.index = 0,
> + };
> +
> + ionic_dev_cmd_go(idev, &cmd);
> +}
> +
> +void ionic_dev_cmd_port_init(struct ionic_dev *idev)
> +{
> + union ionic_dev_cmd cmd = {
> + .port_init.opcode = IONIC_CMD_PORT_INIT,
> + .port_init.index = 0,
> + .port_init.info_pa = cpu_to_le64(idev->port_info_pa),
> + };
> +
> + ionic_dev_cmd_go(idev, &cmd);
> +}
> +
> +void ionic_dev_cmd_port_reset(struct ionic_dev *idev)
> +{
> + union ionic_dev_cmd cmd = {
> + .port_reset.opcode = IONIC_CMD_PORT_RESET,
> + .port_reset.index = 0,
> + };
> +
> + ionic_dev_cmd_go(idev, &cmd);
> +}
> +
> +void ionic_dev_cmd_port_state(struct ionic_dev *idev, u8 state)
> +{
> + union ionic_dev_cmd cmd = {
> + .port_setattr.opcode = IONIC_CMD_PORT_SETATTR,
> + .port_setattr.index = 0,
> + .port_setattr.attr = IONIC_PORT_ATTR_STATE,
> + .port_setattr.state = state,
> + };
> +
> + ionic_dev_cmd_go(idev, &cmd);
> +}
> +
> +void ionic_dev_cmd_port_speed(struct ionic_dev *idev, u32 speed)
> +{
> + union ionic_dev_cmd cmd = {
> + .port_setattr.opcode = IONIC_CMD_PORT_SETATTR,
> + .port_setattr.index = 0,
> + .port_setattr.attr = IONIC_PORT_ATTR_SPEED,
> + .port_setattr.speed = cpu_to_le32(speed),
> + };
> +
> + ionic_dev_cmd_go(idev, &cmd);
> +}
> +
> +void ionic_dev_cmd_port_autoneg(struct ionic_dev *idev, u8 an_enable)
> +{
> + union ionic_dev_cmd cmd = {
> + .port_setattr.opcode = IONIC_CMD_PORT_SETATTR,
> + .port_setattr.index = 0,
> + .port_setattr.attr = IONIC_PORT_ATTR_AUTONEG,
> + .port_setattr.an_enable = an_enable,
> + };
> +
> + ionic_dev_cmd_go(idev, &cmd);
> +}
> +
> +void ionic_dev_cmd_port_fec(struct ionic_dev *idev, u8 fec_type)
> +{
> + union ionic_dev_cmd cmd = {
> + .port_setattr.opcode = IONIC_CMD_PORT_SETATTR,
> + .port_setattr.index = 0,
> + .port_setattr.attr = IONIC_PORT_ATTR_FEC,
> + .port_setattr.fec_type = fec_type,
> + };
> +
> + ionic_dev_cmd_go(idev, &cmd);
> +}
> +
> +void ionic_dev_cmd_port_pause(struct ionic_dev *idev, u8 pause_type)
> +{
> + union ionic_dev_cmd cmd = {
> + .port_setattr.opcode = IONIC_CMD_PORT_SETATTR,
> + .port_setattr.index = 0,
> + .port_setattr.attr = IONIC_PORT_ATTR_PAUSE,
> + .port_setattr.pause_type = pause_type,
> + };
> +
> + ionic_dev_cmd_go(idev, &cmd);
> +}
Hm. So you haven't moved those?
> diff --git a/drivers/net/ethernet/pensando/ionic/ionic_dev.h b/drivers/net/ethernet/pensando/ionic/ionic_dev.h
> index 7050545a83aa..81b6910aabc1 100644
> --- a/drivers/net/ethernet/pensando/ionic/ionic_dev.h
> +++ b/drivers/net/ethernet/pensando/ionic/ionic_dev.h
> @@ -117,6 +117,10 @@ struct ionic_dev {
> struct ionic_intr __iomem *intr_ctrl;
> u64 __iomem *intr_status;
>
> + u32 port_info_sz;
> + struct ionic_port_info *port_info;
> + dma_addr_t port_info_pa;
> +
> struct ionic_devinfo dev_info;
> };
>
> @@ -135,4 +139,13 @@ void ionic_dev_cmd_identify(struct ionic_dev *idev, u8 ver);
> void ionic_dev_cmd_init(struct ionic_dev *idev);
> void ionic_dev_cmd_reset(struct ionic_dev *idev);
>
> +void ionic_dev_cmd_port_identify(struct ionic_dev *idev);
> +void ionic_dev_cmd_port_init(struct ionic_dev *idev);
> +void ionic_dev_cmd_port_reset(struct ionic_dev *idev);
> +void ionic_dev_cmd_port_state(struct ionic_dev *idev, u8 state);
> +void ionic_dev_cmd_port_speed(struct ionic_dev *idev, u32 speed);
> +void ionic_dev_cmd_port_autoneg(struct ionic_dev *idev, u8 an_enable);
> +void ionic_dev_cmd_port_fec(struct ionic_dev *idev, u8 fec_type);
> +void ionic_dev_cmd_port_pause(struct ionic_dev *idev, u8 pause_type);
> +
> #endif /* _IONIC_DEV_H_ */
> diff --git a/drivers/net/ethernet/pensando/ionic/ionic_main.c b/drivers/net/ethernet/pensando/ionic/ionic_main.c
> index 5c311b9241ee..96de2789587d 100644
> --- a/drivers/net/ethernet/pensando/ionic/ionic_main.c
> +++ b/drivers/net/ethernet/pensando/ionic/ionic_main.c
> @@ -317,6 +317,92 @@ int ionic_reset(struct ionic *ionic)
> return err;
> }
>
> +int ionic_port_identify(struct ionic *ionic)
> +{
> + struct ionic_identity *ident = &ionic->ident;
> + struct ionic_dev *idev = &ionic->idev;
> + size_t sz;
> + int err;
> +
> + mutex_lock(&ionic->dev_cmd_lock);
> +
> + ionic_dev_cmd_port_identify(idev);
> + err = ionic_dev_cmd_wait(ionic, DEVCMD_TIMEOUT);
> + if (!err) {
> + sz = min(sizeof(ident->port), sizeof(idev->dev_cmd_regs->data));
> + memcpy_fromio(&ident->port, &idev->dev_cmd_regs->data, sz);
> + }
> +
> + mutex_unlock(&ionic->dev_cmd_lock);
> +
> + return err;
> +}
> +
> +int ionic_port_init(struct ionic *ionic)
> +{
> + struct ionic_identity *ident = &ionic->ident;
> + struct ionic_dev *idev = &ionic->idev;
> + size_t sz;
> + int err;
> +
> + if (idev->port_info)
> + return 0;
> +
> + idev->port_info_sz = ALIGN(sizeof(*idev->port_info), PAGE_SIZE);
> + idev->port_info = dma_alloc_coherent(ionic->dev, idev->port_info_sz,
> + &idev->port_info_pa,
> + GFP_KERNEL);
> + if (!idev->port_info) {
> + dev_err(ionic->dev, "Failed to allocate port info, aborting\n");
> + return -ENOMEM;
> + }
> +
> + sz = min(sizeof(ident->port.config), sizeof(idev->dev_cmd_regs->data));
> +
> + mutex_lock(&ionic->dev_cmd_lock);
> +
> + memcpy_toio(&idev->dev_cmd_regs->data, &ident->port.config, sz);
> + ionic_dev_cmd_port_init(idev);
> + err = ionic_dev_cmd_wait(ionic, DEVCMD_TIMEOUT);
> +
> + ionic_dev_cmd_port_state(&ionic->idev, IONIC_PORT_ADMIN_STATE_UP);
> + (void)ionic_dev_cmd_wait(ionic, DEVCMD_TIMEOUT);
> +
> + mutex_unlock(&ionic->dev_cmd_lock);
> + if (err) {
> + dev_err(ionic->dev, "Failed to init port\n");
> + dma_free_coherent(ionic->dev, idev->port_info_sz,
> + idev->port_info, idev->port_info_pa);
idev->port_info = NULL;
> + }
> +
> + return err;
> +}
> +
> +int ionic_port_reset(struct ionic *ionic)
> +{
> + struct ionic_dev *idev = &ionic->idev;
> + int err;
> +
> + if (!idev->port_info)
> + return 0;
> +
> + mutex_lock(&ionic->dev_cmd_lock);
> + ionic_dev_cmd_port_reset(idev);
> + err = ionic_dev_cmd_wait(ionic, DEVCMD_TIMEOUT);
> + mutex_unlock(&ionic->dev_cmd_lock);
> +
> + dma_free_coherent(ionic->dev, idev->port_info_sz,
> + idev->port_info, idev->port_info_pa);
> +
> + idev->port_info = NULL;
> + idev->port_info_pa = 0;
> +
> + if (err)
> + dev_err(ionic->dev, "Failed to reset port\n");
> +
> + return err;
> +}
> +
> static int __init ionic_init_module(void)
> {
> pr_info("%s %s, ver %s\n",
^ permalink raw reply
* Re: [RESEND PATCH 1/5] dt-bindings: net: Add compatible for BCM4345C5 bluetooth device
From: Rob Herring @ 2019-08-29 22:45 UTC (permalink / raw)
To: megous
Cc: Maxime Ripard, Chen-Yu Tsai, Marcel Holtmann, Johan Hedberg,
Mark Rutland, David S. Miller, netdev, devicetree, linux-kernel,
linux-arm-kernel, linux-bluetooth, Ondrej Jirman
In-Reply-To: <20190823103139.17687-2-megous@megous.com>
On Fri, 23 Aug 2019 12:31:35 +0200, megous@megous.com wrote:
> From: Ondrej Jirman <megous@megous.com>
>
> This is present in the AP6526 WiFi/Bluetooth 5.0 module.
>
> Signed-off-by: Ondrej Jirman <megous@megous.com>
> ---
> Documentation/devicetree/bindings/net/broadcom-bluetooth.txt | 1 +
> 1 file changed, 1 insertion(+)
>
Acked-by: Rob Herring <robh@kernel.org>
^ permalink raw reply
* Re: [PATCH] ipv6: Not to probe neighbourless routes
From: kbuild test robot @ 2019-08-29 22:42 UTC (permalink / raw)
To: Yi Wang
Cc: kbuild-all, davem, kuznet, yoshfuji, netdev, linux-kernel,
xue.zhihong, wang.yi59, wang.liang82, Cheng Lin
In-Reply-To: <1566896907-5121-1-git-send-email-wang.yi59@zte.com.cn>
[-- Warning: decoded text below may be mangled, UTF-8 assumed --]
[-- Attachment #1: Type: text/plain; charset=unknown-8bit, Size: 6132 bytes --]
Hi Yi,
Thank you for the patch! Yet something to improve:
[auto build test ERROR on linus/master]
[cannot apply to v5.3-rc6 next-20190829]
[if your patch is applied to the wrong git tree, please drop us a note to help improve the system]
url: https://github.com/0day-ci/linux/commits/Yi-Wang/ipv6-Not-to-probe-neighbourless-routes/20190830-025439
config: x86_64-allyesconfig (attached as .config)
compiler: gcc-7 (Debian 7.4.0-11) 7.4.0
reproduce:
# save the attached .config to linux build tree
make ARCH=x86_64
If you fix the issue, kindly add following tag
Reported-by: kbuild test robot <lkp@intel.com>
All errors (new ones prefixed by >>):
net/ipv6/route.c: In function 'rt6_probe':
>> net/ipv6/route.c:660:10: error: 'struct fib6_nh' has no member named 'last_probe'
fib6_nh->last_probe = jiffies;
^~
vim +660 net/ipv6/route.c
c2f17e827b4199 Hannes Frederic Sowa 2013-10-21 619
cc3a86c802f0ba David Ahern 2019-04-09 620 static void rt6_probe(struct fib6_nh *fib6_nh)
270972554c91ac YOSHIFUJI Hideaki 2006-03-20 621 {
f547fac624be53 Sabrina Dubroca 2018-10-12 622 struct __rt6_probe_work *work = NULL;
5e670d844b2a4e David Ahern 2018-04-17 623 const struct in6_addr *nh_gw;
f2c31e32b378a6 Eric Dumazet 2011-07-29 624 struct neighbour *neigh;
5e670d844b2a4e David Ahern 2018-04-17 625 struct net_device *dev;
f547fac624be53 Sabrina Dubroca 2018-10-12 626 struct inet6_dev *idev;
5e670d844b2a4e David Ahern 2018-04-17 627
270972554c91ac YOSHIFUJI Hideaki 2006-03-20 628 /*
270972554c91ac YOSHIFUJI Hideaki 2006-03-20 629 * Okay, this does not seem to be appropriate
270972554c91ac YOSHIFUJI Hideaki 2006-03-20 630 * for now, however, we need to check if it
270972554c91ac YOSHIFUJI Hideaki 2006-03-20 631 * is really so; aka Router Reachability Probing.
270972554c91ac YOSHIFUJI Hideaki 2006-03-20 632 *
270972554c91ac YOSHIFUJI Hideaki 2006-03-20 633 * Router Reachability Probe MUST be rate-limited
270972554c91ac YOSHIFUJI Hideaki 2006-03-20 634 * to no more than one per minute.
270972554c91ac YOSHIFUJI Hideaki 2006-03-20 635 */
cc3a86c802f0ba David Ahern 2019-04-09 636 if (fib6_nh->fib_nh_gw_family)
7ff74a596b6aa4 YOSHIFUJI Hideaki / 吉藤英明 2013-01-17 637 return;
5e670d844b2a4e David Ahern 2018-04-17 638
cc3a86c802f0ba David Ahern 2019-04-09 639 nh_gw = &fib6_nh->fib_nh_gw6;
cc3a86c802f0ba David Ahern 2019-04-09 640 dev = fib6_nh->fib_nh_dev;
2152caea719657 YOSHIFUJI Hideaki / 吉藤英明 2013-01-17 641 rcu_read_lock_bh();
5e670d844b2a4e David Ahern 2018-04-17 642 neigh = __ipv6_neigh_lookup_noref(dev, nh_gw);
2152caea719657 YOSHIFUJI Hideaki / 吉藤英明 2013-01-17 643 if (neigh) {
8d6c31bf574177 Martin KaFai Lau 2015-07-24 644 if (neigh->nud_state & NUD_VALID)
8d6c31bf574177 Martin KaFai Lau 2015-07-24 645 goto out;
8d6c31bf574177 Martin KaFai Lau 2015-07-24 646
e3f0c73ec3f208 Cheng Lin 2019-08-27 647 idev = __in6_dev_get(dev);
2152caea719657 YOSHIFUJI Hideaki / 吉藤英明 2013-01-17 648 write_lock(&neigh->lock);
990edb428c2c85 Martin KaFai Lau 2015-07-24 649 if (!(neigh->nud_state & NUD_VALID) &&
990edb428c2c85 Martin KaFai Lau 2015-07-24 650 time_after(jiffies,
dcd1f572954f9d David Ahern 2018-04-18 651 neigh->updated + idev->cnf.rtr_probe_interval)) {
c2f17e827b4199 Hannes Frederic Sowa 2013-10-21 652 work = kmalloc(sizeof(*work), GFP_ATOMIC);
990edb428c2c85 Martin KaFai Lau 2015-07-24 653 if (work)
7e980569642811 Jiri Benc 2013-12-11 654 __neigh_set_probe_once(neigh);
990edb428c2c85 Martin KaFai Lau 2015-07-24 655 }
2152caea719657 YOSHIFUJI Hideaki / 吉藤英明 2013-01-17 656 write_unlock(&neigh->lock);
990edb428c2c85 Martin KaFai Lau 2015-07-24 657 }
2152caea719657 YOSHIFUJI Hideaki / 吉藤英明 2013-01-17 658
c2f17e827b4199 Hannes Frederic Sowa 2013-10-21 659 if (work) {
cc3a86c802f0ba David Ahern 2019-04-09 @660 fib6_nh->last_probe = jiffies;
c2f17e827b4199 Hannes Frederic Sowa 2013-10-21 661 INIT_WORK(&work->work, rt6_probe_deferred);
5e670d844b2a4e David Ahern 2018-04-17 662 work->target = *nh_gw;
5e670d844b2a4e David Ahern 2018-04-17 663 dev_hold(dev);
5e670d844b2a4e David Ahern 2018-04-17 664 work->dev = dev;
c2f17e827b4199 Hannes Frederic Sowa 2013-10-21 665 schedule_work(&work->work);
c2f17e827b4199 Hannes Frederic Sowa 2013-10-21 666 }
990edb428c2c85 Martin KaFai Lau 2015-07-24 667
8d6c31bf574177 Martin KaFai Lau 2015-07-24 668 out:
2152caea719657 YOSHIFUJI Hideaki / 吉藤英明 2013-01-17 669 rcu_read_unlock_bh();
f2c31e32b378a6 Eric Dumazet 2011-07-29 670 }
270972554c91ac YOSHIFUJI Hideaki 2006-03-20 671 #else
cc3a86c802f0ba David Ahern 2019-04-09 672 static inline void rt6_probe(struct fib6_nh *fib6_nh)
270972554c91ac YOSHIFUJI Hideaki 2006-03-20 673 {
270972554c91ac YOSHIFUJI Hideaki 2006-03-20 674 }
270972554c91ac YOSHIFUJI Hideaki 2006-03-20 675 #endif
270972554c91ac YOSHIFUJI Hideaki 2006-03-20 676
:::::: The code at line 660 was first introduced by commit
:::::: cc3a86c802f0ba9a2627aef256d95ae3b3fa6e91 ipv6: Change rt6_probe to take a fib6_nh
:::::: TO: David Ahern <dsahern@gmail.com>
:::::: CC: David S. Miller <davem@davemloft.net>
---
0-DAY kernel test infrastructure Open Source Technology Center
https://lists.01.org/pipermail/kbuild-all Intel Corporation
[-- Attachment #2: .config.gz --]
[-- Type: application/gzip, Size: 69510 bytes --]
^ permalink raw reply
* Re: [PATCH v6 net-next 02/19] ionic: Add basic framework for IONIC Network device driver
From: Jakub Kicinski @ 2019-08-29 22:38 UTC (permalink / raw)
To: Shannon Nelson; +Cc: netdev, davem
In-Reply-To: <20190829182720.68419-3-snelson@pensando.io>
On Thu, 29 Aug 2019 11:27:03 -0700, Shannon Nelson wrote:
> This patch adds a basic driver framework for the Pensando IONIC
> network device. There is no functionality right now other than
> the ability to load and unload.
>
> Signed-off-by: Shannon Nelson <snelson@pensando.io>
> diff --git a/drivers/net/ethernet/pensando/ionic/ionic_devlink.c b/drivers/net/ethernet/pensando/ionic/ionic_devlink.c
> new file mode 100644
> index 000000000000..6892409cd64b
> --- /dev/null
> +++ b/drivers/net/ethernet/pensando/ionic/ionic_devlink.c
> @@ -0,0 +1,44 @@
> +// SPDX-License-Identifier: GPL-2.0
> +/* Copyright(c) 2017 - 2019 Pensando Systems, Inc */
> +
> +#include <linux/module.h>
> +#include <linux/netdevice.h>
> +
> +#include "ionic.h"
> +#include "ionic_bus.h"
> +#include "ionic_devlink.h"
> +
> +static int ionic_dl_info_get(struct devlink *dl, struct devlink_info_req *req,
> + struct netlink_ext_ack *extack)
> +{
> + devlink_info_driver_name_put(req, IONIC_DRV_NAME);
This may fail, should the error not be propagated?
> + return 0;
> +}
> +
> +static const struct devlink_ops ionic_dl_ops = {
> + .info_get = ionic_dl_info_get,
> +};
> +
> +struct ionic *ionic_devlink_alloc(struct device *dev)
> +{
> + struct ionic *ionic;
> + struct devlink *dl;
> +
> + dl = devlink_alloc(&ionic_dl_ops, sizeof(struct ionic));
> + if (!dl) {
> + dev_warn(dev, "devlink_alloc failed");
missing new line at the end of warning, but the warning is unnecessary,
if memory allocation fails kernel will generate a big OOM splat, anyway
> + return NULL;
> + }
> +
> + ionic = devlink_priv(dl);
> +
> + return ionic;
return devlink_priv(dl);
> +}
> +
> +void ionic_devlink_free(struct ionic *ionic)
> +{
> + struct devlink *dl = priv_to_devlink(ionic);
> +
> + devlink_free(dl);
> +}
^ permalink raw reply
* Re: [PATCH v6 net-next 01/19] devlink: Add new info version tags for ASIC and FW
From: Jakub Kicinski @ 2019-08-29 22:33 UTC (permalink / raw)
To: Shannon Nelson; +Cc: netdev, davem, Jiri Pirko
In-Reply-To: <20190829182720.68419-2-snelson@pensando.io>
On Thu, 29 Aug 2019 11:27:02 -0700, Shannon Nelson wrote:
> The current tag set is still rather small and needs a couple
> more tags to help with ASIC identification and to have a
> more generic FW version.
>
> Cc: Jakub Kicinski <jakub.kicinski@netronome.com>
> Cc: Jiri Pirko <jiri@resnulli.us>
> Signed-off-by: Shannon Nelson <snelson@pensando.io>
Acked-by: Jakub Kicinski <jakub.kicinski@netronome.com>
^ permalink raw reply
* Re: [PATCH] ipv6: Not to probe neighbourless routes
From: kbuild test robot @ 2019-08-29 22:20 UTC (permalink / raw)
To: Yi Wang
Cc: kbuild-all, davem, kuznet, yoshfuji, netdev, linux-kernel,
xue.zhihong, wang.yi59, wang.liang82, Cheng Lin
In-Reply-To: <1566896907-5121-1-git-send-email-wang.yi59@zte.com.cn>
[-- Warning: decoded text below may be mangled, UTF-8 assumed --]
[-- Attachment #1: Type: text/plain; charset=unknown-8bit, Size: 6124 bytes --]
Hi Yi,
Thank you for the patch! Yet something to improve:
[auto build test ERROR on linus/master]
[cannot apply to v5.3-rc6 next-20190829]
[if your patch is applied to the wrong git tree, please drop us a note to help improve the system]
url: https://github.com/0day-ci/linux/commits/Yi-Wang/ipv6-Not-to-probe-neighbourless-routes/20190830-025439
config: x86_64-rhel (attached as .config)
compiler: gcc-7 (Debian 7.4.0-11) 7.4.0
reproduce:
# save the attached .config to linux build tree
make ARCH=x86_64
If you fix the issue, kindly add following tag
Reported-by: kbuild test robot <lkp@intel.com>
All errors (new ones prefixed by >>):
net/ipv6/route.c: In function 'rt6_probe':
>> net/ipv6/route.c:660:10: error: 'struct fib6_nh' has no member named 'last_probe'
fib6_nh->last_probe = jiffies;
^~
vim +660 net/ipv6/route.c
c2f17e827b4199 Hannes Frederic Sowa 2013-10-21 619
cc3a86c802f0ba David Ahern 2019-04-09 620 static void rt6_probe(struct fib6_nh *fib6_nh)
270972554c91ac YOSHIFUJI Hideaki 2006-03-20 621 {
f547fac624be53 Sabrina Dubroca 2018-10-12 622 struct __rt6_probe_work *work = NULL;
5e670d844b2a4e David Ahern 2018-04-17 623 const struct in6_addr *nh_gw;
f2c31e32b378a6 Eric Dumazet 2011-07-29 624 struct neighbour *neigh;
5e670d844b2a4e David Ahern 2018-04-17 625 struct net_device *dev;
f547fac624be53 Sabrina Dubroca 2018-10-12 626 struct inet6_dev *idev;
5e670d844b2a4e David Ahern 2018-04-17 627
270972554c91ac YOSHIFUJI Hideaki 2006-03-20 628 /*
270972554c91ac YOSHIFUJI Hideaki 2006-03-20 629 * Okay, this does not seem to be appropriate
270972554c91ac YOSHIFUJI Hideaki 2006-03-20 630 * for now, however, we need to check if it
270972554c91ac YOSHIFUJI Hideaki 2006-03-20 631 * is really so; aka Router Reachability Probing.
270972554c91ac YOSHIFUJI Hideaki 2006-03-20 632 *
270972554c91ac YOSHIFUJI Hideaki 2006-03-20 633 * Router Reachability Probe MUST be rate-limited
270972554c91ac YOSHIFUJI Hideaki 2006-03-20 634 * to no more than one per minute.
270972554c91ac YOSHIFUJI Hideaki 2006-03-20 635 */
cc3a86c802f0ba David Ahern 2019-04-09 636 if (fib6_nh->fib_nh_gw_family)
7ff74a596b6aa4 YOSHIFUJI Hideaki / 吉藤英明 2013-01-17 637 return;
5e670d844b2a4e David Ahern 2018-04-17 638
cc3a86c802f0ba David Ahern 2019-04-09 639 nh_gw = &fib6_nh->fib_nh_gw6;
cc3a86c802f0ba David Ahern 2019-04-09 640 dev = fib6_nh->fib_nh_dev;
2152caea719657 YOSHIFUJI Hideaki / 吉藤英明 2013-01-17 641 rcu_read_lock_bh();
5e670d844b2a4e David Ahern 2018-04-17 642 neigh = __ipv6_neigh_lookup_noref(dev, nh_gw);
2152caea719657 YOSHIFUJI Hideaki / 吉藤英明 2013-01-17 643 if (neigh) {
8d6c31bf574177 Martin KaFai Lau 2015-07-24 644 if (neigh->nud_state & NUD_VALID)
8d6c31bf574177 Martin KaFai Lau 2015-07-24 645 goto out;
8d6c31bf574177 Martin KaFai Lau 2015-07-24 646
e3f0c73ec3f208 Cheng Lin 2019-08-27 647 idev = __in6_dev_get(dev);
2152caea719657 YOSHIFUJI Hideaki / 吉藤英明 2013-01-17 648 write_lock(&neigh->lock);
990edb428c2c85 Martin KaFai Lau 2015-07-24 649 if (!(neigh->nud_state & NUD_VALID) &&
990edb428c2c85 Martin KaFai Lau 2015-07-24 650 time_after(jiffies,
dcd1f572954f9d David Ahern 2018-04-18 651 neigh->updated + idev->cnf.rtr_probe_interval)) {
c2f17e827b4199 Hannes Frederic Sowa 2013-10-21 652 work = kmalloc(sizeof(*work), GFP_ATOMIC);
990edb428c2c85 Martin KaFai Lau 2015-07-24 653 if (work)
7e980569642811 Jiri Benc 2013-12-11 654 __neigh_set_probe_once(neigh);
990edb428c2c85 Martin KaFai Lau 2015-07-24 655 }
2152caea719657 YOSHIFUJI Hideaki / 吉藤英明 2013-01-17 656 write_unlock(&neigh->lock);
990edb428c2c85 Martin KaFai Lau 2015-07-24 657 }
2152caea719657 YOSHIFUJI Hideaki / 吉藤英明 2013-01-17 658
c2f17e827b4199 Hannes Frederic Sowa 2013-10-21 659 if (work) {
cc3a86c802f0ba David Ahern 2019-04-09 @660 fib6_nh->last_probe = jiffies;
c2f17e827b4199 Hannes Frederic Sowa 2013-10-21 661 INIT_WORK(&work->work, rt6_probe_deferred);
5e670d844b2a4e David Ahern 2018-04-17 662 work->target = *nh_gw;
5e670d844b2a4e David Ahern 2018-04-17 663 dev_hold(dev);
5e670d844b2a4e David Ahern 2018-04-17 664 work->dev = dev;
c2f17e827b4199 Hannes Frederic Sowa 2013-10-21 665 schedule_work(&work->work);
c2f17e827b4199 Hannes Frederic Sowa 2013-10-21 666 }
990edb428c2c85 Martin KaFai Lau 2015-07-24 667
8d6c31bf574177 Martin KaFai Lau 2015-07-24 668 out:
2152caea719657 YOSHIFUJI Hideaki / 吉藤英明 2013-01-17 669 rcu_read_unlock_bh();
f2c31e32b378a6 Eric Dumazet 2011-07-29 670 }
270972554c91ac YOSHIFUJI Hideaki 2006-03-20 671 #else
cc3a86c802f0ba David Ahern 2019-04-09 672 static inline void rt6_probe(struct fib6_nh *fib6_nh)
270972554c91ac YOSHIFUJI Hideaki 2006-03-20 673 {
270972554c91ac YOSHIFUJI Hideaki 2006-03-20 674 }
270972554c91ac YOSHIFUJI Hideaki 2006-03-20 675 #endif
270972554c91ac YOSHIFUJI Hideaki 2006-03-20 676
:::::: The code at line 660 was first introduced by commit
:::::: cc3a86c802f0ba9a2627aef256d95ae3b3fa6e91 ipv6: Change rt6_probe to take a fib6_nh
:::::: TO: David Ahern <dsahern@gmail.com>
:::::: CC: David S. Miller <davem@davemloft.net>
---
0-DAY kernel test infrastructure Open Source Technology Center
https://lists.01.org/pipermail/kbuild-all Intel Corporation
[-- Attachment #2: .config.gz --]
[-- Type: application/gzip, Size: 43525 bytes --]
^ permalink raw reply
* Re: [PATCH net-next v5] sched: Add dualpi2 qdisc
From: Bob Briscoe @ 2019-08-29 22:18 UTC (permalink / raw)
To: Dave Taht
Cc: Tilmans, Olivier (Nokia - BE/Antwerp), Eric Dumazet,
Stephen Hemminger, Olga Albisser,
De Schepper, Koen (Nokia - BE/Antwerp), Henrik Steen,
Jamal Hadi Salim, Cong Wang, Jiri Pirko, David S. Miller,
linux-kernel@vger.kernel.org, netdev@vger.kernel.org
In-Reply-To: <CAA93jw5R2QWSngdKX5RSvGR5NEvFTH-Sp5__k+EroxkkQkfzcw@mail.gmail.com>
Dave,
On 28/08/2019 17:55, Dave Taht wrote:
> On Wed, Aug 28, 2019 at 7:00 AM Bob Briscoe <research@bobbriscoe.net> wrote:
>> Olivier, Dave,
>>
>> On 23/08/2019 13:59, Tilmans, Olivier (Nokia - BE/Antwerp) wrote:
>>
>> as best as I can
>> tell (but could be wrong) the NQB idea wants to put something into the
>> l4s fast queue? Or is NQB supposed to
>> be a third queue?
>>
>> NQB is not supported in this release of the code. But FYI, it's not for a third queue.
> At the time of my code review of dualpi I had not gone back to review
> the NQB draft fully.
>
>> We can add support for NQB in the future, by expanding the
>> dualpi2_skb_classify() function. This is however out of scope at the
>> moment as NQB is not yet adopted by the TSV WG. I'd guess we may want more
>> than just the NQB DSCP codepoint in the L queue, which then warrant
>> another way to classify traffic, e.g., using tc filter hints.
> Yes, you'll find find folk are fans of being able to put tc (and ebpf)
> filters in front of various qdiscs for classification, logging, and/or
> dropping behavior.
>
> A fairly typical stanza is here:
> https://github.com/torvalds/linux/blob/master/net/sched/sch_sfq.c#L171
> to line 193.
Yes, I got a student to add hooks for the Linux classification
architecture (either adding more, or overriding the defaults) a couple
of years ago, along with creating a classful structure. But his
unfinished branch got left dangling once he graduated and is now way out
of date. it's still our intention to take that direction tho.
>
>> The IETF adopted the NQB draft at the meeting just passed in July, but the draft has not yet been updated to reflect that: https://tools.ietf.org/html/draft-white-tsvwg-nqb-02
> Hmmm... no. I think oliver's statement was correct.
>
> NQB was put into the "call for adoption into tsvwg" state (
> https://mailarchive.ietf.org/arch/msg/tsvwg/fjyYQgU9xQCNalwPO7v9-al6mGk
> ) in the tsvwg aug 21st, which
> doesn't mean "adopted by the ietf", either.
You're right.
I've been away from all this for a while. In the tsvwg meeting there
were perhaps a couple of dozen folks stating support and no-one against,
so I had (wrongly) extrapolated from that - I should have checked the
status of the ML discussion first.
> In response to that call
> several folk did put in (rather pithy),
> comments on the current state of the NQB idea and internet draft, starting here:
>
> https://mailarchive.ietf.org/arch/msg/tsvwg/hZGjm899t87YZl9JJUOWQq4KBsk
> While using up ECT1 in the L4S code as an identifier and not as a
> congestion indicator is very controversial for me (
> https://lwn.net/Articles/783673/ ), AND I'd rather it not be baked
> into the linux api for dualpi should this identifier not be chosen by
> the wg (thus my suggestion of a mask or lookup table)...
That ship has sailed. You can consider it controversial if you want, but
the tsvwg decided to use ECT(1) as an identifier for L4S after long
discussions back in 2016. Years of a large number of people's work was
predicated on that decision. So the dualpi2 code reflects the way the
IETF is approaching this.
>
> ... I also dearly would like both sides of this code - dualpi and tcp
> prague - in a simultaneously testable and high quality state. Without
> that, many core ideas in dualpi cannot be tested, nor objectively
> evaluated against other tcps and qdiscs using rfc3168 behavior along
> the path. Multiple experimental ideas in RFC8311 (such as those in
> section 4.3) have also not been re-evaluated in any context.
We're working on that - top priority now.
>
> Is the known to work reference codebase for "tcp prague" still 3.19 based?
It is, but Olivier recently found the elusive cause of the problem that
made later versions bursty. So we're getting close.
Bob
>> Bob
>>
>> --
>> ________________________________________________________________
>> Bob Briscoe http://bobbriscoe.net/
>
>
> --
>
> Dave Täht
> CTO, TekLibre, LLC
> http://www.teklibre.com
> Tel: 1-831-205-9740
--
________________________________________________________________
Bob Briscoe http://bobbriscoe.net/
^ permalink raw reply
* Re: general protection fault in tls_sk_proto_close (2)
From: John Fastabend @ 2019-08-29 22:18 UTC (permalink / raw)
To: Jakub Kicinski, John Fastabend
Cc: Hillf Danton, syzbot, aviadye, borisp, daniel, davejwatson, davem,
linux-kernel, netdev, syzkaller-bugs
In-Reply-To: <20190829115315.5686c18f@cakuba.netronome.com>
Jakub Kicinski wrote:
> On Thu, 29 Aug 2019 11:48:32 -0700, John Fastabend wrote:
> > Jakub Kicinski wrote:
> > > On Thu, 29 Aug 2019 11:52:00 +0800, Hillf Danton wrote:
> > > > Alternatively work is done if sock is closed again. Anyway ctx is reset
> > > > under sock's callback lock in write mode.
> > > >
> > > > --- a/net/tls/tls_main.c
> > > > +++ b/net/tls/tls_main.c
> > > > @@ -295,6 +295,8 @@ static void tls_sk_proto_close(struct so
> > > > long timeo = sock_sndtimeo(sk, 0);
> > > > bool free_ctx;
> > > >
> > > > + if (!ctx)
> > > > + return;
> > > > if (ctx->tx_conf == TLS_SW)
> > > > tls_sw_cancel_work_tx(ctx);
> > >
> > > That's no bueno, the real socket's close will never get called.
> >
> > Seems when we refactored BPF side we dropped the check for ULP on one
> > path so I'll add that back now. It would be nice and seems we are
> > getting closer now that tls side is a bit more dynamic if the ordering
> > didn't matter.
>
> We'd probably need some more generic way of communicating the changes
> in sk_proto stack, e.g. by moving the update into one of sk_proto
> callbacks? but yes.
>
> > diff --git a/net/core/sock_map.c b/net/core/sock_map.c
> > index 1330a7442e5b..30d11558740e 100644
> > --- a/net/core/sock_map.c
> > +++ b/net/core/sock_map.c
> > @@ -666,6 +666,8 @@ static int sock_hash_update_common(struct bpf_map *map, void *key,
> > WARN_ON_ONCE(!rcu_read_lock_held());
> > if (unlikely(flags > BPF_EXIST))
> > return -EINVAL;
> > + if (unlikely(icsk->icsk_ulp_data))
> > + return -EINVAL;
> >
> > link = sk_psock_init_link();
> > if (!link)
>
> Thanks! That looks good, if you feel like submitting officially feel
> free to add my Reviewed-by!
I'll send it out this evening after running the selftests.
.John
^ permalink raw reply
* Re: [PATCH v3 1/2] net: core: Notify on changes to dev->promiscuity.
From: David Miller @ 2019-08-29 22:12 UTC (permalink / raw)
To: idosch
Cc: andrew, jiri, horatiu.vultur, alexandre.belloni, UNGLinuxDriver,
allan.nielsen, ivecera, f.fainelli, netdev, linux-kernel
In-Reply-To: <20190829193613.GA23259@splinter>
From: Ido Schimmel <idosch@idosch.org>
Date: Thu, 29 Aug 2019 22:36:13 +0300
> I fully agree that we should make it easy for users to capture offloaded
> traffic, which is why I suggested patching libpcap. Add a flag to
> capable netdevs that tells libpcap that in order to capture all the
> traffic from this interface it needs to add a tc filter with a trap
> action. That way zero familiarity with tc is required from users.
Why not just make setting promisc mode on the device do this rather than
require all of this tc indirection nonsense?
That's the whole point of this conversation I thought?
^ permalink raw reply
* Re: [PATCH v3 1/2] net: core: Notify on changes to dev->promiscuity.
From: David Miller @ 2019-08-29 22:10 UTC (permalink / raw)
To: andrew
Cc: idosch, jiri, horatiu.vultur, alexandre.belloni, UNGLinuxDriver,
allan.nielsen, ivecera, f.fainelli, netdev, linux-kernel
In-Reply-To: <20190829182957.GA17530@lunn.ch>
From: Andrew Lunn <andrew@lunn.ch>
Date: Thu, 29 Aug 2019 20:29:57 +0200
> We should also think about the different classes of users. Somebody
> using a TOR switch with a NOS is very different to a user of a SOHO
> switch in their WiFi access point. The first probably knows tc very
> well, the second has probably never heard of it, and just wants
> tcpdump to work like on their desktop.
+1
^ permalink raw reply
* Re: [PATCH v3 1/2] net: core: Notify on changes to dev->promiscuity.
From: David Miller @ 2019-08-29 22:08 UTC (permalink / raw)
To: idosch
Cc: andrew, jiri, horatiu.vultur, alexandre.belloni, UNGLinuxDriver,
allan.nielsen, ivecera, f.fainelli, netdev, linux-kernel
In-Reply-To: <20190829175759.GA19471@splinter>
From: Ido Schimmel <idosch@idosch.org>
Date: Thu, 29 Aug 2019 20:57:59 +0300
> On a software switch, when you run tcpdump without '-p', do you incur
> major packet loss? No. Will this happen when you punt several Tbps to
> your CPU on the hardware switch? Yes.
>
> Extending the definition of promiscuous mode to mean punt all traffic to
> the CPU is wrong, IMO. You will not be able to capture all the packets
This is so illogical, it is mind boggling.
How different is this to using tcpdump/wireshark on a 100GB or 1TB
network interface?
There is no difference.
Please stop portraying switches as special in this regard, they are
not.
^ permalink raw reply
* Re: [PATCH v2 net-next 05/15] net: sgi: ioc3-eth: allocate space for desc rings only once
From: Jakub Kicinski @ 2019-08-29 22:05 UTC (permalink / raw)
To: Thomas Bogendoerfer
Cc: Ralf Baechle, Paul Burton, James Hogan, David S. Miller,
linux-mips, linux-kernel, netdev
In-Reply-To: <20190830000058.882feb357058437cddc71315@suse.de>
On Fri, 30 Aug 2019 00:00:58 +0200, Thomas Bogendoerfer wrote:
> On Thu, 29 Aug 2019 14:05:37 -0700
> Jakub Kicinski <jakub.kicinski@netronome.com> wrote:
>
> > On Thu, 29 Aug 2019 17:50:03 +0200, Thomas Bogendoerfer wrote:
> > > + if (skb)
> > > + dev_kfree_skb_any(skb);
> >
> > I think dev_kfree_skb_any() accepts NULL
>
> yes, I'll drop the if
>
> > > +
> > > + /* Allocate and rx ring. 4kb = 512 entries */
> > > + ip->rxr = (unsigned long *)get_zeroed_page(GFP_ATOMIC);
> > > + if (!ip->rxr) {
> > > + pr_err("ioc3-eth: rx ring allocation failed\n");
> > > + err = -ENOMEM;
> > > + goto out_stop;
> > > + }
> > > +
> > > + /* Allocate tx rings. 16kb = 128 bufs. */
> > > + ip->txr = (struct ioc3_etxd *)__get_free_pages(GFP_KERNEL, 2);
> > > + if (!ip->txr) {
> > > + pr_err("ioc3-eth: tx ring allocation failed\n");
> > > + err = -ENOMEM;
> > > + goto out_stop;
> > > + }
> >
> > Please just use kcalloc()/kmalloc_array() here,
>
> both allocation will be replaced in patch 11 with dma_direct_alloc_pages.
> So I hope I don't need to change it here.
Ah, missed that!
> Out of curiosity does kcalloc/kmalloc_array give me the same guarantees about
> alignment ? rx ring needs to be 4KB aligned, tx ring 16KB aligned.
I don't think so, actually, I was mostly worried you are passing
address from get_page() into kfree() here ;) But patch 11 cures that,
so that's good, too.
> >, and make sure the flags
> > are set to GFP_KERNEL whenever possible. Here and in ioc3_alloc_rings()
> > it looks like GFP_ATOMIC is unnecessary.
>
> yes, I'll change it
^ permalink raw reply
* Re: [PATCH bpf-next 01/13] bpf: add bpf_map_value_size and bp_map_copy_value helper functions
From: Song Liu @ 2019-08-29 22:04 UTC (permalink / raw)
To: Yonghong Song
Cc: bpf, Networking, Alexei Starovoitov, Brian Vazquez,
Daniel Borkmann, Kernel Team
In-Reply-To: <20190829064502.2750359-1-yhs@fb.com>
> On Aug 28, 2019, at 11:45 PM, Yonghong Song <yhs@fb.com> wrote:
>
> From: Brian Vazquez <brianvv@google.com>
>
> Move reusable code from map_lookup_elem to helper functions to avoid code
> duplication in kernel/bpf/syscall.c
>
> Suggested-by: Stanislav Fomichev <sdf@google.com>
> Signed-off-by: Brian Vazquez <brianvv@google.com>
Acked-by: Song Liu <songliubraving@fb.com>
Yonghong, we also need your SoB.
^ permalink raw reply
* Re: [PATCH v2 net-next 05/15] net: sgi: ioc3-eth: allocate space for desc rings only once
From: Thomas Bogendoerfer @ 2019-08-29 22:00 UTC (permalink / raw)
To: Jakub Kicinski
Cc: Ralf Baechle, Paul Burton, James Hogan, David S. Miller,
linux-mips, linux-kernel, netdev
In-Reply-To: <20190829140537.68abfc9f@cakuba.netronome.com>
On Thu, 29 Aug 2019 14:05:37 -0700
Jakub Kicinski <jakub.kicinski@netronome.com> wrote:
> On Thu, 29 Aug 2019 17:50:03 +0200, Thomas Bogendoerfer wrote:
> > + if (skb)
> > + dev_kfree_skb_any(skb);
>
> I think dev_kfree_skb_any() accepts NULL
yes, I'll drop the if
> > +
> > + /* Allocate and rx ring. 4kb = 512 entries */
> > + ip->rxr = (unsigned long *)get_zeroed_page(GFP_ATOMIC);
> > + if (!ip->rxr) {
> > + pr_err("ioc3-eth: rx ring allocation failed\n");
> > + err = -ENOMEM;
> > + goto out_stop;
> > + }
> > +
> > + /* Allocate tx rings. 16kb = 128 bufs. */
> > + ip->txr = (struct ioc3_etxd *)__get_free_pages(GFP_KERNEL, 2);
> > + if (!ip->txr) {
> > + pr_err("ioc3-eth: tx ring allocation failed\n");
> > + err = -ENOMEM;
> > + goto out_stop;
> > + }
>
> Please just use kcalloc()/kmalloc_array() here,
both allocation will be replaced in patch 11 with dma_direct_alloc_pages.
So I hope I don't need to change it here.
Out of curiosity does kcalloc/kmalloc_array give me the same guarantees about
alignment ? rx ring needs to be 4KB aligned, tx ring 16KB aligned.
>, and make sure the flags
> are set to GFP_KERNEL whenever possible. Here and in ioc3_alloc_rings()
> it looks like GFP_ATOMIC is unnecessary.
yes, I'll change it
Thomas.
--
SUSE Software Solutions Germany GmbH
HRB 247165 (AG München)
Geschäftsführer: Felix Imendörffer
^ permalink raw reply
* ANNOUNCE: rpld an another RPL implementation for Linux
From: Alexander Aring @ 2019-08-29 21:57 UTC (permalink / raw)
To: open list:NETWORKING [GENERAL]
Cc: Michael Richardson, Jamal Hadi Salim, Robert Kaiser,
Martin Gergeleit, Kai Beckmann, koen, linux-wpan - ML, reubenhwk,
BlueZ development, Stefan Schmidt, sebastian.meiling,
Marcel Holtmann, Werner Almesberger, Jukka Rissanen
Hi,
I had some free time, I wanted to know how RPL [0] works so I did a
implementation. It's _very_ basic as it only gives you a "routable"
(is that a word?) thing afterwards in a very constrained setup of RPL
messages.
Took ~1 month to implement it and I reused some great code from radvd
[1]. I released it under the same license (BSD?). Anyway, I know there
exists a lot of memory leaks and the parameters are just crazy as not
practical in a real environment BUT it works.
I changed a little bit the dependencies from radvd (because fancy new things):
- lua for config handling
- libev for event loop handling
- libmnl for netlink handling
The code is available at:
https://github.com/linux-wpan/rpld
With a recent kernel (I think 4.19 and above) and necessary user space
dependencies, just build it and run the start script. It will create
some virtual IEEE 802.15.4 6LoWPAN interfaces and you can run
traceroute from namespace ns0 (which is the RPL DODAG root) to any
other node e.g. namespace ns5. With more knowledge of the scripts you
can change the underlying topology, everybody is welcome to improve
them.
I will work more on it when I have time... to have at least something
running means the real fun can begin (but it was already fun before).
The big thing what everybody wants is source routing, which requires
some control plane for RPL into the kernel to say how and when to put
source routing headers in IPv6. I think somehow I know what's
necessary now... but I didn't implemented it, this simple
implementation just filling up routing tables as RPL supports storing
(routing table) or non-storing (source routing) modes. People tells me
to lookup frrouting to look how they do source routing, I will if I
get the chance.
It doesn't run on Bluetooth yet, I know there exists a lack of UAPI to
figure out the linklayer which is used by 6LoWPAN. I need somehow a
SLAVE_INFO attribute in netlink to figure this out and tell me some
6LoWPAN specific attributes. I am sorry Bluetooth people, but I think
you are also more interested in source routing because I heard
somebody saying it's the more common approach outside (but I never saw
any other RPL implementation than unstrung running).
Also I did something in my masters thesis to make a better parent
selection, if this implementation becomes stable I can look to get
this migrated.
Please, radvd maintainer let me know if everything is okay from your
side. As I said I reused some code from radvd. I also operate on
ICMPv6 sockets. The same to Michael Richardson unstrung [2]. If there
is anything to talk or you have complains, I can change it.
Thanks, I really only wanted to get more knowledge about routing
protocols and how to implement such. Besides all known issues, I still
think it's a good starting point.
- Alex
[0] https://tools.ietf.org/html/rfc6550
[1] https://github.com/reubenhwk/radvd
[2] https://github.com/AnimaGUS-minerva/unstrung
^ permalink raw reply
* Re: [PATCH net-next v2 3/3] net: tls: export protocol version, cipher, tx_conf/rx_conf to socket diag
From: Jakub Kicinski @ 2019-08-29 21:56 UTC (permalink / raw)
To: Davide Caratti
Cc: borisp, Eric Dumazet, aviadye, davejwatson, davem, john.fastabend,
Matthieu Baerts, netdev
In-Reply-To: <22da29aa0d0c683afeba7549cabc64c5e073d308.1567095873.git.dcaratti@redhat.com>
On Thu, 29 Aug 2019 18:48:04 +0200, Davide Caratti wrote:
> When an application configures kernel TLS on top of a TCP socket, it's
> now possible for inet_diag_handler() to collect information regarding the
> protocol version, the cipher type and TX / RX configuration, in case
> INET_DIAG_INFO is requested.
>
> Signed-off-by: Davide Caratti <dcaratti@redhat.com>
> diff --git a/include/net/tls.h b/include/net/tls.h
> index 4997742475cd..990f1d9182a3 100644
> --- a/include/net/tls.h
> +++ b/include/net/tls.h
> @@ -431,6 +431,25 @@ static inline bool is_tx_ready(struct tls_sw_context_tx *ctx)
> return READ_ONCE(rec->tx_ready);
> }
>
> +static inline u16 tls_user_config(struct tls_context *ctx, bool tx)
> +{
> + u16 config = tx ? ctx->tx_conf : ctx->rx_conf;
> +
> + switch (config) {
> + case TLS_BASE:
> + return TLS_CONF_BASE;
> + case TLS_SW:
> + return TLS_CONF_SW;
> +#ifdef CONFIG_TLS_DEVICE
Recently the TLS_HW define was taken out of the ifdef, so the ifdef
around this is no longer necessary.
> + case TLS_HW:
> + return TLS_CONF_HW;
> +#endif
> + case TLS_HW_RECORD:
> + return TLS_CONF_HW_RECORD;
> + }
> + return 0;
> +}
> +
> struct sk_buff *
> tls_validate_xmit_skb(struct sock *sk, struct net_device *dev,
> struct sk_buff *skb);
> diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c
> index f8f2d2c3d627..3351a2ace369 100644
> --- a/net/tls/tls_main.c
> +++ b/net/tls/tls_main.c
> @@ -39,6 +39,7 @@
> #include <linux/netdevice.h>
> #include <linux/sched/signal.h>
> #include <linux/inetdevice.h>
> +#include <linux/inet_diag.h>
>
> #include <net/tls.h>
>
> @@ -835,6 +836,67 @@ static void tls_update(struct sock *sk, struct proto *p)
> }
> }
>
> +static int tls_get_info(const struct sock *sk, struct sk_buff *skb)
> +{
> + struct tls_context *ctx;
> + u16 version, cipher_type;
Unfortunately revere christmas tree will be needed :(
> + struct nlattr *start;
> + int err;
^ permalink raw reply
* RE: linux-next: Tree for Aug 29 (mlx5)
From: Haiyang Zhang @ 2019-08-29 21:48 UTC (permalink / raw)
To: Saeed Mahameed, sfr@canb.auug.org.au, Eran Ben Elisha,
linux-next@vger.kernel.org, rdunlap@infradead.org
Cc: linux-kernel@vger.kernel.org, netdev@vger.kernel.org,
Leon Romanovsky
In-Reply-To: <c92d20e27268f515e0d4c8a28f92c0da041c2acc.camel@mellanox.com>
> -----Original Message-----
> From: Saeed Mahameed <saeedm@mellanox.com>
> Sent: Thursday, August 29, 2019 2:32 PM
> To: sfr@canb.auug.org.au; Eran Ben Elisha <eranbe@mellanox.com>; linux-
> next@vger.kernel.org; rdunlap@infradead.org; Haiyang Zhang
> <haiyangz@microsoft.com>
> Cc: linux-kernel@vger.kernel.org; netdev@vger.kernel.org; Leon
> Romanovsky <leonro@mellanox.com>
> Subject: Re: linux-next: Tree for Aug 29 (mlx5)
>
> On Thu, 2019-08-29 at 12:55 -0700, Randy Dunlap wrote:
> > On 8/29/19 12:54 PM, Randy Dunlap wrote:
> > > On 8/29/19 4:08 AM, Stephen Rothwell wrote:
> > > > Hi all,
> > > >
> > > > Changes since 20190828:
> > > >
> > >
> > > on x86_64:
> > > when CONFIG_PCI_HYPERV=m
> >
> > and CONFIG_PCI_HYPERV_INTERFACE=m
> >
>
> Haiyang and Eran, I think CONFIG_PCI_HYPERV_INTERFACE was never
> supposed to be a module ? it supposed to provide an always available
> interface to drivers ..
>
> Anyway, maybe we need to imply CONFIG_PCI_HYPERV_INTERFACE in mlx5.
The symbolic dependency by driver mlx5e, automatically triggers loading of
pci_hyperv_interface module. And this module can be loaded in any platforms.
Currently, mlx5e driver has #if IS_ENABLED(CONFIG_PCI_HYPERV_INTERFACE)
around the code using the interface.
I agree --
Adding "select PCI_HYPERV_INTERFACE" for mlx5e will clean up these #if's.
Thanks,
- Haiyang
^ permalink raw reply
* Re: [PATCH bpf-next 2/2] nfp: bpf: add simple map op cache
From: Jakub Kicinski @ 2019-08-29 21:36 UTC (permalink / raw)
To: Song Liu
Cc: Alexei Starovoitov, Daniel Borkmann, Networking, oss-drivers,
jaco.gericke, Quentin Monnet
In-Reply-To: <CAPhsuW5ExXPXYi5D2MND5JREh8EKNHUvSNoBEJ7L3-XK3GD9mA@mail.gmail.com>
On Thu, 29 Aug 2019 14:29:44 -0700, Song Liu wrote:
> On Tue, Aug 27, 2019 at 10:40 PM Jakub Kicinski
> <jakub.kicinski@netronome.com> wrote:
> >
> > Each get_next and lookup call requires a round trip to the device.
> > However, the device is capable of giving us a few entries back,
> > instead of just one.
> >
> > In this patch we ask for a small yet reasonable number of entries
> > (4) on every get_next call, and on subsequent get_next/lookup calls
> > check this little cache for a hit. The cache is only kept for 250us,
> > and is invalidated on every operation which may modify the map
> > (e.g. delete or update call). Note that operations may be performed
> > simultaneously, so we have to keep track of operations in flight.
> >
> > Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
> > Reviewed-by: Quentin Monnet <quentin.monnet@netronome.com>
> > ---
> > drivers/net/ethernet/netronome/nfp/bpf/cmsg.c | 179 +++++++++++++++++-
> > drivers/net/ethernet/netronome/nfp/bpf/fw.h | 1 +
> > drivers/net/ethernet/netronome/nfp/bpf/main.c | 18 ++
> > drivers/net/ethernet/netronome/nfp/bpf/main.h | 23 +++
> > .../net/ethernet/netronome/nfp/bpf/offload.c | 3 +
> > 5 files changed, 215 insertions(+), 9 deletions(-)
> >
> > diff --git a/drivers/net/ethernet/netronome/nfp/bpf/cmsg.c b/drivers/net/ethernet/netronome/nfp/bpf/cmsg.c
> > index fcf880c82f3f..0e2db6ea79e9 100644
> > --- a/drivers/net/ethernet/netronome/nfp/bpf/cmsg.c
> > +++ b/drivers/net/ethernet/netronome/nfp/bpf/cmsg.c
> > @@ -6,6 +6,7 @@
> > #include <linux/bug.h>
> > #include <linux/jiffies.h>
> > #include <linux/skbuff.h>
> > +#include <linux/timekeeping.h>
> >
> > #include "../ccm.h"
> > #include "../nfp_app.h"
> > @@ -175,29 +176,151 @@ nfp_bpf_ctrl_reply_val(struct nfp_app_bpf *bpf, struct cmsg_reply_map_op *reply,
> > return &reply->data[bpf->cmsg_key_sz * (n + 1) + bpf->cmsg_val_sz * n];
> > }
> >
> > +static bool nfp_bpf_ctrl_op_cache_invalidate(enum nfp_ccm_type op)
> > +{
> > + return op == NFP_CCM_TYPE_BPF_MAP_UPDATE ||
> > + op == NFP_CCM_TYPE_BPF_MAP_DELETE;
> > +}
> > +
> > +static bool nfp_bpf_ctrl_op_cache_capable(enum nfp_ccm_type op)
> > +{
> > + return op == NFP_CCM_TYPE_BPF_MAP_LOOKUP ||
> > + op == NFP_CCM_TYPE_BPF_MAP_GETNEXT;
> > +}
> > +
> > +static bool nfp_bpf_ctrl_op_cache_fill(enum nfp_ccm_type op)
> > +{
> > + return op == NFP_CCM_TYPE_BPF_MAP_GETFIRST ||
> > + op == NFP_CCM_TYPE_BPF_MAP_GETNEXT;
> > +}
> > +
> > +static unsigned int
> > +nfp_bpf_ctrl_op_cache_get(struct nfp_bpf_map *nfp_map, enum nfp_ccm_type op,
> > + const u8 *key, u8 *out_key, u8 *out_value,
> > + u32 *cache_gen)
> > +{
> > + struct bpf_map *map = &nfp_map->offmap->map;
> > + struct nfp_app_bpf *bpf = nfp_map->bpf;
> > + unsigned int i, count, n_entries;
> > + struct cmsg_reply_map_op *reply;
> > +
> > + n_entries = nfp_bpf_ctrl_op_cache_fill(op) ? bpf->cmsg_cache_cnt : 1;
> > +
> > + spin_lock(&nfp_map->cache_lock);
> > + *cache_gen = nfp_map->cache_gen;
> > + if (nfp_map->cache_blockers)
> > + n_entries = 1;
> > +
> > + if (nfp_bpf_ctrl_op_cache_invalidate(op))
> > + goto exit_block;
> > + if (!nfp_bpf_ctrl_op_cache_capable(op))
> > + goto exit_unlock;
> > +
> > + if (!nfp_map->cache)
> > + goto exit_unlock;
> > + if (nfp_map->cache_to < ktime_get_ns())
> > + goto exit_invalidate;
> > +
> > + reply = (void *)nfp_map->cache->data;
> > + count = be32_to_cpu(reply->count);
>
> Do we need to check whether count is too big (from firmware bug)?
It's validated below, when the skb is received (see my "here" below)
> > +
> > + for (i = 0; i < count; i++) {
> > + void *cached_key;
> > +
> > + cached_key = nfp_bpf_ctrl_reply_key(bpf, reply, i);
> > + if (memcmp(cached_key, key, map->key_size))
> > + continue;
> > +
> > + if (op == NFP_CCM_TYPE_BPF_MAP_LOOKUP)
> > + memcpy(out_value, nfp_bpf_ctrl_reply_val(bpf, reply, i),
> > + map->value_size);
> > + if (op == NFP_CCM_TYPE_BPF_MAP_GETNEXT) {
> > + if (i + 1 == count)
> > + break;
> > +
> > + memcpy(out_key,
> > + nfp_bpf_ctrl_reply_key(bpf, reply, i + 1),
> > + map->key_size);
> > + }
> > +
> > + n_entries = 0;
> > + goto exit_unlock;
> > + }
> > + goto exit_unlock;
> > +
> > +exit_block:
> > + nfp_map->cache_blockers++;
> > +exit_invalidate:
> > + dev_consume_skb_any(nfp_map->cache);
> > + nfp_map->cache = NULL;
> > +exit_unlock:
> > + spin_unlock(&nfp_map->cache_lock);
> > + return n_entries;
> > +}
> > static int
> > nfp_bpf_ctrl_entry_op(struct bpf_offloaded_map *offmap, enum nfp_ccm_type op,
> > u8 *key, u8 *value, u64 flags, u8 *out_key, u8 *out_value)
> > {
> > struct nfp_bpf_map *nfp_map = offmap->dev_priv;
> > + unsigned int n_entries, reply_entries, count;
> > struct nfp_app_bpf *bpf = nfp_map->bpf;
> > struct bpf_map *map = &offmap->map;
> > struct cmsg_reply_map_op *reply;
> > struct cmsg_req_map_op *req;
> > struct sk_buff *skb;
> > + u32 cache_gen;
> > int err;
> >
> > /* FW messages have no space for more than 32 bits of flags */
> > if (flags >> 32)
> > return -EOPNOTSUPP;
> >
> > + /* Handle op cache */
> > + n_entries = nfp_bpf_ctrl_op_cache_get(nfp_map, op, key, out_key,
> > + out_value, &cache_gen);
> > + if (!n_entries)
> > + return 0;
> > +
> > skb = nfp_bpf_cmsg_map_req_alloc(bpf, 1);
> > - if (!skb)
> > - return -ENOMEM;
> > + if (!skb) {
> > + err = -ENOMEM;
> > + goto err_cache_put;
> > + }
> >
> > req = (void *)skb->data;
> > req->tid = cpu_to_be32(nfp_map->tid);
> > - req->count = cpu_to_be32(1);
> > + req->count = cpu_to_be32(n_entries);
> > req->flags = cpu_to_be32(flags);
> >
> > /* Copy inputs */
> > @@ -207,16 +330,38 @@ nfp_bpf_ctrl_entry_op(struct bpf_offloaded_map *offmap, enum nfp_ccm_type op,
> > memcpy(nfp_bpf_ctrl_req_val(bpf, req, 0), value,
> > map->value_size);
> >
> > - skb = nfp_ccm_communicate(&bpf->ccm, skb, op,
> > - nfp_bpf_cmsg_map_reply_size(bpf, 1));
> > - if (IS_ERR(skb))
> > - return PTR_ERR(skb);
> > + skb = nfp_ccm_communicate(&bpf->ccm, skb, op, 0);
> > + if (IS_ERR(skb)) {
> > + err = PTR_ERR(skb);
> > + goto err_cache_put;
> > + }
> > +
> > + if (skb->len < sizeof(*reply)) {
> > + cmsg_warn(bpf, "cmsg drop - type 0x%02x too short %d!\n",
> > + op, skb->len);
> > + err = -EIO;
> > + goto err_free;
> > + }
> >
> > reply = (void *)skb->data;
> > + count = be32_to_cpu(reply->count);
> > err = nfp_bpf_ctrl_rc_to_errno(bpf, &reply->reply_hdr);
> > + /* FW responds with message sized to hold the good entries,
> > + * plus one extra entry if there was an error.
> > + */
> > + reply_entries = count + !!err;
> > + if (n_entries > 1 && count)
> > + err = 0;
> > if (err)
> > goto err_free;
> >
> > + if (skb->len != nfp_bpf_cmsg_map_reply_size(bpf, reply_entries)) {
here, reply_entries is derived directly from reply->count
> > + cmsg_warn(bpf, "cmsg drop - type 0x%02x too short %d for %d entries!\n",
> > + op, skb->len, reply_entries);
> > + err = -EIO;
> > + goto err_free;
> > + }
> > +
> > /* Copy outputs */
> > if (out_key)
> > memcpy(out_key, nfp_bpf_ctrl_reply_key(bpf, reply, 0),
> > @@ -225,11 +370,13 @@ nfp_bpf_ctrl_entry_op(struct bpf_offloaded_map *offmap, enum nfp_ccm_type op,
> > memcpy(out_value, nfp_bpf_ctrl_reply_val(bpf, reply, 0),
> > map->value_size);
> >
> > - dev_consume_skb_any(skb);
> > + nfp_bpf_ctrl_op_cache_put(nfp_map, op, skb, cache_gen);
> >
> > return 0;
> > err_free:
> > dev_kfree_skb_any(skb);
> > +err_cache_put:
> > + nfp_bpf_ctrl_op_cache_put(nfp_map, op, NULL, cache_gen);
> > return err;
> > }
> >
> > @@ -275,7 +422,21 @@ unsigned int nfp_bpf_ctrl_cmsg_min_mtu(struct nfp_app_bpf *bpf)
> >
> > unsigned int nfp_bpf_ctrl_cmsg_mtu(struct nfp_app_bpf *bpf)
> > {
> > - return max(NFP_NET_DEFAULT_MTU, nfp_bpf_ctrl_cmsg_min_mtu(bpf));
> > + return max3(NFP_NET_DEFAULT_MTU,
> > + nfp_bpf_cmsg_map_req_size(bpf, NFP_BPF_MAP_CACHE_CNT),
> > + nfp_bpf_cmsg_map_reply_size(bpf, NFP_BPF_MAP_CACHE_CNT));
> > +}
> > +
> > +unsigned int nfp_bpf_ctrl_cmsg_cache_cnt(struct nfp_app_bpf *bpf)
> > +{
> > + unsigned int mtu, req_max, reply_max, entry_sz;
> > +
> > + mtu = bpf->app->ctrl->dp.mtu;
> > + entry_sz = bpf->cmsg_key_sz + bpf->cmsg_val_sz;
> > + req_max = (mtu - sizeof(struct cmsg_req_map_op)) / entry_sz;
> > + reply_max = (mtu - sizeof(struct cmsg_reply_map_op)) / entry_sz;
> > +
> > + return min3(req_max, reply_max, NFP_BPF_MAP_CACHE_CNT);
> > }
> >
> > void nfp_bpf_ctrl_msg_rx(struct nfp_app *app, struct sk_buff *skb)
> > diff --git a/drivers/net/ethernet/netronome/nfp/bpf/fw.h b/drivers/net/ethernet/netronome/nfp/bpf/fw.h
> > index 06c4286bd79e..a83a0ad5e27d 100644
> > --- a/drivers/net/ethernet/netronome/nfp/bpf/fw.h
> > +++ b/drivers/net/ethernet/netronome/nfp/bpf/fw.h
> > @@ -24,6 +24,7 @@ enum bpf_cap_tlv_type {
> > NFP_BPF_CAP_TYPE_QUEUE_SELECT = 5,
> > NFP_BPF_CAP_TYPE_ADJUST_TAIL = 6,
> > NFP_BPF_CAP_TYPE_ABI_VERSION = 7,
> > + NFP_BPF_CAP_TYPE_CMSG_MULTI_ENT = 8,
> > };
> >
> > struct nfp_bpf_cap_tlv_func {
> > diff --git a/drivers/net/ethernet/netronome/nfp/bpf/main.c b/drivers/net/ethernet/netronome/nfp/bpf/main.c
> > index 2b1773ed3de9..8f732771d3fa 100644
> > --- a/drivers/net/ethernet/netronome/nfp/bpf/main.c
> > +++ b/drivers/net/ethernet/netronome/nfp/bpf/main.c
> > @@ -299,6 +299,14 @@ nfp_bpf_parse_cap_adjust_tail(struct nfp_app_bpf *bpf, void __iomem *value,
> > return 0;
> > }
> >
> > +static int
> > +nfp_bpf_parse_cap_cmsg_multi_ent(struct nfp_app_bpf *bpf, void __iomem *value,
> > + u32 length)
> > +{
> > + bpf->cmsg_multi_ent = true;
> > + return 0;
> > +}
> > +
> > static int
> > nfp_bpf_parse_cap_abi_version(struct nfp_app_bpf *bpf, void __iomem *value,
> > u32 length)
> > @@ -375,6 +383,11 @@ static int nfp_bpf_parse_capabilities(struct nfp_app *app)
> > length))
> > goto err_release_free;
> > break;
> > + case NFP_BPF_CAP_TYPE_CMSG_MULTI_ENT:
> > + if (nfp_bpf_parse_cap_cmsg_multi_ent(app->priv, value,
> > + length))
>
> Do we plan to extend nfp_bpf_parse_cap_cmsg_multi_ent() to return
> non-zero in the
> future?
Yes, the TLV format allows for the entry to be extended and then
parsing may fail. It's mostly a pattern the BPF TLV parsing follows,
though.
^ permalink raw reply
* Re: linux-next: Tree for Aug 29 (mlx5)
From: Saeed Mahameed @ 2019-08-29 21:31 UTC (permalink / raw)
To: sfr@canb.auug.org.au, Eran Ben Elisha, linux-next@vger.kernel.org,
rdunlap@infradead.org, haiyangz
Cc: linux-kernel@vger.kernel.org, netdev@vger.kernel.org,
Leon Romanovsky
In-Reply-To: <52bcddef-fcf2-8de5-d15a-9e7ee2d5b14d@infradead.org>
On Thu, 2019-08-29 at 12:55 -0700, Randy Dunlap wrote:
> On 8/29/19 12:54 PM, Randy Dunlap wrote:
> > On 8/29/19 4:08 AM, Stephen Rothwell wrote:
> > > Hi all,
> > >
> > > Changes since 20190828:
> > >
> >
> > on x86_64:
> > when CONFIG_PCI_HYPERV=m
>
> and CONFIG_PCI_HYPERV_INTERFACE=m
>
Haiyang and Eran, I think CONFIG_PCI_HYPERV_INTERFACE was never
supposed to be a module ? it supposed to provide an always available
interface to drivers ..
Anyway, maybe we need to imply CONFIG_PCI_HYPERV_INTERFACE in mlx5.
Thanks,
Saeed.
> > and mxlx5 is builtin (=y).
> >
> > ld: drivers/net/ethernet/mellanox/mlx5/core/main.o: in function
> > `mlx5_unload':
> > main.c:(.text+0x5d): undefined reference to `mlx5_hv_vhca_cleanup'
> > ld: drivers/net/ethernet/mellanox/mlx5/core/main.o: in function
> > `mlx5_cleanup_once':
> > main.c:(.text+0x158): undefined reference to `mlx5_hv_vhca_destroy'
> > ld: drivers/net/ethernet/mellanox/mlx5/core/main.o: in function
> > `mlx5_load_one':
> > main.c:(.text+0x4191): undefined reference to `mlx5_hv_vhca_create'
> > ld: main.c:(.text+0x4772): undefined reference to
> > `mlx5_hv_vhca_init'
> > ld: main.c:(.text+0x4b07): undefined reference to
> > `mlx5_hv_vhca_cleanup'
> >
> >
>
>
^ permalink raw reply
* Re: [PATCH bpf-next 1/2] nfp: bpf: rework MTU checking
From: Song Liu @ 2019-08-29 21:30 UTC (permalink / raw)
To: Jakub Kicinski
Cc: Alexei Starovoitov, Daniel Borkmann, Networking, oss-drivers,
jaco.gericke, Quentin Monnet
In-Reply-To: <20190828053629.28658-2-jakub.kicinski@netronome.com>
On Tue, Aug 27, 2019 at 10:38 PM Jakub Kicinski
<jakub.kicinski@netronome.com> wrote:
>
> If control channel MTU is too low to support map operations a warning
> will be printed. This is not enough, we want to make sure probe fails
> in such scenario, as this would clearly be a faulty configuration.
>
> Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
> Reviewed-by: Quentin Monnet <quentin.monnet@netronome.com>
Acked-by: Song Liu <songliubraving@fb.com>
^ permalink raw reply
* Re: [PATCH bpf-next 2/2] nfp: bpf: add simple map op cache
From: Song Liu @ 2019-08-29 21:29 UTC (permalink / raw)
To: Jakub Kicinski
Cc: Alexei Starovoitov, Daniel Borkmann, Networking, oss-drivers,
jaco.gericke, Quentin Monnet
In-Reply-To: <20190828053629.28658-3-jakub.kicinski@netronome.com>
On Tue, Aug 27, 2019 at 10:40 PM Jakub Kicinski
<jakub.kicinski@netronome.com> wrote:
>
> Each get_next and lookup call requires a round trip to the device.
> However, the device is capable of giving us a few entries back,
> instead of just one.
>
> In this patch we ask for a small yet reasonable number of entries
> (4) on every get_next call, and on subsequent get_next/lookup calls
> check this little cache for a hit. The cache is only kept for 250us,
> and is invalidated on every operation which may modify the map
> (e.g. delete or update call). Note that operations may be performed
> simultaneously, so we have to keep track of operations in flight.
>
> Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
> Reviewed-by: Quentin Monnet <quentin.monnet@netronome.com>
> ---
> drivers/net/ethernet/netronome/nfp/bpf/cmsg.c | 179 +++++++++++++++++-
> drivers/net/ethernet/netronome/nfp/bpf/fw.h | 1 +
> drivers/net/ethernet/netronome/nfp/bpf/main.c | 18 ++
> drivers/net/ethernet/netronome/nfp/bpf/main.h | 23 +++
> .../net/ethernet/netronome/nfp/bpf/offload.c | 3 +
> 5 files changed, 215 insertions(+), 9 deletions(-)
>
> diff --git a/drivers/net/ethernet/netronome/nfp/bpf/cmsg.c b/drivers/net/ethernet/netronome/nfp/bpf/cmsg.c
> index fcf880c82f3f..0e2db6ea79e9 100644
> --- a/drivers/net/ethernet/netronome/nfp/bpf/cmsg.c
> +++ b/drivers/net/ethernet/netronome/nfp/bpf/cmsg.c
> @@ -6,6 +6,7 @@
> #include <linux/bug.h>
> #include <linux/jiffies.h>
> #include <linux/skbuff.h>
> +#include <linux/timekeeping.h>
>
> #include "../ccm.h"
> #include "../nfp_app.h"
> @@ -175,29 +176,151 @@ nfp_bpf_ctrl_reply_val(struct nfp_app_bpf *bpf, struct cmsg_reply_map_op *reply,
> return &reply->data[bpf->cmsg_key_sz * (n + 1) + bpf->cmsg_val_sz * n];
> }
>
> +static bool nfp_bpf_ctrl_op_cache_invalidate(enum nfp_ccm_type op)
> +{
> + return op == NFP_CCM_TYPE_BPF_MAP_UPDATE ||
> + op == NFP_CCM_TYPE_BPF_MAP_DELETE;
> +}
> +
> +static bool nfp_bpf_ctrl_op_cache_capable(enum nfp_ccm_type op)
> +{
> + return op == NFP_CCM_TYPE_BPF_MAP_LOOKUP ||
> + op == NFP_CCM_TYPE_BPF_MAP_GETNEXT;
> +}
> +
> +static bool nfp_bpf_ctrl_op_cache_fill(enum nfp_ccm_type op)
> +{
> + return op == NFP_CCM_TYPE_BPF_MAP_GETFIRST ||
> + op == NFP_CCM_TYPE_BPF_MAP_GETNEXT;
> +}
> +
> +static unsigned int
> +nfp_bpf_ctrl_op_cache_get(struct nfp_bpf_map *nfp_map, enum nfp_ccm_type op,
> + const u8 *key, u8 *out_key, u8 *out_value,
> + u32 *cache_gen)
> +{
> + struct bpf_map *map = &nfp_map->offmap->map;
> + struct nfp_app_bpf *bpf = nfp_map->bpf;
> + unsigned int i, count, n_entries;
> + struct cmsg_reply_map_op *reply;
> +
> + n_entries = nfp_bpf_ctrl_op_cache_fill(op) ? bpf->cmsg_cache_cnt : 1;
> +
> + spin_lock(&nfp_map->cache_lock);
> + *cache_gen = nfp_map->cache_gen;
> + if (nfp_map->cache_blockers)
> + n_entries = 1;
> +
> + if (nfp_bpf_ctrl_op_cache_invalidate(op))
> + goto exit_block;
> + if (!nfp_bpf_ctrl_op_cache_capable(op))
> + goto exit_unlock;
> +
> + if (!nfp_map->cache)
> + goto exit_unlock;
> + if (nfp_map->cache_to < ktime_get_ns())
> + goto exit_invalidate;
> +
> + reply = (void *)nfp_map->cache->data;
> + count = be32_to_cpu(reply->count);
Do we need to check whether count is too big (from firmware bug)?
> +
> + for (i = 0; i < count; i++) {
> + void *cached_key;
> +
> + cached_key = nfp_bpf_ctrl_reply_key(bpf, reply, i);
> + if (memcmp(cached_key, key, map->key_size))
> + continue;
> +
> + if (op == NFP_CCM_TYPE_BPF_MAP_LOOKUP)
> + memcpy(out_value, nfp_bpf_ctrl_reply_val(bpf, reply, i),
> + map->value_size);
> + if (op == NFP_CCM_TYPE_BPF_MAP_GETNEXT) {
> + if (i + 1 == count)
> + break;
> +
> + memcpy(out_key,
> + nfp_bpf_ctrl_reply_key(bpf, reply, i + 1),
> + map->key_size);
> + }
> +
> + n_entries = 0;
> + goto exit_unlock;
> + }
> + goto exit_unlock;
> +
> +exit_block:
> + nfp_map->cache_blockers++;
> +exit_invalidate:
> + dev_consume_skb_any(nfp_map->cache);
> + nfp_map->cache = NULL;
> +exit_unlock:
> + spin_unlock(&nfp_map->cache_lock);
> + return n_entries;
> +}
> +
> +static void
> +nfp_bpf_ctrl_op_cache_put(struct nfp_bpf_map *nfp_map, enum nfp_ccm_type op,
> + struct sk_buff *skb, u32 cache_gen)
> +{
> + bool blocker, filler;
> +
> + blocker = nfp_bpf_ctrl_op_cache_invalidate(op);
> + filler = nfp_bpf_ctrl_op_cache_fill(op);
> + if (blocker || filler) {
> + u64 to = 0;
> +
> + if (filler)
> + to = ktime_get_ns() + NFP_BPF_MAP_CACHE_TIME_NS;
> +
> + spin_lock(&nfp_map->cache_lock);
> + if (blocker) {
> + nfp_map->cache_blockers--;
> + nfp_map->cache_gen++;
> + }
> + if (filler && !nfp_map->cache_blockers &&
> + nfp_map->cache_gen == cache_gen) {
> + nfp_map->cache_to = to;
> + swap(nfp_map->cache, skb);
> + }
> + spin_unlock(&nfp_map->cache_lock);
> + }
> +
> + dev_consume_skb_any(skb);
> +}
> +
> static int
> nfp_bpf_ctrl_entry_op(struct bpf_offloaded_map *offmap, enum nfp_ccm_type op,
> u8 *key, u8 *value, u64 flags, u8 *out_key, u8 *out_value)
> {
> struct nfp_bpf_map *nfp_map = offmap->dev_priv;
> + unsigned int n_entries, reply_entries, count;
> struct nfp_app_bpf *bpf = nfp_map->bpf;
> struct bpf_map *map = &offmap->map;
> struct cmsg_reply_map_op *reply;
> struct cmsg_req_map_op *req;
> struct sk_buff *skb;
> + u32 cache_gen;
> int err;
>
> /* FW messages have no space for more than 32 bits of flags */
> if (flags >> 32)
> return -EOPNOTSUPP;
>
> + /* Handle op cache */
> + n_entries = nfp_bpf_ctrl_op_cache_get(nfp_map, op, key, out_key,
> + out_value, &cache_gen);
> + if (!n_entries)
> + return 0;
> +
> skb = nfp_bpf_cmsg_map_req_alloc(bpf, 1);
> - if (!skb)
> - return -ENOMEM;
> + if (!skb) {
> + err = -ENOMEM;
> + goto err_cache_put;
> + }
>
> req = (void *)skb->data;
> req->tid = cpu_to_be32(nfp_map->tid);
> - req->count = cpu_to_be32(1);
> + req->count = cpu_to_be32(n_entries);
> req->flags = cpu_to_be32(flags);
>
> /* Copy inputs */
> @@ -207,16 +330,38 @@ nfp_bpf_ctrl_entry_op(struct bpf_offloaded_map *offmap, enum nfp_ccm_type op,
> memcpy(nfp_bpf_ctrl_req_val(bpf, req, 0), value,
> map->value_size);
>
> - skb = nfp_ccm_communicate(&bpf->ccm, skb, op,
> - nfp_bpf_cmsg_map_reply_size(bpf, 1));
> - if (IS_ERR(skb))
> - return PTR_ERR(skb);
> + skb = nfp_ccm_communicate(&bpf->ccm, skb, op, 0);
> + if (IS_ERR(skb)) {
> + err = PTR_ERR(skb);
> + goto err_cache_put;
> + }
> +
> + if (skb->len < sizeof(*reply)) {
> + cmsg_warn(bpf, "cmsg drop - type 0x%02x too short %d!\n",
> + op, skb->len);
> + err = -EIO;
> + goto err_free;
> + }
>
> reply = (void *)skb->data;
> + count = be32_to_cpu(reply->count);
> err = nfp_bpf_ctrl_rc_to_errno(bpf, &reply->reply_hdr);
> + /* FW responds with message sized to hold the good entries,
> + * plus one extra entry if there was an error.
> + */
> + reply_entries = count + !!err;
> + if (n_entries > 1 && count)
> + err = 0;
> if (err)
> goto err_free;
>
> + if (skb->len != nfp_bpf_cmsg_map_reply_size(bpf, reply_entries)) {
> + cmsg_warn(bpf, "cmsg drop - type 0x%02x too short %d for %d entries!\n",
> + op, skb->len, reply_entries);
> + err = -EIO;
> + goto err_free;
> + }
> +
> /* Copy outputs */
> if (out_key)
> memcpy(out_key, nfp_bpf_ctrl_reply_key(bpf, reply, 0),
> @@ -225,11 +370,13 @@ nfp_bpf_ctrl_entry_op(struct bpf_offloaded_map *offmap, enum nfp_ccm_type op,
> memcpy(out_value, nfp_bpf_ctrl_reply_val(bpf, reply, 0),
> map->value_size);
>
> - dev_consume_skb_any(skb);
> + nfp_bpf_ctrl_op_cache_put(nfp_map, op, skb, cache_gen);
>
> return 0;
> err_free:
> dev_kfree_skb_any(skb);
> +err_cache_put:
> + nfp_bpf_ctrl_op_cache_put(nfp_map, op, NULL, cache_gen);
> return err;
> }
>
> @@ -275,7 +422,21 @@ unsigned int nfp_bpf_ctrl_cmsg_min_mtu(struct nfp_app_bpf *bpf)
>
> unsigned int nfp_bpf_ctrl_cmsg_mtu(struct nfp_app_bpf *bpf)
> {
> - return max(NFP_NET_DEFAULT_MTU, nfp_bpf_ctrl_cmsg_min_mtu(bpf));
> + return max3(NFP_NET_DEFAULT_MTU,
> + nfp_bpf_cmsg_map_req_size(bpf, NFP_BPF_MAP_CACHE_CNT),
> + nfp_bpf_cmsg_map_reply_size(bpf, NFP_BPF_MAP_CACHE_CNT));
> +}
> +
> +unsigned int nfp_bpf_ctrl_cmsg_cache_cnt(struct nfp_app_bpf *bpf)
> +{
> + unsigned int mtu, req_max, reply_max, entry_sz;
> +
> + mtu = bpf->app->ctrl->dp.mtu;
> + entry_sz = bpf->cmsg_key_sz + bpf->cmsg_val_sz;
> + req_max = (mtu - sizeof(struct cmsg_req_map_op)) / entry_sz;
> + reply_max = (mtu - sizeof(struct cmsg_reply_map_op)) / entry_sz;
> +
> + return min3(req_max, reply_max, NFP_BPF_MAP_CACHE_CNT);
> }
>
> void nfp_bpf_ctrl_msg_rx(struct nfp_app *app, struct sk_buff *skb)
> diff --git a/drivers/net/ethernet/netronome/nfp/bpf/fw.h b/drivers/net/ethernet/netronome/nfp/bpf/fw.h
> index 06c4286bd79e..a83a0ad5e27d 100644
> --- a/drivers/net/ethernet/netronome/nfp/bpf/fw.h
> +++ b/drivers/net/ethernet/netronome/nfp/bpf/fw.h
> @@ -24,6 +24,7 @@ enum bpf_cap_tlv_type {
> NFP_BPF_CAP_TYPE_QUEUE_SELECT = 5,
> NFP_BPF_CAP_TYPE_ADJUST_TAIL = 6,
> NFP_BPF_CAP_TYPE_ABI_VERSION = 7,
> + NFP_BPF_CAP_TYPE_CMSG_MULTI_ENT = 8,
> };
>
> struct nfp_bpf_cap_tlv_func {
> diff --git a/drivers/net/ethernet/netronome/nfp/bpf/main.c b/drivers/net/ethernet/netronome/nfp/bpf/main.c
> index 2b1773ed3de9..8f732771d3fa 100644
> --- a/drivers/net/ethernet/netronome/nfp/bpf/main.c
> +++ b/drivers/net/ethernet/netronome/nfp/bpf/main.c
> @@ -299,6 +299,14 @@ nfp_bpf_parse_cap_adjust_tail(struct nfp_app_bpf *bpf, void __iomem *value,
> return 0;
> }
>
> +static int
> +nfp_bpf_parse_cap_cmsg_multi_ent(struct nfp_app_bpf *bpf, void __iomem *value,
> + u32 length)
> +{
> + bpf->cmsg_multi_ent = true;
> + return 0;
> +}
> +
> static int
> nfp_bpf_parse_cap_abi_version(struct nfp_app_bpf *bpf, void __iomem *value,
> u32 length)
> @@ -375,6 +383,11 @@ static int nfp_bpf_parse_capabilities(struct nfp_app *app)
> length))
> goto err_release_free;
> break;
> + case NFP_BPF_CAP_TYPE_CMSG_MULTI_ENT:
> + if (nfp_bpf_parse_cap_cmsg_multi_ent(app->priv, value,
> + length))
Do we plan to extend nfp_bpf_parse_cap_cmsg_multi_ent() to return
non-zero in the
future?
> + goto err_release_free;
> + break;
> default:
> nfp_dbg(cpp, "unknown BPF capability: %d\n", type);
> break;
> @@ -426,6 +439,11 @@ static int nfp_bpf_start(struct nfp_app *app)
> return -EINVAL;
> }
>
> + if (bpf->cmsg_multi_ent)
> + bpf->cmsg_cache_cnt = nfp_bpf_ctrl_cmsg_cache_cnt(bpf);
> + else
> + bpf->cmsg_cache_cnt = 1;
> +
> return 0;
> }
>
> diff --git a/drivers/net/ethernet/netronome/nfp/bpf/main.h b/drivers/net/ethernet/netronome/nfp/bpf/main.h
> index f4802036eb42..fac9c6f9e197 100644
> --- a/drivers/net/ethernet/netronome/nfp/bpf/main.h
> +++ b/drivers/net/ethernet/netronome/nfp/bpf/main.h
> @@ -99,6 +99,7 @@ enum pkt_vec {
> * @maps_neutral: hash table of offload-neutral maps (on pointer)
> *
> * @abi_version: global BPF ABI version
> + * @cmsg_cache_cnt: number of entries to read for caching
> *
> * @adjust_head: adjust head capability
> * @adjust_head.flags: extra flags for adjust head
> @@ -124,6 +125,7 @@ enum pkt_vec {
> * @pseudo_random: FW initialized the pseudo-random machinery (CSRs)
> * @queue_select: BPF can set the RX queue ID in packet vector
> * @adjust_tail: BPF can simply trunc packet size for adjust tail
> + * @cmsg_multi_ent: FW can pack multiple map entries in a single cmsg
> */
> struct nfp_app_bpf {
> struct nfp_app *app;
> @@ -134,6 +136,8 @@ struct nfp_app_bpf {
> unsigned int cmsg_key_sz;
> unsigned int cmsg_val_sz;
>
> + unsigned int cmsg_cache_cnt;
> +
> struct list_head map_list;
> unsigned int maps_in_use;
> unsigned int map_elems_in_use;
> @@ -169,6 +173,7 @@ struct nfp_app_bpf {
> bool pseudo_random;
> bool queue_select;
> bool adjust_tail;
> + bool cmsg_multi_ent;
> };
>
> enum nfp_bpf_map_use {
> @@ -183,11 +188,21 @@ struct nfp_bpf_map_word {
> unsigned char non_zero_update :1;
> };
>
> +#define NFP_BPF_MAP_CACHE_CNT 4U
> +#define NFP_BPF_MAP_CACHE_TIME_NS (250 * 1000)
> +
> /**
> * struct nfp_bpf_map - private per-map data attached to BPF maps for offload
> * @offmap: pointer to the offloaded BPF map
> * @bpf: back pointer to bpf app private structure
> * @tid: table id identifying map on datapath
> + *
> + * @cache_lock: protects @cache_blockers, @cache_to, @cache
> + * @cache_blockers: number of ops in flight which block caching
> + * @cache_gen: counter incremented by every blocker on exit
> + * @cache_to: time when cache will no longer be valid (ns)
> + * @cache: skb with cached response
> + *
> * @l: link on the nfp_app_bpf->map_list list
> * @use_map: map of how the value is used (in 4B chunks)
> */
> @@ -195,6 +210,13 @@ struct nfp_bpf_map {
> struct bpf_offloaded_map *offmap;
> struct nfp_app_bpf *bpf;
> u32 tid;
> +
> + spinlock_t cache_lock;
> + u32 cache_blockers;
> + u32 cache_gen;
> + u64 cache_to;
> + struct sk_buff *cache;
> +
> struct list_head l;
> struct nfp_bpf_map_word use_map[];
> };
> @@ -566,6 +588,7 @@ void *nfp_bpf_relo_for_vnic(struct nfp_prog *nfp_prog, struct nfp_bpf_vnic *bv);
>
> unsigned int nfp_bpf_ctrl_cmsg_min_mtu(struct nfp_app_bpf *bpf);
> unsigned int nfp_bpf_ctrl_cmsg_mtu(struct nfp_app_bpf *bpf);
> +unsigned int nfp_bpf_ctrl_cmsg_cache_cnt(struct nfp_app_bpf *bpf);
> long long int
> nfp_bpf_ctrl_alloc_map(struct nfp_app_bpf *bpf, struct bpf_map *map);
> void
> diff --git a/drivers/net/ethernet/netronome/nfp/bpf/offload.c b/drivers/net/ethernet/netronome/nfp/bpf/offload.c
> index 39c9fec222b4..88fab6a82acf 100644
> --- a/drivers/net/ethernet/netronome/nfp/bpf/offload.c
> +++ b/drivers/net/ethernet/netronome/nfp/bpf/offload.c
> @@ -385,6 +385,7 @@ nfp_bpf_map_alloc(struct nfp_app_bpf *bpf, struct bpf_offloaded_map *offmap)
> offmap->dev_priv = nfp_map;
> nfp_map->offmap = offmap;
> nfp_map->bpf = bpf;
> + spin_lock_init(&nfp_map->cache_lock);
>
> res = nfp_bpf_ctrl_alloc_map(bpf, &offmap->map);
> if (res < 0) {
> @@ -407,6 +408,8 @@ nfp_bpf_map_free(struct nfp_app_bpf *bpf, struct bpf_offloaded_map *offmap)
> struct nfp_bpf_map *nfp_map = offmap->dev_priv;
>
> nfp_bpf_ctrl_free_map(bpf, nfp_map);
> + dev_consume_skb_any(nfp_map->cache);
> + WARN_ON_ONCE(nfp_map->cache_blockers);
> list_del_init(&nfp_map->l);
> bpf->map_elems_in_use -= offmap->map.max_entries;
> bpf->maps_in_use--;
> --
> 2.21.0
>
^ permalink raw reply
* Re: [PATCH v2 net-next 02/15] MIPS: SGI-IP27: restructure ioc3 register access
From: Shannon Nelson @ 2019-08-29 21:26 UTC (permalink / raw)
To: Thomas Bogendoerfer, Ralf Baechle, Paul Burton, James Hogan,
David S. Miller, linux-mips, linux-kernel, netdev
In-Reply-To: <20190829155014.9229-3-tbogendoerfer@suse.de>
On 8/29/19 8:50 AM, Thomas Bogendoerfer wrote:
> Break up the big ioc3 register struct into functional pieces to
> make use in sub-function drivers more straightforward. And while
> doing that get rid of all volatile access by using readX/writeX.
>
> Signed-off-by: Thomas Bogendoerfer <tbogendoerfer@suse.de>
> ---
> diff --git a/arch/mips/sgi-ip27/ip27-console.c b/arch/mips/sgi-ip27/ip27-console.c
> index 6bdb48d41276..5886bee89d06 100644
> --- a/arch/mips/sgi-ip27/ip27-console.c
> +++ b/arch/mips/sgi-ip27/ip27-console.c
> @@ -35,6 +35,7 @@ void prom_putchar(char c)
> {
> struct ioc3_uartregs *uart = console_uart();
>
> - while ((uart->iu_lsr & 0x20) == 0);
> - uart->iu_thr = c;
> + while ((readb(&uart->iu_lsr) & 0x20) == 0)
> + ;
> + writeb(c, &uart->iu_thr);
> }
Is it ever possible to never see your bit get set?
Instead of a tight forever spin, you might add a short delay and a retry
limit.
I see this in several other times in the following code as well. It
might be interesting to see how many times through and perhaps how many
usecs are normally spent in these loops.
Not a binding request, just a thought...
sln
^ permalink raw reply
* Re: [PATCH v3 03/11] net/mlx5e: Remove unlikely() from WARN*() condition
From: Saeed Mahameed @ 2019-08-29 21:23 UTC (permalink / raw)
To: efremov@linux.com, linux-kernel@vger.kernel.org,
davem@davemloft.net
Cc: joe@perches.com, Boris Pismenny, netdev@vger.kernel.org,
leon@kernel.org, akpm@linux-foundation.org
In-Reply-To: <20190829165025.15750-3-efremov@linux.com>
On Thu, 2019-08-29 at 19:50 +0300, Denis Efremov wrote:
> "unlikely(WARN_ON_ONCE(x))" is excessive. WARN_ON_ONCE() already uses
> unlikely() internally.
>
> Signed-off-by: Denis Efremov <efremov@linux.com>
> Cc: Boris Pismenny <borisp@mellanox.com>
> Cc: Saeed Mahameed <saeedm@mellanox.com>
> Cc: Leon Romanovsky <leon@kernel.org>
> Cc: Joe Perches <joe@perches.com>
> Cc: Andrew Morton <akpm@linux-foundation.org>
> Cc: netdev@vger.kernel.org
> ---
> drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c | 2 +-
> 1 file changed, 1 insertion(+), 1 deletion(-)
>
> diff --git
> a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c
> b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c
> index 7833ddef0427..e5222d17df35 100644
> --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c
> +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c
> @@ -408,7 +408,7 @@ struct sk_buff *mlx5e_ktls_handle_tx_skb(struct
> net_device *netdev,
> goto out;
>
> tls_ctx = tls_get_ctx(skb->sk);
> - if (unlikely(WARN_ON_ONCE(tls_ctx->netdev != netdev)))
> + if (WARN_ON_ONCE(tls_ctx->netdev != netdev))
> goto err_out;
>
> priv_tx = mlx5e_get_ktls_tx_priv_ctx(tls_ctx);
Acked-by: Saeed Mahameed <saeedm@mellanox.com>
Dave, you can take this one.
^ permalink raw reply
* Re: [PATCH v2 net-next 00/15] ioc3-eth improvements
From: Jakub Kicinski @ 2019-08-29 21:15 UTC (permalink / raw)
To: Thomas Bogendoerfer
Cc: Ralf Baechle, Paul Burton, James Hogan, David S. Miller,
linux-mips, linux-kernel, netdev
In-Reply-To: <20190829155014.9229-1-tbogendoerfer@suse.de>
On Thu, 29 Aug 2019 17:49:58 +0200, Thomas Bogendoerfer wrote:
> In my patch series for splitting out the serial code from ioc3-eth
> by using a MFD device there was one big patch for ioc3-eth.c,
> which wasn't really usefull for reviews. This series contains the
> ioc3-eth changes splitted in smaller steps and few more cleanups.
> Only the conversion to MFD will be done later in a different series.
>
> Changes in v2:
> - use net_err_ratelimited for printing various ioc3 errors
> - added missing clearing of rx buf valid flags into ioc3_alloc_rings
> - use __func__ for printing out of memory messages
Only a few more comments on patch 5, otherwise looks good!
^ permalink raw reply
* Re: [PATCH v2 bpf-next 1/3] capability: introduce CAP_BPF and CAP_TRACING
From: Alexei Starovoitov @ 2019-08-29 21:10 UTC (permalink / raw)
To: Jesper Dangaard Brouer
Cc: Toke Høiland-Jørgensen, Alexei Starovoitov, luto, davem,
peterz, rostedt, netdev, bpf, kernel-team, linux-api
In-Reply-To: <20190829222530.3c6163ac@carbon>
On Thu, Aug 29, 2019 at 10:25:30PM +0200, Jesper Dangaard Brouer wrote:
> On Thu, 29 Aug 2019 20:05:49 +0200
> Toke Høiland-Jørgensen <toke@redhat.com> wrote:
>
> > Alexei Starovoitov <alexei.starovoitov@gmail.com> writes:
> >
> > > On Thu, Aug 29, 2019 at 09:44:18AM +0200, Toke Høiland-Jørgensen wrote:
> > >> Alexei Starovoitov <ast@kernel.org> writes:
> > >>
> > >> > CAP_BPF allows the following BPF operations:
> > >> > - Loading all types of BPF programs
> > >> > - Creating all types of BPF maps except:
> > >> > - stackmap that needs CAP_TRACING
> > >> > - devmap that needs CAP_NET_ADMIN
> > >> > - cpumap that needs CAP_SYS_ADMIN
> > >>
> > >> Why CAP_SYS_ADMIN instead of CAP_NET_ADMIN for cpumap?
> > >
> > > Currently it's cap_sys_admin and I think it should stay this way
> > > because it creates kthreads.
> >
> > Ah, right. I can sorta see that makes sense because of the kthreads, but
> > it also means that you can use all of XDP *except* cpumap with
> > CAP_NET_ADMIN+CAP_BPF. That is bound to create confusion, isn't it?
>
> Hmm... I see 'cpumap' primarily as a network stack feature. It is about
> starting the network stack on a specific CPU, allocating and building
> SKBs on that remote CPU. It can only be used together with XDP_REDIRECT.
> I would prefer CAP_NET_ADMIN like the devmap, to keep the XDP
> capabilities consistent.
I don't mind relaxing cpumap to cap_net_admin.
Looking at the reaction to the rest of the set. I'd rather discuss it
and do it later after basic cap_bpf is in.
^ permalink raw reply
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