* Re: Loopback performance from kernel 2.6.12 to 2.6.37
From: Eric Dumazet @ 2010-11-09 6:42 UTC (permalink / raw)
To: Andrew Hendry; +Cc: Jesper Dangaard Brouer, netdev
In-Reply-To: <1289284715.2790.87.camel@edumazet-laptop>
Le mardi 09 novembre 2010 à 07:38 +0100, Eric Dumazet a écrit :
> Hmm, your clock source is HPET, that might explain the problem on a
> scheduler intensive workload.
>
And if a packet sniffer (dhclient for example) makes all packets being
timestamped, it also can explain a slowdown, even if there is no
scheduler artifacts.
cat /proc/net/packet
> My HP dev machine
> # grep . /sys/devices/system/clocksource/clocksource0/*
> /sys/devices/system/clocksource/clocksource0/available_clocksource:tsc hpet acpi_pm
> /sys/devices/system/clocksource/clocksource0/current_clocksource:tsc
>
> My laptop:
> $ grep . /sys/devices/system/clocksource/clocksource0/*
> /sys/devices/system/clocksource/clocksource0/available_clocksource:tsc hpet acpi_pm
> /sys/devices/system/clocksource/clocksource0/current_clocksource:tsc
>
^ permalink raw reply
* Re: [PATCH] Fix CAN info leak/minor heap overflow
From: Oliver Hartkopp @ 2010-11-09 7:52 UTC (permalink / raw)
To: David Miller
Cc: Urs Thuermann, netdev, Dan Rosenberg, security, Linus Torvalds
In-Reply-To: <ygfiq0bsjry.fsf@janus.isnogud.escape.de>
On 05.11.2010 19:33, Urs Thuermann wrote:
> This patch removes the leakage of kernel space addresses to userspace.
> Instead, socket inode numbers are used to create unique proc file
> names for CAN_BCM sockets and for referring to sockets in filter
> lists. In addition, this makes debugging easier, since inode numbers
> are also shown in ls -l /proc/<pid>/fd/<fd> and lsof(8) output.
>
> BTW, if kernel space addresses are considered security critical
> information one should also take a look and possibly change
>
> /proc/net/{tcp,tcp6,udp,udp6,raw,raw6,unix}
>
> and maybe some others.
>
> The change of the procfs content leads to a new version string
> 20101105.
>
> Signed-off-by: Urs Thuermann <urs@isnogud.escape.de>
> Signed-off-by: Oliver Hartkopp <socketcan@hartkopp.net>
Besides the ongoing(?) discussion about the exposed kernel addresses in procfs
- what are your plans about this patch that already moves the kernel addresses
to inode numbers?
Is it something for net-2.6 / net-next-2.6 / stable ?
Especially in this case we do not see any problems with userspace tools that
could break as it would be for some other /proc/net entries.
Once this patch is applied (and the procfs layout is changed anyway), i'd also
like to send a patch from my backlog that would extend the procfs output for
can-bcm with an additional drop counter.
Best regards,
Oliver
> CC: Dan Rosenberg <drosenberg@vsecurity.com>
> CC: Linus Torvalds <torvalds@linux-foundation.org>
>
> ---
>
> diff --git a/include/linux/can/core.h b/include/linux/can/core.h
> index 6c507be..e20a841 100644
> --- a/include/linux/can/core.h
> +++ b/include/linux/can/core.h
> @@ -19,7 +19,7 @@
> #include <linux/skbuff.h>
> #include <linux/netdevice.h>
>
> -#define CAN_VERSION "20090105"
> +#define CAN_VERSION "20101105"
>
> /* increment this number each time you change some user-space interface */
> #define CAN_ABI_VERSION "8"
> diff --git a/net/can/bcm.c b/net/can/bcm.c
> index 08ffe9e..0e81e04 100644
> --- a/net/can/bcm.c
> +++ b/net/can/bcm.c
> @@ -86,6 +86,12 @@ MODULE_LICENSE("Dual BSD/GPL");
> MODULE_AUTHOR("Oliver Hartkopp <oliver.hartkopp@volkswagen.de>");
> MODULE_ALIAS("can-proto-2");
>
> +/*
> + * Point to the sockets inode number inside the bcm ident string.
> + * We skip the string length of "bcm " (== 4) created in bcm_init().
> + */
> +#define INODENUM(bo) (bo->ident + 4)
> +
> /* easy access to can_frame payload */
> static inline u64 GET_U64(const struct can_frame *cp)
> {
> @@ -125,7 +131,7 @@ struct bcm_sock {
> struct list_head tx_ops;
> unsigned long dropped_usr_msgs;
> struct proc_dir_entry *bcm_proc_read;
> - char procname [9]; /* pointer printed in ASCII with \0 */
> + char ident[32];
> };
>
> static inline struct bcm_sock *bcm_sk(const struct sock *sk)
> @@ -165,9 +171,7 @@ static int bcm_proc_show(struct seq_file *m, void *v)
> struct bcm_sock *bo = bcm_sk(sk);
> struct bcm_op *op;
>
> - seq_printf(m, ">>> socket %p", sk->sk_socket);
> - seq_printf(m, " / sk %p", sk);
> - seq_printf(m, " / bo %p", bo);
> + seq_printf(m, ">>> socket inode %s", INODENUM(bo));
> seq_printf(m, " / dropped %lu", bo->dropped_usr_msgs);
> seq_printf(m, " / bound %s", bcm_proc_getifname(ifname, bo->ifindex));
> seq_printf(m, " <<<\n");
> @@ -1168,7 +1172,7 @@ static int bcm_rx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg,
> err = can_rx_register(dev, op->can_id,
> REGMASK(op->can_id),
> bcm_rx_handler, op,
> - "bcm");
> + bo->ident);
>
> op->rx_reg_dev = dev;
> dev_put(dev);
> @@ -1177,7 +1181,7 @@ static int bcm_rx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg,
> } else
> err = can_rx_register(NULL, op->can_id,
> REGMASK(op->can_id),
> - bcm_rx_handler, op, "bcm");
> + bcm_rx_handler, op, bo->ident);
> if (err) {
> /* this bcm rx op is broken -> remove it */
> list_del(&op->list);
> @@ -1402,6 +1406,8 @@ static int bcm_init(struct sock *sk)
> {
> struct bcm_sock *bo = bcm_sk(sk);
>
> + snprintf(bo->ident, sizeof(bo->ident), "bcm %lu", sock_i_ino(sk));
> +
> bo->bound = 0;
> bo->ifindex = 0;
> bo->dropped_usr_msgs = 0;
> @@ -1466,7 +1472,7 @@ static int bcm_release(struct socket *sock)
>
> /* remove procfs entry */
> if (proc_dir && bo->bcm_proc_read)
> - remove_proc_entry(bo->procname, proc_dir);
> + remove_proc_entry(INODENUM(bo), proc_dir);
>
> /* remove device reference */
> if (bo->bound) {
> @@ -1519,13 +1525,11 @@ static int bcm_connect(struct socket *sock, struct sockaddr *uaddr, int len,
>
> bo->bound = 1;
>
> - if (proc_dir) {
> - /* unique socket address as filename */
> - sprintf(bo->procname, "%p", sock);
> - bo->bcm_proc_read = proc_create_data(bo->procname, 0644,
> + /* use unique socket inode number as filename */
> + if (proc_dir)
> + bo->bcm_proc_read = proc_create_data(INODENUM(bo), 0644,
> proc_dir,
> &bcm_proc_fops, sk);
> - }
>
> return 0;
> }
> diff --git a/net/can/proc.c b/net/can/proc.c
> index f4265cc..15bed1c 100644
> --- a/net/can/proc.c
> +++ b/net/can/proc.c
> @@ -204,23 +204,17 @@ static void can_print_rcvlist(struct seq_file *m, struct hlist_head *rx_list,
>
> hlist_for_each_entry_rcu(r, n, rx_list, list) {
> char *fmt = (r->can_id & CAN_EFF_FLAG)?
> - " %-5s %08X %08x %08x %08x %8ld %s\n" :
> - " %-5s %03X %08x %08lx %08lx %8ld %s\n";
> + " %-5s %08X %08x %8ld %s\n" :
> + " %-5s %03X %08x %8ld %s\n";
>
> seq_printf(m, fmt, DNAME(dev), r->can_id, r->mask,
> - (unsigned long)r->func, (unsigned long)r->data,
> r->matches, r->ident);
> }
> }
>
> static void can_print_recv_banner(struct seq_file *m)
> {
> - /*
> - * can1. 00000000 00000000 00000000
> - * ....... 0 tp20
> - */
> - seq_puts(m, " device can_id can_mask function"
> - " userdata matches ident\n");
> + seq_puts(m, " device can_id can_mask matches ident\n");
> }
>
> static int can_stats_proc_show(struct seq_file *m, void *v)
> diff --git a/net/can/raw.c b/net/can/raw.c
> index e88f610..e057f0d 100644
> --- a/net/can/raw.c
> +++ b/net/can/raw.c
> @@ -88,6 +88,7 @@ struct raw_sock {
> struct can_filter dfilter; /* default/single filter */
> struct can_filter *filter; /* pointer to filter(s) */
> can_err_mask_t err_mask;
> + char ident[32];
> };
>
> /*
> @@ -154,13 +155,14 @@ static void raw_rcv(struct sk_buff *oskb, void *data)
> static int raw_enable_filters(struct net_device *dev, struct sock *sk,
> struct can_filter *filter, int count)
> {
> + struct raw_sock *ro = raw_sk(sk);
> int err = 0;
> int i;
>
> for (i = 0; i < count; i++) {
> err = can_rx_register(dev, filter[i].can_id,
> filter[i].can_mask,
> - raw_rcv, sk, "raw");
> + raw_rcv, sk, ro->ident);
> if (err) {
> /* clean up successfully registered filters */
> while (--i >= 0)
> @@ -177,11 +179,12 @@ static int raw_enable_filters(struct net_device *dev, struct sock *sk,
> static int raw_enable_errfilter(struct net_device *dev, struct sock *sk,
> can_err_mask_t err_mask)
> {
> + struct raw_sock *ro = raw_sk(sk);
> int err = 0;
>
> if (err_mask)
> err = can_rx_register(dev, 0, err_mask | CAN_ERR_FLAG,
> - raw_rcv, sk, "raw");
> + raw_rcv, sk, ro->ident);
>
> return err;
> }
> @@ -281,6 +284,8 @@ static int raw_init(struct sock *sk)
> {
> struct raw_sock *ro = raw_sk(sk);
>
> + snprintf(ro->ident, sizeof(ro->ident), "raw %lu", sock_i_ino(sk));
> +
> ro->bound = 0;
> ro->ifindex = 0;
>
^ permalink raw reply
* [e1000e] BUG triggered when triggering LED blinking
From: Holger Eitzenberger @ 2010-11-09 8:39 UTC (permalink / raw)
To: e1000-devel; +Cc: netdev
[-- Attachment #1: Type: text/plain, Size: 2673 bytes --]
Hi,
using e1000e driver version 1.2.10 and kernel version 2.6.32.24 I see
the kernel go BUG() sporadically at the time 'ethtool -p eth0 3' comes
back.
Network hardware is four times 'Intel Corporation 82583V Gigabit Network
Connection' (0x8086:0x150c) on Atom N450.
kernel BUG at kernel/workqueue.c:287!
invalid opcode: 0000 [#1] SMP
last sysfs file:
/sys/devices/pci0000:00/0000:00:1d.0/usb2/2-1/2-1:1.1/input/input2/event2/dev
Modules linked in: nls_utf8 isofs edd ide_cd_mod sr_mod cdrom sg sd_mod
pata_acpi ata_generic usb_storage ppdev ide_pci_generic ata_piix libata
evdev rtc_cmos uhci_hcd parport_pc scsi_mod i2c_i801 ehci_hcd rtc_core
rtc_lib e1000e parport ftdi_sio usbhid usbserial
Pid: 8, comm: events/1 Not tainted (2.6.32.24-62.gce8dff6-ai #1) To Be
Filled By O.E.M.
EIP: 0060:[<c102ed4f>] EFLAGS: 00010206 CPU: 1
EIP is at worker_thread+0xc5/0x144
EAX: c1c052e0 EBX: c1d052e0 ECX: f70cac1c EDX: f70cac1c
ESI: f81c75b0 EDI: f70cac18 EBP: f705e3b0 ESP: f7093f90
DS: 007b ES: 007b FS: 00d8 GS: 0000 SS: 0068
Process events/1 (pid: 8, ti=f7092000 task=f705e3b0 task.ti=f7092000)
Stack:
f705e5a0 c1d052ec c1d052e4 00000000 f705e3b0 c103151e f7093fa8 f7093fa8
<0> f7061f68 c1d052e0 c102ec8a 00000000 c103132b 00000000 00000000
00000000
<0> f7093fd0 f7093fd0 c10312ca 00000000 00000000 c100329f f7061f5c
00000000
Call Trace:
[<c103151e>] ? autoremove_wake_function+0x0/0x2d
[<c102ec8a>] ? worker_thread+0x0/0x144
[<c103132b>] ? kthread+0x61/0x66
[<c10312ca>] ? kthread+0x0/0x66
[<c100329f>] ? kernel_thread_helper+0x7/0x10
Code: e9 85 00 00 00 8d 79 fc 8b 77 0c 89 7b 18 8b 11 8b 41 04 89 42 04
89 10 89 09 89 49 04 f0 fe 03 fb 8b 41 fc 83 e0 fc 39 c3 74 04 <0f> 0b
eb fe f0 80 61 fc fe 89 f8 ff d6 89 e0 25 00 e0 ff ff 8b
EIP: [<c102ed4f>] worker_thread+0xc5/0x144 SS:ESP 0068:f7093f90
---[ end trace e297b781eb382c2f ]---
The full trace is attached, it may become clearer from that.
After taking a look I think this may be caused by initializing
adapter->led_blink_task several times in e1000_phys_id(), while possibly
led_blink_task is running:
if ((hw->phy.type == e1000_phy_ife) ||
(hw->mac.type == e1000_pchlan) ||
(hw->mac.type == e1000_82574)) {
INIT_WORK(&adapter->led_blink_task, e1000e_led_blink_task);
if (!adapter->blink_timer.function) {
I can't reproduce it after moving it inside the following if block,
but I'm not quite sure if this catches all races in there. Especially
the msleep_interruptible() may be too optimistic because it may
actually not wait long enough. Someone with more knowledge of the
driver should take a look.
I've attached a proposed fix for the double initialization, please check.
/holger
[-- Warning: decoded text below may be mangled, UTF-8 assumed --]
[-- Attachment #2: putty.log --]
[-- Type: text/plain; charset=unknown-8bit, Size: 4366 bytes --]
=~=~=~=~=~=~=~=~=~=~=~= PuTTY log 2010.11.03 16:51:28 =~=~=~=~=~=~=~=~=~=~=~=
ÿ------------[ cut here ]------------
kernel BUG at kernel/workqueue.c:287!
invalid opcode: 0000 [#1] SMP
last sysfs file: /sys/devices/pci0000:00/0000:00:1d.0/usb2/2-1/2-1:1.1/input/input2/event2/dev
Modules linked in: nls_utf8 isofs edd ide_cd_mod sr_mod cdrom sg sd_mod pata_acpi ata_generic usb_storage ppdev ide_pci_generic ata_piix libata evdev rtc_cmos uhci_hcd parport_pc scsi_mod i2c_i801 ehci_hcd rtc_core rtc_lib e1000e parport ftdi_sio usbhid usbserial
Pid: 8, comm: events/1 Not tainted (2.6.32.24-62.gce8dff6-ai #1) To Be Filled By O.E.M.
EIP: 0060:[<c102ed4f>] EFLAGS: 00010206 CPU: 1
EIP is at worker_thread+0xc5/0x144
EAX: c1c052e0 EBX: c1d052e0 ECX: f70cac1c EDX: f70cac1c
ESI: f81c75b0 EDI: f70cac18 EBP: f705e3b0 ESP: f7093f90
DS: 007b ES: 007b FS: 00d8 GS: 0000 SS: 0068
Process events/1 (pid: 8, ti=f7092000 task=f705e3b0 task.ti=f7092000)
Stack:
f705e5a0 c1d052ec c1d052e4 00000000 f705e3b0 c103151e f7093fa8 f7093fa8
<0> f7061f68 c1d052e0 c102ec8a 00000000 c103132b 00000000 00000000 00000000
<0> f7093fd0 f7093fd0 c10312ca 00000000 00000000 c100329f f7061f5c 00000000
Call Trace:
[<c103151e>] ? autoremove_wake_function+0x0/0x2d
[<c102ec8a>] ? worker_thread+0x0/0x144
[<c103132b>] ? kthread+0x61/0x66
[<c10312ca>] ? kthread+0x0/0x66
[<c100329f>] ? kernel_thread_helper+0x7/0x10
Code: e9 85 00 00 00 8d 79 fc 8b 77 0c 89 7b 18 8b 11 8b 41 04 89 42 04 89 10 89 09 89 49 04 f0 fe 03 fb 8b 41 fc 83 e0 fc 39 c3 74 04 <0f> 0b eb fe f0 80 61 fc fe 89 f8 ff d6 89 e0 25 00 e0 ff ff 8b
EIP: [<c102ed4f>] worker_thread+0xc5/0x144 SS:ESP 0068:f7093f90
---[ end trace e297b781eb382c2f ]---
------------[ cut here ]------------
kernel BUG at kernel/workqueue.c:191!
invalid opcode: 0000 [#2] SMP
last sysfs file: /sys/devices/pci0000:00/0000:00:1d.0/usb2/2-1/2-1:1.1/input/input2/event2/dev
Modules linked in: nls_utf8 isofs edd ide_cd_mod sr_mod cdrom sg sd_mod pata_acpi ata_generic usb_storage ppdev ide_pci_generic ata_piix libata evdev rtc_cmos uhci_hcd parport_pc scsi_mod i2c_i801 ehci_hcd rtc_core rtc_lib e1000e parport ftdi_sio usbhid usbserial
Pid: 1012, comm: klogd Tainted: G D (2.6.32.24-62.gce8dff6-ai #1) To Be Filled By O.E.M.
EIP: 0060:[<c102eeac>] EFLAGS: 00010283 CPU: 0
EIP is at queue_work_on+0x1b/0x44
EAX: f70cac1c EBX: 00000000 ECX: f70cac18 EDX: 00000000
ESI: f7001280 EDI: f81c7920 EBP: f71dbf60 ESP: f71dbf3c
DS: 007b ES: 007b FS: 00d8 GS: 0033 SS: 0068
Process klogd (pid: 1012, ti=f71da000 task=f71d87a0 task.ti=f71da000)
Stack:
f70c8330 c133ca00 f81c7931 00000100 c1029710 c133d810 c133d610 c133d410
<0> c133d210 f71dbf60 f71dbf60 00000001 00000004 00000100 00000141 c102652e
<0> c1318010 0000000a 00000000 00000046 00000000 099251d0 bfb6e968 c10265be
Call Trace:
[<f81c7931>] ? e1000e_set_ethtool_ops+0x1d1/0x38b0 [e1000e]
[<c1029710>] ? run_timer_softirq+0x116/0x16a
[<c102652e>] ? __do_softirq+0x78/0xe5
[<c10265be>] ? do_softirq+0x23/0x27
[<c102668d>] ? irq_exit+0x26/0x58
[<c100f9ea>] ? smp_apic_timer_interrupt+0x6c/0x76
[<c10030f6>] ? apic_timer_interrupt+0x2a/0x30
Code: 2c c1 8b 00 03 04 8d c0 bb 2c c1 e9 3d ff ff ff 56 89 d6 53 89 c3 f0 0f ba 29 00 19 c0 31 d2 85 c0 75 2c 8d 41 04 39 41 04 74 04 <0f> 0b eb fe 83 7e 10 00 89 ca 0f 45 1d b4 bc 2c c1 8b 06 03 04
EIP: [<c102eeac>] queue_work_on+0x1b/0x44 SS:ESP 0068:f71dbf3c
---[ end trace e297b781eb382c30 ]---
Kernel panic - not syncing: Fatal exception in interrupt
Pid: 1012, comm: klogd Tainted: G D 2.6.32.24-62.gce8dff6-ai #1
Call Trace:
[<c11e0a50>] ? panic+0x38/0xda
[<c11e3371>] ? oops_end+0x89/0x94
[<c1003628>] ? do_invalid_op+0x0/0x70
[<c100368f>] ? do_invalid_op+0x67/0x70
[<c102eeac>] ? queue_work_on+0x1b/0x44
[<c117bfb3>] ? sys_sendto+0xfc/0x127
[<c101c3cc>] ? dequeue_task_fair+0x3f/0x1bc
[<c1018e0b>] ? sched_slice+0x6d/0x79
[<c11e2ac6>] ? error_code+0x66/0x6c
[<f81c7920>] ? e1000e_set_ethtool_ops+0x1c0/0x38b0 [e1000e]
[<c1003628>] ? do_invalid_op+0x0/0x70
[<c102eeac>] ? queue_work_on+0x1b/0x44
[<f81c7931>] ? e1000e_set_ethtool_ops+0x1d1/0x38b0 [e1000e]
[<c1029710>] ? run_timer_softirq+0x116/0x16a
[<c102652e>] ? __do_softirq+0x78/0xe5
[<c10265be>] ? do_softirq+0x23/0x27
[<c102668d>] ? irq_exit+0x26/0x58
[<c100f9ea>] ? smp_apic_timer_interrupt+0x6c/0x76
[<c10030f6>] ? apic_timer_interrupt+0x2a/0x30
[-- Attachment #3: e1000e-fix.diff --]
[-- Type: text/x-diff, Size: 708 bytes --]
Index: linux-2.6.32.y/drivers/net/e1000e/ethtool.c
===================================================================
--- linux-2.6.32.y.orig/drivers/net/e1000e/ethtool.c 2010-11-08 15:34:35.000000000 +0100
+++ linux-2.6.32.y/drivers/net/e1000e/ethtool.c 2010-11-08 17:32:27.000000000 +0100
@@ -1833,8 +1833,8 @@
if ((hw->phy.type == e1000_phy_ife) ||
(hw->mac.type == e1000_pchlan) ||
(hw->mac.type == e1000_82574)) {
- INIT_WORK(&adapter->led_blink_task, e1000e_led_blink_task);
if (!adapter->blink_timer.function) {
+ INIT_WORK(&adapter->led_blink_task, e1000e_led_blink_task);
init_timer(&adapter->blink_timer);
adapter->blink_timer.function =
e1000_led_blink_callback;
^ permalink raw reply
* [PATCH v15 00/17] Provide a zero-copy method on KVM virtio-net.
From: xiaohui.xin @ 2010-11-09 9:03 UTC (permalink / raw)
To: netdev, kvm, linux-kernel, mst, mingo, davem, herbert, jdike
We provide an zero-copy method which driver side may get external
buffers to DMA. Here external means driver don't use kernel space
to allocate skb buffers. Currently the external buffer can be from
guest virtio-net driver.
The idea is simple, just to pin the guest VM user space and then
let host NIC driver has the chance to directly DMA to it.
The patches are based on vhost-net backend driver. We add a device
which provides proto_ops as sendmsg/recvmsg to vhost-net to
send/recv directly to/from the NIC driver. KVM guest who use the
vhost-net backend may bind any ethX interface in the host side to
get copyless data transfer thru guest virtio-net frontend.
patch 01-11: net core and kernel changes.
patch 12-14: new device as interface to mantpulate external buffers.
patch 15: for vhost-net.
patch 16: An example on modifying NIC driver to using napi_gro_frags().
patch 17: An example how to get guest buffers based on driver
who using napi_gro_frags().
The guest virtio-net driver submits multiple requests thru vhost-net
backend driver to the kernel. And the requests are queued and then
completed after corresponding actions in h/w are done.
For read, user space buffers are dispensed to NIC driver for rx when
a page constructor API is invoked. Means NICs can allocate user buffers
from a page constructor. We add a hook in netif_receive_skb() function
to intercept the incoming packets, and notify the zero-copy device.
For write, the zero-copy deivce may allocates a new host skb and puts
payload on the skb_shinfo(skb)->frags, and copied the header to skb->data.
The request remains pending until the skb is transmitted by h/w.
We provide multiple submits and asynchronous notifiicaton to
vhost-net too.
Our goal is to improve the bandwidth and reduce the CPU usage.
Exact performance data will be provided later.
What we have not done yet:
Performance tuning
what we have done in v1:
polish the RCU usage
deal with write logging in asynchroush mode in vhost
add notifier block for mp device
rename page_ctor to mp_port in netdevice.h to make it looks generic
add mp_dev_change_flags() for mp device to change NIC state
add CONIFG_VHOST_MPASSTHRU to limit the usage when module is not load
a small fix for missing dev_put when fail
using dynamic minor instead of static minor number
a __KERNEL__ protect to mp_get_sock()
what we have done in v2:
remove most of the RCU usage, since the ctor pointer is only
changed by BIND/UNBIND ioctl, and during that time, NIC will be
stopped to get good cleanup(all outstanding requests are finished),
so the ctor pointer cannot be raced into wrong situation.
Remove the struct vhost_notifier with struct kiocb.
Let vhost-net backend to alloc/free the kiocb and transfer them
via sendmsg/recvmsg.
use get_user_pages_fast() and set_page_dirty_lock() when read.
Add some comments for netdev_mp_port_prep() and handle_mpassthru().
what we have done in v3:
the async write logging is rewritten
a drafted synchronous write function for qemu live migration
a limit for locked pages from get_user_pages_fast() to prevent Dos
by using RLIMIT_MEMLOCK
what we have done in v4:
add iocb completion callback from vhost-net to queue iocb in mp device
replace vq->receiver by mp_sock_data_ready()
remove stuff in mp device which access structures from vhost-net
modify skb_reserve() to ignore host NIC driver reserved space
rebase to the latest vhost tree
split large patches into small pieces, especially for net core part.
what we have done in v5:
address Arnd Bergmann's comments
-remove IFF_MPASSTHRU_EXCL flag in mp device
-Add CONFIG_COMPAT macro
-remove mp_release ops
move dev_is_mpassthru() as inline func
fix a bug in memory relinquish
Apply to current git (2.6.34-rc6) tree.
what we have done in v6:
move create_iocb() out of page_dtor which may happen in interrupt context
-This remove the potential issues which lock called in interrupt context
make the cache used by mp, vhost as static, and created/destoryed during
modules init/exit functions.
-This makes multiple mp guest created at the same time.
what we have done in v7:
some cleanup prepared to suppprt PS mode
what we have done in v8:
discarding the modifications to point skb->data to guest buffer directly.
Add code to modify driver to support napi_gro_frags() with Herbert's comments.
To support PS mode.
Add mergeable buffer support in mp device.
Add GSO/GRO support in mp deice.
Address comments from Eric Dumazet about cache line and rcu usage.
what we have done in v9:
v8 patch is based on a fix in dev_gro_receive().
But Herbert did not agree with the fix we have sent out.
And he suggest another fix. v9 is modified to base on that fix.
what we have done in v10:
Fix a partial csum error.
Cleanup some unused fields with struct page_info{} in mp device.
Modify kmem_cache_zalloc() to kmem_cache_alloc() based on Michael S. Thirkin.
what we have done in v11:
Address comments from Michael S. Thirkin to add two new ioctls in mp device.
But still need to revise.
what we have done in v12:
Address most comments from Ben Hutchings, except the compat ioctls.
As the comments are sparse, so do not make a split patch.
Change struct mpassthru_port to struct mp_port, and struct page_ctor
to struct page_pool.
what we have done in v13:
Export functions to other drivers like macvtap, in case it want to reuse it to
get zero-copy.
Rebase on 2.6.36-rc7.
what we have done in v14:
Address the comments from David Miller for bonding device issue.
Currently, we treat it in two cases. One case is that bonding is created before
zero-copy mode is enabled for a device. The code will check if all the slaves are
capable of zero-copy. If yes, it will force all the slaves in zero-copy mode.
If not, fails zero-copy. The other case is that zero-copy is enabled before bonding
is created, just fail bonding.
what we have done in v15:
Address comments from Eric Dumazet about how to clear destructor_arg field of shinfo.
Performance:
We have seen the performance data request from mailling-list.
And we are now looking into this.
^ permalink raw reply
* [PATCH v15 01/17] Add a new structure for skb buffer from external.
From: xiaohui.xin @ 2010-11-09 9:03 UTC (permalink / raw)
To: netdev, kvm, linux-kernel, mst, mingo, davem, herbert, jdike; +Cc: Xin Xiaohui
In-Reply-To: <1289293402-4791-1-git-send-email-xiaohui.xin@intel.com>
From: Xin Xiaohui <xiaohui.xin@intel.com>
Signed-off-by: Xin Xiaohui <xiaohui.xin@intel.com>
Signed-off-by: Zhao Yu <yzhao81new@gmail.com>
Reviewed-by: Jeff Dike <jdike@linux.intel.com>
---
include/linux/skbuff.h | 9 +++++++++
1 files changed, 9 insertions(+), 0 deletions(-)
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 77eb60d..696e690 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -211,6 +211,15 @@ struct skb_shared_info {
skb_frag_t frags[MAX_SKB_FRAGS];
};
+/* The structure is for a skb which pages may point to
+ * an external buffer, which is not allocated from kernel space.
+ * It also contains a destructor for itself.
+ */
+struct skb_ext_page {
+ struct page *page;
+ void (*dtor)(struct skb_ext_page *);
+};
+
/* We divide dataref into two halves. The higher 16 bits hold references
* to the payload part of skb->data. The lower 16 bits hold references to
* the entire skb->data. A clone of a headerless skb holds the length of
--
1.7.3
^ permalink raw reply related
* [PATCH v15 03/17]Add a ndo_mp_port_prep pointer to net_device_ops.
From: xiaohui.xin @ 2010-11-09 9:03 UTC (permalink / raw)
To: netdev, kvm, linux-kernel, mst, mingo, davem, herbert, jdike; +Cc: Xin Xiaohui
In-Reply-To: <fc6e95d63a2c62aaf77f8ded22fc43ccefcdbbff.1289280885.git.xiaohui.xin@intel.com>
From: Xin Xiaohui <xiaohui.xin@intel.com>
If the driver want to allocate external buffers,
then it can export it's capability, as the skb
buffer header length, the page length can be DMA, etc.
The external buffers owner may utilize this.
Signed-off-by: Xin Xiaohui <xiaohui.xin@intel.com>
Signed-off-by: Zhao Yu <yzhao81new@gmail.com>
Reviewed-by: Jeff Dike <jdike@linux.intel.com>
---
include/linux/netdevice.h | 10 ++++++++++
1 files changed, 10 insertions(+), 0 deletions(-)
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index f6b1870..575777f 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -723,6 +723,12 @@ struct netdev_rx_queue {
* int (*ndo_set_vf_port)(struct net_device *dev, int vf,
* struct nlattr *port[]);
* int (*ndo_get_vf_port)(struct net_device *dev, int vf, struct sk_buff *skb);
+ *
+ * int (*ndo_mp_port_prep)(struct net_device *dev, struct mp_port *port);
+ * If the driver want to allocate external buffers,
+ * then it can export it's capability, as the skb
+ * buffer header length, the page length can be DMA, etc.
+ * The external buffers owner may utilize this.
*/
#define HAVE_NET_DEVICE_OPS
struct net_device_ops {
@@ -795,6 +801,10 @@ struct net_device_ops {
int (*ndo_fcoe_get_wwn)(struct net_device *dev,
u64 *wwn, int type);
#endif
+#if defined(CONFIG_MEDIATE_PASSTHRU) || defined(CONFIG_MEDIATE_PASSTHRU_MODULE)
+ int (*ndo_mp_port_prep)(struct net_device *dev,
+ struct mp_port *port);
+#endif
};
/*
--
1.7.3
^ permalink raw reply related
* [PATCH v15 04/17]Add a function make external buffer owner to query capability.
From: xiaohui.xin @ 2010-11-09 9:03 UTC (permalink / raw)
To: netdev, kvm, linux-kernel, mst, mingo, davem, herbert, jdike; +Cc: Xin Xiaohui
In-Reply-To: <fc6e95d63a2c62aaf77f8ded22fc43ccefcdbbff.1289280885.git.xiaohui.xin@intel.com>
From: Xin Xiaohui <xiaohui.xin@intel.com>
The external buffer owner can use the functions to get
the capability of the underlying NIC driver.
Signed-off-by: Xin Xiaohui <xiaohui.xin@intel.com>
Signed-off-by: Zhao Yu <yzhaonew@gmail.com>
Reviewed-by: Jeff Dike <jdike@linux.intel.com>
---
include/linux/netdevice.h | 2 ++
net/core/dev.c | 41 +++++++++++++++++++++++++++++++++++++++++
2 files changed, 43 insertions(+), 0 deletions(-)
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 575777f..8dcf6de 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -1736,6 +1736,8 @@ extern gro_result_t napi_frags_finish(struct napi_struct *napi,
gro_result_t ret);
extern struct sk_buff * napi_frags_skb(struct napi_struct *napi);
extern gro_result_t napi_gro_frags(struct napi_struct *napi);
+extern int netdev_mp_port_prep(struct net_device *dev,
+ struct mp_port *port);
static inline void napi_free_frags(struct napi_struct *napi)
{
diff --git a/net/core/dev.c b/net/core/dev.c
index 660dd41..84fbb83 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -2942,6 +2942,47 @@ out:
return ret;
}
+/* To support meidate passthru(zero-copy) with NIC driver,
+ * we'd better query NIC driver for the capability it can
+ * provide, especially for packet split mode, now we only
+ * query for the header size, and the payload a descriptor
+ * may carry.
+ * Now, it's only called by mpassthru device.
+ */
+#if defined(CONFIG_MEDIATE_PASSTHRU) || defined(CONFIG_MEDIATE_PASSTHRU_MODULE)
+int netdev_mp_port_prep(struct net_device *dev,
+ struct mp_port *port)
+{
+ int rc;
+ int npages, data_len;
+ const struct net_device_ops *ops = dev->netdev_ops;
+
+ if (ops->ndo_mp_port_prep) {
+ rc = ops->ndo_mp_port_prep(dev, port);
+ if (rc)
+ return rc;
+ } else
+ return -EINVAL;
+
+ if (port->hdr_len <= 0)
+ goto err;
+
+ npages = port->npages;
+ data_len = port->data_len;
+ if (npages <= 0 || npages > MAX_SKB_FRAGS ||
+ (data_len < PAGE_SIZE * (npages - 1) ||
+ data_len > PAGE_SIZE * npages))
+ goto err;
+
+ return 0;
+err:
+ dev_warn(&dev->dev, "invalid page constructor parameters\n");
+
+ return -EINVAL;
+}
+EXPORT_SYMBOL(netdev_mp_port_prep);
+#endif
+
/**
* netif_receive_skb - process receive buffer from network
* @skb: buffer to process
--
1.7.3
^ permalink raw reply related
* [PATCH v15 05/17] Add a function to indicate if device use external buffer.
From: xiaohui.xin @ 2010-11-09 9:03 UTC (permalink / raw)
To: netdev, kvm, linux-kernel, mst, mingo, davem, herbert, jdike; +Cc: Xin Xiaohui
In-Reply-To: <fc6e95d63a2c62aaf77f8ded22fc43ccefcdbbff.1289280885.git.xiaohui.xin@intel.com>
From: Xin Xiaohui <xiaohui.xin@intel.com>
Signed-off-by: Xin Xiaohui <xiaohui.xin@intel.com>
Signed-off-by: Zhao Yu <yzhao81new@gmail.com>
Reviewed-by: Jeff Dike <jdike@linux.intel.com>
---
include/linux/netdevice.h | 5 +++++
1 files changed, 5 insertions(+), 0 deletions(-)
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 8dcf6de..f91d9bb 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -1739,6 +1739,11 @@ extern gro_result_t napi_gro_frags(struct napi_struct *napi);
extern int netdev_mp_port_prep(struct net_device *dev,
struct mp_port *port);
+static inline bool dev_is_mpassthru(struct net_device *dev)
+{
+ return dev && dev->mp_port;
+}
+
static inline void napi_free_frags(struct napi_struct *napi)
{
kfree_skb(napi->skb);
--
1.7.3
^ permalink raw reply related
* [PATCH v15 09/17] Don't do skb recycle, if device use external buffer.
From: xiaohui.xin @ 2010-11-09 9:03 UTC (permalink / raw)
To: netdev, kvm, linux-kernel, mst, mingo, davem, herbert, jdike; +Cc: Xin Xiaohui
In-Reply-To: <fc6e95d63a2c62aaf77f8ded22fc43ccefcdbbff.1289280885.git.xiaohui.xin@intel.com>
From: Xin Xiaohui <xiaohui.xin@intel.com>
Signed-off-by: Xin Xiaohui <xiaohui.xin@intel.com>
Signed-off-by: Zhao Yu <yzhao81new@gmail.com>
Reviewed-by: Jeff Dike <jdike@linux.intel.com>
---
net/core/skbuff.c | 6 ++++++
1 files changed, 6 insertions(+), 0 deletions(-)
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 3d81113..075f4c5 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -557,6 +557,12 @@ bool skb_recycle_check(struct sk_buff *skb, int skb_size)
if (skb_shared(skb) || skb_cloned(skb))
return false;
+ /* if the device wants to do mediate passthru, the skb may
+ * get external buffer, so don't recycle
+ */
+ if (dev_is_mpassthru(skb->dev))
+ return 0;
+
skb_release_head_state(skb);
shinfo = skb_shinfo(skb);
--
1.7.3
^ permalink raw reply related
* [PATCH v15 17/17] An example how to alloc user buffer based on napi_gro_frags() interface.
From: xiaohui.xin @ 2010-11-09 9:03 UTC (permalink / raw)
To: netdev, kvm, linux-kernel, mst, mingo, davem, herbert, jdike; +Cc: Xin Xiaohui
In-Reply-To: <fc6e95d63a2c62aaf77f8ded22fc43ccefcdbbff.1289280885.git.xiaohui.xin@intel.com>
From: Xin Xiaohui <xiaohui.xin@intel.com>
This example is made on ixgbe driver which using napi_gro_frags().
It can get buffers from guest side directly using netdev_alloc_page()
and release guest buffers using netdev_free_page().
Signed-off-by: Xin Xiaohui <xiaohui.xin@intel.com>
---
drivers/net/ixgbe/ixgbe_main.c | 37 +++++++++++++++++++++++++++++++++----
1 files changed, 33 insertions(+), 4 deletions(-)
diff --git a/drivers/net/ixgbe/ixgbe_main.c b/drivers/net/ixgbe/ixgbe_main.c
index a4a5263..9f5598b 100644
--- a/drivers/net/ixgbe/ixgbe_main.c
+++ b/drivers/net/ixgbe/ixgbe_main.c
@@ -1032,7 +1032,14 @@ static inline void ixgbe_release_rx_desc(struct ixgbe_hw *hw,
static bool is_rx_buffer_mapped_as_page(struct ixgbe_rx_buffer *bi,
struct net_device *dev)
{
- return true;
+ return dev_is_mpassthru(dev);
+}
+
+static u32 get_page_skb_offset(struct net_device *dev)
+{
+ if (!dev_is_mpassthru(dev))
+ return 0;
+ return dev->mp_port->vnet_hlen;
}
/**
@@ -1105,7 +1112,8 @@ static void ixgbe_alloc_rx_buffers(struct ixgbe_adapter *adapter,
adapter->alloc_rx_page_failed++;
goto no_buffers;
}
- bi->page_skb_offset = 0;
+ bi->page_skb_offset =
+ get_page_skb_offset(adapter->netdev);
bi->dma = dma_map_page(&pdev->dev, bi->page_skb,
bi->page_skb_offset,
(PAGE_SIZE / 2),
@@ -1242,8 +1250,10 @@ static bool ixgbe_clean_rx_irq(struct ixgbe_q_vector *q_vector,
len = le16_to_cpu(rx_desc->wb.upper.length);
}
- if (is_no_buffer(rx_buffer_info))
+ if (is_no_buffer(rx_buffer_info)) {
+ printk("no buffers\n");
break;
+ }
cleaned = true;
if (!rx_buffer_info->mapped_as_page) {
@@ -1299,6 +1309,11 @@ static bool ixgbe_clean_rx_irq(struct ixgbe_q_vector *q_vector,
rx_buffer_info->page_skb,
rx_buffer_info->page_skb_offset,
len);
+ if (dev_is_mpassthru(netdev) &&
+ netdev->mp_port->hash)
+ skb_shinfo(skb)->destructor_arg =
+ netdev->mp_port->hash(netdev,
+ rx_buffer_info->page_skb);
rx_buffer_info->page_skb = NULL;
skb->len += len;
skb->data_len += len;
@@ -1316,7 +1331,8 @@ static bool ixgbe_clean_rx_irq(struct ixgbe_q_vector *q_vector,
upper_len);
if ((rx_ring->rx_buf_len > (PAGE_SIZE / 2)) ||
- (page_count(rx_buffer_info->page) != 1))
+ (page_count(rx_buffer_info->page) != 1) ||
+ dev_is_mpassthru(netdev))
rx_buffer_info->page = NULL;
else
get_page(rx_buffer_info->page);
@@ -6529,6 +6545,16 @@ static void ixgbe_netpoll(struct net_device *netdev)
}
#endif
+#if defined(CONFIG_MEDIATE_PASSTHRU) || defined(CONFIG_MEDIATE_PASSTHRU_MODULE)
+static int ixgbe_ndo_mp_port_prep(struct net_device *dev, struct mp_port *port)
+{
+ port->hdr_len = 128;
+ port->data_len = 2048;
+ port->npages = 1;
+ return 0;
+}
+#endif
+
static const struct net_device_ops ixgbe_netdev_ops = {
.ndo_open = ixgbe_open,
.ndo_stop = ixgbe_close,
@@ -6548,6 +6574,9 @@ static const struct net_device_ops ixgbe_netdev_ops = {
.ndo_set_vf_vlan = ixgbe_ndo_set_vf_vlan,
.ndo_set_vf_tx_rate = ixgbe_ndo_set_vf_bw,
.ndo_get_vf_config = ixgbe_ndo_get_vf_config,
+#if defined(CONFIG_MEDIATE_PASSTHRU) || defined(CONFIG_MEDIATE_PASSTHRU_MODULE)
+ .ndo_mp_port_prep = ixgbe_ndo_mp_port_prep,
+#endif
#ifdef CONFIG_NET_POLL_CONTROLLER
.ndo_poll_controller = ixgbe_netpoll,
#endif
--
1.7.3
^ permalink raw reply related
* [PATCH v15 02/17]Add a new struct for device to manipulate external buffer.
From: xiaohui.xin @ 2010-11-09 9:03 UTC (permalink / raw)
To: netdev, kvm, linux-kernel, mst, mingo, davem, herbert, jdike; +Cc: Xin Xiaohui
In-Reply-To: <fc6e95d63a2c62aaf77f8ded22fc43ccefcdbbff.1289280885.git.xiaohui.xin@intel.com>
From: Xin Xiaohui <xiaohui.xin@intel.com>
Add a structure in structure net_device, the new field is
named as mp_port. It's for mediate passthru (zero-copy).
It contains the capability for the net device driver,
a socket, and an external buffer creator, external means
skb buffer belongs to the device may not be allocated from
kernel space.
Signed-off-by: Xin Xiaohui <xiaohui.xin@intel.com>
Signed-off-by: Zhao Yu <yzhao81new@gmail.com>
Reviewed-by: Jeff Dike <jdike@linux.intel.com>
---
include/linux/netdevice.h | 25 ++++++++++++++++++++++++-
1 files changed, 24 insertions(+), 1 deletions(-)
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 46c36ff..f6b1870 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -325,6 +325,28 @@ enum netdev_state_t {
__LINK_STATE_DORMANT,
};
+/*The structure for mediate passthru(zero-copy). */
+struct mp_port {
+ /* the header len */
+ int hdr_len;
+ /* the max payload len for one descriptor */
+ int data_len;
+ /* the pages for DMA in one time */
+ int npages;
+ /* the socket bind to */
+ struct socket *sock;
+ /* the header len for virtio-net */
+ int vnet_hlen;
+ /* the external buffer page creator */
+ struct skb_ext_page *(*ctor)(struct mp_port *,
+ struct sk_buff *, int);
+ /* the hash function attached to find according
+ * backend ring descriptor info for one external
+ * buffer page.
+ */
+ struct skb_ext_page *(*hash)(struct net_device *,
+ struct page *);
+};
/*
* This structure holds at boot time configured netdevice settings. They
@@ -1045,7 +1067,8 @@ struct net_device {
/* GARP */
struct garp_port *garp_port;
-
+ /* mpassthru */
+ struct mp_port *mp_port;
/* class/net/name entry */
struct device dev;
/* space for optional device, statistics, and wireless sysfs groups */
--
1.7.3
^ permalink raw reply related
* [PATCH v15 06/17] Use callback to deal with skb_release_data() specially.
From: xiaohui.xin @ 2010-11-09 9:03 UTC (permalink / raw)
To: netdev, kvm, linux-kernel, mst, mingo, davem, herbert, jdike; +Cc: Xin Xiaohui
In-Reply-To: <fc6e95d63a2c62aaf77f8ded22fc43ccefcdbbff.1289280885.git.xiaohui.xin@intel.com>
From: Xin Xiaohui <xiaohui.xin@intel.com>
If buffer is external, then use the callback to destruct
buffers.
Signed-off-by: Xin Xiaohui <xiaohui.xin@intel.com>
Signed-off-by: Zhao Yu <yzhao81new@gmail.com>
Reviewed-by: Jeff Dike <jdike@linux.intel.com>
---
include/linux/skbuff.h | 7 ++++---
net/core/skbuff.c | 7 +++++++
2 files changed, 11 insertions(+), 3 deletions(-)
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 696e690..6e1e991 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -199,14 +199,15 @@ struct skb_shared_info {
struct sk_buff *frag_list;
struct skb_shared_hwtstamps hwtstamps;
+ /* Intermediate layers must ensure that destructor_arg
+ * remains valid until skb destructor */
+ void * destructor_arg;
+
/*
* Warning : all fields before dataref are cleared in __alloc_skb()
*/
atomic_t dataref;
- /* Intermediate layers must ensure that destructor_arg
- * remains valid until skb destructor */
- void * destructor_arg;
/* must be last field, see pskb_expand_head() */
skb_frag_t frags[MAX_SKB_FRAGS];
};
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index c83b421..68e197e 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -343,6 +343,13 @@ static void skb_release_data(struct sk_buff *skb)
if (skb_has_frags(skb))
skb_drop_fraglist(skb);
+ if (skb->dev && dev_is_mpassthru(skb->dev)) {
+ struct skb_ext_page *ext_page =
+ skb_shinfo(skb)->destructor_arg;
+ if (ext_page && ext_page->dtor)
+ ext_page->dtor(ext_page);
+ }
+
kfree(skb->head);
}
}
--
1.7.3
^ permalink raw reply related
* [PATCH v15 07/17]Modify netdev_alloc_page() to get external buffer
From: xiaohui.xin @ 2010-11-09 9:03 UTC (permalink / raw)
To: netdev, kvm, linux-kernel, mst, mingo, davem, herbert, jdike; +Cc: Xin Xiaohui
In-Reply-To: <fc6e95d63a2c62aaf77f8ded22fc43ccefcdbbff.1289280885.git.xiaohui.xin@intel.com>
From: Xin Xiaohui <xiaohui.xin@intel.com>
Currently, it can get external buffers from mp device.
Signed-off-by: Xin Xiaohui <xiaohui.xin@intel.com>
Signed-off-by: Zhao Yu <yzhao81new@gmail.com>
Reviewed-by: Jeff Dike <jdike@linux.intel.com>
---
net/core/skbuff.c | 27 +++++++++++++++++++++++++++
1 files changed, 27 insertions(+), 0 deletions(-)
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 68e197e..a1018bd 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -261,11 +261,38 @@ struct sk_buff *__netdev_alloc_skb(struct net_device *dev,
}
EXPORT_SYMBOL(__netdev_alloc_skb);
+struct page *netdev_alloc_ext_pages(struct net_device *dev, int npages)
+{
+ struct mp_port *port;
+ struct skb_ext_page *ext_page = NULL;
+
+ port = dev->mp_port;
+ if (!port)
+ goto out;
+ ext_page = port->ctor(port, NULL, npages);
+ if (ext_page)
+ return ext_page->page;
+out:
+ return NULL;
+
+}
+EXPORT_SYMBOL(netdev_alloc_ext_pages);
+
+struct page *netdev_alloc_ext_page(struct net_device *dev)
+{
+ return netdev_alloc_ext_pages(dev, 1);
+
+}
+EXPORT_SYMBOL(netdev_alloc_ext_page);
+
struct page *__netdev_alloc_page(struct net_device *dev, gfp_t gfp_mask)
{
int node = dev->dev.parent ? dev_to_node(dev->dev.parent) : -1;
struct page *page;
+ if (dev_is_mpassthru(dev))
+ return netdev_alloc_ext_page(dev);
+
page = alloc_pages_node(node, gfp_mask, 0);
return page;
}
--
1.7.3
^ permalink raw reply related
* [PATCH v15 08/17]Modify netdev_free_page() to release external buffer
From: xiaohui.xin @ 2010-11-09 9:03 UTC (permalink / raw)
To: netdev, kvm, linux-kernel, mst, mingo, davem, herbert, jdike; +Cc: Xin Xiaohui
In-Reply-To: <fc6e95d63a2c62aaf77f8ded22fc43ccefcdbbff.1289280885.git.xiaohui.xin@intel.com>
From: Xin Xiaohui <xiaohui.xin@intel.com>
Currently, it can get external buffers from mp device.
Signed-off-by: Xin Xiaohui <xiaohui.xin@intel.com>
Signed-off-by: Zhao Yu <yzhao81new@gmail.com>
Reviewed-by: Jeff Dike <jdike@linux.intel.com>
---
include/linux/skbuff.h | 4 +++-
net/core/skbuff.c | 24 ++++++++++++++++++++++++
2 files changed, 27 insertions(+), 1 deletions(-)
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 6e1e991..6309ce6 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -1586,9 +1586,11 @@ static inline struct page *netdev_alloc_page(struct net_device *dev)
return __netdev_alloc_page(dev, GFP_ATOMIC);
}
+extern void __netdev_free_page(struct net_device *dev, struct page *page);
+
static inline void netdev_free_page(struct net_device *dev, struct page *page)
{
- __free_page(page);
+ __netdev_free_page(dev, page);
}
/**
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index a1018bd..3d81113 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -298,6 +298,30 @@ struct page *__netdev_alloc_page(struct net_device *dev, gfp_t gfp_mask)
}
EXPORT_SYMBOL(__netdev_alloc_page);
+void netdev_free_ext_page(struct net_device *dev, struct page *page)
+{
+ struct skb_ext_page *ext_page = NULL;
+ if (dev_is_mpassthru(dev) && dev->mp_port->hash) {
+ ext_page = dev->mp_port->hash(dev, page);
+ if (ext_page)
+ ext_page->dtor(ext_page);
+ else
+ __free_page(page);
+ }
+}
+EXPORT_SYMBOL(netdev_free_ext_page);
+
+void __netdev_free_page(struct net_device *dev, struct page *page)
+{
+ if (dev_is_mpassthru(dev)) {
+ netdev_free_ext_page(dev, page);
+ return;
+ }
+
+ __free_page(page);
+}
+EXPORT_SYMBOL(__netdev_free_page);
+
void skb_add_rx_frag(struct sk_buff *skb, int i, struct page *page, int off,
int size)
{
--
1.7.3
^ permalink raw reply related
* [PATCH v15 10/17]If device is in zero-copy mode first, bonding will fail.
From: xiaohui.xin @ 2010-11-09 9:03 UTC (permalink / raw)
To: netdev, kvm, linux-kernel, mst, mingo, davem, herbert, jdike; +Cc: Xin Xiaohui
In-Reply-To: <fc6e95d63a2c62aaf77f8ded22fc43ccefcdbbff.1289280885.git.xiaohui.xin@intel.com>
From: Xin Xiaohui <xiaohui.xin@intel.com>
If device is in this zero-copy mode first, we cannot handle this,
so fail it. This patch is for this.
If bonding is created first, and one of the device will be in zero-copy
mode, this will be handled by mp device. It will first check if all the
slaves have the zero-copy capability. If no, fail too. Otherwise make
all the slaves in zero-copy mode.
Signed-off-by: Xin Xiaohui <xiaohui.xin@intel.com>
---
drivers/net/bonding/bond_main.c | 4 ++++
1 files changed, 4 insertions(+), 0 deletions(-)
diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 3b16f62..dfb6a2c 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -1428,6 +1428,10 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev)
bond_dev->name);
}
+ /* if the device is in zero-copy mode before bonding, fail it. */
+ if (dev_is_mpassthru(slave_dev))
+ return -EBUSY;
+
/* already enslaved */
if (slave_dev->flags & IFF_SLAVE) {
pr_debug("Error, Device was already enslaved\n");
--
1.7.3
^ permalink raw reply related
* [PATCH v15 11/17] Add a hook to intercept external buffers from NIC driver.
From: xiaohui.xin @ 2010-11-09 9:03 UTC (permalink / raw)
To: netdev, kvm, linux-kernel, mst, mingo, davem, herbert, jdike; +Cc: Xin Xiaohui
In-Reply-To: <fc6e95d63a2c62aaf77f8ded22fc43ccefcdbbff.1289280885.git.xiaohui.xin@intel.com>
From: Xin Xiaohui <xiaohui.xin@intel.com>
The hook is called in __netif_receive_skb().
Signed-off-by: Xin Xiaohui <xiaohui.xin@intel.com>
Signed-off-by: Zhao Yu <yzhao81new@gmail.com>
Reviewed-by: Jeff Dike <jdike@linux.intel.com>
---
net/core/dev.c | 40 ++++++++++++++++++++++++++++++++++++++++
1 files changed, 40 insertions(+), 0 deletions(-)
diff --git a/net/core/dev.c b/net/core/dev.c
index 84fbb83..bdad1c8 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -2814,6 +2814,40 @@ int __skb_bond_should_drop(struct sk_buff *skb, struct net_device *master)
}
EXPORT_SYMBOL(__skb_bond_should_drop);
+#if defined(CONFIG_MEDIATE_PASSTHRU) || defined(CONFIG_MEDIATE_PASSTHRU_MODULE)
+/* Add a hook to intercept mediate passthru(zero-copy) packets,
+ * and insert it to the socket queue owned by mp_port specially.
+ */
+static inline struct sk_buff *handle_mpassthru(struct sk_buff *skb,
+ struct packet_type **pt_prev,
+ int *ret,
+ struct net_device *orig_dev)
+{
+ struct mp_port *mp_port = NULL;
+ struct sock *sk = NULL;
+
+ if (!dev_is_mpassthru(skb->dev) && !dev_is_mpassthru(orig_dev))
+ return skb;
+ if (dev_is_mpassthru(skb->dev))
+ mp_port = skb->dev->mp_port;
+ else if (orig_dev->master == skb->dev && dev_is_mpassthru(orig_dev))
+ mp_port = orig_dev->mp_port;
+
+ if (*pt_prev) {
+ *ret = deliver_skb(skb, *pt_prev, orig_dev);
+ *pt_prev = NULL;
+ }
+
+ sk = mp_port->sock->sk;
+ skb_queue_tail(&sk->sk_receive_queue, skb);
+ sk->sk_state_change(sk);
+
+ return NULL;
+}
+#else
+#define handle_mpassthru(skb, pt_prev, ret, orig_dev) (skb)
+#endif
+
static int __netif_receive_skb(struct sk_buff *skb)
{
struct packet_type *ptype, *pt_prev;
@@ -2891,6 +2925,11 @@ static int __netif_receive_skb(struct sk_buff *skb)
ncls:
#endif
+ /* To intercept mediate passthru(zero-copy) packets here */
+ skb = handle_mpassthru(skb, &pt_prev, &ret, orig_dev);
+ if (!skb)
+ goto out;
+
/* Handle special case of bridge or macvlan */
rx_handler = rcu_dereference(skb->dev->rx_handler);
if (rx_handler) {
@@ -2983,6 +3022,7 @@ err:
EXPORT_SYMBOL(netdev_mp_port_prep);
#endif
+
/**
* netif_receive_skb - process receive buffer from network
* @skb: buffer to process
--
1.7.3
^ permalink raw reply related
* [PATCH v15 12/17] Add header file for mp device.
From: xiaohui.xin @ 2010-11-09 9:03 UTC (permalink / raw)
To: netdev, kvm, linux-kernel, mst, mingo, davem, herbert, jdike; +Cc: Xin Xiaohui
In-Reply-To: <fc6e95d63a2c62aaf77f8ded22fc43ccefcdbbff.1289280885.git.xiaohui.xin@intel.com>
From: Xin Xiaohui <xiaohui.xin@intel.com>
Signed-off-by: Xin Xiaohui <xiaohui.xin@intel.com>
Signed-off-by: Zhao Yu <yzhao81new@gmail.com>
Reviewed-by: Jeff Dike <jdike@linux.intel.com>
---
include/linux/mpassthru.h | 133 +++++++++++++++++++++++++++++++++++++++++++++
1 files changed, 133 insertions(+), 0 deletions(-)
create mode 100644 include/linux/mpassthru.h
diff --git a/include/linux/mpassthru.h b/include/linux/mpassthru.h
new file mode 100644
index 0000000..1115f55
--- /dev/null
+++ b/include/linux/mpassthru.h
@@ -0,0 +1,133 @@
+#ifndef __MPASSTHRU_H
+#define __MPASSTHRU_H
+
+#include <linux/types.h>
+#include <linux/if_ether.h>
+#include <linux/ioctl.h>
+
+/* ioctl defines */
+#define MPASSTHRU_BINDDEV _IOW('M', 213, int)
+#define MPASSTHRU_UNBINDDEV _IO('M', 214)
+#define MPASSTHRU_SET_MEM_LOCKED _IOW('M', 215, unsigned long)
+#define MPASSTHRU_GET_MEM_LOCKED_NEED _IOR('M', 216, unsigned long)
+
+#define COPY_THRESHOLD (L1_CACHE_BYTES * 4)
+#define COPY_HDR_LEN (L1_CACHE_BYTES < 64 ? 64 : L1_CACHE_BYTES)
+
+#define DEFAULT_NEED ((8192*2*2)*4096)
+
+struct frag {
+ u16 offset;
+ u16 size;
+};
+
+#define HASH_BUCKETS (8192*2)
+struct page_info {
+ struct list_head list;
+ struct page_info *next;
+ struct page_info *prev;
+ struct page *pages[MAX_SKB_FRAGS];
+ struct sk_buff *skb;
+ struct page_pool *pool;
+
+ /* The pointer relayed to skb, to indicate
+ * it's a external allocated skb or kernel
+ */
+ struct skb_ext_page ext_page;
+ /* flag to indicate read or write */
+#define INFO_READ 0
+#define INFO_WRITE 1
+ unsigned flags;
+ /* exact number of locked pages */
+ unsigned pnum;
+
+ /* The fields after that is for backend
+ * driver, now for vhost-net.
+ */
+ /* the kiocb structure related to */
+ struct kiocb *iocb;
+ /* the ring descriptor index */
+ unsigned int desc_pos;
+ /* the iovec coming from backend, we only
+ * need few of them */
+ struct iovec hdr[2];
+ struct iovec iov[2];
+};
+
+struct page_pool {
+ /* the queue for rx side */
+ struct list_head readq;
+ /* the lock to protect readq */
+ spinlock_t read_lock;
+ /* record the orignal rlimit */
+ struct rlimit o_rlim;
+ /* userspace wants to locked */
+ int locked_pages;
+ /* currently locked pages */
+ int cur_pages;
+ /* the memory locked before */
+ unsigned long orig_locked_vm;
+ /* the device according to */
+ struct net_device *dev;
+ /* the mp_port according to dev */
+ struct mp_port port;
+ /* the hash_table list to find each locked page */
+ struct page_info **hash_table;
+};
+
+static struct kmem_cache *ext_page_info_cache;
+
+#ifdef __KERNEL__
+#if defined(CONFIG_MEDIATE_PASSTHRU) || defined(CONFIG_MEDIATE_PASSTHRU_MODULE)
+struct socket *mp_get_socket(struct file *);
+struct page_pool *page_pool_create(struct net_device *dev,
+ struct socket *sock);
+int async_recvmsg(struct kiocb *iocb, struct page_pool *pool,
+ struct iovec *iov, int count, int flags);
+int async_sendmsg(struct sock *sk, struct kiocb *iocb,
+ struct page_pool *pool, struct iovec *iov,
+ int count);
+void async_data_ready(struct sock *sk, struct page_pool *pool);
+void dev_change_state(struct net_device *dev);
+void page_pool_destroy(struct mm_struct *mm, struct page_pool *pool);
+#else
+#include <linux/err.h>
+#include <linux/errno.h>
+struct file;
+struct socket;
+static inline struct socket *mp_get_socket(struct file *f)
+{
+ return ERR_PTR(-EINVAL);
+}
+static inline struct page_pool *page_pool_create(struct net_device *dev,
+ struct socket *sock)
+{
+ return ERR_PTR(-EINVAL);
+}
+static inline int async_recvmsg(struct kiocb *iocb, struct page_pool *pool,
+ struct iovec *iov, int count, int flags)
+{
+ return -EINVAL;
+}
+static inline int async_sendmsg(struct sock *sk, struct kiocb *iocb,
+ struct page_pool *pool, struct iovec *iov,
+ int count)
+{
+ return -EINVAL;
+}
+static inline void async_data_ready(struct sock *sk, struct page_pool *pool)
+{
+ return;
+}
+static inline void dev_change_state(struct net_device *dev)
+{
+ return;
+}
+static inline void page_pool_destroy(struct mm_struct *mm,
+ struct page_pool *pool)
+{
+ return;
+}
+#endif /* CONFIG_MEDIATE_PASSTHRU */
+#endif /* __KERNEL__ */
+#endif /* __MPASSTHRU_H */
--
1.7.3
^ permalink raw reply related
* [PATCH v15 13/17] Add mp(mediate passthru) device.
From: xiaohui.xin @ 2010-11-09 9:03 UTC (permalink / raw)
To: netdev, kvm, linux-kernel, mst, mingo, davem, herbert, jdike; +Cc: Xin Xiaohui
In-Reply-To: <fc6e95d63a2c62aaf77f8ded22fc43ccefcdbbff.1289280885.git.xiaohui.xin@intel.com>
From: Xin Xiaohui <xiaohui.xin@intel.com>
The patch add mp(mediate passthru) device, which now
based on vhost-net backend driver and provides proto_ops
to send/receive guest buffers data from/to guest vitio-net
driver.
It also exports async functions which can be used by other
drivers like macvtap to utilize zero-copy too.
Signed-off-by: Xin Xiaohui <xiaohui.xin@intel.com>
Signed-off-by: Zhao Yu <yzhao81new@gmail.com>
Reviewed-by: Jeff Dike <jdike@linux.intel.com>
---
drivers/vhost/mpassthru.c | 1515 +++++++++++++++++++++++++++++++++++++++++++++
1 files changed, 1515 insertions(+), 0 deletions(-)
create mode 100644 drivers/vhost/mpassthru.c
diff --git a/drivers/vhost/mpassthru.c b/drivers/vhost/mpassthru.c
new file mode 100644
index 0000000..492430c
--- /dev/null
+++ b/drivers/vhost/mpassthru.c
@@ -0,0 +1,1515 @@
+/*
+ * MPASSTHRU - Mediate passthrough device.
+ * Copyright (C) 2009 ZhaoYu, XinXiaohui, Dike, Jeffery G
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#define DRV_NAME "mpassthru"
+#define DRV_DESCRIPTION "Mediate passthru device driver"
+#define DRV_COPYRIGHT "(C) 2009 ZhaoYu, XinXiaohui, Dike, Jeffery G"
+
+#include <linux/compat.h>
+#include <linux/module.h>
+#include <linux/errno.h>
+#include <linux/kernel.h>
+#include <linux/major.h>
+#include <linux/slab.h>
+#include <linux/smp_lock.h>
+#include <linux/poll.h>
+#include <linux/fcntl.h>
+#include <linux/init.h>
+#include <linux/aio.h>
+
+#include <linux/skbuff.h>
+#include <linux/netdevice.h>
+#include <linux/etherdevice.h>
+#include <linux/miscdevice.h>
+#include <linux/ethtool.h>
+#include <linux/rtnetlink.h>
+#include <linux/if.h>
+#include <linux/if_arp.h>
+#include <linux/if_ether.h>
+#include <linux/crc32.h>
+#include <linux/nsproxy.h>
+#include <linux/uaccess.h>
+#include <linux/virtio_net.h>
+#include <linux/mpassthru.h>
+#include <net/net_namespace.h>
+#include <net/netns/generic.h>
+#include <net/rtnetlink.h>
+#include <net/sock.h>
+
+#include <asm/system.h>
+#include "../net/bonding/bonding.h"
+
+struct mp_struct {
+ struct mp_file *mfile;
+ struct net_device *dev;
+ struct page_pool *pool;
+ struct socket socket;
+ struct socket_wq wq;
+ struct mm_struct *mm;
+};
+
+struct mp_file {
+ atomic_t count;
+ struct mp_struct *mp;
+ struct net *net;
+};
+
+struct mp_sock {
+ struct sock sk;
+ struct mp_struct *mp;
+};
+
+/* The main function to allocate external buffers */
+static struct skb_ext_page *page_ctor(struct mp_port *port,
+ struct sk_buff *skb,
+ int npages)
+{
+ int i;
+ unsigned long flags;
+ struct page_pool *pool;
+ struct page_info *info = NULL;
+
+ if (npages != 1)
+ BUG();
+ pool = container_of(port, struct page_pool, port);
+
+ spin_lock_irqsave(&pool->read_lock, flags);
+ if (!list_empty(&pool->readq)) {
+ info = list_first_entry(&pool->readq, struct page_info, list);
+ list_del(&info->list);
+ }
+ spin_unlock_irqrestore(&pool->read_lock, flags);
+ if (!info)
+ return NULL;
+
+ for (i = 0; i < info->pnum; i++)
+ get_page(info->pages[i]);
+ info->skb = skb;
+ return &info->ext_page;
+}
+
+static struct page_info *mp_hash_lookup(struct page_pool *pool,
+ struct page *page);
+static struct page_info *mp_hash_delete(struct page_pool *pool,
+ struct page_info *info);
+
+static struct skb_ext_page *mp_lookup(struct net_device *dev,
+ struct page *page)
+{
+ struct mp_struct *mp =
+ container_of(dev->mp_port->sock->sk, struct mp_sock, sk)->mp;
+ struct page_pool *pool = mp->pool;
+ struct page_info *info;
+
+ info = mp_hash_lookup(pool, page);
+ if (!info)
+ return NULL;
+ return &info->ext_page;
+}
+
+struct page_pool *page_pool_create(struct net_device *dev,
+ struct socket *sock)
+{
+ struct page_pool *pool;
+ struct net_device *master;
+ struct slave *slave;
+ struct bonding *bond;
+ int i;
+ int rc;
+
+ pool = kzalloc(sizeof(*pool), GFP_KERNEL);
+ if (!pool)
+ return NULL;
+
+ /* How to deal with bonding device:
+ * check if all the slaves are capable of zero-copy.
+ * if not, fail.
+ */
+ master = dev->master;
+ if (master) {
+ bond = netdev_priv(master);
+ read_lock(&bond->lock);
+ bond_for_each_slave(bond, slave, i) {
+ rc = netdev_mp_port_prep(slave->dev, &pool->port);
+ if (rc)
+ break;
+ }
+ read_unlock(&bond->lock);
+ } else
+ rc = netdev_mp_port_prep(dev, &pool->port);
+ if (rc)
+ goto fail;
+
+ INIT_LIST_HEAD(&pool->readq);
+ spin_lock_init(&pool->read_lock);
+ pool->hash_table =
+ kzalloc(sizeof(struct page_info *) * HASH_BUCKETS, GFP_KERNEL);
+ if (!pool->hash_table)
+ goto fail;
+
+ pool->dev = dev;
+ pool->port.ctor = page_ctor;
+ pool->port.sock = sock;
+ pool->port.hash = mp_lookup;
+ pool->locked_pages = 0;
+ pool->cur_pages = 0;
+ pool->orig_locked_vm = 0;
+
+ /* for bonding device, assign all the slaves the same page_pool */
+ if (master) {
+ read_lock(&bond->lock);
+ bond_for_each_slave(bond, slave, i) {
+ dev_hold(slave->dev);
+ slave->dev->mp_port = &pool->port;
+ }
+ read_unlock(&bond->lock);
+ } else {
+ dev_hold(dev);
+ dev->mp_port = &pool->port;
+ }
+
+ return pool;
+fail:
+ kfree(pool);
+ return NULL;
+}
+EXPORT_SYMBOL_GPL(page_pool_create);
+
+void dev_bond_hold(struct net_device *dev)
+{
+ struct net_device *master;
+ struct bonding *bond;
+ struct slave *slave;
+ int i;
+
+ master = dev->master;
+ if (master) {
+ bond = netdev_priv(master);
+ read_lock(&bond->lock);
+ bond_for_each_slave(bond, slave, i) {
+ if (slave->dev != dev)
+ dev_hold(slave->dev);
+ }
+ read_unlock(&bond->lock);
+ }
+}
+
+void dev_bond_put(struct net_device *dev)
+{
+ struct net_device *master;
+ struct bonding *bond;
+ struct slave *slave;
+ int i;
+
+ master = dev->master;
+ if (master) {
+ bond = netdev_priv(master);
+ read_lock(&bond->lock);
+ bond_for_each_slave(bond, slave, i) {
+ if (slave->dev != dev)
+ dev_put(slave->dev);
+ }
+ read_unlock(&bond->lock);
+ }
+}
+
+void dev_change_state(struct net_device *dev)
+{
+ struct net_device *master;
+ struct bonding *bond;
+ struct slave *slave;
+ int i;
+
+ master = dev->master;
+ if (master) {
+ bond = netdev_priv(master);
+ read_lock(&bond->lock);
+ bond_for_each_slave(bond, slave, i) {
+ dev_change_flags(slave->dev,
+ slave->dev->flags & (~IFF_UP));
+ dev_change_flags(slave->dev,
+ slave->dev->flags | IFF_UP);
+ }
+ read_unlock(&bond->lock);
+ } else {
+ dev_change_flags(dev, dev->flags & (~IFF_UP));
+ dev_change_flags(dev, dev->flags | IFF_UP);
+ }
+}
+EXPORT_SYMBOL_GPL(dev_change_state);
+
+static int mp_page_pool_attach(struct mp_struct *mp, struct page_pool *pool)
+{
+ int rc = 0;
+ /* should be protected by mp_mutex */
+ if (mp->pool) {
+ rc = -EBUSY;
+ goto fail;
+ }
+ if (mp->dev != pool->dev) {
+ rc = -EFAULT;
+ goto fail;
+ }
+ mp->pool = pool;
+ return 0;
+fail:
+ kfree(pool->hash_table);
+ kfree(pool);
+ return rc;
+}
+
+struct page_info *info_dequeue(struct page_pool *pool)
+{
+ unsigned long flags;
+ struct page_info *info = NULL;
+ spin_lock_irqsave(&pool->read_lock, flags);
+ if (!list_empty(&pool->readq)) {
+ info = list_first_entry(&pool->readq,
+ struct page_info, list);
+ list_del(&info->list);
+ }
+ spin_unlock_irqrestore(&pool->read_lock, flags);
+ return info;
+}
+
+static void mp_ki_dtor(struct kiocb *iocb)
+{
+ struct page_info *info = (struct page_info *)(iocb->private);
+ int i;
+
+ if (info->flags == INFO_READ) {
+ for (i = 0; i < info->pnum; i++) {
+ if (info->pages[i]) {
+ set_page_dirty_lock(info->pages[i]);
+ put_page(info->pages[i]);
+ }
+ }
+ mp_hash_delete(info->pool, info);
+ if (info->skb) {
+ info->skb->destructor = NULL;
+ kfree_skb(info->skb);
+ }
+ }
+ /* Decrement the number of locked pages */
+ info->pool->cur_pages -= info->pnum;
+ kmem_cache_free(ext_page_info_cache, info);
+
+ return;
+}
+
+static struct kiocb *create_iocb(struct page_info *info, int size)
+{
+ struct kiocb *iocb = NULL;
+
+ iocb = info->iocb;
+ if (!iocb)
+ return iocb;
+ iocb->ki_flags = 0;
+ iocb->ki_users = 1;
+ iocb->ki_key = 0;
+ iocb->ki_ctx = NULL;
+ iocb->ki_cancel = NULL;
+ iocb->ki_retry = NULL;
+ iocb->ki_eventfd = NULL;
+ iocb->ki_pos = info->desc_pos;
+ iocb->ki_nbytes = size;
+ iocb->ki_dtor(iocb);
+ iocb->private = (void *)info;
+ iocb->ki_dtor = mp_ki_dtor;
+
+ return iocb;
+}
+
+void page_pool_destroy(struct mm_struct *mm, struct page_pool *pool)
+{
+ struct page_info *info;
+ struct net_device *master;
+ struct slave *slave;
+ struct bonding *bond;
+ int i;
+
+ if (!pool)
+ return;
+
+ while ((info = info_dequeue(pool))) {
+ for (i = 0; i < info->pnum; i++)
+ if (info->pages[i])
+ put_page(info->pages[i]);
+ create_iocb(info, 0);
+ kmem_cache_free(ext_page_info_cache, info);
+ }
+ down_write(&mm->mmap_sem);
+ mm->locked_vm -= pool->locked_pages;
+ up_write(&mm->mmap_sem);
+
+ master = pool->dev->master;
+ if (master) {
+ bond = netdev_priv(master);
+ read_lock(&bond->lock);
+ bond_for_each_slave(bond, slave, i) {
+ slave->dev->mp_port = NULL;
+ dev_put(slave->dev);
+ }
+ read_unlock(&bond->lock);
+ } else {
+ pool->dev->mp_port = NULL;
+ dev_put(pool->dev);
+ }
+
+ kfree(pool->hash_table);
+ kfree(pool);
+}
+EXPORT_SYMBOL_GPL(page_pool_destroy);
+
+static void mp_page_pool_detach(struct mp_struct *mp)
+{
+ /* locked by mp_mutex */
+ if (mp->pool) {
+ page_pool_destroy(mp->mm, mp->pool);
+ mp->pool = NULL;
+ }
+}
+
+static void __mp_detach(struct mp_struct *mp)
+{
+ struct net_device *master;
+ struct bonding *bond;
+ struct slave *slave;
+ int i;
+
+ mp->mfile = NULL;
+ master = mp->dev->master;
+ if (master) {
+ bond = netdev_priv(master);
+ read_lock(&bond->lock);
+ bond_for_each_slave(bond, slave, i)
+ dev_change_flags(slave->dev,
+ slave->dev->flags & ~IFF_UP);
+ read_unlock(&bond->lock);
+ } else
+ dev_change_flags(mp->dev, mp->dev->flags & ~IFF_UP);
+ mp_page_pool_detach(mp);
+ if (master) {
+ bond = netdev_priv(master);
+ read_lock(&bond->lock);
+ bond_for_each_slave(bond, slave, i)
+ dev_change_flags(slave->dev,
+ slave->dev->flags | IFF_UP);
+ read_unlock(&bond->lock);
+ } else
+ dev_change_flags(mp->dev, mp->dev->flags | IFF_UP);
+}
+
+static DEFINE_MUTEX(mp_mutex);
+
+static void mp_detach(struct mp_struct *mp)
+{
+ mutex_lock(&mp_mutex);
+ __mp_detach(mp);
+ mutex_unlock(&mp_mutex);
+}
+
+static struct mp_struct *mp_get(struct mp_file *mfile)
+{
+ struct mp_struct *mp = NULL;
+ if (atomic_inc_not_zero(&mfile->count))
+ mp = mfile->mp;
+
+ return mp;
+}
+
+static void mp_put(struct mp_file *mfile)
+{
+ if (atomic_dec_and_test(&mfile->count)) {
+ if (mfile->mp)
+ return;
+ if (!rtnl_is_locked()) {
+ rtnl_lock();
+ mp_detach(mfile->mp);
+ rtnl_unlock();
+ } else
+ mp_detach(mfile->mp);
+ }
+}
+
+static void iocb_tag(struct kiocb *iocb)
+{
+ iocb->ki_flags = 1;
+}
+
+/* The callback to destruct the external buffers or skb */
+static void page_dtor(struct skb_ext_page *ext_page)
+{
+ struct page_info *info;
+ struct page_pool *pool;
+ struct sock *sk;
+ struct sk_buff *skb;
+
+ if (!ext_page)
+ return;
+ info = container_of(ext_page, struct page_info, ext_page);
+ if (!info)
+ return;
+ pool = info->pool;
+ skb = info->skb;
+
+ if (info->flags == INFO_READ) {
+ create_iocb(info, 0);
+ return;
+ }
+
+ /* For transmit, we should wait for the DMA finish by hardware.
+ * Queue the notifier to wake up the backend driver
+ */
+
+ iocb_tag(info->iocb);
+ sk = pool->port.sock->sk;
+ sk->sk_write_space(sk);
+
+ return;
+}
+
+/* For small exteranl buffers transmit, we don't need to call
+ * get_user_pages().
+ */
+static struct page_info *alloc_small_page_info(struct page_pool *pool,
+ struct kiocb *iocb, int total)
+{
+ struct page_info *info =
+ kmem_cache_alloc(ext_page_info_cache, GFP_KERNEL);
+
+ if (!info)
+ return NULL;
+ info->ext_page.dtor = page_dtor;
+ info->pool = pool;
+ info->flags = INFO_WRITE;
+ info->iocb = iocb;
+ info->pnum = 0;
+ return info;
+}
+
+typedef u32 key_mp_t;
+static inline key_mp_t mp_hash(struct page *page, int buckets)
+{
+ key_mp_t k;
+#if BITS_PER_LONG == 64
+ k = ((((unsigned long)page << 32UL) >> 32UL) /
+ sizeof(struct page)) % buckets ;
+#elif BITS_PER_LONG == 32
+ k = ((unsigned long)page / sizeof(struct page)) % buckets;
+#endif
+
+ return k;
+}
+
+static void mp_hash_insert(struct page_pool *pool,
+ struct page *page, struct page_info *page_info)
+{
+ struct page_info *tmp;
+ key_mp_t key = mp_hash(page, HASH_BUCKETS);
+ if (!pool->hash_table[key]) {
+ pool->hash_table[key] = page_info;
+ return;
+ }
+
+ tmp = pool->hash_table[key];
+ while (tmp->next)
+ tmp = tmp->next;
+
+ tmp->next = page_info;
+ page_info->prev = tmp;
+ return;
+}
+
+static struct page_info *mp_hash_delete(struct page_pool *pool,
+ struct page_info *info)
+{
+ key_mp_t key = mp_hash(info->pages[0], HASH_BUCKETS);
+ struct page_info *tmp = NULL;
+
+ tmp = pool->hash_table[key];
+ while (tmp) {
+ if (tmp == info) {
+ if (!tmp->prev) {
+ pool->hash_table[key] = tmp->next;
+ if (tmp->next)
+ tmp->next->prev = NULL;
+ } else {
+ tmp->prev->next = tmp->next;
+ if (tmp->next)
+ tmp->next->prev = tmp->prev;
+ }
+ return tmp;
+ }
+ tmp = tmp->next;
+ }
+ return tmp;
+}
+
+static struct page_info *mp_hash_lookup(struct page_pool *pool,
+ struct page *page)
+{
+ key_mp_t key = mp_hash(page, HASH_BUCKETS);
+ struct page_info *tmp = NULL;
+
+ int i;
+ tmp = pool->hash_table[key];
+ while (tmp) {
+ for (i = 0; i < tmp->pnum; i++) {
+ if (tmp->pages[i] == page)
+ return tmp;
+ }
+ tmp = tmp->next;
+ }
+ return tmp;
+}
+
+/* The main function to transform the guest user space address
+ * to host kernel address via get_user_pages(). Thus the hardware
+ * can do DMA directly to the external buffer address.
+ */
+static struct page_info *alloc_page_info(struct page_pool *pool,
+ struct kiocb *iocb, struct iovec *iov,
+ int count, struct frag *frags,
+ int npages, int total)
+{
+ int rc;
+ int i, j, n = 0;
+ int len;
+ unsigned long base;
+ struct page_info *info = NULL;
+
+ if (pool->cur_pages + count > pool->locked_pages) {
+ printk(KERN_INFO "Exceed memory lock rlimt.");
+ return NULL;
+ }
+
+ info = kmem_cache_alloc(ext_page_info_cache, GFP_KERNEL);
+
+ if (!info)
+ return NULL;
+ info->skb = NULL;
+ info->next = info->prev = NULL;
+
+ for (i = j = 0; i < count; i++) {
+ base = (unsigned long)iov[i].iov_base;
+ len = iov[i].iov_len;
+
+ if (!len)
+ continue;
+ n = ((base & ~PAGE_MASK) + len + ~PAGE_MASK) >> PAGE_SHIFT;
+
+ rc = get_user_pages_fast(base, n, npages ? 1 : 0,
+ &info->pages[j]);
+ if (rc != n)
+ goto failed;
+
+ while (n--) {
+ frags[j].offset = base & ~PAGE_MASK;
+ frags[j].size = min_t(int, len,
+ PAGE_SIZE - frags[j].offset);
+ len -= frags[j].size;
+ base += frags[j].size;
+ j++;
+ }
+ }
+
+#ifdef CONFIG_HIGHMEM
+ if (npages && !(dev->features & NETIF_F_HIGHDMA)) {
+ for (i = 0; i < j; i++) {
+ if (PageHighMem(info->pages[i]))
+ goto failed;
+ }
+ }
+#endif
+
+ info->ext_page.dtor = page_dtor;
+ info->ext_page.page = info->pages[0];
+ info->pool = pool;
+ info->pnum = j;
+ info->iocb = iocb;
+ if (!npages)
+ info->flags = INFO_WRITE;
+ else
+ info->flags = INFO_READ;
+
+ if (info->flags == INFO_READ) {
+ if (frags[0].offset == 0 && iocb->ki_iovec[0].iov_len) {
+ frags[0].offset = iocb->ki_iovec[0].iov_len;
+ pool->port.vnet_hlen = iocb->ki_iovec[0].iov_len;
+ }
+ for (i = 0; i < j; i++)
+ mp_hash_insert(pool, info->pages[i], info);
+ }
+ /* increment the number of locked pages */
+ pool->cur_pages += j;
+ return info;
+
+failed:
+ for (i = 0; i < j; i++)
+ put_page(info->pages[i]);
+
+ kmem_cache_free(ext_page_info_cache, info);
+
+ return NULL;
+}
+
+static void mp_sock_destruct(struct sock *sk)
+{
+ struct mp_struct *mp = container_of(sk, struct mp_sock, sk)->mp;
+ kfree(mp);
+}
+
+static void mp_sock_state_change(struct sock *sk)
+{
+ wait_queue_head_t *wqueue = sk_sleep(sk);
+ if (wqueue && waitqueue_active(wqueue))
+ wake_up_interruptible_sync_poll(wqueue, POLLIN);
+}
+
+static void mp_sock_write_space(struct sock *sk)
+{
+ wait_queue_head_t *wqueue = sk_sleep(sk);
+ if (wqueue && waitqueue_active(wqueue))
+ wake_up_interruptible_sync_poll(wqueue, POLLOUT);
+}
+
+void async_data_ready(struct sock *sk, struct page_pool *pool)
+{
+ struct sk_buff *skb = NULL;
+ struct page_info *info = NULL;
+ int len;
+
+ while ((skb = skb_dequeue(&sk->sk_receive_queue)) != NULL) {
+ struct page *page;
+ int off;
+ int size = 0, i = 0;
+ struct skb_shared_info *shinfo = skb_shinfo(skb);
+ struct skb_ext_page *ext_page =
+ (struct skb_ext_page *)(shinfo->destructor_arg);
+ struct virtio_net_hdr_mrg_rxbuf hdr = {
+ .hdr.flags = 0,
+ .hdr.gso_type = VIRTIO_NET_HDR_GSO_NONE
+ };
+
+ if (!ext_page) {
+ kfree_skb(skb);
+ continue;
+ }
+ if (skb->ip_summed == CHECKSUM_COMPLETE)
+ printk(KERN_INFO "Complete checksum occurs\n");
+
+ if (shinfo->frags[0].page == ext_page->page) {
+ info = container_of(ext_page,
+ struct page_info,
+ ext_page);
+ if (shinfo->nr_frags)
+ hdr.num_buffers = shinfo->nr_frags;
+ else
+ hdr.num_buffers = shinfo->nr_frags + 1;
+ } else {
+ info = container_of(ext_page,
+ struct page_info,
+ ext_page);
+ hdr.num_buffers = shinfo->nr_frags + 1;
+ }
+ skb_push(skb, ETH_HLEN);
+
+ if (skb_is_gso(skb)) {
+ hdr.hdr.hdr_len = skb_headlen(skb);
+ hdr.hdr.gso_size = shinfo->gso_size;
+ if (shinfo->gso_type & SKB_GSO_TCPV4)
+ hdr.hdr.gso_type = VIRTIO_NET_HDR_GSO_TCPV4;
+ else if (shinfo->gso_type & SKB_GSO_TCPV6)
+ hdr.hdr.gso_type = VIRTIO_NET_HDR_GSO_TCPV6;
+ else if (shinfo->gso_type & SKB_GSO_UDP)
+ hdr.hdr.gso_type = VIRTIO_NET_HDR_GSO_UDP;
+ else
+ BUG();
+ if (shinfo->gso_type & SKB_GSO_TCP_ECN)
+ hdr.hdr.gso_type |= VIRTIO_NET_HDR_GSO_ECN;
+
+ } else
+ hdr.hdr.gso_type = VIRTIO_NET_HDR_GSO_NONE;
+
+ if (skb->ip_summed == CHECKSUM_PARTIAL) {
+ hdr.hdr.flags = VIRTIO_NET_HDR_F_NEEDS_CSUM;
+ hdr.hdr.csum_start =
+ skb->csum_start - skb_headroom(skb);
+ hdr.hdr.csum_offset = skb->csum_offset;
+ }
+
+ off = info->hdr[0].iov_len;
+ len = memcpy_toiovec(info->iov, (unsigned char *)&hdr, off);
+ if (len) {
+ pr_debug("Unable to write vnet_hdr at addr '%p': '%d'\n",
+ info->iov, len);
+ goto clean;
+ }
+
+ memcpy_toiovec(info->iov, skb->data, skb_headlen(skb));
+
+ info->iocb->ki_left = hdr.num_buffers;
+ if (shinfo->frags[0].page == ext_page->page) {
+ size = shinfo->frags[0].size +
+ shinfo->frags[0].page_offset - off;
+ i = 1;
+ } else {
+ size = skb_headlen(skb);
+ i = 0;
+ }
+ create_iocb(info, off + size);
+ for (i = i; i < shinfo->nr_frags; i++) {
+ page = shinfo->frags[i].page;
+ info = mp_hash_lookup(pool, shinfo->frags[i].page);
+ create_iocb(info, shinfo->frags[i].size);
+ }
+ info->skb = skb;
+ shinfo->nr_frags = 0;
+ shinfo->destructor_arg = NULL;
+ continue;
+clean:
+ kfree_skb(skb);
+ for (i = 0; i < info->pnum; i++)
+ put_page(info->pages[i]);
+ kmem_cache_free(ext_page_info_cache, info);
+ }
+ return;
+}
+EXPORT_SYMBOL_GPL(async_data_ready);
+
+static void mp_sock_data_ready(struct sock *sk, int coming)
+{
+ struct mp_struct *mp = container_of(sk, struct mp_sock, sk)->mp;
+ struct page_pool *pool = NULL;
+
+ pool = mp->pool;
+ if (!pool)
+ return;
+ return async_data_ready(sk, pool);
+}
+
+static inline struct sk_buff *mp_alloc_skb(struct sock *sk, size_t prepad,
+ size_t len, size_t linear,
+ int noblock, int *err)
+{
+ struct sk_buff *skb;
+
+ /* Under a page? Don't bother with paged skb. */
+ if (prepad + len < PAGE_SIZE || !linear)
+ linear = len;
+
+ skb = sock_alloc_send_pskb(sk, prepad + linear, len - linear, noblock,
+ err);
+ if (!skb)
+ return NULL;
+
+ skb_reserve(skb, prepad);
+ skb_put(skb, linear);
+ skb->data_len = len - linear;
+ skb->len += len - linear;
+
+ return skb;
+}
+
+static int mp_skb_from_vnet_hdr(struct sk_buff *skb,
+ struct virtio_net_hdr *vnet_hdr)
+{
+ unsigned short gso_type = 0;
+ if (vnet_hdr->gso_type != VIRTIO_NET_HDR_GSO_NONE) {
+ switch (vnet_hdr->gso_type & ~VIRTIO_NET_HDR_GSO_ECN) {
+ case VIRTIO_NET_HDR_GSO_TCPV4:
+ gso_type = SKB_GSO_TCPV4;
+ break;
+ case VIRTIO_NET_HDR_GSO_TCPV6:
+ gso_type = SKB_GSO_TCPV6;
+ break;
+ case VIRTIO_NET_HDR_GSO_UDP:
+ gso_type = SKB_GSO_UDP;
+ break;
+ default:
+ return -EINVAL;
+ }
+
+ if (vnet_hdr->gso_type & VIRTIO_NET_HDR_GSO_ECN)
+ gso_type |= SKB_GSO_TCP_ECN;
+
+ if (vnet_hdr->gso_size == 0)
+ return -EINVAL;
+ }
+
+ if (vnet_hdr->flags & VIRTIO_NET_HDR_F_NEEDS_CSUM) {
+ if (!skb_partial_csum_set(skb, vnet_hdr->csum_start,
+ vnet_hdr->csum_offset))
+ return -EINVAL;
+ }
+
+ if (vnet_hdr->gso_type != VIRTIO_NET_HDR_GSO_NONE) {
+ skb_shinfo(skb)->gso_size = vnet_hdr->gso_size;
+ skb_shinfo(skb)->gso_type = gso_type;
+
+ /* Header must be checked, and gso_segs computed. */
+ skb_shinfo(skb)->gso_type |= SKB_GSO_DODGY;
+ skb_shinfo(skb)->gso_segs = 0;
+ }
+ return 0;
+}
+
+int async_sendmsg(struct sock *sk, struct kiocb *iocb, struct page_pool *pool,
+ struct iovec *iov, int count)
+{
+ struct virtio_net_hdr vnet_hdr = {0};
+ int hdr_len = 0;
+ struct page_info *info = NULL;
+ struct frag frags[MAX_SKB_FRAGS];
+ struct sk_buff *skb;
+ int total = 0, header, n, i, len, rc;
+ unsigned long base;
+
+ total = iov_length(iov, count);
+
+ if (total < ETH_HLEN)
+ return -EINVAL;
+
+ if (total <= COPY_THRESHOLD)
+ goto copy;
+
+ n = 0;
+ for (i = 0; i < count; i++) {
+ base = (unsigned long)iov[i].iov_base;
+ len = iov[i].iov_len;
+ if (!len)
+ continue;
+ n += ((base & ~PAGE_MASK) + len + ~PAGE_MASK) >> PAGE_SHIFT;
+ if (n > MAX_SKB_FRAGS)
+ return -EINVAL;
+ }
+
+copy:
+ hdr_len = sizeof(vnet_hdr);
+ if ((total - iocb->ki_iovec[0].iov_len) < 0)
+ return -EINVAL;
+
+ rc = memcpy_fromiovecend((void *)&vnet_hdr, iocb->ki_iovec, 0, hdr_len);
+ if (rc < 0)
+ return -EINVAL;
+
+ if ((vnet_hdr.flags & VIRTIO_NET_HDR_F_NEEDS_CSUM) &&
+ vnet_hdr.csum_start + vnet_hdr.csum_offset + 2 >
+ vnet_hdr.hdr_len)
+ vnet_hdr.hdr_len = vnet_hdr.csum_start +
+ vnet_hdr.csum_offset + 2;
+
+ if (vnet_hdr.hdr_len > total)
+ return -EINVAL;
+
+ header = total > COPY_THRESHOLD ? COPY_HDR_LEN : total;
+
+ skb = mp_alloc_skb(sk, NET_IP_ALIGN, header,
+ iocb->ki_iovec[0].iov_len, 1, &rc);
+ if (!skb)
+ goto drop;
+
+ skb_set_network_header(skb, ETH_HLEN);
+ memcpy_fromiovec(skb->data, iov, header);
+
+ skb_reset_mac_header(skb);
+ skb->protocol = eth_hdr(skb)->h_proto;
+
+ rc = mp_skb_from_vnet_hdr(skb, &vnet_hdr);
+ if (rc)
+ goto drop;
+
+ if (header == total) {
+ rc = total;
+ info = alloc_small_page_info(pool, iocb, total);
+ } else {
+ info = alloc_page_info(pool, iocb, iov, count, frags, 0, total);
+ if (info)
+ for (i = 0; i < info->pnum; i++) {
+ skb_add_rx_frag(skb, i, info->pages[i],
+ frags[i].offset, frags[i].size);
+ info->pages[i] = NULL;
+ }
+ }
+ if (!pool->cur_pages)
+ sk->sk_state_change(sk);
+
+ if (info != NULL) {
+ info->desc_pos = iocb->ki_pos;
+ info->skb = skb;
+ skb_shinfo(skb)->destructor_arg = &info->ext_page;
+ skb->dev = pool->dev->master ? pool->dev->master : pool->dev;
+ create_iocb(info, total);
+ dev_queue_xmit(skb);
+ return 0;
+ }
+drop:
+ kfree_skb(skb);
+ if (info) {
+ for (i = 0; i < info->pnum; i++)
+ put_page(info->pages[i]);
+ kmem_cache_free(ext_page_info_cache, info);
+ }
+ pool->dev->stats.tx_dropped++;
+ return -ENOMEM;
+}
+EXPORT_SYMBOL_GPL(async_sendmsg);
+
+static int mp_sendmsg(struct kiocb *iocb, struct socket *sock,
+ struct msghdr *m, size_t total_len)
+{
+ struct mp_struct *mp = container_of(sock->sk, struct mp_sock, sk)->mp;
+ struct page_pool *pool;
+ struct iovec *iov = m->msg_iov;
+ int count = m->msg_iovlen;
+
+ pool = mp->pool;
+ if (!pool)
+ return -ENODEV;
+ return async_sendmsg(sock->sk, iocb, pool, iov, count);
+}
+
+int async_recvmsg(struct kiocb *iocb, struct page_pool *pool,
+ struct iovec *iov, int count, int flags)
+{
+ int npages, payload;
+ struct page_info *info;
+ struct frag frags[MAX_SKB_FRAGS];
+ unsigned long base;
+ int i, len;
+ unsigned long flag;
+
+ if (!(flags & MSG_DONTWAIT))
+ return -EINVAL;
+
+ if (!pool)
+ return -EINVAL;
+
+ /* Error detections in case invalid external buffer */
+ if (count > 2 && iov[1].iov_len < pool->port.hdr_len &&
+ pool->dev->features & NETIF_F_SG) {
+ return -EINVAL;
+ }
+
+ npages = pool->port.npages;
+ payload = pool->port.data_len;
+
+ /* If KVM guest virtio-net FE driver use SG feature */
+ if (count > 2) {
+ for (i = 2; i < count; i++) {
+ base = (unsigned long)iov[i].iov_base & ~PAGE_MASK;
+ len = iov[i].iov_len;
+ if (npages == 1)
+ len = min_t(int, len, PAGE_SIZE - base);
+ else if (base)
+ break;
+ payload -= len;
+ if (payload <= 0)
+ goto proceed;
+ if (npages == 1 || (len & ~PAGE_MASK))
+ break;
+ }
+ }
+
+ if ((((unsigned long)iov[1].iov_base & ~PAGE_MASK)
+ - NET_SKB_PAD - NET_IP_ALIGN) >= 0)
+ goto proceed;
+
+ return -EINVAL;
+proceed:
+ /* skip the virtnet head */
+ if (count > 1) {
+ iov++;
+ count--;
+ }
+
+ /* Translate address to kernel */
+ info = alloc_page_info(pool, iocb, iov, count, frags, npages, 0);
+ if (!info)
+ return -ENOMEM;
+ info->hdr[0].iov_base = iocb->ki_iovec[0].iov_base;
+ info->hdr[0].iov_len = iocb->ki_iovec[0].iov_len;
+ iocb->ki_iovec[0].iov_len = 0;
+ iocb->ki_left = 0;
+ info->desc_pos = iocb->ki_pos;
+
+ if (count > 1) {
+ iov--;
+ count++;
+ }
+
+ memcpy(info->iov, iov, sizeof(struct iovec) * count);
+
+ spin_lock_irqsave(&pool->read_lock, flag);
+ list_add_tail(&info->list, &pool->readq);
+ spin_unlock_irqrestore(&pool->read_lock, flag);
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(async_recvmsg);
+
+static int mp_recvmsg(struct kiocb *iocb, struct socket *sock,
+ struct msghdr *m, size_t total_len,
+ int flags)
+{
+ struct mp_struct *mp = container_of(sock->sk, struct mp_sock, sk)->mp;
+ struct page_pool *pool;
+ struct iovec *iov = m->msg_iov;
+ int count = m->msg_iovlen;
+
+ pool = mp->pool;
+ if (!pool)
+ return -EINVAL;
+
+ return async_recvmsg(iocb, pool, iov, count, flags);
+}
+
+/* Ops structure to mimic raw sockets with mp device */
+static const struct proto_ops mp_socket_ops = {
+ .sendmsg = mp_sendmsg,
+ .recvmsg = mp_recvmsg,
+};
+
+static struct proto mp_proto = {
+ .name = "mp",
+ .owner = THIS_MODULE,
+ .obj_size = sizeof(struct mp_sock),
+};
+
+static int mp_chr_open(struct inode *inode, struct file * file)
+{
+ struct mp_file *mfile;
+ cycle_kernel_lock();
+
+ pr_debug("mp: mp_chr_open\n");
+ mfile = kzalloc(sizeof(*mfile), GFP_KERNEL);
+ if (!mfile)
+ return -ENOMEM;
+ atomic_set(&mfile->count, 0);
+ mfile->mp = NULL;
+ mfile->net = get_net(current->nsproxy->net_ns);
+ file->private_data = mfile;
+ return 0;
+}
+
+static int mp_attach(struct mp_struct *mp, struct file *file)
+{
+ struct mp_file *mfile = file->private_data;
+ int err;
+
+ netif_tx_lock_bh(mp->dev);
+
+ err = -EINVAL;
+
+ if (mfile->mp)
+ goto out;
+
+ err = -EBUSY;
+ if (mp->mfile)
+ goto out;
+
+ err = 0;
+ mfile->mp = mp;
+ mp->mfile = mfile;
+ mp->socket.file = file;
+ sock_hold(mp->socket.sk);
+ atomic_inc(&mfile->count);
+
+out:
+ netif_tx_unlock_bh(mp->dev);
+ return err;
+}
+
+static int do_unbind(struct mp_file *mfile)
+{
+ struct mp_struct *mp = mp_get(mfile);
+
+ if (mp) {
+ mp_detach(mp);
+ sock_put(mp->socket.sk);
+ }
+ mp_put(mfile);
+ return 0;
+}
+
+static long mp_chr_ioctl(struct file *file, unsigned int cmd,
+ unsigned long arg)
+{
+ struct mp_file *mfile = file->private_data;
+ struct mp_struct *mp;
+ struct net_device *dev;
+ struct page_pool *pool;
+ void __user* argp = (void __user *)arg;
+ unsigned long __user *limitp = argp;
+ struct ifreq ifr;
+ struct sock *sk;
+ unsigned long limit, locked, lock_limit;
+ int ret;
+
+ ret = -EINVAL;
+
+ switch (cmd) {
+ case MPASSTHRU_BINDDEV:
+ ret = -EFAULT;
+ if (copy_from_user(&ifr, argp, sizeof ifr))
+ break;
+
+ ifr.ifr_name[IFNAMSIZ-1] = '\0';
+
+ ret = -ENODEV;
+
+ rtnl_lock();
+ dev = dev_get_by_name(mfile->net, ifr.ifr_name);
+ if (!dev) {
+ rtnl_unlock();
+ break;
+ }
+ dev_bond_hold(dev);
+ mutex_lock(&mp_mutex);
+
+ ret = -EBUSY;
+
+ /* the device can be only bind once */
+ if (dev_is_mpassthru(dev))
+ goto err_dev_put;
+
+ ret = -EFAULT;
+
+ if (!(dev->features & NETIF_F_SG)) {
+ pr_debug("The device has no SG features.\n");
+ goto err_dev_put;
+ }
+ mp = mfile->mp;
+ if (mp)
+ goto err_dev_put;
+
+ mp = kzalloc(sizeof(*mp), GFP_KERNEL);
+ if (!mp) {
+ ret = -ENOMEM;
+ goto err_dev_put;
+ }
+ mp->dev = dev;
+ mp->mm = get_task_mm(current);
+ ret = -ENOMEM;
+
+ sk = sk_alloc(mfile->net, AF_UNSPEC, GFP_KERNEL, &mp_proto);
+ if (!sk)
+ goto err_free_mp;
+
+ mp->socket.wq = &mp->wq;
+ init_waitqueue_head(&mp->wq.wait);
+ mp->socket.ops = &mp_socket_ops;
+ sock_init_data(&mp->socket, sk);
+ sk->sk_sndbuf = INT_MAX;
+ container_of(sk, struct mp_sock, sk)->mp = mp;
+
+ sk->sk_destruct = mp_sock_destruct;
+ sk->sk_data_ready = mp_sock_data_ready;
+ sk->sk_write_space = mp_sock_write_space;
+ sk->sk_state_change = mp_sock_state_change;
+
+ pool = page_pool_create(dev, &mp->socket);
+ if (!pool) {
+ ret = -EFAULT;
+ goto err_free_sk;
+ }
+
+ ret = mp_attach(mp, file);
+ if (ret < 0)
+ goto err_free_sk;
+
+ ret = mp_page_pool_attach(mp, pool);
+ if (ret < 0)
+ goto err_free_sk;
+ dev_bond_put(dev);
+ dev_put(dev);
+ dev_change_state(dev);
+out:
+ mutex_unlock(&mp_mutex);
+ rtnl_unlock();
+ break;
+err_free_sk:
+ sk_free(sk);
+err_free_mp:
+ mfile->mp = NULL;
+ kfree(mp);
+err_dev_put:
+ dev_bond_put(dev);
+ dev_put(dev);
+ goto out;
+
+ case MPASSTHRU_UNBINDDEV:
+ rtnl_lock();
+ ret = do_unbind(mfile);
+ rtnl_unlock();
+ break;
+
+ case MPASSTHRU_SET_MEM_LOCKED:
+ ret = copy_from_user(&limit, limitp, sizeof limit);
+ if (ret < 0)
+ return ret;
+
+ mp = mp_get(mfile);
+ if (!mp)
+ return -ENODEV;
+
+ mutex_lock(&mp_mutex);
+ if (mp->mm != current->mm) {
+ mutex_unlock(&mp_mutex);
+ return -EPERM;
+ }
+
+ limit = PAGE_ALIGN(limit) >> PAGE_SHIFT;
+ down_write(&mp->mm->mmap_sem);
+ if (!mp->pool->locked_pages)
+ mp->pool->orig_locked_vm = mp->mm->locked_vm;
+ locked = limit + mp->pool->orig_locked_vm;
+ lock_limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT;
+
+ if ((locked > lock_limit) && !capable(CAP_IPC_LOCK)) {
+ up_write(&mp->mm->mmap_sem);
+ mutex_unlock(&mp_mutex);
+ mp_put(mfile);
+ return -ENOMEM;
+ }
+ mp->mm->locked_vm = locked;
+ up_write(&mp->mm->mmap_sem);
+
+ mp->pool->locked_pages = limit;
+ mutex_unlock(&mp_mutex);
+
+ mp_put(mfile);
+ return 0;
+
+ case MPASSTHRU_GET_MEM_LOCKED_NEED:
+ limit = DEFAULT_NEED;
+ return copy_to_user(limitp, &limit, sizeof limit);
+
+
+ default:
+ break;
+ }
+ return ret;
+}
+
+static unsigned int mp_chr_poll(struct file *file, poll_table * wait)
+{
+ struct mp_file *mfile = file->private_data;
+ struct mp_struct *mp = mp_get(mfile);
+ struct sock *sk;
+ unsigned int mask = 0;
+
+ if (!mp)
+ return POLLERR;
+
+ sk = mp->socket.sk;
+
+ poll_wait(file, &mp->wq.wait, wait);
+
+ if (!skb_queue_empty(&sk->sk_receive_queue))
+ mask |= POLLIN | POLLRDNORM;
+
+ if (sock_writeable(sk) ||
+ (!test_and_set_bit(SOCK_ASYNC_NOSPACE, &sk->sk_socket->flags) &&
+ sock_writeable(sk)))
+ mask |= POLLOUT | POLLWRNORM;
+
+ if (mp->dev->reg_state != NETREG_REGISTERED)
+ mask = POLLERR;
+
+ mp_put(mfile);
+ return mask;
+}
+
+static ssize_t mp_chr_aio_write(struct kiocb *iocb, const struct iovec *iov,
+ unsigned long count, loff_t pos)
+{
+ struct file *file = iocb->ki_filp;
+ struct mp_struct *mp = mp_get(file->private_data);
+ struct sock *sk = mp->socket.sk;
+ struct sk_buff *skb;
+ int len, err;
+ ssize_t result = 0;
+
+ if (!mp)
+ return -EBADFD;
+
+ /* currently, async is not supported.
+ * but we may support real async aio from user application,
+ * maybe qemu virtio-net backend.
+ */
+ if (!is_sync_kiocb(iocb))
+ return -EFAULT;
+
+ len = iov_length(iov, count);
+
+ if (unlikely(len < ETH_HLEN))
+ return -EINVAL;
+
+ skb = sock_alloc_send_skb(sk, len + NET_IP_ALIGN,
+ file->f_flags & O_NONBLOCK, &err);
+
+ if (!skb)
+ return -ENOMEM;
+
+ skb_reserve(skb, NET_IP_ALIGN);
+ skb_put(skb, len);
+
+ if (skb_copy_datagram_from_iovec(skb, 0, iov, 0, len)) {
+ kfree_skb(skb);
+ return -EAGAIN;
+ }
+
+ skb->protocol = eth_type_trans(skb, mp->dev);
+ skb->dev = mp->dev;
+
+ dev_queue_xmit(skb);
+
+ mp_put(file->private_data);
+ return result;
+}
+
+static int mp_chr_close(struct inode *inode, struct file *file)
+{
+ struct mp_file *mfile = file->private_data;
+
+ /*
+ * Ignore return value since an error only means there was nothing to
+ * do
+ */
+ rtnl_lock();
+ do_unbind(mfile);
+ rtnl_unlock();
+ put_net(mfile->net);
+ kfree(mfile);
+
+ return 0;
+}
+
+#ifdef CONFIG_COMPAT
+static long mp_chr_compat_ioctl(struct file *f, unsigned int ioctl,
+ unsigned long arg)
+{
+ return mp_chr_ioctl(f, ioctl, (unsigned long)compat_ptr(arg));
+}
+#endif
+
+static const struct file_operations mp_fops = {
+ .owner = THIS_MODULE,
+ .llseek = no_llseek,
+ .write = do_sync_write,
+ .aio_write = mp_chr_aio_write,
+ .poll = mp_chr_poll,
+ .unlocked_ioctl = mp_chr_ioctl,
+#ifdef CONFIG_COMPAT
+ .compat_ioctl = mp_chr_compat_ioctl,
+#endif
+ .open = mp_chr_open,
+ .release = mp_chr_close,
+};
+
+static struct miscdevice mp_miscdev = {
+ .minor = MISC_DYNAMIC_MINOR,
+ .name = "mp",
+ .nodename = "net/mp",
+ .fops = &mp_fops,
+};
+
+static int mp_device_event(struct notifier_block *unused,
+ unsigned long event, void *ptr)
+{
+ struct net_device *dev = ptr;
+ struct mp_port *port;
+ struct mp_struct *mp = NULL;
+ struct socket *sock = NULL;
+ struct sock *sk;
+
+ port = dev->mp_port;
+ if (port == NULL)
+ return NOTIFY_DONE;
+
+ switch (event) {
+ case NETDEV_UNREGISTER:
+ sock = dev->mp_port->sock;
+ mp = container_of(sock->sk, struct mp_sock, sk)->mp;
+ do_unbind(mp->mfile);
+ break;
+ case NETDEV_CHANGE:
+ sk = dev->mp_port->sock->sk;
+ sk->sk_state_change(sk);
+ break;
+ }
+ return NOTIFY_DONE;
+}
+
+static struct notifier_block mp_notifier_block __read_mostly = {
+ .notifier_call = mp_device_event,
+};
+
+static int mp_init(void)
+{
+ int err = 0;
+
+ ext_page_info_cache = kmem_cache_create("skb_page_info",
+ sizeof(struct page_info),
+ 0, SLAB_HWCACHE_ALIGN, NULL);
+ if (!ext_page_info_cache)
+ return -ENOMEM;
+
+ err = misc_register(&mp_miscdev);
+ if (err) {
+ printk(KERN_ERR "mp: Can't register misc device\n");
+ kmem_cache_destroy(ext_page_info_cache);
+ } else {
+ printk(KERN_INFO "Registering mp misc device - minor = %d\n",
+ mp_miscdev.minor);
+ register_netdevice_notifier(&mp_notifier_block);
+ }
+ return err;
+}
+
+void mp_exit(void)
+{
+ unregister_netdevice_notifier(&mp_notifier_block);
+ misc_deregister(&mp_miscdev);
+ kmem_cache_destroy(ext_page_info_cache);
+}
+
+/* Get an underlying socket object from mp file. Returns error unless file is
+ * attached to a device. The returned object works like a packet socket, it
+ * can be used for sock_sendmsg/sock_recvmsg. The caller is responsible for
+ * holding a reference to the file for as long as the socket is in use. */
+struct socket *mp_get_socket(struct file *file)
+{
+ struct mp_file *mfile = file->private_data;
+ struct mp_struct *mp;
+
+ if (file->f_op != &mp_fops)
+ return ERR_PTR(-EINVAL);
+ mp = mp_get(mfile);
+ if (!mp)
+ return ERR_PTR(-EBADFD);
+ mp_put(mfile);
+ return &mp->socket;
+}
+EXPORT_SYMBOL_GPL(mp_get_socket);
+
+module_init(mp_init);
+module_exit(mp_exit);
+MODULE_AUTHOR(DRV_COPYRIGHT);
+MODULE_DESCRIPTION(DRV_DESCRIPTION);
+MODULE_LICENSE("GPL v2");
--
1.7.3
^ permalink raw reply related
* [PATCH v15 14/17]Add a kconfig entry and make entry for mp device.
From: xiaohui.xin @ 2010-11-09 9:03 UTC (permalink / raw)
To: netdev, kvm, linux-kernel, mst, mingo, davem, herbert, jdike; +Cc: Xin Xiaohui
In-Reply-To: <fc6e95d63a2c62aaf77f8ded22fc43ccefcdbbff.1289280885.git.xiaohui.xin@intel.com>
From: Xin Xiaohui <xiaohui.xin@intel.com>
Signed-off-by: Xin Xiaohui <xiaohui.xin@intel.com>
Reviewed-by: Jeff Dike <jdike@linux.intel.com>
---
drivers/vhost/Kconfig | 10 ++++++++++
drivers/vhost/Makefile | 2 ++
2 files changed, 12 insertions(+), 0 deletions(-)
diff --git a/drivers/vhost/Kconfig b/drivers/vhost/Kconfig
index e4e2fd1..a6b8cbf 100644
--- a/drivers/vhost/Kconfig
+++ b/drivers/vhost/Kconfig
@@ -9,3 +9,13 @@ config VHOST_NET
To compile this driver as a module, choose M here: the module will
be called vhost_net.
+config MEDIATE_PASSTHRU
+ tristate "mediate passthru network driver (EXPERIMENTAL)"
+ depends on VHOST_NET
+ ---help---
+ zerocopy network I/O support, we call it as mediate passthru to
+ be distiguish with hardare passthru.
+
+ To compile this driver as a module, choose M here: the module will
+ be called mpassthru.
+
diff --git a/drivers/vhost/Makefile b/drivers/vhost/Makefile
index 72dd020..c18b9fc 100644
--- a/drivers/vhost/Makefile
+++ b/drivers/vhost/Makefile
@@ -1,2 +1,4 @@
obj-$(CONFIG_VHOST_NET) += vhost_net.o
vhost_net-y := vhost.o net.o
+
+obj-$(CONFIG_MEDIATE_PASSTHRU) += mpassthru.o
--
1.7.3
^ permalink raw reply related
* [PATCH v15 15/17] Provides multiple submits and asynchronous notifications.
From: xiaohui.xin @ 2010-11-09 9:03 UTC (permalink / raw)
To: netdev, kvm, linux-kernel, mst, mingo, davem, herbert, jdike; +Cc: Xin Xiaohui
In-Reply-To: <fc6e95d63a2c62aaf77f8ded22fc43ccefcdbbff.1289280885.git.xiaohui.xin@intel.com>
From: Xin Xiaohui <xiaohui.xin@intel.com>
The vhost-net backend now only supports synchronous send/recv
operations. The patch provides multiple submits and asynchronous
notifications. This is needed for zero-copy case.
Signed-off-by: Xin Xiaohui <xiaohui.xin@intel.com>
---
drivers/vhost/net.c | 355 +++++++++++++++++++++++++++++++++++++++++++++----
drivers/vhost/vhost.c | 78 +++++++++++
drivers/vhost/vhost.h | 15 ++-
3 files changed, 423 insertions(+), 25 deletions(-)
diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c
index 7c80082..17c599a 100644
--- a/drivers/vhost/net.c
+++ b/drivers/vhost/net.c
@@ -24,6 +24,8 @@
#include <linux/if_arp.h>
#include <linux/if_tun.h>
#include <linux/if_macvlan.h>
+#include <linux/mpassthru.h>
+#include <linux/aio.h>
#include <net/sock.h>
@@ -32,6 +34,7 @@
/* Max number of bytes transferred before requeueing the job.
* Using this limit prevents one virtqueue from starving others. */
#define VHOST_NET_WEIGHT 0x80000
+static struct kmem_cache *notify_cache;
enum {
VHOST_NET_VQ_RX = 0,
@@ -49,6 +52,7 @@ struct vhost_net {
struct vhost_dev dev;
struct vhost_virtqueue vqs[VHOST_NET_VQ_MAX];
struct vhost_poll poll[VHOST_NET_VQ_MAX];
+ struct kmem_cache *cache;
/* Tells us whether we are polling a socket for TX.
* We only do this when socket buffer fills up.
* Protected by tx vq lock. */
@@ -109,11 +113,184 @@ static void tx_poll_start(struct vhost_net *net, struct socket *sock)
net->tx_poll_state = VHOST_NET_POLL_STARTED;
}
+struct kiocb *notify_dequeue(struct vhost_virtqueue *vq)
+{
+ struct kiocb *iocb = NULL;
+ unsigned long flags;
+
+ spin_lock_irqsave(&vq->notify_lock, flags);
+ if (!list_empty(&vq->notifier)) {
+ iocb = list_first_entry(&vq->notifier,
+ struct kiocb, ki_list);
+ list_del(&iocb->ki_list);
+ }
+ spin_unlock_irqrestore(&vq->notify_lock, flags);
+ return iocb;
+}
+
+static void handle_iocb(struct kiocb *iocb)
+{
+ struct vhost_virtqueue *vq = iocb->private;
+ unsigned long flags;
+
+ spin_lock_irqsave(&vq->notify_lock, flags);
+ list_add_tail(&iocb->ki_list, &vq->notifier);
+ spin_unlock_irqrestore(&vq->notify_lock, flags);
+}
+
+static int is_async_vq(struct vhost_virtqueue *vq)
+{
+ return (vq->link_state == VHOST_VQ_LINK_ASYNC);
+}
+
+static void handle_async_rx_events_notify(struct vhost_net *net,
+ struct vhost_virtqueue *vq,
+ struct socket *sock)
+{
+ struct kiocb *iocb = NULL;
+ struct vhost_log *vq_log = NULL;
+ int rx_total_len = 0;
+ unsigned int head, log, in, out;
+ int size;
+
+ if (!is_async_vq(vq))
+ return;
+
+ if (sock->sk->sk_data_ready)
+ sock->sk->sk_data_ready(sock->sk, 0);
+
+ vq_log = unlikely(vhost_has_feature(&net->dev, VHOST_F_LOG_ALL)) ?
+ vq->log : NULL;
+
+ while ((iocb = notify_dequeue(vq)) != NULL) {
+ if (!iocb->ki_left) {
+ vhost_add_used_and_signal(&net->dev, vq,
+ iocb->ki_pos, iocb->ki_nbytes);
+ size = iocb->ki_nbytes;
+ head = iocb->ki_pos;
+ rx_total_len += iocb->ki_nbytes;
+
+ if (iocb->ki_dtor)
+ iocb->ki_dtor(iocb);
+ kmem_cache_free(net->cache, iocb);
+
+ /* when log is enabled, recomputing the log is needed,
+ * since these buffers are in async queue, may not get
+ * the log info before.
+ */
+ if (unlikely(vq_log)) {
+ if (!log)
+ __vhost_get_vq_desc(&net->dev, vq,
+ vq->iov,
+ ARRAY_SIZE(vq->iov),
+ &out, &in, vq_log,
+ &log, head);
+ vhost_log_write(vq, vq_log, log, size);
+ }
+ if (unlikely(rx_total_len >= VHOST_NET_WEIGHT)) {
+ vhost_poll_queue(&vq->poll);
+ break;
+ }
+ } else {
+ int i = 0;
+ int count = iocb->ki_left;
+ int hc = count;
+ while (count--) {
+ if (iocb) {
+ vq->heads[i].id = iocb->ki_pos;
+ vq->heads[i].len = iocb->ki_nbytes;
+ size = iocb->ki_nbytes;
+ head = iocb->ki_pos;
+ rx_total_len += iocb->ki_nbytes;
+
+ if (iocb->ki_dtor)
+ iocb->ki_dtor(iocb);
+ kmem_cache_free(net->cache, iocb);
+
+ if (unlikely(vq_log)) {
+ if (!log)
+ __vhost_get_vq_desc(
+ &net->dev, vq, vq->iov,
+ ARRAY_SIZE(vq->iov),
+ &out, &in, vq_log,
+ &log, head);
+ vhost_log_write(
+ vq, vq_log, log, size);
+ }
+ } else
+ break;
+
+ i++;
+ if (count)
+ iocb = notify_dequeue(vq);
+ }
+ vhost_add_used_and_signal_n(
+ &net->dev, vq, vq->heads, hc);
+ }
+ }
+}
+
+static void handle_async_tx_events_notify(struct vhost_net *net,
+ struct vhost_virtqueue *vq)
+{
+ struct kiocb *iocb = NULL;
+ struct list_head *entry, *tmp;
+ unsigned long flags;
+ int tx_total_len = 0;
+
+ if (!is_async_vq(vq))
+ return;
+
+ spin_lock_irqsave(&vq->notify_lock, flags);
+ list_for_each_safe(entry, tmp, &vq->notifier) {
+ iocb = list_entry(entry,
+ struct kiocb, ki_list);
+ if (!iocb->ki_flags)
+ continue;
+ list_del(&iocb->ki_list);
+ vhost_add_used_and_signal(&net->dev, vq,
+ iocb->ki_pos, 0);
+ tx_total_len += iocb->ki_nbytes;
+
+ if (iocb->ki_dtor)
+ iocb->ki_dtor(iocb);
+
+ kmem_cache_free(net->cache, iocb);
+ if (unlikely(tx_total_len >= VHOST_NET_WEIGHT)) {
+ vhost_poll_queue(&vq->poll);
+ break;
+ }
+ }
+ spin_unlock_irqrestore(&vq->notify_lock, flags);
+}
+
+static struct kiocb *create_iocb(struct vhost_net *net,
+ struct vhost_virtqueue *vq,
+ unsigned head)
+{
+ struct kiocb *iocb = NULL;
+
+ if (!is_async_vq(vq))
+ return NULL;
+
+ iocb = kmem_cache_zalloc(net->cache, GFP_KERNEL);
+ if (!iocb)
+ return NULL;
+ iocb->private = vq;
+ iocb->ki_pos = head;
+ iocb->ki_dtor = handle_iocb;
+ if (vq == &net->dev.vqs[VHOST_NET_VQ_RX])
+ iocb->ki_user_data = vq->num;
+ iocb->ki_iovec = vq->hdr;
+ return iocb;
+}
+
/* Expects to be always run from workqueue - which acts as
* read-size critical section for our kind of RCU. */
static void handle_tx(struct vhost_net *net)
{
struct vhost_virtqueue *vq = &net->dev.vqs[VHOST_NET_VQ_TX];
+ struct kiocb *iocb = NULL;
unsigned out, in, s;
int head;
struct msghdr msg = {
@@ -146,6 +323,10 @@ static void handle_tx(struct vhost_net *net)
if (wmem < sock->sk->sk_sndbuf / 2)
tx_poll_stop(net);
hdr_size = vq->vhost_hlen;
+ if (!vq->vhost_hlen && is_async_vq(vq))
+ hdr_size = vq->sock_hlen;
+
+ handle_async_tx_events_notify(net, vq);
for (;;) {
head = vhost_get_vq_desc(&net->dev, vq, vq->iov,
@@ -157,11 +338,14 @@ static void handle_tx(struct vhost_net *net)
break;
/* Nothing new? Wait for eventfd to tell us they refilled. */
if (head == vq->num) {
- wmem = atomic_read(&sock->sk->sk_wmem_alloc);
- if (wmem >= sock->sk->sk_sndbuf * 3 / 4) {
- tx_poll_start(net, sock);
- set_bit(SOCK_ASYNC_NOSPACE, &sock->flags);
- break;
+ if (!is_async_vq(vq)) {
+ wmem = atomic_read(&sock->sk->sk_wmem_alloc);
+ if (wmem >= sock->sk->sk_sndbuf * 3 / 4) {
+ tx_poll_start(net, sock);
+ set_bit(SOCK_ASYNC_NOSPACE,
+ &sock->flags);
+ break;
+ }
}
if (unlikely(vhost_enable_notify(vq))) {
vhost_disable_notify(vq);
@@ -178,6 +362,13 @@ static void handle_tx(struct vhost_net *net)
s = move_iovec_hdr(vq->iov, vq->hdr, hdr_size, out);
msg.msg_iovlen = out;
len = iov_length(vq->iov, out);
+ /* if async operations supported */
+ if (is_async_vq(vq)) {
+ iocb = create_iocb(net, vq, head);
+ if (!iocb)
+ break;
+ }
+
/* Sanity check */
if (!len) {
vq_err(vq, "Unexpected header len for TX: "
@@ -186,12 +377,18 @@ static void handle_tx(struct vhost_net *net)
break;
}
/* TODO: Check specific error and bomb out unless ENOBUFS? */
- err = sock->ops->sendmsg(NULL, sock, &msg, len);
+ err = sock->ops->sendmsg(iocb, sock, &msg, len);
if (unlikely(err < 0)) {
+ if (is_async_vq(vq))
+ kmem_cache_free(net->cache, iocb);
vhost_discard_vq_desc(vq, 1);
tx_poll_start(net, sock);
break;
}
+
+ if (is_async_vq(vq))
+ continue;
+
if (err != len)
pr_debug("Truncated TX packet: "
" len %d != %zd\n", err, len);
@@ -203,6 +400,8 @@ static void handle_tx(struct vhost_net *net)
}
}
+ handle_async_tx_events_notify(net, vq);
+
mutex_unlock(&vq->mutex);
unuse_mm(net->dev.mm);
}
@@ -396,7 +595,8 @@ static void handle_rx_big(struct vhost_net *net)
static void handle_rx_mergeable(struct vhost_net *net)
{
struct vhost_virtqueue *vq = &net->dev.vqs[VHOST_NET_VQ_RX];
- unsigned uninitialized_var(in), log;
+ unsigned uninitialized_var(in), log, out;
+ struct kiocb *iocb;
struct vhost_log *vq_log;
struct msghdr msg = {
.msg_name = NULL,
@@ -417,28 +617,44 @@ static void handle_rx_mergeable(struct vhost_net *net)
size_t vhost_hlen, sock_hlen;
size_t vhost_len, sock_len;
struct socket *sock = rcu_dereference(vq->private_data);
- if (!sock || skb_queue_empty(&sock->sk->sk_receive_queue))
+ if (!sock || (skb_queue_empty(&sock->sk->sk_receive_queue) &&
+ !is_async_vq(vq)))
return;
-
use_mm(net->dev.mm);
mutex_lock(&vq->mutex);
vhost_disable_notify(vq);
vhost_hlen = vq->vhost_hlen;
sock_hlen = vq->sock_hlen;
+ /* In async cases, when write log is enabled, in case the submitted
+ * buffers did not get log info before the log enabling, so we'd
+ * better recompute the log info when needed. We do this in
+ * handle_async_rx_events_notify().
+ */
+
vq_log = unlikely(vhost_has_feature(&net->dev, VHOST_F_LOG_ALL)) ?
vq->log : NULL;
- while ((sock_len = peek_head_len(sock->sk))) {
- sock_len += sock_hlen;
- vhost_len = sock_len + vhost_hlen;
- headcount = get_rx_bufs(vq, vq->heads, vhost_len,
+ handle_async_rx_events_notify(net, vq, sock);
+
+ while (is_async_vq(vq) || (sock_len = peek_head_len(sock->sk))) {
+ if (is_async_vq(vq))
+ headcount = vhost_get_vq_desc(&net->dev, vq, vq->iov,
+ ARRAY_SIZE(vq->iov),
+ &out, &in,
+ vq->log, &log);
+ else {
+ sock_len += sock_hlen;
+ vhost_len = sock_len + vhost_hlen;
+ headcount = get_rx_bufs(vq, vq->heads, vhost_len,
&in, vq_log, &log);
+ }
/* On error, stop handling until the next kick. */
if (unlikely(headcount < 0))
break;
/* OK, now we need to know about added descriptors. */
- if (!headcount) {
+ if ((!headcount && !is_async_vq(vq)) ||
+ (headcount == vq->num && is_async_vq(vq))) {
if (unlikely(vhost_enable_notify(vq))) {
/* They have slipped one in as we were
* doing that: check again. */
@@ -450,16 +666,41 @@ static void handle_rx_mergeable(struct vhost_net *net)
break;
}
/* We don't need to be notified again. */
- if (unlikely((vhost_hlen)))
- /* Skip header. TODO: support TSO. */
- move_iovec_hdr(vq->iov, vq->hdr, vhost_hlen, in);
- else
- /* Copy the header for use in VIRTIO_NET_F_MRG_RXBUF:
- * needed because sendmsg can modify msg_iov. */
- copy_iovec_hdr(vq->iov, vq->hdr, sock_hlen, in);
+ if (unlikely((vhost_hlen))) {
+ if (is_async_vq(vq))
+ vq->hdr[0].iov_len = vhost_hlen;
+ else
+ /* Skip header. TODO: support TSO. */
+ move_iovec_hdr(vq->iov, vq->hdr,
+ vhost_hlen, in);
+ } else {
+ if (is_async_vq(vq))
+ vq->hdr[0].iov_len = sock_hlen;
+ else
+ /* Copy the header for use in
+ * VIRTIO_NET_F_MRG_RXBUF:
+ * needed because sendmsg can
+ * modify msg_iov. */
+ copy_iovec_hdr(vq->iov, vq->hdr,
+ sock_hlen, in);
+ }
msg.msg_iovlen = in;
- err = sock->ops->recvmsg(NULL, sock, &msg,
+ if (is_async_vq(vq)) {
+ iocb = create_iocb(net, vq, headcount);
+ if (!iocb)
+ break;
+ }
+ err = sock->ops->recvmsg(iocb, sock, &msg,
sock_len, MSG_DONTWAIT | MSG_TRUNC);
+ if (is_async_vq(vq)) {
+ if (err < 0) {
+ kmem_cache_free(net->cache, iocb);
+ vhost_discard_vq_desc(vq, headcount);
+ break;
+ }
+ continue;
+ }
+
/* Userspace might have consumed the packet meanwhile:
* it's not supposed to do this usually, but might be hard
* to prevent. Discard data we got (if any) and keep going. */
@@ -496,6 +737,8 @@ static void handle_rx_mergeable(struct vhost_net *net)
}
}
+ handle_async_rx_events_notify(net, vq, sock);
+
mutex_unlock(&vq->mutex);
unuse_mm(net->dev.mm);
}
@@ -561,6 +804,7 @@ static int vhost_net_open(struct inode *inode, struct file *f)
vhost_poll_init(n->poll + VHOST_NET_VQ_TX, handle_tx_net, POLLOUT, dev);
vhost_poll_init(n->poll + VHOST_NET_VQ_RX, handle_rx_net, POLLIN, dev);
n->tx_poll_state = VHOST_NET_POLL_DISABLED;
+ n->cache = NULL;
f->private_data = n;
@@ -624,6 +868,21 @@ static void vhost_net_flush(struct vhost_net *n)
vhost_net_flush_vq(n, VHOST_NET_VQ_RX);
}
+static void vhost_async_cleanup(struct vhost_net *n)
+{
+ /* clean the notifier */
+ struct vhost_virtqueue *vq;
+ struct kiocb *iocb = NULL;
+ if (n->cache) {
+ vq = &n->dev.vqs[VHOST_NET_VQ_RX];
+ while ((iocb = notify_dequeue(vq)) != NULL)
+ kmem_cache_free(n->cache, iocb);
+ vq = &n->dev.vqs[VHOST_NET_VQ_TX];
+ while ((iocb = notify_dequeue(vq)) != NULL)
+ kmem_cache_free(n->cache, iocb);
+ }
+}
+
static int vhost_net_release(struct inode *inode, struct file *f)
{
struct vhost_net *n = f->private_data;
@@ -640,6 +899,7 @@ static int vhost_net_release(struct inode *inode, struct file *f)
/* We do an extra flush before freeing memory,
* since jobs can re-queue themselves. */
vhost_net_flush(n);
+ vhost_async_cleanup(n);
kfree(n);
return 0;
}
@@ -691,21 +951,61 @@ static struct socket *get_tap_socket(int fd)
return sock;
}
-static struct socket *get_socket(int fd)
+static struct socket *get_mp_socket(int fd)
+{
+ struct file *file = fget(fd);
+ struct socket *sock;
+ if (!file)
+ return ERR_PTR(-EBADF);
+ sock = mp_get_socket(file);
+ if (IS_ERR(sock))
+ fput(file);
+ return sock;
+}
+
+static struct socket *get_socket(struct vhost_virtqueue *vq, int fd,
+ enum vhost_vq_link_state *state)
{
struct socket *sock;
/* special case to disable backend */
if (fd == -1)
return NULL;
+
+ *state = VHOST_VQ_LINK_SYNC;
+
sock = get_raw_socket(fd);
if (!IS_ERR(sock))
return sock;
sock = get_tap_socket(fd);
if (!IS_ERR(sock))
return sock;
+ /* If we dont' have notify_cache, then dont do mpassthru */
+ if (!notify_cache)
+ return ERR_PTR(-ENOTSOCK);
+ /* If we don't have mergeable buffer then dont do mpassthru */
+ if (vhost_has_feature(vq->dev, VIRTIO_NET_F_MRG_RXBUF)) {
+ sock = get_mp_socket(fd);
+ if (!IS_ERR(sock)) {
+ *state = VHOST_VQ_LINK_ASYNC;
+ return sock;
+ }
+ }
return ERR_PTR(-ENOTSOCK);
}
+static void vhost_init_link_state(struct vhost_net *n, int index)
+{
+ struct vhost_virtqueue *vq = n->vqs + index;
+
+ WARN_ON(!mutex_is_locked(&vq->mutex));
+ if (vq->link_state == VHOST_VQ_LINK_ASYNC) {
+ INIT_LIST_HEAD(&vq->notifier);
+ spin_lock_init(&vq->notify_lock);
+ if (!n->cache)
+ n->cache = notify_cache;
+ }
+}
+
static long vhost_net_set_backend(struct vhost_net *n, unsigned index, int fd)
{
struct socket *sock, *oldsock;
@@ -729,12 +1029,14 @@ static long vhost_net_set_backend(struct vhost_net *n, unsigned index, int fd)
r = -EFAULT;
goto err_vq;
}
- sock = get_socket(fd);
+ sock = get_socket(vq, fd, &vq->link_state);
if (IS_ERR(sock)) {
r = PTR_ERR(sock);
goto err_vq;
}
+ vhost_init_link_state(n, index);
+
/* start polling new socket */
oldsock = vq->private_data;
if (sock != oldsock) {
@@ -879,6 +1181,9 @@ static struct miscdevice vhost_net_misc = {
static int vhost_net_init(void)
{
+ notify_cache = kmem_cache_create("vhost_kiocb",
+ sizeof(struct kiocb), 0,
+ SLAB_HWCACHE_ALIGN, NULL);
return misc_register(&vhost_net_misc);
}
module_init(vhost_net_init);
@@ -886,6 +1191,8 @@ module_init(vhost_net_init);
static void vhost_net_exit(void)
{
misc_deregister(&vhost_net_misc);
+ if (notify_cache)
+ kmem_cache_destroy(notify_cache);
}
module_exit(vhost_net_exit);
diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c
index dd3d6f7..295d9ab 100644
--- a/drivers/vhost/vhost.c
+++ b/drivers/vhost/vhost.c
@@ -1015,6 +1015,84 @@ static int get_indirect(struct vhost_dev *dev, struct vhost_virtqueue *vq,
return 0;
}
+/* To recompute the log */
+int __vhost_get_vq_desc(struct vhost_dev *dev, struct vhost_virtqueue *vq,
+ struct iovec iov[], unsigned int iov_size,
+ unsigned int *out_num, unsigned int *in_num,
+ struct vhost_log *log, unsigned int *log_num,
+ unsigned int head)
+{
+ struct vring_desc desc;
+ unsigned int i, found = 0;
+ int ret;
+
+ /* When we start there are none of either input nor output. */
+ *out_num = *in_num = 0;
+ if (unlikely(log))
+ *log_num = 0;
+
+ i = head;
+ do {
+ unsigned iov_count = *in_num + *out_num;
+ if (unlikely(i >= vq->num)) {
+ vq_err(vq, "Desc index is %u > %u, head = %u",
+ i, vq->num, head);
+ return -EINVAL;
+ }
+ if (unlikely(++found > vq->num)) {
+ vq_err(vq, "Loop detected: last one at %u "
+ "vq size %u head %u\n",
+ i, vq->num, head);
+ return -EINVAL;
+ }
+ ret = copy_from_user(&desc, vq->desc + i, sizeof desc);
+ if (unlikely(ret)) {
+ vq_err(vq, "Failed to get descriptor: idx %d addr %p\n",
+ i, vq->desc + i);
+ return -EFAULT;
+ }
+ if (desc.flags & VRING_DESC_F_INDIRECT) {
+ ret = get_indirect(dev, vq, iov, iov_size,
+ out_num, in_num,
+ log, log_num, &desc);
+ if (unlikely(ret < 0)) {
+ vq_err(vq, "Failure detected "
+ "in indirect descriptor at idx %d\n", i);
+ return ret;
+ }
+ continue;
+ }
+
+ ret = translate_desc(dev, desc.addr, desc.len, iov + iov_count,
+ iov_size - iov_count);
+ if (unlikely(ret < 0)) {
+ vq_err(vq, "Translation failure %d descriptor idx %d\n",
+ ret, i);
+ return ret;
+ }
+ if (desc.flags & VRING_DESC_F_WRITE) {
+ /* If this is an input descriptor,
+ * increment that count. */
+ *in_num += ret;
+ if (unlikely(log)) {
+ log[*log_num].addr = desc.addr;
+ log[*log_num].len = desc.len;
+ ++*log_num;
+ }
+ } else {
+ /* If it's an output descriptor, they're all supposed
+ * to come before any input descriptors. */
+ if (unlikely(*in_num)) {
+ vq_err(vq, "Descriptor has out after in: "
+ "idx %d\n", i);
+ return -EINVAL;
+ }
+ *out_num += ret;
+ }
+ } while ((i = next_desc(&desc)) != -1);
+
+ return head;
+}
/* This looks in the virtqueue and for the first available buffer, and converts
* it to an iovec for convenient access. Since descriptors consist of some
* number of output then some number of input descriptors, it's actually two
diff --git a/drivers/vhost/vhost.h b/drivers/vhost/vhost.h
index afd7729..915336d 100644
--- a/drivers/vhost/vhost.h
+++ b/drivers/vhost/vhost.h
@@ -55,6 +55,11 @@ struct vhost_log {
u64 len;
};
+enum vhost_vq_link_state {
+ VHOST_VQ_LINK_SYNC = 0,
+ VHOST_VQ_LINK_ASYNC = 1,
+};
+
/* The virtqueue structure describes a queue attached to a device. */
struct vhost_virtqueue {
struct vhost_dev *dev;
@@ -110,6 +115,10 @@ struct vhost_virtqueue {
/* Log write descriptors */
void __user *log_base;
struct vhost_log log[VHOST_NET_MAX_SG];
+ /* Differiate async socket for 0-copy from normal */
+ enum vhost_vq_link_state link_state;
+ struct list_head notifier;
+ spinlock_t notify_lock;
};
struct vhost_dev {
@@ -136,7 +145,11 @@ void vhost_dev_cleanup(struct vhost_dev *);
long vhost_dev_ioctl(struct vhost_dev *, unsigned int ioctl, unsigned long arg);
int vhost_vq_access_ok(struct vhost_virtqueue *vq);
int vhost_log_access_ok(struct vhost_dev *);
-
+int __vhost_get_vq_desc(struct vhost_dev *, struct vhost_virtqueue *,
+ struct iovec iov[], unsigned int iov_count,
+ unsigned int *out_num, unsigned int *in_num,
+ struct vhost_log *log, unsigned int *log_num,
+ unsigned int head);
int vhost_get_vq_desc(struct vhost_dev *, struct vhost_virtqueue *,
struct iovec iov[], unsigned int iov_count,
unsigned int *out_num, unsigned int *in_num,
--
1.7.3
^ permalink raw reply related
* [PATCH v15 16/17] An example how to modifiy NIC driver to use napi_gro_frags() interface
From: xiaohui.xin @ 2010-11-09 9:03 UTC (permalink / raw)
To: netdev, kvm, linux-kernel, mst, mingo, davem, herbert, jdike; +Cc: Xin Xiaohui
In-Reply-To: <fc6e95d63a2c62aaf77f8ded22fc43ccefcdbbff.1289280885.git.xiaohui.xin@intel.com>
From: Xin Xiaohui <xiaohui.xin@intel.com>
This example is made on ixgbe driver.
It provides API is_rx_buffer_mapped_as_page() to indicate
if the driver use napi_gro_frags() interface or not.
The example allocates 2 pages for DMA for one ring descriptor
using netdev_alloc_page(). When packets is coming, using
napi_gro_frags() to allocate skb and to receive the packets.
Signed-off-by: Xin Xiaohui <xiaohui.xin@intel.com>
---
drivers/net/ixgbe/ixgbe.h | 3 +
drivers/net/ixgbe/ixgbe_main.c | 163 +++++++++++++++++++++++++++++++---------
2 files changed, 131 insertions(+), 35 deletions(-)
diff --git a/drivers/net/ixgbe/ixgbe.h b/drivers/net/ixgbe/ixgbe.h
index 9e15eb9..89367ca 100644
--- a/drivers/net/ixgbe/ixgbe.h
+++ b/drivers/net/ixgbe/ixgbe.h
@@ -131,6 +131,9 @@ struct ixgbe_rx_buffer {
struct page *page;
dma_addr_t page_dma;
unsigned int page_offset;
+ u16 mapped_as_page;
+ struct page *page_skb;
+ unsigned int page_skb_offset;
};
struct ixgbe_queue_stats {
diff --git a/drivers/net/ixgbe/ixgbe_main.c b/drivers/net/ixgbe/ixgbe_main.c
index e32af43..a4a5263 100644
--- a/drivers/net/ixgbe/ixgbe_main.c
+++ b/drivers/net/ixgbe/ixgbe_main.c
@@ -1029,6 +1029,12 @@ static inline void ixgbe_release_rx_desc(struct ixgbe_hw *hw,
IXGBE_WRITE_REG(hw, IXGBE_RDT(rx_ring->reg_idx), val);
}
+static bool is_rx_buffer_mapped_as_page(struct ixgbe_rx_buffer *bi,
+ struct net_device *dev)
+{
+ return true;
+}
+
/**
* ixgbe_alloc_rx_buffers - Replace used receive buffers; packet split
* @adapter: address of board private structure
@@ -1045,13 +1051,17 @@ static void ixgbe_alloc_rx_buffers(struct ixgbe_adapter *adapter,
i = rx_ring->next_to_use;
bi = &rx_ring->rx_buffer_info[i];
+
while (cleaned_count--) {
rx_desc = IXGBE_RX_DESC_ADV(*rx_ring, i);
+ bi->mapped_as_page =
+ is_rx_buffer_mapped_as_page(bi, adapter->netdev);
+
if (!bi->page_dma &&
(rx_ring->flags & IXGBE_RING_RX_PS_ENABLED)) {
if (!bi->page) {
- bi->page = alloc_page(GFP_ATOMIC);
+ bi->page = netdev_alloc_page(adapter->netdev);
if (!bi->page) {
adapter->alloc_rx_page_failed++;
goto no_buffers;
@@ -1068,7 +1078,7 @@ static void ixgbe_alloc_rx_buffers(struct ixgbe_adapter *adapter,
DMA_FROM_DEVICE);
}
- if (!bi->skb) {
+ if (!bi->mapped_as_page && !bi->skb) {
struct sk_buff *skb;
/* netdev_alloc_skb reserves 32 bytes up front!! */
uint bufsz = rx_ring->rx_buf_len + SMP_CACHE_BYTES;
@@ -1088,6 +1098,19 @@ static void ixgbe_alloc_rx_buffers(struct ixgbe_adapter *adapter,
rx_ring->rx_buf_len,
DMA_FROM_DEVICE);
}
+
+ if (bi->mapped_as_page && !bi->page_skb) {
+ bi->page_skb = netdev_alloc_page(adapter->netdev);
+ if (!bi->page_skb) {
+ adapter->alloc_rx_page_failed++;
+ goto no_buffers;
+ }
+ bi->page_skb_offset = 0;
+ bi->dma = dma_map_page(&pdev->dev, bi->page_skb,
+ bi->page_skb_offset,
+ (PAGE_SIZE / 2),
+ PCI_DMA_FROMDEVICE);
+ }
/* Refresh the desc even if buffer_addrs didn't change because
* each write-back erases this info. */
if (rx_ring->flags & IXGBE_RING_RX_PS_ENABLED) {
@@ -1165,6 +1188,13 @@ struct ixgbe_rsc_cb {
bool delay_unmap;
};
+static bool is_no_buffer(struct ixgbe_rx_buffer *rx_buffer_info)
+{
+ return (!rx_buffer_info->skb ||
+ !rx_buffer_info->page_skb) &&
+ !rx_buffer_info->page;
+}
+
#define IXGBE_RSC_CB(skb) ((struct ixgbe_rsc_cb *)(skb)->cb)
static bool ixgbe_clean_rx_irq(struct ixgbe_q_vector *q_vector,
@@ -1174,6 +1204,7 @@ static bool ixgbe_clean_rx_irq(struct ixgbe_q_vector *q_vector,
struct ixgbe_adapter *adapter = q_vector->adapter;
struct net_device *netdev = adapter->netdev;
struct pci_dev *pdev = adapter->pdev;
+ struct napi_struct *napi = &q_vector->napi;
union ixgbe_adv_rx_desc *rx_desc, *next_rxd;
struct ixgbe_rx_buffer *rx_buffer_info, *next_buffer;
struct sk_buff *skb;
@@ -1211,32 +1242,68 @@ static bool ixgbe_clean_rx_irq(struct ixgbe_q_vector *q_vector,
len = le16_to_cpu(rx_desc->wb.upper.length);
}
+ if (is_no_buffer(rx_buffer_info))
+ break;
cleaned = true;
- skb = rx_buffer_info->skb;
- prefetch(skb->data);
- rx_buffer_info->skb = NULL;
- if (rx_buffer_info->dma) {
- if ((adapter->flags2 & IXGBE_FLAG2_RSC_ENABLED) &&
- (!(staterr & IXGBE_RXD_STAT_EOP)) &&
- (!(skb->prev))) {
- /*
- * When HWRSC is enabled, delay unmapping
- * of the first packet. It carries the
- * header information, HW may still
- * access the header after the writeback.
- * Only unmap it when EOP is reached
- */
- IXGBE_RSC_CB(skb)->delay_unmap = true;
- IXGBE_RSC_CB(skb)->dma = rx_buffer_info->dma;
- } else {
- dma_unmap_single(&pdev->dev,
- rx_buffer_info->dma,
- rx_ring->rx_buf_len,
- DMA_FROM_DEVICE);
+ if (!rx_buffer_info->mapped_as_page) {
+ skb = rx_buffer_info->skb;
+ prefetch(skb->data);
+ rx_buffer_info->skb = NULL;
+
+ if (rx_buffer_info->dma) {
+ if ((adapter->flags2 & IXGBE_FLAG2_RSC_ENABLED) &&
+ (!(staterr & IXGBE_RXD_STAT_EOP)) &&
+ (!(skb->prev))) {
+ /*
+ * When HWRSC is enabled, delay unmapping
+ * of the first packet. It carries the
+ * header information, HW may still
+ * access the header after the writeback.
+ * Only unmap it when EOP is reached
+ */
+ IXGBE_RSC_CB(skb)->delay_unmap = true;
+ IXGBE_RSC_CB(skb)->dma = rx_buffer_info->dma;
+ } else
+ dma_unmap_single(&pdev->dev,
+ rx_buffer_info->dma,
+ rx_ring->rx_buf_len,
+ DMA_FROM_DEVICE);
+ rx_buffer_info->dma = 0;
+ skb_put(skb, len);
+ }
+ } else {
+ skb = napi_get_frags(napi);
+ prefetch(rx_buffer_info->page_skb_offset);
+ rx_buffer_info->skb = NULL;
+ if (rx_buffer_info->dma) {
+ if ((adapter->flags2 & IXGBE_FLAG2_RSC_ENABLED) &&
+ (!(staterr & IXGBE_RXD_STAT_EOP)) &&
+ (!(skb->prev))) {
+ /*
+ * When HWRSC is enabled, delay unmapping
+ * of the first packet. It carries the
+ * header information, HW may still
+ * access the header after the writeback.
+ * Only unmap it when EOP is reached
+ */
+ IXGBE_RSC_CB(skb)->delay_unmap = true;
+ IXGBE_RSC_CB(skb)->dma = rx_buffer_info->dma;
+ } else
+ dma_unmap_page(&pdev->dev, rx_buffer_info->dma,
+ PAGE_SIZE / 2,
+ PCI_DMA_FROMDEVICE);
+ rx_buffer_info->dma = 0;
+ skb_fill_page_desc(skb,
+ skb_shinfo(skb)->nr_frags,
+ rx_buffer_info->page_skb,
+ rx_buffer_info->page_skb_offset,
+ len);
+ rx_buffer_info->page_skb = NULL;
+ skb->len += len;
+ skb->data_len += len;
+ skb->truesize += len;
}
- rx_buffer_info->dma = 0;
- skb_put(skb, len);
}
if (upper_len) {
@@ -1283,10 +1350,16 @@ static bool ixgbe_clean_rx_irq(struct ixgbe_q_vector *q_vector,
skb = ixgbe_transform_rsc_queue(skb, &(rx_ring->rsc_count));
if (adapter->flags2 & IXGBE_FLAG2_RSC_ENABLED) {
if (IXGBE_RSC_CB(skb)->delay_unmap) {
- dma_unmap_single(&pdev->dev,
- IXGBE_RSC_CB(skb)->dma,
- rx_ring->rx_buf_len,
- DMA_FROM_DEVICE);
+ if (!rx_buffer_info->mapped_as_page)
+ dma_unmap_single(&pdev->dev,
+ IXGBE_RSC_CB(skb)->dma,
+ rx_ring->rx_buf_len,
+ DMA_FROM_DEVICE);
+ else
+ dma_unmap_page(&pdev->dev,
+ IXGBE_RSC_CB(skb)->dma,
+ PAGE_SIZE / 2,
+ DMA_FROM_DEVICE);
IXGBE_RSC_CB(skb)->dma = 0;
IXGBE_RSC_CB(skb)->delay_unmap = false;
}
@@ -1304,6 +1377,11 @@ static bool ixgbe_clean_rx_irq(struct ixgbe_q_vector *q_vector,
rx_buffer_info->dma = next_buffer->dma;
next_buffer->skb = skb;
next_buffer->dma = 0;
+ if (rx_buffer_info->mapped_as_page) {
+ rx_buffer_info->page_skb =
+ next_buffer->page_skb;
+ next_buffer->page_skb = NULL;
+ }
} else {
skb->next = next_buffer->skb;
skb->next->prev = skb;
@@ -1323,7 +1401,8 @@ static bool ixgbe_clean_rx_irq(struct ixgbe_q_vector *q_vector,
total_rx_bytes += skb->len;
total_rx_packets++;
- skb->protocol = eth_type_trans(skb, adapter->netdev);
+ if (!rx_buffer_info->mapped_as_page)
+ skb->protocol = eth_type_trans(skb, adapter->netdev);
#ifdef IXGBE_FCOE
/* if ddp, not passing to ULD unless for FCP_RSP or error */
if (adapter->flags & IXGBE_FLAG_FCOE_ENABLED) {
@@ -1332,7 +1411,14 @@ static bool ixgbe_clean_rx_irq(struct ixgbe_q_vector *q_vector,
goto next_desc;
}
#endif /* IXGBE_FCOE */
- ixgbe_receive_skb(q_vector, skb, staterr, rx_ring, rx_desc);
+
+ if (!rx_buffer_info->mapped_as_page)
+ ixgbe_receive_skb(q_vector, skb, staterr,
+ rx_ring, rx_desc);
+ else {
+ skb_record_rx_queue(skb, rx_ring->queue_index);
+ napi_gro_frags(napi);
+ }
next_desc:
rx_desc->wb.upper.status_error = 0;
@@ -3622,9 +3708,16 @@ static void ixgbe_clean_rx_ring(struct ixgbe_adapter *adapter,
rx_buffer_info = &rx_ring->rx_buffer_info[i];
if (rx_buffer_info->dma) {
- dma_unmap_single(&pdev->dev, rx_buffer_info->dma,
- rx_ring->rx_buf_len,
- DMA_FROM_DEVICE);
+ if (!rx_buffer_info->mapped_as_page)
+ dma_unmap_single(&pdev->dev, rx_buffer_info->dma,
+ rx_ring->rx_buf_len,
+ PCI_DMA_FROMDEVICE);
+ else {
+ dma_unmap_page(&pdev->dev, rx_buffer_info->dma,
+ PAGE_SIZE / 2,
+ PCI_DMA_FROMDEVICE);
+ rx_buffer_info->page_skb = NULL;
+ }
rx_buffer_info->dma = 0;
}
if (rx_buffer_info->skb) {
@@ -3651,7 +3744,7 @@ static void ixgbe_clean_rx_ring(struct ixgbe_adapter *adapter,
PAGE_SIZE / 2, DMA_FROM_DEVICE);
rx_buffer_info->page_dma = 0;
}
- put_page(rx_buffer_info->page);
+ netdev_free_page(adapter->netdev, rx_buffer_info->page);
rx_buffer_info->page = NULL;
rx_buffer_info->page_offset = 0;
}
--
1.7.3
^ permalink raw reply related
* Re: Netlink limitations
From: Patrick McHardy @ 2010-11-09 9:27 UTC (permalink / raw)
To: Jan Engelhardt, David S. Miller, pablo, netdev
In-Reply-To: <20101108151635.GA20629@canuck.infradead.org>
Am 08.11.2010 16:16, schrieb Thomas Graf:
> On Sun, Nov 07, 2010 at 06:17:43PM +0100, Patrick McHardy wrote:
>> On 07.11.2010 17:44, Jan Engelhardt wrote:
>>> ...
>
>> That's somewhat similar to the nlattr32 idea, but a length of 0 makes
>> more sense since that's currently not used. In that case the length
>> would be read from a second length field which has 32 bits.
>
> I agree. This makes perfect sense. I was just thinking wheter we want
> to encode more information into the attribute header if we extend it
> anyways.
What kind of additional information are you thinking about?
^ permalink raw reply
* Re: Netlink limitations
From: Jan Engelhardt @ 2010-11-09 11:58 UTC (permalink / raw)
To: Thomas Graf; +Cc: Patrick McHardy, David S. Miller, pablo, netdev
In-Reply-To: <20101108151635.GA20629@canuck.infradead.org>
On Monday 2010-11-08 16:16, Thomas Graf wrote:
>
>Also, it is not required to pack everything in attributes. Your protocol
>may specify that the whole message payload consists of chained attributes.
Yeah but that does not work well with nla_parse and nfnetlink.c
unserializing the byte stream into a tb[] array.
Does it hurt to not use nfnetlink? The only issue I see is that
af_netlink.c's nl_table is an array, when it should preferably be a
hash or tree if we are going to add more subsystems.
^ permalink raw reply
* Re: Netlink limitations
From: Jan Engelhardt @ 2010-11-09 12:10 UTC (permalink / raw)
To: Patrick McHardy
Cc: David S. Miller, Holger Eitzenberger, Pablo Neira Ayuso, netdev
In-Reply-To: <4CD6DF37.6010800@trash.net>
On Sunday 2010-11-07 18:17, Patrick McHardy wrote:
>On 07.11.2010 17:44, Jan Engelhardt wrote:
>> we mentioned it only briefly at the Netfilter workshop a few weeks ago,
>> but as I am trying to figure out how to use Netlink in Xtables,
>> Netlink's limitations really start ruining my day.
>>
>> The well-known issue is that NL messages[sic] the kernel is supposed to
>> receive have a max size of 64K, due to nlmsghdr's use of uint16_t. This
>> is very problematic because attributes can easily amass more than 64K.
>> Think of a chain full of rules, represented by a top-level attribute
>> that nests attributes. The problem is bidirectional, a table
>> dump has the same problem.
>
>Messages are not limited to 64k, individual attributes are. Holger
>started working on a nlattr32, which uses 32 bit for the length
>value.
Does he have a format specification available?
^ permalink raw reply
* Re: Netlink limitations
From: Patrick McHardy @ 2010-11-09 12:24 UTC (permalink / raw)
To: Jan Engelhardt
Cc: David S. Miller, Holger Eitzenberger, Pablo Neira Ayuso, netdev
In-Reply-To: <alpine.LNX.2.01.1011091303250.21752@obet.zrqbmnf.qr>
Am 09.11.2010 13:10, schrieb Jan Engelhardt:
>
> On Sunday 2010-11-07 18:17, Patrick McHardy wrote:
>> On 07.11.2010 17:44, Jan Engelhardt wrote:
>>> we mentioned it only briefly at the Netfilter workshop a few weeks ago,
>>> but as I am trying to figure out how to use Netlink in Xtables,
>>> Netlink's limitations really start ruining my day.
>>>
>>> The well-known issue is that NL messages[sic] the kernel is supposed to
>>> receive have a max size of 64K, due to nlmsghdr's use of uint16_t. This
>>> is very problematic because attributes can easily amass more than 64K.
>>> Think of a chain full of rules, represented by a top-level attribute
>>> that nests attributes. The problem is bidirectional, a table
>>> dump has the same problem.
>>
>> Messages are not limited to 64k, individual attributes are. Holger
>> started working on a nlattr32, which uses 32 bit for the length
>> value.
>
> Does he have a format specification available?
As I said, the basic idea is to use a length value of zero to indicate
that the length should be read from a second length member. Basically:
struct nlattr32 {
__u16 nla_len;
__u16 nla_type;
__u32 nla_len2;
};
^ permalink raw reply
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox