* Re: [Suggestion] net/atm : for sprintf, need check the total write length whether larger than a page.
From: Chen Gang @ 2012-12-03 8:56 UTC (permalink / raw)
To: David.Woodhouse, David Miller, krzysiek, Joe Perches, edumazet,
netdev
In-Reply-To: <50AC58BC.1020004@asianux.com>
Hello Maintainers:
was this suggestion replied ? (it seems not).
and please help to check whether this suggestion is valid.
thanks.
gchen.
于 2012年11月21日 12:29, Chen Gang 写道:
> Hello David Miller:
>
> in net/atm/atm_sysfs.c:
> suggest to check the write length whether larger than a page.
> the length of parameter buf is one page size (reference: fill_read_buffer at fs/sysfs/file.c)
> and the count of atm adresses are not limited (reference: atm_dev_ioctl -> atm_add_addr)
>
> thanks.
>
> gchen.
>
> 34 static ssize_t show_atmaddress(struct device *cdev,
> 35 struct device_attribute *attr, char *buf)
> 36 {
> 37 unsigned long flags;
> 38 char *pos = buf;
> 39 struct atm_dev *adev = to_atm_dev(cdev);
> 40 struct atm_dev_addr *aaddr;
> 41 int bin[] = { 1, 2, 10, 6, 1 }, *fmt = bin;
> 42 int i, j;
> 43
> 44 spin_lock_irqsave(&adev->lock, flags);
> 45 list_for_each_entry(aaddr, &adev->local, entry) {
> 46 for (i = 0, j = 0; i < ATM_ESA_LEN; ++i, ++j) {
> 47 if (j == *fmt) {
> 48 pos += sprintf(pos, ".");
> 49 ++fmt;
> 50 j = 0;
> 51 }
> 52 pos += sprintf(pos, "%02x",
> 53 aaddr->addr.sas_addr.prv[i]);
> 54 }
> 55 pos += sprintf(pos, "\n");
> 56 }
> 57 spin_unlock_irqrestore(&adev->lock, flags);
> 58
> 59 return pos - buf;
> 60 }
> 61
>
>
>
> in net/atm/addr.c
>
> 67 int atm_add_addr(struct atm_dev *dev, const struct sockaddr_atmsvc *addr,
> 68 enum atm_addr_type_t atype)
> 69 {
> 70 unsigned long flags;
> 71 struct atm_dev_addr *this;
> 72 struct list_head *head;
> 73 int error;
> 74
> 75 error = check_addr(addr);
> 76 if (error)
> 77 return error;
> 78 spin_lock_irqsave(&dev->lock, flags);
> 79 if (atype == ATM_ADDR_LECS)
> 80 head = &dev->lecs;
> 81 else
> 82 head = &dev->local;
> 83 list_for_each_entry(this, head, entry) {
> 84 if (identical(&this->addr, addr)) {
> 85 spin_unlock_irqrestore(&dev->lock, flags);
> 86 return -EEXIST;
> 87 }
> 88 }
> 89 this = kmalloc(sizeof(struct atm_dev_addr), GFP_ATOMIC);
> 90 if (!this) {
> 91 spin_unlock_irqrestore(&dev->lock, flags);
> 92 return -ENOMEM;
> 93 }
> 94 this->addr = *addr;
> 95 list_add(&this->entry, head);
> 96 spin_unlock_irqrestore(&dev->lock, flags);
> 97 if (head == &dev->local)
> 98 notify_sigd(dev);
> 99 return 0;
> 100 }
> 101
>
>
> in net/atm/resources.c
>
> 195 int atm_dev_ioctl(unsigned int cmd, void __user *arg, int compat)
> 196 {
> 197 void __user *buf;
> 198 int error, len, number, size = 0;
> 199 struct atm_dev *dev;
> 200 struct list_head *p;
> 201 int *tmp_buf, *tmp_p;
> 202 int __user *sioc_len;
> 203 int __user *iobuf_len;
> 204
> 205 #ifndef CONFIG_COMPAT
> 206 compat = 0; /* Just so the compiler _knows_ */
> 207 #endif
> 208
> 209 switch (cmd) {
> 210 case ATM_GETNAMES:
> 211 if (compat) {
> 212 #ifdef CONFIG_COMPAT
> 213 struct compat_atm_iobuf __user *ciobuf = arg;
> 214 compat_uptr_t cbuf;
> 215 iobuf_len = &ciobuf->length;
> 216 if (get_user(cbuf, &ciobuf->buffer))
> 217 return -EFAULT;
> 218 buf = compat_ptr(cbuf);
> 219 #endif
> 220 } else {
> 221 struct atm_iobuf __user *iobuf = arg;
> 222 iobuf_len = &iobuf->length;
> 223 if (get_user(buf, &iobuf->buffer))
> 224 return -EFAULT;
> 225 }
> 226 if (get_user(len, iobuf_len))
> 227 return -EFAULT;
> 228 mutex_lock(&atm_dev_mutex);
> 229 list_for_each(p, &atm_devs)
> 230 size += sizeof(int);
> 231 if (size > len) {
> 232 mutex_unlock(&atm_dev_mutex);
> 233 return -E2BIG;
> 234 }
> 235 tmp_buf = kmalloc(size, GFP_ATOMIC);
> 236 if (!tmp_buf) {
> 237 mutex_unlock(&atm_dev_mutex);
> 238 return -ENOMEM;
> 239 }
> 240 tmp_p = tmp_buf;
> 241 list_for_each(p, &atm_devs) {
> 242 dev = list_entry(p, struct atm_dev, dev_list);
> 243 *tmp_p++ = dev->number;
> 244 }
> 245 mutex_unlock(&atm_dev_mutex);
> 246 error = ((copy_to_user(buf, tmp_buf, size)) ||
> 247 put_user(size, iobuf_len))
> 248 ? -EFAULT : 0;
> 249 kfree(tmp_buf);
> 250 return error;
> 251 default:
> 252 break;
> 253 }
> 254
> 255 if (compat) {
> 256 #ifdef CONFIG_COMPAT
> 257 struct compat_atmif_sioc __user *csioc = arg;
> 258 compat_uptr_t carg;
> 259
> 260 sioc_len = &csioc->length;
> 261 if (get_user(carg, &csioc->arg))
> 262 return -EFAULT;
> 263 buf = compat_ptr(carg);
> 264
> 265 if (get_user(len, &csioc->length))
> 266 return -EFAULT;
> 267 if (get_user(number, &csioc->number))
> 268 return -EFAULT;
> 269 #endif
> 270 } else {
> 271 struct atmif_sioc __user *sioc = arg;
> 272
> 273 sioc_len = &sioc->length;
> 274 if (get_user(buf, &sioc->arg))
> 275 return -EFAULT;
> 276 if (get_user(len, &sioc->length))
> 277 return -EFAULT;
> 278 if (get_user(number, &sioc->number))
> 279 return -EFAULT;
> 280 }
> 281
> 282 dev = try_then_request_module(atm_dev_lookup(number), "atm-device-%d",
> 283 number);
> 284 if (!dev)
> 285 return -ENODEV;
> 286
> 287 switch (cmd) {
> 288 case ATM_GETTYPE:
> 289 size = strlen(dev->type) + 1;
> 290 if (copy_to_user(buf, dev->type, size)) {
> 291 error = -EFAULT;
> 292 goto done;
> 293 }
> 294 break;
> 295 case ATM_GETESI:
> 296 size = ESI_LEN;
> 297 if (copy_to_user(buf, dev->esi, size)) {
> 298 error = -EFAULT;
> 299 goto done;
> 300 }
> 301 break;
> 302 case ATM_SETESI:
> 303 {
> 304 int i;
> 305
> 306 for (i = 0; i < ESI_LEN; i++)
> 307 if (dev->esi[i]) {
> 308 error = -EEXIST;
> 309 goto done;
> 310 }
> 311 }
> 312 /* fall through */
> 313 case ATM_SETESIF:
> 314 {
> 315 unsigned char esi[ESI_LEN];
> 316
> 317 if (!capable(CAP_NET_ADMIN)) {
> 318 error = -EPERM;
> 319 goto done;
> 320 }
> 321 if (copy_from_user(esi, buf, ESI_LEN)) {
> 322 error = -EFAULT;
> 323 goto done;
> 324 }
> 325 memcpy(dev->esi, esi, ESI_LEN);
> 326 error = ESI_LEN;
> 327 goto done;
> 328 }
> 329 case ATM_GETSTATZ:
> 330 if (!capable(CAP_NET_ADMIN)) {
> 331 error = -EPERM;
> 332 goto done;
> 333 }
> 334 /* fall through */
> 335 case ATM_GETSTAT:
> 336 size = sizeof(struct atm_dev_stats);
> 337 error = fetch_stats(dev, buf, cmd == ATM_GETSTATZ);
> 338 if (error)
> 339 goto done;
> 340 break;
> 341 case ATM_GETCIRANGE:
> 342 size = sizeof(struct atm_cirange);
> 343 if (copy_to_user(buf, &dev->ci_range, size)) {
> 344 error = -EFAULT;
> 345 goto done;
> 346 }
> 347 break;
> 348 case ATM_GETLINKRATE:
> 349 size = sizeof(int);
> 350 if (copy_to_user(buf, &dev->link_rate, size)) {
> 351 error = -EFAULT;
> 352 goto done;
> 353 }
> 354 break;
> 355 case ATM_RSTADDR:
> 356 if (!capable(CAP_NET_ADMIN)) {
> 357 error = -EPERM;
> 358 goto done;
> 359 }
> 360 atm_reset_addr(dev, ATM_ADDR_LOCAL);
> 361 break;
> 362 case ATM_ADDADDR:
> 363 case ATM_DELADDR:
> 364 case ATM_ADDLECSADDR:
> 365 case ATM_DELLECSADDR:
> 366 {
> 367 struct sockaddr_atmsvc addr;
> 368
> 369 if (!capable(CAP_NET_ADMIN)) {
> 370 error = -EPERM;
> 371 goto done;
> 372 }
> 373
> 374 if (copy_from_user(&addr, buf, sizeof(addr))) {
> 375 error = -EFAULT;
> 376 goto done;
> 377 }
> 378 if (cmd == ATM_ADDADDR || cmd == ATM_ADDLECSADDR)
> 379 error = atm_add_addr(dev, &addr,
> 380 (cmd == ATM_ADDADDR ?
> 381 ATM_ADDR_LOCAL : ATM_ADDR_LECS));
> 382 else
> 383 error = atm_del_addr(dev, &addr,
> 384 (cmd == ATM_DELADDR ?
> 385 ATM_ADDR_LOCAL : ATM_ADDR_LECS));
> 386 goto done;
> 387 }
> ... ...
> ... ...
>
>
>
--
Chen Gang
Asianux Corporation
^ permalink raw reply
* re: netdevice wanrouter: Convert directly reference of netdev->priv
From: Dan Carpenter @ 2012-12-03 9:04 UTC (permalink / raw)
To: wangchen; +Cc: netdev
Hello Wang Chen,
The patch 7be6065b39c3: "netdevice wanrouter: Convert directly
reference of netdev->priv" from Nov 20, 2008, leads to the following
Smatch warning:
net/wanrouter/wanmain.c:610 wanrouter_device_new_if()
error: potential NULL dereference 'dev'.
This is an old patch from 2008. It removed the allocation in
wanrouter_device_new_if() so it looks like wanrouter has been completely
broken for four years.
@@ -589,10 +591,6 @@ static int wanrouter_device_new_if(struct wan_device *wandev,
err = -EPROTONOSUPPORT;
goto out;
} else {
- dev = kzalloc(sizeof(struct net_device), GFP_KERNEL);
- err = -ENOBUFS;
- if (dev == NULL)
- goto out;
err = wandev->new_if(wandev, dev, cnf);
"dev" is still NULL after the call to ->new_if().
}
Here is what the code looks like now:
net/wanrouter/wanmain.c
590 if (cnf->config_id == WANCONFIG_MPPP) {
591 printk(KERN_INFO "%s: Wanpipe Mulit-Port PPP support has not been compiled in!\n",
592 wandev->name);
593 err = -EPROTONOSUPPORT;
594 goto out;
595 } else {
We were supposed to allocate "dev" here.
596 err = wandev->new_if(wandev, dev, cnf);
597 }
598
599 if (!err) {
600 /* Register network interface. This will invoke init()
601 * function supplied by the driver. If device registered
602 * successfully, add it to the interface list.
603 */
604
605 #ifdef WANDEBUG
606 printk(KERN_INFO "%s: registering interface %s...\n",
607 wanrouter_modname, dev->name);
608 #endif
609
610 err = register_netdev(dev);
^^^^^^^^^^^^^^^^^^^^
The kernel will always oops inside the call to register_netdev() because
"dev" is still NULL.
I suspect we should just revert the patch?
regards,
dan carpenter
^ permalink raw reply
* Re: [net-next rfc v7 2/3] virtio_net: multiqueue support
From: Michael S. Tsirkin @ 2012-12-03 9:47 UTC (permalink / raw)
To: Jason Wang
Cc: krkumar2, kvm, netdev, linux-kernel, virtualization, bhutchings,
jwhan, shiyer
In-Reply-To: <20845723.CY8SZ4xV0F@jason-thinkpad-t430s>
On Mon, Dec 03, 2012 at 02:05:27PM +0800, Jason Wang wrote:
> On Monday, December 03, 2012 12:34:08 PM Rusty Russell wrote:
> > Jason Wang <jasowang@redhat.com> writes:
> > > +static const struct ethtool_ops virtnet_ethtool_ops;
> > > +
> > > +/*
> > > + * Converting between virtqueue no. and kernel tx/rx queue no.
> > > + * 0:rx0 1:tx0 2:cvq 3:rx1 4:tx1 ... 2N+1:rxN 2N+2:txN
> > > + */
> > > +static int vq2txq(struct virtqueue *vq)
> > > +{
> > > + int index = virtqueue_get_queue_index(vq);
> > > + return index == 1 ? 0 : (index - 2) / 2;
> > > +}
> > > +
> > > +static int txq2vq(int txq)
> > > +{
> > > + return txq ? 2 * txq + 2 : 1;
> > > +}
> > > +
> > > +static int vq2rxq(struct virtqueue *vq)
> > > +{
> > > + int index = virtqueue_get_queue_index(vq);
> > > + return index ? (index - 1) / 2 : 0;
> > > +}
> > > +
> > > +static int rxq2vq(int rxq)
> > > +{
> > > + return rxq ? 2 * rxq + 1 : 0;
> > > +}
> > > +
> >
> > I thought MST changed the proposed spec to make the control queue always
> > the last one, so this logic becomes trivial.
>
> But it may break the support of legacy guest. If we boot a legacy single queue
> guest on a 2 queue virtio-net device. It may think vq 2 is cvq which is indeed
> rx1.
Legacy guyest support should be handled by host using feature
bits in the usual way: host should detect legacy guest
by checking the VIRTIO_NET_F_RFS feature.
If VIRTIO_NET_F_RFS is acked, cvq is vq max_virtqueue_pairs * 2.
If it's not acked, cvq is vq 2.
^ permalink raw reply
* [PATCH 1/1] net: mvneta: Remove unneeded version.h header inclusion
From: Sachin Kamat @ 2012-12-03 9:45 UTC (permalink / raw)
To: netdev; +Cc: thomas.petazzoni, sachin.kamat, patches
linux/version.h inclusion is not necessary.
Signed-off-by: Sachin Kamat <sachin.kamat@linaro.org>
---
drivers/net/ethernet/marvell/mvneta.c | 1 -
1 files changed, 0 insertions(+), 1 deletions(-)
diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c
index 3f8086b..a1e0e9f 100644
--- a/drivers/net/ethernet/marvell/mvneta.c
+++ b/drivers/net/ethernet/marvell/mvneta.c
@@ -12,7 +12,6 @@
*/
#include <linux/kernel.h>
-#include <linux/version.h>
#include <linux/netdevice.h>
#include <linux/etherdevice.h>
#include <linux/platform_device.h>
--
1.7.4.1
^ permalink raw reply related
* [PATCH net 1/1] bnx2x: recognize fan failure
From: Yuval Mintz @ 2012-12-03 9:56 UTC (permalink / raw)
To: davem, netdev; +Cc: ariele, Yaniv Rosner, Yuval Mintz, Eilon Greenstein
From: Yaniv Rosner <yaniv.rosner@broadcom.com>
If fan failure is detected, MCP prevents PCI I/O registers from being
mapped to the bar, causing a fatal error as driver is unaware.
This patch recognizes such an event occurred and gracefully terminates
the probe process.
Signed-off-by: Yaniv Rosner <yaniv.rosner@broadcom.com>
Signed-off-by: Yuval Mintz <yuvalmin@broadcom.com>
Signed-off-by: Eilon Greenstein <eilong@broadcom.com>
---
Hi Dave,
This patch prevents a fatal error on newer bnx2x boards.
Please consider applying it to 'net'.
---
drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c | 8 ++++++++
drivers/net/ethernet/broadcom/bnx2x/bnx2x_reg.h | 4 +++-
2 files changed, 11 insertions(+), 1 deletions(-)
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
index 01611b3..101392b 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
@@ -11346,6 +11346,14 @@ static int __devinit bnx2x_init_dev(struct pci_dev *pdev,
goto err_out_disable;
}
+ pci_read_config_dword(pdev, PCICFG_REVISION_ID_OFFSET, &pci_cfg_dword);
+ if ((pci_cfg_dword & PCICFG_REVESION_ID_MASK) ==
+ PCICFG_REVESION_ID_ERROR_VAL) {
+ pr_err("PCI device error, probably due to fan failure, aborting\n");
+ rc = -ENODEV;
+ goto err_out_disable;
+ }
+
if (atomic_read(&pdev->enable_cnt) == 1) {
rc = pci_request_regions(pdev, DRV_MODULE_NAME);
if (rc) {
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_reg.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_reg.h
index 1b1999d..698cbf7 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_reg.h
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_reg.h
@@ -6130,7 +6130,9 @@
#define PCICFG_COMMAND_INT_DISABLE (1<<10)
#define PCICFG_COMMAND_RESERVED (0x1f<<11)
#define PCICFG_STATUS_OFFSET 0x06
-#define PCICFG_REVESION_ID_OFFSET 0x08
+#define PCICFG_REVISION_ID_OFFSET 0x08
+#define PCICFG_REVESION_ID_MASK 0xff
+#define PCICFG_REVESION_ID_ERROR_VAL 0xff
#define PCICFG_CACHE_LINE_SIZE 0x0c
#define PCICFG_LATENCY_TIMER 0x0d
#define PCICFG_BAR_1_LOW 0x10
--
1.7.1
^ permalink raw reply related
* Re: [net-next rfc v7 2/3] virtio_net: multiqueue support
From: Jason Wang @ 2012-12-03 10:01 UTC (permalink / raw)
To: Michael S. Tsirkin
Cc: krkumar2, kvm, netdev, linux-kernel, virtualization, bhutchings,
jwhan, shiyer
In-Reply-To: <20121203094735.GA23009@redhat.com>
On 12/03/2012 05:47 PM, Michael S. Tsirkin wrote:
> On Mon, Dec 03, 2012 at 02:05:27PM +0800, Jason Wang wrote:
>> On Monday, December 03, 2012 12:34:08 PM Rusty Russell wrote:
>>> Jason Wang <jasowang@redhat.com> writes:
>>>> +static const struct ethtool_ops virtnet_ethtool_ops;
>>>> +
>>>> +/*
>>>> + * Converting between virtqueue no. and kernel tx/rx queue no.
>>>> + * 0:rx0 1:tx0 2:cvq 3:rx1 4:tx1 ... 2N+1:rxN 2N+2:txN
>>>> + */
>>>> +static int vq2txq(struct virtqueue *vq)
>>>> +{
>>>> + int index = virtqueue_get_queue_index(vq);
>>>> + return index == 1 ? 0 : (index - 2) / 2;
>>>> +}
>>>> +
>>>> +static int txq2vq(int txq)
>>>> +{
>>>> + return txq ? 2 * txq + 2 : 1;
>>>> +}
>>>> +
>>>> +static int vq2rxq(struct virtqueue *vq)
>>>> +{
>>>> + int index = virtqueue_get_queue_index(vq);
>>>> + return index ? (index - 1) / 2 : 0;
>>>> +}
>>>> +
>>>> +static int rxq2vq(int rxq)
>>>> +{
>>>> + return rxq ? 2 * rxq + 1 : 0;
>>>> +}
>>>> +
>>> I thought MST changed the proposed spec to make the control queue always
>>> the last one, so this logic becomes trivial.
>> But it may break the support of legacy guest. If we boot a legacy single queue
>> guest on a 2 queue virtio-net device. It may think vq 2 is cvq which is indeed
>> rx1.
> Legacy guyest support should be handled by host using feature
> bits in the usual way: host should detect legacy guest
> by checking the VIRTIO_NET_F_RFS feature.
>
> If VIRTIO_NET_F_RFS is acked, cvq is vq max_virtqueue_pairs * 2.
> If it's not acked, cvq is vq 2.
>
We could, but we didn't gain much from this. Furthermore, we need also do the dynamic creation/destroying of virtqueues during feature negotiation which seems not supported in qemu now.
^ permalink raw reply
* Re: [net-next rfc v7 2/3] virtio_net: multiqueue support
From: Michael S. Tsirkin @ 2012-12-03 10:14 UTC (permalink / raw)
To: Jason Wang
Cc: rusty, krkumar2, virtualization, netdev, linux-kernel, kvm,
bhutchings, jwhan, shiyer
In-Reply-To: <1354011360-39479-3-git-send-email-jasowang@redhat.com>
On Tue, Nov 27, 2012 at 06:15:59PM +0800, Jason Wang wrote:
> - if (!try_fill_recv(&vi->rq, GFP_KERNEL))
> - schedule_delayed_work(&vi->rq.refill, 0);
> + for (i = 0; i < vi->max_queue_pairs; i++)
> + if (!try_fill_recv(&vi->rq[i], GFP_KERNEL))
> + schedule_delayed_work(&vi->rq[i].refill, 0);
>
> mutex_lock(&vi->config_lock);
> vi->config_enable = true;
> mutex_unlock(&vi->config_lock);
>
> + BUG_ON(virtnet_set_queues(vi));
> +
> return 0;
> }
> #endif
Also crashing on device nack of command is also not nice.
In this case it seems we can just switch to
single-queue mode which should always be safe.
^ permalink raw reply
* Re: [RFC PATCH 2/2] tun: fix LSM/SELinux labeling of tun/tap devices
From: Jason Wang @ 2012-12-03 10:15 UTC (permalink / raw)
To: Paul Moore; +Cc: netdev, linux-security-module, selinux
In-Reply-To: <20121129220637.30020.9980.stgit@sifl>
On 11/30/2012 06:06 AM, Paul Moore wrote:
> This patch corrects some problems with LSM/SELinux that were introduced
> with the multiqueue patchset. The problem stems from the fact that the
> multiqueue work changed the relationship between the tun device and its
> associated socket; before the socket persisted for the life of the
> device, however after the multiqueue changes the socket only persisted
> for the life of the userspace connection (fd open). For non-persistent
> devices this is not an issue, but for persistent devices this can cause
> the tun device to lose its SELinux label.
>
> We correct this problem by adding an opaque LSM security blob to the
> tun device struct which allows us to have the LSM security state, e.g.
> SELinux labeling information, persist for the lifetime of the tun
> device.
Hi Paul, thanks for the patchset. I've one question, see below.
>
> Signed-off-by: Paul Moore <pmoore@redhat.com>
> ---
> drivers/net/tun.c | 13 ++++++++---
> include/linux/security.h | 37 ++++++++++++++++++++++-----------
> security/capability.c | 14 +++++++++---
> security/security.c | 22 ++++++++++++-------
> security/selinux/hooks.c | 42 +++++++++++++++++++++++--------------
> security/selinux/include/objsec.h | 4 ++++
> 6 files changed, 88 insertions(+), 44 deletions(-)
>
> diff --git a/drivers/net/tun.c b/drivers/net/tun.c
> index 877ffe2..85cc924 100644
> --- a/drivers/net/tun.c
> +++ b/drivers/net/tun.c
> @@ -182,6 +182,7 @@ struct tun_struct {
> struct hlist_head flows[TUN_NUM_FLOW_ENTRIES];
> struct timer_list flow_gc_timer;
> unsigned long ageing_time;
> + void *security;
> };
>
> static inline u32 tun_hashfn(u32 rxhash)
> @@ -465,6 +466,10 @@ static int tun_attach(struct tun_struct *tun, struct file *file)
> struct tun_file *tfile = file->private_data;
> int err;
>
> + err = security_tun_dev_attach(tfile->socket.sk, tun->security);
> + if (err < 0)
> + goto out;
> +
> err = -EINVAL;
> if (rcu_dereference_protected(tfile->tun, lockdep_rtnl_is_held()))
> goto out;
> @@ -1365,6 +1370,7 @@ static void tun_free_netdev(struct net_device *dev)
> struct tun_struct *tun = netdev_priv(dev);
>
> tun_flow_uninit(tun);
> + security_tun_dev_free_security(tun->security);
> free_netdev(dev);
> }
>
> @@ -1548,9 +1554,6 @@ static int tun_set_iff(struct net *net, struct file *file, struct ifreq *ifr)
>
> if (tun_not_capable(tun))
> return -EPERM;
> - err = security_tun_dev_attach(tfile->socket.sk);
> - if (err < 0)
> - return err;
>
> err = tun_attach(tun, file);
> if (err < 0)
> @@ -1601,7 +1604,9 @@ static int tun_set_iff(struct net *net, struct file *file, struct ifreq *ifr)
>
> spin_lock_init(&tun->lock);
>
> - security_tun_dev_post_create(&tfile->sk);
> + err = security_tun_dev_alloc_security(&tun->security);
> + if (err < 0)
> + goto err_free_dev;
>
> tun_net_init(dev);
>
> diff --git a/include/linux/security.h b/include/linux/security.h
> index 05e88bd..260e151 100644
> --- a/include/linux/security.h
> +++ b/include/linux/security.h
> @@ -983,17 +983,23 @@ static inline void security_free_mnt_opts(struct security_mnt_opts *opts)
> * tells the LSM to decrement the number of secmark labeling rules loaded
> * @req_classify_flow:
> * Sets the flow's sid to the openreq sid.
> + * @tun_dev_alloc_security:
> + * This hook allows a module to allocate a security structure for a TUN
> + * device.
> + * @security pointer to a security structure pointer.
> + * Returns a zero on success, negative values on failure.
> + * @tun_dev_free_security:
> + * This hook allows a module to free the security structure for a TUN
> + * device.
> + * @security pointer to the TUN device's security structure
> * @tun_dev_create:
> * Check permissions prior to creating a new TUN device.
> - * @tun_dev_post_create:
> - * This hook allows a module to update or allocate a per-socket security
> - * structure.
> - * @sk contains the newly created sock structure.
> * @tun_dev_attach:
> * Check permissions prior to attaching to a persistent TUN device. This
> * hook can also be used by the module to update any security state
> * associated with the TUN device's sock structure.
> * @sk contains the existing sock structure.
> + * @security pointer to the TUN device's security structure.
> *
> * Security hooks for XFRM operations.
> *
> @@ -1613,9 +1619,10 @@ struct security_operations {
> void (*secmark_refcount_inc) (void);
> void (*secmark_refcount_dec) (void);
> void (*req_classify_flow) (const struct request_sock *req, struct flowi *fl);
> - int (*tun_dev_create)(void);
> - void (*tun_dev_post_create)(struct sock *sk);
> - int (*tun_dev_attach)(struct sock *sk);
> + int (*tun_dev_alloc_security) (void **security);
> + void (*tun_dev_free_security) (void *security);
> + int (*tun_dev_create) (void);
> + int (*tun_dev_attach) (struct sock *sk, void *security);
> #endif /* CONFIG_SECURITY_NETWORK */
>
> #ifdef CONFIG_SECURITY_NETWORK_XFRM
> @@ -2553,9 +2560,10 @@ void security_inet_conn_established(struct sock *sk,
> int security_secmark_relabel_packet(u32 secid);
> void security_secmark_refcount_inc(void);
> void security_secmark_refcount_dec(void);
> +int security_tun_dev_alloc_security(void **security);
> +void security_tun_dev_free_security(void *security);
> int security_tun_dev_create(void);
> -void security_tun_dev_post_create(struct sock *sk);
> -int security_tun_dev_attach(struct sock *sk);
> +int security_tun_dev_attach(struct sock *sk, void *security);
>
> #else /* CONFIG_SECURITY_NETWORK */
> static inline int security_unix_stream_connect(struct sock *sock,
> @@ -2720,16 +2728,21 @@ static inline void security_secmark_refcount_dec(void)
> {
> }
>
> -static inline int security_tun_dev_create(void)
> +static inline int security_tun_dev_alloc_security(void **security)
> {
> return 0;
> }
>
> -static inline void security_tun_dev_post_create(struct sock *sk)
> +static inline void security_tun_dev_free_security(void *security)
> {
> }
>
> -static inline int security_tun_dev_attach(struct sock *sk)
> +static inline int security_tun_dev_create(void)
> +{
> + return 0;
> +}
> +
> +static inline int security_tun_dev_attach(struct sock *sk, void *security)
> {
> return 0;
> }
> diff --git a/security/capability.c b/security/capability.c
> index b14a30c..fd6e2dc 100644
> --- a/security/capability.c
> +++ b/security/capability.c
> @@ -704,16 +704,21 @@ static void cap_req_classify_flow(const struct request_sock *req,
> {
> }
>
> -static int cap_tun_dev_create(void)
> +static int cap_tun_dev_alloc_security(void **security)
> {
> return 0;
> }
>
> -static void cap_tun_dev_post_create(struct sock *sk)
> +static void cap_tun_dev_free_security(void *security)
> +{
> +}
> +
> +static int cap_tun_dev_create(void)
> {
> + return 0;
> }
>
> -static int cap_tun_dev_attach(struct sock *sk)
> +static int cap_tun_dev_attach(struct sock *sk, void *security)
> {
> return 0;
> }
> @@ -1044,8 +1049,9 @@ void __init security_fixup_ops(struct security_operations *ops)
> set_to_cap_if_null(ops, secmark_refcount_inc);
> set_to_cap_if_null(ops, secmark_refcount_dec);
> set_to_cap_if_null(ops, req_classify_flow);
> + set_to_cap_if_null(ops, tun_dev_alloc_security);
> + set_to_cap_if_null(ops, tun_dev_free_security);
> set_to_cap_if_null(ops, tun_dev_create);
> - set_to_cap_if_null(ops, tun_dev_post_create);
> set_to_cap_if_null(ops, tun_dev_attach);
> #endif /* CONFIG_SECURITY_NETWORK */
> #ifdef CONFIG_SECURITY_NETWORK_XFRM
> diff --git a/security/security.c b/security/security.c
> index 8dcd4ae..613ad36 100644
> --- a/security/security.c
> +++ b/security/security.c
> @@ -1244,21 +1244,27 @@ void security_secmark_refcount_dec(void)
> }
> EXPORT_SYMBOL(security_secmark_refcount_dec);
>
> -int security_tun_dev_create(void)
> +int security_tun_dev_alloc_security(void **security)
> {
> - return security_ops->tun_dev_create();
> + return security_ops->tun_dev_alloc_security(security);
> }
> -EXPORT_SYMBOL(security_tun_dev_create);
> +EXPORT_SYMBOL(security_tun_dev_alloc_security);
>
> -void security_tun_dev_post_create(struct sock *sk)
> +void security_tun_dev_free_security(void *security)
> {
> - return security_ops->tun_dev_post_create(sk);
> + security_ops->tun_dev_free_security(security);
> }
> -EXPORT_SYMBOL(security_tun_dev_post_create);
> +EXPORT_SYMBOL(security_tun_dev_free_security);
> +
> +int security_tun_dev_create(void)
> +{
> + return security_ops->tun_dev_create();
> +}
> +EXPORT_SYMBOL(security_tun_dev_create);
>
> -int security_tun_dev_attach(struct sock *sk)
> +int security_tun_dev_attach(struct sock *sk, void *security)
> {
> - return security_ops->tun_dev_attach(sk);
> + return security_ops->tun_dev_attach(sk, security);
> }
> EXPORT_SYMBOL(security_tun_dev_attach);
>
> diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c
> index 61a5336..67b3423 100644
> --- a/security/selinux/hooks.c
> +++ b/security/selinux/hooks.c
> @@ -4414,40 +4414,49 @@ static int selinux_tun_dev_create(void)
> NULL);
> }
>
> -static void selinux_tun_dev_post_create(struct sock *sk)
> +static int selinux_tun_dev_alloc_security(void **security)
> {
> - struct sk_security_struct *sksec = sk->sk_security;
> + struct tun_security_struct *tunsec;
>
> - /* we don't currently perform any NetLabel based labeling here and it
> - * isn't clear that we would want to do so anyway; while we could apply
> - * labeling without the support of the TUN user the resulting labeled
> - * traffic from the other end of the connection would almost certainly
> - * cause confusion to the TUN user that had no idea network labeling
> - * protocols were being used */
> + tunsec = kzalloc(sizeof(*tunsec), GFP_KERNEL);
> + if (!tunsec)
> + return -ENOMEM;
> + tunsec->sid = current_sid();
>
> - /* see the comments in selinux_tun_dev_create() about why we don't use
> - * the sockcreate SID here */
> + *security = tunsec;
> + return 0;
> +}
>
> - sksec->sid = current_sid();
> - sksec->sclass = SECCLASS_TUN_SOCKET;
> +static void selinux_tun_dev_free_security(void *security)
> +{
> + kfree(security);
> }
>
> -static int selinux_tun_dev_attach(struct sock *sk)
> +static int selinux_tun_dev_attach(struct sock *sk, void *security)
> {
> + struct tun_security_struct *tunsec = security;
> struct sk_security_struct *sksec = sk->sk_security;
> u32 sid = current_sid();
> int err;
>
> + /* we don't currently perform any NetLabel based labeling here and it
> + * isn't clear that we would want to do so anyway; while we could apply
> + * labeling without the support of the TUN user the resulting labeled
> + * traffic from the other end of the connection would almost certainly
> + * cause confusion to the TUN user that had no idea network labeling
> + * protocols were being used */
> +
> err = avc_has_perm(sid, sksec->sid, SECCLASS_TUN_SOCKET,
> TUN_SOCKET__RELABELFROM, NULL);
> if (err)
> return err;
> - err = avc_has_perm(sid, sid, SECCLASS_TUN_SOCKET,
> + err = avc_has_perm(sid, tunsec->sid, SECCLASS_TUN_SOCKET,
> TUN_SOCKET__RELABELTO, NULL);
> if (err)
> return err;
>
> - sksec->sid = sid;
> + sksec->sid = tunsec->sid;
> + sksec->sclass = SECCLASS_TUN_SOCKET;
I'm not sure whether this is correct, looks like we need to differ between TUNSETQUEUE and TUNSETIFF. When userspace call TUNSETIFF for persistent device, looks like we need change the sid of tunsec
like in the past.
Thanks
>
> return 0;
> }
> @@ -5642,8 +5651,9 @@ static struct security_operations selinux_ops = {
> .secmark_refcount_inc = selinux_secmark_refcount_inc,
> .secmark_refcount_dec = selinux_secmark_refcount_dec,
> .req_classify_flow = selinux_req_classify_flow,
> + .tun_dev_alloc_security = selinux_tun_dev_alloc_security,
> + .tun_dev_free_security = selinux_tun_dev_free_security,
> .tun_dev_create = selinux_tun_dev_create,
> - .tun_dev_post_create = selinux_tun_dev_post_create,
> .tun_dev_attach = selinux_tun_dev_attach,
>
> #ifdef CONFIG_SECURITY_NETWORK_XFRM
> diff --git a/security/selinux/include/objsec.h b/security/selinux/include/objsec.h
> index 26c7eee..aa47bca 100644
> --- a/security/selinux/include/objsec.h
> +++ b/security/selinux/include/objsec.h
> @@ -110,6 +110,10 @@ struct sk_security_struct {
> u16 sclass; /* sock security class */
> };
>
> +struct tun_security_struct {
> + u32 sid; /* SID for the tun device sockets */
> +};
> +
> struct key_security_struct {
> u32 sid; /* SID of key */
> };
>
> --
> To unsubscribe from this list: send the line "unsubscribe netdev" in
> the body of a message to majordomo@vger.kernel.org
> More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply
* Re: [net-next rfc v7 2/3] virtio_net: multiqueue support
From: Jason Wang @ 2012-12-03 10:30 UTC (permalink / raw)
To: Michael S. Tsirkin
Cc: krkumar2, kvm, netdev, linux-kernel, virtualization, bhutchings,
jwhan, shiyer
In-Reply-To: <20121203101436.GB23009@redhat.com>
On 12/03/2012 06:14 PM, Michael S. Tsirkin wrote:
> On Tue, Nov 27, 2012 at 06:15:59PM +0800, Jason Wang wrote:
>> > - if (!try_fill_recv(&vi->rq, GFP_KERNEL))
>> > - schedule_delayed_work(&vi->rq.refill, 0);
>> > + for (i = 0; i < vi->max_queue_pairs; i++)
>> > + if (!try_fill_recv(&vi->rq[i], GFP_KERNEL))
>> > + schedule_delayed_work(&vi->rq[i].refill, 0);
>> >
>> > mutex_lock(&vi->config_lock);
>> > vi->config_enable = true;
>> > mutex_unlock(&vi->config_lock);
>> >
>> > + BUG_ON(virtnet_set_queues(vi));
>> > +
>> > return 0;
>> > }
>> > #endif
> Also crashing on device nack of command is also not nice.
> In this case it seems we can just switch to
> single-queue mode which should always be safe.
Not sure it's safe. It depends on the reason why this call fails. If we
left a state that the driver only use single queue but the device use
multi queues, we may still lost the network.
^ permalink raw reply
* RE: [PATCH 5/5] smsc95xx: expand check_ macros
From: David Laight @ 2012-12-03 10:41 UTC (permalink / raw)
To: Steve Glendinning, netdev
In-Reply-To: <1354290952-27109-6-git-send-email-steve.glendinning@shawell.net>
> - check_warn_return(ret, "Error reading MII_ACCESS\n");
> + if (ret < 0) {
> + netdev_warn(dev->net, "Error reading MII_ACCESS\n");
> + return ret;
> + }
> +
It might be worth defining something like:
#define check_warn(dev, ret, errmsg) \
(ret >= 0 ? 0 : (netdev_warn(dev->net, errmsg), ret))
so the above code can be:
if (check_warn(dev, ret, "Error reading MII_ACCESS\n"))
return ret;
David
^ permalink raw reply
* [PATCHv5] virtio-spec: virtio network device RFS support
From: Michael S. Tsirkin @ 2012-12-03 10:58 UTC (permalink / raw)
To: Jason Wang; +Cc: netdev, kvm, virtualization
Add RFS support to virtio network device.
Add a new feature flag VIRTIO_NET_F_RFS for this feature, a new
configuration field max_virtqueue_pairs to detect supported number of
virtqueues as well as a new command VIRTIO_NET_CTRL_RFS to program
packet steering for unidirectional protocols.
---
Changes from v5:
- Address Rusty's comments.
Changes are only in the text, not the ideas.
- Some minor formatting changes.
Changes from v4:
- address Jason's comments
- have configuration specify the number of VQ pairs and not pairs - 1
Changes from v3:
- rename multiqueue -> rfs this is what we support
- Be more explicit about what driver should do.
- Simplify layout making VQs functionality depend on feature.
- Remove unused commands, only leave in programming # of queues
Changes from v2:
Address Jason's comments on v2:
- Changed STEERING_HOST to STEERING_RX_FOLLOWS_TX:
this is both clearer and easier to support.
It does not look like we need a separate steering command
since host can just watch tx packets as they go.
- Moved RX and TX steering sections near each other.
- Add motivation for other changes in v2
Changes from Jason's rfc:
- reserved vq 3: this makes all rx vqs even and tx vqs odd, which
looks nicer to me.
- documented packet steering, added a generalized steering programming
command. Current modes are single queue and host driven multiqueue,
but I envision support for guest driven multiqueue in the future.
- make default vqs unused when in mq mode - this wastes some memory
but makes it more efficient to switch between modes as
we can avoid this causing packet reordering.
Rusty, could you please take a look and comment soon?
If this looks OK to everyone, we can proceed with finalizing the
implementation. Would be nice to try and put it in 3.8.
virtio-spec.lyx | 310 ++++++++++++++++++++++++++++++++++++++++++++++++++++++--
1 file changed, 301 insertions(+), 9 deletions(-)
diff --git a/virtio-spec.lyx b/virtio-spec.lyx
index 83f2771..119925c 100644
--- a/virtio-spec.lyx
+++ b/virtio-spec.lyx
@@ -59,6 +59,7 @@
\author -608949062 "Rusty Russell,,,"
\author -385801441 "Cornelia Huck" cornelia.huck@de.ibm.com
\author 1531152142 "Paolo Bonzini,,,"
+\author 1986246365 "Michael S. Tsirkin"
\end_header
\begin_body
@@ -4170,9 +4171,46 @@ ID 1
\end_layout
\begin_layout Description
-Virtqueues 0:receiveq.
- 1:transmitq.
- 2:controlq
+Virtqueues 0:receiveq
+\change_inserted 1986246365 1352742829
+0
+\change_unchanged
+.
+ 1:transmitq
+\change_inserted 1986246365 1352742832
+0
+\change_deleted 1986246365 1352742947
+.
+
+\change_inserted 1986246365 1352742952
+.
+ ....
+ 2N
+\begin_inset Foot
+status open
+
+\begin_layout Plain Layout
+
+\change_inserted 1986246365 1354531595
+N=0 if VIRTIO_NET_F_RFS is not negotiated, otherwise N is derived from
+\emph on
+max_virtqueue_pairs
+\emph default
+ control
+\emph on
+
+\emph default
+field.
+
+\end_layout
+
+\end_inset
+
+: receivqN.
+ 2N+1: transmitqN.
+ 2N+
+\change_unchanged
+2:controlq
\begin_inset Foot
status open
@@ -4343,6 +4381,16 @@ VIRTIO_NET_F_CTRL_VLAN
\begin_layout Description
VIRTIO_NET_F_GUEST_ANNOUNCE(21) Guest can send gratuitous packets.
+\change_inserted 1986246365 1352742767
+
+\end_layout
+
+\begin_layout Description
+
+\change_inserted 1986246365 1352742808
+VIRTIO_NET_F_RFS(22) Device supports Receive Flow Steering.
+\change_unchanged
+
\end_layout
\end_deeper
@@ -4355,11 +4403,45 @@ configuration
\begin_inset space ~
\end_inset
-layout Two configuration fields are currently defined.
+layout
+\change_deleted 1986246365 1352743300
+Two
+\change_inserted 1986246365 1354531413
+Three
+\change_unchanged
+ configuration fields are currently defined.
The mac address field always exists (though is only valid if VIRTIO_NET_F_MAC
is set), and the status field only exists if VIRTIO_NET_F_STATUS is set.
Two read-only bits are currently defined for the status field: VIRTIO_NET_S_LIN
K_UP and VIRTIO_NET_S_ANNOUNCE.
+
+\change_inserted 1986246365 1354531470
+ The following read-only field,
+\emph on
+max_virtqueue_pairs
+\emph default
+ only exists if VIRTIO_NET_F_RFS is set.
+ This field specifies the maximum number of each of transmit and receive
+ virtqueues (receiveq0..receiveq
+\emph on
+N
+\emph default
+ and transmitq0..transmitq
+\emph on
+N
+\emph default
+ respectively;
+\emph on
+N
+\emph default
+=
+\emph on
+max_virtqueue_pairs - 1
+\emph default
+) that can be configured once VIRTIO_NET_F_RFS is negotiated.
+ Legal values for this field are 1 to 8000h.
+
+\change_unchanged
\begin_inset listings
inline false
@@ -4392,6 +4474,17 @@ struct virtio_net_config {
\begin_layout Plain Layout
u16 status;
+\change_inserted 1986246365 1354531427
+
+\end_layout
+
+\begin_layout Plain Layout
+
+\change_inserted 1986246365 1354531437
+
+ u16 max_virtqueue_pairs;
+\change_unchanged
+
\end_layout
\begin_layout Plain Layout
@@ -4410,7 +4503,24 @@ Device Initialization
\begin_layout Enumerate
The initialization routine should identify the receive and transmission
- virtqueues.
+ virtqueues
+\change_inserted 1986246365 1352744077
+, up to N+1 of each kind
+\change_unchanged
+.
+
+\change_inserted 1986246365 1352743942
+ If VIRTIO_NET_F_RFS feature bit is negotiated,
+\emph on
+N=max_virtqueue_pairs-1
+\emph default
+, otherwise identify
+\emph on
+N=0
+\emph default
+.
+\change_unchanged
+
\end_layout
\begin_layout Enumerate
@@ -4452,10 +4562,33 @@ status
config field.
Otherwise, the link should be assumed active.
+\change_inserted 1986246365 1354529306
+
\end_layout
\begin_layout Enumerate
-The receive virtqueue should be filled with receive buffers.
+
+\change_inserted 1986246365 1354531717
+Only receiveq0, transmitq0 and controlq are used by default.
+ To use more queues driver must negotiate the VIRTIO_NET_F_RFS feature;
+ initialize up to
+\emph on
+max_virtqueue_pairs
+\emph default
+ of each of transmit and receive queues; execute_VIRTIO_NET_CTRL_RFS_VQ_PAIRS_SE
+T command specifying the number of the transmit and receive queues that
+ is going to be used and wait until the device consumes the controlq buffer
+ and acks this command.
+\change_unchanged
+
+\end_layout
+
+\begin_layout Enumerate
+The receive virtqueue
+\change_inserted 1986246365 1352743953
+s
+\change_unchanged
+ should be filled with receive buffers.
This is described in detail below in
\begin_inset Quotes eld
\end_inset
@@ -4550,8 +4683,15 @@ Device Operation
\end_layout
\begin_layout Standard
-Packets are transmitted by placing them in the transmitq, and buffers for
- incoming packets are placed in the receiveq.
+Packets are transmitted by placing them in the transmitq
+\change_inserted 1986246365 1353593685
+0..transmitqN
+\change_unchanged
+, and buffers for incoming packets are placed in the receiveq
+\change_inserted 1986246365 1353593692
+0..receiveqN
+\change_unchanged
+.
In each case, the packet itself is preceeded by a header:
\end_layout
@@ -4861,6 +5001,17 @@ If VIRTIO_NET_F_MRG_RXBUF is negotiated, each buffer must be at least the
struct virtio_net_hdr
\family default
.
+\change_inserted 1986246365 1353594518
+
+\end_layout
+
+\begin_layout Standard
+
+\change_inserted 1986246365 1353594638
+If VIRTIO_NET_F_RFS is negotiated, each of receiveq0...receiveqN that will
+ be used should be populated with receive buffers.
+\change_unchanged
+
\end_layout
\begin_layout Subsection*
@@ -5293,8 +5444,149 @@ Sending VIRTIO_NET_CTRL_ANNOUNCE_ACK command through control vq.
\end_layout
-\begin_layout Enumerate
+\begin_layout Subsection*
+
+\change_inserted 1986246365 1353593879
+Packet Receive Flow Steering
+\end_layout
+
+\begin_layout Standard
+
+\change_inserted 1986246365 1354528882
+If the driver negotiates the VIRTIO_NET_F_RFS feature bit (depends on VIRTIO_NET
+_F_CTRL_VQ), it can transmit outgoing packets on one of the multiple transmitq0..t
+ransmitqN and ask the device to queue incoming packets into one the multiple
+ receiveq0..receiveqN depending on the packet flow.
+\change_unchanged
+
+\end_layout
+
+\begin_layout Standard
+
+\change_inserted 1986246365 1353594292
+\begin_inset listings
+inline false
+status open
+
+\begin_layout Plain Layout
+
+\change_inserted 1986246365 1353594178
+
+struct virtio_net_ctrl_rfs {
+\end_layout
+
+\begin_layout Plain Layout
+
+\change_inserted 1986246365 1353594212
+
+ u16 virtqueue_pairs;
+\end_layout
+
+\begin_layout Plain Layout
+
+\change_inserted 1986246365 1353594172
+
+};
+\end_layout
+
+\begin_layout Plain Layout
+
+\change_inserted 1986246365 1353594172
+
+\end_layout
+
+\begin_layout Plain Layout
+
+\change_inserted 1986246365 1353594263
+
+#define VIRTIO_NET_CTRL_RFS 1
+\end_layout
+
+\begin_layout Plain Layout
+
+\change_inserted 1986246365 1353594273
+
+ #define VIRTIO_NET_CTRL_RFS_VQ_PAIRS_SET 0
+\end_layout
+
+\begin_layout Plain Layout
+
+\change_inserted 1986246365 1353594273
+
+ #define VIRTIO_NET_CTRL_RFS_VQ_PAIRS_MIN 1
+\end_layout
+
+\begin_layout Plain Layout
+
+\change_inserted 1986246365 1353594273
+
+ #define VIRTIO_NET_CTRL_RFS_VQ_PAIRS_MAX 0x8000
+\end_layout
+
+\end_inset
+
+
+\end_layout
+
+\begin_layout Standard
+
+\change_inserted 1986246365 1354531492
+RFS acceleration is disabled by default.
+ Driver enables RFS by executing the VIRTIO_NET_CTRL_RFS_VQ_PAIRS_SET command,
+ specifying the number of the transmit and receive queues that will be used;
+ thus transmitq0..transmitqn and receiveq0..receiveqn where
+\emph on
+n=virtqueue_pairs-1
+\emph default
+ will be used.
+ All these virtqueues must have been pre-configured in advance.
+ The range of legal values for the
+\emph on
+ virtqueue_pairs
+\emph off
+ field is between 1 and
+\emph on
+max_virtqueue_pairs
+\emph off
+.
+\end_layout
+
+\begin_layout Standard
+
+\change_inserted 1986246365 1353595328
+Programming of the receive flow classificator is implicit.
+ Transmitting a packet of a specific flow on transmitqX will cause incoming
+ packets for this flow to be steered to receiveqX.
+ For uni-directional protocols, or where no packets have been transmitted
+ yet, device will steer a packet to a random queue out of the specified
+ receiveq0..receiveqn.
+\change_unchanged
+
+\end_layout
+
+\begin_layout Standard
+
+\change_inserted 1986246365 1354528710
+RFS acceleration is disabled by setting
+\emph on
+virtqueue_pairs = 1
+\emph default
+ (this is the default).
+ After the command is consumed by the device, the device will not steer
+ new packets on virtqueues receveq1..receiveqN (i.e.
+ other than receiveq0) nor read from transmitq1..transmitqN (i.e.
+ other than transmitq0); accordingly, driver should not transmit new packets
+ on virtqueues other than transmitq0.
+\change_unchanged
+
+\end_layout
+
+\begin_layout Standard
+
+\change_deleted 1986246365 1353593873
.
+
+\change_unchanged
\end_layout
^ permalink raw reply related
* Re: [net-next rfc v7 2/3] virtio_net: multiqueue support
From: Michael S. Tsirkin @ 2012-12-03 11:00 UTC (permalink / raw)
To: Jason Wang
Cc: krkumar2, kvm, netdev, linux-kernel, virtualization, bhutchings,
jwhan, shiyer
In-Reply-To: <50BC7F59.301@redhat.com>
On Mon, Dec 03, 2012 at 06:30:49PM +0800, Jason Wang wrote:
> On 12/03/2012 06:14 PM, Michael S. Tsirkin wrote:
> > On Tue, Nov 27, 2012 at 06:15:59PM +0800, Jason Wang wrote:
> >> > - if (!try_fill_recv(&vi->rq, GFP_KERNEL))
> >> > - schedule_delayed_work(&vi->rq.refill, 0);
> >> > + for (i = 0; i < vi->max_queue_pairs; i++)
> >> > + if (!try_fill_recv(&vi->rq[i], GFP_KERNEL))
> >> > + schedule_delayed_work(&vi->rq[i].refill, 0);
> >> >
> >> > mutex_lock(&vi->config_lock);
> >> > vi->config_enable = true;
> >> > mutex_unlock(&vi->config_lock);
> >> >
> >> > + BUG_ON(virtnet_set_queues(vi));
> >> > +
> >> > return 0;
> >> > }
> >> > #endif
> > Also crashing on device nack of command is also not nice.
> > In this case it seems we can just switch to
> > single-queue mode which should always be safe.
>
> Not sure it's safe. It depends on the reason why this call fails. If we
> left a state that the driver only use single queue but the device use
> multi queues, we may still lost the network.
Not the way driver is currently written - you'll happily
process incoming packets from all queues so no problem?
--
MST
^ permalink raw reply
* Re: [net-next rfc v7 2/3] virtio_net: multiqueue support
From: Michael S. Tsirkin @ 2012-12-03 11:11 UTC (permalink / raw)
To: Jason Wang
Cc: Rusty Russell, krkumar2, virtualization, netdev, linux-kernel,
kvm, bhutchings, jwhan, shiyer
In-Reply-To: <50BC7896.4010504@redhat.com>
On Mon, Dec 03, 2012 at 06:01:58PM +0800, Jason Wang wrote:
> On 12/03/2012 05:47 PM, Michael S. Tsirkin wrote:
> > On Mon, Dec 03, 2012 at 02:05:27PM +0800, Jason Wang wrote:
> >> On Monday, December 03, 2012 12:34:08 PM Rusty Russell wrote:
> >>> Jason Wang <jasowang@redhat.com> writes:
> >>>> +static const struct ethtool_ops virtnet_ethtool_ops;
> >>>> +
> >>>> +/*
> >>>> + * Converting between virtqueue no. and kernel tx/rx queue no.
> >>>> + * 0:rx0 1:tx0 2:cvq 3:rx1 4:tx1 ... 2N+1:rxN 2N+2:txN
> >>>> + */
> >>>> +static int vq2txq(struct virtqueue *vq)
> >>>> +{
> >>>> + int index = virtqueue_get_queue_index(vq);
> >>>> + return index == 1 ? 0 : (index - 2) / 2;
> >>>> +}
> >>>> +
> >>>> +static int txq2vq(int txq)
> >>>> +{
> >>>> + return txq ? 2 * txq + 2 : 1;
> >>>> +}
> >>>> +
> >>>> +static int vq2rxq(struct virtqueue *vq)
> >>>> +{
> >>>> + int index = virtqueue_get_queue_index(vq);
> >>>> + return index ? (index - 1) / 2 : 0;
> >>>> +}
> >>>> +
> >>>> +static int rxq2vq(int rxq)
> >>>> +{
> >>>> + return rxq ? 2 * rxq + 1 : 0;
> >>>> +}
> >>>> +
> >>> I thought MST changed the proposed spec to make the control queue always
> >>> the last one, so this logic becomes trivial.
> >> But it may break the support of legacy guest. If we boot a legacy single queue
> >> guest on a 2 queue virtio-net device. It may think vq 2 is cvq which is indeed
> >> rx1.
> > Legacy guyest support should be handled by host using feature
> > bits in the usual way: host should detect legacy guest
> > by checking the VIRTIO_NET_F_RFS feature.
> >
> > If VIRTIO_NET_F_RFS is acked, cvq is vq max_virtqueue_pairs * 2.
> > If it's not acked, cvq is vq 2.
> >
>
> We could, but we didn't gain much from this.
It just seems cleaner and easier to understand.
> Furthermore, we need also
> do the dynamic creation/destroying of virtqueues during feature
> negotiation which seems not supported in qemu now.
It's not *done* in qemu now, but it seems easy: just call
virtio_add_queue for vq2 and on from virtio_net_set_features.
As features can be modified multiple times, we
should add virtio_del_queue and call that beforehand
to get to the known state (two vqs).
--
MST
^ permalink raw reply
* [patch net-next] net: call notifiers for mtu change even if iface is not up
From: Jiri Pirko @ 2012-12-03 11:16 UTC (permalink / raw)
To: netdev; +Cc: davem, edumazet, bhutchings, psimerda
Do the same thing as in set mac. Call notifiers every time.
Signed-off-by: Jiri Pirko <jiri@resnulli.us>
---
net/core/dev.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/net/core/dev.c b/net/core/dev.c
index 2f94df2..0685a72 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -4971,7 +4971,7 @@ int dev_set_mtu(struct net_device *dev, int new_mtu)
else
dev->mtu = new_mtu;
- if (!err && dev->flags & IFF_UP)
+ if (!err)
call_netdevice_notifiers(NETDEV_CHANGEMTU, dev);
return err;
}
--
1.8.0
^ permalink raw reply related
* Re: [net-next rfc v7 1/3] virtio-net: separate fields of sending/receiving queue from virtnet_info
From: Michael S. Tsirkin @ 2012-12-03 11:18 UTC (permalink / raw)
To: Jason Wang
Cc: krkumar2, kvm, netdev, linux-kernel, virtualization, bhutchings,
jwhan, shiyer
In-Reply-To: <3524590.ZWGua7A8ne@jason-thinkpad-t430s>
On Mon, Dec 03, 2012 at 01:15:01PM +0800, Jason Wang wrote:
> > > +
>
> > > + /* Work struct for refilling if we run low on memory. */
>
> > > + struct delayed_work refill;
>
> >
>
> > I can't really see the justificaiton for a refill per queue. Just have
>
> > one work iterate all the queues if it happens, unless it happens often
>
> > (in which case, we need to look harder at this anyway).
>
>
>
> But during this kind of iteration, we may need enable/disable the napi
> regardless of whether the receive queue has lots to be refilled. This may add
> extra latency.
We are running from the timer, so latency is not a concern I think.
--
MST
^ permalink raw reply
* [PATCH V3 0/5] Add LE hash collision bug fix for active and passive offloaded connections
From: Vipul Pandya @ 2012-12-03 11:22 UTC (permalink / raw)
To: linux-rdma-u79uwXL29TY76Z2rM5mHXA, netdev-u79uwXL29TY76Z2rM5mHXA
Cc: roland-BHEL68pLQRGGvPXPguhicg, davem-fT/PcQaiUtIeIZ0/mPfg9Q,
divy-ut6Up61K2wZBDgjK7y7TUQ, dm-ut6Up61K2wZBDgjK7y7TUQ,
kumaras-ut6Up61K2wZBDgjK7y7TUQ,
swise-7bPotxP6k4+P2YhJcF5u+vpXobYPEAuW,
abhishek-ut6Up61K2wZBDgjK7y7TUQ, Vipul Pandya
This patch series fixes the LE hash collision issue in cxgb4 and RDMA/cxgb4
drivers in kernel.org.
If the hash functionality is enabled in T4 then tuple information of active and
passive offloaded connections are stored in DDR3 memory. LE (Lookup Engine)
implements the interface to search this tuple entries using hash algorithm. To
avoid LE hash collision, firmware provides new mechanisms to setup active and
passive open connections.
In case of active open connection, firmware detects LE hash collision situation
and notifies driver. Driver uses fw_ofld_connection work request to offload
that connection. Its tuple information will be stored in TCAM memory array.
In case of passive open connection, server filter region is created in TCAM.
This region stores the filter which will redirect the incoming SYN packet to
offload queues. After this driver tries to establish the connection using
firmware work request.
This patch series also adds framework for managing filters and to use T4's
filter capabilities.
Following testing has been carried out successfully on this patch series.
1. 1000 active open connections created and saw that tcam_full counter is
getting incremented through debugfs file.
2. Multiple passive open connections were created and ran the same test
repetatively to verify server filter is getting created and deleted properly.
The patch-series is based on Roland's infiniband tree (for-next branch),
and involves changes on cxgb4 and RDMA/cxgb4 drivers. Both linux-rdma and netdev
are included in this post for review.
We have some more bug fixes in RDMA/cxgb4 after this patch series. So, we would
like to request this series to get mereged through Roland's infiniband for-next
tree.
V2: Changed commenting style from kernel-doc format('/**') to normal
V3: Resending the whole patch series again with the missing patches in V2
Thanks,
Vipul Pandya
Vipul Pandya (5):
cxgb4: Add T4 filter support
cxgb4: Add LE hash collision bug fix path in LLD driver
RDMA/cxgb4: Fix LE hash collision bug for active open connection
RDMA/cxgb4: Fix LE hash collision bug for passive open connection
RDMA/cxgb4: Fix bug for active and passive LE hash collision path
drivers/infiniband/hw/cxgb4/cm.c | 789 +++++++++++++++++++---
drivers/infiniband/hw/cxgb4/device.c | 210 ++++++-
drivers/infiniband/hw/cxgb4/iw_cxgb4.h | 33 +
drivers/net/ethernet/chelsio/cxgb4/cxgb4.h | 146 +++++
drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c | 473 +++++++++++++-
drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.h | 23 +-
drivers/net/ethernet/chelsio/cxgb4/l2t.c | 34 +
drivers/net/ethernet/chelsio/cxgb4/l2t.h | 3 +
drivers/net/ethernet/chelsio/cxgb4/t4_hw.c | 23 +-
drivers/net/ethernet/chelsio/cxgb4/t4_msg.h | 66 ++
drivers/net/ethernet/chelsio/cxgb4/t4_regs.h | 37 ++
drivers/net/ethernet/chelsio/cxgb4/t4fw_api.h | 388 +++++++++++
12 files changed, 2100 insertions(+), 125 deletions(-)
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply
* [PATCH V3 1/5] cxgb4: Add T4 filter support
From: Vipul Pandya @ 2012-12-03 11:22 UTC (permalink / raw)
To: linux-rdma-u79uwXL29TY76Z2rM5mHXA, netdev-u79uwXL29TY76Z2rM5mHXA
Cc: roland-BHEL68pLQRGGvPXPguhicg, davem-fT/PcQaiUtIeIZ0/mPfg9Q,
divy-ut6Up61K2wZBDgjK7y7TUQ, dm-ut6Up61K2wZBDgjK7y7TUQ,
kumaras-ut6Up61K2wZBDgjK7y7TUQ,
swise-7bPotxP6k4+P2YhJcF5u+vpXobYPEAuW,
abhishek-ut6Up61K2wZBDgjK7y7TUQ, Vipul Pandya
In-Reply-To: <1354533781-31575-1-git-send-email-vipul-ut6Up61K2wZBDgjK7y7TUQ@public.gmane.org>
The T4 architecture is capable of filtering ingress packets at line rate
using the rule in TCAM. If packet hits a rule in the TCAM then it can be either
dropped or passed to the receive queues based on a rule settings.
This patch adds framework for managing filters and to use T4's filter
capabilities. It constructs a Firmware Filter Work Request which writes the
filter at a specified index to get the work done. It hosts shadow copy of
ingress filter entry to check field size limitations and save memory in the
case where the filter table is large.
Signed-off-by: Vipul Pandya <vipul-ut6Up61K2wZBDgjK7y7TUQ@public.gmane.org>
---
V2: Changed commenting style from kernel-doc format('/**') to normal
V3: Resending the whole patch series again with the missing patches in V2
drivers/net/ethernet/chelsio/cxgb4/cxgb4.h | 134 ++++++++++
drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c | 301 ++++++++++++++++++++++-
drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.h | 2 +
drivers/net/ethernet/chelsio/cxgb4/l2t.c | 33 +++
drivers/net/ethernet/chelsio/cxgb4/l2t.h | 3 +
drivers/net/ethernet/chelsio/cxgb4/t4_hw.c | 23 ++-
drivers/net/ethernet/chelsio/cxgb4/t4_msg.h | 1 +
drivers/net/ethernet/chelsio/cxgb4/t4fw_api.h | 279 +++++++++++++++++++++
8 files changed, 770 insertions(+), 6 deletions(-)
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h b/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h
index 378988b..b6403d1 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h
@@ -545,6 +545,132 @@ struct adapter {
spinlock_t stats_lock;
};
+/*
+ * Defined bit width of user definable filter tuples
+ */
+#define ETHTYPE_BITWIDTH 16
+#define FRAG_BITWIDTH 1
+#define MACIDX_BITWIDTH 9
+#define FCOE_BITWIDTH 1
+#define IPORT_BITWIDTH 3
+#define MATCHTYPE_BITWIDTH 3
+#define PROTO_BITWIDTH 8
+#define TOS_BITWIDTH 8
+#define PF_BITWIDTH 8
+#define VF_BITWIDTH 8
+#define IVLAN_BITWIDTH 16
+#define OVLAN_BITWIDTH 16
+
+/* Filter matching rules. These consist of a set of ingress packet field
+ * (value, mask) tuples. The associated ingress packet field matches the
+ * tuple when ((field & mask) == value). (Thus a wildcard "don't care" field
+ * rule can be constructed by specifying a tuple of (0, 0).) A filter rule
+ * matches an ingress packet when all of the individual individual field
+ * matching rules are true.
+ *
+ * Partial field masks are always valid, however, while it may be easy to
+ * understand their meanings for some fields (e.g. IP address to match a
+ * subnet), for others making sensible partial masks is less intuitive (e.g.
+ * MPS match type) ...
+ *
+ * Most of the following data structures are modeled on T4 capabilities.
+ * Drivers for earlier chips use the subsets which make sense for those chips.
+ * We really need to come up with a hardware-independent mechanism to
+ * represent hardware filter capabilities ...
+ */
+struct ch_filter_tuple {
+ /*
+ * Compressed header matching field rules. The TP_VLAN_PRI_MAP
+ * register selects which of these fields will participate in the
+ * filter match rules -- up to a maximum of 36 bits. Because
+ * TP_VLAN_PRI_MAP is a global register, all filters must use the same
+ * set of fields.
+ */
+ uint32_t ethtype:ETHTYPE_BITWIDTH; /* Ethernet type */
+ uint32_t frag:FRAG_BITWIDTH; /* IP fragmentation header */
+ uint32_t ivlan_vld:1; /* inner VLAN valid */
+ uint32_t ovlan_vld:1; /* outer VLAN valid */
+ uint32_t pfvf_vld:1; /* PF/VF valid */
+ uint32_t macidx:MACIDX_BITWIDTH; /* exact match MAC index */
+ uint32_t fcoe:FCOE_BITWIDTH; /* FCoE packet */
+ uint32_t iport:IPORT_BITWIDTH; /* ingress port */
+ uint32_t matchtype:MATCHTYPE_BITWIDTH; /* MPS match type */
+ uint32_t proto:PROTO_BITWIDTH; /* protocol type */
+ uint32_t tos:TOS_BITWIDTH; /* TOS/Traffic Type */
+ uint32_t pf:PF_BITWIDTH; /* PCI-E PF ID */
+ uint32_t vf:VF_BITWIDTH; /* PCI-E VF ID */
+ uint32_t ivlan:IVLAN_BITWIDTH; /* inner VLAN */
+ uint32_t ovlan:OVLAN_BITWIDTH; /* outer VLAN */
+
+ /* Uncompressed header matching field rules. These are always
+ * available for field rules.
+ */
+ uint8_t lip[16]; /* local IP address (IPv4 in [3:0]) */
+ uint8_t fip[16]; /* foreign IP address (IPv4 in [3:0]) */
+ uint16_t lport; /* local port */
+ uint16_t fport; /* foreign port */
+};
+
+/* A filter ioctl command.
+ */
+struct ch_filter_specification {
+ /*
+ * Administrative fields for filter.
+ */
+ uint32_t hitcnts:1; /* count filter hits in TCB */
+ uint32_t prio:1; /* filter has priority over active/server */
+
+ /* Fundamental filter typing. This is the one element of filter
+ * matching that doesn't exist as a (value, mask) tuple.
+ */
+ uint32_t type:1; /* 0 => IPv4, 1 => IPv6 */
+
+ /* Packet dispatch information. Ingress packets which match the
+ * filter rules will be dropped, passed to the host or switched back
+ * out as egress packets.
+ */
+ uint32_t action:2; /* drop, pass, switch */
+
+ uint32_t rpttid:1; /* report TID in RSS hash field */
+
+ uint32_t dirsteer:1; /* 0 => RSS, 1 => steer to iq */
+ uint32_t iq:10; /* ingress queue */
+
+ uint32_t maskhash:1; /* dirsteer=0: store RSS hash in TCB */
+ uint32_t dirsteerhash:1;/* dirsteer=1: 0 => TCB contains RSS hash */
+ /* 1 => TCB contains IQ ID */
+
+ /* Switch proxy/rewrite fields. An ingress packet which matches a
+ * filter with "switch" set will be looped back out as an egress
+ * packet -- potentially with some Ethernet header rewriting.
+ */
+ uint32_t eport:2; /* egress port to switch packet out */
+ uint32_t newdmac:1; /* rewrite destination MAC address */
+ uint32_t newsmac:1; /* rewrite source MAC address */
+ uint32_t newvlan:2; /* rewrite VLAN Tag */
+ uint8_t dmac[ETH_ALEN]; /* new destination MAC address */
+ uint8_t smac[ETH_ALEN]; /* new source MAC address */
+ uint16_t vlan; /* VLAN Tag to insert */
+
+ /* Filter rule value/mask pairs.
+ */
+ struct ch_filter_tuple val;
+ struct ch_filter_tuple mask;
+};
+
+enum {
+ FILTER_PASS = 0, /* default */
+ FILTER_DROP,
+ FILTER_SWITCH
+};
+
+enum {
+ VLAN_NOCHANGE = 0, /* default */
+ VLAN_REMOVE,
+ VLAN_INSERT,
+ VLAN_REWRITE
+};
+
static inline u32 t4_read_reg(struct adapter *adap, u32 reg_addr)
{
return readl(adap->regs + reg_addr);
@@ -701,6 +827,12 @@ static inline int t4_wr_mbox_ns(struct adapter *adap, int mbox, const void *cmd,
void t4_write_indirect(struct adapter *adap, unsigned int addr_reg,
unsigned int data_reg, const u32 *vals,
unsigned int nregs, unsigned int start_idx);
+void t4_read_indirect(struct adapter *adap, unsigned int addr_reg,
+ unsigned int data_reg, u32 *vals, unsigned int nregs,
+ unsigned int start_idx);
+
+struct fw_filter_wr;
+
void t4_intr_enable(struct adapter *adapter);
void t4_intr_disable(struct adapter *adapter);
int t4_slow_intr_handler(struct adapter *adapter);
@@ -737,6 +869,8 @@ void t4_tp_get_tcp_stats(struct adapter *adap, struct tp_tcp_stats *v4,
void t4_load_mtus(struct adapter *adap, const unsigned short *mtus,
const unsigned short *alpha, const unsigned short *beta);
+void t4_mk_filtdelwr(unsigned int ftid, struct fw_filter_wr *wr, int qid);
+
void t4_wol_magic_enable(struct adapter *adap, unsigned int port,
const u8 *addr);
int t4_wol_pat_enable(struct adapter *adap, unsigned int port, unsigned int map,
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
index 0df1284..a678287 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
@@ -175,6 +175,32 @@ enum {
MIN_FL_ENTRIES = 16
};
+/*
+ * Host shadow copy of ingress filter entry. This is in host native format
+ * and doesn't match the ordering or bit order, etc. of the hardware of the
+ * firmware command. The use of bit-field structure elements is purely to
+ * remind ourselves of the field size limitations and save memory in the case
+ * where the filter table is large.
+ */
+struct filter_entry {
+ /*
+ * Administrative fields for filter.
+ */
+ u32 valid:1; /* filter allocated and valid */
+ u32 locked:1; /* filter is administratively locked */
+
+ u32 pending:1; /* filter action is pending firmware reply */
+ u32 smtidx:8; /* Source MAC Table index for smac */
+ struct l2t_entry *l2t; /* Layer Two Table entry for dmac */
+
+ /* The filter itself. Most of this is a straight copy of information
+ * provided by the extended ioctl(). Some fields are translated to
+ * internal forms -- for instance the Ingress Queue ID passed in from
+ * the ioctl() is translated into the Absolute Ingress Queue ID.
+ */
+ struct ch_filter_specification fs;
+};
+
#define DFLT_MSG_ENABLE (NETIF_MSG_DRV | NETIF_MSG_PROBE | NETIF_MSG_LINK | \
NETIF_MSG_TIMER | NETIF_MSG_IFDOWN | NETIF_MSG_IFUP |\
NETIF_MSG_RX_ERR | NETIF_MSG_TX_ERR)
@@ -325,6 +351,9 @@ enum {
static unsigned int tp_vlan_pri_map = TP_VLAN_PRI_MAP_DEFAULT;
+module_param(tp_vlan_pri_map, uint, 0644);
+MODULE_PARM_DESC(tp_vlan_pri_map, "global compressed filter configuration");
+
static struct dentry *cxgb4_debugfs_root;
static LIST_HEAD(adapter_list);
@@ -507,7 +536,70 @@ static int link_start(struct net_device *dev)
}
/*
- * Response queue handler for the FW event queue.
+ * Clear a filter and release any of its resources that we own. This also
+ * clears the filter's "pending" status.
+ */
+static void clear_filter(struct adapter *adap, struct filter_entry *f)
+{
+ /*
+ * If the new or old filter have loopback rewriteing rules then we'll
+ * need to free any existing Layer Two Table (L2T) entries of the old
+ * filter rule. The firmware will handle freeing up any Source MAC
+ * Table (SMT) entries used for rewriting Source MAC Addresses in
+ * loopback rules.
+ */
+ if (f->l2t)
+ cxgb4_l2t_release(f->l2t);
+
+ /* The zeroing of the filter rule below clears the filter valid,
+ * pending, locked flags, l2t pointer, etc. so it's all we need for
+ * this operation.
+ */
+ memset(f, 0, sizeof(*f));
+}
+
+/* Handle a filter write/deletion reply.
+ */
+static void filter_rpl(struct adapter *adap, const struct cpl_set_tcb_rpl *rpl)
+{
+ unsigned int idx = GET_TID(rpl);
+ unsigned int nidx = idx - adap->tids.ftid_base;
+ unsigned int ret;
+ struct filter_entry *f;
+
+ if (idx >= adap->tids.ftid_base && nidx <
+ (adap->tids.nftids + adap->tids.nsftids)) {
+ idx = nidx;
+ ret = GET_TCB_COOKIE(rpl->cookie);
+ f = &adap->tids.ftid_tab[idx];
+
+ if (ret == FW_FILTER_WR_FLT_DELETED) {
+ /*
+ * Clear the filter when we get confirmation from the
+ * hardware that the filter has been deleted.
+ */
+ clear_filter(adap, f);
+ } else if (ret == FW_FILTER_WR_SMT_TBL_FULL) {
+ dev_err(adap->pdev_dev, "filter %u setup failed due to full SMT\n",
+ idx);
+ clear_filter(adap, f);
+ } else if (ret == FW_FILTER_WR_FLT_ADDED) {
+ f->smtidx = (be64_to_cpu(rpl->oldval) >> 24) & 0xff;
+ f->pending = 0; /* asynchronous setup completed */
+ f->valid = 1;
+ } else {
+ /*
+ * Something went wrong. Issue a warning about the
+ * problem and clear everything out.
+ */
+ dev_err(adap->pdev_dev, "filter %u setup failed with error %u\n",
+ idx, ret);
+ clear_filter(adap, f);
+ }
+ }
+}
+
+/* Response queue handler for the FW event queue.
*/
static int fwevtq_handler(struct sge_rspq *q, const __be64 *rsp,
const struct pkt_gl *gl)
@@ -542,6 +634,10 @@ static int fwevtq_handler(struct sge_rspq *q, const __be64 *rsp,
const struct cpl_l2t_write_rpl *p = (void *)rsp;
do_l2t_write_rpl(q->adap, p);
+ } else if (opcode == CPL_SET_TCB_RPL) {
+ const struct cpl_set_tcb_rpl *p = (void *)rsp;
+
+ filter_rpl(q->adap, p);
} else
dev_err(q->adap->pdev_dev,
"unexpected CPL %#x on FW event queue\n", opcode);
@@ -983,6 +1079,149 @@ static void t4_free_mem(void *addr)
kfree(addr);
}
+/*
+ * Send a Work Request to write the filter at a specified index. We construct
+ * a Firmware Filter Work Request to have the work done and put the indicated
+ * filter into "pending" mode which will prevent any further actions against
+ * it till we get a reply from the firmware on the completion status of the
+ * request.
+ */
+static int set_filter_wr(struct adapter *adapter, int fidx)
+{
+ struct filter_entry *f = &adapter->tids.ftid_tab[fidx];
+ struct sk_buff *skb;
+ struct fw_filter_wr *fwr;
+ unsigned int ftid;
+
+ /* If the new filter requires loopback Destination MAC and/or VLAN
+ * rewriting then we need to allocate a Layer 2 Table (L2T) entry for
+ * the filter.
+ */
+ if (f->fs.newdmac || f->fs.newvlan) {
+ /* allocate L2T entry for new filter */
+ f->l2t = t4_l2t_alloc_switching(adapter->l2t);
+ if (f->l2t == NULL)
+ return -EAGAIN;
+ if (t4_l2t_set_switching(adapter, f->l2t, f->fs.vlan,
+ f->fs.eport, f->fs.dmac)) {
+ cxgb4_l2t_release(f->l2t);
+ f->l2t = NULL;
+ return -ENOMEM;
+ }
+ }
+
+ ftid = adapter->tids.ftid_base + fidx;
+
+ skb = alloc_skb(sizeof(*fwr), GFP_KERNEL | __GFP_NOFAIL);
+ fwr = (struct fw_filter_wr *)__skb_put(skb, sizeof(*fwr));
+ memset(fwr, 0, sizeof(*fwr));
+
+ /* It would be nice to put most of the following in t4_hw.c but most
+ * of the work is translating the cxgbtool ch_filter_specification
+ * into the Work Request and the definition of that structure is
+ * currently in cxgbtool.h which isn't appropriate to pull into the
+ * common code. We may eventually try to come up with a more neutral
+ * filter specification structure but for now it's easiest to simply
+ * put this fairly direct code in line ...
+ */
+ fwr->op_pkd = htonl(FW_WR_OP(FW_FILTER_WR));
+ fwr->len16_pkd = htonl(FW_WR_LEN16(sizeof(*fwr)/16));
+ fwr->tid_to_iq =
+ htonl(V_FW_FILTER_WR_TID(ftid) |
+ V_FW_FILTER_WR_RQTYPE(f->fs.type) |
+ V_FW_FILTER_WR_NOREPLY(0) |
+ V_FW_FILTER_WR_IQ(f->fs.iq));
+ fwr->del_filter_to_l2tix =
+ htonl(V_FW_FILTER_WR_RPTTID(f->fs.rpttid) |
+ V_FW_FILTER_WR_DROP(f->fs.action == FILTER_DROP) |
+ V_FW_FILTER_WR_DIRSTEER(f->fs.dirsteer) |
+ V_FW_FILTER_WR_MASKHASH(f->fs.maskhash) |
+ V_FW_FILTER_WR_DIRSTEERHASH(f->fs.dirsteerhash) |
+ V_FW_FILTER_WR_LPBK(f->fs.action == FILTER_SWITCH) |
+ V_FW_FILTER_WR_DMAC(f->fs.newdmac) |
+ V_FW_FILTER_WR_SMAC(f->fs.newsmac) |
+ V_FW_FILTER_WR_INSVLAN(f->fs.newvlan == VLAN_INSERT ||
+ f->fs.newvlan == VLAN_REWRITE) |
+ V_FW_FILTER_WR_RMVLAN(f->fs.newvlan == VLAN_REMOVE ||
+ f->fs.newvlan == VLAN_REWRITE) |
+ V_FW_FILTER_WR_HITCNTS(f->fs.hitcnts) |
+ V_FW_FILTER_WR_TXCHAN(f->fs.eport) |
+ V_FW_FILTER_WR_PRIO(f->fs.prio) |
+ V_FW_FILTER_WR_L2TIX(f->l2t ? f->l2t->idx : 0));
+ fwr->ethtype = htons(f->fs.val.ethtype);
+ fwr->ethtypem = htons(f->fs.mask.ethtype);
+ fwr->frag_to_ovlan_vldm =
+ (V_FW_FILTER_WR_FRAG(f->fs.val.frag) |
+ V_FW_FILTER_WR_FRAGM(f->fs.mask.frag) |
+ V_FW_FILTER_WR_IVLAN_VLD(f->fs.val.ivlan_vld) |
+ V_FW_FILTER_WR_OVLAN_VLD(f->fs.val.ovlan_vld) |
+ V_FW_FILTER_WR_IVLAN_VLDM(f->fs.mask.ivlan_vld) |
+ V_FW_FILTER_WR_OVLAN_VLDM(f->fs.mask.ovlan_vld));
+ fwr->smac_sel = 0;
+ fwr->rx_chan_rx_rpl_iq =
+ htons(V_FW_FILTER_WR_RX_CHAN(0) |
+ V_FW_FILTER_WR_RX_RPL_IQ(adapter->sge.fw_evtq.abs_id));
+ fwr->maci_to_matchtypem =
+ htonl(V_FW_FILTER_WR_MACI(f->fs.val.macidx) |
+ V_FW_FILTER_WR_MACIM(f->fs.mask.macidx) |
+ V_FW_FILTER_WR_FCOE(f->fs.val.fcoe) |
+ V_FW_FILTER_WR_FCOEM(f->fs.mask.fcoe) |
+ V_FW_FILTER_WR_PORT(f->fs.val.iport) |
+ V_FW_FILTER_WR_PORTM(f->fs.mask.iport) |
+ V_FW_FILTER_WR_MATCHTYPE(f->fs.val.matchtype) |
+ V_FW_FILTER_WR_MATCHTYPEM(f->fs.mask.matchtype));
+ fwr->ptcl = f->fs.val.proto;
+ fwr->ptclm = f->fs.mask.proto;
+ fwr->ttyp = f->fs.val.tos;
+ fwr->ttypm = f->fs.mask.tos;
+ fwr->ivlan = htons(f->fs.val.ivlan);
+ fwr->ivlanm = htons(f->fs.mask.ivlan);
+ fwr->ovlan = htons(f->fs.val.ovlan);
+ fwr->ovlanm = htons(f->fs.mask.ovlan);
+ memcpy(fwr->lip, f->fs.val.lip, sizeof(fwr->lip));
+ memcpy(fwr->lipm, f->fs.mask.lip, sizeof(fwr->lipm));
+ memcpy(fwr->fip, f->fs.val.fip, sizeof(fwr->fip));
+ memcpy(fwr->fipm, f->fs.mask.fip, sizeof(fwr->fipm));
+ fwr->lp = htons(f->fs.val.lport);
+ fwr->lpm = htons(f->fs.mask.lport);
+ fwr->fp = htons(f->fs.val.fport);
+ fwr->fpm = htons(f->fs.mask.fport);
+ if (f->fs.newsmac)
+ memcpy(fwr->sma, f->fs.smac, sizeof(fwr->sma));
+
+ /* Mark the filter as "pending" and ship off the Filter Work Request.
+ * When we get the Work Request Reply we'll clear the pending status.
+ */
+ f->pending = 1;
+ set_wr_txq(skb, CPL_PRIORITY_CONTROL, f->fs.val.iport & 0x3);
+ t4_ofld_send(adapter, skb);
+ return 0;
+}
+
+/* Delete the filter at a specified index.
+ */
+static int del_filter_wr(struct adapter *adapter, int fidx)
+{
+ struct filter_entry *f = &adapter->tids.ftid_tab[fidx];
+ struct sk_buff *skb;
+ struct fw_filter_wr *fwr;
+ unsigned int len, ftid;
+
+ len = sizeof(*fwr);
+ ftid = adapter->tids.ftid_base + fidx;
+
+ skb = alloc_skb(len, GFP_KERNEL | __GFP_NOFAIL);
+ fwr = (struct fw_filter_wr *)__skb_put(skb, len);
+ t4_mk_filtdelwr(ftid, fwr, adapter->sge.fw_evtq.abs_id);
+
+ /* Mark the filter as "pending" and ship off the Filter Work Request.
+ * When we get the Work Request Reply we'll clear the pending status.
+ */
+ f->pending = 1;
+ t4_mgmt_tx(adapter, skb);
+ return 0;
+}
+
static inline int is_offload(const struct adapter *adap)
{
return adap->params.offload;
@@ -2195,7 +2434,7 @@ int cxgb4_alloc_atid(struct tid_info *t, void *data)
if (t->afree) {
union aopen_entry *p = t->afree;
- atid = p - t->atid_tab;
+ atid = (p - t->atid_tab) + t->atid_base;
t->afree = p->next;
p->data = data;
t->atids_in_use++;
@@ -2210,7 +2449,7 @@ EXPORT_SYMBOL(cxgb4_alloc_atid);
*/
void cxgb4_free_atid(struct tid_info *t, unsigned int atid)
{
- union aopen_entry *p = &t->atid_tab[atid];
+ union aopen_entry *p = &t->atid_tab[atid - t->atid_base];
spin_lock_bh(&t->atid_lock);
p->next = t->afree;
@@ -2362,11 +2601,16 @@ EXPORT_SYMBOL(cxgb4_remove_tid);
static int tid_init(struct tid_info *t)
{
size_t size;
+ unsigned int stid_bmap_size;
unsigned int natids = t->natids;
- size = t->ntids * sizeof(*t->tid_tab) + natids * sizeof(*t->atid_tab) +
+ stid_bmap_size = BITS_TO_LONGS(t->nstids);
+ size = t->ntids * sizeof(*t->tid_tab) +
+ natids * sizeof(*t->atid_tab) +
t->nstids * sizeof(*t->stid_tab) +
- BITS_TO_LONGS(t->nstids) * sizeof(long);
+ stid_bmap_size * sizeof(long) +
+ t->nftids * sizeof(*t->ftid_tab);
+
t->tid_tab = t4_alloc_mem(size);
if (!t->tid_tab)
return -ENOMEM;
@@ -2374,6 +2618,7 @@ static int tid_init(struct tid_info *t)
t->atid_tab = (union aopen_entry *)&t->tid_tab[t->ntids];
t->stid_tab = (struct serv_entry *)&t->atid_tab[natids];
t->stid_bmap = (unsigned long *)&t->stid_tab[t->nstids];
+ t->ftid_tab = (struct filter_entry *)&t->stid_bmap[stid_bmap_size];
spin_lock_init(&t->stid_lock);
spin_lock_init(&t->atid_lock);
@@ -2999,6 +3244,41 @@ static int cxgb_close(struct net_device *dev)
return t4_enable_vi(adapter, adapter->fn, pi->viid, false, false);
}
+/*
+ * Return an error number if the indicated filter isn't writable ...
+ */
+static int writable_filter(struct filter_entry *f)
+{
+ if (f->locked)
+ return -EPERM;
+ if (f->pending)
+ return -EBUSY;
+
+ return 0;
+}
+
+/* Delete the filter at the specified index (if valid). The checks for all
+ * the common problems with doing this like the filter being locked, currently
+ * pending in another operation, etc.
+ */
+static int delete_filter(struct adapter *adapter, unsigned int fidx)
+{
+ struct filter_entry *f;
+ int ret;
+
+ if (fidx >= adapter->tids.nftids)
+ return -EINVAL;
+
+ f = &adapter->tids.ftid_tab[fidx];
+ ret = writable_filter(f);
+ if (ret)
+ return ret;
+ if (f->valid)
+ return del_filter_wr(adapter, fidx);
+
+ return 0;
+}
+
static struct rtnl_link_stats64 *cxgb_get_stats(struct net_device *dev,
struct rtnl_link_stats64 *ns)
{
@@ -4662,6 +4942,17 @@ static void __devexit remove_one(struct pci_dev *pdev)
if (adapter->debugfs_root)
debugfs_remove_recursive(adapter->debugfs_root);
+ /*
+ * If we allocated filters, free up state associated with any
+ * valid filters ...
+ */
+ if (adapter->tids.ftid_tab) {
+ struct filter_entry *f = &adapter->tids.ftid_tab[0];
+ for (i = 0; i < adapter->tids.nftids; i++, f++)
+ if (f->valid)
+ clear_filter(adapter, f);
+ }
+
if (adapter->flags & FULL_INIT_DONE)
cxgb_down(adapter);
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.h b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.h
index 39bec73..59a6133 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.h
@@ -97,7 +97,9 @@ struct tid_info {
union aopen_entry *atid_tab;
unsigned int natids;
+ unsigned int atid_base;
+ struct filter_entry *ftid_tab;
unsigned int nftids;
unsigned int ftid_base;
unsigned int aftid_base;
diff --git a/drivers/net/ethernet/chelsio/cxgb4/l2t.c b/drivers/net/ethernet/chelsio/cxgb4/l2t.c
index 6ac77a6..18ca67f 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/l2t.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/l2t.c
@@ -484,6 +484,39 @@ void t4_l2t_update(struct adapter *adap, struct neighbour *neigh)
handle_failed_resolution(adap, arpq);
}
+/*
+ * Allocate an L2T entry for use by a switching rule. Such need to be
+ * explicitly freed and while busy they are not on any hash chain, so normal
+ * address resolution updates do not see them.
+ */
+struct l2t_entry *t4_l2t_alloc_switching(struct l2t_data *d)
+{
+ struct l2t_entry *e;
+
+ write_lock_bh(&d->lock);
+ e = alloc_l2e(d);
+ if (e) {
+ spin_lock(&e->lock); /* avoid race with t4_l2t_free */
+ e->state = L2T_STATE_SWITCHING;
+ atomic_set(&e->refcnt, 1);
+ spin_unlock(&e->lock);
+ }
+ write_unlock_bh(&d->lock);
+ return e;
+}
+
+/* Sets/updates the contents of a switching L2T entry that has been allocated
+ * with an earlier call to @t4_l2t_alloc_switching.
+ */
+int t4_l2t_set_switching(struct adapter *adap, struct l2t_entry *e, u16 vlan,
+ u8 port, u8 *eth_addr)
+{
+ e->vlan = vlan;
+ e->lport = port;
+ memcpy(e->dmac, eth_addr, ETH_ALEN);
+ return write_l2e(adap, e, 0);
+}
+
struct l2t_data *t4_init_l2t(void)
{
int i;
diff --git a/drivers/net/ethernet/chelsio/cxgb4/l2t.h b/drivers/net/ethernet/chelsio/cxgb4/l2t.h
index 02b31d0..108c0f1 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/l2t.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/l2t.h
@@ -100,6 +100,9 @@ struct l2t_entry *cxgb4_l2t_get(struct l2t_data *d, struct neighbour *neigh,
unsigned int priority);
void t4_l2t_update(struct adapter *adap, struct neighbour *neigh);
+struct l2t_entry *t4_l2t_alloc_switching(struct l2t_data *d);
+int t4_l2t_set_switching(struct adapter *adap, struct l2t_entry *e, u16 vlan,
+ u8 port, u8 *eth_addr);
struct l2t_data *t4_init_l2t(void);
void do_l2t_write_rpl(struct adapter *p, const struct cpl_l2t_write_rpl *rpl);
diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c
index 730ae2c..7638181 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c
@@ -109,7 +109,7 @@ void t4_set_reg_field(struct adapter *adapter, unsigned int addr, u32 mask,
* Reads registers that are accessed indirectly through an address/data
* register pair.
*/
-static void t4_read_indirect(struct adapter *adap, unsigned int addr_reg,
+void t4_read_indirect(struct adapter *adap, unsigned int addr_reg,
unsigned int data_reg, u32 *vals,
unsigned int nregs, unsigned int start_idx)
{
@@ -2268,6 +2268,27 @@ int t4_wol_pat_enable(struct adapter *adap, unsigned int port, unsigned int map,
return 0;
}
+/*
+ * t4_mk_filtdelwr - create a delete filter WR
+ * @ftid: the filter ID
+ * @wr: the filter work request to populate
+ * @qid: ingress queue to receive the delete notification
+ *
+ * Creates a filter work request to delete the supplied filter. If @qid is
+ * negative the delete notification is suppressed.
+ */
+void t4_mk_filtdelwr(unsigned int ftid, struct fw_filter_wr *wr, int qid)
+{
+ memset(wr, 0, sizeof(*wr));
+ wr->op_pkd = htonl(FW_WR_OP(FW_FILTER_WR));
+ wr->len16_pkd = htonl(FW_WR_LEN16(sizeof(*wr) / 16));
+ wr->tid_to_iq = htonl(V_FW_FILTER_WR_TID(ftid) |
+ V_FW_FILTER_WR_NOREPLY(qid < 0));
+ wr->del_filter_to_l2tix = htonl(F_FW_FILTER_WR_DEL_FILTER);
+ if (qid >= 0)
+ wr->rx_chan_rx_rpl_iq = htons(V_FW_FILTER_WR_RX_RPL_IQ(qid));
+}
+
#define INIT_CMD(var, cmd, rd_wr) do { \
(var).op_to_write = htonl(FW_CMD_OP(FW_##cmd##_CMD) | \
FW_CMD_REQUEST | FW_CMD_##rd_wr); \
diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_msg.h b/drivers/net/ethernet/chelsio/cxgb4/t4_msg.h
index eb71b82..480eb43 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/t4_msg.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/t4_msg.h
@@ -332,6 +332,7 @@ struct cpl_set_tcb_field {
__be16 word_cookie;
#define TCB_WORD(x) ((x) << 0)
#define TCB_COOKIE(x) ((x) << 5)
+#define GET_TCB_COOKIE(x) (((x) >> 5) & 7)
__be64 mask;
__be64 val;
};
diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4fw_api.h b/drivers/net/ethernet/chelsio/cxgb4/t4fw_api.h
index a636463..b4dc560 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/t4fw_api.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/t4fw_api.h
@@ -35,6 +35,10 @@
#ifndef _T4FW_INTERFACE_H_
#define _T4FW_INTERFACE_H_
+enum fw_ret_val {
+ FW_ENOEXEC = 8, /* Exec format error; inv microcode */
+};
+
#define FW_T4VF_SGE_BASE_ADDR 0x0000
#define FW_T4VF_MPS_BASE_ADDR 0x0100
#define FW_T4VF_PL_BASE_ADDR 0x0200
@@ -81,6 +85,281 @@ struct fw_wr_hdr {
#define HW_TPL_FR_MT_PR_IV_P_FC 0X32B
+/* filter wr reply code in cookie in CPL_SET_TCB_RPL */
+enum fw_filter_wr_cookie {
+ FW_FILTER_WR_SUCCESS,
+ FW_FILTER_WR_FLT_ADDED,
+ FW_FILTER_WR_FLT_DELETED,
+ FW_FILTER_WR_SMT_TBL_FULL,
+ FW_FILTER_WR_EINVAL,
+};
+
+struct fw_filter_wr {
+ __be32 op_pkd;
+ __be32 len16_pkd;
+ __be64 r3;
+ __be32 tid_to_iq;
+ __be32 del_filter_to_l2tix;
+ __be16 ethtype;
+ __be16 ethtypem;
+ __u8 frag_to_ovlan_vldm;
+ __u8 smac_sel;
+ __be16 rx_chan_rx_rpl_iq;
+ __be32 maci_to_matchtypem;
+ __u8 ptcl;
+ __u8 ptclm;
+ __u8 ttyp;
+ __u8 ttypm;
+ __be16 ivlan;
+ __be16 ivlanm;
+ __be16 ovlan;
+ __be16 ovlanm;
+ __u8 lip[16];
+ __u8 lipm[16];
+ __u8 fip[16];
+ __u8 fipm[16];
+ __be16 lp;
+ __be16 lpm;
+ __be16 fp;
+ __be16 fpm;
+ __be16 r7;
+ __u8 sma[6];
+};
+
+#define S_FW_FILTER_WR_TID 12
+#define M_FW_FILTER_WR_TID 0xfffff
+#define V_FW_FILTER_WR_TID(x) ((x) << S_FW_FILTER_WR_TID)
+#define G_FW_FILTER_WR_TID(x) \
+ (((x) >> S_FW_FILTER_WR_TID) & M_FW_FILTER_WR_TID)
+
+#define S_FW_FILTER_WR_RQTYPE 11
+#define M_FW_FILTER_WR_RQTYPE 0x1
+#define V_FW_FILTER_WR_RQTYPE(x) ((x) << S_FW_FILTER_WR_RQTYPE)
+#define G_FW_FILTER_WR_RQTYPE(x) \
+ (((x) >> S_FW_FILTER_WR_RQTYPE) & M_FW_FILTER_WR_RQTYPE)
+#define F_FW_FILTER_WR_RQTYPE V_FW_FILTER_WR_RQTYPE(1U)
+
+#define S_FW_FILTER_WR_NOREPLY 10
+#define M_FW_FILTER_WR_NOREPLY 0x1
+#define V_FW_FILTER_WR_NOREPLY(x) ((x) << S_FW_FILTER_WR_NOREPLY)
+#define G_FW_FILTER_WR_NOREPLY(x) \
+ (((x) >> S_FW_FILTER_WR_NOREPLY) & M_FW_FILTER_WR_NOREPLY)
+#define F_FW_FILTER_WR_NOREPLY V_FW_FILTER_WR_NOREPLY(1U)
+
+#define S_FW_FILTER_WR_IQ 0
+#define M_FW_FILTER_WR_IQ 0x3ff
+#define V_FW_FILTER_WR_IQ(x) ((x) << S_FW_FILTER_WR_IQ)
+#define G_FW_FILTER_WR_IQ(x) \
+ (((x) >> S_FW_FILTER_WR_IQ) & M_FW_FILTER_WR_IQ)
+
+#define S_FW_FILTER_WR_DEL_FILTER 31
+#define M_FW_FILTER_WR_DEL_FILTER 0x1
+#define V_FW_FILTER_WR_DEL_FILTER(x) ((x) << S_FW_FILTER_WR_DEL_FILTER)
+#define G_FW_FILTER_WR_DEL_FILTER(x) \
+ (((x) >> S_FW_FILTER_WR_DEL_FILTER) & M_FW_FILTER_WR_DEL_FILTER)
+#define F_FW_FILTER_WR_DEL_FILTER V_FW_FILTER_WR_DEL_FILTER(1U)
+
+#define S_FW_FILTER_WR_RPTTID 25
+#define M_FW_FILTER_WR_RPTTID 0x1
+#define V_FW_FILTER_WR_RPTTID(x) ((x) << S_FW_FILTER_WR_RPTTID)
+#define G_FW_FILTER_WR_RPTTID(x) \
+ (((x) >> S_FW_FILTER_WR_RPTTID) & M_FW_FILTER_WR_RPTTID)
+#define F_FW_FILTER_WR_RPTTID V_FW_FILTER_WR_RPTTID(1U)
+
+#define S_FW_FILTER_WR_DROP 24
+#define M_FW_FILTER_WR_DROP 0x1
+#define V_FW_FILTER_WR_DROP(x) ((x) << S_FW_FILTER_WR_DROP)
+#define G_FW_FILTER_WR_DROP(x) \
+ (((x) >> S_FW_FILTER_WR_DROP) & M_FW_FILTER_WR_DROP)
+#define F_FW_FILTER_WR_DROP V_FW_FILTER_WR_DROP(1U)
+
+#define S_FW_FILTER_WR_DIRSTEER 23
+#define M_FW_FILTER_WR_DIRSTEER 0x1
+#define V_FW_FILTER_WR_DIRSTEER(x) ((x) << S_FW_FILTER_WR_DIRSTEER)
+#define G_FW_FILTER_WR_DIRSTEER(x) \
+ (((x) >> S_FW_FILTER_WR_DIRSTEER) & M_FW_FILTER_WR_DIRSTEER)
+#define F_FW_FILTER_WR_DIRSTEER V_FW_FILTER_WR_DIRSTEER(1U)
+
+#define S_FW_FILTER_WR_MASKHASH 22
+#define M_FW_FILTER_WR_MASKHASH 0x1
+#define V_FW_FILTER_WR_MASKHASH(x) ((x) << S_FW_FILTER_WR_MASKHASH)
+#define G_FW_FILTER_WR_MASKHASH(x) \
+ (((x) >> S_FW_FILTER_WR_MASKHASH) & M_FW_FILTER_WR_MASKHASH)
+#define F_FW_FILTER_WR_MASKHASH V_FW_FILTER_WR_MASKHASH(1U)
+
+#define S_FW_FILTER_WR_DIRSTEERHASH 21
+#define M_FW_FILTER_WR_DIRSTEERHASH 0x1
+#define V_FW_FILTER_WR_DIRSTEERHASH(x) ((x) << S_FW_FILTER_WR_DIRSTEERHASH)
+#define G_FW_FILTER_WR_DIRSTEERHASH(x) \
+ (((x) >> S_FW_FILTER_WR_DIRSTEERHASH) & M_FW_FILTER_WR_DIRSTEERHASH)
+#define F_FW_FILTER_WR_DIRSTEERHASH V_FW_FILTER_WR_DIRSTEERHASH(1U)
+
+#define S_FW_FILTER_WR_LPBK 20
+#define M_FW_FILTER_WR_LPBK 0x1
+#define V_FW_FILTER_WR_LPBK(x) ((x) << S_FW_FILTER_WR_LPBK)
+#define G_FW_FILTER_WR_LPBK(x) \
+ (((x) >> S_FW_FILTER_WR_LPBK) & M_FW_FILTER_WR_LPBK)
+#define F_FW_FILTER_WR_LPBK V_FW_FILTER_WR_LPBK(1U)
+
+#define S_FW_FILTER_WR_DMAC 19
+#define M_FW_FILTER_WR_DMAC 0x1
+#define V_FW_FILTER_WR_DMAC(x) ((x) << S_FW_FILTER_WR_DMAC)
+#define G_FW_FILTER_WR_DMAC(x) \
+ (((x) >> S_FW_FILTER_WR_DMAC) & M_FW_FILTER_WR_DMAC)
+#define F_FW_FILTER_WR_DMAC V_FW_FILTER_WR_DMAC(1U)
+
+#define S_FW_FILTER_WR_SMAC 18
+#define M_FW_FILTER_WR_SMAC 0x1
+#define V_FW_FILTER_WR_SMAC(x) ((x) << S_FW_FILTER_WR_SMAC)
+#define G_FW_FILTER_WR_SMAC(x) \
+ (((x) >> S_FW_FILTER_WR_SMAC) & M_FW_FILTER_WR_SMAC)
+#define F_FW_FILTER_WR_SMAC V_FW_FILTER_WR_SMAC(1U)
+
+#define S_FW_FILTER_WR_INSVLAN 17
+#define M_FW_FILTER_WR_INSVLAN 0x1
+#define V_FW_FILTER_WR_INSVLAN(x) ((x) << S_FW_FILTER_WR_INSVLAN)
+#define G_FW_FILTER_WR_INSVLAN(x) \
+ (((x) >> S_FW_FILTER_WR_INSVLAN) & M_FW_FILTER_WR_INSVLAN)
+#define F_FW_FILTER_WR_INSVLAN V_FW_FILTER_WR_INSVLAN(1U)
+
+#define S_FW_FILTER_WR_RMVLAN 16
+#define M_FW_FILTER_WR_RMVLAN 0x1
+#define V_FW_FILTER_WR_RMVLAN(x) ((x) << S_FW_FILTER_WR_RMVLAN)
+#define G_FW_FILTER_WR_RMVLAN(x) \
+ (((x) >> S_FW_FILTER_WR_RMVLAN) & M_FW_FILTER_WR_RMVLAN)
+#define F_FW_FILTER_WR_RMVLAN V_FW_FILTER_WR_RMVLAN(1U)
+
+#define S_FW_FILTER_WR_HITCNTS 15
+#define M_FW_FILTER_WR_HITCNTS 0x1
+#define V_FW_FILTER_WR_HITCNTS(x) ((x) << S_FW_FILTER_WR_HITCNTS)
+#define G_FW_FILTER_WR_HITCNTS(x) \
+ (((x) >> S_FW_FILTER_WR_HITCNTS) & M_FW_FILTER_WR_HITCNTS)
+#define F_FW_FILTER_WR_HITCNTS V_FW_FILTER_WR_HITCNTS(1U)
+
+#define S_FW_FILTER_WR_TXCHAN 13
+#define M_FW_FILTER_WR_TXCHAN 0x3
+#define V_FW_FILTER_WR_TXCHAN(x) ((x) << S_FW_FILTER_WR_TXCHAN)
+#define G_FW_FILTER_WR_TXCHAN(x) \
+ (((x) >> S_FW_FILTER_WR_TXCHAN) & M_FW_FILTER_WR_TXCHAN)
+
+#define S_FW_FILTER_WR_PRIO 12
+#define M_FW_FILTER_WR_PRIO 0x1
+#define V_FW_FILTER_WR_PRIO(x) ((x) << S_FW_FILTER_WR_PRIO)
+#define G_FW_FILTER_WR_PRIO(x) \
+ (((x) >> S_FW_FILTER_WR_PRIO) & M_FW_FILTER_WR_PRIO)
+#define F_FW_FILTER_WR_PRIO V_FW_FILTER_WR_PRIO(1U)
+
+#define S_FW_FILTER_WR_L2TIX 0
+#define M_FW_FILTER_WR_L2TIX 0xfff
+#define V_FW_FILTER_WR_L2TIX(x) ((x) << S_FW_FILTER_WR_L2TIX)
+#define G_FW_FILTER_WR_L2TIX(x) \
+ (((x) >> S_FW_FILTER_WR_L2TIX) & M_FW_FILTER_WR_L2TIX)
+
+#define S_FW_FILTER_WR_FRAG 7
+#define M_FW_FILTER_WR_FRAG 0x1
+#define V_FW_FILTER_WR_FRAG(x) ((x) << S_FW_FILTER_WR_FRAG)
+#define G_FW_FILTER_WR_FRAG(x) \
+ (((x) >> S_FW_FILTER_WR_FRAG) & M_FW_FILTER_WR_FRAG)
+#define F_FW_FILTER_WR_FRAG V_FW_FILTER_WR_FRAG(1U)
+
+#define S_FW_FILTER_WR_FRAGM 6
+#define M_FW_FILTER_WR_FRAGM 0x1
+#define V_FW_FILTER_WR_FRAGM(x) ((x) << S_FW_FILTER_WR_FRAGM)
+#define G_FW_FILTER_WR_FRAGM(x) \
+ (((x) >> S_FW_FILTER_WR_FRAGM) & M_FW_FILTER_WR_FRAGM)
+#define F_FW_FILTER_WR_FRAGM V_FW_FILTER_WR_FRAGM(1U)
+
+#define S_FW_FILTER_WR_IVLAN_VLD 5
+#define M_FW_FILTER_WR_IVLAN_VLD 0x1
+#define V_FW_FILTER_WR_IVLAN_VLD(x) ((x) << S_FW_FILTER_WR_IVLAN_VLD)
+#define G_FW_FILTER_WR_IVLAN_VLD(x) \
+ (((x) >> S_FW_FILTER_WR_IVLAN_VLD) & M_FW_FILTER_WR_IVLAN_VLD)
+#define F_FW_FILTER_WR_IVLAN_VLD V_FW_FILTER_WR_IVLAN_VLD(1U)
+
+#define S_FW_FILTER_WR_OVLAN_VLD 4
+#define M_FW_FILTER_WR_OVLAN_VLD 0x1
+#define V_FW_FILTER_WR_OVLAN_VLD(x) ((x) << S_FW_FILTER_WR_OVLAN_VLD)
+#define G_FW_FILTER_WR_OVLAN_VLD(x) \
+ (((x) >> S_FW_FILTER_WR_OVLAN_VLD) & M_FW_FILTER_WR_OVLAN_VLD)
+#define F_FW_FILTER_WR_OVLAN_VLD V_FW_FILTER_WR_OVLAN_VLD(1U)
+
+#define S_FW_FILTER_WR_IVLAN_VLDM 3
+#define M_FW_FILTER_WR_IVLAN_VLDM 0x1
+#define V_FW_FILTER_WR_IVLAN_VLDM(x) ((x) << S_FW_FILTER_WR_IVLAN_VLDM)
+#define G_FW_FILTER_WR_IVLAN_VLDM(x) \
+ (((x) >> S_FW_FILTER_WR_IVLAN_VLDM) & M_FW_FILTER_WR_IVLAN_VLDM)
+#define F_FW_FILTER_WR_IVLAN_VLDM V_FW_FILTER_WR_IVLAN_VLDM(1U)
+
+#define S_FW_FILTER_WR_OVLAN_VLDM 2
+#define M_FW_FILTER_WR_OVLAN_VLDM 0x1
+#define V_FW_FILTER_WR_OVLAN_VLDM(x) ((x) << S_FW_FILTER_WR_OVLAN_VLDM)
+#define G_FW_FILTER_WR_OVLAN_VLDM(x) \
+ (((x) >> S_FW_FILTER_WR_OVLAN_VLDM) & M_FW_FILTER_WR_OVLAN_VLDM)
+#define F_FW_FILTER_WR_OVLAN_VLDM V_FW_FILTER_WR_OVLAN_VLDM(1U)
+
+#define S_FW_FILTER_WR_RX_CHAN 15
+#define M_FW_FILTER_WR_RX_CHAN 0x1
+#define V_FW_FILTER_WR_RX_CHAN(x) ((x) << S_FW_FILTER_WR_RX_CHAN)
+#define G_FW_FILTER_WR_RX_CHAN(x) \
+ (((x) >> S_FW_FILTER_WR_RX_CHAN) & M_FW_FILTER_WR_RX_CHAN)
+#define F_FW_FILTER_WR_RX_CHAN V_FW_FILTER_WR_RX_CHAN(1U)
+
+#define S_FW_FILTER_WR_RX_RPL_IQ 0
+#define M_FW_FILTER_WR_RX_RPL_IQ 0x3ff
+#define V_FW_FILTER_WR_RX_RPL_IQ(x) ((x) << S_FW_FILTER_WR_RX_RPL_IQ)
+#define G_FW_FILTER_WR_RX_RPL_IQ(x) \
+ (((x) >> S_FW_FILTER_WR_RX_RPL_IQ) & M_FW_FILTER_WR_RX_RPL_IQ)
+
+#define S_FW_FILTER_WR_MACI 23
+#define M_FW_FILTER_WR_MACI 0x1ff
+#define V_FW_FILTER_WR_MACI(x) ((x) << S_FW_FILTER_WR_MACI)
+#define G_FW_FILTER_WR_MACI(x) \
+ (((x) >> S_FW_FILTER_WR_MACI) & M_FW_FILTER_WR_MACI)
+
+#define S_FW_FILTER_WR_MACIM 14
+#define M_FW_FILTER_WR_MACIM 0x1ff
+#define V_FW_FILTER_WR_MACIM(x) ((x) << S_FW_FILTER_WR_MACIM)
+#define G_FW_FILTER_WR_MACIM(x) \
+ (((x) >> S_FW_FILTER_WR_MACIM) & M_FW_FILTER_WR_MACIM)
+
+#define S_FW_FILTER_WR_FCOE 13
+#define M_FW_FILTER_WR_FCOE 0x1
+#define V_FW_FILTER_WR_FCOE(x) ((x) << S_FW_FILTER_WR_FCOE)
+#define G_FW_FILTER_WR_FCOE(x) \
+ (((x) >> S_FW_FILTER_WR_FCOE) & M_FW_FILTER_WR_FCOE)
+#define F_FW_FILTER_WR_FCOE V_FW_FILTER_WR_FCOE(1U)
+
+#define S_FW_FILTER_WR_FCOEM 12
+#define M_FW_FILTER_WR_FCOEM 0x1
+#define V_FW_FILTER_WR_FCOEM(x) ((x) << S_FW_FILTER_WR_FCOEM)
+#define G_FW_FILTER_WR_FCOEM(x) \
+ (((x) >> S_FW_FILTER_WR_FCOEM) & M_FW_FILTER_WR_FCOEM)
+#define F_FW_FILTER_WR_FCOEM V_FW_FILTER_WR_FCOEM(1U)
+
+#define S_FW_FILTER_WR_PORT 9
+#define M_FW_FILTER_WR_PORT 0x7
+#define V_FW_FILTER_WR_PORT(x) ((x) << S_FW_FILTER_WR_PORT)
+#define G_FW_FILTER_WR_PORT(x) \
+ (((x) >> S_FW_FILTER_WR_PORT) & M_FW_FILTER_WR_PORT)
+
+#define S_FW_FILTER_WR_PORTM 6
+#define M_FW_FILTER_WR_PORTM 0x7
+#define V_FW_FILTER_WR_PORTM(x) ((x) << S_FW_FILTER_WR_PORTM)
+#define G_FW_FILTER_WR_PORTM(x) \
+ (((x) >> S_FW_FILTER_WR_PORTM) & M_FW_FILTER_WR_PORTM)
+
+#define S_FW_FILTER_WR_MATCHTYPE 3
+#define M_FW_FILTER_WR_MATCHTYPE 0x7
+#define V_FW_FILTER_WR_MATCHTYPE(x) ((x) << S_FW_FILTER_WR_MATCHTYPE)
+#define G_FW_FILTER_WR_MATCHTYPE(x) \
+ (((x) >> S_FW_FILTER_WR_MATCHTYPE) & M_FW_FILTER_WR_MATCHTYPE)
+
+#define S_FW_FILTER_WR_MATCHTYPEM 0
+#define M_FW_FILTER_WR_MATCHTYPEM 0x7
+#define V_FW_FILTER_WR_MATCHTYPEM(x) ((x) << S_FW_FILTER_WR_MATCHTYPEM)
+#define G_FW_FILTER_WR_MATCHTYPEM(x) \
+ (((x) >> S_FW_FILTER_WR_MATCHTYPEM) & M_FW_FILTER_WR_MATCHTYPEM)
+
struct fw_ulptx_wr {
__be32 op_to_compl;
__be32 flowid_len16;
--
1.7.1
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply related
* Re: [net-next rfc v7 3/3] virtio-net: change the number of queues through ethtool
From: Michael S. Tsirkin @ 2012-12-03 11:25 UTC (permalink / raw)
To: Jason Wang
Cc: krkumar2, kvm, netdev, linux-kernel, virtualization, bhutchings,
jwhan, shiyer
In-Reply-To: <7408756.Sj6HEpCzzZ@jason-thinkpad-t430s>
On Mon, Dec 03, 2012 at 02:09:28PM +0800, Jason Wang wrote:
> On Sunday, December 02, 2012 06:09:06 PM Michael S. Tsirkin wrote:
> > On Tue, Nov 27, 2012 at 06:16:00PM +0800, Jason Wang wrote:
> > > This patch implement the {set|get}_channels method of ethool to allow user
> > > to change the number of queues dymaically when the device is running.
> > > This would let the user to configure it on demand.
> > >
> > > Signed-off-by: Jason Wang <jasowang@redhat.com>
> > > ---
> > >
> > > drivers/net/virtio_net.c | 41 +++++++++++++++++++++++++++++++++++++++++
> > > 1 files changed, 41 insertions(+), 0 deletions(-)
> > >
> > > diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
> > > index bcaa6e5..f08ec2a 100644
> > > --- a/drivers/net/virtio_net.c
> > > +++ b/drivers/net/virtio_net.c
> > > @@ -1578,10 +1578,51 @@ static struct virtio_driver virtio_net_driver = {
> > >
> > > #endif
> > > };
> > >
> > > +/* TODO: Eliminate OOO packets during switching */
> > > +static int virtnet_set_channels(struct net_device *dev,
> > > + struct ethtool_channels *channels)
> > > +{
> > > + struct virtnet_info *vi = netdev_priv(dev);
> > > + u16 queue_pairs = channels->combined_count;
by the way shouldn't this be combined_count / 2?
And below channels->max_combined = vi->max_queue_pairs * 2; ?
> > > +
> > > + /* We don't support separate rx/tx channels.
> > > + * We don't allow setting 'other' channels.
> > > + */
> > > + if (channels->rx_count || channels->tx_count || channels->other_count)
> > > + return -EINVAL;
> > > +
> > > + /* Only two modes were support currently */
> > > + if (queue_pairs != vi->max_queue_pairs && queue_pairs != 1)
> > > + return -EINVAL;
> > > +
> >
> > Why the limitation?
>
> Not sure the value bettwen 1 and max_queue_pairs is useful. But anyway, I can
> remove this limitation.
I guess a reasonable value would be number of active CPUs,
which can change with CPU hotplug.
> > Also how does userspace discover what the legal values are?
>
> Userspace only check whether the value is greater than max_queue_pairs.
Exactly. One can query max combined but the fact that configuring
any less is impossible might be surprising.
> >
> > > + vi->curr_queue_pairs = queue_pairs;
> > > + BUG_ON(virtnet_set_queues(vi));
> > > +
> > > + netif_set_real_num_tx_queues(dev, vi->curr_queue_pairs);
> > > + netif_set_real_num_rx_queues(dev, vi->curr_queue_pairs);
> > > +
> > > + return 0;
> > > +}
> > > +
> > > +static void virtnet_get_channels(struct net_device *dev,
> > > + struct ethtool_channels *channels)
> > > +{
> > > + struct virtnet_info *vi = netdev_priv(dev);
> > > +
> > > + channels->combined_count = vi->curr_queue_pairs;
> > > + channels->max_combined = vi->max_queue_pairs;
> > > + channels->max_other = 0;
> > > + channels->rx_count = 0;
> > > + channels->tx_count = 0;
> > > + channels->other_count = 0;
> > > +}
> > > +
> > >
> > > static const struct ethtool_ops virtnet_ethtool_ops = {
> > >
> > > .get_drvinfo = virtnet_get_drvinfo,
> > > .get_link = ethtool_op_get_link,
> > > .get_ringparam = virtnet_get_ringparam,
> > >
> > > + .set_channels = virtnet_set_channels,
> > > + .get_channels = virtnet_get_channels,
> > >
> > > };
> > >
> > > static int __init init(void)
> >
> > --
> > To unsubscribe from this list: send the line "unsubscribe kvm" in
> > the body of a message to majordomo@vger.kernel.org
> > More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply
* [PATCH V3 2/5] cxgb4: Add LE hash collision bug fix path in LLD driver
From: Vipul Pandya @ 2012-12-03 11:22 UTC (permalink / raw)
To: linux-rdma, netdev
Cc: roland, davem, divy, dm, kumaras, swise, abhishek, Vipul Pandya
In-Reply-To: <1354533781-31575-1-git-send-email-vipul@chelsio.com>
It supports establishing passive open connection through firmware filter work
request. Passive open connection will go through this path as now instead of
listening server we create a server filter which will redirect the incoming SYN
packet to the offload queue.
It divides filter region into regular filters and server filter portion. It
introduces new server filter region which will be exclusively used for creating
server filters. This region will not overlap with regular filter region.
It provides new API cxgb4_alloc_sftid in LLD for getting stid in case of LE
hash collision path. This new stid will be used to open server filter in the
filter region.
Signed-off-by: Vipul Pandya <vipul@chelsio.com>
---
V2: Changed commenting style from kernel-doc format('/**') to normal
V3: Resending the whole patch series again with the missing patches in V2
drivers/net/ethernet/chelsio/cxgb4/cxgb4.h | 4 +
drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c | 150 +++++++++++++++++++++-
drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.h | 15 ++-
drivers/net/ethernet/chelsio/cxgb4/t4_regs.h | 33 +++++
4 files changed, 193 insertions(+), 9 deletions(-)
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h b/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h
index b6403d1..868acde 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h
@@ -35,6 +35,8 @@
#ifndef __CXGB4_H__
#define __CXGB4_H__
+#include "t4_hw.h"
+
#include <linux/bitops.h>
#include <linux/cache.h>
#include <linux/interrupt.h>
@@ -212,6 +214,8 @@ struct tp_err_stats {
struct tp_params {
unsigned int ntxchan; /* # of Tx channels */
unsigned int tre; /* log2 of core clocks per TP tick */
+ unsigned short tx_modq_map; /* TX modulation scheduler queue to */
+ /* channel map */
uint32_t dack_re; /* DACK timer resolution */
unsigned short tx_modq[NCHAN]; /* channel to modulation queue map */
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
index a678287..f55386b 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
@@ -2489,7 +2489,34 @@ int cxgb4_alloc_stid(struct tid_info *t, int family, void *data)
EXPORT_SYMBOL(cxgb4_alloc_stid);
/*
- * Release a server TID.
+ * Allocate a server filter TID and set it to the supplied value.
+ */
+int cxgb4_alloc_sftid(struct tid_info *t, int family, void *data)
+{
+ int stid;
+
+ spin_lock_bh(&t->stid_lock);
+ if (family == PF_INET) {
+ stid = find_next_zero_bit(t->stid_bmap,
+ t->nstids + t->nsftids, t->nstids);
+ if (stid < (t->nstids + t->nsftids))
+ __set_bit(stid, t->stid_bmap);
+ else
+ stid = -1;
+ } else {
+ stid = -1;
+ }
+ if (stid >= 0) {
+ t->stid_tab[stid].data = data;
+ stid += t->stid_base;
+ t->stids_in_use++;
+ }
+ spin_unlock_bh(&t->stid_lock);
+ return stid;
+}
+EXPORT_SYMBOL(cxgb4_alloc_sftid);
+
+/* Release a server TID.
*/
void cxgb4_free_stid(struct tid_info *t, unsigned int stid, int family)
{
@@ -2604,12 +2631,14 @@ static int tid_init(struct tid_info *t)
unsigned int stid_bmap_size;
unsigned int natids = t->natids;
- stid_bmap_size = BITS_TO_LONGS(t->nstids);
+ stid_bmap_size = BITS_TO_LONGS(t->nstids + t->nsftids);
size = t->ntids * sizeof(*t->tid_tab) +
natids * sizeof(*t->atid_tab) +
t->nstids * sizeof(*t->stid_tab) +
+ t->nsftids * sizeof(*t->stid_tab) +
stid_bmap_size * sizeof(long) +
- t->nftids * sizeof(*t->ftid_tab);
+ t->nftids * sizeof(*t->ftid_tab) +
+ t->nsftids * sizeof(*t->ftid_tab);
t->tid_tab = t4_alloc_mem(size);
if (!t->tid_tab)
@@ -2617,7 +2646,7 @@ static int tid_init(struct tid_info *t)
t->atid_tab = (union aopen_entry *)&t->tid_tab[t->ntids];
t->stid_tab = (struct serv_entry *)&t->atid_tab[natids];
- t->stid_bmap = (unsigned long *)&t->stid_tab[t->nstids];
+ t->stid_bmap = (unsigned long *)&t->stid_tab[t->nstids + t->nsftids];
t->ftid_tab = (struct filter_entry *)&t->stid_bmap[stid_bmap_size];
spin_lock_init(&t->stid_lock);
spin_lock_init(&t->atid_lock);
@@ -2633,7 +2662,7 @@ static int tid_init(struct tid_info *t)
t->atid_tab[natids - 1].next = &t->atid_tab[natids];
t->afree = t->atid_tab;
}
- bitmap_zero(t->stid_bmap, t->nstids);
+ bitmap_zero(t->stid_bmap, t->nstids + t->nsftids);
return 0;
}
@@ -2995,6 +3024,7 @@ static void uld_attach(struct adapter *adap, unsigned int uld)
{
void *handle;
struct cxgb4_lld_info lli;
+ unsigned short i;
lli.pdev = adap->pdev;
lli.l2t = adap->l2t;
@@ -3021,10 +3051,16 @@ static void uld_attach(struct adapter *adap, unsigned int uld)
lli.ucq_density = 1 << QUEUESPERPAGEPF0_GET(
t4_read_reg(adap, SGE_INGRESS_QUEUES_PER_PAGE_PF) >>
(adap->fn * 4));
+ lli.filt_mode = tp_vlan_pri_map;
+ /* MODQ_REQ_MAP sets queues 0-3 to chan 0-3 */
+ for (i = 0; i < NCHAN; i++)
+ lli.tx_modq[i] = i;
lli.gts_reg = adap->regs + MYPF_REG(SGE_PF_GTS);
lli.db_reg = adap->regs + MYPF_REG(SGE_PF_KDOORBELL);
lli.fw_vers = adap->params.fw_vers;
lli.dbfifo_int_thresh = dbfifo_int_thresh;
+ lli.sge_pktshift = adap->sge.pktshift;
+ lli.enable_fw_ofld_conn = adap->flags & FW_OFLD_CONN;
handle = ulds[uld].add(&lli);
if (IS_ERR(handle)) {
@@ -3266,7 +3302,7 @@ static int delete_filter(struct adapter *adapter, unsigned int fidx)
struct filter_entry *f;
int ret;
- if (fidx >= adapter->tids.nftids)
+ if (fidx >= adapter->tids.nftids + adapter->tids.nsftids)
return -EINVAL;
f = &adapter->tids.ftid_tab[fidx];
@@ -3279,6 +3315,77 @@ static int delete_filter(struct adapter *adapter, unsigned int fidx)
return 0;
}
+int cxgb4_create_server_filter(const struct net_device *dev, unsigned int stid,
+ __be32 sip, __be16 sport, unsigned int queue)
+{
+ int ret;
+ struct filter_entry *f;
+ struct adapter *adap;
+ int i;
+ u8 *val;
+
+ adap = netdev2adap(dev);
+
+ /* Check to make sure the filter requested is writable ...
+ */
+ f = &adap->tids.ftid_tab[stid];
+ ret = writable_filter(f);
+ if (ret)
+ return ret;
+
+ /* Clear out any old resources being used by the filter before
+ * we start constructing the new filter.
+ */
+ if (f->valid)
+ clear_filter(adap, f);
+
+ /* Clear out filter specifications */
+ memset(&f->fs, 0, sizeof(struct ch_filter_specification));
+ f->fs.val.lport = cpu_to_be16(sport);
+ f->fs.mask.lport = ~0;
+ val = (u8 *)&sip;
+ if ((val[0] | val[1] | val[2] | val[3]) != 0)
+ for (i = 0; i < 4; i++) {
+ f->fs.val.lip[i] = val[i];
+ f->fs.mask.lip[i] = ~0;
+ }
+
+ f->fs.dirsteer = 1;
+ f->fs.iq = queue;
+ /* Mark filter as locked */
+ f->locked = 1;
+ f->fs.rpttid = 1;
+
+ ret = set_filter_wr(adap, stid);
+ if (ret) {
+ clear_filter(adap, f);
+ return ret;
+ }
+
+ return 0;
+}
+EXPORT_SYMBOL(cxgb4_create_server_filter);
+
+int cxgb4_remove_server_filter(const struct net_device *dev, unsigned int stid,
+ unsigned int queue, bool ipv6)
+{
+ int ret;
+ struct filter_entry *f;
+ struct adapter *adap;
+
+ adap = netdev2adap(dev);
+ f = &adap->tids.ftid_tab[stid];
+ /* Unlock the filter */
+ f->locked = 0;
+
+ ret = delete_filter(adap, stid);
+ if (ret)
+ return ret;
+
+ return 0;
+}
+EXPORT_SYMBOL(cxgb4_remove_server_filter);
+
static struct rtnl_link_stats64 *cxgb_get_stats(struct net_device *dev,
struct rtnl_link_stats64 *ns)
{
@@ -3525,6 +3632,34 @@ static int adap_init1(struct adapter *adap, struct fw_caps_config_cmd *c)
v = t4_read_reg(adap, TP_PIO_DATA);
t4_write_reg(adap, TP_PIO_DATA, v & ~CSUM_HAS_PSEUDO_HDR);
+ /* first 4 Tx modulation queues point to consecutive Tx channels */
+ adap->params.tp.tx_modq_map = 0xE4;
+ t4_write_reg(adap, A_TP_TX_MOD_QUEUE_REQ_MAP,
+ V_TX_MOD_QUEUE_REQ_MAP(adap->params.tp.tx_modq_map));
+
+ /* associate each Tx modulation queue with consecutive Tx channels */
+ v = 0x84218421;
+ t4_write_indirect(adap, TP_PIO_ADDR, TP_PIO_DATA,
+ &v, 1, A_TP_TX_SCHED_HDR);
+ t4_write_indirect(adap, TP_PIO_ADDR, TP_PIO_DATA,
+ &v, 1, A_TP_TX_SCHED_FIFO);
+ t4_write_indirect(adap, TP_PIO_ADDR, TP_PIO_DATA,
+ &v, 1, A_TP_TX_SCHED_PCMD);
+
+#define T4_TX_MODQ_10G_WEIGHT_DEFAULT 16 /* in KB units */
+ if (is_offload(adap)) {
+ t4_write_reg(adap, A_TP_TX_MOD_QUEUE_WEIGHT0,
+ V_TX_MODQ_WEIGHT0(T4_TX_MODQ_10G_WEIGHT_DEFAULT) |
+ V_TX_MODQ_WEIGHT1(T4_TX_MODQ_10G_WEIGHT_DEFAULT) |
+ V_TX_MODQ_WEIGHT2(T4_TX_MODQ_10G_WEIGHT_DEFAULT) |
+ V_TX_MODQ_WEIGHT3(T4_TX_MODQ_10G_WEIGHT_DEFAULT));
+ t4_write_reg(adap, A_TP_TX_MOD_CHANNEL_WEIGHT,
+ V_TX_MODQ_WEIGHT0(T4_TX_MODQ_10G_WEIGHT_DEFAULT) |
+ V_TX_MODQ_WEIGHT1(T4_TX_MODQ_10G_WEIGHT_DEFAULT) |
+ V_TX_MODQ_WEIGHT2(T4_TX_MODQ_10G_WEIGHT_DEFAULT) |
+ V_TX_MODQ_WEIGHT3(T4_TX_MODQ_10G_WEIGHT_DEFAULT));
+ }
+
/* get basic stuff going */
return t4_early_init(adap, adap->fn);
}
@@ -4948,7 +5083,8 @@ static void __devexit remove_one(struct pci_dev *pdev)
*/
if (adapter->tids.ftid_tab) {
struct filter_entry *f = &adapter->tids.ftid_tab[0];
- for (i = 0; i < adapter->tids.nftids; i++, f++)
+ for (i = 0; i < (adapter->tids.nftids +
+ adapter->tids.nsftids); i++, f++)
if (f->valid)
clear_filter(adapter, f);
}
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.h b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.h
index 59a6133..065bbd5 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.h
@@ -131,7 +131,7 @@ static inline void *lookup_atid(const struct tid_info *t, unsigned int atid)
static inline void *lookup_stid(const struct tid_info *t, unsigned int stid)
{
stid -= t->stid_base;
- return stid < t->nstids ? t->stid_tab[stid].data : NULL;
+ return stid < (t->nstids + t->nsftids) ? t->stid_tab[stid].data : NULL;
}
static inline void cxgb4_insert_tid(struct tid_info *t, void *data,
@@ -143,6 +143,7 @@ static inline void cxgb4_insert_tid(struct tid_info *t, void *data,
int cxgb4_alloc_atid(struct tid_info *t, void *data);
int cxgb4_alloc_stid(struct tid_info *t, int family, void *data);
+int cxgb4_alloc_sftid(struct tid_info *t, int family, void *data);
void cxgb4_free_atid(struct tid_info *t, unsigned int atid);
void cxgb4_free_stid(struct tid_info *t, unsigned int stid, int family);
void cxgb4_remove_tid(struct tid_info *t, unsigned int qid, unsigned int tid);
@@ -151,7 +152,10 @@ struct in6_addr;
int cxgb4_create_server(const struct net_device *dev, unsigned int stid,
__be32 sip, __be16 sport, unsigned int queue);
-
+int cxgb4_create_server_filter(const struct net_device *dev, unsigned int stid,
+ __be32 sip, __be16 sport, unsigned int queue);
+int cxgb4_remove_server_filter(const struct net_device *dev, unsigned int stid,
+ unsigned int queue, bool ipv6);
static inline void set_wr_txq(struct sk_buff *skb, int prio, int queue)
{
skb_set_queue_mapping(skb, (queue << 1) | prio);
@@ -223,9 +227,16 @@ struct cxgb4_lld_info {
unsigned int iscsi_iolen; /* iSCSI max I/O length */
unsigned short udb_density; /* # of user DB/page */
unsigned short ucq_density; /* # of user CQs/page */
+ unsigned short filt_mode; /* filter optional components */
+ unsigned short tx_modq[NCHAN]; /* maps each tx channel to a */
+ /* scheduler queue */
void __iomem *gts_reg; /* address of GTS register */
void __iomem *db_reg; /* address of kernel doorbell */
int dbfifo_int_thresh; /* doorbell fifo int threshold */
+ unsigned int sge_pktshift; /* Padding between CPL and */
+ /* packet data */
+ bool enable_fw_ofld_conn; /* Enable connection through fw */
+ /* WR */
};
struct cxgb4_uld_info {
diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_regs.h b/drivers/net/ethernet/chelsio/cxgb4/t4_regs.h
index a1a8b57..66ab614 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/t4_regs.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/t4_regs.h
@@ -1032,4 +1032,37 @@
#define ADDRESS(x) ((x) << ADDRESS_SHIFT)
#define XGMAC_PORT_INT_CAUSE 0x10dc
+
+#define A_TP_TX_MOD_QUEUE_REQ_MAP 0x7e28
+
+#define A_TP_TX_MOD_CHANNEL_WEIGHT 0x7e34
+
+#define S_TX_MOD_QUEUE_REQ_MAP 0
+#define M_TX_MOD_QUEUE_REQ_MAP 0xffffU
+#define V_TX_MOD_QUEUE_REQ_MAP(x) ((x) << S_TX_MOD_QUEUE_REQ_MAP)
+
+#define A_TP_TX_MOD_QUEUE_WEIGHT0 0x7e30
+
+#define S_TX_MODQ_WEIGHT3 24
+#define M_TX_MODQ_WEIGHT3 0xffU
+#define V_TX_MODQ_WEIGHT3(x) ((x) << S_TX_MODQ_WEIGHT3)
+
+#define S_TX_MODQ_WEIGHT2 16
+#define M_TX_MODQ_WEIGHT2 0xffU
+#define V_TX_MODQ_WEIGHT2(x) ((x) << S_TX_MODQ_WEIGHT2)
+
+#define S_TX_MODQ_WEIGHT1 8
+#define M_TX_MODQ_WEIGHT1 0xffU
+#define V_TX_MODQ_WEIGHT1(x) ((x) << S_TX_MODQ_WEIGHT1)
+
+#define S_TX_MODQ_WEIGHT0 0
+#define M_TX_MODQ_WEIGHT0 0xffU
+#define V_TX_MODQ_WEIGHT0(x) ((x) << S_TX_MODQ_WEIGHT0)
+
+#define A_TP_TX_SCHED_HDR 0x23
+
+#define A_TP_TX_SCHED_FIFO 0x24
+
+#define A_TP_TX_SCHED_PCMD 0x25
+
#endif /* __T4_REGS_H */
--
1.7.1
^ permalink raw reply related
* [PATCH V3 3/5] RDMA/cxgb4: Fix LE hash collision bug for active open connection
From: Vipul Pandya @ 2012-12-03 11:22 UTC (permalink / raw)
To: linux-rdma, netdev
Cc: roland, davem, divy, dm, kumaras, swise, abhishek, Vipul Pandya
In-Reply-To: <1354533781-31575-1-git-send-email-vipul@chelsio.com>
It enables establishing active open connection using fw_ofld_connection work
request when cpl_act_open_rpl says TCAM full error which may be because
of LE hash collision. Current support is only for IPv4 active open connections.
Sets ntuple bits in active open requests. For T4 firmware greater than 1.4.10.0
ntuple bits are required to be set.
Adds nocong and enable_ecn module parameter options.
Signed-off-by: Vipul Pandya <vipul@chelsio.com>
---
V2: Changed commenting style from kernel-doc format('/**') to normal
V3: Resending the whole patch series again with the missing patches in V2
drivers/infiniband/hw/cxgb4/cm.c | 158 ++++++++++++++++++++++++-
drivers/infiniband/hw/cxgb4/iw_cxgb4.h | 1 +
drivers/net/ethernet/chelsio/cxgb4/t4_msg.h | 19 +++
drivers/net/ethernet/chelsio/cxgb4/t4_regs.h | 2 +
drivers/net/ethernet/chelsio/cxgb4/t4fw_api.h | 109 +++++++++++++++++
5 files changed, 283 insertions(+), 6 deletions(-)
diff --git a/drivers/infiniband/hw/cxgb4/cm.c b/drivers/infiniband/hw/cxgb4/cm.c
index 5de8696..4878704 100644
--- a/drivers/infiniband/hw/cxgb4/cm.c
+++ b/drivers/infiniband/hw/cxgb4/cm.c
@@ -61,6 +61,14 @@ static char *states[] = {
NULL,
};
+static int nocong;
+module_param(nocong, int, 0644);
+MODULE_PARM_DESC(nocong, "Turn of congestion control (default=0)");
+
+static int enable_ecn;
+module_param(enable_ecn, int, 0644);
+MODULE_PARM_DESC(enable_ecn, "Enable ECN (default=0/disabled)");
+
static int dack_mode = 1;
module_param(dack_mode, int, 0644);
MODULE_PARM_DESC(dack_mode, "Delayed ack mode (default=1)");
@@ -441,6 +449,50 @@ static int send_abort(struct c4iw_ep *ep, struct sk_buff *skb, gfp_t gfp)
return c4iw_l2t_send(&ep->com.dev->rdev, skb, ep->l2t);
}
+#define VLAN_NONE 0xfff
+#define FILTER_SEL_VLAN_NONE 0xffff
+#define FILTER_SEL_WIDTH_P_FC (3+1) /* port uses 3 bits, FCoE one bit */
+#define FILTER_SEL_WIDTH_VIN_P_FC \
+ (6 + 7 + FILTER_SEL_WIDTH_P_FC) /* 6 bits are unused, VF uses 7 bits*/
+#define FILTER_SEL_WIDTH_TAG_P_FC \
+ (3 + FILTER_SEL_WIDTH_VIN_P_FC) /* PF uses 3 bits */
+#define FILTER_SEL_WIDTH_VLD_TAG_P_FC (1 + FILTER_SEL_WIDTH_TAG_P_FC)
+
+static unsigned int select_ntuple(struct c4iw_dev *dev, struct dst_entry *dst,
+ struct l2t_entry *l2t)
+{
+ unsigned int ntuple = 0;
+ u32 viid;
+
+ switch (dev->rdev.lldi.filt_mode) {
+
+ /* default filter mode */
+ case HW_TPL_FR_MT_PR_IV_P_FC:
+ if (l2t->vlan == VLAN_NONE)
+ ntuple |= FILTER_SEL_VLAN_NONE << FILTER_SEL_WIDTH_P_FC;
+ else {
+ ntuple |= l2t->vlan << FILTER_SEL_WIDTH_P_FC;
+ ntuple |= 1 << FILTER_SEL_WIDTH_VLD_TAG_P_FC;
+ }
+ ntuple |= l2t->lport << S_PORT | IPPROTO_TCP <<
+ FILTER_SEL_WIDTH_VLD_TAG_P_FC;
+ break;
+ case HW_TPL_FR_MT_PR_OV_P_FC: {
+ viid = cxgb4_port_viid(l2t->neigh->dev);
+
+ ntuple |= FW_VIID_VIN_GET(viid) << FILTER_SEL_WIDTH_P_FC;
+ ntuple |= FW_VIID_PFN_GET(viid) << FILTER_SEL_WIDTH_VIN_P_FC;
+ ntuple |= FW_VIID_VIVLD_GET(viid) << FILTER_SEL_WIDTH_TAG_P_FC;
+ ntuple |= l2t->lport << S_PORT | IPPROTO_TCP <<
+ FILTER_SEL_WIDTH_VLD_TAG_P_FC;
+ break;
+ }
+ default:
+ break;
+ }
+ return ntuple;
+}
+
static int send_connect(struct c4iw_ep *ep)
{
struct cpl_act_open_req *req;
@@ -463,7 +515,8 @@ static int send_connect(struct c4iw_ep *ep)
cxgb4_best_mtu(ep->com.dev->rdev.lldi.mtus, ep->mtu, &mtu_idx);
wscale = compute_wscale(rcv_win);
- opt0 = KEEP_ALIVE(1) |
+ opt0 = (nocong ? NO_CONG(1) : 0) |
+ KEEP_ALIVE(1) |
DELACK(1) |
WND_SCALE(wscale) |
MSS_IDX(mtu_idx) |
@@ -474,6 +527,7 @@ static int send_connect(struct c4iw_ep *ep)
ULP_MODE(ULP_MODE_TCPDDP) |
RCV_BUFSIZ(rcv_win>>10);
opt2 = RX_CHANNEL(0) |
+ CCTRL_ECN(enable_ecn) |
RSS_QUEUE_VALID | RSS_QUEUE(ep->rss_qid);
if (enable_tcp_timestamps)
opt2 |= TSTAMPS_EN(1);
@@ -492,7 +546,7 @@ static int send_connect(struct c4iw_ep *ep)
req->local_ip = ep->com.local_addr.sin_addr.s_addr;
req->peer_ip = ep->com.remote_addr.sin_addr.s_addr;
req->opt0 = cpu_to_be64(opt0);
- req->params = 0;
+ req->params = cpu_to_be32(select_ntuple(ep->com.dev, ep->dst, ep->l2t));
req->opt2 = cpu_to_be32(opt2);
return c4iw_l2t_send(&ep->com.dev->rdev, skb, ep->l2t);
}
@@ -1383,6 +1437,61 @@ static int abort_rpl(struct c4iw_dev *dev, struct sk_buff *skb)
return 0;
}
+static void send_fw_act_open_req(struct c4iw_ep *ep, unsigned int atid)
+{
+ struct sk_buff *skb;
+ struct fw_ofld_connection_wr *req;
+ unsigned int mtu_idx;
+ int wscale;
+
+ skb = get_skb(NULL, sizeof(*req), GFP_KERNEL);
+ req = (struct fw_ofld_connection_wr *)__skb_put(skb, sizeof(*req));
+ memset(req, 0, sizeof(*req));
+ req->op_compl = htonl(V_WR_OP(FW_OFLD_CONNECTION_WR));
+ req->len16_pkd = htonl(FW_WR_LEN16(DIV_ROUND_UP(sizeof(*req), 16)));
+ req->le.filter = cpu_to_be32(select_ntuple(ep->com.dev, ep->dst,
+ ep->l2t));
+ req->le.lport = ep->com.local_addr.sin_port;
+ req->le.pport = ep->com.remote_addr.sin_port;
+ req->le.u.ipv4.lip = ep->com.local_addr.sin_addr.s_addr;
+ req->le.u.ipv4.pip = ep->com.remote_addr.sin_addr.s_addr;
+ req->tcb.t_state_to_astid =
+ htonl(V_FW_OFLD_CONNECTION_WR_T_STATE(TCP_SYN_SENT) |
+ V_FW_OFLD_CONNECTION_WR_ASTID(atid));
+ req->tcb.cplrxdataack_cplpassacceptrpl =
+ htons(F_FW_OFLD_CONNECTION_WR_CPLRXDATAACK);
+ req->tcb.tx_max = jiffies;
+ cxgb4_best_mtu(ep->com.dev->rdev.lldi.mtus, ep->mtu, &mtu_idx);
+ wscale = compute_wscale(rcv_win);
+ req->tcb.opt0 = TCAM_BYPASS(1) |
+ (nocong ? NO_CONG(1) : 0) |
+ KEEP_ALIVE(1) |
+ DELACK(1) |
+ WND_SCALE(wscale) |
+ MSS_IDX(mtu_idx) |
+ L2T_IDX(ep->l2t->idx) |
+ TX_CHAN(ep->tx_chan) |
+ SMAC_SEL(ep->smac_idx) |
+ DSCP(ep->tos) |
+ ULP_MODE(ULP_MODE_TCPDDP) |
+ RCV_BUFSIZ(rcv_win >> 10);
+ req->tcb.opt2 = PACE(1) |
+ TX_QUEUE(ep->com.dev->rdev.lldi.tx_modq[ep->tx_chan]) |
+ RX_CHANNEL(0) |
+ CCTRL_ECN(enable_ecn) |
+ RSS_QUEUE_VALID | RSS_QUEUE(ep->rss_qid);
+ if (enable_tcp_timestamps)
+ req->tcb.opt2 |= TSTAMPS_EN(1);
+ if (enable_tcp_sack)
+ req->tcb.opt2 |= SACK_EN(1);
+ if (wscale && enable_tcp_window_scaling)
+ req->tcb.opt2 |= WND_SCALE_EN(1);
+ req->tcb.opt0 = cpu_to_be64(req->tcb.opt0);
+ req->tcb.opt2 = cpu_to_be32(req->tcb.opt2);
+ set_wr_txq(skb, CPL_PRIORITY_CONTROL, 0);
+ c4iw_l2t_send(&ep->com.dev->rdev, skb, ep->l2t);
+}
+
/*
* Return whether a failed active open has allocated a TID
*/
@@ -1419,6 +1528,14 @@ static int act_open_rpl(struct c4iw_dev *dev, struct sk_buff *skb)
case CPL_ERR_CONN_RESET:
case CPL_ERR_CONN_TIMEDOUT:
break;
+ case CPL_ERR_TCAM_FULL:
+ mutex_lock(&dev->rdev.stats.lock);
+ dev->rdev.stats.tcam_full++;
+ mutex_unlock(&dev->rdev.stats.lock);
+ send_fw_act_open_req(ep,
+ GET_TID_TID(GET_AOPEN_ATID(ntohl(rpl->atid_status))));
+ return 0;
+ break;
default:
printk(KERN_INFO MOD "Active open failure - "
"atid %u status %u errno %d %pI4:%u->%pI4:%u\n",
@@ -1510,14 +1627,15 @@ static void accept_cr(struct c4iw_ep *ep, __be32 peer_ip, struct sk_buff *skb,
skb_get(skb);
cxgb4_best_mtu(ep->com.dev->rdev.lldi.mtus, ep->mtu, &mtu_idx);
wscale = compute_wscale(rcv_win);
- opt0 = KEEP_ALIVE(1) |
+ opt0 = (nocong ? NO_CONG(1) : 0) |
+ KEEP_ALIVE(1) |
DELACK(1) |
WND_SCALE(wscale) |
MSS_IDX(mtu_idx) |
L2T_IDX(ep->l2t->idx) |
TX_CHAN(ep->tx_chan) |
SMAC_SEL(ep->smac_idx) |
- DSCP(ep->tos) |
+ DSCP(ep->tos >> 2) |
ULP_MODE(ULP_MODE_TCPDDP) |
RCV_BUFSIZ(rcv_win>>10);
opt2 = RX_CHANNEL(0) |
@@ -1529,6 +1647,15 @@ static void accept_cr(struct c4iw_ep *ep, __be32 peer_ip, struct sk_buff *skb,
opt2 |= SACK_EN(1);
if (wscale && enable_tcp_window_scaling)
opt2 |= WND_SCALE_EN(1);
+ if (enable_ecn) {
+ const struct tcphdr *tcph;
+ u32 hlen = ntohl(req->hdr_len);
+
+ tcph = (const void *)(req + 1) + G_ETH_HDR_LEN(hlen) +
+ G_IP_HDR_LEN(hlen);
+ if (tcph->ece && tcph->cwr)
+ opt2 |= CCTRL_ECN(1);
+ }
rpl = cplhdr(skb);
INIT_TP_WR(rpl, ep->hwtid);
@@ -2647,11 +2774,14 @@ static int fw6_msg(struct c4iw_dev *dev, struct sk_buff *skb)
struct cpl_fw6_msg *rpl = cplhdr(skb);
struct c4iw_wr_wait *wr_waitp;
int ret;
+ u8 opcode;
+ struct cpl_fw6_msg_ofld_connection_wr_rpl *req;
+ struct c4iw_ep *ep;
PDBG("%s type %u\n", __func__, rpl->type);
switch (rpl->type) {
- case 1:
+ case FW6_TYPE_WR_RPL:
ret = (int)((be64_to_cpu(rpl->data[0]) >> 8) & 0xff);
wr_waitp = (struct c4iw_wr_wait *)(__force unsigned long) rpl->data[1];
PDBG("%s wr_waitp %p ret %u\n", __func__, wr_waitp, ret);
@@ -2659,9 +2789,25 @@ static int fw6_msg(struct c4iw_dev *dev, struct sk_buff *skb)
c4iw_wake_up(wr_waitp, ret ? -ret : 0);
kfree_skb(skb);
break;
- case 2:
+ case FW6_TYPE_CQE:
sched(dev, skb);
break;
+ case FW6_TYPE_OFLD_CONNECTION_WR_RPL:
+ opcode = *(const u8 *)rpl->data;
+ if (opcode == FW_OFLD_CONNECTION_WR) {
+ req =
+ (struct cpl_fw6_msg_ofld_connection_wr_rpl *)rpl->data;
+ if (req->t_state == TCP_SYN_SENT
+ && (req->retval == FW_ENOMEM
+ || req->retval == FW_EADDRINUSE)) {
+ ep = (struct c4iw_ep *)
+ lookup_atid(dev->rdev.lldi.tids,
+ req->tid);
+ c4iw_l2t_send(&dev->rdev, skb, ep->l2t);
+ return 0;
+ }
+ }
+ break;
default:
printk(KERN_ERR MOD "%s unexpected fw6 msg type %u\n", __func__,
rpl->type);
diff --git a/drivers/infiniband/hw/cxgb4/iw_cxgb4.h b/drivers/infiniband/hw/cxgb4/iw_cxgb4.h
index 9beb3a9..6a17fde 100644
--- a/drivers/infiniband/hw/cxgb4/iw_cxgb4.h
+++ b/drivers/infiniband/hw/cxgb4/iw_cxgb4.h
@@ -130,6 +130,7 @@ struct c4iw_stats {
u64 db_empty;
u64 db_drop;
u64 db_state_transitions;
+ u64 tcam_full;
};
struct c4iw_rdev {
diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_msg.h b/drivers/net/ethernet/chelsio/cxgb4/t4_msg.h
index 480eb43..5b51c01 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/t4_msg.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/t4_msg.h
@@ -193,6 +193,10 @@ struct work_request_hdr {
__be64 wr_lo;
};
+/* wr_hi fields */
+#define S_WR_OP 24
+#define V_WR_OP(x) ((__u64)(x) << S_WR_OP)
+
#define WR_HDR struct work_request_hdr wr
struct cpl_pass_open_req {
@@ -204,12 +208,14 @@ struct cpl_pass_open_req {
__be32 peer_ip;
__be64 opt0;
#define TX_CHAN(x) ((x) << 2)
+#define NO_CONG(x) ((x) << 4)
#define DELACK(x) ((x) << 5)
#define ULP_MODE(x) ((x) << 8)
#define RCV_BUFSIZ(x) ((x) << 12)
#define DSCP(x) ((x) << 22)
#define SMAC_SEL(x) ((u64)(x) << 28)
#define L2T_IDX(x) ((u64)(x) << 36)
+#define TCAM_BYPASS(x) ((u64)(x) << 48)
#define NAGLE(x) ((u64)(x) << 49)
#define WND_SCALE(x) ((u64)(x) << 50)
#define KEEP_ALIVE(x) ((u64)(x) << 54)
@@ -247,8 +253,10 @@ struct cpl_pass_accept_rpl {
#define RSS_QUEUE_VALID (1 << 10)
#define RX_COALESCE_VALID(x) ((x) << 11)
#define RX_COALESCE(x) ((x) << 12)
+#define PACE(x) ((x) << 16)
#define TX_QUEUE(x) ((x) << 23)
#define RX_CHANNEL(x) ((x) << 26)
+#define CCTRL_ECN(x) ((x) << 27)
#define WND_SCALE_EN(x) ((x) << 28)
#define TSTAMPS_EN(x) ((x) << 29)
#define SACK_EN(x) ((x) << 30)
@@ -635,6 +643,17 @@ struct cpl_fw6_msg {
/* cpl_fw6_msg.type values */
enum {
FW6_TYPE_CMD_RPL = 0,
+ FW6_TYPE_WR_RPL = 1,
+ FW6_TYPE_CQE = 2,
+ FW6_TYPE_OFLD_CONNECTION_WR_RPL = 3,
+};
+
+struct cpl_fw6_msg_ofld_connection_wr_rpl {
+ __u64 cookie;
+ __be32 tid; /* or atid in case of active failure */
+ __u8 t_state;
+ __u8 retval;
+ __u8 rsvd[2];
};
enum {
diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_regs.h b/drivers/net/ethernet/chelsio/cxgb4/t4_regs.h
index 66ab614..bdc1bbc 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/t4_regs.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/t4_regs.h
@@ -1065,4 +1065,6 @@
#define A_TP_TX_SCHED_PCMD 0x25
+#define S_PORT 1
+
#endif /* __T4_REGS_H */
diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4fw_api.h b/drivers/net/ethernet/chelsio/cxgb4/t4fw_api.h
index b4dc560..6e3542f 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/t4fw_api.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/t4fw_api.h
@@ -39,6 +39,11 @@ enum fw_ret_val {
FW_ENOEXEC = 8, /* Exec format error; inv microcode */
};
+enum fw_retval {
+ FW_ENOMEM = 12, /* out of memory */
+ FW_EADDRINUSE = 98, /* address already in use */
+};
+
#define FW_T4VF_SGE_BASE_ADDR 0x0000
#define FW_T4VF_MPS_BASE_ADDR 0x0100
#define FW_T4VF_PL_BASE_ADDR 0x0200
@@ -50,6 +55,7 @@ enum fw_wr_opcodes {
FW_ULPTX_WR = 0x04,
FW_TP_WR = 0x05,
FW_ETH_TX_PKT_WR = 0x08,
+ FW_OFLD_CONNECTION_WR = 0x2f,
FW_FLOWC_WR = 0x0a,
FW_OFLD_TX_DATA_WR = 0x0b,
FW_CMD_WR = 0x10,
@@ -84,6 +90,7 @@ struct fw_wr_hdr {
#define FW_WR_LEN16(x) ((x) << 0)
#define HW_TPL_FR_MT_PR_IV_P_FC 0X32B
+#define HW_TPL_FR_MT_PR_OV_P_FC 0X327
/* filter wr reply code in cookie in CPL_SET_TCB_RPL */
enum fw_filter_wr_cookie {
@@ -378,6 +385,108 @@ struct fw_eth_tx_pkt_wr {
__be64 r3;
};
+struct fw_ofld_connection_wr {
+ __be32 op_compl;
+ __be32 len16_pkd;
+ __u64 cookie;
+ __be64 r2;
+ __be64 r3;
+ struct fw_ofld_connection_le {
+ __be32 version_cpl;
+ __be32 filter;
+ __be32 r1;
+ __be16 lport;
+ __be16 pport;
+ union fw_ofld_connection_leip {
+ struct fw_ofld_connection_le_ipv4 {
+ __be32 pip;
+ __be32 lip;
+ __be64 r0;
+ __be64 r1;
+ __be64 r2;
+ } ipv4;
+ struct fw_ofld_connection_le_ipv6 {
+ __be64 pip_hi;
+ __be64 pip_lo;
+ __be64 lip_hi;
+ __be64 lip_lo;
+ } ipv6;
+ } u;
+ } le;
+ struct fw_ofld_connection_tcb {
+ __be32 t_state_to_astid;
+ __be16 cplrxdataack_cplpassacceptrpl;
+ __be16 rcv_adv;
+ __be32 rcv_nxt;
+ __be32 tx_max;
+ __be64 opt0;
+ __be32 opt2;
+ __be32 r1;
+ __be64 r2;
+ __be64 r3;
+ } tcb;
+};
+
+#define S_FW_OFLD_CONNECTION_WR_VERSION 31
+#define M_FW_OFLD_CONNECTION_WR_VERSION 0x1
+#define V_FW_OFLD_CONNECTION_WR_VERSION(x) \
+ ((x) << S_FW_OFLD_CONNECTION_WR_VERSION)
+#define G_FW_OFLD_CONNECTION_WR_VERSION(x) \
+ (((x) >> S_FW_OFLD_CONNECTION_WR_VERSION) & \
+ M_FW_OFLD_CONNECTION_WR_VERSION)
+#define F_FW_OFLD_CONNECTION_WR_VERSION \
+ V_FW_OFLD_CONNECTION_WR_VERSION(1U)
+
+#define S_FW_OFLD_CONNECTION_WR_CPL 30
+#define M_FW_OFLD_CONNECTION_WR_CPL 0x1
+#define V_FW_OFLD_CONNECTION_WR_CPL(x) ((x) << S_FW_OFLD_CONNECTION_WR_CPL)
+#define G_FW_OFLD_CONNECTION_WR_CPL(x) \
+ (((x) >> S_FW_OFLD_CONNECTION_WR_CPL) & M_FW_OFLD_CONNECTION_WR_CPL)
+#define F_FW_OFLD_CONNECTION_WR_CPL V_FW_OFLD_CONNECTION_WR_CPL(1U)
+
+#define S_FW_OFLD_CONNECTION_WR_T_STATE 28
+#define M_FW_OFLD_CONNECTION_WR_T_STATE 0xf
+#define V_FW_OFLD_CONNECTION_WR_T_STATE(x) \
+ ((x) << S_FW_OFLD_CONNECTION_WR_T_STATE)
+#define G_FW_OFLD_CONNECTION_WR_T_STATE(x) \
+ (((x) >> S_FW_OFLD_CONNECTION_WR_T_STATE) & \
+ M_FW_OFLD_CONNECTION_WR_T_STATE)
+
+#define S_FW_OFLD_CONNECTION_WR_RCV_SCALE 24
+#define M_FW_OFLD_CONNECTION_WR_RCV_SCALE 0xf
+#define V_FW_OFLD_CONNECTION_WR_RCV_SCALE(x) \
+ ((x) << S_FW_OFLD_CONNECTION_WR_RCV_SCALE)
+#define G_FW_OFLD_CONNECTION_WR_RCV_SCALE(x) \
+ (((x) >> S_FW_OFLD_CONNECTION_WR_RCV_SCALE) & \
+ M_FW_OFLD_CONNECTION_WR_RCV_SCALE)
+
+#define S_FW_OFLD_CONNECTION_WR_ASTID 0
+#define M_FW_OFLD_CONNECTION_WR_ASTID 0xffffff
+#define V_FW_OFLD_CONNECTION_WR_ASTID(x) \
+ ((x) << S_FW_OFLD_CONNECTION_WR_ASTID)
+#define G_FW_OFLD_CONNECTION_WR_ASTID(x) \
+ (((x) >> S_FW_OFLD_CONNECTION_WR_ASTID) & M_FW_OFLD_CONNECTION_WR_ASTID)
+
+#define S_FW_OFLD_CONNECTION_WR_CPLRXDATAACK 15
+#define M_FW_OFLD_CONNECTION_WR_CPLRXDATAACK 0x1
+#define V_FW_OFLD_CONNECTION_WR_CPLRXDATAACK(x) \
+ ((x) << S_FW_OFLD_CONNECTION_WR_CPLRXDATAACK)
+#define G_FW_OFLD_CONNECTION_WR_CPLRXDATAACK(x) \
+ (((x) >> S_FW_OFLD_CONNECTION_WR_CPLRXDATAACK) & \
+ M_FW_OFLD_CONNECTION_WR_CPLRXDATAACK)
+#define F_FW_OFLD_CONNECTION_WR_CPLRXDATAACK \
+ V_FW_OFLD_CONNECTION_WR_CPLRXDATAACK(1U)
+
+#define S_FW_OFLD_CONNECTION_WR_CPLPASSACCEPTRPL 14
+#define M_FW_OFLD_CONNECTION_WR_CPLPASSACCEPTRPL 0x1
+#define V_FW_OFLD_CONNECTION_WR_CPLPASSACCEPTRPL(x) \
+ ((x) << S_FW_OFLD_CONNECTION_WR_CPLPASSACCEPTRPL)
+#define G_FW_OFLD_CONNECTION_WR_CPLPASSACCEPTRPL(x) \
+ (((x) >> S_FW_OFLD_CONNECTION_WR_CPLPASSACCEPTRPL) & \
+ M_FW_OFLD_CONNECTION_WR_CPLPASSACCEPTRPL)
+#define F_FW_OFLD_CONNECTION_WR_CPLPASSACCEPTRPL \
+ V_FW_OFLD_CONNECTION_WR_CPLPASSACCEPTRPL(1U)
+
enum fw_flowc_mnem {
FW_FLOWC_MNEM_PFNVFN, /* PFN [15:8] VFN [7:0] */
FW_FLOWC_MNEM_CH,
--
1.7.1
^ permalink raw reply related
* [PATCH V3 4/5] RDMA/cxgb4: Fix LE hash collision bug for passive open connection
From: Vipul Pandya @ 2012-12-03 11:23 UTC (permalink / raw)
To: linux-rdma, netdev
Cc: roland, davem, divy, dm, kumaras, swise, abhishek, Vipul Pandya
In-Reply-To: <1354533781-31575-1-git-send-email-vipul@chelsio.com>
It establishes passive open connection through firmware work request. Passive
open connection will go through this path as now instead of listening server we
create a server filter which will redirect the incoming SYN packet to the
offload queue. After this driver tries to establish the connection using
firmware work request.
Signed-off-by: Vipul Pandya <vipul@chelsio.com>
---
V2: Changed commenting style from kernel-doc format('/**') to normal
V3: Resending the whole patch series again with the missing patches in V2
drivers/infiniband/hw/cxgb4/cm.c | 411 ++++++++++++++++++++---
drivers/infiniband/hw/cxgb4/device.c | 85 +++++-
drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c | 9 +
drivers/net/ethernet/chelsio/cxgb4/t4_msg.h | 46 +++
4 files changed, 496 insertions(+), 55 deletions(-)
diff --git a/drivers/infiniband/hw/cxgb4/cm.c b/drivers/infiniband/hw/cxgb4/cm.c
index 4878704..2ac6a2c 100644
--- a/drivers/infiniband/hw/cxgb4/cm.c
+++ b/drivers/infiniband/hw/cxgb4/cm.c
@@ -38,10 +38,12 @@
#include <linux/inetdevice.h>
#include <linux/ip.h>
#include <linux/tcp.h>
+#include <linux/if_vlan.h>
#include <net/neighbour.h>
#include <net/netevent.h>
#include <net/route.h>
+#include <net/tcp.h>
#include "iw_cxgb4.h"
@@ -1569,13 +1571,14 @@ static int pass_open_rpl(struct c4iw_dev *dev, struct sk_buff *skb)
struct c4iw_listen_ep *ep = lookup_stid(t, stid);
if (!ep) {
- printk(KERN_ERR MOD "stid %d lookup failure!\n", stid);
- return 0;
+ PDBG("%s stid %d lookup failure!\n", __func__, stid);
+ goto out;
}
PDBG("%s ep %p status %d error %d\n", __func__, ep,
rpl->status, status2errno(rpl->status));
c4iw_wake_up(&ep->com.wr_wait, status2errno(rpl->status));
+out:
return 0;
}
@@ -1779,15 +1782,23 @@ static int pass_accept_req(struct c4iw_dev *dev, struct sk_buff *skb)
unsigned int hwtid = GET_TID(req);
struct dst_entry *dst;
struct rtable *rt;
- __be32 local_ip, peer_ip;
+ __be32 local_ip, peer_ip = 0;
__be16 local_port, peer_port;
int err;
+ u16 peer_mss = ntohs(req->tcpopt.mss);
parent_ep = lookup_stid(t, stid);
- PDBG("%s parent ep %p tid %u\n", __func__, parent_ep, hwtid);
-
+ if (!parent_ep) {
+ PDBG("%s connect request on invalid stid %d\n", __func__, stid);
+ goto reject;
+ }
get_4tuple(req, &local_ip, &peer_ip, &local_port, &peer_port);
+ PDBG("%s parent ep %p hwtid %u laddr 0x%x raddr 0x%x lport %d " \
+ "rport %d peer_mss %d\n", __func__, parent_ep, hwtid,
+ ntohl(local_ip), ntohl(peer_ip), ntohs(local_port),
+ ntohs(peer_port), peer_mss);
+
if (state_read(&parent_ep->com) != LISTEN) {
printk(KERN_ERR "%s - listening ep not in LISTEN\n",
__func__);
@@ -1821,6 +1832,9 @@ static int pass_accept_req(struct c4iw_dev *dev, struct sk_buff *skb)
goto reject;
}
+ if (peer_mss && child_ep->mtu > (peer_mss + 40))
+ child_ep->mtu = peer_mss + 40;
+
state_set(&child_ep->com, CONNECTING);
child_ep->com.dev = dev;
child_ep->com.cm_id = NULL;
@@ -1861,6 +1875,9 @@ static int pass_establish(struct c4iw_dev *dev, struct sk_buff *skb)
ep->snd_seq = be32_to_cpu(req->snd_isn);
ep->rcv_seq = be32_to_cpu(req->rcv_isn);
+ PDBG("%s ep %p hwtid %u tcp_opt 0x%02x\n", __func__, ep, tid,
+ ntohs(req->tcp_opt));
+
set_emss(ep, ntohs(req->tcp_opt));
dst_confirm(ep->dst);
@@ -2478,7 +2495,6 @@ int c4iw_create_listen(struct iw_cm_id *cm_id, int backlog)
struct c4iw_dev *dev = to_c4iw_dev(cm_id->device);
struct c4iw_listen_ep *ep;
-
might_sleep();
ep = alloc_ep(sizeof(*ep), GFP_KERNEL);
@@ -2497,30 +2513,49 @@ int c4iw_create_listen(struct iw_cm_id *cm_id, int backlog)
/*
* Allocate a server TID.
*/
- ep->stid = cxgb4_alloc_stid(dev->rdev.lldi.tids, PF_INET, ep);
+ if (dev->rdev.lldi.enable_fw_ofld_conn)
+ ep->stid = cxgb4_alloc_sftid(dev->rdev.lldi.tids, PF_INET, ep);
+ else
+ ep->stid = cxgb4_alloc_stid(dev->rdev.lldi.tids, PF_INET, ep);
+
if (ep->stid == -1) {
printk(KERN_ERR MOD "%s - cannot alloc stid.\n", __func__);
err = -ENOMEM;
goto fail2;
}
-
state_set(&ep->com, LISTEN);
- c4iw_init_wr_wait(&ep->com.wr_wait);
- err = cxgb4_create_server(ep->com.dev->rdev.lldi.ports[0], ep->stid,
- ep->com.local_addr.sin_addr.s_addr,
- ep->com.local_addr.sin_port,
- ep->com.dev->rdev.lldi.rxq_ids[0]);
- if (err)
- goto fail3;
-
- /* wait for pass_open_rpl */
- err = c4iw_wait_for_reply(&ep->com.dev->rdev, &ep->com.wr_wait, 0, 0,
- __func__);
+ if (dev->rdev.lldi.enable_fw_ofld_conn) {
+ do {
+ err = cxgb4_create_server_filter(
+ ep->com.dev->rdev.lldi.ports[0], ep->stid,
+ ep->com.local_addr.sin_addr.s_addr,
+ ep->com.local_addr.sin_port,
+ ep->com.dev->rdev.lldi.rxq_ids[0]);
+ if (err == -EBUSY) {
+ set_current_state(TASK_UNINTERRUPTIBLE);
+ schedule_timeout(usecs_to_jiffies(100));
+ }
+ } while (err == -EBUSY);
+ } else {
+ c4iw_init_wr_wait(&ep->com.wr_wait);
+ err = cxgb4_create_server(ep->com.dev->rdev.lldi.ports[0],
+ ep->stid, ep->com.local_addr.sin_addr.s_addr,
+ ep->com.local_addr.sin_port,
+ ep->com.dev->rdev.lldi.rxq_ids[0]);
+ if (!err)
+ err = c4iw_wait_for_reply(&ep->com.dev->rdev,
+ &ep->com.wr_wait,
+ 0, 0, __func__);
+ }
if (!err) {
cm_id->provider_data = ep;
goto out;
}
-fail3:
+ pr_err("%s cxgb4_create_server/filter failed err %d " \
+ "stid %d laddr %08x lport %d\n", \
+ __func__, err, ep->stid,
+ ntohl(ep->com.local_addr.sin_addr.s_addr),
+ ntohs(ep->com.local_addr.sin_port));
cxgb4_free_stid(ep->com.dev->rdev.lldi.tids, ep->stid, PF_INET);
fail2:
cm_id->rem_ref(cm_id);
@@ -2539,12 +2574,18 @@ int c4iw_destroy_listen(struct iw_cm_id *cm_id)
might_sleep();
state_set(&ep->com, DEAD);
- c4iw_init_wr_wait(&ep->com.wr_wait);
- err = listen_stop(ep);
- if (err)
- goto done;
- err = c4iw_wait_for_reply(&ep->com.dev->rdev, &ep->com.wr_wait, 0, 0,
- __func__);
+ if (ep->com.dev->rdev.lldi.enable_fw_ofld_conn) {
+ err = cxgb4_remove_server_filter(
+ ep->com.dev->rdev.lldi.ports[0], ep->stid,
+ ep->com.dev->rdev.lldi.rxq_ids[0], 0);
+ } else {
+ c4iw_init_wr_wait(&ep->com.wr_wait);
+ err = listen_stop(ep);
+ if (err)
+ goto done;
+ err = c4iw_wait_for_reply(&ep->com.dev->rdev, &ep->com.wr_wait,
+ 0, 0, __func__);
+ }
cxgb4_free_stid(ep->com.dev->rdev.lldi.tids, ep->stid, PF_INET);
done:
cm_id->rem_ref(cm_id);
@@ -2621,10 +2662,298 @@ int c4iw_ep_disconnect(struct c4iw_ep *ep, int abrupt, gfp_t gfp)
return ret;
}
-static int async_event(struct c4iw_dev *dev, struct sk_buff *skb)
+static void active_ofld_conn_reply(struct c4iw_dev *dev, struct sk_buff *skb,
+ struct cpl_fw6_msg_ofld_connection_wr_rpl *req)
+{
+ struct c4iw_ep *ep;
+
+ ep = (struct c4iw_ep *)lookup_atid(dev->rdev.lldi.tids, req->tid);
+ if (!ep)
+ return;
+
+ switch (req->retval) {
+ case FW_ENOMEM:
+ case FW_EADDRINUSE:
+ PDBG("%s ofld conn wr ret %d\n", __func__, req->retval);
+ break;
+ default:
+ pr_info("%s unexpected ofld conn wr retval %d\n",
+ __func__, req->retval);
+ break;
+ }
+ connect_reply_upcall(ep, status2errno(req->retval));
+}
+
+static void passive_ofld_conn_reply(struct c4iw_dev *dev, struct sk_buff *skb,
+ struct cpl_fw6_msg_ofld_connection_wr_rpl *req)
+{
+ struct sk_buff *rpl_skb;
+ struct cpl_pass_accept_req *cpl;
+ int ret;
+
+ rpl_skb = (struct sk_buff *)cpu_to_be64(req->cookie);
+ BUG_ON(!rpl_skb);
+ if (req->retval) {
+ PDBG("%s passive open failure %d\n", __func__, req->retval);
+ kfree_skb(rpl_skb);
+ } else {
+ cpl = (struct cpl_pass_accept_req *)cplhdr(rpl_skb);
+ OPCODE_TID(cpl) = htonl(MK_OPCODE_TID(CPL_PASS_ACCEPT_REQ,
+ htonl(req->tid)));
+ ret = pass_accept_req(dev, rpl_skb);
+ if (!ret)
+ kfree_skb(rpl_skb);
+ }
+ return;
+}
+
+static int deferred_fw6_msg(struct c4iw_dev *dev, struct sk_buff *skb)
{
struct cpl_fw6_msg *rpl = cplhdr(skb);
- c4iw_ev_dispatch(dev, (struct t4_cqe *)&rpl->data[0]);
+ struct cpl_fw6_msg_ofld_connection_wr_rpl *req;
+
+ switch (rpl->type) {
+ case FW6_TYPE_CQE:
+ c4iw_ev_dispatch(dev, (struct t4_cqe *)&rpl->data[0]);
+ break;
+ case FW6_TYPE_OFLD_CONNECTION_WR_RPL:
+ req = (struct cpl_fw6_msg_ofld_connection_wr_rpl *)rpl->data;
+ switch (req->t_state) {
+ case TCP_SYN_SENT:
+ active_ofld_conn_reply(dev, skb, req);
+ break;
+ case TCP_SYN_RECV:
+ passive_ofld_conn_reply(dev, skb, req);
+ break;
+ default:
+ pr_err("%s unexpected ofld conn wr state %d\n",
+ __func__, req->t_state);
+ break;
+ }
+ break;
+ }
+ return 0;
+}
+
+static void build_cpl_pass_accept_req(struct sk_buff *skb, int stid , u8 tos)
+{
+ u32 l2info;
+ u16 vlantag, len, hdr_len;
+ u8 intf;
+ struct cpl_rx_pkt *cpl = cplhdr(skb);
+ struct cpl_pass_accept_req *req;
+ struct tcp_options_received tmp_opt;
+
+ /* Store values from cpl_rx_pkt in temporary location. */
+ vlantag = cpl->vlan;
+ len = cpl->len;
+ l2info = cpl->l2info;
+ hdr_len = cpl->hdr_len;
+ intf = cpl->iff;
+
+ __skb_pull(skb, sizeof(*req) + sizeof(struct rss_header));
+
+ /* We need to parse the TCP options from SYN packet.
+ * to generate cpl_pass_accept_req.
+ */
+ memset(&tmp_opt, 0, sizeof(tmp_opt));
+ tcp_clear_options(&tmp_opt);
+ tcp_parse_options(skb, &tmp_opt, 0, 0, NULL);
+
+ req = (struct cpl_pass_accept_req *)__skb_push(skb, sizeof(*req));
+ memset(req, 0, sizeof(*req));
+ req->l2info = cpu_to_be16(V_SYN_INTF(intf) |
+ V_SYN_MAC_IDX(G_RX_MACIDX(htonl(l2info))) |
+ F_SYN_XACT_MATCH);
+ req->hdr_len = cpu_to_be32(V_SYN_RX_CHAN(G_RX_CHAN(htonl(l2info))) |
+ V_TCP_HDR_LEN(G_RX_TCPHDR_LEN(htons(hdr_len))) |
+ V_IP_HDR_LEN(G_RX_IPHDR_LEN(htons(hdr_len))) |
+ V_ETH_HDR_LEN(G_RX_ETHHDR_LEN(htonl(l2info))));
+ req->vlan = vlantag;
+ req->len = len;
+ req->tos_stid = cpu_to_be32(PASS_OPEN_TID(stid) |
+ PASS_OPEN_TOS(tos));
+ req->tcpopt.mss = htons(tmp_opt.mss_clamp);
+ if (tmp_opt.wscale_ok)
+ req->tcpopt.wsf = tmp_opt.snd_wscale;
+ req->tcpopt.tstamp = tmp_opt.saw_tstamp;
+ if (tmp_opt.sack_ok)
+ req->tcpopt.sack = 1;
+ OPCODE_TID(req) = htonl(MK_OPCODE_TID(CPL_PASS_ACCEPT_REQ, 0));
+ return;
+}
+
+static void send_fw_pass_open_req(struct c4iw_dev *dev, struct sk_buff *skb,
+ __be32 laddr, __be16 lport,
+ __be32 raddr, __be16 rport,
+ u32 rcv_isn, u32 filter, u16 window,
+ u32 rss_qid, u8 port_id)
+{
+ struct sk_buff *req_skb;
+ struct fw_ofld_connection_wr *req;
+ struct cpl_pass_accept_req *cpl = cplhdr(skb);
+
+ req_skb = alloc_skb(sizeof(struct fw_ofld_connection_wr), GFP_KERNEL);
+ req = (struct fw_ofld_connection_wr *)__skb_put(req_skb, sizeof(*req));
+ memset(req, 0, sizeof(*req));
+ req->op_compl = htonl(V_WR_OP(FW_OFLD_CONNECTION_WR) | FW_WR_COMPL(1));
+ req->len16_pkd = htonl(FW_WR_LEN16(DIV_ROUND_UP(sizeof(*req), 16)));
+ req->le.version_cpl = htonl(F_FW_OFLD_CONNECTION_WR_CPL);
+ req->le.filter = filter;
+ req->le.lport = lport;
+ req->le.pport = rport;
+ req->le.u.ipv4.lip = laddr;
+ req->le.u.ipv4.pip = raddr;
+ req->tcb.rcv_nxt = htonl(rcv_isn + 1);
+ req->tcb.rcv_adv = htons(window);
+ req->tcb.t_state_to_astid =
+ htonl(V_FW_OFLD_CONNECTION_WR_T_STATE(TCP_SYN_RECV) |
+ V_FW_OFLD_CONNECTION_WR_RCV_SCALE(cpl->tcpopt.wsf) |
+ V_FW_OFLD_CONNECTION_WR_ASTID(
+ GET_PASS_OPEN_TID(ntohl(cpl->tos_stid))));
+
+ /*
+ * We store the qid in opt2 which will be used by the firmware
+ * to send us the wr response.
+ */
+ req->tcb.opt2 = htonl(V_RSS_QUEUE(rss_qid));
+
+ /*
+ * We initialize the MSS index in TCB to 0xF.
+ * So that when driver sends cpl_pass_accept_rpl
+ * TCB picks up the correct value. If this was 0
+ * TP will ignore any value > 0 for MSS index.
+ */
+ req->tcb.opt0 = cpu_to_be64(V_MSS_IDX(0xF));
+ req->cookie = cpu_to_be64((u64)skb);
+
+ set_wr_txq(req_skb, CPL_PRIORITY_CONTROL, port_id);
+ cxgb4_ofld_send(dev->rdev.lldi.ports[0], req_skb);
+}
+
+/*
+ * Handler for CPL_RX_PKT message. Need to handle cpl_rx_pkt
+ * messages when a filter is being used instead of server to
+ * redirect a syn packet. When packets hit filter they are redirected
+ * to the offload queue and driver tries to establish the connection
+ * using firmware work request.
+ */
+static int rx_pkt(struct c4iw_dev *dev, struct sk_buff *skb)
+{
+ int stid;
+ unsigned int filter;
+ struct ethhdr *eh = NULL;
+ struct vlan_ethhdr *vlan_eh = NULL;
+ struct iphdr *iph;
+ struct tcphdr *tcph;
+ struct rss_header *rss = (void *)skb->data;
+ struct cpl_rx_pkt *cpl = (void *)skb->data;
+ struct cpl_pass_accept_req *req = (void *)(rss + 1);
+ struct l2t_entry *e;
+ struct dst_entry *dst;
+ struct rtable *rt;
+ struct c4iw_ep *lep;
+ u16 window;
+ struct port_info *pi;
+ struct net_device *pdev;
+ u16 rss_qid;
+ int step;
+ u32 tx_chan;
+ struct neighbour *neigh;
+
+ /* Drop all non-SYN packets */
+ if (!(cpl->l2info & cpu_to_be32(F_RXF_SYN)))
+ goto reject;
+
+ /*
+ * Drop all packets which did not hit the filter.
+ * Unlikely to happen.
+ */
+ if (!(rss->filter_hit && rss->filter_tid))
+ goto reject;
+
+ /*
+ * Calculate the server tid from filter hit index from cpl_rx_pkt.
+ */
+ stid = cpu_to_be32(rss->hash_val) - dev->rdev.lldi.tids->sftid_base
+ + dev->rdev.lldi.tids->nstids;
+
+ lep = (struct c4iw_ep *)lookup_stid(dev->rdev.lldi.tids, stid);
+ if (!lep) {
+ PDBG("%s connect request on invalid stid %d\n", __func__, stid);
+ goto reject;
+ }
+
+ if (G_RX_ETHHDR_LEN(ntohl(cpl->l2info)) == ETH_HLEN) {
+ eh = (struct ethhdr *)(req + 1);
+ iph = (struct iphdr *)(eh + 1);
+ } else {
+ vlan_eh = (struct vlan_ethhdr *)(req + 1);
+ iph = (struct iphdr *)(vlan_eh + 1);
+ skb->vlan_tci = ntohs(cpl->vlan);
+ }
+
+ if (iph->version != 0x4)
+ goto reject;
+
+ tcph = (struct tcphdr *)(iph + 1);
+ skb_set_network_header(skb, (void *)iph - (void *)rss);
+ skb_set_transport_header(skb, (void *)tcph - (void *)rss);
+ skb_get(skb);
+
+ PDBG("%s lip 0x%x lport %u pip 0x%x pport %u tos %d\n", __func__,
+ ntohl(iph->daddr), ntohs(tcph->dest), ntohl(iph->saddr),
+ ntohs(tcph->source), iph->tos);
+
+ rt = find_route(dev, iph->daddr, iph->saddr, tcph->dest, tcph->source,
+ iph->tos);
+ if (!rt) {
+ pr_err("%s - failed to find dst entry!\n",
+ __func__);
+ goto reject;
+ }
+ dst = &rt->dst;
+ neigh = dst_neigh_lookup_skb(dst, skb);
+
+ if (neigh->dev->flags & IFF_LOOPBACK) {
+ pdev = ip_dev_find(&init_net, iph->daddr);
+ e = cxgb4_l2t_get(dev->rdev.lldi.l2t, neigh,
+ pdev, 0);
+ pi = (struct port_info *)netdev_priv(pdev);
+ tx_chan = cxgb4_port_chan(pdev);
+ dev_put(pdev);
+ } else {
+ e = cxgb4_l2t_get(dev->rdev.lldi.l2t, neigh,
+ neigh->dev, 0);
+ pi = (struct port_info *)netdev_priv(neigh->dev);
+ tx_chan = cxgb4_port_chan(neigh->dev);
+ }
+ if (!e) {
+ pr_err("%s - failed to allocate l2t entry!\n",
+ __func__);
+ goto free_dst;
+ }
+
+ step = dev->rdev.lldi.nrxq / dev->rdev.lldi.nchan;
+ rss_qid = dev->rdev.lldi.rxq_ids[pi->port_id * step];
+ window = htons(tcph->window);
+
+ /* Calcuate filter portion for LE region. */
+ filter = cpu_to_be32(select_ntuple(dev, dst, e));
+
+ /*
+ * Synthesize the cpl_pass_accept_req. We have everything except the
+ * TID. Once firmware sends a reply with TID we update the TID field
+ * in cpl and pass it through the regular cpl_pass_accept_req path.
+ */
+ build_cpl_pass_accept_req(skb, stid, iph->tos);
+ send_fw_pass_open_req(dev, skb, iph->daddr, tcph->dest, iph->saddr,
+ tcph->source, ntohl(tcph->seq), filter, window,
+ rss_qid, pi->port_id);
+ cxgb4_l2t_release(e);
+free_dst:
+ dst_release(dst);
+reject:
return 0;
}
@@ -2647,7 +2976,8 @@ static c4iw_handler_func work_handlers[NUM_CPL_CMDS] = {
[CPL_CLOSE_CON_RPL] = close_con_rpl,
[CPL_RDMA_TERMINATE] = terminate,
[CPL_FW4_ACK] = fw4_ack,
- [CPL_FW6_MSG] = async_event
+ [CPL_FW6_MSG] = deferred_fw6_msg,
+ [CPL_RX_PKT] = rx_pkt
};
static void process_timeout(struct c4iw_ep *ep)
@@ -2774,9 +3104,6 @@ static int fw6_msg(struct c4iw_dev *dev, struct sk_buff *skb)
struct cpl_fw6_msg *rpl = cplhdr(skb);
struct c4iw_wr_wait *wr_waitp;
int ret;
- u8 opcode;
- struct cpl_fw6_msg_ofld_connection_wr_rpl *req;
- struct c4iw_ep *ep;
PDBG("%s type %u\n", __func__, rpl->type);
@@ -2790,23 +3117,8 @@ static int fw6_msg(struct c4iw_dev *dev, struct sk_buff *skb)
kfree_skb(skb);
break;
case FW6_TYPE_CQE:
- sched(dev, skb);
- break;
case FW6_TYPE_OFLD_CONNECTION_WR_RPL:
- opcode = *(const u8 *)rpl->data;
- if (opcode == FW_OFLD_CONNECTION_WR) {
- req =
- (struct cpl_fw6_msg_ofld_connection_wr_rpl *)rpl->data;
- if (req->t_state == TCP_SYN_SENT
- && (req->retval == FW_ENOMEM
- || req->retval == FW_EADDRINUSE)) {
- ep = (struct c4iw_ep *)
- lookup_atid(dev->rdev.lldi.tids,
- req->tid);
- c4iw_l2t_send(&dev->rdev, skb, ep->l2t);
- return 0;
- }
- }
+ sched(dev, skb);
break;
default:
printk(KERN_ERR MOD "%s unexpected fw6 msg type %u\n", __func__,
@@ -2868,7 +3180,8 @@ c4iw_handler_func c4iw_handlers[NUM_CPL_CMDS] = {
[CPL_RDMA_TERMINATE] = sched,
[CPL_FW4_ACK] = sched,
[CPL_SET_TCB_RPL] = set_tcb_rpl,
- [CPL_FW6_MSG] = fw6_msg
+ [CPL_FW6_MSG] = fw6_msg,
+ [CPL_RX_PKT] = sched
};
int __init c4iw_cm_init(void)
diff --git a/drivers/infiniband/hw/cxgb4/device.c b/drivers/infiniband/hw/cxgb4/device.c
index cb4ecd7..6b5b3d1 100644
--- a/drivers/infiniband/hw/cxgb4/device.c
+++ b/drivers/infiniband/hw/cxgb4/device.c
@@ -279,6 +279,7 @@ static int stats_show(struct seq_file *seq, void *v)
seq_printf(seq, " DB State: %s Transitions %llu\n",
db_state_str[dev->db_state],
dev->rdev.stats.db_state_transitions);
+ seq_printf(seq, "TCAM_FULL: %10llu\n", dev->rdev.stats.tcam_full);
return 0;
}
@@ -577,14 +578,76 @@ out:
return ctx;
}
+static inline struct sk_buff *copy_gl_to_skb_pkt(const struct pkt_gl *gl,
+ const __be64 *rsp,
+ u32 pktshift)
+{
+ struct sk_buff *skb;
+
+ /*
+ * Allocate space for cpl_pass_accept_req which will be synthesized by
+ * driver. Once the driver synthesizes the request the skb will go
+ * through the regular cpl_pass_accept_req processing.
+ * The math here assumes sizeof cpl_pass_accept_req >= sizeof
+ * cpl_rx_pkt.
+ */
+ skb = alloc_skb(gl->tot_len + sizeof(struct cpl_pass_accept_req) +
+ sizeof(struct rss_header) - pktshift, GFP_ATOMIC);
+ if (unlikely(!skb))
+ return NULL;
+
+ __skb_put(skb, gl->tot_len + sizeof(struct cpl_pass_accept_req) +
+ sizeof(struct rss_header) - pktshift);
+
+ /*
+ * This skb will contain:
+ * rss_header from the rspq descriptor (1 flit)
+ * cpl_rx_pkt struct from the rspq descriptor (2 flits)
+ * space for the difference between the size of an
+ * rx_pkt and pass_accept_req cpl (1 flit)
+ * the packet data from the gl
+ */
+ skb_copy_to_linear_data(skb, rsp, sizeof(struct cpl_pass_accept_req) +
+ sizeof(struct rss_header));
+ skb_copy_to_linear_data_offset(skb, sizeof(struct rss_header) +
+ sizeof(struct cpl_pass_accept_req),
+ gl->va + pktshift,
+ gl->tot_len - pktshift);
+ return skb;
+}
+
+static inline int recv_rx_pkt(struct c4iw_dev *dev, const struct pkt_gl *gl,
+ const __be64 *rsp)
+{
+ unsigned int opcode = *(u8 *)rsp;
+ struct sk_buff *skb;
+
+ if (opcode != CPL_RX_PKT)
+ goto out;
+
+ skb = copy_gl_to_skb_pkt(gl , rsp, dev->rdev.lldi.sge_pktshift);
+ if (skb == NULL)
+ goto out;
+
+ if (c4iw_handlers[opcode] == NULL) {
+ pr_info("%s no handler opcode 0x%x...\n", __func__,
+ opcode);
+ kfree_skb(skb);
+ goto out;
+ }
+ c4iw_handlers[opcode](dev, skb);
+ return 1;
+out:
+ return 0;
+}
+
static int c4iw_uld_rx_handler(void *handle, const __be64 *rsp,
const struct pkt_gl *gl)
{
struct uld_ctx *ctx = handle;
struct c4iw_dev *dev = ctx->dev;
struct sk_buff *skb;
- const struct cpl_act_establish *rpl;
- unsigned int opcode;
+ u8 opcode;
if (gl == NULL) {
/* omit RSS and rsp_ctrl at end of descriptor */
@@ -601,19 +664,29 @@ static int c4iw_uld_rx_handler(void *handle, const __be64 *rsp,
u32 qid = be32_to_cpu(rc->pldbuflen_qid);
c4iw_ev_handler(dev, qid);
return 0;
+ } else if (unlikely(*(u8 *)rsp != *(u8 *)gl->va)) {
+ if (recv_rx_pkt(dev, gl, rsp))
+ return 0;
+
+ pr_info("%s: unexpected FL contents at %p, " \
+ "RSS %#llx, FL %#llx, len %u\n",
+ pci_name(ctx->lldi.pdev), gl->va,
+ (unsigned long long)be64_to_cpu(*rsp),
+ (unsigned long long)be64_to_cpu(*(u64 *)gl->va),
+ gl->tot_len);
+
+ return 0;
} else {
skb = cxgb4_pktgl_to_skb(gl, 128, 128);
if (unlikely(!skb))
goto nomem;
}
- rpl = cplhdr(skb);
- opcode = rpl->ot.opcode;
-
+ opcode = *(u8 *)rsp;
if (c4iw_handlers[opcode])
c4iw_handlers[opcode](dev, skb);
else
- printk(KERN_INFO "%s no handler opcode 0x%x...\n", __func__,
+ pr_info("%s no handler opcode 0x%x...\n", __func__,
opcode);
return 0;
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
index f55386b..1a26e3f 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
@@ -3326,6 +3326,10 @@ int cxgb4_create_server_filter(const struct net_device *dev, unsigned int stid,
adap = netdev2adap(dev);
+ /* Adjust stid to correct filter index */
+ stid -= adap->tids.nstids;
+ stid += adap->tids.nftids;
+
/* Check to make sure the filter requested is writable ...
*/
f = &adap->tids.ftid_tab[stid];
@@ -3374,6 +3378,11 @@ int cxgb4_remove_server_filter(const struct net_device *dev, unsigned int stid,
struct adapter *adap;
adap = netdev2adap(dev);
+
+ /* Adjust stid to correct filter index */
+ stid -= adap->tids.nstids;
+ stid += adap->tids.nftids;
+
f = &adap->tids.ftid_tab[stid];
/* Unlock the filter */
f->locked = 0;
diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_msg.h b/drivers/net/ethernet/chelsio/cxgb4/t4_msg.h
index 5b51c01..1179616 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/t4_msg.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/t4_msg.h
@@ -199,6 +199,18 @@ struct work_request_hdr {
#define WR_HDR struct work_request_hdr wr
+/* option 0 fields */
+#define S_MSS_IDX 60
+#define M_MSS_IDX 0xF
+#define V_MSS_IDX(x) ((__u64)(x) << S_MSS_IDX)
+#define G_MSS_IDX(x) (((x) >> S_MSS_IDX) & M_MSS_IDX)
+
+/* option 2 fields */
+#define S_RSS_QUEUE 0
+#define M_RSS_QUEUE 0x3FF
+#define V_RSS_QUEUE(x) ((x) << S_RSS_QUEUE)
+#define G_RSS_QUEUE(x) (((x) >> S_RSS_QUEUE) & M_RSS_QUEUE)
+
struct cpl_pass_open_req {
WR_HDR;
union opcode_tid ot;
@@ -300,6 +312,9 @@ struct cpl_pass_establish {
union opcode_tid ot;
__be32 rsvd;
__be32 tos_stid;
+#define PASS_OPEN_TID(x) ((x) << 0)
+#define PASS_OPEN_TOS(x) ((x) << 24)
+#define GET_PASS_OPEN_TID(x) (((x) >> 0) & 0xFFFFFF)
#define GET_POPEN_TID(x) ((x) & 0xffffff)
#define GET_POPEN_TOS(x) (((x) >> 24) & 0xff)
__be16 mac_idx;
@@ -545,6 +560,37 @@ struct cpl_rx_pkt {
__be16 err_vec;
};
+/* rx_pkt.l2info fields */
+#define S_RX_ETHHDR_LEN 0
+#define M_RX_ETHHDR_LEN 0x1F
+#define V_RX_ETHHDR_LEN(x) ((x) << S_RX_ETHHDR_LEN)
+#define G_RX_ETHHDR_LEN(x) (((x) >> S_RX_ETHHDR_LEN) & M_RX_ETHHDR_LEN)
+
+#define S_RX_MACIDX 8
+#define M_RX_MACIDX 0x1FF
+#define V_RX_MACIDX(x) ((x) << S_RX_MACIDX)
+#define G_RX_MACIDX(x) (((x) >> S_RX_MACIDX) & M_RX_MACIDX)
+
+#define S_RXF_SYN 21
+#define V_RXF_SYN(x) ((x) << S_RXF_SYN)
+#define F_RXF_SYN V_RXF_SYN(1U)
+
+#define S_RX_CHAN 28
+#define M_RX_CHAN 0xF
+#define V_RX_CHAN(x) ((x) << S_RX_CHAN)
+#define G_RX_CHAN(x) (((x) >> S_RX_CHAN) & M_RX_CHAN)
+
+/* rx_pkt.hdr_len fields */
+#define S_RX_TCPHDR_LEN 0
+#define M_RX_TCPHDR_LEN 0x3F
+#define V_RX_TCPHDR_LEN(x) ((x) << S_RX_TCPHDR_LEN)
+#define G_RX_TCPHDR_LEN(x) (((x) >> S_RX_TCPHDR_LEN) & M_RX_TCPHDR_LEN)
+
+#define S_RX_IPHDR_LEN 6
+#define M_RX_IPHDR_LEN 0x3FF
+#define V_RX_IPHDR_LEN(x) ((x) << S_RX_IPHDR_LEN)
+#define G_RX_IPHDR_LEN(x) (((x) >> S_RX_IPHDR_LEN) & M_RX_IPHDR_LEN)
+
struct cpl_trace_pkt {
u8 opcode;
u8 intf;
--
1.7.1
^ permalink raw reply related
* [PATCH V3 5/5] RDMA/cxgb4: Fix bug for active and passive LE hash collision path
From: Vipul Pandya @ 2012-12-03 11:23 UTC (permalink / raw)
To: linux-rdma, netdev
Cc: roland, davem, divy, dm, kumaras, swise, abhishek, Vipul Pandya
In-Reply-To: <1354533781-31575-1-git-send-email-vipul@chelsio.com>
Retries active opens for INUSE errors.
Logs any active ofld_connect_wr error replies.
Sends ofld_connect_wr on same ctrlq. It needs to go on the same control txq as
regular CPL active/passive messages.
Retries on active open replies with EADDRINUSE.
Uses active open fw wr only if active filter region is set.
Adds stat for ofld_connect_wr failures.
This patch also adds debugfs file to show endpoints.
Signed-off-by: Vipul Pandya <vipul@chelsio.com>
---
V2: Changed commenting style from kernel-doc format('/**') to normal
V3: Resending the whole patch series again with the missing patches in V2
drivers/infiniband/hw/cxgb4/cm.c | 277 ++++++++++++++++-------
drivers/infiniband/hw/cxgb4/device.c | 125 ++++++++++
drivers/infiniband/hw/cxgb4/iw_cxgb4.h | 32 +++
drivers/net/ethernet/chelsio/cxgb4/cxgb4.h | 1 +
drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c | 19 ++-
drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.h | 8 +-
drivers/net/ethernet/chelsio/cxgb4/t4_regs.h | 2 +
7 files changed, 376 insertions(+), 88 deletions(-)
diff --git a/drivers/infiniband/hw/cxgb4/cm.c b/drivers/infiniband/hw/cxgb4/cm.c
index 2ac6a2c..b2ea840 100644
--- a/drivers/infiniband/hw/cxgb4/cm.c
+++ b/drivers/infiniband/hw/cxgb4/cm.c
@@ -275,6 +275,7 @@ void _c4iw_free_ep(struct kref *kref)
cxgb4_remove_tid(ep->com.dev->rdev.lldi.tids, 0, ep->hwtid);
dst_release(ep->dst);
cxgb4_l2t_release(ep->l2t);
+ remove_handle(ep->com.dev, &ep->com.dev->hwtid_idr, ep->hwtid);
}
kfree(ep);
}
@@ -550,6 +551,7 @@ static int send_connect(struct c4iw_ep *ep)
req->opt0 = cpu_to_be64(opt0);
req->params = cpu_to_be32(select_ntuple(ep->com.dev, ep->dst, ep->l2t));
req->opt2 = cpu_to_be32(opt2);
+ set_bit(ACT_OPEN_REQ, &ep->com.history);
return c4iw_l2t_send(&ep->com.dev->rdev, skb, ep->l2t);
}
@@ -826,6 +828,7 @@ static int act_establish(struct c4iw_dev *dev, struct sk_buff *skb)
/* setup the hwtid for this connection */
ep->hwtid = tid;
cxgb4_insert_tid(t, ep, tid);
+ insert_handle(dev, &dev->hwtid_idr, ep, ep->hwtid);
ep->snd_seq = be32_to_cpu(req->snd_isn);
ep->rcv_seq = be32_to_cpu(req->rcv_isn);
@@ -833,7 +836,9 @@ static int act_establish(struct c4iw_dev *dev, struct sk_buff *skb)
set_emss(ep, ntohs(req->tcp_opt));
/* dealloc the atid */
+ remove_handle(ep->com.dev, &ep->com.dev->atid_idr, atid);
cxgb4_free_atid(t, atid);
+ set_bit(ACT_ESTAB, &ep->com.history);
/* start MPA negotiation */
send_flowc(ep, NULL);
@@ -859,6 +864,7 @@ static void close_complete_upcall(struct c4iw_ep *ep)
ep->com.cm_id->rem_ref(ep->com.cm_id);
ep->com.cm_id = NULL;
ep->com.qp = NULL;
+ set_bit(CLOSE_UPCALL, &ep->com.history);
}
}
@@ -867,6 +873,7 @@ static int abort_connection(struct c4iw_ep *ep, struct sk_buff *skb, gfp_t gfp)
PDBG("%s ep %p tid %u\n", __func__, ep, ep->hwtid);
close_complete_upcall(ep);
state_set(&ep->com, ABORTING);
+ set_bit(ABORT_CONN, &ep->com.history);
return send_abort(ep, skb, gfp);
}
@@ -881,6 +888,7 @@ static void peer_close_upcall(struct c4iw_ep *ep)
PDBG("peer close delivered ep %p cm_id %p tid %u\n",
ep, ep->com.cm_id, ep->hwtid);
ep->com.cm_id->event_handler(ep->com.cm_id, &event);
+ set_bit(DISCONN_UPCALL, &ep->com.history);
}
}
@@ -899,6 +907,7 @@ static void peer_abort_upcall(struct c4iw_ep *ep)
ep->com.cm_id->rem_ref(ep->com.cm_id);
ep->com.cm_id = NULL;
ep->com.qp = NULL;
+ set_bit(ABORT_UPCALL, &ep->com.history);
}
}
@@ -931,6 +940,7 @@ static void connect_reply_upcall(struct c4iw_ep *ep, int status)
PDBG("%s ep %p tid %u status %d\n", __func__, ep,
ep->hwtid, status);
+ set_bit(CONN_RPL_UPCALL, &ep->com.history);
ep->com.cm_id->event_handler(ep->com.cm_id, &event);
if (status < 0) {
@@ -971,6 +981,7 @@ static void connect_request_upcall(struct c4iw_ep *ep)
ep->parent_ep->com.cm_id,
&event);
}
+ set_bit(CONNREQ_UPCALL, &ep->com.history);
c4iw_put_ep(&ep->parent_ep->com);
ep->parent_ep = NULL;
}
@@ -987,6 +998,7 @@ static void established_upcall(struct c4iw_ep *ep)
if (ep->com.cm_id) {
PDBG("%s ep %p tid %u\n", __func__, ep, ep->hwtid);
ep->com.cm_id->event_handler(ep->com.cm_id, &event);
+ set_bit(ESTAB_UPCALL, &ep->com.history);
}
}
@@ -1372,6 +1384,7 @@ static int rx_data(struct c4iw_dev *dev, struct sk_buff *skb)
unsigned int dlen = ntohs(hdr->len);
unsigned int tid = GET_TID(hdr);
struct tid_info *t = dev->rdev.lldi.tids;
+ __u8 status = hdr->status;
ep = lookup_tid(t, tid);
PDBG("%s ep %p tid %u dlen %u\n", __func__, ep, ep->hwtid, dlen);
@@ -1394,9 +1407,9 @@ static int rx_data(struct c4iw_dev *dev, struct sk_buff *skb)
case MPA_REP_SENT:
break;
default:
- printk(KERN_ERR MOD "%s Unexpected streaming data."
- " ep %p state %d tid %u\n",
- __func__, ep, state_read(&ep->com), ep->hwtid);
+ pr_err("%s Unexpected streaming data." \
+ " ep %p state %d tid %u status %d\n",
+ __func__, ep, state_read(&ep->com), ep->hwtid, status);
/*
* The ep will timeout and inform the ULP of the failure.
@@ -1463,6 +1476,7 @@ static void send_fw_act_open_req(struct c4iw_ep *ep, unsigned int atid)
req->tcb.cplrxdataack_cplpassacceptrpl =
htons(F_FW_OFLD_CONNECTION_WR_CPLRXDATAACK);
req->tcb.tx_max = jiffies;
+ req->tcb.rcv_adv = htons(1);
cxgb4_best_mtu(ep->com.dev->rdev.lldi.mtus, ep->mtu, &mtu_idx);
wscale = compute_wscale(rcv_win);
req->tcb.opt0 = TCAM_BYPASS(1) |
@@ -1490,7 +1504,8 @@ static void send_fw_act_open_req(struct c4iw_ep *ep, unsigned int atid)
req->tcb.opt2 |= WND_SCALE_EN(1);
req->tcb.opt0 = cpu_to_be64(req->tcb.opt0);
req->tcb.opt2 = cpu_to_be32(req->tcb.opt2);
- set_wr_txq(skb, CPL_PRIORITY_CONTROL, 0);
+ set_wr_txq(skb, CPL_PRIORITY_CONTROL, ep->ctrlq_idx);
+ set_bit(ACT_OFLD_CONN, &ep->com.history);
c4iw_l2t_send(&ep->com.dev->rdev, skb, ep->l2t);
}
@@ -1503,6 +1518,111 @@ static inline int act_open_has_tid(int status)
status != CPL_ERR_ARP_MISS;
}
+#define ACT_OPEN_RETRY_COUNT 2
+
+static int c4iw_reconnect(struct c4iw_ep *ep)
+{
+ int err = 0;
+ struct rtable *rt;
+ struct port_info *pi;
+ struct net_device *pdev;
+ int step;
+ struct neighbour *neigh;
+
+ PDBG("%s qp %p cm_id %p\n", __func__, ep->com.qp, ep->com.cm_id);
+ init_timer(&ep->timer);
+
+ /*
+ * Allocate an active TID to initiate a TCP connection.
+ */
+ ep->atid = cxgb4_alloc_atid(ep->com.dev->rdev.lldi.tids, ep);
+ if (ep->atid == -1) {
+ pr_err("%s - cannot alloc atid.\n", __func__);
+ err = -ENOMEM;
+ goto fail2;
+ }
+ insert_handle(ep->com.dev, &ep->com.dev->atid_idr, ep, ep->atid);
+
+ /* find a route */
+ rt = find_route(ep->com.dev,
+ ep->com.cm_id->local_addr.sin_addr.s_addr,
+ ep->com.cm_id->remote_addr.sin_addr.s_addr,
+ ep->com.cm_id->local_addr.sin_port,
+ ep->com.cm_id->remote_addr.sin_port, 0);
+ if (!rt) {
+ pr_err("%s - cannot find route.\n", __func__);
+ err = -EHOSTUNREACH;
+ goto fail3;
+ }
+ ep->dst = &rt->dst;
+
+ neigh = dst_neigh_lookup(ep->dst,
+ &ep->com.cm_id->remote_addr.sin_addr.s_addr);
+ /* get a l2t entry */
+ if (neigh->dev->flags & IFF_LOOPBACK) {
+ PDBG("%s LOOPBACK\n", __func__);
+ pdev = ip_dev_find(&init_net,
+ ep->com.cm_id->remote_addr.sin_addr.s_addr);
+ ep->l2t = cxgb4_l2t_get(ep->com.dev->rdev.lldi.l2t,
+ neigh, pdev, 0);
+ pi = (struct port_info *)netdev_priv(pdev);
+ ep->mtu = pdev->mtu;
+ ep->tx_chan = cxgb4_port_chan(pdev);
+ ep->smac_idx = (cxgb4_port_viid(pdev) & 0x7F) << 1;
+ dev_put(pdev);
+ } else {
+ ep->l2t = cxgb4_l2t_get(ep->com.dev->rdev.lldi.l2t,
+ neigh, neigh->dev, 0);
+ pi = (struct port_info *)netdev_priv(neigh->dev);
+ ep->mtu = dst_mtu(ep->dst);
+ ep->tx_chan = cxgb4_port_chan(neigh->dev);
+ ep->smac_idx = (cxgb4_port_viid(neigh->dev) &
+ 0x7F) << 1;
+ }
+
+ step = ep->com.dev->rdev.lldi.ntxq / ep->com.dev->rdev.lldi.nchan;
+ ep->txq_idx = pi->port_id * step;
+ ep->ctrlq_idx = pi->port_id;
+ step = ep->com.dev->rdev.lldi.nrxq / ep->com.dev->rdev.lldi.nchan;
+ ep->rss_qid = ep->com.dev->rdev.lldi.rxq_ids[pi->port_id * step];
+
+ if (!ep->l2t) {
+ pr_err("%s - cannot alloc l2e.\n", __func__);
+ err = -ENOMEM;
+ goto fail4;
+ }
+
+ PDBG("%s txq_idx %u tx_chan %u smac_idx %u rss_qid %u l2t_idx %u\n",
+ __func__, ep->txq_idx, ep->tx_chan, ep->smac_idx, ep->rss_qid,
+ ep->l2t->idx);
+
+ state_set(&ep->com, CONNECTING);
+ ep->tos = 0;
+
+ /* send connect request to rnic */
+ err = send_connect(ep);
+ if (!err)
+ goto out;
+
+ cxgb4_l2t_release(ep->l2t);
+fail4:
+ dst_release(ep->dst);
+fail3:
+ remove_handle(ep->com.dev, &ep->com.dev->atid_idr, ep->atid);
+ cxgb4_free_atid(ep->com.dev->rdev.lldi.tids, ep->atid);
+fail2:
+ /*
+ * remember to send notification to upper layer.
+ * We are in here so the upper layer is not aware that this is
+ * re-connect attempt and so, upper layer is still waiting for
+ * response of 1st connect request.
+ */
+ connect_reply_upcall(ep, -ECONNRESET);
+ c4iw_put_ep(&ep->com);
+out:
+ return err;
+}
+
static int act_open_rpl(struct c4iw_dev *dev, struct sk_buff *skb)
{
struct c4iw_ep *ep;
@@ -1523,6 +1643,8 @@ static int act_open_rpl(struct c4iw_dev *dev, struct sk_buff *skb)
return 0;
}
+ set_bit(ACT_OPEN_RPL, &ep->com.history);
+
/*
* Log interesting failures.
*/
@@ -1531,12 +1653,27 @@ static int act_open_rpl(struct c4iw_dev *dev, struct sk_buff *skb)
case CPL_ERR_CONN_TIMEDOUT:
break;
case CPL_ERR_TCAM_FULL:
- mutex_lock(&dev->rdev.stats.lock);
- dev->rdev.stats.tcam_full++;
- mutex_unlock(&dev->rdev.stats.lock);
- send_fw_act_open_req(ep,
- GET_TID_TID(GET_AOPEN_ATID(ntohl(rpl->atid_status))));
- return 0;
+ if (dev->rdev.lldi.enable_fw_ofld_conn) {
+ mutex_lock(&dev->rdev.stats.lock);
+ dev->rdev.stats.tcam_full++;
+ mutex_unlock(&dev->rdev.stats.lock);
+ send_fw_act_open_req(ep,
+ GET_TID_TID(GET_AOPEN_ATID(
+ ntohl(rpl->atid_status))));
+ return 0;
+ }
+ break;
+ case CPL_ERR_CONN_EXIST:
+ if (ep->retry_count++ < ACT_OPEN_RETRY_COUNT) {
+ set_bit(ACT_RETRY_INUSE, &ep->com.history);
+ remove_handle(ep->com.dev, &ep->com.dev->atid_idr,
+ atid);
+ cxgb4_free_atid(t, atid);
+ dst_release(ep->dst);
+ cxgb4_l2t_release(ep->l2t);
+ c4iw_reconnect(ep);
+ return 0;
+ }
break;
default:
printk(KERN_INFO MOD "Active open failure - "
@@ -1555,6 +1692,7 @@ static int act_open_rpl(struct c4iw_dev *dev, struct sk_buff *skb)
if (status && act_open_has_tid(status))
cxgb4_remove_tid(ep->com.dev->rdev.lldi.tids, 0, GET_TID(rpl));
+ remove_handle(ep->com.dev, &ep->com.dev->atid_idr, atid);
cxgb4_free_atid(t, atid);
dst_release(ep->dst);
cxgb4_l2t_release(ep->l2t);
@@ -1775,7 +1913,7 @@ out:
static int pass_accept_req(struct c4iw_dev *dev, struct sk_buff *skb)
{
- struct c4iw_ep *child_ep, *parent_ep;
+ struct c4iw_ep *child_ep = NULL, *parent_ep;
struct cpl_pass_accept_req *req = cplhdr(skb);
unsigned int stid = GET_POPEN_TID(ntohl(req->tos_stid));
struct tid_info *t = dev->rdev.lldi.tids;
@@ -1856,6 +1994,7 @@ static int pass_accept_req(struct c4iw_dev *dev, struct sk_buff *skb)
init_timer(&child_ep->timer);
cxgb4_insert_tid(t, child_ep, hwtid);
accept_cr(child_ep, peer_ip, skb, req);
+ set_bit(PASS_ACCEPT_REQ, &child_ep->com.history);
goto out;
reject:
reject_cr(dev, hwtid, peer_ip, skb);
@@ -1879,11 +2018,13 @@ static int pass_establish(struct c4iw_dev *dev, struct sk_buff *skb)
ntohs(req->tcp_opt));
set_emss(ep, ntohs(req->tcp_opt));
+ insert_handle(dev, &dev->hwtid_idr, ep, ep->hwtid);
dst_confirm(ep->dst);
state_set(&ep->com, MPA_REQ_WAIT);
start_ep_timer(ep);
send_flowc(ep, skb);
+ set_bit(PASS_ESTAB, &ep->com.history);
return 0;
}
@@ -1903,6 +2044,7 @@ static int peer_close(struct c4iw_dev *dev, struct sk_buff *skb)
PDBG("%s ep %p tid %u\n", __func__, ep, ep->hwtid);
dst_confirm(ep->dst);
+ set_bit(PEER_CLOSE, &ep->com.history);
mutex_lock(&ep->com.mutex);
switch (ep->com.state) {
case MPA_REQ_WAIT:
@@ -1982,74 +2124,6 @@ static int is_neg_adv_abort(unsigned int status)
status == CPL_ERR_PERSIST_NEG_ADVICE;
}
-static int c4iw_reconnect(struct c4iw_ep *ep)
-{
- struct rtable *rt;
- int err = 0;
-
- PDBG("%s qp %p cm_id %p\n", __func__, ep->com.qp, ep->com.cm_id);
- init_timer(&ep->timer);
-
- /*
- * Allocate an active TID to initiate a TCP connection.
- */
- ep->atid = cxgb4_alloc_atid(ep->com.dev->rdev.lldi.tids, ep);
- if (ep->atid == -1) {
- printk(KERN_ERR MOD "%s - cannot alloc atid.\n", __func__);
- err = -ENOMEM;
- goto fail2;
- }
-
- /* find a route */
- rt = find_route(ep->com.dev,
- ep->com.cm_id->local_addr.sin_addr.s_addr,
- ep->com.cm_id->remote_addr.sin_addr.s_addr,
- ep->com.cm_id->local_addr.sin_port,
- ep->com.cm_id->remote_addr.sin_port, 0);
- if (!rt) {
- printk(KERN_ERR MOD "%s - cannot find route.\n", __func__);
- err = -EHOSTUNREACH;
- goto fail3;
- }
- ep->dst = &rt->dst;
-
- err = import_ep(ep, ep->com.cm_id->remote_addr.sin_addr.s_addr,
- ep->dst, ep->com.dev, false);
- if (err) {
- printk(KERN_ERR MOD "%s - cannot alloc l2e.\n", __func__);
- goto fail4;
- }
-
- PDBG("%s txq_idx %u tx_chan %u smac_idx %u rss_qid %u l2t_idx %u\n",
- __func__, ep->txq_idx, ep->tx_chan, ep->smac_idx, ep->rss_qid,
- ep->l2t->idx);
-
- state_set(&ep->com, CONNECTING);
- ep->tos = 0;
-
- /* send connect request to rnic */
- err = send_connect(ep);
- if (!err)
- goto out;
-
- cxgb4_l2t_release(ep->l2t);
-fail4:
- dst_release(ep->dst);
-fail3:
- cxgb4_free_atid(ep->com.dev->rdev.lldi.tids, ep->atid);
-fail2:
- /*
- * remember to send notification to upper layer.
- * We are in here so the upper layer is not aware that this is
- * re-connect attempt and so, upper layer is still waiting for
- * response of 1st connect request.
- */
- connect_reply_upcall(ep, -ECONNRESET);
- c4iw_put_ep(&ep->com);
-out:
- return err;
-}
-
static int peer_abort(struct c4iw_dev *dev, struct sk_buff *skb)
{
struct cpl_abort_req_rss *req = cplhdr(skb);
@@ -2070,6 +2144,7 @@ static int peer_abort(struct c4iw_dev *dev, struct sk_buff *skb)
}
PDBG("%s ep %p tid %u state %u\n", __func__, ep, ep->hwtid,
ep->com.state);
+ set_bit(PEER_ABORT, &ep->com.history);
/*
* Wake up any threads in rdma_init() or rdma_fini().
@@ -2284,6 +2359,7 @@ int c4iw_reject_cr(struct iw_cm_id *cm_id, const void *pdata, u8 pdata_len)
c4iw_put_ep(&ep->com);
return -ECONNRESET;
}
+ set_bit(ULP_REJECT, &ep->com.history);
BUG_ON(state_read(&ep->com) != MPA_REQ_RCVD);
if (mpa_rev == 0)
abort_connection(ep, NULL, GFP_KERNEL);
@@ -2313,6 +2389,7 @@ int c4iw_accept_cr(struct iw_cm_id *cm_id, struct iw_cm_conn_param *conn_param)
BUG_ON(state_read(&ep->com) != MPA_REQ_RCVD);
BUG_ON(!qp);
+ set_bit(ULP_ACCEPT, &ep->com.history);
if ((conn_param->ord > c4iw_max_read_depth) ||
(conn_param->ird > c4iw_max_read_depth)) {
abort_connection(ep, NULL, GFP_KERNEL);
@@ -2436,6 +2513,7 @@ int c4iw_connect(struct iw_cm_id *cm_id, struct iw_cm_conn_param *conn_param)
err = -ENOMEM;
goto fail2;
}
+ insert_handle(dev, &dev->atid_idr, ep, ep->atid);
PDBG("%s saddr 0x%x sport 0x%x raddr 0x%x rport 0x%x\n", __func__,
ntohl(cm_id->local_addr.sin_addr.s_addr),
@@ -2481,6 +2559,7 @@ int c4iw_connect(struct iw_cm_id *cm_id, struct iw_cm_conn_param *conn_param)
fail4:
dst_release(ep->dst);
fail3:
+ remove_handle(ep->com.dev, &ep->com.dev->atid_idr, ep->atid);
cxgb4_free_atid(ep->com.dev->rdev.lldi.tids, ep->atid);
fail2:
cm_id->rem_ref(cm_id);
@@ -2523,6 +2602,7 @@ int c4iw_create_listen(struct iw_cm_id *cm_id, int backlog)
err = -ENOMEM;
goto fail2;
}
+ insert_handle(dev, &dev->stid_idr, ep, ep->stid);
state_set(&ep->com, LISTEN);
if (dev->rdev.lldi.enable_fw_ofld_conn) {
do {
@@ -2530,7 +2610,10 @@ int c4iw_create_listen(struct iw_cm_id *cm_id, int backlog)
ep->com.dev->rdev.lldi.ports[0], ep->stid,
ep->com.local_addr.sin_addr.s_addr,
ep->com.local_addr.sin_port,
- ep->com.dev->rdev.lldi.rxq_ids[0]);
+ 0,
+ ep->com.dev->rdev.lldi.rxq_ids[0],
+ 0,
+ 0);
if (err == -EBUSY) {
set_current_state(TASK_UNINTERRUPTIBLE);
schedule_timeout(usecs_to_jiffies(100));
@@ -2541,6 +2624,7 @@ int c4iw_create_listen(struct iw_cm_id *cm_id, int backlog)
err = cxgb4_create_server(ep->com.dev->rdev.lldi.ports[0],
ep->stid, ep->com.local_addr.sin_addr.s_addr,
ep->com.local_addr.sin_port,
+ 0,
ep->com.dev->rdev.lldi.rxq_ids[0]);
if (!err)
err = c4iw_wait_for_reply(&ep->com.dev->rdev,
@@ -2586,6 +2670,7 @@ int c4iw_destroy_listen(struct iw_cm_id *cm_id)
err = c4iw_wait_for_reply(&ep->com.dev->rdev, &ep->com.wr_wait,
0, 0, __func__);
}
+ remove_handle(ep->com.dev, &ep->com.dev->stid_idr, ep->stid);
cxgb4_free_stid(ep->com.dev->rdev.lldi.tids, ep->stid, PF_INET);
done:
cm_id->rem_ref(cm_id);
@@ -2649,10 +2734,13 @@ int c4iw_ep_disconnect(struct c4iw_ep *ep, int abrupt, gfp_t gfp)
if (close) {
if (abrupt) {
+ set_bit(EP_DISC_ABORT, &ep->com.history);
close_complete_upcall(ep);
ret = send_abort(ep, NULL, gfp);
- } else
+ } else {
+ set_bit(EP_DISC_CLOSE, &ep->com.history);
ret = send_halfclose(ep, gfp);
+ }
if (ret)
fatal = 1;
}
@@ -2666,6 +2754,7 @@ static void active_ofld_conn_reply(struct c4iw_dev *dev, struct sk_buff *skb,
struct cpl_fw6_msg_ofld_connection_wr_rpl *req)
{
struct c4iw_ep *ep;
+ int atid = be32_to_cpu(req->tid);
ep = (struct c4iw_ep *)lookup_atid(dev->rdev.lldi.tids, req->tid);
if (!ep)
@@ -2673,15 +2762,35 @@ static void active_ofld_conn_reply(struct c4iw_dev *dev, struct sk_buff *skb,
switch (req->retval) {
case FW_ENOMEM:
+ set_bit(ACT_RETRY_NOMEM, &ep->com.history);
+ if (ep->retry_count++ < ACT_OPEN_RETRY_COUNT) {
+ send_fw_act_open_req(ep, atid);
+ return;
+ }
case FW_EADDRINUSE:
- PDBG("%s ofld conn wr ret %d\n", __func__, req->retval);
+ set_bit(ACT_RETRY_INUSE, &ep->com.history);
+ if (ep->retry_count++ < ACT_OPEN_RETRY_COUNT) {
+ send_fw_act_open_req(ep, atid);
+ return;
+ }
break;
default:
pr_info("%s unexpected ofld conn wr retval %d\n",
__func__, req->retval);
break;
}
+ pr_err("active ofld_connect_wr failure %d atid %d\n",
+ req->retval, atid);
+ mutex_lock(&dev->rdev.stats.lock);
+ dev->rdev.stats.act_ofld_conn_fails++;
+ mutex_unlock(&dev->rdev.stats.lock);
connect_reply_upcall(ep, status2errno(req->retval));
+ state_set(&ep->com, DEAD);
+ remove_handle(dev, &dev->atid_idr, atid);
+ cxgb4_free_atid(dev->rdev.lldi.tids, atid);
+ dst_release(ep->dst);
+ cxgb4_l2t_release(ep->l2t);
+ c4iw_put_ep(&ep->com);
}
static void passive_ofld_conn_reply(struct c4iw_dev *dev, struct sk_buff *skb,
@@ -2695,6 +2804,9 @@ static void passive_ofld_conn_reply(struct c4iw_dev *dev, struct sk_buff *skb,
BUG_ON(!rpl_skb);
if (req->retval) {
PDBG("%s passive open failure %d\n", __func__, req->retval);
+ mutex_lock(&dev->rdev.stats.lock);
+ dev->rdev.stats.pas_ofld_conn_fails++;
+ mutex_unlock(&dev->rdev.stats.lock);
kfree_skb(rpl_skb);
} else {
cpl = (struct cpl_pass_accept_req *)cplhdr(rpl_skb);
@@ -2988,6 +3100,7 @@ static void process_timeout(struct c4iw_ep *ep)
mutex_lock(&ep->com.mutex);
PDBG("%s ep %p tid %u state %d\n", __func__, ep, ep->hwtid,
ep->com.state);
+ set_bit(TIMEDOUT, &ep->com.history);
switch (ep->com.state) {
case MPA_REQ_SENT:
__state_set(&ep->com, ABORTING);
diff --git a/drivers/infiniband/hw/cxgb4/device.c b/drivers/infiniband/hw/cxgb4/device.c
index 6b5b3d1..ba11c76 100644
--- a/drivers/infiniband/hw/cxgb4/device.c
+++ b/drivers/infiniband/hw/cxgb4/device.c
@@ -280,6 +280,10 @@ static int stats_show(struct seq_file *seq, void *v)
db_state_str[dev->db_state],
dev->rdev.stats.db_state_transitions);
seq_printf(seq, "TCAM_FULL: %10llu\n", dev->rdev.stats.tcam_full);
+ seq_printf(seq, "ACT_OFLD_CONN_FAILS: %10llu\n",
+ dev->rdev.stats.act_ofld_conn_fails);
+ seq_printf(seq, "PAS_OFLD_CONN_FAILS: %10llu\n",
+ dev->rdev.stats.pas_ofld_conn_fails);
return 0;
}
@@ -310,6 +314,9 @@ static ssize_t stats_clear(struct file *file, const char __user *buf,
dev->rdev.stats.db_empty = 0;
dev->rdev.stats.db_drop = 0;
dev->rdev.stats.db_state_transitions = 0;
+ dev->rdev.stats.tcam_full = 0;
+ dev->rdev.stats.act_ofld_conn_fails = 0;
+ dev->rdev.stats.pas_ofld_conn_fails = 0;
mutex_unlock(&dev->rdev.stats.lock);
return count;
}
@@ -323,6 +330,113 @@ static const struct file_operations stats_debugfs_fops = {
.write = stats_clear,
};
+static int dump_ep(int id, void *p, void *data)
+{
+ struct c4iw_ep *ep = p;
+ struct c4iw_debugfs_data *epd = data;
+ int space;
+ int cc;
+
+ space = epd->bufsize - epd->pos - 1;
+ if (space == 0)
+ return 1;
+
+ cc = snprintf(epd->buf + epd->pos, space,
+ "ep %p cm_id %p qp %p state %d flags 0x%lx history 0x%lx "
+ "hwtid %d atid %d %pI4:%d <-> %pI4:%d\n",
+ ep, ep->com.cm_id, ep->com.qp, (int)ep->com.state,
+ ep->com.flags, ep->com.history, ep->hwtid, ep->atid,
+ &ep->com.local_addr.sin_addr.s_addr,
+ ntohs(ep->com.local_addr.sin_port),
+ &ep->com.remote_addr.sin_addr.s_addr,
+ ntohs(ep->com.remote_addr.sin_port));
+ if (cc < space)
+ epd->pos += cc;
+ return 0;
+}
+
+static int dump_listen_ep(int id, void *p, void *data)
+{
+ struct c4iw_listen_ep *ep = p;
+ struct c4iw_debugfs_data *epd = data;
+ int space;
+ int cc;
+
+ space = epd->bufsize - epd->pos - 1;
+ if (space == 0)
+ return 1;
+
+ cc = snprintf(epd->buf + epd->pos, space,
+ "ep %p cm_id %p state %d flags 0x%lx stid %d backlog %d "
+ "%pI4:%d\n", ep, ep->com.cm_id, (int)ep->com.state,
+ ep->com.flags, ep->stid, ep->backlog,
+ &ep->com.local_addr.sin_addr.s_addr,
+ ntohs(ep->com.local_addr.sin_port));
+ if (cc < space)
+ epd->pos += cc;
+ return 0;
+}
+
+static int ep_release(struct inode *inode, struct file *file)
+{
+ struct c4iw_debugfs_data *epd = file->private_data;
+ if (!epd) {
+ pr_info("%s null qpd?\n", __func__);
+ return 0;
+ }
+ vfree(epd->buf);
+ kfree(epd);
+ return 0;
+}
+
+static int ep_open(struct inode *inode, struct file *file)
+{
+ struct c4iw_debugfs_data *epd;
+ int ret = 0;
+ int count = 1;
+
+ epd = kmalloc(sizeof(*epd), GFP_KERNEL);
+ if (!epd) {
+ ret = -ENOMEM;
+ goto out;
+ }
+ epd->devp = inode->i_private;
+ epd->pos = 0;
+
+ spin_lock_irq(&epd->devp->lock);
+ idr_for_each(&epd->devp->hwtid_idr, count_idrs, &count);
+ idr_for_each(&epd->devp->atid_idr, count_idrs, &count);
+ idr_for_each(&epd->devp->stid_idr, count_idrs, &count);
+ spin_unlock_irq(&epd->devp->lock);
+
+ epd->bufsize = count * 160;
+ epd->buf = vmalloc(epd->bufsize);
+ if (!epd->buf) {
+ ret = -ENOMEM;
+ goto err1;
+ }
+
+ spin_lock_irq(&epd->devp->lock);
+ idr_for_each(&epd->devp->hwtid_idr, dump_ep, epd);
+ idr_for_each(&epd->devp->atid_idr, dump_ep, epd);
+ idr_for_each(&epd->devp->stid_idr, dump_listen_ep, epd);
+ spin_unlock_irq(&epd->devp->lock);
+
+ file->private_data = epd;
+ goto out;
+err1:
+ kfree(epd);
+out:
+ return ret;
+}
+
+static const struct file_operations ep_debugfs_fops = {
+ .owner = THIS_MODULE,
+ .open = ep_open,
+ .release = ep_release,
+ .read = debugfs_read,
+};
+
static int setup_debugfs(struct c4iw_dev *devp)
{
struct dentry *de;
@@ -345,6 +459,11 @@ static int setup_debugfs(struct c4iw_dev *devp)
if (de && de->d_inode)
de->d_inode->i_size = 4096;
+ de = debugfs_create_file("eps", S_IWUSR, devp->debugfs_root,
+ (void *)devp, &ep_debugfs_fops);
+ if (de && de->d_inode)
+ de->d_inode->i_size = 4096;
+
return 0;
}
@@ -476,6 +595,9 @@ static void c4iw_dealloc(struct uld_ctx *ctx)
idr_destroy(&ctx->dev->cqidr);
idr_destroy(&ctx->dev->qpidr);
idr_destroy(&ctx->dev->mmidr);
+ idr_destroy(&ctx->dev->hwtid_idr);
+ idr_destroy(&ctx->dev->stid_idr);
+ idr_destroy(&ctx->dev->atid_idr);
iounmap(ctx->dev->rdev.oc_mw_kva);
ib_dealloc_device(&ctx->dev->ibdev);
ctx->dev = NULL;
@@ -533,6 +655,9 @@ static struct c4iw_dev *c4iw_alloc(const struct cxgb4_lld_info *infop)
idr_init(&devp->cqidr);
idr_init(&devp->qpidr);
idr_init(&devp->mmidr);
+ idr_init(&devp->hwtid_idr);
+ idr_init(&devp->stid_idr);
+ idr_init(&devp->atid_idr);
spin_lock_init(&devp->lock);
mutex_init(&devp->rdev.stats.lock);
mutex_init(&devp->db_mutex);
diff --git a/drivers/infiniband/hw/cxgb4/iw_cxgb4.h b/drivers/infiniband/hw/cxgb4/iw_cxgb4.h
index 6a17fde..9c1644f 100644
--- a/drivers/infiniband/hw/cxgb4/iw_cxgb4.h
+++ b/drivers/infiniband/hw/cxgb4/iw_cxgb4.h
@@ -131,6 +131,8 @@ struct c4iw_stats {
u64 db_drop;
u64 db_state_transitions;
u64 tcam_full;
+ u64 act_ofld_conn_fails;
+ u64 pas_ofld_conn_fails;
};
struct c4iw_rdev {
@@ -224,6 +226,9 @@ struct c4iw_dev {
struct dentry *debugfs_root;
enum db_state db_state;
int qpcnt;
+ struct idr hwtid_idr;
+ struct idr atid_idr;
+ struct idr stid_idr;
};
static inline struct c4iw_dev *to_c4iw_dev(struct ib_device *ibdev)
@@ -713,6 +718,31 @@ enum c4iw_ep_flags {
CLOSE_SENT = 3,
};
+enum c4iw_ep_history {
+ ACT_OPEN_REQ = 0,
+ ACT_OFLD_CONN = 1,
+ ACT_OPEN_RPL = 2,
+ ACT_ESTAB = 3,
+ PASS_ACCEPT_REQ = 4,
+ PASS_ESTAB = 5,
+ ABORT_UPCALL = 6,
+ ESTAB_UPCALL = 7,
+ CLOSE_UPCALL = 8,
+ ULP_ACCEPT = 9,
+ ULP_REJECT = 10,
+ TIMEDOUT = 11,
+ PEER_ABORT = 12,
+ PEER_CLOSE = 13,
+ CONNREQ_UPCALL = 14,
+ ABORT_CONN = 15,
+ DISCONN_UPCALL = 16,
+ EP_DISC_CLOSE = 17,
+ EP_DISC_ABORT = 18,
+ CONN_RPL_UPCALL = 19,
+ ACT_RETRY_NOMEM = 20,
+ ACT_RETRY_INUSE = 21
+};
+
struct c4iw_ep_common {
struct iw_cm_id *cm_id;
struct c4iw_qp *qp;
@@ -724,6 +754,7 @@ struct c4iw_ep_common {
struct sockaddr_in remote_addr;
struct c4iw_wr_wait wr_wait;
unsigned long flags;
+ unsigned long history;
};
struct c4iw_listen_ep {
@@ -761,6 +792,7 @@ struct c4iw_ep {
u8 tos;
u8 retry_with_mpa_v1;
u8 tried_with_mpa_v1;
+ unsigned int retry_count;
};
static inline struct c4iw_ep *to_ep(struct iw_cm_id *cm_id)
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h b/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h
index 868acde..d47a076 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h
@@ -530,6 +530,7 @@ struct adapter {
struct net_device *port[MAX_NPORTS];
u8 chan_map[NCHAN]; /* channel -> port map */
+ u32 filter_mode;
unsigned int l2t_start;
unsigned int l2t_end;
struct l2t_data *l2t;
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
index 1a26e3f..fe945c7 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
@@ -2678,7 +2678,8 @@ static int tid_init(struct tid_info *t)
* Returns <0 on error and one of the %NET_XMIT_* values on success.
*/
int cxgb4_create_server(const struct net_device *dev, unsigned int stid,
- __be32 sip, __be16 sport, unsigned int queue)
+ __be32 sip, __be16 sport, __be16 vlan,
+ unsigned int queue)
{
unsigned int chan;
struct sk_buff *skb;
@@ -3051,7 +3052,7 @@ static void uld_attach(struct adapter *adap, unsigned int uld)
lli.ucq_density = 1 << QUEUESPERPAGEPF0_GET(
t4_read_reg(adap, SGE_INGRESS_QUEUES_PER_PAGE_PF) >>
(adap->fn * 4));
- lli.filt_mode = tp_vlan_pri_map;
+ lli.filt_mode = adap->filter_mode;
/* MODQ_REQ_MAP sets queues 0-3 to chan 0-3 */
for (i = 0; i < NCHAN; i++)
lli.tx_modq[i] = i;
@@ -3316,7 +3317,8 @@ static int delete_filter(struct adapter *adapter, unsigned int fidx)
}
int cxgb4_create_server_filter(const struct net_device *dev, unsigned int stid,
- __be32 sip, __be16 sport, unsigned int queue)
+ __be32 sip, __be16 sport, __be16 vlan,
+ unsigned int queue, unsigned char port, unsigned char mask)
{
int ret;
struct filter_entry *f;
@@ -3348,11 +3350,16 @@ int cxgb4_create_server_filter(const struct net_device *dev, unsigned int stid,
f->fs.val.lport = cpu_to_be16(sport);
f->fs.mask.lport = ~0;
val = (u8 *)&sip;
- if ((val[0] | val[1] | val[2] | val[3]) != 0)
+ if ((val[0] | val[1] | val[2] | val[3]) != 0) {
for (i = 0; i < 4; i++) {
f->fs.val.lip[i] = val[i];
f->fs.mask.lip[i] = ~0;
}
+ if (adap->filter_mode & F_PORT) {
+ f->fs.val.iport = port;
+ f->fs.mask.iport = mask;
+ }
+ }
f->fs.dirsteer = 1;
f->fs.iq = queue;
@@ -4459,6 +4466,10 @@ static int adap_init0(struct adapter *adap)
for (j = 0; j < NCHAN; j++)
adap->params.tp.tx_modq[j] = j;
+ t4_read_indirect(adap, TP_PIO_ADDR, TP_PIO_DATA,
+ &adap->filter_mode, 1,
+ TP_VLAN_PRI_MAP);
+
adap->flags |= FW_OK;
return 0;
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.h b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.h
index 065bbd5..e2bbc7f 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.h
@@ -38,6 +38,7 @@
#include <linux/cache.h>
#include <linux/spinlock.h>
#include <linux/skbuff.h>
+#include <linux/inetdevice.h>
#include <linux/atomic.h>
/* CPL message priority levels */
@@ -151,9 +152,12 @@ void cxgb4_remove_tid(struct tid_info *t, unsigned int qid, unsigned int tid);
struct in6_addr;
int cxgb4_create_server(const struct net_device *dev, unsigned int stid,
- __be32 sip, __be16 sport, unsigned int queue);
+ __be32 sip, __be16 sport, __be16 vlan,
+ unsigned int queue);
int cxgb4_create_server_filter(const struct net_device *dev, unsigned int stid,
- __be32 sip, __be16 sport, unsigned int queue);
+ __be32 sip, __be16 sport, __be16 vlan,
+ unsigned int queue,
+ unsigned char port, unsigned char mask);
int cxgb4_remove_server_filter(const struct net_device *dev, unsigned int stid,
unsigned int queue, bool ipv6);
static inline void set_wr_txq(struct sk_buff *skb, int prio, int queue)
diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_regs.h b/drivers/net/ethernet/chelsio/cxgb4/t4_regs.h
index bdc1bbc..3139221 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/t4_regs.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/t4_regs.h
@@ -1066,5 +1066,7 @@
#define A_TP_TX_SCHED_PCMD 0x25
#define S_PORT 1
+#define V_PORT(x) ((x) << S_PORT)
+#define F_PORT V_PORT(1U)
#endif /* __T4_REGS_H */
--
1.7.1
^ permalink raw reply related
* [PATCH v2] net/macb: Use non-coherent memory for rx buffers
From: Nicolas Ferre @ 2012-12-03 12:14 UTC (permalink / raw)
To: David S. Miller, netdev
Cc: linux-arm-kernel, linux-kernel, Joachim Eastwood,
Jean-Christophe PLAGNIOL-VILLARD, Havard Skinnemoen,
Nicolas Ferre
In-Reply-To: <CAGhQ9VwWmP_B17LnAEqDHcL8Yd-s0C-Bf35z3+=vnJmK_NoCSw@mail.gmail.com>
From: Havard Skinnemoen <havard@skinnemoen.net>
Allocate regular pages to use as backing for the RX ring and use the
DMA API to sync the caches. This should give a bit better performance
since it allows the CPU to do burst transfers from memory. It is also
a necessary step on the way to reduce the amount of copying done by
the driver.
Signed-off-by: Havard Skinnemoen <havard@skinnemoen.net>
[nicolas.ferre@atmel.com: adapt to newer kernel]
Signed-off-by: Nicolas Ferre <nicolas.ferre@atmel.com>
---
v2: - keep struct macb members as they are shared between
at91_ether and macb.
drivers/net/ethernet/cadence/macb.c | 206 +++++++++++++++++++++++-------------
drivers/net/ethernet/cadence/macb.h | 18 ++++
2 files changed, 148 insertions(+), 76 deletions(-)
diff --git a/drivers/net/ethernet/cadence/macb.c b/drivers/net/ethernet/cadence/macb.c
index 6a59bce..c2955da 100644
--- a/drivers/net/ethernet/cadence/macb.c
+++ b/drivers/net/ethernet/cadence/macb.c
@@ -10,6 +10,7 @@
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <linux/clk.h>
+#include <linux/highmem.h>
#include <linux/module.h>
#include <linux/moduleparam.h>
#include <linux/kernel.h>
@@ -35,6 +36,8 @@
#define RX_BUFFER_SIZE 128
#define RX_RING_SIZE 512 /* must be power of 2 */
#define RX_RING_BYTES (sizeof(struct macb_dma_desc) * RX_RING_SIZE)
+#define RX_BUFFERS_PER_PAGE (PAGE_SIZE / RX_BUFFER_SIZE)
+#define RX_RING_PAGES (RX_RING_SIZE / RX_BUFFERS_PER_PAGE)
#define TX_RING_SIZE 128 /* must be power of 2 */
#define TX_RING_BYTES (sizeof(struct macb_dma_desc) * TX_RING_SIZE)
@@ -90,9 +93,16 @@ static struct macb_dma_desc *macb_rx_desc(struct macb *bp, unsigned int index)
return &bp->rx_ring[macb_rx_ring_wrap(index)];
}
-static void *macb_rx_buffer(struct macb *bp, unsigned int index)
+static struct macb_rx_page *macb_rx_page(struct macb *bp, unsigned int index)
{
- return bp->rx_buffers + RX_BUFFER_SIZE * macb_rx_ring_wrap(index);
+ unsigned int entry = macb_rx_ring_wrap(index);
+
+ return &bp->rx_page[entry / RX_BUFFERS_PER_PAGE];
+}
+
+static unsigned int macb_rx_page_offset(struct macb *bp, unsigned int index)
+{
+ return (index % RX_BUFFERS_PER_PAGE) * RX_BUFFER_SIZE;
}
void macb_set_hwaddr(struct macb *bp)
@@ -528,11 +538,15 @@ static void macb_tx_interrupt(struct macb *bp)
static int macb_rx_frame(struct macb *bp, unsigned int first_frag,
unsigned int last_frag)
{
- unsigned int len;
- unsigned int frag;
- unsigned int offset;
- struct sk_buff *skb;
- struct macb_dma_desc *desc;
+ unsigned int len;
+ unsigned int frag;
+ unsigned int skb_offset;
+ unsigned int pg_offset;
+ struct macb_rx_page *rx_page;
+ dma_addr_t phys;
+ void *buf;
+ struct sk_buff *skb;
+ struct macb_dma_desc *desc;
desc = macb_rx_desc(bp, last_frag);
len = MACB_BFEXT(RX_FRMLEN, desc->ctrl);
@@ -566,7 +580,7 @@ static int macb_rx_frame(struct macb *bp, unsigned int first_frag,
return 1;
}
- offset = 0;
+ skb_offset = 0;
len += NET_IP_ALIGN;
skb_checksum_none_assert(skb);
skb_put(skb, len);
@@ -574,13 +588,28 @@ static int macb_rx_frame(struct macb *bp, unsigned int first_frag,
for (frag = first_frag; ; frag++) {
unsigned int frag_len = RX_BUFFER_SIZE;
- if (offset + frag_len > len) {
+ if (skb_offset + frag_len > len) {
BUG_ON(frag != last_frag);
- frag_len = len - offset;
+ frag_len = len - skb_offset;
}
- skb_copy_to_linear_data_offset(skb, offset,
- macb_rx_buffer(bp, frag), frag_len);
- offset += RX_BUFFER_SIZE;
+
+ rx_page = macb_rx_page(bp, frag);
+ pg_offset = macb_rx_page_offset(bp, frag);
+ phys = rx_page->phys;
+
+ dma_sync_single_range_for_cpu(&bp->pdev->dev, phys,
+ pg_offset, frag_len, DMA_FROM_DEVICE);
+
+ buf = kmap_atomic(rx_page->page);
+ skb_copy_to_linear_data_offset(skb, skb_offset,
+ buf + pg_offset, frag_len);
+ kunmap_atomic(buf);
+
+ skb_offset += frag_len;
+
+ dma_sync_single_range_for_device(&bp->pdev->dev, phys,
+ pg_offset, frag_len, DMA_FROM_DEVICE);
+
desc = macb_rx_desc(bp, frag);
desc->addr &= ~MACB_BIT(RX_USED);
@@ -860,86 +889,90 @@ static int macb_start_xmit(struct sk_buff *skb, struct net_device *dev)
return NETDEV_TX_OK;
}
-static void macb_free_consistent(struct macb *bp)
+static void macb_free_rings(struct macb *bp)
{
- if (bp->tx_skb) {
- kfree(bp->tx_skb);
- bp->tx_skb = NULL;
- }
- if (bp->rx_ring) {
- dma_free_coherent(&bp->pdev->dev, RX_RING_BYTES,
- bp->rx_ring, bp->rx_ring_dma);
- bp->rx_ring = NULL;
- }
- if (bp->tx_ring) {
- dma_free_coherent(&bp->pdev->dev, TX_RING_BYTES,
- bp->tx_ring, bp->tx_ring_dma);
- bp->tx_ring = NULL;
- }
- if (bp->rx_buffers) {
- dma_free_coherent(&bp->pdev->dev,
- RX_RING_SIZE * RX_BUFFER_SIZE,
- bp->rx_buffers, bp->rx_buffers_dma);
- bp->rx_buffers = NULL;
+ int i;
+
+ for (i = 0; i < RX_RING_PAGES; i++) {
+ struct macb_rx_page *rx_page = &bp->rx_page[i];
+
+ if (!rx_page->page)
+ continue;
+
+ dma_unmap_page(&bp->pdev->dev, rx_page->phys,
+ PAGE_SIZE, DMA_FROM_DEVICE);
+ put_page(rx_page->page);
+ rx_page->page = NULL;
}
+
+ kfree(bp->tx_skb);
+ kfree(bp->rx_page);
+ dma_free_coherent(&bp->pdev->dev, TX_RING_BYTES, bp->tx_ring,
+ bp->tx_ring_dma);
+ dma_free_coherent(&bp->pdev->dev, RX_RING_BYTES, bp->rx_ring,
+ bp->rx_ring_dma);
}
-static int macb_alloc_consistent(struct macb *bp)
+static int macb_init_rings(struct macb *bp)
{
- int size;
+ struct page *page;
+ dma_addr_t phys;
+ unsigned int page_idx;
+ unsigned int ring_idx;
+ unsigned int i;
- size = TX_RING_SIZE * sizeof(struct macb_tx_skb);
- bp->tx_skb = kmalloc(size, GFP_KERNEL);
- if (!bp->tx_skb)
- goto out_err;
-
- size = RX_RING_BYTES;
- bp->rx_ring = dma_alloc_coherent(&bp->pdev->dev, size,
+ bp->rx_ring = dma_alloc_coherent(&bp->pdev->dev, RX_RING_BYTES,
&bp->rx_ring_dma, GFP_KERNEL);
if (!bp->rx_ring)
- goto out_err;
+ goto err_alloc_rx_ring;
+
netdev_dbg(bp->dev,
"Allocated RX ring of %d bytes at %08lx (mapped %p)\n",
- size, (unsigned long)bp->rx_ring_dma, bp->rx_ring);
+ RX_RING_BYTES, (unsigned long)bp->rx_ring_dma, bp->rx_ring);
- size = TX_RING_BYTES;
- bp->tx_ring = dma_alloc_coherent(&bp->pdev->dev, size,
+ bp->tx_ring = dma_alloc_coherent(&bp->pdev->dev, TX_RING_BYTES,
&bp->tx_ring_dma, GFP_KERNEL);
if (!bp->tx_ring)
- goto out_err;
- netdev_dbg(bp->dev,
- "Allocated TX ring of %d bytes at %08lx (mapped %p)\n",
- size, (unsigned long)bp->tx_ring_dma, bp->tx_ring);
-
- size = RX_RING_SIZE * RX_BUFFER_SIZE;
- bp->rx_buffers = dma_alloc_coherent(&bp->pdev->dev, size,
- &bp->rx_buffers_dma, GFP_KERNEL);
- if (!bp->rx_buffers)
- goto out_err;
+ goto err_alloc_tx_ring;
+
netdev_dbg(bp->dev,
- "Allocated RX buffers of %d bytes at %08lx (mapped %p)\n",
- size, (unsigned long)bp->rx_buffers_dma, bp->rx_buffers);
+ "Allocated TX ring of %d bytes at 0x%08lx (mapped %p)\n",
+ TX_RING_BYTES, (unsigned long)bp->tx_ring_dma, bp->tx_ring);
- return 0;
+ bp->rx_page = kcalloc(RX_RING_PAGES, sizeof(struct macb_rx_page),
+ GFP_KERNEL);
+ if (!bp->rx_page)
+ goto err_alloc_rx_page;
-out_err:
- macb_free_consistent(bp);
- return -ENOMEM;
-}
+ bp->tx_skb = kcalloc(TX_RING_SIZE, sizeof(struct macb_tx_skb),
+ GFP_KERNEL);
+ if (!bp->tx_skb)
+ goto err_alloc_tx_skb;
-static void macb_init_rings(struct macb *bp)
-{
- int i;
- dma_addr_t addr;
+ for (page_idx = 0, ring_idx = 0; page_idx < RX_RING_PAGES; page_idx++) {
+ page = alloc_page(GFP_KERNEL);
+ if (!page)
+ goto err_alloc_page;
+
+ phys = dma_map_page(&bp->pdev->dev, page, 0, PAGE_SIZE,
+ DMA_FROM_DEVICE);
+ if (dma_mapping_error(&bp->pdev->dev, phys))
+ goto err_map_page;
+
+ bp->rx_page[page_idx].page = page;
+ bp->rx_page[page_idx].phys = phys;
- addr = bp->rx_buffers_dma;
- for (i = 0; i < RX_RING_SIZE; i++) {
- bp->rx_ring[i].addr = addr;
- bp->rx_ring[i].ctrl = 0;
- addr += RX_BUFFER_SIZE;
+ for (i = 0; i < RX_BUFFERS_PER_PAGE; i++, ring_idx++) {
+ bp->rx_ring[ring_idx].addr = phys;
+ bp->rx_ring[ring_idx].ctrl = 0;
+ phys += RX_BUFFER_SIZE;
+ }
}
bp->rx_ring[RX_RING_SIZE - 1].addr |= MACB_BIT(RX_WRAP);
+ netdev_dbg(bp->dev, "Allocated %u RX buffers (%lu pages)\n",
+ RX_RING_SIZE, RX_RING_PAGES);
+
for (i = 0; i < TX_RING_SIZE; i++) {
bp->tx_ring[i].addr = 0;
bp->tx_ring[i].ctrl = MACB_BIT(TX_USED);
@@ -947,6 +980,28 @@ static void macb_init_rings(struct macb *bp)
bp->tx_ring[TX_RING_SIZE - 1].ctrl |= MACB_BIT(TX_WRAP);
bp->rx_tail = bp->tx_head = bp->tx_tail = 0;
+
+ return 0;
+
+err_map_page:
+ __free_page(page);
+err_alloc_page:
+ while (page_idx--) {
+ dma_unmap_page(&bp->pdev->dev, bp->rx_page[page_idx].phys,
+ PAGE_SIZE, DMA_FROM_DEVICE);
+ __free_page(bp->rx_page[page_idx].page);
+ }
+ kfree(bp->tx_skb);
+err_alloc_tx_skb:
+ kfree(bp->rx_page);
+err_alloc_rx_page:
+ dma_free_coherent(&bp->pdev->dev, TX_RING_BYTES, bp->tx_ring,
+ bp->tx_ring_dma);
+err_alloc_tx_ring:
+ dma_free_coherent(&bp->pdev->dev, RX_RING_BYTES, bp->rx_ring,
+ bp->rx_ring_dma);
+err_alloc_rx_ring:
+ return -ENOMEM;
}
static void macb_reset_hw(struct macb *bp)
@@ -1221,16 +1276,15 @@ static int macb_open(struct net_device *dev)
if (!bp->phy_dev)
return -EAGAIN;
- err = macb_alloc_consistent(bp);
+ err = macb_init_rings(bp);
if (err) {
- netdev_err(dev, "Unable to allocate DMA memory (error %d)\n",
+ netdev_err(dev, "Unable to allocate DMA rings (error %d)\n",
err);
return err;
}
napi_enable(&bp->napi);
- macb_init_rings(bp);
macb_init_hw(bp);
/* schedule a link state check */
@@ -1257,7 +1311,7 @@ static int macb_close(struct net_device *dev)
netif_carrier_off(dev);
spin_unlock_irqrestore(&bp->lock, flags);
- macb_free_consistent(bp);
+ macb_free_rings(bp);
return 0;
}
diff --git a/drivers/net/ethernet/cadence/macb.h b/drivers/net/ethernet/cadence/macb.h
index 570908b..e82242b 100644
--- a/drivers/net/ethernet/cadence/macb.h
+++ b/drivers/net/ethernet/cadence/macb.h
@@ -453,6 +453,23 @@ struct macb_dma_desc {
#define MACB_TX_USED_SIZE 1
/**
+ * struct macb_rx_page - data associated with a page used as RX buffers
+ * @page: Physical page used as storage for the buffers
+ * @phys: DMA address of the page
+ *
+ * Each page is used to provide %MACB_RX_BUFFERS_PER_PAGE RX buffers.
+ * The page gets an initial reference when it is inserted into the
+ * ring, and an additional reference each time it is passed up the
+ * stack as a fragment. When all the buffers have been used, we drop
+ * the initial reference and allocate a new page. Any additional
+ * references are dropped when the higher layers free the skb.
+ */
+struct macb_rx_page {
+ struct page *page;
+ dma_addr_t phys;
+};
+
+/**
* struct macb_tx_skb - data about an skb which is being transmitted
* @skb: skb currently being transmitted
* @mapping: DMA address of the skb's data buffer
@@ -543,6 +560,7 @@ struct macb {
unsigned int rx_tail;
struct macb_dma_desc *rx_ring;
+ struct macb_rx_page *rx_page;
void *rx_buffers;
unsigned int tx_head, tx_tail;
--
1.8.0
^ permalink raw reply related
* [PATCH] net/macb: Use dmapool to align descriptors on 64bits
From: Nicolas Ferre @ 2012-12-03 12:15 UTC (permalink / raw)
To: David S. Miller, netdev
Cc: linux-arm-kernel, linux-kernel, Joachim Eastwood,
Jean-Christophe PLAGNIOL-VILLARD, Nicolas Ferre
Depending on datapath, some revisions of GEM need
64bits aligned descriptors. Use dmapool to allocate
these descriptors.
Note that different size between RX and TX rings
leads to the creation of two pools.
Signed-off-by: Nicolas Ferre <nicolas.ferre@atmel.com>
---
drivers/net/ethernet/cadence/macb.c | 99 ++++++++++++++++++++++++-------------
drivers/net/ethernet/cadence/macb.h | 3 ++
2 files changed, 69 insertions(+), 33 deletions(-)
diff --git a/drivers/net/ethernet/cadence/macb.c b/drivers/net/ethernet/cadence/macb.c
index c2955da..4b541a3 100644
--- a/drivers/net/ethernet/cadence/macb.c
+++ b/drivers/net/ethernet/cadence/macb.c
@@ -22,6 +22,7 @@
#include <linux/interrupt.h>
#include <linux/netdevice.h>
#include <linux/etherdevice.h>
+#include <linux/dmapool.h>
#include <linux/dma-mapping.h>
#include <linux/platform_data/macb.h>
#include <linux/platform_device.h>
@@ -889,6 +890,47 @@ static int macb_start_xmit(struct sk_buff *skb, struct net_device *dev)
return NETDEV_TX_OK;
}
+/*
+ * Retrieve the maximum supported data bus width from decoding the
+ * design configuration register.
+ *
+ * Result in bytes.
+ */
+static u32 macb_dma_bus_width(struct macb *bp)
+{
+ u32 dbwdef;
+
+ if (!macb_is_gem(bp))
+ return 4;
+
+ dbwdef = GEM_BFEXT(DBWDEF, gem_readl(bp, DCFG1));
+ switch (dbwdef) {
+ case 4:
+ case 2:
+ return dbwdef * 4;
+ case 1:
+ default:
+ return 4;
+ }
+}
+
+/*
+ * Get the DMA bus width field of the network configuration register that we
+ * should program.
+ */
+static u32 macb_dbw(struct macb *bp)
+{
+ switch (macb_dma_bus_width(bp)) {
+ case 16:
+ return GEM_BF(DBW, GEM_DBW128);
+ case 8:
+ return GEM_BF(DBW, GEM_DBW64);
+ case 4:
+ default:
+ return GEM_BF(DBW, GEM_DBW32);
+ }
+}
+
static void macb_free_rings(struct macb *bp)
{
int i;
@@ -907,10 +949,12 @@ static void macb_free_rings(struct macb *bp)
kfree(bp->tx_skb);
kfree(bp->rx_page);
- dma_free_coherent(&bp->pdev->dev, TX_RING_BYTES, bp->tx_ring,
- bp->tx_ring_dma);
- dma_free_coherent(&bp->pdev->dev, RX_RING_BYTES, bp->rx_ring,
- bp->rx_ring_dma);
+ dma_pool_free(bp->tx_pool, bp->tx_ring, bp->tx_ring_dma);
+ dma_pool_free(bp->rx_pool, bp->rx_ring, bp->rx_ring_dma);
+ dma_pool_destroy(bp->tx_pool);
+ dma_pool_destroy(bp->rx_pool);
+ bp->tx_pool = NULL;
+ bp->rx_pool = NULL;
}
static int macb_init_rings(struct macb *bp)
@@ -920,9 +964,16 @@ static int macb_init_rings(struct macb *bp)
unsigned int page_idx;
unsigned int ring_idx;
unsigned int i;
+ unsigned int dma_bw = macb_dma_bus_width(bp);
+
+ bp->rx_pool = dma_pool_create(bp->pdev->name, &bp->pdev->dev,
+ RX_RING_BYTES, dma_bw, 0);
+ bp->tx_pool = dma_pool_create(bp->pdev->name, &bp->pdev->dev,
+ TX_RING_BYTES, dma_bw, 0);
+ if (!bp->rx_pool || !bp->tx_pool)
+ goto err_alloc_rx_ring;
- bp->rx_ring = dma_alloc_coherent(&bp->pdev->dev, RX_RING_BYTES,
- &bp->rx_ring_dma, GFP_KERNEL);
+ bp->rx_ring = dma_pool_alloc(bp->rx_pool, GFP_KERNEL, &bp->rx_ring_dma);
if (!bp->rx_ring)
goto err_alloc_rx_ring;
@@ -930,8 +981,7 @@ static int macb_init_rings(struct macb *bp)
"Allocated RX ring of %d bytes at %08lx (mapped %p)\n",
RX_RING_BYTES, (unsigned long)bp->rx_ring_dma, bp->rx_ring);
- bp->tx_ring = dma_alloc_coherent(&bp->pdev->dev, TX_RING_BYTES,
- &bp->tx_ring_dma, GFP_KERNEL);
+ bp->tx_ring = dma_pool_alloc(bp->tx_pool, GFP_KERNEL, &bp->tx_ring_dma);
if (!bp->tx_ring)
goto err_alloc_tx_ring;
@@ -995,12 +1045,16 @@ err_alloc_page:
err_alloc_tx_skb:
kfree(bp->rx_page);
err_alloc_rx_page:
- dma_free_coherent(&bp->pdev->dev, TX_RING_BYTES, bp->tx_ring,
- bp->tx_ring_dma);
+ dma_pool_free(bp->tx_pool, bp->tx_ring, bp->tx_ring_dma);
err_alloc_tx_ring:
- dma_free_coherent(&bp->pdev->dev, RX_RING_BYTES, bp->rx_ring,
- bp->rx_ring_dma);
+ dma_pool_free(bp->rx_pool, bp->rx_ring, bp->rx_ring_dma);
err_alloc_rx_ring:
+ if (bp->tx_pool)
+ dma_pool_destroy(bp->tx_pool);
+ if (bp->rx_pool)
+ dma_pool_destroy(bp->rx_pool);
+ bp->rx_pool = NULL;
+ bp->tx_pool = NULL;
return -ENOMEM;
}
@@ -1067,27 +1121,6 @@ static u32 macb_mdc_clk_div(struct macb *bp)
}
/*
- * Get the DMA bus width field of the network configuration register that we
- * should program. We find the width from decoding the design configuration
- * register to find the maximum supported data bus width.
- */
-static u32 macb_dbw(struct macb *bp)
-{
- if (!macb_is_gem(bp))
- return 0;
-
- switch (GEM_BFEXT(DBWDEF, gem_readl(bp, DCFG1))) {
- case 4:
- return GEM_BF(DBW, GEM_DBW128);
- case 2:
- return GEM_BF(DBW, GEM_DBW64);
- case 1:
- default:
- return GEM_BF(DBW, GEM_DBW32);
- }
-}
-
-/*
* Configure the receive DMA engine
* - use the correct receive buffer size
* - set the possibility to use INCR16 bursts
diff --git a/drivers/net/ethernet/cadence/macb.h b/drivers/net/ethernet/cadence/macb.h
index e82242b..b4c9515 100644
--- a/drivers/net/ethernet/cadence/macb.h
+++ b/drivers/net/ethernet/cadence/macb.h
@@ -584,6 +584,9 @@ struct macb {
dma_addr_t tx_ring_dma;
dma_addr_t rx_buffers_dma;
+ struct dma_pool *rx_pool;
+ struct dma_pool *tx_pool;
+
struct mii_bus *mii_bus;
struct phy_device *phy_dev;
unsigned int link;
--
1.8.0
^ permalink raw reply related
* [PATCH] net/macb: increase RX buffer size for GEM
From: Nicolas Ferre @ 2012-12-03 12:15 UTC (permalink / raw)
To: David S. Miller, netdev
Cc: linux-arm-kernel, linux-kernel, Joachim Eastwood,
Jean-Christophe PLAGNIOL-VILLARD, Nicolas Ferre
Macb Ethernet controller requires a RX buffer of 128 bytes. It is
highly sub-optimal for Gigabit-capable GEM that is able to use
a bigger DMA buffer. Change this constant and associated macros
with data stored in the private structure.
I also kept the result of buffers per page calculation to lower the
impact of this move to a variable rx buffer size on rx hot path.
RX DMA buffer size has to be multiple of 64 bytes as indicated in
DMA Configuration Register specification.
Signed-off-by: Nicolas Ferre <nicolas.ferre@atmel.com>
---
drivers/net/ethernet/cadence/macb.c | 61 ++++++++++++++++++++++++++++---------
drivers/net/ethernet/cadence/macb.h | 2 ++
2 files changed, 49 insertions(+), 14 deletions(-)
diff --git a/drivers/net/ethernet/cadence/macb.c b/drivers/net/ethernet/cadence/macb.c
index 4b541a3..b4f45f4 100644
--- a/drivers/net/ethernet/cadence/macb.c
+++ b/drivers/net/ethernet/cadence/macb.c
@@ -34,11 +34,11 @@
#include "macb.h"
-#define RX_BUFFER_SIZE 128
+#define MACB_RX_BUFFER_SIZE 128
+#define GEM_RX_BUFFER_SIZE 2048
+#define RX_BUFFER_MULTIPLE 64 /* bytes */
#define RX_RING_SIZE 512 /* must be power of 2 */
#define RX_RING_BYTES (sizeof(struct macb_dma_desc) * RX_RING_SIZE)
-#define RX_BUFFERS_PER_PAGE (PAGE_SIZE / RX_BUFFER_SIZE)
-#define RX_RING_PAGES (RX_RING_SIZE / RX_BUFFERS_PER_PAGE)
#define TX_RING_SIZE 128 /* must be power of 2 */
#define TX_RING_BYTES (sizeof(struct macb_dma_desc) * TX_RING_SIZE)
@@ -98,12 +98,17 @@ static struct macb_rx_page *macb_rx_page(struct macb *bp, unsigned int index)
{
unsigned int entry = macb_rx_ring_wrap(index);
- return &bp->rx_page[entry / RX_BUFFERS_PER_PAGE];
+ return &bp->rx_page[entry / bp->rx_buffers_per_page];
}
static unsigned int macb_rx_page_offset(struct macb *bp, unsigned int index)
{
- return (index % RX_BUFFERS_PER_PAGE) * RX_BUFFER_SIZE;
+ return (index % bp->rx_buffers_per_page) * bp->rx_buffer_size;
+}
+
+static unsigned int rx_ring_pages(struct macb *bp)
+{
+ return RX_RING_SIZE / bp->rx_buffers_per_page;
}
void macb_set_hwaddr(struct macb *bp)
@@ -587,7 +592,7 @@ static int macb_rx_frame(struct macb *bp, unsigned int first_frag,
skb_put(skb, len);
for (frag = first_frag; ; frag++) {
- unsigned int frag_len = RX_BUFFER_SIZE;
+ unsigned int frag_len = bp->rx_buffer_size;
if (skb_offset + frag_len > len) {
BUG_ON(frag != last_frag);
@@ -931,11 +936,36 @@ static u32 macb_dbw(struct macb *bp)
}
}
+static void macb_init_rx_buffer_size(struct macb *bp)
+{
+ if (!macb_is_gem(bp)) {
+ bp->rx_buffer_size = MACB_RX_BUFFER_SIZE;
+ } else {
+ bp->rx_buffer_size = GEM_RX_BUFFER_SIZE;
+
+ if (bp->rx_buffer_size > PAGE_SIZE) {
+ netdev_warn(bp->dev,
+ "RX buffer cannot be bigger than PAGE_SIZE, shrinking\n");
+ bp->rx_buffer_size = PAGE_SIZE;
+ }
+ if (bp->rx_buffer_size % RX_BUFFER_MULTIPLE) {
+ netdev_warn(bp->dev,
+ "RX buffer must be multiple of %d bytes, shrinking\n",
+ RX_BUFFER_MULTIPLE);
+ bp->rx_buffer_size =
+ rounddown(bp->rx_buffer_size, RX_BUFFER_MULTIPLE);
+ }
+ bp->rx_buffer_size = max(RX_BUFFER_MULTIPLE, GEM_RX_BUFFER_SIZE);
+ }
+
+ bp->rx_buffers_per_page = PAGE_SIZE / bp->rx_buffer_size;
+}
+
static void macb_free_rings(struct macb *bp)
{
int i;
- for (i = 0; i < RX_RING_PAGES; i++) {
+ for (i = 0; i < rx_ring_pages(bp); i++) {
struct macb_rx_page *rx_page = &bp->rx_page[i];
if (!rx_page->page)
@@ -989,7 +1019,10 @@ static int macb_init_rings(struct macb *bp)
"Allocated TX ring of %d bytes at 0x%08lx (mapped %p)\n",
TX_RING_BYTES, (unsigned long)bp->tx_ring_dma, bp->tx_ring);
- bp->rx_page = kcalloc(RX_RING_PAGES, sizeof(struct macb_rx_page),
+ /* RX buffers initialization */
+ macb_init_rx_buffer_size(bp);
+
+ bp->rx_page = kcalloc(rx_ring_pages(bp), sizeof(struct macb_rx_page),
GFP_KERNEL);
if (!bp->rx_page)
goto err_alloc_rx_page;
@@ -999,7 +1032,7 @@ static int macb_init_rings(struct macb *bp)
if (!bp->tx_skb)
goto err_alloc_tx_skb;
- for (page_idx = 0, ring_idx = 0; page_idx < RX_RING_PAGES; page_idx++) {
+ for (page_idx = 0, ring_idx = 0; page_idx < rx_ring_pages(bp); page_idx++) {
page = alloc_page(GFP_KERNEL);
if (!page)
goto err_alloc_page;
@@ -1012,16 +1045,16 @@ static int macb_init_rings(struct macb *bp)
bp->rx_page[page_idx].page = page;
bp->rx_page[page_idx].phys = phys;
- for (i = 0; i < RX_BUFFERS_PER_PAGE; i++, ring_idx++) {
+ for (i = 0; i < bp->rx_buffers_per_page; i++, ring_idx++) {
bp->rx_ring[ring_idx].addr = phys;
bp->rx_ring[ring_idx].ctrl = 0;
- phys += RX_BUFFER_SIZE;
+ phys += bp->rx_buffer_size;
}
}
bp->rx_ring[RX_RING_SIZE - 1].addr |= MACB_BIT(RX_WRAP);
- netdev_dbg(bp->dev, "Allocated %u RX buffers (%lu pages)\n",
- RX_RING_SIZE, RX_RING_PAGES);
+ netdev_dbg(bp->dev, "Allocated %u RX buffers of size %u (%u pages)\n",
+ RX_RING_SIZE, bp->rx_buffer_size, rx_ring_pages(bp));
for (i = 0; i < TX_RING_SIZE; i++) {
bp->tx_ring[i].addr = 0;
@@ -1134,7 +1167,7 @@ static void macb_configure_dma(struct macb *bp)
if (macb_is_gem(bp)) {
dmacfg = gem_readl(bp, DMACFG) & ~GEM_BF(RXBS, -1L);
- dmacfg |= GEM_BF(RXBS, RX_BUFFER_SIZE / 64);
+ dmacfg |= GEM_BF(RXBS, bp->rx_buffer_size / RX_BUFFER_MULTIPLE);
dmacfg |= GEM_BF(FBLDO, 16);
dmacfg |= GEM_BIT(TXPBMS) | GEM_BF(RXBMS, -1L);
gem_writel(bp, DMACFG, dmacfg);
diff --git a/drivers/net/ethernet/cadence/macb.h b/drivers/net/ethernet/cadence/macb.h
index b4c9515..88780e2 100644
--- a/drivers/net/ethernet/cadence/macb.h
+++ b/drivers/net/ethernet/cadence/macb.h
@@ -562,6 +562,8 @@ struct macb {
struct macb_dma_desc *rx_ring;
struct macb_rx_page *rx_page;
void *rx_buffers;
+ size_t rx_buffer_size;
+ unsigned int rx_buffers_per_page;
unsigned int tx_head, tx_tail;
struct macb_dma_desc *tx_ring;
--
1.8.0
^ permalink raw reply related
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox